890 files changed, 65655 insertions, 34543 deletions

diff --git a/net/6lowpan/Kconfig b/net/6lowpan/Kconfig
index e4a02ef55102..7fa0f382e7d1 100644
--- a/net/6lowpan/Kconfig
+++ b/net/6lowpan/Kconfig
@@ -1,6 +1,61 @@
-config 6LOWPAN
+menuconfig 6LOWPAN
 	tristate "6LoWPAN Support"
 	depends on IPV6
 	---help---
 	  This enables IPv6 over Low power Wireless Personal Area Network -
 	  "6LoWPAN" which is supported by IEEE 802.15.4 or Bluetooth stacks.
+
+menuconfig 6LOWPAN_NHC
+	tristate "Next Header Compression Support"
+	depends on 6LOWPAN
+	default y
+	---help---
+	  Support for next header compression.
+
+if 6LOWPAN_NHC
+
+config 6LOWPAN_NHC_DEST
+	tristate "Destination Options Header Support"
+	default y
+	---help---
+	  6LoWPAN IPv6 Destination Options Header compression according to
+	  RFC6282.
+
+config 6LOWPAN_NHC_FRAGMENT
+	tristate "Fragment Header Support"
+	default y
+	---help---
+	  6LoWPAN IPv6 Fragment Header compression according to RFC6282.
+
+config 6LOWPAN_NHC_HOP
+	tristate "Hop-by-Hop Options Header Support"
+	default y
+	---help---
+	  6LoWPAN IPv6 Hop-by-Hop Options Header compression according to
+	  RFC6282.
+
+config 6LOWPAN_NHC_IPV6
+	tristate "IPv6 Header Support"
+	default y
+	---help---
+	  6LoWPAN IPv6 Header compression according to RFC6282.
+
+config 6LOWPAN_NHC_MOBILITY
+	tristate "Mobility Header Support"
+	default y
+	---help---
+	  6LoWPAN IPv6 Mobility Header compression according to RFC6282.
+
+config 6LOWPAN_NHC_ROUTING
+	tristate "Routing Header Support"
+	default y
+	---help---
+	  6LoWPAN IPv6 Routing Header compression according to RFC6282.
+
+config 6LOWPAN_NHC_UDP
+	tristate "UDP Header Support"
+	default y
+	---help---
+	  6LoWPAN IPv6 UDP Header compression according to RFC6282.
+
+endif
diff --git a/net/6lowpan/Makefile b/net/6lowpan/Makefile
index 415886bb456a..eb8baa72adc8 100644
--- a/net/6lowpan/Makefile
+++ b/net/6lowpan/Makefile
@@ -1,3 +1,12 @@
-obj-$(CONFIG_6LOWPAN) := 6lowpan.o
+obj-$(CONFIG_6LOWPAN) += 6lowpan.o
 
-6lowpan-y := iphc.o
+6lowpan-y := iphc.o nhc.o
+
+#rfc6282 nhcs
+obj-$(CONFIG_6LOWPAN_NHC_DEST) += nhc_dest.o
+obj-$(CONFIG_6LOWPAN_NHC_FRAGMENT) += nhc_fragment.o
+obj-$(CONFIG_6LOWPAN_NHC_HOP) += nhc_hop.o
+obj-$(CONFIG_6LOWPAN_NHC_IPV6) += nhc_ipv6.o
+obj-$(CONFIG_6LOWPAN_NHC_MOBILITY) += nhc_mobility.o
+obj-$(CONFIG_6LOWPAN_NHC_ROUTING) += nhc_routing.o
+obj-$(CONFIG_6LOWPAN_NHC_UDP) += nhc_udp.o
diff --git a/net/6lowpan/iphc.c b/net/6lowpan/iphc.c
index 142eef55c9e2..94a375c04f21 100644
--- a/net/6lowpan/iphc.c
+++ b/net/6lowpan/iphc.c
@@ -15,9 +15,6 @@
  * 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:
@@ -57,6 +54,8 @@
 #include <net/ipv6.h>
 #include <net/af_ieee802154.h>
 
+#include "nhc.h"
+
 /* Uncompress address function for source and
  * destination address(non-multicast).
  *
@@ -171,37 +170,6 @@ static int uncompress_context_based_src_addr(struct sk_buff *skb,
 	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.
  */
@@ -258,84 +226,15 @@ static int lowpan_uncompress_multicast_daddr(struct sk_buff *skb,
 	return 0;
 }
 
-static int uncompress_udp_header(struct sk_buff *skb, struct udphdr *uh)
-{
-	bool fail;
-	u8 tmp = 0, val = 0;
-
-	fail = lowpan_fetch_skb(skb, &tmp, sizeof(tmp));
-
-	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,
-						 sizeof(uh->source));
-			fail |= lowpan_fetch_skb(skb, &uh->dest,
-						 sizeof(uh->dest));
-			break;
-		case LOWPAN_NHC_UDP_CS_P_01:
-			fail |= lowpan_fetch_skb(skb, &uh->source,
-						 sizeof(uh->source));
-			fail |= lowpan_fetch_skb(skb, &val, sizeof(val));
-			uh->dest = htons(val + LOWPAN_NHC_UDP_8BIT_PORT);
-			break;
-		case LOWPAN_NHC_UDP_CS_P_10:
-			fail |= lowpan_fetch_skb(skb, &val, sizeof(val));
-			uh->source = htons(val + LOWPAN_NHC_UDP_8BIT_PORT);
-			fail |= lowpan_fetch_skb(skb, &uh->dest,
-						 sizeof(uh->dest));
-			break;
-		case LOWPAN_NHC_UDP_CS_P_11:
-			fail |= lowpan_fetch_skb(skb, &val, sizeof(val));
-			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;
-		}
-
-		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,
-						 sizeof(uh->check));
-		}
-
-		/* UDP length 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)
+int
+lowpan_header_decompress(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)
 {
 	struct ipv6hdr hdr = {};
 	u8 tmp, num_context = 0;
@@ -348,7 +247,7 @@ int lowpan_process_data(struct sk_buff *skb, struct net_device *dev,
 	if (iphc1 & LOWPAN_IPHC_CID) {
 		pr_debug("CID flag is set, increase header with one\n");
 		if (lowpan_fetch_skb(skb, &num_context, sizeof(num_context)))
-			goto drop;
+			return -EINVAL;
 	}
 
 	hdr.version = 6;
@@ -360,7 +259,7 @@ int lowpan_process_data(struct sk_buff *skb, struct net_device *dev,
 	 */
 	case 0: /* 00b */
 		if (lowpan_fetch_skb(skb, &tmp, sizeof(tmp)))
-			goto drop;
+			return -EINVAL;
 
 		memcpy(&hdr.flow_lbl, &skb->data[0], 3);
 		skb_pull(skb, 3);
@@ -373,7 +272,7 @@ int lowpan_process_data(struct sk_buff *skb, struct net_device *dev,
 	 */
 	case 2: /* 10b */
 		if (lowpan_fetch_skb(skb, &tmp, sizeof(tmp)))
-			goto drop;
+			return -EINVAL;
 
 		hdr.priority = ((tmp >> 2) & 0x0f);
 		hdr.flow_lbl[0] = ((tmp << 6) & 0xC0) | ((tmp >> 2) & 0x30);
@@ -383,7 +282,7 @@ int lowpan_process_data(struct sk_buff *skb, struct net_device *dev,
 	 */
 	case 1: /* 01b */
 		if (lowpan_fetch_skb(skb, &tmp, sizeof(tmp)))
-			goto drop;
+			return -EINVAL;
 
 		hdr.flow_lbl[0] = (skb->data[0] & 0x0F) | ((tmp >> 2) & 0x30);
 		memcpy(&hdr.flow_lbl[1], &skb->data[0], 2);
@@ -400,7 +299,7 @@ int lowpan_process_data(struct sk_buff *skb, struct net_device *dev,
 	if ((iphc0 & LOWPAN_IPHC_NH_C) == 0) {
 		/* Next header is carried inline */
 		if (lowpan_fetch_skb(skb, &hdr.nexthdr, sizeof(hdr.nexthdr)))
-			goto drop;
+			return -EINVAL;
 
 		pr_debug("NH flag is set, next header carried inline: %02x\n",
 			 hdr.nexthdr);
@@ -412,7 +311,7 @@ int lowpan_process_data(struct sk_buff *skb, struct net_device *dev,
 	} else {
 		if (lowpan_fetch_skb(skb, &hdr.hop_limit,
 				     sizeof(hdr.hop_limit)))
-			goto drop;
+			return -EINVAL;
 	}
 
 	/* Extract SAM to the tmp variable */
@@ -431,7 +330,7 @@ int lowpan_process_data(struct sk_buff *skb, struct net_device *dev,
 
 	/* Check on error of previous branch */
 	if (err)
-		goto drop;
+		return -EINVAL;
 
 	/* Extract DAM to the tmp variable */
 	tmp = ((iphc1 & LOWPAN_IPHC_DAM_11) >> LOWPAN_IPHC_DAM_BIT) & 0x03;
@@ -446,7 +345,7 @@ int lowpan_process_data(struct sk_buff *skb, struct net_device *dev,
 								tmp);
 
 			if (err)
-				goto drop;
+				return -EINVAL;
 		}
 	} else {
 		err = uncompress_addr(skb, &hdr.daddr, tmp, daddr,
@@ -454,37 +353,18 @@ int lowpan_process_data(struct sk_buff *skb, struct net_device *dev,
 		pr_debug("dest: stateless compression mode %d dest %pI6c\n",
 			 tmp, &hdr.daddr);
 		if (err)
-			goto drop;
+			return -EINVAL;
 	}
 
-	/* UDP data uncompression */
+	/* Next header 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;
+		err = lowpan_nhc_do_uncompression(skb, dev, &hdr);
+		if (err < 0)
+			return err;
+	} else {
+		err = skb_cow(skb, sizeof(hdr));
+		if (unlikely(err))
+			return err;
 	}
 
 	hdr.payload_len = htons(skb->len);
@@ -497,15 +377,15 @@ int lowpan_process_data(struct sk_buff *skb, struct net_device *dev,
 		hdr.version, ntohs(hdr.payload_len), hdr.nexthdr,
 		hdr.hop_limit, &hdr.daddr);
 
-	raw_dump_table(__func__, "raw header dump", (u8 *)&hdr, sizeof(hdr));
+	skb_push(skb, sizeof(hdr));
+	skb_reset_network_header(skb);
+	skb_copy_to_linear_data(skb, &hdr, sizeof(hdr));
 
-	return skb_deliver(skb, &hdr, dev, deliver_skb);
+	raw_dump_table(__func__, "raw header dump", (u8 *)&hdr, sizeof(hdr));
 
-drop:
-	kfree_skb(skb);
-	return -EINVAL;
+	return 0;
 }
-EXPORT_SYMBOL_GPL(lowpan_process_data);
+EXPORT_SYMBOL_GPL(lowpan_header_decompress);
 
 static u8 lowpan_compress_addr_64(u8 **hc_ptr, u8 shift,
 				  const struct in6_addr *ipaddr,
@@ -533,63 +413,6 @@ static u8 lowpan_compress_addr_64(u8 **hc_ptr, u8 shift,
 	return rol8(val, shift);
 }
 
-static void compress_udp_header(u8 **hc_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(hc_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(hc_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(hc_ptr, &tmp, sizeof(tmp));
-		/* source port */
-		lowpan_push_hc_data(hc_ptr, &uh->source, sizeof(uh->source));
-		/* destination port */
-		tmp = ntohs(uh->dest) - LOWPAN_NHC_UDP_8BIT_PORT;
-		lowpan_push_hc_data(hc_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(hc_ptr, &tmp, sizeof(tmp));
-		/* source port */
-		tmp = ntohs(uh->source) - LOWPAN_NHC_UDP_8BIT_PORT;
-		lowpan_push_hc_data(hc_ptr, &tmp, sizeof(tmp));
-		/* destination port */
-		lowpan_push_hc_data(hc_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(hc_ptr, &tmp, sizeof(tmp));
-		/* source port */
-		lowpan_push_hc_data(hc_ptr, &uh->source, sizeof(uh->source));
-		/* destination port */
-		lowpan_push_hc_data(hc_ptr, &uh->dest, sizeof(uh->dest));
-	}
-
-	/* checksum is always inline */
-	lowpan_push_hc_data(hc_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)
@@ -597,7 +420,7 @@ int lowpan_header_compress(struct sk_buff *skb, struct net_device *dev,
 	u8 tmp, iphc0, iphc1, *hc_ptr;
 	struct ipv6hdr *hdr;
 	u8 head[100] = {};
-	int addr_type;
+	int ret, addr_type;
 
 	if (type != ETH_P_IPV6)
 		return -EINVAL;
@@ -674,13 +497,12 @@ int lowpan_header_compress(struct sk_buff *skb, struct net_device *dev,
 
 	/* 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)
-		lowpan_push_hc_data(&hc_ptr, &hdr->nexthdr,
-				    sizeof(hdr->nexthdr));
+	/* Check if we provide the nhc format for nexthdr and compression
+	 * functionality. If not nexthdr is handled inline and not compressed.
+	 */
+	ret = lowpan_nhc_check_compression(skb, hdr, &hc_ptr, &iphc0);
+	if (ret < 0)
+		return ret;
 
 	/* Hop limit
 	 * if 1:   compress, encoding is 01
@@ -766,9 +588,12 @@ int lowpan_header_compress(struct sk_buff *skb, struct net_device *dev,
 		}
 	}
 
-	/* UDP header compression */
-	if (hdr->nexthdr == UIP_PROTO_UDP)
-		compress_udp_header(&hc_ptr, skb);
+	/* next header compression */
+	if (iphc0 & LOWPAN_IPHC_NH_C) {
+		ret = lowpan_nhc_do_compression(skb, hdr, &hc_ptr);
+		if (ret < 0)
+			return ret;
+	}
 
 	head[0] = iphc0;
 	head[1] = iphc1;
@@ -786,4 +611,18 @@ int lowpan_header_compress(struct sk_buff *skb, struct net_device *dev,
 }
 EXPORT_SYMBOL_GPL(lowpan_header_compress);
 
+static int __init lowpan_module_init(void)
+{
+	request_module_nowait("nhc_dest");
+	request_module_nowait("nhc_fragment");
+	request_module_nowait("nhc_hop");
+	request_module_nowait("nhc_ipv6");
+	request_module_nowait("nhc_mobility");
+	request_module_nowait("nhc_routing");
+	request_module_nowait("nhc_udp");
+
+	return 0;
+}
+module_init(lowpan_module_init);
+
 MODULE_LICENSE("GPL");
diff --git a/net/6lowpan/nhc.c b/net/6lowpan/nhc.c
new file mode 100644
index 000000000000..fd20fc51a7c4
--- /dev/null
+++ b/net/6lowpan/nhc.c
@@ -0,0 +1,241 @@
+/*
+ *	6LoWPAN next header compression
+ *
+ *
+ *	Authors:
+ *	Alexander Aring		<aar@pengutronix.de>
+ *
+ *	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/netdevice.h>
+
+#include <net/ipv6.h>
+
+#include "nhc.h"
+
+static struct rb_root rb_root = RB_ROOT;
+static struct lowpan_nhc *lowpan_nexthdr_nhcs[NEXTHDR_MAX];
+static DEFINE_SPINLOCK(lowpan_nhc_lock);
+
+static int lowpan_nhc_insert(struct lowpan_nhc *nhc)
+{
+	struct rb_node **new = &rb_root.rb_node, *parent = NULL;
+
+	/* Figure out where to put new node */
+	while (*new) {
+		struct lowpan_nhc *this = container_of(*new, struct lowpan_nhc,
+						       node);
+		int result, len_dif, len;
+
+		len_dif = nhc->idlen - this->idlen;
+
+		if (nhc->idlen < this->idlen)
+			len = nhc->idlen;
+		else
+			len = this->idlen;
+
+		result = memcmp(nhc->id, this->id, len);
+		if (!result)
+			result = len_dif;
+
+		parent = *new;
+		if (result < 0)
+			new = &((*new)->rb_left);
+		else if (result > 0)
+			new = &((*new)->rb_right);
+		else
+			return -EEXIST;
+	}
+
+	/* Add new node and rebalance tree. */
+	rb_link_node(&nhc->node, parent, new);
+	rb_insert_color(&nhc->node, &rb_root);
+
+	return 0;
+}
+
+static void lowpan_nhc_remove(struct lowpan_nhc *nhc)
+{
+	rb_erase(&nhc->node, &rb_root);
+}
+
+static struct lowpan_nhc *lowpan_nhc_by_nhcid(const struct sk_buff *skb)
+{
+	struct rb_node *node = rb_root.rb_node;
+	const u8 *nhcid_skb_ptr = skb->data;
+
+	while (node) {
+		struct lowpan_nhc *nhc = container_of(node, struct lowpan_nhc,
+						      node);
+		u8 nhcid_skb_ptr_masked[LOWPAN_NHC_MAX_ID_LEN];
+		int result, i;
+
+		if (nhcid_skb_ptr + nhc->idlen > skb->data + skb->len)
+			return NULL;
+
+		/* copy and mask afterwards the nhid value from skb */
+		memcpy(nhcid_skb_ptr_masked, nhcid_skb_ptr, nhc->idlen);
+		for (i = 0; i < nhc->idlen; i++)
+			nhcid_skb_ptr_masked[i] &= nhc->idmask[i];
+
+		result = memcmp(nhcid_skb_ptr_masked, nhc->id, nhc->idlen);
+		if (result < 0)
+			node = node->rb_left;
+		else if (result > 0)
+			node = node->rb_right;
+		else
+			return nhc;
+	}
+
+	return NULL;
+}
+
+int lowpan_nhc_check_compression(struct sk_buff *skb,
+				 const struct ipv6hdr *hdr, u8 **hc_ptr,
+				 u8 *iphc0)
+{
+	struct lowpan_nhc *nhc;
+
+	spin_lock_bh(&lowpan_nhc_lock);
+
+	nhc = lowpan_nexthdr_nhcs[hdr->nexthdr];
+	if (nhc && nhc->compress)
+		*iphc0 |= LOWPAN_IPHC_NH_C;
+	else
+		lowpan_push_hc_data(hc_ptr, &hdr->nexthdr,
+				    sizeof(hdr->nexthdr));
+
+	spin_unlock_bh(&lowpan_nhc_lock);
+
+	return 0;
+}
+
+int lowpan_nhc_do_compression(struct sk_buff *skb, const struct ipv6hdr *hdr,
+			      u8 **hc_ptr)
+{
+	int ret;
+	struct lowpan_nhc *nhc;
+
+	spin_lock_bh(&lowpan_nhc_lock);
+
+	nhc = lowpan_nexthdr_nhcs[hdr->nexthdr];
+	/* check if the nhc module was removed in unlocked part.
+	 * TODO: this is a workaround we should prevent unloading
+	 * of nhc modules while unlocked part, this will always drop
+	 * the lowpan packet but it's very unlikely.
+	 *
+	 * Solution isn't easy because we need to decide at
+	 * lowpan_nhc_check_compression if we do a compression or not.
+	 * Because the inline data which is added to skb, we can't move this
+	 * handling.
+	 */
+	if (unlikely(!nhc || !nhc->compress)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/* In the case of RAW sockets the transport header is not set by
+	 * the ip6 stack so we must set it ourselves
+	 */
+	if (skb->transport_header == skb->network_header)
+		skb_set_transport_header(skb, sizeof(struct ipv6hdr));
+
+	ret = nhc->compress(skb, hc_ptr);
+	if (ret < 0)
+		goto out;
+
+	/* skip the transport header */
+	skb_pull(skb, nhc->nexthdrlen);
+
+out:
+	spin_unlock_bh(&lowpan_nhc_lock);
+
+	return ret;
+}
+
+int lowpan_nhc_do_uncompression(struct sk_buff *skb, struct net_device *dev,
+				struct ipv6hdr *hdr)
+{
+	struct lowpan_nhc *nhc;
+	int ret;
+
+	spin_lock_bh(&lowpan_nhc_lock);
+
+	nhc = lowpan_nhc_by_nhcid(skb);
+	if (nhc) {
+		if (nhc->uncompress) {
+			ret = nhc->uncompress(skb, sizeof(struct ipv6hdr) +
+					      nhc->nexthdrlen);
+			if (ret < 0) {
+				spin_unlock_bh(&lowpan_nhc_lock);
+				return ret;
+			}
+		} else {
+			spin_unlock_bh(&lowpan_nhc_lock);
+			netdev_warn(dev, "received nhc id for %s which is not implemented.\n",
+				    nhc->name);
+			return -ENOTSUPP;
+		}
+	} else {
+		spin_unlock_bh(&lowpan_nhc_lock);
+		netdev_warn(dev, "received unknown nhc id which was not found.\n");
+		return -ENOENT;
+	}
+
+	hdr->nexthdr = nhc->nexthdr;
+	skb_reset_transport_header(skb);
+	raw_dump_table(__func__, "raw transport header dump",
+		       skb_transport_header(skb), nhc->nexthdrlen);
+
+	spin_unlock_bh(&lowpan_nhc_lock);
+
+	return 0;
+}
+
+int lowpan_nhc_add(struct lowpan_nhc *nhc)
+{
+	int ret;
+
+	if (!nhc->idlen || !nhc->idsetup)
+		return -EINVAL;
+
+	WARN_ONCE(nhc->idlen > LOWPAN_NHC_MAX_ID_LEN,
+		  "LOWPAN_NHC_MAX_ID_LEN should be updated to %zd.\n",
+		  nhc->idlen);
+
+	nhc->idsetup(nhc);
+
+	spin_lock_bh(&lowpan_nhc_lock);
+
+	if (lowpan_nexthdr_nhcs[nhc->nexthdr]) {
+		ret = -EEXIST;
+		goto out;
+	}
+
+	ret = lowpan_nhc_insert(nhc);
+	if (ret < 0)
+		goto out;
+
+	lowpan_nexthdr_nhcs[nhc->nexthdr] = nhc;
+out:
+	spin_unlock_bh(&lowpan_nhc_lock);
+	return ret;
+}
+EXPORT_SYMBOL(lowpan_nhc_add);
+
+void lowpan_nhc_del(struct lowpan_nhc *nhc)
+{
+	spin_lock_bh(&lowpan_nhc_lock);
+
+	lowpan_nhc_remove(nhc);
+	lowpan_nexthdr_nhcs[nhc->nexthdr] = NULL;
+
+	spin_unlock_bh(&lowpan_nhc_lock);
+
+	synchronize_net();
+}
+EXPORT_SYMBOL(lowpan_nhc_del);
diff --git a/net/6lowpan/nhc.h b/net/6lowpan/nhc.h
new file mode 100644
index 000000000000..ed44938eb5de
--- /dev/null
+++ b/net/6lowpan/nhc.h
@@ -0,0 +1,146 @@
+#ifndef __6LOWPAN_NHC_H
+#define __6LOWPAN_NHC_H
+
+#include <linux/skbuff.h>
+#include <linux/rbtree.h>
+#include <linux/module.h>
+
+#include <net/6lowpan.h>
+#include <net/ipv6.h>
+
+#define LOWPAN_NHC_MAX_ID_LEN	1
+
+/**
+ * LOWPAN_NHC - helper macro to generate nh id fields and lowpan_nhc struct
+ *
+ * @__nhc: variable name of the lowpan_nhc struct.
+ * @_name: const char * of common header compression name.
+ * @_nexthdr: ipv6 nexthdr field for the header compression.
+ * @_nexthdrlen: ipv6 nexthdr len for the reserved space.
+ * @_idsetup: callback to setup id and mask values.
+ * @_idlen: len for the next header id and mask, should be always the same.
+ * @_uncompress: callback for uncompression call.
+ * @_compress: callback for compression call.
+ */
+#define LOWPAN_NHC(__nhc, _name, _nexthdr,	\
+		   _hdrlen, _idsetup, _idlen,	\
+		   _uncompress, _compress)	\
+static u8 __nhc##_val[_idlen];			\
+static u8 __nhc##_mask[_idlen];			\
+static struct lowpan_nhc __nhc = {		\
+	.name		= _name,		\
+	.nexthdr	= _nexthdr,		\
+	.nexthdrlen	= _hdrlen,		\
+	.id		= __nhc##_val,		\
+	.idmask		= __nhc##_mask,		\
+	.idlen		= _idlen,		\
+	.idsetup	= _idsetup,		\
+	.uncompress	= _uncompress,		\
+	.compress	= _compress,		\
+}
+
+#define module_lowpan_nhc(__nhc)		\
+static int __init __nhc##_init(void)		\
+{						\
+	return lowpan_nhc_add(&(__nhc));	\
+}						\
+module_init(__nhc##_init);			\
+static void __exit __nhc##_exit(void)		\
+{						\
+	lowpan_nhc_del(&(__nhc));		\
+}						\
+module_exit(__nhc##_exit);
+
+/**
+ * struct lowpan_nhc - hold 6lowpan next hdr compression ifnformation
+ *
+ * @node: holder for the rbtree.
+ * @name: name of the specific next header compression
+ * @nexthdr: next header value of the protocol which should be compressed.
+ * @nexthdrlen: ipv6 nexthdr len for the reserved space.
+ * @id: array for nhc id. Note this need to be in network byteorder.
+ * @mask: array for nhc id mask. Note this need to be in network byteorder.
+ * @len: the length of the next header id and mask.
+ * @setup: callback to setup fill the next header id value and mask.
+ * @compress: callback to do the header compression.
+ * @uncompress: callback to do the header uncompression.
+ */
+struct lowpan_nhc {
+	struct rb_node	node;
+	const char	*name;
+	const u8	nexthdr;
+	const size_t	nexthdrlen;
+	u8		*id;
+	u8		*idmask;
+	const size_t	idlen;
+
+	void		(*idsetup)(struct lowpan_nhc *nhc);
+	int		(*uncompress)(struct sk_buff *skb, size_t needed);
+	int		(*compress)(struct sk_buff *skb, u8 **hc_ptr);
+};
+
+/**
+ * lowpan_nhc_by_nexthdr - return the 6lowpan nhc by ipv6 nexthdr.
+ *
+ * @nexthdr: ipv6 nexthdr value.
+ */
+struct lowpan_nhc *lowpan_nhc_by_nexthdr(u8 nexthdr);
+
+/**
+ * lowpan_nhc_check_compression - checks if we support compression format. If
+ *	we support the nhc by nexthdr field, the 6LoWPAN iphc NHC bit will be
+ *	set. If we don't support nexthdr will be added as inline data to the
+ *	6LoWPAN header.
+ *
+ * @skb: skb of 6LoWPAN header to read nhc and replace header.
+ * @hdr: ipv6hdr to check the nexthdr value
+ * @hc_ptr: pointer for 6LoWPAN header which should increment at the end of
+ *	    replaced header.
+ * @iphc0: iphc0 pointer to set the 6LoWPAN NHC bit
+ */
+int lowpan_nhc_check_compression(struct sk_buff *skb,
+				 const struct ipv6hdr *hdr, u8 **hc_ptr,
+				 u8 *iphc0);
+
+/**
+ * lowpan_nhc_do_compression - calling compress callback for nhc
+ *
+ * @skb: skb of 6LoWPAN header to read nhc and replace header.
+ * @hdr: ipv6hdr to set the nexthdr value
+ * @hc_ptr: pointer for 6LoWPAN header which should increment at the end of
+ *	    replaced header.
+ */
+int lowpan_nhc_do_compression(struct sk_buff *skb, const struct ipv6hdr *hdr,
+			      u8 **hc_ptr);
+
+/**
+ * lowpan_nhc_do_uncompression - calling uncompress callback for nhc
+ *
+ * @nhc: 6LoWPAN nhc context, get by lowpan_nhc_by_ functions.
+ * @skb: skb of 6LoWPAN header, skb->data should be pointed to nhc id value.
+ * @dev: netdevice for print logging information.
+ * @hdr: ipv6hdr for setting nexthdr value.
+ */
+int lowpan_nhc_do_uncompression(struct sk_buff *skb, struct net_device *dev,
+				struct ipv6hdr *hdr);
+
+/**
+ * lowpan_nhc_add - register a next header compression to framework
+ *
+ * @nhc: nhc which should be add.
+ */
+int lowpan_nhc_add(struct lowpan_nhc *nhc);
+
+/**
+ * lowpan_nhc_del - delete a next header compression from framework
+ *
+ * @nhc: nhc which should be delete.
+ */
+void lowpan_nhc_del(struct lowpan_nhc *nhc);
+
+/**
+ * lowpan_nhc_init - adding all default nhcs
+ */
+void lowpan_nhc_init(void);
+
+#endif /* __6LOWPAN_NHC_H */
diff --git a/net/6lowpan/nhc_dest.c b/net/6lowpan/nhc_dest.c
new file mode 100644
index 000000000000..0b292c9646eb
--- /dev/null
+++ b/net/6lowpan/nhc_dest.c
@@ -0,0 +1,28 @@
+/*
+ *	6LoWPAN IPv6 Destination Options Header compression according to
+ *	RFC6282
+ *
+ *	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 "nhc.h"
+
+#define LOWPAN_NHC_DEST_IDLEN	1
+#define LOWPAN_NHC_DEST_ID_0	0xe6
+#define LOWPAN_NHC_DEST_MASK_0	0xfe
+
+static void dest_nhid_setup(struct lowpan_nhc *nhc)
+{
+	nhc->id[0] = LOWPAN_NHC_DEST_ID_0;
+	nhc->idmask[0] = LOWPAN_NHC_DEST_MASK_0;
+}
+
+LOWPAN_NHC(nhc_dest, "RFC6282 Destination Options", NEXTHDR_DEST, 0,
+	   dest_nhid_setup, LOWPAN_NHC_DEST_IDLEN, NULL, NULL);
+
+module_lowpan_nhc(nhc_dest);
+MODULE_DESCRIPTION("6LoWPAN next header RFC6282 Destination Options compression");
+MODULE_LICENSE("GPL");
diff --git a/net/6lowpan/nhc_fragment.c b/net/6lowpan/nhc_fragment.c
new file mode 100644
index 000000000000..473dbc58ef84
--- /dev/null
+++ b/net/6lowpan/nhc_fragment.c
@@ -0,0 +1,27 @@
+/*
+ *	6LoWPAN IPv6 Fragment Header compression according to RFC6282
+ *
+ *	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 "nhc.h"
+
+#define LOWPAN_NHC_FRAGMENT_IDLEN	1
+#define LOWPAN_NHC_FRAGMENT_ID_0	0xe4
+#define LOWPAN_NHC_FRAGMENT_MASK_0	0xfe
+
+static void fragment_nhid_setup(struct lowpan_nhc *nhc)
+{
+	nhc->id[0] = LOWPAN_NHC_FRAGMENT_ID_0;
+	nhc->idmask[0] = LOWPAN_NHC_FRAGMENT_MASK_0;
+}
+
+LOWPAN_NHC(nhc_fragment, "RFC6282 Fragment", NEXTHDR_FRAGMENT, 0,
+	   fragment_nhid_setup, LOWPAN_NHC_FRAGMENT_IDLEN, NULL, NULL);
+
+module_lowpan_nhc(nhc_fragment);
+MODULE_DESCRIPTION("6LoWPAN next header RFC6282 Fragment compression");
+MODULE_LICENSE("GPL");
diff --git a/net/6lowpan/nhc_hop.c b/net/6lowpan/nhc_hop.c
new file mode 100644
index 000000000000..1eb66be16f19
--- /dev/null
+++ b/net/6lowpan/nhc_hop.c
@@ -0,0 +1,27 @@
+/*
+ *	6LoWPAN IPv6 Hop-by-Hop Options Header compression according to RFC6282
+ *
+ *	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 "nhc.h"
+
+#define LOWPAN_NHC_HOP_IDLEN	1
+#define LOWPAN_NHC_HOP_ID_0	0xe0
+#define LOWPAN_NHC_HOP_MASK_0	0xfe
+
+static void hop_nhid_setup(struct lowpan_nhc *nhc)
+{
+	nhc->id[0] = LOWPAN_NHC_HOP_ID_0;
+	nhc->idmask[0] = LOWPAN_NHC_HOP_MASK_0;
+}
+
+LOWPAN_NHC(nhc_hop, "RFC6282 Hop-by-Hop Options", NEXTHDR_HOP, 0,
+	   hop_nhid_setup, LOWPAN_NHC_HOP_IDLEN, NULL, NULL);
+
+module_lowpan_nhc(nhc_hop);
+MODULE_DESCRIPTION("6LoWPAN next header RFC6282 Hop-by-Hop Options compression");
+MODULE_LICENSE("GPL");
diff --git a/net/6lowpan/nhc_ipv6.c b/net/6lowpan/nhc_ipv6.c
new file mode 100644
index 000000000000..2313d1600af3
--- /dev/null
+++ b/net/6lowpan/nhc_ipv6.c
@@ -0,0 +1,27 @@
+/*
+ *	6LoWPAN IPv6 Header compression according to RFC6282
+ *
+ *	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 "nhc.h"
+
+#define LOWPAN_NHC_IPV6_IDLEN	1
+#define LOWPAN_NHC_IPV6_ID_0	0xee
+#define LOWPAN_NHC_IPV6_MASK_0	0xfe
+
+static void ipv6_nhid_setup(struct lowpan_nhc *nhc)
+{
+	nhc->id[0] = LOWPAN_NHC_IPV6_ID_0;
+	nhc->idmask[0] = LOWPAN_NHC_IPV6_MASK_0;
+}
+
+LOWPAN_NHC(nhc_ipv6, "RFC6282 IPv6", NEXTHDR_IPV6, 0, ipv6_nhid_setup,
+	   LOWPAN_NHC_IPV6_IDLEN, NULL, NULL);
+
+module_lowpan_nhc(nhc_ipv6);
+MODULE_DESCRIPTION("6LoWPAN next header RFC6282 IPv6 compression");
+MODULE_LICENSE("GPL");
diff --git a/net/6lowpan/nhc_mobility.c b/net/6lowpan/nhc_mobility.c
new file mode 100644
index 000000000000..60d3f3886c98
--- /dev/null
+++ b/net/6lowpan/nhc_mobility.c
@@ -0,0 +1,27 @@
+/*
+ *	6LoWPAN IPv6 Mobility Header compression according to RFC6282
+ *
+ *	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 "nhc.h"
+
+#define LOWPAN_NHC_MOBILITY_IDLEN	1
+#define LOWPAN_NHC_MOBILITY_ID_0	0xe8
+#define LOWPAN_NHC_MOBILITY_MASK_0	0xfe
+
+static void mobility_nhid_setup(struct lowpan_nhc *nhc)
+{
+	nhc->id[0] = LOWPAN_NHC_MOBILITY_ID_0;
+	nhc->idmask[0] = LOWPAN_NHC_MOBILITY_MASK_0;
+}
+
+LOWPAN_NHC(nhc_mobility, "RFC6282 Mobility", NEXTHDR_MOBILITY, 0,
+	   mobility_nhid_setup, LOWPAN_NHC_MOBILITY_IDLEN, NULL, NULL);
+
+module_lowpan_nhc(nhc_mobility);
+MODULE_DESCRIPTION("6LoWPAN next header RFC6282 Mobility compression");
+MODULE_LICENSE("GPL");
diff --git a/net/6lowpan/nhc_routing.c b/net/6lowpan/nhc_routing.c
new file mode 100644
index 000000000000..c393280f11c4
--- /dev/null
+++ b/net/6lowpan/nhc_routing.c
@@ -0,0 +1,27 @@
+/*
+ *	6LoWPAN IPv6 Routing Header compression according to RFC6282
+ *
+ *	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 "nhc.h"
+
+#define LOWPAN_NHC_ROUTING_IDLEN	1
+#define LOWPAN_NHC_ROUTING_ID_0		0xe2
+#define LOWPAN_NHC_ROUTING_MASK_0	0xfe
+
+static void routing_nhid_setup(struct lowpan_nhc *nhc)
+{
+	nhc->id[0] = LOWPAN_NHC_ROUTING_ID_0;
+	nhc->idmask[0] = LOWPAN_NHC_ROUTING_MASK_0;
+}
+
+LOWPAN_NHC(nhc_routing, "RFC6282 Routing", NEXTHDR_ROUTING, 0,
+	   routing_nhid_setup, LOWPAN_NHC_ROUTING_IDLEN, NULL, NULL);
+
+module_lowpan_nhc(nhc_routing);
+MODULE_DESCRIPTION("6LoWPAN next header RFC6282 Routing compression");
+MODULE_LICENSE("GPL");
diff --git a/net/6lowpan/nhc_udp.c b/net/6lowpan/nhc_udp.c
new file mode 100644
index 000000000000..c6bcaeb428ae
--- /dev/null
+++ b/net/6lowpan/nhc_udp.c
@@ -0,0 +1,157 @@
+/*
+ *	6LoWPAN IPv6 UDP compression according to RFC6282
+ *
+ *
+ *	Authors:
+ *	Alexander Aring	<aar@pengutronix.de>
+ *
+ *	Orignal written by:
+ *	Alexander Smirnov <alex.bluesman.smirnov@gmail.com>
+ *	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
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ */
+
+#include "nhc.h"
+
+#define LOWPAN_NHC_UDP_IDLEN	1
+
+static int udp_uncompress(struct sk_buff *skb, size_t needed)
+{
+	u8 tmp = 0, val = 0;
+	struct udphdr uh;
+	bool fail;
+	int err;
+
+	fail = lowpan_fetch_skb(skb, &tmp, sizeof(tmp));
+
+	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, sizeof(uh.source));
+		fail |= lowpan_fetch_skb(skb, &uh.dest, sizeof(uh.dest));
+		break;
+	case LOWPAN_NHC_UDP_CS_P_01:
+		fail |= lowpan_fetch_skb(skb, &uh.source, sizeof(uh.source));
+		fail |= lowpan_fetch_skb(skb, &val, sizeof(val));
+		uh.dest = htons(val + LOWPAN_NHC_UDP_8BIT_PORT);
+		break;
+	case LOWPAN_NHC_UDP_CS_P_10:
+		fail |= lowpan_fetch_skb(skb, &val, sizeof(val));
+		uh.source = htons(val + LOWPAN_NHC_UDP_8BIT_PORT);
+		fail |= lowpan_fetch_skb(skb, &uh.dest, sizeof(uh.dest));
+		break;
+	case LOWPAN_NHC_UDP_CS_P_11:
+		fail |= lowpan_fetch_skb(skb, &val, sizeof(val));
+		uh.source = htons(LOWPAN_NHC_UDP_4BIT_PORT + (val >> 4));
+		uh.dest = htons(LOWPAN_NHC_UDP_4BIT_PORT + (val & 0x0f));
+		break;
+	default:
+		BUG();
+	}
+
+	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");
+		fail = true;
+	} else {
+		fail |= lowpan_fetch_skb(skb, &uh.check, sizeof(uh.check));
+	}
+
+	if (fail)
+		return -EINVAL;
+
+	/* UDP length 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));
+
+	/* replace the compressed UDP head by the uncompressed UDP
+	 * header
+	 */
+	err = skb_cow(skb, needed);
+	if (unlikely(err))
+		return err;
+
+	skb_push(skb, sizeof(struct udphdr));
+	skb_copy_to_linear_data(skb, &uh, sizeof(struct udphdr));
+
+	return 0;
+}
+
+static int udp_compress(struct sk_buff *skb, u8 **hc_ptr)
+{
+	const 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(hc_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(hc_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(hc_ptr, &tmp, sizeof(tmp));
+		/* source port */
+		lowpan_push_hc_data(hc_ptr, &uh->source, sizeof(uh->source));
+		/* destination port */
+		tmp = ntohs(uh->dest) - LOWPAN_NHC_UDP_8BIT_PORT;
+		lowpan_push_hc_data(hc_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(hc_ptr, &tmp, sizeof(tmp));
+		/* source port */
+		tmp = ntohs(uh->source) - LOWPAN_NHC_UDP_8BIT_PORT;
+		lowpan_push_hc_data(hc_ptr, &tmp, sizeof(tmp));
+		/* destination port */
+		lowpan_push_hc_data(hc_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(hc_ptr, &tmp, sizeof(tmp));
+		/* source port */
+		lowpan_push_hc_data(hc_ptr, &uh->source, sizeof(uh->source));
+		/* destination port */
+		lowpan_push_hc_data(hc_ptr, &uh->dest, sizeof(uh->dest));
+	}
+
+	/* checksum is always inline */
+	lowpan_push_hc_data(hc_ptr, &uh->check, sizeof(uh->check));
+
+	return 0;
+}
+
+static void udp_nhid_setup(struct lowpan_nhc *nhc)
+{
+	nhc->id[0] = LOWPAN_NHC_UDP_ID;
+	nhc->idmask[0] = LOWPAN_NHC_UDP_MASK;
+}
+
+LOWPAN_NHC(nhc_udp, "RFC6282 UDP", NEXTHDR_UDP, sizeof(struct udphdr),
+	   udp_nhid_setup, LOWPAN_NHC_UDP_IDLEN, udp_uncompress, udp_compress);
+
+module_lowpan_nhc(nhc_udp);
+MODULE_DESCRIPTION("6LoWPAN next header RFC6282 UDP compression");
+MODULE_LICENSE("GPL");
diff --git a/net/802/fc.c b/net/802/fc.c
index 7c174b6750cd..7b9219022418 100644
--- a/net/802/fc.c
+++ b/net/802/fc.c
@@ -75,29 +75,8 @@ static int fc_header(struct sk_buff *skb, struct net_device *dev,
 	return -hdr_len;
 }
 
-/*
- *	A neighbour discovery of some species (eg arp) has completed. We
- *	can now send the packet.
- */
-
-static int fc_rebuild_header(struct sk_buff *skb)
-{
-#ifdef CONFIG_INET
-	struct fch_hdr *fch=(struct fch_hdr *)skb->data;
-	struct fcllc *fcllc=(struct fcllc *)(skb->data+sizeof(struct fch_hdr));
-	if(fcllc->ethertype != htons(ETH_P_IP)) {
-		printk("fc_rebuild_header: Don't know how to resolve type %04X addresses ?\n", ntohs(fcllc->ethertype));
-		return 0;
-	}
-	return arp_find(fch->daddr, skb);
-#else
-	return 0;
-#endif
-}
-
 static const struct header_ops fc_header_ops = {
 	.create	 = fc_header,
-	.rebuild = fc_rebuild_header,
 };
 
 static void fc_setup(struct net_device *dev)
diff --git a/net/802/fddi.c b/net/802/fddi.c
index 59e7346f1193..7d3a0af954e8 100644
--- a/net/802/fddi.c
+++ b/net/802/fddi.c
@@ -87,31 +87,6 @@ static int fddi_header(struct sk_buff *skb, struct net_device *dev,
 	return -hl;
 }
 
-
-/*
- * Rebuild the FDDI MAC header. This is called after an ARP
- * (or in future other address resolution) has completed on
- * this sk_buff.  We now let ARP fill in the other fields.
- */
-
-static int fddi_rebuild_header(struct sk_buff	*skb)
-{
-	struct fddihdr *fddi = (struct fddihdr *)skb->data;
-
-#ifdef CONFIG_INET
-	if (fddi->hdr.llc_snap.ethertype == htons(ETH_P_IP))
-		/* Try to get ARP to resolve the header and fill destination address */
-		return arp_find(fddi->daddr, skb);
-	else
-#endif
-	{
-		printk("%s: Don't know how to resolve type %04X addresses.\n",
-		       skb->dev->name, ntohs(fddi->hdr.llc_snap.ethertype));
-		return 0;
-	}
-}
-
-
 /*
  * Determine the packet's protocol ID and fill in skb fields.
  * This routine is called before an incoming packet is passed
@@ -177,7 +152,6 @@ EXPORT_SYMBOL(fddi_change_mtu);
 
 static const struct header_ops fddi_header_ops = {
 	.create		= fddi_header,
-	.rebuild	= fddi_rebuild_header,
 };
 
 
diff --git a/net/802/hippi.c b/net/802/hippi.c
index 2e03f8259dd5..ade1a52cdcff 100644
--- a/net/802/hippi.c
+++ b/net/802/hippi.c
@@ -91,33 +91,6 @@ static int hippi_header(struct sk_buff *skb, struct net_device *dev,
 
 
 /*
- * Rebuild the HIPPI MAC header. This is called after an ARP has
- * completed on this sk_buff. We now let ARP fill in the other fields.
- */
-
-static int hippi_rebuild_header(struct sk_buff *skb)
-{
-	struct hippi_hdr *hip = (struct hippi_hdr *)skb->data;
-
-	/*
-	 * Only IP is currently supported
-	 */
-
-	if(hip->snap.ethertype != htons(ETH_P_IP))
-	{
-		printk(KERN_DEBUG "%s: unable to resolve type %X addresses.\n",skb->dev->name,ntohs(hip->snap.ethertype));
-		return 0;
-	}
-
-	/*
-	 * We don't support dynamic ARP on HIPPI, but we use the ARP
-	 * static ARP tables to hold the I-FIELDs.
-	 */
-	return arp_find(hip->le.daddr, skb);
-}
-
-
-/*
  *	Determine the packet's protocol ID.
  */
 
@@ -186,7 +159,6 @@ EXPORT_SYMBOL(hippi_neigh_setup_dev);
 
 static const struct header_ops hippi_header_ops = {
 	.create		= hippi_header,
-	.rebuild	= hippi_rebuild_header,
 };
 
 
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 64c6bed4a3d3..59555f0f8fc8 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -413,7 +413,10 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
 			vlan_transfer_features(dev, vlandev);
 		break;
 
-	case NETDEV_DOWN:
+	case NETDEV_DOWN: {
+		struct net_device *tmp;
+		LIST_HEAD(close_list);
+
 		if (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)
 			vlan_vid_del(dev, htons(ETH_P_8021Q), 0);
 
@@ -425,15 +428,22 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
 
 			vlan = vlan_dev_priv(vlandev);
 			if (!(vlan->flags & VLAN_FLAG_LOOSE_BINDING))
-				dev_change_flags(vlandev, flgs & ~IFF_UP);
+				list_add(&vlandev->close_list, &close_list);
+		}
+
+		dev_close_many(&close_list, false);
+
+		list_for_each_entry_safe(vlandev, tmp, &close_list, close_list) {
 			netif_stacked_transfer_operstate(dev, vlandev);
+			list_del_init(&vlandev->close_list);
 		}
+		list_del(&close_list);
 		break;
-
+	}
 	case NETDEV_UP:
 		/* Put all VLANs for this dev in the up state too.  */
 		vlan_group_for_each_dev(grp, i, vlandev) {
-			flgs = vlandev->flags;
+			flgs = dev_get_flags(vlandev);
 			if (flgs & IFF_UP)
 				continue;
 
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index 90cc2bdd4064..61bf2a06e85d 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -9,7 +9,7 @@ bool vlan_do_receive(struct sk_buff **skbp)
 {
 	struct sk_buff *skb = *skbp;
 	__be16 vlan_proto = skb->vlan_proto;
-	u16 vlan_id = vlan_tx_tag_get_id(skb);
+	u16 vlan_id = skb_vlan_tag_get_id(skb);
 	struct net_device *vlan_dev;
 	struct vlan_pcpu_stats *rx_stats;
 
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 0d441ec8763e..01d7ba840df8 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -26,6 +26,7 @@
 #include <linux/slab.h>
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
+#include <linux/net_tstamp.h>
 #include <linux/etherdevice.h>
 #include <linux/ethtool.h>
 #include <net/arp.h>
@@ -36,39 +37,6 @@
 #include <linux/netpoll.h>
 
 /*
- *	Rebuild the Ethernet MAC header. This is called after an ARP
- *	(or in future other address resolution) has completed on this
- *	sk_buff. We now let ARP fill in the other fields.
- *
- *	This routine CANNOT use cached dst->neigh!
- *	Really, it is used only when dst->neigh is wrong.
- *
- * TODO:  This needs a checkup, I'm ignorant here. --BLG
- */
-static int vlan_dev_rebuild_header(struct sk_buff *skb)
-{
-	struct net_device *dev = skb->dev;
-	struct vlan_ethhdr *veth = (struct vlan_ethhdr *)(skb->data);
-
-	switch (veth->h_vlan_encapsulated_proto) {
-#ifdef CONFIG_INET
-	case htons(ETH_P_IP):
-
-		/* TODO:  Confirm this will work with VLAN headers... */
-		return arp_find(veth->h_dest, skb);
-#endif
-	default:
-		pr_debug("%s: unable to resolve type %X addresses\n",
-			 dev->name, ntohs(veth->h_vlan_encapsulated_proto));
-
-		ether_addr_copy(veth->h_source, dev->dev_addr);
-		break;
-	}
-
-	return 0;
-}
-
-/*
  *	Create the VLAN header for an arbitrary protocol layer
  *
  *	saddr=NULL	means use device source address
@@ -150,7 +118,7 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb,
 		u16 vlan_tci;
 		vlan_tci = vlan->vlan_id;
 		vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb->priority);
-		skb = __vlan_hwaccel_put_tag(skb, vlan->vlan_proto, vlan_tci);
+		__vlan_hwaccel_put_tag(skb, vlan->vlan_proto, vlan_tci);
 	}
 
 	skb->dev = vlan->real_dev;
@@ -533,7 +501,6 @@ static int vlan_dev_get_lock_subclass(struct net_device *dev)
 
 static const struct header_ops vlan_header_ops = {
 	.create	 = vlan_dev_hard_header,
-	.rebuild = vlan_dev_rebuild_header,
 	.parse	 = eth_header_parse,
 };
 
@@ -553,7 +520,6 @@ static int vlan_passthru_hard_header(struct sk_buff *skb, struct net_device *dev
 
 static const struct header_ops vlan_passthru_header_ops = {
 	.create	 = vlan_passthru_hard_header,
-	.rebuild = dev_rebuild_header,
 	.parse	 = eth_header_parse,
 };
 
@@ -572,21 +538,22 @@ static int vlan_dev_init(struct net_device *dev)
 	/* IFF_BROADCAST|IFF_MULTICAST; ??? */
 	dev->flags  = real_dev->flags & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI |
 					  IFF_MASTER | IFF_SLAVE);
-	dev->iflink = real_dev->ifindex;
 	dev->state  = (real_dev->state & ((1<<__LINK_STATE_NOCARRIER) |
 					  (1<<__LINK_STATE_DORMANT))) |
 		      (1<<__LINK_STATE_PRESENT);
 
 	dev->hw_features = NETIF_F_ALL_CSUM | NETIF_F_SG |
-			   NETIF_F_FRAGLIST | NETIF_F_ALL_TSO |
+			   NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE |
 			   NETIF_F_HIGHDMA | NETIF_F_SCTP_CSUM |
 			   NETIF_F_ALL_FCOE;
 
-	dev->features |= real_dev->vlan_features | NETIF_F_LLTX;
+	dev->features |= real_dev->vlan_features | NETIF_F_LLTX |
+			 NETIF_F_GSO_SOFTWARE;
 	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");
 
+	dev->vlan_features = real_dev->vlan_features & ~NETIF_F_ALL_FCOE;
 
 	/* ipv6 shared card related stuff */
 	dev->dev_id = real_dev->dev_id;
@@ -647,7 +614,7 @@ static netdev_features_t vlan_dev_fix_features(struct net_device *dev,
 	features |= NETIF_F_RXCSUM;
 	features = netdev_intersect_features(features, real_dev->features);
 
-	features |= old_features & NETIF_F_SOFT_FEATURES;
+	features |= old_features & (NETIF_F_SOFT_FEATURES | NETIF_F_GSO_SOFTWARE);
 	features |= NETIF_F_LLTX;
 
 	return features;
@@ -669,6 +636,23 @@ static void vlan_ethtool_get_drvinfo(struct net_device *dev,
 	strlcpy(info->fw_version, "N/A", sizeof(info->fw_version));
 }
 
+static int vlan_ethtool_get_ts_info(struct net_device *dev,
+				    struct ethtool_ts_info *info)
+{
+	const struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+	const struct ethtool_ops *ops = vlan->real_dev->ethtool_ops;
+
+	if (ops->get_ts_info) {
+		return ops->get_ts_info(vlan->real_dev, info);
+	} else {
+		info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE |
+			SOF_TIMESTAMPING_SOFTWARE;
+		info->phc_index = -1;
+	}
+
+	return 0;
+}
+
 static struct rtnl_link_stats64 *vlan_dev_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 {
 	struct vlan_pcpu_stats *p;
@@ -748,10 +732,18 @@ static void vlan_dev_netpoll_cleanup(struct net_device *dev)
 }
 #endif /* CONFIG_NET_POLL_CONTROLLER */
 
+static int vlan_dev_get_iflink(const struct net_device *dev)
+{
+	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
+
+	return real_dev->ifindex;
+}
+
 static const struct ethtool_ops vlan_ethtool_ops = {
 	.get_settings	        = vlan_ethtool_get_settings,
 	.get_drvinfo	        = vlan_ethtool_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
+	.get_ts_info		= vlan_ethtool_get_ts_info,
 };
 
 static const struct net_device_ops vlan_netdev_ops = {
@@ -783,6 +775,7 @@ static const struct net_device_ops vlan_netdev_ops = {
 #endif
 	.ndo_fix_features	= vlan_dev_fix_features,
 	.ndo_get_lock_subclass  = vlan_dev_get_lock_subclass,
+	.ndo_get_iflink		= vlan_dev_get_iflink,
 };
 
 static void vlan_dev_free(struct net_device *dev)
@@ -807,5 +800,5 @@ void vlan_setup(struct net_device *dev)
 	dev->destructor		= vlan_dev_free;
 	dev->ethtool_ops	= &vlan_ethtool_ops;
 
-	memset(dev->broadcast, 0, ETH_ALEN);
+	eth_zero_addr(dev->broadcast);
 }
diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
index 8ac8a5cc2143..c92b52f37d38 100644
--- a/net/8021q/vlan_netlink.c
+++ b/net/8021q/vlan_netlink.c
@@ -238,6 +238,13 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
+static struct net *vlan_get_link_net(const struct net_device *dev)
+{
+	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
+
+	return dev_net(real_dev);
+}
+
 struct rtnl_link_ops vlan_link_ops __read_mostly = {
 	.kind		= "vlan",
 	.maxtype	= IFLA_VLAN_MAX,
@@ -250,6 +257,7 @@ struct rtnl_link_ops vlan_link_ops __read_mostly = {
 	.dellink	= unregister_vlan_dev,
 	.get_size	= vlan_get_size,
 	.fill_info	= vlan_fill_info,
+	.get_link_net	= vlan_get_link_net,
 };
 
 int __init vlan_netlink_init(void)
diff --git a/net/9p/client.c b/net/9p/client.c
index e86a9bea1d16..6f4c4c88db84 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -34,6 +34,7 @@
 #include <linux/slab.h>
 #include <linux/sched.h>
 #include <linux/uaccess.h>
+#include <linux/uio.h>
 #include <net/9p/9p.h>
 #include <linux/parser.h>
 #include <net/9p/client.h>
@@ -555,7 +556,7 @@ out_err:
  */
 
 static int p9_check_zc_errors(struct p9_client *c, struct p9_req_t *req,
-			      char *uidata, int in_hdrlen, int kern_buf)
+			      struct iov_iter *uidata, int in_hdrlen)
 {
 	int err;
 	int ecode;
@@ -591,16 +592,11 @@ static int p9_check_zc_errors(struct p9_client *c, struct p9_req_t *req,
 		ename = &req->rc->sdata[req->rc->offset];
 		if (len > inline_len) {
 			/* We have error in external buffer */
-			if (kern_buf) {
-				memcpy(ename + inline_len, uidata,
-				       len - inline_len);
-			} else {
-				err = copy_from_user(ename + inline_len,
-						     uidata, len - inline_len);
-				if (err) {
-					err = -EFAULT;
-					goto out_err;
-				}
+			err = copy_from_iter(ename + inline_len,
+					     len - inline_len, uidata);
+			if (err != len - inline_len) {
+				err = -EFAULT;
+				goto out_err;
 			}
 		}
 		ename = NULL;
@@ -806,8 +802,8 @@ reterr:
  * p9_client_zc_rpc - issue a request and wait for a response
  * @c: client session
  * @type: type of request
- * @uidata: user bffer that should be ued for zero copy read
- * @uodata: user buffer that shoud be user for zero copy write
+ * @uidata: destination for zero copy read
+ * @uodata: source for zero copy write
  * @inlen: read buffer size
  * @olen: write buffer size
  * @hdrlen: reader header size, This is the size of response protocol data
@@ -816,9 +812,10 @@ reterr:
  * Returns request structure (which client must free using p9_free_req)
  */
 static struct p9_req_t *p9_client_zc_rpc(struct p9_client *c, int8_t type,
-					 char *uidata, char *uodata,
+					 struct iov_iter *uidata,
+					 struct iov_iter *uodata,
 					 int inlen, int olen, int in_hdrlen,
-					 int kern_buf, const char *fmt, ...)
+					 const char *fmt, ...)
 {
 	va_list ap;
 	int sigpending, err;
@@ -841,12 +838,8 @@ static struct p9_req_t *p9_client_zc_rpc(struct p9_client *c, int8_t type,
 	} else
 		sigpending = 0;
 
-	/* If we are called with KERNEL_DS force kern_buf */
-	if (segment_eq(get_fs(), KERNEL_DS))
-		kern_buf = 1;
-
 	err = c->trans_mod->zc_request(c, req, uidata, uodata,
-				       inlen, olen, in_hdrlen, kern_buf);
+				       inlen, olen, in_hdrlen);
 	if (err < 0) {
 		if (err == -EIO)
 			c->status = Disconnected;
@@ -876,7 +869,7 @@ static struct p9_req_t *p9_client_zc_rpc(struct p9_client *c, int8_t type,
 	if (err < 0)
 		goto reterr;
 
-	err = p9_check_zc_errors(c, req, uidata, in_hdrlen, kern_buf);
+	err = p9_check_zc_errors(c, req, uidata, in_hdrlen);
 	trace_9p_client_res(c, type, req->rc->tag, err);
 	if (!err)
 		return req;
@@ -1123,6 +1116,7 @@ struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid,
 		fid = NULL;
 		goto error;
 	}
+	fid->uid = n_uname;
 
 	req = p9_client_rpc(clnt, P9_TATTACH, "ddss?u", fid->fid,
 			afid ? afid->fid : P9_NOFID, uname, aname, n_uname);
@@ -1541,142 +1535,128 @@ error:
 EXPORT_SYMBOL(p9_client_unlinkat);
 
 int
-p9_client_read(struct p9_fid *fid, char *data, char __user *udata, u64 offset,
-								u32 count)
+p9_client_read(struct p9_fid *fid, u64 offset, struct iov_iter *to, int *err)
 {
-	char *dataptr;
-	int kernel_buf = 0;
+	struct p9_client *clnt = fid->clnt;
 	struct p9_req_t *req;
-	struct p9_client *clnt;
-	int err, rsize, non_zc = 0;
-
+	int total = 0;
 
 	p9_debug(P9_DEBUG_9P, ">>> TREAD fid %d offset %llu %d\n",
-		   fid->fid, (unsigned long long) offset, count);
-	err = 0;
-	clnt = fid->clnt;
-
-	rsize = fid->iounit;
-	if (!rsize || rsize > clnt->msize-P9_IOHDRSZ)
-		rsize = clnt->msize - P9_IOHDRSZ;
-
-	if (count < rsize)
-		rsize = count;
-
-	/* Don't bother zerocopy for small IO (< 1024) */
-	if (clnt->trans_mod->zc_request && rsize > 1024) {
-		char *indata;
-		if (data) {
-			kernel_buf = 1;
-			indata = data;
-		} else
-			indata = (__force char *)udata;
-		/*
-		 * response header len is 11
-		 * PDU Header(7) + IO Size (4)
-		 */
-		req = p9_client_zc_rpc(clnt, P9_TREAD, indata, NULL, rsize, 0,
-				       11, kernel_buf, "dqd", fid->fid,
-				       offset, rsize);
-	} else {
-		non_zc = 1;
-		req = p9_client_rpc(clnt, P9_TREAD, "dqd", fid->fid, offset,
-				    rsize);
-	}
-	if (IS_ERR(req)) {
-		err = PTR_ERR(req);
-		goto error;
-	}
+		   fid->fid, (unsigned long long) offset, (int)iov_iter_count(to));
+
+	while (iov_iter_count(to)) {
+		int count = iov_iter_count(to);
+		int rsize, non_zc = 0;
+		char *dataptr;
+			
+		rsize = fid->iounit;
+		if (!rsize || rsize > clnt->msize-P9_IOHDRSZ)
+			rsize = clnt->msize - P9_IOHDRSZ;
+
+		if (count < rsize)
+			rsize = count;
+
+		/* Don't bother zerocopy for small IO (< 1024) */
+		if (clnt->trans_mod->zc_request && rsize > 1024) {
+			/*
+			 * response header len is 11
+			 * PDU Header(7) + IO Size (4)
+			 */
+			req = p9_client_zc_rpc(clnt, P9_TREAD, to, NULL, rsize,
+					       0, 11, "dqd", fid->fid,
+					       offset, rsize);
+		} else {
+			non_zc = 1;
+			req = p9_client_rpc(clnt, P9_TREAD, "dqd", fid->fid, offset,
+					    rsize);
+		}
+		if (IS_ERR(req)) {
+			*err = PTR_ERR(req);
+			break;
+		}
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "D", &count, &dataptr);
-	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
-		goto free_and_error;
-	}
+		*err = p9pdu_readf(req->rc, clnt->proto_version,
+				   "D", &count, &dataptr);
+		if (*err) {
+			trace_9p_protocol_dump(clnt, req->rc);
+			p9_free_req(clnt, req);
+			break;
+		}
 
-	p9_debug(P9_DEBUG_9P, "<<< RREAD count %d\n", count);
+		p9_debug(P9_DEBUG_9P, "<<< RREAD count %d\n", count);
+		if (!count) {
+			p9_free_req(clnt, req);
+			break;
+		}
 
-	if (non_zc) {
-		if (data) {
-			memmove(data, dataptr, count);
-		} else {
-			err = copy_to_user(udata, dataptr, count);
-			if (err) {
-				err = -EFAULT;
-				goto free_and_error;
+		if (non_zc) {
+			int n = copy_to_iter(dataptr, count, to);
+			total += n;
+			offset += n;
+			if (n != count) {
+				*err = -EFAULT;
+				p9_free_req(clnt, req);
+				break;
 			}
+		} else {
+			iov_iter_advance(to, count);
+			total += count;
+			offset += count;
 		}
+		p9_free_req(clnt, req);
 	}
-	p9_free_req(clnt, req);
-	return count;
-
-free_and_error:
-	p9_free_req(clnt, req);
-error:
-	return err;
+	return total;
 }
 EXPORT_SYMBOL(p9_client_read);
 
 int
-p9_client_write(struct p9_fid *fid, char *data, const char __user *udata,
-							u64 offset, u32 count)
+p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err)
 {
-	int err, rsize;
-	int kernel_buf = 0;
-	struct p9_client *clnt;
+	struct p9_client *clnt = fid->clnt;
 	struct p9_req_t *req;
+	int total = 0;
+
+	p9_debug(P9_DEBUG_9P, ">>> TWRITE fid %d offset %llu count %zd\n",
+				fid->fid, (unsigned long long) offset,
+				iov_iter_count(from));
+
+	while (iov_iter_count(from)) {
+		int count = iov_iter_count(from);
+		int rsize = fid->iounit;
+		if (!rsize || rsize > clnt->msize-P9_IOHDRSZ)
+			rsize = clnt->msize - P9_IOHDRSZ;
+
+		if (count < rsize)
+			rsize = count;
+
+		/* Don't bother zerocopy for small IO (< 1024) */
+		if (clnt->trans_mod->zc_request && rsize > 1024) {
+			req = p9_client_zc_rpc(clnt, P9_TWRITE, NULL, from, 0,
+					       rsize, P9_ZC_HDR_SZ, "dqd",
+					       fid->fid, offset, rsize);
+		} else {
+			req = p9_client_rpc(clnt, P9_TWRITE, "dqV", fid->fid,
+						    offset, rsize, from);
+		}
+		if (IS_ERR(req)) {
+			*err = PTR_ERR(req);
+			break;
+		}
 
-	p9_debug(P9_DEBUG_9P, ">>> TWRITE fid %d offset %llu count %d\n",
-				fid->fid, (unsigned long long) offset, count);
-	err = 0;
-	clnt = fid->clnt;
-
-	rsize = fid->iounit;
-	if (!rsize || rsize > clnt->msize-P9_IOHDRSZ)
-		rsize = clnt->msize - P9_IOHDRSZ;
+		*err = p9pdu_readf(req->rc, clnt->proto_version, "d", &count);
+		if (*err) {
+			trace_9p_protocol_dump(clnt, req->rc);
+			p9_free_req(clnt, req);
+		}
 
-	if (count < rsize)
-		rsize = count;
+		p9_debug(P9_DEBUG_9P, "<<< RWRITE count %d\n", count);
 
-	/* Don't bother zerocopy for small IO (< 1024) */
-	if (clnt->trans_mod->zc_request && rsize > 1024) {
-		char *odata;
-		if (data) {
-			kernel_buf = 1;
-			odata = data;
-		} else
-			odata = (char *)udata;
-		req = p9_client_zc_rpc(clnt, P9_TWRITE, NULL, odata, 0, rsize,
-				       P9_ZC_HDR_SZ, kernel_buf, "dqd",
-				       fid->fid, offset, rsize);
-	} else {
-		if (data)
-			req = p9_client_rpc(clnt, P9_TWRITE, "dqD", fid->fid,
-					    offset, rsize, data);
-		else
-			req = p9_client_rpc(clnt, P9_TWRITE, "dqU", fid->fid,
-					    offset, rsize, udata);
-	}
-	if (IS_ERR(req)) {
-		err = PTR_ERR(req);
-		goto error;
-	}
-
-	err = p9pdu_readf(req->rc, clnt->proto_version, "d", &count);
-	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
-		goto free_and_error;
+		p9_free_req(clnt, req);
+		iov_iter_advance(from, count);
+		total += count;
+		offset += count;
 	}
-
-	p9_debug(P9_DEBUG_9P, "<<< RWRITE count %d\n", count);
-
-	p9_free_req(clnt, req);
-	return count;
-
-free_and_error:
-	p9_free_req(clnt, req);
-error:
-	return err;
+	return total;
 }
 EXPORT_SYMBOL(p9_client_write);
 
@@ -2068,6 +2048,10 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset)
 	struct p9_client *clnt;
 	struct p9_req_t *req;
 	char *dataptr;
+	struct kvec kv = {.iov_base = data, .iov_len = count};
+	struct iov_iter to;
+
+	iov_iter_kvec(&to, READ | ITER_KVEC, &kv, 1, count);
 
 	p9_debug(P9_DEBUG_9P, ">>> TREADDIR fid %d offset %llu count %d\n",
 				fid->fid, (unsigned long long) offset, count);
@@ -2088,8 +2072,8 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset)
 		 * response header len is 11
 		 * PDU Header(7) + IO Size (4)
 		 */
-		req = p9_client_zc_rpc(clnt, P9_TREADDIR, data, NULL, rsize, 0,
-				       11, 1, "dqd", fid->fid, offset, rsize);
+		req = p9_client_zc_rpc(clnt, P9_TREADDIR, &to, NULL, rsize, 0,
+				       11, "dqd", fid->fid, offset, rsize);
 	} else {
 		non_zc = 1;
 		req = p9_client_rpc(clnt, P9_TREADDIR, "dqd", fid->fid,
diff --git a/net/9p/protocol.c b/net/9p/protocol.c
index ab9127ec5b7a..16d287565987 100644
--- a/net/9p/protocol.c
+++ b/net/9p/protocol.c
@@ -33,6 +33,7 @@
 #include <linux/sched.h>
 #include <linux/stddef.h>
 #include <linux/types.h>
+#include <linux/uio.h>
 #include <net/9p/9p.h>
 #include <net/9p/client.h>
 #include "protocol.h"
@@ -69,10 +70,11 @@ static size_t pdu_write(struct p9_fcall *pdu, const void *data, size_t size)
 }
 
 static size_t
-pdu_write_u(struct p9_fcall *pdu, const char __user *udata, size_t size)
+pdu_write_u(struct p9_fcall *pdu, struct iov_iter *from, size_t size)
 {
 	size_t len = min(pdu->capacity - pdu->size, size);
-	if (copy_from_user(&pdu->sdata[pdu->size], udata, len))
+	struct iov_iter i = *from;
+	if (copy_from_iter(&pdu->sdata[pdu->size], len, &i) != len)
 		len = 0;
 
 	pdu->size += len;
@@ -273,7 +275,7 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt,
 			}
 			break;
 		case 'R':{
-				int16_t *nwqid = va_arg(ap, int16_t *);
+				uint16_t *nwqid = va_arg(ap, uint16_t *);
 				struct p9_qid **wqids =
 				    va_arg(ap, struct p9_qid **);
 
@@ -437,23 +439,13 @@ p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt,
 						 stbuf->extension, stbuf->n_uid,
 						 stbuf->n_gid, stbuf->n_muid);
 			} break;
-		case 'D':{
+		case 'V':{
 				uint32_t count = va_arg(ap, uint32_t);
-				const void *data = va_arg(ap, const void *);
-
-				errcode = p9pdu_writef(pdu, proto_version, "d",
-									count);
-				if (!errcode && pdu_write(pdu, data, count))
-					errcode = -EFAULT;
-			}
-			break;
-		case 'U':{
-				int32_t count = va_arg(ap, int32_t);
-				const char __user *udata =
-						va_arg(ap, const void __user *);
+				struct iov_iter *from =
+						va_arg(ap, struct iov_iter *);
 				errcode = p9pdu_writef(pdu, proto_version, "d",
 									count);
-				if (!errcode && pdu_write_u(pdu, udata, count))
+				if (!errcode && pdu_write_u(pdu, from, count))
 					errcode = -EFAULT;
 			}
 			break;
@@ -479,7 +471,7 @@ p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt,
 			}
 			break;
 		case 'R':{
-				int16_t nwqid = va_arg(ap, int);
+				uint16_t nwqid = va_arg(ap, int);
 				struct p9_qid *wqids =
 				    va_arg(ap, struct p9_qid *);
 
diff --git a/net/9p/trans_common.c b/net/9p/trans_common.c
index 2ee3879161b1..38aa6345bdfa 100644
--- a/net/9p/trans_common.c
+++ b/net/9p/trans_common.c
@@ -12,12 +12,8 @@
  *
  */
 
-#include <linux/slab.h>
+#include <linux/mm.h>
 #include <linux/module.h>
-#include <net/9p/9p.h>
-#include <net/9p/client.h>
-#include <linux/scatterlist.h>
-#include "trans_common.h"
 
 /**
  *  p9_release_req_pages - Release pages after the transaction.
@@ -31,39 +27,3 @@ void p9_release_pages(struct page **pages, int nr_pages)
 			put_page(pages[i]);
 }
 EXPORT_SYMBOL(p9_release_pages);
-
-/**
- * p9_nr_pages - Return number of pages needed to accommodate the payload.
- */
-int p9_nr_pages(char *data, int len)
-{
-	unsigned long start_page, end_page;
-	start_page =  (unsigned long)data >> PAGE_SHIFT;
-	end_page = ((unsigned long)data + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	return end_page - start_page;
-}
-EXPORT_SYMBOL(p9_nr_pages);
-
-/**
- * payload_gup - Translates user buffer into kernel pages and
- * pins them either for read/write through get_user_pages_fast().
- * @req: Request to be sent to server.
- * @pdata_off: data offset into the first page after translation (gup).
- * @pdata_len: Total length of the IO. gup may not return requested # of pages.
- * @nr_pages: number of pages to accommodate the payload
- * @rw: Indicates if the pages are for read or write.
- */
-
-int p9_payload_gup(char *data, int *nr_pages, struct page **pages, int write)
-{
-	int nr_mapped_pages;
-
-	nr_mapped_pages = get_user_pages_fast((unsigned long)data,
-					      *nr_pages, write, pages);
-	if (nr_mapped_pages <= 0)
-		return nr_mapped_pages;
-
-	*nr_pages = nr_mapped_pages;
-	return 0;
-}
-EXPORT_SYMBOL(p9_payload_gup);
diff --git a/net/9p/trans_common.h b/net/9p/trans_common.h
index 173bb550a9eb..c43babb3f635 100644
--- a/net/9p/trans_common.h
+++ b/net/9p/trans_common.h
@@ -13,5 +13,3 @@
  */
 
 void p9_release_pages(struct page **, int);
-int p9_payload_gup(char *, int *, struct page **, int);
-int p9_nr_pages(char *, int);
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index 80d08f6664cb..bced8c074c12 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -734,6 +734,7 @@ static int parse_opts(char *params, struct p9_fd_opts *opts)
 	opts->port = P9_PORT;
 	opts->rfd = ~0;
 	opts->wfd = ~0;
+	opts->privport = 0;
 
 	if (!params)
 		return 0;
@@ -940,7 +941,7 @@ p9_fd_create_tcp(struct p9_client *client, const char *addr, char *args)
 	sin_server.sin_family = AF_INET;
 	sin_server.sin_addr.s_addr = in_aton(addr);
 	sin_server.sin_port = htons(opts.port);
-	err = __sock_create(read_pnet(&current->nsproxy->net_ns), PF_INET,
+	err = __sock_create(current->nsproxy->net_ns, PF_INET,
 			    SOCK_STREAM, IPPROTO_TCP, &csocket, 1);
 	if (err) {
 		pr_err("%s (%d): problem creating socket\n",
@@ -988,7 +989,7 @@ p9_fd_create_unix(struct p9_client *client, const char *addr, char *args)
 
 	sun_server.sun_family = PF_UNIX;
 	strcpy(sun_server.sun_path, addr);
-	err = __sock_create(read_pnet(&current->nsproxy->net_ns), PF_UNIX,
+	err = __sock_create(current->nsproxy->net_ns, PF_UNIX,
 			    SOCK_STREAM, 0, &csocket, 1);
 	if (err < 0) {
 		pr_err("%s (%d): problem creating socket\n",
@@ -1013,7 +1014,6 @@ p9_fd_create(struct p9_client *client, const char *addr, char *args)
 {
 	int err;
 	struct p9_fd_opts opts;
-	struct p9_trans_fd *p;
 
 	parse_opts(args, &opts);
 
@@ -1026,7 +1026,6 @@ p9_fd_create(struct p9_client *client, const char *addr, char *args)
 	if (err < 0)
 		return err;
 
-	p = (struct p9_trans_fd *) client->trans;
 	p9_conn_create(client);
 
 	return 0;
diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c
index 14ad43b5cf89..3533d2a53ab6 100644
--- a/net/9p/trans_rdma.c
+++ b/net/9p/trans_rdma.c
@@ -139,6 +139,7 @@ struct p9_rdma_opts {
 	int sq_depth;
 	int rq_depth;
 	long timeout;
+	int privport;
 };
 
 /*
@@ -146,7 +147,10 @@ struct p9_rdma_opts {
  */
 enum {
 	/* Options that take integer arguments */
-	Opt_port, Opt_rq_depth, Opt_sq_depth, Opt_timeout, Opt_err,
+	Opt_port, Opt_rq_depth, Opt_sq_depth, Opt_timeout,
+	/* Options that take no argument */
+	Opt_privport,
+	Opt_err,
 };
 
 static match_table_t tokens = {
@@ -154,6 +158,7 @@ static match_table_t tokens = {
 	{Opt_sq_depth, "sq=%u"},
 	{Opt_rq_depth, "rq=%u"},
 	{Opt_timeout, "timeout=%u"},
+	{Opt_privport, "privport"},
 	{Opt_err, NULL},
 };
 
@@ -175,6 +180,7 @@ static int parse_opts(char *params, struct p9_rdma_opts *opts)
 	opts->sq_depth = P9_RDMA_SQ_DEPTH;
 	opts->rq_depth = P9_RDMA_RQ_DEPTH;
 	opts->timeout = P9_RDMA_TIMEOUT;
+	opts->privport = 0;
 
 	if (!params)
 		return 0;
@@ -193,13 +199,13 @@ 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,
-				 "integer field, but no integer?\n");
-			continue;
+		if ((token != Opt_err) && (token != Opt_privport)) {
+			r = match_int(&args[0], &option);
+			if (r < 0) {
+				p9_debug(P9_DEBUG_ERROR,
+					 "integer field, but no integer?\n");
+				continue;
+			}
 		}
 		switch (token) {
 		case Opt_port:
@@ -214,6 +220,9 @@ static int parse_opts(char *params, struct p9_rdma_opts *opts)
 		case Opt_timeout:
 			opts->timeout = option;
 			break;
+		case Opt_privport:
+			opts->privport = 1;
+			break;
 		default:
 			continue;
 		}
@@ -607,6 +616,23 @@ static int rdma_cancelled(struct p9_client *client, struct p9_req_t *req)
 	return 0;
 }
 
+static int p9_rdma_bind_privport(struct p9_trans_rdma *rdma)
+{
+	struct sockaddr_in cl = {
+		.sin_family = AF_INET,
+		.sin_addr.s_addr = htonl(INADDR_ANY),
+	};
+	int port, err = -EINVAL;
+
+	for (port = P9_DEF_MAX_RESVPORT; port >= P9_DEF_MIN_RESVPORT; port--) {
+		cl.sin_port = htons((ushort)port);
+		err = rdma_bind_addr(rdma->cm_id, (struct sockaddr *)&cl);
+		if (err != -EADDRINUSE)
+			break;
+	}
+	return err;
+}
+
 /**
  * trans_create_rdma - Transport method for creating atransport instance
  * @client: client instance
@@ -642,6 +668,16 @@ rdma_create_trans(struct p9_client *client, const char *addr, char *args)
 	/* Associate the client with the transport */
 	client->trans = rdma;
 
+	/* Bind to a privileged port if we need to */
+	if (opts.privport) {
+		err = p9_rdma_bind_privport(rdma);
+		if (err < 0) {
+			pr_err("%s (%d): problem binding to privport: %d\n",
+			       __func__, task_pid_nr(current), -err);
+			goto error;
+		}
+	}
+
 	/* Resolve the server's address */
 	rdma->addr.sin_family = AF_INET;
 	rdma->addr.sin_addr.s_addr = in_aton(addr);
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index daa749c8b3fb..9dd49ca67dbc 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -217,15 +217,15 @@ static int p9_virtio_cancel(struct p9_client *client, struct p9_req_t *req)
  * @start: which segment of the sg_list to start at
  * @pdata: a list of pages to add into sg.
  * @nr_pages: number of pages to pack into the scatter/gather list
- * @data: data to pack into scatter/gather list
+ * @offs: amount of data in the beginning of first page _not_ to pack
  * @count: amount of data to pack into the scatter/gather list
  */
 static int
 pack_sg_list_p(struct scatterlist *sg, int start, int limit,
-	       struct page **pdata, int nr_pages, char *data, int count)
+	       struct page **pdata, int nr_pages, size_t offs, int count)
 {
 	int i = 0, s;
-	int data_off;
+	int data_off = offs;
 	int index = start;
 
 	BUG_ON(nr_pages > (limit - start));
@@ -233,16 +233,14 @@ pack_sg_list_p(struct scatterlist *sg, int start, int limit,
 	 * if the first page doesn't start at
 	 * page boundary find the offset
 	 */
-	data_off = offset_in_page(data);
 	while (nr_pages) {
-		s = rest_of_page(data);
+		s = PAGE_SIZE - data_off;
 		if (s > count)
 			s = count;
 		/* Make sure we don't terminate early. */
 		sg_unmark_end(&sg[index]);
 		sg_set_page(&sg[index++], pdata[i++], s, data_off);
 		data_off = 0;
-		data += s;
 		count -= s;
 		nr_pages--;
 	}
@@ -314,11 +312,20 @@ req_retry:
 }
 
 static int p9_get_mapped_pages(struct virtio_chan *chan,
-			       struct page **pages, char *data,
-			       int nr_pages, int write, int kern_buf)
+			       struct page ***pages,
+			       struct iov_iter *data,
+			       int count,
+			       size_t *offs,
+			       int *need_drop)
 {
+	int nr_pages;
 	int err;
-	if (!kern_buf) {
+
+	if (!iov_iter_count(data))
+		return 0;
+
+	if (!(data->type & ITER_KVEC)) {
+		int n;
 		/*
 		 * We allow only p9_max_pages pinned. We wait for the
 		 * Other zc request to finish here
@@ -329,26 +336,49 @@ static int p9_get_mapped_pages(struct virtio_chan *chan,
 			if (err == -ERESTARTSYS)
 				return err;
 		}
-		err = p9_payload_gup(data, &nr_pages, pages, write);
-		if (err < 0)
-			return err;
+		n = iov_iter_get_pages_alloc(data, pages, count, offs);
+		if (n < 0)
+			return n;
+		*need_drop = 1;
+		nr_pages = DIV_ROUND_UP(n + *offs, PAGE_SIZE);
 		atomic_add(nr_pages, &vp_pinned);
+		return n;
 	} else {
 		/* kernel buffer, no need to pin pages */
-		int s, index = 0;
-		int count = nr_pages;
-		while (nr_pages) {
-			s = rest_of_page(data);
-			if (is_vmalloc_addr(data))
-				pages[index++] = vmalloc_to_page(data);
+		int index;
+		size_t len;
+		void *p;
+
+		/* we'd already checked that it's non-empty */
+		while (1) {
+			len = iov_iter_single_seg_count(data);
+			if (likely(len)) {
+				p = data->kvec->iov_base + data->iov_offset;
+				break;
+			}
+			iov_iter_advance(data, 0);
+		}
+		if (len > count)
+			len = count;
+
+		nr_pages = DIV_ROUND_UP((unsigned long)p + len, PAGE_SIZE) -
+			   (unsigned long)p / PAGE_SIZE;
+
+		*pages = kmalloc(sizeof(struct page *) * nr_pages, GFP_NOFS);
+		if (!*pages)
+			return -ENOMEM;
+
+		*need_drop = 0;
+		p -= (*offs = (unsigned long)p % PAGE_SIZE);
+		for (index = 0; index < nr_pages; index++) {
+			if (is_vmalloc_addr(p))
+				(*pages)[index] = vmalloc_to_page(p);
 			else
-				pages[index++] = kmap_to_page(data);
-			data += s;
-			nr_pages--;
+				(*pages)[index] = kmap_to_page(p);
+			p += PAGE_SIZE;
 		}
-		nr_pages = count;
+		return len;
 	}
-	return nr_pages;
 }
 
 /**
@@ -364,8 +394,8 @@ static int p9_get_mapped_pages(struct virtio_chan *chan,
  */
 static int
 p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req,
-		     char *uidata, char *uodata, int inlen,
-		     int outlen, int in_hdr_len, int kern_buf)
+		     struct iov_iter *uidata, struct iov_iter *uodata,
+		     int inlen, int outlen, int in_hdr_len)
 {
 	int in, out, err, out_sgs, in_sgs;
 	unsigned long flags;
@@ -373,41 +403,32 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req,
 	struct page **in_pages = NULL, **out_pages = NULL;
 	struct virtio_chan *chan = client->trans;
 	struct scatterlist *sgs[4];
+	size_t offs;
+	int need_drop = 0;
 
 	p9_debug(P9_DEBUG_TRANS, "virtio request\n");
 
 	if (uodata) {
-		out_nr_pages = p9_nr_pages(uodata, outlen);
-		out_pages = kmalloc(sizeof(struct page *) * out_nr_pages,
-				    GFP_NOFS);
-		if (!out_pages) {
-			err = -ENOMEM;
-			goto err_out;
-		}
-		out_nr_pages = p9_get_mapped_pages(chan, out_pages, uodata,
-						   out_nr_pages, 0, kern_buf);
-		if (out_nr_pages < 0) {
-			err = out_nr_pages;
-			kfree(out_pages);
-			out_pages = NULL;
-			goto err_out;
-		}
-	}
-	if (uidata) {
-		in_nr_pages = p9_nr_pages(uidata, inlen);
-		in_pages = kmalloc(sizeof(struct page *) * in_nr_pages,
-				   GFP_NOFS);
-		if (!in_pages) {
-			err = -ENOMEM;
-			goto err_out;
+		int n = p9_get_mapped_pages(chan, &out_pages, uodata,
+					    outlen, &offs, &need_drop);
+		if (n < 0)
+			return n;
+		out_nr_pages = DIV_ROUND_UP(n + offs, PAGE_SIZE);
+		if (n != outlen) {
+			__le32 v = cpu_to_le32(n);
+			memcpy(&req->tc->sdata[req->tc->size - 4], &v, 4);
+			outlen = n;
 		}
-		in_nr_pages = p9_get_mapped_pages(chan, in_pages, uidata,
-						  in_nr_pages, 1, kern_buf);
-		if (in_nr_pages < 0) {
-			err = in_nr_pages;
-			kfree(in_pages);
-			in_pages = NULL;
-			goto err_out;
+	} else if (uidata) {
+		int n = p9_get_mapped_pages(chan, &in_pages, uidata,
+					    inlen, &offs, &need_drop);
+		if (n < 0)
+			return n;
+		in_nr_pages = DIV_ROUND_UP(n + offs, PAGE_SIZE);
+		if (n != inlen) {
+			__le32 v = cpu_to_le32(n);
+			memcpy(&req->tc->sdata[req->tc->size - 4], &v, 4);
+			inlen = n;
 		}
 	}
 	req->status = REQ_STATUS_SENT;
@@ -426,7 +447,7 @@ req_retry_pinned:
 	if (out_pages) {
 		sgs[out_sgs++] = chan->sg + out;
 		out += pack_sg_list_p(chan->sg, out, VIRTQUEUE_NUM,
-				      out_pages, out_nr_pages, uodata, outlen);
+				      out_pages, out_nr_pages, offs, outlen);
 	}
 		
 	/*
@@ -444,7 +465,7 @@ req_retry_pinned:
 	if (in_pages) {
 		sgs[out_sgs + in_sgs++] = chan->sg + out + in;
 		in += pack_sg_list_p(chan->sg, out + in, VIRTQUEUE_NUM,
-				     in_pages, in_nr_pages, uidata, inlen);
+				     in_pages, in_nr_pages, offs, inlen);
 	}
 
 	BUG_ON(out_sgs + in_sgs > ARRAY_SIZE(sgs));
@@ -478,7 +499,7 @@ req_retry_pinned:
 	 * Non kernel buffers are pinned, unpin them
 	 */
 err_out:
-	if (!kern_buf) {
+	if (need_drop) {
 		if (in_pages) {
 			p9_release_pages(in_pages, in_nr_pages);
 			atomic_sub(in_nr_pages, &vp_pinned);
@@ -504,7 +525,10 @@ static ssize_t p9_mount_tag_show(struct device *dev,
 	vdev = dev_to_virtio(dev);
 	chan = vdev->priv;
 
-	return snprintf(buf, chan->tag_len + 1, "%s", chan->tag);
+	memcpy(buf, chan->tag, chan->tag_len);
+	buf[chan->tag_len] = 0;
+
+	return chan->tag_len + 1;
 }
 
 static DEVICE_ATTR(mount_tag, 0444, p9_mount_tag_show, NULL);
@@ -524,6 +548,12 @@ static int p9_virtio_probe(struct virtio_device *vdev)
 	int err;
 	struct virtio_chan *chan;
 
+	if (!vdev->config->get) {
+		dev_err(&vdev->dev, "%s failure: config access disabled\n",
+			__func__);
+		return -EINVAL;
+	}
+
 	chan = kmalloc(sizeof(struct virtio_chan), GFP_KERNEL);
 	if (!chan) {
 		pr_err("Failed to allocate virtio 9P channel\n");
@@ -652,14 +682,30 @@ p9_virtio_create(struct p9_client *client, const char *devname, char *args)
 static void p9_virtio_remove(struct virtio_device *vdev)
 {
 	struct virtio_chan *chan = vdev->priv;
-
-	if (chan->inuse)
-		p9_virtio_close(chan->client);
-	vdev->config->del_vqs(vdev);
+	unsigned long warning_time;
 
 	mutex_lock(&virtio_9p_lock);
+
+	/* Remove self from list so we don't get new users. */
 	list_del(&chan->chan_list);
+	warning_time = jiffies;
+
+	/* Wait for existing users to close. */
+	while (chan->inuse) {
+		mutex_unlock(&virtio_9p_lock);
+		msleep(250);
+		if (time_after(jiffies, warning_time + 10 * HZ)) {
+			dev_emerg(&vdev->dev,
+				  "p9_virtio_remove: waiting for device in use.\n");
+			warning_time = jiffies;
+		}
+		mutex_lock(&virtio_9p_lock);
+	}
+
 	mutex_unlock(&virtio_9p_lock);
+
+	vdev->config->del_vqs(vdev);
+
 	sysfs_remove_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr);
 	kobject_uevent(&(vdev->dev.kobj), KOBJ_CHANGE);
 	kfree(chan->tag);
diff --git a/net/Kconfig b/net/Kconfig
index 99815b5454bf..44dd5786ee91 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -228,20 +228,21 @@ source "net/vmw_vsock/Kconfig"
 source "net/netlink/Kconfig"
 source "net/mpls/Kconfig"
 source "net/hsr/Kconfig"
+source "net/switchdev/Kconfig"
 
 config RPS
-	boolean
+	bool
 	depends on SMP && SYSFS
 	default y
 
 config RFS_ACCEL
-	boolean
+	bool
 	depends on RPS
 	select CPU_RMAP
 	default y
 
 config XPS
-	boolean
+	bool
 	depends on SMP
 	default y
 
@@ -253,18 +254,18 @@ config CGROUP_NET_PRIO
 	  a per-interface basis.
 
 config CGROUP_NET_CLASSID
-	boolean "Network classid cgroup"
+	bool "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
+	bool
 	default y
 
 config BQL
-	boolean
+	bool
 	depends on SYSFS
 	select DQL
 	default y
@@ -281,7 +282,7 @@ config BPF_JIT
 	  this feature changing /proc/sys/net/core/bpf_jit_enable
 
 config NET_FLOW_LIMIT
-	boolean
+	bool
 	depends on RPS
 	default y
 	---help---
diff --git a/net/Makefile b/net/Makefile
index 7ed1970074b0..3995613e5510 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -5,8 +5,6 @@
 # Rewritten to use lists instead of if-statements.
 #
 
-obj-y	:= nonet.o
-
 obj-$(CONFIG_NET)		:= socket.o core/
 
 tmp-$(CONFIG_COMPAT) 		:= compat.o
@@ -71,5 +69,8 @@ obj-$(CONFIG_BATMAN_ADV)	+= batman-adv/
 obj-$(CONFIG_NFC)		+= nfc/
 obj-$(CONFIG_OPENVSWITCH)	+= openvswitch/
 obj-$(CONFIG_VSOCKETS)	+= vmw_vsock/
-obj-$(CONFIG_NET_MPLS_GSO)	+= mpls/
+obj-$(CONFIG_MPLS)		+= mpls/
 obj-$(CONFIG_HSR)		+= hsr/
+ifneq ($(CONFIG_NET_SWITCHDEV),)
+obj-y				+= switchdev/
+endif
diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c
index d1c55d8dd0a2..8ad3ec2610b6 100644
--- a/net/appletalk/aarp.c
+++ b/net/appletalk/aarp.c
@@ -141,7 +141,7 @@ static void __aarp_send_query(struct aarp_entry *a)
 	eah->pa_src_net	 = sat->s_net;
 	eah->pa_src_node = sat->s_node;
 
-	memset(eah->hw_dst, '\0', ETH_ALEN);
+	eth_zero_addr(eah->hw_dst);
 
 	eah->pa_dst_zero = 0;
 	eah->pa_dst_net	 = a->target_addr.s_net;
@@ -189,7 +189,7 @@ static void aarp_send_reply(struct net_device *dev, struct atalk_addr *us,
 	eah->pa_src_node = us->s_node;
 
 	if (!sha)
-		memset(eah->hw_dst, '\0', ETH_ALEN);
+		eth_zero_addr(eah->hw_dst);
 	else
 		ether_addr_copy(eah->hw_dst, sha);
 
@@ -239,7 +239,7 @@ static void aarp_send_probe(struct net_device *dev, struct atalk_addr *us)
 	eah->pa_src_net	 = us->s_net;
 	eah->pa_src_node = us->s_node;
 
-	memset(eah->hw_dst, '\0', ETH_ALEN);
+	eth_zero_addr(eah->hw_dst);
 
 	eah->pa_dst_zero = 0;
 	eah->pa_dst_net	 = us->s_net;
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index c00897f65a31..3b7ad43c7dad 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1559,8 +1559,7 @@ freeit:
 	return 0;
 }
 
-static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
-			 size_t len)
+static int atalk_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 {
 	struct sock *sk = sock->sk;
 	struct atalk_sock *at = at_sk(sk);
@@ -1659,7 +1658,7 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
 
 	SOCK_DEBUG(sk, "SK %p: Copy user data (%Zd bytes).\n", sk, len);
 
-	err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
+	err = memcpy_from_msg(skb_put(skb, len), msg, len);
 	if (err) {
 		kfree_skb(skb);
 		err = -EFAULT;
@@ -1728,8 +1727,8 @@ out:
 	return err ? : len;
 }
 
-static int atalk_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
-			 size_t size, int flags)
+static int atalk_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+			 int flags)
 {
 	struct sock *sk = sock->sk;
 	struct ddpehdr *ddp;
@@ -1758,7 +1757,7 @@ static int atalk_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
 		copied = size;
 		msg->msg_flags |= MSG_TRUNC;
 	}
-	err = skb_copy_datagram_iovec(skb, offset, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, offset, msg, copied);
 
 	if (!err && msg->msg_name) {
 		DECLARE_SOCKADDR(struct sockaddr_at *, sat, msg->msg_name);
diff --git a/net/atm/common.c b/net/atm/common.c
index 6a765156a3f6..ed0466637e13 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -523,8 +523,8 @@ int vcc_connect(struct socket *sock, int itf, short vpi, int vci)
 	return 0;
 }
 
-int vcc_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
-		size_t size, int flags)
+int vcc_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+		int flags)
 {
 	struct sock *sk = sock->sk;
 	struct atm_vcc *vcc;
@@ -554,7 +554,7 @@ int vcc_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
 		msg->msg_flags |= MSG_TRUNC;
 	}
 
-	error = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	error = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (error)
 		return error;
 	sock_recv_ts_and_drops(msg, sk, skb);
@@ -569,16 +569,13 @@ int vcc_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
 	return copied;
 }
 
-int vcc_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m,
-		size_t total_len)
+int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size)
 {
 	struct sock *sk = sock->sk;
 	DEFINE_WAIT(wait);
 	struct atm_vcc *vcc;
 	struct sk_buff *skb;
 	int eff, error;
-	const void __user *buff;
-	int size;
 
 	lock_sock(sk);
 	if (sock->state != SS_CONNECTED) {
@@ -589,12 +586,6 @@ int vcc_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m,
 		error = -EISCONN;
 		goto out;
 	}
-	if (m->msg_iovlen != 1) {
-		error = -ENOSYS; /* fix this later @@@ */
-		goto out;
-	}
-	buff = m->msg_iov->iov_base;
-	size = m->msg_iov->iov_len;
 	vcc = ATM_SD(sock);
 	if (test_bit(ATM_VF_RELEASED, &vcc->flags) ||
 	    test_bit(ATM_VF_CLOSE, &vcc->flags) ||
@@ -607,7 +598,7 @@ int vcc_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m,
 		error = 0;
 		goto out;
 	}
-	if (size < 0 || size > vcc->qos.txtp.max_sdu) {
+	if (size > vcc->qos.txtp.max_sdu) {
 		error = -EMSGSIZE;
 		goto out;
 	}
@@ -639,7 +630,7 @@ int vcc_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m,
 		goto out;
 	skb->dev = NULL; /* for paths shared with net_device interfaces */
 	ATM_SKB(skb)->atm_options = vcc->atm_options;
-	if (copy_from_user(skb_put(skb, size), buff, size)) {
+	if (copy_from_iter(skb_put(skb, size), size, &m->msg_iter) != size) {
 		kfree_skb(skb);
 		error = -EFAULT;
 		goto out;
diff --git a/net/atm/common.h b/net/atm/common.h
index cc3c2dae4d79..4d6f5b2068ac 100644
--- a/net/atm/common.h
+++ b/net/atm/common.h
@@ -13,10 +13,9 @@
 int vcc_create(struct net *net, struct socket *sock, int protocol, int family);
 int vcc_release(struct socket *sock);
 int vcc_connect(struct socket *sock, int itf, short vpi, int vci);
-int vcc_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
-		size_t size, int flags);
-int vcc_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m,
-		size_t total_len);
+int vcc_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+		int flags);
+int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len);
 unsigned int vcc_poll(struct file *file, struct socket *sock, poll_table *wait);
 int vcc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
 int vcc_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
diff --git a/net/atm/lec.c b/net/atm/lec.c
index 4b98f897044a..cd3b37989057 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -2001,7 +2001,7 @@ lec_vcc_added(struct lec_priv *priv, const struct atmlec_ioc *ioc_data,
 		if (entry == NULL)
 			goto out;
 		memcpy(entry->atm_addr, ioc_data->atm_addr, ATM_ESA_LEN);
-		memset(entry->mac_addr, 0, ETH_ALEN);
+		eth_zero_addr(entry->mac_addr);
 		entry->recv_vcc = vcc;
 		entry->old_recv_push = old_push;
 		entry->status = ESI_UNKNOWN;
@@ -2086,7 +2086,7 @@ lec_vcc_added(struct lec_priv *priv, const struct atmlec_ioc *ioc_data,
 	entry->vcc = vcc;
 	entry->old_push = old_push;
 	memcpy(entry->atm_addr, ioc_data->atm_addr, ATM_ESA_LEN);
-	memset(entry->mac_addr, 0, ETH_ALEN);
+	eth_zero_addr(entry->mac_addr);
 	entry->status = ESI_UNKNOWN;
 	hlist_add_head(&entry->next, &priv->lec_arp_empty_ones);
 	entry->timer.expires = jiffies + priv->vcc_timeout_period;
diff --git a/net/atm/signaling.c b/net/atm/signaling.c
index 523bce72f698..4fd6af47383a 100644
--- a/net/atm/signaling.c
+++ b/net/atm/signaling.c
@@ -19,36 +19,15 @@
 #include "resources.h"
 #include "signaling.h"
 
-#undef WAIT_FOR_DEMON		/* #define this if system calls on SVC sockets
-				   should block until the demon runs.
-				   Danger: may cause nasty hangs if the demon
-				   crashes. */
-
 struct atm_vcc *sigd = NULL;
-#ifdef WAIT_FOR_DEMON
-static DECLARE_WAIT_QUEUE_HEAD(sigd_sleep);
-#endif
 
 static void sigd_put_skb(struct sk_buff *skb)
 {
-#ifdef WAIT_FOR_DEMON
-	DECLARE_WAITQUEUE(wait, current);
-
-	add_wait_queue(&sigd_sleep, &wait);
-	while (!sigd) {
-		set_current_state(TASK_UNINTERRUPTIBLE);
-		pr_debug("atmsvc: waiting for signaling daemon...\n");
-		schedule();
-	}
-	current->state = TASK_RUNNING;
-	remove_wait_queue(&sigd_sleep, &wait);
-#else
 	if (!sigd) {
 		pr_debug("atmsvc: no signaling daemon\n");
 		kfree_skb(skb);
 		return;
 	}
-#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));
@@ -261,8 +240,5 @@ int sigd_attach(struct atm_vcc *vcc)
 	vcc_insert_socket(sk_atm(vcc));
 	set_bit(ATM_VF_META, &vcc->flags);
 	set_bit(ATM_VF_READY, &vcc->flags);
-#ifdef WAIT_FOR_DEMON
-	wake_up(&sigd_sleep);
-#endif
 	return 0;
 }
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index c35c3f48fc0f..330c1f4a5a0b 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1432,8 +1432,7 @@ out:
 	return err;
 }
 
-static int ax25_sendmsg(struct kiocb *iocb, struct socket *sock,
-			struct msghdr *msg, size_t len)
+static int ax25_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 {
 	DECLARE_SOCKADDR(struct sockaddr_ax25 *, usax, msg->msg_name);
 	struct sock *sk = sock->sk;
@@ -1549,7 +1548,7 @@ static int ax25_sendmsg(struct kiocb *iocb, struct socket *sock,
 	skb_reserve(skb, size - len);
 
 	/* User data follows immediately after the AX.25 data */
-	if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) {
+	if (memcpy_from_msg(skb_put(skb, len), msg, len)) {
 		err = -EFAULT;
 		kfree_skb(skb);
 		goto out;
@@ -1599,8 +1598,8 @@ out:
 	return err;
 }
 
-static int ax25_recvmsg(struct kiocb *iocb, struct socket *sock,
-	struct msghdr *msg, size_t size, int flags)
+static int ax25_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+			int flags)
 {
 	struct sock *sk = sock->sk;
 	struct sk_buff *skb;
@@ -1634,7 +1633,7 @@ static int ax25_recvmsg(struct kiocb *iocb, struct socket *sock,
 		msg->msg_flags |= MSG_TRUNC;
 	}
 
-	skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	skb_copy_datagram_msg(skb, 0, msg, copied);
 
 	if (msg->msg_name) {
 		ax25_digi digi;
diff --git a/net/ax25/ax25_ip.c b/net/ax25/ax25_ip.c
index 67de6b33f2c3..7c646bb2c6f7 100644
--- a/net/ax25/ax25_ip.c
+++ b/net/ax25/ax25_ip.c
@@ -46,9 +46,9 @@
 
 #ifdef CONFIG_INET
 
-int ax25_hard_header(struct sk_buff *skb, struct net_device *dev,
-		     unsigned short type, const void *daddr,
-		     const void *saddr, unsigned int len)
+static int ax25_hard_header(struct sk_buff *skb, struct net_device *dev,
+			    unsigned short type, const void *daddr,
+			    const void *saddr, unsigned int len)
 {
 	unsigned char *buff;
 
@@ -100,7 +100,7 @@ int ax25_hard_header(struct sk_buff *skb, struct net_device *dev,
 	return -AX25_HEADER_LEN;	/* Unfinished header */
 }
 
-int ax25_rebuild_header(struct sk_buff *skb)
+netdev_tx_t ax25_ip_xmit(struct sk_buff *skb)
 {
 	struct sk_buff *ourskb;
 	unsigned char *bp  = skb->data;
@@ -115,9 +115,6 @@ int ax25_rebuild_header(struct sk_buff *skb)
 	dst = (ax25_address *)(bp + 1);
 	src = (ax25_address *)(bp + 8);
 
-	if (arp_find(bp + 1, skb))
-		return 1;
-
 	route = ax25_get_route(dst, NULL);
 	if (route) {
 		digipeat = route->digipeat;
@@ -129,6 +126,7 @@ int ax25_rebuild_header(struct sk_buff *skb)
 		dev = skb->dev;
 
 	if ((ax25_dev = ax25_dev_ax25dev(dev)) == NULL) {
+		kfree_skb(skb);
 		goto put;
 	}
 
@@ -212,31 +210,29 @@ put:
 	if (route)
 		ax25_put_route(route);
 
-	return 1;
+	return NETDEV_TX_OK;
 }
 
 #else	/* INET */
 
-int ax25_hard_header(struct sk_buff *skb, struct net_device *dev,
-		     unsigned short type, const void *daddr,
-		     const void *saddr, unsigned int len)
+static int ax25_hard_header(struct sk_buff *skb, struct net_device *dev,
+			    unsigned short type, const void *daddr,
+			    const void *saddr, unsigned int len)
 {
 	return -AX25_HEADER_LEN;
 }
 
-int ax25_rebuild_header(struct sk_buff *skb)
+netdev_tx_t ax25_ip_xmit(struct sk_buff *skb)
 {
-	return 1;
+	kfree_skb(skb);
+	return NETDEV_TX_OK;
 }
-
 #endif
 
 const struct header_ops ax25_header_ops = {
 	.create = ax25_hard_header,
-	.rebuild = ax25_rebuild_header,
 };
 
-EXPORT_SYMBOL(ax25_hard_header);
-EXPORT_SYMBOL(ax25_rebuild_header);
 EXPORT_SYMBOL(ax25_header_ops);
+EXPORT_SYMBOL(ax25_ip_xmit);
 
diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig
index 11660a3aab5a..c6fc8f756c9a 100644
--- a/net/batman-adv/Kconfig
+++ b/net/batman-adv/Kconfig
@@ -62,6 +62,7 @@ config BATMAN_ADV_MCAST
 config BATMAN_ADV_DEBUG
 	bool "B.A.T.M.A.N. debugging"
 	depends on BATMAN_ADV
+	depends on DEBUG_FS
 	help
 	  This is an option for use by developers; most people should
 	  say N here. This enables compilation of support for
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index 1e8053976e83..00e00e09b000 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -26,9 +26,8 @@
 #include "bat_algo.h"
 #include "network-coding.h"
 
-
 /**
- * batadv_dup_status - duplicate status
+ * enum batadv_dup_status - duplicate status
  * @BATADV_NO_DUP: the packet is a duplicate
  * @BATADV_ORIG_DUP: OGM is a duplicate in the originator (but not for the
  *  neighbor)
@@ -517,7 +516,7 @@ out:
  * @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
+ * @directlink: 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
@@ -879,7 +878,7 @@ batadv_iv_ogm_slide_own_bcast_window(struct batadv_hard_iface *hard_iface)
 		hlist_for_each_entry_rcu(orig_node, head, hash_entry) {
 			spin_lock_bh(&orig_node->bat_iv.ogm_cnt_lock);
 			word_index = hard_iface->if_num * BATADV_NUM_WORDS;
-			word = &(orig_node->bat_iv.bcast_own[word_index]);
+			word = &orig_node->bat_iv.bcast_own[word_index];
 
 			batadv_bit_get_packet(bat_priv, word, 1, 0);
 			if_num = hard_iface->if_num;
@@ -1362,10 +1361,10 @@ out:
 	return ret;
 }
 
-
 /**
  * batadv_iv_ogm_process_per_outif - process a batman iv OGM for an outgoing if
  * @skb: the skb containing the OGM
+ * @ogm_offset: offset from skb->data to start of ogm header
  * @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
@@ -1664,7 +1663,7 @@ static void batadv_iv_ogm_process(const struct sk_buff *skb, int ogm_offset,
 			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]);
+			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);
@@ -1902,10 +1901,10 @@ out:
  * 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
+ * @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 true if the metric via neigh1 is equally good or better than
  * the metric via neigh2, false otherwise.
  */
diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c
index 9586750022f5..e3da07a64026 100644
--- a/net/batman-adv/bitarray.c
+++ b/net/batman-adv/bitarray.c
@@ -29,7 +29,6 @@ static void batadv_bitmap_shift_left(unsigned long *seq_bits, int32_t n)
 	bitmap_shift_left(seq_bits, seq_bits, n, BATADV_TQ_LOCAL_WINDOW_SIZE);
 }
 
-
 /* receive and process one packet within the sequence number window.
  *
  * returns:
diff --git a/net/batman-adv/bitarray.h b/net/batman-adv/bitarray.h
index cc2407351d36..2acaafe60188 100644
--- a/net/batman-adv/bitarray.h
+++ b/net/batman-adv/bitarray.h
@@ -29,8 +29,7 @@ static inline int batadv_test_bit(const unsigned long *seq_bits,
 	diff = last_seqno - curr_seqno;
 	if (diff < 0 || diff >= BATADV_TQ_LOCAL_WINDOW_SIZE)
 		return 0;
-	else
-		return test_bit(diff, seq_bits) != 0;
+	return test_bit(diff, seq_bits) != 0;
 }
 
 /* turn corresponding bit on, so we can remember that we got the packet */
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index a957c8140721..ac4b96eccade 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -69,7 +69,6 @@ static inline uint32_t batadv_choose_backbone_gw(const void *data,
 	return hash % size;
 }
 
-
 /* compares address and vid of two backbone gws */
 static int batadv_compare_backbone_gw(const struct hlist_node *node,
 				      const void *data2)
@@ -245,14 +244,14 @@ batadv_bla_del_backbone_claims(struct batadv_bla_backbone_gw *backbone_gw)
 		spin_unlock_bh(list_lock);
 	}
 
-	/* all claims gone, intialize CRC */
+	/* all claims gone, initialize CRC */
 	backbone_gw->crc = BATADV_BLA_CRC_INIT;
 }
 
 /**
  * batadv_bla_send_claim - sends a claim frame according to the provided info
  * @bat_priv: the bat priv with all the soft interface information
- * @orig: the mac address to be announced within the claim
+ * @mac: the mac address to be announced within the claim
  * @vid: the VLAN ID
  * @claimtype: the type of the claim (CLAIM, UNCLAIM, ANNOUNCE, ...)
  */
@@ -364,6 +363,7 @@ out:
  * @bat_priv: the bat priv with all the soft interface information
  * @orig: the mac address of the originator
  * @vid: the VLAN ID
+ * @own_backbone: set if the requested backbone is local
  *
  * searches for the backbone gw or creates a new one if it could not
  * be found.
@@ -454,6 +454,7 @@ batadv_bla_update_own_backbone_gw(struct batadv_priv *bat_priv,
 /**
  * batadv_bla_answer_request - answer a bla request by sending own claims
  * @bat_priv: the bat priv with all the soft interface information
+ * @primary_if: interface where the request came on
  * @vid: the vid where the request came on
  *
  * Repeat all of our own claims, and finally send an ANNOUNCE frame
@@ -660,7 +661,6 @@ static int batadv_handle_announce(struct batadv_priv *bat_priv,
 	if (unlikely(!backbone_gw))
 		return 1;
 
-
 	/* handle as ANNOUNCE frame */
 	backbone_gw->lasttime = jiffies;
 	crc = ntohs(*((__be16 *)(&an_addr[4])));
@@ -775,6 +775,7 @@ static int batadv_handle_claim(struct batadv_priv *bat_priv,
 /**
  * batadv_check_claim_group
  * @bat_priv: the bat priv with all the soft interface information
+ * @primary_if: the primary interface of this batman interface
  * @hw_src: the Hardware source in the ARP Header
  * @hw_dst: the Hardware destination in the ARP Header
  * @ethhdr: pointer to the Ethernet header of the claim frame
@@ -846,10 +847,10 @@ static int batadv_check_claim_group(struct batadv_priv *bat_priv,
 	return 2;
 }
 
-
 /**
  * batadv_bla_process_claim
  * @bat_priv: the bat priv with all the soft interface information
+ * @primary_if: the primary hard interface of this batman soft interface
  * @skb: the frame to be checked
  *
  * Check if this is a claim frame, and process it accordingly.
@@ -1327,7 +1328,7 @@ int batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv,
 		goto out;
 	}
 	/* not found, add a new entry (overwrite the oldest entry)
-	 * and allow it, its the first occurence.
+	 * and allow it, its the first occurrence.
 	 */
 	curr = (bat_priv->bla.bcast_duplist_curr + BATADV_DUPLIST_SIZE - 1);
 	curr %= BATADV_DUPLIST_SIZE;
@@ -1343,8 +1344,6 @@ out:
 	return ret;
 }
 
-
-
 /**
  * batadv_bla_is_backbone_gw_orig
  * @bat_priv: the bat priv with all the soft interface information
@@ -1386,7 +1385,6 @@ bool batadv_bla_is_backbone_gw_orig(struct batadv_priv *bat_priv, uint8_t *orig,
 	return false;
 }
 
-
 /**
  * batadv_bla_is_backbone_gw
  * @skb: the frame to be checked
@@ -1476,7 +1474,6 @@ int batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb,
 	if (!atomic_read(&bat_priv->bridge_loop_avoidance))
 		goto allow;
 
-
 	if (unlikely(atomic_read(&bat_priv->bla.num_requests)))
 		/* don't allow broadcasts while requests are in flight */
 		if (is_multicast_ether_addr(ethhdr->h_dest) && is_bcast)
diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c
index a12e25efaf6f..a4972874c056 100644
--- a/net/batman-adv/debugfs.c
+++ b/net/batman-adv/debugfs.c
@@ -233,7 +233,6 @@ static int batadv_debug_log_setup(struct batadv_priv *bat_priv)
 
 static void batadv_debug_log_cleanup(struct batadv_priv *bat_priv)
 {
-	return;
 }
 #endif
 
@@ -405,6 +404,7 @@ struct batadv_debuginfo batadv_hardif_debuginfo_##_name = {	\
 		.release = single_release,			\
 	},							\
 }
+
 static BATADV_HARDIF_DEBUGINFO(originators, S_IRUGO,
 			       batadv_originators_hardif_open);
 
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index b5981113c9a7..aad022dd15df 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -1100,6 +1100,7 @@ void batadv_dat_snoop_outgoing_arp_reply(struct batadv_priv *bat_priv,
 	batadv_dat_send_data(bat_priv, skb, ip_src, BATADV_P_DAT_DHT_PUT);
 	batadv_dat_send_data(bat_priv, skb, ip_dst, BATADV_P_DAT_DHT_PUT);
 }
+
 /**
  * batadv_dat_snoop_incoming_arp_reply - snoop the ARP reply and fill the local
  * DAT storage only
diff --git a/net/batman-adv/distributed-arp-table.h b/net/batman-adv/distributed-arp-table.h
index d76e1d06c5b5..2fe0764c64be 100644
--- a/net/batman-adv/distributed-arp-table.h
+++ b/net/batman-adv/distributed-arp-table.h
@@ -25,9 +25,7 @@
 
 #include <linux/if_arp.h>
 
-/**
- * BATADV_DAT_ADDR_MAX - maximum address value in the DHT space
- */
+/* 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);
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index fc1835c6bb40..3d1dcaa3e8b5 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -23,7 +23,6 @@
 #include "hard-interface.h"
 #include "soft-interface.h"
 
-
 /**
  * batadv_frag_clear_chain - delete entries in the fragment buffer chain
  * @head: head of chain with entries.
@@ -251,7 +250,7 @@ batadv_frag_merge_packets(struct hlist_head *chain, struct sk_buff *skb)
 	kfree(entry);
 
 	/* Make room for the rest of the fragments. */
-	if (pskb_expand_head(skb_out, 0, size - skb->len, GFP_ATOMIC) < 0) {
+	if (pskb_expand_head(skb_out, 0, size - skb_out->len, GFP_ATOMIC) < 0) {
 		kfree_skb(skb_out);
 		skb_out = NULL;
 		goto free;
@@ -434,7 +433,7 @@ bool batadv_frag_send_packet(struct sk_buff *skb,
 	 * fragments larger than BATADV_FRAG_MAX_FRAG_SIZE
 	 */
 	mtu = min_t(unsigned, mtu, BATADV_FRAG_MAX_FRAG_SIZE);
-	max_fragment_size = (mtu - header_size - ETH_HLEN);
+	max_fragment_size = mtu - header_size;
 	max_packet_size = max_fragment_size * BATADV_FRAG_MAX_FRAGMENTS;
 
 	/* Don't even try to fragment, if we need more than 16 fragments */
diff --git a/net/batman-adv/fragmentation.h b/net/batman-adv/fragmentation.h
index 5d7a0e66a22b..d848cf6676a2 100644
--- a/net/batman-adv/fragmentation.h
+++ b/net/batman-adv/fragmentation.h
@@ -41,8 +41,7 @@ batadv_frag_check_entry(struct batadv_frag_table_entry *frags_entry)
 	if (!hlist_empty(&frags_entry->head) &&
 	    batadv_has_timed_out(frags_entry->timestamp, BATADV_FRAG_TIMEOUT))
 		return true;
-	else
-		return false;
+	return false;
 }
 
 #endif /* _NET_BATMAN_ADV_FRAGMENTATION_H_ */
diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c
index 90cff585b37d..090828cf1fa7 100644
--- a/net/batman-adv/gateway_client.c
+++ b/net/batman-adv/gateway_client.c
@@ -592,15 +592,16 @@ static int batadv_write_buffer_text(struct batadv_priv *bat_priv,
 
 	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_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);
+	seq_printf(seq, "%s %pM (%3i) %pM [%10s]: %u.%u/%u.%u MBit\n",
+		   (curr_gw == gw_node ? "=>" : "  "),
+		   gw_node->orig_node->orig,
+		   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);
+	ret = seq_has_overflowed(seq) ? -1 : 0;
 
 	if (curr_gw)
 		batadv_gw_node_free_ref(curr_gw);
@@ -775,6 +776,7 @@ batadv_gw_dhcp_recipient_get(struct sk_buff *skb, unsigned int *header_len,
 
 	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
@@ -810,7 +812,7 @@ bool batadv_gw_out_of_range(struct batadv_priv *bat_priv,
 		goto out;
 
 	gw_node = batadv_gw_node_get(bat_priv, orig_dst_node);
-	if (!gw_node->bandwidth_down == 0)
+	if (!gw_node)
 		goto out;
 
 	switch (atomic_read(&bat_priv->gw_mode)) {
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index fbda6b54baff..baf1f9843f2c 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -83,11 +83,12 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev)
 		return true;
 
 	/* no more parents..stop recursion */
-	if (net_dev->iflink == 0 || net_dev->iflink == net_dev->ifindex)
+	if (dev_get_iflink(net_dev) == 0 ||
+	    dev_get_iflink(net_dev) == 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, dev_get_iflink(net_dev));
 	/* if we got a NULL parent_dev there is something broken.. */
 	if (WARN(!parent_dev, "Cannot find parent device"))
 		return false;
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index d1183e882167..12fc77bef23f 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -41,7 +41,6 @@
 #include "network-coding.h"
 #include "fragmentation.h"
 
-
 /* List manipulations on hardif_list have to be rtnl_lock()'ed,
  * list traversals just rcu-locked
  */
@@ -403,6 +402,9 @@ int batadv_batman_skb_recv(struct sk_buff *skb, struct net_device *dev,
 		goto err_free;
 	}
 
+	/* reset control block to avoid left overs from previous users */
+	memset(skb->cb, 0, sizeof(struct batadv_skb_cb));
+
 	/* all receive handlers return whether they received or reused
 	 * the supplied skb. if not, we have to free the skb.
 	 */
@@ -651,7 +653,7 @@ static struct batadv_tvlv_handler
 /**
  * batadv_tvlv_container_free_ref - decrement the tvlv container refcounter and
  *  possibly free it
- * @tvlv_handler: the tvlv container to free
+ * @tvlv: the tvlv container to free
  */
 static void batadv_tvlv_container_free_ref(struct batadv_tvlv_container *tvlv)
 {
@@ -796,11 +798,11 @@ void batadv_tvlv_container_register(struct batadv_priv *bat_priv,
 }
 
 /**
- * batadv_tvlv_realloc_packet_buff - reallocate packet buffer to accomodate
+ * batadv_tvlv_realloc_packet_buff - reallocate packet buffer to accommodate
  *  requested packet size
  * @packet_buff: packet buffer
  * @packet_buff_len: packet buffer size
- * @packet_min_len: requested packet minimum size
+ * @min_packet_len: requested packet minimum size
  * @additional_packet_len: requested additional packet size on top of minimum
  *  size
  *
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index a1fcd884f0b1..4d2318829a34 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -24,7 +24,7 @@
 #define BATADV_DRIVER_DEVICE "batman-adv"
 
 #ifndef BATADV_SOURCE_VERSION
-#define BATADV_SOURCE_VERSION "2014.4.0"
+#define BATADV_SOURCE_VERSION "2015.0"
 #endif
 
 /* B.A.T.M.A.N. parameters */
@@ -92,9 +92,8 @@
 /* numbers of originator to contact for any PUT/GET DHT operation */
 #define BATADV_DAT_CANDIDATES_NUM 3
 
-/**
- * BATADV_TQ_SIMILARITY_THRESHOLD - TQ points that a secondary metric can differ
- *  at most from the primary one in order to be still considered acceptable
+/* BATADV_TQ_SIMILARITY_THRESHOLD - TQ points that a secondary metric can differ
+ * at most from the primary one in order to be still considered acceptable
  */
 #define BATADV_TQ_SIMILARITY_THRESHOLD 50
 
@@ -313,10 +312,10 @@ static inline bool batadv_has_timed_out(unsigned long timestamp,
  *  - when adding 128 - it is neither a predecessor nor a successor,
  *  - after adding more than 127 to the starting value - it is a successor
  */
-#define batadv_seq_before(x, y) ({typeof(x) _d1 = (x); \
-				 typeof(y) _d2 = (y); \
-				 typeof(x) _dummy = (_d1 - _d2); \
-				 (void) (&_d1 == &_d2); \
+#define batadv_seq_before(x, y) ({typeof(x)_d1 = (x); \
+				 typeof(y)_d2 = (y); \
+				 typeof(x)_dummy = (_d1 - _d2); \
+				 (void)(&_d1 == &_d2); \
 				 _dummy > batadv_smallest_signed_int(_dummy); })
 #define batadv_seq_after(x, y) batadv_seq_before(y, x)
 
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index ab6bb2af1d45..b24e4bb64fb5 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -685,11 +685,13 @@ static void batadv_mcast_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv,
 		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.
+	/* If mcast support is being switched off or if this is an initial
+	 * OGM without mcast support then increase the disabled mcast
+	 * node counter.
 	 */
 	} else if (!orig_mcast_enabled &&
-		   orig->capabilities & BATADV_ORIG_CAPA_HAS_MCAST) {
+		   (orig->capabilities & BATADV_ORIG_CAPA_HAS_MCAST ||
+		    !orig_initialized)) {
 		atomic_inc(&bat_priv->mcast.num_disabled);
 		orig->capabilities &= ~BATADV_ORIG_CAPA_HAS_MCAST;
 	}
@@ -738,7 +740,8 @@ 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))
+	if (!(orig->capabilities & BATADV_ORIG_CAPA_HAS_MCAST) &&
+	    orig->capa_initialized & BATADV_ORIG_CAPA_HAS_MCAST)
 		atomic_dec(&bat_priv->mcast.num_disabled);
 
 	batadv_mcast_want_unsnoop_update(bat_priv, orig, BATADV_NO_FLAGS);
diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h
index 73b5d45819c1..3a44ebdb43cb 100644
--- a/net/batman-adv/multicast.h
+++ b/net/batman-adv/multicast.h
@@ -50,7 +50,6 @@ void batadv_mcast_purge_orig(struct batadv_orig_node *orig_node);
 
 static inline void batadv_mcast_mla_update(struct batadv_priv *bat_priv)
 {
-	return;
 }
 
 static inline enum batadv_forw_mode
@@ -67,12 +66,10 @@ static inline int batadv_mcast_init(struct batadv_priv *bat_priv)
 
 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 */
diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index 8d04d174669e..127cc4d7380a 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -133,7 +133,7 @@ int batadv_nc_mesh_init(struct batadv_priv *bat_priv)
 	if (!bat_priv->nc.decoding_hash)
 		goto err;
 
-	batadv_hash_set_lock_class(bat_priv->nc.coding_hash,
+	batadv_hash_set_lock_class(bat_priv->nc.decoding_hash,
 				   &batadv_nc_decoding_hash_lock_class_key);
 
 	INIT_DELAYED_WORK(&bat_priv->nc.work, batadv_nc_worker);
@@ -1212,8 +1212,7 @@ static bool batadv_nc_skb_coding_possible(struct sk_buff *skb,
 {
 	if (BATADV_SKB_CB(skb)->decoded && !batadv_compare_eth(dst, src))
 		return false;
-	else
-		return true;
+	return true;
 }
 
 /**
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 6a484514cd3e..90e805aba379 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -570,9 +570,6 @@ static void batadv_orig_node_free_rcu(struct rcu_head *rcu)
 
 	batadv_frag_purge_orig(orig_node, NULL);
 
-	batadv_tt_global_del_orig(orig_node->bat_priv, orig_node, -1,
-				  "originator timed out");
-
 	if (orig_node->bat_priv->bat_algo_ops->bat_orig_free)
 		orig_node->bat_priv->bat_algo_ops->bat_orig_free(orig_node);
 
@@ -678,6 +675,7 @@ struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv,
 	atomic_set(&orig_node->last_ttvn, 0);
 	orig_node->tt_buff = NULL;
 	orig_node->tt_buff_len = 0;
+	orig_node->last_seen = jiffies;
 	reset_time = jiffies - 1 - msecs_to_jiffies(BATADV_RESET_PROTECTION_MS);
 	orig_node->bcast_seqno_reset = reset_time;
 #ifdef CONFIG_BATMAN_ADV_MCAST
@@ -799,7 +797,6 @@ batadv_purge_orig_ifinfo(struct batadv_priv *bat_priv,
 	return ifinfo_purged;
 }
 
-
 /**
  * batadv_purge_orig_neighbors - purges neighbors from originator
  * @bat_priv: the bat priv with all the soft interface information
@@ -977,6 +974,9 @@ static void _batadv_purge_orig(struct batadv_priv *bat_priv)
 			if (batadv_purge_orig_node(bat_priv, orig_node)) {
 				batadv_gw_node_delete(bat_priv, orig_node);
 				hlist_del_rcu(&orig_node->hash_entry);
+				batadv_tt_global_del_orig(orig_node->bat_priv,
+							  orig_node, -1,
+							  "originator timed out");
 				batadv_orig_node_free_ref(orig_node);
 				continue;
 			}
diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h
index db3a9ed734cb..aa4a43696295 100644
--- a/net/batman-adv/originator.h
+++ b/net/batman-adv/originator.h
@@ -70,7 +70,6 @@ batadv_orig_node_vlan_get(struct batadv_orig_node *orig_node,
 			  unsigned short vid);
 void batadv_orig_node_vlan_free_ref(struct batadv_orig_node_vlan *orig_vlan);
 
-
 /* hashfunction to choose an entry in a hash table of given size
  * hash algorithm from http://en.wikipedia.org/wiki/Hash_table
  */
diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h
index 34e096d2dce1..b81fbbf21a63 100644
--- a/net/batman-adv/packet.h
+++ b/net/batman-adv/packet.h
@@ -198,6 +198,7 @@ struct batadv_bla_claim_dst {
 	uint8_t type;		/* bla_claimframe */
 	__be16 group;		/* group id */
 };
+
 #pragma pack()
 
 /**
@@ -376,7 +377,7 @@ struct batadv_frag_packet {
 	uint8_t reserved:4;
 	uint8_t no:4;
 #else
-#error "unknown bitfield endianess"
+#error "unknown bitfield endianness"
 #endif
 	uint8_t dest[ETH_ALEN];
 	uint8_t orig[ETH_ALEN];
@@ -452,7 +453,7 @@ struct batadv_coded_packet {
  * @src: address of the source
  * @dst: address of the destination
  * @tvlv_len: length of tvlv data following the unicast tvlv header
- * @align: 2 bytes to align the header to a 4 byte boundry
+ * @align: 2 bytes to align the header to a 4 byte boundary
  */
 struct batadv_unicast_tvlv_packet {
 	uint8_t  packet_type;
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index 35f76f2f7824..da83982bf974 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -292,7 +292,6 @@ out:
 	return ret;
 }
 
-
 int batadv_recv_icmp_packet(struct sk_buff *skb,
 			    struct batadv_hard_iface *recv_if)
 {
@@ -443,11 +442,13 @@ batadv_find_router(struct batadv_priv *bat_priv,
 
 	router = batadv_orig_router_get(orig_node, recv_if);
 
+	if (!router)
+		return 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)
+	if (!(recv_if == BATADV_IF_DEFAULT && atomic_read(&bat_priv->bonding)))
 		return router;
 
 	/* bonding: loop through the list of possible routers found
@@ -455,7 +456,7 @@ batadv_find_router(struct batadv_priv *bat_priv,
 	 * 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
+	 * If this can't be found either, return the previously chosen
 	 * router - obviously there are no other candidates.
 	 */
 	rcu_read_lock();
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 5467955eb27c..5ec31d7de24f 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -36,7 +36,6 @@
 #include "bridge_loop_avoidance.h"
 #include "network-coding.h"
 
-
 static int batadv_get_settings(struct net_device *dev, struct ethtool_cmd *cmd);
 static void batadv_get_drvinfo(struct net_device *dev,
 			       struct ethtool_drvinfo *info);
diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c
index f40cb0436eba..a75dc12f96f8 100644
--- a/net/batman-adv/sysfs.c
+++ b/net/batman-adv/sysfs.c
@@ -151,7 +151,6 @@ ssize_t batadv_show_##_name(struct kobject *kobj,			\
 	static BATADV_ATTR(_name, _mode, batadv_show_##_name,		\
 			   batadv_store_##_name)
 
-
 #define BATADV_ATTR_SIF_STORE_UINT(_name, _min, _max, _post_func)	\
 ssize_t batadv_store_##_name(struct kobject *kobj,			\
 			     struct attribute *attr, char *buff,	\
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 5f59e7f899a0..07b263a437d1 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -1780,7 +1780,6 @@ static void batadv_tt_global_del(struct batadv_priv *bat_priv,
 		batadv_tt_global_del_roaming(bat_priv, tt_global_entry,
 					     orig_node, message);
 
-
 out:
 	if (tt_global_entry)
 		batadv_tt_global_entry_free_ref(tt_global_entry);
@@ -2769,9 +2768,8 @@ static bool batadv_send_tt_response(struct batadv_priv *bat_priv,
 {
 	if (batadv_is_my_mac(bat_priv, req_dst))
 		return batadv_send_my_tt_response(bat_priv, tt_data, req_src);
-	else
-		return batadv_send_other_tt_response(bat_priv, tt_data,
-						     req_src, req_dst);
+	return batadv_send_other_tt_response(bat_priv, tt_data, req_src,
+					     req_dst);
 }
 
 static void _batadv_tt_update_changes(struct batadv_priv *bat_priv,
@@ -2854,7 +2852,7 @@ static void batadv_tt_update_changes(struct batadv_priv *bat_priv,
 /**
  * batadv_is_my_client - check if a client is served by the local node
  * @bat_priv: the bat priv with all the soft interface information
- * @addr: the mac adress of the client to check
+ * @addr: the mac address of the client to check
  * @vid: VLAN identifier
  *
  * Returns true if the client is served by this node, false otherwise.
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index 8854c05622a9..9398c3fb4174 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -199,7 +199,6 @@ 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
  * @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
@@ -244,7 +243,6 @@ struct batadv_orig_bat_iv {
  */
 struct batadv_orig_node {
 	uint8_t orig[ETH_ALEN];
-	uint8_t primary_addr[ETH_ALEN];
 	struct hlist_head ifinfo_list;
 	struct batadv_orig_ifinfo *last_bonding_candidate;
 #ifdef CONFIG_BATMAN_ADV_DAT
@@ -970,7 +968,7 @@ struct batadv_tt_orig_list_entry {
 };
 
 /**
- * struct batadv_tt_change_node - structure for tt changes occured
+ * struct batadv_tt_change_node - structure for tt changes occurred
  * @list: list node for batadv_priv_tt::changes_list
  * @change: holds the actual translation table diff data
  */
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index c2e0d14433df..1742b849fcff 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -31,7 +31,7 @@
 
 #define VERSION "0.1"
 
-static struct dentry *lowpan_psm_debugfs;
+static struct dentry *lowpan_enable_debugfs;
 static struct dentry *lowpan_control_debugfs;
 
 #define IFACE_NAME_TEMPLATE "bt%d"
@@ -53,13 +53,9 @@ struct skb_cb {
  * The list contains struct lowpan_dev elements.
  */
 static LIST_HEAD(bt_6lowpan_devices);
-static DEFINE_RWLOCK(devices_lock);
+static DEFINE_SPINLOCK(devices_lock);
 
-/* If psm is set to 0 (default value), then 6lowpan is disabled.
- * Other values are used to indicate a Protocol Service Multiplexer
- * value for 6lowpan.
- */
-static u16 psm_6lowpan;
+static bool enable_6lowpan;
 
 /* We are listening incoming connections via this channel
  */
@@ -67,6 +63,7 @@ static struct l2cap_chan *listen_chan;
 
 struct lowpan_peer {
 	struct list_head list;
+	struct rcu_head rcu;
 	struct l2cap_chan *chan;
 
 	/* peer addresses in various formats */
@@ -93,13 +90,14 @@ static inline struct lowpan_dev *lowpan_dev(const struct net_device *netdev)
 
 static inline void peer_add(struct lowpan_dev *dev, struct lowpan_peer *peer)
 {
-	list_add(&peer->list, &dev->peers);
+	list_add_rcu(&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);
+	list_del_rcu(&peer->list);
+	kfree_rcu(peer, rcu);
 
 	module_put(THIS_MODULE);
 
@@ -114,31 +112,37 @@ static inline bool peer_del(struct lowpan_dev *dev, struct lowpan_peer *peer)
 static inline struct lowpan_peer *peer_lookup_ba(struct lowpan_dev *dev,
 						 bdaddr_t *ba, __u8 type)
 {
-	struct lowpan_peer *peer, *tmp;
+	struct lowpan_peer *peer;
 
 	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) {
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(peer, &dev->peers, list) {
 		BT_DBG("dst addr %pMR dst type %d",
 		       &peer->chan->dst, peer->chan->dst_type);
 
 		if (bacmp(&peer->chan->dst, ba))
 			continue;
 
-		if (type == peer->chan->dst_type)
+		if (type == peer->chan->dst_type) {
+			rcu_read_unlock();
 			return peer;
+		}
 	}
 
+	rcu_read_unlock();
+
 	return NULL;
 }
 
-static inline struct lowpan_peer *peer_lookup_chan(struct lowpan_dev *dev,
-						   struct l2cap_chan *chan)
+static inline struct lowpan_peer *__peer_lookup_chan(struct lowpan_dev *dev,
+						     struct l2cap_chan *chan)
 {
-	struct lowpan_peer *peer, *tmp;
+	struct lowpan_peer *peer;
 
-	list_for_each_entry_safe(peer, tmp, &dev->peers, list) {
+	list_for_each_entry_rcu(peer, &dev->peers, list) {
 		if (peer->chan == chan)
 			return peer;
 	}
@@ -146,12 +150,12 @@ static inline struct lowpan_peer *peer_lookup_chan(struct lowpan_dev *dev,
 	return NULL;
 }
 
-static inline struct lowpan_peer *peer_lookup_conn(struct lowpan_dev *dev,
-						   struct l2cap_conn *conn)
+static inline struct lowpan_peer *__peer_lookup_conn(struct lowpan_dev *dev,
+						     struct l2cap_conn *conn)
 {
-	struct lowpan_peer *peer, *tmp;
+	struct lowpan_peer *peer;
 
-	list_for_each_entry_safe(peer, tmp, &dev->peers, list) {
+	list_for_each_entry_rcu(peer, &dev->peers, list) {
 		if (peer->chan->conn == conn)
 			return peer;
 	}
@@ -163,7 +167,7 @@ static inline struct lowpan_peer *peer_lookup_dst(struct lowpan_dev *dev,
 						  struct in6_addr *daddr,
 						  struct sk_buff *skb)
 {
-	struct lowpan_peer *peer, *tmp;
+	struct lowpan_peer *peer;
 	struct in6_addr *nexthop;
 	struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
 	int count = atomic_read(&dev->peer_count);
@@ -174,9 +178,13 @@ static inline struct lowpan_peer *peer_lookup_dst(struct lowpan_dev *dev,
 	 * send the packet. If only one peer exists, then we can send the
 	 * packet right away.
 	 */
-	if (count == 1)
-		return list_first_entry(&dev->peers, struct lowpan_peer,
-					list);
+	if (count == 1) {
+		rcu_read_lock();
+		peer = list_first_or_null_rcu(&dev->peers, struct lowpan_peer,
+					      list);
+		rcu_read_unlock();
+		return peer;
+	}
 
 	if (!rt) {
 		nexthop = &lowpan_cb(skb)->gw;
@@ -195,53 +203,57 @@ static inline struct lowpan_peer *peer_lookup_dst(struct lowpan_dev *dev,
 
 	BT_DBG("gw %pI6c", nexthop);
 
-	list_for_each_entry_safe(peer, tmp, &dev->peers, list) {
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(peer, &dev->peers, list) {
 		BT_DBG("dst addr %pMR dst type %d ip %pI6c",
 		       &peer->chan->dst, peer->chan->dst_type,
 		       &peer->peer_addr);
 
-		if (!ipv6_addr_cmp(&peer->peer_addr, nexthop))
+		if (!ipv6_addr_cmp(&peer->peer_addr, nexthop)) {
+			rcu_read_unlock();
 			return peer;
+		}
 	}
 
+	rcu_read_unlock();
+
 	return NULL;
 }
 
 static struct lowpan_peer *lookup_peer(struct l2cap_conn *conn)
 {
-	struct lowpan_dev *entry, *tmp;
+	struct lowpan_dev *entry;
 	struct lowpan_peer *peer = NULL;
-	unsigned long flags;
 
-	read_lock_irqsave(&devices_lock, flags);
+	rcu_read_lock();
 
-	list_for_each_entry_safe(entry, tmp, &bt_6lowpan_devices, list) {
-		peer = peer_lookup_conn(entry, conn);
+	list_for_each_entry_rcu(entry, &bt_6lowpan_devices, list) {
+		peer = __peer_lookup_conn(entry, conn);
 		if (peer)
 			break;
 	}
 
-	read_unlock_irqrestore(&devices_lock, flags);
+	rcu_read_unlock();
 
 	return peer;
 }
 
 static struct lowpan_dev *lookup_dev(struct l2cap_conn *conn)
 {
-	struct lowpan_dev *entry, *tmp;
+	struct lowpan_dev *entry;
 	struct lowpan_dev *dev = NULL;
-	unsigned long flags;
 
-	read_lock_irqsave(&devices_lock, flags);
+	rcu_read_lock();
 
-	list_for_each_entry_safe(entry, tmp, &bt_6lowpan_devices, list) {
+	list_for_each_entry_rcu(entry, &bt_6lowpan_devices, list) {
 		if (conn->hcon->hdev == entry->hdev) {
 			dev = entry;
 			break;
 		}
 	}
 
-	read_unlock_irqrestore(&devices_lock, flags);
+	rcu_read_unlock();
 
 	return dev;
 }
@@ -249,59 +261,49 @@ static struct lowpan_dev *lookup_dev(struct l2cap_conn *conn)
 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);
-	if (ret < 0) {
-		BT_DBG("receive skb %d", ret);
 		return NET_RX_DROP;
-	}
 
-	return ret;
+	return netif_rx(skb_cp);
 }
 
-static int process_data(struct sk_buff *skb, struct net_device *netdev,
-			struct l2cap_chan *chan)
+static int iphc_decompress(struct sk_buff *skb, struct net_device *netdev,
+			   struct l2cap_chan *chan)
 {
 	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_chan(dev, chan);
-	read_unlock_irqrestore(&devices_lock, flags);
+	rcu_read_lock();
+	peer = __peer_lookup_chan(dev, chan);
+	rcu_read_unlock();
 	if (!peer)
-		goto drop;
+		return -EINVAL;
 
 	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;
+		return -EINVAL;
 
 	if (lowpan_fetch_skb_u8(skb, &iphc0))
-		goto drop;
+		return -EINVAL;
 
 	if (lowpan_fetch_skb_u8(skb, &iphc1))
-		goto drop;
+		return -EINVAL;
 
-	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);
+	return lowpan_header_decompress(skb, netdev,
+					saddr, IEEE802154_ADDR_LONG,
+					EUI64_ADDR_LEN, daddr,
+					IEEE802154_ADDR_LONG, EUI64_ADDR_LEN,
+					iphc0, iphc1);
 
-drop:
-	kfree_skb(skb);
-	return -EINVAL;
 }
 
 static int recv_pkt(struct sk_buff *skb, struct net_device *dev,
@@ -316,6 +318,10 @@ static int recv_pkt(struct sk_buff *skb, struct net_device *dev,
 	if (dev->type != ARPHRD_6LOWPAN)
 		goto drop;
 
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (!skb)
+		goto drop;
+
 	/* check that it's our buffer */
 	if (skb->data[0] == LOWPAN_DISPATCH_IPV6) {
 		/* Copy the packet so that the IPv6 header is
@@ -340,8 +346,8 @@ static int recv_pkt(struct sk_buff *skb, struct net_device *dev,
 		dev->stats.rx_bytes += skb->len;
 		dev->stats.rx_packets++;
 
-		kfree_skb(local_skb);
-		kfree_skb(skb);
+		consume_skb(local_skb);
+		consume_skb(skb);
 	} else {
 		switch (skb->data[0] & 0xe0) {
 		case LOWPAN_DISPATCH_IPHC:	/* ipv6 datagram */
@@ -349,14 +355,27 @@ static int recv_pkt(struct sk_buff *skb, struct net_device *dev,
 			if (!local_skb)
 				goto drop;
 
-			ret = process_data(local_skb, dev, chan);
-			if (ret != NET_RX_SUCCESS)
+			ret = iphc_decompress(local_skb, dev, chan);
+			if (ret < 0) {
+				kfree_skb(local_skb);
+				goto drop;
+			}
+
+			local_skb->protocol = htons(ETH_P_IPV6);
+			local_skb->pkt_type = PACKET_HOST;
+			local_skb->dev = dev;
+
+			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(skb);
+			consume_skb(local_skb);
+			consume_skb(skb);
 			break;
 		default:
 			break;
@@ -367,7 +386,6 @@ static int recv_pkt(struct sk_buff *skb, struct net_device *dev,
 
 drop:
 	dev->stats.rx_dropped++;
-	kfree_skb(skb);
 	return NET_RX_DROP;
 }
 
@@ -443,7 +461,6 @@ static int setup_header(struct sk_buff *skb, struct net_device *netdev,
 	if (ipv6_addr_is_multicast(&ipv6_daddr)) {
 		lowpan_cb(skb)->chan = NULL;
 	} else {
-		unsigned long flags;
 		u8 addr_type;
 
 		/* Get destination BT device from skb.
@@ -454,19 +471,14 @@ static int setup_header(struct sk_buff *skb, struct net_device *netdev,
 		BT_DBG("dest addr %pMR type %d IP %pI6c", &addr,
 		       addr_type, &ipv6_daddr);
 
-		read_lock_irqsave(&devices_lock, flags);
 		peer = peer_lookup_ba(dev, &addr, addr_type);
-		read_unlock_irqrestore(&devices_lock, flags);
-
 		if (!peer) {
 			/* The packet might be sent to 6lowpan interface
 			 * because of routing (either via default route
 			 * or user set route) so get peer according to
 			 * the destination address.
 			 */
-			read_lock_irqsave(&devices_lock, flags);
 			peer = peer_lookup_dst(dev, &ipv6_daddr, skb);
-			read_unlock_irqrestore(&devices_lock, flags);
 			if (!peer) {
 				BT_DBG("no such peer %pMR found", &addr);
 				return -ENOENT;
@@ -520,12 +532,12 @@ static int send_pkt(struct l2cap_chan *chan, struct sk_buff *skb,
 	 */
 	chan->data = skb;
 
-	memset(&msg, 0, sizeof(msg));
-	msg.msg_iov = (struct iovec *) &iv;
-	msg.msg_iovlen = 1;
 	iv.iov_base = skb->data;
 	iv.iov_len = skb->len;
 
+	memset(&msg, 0, sizeof(msg));
+	iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &iv, 1, skb->len);
+
 	err = l2cap_chan_send(chan, &msg, skb->len);
 	if (err > 0) {
 		netdev->stats.tx_bytes += err;
@@ -549,14 +561,13 @@ static int send_pkt(struct l2cap_chan *chan, struct sk_buff *skb,
 static int send_mcast_pkt(struct sk_buff *skb, struct net_device *netdev)
 {
 	struct sk_buff *local_skb;
-	struct lowpan_dev *entry, *tmp;
-	unsigned long flags;
+	struct lowpan_dev *entry;
 	int err = 0;
 
-	read_lock_irqsave(&devices_lock, flags);
+	rcu_read_lock();
 
-	list_for_each_entry_safe(entry, tmp, &bt_6lowpan_devices, list) {
-		struct lowpan_peer *pentry, *ptmp;
+	list_for_each_entry_rcu(entry, &bt_6lowpan_devices, list) {
+		struct lowpan_peer *pentry;
 		struct lowpan_dev *dev;
 
 		if (entry->netdev != netdev)
@@ -564,7 +575,7 @@ static int send_mcast_pkt(struct sk_buff *skb, struct net_device *netdev)
 
 		dev = lowpan_dev(entry->netdev);
 
-		list_for_each_entry_safe(pentry, ptmp, &dev->peers, list) {
+		list_for_each_entry_rcu(pentry, &dev->peers, list) {
 			int ret;
 
 			local_skb = skb_clone(skb, GFP_ATOMIC);
@@ -581,7 +592,7 @@ static int send_mcast_pkt(struct sk_buff *skb, struct net_device *netdev)
 		}
 	}
 
-	read_unlock_irqrestore(&devices_lock, flags);
+	rcu_read_unlock();
 
 	return err;
 }
@@ -591,17 +602,13 @@ static netdev_tx_t bt_xmit(struct sk_buff *skb, struct net_device *netdev)
 	int err = 0;
 	bdaddr_t addr;
 	u8 addr_type;
-	struct sk_buff *tmpskb;
 
 	/* We must take a copy of the skb before we modify/replace the ipv6
 	 * header as the header could be used elsewhere
 	 */
-	tmpskb = skb_unshare(skb, GFP_ATOMIC);
-	if (!tmpskb) {
-		kfree_skb(skb);
+	skb = skb_unshare(skb, GFP_ATOMIC);
+	if (!skb)
 		return NET_XMIT_DROP;
-	}
-	skb = tmpskb;
 
 	/* Return values from setup_header()
 	 *  <0 - error, packet is dropped
@@ -638,7 +645,26 @@ static netdev_tx_t bt_xmit(struct sk_buff *skb, struct net_device *netdev)
 	return err < 0 ? NET_XMIT_DROP : err;
 }
 
+static struct lock_class_key bt_tx_busylock;
+static struct lock_class_key bt_netdev_xmit_lock_key;
+
+static void bt_set_lockdep_class_one(struct net_device *dev,
+				     struct netdev_queue *txq,
+				     void *_unused)
+{
+	lockdep_set_class(&txq->_xmit_lock, &bt_netdev_xmit_lock_key);
+}
+
+static int bt_dev_init(struct net_device *dev)
+{
+	netdev_for_each_tx_queue(dev, bt_set_lockdep_class_one, NULL);
+	dev->qdisc_tx_busylock = &bt_tx_busylock;
+
+	return 0;
+}
+
 static const struct net_device_ops netdev_ops = {
+	.ndo_init		= bt_dev_init,
 	.ndo_start_xmit		= bt_xmit,
 };
 
@@ -731,7 +757,7 @@ static bool is_bt_6lowpan(struct hci_conn *hcon)
 	if (hcon->type != LE_LINK)
 		return false;
 
-	if (!psm_6lowpan)
+	if (!enable_6lowpan)
 		return false;
 
 	return true;
@@ -783,7 +809,6 @@ static struct l2cap_chan *add_peer_chan(struct l2cap_chan *chan,
 					struct lowpan_dev *dev)
 {
 	struct lowpan_peer *peer;
-	unsigned long flags;
 
 	peer = kzalloc(sizeof(*peer), GFP_ATOMIC);
 	if (!peer)
@@ -806,10 +831,10 @@ static struct l2cap_chan *add_peer_chan(struct l2cap_chan *chan,
 	 */
 	set_ip_addr_bits(chan->dst_type, (u8 *)&peer->peer_addr.s6_addr + 8);
 
-	write_lock_irqsave(&devices_lock, flags);
+	spin_lock(&devices_lock);
 	INIT_LIST_HEAD(&peer->list);
 	peer_add(dev, peer);
-	write_unlock_irqrestore(&devices_lock, flags);
+	spin_unlock(&devices_lock);
 
 	/* Notifying peers about us needs to be done without locks held */
 	INIT_DELAYED_WORK(&dev->notify_peers, do_notify_peers);
@@ -822,7 +847,6 @@ static int setup_netdev(struct l2cap_chan *chan, struct lowpan_dev **dev)
 {
 	struct net_device *netdev;
 	int err = 0;
-	unsigned long flags;
 
 	netdev = alloc_netdev(sizeof(struct lowpan_dev), IFACE_NAME_TEMPLATE,
 			      NET_NAME_UNKNOWN, netdev_setup);
@@ -852,10 +876,10 @@ static int setup_netdev(struct l2cap_chan *chan, struct lowpan_dev **dev)
 	(*dev)->hdev = chan->conn->hcon->hdev;
 	INIT_LIST_HEAD(&(*dev)->peers);
 
-	write_lock_irqsave(&devices_lock, flags);
+	spin_lock(&devices_lock);
 	INIT_LIST_HEAD(&(*dev)->list);
-	list_add(&(*dev)->list, &bt_6lowpan_devices);
-	write_unlock_irqrestore(&devices_lock, flags);
+	list_add_rcu(&(*dev)->list, &bt_6lowpan_devices);
+	spin_unlock(&devices_lock);
 
 	return 0;
 
@@ -909,11 +933,10 @@ static void delete_netdev(struct work_struct *work)
 
 static void chan_close_cb(struct l2cap_chan *chan)
 {
-	struct lowpan_dev *entry, *tmp;
+	struct lowpan_dev *entry;
 	struct lowpan_dev *dev = NULL;
 	struct lowpan_peer *peer;
 	int err = -ENOENT;
-	unsigned long flags;
 	bool last = false, removed = true;
 
 	BT_DBG("chan %p conn %p", chan, chan->conn);
@@ -928,11 +951,11 @@ static void chan_close_cb(struct l2cap_chan *chan)
 		removed = false;
 	}
 
-	write_lock_irqsave(&devices_lock, flags);
+	spin_lock(&devices_lock);
 
-	list_for_each_entry_safe(entry, tmp, &bt_6lowpan_devices, list) {
+	list_for_each_entry_rcu(entry, &bt_6lowpan_devices, list) {
 		dev = lowpan_dev(entry->netdev);
-		peer = peer_lookup_chan(dev, chan);
+		peer = __peer_lookup_chan(dev, chan);
 		if (peer) {
 			last = peer_del(dev, peer);
 			err = 0;
@@ -943,13 +966,12 @@ static void chan_close_cb(struct l2cap_chan *chan)
 			       atomic_read(&chan->kref.refcount));
 
 			l2cap_chan_put(chan);
-			kfree(peer);
 			break;
 		}
 	}
 
 	if (!err && last && dev && !atomic_read(&dev->peer_count)) {
-		write_unlock_irqrestore(&devices_lock, flags);
+		spin_unlock(&devices_lock);
 
 		cancel_delayed_work_sync(&dev->notify_peers);
 
@@ -960,7 +982,7 @@ static void chan_close_cb(struct l2cap_chan *chan)
 			schedule_work(&entry->delete_netdev);
 		}
 	} else {
-		write_unlock_irqrestore(&devices_lock, flags);
+		spin_unlock(&devices_lock);
 	}
 
 	return;
@@ -1023,7 +1045,6 @@ static const struct l2cap_ops bt_6lowpan_chan_ops = {
 	.suspend		= chan_suspend_cb,
 	.get_sndtimeo		= chan_get_sndtimeo_cb,
 	.alloc_skb		= chan_alloc_skb_cb,
-	.memcpy_fromiovec	= l2cap_chan_no_memcpy_fromiovec,
 
 	.teardown		= l2cap_chan_no_teardown,
 	.defer			= l2cap_chan_no_defer,
@@ -1060,7 +1081,7 @@ static int bt_6lowpan_connect(bdaddr_t *addr, u8 dst_type)
 	if (!pchan)
 		return -EINVAL;
 
-	err = l2cap_chan_connect(pchan, cpu_to_le16(psm_6lowpan), 0,
+	err = l2cap_chan_connect(pchan, cpu_to_le16(L2CAP_PSM_IPSP), 0,
 				 addr, dst_type);
 
 	BT_DBG("chan %p err %d", pchan, err);
@@ -1093,7 +1114,7 @@ static struct l2cap_chan *bt_6lowpan_listen(void)
 	struct l2cap_chan *pchan;
 	int err;
 
-	if (psm_6lowpan == 0)
+	if (!enable_6lowpan)
 		return NULL;
 
 	pchan = chan_get();
@@ -1103,10 +1124,11 @@ static struct l2cap_chan *bt_6lowpan_listen(void)
 	pchan->state = BT_LISTEN;
 	pchan->src_type = BDADDR_LE_PUBLIC;
 
-	BT_DBG("psm 0x%04x chan %p src type %d", psm_6lowpan, pchan,
-	       pchan->src_type);
+	atomic_set(&pchan->nesting, L2CAP_NESTING_PARENT);
 
-	err = l2cap_add_psm(pchan, addr, cpu_to_le16(psm_6lowpan));
+	BT_DBG("chan %p src type %d", pchan, pchan->src_type);
+
+	err = l2cap_add_psm(pchan, addr, cpu_to_le16(L2CAP_PSM_IPSP));
 	if (err) {
 		l2cap_chan_put(pchan);
 		BT_ERR("psm cannot be added err %d", err);
@@ -1152,10 +1174,9 @@ static int get_l2cap_conn(char *buf, bdaddr_t *addr, u8 *addr_type,
 
 static void disconnect_all_peers(void)
 {
-	struct lowpan_dev *entry, *tmp_dev;
+	struct lowpan_dev *entry;
 	struct lowpan_peer *peer, *tmp_peer, *new_peer;
 	struct list_head peers;
-	unsigned long flags;
 
 	INIT_LIST_HEAD(&peers);
 
@@ -1164,10 +1185,10 @@ static void disconnect_all_peers(void)
 	 * with the same list at the same time.
 	 */
 
-	read_lock_irqsave(&devices_lock, flags);
+	rcu_read_lock();
 
-	list_for_each_entry_safe(entry, tmp_dev, &bt_6lowpan_devices, list) {
-		list_for_each_entry_safe(peer, tmp_peer, &entry->peers, list) {
+	list_for_each_entry_rcu(entry, &bt_6lowpan_devices, list) {
+		list_for_each_entry_rcu(peer, &entry->peers, list) {
 			new_peer = kmalloc(sizeof(*new_peer), GFP_ATOMIC);
 			if (!new_peer)
 				break;
@@ -1179,26 +1200,37 @@ static void disconnect_all_peers(void)
 		}
 	}
 
-	read_unlock_irqrestore(&devices_lock, flags);
+	rcu_read_unlock();
 
+	spin_lock(&devices_lock);
 	list_for_each_entry_safe(peer, tmp_peer, &peers, list) {
 		l2cap_chan_close(peer->chan, ENOENT);
-		kfree(peer);
+
+		list_del_rcu(&peer->list);
+		kfree_rcu(peer, rcu);
+
+		module_put(THIS_MODULE);
 	}
+	spin_unlock(&devices_lock);
 }
 
-static int lowpan_psm_set(void *data, u64 val)
+struct set_enable {
+	struct work_struct work;
+	bool flag;
+};
+
+static void do_enable_set(struct work_struct *work)
 {
-	u16 psm;
+	struct set_enable *set_enable = container_of(work,
+						     struct set_enable, work);
 
-	psm = val;
-	if (psm == 0 || psm_6lowpan != psm)
+	if (!set_enable->flag || enable_6lowpan != set_enable->flag)
 		/* Disconnect existing connections if 6lowpan is
-		 * disabled (psm = 0), or if psm changes.
+		 * disabled
 		 */
 		disconnect_all_peers();
 
-	psm_6lowpan = psm;
+	enable_6lowpan = set_enable->flag;
 
 	if (listen_chan) {
 		l2cap_chan_close(listen_chan, 0);
@@ -1207,17 +1239,33 @@ static int lowpan_psm_set(void *data, u64 val)
 
 	listen_chan = bt_6lowpan_listen();
 
+	kfree(set_enable);
+}
+
+static int lowpan_enable_set(void *data, u64 val)
+{
+	struct set_enable *set_enable;
+
+	set_enable = kzalloc(sizeof(*set_enable), GFP_KERNEL);
+	if (!set_enable)
+		return -ENOMEM;
+
+	set_enable->flag = !!val;
+	INIT_WORK(&set_enable->work, do_enable_set);
+
+	schedule_work(&set_enable->work);
+
 	return 0;
 }
 
-static int lowpan_psm_get(void *data, u64 *val)
+static int lowpan_enable_get(void *data, u64 *val)
 {
-	*val = psm_6lowpan;
+	*val = enable_6lowpan;
 	return 0;
 }
 
-DEFINE_SIMPLE_ATTRIBUTE(lowpan_psm_fops, lowpan_psm_get,
-			lowpan_psm_set, "%llu\n");
+DEFINE_SIMPLE_ATTRIBUTE(lowpan_enable_fops, lowpan_enable_get,
+			lowpan_enable_set, "%llu\n");
 
 static ssize_t lowpan_control_write(struct file *fp,
 				    const char __user *user_buffer,
@@ -1288,19 +1336,18 @@ static ssize_t lowpan_control_write(struct file *fp,
 
 static int lowpan_control_show(struct seq_file *f, void *ptr)
 {
-	struct lowpan_dev *entry, *tmp_dev;
-	struct lowpan_peer *peer, *tmp_peer;
-	unsigned long flags;
+	struct lowpan_dev *entry;
+	struct lowpan_peer *peer;
 
-	read_lock_irqsave(&devices_lock, flags);
+	spin_lock(&devices_lock);
 
-	list_for_each_entry_safe(entry, tmp_dev, &bt_6lowpan_devices, list) {
-		list_for_each_entry_safe(peer, tmp_peer, &entry->peers, list)
+	list_for_each_entry(entry, &bt_6lowpan_devices, list) {
+		list_for_each_entry(peer, &entry->peers, list)
 			seq_printf(f, "%pMR (type %u)\n",
 				   &peer->chan->dst, peer->chan->dst_type);
 	}
 
-	read_unlock_irqrestore(&devices_lock, flags);
+	spin_unlock(&devices_lock);
 
 	return 0;
 }
@@ -1322,7 +1369,6 @@ static void disconnect_devices(void)
 {
 	struct lowpan_dev *entry, *tmp, *new_dev;
 	struct list_head devices;
-	unsigned long flags;
 
 	INIT_LIST_HEAD(&devices);
 
@@ -1331,9 +1377,9 @@ static void disconnect_devices(void)
 	 * devices list.
 	 */
 
-	read_lock_irqsave(&devices_lock, flags);
+	rcu_read_lock();
 
-	list_for_each_entry_safe(entry, tmp, &bt_6lowpan_devices, list) {
+	list_for_each_entry_rcu(entry, &bt_6lowpan_devices, list) {
 		new_dev = kmalloc(sizeof(*new_dev), GFP_ATOMIC);
 		if (!new_dev)
 			break;
@@ -1341,10 +1387,10 @@ static void disconnect_devices(void)
 		new_dev->netdev = entry->netdev;
 		INIT_LIST_HEAD(&new_dev->list);
 
-		list_add(&new_dev->list, &devices);
+		list_add_rcu(&new_dev->list, &devices);
 	}
 
-	read_unlock_irqrestore(&devices_lock, flags);
+	rcu_read_unlock();
 
 	list_for_each_entry_safe(entry, tmp, &devices, list) {
 		ifdown(entry->netdev);
@@ -1359,17 +1405,15 @@ 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;
+	struct lowpan_dev *entry;
 
 	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) {
+		spin_lock(&devices_lock);
+		list_for_each_entry(entry, &bt_6lowpan_devices, list) {
 			if (entry->netdev == netdev) {
 				BT_DBG("Unregistered netdev %s %p",
 				       netdev->name, netdev);
@@ -1378,7 +1422,7 @@ static int device_event(struct notifier_block *unused,
 				break;
 			}
 		}
-		write_unlock_irqrestore(&devices_lock, flags);
+		spin_unlock(&devices_lock);
 		break;
 	}
 
@@ -1391,9 +1435,9 @@ static struct notifier_block bt_6lowpan_dev_notifier = {
 
 static int __init bt_6lowpan_init(void)
 {
-	lowpan_psm_debugfs = debugfs_create_file("6lowpan_psm", 0644,
-						 bt_debugfs, NULL,
-						 &lowpan_psm_fops);
+	lowpan_enable_debugfs = debugfs_create_file("6lowpan_enable", 0644,
+						    bt_debugfs, NULL,
+						    &lowpan_enable_fops);
 	lowpan_control_debugfs = debugfs_create_file("6lowpan_control", 0644,
 						     bt_debugfs, NULL,
 						     &lowpan_control_fops);
@@ -1403,7 +1447,7 @@ static int __init bt_6lowpan_init(void)
 
 static void __exit bt_6lowpan_exit(void)
 {
-	debugfs_remove(lowpan_psm_debugfs);
+	debugfs_remove(lowpan_enable_debugfs);
 	debugfs_remove(lowpan_control_debugfs);
 
 	if (listen_chan) {
diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig
index 600fb29288f4..b8c794b87523 100644
--- a/net/bluetooth/Kconfig
+++ b/net/bluetooth/Kconfig
@@ -10,6 +10,7 @@ menuconfig BT
 	select CRYPTO
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_AES
+	select CRYPTO_CMAC
 	select CRYPTO_ECB
 	select CRYPTO_SHA256
 	help
@@ -39,11 +40,10 @@ menuconfig BT
 	  to Bluetooth kernel modules are provided in the BlueZ packages.  For
 	  more information, see <http://www.bluez.org/>.
 
-config BT_6LOWPAN
-	tristate "Bluetooth 6LoWPAN support"
-	depends on BT && 6LOWPAN
-	help
-	  IPv6 compression over Bluetooth Low Energy.
+config BT_BREDR
+	bool "Bluetooth Classic (BR/EDR) features"
+	depends on BT
+	default y
 
 source "net/bluetooth/rfcomm/Kconfig"
 
@@ -53,4 +53,50 @@ source "net/bluetooth/cmtp/Kconfig"
 
 source "net/bluetooth/hidp/Kconfig"
 
+config BT_LE
+	bool "Bluetooth Low Energy (LE) features"
+	depends on BT
+	default y
+
+config BT_6LOWPAN
+	tristate "Bluetooth 6LoWPAN support"
+	depends on BT_LE && 6LOWPAN
+	help
+	  IPv6 compression over Bluetooth Low Energy.
+
+config BT_SELFTEST
+	bool "Bluetooth self testing support"
+	depends on BT && DEBUG_KERNEL
+	help
+	  Run self tests when initializing the Bluetooth subsystem.  This
+	  is a developer option and can cause significant delay when booting
+	  the system.
+
+	  When the Bluetooth subsystem is built as module, then the test
+	  cases are run first thing at module load time.  When the Bluetooth
+	  subsystem is compiled into the kernel image, then the test cases
+	  are run late in the initcall hierarchy.
+
+config BT_SELFTEST_ECDH
+	bool "ECDH test cases"
+	depends on BT_LE && BT_SELFTEST
+	help
+	  Run test cases for ECDH cryptographic functionality used by the
+	  Bluetooth Low Energy Secure Connections feature.
+
+config BT_SELFTEST_SMP
+	bool "SMP test cases"
+	depends on BT_LE && BT_SELFTEST
+	help
+	  Run test cases for SMP cryptographic functionality, including both
+	  legacy SMP as well as the Secure Connections features.
+
+config BT_DEBUGFS
+	bool "Export Bluetooth internals in debugfs"
+	depends on BT && DEBUG_FS
+	default y
+	help
+	  Provide extensive information about internal Bluetooth states
+	  in debugfs.
+
 source "drivers/bluetooth/Kconfig"
diff --git a/net/bluetooth/Makefile b/net/bluetooth/Makefile
index 886e9aa3ecf1..9a8ea232d28f 100644
--- a/net/bluetooth/Makefile
+++ b/net/bluetooth/Makefile
@@ -13,6 +13,9 @@ bluetooth_6lowpan-y := 6lowpan.o
 
 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
+	a2mp.o amp.o ecc.o hci_request.o mgmt_util.o
+
+bluetooth-$(CONFIG_BT_DEBUGFS) += hci_debugfs.o
+bluetooth-$(CONFIG_BT_SELFTEST) += selftest.o
 
 subdir-ccflags-y += -D__CHECK_ENDIAN__
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index 5dcade511fdb..5a04eb1a7e57 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -19,9 +19,11 @@
 #include "a2mp.h"
 #include "amp.h"
 
+#define A2MP_FEAT_EXT	0x8000
+
 /* Global AMP Manager list */
-LIST_HEAD(amp_mgr_list);
-DEFINE_MUTEX(amp_mgr_list_lock);
+static LIST_HEAD(amp_mgr_list);
+static DEFINE_MUTEX(amp_mgr_list_lock);
 
 /* A2MP build & send command helper functions */
 static struct a2mp_cmd *__a2mp_build(u8 code, u8 ident, u16 len, void *data)
@@ -43,7 +45,7 @@ static struct a2mp_cmd *__a2mp_build(u8 code, u8 ident, u16 len, void *data)
 	return cmd;
 }
 
-void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *data)
+static void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *data)
 {
 	struct l2cap_chan *chan = mgr->a2mp_chan;
 	struct a2mp_cmd *cmd;
@@ -60,15 +62,14 @@ void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *data)
 
 	memset(&msg, 0, sizeof(msg));
 
-	msg.msg_iov = (struct iovec *) &iv;
-	msg.msg_iovlen = 1;
+	iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &iv, 1, total_len);
 
 	l2cap_chan_send(chan, &msg, total_len);
 
 	kfree(cmd);
 }
 
-u8 __next_ident(struct amp_mgr *mgr)
+static u8 __next_ident(struct amp_mgr *mgr)
 {
 	if (++mgr->ident == 0)
 		mgr->ident = 1;
@@ -76,6 +77,23 @@ u8 __next_ident(struct amp_mgr *mgr)
 	return mgr->ident;
 }
 
+static struct amp_mgr *amp_mgr_lookup_by_state(u8 state)
+{
+	struct amp_mgr *mgr;
+
+	mutex_lock(&amp_mgr_list_lock);
+	list_for_each_entry(mgr, &amp_mgr_list, list) {
+		if (test_and_clear_bit(state, &mgr->state)) {
+			amp_mgr_get(mgr);
+			mutex_unlock(&amp_mgr_list_lock);
+			return mgr;
+		}
+	}
+	mutex_unlock(&amp_mgr_list_lock);
+
+	return NULL;
+}
+
 /* hci_dev_list shall be locked */
 static void __a2mp_add_cl(struct amp_mgr *mgr, struct a2mp_cl *cl)
 {
@@ -720,7 +738,6 @@ static const struct l2cap_ops a2mp_chan_ops = {
 	.resume = l2cap_chan_no_resume,
 	.set_shutdown = l2cap_chan_no_set_shutdown,
 	.get_sndtimeo = l2cap_chan_no_get_sndtimeo,
-	.memcpy_fromiovec = l2cap_chan_no_memcpy_fromiovec,
 };
 
 static struct l2cap_chan *a2mp_chan_open(struct l2cap_conn *conn, bool locked)
@@ -862,23 +879,6 @@ struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn,
 	return mgr->a2mp_chan;
 }
 
-struct amp_mgr *amp_mgr_lookup_by_state(u8 state)
-{
-	struct amp_mgr *mgr;
-
-	mutex_lock(&amp_mgr_list_lock);
-	list_for_each_entry(mgr, &amp_mgr_list, list) {
-		if (test_and_clear_bit(state, &mgr->state)) {
-			amp_mgr_get(mgr);
-			mutex_unlock(&amp_mgr_list_lock);
-			return mgr;
-		}
-	}
-	mutex_unlock(&amp_mgr_list_lock);
-
-	return NULL;
-}
-
 void a2mp_send_getinfo_rsp(struct hci_dev *hdev)
 {
 	struct amp_mgr *mgr;
diff --git a/net/bluetooth/a2mp.h b/net/bluetooth/a2mp.h
index 487b54c1308f..296f665adb09 100644
--- a/net/bluetooth/a2mp.h
+++ b/net/bluetooth/a2mp.h
@@ -17,8 +17,6 @@
 
 #include <net/bluetooth/l2cap.h>
 
-#define A2MP_FEAT_EXT	0x8000
-
 enum amp_mgr_state {
 	READ_LOC_AMP_INFO,
 	READ_LOC_AMP_ASSOC,
@@ -131,16 +129,10 @@ struct a2mp_physlink_rsp {
 #define A2MP_STATUS_PHYS_LINK_EXISTS		0x05
 #define A2MP_STATUS_SECURITY_VIOLATION		0x06
 
-extern struct list_head amp_mgr_list;
-extern struct mutex amp_mgr_list_lock;
-
 struct amp_mgr *amp_mgr_get(struct amp_mgr *mgr);
 int amp_mgr_put(struct amp_mgr *mgr);
-u8 __next_ident(struct amp_mgr *mgr);
 struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn,
 				       struct sk_buff *skb);
-struct amp_mgr *amp_mgr_lookup_by_state(u8 state);
-void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *data);
 void a2mp_discover_amp(struct l2cap_chan *chan);
 void a2mp_send_getinfo_rsp(struct hci_dev *hdev);
 void a2mp_send_getampassoc_rsp(struct hci_dev *hdev, u8 status);
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 339c74ad4553..70f9d945faf7 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -31,7 +31,9 @@
 #include <net/bluetooth/bluetooth.h>
 #include <linux/proc_fs.h>
 
-#define VERSION "2.19"
+#include "selftest.h"
+
+#define VERSION "2.20"
 
 /* Bluetooth sockets */
 #define BT_MAX_PROTO	8
@@ -208,8 +210,8 @@ struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock)
 }
 EXPORT_SYMBOL(bt_accept_dequeue);
 
-int bt_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
-				struct msghdr *msg, size_t len, int flags)
+int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+		    int flags)
 {
 	int noblock = flags & MSG_DONTWAIT;
 	struct sock *sk = sock->sk;
@@ -237,7 +239,7 @@ int bt_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 	}
 
 	skb_reset_transport_header(skb);
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (err == 0) {
 		sock_recv_ts_and_drops(msg, sk, skb);
 
@@ -281,8 +283,8 @@ static long bt_sock_data_wait(struct sock *sk, long timeo)
 	return timeo;
 }
 
-int bt_sock_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
-			       struct msghdr *msg, size_t size, int flags)
+int bt_sock_stream_recvmsg(struct socket *sock, struct msghdr *msg,
+			   size_t size, int flags)
 {
 	struct sock *sk = sock->sk;
 	int err = 0;
@@ -328,7 +330,7 @@ int bt_sock_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 		}
 
 		chunk = min_t(unsigned int, skb->len, size);
-		if (skb_copy_datagram_iovec(skb, 0, msg->msg_iov, chunk)) {
+		if (skb_copy_datagram_msg(skb, 0, msg, chunk)) {
 			skb_queue_head(&sk->sk_receive_queue, skb);
 			if (!copied)
 				copied = -EFAULT;
@@ -709,13 +711,16 @@ EXPORT_SYMBOL_GPL(bt_debugfs);
 
 static int __init bt_init(void)
 {
-	struct sk_buff *skb;
 	int err;
 
-	BUILD_BUG_ON(sizeof(struct bt_skb_cb) > sizeof(skb->cb));
+	sock_skb_cb_check_size(sizeof(struct bt_skb_cb));
 
 	BT_INFO("Core ver %s", VERSION);
 
+	err = bt_selftest();
+	if (err < 0)
+		return err;
+
 	bt_debugfs = debugfs_create_dir("bluetooth", NULL);
 
 	err = bt_sysfs_init();
@@ -744,6 +749,13 @@ static int __init bt_init(void)
 		goto sock_err;
 	}
 
+	err = mgmt_init();
+	if (err < 0) {
+		sco_exit();
+		l2cap_exit();
+		goto sock_err;
+	}
+
 	return 0;
 
 sock_err:
@@ -758,6 +770,8 @@ error:
 
 static void __exit bt_exit(void)
 {
+	mgmt_exit();
+
 	sco_exit();
 
 	l2cap_exit();
diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c
index 2640d78f30b8..ee016f039100 100644
--- a/net/bluetooth/amp.c
+++ b/net/bluetooth/amp.c
@@ -134,6 +134,7 @@ struct hci_conn *phylink_add(struct hci_dev *hdev, struct amp_mgr *mgr,
 static int hmac_sha256(u8 *key, u8 ksize, char *plaintext, u8 psize, u8 *output)
 {
 	struct crypto_shash *tfm;
+	struct shash_desc *shash;
 	int ret;
 
 	if (!ksize)
@@ -148,18 +149,24 @@ static int hmac_sha256(u8 *key, u8 ksize, char *plaintext, u8 psize, u8 *output)
 	ret = crypto_shash_setkey(tfm, key, ksize);
 	if (ret) {
 		BT_DBG("crypto_ahash_setkey failed: err %d", ret);
-	} else {
-		char desc[sizeof(struct shash_desc) +
-			crypto_shash_descsize(tfm)] CRYPTO_MINALIGN_ATTR;
-		struct shash_desc *shash = (struct shash_desc *)desc;
-
-		shash->tfm = tfm;
-		shash->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+		goto failed;
+	}
 
-		ret = crypto_shash_digest(shash, plaintext, psize,
-					  output);
+	shash = kzalloc(sizeof(*shash) + crypto_shash_descsize(tfm),
+			GFP_KERNEL);
+	if (!shash) {
+		ret = -ENOMEM;
+		goto failed;
 	}
 
+	shash->tfm = tfm;
+	shash->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+
+	ret = crypto_shash_digest(shash, plaintext, psize, output);
+
+	kfree(shash);
+
+failed:
 	crypto_free_shash(tfm);
 	return ret;
 }
diff --git a/net/bluetooth/bnep/Kconfig b/net/bluetooth/bnep/Kconfig
index 71791fc9f6b1..9b70317c49dc 100644
--- a/net/bluetooth/bnep/Kconfig
+++ b/net/bluetooth/bnep/Kconfig
@@ -1,6 +1,6 @@
 config BT_BNEP
 	tristate "BNEP protocol support"
-	depends on BT
+	depends on BT_BREDR
 	select CRC32
 	help
 	  BNEP (Bluetooth Network Encapsulation Protocol) is Ethernet
diff --git a/net/bluetooth/bnep/bnep.h b/net/bluetooth/bnep/bnep.h
index 5a5b16f365e9..40854c99bc1e 100644
--- a/net/bluetooth/bnep/bnep.h
+++ b/net/bluetooth/bnep/bnep.h
@@ -111,6 +111,10 @@ struct bnep_ext_hdr {
 #define BNEPCONNDEL	_IOW('B', 201, int)
 #define BNEPGETCONNLIST	_IOR('B', 210, int)
 #define BNEPGETCONNINFO	_IOR('B', 211, int)
+#define BNEPGETSUPPFEAT	_IOR('B', 212, int)
+
+#define BNEP_SETUP_RESPONSE	0
+#define BNEP_SETUP_RSP_SENT	10
 
 struct bnep_connadd_req {
 	int   sock;		/* Connected socket */
diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c
index 85bcc21e84d2..1641367e54ca 100644
--- a/net/bluetooth/bnep/core.c
+++ b/net/bluetooth/bnep/core.c
@@ -231,7 +231,14 @@ static int bnep_rx_control(struct bnep_session *s, void *data, int len)
 		break;
 
 	case BNEP_SETUP_CONN_REQ:
-		err = bnep_send_rsp(s, BNEP_SETUP_CONN_RSP, BNEP_CONN_NOT_ALLOWED);
+		/* Successful response should be sent only once */
+		if (test_bit(BNEP_SETUP_RESPONSE, &s->flags) &&
+		    !test_and_set_bit(BNEP_SETUP_RSP_SENT, &s->flags))
+			err = bnep_send_rsp(s, BNEP_SETUP_CONN_RSP,
+					    BNEP_SUCCESS);
+		else
+			err = bnep_send_rsp(s, BNEP_SETUP_CONN_RSP,
+					    BNEP_CONN_NOT_ALLOWED);
 		break;
 
 	default: {
@@ -239,7 +246,7 @@ static int bnep_rx_control(struct bnep_session *s, void *data, int len)
 			pkt[0] = BNEP_CONTROL;
 			pkt[1] = BNEP_CMD_NOT_UNDERSTOOD;
 			pkt[2] = cmd;
-			bnep_send(s, pkt, sizeof(pkt));
+			err = bnep_send(s, pkt, sizeof(pkt));
 		}
 		break;
 	}
@@ -292,29 +299,55 @@ static int bnep_rx_frame(struct bnep_session *s, struct sk_buff *skb)
 {
 	struct net_device *dev = s->dev;
 	struct sk_buff *nskb;
-	u8 type;
+	u8 type, ctrl_type;
 
 	dev->stats.rx_bytes += skb->len;
 
 	type = *(u8 *) skb->data;
 	skb_pull(skb, 1);
+	ctrl_type = *(u8 *)skb->data;
 
 	if ((type & BNEP_TYPE_MASK) >= sizeof(__bnep_rx_hlen))
 		goto badframe;
 
 	if ((type & BNEP_TYPE_MASK) == BNEP_CONTROL) {
-		bnep_rx_control(s, skb->data, skb->len);
-		kfree_skb(skb);
-		return 0;
-	}
+		if (bnep_rx_control(s, skb->data, skb->len) < 0) {
+			dev->stats.tx_errors++;
+			kfree_skb(skb);
+			return 0;
+		}
 
-	skb_reset_mac_header(skb);
+		if (!(type & BNEP_EXT_HEADER)) {
+			kfree_skb(skb);
+			return 0;
+		}
 
-	/* Verify and pull out header */
-	if (!skb_pull(skb, __bnep_rx_hlen[type & BNEP_TYPE_MASK]))
-		goto badframe;
+		/* Verify and pull ctrl message since it's already processed */
+		switch (ctrl_type) {
+		case BNEP_SETUP_CONN_REQ:
+			/* Pull: ctrl type (1 b), len (1 b), data (len bytes) */
+			if (!skb_pull(skb, 2 + *(u8 *)(skb->data + 1) * 2))
+				goto badframe;
+			break;
+		case BNEP_FILTER_MULTI_ADDR_SET:
+		case BNEP_FILTER_NET_TYPE_SET:
+			/* Pull: ctrl type (1 b), len (2 b), data (len bytes) */
+			if (!skb_pull(skb, 3 + *(u16 *)(skb->data + 1) * 2))
+				goto badframe;
+			break;
+		default:
+			kfree_skb(skb);
+			return 0;
+		}
+	} else {
+		skb_reset_mac_header(skb);
+
+		/* Verify and pull out header */
+		if (!skb_pull(skb, __bnep_rx_hlen[type & BNEP_TYPE_MASK]))
+			goto badframe;
 
-	s->eh.h_proto = get_unaligned((__be16 *) (skb->data - 2));
+		s->eh.h_proto = get_unaligned((__be16 *) (skb->data - 2));
+	}
 
 	if (type & BNEP_EXT_HEADER) {
 		if (bnep_rx_extension(s, skb) < 0)
@@ -511,13 +544,12 @@ static int bnep_session(void *arg)
 
 static struct device *bnep_get_device(struct bnep_session *session)
 {
-	struct hci_conn *conn;
+	struct l2cap_conn *conn = l2cap_pi(session->sock->sk)->chan->conn;
 
-	conn = l2cap_pi(session->sock->sk)->chan->conn->hcon;
-	if (!conn)
+	if (!conn || !conn->hcon)
 		return NULL;
 
-	return &conn->dev;
+	return &conn->hcon->dev;
 }
 
 static struct device_type bnep_type = {
@@ -526,6 +558,7 @@ static struct device_type bnep_type = {
 
 int bnep_add_connection(struct bnep_connadd_req *req, struct socket *sock)
 {
+	u32 valid_flags = BIT(BNEP_SETUP_RESPONSE);
 	struct net_device *dev;
 	struct bnep_session *s, *ss;
 	u8 dst[ETH_ALEN], src[ETH_ALEN];
@@ -533,6 +566,12 @@ int bnep_add_connection(struct bnep_connadd_req *req, struct socket *sock)
 
 	BT_DBG("");
 
+	if (!l2cap_is_socket(sock))
+		return -EBADFD;
+
+	if (req->flags & ~valid_flags)
+		return -EINVAL;
+
 	baswap((void *) dst, &l2cap_pi(sock->sk)->chan->dst);
 	baswap((void *) src, &l2cap_pi(sock->sk)->chan->src);
 
@@ -564,6 +603,7 @@ int bnep_add_connection(struct bnep_connadd_req *req, struct socket *sock)
 	s->sock  = sock;
 	s->role  = req->role;
 	s->state = BT_CONNECTED;
+	s->flags = req->flags;
 
 	s->msg.msg_flags = MSG_NOSIGNAL;
 
@@ -609,11 +649,15 @@ failed:
 
 int bnep_del_connection(struct bnep_conndel_req *req)
 {
+	u32 valid_flags = 0;
 	struct bnep_session *s;
 	int  err = 0;
 
 	BT_DBG("");
 
+	if (req->flags & ~valid_flags)
+		return -EINVAL;
+
 	down_read(&bnep_session_sem);
 
 	s = __bnep_get_session(req->dst);
@@ -629,10 +673,12 @@ int bnep_del_connection(struct bnep_conndel_req *req)
 
 static void __bnep_copy_ci(struct bnep_conninfo *ci, struct bnep_session *s)
 {
+	u32 valid_flags = BIT(BNEP_SETUP_RESPONSE);
+
 	memset(ci, 0, sizeof(*ci));
 	memcpy(ci->dst, s->eh.h_source, ETH_ALEN);
 	strcpy(ci->device, s->dev->name);
-	ci->flags = s->flags;
+	ci->flags = s->flags & valid_flags;
 	ci->state = s->state;
 	ci->role  = s->role;
 }
diff --git a/net/bluetooth/bnep/netdev.c b/net/bluetooth/bnep/netdev.c
index 4b488ec26105..6ceb5d36a32b 100644
--- a/net/bluetooth/bnep/netdev.c
+++ b/net/bluetooth/bnep/netdev.c
@@ -218,7 +218,7 @@ static const struct net_device_ops bnep_netdev_ops = {
 void bnep_net_setup(struct net_device *dev)
 {
 
-	memset(dev->broadcast, 0xff, ETH_ALEN);
+	eth_broadcast_addr(dev->broadcast);
 	dev->addr_len = ETH_ALEN;
 
 	ether_setup(dev);
diff --git a/net/bluetooth/bnep/sock.c b/net/bluetooth/bnep/sock.c
index 5f051290daba..bde2bdd9e929 100644
--- a/net/bluetooth/bnep/sock.c
+++ b/net/bluetooth/bnep/sock.c
@@ -57,6 +57,7 @@ static int bnep_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long
 	struct bnep_conninfo ci;
 	struct socket *nsock;
 	void __user *argp = (void __user *)arg;
+	__u32 supp_feat = BIT(BNEP_SETUP_RESPONSE);
 	int err;
 
 	BT_DBG("cmd %x arg %lx", cmd, arg);
@@ -120,6 +121,12 @@ static int bnep_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long
 
 		return err;
 
+	case BNEPGETSUPPFEAT:
+		if (copy_to_user(argp, &supp_feat, sizeof(supp_feat)))
+			return -EFAULT;
+
+		return 0;
+
 	default:
 		return -EINVAL;
 	}
diff --git a/net/bluetooth/cmtp/Kconfig b/net/bluetooth/cmtp/Kconfig
index 94cbf42ce155..939da0fbdd88 100644
--- a/net/bluetooth/cmtp/Kconfig
+++ b/net/bluetooth/cmtp/Kconfig
@@ -1,6 +1,6 @@
 config BT_CMTP
 	tristate "CMTP protocol support"
-	depends on BT && ISDN_CAPI
+	depends on BT_BREDR && ISDN_CAPI
 	help
 	  CMTP (CAPI Message Transport Protocol) is a transport layer
 	  for CAPI messages.  CMTP is required for the Bluetooth Common
diff --git a/net/bluetooth/cmtp/capi.c b/net/bluetooth/cmtp/capi.c
index 1ca8a87a0787..b0c6c6af76ef 100644
--- a/net/bluetooth/cmtp/capi.c
+++ b/net/bluetooth/cmtp/capi.c
@@ -253,8 +253,6 @@ static void cmtp_recv_interopmsg(struct cmtp_session *session, struct sk_buff *s
 			if (skb->len < CAPI_MSG_BASELEN + 15)
 				break;
 
-			controller = CAPIMSG_U32(skb->data, CAPI_MSG_BASELEN + 10);
-
 			if (!info && ctrl) {
 				int len = min_t(uint, CAPI_MANUFACTURER_LEN,
 						skb->data[CAPI_MSG_BASELEN + 14]);
@@ -270,8 +268,6 @@ static void cmtp_recv_interopmsg(struct cmtp_session *session, struct sk_buff *s
 			if (skb->len < CAPI_MSG_BASELEN + 32)
 				break;
 
-			controller = CAPIMSG_U32(skb->data, CAPI_MSG_BASELEN + 12);
-
 			if (!info && ctrl) {
 				ctrl->version.majorversion = CAPIMSG_U32(skb->data, CAPI_MSG_BASELEN + 16);
 				ctrl->version.minorversion = CAPIMSG_U32(skb->data, CAPI_MSG_BASELEN + 20);
@@ -285,8 +281,6 @@ static void cmtp_recv_interopmsg(struct cmtp_session *session, struct sk_buff *s
 			if (skb->len < CAPI_MSG_BASELEN + 17)
 				break;
 
-			controller = CAPIMSG_U32(skb->data, CAPI_MSG_BASELEN + 12);
-
 			if (!info && ctrl) {
 				int len = min_t(uint, CAPI_SERIAL_LEN,
 						skb->data[CAPI_MSG_BASELEN + 16]);
@@ -339,7 +333,7 @@ void cmtp_recv_capimsg(struct cmtp_session *session, struct sk_buff *skb)
 		return;
 	}
 
-	if (session->flags & (1 << CMTP_LOOPBACK)) {
+	if (session->flags & BIT(CMTP_LOOPBACK)) {
 		kfree_skb(skb);
 		return;
 	}
diff --git a/net/bluetooth/cmtp/core.c b/net/bluetooth/cmtp/core.c
index 67fe5e84e68f..298ed37010e6 100644
--- a/net/bluetooth/cmtp/core.c
+++ b/net/bluetooth/cmtp/core.c
@@ -75,10 +75,11 @@ static void __cmtp_unlink_session(struct cmtp_session *session)
 
 static void __cmtp_copy_session(struct cmtp_session *session, struct cmtp_conninfo *ci)
 {
+	u32 valid_flags = BIT(CMTP_LOOPBACK);
 	memset(ci, 0, sizeof(*ci));
 	bacpy(&ci->bdaddr, &session->bdaddr);
 
-	ci->flags = session->flags;
+	ci->flags = session->flags & valid_flags;
 	ci->state = session->state;
 
 	ci->num = session->num;
@@ -313,7 +314,7 @@ static int cmtp_session(void *arg)
 
 	down_write(&cmtp_session_sem);
 
-	if (!(session->flags & (1 << CMTP_LOOPBACK)))
+	if (!(session->flags & BIT(CMTP_LOOPBACK)))
 		cmtp_detach_device(session);
 
 	fput(session->sock->file);
@@ -329,11 +330,18 @@ static int cmtp_session(void *arg)
 
 int cmtp_add_connection(struct cmtp_connadd_req *req, struct socket *sock)
 {
+	u32 valid_flags = BIT(CMTP_LOOPBACK);
 	struct cmtp_session *session, *s;
 	int i, err;
 
 	BT_DBG("");
 
+	if (!l2cap_is_socket(sock))
+		return -EBADFD;
+
+	if (req->flags & ~valid_flags)
+		return -EINVAL;
+
 	session = kzalloc(sizeof(struct cmtp_session), GFP_KERNEL);
 	if (!session)
 		return -ENOMEM;
@@ -382,7 +390,7 @@ int cmtp_add_connection(struct cmtp_connadd_req *req, struct socket *sock)
 		goto unlink;
 	}
 
-	if (!(session->flags & (1 << CMTP_LOOPBACK))) {
+	if (!(session->flags & BIT(CMTP_LOOPBACK))) {
 		err = cmtp_attach_device(session);
 		if (err < 0) {
 			atomic_inc(&session->terminate);
@@ -406,11 +414,15 @@ failed:
 
 int cmtp_del_connection(struct cmtp_conndel_req *req)
 {
+	u32 valid_flags = 0;
 	struct cmtp_session *session;
 	int err = 0;
 
 	BT_DBG("");
 
+	if (req->flags & ~valid_flags)
+		return -EINVAL;
+
 	down_read(&cmtp_session_sem);
 
 	session = __cmtp_get_session(&req->bdaddr);
diff --git a/net/bluetooth/ecc.c b/net/bluetooth/ecc.c
new file mode 100644
index 000000000000..e1709f8467ac
--- /dev/null
+++ b/net/bluetooth/ecc.c
@@ -0,0 +1,816 @@
+/*
+ * Copyright (c) 2013, Kenneth MacKay
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ *  * Redistributions of source code must retain the above copyright
+ *   notice, this list of conditions and the following disclaimer.
+ *  * 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.
+ *
+ * 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
+ * HOLDER 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/random.h>
+
+#include "ecc.h"
+
+/* 256-bit curve */
+#define ECC_BYTES 32
+
+#define MAX_TRIES 16
+
+/* Number of u64's needed */
+#define NUM_ECC_DIGITS (ECC_BYTES / 8)
+
+struct ecc_point {
+	u64 x[NUM_ECC_DIGITS];
+	u64 y[NUM_ECC_DIGITS];
+};
+
+typedef struct {
+	u64 m_low;
+	u64 m_high;
+} uint128_t;
+
+#define CURVE_P_32 {	0xFFFFFFFFFFFFFFFFull, 0x00000000FFFFFFFFull, \
+			0x0000000000000000ull, 0xFFFFFFFF00000001ull }
+
+#define CURVE_G_32 { \
+		{	0xF4A13945D898C296ull, 0x77037D812DEB33A0ull,	\
+			0xF8BCE6E563A440F2ull, 0x6B17D1F2E12C4247ull }, \
+		{	0xCBB6406837BF51F5ull, 0x2BCE33576B315ECEull,	\
+			0x8EE7EB4A7C0F9E16ull, 0x4FE342E2FE1A7F9Bull }	\
+}
+
+#define CURVE_N_32 {	0xF3B9CAC2FC632551ull, 0xBCE6FAADA7179E84ull,	\
+			0xFFFFFFFFFFFFFFFFull, 0xFFFFFFFF00000000ull }
+
+static u64 curve_p[NUM_ECC_DIGITS] = CURVE_P_32;
+static struct ecc_point curve_g = CURVE_G_32;
+static u64 curve_n[NUM_ECC_DIGITS] = CURVE_N_32;
+
+static void vli_clear(u64 *vli)
+{
+	int i;
+
+	for (i = 0; i < NUM_ECC_DIGITS; i++)
+		vli[i] = 0;
+}
+
+/* Returns true if vli == 0, false otherwise. */
+static bool vli_is_zero(const u64 *vli)
+{
+	int i;
+
+	for (i = 0; i < NUM_ECC_DIGITS; i++) {
+		if (vli[i])
+			return false;
+	}
+
+	return true;
+}
+
+/* Returns nonzero if bit bit of vli is set. */
+static u64 vli_test_bit(const u64 *vli, unsigned int bit)
+{
+	return (vli[bit / 64] & ((u64) 1 << (bit % 64)));
+}
+
+/* Counts the number of 64-bit "digits" in vli. */
+static unsigned int vli_num_digits(const u64 *vli)
+{
+	int i;
+
+	/* Search from the end until we find a non-zero digit.
+	 * We do it in reverse because we expect that most digits will
+	 * be nonzero.
+	 */
+	for (i = NUM_ECC_DIGITS - 1; i >= 0 && vli[i] == 0; i--);
+
+	return (i + 1);
+}
+
+/* Counts the number of bits required for vli. */
+static unsigned int vli_num_bits(const u64 *vli)
+{
+	unsigned int i, num_digits;
+	u64 digit;
+
+	num_digits = vli_num_digits(vli);
+	if (num_digits == 0)
+		return 0;
+
+	digit = vli[num_digits - 1];
+	for (i = 0; digit; i++)
+		digit >>= 1;
+
+	return ((num_digits - 1) * 64 + i);
+}
+
+/* Sets dest = src. */
+static void vli_set(u64 *dest, const u64 *src)
+{
+	int i;
+
+	for (i = 0; i < NUM_ECC_DIGITS; i++)
+		dest[i] = src[i];
+}
+
+/* Returns sign of left - right. */
+static int vli_cmp(const u64 *left, const u64 *right)
+{
+    int i;
+
+    for (i = NUM_ECC_DIGITS - 1; i >= 0; i--) {
+	    if (left[i] > right[i])
+		    return 1;
+	    else if (left[i] < right[i])
+		    return -1;
+    }
+
+    return 0;
+}
+
+/* Computes result = in << c, returning carry. Can modify in place
+ * (if result == in). 0 < shift < 64.
+ */
+static u64 vli_lshift(u64 *result, const u64 *in,
+			   unsigned int shift)
+{
+	u64 carry = 0;
+	int i;
+
+	for (i = 0; i < NUM_ECC_DIGITS; i++) {
+		u64 temp = in[i];
+
+		result[i] = (temp << shift) | carry;
+		carry = temp >> (64 - shift);
+	}
+
+	return carry;
+}
+
+/* Computes vli = vli >> 1. */
+static void vli_rshift1(u64 *vli)
+{
+	u64 *end = vli;
+	u64 carry = 0;
+
+	vli += NUM_ECC_DIGITS;
+
+	while (vli-- > end) {
+		u64 temp = *vli;
+		*vli = (temp >> 1) | carry;
+		carry = temp << 63;
+	}
+}
+
+/* Computes result = left + right, returning carry. Can modify in place. */
+static u64 vli_add(u64 *result, const u64 *left,
+			const u64 *right)
+{
+	u64 carry = 0;
+	int i;
+
+	for (i = 0; i < NUM_ECC_DIGITS; i++) {
+		u64 sum;
+
+		sum = left[i] + right[i] + carry;
+		if (sum != left[i])
+			carry = (sum < left[i]);
+
+		result[i] = sum;
+	}
+
+	return carry;
+}
+
+/* Computes result = left - right, returning borrow. Can modify in place. */
+static u64 vli_sub(u64 *result, const u64 *left, const u64 *right)
+{
+	u64 borrow = 0;
+	int i;
+
+	for (i = 0; i < NUM_ECC_DIGITS; i++) {
+		u64 diff;
+
+		diff = left[i] - right[i] - borrow;
+		if (diff != left[i])
+			borrow = (diff > left[i]);
+
+		result[i] = diff;
+	}
+
+	return borrow;
+}
+
+static uint128_t mul_64_64(u64 left, u64 right)
+{
+	u64 a0 = left & 0xffffffffull;
+	u64 a1 = left >> 32;
+	u64 b0 = right & 0xffffffffull;
+	u64 b1 = right >> 32;
+	u64 m0 = a0 * b0;
+	u64 m1 = a0 * b1;
+	u64 m2 = a1 * b0;
+	u64 m3 = a1 * b1;
+	uint128_t result;
+
+	m2 += (m0 >> 32);
+	m2 += m1;
+
+	/* Overflow */
+	if (m2 < m1)
+		m3 += 0x100000000ull;
+
+	result.m_low = (m0 & 0xffffffffull) | (m2 << 32);
+	result.m_high = m3 + (m2 >> 32);
+
+	return result;
+}
+
+static uint128_t add_128_128(uint128_t a, uint128_t b)
+{
+	uint128_t result;
+
+	result.m_low = a.m_low + b.m_low;
+	result.m_high = a.m_high + b.m_high + (result.m_low < a.m_low);
+
+	return result;
+}
+
+static void vli_mult(u64 *result, const u64 *left, const u64 *right)
+{
+	uint128_t r01 = { 0, 0 };
+	u64 r2 = 0;
+	unsigned int i, k;
+
+	/* Compute each digit of result in sequence, maintaining the
+	 * carries.
+	 */
+	for (k = 0; k < NUM_ECC_DIGITS * 2 - 1; k++) {
+		unsigned int min;
+
+		if (k < NUM_ECC_DIGITS)
+			min = 0;
+		else
+			min = (k + 1) - NUM_ECC_DIGITS;
+
+		for (i = min; i <= k && i < NUM_ECC_DIGITS; i++) {
+			uint128_t product;
+
+			product = mul_64_64(left[i], right[k - i]);
+
+			r01 = add_128_128(r01, product);
+			r2 += (r01.m_high < product.m_high);
+		}
+
+		result[k] = r01.m_low;
+		r01.m_low = r01.m_high;
+		r01.m_high = r2;
+		r2 = 0;
+	}
+
+	result[NUM_ECC_DIGITS * 2 - 1] = r01.m_low;
+}
+
+static void vli_square(u64 *result, const u64 *left)
+{
+	uint128_t r01 = { 0, 0 };
+	u64 r2 = 0;
+	int i, k;
+
+	for (k = 0; k < NUM_ECC_DIGITS * 2 - 1; k++) {
+		unsigned int min;
+
+		if (k < NUM_ECC_DIGITS)
+			min = 0;
+		else
+			min = (k + 1) - NUM_ECC_DIGITS;
+
+		for (i = min; i <= k && i <= k - i; i++) {
+			uint128_t product;
+
+			product = mul_64_64(left[i], left[k - i]);
+
+			if (i < k - i) {
+				r2 += product.m_high >> 63;
+				product.m_high = (product.m_high << 1) |
+						 (product.m_low >> 63);
+				product.m_low <<= 1;
+			}
+
+			r01 = add_128_128(r01, product);
+			r2 += (r01.m_high < product.m_high);
+		}
+
+		result[k] = r01.m_low;
+		r01.m_low = r01.m_high;
+		r01.m_high = r2;
+		r2 = 0;
+	}
+
+	result[NUM_ECC_DIGITS * 2 - 1] = r01.m_low;
+}
+
+/* Computes result = (left + right) % mod.
+ * Assumes that left < mod and right < mod, result != mod.
+ */
+static void vli_mod_add(u64 *result, const u64 *left, const u64 *right,
+			const u64 *mod)
+{
+	u64 carry;
+
+	carry = vli_add(result, left, right);
+
+	/* result > mod (result = mod + remainder), so subtract mod to
+	 * get remainder.
+	 */
+	if (carry || vli_cmp(result, mod) >= 0)
+		vli_sub(result, result, mod);
+}
+
+/* Computes result = (left - right) % mod.
+ * Assumes that left < mod and right < mod, result != mod.
+ */
+static void vli_mod_sub(u64 *result, const u64 *left, const u64 *right,
+			const u64 *mod)
+{
+	u64 borrow = vli_sub(result, left, right);
+
+	/* In this case, p_result == -diff == (max int) - diff.
+	 * Since -x % d == d - x, we can get the correct result from
+	 * result + mod (with overflow).
+	 */
+	if (borrow)
+		vli_add(result, result, mod);
+}
+
+/* Computes result = product % curve_p
+   from http://www.nsa.gov/ia/_files/nist-routines.pdf */
+static void vli_mmod_fast(u64 *result, const u64 *product)
+{
+	u64 tmp[NUM_ECC_DIGITS];
+	int carry;
+
+	/* t */
+	vli_set(result, product);
+
+	/* s1 */
+	tmp[0] = 0;
+	tmp[1] = product[5] & 0xffffffff00000000ull;
+	tmp[2] = product[6];
+	tmp[3] = product[7];
+	carry = vli_lshift(tmp, tmp, 1);
+	carry += vli_add(result, result, tmp);
+
+	/* s2 */
+	tmp[1] = product[6] << 32;
+	tmp[2] = (product[6] >> 32) | (product[7] << 32);
+	tmp[3] = product[7] >> 32;
+	carry += vli_lshift(tmp, tmp, 1);
+	carry += vli_add(result, result, tmp);
+
+	/* s3 */
+	tmp[0] = product[4];
+	tmp[1] = product[5] & 0xffffffff;
+	tmp[2] = 0;
+	tmp[3] = product[7];
+	carry += vli_add(result, result, tmp);
+
+	/* s4 */
+	tmp[0] = (product[4] >> 32) | (product[5] << 32);
+	tmp[1] = (product[5] >> 32) | (product[6] & 0xffffffff00000000ull);
+	tmp[2] = product[7];
+	tmp[3] = (product[6] >> 32) | (product[4] << 32);
+	carry += vli_add(result, result, tmp);
+
+	/* d1 */
+	tmp[0] = (product[5] >> 32) | (product[6] << 32);
+	tmp[1] = (product[6] >> 32);
+	tmp[2] = 0;
+	tmp[3] = (product[4] & 0xffffffff) | (product[5] << 32);
+	carry -= vli_sub(result, result, tmp);
+
+	/* d2 */
+	tmp[0] = product[6];
+	tmp[1] = product[7];
+	tmp[2] = 0;
+	tmp[3] = (product[4] >> 32) | (product[5] & 0xffffffff00000000ull);
+	carry -= vli_sub(result, result, tmp);
+
+	/* d3 */
+	tmp[0] = (product[6] >> 32) | (product[7] << 32);
+	tmp[1] = (product[7] >> 32) | (product[4] << 32);
+	tmp[2] = (product[4] >> 32) | (product[5] << 32);
+	tmp[3] = (product[6] << 32);
+	carry -= vli_sub(result, result, tmp);
+
+	/* d4 */
+	tmp[0] = product[7];
+	tmp[1] = product[4] & 0xffffffff00000000ull;
+	tmp[2] = product[5];
+	tmp[3] = product[6] & 0xffffffff00000000ull;
+	carry -= vli_sub(result, result, tmp);
+
+	if (carry < 0) {
+		do {
+			carry += vli_add(result, result, curve_p);
+		} while (carry < 0);
+	} else {
+		while (carry || vli_cmp(curve_p, result) != 1)
+			carry -= vli_sub(result, result, curve_p);
+	}
+}
+
+/* Computes result = (left * right) % curve_p. */
+static void vli_mod_mult_fast(u64 *result, const u64 *left, const u64 *right)
+{
+	u64 product[2 * NUM_ECC_DIGITS];
+
+	vli_mult(product, left, right);
+	vli_mmod_fast(result, product);
+}
+
+/* Computes result = left^2 % curve_p. */
+static void vli_mod_square_fast(u64 *result, const u64 *left)
+{
+	u64 product[2 * NUM_ECC_DIGITS];
+
+	vli_square(product, left);
+	vli_mmod_fast(result, product);
+}
+
+#define EVEN(vli) (!(vli[0] & 1))
+/* Computes result = (1 / p_input) % mod. All VLIs are the same size.
+ * See "From Euclid's GCD to Montgomery Multiplication to the Great Divide"
+ * https://labs.oracle.com/techrep/2001/smli_tr-2001-95.pdf
+ */
+static void vli_mod_inv(u64 *result, const u64 *input, const u64 *mod)
+{
+	u64 a[NUM_ECC_DIGITS], b[NUM_ECC_DIGITS];
+	u64 u[NUM_ECC_DIGITS], v[NUM_ECC_DIGITS];
+	u64 carry;
+	int cmp_result;
+
+	if (vli_is_zero(input)) {
+		vli_clear(result);
+		return;
+	}
+
+	vli_set(a, input);
+	vli_set(b, mod);
+	vli_clear(u);
+	u[0] = 1;
+	vli_clear(v);
+
+	while ((cmp_result = vli_cmp(a, b)) != 0) {
+		carry = 0;
+
+		if (EVEN(a)) {
+			vli_rshift1(a);
+
+			if (!EVEN(u))
+				carry = vli_add(u, u, mod);
+
+			vli_rshift1(u);
+			if (carry)
+				u[NUM_ECC_DIGITS - 1] |= 0x8000000000000000ull;
+		} else if (EVEN(b)) {
+			vli_rshift1(b);
+
+			if (!EVEN(v))
+				carry = vli_add(v, v, mod);
+
+			vli_rshift1(v);
+			if (carry)
+				v[NUM_ECC_DIGITS - 1] |= 0x8000000000000000ull;
+		} else if (cmp_result > 0) {
+			vli_sub(a, a, b);
+			vli_rshift1(a);
+
+			if (vli_cmp(u, v) < 0)
+				vli_add(u, u, mod);
+
+			vli_sub(u, u, v);
+			if (!EVEN(u))
+				carry = vli_add(u, u, mod);
+
+			vli_rshift1(u);
+			if (carry)
+				u[NUM_ECC_DIGITS - 1] |= 0x8000000000000000ull;
+		} else {
+			vli_sub(b, b, a);
+			vli_rshift1(b);
+
+			if (vli_cmp(v, u) < 0)
+				vli_add(v, v, mod);
+
+			vli_sub(v, v, u);
+			if (!EVEN(v))
+				carry = vli_add(v, v, mod);
+
+			vli_rshift1(v);
+			if (carry)
+				v[NUM_ECC_DIGITS - 1] |= 0x8000000000000000ull;
+		}
+	}
+
+	vli_set(result, u);
+}
+
+/* ------ Point operations ------ */
+
+/* Returns true if p_point is the point at infinity, false otherwise. */
+static bool ecc_point_is_zero(const struct ecc_point *point)
+{
+	return (vli_is_zero(point->x) && vli_is_zero(point->y));
+}
+
+/* Point multiplication algorithm using Montgomery's ladder with co-Z
+ * coordinates. From http://eprint.iacr.org/2011/338.pdf
+ */
+
+/* Double in place */
+static void ecc_point_double_jacobian(u64 *x1, u64 *y1, u64 *z1)
+{
+	/* t1 = x, t2 = y, t3 = z */
+	u64 t4[NUM_ECC_DIGITS];
+	u64 t5[NUM_ECC_DIGITS];
+
+	if (vli_is_zero(z1))
+		return;
+
+	vli_mod_square_fast(t4, y1);   /* t4 = y1^2 */
+	vli_mod_mult_fast(t5, x1, t4); /* t5 = x1*y1^2 = A */
+	vli_mod_square_fast(t4, t4);   /* t4 = y1^4 */
+	vli_mod_mult_fast(y1, y1, z1); /* t2 = y1*z1 = z3 */
+	vli_mod_square_fast(z1, z1);   /* t3 = z1^2 */
+
+	vli_mod_add(x1, x1, z1, curve_p); /* t1 = x1 + z1^2 */
+	vli_mod_add(z1, z1, z1, curve_p); /* t3 = 2*z1^2 */
+	vli_mod_sub(z1, x1, z1, curve_p); /* t3 = x1 - z1^2 */
+	vli_mod_mult_fast(x1, x1, z1);    /* t1 = x1^2 - z1^4 */
+
+	vli_mod_add(z1, x1, x1, curve_p); /* t3 = 2*(x1^2 - z1^4) */
+	vli_mod_add(x1, x1, z1, curve_p); /* t1 = 3*(x1^2 - z1^4) */
+	if (vli_test_bit(x1, 0)) {
+		u64 carry = vli_add(x1, x1, curve_p);
+		vli_rshift1(x1);
+		x1[NUM_ECC_DIGITS - 1] |= carry << 63;
+	} else {
+		vli_rshift1(x1);
+	}
+	/* t1 = 3/2*(x1^2 - z1^4) = B */
+
+	vli_mod_square_fast(z1, x1);      /* t3 = B^2 */
+	vli_mod_sub(z1, z1, t5, curve_p); /* t3 = B^2 - A */
+	vli_mod_sub(z1, z1, t5, curve_p); /* t3 = B^2 - 2A = x3 */
+	vli_mod_sub(t5, t5, z1, curve_p); /* t5 = A - x3 */
+	vli_mod_mult_fast(x1, x1, t5);    /* t1 = B * (A - x3) */
+	vli_mod_sub(t4, x1, t4, curve_p); /* t4 = B * (A - x3) - y1^4 = y3 */
+
+	vli_set(x1, z1);
+	vli_set(z1, y1);
+	vli_set(y1, t4);
+}
+
+/* Modify (x1, y1) => (x1 * z^2, y1 * z^3) */
+static void apply_z(u64 *x1, u64 *y1, u64 *z)
+{
+	u64 t1[NUM_ECC_DIGITS];
+
+	vli_mod_square_fast(t1, z);    /* z^2 */
+	vli_mod_mult_fast(x1, x1, t1); /* x1 * z^2 */
+	vli_mod_mult_fast(t1, t1, z);  /* z^3 */
+	vli_mod_mult_fast(y1, y1, t1); /* y1 * z^3 */
+}
+
+/* P = (x1, y1) => 2P, (x2, y2) => P' */
+static void xycz_initial_double(u64 *x1, u64 *y1, u64 *x2, u64 *y2,
+				u64 *p_initial_z)
+{
+	u64 z[NUM_ECC_DIGITS];
+
+	vli_set(x2, x1);
+	vli_set(y2, y1);
+
+	vli_clear(z);
+	z[0] = 1;
+
+	if (p_initial_z)
+		vli_set(z, p_initial_z);
+
+	apply_z(x1, y1, z);
+
+	ecc_point_double_jacobian(x1, y1, z);
+
+	apply_z(x2, y2, z);
+}
+
+/* Input P = (x1, y1, Z), Q = (x2, y2, Z)
+ * Output P' = (x1', y1', Z3), P + Q = (x3, y3, Z3)
+ * or P => P', Q => P + Q
+ */
+static void xycz_add(u64 *x1, u64 *y1, u64 *x2, u64 *y2)
+{
+	/* t1 = X1, t2 = Y1, t3 = X2, t4 = Y2 */
+	u64 t5[NUM_ECC_DIGITS];
+
+	vli_mod_sub(t5, x2, x1, curve_p); /* t5 = x2 - x1 */
+	vli_mod_square_fast(t5, t5);      /* t5 = (x2 - x1)^2 = A */
+	vli_mod_mult_fast(x1, x1, t5);    /* t1 = x1*A = B */
+	vli_mod_mult_fast(x2, x2, t5);    /* t3 = x2*A = C */
+	vli_mod_sub(y2, y2, y1, curve_p); /* t4 = y2 - y1 */
+	vli_mod_square_fast(t5, y2);      /* t5 = (y2 - y1)^2 = D */
+
+	vli_mod_sub(t5, t5, x1, curve_p); /* t5 = D - B */
+	vli_mod_sub(t5, t5, x2, curve_p); /* t5 = D - B - C = x3 */
+	vli_mod_sub(x2, x2, x1, curve_p); /* t3 = C - B */
+	vli_mod_mult_fast(y1, y1, x2);    /* t2 = y1*(C - B) */
+	vli_mod_sub(x2, x1, t5, curve_p); /* t3 = B - x3 */
+	vli_mod_mult_fast(y2, y2, x2);    /* t4 = (y2 - y1)*(B - x3) */
+	vli_mod_sub(y2, y2, y1, curve_p); /* t4 = y3 */
+
+	vli_set(x2, t5);
+}
+
+/* Input P = (x1, y1, Z), Q = (x2, y2, Z)
+ * Output P + Q = (x3, y3, Z3), P - Q = (x3', y3', Z3)
+ * or P => P - Q, Q => P + Q
+ */
+static void xycz_add_c(u64 *x1, u64 *y1, u64 *x2, u64 *y2)
+{
+	/* t1 = X1, t2 = Y1, t3 = X2, t4 = Y2 */
+	u64 t5[NUM_ECC_DIGITS];
+	u64 t6[NUM_ECC_DIGITS];
+	u64 t7[NUM_ECC_DIGITS];
+
+	vli_mod_sub(t5, x2, x1, curve_p); /* t5 = x2 - x1 */
+	vli_mod_square_fast(t5, t5);      /* t5 = (x2 - x1)^2 = A */
+	vli_mod_mult_fast(x1, x1, t5);    /* t1 = x1*A = B */
+	vli_mod_mult_fast(x2, x2, t5);    /* t3 = x2*A = C */
+	vli_mod_add(t5, y2, y1, curve_p); /* t4 = y2 + y1 */
+	vli_mod_sub(y2, y2, y1, curve_p); /* t4 = y2 - y1 */
+
+	vli_mod_sub(t6, x2, x1, curve_p); /* t6 = C - B */
+	vli_mod_mult_fast(y1, y1, t6);    /* t2 = y1 * (C - B) */
+	vli_mod_add(t6, x1, x2, curve_p); /* t6 = B + C */
+	vli_mod_square_fast(x2, y2);      /* t3 = (y2 - y1)^2 */
+	vli_mod_sub(x2, x2, t6, curve_p); /* t3 = x3 */
+
+	vli_mod_sub(t7, x1, x2, curve_p); /* t7 = B - x3 */
+	vli_mod_mult_fast(y2, y2, t7);    /* t4 = (y2 - y1)*(B - x3) */
+	vli_mod_sub(y2, y2, y1, curve_p); /* t4 = y3 */
+
+	vli_mod_square_fast(t7, t5);      /* t7 = (y2 + y1)^2 = F */
+	vli_mod_sub(t7, t7, t6, curve_p); /* t7 = x3' */
+	vli_mod_sub(t6, t7, x1, curve_p); /* t6 = x3' - B */
+	vli_mod_mult_fast(t6, t6, t5);    /* t6 = (y2 + y1)*(x3' - B) */
+	vli_mod_sub(y1, t6, y1, curve_p); /* t2 = y3' */
+
+	vli_set(x1, t7);
+}
+
+static void ecc_point_mult(struct ecc_point *result,
+			   const struct ecc_point *point, u64 *scalar,
+			   u64 *initial_z, int num_bits)
+{
+	/* R0 and R1 */
+	u64 rx[2][NUM_ECC_DIGITS];
+	u64 ry[2][NUM_ECC_DIGITS];
+	u64 z[NUM_ECC_DIGITS];
+	int i, nb;
+
+	vli_set(rx[1], point->x);
+	vli_set(ry[1], point->y);
+
+	xycz_initial_double(rx[1], ry[1], rx[0], ry[0], initial_z);
+
+	for (i = num_bits - 2; i > 0; i--) {
+		nb = !vli_test_bit(scalar, i);
+		xycz_add_c(rx[1 - nb], ry[1 - nb], rx[nb], ry[nb]);
+		xycz_add(rx[nb], ry[nb], rx[1 - nb], ry[1 - nb]);
+	}
+
+	nb = !vli_test_bit(scalar, 0);
+	xycz_add_c(rx[1 - nb], ry[1 - nb], rx[nb], ry[nb]);
+
+	/* Find final 1/Z value. */
+	vli_mod_sub(z, rx[1], rx[0], curve_p); /* X1 - X0 */
+	vli_mod_mult_fast(z, z, ry[1 - nb]); /* Yb * (X1 - X0) */
+	vli_mod_mult_fast(z, z, point->x);   /* xP * Yb * (X1 - X0) */
+	vli_mod_inv(z, z, curve_p);          /* 1 / (xP * Yb * (X1 - X0)) */
+	vli_mod_mult_fast(z, z, point->y);   /* yP / (xP * Yb * (X1 - X0)) */
+	vli_mod_mult_fast(z, z, rx[1 - nb]); /* Xb * yP / (xP * Yb * (X1 - X0)) */
+	/* End 1/Z calculation */
+
+	xycz_add(rx[nb], ry[nb], rx[1 - nb], ry[1 - nb]);
+
+	apply_z(rx[0], ry[0], z);
+
+	vli_set(result->x, rx[0]);
+	vli_set(result->y, ry[0]);
+}
+
+static void ecc_bytes2native(const u8 bytes[ECC_BYTES],
+			     u64 native[NUM_ECC_DIGITS])
+{
+	int i;
+
+	for (i = 0; i < NUM_ECC_DIGITS; i++) {
+		const u8 *digit = bytes + 8 * (NUM_ECC_DIGITS - 1 - i);
+
+		native[NUM_ECC_DIGITS - 1 - i] =
+				((u64) digit[0] << 0) |
+				((u64) digit[1] << 8) |
+				((u64) digit[2] << 16) |
+				((u64) digit[3] << 24) |
+				((u64) digit[4] << 32) |
+				((u64) digit[5] << 40) |
+				((u64) digit[6] << 48) |
+				((u64) digit[7] << 56);
+	}
+}
+
+static void ecc_native2bytes(const u64 native[NUM_ECC_DIGITS],
+			     u8 bytes[ECC_BYTES])
+{
+	int i;
+
+	for (i = 0; i < NUM_ECC_DIGITS; i++) {
+		u8 *digit = bytes + 8 * (NUM_ECC_DIGITS - 1 - i);
+
+		digit[0] = native[NUM_ECC_DIGITS - 1 - i] >> 0;
+		digit[1] = native[NUM_ECC_DIGITS - 1 - i] >> 8;
+		digit[2] = native[NUM_ECC_DIGITS - 1 - i] >> 16;
+		digit[3] = native[NUM_ECC_DIGITS - 1 - i] >> 24;
+		digit[4] = native[NUM_ECC_DIGITS - 1 - i] >> 32;
+		digit[5] = native[NUM_ECC_DIGITS - 1 - i] >> 40;
+		digit[6] = native[NUM_ECC_DIGITS - 1 - i] >> 48;
+		digit[7] = native[NUM_ECC_DIGITS - 1 - i] >> 56;
+	}
+}
+
+bool ecc_make_key(u8 public_key[64], u8 private_key[32])
+{
+	struct ecc_point pk;
+	u64 priv[NUM_ECC_DIGITS];
+	unsigned int tries = 0;
+
+	do {
+		if (tries++ >= MAX_TRIES)
+			return false;
+
+		get_random_bytes(priv, ECC_BYTES);
+
+		if (vli_is_zero(priv))
+			continue;
+
+		/* Make sure the private key is in the range [1, n-1]. */
+		if (vli_cmp(curve_n, priv) != 1)
+			continue;
+
+		ecc_point_mult(&pk, &curve_g, priv, NULL, vli_num_bits(priv));
+	} while (ecc_point_is_zero(&pk));
+
+	ecc_native2bytes(priv, private_key);
+	ecc_native2bytes(pk.x, public_key);
+	ecc_native2bytes(pk.y, &public_key[32]);
+
+	return true;
+}
+
+bool ecdh_shared_secret(const u8 public_key[64], const u8 private_key[32],
+		        u8 secret[32])
+{
+	u64 priv[NUM_ECC_DIGITS];
+	u64 rand[NUM_ECC_DIGITS];
+	struct ecc_point product, pk;
+
+	get_random_bytes(rand, ECC_BYTES);
+
+	ecc_bytes2native(public_key, pk.x);
+	ecc_bytes2native(&public_key[32], pk.y);
+	ecc_bytes2native(private_key, priv);
+
+	ecc_point_mult(&product, &pk, priv, rand, vli_num_bits(priv));
+
+	ecc_native2bytes(product.x, secret);
+
+	return !ecc_point_is_zero(&product);
+}
diff --git a/net/bluetooth/ecc.h b/net/bluetooth/ecc.h
new file mode 100644
index 000000000000..8d6a2f4d1905
--- /dev/null
+++ b/net/bluetooth/ecc.h
@@ -0,0 +1,54 @@
+/*
+ * Copyright (c) 2013, Kenneth MacKay
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ *  * Redistributions of source code must retain the above copyright
+ *   notice, this list of conditions and the following disclaimer.
+ *  * 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.
+ *
+ * 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
+ * HOLDER 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.
+ */
+
+/* Create a public/private key pair.
+ * Outputs:
+ *	public_key  - Will be filled in with the public key.
+ *	private_key - Will be filled in with the private key.
+ *
+ * Returns true if the key pair was generated successfully, false
+ * if an error occurred. The keys are with the LSB first.
+ */
+bool ecc_make_key(u8 public_key[64], u8 private_key[32]);
+
+/* Compute a shared secret given your secret key and someone else's
+ * public key.
+ * Note: It is recommended that you hash the result of ecdh_shared_secret
+ * before using it for symmetric encryption or HMAC.
+ *
+ * Inputs:
+ *	public_key  - The public key of the remote party
+ *	private_key - Your private key.
+ *
+ * Outputs:
+ *	secret - Will be filled in with the shared secret value.
+ *
+ * Returns true if the shared secret was generated successfully, false
+ * if an error occurred. Both input and output parameters are with the
+ * LSB first.
+ */
+bool ecdh_shared_secret(const u8 public_key[64], const u8 private_key[32],
+		        u8 secret[32]);
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index b9517bd17190..ee5e59839b02 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -25,11 +25,13 @@
 /* Bluetooth HCI connection handling. */
 
 #include <linux/export.h>
+#include <linux/debugfs.h>
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
 #include <net/bluetooth/l2cap.h>
 
+#include "hci_request.h"
 #include "smp.h"
 #include "a2mp.h"
 
@@ -141,10 +143,11 @@ int hci_disconnect(struct hci_conn *conn, __u8 reason)
 	 */
 	if (conn->type == ACL_LINK && conn->role == HCI_ROLE_MASTER) {
 		struct hci_dev *hdev = conn->hdev;
-		struct hci_cp_read_clock_offset cp;
+		struct hci_cp_read_clock_offset clkoff_cp;
 
-		cp.handle = cpu_to_le16(conn->handle);
-		hci_send_cmd(hdev, HCI_OP_READ_CLOCK_OFFSET, sizeof(cp), &cp);
+		clkoff_cp.handle = cpu_to_le16(conn->handle);
+		hci_send_cmd(hdev, HCI_OP_READ_CLOCK_OFFSET, sizeof(clkoff_cp),
+			     &clkoff_cp);
 	}
 
 	conn->state = BT_DISCONN;
@@ -306,7 +309,7 @@ void hci_sco_setup(struct hci_conn *conn, __u8 status)
 		else
 			hci_add_sco(sco, conn->handle);
 	} else {
-		hci_proto_connect_cfm(sco, status);
+		hci_connect_cfm(sco, status);
 		hci_conn_del(sco);
 	}
 }
@@ -415,7 +418,7 @@ static void le_conn_timeout(struct work_struct *work)
 	 * 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)) {
+	if (conn->role == HCI_ROLE_SLAVE) {
 		u8 enable = 0x00;
 		hci_send_cmd(hdev, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable),
 			     &enable);
@@ -448,6 +451,7 @@ 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->rssi = HCI_RSSI_INVALID;
 	conn->tx_power = HCI_TX_POWER_INVALID;
 	conn->max_tx_power = HCI_TX_POWER_INVALID;
 
@@ -517,7 +521,7 @@ 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);
+		cancel_delayed_work(&conn->le_conn_timeout);
 
 		if (hdev->le_pkts)
 			hdev->le_cnt += conn->sent;
@@ -544,6 +548,11 @@ int hci_conn_del(struct hci_conn *conn)
 
 	hci_conn_del_sysfs(conn);
 
+	debugfs_remove_recursive(conn->debugfs);
+
+	if (test_bit(HCI_CONN_PARAM_REMOVAL_PEND, &conn->flags))
+		hci_conn_params_del(conn->hdev, &conn->dst, conn->dst_type);
+
 	hci_dev_put(hdev);
 
 	hci_conn_put(conn);
@@ -562,7 +571,7 @@ struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src)
 
 	list_for_each_entry(d, &hci_dev_list, list) {
 		if (!test_bit(HCI_UP, &d->flags) ||
-		    test_bit(HCI_USER_CHANNEL, &d->dev_flags) ||
+		    hci_dev_test_flag(d, HCI_USER_CHANNEL) ||
 		    d->dev_type != HCI_BREDR)
 			continue;
 
@@ -609,7 +618,7 @@ void hci_le_conn_failed(struct hci_conn *conn, u8 status)
 	mgmt_connect_failed(hdev, &conn->dst, conn->type, conn->dst_type,
 			    status);
 
-	hci_proto_connect_cfm(conn, status);
+	hci_connect_cfm(conn, status);
 
 	hci_conn_del(conn);
 
@@ -624,7 +633,7 @@ void hci_le_conn_failed(struct hci_conn *conn, u8 status)
 	mgmt_reenable_advertising(hdev);
 }
 
-static void create_le_conn_complete(struct hci_dev *hdev, u8 status)
+static void create_le_conn_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
 	struct hci_conn *conn;
 
@@ -656,7 +665,7 @@ static void hci_req_add_le_create_conn(struct hci_request *req,
 	memset(&cp, 0, sizeof(cp));
 
 	/* Update random address, but set require_privacy to false so
-	 * that we never connect with an unresolvable address.
+	 * that we never connect with an non-resolvable address.
 	 */
 	if (hci_update_random_address(req, false, &own_addr_type))
 		return;
@@ -691,7 +700,7 @@ static void hci_req_directed_advertising(struct hci_request *req,
 	 * 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_LE_ADV, &hdev->dev_flags);
+	hci_dev_clear_flag(hdev, HCI_LE_ADV);
 
 	/* Set require_privacy to false so that the remote device has a
 	 * chance of identifying us.
@@ -724,6 +733,14 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst,
 	struct hci_request req;
 	int err;
 
+	/* Let's make sure that le is enabled.*/
+	if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) {
+		if (lmp_le_capable(hdev))
+			return ERR_PTR(-ECONNREFUSED);
+
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
 	/* 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
@@ -782,7 +799,7 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst,
 	 * anyway have to disable it in order to start directed
 	 * advertising.
 	 */
-	if (test_bit(HCI_LE_ADV, &hdev->dev_flags)) {
+	if (hci_dev_test_flag(hdev, HCI_LE_ADV)) {
 		u8 enable = 0x00;
 		hci_req_add(&req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable),
 			    &enable);
@@ -793,7 +810,7 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst,
 		/* If we're active scanning most controllers are unable
 		 * to initiate advertising. Simply reject the attempt.
 		 */
-		if (test_bit(HCI_LE_SCAN, &hdev->dev_flags) &&
+		if (hci_dev_test_flag(hdev, HCI_LE_SCAN) &&
 		    hdev->le_scan_type == LE_SCAN_ACTIVE) {
 			skb_queue_purge(&req.cmd_q);
 			hci_conn_del(conn);
@@ -823,9 +840,9 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst,
 	 * handler for scan disabling knows to set the correct discovery
 	 * state.
 	 */
-	if (test_bit(HCI_LE_SCAN, &hdev->dev_flags)) {
+	if (hci_dev_test_flag(hdev, HCI_LE_SCAN)) {
 		hci_req_add_le_scan_disable(&req);
-		set_bit(HCI_LE_SCAN_INTERRUPTED, &hdev->dev_flags);
+		hci_dev_set_flag(hdev, HCI_LE_SCAN_INTERRUPTED);
 	}
 
 	hci_req_add_le_create_conn(&req, conn);
@@ -847,8 +864,12 @@ struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst,
 {
 	struct hci_conn *acl;
 
-	if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
+	if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) {
+		if (lmp_bredr_capable(hdev))
+			return ERR_PTR(-ECONNREFUSED);
+
 		return ERR_PTR(-EOPNOTSUPP);
+	}
 
 	acl = hci_conn_hash_lookup_ba(hdev, ACL_LINK, dst);
 	if (!acl) {
@@ -921,7 +942,7 @@ int hci_conn_check_link_mode(struct hci_conn *conn)
 	 * 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_dev_test_flag(conn->hdev, HCI_SC_ONLY)) {
 		if (!hci_conn_sc_enabled(conn) ||
 		    !test_bit(HCI_CONN_AES_CCM, &conn->flags) ||
 		    conn->key_type != HCI_LK_AUTH_COMBINATION_P256)
@@ -1075,21 +1096,6 @@ int hci_conn_check_secure(struct hci_conn *conn, __u8 sec_level)
 }
 EXPORT_SYMBOL(hci_conn_check_secure);
 
-/* Change link key */
-int hci_conn_change_link_key(struct hci_conn *conn)
-{
-	BT_DBG("hcon %p", conn);
-
-	if (!test_and_set_bit(HCI_CONN_AUTH_PEND, &conn->flags)) {
-		struct hci_cp_change_conn_link_key cp;
-		cp.handle = cpu_to_le16(conn->handle);
-		hci_send_cmd(conn->hdev, HCI_OP_CHANGE_CONN_LINK_KEY,
-			     sizeof(cp), &cp);
-	}
-
-	return 0;
-}
-
 /* Switch role */
 int hci_conn_switch_role(struct hci_conn *conn, __u8 role)
 {
@@ -1145,7 +1151,7 @@ void hci_conn_hash_flush(struct hci_dev *hdev)
 	list_for_each_entry_safe(c, n, &h->list, list) {
 		c->state = BT_CLOSED;
 
-		hci_proto_disconn_cfm(c, HCI_ERROR_LOCAL_HOST_TERM);
+		hci_disconn_cfm(c, HCI_ERROR_LOCAL_HOST_TERM);
 		hci_conn_del(c);
 	}
 }
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index cb05d7f16a34..c4802f3bd4c5 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -37,6 +37,8 @@
 #include <net/bluetooth/l2cap.h>
 #include <net/bluetooth/mgmt.h>
 
+#include "hci_request.h"
+#include "hci_debugfs.h"
 #include "smp.h"
 
 static void hci_rx_work(struct work_struct *work);
@@ -49,7 +51,7 @@ DEFINE_RWLOCK(hci_dev_list_lock);
 
 /* HCI callback list */
 LIST_HEAD(hci_cb_list);
-DEFINE_RWLOCK(hci_cb_list_lock);
+DEFINE_MUTEX(hci_cb_list_lock);
 
 /* HCI ID Numbering */
 static DEFINE_IDA(hci_index_ida);
@@ -78,7 +80,7 @@ static ssize_t dut_mode_read(struct file *file, char __user *user_buf,
 	struct hci_dev *hdev = file->private_data;
 	char buf[3];
 
-	buf[0] = test_bit(HCI_DUT_MODE, &hdev->dbg_flags) ? 'Y': 'N';
+	buf[0] = hci_dev_test_flag(hdev, HCI_DUT_MODE) ? 'Y': 'N';
 	buf[1] = '\n';
 	buf[2] = '\0';
 	return simple_read_from_buffer(user_buf, count, ppos, buf, 2);
@@ -104,7 +106,7 @@ static ssize_t dut_mode_write(struct file *file, const char __user *user_buf,
 	if (strtobool(buf, &enable))
 		return -EINVAL;
 
-	if (enable == test_bit(HCI_DUT_MODE, &hdev->dbg_flags))
+	if (enable == hci_dev_test_flag(hdev, HCI_DUT_MODE))
 		return -EALREADY;
 
 	hci_req_lock(hdev);
@@ -125,7 +127,7 @@ static ssize_t dut_mode_write(struct file *file, const char __user *user_buf,
 	if (err < 0)
 		return err;
 
-	change_bit(HCI_DUT_MODE, &hdev->dbg_flags);
+	hci_dev_change_flag(hdev, HCI_DUT_MODE);
 
 	return count;
 }
@@ -137,931 +139,18 @@ static const struct file_operations dut_mode_fops = {
 	.llseek		= default_llseek,
 };
 
-static int features_show(struct seq_file *f, void *ptr)
-{
-	struct hci_dev *hdev = f->private;
-	u8 p;
-
-	hci_dev_lock(hdev);
-	for (p = 0; p < HCI_MAX_PAGES && p <= hdev->max_page; p++) {
-		seq_printf(f, "%2u: 0x%2.2x 0x%2.2x 0x%2.2x 0x%2.2x "
-			   "0x%2.2x 0x%2.2x 0x%2.2x 0x%2.2x\n", p,
-			   hdev->features[p][0], hdev->features[p][1],
-			   hdev->features[p][2], hdev->features[p][3],
-			   hdev->features[p][4], hdev->features[p][5],
-			   hdev->features[p][6], hdev->features[p][7]);
-	}
-	if (lmp_le_capable(hdev))
-		seq_printf(f, "LE: 0x%2.2x 0x%2.2x 0x%2.2x 0x%2.2x "
-			   "0x%2.2x 0x%2.2x 0x%2.2x 0x%2.2x\n",
-			   hdev->le_features[0], hdev->le_features[1],
-			   hdev->le_features[2], hdev->le_features[3],
-			   hdev->le_features[4], hdev->le_features[5],
-			   hdev->le_features[6], hdev->le_features[7]);
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-static int features_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, features_show, inode->i_private);
-}
-
-static const struct file_operations features_fops = {
-	.open		= features_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int blacklist_show(struct seq_file *f, void *p)
-{
-	struct hci_dev *hdev = f->private;
-	struct bdaddr_list *b;
-
-	hci_dev_lock(hdev);
-	list_for_each_entry(b, &hdev->blacklist, list)
-		seq_printf(f, "%pMR (type %u)\n", &b->bdaddr, b->bdaddr_type);
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-static int blacklist_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, blacklist_show, inode->i_private);
-}
-
-static const struct file_operations blacklist_fops = {
-	.open		= blacklist_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int whitelist_show(struct seq_file *f, void *p)
-{
-	struct hci_dev *hdev = f->private;
-	struct bdaddr_list *b;
-
-	hci_dev_lock(hdev);
-	list_for_each_entry(b, &hdev->whitelist, list)
-		seq_printf(f, "%pMR (type %u)\n", &b->bdaddr, b->bdaddr_type);
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-static int whitelist_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, whitelist_show, inode->i_private);
-}
-
-static const struct file_operations whitelist_fops = {
-	.open		= whitelist_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int uuids_show(struct seq_file *f, void *p)
-{
-	struct hci_dev *hdev = f->private;
-	struct bt_uuid *uuid;
-
-	hci_dev_lock(hdev);
-	list_for_each_entry(uuid, &hdev->uuids, list) {
-		u8 i, val[16];
-
-		/* The Bluetooth UUID values are stored in big endian,
-		 * but with reversed byte order. So convert them into
-		 * the right order for the %pUb modifier.
-		 */
-		for (i = 0; i < 16; i++)
-			val[i] = uuid->uuid[15 - i];
-
-		seq_printf(f, "%pUb\n", val);
-	}
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-static int uuids_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, uuids_show, inode->i_private);
-}
-
-static const struct file_operations uuids_fops = {
-	.open		= uuids_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int inquiry_cache_show(struct seq_file *f, void *p)
-{
-	struct hci_dev *hdev = f->private;
-	struct discovery_state *cache = &hdev->discovery;
-	struct inquiry_entry *e;
-
-	hci_dev_lock(hdev);
-
-	list_for_each_entry(e, &cache->all, all) {
-		struct inquiry_data *data = &e->data;
-		seq_printf(f, "%pMR %d %d %d 0x%.2x%.2x%.2x 0x%.4x %d %d %u\n",
-			   &data->bdaddr,
-			   data->pscan_rep_mode, data->pscan_period_mode,
-			   data->pscan_mode, data->dev_class[2],
-			   data->dev_class[1], data->dev_class[0],
-			   __le16_to_cpu(data->clock_offset),
-			   data->rssi, data->ssp_mode, e->timestamp);
-	}
-
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-static int inquiry_cache_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, inquiry_cache_show, inode->i_private);
-}
-
-static const struct file_operations inquiry_cache_fops = {
-	.open		= inquiry_cache_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int link_keys_show(struct seq_file *f, void *ptr)
-{
-	struct hci_dev *hdev = f->private;
-	struct list_head *p, *n;
-
-	hci_dev_lock(hdev);
-	list_for_each_safe(p, n, &hdev->link_keys) {
-		struct link_key *key = list_entry(p, struct link_key, list);
-		seq_printf(f, "%pMR %u %*phN %u\n", &key->bdaddr, key->type,
-			   HCI_LINK_KEY_SIZE, key->val, key->pin_len);
-	}
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-static int link_keys_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, link_keys_show, inode->i_private);
-}
-
-static const struct file_operations link_keys_fops = {
-	.open		= link_keys_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int dev_class_show(struct seq_file *f, void *ptr)
-{
-	struct hci_dev *hdev = f->private;
-
-	hci_dev_lock(hdev);
-	seq_printf(f, "0x%.2x%.2x%.2x\n", hdev->dev_class[2],
-		   hdev->dev_class[1], hdev->dev_class[0]);
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-static int dev_class_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, dev_class_show, inode->i_private);
-}
-
-static const struct file_operations dev_class_fops = {
-	.open		= dev_class_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int voice_setting_get(void *data, u64 *val)
-{
-	struct hci_dev *hdev = data;
-
-	hci_dev_lock(hdev);
-	*val = hdev->voice_setting;
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-DEFINE_SIMPLE_ATTRIBUTE(voice_setting_fops, voice_setting_get,
-			NULL, "0x%4.4llx\n");
-
-static int auto_accept_delay_set(void *data, u64 val)
-{
-	struct hci_dev *hdev = data;
-
-	hci_dev_lock(hdev);
-	hdev->auto_accept_delay = val;
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-static int auto_accept_delay_get(void *data, u64 *val)
-{
-	struct hci_dev *hdev = data;
-
-	hci_dev_lock(hdev);
-	*val = hdev->auto_accept_delay;
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-DEFINE_SIMPLE_ATTRIBUTE(auto_accept_delay_fops, auto_accept_delay_get,
-			auto_accept_delay_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->dbg_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->dbg_flags))
-		return -EALREADY;
-
-	change_bit(HCI_FORCE_SC, &hdev->dbg_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;
-
-	if (val != 0 && (val < 500 || val > 3600000))
-		return -EINVAL;
-
-	hci_dev_lock(hdev);
-	hdev->idle_timeout = val;
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-static int idle_timeout_get(void *data, u64 *val)
-{
-	struct hci_dev *hdev = data;
-
-	hci_dev_lock(hdev);
-	*val = hdev->idle_timeout;
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-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;
-
-	if (val == 0 || val % 2 || val > hdev->sniff_max_interval)
-		return -EINVAL;
-
-	hci_dev_lock(hdev);
-	hdev->sniff_min_interval = val;
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-static int sniff_min_interval_get(void *data, u64 *val)
-{
-	struct hci_dev *hdev = data;
-
-	hci_dev_lock(hdev);
-	*val = hdev->sniff_min_interval;
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-DEFINE_SIMPLE_ATTRIBUTE(sniff_min_interval_fops, sniff_min_interval_get,
-			sniff_min_interval_set, "%llu\n");
-
-static int sniff_max_interval_set(void *data, u64 val)
-{
-	struct hci_dev *hdev = data;
-
-	if (val == 0 || val % 2 || val < hdev->sniff_min_interval)
-		return -EINVAL;
-
-	hci_dev_lock(hdev);
-	hdev->sniff_max_interval = val;
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-static int sniff_max_interval_get(void *data, u64 *val)
-{
-	struct hci_dev *hdev = data;
-
-	hci_dev_lock(hdev);
-	*val = hdev->sniff_max_interval;
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-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;
-
-	hci_dev_lock(hdev);
-	seq_printf(f, "%pMR\n", &hdev->static_addr);
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-static int static_address_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, static_address_show, inode->i_private);
-}
-
-static const struct file_operations static_address_fops = {
-	.open		= static_address_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static ssize_t force_static_address_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_STATIC_ADDR, &hdev->dbg_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->dbg_flags))
-		return -EALREADY;
-
-	change_bit(HCI_FORCE_STATIC_ADDR, &hdev->dbg_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);
-	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 white_list_open(struct inode *inode, struct file *file)
-{
-	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);
-	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;
-}
-
-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)
-{
-	struct hci_dev *hdev = f->private;
-	struct list_head *p, *n;
-
-	hci_dev_lock(hdev);
-	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 0x%02x %u %.4x %.16llx %*phN\n",
-			   &ltk->bdaddr, ltk->bdaddr_type, ltk->authenticated,
-			   ltk->type, ltk->enc_size, __le16_to_cpu(ltk->ediv),
-			   __le64_to_cpu(ltk->rand), 16, ltk->val);
-	}
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-static int long_term_keys_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, long_term_keys_show, inode->i_private);
-}
-
-static const struct file_operations long_term_keys_fops = {
-	.open		= long_term_keys_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int conn_min_interval_set(void *data, u64 val)
-{
-	struct hci_dev *hdev = data;
-
-	if (val < 0x0006 || val > 0x0c80 || val > hdev->le_conn_max_interval)
-		return -EINVAL;
-
-	hci_dev_lock(hdev);
-	hdev->le_conn_min_interval = val;
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-static int conn_min_interval_get(void *data, u64 *val)
-{
-	struct hci_dev *hdev = data;
-
-	hci_dev_lock(hdev);
-	*val = hdev->le_conn_min_interval;
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-DEFINE_SIMPLE_ATTRIBUTE(conn_min_interval_fops, conn_min_interval_get,
-			conn_min_interval_set, "%llu\n");
-
-static int conn_max_interval_set(void *data, u64 val)
-{
-	struct hci_dev *hdev = data;
-
-	if (val < 0x0006 || val > 0x0c80 || val < hdev->le_conn_min_interval)
-		return -EINVAL;
-
-	hci_dev_lock(hdev);
-	hdev->le_conn_max_interval = val;
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-static int conn_max_interval_get(void *data, u64 *val)
-{
-	struct hci_dev *hdev = data;
-
-	hci_dev_lock(hdev);
-	*val = hdev->le_conn_max_interval;
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-DEFINE_SIMPLE_ATTRIBUTE(conn_max_interval_fops, conn_max_interval_get,
-			conn_max_interval_set, "%llu\n");
-
-static int conn_latency_set(void *data, u64 val)
-{
-	struct hci_dev *hdev = data;
-
-	if (val > 0x01f3)
-		return -EINVAL;
-
-	hci_dev_lock(hdev);
-	hdev->le_conn_latency = val;
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-static int conn_latency_get(void *data, u64 *val)
-{
-	struct hci_dev *hdev = data;
-
-	hci_dev_lock(hdev);
-	*val = hdev->le_conn_latency;
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-DEFINE_SIMPLE_ATTRIBUTE(conn_latency_fops, conn_latency_get,
-			conn_latency_set, "%llu\n");
-
-static int supervision_timeout_set(void *data, u64 val)
-{
-	struct hci_dev *hdev = data;
-
-	if (val < 0x000a || val > 0x0c80)
-		return -EINVAL;
-
-	hci_dev_lock(hdev);
-	hdev->le_supv_timeout = val;
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-static int supervision_timeout_get(void *data, u64 *val)
-{
-	struct hci_dev *hdev = data;
-
-	hci_dev_lock(hdev);
-	*val = hdev->le_supv_timeout;
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-DEFINE_SIMPLE_ATTRIBUTE(supervision_timeout_fops, supervision_timeout_get,
-			supervision_timeout_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 int adv_min_interval_set(void *data, u64 val)
-{
-	struct hci_dev *hdev = data;
-
-	if (val < 0x0020 || val > 0x4000 || val > hdev->le_adv_max_interval)
-		return -EINVAL;
-
-	hci_dev_lock(hdev);
-	hdev->le_adv_min_interval = val;
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-static int adv_min_interval_get(void *data, u64 *val)
-{
-	struct hci_dev *hdev = data;
-
-	hci_dev_lock(hdev);
-	*val = hdev->le_adv_min_interval;
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-DEFINE_SIMPLE_ATTRIBUTE(adv_min_interval_fops, adv_min_interval_get,
-			adv_min_interval_set, "%llu\n");
-
-static int adv_max_interval_set(void *data, u64 val)
-{
-	struct hci_dev *hdev = data;
-
-	if (val < 0x0020 || val > 0x4000 || val < hdev->le_adv_min_interval)
-		return -EINVAL;
-
-	hci_dev_lock(hdev);
-	hdev->le_adv_max_interval = val;
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-static int adv_max_interval_get(void *data, u64 *val)
-{
-	struct hci_dev *hdev = data;
-
-	hci_dev_lock(hdev);
-	*val = hdev->le_adv_max_interval;
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-DEFINE_SIMPLE_ATTRIBUTE(adv_max_interval_fops, adv_max_interval_get,
-			adv_max_interval_set, "%llu\n");
-
-static int device_list_show(struct seq_file *f, void *ptr)
-{
-	struct hci_dev *hdev = f->private;
-	struct hci_conn_params *p;
-
-	hci_dev_lock(hdev);
-	list_for_each_entry(p, &hdev->le_conn_params, list) {
-		seq_printf(f, "%pMR %u %u\n", &p->addr, p->addr_type,
-			   p->auto_connect);
-	}
-	hci_dev_unlock(hdev);
-
-	return 0;
-}
-
-static int device_list_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, device_list_show, inode->i_private);
-}
-
-static const struct file_operations device_list_fops = {
-	.open		= device_list_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 /* ---- HCI requests ---- */
 
-static void hci_req_sync_complete(struct hci_dev *hdev, u8 result)
+static void hci_req_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode,
+				  struct sk_buff *skb)
 {
 	BT_DBG("%s result 0x%2.2x", hdev->name, result);
 
 	if (hdev->req_status == HCI_REQ_PEND) {
 		hdev->req_result = result;
 		hdev->req_status = HCI_REQ_DONE;
+		if (skb)
+			hdev->req_skb = skb_get(skb);
 		wake_up_interruptible(&hdev->req_wait_q);
 	}
 }
@@ -1077,66 +166,12 @@ static void hci_req_cancel(struct hci_dev *hdev, int err)
 	}
 }
 
-static struct sk_buff *hci_get_cmd_complete(struct hci_dev *hdev, u16 opcode,
-					    u8 event)
-{
-	struct hci_ev_cmd_complete *ev;
-	struct hci_event_hdr *hdr;
-	struct sk_buff *skb;
-
-	hci_dev_lock(hdev);
-
-	skb = hdev->recv_evt;
-	hdev->recv_evt = NULL;
-
-	hci_dev_unlock(hdev);
-
-	if (!skb)
-		return ERR_PTR(-ENODATA);
-
-	if (skb->len < sizeof(*hdr)) {
-		BT_ERR("Too short HCI event");
-		goto failed;
-	}
-
-	hdr = (void *) skb->data;
-	skb_pull(skb, HCI_EVENT_HDR_SIZE);
-
-	if (event) {
-		if (hdr->evt != event)
-			goto failed;
-		return skb;
-	}
-
-	if (hdr->evt != HCI_EV_CMD_COMPLETE) {
-		BT_DBG("Last event is not cmd complete (0x%2.2x)", hdr->evt);
-		goto failed;
-	}
-
-	if (skb->len < sizeof(*ev)) {
-		BT_ERR("Too short cmd_complete event");
-		goto failed;
-	}
-
-	ev = (void *) skb->data;
-	skb_pull(skb, sizeof(*ev));
-
-	if (opcode == __le16_to_cpu(ev->opcode))
-		return skb;
-
-	BT_DBG("opcode doesn't match (0x%2.2x != 0x%2.2x)", opcode,
-	       __le16_to_cpu(ev->opcode));
-
-failed:
-	kfree_skb(skb);
-	return ERR_PTR(-ENODATA);
-}
-
 struct sk_buff *__hci_cmd_sync_ev(struct hci_dev *hdev, u16 opcode, u32 plen,
 				  const void *param, u8 event, u32 timeout)
 {
 	DECLARE_WAITQUEUE(wait, current);
 	struct hci_request req;
+	struct sk_buff *skb;
 	int err = 0;
 
 	BT_DBG("%s", hdev->name);
@@ -1147,13 +182,16 @@ struct sk_buff *__hci_cmd_sync_ev(struct hci_dev *hdev, u16 opcode, u32 plen,
 
 	hdev->req_status = HCI_REQ_PEND;
 
-	err = hci_req_run(&req, hci_req_sync_complete);
-	if (err < 0)
-		return ERR_PTR(err);
-
 	add_wait_queue(&hdev->req_wait_q, &wait);
 	set_current_state(TASK_INTERRUPTIBLE);
 
+	err = hci_req_run_skb(&req, hci_req_sync_complete);
+	if (err < 0) {
+		remove_wait_queue(&hdev->req_wait_q, &wait);
+		set_current_state(TASK_RUNNING);
+		return ERR_PTR(err);
+	}
+
 	schedule_timeout(timeout);
 
 	remove_wait_queue(&hdev->req_wait_q, &wait);
@@ -1176,13 +214,20 @@ struct sk_buff *__hci_cmd_sync_ev(struct hci_dev *hdev, u16 opcode, u32 plen,
 	}
 
 	hdev->req_status = hdev->req_result = 0;
+	skb = hdev->req_skb;
+	hdev->req_skb = NULL;
 
 	BT_DBG("%s end: err %d", hdev->name, err);
 
-	if (err < 0)
+	if (err < 0) {
+		kfree_skb(skb);
 		return ERR_PTR(err);
+	}
 
-	return hci_get_cmd_complete(hdev, opcode, event);
+	if (!skb)
+		return ERR_PTR(-ENODATA);
+
+	return skb;
 }
 EXPORT_SYMBOL(__hci_cmd_sync_ev);
 
@@ -1211,10 +256,16 @@ static int __hci_req_sync(struct hci_dev *hdev,
 
 	func(&req, opt);
 
-	err = hci_req_run(&req, hci_req_sync_complete);
+	add_wait_queue(&hdev->req_wait_q, &wait);
+	set_current_state(TASK_INTERRUPTIBLE);
+
+	err = hci_req_run_skb(&req, hci_req_sync_complete);
 	if (err < 0) {
 		hdev->req_status = 0;
 
+		remove_wait_queue(&hdev->req_wait_q, &wait);
+		set_current_state(TASK_RUNNING);
+
 		/* ENODATA means the HCI request command queue is empty.
 		 * This can happen when a request with conditionals doesn't
 		 * trigger any commands to be sent. This is normal behavior
@@ -1226,9 +277,6 @@ static int __hci_req_sync(struct hci_dev *hdev,
 		return err;
 	}
 
-	add_wait_queue(&hdev->req_wait_q, &wait);
-	set_current_state(TASK_INTERRUPTIBLE);
-
 	schedule_timeout(timeout);
 
 	remove_wait_queue(&hdev->req_wait_q, &wait);
@@ -1298,7 +346,7 @@ static void bredr_init(struct hci_request *req)
 	hci_req_add(req, HCI_OP_READ_BD_ADDR, 0, NULL);
 }
 
-static void amp_init(struct hci_request *req)
+static void amp_init1(struct hci_request *req)
 {
 	req->hdev->flow_ctl_mode = HCI_FLOW_CTL_MODE_BLOCK_BASED;
 
@@ -1308,9 +356,6 @@ static void amp_init(struct hci_request *req)
 	/* Read Local Supported Commands */
 	hci_req_add(req, HCI_OP_READ_LOCAL_COMMANDS, 0, NULL);
 
-	/* Read Local Supported Features */
-	hci_req_add(req, HCI_OP_READ_LOCAL_FEATURES, 0, NULL);
-
 	/* Read Local AMP Info */
 	hci_req_add(req, HCI_OP_READ_LOCAL_AMP_INFO, 0, NULL);
 
@@ -1324,6 +369,16 @@ static void amp_init(struct hci_request *req)
 	hci_req_add(req, HCI_OP_READ_LOCATION_DATA, 0, NULL);
 }
 
+static void amp_init2(struct hci_request *req)
+{
+	/* Read Local Supported Features. Not all AMP controllers
+	 * support this so it's placed conditionally in the second
+	 * stage init.
+	 */
+	if (req->hdev->commands[14] & 0x20)
+		hci_req_add(req, HCI_OP_READ_LOCAL_FEATURES, 0, NULL);
+}
+
 static void hci_init1_req(struct hci_request *req, unsigned long opt)
 {
 	struct hci_dev *hdev = req->hdev;
@@ -1340,7 +395,7 @@ static void hci_init1_req(struct hci_request *req, unsigned long opt)
 		break;
 
 	case HCI_AMP:
-		amp_init(req);
+		amp_init1(req);
 		break;
 
 	default:
@@ -1351,8 +406,6 @@ static void hci_init1_req(struct hci_request *req, unsigned long opt)
 
 static void bredr_setup(struct hci_request *req)
 {
-	struct hci_dev *hdev = req->hdev;
-
 	__le16 param;
 	__u8 flt_type;
 
@@ -1381,14 +434,6 @@ static void bredr_setup(struct hci_request *req)
 	/* Connection accept timeout ~20 secs */
 	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,
-	 * but it does not support page scan related HCI commands.
-	 */
-	if (hdev->manufacturer != 31 && hdev->hci_ver > BLUETOOTH_VER_1_1) {
-		hci_req_add(req, HCI_OP_READ_PAGE_SCAN_ACTIVITY, 0, NULL);
-		hci_req_add(req, HCI_OP_READ_PAGE_SCAN_TYPE, 0, NULL);
-	}
 }
 
 static void le_setup(struct hci_request *req)
@@ -1412,44 +457,7 @@ static void le_setup(struct hci_request *req)
 
 	/* LE-only controllers have LE implicitly enabled */
 	if (!lmp_bredr_capable(hdev))
-		set_bit(HCI_LE_ENABLED, &hdev->dev_flags);
-}
-
-static u8 hci_get_inquiry_mode(struct hci_dev *hdev)
-{
-	if (lmp_ext_inq_capable(hdev))
-		return 0x02;
-
-	if (lmp_inq_rssi_capable(hdev))
-		return 0x01;
-
-	if (hdev->manufacturer == 11 && hdev->hci_rev == 0x00 &&
-	    hdev->lmp_subver == 0x0757)
-		return 0x01;
-
-	if (hdev->manufacturer == 15) {
-		if (hdev->hci_rev == 0x03 && hdev->lmp_subver == 0x6963)
-			return 0x01;
-		if (hdev->hci_rev == 0x09 && hdev->lmp_subver == 0x6963)
-			return 0x01;
-		if (hdev->hci_rev == 0x00 && hdev->lmp_subver == 0x6965)
-			return 0x01;
-	}
-
-	if (hdev->manufacturer == 31 && hdev->hci_rev == 0x2005 &&
-	    hdev->lmp_subver == 0x1805)
-		return 0x01;
-
-	return 0x00;
-}
-
-static void hci_setup_inquiry_mode(struct hci_request *req)
-{
-	u8 mode;
-
-	mode = hci_get_inquiry_mode(req->hdev);
-
-	hci_req_add(req, HCI_OP_WRITE_INQUIRY_MODE, 1, &mode);
+		hci_dev_set_flag(hdev, HCI_LE_ENABLED);
 }
 
 static void hci_setup_event_mask(struct hci_request *req)
@@ -1533,18 +541,27 @@ static void hci_init2_req(struct hci_request *req, unsigned long opt)
 {
 	struct hci_dev *hdev = req->hdev;
 
+	if (hdev->dev_type == HCI_AMP)
+		return amp_init2(req);
+
 	if (lmp_bredr_capable(hdev))
 		bredr_setup(req);
 	else
-		clear_bit(HCI_BREDR_ENABLED, &hdev->dev_flags);
+		hci_dev_clear_flag(hdev, HCI_BREDR_ENABLED);
 
 	if (lmp_le_capable(hdev))
 		le_setup(req);
 
-	/* AVM Berlin (31), aka "BlueFRITZ!", doesn't support the read
-	 * local supported commands HCI command.
+	/* All Bluetooth 1.2 and later controllers should support the
+	 * HCI command for reading the local supported commands.
+	 *
+	 * Unfortunately some controllers indicate Bluetooth 1.2 support,
+	 * but do not have support for this command. If that is the case,
+	 * the driver can quirk the behavior and skip reading the local
+	 * supported commands.
 	 */
-	if (hdev->manufacturer != 31 && hdev->hci_ver > BLUETOOTH_VER_1_1)
+	if (hdev->hci_ver > BLUETOOTH_VER_1_1 &&
+	    !test_bit(HCI_QUIRK_BROKEN_LOCAL_COMMANDS, &hdev->quirks))
 		hci_req_add(req, HCI_OP_READ_LOCAL_COMMANDS, 0, NULL);
 
 	if (lmp_ssp_capable(hdev)) {
@@ -1556,8 +573,9 @@ static void hci_init2_req(struct hci_request *req, unsigned long opt)
 		 */
 		hdev->max_page = 0x01;
 
-		if (test_bit(HCI_SSP_ENABLED, &hdev->dev_flags)) {
+		if (hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) {
 			u8 mode = 0x01;
+
 			hci_req_add(req, HCI_OP_WRITE_SSP_MODE,
 				    sizeof(mode), &mode);
 		} else {
@@ -1570,8 +588,18 @@ static void hci_init2_req(struct hci_request *req, unsigned long opt)
 		}
 	}
 
-	if (lmp_inq_rssi_capable(hdev))
-		hci_setup_inquiry_mode(req);
+	if (lmp_inq_rssi_capable(hdev) ||
+	    test_bit(HCI_QUIRK_FIXUP_INQUIRY_MODE, &hdev->quirks)) {
+		u8 mode;
+
+		/* If Extended Inquiry Result events are supported, then
+		 * they are clearly preferred over Inquiry Result with RSSI
+		 * events.
+		 */
+		mode = lmp_ext_inq_capable(hdev) ? 0x02 : 0x01;
+
+		hci_req_add(req, HCI_OP_WRITE_INQUIRY_MODE, 1, &mode);
+	}
 
 	if (lmp_inq_tx_pwr_capable(hdev))
 		hci_req_add(req, HCI_OP_READ_INQ_RSP_TX_POWER, 0, NULL);
@@ -1584,7 +612,7 @@ static void hci_init2_req(struct hci_request *req, unsigned long opt)
 			    sizeof(cp), &cp);
 	}
 
-	if (test_bit(HCI_LINK_SECURITY, &hdev->dev_flags)) {
+	if (hci_dev_test_flag(hdev, HCI_LINK_SECURITY)) {
 		u8 enable = 1;
 		hci_req_add(req, HCI_OP_WRITE_AUTH_ENABLE, sizeof(enable),
 			    &enable);
@@ -1621,7 +649,7 @@ static void hci_set_le_support(struct hci_request *req)
 
 	memset(&cp, 0, sizeof(cp));
 
-	if (test_bit(HCI_LE_ENABLED, &hdev->dev_flags)) {
+	if (hci_dev_test_flag(hdev, HCI_LE_ENABLED)) {
 		cp.le = 0x01;
 		cp.simul = 0x00;
 	}
@@ -1670,32 +698,27 @@ static void hci_init3_req(struct hci_request *req, unsigned long opt)
 
 	hci_setup_event_mask(req);
 
-	/* Some Broadcom based Bluetooth controllers do not support the
-	 * Delete Stored Link Key command. They are clearly indicating its
-	 * absence in the bit mask of supported commands.
-	 *
-	 * Check the supported commands and only if the the command is marked
-	 * 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 &&
-	    !test_bit(HCI_QUIRK_BROKEN_STORED_LINK_KEY, &hdev->quirks)) {
-		struct hci_cp_delete_stored_link_key cp;
+	if (hdev->commands[6] & 0x20) {
+		struct hci_cp_read_stored_link_key cp;
 
 		bacpy(&cp.bdaddr, BDADDR_ANY);
-		cp.delete_all = 0x01;
-		hci_req_add(req, HCI_OP_DELETE_STORED_LINK_KEY,
-			    sizeof(cp), &cp);
+		cp.read_all = 0x01;
+		hci_req_add(req, HCI_OP_READ_STORED_LINK_KEY, sizeof(cp), &cp);
 	}
 
 	if (hdev->commands[5] & 0x10)
 		hci_setup_link_policy(req);
 
+	if (hdev->commands[8] & 0x01)
+		hci_req_add(req, HCI_OP_READ_PAGE_SCAN_ACTIVITY, 0, NULL);
+
+	/* Some older Broadcom based Bluetooth 1.2 controllers do not
+	 * support the Read Page Scan Type command. Check support for
+	 * this command in the bit mask of supported commands.
+	 */
+	if (hdev->commands[13] & 0x01)
+		hci_req_add(req, HCI_OP_READ_PAGE_SCAN_TYPE, 0, NULL);
+
 	if (lmp_le_capable(hdev)) {
 		u8 events[8];
 
@@ -1713,6 +736,34 @@ static void hci_init3_req(struct hci_request *req, unsigned long opt)
 						 * Parameter Request
 						 */
 
+		/* If the controller supports the Data Length Extension
+		 * feature, enable the corresponding event.
+		 */
+		if (hdev->le_features[0] & HCI_LE_DATA_LEN_EXT)
+			events[0] |= 0x40;	/* LE Data Length Change */
+
+		/* If the controller supports Extended Scanner Filter
+		 * Policies, enable the correspondig event.
+		 */
+		if (hdev->le_features[0] & HCI_LE_EXT_SCAN_POLICY)
+			events[1] |= 0x04;	/* LE Direct Advertising
+						 * Report
+						 */
+
+		/* If the controller supports the LE Read Local P-256
+		 * Public Key command, enable the corresponding event.
+		 */
+		if (hdev->commands[34] & 0x02)
+			events[0] |= 0x80;	/* LE Read Local P-256
+						 * Public Key Complete
+						 */
+
+		/* If the controller supports the LE Generate DHKey
+		 * command, enable the corresponding event.
+		 */
+		if (hdev->commands[34] & 0x04)
+			events[1] |= 0x01;	/* LE Generate DHKey Complete */
+
 		hci_req_add(req, HCI_OP_LE_SET_EVENT_MASK, sizeof(events),
 			    events);
 
@@ -1721,6 +772,14 @@ static void hci_init3_req(struct hci_request *req, unsigned long opt)
 			hci_req_add(req, HCI_OP_LE_READ_ADV_TX_POWER, 0, NULL);
 		}
 
+		if (hdev->le_features[0] & HCI_LE_DATA_LEN_EXT) {
+			/* Read LE Maximum Data Length */
+			hci_req_add(req, HCI_OP_LE_READ_MAX_DATA_LEN, 0, NULL);
+
+			/* Read LE Suggested Default Data Length */
+			hci_req_add(req, HCI_OP_LE_READ_DEF_DATA_LEN, 0, NULL);
+		}
+
 		hci_set_le_support(req);
 	}
 
@@ -1738,6 +797,29 @@ static void hci_init4_req(struct hci_request *req, unsigned long opt)
 {
 	struct hci_dev *hdev = req->hdev;
 
+	/* Some Broadcom based Bluetooth controllers do not support the
+	 * Delete Stored Link Key command. They are clearly indicating its
+	 * absence in the bit mask of supported commands.
+	 *
+	 * Check the supported commands and only if the the command is marked
+	 * 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 &&
+	    !test_bit(HCI_QUIRK_BROKEN_STORED_LINK_KEY, &hdev->quirks)) {
+		struct hci_cp_delete_stored_link_key cp;
+
+		bacpy(&cp.bdaddr, BDADDR_ANY);
+		cp.delete_all = 0x01;
+		hci_req_add(req, HCI_OP_DELETE_STORED_LINK_KEY,
+			    sizeof(cp), &cp);
+	}
+
 	/* Set event mask page 2 if the HCI command for it is supported */
 	if (hdev->commands[22] & 0x04)
 		hci_set_event_mask_page_2(req);
@@ -1755,10 +837,10 @@ static void hci_init4_req(struct hci_request *req, unsigned long opt)
 		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->dbg_flags)) &&
-	    test_bit(HCI_SC_ENABLED, &hdev->dev_flags)) {
+	if (hci_dev_test_flag(hdev, HCI_SSP_ENABLED) &&
+	    bredr_sc_enabled(hdev)) {
 		u8 support = 0x01;
+
 		hci_req_add(req, HCI_OP_WRITE_SC_SUPPORT,
 			    sizeof(support), &support);
 	}
@@ -1775,22 +857,22 @@ static int __hci_init(struct hci_dev *hdev)
 	/* The Device Under Test (DUT) mode is special and available for
 	 * all controller types. So just create it early on.
 	 */
-	if (test_bit(HCI_SETUP, &hdev->dev_flags)) {
+	if (hci_dev_test_flag(hdev, HCI_SETUP)) {
 		debugfs_create_file("dut_mode", 0644, hdev->debugfs, hdev,
 				    &dut_mode_fops);
 	}
 
+	err = __hci_req_sync(hdev, hci_init2_req, 0, HCI_INIT_TIMEOUT);
+	if (err < 0)
+		return err;
+
 	/* HCI_BREDR covers both single-mode LE, BR/EDR and dual-mode
 	 * BR/EDR/LE type controllers. AMP controllers only need the
-	 * first stage init.
+	 * first two stages of init.
 	 */
 	if (hdev->dev_type != HCI_BREDR)
 		return 0;
 
-	err = __hci_req_sync(hdev, hci_init2_req, 0, HCI_INIT_TIMEOUT);
-	if (err < 0)
-		return err;
-
 	err = __hci_req_sync(hdev, hci_init3_req, 0, HCI_INIT_TIMEOUT);
 	if (err < 0)
 		return err;
@@ -1799,108 +881,29 @@ static int __hci_init(struct hci_dev *hdev)
 	if (err < 0)
 		return err;
 
-	/* Only create debugfs entries during the initial setup
-	 * phase and not every time the controller gets powered on.
+	/* This function is only called when the controller is actually in
+	 * configured state. When the controller is marked as unconfigured,
+	 * this initialization procedure is not run.
+	 *
+	 * It means that it is possible that a controller runs through its
+	 * setup phase and then discovers missing settings. If that is the
+	 * case, then this function will not be called. It then will only
+	 * be called during the config phase.
+	 *
+	 * So only when in setup phase or config phase, create the debugfs
+	 * entries and register the SMP channels.
 	 */
-	if (!test_bit(HCI_SETUP, &hdev->dev_flags))
+	if (!hci_dev_test_flag(hdev, HCI_SETUP) &&
+	    !hci_dev_test_flag(hdev, HCI_CONFIG))
 		return 0;
 
-	debugfs_create_file("features", 0444, hdev->debugfs, hdev,
-			    &features_fops);
-	debugfs_create_u16("manufacturer", 0444, hdev->debugfs,
-			   &hdev->manufacturer);
-	debugfs_create_u8("hci_version", 0444, hdev->debugfs, &hdev->hci_ver);
-	debugfs_create_u16("hci_revision", 0444, hdev->debugfs, &hdev->hci_rev);
-	debugfs_create_file("blacklist", 0444, hdev->debugfs, hdev,
-			    &blacklist_fops);
-	debugfs_create_file("whitelist", 0444, hdev->debugfs, hdev,
-			    &whitelist_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("dev_class", 0444, hdev->debugfs,
-				    hdev, &dev_class_fops);
-		debugfs_create_file("voice_setting", 0444, hdev->debugfs,
-				    hdev, &voice_setting_fops);
-	}
-
-	if (lmp_ssp_capable(hdev)) {
-		debugfs_create_file("auto_accept_delay", 0644, hdev->debugfs,
-				    hdev, &auto_accept_delay_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);
-	}
+	hci_debugfs_create_common(hdev);
 
-	if (lmp_sniff_capable(hdev)) {
-		debugfs_create_file("idle_timeout", 0644, hdev->debugfs,
-				    hdev, &idle_timeout_fops);
-		debugfs_create_file("sniff_min_interval", 0644, hdev->debugfs,
-				    hdev, &sniff_min_interval_fops);
-		debugfs_create_file("sniff_max_interval", 0644, hdev->debugfs,
-				    hdev, &sniff_max_interval_fops);
-	}
+	if (lmp_bredr_capable(hdev))
+		hci_debugfs_create_bredr(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("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("conn_latency", 0644, hdev->debugfs,
-				    hdev, &conn_latency_fops);
-		debugfs_create_file("supervision_timeout", 0644, hdev->debugfs,
-				    hdev, &supervision_timeout_fops);
-		debugfs_create_file("adv_channel_map", 0644, hdev->debugfs,
-				    hdev, &adv_channel_map_fops);
-		debugfs_create_file("adv_min_interval", 0644, hdev->debugfs,
-				    hdev, &adv_min_interval_fops);
-		debugfs_create_file("adv_max_interval", 0644, hdev->debugfs,
-				    hdev, &adv_max_interval_fops);
-		debugfs_create_file("device_list", 0444, hdev->debugfs, hdev,
-				    &device_list_fops);
-		debugfs_create_u16("discov_interleaved_timeout", 0644,
-				   hdev->debugfs,
-				   &hdev->discov_interleaved_timeout);
-
-		smp_register(hdev);
-	}
+	if (lmp_le_capable(hdev))
+		hci_debugfs_create_le(hdev);
 
 	return 0;
 }
@@ -2138,7 +1141,7 @@ u32 hci_inquiry_cache_update(struct hci_dev *hdev, struct inquiry_data *data,
 
 	BT_DBG("cache %p, %pMR", cache, &data->bdaddr);
 
-	hci_remove_remote_oob_data(hdev, &data->bdaddr);
+	hci_remove_remote_oob_data(hdev, &data->bdaddr, BDADDR_BREDR);
 
 	if (!data->ssp_mode)
 		flags |= MGMT_DEV_FOUND_LEGACY_PAIRING;
@@ -2253,12 +1256,12 @@ int hci_inquiry(void __user *arg)
 	if (!hdev)
 		return -ENODEV;
 
-	if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) {
+	if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) {
 		err = -EBUSY;
 		goto done;
 	}
 
-	if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) {
+	if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) {
 		err = -EOPNOTSUPP;
 		goto done;
 	}
@@ -2268,7 +1271,7 @@ int hci_inquiry(void __user *arg)
 		goto done;
 	}
 
-	if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) {
+	if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) {
 		err = -EOPNOTSUPP;
 		goto done;
 	}
@@ -2340,17 +1343,17 @@ static int hci_dev_do_open(struct hci_dev *hdev)
 
 	hci_req_lock(hdev);
 
-	if (test_bit(HCI_UNREGISTER, &hdev->dev_flags)) {
+	if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) {
 		ret = -ENODEV;
 		goto done;
 	}
 
-	if (!test_bit(HCI_SETUP, &hdev->dev_flags) &&
-	    !test_bit(HCI_CONFIG, &hdev->dev_flags)) {
+	if (!hci_dev_test_flag(hdev, HCI_SETUP) &&
+	    !hci_dev_test_flag(hdev, HCI_CONFIG)) {
 		/* Check for rfkill but allow the HCI setup stage to
 		 * proceed (which in itself doesn't cause any RF activity).
 		 */
-		if (test_bit(HCI_RFKILLED, &hdev->dev_flags)) {
+		if (hci_dev_test_flag(hdev, HCI_RFKILLED)) {
 			ret = -ERFKILL;
 			goto done;
 		}
@@ -2367,7 +1370,7 @@ static int hci_dev_do_open(struct hci_dev *hdev)
 		 * This check is only valid for BR/EDR controllers
 		 * since AMP controllers do not have an address.
 		 */
-		if (!test_bit(HCI_USER_CHANNEL, &hdev->dev_flags) &&
+		if (!hci_dev_test_flag(hdev, HCI_USER_CHANNEL) &&
 		    hdev->dev_type == HCI_BREDR &&
 		    !bacmp(&hdev->bdaddr, BDADDR_ANY) &&
 		    !bacmp(&hdev->static_addr, BDADDR_ANY)) {
@@ -2389,7 +1392,7 @@ static int hci_dev_do_open(struct hci_dev *hdev)
 	atomic_set(&hdev->cmd_cnt, 1);
 	set_bit(HCI_INIT, &hdev->flags);
 
-	if (test_bit(HCI_SETUP, &hdev->dev_flags)) {
+	if (hci_dev_test_flag(hdev, HCI_SETUP)) {
 		if (hdev->setup)
 			ret = hdev->setup(hdev);
 
@@ -2401,7 +1404,7 @@ static int hci_dev_do_open(struct hci_dev *hdev)
 		 */
 		if (test_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks) ||
 		    test_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks))
-			set_bit(HCI_UNCONFIGURED, &hdev->dev_flags);
+			hci_dev_set_flag(hdev, HCI_UNCONFIGURED);
 
 		/* For an unconfigured controller it is required to
 		 * read at least the version information provided by
@@ -2411,11 +1414,11 @@ static int hci_dev_do_open(struct hci_dev *hdev)
 		 * also the original Bluetooth public device address
 		 * will be read using the Read BD Address command.
 		 */
-		if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags))
+		if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED))
 			ret = __hci_unconf_init(hdev);
 	}
 
-	if (test_bit(HCI_CONFIG, &hdev->dev_flags)) {
+	if (hci_dev_test_flag(hdev, HCI_CONFIG)) {
 		/* If public address change is configured, ensure that
 		 * the address gets programmed. If the driver does not
 		 * support changing the public address, fail the power
@@ -2429,8 +1432,8 @@ static int hci_dev_do_open(struct hci_dev *hdev)
 	}
 
 	if (!ret) {
-		if (!test_bit(HCI_UNCONFIGURED, &hdev->dev_flags) &&
-		    !test_bit(HCI_USER_CHANNEL, &hdev->dev_flags))
+		if (!hci_dev_test_flag(hdev, HCI_UNCONFIGURED) &&
+		    !hci_dev_test_flag(hdev, HCI_USER_CHANNEL))
 			ret = __hci_init(hdev);
 	}
 
@@ -2438,13 +1441,13 @@ static int hci_dev_do_open(struct hci_dev *hdev)
 
 	if (!ret) {
 		hci_dev_hold(hdev);
-		set_bit(HCI_RPA_EXPIRED, &hdev->dev_flags);
+		hci_dev_set_flag(hdev, HCI_RPA_EXPIRED);
 		set_bit(HCI_UP, &hdev->flags);
 		hci_notify(hdev, HCI_DEV_UP);
-		if (!test_bit(HCI_SETUP, &hdev->dev_flags) &&
-		    !test_bit(HCI_CONFIG, &hdev->dev_flags) &&
-		    !test_bit(HCI_UNCONFIGURED, &hdev->dev_flags) &&
-		    !test_bit(HCI_USER_CHANNEL, &hdev->dev_flags) &&
+		if (!hci_dev_test_flag(hdev, HCI_SETUP) &&
+		    !hci_dev_test_flag(hdev, HCI_CONFIG) &&
+		    !hci_dev_test_flag(hdev, HCI_UNCONFIGURED) &&
+		    !hci_dev_test_flag(hdev, HCI_USER_CHANNEL) &&
 		    hdev->dev_type == HCI_BREDR) {
 			hci_dev_lock(hdev);
 			mgmt_powered(hdev, 1);
@@ -2496,8 +1499,8 @@ int hci_dev_open(__u16 dev)
 	 * HCI_USER_CHANNEL will be set first before attempting to
 	 * open the device.
 	 */
-	if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags) &&
-	    !test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) {
+	if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED) &&
+	    !hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) {
 		err = -EOPNOTSUPP;
 		goto done;
 	}
@@ -2507,7 +1510,7 @@ int hci_dev_open(__u16 dev)
 	 * particularly important if the setup procedure has not yet
 	 * completed.
 	 */
-	if (test_and_clear_bit(HCI_AUTO_OFF, &hdev->dev_flags))
+	if (hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF))
 		cancel_delayed_work(&hdev->power_off);
 
 	/* After this call it is guaranteed that the setup procedure
@@ -2522,9 +1525,9 @@ int hci_dev_open(__u16 dev)
 	 * is in use this bit will be cleared again and userspace has
 	 * to explicitly enable it.
 	 */
-	if (!test_bit(HCI_USER_CHANNEL, &hdev->dev_flags) &&
-	    !test_bit(HCI_MGMT, &hdev->dev_flags))
-		set_bit(HCI_BONDABLE, &hdev->dev_flags);
+	if (!hci_dev_test_flag(hdev, HCI_USER_CHANNEL) &&
+	    !hci_dev_test_flag(hdev, HCI_MGMT))
+		hci_dev_set_flag(hdev, HCI_BONDABLE);
 
 	err = hci_dev_do_open(hdev);
 
@@ -2554,6 +1557,13 @@ static int hci_dev_do_close(struct hci_dev *hdev)
 {
 	BT_DBG("%s %p", hdev->name, hdev);
 
+	if (!hci_dev_test_flag(hdev, HCI_UNREGISTER) &&
+	    test_bit(HCI_UP, &hdev->flags)) {
+		/* Execute vendor specific shutdown routine */
+		if (hdev->shutdown)
+			hdev->shutdown(hdev);
+	}
+
 	cancel_delayed_work(&hdev->power_off);
 
 	hci_req_cancel(hdev, ENODEV);
@@ -2572,24 +1582,40 @@ static int hci_dev_do_close(struct hci_dev *hdev)
 	if (hdev->discov_timeout > 0) {
 		cancel_delayed_work(&hdev->discov_off);
 		hdev->discov_timeout = 0;
-		clear_bit(HCI_DISCOVERABLE, &hdev->dev_flags);
-		clear_bit(HCI_LIMITED_DISCOVERABLE, &hdev->dev_flags);
+		hci_dev_clear_flag(hdev, HCI_DISCOVERABLE);
+		hci_dev_clear_flag(hdev, HCI_LIMITED_DISCOVERABLE);
 	}
 
-	if (test_and_clear_bit(HCI_SERVICE_CACHE, &hdev->dev_flags))
+	if (hci_dev_test_and_clear_flag(hdev, HCI_SERVICE_CACHE))
 		cancel_delayed_work(&hdev->service_cache);
 
 	cancel_delayed_work_sync(&hdev->le_scan_disable);
+	cancel_delayed_work_sync(&hdev->le_scan_restart);
 
-	if (test_bit(HCI_MGMT, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_MGMT))
 		cancel_delayed_work_sync(&hdev->rpa_expired);
 
+	/* Avoid potential lockdep warnings from the *_flush() calls by
+	 * ensuring the workqueue is empty up front.
+	 */
+	drain_workqueue(hdev->workqueue);
+
 	hci_dev_lock(hdev);
+
+	hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
+
+	if (!hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF)) {
+		if (hdev->dev_type == HCI_BREDR)
+			mgmt_powered(hdev, 0);
+	}
+
 	hci_inquiry_cache_flush(hdev);
 	hci_pend_le_actions_clear(hdev);
 	hci_conn_hash_flush(hdev);
 	hci_dev_unlock(hdev);
 
+	smp_unregister(hdev);
+
 	hci_notify(hdev, HCI_DEV_DOWN);
 
 	if (hdev->flush)
@@ -2598,8 +1624,8 @@ static int hci_dev_do_close(struct hci_dev *hdev)
 	/* Reset device */
 	skb_queue_purge(&hdev->cmd_q);
 	atomic_set(&hdev->cmd_cnt, 1);
-	if (!test_bit(HCI_AUTO_OFF, &hdev->dev_flags) &&
-	    !test_bit(HCI_UNCONFIGURED, &hdev->dev_flags) &&
+	if (!hci_dev_test_flag(hdev, HCI_AUTO_OFF) &&
+	    !hci_dev_test_flag(hdev, HCI_UNCONFIGURED) &&
 	    test_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks)) {
 		set_bit(HCI_INIT, &hdev->flags);
 		__hci_req_sync(hdev, hci_reset_req, 0, HCI_CMD_TIMEOUT);
@@ -2621,24 +1647,13 @@ static int hci_dev_do_close(struct hci_dev *hdev)
 		hdev->sent_cmd = NULL;
 	}
 
-	kfree_skb(hdev->recv_evt);
-	hdev->recv_evt = NULL;
-
 	/* After this point our queues are empty
 	 * and no tasks are scheduled. */
 	hdev->close(hdev);
 
 	/* Clear flags */
 	hdev->flags &= BIT(HCI_RAW);
-	hdev->dev_flags &= ~HCI_PERSISTENT_MASK;
-
-	if (!test_and_clear_bit(HCI_AUTO_OFF, &hdev->dev_flags)) {
-		if (hdev->dev_type == HCI_BREDR) {
-			hci_dev_lock(hdev);
-			mgmt_powered(hdev, 0);
-			hci_dev_unlock(hdev);
-		}
-	}
+	hci_dev_clear_volatile_flags(hdev);
 
 	/* Controller radio is available but is currently powered down */
 	hdev->amp_status = AMP_STATUS_POWERED_DOWN;
@@ -2662,12 +1677,12 @@ int hci_dev_close(__u16 dev)
 	if (!hdev)
 		return -ENODEV;
 
-	if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) {
+	if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) {
 		err = -EBUSY;
 		goto done;
 	}
 
-	if (test_and_clear_bit(HCI_AUTO_OFF, &hdev->dev_flags))
+	if (hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF))
 		cancel_delayed_work(&hdev->power_off);
 
 	err = hci_dev_do_close(hdev);
@@ -2677,36 +1692,23 @@ done:
 	return err;
 }
 
-int hci_dev_reset(__u16 dev)
+static int hci_dev_do_reset(struct hci_dev *hdev)
 {
-	struct hci_dev *hdev;
-	int ret = 0;
+	int ret;
 
-	hdev = hci_dev_get(dev);
-	if (!hdev)
-		return -ENODEV;
+	BT_DBG("%s %p", hdev->name, hdev);
 
 	hci_req_lock(hdev);
 
-	if (!test_bit(HCI_UP, &hdev->flags)) {
-		ret = -ENETDOWN;
-		goto done;
-	}
-
-	if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) {
-		ret = -EBUSY;
-		goto done;
-	}
-
-	if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) {
-		ret = -EOPNOTSUPP;
-		goto done;
-	}
-
 	/* Drop queues */
 	skb_queue_purge(&hdev->rx_q);
 	skb_queue_purge(&hdev->cmd_q);
 
+	/* Avoid potential lockdep warnings from the *_flush() calls by
+	 * ensuring the workqueue is empty up front.
+	 */
+	drain_workqueue(hdev->workqueue);
+
 	hci_dev_lock(hdev);
 	hci_inquiry_cache_flush(hdev);
 	hci_conn_hash_flush(hdev);
@@ -2720,12 +1722,41 @@ int hci_dev_reset(__u16 dev)
 
 	ret = __hci_req_sync(hdev, hci_reset_req, 0, HCI_INIT_TIMEOUT);
 
-done:
 	hci_req_unlock(hdev);
-	hci_dev_put(hdev);
 	return ret;
 }
 
+int hci_dev_reset(__u16 dev)
+{
+	struct hci_dev *hdev;
+	int err;
+
+	hdev = hci_dev_get(dev);
+	if (!hdev)
+		return -ENODEV;
+
+	if (!test_bit(HCI_UP, &hdev->flags)) {
+		err = -ENETDOWN;
+		goto done;
+	}
+
+	if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) {
+		err = -EBUSY;
+		goto done;
+	}
+
+	if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) {
+		err = -EOPNOTSUPP;
+		goto done;
+	}
+
+	err = hci_dev_do_reset(hdev);
+
+done:
+	hci_dev_put(hdev);
+	return err;
+}
+
 int hci_dev_reset_stat(__u16 dev)
 {
 	struct hci_dev *hdev;
@@ -2735,12 +1766,12 @@ int hci_dev_reset_stat(__u16 dev)
 	if (!hdev)
 		return -ENODEV;
 
-	if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) {
+	if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) {
 		ret = -EBUSY;
 		goto done;
 	}
 
-	if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) {
+	if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) {
 		ret = -EOPNOTSUPP;
 		goto done;
 	}
@@ -2759,29 +1790,29 @@ static void hci_update_scan_state(struct hci_dev *hdev, u8 scan)
 	BT_DBG("%s scan 0x%02x", hdev->name, scan);
 
 	if ((scan & SCAN_PAGE))
-		conn_changed = !test_and_set_bit(HCI_CONNECTABLE,
-						 &hdev->dev_flags);
+		conn_changed = !hci_dev_test_and_set_flag(hdev,
+							  HCI_CONNECTABLE);
 	else
-		conn_changed = test_and_clear_bit(HCI_CONNECTABLE,
-						  &hdev->dev_flags);
+		conn_changed = hci_dev_test_and_clear_flag(hdev,
+							   HCI_CONNECTABLE);
 
 	if ((scan & SCAN_INQUIRY)) {
-		discov_changed = !test_and_set_bit(HCI_DISCOVERABLE,
-						   &hdev->dev_flags);
+		discov_changed = !hci_dev_test_and_set_flag(hdev,
+							    HCI_DISCOVERABLE);
 	} else {
-		clear_bit(HCI_LIMITED_DISCOVERABLE, &hdev->dev_flags);
-		discov_changed = test_and_clear_bit(HCI_DISCOVERABLE,
-						    &hdev->dev_flags);
+		hci_dev_clear_flag(hdev, HCI_LIMITED_DISCOVERABLE);
+		discov_changed = hci_dev_test_and_clear_flag(hdev,
+							     HCI_DISCOVERABLE);
 	}
 
-	if (!test_bit(HCI_MGMT, &hdev->dev_flags))
+	if (!hci_dev_test_flag(hdev, HCI_MGMT))
 		return;
 
 	if (conn_changed || discov_changed) {
 		/* In case this was disabled through mgmt */
-		set_bit(HCI_BREDR_ENABLED, &hdev->dev_flags);
+		hci_dev_set_flag(hdev, HCI_BREDR_ENABLED);
 
-		if (test_bit(HCI_LE_ENABLED, &hdev->dev_flags))
+		if (hci_dev_test_flag(hdev, HCI_LE_ENABLED))
 			mgmt_update_adv_data(hdev);
 
 		mgmt_new_settings(hdev);
@@ -2801,12 +1832,12 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg)
 	if (!hdev)
 		return -ENODEV;
 
-	if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) {
+	if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) {
 		err = -EBUSY;
 		goto done;
 	}
 
-	if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) {
+	if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) {
 		err = -EOPNOTSUPP;
 		goto done;
 	}
@@ -2816,7 +1847,7 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg)
 		goto done;
 	}
 
-	if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) {
+	if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) {
 		err = -EOPNOTSUPP;
 		goto done;
 	}
@@ -2920,7 +1951,7 @@ int hci_get_dev_list(void __user *arg)
 		 * is running, but in that case still indicate that the
 		 * device is actually down.
 		 */
-		if (test_bit(HCI_AUTO_OFF, &hdev->dev_flags))
+		if (hci_dev_test_flag(hdev, HCI_AUTO_OFF))
 			flags &= ~BIT(HCI_UP);
 
 		(dr + n)->dev_id  = hdev->id;
@@ -2958,7 +1989,7 @@ int hci_get_dev_info(void __user *arg)
 	 * is running, but in that case still indicate that the
 	 * device is actually down.
 	 */
-	if (test_bit(HCI_AUTO_OFF, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_AUTO_OFF))
 		flags = hdev->flags & ~BIT(HCI_UP);
 	else
 		flags = hdev->flags;
@@ -3001,16 +2032,16 @@ static int hci_rfkill_set_block(void *data, bool blocked)
 
 	BT_DBG("%p name %s blocked %d", hdev, hdev->name, blocked);
 
-	if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL))
 		return -EBUSY;
 
 	if (blocked) {
-		set_bit(HCI_RFKILLED, &hdev->dev_flags);
-		if (!test_bit(HCI_SETUP, &hdev->dev_flags) &&
-		    !test_bit(HCI_CONFIG, &hdev->dev_flags))
+		hci_dev_set_flag(hdev, HCI_RFKILLED);
+		if (!hci_dev_test_flag(hdev, HCI_SETUP) &&
+		    !hci_dev_test_flag(hdev, HCI_CONFIG))
 			hci_dev_do_close(hdev);
 	} else {
-		clear_bit(HCI_RFKILLED, &hdev->dev_flags);
+		hci_dev_clear_flag(hdev, HCI_RFKILLED);
 	}
 
 	return 0;
@@ -3029,7 +2060,9 @@ static void hci_power_on(struct work_struct *work)
 
 	err = hci_dev_do_open(hdev);
 	if (err < 0) {
+		hci_dev_lock(hdev);
 		mgmt_set_powered_failed(hdev, err);
+		hci_dev_unlock(hdev);
 		return;
 	}
 
@@ -3037,23 +2070,23 @@ static void hci_power_on(struct work_struct *work)
 	 * ignored and they need to be checked now. If they are still
 	 * valid, it is important to turn the device back off.
 	 */
-	if (test_bit(HCI_RFKILLED, &hdev->dev_flags) ||
-	    test_bit(HCI_UNCONFIGURED, &hdev->dev_flags) ||
+	if (hci_dev_test_flag(hdev, HCI_RFKILLED) ||
+	    hci_dev_test_flag(hdev, HCI_UNCONFIGURED) ||
 	    (hdev->dev_type == HCI_BREDR &&
 	     !bacmp(&hdev->bdaddr, BDADDR_ANY) &&
 	     !bacmp(&hdev->static_addr, BDADDR_ANY))) {
-		clear_bit(HCI_AUTO_OFF, &hdev->dev_flags);
+		hci_dev_clear_flag(hdev, HCI_AUTO_OFF);
 		hci_dev_do_close(hdev);
-	} else if (test_bit(HCI_AUTO_OFF, &hdev->dev_flags)) {
+	} else if (hci_dev_test_flag(hdev, HCI_AUTO_OFF)) {
 		queue_delayed_work(hdev->req_workqueue, &hdev->power_off,
 				   HCI_AUTO_OFF_TIMEOUT);
 	}
 
-	if (test_and_clear_bit(HCI_SETUP, &hdev->dev_flags)) {
+	if (hci_dev_test_and_clear_flag(hdev, HCI_SETUP)) {
 		/* For unconfigured devices, set the HCI_RAW flag
 		 * so that userspace can easily identify them.
 		 */
-		if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags))
+		if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED))
 			set_bit(HCI_RAW, &hdev->flags);
 
 		/* For fully configured devices, this will send
@@ -3064,11 +2097,11 @@ static void hci_power_on(struct work_struct *work)
 		 * and no event will be send.
 		 */
 		mgmt_index_added(hdev);
-	} else if (test_and_clear_bit(HCI_CONFIG, &hdev->dev_flags)) {
+	} else if (hci_dev_test_and_clear_flag(hdev, HCI_CONFIG)) {
 		/* When the controller is now configured, then it
 		 * is important to clear the HCI_RAW flag.
 		 */
-		if (!test_bit(HCI_UNCONFIGURED, &hdev->dev_flags))
+		if (!hci_dev_test_flag(hdev, HCI_UNCONFIGURED))
 			clear_bit(HCI_RAW, &hdev->flags);
 
 		/* Powering on the controller with HCI_CONFIG set only
@@ -3089,6 +2122,24 @@ static void hci_power_off(struct work_struct *work)
 	hci_dev_do_close(hdev);
 }
 
+static void hci_error_reset(struct work_struct *work)
+{
+	struct hci_dev *hdev = container_of(work, struct hci_dev, error_reset);
+
+	BT_DBG("%s", hdev->name);
+
+	if (hdev->hw_error)
+		hdev->hw_error(hdev, hdev->hw_error_code);
+	else
+		BT_ERR("%s hardware error 0x%2.2x", hdev->name,
+		       hdev->hw_error_code);
+
+	if (hci_dev_do_close(hdev))
+		return;
+
+	hci_dev_do_open(hdev);
+}
+
 static void hci_discov_off(struct work_struct *work)
 {
 	struct hci_dev *hdev;
@@ -3112,35 +2163,31 @@ void hci_uuids_clear(struct hci_dev *hdev)
 
 void hci_link_keys_clear(struct hci_dev *hdev)
 {
-	struct list_head *p, *n;
-
-	list_for_each_safe(p, n, &hdev->link_keys) {
-		struct link_key *key;
-
-		key = list_entry(p, struct link_key, list);
+	struct link_key *key;
 
-		list_del(p);
-		kfree(key);
+	list_for_each_entry_rcu(key, &hdev->link_keys, list) {
+		list_del_rcu(&key->list);
+		kfree_rcu(key, rcu);
 	}
 }
 
 void hci_smp_ltks_clear(struct hci_dev *hdev)
 {
-	struct smp_ltk *k, *tmp;
+	struct smp_ltk *k;
 
-	list_for_each_entry_safe(k, tmp, &hdev->long_term_keys, list) {
-		list_del(&k->list);
-		kfree(k);
+	list_for_each_entry_rcu(k, &hdev->long_term_keys, list) {
+		list_del_rcu(&k->list);
+		kfree_rcu(k, rcu);
 	}
 }
 
 void hci_smp_irks_clear(struct hci_dev *hdev)
 {
-	struct smp_irk *k, *tmp;
+	struct smp_irk *k;
 
-	list_for_each_entry_safe(k, tmp, &hdev->identity_resolving_keys, list) {
-		list_del(&k->list);
-		kfree(k);
+	list_for_each_entry_rcu(k, &hdev->identity_resolving_keys, list) {
+		list_del_rcu(&k->list);
+		kfree_rcu(k, rcu);
 	}
 }
 
@@ -3148,9 +2195,14 @@ struct link_key *hci_find_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr)
 {
 	struct link_key *k;
 
-	list_for_each_entry(k, &hdev->link_keys, list)
-		if (bacmp(bdaddr, &k->bdaddr) == 0)
+	rcu_read_lock();
+	list_for_each_entry_rcu(k, &hdev->link_keys, list) {
+		if (bacmp(bdaddr, &k->bdaddr) == 0) {
+			rcu_read_unlock();
 			return k;
+		}
+	}
+	rcu_read_unlock();
 
 	return NULL;
 }
@@ -3174,6 +2226,10 @@ static bool hci_persistent_key(struct hci_dev *hdev, struct hci_conn *conn,
 	if (!conn)
 		return true;
 
+	/* BR/EDR key derived using SC from an LE link */
+	if (conn->type == LE_LINK)
+		return true;
+
 	/* Neither local nor remote side had no-bonding as requirement */
 	if (conn->auth_type > 0x01 && conn->remote_auth > 0x01)
 		return true;
@@ -3199,34 +2255,22 @@ static u8 ltk_role(u8 type)
 	return HCI_ROLE_SLAVE;
 }
 
-struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, __le16 ediv, __le64 rand,
-			     u8 role)
+struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr,
+			     u8 addr_type, u8 role)
 {
 	struct smp_ltk *k;
 
-	list_for_each_entry(k, &hdev->long_term_keys, list) {
-		if (k->ediv != ediv || k->rand != rand)
-			continue;
-
-		if (ltk_role(k->type) != role)
+	rcu_read_lock();
+	list_for_each_entry_rcu(k, &hdev->long_term_keys, list) {
+		if (addr_type != k->bdaddr_type || bacmp(bdaddr, &k->bdaddr))
 			continue;
 
-		return k;
-	}
-
-	return NULL;
-}
-
-struct smp_ltk *hci_find_ltk_by_addr(struct hci_dev *hdev, bdaddr_t *bdaddr,
-				     u8 addr_type, u8 role)
-{
-	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 &&
-		    ltk_role(k->type) == role)
+		if (smp_ltk_is_sc(k) || ltk_role(k->type) == role) {
+			rcu_read_unlock();
 			return k;
+		}
+	}
+	rcu_read_unlock();
 
 	return NULL;
 }
@@ -3235,17 +2279,22 @@ 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))
+	rcu_read_lock();
+	list_for_each_entry_rcu(irk, &hdev->identity_resolving_keys, list) {
+		if (!bacmp(&irk->rpa, rpa)) {
+			rcu_read_unlock();
 			return irk;
+		}
 	}
 
-	list_for_each_entry(irk, &hdev->identity_resolving_keys, list) {
+	list_for_each_entry_rcu(irk, &hdev->identity_resolving_keys, list) {
 		if (smp_irk_matches(hdev, irk->val, rpa)) {
 			bacpy(&irk->rpa, rpa);
+			rcu_read_unlock();
 			return irk;
 		}
 	}
+	rcu_read_unlock();
 
 	return NULL;
 }
@@ -3259,11 +2308,15 @@ struct smp_irk *hci_find_irk_by_addr(struct hci_dev *hdev, bdaddr_t *bdaddr,
 	if (addr_type == ADDR_LE_DEV_RANDOM && (bdaddr->b[5] & 0xc0) != 0xc0)
 		return NULL;
 
-	list_for_each_entry(irk, &hdev->identity_resolving_keys, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(irk, &hdev->identity_resolving_keys, list) {
 		if (addr_type == irk->addr_type &&
-		    bacmp(bdaddr, &irk->bdaddr) == 0)
+		    bacmp(bdaddr, &irk->bdaddr) == 0) {
+			rcu_read_unlock();
 			return irk;
+		}
 	}
+	rcu_read_unlock();
 
 	return NULL;
 }
@@ -3284,7 +2337,7 @@ struct link_key *hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn,
 		key = kzalloc(sizeof(*key), GFP_KERNEL);
 		if (!key)
 			return NULL;
-		list_add(&key->list, &hdev->link_keys);
+		list_add_rcu(&key->list, &hdev->link_keys);
 	}
 
 	BT_DBG("%s key for %pMR type %u", hdev->name, bdaddr, type);
@@ -3322,14 +2375,14 @@ struct smp_ltk *hci_add_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr,
 	struct smp_ltk *key, *old_key;
 	u8 role = ltk_role(type);
 
-	old_key = hci_find_ltk_by_addr(hdev, bdaddr, addr_type, role);
+	old_key = hci_find_ltk(hdev, bdaddr, addr_type, role);
 	if (old_key)
 		key = old_key;
 	else {
 		key = kzalloc(sizeof(*key), GFP_KERNEL);
 		if (!key)
 			return NULL;
-		list_add(&key->list, &hdev->long_term_keys);
+		list_add_rcu(&key->list, &hdev->long_term_keys);
 	}
 
 	bacpy(&key->bdaddr, bdaddr);
@@ -3358,7 +2411,7 @@ struct smp_irk *hci_add_irk(struct hci_dev *hdev, bdaddr_t *bdaddr,
 		bacpy(&irk->bdaddr, bdaddr);
 		irk->addr_type = addr_type;
 
-		list_add(&irk->list, &hdev->identity_resolving_keys);
+		list_add_rcu(&irk->list, &hdev->identity_resolving_keys);
 	}
 
 	memcpy(irk->val, val, 16);
@@ -3377,25 +2430,25 @@ int hci_remove_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr)
 
 	BT_DBG("%s removing %pMR", hdev->name, bdaddr);
 
-	list_del(&key->list);
-	kfree(key);
+	list_del_rcu(&key->list);
+	kfree_rcu(key, rcu);
 
 	return 0;
 }
 
 int hci_remove_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type)
 {
-	struct smp_ltk *k, *tmp;
+	struct smp_ltk *k;
 	int removed = 0;
 
-	list_for_each_entry_safe(k, tmp, &hdev->long_term_keys, list) {
+	list_for_each_entry_rcu(k, &hdev->long_term_keys, list) {
 		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);
+		list_del_rcu(&k->list);
+		kfree_rcu(k, rcu);
 		removed++;
 	}
 
@@ -3404,17 +2457,53 @@ int hci_remove_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type)
 
 void hci_remove_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type)
 {
-	struct smp_irk *k, *tmp;
+	struct smp_irk *k;
 
-	list_for_each_entry_safe(k, tmp, &hdev->identity_resolving_keys, list) {
+	list_for_each_entry_rcu(k, &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);
+		list_del_rcu(&k->list);
+		kfree_rcu(k, rcu);
+	}
+}
+
+bool hci_bdaddr_is_paired(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type)
+{
+	struct smp_ltk *k;
+	struct smp_irk *irk;
+	u8 addr_type;
+
+	if (type == BDADDR_BREDR) {
+		if (hci_find_link_key(hdev, bdaddr))
+			return true;
+		return false;
+	}
+
+	/* Convert to HCI addr type which struct smp_ltk uses */
+	if (type == BDADDR_LE_PUBLIC)
+		addr_type = ADDR_LE_DEV_PUBLIC;
+	else
+		addr_type = ADDR_LE_DEV_RANDOM;
+
+	irk = hci_get_irk(hdev, bdaddr, addr_type);
+	if (irk) {
+		bdaddr = &irk->bdaddr;
+		addr_type = irk->addr_type;
+	}
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(k, &hdev->long_term_keys, list) {
+		if (k->bdaddr_type == addr_type && !bacmp(bdaddr, &k->bdaddr)) {
+			rcu_read_unlock();
+			return true;
+		}
 	}
+	rcu_read_unlock();
+
+	return false;
 }
 
 /* HCI command timer function */
@@ -3437,26 +2526,31 @@ static void hci_cmd_timeout(struct work_struct *work)
 }
 
 struct oob_data *hci_find_remote_oob_data(struct hci_dev *hdev,
-					  bdaddr_t *bdaddr)
+					  bdaddr_t *bdaddr, u8 bdaddr_type)
 {
 	struct oob_data *data;
 
-	list_for_each_entry(data, &hdev->remote_oob_data, list)
-		if (bacmp(bdaddr, &data->bdaddr) == 0)
-			return data;
+	list_for_each_entry(data, &hdev->remote_oob_data, list) {
+		if (bacmp(bdaddr, &data->bdaddr) != 0)
+			continue;
+		if (data->bdaddr_type != bdaddr_type)
+			continue;
+		return data;
+	}
 
 	return NULL;
 }
 
-int hci_remove_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr)
+int hci_remove_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr,
+			       u8 bdaddr_type)
 {
 	struct oob_data *data;
 
-	data = hci_find_remote_oob_data(hdev, bdaddr);
+	data = hci_find_remote_oob_data(hdev, bdaddr, bdaddr_type);
 	if (!data)
 		return -ENOENT;
 
-	BT_DBG("%s removing %pMR", hdev->name, bdaddr);
+	BT_DBG("%s removing %pMR (%u)", hdev->name, bdaddr, bdaddr_type);
 
 	list_del(&data->list);
 	kfree(data);
@@ -3475,52 +2569,45 @@ void hci_remote_oob_data_clear(struct hci_dev *hdev)
 }
 
 int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr,
-			    u8 *hash, u8 *randomizer)
+			    u8 bdaddr_type, u8 *hash192, u8 *rand192,
+			    u8 *hash256, u8 *rand256)
 {
 	struct oob_data *data;
 
-	data = hci_find_remote_oob_data(hdev, bdaddr);
+	data = hci_find_remote_oob_data(hdev, bdaddr, bdaddr_type);
 	if (!data) {
 		data = kmalloc(sizeof(*data), GFP_KERNEL);
 		if (!data)
 			return -ENOMEM;
 
 		bacpy(&data->bdaddr, bdaddr);
+		data->bdaddr_type = bdaddr_type;
 		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_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_KERNEL);
-		if (!data)
-			return -ENOMEM;
-
-		bacpy(&data->bdaddr, bdaddr);
-		list_add(&data->list, &hdev->remote_oob_data);
+	if (hash192 && rand192) {
+		memcpy(data->hash192, hash192, sizeof(data->hash192));
+		memcpy(data->rand192, rand192, sizeof(data->rand192));
+		if (hash256 && rand256)
+			data->present = 0x03;
+	} else {
+		memset(data->hash192, 0, sizeof(data->hash192));
+		memset(data->rand192, 0, sizeof(data->rand192));
+		if (hash256 && rand256)
+			data->present = 0x02;
+		else
+			data->present = 0x00;
 	}
 
-	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));
+	if (hash256 && rand256) {
+		memcpy(data->hash256, hash256, sizeof(data->hash256));
+		memcpy(data->rand256, rand256, sizeof(data->rand256));
+	} else {
+		memset(data->hash256, 0, sizeof(data->hash256));
+		memset(data->rand256, 0, sizeof(data->rand256));
+		if (hash192 && rand192)
+			data->present = 0x01;
+	}
 
 	BT_DBG("%s for %pMR", hdev->name, bdaddr);
 
@@ -3613,23 +2700,6 @@ struct hci_conn_params *hci_conn_params_lookup(struct hci_dev *hdev,
 	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;
-}
-
 /* This function requires the caller holds hdev->lock */
 struct hci_conn_params *hci_pend_le_action_lookup(struct list_head *list,
 						  bdaddr_t *addr, u8 addr_type)
@@ -3685,47 +2755,6 @@ struct hci_conn_params *hci_conn_params_add(struct hci_dev *hdev,
 	return params;
 }
 
-/* This function requires the caller holds hdev->lock */
-int hci_conn_params_set(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type,
-			u8 auto_connect)
-{
-	struct hci_conn_params *params;
-
-	params = hci_conn_params_add(hdev, addr, addr_type);
-	if (!params)
-		return -EIO;
-
-	if (params->auto_connect == auto_connect)
-		return 0;
-
-	list_del_init(&params->action);
-
-	switch (auto_connect) {
-	case HCI_AUTO_CONN_DISABLED:
-	case HCI_AUTO_CONN_LINK_LOSS:
-		hci_update_background_scan(hdev);
-		break;
-	case HCI_AUTO_CONN_REPORT:
-		list_add(&params->action, &hdev->pend_le_reports);
-		hci_update_background_scan(hdev);
-		break;
-	case HCI_AUTO_CONN_DIRECT:
-	case HCI_AUTO_CONN_ALWAYS:
-		if (!is_connected(hdev, addr, addr_type)) {
-			list_add(&params->action, &hdev->pend_le_conns);
-			hci_update_background_scan(hdev);
-		}
-		break;
-	}
-
-	params->auto_connect = auto_connect;
-
-	BT_DBG("addr %pMR (type %u) auto_connect %u", addr, addr_type,
-	       auto_connect);
-
-	return 0;
-}
-
 static void hci_conn_params_free(struct hci_conn_params *params)
 {
 	if (params->conn) {
@@ -3782,7 +2811,7 @@ void hci_conn_params_clear_all(struct hci_dev *hdev)
 	BT_DBG("All LE connection parameters were removed");
 }
 
-static void inquiry_complete(struct hci_dev *hdev, u8 status)
+static void inquiry_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
 	if (status) {
 		BT_ERR("Failed to start inquiry: status %d", status);
@@ -3794,11 +2823,11 @@ static void inquiry_complete(struct hci_dev *hdev, u8 status)
 	}
 }
 
-static void le_scan_disable_work_complete(struct hci_dev *hdev, u8 status)
+static void le_scan_disable_work_complete(struct hci_dev *hdev, u8 status,
+					  u16 opcode)
 {
 	/* General inquiry access code (GIAC) */
 	u8 lap[3] = { 0x33, 0x8b, 0x9e };
-	struct hci_request req;
 	struct hci_cp_inquiry cp;
 	int err;
 
@@ -3807,6 +2836,8 @@ static void le_scan_disable_work_complete(struct hci_dev *hdev, u8 status)
 		return;
 	}
 
+	hdev->discovery.scan_start = 0;
+
 	switch (hdev->discovery.type) {
 	case DISCOV_TYPE_LE:
 		hci_dev_lock(hdev);
@@ -3815,21 +2846,39 @@ static void le_scan_disable_work_complete(struct hci_dev *hdev, u8 status)
 		break;
 
 	case DISCOV_TYPE_INTERLEAVED:
-		hci_req_init(&req, hdev);
+		hci_dev_lock(hdev);
 
-		memset(&cp, 0, sizeof(cp));
-		memcpy(&cp.lap, lap, sizeof(cp.lap));
-		cp.length = DISCOV_INTERLEAVED_INQUIRY_LEN;
-		hci_req_add(&req, HCI_OP_INQUIRY, sizeof(cp), &cp);
+		if (test_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY,
+			     &hdev->quirks)) {
+			/* If we were running LE only scan, change discovery
+			 * state. If we were running both LE and BR/EDR inquiry
+			 * simultaneously, and BR/EDR inquiry is already
+			 * finished, stop discovery, otherwise BR/EDR inquiry
+			 * will stop discovery when finished. If we will resolve
+			 * remote device name, do not change discovery state.
+			 */
+			if (!test_bit(HCI_INQUIRY, &hdev->flags) &&
+			    hdev->discovery.state != DISCOVERY_RESOLVING)
+				hci_discovery_set_state(hdev,
+							DISCOVERY_STOPPED);
+		} else {
+			struct hci_request req;
 
-		hci_dev_lock(hdev);
+			hci_inquiry_cache_flush(hdev);
 
-		hci_inquiry_cache_flush(hdev);
+			hci_req_init(&req, hdev);
 
-		err = hci_req_run(&req, inquiry_complete);
-		if (err) {
-			BT_ERR("Inquiry request failed: err %d", err);
-			hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
+			memset(&cp, 0, sizeof(cp));
+			memcpy(&cp.lap, lap, sizeof(cp.lap));
+			cp.length = DISCOV_INTERLEAVED_INQUIRY_LEN;
+			hci_req_add(&req, HCI_OP_INQUIRY, sizeof(cp), &cp);
+
+			err = hci_req_run(&req, inquiry_complete);
+			if (err) {
+				BT_ERR("Inquiry request failed: err %d", err);
+				hci_discovery_set_state(hdev,
+							DISCOVERY_STOPPED);
+			}
 		}
 
 		hci_dev_unlock(hdev);
@@ -3846,6 +2895,8 @@ static void le_scan_disable_work(struct work_struct *work)
 
 	BT_DBG("%s", hdev->name);
 
+	cancel_delayed_work_sync(&hdev->le_scan_restart);
+
 	hci_req_init(&req, hdev);
 
 	hci_req_add_le_scan_disable(&req);
@@ -3855,98 +2906,72 @@ static void le_scan_disable_work(struct work_struct *work)
 		BT_ERR("Disable LE scanning request failed: err %d", err);
 }
 
-static void set_random_addr(struct hci_request *req, bdaddr_t *rpa)
+static void le_scan_restart_work_complete(struct hci_dev *hdev, u8 status,
+					  u16 opcode)
 {
-	struct hci_dev *hdev = req->hdev;
+	unsigned long timeout, duration, scan_start, now;
 
-	/* 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_LE_ADV, &hdev->dev_flags) ||
-	    hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT)) {
-		BT_DBG("Deferring random address update");
-		set_bit(HCI_RPA_EXPIRED, &hdev->dev_flags);
+	BT_DBG("%s", hdev->name);
+
+	if (status) {
+		BT_ERR("Failed to restart LE scan: status %d", status);
 		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 (!test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks) ||
+	    !hdev->discovery.scan_start)
+		return;
 
-	/* 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.
+	/* When the scan was started, hdev->le_scan_disable has been queued
+	 * after duration from scan_start. During scan restart this job
+	 * has been canceled, and we need to queue it again after proper
+	 * timeout, to make sure that scan does not run indefinitely.
 	 */
-	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, 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);
+	duration = hdev->discovery.scan_duration;
+	scan_start = hdev->discovery.scan_start;
+	now = jiffies;
+	if (now - scan_start <= duration) {
+		int elapsed;
+
+		if (now >= scan_start)
+			elapsed = now - scan_start;
+		else
+			elapsed = ULONG_MAX - scan_start + now;
 
-		return 0;
+		timeout = duration - elapsed;
+	} else {
+		timeout = 0;
 	}
+	queue_delayed_work(hdev->workqueue,
+			   &hdev->le_scan_disable, timeout);
+}
 
-	/* 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;
+static void le_scan_restart_work(struct work_struct *work)
+{
+	struct hci_dev *hdev = container_of(work, struct hci_dev,
+					    le_scan_restart.work);
+	struct hci_request req;
+	struct hci_cp_le_set_scan_enable cp;
+	int err;
 
-		get_random_bytes(&urpa, 6);
-		urpa.b[5] &= 0x3f;	/* Clear two most significant bits */
+	BT_DBG("%s", hdev->name);
 
-		*own_addr_type = ADDR_LE_DEV_RANDOM;
-		set_random_addr(req, &urpa);
-		return 0;
-	}
+	/* If controller is not scanning we are done. */
+	if (!hci_dev_test_flag(hdev, HCI_LE_SCAN))
+		return;
 
-	/* 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->dbg_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;
-	}
+	hci_req_init(&req, hdev);
 
-	/* Neither privacy nor static address is being used so use a
-	 * public address.
-	 */
-	*own_addr_type = ADDR_LE_DEV_PUBLIC;
+	hci_req_add_le_scan_disable(&req);
 
-	return 0;
+	memset(&cp, 0, sizeof(cp));
+	cp.enable = LE_SCAN_ENABLE;
+	cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE;
+	hci_req_add(&req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp);
+
+	err = hci_req_run(&req, le_scan_restart_work_complete);
+	if (err)
+		BT_ERR("Restart LE scan request failed: err %d", err);
 }
 
 /* Copy the Identity Address of the controller.
@@ -3957,12 +2982,18 @@ int hci_update_random_address(struct hci_request *req, bool require_privacy,
  *
  * For debugging purposes it is possible to force controllers with a
  * public address to use the static random address instead.
+ *
+ * In case BR/EDR has been disabled on a dual-mode controller and
+ * userspace has configured a static address, then that address
+ * becomes the identity address instead of the public BR/EDR address.
  */
 void hci_copy_identity_address(struct hci_dev *hdev, bdaddr_t *bdaddr,
 			       u8 *bdaddr_type)
 {
-	if (test_bit(HCI_FORCE_STATIC_ADDR, &hdev->dbg_flags) ||
-	    !bacmp(&hdev->bdaddr, BDADDR_ANY)) {
+	if (hci_dev_test_flag(hdev, HCI_FORCE_STATIC_ADDR) ||
+	    !bacmp(&hdev->bdaddr, BDADDR_ANY) ||
+	    (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED) &&
+	     bacmp(&hdev->static_addr, BDADDR_ANY))) {
 		bacpy(bdaddr, &hdev->static_addr);
 		*bdaddr_type = ADDR_LE_DEV_RANDOM;
 	} else {
@@ -4001,6 +3032,12 @@ struct hci_dev *hci_alloc_dev(void)
 	hdev->le_conn_max_interval = 0x0038;
 	hdev->le_conn_latency = 0x0000;
 	hdev->le_supv_timeout = 0x002a;
+	hdev->le_def_tx_len = 0x001b;
+	hdev->le_def_tx_time = 0x0148;
+	hdev->le_max_tx_len = 0x001b;
+	hdev->le_max_tx_time = 0x0148;
+	hdev->le_max_rx_len = 0x001b;
+	hdev->le_max_rx_time = 0x0148;
 
 	hdev->rpa_timeout = HCI_DEFAULT_RPA_TIMEOUT;
 	hdev->discov_interleaved_timeout = DISCOV_INTERLEAVED_TIMEOUT;
@@ -4028,10 +3065,12 @@ struct hci_dev *hci_alloc_dev(void)
 	INIT_WORK(&hdev->cmd_work, hci_cmd_work);
 	INIT_WORK(&hdev->tx_work, hci_tx_work);
 	INIT_WORK(&hdev->power_on, hci_power_on);
+	INIT_WORK(&hdev->error_reset, hci_error_reset);
 
 	INIT_DELAYED_WORK(&hdev->power_off, hci_power_off);
 	INIT_DELAYED_WORK(&hdev->discov_off, hci_discov_off);
 	INIT_DELAYED_WORK(&hdev->le_scan_disable, le_scan_disable_work);
+	INIT_DELAYED_WORK(&hdev->le_scan_restart, le_scan_restart_work);
 
 	skb_queue_head_init(&hdev->rx_q);
 	skb_queue_head_init(&hdev->cmd_q);
@@ -4043,6 +3082,7 @@ struct hci_dev *hci_alloc_dev(void)
 
 	hci_init_sysfs(hdev);
 	discovery_init(hdev);
+	adv_info_init(hdev);
 
 	return hdev;
 }
@@ -4121,16 +3161,16 @@ int hci_register_dev(struct hci_dev *hdev)
 	}
 
 	if (hdev->rfkill && rfkill_blocked(hdev->rfkill))
-		set_bit(HCI_RFKILLED, &hdev->dev_flags);
+		hci_dev_set_flag(hdev, HCI_RFKILLED);
 
-	set_bit(HCI_SETUP, &hdev->dev_flags);
-	set_bit(HCI_AUTO_OFF, &hdev->dev_flags);
+	hci_dev_set_flag(hdev, HCI_SETUP);
+	hci_dev_set_flag(hdev, HCI_AUTO_OFF);
 
 	if (hdev->dev_type == HCI_BREDR) {
 		/* Assume BR/EDR support until proven otherwise (such as
 		 * through reading supported features during init.
 		 */
-		set_bit(HCI_BREDR_ENABLED, &hdev->dev_flags);
+		hci_dev_set_flag(hdev, HCI_BREDR_ENABLED);
 	}
 
 	write_lock(&hci_dev_list_lock);
@@ -4141,7 +3181,7 @@ int hci_register_dev(struct hci_dev *hdev)
 	 * and should not be included in normal operation.
 	 */
 	if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks))
-		set_bit(HCI_UNCONFIGURED, &hdev->dev_flags);
+		hci_dev_set_flag(hdev, HCI_UNCONFIGURED);
 
 	hci_notify(hdev, HCI_DEV_REG);
 	hci_dev_hold(hdev);
@@ -4163,11 +3203,11 @@ EXPORT_SYMBOL(hci_register_dev);
 /* Unregister HCI device */
 void hci_unregister_dev(struct hci_dev *hdev)
 {
-	int i, id;
+	int id;
 
 	BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus);
 
-	set_bit(HCI_UNREGISTER, &hdev->dev_flags);
+	hci_dev_set_flag(hdev, HCI_UNREGISTER);
 
 	id = hdev->id;
 
@@ -4177,14 +3217,11 @@ void hci_unregister_dev(struct hci_dev *hdev)
 
 	hci_dev_do_close(hdev);
 
-	for (i = 0; i < NUM_REASSEMBLY; i++)
-		kfree_skb(hdev->reassembly[i]);
-
 	cancel_work_sync(&hdev->power_on);
 
 	if (!test_bit(HCI_INIT, &hdev->flags) &&
-	    !test_bit(HCI_SETUP, &hdev->dev_flags) &&
-	    !test_bit(HCI_CONFIG, &hdev->dev_flags)) {
+	    !hci_dev_test_flag(hdev, HCI_SETUP) &&
+	    !hci_dev_test_flag(hdev, HCI_CONFIG)) {
 		hci_dev_lock(hdev);
 		mgmt_index_removed(hdev);
 		hci_dev_unlock(hdev);
@@ -4201,8 +3238,6 @@ void hci_unregister_dev(struct hci_dev *hdev)
 		rfkill_destroy(hdev->rfkill);
 	}
 
-	smp_unregister(hdev);
-
 	device_del(&hdev->dev);
 
 	debugfs_remove_recursive(hdev->debugfs);
@@ -4220,6 +3255,7 @@ void hci_unregister_dev(struct hci_dev *hdev)
 	hci_remote_oob_data_clear(hdev);
 	hci_bdaddr_list_clear(&hdev->le_white_list);
 	hci_conn_params_clear_all(hdev);
+	hci_discovery_filter_clear(hdev);
 	hci_dev_unlock(hdev);
 
 	hci_dev_put(hdev);
@@ -4244,6 +3280,24 @@ int hci_resume_dev(struct hci_dev *hdev)
 }
 EXPORT_SYMBOL(hci_resume_dev);
 
+/* Reset HCI device */
+int hci_reset_dev(struct hci_dev *hdev)
+{
+	const u8 hw_err[] = { HCI_EV_HARDWARE_ERROR, 0x01, 0x00 };
+	struct sk_buff *skb;
+
+	skb = bt_skb_alloc(3, GFP_ATOMIC);
+	if (!skb)
+		return -ENOMEM;
+
+	bt_cb(skb)->pkt_type = HCI_EVENT_PKT;
+	memcpy(skb_put(skb, 3), hw_err, 3);
+
+	/* Send Hardware Error to upper stack */
+	return hci_recv_frame(hdev, skb);
+}
+EXPORT_SYMBOL(hci_reset_dev);
+
 /* Receive frame from HCI drivers */
 int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb)
 {
@@ -4266,158 +3320,15 @@ int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(hci_recv_frame);
 
-static int hci_reassembly(struct hci_dev *hdev, int type, void *data,
-			  int count, __u8 index)
-{
-	int len = 0;
-	int hlen = 0;
-	int remain = count;
-	struct sk_buff *skb;
-	struct bt_skb_cb *scb;
-
-	if ((type < HCI_ACLDATA_PKT || type > HCI_EVENT_PKT) ||
-	    index >= NUM_REASSEMBLY)
-		return -EILSEQ;
-
-	skb = hdev->reassembly[index];
-
-	if (!skb) {
-		switch (type) {
-		case HCI_ACLDATA_PKT:
-			len = HCI_MAX_FRAME_SIZE;
-			hlen = HCI_ACL_HDR_SIZE;
-			break;
-		case HCI_EVENT_PKT:
-			len = HCI_MAX_EVENT_SIZE;
-			hlen = HCI_EVENT_HDR_SIZE;
-			break;
-		case HCI_SCODATA_PKT:
-			len = HCI_MAX_SCO_SIZE;
-			hlen = HCI_SCO_HDR_SIZE;
-			break;
-		}
-
-		skb = bt_skb_alloc(len, GFP_ATOMIC);
-		if (!skb)
-			return -ENOMEM;
-
-		scb = (void *) skb->cb;
-		scb->expect = hlen;
-		scb->pkt_type = type;
-
-		hdev->reassembly[index] = skb;
-	}
-
-	while (count) {
-		scb = (void *) skb->cb;
-		len = min_t(uint, scb->expect, count);
-
-		memcpy(skb_put(skb, len), data, len);
-
-		count -= len;
-		data += len;
-		scb->expect -= len;
-		remain = count;
-
-		switch (type) {
-		case HCI_EVENT_PKT:
-			if (skb->len == HCI_EVENT_HDR_SIZE) {
-				struct hci_event_hdr *h = hci_event_hdr(skb);
-				scb->expect = h->plen;
-
-				if (skb_tailroom(skb) < scb->expect) {
-					kfree_skb(skb);
-					hdev->reassembly[index] = NULL;
-					return -ENOMEM;
-				}
-			}
-			break;
-
-		case HCI_ACLDATA_PKT:
-			if (skb->len  == HCI_ACL_HDR_SIZE) {
-				struct hci_acl_hdr *h = hci_acl_hdr(skb);
-				scb->expect = __le16_to_cpu(h->dlen);
-
-				if (skb_tailroom(skb) < scb->expect) {
-					kfree_skb(skb);
-					hdev->reassembly[index] = NULL;
-					return -ENOMEM;
-				}
-			}
-			break;
-
-		case HCI_SCODATA_PKT:
-			if (skb->len == HCI_SCO_HDR_SIZE) {
-				struct hci_sco_hdr *h = hci_sco_hdr(skb);
-				scb->expect = h->dlen;
-
-				if (skb_tailroom(skb) < scb->expect) {
-					kfree_skb(skb);
-					hdev->reassembly[index] = NULL;
-					return -ENOMEM;
-				}
-			}
-			break;
-		}
-
-		if (scb->expect == 0) {
-			/* Complete frame */
-
-			bt_cb(skb)->pkt_type = type;
-			hci_recv_frame(hdev, skb);
-
-			hdev->reassembly[index] = NULL;
-			return remain;
-		}
-	}
-
-	return remain;
-}
-
-#define STREAM_REASSEMBLY 0
-
-int hci_recv_stream_fragment(struct hci_dev *hdev, void *data, int count)
-{
-	int type;
-	int rem = 0;
-
-	while (count) {
-		struct sk_buff *skb = hdev->reassembly[STREAM_REASSEMBLY];
-
-		if (!skb) {
-			struct { char type; } *pkt;
-
-			/* Start of the frame */
-			pkt = data;
-			type = pkt->type;
-
-			data++;
-			count--;
-		} else
-			type = bt_cb(skb)->pkt_type;
-
-		rem = hci_reassembly(hdev, type, data, count,
-				     STREAM_REASSEMBLY);
-		if (rem < 0)
-			return rem;
-
-		data += (count - rem);
-		count = rem;
-	}
-
-	return rem;
-}
-EXPORT_SYMBOL(hci_recv_stream_fragment);
-
 /* ---- Interface to upper protocols ---- */
 
 int hci_register_cb(struct hci_cb *cb)
 {
 	BT_DBG("%p name %s", cb, cb->name);
 
-	write_lock(&hci_cb_list_lock);
-	list_add(&cb->list, &hci_cb_list);
-	write_unlock(&hci_cb_list_lock);
+	mutex_lock(&hci_cb_list_lock);
+	list_add_tail(&cb->list, &hci_cb_list);
+	mutex_unlock(&hci_cb_list_lock);
 
 	return 0;
 }
@@ -4427,9 +3338,9 @@ int hci_unregister_cb(struct hci_cb *cb)
 {
 	BT_DBG("%p name %s", cb, cb->name);
 
-	write_lock(&hci_cb_list_lock);
+	mutex_lock(&hci_cb_list_lock);
 	list_del(&cb->list);
-	write_unlock(&hci_cb_list_lock);
+	mutex_unlock(&hci_cb_list_lock);
 
 	return 0;
 }
@@ -4462,76 +3373,6 @@ static void hci_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 	}
 }
 
-void hci_req_init(struct hci_request *req, struct hci_dev *hdev)
-{
-	skb_queue_head_init(&req->cmd_q);
-	req->hdev = hdev;
-	req->err = 0;
-}
-
-int hci_req_run(struct hci_request *req, hci_req_complete_t complete)
-{
-	struct hci_dev *hdev = req->hdev;
-	struct sk_buff *skb;
-	unsigned long flags;
-
-	BT_DBG("length %u", skb_queue_len(&req->cmd_q));
-
-	/* If an error occured during request building, remove all HCI
-	 * commands queued on the HCI request queue.
-	 */
-	if (req->err) {
-		skb_queue_purge(&req->cmd_q);
-		return req->err;
-	}
-
-	/* Do not allow empty requests */
-	if (skb_queue_empty(&req->cmd_q))
-		return -ENODATA;
-
-	skb = skb_peek_tail(&req->cmd_q);
-	bt_cb(skb)->req.complete = complete;
-
-	spin_lock_irqsave(&hdev->cmd_q.lock, flags);
-	skb_queue_splice_tail(&req->cmd_q, &hdev->cmd_q);
-	spin_unlock_irqrestore(&hdev->cmd_q.lock, flags);
-
-	queue_work(hdev->workqueue, &hdev->cmd_work);
-
-	return 0;
-}
-
-bool hci_req_pending(struct hci_dev *hdev)
-{
-	return (hdev->req_status == HCI_REQ_PEND);
-}
-
-static struct sk_buff *hci_prepare_cmd(struct hci_dev *hdev, u16 opcode,
-				       u32 plen, const void *param)
-{
-	int len = HCI_COMMAND_HDR_SIZE + plen;
-	struct hci_command_hdr *hdr;
-	struct sk_buff *skb;
-
-	skb = bt_skb_alloc(len, GFP_ATOMIC);
-	if (!skb)
-		return NULL;
-
-	hdr = (struct hci_command_hdr *) skb_put(skb, HCI_COMMAND_HDR_SIZE);
-	hdr->opcode = cpu_to_le16(opcode);
-	hdr->plen   = plen;
-
-	if (plen)
-		memcpy(skb_put(skb, plen), param, plen);
-
-	BT_DBG("skb len %d", skb->len);
-
-	bt_cb(skb)->pkt_type = HCI_COMMAND_PKT;
-	bt_cb(skb)->opcode = opcode;
-
-	return skb;
-}
-
 /* Send HCI command */
 int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen,
 		 const void *param)
@@ -4546,7 +3387,7 @@ int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen,
 		return -ENOMEM;
 	}
 
-	/* Stand-alone HCI commands must be flaged as
+	/* Stand-alone HCI commands must be flagged as
 	 * single-command requests.
 	 */
 	bt_cb(skb)->req.start = true;
@@ -4557,43 +3398,6 @@ int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen,
 	return 0;
 }
 
-/* Queue a command to an asynchronous HCI request */
-void hci_req_add_ev(struct hci_request *req, u16 opcode, u32 plen,
-		    const void *param, u8 event)
-{
-	struct hci_dev *hdev = req->hdev;
-	struct sk_buff *skb;
-
-	BT_DBG("%s opcode 0x%4.4x plen %d", hdev->name, opcode, plen);
-
-	/* If an error occured during request building, there is no point in
-	 * queueing the HCI command. We can simply return.
-	 */
-	if (req->err)
-		return;
-
-	skb = hci_prepare_cmd(hdev, opcode, plen, param);
-	if (!skb) {
-		BT_ERR("%s no memory for command (opcode 0x%4.4x)",
-		       hdev->name, opcode);
-		req->err = -ENOMEM;
-		return;
-	}
-
-	if (skb_queue_empty(&req->cmd_q))
-		bt_cb(skb)->req.start = true;
-
-	bt_cb(skb)->req.event = event;
-
-	skb_queue_tail(&req->cmd_q, skb);
-}
-
-void hci_req_add(struct hci_request *req, u16 opcode, u32 plen,
-		 const void *param)
-{
-	hci_req_add_ev(req, opcode, plen, param, 0);
-}
-
 /* Get data from the previously sent command */
 void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode)
 {
@@ -4661,8 +3465,12 @@ static void hci_queue_acl(struct hci_chan *chan, struct sk_buff_head *queue,
 
 		skb_shinfo(skb)->frag_list = NULL;
 
-		/* Queue all fragments atomically */
-		spin_lock(&queue->lock);
+		/* Queue all fragments atomically. We need to use spin_lock_bh
+		 * here because of 6LoWPAN links, as there this function is
+		 * called from softirq and using normal spin lock could cause
+		 * deadlocks.
+		 */
+		spin_lock_bh(&queue->lock);
 
 		__skb_queue_tail(queue, skb);
 
@@ -4679,7 +3487,7 @@ static void hci_queue_acl(struct hci_chan *chan, struct sk_buff_head *queue,
 			__skb_queue_tail(queue, skb);
 		} while (list);
 
-		spin_unlock(&queue->lock);
+		spin_unlock_bh(&queue->lock);
 	}
 }
 
@@ -4939,7 +3747,7 @@ static inline int __get_blocks(struct hci_dev *hdev, struct sk_buff *skb)
 
 static void __check_timeout(struct hci_dev *hdev, unsigned int cnt)
 {
-	if (!test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) {
+	if (!hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) {
 		/* ACL tx timeout must be longer than maximum
 		 * link supervision timeout (40.9 seconds) */
 		if (!cnt && time_after(jiffies, hdev->acl_last_tx +
@@ -5122,7 +3930,7 @@ static void hci_sched_le(struct hci_dev *hdev)
 	if (!hci_conn_num(hdev, LE_LINK))
 		return;
 
-	if (!test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) {
+	if (!hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) {
 		/* LE tx timeout must be longer than maximum
 		 * link supervision timeout (40.9 seconds) */
 		if (!hdev->le_cnt && hdev->le_pkts &&
@@ -5170,7 +3978,7 @@ static void hci_tx_work(struct work_struct *work)
 	BT_DBG("%s acl %d sco %d le %d", hdev->name, hdev->acl_cnt,
 	       hdev->sco_cnt, hdev->le_cnt);
 
-	if (!test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) {
+	if (!hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) {
 		/* Schedule queues and send stuff to HCI driver */
 		hci_sched_acl(hdev);
 		hci_sched_sco(hdev);
@@ -5285,9 +4093,10 @@ static void hci_resend_last(struct hci_dev *hdev)
 	queue_work(hdev->workqueue, &hdev->cmd_work);
 }
 
-void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status)
+void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status,
+			  hci_req_complete_t *req_complete,
+			  hci_req_complete_skb_t *req_complete_skb)
 {
-	hci_req_complete_t req_complete = NULL;
 	struct sk_buff *skb;
 	unsigned long flags;
 
@@ -5319,18 +4128,14 @@ void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status)
 	 * callback would be found in hdev->sent_cmd instead of the
 	 * command queue (hdev->cmd_q).
 	 */
-	if (hdev->sent_cmd) {
-		req_complete = bt_cb(hdev->sent_cmd)->req.complete;
-
-		if (req_complete) {
-			/* We must set the complete callback to NULL to
-			 * avoid calling the callback more than once if
-			 * this function gets called again.
-			 */
-			bt_cb(hdev->sent_cmd)->req.complete = NULL;
+	if (bt_cb(hdev->sent_cmd)->req.complete) {
+		*req_complete = bt_cb(hdev->sent_cmd)->req.complete;
+		return;
+	}
 
-			goto call_complete;
-		}
+	if (bt_cb(hdev->sent_cmd)->req.complete_skb) {
+		*req_complete_skb = bt_cb(hdev->sent_cmd)->req.complete_skb;
+		return;
 	}
 
 	/* Remove all pending commands belonging to this request */
@@ -5341,14 +4146,11 @@ void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status)
 			break;
 		}
 
-		req_complete = bt_cb(skb)->req.complete;
+		*req_complete = bt_cb(skb)->req.complete;
+		*req_complete_skb = bt_cb(skb)->req.complete_skb;
 		kfree_skb(skb);
 	}
 	spin_unlock_irqrestore(&hdev->cmd_q.lock, flags);
-
-call_complete:
-	if (req_complete)
-		req_complete(hdev, status);
 }
 
 static void hci_rx_work(struct work_struct *work)
@@ -5367,7 +4169,7 @@ static void hci_rx_work(struct work_struct *work)
 			hci_send_to_sock(hdev, skb);
 		}
 
-		if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) {
+		if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) {
 			kfree_skb(skb);
 			continue;
 		}
@@ -5437,280 +4239,3 @@ 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);
-}
-
-static void add_to_white_list(struct hci_request *req,
-			      struct hci_conn_params *params)
-{
-	struct hci_cp_le_add_to_white_list cp;
-
-	cp.bdaddr_type = params->addr_type;
-	bacpy(&cp.bdaddr, &params->addr);
-
-	hci_req_add(req, HCI_OP_LE_ADD_TO_WHITE_LIST, sizeof(cp), &cp);
-}
-
-static u8 update_white_list(struct hci_request *req)
-{
-	struct hci_dev *hdev = req->hdev;
-	struct hci_conn_params *params;
-	struct bdaddr_list *b;
-	uint8_t white_list_entries = 0;
-
-	/* Go through the current white list programmed into the
-	 * controller one by one and check if that address is still
-	 * in the list of pending connections or list of devices to
-	 * report. If not present in either list, then queue the
-	 * command to remove it from the controller.
-	 */
-	list_for_each_entry(b, &hdev->le_white_list, list) {
-		struct hci_cp_le_del_from_white_list cp;
-
-		if (hci_pend_le_action_lookup(&hdev->pend_le_conns,
-					      &b->bdaddr, b->bdaddr_type) ||
-		    hci_pend_le_action_lookup(&hdev->pend_le_reports,
-					      &b->bdaddr, b->bdaddr_type)) {
-			white_list_entries++;
-			continue;
-		}
-
-		cp.bdaddr_type = b->bdaddr_type;
-		bacpy(&cp.bdaddr, &b->bdaddr);
-
-		hci_req_add(req, HCI_OP_LE_DEL_FROM_WHITE_LIST,
-			    sizeof(cp), &cp);
-	}
-
-	/* Since all no longer valid white list entries have been
-	 * removed, walk through the list of pending connections
-	 * and ensure that any new device gets programmed into
-	 * the controller.
-	 *
-	 * If the list of the devices is larger than the list of
-	 * available white list entries in the controller, then
-	 * just abort and return filer policy value to not use the
-	 * white list.
-	 */
-	list_for_each_entry(params, &hdev->pend_le_conns, action) {
-		if (hci_bdaddr_list_lookup(&hdev->le_white_list,
-					   &params->addr, params->addr_type))
-			continue;
-
-		if (white_list_entries >= hdev->le_white_list_size) {
-			/* Select filter policy to accept all advertising */
-			return 0x00;
-		}
-
-		if (hci_find_irk_by_addr(hdev, &params->addr,
-					 params->addr_type)) {
-			/* White list can not be used with RPAs */
-			return 0x00;
-		}
-
-		white_list_entries++;
-		add_to_white_list(req, params);
-	}
-
-	/* After adding all new pending connections, walk through
-	 * the list of pending reports and also add these to the
-	 * white list if there is still space.
-	 */
-	list_for_each_entry(params, &hdev->pend_le_reports, action) {
-		if (hci_bdaddr_list_lookup(&hdev->le_white_list,
-					   &params->addr, params->addr_type))
-			continue;
-
-		if (white_list_entries >= hdev->le_white_list_size) {
-			/* Select filter policy to accept all advertising */
-			return 0x00;
-		}
-
-		if (hci_find_irk_by_addr(hdev, &params->addr,
-					 params->addr_type)) {
-			/* White list can not be used with RPAs */
-			return 0x00;
-		}
-
-		white_list_entries++;
-		add_to_white_list(req, params);
-	}
-
-	/* Select filter policy to use white list */
-	return 0x01;
-}
-
-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;
-	u8 filter_policy;
-
-	/* Set require_privacy to false since no SCAN_REQ are send
-	 * during passive scanning. Not using an unresolvable address
-	 * here is important so that peer devices using direct
-	 * advertising with our address will be correctly reported
-	 * by the controller.
-	 */
-	if (hci_update_random_address(req, false, &own_addr_type))
-		return;
-
-	/* Adding or removing entries from the white list must
-	 * happen before enabling scanning. The controller does
-	 * not allow white list modification while scanning.
-	 */
-	filter_policy = update_white_list(req);
-
-	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;
-	param_cp.filter_policy = filter_policy;
-	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;
-
-	if (!test_bit(HCI_UP, &hdev->flags) ||
-	    test_bit(HCI_INIT, &hdev->flags) ||
-	    test_bit(HCI_SETUP, &hdev->dev_flags) ||
-	    test_bit(HCI_CONFIG, &hdev->dev_flags) ||
-	    test_bit(HCI_AUTO_OFF, &hdev->dev_flags) ||
-	    test_bit(HCI_UNREGISTER, &hdev->dev_flags))
-		return;
-
-	/* No point in doing scanning if LE support hasn't been enabled */
-	if (!test_bit(HCI_LE_ENABLED, &hdev->dev_flags))
-		return;
-
-	/* If discovery is active don't interfere with it */
-	if (hdev->discovery.state != DISCOVERY_STOPPED)
-		return;
-
-	hci_req_init(&req, hdev);
-
-	if (list_empty(&hdev->pend_le_conns) &&
-	    list_empty(&hdev->pend_le_reports)) {
-		/* If there is no pending LE connections or devices
-		 * to be scanned for, 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);
-}
-
-static bool disconnected_whitelist_entries(struct hci_dev *hdev)
-{
-	struct bdaddr_list *b;
-
-	list_for_each_entry(b, &hdev->whitelist, list) {
-		struct hci_conn *conn;
-
-		conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &b->bdaddr);
-		if (!conn)
-			return true;
-
-		if (conn->state != BT_CONNECTED && conn->state != BT_CONFIG)
-			return true;
-	}
-
-	return false;
-}
-
-void hci_update_page_scan(struct hci_dev *hdev, struct hci_request *req)
-{
-	u8 scan;
-
-	if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
-		return;
-
-	if (!hdev_is_powered(hdev))
-		return;
-
-	if (mgmt_powering_down(hdev))
-		return;
-
-	if (test_bit(HCI_CONNECTABLE, &hdev->dev_flags) ||
-	    disconnected_whitelist_entries(hdev))
-		scan = SCAN_PAGE;
-	else
-		scan = SCAN_DISABLED;
-
-	if (test_bit(HCI_PSCAN, &hdev->flags) == !!(scan & SCAN_PAGE))
-		return;
-
-	if (test_bit(HCI_DISCOVERABLE, &hdev->dev_flags))
-		scan |= SCAN_INQUIRY;
-
-	if (req)
-		hci_req_add(req, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan);
-	else
-		hci_send_cmd(hdev, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan);
-}
diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c
new file mode 100644
index 000000000000..7db4220941cc
--- /dev/null
+++ b/net/bluetooth/hci_debugfs.c
@@ -0,0 +1,1142 @@
+/*
+   BlueZ - Bluetooth protocol stack for Linux
+
+   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;
+
+   THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+   OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+   FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS.
+   IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY
+   CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES
+   WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+   ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+   OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+
+   ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS,
+   COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS
+   SOFTWARE IS DISCLAIMED.
+*/
+
+#include <linux/debugfs.h>
+
+#include <net/bluetooth/bluetooth.h>
+#include <net/bluetooth/hci_core.h>
+
+#include "hci_debugfs.h"
+
+#define DEFINE_QUIRK_ATTRIBUTE(__name, __quirk)				      \
+static ssize_t __name ## _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(__quirk, &hdev->quirks) ? 'Y' : 'N';		      \
+	buf[1] = '\n';							      \
+	buf[2] = '\0';							      \
+	return simple_read_from_buffer(user_buf, count, ppos, buf, 2);	      \
+}									      \
+									      \
+static ssize_t __name ## _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(__quirk, &hdev->quirks))			      \
+		return -EALREADY;					      \
+									      \
+	change_bit(__quirk, &hdev->quirks);				      \
+									      \
+	return count;							      \
+}									      \
+									      \
+static const struct file_operations __name ## _fops = {			      \
+	.open		= simple_open,					      \
+	.read		= __name ## _read,				      \
+	.write		= __name ## _write,				      \
+	.llseek		= default_llseek,				      \
+}									      \
+
+static int features_show(struct seq_file *f, void *ptr)
+{
+	struct hci_dev *hdev = f->private;
+	u8 p;
+
+	hci_dev_lock(hdev);
+	for (p = 0; p < HCI_MAX_PAGES && p <= hdev->max_page; p++) {
+		seq_printf(f, "%2u: 0x%2.2x 0x%2.2x 0x%2.2x 0x%2.2x "
+			   "0x%2.2x 0x%2.2x 0x%2.2x 0x%2.2x\n", p,
+			   hdev->features[p][0], hdev->features[p][1],
+			   hdev->features[p][2], hdev->features[p][3],
+			   hdev->features[p][4], hdev->features[p][5],
+			   hdev->features[p][6], hdev->features[p][7]);
+	}
+	if (lmp_le_capable(hdev))
+		seq_printf(f, "LE: 0x%2.2x 0x%2.2x 0x%2.2x 0x%2.2x "
+			   "0x%2.2x 0x%2.2x 0x%2.2x 0x%2.2x\n",
+			   hdev->le_features[0], hdev->le_features[1],
+			   hdev->le_features[2], hdev->le_features[3],
+			   hdev->le_features[4], hdev->le_features[5],
+			   hdev->le_features[6], hdev->le_features[7]);
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int features_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, features_show, inode->i_private);
+}
+
+static const struct file_operations features_fops = {
+	.open		= features_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int device_id_show(struct seq_file *f, void *ptr)
+{
+	struct hci_dev *hdev = f->private;
+
+	hci_dev_lock(hdev);
+	seq_printf(f, "%4.4x:%4.4x:%4.4x:%4.4x\n", hdev->devid_source,
+		  hdev->devid_vendor, hdev->devid_product, hdev->devid_version);
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int device_id_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, device_id_show, inode->i_private);
+}
+
+static const struct file_operations device_id_fops = {
+	.open		= device_id_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int device_list_show(struct seq_file *f, void *ptr)
+{
+	struct hci_dev *hdev = f->private;
+	struct hci_conn_params *p;
+	struct bdaddr_list *b;
+
+	hci_dev_lock(hdev);
+	list_for_each_entry(b, &hdev->whitelist, list)
+		seq_printf(f, "%pMR (type %u)\n", &b->bdaddr, b->bdaddr_type);
+	list_for_each_entry(p, &hdev->le_conn_params, list) {
+		seq_printf(f, "%pMR (type %u) %u\n", &p->addr, p->addr_type,
+			   p->auto_connect);
+	}
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int device_list_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, device_list_show, inode->i_private);
+}
+
+static const struct file_operations device_list_fops = {
+	.open		= device_list_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int blacklist_show(struct seq_file *f, void *p)
+{
+	struct hci_dev *hdev = f->private;
+	struct bdaddr_list *b;
+
+	hci_dev_lock(hdev);
+	list_for_each_entry(b, &hdev->blacklist, list)
+		seq_printf(f, "%pMR (type %u)\n", &b->bdaddr, b->bdaddr_type);
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int blacklist_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, blacklist_show, inode->i_private);
+}
+
+static const struct file_operations blacklist_fops = {
+	.open		= blacklist_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int uuids_show(struct seq_file *f, void *p)
+{
+	struct hci_dev *hdev = f->private;
+	struct bt_uuid *uuid;
+
+	hci_dev_lock(hdev);
+	list_for_each_entry(uuid, &hdev->uuids, list) {
+		u8 i, val[16];
+
+		/* The Bluetooth UUID values are stored in big endian,
+		 * but with reversed byte order. So convert them into
+		 * the right order for the %pUb modifier.
+		 */
+		for (i = 0; i < 16; i++)
+			val[i] = uuid->uuid[15 - i];
+
+		seq_printf(f, "%pUb\n", val);
+	}
+	hci_dev_unlock(hdev);
+
+       return 0;
+}
+
+static int uuids_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, uuids_show, inode->i_private);
+}
+
+static const struct file_operations uuids_fops = {
+	.open		= uuids_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int remote_oob_show(struct seq_file *f, void *ptr)
+{
+	struct hci_dev *hdev = f->private;
+	struct oob_data *data;
+
+	hci_dev_lock(hdev);
+	list_for_each_entry(data, &hdev->remote_oob_data, list) {
+		seq_printf(f, "%pMR (type %u) %u %*phN %*phN %*phN %*phN\n",
+			   &data->bdaddr, data->bdaddr_type, data->present,
+			   16, data->hash192, 16, data->rand192,
+			   16, data->hash256, 16, data->rand256);
+	}
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int remote_oob_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, remote_oob_show, inode->i_private);
+}
+
+static const struct file_operations remote_oob_fops = {
+	.open		= remote_oob_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+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 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] = hci_dev_test_flag(hdev, HCI_USE_DEBUG_KEYS) ? '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 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] = hci_dev_test_flag(hdev, HCI_SC_ONLY) ? '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,
+};
+
+void hci_debugfs_create_common(struct hci_dev *hdev)
+{
+	debugfs_create_file("features", 0444, hdev->debugfs, hdev,
+			    &features_fops);
+	debugfs_create_u16("manufacturer", 0444, hdev->debugfs,
+			   &hdev->manufacturer);
+	debugfs_create_u8("hci_version", 0444, hdev->debugfs, &hdev->hci_ver);
+	debugfs_create_u16("hci_revision", 0444, hdev->debugfs, &hdev->hci_rev);
+	debugfs_create_u8("hardware_error", 0444, hdev->debugfs,
+			  &hdev->hw_error_code);
+	debugfs_create_file("device_id", 0444, hdev->debugfs, hdev,
+			    &device_id_fops);
+
+	debugfs_create_file("device_list", 0444, hdev->debugfs, hdev,
+			    &device_list_fops);
+	debugfs_create_file("blacklist", 0444, hdev->debugfs, hdev,
+			    &blacklist_fops);
+	debugfs_create_file("uuids", 0444, hdev->debugfs, hdev, &uuids_fops);
+	debugfs_create_file("remote_oob", 0400, hdev->debugfs, hdev,
+			    &remote_oob_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_ssp_capable(hdev) || lmp_le_capable(hdev))
+		debugfs_create_file("use_debug_keys", 0444, hdev->debugfs,
+				    hdev, &use_debug_keys_fops);
+
+	if (lmp_sc_capable(hdev) || lmp_le_capable(hdev))
+		debugfs_create_file("sc_only_mode", 0444, hdev->debugfs,
+				    hdev, &sc_only_mode_fops);
+}
+
+static int inquiry_cache_show(struct seq_file *f, void *p)
+{
+	struct hci_dev *hdev = f->private;
+	struct discovery_state *cache = &hdev->discovery;
+	struct inquiry_entry *e;
+
+	hci_dev_lock(hdev);
+
+	list_for_each_entry(e, &cache->all, all) {
+		struct inquiry_data *data = &e->data;
+		seq_printf(f, "%pMR %d %d %d 0x%.2x%.2x%.2x 0x%.4x %d %d %u\n",
+			   &data->bdaddr,
+			   data->pscan_rep_mode, data->pscan_period_mode,
+			   data->pscan_mode, data->dev_class[2],
+			   data->dev_class[1], data->dev_class[0],
+			   __le16_to_cpu(data->clock_offset),
+			   data->rssi, data->ssp_mode, e->timestamp);
+	}
+
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int inquiry_cache_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, inquiry_cache_show, inode->i_private);
+}
+
+static const struct file_operations inquiry_cache_fops = {
+	.open		= inquiry_cache_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int link_keys_show(struct seq_file *f, void *ptr)
+{
+	struct hci_dev *hdev = f->private;
+	struct link_key *key;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(key, &hdev->link_keys, list)
+		seq_printf(f, "%pMR %u %*phN %u\n", &key->bdaddr, key->type,
+			   HCI_LINK_KEY_SIZE, key->val, key->pin_len);
+	rcu_read_unlock();
+
+	return 0;
+}
+
+static int link_keys_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, link_keys_show, inode->i_private);
+}
+
+static const struct file_operations link_keys_fops = {
+	.open		= link_keys_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int dev_class_show(struct seq_file *f, void *ptr)
+{
+	struct hci_dev *hdev = f->private;
+
+	hci_dev_lock(hdev);
+	seq_printf(f, "0x%.2x%.2x%.2x\n", hdev->dev_class[2],
+		   hdev->dev_class[1], hdev->dev_class[0]);
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int dev_class_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, dev_class_show, inode->i_private);
+}
+
+static const struct file_operations dev_class_fops = {
+	.open		= dev_class_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int voice_setting_get(void *data, u64 *val)
+{
+	struct hci_dev *hdev = data;
+
+	hci_dev_lock(hdev);
+	*val = hdev->voice_setting;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(voice_setting_fops, voice_setting_get,
+			NULL, "0x%4.4llx\n");
+
+static ssize_t ssp_debug_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] = hdev->ssp_debug_mode ? 'Y': 'N';
+	buf[1] = '\n';
+	buf[2] = '\0';
+	return simple_read_from_buffer(user_buf, count, ppos, buf, 2);
+}
+
+static const struct file_operations ssp_debug_mode_fops = {
+	.open		= simple_open,
+	.read		= ssp_debug_mode_read,
+	.llseek		= default_llseek,
+};
+
+static int auto_accept_delay_set(void *data, u64 val)
+{
+	struct hci_dev *hdev = data;
+
+	hci_dev_lock(hdev);
+	hdev->auto_accept_delay = val;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int auto_accept_delay_get(void *data, u64 *val)
+{
+	struct hci_dev *hdev = data;
+
+	hci_dev_lock(hdev);
+	*val = hdev->auto_accept_delay;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(auto_accept_delay_fops, auto_accept_delay_get,
+			auto_accept_delay_set, "%llu\n");
+
+static int idle_timeout_set(void *data, u64 val)
+{
+	struct hci_dev *hdev = data;
+
+	if (val != 0 && (val < 500 || val > 3600000))
+		return -EINVAL;
+
+	hci_dev_lock(hdev);
+	hdev->idle_timeout = val;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int idle_timeout_get(void *data, u64 *val)
+{
+	struct hci_dev *hdev = data;
+
+	hci_dev_lock(hdev);
+	*val = hdev->idle_timeout;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(idle_timeout_fops, idle_timeout_get,
+			idle_timeout_set, "%llu\n");
+
+static int sniff_min_interval_set(void *data, u64 val)
+{
+	struct hci_dev *hdev = data;
+
+	if (val == 0 || val % 2 || val > hdev->sniff_max_interval)
+		return -EINVAL;
+
+	hci_dev_lock(hdev);
+	hdev->sniff_min_interval = val;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int sniff_min_interval_get(void *data, u64 *val)
+{
+	struct hci_dev *hdev = data;
+
+	hci_dev_lock(hdev);
+	*val = hdev->sniff_min_interval;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(sniff_min_interval_fops, sniff_min_interval_get,
+			sniff_min_interval_set, "%llu\n");
+
+static int sniff_max_interval_set(void *data, u64 val)
+{
+	struct hci_dev *hdev = data;
+
+	if (val == 0 || val % 2 || val < hdev->sniff_min_interval)
+		return -EINVAL;
+
+	hci_dev_lock(hdev);
+	hdev->sniff_max_interval = val;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int sniff_max_interval_get(void *data, u64 *val)
+{
+	struct hci_dev *hdev = data;
+
+	hci_dev_lock(hdev);
+	*val = hdev->sniff_max_interval;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(sniff_max_interval_fops, sniff_max_interval_get,
+			sniff_max_interval_set, "%llu\n");
+
+void hci_debugfs_create_bredr(struct hci_dev *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("dev_class", 0444, hdev->debugfs, hdev,
+			    &dev_class_fops);
+	debugfs_create_file("voice_setting", 0444, hdev->debugfs, hdev,
+			    &voice_setting_fops);
+
+	if (lmp_ssp_capable(hdev)) {
+		debugfs_create_file("ssp_debug_mode", 0444, hdev->debugfs,
+				    hdev, &ssp_debug_mode_fops);
+		debugfs_create_file("auto_accept_delay", 0644, hdev->debugfs,
+				    hdev, &auto_accept_delay_fops);
+	}
+
+	if (lmp_sniff_capable(hdev)) {
+		debugfs_create_file("idle_timeout", 0644, hdev->debugfs,
+				    hdev, &idle_timeout_fops);
+		debugfs_create_file("sniff_min_interval", 0644, hdev->debugfs,
+				    hdev, &sniff_min_interval_fops);
+		debugfs_create_file("sniff_max_interval", 0644, hdev->debugfs,
+				    hdev, &sniff_max_interval_fops);
+	}
+}
+
+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 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 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;
+
+	hci_dev_lock(hdev);
+	seq_printf(f, "%pMR\n", &hdev->static_addr);
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int static_address_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, static_address_show, inode->i_private);
+}
+
+static const struct file_operations static_address_fops = {
+	.open		= static_address_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static ssize_t force_static_address_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] = hci_dev_test_flag(hdev, HCI_FORCE_STATIC_ADDR) ? '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 == hci_dev_test_flag(hdev, HCI_FORCE_STATIC_ADDR))
+		return -EALREADY;
+
+	hci_dev_change_flag(hdev, HCI_FORCE_STATIC_ADDR);
+
+	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);
+	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 white_list_open(struct inode *inode, struct file *file)
+{
+	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 smp_irk *irk;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(irk, &hdev->identity_resolving_keys, list) {
+		seq_printf(f, "%pMR (type %u) %*phN %pMR\n",
+			   &irk->bdaddr, irk->addr_type,
+			   16, irk->val, &irk->rpa);
+	}
+	rcu_read_unlock();
+
+	return 0;
+}
+
+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)
+{
+	struct hci_dev *hdev = f->private;
+	struct smp_ltk *ltk;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(ltk, &hdev->long_term_keys, list)
+		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),
+			   __le64_to_cpu(ltk->rand), 16, ltk->val);
+	rcu_read_unlock();
+
+	return 0;
+}
+
+static int long_term_keys_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, long_term_keys_show, inode->i_private);
+}
+
+static const struct file_operations long_term_keys_fops = {
+	.open		= long_term_keys_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int conn_min_interval_set(void *data, u64 val)
+{
+	struct hci_dev *hdev = data;
+
+	if (val < 0x0006 || val > 0x0c80 || val > hdev->le_conn_max_interval)
+		return -EINVAL;
+
+	hci_dev_lock(hdev);
+	hdev->le_conn_min_interval = val;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int conn_min_interval_get(void *data, u64 *val)
+{
+	struct hci_dev *hdev = data;
+
+	hci_dev_lock(hdev);
+	*val = hdev->le_conn_min_interval;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(conn_min_interval_fops, conn_min_interval_get,
+			conn_min_interval_set, "%llu\n");
+
+static int conn_max_interval_set(void *data, u64 val)
+{
+	struct hci_dev *hdev = data;
+
+	if (val < 0x0006 || val > 0x0c80 || val < hdev->le_conn_min_interval)
+		return -EINVAL;
+
+	hci_dev_lock(hdev);
+	hdev->le_conn_max_interval = val;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int conn_max_interval_get(void *data, u64 *val)
+{
+	struct hci_dev *hdev = data;
+
+	hci_dev_lock(hdev);
+	*val = hdev->le_conn_max_interval;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(conn_max_interval_fops, conn_max_interval_get,
+			conn_max_interval_set, "%llu\n");
+
+static int conn_latency_set(void *data, u64 val)
+{
+	struct hci_dev *hdev = data;
+
+	if (val > 0x01f3)
+		return -EINVAL;
+
+	hci_dev_lock(hdev);
+	hdev->le_conn_latency = val;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int conn_latency_get(void *data, u64 *val)
+{
+	struct hci_dev *hdev = data;
+
+	hci_dev_lock(hdev);
+	*val = hdev->le_conn_latency;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(conn_latency_fops, conn_latency_get,
+			conn_latency_set, "%llu\n");
+
+static int supervision_timeout_set(void *data, u64 val)
+{
+	struct hci_dev *hdev = data;
+
+	if (val < 0x000a || val > 0x0c80)
+		return -EINVAL;
+
+	hci_dev_lock(hdev);
+	hdev->le_supv_timeout = val;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int supervision_timeout_get(void *data, u64 *val)
+{
+	struct hci_dev *hdev = data;
+
+	hci_dev_lock(hdev);
+	*val = hdev->le_supv_timeout;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(supervision_timeout_fops, supervision_timeout_get,
+			supervision_timeout_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 int adv_min_interval_set(void *data, u64 val)
+{
+	struct hci_dev *hdev = data;
+
+	if (val < 0x0020 || val > 0x4000 || val > hdev->le_adv_max_interval)
+		return -EINVAL;
+
+	hci_dev_lock(hdev);
+	hdev->le_adv_min_interval = val;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int adv_min_interval_get(void *data, u64 *val)
+{
+	struct hci_dev *hdev = data;
+
+	hci_dev_lock(hdev);
+	*val = hdev->le_adv_min_interval;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(adv_min_interval_fops, adv_min_interval_get,
+			adv_min_interval_set, "%llu\n");
+
+static int adv_max_interval_set(void *data, u64 val)
+{
+	struct hci_dev *hdev = data;
+
+	if (val < 0x0020 || val > 0x4000 || val < hdev->le_adv_min_interval)
+		return -EINVAL;
+
+	hci_dev_lock(hdev);
+	hdev->le_adv_max_interval = val;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int adv_max_interval_get(void *data, u64 *val)
+{
+	struct hci_dev *hdev = data;
+
+	hci_dev_lock(hdev);
+	*val = hdev->le_adv_max_interval;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(adv_max_interval_fops, adv_max_interval_get,
+			adv_max_interval_set, "%llu\n");
+
+DEFINE_QUIRK_ATTRIBUTE(quirk_strict_duplicate_filter,
+		       HCI_QUIRK_STRICT_DUPLICATE_FILTER);
+DEFINE_QUIRK_ATTRIBUTE(quirk_simultaneous_discovery,
+		       HCI_QUIRK_SIMULTANEOUS_DISCOVERY);
+
+void hci_debugfs_create_le(struct hci_dev *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("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("conn_latency", 0644, hdev->debugfs, hdev,
+			    &conn_latency_fops);
+	debugfs_create_file("supervision_timeout", 0644, hdev->debugfs, hdev,
+			    &supervision_timeout_fops);
+	debugfs_create_file("adv_channel_map", 0644, hdev->debugfs, hdev,
+			    &adv_channel_map_fops);
+	debugfs_create_file("adv_min_interval", 0644, hdev->debugfs, hdev,
+			    &adv_min_interval_fops);
+	debugfs_create_file("adv_max_interval", 0644, hdev->debugfs, hdev,
+			    &adv_max_interval_fops);
+	debugfs_create_u16("discov_interleaved_timeout", 0644, hdev->debugfs,
+			   &hdev->discov_interleaved_timeout);
+
+	debugfs_create_file("quirk_strict_duplicate_filter", 0644,
+			    hdev->debugfs, hdev,
+			    &quirk_strict_duplicate_filter_fops);
+	debugfs_create_file("quirk_simultaneous_discovery", 0644,
+			    hdev->debugfs, hdev,
+			    &quirk_simultaneous_discovery_fops);
+}
+
+void hci_debugfs_create_conn(struct hci_conn *conn)
+{
+	struct hci_dev *hdev = conn->hdev;
+	char name[6];
+
+	if (IS_ERR_OR_NULL(hdev->debugfs))
+		return;
+
+	snprintf(name, sizeof(name), "%u", conn->handle);
+	conn->debugfs = debugfs_create_dir(name, hdev->debugfs);
+}
diff --git a/net/bluetooth/hci_debugfs.h b/net/bluetooth/hci_debugfs.h
new file mode 100644
index 000000000000..4444dc8cedc2
--- /dev/null
+++ b/net/bluetooth/hci_debugfs.h
@@ -0,0 +1,48 @@
+/*
+   BlueZ - Bluetooth protocol stack for Linux
+   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;
+
+   THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+   OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+   FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS.
+   IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY
+   CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES
+   WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+   ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+   OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+
+   ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS,
+   COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS
+   SOFTWARE IS DISCLAIMED.
+*/
+
+#if IS_ENABLED(CONFIG_BT_DEBUGFS)
+
+void hci_debugfs_create_common(struct hci_dev *hdev);
+void hci_debugfs_create_bredr(struct hci_dev *hdev);
+void hci_debugfs_create_le(struct hci_dev *hdev);
+void hci_debugfs_create_conn(struct hci_conn *conn);
+
+#else
+
+static inline void hci_debugfs_create_common(struct hci_dev *hdev)
+{
+}
+
+static inline void hci_debugfs_create_bredr(struct hci_dev *hdev)
+{
+}
+
+static inline void hci_debugfs_create_le(struct hci_dev *hdev)
+{
+}
+
+static inline void hci_debugfs_create_conn(struct hci_conn *conn)
+{
+}
+
+#endif
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 8b0a2a6de419..7b61be73650f 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -30,10 +30,15 @@
 #include <net/bluetooth/hci_core.h>
 #include <net/bluetooth/mgmt.h>
 
+#include "hci_request.h"
+#include "hci_debugfs.h"
 #include "a2mp.h"
 #include "amp.h"
 #include "smp.h"
 
+#define ZERO_KEY "\x00\x00\x00\x00\x00\x00\x00\x00" \
+		 "\x00\x00\x00\x00\x00\x00\x00\x00"
+
 /* Handle HCI Event packets */
 
 static void hci_cc_inquiry_cancel(struct hci_dev *hdev, struct sk_buff *skb)
@@ -65,7 +70,7 @@ static void hci_cc_periodic_inq(struct hci_dev *hdev, struct sk_buff *skb)
 	if (status)
 		return;
 
-	set_bit(HCI_PERIODIC_INQ, &hdev->dev_flags);
+	hci_dev_set_flag(hdev, HCI_PERIODIC_INQ);
 }
 
 static void hci_cc_exit_periodic_inq(struct hci_dev *hdev, struct sk_buff *skb)
@@ -77,7 +82,7 @@ static void hci_cc_exit_periodic_inq(struct hci_dev *hdev, struct sk_buff *skb)
 	if (status)
 		return;
 
-	clear_bit(HCI_PERIODIC_INQ, &hdev->dev_flags);
+	hci_dev_clear_flag(hdev, HCI_PERIODIC_INQ);
 
 	hci_conn_check_pending(hdev);
 }
@@ -189,10 +194,14 @@ static void hci_cc_reset(struct hci_dev *hdev, struct sk_buff *skb)
 
 	clear_bit(HCI_RESET, &hdev->flags);
 
+	if (status)
+		return;
+
 	/* Reset all non-persistent flags */
-	hdev->dev_flags &= ~HCI_PERSISTENT_MASK;
+	hci_dev_clear_volatile_flags(hdev);
+
+	hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
 
-	hdev->discovery.state = DISCOVERY_STOPPED;
 	hdev->inq_tx_power = HCI_TX_POWER_INVALID;
 	hdev->adv_tx_power = HCI_TX_POWER_INVALID;
 
@@ -205,6 +214,42 @@ static void hci_cc_reset(struct hci_dev *hdev, struct sk_buff *skb)
 	hdev->le_scan_type = LE_SCAN_PASSIVE;
 
 	hdev->ssp_debug_mode = 0;
+
+	hci_bdaddr_list_clear(&hdev->le_white_list);
+}
+
+static void hci_cc_read_stored_link_key(struct hci_dev *hdev,
+					struct sk_buff *skb)
+{
+	struct hci_rp_read_stored_link_key *rp = (void *)skb->data;
+	struct hci_cp_read_stored_link_key *sent;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, rp->status);
+
+	sent = hci_sent_cmd_data(hdev, HCI_OP_READ_STORED_LINK_KEY);
+	if (!sent)
+		return;
+
+	if (!rp->status && sent->read_all == 0x01) {
+		hdev->stored_max_keys = rp->max_keys;
+		hdev->stored_num_keys = rp->num_keys;
+	}
+}
+
+static void hci_cc_delete_stored_link_key(struct hci_dev *hdev,
+					  struct sk_buff *skb)
+{
+	struct hci_rp_delete_stored_link_key *rp = (void *)skb->data;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, rp->status);
+
+	if (rp->status)
+		return;
+
+	if (rp->num_keys <= hdev->stored_num_keys)
+		hdev->stored_num_keys -= rp->num_keys;
+	else
+		hdev->stored_num_keys = 0;
 }
 
 static void hci_cc_write_local_name(struct hci_dev *hdev, struct sk_buff *skb)
@@ -220,7 +265,7 @@ static void hci_cc_write_local_name(struct hci_dev *hdev, struct sk_buff *skb)
 
 	hci_dev_lock(hdev);
 
-	if (test_bit(HCI_MGMT, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_MGMT))
 		mgmt_set_local_name_complete(hdev, sent, status);
 	else if (!status)
 		memcpy(hdev->dev_name, sent, HCI_MAX_NAME_LENGTH);
@@ -237,7 +282,8 @@ static void hci_cc_read_local_name(struct hci_dev *hdev, struct sk_buff *skb)
 	if (rp->status)
 		return;
 
-	if (test_bit(HCI_SETUP, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_SETUP) ||
+	    hci_dev_test_flag(hdev, HCI_CONFIG))
 		memcpy(hdev->dev_name, rp->name, HCI_MAX_NAME_LENGTH);
 }
 
@@ -252,6 +298,8 @@ static void hci_cc_write_auth_enable(struct hci_dev *hdev, struct sk_buff *skb)
 	if (!sent)
 		return;
 
+	hci_dev_lock(hdev);
+
 	if (!status) {
 		__u8 param = *((__u8 *) sent);
 
@@ -261,8 +309,10 @@ static void hci_cc_write_auth_enable(struct hci_dev *hdev, struct sk_buff *skb)
 			clear_bit(HCI_AUTH, &hdev->flags);
 	}
 
-	if (test_bit(HCI_MGMT, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_MGMT))
 		mgmt_auth_enable_complete(hdev, status);
+
+	hci_dev_unlock(hdev);
 }
 
 static void hci_cc_write_encrypt_mode(struct hci_dev *hdev, struct sk_buff *skb)
@@ -354,7 +404,7 @@ static void hci_cc_write_class_of_dev(struct hci_dev *hdev, struct sk_buff *skb)
 	if (status == 0)
 		memcpy(hdev->dev_class, sent, 3);
 
-	if (test_bit(HCI_MGMT, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_MGMT))
 		mgmt_set_class_of_dev_complete(hdev, sent, status);
 
 	hci_dev_unlock(hdev);
@@ -438,6 +488,8 @@ static void hci_cc_write_ssp_mode(struct hci_dev *hdev, struct sk_buff *skb)
 	if (!sent)
 		return;
 
+	hci_dev_lock(hdev);
+
 	if (!status) {
 		if (sent->mode)
 			hdev->features[1][0] |= LMP_HOST_SSP;
@@ -445,14 +497,16 @@ static void hci_cc_write_ssp_mode(struct hci_dev *hdev, struct sk_buff *skb)
 			hdev->features[1][0] &= ~LMP_HOST_SSP;
 	}
 
-	if (test_bit(HCI_MGMT, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_MGMT))
 		mgmt_ssp_enable_complete(hdev, sent->mode, status);
 	else if (!status) {
 		if (sent->mode)
-			set_bit(HCI_SSP_ENABLED, &hdev->dev_flags);
+			hci_dev_set_flag(hdev, HCI_SSP_ENABLED);
 		else
-			clear_bit(HCI_SSP_ENABLED, &hdev->dev_flags);
+			hci_dev_clear_flag(hdev, HCI_SSP_ENABLED);
 	}
+
+	hci_dev_unlock(hdev);
 }
 
 static void hci_cc_write_sc_support(struct hci_dev *hdev, struct sk_buff *skb)
@@ -466,6 +520,8 @@ static void hci_cc_write_sc_support(struct hci_dev *hdev, struct sk_buff *skb)
 	if (!sent)
 		return;
 
+	hci_dev_lock(hdev);
+
 	if (!status) {
 		if (sent->support)
 			hdev->features[1][0] |= LMP_HOST_SC;
@@ -473,14 +529,14 @@ static void hci_cc_write_sc_support(struct hci_dev *hdev, struct sk_buff *skb)
 			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 (!hci_dev_test_flag(hdev, HCI_MGMT) && !status) {
 		if (sent->support)
-			set_bit(HCI_SC_ENABLED, &hdev->dev_flags);
+			hci_dev_set_flag(hdev, HCI_SC_ENABLED);
 		else
-			clear_bit(HCI_SC_ENABLED, &hdev->dev_flags);
+			hci_dev_clear_flag(hdev, HCI_SC_ENABLED);
 	}
+
+	hci_dev_unlock(hdev);
 }
 
 static void hci_cc_read_local_version(struct hci_dev *hdev, struct sk_buff *skb)
@@ -492,7 +548,8 @@ static void hci_cc_read_local_version(struct hci_dev *hdev, struct sk_buff *skb)
 	if (rp->status)
 		return;
 
-	if (test_bit(HCI_SETUP, &hdev->dev_flags)) {
+	if (hci_dev_test_flag(hdev, HCI_SETUP) ||
+	    hci_dev_test_flag(hdev, HCI_CONFIG)) {
 		hdev->hci_ver = rp->hci_ver;
 		hdev->hci_rev = __le16_to_cpu(rp->hci_rev);
 		hdev->lmp_ver = rp->lmp_ver;
@@ -511,7 +568,8 @@ static void hci_cc_read_local_commands(struct hci_dev *hdev,
 	if (rp->status)
 		return;
 
-	if (test_bit(HCI_SETUP, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_SETUP) ||
+	    hci_dev_test_flag(hdev, HCI_CONFIG))
 		memcpy(hdev->commands, rp->commands, sizeof(hdev->commands));
 }
 
@@ -633,7 +691,7 @@ static void hci_cc_read_bd_addr(struct hci_dev *hdev, struct sk_buff *skb)
 	if (test_bit(HCI_INIT, &hdev->flags))
 		bacpy(&hdev->bdaddr, &rp->bdaddr);
 
-	if (test_bit(HCI_SETUP, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_SETUP))
 		bacpy(&hdev->setup_addr, &rp->bdaddr);
 }
 
@@ -842,7 +900,7 @@ static void hci_cc_pin_code_reply(struct hci_dev *hdev, struct sk_buff *skb)
 
 	hci_dev_lock(hdev);
 
-	if (test_bit(HCI_MGMT, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_MGMT))
 		mgmt_pin_code_reply_complete(hdev, &rp->bdaddr, rp->status);
 
 	if (rp->status)
@@ -868,7 +926,7 @@ static void hci_cc_pin_code_neg_reply(struct hci_dev *hdev, struct sk_buff *skb)
 
 	hci_dev_lock(hdev);
 
-	if (test_bit(HCI_MGMT, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_MGMT))
 		mgmt_pin_code_neg_reply_complete(hdev, &rp->bdaddr,
 						 rp->status);
 
@@ -927,7 +985,7 @@ static void hci_cc_user_confirm_reply(struct hci_dev *hdev, struct sk_buff *skb)
 
 	hci_dev_lock(hdev);
 
-	if (test_bit(HCI_MGMT, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_MGMT))
 		mgmt_user_confirm_reply_complete(hdev, &rp->bdaddr, ACL_LINK, 0,
 						 rp->status);
 
@@ -943,7 +1001,7 @@ static void hci_cc_user_confirm_neg_reply(struct hci_dev *hdev,
 
 	hci_dev_lock(hdev);
 
-	if (test_bit(HCI_MGMT, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_MGMT))
 		mgmt_user_confirm_neg_reply_complete(hdev, &rp->bdaddr,
 						     ACL_LINK, 0, rp->status);
 
@@ -958,7 +1016,7 @@ static void hci_cc_user_passkey_reply(struct hci_dev *hdev, struct sk_buff *skb)
 
 	hci_dev_lock(hdev);
 
-	if (test_bit(HCI_MGMT, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_MGMT))
 		mgmt_user_passkey_reply_complete(hdev, &rp->bdaddr, ACL_LINK,
 						 0, rp->status);
 
@@ -974,7 +1032,7 @@ static void hci_cc_user_passkey_neg_reply(struct hci_dev *hdev,
 
 	hci_dev_lock(hdev);
 
-	if (test_bit(HCI_MGMT, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_MGMT))
 		mgmt_user_passkey_neg_reply_complete(hdev, &rp->bdaddr,
 						     ACL_LINK, 0, rp->status);
 
@@ -987,11 +1045,6 @@ static void hci_cc_read_local_oob_data(struct hci_dev *hdev,
 	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_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,
@@ -1000,15 +1053,8 @@ static void hci_cc_read_local_oob_ext_data(struct hci_dev *hdev,
 	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);
@@ -1045,13 +1091,13 @@ static void hci_cc_le_set_adv_enable(struct hci_dev *hdev, struct sk_buff *skb)
 
 	hci_dev_lock(hdev);
 
-	/* If we're doing connection initation as peripheral. Set a
+	/* If we're doing connection initiation as peripheral. Set a
 	 * timeout in case something goes wrong.
 	 */
 	if (*sent) {
 		struct hci_conn *conn;
 
-		set_bit(HCI_LE_ADV, &hdev->dev_flags);
+		hci_dev_set_flag(hdev, HCI_LE_ADV);
 
 		conn = hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT);
 		if (conn)
@@ -1059,7 +1105,7 @@ static void hci_cc_le_set_adv_enable(struct hci_dev *hdev, struct sk_buff *skb)
 					   &conn->le_conn_timeout,
 					   conn->conn_timeout);
 	} else {
-		clear_bit(HCI_LE_ADV, &hdev->dev_flags);
+		hci_dev_clear_flag(hdev, HCI_LE_ADV);
 	}
 
 	hci_dev_unlock(hdev);
@@ -1130,9 +1176,11 @@ static void hci_cc_le_set_scan_enable(struct hci_dev *hdev,
 	if (!cp)
 		return;
 
+	hci_dev_lock(hdev);
+
 	switch (cp->enable) {
 	case LE_SCAN_ENABLE:
-		set_bit(HCI_LE_SCAN, &hdev->dev_flags);
+		hci_dev_set_flag(hdev, HCI_LE_SCAN);
 		if (hdev->le_scan_type == LE_SCAN_ACTIVE)
 			clear_pending_adv_report(hdev);
 		break;
@@ -1157,7 +1205,7 @@ static void hci_cc_le_set_scan_enable(struct hci_dev *hdev,
 		 */
 		cancel_delayed_work(&hdev->le_scan_disable);
 
-		clear_bit(HCI_LE_SCAN, &hdev->dev_flags);
+		hci_dev_clear_flag(hdev, HCI_LE_SCAN);
 
 		/* The HCI_LE_SCAN_INTERRUPTED flag indicates that we
 		 * interrupted scanning due to a connect request. Mark
@@ -1166,10 +1214,9 @@ static void hci_cc_le_set_scan_enable(struct hci_dev *hdev,
 		 * been disabled because of active scanning, so
 		 * re-enable it again if necessary.
 		 */
-		if (test_and_clear_bit(HCI_LE_SCAN_INTERRUPTED,
-				       &hdev->dev_flags))
+		if (hci_dev_test_and_clear_flag(hdev, HCI_LE_SCAN_INTERRUPTED))
 			hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
-		else if (!test_bit(HCI_LE_ADV, &hdev->dev_flags) &&
+		else if (!hci_dev_test_flag(hdev, HCI_LE_ADV) &&
 			 hdev->discovery.state == DISCOVERY_FINDING)
 			mgmt_reenable_advertising(hdev);
 
@@ -1179,6 +1226,8 @@ static void hci_cc_le_set_scan_enable(struct hci_dev *hdev,
 		BT_ERR("Used reserved LE_Scan_Enable param %d", cp->enable);
 		break;
 	}
+
+	hci_dev_unlock(hdev);
 }
 
 static void hci_cc_le_read_white_list_size(struct hci_dev *hdev,
@@ -1258,6 +1307,55 @@ static void hci_cc_le_read_supported_states(struct hci_dev *hdev,
 	memcpy(hdev->le_states, rp->le_states, 8);
 }
 
+static void hci_cc_le_read_def_data_len(struct hci_dev *hdev,
+					struct sk_buff *skb)
+{
+	struct hci_rp_le_read_def_data_len *rp = (void *) skb->data;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, rp->status);
+
+	if (rp->status)
+		return;
+
+	hdev->le_def_tx_len = le16_to_cpu(rp->tx_len);
+	hdev->le_def_tx_time = le16_to_cpu(rp->tx_time);
+}
+
+static void hci_cc_le_write_def_data_len(struct hci_dev *hdev,
+					 struct sk_buff *skb)
+{
+	struct hci_cp_le_write_def_data_len *sent;
+	__u8 status = *((__u8 *) skb->data);
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, status);
+
+	if (status)
+		return;
+
+	sent = hci_sent_cmd_data(hdev, HCI_OP_LE_WRITE_DEF_DATA_LEN);
+	if (!sent)
+		return;
+
+	hdev->le_def_tx_len = le16_to_cpu(sent->tx_len);
+	hdev->le_def_tx_time = le16_to_cpu(sent->tx_time);
+}
+
+static void hci_cc_le_read_max_data_len(struct hci_dev *hdev,
+					struct sk_buff *skb)
+{
+	struct hci_rp_le_read_max_data_len *rp = (void *) skb->data;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, rp->status);
+
+	if (rp->status)
+		return;
+
+	hdev->le_max_tx_len = le16_to_cpu(rp->tx_len);
+	hdev->le_max_tx_time = le16_to_cpu(rp->tx_time);
+	hdev->le_max_rx_len = le16_to_cpu(rp->rx_len);
+	hdev->le_max_rx_time = le16_to_cpu(rp->rx_time);
+}
+
 static void hci_cc_write_le_host_supported(struct hci_dev *hdev,
 					   struct sk_buff *skb)
 {
@@ -1273,19 +1371,23 @@ static void hci_cc_write_le_host_supported(struct hci_dev *hdev,
 	if (!sent)
 		return;
 
+	hci_dev_lock(hdev);
+
 	if (sent->le) {
 		hdev->features[1][0] |= LMP_HOST_LE;
-		set_bit(HCI_LE_ENABLED, &hdev->dev_flags);
+		hci_dev_set_flag(hdev, HCI_LE_ENABLED);
 	} else {
 		hdev->features[1][0] &= ~LMP_HOST_LE;
-		clear_bit(HCI_LE_ENABLED, &hdev->dev_flags);
-		clear_bit(HCI_ADVERTISING, &hdev->dev_flags);
+		hci_dev_clear_flag(hdev, HCI_LE_ENABLED);
+		hci_dev_clear_flag(hdev, HCI_ADVERTISING);
 	}
 
 	if (sent->simul)
 		hdev->features[1][0] |= LMP_HOST_LE_BREDR;
 	else
 		hdev->features[1][0] &= ~LMP_HOST_LE_BREDR;
+
+	hci_dev_unlock(hdev);
 }
 
 static void hci_cc_set_adv_param(struct hci_dev *hdev, struct sk_buff *skb)
@@ -1374,6 +1476,21 @@ unlock:
 	hci_dev_unlock(hdev);
 }
 
+static void hci_cc_write_ssp_debug_mode(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	u8 status = *((u8 *) skb->data);
+	u8 *mode;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, status);
+
+	if (status)
+		return;
+
+	mode = hci_sent_cmd_data(hdev, HCI_OP_WRITE_SSP_DEBUG_MODE);
+	if (mode)
+		hdev->ssp_debug_mode = *mode;
+}
+
 static void hci_cs_inquiry(struct hci_dev *hdev, __u8 status)
 {
 	BT_DBG("%s status 0x%2.2x", hdev->name, status);
@@ -1407,7 +1524,7 @@ static void hci_cs_create_conn(struct hci_dev *hdev, __u8 status)
 		if (conn && conn->state == BT_CONNECT) {
 			if (status != 0x0c || conn->attempt > 2) {
 				conn->state = BT_CLOSED;
-				hci_proto_connect_cfm(conn, status);
+				hci_connect_cfm(conn, status);
 				hci_conn_del(conn);
 			} else
 				conn->state = BT_CONNECT2;
@@ -1451,7 +1568,7 @@ static void hci_cs_add_sco(struct hci_dev *hdev, __u8 status)
 		if (sco) {
 			sco->state = BT_CLOSED;
 
-			hci_proto_connect_cfm(sco, status);
+			hci_connect_cfm(sco, status);
 			hci_conn_del(sco);
 		}
 	}
@@ -1478,7 +1595,7 @@ static void hci_cs_auth_requested(struct hci_dev *hdev, __u8 status)
 	conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(cp->handle));
 	if (conn) {
 		if (conn->state == BT_CONFIG) {
-			hci_proto_connect_cfm(conn, status);
+			hci_connect_cfm(conn, status);
 			hci_conn_drop(conn);
 		}
 	}
@@ -1505,7 +1622,7 @@ static void hci_cs_set_conn_encrypt(struct hci_dev *hdev, __u8 status)
 	conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(cp->handle));
 	if (conn) {
 		if (conn->state == BT_CONFIG) {
-			hci_proto_connect_cfm(conn, status);
+			hci_connect_cfm(conn, status);
 			hci_conn_drop(conn);
 		}
 	}
@@ -1576,9 +1693,15 @@ static void hci_check_pending_name(struct hci_dev *hdev, struct hci_conn *conn,
 	struct discovery_state *discov = &hdev->discovery;
 	struct inquiry_entry *e;
 
-	if (conn && !test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags))
-		mgmt_device_connected(hdev, bdaddr, ACL_LINK, 0x00, 0, name,
-				      name_len, conn->dev_class);
+	/* Update the mgmt connected state if necessary. Be careful with
+	 * conn objects that exist but are not (yet) connected however.
+	 * Only those in BT_CONFIG or BT_CONNECTED states can be
+	 * considered connected.
+	 */
+	if (conn &&
+	    (conn->state == BT_CONFIG || conn->state == BT_CONNECTED) &&
+	    !test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags))
+		mgmt_device_connected(hdev, conn, 0, name, name_len);
 
 	if (discov->state == DISCOVERY_STOPPED)
 		return;
@@ -1633,7 +1756,7 @@ static void hci_cs_remote_name_req(struct hci_dev *hdev, __u8 status)
 
 	conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &cp->bdaddr);
 
-	if (test_bit(HCI_MGMT, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_MGMT))
 		hci_check_pending_name(hdev, conn, &cp->bdaddr, NULL, 0);
 
 	if (!conn)
@@ -1675,7 +1798,7 @@ static void hci_cs_read_remote_features(struct hci_dev *hdev, __u8 status)
 	conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(cp->handle));
 	if (conn) {
 		if (conn->state == BT_CONFIG) {
-			hci_proto_connect_cfm(conn, status);
+			hci_connect_cfm(conn, status);
 			hci_conn_drop(conn);
 		}
 	}
@@ -1702,7 +1825,7 @@ static void hci_cs_read_remote_ext_features(struct hci_dev *hdev, __u8 status)
 	conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(cp->handle));
 	if (conn) {
 		if (conn->state == BT_CONFIG) {
-			hci_proto_connect_cfm(conn, status);
+			hci_connect_cfm(conn, status);
 			hci_conn_drop(conn);
 		}
 	}
@@ -1737,7 +1860,7 @@ static void hci_cs_setup_sync_conn(struct hci_dev *hdev, __u8 status)
 		if (sco) {
 			sco->state = BT_CLOSED;
 
-			hci_proto_connect_cfm(sco, status);
+			hci_connect_cfm(sco, status);
 			hci_conn_del(sco);
 		}
 	}
@@ -1913,6 +2036,33 @@ unlock:
 	hci_dev_unlock(hdev);
 }
 
+static void hci_cs_le_read_remote_features(struct hci_dev *hdev, u8 status)
+{
+	struct hci_cp_le_read_remote_features *cp;
+	struct hci_conn *conn;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, status);
+
+	if (!status)
+		return;
+
+	cp = hci_sent_cmd_data(hdev, HCI_OP_LE_READ_REMOTE_FEATURES);
+	if (!cp)
+		return;
+
+	hci_dev_lock(hdev);
+
+	conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(cp->handle));
+	if (conn) {
+		if (conn->state == BT_CONFIG) {
+			hci_connect_cfm(conn, status);
+			hci_conn_drop(conn);
+		}
+	}
+
+	hci_dev_unlock(hdev);
+}
+
 static void hci_cs_le_start_enc(struct hci_dev *hdev, u8 status)
 {
 	struct hci_cp_le_start_enc *cp;
@@ -1943,6 +2093,29 @@ unlock:
 	hci_dev_unlock(hdev);
 }
 
+static void hci_cs_switch_role(struct hci_dev *hdev, u8 status)
+{
+	struct hci_cp_switch_role *cp;
+	struct hci_conn *conn;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, status);
+
+	if (!status)
+		return;
+
+	cp = hci_sent_cmd_data(hdev, HCI_OP_SWITCH_ROLE);
+	if (!cp)
+		return;
+
+	hci_dev_lock(hdev);
+
+	conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &cp->bdaddr);
+	if (conn)
+		clear_bit(HCI_CONN_RSWITCH_PEND, &conn->flags);
+
+	hci_dev_unlock(hdev);
+}
+
 static void hci_inquiry_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	__u8 status = *((__u8 *) skb->data);
@@ -1959,7 +2132,7 @@ static void hci_inquiry_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	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))
+	if (!hci_dev_test_flag(hdev, HCI_MGMT))
 		return;
 
 	hci_dev_lock(hdev);
@@ -1968,7 +2141,16 @@ static void hci_inquiry_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		goto unlock;
 
 	if (list_empty(&discov->resolve)) {
-		hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
+		/* When BR/EDR inquiry is active and no LE scanning is in
+		 * progress, then change discovery state to indicate completion.
+		 *
+		 * When running LE scanning and BR/EDR inquiry simultaneously
+		 * and the LE scan already finished, then change the discovery
+		 * state to indicate completion.
+		 */
+		if (!hci_dev_test_flag(hdev, HCI_LE_SCAN) ||
+		    !test_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks))
+			hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
 		goto unlock;
 	}
 
@@ -1977,7 +2159,16 @@ static void hci_inquiry_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		e->name_state = NAME_PENDING;
 		hci_discovery_set_state(hdev, DISCOVERY_RESOLVING);
 	} else {
-		hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
+		/* When BR/EDR inquiry is active and no LE scanning is in
+		 * progress, then change discovery state to indicate completion.
+		 *
+		 * When running LE scanning and BR/EDR inquiry simultaneously
+		 * and the LE scan already finished, then change the discovery
+		 * state to indicate completion.
+		 */
+		if (!hci_dev_test_flag(hdev, HCI_LE_SCAN) ||
+		    !test_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks))
+			hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
 	}
 
 unlock:
@@ -1995,7 +2186,7 @@ static void hci_inquiry_result_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	if (!num_rsp)
 		return;
 
-	if (test_bit(HCI_PERIODIC_INQ, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_PERIODIC_INQ))
 		return;
 
 	hci_dev_lock(hdev);
@@ -2009,13 +2200,14 @@ static void hci_inquiry_result_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		data.pscan_mode		= info->pscan_mode;
 		memcpy(data.dev_class, info->dev_class, 3);
 		data.clock_offset	= info->clock_offset;
-		data.rssi		= 0x00;
+		data.rssi		= HCI_RSSI_INVALID;
 		data.ssp_mode		= 0x00;
 
 		flags = hci_inquiry_cache_update(hdev, &data, false);
 
 		mgmt_device_found(hdev, &info->bdaddr, ACL_LINK, 0x00,
-				  info->dev_class, 0, flags, NULL, 0, NULL, 0);
+				  info->dev_class, HCI_RSSI_INVALID,
+				  flags, NULL, 0, NULL, 0);
 	}
 
 	hci_dev_unlock(hdev);
@@ -2057,6 +2249,7 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		} else
 			conn->state = BT_CONNECTED;
 
+		hci_debugfs_create_conn(conn);
 		hci_conn_add_sysfs(conn);
 
 		if (test_bit(HCI_AUTH, &hdev->flags))
@@ -2072,7 +2265,7 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 			hci_send_cmd(hdev, HCI_OP_READ_REMOTE_FEATURES,
 				     sizeof(cp), &cp);
 
-			hci_update_page_scan(hdev, NULL);
+			hci_update_page_scan(hdev);
 		}
 
 		/* Set packet type for incoming connection */
@@ -2094,10 +2287,10 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_sco_setup(conn, ev->status);
 
 	if (ev->status) {
-		hci_proto_connect_cfm(conn, ev->status);
+		hci_connect_cfm(conn, ev->status);
 		hci_conn_del(conn);
 	} else if (ev->link_type != ACL_LINK)
-		hci_proto_connect_cfm(conn, ev->status);
+		hci_connect_cfm(conn, ev->status);
 
 unlock:
 	hci_dev_unlock(hdev);
@@ -2139,7 +2332,12 @@ static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		return;
 	}
 
-	if (!test_bit(HCI_CONNECTABLE, &hdev->dev_flags) &&
+	/* Require HCI_CONNECTABLE or a whitelist entry to accept the
+	 * connection. These features are only touched through mgmt so
+	 * only do the checks if HCI_MGMT is set.
+	 */
+	if (hci_dev_test_flag(hdev, HCI_MGMT) &&
+	    !hci_dev_test_flag(hdev, HCI_CONNECTABLE) &&
 	    !hci_bdaddr_list_lookup(&hdev->whitelist, &ev->bdaddr,
 				    BDADDR_BREDR)) {
 		    hci_reject_conn(hdev, &ev->bdaddr);
@@ -2200,7 +2398,7 @@ static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 			     &cp);
 	} else {
 		conn->state = BT_CONNECT2;
-		hci_proto_connect_cfm(conn, 0);
+		hci_connect_cfm(conn, 0);
 	}
 }
 
@@ -2253,7 +2451,7 @@ static void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		if (test_bit(HCI_CONN_FLUSH_KEY, &conn->flags))
 			hci_remove_link_key(hdev, &conn->dst);
 
-		hci_update_page_scan(hdev, NULL);
+		hci_update_page_scan(hdev);
 	}
 
 	params = hci_conn_params_lookup(hdev, &conn->dst, conn->dst_type);
@@ -2278,7 +2476,7 @@ static void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 
 	type = conn->type;
 
-	hci_proto_disconn_cfm(conn, ev->reason);
+	hci_disconn_cfm(conn, ev->reason);
 	hci_conn_del(conn);
 
 	/* Re-enable advertising if necessary, since it might
@@ -2335,7 +2533,7 @@ static void hci_auth_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 				     &cp);
 		} else {
 			conn->state = BT_CONNECTED;
-			hci_proto_connect_cfm(conn, ev->status);
+			hci_connect_cfm(conn, ev->status);
 			hci_conn_drop(conn);
 		}
 	} else {
@@ -2376,7 +2574,7 @@ static void hci_remote_name_evt(struct hci_dev *hdev, struct sk_buff *skb)
 
 	conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr);
 
-	if (!test_bit(HCI_MGMT, &hdev->dev_flags))
+	if (!hci_dev_test_flag(hdev, HCI_MGMT))
 		goto check_auth;
 
 	if (ev->status == 0)
@@ -2442,7 +2640,7 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	 * whenever the encryption procedure fails.
 	 */
 	if (ev->status && conn->type == LE_LINK)
-		set_bit(HCI_RPA_EXPIRED, &hdev->dev_flags);
+		hci_dev_set_flag(hdev, HCI_RPA_EXPIRED);
 
 	clear_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags);
 
@@ -2460,15 +2658,15 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		 * connections that are not encrypted with AES-CCM
 		 * using a P-256 authenticated combination key.
 		 */
-		if (test_bit(HCI_SC_ONLY, &hdev->dev_flags) &&
+		if (hci_dev_test_flag(hdev, HCI_SC_ONLY) &&
 		    (!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_connect_cfm(conn, HCI_ERROR_AUTH_FAILURE);
 			hci_conn_drop(conn);
 			goto unlock;
 		}
 
-		hci_proto_connect_cfm(conn, ev->status);
+		hci_connect_cfm(conn, ev->status);
 		hci_conn_drop(conn);
 	} else
 		hci_encrypt_cfm(conn, ev->status, ev->encrypt);
@@ -2520,7 +2718,8 @@ static void hci_remote_features_evt(struct hci_dev *hdev,
 	if (conn->state != BT_CONFIG)
 		goto unlock;
 
-	if (!ev->status && lmp_ssp_capable(hdev) && lmp_ssp_capable(conn)) {
+	if (!ev->status && lmp_ext_feat_capable(hdev) &&
+	    lmp_ext_feat_capable(conn)) {
 		struct hci_cp_read_remote_ext_features cp;
 		cp.handle = ev->handle;
 		cp.page = 0x01;
@@ -2536,13 +2735,11 @@ static void hci_remote_features_evt(struct hci_dev *hdev,
 		cp.pscan_rep_mode = 0x02;
 		hci_send_cmd(hdev, HCI_OP_REMOTE_NAME_REQ, sizeof(cp), &cp);
 	} else if (!test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags))
-		mgmt_device_connected(hdev, &conn->dst, conn->type,
-				      conn->dst_type, 0, NULL, 0,
-				      conn->dev_class);
+		mgmt_device_connected(hdev, conn, 0, NULL, 0);
 
 	if (!hci_outgoing_auth_needed(hdev, conn)) {
 		conn->state = BT_CONNECTED;
-		hci_proto_connect_cfm(conn, ev->status);
+		hci_connect_cfm(conn, ev->status);
 		hci_conn_drop(conn);
 	}
 
@@ -2550,17 +2747,19 @@ unlock:
 	hci_dev_unlock(hdev);
 }
 
-static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
+static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb,
+				 u16 *opcode, u8 *status,
+				 hci_req_complete_t *req_complete,
+				 hci_req_complete_skb_t *req_complete_skb)
 {
 	struct hci_ev_cmd_complete *ev = (void *) skb->data;
-	u8 status = skb->data[sizeof(*ev)];
-	__u16 opcode;
 
-	skb_pull(skb, sizeof(*ev));
+	*opcode = __le16_to_cpu(ev->opcode);
+	*status = skb->data[sizeof(*ev)];
 
-	opcode = __le16_to_cpu(ev->opcode);
+	skb_pull(skb, sizeof(*ev));
 
-	switch (opcode) {
+	switch (*opcode) {
 	case HCI_OP_INQUIRY_CANCEL:
 		hci_cc_inquiry_cancel(hdev, skb);
 		break;
@@ -2601,6 +2800,14 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_cc_reset(hdev, skb);
 		break;
 
+	case HCI_OP_READ_STORED_LINK_KEY:
+		hci_cc_read_stored_link_key(hdev, skb);
+		break;
+
+	case HCI_OP_DELETE_STORED_LINK_KEY:
+		hci_cc_delete_stored_link_key(hdev, skb);
+		break;
+
 	case HCI_OP_WRITE_LOCAL_NAME:
 		hci_cc_write_local_name(hdev, skb);
 		break;
@@ -2793,6 +3000,18 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_cc_le_read_supported_states(hdev, skb);
 		break;
 
+	case HCI_OP_LE_READ_DEF_DATA_LEN:
+		hci_cc_le_read_def_data_len(hdev, skb);
+		break;
+
+	case HCI_OP_LE_WRITE_DEF_DATA_LEN:
+		hci_cc_le_write_def_data_len(hdev, skb);
+		break;
+
+	case HCI_OP_LE_READ_MAX_DATA_LEN:
+		hci_cc_le_read_max_data_len(hdev, skb);
+		break;
+
 	case HCI_OP_WRITE_LE_HOST_SUPPORTED:
 		hci_cc_write_le_host_supported(hdev, skb);
 		break;
@@ -2813,33 +3032,41 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_cc_read_tx_power(hdev, skb);
 		break;
 
+	case HCI_OP_WRITE_SSP_DEBUG_MODE:
+		hci_cc_write_ssp_debug_mode(hdev, skb);
+		break;
+
 	default:
-		BT_DBG("%s opcode 0x%4.4x", hdev->name, opcode);
+		BT_DBG("%s opcode 0x%4.4x", hdev->name, *opcode);
 		break;
 	}
 
-	if (opcode != HCI_OP_NOP)
+	if (*opcode != HCI_OP_NOP)
 		cancel_delayed_work(&hdev->cmd_timer);
 
-	hci_req_cmd_complete(hdev, opcode, status);
-
-	if (ev->ncmd && !test_bit(HCI_RESET, &hdev->flags)) {
+	if (ev->ncmd && !test_bit(HCI_RESET, &hdev->flags))
 		atomic_set(&hdev->cmd_cnt, 1);
-		if (!skb_queue_empty(&hdev->cmd_q))
-			queue_work(hdev->workqueue, &hdev->cmd_work);
-	}
+
+	hci_req_cmd_complete(hdev, *opcode, *status, req_complete,
+			     req_complete_skb);
+
+	if (atomic_read(&hdev->cmd_cnt) && !skb_queue_empty(&hdev->cmd_q))
+		queue_work(hdev->workqueue, &hdev->cmd_work);
 }
 
-static void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb)
+static void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb,
+			       u16 *opcode, u8 *status,
+			       hci_req_complete_t *req_complete,
+			       hci_req_complete_skb_t *req_complete_skb)
 {
 	struct hci_ev_cmd_status *ev = (void *) skb->data;
-	__u16 opcode;
 
 	skb_pull(skb, sizeof(*ev));
 
-	opcode = __le16_to_cpu(ev->opcode);
+	*opcode = __le16_to_cpu(ev->opcode);
+	*status = ev->status;
 
-	switch (opcode) {
+	switch (*opcode) {
 	case HCI_OP_INQUIRY:
 		hci_cs_inquiry(hdev, ev->status);
 		break;
@@ -2848,6 +3075,10 @@ static void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_cs_create_conn(hdev, ev->status);
 		break;
 
+	case HCI_OP_DISCONNECT:
+		hci_cs_disconnect(hdev, ev->status);
+		break;
+
 	case HCI_OP_ADD_SCO:
 		hci_cs_add_sco(hdev, ev->status);
 		break;
@@ -2876,51 +3107,71 @@ static void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_cs_setup_sync_conn(hdev, ev->status);
 		break;
 
-	case HCI_OP_SNIFF_MODE:
-		hci_cs_sniff_mode(hdev, ev->status);
+	case HCI_OP_CREATE_PHY_LINK:
+		hci_cs_create_phylink(hdev, ev->status);
 		break;
 
-	case HCI_OP_EXIT_SNIFF_MODE:
-		hci_cs_exit_sniff_mode(hdev, ev->status);
+	case HCI_OP_ACCEPT_PHY_LINK:
+		hci_cs_accept_phylink(hdev, ev->status);
 		break;
 
-	case HCI_OP_DISCONNECT:
-		hci_cs_disconnect(hdev, ev->status);
+	case HCI_OP_SNIFF_MODE:
+		hci_cs_sniff_mode(hdev, ev->status);
 		break;
 
-	case HCI_OP_CREATE_PHY_LINK:
-		hci_cs_create_phylink(hdev, ev->status);
+	case HCI_OP_EXIT_SNIFF_MODE:
+		hci_cs_exit_sniff_mode(hdev, ev->status);
 		break;
 
-	case HCI_OP_ACCEPT_PHY_LINK:
-		hci_cs_accept_phylink(hdev, ev->status);
+	case HCI_OP_SWITCH_ROLE:
+		hci_cs_switch_role(hdev, ev->status);
 		break;
 
 	case HCI_OP_LE_CREATE_CONN:
 		hci_cs_le_create_conn(hdev, ev->status);
 		break;
 
+	case HCI_OP_LE_READ_REMOTE_FEATURES:
+		hci_cs_le_read_remote_features(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);
+		BT_DBG("%s opcode 0x%4.4x", hdev->name, *opcode);
 		break;
 	}
 
-	if (opcode != HCI_OP_NOP)
+	if (*opcode != HCI_OP_NOP)
 		cancel_delayed_work(&hdev->cmd_timer);
 
+	if (ev->ncmd && !test_bit(HCI_RESET, &hdev->flags))
+		atomic_set(&hdev->cmd_cnt, 1);
+
+	/* Indicate request completion if the command failed. Also, if
+	 * we're not waiting for a special event and we get a success
+	 * command status we should try to flag the request as completed
+	 * (since for this kind of commands there will not be a command
+	 * complete event).
+	 */
 	if (ev->status ||
 	    (hdev->sent_cmd && !bt_cb(hdev->sent_cmd)->req.event))
-		hci_req_cmd_complete(hdev, opcode, ev->status);
+		hci_req_cmd_complete(hdev, *opcode, ev->status, req_complete,
+				     req_complete_skb);
 
-	if (ev->ncmd && !test_bit(HCI_RESET, &hdev->flags)) {
-		atomic_set(&hdev->cmd_cnt, 1);
-		if (!skb_queue_empty(&hdev->cmd_q))
-			queue_work(hdev->workqueue, &hdev->cmd_work);
-	}
+	if (atomic_read(&hdev->cmd_cnt) && !skb_queue_empty(&hdev->cmd_q))
+		queue_work(hdev->workqueue, &hdev->cmd_work);
+}
+
+static void hci_hardware_error_evt(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_ev_hardware_error *ev = (void *) skb->data;
+
+	hdev->hw_error_code = ev->code;
+
+	queue_work(hdev->req_workqueue, &hdev->error_reset);
 }
 
 static void hci_role_change_evt(struct hci_dev *hdev, struct sk_buff *skb)
@@ -3129,11 +3380,11 @@ static void hci_pin_code_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_conn_drop(conn);
 	}
 
-	if (!test_bit(HCI_BONDABLE, &hdev->dev_flags) &&
+	if (!hci_dev_test_flag(hdev, HCI_BONDABLE) &&
 	    !test_bit(HCI_CONN_AUTH_INITIATOR, &conn->flags)) {
 		hci_send_cmd(hdev, HCI_OP_PIN_CODE_NEG_REPLY,
 			     sizeof(ev->bdaddr), &ev->bdaddr);
-	} else if (test_bit(HCI_MGMT, &hdev->dev_flags)) {
+	} else if (hci_dev_test_flag(hdev, HCI_MGMT)) {
 		u8 secure;
 
 		if (conn->pending_sec_level == BT_SECURITY_HIGH)
@@ -3148,6 +3399,38 @@ unlock:
 	hci_dev_unlock(hdev);
 }
 
+static void conn_set_key(struct hci_conn *conn, u8 key_type, u8 pin_len)
+{
+	if (key_type == HCI_LK_CHANGED_COMBINATION)
+		return;
+
+	conn->pin_length = pin_len;
+	conn->key_type = key_type;
+
+	switch (key_type) {
+	case HCI_LK_LOCAL_UNIT:
+	case HCI_LK_REMOTE_UNIT:
+	case HCI_LK_DEBUG_COMBINATION:
+		return;
+	case HCI_LK_COMBINATION:
+		if (pin_len == 16)
+			conn->pending_sec_level = BT_SECURITY_HIGH;
+		else
+			conn->pending_sec_level = BT_SECURITY_MEDIUM;
+		break;
+	case HCI_LK_UNAUTH_COMBINATION_P192:
+	case HCI_LK_UNAUTH_COMBINATION_P256:
+		conn->pending_sec_level = BT_SECURITY_MEDIUM;
+		break;
+	case HCI_LK_AUTH_COMBINATION_P192:
+		conn->pending_sec_level = BT_SECURITY_HIGH;
+		break;
+	case HCI_LK_AUTH_COMBINATION_P256:
+		conn->pending_sec_level = BT_SECURITY_FIPS;
+		break;
+	}
+}
+
 static void hci_link_key_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct hci_ev_link_key_req *ev = (void *) skb->data;
@@ -3157,7 +3440,7 @@ static void hci_link_key_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 
 	BT_DBG("%s", hdev->name);
 
-	if (!test_bit(HCI_MGMT, &hdev->dev_flags))
+	if (!hci_dev_test_flag(hdev, HCI_MGMT))
 		return;
 
 	hci_dev_lock(hdev);
@@ -3174,6 +3457,8 @@ 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) {
+		clear_bit(HCI_CONN_NEW_LINK_KEY, &conn->flags);
+
 		if ((key->type == HCI_LK_UNAUTH_COMBINATION_P192 ||
 		     key->type == HCI_LK_UNAUTH_COMBINATION_P256) &&
 		    conn->auth_type != 0xff && (conn->auth_type & 0x01)) {
@@ -3189,8 +3474,7 @@ static void hci_link_key_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 			goto not_found;
 		}
 
-		conn->key_type = key->type;
-		conn->pin_length = key->pin_len;
+		conn_set_key(conn, key->type, key->pin_len);
 	}
 
 	bacpy(&cp.bdaddr, &ev->bdaddr);
@@ -3220,18 +3504,17 @@ static void hci_link_key_notify_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	hci_dev_lock(hdev);
 
 	conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr);
-	if (conn) {
-		hci_conn_hold(conn);
-		conn->disc_timeout = HCI_DISCONN_TIMEOUT;
-		pin_len = conn->pin_length;
+	if (!conn)
+		goto unlock;
 
-		if (ev->key_type != HCI_LK_CHANGED_COMBINATION)
-			conn->key_type = ev->key_type;
+	hci_conn_hold(conn);
+	conn->disc_timeout = HCI_DISCONN_TIMEOUT;
+	hci_conn_drop(conn);
 
-		hci_conn_drop(conn);
-	}
+	set_bit(HCI_CONN_NEW_LINK_KEY, &conn->flags);
+	conn_set_key(conn, ev->key_type, conn->pin_length);
 
-	if (!test_bit(HCI_MGMT, &hdev->dev_flags))
+	if (!hci_dev_test_flag(hdev, HCI_MGMT))
 		goto unlock;
 
 	key = hci_add_link_key(hdev, conn, &ev->bdaddr, ev->link_key,
@@ -3239,6 +3522,12 @@ static void hci_link_key_notify_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	if (!key)
 		goto unlock;
 
+	/* Update connection information since adding the key will have
+	 * fixed up the type in the case of changed combination keys.
+	 */
+	if (ev->key_type == HCI_LK_CHANGED_COMBINATION)
+		conn_set_key(conn, key->type, key->pin_len);
+
 	mgmt_new_link_key(hdev, key, persistent);
 
 	/* Keep debug keys around only if the HCI_KEEP_DEBUG_KEYS flag
@@ -3247,16 +3536,17 @@ static void hci_link_key_notify_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	 * store_hint being 0).
 	 */
 	if (key->type == HCI_LK_DEBUG_COMBINATION &&
-	    !test_bit(HCI_KEEP_DEBUG_KEYS, &hdev->dev_flags)) {
-		list_del(&key->list);
-		kfree(key);
-	} else if (conn) {
-		if (persistent)
-			clear_bit(HCI_CONN_FLUSH_KEY, &conn->flags);
-		else
-			set_bit(HCI_CONN_FLUSH_KEY, &conn->flags);
+	    !hci_dev_test_flag(hdev, HCI_KEEP_DEBUG_KEYS)) {
+		list_del_rcu(&key->list);
+		kfree_rcu(key, rcu);
+		goto unlock;
 	}
 
+	if (persistent)
+		clear_bit(HCI_CONN_FLUSH_KEY, &conn->flags);
+	else
+		set_bit(HCI_CONN_FLUSH_KEY, &conn->flags);
+
 unlock:
 	hci_dev_unlock(hdev);
 }
@@ -3329,7 +3619,7 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev,
 	if (!num_rsp)
 		return;
 
-	if (test_bit(HCI_PERIODIC_INQ, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_PERIODIC_INQ))
 		return;
 
 	hci_dev_lock(hdev);
@@ -3434,13 +3724,11 @@ static void hci_remote_ext_features_evt(struct hci_dev *hdev,
 		cp.pscan_rep_mode = 0x02;
 		hci_send_cmd(hdev, HCI_OP_REMOTE_NAME_REQ, sizeof(cp), &cp);
 	} else if (!test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags))
-		mgmt_device_connected(hdev, &conn->dst, conn->type,
-				      conn->dst_type, 0, NULL, 0,
-				      conn->dev_class);
+		mgmt_device_connected(hdev, conn, 0, NULL, 0);
 
 	if (!hci_outgoing_auth_needed(hdev, conn)) {
 		conn->state = BT_CONNECTED;
-		hci_proto_connect_cfm(conn, ev->status);
+		hci_connect_cfm(conn, ev->status);
 		hci_conn_drop(conn);
 	}
 
@@ -3475,6 +3763,7 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev,
 		conn->handle = __le16_to_cpu(ev->handle);
 		conn->state  = BT_CONNECTED;
 
+		hci_debugfs_create_conn(conn);
 		hci_conn_add_sysfs(conn);
 		break;
 
@@ -3498,7 +3787,7 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev,
 		break;
 	}
 
-	hci_proto_connect_cfm(conn, ev->status);
+	hci_connect_cfm(conn, ev->status);
 	if (ev->status)
 		hci_conn_del(conn);
 
@@ -3536,7 +3825,7 @@ static void hci_extended_inquiry_result_evt(struct hci_dev *hdev,
 	if (!num_rsp)
 		return;
 
-	if (test_bit(HCI_PERIODIC_INQ, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_PERIODIC_INQ))
 		return;
 
 	hci_dev_lock(hdev);
@@ -3554,7 +3843,7 @@ static void hci_extended_inquiry_result_evt(struct hci_dev *hdev,
 		data.rssi		= info->rssi;
 		data.ssp_mode		= 0x01;
 
-		if (test_bit(HCI_MGMT, &hdev->dev_flags))
+		if (hci_dev_test_flag(hdev, HCI_MGMT))
 			name_known = eir_has_data_type(info->data,
 						       sizeof(info->data),
 						       EIR_NAME_COMPLETE);
@@ -3609,7 +3898,7 @@ static void hci_key_refresh_complete_evt(struct hci_dev *hdev,
 		if (!ev->status)
 			conn->state = BT_CONNECTED;
 
-		hci_proto_connect_cfm(conn, ev->status);
+		hci_connect_cfm(conn, ev->status);
 		hci_conn_drop(conn);
 	} else {
 		hci_auth_cfm(conn, ev->status);
@@ -3641,6 +3930,48 @@ static u8 hci_get_auth_req(struct hci_conn *conn)
 	return (conn->remote_auth & ~0x01) | (conn->auth_type & 0x01);
 }
 
+static u8 bredr_oob_data_present(struct hci_conn *conn)
+{
+	struct hci_dev *hdev = conn->hdev;
+	struct oob_data *data;
+
+	data = hci_find_remote_oob_data(hdev, &conn->dst, BDADDR_BREDR);
+	if (!data)
+		return 0x00;
+
+	if (bredr_sc_enabled(hdev)) {
+		/* When Secure Connections is enabled, then just
+		 * return the present value stored with the OOB
+		 * data. The stored value contains the right present
+		 * information. However it can only be trusted when
+		 * not in Secure Connection Only mode.
+		 */
+		if (!hci_dev_test_flag(hdev, HCI_SC_ONLY))
+			return data->present;
+
+		/* When Secure Connections Only mode is enabled, then
+		 * the P-256 values are required. If they are not
+		 * available, then do not declare that OOB data is
+		 * present.
+		 */
+		if (!memcmp(data->rand256, ZERO_KEY, 16) ||
+		    !memcmp(data->hash256, ZERO_KEY, 16))
+			return 0x00;
+
+		return 0x02;
+	}
+
+	/* When Secure Connections is not enabled or actually
+	 * not supported by the hardware, then check that if
+	 * P-192 data values are present.
+	 */
+	if (!memcmp(data->rand192, ZERO_KEY, 16) ||
+	    !memcmp(data->hash192, ZERO_KEY, 16))
+		return 0x00;
+
+	return 0x01;
+}
+
 static void hci_io_capa_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct hci_ev_io_capa_request *ev = (void *) skb->data;
@@ -3656,13 +3987,13 @@ static void hci_io_capa_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 
 	hci_conn_hold(conn);
 
-	if (!test_bit(HCI_MGMT, &hdev->dev_flags))
+	if (!hci_dev_test_flag(hdev, HCI_MGMT))
 		goto unlock;
 
 	/* Allow pairing if we're pairable, the initiators of the
 	 * pairing or if the remote is not requesting bonding.
 	 */
-	if (test_bit(HCI_BONDABLE, &hdev->dev_flags) ||
+	if (hci_dev_test_flag(hdev, HCI_BONDABLE) ||
 	    test_bit(HCI_CONN_AUTH_INITIATOR, &conn->flags) ||
 	    (conn->remote_auth & ~0x01) == HCI_AT_NO_BONDING) {
 		struct hci_cp_io_capability_reply cp;
@@ -3688,16 +4019,11 @@ static void hci_io_capa_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		/* If we're not bondable, force one of the non-bondable
 		 * authentication requirement values.
 		 */
-		if (!test_bit(HCI_BONDABLE, &hdev->dev_flags))
+		if (!hci_dev_test_flag(hdev, HCI_BONDABLE))
 			conn->auth_type &= HCI_AT_NO_BONDING_MITM;
 
 		cp.authentication = conn->auth_type;
-
-		if (hci_find_remote_oob_data(hdev, &conn->dst) &&
-		    (conn->out || test_bit(HCI_CONN_REMOTE_OOB, &conn->flags)))
-			cp.oob_data = 0x01;
-		else
-			cp.oob_data = 0x00;
+		cp.oob_data = bredr_oob_data_present(conn);
 
 		hci_send_cmd(hdev, HCI_OP_IO_CAPABILITY_REPLY,
 			     sizeof(cp), &cp);
@@ -3730,8 +4056,6 @@ static void hci_io_capa_reply_evt(struct hci_dev *hdev, struct sk_buff *skb)
 
 	conn->remote_cap = ev->capability;
 	conn->remote_auth = ev->authentication;
-	if (ev->oob_data)
-		set_bit(HCI_CONN_REMOTE_OOB, &conn->flags);
 
 unlock:
 	hci_dev_unlock(hdev);
@@ -3748,7 +4072,7 @@ static void hci_user_confirm_request_evt(struct hci_dev *hdev,
 
 	hci_dev_lock(hdev);
 
-	if (!test_bit(HCI_MGMT, &hdev->dev_flags))
+	if (!hci_dev_test_flag(hdev, HCI_MGMT))
 		goto unlock;
 
 	conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr);
@@ -3819,7 +4143,7 @@ static void hci_user_passkey_request_evt(struct hci_dev *hdev,
 
 	BT_DBG("%s", hdev->name);
 
-	if (test_bit(HCI_MGMT, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_MGMT))
 		mgmt_user_passkey_request(hdev, &ev->bdaddr, ACL_LINK, 0);
 }
 
@@ -3838,7 +4162,7 @@ static void hci_user_passkey_notify_evt(struct hci_dev *hdev,
 	conn->passkey_notify = __le32_to_cpu(ev->passkey);
 	conn->passkey_entered = 0;
 
-	if (test_bit(HCI_MGMT, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_MGMT))
 		mgmt_user_passkey_notify(hdev, &conn->dst, conn->type,
 					 conn->dst_type, conn->passkey_notify,
 					 conn->passkey_entered);
@@ -3876,7 +4200,7 @@ static void hci_keypress_notify_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		return;
 	}
 
-	if (test_bit(HCI_MGMT, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_MGMT))
 		mgmt_user_passkey_notify(hdev, &conn->dst, conn->type,
 					 conn->dst_type, conn->passkey_notify,
 					 conn->passkey_entered);
@@ -3945,40 +4269,43 @@ static void hci_remote_oob_data_request_evt(struct hci_dev *hdev,
 
 	hci_dev_lock(hdev);
 
-	if (!test_bit(HCI_MGMT, &hdev->dev_flags))
+	if (!hci_dev_test_flag(hdev, HCI_MGMT))
 		goto unlock;
 
-	data = hci_find_remote_oob_data(hdev, &ev->bdaddr);
-	if (data) {
-		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.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));
+	data = hci_find_remote_oob_data(hdev, &ev->bdaddr, BDADDR_BREDR);
+	if (!data) {
+		struct hci_cp_remote_oob_data_neg_reply cp;
 
-			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);
+		hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_DATA_NEG_REPLY,
+			     sizeof(cp), &cp);
+		goto unlock;
+	}
 
-			bacpy(&cp.bdaddr, &ev->bdaddr);
-			memcpy(cp.hash, data->hash192, sizeof(cp.hash));
-			memcpy(cp.randomizer, data->randomizer192,
-			       sizeof(cp.randomizer));
+	if (bredr_sc_enabled(hdev)) {
+		struct hci_cp_remote_oob_ext_data_reply cp;
 
-			hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_DATA_REPLY,
-				     sizeof(cp), &cp);
+		bacpy(&cp.bdaddr, &ev->bdaddr);
+		if (hci_dev_test_flag(hdev, HCI_SC_ONLY)) {
+			memset(cp.hash192, 0, sizeof(cp.hash192));
+			memset(cp.rand192, 0, sizeof(cp.rand192));
+		} else {
+			memcpy(cp.hash192, data->hash192, sizeof(cp.hash192));
+			memcpy(cp.rand192, data->rand192, sizeof(cp.rand192));
 		}
+		memcpy(cp.hash256, data->hash256, sizeof(cp.hash256));
+		memcpy(cp.rand256, data->rand256, sizeof(cp.rand256));
+
+		hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_EXT_DATA_REPLY,
+			     sizeof(cp), &cp);
 	} else {
-		struct hci_cp_remote_oob_data_neg_reply cp;
+		struct hci_cp_remote_oob_data_reply cp;
 
 		bacpy(&cp.bdaddr, &ev->bdaddr);
-		hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_DATA_NEG_REPLY,
+		memcpy(cp.hash, data->hash192, sizeof(cp.hash));
+		memcpy(cp.rand, data->rand192, sizeof(cp.rand));
+
+		hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_DATA_REPLY,
 			     sizeof(cp), &cp);
 	}
 
@@ -4018,6 +4345,7 @@ static void hci_phy_link_complete_evt(struct hci_dev *hdev,
 	hcon->disc_timeout = HCI_DISCONN_TIMEOUT;
 	hci_conn_drop(hcon);
 
+	hci_debugfs_create_conn(hcon);
 	hci_conn_add_sysfs(hcon);
 
 	amp_physical_cfm(bredr_hcon, hcon);
@@ -4124,7 +4452,7 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	/* All controllers implicitly stop advertising in the event of a
 	 * connection, so ensure that the state bit is cleared.
 	 */
-	clear_bit(HCI_LE_ADV, &hdev->dev_flags);
+	hci_dev_clear_flag(hdev, HCI_LE_ADV);
 
 	conn = hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT);
 	if (!conn) {
@@ -4147,7 +4475,7 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		if (conn->out) {
 			conn->resp_addr_type = ev->bdaddr_type;
 			bacpy(&conn->resp_addr, &ev->bdaddr);
-			if (test_bit(HCI_PRIVACY, &hdev->dev_flags)) {
+			if (hci_dev_test_flag(hdev, HCI_PRIVACY)) {
 				conn->init_addr_type = ADDR_LE_DEV_RANDOM;
 				bacpy(&conn->init_addr, &hdev->rpa);
 			} else {
@@ -4214,20 +4542,46 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	}
 
 	if (!test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags))
-		mgmt_device_connected(hdev, &conn->dst, conn->type,
-				      conn->dst_type, 0, NULL, 0, NULL);
+		mgmt_device_connected(hdev, conn, 0, NULL, 0);
 
 	conn->sec_level = BT_SECURITY_LOW;
 	conn->handle = __le16_to_cpu(ev->handle);
-	conn->state = BT_CONNECTED;
+	conn->state = BT_CONFIG;
 
 	conn->le_conn_interval = le16_to_cpu(ev->interval);
 	conn->le_conn_latency = le16_to_cpu(ev->latency);
 	conn->le_supv_timeout = le16_to_cpu(ev->supervision_timeout);
 
+	hci_debugfs_create_conn(conn);
 	hci_conn_add_sysfs(conn);
 
-	hci_proto_connect_cfm(conn, ev->status);
+	if (!ev->status) {
+		/* The remote features procedure is defined for master
+		 * role only. So only in case of an initiated connection
+		 * request the remote features.
+		 *
+		 * If the local controller supports slave-initiated features
+		 * exchange, then requesting the remote features in slave
+		 * role is possible. Otherwise just transition into the
+		 * connected state without requesting the remote features.
+		 */
+		if (conn->out ||
+		    (hdev->le_features[0] & HCI_LE_SLAVE_FEATURES)) {
+			struct hci_cp_le_read_remote_features cp;
+
+			cp.handle = __cpu_to_le16(conn->handle);
+
+			hci_send_cmd(hdev, HCI_OP_LE_READ_REMOTE_FEATURES,
+				     sizeof(cp), &cp);
+
+			hci_conn_hold(conn);
+		} else {
+			conn->state = BT_CONNECTED;
+			hci_connect_cfm(conn, ev->status);
+		}
+	} else {
+		hci_connect_cfm(conn, ev->status);
+	}
 
 	params = hci_pend_le_action_lookup(&hdev->pend_le_conns, &conn->dst,
 					   conn->dst_type);
@@ -4269,25 +4623,26 @@ static void hci_le_conn_update_complete_evt(struct hci_dev *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, u8 adv_type)
+static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev,
+					      bdaddr_t *addr,
+					      u8 addr_type, u8 adv_type)
 {
 	struct hci_conn *conn;
 	struct hci_conn_params *params;
 
 	/* If the event is not connectable don't proceed further */
 	if (adv_type != LE_ADV_IND && adv_type != LE_ADV_DIRECT_IND)
-		return;
+		return NULL;
 
 	/* Ignore if the device is blocked */
 	if (hci_bdaddr_list_lookup(&hdev->blacklist, addr, addr_type))
-		return;
+		return NULL;
 
 	/* Most controller will fail if we try to create new connections
 	 * while we have an existing one in slave role.
 	 */
 	if (hdev->conn_hash.le_num_slave > 0)
-		return;
+		return NULL;
 
 	/* If we're not connectable only connect devices that we have in
 	 * our pend_le_conns list.
@@ -4295,7 +4650,7 @@ static void check_pending_le_conn(struct hci_dev *hdev, bdaddr_t *addr,
 	params = hci_pend_le_action_lookup(&hdev->pend_le_conns,
 					   addr, addr_type);
 	if (!params)
-		return;
+		return NULL;
 
 	switch (params->auto_connect) {
 	case HCI_AUTO_CONN_DIRECT:
@@ -4304,7 +4659,7 @@ static void check_pending_le_conn(struct hci_dev *hdev, bdaddr_t *addr,
 		 * incoming connections from slave devices.
 		 */
 		if (adv_type != LE_ADV_DIRECT_IND)
-			return;
+			return NULL;
 		break;
 	case HCI_AUTO_CONN_ALWAYS:
 		/* Devices advertising with ADV_IND or ADV_DIRECT_IND
@@ -4315,7 +4670,7 @@ static void check_pending_le_conn(struct hci_dev *hdev, bdaddr_t *addr,
 		 */
 		break;
 	default:
-		return;
+		return NULL;
 	}
 
 	conn = hci_connect_le(hdev, addr, addr_type, BT_SECURITY_LOW,
@@ -4328,7 +4683,7 @@ static void check_pending_le_conn(struct hci_dev *hdev, bdaddr_t *addr,
 		 * count consistent once the connection is established.
 		 */
 		params->conn = hci_conn_get(conn);
-		return;
+		return conn;
 	}
 
 	switch (PTR_ERR(conn)) {
@@ -4341,17 +4696,48 @@ static void check_pending_le_conn(struct hci_dev *hdev, bdaddr_t *addr,
 		break;
 	default:
 		BT_DBG("Failed to connect: err %ld", PTR_ERR(conn));
+		return NULL;
 	}
+
+	return NULL;
 }
 
 static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr,
-			       u8 bdaddr_type, s8 rssi, u8 *data, u8 len)
+			       u8 bdaddr_type, bdaddr_t *direct_addr,
+			       u8 direct_addr_type, s8 rssi, u8 *data, u8 len)
 {
 	struct discovery_state *d = &hdev->discovery;
 	struct smp_irk *irk;
+	struct hci_conn *conn;
 	bool match;
 	u32 flags;
 
+	/* If the direct address is present, then this report is from
+	 * a LE Direct Advertising Report event. In that case it is
+	 * important to see if the address is matching the local
+	 * controller address.
+	 */
+	if (direct_addr) {
+		/* Only resolvable random addresses are valid for these
+		 * kind of reports and others can be ignored.
+		 */
+		if (!hci_bdaddr_is_rpa(direct_addr, direct_addr_type))
+			return;
+
+		/* If the controller is not using resolvable random
+		 * addresses, then this report can be ignored.
+		 */
+		if (!hci_dev_test_flag(hdev, HCI_PRIVACY))
+			return;
+
+		/* If the local IRK of the controller does not match
+		 * with the resolvable random address provided, then
+		 * this report can be ignored.
+		 */
+		if (!smp_irk_matches(hdev, hdev->irk, direct_addr))
+			return;
+	}
+
 	/* Check if we need to convert to identity address */
 	irk = hci_get_irk(hdev, bdaddr, bdaddr_type);
 	if (irk) {
@@ -4360,7 +4746,14 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr,
 	}
 
 	/* Check if we have been requested to connect to this device */
-	check_pending_le_conn(hdev, bdaddr, bdaddr_type, type);
+	conn = check_pending_le_conn(hdev, bdaddr, bdaddr_type, type);
+	if (conn && type == LE_ADV_IND) {
+		/* Store report for later inclusion by
+		 * mgmt_device_connected
+		 */
+		memcpy(conn->le_adv_data, data, len);
+		conn->le_adv_data_len = len;
+	}
 
 	/* Passive scanning shouldn't trigger any device found events,
 	 * except for devices marked as CONN_REPORT for which we do send
@@ -4481,7 +4874,8 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb)
 
 		rssi = ev->data[ev->length];
 		process_adv_report(hdev, ev->evt_type, &ev->bdaddr,
-				   ev->bdaddr_type, rssi, ev->data, ev->length);
+				   ev->bdaddr_type, NULL, 0, rssi,
+				   ev->data, ev->length);
 
 		ptr += sizeof(*ev) + ev->length + 1;
 	}
@@ -4489,6 +4883,48 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	hci_dev_unlock(hdev);
 }
 
+static void hci_le_remote_feat_complete_evt(struct hci_dev *hdev,
+					    struct sk_buff *skb)
+{
+	struct hci_ev_le_remote_feat_complete *ev = (void *)skb->data;
+	struct hci_conn *conn;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, ev->status);
+
+	hci_dev_lock(hdev);
+
+	conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle));
+	if (conn) {
+		if (!ev->status)
+			memcpy(conn->features[0], ev->features, 8);
+
+		if (conn->state == BT_CONFIG) {
+			__u8 status;
+
+			/* If the local controller supports slave-initiated
+			 * features exchange, but the remote controller does
+			 * not, then it is possible that the error code 0x1a
+			 * for unsupported remote feature gets returned.
+			 *
+			 * In this specific case, allow the connection to
+			 * transition into connected state and mark it as
+			 * successful.
+			 */
+			if ((hdev->le_features[0] & HCI_LE_SLAVE_FEATURES) &&
+			    !conn->out && ev->status == 0x1a)
+				status = 0x00;
+			else
+				status = ev->status;
+
+			conn->state = BT_CONNECTED;
+			hci_connect_cfm(conn, status);
+			hci_conn_drop(conn);
+		}
+	}
+
+	hci_dev_unlock(hdev);
+}
+
 static void hci_le_ltk_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct hci_ev_le_ltk_req *ev = (void *) skb->data;
@@ -4505,10 +4941,20 @@ 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->rand, conn->role);
-	if (ltk == NULL)
+	ltk = hci_find_ltk(hdev, &conn->dst, conn->dst_type, conn->role);
+	if (!ltk)
 		goto not_found;
 
+	if (smp_ltk_is_sc(ltk)) {
+		/* With SC both EDiv and Rand are set to zero */
+		if (ev->ediv || ev->rand)
+			goto not_found;
+	} else {
+		/* For non-SC keys check that EDiv and Rand match */
+		if (ev->ediv != ltk->ediv || ev->rand != ltk->rand)
+			goto not_found;
+	}
+
 	memcpy(cp.ltk, ltk->val, sizeof(ltk->val));
 	cp.handle = cpu_to_le16(conn->handle);
 
@@ -4526,8 +4972,8 @@ static void hci_le_ltk_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	 */
 	if (ltk->type == SMP_STK) {
 		set_bit(HCI_CONN_STK_ENCRYPT, &conn->flags);
-		list_del(&ltk->list);
-		kfree(ltk);
+		list_del_rcu(&ltk->list);
+		kfree_rcu(ltk, rcu);
 	} else {
 		clear_bit(HCI_CONN_STK_ENCRYPT, &conn->flags);
 	}
@@ -4612,6 +5058,27 @@ static void hci_le_remote_conn_param_req_evt(struct hci_dev *hdev,
 	hci_send_cmd(hdev, HCI_OP_LE_CONN_PARAM_REQ_REPLY, sizeof(cp), &cp);
 }
 
+static void hci_le_direct_adv_report_evt(struct hci_dev *hdev,
+					 struct sk_buff *skb)
+{
+	u8 num_reports = skb->data[0];
+	void *ptr = &skb->data[1];
+
+	hci_dev_lock(hdev);
+
+	while (num_reports--) {
+		struct hci_ev_le_direct_adv_info *ev = ptr;
+
+		process_adv_report(hdev, ev->evt_type, &ev->bdaddr,
+				   ev->bdaddr_type, &ev->direct_addr,
+				   ev->direct_addr_type, ev->rssi, NULL, 0);
+
+		ptr += sizeof(*ev);
+	}
+
+	hci_dev_unlock(hdev);
+}
+
 static void hci_le_meta_evt(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct hci_ev_le_meta *le_ev = (void *) skb->data;
@@ -4631,6 +5098,10 @@ static void hci_le_meta_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_le_adv_report_evt(hdev, skb);
 		break;
 
+	case HCI_EV_LE_REMOTE_FEAT_COMPLETE:
+		hci_le_remote_feat_complete_evt(hdev, skb);
+		break;
+
 	case HCI_EV_LE_LTK_REQ:
 		hci_le_ltk_request_evt(hdev, skb);
 		break;
@@ -4639,6 +5110,10 @@ static void hci_le_meta_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_le_remote_conn_param_req_evt(hdev, skb);
 		break;
 
+	case HCI_EV_LE_DIRECT_ADV_REPORT:
+		hci_le_direct_adv_report_evt(hdev, skb);
+		break;
+
 	default:
 		break;
 	}
@@ -4660,32 +5135,79 @@ static void hci_chan_selected_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	amp_read_loc_assoc_final_data(hdev, hcon);
 }
 
-void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb)
+static bool hci_get_cmd_complete(struct hci_dev *hdev, u16 opcode,
+				 u8 event, struct sk_buff *skb)
 {
-	struct hci_event_hdr *hdr = (void *) skb->data;
-	__u8 event = hdr->evt;
+	struct hci_ev_cmd_complete *ev;
+	struct hci_event_hdr *hdr;
 
-	hci_dev_lock(hdev);
+	if (!skb)
+		return false;
 
-	/* Received events are (currently) only needed when a request is
-	 * ongoing so avoid unnecessary memory allocation.
-	 */
-	if (hci_req_pending(hdev)) {
-		kfree_skb(hdev->recv_evt);
-		hdev->recv_evt = skb_clone(skb, GFP_KERNEL);
+	if (skb->len < sizeof(*hdr)) {
+		BT_ERR("Too short HCI event");
+		return false;
 	}
 
-	hci_dev_unlock(hdev);
-
+	hdr = (void *) skb->data;
 	skb_pull(skb, HCI_EVENT_HDR_SIZE);
 
+	if (event) {
+		if (hdr->evt != event)
+			return false;
+		return true;
+	}
+
+	if (hdr->evt != HCI_EV_CMD_COMPLETE) {
+		BT_DBG("Last event is not cmd complete (0x%2.2x)", hdr->evt);
+		return false;
+	}
+
+	if (skb->len < sizeof(*ev)) {
+		BT_ERR("Too short cmd_complete event");
+		return false;
+	}
+
+	ev = (void *) skb->data;
+	skb_pull(skb, sizeof(*ev));
+
+	if (opcode != __le16_to_cpu(ev->opcode)) {
+		BT_DBG("opcode doesn't match (0x%2.2x != 0x%2.2x)", opcode,
+		       __le16_to_cpu(ev->opcode));
+		return false;
+	}
+
+	return true;
+}
+
+void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_event_hdr *hdr = (void *) skb->data;
+	hci_req_complete_t req_complete = NULL;
+	hci_req_complete_skb_t req_complete_skb = NULL;
+	struct sk_buff *orig_skb = NULL;
+	u8 status = 0, event = hdr->evt, req_evt = 0;
+	u16 opcode = HCI_OP_NOP;
+
 	if (hdev->sent_cmd && bt_cb(hdev->sent_cmd)->req.event == event) {
 		struct hci_command_hdr *cmd_hdr = (void *) hdev->sent_cmd->data;
-		u16 opcode = __le16_to_cpu(cmd_hdr->opcode);
-
-		hci_req_cmd_complete(hdev, opcode, 0);
+		opcode = __le16_to_cpu(cmd_hdr->opcode);
+		hci_req_cmd_complete(hdev, opcode, status, &req_complete,
+				     &req_complete_skb);
+		req_evt = event;
 	}
 
+	/* If it looks like we might end up having to call
+	 * req_complete_skb, store a pristine copy of the skb since the
+	 * various handlers may modify the original one through
+	 * skb_pull() calls, etc.
+	 */
+	if (req_complete_skb || event == HCI_EV_CMD_STATUS ||
+	    event == HCI_EV_CMD_COMPLETE)
+		orig_skb = skb_clone(skb, GFP_KERNEL);
+
+	skb_pull(skb, HCI_EVENT_HDR_SIZE);
+
 	switch (event) {
 	case HCI_EV_INQUIRY_COMPLETE:
 		hci_inquiry_complete_evt(hdev, skb);
@@ -4728,11 +5250,17 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb)
 		break;
 
 	case HCI_EV_CMD_COMPLETE:
-		hci_cmd_complete_evt(hdev, skb);
+		hci_cmd_complete_evt(hdev, skb, &opcode, &status,
+				     &req_complete, &req_complete_skb);
 		break;
 
 	case HCI_EV_CMD_STATUS:
-		hci_cmd_status_evt(hdev, skb);
+		hci_cmd_status_evt(hdev, skb, &opcode, &status, &req_complete,
+				   &req_complete_skb);
+		break;
+
+	case HCI_EV_HARDWARE_ERROR:
+		hci_hardware_error_evt(hdev, skb);
 		break;
 
 	case HCI_EV_ROLE_CHANGE:
@@ -4860,6 +5388,17 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb)
 		break;
 	}
 
+	if (req_complete) {
+		req_complete(hdev, status, opcode);
+	} else if (req_complete_skb) {
+		if (!hci_get_cmd_complete(hdev, opcode, req_evt, orig_skb)) {
+			kfree_skb(orig_skb);
+			orig_skb = NULL;
+		}
+		req_complete_skb(hdev, status, opcode, orig_skb);
+	}
+
+	kfree_skb(orig_skb);
 	kfree_skb(skb);
 	hdev->stat.evt_rx++;
 }
diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c
new file mode 100644
index 000000000000..d6025d6e6d59
--- /dev/null
+++ b/net/bluetooth/hci_request.c
@@ -0,0 +1,568 @@
+/*
+   BlueZ - Bluetooth protocol stack for Linux
+
+   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;
+
+   THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+   OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+   FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS.
+   IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY
+   CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES
+   WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+   ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+   OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+
+   ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS,
+   COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS
+   SOFTWARE IS DISCLAIMED.
+*/
+
+#include <net/bluetooth/bluetooth.h>
+#include <net/bluetooth/hci_core.h>
+
+#include "smp.h"
+#include "hci_request.h"
+
+void hci_req_init(struct hci_request *req, struct hci_dev *hdev)
+{
+	skb_queue_head_init(&req->cmd_q);
+	req->hdev = hdev;
+	req->err = 0;
+}
+
+static int req_run(struct hci_request *req, hci_req_complete_t complete,
+		   hci_req_complete_skb_t complete_skb)
+{
+	struct hci_dev *hdev = req->hdev;
+	struct sk_buff *skb;
+	unsigned long flags;
+
+	BT_DBG("length %u", skb_queue_len(&req->cmd_q));
+
+	/* If an error occurred during request building, remove all HCI
+	 * commands queued on the HCI request queue.
+	 */
+	if (req->err) {
+		skb_queue_purge(&req->cmd_q);
+		return req->err;
+	}
+
+	/* Do not allow empty requests */
+	if (skb_queue_empty(&req->cmd_q))
+		return -ENODATA;
+
+	skb = skb_peek_tail(&req->cmd_q);
+	bt_cb(skb)->req.complete = complete;
+	bt_cb(skb)->req.complete_skb = complete_skb;
+
+	spin_lock_irqsave(&hdev->cmd_q.lock, flags);
+	skb_queue_splice_tail(&req->cmd_q, &hdev->cmd_q);
+	spin_unlock_irqrestore(&hdev->cmd_q.lock, flags);
+
+	queue_work(hdev->workqueue, &hdev->cmd_work);
+
+	return 0;
+}
+
+int hci_req_run(struct hci_request *req, hci_req_complete_t complete)
+{
+	return req_run(req, complete, NULL);
+}
+
+int hci_req_run_skb(struct hci_request *req, hci_req_complete_skb_t complete)
+{
+	return req_run(req, NULL, complete);
+}
+
+struct sk_buff *hci_prepare_cmd(struct hci_dev *hdev, u16 opcode, u32 plen,
+				const void *param)
+{
+	int len = HCI_COMMAND_HDR_SIZE + plen;
+	struct hci_command_hdr *hdr;
+	struct sk_buff *skb;
+
+	skb = bt_skb_alloc(len, GFP_ATOMIC);
+	if (!skb)
+		return NULL;
+
+	hdr = (struct hci_command_hdr *) skb_put(skb, HCI_COMMAND_HDR_SIZE);
+	hdr->opcode = cpu_to_le16(opcode);
+	hdr->plen   = plen;
+
+	if (plen)
+		memcpy(skb_put(skb, plen), param, plen);
+
+	BT_DBG("skb len %d", skb->len);
+
+	bt_cb(skb)->pkt_type = HCI_COMMAND_PKT;
+	bt_cb(skb)->opcode = opcode;
+
+	return skb;
+}
+
+/* Queue a command to an asynchronous HCI request */
+void hci_req_add_ev(struct hci_request *req, u16 opcode, u32 plen,
+		    const void *param, u8 event)
+{
+	struct hci_dev *hdev = req->hdev;
+	struct sk_buff *skb;
+
+	BT_DBG("%s opcode 0x%4.4x plen %d", hdev->name, opcode, plen);
+
+	/* If an error occurred during request building, there is no point in
+	 * queueing the HCI command. We can simply return.
+	 */
+	if (req->err)
+		return;
+
+	skb = hci_prepare_cmd(hdev, opcode, plen, param);
+	if (!skb) {
+		BT_ERR("%s no memory for command (opcode 0x%4.4x)",
+		       hdev->name, opcode);
+		req->err = -ENOMEM;
+		return;
+	}
+
+	if (skb_queue_empty(&req->cmd_q))
+		bt_cb(skb)->req.start = true;
+
+	bt_cb(skb)->req.event = event;
+
+	skb_queue_tail(&req->cmd_q, skb);
+}
+
+void hci_req_add(struct hci_request *req, u16 opcode, u32 plen,
+		 const void *param)
+{
+	hci_req_add_ev(req, opcode, plen, param, 0);
+}
+
+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);
+}
+
+static void add_to_white_list(struct hci_request *req,
+			      struct hci_conn_params *params)
+{
+	struct hci_cp_le_add_to_white_list cp;
+
+	cp.bdaddr_type = params->addr_type;
+	bacpy(&cp.bdaddr, &params->addr);
+
+	hci_req_add(req, HCI_OP_LE_ADD_TO_WHITE_LIST, sizeof(cp), &cp);
+}
+
+static u8 update_white_list(struct hci_request *req)
+{
+	struct hci_dev *hdev = req->hdev;
+	struct hci_conn_params *params;
+	struct bdaddr_list *b;
+	uint8_t white_list_entries = 0;
+
+	/* Go through the current white list programmed into the
+	 * controller one by one and check if that address is still
+	 * in the list of pending connections or list of devices to
+	 * report. If not present in either list, then queue the
+	 * command to remove it from the controller.
+	 */
+	list_for_each_entry(b, &hdev->le_white_list, list) {
+		struct hci_cp_le_del_from_white_list cp;
+
+		if (hci_pend_le_action_lookup(&hdev->pend_le_conns,
+					      &b->bdaddr, b->bdaddr_type) ||
+		    hci_pend_le_action_lookup(&hdev->pend_le_reports,
+					      &b->bdaddr, b->bdaddr_type)) {
+			white_list_entries++;
+			continue;
+		}
+
+		cp.bdaddr_type = b->bdaddr_type;
+		bacpy(&cp.bdaddr, &b->bdaddr);
+
+		hci_req_add(req, HCI_OP_LE_DEL_FROM_WHITE_LIST,
+			    sizeof(cp), &cp);
+	}
+
+	/* Since all no longer valid white list entries have been
+	 * removed, walk through the list of pending connections
+	 * and ensure that any new device gets programmed into
+	 * the controller.
+	 *
+	 * If the list of the devices is larger than the list of
+	 * available white list entries in the controller, then
+	 * just abort and return filer policy value to not use the
+	 * white list.
+	 */
+	list_for_each_entry(params, &hdev->pend_le_conns, action) {
+		if (hci_bdaddr_list_lookup(&hdev->le_white_list,
+					   &params->addr, params->addr_type))
+			continue;
+
+		if (white_list_entries >= hdev->le_white_list_size) {
+			/* Select filter policy to accept all advertising */
+			return 0x00;
+		}
+
+		if (hci_find_irk_by_addr(hdev, &params->addr,
+					 params->addr_type)) {
+			/* White list can not be used with RPAs */
+			return 0x00;
+		}
+
+		white_list_entries++;
+		add_to_white_list(req, params);
+	}
+
+	/* After adding all new pending connections, walk through
+	 * the list of pending reports and also add these to the
+	 * white list if there is still space.
+	 */
+	list_for_each_entry(params, &hdev->pend_le_reports, action) {
+		if (hci_bdaddr_list_lookup(&hdev->le_white_list,
+					   &params->addr, params->addr_type))
+			continue;
+
+		if (white_list_entries >= hdev->le_white_list_size) {
+			/* Select filter policy to accept all advertising */
+			return 0x00;
+		}
+
+		if (hci_find_irk_by_addr(hdev, &params->addr,
+					 params->addr_type)) {
+			/* White list can not be used with RPAs */
+			return 0x00;
+		}
+
+		white_list_entries++;
+		add_to_white_list(req, params);
+	}
+
+	/* Select filter policy to use white list */
+	return 0x01;
+}
+
+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;
+	u8 filter_policy;
+
+	/* Set require_privacy to false since no SCAN_REQ are send
+	 * during passive scanning. Not using an non-resolvable address
+	 * here is important so that peer devices using direct
+	 * advertising with our address will be correctly reported
+	 * by the controller.
+	 */
+	if (hci_update_random_address(req, false, &own_addr_type))
+		return;
+
+	/* Adding or removing entries from the white list must
+	 * happen before enabling scanning. The controller does
+	 * not allow white list modification while scanning.
+	 */
+	filter_policy = update_white_list(req);
+
+	/* When the controller is using random resolvable addresses and
+	 * with that having LE privacy enabled, then controllers with
+	 * Extended Scanner Filter Policies support can now enable support
+	 * for handling directed advertising.
+	 *
+	 * So instead of using filter polices 0x00 (no whitelist)
+	 * and 0x01 (whitelist enabled) use the new filter policies
+	 * 0x02 (no whitelist) and 0x03 (whitelist enabled).
+	 */
+	if (hci_dev_test_flag(hdev, HCI_PRIVACY) &&
+	    (hdev->le_features[0] & HCI_LE_EXT_SCAN_POLICY))
+		filter_policy |= 0x02;
+
+	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;
+	param_cp.filter_policy = filter_policy;
+	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 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 (hci_dev_test_flag(hdev, HCI_LE_ADV) ||
+	    hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT)) {
+		BT_DBG("Deferring random address update");
+		hci_dev_set_flag(hdev, HCI_RPA_EXPIRED);
+		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 (hci_dev_test_flag(hdev, HCI_PRIVACY)) {
+		int to;
+
+		*own_addr_type = ADDR_LE_DEV_RANDOM;
+
+		if (!hci_dev_test_and_clear_flag(hdev, HCI_RPA_EXPIRED) &&
+		    !bacmp(&hdev->random_addr, &hdev->rpa))
+			return 0;
+
+		err = smp_generate_rpa(hdev, 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 non-resolvable private address. This is useful for active
+	 * scanning and non-connectable advertising.
+	 */
+	if (require_privacy) {
+		bdaddr_t nrpa;
+
+		while (true) {
+			/* The non-resolvable private address is generated
+			 * from random six bytes with the two most significant
+			 * bits cleared.
+			 */
+			get_random_bytes(&nrpa, 6);
+			nrpa.b[5] &= 0x3f;
+
+			/* The non-resolvable private address shall not be
+			 * equal to the public address.
+			 */
+			if (bacmp(&hdev->bdaddr, &nrpa))
+				break;
+		}
+
+		*own_addr_type = ADDR_LE_DEV_RANDOM;
+		set_random_addr(req, &nrpa);
+		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.
+	 *
+	 * In case BR/EDR has been disabled on a dual-mode controller
+	 * and a static address has been configured, then use that
+	 * address instead of the public BR/EDR address.
+	 */
+	if (hci_dev_test_flag(hdev, HCI_FORCE_STATIC_ADDR) ||
+	    !bacmp(&hdev->bdaddr, BDADDR_ANY) ||
+	    (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED) &&
+	     bacmp(&hdev->static_addr, 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;
+}
+
+static bool disconnected_whitelist_entries(struct hci_dev *hdev)
+{
+	struct bdaddr_list *b;
+
+	list_for_each_entry(b, &hdev->whitelist, list) {
+		struct hci_conn *conn;
+
+		conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &b->bdaddr);
+		if (!conn)
+			return true;
+
+		if (conn->state != BT_CONNECTED && conn->state != BT_CONFIG)
+			return true;
+	}
+
+	return false;
+}
+
+void __hci_update_page_scan(struct hci_request *req)
+{
+	struct hci_dev *hdev = req->hdev;
+	u8 scan;
+
+	if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED))
+		return;
+
+	if (!hdev_is_powered(hdev))
+		return;
+
+	if (mgmt_powering_down(hdev))
+		return;
+
+	if (hci_dev_test_flag(hdev, HCI_CONNECTABLE) ||
+	    disconnected_whitelist_entries(hdev))
+		scan = SCAN_PAGE;
+	else
+		scan = SCAN_DISABLED;
+
+	if (test_bit(HCI_PSCAN, &hdev->flags) == !!(scan & SCAN_PAGE))
+		return;
+
+	if (hci_dev_test_flag(hdev, HCI_DISCOVERABLE))
+		scan |= SCAN_INQUIRY;
+
+	hci_req_add(req, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan);
+}
+
+void hci_update_page_scan(struct hci_dev *hdev)
+{
+	struct hci_request req;
+
+	hci_req_init(&req, hdev);
+	__hci_update_page_scan(&req);
+	hci_req_run(&req, NULL);
+}
+
+/* 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_request *req)
+{
+	struct hci_dev *hdev = req->hdev;
+	struct hci_conn *conn;
+
+	if (!test_bit(HCI_UP, &hdev->flags) ||
+	    test_bit(HCI_INIT, &hdev->flags) ||
+	    hci_dev_test_flag(hdev, HCI_SETUP) ||
+	    hci_dev_test_flag(hdev, HCI_CONFIG) ||
+	    hci_dev_test_flag(hdev, HCI_AUTO_OFF) ||
+	    hci_dev_test_flag(hdev, HCI_UNREGISTER))
+		return;
+
+	/* No point in doing scanning if LE support hasn't been enabled */
+	if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED))
+		return;
+
+	/* If discovery is active don't interfere with it */
+	if (hdev->discovery.state != DISCOVERY_STOPPED)
+		return;
+
+	/* Reset RSSI and UUID filters when starting background scanning
+	 * since these filters are meant for service discovery only.
+	 *
+	 * The Start Discovery and Start Service Discovery operations
+	 * ensure to set proper values for RSSI threshold and UUID
+	 * filter list. So it is safe to just reset them here.
+	 */
+	hci_discovery_filter_clear(hdev);
+
+	if (list_empty(&hdev->pend_le_conns) &&
+	    list_empty(&hdev->pend_le_reports)) {
+		/* If there is no pending LE connections or devices
+		 * to be scanned for, we should stop the background
+		 * scanning.
+		 */
+
+		/* If controller is not scanning we are done. */
+		if (!hci_dev_test_flag(hdev, HCI_LE_SCAN))
+			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 (hci_dev_test_flag(hdev, HCI_LE_SCAN))
+			hci_req_add_le_scan_disable(req);
+
+		hci_req_add_le_passive_scan(req);
+
+		BT_DBG("%s starting background scanning", hdev->name);
+	}
+}
+
+static void update_background_scan_complete(struct hci_dev *hdev, u8 status,
+					    u16 opcode)
+{
+	if (status)
+		BT_DBG("HCI request failed to update background scanning: "
+		       "status 0x%2.2x", status);
+}
+
+void hci_update_background_scan(struct hci_dev *hdev)
+{
+	int err;
+	struct hci_request req;
+
+	hci_req_init(&req, hdev);
+
+	__hci_update_background_scan(&req);
+
+	err = hci_req_run(&req, update_background_scan_complete);
+	if (err && err != -ENODATA)
+		BT_ERR("Failed to run HCI request: err %d", err);
+}
diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h
new file mode 100644
index 000000000000..bf6df92f42db
--- /dev/null
+++ b/net/bluetooth/hci_request.h
@@ -0,0 +1,57 @@
+/*
+   BlueZ - Bluetooth protocol stack for Linux
+   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;
+
+   THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+   OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+   FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS.
+   IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY
+   CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES
+   WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+   ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+   OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+
+   ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS,
+   COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS
+   SOFTWARE IS DISCLAIMED.
+*/
+
+struct hci_request {
+	struct hci_dev		*hdev;
+	struct sk_buff_head	cmd_q;
+
+	/* If something goes wrong when building the HCI request, the error
+	 * value is stored in this field.
+	 */
+	int			err;
+};
+
+void hci_req_init(struct hci_request *req, struct hci_dev *hdev);
+int hci_req_run(struct hci_request *req, hci_req_complete_t complete);
+int hci_req_run_skb(struct hci_request *req, hci_req_complete_skb_t complete);
+void hci_req_add(struct hci_request *req, u16 opcode, u32 plen,
+		 const void *param);
+void hci_req_add_ev(struct hci_request *req, u16 opcode, u32 plen,
+		    const void *param, u8 event);
+void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status,
+			  hci_req_complete_t *req_complete,
+			  hci_req_complete_skb_t *req_complete_skb);
+
+struct sk_buff *hci_prepare_cmd(struct hci_dev *hdev, u16 opcode, u32 plen,
+				const void *param);
+
+void hci_req_add_le_scan_disable(struct hci_request *req);
+void hci_req_add_le_passive_scan(struct hci_request *req);
+
+void hci_update_page_scan(struct hci_dev *hdev);
+void __hci_update_page_scan(struct hci_request *req);
+
+int hci_update_random_address(struct hci_request *req, bool require_privacy,
+			      u8 *own_addr_type);
+
+void hci_update_background_scan(struct hci_dev *hdev);
+void __hci_update_background_scan(struct hci_request *req);
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 115f149362ba..56f9edbf3d05 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -30,6 +30,12 @@
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
 #include <net/bluetooth/hci_mon.h>
+#include <net/bluetooth/mgmt.h>
+
+#include "mgmt_util.h"
+
+static LIST_HEAD(mgmt_chan_list);
+static DEFINE_MUTEX(mgmt_chan_list_lock);
 
 static atomic_t monitor_promisc = ATOMIC_INIT(0);
 
@@ -44,11 +50,32 @@ struct hci_pinfo {
 	struct hci_filter filter;
 	__u32             cmsg_mask;
 	unsigned short    channel;
+	unsigned long     flags;
 };
 
-static inline int hci_test_bit(int nr, void *addr)
+void hci_sock_set_flag(struct sock *sk, int nr)
+{
+	set_bit(nr, &hci_pi(sk)->flags);
+}
+
+void hci_sock_clear_flag(struct sock *sk, int nr)
+{
+	clear_bit(nr, &hci_pi(sk)->flags);
+}
+
+int hci_sock_test_flag(struct sock *sk, int nr)
+{
+	return test_bit(nr, &hci_pi(sk)->flags);
+}
+
+unsigned short hci_sock_get_channel(struct sock *sk)
 {
-	return *((__u32 *) addr + (nr >> 5)) & ((__u32) 1 << (nr & 31));
+	return hci_pi(sk)->channel;
+}
+
+static inline int hci_test_bit(int nr, const void *addr)
+{
+	return *((const __u32 *) addr + (nr >> 5)) & ((__u32) 1 << (nr & 31));
 }
 
 /* Security filter */
@@ -183,18 +210,23 @@ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb)
 	kfree_skb(skb_copy);
 }
 
-/* Send frame to control socket */
-void hci_send_to_control(struct sk_buff *skb, struct sock *skip_sk)
+/* Send frame to sockets with specific channel */
+void hci_send_to_channel(unsigned short channel, struct sk_buff *skb,
+			 int flag, struct sock *skip_sk)
 {
 	struct sock *sk;
 
-	BT_DBG("len %d", skb->len);
+	BT_DBG("channel %u len %d", channel, skb->len);
 
 	read_lock(&hci_sk_list.lock);
 
 	sk_for_each(sk, &hci_sk_list.head) {
 		struct sk_buff *nskb;
 
+		/* Ignore socket without the flag set */
+		if (!hci_sock_test_flag(sk, flag))
+			continue;
+
 		/* Skip the original socket */
 		if (sk == skip_sk)
 			continue;
@@ -202,7 +234,7 @@ void hci_send_to_control(struct sk_buff *skb, struct sock *skip_sk)
 		if (sk->sk_state != BT_BOUND)
 			continue;
 
-		if (hci_pi(sk)->channel != HCI_CHANNEL_CONTROL)
+		if (hci_pi(sk)->channel != channel)
 			continue;
 
 		nskb = skb_clone(skb, GFP_ATOMIC);
@@ -219,8 +251,8 @@ void hci_send_to_control(struct sk_buff *skb, struct sock *skip_sk)
 /* Send frame to monitor socket */
 void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb)
 {
-	struct sock *sk;
 	struct sk_buff *skb_copy = NULL;
+	struct hci_mon_hdr *hdr;
 	__le16 opcode;
 
 	if (!atomic_read(&monitor_promisc))
@@ -251,74 +283,22 @@ void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb)
 		return;
 	}
 
-	read_lock(&hci_sk_list.lock);
-
-	sk_for_each(sk, &hci_sk_list.head) {
-		struct sk_buff *nskb;
-
-		if (sk->sk_state != BT_BOUND)
-			continue;
-
-		if (hci_pi(sk)->channel != HCI_CHANNEL_MONITOR)
-			continue;
-
-		if (!skb_copy) {
-			struct hci_mon_hdr *hdr;
-
-			/* Create a private copy with headroom */
-			skb_copy = __pskb_copy_fclone(skb, HCI_MON_HDR_SIZE,
-						      GFP_ATOMIC, true);
-			if (!skb_copy)
-				continue;
-
-			/* Put header before the data */
-			hdr = (void *) skb_push(skb_copy, HCI_MON_HDR_SIZE);
-			hdr->opcode = opcode;
-			hdr->index = cpu_to_le16(hdev->id);
-			hdr->len = cpu_to_le16(skb->len);
-		}
-
-		nskb = skb_clone(skb_copy, GFP_ATOMIC);
-		if (!nskb)
-			continue;
-
-		if (sock_queue_rcv_skb(sk, nskb))
-			kfree_skb(nskb);
-	}
+	/* Create a private copy with headroom */
+	skb_copy = __pskb_copy_fclone(skb, HCI_MON_HDR_SIZE, GFP_ATOMIC, true);
+	if (!skb_copy)
+		return;
 
-	read_unlock(&hci_sk_list.lock);
+	/* Put header before the data */
+	hdr = (void *) skb_push(skb_copy, HCI_MON_HDR_SIZE);
+	hdr->opcode = opcode;
+	hdr->index = cpu_to_le16(hdev->id);
+	hdr->len = cpu_to_le16(skb->len);
 
+	hci_send_to_channel(HCI_CHANNEL_MONITOR, skb_copy,
+			    HCI_SOCK_TRUSTED, NULL);
 	kfree_skb(skb_copy);
 }
 
-static void send_monitor_event(struct sk_buff *skb)
-{
-	struct sock *sk;
-
-	BT_DBG("len %d", skb->len);
-
-	read_lock(&hci_sk_list.lock);
-
-	sk_for_each(sk, &hci_sk_list.head) {
-		struct sk_buff *nskb;
-
-		if (sk->sk_state != BT_BOUND)
-			continue;
-
-		if (hci_pi(sk)->channel != HCI_CHANNEL_MONITOR)
-			continue;
-
-		nskb = skb_clone(skb, GFP_ATOMIC);
-		if (!nskb)
-			continue;
-
-		if (sock_queue_rcv_skb(sk, nskb))
-			kfree_skb(nskb);
-	}
-
-	read_unlock(&hci_sk_list.lock);
-}
-
 static struct sk_buff *create_monitor_event(struct hci_dev *hdev, int event)
 {
 	struct hci_mon_hdr *hdr;
@@ -422,7 +402,8 @@ void hci_sock_dev_event(struct hci_dev *hdev, int event)
 
 		skb = create_monitor_event(hdev, event);
 		if (skb) {
-			send_monitor_event(skb);
+			hci_send_to_channel(HCI_CHANNEL_MONITOR, skb,
+					    HCI_SOCK_TRUSTED, NULL);
 			kfree_skb(skb);
 		}
 	}
@@ -453,6 +434,56 @@ void hci_sock_dev_event(struct hci_dev *hdev, int event)
 	}
 }
 
+static struct hci_mgmt_chan *__hci_mgmt_chan_find(unsigned short channel)
+{
+	struct hci_mgmt_chan *c;
+
+	list_for_each_entry(c, &mgmt_chan_list, list) {
+		if (c->channel == channel)
+			return c;
+	}
+
+	return NULL;
+}
+
+static struct hci_mgmt_chan *hci_mgmt_chan_find(unsigned short channel)
+{
+	struct hci_mgmt_chan *c;
+
+	mutex_lock(&mgmt_chan_list_lock);
+	c = __hci_mgmt_chan_find(channel);
+	mutex_unlock(&mgmt_chan_list_lock);
+
+	return c;
+}
+
+int hci_mgmt_chan_register(struct hci_mgmt_chan *c)
+{
+	if (c->channel < HCI_CHANNEL_CONTROL)
+		return -EINVAL;
+
+	mutex_lock(&mgmt_chan_list_lock);
+	if (__hci_mgmt_chan_find(c->channel)) {
+		mutex_unlock(&mgmt_chan_list_lock);
+		return -EALREADY;
+	}
+
+	list_add_tail(&c->list, &mgmt_chan_list);
+
+	mutex_unlock(&mgmt_chan_list_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL(hci_mgmt_chan_register);
+
+void hci_mgmt_chan_unregister(struct hci_mgmt_chan *c)
+{
+	mutex_lock(&mgmt_chan_list_lock);
+	list_del(&c->list);
+	mutex_unlock(&mgmt_chan_list_lock);
+}
+EXPORT_SYMBOL(hci_mgmt_chan_unregister);
+
 static int hci_sock_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
@@ -473,7 +504,7 @@ static int hci_sock_release(struct socket *sock)
 	if (hdev) {
 		if (hci_pi(sk)->channel == HCI_CHANNEL_USER) {
 			mgmt_index_added(hdev);
-			clear_bit(HCI_USER_CHANNEL, &hdev->dev_flags);
+			hci_dev_clear_flag(hdev, HCI_USER_CHANNEL);
 			hci_dev_close(hdev->id);
 		}
 
@@ -533,10 +564,10 @@ static int hci_sock_bound_ioctl(struct sock *sk, unsigned int cmd,
 	if (!hdev)
 		return -EBADFD;
 
-	if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL))
 		return -EBUSY;
 
-	if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED))
 		return -EOPNOTSUPP;
 
 	if (hdev->dev_type != HCI_BREDR)
@@ -712,14 +743,14 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr *addr,
 
 		if (test_bit(HCI_UP, &hdev->flags) ||
 		    test_bit(HCI_INIT, &hdev->flags) ||
-		    test_bit(HCI_SETUP, &hdev->dev_flags) ||
-		    test_bit(HCI_CONFIG, &hdev->dev_flags)) {
+		    hci_dev_test_flag(hdev, HCI_SETUP) ||
+		    hci_dev_test_flag(hdev, HCI_CONFIG)) {
 			err = -EBUSY;
 			hci_dev_put(hdev);
 			goto done;
 		}
 
-		if (test_and_set_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) {
+		if (hci_dev_test_and_set_flag(hdev, HCI_USER_CHANNEL)) {
 			err = -EUSERS;
 			hci_dev_put(hdev);
 			goto done;
@@ -729,7 +760,7 @@ 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);
+			hci_dev_clear_flag(hdev, HCI_USER_CHANNEL);
 			mgmt_index_added(hdev);
 			hci_dev_put(hdev);
 			goto done;
@@ -740,38 +771,62 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr *addr,
 		hci_pi(sk)->hdev = hdev;
 		break;
 
-	case HCI_CHANNEL_CONTROL:
+	case HCI_CHANNEL_MONITOR:
 		if (haddr.hci_dev != HCI_DEV_NONE) {
 			err = -EINVAL;
 			goto done;
 		}
 
-		if (!capable(CAP_NET_ADMIN)) {
+		if (!capable(CAP_NET_RAW)) {
 			err = -EPERM;
 			goto done;
 		}
 
+		/* The monitor interface is restricted to CAP_NET_RAW
+		 * capabilities and with that implicitly trusted.
+		 */
+		hci_sock_set_flag(sk, HCI_SOCK_TRUSTED);
+
+		send_monitor_replay(sk);
+
+		atomic_inc(&monitor_promisc);
 		break;
 
-	case HCI_CHANNEL_MONITOR:
-		if (haddr.hci_dev != HCI_DEV_NONE) {
+	default:
+		if (!hci_mgmt_chan_find(haddr.hci_channel)) {
 			err = -EINVAL;
 			goto done;
 		}
 
-		if (!capable(CAP_NET_RAW)) {
-			err = -EPERM;
+		if (haddr.hci_dev != HCI_DEV_NONE) {
+			err = -EINVAL;
 			goto done;
 		}
 
-		send_monitor_replay(sk);
-
-		atomic_inc(&monitor_promisc);
+		/* Users with CAP_NET_ADMIN capabilities are allowed
+		 * access to all management commands and events. For
+		 * untrusted users the interface is restricted and
+		 * also only untrusted events are sent.
+		 */
+		if (capable(CAP_NET_ADMIN))
+			hci_sock_set_flag(sk, HCI_SOCK_TRUSTED);
+
+		/* At the moment the index and unconfigured index events
+		 * are enabled unconditionally. Setting them on each
+		 * socket when binding keeps this functionality. They
+		 * however might be cleared later and then sending of these
+		 * events will be disabled, but that is then intentional.
+		 *
+		 * This also enables generic events that are safe to be
+		 * received by untrusted users. Example for such events
+		 * are changes to settings, class of device, name etc.
+		 */
+		if (haddr.hci_channel == HCI_CHANNEL_CONTROL) {
+			hci_sock_set_flag(sk, HCI_MGMT_INDEX_EVENTS);
+			hci_sock_set_flag(sk, HCI_MGMT_UNCONF_INDEX_EVENTS);
+			hci_sock_set_flag(sk, HCI_MGMT_GENERIC_EVENTS);
+		}
 		break;
-
-	default:
-		err = -EINVAL;
-		goto done;
 	}
 
 
@@ -851,8 +906,8 @@ static void hci_sock_cmsg(struct sock *sk, struct msghdr *msg,
 	}
 }
 
-static int hci_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
-			    struct msghdr *msg, size_t len, int flags)
+static int hci_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+			    int flags)
 {
 	int noblock = flags & MSG_DONTWAIT;
 	struct sock *sk = sock->sk;
@@ -878,17 +933,20 @@ static int hci_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 	}
 
 	skb_reset_transport_header(skb);
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 
 	switch (hci_pi(sk)->channel) {
 	case HCI_CHANNEL_RAW:
 		hci_sock_cmsg(sk, msg, skb);
 		break;
 	case HCI_CHANNEL_USER:
-	case HCI_CHANNEL_CONTROL:
 	case HCI_CHANNEL_MONITOR:
 		sock_recv_timestamp(msg, sk, skb);
 		break;
+	default:
+		if (hci_mgmt_chan_find(hci_pi(sk)->channel))
+			sock_recv_timestamp(msg, sk, skb);
+		break;
 	}
 
 	skb_free_datagram(sk, skb);
@@ -896,10 +954,122 @@ static int hci_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 	return err ? : copied;
 }
 
-static int hci_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
-			    struct msghdr *msg, size_t len)
+static int hci_mgmt_cmd(struct hci_mgmt_chan *chan, struct sock *sk,
+			struct msghdr *msg, size_t msglen)
+{
+	void *buf;
+	u8 *cp;
+	struct mgmt_hdr *hdr;
+	u16 opcode, index, len;
+	struct hci_dev *hdev = NULL;
+	const struct hci_mgmt_handler *handler;
+	bool var_len, no_hdev;
+	int err;
+
+	BT_DBG("got %zu bytes", msglen);
+
+	if (msglen < sizeof(*hdr))
+		return -EINVAL;
+
+	buf = kmalloc(msglen, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	if (memcpy_from_msg(buf, msg, msglen)) {
+		err = -EFAULT;
+		goto done;
+	}
+
+	hdr = buf;
+	opcode = __le16_to_cpu(hdr->opcode);
+	index = __le16_to_cpu(hdr->index);
+	len = __le16_to_cpu(hdr->len);
+
+	if (len != msglen - sizeof(*hdr)) {
+		err = -EINVAL;
+		goto done;
+	}
+
+	if (opcode >= chan->handler_count ||
+	    chan->handlers[opcode].func == NULL) {
+		BT_DBG("Unknown op %u", opcode);
+		err = mgmt_cmd_status(sk, index, opcode,
+				      MGMT_STATUS_UNKNOWN_COMMAND);
+		goto done;
+	}
+
+	handler = &chan->handlers[opcode];
+
+	if (!hci_sock_test_flag(sk, HCI_SOCK_TRUSTED) &&
+	    !(handler->flags & HCI_MGMT_UNTRUSTED)) {
+		err = mgmt_cmd_status(sk, index, opcode,
+				      MGMT_STATUS_PERMISSION_DENIED);
+		goto done;
+	}
+
+	if (index != MGMT_INDEX_NONE) {
+		hdev = hci_dev_get(index);
+		if (!hdev) {
+			err = mgmt_cmd_status(sk, index, opcode,
+					      MGMT_STATUS_INVALID_INDEX);
+			goto done;
+		}
+
+		if (hci_dev_test_flag(hdev, HCI_SETUP) ||
+		    hci_dev_test_flag(hdev, HCI_CONFIG) ||
+		    hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) {
+			err = mgmt_cmd_status(sk, index, opcode,
+					      MGMT_STATUS_INVALID_INDEX);
+			goto done;
+		}
+
+		if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED) &&
+		    !(handler->flags & HCI_MGMT_UNCONFIGURED)) {
+			err = mgmt_cmd_status(sk, index, opcode,
+					      MGMT_STATUS_INVALID_INDEX);
+			goto done;
+		}
+	}
+
+	no_hdev = (handler->flags & HCI_MGMT_NO_HDEV);
+	if (no_hdev != !hdev) {
+		err = mgmt_cmd_status(sk, index, opcode,
+				      MGMT_STATUS_INVALID_INDEX);
+		goto done;
+	}
+
+	var_len = (handler->flags & HCI_MGMT_VAR_LEN);
+	if ((var_len && len < handler->data_len) ||
+	    (!var_len && len != handler->data_len)) {
+		err = mgmt_cmd_status(sk, index, opcode,
+				      MGMT_STATUS_INVALID_PARAMS);
+		goto done;
+	}
+
+	if (hdev && chan->hdev_init)
+		chan->hdev_init(sk, hdev);
+
+	cp = buf + sizeof(*hdr);
+
+	err = handler->func(sk, hdev, cp, len);
+	if (err < 0)
+		goto done;
+
+	err = msglen;
+
+done:
+	if (hdev)
+		hci_dev_put(hdev);
+
+	kfree(buf);
+	return err;
+}
+
+static int hci_sock_sendmsg(struct socket *sock, struct msghdr *msg,
+			    size_t len)
 {
 	struct sock *sk = sock->sk;
+	struct hci_mgmt_chan *chan;
 	struct hci_dev *hdev;
 	struct sk_buff *skb;
 	int err;
@@ -921,14 +1091,18 @@ static int hci_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 	case HCI_CHANNEL_RAW:
 	case HCI_CHANNEL_USER:
 		break;
-	case HCI_CHANNEL_CONTROL:
-		err = mgmt_control(sk, msg, len);
-		goto done;
 	case HCI_CHANNEL_MONITOR:
 		err = -EOPNOTSUPP;
 		goto done;
 	default:
-		err = -EINVAL;
+		mutex_lock(&mgmt_chan_list_lock);
+		chan = __hci_mgmt_chan_find(hci_pi(sk)->channel);
+		if (chan)
+			err = hci_mgmt_cmd(chan, sk, msg, len);
+		else
+			err = -EINVAL;
+
+		mutex_unlock(&mgmt_chan_list_lock);
 		goto done;
 	}
 
@@ -947,7 +1121,7 @@ static int hci_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 	if (!skb)
 		goto done;
 
-	if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) {
+	if (memcpy_from_msg(skb_put(skb, len), msg, len)) {
 		err = -EFAULT;
 		goto drop;
 	}
@@ -987,7 +1161,7 @@ static int hci_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 			skb_queue_tail(&hdev->raw_q, skb);
 			queue_work(hdev->workqueue, &hdev->tx_work);
 		} else {
-			/* Stand-alone HCI commands must be flaged as
+			/* Stand-alone HCI commands must be flagged as
 			 * single-command requests.
 			 */
 			bt_cb(skb)->req.start = true;
@@ -1230,6 +1404,8 @@ int __init hci_sock_init(void)
 {
 	int err;
 
+	BUILD_BUG_ON(sizeof(struct sockaddr_hci) > sizeof(struct sockaddr));
+
 	err = proto_register(&hci_sk_proto, 0);
 	if (err < 0)
 		return err;
diff --git a/net/bluetooth/hidp/Kconfig b/net/bluetooth/hidp/Kconfig
index 9332bc7aa851..bc8610b24077 100644
--- a/net/bluetooth/hidp/Kconfig
+++ b/net/bluetooth/hidp/Kconfig
@@ -1,6 +1,6 @@
 config BT_HIDP
 	tristate "HIDP protocol support"
-	depends on BT && INPUT
+	depends on BT_BREDR && INPUT
 	select HID
 	help
 	  HIDP (Human Interface Device Protocol) is a transport layer
diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c
index 1b7d605706aa..9070dfd6b4ad 100644
--- a/net/bluetooth/hidp/core.c
+++ b/net/bluetooth/hidp/core.c
@@ -70,10 +70,11 @@ static void hidp_session_terminate(struct hidp_session *s);
 
 static void hidp_copy_session(struct hidp_session *session, struct hidp_conninfo *ci)
 {
+	u32 valid_flags = 0;
 	memset(ci, 0, sizeof(*ci));
 	bacpy(&ci->bdaddr, &session->bdaddr);
 
-	ci->flags = session->flags;
+	ci->flags = session->flags & valid_flags;
 	ci->state = BT_CONNECTED;
 
 	if (session->input) {
@@ -736,14 +737,10 @@ static int hidp_setup_hid(struct hidp_session *session,
 	struct hid_device *hid;
 	int err;
 
-	session->rd_data = kzalloc(req->rd_size, GFP_KERNEL);
-	if (!session->rd_data)
-		return -ENOMEM;
+	session->rd_data = memdup_user(req->rd_data, req->rd_size);
+	if (IS_ERR(session->rd_data))
+		return PTR_ERR(session->rd_data);
 
-	if (copy_from_user(session->rd_data, req->rd_data, req->rd_size)) {
-		err = -EFAULT;
-		goto fault;
-	}
 	session->rd_size = req->rd_size;
 
 	hid = hid_allocate_device();
@@ -911,7 +908,7 @@ static int hidp_session_new(struct hidp_session **out, const bdaddr_t *bdaddr,
 	kref_init(&session->ref);
 	atomic_set(&session->state, HIDP_SESSION_IDLING);
 	init_waitqueue_head(&session->state_queue);
-	session->flags = req->flags & (1 << HIDP_BLUETOOTH_VENDOR_ID);
+	session->flags = req->flags & BIT(HIDP_BLUETOOTH_VENDOR_ID);
 
 	/* connection management */
 	bacpy(&session->bdaddr, bdaddr);
@@ -1316,15 +1313,21 @@ int hidp_connection_add(struct hidp_connadd_req *req,
 			struct socket *ctrl_sock,
 			struct socket *intr_sock)
 {
+	u32 valid_flags = BIT(HIDP_VIRTUAL_CABLE_UNPLUG) |
+			  BIT(HIDP_BOOT_PROTOCOL_MODE);
 	struct hidp_session *session;
 	struct l2cap_conn *conn;
-	struct l2cap_chan *chan = l2cap_pi(ctrl_sock->sk)->chan;
+	struct l2cap_chan *chan;
 	int ret;
 
 	ret = hidp_verify_sockets(ctrl_sock, intr_sock);
 	if (ret)
 		return ret;
 
+	if (req->flags & ~valid_flags)
+		return -EINVAL;
+
+	chan = l2cap_pi(ctrl_sock->sk)->chan;
 	conn = NULL;
 	l2cap_chan_lock(chan);
 	if (chan->conn)
@@ -1354,13 +1357,17 @@ out_conn:
 
 int hidp_connection_del(struct hidp_conndel_req *req)
 {
+	u32 valid_flags = BIT(HIDP_VIRTUAL_CABLE_UNPLUG);
 	struct hidp_session *session;
 
+	if (req->flags & ~valid_flags)
+		return -EINVAL;
+
 	session = hidp_session_find(&req->bdaddr);
 	if (!session)
 		return -ENOENT;
 
-	if (req->flags & (1 << HIDP_VIRTUAL_CABLE_UNPLUG))
+	if (req->flags & BIT(HIDP_VIRTUAL_CABLE_UNPLUG))
 		hidp_send_ctrl_message(session,
 				       HIDP_TRANS_HID_CONTROL |
 				         HIDP_CTRL_VIRTUAL_CABLE_UNPLUG,
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index b6f9777e057d..dad419782a12 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -46,7 +46,6 @@
 bool disable_ertm;
 
 static u32 l2cap_feat_mask = L2CAP_FEAT_FIXED_CHAN | L2CAP_FEAT_UCD;
-static u8 l2cap_fixed_chan[8] = { L2CAP_FC_SIG_BREDR | L2CAP_FC_CONNLESS, };
 
 static LIST_HEAD(chan_list);
 static DEFINE_RWLOCK(chan_list_lock);
@@ -64,10 +63,10 @@ static void l2cap_send_disconn_req(struct l2cap_chan *chan, int err);
 static void l2cap_tx(struct l2cap_chan *chan, struct l2cap_ctrl *control,
 		     struct sk_buff_head *skbs, u8 event);
 
-static inline __u8 bdaddr_type(struct hci_conn *hcon, __u8 type)
+static inline u8 bdaddr_type(u8 link_type, u8 bdaddr_type)
 {
-	if (hcon->type == LE_LINK) {
-		if (type == ADDR_LE_DEV_PUBLIC)
+	if (link_type == LE_LINK) {
+		if (bdaddr_type == ADDR_LE_DEV_PUBLIC)
 			return BDADDR_LE_PUBLIC;
 		else
 			return BDADDR_LE_RANDOM;
@@ -76,6 +75,16 @@ static inline __u8 bdaddr_type(struct hci_conn *hcon, __u8 type)
 	return BDADDR_BREDR;
 }
 
+static inline u8 bdaddr_src_type(struct hci_conn *hcon)
+{
+	return bdaddr_type(hcon->type, hcon->src_type);
+}
+
+static inline u8 bdaddr_dst_type(struct hci_conn *hcon)
+{
+	return bdaddr_type(hcon->type, hcon->dst_type);
+}
+
 /* ---- L2CAP channels ---- */
 
 static struct l2cap_chan *__l2cap_get_chan_by_dcid(struct l2cap_conn *conn,
@@ -283,7 +292,7 @@ static struct sk_buff *l2cap_ertm_seq_in_queue(struct sk_buff_head *head,
 	struct sk_buff *skb;
 
 	skb_queue_walk(head, skb) {
-		if (bt_cb(skb)->control.txseq == seq)
+		if (bt_cb(skb)->l2cap.txseq == seq)
 			return skb;
 	}
 
@@ -424,6 +433,9 @@ struct l2cap_chan *l2cap_chan_create(void)
 
 	mutex_init(&chan->lock);
 
+	/* Set default lock nesting level */
+	atomic_set(&chan->nesting, L2CAP_NESTING_NORMAL);
+
 	write_lock(&chan_list_lock);
 	list_add(&chan->global_l, &chan_list);
 	write_unlock(&chan_list_lock);
@@ -567,7 +579,8 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err)
 
 	__clear_chan_timer(chan);
 
-	BT_DBG("chan %p, conn %p, err %d", chan, conn, err);
+	BT_DBG("chan %p, conn %p, err %d, state %s", chan, conn, err,
+	       state_to_string(chan->state));
 
 	chan->ops->teardown(chan, err);
 
@@ -643,7 +656,7 @@ static void l2cap_conn_update_id_addr(struct work_struct *work)
 	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);
+		chan->dst_type = bdaddr_dst_type(hcon);
 		l2cap_chan_unlock(chan);
 	}
 
@@ -836,7 +849,10 @@ static void l2cap_send_cmd(struct l2cap_conn *conn, u8 ident, u8 code, u16 len,
 	if (!skb)
 		return;
 
-	if (lmp_no_flush_capable(conn->hcon->hdev))
+	/* Use NO_FLUSH if supported or we have an LE link (which does
+	 * not support auto-flushing packets) */
+	if (lmp_no_flush_capable(conn->hcon->hdev) ||
+	    conn->hcon->type == LE_LINK)
 		flags = ACL_START_NO_FLUSH;
 	else
 		flags = ACL_START;
@@ -870,8 +886,13 @@ static void l2cap_do_send(struct l2cap_chan *chan, struct sk_buff *skb)
 		return;
 	}
 
-	if (!test_bit(FLAG_FLUSHABLE, &chan->flags) &&
-	    lmp_no_flush_capable(hcon->hdev))
+	/* Use NO_FLUSH for LE links (where this is the only option) or
+	 * if the BR/EDR link supports it and flushing has not been
+	 * explicitly requested (through FLAG_FLUSHABLE).
+	 */
+	if (hcon->type == LE_LINK ||
+	    (!test_bit(FLAG_FLUSHABLE, &chan->flags) &&
+	     lmp_no_flush_capable(hcon->hdev)))
 		flags = ACL_START_NO_FLUSH;
 	else
 		flags = ACL_START;
@@ -933,11 +954,11 @@ static inline void __unpack_control(struct l2cap_chan *chan,
 {
 	if (test_bit(FLAG_EXT_CTRL, &chan->flags)) {
 		__unpack_extended_control(get_unaligned_le32(skb->data),
-					  &bt_cb(skb)->control);
+					  &bt_cb(skb)->l2cap);
 		skb_pull(skb, L2CAP_EXT_CTRL_SIZE);
 	} else {
 		__unpack_enhanced_control(get_unaligned_le16(skb->data),
-					  &bt_cb(skb)->control);
+					  &bt_cb(skb)->l2cap);
 		skb_pull(skb, L2CAP_ENH_CTRL_SIZE);
 	}
 }
@@ -1108,10 +1129,10 @@ static bool __amp_capable(struct l2cap_chan *chan)
 	struct hci_dev *hdev;
 	bool amp_available = false;
 
-	if (!conn->hs_enabled)
+	if (!(conn->local_fixed_chan & L2CAP_FC_A2MP))
 		return false;
 
-	if (!(conn->fixed_chan_mask & L2CAP_FC_A2MP))
+	if (!(conn->remote_fixed_chan & L2CAP_FC_A2MP))
 		return false;
 
 	read_lock(&hci_dev_list_lock);
@@ -1179,8 +1200,8 @@ static void l2cap_move_setup(struct l2cap_chan *chan)
 
 	chan->retry_count = 0;
 	skb_queue_walk(&chan->tx_q, skb) {
-		if (bt_cb(skb)->control.retries)
-			bt_cb(skb)->control.retries = 1;
+		if (bt_cb(skb)->l2cap.retries)
+			bt_cb(skb)->l2cap.retries = 1;
 		else
 			break;
 	}
@@ -1223,6 +1244,13 @@ static void l2cap_move_done(struct l2cap_chan *chan)
 
 static void l2cap_chan_ready(struct l2cap_chan *chan)
 {
+	/* The channel may have already been flagged as connected in
+	 * case of receiving data before the L2CAP info req/rsp
+	 * procedure is complete.
+	 */
+	if (chan->state == BT_CONNECTED)
+		return;
+
 	/* This clears all conf flags, including CONF_NOT_COMPLETE */
 	chan->conf_state = 0;
 	__clear_chan_timer(chan);
@@ -1818,8 +1846,8 @@ static void l2cap_streaming_send(struct l2cap_chan *chan,
 
 		skb = skb_dequeue(&chan->tx_q);
 
-		bt_cb(skb)->control.retries = 1;
-		control = &bt_cb(skb)->control;
+		bt_cb(skb)->l2cap.retries = 1;
+		control = &bt_cb(skb)->l2cap;
 
 		control->reqseq = 0;
 		control->txseq = chan->next_tx_seq;
@@ -1863,8 +1891,8 @@ static int l2cap_ertm_send(struct l2cap_chan *chan)
 
 		skb = chan->tx_send_head;
 
-		bt_cb(skb)->control.retries = 1;
-		control = &bt_cb(skb)->control;
+		bt_cb(skb)->l2cap.retries = 1;
+		control = &bt_cb(skb)->l2cap;
 
 		if (test_and_clear_bit(CONN_SEND_FBIT, &chan->conn_state))
 			control->final = 1;
@@ -1935,11 +1963,11 @@ static void l2cap_ertm_resend(struct l2cap_chan *chan)
 			continue;
 		}
 
-		bt_cb(skb)->control.retries++;
-		control = bt_cb(skb)->control;
+		bt_cb(skb)->l2cap.retries++;
+		control = bt_cb(skb)->l2cap;
 
 		if (chan->max_tx != 0 &&
-		    bt_cb(skb)->control.retries > chan->max_tx) {
+		    bt_cb(skb)->l2cap.retries > chan->max_tx) {
 			BT_DBG("Retry limit exceeded (%d)", chan->max_tx);
 			l2cap_send_disconn_req(chan, ECONNRESET);
 			l2cap_seq_list_clear(&chan->retrans_list);
@@ -2017,7 +2045,7 @@ static void l2cap_retransmit_all(struct l2cap_chan *chan,
 
 	if (chan->unacked_frames) {
 		skb_queue_walk(&chan->tx_q, skb) {
-			if (bt_cb(skb)->control.txseq == control->reqseq ||
+			if (bt_cb(skb)->l2cap.txseq == control->reqseq ||
 			    skb == chan->tx_send_head)
 				break;
 		}
@@ -2027,7 +2055,7 @@ static void l2cap_retransmit_all(struct l2cap_chan *chan,
 				break;
 
 			l2cap_seq_list_append(&chan->retrans_list,
-					      bt_cb(skb)->control.txseq);
+					      bt_cb(skb)->l2cap.txseq);
 		}
 
 		l2cap_ertm_resend(chan);
@@ -2092,8 +2120,7 @@ static inline int l2cap_skbuff_fromiovec(struct l2cap_chan *chan,
 	struct sk_buff **frag;
 	int sent = 0;
 
-	if (chan->ops->memcpy_fromiovec(chan, skb_put(skb, count),
-					msg->msg_iov, count))
+	if (copy_from_iter(skb_put(skb, count), count, &msg->msg_iter) != count)
 		return -EFAULT;
 
 	sent += count;
@@ -2113,8 +2140,8 @@ static inline int l2cap_skbuff_fromiovec(struct l2cap_chan *chan,
 
 		*frag = tmp;
 
-		if (chan->ops->memcpy_fromiovec(chan, skb_put(*frag, count),
-						msg->msg_iov, count))
+		if (copy_from_iter(skb_put(*frag, count), count,
+				   &msg->msg_iter) != count)
 			return -EFAULT;
 
 		sent += count;
@@ -2240,8 +2267,8 @@ static struct sk_buff *l2cap_create_iframe_pdu(struct l2cap_chan *chan,
 		return ERR_PTR(err);
 	}
 
-	bt_cb(skb)->control.fcs = chan->fcs;
-	bt_cb(skb)->control.retries = 0;
+	bt_cb(skb)->l2cap.fcs = chan->fcs;
+	bt_cb(skb)->l2cap.retries = 0;
 	return skb;
 }
 
@@ -2294,7 +2321,7 @@ static int l2cap_segment_sdu(struct l2cap_chan *chan,
 			return PTR_ERR(skb);
 		}
 
-		bt_cb(skb)->control.sar = sar;
+		bt_cb(skb)->l2cap.sar = sar;
 		__skb_queue_tail(seg_queue, skb);
 
 		len -= pdu_len;
@@ -2829,7 +2856,7 @@ static void l2cap_raw_recv(struct l2cap_conn *conn, struct sk_buff *skb)
 			continue;
 
 		/* Don't send frame to the channel it came from */
-		if (bt_cb(skb)->chan == chan)
+		if (bt_cb(skb)->l2cap.chan == chan)
 			continue;
 
 		nskb = skb_clone(skb, GFP_KERNEL);
@@ -3084,12 +3111,14 @@ static inline __u8 l2cap_select_mode(__u8 mode, __u16 remote_feat_mask)
 
 static inline bool __l2cap_ews_supported(struct l2cap_conn *conn)
 {
-	return conn->hs_enabled && conn->feat_mask & L2CAP_FEAT_EXT_WINDOW;
+	return ((conn->local_fixed_chan & L2CAP_FC_A2MP) &&
+		(conn->feat_mask & L2CAP_FEAT_EXT_WINDOW));
 }
 
 static inline bool __l2cap_efs_supported(struct l2cap_conn *conn)
 {
-	return conn->hs_enabled && conn->feat_mask & L2CAP_FEAT_EXT_FLOW;
+	return ((conn->local_fixed_chan & L2CAP_FC_A2MP) &&
+		(conn->feat_mask & L2CAP_FEAT_EXT_FLOW));
 }
 
 static void __l2cap_set_ertm_timeouts(struct l2cap_chan *chan,
@@ -3318,7 +3347,7 @@ static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data)
 			break;
 
 		case L2CAP_CONF_EWS:
-			if (!chan->conn->hs_enabled)
+			if (!(chan->conn->local_fixed_chan & L2CAP_FC_A2MP))
 				return -ECONNREFUSED;
 
 			set_bit(FLAG_EXT_CTRL, &chan->flags);
@@ -3778,8 +3807,8 @@ static struct l2cap_chan *l2cap_connect(struct l2cap_conn *conn,
 
 	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->src_type = bdaddr_src_type(conn->hcon);
+	chan->dst_type = bdaddr_dst_type(conn->hcon);
 	chan->psm  = psm;
 	chan->dcid = scid;
 	chan->local_amp_id = amp_id;
@@ -3871,11 +3900,9 @@ static int l2cap_connect_req(struct l2cap_conn *conn,
 		return -EPROTO;
 
 	hci_dev_lock(hdev);
-	if (test_bit(HCI_MGMT, &hdev->dev_flags) &&
+	if (hci_dev_test_flag(hdev, HCI_MGMT) &&
 	    !test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &hcon->flags))
-		mgmt_device_connected(hdev, &hcon->dst, hcon->type,
-				      hcon->dst_type, 0, NULL, 0,
-				      hcon->dev_class);
+		mgmt_device_connected(hdev, hcon, 0, NULL, 0);
 	hci_dev_unlock(hdev);
 
 	l2cap_connect(conn, cmd, data, L2CAP_CONN_RSP, 0);
@@ -4084,7 +4111,7 @@ static inline int l2cap_config_req(struct l2cap_conn *conn,
 		chan->num_conf_req++;
 	}
 
-	/* Got Conf Rsp PENDING from remote side and asume we sent
+	/* Got Conf Rsp PENDING from remote side and assume we sent
 	   Conf Rsp PENDING in the code above */
 	if (test_bit(CONF_REM_CONF_PEND, &chan->conf_state) &&
 	    test_bit(CONF_LOC_CONF_PEND, &chan->conf_state)) {
@@ -4324,7 +4351,7 @@ static inline int l2cap_information_req(struct l2cap_conn *conn,
 		if (!disable_ertm)
 			feat_mask |= L2CAP_FEAT_ERTM | L2CAP_FEAT_STREAMING
 				| L2CAP_FEAT_FCS;
-		if (conn->hs_enabled)
+		if (conn->local_fixed_chan & L2CAP_FC_A2MP)
 			feat_mask |= L2CAP_FEAT_EXT_FLOW
 				| L2CAP_FEAT_EXT_WINDOW;
 
@@ -4335,14 +4362,10 @@ static inline int l2cap_information_req(struct l2cap_conn *conn,
 		u8 buf[12];
 		struct l2cap_info_rsp *rsp = (struct l2cap_info_rsp *) buf;
 
-		if (conn->hs_enabled)
-			l2cap_fixed_chan[0] |= L2CAP_FC_A2MP;
-		else
-			l2cap_fixed_chan[0] &= ~L2CAP_FC_A2MP;
-
 		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));
+		rsp->data[0] = conn->local_fixed_chan;
+		memset(rsp->data + 1, 0, 7);
 		l2cap_send_cmd(conn, cmd->ident, L2CAP_INFO_RSP, sizeof(buf),
 			       buf);
 	} else {
@@ -4408,7 +4431,7 @@ static inline int l2cap_information_rsp(struct l2cap_conn *conn,
 		break;
 
 	case L2CAP_IT_FIXED_CHAN:
-		conn->fixed_chan_mask = rsp->data[0];
+		conn->remote_fixed_chan = rsp->data[0];
 		conn->info_state |= L2CAP_INFO_FEAT_MASK_REQ_DONE;
 		conn->info_ident = 0;
 
@@ -4432,7 +4455,7 @@ static int l2cap_create_channel_req(struct l2cap_conn *conn,
 	if (cmd_len != sizeof(*req))
 		return -EPROTO;
 
-	if (!conn->hs_enabled)
+	if (!(conn->local_fixed_chan & L2CAP_FC_A2MP))
 		return -EINVAL;
 
 	psm = le16_to_cpu(req->psm);
@@ -4862,7 +4885,7 @@ static inline int l2cap_move_channel_req(struct l2cap_conn *conn,
 
 	BT_DBG("icid 0x%4.4x, dest_amp_id %d", icid, req->dest_amp_id);
 
-	if (!conn->hs_enabled)
+	if (!(conn->local_fixed_chan & L2CAP_FC_A2MP))
 		return -EINVAL;
 
 	chan = l2cap_get_chan_by_dcid(conn, icid);
@@ -5217,9 +5240,10 @@ static int l2cap_le_connect_rsp(struct l2cap_conn *conn,
 				u8 *data)
 {
 	struct l2cap_le_conn_rsp *rsp = (struct l2cap_le_conn_rsp *) data;
+	struct hci_conn *hcon = conn->hcon;
 	u16 dcid, mtu, mps, credits, result;
 	struct l2cap_chan *chan;
-	int err;
+	int err, sec_level;
 
 	if (cmd_len < sizeof(*rsp))
 		return -EPROTO;
@@ -5258,6 +5282,26 @@ static int l2cap_le_connect_rsp(struct l2cap_conn *conn,
 		l2cap_chan_ready(chan);
 		break;
 
+	case L2CAP_CR_AUTHENTICATION:
+	case L2CAP_CR_ENCRYPTION:
+		/* If we already have MITM protection we can't do
+		 * anything.
+		 */
+		if (hcon->sec_level > BT_SECURITY_MEDIUM) {
+			l2cap_chan_del(chan, ECONNREFUSED);
+			break;
+		}
+
+		sec_level = hcon->sec_level + 1;
+		if (chan->sec_level < sec_level)
+			chan->sec_level = sec_level;
+
+		/* We'll need to send a new Connect Request */
+		clear_bit(FLAG_LE_CONN_REQ_SENT, &chan->flags);
+
+		smp_conn_security(hcon, chan->sec_level);
+		break;
+
 	default:
 		l2cap_chan_del(chan, ECONNREFUSED);
 		break;
@@ -5390,7 +5434,8 @@ static int l2cap_le_connect_req(struct l2cap_conn *conn,
 	mutex_lock(&conn->chan_lock);
 	l2cap_chan_lock(pchan);
 
-	if (!smp_sufficient_security(conn->hcon, pchan->sec_level)) {
+	if (!smp_sufficient_security(conn->hcon, pchan->sec_level,
+				     SMP_ALLOW_STK)) {
 		result = L2CAP_CR_AUTHENTICATION;
 		chan = NULL;
 		goto response_unlock;
@@ -5413,8 +5458,8 @@ static int l2cap_le_connect_req(struct l2cap_conn *conn,
 
 	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->src_type = bdaddr_src_type(conn->hcon);
+	chan->dst_type = bdaddr_dst_type(conn->hcon);
 	chan->psm  = psm;
 	chan->dcid = scid;
 	chan->omtu = mtu;
@@ -5494,6 +5539,7 @@ static inline int l2cap_le_credits(struct l2cap_conn *conn,
 	if (credits > max_credits) {
 		BT_ERR("LE credits overflow");
 		l2cap_send_disconn_req(chan, ECONNRESET);
+		l2cap_chan_unlock(chan);
 
 		/* Return 0 so that we don't trigger an unnecessary
 		 * command reject packet.
@@ -5872,7 +5918,7 @@ static int l2cap_rx_queued_iframes(struct l2cap_chan *chan)
 
 		skb_unlink(skb, &chan->srej_q);
 		chan->buffer_seq = __next_seq(chan, chan->buffer_seq);
-		err = l2cap_reassemble_sdu(chan, skb, &bt_cb(skb)->control);
+		err = l2cap_reassemble_sdu(chan, skb, &bt_cb(skb)->l2cap);
 		if (err)
 			break;
 	}
@@ -5906,7 +5952,7 @@ static void l2cap_handle_srej(struct l2cap_chan *chan,
 		return;
 	}
 
-	if (chan->max_tx != 0 && bt_cb(skb)->control.retries >= chan->max_tx) {
+	if (chan->max_tx != 0 && bt_cb(skb)->l2cap.retries >= chan->max_tx) {
 		BT_DBG("Retry limit exceeded (%d)", chan->max_tx);
 		l2cap_send_disconn_req(chan, ECONNRESET);
 		return;
@@ -5959,7 +6005,7 @@ static void l2cap_handle_rej(struct l2cap_chan *chan,
 	skb = l2cap_ertm_seq_in_queue(&chan->tx_q, control->reqseq);
 
 	if (chan->max_tx && skb &&
-	    bt_cb(skb)->control.retries >= chan->max_tx) {
+	    bt_cb(skb)->l2cap.retries >= chan->max_tx) {
 		BT_DBG("Retry limit exceeded (%d)", chan->max_tx);
 		l2cap_send_disconn_req(chan, ECONNRESET);
 		return;
@@ -6519,7 +6565,7 @@ static int l2cap_stream_rx(struct l2cap_chan *chan, struct l2cap_ctrl *control,
 
 static int l2cap_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb)
 {
-	struct l2cap_ctrl *control = &bt_cb(skb)->control;
+	struct l2cap_ctrl *control = &bt_cb(skb)->l2cap;
 	u16 len;
 	u8 event;
 
@@ -6746,6 +6792,13 @@ static void l2cap_data_channel(struct l2cap_conn *conn, u16 cid,
 
 	BT_DBG("chan %p, len %d", chan, skb->len);
 
+	/* If we receive data on a fixed channel before the info req/rsp
+	 * procdure is done simply assume that the channel is supported
+	 * and mark it as ready.
+	 */
+	if (chan->chan_type == L2CAP_CHAN_FIXED)
+		l2cap_chan_ready(chan);
+
 	if (chan->state != BT_CONNECTED)
 		goto drop;
 
@@ -6811,8 +6864,8 @@ static void l2cap_conless_channel(struct l2cap_conn *conn, __le16 psm,
 		goto drop;
 
 	/* Store remote BD_ADDR and PSM for msg_name */
-	bacpy(&bt_cb(skb)->bdaddr, &hcon->dst);
-	bt_cb(skb)->psm = psm;
+	bacpy(&bt_cb(skb)->l2cap.bdaddr, &hcon->dst);
+	bt_cb(skb)->l2cap.psm = psm;
 
 	if (!chan->ops->recv(chan, skb)) {
 		l2cap_chan_put(chan);
@@ -6852,7 +6905,7 @@ static void l2cap_recv_frame(struct l2cap_conn *conn, struct sk_buff *skb)
 	 */
 	if (hcon->type == LE_LINK &&
 	    hci_bdaddr_list_lookup(&hcon->hdev->blacklist, &hcon->dst,
-				   bdaddr_type(hcon, hcon->dst_type))) {
+				   bdaddr_dst_type(hcon))) {
 		kfree_skb(skb);
 		return;
 	}
@@ -6931,9 +6984,16 @@ static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon)
 
 	conn->feat_mask = 0;
 
-	if (hcon->type == ACL_LINK)
-		conn->hs_enabled = test_bit(HCI_HS_ENABLED,
-					    &hcon->hdev->dev_flags);
+	conn->local_fixed_chan = L2CAP_FC_SIG_BREDR | L2CAP_FC_CONNLESS;
+
+	if (hcon->type == ACL_LINK &&
+	    hci_dev_test_flag(hcon->hdev, HCI_HS_ENABLED))
+		conn->local_fixed_chan |= L2CAP_FC_A2MP;
+
+	if (hci_dev_test_flag(hcon->hdev, HCI_LE_ENABLED) &&
+	    (bredr_sc_enabled(hcon->hdev) ||
+	     hci_dev_test_flag(hcon->hdev, HCI_FORCE_BREDR_SMP)))
+		conn->local_fixed_chan |= L2CAP_FC_SMP_BREDR;
 
 	mutex_init(&conn->ident_lock);
 	mutex_init(&conn->chan_lock);
@@ -7052,7 +7112,7 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid,
 		else
 			dst_type = ADDR_LE_DEV_RANDOM;
 
-		if (test_bit(HCI_ADVERTISING, &hdev->dev_flags))
+		if (hci_dev_test_flag(hdev, HCI_ADVERTISING))
 			role = HCI_ROLE_SLAVE;
 		else
 			role = HCI_ROLE_MASTER;
@@ -7087,7 +7147,7 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid,
 
 	/* Update source addr of the socket */
 	bacpy(&chan->src, &hcon->src);
-	chan->src_type = bdaddr_type(hcon, hcon->src_type);
+	chan->src_type = bdaddr_src_type(hcon);
 
 	__l2cap_chan_add(conn, chan);
 
@@ -7161,8 +7221,10 @@ int l2cap_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr)
  * global list (by passing NULL as first parameter).
  */
 static struct l2cap_chan *l2cap_global_fixed_chan(struct l2cap_chan *c,
-						  bdaddr_t *src, u8 link_type)
+						  struct hci_conn *hcon)
 {
+	u8 src_type = bdaddr_src_type(hcon);
+
 	read_lock(&chan_list_lock);
 
 	if (c)
@@ -7175,11 +7237,9 @@ static struct l2cap_chan *l2cap_global_fixed_chan(struct l2cap_chan *c,
 			continue;
 		if (c->state != BT_LISTEN)
 			continue;
-		if (bacmp(&c->src, src) && bacmp(&c->src, BDADDR_ANY))
-			continue;
-		if (link_type == ACL_LINK && c->src_type != BDADDR_BREDR)
+		if (bacmp(&c->src, &hcon->src) && bacmp(&c->src, BDADDR_ANY))
 			continue;
-		if (link_type == LE_LINK && c->src_type == BDADDR_BREDR)
+		if (src_type != c->src_type)
 			continue;
 
 		l2cap_chan_hold(c);
@@ -7192,13 +7252,16 @@ static struct l2cap_chan *l2cap_global_fixed_chan(struct l2cap_chan *c,
 	return NULL;
 }
 
-void l2cap_connect_cfm(struct hci_conn *hcon, u8 status)
+static void l2cap_connect_cfm(struct hci_conn *hcon, u8 status)
 {
 	struct hci_dev *hdev = hcon->hdev;
 	struct l2cap_conn *conn;
 	struct l2cap_chan *pchan;
 	u8 dst_type;
 
+	if (hcon->type != ACL_LINK && hcon->type != LE_LINK)
+		return;
+
 	BT_DBG("hcon %p bdaddr %pMR status %d", hcon, &hcon->dst, status);
 
 	if (status) {
@@ -7210,7 +7273,7 @@ void l2cap_connect_cfm(struct hci_conn *hcon, u8 status)
 	if (!conn)
 		return;
 
-	dst_type = bdaddr_type(hcon, hcon->dst_type);
+	dst_type = bdaddr_dst_type(hcon);
 
 	/* If device is blocked, do not create channels for it */
 	if (hci_bdaddr_list_lookup(&hdev->blacklist, &hcon->dst, dst_type))
@@ -7221,7 +7284,7 @@ void l2cap_connect_cfm(struct hci_conn *hcon, u8 status)
 	 * we left off, because the list lock would prevent calling the
 	 * potentially sleeping l2cap_chan_lock() function.
 	 */
-	pchan = l2cap_global_fixed_chan(NULL, &hdev->bdaddr, hcon->type);
+	pchan = l2cap_global_fixed_chan(NULL, hcon);
 	while (pchan) {
 		struct l2cap_chan *chan, *next;
 
@@ -7234,7 +7297,7 @@ void l2cap_connect_cfm(struct hci_conn *hcon, u8 status)
 		if (chan) {
 			bacpy(&chan->src, &hcon->src);
 			bacpy(&chan->dst, &hcon->dst);
-			chan->src_type = bdaddr_type(hcon, hcon->src_type);
+			chan->src_type = bdaddr_src_type(hcon);
 			chan->dst_type = dst_type;
 
 			__l2cap_chan_add(conn, chan);
@@ -7242,8 +7305,7 @@ void l2cap_connect_cfm(struct hci_conn *hcon, u8 status)
 
 		l2cap_chan_unlock(pchan);
 next:
-		next = l2cap_global_fixed_chan(pchan, &hdev->bdaddr,
-					       hcon->type);
+		next = l2cap_global_fixed_chan(pchan, hcon);
 		l2cap_chan_put(pchan);
 		pchan = next;
 	}
@@ -7262,8 +7324,11 @@ int l2cap_disconn_ind(struct hci_conn *hcon)
 	return conn->disc_reason;
 }
 
-void l2cap_disconn_cfm(struct hci_conn *hcon, u8 reason)
+static void l2cap_disconn_cfm(struct hci_conn *hcon, u8 reason)
 {
+	if (hcon->type != ACL_LINK && hcon->type != LE_LINK)
+		return;
+
 	BT_DBG("hcon %p reason %d", hcon, reason);
 
 	l2cap_conn_del(hcon, bt_to_errno(reason));
@@ -7286,13 +7351,13 @@ static inline void l2cap_check_encryption(struct l2cap_chan *chan, u8 encrypt)
 	}
 }
 
-int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt)
+static void l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt)
 {
 	struct l2cap_conn *conn = hcon->l2cap_data;
 	struct l2cap_chan *chan;
 
 	if (!conn)
-		return 0;
+		return;
 
 	BT_DBG("conn %p status 0x%2.2x encrypt %u", conn, status, encrypt);
 
@@ -7330,7 +7395,8 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt)
 				l2cap_start_connection(chan);
 			else
 				__set_chan_timer(chan, L2CAP_DISC_TIMEOUT);
-		} else if (chan->state == BT_CONNECT2) {
+		} else if (chan->state == BT_CONNECT2 &&
+			   chan->mode != L2CAP_MODE_LE_FLOWCTL) {
 			struct l2cap_conn_rsp rsp;
 			__u16 res, stat;
 
@@ -7374,8 +7440,6 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt)
 	}
 
 	mutex_unlock(&conn->chan_lock);
-
-	return 0;
 }
 
 int l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags)
@@ -7483,6 +7547,13 @@ drop:
 	return 0;
 }
 
+static struct hci_cb l2cap_cb = {
+	.name		= "L2CAP",
+	.connect_cfm	= l2cap_connect_cfm,
+	.disconn_cfm	= l2cap_disconn_cfm,
+	.security_cfm	= l2cap_security_cfm,
+};
+
 static int l2cap_debugfs_show(struct seq_file *f, void *p)
 {
 	struct l2cap_chan *c;
@@ -7490,8 +7561,8 @@ static int l2cap_debugfs_show(struct seq_file *f, void *p)
 	read_lock(&chan_list_lock);
 
 	list_for_each_entry(c, &chan_list, global_l) {
-		seq_printf(f, "%pMR %pMR %d %d 0x%4.4x 0x%4.4x %d %d %d %d\n",
-			   &c->src, &c->dst,
+		seq_printf(f, "%pMR (%u) %pMR (%u) %d %d 0x%4.4x 0x%4.4x %d %d %d %d\n",
+			   &c->src, c->src_type, &c->dst, c->dst_type,
 			   c->state, __le16_to_cpu(c->psm),
 			   c->scid, c->dcid, c->imtu, c->omtu,
 			   c->sec_level, c->mode);
@@ -7524,6 +7595,8 @@ int __init l2cap_init(void)
 	if (err < 0)
 		return err;
 
+	hci_register_cb(&l2cap_cb);
+
 	if (IS_ERR_OR_NULL(bt_debugfs))
 		return 0;
 
@@ -7541,6 +7614,7 @@ int __init l2cap_init(void)
 void l2cap_exit(void)
 {
 	debugfs_remove(l2cap_debugfs);
+	hci_unregister_cb(&l2cap_cb);
 	l2cap_cleanup_sockets();
 }
 
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 31f106e61ca2..a7278f05eafb 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -285,6 +285,12 @@ static int l2cap_sock_listen(struct socket *sock, int backlog)
 	sk->sk_max_ack_backlog = backlog;
 	sk->sk_ack_backlog = 0;
 
+	/* Listening channels need to use nested locking in order not to
+	 * cause lockdep warnings when the created child channels end up
+	 * being locked in the same thread as the parent channel.
+	 */
+	atomic_set(&chan->nesting, L2CAP_NESTING_PARENT);
+
 	chan->state = BT_LISTEN;
 	sk->sk_state = BT_LISTEN;
 
@@ -296,12 +302,12 @@ done:
 static int l2cap_sock_accept(struct socket *sock, struct socket *newsock,
 			     int flags)
 {
-	DECLARE_WAITQUEUE(wait, current);
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 	struct sock *sk = sock->sk, *nsk;
 	long timeo;
 	int err = 0;
 
-	lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
+	lock_sock_nested(sk, L2CAP_NESTING_PARENT);
 
 	timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK);
 
@@ -310,8 +316,6 @@ static int l2cap_sock_accept(struct socket *sock, struct socket *newsock,
 	/* Wait for an incoming connection. (wake-one). */
 	add_wait_queue_exclusive(sk_sleep(sk), &wait);
 	while (1) {
-		set_current_state(TASK_INTERRUPTIBLE);
-
 		if (sk->sk_state != BT_LISTEN) {
 			err = -EBADFD;
 			break;
@@ -332,10 +336,11 @@ static int l2cap_sock_accept(struct socket *sock, struct socket *newsock,
 		}
 
 		release_sock(sk);
-		timeo = schedule_timeout(timeo);
-		lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
+
+		timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo);
+
+		lock_sock_nested(sk, L2CAP_NESTING_PARENT);
 	}
-	__set_current_state(TASK_RUNNING);
 	remove_wait_queue(sk_sleep(sk), &wait);
 
 	if (err)
@@ -939,8 +944,8 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
 	return err;
 }
 
-static int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
-			      struct msghdr *msg, size_t len)
+static int l2cap_sock_sendmsg(struct socket *sock, struct msghdr *msg,
+			      size_t len)
 {
 	struct sock *sk = sock->sk;
 	struct l2cap_chan *chan = l2cap_pi(sk)->chan;
@@ -971,8 +976,8 @@ static int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 	return err;
 }
 
-static int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
-			      struct msghdr *msg, size_t len, int flags)
+static int l2cap_sock_recvmsg(struct socket *sock, struct msghdr *msg,
+			      size_t len, int flags)
 {
 	struct sock *sk = sock->sk;
 	struct l2cap_pinfo *pi = l2cap_pi(sk);
@@ -999,9 +1004,9 @@ static int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 	release_sock(sk);
 
 	if (sock->type == SOCK_STREAM)
-		err = bt_sock_stream_recvmsg(iocb, sock, msg, len, flags);
+		err = bt_sock_stream_recvmsg(sock, msg, len, flags);
 	else
-		err = bt_sock_recvmsg(iocb, sock, msg, len, flags);
+		err = bt_sock_recvmsg(sock, msg, len, flags);
 
 	if (pi->chan->mode != L2CAP_MODE_ERTM)
 		return err;
@@ -1096,6 +1101,8 @@ static int l2cap_sock_shutdown(struct socket *sock, int how)
 	chan = l2cap_pi(sk)->chan;
 	conn = chan->conn;
 
+	BT_DBG("chan %p state %s", chan, state_to_string(chan->state));
+
 	if (conn)
 		mutex_lock(&conn->chan_lock);
 
@@ -1153,12 +1160,16 @@ static void l2cap_sock_cleanup_listen(struct sock *parent)
 {
 	struct sock *sk;
 
-	BT_DBG("parent %p", parent);
+	BT_DBG("parent %p state %s", parent,
+	       state_to_string(parent->sk_state));
 
 	/* Close not yet accepted channels */
 	while ((sk = bt_accept_dequeue(parent, NULL))) {
 		struct l2cap_chan *chan = l2cap_pi(sk)->chan;
 
+		BT_DBG("child chan %p state %s", chan,
+		       state_to_string(chan->state));
+
 		l2cap_chan_lock(chan);
 		__clear_chan_timer(chan);
 		l2cap_chan_close(chan, ECONNRESET);
@@ -1246,7 +1257,16 @@ static void l2cap_sock_teardown_cb(struct l2cap_chan *chan, int err)
 	struct sock *sk = chan->data;
 	struct sock *parent;
 
-	lock_sock(sk);
+	BT_DBG("chan %p state %s", chan, state_to_string(chan->state));
+
+	/* This callback can be called both for server (BT_LISTEN)
+	 * sockets as well as "normal" ones. To avoid lockdep warnings
+	 * with child socket locking (through l2cap_sock_cleanup_listen)
+	 * we need separation into separate nesting levels. The simplest
+	 * way to accomplish this is to inherit the nesting level used
+	 * for the channel.
+	 */
+	lock_sock_nested(sk, atomic_read(&chan->nesting));
 
 	parent = bt_sk(sk)->parent;
 
@@ -1310,18 +1330,11 @@ static struct sk_buff *l2cap_sock_alloc_skb_cb(struct l2cap_chan *chan,
 
 	skb->priority = sk->sk_priority;
 
-	bt_cb(skb)->chan = chan;
+	bt_cb(skb)->l2cap.chan = chan;
 
 	return skb;
 }
 
-static int l2cap_sock_memcpy_fromiovec_cb(struct l2cap_chan *chan,
-					  unsigned char *kdata,
-					  struct iovec *iov, int len)
-{
-	return memcpy_fromiovec(kdata, iov, len);
-}
-
 static void l2cap_sock_ready_cb(struct l2cap_chan *chan)
 {
 	struct sock *sk = chan->data;
@@ -1406,7 +1419,6 @@ static const struct l2cap_ops l2cap_chan_ops = {
 	.set_shutdown		= l2cap_sock_set_shutdown_cb,
 	.get_sndtimeo		= l2cap_sock_get_sndtimeo_cb,
 	.alloc_skb		= l2cap_sock_alloc_skb_cb,
-	.memcpy_fromiovec	= l2cap_sock_memcpy_fromiovec_cb,
 };
 
 static void l2cap_sock_destruct(struct sock *sk)
@@ -1432,8 +1444,8 @@ static void l2cap_skb_msg_name(struct sk_buff *skb, void *msg_name,
 
 	memset(la, 0, sizeof(struct sockaddr_l2));
 	la->l2_family = AF_BLUETOOTH;
-	la->l2_psm = bt_cb(skb)->psm;
-	bacpy(&la->l2_bdaddr, &bt_cb(skb)->bdaddr);
+	la->l2_psm = bt_cb(skb)->l2cap.psm;
+	bacpy(&la->l2_bdaddr, &bt_cb(skb)->l2cap.bdaddr);
 
 	*msg_namelen = sizeof(struct sockaddr_l2);
 }
@@ -1601,6 +1613,8 @@ int __init l2cap_init_sockets(void)
 {
 	int err;
 
+	BUILD_BUG_ON(sizeof(struct sockaddr_l2) > sizeof(struct sockaddr));
+
 	err = proto_register(&l2cap_proto, 0);
 	if (err < 0)
 		return err;
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index efb71b022ab6..7fd87e7135b5 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -29,13 +29,16 @@
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
+#include <net/bluetooth/hci_sock.h>
 #include <net/bluetooth/l2cap.h>
 #include <net/bluetooth/mgmt.h>
 
+#include "hci_request.h"
 #include "smp.h"
+#include "mgmt_util.h"
 
 #define MGMT_VERSION	1
-#define MGMT_REVISION	7
+#define MGMT_REVISION	9
 
 static const u16 mgmt_commands[] = {
 	MGMT_OP_READ_INDEX_LIST,
@@ -93,6 +96,12 @@ static const u16 mgmt_commands[] = {
 	MGMT_OP_READ_CONFIG_INFO,
 	MGMT_OP_SET_EXTERNAL_CONFIG,
 	MGMT_OP_SET_PUBLIC_ADDRESS,
+	MGMT_OP_START_SERVICE_DISCOVERY,
+	MGMT_OP_READ_LOCAL_OOB_EXT_DATA,
+	MGMT_OP_READ_EXT_INDEX_LIST,
+	MGMT_OP_READ_ADV_FEATURES,
+	MGMT_OP_ADD_ADVERTISING,
+	MGMT_OP_REMOVE_ADVERTISING,
 };
 
 static const u16 mgmt_events[] = {
@@ -125,19 +134,39 @@ static const u16 mgmt_events[] = {
 	MGMT_EV_UNCONF_INDEX_ADDED,
 	MGMT_EV_UNCONF_INDEX_REMOVED,
 	MGMT_EV_NEW_CONFIG_OPTIONS,
+	MGMT_EV_EXT_INDEX_ADDED,
+	MGMT_EV_EXT_INDEX_REMOVED,
+	MGMT_EV_LOCAL_OOB_DATA_UPDATED,
+	MGMT_EV_ADVERTISING_ADDED,
+	MGMT_EV_ADVERTISING_REMOVED,
 };
 
-#define CACHE_TIMEOUT	msecs_to_jiffies(2 * 1000)
+static const u16 mgmt_untrusted_commands[] = {
+	MGMT_OP_READ_INDEX_LIST,
+	MGMT_OP_READ_INFO,
+	MGMT_OP_READ_UNCONF_INDEX_LIST,
+	MGMT_OP_READ_CONFIG_INFO,
+	MGMT_OP_READ_EXT_INDEX_LIST,
+};
 
-struct pending_cmd {
-	struct list_head list;
-	u16 opcode;
-	int index;
-	void *param;
-	struct sock *sk;
-	void *user_data;
+static const u16 mgmt_untrusted_events[] = {
+	MGMT_EV_INDEX_ADDED,
+	MGMT_EV_INDEX_REMOVED,
+	MGMT_EV_NEW_SETTINGS,
+	MGMT_EV_CLASS_OF_DEV_CHANGED,
+	MGMT_EV_LOCAL_NAME_CHANGED,
+	MGMT_EV_UNCONF_INDEX_ADDED,
+	MGMT_EV_UNCONF_INDEX_REMOVED,
+	MGMT_EV_NEW_CONFIG_OPTIONS,
+	MGMT_EV_EXT_INDEX_ADDED,
+	MGMT_EV_EXT_INDEX_REMOVED,
 };
 
+#define CACHE_TIMEOUT	msecs_to_jiffies(2 * 1000)
+
+#define ZERO_KEY "\x00\x00\x00\x00\x00\x00\x00\x00" \
+		 "\x00\x00\x00\x00\x00\x00\x00\x00"
+
 /* HCI to MGMT error code conversion table */
 static u8 mgmt_status_table[] = {
 	MGMT_STATUS_SUCCESS,
@@ -211,98 +240,32 @@ static u8 mgmt_status(u8 hci_status)
 	return MGMT_STATUS_FAILED;
 }
 
-static int mgmt_event(u16 event, struct hci_dev *hdev, void *data, u16 data_len,
-		      struct sock *skip_sk)
+static int mgmt_index_event(u16 event, struct hci_dev *hdev, void *data,
+			    u16 len, int flag)
 {
-	struct sk_buff *skb;
-	struct mgmt_hdr *hdr;
-
-	skb = alloc_skb(sizeof(*hdr) + data_len, GFP_KERNEL);
-	if (!skb)
-		return -ENOMEM;
-
-	hdr = (void *) skb_put(skb, sizeof(*hdr));
-	hdr->opcode = cpu_to_le16(event);
-	if (hdev)
-		hdr->index = cpu_to_le16(hdev->id);
-	else
-		hdr->index = cpu_to_le16(MGMT_INDEX_NONE);
-	hdr->len = cpu_to_le16(data_len);
-
-	if (data)
-		memcpy(skb_put(skb, data_len), data, data_len);
-
-	/* Time stamp */
-	__net_timestamp(skb);
-
-	hci_send_to_control(skb, skip_sk);
-	kfree_skb(skb);
-
-	return 0;
+	return mgmt_send_event(event, hdev, HCI_CHANNEL_CONTROL, data, len,
+			       flag, NULL);
 }
 
-static int cmd_status(struct sock *sk, u16 index, u16 cmd, u8 status)
+static int mgmt_limited_event(u16 event, struct hci_dev *hdev, void *data,
+			      u16 len, int flag, struct sock *skip_sk)
 {
-	struct sk_buff *skb;
-	struct mgmt_hdr *hdr;
-	struct mgmt_ev_cmd_status *ev;
-	int err;
-
-	BT_DBG("sock %p, index %u, cmd %u, status %u", sk, index, cmd, status);
-
-	skb = alloc_skb(sizeof(*hdr) + sizeof(*ev), GFP_KERNEL);
-	if (!skb)
-		return -ENOMEM;
-
-	hdr = (void *) skb_put(skb, sizeof(*hdr));
-
-	hdr->opcode = cpu_to_le16(MGMT_EV_CMD_STATUS);
-	hdr->index = cpu_to_le16(index);
-	hdr->len = cpu_to_le16(sizeof(*ev));
-
-	ev = (void *) skb_put(skb, sizeof(*ev));
-	ev->status = status;
-	ev->opcode = cpu_to_le16(cmd);
-
-	err = sock_queue_rcv_skb(sk, skb);
-	if (err < 0)
-		kfree_skb(skb);
-
-	return err;
+	return mgmt_send_event(event, hdev, HCI_CHANNEL_CONTROL, data, len,
+			       flag, skip_sk);
 }
 
-static int cmd_complete(struct sock *sk, u16 index, u16 cmd, u8 status,
-			void *rp, size_t rp_len)
+static int mgmt_generic_event(u16 event, struct hci_dev *hdev, void *data,
+			      u16 len, struct sock *skip_sk)
 {
-	struct sk_buff *skb;
-	struct mgmt_hdr *hdr;
-	struct mgmt_ev_cmd_complete *ev;
-	int err;
-
-	BT_DBG("sock %p", sk);
-
-	skb = alloc_skb(sizeof(*hdr) + sizeof(*ev) + rp_len, GFP_KERNEL);
-	if (!skb)
-		return -ENOMEM;
-
-	hdr = (void *) skb_put(skb, sizeof(*hdr));
-
-	hdr->opcode = cpu_to_le16(MGMT_EV_CMD_COMPLETE);
-	hdr->index = cpu_to_le16(index);
-	hdr->len = cpu_to_le16(sizeof(*ev) + rp_len);
-
-	ev = (void *) skb_put(skb, sizeof(*ev) + rp_len);
-	ev->opcode = cpu_to_le16(cmd);
-	ev->status = status;
-
-	if (rp)
-		memcpy(ev->data, rp, rp_len);
-
-	err = sock_queue_rcv_skb(sk, skb);
-	if (err < 0)
-		kfree_skb(skb);
+	return mgmt_send_event(event, hdev, HCI_CHANNEL_CONTROL, data, len,
+			       HCI_MGMT_GENERIC_EVENTS, skip_sk);
+}
 
-	return err;
+static int mgmt_event(u16 event, struct hci_dev *hdev, void *data, u16 len,
+		      struct sock *skip_sk)
+{
+	return mgmt_send_event(event, hdev, HCI_CHANNEL_CONTROL, data, len,
+			       HCI_SOCK_TRUSTED, skip_sk);
 }
 
 static int read_version(struct sock *sk, struct hci_dev *hdev, void *data,
@@ -315,22 +278,28 @@ static int read_version(struct sock *sk, struct hci_dev *hdev, void *data,
 	rp.version = MGMT_VERSION;
 	rp.revision = cpu_to_le16(MGMT_REVISION);
 
-	return cmd_complete(sk, MGMT_INDEX_NONE, MGMT_OP_READ_VERSION, 0, &rp,
-			    sizeof(rp));
+	return mgmt_cmd_complete(sk, MGMT_INDEX_NONE, MGMT_OP_READ_VERSION, 0,
+				 &rp, sizeof(rp));
 }
 
 static int read_commands(struct sock *sk, struct hci_dev *hdev, void *data,
 			 u16 data_len)
 {
 	struct mgmt_rp_read_commands *rp;
-	const u16 num_commands = ARRAY_SIZE(mgmt_commands);
-	const u16 num_events = ARRAY_SIZE(mgmt_events);
-	__le16 *opcode;
+	u16 num_commands, num_events;
 	size_t rp_size;
 	int i, err;
 
 	BT_DBG("sock %p", sk);
 
+	if (hci_sock_test_flag(sk, HCI_SOCK_TRUSTED)) {
+		num_commands = ARRAY_SIZE(mgmt_commands);
+		num_events = ARRAY_SIZE(mgmt_events);
+	} else {
+		num_commands = ARRAY_SIZE(mgmt_untrusted_commands);
+		num_events = ARRAY_SIZE(mgmt_untrusted_events);
+	}
+
 	rp_size = sizeof(*rp) + ((num_commands + num_events) * sizeof(u16));
 
 	rp = kmalloc(rp_size, GFP_KERNEL);
@@ -340,14 +309,26 @@ static int read_commands(struct sock *sk, struct hci_dev *hdev, void *data,
 	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);
+	if (hci_sock_test_flag(sk, HCI_SOCK_TRUSTED)) {
+		__le16 *opcode = rp->opcodes;
 
-	for (i = 0; i < num_events; i++, opcode++)
-		put_unaligned_le16(mgmt_events[i], opcode);
+		for (i = 0; i < num_commands; i++, opcode++)
+			put_unaligned_le16(mgmt_commands[i], opcode);
 
-	err = cmd_complete(sk, MGMT_INDEX_NONE, MGMT_OP_READ_COMMANDS, 0, rp,
-			   rp_size);
+		for (i = 0; i < num_events; i++, opcode++)
+			put_unaligned_le16(mgmt_events[i], opcode);
+	} else {
+		__le16 *opcode = rp->opcodes;
+
+		for (i = 0; i < num_commands; i++, opcode++)
+			put_unaligned_le16(mgmt_untrusted_commands[i], opcode);
+
+		for (i = 0; i < num_events; i++, opcode++)
+			put_unaligned_le16(mgmt_untrusted_events[i], opcode);
+	}
+
+	err = mgmt_cmd_complete(sk, MGMT_INDEX_NONE, MGMT_OP_READ_COMMANDS, 0,
+				rp, rp_size);
 	kfree(rp);
 
 	return err;
@@ -369,7 +350,7 @@ static int read_index_list(struct sock *sk, struct hci_dev *hdev, void *data,
 	count = 0;
 	list_for_each_entry(d, &hci_dev_list, list) {
 		if (d->dev_type == HCI_BREDR &&
-		    !test_bit(HCI_UNCONFIGURED, &d->dev_flags))
+		    !hci_dev_test_flag(d, HCI_UNCONFIGURED))
 			count++;
 	}
 
@@ -382,9 +363,9 @@ static int read_index_list(struct sock *sk, struct hci_dev *hdev, void *data,
 
 	count = 0;
 	list_for_each_entry(d, &hci_dev_list, list) {
-		if (test_bit(HCI_SETUP, &d->dev_flags) ||
-		    test_bit(HCI_CONFIG, &d->dev_flags) ||
-		    test_bit(HCI_USER_CHANNEL, &d->dev_flags))
+		if (hci_dev_test_flag(d, HCI_SETUP) ||
+		    hci_dev_test_flag(d, HCI_CONFIG) ||
+		    hci_dev_test_flag(d, HCI_USER_CHANNEL))
 			continue;
 
 		/* Devices marked as raw-only are neither configured
@@ -394,7 +375,7 @@ static int read_index_list(struct sock *sk, struct hci_dev *hdev, void *data,
 			continue;
 
 		if (d->dev_type == HCI_BREDR &&
-		    !test_bit(HCI_UNCONFIGURED, &d->dev_flags)) {
+		    !hci_dev_test_flag(d, HCI_UNCONFIGURED)) {
 			rp->index[count++] = cpu_to_le16(d->id);
 			BT_DBG("Added hci%u", d->id);
 		}
@@ -405,8 +386,8 @@ static int read_index_list(struct sock *sk, struct hci_dev *hdev, void *data,
 
 	read_unlock(&hci_dev_list_lock);
 
-	err = cmd_complete(sk, MGMT_INDEX_NONE, MGMT_OP_READ_INDEX_LIST, 0, rp,
-			   rp_len);
+	err = mgmt_cmd_complete(sk, MGMT_INDEX_NONE, MGMT_OP_READ_INDEX_LIST,
+				0, rp, rp_len);
 
 	kfree(rp);
 
@@ -429,7 +410,7 @@ static int read_unconf_index_list(struct sock *sk, struct hci_dev *hdev,
 	count = 0;
 	list_for_each_entry(d, &hci_dev_list, list) {
 		if (d->dev_type == HCI_BREDR &&
-		    test_bit(HCI_UNCONFIGURED, &d->dev_flags))
+		    hci_dev_test_flag(d, HCI_UNCONFIGURED))
 			count++;
 	}
 
@@ -442,9 +423,9 @@ static int read_unconf_index_list(struct sock *sk, struct hci_dev *hdev,
 
 	count = 0;
 	list_for_each_entry(d, &hci_dev_list, list) {
-		if (test_bit(HCI_SETUP, &d->dev_flags) ||
-		    test_bit(HCI_CONFIG, &d->dev_flags) ||
-		    test_bit(HCI_USER_CHANNEL, &d->dev_flags))
+		if (hci_dev_test_flag(d, HCI_SETUP) ||
+		    hci_dev_test_flag(d, HCI_CONFIG) ||
+		    hci_dev_test_flag(d, HCI_USER_CHANNEL))
 			continue;
 
 		/* Devices marked as raw-only are neither configured
@@ -454,7 +435,7 @@ static int read_unconf_index_list(struct sock *sk, struct hci_dev *hdev,
 			continue;
 
 		if (d->dev_type == HCI_BREDR &&
-		    test_bit(HCI_UNCONFIGURED, &d->dev_flags)) {
+		    hci_dev_test_flag(d, HCI_UNCONFIGURED)) {
 			rp->index[count++] = cpu_to_le16(d->id);
 			BT_DBG("Added hci%u", d->id);
 		}
@@ -465,8 +446,84 @@ static int read_unconf_index_list(struct sock *sk, struct hci_dev *hdev,
 
 	read_unlock(&hci_dev_list_lock);
 
-	err = cmd_complete(sk, MGMT_INDEX_NONE, MGMT_OP_READ_UNCONF_INDEX_LIST,
-			   0, rp, rp_len);
+	err = mgmt_cmd_complete(sk, MGMT_INDEX_NONE,
+				MGMT_OP_READ_UNCONF_INDEX_LIST, 0, rp, rp_len);
+
+	kfree(rp);
+
+	return err;
+}
+
+static int read_ext_index_list(struct sock *sk, struct hci_dev *hdev,
+			       void *data, u16 data_len)
+{
+	struct mgmt_rp_read_ext_index_list *rp;
+	struct hci_dev *d;
+	size_t rp_len;
+	u16 count;
+	int err;
+
+	BT_DBG("sock %p", sk);
+
+	read_lock(&hci_dev_list_lock);
+
+	count = 0;
+	list_for_each_entry(d, &hci_dev_list, list) {
+		if (d->dev_type == HCI_BREDR || d->dev_type == HCI_AMP)
+			count++;
+	}
+
+	rp_len = sizeof(*rp) + (sizeof(rp->entry[0]) * count);
+	rp = kmalloc(rp_len, GFP_ATOMIC);
+	if (!rp) {
+		read_unlock(&hci_dev_list_lock);
+		return -ENOMEM;
+	}
+
+	count = 0;
+	list_for_each_entry(d, &hci_dev_list, list) {
+		if (hci_dev_test_flag(d, HCI_SETUP) ||
+		    hci_dev_test_flag(d, HCI_CONFIG) ||
+		    hci_dev_test_flag(d, HCI_USER_CHANNEL))
+			continue;
+
+		/* Devices marked as raw-only are neither configured
+		 * nor unconfigured controllers.
+		 */
+		if (test_bit(HCI_QUIRK_RAW_DEVICE, &d->quirks))
+			continue;
+
+		if (d->dev_type == HCI_BREDR) {
+			if (hci_dev_test_flag(d, HCI_UNCONFIGURED))
+				rp->entry[count].type = 0x01;
+			else
+				rp->entry[count].type = 0x00;
+		} else if (d->dev_type == HCI_AMP) {
+			rp->entry[count].type = 0x02;
+		} else {
+			continue;
+		}
+
+		rp->entry[count].bus = d->bus;
+		rp->entry[count++].index = cpu_to_le16(d->id);
+		BT_DBG("Added hci%u", d->id);
+	}
+
+	rp->num_controllers = cpu_to_le16(count);
+	rp_len = sizeof(*rp) + (sizeof(rp->entry[0]) * count);
+
+	read_unlock(&hci_dev_list_lock);
+
+	/* If this command is called at least once, then all the
+	 * default index and unconfigured index events are disabled
+	 * and from now on only extended index events are used.
+	 */
+	hci_sock_set_flag(sk, HCI_MGMT_EXT_INDEX_EVENTS);
+	hci_sock_clear_flag(sk, HCI_MGMT_INDEX_EVENTS);
+	hci_sock_clear_flag(sk, HCI_MGMT_UNCONF_INDEX_EVENTS);
+
+	err = mgmt_cmd_complete(sk, MGMT_INDEX_NONE,
+				MGMT_OP_READ_EXT_INDEX_LIST, 0, rp, rp_len);
 
 	kfree(rp);
 
@@ -476,7 +533,7 @@ static int read_unconf_index_list(struct sock *sk, struct hci_dev *hdev,
 static bool is_configured(struct hci_dev *hdev)
 {
 	if (test_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks) &&
-	    !test_bit(HCI_EXT_CONFIGURED, &hdev->dev_flags))
+	    !hci_dev_test_flag(hdev, HCI_EXT_CONFIGURED))
 		return false;
 
 	if (test_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks) &&
@@ -491,7 +548,7 @@ static __le32 get_missing_options(struct hci_dev *hdev)
 	u32 options = 0;
 
 	if (test_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks) &&
-	    !test_bit(HCI_EXT_CONFIGURED, &hdev->dev_flags))
+	    !hci_dev_test_flag(hdev, HCI_EXT_CONFIGURED))
 		options |= MGMT_OPTION_EXTERNAL_CONFIG;
 
 	if (test_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks) &&
@@ -505,16 +562,16 @@ static int new_options(struct hci_dev *hdev, struct sock *skip)
 {
 	__le32 options = get_missing_options(hdev);
 
-	return mgmt_event(MGMT_EV_NEW_CONFIG_OPTIONS, hdev, &options,
-			  sizeof(options), skip);
+	return mgmt_generic_event(MGMT_EV_NEW_CONFIG_OPTIONS, hdev, &options,
+				  sizeof(options), skip);
 }
 
 static int send_options_rsp(struct sock *sk, u16 opcode, struct hci_dev *hdev)
 {
 	__le32 options = get_missing_options(hdev);
 
-	return cmd_complete(sk, hdev->id, opcode, 0, &options,
-			    sizeof(options));
+	return mgmt_cmd_complete(sk, hdev->id, opcode, 0, &options,
+				 sizeof(options));
 }
 
 static int read_config_info(struct sock *sk, struct hci_dev *hdev,
@@ -541,8 +598,8 @@ static int read_config_info(struct sock *sk, struct hci_dev *hdev,
 
 	hci_dev_unlock(hdev);
 
-	return cmd_complete(sk, hdev->id, MGMT_OP_READ_CONFIG_INFO, 0, &rp,
-			    sizeof(rp));
+	return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_READ_CONFIG_INFO, 0,
+				 &rp, sizeof(rp));
 }
 
 static u32 get_supported_settings(struct hci_dev *hdev)
@@ -566,15 +623,16 @@ static u32 get_supported_settings(struct hci_dev *hdev)
 			settings |= MGMT_SETTING_HS;
 		}
 
-		if (lmp_sc_capable(hdev) ||
-		    test_bit(HCI_FORCE_SC, &hdev->dbg_flags))
+		if (lmp_sc_capable(hdev))
 			settings |= MGMT_SETTING_SECURE_CONN;
 	}
 
 	if (lmp_le_capable(hdev)) {
 		settings |= MGMT_SETTING_LE;
 		settings |= MGMT_SETTING_ADVERTISING;
+		settings |= MGMT_SETTING_SECURE_CONN;
 		settings |= MGMT_SETTING_PRIVACY;
+		settings |= MGMT_SETTING_STATIC_ADDRESS;
 	}
 
 	if (test_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks) ||
@@ -591,45 +649,64 @@ static u32 get_current_settings(struct hci_dev *hdev)
 	if (hdev_is_powered(hdev))
 		settings |= MGMT_SETTING_POWERED;
 
-	if (test_bit(HCI_CONNECTABLE, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_CONNECTABLE))
 		settings |= MGMT_SETTING_CONNECTABLE;
 
-	if (test_bit(HCI_FAST_CONNECTABLE, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_FAST_CONNECTABLE))
 		settings |= MGMT_SETTING_FAST_CONNECTABLE;
 
-	if (test_bit(HCI_DISCOVERABLE, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_DISCOVERABLE))
 		settings |= MGMT_SETTING_DISCOVERABLE;
 
-	if (test_bit(HCI_BONDABLE, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_BONDABLE))
 		settings |= MGMT_SETTING_BONDABLE;
 
-	if (test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_BREDR_ENABLED))
 		settings |= MGMT_SETTING_BREDR;
 
-	if (test_bit(HCI_LE_ENABLED, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_LE_ENABLED))
 		settings |= MGMT_SETTING_LE;
 
-	if (test_bit(HCI_LINK_SECURITY, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_LINK_SECURITY))
 		settings |= MGMT_SETTING_LINK_SECURITY;
 
-	if (test_bit(HCI_SSP_ENABLED, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_SSP_ENABLED))
 		settings |= MGMT_SETTING_SSP;
 
-	if (test_bit(HCI_HS_ENABLED, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_HS_ENABLED))
 		settings |= MGMT_SETTING_HS;
 
-	if (test_bit(HCI_ADVERTISING, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_ADVERTISING))
 		settings |= MGMT_SETTING_ADVERTISING;
 
-	if (test_bit(HCI_SC_ENABLED, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_SC_ENABLED))
 		settings |= MGMT_SETTING_SECURE_CONN;
 
-	if (test_bit(HCI_KEEP_DEBUG_KEYS, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_KEEP_DEBUG_KEYS))
 		settings |= MGMT_SETTING_DEBUG_KEYS;
 
-	if (test_bit(HCI_PRIVACY, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_PRIVACY))
 		settings |= MGMT_SETTING_PRIVACY;
 
+	/* The current setting for static address has two purposes. The
+	 * first is to indicate if the static address will be used and
+	 * the second is to indicate if it is actually set.
+	 *
+	 * This means if the static address is not configured, this flag
+	 * will never be set. If the address is configured, then if the
+	 * address is actually used decides if the flag is set or not.
+	 *
+	 * For single mode LE only controllers and dual-mode controllers
+	 * with BR/EDR disabled, the existence of the static address will
+	 * be evaluated.
+	 */
+	if (hci_dev_test_flag(hdev, HCI_FORCE_STATIC_ADDR) ||
+	    !hci_dev_test_flag(hdev, HCI_BREDR_ENABLED) ||
+	    !bacmp(&hdev->bdaddr, BDADDR_ANY)) {
+		if (bacmp(&hdev->static_addr, BDADDR_ANY))
+			settings |= MGMT_SETTING_STATIC_ADDRESS;
+	}
+
 	return settings;
 }
 
@@ -743,35 +820,19 @@ static u8 *create_uuid128_list(struct hci_dev *hdev, u8 *data, ptrdiff_t len)
 	return ptr;
 }
 
-static struct pending_cmd *mgmt_pending_find(u16 opcode, struct hci_dev *hdev)
+static struct mgmt_pending_cmd *pending_find(u16 opcode, struct hci_dev *hdev)
 {
-	struct pending_cmd *cmd;
-
-	list_for_each_entry(cmd, &hdev->mgmt_pending, list) {
-		if (cmd->opcode == opcode)
-			return cmd;
-	}
-
-	return NULL;
+	return mgmt_pending_find(HCI_CHANNEL_CONTROL, opcode, hdev);
 }
 
-static struct pending_cmd *mgmt_pending_find_data(u16 opcode,
+static struct mgmt_pending_cmd *pending_find_data(u16 opcode,
 						  struct hci_dev *hdev,
 						  const void *data)
 {
-	struct pending_cmd *cmd;
-
-	list_for_each_entry(cmd, &hdev->mgmt_pending, list) {
-		if (cmd->user_data != data)
-			continue;
-		if (cmd->opcode == opcode)
-			return cmd;
-	}
-
-	return NULL;
+	return mgmt_pending_find_data(HCI_CHANNEL_CONTROL, opcode, hdev, data);
 }
 
-static u8 create_scan_rsp_data(struct hci_dev *hdev, u8 *ptr)
+static u8 create_default_scan_rsp_data(struct hci_dev *hdev, u8 *ptr)
 {
 	u8 ad_len = 0;
 	size_t name_len;
@@ -797,21 +858,36 @@ static u8 create_scan_rsp_data(struct hci_dev *hdev, u8 *ptr)
 	return ad_len;
 }
 
-static void update_scan_rsp_data(struct hci_request *req)
+static u8 create_instance_scan_rsp_data(struct hci_dev *hdev, u8 *ptr)
+{
+	/* TODO: Set the appropriate entries based on advertising instance flags
+	 * here once flags other than 0 are supported.
+	 */
+	memcpy(ptr, hdev->adv_instance.scan_rsp_data,
+	       hdev->adv_instance.scan_rsp_len);
+
+	return hdev->adv_instance.scan_rsp_len;
+}
+
+static void update_scan_rsp_data_for_instance(struct hci_request *req,
+					      u8 instance)
 {
 	struct hci_dev *hdev = req->hdev;
 	struct hci_cp_le_set_scan_rsp_data cp;
 	u8 len;
 
-	if (!test_bit(HCI_LE_ENABLED, &hdev->dev_flags))
+	if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED))
 		return;
 
 	memset(&cp, 0, sizeof(cp));
 
-	len = create_scan_rsp_data(hdev, cp.data);
+	if (instance)
+		len = create_instance_scan_rsp_data(hdev, cp.data);
+	else
+		len = create_default_scan_rsp_data(hdev, cp.data);
 
 	if (hdev->scan_rsp_data_len == len &&
-	    memcmp(cp.data, hdev->scan_rsp_data, len) == 0)
+	    !memcmp(cp.data, hdev->scan_rsp_data, len))
 		return;
 
 	memcpy(hdev->scan_rsp_data, cp.data, sizeof(cp.data));
@@ -822,14 +898,33 @@ static void update_scan_rsp_data(struct hci_request *req)
 	hci_req_add(req, HCI_OP_LE_SET_SCAN_RSP_DATA, sizeof(cp), &cp);
 }
 
+static void update_scan_rsp_data(struct hci_request *req)
+{
+	struct hci_dev *hdev = req->hdev;
+	u8 instance;
+
+	/* The "Set Advertising" setting supersedes the "Add Advertising"
+	 * setting. Here we set the scan response data based on which
+	 * setting was set. When neither apply, default to the global settings,
+	 * represented by instance "0".
+	 */
+	if (hci_dev_test_flag(hdev, HCI_ADVERTISING_INSTANCE) &&
+	    !hci_dev_test_flag(hdev, HCI_ADVERTISING))
+		instance = 0x01;
+	else
+		instance = 0x00;
+
+	update_scan_rsp_data_for_instance(req, instance);
+}
+
 static u8 get_adv_discov_flags(struct hci_dev *hdev)
 {
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 
 	/* If there's a pending mgmt command the flags will not yet have
 	 * their final values, so check for this first.
 	 */
-	cmd = mgmt_pending_find(MGMT_OP_SET_DISCOVERABLE, hdev);
+	cmd = pending_find(MGMT_OP_SET_DISCOVERABLE, hdev);
 	if (cmd) {
 		struct mgmt_mode *cp = cmd->param;
 		if (cp->val == 0x01)
@@ -837,39 +932,131 @@ static u8 get_adv_discov_flags(struct hci_dev *hdev)
 		else if (cp->val == 0x02)
 			return LE_AD_LIMITED;
 	} else {
-		if (test_bit(HCI_LIMITED_DISCOVERABLE, &hdev->dev_flags))
+		if (hci_dev_test_flag(hdev, HCI_LIMITED_DISCOVERABLE))
 			return LE_AD_LIMITED;
-		else if (test_bit(HCI_DISCOVERABLE, &hdev->dev_flags))
+		else if (hci_dev_test_flag(hdev, HCI_DISCOVERABLE))
 			return LE_AD_GENERAL;
 	}
 
 	return 0;
 }
 
-static u8 create_adv_data(struct hci_dev *hdev, u8 *ptr)
+static u8 get_current_adv_instance(struct hci_dev *hdev)
+{
+	/* The "Set Advertising" setting supersedes the "Add Advertising"
+	 * setting. Here we set the advertising data based on which
+	 * setting was set. When neither apply, default to the global settings,
+	 * represented by instance "0".
+	 */
+	if (hci_dev_test_flag(hdev, HCI_ADVERTISING_INSTANCE) &&
+	    !hci_dev_test_flag(hdev, HCI_ADVERTISING))
+		return 0x01;
+
+	return 0x00;
+}
+
+static bool get_connectable(struct hci_dev *hdev)
+{
+	struct mgmt_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 = pending_find(MGMT_OP_SET_CONNECTABLE, hdev);
+	if (cmd) {
+		struct mgmt_mode *cp = cmd->param;
+
+		return cp->val;
+	}
+
+	return hci_dev_test_flag(hdev, HCI_CONNECTABLE);
+}
+
+static u32 get_adv_instance_flags(struct hci_dev *hdev, u8 instance)
+{
+	u32 flags;
+
+	if (instance > 0x01)
+		return 0;
+
+	if (instance == 0x01)
+		return hdev->adv_instance.flags;
+
+	/* Instance 0 always manages the "Tx Power" and "Flags" fields */
+	flags = MGMT_ADV_FLAG_TX_POWER | MGMT_ADV_FLAG_MANAGED_FLAGS;
+
+	/* For instance 0, the HCI_ADVERTISING_CONNECTABLE setting corresponds
+	 * to the "connectable" instance flag.
+	 */
+	if (hci_dev_test_flag(hdev, HCI_ADVERTISING_CONNECTABLE))
+		flags |= MGMT_ADV_FLAG_CONNECTABLE;
+
+	return flags;
+}
+
+static u8 get_adv_instance_scan_rsp_len(struct hci_dev *hdev, u8 instance)
+{
+	/* Ignore instance 0 and other unsupported instances */
+	if (instance != 0x01)
+		return 0;
+
+	/* TODO: Take into account the "appearance" and "local-name" flags here.
+	 * These are currently being ignored as they are not supported.
+	 */
+	return hdev->adv_instance.scan_rsp_len;
+}
+
+static u8 create_instance_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr)
 {
 	u8 ad_len = 0, flags = 0;
+	u32 instance_flags = get_adv_instance_flags(hdev, instance);
 
-	flags |= get_adv_discov_flags(hdev);
+	/* The Add Advertising command allows userspace to set both the general
+	 * and limited discoverable flags.
+	 */
+	if (instance_flags & MGMT_ADV_FLAG_DISCOV)
+		flags |= LE_AD_GENERAL;
 
-	if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
-		flags |= LE_AD_NO_BREDR;
+	if (instance_flags & MGMT_ADV_FLAG_LIMITED_DISCOV)
+		flags |= LE_AD_LIMITED;
 
-	if (flags) {
-		BT_DBG("adv flags 0x%02x", flags);
+	if (flags || (instance_flags & MGMT_ADV_FLAG_MANAGED_FLAGS)) {
+		/* If a discovery flag wasn't provided, simply use the global
+		 * settings.
+		 */
+		if (!flags)
+			flags |= get_adv_discov_flags(hdev);
 
-		ptr[0] = 2;
-		ptr[1] = EIR_FLAGS;
-		ptr[2] = flags;
+		if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED))
+			flags |= LE_AD_NO_BREDR;
 
-		ad_len += 3;
-		ptr += 3;
+		/* If flags would still be empty, then there is no need to
+		 * include the "Flags" AD field".
+		 */
+		if (flags) {
+			ptr[0] = 0x02;
+			ptr[1] = EIR_FLAGS;
+			ptr[2] = flags;
+
+			ad_len += 3;
+			ptr += 3;
+		}
 	}
 
-	if (hdev->adv_tx_power != HCI_TX_POWER_INVALID) {
-		ptr[0] = 2;
+	if (instance) {
+		memcpy(ptr, hdev->adv_instance.adv_data,
+		       hdev->adv_instance.adv_data_len);
+
+		ad_len += hdev->adv_instance.adv_data_len;
+		ptr += hdev->adv_instance.adv_data_len;
+	}
+
+	/* Provide Tx Power only if we can provide a valid value for it */
+	if (hdev->adv_tx_power != HCI_TX_POWER_INVALID &&
+	    (instance_flags & MGMT_ADV_FLAG_TX_POWER)) {
+		ptr[0] = 0x02;
 		ptr[1] = EIR_TX_POWER;
-		ptr[2] = (u8) hdev->adv_tx_power;
+		ptr[2] = (u8)hdev->adv_tx_power;
 
 		ad_len += 3;
 		ptr += 3;
@@ -878,19 +1065,20 @@ static u8 create_adv_data(struct hci_dev *hdev, u8 *ptr)
 	return ad_len;
 }
 
-static void update_adv_data(struct hci_request *req)
+static void update_adv_data_for_instance(struct hci_request *req, u8 instance)
 {
 	struct hci_dev *hdev = req->hdev;
 	struct hci_cp_le_set_adv_data cp;
 	u8 len;
 
-	if (!test_bit(HCI_LE_ENABLED, &hdev->dev_flags))
+	if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED))
 		return;
 
 	memset(&cp, 0, sizeof(cp));
 
-	len = create_adv_data(hdev, cp.data);
+	len = create_instance_adv_data(hdev, instance, cp.data);
 
+	/* There's nothing to do if the data hasn't changed */
 	if (hdev->adv_data_len == len &&
 	    memcmp(cp.data, hdev->adv_data, len) == 0)
 		return;
@@ -903,6 +1091,14 @@ static void update_adv_data(struct hci_request *req)
 	hci_req_add(req, HCI_OP_LE_SET_ADV_DATA, sizeof(cp), &cp);
 }
 
+static void update_adv_data(struct hci_request *req)
+{
+	struct hci_dev *hdev = req->hdev;
+	u8 instance = get_current_adv_instance(hdev);
+
+	update_adv_data_for_instance(req, instance);
+}
+
 int mgmt_update_adv_data(struct hci_dev *hdev)
 {
 	struct hci_request req;
@@ -972,10 +1168,10 @@ static void update_eir(struct hci_request *req)
 	if (!lmp_ext_inq_capable(hdev))
 		return;
 
-	if (!test_bit(HCI_SSP_ENABLED, &hdev->dev_flags))
+	if (!hci_dev_test_flag(hdev, HCI_SSP_ENABLED))
 		return;
 
-	if (test_bit(HCI_SERVICE_CACHE, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_SERVICE_CACHE))
 		return;
 
 	memset(&cp, 0, sizeof(cp));
@@ -1011,17 +1207,17 @@ static void update_class(struct hci_request *req)
 	if (!hdev_is_powered(hdev))
 		return;
 
-	if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
+	if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED))
 		return;
 
-	if (test_bit(HCI_SERVICE_CACHE, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_SERVICE_CACHE))
 		return;
 
 	cod[0] = hdev->minor_class;
 	cod[1] = hdev->major_class;
 	cod[2] = get_service_classes(hdev);
 
-	if (test_bit(HCI_LIMITED_DISCOVERABLE, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_LIMITED_DISCOVERABLE))
 		cod[1] |= 0x20;
 
 	if (memcmp(cod, hdev->dev_class, 3) == 0)
@@ -1030,22 +1226,6 @@ 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 disable_advertising(struct hci_request *req)
 {
 	u8 enable = 0x00;
@@ -1059,11 +1239,13 @@ static void enable_advertising(struct hci_request *req)
 	struct hci_cp_le_set_adv_param cp;
 	u8 own_addr_type, enable = 0x01;
 	bool connectable;
+	u8 instance;
+	u32 flags;
 
 	if (hci_conn_num(hdev, LE_LINK) > 0)
 		return;
 
-	if (test_bit(HCI_LE_ADV, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_LE_ADV))
 		disable_advertising(req);
 
 	/* Clear the HCI_LE_ADV bit temporarily so that the
@@ -1071,9 +1253,16 @@ static void enable_advertising(struct hci_request *req)
 	 * 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_LE_ADV, &hdev->dev_flags);
+	hci_dev_clear_flag(hdev, HCI_LE_ADV);
+
+	instance = get_current_adv_instance(hdev);
+	flags = get_adv_instance_flags(hdev, instance);
 
-	connectable = get_connectable(hdev);
+	/* If the "connectable" instance flag was not set, then choose between
+	 * ADV_IND and ADV_NONCONN_IND based on the global connectable setting.
+	 */
+	connectable = (flags & MGMT_ADV_FLAG_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
@@ -1085,7 +1274,14 @@ static void enable_advertising(struct hci_request *req)
 	memset(&cp, 0, sizeof(cp));
 	cp.min_interval = cpu_to_le16(hdev->le_adv_min_interval);
 	cp.max_interval = cpu_to_le16(hdev->le_adv_max_interval);
-	cp.type = connectable ? LE_ADV_IND : LE_ADV_NONCONN_IND;
+
+	if (connectable)
+		cp.type = LE_ADV_IND;
+	else if (get_adv_instance_scan_rsp_len(hdev, instance))
+		cp.type = LE_ADV_SCAN_IND;
+	else
+		cp.type = LE_ADV_NONCONN_IND;
+
 	cp.own_address_type = own_addr_type;
 	cp.channel_map = hdev->le_adv_channel_map;
 
@@ -1100,7 +1296,7 @@ static void service_cache_off(struct work_struct *work)
 					    service_cache.work);
 	struct hci_request req;
 
-	if (!test_and_clear_bit(HCI_SERVICE_CACHE, &hdev->dev_flags))
+	if (!hci_dev_test_and_clear_flag(hdev, HCI_SERVICE_CACHE))
 		return;
 
 	hci_req_init(&req, hdev);
@@ -1123,9 +1319,9 @@ static void rpa_expired(struct work_struct *work)
 
 	BT_DBG("");
 
-	set_bit(HCI_RPA_EXPIRED, &hdev->dev_flags);
+	hci_dev_set_flag(hdev, HCI_RPA_EXPIRED);
 
-	if (!test_bit(HCI_ADVERTISING, &hdev->dev_flags))
+	if (!hci_dev_test_flag(hdev, HCI_ADVERTISING))
 		return;
 
 	/* The generation of a new RPA and programming it into the
@@ -1138,7 +1334,7 @@ static void rpa_expired(struct work_struct *work)
 
 static void mgmt_init_hdev(struct sock *sk, struct hci_dev *hdev)
 {
-	if (test_and_set_bit(HCI_MGMT, &hdev->dev_flags))
+	if (hci_dev_test_and_set_flag(hdev, HCI_MGMT))
 		return;
 
 	INIT_DELAYED_WORK(&hdev->service_cache, service_cache_off);
@@ -1149,7 +1345,7 @@ static void mgmt_init_hdev(struct sock *sk, struct hci_dev *hdev)
 	 * for mgmt we require user-space to explicitly enable
 	 * it
 	 */
-	clear_bit(HCI_BONDABLE, &hdev->dev_flags);
+	hci_dev_clear_flag(hdev, HCI_BONDABLE);
 }
 
 static int read_controller_info(struct sock *sk, struct hci_dev *hdev,
@@ -1178,77 +1374,19 @@ static int read_controller_info(struct sock *sk, struct hci_dev *hdev,
 
 	hci_dev_unlock(hdev);
 
-	return cmd_complete(sk, hdev->id, MGMT_OP_READ_INFO, 0, &rp,
-			    sizeof(rp));
-}
-
-static void mgmt_pending_free(struct pending_cmd *cmd)
-{
-	sock_put(cmd->sk);
-	kfree(cmd->param);
-	kfree(cmd);
-}
-
-static struct pending_cmd *mgmt_pending_add(struct sock *sk, u16 opcode,
-					    struct hci_dev *hdev, void *data,
-					    u16 len)
-{
-	struct pending_cmd *cmd;
-
-	cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
-	if (!cmd)
-		return NULL;
-
-	cmd->opcode = opcode;
-	cmd->index = hdev->id;
-
-	cmd->param = kmalloc(len, GFP_KERNEL);
-	if (!cmd->param) {
-		kfree(cmd);
-		return NULL;
-	}
-
-	if (data)
-		memcpy(cmd->param, data, len);
-
-	cmd->sk = sk;
-	sock_hold(sk);
-
-	list_add(&cmd->list, &hdev->mgmt_pending);
-
-	return cmd;
-}
-
-static void mgmt_pending_foreach(u16 opcode, struct hci_dev *hdev,
-				 void (*cb)(struct pending_cmd *cmd,
-					    void *data),
-				 void *data)
-{
-	struct pending_cmd *cmd, *tmp;
-
-	list_for_each_entry_safe(cmd, tmp, &hdev->mgmt_pending, list) {
-		if (opcode > 0 && cmd->opcode != opcode)
-			continue;
-
-		cb(cmd, data);
-	}
-}
-
-static void mgmt_pending_remove(struct pending_cmd *cmd)
-{
-	list_del(&cmd->list);
-	mgmt_pending_free(cmd);
+	return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_READ_INFO, 0, &rp,
+				 sizeof(rp));
 }
 
 static int send_settings_rsp(struct sock *sk, u16 opcode, struct hci_dev *hdev)
 {
 	__le32 settings = cpu_to_le32(get_current_settings(hdev));
 
-	return cmd_complete(sk, hdev->id, opcode, 0, &settings,
-			    sizeof(settings));
+	return mgmt_cmd_complete(sk, hdev->id, opcode, 0, &settings,
+				 sizeof(settings));
 }
 
-static void clean_up_hci_complete(struct hci_dev *hdev, u8 status)
+static void clean_up_hci_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
 	BT_DBG("%s status 0x%02x", hdev->name, status);
 
@@ -1266,9 +1404,10 @@ static bool hci_stop_discovery(struct hci_request *req)
 
 	switch (hdev->discovery.state) {
 	case DISCOVERY_FINDING:
-		if (test_bit(HCI_INQUIRY, &hdev->flags)) {
+		if (test_bit(HCI_INQUIRY, &hdev->flags))
 			hci_req_add(req, HCI_OP_INQUIRY_CANCEL, 0, NULL);
-		} else {
+
+		if (hci_dev_test_flag(hdev, HCI_LE_SCAN)) {
 			cancel_delayed_work(&hdev->le_scan_disable);
 			hci_req_add_le_scan_disable(req);
 		}
@@ -1289,7 +1428,7 @@ static bool hci_stop_discovery(struct hci_request *req)
 
 	default:
 		/* Passive scanning */
-		if (test_bit(HCI_LE_SCAN, &hdev->dev_flags)) {
+		if (hci_dev_test_flag(hdev, HCI_LE_SCAN)) {
 			hci_req_add_le_scan_disable(req);
 			return true;
 		}
@@ -1300,6 +1439,49 @@ static bool hci_stop_discovery(struct hci_request *req)
 	return false;
 }
 
+static void advertising_added(struct sock *sk, struct hci_dev *hdev,
+			      u8 instance)
+{
+	struct mgmt_ev_advertising_added ev;
+
+	ev.instance = instance;
+
+	mgmt_event(MGMT_EV_ADVERTISING_ADDED, hdev, &ev, sizeof(ev), sk);
+}
+
+static void advertising_removed(struct sock *sk, struct hci_dev *hdev,
+				u8 instance)
+{
+	struct mgmt_ev_advertising_removed ev;
+
+	ev.instance = instance;
+
+	mgmt_event(MGMT_EV_ADVERTISING_REMOVED, hdev, &ev, sizeof(ev), sk);
+}
+
+static void clear_adv_instance(struct hci_dev *hdev)
+{
+	struct hci_request req;
+
+	if (!hci_dev_test_flag(hdev, HCI_ADVERTISING_INSTANCE))
+		return;
+
+	if (hdev->adv_instance.timeout)
+		cancel_delayed_work(&hdev->adv_instance.timeout_exp);
+
+	memset(&hdev->adv_instance, 0, sizeof(hdev->adv_instance));
+	advertising_removed(NULL, hdev, 1);
+	hci_dev_clear_flag(hdev, HCI_ADVERTISING_INSTANCE);
+
+	if (!hdev_is_powered(hdev) ||
+	    hci_dev_test_flag(hdev, HCI_ADVERTISING))
+		return;
+
+	hci_req_init(&req, hdev);
+	disable_advertising(&req);
+	hci_req_run(&req, NULL);
+}
+
 static int clean_up_hci_state(struct hci_dev *hdev)
 {
 	struct hci_request req;
@@ -1315,7 +1497,10 @@ static int clean_up_hci_state(struct hci_dev *hdev)
 		hci_req_add(&req, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan);
 	}
 
-	if (test_bit(HCI_LE_ADV, &hdev->dev_flags))
+	if (hdev->adv_instance.timeout)
+		clear_adv_instance(hdev);
+
+	if (hci_dev_test_flag(hdev, HCI_LE_ADV))
 		disable_advertising(&req);
 
 	discov_stopped = hci_stop_discovery(&req);
@@ -1363,24 +1548,24 @@ static int set_powered(struct sock *sk, struct hci_dev *hdev, void *data,
 		       u16 len)
 {
 	struct mgmt_mode *cp = data;
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 	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_POWERED,
-				  MGMT_STATUS_INVALID_PARAMS);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_POWERED,
+				       MGMT_STATUS_INVALID_PARAMS);
 
 	hci_dev_lock(hdev);
 
-	if (mgmt_pending_find(MGMT_OP_SET_POWERED, hdev)) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_SET_POWERED,
-				 MGMT_STATUS_BUSY);
+	if (pending_find(MGMT_OP_SET_POWERED, hdev)) {
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_POWERED,
+				      MGMT_STATUS_BUSY);
 		goto failed;
 	}
 
-	if (test_and_clear_bit(HCI_AUTO_OFF, &hdev->dev_flags)) {
+	if (hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF)) {
 		cancel_delayed_work(&hdev->power_off);
 
 		if (cp->val) {
@@ -1427,11 +1612,10 @@ failed:
 
 static int new_settings(struct hci_dev *hdev, struct sock *skip)
 {
-	__le32 ev;
-
-	ev = cpu_to_le32(get_current_settings(hdev));
+	__le32 ev = cpu_to_le32(get_current_settings(hdev));
 
-	return mgmt_event(MGMT_EV_NEW_SETTINGS, hdev, &ev, sizeof(ev), skip);
+	return mgmt_generic_event(MGMT_EV_NEW_SETTINGS, hdev, &ev,
+				  sizeof(ev), skip);
 }
 
 int mgmt_new_settings(struct hci_dev *hdev)
@@ -1445,7 +1629,7 @@ struct cmd_lookup {
 	u8 mgmt_status;
 };
 
-static void settings_rsp(struct pending_cmd *cmd, void *data)
+static void settings_rsp(struct mgmt_pending_cmd *cmd, void *data)
 {
 	struct cmd_lookup *match = data;
 
@@ -1461,19 +1645,45 @@ static void settings_rsp(struct pending_cmd *cmd, void *data)
 	mgmt_pending_free(cmd);
 }
 
-static void cmd_status_rsp(struct pending_cmd *cmd, void *data)
+static void cmd_status_rsp(struct mgmt_pending_cmd *cmd, void *data)
 {
 	u8 *status = data;
 
-	cmd_status(cmd->sk, cmd->index, cmd->opcode, *status);
+	mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode, *status);
 	mgmt_pending_remove(cmd);
 }
 
+static void cmd_complete_rsp(struct mgmt_pending_cmd *cmd, void *data)
+{
+	if (cmd->cmd_complete) {
+		u8 *status = data;
+
+		cmd->cmd_complete(cmd, *status);
+		mgmt_pending_remove(cmd);
+
+		return;
+	}
+
+	cmd_status_rsp(cmd, data);
+}
+
+static int generic_cmd_complete(struct mgmt_pending_cmd *cmd, u8 status)
+{
+	return mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, status,
+				 cmd->param, cmd->param_len);
+}
+
+static int addr_cmd_complete(struct mgmt_pending_cmd *cmd, u8 status)
+{
+	return mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, status,
+				 cmd->param, sizeof(struct mgmt_addr_info));
+}
+
 static u8 mgmt_bredr_support(struct hci_dev *hdev)
 {
 	if (!lmp_bredr_capable(hdev))
 		return MGMT_STATUS_NOT_SUPPORTED;
-	else if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
+	else if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED))
 		return MGMT_STATUS_REJECTED;
 	else
 		return MGMT_STATUS_SUCCESS;
@@ -1483,15 +1693,16 @@ static u8 mgmt_le_support(struct hci_dev *hdev)
 {
 	if (!lmp_le_capable(hdev))
 		return MGMT_STATUS_NOT_SUPPORTED;
-	else if (!test_bit(HCI_LE_ENABLED, &hdev->dev_flags))
+	else if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED))
 		return MGMT_STATUS_REJECTED;
 	else
 		return MGMT_STATUS_SUCCESS;
 }
 
-static void set_discoverable_complete(struct hci_dev *hdev, u8 status)
+static void set_discoverable_complete(struct hci_dev *hdev, u8 status,
+				      u16 opcode)
 {
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 	struct mgmt_mode *cp;
 	struct hci_request req;
 	bool changed;
@@ -1500,21 +1711,20 @@ static void set_discoverable_complete(struct hci_dev *hdev, u8 status)
 
 	hci_dev_lock(hdev);
 
-	cmd = mgmt_pending_find(MGMT_OP_SET_DISCOVERABLE, hdev);
+	cmd = pending_find(MGMT_OP_SET_DISCOVERABLE, hdev);
 	if (!cmd)
 		goto unlock;
 
 	if (status) {
 		u8 mgmt_err = mgmt_status(status);
-		cmd_status(cmd->sk, cmd->index, cmd->opcode, mgmt_err);
-		clear_bit(HCI_LIMITED_DISCOVERABLE, &hdev->dev_flags);
+		mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode, mgmt_err);
+		hci_dev_clear_flag(hdev, HCI_LIMITED_DISCOVERABLE);
 		goto remove_cmd;
 	}
 
 	cp = cmd->param;
 	if (cp->val) {
-		changed = !test_and_set_bit(HCI_DISCOVERABLE,
-					    &hdev->dev_flags);
+		changed = !hci_dev_test_and_set_flag(hdev, HCI_DISCOVERABLE);
 
 		if (hdev->discov_timeout > 0) {
 			int to = msecs_to_jiffies(hdev->discov_timeout * 1000);
@@ -1522,8 +1732,7 @@ static void set_discoverable_complete(struct hci_dev *hdev, u8 status)
 					   to);
 		}
 	} else {
-		changed = test_and_clear_bit(HCI_DISCOVERABLE,
-					     &hdev->dev_flags);
+		changed = hci_dev_test_and_clear_flag(hdev, HCI_DISCOVERABLE);
 	}
 
 	send_settings_rsp(cmd->sk, MGMT_OP_SET_DISCOVERABLE, hdev);
@@ -1537,7 +1746,7 @@ static void set_discoverable_complete(struct hci_dev *hdev, u8 status)
 	 * entries.
 	 */
 	hci_req_init(&req, hdev);
-	hci_update_page_scan(hdev, &req);
+	__hci_update_page_scan(&req);
 	update_class(&req);
 	hci_req_run(&req, NULL);
 
@@ -1552,7 +1761,7 @@ static int set_discoverable(struct sock *sk, struct hci_dev *hdev, void *data,
 			    u16 len)
 {
 	struct mgmt_cp_set_discoverable *cp = data;
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 	struct hci_request req;
 	u16 timeout;
 	u8 scan;
@@ -1560,14 +1769,14 @@ static int set_discoverable(struct sock *sk, struct hci_dev *hdev, void *data,
 
 	BT_DBG("request for %s", hdev->name);
 
-	if (!test_bit(HCI_LE_ENABLED, &hdev->dev_flags) &&
-	    !test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE,
-				  MGMT_STATUS_REJECTED);
+	if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED) &&
+	    !hci_dev_test_flag(hdev, HCI_BREDR_ENABLED))
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE,
+				       MGMT_STATUS_REJECTED);
 
 	if (cp->val != 0x00 && cp->val != 0x01 && cp->val != 0x02)
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE,
-				  MGMT_STATUS_INVALID_PARAMS);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE,
+				       MGMT_STATUS_INVALID_PARAMS);
 
 	timeout = __le16_to_cpu(cp->timeout);
 
@@ -1576,27 +1785,27 @@ static int set_discoverable(struct sock *sk, struct hci_dev *hdev, void *data,
 	 */
 	if ((cp->val == 0x00 && timeout > 0) ||
 	    (cp->val == 0x02 && timeout == 0))
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE,
-				  MGMT_STATUS_INVALID_PARAMS);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE,
+				       MGMT_STATUS_INVALID_PARAMS);
 
 	hci_dev_lock(hdev);
 
 	if (!hdev_is_powered(hdev) && timeout > 0) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE,
-				 MGMT_STATUS_NOT_POWERED);
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE,
+				      MGMT_STATUS_NOT_POWERED);
 		goto failed;
 	}
 
-	if (mgmt_pending_find(MGMT_OP_SET_DISCOVERABLE, hdev) ||
-	    mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, hdev)) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE,
-				 MGMT_STATUS_BUSY);
+	if (pending_find(MGMT_OP_SET_DISCOVERABLE, hdev) ||
+	    pending_find(MGMT_OP_SET_CONNECTABLE, hdev)) {
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE,
+				      MGMT_STATUS_BUSY);
 		goto failed;
 	}
 
-	if (!test_bit(HCI_CONNECTABLE, &hdev->dev_flags)) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE,
-				 MGMT_STATUS_REJECTED);
+	if (!hci_dev_test_flag(hdev, HCI_CONNECTABLE)) {
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE,
+				      MGMT_STATUS_REJECTED);
 		goto failed;
 	}
 
@@ -1607,8 +1816,8 @@ static int set_discoverable(struct sock *sk, struct hci_dev *hdev, void *data,
 		 * not a valid operation since it requires a timeout
 		 * and so no need to check HCI_LIMITED_DISCOVERABLE.
 		 */
-		if (!!cp->val != test_bit(HCI_DISCOVERABLE, &hdev->dev_flags)) {
-			change_bit(HCI_DISCOVERABLE, &hdev->dev_flags);
+		if (!!cp->val != hci_dev_test_flag(hdev, HCI_DISCOVERABLE)) {
+			hci_dev_change_flag(hdev, HCI_DISCOVERABLE);
 			changed = true;
 		}
 
@@ -1626,9 +1835,9 @@ static int set_discoverable(struct sock *sk, struct hci_dev *hdev, void *data,
 	 * value with the new value. And if only the timeout gets updated,
 	 * then no need for any HCI transactions.
 	 */
-	if (!!cp->val == test_bit(HCI_DISCOVERABLE, &hdev->dev_flags) &&
-	    (cp->val == 0x02) == test_bit(HCI_LIMITED_DISCOVERABLE,
-					  &hdev->dev_flags)) {
+	if (!!cp->val == hci_dev_test_flag(hdev, HCI_DISCOVERABLE) &&
+	    (cp->val == 0x02) == hci_dev_test_flag(hdev,
+						   HCI_LIMITED_DISCOVERABLE)) {
 		cancel_delayed_work(&hdev->discov_off);
 		hdev->discov_timeout = timeout;
 
@@ -1657,16 +1866,16 @@ static int set_discoverable(struct sock *sk, struct hci_dev *hdev, void *data,
 
 	/* Limited discoverable mode */
 	if (cp->val == 0x02)
-		set_bit(HCI_LIMITED_DISCOVERABLE, &hdev->dev_flags);
+		hci_dev_set_flag(hdev, HCI_LIMITED_DISCOVERABLE);
 	else
-		clear_bit(HCI_LIMITED_DISCOVERABLE, &hdev->dev_flags);
+		hci_dev_clear_flag(hdev, HCI_LIMITED_DISCOVERABLE);
 
 	hci_req_init(&req, hdev);
 
 	/* The procedure for LE-only controllers is much simpler - just
 	 * update the advertising data.
 	 */
-	if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
+	if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED))
 		goto update_ad;
 
 	scan = SCAN_PAGE;
@@ -1696,7 +1905,7 @@ static int set_discoverable(struct sock *sk, struct hci_dev *hdev, void *data,
 
 		scan |= SCAN_INQUIRY;
 	} else {
-		clear_bit(HCI_LIMITED_DISCOVERABLE, &hdev->dev_flags);
+		hci_dev_clear_flag(hdev, HCI_LIMITED_DISCOVERABLE);
 	}
 
 	hci_req_add(&req, HCI_OP_WRITE_SCAN_ENABLE, sizeof(scan), &scan);
@@ -1719,7 +1928,7 @@ static void write_fast_connectable(struct hci_request *req, bool enable)
 	struct hci_cp_write_page_scan_activity acp;
 	u8 type;
 
-	if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
+	if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED))
 		return;
 
 	if (hdev->hci_ver < BLUETOOTH_VER_1_2)
@@ -1748,9 +1957,10 @@ static void write_fast_connectable(struct hci_request *req, bool enable)
 		hci_req_add(req, HCI_OP_WRITE_PAGE_SCAN_TYPE, 1, &type);
 }
 
-static void set_connectable_complete(struct hci_dev *hdev, u8 status)
+static void set_connectable_complete(struct hci_dev *hdev, u8 status,
+				     u16 opcode)
 {
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 	struct mgmt_mode *cp;
 	bool conn_changed, discov_changed;
 
@@ -1758,33 +1968,33 @@ static void set_connectable_complete(struct hci_dev *hdev, u8 status)
 
 	hci_dev_lock(hdev);
 
-	cmd = mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, hdev);
+	cmd = pending_find(MGMT_OP_SET_CONNECTABLE, hdev);
 	if (!cmd)
 		goto unlock;
 
 	if (status) {
 		u8 mgmt_err = mgmt_status(status);
-		cmd_status(cmd->sk, cmd->index, cmd->opcode, mgmt_err);
+		mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode, mgmt_err);
 		goto remove_cmd;
 	}
 
 	cp = cmd->param;
 	if (cp->val) {
-		conn_changed = !test_and_set_bit(HCI_CONNECTABLE,
-						 &hdev->dev_flags);
+		conn_changed = !hci_dev_test_and_set_flag(hdev,
+							  HCI_CONNECTABLE);
 		discov_changed = false;
 	} else {
-		conn_changed = test_and_clear_bit(HCI_CONNECTABLE,
-						  &hdev->dev_flags);
-		discov_changed = test_and_clear_bit(HCI_DISCOVERABLE,
-						    &hdev->dev_flags);
+		conn_changed = hci_dev_test_and_clear_flag(hdev,
+							   HCI_CONNECTABLE);
+		discov_changed = hci_dev_test_and_clear_flag(hdev,
+							     HCI_DISCOVERABLE);
 	}
 
 	send_settings_rsp(cmd->sk, MGMT_OP_SET_CONNECTABLE, hdev);
 
 	if (conn_changed || discov_changed) {
 		new_settings(hdev, cmd->sk);
-		hci_update_page_scan(hdev, NULL);
+		hci_update_page_scan(hdev);
 		if (discov_changed)
 			mgmt_update_adv_data(hdev);
 		hci_update_background_scan(hdev);
@@ -1803,14 +2013,14 @@ static int set_connectable_update_settings(struct hci_dev *hdev,
 	bool changed = false;
 	int err;
 
-	if (!!val != test_bit(HCI_CONNECTABLE, &hdev->dev_flags))
+	if (!!val != hci_dev_test_flag(hdev, HCI_CONNECTABLE))
 		changed = true;
 
 	if (val) {
-		set_bit(HCI_CONNECTABLE, &hdev->dev_flags);
+		hci_dev_set_flag(hdev, HCI_CONNECTABLE);
 	} else {
-		clear_bit(HCI_CONNECTABLE, &hdev->dev_flags);
-		clear_bit(HCI_DISCOVERABLE, &hdev->dev_flags);
+		hci_dev_clear_flag(hdev, HCI_CONNECTABLE);
+		hci_dev_clear_flag(hdev, HCI_DISCOVERABLE);
 	}
 
 	err = send_settings_rsp(sk, MGMT_OP_SET_CONNECTABLE, hdev);
@@ -1818,7 +2028,7 @@ static int set_connectable_update_settings(struct hci_dev *hdev,
 		return err;
 
 	if (changed) {
-		hci_update_page_scan(hdev, NULL);
+		hci_update_page_scan(hdev);
 		hci_update_background_scan(hdev);
 		return new_settings(hdev, sk);
 	}
@@ -1830,21 +2040,21 @@ static int set_connectable(struct sock *sk, struct hci_dev *hdev, void *data,
 			   u16 len)
 {
 	struct mgmt_mode *cp = data;
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 	struct hci_request req;
 	u8 scan;
 	int err;
 
 	BT_DBG("request for %s", hdev->name);
 
-	if (!test_bit(HCI_LE_ENABLED, &hdev->dev_flags) &&
-	    !test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_CONNECTABLE,
-				  MGMT_STATUS_REJECTED);
+	if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED) &&
+	    !hci_dev_test_flag(hdev, HCI_BREDR_ENABLED))
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_CONNECTABLE,
+				       MGMT_STATUS_REJECTED);
 
 	if (cp->val != 0x00 && cp->val != 0x01)
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_CONNECTABLE,
-				  MGMT_STATUS_INVALID_PARAMS);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_CONNECTABLE,
+				       MGMT_STATUS_INVALID_PARAMS);
 
 	hci_dev_lock(hdev);
 
@@ -1853,10 +2063,10 @@ static int set_connectable(struct sock *sk, struct hci_dev *hdev, void *data,
 		goto failed;
 	}
 
-	if (mgmt_pending_find(MGMT_OP_SET_DISCOVERABLE, hdev) ||
-	    mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, hdev)) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_SET_CONNECTABLE,
-				 MGMT_STATUS_BUSY);
+	if (pending_find(MGMT_OP_SET_DISCOVERABLE, hdev) ||
+	    pending_find(MGMT_OP_SET_CONNECTABLE, hdev)) {
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_CONNECTABLE,
+				      MGMT_STATUS_BUSY);
 		goto failed;
 	}
 
@@ -1872,10 +2082,10 @@ static int set_connectable(struct sock *sk, struct hci_dev *hdev, void *data,
 	 * by-product of disabling connectable, we need to update the
 	 * advertising flags.
 	 */
-	if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) {
+	if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) {
 		if (!cp->val) {
-			clear_bit(HCI_LIMITED_DISCOVERABLE, &hdev->dev_flags);
-			clear_bit(HCI_DISCOVERABLE, &hdev->dev_flags);
+			hci_dev_clear_flag(hdev, HCI_LIMITED_DISCOVERABLE);
+			hci_dev_clear_flag(hdev, HCI_DISCOVERABLE);
 		}
 		update_adv_data(&req);
 	} else if (cp->val != test_bit(HCI_PSCAN, &hdev->flags)) {
@@ -1904,17 +2114,9 @@ static int set_connectable(struct sock *sk, struct hci_dev *hdev, void *data,
 	}
 
 no_scan_update:
-	/* If we're going from non-connectable to connectable or
-	 * vice-versa when fast connectable is enabled ensure that fast
-	 * connectable gets disabled. write_fast_connectable won't do
-	 * anything if the page scan parameters are already what they
-	 * should be.
-	 */
-	if (cp->val || test_bit(HCI_FAST_CONNECTABLE, &hdev->dev_flags))
-		write_fast_connectable(&req, false);
-
 	/* Update the advertising parameters if necessary */
-	if (test_bit(HCI_ADVERTISING, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_ADVERTISING) ||
+	    hci_dev_test_flag(hdev, HCI_ADVERTISING_INSTANCE))
 		enable_advertising(&req);
 
 	err = hci_req_run(&req, set_connectable_complete);
@@ -1941,15 +2143,15 @@ static int set_bondable(struct sock *sk, struct hci_dev *hdev, void *data,
 	BT_DBG("request for %s", hdev->name);
 
 	if (cp->val != 0x00 && cp->val != 0x01)
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_BONDABLE,
-				  MGMT_STATUS_INVALID_PARAMS);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_BONDABLE,
+				       MGMT_STATUS_INVALID_PARAMS);
 
 	hci_dev_lock(hdev);
 
 	if (cp->val)
-		changed = !test_and_set_bit(HCI_BONDABLE, &hdev->dev_flags);
+		changed = !hci_dev_test_and_set_flag(hdev, HCI_BONDABLE);
 	else
-		changed = test_and_clear_bit(HCI_BONDABLE, &hdev->dev_flags);
+		changed = hci_dev_test_and_clear_flag(hdev, HCI_BONDABLE);
 
 	err = send_settings_rsp(sk, MGMT_OP_SET_BONDABLE, hdev);
 	if (err < 0)
@@ -1967,7 +2169,7 @@ static int set_link_security(struct sock *sk, struct hci_dev *hdev, void *data,
 			     u16 len)
 {
 	struct mgmt_mode *cp = data;
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 	u8 val, status;
 	int err;
 
@@ -1975,21 +2177,20 @@ static int set_link_security(struct sock *sk, struct hci_dev *hdev, void *data,
 
 	status = mgmt_bredr_support(hdev);
 	if (status)
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_LINK_SECURITY,
-				  status);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_LINK_SECURITY,
+				       status);
 
 	if (cp->val != 0x00 && cp->val != 0x01)
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_LINK_SECURITY,
-				  MGMT_STATUS_INVALID_PARAMS);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_LINK_SECURITY,
+				       MGMT_STATUS_INVALID_PARAMS);
 
 	hci_dev_lock(hdev);
 
 	if (!hdev_is_powered(hdev)) {
 		bool changed = false;
 
-		if (!!cp->val != test_bit(HCI_LINK_SECURITY,
-					  &hdev->dev_flags)) {
-			change_bit(HCI_LINK_SECURITY, &hdev->dev_flags);
+		if (!!cp->val != hci_dev_test_flag(hdev, HCI_LINK_SECURITY)) {
+			hci_dev_change_flag(hdev, HCI_LINK_SECURITY);
 			changed = true;
 		}
 
@@ -2003,9 +2204,9 @@ static int set_link_security(struct sock *sk, struct hci_dev *hdev, void *data,
 		goto failed;
 	}
 
-	if (mgmt_pending_find(MGMT_OP_SET_LINK_SECURITY, hdev)) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_SET_LINK_SECURITY,
-				 MGMT_STATUS_BUSY);
+	if (pending_find(MGMT_OP_SET_LINK_SECURITY, hdev)) {
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_LINK_SECURITY,
+				      MGMT_STATUS_BUSY);
 		goto failed;
 	}
 
@@ -2036,7 +2237,7 @@ failed:
 static int set_ssp(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 {
 	struct mgmt_mode *cp = data;
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 	u8 status;
 	int err;
 
@@ -2044,15 +2245,15 @@ static int set_ssp(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 
 	status = mgmt_bredr_support(hdev);
 	if (status)
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_SSP, status);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_SSP, status);
 
 	if (!lmp_ssp_capable(hdev))
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_SSP,
-				  MGMT_STATUS_NOT_SUPPORTED);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_SSP,
+				       MGMT_STATUS_NOT_SUPPORTED);
 
 	if (cp->val != 0x00 && cp->val != 0x01)
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_SSP,
-				  MGMT_STATUS_INVALID_PARAMS);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_SSP,
+				       MGMT_STATUS_INVALID_PARAMS);
 
 	hci_dev_lock(hdev);
 
@@ -2060,16 +2261,16 @@ static int set_ssp(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 		bool changed;
 
 		if (cp->val) {
-			changed = !test_and_set_bit(HCI_SSP_ENABLED,
-						    &hdev->dev_flags);
+			changed = !hci_dev_test_and_set_flag(hdev,
+							     HCI_SSP_ENABLED);
 		} else {
-			changed = test_and_clear_bit(HCI_SSP_ENABLED,
-						     &hdev->dev_flags);
+			changed = hci_dev_test_and_clear_flag(hdev,
+							      HCI_SSP_ENABLED);
 			if (!changed)
-				changed = test_and_clear_bit(HCI_HS_ENABLED,
-							     &hdev->dev_flags);
+				changed = hci_dev_test_and_clear_flag(hdev,
+								      HCI_HS_ENABLED);
 			else
-				clear_bit(HCI_HS_ENABLED, &hdev->dev_flags);
+				hci_dev_clear_flag(hdev, HCI_HS_ENABLED);
 		}
 
 		err = send_settings_rsp(sk, MGMT_OP_SET_SSP, hdev);
@@ -2082,14 +2283,13 @@ static int set_ssp(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 		goto failed;
 	}
 
-	if (mgmt_pending_find(MGMT_OP_SET_SSP, hdev) ||
-	    mgmt_pending_find(MGMT_OP_SET_HS, hdev)) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_SET_SSP,
-				 MGMT_STATUS_BUSY);
+	if (pending_find(MGMT_OP_SET_SSP, hdev)) {
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_SSP,
+				      MGMT_STATUS_BUSY);
 		goto failed;
 	}
 
-	if (!!cp->val == test_bit(HCI_SSP_ENABLED, &hdev->dev_flags)) {
+	if (!!cp->val == hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) {
 		err = send_settings_rsp(sk, MGMT_OP_SET_SSP, hdev);
 		goto failed;
 	}
@@ -2100,7 +2300,7 @@ static int set_ssp(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 		goto failed;
 	}
 
-	if (!cp->val && test_bit(HCI_USE_DEBUG_KEYS, &hdev->dev_flags))
+	if (!cp->val && hci_dev_test_flag(hdev, HCI_USE_DEBUG_KEYS))
 		hci_send_cmd(hdev, HCI_OP_WRITE_SSP_DEBUG_MODE,
 			     sizeof(cp->val), &cp->val);
 
@@ -2126,32 +2326,38 @@ static int set_hs(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 
 	status = mgmt_bredr_support(hdev);
 	if (status)
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_HS, status);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, status);
 
 	if (!lmp_ssp_capable(hdev))
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_HS,
-				  MGMT_STATUS_NOT_SUPPORTED);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS,
+				       MGMT_STATUS_NOT_SUPPORTED);
 
-	if (!test_bit(HCI_SSP_ENABLED, &hdev->dev_flags))
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_HS,
-				  MGMT_STATUS_REJECTED);
+	if (!hci_dev_test_flag(hdev, HCI_SSP_ENABLED))
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS,
+				       MGMT_STATUS_REJECTED);
 
 	if (cp->val != 0x00 && cp->val != 0x01)
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_HS,
-				  MGMT_STATUS_INVALID_PARAMS);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS,
+				       MGMT_STATUS_INVALID_PARAMS);
 
 	hci_dev_lock(hdev);
 
+	if (pending_find(MGMT_OP_SET_SSP, hdev)) {
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS,
+				      MGMT_STATUS_BUSY);
+		goto unlock;
+	}
+
 	if (cp->val) {
-		changed = !test_and_set_bit(HCI_HS_ENABLED, &hdev->dev_flags);
+		changed = !hci_dev_test_and_set_flag(hdev, HCI_HS_ENABLED);
 	} else {
 		if (hdev_is_powered(hdev)) {
-			err = cmd_status(sk, hdev->id, MGMT_OP_SET_HS,
-					 MGMT_STATUS_REJECTED);
+			err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS,
+					      MGMT_STATUS_REJECTED);
 			goto unlock;
 		}
 
-		changed = test_and_clear_bit(HCI_HS_ENABLED, &hdev->dev_flags);
+		changed = hci_dev_test_and_clear_flag(hdev, HCI_HS_ENABLED);
 	}
 
 	err = send_settings_rsp(sk, MGMT_OP_SET_HS, hdev);
@@ -2166,16 +2372,18 @@ unlock:
 	return err;
 }
 
-static void le_enable_complete(struct hci_dev *hdev, u8 status)
+static void le_enable_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
 	struct cmd_lookup match = { NULL, hdev };
 
+	hci_dev_lock(hdev);
+
 	if (status) {
 		u8 mgmt_err = mgmt_status(status);
 
 		mgmt_pending_foreach(MGMT_OP_SET_LE, hdev, cmd_status_rsp,
 				     &mgmt_err);
-		return;
+		goto unlock;
 	}
 
 	mgmt_pending_foreach(MGMT_OP_SET_LE, hdev, settings_rsp, &match);
@@ -2190,27 +2398,25 @@ static void le_enable_complete(struct hci_dev *hdev, u8 status)
 	 * has actually been enabled. During power on, the
 	 * update in powered_update_hci will take care of it.
 	 */
-	if (test_bit(HCI_LE_ENABLED, &hdev->dev_flags)) {
+	if (hci_dev_test_flag(hdev, HCI_LE_ENABLED)) {
 		struct hci_request req;
 
-		hci_dev_lock(hdev);
-
 		hci_req_init(&req, hdev);
 		update_adv_data(&req);
 		update_scan_rsp_data(&req);
+		__hci_update_background_scan(&req);
 		hci_req_run(&req, NULL);
-
-		hci_update_background_scan(hdev);
-
-		hci_dev_unlock(hdev);
 	}
+
+unlock:
+	hci_dev_unlock(hdev);
 }
 
 static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 {
 	struct mgmt_mode *cp = data;
 	struct hci_cp_write_le_host_supported hci_cp;
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 	struct hci_request req;
 	int err;
 	u8 val, enabled;
@@ -2218,17 +2424,29 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 	BT_DBG("request for %s", hdev->name);
 
 	if (!lmp_le_capable(hdev))
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_LE,
-				  MGMT_STATUS_NOT_SUPPORTED);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_LE,
+				       MGMT_STATUS_NOT_SUPPORTED);
 
 	if (cp->val != 0x00 && cp->val != 0x01)
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_LE,
-				  MGMT_STATUS_INVALID_PARAMS);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_LE,
+				       MGMT_STATUS_INVALID_PARAMS);
 
-	/* LE-only devices do not allow toggling LE on/off */
-	if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_LE,
-				  MGMT_STATUS_REJECTED);
+	/* Bluetooth single mode LE only controllers or dual-mode
+	 * controllers configured as LE only devices, do not allow
+	 * switching LE off. These have either LE enabled explicitly
+	 * or BR/EDR has been previously switched off.
+	 *
+	 * When trying to enable an already enabled LE, then gracefully
+	 * send a positive response. Trying to disable it however will
+	 * result into rejection.
+	 */
+	if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) {
+		if (cp->val == 0x01)
+			return send_settings_rsp(sk, MGMT_OP_SET_LE, hdev);
+
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_LE,
+				       MGMT_STATUS_REJECTED);
+	}
 
 	hci_dev_lock(hdev);
 
@@ -2238,13 +2456,13 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 	if (!hdev_is_powered(hdev) || val == enabled) {
 		bool changed = false;
 
-		if (val != test_bit(HCI_LE_ENABLED, &hdev->dev_flags)) {
-			change_bit(HCI_LE_ENABLED, &hdev->dev_flags);
+		if (val != hci_dev_test_flag(hdev, HCI_LE_ENABLED)) {
+			hci_dev_change_flag(hdev, HCI_LE_ENABLED);
 			changed = true;
 		}
 
-		if (!val && test_bit(HCI_ADVERTISING, &hdev->dev_flags)) {
-			clear_bit(HCI_ADVERTISING, &hdev->dev_flags);
+		if (!val && hci_dev_test_flag(hdev, HCI_ADVERTISING)) {
+			hci_dev_clear_flag(hdev, HCI_ADVERTISING);
 			changed = true;
 		}
 
@@ -2258,10 +2476,10 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 		goto unlock;
 	}
 
-	if (mgmt_pending_find(MGMT_OP_SET_LE, hdev) ||
-	    mgmt_pending_find(MGMT_OP_SET_ADVERTISING, hdev)) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_SET_LE,
-				 MGMT_STATUS_BUSY);
+	if (pending_find(MGMT_OP_SET_LE, hdev) ||
+	    pending_find(MGMT_OP_SET_ADVERTISING, hdev)) {
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_LE,
+				      MGMT_STATUS_BUSY);
 		goto unlock;
 	}
 
@@ -2279,7 +2497,7 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 		hci_cp.le = val;
 		hci_cp.simul = 0x00;
 	} else {
-		if (test_bit(HCI_LE_ADV, &hdev->dev_flags))
+		if (hci_dev_test_flag(hdev, HCI_LE_ADV))
 			disable_advertising(&req);
 	}
 
@@ -2303,7 +2521,7 @@ unlock:
  */
 static bool pending_eir_or_class(struct hci_dev *hdev)
 {
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 
 	list_for_each_entry(cmd, &hdev->mgmt_pending, list) {
 		switch (cmd->opcode) {
@@ -2339,16 +2557,16 @@ static u8 get_uuid_size(const u8 *uuid)
 
 static void mgmt_class_complete(struct hci_dev *hdev, u16 mgmt_op, u8 status)
 {
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 
 	hci_dev_lock(hdev);
 
-	cmd = mgmt_pending_find(mgmt_op, hdev);
+	cmd = pending_find(mgmt_op, hdev);
 	if (!cmd)
 		goto unlock;
 
-	cmd_complete(cmd->sk, cmd->index, cmd->opcode, mgmt_status(status),
-		     hdev->dev_class, 3);
+	mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode,
+			  mgmt_status(status), hdev->dev_class, 3);
 
 	mgmt_pending_remove(cmd);
 
@@ -2356,7 +2574,7 @@ unlock:
 	hci_dev_unlock(hdev);
 }
 
-static void add_uuid_complete(struct hci_dev *hdev, u8 status)
+static void add_uuid_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
 	BT_DBG("status 0x%02x", status);
 
@@ -2366,7 +2584,7 @@ static void add_uuid_complete(struct hci_dev *hdev, u8 status)
 static int add_uuid(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 {
 	struct mgmt_cp_add_uuid *cp = data;
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 	struct hci_request req;
 	struct bt_uuid *uuid;
 	int err;
@@ -2376,8 +2594,8 @@ static int add_uuid(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 	hci_dev_lock(hdev);
 
 	if (pending_eir_or_class(hdev)) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_ADD_UUID,
-				 MGMT_STATUS_BUSY);
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_UUID,
+				      MGMT_STATUS_BUSY);
 		goto failed;
 	}
 
@@ -2403,8 +2621,8 @@ static int add_uuid(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 		if (err != -ENODATA)
 			goto failed;
 
-		err = cmd_complete(sk, hdev->id, MGMT_OP_ADD_UUID, 0,
-				   hdev->dev_class, 3);
+		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_ADD_UUID, 0,
+					hdev->dev_class, 3);
 		goto failed;
 	}
 
@@ -2426,7 +2644,7 @@ static bool enable_service_cache(struct hci_dev *hdev)
 	if (!hdev_is_powered(hdev))
 		return false;
 
-	if (!test_and_set_bit(HCI_SERVICE_CACHE, &hdev->dev_flags)) {
+	if (!hci_dev_test_and_set_flag(hdev, HCI_SERVICE_CACHE)) {
 		queue_delayed_work(hdev->workqueue, &hdev->service_cache,
 				   CACHE_TIMEOUT);
 		return true;
@@ -2435,7 +2653,7 @@ static bool enable_service_cache(struct hci_dev *hdev)
 	return false;
 }
 
-static void remove_uuid_complete(struct hci_dev *hdev, u8 status)
+static void remove_uuid_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
 	BT_DBG("status 0x%02x", status);
 
@@ -2446,7 +2664,7 @@ static int remove_uuid(struct sock *sk, struct hci_dev *hdev, void *data,
 		       u16 len)
 {
 	struct mgmt_cp_remove_uuid *cp = data;
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 	struct bt_uuid *match, *tmp;
 	u8 bt_uuid_any[] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 };
 	struct hci_request req;
@@ -2457,8 +2675,8 @@ static int remove_uuid(struct sock *sk, struct hci_dev *hdev, void *data,
 	hci_dev_lock(hdev);
 
 	if (pending_eir_or_class(hdev)) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_REMOVE_UUID,
-				 MGMT_STATUS_BUSY);
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_REMOVE_UUID,
+				      MGMT_STATUS_BUSY);
 		goto unlock;
 	}
 
@@ -2466,8 +2684,9 @@ static int remove_uuid(struct sock *sk, struct hci_dev *hdev, void *data,
 		hci_uuids_clear(hdev);
 
 		if (enable_service_cache(hdev)) {
-			err = cmd_complete(sk, hdev->id, MGMT_OP_REMOVE_UUID,
-					   0, hdev->dev_class, 3);
+			err = mgmt_cmd_complete(sk, hdev->id,
+						MGMT_OP_REMOVE_UUID,
+						0, hdev->dev_class, 3);
 			goto unlock;
 		}
 
@@ -2486,8 +2705,8 @@ static int remove_uuid(struct sock *sk, struct hci_dev *hdev, void *data,
 	}
 
 	if (found == 0) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_REMOVE_UUID,
-				 MGMT_STATUS_INVALID_PARAMS);
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_REMOVE_UUID,
+				      MGMT_STATUS_INVALID_PARAMS);
 		goto unlock;
 	}
 
@@ -2502,8 +2721,8 @@ update_class:
 		if (err != -ENODATA)
 			goto unlock;
 
-		err = cmd_complete(sk, hdev->id, MGMT_OP_REMOVE_UUID, 0,
-				   hdev->dev_class, 3);
+		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_REMOVE_UUID, 0,
+					hdev->dev_class, 3);
 		goto unlock;
 	}
 
@@ -2520,7 +2739,7 @@ unlock:
 	return err;
 }
 
-static void set_class_complete(struct hci_dev *hdev, u8 status)
+static void set_class_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
 	BT_DBG("status 0x%02x", status);
 
@@ -2531,27 +2750,27 @@ static int set_dev_class(struct sock *sk, struct hci_dev *hdev, void *data,
 			 u16 len)
 {
 	struct mgmt_cp_set_dev_class *cp = data;
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 	struct hci_request req;
 	int err;
 
 	BT_DBG("request for %s", hdev->name);
 
 	if (!lmp_bredr_capable(hdev))
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_DEV_CLASS,
-				  MGMT_STATUS_NOT_SUPPORTED);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_DEV_CLASS,
+				       MGMT_STATUS_NOT_SUPPORTED);
 
 	hci_dev_lock(hdev);
 
 	if (pending_eir_or_class(hdev)) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_SET_DEV_CLASS,
-				 MGMT_STATUS_BUSY);
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_DEV_CLASS,
+				      MGMT_STATUS_BUSY);
 		goto unlock;
 	}
 
 	if ((cp->minor & 0x03) != 0 || (cp->major & 0xe0) != 0) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_SET_DEV_CLASS,
-				 MGMT_STATUS_INVALID_PARAMS);
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_DEV_CLASS,
+				      MGMT_STATUS_INVALID_PARAMS);
 		goto unlock;
 	}
 
@@ -2559,14 +2778,14 @@ static int set_dev_class(struct sock *sk, struct hci_dev *hdev, void *data,
 	hdev->minor_class = cp->minor;
 
 	if (!hdev_is_powered(hdev)) {
-		err = cmd_complete(sk, hdev->id, MGMT_OP_SET_DEV_CLASS, 0,
-				   hdev->dev_class, 3);
+		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_SET_DEV_CLASS, 0,
+					hdev->dev_class, 3);
 		goto unlock;
 	}
 
 	hci_req_init(&req, hdev);
 
-	if (test_and_clear_bit(HCI_SERVICE_CACHE, &hdev->dev_flags)) {
+	if (hci_dev_test_and_clear_flag(hdev, HCI_SERVICE_CACHE)) {
 		hci_dev_unlock(hdev);
 		cancel_delayed_work_sync(&hdev->service_cache);
 		hci_dev_lock(hdev);
@@ -2580,8 +2799,8 @@ static int set_dev_class(struct sock *sk, struct hci_dev *hdev, void *data,
 		if (err != -ENODATA)
 			goto unlock;
 
-		err = cmd_complete(sk, hdev->id, MGMT_OP_SET_DEV_CLASS, 0,
-				   hdev->dev_class, 3);
+		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_SET_DEV_CLASS, 0,
+					hdev->dev_class, 3);
 		goto unlock;
 	}
 
@@ -2611,15 +2830,15 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data,
 	BT_DBG("request for %s", hdev->name);
 
 	if (!lmp_bredr_capable(hdev))
-		return cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS,
-				  MGMT_STATUS_NOT_SUPPORTED);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS,
+				       MGMT_STATUS_NOT_SUPPORTED);
 
 	key_count = __le16_to_cpu(cp->key_count);
 	if (key_count > max_key_count) {
 		BT_ERR("load_link_keys: too big key_count value %u",
 		       key_count);
-		return cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS,
-				  MGMT_STATUS_INVALID_PARAMS);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS,
+				       MGMT_STATUS_INVALID_PARAMS);
 	}
 
 	expected_len = sizeof(*cp) + key_count *
@@ -2627,13 +2846,13 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data,
 	if (expected_len != len) {
 		BT_ERR("load_link_keys: expected %u bytes, got %u bytes",
 		       expected_len, len);
-		return cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS,
-				  MGMT_STATUS_INVALID_PARAMS);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS,
+				       MGMT_STATUS_INVALID_PARAMS);
 	}
 
 	if (cp->debug_keys != 0x00 && cp->debug_keys != 0x01)
-		return cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS,
-				  MGMT_STATUS_INVALID_PARAMS);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS,
+				       MGMT_STATUS_INVALID_PARAMS);
 
 	BT_DBG("%s debug_keys %u key_count %u", hdev->name, cp->debug_keys,
 	       key_count);
@@ -2642,8 +2861,9 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data,
 		struct mgmt_link_key_info *key = &cp->keys[i];
 
 		if (key->addr.type != BDADDR_BREDR || key->type > 0x08)
-			return cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS,
-					  MGMT_STATUS_INVALID_PARAMS);
+			return mgmt_cmd_status(sk, hdev->id,
+					       MGMT_OP_LOAD_LINK_KEYS,
+					       MGMT_STATUS_INVALID_PARAMS);
 	}
 
 	hci_dev_lock(hdev);
@@ -2651,11 +2871,10 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data,
 	hci_link_keys_clear(hdev);
 
 	if (cp->debug_keys)
-		changed = !test_and_set_bit(HCI_KEEP_DEBUG_KEYS,
-					    &hdev->dev_flags);
+		changed = !hci_dev_test_and_set_flag(hdev, HCI_KEEP_DEBUG_KEYS);
 	else
-		changed = test_and_clear_bit(HCI_KEEP_DEBUG_KEYS,
-					     &hdev->dev_flags);
+		changed = hci_dev_test_and_clear_flag(hdev,
+						      HCI_KEEP_DEBUG_KEYS);
 
 	if (changed)
 		new_settings(hdev, NULL);
@@ -2673,7 +2892,7 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data,
 				 key->type, key->pin_len, NULL);
 	}
 
-	cmd_complete(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS, 0, NULL, 0);
+	mgmt_cmd_complete(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS, 0, NULL, 0);
 
 	hci_dev_unlock(hdev);
 
@@ -2698,7 +2917,7 @@ static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data,
 	struct mgmt_cp_unpair_device *cp = data;
 	struct mgmt_rp_unpair_device rp;
 	struct hci_cp_disconnect dc;
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 	struct hci_conn *conn;
 	int err;
 
@@ -2707,28 +2926,59 @@ static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data,
 	rp.addr.type = cp->addr.type;
 
 	if (!bdaddr_type_is_valid(cp->addr.type))
-		return cmd_complete(sk, hdev->id, MGMT_OP_UNPAIR_DEVICE,
-				    MGMT_STATUS_INVALID_PARAMS,
-				    &rp, sizeof(rp));
+		return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_UNPAIR_DEVICE,
+					 MGMT_STATUS_INVALID_PARAMS,
+					 &rp, sizeof(rp));
 
 	if (cp->disconnect != 0x00 && cp->disconnect != 0x01)
-		return cmd_complete(sk, hdev->id, MGMT_OP_UNPAIR_DEVICE,
-				    MGMT_STATUS_INVALID_PARAMS,
-				    &rp, sizeof(rp));
+		return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_UNPAIR_DEVICE,
+					 MGMT_STATUS_INVALID_PARAMS,
+					 &rp, sizeof(rp));
 
 	hci_dev_lock(hdev);
 
 	if (!hdev_is_powered(hdev)) {
-		err = cmd_complete(sk, hdev->id, MGMT_OP_UNPAIR_DEVICE,
-				   MGMT_STATUS_NOT_POWERED, &rp, sizeof(rp));
+		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_UNPAIR_DEVICE,
+					MGMT_STATUS_NOT_POWERED, &rp,
+					sizeof(rp));
 		goto unlock;
 	}
 
 	if (cp->addr.type == BDADDR_BREDR) {
+		/* If disconnection is requested, then look up the
+		 * connection. If the remote device is connected, it
+		 * will be later used to terminate the link.
+		 *
+		 * Setting it to NULL explicitly will cause no
+		 * termination of the link.
+		 */
+		if (cp->disconnect)
+			conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK,
+						       &cp->addr.bdaddr);
+		else
+			conn = NULL;
+
 		err = hci_remove_link_key(hdev, &cp->addr.bdaddr);
 	} else {
 		u8 addr_type;
 
+		conn = hci_conn_hash_lookup_ba(hdev, LE_LINK,
+					       &cp->addr.bdaddr);
+		if (conn) {
+			/* Defer clearing up the connection parameters
+			 * until closing to give a chance of keeping
+			 * them if a repairing happens.
+			 */
+			set_bit(HCI_CONN_PARAM_REMOVAL_PEND, &conn->flags);
+
+			/* If disconnection is not requested, then
+			 * clear the connection variable so that the
+			 * link is not terminated.
+			 */
+			if (!cp->disconnect)
+				conn = NULL;
+		}
+
 		if (cp->addr.type == BDADDR_LE_PUBLIC)
 			addr_type = ADDR_LE_DEV_PUBLIC;
 		else
@@ -2736,31 +2986,22 @@ static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data,
 
 		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,
-				   MGMT_STATUS_NOT_PAIRED, &rp, sizeof(rp));
+		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_UNPAIR_DEVICE,
+					MGMT_STATUS_NOT_PAIRED, &rp,
+					sizeof(rp));
 		goto unlock;
 	}
 
-	if (cp->disconnect) {
-		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);
-	} else {
-		conn = NULL;
-	}
-
+	/* If the connection variable is set, then termination of the
+	 * link is requested.
+	 */
 	if (!conn) {
-		err = cmd_complete(sk, hdev->id, MGMT_OP_UNPAIR_DEVICE, 0,
-				   &rp, sizeof(rp));
+		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_UNPAIR_DEVICE, 0,
+					&rp, sizeof(rp));
 		device_unpaired(hdev, &cp->addr.bdaddr, cp->addr.type, sk);
 		goto unlock;
 	}
@@ -2772,6 +3013,8 @@ static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data,
 		goto unlock;
 	}
 
+	cmd->cmd_complete = addr_cmd_complete;
+
 	dc.handle = cpu_to_le16(conn->handle);
 	dc.reason = 0x13; /* Remote User Terminated Connection */
 	err = hci_send_cmd(hdev, HCI_OP_DISCONNECT, sizeof(dc), &dc);
@@ -2788,7 +3031,7 @@ static int disconnect(struct sock *sk, struct hci_dev *hdev, void *data,
 {
 	struct mgmt_cp_disconnect *cp = data;
 	struct mgmt_rp_disconnect rp;
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 	struct hci_conn *conn;
 	int err;
 
@@ -2799,21 +3042,22 @@ static int disconnect(struct sock *sk, struct hci_dev *hdev, void *data,
 	rp.addr.type = cp->addr.type;
 
 	if (!bdaddr_type_is_valid(cp->addr.type))
-		return cmd_complete(sk, hdev->id, MGMT_OP_DISCONNECT,
-				    MGMT_STATUS_INVALID_PARAMS,
-				    &rp, sizeof(rp));
+		return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_DISCONNECT,
+					 MGMT_STATUS_INVALID_PARAMS,
+					 &rp, sizeof(rp));
 
 	hci_dev_lock(hdev);
 
 	if (!test_bit(HCI_UP, &hdev->flags)) {
-		err = cmd_complete(sk, hdev->id, MGMT_OP_DISCONNECT,
-				   MGMT_STATUS_NOT_POWERED, &rp, sizeof(rp));
+		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_DISCONNECT,
+					MGMT_STATUS_NOT_POWERED, &rp,
+					sizeof(rp));
 		goto failed;
 	}
 
-	if (mgmt_pending_find(MGMT_OP_DISCONNECT, hdev)) {
-		err = cmd_complete(sk, hdev->id, MGMT_OP_DISCONNECT,
-				   MGMT_STATUS_BUSY, &rp, sizeof(rp));
+	if (pending_find(MGMT_OP_DISCONNECT, hdev)) {
+		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_DISCONNECT,
+					MGMT_STATUS_BUSY, &rp, sizeof(rp));
 		goto failed;
 	}
 
@@ -2824,8 +3068,9 @@ static int disconnect(struct sock *sk, struct hci_dev *hdev, void *data,
 		conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, &cp->addr.bdaddr);
 
 	if (!conn || conn->state == BT_OPEN || conn->state == BT_CLOSED) {
-		err = cmd_complete(sk, hdev->id, MGMT_OP_DISCONNECT,
-				   MGMT_STATUS_NOT_CONNECTED, &rp, sizeof(rp));
+		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_DISCONNECT,
+					MGMT_STATUS_NOT_CONNECTED, &rp,
+					sizeof(rp));
 		goto failed;
 	}
 
@@ -2835,6 +3080,8 @@ static int disconnect(struct sock *sk, struct hci_dev *hdev, void *data,
 		goto failed;
 	}
 
+	cmd->cmd_complete = generic_cmd_complete;
+
 	err = hci_disconnect(conn, HCI_ERROR_REMOTE_USER_TERM);
 	if (err < 0)
 		mgmt_pending_remove(cmd);
@@ -2877,8 +3124,8 @@ static int get_connections(struct sock *sk, struct hci_dev *hdev, void *data,
 	hci_dev_lock(hdev);
 
 	if (!hdev_is_powered(hdev)) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_GET_CONNECTIONS,
-				 MGMT_STATUS_NOT_POWERED);
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_GET_CONNECTIONS,
+				      MGMT_STATUS_NOT_POWERED);
 		goto unlock;
 	}
 
@@ -2911,8 +3158,8 @@ static int get_connections(struct sock *sk, struct hci_dev *hdev, void *data,
 	/* Recalculate length in case of filtered SCO connections, etc */
 	rp_len = sizeof(*rp) + (i * sizeof(struct mgmt_addr_info));
 
-	err = cmd_complete(sk, hdev->id, MGMT_OP_GET_CONNECTIONS, 0, rp,
-			   rp_len);
+	err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_GET_CONNECTIONS, 0, rp,
+				rp_len);
 
 	kfree(rp);
 
@@ -2924,7 +3171,7 @@ unlock:
 static int send_pin_code_neg_reply(struct sock *sk, struct hci_dev *hdev,
 				   struct mgmt_cp_pin_code_neg_reply *cp)
 {
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 	int err;
 
 	cmd = mgmt_pending_add(sk, MGMT_OP_PIN_CODE_NEG_REPLY, hdev, cp,
@@ -2946,7 +3193,7 @@ static int pin_code_reply(struct sock *sk, struct hci_dev *hdev, void *data,
 	struct hci_conn *conn;
 	struct mgmt_cp_pin_code_reply *cp = data;
 	struct hci_cp_pin_code_reply reply;
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 	int err;
 
 	BT_DBG("");
@@ -2954,15 +3201,15 @@ static int pin_code_reply(struct sock *sk, struct hci_dev *hdev, void *data,
 	hci_dev_lock(hdev);
 
 	if (!hdev_is_powered(hdev)) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_PIN_CODE_REPLY,
-				 MGMT_STATUS_NOT_POWERED);
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_PIN_CODE_REPLY,
+				      MGMT_STATUS_NOT_POWERED);
 		goto failed;
 	}
 
 	conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &cp->addr.bdaddr);
 	if (!conn) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_PIN_CODE_REPLY,
-				 MGMT_STATUS_NOT_CONNECTED);
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_PIN_CODE_REPLY,
+				      MGMT_STATUS_NOT_CONNECTED);
 		goto failed;
 	}
 
@@ -2975,8 +3222,8 @@ static int pin_code_reply(struct sock *sk, struct hci_dev *hdev, void *data,
 
 		err = send_pin_code_neg_reply(sk, hdev, &ncp);
 		if (err >= 0)
-			err = cmd_status(sk, hdev->id, MGMT_OP_PIN_CODE_REPLY,
-					 MGMT_STATUS_INVALID_PARAMS);
+			err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_PIN_CODE_REPLY,
+					      MGMT_STATUS_INVALID_PARAMS);
 
 		goto failed;
 	}
@@ -2987,6 +3234,8 @@ static int pin_code_reply(struct sock *sk, struct hci_dev *hdev, void *data,
 		goto failed;
 	}
 
+	cmd->cmd_complete = addr_cmd_complete;
+
 	bacpy(&reply.bdaddr, &cp->addr.bdaddr);
 	reply.pin_len = cp->pin_len;
 	memcpy(reply.pin_code, cp->pin_code, sizeof(reply.pin_code));
@@ -3008,8 +3257,8 @@ static int set_io_capability(struct sock *sk, struct hci_dev *hdev, void *data,
 	BT_DBG("");
 
 	if (cp->io_capability > SMP_IO_KEYBOARD_DISPLAY)
-		return cmd_complete(sk, hdev->id, MGMT_OP_SET_IO_CAPABILITY,
-				    MGMT_STATUS_INVALID_PARAMS, NULL, 0);
+		return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_SET_IO_CAPABILITY,
+					 MGMT_STATUS_INVALID_PARAMS, NULL, 0);
 
 	hci_dev_lock(hdev);
 
@@ -3020,14 +3269,14 @@ static int set_io_capability(struct sock *sk, struct hci_dev *hdev, void *data,
 
 	hci_dev_unlock(hdev);
 
-	return cmd_complete(sk, hdev->id, MGMT_OP_SET_IO_CAPABILITY, 0, NULL,
-			    0);
+	return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_SET_IO_CAPABILITY, 0,
+				 NULL, 0);
 }
 
-static struct pending_cmd *find_pairing(struct hci_conn *conn)
+static struct mgmt_pending_cmd *find_pairing(struct hci_conn *conn)
 {
 	struct hci_dev *hdev = conn->hdev;
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 
 	list_for_each_entry(cmd, &hdev->mgmt_pending, list) {
 		if (cmd->opcode != MGMT_OP_PAIR_DEVICE)
@@ -3042,16 +3291,17 @@ static struct pending_cmd *find_pairing(struct hci_conn *conn)
 	return NULL;
 }
 
-static void pairing_complete(struct pending_cmd *cmd, u8 status)
+static int pairing_complete(struct mgmt_pending_cmd *cmd, u8 status)
 {
 	struct mgmt_rp_pair_device rp;
 	struct hci_conn *conn = cmd->user_data;
+	int err;
 
 	bacpy(&rp.addr.bdaddr, &conn->dst);
 	rp.addr.type = link_to_bdaddr(conn->type, conn->dst_type);
 
-	cmd_complete(cmd->sk, cmd->index, MGMT_OP_PAIR_DEVICE, status,
-		     &rp, sizeof(rp));
+	err = mgmt_cmd_complete(cmd->sk, cmd->index, MGMT_OP_PAIR_DEVICE,
+				status, &rp, sizeof(rp));
 
 	/* So we don't get further callbacks for this connection */
 	conn->connect_cfm_cb = NULL;
@@ -3059,37 +3309,48 @@ static void pairing_complete(struct pending_cmd *cmd, u8 status)
 	conn->disconn_cfm_cb = NULL;
 
 	hci_conn_drop(conn);
+
+	/* The device is paired so there is no need to remove
+	 * its connection parameters anymore.
+	 */
+	clear_bit(HCI_CONN_PARAM_REMOVAL_PEND, &conn->flags);
+
 	hci_conn_put(conn);
 
-	mgmt_pending_remove(cmd);
+	return err;
 }
 
 void mgmt_smp_complete(struct hci_conn *conn, bool complete)
 {
 	u8 status = complete ? MGMT_STATUS_SUCCESS : MGMT_STATUS_FAILED;
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 
 	cmd = find_pairing(conn);
-	if (cmd)
-		pairing_complete(cmd, status);
+	if (cmd) {
+		cmd->cmd_complete(cmd, status);
+		mgmt_pending_remove(cmd);
+	}
 }
 
 static void pairing_complete_cb(struct hci_conn *conn, u8 status)
 {
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 
 	BT_DBG("status %u", status);
 
 	cmd = find_pairing(conn);
-	if (!cmd)
+	if (!cmd) {
 		BT_DBG("Unable to find a pending command");
-	else
-		pairing_complete(cmd, mgmt_status(status));
+		return;
+	}
+
+	cmd->cmd_complete(cmd, mgmt_status(status));
+	mgmt_pending_remove(cmd);
 }
 
 static void le_pairing_complete_cb(struct hci_conn *conn, u8 status)
 {
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 
 	BT_DBG("status %u", status);
 
@@ -3097,10 +3358,13 @@ static void le_pairing_complete_cb(struct hci_conn *conn, u8 status)
 		return;
 
 	cmd = find_pairing(conn);
-	if (!cmd)
+	if (!cmd) {
 		BT_DBG("Unable to find a pending command");
-	else
-		pairing_complete(cmd, mgmt_status(status));
+		return;
+	}
+
+	cmd->cmd_complete(cmd, mgmt_status(status));
+	mgmt_pending_remove(cmd);
 }
 
 static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data,
@@ -3108,7 +3372,7 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data,
 {
 	struct mgmt_cp_pair_device *cp = data;
 	struct mgmt_rp_pair_device rp;
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 	u8 sec_level, auth_type;
 	struct hci_conn *conn;
 	int err;
@@ -3120,20 +3384,28 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data,
 	rp.addr.type = cp->addr.type;
 
 	if (!bdaddr_type_is_valid(cp->addr.type))
-		return cmd_complete(sk, hdev->id, MGMT_OP_PAIR_DEVICE,
-				    MGMT_STATUS_INVALID_PARAMS,
-				    &rp, sizeof(rp));
+		return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_PAIR_DEVICE,
+					 MGMT_STATUS_INVALID_PARAMS,
+					 &rp, sizeof(rp));
 
 	if (cp->io_cap > SMP_IO_KEYBOARD_DISPLAY)
-		return cmd_complete(sk, hdev->id, MGMT_OP_PAIR_DEVICE,
-				    MGMT_STATUS_INVALID_PARAMS,
-				    &rp, sizeof(rp));
+		return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_PAIR_DEVICE,
+					 MGMT_STATUS_INVALID_PARAMS,
+					 &rp, sizeof(rp));
 
 	hci_dev_lock(hdev);
 
 	if (!hdev_is_powered(hdev)) {
-		err = cmd_complete(sk, hdev->id, MGMT_OP_PAIR_DEVICE,
-				   MGMT_STATUS_NOT_POWERED, &rp, sizeof(rp));
+		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_PAIR_DEVICE,
+					MGMT_STATUS_NOT_POWERED, &rp,
+					sizeof(rp));
+		goto unlock;
+	}
+
+	if (hci_bdaddr_is_paired(hdev, &cp->addr.bdaddr, cp->addr.type)) {
+		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_PAIR_DEVICE,
+					MGMT_STATUS_ALREADY_PAIRED, &rp,
+					sizeof(rp));
 		goto unlock;
 	}
 
@@ -3174,19 +3446,22 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data,
 
 		if (PTR_ERR(conn) == -EBUSY)
 			status = MGMT_STATUS_BUSY;
+		else if (PTR_ERR(conn) == -EOPNOTSUPP)
+			status = MGMT_STATUS_NOT_SUPPORTED;
+		else if (PTR_ERR(conn) == -ECONNREFUSED)
+			status = MGMT_STATUS_REJECTED;
 		else
 			status = MGMT_STATUS_CONNECT_FAILED;
 
-		err = cmd_complete(sk, hdev->id, MGMT_OP_PAIR_DEVICE,
-				   status, &rp,
-				   sizeof(rp));
+		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_PAIR_DEVICE,
+					status, &rp, sizeof(rp));
 		goto unlock;
 	}
 
 	if (conn->connect_cfm_cb) {
 		hci_conn_drop(conn);
-		err = cmd_complete(sk, hdev->id, MGMT_OP_PAIR_DEVICE,
-				   MGMT_STATUS_BUSY, &rp, sizeof(rp));
+		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_PAIR_DEVICE,
+					MGMT_STATUS_BUSY, &rp, sizeof(rp));
 		goto unlock;
 	}
 
@@ -3197,6 +3472,8 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data,
 		goto unlock;
 	}
 
+	cmd->cmd_complete = pairing_complete;
+
 	/* For LE, just connecting isn't a proof that the pairing finished */
 	if (cp->addr.type == BDADDR_BREDR) {
 		conn->connect_cfm_cb = pairing_complete_cb;
@@ -3212,8 +3489,10 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data,
 	cmd->user_data = hci_conn_get(conn);
 
 	if ((conn->state == BT_CONNECTED || conn->state == BT_CONFIG) &&
-	    hci_conn_security(conn, sec_level, auth_type, true))
-		pairing_complete(cmd, 0);
+	    hci_conn_security(conn, sec_level, auth_type, true)) {
+		cmd->cmd_complete(cmd, 0);
+		mgmt_pending_remove(cmd);
+	}
 
 	err = 0;
 
@@ -3226,7 +3505,7 @@ static int cancel_pair_device(struct sock *sk, struct hci_dev *hdev, void *data,
 			      u16 len)
 {
 	struct mgmt_addr_info *addr = data;
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 	struct hci_conn *conn;
 	int err;
 
@@ -3235,30 +3514,31 @@ static int cancel_pair_device(struct sock *sk, struct hci_dev *hdev, void *data,
 	hci_dev_lock(hdev);
 
 	if (!hdev_is_powered(hdev)) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_CANCEL_PAIR_DEVICE,
-				 MGMT_STATUS_NOT_POWERED);
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_CANCEL_PAIR_DEVICE,
+				      MGMT_STATUS_NOT_POWERED);
 		goto unlock;
 	}
 
-	cmd = mgmt_pending_find(MGMT_OP_PAIR_DEVICE, hdev);
+	cmd = pending_find(MGMT_OP_PAIR_DEVICE, hdev);
 	if (!cmd) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_CANCEL_PAIR_DEVICE,
-				 MGMT_STATUS_INVALID_PARAMS);
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_CANCEL_PAIR_DEVICE,
+				      MGMT_STATUS_INVALID_PARAMS);
 		goto unlock;
 	}
 
 	conn = cmd->user_data;
 
 	if (bacmp(&addr->bdaddr, &conn->dst) != 0) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_CANCEL_PAIR_DEVICE,
-				 MGMT_STATUS_INVALID_PARAMS);
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_CANCEL_PAIR_DEVICE,
+				      MGMT_STATUS_INVALID_PARAMS);
 		goto unlock;
 	}
 
-	pairing_complete(cmd, MGMT_STATUS_CANCELLED);
+	cmd->cmd_complete(cmd, MGMT_STATUS_CANCELLED);
+	mgmt_pending_remove(cmd);
 
-	err = cmd_complete(sk, hdev->id, MGMT_OP_CANCEL_PAIR_DEVICE, 0,
-			   addr, sizeof(*addr));
+	err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_CANCEL_PAIR_DEVICE, 0,
+				addr, sizeof(*addr));
 unlock:
 	hci_dev_unlock(hdev);
 	return err;
@@ -3268,16 +3548,16 @@ static int user_pairing_resp(struct sock *sk, struct hci_dev *hdev,
 			     struct mgmt_addr_info *addr, u16 mgmt_op,
 			     u16 hci_op, __le32 passkey)
 {
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 	struct hci_conn *conn;
 	int err;
 
 	hci_dev_lock(hdev);
 
 	if (!hdev_is_powered(hdev)) {
-		err = cmd_complete(sk, hdev->id, mgmt_op,
-				   MGMT_STATUS_NOT_POWERED, addr,
-				   sizeof(*addr));
+		err = mgmt_cmd_complete(sk, hdev->id, mgmt_op,
+					MGMT_STATUS_NOT_POWERED, addr,
+					sizeof(*addr));
 		goto done;
 	}
 
@@ -3287,22 +3567,22 @@ static int user_pairing_resp(struct sock *sk, struct hci_dev *hdev,
 		conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, &addr->bdaddr);
 
 	if (!conn) {
-		err = cmd_complete(sk, hdev->id, mgmt_op,
-				   MGMT_STATUS_NOT_CONNECTED, addr,
-				   sizeof(*addr));
+		err = mgmt_cmd_complete(sk, hdev->id, mgmt_op,
+					MGMT_STATUS_NOT_CONNECTED, addr,
+					sizeof(*addr));
 		goto done;
 	}
 
 	if (addr->type == BDADDR_LE_PUBLIC || addr->type == BDADDR_LE_RANDOM) {
 		err = smp_user_confirm_reply(conn, mgmt_op, passkey);
 		if (!err)
-			err = cmd_complete(sk, hdev->id, mgmt_op,
-					   MGMT_STATUS_SUCCESS, addr,
-					   sizeof(*addr));
+			err = mgmt_cmd_complete(sk, hdev->id, mgmt_op,
+						MGMT_STATUS_SUCCESS, addr,
+						sizeof(*addr));
 		else
-			err = cmd_complete(sk, hdev->id, mgmt_op,
-					   MGMT_STATUS_FAILED, addr,
-					   sizeof(*addr));
+			err = mgmt_cmd_complete(sk, hdev->id, mgmt_op,
+						MGMT_STATUS_FAILED, addr,
+						sizeof(*addr));
 
 		goto done;
 	}
@@ -3313,6 +3593,8 @@ static int user_pairing_resp(struct sock *sk, struct hci_dev *hdev,
 		goto done;
 	}
 
+	cmd->cmd_complete = addr_cmd_complete;
+
 	/* Continue with pairing via HCI */
 	if (hci_op == HCI_OP_USER_PASSKEY_REPLY) {
 		struct hci_cp_user_passkey_reply cp;
@@ -3352,8 +3634,8 @@ static int user_confirm_reply(struct sock *sk, struct hci_dev *hdev, void *data,
 	BT_DBG("");
 
 	if (len != sizeof(*cp))
-		return cmd_status(sk, hdev->id, MGMT_OP_USER_CONFIRM_REPLY,
-				  MGMT_STATUS_INVALID_PARAMS);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_USER_CONFIRM_REPLY,
+				       MGMT_STATUS_INVALID_PARAMS);
 
 	return user_pairing_resp(sk, hdev, &cp->addr,
 				 MGMT_OP_USER_CONFIRM_REPLY,
@@ -3406,27 +3688,27 @@ static void update_name(struct hci_request *req)
 	hci_req_add(req, HCI_OP_WRITE_LOCAL_NAME, sizeof(cp), &cp);
 }
 
-static void set_name_complete(struct hci_dev *hdev, u8 status)
+static void set_name_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
 	struct mgmt_cp_set_local_name *cp;
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 
 	BT_DBG("status 0x%02x", status);
 
 	hci_dev_lock(hdev);
 
-	cmd = mgmt_pending_find(MGMT_OP_SET_LOCAL_NAME, hdev);
+	cmd = pending_find(MGMT_OP_SET_LOCAL_NAME, hdev);
 	if (!cmd)
 		goto unlock;
 
 	cp = cmd->param;
 
 	if (status)
-		cmd_status(cmd->sk, hdev->id, MGMT_OP_SET_LOCAL_NAME,
-			   mgmt_status(status));
+		mgmt_cmd_status(cmd->sk, hdev->id, MGMT_OP_SET_LOCAL_NAME,
+			        mgmt_status(status));
 	else
-		cmd_complete(cmd->sk, hdev->id, MGMT_OP_SET_LOCAL_NAME, 0,
-			     cp, sizeof(*cp));
+		mgmt_cmd_complete(cmd->sk, hdev->id, MGMT_OP_SET_LOCAL_NAME, 0,
+				  cp, sizeof(*cp));
 
 	mgmt_pending_remove(cmd);
 
@@ -3438,7 +3720,7 @@ static int set_local_name(struct sock *sk, struct hci_dev *hdev, void *data,
 			  u16 len)
 {
 	struct mgmt_cp_set_local_name *cp = data;
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 	struct hci_request req;
 	int err;
 
@@ -3452,8 +3734,8 @@ static int set_local_name(struct sock *sk, struct hci_dev *hdev, void *data,
 	if (!memcmp(hdev->dev_name, cp->name, sizeof(hdev->dev_name)) &&
 	    !memcmp(hdev->short_name, cp->short_name,
 		    sizeof(hdev->short_name))) {
-		err = cmd_complete(sk, hdev->id, MGMT_OP_SET_LOCAL_NAME, 0,
-				   data, len);
+		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_SET_LOCAL_NAME, 0,
+					data, len);
 		goto failed;
 	}
 
@@ -3462,13 +3744,13 @@ static int set_local_name(struct sock *sk, struct hci_dev *hdev, void *data,
 	if (!hdev_is_powered(hdev)) {
 		memcpy(hdev->dev_name, cp->name, sizeof(hdev->dev_name));
 
-		err = cmd_complete(sk, hdev->id, MGMT_OP_SET_LOCAL_NAME, 0,
-				   data, len);
+		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_SET_LOCAL_NAME, 0,
+					data, len);
 		if (err < 0)
 			goto failed;
 
-		err = mgmt_event(MGMT_EV_LOCAL_NAME_CHANGED, hdev, data, len,
-				 sk);
+		err = mgmt_generic_event(MGMT_EV_LOCAL_NAME_CHANGED, hdev,
+					 data, len, sk);
 
 		goto failed;
 	}
@@ -3503,10 +3785,70 @@ failed:
 	return err;
 }
 
+static void read_local_oob_data_complete(struct hci_dev *hdev, u8 status,
+				         u16 opcode, struct sk_buff *skb)
+{
+	struct mgmt_rp_read_local_oob_data mgmt_rp;
+	size_t rp_size = sizeof(mgmt_rp);
+	struct mgmt_pending_cmd *cmd;
+
+	BT_DBG("%s status %u", hdev->name, status);
+
+	cmd = pending_find(MGMT_OP_READ_LOCAL_OOB_DATA, hdev);
+	if (!cmd)
+		return;
+
+	if (status || !skb) {
+		mgmt_cmd_status(cmd->sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA,
+				status ? mgmt_status(status) : MGMT_STATUS_FAILED);
+		goto remove;
+	}
+
+	memset(&mgmt_rp, 0, sizeof(mgmt_rp));
+
+	if (opcode == HCI_OP_READ_LOCAL_OOB_DATA) {
+		struct hci_rp_read_local_oob_data *rp = (void *) skb->data;
+
+		if (skb->len < sizeof(*rp)) {
+			mgmt_cmd_status(cmd->sk, hdev->id,
+					MGMT_OP_READ_LOCAL_OOB_DATA,
+					MGMT_STATUS_FAILED);
+			goto remove;
+		}
+
+		memcpy(mgmt_rp.hash192, rp->hash, sizeof(rp->hash));
+		memcpy(mgmt_rp.rand192, rp->rand, sizeof(rp->rand));
+
+		rp_size -= sizeof(mgmt_rp.hash256) + sizeof(mgmt_rp.rand256);
+	} else {
+		struct hci_rp_read_local_oob_ext_data *rp = (void *) skb->data;
+
+		if (skb->len < sizeof(*rp)) {
+			mgmt_cmd_status(cmd->sk, hdev->id,
+					MGMT_OP_READ_LOCAL_OOB_DATA,
+					MGMT_STATUS_FAILED);
+			goto remove;
+		}
+
+		memcpy(mgmt_rp.hash192, rp->hash192, sizeof(rp->hash192));
+		memcpy(mgmt_rp.rand192, rp->rand192, sizeof(rp->rand192));
+
+		memcpy(mgmt_rp.hash256, rp->hash256, sizeof(rp->hash256));
+		memcpy(mgmt_rp.rand256, rp->rand256, sizeof(rp->rand256));
+	}
+
+	mgmt_cmd_complete(cmd->sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA,
+			  MGMT_STATUS_SUCCESS, &mgmt_rp, rp_size);
+
+remove:
+	mgmt_pending_remove(cmd);
+}
+
 static int read_local_oob_data(struct sock *sk, struct hci_dev *hdev,
 			       void *data, u16 data_len)
 {
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
+	struct hci_request req;
 	int err;
 
 	BT_DBG("%s", hdev->name);
@@ -3514,20 +3856,20 @@ static int read_local_oob_data(struct sock *sk, struct hci_dev *hdev,
 	hci_dev_lock(hdev);
 
 	if (!hdev_is_powered(hdev)) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA,
-				 MGMT_STATUS_NOT_POWERED);
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA,
+				      MGMT_STATUS_NOT_POWERED);
 		goto unlock;
 	}
 
 	if (!lmp_ssp_capable(hdev)) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA,
-				 MGMT_STATUS_NOT_SUPPORTED);
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA,
+				      MGMT_STATUS_NOT_SUPPORTED);
 		goto unlock;
 	}
 
-	if (mgmt_pending_find(MGMT_OP_READ_LOCAL_OOB_DATA, hdev)) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA,
-				 MGMT_STATUS_BUSY);
+	if (pending_find(MGMT_OP_READ_LOCAL_OOB_DATA, hdev)) {
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA,
+				      MGMT_STATUS_BUSY);
 		goto unlock;
 	}
 
@@ -3537,12 +3879,14 @@ static int read_local_oob_data(struct sock *sk, struct hci_dev *hdev,
 		goto unlock;
 	}
 
-	if (test_bit(HCI_SC_ENABLED, &hdev->dev_flags))
-		err = hci_send_cmd(hdev, HCI_OP_READ_LOCAL_OOB_EXT_DATA,
-				   0, NULL);
+	hci_req_init(&req, hdev);
+
+	if (bredr_sc_enabled(hdev))
+		hci_req_add(&req, HCI_OP_READ_LOCAL_OOB_EXT_DATA, 0, NULL);
 	else
-		err = hci_send_cmd(hdev, HCI_OP_READ_LOCAL_OOB_DATA, 0, NULL);
+		hci_req_add(&req, HCI_OP_READ_LOCAL_OOB_DATA, 0, NULL);
 
+	err = hci_req_run_skb(&req, read_local_oob_data_complete);
 	if (err < 0)
 		mgmt_pending_remove(cmd);
 
@@ -3554,47 +3898,106 @@ unlock:
 static int add_remote_oob_data(struct sock *sk, struct hci_dev *hdev,
 			       void *data, u16 len)
 {
+	struct mgmt_addr_info *addr = data;
 	int err;
 
 	BT_DBG("%s ", hdev->name);
 
+	if (!bdaddr_type_is_valid(addr->type))
+		return mgmt_cmd_complete(sk, hdev->id,
+					 MGMT_OP_ADD_REMOTE_OOB_DATA,
+					 MGMT_STATUS_INVALID_PARAMS,
+					 addr, sizeof(*addr));
+
 	hci_dev_lock(hdev);
 
 	if (len == MGMT_ADD_REMOTE_OOB_DATA_SIZE) {
 		struct mgmt_cp_add_remote_oob_data *cp = data;
 		u8 status;
 
+		if (cp->addr.type != BDADDR_BREDR) {
+			err = mgmt_cmd_complete(sk, hdev->id,
+						MGMT_OP_ADD_REMOTE_OOB_DATA,
+						MGMT_STATUS_INVALID_PARAMS,
+						&cp->addr, sizeof(cp->addr));
+			goto unlock;
+		}
+
 		err = hci_add_remote_oob_data(hdev, &cp->addr.bdaddr,
-					      cp->hash, cp->randomizer);
+					      cp->addr.type, cp->hash,
+					      cp->rand, NULL, NULL);
 		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));
+		err = mgmt_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 *rand192, *hash192, *rand256, *hash256;
 		u8 status;
 
-		err = hci_add_remote_oob_ext_data(hdev, &cp->addr.bdaddr,
-						  cp->hash192,
-						  cp->randomizer192,
-						  cp->hash256,
-						  cp->randomizer256);
+		if (bdaddr_type_is_le(cp->addr.type)) {
+			/* Enforce zero-valued 192-bit parameters as
+			 * long as legacy SMP OOB isn't implemented.
+			 */
+			if (memcmp(cp->rand192, ZERO_KEY, 16) ||
+			    memcmp(cp->hash192, ZERO_KEY, 16)) {
+				err = mgmt_cmd_complete(sk, hdev->id,
+							MGMT_OP_ADD_REMOTE_OOB_DATA,
+							MGMT_STATUS_INVALID_PARAMS,
+							addr, sizeof(*addr));
+				goto unlock;
+			}
+
+			rand192 = NULL;
+			hash192 = NULL;
+		} else {
+			/* In case one of the P-192 values is set to zero,
+			 * then just disable OOB data for P-192.
+			 */
+			if (!memcmp(cp->rand192, ZERO_KEY, 16) ||
+			    !memcmp(cp->hash192, ZERO_KEY, 16)) {
+				rand192 = NULL;
+				hash192 = NULL;
+			} else {
+				rand192 = cp->rand192;
+				hash192 = cp->hash192;
+			}
+		}
+
+		/* In case one of the P-256 values is set to zero, then just
+		 * disable OOB data for P-256.
+		 */
+		if (!memcmp(cp->rand256, ZERO_KEY, 16) ||
+		    !memcmp(cp->hash256, ZERO_KEY, 16)) {
+			rand256 = NULL;
+			hash256 = NULL;
+		} else {
+			rand256 = cp->rand256;
+			hash256 = cp->hash256;
+		}
+
+		err = hci_add_remote_oob_data(hdev, &cp->addr.bdaddr,
+					      cp->addr.type, hash192, rand192,
+					      hash256, rand256);
 		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));
+		err = mgmt_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);
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_REMOTE_OOB_DATA,
+				      MGMT_STATUS_INVALID_PARAMS);
 	}
 
+unlock:
 	hci_dev_unlock(hdev);
 	return err;
 }
@@ -3608,93 +4011,251 @@ static int remove_remote_oob_data(struct sock *sk, struct hci_dev *hdev,
 
 	BT_DBG("%s", hdev->name);
 
+	if (cp->addr.type != BDADDR_BREDR)
+		return mgmt_cmd_complete(sk, hdev->id,
+					 MGMT_OP_REMOVE_REMOTE_OOB_DATA,
+					 MGMT_STATUS_INVALID_PARAMS,
+					 &cp->addr, sizeof(cp->addr));
+
 	hci_dev_lock(hdev);
 
-	err = hci_remove_remote_oob_data(hdev, &cp->addr.bdaddr);
+	if (!bacmp(&cp->addr.bdaddr, BDADDR_ANY)) {
+		hci_remote_oob_data_clear(hdev);
+		status = MGMT_STATUS_SUCCESS;
+		goto done;
+	}
+
+	err = hci_remove_remote_oob_data(hdev, &cp->addr.bdaddr, cp->addr.type);
 	if (err < 0)
 		status = MGMT_STATUS_INVALID_PARAMS;
 	else
 		status = MGMT_STATUS_SUCCESS;
 
-	err = cmd_complete(sk, hdev->id, MGMT_OP_REMOVE_REMOTE_OOB_DATA,
-			   status, &cp->addr, sizeof(cp->addr));
+done:
+	err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_REMOVE_REMOTE_OOB_DATA,
+				status, &cp->addr, sizeof(cp->addr));
 
 	hci_dev_unlock(hdev);
 	return err;
 }
 
-static int mgmt_start_discovery_failed(struct hci_dev *hdev, u8 status)
+static bool trigger_bredr_inquiry(struct hci_request *req, u8 *status)
 {
-	struct pending_cmd *cmd;
-	u8 type;
+	struct hci_dev *hdev = req->hdev;
+	struct hci_cp_inquiry cp;
+	/* General inquiry access code (GIAC) */
+	u8 lap[3] = { 0x33, 0x8b, 0x9e };
+
+	*status = mgmt_bredr_support(hdev);
+	if (*status)
+		return false;
+
+	if (hci_dev_test_flag(hdev, HCI_INQUIRY)) {
+		*status = MGMT_STATUS_BUSY;
+		return false;
+	}
+
+	hci_inquiry_cache_flush(hdev);
+
+	memset(&cp, 0, sizeof(cp));
+	memcpy(&cp.lap, lap, sizeof(cp.lap));
+	cp.length = DISCOV_BREDR_INQUIRY_LEN;
+
+	hci_req_add(req, HCI_OP_INQUIRY, sizeof(cp), &cp);
+
+	return true;
+}
+
+static bool trigger_le_scan(struct hci_request *req, u16 interval, u8 *status)
+{
+	struct hci_dev *hdev = req->hdev;
+	struct hci_cp_le_set_scan_param param_cp;
+	struct hci_cp_le_set_scan_enable enable_cp;
+	u8 own_addr_type;
 	int err;
 
-	hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
+	*status = mgmt_le_support(hdev);
+	if (*status)
+		return false;
 
-	cmd = mgmt_pending_find(MGMT_OP_START_DISCOVERY, hdev);
-	if (!cmd)
-		return -ENOENT;
+	if (hci_dev_test_flag(hdev, HCI_LE_ADV)) {
+		/* Don't let discovery abort an outgoing connection attempt
+		 * that's using directed advertising.
+		 */
+		if (hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT)) {
+			*status = MGMT_STATUS_REJECTED;
+			return false;
+		}
 
-	type = hdev->discovery.type;
+		disable_advertising(req);
+	}
 
-	err = cmd_complete(cmd->sk, hdev->id, cmd->opcode, mgmt_status(status),
-			   &type, sizeof(type));
-	mgmt_pending_remove(cmd);
+	/* 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 (hci_dev_test_flag(hdev, HCI_LE_SCAN))
+		hci_req_add_le_scan_disable(req);
 
-	return err;
+	/* All active scans will be done with either a resolvable private
+	 * address (when privacy feature has been enabled) or non-resolvable
+	 * private address.
+	 */
+	err = hci_update_random_address(req, true, &own_addr_type);
+	if (err < 0) {
+		*status = MGMT_STATUS_FAILED;
+		return false;
+	}
+
+	memset(&param_cp, 0, sizeof(param_cp));
+	param_cp.type = LE_SCAN_ACTIVE;
+	param_cp.interval = cpu_to_le16(interval);
+	param_cp.window = cpu_to_le16(DISCOV_LE_SCAN_WIN);
+	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);
+
+	return true;
 }
 
-static void start_discovery_complete(struct hci_dev *hdev, u8 status)
+static bool trigger_discovery(struct hci_request *req, u8 *status)
 {
-	unsigned long timeout = 0;
+	struct hci_dev *hdev = req->hdev;
+
+	switch (hdev->discovery.type) {
+	case DISCOV_TYPE_BREDR:
+		if (!trigger_bredr_inquiry(req, status))
+			return false;
+		break;
+
+	case DISCOV_TYPE_INTERLEAVED:
+		if (test_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY,
+			     &hdev->quirks)) {
+			/* During simultaneous discovery, we double LE scan
+			 * interval. We must leave some time for the controller
+			 * to do BR/EDR inquiry.
+			 */
+			if (!trigger_le_scan(req, DISCOV_LE_SCAN_INT * 2,
+					     status))
+				return false;
+
+			if (!trigger_bredr_inquiry(req, status))
+				return false;
+
+			return true;
+		}
+
+		if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) {
+			*status = MGMT_STATUS_NOT_SUPPORTED;
+			return false;
+		}
+		/* fall through */
+
+	case DISCOV_TYPE_LE:
+		if (!trigger_le_scan(req, DISCOV_LE_SCAN_INT, status))
+			return false;
+		break;
+
+	default:
+		*status = MGMT_STATUS_INVALID_PARAMS;
+		return false;
+	}
+
+	return true;
+}
+
+static void start_discovery_complete(struct hci_dev *hdev, u8 status,
+				     u16 opcode)
+{
+	struct mgmt_pending_cmd *cmd;
+	unsigned long timeout;
 
 	BT_DBG("status %d", status);
 
+	hci_dev_lock(hdev);
+
+	cmd = pending_find(MGMT_OP_START_DISCOVERY, hdev);
+	if (!cmd)
+		cmd = pending_find(MGMT_OP_START_SERVICE_DISCOVERY, hdev);
+
+	if (cmd) {
+		cmd->cmd_complete(cmd, mgmt_status(status));
+		mgmt_pending_remove(cmd);
+	}
+
 	if (status) {
-		hci_dev_lock(hdev);
-		mgmt_start_discovery_failed(hdev, status);
-		hci_dev_unlock(hdev);
-		return;
+		hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
+		goto unlock;
 	}
 
-	hci_dev_lock(hdev);
 	hci_discovery_set_state(hdev, DISCOVERY_FINDING);
-	hci_dev_unlock(hdev);
 
+	/* If the scan involves LE scan, pick proper timeout to schedule
+	 * hdev->le_scan_disable that will stop it.
+	 */
 	switch (hdev->discovery.type) {
 	case DISCOV_TYPE_LE:
 		timeout = msecs_to_jiffies(DISCOV_LE_TIMEOUT);
 		break;
-
 	case DISCOV_TYPE_INTERLEAVED:
-		timeout = msecs_to_jiffies(hdev->discov_interleaved_timeout);
+		 /* When running simultaneous discovery, the LE scanning time
+		 * should occupy the whole discovery time sine BR/EDR inquiry
+		 * and LE scanning are scheduled by the controller.
+		 *
+		 * For interleaving discovery in comparison, BR/EDR inquiry
+		 * and LE scanning are done sequentially with separate
+		 * timeouts.
+		 */
+		if (test_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks))
+			timeout = msecs_to_jiffies(DISCOV_LE_TIMEOUT);
+		else
+			timeout = msecs_to_jiffies(hdev->discov_interleaved_timeout);
 		break;
-
 	case DISCOV_TYPE_BREDR:
+		timeout = 0;
 		break;
-
 	default:
 		BT_ERR("Invalid discovery type %d", hdev->discovery.type);
+		timeout = 0;
+		break;
 	}
 
-	if (!timeout)
-		return;
+	if (timeout) {
+		/* When service discovery is used and the controller has
+		 * a strict duplicate filter, it is important to remember
+		 * the start and duration of the scan. This is required
+		 * for restarting scanning during the discovery phase.
+		 */
+		if (test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER,
+			     &hdev->quirks) &&
+		    hdev->discovery.result_filtering) {
+			hdev->discovery.scan_start = jiffies;
+			hdev->discovery.scan_duration = timeout;
+		}
+
+		queue_delayed_work(hdev->workqueue,
+				   &hdev->le_scan_disable, timeout);
+	}
 
-	queue_delayed_work(hdev->workqueue, &hdev->le_scan_disable, timeout);
+unlock:
+	hci_dev_unlock(hdev);
 }
 
 static int start_discovery(struct sock *sk, struct hci_dev *hdev,
 			   void *data, u16 len)
 {
 	struct mgmt_cp_start_discovery *cp = data;
-	struct pending_cmd *cmd;
-	struct hci_cp_le_set_scan_param param_cp;
-	struct hci_cp_le_set_scan_enable enable_cp;
-	struct hci_cp_inquiry inq_cp;
+	struct mgmt_pending_cmd *cmd;
 	struct hci_request req;
-	/* General inquiry access code (GIAC) */
-	u8 lap[3] = { 0x33, 0x8b, 0x9e };
-	u8 status, own_addr_type;
+	u8 status;
 	int err;
 
 	BT_DBG("%s", hdev->name);
@@ -3702,176 +4263,191 @@ static int start_discovery(struct sock *sk, struct hci_dev *hdev,
 	hci_dev_lock(hdev);
 
 	if (!hdev_is_powered(hdev)) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_START_DISCOVERY,
-				 MGMT_STATUS_NOT_POWERED);
-		goto failed;
-	}
-
-	if (test_bit(HCI_PERIODIC_INQ, &hdev->dev_flags)) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_START_DISCOVERY,
-				 MGMT_STATUS_BUSY);
+		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_START_DISCOVERY,
+					MGMT_STATUS_NOT_POWERED,
+					&cp->type, sizeof(cp->type));
 		goto failed;
 	}
 
-	if (hdev->discovery.state != DISCOVERY_STOPPED) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_START_DISCOVERY,
-				 MGMT_STATUS_BUSY);
+	if (hdev->discovery.state != DISCOVERY_STOPPED ||
+	    hci_dev_test_flag(hdev, HCI_PERIODIC_INQ)) {
+		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_START_DISCOVERY,
+					MGMT_STATUS_BUSY, &cp->type,
+					sizeof(cp->type));
 		goto failed;
 	}
 
-	cmd = mgmt_pending_add(sk, MGMT_OP_START_DISCOVERY, hdev, NULL, 0);
+	cmd = mgmt_pending_add(sk, MGMT_OP_START_DISCOVERY, hdev, data, len);
 	if (!cmd) {
 		err = -ENOMEM;
 		goto failed;
 	}
 
+	cmd->cmd_complete = generic_cmd_complete;
+
+	/* Clear the discovery filter first to free any previously
+	 * allocated memory for the UUID list.
+	 */
+	hci_discovery_filter_clear(hdev);
+
 	hdev->discovery.type = cp->type;
+	hdev->discovery.report_invalid_rssi = false;
 
 	hci_req_init(&req, hdev);
 
-	switch (hdev->discovery.type) {
-	case DISCOV_TYPE_BREDR:
-		status = mgmt_bredr_support(hdev);
-		if (status) {
-			err = cmd_status(sk, hdev->id, MGMT_OP_START_DISCOVERY,
-					 status);
-			mgmt_pending_remove(cmd);
-			goto failed;
-		}
+	if (!trigger_discovery(&req, &status)) {
+		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_START_DISCOVERY,
+					status, &cp->type, sizeof(cp->type));
+		mgmt_pending_remove(cmd);
+		goto failed;
+	}
 
-		if (test_bit(HCI_INQUIRY, &hdev->flags)) {
-			err = cmd_status(sk, hdev->id, MGMT_OP_START_DISCOVERY,
-					 MGMT_STATUS_BUSY);
-			mgmt_pending_remove(cmd);
-			goto failed;
-		}
+	err = hci_req_run(&req, start_discovery_complete);
+	if (err < 0) {
+		mgmt_pending_remove(cmd);
+		goto failed;
+	}
 
-		hci_inquiry_cache_flush(hdev);
+	hci_discovery_set_state(hdev, DISCOVERY_STARTING);
 
-		memset(&inq_cp, 0, sizeof(inq_cp));
-		memcpy(&inq_cp.lap, lap, sizeof(inq_cp.lap));
-		inq_cp.length = DISCOV_BREDR_INQUIRY_LEN;
-		hci_req_add(&req, HCI_OP_INQUIRY, sizeof(inq_cp), &inq_cp);
-		break;
+failed:
+	hci_dev_unlock(hdev);
+	return err;
+}
 
-	case DISCOV_TYPE_LE:
-	case DISCOV_TYPE_INTERLEAVED:
-		status = mgmt_le_support(hdev);
-		if (status) {
-			err = cmd_status(sk, hdev->id, MGMT_OP_START_DISCOVERY,
-					 status);
-			mgmt_pending_remove(cmd);
-			goto failed;
-		}
+static int service_discovery_cmd_complete(struct mgmt_pending_cmd *cmd,
+					  u8 status)
+{
+	return mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, status,
+				 cmd->param, 1);
+}
 
-		if (hdev->discovery.type == DISCOV_TYPE_INTERLEAVED &&
-		    !test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) {
-			err = cmd_status(sk, hdev->id, MGMT_OP_START_DISCOVERY,
-					 MGMT_STATUS_NOT_SUPPORTED);
-			mgmt_pending_remove(cmd);
-			goto failed;
-		}
+static int start_service_discovery(struct sock *sk, struct hci_dev *hdev,
+				   void *data, u16 len)
+{
+	struct mgmt_cp_start_service_discovery *cp = data;
+	struct mgmt_pending_cmd *cmd;
+	struct hci_request req;
+	const u16 max_uuid_count = ((U16_MAX - sizeof(*cp)) / 16);
+	u16 uuid_count, expected_len;
+	u8 status;
+	int err;
 
-		if (test_bit(HCI_LE_ADV, &hdev->dev_flags)) {
-			/* Don't let discovery abort an outgoing
-			 * connection attempt that's using directed
-			 * advertising.
-			 */
-			if (hci_conn_hash_lookup_state(hdev, LE_LINK,
-						       BT_CONNECT)) {
-				err = cmd_status(sk, hdev->id,
-						 MGMT_OP_START_DISCOVERY,
-						 MGMT_STATUS_REJECTED);
-				mgmt_pending_remove(cmd);
-				goto failed;
-			}
+	BT_DBG("%s", hdev->name);
 
-			disable_advertising(&req);
-		}
+	hci_dev_lock(hdev);
 
-		/* 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);
+	if (!hdev_is_powered(hdev)) {
+		err = mgmt_cmd_complete(sk, hdev->id,
+					MGMT_OP_START_SERVICE_DISCOVERY,
+					MGMT_STATUS_NOT_POWERED,
+					&cp->type, sizeof(cp->type));
+		goto failed;
+	}
 
-		memset(&param_cp, 0, sizeof(param_cp));
+	if (hdev->discovery.state != DISCOVERY_STOPPED ||
+	    hci_dev_test_flag(hdev, HCI_PERIODIC_INQ)) {
+		err = mgmt_cmd_complete(sk, hdev->id,
+					MGMT_OP_START_SERVICE_DISCOVERY,
+					MGMT_STATUS_BUSY, &cp->type,
+					sizeof(cp->type));
+		goto failed;
+	}
 
-		/* 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_FAILED);
+	uuid_count = __le16_to_cpu(cp->uuid_count);
+	if (uuid_count > max_uuid_count) {
+		BT_ERR("service_discovery: too big uuid_count value %u",
+		       uuid_count);
+		err = mgmt_cmd_complete(sk, hdev->id,
+					MGMT_OP_START_SERVICE_DISCOVERY,
+					MGMT_STATUS_INVALID_PARAMS, &cp->type,
+					sizeof(cp->type));
+		goto failed;
+	}
+
+	expected_len = sizeof(*cp) + uuid_count * 16;
+	if (expected_len != len) {
+		BT_ERR("service_discovery: expected %u bytes, got %u bytes",
+		       expected_len, len);
+		err = mgmt_cmd_complete(sk, hdev->id,
+					MGMT_OP_START_SERVICE_DISCOVERY,
+					MGMT_STATUS_INVALID_PARAMS, &cp->type,
+					sizeof(cp->type));
+		goto failed;
+	}
+
+	cmd = mgmt_pending_add(sk, MGMT_OP_START_SERVICE_DISCOVERY,
+			       hdev, data, len);
+	if (!cmd) {
+		err = -ENOMEM;
+		goto failed;
+	}
+
+	cmd->cmd_complete = service_discovery_cmd_complete;
+
+	/* Clear the discovery filter first to free any previously
+	 * allocated memory for the UUID list.
+	 */
+	hci_discovery_filter_clear(hdev);
+
+	hdev->discovery.result_filtering = true;
+	hdev->discovery.type = cp->type;
+	hdev->discovery.rssi = cp->rssi;
+	hdev->discovery.uuid_count = uuid_count;
+
+	if (uuid_count > 0) {
+		hdev->discovery.uuids = kmemdup(cp->uuids, uuid_count * 16,
+						GFP_KERNEL);
+		if (!hdev->discovery.uuids) {
+			err = mgmt_cmd_complete(sk, hdev->id,
+						MGMT_OP_START_SERVICE_DISCOVERY,
+						MGMT_STATUS_FAILED,
+						&cp->type, sizeof(cp->type));
 			mgmt_pending_remove(cmd);
 			goto failed;
 		}
+	}
 
-		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 = 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);
-		break;
+	hci_req_init(&req, hdev);
 
-	default:
-		err = cmd_status(sk, hdev->id, MGMT_OP_START_DISCOVERY,
-				 MGMT_STATUS_INVALID_PARAMS);
+	if (!trigger_discovery(&req, &status)) {
+		err = mgmt_cmd_complete(sk, hdev->id,
+					MGMT_OP_START_SERVICE_DISCOVERY,
+					status, &cp->type, sizeof(cp->type));
 		mgmt_pending_remove(cmd);
 		goto failed;
 	}
 
 	err = hci_req_run(&req, start_discovery_complete);
-	if (err < 0)
+	if (err < 0) {
 		mgmt_pending_remove(cmd);
-	else
-		hci_discovery_set_state(hdev, DISCOVERY_STARTING);
+		goto failed;
+	}
+
+	hci_discovery_set_state(hdev, DISCOVERY_STARTING);
 
 failed:
 	hci_dev_unlock(hdev);
 	return err;
 }
 
-static int mgmt_stop_discovery_failed(struct hci_dev *hdev, u8 status)
+static void stop_discovery_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
-	struct pending_cmd *cmd;
-	int err;
-
-	cmd = mgmt_pending_find(MGMT_OP_STOP_DISCOVERY, hdev);
-	if (!cmd)
-		return -ENOENT;
-
-	err = cmd_complete(cmd->sk, hdev->id, cmd->opcode, mgmt_status(status),
-			   &hdev->discovery.type, sizeof(hdev->discovery.type));
-	mgmt_pending_remove(cmd);
+	struct mgmt_pending_cmd *cmd;
 
-	return err;
-}
-
-static void stop_discovery_complete(struct hci_dev *hdev, u8 status)
-{
 	BT_DBG("status %d", status);
 
 	hci_dev_lock(hdev);
 
-	if (status) {
-		mgmt_stop_discovery_failed(hdev, status);
-		goto unlock;
+	cmd = pending_find(MGMT_OP_STOP_DISCOVERY, hdev);
+	if (cmd) {
+		cmd->cmd_complete(cmd, mgmt_status(status));
+		mgmt_pending_remove(cmd);
 	}
 
-	hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
+	if (!status)
+		hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
 
-unlock:
 	hci_dev_unlock(hdev);
 }
 
@@ -3879,7 +4455,7 @@ static int stop_discovery(struct sock *sk, struct hci_dev *hdev, void *data,
 			  u16 len)
 {
 	struct mgmt_cp_stop_discovery *mgmt_cp = data;
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 	struct hci_request req;
 	int err;
 
@@ -3888,25 +4464,27 @@ static int stop_discovery(struct sock *sk, struct hci_dev *hdev, void *data,
 	hci_dev_lock(hdev);
 
 	if (!hci_discovery_active(hdev)) {
-		err = cmd_complete(sk, hdev->id, MGMT_OP_STOP_DISCOVERY,
-				   MGMT_STATUS_REJECTED, &mgmt_cp->type,
-				   sizeof(mgmt_cp->type));
+		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_STOP_DISCOVERY,
+					MGMT_STATUS_REJECTED, &mgmt_cp->type,
+					sizeof(mgmt_cp->type));
 		goto unlock;
 	}
 
 	if (hdev->discovery.type != mgmt_cp->type) {
-		err = cmd_complete(sk, hdev->id, MGMT_OP_STOP_DISCOVERY,
-				   MGMT_STATUS_INVALID_PARAMS, &mgmt_cp->type,
-				   sizeof(mgmt_cp->type));
+		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_STOP_DISCOVERY,
+					MGMT_STATUS_INVALID_PARAMS,
+					&mgmt_cp->type, sizeof(mgmt_cp->type));
 		goto unlock;
 	}
 
-	cmd = mgmt_pending_add(sk, MGMT_OP_STOP_DISCOVERY, hdev, NULL, 0);
+	cmd = mgmt_pending_add(sk, MGMT_OP_STOP_DISCOVERY, hdev, data, len);
 	if (!cmd) {
 		err = -ENOMEM;
 		goto unlock;
 	}
 
+	cmd->cmd_complete = generic_cmd_complete;
+
 	hci_req_init(&req, hdev);
 
 	hci_stop_discovery(&req);
@@ -3921,8 +4499,8 @@ static int stop_discovery(struct sock *sk, struct hci_dev *hdev, void *data,
 
 	/* 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));
+		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_STOP_DISCOVERY, 0,
+					&mgmt_cp->type, sizeof(mgmt_cp->type));
 		hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
 	}
 
@@ -3943,17 +4521,17 @@ static int confirm_name(struct sock *sk, struct hci_dev *hdev, void *data,
 	hci_dev_lock(hdev);
 
 	if (!hci_discovery_active(hdev)) {
-		err = cmd_complete(sk, hdev->id, MGMT_OP_CONFIRM_NAME,
-				   MGMT_STATUS_FAILED, &cp->addr,
-				   sizeof(cp->addr));
+		err = mgmt_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_complete(sk, hdev->id, MGMT_OP_CONFIRM_NAME,
-				   MGMT_STATUS_INVALID_PARAMS, &cp->addr,
-				   sizeof(cp->addr));
+		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_CONFIRM_NAME,
+					MGMT_STATUS_INVALID_PARAMS, &cp->addr,
+					sizeof(cp->addr));
 		goto failed;
 	}
 
@@ -3965,8 +4543,8 @@ static int confirm_name(struct sock *sk, struct hci_dev *hdev, void *data,
 		hci_inquiry_cache_update_resolve(hdev, e);
 	}
 
-	err = cmd_complete(sk, hdev->id, MGMT_OP_CONFIRM_NAME, 0, &cp->addr,
-			   sizeof(cp->addr));
+	err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_CONFIRM_NAME, 0,
+				&cp->addr, sizeof(cp->addr));
 
 failed:
 	hci_dev_unlock(hdev);
@@ -3983,9 +4561,9 @@ static int block_device(struct sock *sk, struct hci_dev *hdev, void *data,
 	BT_DBG("%s", hdev->name);
 
 	if (!bdaddr_type_is_valid(cp->addr.type))
-		return cmd_complete(sk, hdev->id, MGMT_OP_BLOCK_DEVICE,
-				    MGMT_STATUS_INVALID_PARAMS,
-				    &cp->addr, sizeof(cp->addr));
+		return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_BLOCK_DEVICE,
+					 MGMT_STATUS_INVALID_PARAMS,
+					 &cp->addr, sizeof(cp->addr));
 
 	hci_dev_lock(hdev);
 
@@ -4001,8 +4579,8 @@ static int block_device(struct sock *sk, struct hci_dev *hdev, void *data,
 	status = MGMT_STATUS_SUCCESS;
 
 done:
-	err = cmd_complete(sk, hdev->id, MGMT_OP_BLOCK_DEVICE, status,
-			   &cp->addr, sizeof(cp->addr));
+	err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_BLOCK_DEVICE, status,
+				&cp->addr, sizeof(cp->addr));
 
 	hci_dev_unlock(hdev);
 
@@ -4019,9 +4597,9 @@ static int unblock_device(struct sock *sk, struct hci_dev *hdev, void *data,
 	BT_DBG("%s", hdev->name);
 
 	if (!bdaddr_type_is_valid(cp->addr.type))
-		return cmd_complete(sk, hdev->id, MGMT_OP_UNBLOCK_DEVICE,
-				    MGMT_STATUS_INVALID_PARAMS,
-				    &cp->addr, sizeof(cp->addr));
+		return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_UNBLOCK_DEVICE,
+					 MGMT_STATUS_INVALID_PARAMS,
+					 &cp->addr, sizeof(cp->addr));
 
 	hci_dev_lock(hdev);
 
@@ -4037,8 +4615,8 @@ static int unblock_device(struct sock *sk, struct hci_dev *hdev, void *data,
 	status = MGMT_STATUS_SUCCESS;
 
 done:
-	err = cmd_complete(sk, hdev->id, MGMT_OP_UNBLOCK_DEVICE, status,
-			   &cp->addr, sizeof(cp->addr));
+	err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_UNBLOCK_DEVICE, status,
+				&cp->addr, sizeof(cp->addr));
 
 	hci_dev_unlock(hdev);
 
@@ -4058,8 +4636,8 @@ static int set_device_id(struct sock *sk, struct hci_dev *hdev, void *data,
 	source = __le16_to_cpu(cp->source);
 
 	if (source > 0x0002)
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_DEVICE_ID,
-				  MGMT_STATUS_INVALID_PARAMS);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_DEVICE_ID,
+				       MGMT_STATUS_INVALID_PARAMS);
 
 	hci_dev_lock(hdev);
 
@@ -4068,7 +4646,8 @@ static int set_device_id(struct sock *sk, struct hci_dev *hdev, void *data,
 	hdev->devid_product = __le16_to_cpu(cp->product);
 	hdev->devid_version = __le16_to_cpu(cp->version);
 
-	err = cmd_complete(sk, hdev->id, MGMT_OP_SET_DEVICE_ID, 0, NULL, 0);
+	err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_SET_DEVICE_ID, 0,
+				NULL, 0);
 
 	hci_req_init(&req, hdev);
 	update_eir(&req);
@@ -4079,22 +4658,32 @@ static int set_device_id(struct sock *sk, struct hci_dev *hdev, void *data,
 	return err;
 }
 
-static void set_advertising_complete(struct hci_dev *hdev, u8 status)
+static void enable_advertising_instance(struct hci_dev *hdev, u8 status,
+					u16 opcode)
+{
+	BT_DBG("status %d", status);
+}
+
+static void set_advertising_complete(struct hci_dev *hdev, u8 status,
+				     u16 opcode)
 {
 	struct cmd_lookup match = { NULL, hdev };
+	struct hci_request req;
+
+	hci_dev_lock(hdev);
 
 	if (status) {
 		u8 mgmt_err = mgmt_status(status);
 
 		mgmt_pending_foreach(MGMT_OP_SET_ADVERTISING, hdev,
 				     cmd_status_rsp, &mgmt_err);
-		return;
+		goto unlock;
 	}
 
-	if (test_bit(HCI_LE_ADV, &hdev->dev_flags))
-		set_bit(HCI_ADVERTISING, &hdev->dev_flags);
+	if (hci_dev_test_flag(hdev, HCI_LE_ADV))
+		hci_dev_set_flag(hdev, HCI_ADVERTISING);
 	else
-		clear_bit(HCI_ADVERTISING, &hdev->dev_flags);
+		hci_dev_clear_flag(hdev, HCI_ADVERTISING);
 
 	mgmt_pending_foreach(MGMT_OP_SET_ADVERTISING, hdev, settings_rsp,
 			     &match);
@@ -4103,47 +4692,72 @@ static void set_advertising_complete(struct hci_dev *hdev, u8 status)
 
 	if (match.sk)
 		sock_put(match.sk);
+
+	/* If "Set Advertising" was just disabled and instance advertising was
+	 * set up earlier, then enable the advertising instance.
+	 */
+	if (hci_dev_test_flag(hdev, HCI_ADVERTISING) ||
+	    !hci_dev_test_flag(hdev, HCI_ADVERTISING_INSTANCE))
+		goto unlock;
+
+	hci_req_init(&req, hdev);
+
+	update_adv_data(&req);
+	enable_advertising(&req);
+
+	if (hci_req_run(&req, enable_advertising_instance) < 0)
+		BT_ERR("Failed to re-configure advertising");
+
+unlock:
+	hci_dev_unlock(hdev);
 }
 
 static int set_advertising(struct sock *sk, struct hci_dev *hdev, void *data,
 			   u16 len)
 {
 	struct mgmt_mode *cp = data;
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 	struct hci_request req;
-	u8 val, enabled, status;
+	u8 val, status;
 	int err;
 
 	BT_DBG("request for %s", hdev->name);
 
 	status = mgmt_le_support(hdev);
 	if (status)
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING,
-				  status);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING,
+				       status);
 
-	if (cp->val != 0x00 && cp->val != 0x01)
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING,
-				  MGMT_STATUS_INVALID_PARAMS);
+	if (cp->val != 0x00 && cp->val != 0x01 && cp->val != 0x02)
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING,
+				       MGMT_STATUS_INVALID_PARAMS);
 
 	hci_dev_lock(hdev);
 
 	val = !!cp->val;
-	enabled = test_bit(HCI_ADVERTISING, &hdev->dev_flags);
 
 	/* The following conditions are ones which mean that we should
 	 * not do any HCI communication but directly send a mgmt
 	 * response to user space (after toggling the flag if
 	 * necessary).
 	 */
-	if (!hdev_is_powered(hdev) || val == enabled ||
+	if (!hdev_is_powered(hdev) ||
+	    (val == hci_dev_test_flag(hdev, HCI_ADVERTISING) &&
+	     (cp->val == 0x02) == hci_dev_test_flag(hdev, HCI_ADVERTISING_CONNECTABLE)) ||
 	    hci_conn_num(hdev, LE_LINK) > 0 ||
-	    (test_bit(HCI_LE_SCAN, &hdev->dev_flags) &&
+	    (hci_dev_test_flag(hdev, HCI_LE_SCAN) &&
 	     hdev->le_scan_type == LE_SCAN_ACTIVE)) {
-		bool changed = false;
+		bool changed;
 
-		if (val != test_bit(HCI_ADVERTISING, &hdev->dev_flags)) {
-			change_bit(HCI_ADVERTISING, &hdev->dev_flags);
-			changed = true;
+		if (cp->val) {
+			changed = !hci_dev_test_and_set_flag(hdev, HCI_ADVERTISING);
+			if (cp->val == 0x02)
+				hci_dev_set_flag(hdev, HCI_ADVERTISING_CONNECTABLE);
+			else
+				hci_dev_clear_flag(hdev, HCI_ADVERTISING_CONNECTABLE);
+		} else {
+			changed = hci_dev_test_and_clear_flag(hdev, HCI_ADVERTISING);
+			hci_dev_clear_flag(hdev, HCI_ADVERTISING_CONNECTABLE);
 		}
 
 		err = send_settings_rsp(sk, MGMT_OP_SET_ADVERTISING, hdev);
@@ -4156,10 +4770,10 @@ static int set_advertising(struct sock *sk, struct hci_dev *hdev, void *data,
 		goto unlock;
 	}
 
-	if (mgmt_pending_find(MGMT_OP_SET_ADVERTISING, hdev) ||
-	    mgmt_pending_find(MGMT_OP_SET_LE, hdev)) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING,
-				 MGMT_STATUS_BUSY);
+	if (pending_find(MGMT_OP_SET_ADVERTISING, hdev) ||
+	    pending_find(MGMT_OP_SET_LE, hdev)) {
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING,
+				      MGMT_STATUS_BUSY);
 		goto unlock;
 	}
 
@@ -4171,10 +4785,19 @@ static int set_advertising(struct sock *sk, struct hci_dev *hdev, void *data,
 
 	hci_req_init(&req, hdev);
 
-	if (val)
-		enable_advertising(&req);
+	if (cp->val == 0x02)
+		hci_dev_set_flag(hdev, HCI_ADVERTISING_CONNECTABLE);
 	else
+		hci_dev_clear_flag(hdev, HCI_ADVERTISING_CONNECTABLE);
+
+	if (val) {
+		/* Switch to instance "0" for the Set Advertising setting. */
+		update_adv_data_for_instance(&req, 0);
+		update_scan_rsp_data_for_instance(&req, 0);
+		enable_advertising(&req);
+	} else {
 		disable_advertising(&req);
+	}
 
 	err = hci_req_run(&req, set_advertising_complete);
 	if (err < 0)
@@ -4194,34 +4817,38 @@ static int set_static_address(struct sock *sk, struct hci_dev *hdev,
 	BT_DBG("%s", hdev->name);
 
 	if (!lmp_le_capable(hdev))
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_STATIC_ADDRESS,
-				  MGMT_STATUS_NOT_SUPPORTED);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_STATIC_ADDRESS,
+				       MGMT_STATUS_NOT_SUPPORTED);
 
 	if (hdev_is_powered(hdev))
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_STATIC_ADDRESS,
-				  MGMT_STATUS_REJECTED);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_STATIC_ADDRESS,
+				       MGMT_STATUS_REJECTED);
 
 	if (bacmp(&cp->bdaddr, BDADDR_ANY)) {
 		if (!bacmp(&cp->bdaddr, BDADDR_NONE))
-			return cmd_status(sk, hdev->id,
-					  MGMT_OP_SET_STATIC_ADDRESS,
-					  MGMT_STATUS_INVALID_PARAMS);
+			return mgmt_cmd_status(sk, hdev->id,
+					       MGMT_OP_SET_STATIC_ADDRESS,
+					       MGMT_STATUS_INVALID_PARAMS);
 
 		/* Two most significant bits shall be set */
 		if ((cp->bdaddr.b[5] & 0xc0) != 0xc0)
-			return cmd_status(sk, hdev->id,
-					  MGMT_OP_SET_STATIC_ADDRESS,
-					  MGMT_STATUS_INVALID_PARAMS);
+			return mgmt_cmd_status(sk, hdev->id,
+					       MGMT_OP_SET_STATIC_ADDRESS,
+					       MGMT_STATUS_INVALID_PARAMS);
 	}
 
 	hci_dev_lock(hdev);
 
 	bacpy(&hdev->static_addr, &cp->bdaddr);
 
-	err = cmd_complete(sk, hdev->id, MGMT_OP_SET_STATIC_ADDRESS, 0, NULL, 0);
+	err = send_settings_rsp(sk, MGMT_OP_SET_STATIC_ADDRESS, hdev);
+	if (err < 0)
+		goto unlock;
 
-	hci_dev_unlock(hdev);
+	err = new_settings(hdev, sk);
 
+unlock:
+	hci_dev_unlock(hdev);
 	return err;
 }
 
@@ -4235,36 +4862,37 @@ static int set_scan_params(struct sock *sk, struct hci_dev *hdev,
 	BT_DBG("%s", hdev->name);
 
 	if (!lmp_le_capable(hdev))
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_SCAN_PARAMS,
-				  MGMT_STATUS_NOT_SUPPORTED);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_SCAN_PARAMS,
+				       MGMT_STATUS_NOT_SUPPORTED);
 
 	interval = __le16_to_cpu(cp->interval);
 
 	if (interval < 0x0004 || interval > 0x4000)
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_SCAN_PARAMS,
-				  MGMT_STATUS_INVALID_PARAMS);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_SCAN_PARAMS,
+				       MGMT_STATUS_INVALID_PARAMS);
 
 	window = __le16_to_cpu(cp->window);
 
 	if (window < 0x0004 || window > 0x4000)
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_SCAN_PARAMS,
-				  MGMT_STATUS_INVALID_PARAMS);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_SCAN_PARAMS,
+				       MGMT_STATUS_INVALID_PARAMS);
 
 	if (window > interval)
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_SCAN_PARAMS,
-				  MGMT_STATUS_INVALID_PARAMS);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_SCAN_PARAMS,
+				       MGMT_STATUS_INVALID_PARAMS);
 
 	hci_dev_lock(hdev);
 
 	hdev->le_scan_interval = interval;
 	hdev->le_scan_window = window;
 
-	err = cmd_complete(sk, hdev->id, MGMT_OP_SET_SCAN_PARAMS, 0, NULL, 0);
+	err = mgmt_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) &&
+	if (hci_dev_test_flag(hdev, HCI_LE_SCAN) &&
 	    hdev->discovery.state == DISCOVERY_STOPPED) {
 		struct hci_request req;
 
@@ -4281,28 +4909,29 @@ static int set_scan_params(struct sock *sk, struct hci_dev *hdev,
 	return err;
 }
 
-static void fast_connectable_complete(struct hci_dev *hdev, u8 status)
+static void fast_connectable_complete(struct hci_dev *hdev, u8 status,
+				      u16 opcode)
 {
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 
 	BT_DBG("status 0x%02x", status);
 
 	hci_dev_lock(hdev);
 
-	cmd = mgmt_pending_find(MGMT_OP_SET_FAST_CONNECTABLE, hdev);
+	cmd = pending_find(MGMT_OP_SET_FAST_CONNECTABLE, hdev);
 	if (!cmd)
 		goto unlock;
 
 	if (status) {
-		cmd_status(cmd->sk, hdev->id, MGMT_OP_SET_FAST_CONNECTABLE,
-			   mgmt_status(status));
+		mgmt_cmd_status(cmd->sk, hdev->id, MGMT_OP_SET_FAST_CONNECTABLE,
+			        mgmt_status(status));
 	} else {
 		struct mgmt_mode *cp = cmd->param;
 
 		if (cp->val)
-			set_bit(HCI_FAST_CONNECTABLE, &hdev->dev_flags);
+			hci_dev_set_flag(hdev, HCI_FAST_CONNECTABLE);
 		else
-			clear_bit(HCI_FAST_CONNECTABLE, &hdev->dev_flags);
+			hci_dev_clear_flag(hdev, HCI_FAST_CONNECTABLE);
 
 		send_settings_rsp(cmd->sk, MGMT_OP_SET_FAST_CONNECTABLE, hdev);
 		new_settings(hdev, cmd->sk);
@@ -4318,40 +4947,40 @@ static int set_fast_connectable(struct sock *sk, struct hci_dev *hdev,
 				void *data, u16 len)
 {
 	struct mgmt_mode *cp = data;
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 	struct hci_request req;
 	int err;
 
 	BT_DBG("%s", hdev->name);
 
-	if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags) ||
+	if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED) ||
 	    hdev->hci_ver < BLUETOOTH_VER_1_2)
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_FAST_CONNECTABLE,
-				  MGMT_STATUS_NOT_SUPPORTED);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_FAST_CONNECTABLE,
+				       MGMT_STATUS_NOT_SUPPORTED);
 
 	if (cp->val != 0x00 && cp->val != 0x01)
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_FAST_CONNECTABLE,
-				  MGMT_STATUS_INVALID_PARAMS);
-
-	if (!hdev_is_powered(hdev))
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_FAST_CONNECTABLE,
-				  MGMT_STATUS_NOT_POWERED);
-
-	if (!test_bit(HCI_CONNECTABLE, &hdev->dev_flags))
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_FAST_CONNECTABLE,
-				  MGMT_STATUS_REJECTED);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_FAST_CONNECTABLE,
+				       MGMT_STATUS_INVALID_PARAMS);
 
 	hci_dev_lock(hdev);
 
-	if (mgmt_pending_find(MGMT_OP_SET_FAST_CONNECTABLE, hdev)) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_SET_FAST_CONNECTABLE,
-				 MGMT_STATUS_BUSY);
+	if (pending_find(MGMT_OP_SET_FAST_CONNECTABLE, hdev)) {
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_FAST_CONNECTABLE,
+				      MGMT_STATUS_BUSY);
+		goto unlock;
+	}
+
+	if (!!cp->val == hci_dev_test_flag(hdev, HCI_FAST_CONNECTABLE)) {
+		err = send_settings_rsp(sk, MGMT_OP_SET_FAST_CONNECTABLE,
+					hdev);
 		goto unlock;
 	}
 
-	if (!!cp->val == test_bit(HCI_FAST_CONNECTABLE, &hdev->dev_flags)) {
+	if (!hdev_is_powered(hdev)) {
+		hci_dev_change_flag(hdev, HCI_FAST_CONNECTABLE);
 		err = send_settings_rsp(sk, MGMT_OP_SET_FAST_CONNECTABLE,
 					hdev);
+		new_settings(hdev, sk);
 		goto unlock;
 	}
 
@@ -4368,8 +4997,8 @@ static int set_fast_connectable(struct sock *sk, struct hci_dev *hdev,
 
 	err = hci_req_run(&req, fast_connectable_complete);
 	if (err < 0) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_SET_FAST_CONNECTABLE,
-				 MGMT_STATUS_FAILED);
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_FAST_CONNECTABLE,
+				      MGMT_STATUS_FAILED);
 		mgmt_pending_remove(cmd);
 	}
 
@@ -4379,15 +5008,15 @@ unlock:
 	return err;
 }
 
-static void set_bredr_complete(struct hci_dev *hdev, u8 status)
+static void set_bredr_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 
 	BT_DBG("status 0x%02x", status);
 
 	hci_dev_lock(hdev);
 
-	cmd = mgmt_pending_find(MGMT_OP_SET_BREDR, hdev);
+	cmd = pending_find(MGMT_OP_SET_BREDR, hdev);
 	if (!cmd)
 		goto unlock;
 
@@ -4397,9 +5026,9 @@ static void set_bredr_complete(struct hci_dev *hdev, u8 status)
 		/* We need to restore the flag if related HCI commands
 		 * failed.
 		 */
-		clear_bit(HCI_BREDR_ENABLED, &hdev->dev_flags);
+		hci_dev_clear_flag(hdev, HCI_BREDR_ENABLED);
 
-		cmd_status(cmd->sk, cmd->index, cmd->opcode, mgmt_err);
+		mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode, mgmt_err);
 	} else {
 		send_settings_rsp(cmd->sk, MGMT_OP_SET_BREDR, hdev);
 		new_settings(hdev, cmd->sk);
@@ -4414,41 +5043,41 @@ unlock:
 static int set_bredr(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 {
 	struct mgmt_mode *cp = data;
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 	struct hci_request req;
 	int err;
 
 	BT_DBG("request for %s", hdev->name);
 
 	if (!lmp_bredr_capable(hdev) || !lmp_le_capable(hdev))
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR,
-				  MGMT_STATUS_NOT_SUPPORTED);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR,
+				       MGMT_STATUS_NOT_SUPPORTED);
 
-	if (!test_bit(HCI_LE_ENABLED, &hdev->dev_flags))
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR,
-				  MGMT_STATUS_REJECTED);
+	if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED))
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR,
+				       MGMT_STATUS_REJECTED);
 
 	if (cp->val != 0x00 && cp->val != 0x01)
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR,
-				  MGMT_STATUS_INVALID_PARAMS);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR,
+				       MGMT_STATUS_INVALID_PARAMS);
 
 	hci_dev_lock(hdev);
 
-	if (cp->val == test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) {
+	if (cp->val == hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) {
 		err = send_settings_rsp(sk, MGMT_OP_SET_BREDR, hdev);
 		goto unlock;
 	}
 
 	if (!hdev_is_powered(hdev)) {
 		if (!cp->val) {
-			clear_bit(HCI_DISCOVERABLE, &hdev->dev_flags);
-			clear_bit(HCI_SSP_ENABLED, &hdev->dev_flags);
-			clear_bit(HCI_LINK_SECURITY, &hdev->dev_flags);
-			clear_bit(HCI_FAST_CONNECTABLE, &hdev->dev_flags);
-			clear_bit(HCI_HS_ENABLED, &hdev->dev_flags);
+			hci_dev_clear_flag(hdev, HCI_DISCOVERABLE);
+			hci_dev_clear_flag(hdev, HCI_SSP_ENABLED);
+			hci_dev_clear_flag(hdev, HCI_LINK_SECURITY);
+			hci_dev_clear_flag(hdev, HCI_FAST_CONNECTABLE);
+			hci_dev_clear_flag(hdev, HCI_HS_ENABLED);
 		}
 
-		change_bit(HCI_BREDR_ENABLED, &hdev->dev_flags);
+		hci_dev_change_flag(hdev, HCI_BREDR_ENABLED);
 
 		err = send_settings_rsp(sk, MGMT_OP_SET_BREDR, hdev);
 		if (err < 0)
@@ -4460,14 +5089,36 @@ static int set_bredr(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 
 	/* Reject disabling when powered on */
 	if (!cp->val) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR,
-				 MGMT_STATUS_REJECTED);
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR,
+				      MGMT_STATUS_REJECTED);
 		goto unlock;
+	} else {
+		/* When configuring a dual-mode controller to operate
+		 * with LE only and using a static address, then switching
+		 * BR/EDR back on is not allowed.
+		 *
+		 * Dual-mode controllers shall operate with the public
+		 * address as its identity address for BR/EDR and LE. So
+		 * reject the attempt to create an invalid configuration.
+		 *
+		 * The same restrictions applies when secure connections
+		 * has been enabled. For BR/EDR this is a controller feature
+		 * while for LE it is a host stack feature. This means that
+		 * switching BR/EDR back on when secure connections has been
+		 * enabled is not a supported transaction.
+		 */
+		if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED) &&
+		    (bacmp(&hdev->static_addr, BDADDR_ANY) ||
+		     hci_dev_test_flag(hdev, HCI_SC_ENABLED))) {
+			err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR,
+					      MGMT_STATUS_REJECTED);
+			goto unlock;
+		}
 	}
 
-	if (mgmt_pending_find(MGMT_OP_SET_BREDR, hdev)) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR,
-				 MGMT_STATUS_BUSY);
+	if (pending_find(MGMT_OP_SET_BREDR, hdev)) {
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR,
+				      MGMT_STATUS_BUSY);
 		goto unlock;
 	}
 
@@ -4480,12 +5131,12 @@ static int set_bredr(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 	/* We need to flip the bit already here so that update_adv_data
 	 * generates the correct flags.
 	 */
-	set_bit(HCI_BREDR_ENABLED, &hdev->dev_flags);
+	hci_dev_set_flag(hdev, HCI_BREDR_ENABLED);
 
 	hci_req_init(&req, hdev);
 
 	write_fast_connectable(&req, false);
-	hci_update_page_scan(hdev, &req);
+	__hci_update_page_scan(&req);
 
 	/* Since only the advertising data flags will change, there
 	 * is no need to update the scan response data.
@@ -4501,46 +5152,94 @@ unlock:
 	return err;
 }
 
+static void sc_enable_complete(struct hci_dev *hdev, u8 status, u16 opcode)
+{
+	struct mgmt_pending_cmd *cmd;
+	struct mgmt_mode *cp;
+
+	BT_DBG("%s status %u", hdev->name, status);
+
+	hci_dev_lock(hdev);
+
+	cmd = pending_find(MGMT_OP_SET_SECURE_CONN, hdev);
+	if (!cmd)
+		goto unlock;
+
+	if (status) {
+		mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode,
+			        mgmt_status(status));
+		goto remove;
+	}
+
+	cp = cmd->param;
+
+	switch (cp->val) {
+	case 0x00:
+		hci_dev_clear_flag(hdev, HCI_SC_ENABLED);
+		hci_dev_clear_flag(hdev, HCI_SC_ONLY);
+		break;
+	case 0x01:
+		hci_dev_set_flag(hdev, HCI_SC_ENABLED);
+		hci_dev_clear_flag(hdev, HCI_SC_ONLY);
+		break;
+	case 0x02:
+		hci_dev_set_flag(hdev, HCI_SC_ENABLED);
+		hci_dev_set_flag(hdev, HCI_SC_ONLY);
+		break;
+	}
+
+	send_settings_rsp(cmd->sk, MGMT_OP_SET_SECURE_CONN, hdev);
+	new_settings(hdev, cmd->sk);
+
+remove:
+	mgmt_pending_remove(cmd);
+unlock:
+	hci_dev_unlock(hdev);
+}
+
 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;
+	struct mgmt_pending_cmd *cmd;
+	struct hci_request req;
+	u8 val;
 	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->dbg_flags))
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN,
-				  MGMT_STATUS_NOT_SUPPORTED);
+	    !hci_dev_test_flag(hdev, HCI_LE_ENABLED))
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN,
+				       MGMT_STATUS_NOT_SUPPORTED);
+
+	if (hci_dev_test_flag(hdev, HCI_BREDR_ENABLED) &&
+	    lmp_sc_capable(hdev) &&
+	    !hci_dev_test_flag(hdev, HCI_SSP_ENABLED))
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN,
+				       MGMT_STATUS_REJECTED);
 
 	if (cp->val != 0x00 && cp->val != 0x01 && cp->val != 0x02)
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN,
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN,
 				  MGMT_STATUS_INVALID_PARAMS);
 
 	hci_dev_lock(hdev);
 
-	if (!hdev_is_powered(hdev)) {
+	if (!hdev_is_powered(hdev) || !lmp_sc_capable(hdev) ||
+	    !hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) {
 		bool changed;
 
 		if (cp->val) {
-			changed = !test_and_set_bit(HCI_SC_ENABLED,
-						    &hdev->dev_flags);
+			changed = !hci_dev_test_and_set_flag(hdev,
+							     HCI_SC_ENABLED);
 			if (cp->val == 0x02)
-				set_bit(HCI_SC_ONLY, &hdev->dev_flags);
+				hci_dev_set_flag(hdev, HCI_SC_ONLY);
 			else
-				clear_bit(HCI_SC_ONLY, &hdev->dev_flags);
+				hci_dev_clear_flag(hdev, HCI_SC_ONLY);
 		} else {
-			changed = test_and_clear_bit(HCI_SC_ENABLED,
-						     &hdev->dev_flags);
-			clear_bit(HCI_SC_ONLY, &hdev->dev_flags);
+			changed = hci_dev_test_and_clear_flag(hdev,
+							      HCI_SC_ENABLED);
+			hci_dev_clear_flag(hdev, HCI_SC_ONLY);
 		}
 
 		err = send_settings_rsp(sk, MGMT_OP_SET_SECURE_CONN, hdev);
@@ -4553,16 +5252,16 @@ static int set_secure_conn(struct sock *sk, struct hci_dev *hdev,
 		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);
+	if (pending_find(MGMT_OP_SET_SECURE_CONN, hdev)) {
+		err = mgmt_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)) {
+	if (val == hci_dev_test_flag(hdev, HCI_SC_ENABLED) &&
+	    (cp->val == 0x02) == hci_dev_test_flag(hdev, HCI_SC_ONLY)) {
 		err = send_settings_rsp(sk, MGMT_OP_SET_SECURE_CONN, hdev);
 		goto failed;
 	}
@@ -4573,17 +5272,14 @@ static int set_secure_conn(struct sock *sk, struct hci_dev *hdev,
 		goto failed;
 	}
 
-	err = hci_send_cmd(hdev, HCI_OP_WRITE_SC_SUPPORT, 1, &val);
+	hci_req_init(&req, hdev);
+	hci_req_add(&req, HCI_OP_WRITE_SC_SUPPORT, 1, &val);
+	err = hci_req_run(&req, sc_enable_complete);
 	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;
@@ -4599,27 +5295,26 @@ static int set_debug_keys(struct sock *sk, struct hci_dev *hdev,
 	BT_DBG("request for %s", hdev->name);
 
 	if (cp->val != 0x00 && cp->val != 0x01 && cp->val != 0x02)
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_DEBUG_KEYS,
-				  MGMT_STATUS_INVALID_PARAMS);
+		return mgmt_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_KEEP_DEBUG_KEYS,
-					    &hdev->dev_flags);
+		changed = !hci_dev_test_and_set_flag(hdev, HCI_KEEP_DEBUG_KEYS);
 	else
-		changed = test_and_clear_bit(HCI_KEEP_DEBUG_KEYS,
-					     &hdev->dev_flags);
+		changed = hci_dev_test_and_clear_flag(hdev,
+						      HCI_KEEP_DEBUG_KEYS);
 
 	if (cp->val == 0x02)
-		use_changed = !test_and_set_bit(HCI_USE_DEBUG_KEYS,
-						&hdev->dev_flags);
+		use_changed = !hci_dev_test_and_set_flag(hdev,
+							 HCI_USE_DEBUG_KEYS);
 	else
-		use_changed = test_and_clear_bit(HCI_USE_DEBUG_KEYS,
-						 &hdev->dev_flags);
+		use_changed = hci_dev_test_and_clear_flag(hdev,
+							  HCI_USE_DEBUG_KEYS);
 
 	if (hdev_is_powered(hdev) && use_changed &&
-	    test_bit(HCI_SSP_ENABLED, &hdev->dev_flags)) {
+	    hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) {
 		u8 mode = (cp->val == 0x02) ? 0x01 : 0x00;
 		hci_send_cmd(hdev, HCI_OP_WRITE_SSP_DEBUG_MODE,
 			     sizeof(mode), &mode);
@@ -4647,32 +5342,32 @@ static int set_privacy(struct sock *sk, struct hci_dev *hdev, void *cp_data,
 	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);
+		return mgmt_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);
+		return mgmt_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);
+		return mgmt_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);
+	hci_dev_set_flag(hdev, HCI_RPA_RESOLVING);
 
 	if (cp->privacy) {
-		changed = !test_and_set_bit(HCI_PRIVACY, &hdev->dev_flags);
+		changed = !hci_dev_test_and_set_flag(hdev, HCI_PRIVACY);
 		memcpy(hdev->irk, cp->irk, sizeof(hdev->irk));
-		set_bit(HCI_RPA_EXPIRED, &hdev->dev_flags);
+		hci_dev_set_flag(hdev, HCI_RPA_EXPIRED);
 	} else {
-		changed = test_and_clear_bit(HCI_PRIVACY, &hdev->dev_flags);
+		changed = hci_dev_test_and_clear_flag(hdev, HCI_PRIVACY);
 		memset(hdev->irk, 0, sizeof(hdev->irk));
-		clear_bit(HCI_RPA_EXPIRED, &hdev->dev_flags);
+		hci_dev_clear_flag(hdev, HCI_RPA_EXPIRED);
 	}
 
 	err = send_settings_rsp(sk, MGMT_OP_SET_PRIVACY, hdev);
@@ -4715,22 +5410,22 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data,
 	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);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_IRKS,
+				       MGMT_STATUS_NOT_SUPPORTED);
 
 	irk_count = __le16_to_cpu(cp->irk_count);
 	if (irk_count > max_irk_count) {
 		BT_ERR("load_irks: too big irk_count value %u", irk_count);
-		return cmd_status(sk, hdev->id, MGMT_OP_LOAD_IRKS,
-				  MGMT_STATUS_INVALID_PARAMS);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_IRKS,
+				       MGMT_STATUS_INVALID_PARAMS);
 	}
 
 	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);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_IRKS,
+				       MGMT_STATUS_INVALID_PARAMS);
 	}
 
 	BT_DBG("%s irk_count %u", hdev->name, irk_count);
@@ -4739,9 +5434,9 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data,
 		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);
+			return mgmt_cmd_status(sk, hdev->id,
+					       MGMT_OP_LOAD_IRKS,
+					       MGMT_STATUS_INVALID_PARAMS);
 	}
 
 	hci_dev_lock(hdev);
@@ -4761,9 +5456,9 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data,
 			    BDADDR_ANY);
 	}
 
-	set_bit(HCI_RPA_RESOLVING, &hdev->dev_flags);
+	hci_dev_set_flag(hdev, HCI_RPA_RESOLVING);
 
-	err = cmd_complete(sk, hdev->id, MGMT_OP_LOAD_IRKS, 0, NULL, 0);
+	err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_LOAD_IRKS, 0, NULL, 0);
 
 	hci_dev_unlock(hdev);
 
@@ -4801,14 +5496,14 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
 	BT_DBG("request for %s", hdev->name);
 
 	if (!lmp_le_capable(hdev))
-		return cmd_status(sk, hdev->id, MGMT_OP_LOAD_LONG_TERM_KEYS,
-				  MGMT_STATUS_NOT_SUPPORTED);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LONG_TERM_KEYS,
+				       MGMT_STATUS_NOT_SUPPORTED);
 
 	key_count = __le16_to_cpu(cp->key_count);
 	if (key_count > max_key_count) {
 		BT_ERR("load_ltks: too big key_count value %u", key_count);
-		return cmd_status(sk, hdev->id, MGMT_OP_LOAD_LONG_TERM_KEYS,
-				  MGMT_STATUS_INVALID_PARAMS);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LONG_TERM_KEYS,
+				       MGMT_STATUS_INVALID_PARAMS);
 	}
 
 	expected_len = sizeof(*cp) + key_count *
@@ -4816,8 +5511,8 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
 	if (expected_len != len) {
 		BT_ERR("load_keys: expected %u bytes, got %u bytes",
 		       expected_len, len);
-		return cmd_status(sk, hdev->id, MGMT_OP_LOAD_LONG_TERM_KEYS,
-				  MGMT_STATUS_INVALID_PARAMS);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LONG_TERM_KEYS,
+				       MGMT_STATUS_INVALID_PARAMS);
 	}
 
 	BT_DBG("%s key_count %u", hdev->name, key_count);
@@ -4826,9 +5521,9 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
 		struct mgmt_ltk_info *key = &cp->keys[i];
 
 		if (!ltk_is_valid(key))
-			return cmd_status(sk, hdev->id,
-					  MGMT_OP_LOAD_LONG_TERM_KEYS,
-					  MGMT_STATUS_INVALID_PARAMS);
+			return mgmt_cmd_status(sk, hdev->id,
+					       MGMT_OP_LOAD_LONG_TERM_KEYS,
+					       MGMT_STATUS_INVALID_PARAMS);
 	}
 
 	hci_dev_lock(hdev);
@@ -4844,18 +5539,26 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
 		else
 			addr_type = ADDR_LE_DEV_RANDOM;
 
-		if (key->master)
-			type = SMP_LTK;
-		else
-			type = SMP_LTK_SLAVE;
-
 		switch (key->type) {
 		case MGMT_LTK_UNAUTHENTICATED:
 			authenticated = 0x00;
+			type = key->master ? SMP_LTK : SMP_LTK_SLAVE;
 			break;
 		case MGMT_LTK_AUTHENTICATED:
 			authenticated = 0x01;
+			type = key->master ? SMP_LTK : SMP_LTK_SLAVE;
+			break;
+		case MGMT_LTK_P256_UNAUTH:
+			authenticated = 0x00;
+			type = SMP_LTK_P256;
+			break;
+		case MGMT_LTK_P256_AUTH:
+			authenticated = 0x01;
+			type = SMP_LTK_P256;
 			break;
+		case MGMT_LTK_P256_DEBUG:
+			authenticated = 0x00;
+			type = SMP_LTK_P256_DEBUG;
 		default:
 			continue;
 		}
@@ -4865,7 +5568,7 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
 			    key->rand);
 	}
 
-	err = cmd_complete(sk, hdev->id, MGMT_OP_LOAD_LONG_TERM_KEYS, 0,
+	err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_LOAD_LONG_TERM_KEYS, 0,
 			   NULL, 0);
 
 	hci_dev_unlock(hdev);
@@ -4873,67 +5576,46 @@ 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)
+static int conn_info_cmd_complete(struct mgmt_pending_cmd *cmd, u8 status)
 {
-	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;
+	struct mgmt_rp_get_conn_info rp;
+	int err;
 
-	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;
+	memcpy(&rp.addr, cmd->param, sizeof(rp.addr));
 
-	if (!match->mgmt_status) {
+	if (status == MGMT_STATUS_SUCCESS) {
 		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;
-		}
+		rp.tx_power = conn->tx_power;
+		rp.max_tx_power = conn->max_tx_power;
+	} else {
+		rp.rssi = HCI_RSSI_INVALID;
+		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));
+	err = mgmt_cmd_complete(cmd->sk, cmd->index, MGMT_OP_GET_CONN_INFO,
+				status, &rp, sizeof(rp));
 
 	hci_conn_drop(conn);
 	hci_conn_put(conn);
 
-	mgmt_pending_remove(cmd);
+	return err;
 }
 
-static void conn_info_refresh_complete(struct hci_dev *hdev, u8 status)
+static void conn_info_refresh_complete(struct hci_dev *hdev, u8 hci_status,
+				       u16 opcode)
 {
 	struct hci_cp_read_rssi *cp;
+	struct mgmt_pending_cmd *cmd;
 	struct hci_conn *conn;
-	struct cmd_conn_lookup match;
 	u16 handle;
+	u8 status;
 
-	BT_DBG("status 0x%02x", status);
+	BT_DBG("status 0x%02x", hci_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
@@ -4946,29 +5628,29 @@ static void conn_info_refresh_complete(struct hci_dev *hdev, u8 status)
 	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;
+		status = MGMT_STATUS_SUCCESS;
+	} else {
+		status = mgmt_status(hci_status);
 	}
 
 	if (!cp) {
-		BT_ERR("invalid sent_cmd in response");
+		BT_ERR("invalid sent_cmd in conn_info 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);
+		BT_ERR("unknown handle (%d) in conn_info response", handle);
 		goto unlock;
 	}
 
-	match.conn = conn;
-	match.mgmt_status = mgmt_status(status);
+	cmd = pending_find_data(MGMT_OP_GET_CONN_INFO, hdev, conn);
+	if (!cmd)
+		goto unlock;
 
-	/* 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);
+	cmd->cmd_complete(cmd, status);
+	mgmt_pending_remove(cmd);
 
 unlock:
 	hci_dev_unlock(hdev);
@@ -4990,15 +5672,16 @@ static int get_conn_info(struct sock *sk, struct hci_dev *hdev, void *data,
 	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));
+		return mgmt_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));
+		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_GET_CONN_INFO,
+					MGMT_STATUS_NOT_POWERED, &rp,
+					sizeof(rp));
 		goto unlock;
 	}
 
@@ -5009,8 +5692,15 @@ static int get_conn_info(struct sock *sk, struct hci_dev *hdev, void *data,
 		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));
+		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_GET_CONN_INFO,
+					MGMT_STATUS_NOT_CONNECTED, &rp,
+					sizeof(rp));
+		goto unlock;
+	}
+
+	if (pending_find_data(MGMT_OP_GET_CONN_INFO, hdev, conn)) {
+		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_GET_CONN_INFO,
+					MGMT_STATUS_BUSY, &rp, sizeof(rp));
 		goto unlock;
 	}
 
@@ -5030,7 +5720,7 @@ static int get_conn_info(struct sock *sk, struct hci_dev *hdev, void *data,
 		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;
+		struct mgmt_pending_cmd *cmd;
 
 		hci_req_init(&req, hdev);
 		req_rssi_cp.handle = cpu_to_le16(conn->handle);
@@ -5069,6 +5759,7 @@ static int get_conn_info(struct sock *sk, struct hci_dev *hdev, void *data,
 
 		hci_conn_hold(conn);
 		cmd->user_data = hci_conn_get(conn);
+		cmd->cmd_complete = conn_info_cmd_complete;
 
 		conn->conn_info_timestamp = jiffies;
 	} else {
@@ -5077,8 +5768,8 @@ static int get_conn_info(struct sock *sk, struct hci_dev *hdev, void *data,
 		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));
+		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_GET_CONN_INFO,
+					MGMT_STATUS_SUCCESS, &rp, sizeof(rp));
 	}
 
 unlock:
@@ -5086,12 +5777,46 @@ unlock:
 	return err;
 }
 
-static void get_clock_info_complete(struct hci_dev *hdev, u8 status)
+static int clock_info_cmd_complete(struct mgmt_pending_cmd *cmd, u8 status)
 {
-	struct mgmt_cp_get_clock_info *cp;
+	struct hci_conn *conn = cmd->user_data;
 	struct mgmt_rp_get_clock_info rp;
+	struct hci_dev *hdev;
+	int err;
+
+	memset(&rp, 0, sizeof(rp));
+	memcpy(&rp.addr, &cmd->param, sizeof(rp.addr));
+
+	if (status)
+		goto complete;
+
+	hdev = hci_dev_get(cmd->index);
+	if (hdev) {
+		rp.local_clock = cpu_to_le32(hdev->clock);
+		hci_dev_put(hdev);
+	}
+
+	if (conn) {
+		rp.piconet_clock = cpu_to_le32(conn->clock);
+		rp.accuracy = cpu_to_le16(conn->clock_accuracy);
+	}
+
+complete:
+	err = mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, status, &rp,
+				sizeof(rp));
+
+	if (conn) {
+		hci_conn_drop(conn);
+		hci_conn_put(conn);
+	}
+
+	return err;
+}
+
+static void get_clock_info_complete(struct hci_dev *hdev, u8 status, u16 opcode)
+{
 	struct hci_cp_read_clock *hci_cp;
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 	struct hci_conn *conn;
 
 	BT_DBG("%s status %u", hdev->name, status);
@@ -5109,33 +5834,12 @@ static void get_clock_info_complete(struct hci_dev *hdev, u8 status)
 		conn = NULL;
 	}
 
-	cmd = mgmt_pending_find_data(MGMT_OP_GET_CLOCK_INFO, hdev, conn);
+	cmd = pending_find_data(MGMT_OP_GET_CLOCK_INFO, hdev, conn);
 	if (!cmd)
 		goto unlock;
 
-	cp = cmd->param;
-
-	memset(&rp, 0, sizeof(rp));
-	memcpy(&rp.addr, &cp->addr, sizeof(rp.addr));
-
-	if (status)
-		goto send_rsp;
-
-	rp.local_clock = cpu_to_le32(hdev->clock);
-
-	if (conn) {
-		rp.piconet_clock = cpu_to_le32(conn->clock);
-		rp.accuracy = cpu_to_le16(conn->clock_accuracy);
-	}
-
-send_rsp:
-	cmd_complete(cmd->sk, cmd->index, cmd->opcode, mgmt_status(status),
-		     &rp, sizeof(rp));
+	cmd->cmd_complete(cmd, mgmt_status(status));
 	mgmt_pending_remove(cmd);
-	if (conn) {
-		hci_conn_drop(conn);
-		hci_conn_put(conn);
-	}
 
 unlock:
 	hci_dev_unlock(hdev);
@@ -5147,7 +5851,7 @@ static int get_clock_info(struct sock *sk, struct hci_dev *hdev, void *data,
 	struct mgmt_cp_get_clock_info *cp = data;
 	struct mgmt_rp_get_clock_info rp;
 	struct hci_cp_read_clock hci_cp;
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 	struct hci_request req;
 	struct hci_conn *conn;
 	int err;
@@ -5159,15 +5863,16 @@ static int get_clock_info(struct sock *sk, struct hci_dev *hdev, void *data,
 	rp.addr.type = cp->addr.type;
 
 	if (cp->addr.type != BDADDR_BREDR)
-		return cmd_complete(sk, hdev->id, MGMT_OP_GET_CLOCK_INFO,
-				    MGMT_STATUS_INVALID_PARAMS,
-				    &rp, sizeof(rp));
+		return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_GET_CLOCK_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_CLOCK_INFO,
-				   MGMT_STATUS_NOT_POWERED, &rp, sizeof(rp));
+		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_GET_CLOCK_INFO,
+					MGMT_STATUS_NOT_POWERED, &rp,
+					sizeof(rp));
 		goto unlock;
 	}
 
@@ -5175,10 +5880,10 @@ static int get_clock_info(struct sock *sk, struct hci_dev *hdev, void *data,
 		conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK,
 					       &cp->addr.bdaddr);
 		if (!conn || conn->state != BT_CONNECTED) {
-			err = cmd_complete(sk, hdev->id,
-					   MGMT_OP_GET_CLOCK_INFO,
-					   MGMT_STATUS_NOT_CONNECTED,
-					   &rp, sizeof(rp));
+			err = mgmt_cmd_complete(sk, hdev->id,
+						MGMT_OP_GET_CLOCK_INFO,
+						MGMT_STATUS_NOT_CONNECTED,
+						&rp, sizeof(rp));
 			goto unlock;
 		}
 	} else {
@@ -5191,6 +5896,8 @@ static int get_clock_info(struct sock *sk, struct hci_dev *hdev, void *data,
 		goto unlock;
 	}
 
+	cmd->cmd_complete = clock_info_cmd_complete;
+
 	hci_req_init(&req, hdev);
 
 	memset(&hci_cp, 0, sizeof(hci_cp));
@@ -5214,6 +5921,65 @@ unlock:
 	return err;
 }
 
+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;
+}
+
+/* This function requires the caller holds hdev->lock */
+static int hci_conn_params_set(struct hci_request *req, bdaddr_t *addr,
+			       u8 addr_type, u8 auto_connect)
+{
+	struct hci_dev *hdev = req->hdev;
+	struct hci_conn_params *params;
+
+	params = hci_conn_params_add(hdev, addr, addr_type);
+	if (!params)
+		return -EIO;
+
+	if (params->auto_connect == auto_connect)
+		return 0;
+
+	list_del_init(&params->action);
+
+	switch (auto_connect) {
+	case HCI_AUTO_CONN_DISABLED:
+	case HCI_AUTO_CONN_LINK_LOSS:
+		__hci_update_background_scan(req);
+		break;
+	case HCI_AUTO_CONN_REPORT:
+		list_add(&params->action, &hdev->pend_le_reports);
+		__hci_update_background_scan(req);
+		break;
+	case HCI_AUTO_CONN_DIRECT:
+	case HCI_AUTO_CONN_ALWAYS:
+		if (!is_connected(hdev, addr, addr_type)) {
+			list_add(&params->action, &hdev->pend_le_conns);
+			__hci_update_background_scan(req);
+		}
+		break;
+	}
+
+	params->auto_connect = auto_connect;
+
+	BT_DBG("addr %pMR (type %u) auto_connect %u", addr, addr_type,
+	       auto_connect);
+
+	return 0;
+}
+
 static void device_added(struct sock *sk, struct hci_dev *hdev,
 			 bdaddr_t *bdaddr, u8 type, u8 action)
 {
@@ -5226,10 +5992,31 @@ static void device_added(struct sock *sk, struct hci_dev *hdev,
 	mgmt_event(MGMT_EV_DEVICE_ADDED, hdev, &ev, sizeof(ev), sk);
 }
 
+static void add_device_complete(struct hci_dev *hdev, u8 status, u16 opcode)
+{
+	struct mgmt_pending_cmd *cmd;
+
+	BT_DBG("status 0x%02x", status);
+
+	hci_dev_lock(hdev);
+
+	cmd = pending_find(MGMT_OP_ADD_DEVICE, hdev);
+	if (!cmd)
+		goto unlock;
+
+	cmd->cmd_complete(cmd, mgmt_status(status));
+	mgmt_pending_remove(cmd);
+
+unlock:
+	hci_dev_unlock(hdev);
+}
+
 static int add_device(struct sock *sk, struct hci_dev *hdev,
 		      void *data, u16 len)
 {
 	struct mgmt_cp_add_device *cp = data;
+	struct mgmt_pending_cmd *cmd;
+	struct hci_request req;
 	u8 auto_conn, addr_type;
 	int err;
 
@@ -5237,23 +6024,33 @@ static int add_device(struct sock *sk, struct hci_dev *hdev,
 
 	if (!bdaddr_type_is_valid(cp->addr.type) ||
 	    !bacmp(&cp->addr.bdaddr, BDADDR_ANY))
-		return cmd_complete(sk, hdev->id, MGMT_OP_ADD_DEVICE,
-				    MGMT_STATUS_INVALID_PARAMS,
-				    &cp->addr, sizeof(cp->addr));
+		return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_ADD_DEVICE,
+					 MGMT_STATUS_INVALID_PARAMS,
+					 &cp->addr, sizeof(cp->addr));
 
 	if (cp->action != 0x00 && cp->action != 0x01 && cp->action != 0x02)
-		return cmd_complete(sk, hdev->id, MGMT_OP_ADD_DEVICE,
-				    MGMT_STATUS_INVALID_PARAMS,
-				    &cp->addr, sizeof(cp->addr));
+		return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_ADD_DEVICE,
+					 MGMT_STATUS_INVALID_PARAMS,
+					 &cp->addr, sizeof(cp->addr));
+
+	hci_req_init(&req, hdev);
 
 	hci_dev_lock(hdev);
 
+	cmd = mgmt_pending_add(sk, MGMT_OP_ADD_DEVICE, hdev, data, len);
+	if (!cmd) {
+		err = -ENOMEM;
+		goto unlock;
+	}
+
+	cmd->cmd_complete = addr_cmd_complete;
+
 	if (cp->addr.type == BDADDR_BREDR) {
 		/* Only incoming connections action is supported for now */
 		if (cp->action != 0x01) {
-			err = cmd_complete(sk, hdev->id, MGMT_OP_ADD_DEVICE,
-					   MGMT_STATUS_INVALID_PARAMS,
-					   &cp->addr, sizeof(cp->addr));
+			err = cmd->cmd_complete(cmd,
+						MGMT_STATUS_INVALID_PARAMS);
+			mgmt_pending_remove(cmd);
 			goto unlock;
 		}
 
@@ -5262,7 +6059,7 @@ static int add_device(struct sock *sk, struct hci_dev *hdev,
 		if (err)
 			goto unlock;
 
-		hci_update_page_scan(hdev, NULL);
+		__hci_update_page_scan(&req);
 
 		goto added;
 	}
@@ -5282,19 +6079,25 @@ static int add_device(struct sock *sk, struct hci_dev *hdev,
 	/* If the connection parameters don't exist for this device,
 	 * they will be created and configured with defaults.
 	 */
-	if (hci_conn_params_set(hdev, &cp->addr.bdaddr, addr_type,
+	if (hci_conn_params_set(&req, &cp->addr.bdaddr, addr_type,
 				auto_conn) < 0) {
-		err = cmd_complete(sk, hdev->id, MGMT_OP_ADD_DEVICE,
-				   MGMT_STATUS_FAILED,
-				   &cp->addr, sizeof(cp->addr));
+		err = cmd->cmd_complete(cmd, MGMT_STATUS_FAILED);
+		mgmt_pending_remove(cmd);
 		goto unlock;
 	}
 
 added:
 	device_added(sk, hdev, &cp->addr.bdaddr, cp->addr.type, cp->action);
 
-	err = cmd_complete(sk, hdev->id, MGMT_OP_ADD_DEVICE,
-			   MGMT_STATUS_SUCCESS, &cp->addr, sizeof(cp->addr));
+	err = hci_req_run(&req, add_device_complete);
+	if (err < 0) {
+		/* ENODATA means no HCI commands were needed (e.g. if
+		 * the adapter is powered off).
+		 */
+		if (err == -ENODATA)
+			err = cmd->cmd_complete(cmd, MGMT_STATUS_SUCCESS);
+		mgmt_pending_remove(cmd);
+	}
 
 unlock:
 	hci_dev_unlock(hdev);
@@ -5312,24 +6115,55 @@ static void device_removed(struct sock *sk, struct hci_dev *hdev,
 	mgmt_event(MGMT_EV_DEVICE_REMOVED, hdev, &ev, sizeof(ev), sk);
 }
 
+static void remove_device_complete(struct hci_dev *hdev, u8 status, u16 opcode)
+{
+	struct mgmt_pending_cmd *cmd;
+
+	BT_DBG("status 0x%02x", status);
+
+	hci_dev_lock(hdev);
+
+	cmd = pending_find(MGMT_OP_REMOVE_DEVICE, hdev);
+	if (!cmd)
+		goto unlock;
+
+	cmd->cmd_complete(cmd, mgmt_status(status));
+	mgmt_pending_remove(cmd);
+
+unlock:
+	hci_dev_unlock(hdev);
+}
+
 static int remove_device(struct sock *sk, struct hci_dev *hdev,
 			 void *data, u16 len)
 {
 	struct mgmt_cp_remove_device *cp = data;
+	struct mgmt_pending_cmd *cmd;
+	struct hci_request req;
 	int err;
 
 	BT_DBG("%s", hdev->name);
 
+	hci_req_init(&req, hdev);
+
 	hci_dev_lock(hdev);
 
+	cmd = mgmt_pending_add(sk, MGMT_OP_REMOVE_DEVICE, hdev, data, len);
+	if (!cmd) {
+		err = -ENOMEM;
+		goto unlock;
+	}
+
+	cmd->cmd_complete = addr_cmd_complete;
+
 	if (bacmp(&cp->addr.bdaddr, BDADDR_ANY)) {
 		struct hci_conn_params *params;
 		u8 addr_type;
 
 		if (!bdaddr_type_is_valid(cp->addr.type)) {
-			err = cmd_complete(sk, hdev->id, MGMT_OP_REMOVE_DEVICE,
-					   MGMT_STATUS_INVALID_PARAMS,
-					   &cp->addr, sizeof(cp->addr));
+			err = cmd->cmd_complete(cmd,
+						MGMT_STATUS_INVALID_PARAMS);
+			mgmt_pending_remove(cmd);
 			goto unlock;
 		}
 
@@ -5338,14 +6172,13 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev,
 						  &cp->addr.bdaddr,
 						  cp->addr.type);
 			if (err) {
-				err = cmd_complete(sk, hdev->id,
-						   MGMT_OP_REMOVE_DEVICE,
-						   MGMT_STATUS_INVALID_PARAMS,
-						   &cp->addr, sizeof(cp->addr));
+				err = cmd->cmd_complete(cmd,
+							MGMT_STATUS_INVALID_PARAMS);
+				mgmt_pending_remove(cmd);
 				goto unlock;
 			}
 
-			hci_update_page_scan(hdev, NULL);
+			__hci_update_page_scan(&req);
 
 			device_removed(sk, hdev, &cp->addr.bdaddr,
 				       cp->addr.type);
@@ -5360,23 +6193,23 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev,
 		params = hci_conn_params_lookup(hdev, &cp->addr.bdaddr,
 						addr_type);
 		if (!params) {
-			err = cmd_complete(sk, hdev->id, MGMT_OP_REMOVE_DEVICE,
-					   MGMT_STATUS_INVALID_PARAMS,
-					   &cp->addr, sizeof(cp->addr));
+			err = cmd->cmd_complete(cmd,
+						MGMT_STATUS_INVALID_PARAMS);
+			mgmt_pending_remove(cmd);
 			goto unlock;
 		}
 
 		if (params->auto_connect == HCI_AUTO_CONN_DISABLED) {
-			err = cmd_complete(sk, hdev->id, MGMT_OP_REMOVE_DEVICE,
-					   MGMT_STATUS_INVALID_PARAMS,
-					   &cp->addr, sizeof(cp->addr));
+			err = cmd->cmd_complete(cmd,
+						MGMT_STATUS_INVALID_PARAMS);
+			mgmt_pending_remove(cmd);
 			goto unlock;
 		}
 
 		list_del(&params->action);
 		list_del(&params->list);
 		kfree(params);
-		hci_update_background_scan(hdev);
+		__hci_update_background_scan(&req);
 
 		device_removed(sk, hdev, &cp->addr.bdaddr, cp->addr.type);
 	} else {
@@ -5384,9 +6217,9 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev,
 		struct bdaddr_list *b, *btmp;
 
 		if (cp->addr.type) {
-			err = cmd_complete(sk, hdev->id, MGMT_OP_REMOVE_DEVICE,
-					   MGMT_STATUS_INVALID_PARAMS,
-					   &cp->addr, sizeof(cp->addr));
+			err = cmd->cmd_complete(cmd,
+						MGMT_STATUS_INVALID_PARAMS);
+			mgmt_pending_remove(cmd);
 			goto unlock;
 		}
 
@@ -5396,7 +6229,7 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev,
 			kfree(b);
 		}
 
-		hci_update_page_scan(hdev, NULL);
+		__hci_update_page_scan(&req);
 
 		list_for_each_entry_safe(p, tmp, &hdev->le_conn_params, list) {
 			if (p->auto_connect == HCI_AUTO_CONN_DISABLED)
@@ -5409,12 +6242,19 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev,
 
 		BT_DBG("All LE connection parameters were removed");
 
-		hci_update_background_scan(hdev);
+		__hci_update_background_scan(&req);
 	}
 
 complete:
-	err = cmd_complete(sk, hdev->id, MGMT_OP_REMOVE_DEVICE,
-			   MGMT_STATUS_SUCCESS, &cp->addr, sizeof(cp->addr));
+	err = hci_req_run(&req, remove_device_complete);
+	if (err < 0) {
+		/* ENODATA means no HCI commands were needed (e.g. if
+		 * the adapter is powered off).
+		 */
+		if (err == -ENODATA)
+			err = cmd->cmd_complete(cmd, MGMT_STATUS_SUCCESS);
+		mgmt_pending_remove(cmd);
+	}
 
 unlock:
 	hci_dev_unlock(hdev);
@@ -5431,15 +6271,15 @@ static int load_conn_param(struct sock *sk, struct hci_dev *hdev, void *data,
 	int i;
 
 	if (!lmp_le_capable(hdev))
-		return cmd_status(sk, hdev->id, MGMT_OP_LOAD_CONN_PARAM,
-				  MGMT_STATUS_NOT_SUPPORTED);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_CONN_PARAM,
+				       MGMT_STATUS_NOT_SUPPORTED);
 
 	param_count = __le16_to_cpu(cp->param_count);
 	if (param_count > max_param_count) {
 		BT_ERR("load_conn_param: too big param_count value %u",
 		       param_count);
-		return cmd_status(sk, hdev->id, MGMT_OP_LOAD_CONN_PARAM,
-				  MGMT_STATUS_INVALID_PARAMS);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_CONN_PARAM,
+				       MGMT_STATUS_INVALID_PARAMS);
 	}
 
 	expected_len = sizeof(*cp) + param_count *
@@ -5447,8 +6287,8 @@ static int load_conn_param(struct sock *sk, struct hci_dev *hdev, void *data,
 	if (expected_len != len) {
 		BT_ERR("load_conn_param: expected %u bytes, got %u bytes",
 		       expected_len, len);
-		return cmd_status(sk, hdev->id, MGMT_OP_LOAD_CONN_PARAM,
-				  MGMT_STATUS_INVALID_PARAMS);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_CONN_PARAM,
+				       MGMT_STATUS_INVALID_PARAMS);
 	}
 
 	BT_DBG("%s param_count %u", hdev->name, param_count);
@@ -5503,7 +6343,8 @@ static int load_conn_param(struct sock *sk, struct hci_dev *hdev, void *data,
 
 	hci_dev_unlock(hdev);
 
-	return cmd_complete(sk, hdev->id, MGMT_OP_LOAD_CONN_PARAM, 0, NULL, 0);
+	return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_LOAD_CONN_PARAM, 0,
+				 NULL, 0);
 }
 
 static int set_external_config(struct sock *sk, struct hci_dev *hdev,
@@ -5516,25 +6357,23 @@ static int set_external_config(struct sock *sk, struct hci_dev *hdev,
 	BT_DBG("%s", hdev->name);
 
 	if (hdev_is_powered(hdev))
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_EXTERNAL_CONFIG,
-				  MGMT_STATUS_REJECTED);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_EXTERNAL_CONFIG,
+				       MGMT_STATUS_REJECTED);
 
 	if (cp->config != 0x00 && cp->config != 0x01)
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_EXTERNAL_CONFIG,
-				    MGMT_STATUS_INVALID_PARAMS);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_EXTERNAL_CONFIG,
+				         MGMT_STATUS_INVALID_PARAMS);
 
 	if (!test_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks))
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_EXTERNAL_CONFIG,
-				  MGMT_STATUS_NOT_SUPPORTED);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_EXTERNAL_CONFIG,
+				       MGMT_STATUS_NOT_SUPPORTED);
 
 	hci_dev_lock(hdev);
 
 	if (cp->config)
-		changed = !test_and_set_bit(HCI_EXT_CONFIGURED,
-					    &hdev->dev_flags);
+		changed = !hci_dev_test_and_set_flag(hdev, HCI_EXT_CONFIGURED);
 	else
-		changed = test_and_clear_bit(HCI_EXT_CONFIGURED,
-					     &hdev->dev_flags);
+		changed = hci_dev_test_and_clear_flag(hdev, HCI_EXT_CONFIGURED);
 
 	err = send_options_rsp(sk, MGMT_OP_SET_EXTERNAL_CONFIG, hdev);
 	if (err < 0)
@@ -5545,12 +6384,12 @@ static int set_external_config(struct sock *sk, struct hci_dev *hdev,
 
 	err = new_options(hdev, sk);
 
-	if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags) == is_configured(hdev)) {
+	if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED) == is_configured(hdev)) {
 		mgmt_index_removed(hdev);
 
-		if (test_and_change_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) {
-			set_bit(HCI_CONFIG, &hdev->dev_flags);
-			set_bit(HCI_AUTO_OFF, &hdev->dev_flags);
+		if (hci_dev_test_and_change_flag(hdev, HCI_UNCONFIGURED)) {
+			hci_dev_set_flag(hdev, HCI_CONFIG);
+			hci_dev_set_flag(hdev, HCI_AUTO_OFF);
 
 			queue_work(hdev->req_workqueue, &hdev->power_on);
 		} else {
@@ -5574,16 +6413,16 @@ static int set_public_address(struct sock *sk, struct hci_dev *hdev,
 	BT_DBG("%s", hdev->name);
 
 	if (hdev_is_powered(hdev))
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_PUBLIC_ADDRESS,
-				  MGMT_STATUS_REJECTED);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_PUBLIC_ADDRESS,
+				       MGMT_STATUS_REJECTED);
 
 	if (!bacmp(&cp->bdaddr, BDADDR_ANY))
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_PUBLIC_ADDRESS,
-				  MGMT_STATUS_INVALID_PARAMS);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_PUBLIC_ADDRESS,
+				       MGMT_STATUS_INVALID_PARAMS);
 
 	if (!hdev->set_bdaddr)
-		return cmd_status(sk, hdev->id, MGMT_OP_SET_PUBLIC_ADDRESS,
-				  MGMT_STATUS_NOT_SUPPORTED);
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_PUBLIC_ADDRESS,
+				       MGMT_STATUS_NOT_SUPPORTED);
 
 	hci_dev_lock(hdev);
 
@@ -5597,16 +6436,16 @@ static int set_public_address(struct sock *sk, struct hci_dev *hdev,
 	if (!changed)
 		goto unlock;
 
-	if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED))
 		err = new_options(hdev, sk);
 
 	if (is_configured(hdev)) {
 		mgmt_index_removed(hdev);
 
-		clear_bit(HCI_UNCONFIGURED, &hdev->dev_flags);
+		hci_dev_clear_flag(hdev, HCI_UNCONFIGURED);
 
-		set_bit(HCI_CONFIG, &hdev->dev_flags);
-		set_bit(HCI_AUTO_OFF, &hdev->dev_flags);
+		hci_dev_set_flag(hdev, HCI_CONFIG);
+		hci_dev_set_flag(hdev, HCI_AUTO_OFF);
 
 		queue_work(hdev->req_workqueue, &hdev->power_on);
 	}
@@ -5616,217 +6455,858 @@ unlock:
 	return err;
 }
 
-static const struct mgmt_handler {
-	int (*func) (struct sock *sk, struct hci_dev *hdev, void *data,
-		     u16 data_len);
-	bool var_len;
-	size_t data_len;
-} mgmt_handlers[] = {
-	{ NULL }, /* 0x0000 (no command) */
-	{ read_version,           false, MGMT_READ_VERSION_SIZE },
-	{ read_commands,          false, MGMT_READ_COMMANDS_SIZE },
-	{ read_index_list,        false, MGMT_READ_INDEX_LIST_SIZE },
-	{ read_controller_info,   false, MGMT_READ_INFO_SIZE },
-	{ set_powered,            false, MGMT_SETTING_SIZE },
-	{ set_discoverable,       false, MGMT_SET_DISCOVERABLE_SIZE },
-	{ set_connectable,        false, MGMT_SETTING_SIZE },
-	{ set_fast_connectable,   false, MGMT_SETTING_SIZE },
-	{ set_bondable,           false, MGMT_SETTING_SIZE },
-	{ set_link_security,      false, MGMT_SETTING_SIZE },
-	{ set_ssp,                false, MGMT_SETTING_SIZE },
-	{ set_hs,                 false, MGMT_SETTING_SIZE },
-	{ set_le,                 false, MGMT_SETTING_SIZE },
-	{ set_dev_class,          false, MGMT_SET_DEV_CLASS_SIZE },
-	{ set_local_name,         false, MGMT_SET_LOCAL_NAME_SIZE },
-	{ add_uuid,               false, MGMT_ADD_UUID_SIZE },
-	{ remove_uuid,            false, MGMT_REMOVE_UUID_SIZE },
-	{ load_link_keys,         true,  MGMT_LOAD_LINK_KEYS_SIZE },
-	{ load_long_term_keys,    true,  MGMT_LOAD_LONG_TERM_KEYS_SIZE },
-	{ disconnect,             false, MGMT_DISCONNECT_SIZE },
-	{ get_connections,        false, MGMT_GET_CONNECTIONS_SIZE },
-	{ pin_code_reply,         false, MGMT_PIN_CODE_REPLY_SIZE },
-	{ pin_code_neg_reply,     false, MGMT_PIN_CODE_NEG_REPLY_SIZE },
-	{ set_io_capability,      false, MGMT_SET_IO_CAPABILITY_SIZE },
-	{ pair_device,            false, MGMT_PAIR_DEVICE_SIZE },
-	{ cancel_pair_device,     false, MGMT_CANCEL_PAIR_DEVICE_SIZE },
-	{ unpair_device,          false, MGMT_UNPAIR_DEVICE_SIZE },
-	{ user_confirm_reply,     false, MGMT_USER_CONFIRM_REPLY_SIZE },
-	{ user_confirm_neg_reply, false, MGMT_USER_CONFIRM_NEG_REPLY_SIZE },
-	{ 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,    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 },
-	{ confirm_name,           false, MGMT_CONFIRM_NAME_SIZE },
-	{ block_device,           false, MGMT_BLOCK_DEVICE_SIZE },
-	{ unblock_device,         false, MGMT_UNBLOCK_DEVICE_SIZE },
-	{ set_device_id,          false, MGMT_SET_DEVICE_ID_SIZE },
-	{ set_advertising,        false, MGMT_SETTING_SIZE },
-	{ 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 },
-	{ get_clock_info,         false, MGMT_GET_CLOCK_INFO_SIZE },
-	{ add_device,             false, MGMT_ADD_DEVICE_SIZE },
-	{ remove_device,          false, MGMT_REMOVE_DEVICE_SIZE },
-	{ load_conn_param,        true,  MGMT_LOAD_CONN_PARAM_SIZE },
-	{ read_unconf_index_list, false, MGMT_READ_UNCONF_INDEX_LIST_SIZE },
-	{ read_config_info,       false, MGMT_READ_CONFIG_INFO_SIZE },
-	{ set_external_config,    false, MGMT_SET_EXTERNAL_CONFIG_SIZE },
-	{ set_public_address,     false, MGMT_SET_PUBLIC_ADDRESS_SIZE },
-};
+static inline u16 eir_append_data(u8 *eir, u16 eir_len, u8 type, u8 *data,
+				  u8 data_len)
+{
+	eir[eir_len++] = sizeof(type) + data_len;
+	eir[eir_len++] = type;
+	memcpy(&eir[eir_len], data, data_len);
+	eir_len += data_len;
+
+	return eir_len;
+}
 
-int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
+static void read_local_oob_ext_data_complete(struct hci_dev *hdev, u8 status,
+					     u16 opcode, struct sk_buff *skb)
 {
-	void *buf;
-	u8 *cp;
-	struct mgmt_hdr *hdr;
-	u16 opcode, index, len;
-	struct hci_dev *hdev = NULL;
-	const struct mgmt_handler *handler;
+	const struct mgmt_cp_read_local_oob_ext_data *mgmt_cp;
+	struct mgmt_rp_read_local_oob_ext_data *mgmt_rp;
+	u8 *h192, *r192, *h256, *r256;
+	struct mgmt_pending_cmd *cmd;
+	u16 eir_len;
 	int err;
 
-	BT_DBG("got %zu bytes", msglen);
+	BT_DBG("%s status %u", hdev->name, status);
 
-	if (msglen < sizeof(*hdr))
-		return -EINVAL;
+	cmd = pending_find(MGMT_OP_READ_LOCAL_OOB_EXT_DATA, hdev);
+	if (!cmd)
+		return;
 
-	buf = kmalloc(msglen, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
+	mgmt_cp = cmd->param;
 
-	if (memcpy_fromiovec(buf, msg->msg_iov, msglen)) {
-		err = -EFAULT;
+	if (status) {
+		status = mgmt_status(status);
+		eir_len = 0;
+
+		h192 = NULL;
+		r192 = NULL;
+		h256 = NULL;
+		r256 = NULL;
+	} else if (opcode == HCI_OP_READ_LOCAL_OOB_DATA) {
+		struct hci_rp_read_local_oob_data *rp;
+
+		if (skb->len != sizeof(*rp)) {
+			status = MGMT_STATUS_FAILED;
+			eir_len = 0;
+		} else {
+			status = MGMT_STATUS_SUCCESS;
+			rp = (void *)skb->data;
+
+			eir_len = 5 + 18 + 18;
+			h192 = rp->hash;
+			r192 = rp->rand;
+			h256 = NULL;
+			r256 = NULL;
+		}
+	} else {
+		struct hci_rp_read_local_oob_ext_data *rp;
+
+		if (skb->len != sizeof(*rp)) {
+			status = MGMT_STATUS_FAILED;
+			eir_len = 0;
+		} else {
+			status = MGMT_STATUS_SUCCESS;
+			rp = (void *)skb->data;
+
+			if (hci_dev_test_flag(hdev, HCI_SC_ONLY)) {
+				eir_len = 5 + 18 + 18;
+				h192 = NULL;
+				r192 = NULL;
+			} else {
+				eir_len = 5 + 18 + 18 + 18 + 18;
+				h192 = rp->hash192;
+				r192 = rp->rand192;
+			}
+
+			h256 = rp->hash256;
+			r256 = rp->rand256;
+		}
+	}
+
+	mgmt_rp = kmalloc(sizeof(*mgmt_rp) + eir_len, GFP_KERNEL);
+	if (!mgmt_rp)
 		goto done;
+
+	if (status)
+		goto send_rsp;
+
+	eir_len = eir_append_data(mgmt_rp->eir, 0, EIR_CLASS_OF_DEV,
+				  hdev->dev_class, 3);
+
+	if (h192 && r192) {
+		eir_len = eir_append_data(mgmt_rp->eir, eir_len,
+					  EIR_SSP_HASH_C192, h192, 16);
+		eir_len = eir_append_data(mgmt_rp->eir, eir_len,
+					  EIR_SSP_RAND_R192, r192, 16);
+	}
+
+	if (h256 && r256) {
+		eir_len = eir_append_data(mgmt_rp->eir, eir_len,
+					  EIR_SSP_HASH_C256, h256, 16);
+		eir_len = eir_append_data(mgmt_rp->eir, eir_len,
+					  EIR_SSP_RAND_R256, r256, 16);
 	}
 
-	hdr = buf;
-	opcode = __le16_to_cpu(hdr->opcode);
-	index = __le16_to_cpu(hdr->index);
-	len = __le16_to_cpu(hdr->len);
+send_rsp:
+	mgmt_rp->type = mgmt_cp->type;
+	mgmt_rp->eir_len = cpu_to_le16(eir_len);
 
-	if (len != msglen - sizeof(*hdr)) {
-		err = -EINVAL;
+	err = mgmt_cmd_complete(cmd->sk, hdev->id,
+				MGMT_OP_READ_LOCAL_OOB_EXT_DATA, status,
+				mgmt_rp, sizeof(*mgmt_rp) + eir_len);
+	if (err < 0 || status)
 		goto done;
+
+	hci_sock_set_flag(cmd->sk, HCI_MGMT_OOB_DATA_EVENTS);
+
+	err = mgmt_limited_event(MGMT_EV_LOCAL_OOB_DATA_UPDATED, hdev,
+				 mgmt_rp, sizeof(*mgmt_rp) + eir_len,
+				 HCI_MGMT_OOB_DATA_EVENTS, cmd->sk);
+done:
+	kfree(mgmt_rp);
+	mgmt_pending_remove(cmd);
+}
+
+static int read_local_ssp_oob_req(struct hci_dev *hdev, struct sock *sk,
+				  struct mgmt_cp_read_local_oob_ext_data *cp)
+{
+	struct mgmt_pending_cmd *cmd;
+	struct hci_request req;
+	int err;
+
+	cmd = mgmt_pending_add(sk, MGMT_OP_READ_LOCAL_OOB_EXT_DATA, hdev,
+			       cp, sizeof(*cp));
+	if (!cmd)
+		return -ENOMEM;
+
+	hci_req_init(&req, hdev);
+
+	if (bredr_sc_enabled(hdev))
+		hci_req_add(&req, HCI_OP_READ_LOCAL_OOB_EXT_DATA, 0, NULL);
+	else
+		hci_req_add(&req, HCI_OP_READ_LOCAL_OOB_DATA, 0, NULL);
+
+	err = hci_req_run_skb(&req, read_local_oob_ext_data_complete);
+	if (err < 0) {
+		mgmt_pending_remove(cmd);
+		return err;
 	}
 
-	if (index != MGMT_INDEX_NONE) {
-		hdev = hci_dev_get(index);
-		if (!hdev) {
-			err = cmd_status(sk, index, opcode,
-					 MGMT_STATUS_INVALID_INDEX);
-			goto done;
+	return 0;
+}
+
+static int read_local_oob_ext_data(struct sock *sk, struct hci_dev *hdev,
+				   void *data, u16 data_len)
+{
+	struct mgmt_cp_read_local_oob_ext_data *cp = data;
+	struct mgmt_rp_read_local_oob_ext_data *rp;
+	size_t rp_len;
+	u16 eir_len;
+	u8 status, flags, role, addr[7], hash[16], rand[16];
+	int err;
+
+	BT_DBG("%s", hdev->name);
+
+	if (hdev_is_powered(hdev)) {
+		switch (cp->type) {
+		case BIT(BDADDR_BREDR):
+			status = mgmt_bredr_support(hdev);
+			if (status)
+				eir_len = 0;
+			else
+				eir_len = 5;
+			break;
+		case (BIT(BDADDR_LE_PUBLIC) | BIT(BDADDR_LE_RANDOM)):
+			status = mgmt_le_support(hdev);
+			if (status)
+				eir_len = 0;
+			else
+				eir_len = 9 + 3 + 18 + 18 + 3;
+			break;
+		default:
+			status = MGMT_STATUS_INVALID_PARAMS;
+			eir_len = 0;
+			break;
 		}
+	} else {
+		status = MGMT_STATUS_NOT_POWERED;
+		eir_len = 0;
+	}
+
+	rp_len = sizeof(*rp) + eir_len;
+	rp = kmalloc(rp_len, GFP_ATOMIC);
+	if (!rp)
+		return -ENOMEM;
+
+	if (status)
+		goto complete;
+
+	hci_dev_lock(hdev);
+
+	eir_len = 0;
+	switch (cp->type) {
+	case BIT(BDADDR_BREDR):
+		if (hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) {
+			err = read_local_ssp_oob_req(hdev, sk, cp);
+			hci_dev_unlock(hdev);
+			if (!err)
+				goto done;
 
-		if (test_bit(HCI_SETUP, &hdev->dev_flags) ||
-		    test_bit(HCI_CONFIG, &hdev->dev_flags) ||
-		    test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) {
-			err = cmd_status(sk, index, opcode,
-					 MGMT_STATUS_INVALID_INDEX);
-			goto done;
+			status = MGMT_STATUS_FAILED;
+			goto complete;
+		} else {
+			eir_len = eir_append_data(rp->eir, eir_len,
+						  EIR_CLASS_OF_DEV,
+						  hdev->dev_class, 3);
 		}
+		break;
+	case (BIT(BDADDR_LE_PUBLIC) | BIT(BDADDR_LE_RANDOM)):
+		if (hci_dev_test_flag(hdev, HCI_SC_ENABLED) &&
+		    smp_generate_oob(hdev, hash, rand) < 0) {
+			hci_dev_unlock(hdev);
+			status = MGMT_STATUS_FAILED;
+			goto complete;
+		}
+
+		/* This should return the active RPA, but since the RPA
+		 * is only programmed on demand, it is really hard to fill
+		 * this in at the moment. For now disallow retrieving
+		 * local out-of-band data when privacy is in use.
+		 *
+		 * Returning the identity address will not help here since
+		 * pairing happens before the identity resolving key is
+		 * known and thus the connection establishment happens
+		 * based on the RPA and not the identity address.
+		 */
+		if (hci_dev_test_flag(hdev, HCI_PRIVACY)) {
+			hci_dev_unlock(hdev);
+			status = MGMT_STATUS_REJECTED;
+			goto complete;
+		}
+
+		if (hci_dev_test_flag(hdev, HCI_FORCE_STATIC_ADDR) ||
+		   !bacmp(&hdev->bdaddr, BDADDR_ANY) ||
+		   (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED) &&
+		    bacmp(&hdev->static_addr, BDADDR_ANY))) {
+			memcpy(addr, &hdev->static_addr, 6);
+			addr[6] = 0x01;
+		} else {
+			memcpy(addr, &hdev->bdaddr, 6);
+			addr[6] = 0x00;
+		}
+
+		eir_len = eir_append_data(rp->eir, eir_len, EIR_LE_BDADDR,
+					  addr, sizeof(addr));
 
-		if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags) &&
-		    opcode != MGMT_OP_READ_CONFIG_INFO &&
-		    opcode != MGMT_OP_SET_EXTERNAL_CONFIG &&
-		    opcode != MGMT_OP_SET_PUBLIC_ADDRESS) {
-			err = cmd_status(sk, index, opcode,
-					 MGMT_STATUS_INVALID_INDEX);
-			goto done;
+		if (hci_dev_test_flag(hdev, HCI_ADVERTISING))
+			role = 0x02;
+		else
+			role = 0x01;
+
+		eir_len = eir_append_data(rp->eir, eir_len, EIR_LE_ROLE,
+					  &role, sizeof(role));
+
+		if (hci_dev_test_flag(hdev, HCI_SC_ENABLED)) {
+			eir_len = eir_append_data(rp->eir, eir_len,
+						  EIR_LE_SC_CONFIRM,
+						  hash, sizeof(hash));
+
+			eir_len = eir_append_data(rp->eir, eir_len,
+						  EIR_LE_SC_RANDOM,
+						  rand, sizeof(rand));
 		}
+
+		flags = get_adv_discov_flags(hdev);
+
+		if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED))
+			flags |= LE_AD_NO_BREDR;
+
+		eir_len = eir_append_data(rp->eir, eir_len, EIR_FLAGS,
+					  &flags, sizeof(flags));
+		break;
 	}
 
-	if (opcode >= ARRAY_SIZE(mgmt_handlers) ||
-	    mgmt_handlers[opcode].func == NULL) {
-		BT_DBG("Unknown op %u", opcode);
-		err = cmd_status(sk, index, opcode,
-				 MGMT_STATUS_UNKNOWN_COMMAND);
+	hci_dev_unlock(hdev);
+
+	hci_sock_set_flag(sk, HCI_MGMT_OOB_DATA_EVENTS);
+
+	status = MGMT_STATUS_SUCCESS;
+
+complete:
+	rp->type = cp->type;
+	rp->eir_len = cpu_to_le16(eir_len);
+
+	err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_EXT_DATA,
+				status, rp, sizeof(*rp) + eir_len);
+	if (err < 0 || status)
 		goto done;
+
+	err = mgmt_limited_event(MGMT_EV_LOCAL_OOB_DATA_UPDATED, hdev,
+				 rp, sizeof(*rp) + eir_len,
+				 HCI_MGMT_OOB_DATA_EVENTS, sk);
+
+done:
+	kfree(rp);
+
+	return err;
+}
+
+static u32 get_supported_adv_flags(struct hci_dev *hdev)
+{
+	u32 flags = 0;
+
+	flags |= MGMT_ADV_FLAG_CONNECTABLE;
+	flags |= MGMT_ADV_FLAG_DISCOV;
+	flags |= MGMT_ADV_FLAG_LIMITED_DISCOV;
+	flags |= MGMT_ADV_FLAG_MANAGED_FLAGS;
+
+	if (hdev->adv_tx_power != HCI_TX_POWER_INVALID)
+		flags |= MGMT_ADV_FLAG_TX_POWER;
+
+	return flags;
+}
+
+static int read_adv_features(struct sock *sk, struct hci_dev *hdev,
+			     void *data, u16 data_len)
+{
+	struct mgmt_rp_read_adv_features *rp;
+	size_t rp_len;
+	int err;
+	bool instance;
+	u32 supported_flags;
+
+	BT_DBG("%s", hdev->name);
+
+	if (!lmp_le_capable(hdev))
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_READ_ADV_FEATURES,
+				       MGMT_STATUS_REJECTED);
+
+	hci_dev_lock(hdev);
+
+	rp_len = sizeof(*rp);
+
+	/* Currently only one instance is supported, so just add 1 to the
+	 * response length.
+	 */
+	instance = hci_dev_test_flag(hdev, HCI_ADVERTISING_INSTANCE);
+	if (instance)
+		rp_len++;
+
+	rp = kmalloc(rp_len, GFP_ATOMIC);
+	if (!rp) {
+		hci_dev_unlock(hdev);
+		return -ENOMEM;
 	}
 
-	if (hdev && (opcode <= MGMT_OP_READ_INDEX_LIST ||
-		     opcode == MGMT_OP_READ_UNCONF_INDEX_LIST)) {
-		err = cmd_status(sk, index, opcode,
-				 MGMT_STATUS_INVALID_INDEX);
-		goto done;
+	supported_flags = get_supported_adv_flags(hdev);
+
+	rp->supported_flags = cpu_to_le32(supported_flags);
+	rp->max_adv_data_len = HCI_MAX_AD_LENGTH;
+	rp->max_scan_rsp_len = HCI_MAX_AD_LENGTH;
+	rp->max_instances = 1;
+
+	/* Currently only one instance is supported, so simply return the
+	 * current instance number.
+	 */
+	if (instance) {
+		rp->num_instances = 1;
+		rp->instance[0] = 1;
+	} else {
+		rp->num_instances = 0;
 	}
 
-	if (!hdev && (opcode > MGMT_OP_READ_INDEX_LIST &&
-		      opcode != MGMT_OP_READ_UNCONF_INDEX_LIST)) {
-		err = cmd_status(sk, index, opcode,
-				 MGMT_STATUS_INVALID_INDEX);
-		goto done;
+	hci_dev_unlock(hdev);
+
+	err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_READ_ADV_FEATURES,
+				MGMT_STATUS_SUCCESS, rp, rp_len);
+
+	kfree(rp);
+
+	return err;
+}
+
+static bool tlv_data_is_valid(struct hci_dev *hdev, u32 adv_flags, u8 *data,
+			      u8 len, bool is_adv_data)
+{
+	u8 max_len = HCI_MAX_AD_LENGTH;
+	int i, cur_len;
+	bool flags_managed = false;
+	bool tx_power_managed = false;
+	u32 flags_params = MGMT_ADV_FLAG_DISCOV | MGMT_ADV_FLAG_LIMITED_DISCOV |
+			   MGMT_ADV_FLAG_MANAGED_FLAGS;
+
+	if (is_adv_data && (adv_flags & flags_params)) {
+		flags_managed = true;
+		max_len -= 3;
 	}
 
-	handler = &mgmt_handlers[opcode];
+	if (is_adv_data && (adv_flags & MGMT_ADV_FLAG_TX_POWER)) {
+		tx_power_managed = true;
+		max_len -= 3;
+	}
 
-	if ((handler->var_len && len < handler->data_len) ||
-	    (!handler->var_len && len != handler->data_len)) {
-		err = cmd_status(sk, index, opcode,
-				 MGMT_STATUS_INVALID_PARAMS);
-		goto done;
+	if (len > max_len)
+		return false;
+
+	/* Make sure that the data is correctly formatted. */
+	for (i = 0, cur_len = 0; i < len; i += (cur_len + 1)) {
+		cur_len = data[i];
+
+		if (flags_managed && data[i + 1] == EIR_FLAGS)
+			return false;
+
+		if (tx_power_managed && data[i + 1] == EIR_TX_POWER)
+			return false;
+
+		/* If the current field length would exceed the total data
+		 * length, then it's invalid.
+		 */
+		if (i + cur_len >= len)
+			return false;
+	}
+
+	return true;
+}
+
+static void add_advertising_complete(struct hci_dev *hdev, u8 status,
+				     u16 opcode)
+{
+	struct mgmt_pending_cmd *cmd;
+	struct mgmt_rp_add_advertising rp;
+
+	BT_DBG("status %d", status);
+
+	hci_dev_lock(hdev);
+
+	cmd = pending_find(MGMT_OP_ADD_ADVERTISING, hdev);
+
+	if (status) {
+		hci_dev_clear_flag(hdev, HCI_ADVERTISING_INSTANCE);
+		memset(&hdev->adv_instance, 0, sizeof(hdev->adv_instance));
+		advertising_removed(cmd ? cmd->sk : NULL, hdev, 1);
 	}
 
-	if (hdev)
-		mgmt_init_hdev(sk, hdev);
+	if (!cmd)
+		goto unlock;
+
+	rp.instance = 0x01;
+
+	if (status)
+		mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode,
+				mgmt_status(status));
+	else
+		mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode,
+				  mgmt_status(status), &rp, sizeof(rp));
+
+	mgmt_pending_remove(cmd);
+
+unlock:
+	hci_dev_unlock(hdev);
+}
+
+static void adv_timeout_expired(struct work_struct *work)
+{
+	struct hci_dev *hdev = container_of(work, struct hci_dev,
+					    adv_instance.timeout_exp.work);
 
-	cp = buf + sizeof(*hdr);
+	hdev->adv_instance.timeout = 0;
 
-	err = handler->func(sk, hdev, cp, len);
+	hci_dev_lock(hdev);
+	clear_adv_instance(hdev);
+	hci_dev_unlock(hdev);
+}
+
+static int add_advertising(struct sock *sk, struct hci_dev *hdev,
+			   void *data, u16 data_len)
+{
+	struct mgmt_cp_add_advertising *cp = data;
+	struct mgmt_rp_add_advertising rp;
+	u32 flags;
+	u32 supported_flags;
+	u8 status;
+	u16 timeout;
+	int err;
+	struct mgmt_pending_cmd *cmd;
+	struct hci_request req;
+
+	BT_DBG("%s", hdev->name);
+
+	status = mgmt_le_support(hdev);
+	if (status)
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING,
+				       status);
+
+	flags = __le32_to_cpu(cp->flags);
+	timeout = __le16_to_cpu(cp->timeout);
+
+	/* The current implementation only supports adding one instance and only
+	 * a subset of the specified flags.
+	 */
+	supported_flags = get_supported_adv_flags(hdev);
+	if (cp->instance != 0x01 || (flags & ~supported_flags))
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING,
+				       MGMT_STATUS_INVALID_PARAMS);
+
+	hci_dev_lock(hdev);
+
+	if (timeout && !hdev_is_powered(hdev)) {
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING,
+				      MGMT_STATUS_REJECTED);
+		goto unlock;
+	}
+
+	if (pending_find(MGMT_OP_ADD_ADVERTISING, hdev) ||
+	    pending_find(MGMT_OP_REMOVE_ADVERTISING, hdev) ||
+	    pending_find(MGMT_OP_SET_LE, hdev)) {
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING,
+				      MGMT_STATUS_BUSY);
+		goto unlock;
+	}
+
+	if (!tlv_data_is_valid(hdev, flags, cp->data, cp->adv_data_len, true) ||
+	    !tlv_data_is_valid(hdev, flags, cp->data + cp->adv_data_len,
+			       cp->scan_rsp_len, false)) {
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING,
+				      MGMT_STATUS_INVALID_PARAMS);
+		goto unlock;
+	}
+
+	INIT_DELAYED_WORK(&hdev->adv_instance.timeout_exp, adv_timeout_expired);
+
+	hdev->adv_instance.flags = flags;
+	hdev->adv_instance.adv_data_len = cp->adv_data_len;
+	hdev->adv_instance.scan_rsp_len = cp->scan_rsp_len;
+
+	if (cp->adv_data_len)
+		memcpy(hdev->adv_instance.adv_data, cp->data, cp->adv_data_len);
+
+	if (cp->scan_rsp_len)
+		memcpy(hdev->adv_instance.scan_rsp_data,
+		       cp->data + cp->adv_data_len, cp->scan_rsp_len);
+
+	if (hdev->adv_instance.timeout)
+		cancel_delayed_work(&hdev->adv_instance.timeout_exp);
+
+	hdev->adv_instance.timeout = timeout;
+
+	if (timeout)
+		queue_delayed_work(hdev->workqueue,
+				   &hdev->adv_instance.timeout_exp,
+				   msecs_to_jiffies(timeout * 1000));
+
+	if (!hci_dev_test_and_set_flag(hdev, HCI_ADVERTISING_INSTANCE))
+		advertising_added(sk, hdev, 1);
+
+	/* If the HCI_ADVERTISING flag is set or the device isn't powered then
+	 * we have no HCI communication to make. Simply return.
+	 */
+	if (!hdev_is_powered(hdev) ||
+	    hci_dev_test_flag(hdev, HCI_ADVERTISING)) {
+		rp.instance = 0x01;
+		err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_ADD_ADVERTISING,
+					MGMT_STATUS_SUCCESS, &rp, sizeof(rp));
+		goto unlock;
+	}
+
+	/* We're good to go, update advertising data, parameters, and start
+	 * advertising.
+	 */
+	cmd = mgmt_pending_add(sk, MGMT_OP_ADD_ADVERTISING, hdev, data,
+			       data_len);
+	if (!cmd) {
+		err = -ENOMEM;
+		goto unlock;
+	}
+
+	hci_req_init(&req, hdev);
+
+	update_adv_data(&req);
+	update_scan_rsp_data(&req);
+	enable_advertising(&req);
+
+	err = hci_req_run(&req, add_advertising_complete);
 	if (err < 0)
-		goto done;
+		mgmt_pending_remove(cmd);
+
+unlock:
+	hci_dev_unlock(hdev);
 
-	err = msglen;
+	return err;
+}
 
-done:
-	if (hdev)
-		hci_dev_put(hdev);
+static void remove_advertising_complete(struct hci_dev *hdev, u8 status,
+					u16 opcode)
+{
+	struct mgmt_pending_cmd *cmd;
+	struct mgmt_rp_remove_advertising rp;
+
+	BT_DBG("status %d", status);
+
+	hci_dev_lock(hdev);
+
+	/* A failure status here only means that we failed to disable
+	 * advertising. Otherwise, the advertising instance has been removed,
+	 * so report success.
+	 */
+	cmd = pending_find(MGMT_OP_REMOVE_ADVERTISING, hdev);
+	if (!cmd)
+		goto unlock;
+
+	rp.instance = 1;
+
+	mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, MGMT_STATUS_SUCCESS,
+			  &rp, sizeof(rp));
+	mgmt_pending_remove(cmd);
+
+unlock:
+	hci_dev_unlock(hdev);
+}
+
+static int remove_advertising(struct sock *sk, struct hci_dev *hdev,
+			      void *data, u16 data_len)
+{
+	struct mgmt_cp_remove_advertising *cp = data;
+	struct mgmt_rp_remove_advertising rp;
+	int err;
+	struct mgmt_pending_cmd *cmd;
+	struct hci_request req;
+
+	BT_DBG("%s", hdev->name);
+
+	/* The current implementation only allows modifying instance no 1. A
+	 * value of 0 indicates that all instances should be cleared.
+	 */
+	if (cp->instance > 1)
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_REMOVE_ADVERTISING,
+				       MGMT_STATUS_INVALID_PARAMS);
+
+	hci_dev_lock(hdev);
+
+	if (pending_find(MGMT_OP_ADD_ADVERTISING, hdev) ||
+	    pending_find(MGMT_OP_REMOVE_ADVERTISING, hdev) ||
+	    pending_find(MGMT_OP_SET_LE, hdev)) {
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_REMOVE_ADVERTISING,
+				      MGMT_STATUS_BUSY);
+		goto unlock;
+	}
+
+	if (!hci_dev_test_flag(hdev, HCI_ADVERTISING_INSTANCE)) {
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_REMOVE_ADVERTISING,
+				      MGMT_STATUS_INVALID_PARAMS);
+		goto unlock;
+	}
+
+	if (hdev->adv_instance.timeout)
+		cancel_delayed_work(&hdev->adv_instance.timeout_exp);
+
+	memset(&hdev->adv_instance, 0, sizeof(hdev->adv_instance));
+
+	advertising_removed(sk, hdev, 1);
+
+	hci_dev_clear_flag(hdev, HCI_ADVERTISING_INSTANCE);
+
+	/* If the HCI_ADVERTISING flag is set or the device isn't powered then
+	 * we have no HCI communication to make. Simply return.
+	 */
+	if (!hdev_is_powered(hdev) ||
+	    hci_dev_test_flag(hdev, HCI_ADVERTISING)) {
+		rp.instance = 1;
+		err = mgmt_cmd_complete(sk, hdev->id,
+					MGMT_OP_REMOVE_ADVERTISING,
+					MGMT_STATUS_SUCCESS, &rp, sizeof(rp));
+		goto unlock;
+	}
+
+	cmd = mgmt_pending_add(sk, MGMT_OP_REMOVE_ADVERTISING, hdev, data,
+			       data_len);
+	if (!cmd) {
+		err = -ENOMEM;
+		goto unlock;
+	}
+
+	hci_req_init(&req, hdev);
+	disable_advertising(&req);
+
+	err = hci_req_run(&req, remove_advertising_complete);
+	if (err < 0)
+		mgmt_pending_remove(cmd);
+
+unlock:
+	hci_dev_unlock(hdev);
 
-	kfree(buf);
 	return err;
 }
 
+static const struct hci_mgmt_handler mgmt_handlers[] = {
+	{ NULL }, /* 0x0000 (no command) */
+	{ read_version,            MGMT_READ_VERSION_SIZE,
+						HCI_MGMT_NO_HDEV |
+						HCI_MGMT_UNTRUSTED },
+	{ read_commands,           MGMT_READ_COMMANDS_SIZE,
+						HCI_MGMT_NO_HDEV |
+						HCI_MGMT_UNTRUSTED },
+	{ read_index_list,         MGMT_READ_INDEX_LIST_SIZE,
+						HCI_MGMT_NO_HDEV |
+						HCI_MGMT_UNTRUSTED },
+	{ read_controller_info,    MGMT_READ_INFO_SIZE,
+						HCI_MGMT_UNTRUSTED },
+	{ set_powered,             MGMT_SETTING_SIZE },
+	{ set_discoverable,        MGMT_SET_DISCOVERABLE_SIZE },
+	{ set_connectable,         MGMT_SETTING_SIZE },
+	{ set_fast_connectable,    MGMT_SETTING_SIZE },
+	{ set_bondable,            MGMT_SETTING_SIZE },
+	{ set_link_security,       MGMT_SETTING_SIZE },
+	{ set_ssp,                 MGMT_SETTING_SIZE },
+	{ set_hs,                  MGMT_SETTING_SIZE },
+	{ set_le,                  MGMT_SETTING_SIZE },
+	{ set_dev_class,           MGMT_SET_DEV_CLASS_SIZE },
+	{ set_local_name,          MGMT_SET_LOCAL_NAME_SIZE },
+	{ add_uuid,                MGMT_ADD_UUID_SIZE },
+	{ remove_uuid,             MGMT_REMOVE_UUID_SIZE },
+	{ load_link_keys,          MGMT_LOAD_LINK_KEYS_SIZE,
+						HCI_MGMT_VAR_LEN },
+	{ load_long_term_keys,     MGMT_LOAD_LONG_TERM_KEYS_SIZE,
+						HCI_MGMT_VAR_LEN },
+	{ disconnect,              MGMT_DISCONNECT_SIZE },
+	{ get_connections,         MGMT_GET_CONNECTIONS_SIZE },
+	{ pin_code_reply,          MGMT_PIN_CODE_REPLY_SIZE },
+	{ pin_code_neg_reply,      MGMT_PIN_CODE_NEG_REPLY_SIZE },
+	{ set_io_capability,       MGMT_SET_IO_CAPABILITY_SIZE },
+	{ pair_device,             MGMT_PAIR_DEVICE_SIZE },
+	{ cancel_pair_device,      MGMT_CANCEL_PAIR_DEVICE_SIZE },
+	{ unpair_device,           MGMT_UNPAIR_DEVICE_SIZE },
+	{ user_confirm_reply,      MGMT_USER_CONFIRM_REPLY_SIZE },
+	{ user_confirm_neg_reply,  MGMT_USER_CONFIRM_NEG_REPLY_SIZE },
+	{ user_passkey_reply,      MGMT_USER_PASSKEY_REPLY_SIZE },
+	{ user_passkey_neg_reply,  MGMT_USER_PASSKEY_NEG_REPLY_SIZE },
+	{ read_local_oob_data,     MGMT_READ_LOCAL_OOB_DATA_SIZE },
+	{ add_remote_oob_data,     MGMT_ADD_REMOTE_OOB_DATA_SIZE,
+						HCI_MGMT_VAR_LEN },
+	{ remove_remote_oob_data,  MGMT_REMOVE_REMOTE_OOB_DATA_SIZE },
+	{ start_discovery,         MGMT_START_DISCOVERY_SIZE },
+	{ stop_discovery,          MGMT_STOP_DISCOVERY_SIZE },
+	{ confirm_name,            MGMT_CONFIRM_NAME_SIZE },
+	{ block_device,            MGMT_BLOCK_DEVICE_SIZE },
+	{ unblock_device,          MGMT_UNBLOCK_DEVICE_SIZE },
+	{ set_device_id,           MGMT_SET_DEVICE_ID_SIZE },
+	{ set_advertising,         MGMT_SETTING_SIZE },
+	{ set_bredr,               MGMT_SETTING_SIZE },
+	{ set_static_address,      MGMT_SET_STATIC_ADDRESS_SIZE },
+	{ set_scan_params,         MGMT_SET_SCAN_PARAMS_SIZE },
+	{ set_secure_conn,         MGMT_SETTING_SIZE },
+	{ set_debug_keys,          MGMT_SETTING_SIZE },
+	{ set_privacy,             MGMT_SET_PRIVACY_SIZE },
+	{ load_irks,               MGMT_LOAD_IRKS_SIZE,
+						HCI_MGMT_VAR_LEN },
+	{ get_conn_info,           MGMT_GET_CONN_INFO_SIZE },
+	{ get_clock_info,          MGMT_GET_CLOCK_INFO_SIZE },
+	{ add_device,              MGMT_ADD_DEVICE_SIZE },
+	{ remove_device,           MGMT_REMOVE_DEVICE_SIZE },
+	{ load_conn_param,         MGMT_LOAD_CONN_PARAM_SIZE,
+						HCI_MGMT_VAR_LEN },
+	{ read_unconf_index_list,  MGMT_READ_UNCONF_INDEX_LIST_SIZE,
+						HCI_MGMT_NO_HDEV |
+						HCI_MGMT_UNTRUSTED },
+	{ read_config_info,        MGMT_READ_CONFIG_INFO_SIZE,
+						HCI_MGMT_UNCONFIGURED |
+						HCI_MGMT_UNTRUSTED },
+	{ set_external_config,     MGMT_SET_EXTERNAL_CONFIG_SIZE,
+						HCI_MGMT_UNCONFIGURED },
+	{ set_public_address,      MGMT_SET_PUBLIC_ADDRESS_SIZE,
+						HCI_MGMT_UNCONFIGURED },
+	{ start_service_discovery, MGMT_START_SERVICE_DISCOVERY_SIZE,
+						HCI_MGMT_VAR_LEN },
+	{ read_local_oob_ext_data, MGMT_READ_LOCAL_OOB_EXT_DATA_SIZE },
+	{ read_ext_index_list,     MGMT_READ_EXT_INDEX_LIST_SIZE,
+						HCI_MGMT_NO_HDEV |
+						HCI_MGMT_UNTRUSTED },
+	{ read_adv_features,       MGMT_READ_ADV_FEATURES_SIZE },
+	{ add_advertising,	   MGMT_ADD_ADVERTISING_SIZE,
+						HCI_MGMT_VAR_LEN },
+	{ remove_advertising,	   MGMT_REMOVE_ADVERTISING_SIZE },
+};
+
 void mgmt_index_added(struct hci_dev *hdev)
 {
-	if (hdev->dev_type != HCI_BREDR)
-		return;
+	struct mgmt_ev_ext_index ev;
 
 	if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks))
 		return;
 
-	if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags))
-		mgmt_event(MGMT_EV_UNCONF_INDEX_ADDED, hdev, NULL, 0, NULL);
-	else
-		mgmt_event(MGMT_EV_INDEX_ADDED, hdev, NULL, 0, NULL);
+	switch (hdev->dev_type) {
+	case HCI_BREDR:
+		if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) {
+			mgmt_index_event(MGMT_EV_UNCONF_INDEX_ADDED, hdev,
+					 NULL, 0, HCI_MGMT_UNCONF_INDEX_EVENTS);
+			ev.type = 0x01;
+		} else {
+			mgmt_index_event(MGMT_EV_INDEX_ADDED, hdev, NULL, 0,
+					 HCI_MGMT_INDEX_EVENTS);
+			ev.type = 0x00;
+		}
+		break;
+	case HCI_AMP:
+		ev.type = 0x02;
+		break;
+	default:
+		return;
+	}
+
+	ev.bus = hdev->bus;
+
+	mgmt_index_event(MGMT_EV_EXT_INDEX_ADDED, hdev, &ev, sizeof(ev),
+			 HCI_MGMT_EXT_INDEX_EVENTS);
 }
 
 void mgmt_index_removed(struct hci_dev *hdev)
 {
+	struct mgmt_ev_ext_index ev;
 	u8 status = MGMT_STATUS_INVALID_INDEX;
 
-	if (hdev->dev_type != HCI_BREDR)
+	if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks))
 		return;
 
-	if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks))
+	switch (hdev->dev_type) {
+	case HCI_BREDR:
+		mgmt_pending_foreach(0, hdev, cmd_complete_rsp, &status);
+
+		if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) {
+			mgmt_index_event(MGMT_EV_UNCONF_INDEX_REMOVED, hdev,
+					 NULL, 0, HCI_MGMT_UNCONF_INDEX_EVENTS);
+			ev.type = 0x01;
+		} else {
+			mgmt_index_event(MGMT_EV_INDEX_REMOVED, hdev, NULL, 0,
+					 HCI_MGMT_INDEX_EVENTS);
+			ev.type = 0x00;
+		}
+		break;
+	case HCI_AMP:
+		ev.type = 0x02;
+		break;
+	default:
 		return;
+	}
 
-	mgmt_pending_foreach(0, hdev, cmd_status_rsp, &status);
+	ev.bus = hdev->bus;
 
-	if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags))
-		mgmt_event(MGMT_EV_UNCONF_INDEX_REMOVED, hdev, NULL, 0, NULL);
-	else
-		mgmt_event(MGMT_EV_INDEX_REMOVED, hdev, NULL, 0, NULL);
+	mgmt_index_event(MGMT_EV_EXT_INDEX_REMOVED, hdev, &ev, sizeof(ev),
+			 HCI_MGMT_EXT_INDEX_EVENTS);
 }
 
 /* This function requires the caller holds hdev->lock */
-static void restart_le_actions(struct hci_dev *hdev)
+static void restart_le_actions(struct hci_request *req)
 {
+	struct hci_dev *hdev = req->hdev;
 	struct hci_conn_params *p;
 
 	list_for_each_entry(p, &hdev->le_conn_params, list) {
@@ -5848,18 +7328,25 @@ static void restart_le_actions(struct hci_dev *hdev)
 		}
 	}
 
-	hci_update_background_scan(hdev);
+	__hci_update_background_scan(req);
 }
 
-static void powered_complete(struct hci_dev *hdev, u8 status)
+static void powered_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
 	struct cmd_lookup match = { NULL, hdev };
 
 	BT_DBG("status 0x%02x", status);
 
-	hci_dev_lock(hdev);
+	if (!status) {
+		/* Register the available SMP channels (BR/EDR and LE) only
+		 * when successfully powering on the controller. This late
+		 * registration is required so that LE SMP can clearly
+		 * decide if the public address or static address is used.
+		 */
+		smp_register(hdev);
+	}
 
-	restart_le_actions(hdev);
+	hci_dev_lock(hdev);
 
 	mgmt_pending_foreach(MGMT_OP_SET_POWERED, hdev, settings_rsp, &match);
 
@@ -5878,14 +7365,21 @@ static int powered_update_hci(struct hci_dev *hdev)
 
 	hci_req_init(&req, hdev);
 
-	if (test_bit(HCI_SSP_ENABLED, &hdev->dev_flags) &&
+	if (hci_dev_test_flag(hdev, HCI_SSP_ENABLED) &&
 	    !lmp_host_ssp_capable(hdev)) {
-		u8 ssp = 1;
+		u8 mode = 0x01;
+
+		hci_req_add(&req, HCI_OP_WRITE_SSP_MODE, sizeof(mode), &mode);
 
-		hci_req_add(&req, HCI_OP_WRITE_SSP_MODE, 1, &ssp);
+		if (bredr_sc_enabled(hdev) && !lmp_host_sc_capable(hdev)) {
+			u8 support = 0x01;
+
+			hci_req_add(&req, HCI_OP_WRITE_SC_SUPPORT,
+				    sizeof(support), &support);
+		}
 	}
 
-	if (test_bit(HCI_LE_ENABLED, &hdev->dev_flags) &&
+	if (hci_dev_test_flag(hdev, HCI_LE_ENABLED) &&
 	    lmp_bredr_capable(hdev)) {
 		struct hci_cp_write_le_host_supported cp;
 
@@ -5906,23 +7400,29 @@ static int powered_update_hci(struct hci_dev *hdev)
 		 * advertising data. This also applies to the case
 		 * where BR/EDR was toggled during the AUTO_OFF phase.
 		 */
-		if (test_bit(HCI_LE_ENABLED, &hdev->dev_flags)) {
+		if (hci_dev_test_flag(hdev, HCI_LE_ENABLED)) {
 			update_adv_data(&req);
 			update_scan_rsp_data(&req);
 		}
 
-		if (test_bit(HCI_ADVERTISING, &hdev->dev_flags))
+		if (hci_dev_test_flag(hdev, HCI_ADVERTISING) ||
+		    hci_dev_test_flag(hdev, HCI_ADVERTISING_INSTANCE))
 			enable_advertising(&req);
+
+		restart_le_actions(&req);
 	}
 
-	link_sec = test_bit(HCI_LINK_SECURITY, &hdev->dev_flags);
+	link_sec = hci_dev_test_flag(hdev, HCI_LINK_SECURITY);
 	if (link_sec != test_bit(HCI_AUTH, &hdev->flags))
 		hci_req_add(&req, HCI_OP_WRITE_AUTH_ENABLE,
 			    sizeof(link_sec), &link_sec);
 
 	if (lmp_bredr_capable(hdev)) {
-		write_fast_connectable(&req, false);
-		hci_update_page_scan(hdev, &req);
+		if (hci_dev_test_flag(hdev, HCI_FAST_CONNECTABLE))
+			write_fast_connectable(&req, true);
+		else
+			write_fast_connectable(&req, false);
+		__hci_update_page_scan(&req);
 		update_class(&req);
 		update_name(&req);
 		update_eir(&req);
@@ -5934,11 +7434,10 @@ static int powered_update_hci(struct hci_dev *hdev)
 int mgmt_powered(struct hci_dev *hdev, u8 powered)
 {
 	struct cmd_lookup match = { NULL, hdev };
-	u8 status_not_powered = MGMT_STATUS_NOT_POWERED;
-	u8 zero_cod[] = { 0, 0, 0 };
+	u8 status, zero_cod[] = { 0, 0, 0 };
 	int err;
 
-	if (!test_bit(HCI_MGMT, &hdev->dev_flags))
+	if (!hci_dev_test_flag(hdev, HCI_MGMT))
 		return 0;
 
 	if (powered) {
@@ -5951,11 +7450,24 @@ int mgmt_powered(struct hci_dev *hdev, u8 powered)
 	}
 
 	mgmt_pending_foreach(MGMT_OP_SET_POWERED, hdev, settings_rsp, &match);
-	mgmt_pending_foreach(0, hdev, cmd_status_rsp, &status_not_powered);
+
+	/* If the power off is because of hdev unregistration let
+	 * use the appropriate INVALID_INDEX status. Otherwise use
+	 * NOT_POWERED. We cover both scenarios here since later in
+	 * mgmt_index_removed() any hci_conn callbacks will have already
+	 * been triggered, potentially causing misleading DISCONNECTED
+	 * status responses.
+	 */
+	if (hci_dev_test_flag(hdev, HCI_UNREGISTER))
+		status = MGMT_STATUS_INVALID_INDEX;
+	else
+		status = MGMT_STATUS_NOT_POWERED;
+
+	mgmt_pending_foreach(0, hdev, cmd_complete_rsp, &status);
 
 	if (memcmp(hdev->dev_class, zero_cod, sizeof(zero_cod)) != 0)
-		mgmt_event(MGMT_EV_CLASS_OF_DEV_CHANGED, hdev,
-			   zero_cod, sizeof(zero_cod), NULL);
+		mgmt_generic_event(MGMT_EV_CLASS_OF_DEV_CHANGED, hdev,
+				   zero_cod, sizeof(zero_cod), NULL);
 
 new_settings:
 	err = new_settings(hdev, match.sk);
@@ -5968,10 +7480,10 @@ new_settings:
 
 void mgmt_set_powered_failed(struct hci_dev *hdev, int err)
 {
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 	u8 status;
 
-	cmd = mgmt_pending_find(MGMT_OP_SET_POWERED, hdev);
+	cmd = pending_find(MGMT_OP_SET_POWERED, hdev);
 	if (!cmd)
 		return;
 
@@ -5980,7 +7492,7 @@ void mgmt_set_powered_failed(struct hci_dev *hdev, int err)
 	else
 		status = MGMT_STATUS_FAILED;
 
-	cmd_status(cmd->sk, hdev->id, MGMT_OP_SET_POWERED, status);
+	mgmt_cmd_status(cmd->sk, hdev->id, MGMT_OP_SET_POWERED, status);
 
 	mgmt_pending_remove(cmd);
 }
@@ -5996,17 +7508,23 @@ void mgmt_discoverable_timeout(struct hci_dev *hdev)
 	 * of a timeout triggered from general discoverable, it is
 	 * safe to unconditionally clear the flag.
 	 */
-	clear_bit(HCI_LIMITED_DISCOVERABLE, &hdev->dev_flags);
-	clear_bit(HCI_DISCOVERABLE, &hdev->dev_flags);
+	hci_dev_clear_flag(hdev, HCI_LIMITED_DISCOVERABLE);
+	hci_dev_clear_flag(hdev, HCI_DISCOVERABLE);
 
 	hci_req_init(&req, hdev);
-	if (test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) {
+	if (hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) {
 		u8 scan = SCAN_PAGE;
 		hci_req_add(&req, HCI_OP_WRITE_SCAN_ENABLE,
 			    sizeof(scan), &scan);
 	}
 	update_class(&req);
-	update_adv_data(&req);
+
+	/* Advertising instances don't use the global discoverable setting, so
+	 * only update AD if advertising was enabled using Set Advertising.
+	 */
+	if (hci_dev_test_flag(hdev, HCI_ADVERTISING))
+		update_adv_data(&req);
+
 	hci_req_run(&req, NULL);
 
 	hdev->discov_timeout = 0;
@@ -6035,8 +7553,19 @@ void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key,
 
 static u8 mgmt_ltk_type(struct smp_ltk *ltk)
 {
-	if (ltk->authenticated)
-		return MGMT_LTK_AUTHENTICATED;
+	switch (ltk->type) {
+	case SMP_LTK:
+	case SMP_LTK_SLAVE:
+		if (ltk->authenticated)
+			return MGMT_LTK_AUTHENTICATED;
+		return MGMT_LTK_UNAUTHENTICATED;
+	case SMP_LTK_P256:
+		if (ltk->authenticated)
+			return MGMT_LTK_P256_AUTH;
+		return MGMT_LTK_P256_UNAUTH;
+	case SMP_LTK_P256_DEBUG:
+		return MGMT_LTK_P256_DEBUG;
+	}
 
 	return MGMT_LTK_UNAUTHENTICATED;
 }
@@ -6133,7 +7662,7 @@ void mgmt_new_csrk(struct hci_dev *hdev, struct smp_csrk *csrk,
 
 	bacpy(&ev.key.addr.bdaddr, &csrk->bdaddr);
 	ev.key.addr.type = link_to_bdaddr(LE_LINK, csrk->bdaddr_type);
-	ev.key.master = csrk->master;
+	ev.key.type = csrk->type;
 	memcpy(ev.key.val, csrk->val, sizeof(csrk->val));
 
 	mgmt_event(MGMT_EV_NEW_CSRK, hdev, &ev, sizeof(ev), NULL);
@@ -6160,37 +7689,36 @@ void mgmt_new_conn_param(struct hci_dev *hdev, bdaddr_t *bdaddr,
 	mgmt_event(MGMT_EV_NEW_CONN_PARAM, hdev, &ev, sizeof(ev), NULL);
 }
 
-static inline u16 eir_append_data(u8 *eir, u16 eir_len, u8 type, u8 *data,
-				  u8 data_len)
-{
-	eir[eir_len++] = sizeof(type) + data_len;
-	eir[eir_len++] = type;
-	memcpy(&eir[eir_len], data, data_len);
-	eir_len += data_len;
-
-	return eir_len;
-}
-
-void mgmt_device_connected(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
-			   u8 addr_type, u32 flags, u8 *name, u8 name_len,
-			   u8 *dev_class)
+void mgmt_device_connected(struct hci_dev *hdev, struct hci_conn *conn,
+			   u32 flags, u8 *name, u8 name_len)
 {
 	char buf[512];
 	struct mgmt_ev_device_connected *ev = (void *) buf;
 	u16 eir_len = 0;
 
-	bacpy(&ev->addr.bdaddr, bdaddr);
-	ev->addr.type = link_to_bdaddr(link_type, addr_type);
+	bacpy(&ev->addr.bdaddr, &conn->dst);
+	ev->addr.type = link_to_bdaddr(conn->type, conn->dst_type);
 
 	ev->flags = __cpu_to_le32(flags);
 
-	if (name_len > 0)
-		eir_len = eir_append_data(ev->eir, 0, EIR_NAME_COMPLETE,
-					  name, name_len);
+	/* We must ensure that the EIR Data fields are ordered and
+	 * unique. Keep it simple for now and avoid the problem by not
+	 * adding any BR/EDR data to the LE adv.
+	 */
+	if (conn->le_adv_data_len > 0) {
+		memcpy(&ev->eir[eir_len],
+		       conn->le_adv_data, conn->le_adv_data_len);
+		eir_len = conn->le_adv_data_len;
+	} else {
+		if (name_len > 0)
+			eir_len = eir_append_data(ev->eir, 0, EIR_NAME_COMPLETE,
+						  name, name_len);
 
-	if (dev_class && memcmp(dev_class, "\0\0\0", 3) != 0)
-		eir_len = eir_append_data(ev->eir, eir_len,
-					  EIR_CLASS_OF_DEV, dev_class, 3);
+		if (memcmp(conn->dev_class, "\0\0\0", 3) != 0)
+			eir_len = eir_append_data(ev->eir, eir_len,
+						  EIR_CLASS_OF_DEV,
+						  conn->dev_class, 3);
+	}
 
 	ev->eir_len = cpu_to_le16(eir_len);
 
@@ -6198,17 +7726,11 @@ void mgmt_device_connected(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 		    sizeof(*ev) + eir_len, NULL);
 }
 
-static void disconnect_rsp(struct pending_cmd *cmd, void *data)
+static void disconnect_rsp(struct mgmt_pending_cmd *cmd, void *data)
 {
-	struct mgmt_cp_disconnect *cp = cmd->param;
 	struct sock **sk = data;
-	struct mgmt_rp_disconnect rp;
-
-	bacpy(&rp.addr.bdaddr, &cp->addr.bdaddr);
-	rp.addr.type = cp->addr.type;
 
-	cmd_complete(cmd->sk, cmd->index, MGMT_OP_DISCONNECT, 0, &rp,
-		     sizeof(rp));
+	cmd->cmd_complete(cmd, 0);
 
 	*sk = cmd->sk;
 	sock_hold(*sk);
@@ -6216,29 +7738,23 @@ static void disconnect_rsp(struct pending_cmd *cmd, void *data)
 	mgmt_pending_remove(cmd);
 }
 
-static void unpair_device_rsp(struct pending_cmd *cmd, void *data)
+static void unpair_device_rsp(struct mgmt_pending_cmd *cmd, void *data)
 {
 	struct hci_dev *hdev = data;
 	struct mgmt_cp_unpair_device *cp = cmd->param;
-	struct mgmt_rp_unpair_device rp;
-
-	memset(&rp, 0, sizeof(rp));
-	bacpy(&rp.addr.bdaddr, &cp->addr.bdaddr);
-	rp.addr.type = cp->addr.type;
 
 	device_unpaired(hdev, &cp->addr.bdaddr, cp->addr.type, cmd->sk);
 
-	cmd_complete(cmd->sk, cmd->index, cmd->opcode, 0, &rp, sizeof(rp));
-
+	cmd->cmd_complete(cmd, 0);
 	mgmt_pending_remove(cmd);
 }
 
 bool mgmt_powering_down(struct hci_dev *hdev)
 {
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 	struct mgmt_mode *cp;
 
-	cmd = mgmt_pending_find(MGMT_OP_SET_POWERED, hdev);
+	cmd = pending_find(MGMT_OP_SET_POWERED, hdev);
 	if (!cmd)
 		return false;
 
@@ -6290,13 +7806,12 @@ void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr,
 {
 	u8 bdaddr_type = link_to_bdaddr(link_type, addr_type);
 	struct mgmt_cp_disconnect *cp;
-	struct mgmt_rp_disconnect rp;
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 
 	mgmt_pending_foreach(MGMT_OP_UNPAIR_DEVICE, hdev, unpair_device_rsp,
 			     hdev);
 
-	cmd = mgmt_pending_find(MGMT_OP_DISCONNECT, hdev);
+	cmd = pending_find(MGMT_OP_DISCONNECT, hdev);
 	if (!cmd)
 		return;
 
@@ -6308,12 +7823,7 @@ void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr,
 	if (cp->addr.type != bdaddr_type)
 		return;
 
-	bacpy(&rp.addr.bdaddr, bdaddr);
-	rp.addr.type = bdaddr_type;
-
-	cmd_complete(cmd->sk, cmd->index, MGMT_OP_DISCONNECT,
-		     mgmt_status(status), &rp, sizeof(rp));
-
+	cmd->cmd_complete(cmd, mgmt_status(status));
 	mgmt_pending_remove(cmd);
 }
 
@@ -6351,38 +7861,26 @@ void mgmt_pin_code_request(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 secure)
 void mgmt_pin_code_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr,
 				  u8 status)
 {
-	struct pending_cmd *cmd;
-	struct mgmt_rp_pin_code_reply rp;
+	struct mgmt_pending_cmd *cmd;
 
-	cmd = mgmt_pending_find(MGMT_OP_PIN_CODE_REPLY, hdev);
+	cmd = pending_find(MGMT_OP_PIN_CODE_REPLY, hdev);
 	if (!cmd)
 		return;
 
-	bacpy(&rp.addr.bdaddr, bdaddr);
-	rp.addr.type = BDADDR_BREDR;
-
-	cmd_complete(cmd->sk, hdev->id, MGMT_OP_PIN_CODE_REPLY,
-		     mgmt_status(status), &rp, sizeof(rp));
-
+	cmd->cmd_complete(cmd, mgmt_status(status));
 	mgmt_pending_remove(cmd);
 }
 
 void mgmt_pin_code_neg_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr,
 				      u8 status)
 {
-	struct pending_cmd *cmd;
-	struct mgmt_rp_pin_code_reply rp;
+	struct mgmt_pending_cmd *cmd;
 
-	cmd = mgmt_pending_find(MGMT_OP_PIN_CODE_NEG_REPLY, hdev);
+	cmd = pending_find(MGMT_OP_PIN_CODE_NEG_REPLY, hdev);
 	if (!cmd)
 		return;
 
-	bacpy(&rp.addr.bdaddr, bdaddr);
-	rp.addr.type = BDADDR_BREDR;
-
-	cmd_complete(cmd->sk, hdev->id, MGMT_OP_PIN_CODE_NEG_REPLY,
-		     mgmt_status(status), &rp, sizeof(rp));
-
+	cmd->cmd_complete(cmd, mgmt_status(status));
 	mgmt_pending_remove(cmd);
 }
 
@@ -6421,22 +7919,16 @@ static int user_pairing_resp_complete(struct hci_dev *hdev, bdaddr_t *bdaddr,
 				      u8 link_type, u8 addr_type, u8 status,
 				      u8 opcode)
 {
-	struct pending_cmd *cmd;
-	struct mgmt_rp_user_confirm_reply rp;
-	int err;
+	struct mgmt_pending_cmd *cmd;
 
-	cmd = mgmt_pending_find(opcode, hdev);
+	cmd = pending_find(opcode, hdev);
 	if (!cmd)
 		return -ENOENT;
 
-	bacpy(&rp.addr.bdaddr, bdaddr);
-	rp.addr.type = link_to_bdaddr(link_type, addr_type);
-	err = cmd_complete(cmd->sk, hdev->id, opcode, mgmt_status(status),
-			   &rp, sizeof(rp));
-
+	cmd->cmd_complete(cmd, mgmt_status(status));
 	mgmt_pending_remove(cmd);
 
-	return err;
+	return 0;
 }
 
 int mgmt_user_confirm_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr,
@@ -6488,7 +7980,7 @@ int mgmt_user_passkey_notify(struct hci_dev *hdev, bdaddr_t *bdaddr,
 void mgmt_auth_failed(struct hci_conn *conn, u8 hci_status)
 {
 	struct mgmt_ev_auth_failed ev;
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 	u8 status = mgmt_status(hci_status);
 
 	bacpy(&ev.addr.bdaddr, &conn->dst);
@@ -6500,8 +7992,10 @@ void mgmt_auth_failed(struct hci_conn *conn, u8 hci_status)
 	mgmt_event(MGMT_EV_AUTH_FAILED, conn->hdev, &ev, sizeof(ev),
 		    cmd ? cmd->sk : NULL);
 
-	if (cmd)
-		pairing_complete(cmd, status);
+	if (cmd) {
+		cmd->cmd_complete(cmd, status);
+		mgmt_pending_remove(cmd);
+	}
 }
 
 void mgmt_auth_enable_complete(struct hci_dev *hdev, u8 status)
@@ -6517,11 +8011,9 @@ void mgmt_auth_enable_complete(struct hci_dev *hdev, u8 status)
 	}
 
 	if (test_bit(HCI_AUTH, &hdev->flags))
-		changed = !test_and_set_bit(HCI_LINK_SECURITY,
-					    &hdev->dev_flags);
+		changed = !hci_dev_test_and_set_flag(hdev, HCI_LINK_SECURITY);
 	else
-		changed = test_and_clear_bit(HCI_LINK_SECURITY,
-					     &hdev->dev_flags);
+		changed = hci_dev_test_and_clear_flag(hdev, HCI_LINK_SECURITY);
 
 	mgmt_pending_foreach(MGMT_OP_SET_LINK_SECURITY, hdev, settings_rsp,
 			     &match);
@@ -6557,9 +8049,9 @@ void mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status)
 	if (status) {
 		u8 mgmt_err = mgmt_status(status);
 
-		if (enable && test_and_clear_bit(HCI_SSP_ENABLED,
-						 &hdev->dev_flags)) {
-			clear_bit(HCI_HS_ENABLED, &hdev->dev_flags);
+		if (enable && hci_dev_test_and_clear_flag(hdev,
+							  HCI_SSP_ENABLED)) {
+			hci_dev_clear_flag(hdev, HCI_HS_ENABLED);
 			new_settings(hdev, NULL);
 		}
 
@@ -6569,14 +8061,14 @@ void mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status)
 	}
 
 	if (enable) {
-		changed = !test_and_set_bit(HCI_SSP_ENABLED, &hdev->dev_flags);
+		changed = !hci_dev_test_and_set_flag(hdev, HCI_SSP_ENABLED);
 	} else {
-		changed = test_and_clear_bit(HCI_SSP_ENABLED, &hdev->dev_flags);
+		changed = hci_dev_test_and_clear_flag(hdev, HCI_SSP_ENABLED);
 		if (!changed)
-			changed = test_and_clear_bit(HCI_HS_ENABLED,
-						     &hdev->dev_flags);
+			changed = hci_dev_test_and_clear_flag(hdev,
+							      HCI_HS_ENABLED);
 		else
-			clear_bit(HCI_HS_ENABLED, &hdev->dev_flags);
+			hci_dev_clear_flag(hdev, HCI_HS_ENABLED);
 	}
 
 	mgmt_pending_foreach(MGMT_OP_SET_SSP, hdev, settings_rsp, &match);
@@ -6589,8 +8081,8 @@ void mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status)
 
 	hci_req_init(&req, hdev);
 
-	if (test_bit(HCI_SSP_ENABLED, &hdev->dev_flags)) {
-		if (test_bit(HCI_USE_DEBUG_KEYS, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) {
+		if (hci_dev_test_flag(hdev, HCI_USE_DEBUG_KEYS))
 			hci_req_add(&req, HCI_OP_WRITE_SSP_DEBUG_MODE,
 				    sizeof(enable), &enable);
 		update_eir(&req);
@@ -6601,44 +8093,7 @@ 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)
+static void sk_lookup(struct mgmt_pending_cmd *cmd, void *data)
 {
 	struct cmd_lookup *match = data;
 
@@ -6658,8 +8113,8 @@ void mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class,
 	mgmt_pending_foreach(MGMT_OP_REMOVE_UUID, hdev, sk_lookup, &match);
 
 	if (!status)
-		mgmt_event(MGMT_EV_CLASS_OF_DEV_CHANGED, hdev, dev_class, 3,
-			   NULL);
+		mgmt_generic_event(MGMT_EV_CLASS_OF_DEV_CHANGED, hdev,
+				   dev_class, 3, NULL);
 
 	if (match.sk)
 		sock_put(match.sk);
@@ -6668,7 +8123,7 @@ void mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class,
 void mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status)
 {
 	struct mgmt_cp_set_local_name ev;
-	struct pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd;
 
 	if (status)
 		return;
@@ -6677,66 +8132,146 @@ void mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status)
 	memcpy(ev.name, name, HCI_MAX_NAME_LENGTH);
 	memcpy(ev.short_name, hdev->short_name, HCI_MAX_SHORT_NAME_LENGTH);
 
-	cmd = mgmt_pending_find(MGMT_OP_SET_LOCAL_NAME, hdev);
+	cmd = pending_find(MGMT_OP_SET_LOCAL_NAME, hdev);
 	if (!cmd) {
 		memcpy(hdev->dev_name, name, sizeof(hdev->dev_name));
 
 		/* If this is a HCI command related to powering on the
 		 * HCI dev don't send any mgmt signals.
 		 */
-		if (mgmt_pending_find(MGMT_OP_SET_POWERED, hdev))
+		if (pending_find(MGMT_OP_SET_POWERED, hdev))
 			return;
 	}
 
-	mgmt_event(MGMT_EV_LOCAL_NAME_CHANGED, hdev, &ev, sizeof(ev),
-		   cmd ? cmd->sk : NULL);
+	mgmt_generic_event(MGMT_EV_LOCAL_NAME_CHANGED, hdev, &ev, sizeof(ev),
+			   cmd ? cmd->sk : NULL);
 }
 
-void mgmt_read_local_oob_data_complete(struct hci_dev *hdev, u8 *hash192,
-				       u8 *randomizer192, u8 *hash256,
-				       u8 *randomizer256, u8 status)
+static inline bool has_uuid(u8 *uuid, u16 uuid_count, u8 (*uuids)[16])
 {
-	struct pending_cmd *cmd;
-
-	BT_DBG("%s status %u", hdev->name, status);
+	int i;
 
-	cmd = mgmt_pending_find(MGMT_OP_READ_LOCAL_OOB_DATA, hdev);
-	if (!cmd)
-		return;
+	for (i = 0; i < uuid_count; i++) {
+		if (!memcmp(uuid, uuids[i], 16))
+			return true;
+	}
 
-	if (status) {
-		cmd_status(cmd->sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA,
-			   mgmt_status(status));
-	} else {
-		if (test_bit(HCI_SC_ENABLED, &hdev->dev_flags) &&
-		    hash256 && randomizer256) {
-			struct mgmt_rp_read_local_oob_ext_data rp;
+	return false;
+}
 
-			memcpy(rp.hash192, hash192, sizeof(rp.hash192));
-			memcpy(rp.randomizer192, randomizer192,
-			       sizeof(rp.randomizer192));
+static bool eir_has_uuids(u8 *eir, u16 eir_len, u16 uuid_count, u8 (*uuids)[16])
+{
+	u16 parsed = 0;
 
-			memcpy(rp.hash256, hash256, sizeof(rp.hash256));
-			memcpy(rp.randomizer256, randomizer256,
-			       sizeof(rp.randomizer256));
+	while (parsed < eir_len) {
+		u8 field_len = eir[0];
+		u8 uuid[16];
+		int i;
 
-			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;
+		if (field_len == 0)
+			break;
 
-			memcpy(rp.hash, hash192, sizeof(rp.hash));
-			memcpy(rp.randomizer, randomizer192,
-			       sizeof(rp.randomizer));
+		if (eir_len - parsed < field_len + 1)
+			break;
 
-			cmd_complete(cmd->sk, hdev->id,
-				     MGMT_OP_READ_LOCAL_OOB_DATA, 0,
-				     &rp, sizeof(rp));
+		switch (eir[1]) {
+		case EIR_UUID16_ALL:
+		case EIR_UUID16_SOME:
+			for (i = 0; i + 3 <= field_len; i += 2) {
+				memcpy(uuid, bluetooth_base_uuid, 16);
+				uuid[13] = eir[i + 3];
+				uuid[12] = eir[i + 2];
+				if (has_uuid(uuid, uuid_count, uuids))
+					return true;
+			}
+			break;
+		case EIR_UUID32_ALL:
+		case EIR_UUID32_SOME:
+			for (i = 0; i + 5 <= field_len; i += 4) {
+				memcpy(uuid, bluetooth_base_uuid, 16);
+				uuid[15] = eir[i + 5];
+				uuid[14] = eir[i + 4];
+				uuid[13] = eir[i + 3];
+				uuid[12] = eir[i + 2];
+				if (has_uuid(uuid, uuid_count, uuids))
+					return true;
+			}
+			break;
+		case EIR_UUID128_ALL:
+		case EIR_UUID128_SOME:
+			for (i = 0; i + 17 <= field_len; i += 16) {
+				memcpy(uuid, eir + i + 2, 16);
+				if (has_uuid(uuid, uuid_count, uuids))
+					return true;
+			}
+			break;
 		}
+
+		parsed += field_len + 1;
+		eir += field_len + 1;
 	}
 
-	mgmt_pending_remove(cmd);
+	return false;
+}
+
+static void restart_le_scan(struct hci_dev *hdev)
+{
+	/* If controller is not scanning we are done. */
+	if (!hci_dev_test_flag(hdev, HCI_LE_SCAN))
+		return;
+
+	if (time_after(jiffies + DISCOV_LE_RESTART_DELAY,
+		       hdev->discovery.scan_start +
+		       hdev->discovery.scan_duration))
+		return;
+
+	queue_delayed_work(hdev->workqueue, &hdev->le_scan_restart,
+			   DISCOV_LE_RESTART_DELAY);
+}
+
+static bool is_filter_match(struct hci_dev *hdev, s8 rssi, u8 *eir,
+			    u16 eir_len, u8 *scan_rsp, u8 scan_rsp_len)
+{
+	/* If a RSSI threshold has been specified, and
+	 * HCI_QUIRK_STRICT_DUPLICATE_FILTER is not set, then all results with
+	 * a RSSI smaller than the RSSI threshold will be dropped. If the quirk
+	 * is set, let it through for further processing, as we might need to
+	 * restart the scan.
+	 *
+	 * For BR/EDR devices (pre 1.2) providing no RSSI during inquiry,
+	 * the results are also dropped.
+	 */
+	if (hdev->discovery.rssi != HCI_RSSI_INVALID &&
+	    (rssi == HCI_RSSI_INVALID ||
+	    (rssi < hdev->discovery.rssi &&
+	     !test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks))))
+		return  false;
+
+	if (hdev->discovery.uuid_count != 0) {
+		/* If a list of UUIDs is provided in filter, results with no
+		 * matching UUID should be dropped.
+		 */
+		if (!eir_has_uuids(eir, eir_len, hdev->discovery.uuid_count,
+				   hdev->discovery.uuids) &&
+		    !eir_has_uuids(scan_rsp, scan_rsp_len,
+				   hdev->discovery.uuid_count,
+				   hdev->discovery.uuids))
+			return false;
+	}
+
+	/* If duplicate filtering does not report RSSI changes, then restart
+	 * scanning to ensure updated result with updated RSSI values.
+	 */
+	if (test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks)) {
+		restart_le_scan(hdev);
+
+		/* Validate RSSI value against the RSSI threshold once more. */
+		if (hdev->discovery.rssi != HCI_RSSI_INVALID &&
+		    rssi < hdev->discovery.rssi)
+			return false;
+	}
+
+	return true;
 }
 
 void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
@@ -6744,7 +8279,7 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 		       u8 *eir, u16 eir_len, u8 *scan_rsp, u8 scan_rsp_len)
 {
 	char buf[512];
-	struct mgmt_ev_device_found *ev = (void *) buf;
+	struct mgmt_ev_device_found *ev = (void *)buf;
 	size_t ev_size;
 
 	/* Don't send events for a non-kernel initiated discovery. With
@@ -6758,6 +8293,13 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 			return;
 	}
 
+	if (hdev->discovery.result_filtering) {
+		/* We are using service discovery */
+		if (!is_filter_match(hdev, rssi, eir, eir_len, scan_rsp,
+				     scan_rsp_len))
+			return;
+	}
+
 	/* Make sure that the buffer is big enough. The 5 extra bytes
 	 * are for the potential CoD field.
 	 */
@@ -6766,12 +8308,25 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 
 	memset(buf, 0, sizeof(buf));
 
+	/* In case of device discovery with BR/EDR devices (pre 1.2), the
+	 * RSSI value was reported as 0 when not available. This behavior
+	 * is kept when using device discovery. This is required for full
+	 * backwards compatibility with the API.
+	 *
+	 * However when using service discovery, the value 127 will be
+	 * returned when the RSSI is not available.
+	 */
+	if (rssi == HCI_RSSI_INVALID && !hdev->discovery.report_invalid_rssi &&
+	    link_type == ACL_LINK)
+		rssi = 0;
+
 	bacpy(&ev->addr.bdaddr, bdaddr);
 	ev->addr.type = link_to_bdaddr(link_type, addr_type);
 	ev->rssi = rssi;
 	ev->flags = cpu_to_le32(flags);
 
 	if (eir_len > 0)
+		/* Copy EIR or advertising data into event */
 		memcpy(ev->eir, eir, eir_len);
 
 	if (dev_class && !eir_has_data_type(ev->eir, eir_len, EIR_CLASS_OF_DEV))
@@ -6779,6 +8334,7 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 					  dev_class, 3);
 
 	if (scan_rsp_len > 0)
+		/* Append scan response data to event */
 		memcpy(ev->eir + eir_len, scan_rsp, scan_rsp_len);
 
 	ev->eir_len = cpu_to_le16(eir_len + scan_rsp_len);
@@ -6813,23 +8369,9 @@ void mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 void mgmt_discovering(struct hci_dev *hdev, u8 discovering)
 {
 	struct mgmt_ev_discovering ev;
-	struct pending_cmd *cmd;
 
 	BT_DBG("%s discovering %u", hdev->name, discovering);
 
-	if (discovering)
-		cmd = mgmt_pending_find(MGMT_OP_START_DISCOVERY, hdev);
-	else
-		cmd = mgmt_pending_find(MGMT_OP_STOP_DISCOVERY, hdev);
-
-	if (cmd != NULL) {
-		u8 type = hdev->discovery.type;
-
-		cmd_complete(cmd->sk, hdev->id, cmd->opcode, 0, &type,
-			     sizeof(type));
-		mgmt_pending_remove(cmd);
-	}
-
 	memset(&ev, 0, sizeof(ev));
 	ev.type = hdev->discovery.type;
 	ev.discovering = discovering;
@@ -6837,7 +8379,7 @@ void mgmt_discovering(struct hci_dev *hdev, u8 discovering)
 	mgmt_event(MGMT_EV_DISCOVERING, hdev, &ev, sizeof(ev), NULL);
 }
 
-static void adv_enable_complete(struct hci_dev *hdev, u8 status)
+static void adv_enable_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
 	BT_DBG("%s status %u", hdev->name, status);
 }
@@ -6846,10 +8388,28 @@ void mgmt_reenable_advertising(struct hci_dev *hdev)
 {
 	struct hci_request req;
 
-	if (!test_bit(HCI_ADVERTISING, &hdev->dev_flags))
+	if (!hci_dev_test_flag(hdev, HCI_ADVERTISING) &&
+	    !hci_dev_test_flag(hdev, HCI_ADVERTISING_INSTANCE))
 		return;
 
 	hci_req_init(&req, hdev);
 	enable_advertising(&req);
 	hci_req_run(&req, adv_enable_complete);
 }
+
+static struct hci_mgmt_chan chan = {
+	.channel	= HCI_CHANNEL_CONTROL,
+	.handler_count	= ARRAY_SIZE(mgmt_handlers),
+	.handlers	= mgmt_handlers,
+	.hdev_init	= mgmt_init_hdev,
+};
+
+int mgmt_init(void)
+{
+	return hci_mgmt_chan_register(&chan);
+}
+
+void mgmt_exit(void)
+{
+	hci_mgmt_chan_unregister(&chan);
+}
diff --git a/net/bluetooth/mgmt_util.c b/net/bluetooth/mgmt_util.c
new file mode 100644
index 000000000000..8c30c7eb8bef
--- /dev/null
+++ b/net/bluetooth/mgmt_util.c
@@ -0,0 +1,210 @@
+/*
+   BlueZ - Bluetooth protocol stack for Linux
+
+   Copyright (C) 2015  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;
+
+   THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+   OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+   FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS.
+   IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY
+   CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES
+   WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+   ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+   OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+
+   ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS,
+   COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS
+   SOFTWARE IS DISCLAIMED.
+*/
+
+#include <net/bluetooth/bluetooth.h>
+#include <net/bluetooth/hci_core.h>
+#include <net/bluetooth/mgmt.h>
+
+#include "mgmt_util.h"
+
+int mgmt_send_event(u16 event, struct hci_dev *hdev, unsigned short channel,
+		    void *data, u16 data_len, int flag, struct sock *skip_sk)
+{
+	struct sk_buff *skb;
+	struct mgmt_hdr *hdr;
+
+	skb = alloc_skb(sizeof(*hdr) + data_len, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	hdr = (void *) skb_put(skb, sizeof(*hdr));
+	hdr->opcode = cpu_to_le16(event);
+	if (hdev)
+		hdr->index = cpu_to_le16(hdev->id);
+	else
+		hdr->index = cpu_to_le16(MGMT_INDEX_NONE);
+	hdr->len = cpu_to_le16(data_len);
+
+	if (data)
+		memcpy(skb_put(skb, data_len), data, data_len);
+
+	/* Time stamp */
+	__net_timestamp(skb);
+
+	hci_send_to_channel(channel, skb, flag, skip_sk);
+	kfree_skb(skb);
+
+	return 0;
+}
+
+int mgmt_cmd_status(struct sock *sk, u16 index, u16 cmd, u8 status)
+{
+	struct sk_buff *skb;
+	struct mgmt_hdr *hdr;
+	struct mgmt_ev_cmd_status *ev;
+	int err;
+
+	BT_DBG("sock %p, index %u, cmd %u, status %u", sk, index, cmd, status);
+
+	skb = alloc_skb(sizeof(*hdr) + sizeof(*ev), GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	hdr = (void *) skb_put(skb, sizeof(*hdr));
+
+	hdr->opcode = cpu_to_le16(MGMT_EV_CMD_STATUS);
+	hdr->index = cpu_to_le16(index);
+	hdr->len = cpu_to_le16(sizeof(*ev));
+
+	ev = (void *) skb_put(skb, sizeof(*ev));
+	ev->status = status;
+	ev->opcode = cpu_to_le16(cmd);
+
+	err = sock_queue_rcv_skb(sk, skb);
+	if (err < 0)
+		kfree_skb(skb);
+
+	return err;
+}
+
+int mgmt_cmd_complete(struct sock *sk, u16 index, u16 cmd, u8 status,
+		      void *rp, size_t rp_len)
+{
+	struct sk_buff *skb;
+	struct mgmt_hdr *hdr;
+	struct mgmt_ev_cmd_complete *ev;
+	int err;
+
+	BT_DBG("sock %p", sk);
+
+	skb = alloc_skb(sizeof(*hdr) + sizeof(*ev) + rp_len, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	hdr = (void *) skb_put(skb, sizeof(*hdr));
+
+	hdr->opcode = cpu_to_le16(MGMT_EV_CMD_COMPLETE);
+	hdr->index = cpu_to_le16(index);
+	hdr->len = cpu_to_le16(sizeof(*ev) + rp_len);
+
+	ev = (void *) skb_put(skb, sizeof(*ev) + rp_len);
+	ev->opcode = cpu_to_le16(cmd);
+	ev->status = status;
+
+	if (rp)
+		memcpy(ev->data, rp, rp_len);
+
+	err = sock_queue_rcv_skb(sk, skb);
+	if (err < 0)
+		kfree_skb(skb);
+
+	return err;
+}
+
+struct mgmt_pending_cmd *mgmt_pending_find(unsigned short channel, u16 opcode,
+					   struct hci_dev *hdev)
+{
+	struct mgmt_pending_cmd *cmd;
+
+	list_for_each_entry(cmd, &hdev->mgmt_pending, list) {
+		if (hci_sock_get_channel(cmd->sk) != channel)
+			continue;
+		if (cmd->opcode == opcode)
+			return cmd;
+	}
+
+	return NULL;
+}
+
+struct mgmt_pending_cmd *mgmt_pending_find_data(unsigned short channel,
+						u16 opcode,
+						struct hci_dev *hdev,
+						const void *data)
+{
+	struct mgmt_pending_cmd *cmd;
+
+	list_for_each_entry(cmd, &hdev->mgmt_pending, list) {
+		if (cmd->user_data != data)
+			continue;
+		if (cmd->opcode == opcode)
+			return cmd;
+	}
+
+	return NULL;
+}
+
+void mgmt_pending_foreach(u16 opcode, struct hci_dev *hdev,
+			  void (*cb)(struct mgmt_pending_cmd *cmd, void *data),
+			  void *data)
+{
+	struct mgmt_pending_cmd *cmd, *tmp;
+
+	list_for_each_entry_safe(cmd, tmp, &hdev->mgmt_pending, list) {
+		if (opcode > 0 && cmd->opcode != opcode)
+			continue;
+
+		cb(cmd, data);
+	}
+}
+
+struct mgmt_pending_cmd *mgmt_pending_add(struct sock *sk, u16 opcode,
+					  struct hci_dev *hdev,
+					  void *data, u16 len)
+{
+	struct mgmt_pending_cmd *cmd;
+
+	cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
+	if (!cmd)
+		return NULL;
+
+	cmd->opcode = opcode;
+	cmd->index = hdev->id;
+
+	cmd->param = kmemdup(data, len, GFP_KERNEL);
+	if (!cmd->param) {
+		kfree(cmd);
+		return NULL;
+	}
+
+	cmd->param_len = len;
+
+	cmd->sk = sk;
+	sock_hold(sk);
+
+	list_add(&cmd->list, &hdev->mgmt_pending);
+
+	return cmd;
+}
+
+void mgmt_pending_free(struct mgmt_pending_cmd *cmd)
+{
+	sock_put(cmd->sk);
+	kfree(cmd->param);
+	kfree(cmd);
+}
+
+void mgmt_pending_remove(struct mgmt_pending_cmd *cmd)
+{
+	list_del(&cmd->list);
+	mgmt_pending_free(cmd);
+}
diff --git a/net/bluetooth/mgmt_util.h b/net/bluetooth/mgmt_util.h
new file mode 100644
index 000000000000..6559f189213c
--- /dev/null
+++ b/net/bluetooth/mgmt_util.h
@@ -0,0 +1,53 @@
+/*
+   BlueZ - Bluetooth protocol stack for Linux
+   Copyright (C) 2015  Intel Coropration
+
+   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;
+
+   THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+   OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+   FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS.
+   IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY
+   CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES
+   WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+   ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+   OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+
+   ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS,
+   COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS
+   SOFTWARE IS DISCLAIMED.
+*/
+
+struct mgmt_pending_cmd {
+	struct list_head list;
+	u16 opcode;
+	int index;
+	void *param;
+	size_t param_len;
+	struct sock *sk;
+	void *user_data;
+	int (*cmd_complete)(struct mgmt_pending_cmd *cmd, u8 status);
+};
+
+int mgmt_send_event(u16 event, struct hci_dev *hdev, unsigned short channel,
+		    void *data, u16 data_len, int flag, struct sock *skip_sk);
+int mgmt_cmd_status(struct sock *sk, u16 index, u16 cmd, u8 status);
+int mgmt_cmd_complete(struct sock *sk, u16 index, u16 cmd, u8 status,
+		      void *rp, size_t rp_len);
+
+struct mgmt_pending_cmd *mgmt_pending_find(unsigned short channel, u16 opcode,
+					   struct hci_dev *hdev);
+struct mgmt_pending_cmd *mgmt_pending_find_data(unsigned short channel,
+						u16 opcode,
+						struct hci_dev *hdev,
+						const void *data);
+void mgmt_pending_foreach(u16 opcode, struct hci_dev *hdev,
+			  void (*cb)(struct mgmt_pending_cmd *cmd, void *data),
+			  void *data);
+struct mgmt_pending_cmd *mgmt_pending_add(struct sock *sk, u16 opcode,
+					  struct hci_dev *hdev,
+					  void *data, u16 len);
+void mgmt_pending_free(struct mgmt_pending_cmd *cmd);
+void mgmt_pending_remove(struct mgmt_pending_cmd *cmd);
diff --git a/net/bluetooth/rfcomm/Kconfig b/net/bluetooth/rfcomm/Kconfig
index 18d352ea2bc7..335df7515220 100644
--- a/net/bluetooth/rfcomm/Kconfig
+++ b/net/bluetooth/rfcomm/Kconfig
@@ -1,6 +1,6 @@
 config BT_RFCOMM
 	tristate "RFCOMM protocol support"
-	depends on BT
+	depends on BT_BREDR
 	help
 	  RFCOMM provides connection oriented stream transport.  RFCOMM
 	  support is required for Dialup Networking, OBEX and other Bluetooth
diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c
index af73bc3acb40..4fea24275b17 100644
--- a/net/bluetooth/rfcomm/core.c
+++ b/net/bluetooth/rfcomm/core.c
@@ -78,8 +78,10 @@ static struct rfcomm_session *rfcomm_session_del(struct rfcomm_session *s);
 #define __get_type(b)     ((b & 0xef))
 
 #define __test_ea(b)      ((b & 0x01))
-#define __test_cr(b)      ((b & 0x02))
-#define __test_pf(b)      ((b & 0x10))
+#define __test_cr(b)      (!!(b & 0x02))
+#define __test_pf(b)      (!!(b & 0x10))
+
+#define __session_dir(s)  ((s)->initiator ? 0x00 : 0x01)
 
 #define __addr(cr, dlci)       (((dlci & 0x3f) << 2) | (cr << 1) | 0x01)
 #define __ctrl(type, pf)       (((type & 0xef) | (pf << 4)))
@@ -101,11 +103,11 @@ static struct rfcomm_session *rfcomm_session_del(struct rfcomm_session *s);
 #define __get_rpn_stop_bits(line) (((line) >> 2) & 0x1)
 #define __get_rpn_parity(line)    (((line) >> 3) & 0x7)
 
+static DECLARE_WAIT_QUEUE_HEAD(rfcomm_wq);
+
 static void rfcomm_schedule(void)
 {
-	if (!rfcomm_thread)
-		return;
-	wake_up_process(rfcomm_thread);
+	wake_up_all(&rfcomm_wq);
 }
 
 /* ---- RFCOMM FCS computation ---- */
@@ -388,7 +390,7 @@ static int __rfcomm_dlc_open(struct rfcomm_dlc *d, bdaddr_t *src, bdaddr_t *dst,
 			return err;
 	}
 
-	dlci = __dlci(!s->initiator, channel);
+	dlci = __dlci(__session_dir(s), channel);
 
 	/* Check if DLCI already exists */
 	if (rfcomm_dlc_get(s, dlci))
@@ -543,7 +545,7 @@ struct rfcomm_dlc *rfcomm_dlc_exists(bdaddr_t *src, bdaddr_t *dst, u8 channel)
 	rfcomm_lock();
 	s = rfcomm_session_get(src, dst);
 	if (s) {
-		dlci = __dlci(!s->initiator, channel);
+		dlci = __dlci(__session_dir(s), channel);
 		dlc = rfcomm_dlc_get(s, dlci);
 	}
 	rfcomm_unlock();
@@ -769,7 +771,7 @@ static struct rfcomm_session *rfcomm_session_create(bdaddr_t *src,
 
 	bacpy(&addr.l2_bdaddr, dst);
 	addr.l2_family = AF_BLUETOOTH;
-	addr.l2_psm    = cpu_to_le16(RFCOMM_PSM);
+	addr.l2_psm    = cpu_to_le16(L2CAP_PSM_RFCOMM);
 	addr.l2_cid    = 0;
 	addr.l2_bdaddr_type = BDADDR_BREDR;
 	*err = kernel_connect(sock, (struct sockaddr *) &addr, sizeof(addr), O_NONBLOCK);
@@ -904,7 +906,7 @@ static int rfcomm_send_nsc(struct rfcomm_session *s, int cr, u8 type)
 	hdr->len  = __len8(sizeof(*mcc) + 1);
 
 	mcc = (void *) ptr; ptr += sizeof(*mcc);
-	mcc->type = __mcc_type(cr, RFCOMM_NSC);
+	mcc->type = __mcc_type(0, RFCOMM_NSC);
 	mcc->len  = __len8(1);
 
 	/* Type that we didn't like */
@@ -2036,7 +2038,7 @@ static int rfcomm_add_listener(bdaddr_t *ba)
 	/* Bind socket */
 	bacpy(&addr.l2_bdaddr, ba);
 	addr.l2_family = AF_BLUETOOTH;
-	addr.l2_psm    = cpu_to_le16(RFCOMM_PSM);
+	addr.l2_psm    = cpu_to_le16(L2CAP_PSM_RFCOMM);
 	addr.l2_cid    = 0;
 	addr.l2_bdaddr_type = BDADDR_BREDR;
 	err = kernel_bind(sock, (struct sockaddr *) &addr, sizeof(addr));
@@ -2086,24 +2088,22 @@ static void rfcomm_kill_listener(void)
 
 static int rfcomm_run(void *unused)
 {
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 	BT_DBG("");
 
 	set_user_nice(current, -10);
 
 	rfcomm_add_listener(BDADDR_ANY);
 
-	while (1) {
-		set_current_state(TASK_INTERRUPTIBLE);
-
-		if (kthread_should_stop())
-			break;
+	add_wait_queue(&rfcomm_wq, &wait);
+	while (!kthread_should_stop()) {
 
 		/* Process stuff */
 		rfcomm_process_sessions();
 
-		schedule();
+		wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
 	}
-	__set_current_state(TASK_RUNNING);
+	remove_wait_queue(&rfcomm_wq, &wait);
 
 	rfcomm_kill_listener();
 
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 8bbbb5ec468c..825e8fb5114b 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -468,7 +468,7 @@ done:
 
 static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int flags)
 {
-	DECLARE_WAITQUEUE(wait, current);
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 	struct sock *sk = sock->sk, *nsk;
 	long timeo;
 	int err = 0;
@@ -487,8 +487,6 @@ static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int f
 	/* Wait for an incoming connection. (wake-one). */
 	add_wait_queue_exclusive(sk_sleep(sk), &wait);
 	while (1) {
-		set_current_state(TASK_INTERRUPTIBLE);
-
 		if (sk->sk_state != BT_LISTEN) {
 			err = -EBADFD;
 			break;
@@ -509,10 +507,11 @@ static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int f
 		}
 
 		release_sock(sk);
-		timeo = schedule_timeout(timeo);
+
+		timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo);
+
 		lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
 	}
-	__set_current_state(TASK_RUNNING);
 	remove_wait_queue(sk_sleep(sk), &wait);
 
 	if (err)
@@ -550,8 +549,8 @@ static int rfcomm_sock_getname(struct socket *sock, struct sockaddr *addr, int *
 	return 0;
 }
 
-static int rfcomm_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
-			       struct msghdr *msg, size_t len)
+static int rfcomm_sock_sendmsg(struct socket *sock, struct msghdr *msg,
+			       size_t len)
 {
 	struct sock *sk = sock->sk;
 	struct rfcomm_dlc *d = rfcomm_pi(sk)->dlc;
@@ -588,7 +587,7 @@ static int rfcomm_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 		}
 		skb_reserve(skb, RFCOMM_SKB_HEAD_RESERVE);
 
-		err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size);
+		err = memcpy_from_msg(skb_put(skb, size), msg, size);
 		if (err) {
 			kfree_skb(skb);
 			if (sent == 0)
@@ -616,8 +615,8 @@ done:
 	return sent;
 }
 
-static int rfcomm_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
-			       struct msghdr *msg, size_t size, int flags)
+static int rfcomm_sock_recvmsg(struct socket *sock, struct msghdr *msg,
+			       size_t size, int flags)
 {
 	struct sock *sk = sock->sk;
 	struct rfcomm_dlc *d = rfcomm_pi(sk)->dlc;
@@ -628,7 +627,7 @@ static int rfcomm_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 		return 0;
 	}
 
-	len = bt_sock_stream_recvmsg(iocb, sock, msg, size, flags);
+	len = bt_sock_stream_recvmsg(sock, msg, size, flags);
 
 	lock_sock(sk);
 	if (!(flags & MSG_PEEK) && len > 0)
@@ -1058,6 +1057,8 @@ int __init rfcomm_init_sockets(void)
 {
 	int err;
 
+	BUILD_BUG_ON(sizeof(struct sockaddr_rc) > sizeof(struct sockaddr));
+
 	err = proto_register(&rfcomm_proto, 0);
 	if (err < 0)
 		return err;
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 7ee9e4ab00f8..4322c833e748 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -285,7 +285,7 @@ static int sco_send_frame(struct sock *sk, struct msghdr *msg, int len)
 	if (!skb)
 		return err;
 
-	if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) {
+	if (memcpy_from_msg(skb_put(skb, len), msg, len)) {
 		kfree_skb(skb);
 		return -EFAULT;
 	}
@@ -618,7 +618,7 @@ done:
 
 static int sco_sock_accept(struct socket *sock, struct socket *newsock, int flags)
 {
-	DECLARE_WAITQUEUE(wait, current);
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 	struct sock *sk = sock->sk, *ch;
 	long timeo;
 	int err = 0;
@@ -632,8 +632,6 @@ static int sco_sock_accept(struct socket *sock, struct socket *newsock, int flag
 	/* Wait for an incoming connection. (wake-one). */
 	add_wait_queue_exclusive(sk_sleep(sk), &wait);
 	while (1) {
-		set_current_state(TASK_INTERRUPTIBLE);
-
 		if (sk->sk_state != BT_LISTEN) {
 			err = -EBADFD;
 			break;
@@ -654,10 +652,10 @@ static int sco_sock_accept(struct socket *sock, struct socket *newsock, int flag
 		}
 
 		release_sock(sk);
-		timeo = schedule_timeout(timeo);
+
+		timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo);
 		lock_sock(sk);
 	}
-	__set_current_state(TASK_RUNNING);
 	remove_wait_queue(sk_sleep(sk), &wait);
 
 	if (err)
@@ -690,8 +688,8 @@ static int sco_sock_getname(struct socket *sock, struct sockaddr *addr, int *len
 	return 0;
 }
 
-static int sco_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
-			    struct msghdr *msg, size_t len)
+static int sco_sock_sendmsg(struct socket *sock, struct msghdr *msg,
+			    size_t len)
 {
 	struct sock *sk = sock->sk;
 	int err;
@@ -760,8 +758,8 @@ static void sco_conn_defer_accept(struct hci_conn *conn, u16 setting)
 	}
 }
 
-static int sco_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
-			    struct msghdr *msg, size_t len, int flags)
+static int sco_sock_recvmsg(struct socket *sock, struct msghdr *msg,
+			    size_t len, int flags)
 {
 	struct sock *sk = sock->sk;
 	struct sco_pinfo *pi = sco_pi(sk);
@@ -779,7 +777,7 @@ static int sco_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 	release_sock(sk);
 
-	return bt_sock_recvmsg(iocb, sock, msg, len, flags);
+	return bt_sock_recvmsg(sock, msg, len, flags);
 }
 
 static int sco_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen)
@@ -1085,9 +1083,13 @@ int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags)
 	return lm;
 }
 
-void sco_connect_cfm(struct hci_conn *hcon, __u8 status)
+static void sco_connect_cfm(struct hci_conn *hcon, __u8 status)
 {
+	if (hcon->type != SCO_LINK && hcon->type != ESCO_LINK)
+		return;
+
 	BT_DBG("hcon %p bdaddr %pMR status %d", hcon, &hcon->dst, status);
+
 	if (!status) {
 		struct sco_conn *conn;
 
@@ -1098,8 +1100,11 @@ void sco_connect_cfm(struct hci_conn *hcon, __u8 status)
 		sco_conn_del(hcon, bt_to_errno(status));
 }
 
-void sco_disconn_cfm(struct hci_conn *hcon, __u8 reason)
+static void sco_disconn_cfm(struct hci_conn *hcon, __u8 reason)
 {
+	if (hcon->type != SCO_LINK && hcon->type != ESCO_LINK)
+		return;
+
 	BT_DBG("hcon %p reason %d", hcon, reason);
 
 	sco_conn_del(hcon, bt_to_errno(reason));
@@ -1124,6 +1129,12 @@ drop:
 	return 0;
 }
 
+static struct hci_cb sco_cb = {
+	.name		= "SCO",
+	.connect_cfm	= sco_connect_cfm,
+	.disconn_cfm	= sco_disconn_cfm,
+};
+
 static int sco_debugfs_show(struct seq_file *f, void *p)
 {
 	struct sock *sk;
@@ -1184,6 +1195,8 @@ int __init sco_init(void)
 {
 	int err;
 
+	BUILD_BUG_ON(sizeof(struct sockaddr_sco) > sizeof(struct sockaddr));
+
 	err = proto_register(&sco_proto, 0);
 	if (err < 0)
 		return err;
@@ -1203,6 +1216,8 @@ int __init sco_init(void)
 
 	BT_INFO("SCO socket layer initialized");
 
+	hci_register_cb(&sco_cb);
+
 	if (IS_ERR_OR_NULL(bt_debugfs))
 		return 0;
 
@@ -1216,12 +1231,14 @@ error:
 	return err;
 }
 
-void __exit sco_exit(void)
+void sco_exit(void)
 {
 	bt_procfs_cleanup(&init_net, "sco");
 
 	debugfs_remove(sco_debugfs);
 
+	hci_unregister_cb(&sco_cb);
+
 	bt_sock_unregister(BTPROTO_SCO);
 
 	proto_unregister(&sco_proto);
diff --git a/net/bluetooth/selftest.c b/net/bluetooth/selftest.c
new file mode 100644
index 000000000000..dc688f13e496
--- /dev/null
+++ b/net/bluetooth/selftest.c
@@ -0,0 +1,271 @@
+/*
+   BlueZ - Bluetooth protocol stack for Linux
+
+   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;
+
+   THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+   OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+   FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS.
+   IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY
+   CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES
+   WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+   ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+   OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+
+   ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS,
+   COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS
+   SOFTWARE IS DISCLAIMED.
+*/
+
+#include <linux/debugfs.h>
+
+#include <net/bluetooth/bluetooth.h>
+#include <net/bluetooth/hci_core.h>
+
+#include "ecc.h"
+#include "smp.h"
+#include "selftest.h"
+
+#if IS_ENABLED(CONFIG_BT_SELFTEST_ECDH)
+
+static const u8 priv_a_1[32] __initconst = {
+	0xbd, 0x1a, 0x3c, 0xcd, 0xa6, 0xb8, 0x99, 0x58,
+	0x99, 0xb7, 0x40, 0xeb, 0x7b, 0x60, 0xff, 0x4a,
+	0x50, 0x3f, 0x10, 0xd2, 0xe3, 0xb3, 0xc9, 0x74,
+	0x38, 0x5f, 0xc5, 0xa3, 0xd4, 0xf6, 0x49, 0x3f,
+};
+static const u8 priv_b_1[32] __initconst = {
+	0xfd, 0xc5, 0x7f, 0xf4, 0x49, 0xdd, 0x4f, 0x6b,
+	0xfb, 0x7c, 0x9d, 0xf1, 0xc2, 0x9a, 0xcb, 0x59,
+	0x2a, 0xe7, 0xd4, 0xee, 0xfb, 0xfc, 0x0a, 0x90,
+	0x9a, 0xbb, 0xf6, 0x32, 0x3d, 0x8b, 0x18, 0x55,
+};
+static const u8 pub_a_1[64] __initconst = {
+	0xe6, 0x9d, 0x35, 0x0e, 0x48, 0x01, 0x03, 0xcc,
+	0xdb, 0xfd, 0xf4, 0xac, 0x11, 0x91, 0xf4, 0xef,
+	0xb9, 0xa5, 0xf9, 0xe9, 0xa7, 0x83, 0x2c, 0x5e,
+	0x2c, 0xbe, 0x97, 0xf2, 0xd2, 0x03, 0xb0, 0x20,
+
+	0x8b, 0xd2, 0x89, 0x15, 0xd0, 0x8e, 0x1c, 0x74,
+	0x24, 0x30, 0xed, 0x8f, 0xc2, 0x45, 0x63, 0x76,
+	0x5c, 0x15, 0x52, 0x5a, 0xbf, 0x9a, 0x32, 0x63,
+	0x6d, 0xeb, 0x2a, 0x65, 0x49, 0x9c, 0x80, 0xdc,
+};
+static const u8 pub_b_1[64] __initconst = {
+	0x90, 0xa1, 0xaa, 0x2f, 0xb2, 0x77, 0x90, 0x55,
+	0x9f, 0xa6, 0x15, 0x86, 0xfd, 0x8a, 0xb5, 0x47,
+	0x00, 0x4c, 0x9e, 0xf1, 0x84, 0x22, 0x59, 0x09,
+	0x96, 0x1d, 0xaf, 0x1f, 0xf0, 0xf0, 0xa1, 0x1e,
+
+	0x4a, 0x21, 0xb1, 0x15, 0xf9, 0xaf, 0x89, 0x5f,
+	0x76, 0x36, 0x8e, 0xe2, 0x30, 0x11, 0x2d, 0x47,
+	0x60, 0x51, 0xb8, 0x9a, 0x3a, 0x70, 0x56, 0x73,
+	0x37, 0xad, 0x9d, 0x42, 0x3e, 0xf3, 0x55, 0x4c,
+};
+static const u8 dhkey_1[32] __initconst = {
+	0x98, 0xa6, 0xbf, 0x73, 0xf3, 0x34, 0x8d, 0x86,
+	0xf1, 0x66, 0xf8, 0xb4, 0x13, 0x6b, 0x79, 0x99,
+	0x9b, 0x7d, 0x39, 0x0a, 0xa6, 0x10, 0x10, 0x34,
+	0x05, 0xad, 0xc8, 0x57, 0xa3, 0x34, 0x02, 0xec,
+};
+
+static const u8 priv_a_2[32] __initconst = {
+	0x63, 0x76, 0x45, 0xd0, 0xf7, 0x73, 0xac, 0xb7,
+	0xff, 0xdd, 0x03, 0x72, 0xb9, 0x72, 0x85, 0xb4,
+	0x41, 0xb6, 0x5d, 0x0c, 0x5d, 0x54, 0x84, 0x60,
+	0x1a, 0xa3, 0x9a, 0x3c, 0x69, 0x16, 0xa5, 0x06,
+};
+static const u8 priv_b_2[32] __initconst = {
+	0xba, 0x30, 0x55, 0x50, 0x19, 0xa2, 0xca, 0xa3,
+	0xa5, 0x29, 0x08, 0xc6, 0xb5, 0x03, 0x88, 0x7e,
+	0x03, 0x2b, 0x50, 0x73, 0xd4, 0x2e, 0x50, 0x97,
+	0x64, 0xcd, 0x72, 0x0d, 0x67, 0xa0, 0x9a, 0x52,
+};
+static const u8 pub_a_2[64] __initconst = {
+	0xdd, 0x78, 0x5c, 0x74, 0x03, 0x9b, 0x7e, 0x98,
+	0xcb, 0x94, 0x87, 0x4a, 0xad, 0xfa, 0xf8, 0xd5,
+	0x43, 0x3e, 0x5c, 0xaf, 0xea, 0xb5, 0x4c, 0xf4,
+	0x9e, 0x80, 0x79, 0x57, 0x7b, 0xa4, 0x31, 0x2c,
+
+	0x4f, 0x5d, 0x71, 0x43, 0x77, 0x43, 0xf8, 0xea,
+	0xd4, 0x3e, 0xbd, 0x17, 0x91, 0x10, 0x21, 0xd0,
+	0x1f, 0x87, 0x43, 0x8e, 0x40, 0xe2, 0x52, 0xcd,
+	0xbe, 0xdf, 0x98, 0x38, 0x18, 0x12, 0x95, 0x91,
+};
+static const u8 pub_b_2[64] __initconst = {
+	0xcc, 0x00, 0x65, 0xe1, 0xf5, 0x6c, 0x0d, 0xcf,
+	0xec, 0x96, 0x47, 0x20, 0x66, 0xc9, 0xdb, 0x84,
+	0x81, 0x75, 0xa8, 0x4d, 0xc0, 0xdf, 0xc7, 0x9d,
+	0x1b, 0x3f, 0x3d, 0xf2, 0x3f, 0xe4, 0x65, 0xf4,
+
+	0x79, 0xb2, 0xec, 0xd8, 0xca, 0x55, 0xa1, 0xa8,
+	0x43, 0x4d, 0x6b, 0xca, 0x10, 0xb0, 0xc2, 0x01,
+	0xc2, 0x33, 0x4e, 0x16, 0x24, 0xc4, 0xef, 0xee,
+	0x99, 0xd8, 0xbb, 0xbc, 0x48, 0xd0, 0x01, 0x02,
+};
+static const u8 dhkey_2[32] __initconst = {
+	0x69, 0xeb, 0x21, 0x32, 0xf2, 0xc6, 0x05, 0x41,
+	0x60, 0x19, 0xcd, 0x5e, 0x94, 0xe1, 0xe6, 0x5f,
+	0x33, 0x07, 0xe3, 0x38, 0x4b, 0x68, 0xe5, 0x62,
+	0x3f, 0x88, 0x6d, 0x2f, 0x3a, 0x84, 0x85, 0xab,
+};
+
+static const u8 priv_a_3[32] __initconst = {
+	0xbd, 0x1a, 0x3c, 0xcd, 0xa6, 0xb8, 0x99, 0x58,
+	0x99, 0xb7, 0x40, 0xeb, 0x7b, 0x60, 0xff, 0x4a,
+	0x50, 0x3f, 0x10, 0xd2, 0xe3, 0xb3, 0xc9, 0x74,
+	0x38, 0x5f, 0xc5, 0xa3, 0xd4, 0xf6, 0x49, 0x3f,
+};
+static const u8 pub_a_3[64] __initconst = {
+	0xe6, 0x9d, 0x35, 0x0e, 0x48, 0x01, 0x03, 0xcc,
+	0xdb, 0xfd, 0xf4, 0xac, 0x11, 0x91, 0xf4, 0xef,
+	0xb9, 0xa5, 0xf9, 0xe9, 0xa7, 0x83, 0x2c, 0x5e,
+	0x2c, 0xbe, 0x97, 0xf2, 0xd2, 0x03, 0xb0, 0x20,
+
+	0x8b, 0xd2, 0x89, 0x15, 0xd0, 0x8e, 0x1c, 0x74,
+	0x24, 0x30, 0xed, 0x8f, 0xc2, 0x45, 0x63, 0x76,
+	0x5c, 0x15, 0x52, 0x5a, 0xbf, 0x9a, 0x32, 0x63,
+	0x6d, 0xeb, 0x2a, 0x65, 0x49, 0x9c, 0x80, 0xdc,
+};
+static const u8 dhkey_3[32] __initconst = {
+	0x2d, 0xab, 0x00, 0x48, 0xcb, 0xb3, 0x7b, 0xda,
+	0x55, 0x7b, 0x8b, 0x72, 0xa8, 0x57, 0x87, 0xc3,
+	0x87, 0x27, 0x99, 0x32, 0xfc, 0x79, 0x5f, 0xae,
+	0x7c, 0x1c, 0xf9, 0x49, 0xe6, 0xd7, 0xaa, 0x70,
+};
+
+static int __init test_ecdh_sample(const u8 priv_a[32], const u8 priv_b[32],
+				   const u8 pub_a[64], const u8 pub_b[64],
+				   const u8 dhkey[32])
+{
+	u8 dhkey_a[32], dhkey_b[32];
+
+	ecdh_shared_secret(pub_b, priv_a, dhkey_a);
+	ecdh_shared_secret(pub_a, priv_b, dhkey_b);
+
+	if (memcmp(dhkey_a, dhkey, 32))
+		return -EINVAL;
+
+	if (memcmp(dhkey_b, dhkey, 32))
+		return -EINVAL;
+
+	return 0;
+}
+
+static char test_ecdh_buffer[32];
+
+static ssize_t test_ecdh_read(struct file *file, char __user *user_buf,
+			      size_t count, loff_t *ppos)
+{
+	return simple_read_from_buffer(user_buf, count, ppos, test_ecdh_buffer,
+				       strlen(test_ecdh_buffer));
+}
+
+static const struct file_operations test_ecdh_fops = {
+	.open		= simple_open,
+	.read		= test_ecdh_read,
+	.llseek		= default_llseek,
+};
+
+static int __init test_ecdh(void)
+{
+	ktime_t calltime, delta, rettime;
+	unsigned long long duration;
+	int err;
+
+	calltime = ktime_get();
+
+	err = test_ecdh_sample(priv_a_1, priv_b_1, pub_a_1, pub_b_1, dhkey_1);
+	if (err) {
+		BT_ERR("ECDH sample 1 failed");
+		goto done;
+	}
+
+	err = test_ecdh_sample(priv_a_2, priv_b_2, pub_a_2, pub_b_2, dhkey_2);
+	if (err) {
+		BT_ERR("ECDH sample 2 failed");
+		goto done;
+	}
+
+	err = test_ecdh_sample(priv_a_3, priv_a_3, pub_a_3, pub_a_3, dhkey_3);
+	if (err) {
+		BT_ERR("ECDH sample 3 failed");
+		goto done;
+	}
+
+	rettime = ktime_get();
+	delta = ktime_sub(rettime, calltime);
+	duration = (unsigned long long) ktime_to_ns(delta) >> 10;
+
+	BT_INFO("ECDH test passed in %llu usecs", duration);
+
+done:
+	if (!err)
+		snprintf(test_ecdh_buffer, sizeof(test_ecdh_buffer),
+			 "PASS (%llu usecs)\n", duration);
+	else
+		snprintf(test_ecdh_buffer, sizeof(test_ecdh_buffer), "FAIL\n");
+
+	debugfs_create_file("selftest_ecdh", 0444, bt_debugfs, NULL,
+			    &test_ecdh_fops);
+
+	return err;
+}
+
+#else
+
+static inline int test_ecdh(void)
+{
+	return 0;
+}
+
+#endif
+
+static int __init run_selftest(void)
+{
+	int err;
+
+	BT_INFO("Starting self testing");
+
+	err = test_ecdh();
+	if (err)
+		goto done;
+
+	err = bt_selftest_smp();
+
+done:
+	BT_INFO("Finished self testing");
+
+	return err;
+}
+
+#if IS_MODULE(CONFIG_BT)
+
+/* This is run when CONFIG_BT_SELFTEST=y and CONFIG_BT=m and is just a
+ * wrapper to allow running this at module init.
+ *
+ * If CONFIG_BT_SELFTEST=n, then this code is not compiled at all.
+ */
+int __init bt_selftest(void)
+{
+	return run_selftest();
+}
+
+#else
+
+/* This is run when CONFIG_BT_SELFTEST=y and CONFIG_BT=y and is run
+ * via late_initcall() as last item in the initialization sequence.
+ *
+ * If CONFIG_BT_SELFTEST=n, then this code is not compiled at all.
+ */
+static int __init bt_selftest_init(void)
+{
+	return run_selftest();
+}
+late_initcall(bt_selftest_init);
+
+#endif
diff --git a/net/bluetooth/selftest.h b/net/bluetooth/selftest.h
new file mode 100644
index 000000000000..2aa0a346a913
--- /dev/null
+++ b/net/bluetooth/selftest.h
@@ -0,0 +1,45 @@
+/*
+   BlueZ - Bluetooth protocol stack for Linux
+   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;
+
+   THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+   OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+   FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS.
+   IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY
+   CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES
+   WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+   ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+   OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+
+   ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS,
+   COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS
+   SOFTWARE IS DISCLAIMED.
+*/
+
+#if IS_ENABLED(CONFIG_BT_SELFTEST) && IS_MODULE(CONFIG_BT)
+
+/* When CONFIG_BT_SELFTEST=y and the CONFIG_BT=m, then the self testing
+ * is run at module loading time.
+ */
+int bt_selftest(void);
+
+#else
+
+/* When CONFIG_BT_SELFTEST=y and CONFIG_BT=y, then the self testing
+ * is run via late_initcall() to make sure that subsys_initcall() of
+ * the Bluetooth subsystem and device_initcall() of the Crypto subsystem
+ * do not clash.
+ *
+ * When CONFIG_BT_SELFTEST=n, then this turns into an empty call that
+ * has no impact.
+ */
+static inline int bt_selftest(void)
+{
+	return 0;
+}
+
+#endif
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index f09b6b65cf6b..1ab3dc9c8f99 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -20,6 +20,7 @@
    SOFTWARE IS DISCLAIMED.
 */
 
+#include <linux/debugfs.h>
 #include <linux/crypto.h>
 #include <linux/scatterlist.h>
 #include <crypto/b128ops.h>
@@ -29,14 +30,34 @@
 #include <net/bluetooth/l2cap.h>
 #include <net/bluetooth/mgmt.h>
 
+#include "ecc.h"
 #include "smp.h"
 
+/* Low-level debug macros to be used for stuff that we don't want
+ * accidentially in dmesg, i.e. the values of the various crypto keys
+ * and the inputs & outputs of crypto functions.
+ */
+#ifdef DEBUG
+#define SMP_DBG(fmt, ...) printk(KERN_DEBUG "%s: " fmt, __func__, \
+				 ##__VA_ARGS__)
+#else
+#define SMP_DBG(fmt, ...) no_printk(KERN_DEBUG "%s: " fmt, __func__, \
+				    ##__VA_ARGS__)
+#endif
+
 #define SMP_ALLOW_CMD(smp, code)	set_bit(code, &smp->allow_cmd)
 
+/* Keys which are not distributed with Secure Connections */
+#define SMP_SC_NO_DIST (SMP_DIST_ENC_KEY | SMP_DIST_LINK_KEY);
+
 #define SMP_TIMEOUT	msecs_to_jiffies(30000)
 
-#define AUTH_REQ_MASK   0x07
-#define KEY_DIST_MASK	0x07
+#define AUTH_REQ_MASK(dev)	(hci_dev_test_flag(dev, HCI_SC_ENABLED) ? \
+				 0x1f : 0x07)
+#define KEY_DIST_MASK		0x07
+
+/* Maximum message length that can be passed to aes_cmac */
+#define CMAC_MSG_MAX	80
 
 enum {
 	SMP_FLAG_TK_VALID,
@@ -44,6 +65,24 @@ enum {
 	SMP_FLAG_MITM_AUTH,
 	SMP_FLAG_COMPLETE,
 	SMP_FLAG_INITIATOR,
+	SMP_FLAG_SC,
+	SMP_FLAG_REMOTE_PK,
+	SMP_FLAG_DEBUG_KEY,
+	SMP_FLAG_WAIT_USER,
+	SMP_FLAG_DHKEY_PENDING,
+	SMP_FLAG_REMOTE_OOB,
+	SMP_FLAG_LOCAL_OOB,
+};
+
+struct smp_dev {
+	/* Secure Connections OOB data */
+	u8			local_pk[64];
+	u8			local_sk[32];
+	u8			local_rand[16];
+	bool			debug_key;
+
+	struct crypto_blkcipher	*tfm_aes;
+	struct crypto_hash	*tfm_cmac;
 };
 
 struct smp_chan {
@@ -57,6 +96,8 @@ struct smp_chan {
 	u8		rrnd[16]; /* SMP Pairing Random (remote) */
 	u8		pcnf[16]; /* SMP Pairing Confirm */
 	u8		tk[16]; /* SMP Temporary Key */
+	u8		rr[16]; /* Remote OOB ra/rb value */
+	u8		lr[16]; /* Local OOB ra/rb value */
 	u8		enc_key_size;
 	u8		remote_key_dist;
 	bdaddr_t	id_addr;
@@ -67,9 +108,43 @@ struct smp_chan {
 	struct smp_ltk	*ltk;
 	struct smp_ltk	*slave_ltk;
 	struct smp_irk	*remote_irk;
+	u8		*link_key;
 	unsigned long	flags;
+	u8		method;
+	u8		passkey_round;
+
+	/* Secure Connections variables */
+	u8			local_pk[64];
+	u8			local_sk[32];
+	u8			remote_pk[64];
+	u8			dhkey[32];
+	u8			mackey[16];
 
 	struct crypto_blkcipher	*tfm_aes;
+	struct crypto_hash	*tfm_cmac;
+};
+
+/* These debug key values are defined in the SMP section of the core
+ * specification. debug_pk is the public debug key and debug_sk the
+ * private debug key.
+ */
+static const u8 debug_pk[64] = {
+		0xe6, 0x9d, 0x35, 0x0e, 0x48, 0x01, 0x03, 0xcc,
+		0xdb, 0xfd, 0xf4, 0xac, 0x11, 0x91, 0xf4, 0xef,
+		0xb9, 0xa5, 0xf9, 0xe9, 0xa7, 0x83, 0x2c, 0x5e,
+		0x2c, 0xbe, 0x97, 0xf2, 0xd2, 0x03, 0xb0, 0x20,
+
+		0x8b, 0xd2, 0x89, 0x15, 0xd0, 0x8e, 0x1c, 0x74,
+		0x24, 0x30, 0xed, 0x8f, 0xc2, 0x45, 0x63, 0x76,
+		0x5c, 0x15, 0x52, 0x5a, 0xbf, 0x9a, 0x32, 0x63,
+		0x6d, 0xeb, 0x2a, 0x65, 0x49, 0x9c, 0x80, 0xdc,
+};
+
+static const u8 debug_sk[32] = {
+		0xbd, 0x1a, 0x3c, 0xcd, 0xa6, 0xb8, 0x99, 0x58,
+		0x99, 0xb7, 0x40, 0xeb, 0x7b, 0x60, 0xff, 0x4a,
+		0x50, 0x3f, 0x10, 0xd2, 0xe3, 0xb3, 0xc9, 0x74,
+		0x38, 0x5f, 0xc5, 0xa3, 0xd4, 0xf6, 0x49, 0x3f,
 };
 
 static inline void swap_buf(const u8 *src, u8 *dst, size_t len)
@@ -80,6 +155,215 @@ static inline void swap_buf(const u8 *src, u8 *dst, size_t len)
 		dst[len - 1 - i] = src[i];
 }
 
+/* The following functions map to the LE SC SMP crypto functions
+ * AES-CMAC, f4, f5, f6, g2 and h6.
+ */
+
+static int aes_cmac(struct crypto_hash *tfm, const u8 k[16], const u8 *m,
+		    size_t len, u8 mac[16])
+{
+	uint8_t tmp[16], mac_msb[16], msg_msb[CMAC_MSG_MAX];
+	struct hash_desc desc;
+	struct scatterlist sg;
+	int err;
+
+	if (len > CMAC_MSG_MAX)
+		return -EFBIG;
+
+	if (!tfm) {
+		BT_ERR("tfm %p", tfm);
+		return -EINVAL;
+	}
+
+	desc.tfm = tfm;
+	desc.flags = 0;
+
+	crypto_hash_init(&desc);
+
+	/* Swap key and message from LSB to MSB */
+	swap_buf(k, tmp, 16);
+	swap_buf(m, msg_msb, len);
+
+	SMP_DBG("msg (len %zu) %*phN", len, (int) len, m);
+	SMP_DBG("key %16phN", k);
+
+	err = crypto_hash_setkey(tfm, tmp, 16);
+	if (err) {
+		BT_ERR("cipher setkey failed: %d", err);
+		return err;
+	}
+
+	sg_init_one(&sg, msg_msb, len);
+
+	err = crypto_hash_update(&desc, &sg, len);
+	if (err) {
+		BT_ERR("Hash update error %d", err);
+		return err;
+	}
+
+	err = crypto_hash_final(&desc, mac_msb);
+	if (err) {
+		BT_ERR("Hash final error %d", err);
+		return err;
+	}
+
+	swap_buf(mac_msb, mac, 16);
+
+	SMP_DBG("mac %16phN", mac);
+
+	return 0;
+}
+
+static int smp_f4(struct crypto_hash *tfm_cmac, const u8 u[32], const u8 v[32],
+		  const u8 x[16], u8 z, u8 res[16])
+{
+	u8 m[65];
+	int err;
+
+	SMP_DBG("u %32phN", u);
+	SMP_DBG("v %32phN", v);
+	SMP_DBG("x %16phN z %02x", x, z);
+
+	m[0] = z;
+	memcpy(m + 1, v, 32);
+	memcpy(m + 33, u, 32);
+
+	err = aes_cmac(tfm_cmac, x, m, sizeof(m), res);
+	if (err)
+		return err;
+
+	SMP_DBG("res %16phN", res);
+
+	return err;
+}
+
+static int smp_f5(struct crypto_hash *tfm_cmac, const u8 w[32],
+		  const u8 n1[16], const u8 n2[16], const u8 a1[7],
+		  const u8 a2[7], u8 mackey[16], u8 ltk[16])
+{
+	/* The btle, salt and length "magic" values are as defined in
+	 * the SMP section of the Bluetooth core specification. In ASCII
+	 * the btle value ends up being 'btle'. The salt is just a
+	 * random number whereas length is the value 256 in little
+	 * endian format.
+	 */
+	const u8 btle[4] = { 0x65, 0x6c, 0x74, 0x62 };
+	const u8 salt[16] = { 0xbe, 0x83, 0x60, 0x5a, 0xdb, 0x0b, 0x37, 0x60,
+			      0x38, 0xa5, 0xf5, 0xaa, 0x91, 0x83, 0x88, 0x6c };
+	const u8 length[2] = { 0x00, 0x01 };
+	u8 m[53], t[16];
+	int err;
+
+	SMP_DBG("w %32phN", w);
+	SMP_DBG("n1 %16phN n2 %16phN", n1, n2);
+	SMP_DBG("a1 %7phN a2 %7phN", a1, a2);
+
+	err = aes_cmac(tfm_cmac, salt, w, 32, t);
+	if (err)
+		return err;
+
+	SMP_DBG("t %16phN", t);
+
+	memcpy(m, length, 2);
+	memcpy(m + 2, a2, 7);
+	memcpy(m + 9, a1, 7);
+	memcpy(m + 16, n2, 16);
+	memcpy(m + 32, n1, 16);
+	memcpy(m + 48, btle, 4);
+
+	m[52] = 0; /* Counter */
+
+	err = aes_cmac(tfm_cmac, t, m, sizeof(m), mackey);
+	if (err)
+		return err;
+
+	SMP_DBG("mackey %16phN", mackey);
+
+	m[52] = 1; /* Counter */
+
+	err = aes_cmac(tfm_cmac, t, m, sizeof(m), ltk);
+	if (err)
+		return err;
+
+	SMP_DBG("ltk %16phN", ltk);
+
+	return 0;
+}
+
+static int smp_f6(struct crypto_hash *tfm_cmac, const u8 w[16],
+		  const u8 n1[16], const u8 n2[16], const u8 r[16],
+		  const u8 io_cap[3], const u8 a1[7], const u8 a2[7],
+		  u8 res[16])
+{
+	u8 m[65];
+	int err;
+
+	SMP_DBG("w %16phN", w);
+	SMP_DBG("n1 %16phN n2 %16phN", n1, n2);
+	SMP_DBG("r %16phN io_cap %3phN a1 %7phN a2 %7phN", r, io_cap, a1, a2);
+
+	memcpy(m, a2, 7);
+	memcpy(m + 7, a1, 7);
+	memcpy(m + 14, io_cap, 3);
+	memcpy(m + 17, r, 16);
+	memcpy(m + 33, n2, 16);
+	memcpy(m + 49, n1, 16);
+
+	err = aes_cmac(tfm_cmac, w, m, sizeof(m), res);
+	if (err)
+		return err;
+
+	SMP_DBG("res %16phN", res);
+
+	return err;
+}
+
+static int smp_g2(struct crypto_hash *tfm_cmac, const u8 u[32], const u8 v[32],
+		  const u8 x[16], const u8 y[16], u32 *val)
+{
+	u8 m[80], tmp[16];
+	int err;
+
+	SMP_DBG("u %32phN", u);
+	SMP_DBG("v %32phN", v);
+	SMP_DBG("x %16phN y %16phN", x, y);
+
+	memcpy(m, y, 16);
+	memcpy(m + 16, v, 32);
+	memcpy(m + 48, u, 32);
+
+	err = aes_cmac(tfm_cmac, x, m, sizeof(m), tmp);
+	if (err)
+		return err;
+
+	*val = get_unaligned_le32(tmp);
+	*val %= 1000000;
+
+	SMP_DBG("val %06u", *val);
+
+	return 0;
+}
+
+static int smp_h6(struct crypto_hash *tfm_cmac, const u8 w[16],
+		  const u8 key_id[4], u8 res[16])
+{
+	int err;
+
+	SMP_DBG("w %16phN key_id %4phN", w, key_id);
+
+	err = aes_cmac(tfm_cmac, w, key_id, 4, res);
+	if (err)
+		return err;
+
+	SMP_DBG("res %16phN", res);
+
+	return err;
+}
+
+/* The following functions map to the legacy SMP crypto functions e, c1,
+ * s1 and ah.
+ */
+
 static int smp_e(struct crypto_blkcipher *tfm, const u8 *k, u8 *r)
 {
 	struct blkcipher_desc desc;
@@ -87,7 +371,7 @@ static int smp_e(struct crypto_blkcipher *tfm, const u8 *k, u8 *r)
 	uint8_t tmp[16], data[16];
 	int err;
 
-	if (tfm == NULL) {
+	if (!tfm) {
 		BT_ERR("tfm %p", tfm);
 		return -EINVAL;
 	}
@@ -119,7 +403,65 @@ static int smp_e(struct crypto_blkcipher *tfm, const u8 *k, u8 *r)
 	return err;
 }
 
-static int smp_ah(struct crypto_blkcipher *tfm, u8 irk[16], u8 r[3], u8 res[3])
+static int smp_c1(struct crypto_blkcipher *tfm_aes, const u8 k[16],
+		  const u8 r[16], const u8 preq[7], const u8 pres[7], u8 _iat,
+		  const bdaddr_t *ia, u8 _rat, const bdaddr_t *ra, u8 res[16])
+{
+	u8 p1[16], p2[16];
+	int err;
+
+	memset(p1, 0, 16);
+
+	/* p1 = pres || preq || _rat || _iat */
+	p1[0] = _iat;
+	p1[1] = _rat;
+	memcpy(p1 + 2, preq, 7);
+	memcpy(p1 + 9, pres, 7);
+
+	/* p2 = padding || ia || 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);
+
+	/* res = e(k, res) */
+	err = smp_e(tfm_aes, k, res);
+	if (err) {
+		BT_ERR("Encrypt data error");
+		return err;
+	}
+
+	/* res = res XOR p2 */
+	u128_xor((u128 *) res, (u128 *) res, (u128 *) p2);
+
+	/* res = e(k, res) */
+	err = smp_e(tfm_aes, k, res);
+	if (err)
+		BT_ERR("Encrypt data error");
+
+	return err;
+}
+
+static int smp_s1(struct crypto_blkcipher *tfm_aes, const u8 k[16],
+		  const u8 r1[16], const u8 r2[16], u8 _r[16])
+{
+	int err;
+
+	/* Just least significant octets from r1 and r2 are considered */
+	memcpy(_r, r2, 8);
+	memcpy(_r + 8, r1, 8);
+
+	err = smp_e(tfm_aes, k, _r);
+	if (err)
+		BT_ERR("Encrypt data error");
+
+	return err;
+}
+
+static int smp_ah(struct crypto_blkcipher *tfm, const u8 irk[16],
+		  const u8 r[3], u8 res[3])
 {
 	u8 _res[16];
 	int err;
@@ -145,44 +487,45 @@ static int smp_ah(struct crypto_blkcipher *tfm, u8 irk[16], u8 r[3], u8 res[3])
 	return 0;
 }
 
-bool smp_irk_matches(struct hci_dev *hdev, u8 irk[16], bdaddr_t *bdaddr)
+bool smp_irk_matches(struct hci_dev *hdev, const u8 irk[16],
+		     const bdaddr_t *bdaddr)
 {
 	struct l2cap_chan *chan = hdev->smp_data;
-	struct crypto_blkcipher *tfm;
+	struct smp_dev *smp;
 	u8 hash[3];
 	int err;
 
 	if (!chan || !chan->data)
 		return false;
 
-	tfm = chan->data;
+	smp = chan->data;
 
 	BT_DBG("RPA %pMR IRK %*phN", bdaddr, 16, irk);
 
-	err = smp_ah(tfm, irk, &bdaddr->b[3], hash);
+	err = smp_ah(smp->tfm_aes, irk, &bdaddr->b[3], hash);
 	if (err)
 		return false;
 
 	return !memcmp(bdaddr->b, hash, 3);
 }
 
-int smp_generate_rpa(struct hci_dev *hdev, u8 irk[16], bdaddr_t *rpa)
+int smp_generate_rpa(struct hci_dev *hdev, const u8 irk[16], bdaddr_t *rpa)
 {
 	struct l2cap_chan *chan = hdev->smp_data;
-	struct crypto_blkcipher *tfm;
+	struct smp_dev *smp;
 	int err;
 
 	if (!chan || !chan->data)
 		return -EOPNOTSUPP;
 
-	tfm = chan->data;
+	smp = chan->data;
 
 	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);
+	err = smp_ah(smp->tfm_aes, irk, &rpa->b[3], rpa->b);
 	if (err < 0)
 		return err;
 
@@ -191,67 +534,51 @@ int smp_generate_rpa(struct hci_dev *hdev, u8 irk[16], bdaddr_t *rpa)
 	return 0;
 }
 
-static int smp_c1(struct smp_chan *smp, 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])
+int smp_generate_oob(struct hci_dev *hdev, u8 hash[16], u8 rand[16])
 {
-	struct hci_dev *hdev = smp->conn->hcon->hdev;
-	u8 p1[16], p2[16];
+	struct l2cap_chan *chan = hdev->smp_data;
+	struct smp_dev *smp;
 	int err;
 
-	BT_DBG("%s", hdev->name);
-
-	memset(p1, 0, 16);
-
-	/* p1 = pres || preq || _rat || _iat */
-	p1[0] = _iat;
-	p1[1] = _rat;
-	memcpy(p1 + 2, preq, 7);
-	memcpy(p1 + 9, pres, 7);
-
-	/* p2 = padding || ia || ra */
-	memcpy(p2, ra, 6);
-	memcpy(p2 + 6, ia, 6);
-	memset(p2 + 12, 0, 4);
+	if (!chan || !chan->data)
+		return -EOPNOTSUPP;
 
-	/* res = r XOR p1 */
-	u128_xor((u128 *) res, (u128 *) r, (u128 *) p1);
+	smp = chan->data;
 
-	/* res = e(k, res) */
-	err = smp_e(smp->tfm_aes, k, res);
-	if (err) {
-		BT_ERR("Encrypt data error");
-		return err;
+	if (hci_dev_test_flag(hdev, HCI_USE_DEBUG_KEYS)) {
+		BT_DBG("Using debug keys");
+		memcpy(smp->local_pk, debug_pk, 64);
+		memcpy(smp->local_sk, debug_sk, 32);
+		smp->debug_key = true;
+	} else {
+		while (true) {
+			/* Generate local key pair for Secure Connections */
+			if (!ecc_make_key(smp->local_pk, smp->local_sk))
+				return -EIO;
+
+			/* This is unlikely, but we need to check that
+			 * we didn't accidentially generate a debug key.
+			 */
+			if (memcmp(smp->local_sk, debug_sk, 32))
+				break;
+		}
+		smp->debug_key = false;
 	}
 
-	/* res = res XOR p2 */
-	u128_xor((u128 *) res, (u128 *) res, (u128 *) p2);
-
-	/* res = e(k, res) */
-	err = smp_e(smp->tfm_aes, k, res);
-	if (err)
-		BT_ERR("Encrypt data error");
-
-	return err;
-}
-
-static int smp_s1(struct smp_chan *smp, u8 k[16], u8 r1[16], u8 r2[16],
-		  u8 _r[16])
-{
-	struct hci_dev *hdev = smp->conn->hcon->hdev;
-	int err;
+	SMP_DBG("OOB Public Key X: %32phN", smp->local_pk);
+	SMP_DBG("OOB Public Key Y: %32phN", smp->local_pk + 32);
+	SMP_DBG("OOB Private Key:  %32phN", smp->local_sk);
 
-	BT_DBG("%s", hdev->name);
+	get_random_bytes(smp->local_rand, 16);
 
-	/* Just least significant octets from r1 and r2 are considered */
-	memcpy(_r, r2, 8);
-	memcpy(_r + 8, r1, 8);
+	err = smp_f4(smp->tfm_cmac, smp->local_pk, smp->local_pk,
+		     smp->local_rand, 0, hash);
+	if (err < 0)
+		return err;
 
-	err = smp_e(smp->tfm_aes, k, _r);
-	if (err)
-		BT_ERR("Encrypt data error");
+	memcpy(rand, smp->local_rand, 16);
 
-	return err;
+	return 0;
 }
 
 static void smp_send_cmd(struct l2cap_conn *conn, u8 code, u16 len, void *data)
@@ -274,8 +601,7 @@ static void smp_send_cmd(struct l2cap_conn *conn, u8 code, u16 len, void *data)
 
 	memset(&msg, 0, sizeof(msg));
 
-	msg.msg_iov = (struct iovec *) &iv;
-	msg.msg_iovlen = 2;
+	iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iv, 2, 1 + len);
 
 	l2cap_chan_send(chan, &msg, 1 + len);
 
@@ -288,17 +614,22 @@ static void smp_send_cmd(struct l2cap_conn *conn, u8 code, u16 len, void *data)
 	schedule_delayed_work(&smp->security_timer, SMP_TIMEOUT);
 }
 
-static __u8 authreq_to_seclevel(__u8 authreq)
+static u8 authreq_to_seclevel(u8 authreq)
 {
-	if (authreq & SMP_AUTH_MITM)
-		return BT_SECURITY_HIGH;
-	else
+	if (authreq & SMP_AUTH_MITM) {
+		if (authreq & SMP_AUTH_SC)
+			return BT_SECURITY_FIPS;
+		else
+			return BT_SECURITY_HIGH;
+	} else {
 		return BT_SECURITY_MEDIUM;
+	}
 }
 
 static __u8 seclevel_to_authreq(__u8 sec_level)
 {
 	switch (sec_level) {
+	case BT_SECURITY_FIPS:
 	case BT_SECURITY_HIGH:
 		return SMP_AUTH_MITM | SMP_AUTH_BONDING;
 	case BT_SECURITY_MEDIUM:
@@ -316,9 +647,9 @@ static void build_pairing_cmd(struct l2cap_conn *conn,
 	struct smp_chan *smp = chan->data;
 	struct hci_conn *hcon = conn->hcon;
 	struct hci_dev *hdev = hcon->hdev;
-	u8 local_dist = 0, remote_dist = 0;
+	u8 local_dist = 0, remote_dist = 0, oob_flag = SMP_OOB_NOT_PRESENT;
 
-	if (test_bit(HCI_BONDABLE, &conn->hcon->hdev->dev_flags)) {
+	if (hci_dev_test_flag(hdev, HCI_BONDABLE)) {
 		local_dist = SMP_DIST_ENC_KEY | SMP_DIST_SIGN;
 		remote_dist = SMP_DIST_ENC_KEY | SMP_DIST_SIGN;
 		authreq |= SMP_AUTH_BONDING;
@@ -326,30 +657,60 @@ static void build_pairing_cmd(struct l2cap_conn *conn,
 		authreq &= ~SMP_AUTH_BONDING;
 	}
 
-	if (test_bit(HCI_RPA_RESOLVING, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_RPA_RESOLVING))
 		remote_dist |= SMP_DIST_ID_KEY;
 
-	if (test_bit(HCI_PRIVACY, &hdev->dev_flags))
+	if (hci_dev_test_flag(hdev, HCI_PRIVACY))
 		local_dist |= SMP_DIST_ID_KEY;
 
+	if (hci_dev_test_flag(hdev, HCI_SC_ENABLED) &&
+	    (authreq & SMP_AUTH_SC)) {
+		struct oob_data *oob_data;
+		u8 bdaddr_type;
+
+		if (hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) {
+			local_dist |= SMP_DIST_LINK_KEY;
+			remote_dist |= SMP_DIST_LINK_KEY;
+		}
+
+		if (hcon->dst_type == ADDR_LE_DEV_PUBLIC)
+			bdaddr_type = BDADDR_LE_PUBLIC;
+		else
+			bdaddr_type = BDADDR_LE_RANDOM;
+
+		oob_data = hci_find_remote_oob_data(hdev, &hcon->dst,
+						    bdaddr_type);
+		if (oob_data && oob_data->present) {
+			set_bit(SMP_FLAG_REMOTE_OOB, &smp->flags);
+			oob_flag = SMP_OOB_PRESENT;
+			memcpy(smp->rr, oob_data->rand256, 16);
+			memcpy(smp->pcnf, oob_data->hash256, 16);
+			SMP_DBG("OOB Remote Confirmation: %16phN", smp->pcnf);
+			SMP_DBG("OOB Remote Random: %16phN", smp->rr);
+		}
+
+	} else {
+		authreq &= ~SMP_AUTH_SC;
+	}
+
 	if (rsp == NULL) {
 		req->io_capability = conn->hcon->io_capability;
-		req->oob_flag = SMP_OOB_NOT_PRESENT;
+		req->oob_flag = oob_flag;
 		req->max_key_size = SMP_MAX_ENC_KEY_SIZE;
 		req->init_key_dist = local_dist;
 		req->resp_key_dist = remote_dist;
-		req->auth_req = (authreq & AUTH_REQ_MASK);
+		req->auth_req = (authreq & AUTH_REQ_MASK(hdev));
 
 		smp->remote_key_dist = remote_dist;
 		return;
 	}
 
 	rsp->io_capability = conn->hcon->io_capability;
-	rsp->oob_flag = SMP_OOB_NOT_PRESENT;
+	rsp->oob_flag = oob_flag;
 	rsp->max_key_size = SMP_MAX_ENC_KEY_SIZE;
 	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);
+	rsp->auth_req = (authreq & AUTH_REQ_MASK(hdev));
 
 	smp->remote_key_dist = rsp->init_key_dist;
 }
@@ -372,6 +733,7 @@ static void smp_chan_destroy(struct l2cap_conn *conn)
 {
 	struct l2cap_chan *chan = conn->smp;
 	struct smp_chan *smp = chan->data;
+	struct hci_conn *hcon = conn->hcon;
 	bool complete;
 
 	BUG_ON(!smp);
@@ -379,34 +741,46 @@ static void smp_chan_destroy(struct l2cap_conn *conn)
 	cancel_delayed_work_sync(&smp->security_timer);
 
 	complete = test_bit(SMP_FLAG_COMPLETE, &smp->flags);
-	mgmt_smp_complete(conn->hcon, complete);
+	mgmt_smp_complete(hcon, complete);
 
-	kfree(smp->csrk);
-	kfree(smp->slave_csrk);
+	kzfree(smp->csrk);
+	kzfree(smp->slave_csrk);
+	kzfree(smp->link_key);
 
 	crypto_free_blkcipher(smp->tfm_aes);
+	crypto_free_hash(smp->tfm_cmac);
+
+	/* Ensure that we don't leave any debug key around if debug key
+	 * support hasn't been explicitly enabled.
+	 */
+	if (smp->ltk && smp->ltk->type == SMP_LTK_P256_DEBUG &&
+	    !hci_dev_test_flag(hcon->hdev, HCI_KEEP_DEBUG_KEYS)) {
+		list_del_rcu(&smp->ltk->list);
+		kfree_rcu(smp->ltk, rcu);
+		smp->ltk = NULL;
+	}
 
 	/* If pairing failed clean up any keys we might have */
 	if (!complete) {
 		if (smp->ltk) {
-			list_del(&smp->ltk->list);
-			kfree(smp->ltk);
+			list_del_rcu(&smp->ltk->list);
+			kfree_rcu(smp->ltk, rcu);
 		}
 
 		if (smp->slave_ltk) {
-			list_del(&smp->slave_ltk->list);
-			kfree(smp->slave_ltk);
+			list_del_rcu(&smp->slave_ltk->list);
+			kfree_rcu(smp->slave_ltk, rcu);
 		}
 
 		if (smp->remote_irk) {
-			list_del(&smp->remote_irk->list);
-			kfree(smp->remote_irk);
+			list_del_rcu(&smp->remote_irk->list);
+			kfree_rcu(smp->remote_irk, rcu);
 		}
 	}
 
 	chan->data = NULL;
-	kfree(smp);
-	hci_conn_drop(conn->hcon);
+	kzfree(smp);
+	hci_conn_drop(hcon);
 }
 
 static void smp_failure(struct l2cap_conn *conn, u8 reason)
@@ -430,6 +804,7 @@ static void smp_failure(struct l2cap_conn *conn, u8 reason)
 #define REQ_PASSKEY	0x02
 #define CFM_PASSKEY	0x03
 #define REQ_OOB		0x04
+#define DSP_PASSKEY	0x05
 #define OVERLAP		0xFF
 
 static const u8 gen_method[5][5] = {
@@ -440,6 +815,14 @@ static const u8 gen_method[5][5] = {
 	{ CFM_PASSKEY, CFM_PASSKEY, REQ_PASSKEY, JUST_WORKS, OVERLAP     },
 };
 
+static const u8 sc_method[5][5] = {
+	{ JUST_WORKS,  JUST_CFM,    REQ_PASSKEY, JUST_WORKS, REQ_PASSKEY },
+	{ JUST_WORKS,  CFM_PASSKEY, REQ_PASSKEY, JUST_WORKS, CFM_PASSKEY },
+	{ DSP_PASSKEY, DSP_PASSKEY, REQ_PASSKEY, JUST_WORKS, DSP_PASSKEY },
+	{ JUST_WORKS,  JUST_CFM,    JUST_WORKS,  JUST_WORKS, JUST_CFM    },
+	{ DSP_PASSKEY, CFM_PASSKEY, REQ_PASSKEY, JUST_WORKS, CFM_PASSKEY },
+};
+
 static u8 get_auth_method(struct smp_chan *smp, u8 local_io, u8 remote_io)
 {
 	/* If either side has unknown io_caps, use JUST_CFM (which gets
@@ -449,6 +832,9 @@ static u8 get_auth_method(struct smp_chan *smp, u8 local_io, u8 remote_io)
 	    remote_io > SMP_IO_KEYBOARD_DISPLAY)
 		return JUST_CFM;
 
+	if (test_bit(SMP_FLAG_SC, &smp->flags))
+		return sc_method[remote_io][local_io];
+
 	return gen_method[remote_io][local_io];
 }
 
@@ -458,7 +844,6 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth,
 	struct hci_conn *hcon = conn->hcon;
 	struct l2cap_chan *chan = conn->smp;
 	struct smp_chan *smp = chan->data;
-	u8 method;
 	u32 passkey = 0;
 	int ret = 0;
 
@@ -475,26 +860,34 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth,
 	 * table.
 	 */
 	if (!(auth & SMP_AUTH_MITM))
-		method = JUST_CFM;
+		smp->method = JUST_CFM;
 	else
-		method = get_auth_method(smp, local_io, remote_io);
+		smp->method = get_auth_method(smp, local_io, remote_io);
 
 	/* Don't confirm locally initiated pairing attempts */
-	if (method == JUST_CFM && test_bit(SMP_FLAG_INITIATOR, &smp->flags))
-		method = JUST_WORKS;
+	if (smp->method == JUST_CFM && test_bit(SMP_FLAG_INITIATOR,
+						&smp->flags))
+		smp->method = JUST_WORKS;
 
 	/* Don't bother user space with no IO capabilities */
-	if (method == JUST_CFM && hcon->io_capability == HCI_IO_NO_INPUT_OUTPUT)
-		method = JUST_WORKS;
+	if (smp->method == JUST_CFM &&
+	    hcon->io_capability == HCI_IO_NO_INPUT_OUTPUT)
+		smp->method = JUST_WORKS;
 
 	/* If Just Works, Continue with Zero TK */
-	if (method == JUST_WORKS) {
+	if (smp->method == JUST_WORKS) {
 		set_bit(SMP_FLAG_TK_VALID, &smp->flags);
 		return 0;
 	}
 
+	/* If this function is used for SC -> legacy fallback we
+	 * can only recover the just-works case.
+	 */
+	if (test_bit(SMP_FLAG_SC, &smp->flags))
+		return -EINVAL;
+
 	/* Not Just Works/Confirm results in MITM Authentication */
-	if (method != JUST_CFM) {
+	if (smp->method != JUST_CFM) {
 		set_bit(SMP_FLAG_MITM_AUTH, &smp->flags);
 		if (hcon->pending_sec_level < BT_SECURITY_HIGH)
 			hcon->pending_sec_level = BT_SECURITY_HIGH;
@@ -503,15 +896,15 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth,
 	/* If both devices have Keyoard-Display I/O, the master
 	 * Confirms and the slave Enters the passkey.
 	 */
-	if (method == OVERLAP) {
+	if (smp->method == OVERLAP) {
 		if (hcon->role == HCI_ROLE_MASTER)
-			method = CFM_PASSKEY;
+			smp->method = CFM_PASSKEY;
 		else
-			method = REQ_PASSKEY;
+			smp->method = REQ_PASSKEY;
 	}
 
 	/* Generate random passkey. */
-	if (method == CFM_PASSKEY) {
+	if (smp->method == CFM_PASSKEY) {
 		memset(smp->tk, 0, sizeof(smp->tk));
 		get_random_bytes(&passkey, sizeof(passkey));
 		passkey %= 1000000;
@@ -520,12 +913,10 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth,
 		set_bit(SMP_FLAG_TK_VALID, &smp->flags);
 	}
 
-	hci_dev_lock(hcon->hdev);
-
-	if (method == REQ_PASSKEY)
+	if (smp->method == REQ_PASSKEY)
 		ret = mgmt_user_passkey_request(hcon->hdev, &hcon->dst,
 						hcon->type, hcon->dst_type);
-	else if (method == JUST_CFM)
+	else if (smp->method == JUST_CFM)
 		ret = mgmt_user_confirm_request(hcon->hdev, &hcon->dst,
 						hcon->type, hcon->dst_type,
 						passkey, 1);
@@ -534,8 +925,6 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth,
 						hcon->type, hcon->dst_type,
 						passkey, 0);
 
-	hci_dev_unlock(hcon->hdev);
-
 	return ret;
 }
 
@@ -547,7 +936,7 @@ static u8 smp_confirm(struct smp_chan *smp)
 
 	BT_DBG("conn %p", conn);
 
-	ret = smp_c1(smp, smp->tk, smp->prnd, smp->preq, smp->prsp,
+	ret = smp_c1(smp->tfm_aes, 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);
@@ -578,7 +967,7 @@ static u8 smp_random(struct smp_chan *smp)
 
 	BT_DBG("conn %p %s", conn, conn->hcon->out ? "master" : "slave");
 
-	ret = smp_c1(smp, smp->tk, smp->rrnd, smp->preq, smp->prsp,
+	ret = smp_c1(smp->tfm_aes, smp->tk, smp->rrnd, smp->preq, smp->prsp,
 		     hcon->init_addr_type, &hcon->init_addr,
 		     hcon->resp_addr_type, &hcon->resp_addr, confirm);
 	if (ret)
@@ -594,7 +983,7 @@ static u8 smp_random(struct smp_chan *smp)
 		__le64 rand = 0;
 		__le16 ediv = 0;
 
-		smp_s1(smp, smp->tk, smp->rrnd, smp->prnd, stk);
+		smp_s1(smp->tfm_aes, smp->tk, smp->rrnd, smp->prnd, stk);
 
 		memset(stk + smp->enc_key_size, 0,
 		       SMP_MAX_ENC_KEY_SIZE - smp->enc_key_size);
@@ -613,7 +1002,7 @@ static u8 smp_random(struct smp_chan *smp)
 		smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd),
 			     smp->prnd);
 
-		smp_s1(smp, smp->tk, smp->prnd, smp->rrnd, stk);
+		smp_s1(smp->tfm_aes, smp->tk, smp->prnd, smp->rrnd, stk);
 
 		memset(stk + smp->enc_key_size, 0,
 		       SMP_MAX_ENC_KEY_SIZE - smp->enc_key_size);
@@ -648,11 +1037,13 @@ static void smp_notify_keys(struct l2cap_conn *conn)
 		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.
+		 * from now on (assuming this is an LE link).
 		 */
-		bacpy(&hcon->dst, &smp->remote_irk->bdaddr);
-		hcon->dst_type = smp->remote_irk->addr_type;
-		queue_work(hdev->workqueue, &conn->id_addr_update_work);
+		if (hcon->type == LE_LINK) {
+			bacpy(&hcon->dst, &smp->remote_irk->bdaddr);
+			hcon->dst_type = smp->remote_irk->addr_type;
+			queue_work(hdev->workqueue, &conn->id_addr_update_work);
+		}
 
 		/* When receiving an indentity resolving key for
 		 * a remote device that does not use a resolvable
@@ -665,16 +1056,26 @@ static void smp_notify_keys(struct l2cap_conn *conn)
 		 * just remove it.
 		 */
 		if (!bacmp(&smp->remote_irk->rpa, BDADDR_ANY)) {
-			list_del(&smp->remote_irk->list);
-			kfree(smp->remote_irk);
+			list_del_rcu(&smp->remote_irk->list);
+			kfree_rcu(smp->remote_irk, rcu);
 			smp->remote_irk = NULL;
 		}
 	}
 
-	/* 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 (hcon->type == ACL_LINK) {
+		if (hcon->key_type == HCI_LK_DEBUG_COMBINATION)
+			persistent = false;
+		else
+			persistent = !test_bit(HCI_CONN_FLUSH_KEY,
+					       &hcon->flags);
+	} else {
+		/* 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;
@@ -699,6 +1100,81 @@ static void smp_notify_keys(struct l2cap_conn *conn)
 		bacpy(&smp->slave_ltk->bdaddr, &hcon->dst);
 		mgmt_new_ltk(hdev, smp->slave_ltk, persistent);
 	}
+
+	if (smp->link_key) {
+		struct link_key *key;
+		u8 type;
+
+		if (test_bit(SMP_FLAG_DEBUG_KEY, &smp->flags))
+			type = HCI_LK_DEBUG_COMBINATION;
+		else if (hcon->sec_level == BT_SECURITY_FIPS)
+			type = HCI_LK_AUTH_COMBINATION_P256;
+		else
+			type = HCI_LK_UNAUTH_COMBINATION_P256;
+
+		key = hci_add_link_key(hdev, smp->conn->hcon, &hcon->dst,
+				       smp->link_key, type, 0, &persistent);
+		if (key) {
+			mgmt_new_link_key(hdev, key, persistent);
+
+			/* Don't keep debug keys around if the relevant
+			 * flag is not set.
+			 */
+			if (!hci_dev_test_flag(hdev, HCI_KEEP_DEBUG_KEYS) &&
+			    key->type == HCI_LK_DEBUG_COMBINATION) {
+				list_del_rcu(&key->list);
+				kfree_rcu(key, rcu);
+			}
+		}
+	}
+}
+
+static void sc_add_ltk(struct smp_chan *smp)
+{
+	struct hci_conn *hcon = smp->conn->hcon;
+	u8 key_type, auth;
+
+	if (test_bit(SMP_FLAG_DEBUG_KEY, &smp->flags))
+		key_type = SMP_LTK_P256_DEBUG;
+	else
+		key_type = SMP_LTK_P256;
+
+	if (hcon->pending_sec_level == BT_SECURITY_FIPS)
+		auth = 1;
+	else
+		auth = 0;
+
+	memset(smp->tk + smp->enc_key_size, 0,
+	       SMP_MAX_ENC_KEY_SIZE - smp->enc_key_size);
+
+	smp->ltk = hci_add_ltk(hcon->hdev, &hcon->dst, hcon->dst_type,
+			       key_type, auth, smp->tk, smp->enc_key_size,
+			       0, 0);
+}
+
+static void sc_generate_link_key(struct smp_chan *smp)
+{
+	/* These constants are as specified in the core specification.
+	 * In ASCII they spell out to 'tmp1' and 'lebr'.
+	 */
+	const u8 tmp1[4] = { 0x31, 0x70, 0x6d, 0x74 };
+	const u8 lebr[4] = { 0x72, 0x62, 0x65, 0x6c };
+
+	smp->link_key = kzalloc(16, GFP_KERNEL);
+	if (!smp->link_key)
+		return;
+
+	if (smp_h6(smp->tfm_cmac, smp->tk, tmp1, smp->link_key)) {
+		kzfree(smp->link_key);
+		smp->link_key = NULL;
+		return;
+	}
+
+	if (smp_h6(smp->tfm_cmac, smp->link_key, lebr, smp->link_key)) {
+		kzfree(smp->link_key);
+		smp->link_key = NULL;
+		return;
+	}
 }
 
 static void smp_allow_key_dist(struct smp_chan *smp)
@@ -715,6 +1191,35 @@ static void smp_allow_key_dist(struct smp_chan *smp)
 		SMP_ALLOW_CMD(smp, SMP_CMD_SIGN_INFO);
 }
 
+static void sc_generate_ltk(struct smp_chan *smp)
+{
+	/* These constants are as specified in the core specification.
+	 * In ASCII they spell out to 'tmp2' and 'brle'.
+	 */
+	const u8 tmp2[4] = { 0x32, 0x70, 0x6d, 0x74 };
+	const u8 brle[4] = { 0x65, 0x6c, 0x72, 0x62 };
+	struct hci_conn *hcon = smp->conn->hcon;
+	struct hci_dev *hdev = hcon->hdev;
+	struct link_key *key;
+
+	key = hci_find_link_key(hdev, &hcon->dst);
+	if (!key) {
+		BT_ERR("%s No Link Key found to generate LTK", hdev->name);
+		return;
+	}
+
+	if (key->type == HCI_LK_DEBUG_COMBINATION)
+		set_bit(SMP_FLAG_DEBUG_KEY, &smp->flags);
+
+	if (smp_h6(smp->tfm_cmac, key->val, tmp2, smp->tk))
+		return;
+
+	if (smp_h6(smp->tfm_cmac, smp->tk, brle, smp->tk))
+		return;
+
+	sc_add_ltk(smp);
+}
+
 static void smp_distribute_keys(struct smp_chan *smp)
 {
 	struct smp_cmd_pairing *req, *rsp;
@@ -743,6 +1248,16 @@ static void smp_distribute_keys(struct smp_chan *smp)
 		*keydist &= req->resp_key_dist;
 	}
 
+	if (test_bit(SMP_FLAG_SC, &smp->flags)) {
+		if (hcon->type == LE_LINK && (*keydist & SMP_DIST_LINK_KEY))
+			sc_generate_link_key(smp);
+		if (hcon->type == ACL_LINK && (*keydist & SMP_DIST_ENC_KEY))
+			sc_generate_ltk(smp);
+
+		/* Clear the keys which are generated but not distributed */
+		*keydist &= ~SMP_SC_NO_DIST;
+	}
+
 	BT_DBG("keydist 0x%x", *keydist);
 
 	if (*keydist & SMP_DIST_ENC_KEY) {
@@ -805,7 +1320,10 @@ static void smp_distribute_keys(struct smp_chan *smp)
 
 		csrk = kzalloc(sizeof(*csrk), GFP_KERNEL);
 		if (csrk) {
-			csrk->master = 0x00;
+			if (hcon->sec_level > BT_SECURITY_MEDIUM)
+				csrk->type = MGMT_CSRK_LOCAL_AUTHENTICATED;
+			else
+				csrk->type = MGMT_CSRK_LOCAL_UNAUTHENTICATED;
 			memcpy(csrk->val, sign.csrk, sizeof(csrk->val));
 		}
 		smp->slave_csrk = csrk;
@@ -850,7 +1368,15 @@ static struct smp_chan *smp_chan_create(struct l2cap_conn *conn)
 	smp->tfm_aes = crypto_alloc_blkcipher("ecb(aes)", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(smp->tfm_aes)) {
 		BT_ERR("Unable to create ECB crypto context");
-		kfree(smp);
+		kzfree(smp);
+		return NULL;
+	}
+
+	smp->tfm_cmac = crypto_alloc_hash("cmac(aes)", 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(smp->tfm_cmac)) {
+		BT_ERR("Unable to create CMAC crypto context");
+		crypto_free_blkcipher(smp->tfm_aes);
+		kzfree(smp);
 		return NULL;
 	}
 
@@ -866,6 +1392,213 @@ static struct smp_chan *smp_chan_create(struct l2cap_conn *conn)
 	return smp;
 }
 
+static int sc_mackey_and_ltk(struct smp_chan *smp, u8 mackey[16], u8 ltk[16])
+{
+	struct hci_conn *hcon = smp->conn->hcon;
+	u8 *na, *nb, a[7], b[7];
+
+	if (hcon->out) {
+		na   = smp->prnd;
+		nb   = smp->rrnd;
+	} else {
+		na   = smp->rrnd;
+		nb   = smp->prnd;
+	}
+
+	memcpy(a, &hcon->init_addr, 6);
+	memcpy(b, &hcon->resp_addr, 6);
+	a[6] = hcon->init_addr_type;
+	b[6] = hcon->resp_addr_type;
+
+	return smp_f5(smp->tfm_cmac, smp->dhkey, na, nb, a, b, mackey, ltk);
+}
+
+static void sc_dhkey_check(struct smp_chan *smp)
+{
+	struct hci_conn *hcon = smp->conn->hcon;
+	struct smp_cmd_dhkey_check check;
+	u8 a[7], b[7], *local_addr, *remote_addr;
+	u8 io_cap[3], r[16];
+
+	memcpy(a, &hcon->init_addr, 6);
+	memcpy(b, &hcon->resp_addr, 6);
+	a[6] = hcon->init_addr_type;
+	b[6] = hcon->resp_addr_type;
+
+	if (hcon->out) {
+		local_addr = a;
+		remote_addr = b;
+		memcpy(io_cap, &smp->preq[1], 3);
+	} else {
+		local_addr = b;
+		remote_addr = a;
+		memcpy(io_cap, &smp->prsp[1], 3);
+	}
+
+	memset(r, 0, sizeof(r));
+
+	if (smp->method == REQ_PASSKEY || smp->method == DSP_PASSKEY)
+		put_unaligned_le32(hcon->passkey_notify, r);
+
+	if (smp->method == REQ_OOB)
+		memcpy(r, smp->rr, 16);
+
+	smp_f6(smp->tfm_cmac, smp->mackey, smp->prnd, smp->rrnd, r, io_cap,
+	       local_addr, remote_addr, check.e);
+
+	smp_send_cmd(smp->conn, SMP_CMD_DHKEY_CHECK, sizeof(check), &check);
+}
+
+static u8 sc_passkey_send_confirm(struct smp_chan *smp)
+{
+	struct l2cap_conn *conn = smp->conn;
+	struct hci_conn *hcon = conn->hcon;
+	struct smp_cmd_pairing_confirm cfm;
+	u8 r;
+
+	r = ((hcon->passkey_notify >> smp->passkey_round) & 0x01);
+	r |= 0x80;
+
+	get_random_bytes(smp->prnd, sizeof(smp->prnd));
+
+	if (smp_f4(smp->tfm_cmac, smp->local_pk, smp->remote_pk, smp->prnd, r,
+		   cfm.confirm_val))
+		return SMP_UNSPECIFIED;
+
+	smp_send_cmd(conn, SMP_CMD_PAIRING_CONFIRM, sizeof(cfm), &cfm);
+
+	return 0;
+}
+
+static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op)
+{
+	struct l2cap_conn *conn = smp->conn;
+	struct hci_conn *hcon = conn->hcon;
+	struct hci_dev *hdev = hcon->hdev;
+	u8 cfm[16], r;
+
+	/* Ignore the PDU if we've already done 20 rounds (0 - 19) */
+	if (smp->passkey_round >= 20)
+		return 0;
+
+	switch (smp_op) {
+	case SMP_CMD_PAIRING_RANDOM:
+		r = ((hcon->passkey_notify >> smp->passkey_round) & 0x01);
+		r |= 0x80;
+
+		if (smp_f4(smp->tfm_cmac, smp->remote_pk, smp->local_pk,
+			   smp->rrnd, r, cfm))
+			return SMP_UNSPECIFIED;
+
+		if (memcmp(smp->pcnf, cfm, 16))
+			return SMP_CONFIRM_FAILED;
+
+		smp->passkey_round++;
+
+		if (smp->passkey_round == 20) {
+			/* Generate MacKey and LTK */
+			if (sc_mackey_and_ltk(smp, smp->mackey, smp->tk))
+				return SMP_UNSPECIFIED;
+		}
+
+		/* The round is only complete when the initiator
+		 * receives pairing random.
+		 */
+		if (!hcon->out) {
+			smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM,
+				     sizeof(smp->prnd), smp->prnd);
+			if (smp->passkey_round == 20)
+				SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK);
+			else
+				SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_CONFIRM);
+			return 0;
+		}
+
+		/* Start the next round */
+		if (smp->passkey_round != 20)
+			return sc_passkey_round(smp, 0);
+
+		/* Passkey rounds are complete - start DHKey Check */
+		sc_dhkey_check(smp);
+		SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK);
+
+		break;
+
+	case SMP_CMD_PAIRING_CONFIRM:
+		if (test_bit(SMP_FLAG_WAIT_USER, &smp->flags)) {
+			set_bit(SMP_FLAG_CFM_PENDING, &smp->flags);
+			return 0;
+		}
+
+		SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM);
+
+		if (hcon->out) {
+			smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM,
+				     sizeof(smp->prnd), smp->prnd);
+			return 0;
+		}
+
+		return sc_passkey_send_confirm(smp);
+
+	case SMP_CMD_PUBLIC_KEY:
+	default:
+		/* Initiating device starts the round */
+		if (!hcon->out)
+			return 0;
+
+		BT_DBG("%s Starting passkey round %u", hdev->name,
+		       smp->passkey_round + 1);
+
+		SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_CONFIRM);
+
+		return sc_passkey_send_confirm(smp);
+	}
+
+	return 0;
+}
+
+static int sc_user_reply(struct smp_chan *smp, u16 mgmt_op, __le32 passkey)
+{
+	struct l2cap_conn *conn = smp->conn;
+	struct hci_conn *hcon = conn->hcon;
+	u8 smp_op;
+
+	clear_bit(SMP_FLAG_WAIT_USER, &smp->flags);
+
+	switch (mgmt_op) {
+	case MGMT_OP_USER_PASSKEY_NEG_REPLY:
+		smp_failure(smp->conn, SMP_PASSKEY_ENTRY_FAILED);
+		return 0;
+	case MGMT_OP_USER_CONFIRM_NEG_REPLY:
+		smp_failure(smp->conn, SMP_NUMERIC_COMP_FAILED);
+		return 0;
+	case MGMT_OP_USER_PASSKEY_REPLY:
+		hcon->passkey_notify = le32_to_cpu(passkey);
+		smp->passkey_round = 0;
+
+		if (test_and_clear_bit(SMP_FLAG_CFM_PENDING, &smp->flags))
+			smp_op = SMP_CMD_PAIRING_CONFIRM;
+		else
+			smp_op = 0;
+
+		if (sc_passkey_round(smp, smp_op))
+			return -EIO;
+
+		return 0;
+	}
+
+	/* Initiator sends DHKey check first */
+	if (hcon->out) {
+		sc_dhkey_check(smp);
+		SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK);
+	} else if (test_and_clear_bit(SMP_FLAG_DHKEY_PENDING, &smp->flags)) {
+		sc_dhkey_check(smp);
+		sc_add_ltk(smp);
+	}
+
+	return 0;
+}
+
 int smp_user_confirm_reply(struct hci_conn *hcon, u16 mgmt_op, __le32 passkey)
 {
 	struct l2cap_conn *conn = hcon->l2cap_data;
@@ -891,6 +1624,11 @@ int smp_user_confirm_reply(struct hci_conn *hcon, u16 mgmt_op, __le32 passkey)
 
 	smp = chan->data;
 
+	if (test_bit(SMP_FLAG_SC, &smp->flags)) {
+		err = sc_user_reply(smp, mgmt_op, passkey);
+		goto unlock;
+	}
+
 	switch (mgmt_op) {
 	case MGMT_OP_USER_PASSKEY_REPLY:
 		value = le32_to_cpu(passkey);
@@ -926,6 +1664,46 @@ unlock:
 	return err;
 }
 
+static void build_bredr_pairing_cmd(struct smp_chan *smp,
+				    struct smp_cmd_pairing *req,
+				    struct smp_cmd_pairing *rsp)
+{
+	struct l2cap_conn *conn = smp->conn;
+	struct hci_dev *hdev = conn->hcon->hdev;
+	u8 local_dist = 0, remote_dist = 0;
+
+	if (hci_dev_test_flag(hdev, HCI_BONDABLE)) {
+		local_dist = SMP_DIST_ENC_KEY | SMP_DIST_SIGN;
+		remote_dist = SMP_DIST_ENC_KEY | SMP_DIST_SIGN;
+	}
+
+	if (hci_dev_test_flag(hdev, HCI_RPA_RESOLVING))
+		remote_dist |= SMP_DIST_ID_KEY;
+
+	if (hci_dev_test_flag(hdev, HCI_PRIVACY))
+		local_dist |= SMP_DIST_ID_KEY;
+
+	if (!rsp) {
+		memset(req, 0, sizeof(*req));
+
+		req->init_key_dist   = local_dist;
+		req->resp_key_dist   = remote_dist;
+		req->max_key_size    = SMP_MAX_ENC_KEY_SIZE;
+
+		smp->remote_key_dist = remote_dist;
+
+		return;
+	}
+
+	memset(rsp, 0, sizeof(*rsp));
+
+	rsp->max_key_size    = SMP_MAX_ENC_KEY_SIZE;
+	rsp->init_key_dist   = req->init_key_dist & remote_dist;
+	rsp->resp_key_dist   = req->resp_key_dist & local_dist;
+
+	smp->remote_key_dist = rsp->init_key_dist;
+}
+
 static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb)
 {
 	struct smp_cmd_pairing rsp, *req = (void *) skb->data;
@@ -952,16 +1730,57 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb)
 		return SMP_UNSPECIFIED;
 
 	/* We didn't start the pairing, so match remote */
-	auth = req->auth_req & AUTH_REQ_MASK;
+	auth = req->auth_req & AUTH_REQ_MASK(hdev);
 
-	if (!test_bit(HCI_BONDABLE, &hdev->dev_flags) &&
+	if (!hci_dev_test_flag(hdev, HCI_BONDABLE) &&
 	    (auth & SMP_AUTH_BONDING))
 		return SMP_PAIRING_NOTSUPP;
 
+	if (hci_dev_test_flag(hdev, HCI_SC_ONLY) && !(auth & SMP_AUTH_SC))
+		return SMP_AUTH_REQUIREMENTS;
+
 	smp->preq[0] = SMP_CMD_PAIRING_REQ;
 	memcpy(&smp->preq[1], req, sizeof(*req));
 	skb_pull(skb, sizeof(*req));
 
+	/* If the remote side's OOB flag is set it means it has
+	 * successfully received our local OOB data - therefore set the
+	 * flag to indicate that local OOB is in use.
+	 */
+	if (req->oob_flag == SMP_OOB_PRESENT)
+		set_bit(SMP_FLAG_LOCAL_OOB, &smp->flags);
+
+	/* SMP over BR/EDR requires special treatment */
+	if (conn->hcon->type == ACL_LINK) {
+		/* We must have a BR/EDR SC link */
+		if (!test_bit(HCI_CONN_AES_CCM, &conn->hcon->flags) &&
+		    !hci_dev_test_flag(hdev, HCI_FORCE_BREDR_SMP))
+			return SMP_CROSS_TRANSP_NOT_ALLOWED;
+
+		set_bit(SMP_FLAG_SC, &smp->flags);
+
+		build_bredr_pairing_cmd(smp, req, &rsp);
+
+		key_size = min(req->max_key_size, rsp.max_key_size);
+		if (check_enc_key_size(conn, key_size))
+			return SMP_ENC_KEY_SIZE;
+
+		/* Clear bits which are generated but not distributed */
+		smp->remote_key_dist &= ~SMP_SC_NO_DIST;
+
+		smp->prsp[0] = SMP_CMD_PAIRING_RSP;
+		memcpy(&smp->prsp[1], &rsp, sizeof(rsp));
+		smp_send_cmd(conn, SMP_CMD_PAIRING_RSP, sizeof(rsp), &rsp);
+
+		smp_distribute_keys(smp);
+		return 0;
+	}
+
+	build_pairing_cmd(conn, req, &rsp, auth);
+
+	if (rsp.auth_req & SMP_AUTH_SC)
+		set_bit(SMP_FLAG_SC, &smp->flags);
+
 	if (conn->hcon->io_capability == HCI_IO_NO_INPUT_OUTPUT)
 		sec_level = BT_SECURITY_MEDIUM;
 	else
@@ -970,7 +1789,7 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb)
 	if (sec_level > conn->hcon->pending_sec_level)
 		conn->hcon->pending_sec_level = sec_level;
 
-	/* If we need MITM check that it can be acheived */
+	/* If we need MITM check that it can be achieved */
 	if (conn->hcon->pending_sec_level >= BT_SECURITY_HIGH) {
 		u8 method;
 
@@ -980,8 +1799,6 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb)
 			return SMP_AUTH_REQUIREMENTS;
 	}
 
-	build_pairing_cmd(conn, req, &rsp, auth);
-
 	key_size = min(req->max_key_size, rsp.max_key_size);
 	if (check_enc_key_size(conn, key_size))
 		return SMP_ENC_KEY_SIZE;
@@ -992,8 +1809,24 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb)
 	memcpy(&smp->prsp[1], &rsp, sizeof(rsp));
 
 	smp_send_cmd(conn, SMP_CMD_PAIRING_RSP, sizeof(rsp), &rsp);
+
+	clear_bit(SMP_FLAG_INITIATOR, &smp->flags);
+
+	/* Strictly speaking we shouldn't allow Pairing Confirm for the
+	 * SC case, however some implementations incorrectly copy RFU auth
+	 * req bits from our security request, which may create a false
+	 * positive SC enablement.
+	 */
 	SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_CONFIRM);
 
+	if (test_bit(SMP_FLAG_SC, &smp->flags)) {
+		SMP_ALLOW_CMD(smp, SMP_CMD_PUBLIC_KEY);
+		/* Clear bits which are generated but not distributed */
+		smp->remote_key_dist &= ~SMP_SC_NO_DIST;
+		/* Wait for Public Key from Initiating Device */
+		return 0;
+	}
+
 	/* Request setup of TK */
 	ret = tk_request(conn, 0, auth, rsp.io_capability, req->io_capability);
 	if (ret)
@@ -1002,11 +1835,66 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb)
 	return 0;
 }
 
+static u8 sc_send_public_key(struct smp_chan *smp)
+{
+	struct hci_dev *hdev = smp->conn->hcon->hdev;
+
+	BT_DBG("");
+
+	if (test_bit(SMP_FLAG_LOCAL_OOB, &smp->flags)) {
+		struct l2cap_chan *chan = hdev->smp_data;
+		struct smp_dev *smp_dev;
+
+		if (!chan || !chan->data)
+			return SMP_UNSPECIFIED;
+
+		smp_dev = chan->data;
+
+		memcpy(smp->local_pk, smp_dev->local_pk, 64);
+		memcpy(smp->local_sk, smp_dev->local_sk, 32);
+		memcpy(smp->lr, smp_dev->local_rand, 16);
+
+		if (smp_dev->debug_key)
+			set_bit(SMP_FLAG_DEBUG_KEY, &smp->flags);
+
+		goto done;
+	}
+
+	if (hci_dev_test_flag(hdev, HCI_USE_DEBUG_KEYS)) {
+		BT_DBG("Using debug keys");
+		memcpy(smp->local_pk, debug_pk, 64);
+		memcpy(smp->local_sk, debug_sk, 32);
+		set_bit(SMP_FLAG_DEBUG_KEY, &smp->flags);
+	} else {
+		while (true) {
+			/* Generate local key pair for Secure Connections */
+			if (!ecc_make_key(smp->local_pk, smp->local_sk))
+				return SMP_UNSPECIFIED;
+
+			/* This is unlikely, but we need to check that
+			 * we didn't accidentially generate a debug key.
+			 */
+			if (memcmp(smp->local_sk, debug_sk, 32))
+				break;
+		}
+	}
+
+done:
+	SMP_DBG("Local Public Key X: %32phN", smp->local_pk);
+	SMP_DBG("Local Public Key Y: %32phN", smp->local_pk + 32);
+	SMP_DBG("Local Private Key:  %32phN", smp->local_sk);
+
+	smp_send_cmd(smp->conn, SMP_CMD_PUBLIC_KEY, 64, smp->local_pk);
+
+	return 0;
+}
+
 static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb)
 {
 	struct smp_cmd_pairing *req, *rsp = (void *) skb->data;
 	struct l2cap_chan *chan = conn->smp;
 	struct smp_chan *smp = chan->data;
+	struct hci_dev *hdev = conn->hcon->hdev;
 	u8 key_size, auth;
 	int ret;
 
@@ -1026,9 +1914,40 @@ 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;
 
-	auth = rsp->auth_req & AUTH_REQ_MASK;
+	auth = rsp->auth_req & AUTH_REQ_MASK(hdev);
+
+	if (hci_dev_test_flag(hdev, HCI_SC_ONLY) && !(auth & SMP_AUTH_SC))
+		return SMP_AUTH_REQUIREMENTS;
+
+	/* If the remote side's OOB flag is set it means it has
+	 * successfully received our local OOB data - therefore set the
+	 * flag to indicate that local OOB is in use.
+	 */
+	if (rsp->oob_flag == SMP_OOB_PRESENT)
+		set_bit(SMP_FLAG_LOCAL_OOB, &smp->flags);
+
+	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;
+
+	/* For BR/EDR this means we're done and can start phase 3 */
+	if (conn->hcon->type == ACL_LINK) {
+		/* Clear bits which are generated but not distributed */
+		smp->remote_key_dist &= ~SMP_SC_NO_DIST;
+		smp_distribute_keys(smp);
+		return 0;
+	}
 
-	/* If we need MITM check that it can be acheived */
+	if ((req->auth_req & SMP_AUTH_SC) && (auth & SMP_AUTH_SC))
+		set_bit(SMP_FLAG_SC, &smp->flags);
+	else if (conn->hcon->pending_sec_level > BT_SECURITY_HIGH)
+		conn->hcon->pending_sec_level = BT_SECURITY_HIGH;
+
+	/* If we need MITM check that it can be achieved */
 	if (conn->hcon->pending_sec_level >= BT_SECURITY_HIGH) {
 		u8 method;
 
@@ -1040,14 +1959,18 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb)
 
 	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 (test_bit(SMP_FLAG_SC, &smp->flags)) {
+		/* Clear bits which are generated but not distributed */
+		smp->remote_key_dist &= ~SMP_SC_NO_DIST;
+		SMP_ALLOW_CMD(smp, SMP_CMD_PUBLIC_KEY);
+		return sc_send_public_key(smp);
+	}
+
 	auth |= req->auth_req;
 
 	ret = tk_request(conn, 0, auth, req->io_capability, rsp->io_capability);
@@ -1063,6 +1986,65 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb)
 	return 0;
 }
 
+static u8 sc_check_confirm(struct smp_chan *smp)
+{
+	struct l2cap_conn *conn = smp->conn;
+
+	BT_DBG("");
+
+	if (smp->method == REQ_PASSKEY || smp->method == DSP_PASSKEY)
+		return sc_passkey_round(smp, SMP_CMD_PAIRING_CONFIRM);
+
+	if (conn->hcon->out) {
+		smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd),
+			     smp->prnd);
+		SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM);
+	}
+
+	return 0;
+}
+
+/* Work-around for some implementations that incorrectly copy RFU bits
+ * from our security request and thereby create the impression that
+ * we're doing SC when in fact the remote doesn't support it.
+ */
+static int fixup_sc_false_positive(struct smp_chan *smp)
+{
+	struct l2cap_conn *conn = smp->conn;
+	struct hci_conn *hcon = conn->hcon;
+	struct hci_dev *hdev = hcon->hdev;
+	struct smp_cmd_pairing *req, *rsp;
+	u8 auth;
+
+	/* The issue is only observed when we're in slave role */
+	if (hcon->out)
+		return SMP_UNSPECIFIED;
+
+	if (hci_dev_test_flag(hdev, HCI_SC_ONLY)) {
+		BT_ERR("Refusing SMP SC -> legacy fallback in SC-only mode");
+		return SMP_UNSPECIFIED;
+	}
+
+	BT_ERR("Trying to fall back to legacy SMP");
+
+	req = (void *) &smp->preq[1];
+	rsp = (void *) &smp->prsp[1];
+
+	/* Rebuild key dist flags which may have been cleared for SC */
+	smp->remote_key_dist = (req->init_key_dist & rsp->resp_key_dist);
+
+	auth = req->auth_req & AUTH_REQ_MASK(hdev);
+
+	if (tk_request(conn, 0, auth, rsp->io_capability, req->io_capability)) {
+		BT_ERR("Failed to fall back to legacy SMP");
+		return SMP_UNSPECIFIED;
+	}
+
+	clear_bit(SMP_FLAG_SC, &smp->flags);
+
+	return 0;
+}
+
 static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb)
 {
 	struct l2cap_chan *chan = conn->smp;
@@ -1076,6 +2058,20 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb)
 	memcpy(smp->pcnf, skb->data, sizeof(smp->pcnf));
 	skb_pull(skb, sizeof(smp->pcnf));
 
+	if (test_bit(SMP_FLAG_SC, &smp->flags)) {
+		int ret;
+
+		/* Public Key exchange must happen before any other steps */
+		if (test_bit(SMP_FLAG_REMOTE_PK, &smp->flags))
+			return sc_check_confirm(smp);
+
+		BT_ERR("Unexpected SMP Pairing Confirm");
+
+		ret = fixup_sc_false_positive(smp);
+		if (ret)
+			return ret;
+	}
+
 	if (conn->hcon->out) {
 		smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd),
 			     smp->prnd);
@@ -1085,8 +2081,8 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb)
 
 	if (test_bit(SMP_FLAG_TK_VALID, &smp->flags))
 		return smp_confirm(smp);
-	else
-		set_bit(SMP_FLAG_CFM_PENDING, &smp->flags);
+
+	set_bit(SMP_FLAG_CFM_PENDING, &smp->flags);
 
 	return 0;
 }
@@ -1095,6 +2091,10 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb)
 {
 	struct l2cap_chan *chan = conn->smp;
 	struct smp_chan *smp = chan->data;
+	struct hci_conn *hcon = conn->hcon;
+	u8 *pkax, *pkbx, *na, *nb;
+	u32 passkey;
+	int err;
 
 	BT_DBG("conn %p", conn);
 
@@ -1104,7 +2104,75 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb)
 	memcpy(smp->rrnd, skb->data, sizeof(smp->rrnd));
 	skb_pull(skb, sizeof(smp->rrnd));
 
-	return smp_random(smp);
+	if (!test_bit(SMP_FLAG_SC, &smp->flags))
+		return smp_random(smp);
+
+	if (hcon->out) {
+		pkax = smp->local_pk;
+		pkbx = smp->remote_pk;
+		na   = smp->prnd;
+		nb   = smp->rrnd;
+	} else {
+		pkax = smp->remote_pk;
+		pkbx = smp->local_pk;
+		na   = smp->rrnd;
+		nb   = smp->prnd;
+	}
+
+	if (smp->method == REQ_OOB) {
+		if (!hcon->out)
+			smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM,
+				     sizeof(smp->prnd), smp->prnd);
+		SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK);
+		goto mackey_and_ltk;
+	}
+
+	/* Passkey entry has special treatment */
+	if (smp->method == REQ_PASSKEY || smp->method == DSP_PASSKEY)
+		return sc_passkey_round(smp, SMP_CMD_PAIRING_RANDOM);
+
+	if (hcon->out) {
+		u8 cfm[16];
+
+		err = smp_f4(smp->tfm_cmac, smp->remote_pk, smp->local_pk,
+			     smp->rrnd, 0, cfm);
+		if (err)
+			return SMP_UNSPECIFIED;
+
+		if (memcmp(smp->pcnf, cfm, 16))
+			return SMP_CONFIRM_FAILED;
+	} else {
+		smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd),
+			     smp->prnd);
+		SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK);
+	}
+
+mackey_and_ltk:
+	/* Generate MacKey and LTK */
+	err = sc_mackey_and_ltk(smp, smp->mackey, smp->tk);
+	if (err)
+		return SMP_UNSPECIFIED;
+
+	if (smp->method == JUST_WORKS || smp->method == REQ_OOB) {
+		if (hcon->out) {
+			sc_dhkey_check(smp);
+			SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK);
+		}
+		return 0;
+	}
+
+	err = smp_g2(smp->tfm_cmac, pkax, pkbx, na, nb, &passkey);
+	if (err)
+		return SMP_UNSPECIFIED;
+
+	err = mgmt_user_confirm_request(hcon->hdev, &hcon->dst, hcon->type,
+					hcon->dst_type, passkey, 0);
+	if (err)
+		return SMP_UNSPECIFIED;
+
+	set_bit(SMP_FLAG_WAIT_USER, &smp->flags);
+
+	return 0;
 }
 
 static bool smp_ltk_encrypt(struct l2cap_conn *conn, u8 sec_level)
@@ -1112,8 +2180,7 @@ static bool 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,
-				   hcon->role);
+	key = hci_find_ltk(hcon->hdev, &hcon->dst, hcon->dst_type, hcon->role);
 	if (!key)
 		return false;
 
@@ -1132,20 +2199,21 @@ static bool smp_ltk_encrypt(struct l2cap_conn *conn, u8 sec_level)
 	return true;
 }
 
-bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level)
+bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level,
+			     enum smp_key_pref key_pref)
 {
 	if (sec_level == BT_SECURITY_LOW)
 		return true;
 
-	/* If we're encrypted with an STK always claim insufficient
-	 * security. This way we allow the connection to be re-encrypted
-	 * with an LTK, even if the LTK provides the same level of
-	 * security. Only exception is if we don't have an LTK (e.g.
-	 * because of key distribution bits).
+	/* If we're encrypted with an STK but the caller prefers using
+	 * LTK claim insufficient security. This way we allow the
+	 * connection to be re-encrypted with an LTK, even if the LTK
+	 * provides the same level of security. Only exception is if we
+	 * don't have an LTK (e.g. because of key distribution bits).
 	 */
-	if (test_bit(HCI_CONN_STK_ENCRYPT, &hcon->flags) &&
-	    hci_find_ltk_by_addr(hcon->hdev, &hcon->dst, hcon->dst_type,
-				 hcon->role))
+	if (key_pref == SMP_USE_LTK &&
+	    test_bit(HCI_CONN_STK_ENCRYPT, &hcon->flags) &&
+	    hci_find_ltk(hcon->hdev, &hcon->dst, hcon->dst_type, hcon->role))
 		return false;
 
 	if (hcon->sec_level >= sec_level)
@@ -1159,6 +2227,7 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb)
 	struct smp_cmd_security_req *rp = (void *) skb->data;
 	struct smp_cmd_pairing cp;
 	struct hci_conn *hcon = conn->hcon;
+	struct hci_dev *hdev = hcon->hdev;
 	struct smp_chan *smp;
 	u8 sec_level, auth;
 
@@ -1170,14 +2239,17 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb)
 	if (hcon->role != HCI_ROLE_MASTER)
 		return SMP_CMD_NOTSUPP;
 
-	auth = rp->auth_req & AUTH_REQ_MASK;
+	auth = rp->auth_req & AUTH_REQ_MASK(hdev);
+
+	if (hci_dev_test_flag(hdev, HCI_SC_ONLY) && !(auth & SMP_AUTH_SC))
+		return SMP_AUTH_REQUIREMENTS;
 
 	if (hcon->io_capability == HCI_IO_NO_INPUT_OUTPUT)
 		sec_level = BT_SECURITY_MEDIUM;
 	else
 		sec_level = authreq_to_seclevel(auth);
 
-	if (smp_sufficient_security(hcon, sec_level))
+	if (smp_sufficient_security(hcon, sec_level, SMP_USE_LTK))
 		return 0;
 
 	if (sec_level > hcon->pending_sec_level)
@@ -1190,7 +2262,7 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb)
 	if (!smp)
 		return SMP_UNSPECIFIED;
 
-	if (!test_bit(HCI_BONDABLE, &hcon->hdev->dev_flags) &&
+	if (!hci_dev_test_flag(hdev, HCI_BONDABLE) &&
 	    (auth & SMP_AUTH_BONDING))
 		return SMP_PAIRING_NOTSUPP;
 
@@ -1224,10 +2296,10 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level)
 
 	chan = conn->smp;
 
-	if (!test_bit(HCI_LE_ENABLED, &hcon->hdev->dev_flags))
+	if (!hci_dev_test_flag(hcon->hdev, HCI_LE_ENABLED))
 		return 1;
 
-	if (smp_sufficient_security(hcon, sec_level))
+	if (smp_sufficient_security(hcon, sec_level, SMP_USE_LTK))
 		return 1;
 
 	if (sec_level > hcon->pending_sec_level)
@@ -1253,6 +2325,9 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level)
 
 	authreq = seclevel_to_authreq(sec_level);
 
+	if (hci_dev_test_flag(hcon->hdev, HCI_SC_ENABLED))
+		authreq |= SMP_AUTH_SC;
+
 	/* Require MITM if IO Capability allows or the security level
 	 * requires it.
 	 */
@@ -1329,7 +2404,6 @@ static int smp_cmd_master_ident(struct l2cap_conn *conn, struct sk_buff *skb)
 
 	skb_pull(skb, sizeof(*rp));
 
-	hci_dev_lock(hdev);
 	authenticated = (hcon->sec_level == BT_SECURITY_HIGH);
 	ltk = hci_add_ltk(hdev, &hcon->dst, hcon->dst_type, SMP_LTK,
 			  authenticated, smp->tk, smp->enc_key_size,
@@ -1337,7 +2411,6 @@ static int smp_cmd_master_ident(struct l2cap_conn *conn, struct sk_buff *skb)
 	smp->ltk = ltk;
 	if (!(smp->remote_key_dist & KEY_DIST_MASK))
 		smp_distribute_keys(smp);
-	hci_dev_unlock(hdev);
 
 	return 0;
 }
@@ -1384,16 +2457,18 @@ static int smp_cmd_ident_addr_info(struct l2cap_conn *conn,
 
 	skb_pull(skb, sizeof(*info));
 
-	hci_dev_lock(hcon->hdev);
-
 	/* 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.
+	 *
+	 * The Identity Address must also be a Static Random or Public
+	 * Address, which hci_is_identity_address() checks for.
 	 */
-	if (!bacmp(&info->bdaddr, BDADDR_ANY)) {
+	if (!bacmp(&info->bdaddr, BDADDR_ANY) ||
+	    !hci_is_identity_address(&info->bdaddr, info->addr_type)) {
 		BT_ERR("Ignoring IRK with no identity address");
 		goto distribute;
 	}
@@ -1413,8 +2488,6 @@ distribute:
 	if (!(smp->remote_key_dist & KEY_DIST_MASK))
 		smp_distribute_keys(smp);
 
-	hci_dev_unlock(hcon->hdev);
-
 	return 0;
 }
 
@@ -1423,7 +2496,6 @@ static int smp_cmd_sign_info(struct l2cap_conn *conn, struct sk_buff *skb)
 	struct smp_cmd_sign_info *rp = (void *) skb->data;
 	struct l2cap_chan *chan = conn->smp;
 	struct smp_chan *smp = chan->data;
-	struct hci_dev *hdev = conn->hcon->hdev;
 	struct smp_csrk *csrk;
 
 	BT_DBG("conn %p", conn);
@@ -1436,15 +2508,249 @@ static int smp_cmd_sign_info(struct l2cap_conn *conn, struct sk_buff *skb)
 
 	skb_pull(skb, sizeof(*rp));
 
-	hci_dev_lock(hdev);
 	csrk = kzalloc(sizeof(*csrk), GFP_KERNEL);
 	if (csrk) {
-		csrk->master = 0x01;
+		if (conn->hcon->sec_level > BT_SECURITY_MEDIUM)
+			csrk->type = MGMT_CSRK_REMOTE_AUTHENTICATED;
+		else
+			csrk->type = MGMT_CSRK_REMOTE_UNAUTHENTICATED;
 		memcpy(csrk->val, rp->csrk, sizeof(csrk->val));
 	}
 	smp->csrk = csrk;
 	smp_distribute_keys(smp);
-	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static u8 sc_select_method(struct smp_chan *smp)
+{
+	struct l2cap_conn *conn = smp->conn;
+	struct hci_conn *hcon = conn->hcon;
+	struct smp_cmd_pairing *local, *remote;
+	u8 local_mitm, remote_mitm, local_io, remote_io, method;
+
+	if (test_bit(SMP_FLAG_REMOTE_OOB, &smp->flags) ||
+	    test_bit(SMP_FLAG_LOCAL_OOB, &smp->flags))
+		return REQ_OOB;
+
+	/* The preq/prsp contain the raw Pairing Request/Response PDUs
+	 * which are needed as inputs to some crypto functions. To get
+	 * the "struct smp_cmd_pairing" from them we need to skip the
+	 * first byte which contains the opcode.
+	 */
+	if (hcon->out) {
+		local = (void *) &smp->preq[1];
+		remote = (void *) &smp->prsp[1];
+	} else {
+		local = (void *) &smp->prsp[1];
+		remote = (void *) &smp->preq[1];
+	}
+
+	local_io = local->io_capability;
+	remote_io = remote->io_capability;
+
+	local_mitm = (local->auth_req & SMP_AUTH_MITM);
+	remote_mitm = (remote->auth_req & SMP_AUTH_MITM);
+
+	/* If either side wants MITM, look up the method from the table,
+	 * otherwise use JUST WORKS.
+	 */
+	if (local_mitm || remote_mitm)
+		method = get_auth_method(smp, local_io, remote_io);
+	else
+		method = JUST_WORKS;
+
+	/* Don't confirm locally initiated pairing attempts */
+	if (method == JUST_CFM && test_bit(SMP_FLAG_INITIATOR, &smp->flags))
+		method = JUST_WORKS;
+
+	return method;
+}
+
+static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb)
+{
+	struct smp_cmd_public_key *key = (void *) skb->data;
+	struct hci_conn *hcon = conn->hcon;
+	struct l2cap_chan *chan = conn->smp;
+	struct smp_chan *smp = chan->data;
+	struct hci_dev *hdev = hcon->hdev;
+	struct smp_cmd_pairing_confirm cfm;
+	int err;
+
+	BT_DBG("conn %p", conn);
+
+	if (skb->len < sizeof(*key))
+		return SMP_INVALID_PARAMS;
+
+	memcpy(smp->remote_pk, key, 64);
+
+	if (test_bit(SMP_FLAG_REMOTE_OOB, &smp->flags)) {
+		err = smp_f4(smp->tfm_cmac, smp->remote_pk, smp->remote_pk,
+			     smp->rr, 0, cfm.confirm_val);
+		if (err)
+			return SMP_UNSPECIFIED;
+
+		if (memcmp(cfm.confirm_val, smp->pcnf, 16))
+			return SMP_CONFIRM_FAILED;
+	}
+
+	/* Non-initiating device sends its public key after receiving
+	 * the key from the initiating device.
+	 */
+	if (!hcon->out) {
+		err = sc_send_public_key(smp);
+		if (err)
+			return err;
+	}
+
+	SMP_DBG("Remote Public Key X: %32phN", smp->remote_pk);
+	SMP_DBG("Remote Public Key Y: %32phN", smp->remote_pk + 32);
+
+	if (!ecdh_shared_secret(smp->remote_pk, smp->local_sk, smp->dhkey))
+		return SMP_UNSPECIFIED;
+
+	SMP_DBG("DHKey %32phN", smp->dhkey);
+
+	set_bit(SMP_FLAG_REMOTE_PK, &smp->flags);
+
+	smp->method = sc_select_method(smp);
+
+	BT_DBG("%s selected method 0x%02x", hdev->name, smp->method);
+
+	/* JUST_WORKS and JUST_CFM result in an unauthenticated key */
+	if (smp->method == JUST_WORKS || smp->method == JUST_CFM)
+		hcon->pending_sec_level = BT_SECURITY_MEDIUM;
+	else
+		hcon->pending_sec_level = BT_SECURITY_FIPS;
+
+	if (!memcmp(debug_pk, smp->remote_pk, 64))
+		set_bit(SMP_FLAG_DEBUG_KEY, &smp->flags);
+
+	if (smp->method == DSP_PASSKEY) {
+		get_random_bytes(&hcon->passkey_notify,
+				 sizeof(hcon->passkey_notify));
+		hcon->passkey_notify %= 1000000;
+		hcon->passkey_entered = 0;
+		smp->passkey_round = 0;
+		if (mgmt_user_passkey_notify(hdev, &hcon->dst, hcon->type,
+					     hcon->dst_type,
+					     hcon->passkey_notify,
+					     hcon->passkey_entered))
+			return SMP_UNSPECIFIED;
+		SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_CONFIRM);
+		return sc_passkey_round(smp, SMP_CMD_PUBLIC_KEY);
+	}
+
+	if (smp->method == REQ_OOB) {
+		if (hcon->out)
+			smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM,
+				     sizeof(smp->prnd), smp->prnd);
+
+		SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM);
+
+		return 0;
+	}
+
+	if (hcon->out)
+		SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_CONFIRM);
+
+	if (smp->method == REQ_PASSKEY) {
+		if (mgmt_user_passkey_request(hdev, &hcon->dst, hcon->type,
+					      hcon->dst_type))
+			return SMP_UNSPECIFIED;
+		SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_CONFIRM);
+		set_bit(SMP_FLAG_WAIT_USER, &smp->flags);
+		return 0;
+	}
+
+	/* The Initiating device waits for the non-initiating device to
+	 * send the confirm value.
+	 */
+	if (conn->hcon->out)
+		return 0;
+
+	err = smp_f4(smp->tfm_cmac, smp->local_pk, smp->remote_pk, smp->prnd,
+		     0, cfm.confirm_val);
+	if (err)
+		return SMP_UNSPECIFIED;
+
+	smp_send_cmd(conn, SMP_CMD_PAIRING_CONFIRM, sizeof(cfm), &cfm);
+	SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM);
+
+	return 0;
+}
+
+static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb)
+{
+	struct smp_cmd_dhkey_check *check = (void *) skb->data;
+	struct l2cap_chan *chan = conn->smp;
+	struct hci_conn *hcon = conn->hcon;
+	struct smp_chan *smp = chan->data;
+	u8 a[7], b[7], *local_addr, *remote_addr;
+	u8 io_cap[3], r[16], e[16];
+	int err;
+
+	BT_DBG("conn %p", conn);
+
+	if (skb->len < sizeof(*check))
+		return SMP_INVALID_PARAMS;
+
+	memcpy(a, &hcon->init_addr, 6);
+	memcpy(b, &hcon->resp_addr, 6);
+	a[6] = hcon->init_addr_type;
+	b[6] = hcon->resp_addr_type;
+
+	if (hcon->out) {
+		local_addr = a;
+		remote_addr = b;
+		memcpy(io_cap, &smp->prsp[1], 3);
+	} else {
+		local_addr = b;
+		remote_addr = a;
+		memcpy(io_cap, &smp->preq[1], 3);
+	}
+
+	memset(r, 0, sizeof(r));
+
+	if (smp->method == REQ_PASSKEY || smp->method == DSP_PASSKEY)
+		put_unaligned_le32(hcon->passkey_notify, r);
+	else if (smp->method == REQ_OOB)
+		memcpy(r, smp->lr, 16);
+
+	err = smp_f6(smp->tfm_cmac, smp->mackey, smp->rrnd, smp->prnd, r,
+		     io_cap, remote_addr, local_addr, e);
+	if (err)
+		return SMP_UNSPECIFIED;
+
+	if (memcmp(check->e, e, 16))
+		return SMP_DHKEY_CHECK_FAILED;
+
+	if (!hcon->out) {
+		if (test_bit(SMP_FLAG_WAIT_USER, &smp->flags)) {
+			set_bit(SMP_FLAG_DHKEY_PENDING, &smp->flags);
+			return 0;
+		}
+
+		/* Slave sends DHKey check as response to master */
+		sc_dhkey_check(smp);
+	}
+
+	sc_add_ltk(smp);
+
+	if (hcon->out) {
+		hci_le_start_enc(hcon, 0, 0, smp->tk);
+		hcon->enc_key_size = smp->enc_key_size;
+	}
+
+	return 0;
+}
+
+static int smp_cmd_keypress_notify(struct l2cap_conn *conn,
+				   struct sk_buff *skb)
+{
+	struct smp_cmd_keypress_notify *kp = (void *) skb->data;
+
+	BT_DBG("value 0x%02x", kp->value);
 
 	return 0;
 }
@@ -1457,15 +2763,10 @@ static int smp_sig_channel(struct l2cap_chan *chan, struct sk_buff *skb)
 	__u8 code, reason;
 	int err = 0;
 
-	if (hcon->type != LE_LINK) {
-		kfree_skb(skb);
-		return 0;
-	}
-
 	if (skb->len < 1)
 		return -EILSEQ;
 
-	if (!test_bit(HCI_LE_ENABLED, &hcon->hdev->dev_flags)) {
+	if (!hci_dev_test_flag(hcon->hdev, HCI_LE_ENABLED)) {
 		reason = SMP_PAIRING_NOTSUPP;
 		goto done;
 	}
@@ -1533,6 +2834,18 @@ static int smp_sig_channel(struct l2cap_chan *chan, struct sk_buff *skb)
 		reason = smp_cmd_sign_info(conn, skb);
 		break;
 
+	case SMP_CMD_PUBLIC_KEY:
+		reason = smp_cmd_public_key(conn, skb);
+		break;
+
+	case SMP_CMD_DHKEY_CHECK:
+		reason = smp_cmd_dhkey_check(conn, skb);
+		break;
+
+	case SMP_CMD_KEYPRESS_NOTIFY:
+		reason = smp_cmd_keypress_notify(conn, skb);
+		break;
+
 	default:
 		BT_DBG("Unknown command code 0x%2.2x", code);
 		reason = SMP_CMD_NOTSUPP;
@@ -1568,6 +2881,74 @@ static void smp_teardown_cb(struct l2cap_chan *chan, int err)
 	l2cap_chan_put(chan);
 }
 
+static void bredr_pairing(struct l2cap_chan *chan)
+{
+	struct l2cap_conn *conn = chan->conn;
+	struct hci_conn *hcon = conn->hcon;
+	struct hci_dev *hdev = hcon->hdev;
+	struct smp_cmd_pairing req;
+	struct smp_chan *smp;
+
+	BT_DBG("chan %p", chan);
+
+	/* Only new pairings are interesting */
+	if (!test_bit(HCI_CONN_NEW_LINK_KEY, &hcon->flags))
+		return;
+
+	/* Don't bother if we're not encrypted */
+	if (!test_bit(HCI_CONN_ENCRYPT, &hcon->flags))
+		return;
+
+	/* Only master may initiate SMP over BR/EDR */
+	if (hcon->role != HCI_ROLE_MASTER)
+		return;
+
+	/* Secure Connections support must be enabled */
+	if (!hci_dev_test_flag(hdev, HCI_SC_ENABLED))
+		return;
+
+	/* BR/EDR must use Secure Connections for SMP */
+	if (!test_bit(HCI_CONN_AES_CCM, &hcon->flags) &&
+	    !hci_dev_test_flag(hdev, HCI_FORCE_BREDR_SMP))
+		return;
+
+	/* If our LE support is not enabled don't do anything */
+	if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED))
+		return;
+
+	/* Don't bother if remote LE support is not enabled */
+	if (!lmp_host_le_capable(hcon))
+		return;
+
+	/* Remote must support SMP fixed chan for BR/EDR */
+	if (!(conn->remote_fixed_chan & L2CAP_FC_SMP_BREDR))
+		return;
+
+	/* Don't bother if SMP is already ongoing */
+	if (chan->data)
+		return;
+
+	smp = smp_chan_create(conn);
+	if (!smp) {
+		BT_ERR("%s unable to create SMP context for BR/EDR",
+		       hdev->name);
+		return;
+	}
+
+	set_bit(SMP_FLAG_SC, &smp->flags);
+
+	BT_DBG("%s starting SMP over BR/EDR", hdev->name);
+
+	/* Prepare and send the BR/EDR SMP Pairing Request */
+	build_bredr_pairing_cmd(smp, &req, NULL);
+
+	smp->preq[0] = SMP_CMD_PAIRING_REQ;
+	memcpy(&smp->preq[1], &req, sizeof(req));
+
+	smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(req), &req);
+	SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP);
+}
+
 static void smp_resume_cb(struct l2cap_chan *chan)
 {
 	struct smp_chan *smp = chan->data;
@@ -1576,6 +2957,11 @@ static void smp_resume_cb(struct l2cap_chan *chan)
 
 	BT_DBG("chan %p", chan);
 
+	if (hcon->type == ACL_LINK) {
+		bredr_pairing(chan);
+		return;
+	}
+
 	if (!smp)
 		return;
 
@@ -1590,11 +2976,15 @@ static void smp_resume_cb(struct l2cap_chan *chan)
 static void smp_ready_cb(struct l2cap_chan *chan)
 {
 	struct l2cap_conn *conn = chan->conn;
+	struct hci_conn *hcon = conn->hcon;
 
 	BT_DBG("chan %p", chan);
 
 	conn->smp = chan;
 	l2cap_chan_hold(chan);
+
+	if (hcon->type == ACL_LINK && test_bit(HCI_CONN_ENCRYPT, &hcon->flags))
+		bredr_pairing(chan);
 }
 
 static int smp_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb)
@@ -1627,7 +3017,7 @@ static struct sk_buff *smp_alloc_skb_cb(struct l2cap_chan *chan,
 		return ERR_PTR(-ENOMEM);
 
 	skb->priority = HCI_PRIO_MAX;
-	bt_cb(skb)->chan = chan;
+	bt_cb(skb)->l2cap.chan = chan;
 
 	return skb;
 }
@@ -1647,7 +3037,6 @@ static const struct l2cap_ops smp_chan_ops = {
 	.suspend		= l2cap_chan_no_suspend,
 	.set_shutdown		= l2cap_chan_no_set_shutdown,
 	.get_sndtimeo		= l2cap_chan_no_get_sndtimeo,
-	.memcpy_fromiovec	= l2cap_chan_no_memcpy_fromiovec,
 };
 
 static inline struct l2cap_chan *smp_new_conn_cb(struct l2cap_chan *pchan)
@@ -1668,6 +3057,13 @@ static inline struct l2cap_chan *smp_new_conn_cb(struct l2cap_chan *pchan)
 	chan->omtu	= pchan->omtu;
 	chan->mode	= pchan->mode;
 
+	/* Other L2CAP channels may request SMP routines in order to
+	 * change the security level. This means that the SMP channel
+	 * lock must be considered in its own category to avoid lockdep
+	 * warnings.
+	 */
+	atomic_set(&chan->nesting, L2CAP_NESTING_SMP);
+
 	BT_DBG("created chan %p", chan);
 
 	return chan;
@@ -1689,63 +3085,586 @@ static const struct l2cap_ops smp_root_chan_ops = {
 	.resume			= l2cap_chan_no_resume,
 	.set_shutdown		= l2cap_chan_no_set_shutdown,
 	.get_sndtimeo		= l2cap_chan_no_get_sndtimeo,
-	.memcpy_fromiovec	= l2cap_chan_no_memcpy_fromiovec,
 };
 
-int smp_register(struct hci_dev *hdev)
+static struct l2cap_chan *smp_add_cid(struct hci_dev *hdev, u16 cid)
 {
 	struct l2cap_chan *chan;
-	struct crypto_blkcipher	*tfm_aes;
+	struct smp_dev *smp;
+	struct crypto_blkcipher *tfm_aes;
+	struct crypto_hash *tfm_cmac;
 
-	BT_DBG("%s", hdev->name);
+	if (cid == L2CAP_CID_SMP_BREDR) {
+		smp = NULL;
+		goto create_chan;
+	}
+
+	smp = kzalloc(sizeof(*smp), GFP_KERNEL);
+	if (!smp)
+		return ERR_PTR(-ENOMEM);
 
 	tfm_aes = crypto_alloc_blkcipher("ecb(aes)", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(tfm_aes)) {
-		int err = PTR_ERR(tfm_aes);
-		BT_ERR("Unable to create crypto context");
-		return err;
+		BT_ERR("Unable to create ECB crypto context");
+		kzfree(smp);
+		return ERR_CAST(tfm_aes);
+	}
+
+	tfm_cmac = crypto_alloc_hash("cmac(aes)", 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(tfm_cmac)) {
+		BT_ERR("Unable to create CMAC crypto context");
+		crypto_free_blkcipher(tfm_aes);
+		kzfree(smp);
+		return ERR_CAST(tfm_cmac);
 	}
 
+	smp->tfm_aes = tfm_aes;
+	smp->tfm_cmac = tfm_cmac;
+
+create_chan:
 	chan = l2cap_chan_create();
 	if (!chan) {
-		crypto_free_blkcipher(tfm_aes);
-		return -ENOMEM;
+		if (smp) {
+			crypto_free_blkcipher(smp->tfm_aes);
+			crypto_free_hash(smp->tfm_cmac);
+			kzfree(smp);
+		}
+		return ERR_PTR(-ENOMEM);
 	}
 
-	chan->data = tfm_aes;
+	chan->data = smp;
 
-	l2cap_add_scid(chan, L2CAP_CID_SMP);
+	l2cap_add_scid(chan, cid);
 
 	l2cap_chan_set_defaults(chan);
 
-	bacpy(&chan->src, &hdev->bdaddr);
-	chan->src_type = BDADDR_LE_PUBLIC;
+	if (cid == L2CAP_CID_SMP) {
+		u8 bdaddr_type;
+
+		hci_copy_identity_address(hdev, &chan->src, &bdaddr_type);
+
+		if (bdaddr_type == ADDR_LE_DEV_PUBLIC)
+			chan->src_type = BDADDR_LE_PUBLIC;
+		else
+			chan->src_type = BDADDR_LE_RANDOM;
+	} else {
+		bacpy(&chan->src, &hdev->bdaddr);
+		chan->src_type = BDADDR_BREDR;
+	}
+
 	chan->state = BT_LISTEN;
 	chan->mode = L2CAP_MODE_BASIC;
 	chan->imtu = L2CAP_DEFAULT_MTU;
 	chan->ops = &smp_root_chan_ops;
 
+	/* Set correct nesting level for a parent/listening channel */
+	atomic_set(&chan->nesting, L2CAP_NESTING_PARENT);
+
+	return chan;
+}
+
+static void smp_del_chan(struct l2cap_chan *chan)
+{
+	struct smp_dev *smp;
+
+	BT_DBG("chan %p", chan);
+
+	smp = chan->data;
+	if (smp) {
+		chan->data = NULL;
+		if (smp->tfm_aes)
+			crypto_free_blkcipher(smp->tfm_aes);
+		if (smp->tfm_cmac)
+			crypto_free_hash(smp->tfm_cmac);
+		kzfree(smp);
+	}
+
+	l2cap_chan_put(chan);
+}
+
+static ssize_t force_bredr_smp_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] = hci_dev_test_flag(hdev, HCI_FORCE_BREDR_SMP) ? 'Y': 'N';
+	buf[1] = '\n';
+	buf[2] = '\0';
+	return simple_read_from_buffer(user_buf, count, ppos, buf, 2);
+}
+
+static ssize_t force_bredr_smp_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 (copy_from_user(buf, user_buf, buf_size))
+		return -EFAULT;
+
+	buf[buf_size] = '\0';
+	if (strtobool(buf, &enable))
+		return -EINVAL;
+
+	if (enable == hci_dev_test_flag(hdev, HCI_FORCE_BREDR_SMP))
+		return -EALREADY;
+
+	if (enable) {
+		struct l2cap_chan *chan;
+
+		chan = smp_add_cid(hdev, L2CAP_CID_SMP_BREDR);
+		if (IS_ERR(chan))
+			return PTR_ERR(chan);
+
+		hdev->smp_bredr_data = chan;
+	} else {
+		struct l2cap_chan *chan;
+
+		chan = hdev->smp_bredr_data;
+		hdev->smp_bredr_data = NULL;
+		smp_del_chan(chan);
+	}
+
+	hci_dev_change_flag(hdev, HCI_FORCE_BREDR_SMP);
+
+	return count;
+}
+
+static const struct file_operations force_bredr_smp_fops = {
+	.open		= simple_open,
+	.read		= force_bredr_smp_read,
+	.write		= force_bredr_smp_write,
+	.llseek		= default_llseek,
+};
+
+int smp_register(struct hci_dev *hdev)
+{
+	struct l2cap_chan *chan;
+
+	BT_DBG("%s", hdev->name);
+
+	/* If the controller does not support Low Energy operation, then
+	 * there is also no need to register any SMP channel.
+	 */
+	if (!lmp_le_capable(hdev))
+		return 0;
+
+	if (WARN_ON(hdev->smp_data)) {
+		chan = hdev->smp_data;
+		hdev->smp_data = NULL;
+		smp_del_chan(chan);
+	}
+
+	chan = smp_add_cid(hdev, L2CAP_CID_SMP);
+	if (IS_ERR(chan))
+		return PTR_ERR(chan);
+
 	hdev->smp_data = chan;
 
+	/* If the controller does not support BR/EDR Secure Connections
+	 * feature, then the BR/EDR SMP channel shall not be present.
+	 *
+	 * To test this with Bluetooth 4.0 controllers, create a debugfs
+	 * switch that allows forcing BR/EDR SMP support and accepting
+	 * cross-transport pairing on non-AES encrypted connections.
+	 */
+	if (!lmp_sc_capable(hdev)) {
+		debugfs_create_file("force_bredr_smp", 0644, hdev->debugfs,
+				    hdev, &force_bredr_smp_fops);
+		return 0;
+	}
+
+	if (WARN_ON(hdev->smp_bredr_data)) {
+		chan = hdev->smp_bredr_data;
+		hdev->smp_bredr_data = NULL;
+		smp_del_chan(chan);
+	}
+
+	chan = smp_add_cid(hdev, L2CAP_CID_SMP_BREDR);
+	if (IS_ERR(chan)) {
+		int err = PTR_ERR(chan);
+		chan = hdev->smp_data;
+		hdev->smp_data = NULL;
+		smp_del_chan(chan);
+		return err;
+	}
+
+	hdev->smp_bredr_data = chan;
+
 	return 0;
 }
 
 void smp_unregister(struct hci_dev *hdev)
 {
-	struct l2cap_chan *chan = hdev->smp_data;
-	struct crypto_blkcipher *tfm_aes;
+	struct l2cap_chan *chan;
 
-	if (!chan)
-		return;
+	if (hdev->smp_bredr_data) {
+		chan = hdev->smp_bredr_data;
+		hdev->smp_bredr_data = NULL;
+		smp_del_chan(chan);
+	}
 
-	BT_DBG("%s chan %p", hdev->name, chan);
+	if (hdev->smp_data) {
+		chan = hdev->smp_data;
+		hdev->smp_data = NULL;
+		smp_del_chan(chan);
+	}
+}
 
-	tfm_aes = chan->data;
-	if (tfm_aes) {
-		chan->data = NULL;
+#if IS_ENABLED(CONFIG_BT_SELFTEST_SMP)
+
+static int __init test_ah(struct crypto_blkcipher *tfm_aes)
+{
+	const u8 irk[16] = {
+			0x9b, 0x7d, 0x39, 0x0a, 0xa6, 0x10, 0x10, 0x34,
+			0x05, 0xad, 0xc8, 0x57, 0xa3, 0x34, 0x02, 0xec };
+	const u8 r[3] = { 0x94, 0x81, 0x70 };
+	const u8 exp[3] = { 0xaa, 0xfb, 0x0d };
+	u8 res[3];
+	int err;
+
+	err = smp_ah(tfm_aes, irk, r, res);
+	if (err)
+		return err;
+
+	if (memcmp(res, exp, 3))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int __init test_c1(struct crypto_blkcipher *tfm_aes)
+{
+	const u8 k[16] = {
+			0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+			0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 };
+	const u8 r[16] = {
+			0xe0, 0x2e, 0x70, 0xc6, 0x4e, 0x27, 0x88, 0x63,
+			0x0e, 0x6f, 0xad, 0x56, 0x21, 0xd5, 0x83, 0x57 };
+	const u8 preq[7] = { 0x01, 0x01, 0x00, 0x00, 0x10, 0x07, 0x07 };
+	const u8 pres[7] = { 0x02, 0x03, 0x00, 0x00, 0x08, 0x00, 0x05 };
+	const u8 _iat = 0x01;
+	const u8 _rat = 0x00;
+	const bdaddr_t ra = { { 0xb6, 0xb5, 0xb4, 0xb3, 0xb2, 0xb1 } };
+	const bdaddr_t ia = { { 0xa6, 0xa5, 0xa4, 0xa3, 0xa2, 0xa1 } };
+	const u8 exp[16] = {
+			0x86, 0x3b, 0xf1, 0xbe, 0xc5, 0x4d, 0xa7, 0xd2,
+			0xea, 0x88, 0x89, 0x87, 0xef, 0x3f, 0x1e, 0x1e };
+	u8 res[16];
+	int err;
+
+	err = smp_c1(tfm_aes, k, r, preq, pres, _iat, &ia, _rat, &ra, res);
+	if (err)
+		return err;
+
+	if (memcmp(res, exp, 16))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int __init test_s1(struct crypto_blkcipher *tfm_aes)
+{
+	const u8 k[16] = {
+			0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+			0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 };
+	const u8 r1[16] = {
+			0x88, 0x77, 0x66, 0x55, 0x44, 0x33, 0x22, 0x11 };
+	const u8 r2[16] = {
+			0x00, 0xff, 0xee, 0xdd, 0xcc, 0xbb, 0xaa, 0x99 };
+	const u8 exp[16] = {
+			0x62, 0xa0, 0x6d, 0x79, 0xae, 0x16, 0x42, 0x5b,
+			0x9b, 0xf4, 0xb0, 0xe8, 0xf0, 0xe1, 0x1f, 0x9a };
+	u8 res[16];
+	int err;
+
+	err = smp_s1(tfm_aes, k, r1, r2, res);
+	if (err)
+		return err;
+
+	if (memcmp(res, exp, 16))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int __init test_f4(struct crypto_hash *tfm_cmac)
+{
+	const u8 u[32] = {
+			0xe6, 0x9d, 0x35, 0x0e, 0x48, 0x01, 0x03, 0xcc,
+			0xdb, 0xfd, 0xf4, 0xac, 0x11, 0x91, 0xf4, 0xef,
+			0xb9, 0xa5, 0xf9, 0xe9, 0xa7, 0x83, 0x2c, 0x5e,
+			0x2c, 0xbe, 0x97, 0xf2, 0xd2, 0x03, 0xb0, 0x20 };
+	const u8 v[32] = {
+			0xfd, 0xc5, 0x7f, 0xf4, 0x49, 0xdd, 0x4f, 0x6b,
+			0xfb, 0x7c, 0x9d, 0xf1, 0xc2, 0x9a, 0xcb, 0x59,
+			0x2a, 0xe7, 0xd4, 0xee, 0xfb, 0xfc, 0x0a, 0x90,
+			0x9a, 0xbb, 0xf6, 0x32, 0x3d, 0x8b, 0x18, 0x55 };
+	const u8 x[16] = {
+			0xab, 0xae, 0x2b, 0x71, 0xec, 0xb2, 0xff, 0xff,
+			0x3e, 0x73, 0x77, 0xd1, 0x54, 0x84, 0xcb, 0xd5 };
+	const u8 z = 0x00;
+	const u8 exp[16] = {
+			0x2d, 0x87, 0x74, 0xa9, 0xbe, 0xa1, 0xed, 0xf1,
+			0x1c, 0xbd, 0xa9, 0x07, 0xf1, 0x16, 0xc9, 0xf2 };
+	u8 res[16];
+	int err;
+
+	err = smp_f4(tfm_cmac, u, v, x, z, res);
+	if (err)
+		return err;
+
+	if (memcmp(res, exp, 16))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int __init test_f5(struct crypto_hash *tfm_cmac)
+{
+	const u8 w[32] = {
+			0x98, 0xa6, 0xbf, 0x73, 0xf3, 0x34, 0x8d, 0x86,
+			0xf1, 0x66, 0xf8, 0xb4, 0x13, 0x6b, 0x79, 0x99,
+			0x9b, 0x7d, 0x39, 0x0a, 0xa6, 0x10, 0x10, 0x34,
+			0x05, 0xad, 0xc8, 0x57, 0xa3, 0x34, 0x02, 0xec };
+	const u8 n1[16] = {
+			0xab, 0xae, 0x2b, 0x71, 0xec, 0xb2, 0xff, 0xff,
+			0x3e, 0x73, 0x77, 0xd1, 0x54, 0x84, 0xcb, 0xd5 };
+	const u8 n2[16] = {
+			0xcf, 0xc4, 0x3d, 0xff, 0xf7, 0x83, 0x65, 0x21,
+			0x6e, 0x5f, 0xa7, 0x25, 0xcc, 0xe7, 0xe8, 0xa6 };
+	const u8 a1[7] = { 0xce, 0xbf, 0x37, 0x37, 0x12, 0x56, 0x00 };
+	const u8 a2[7] = { 0xc1, 0xcf, 0x2d, 0x70, 0x13, 0xa7, 0x00 };
+	const u8 exp_ltk[16] = {
+			0x38, 0x0a, 0x75, 0x94, 0xb5, 0x22, 0x05, 0x98,
+			0x23, 0xcd, 0xd7, 0x69, 0x11, 0x79, 0x86, 0x69 };
+	const u8 exp_mackey[16] = {
+			0x20, 0x6e, 0x63, 0xce, 0x20, 0x6a, 0x3f, 0xfd,
+			0x02, 0x4a, 0x08, 0xa1, 0x76, 0xf1, 0x65, 0x29 };
+	u8 mackey[16], ltk[16];
+	int err;
+
+	err = smp_f5(tfm_cmac, w, n1, n2, a1, a2, mackey, ltk);
+	if (err)
+		return err;
+
+	if (memcmp(mackey, exp_mackey, 16))
+		return -EINVAL;
+
+	if (memcmp(ltk, exp_ltk, 16))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int __init test_f6(struct crypto_hash *tfm_cmac)
+{
+	const u8 w[16] = {
+			0x20, 0x6e, 0x63, 0xce, 0x20, 0x6a, 0x3f, 0xfd,
+			0x02, 0x4a, 0x08, 0xa1, 0x76, 0xf1, 0x65, 0x29 };
+	const u8 n1[16] = {
+			0xab, 0xae, 0x2b, 0x71, 0xec, 0xb2, 0xff, 0xff,
+			0x3e, 0x73, 0x77, 0xd1, 0x54, 0x84, 0xcb, 0xd5 };
+	const u8 n2[16] = {
+			0xcf, 0xc4, 0x3d, 0xff, 0xf7, 0x83, 0x65, 0x21,
+			0x6e, 0x5f, 0xa7, 0x25, 0xcc, 0xe7, 0xe8, 0xa6 };
+	const u8 r[16] = {
+			0xc8, 0x0f, 0x2d, 0x0c, 0xd2, 0x42, 0xda, 0x08,
+			0x54, 0xbb, 0x53, 0xb4, 0x3b, 0x34, 0xa3, 0x12 };
+	const u8 io_cap[3] = { 0x02, 0x01, 0x01 };
+	const u8 a1[7] = { 0xce, 0xbf, 0x37, 0x37, 0x12, 0x56, 0x00 };
+	const u8 a2[7] = { 0xc1, 0xcf, 0x2d, 0x70, 0x13, 0xa7, 0x00 };
+	const u8 exp[16] = {
+			0x61, 0x8f, 0x95, 0xda, 0x09, 0x0b, 0x6c, 0xd2,
+			0xc5, 0xe8, 0xd0, 0x9c, 0x98, 0x73, 0xc4, 0xe3 };
+	u8 res[16];
+	int err;
+
+	err = smp_f6(tfm_cmac, w, n1, n2, r, io_cap, a1, a2, res);
+	if (err)
+		return err;
+
+	if (memcmp(res, exp, 16))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int __init test_g2(struct crypto_hash *tfm_cmac)
+{
+	const u8 u[32] = {
+			0xe6, 0x9d, 0x35, 0x0e, 0x48, 0x01, 0x03, 0xcc,
+			0xdb, 0xfd, 0xf4, 0xac, 0x11, 0x91, 0xf4, 0xef,
+			0xb9, 0xa5, 0xf9, 0xe9, 0xa7, 0x83, 0x2c, 0x5e,
+			0x2c, 0xbe, 0x97, 0xf2, 0xd2, 0x03, 0xb0, 0x20 };
+	const u8 v[32] = {
+			0xfd, 0xc5, 0x7f, 0xf4, 0x49, 0xdd, 0x4f, 0x6b,
+			0xfb, 0x7c, 0x9d, 0xf1, 0xc2, 0x9a, 0xcb, 0x59,
+			0x2a, 0xe7, 0xd4, 0xee, 0xfb, 0xfc, 0x0a, 0x90,
+			0x9a, 0xbb, 0xf6, 0x32, 0x3d, 0x8b, 0x18, 0x55 };
+	const u8 x[16] = {
+			0xab, 0xae, 0x2b, 0x71, 0xec, 0xb2, 0xff, 0xff,
+			0x3e, 0x73, 0x77, 0xd1, 0x54, 0x84, 0xcb, 0xd5 };
+	const u8 y[16] = {
+			0xcf, 0xc4, 0x3d, 0xff, 0xf7, 0x83, 0x65, 0x21,
+			0x6e, 0x5f, 0xa7, 0x25, 0xcc, 0xe7, 0xe8, 0xa6 };
+	const u32 exp_val = 0x2f9ed5ba % 1000000;
+	u32 val;
+	int err;
+
+	err = smp_g2(tfm_cmac, u, v, x, y, &val);
+	if (err)
+		return err;
+
+	if (val != exp_val)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int __init test_h6(struct crypto_hash *tfm_cmac)
+{
+	const u8 w[16] = {
+			0x9b, 0x7d, 0x39, 0x0a, 0xa6, 0x10, 0x10, 0x34,
+			0x05, 0xad, 0xc8, 0x57, 0xa3, 0x34, 0x02, 0xec };
+	const u8 key_id[4] = { 0x72, 0x62, 0x65, 0x6c };
+	const u8 exp[16] = {
+			0x99, 0x63, 0xb1, 0x80, 0xe2, 0xa9, 0xd3, 0xe8,
+			0x1c, 0xc9, 0x6d, 0xe7, 0x02, 0xe1, 0x9a, 0x2d };
+	u8 res[16];
+	int err;
+
+	err = smp_h6(tfm_cmac, w, key_id, res);
+	if (err)
+		return err;
+
+	if (memcmp(res, exp, 16))
+		return -EINVAL;
+
+	return 0;
+}
+
+static char test_smp_buffer[32];
+
+static ssize_t test_smp_read(struct file *file, char __user *user_buf,
+			     size_t count, loff_t *ppos)
+{
+	return simple_read_from_buffer(user_buf, count, ppos, test_smp_buffer,
+				       strlen(test_smp_buffer));
+}
+
+static const struct file_operations test_smp_fops = {
+	.open		= simple_open,
+	.read		= test_smp_read,
+	.llseek		= default_llseek,
+};
+
+static int __init run_selftests(struct crypto_blkcipher *tfm_aes,
+				struct crypto_hash *tfm_cmac)
+{
+	ktime_t calltime, delta, rettime;
+	unsigned long long duration;
+	int err;
+
+	calltime = ktime_get();
+
+	err = test_ah(tfm_aes);
+	if (err) {
+		BT_ERR("smp_ah test failed");
+		goto done;
+	}
+
+	err = test_c1(tfm_aes);
+	if (err) {
+		BT_ERR("smp_c1 test failed");
+		goto done;
+	}
+
+	err = test_s1(tfm_aes);
+	if (err) {
+		BT_ERR("smp_s1 test failed");
+		goto done;
+	}
+
+	err = test_f4(tfm_cmac);
+	if (err) {
+		BT_ERR("smp_f4 test failed");
+		goto done;
+	}
+
+	err = test_f5(tfm_cmac);
+	if (err) {
+		BT_ERR("smp_f5 test failed");
+		goto done;
+	}
+
+	err = test_f6(tfm_cmac);
+	if (err) {
+		BT_ERR("smp_f6 test failed");
+		goto done;
+	}
+
+	err = test_g2(tfm_cmac);
+	if (err) {
+		BT_ERR("smp_g2 test failed");
+		goto done;
+	}
+
+	err = test_h6(tfm_cmac);
+	if (err) {
+		BT_ERR("smp_h6 test failed");
+		goto done;
+	}
+
+	rettime = ktime_get();
+	delta = ktime_sub(rettime, calltime);
+	duration = (unsigned long long) ktime_to_ns(delta) >> 10;
+
+	BT_INFO("SMP test passed in %llu usecs", duration);
+
+done:
+	if (!err)
+		snprintf(test_smp_buffer, sizeof(test_smp_buffer),
+			 "PASS (%llu usecs)\n", duration);
+	else
+		snprintf(test_smp_buffer, sizeof(test_smp_buffer), "FAIL\n");
+
+	debugfs_create_file("selftest_smp", 0444, bt_debugfs, NULL,
+			    &test_smp_fops);
+
+	return err;
+}
+
+int __init bt_selftest_smp(void)
+{
+	struct crypto_blkcipher *tfm_aes;
+	struct crypto_hash *tfm_cmac;
+	int err;
+
+	tfm_aes = crypto_alloc_blkcipher("ecb(aes)", 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(tfm_aes)) {
+		BT_ERR("Unable to create ECB crypto context");
+		return PTR_ERR(tfm_aes);
+	}
+
+	tfm_cmac = crypto_alloc_hash("cmac(aes)", 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(tfm_cmac)) {
+		BT_ERR("Unable to create CMAC crypto context");
 		crypto_free_blkcipher(tfm_aes);
+		return PTR_ERR(tfm_cmac);
 	}
 
-	hdev->smp_data = NULL;
-	l2cap_chan_put(chan);
+	err = run_selftests(tfm_aes, tfm_cmac);
+
+	crypto_free_hash(tfm_cmac);
+	crypto_free_blkcipher(tfm_aes);
+
+	return err;
 }
+
+#endif
diff --git a/net/bluetooth/smp.h b/net/bluetooth/smp.h
index 86a683a8b491..6cf872563ea7 100644
--- a/net/bluetooth/smp.h
+++ b/net/bluetooth/smp.h
@@ -50,10 +50,13 @@ struct smp_cmd_pairing {
 #define SMP_DIST_ENC_KEY	0x01
 #define SMP_DIST_ID_KEY		0x02
 #define SMP_DIST_SIGN		0x04
+#define SMP_DIST_LINK_KEY	0x08
 
 #define SMP_AUTH_NONE		0x00
 #define SMP_AUTH_BONDING	0x01
 #define SMP_AUTH_MITM		0x04
+#define SMP_AUTH_SC		0x08
+#define SMP_AUTH_KEYPRESS	0x10
 
 #define SMP_CMD_PAIRING_CONFIRM	0x03
 struct smp_cmd_pairing_confirm {
@@ -102,7 +105,23 @@ struct smp_cmd_security_req {
 	__u8	auth_req;
 } __packed;
 
-#define SMP_CMD_MAX		0x0b
+#define SMP_CMD_PUBLIC_KEY	0x0c
+struct smp_cmd_public_key {
+	__u8	x[32];
+	__u8	y[32];
+} __packed;
+
+#define SMP_CMD_DHKEY_CHECK	0x0d
+struct smp_cmd_dhkey_check {
+	__u8	e[16];
+} __packed;
+
+#define SMP_CMD_KEYPRESS_NOTIFY	0x0e
+struct smp_cmd_keypress_notify {
+	__u8	value;
+} __packed;
+
+#define SMP_CMD_MAX		0x0e
 
 #define SMP_PASSKEY_ENTRY_FAILED	0x01
 #define SMP_OOB_NOT_AVAIL		0x02
@@ -114,6 +133,10 @@ struct smp_cmd_security_req {
 #define SMP_UNSPECIFIED			0x08
 #define SMP_REPEATED_ATTEMPTS		0x09
 #define SMP_INVALID_PARAMS		0x0a
+#define SMP_DHKEY_CHECK_FAILED		0x0b
+#define SMP_NUMERIC_COMP_FAILED		0x0c
+#define SMP_BREDR_PAIRING_IN_PROGRESS	0x0d
+#define SMP_CROSS_TRANSP_NOT_ALLOWED	0x0e
 
 #define SMP_MIN_ENC_KEY_SIZE		7
 #define SMP_MAX_ENC_KEY_SIZE		16
@@ -123,25 +146,64 @@ enum {
 	SMP_STK,
 	SMP_LTK,
 	SMP_LTK_SLAVE,
+	SMP_LTK_P256,
+	SMP_LTK_P256_DEBUG,
 };
 
+static inline bool smp_ltk_is_sc(struct smp_ltk *key)
+{
+	switch (key->type) {
+	case SMP_LTK_P256:
+	case SMP_LTK_P256_DEBUG:
+		return true;
+	}
+
+	return false;
+}
+
 static inline u8 smp_ltk_sec_level(struct smp_ltk *key)
 {
-	if (key->authenticated)
-		return BT_SECURITY_HIGH;
+	if (key->authenticated) {
+		if (smp_ltk_is_sc(key))
+			return BT_SECURITY_FIPS;
+		else
+			return BT_SECURITY_HIGH;
+	}
 
 	return BT_SECURITY_MEDIUM;
 }
 
+/* Key preferences for smp_sufficient security */
+enum smp_key_pref {
+	SMP_ALLOW_STK,
+	SMP_USE_LTK,
+};
+
 /* SMP Commands */
-bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level);
+bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level,
+			     enum smp_key_pref key_pref);
 int smp_conn_security(struct hci_conn *hcon, __u8 sec_level);
 int smp_user_confirm_reply(struct hci_conn *conn, u16 mgmt_op, __le32 passkey);
 
-bool smp_irk_matches(struct hci_dev *hdev, u8 irk[16], bdaddr_t *bdaddr);
-int smp_generate_rpa(struct hci_dev *hdev, u8 irk[16], bdaddr_t *rpa);
+bool smp_irk_matches(struct hci_dev *hdev, const u8 irk[16],
+		     const bdaddr_t *bdaddr);
+int smp_generate_rpa(struct hci_dev *hdev, const u8 irk[16], bdaddr_t *rpa);
+int smp_generate_oob(struct hci_dev *hdev, u8 hash[16], u8 rand[16]);
 
 int smp_register(struct hci_dev *hdev);
 void smp_unregister(struct hci_dev *hdev);
 
+#if IS_ENABLED(CONFIG_BT_SELFTEST_SMP)
+
+int bt_selftest_smp(void);
+
+#else
+
+static inline int bt_selftest_smp(void)
+{
+	return 0;
+}
+
+#endif
+
 #endif /* __SMP_H */
diff --git a/net/bridge/br.c b/net/bridge/br.c
index 44425aff7cba..02c24cf63c34 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -19,6 +19,7 @@
 #include <linux/llc.h>
 #include <net/llc.h>
 #include <net/stp.h>
+#include <net/switchdev.h>
 
 #include "br_private.h"
 
@@ -120,6 +121,48 @@ static struct notifier_block br_device_notifier = {
 	.notifier_call = br_device_event
 };
 
+static int br_netdev_switch_event(struct notifier_block *unused,
+				  unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_switch_notifier_info_to_dev(ptr);
+	struct net_bridge_port *p;
+	struct net_bridge *br;
+	struct netdev_switch_notifier_fdb_info *fdb_info;
+	int err = NOTIFY_DONE;
+
+	rtnl_lock();
+	p = br_port_get_rtnl(dev);
+	if (!p)
+		goto out;
+
+	br = p->br;
+
+	switch (event) {
+	case NETDEV_SWITCH_FDB_ADD:
+		fdb_info = ptr;
+		err = br_fdb_external_learn_add(br, p, fdb_info->addr,
+						fdb_info->vid);
+		if (err)
+			err = notifier_from_errno(err);
+		break;
+	case NETDEV_SWITCH_FDB_DEL:
+		fdb_info = ptr;
+		err = br_fdb_external_learn_del(br, p, fdb_info->addr,
+						fdb_info->vid);
+		if (err)
+			err = notifier_from_errno(err);
+		break;
+	}
+
+out:
+	rtnl_unlock();
+	return err;
+}
+
+static struct notifier_block br_netdev_switch_notifier = {
+	.notifier_call = br_netdev_switch_event,
+};
+
 static void __net_exit br_net_exit(struct net *net)
 {
 	struct net_device *dev;
@@ -147,6 +190,8 @@ static int __init br_init(void)
 {
 	int err;
 
+	BUILD_BUG_ON(sizeof(struct br_input_skb_cb) > FIELD_SIZEOF(struct sk_buff, cb));
+
 	err = stp_proto_register(&br_stp_proto);
 	if (err < 0) {
 		pr_err("bridge: can't register sap for STP\n");
@@ -169,10 +214,14 @@ static int __init br_init(void)
 	if (err)
 		goto err_out3;
 
-	err = br_netlink_init();
+	err = register_netdev_switch_notifier(&br_netdev_switch_notifier);
 	if (err)
 		goto err_out4;
 
+	err = br_netlink_init();
+	if (err)
+		goto err_out5;
+
 	brioctl_set(br_ioctl_deviceless_stub);
 
 #if IS_ENABLED(CONFIG_ATM_LANE)
@@ -185,6 +234,8 @@ static int __init br_init(void)
 
 	return 0;
 
+err_out5:
+	unregister_netdev_switch_notifier(&br_netdev_switch_notifier);
 err_out4:
 	unregister_netdevice_notifier(&br_device_notifier);
 err_out3:
@@ -202,6 +253,7 @@ static void __exit br_deinit(void)
 {
 	stp_proto_unregister(&br_stp_proto);
 	br_netlink_fini();
+	unregister_netdev_switch_notifier(&br_netdev_switch_notifier);
 	unregister_netdevice_notifier(&br_device_notifier);
 	brioctl_set(NULL);
 	unregister_pernet_subsys(&br_net_ops);
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index ffd379db5938..4ff77a16956c 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -25,6 +25,9 @@
 #define COMMON_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | \
 			 NETIF_F_GSO_MASK | NETIF_F_HW_CSUM)
 
+const struct nf_br_ops __rcu *nf_br_ops __read_mostly;
+EXPORT_SYMBOL_GPL(nf_br_ops);
+
 /* net device transmit always called with BH disabled */
 netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 {
@@ -33,16 +36,15 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct net_bridge_fdb_entry *dst;
 	struct net_bridge_mdb_entry *mdst;
 	struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats);
+	const struct nf_br_ops *nf_ops;
 	u16 vid = 0;
 
 	rcu_read_lock();
-#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-	if (skb->nf_bridge && (skb->nf_bridge->mask & BRNF_BRIDGED_DNAT)) {
-		br_nf_pre_routing_finish_bridge_slow(skb);
+	nf_ops = rcu_dereference(nf_br_ops);
+	if (nf_ops && nf_ops->br_dev_xmit_hook(skb)) {
 		rcu_read_unlock();
 		return NETDEV_TX_OK;
 	}
-#endif
 
 	u64_stats_update_begin(&brstats->syncp);
 	brstats->tx_packets++;
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 6f6c95cfe8f2..659fb96672e4 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -90,7 +90,7 @@ static void fdb_rcu_free(struct rcu_head *head)
  * are then updated with the new information.
  * Called under RTNL.
  */
-static void fdb_add_hw(struct net_bridge *br, const unsigned char *addr)
+static void fdb_add_hw_addr(struct net_bridge *br, const unsigned char *addr)
 {
 	int err;
 	struct net_bridge_port *p;
@@ -118,7 +118,7 @@ undo:
  * the ports with needed information.
  * Called under RTNL.
  */
-static void fdb_del_hw(struct net_bridge *br, const unsigned char *addr)
+static void fdb_del_hw_addr(struct net_bridge *br, const unsigned char *addr)
 {
 	struct net_bridge_port *p;
 
@@ -133,7 +133,7 @@ static void fdb_del_hw(struct net_bridge *br, const unsigned char *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);
+		fdb_del_hw_addr(br, f->addr.addr);
 
 	hlist_del_rcu(&f->hlist);
 	fdb_notify(br, f, RTM_DELNEIGH);
@@ -481,6 +481,7 @@ static struct net_bridge_fdb_entry *fdb_create(struct hlist_head *head,
 		fdb->is_local = 0;
 		fdb->is_static = 0;
 		fdb->added_by_user = 0;
+		fdb->added_by_external_learn = 0;
 		fdb->updated = fdb->used = jiffies;
 		hlist_add_head_rcu(&fdb->hlist, head);
 	}
@@ -514,7 +515,7 @@ 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_add_hw_addr(br, addr);
 	fdb_notify(br, fdb, RTM_NEWNEIGH);
 	return 0;
 }
@@ -613,7 +614,7 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br,
 	ndm->ndm_family	 = AF_BRIDGE;
 	ndm->ndm_pad1    = 0;
 	ndm->ndm_pad2    = 0;
-	ndm->ndm_flags	 = 0;
+	ndm->ndm_flags	 = fdb->added_by_external_learn ? NTF_EXT_LEARNED : 0;
 	ndm->ndm_type	 = 0;
 	ndm->ndm_ifindex = fdb->dst ? fdb->dst->dev->ifindex : br->dev->ifindex;
 	ndm->ndm_state   = fdb_to_nud(fdb);
@@ -632,7 +633,8 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br,
 	if (fdb->vlan_id && nla_put(skb, NDA_VLAN, sizeof(u16), &fdb->vlan_id))
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
@@ -685,6 +687,9 @@ int br_fdb_dump(struct sk_buff *skb,
 	if (!(dev->priv_flags & IFF_EBRIDGE))
 		goto out;
 
+	if (!filter_dev)
+		idx = ndo_dflt_fdb_dump(skb, cb, dev, NULL, idx);
+
 	for (i = 0; i < BR_HASH_SIZE; i++) {
 		struct net_bridge_fdb_entry *f;
 
@@ -696,7 +701,7 @@ int br_fdb_dump(struct sk_buff *skb,
 			    (!f->dst || f->dst->dev != filter_dev)) {
 				if (filter_dev != dev)
 					goto skip;
-				/* !f->dst is a speacial case for bridge
+				/* !f->dst is a special case for bridge
 				 * It means the MAC belongs to the bridge
 				 * Therefore need a little more filtering
 				 * we only want to dump the !f->dst case
@@ -704,6 +709,8 @@ int br_fdb_dump(struct sk_buff *skb,
 				if (f->dst)
 					goto skip;
 			}
+			if (!filter_dev && f->dst)
+				goto skip;
 
 			if (fdb_fill_info(skb, br, f,
 					  NETLINK_CB(cb->skb).portid,
@@ -754,19 +761,19 @@ static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr,
 			fdb->is_local = 1;
 			if (!fdb->is_static) {
 				fdb->is_static = 1;
-				fdb_add_hw(br, addr);
+				fdb_add_hw_addr(br, addr);
 			}
 		} else if (state & NUD_NOARP) {
 			fdb->is_local = 0;
 			if (!fdb->is_static) {
 				fdb->is_static = 1;
-				fdb_add_hw(br, addr);
+				fdb_add_hw_addr(br, addr);
 			}
 		} else {
 			fdb->is_local = 0;
 			if (fdb->is_static) {
 				fdb->is_static = 0;
-				fdb_del_hw(br, addr);
+				fdb_del_hw_addr(br, addr);
 			}
 		}
 
@@ -789,9 +796,11 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge_port *p,
 	int err = 0;
 
 	if (ndm->ndm_flags & NTF_USE) {
+		local_bh_disable();
 		rcu_read_lock();
 		br_fdb_update(p->br, p, addr, vid, true);
 		rcu_read_unlock();
+		local_bh_enable();
 	} else {
 		spin_lock_bh(&p->br->hash_lock);
 		err = fdb_add_entry(p, addr, ndm->ndm_state,
@@ -805,33 +814,17 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge_port *p,
 /* Add new permanent fdb entry with RTM_NEWNEIGH */
 int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 	       struct net_device *dev,
-	       const unsigned char *addr, u16 nlh_flags)
+	       const unsigned char *addr, u16 vid, u16 nlh_flags)
 {
 	struct net_bridge_port *p;
 	int err = 0;
 	struct net_port_vlans *pv;
-	unsigned short vid = VLAN_N_VID;
 
 	if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE))) {
 		pr_info("bridge: RTM_NEWNEIGH with invalid state %#x\n", ndm->ndm_state);
 		return -EINVAL;
 	}
 
-	if (tb[NDA_VLAN]) {
-		if (nla_len(tb[NDA_VLAN]) != sizeof(unsigned short)) {
-			pr_info("bridge: RTM_NEWNEIGH with invalid vlan\n");
-			return -EINVAL;
-		}
-
-		vid = nla_get_u16(tb[NDA_VLAN]);
-
-		if (!vid || vid >= VLAN_VID_MASK) {
-			pr_info("bridge: RTM_NEWNEIGH with invalid vlan id %d\n",
-				vid);
-			return -EINVAL;
-		}
-	}
-
 	if (is_zero_ether_addr(addr)) {
 		pr_info("bridge: RTM_NEWNEIGH with invalid ether address\n");
 		return -EINVAL;
@@ -845,7 +838,7 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 	}
 
 	pv = nbp_get_vlan_info(p);
-	if (vid != VLAN_N_VID) {
+	if (vid) {
 		if (!pv || !test_bit(vid, pv->vlan_bitmap)) {
 			pr_info("bridge: RTM_NEWNEIGH with unconfigured "
 				"vlan %d on port %s\n", vid, dev->name);
@@ -855,10 +848,9 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 		/* VID was specified, so use it. */
 		err = __br_fdb_add(ndm, p, addr, nlh_flags, vid);
 	} else {
-		if (!pv || bitmap_empty(pv->vlan_bitmap, VLAN_N_VID)) {
-			err = __br_fdb_add(ndm, p, addr, nlh_flags, 0);
+		err = __br_fdb_add(ndm, p, addr, nlh_flags, 0);
+		if (err || !pv)
 			goto out;
-		}
 
 		/* We have vlans configured on this port and user didn't
 		 * specify a VLAN.  To be nice, add/update entry for every
@@ -903,27 +895,12 @@ static int __br_fdb_delete(struct net_bridge_port *p,
 /* Remove neighbor entry with RTM_DELNEIGH */
 int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
 		  struct net_device *dev,
-		  const unsigned char *addr)
+		  const unsigned char *addr, u16 vid)
 {
 	struct net_bridge_port *p;
 	int err;
 	struct net_port_vlans *pv;
-	unsigned short vid = VLAN_N_VID;
-
-	if (tb[NDA_VLAN]) {
-		if (nla_len(tb[NDA_VLAN]) != sizeof(unsigned short)) {
-			pr_info("bridge: RTM_NEWNEIGH with invalid vlan\n");
-			return -EINVAL;
-		}
 
-		vid = nla_get_u16(tb[NDA_VLAN]);
-
-		if (!vid || vid >= VLAN_VID_MASK) {
-			pr_info("bridge: RTM_NEWNEIGH with invalid vlan id %d\n",
-				vid);
-			return -EINVAL;
-		}
-	}
 	p = br_port_get_rtnl(dev);
 	if (p == NULL) {
 		pr_info("bridge: RTM_DELNEIGH %s not a bridge port\n",
@@ -932,7 +909,7 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
 	}
 
 	pv = nbp_get_vlan_info(p);
-	if (vid != VLAN_N_VID) {
+	if (vid) {
 		if (!pv || !test_bit(vid, pv->vlan_bitmap)) {
 			pr_info("bridge: RTM_DELNEIGH with unconfigured "
 				"vlan %d on port %s\n", vid, dev->name);
@@ -941,16 +918,15 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
 
 		err = __br_fdb_delete(p, addr, vid);
 	} else {
-		if (!pv || bitmap_empty(pv->vlan_bitmap, VLAN_N_VID)) {
-			err = __br_fdb_delete(p, addr, 0);
+		err = -ENOENT;
+		err &= __br_fdb_delete(p, addr, 0);
+		if (!pv)
 			goto out;
-		}
 
 		/* We have vlans configured on this port and user didn't
 		 * specify a VLAN.  To be nice, add/update entry for every
 		 * vlan on this port.
 		 */
-		err = -ENOENT;
 		for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) {
 			err &= __br_fdb_delete(p, addr, vid);
 		}
@@ -1014,3 +990,61 @@ void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p)
 		}
 	}
 }
+
+int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p,
+			      const unsigned char *addr, u16 vid)
+{
+	struct hlist_head *head;
+	struct net_bridge_fdb_entry *fdb;
+	int err = 0;
+
+	ASSERT_RTNL();
+	spin_lock_bh(&br->hash_lock);
+
+	head = &br->hash[br_mac_hash(addr, vid)];
+	fdb = fdb_find(head, addr, vid);
+	if (!fdb) {
+		fdb = fdb_create(head, p, addr, vid);
+		if (!fdb) {
+			err = -ENOMEM;
+			goto err_unlock;
+		}
+		fdb->added_by_external_learn = 1;
+		fdb_notify(br, fdb, RTM_NEWNEIGH);
+	} else if (fdb->added_by_external_learn) {
+		/* Refresh entry */
+		fdb->updated = fdb->used = jiffies;
+	} else if (!fdb->added_by_user) {
+		/* Take over SW learned entry */
+		fdb->added_by_external_learn = 1;
+		fdb->updated = jiffies;
+		fdb_notify(br, fdb, RTM_NEWNEIGH);
+	}
+
+err_unlock:
+	spin_unlock_bh(&br->hash_lock);
+
+	return err;
+}
+
+int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p,
+			      const unsigned char *addr, u16 vid)
+{
+	struct hlist_head *head;
+	struct net_bridge_fdb_entry *fdb;
+	int err = 0;
+
+	ASSERT_RTNL();
+	spin_lock_bh(&br->hash_lock);
+
+	head = &br->hash[br_mac_hash(addr, vid)];
+	fdb = fdb_find(head, addr, vid);
+	if (fdb && fdb->added_by_external_learn)
+		fdb_delete(br, fdb);
+	else
+		err = -ENOENT;
+
+	spin_unlock_bh(&br->hash_lock);
+
+	return err;
+}
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 44cb786b925a..e97572b5d2cc 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -35,11 +35,9 @@ static inline int should_deliver(const struct net_bridge_port *p,
 		p->state == BR_STATE_FORWARDING;
 }
 
-int br_dev_queue_push_xmit(struct sk_buff *skb)
+int br_dev_queue_push_xmit(struct sock *sk, struct sk_buff *skb)
 {
-	/* ip_fragment doesn't copy the MAC header */
-	if (nf_bridge_maybe_copy_header(skb) ||
-	    !is_skb_forwardable(skb->dev, skb)) {
+	if (!is_skb_forwardable(skb->dev, skb)) {
 		kfree_skb(skb);
 	} else {
 		skb_push(skb, ETH_HLEN);
@@ -51,9 +49,10 @@ int br_dev_queue_push_xmit(struct sk_buff *skb)
 }
 EXPORT_SYMBOL_GPL(br_dev_queue_push_xmit);
 
-int br_forward_finish(struct sk_buff *skb)
+int br_forward_finish(struct sock *sk, struct sk_buff *skb)
 {
-	return NF_HOOK(NFPROTO_BRIDGE, NF_BR_POST_ROUTING, skb, NULL, skb->dev,
+	return NF_HOOK(NFPROTO_BRIDGE, NF_BR_POST_ROUTING, sk, skb,
+		       NULL, skb->dev,
 		       br_dev_queue_push_xmit);
 
 }
@@ -77,7 +76,8 @@ static void __br_deliver(const struct net_bridge_port *to, struct sk_buff *skb)
 		return;
 	}
 
-	NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev,
+	NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, NULL, skb,
+		NULL, skb->dev,
 		br_forward_finish);
 }
 
@@ -98,7 +98,8 @@ static void __br_forward(const struct net_bridge_port *to, struct sk_buff *skb)
 	skb->dev = to->dev;
 	skb_forward_csum(skb);
 
-	NF_HOOK(NFPROTO_BRIDGE, NF_BR_FORWARD, skb, indev, skb->dev,
+	NF_HOOK(NFPROTO_BRIDGE, NF_BR_FORWARD, NULL, skb,
+		indev, skb->dev,
 		br_forward_finish);
 }
 
@@ -184,6 +185,14 @@ static void br_flood(struct net_bridge *br, struct sk_buff *skb,
 		/* Do not flood unicast traffic to ports that turn it off */
 		if (unicast && !(p->flags & BR_FLOOD))
 			continue;
+
+		/* Do not flood to ports that enable proxy ARP */
+		if (p->flags & BR_PROXYARP)
+			continue;
+		if ((p->flags & BR_PROXYARP_WIFI) &&
+		    BR_INPUT_SKB_CB(skb)->proxyarp_replied)
+			continue;
+
 		prev = maybe_deliver(prev, p, skb, __packet_hook);
 		if (IS_ERR(prev))
 			goto out;
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index ed307db7a12b..1849d96b3c91 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -424,6 +424,7 @@ netdev_features_t br_features_recompute(struct net_bridge *br,
 		features = netdev_increment_features(features,
 						     p->dev->features, mask);
 	}
+	features = netdev_add_tso_features(features, mask);
 
 	return features;
 }
@@ -435,10 +436,16 @@ int br_add_if(struct net_bridge *br, struct net_device *dev)
 	int err = 0;
 	bool changed_addr;
 
-	/* Don't allow bridging non-ethernet like devices */
+	/* Don't allow bridging non-ethernet like devices, or DSA-enabled
+	 * master network devices since the bridge layer rx_handler prevents
+	 * the DSA fake ethertype handler to be invoked, so we do not strip off
+	 * the DSA switch tag protocol header and the bridge layer just return
+	 * RX_HANDLER_CONSUMED, stopping RX processing for these frames.
+	 */
 	if ((dev->flags & IFF_LOOPBACK) ||
 	    dev->type != ARPHRD_ETHER || dev->addr_len != ETH_ALEN ||
-	    !is_valid_ether_addr(dev->dev_addr))
+	    !is_valid_ether_addr(dev->dev_addr) ||
+	    netdev_uses_dsa(dev))
 		return -EINVAL;
 
 	/* No bridging of bridges */
@@ -556,6 +563,8 @@ int br_del_if(struct net_bridge *br, struct net_device *dev)
 	 */
 	del_nbp(p);
 
+	dev_set_mtu(br->dev, br_min_mtu(br));
+
 	spin_lock_bh(&br->lock);
 	changed_addr = br_stp_recalculate_bridge_id(br);
 	spin_unlock_bh(&br->lock);
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 6fd5522df696..f921a5dce22d 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -16,6 +16,8 @@
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/netfilter_bridge.h>
+#include <linux/neighbour.h>
+#include <net/arp.h>
 #include <linux/export.h>
 #include <linux/rculist.h>
 #include "br_private.h"
@@ -53,12 +55,72 @@ static int br_pass_frame_up(struct sk_buff *skb)
 	if (!skb)
 		return NET_RX_DROP;
 
-	return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, skb, indev, NULL,
-		       netif_receive_skb);
+	return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, NULL, skb,
+		       indev, NULL,
+		       netif_receive_skb_sk);
+}
+
+static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br,
+			    u16 vid, struct net_bridge_port *p)
+{
+	struct net_device *dev = br->dev;
+	struct neighbour *n;
+	struct arphdr *parp;
+	u8 *arpptr, *sha;
+	__be32 sip, tip;
+
+	BR_INPUT_SKB_CB(skb)->proxyarp_replied = false;
+
+	if (dev->flags & IFF_NOARP)
+		return;
+
+	if (!pskb_may_pull(skb, arp_hdr_len(dev))) {
+		dev->stats.tx_dropped++;
+		return;
+	}
+	parp = arp_hdr(skb);
+
+	if (parp->ar_pro != htons(ETH_P_IP) ||
+	    parp->ar_op != htons(ARPOP_REQUEST) ||
+	    parp->ar_hln != dev->addr_len ||
+	    parp->ar_pln != 4)
+		return;
+
+	arpptr = (u8 *)parp + sizeof(struct arphdr);
+	sha = arpptr;
+	arpptr += dev->addr_len;	/* sha */
+	memcpy(&sip, arpptr, sizeof(sip));
+	arpptr += sizeof(sip);
+	arpptr += dev->addr_len;	/* tha */
+	memcpy(&tip, arpptr, sizeof(tip));
+
+	if (ipv4_is_loopback(tip) ||
+	    ipv4_is_multicast(tip))
+		return;
+
+	n = neigh_lookup(&arp_tbl, &tip, dev);
+	if (n) {
+		struct net_bridge_fdb_entry *f;
+
+		if (!(n->nud_state & NUD_VALID)) {
+			neigh_release(n);
+			return;
+		}
+
+		f = __br_fdb_get(br, n->ha, vid);
+		if (f && ((p->flags & BR_PROXYARP) ||
+			  (f->dst && (f->dst->flags & BR_PROXYARP_WIFI)))) {
+			arp_send(ARPOP_REPLY, ETH_P_ARP, sip, skb->dev, tip,
+				 sha, n->ha, sha);
+			BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+		}
+
+		neigh_release(n);
+	}
 }
 
 /* note: already called with rcu_read_lock */
-int br_handle_frame_finish(struct sk_buff *skb)
+int br_handle_frame_finish(struct sock *sk, struct sk_buff *skb)
 {
 	const unsigned char *dest = eth_hdr(skb)->h_dest;
 	struct net_bridge_port *p = br_port_get_rcu(skb->dev);
@@ -97,6 +159,9 @@ int br_handle_frame_finish(struct sk_buff *skb)
 
 	dst = NULL;
 
+	if (IS_ENABLED(CONFIG_INET) && skb->protocol == htons(ETH_P_ARP))
+		br_do_proxy_arp(skb, br, vid, p);
+
 	if (is_broadcast_ether_addr(dest)) {
 		skb2 = skb;
 		unicast = false;
@@ -143,7 +208,7 @@ drop:
 EXPORT_SYMBOL_GPL(br_handle_frame_finish);
 
 /* note: already called with rcu_read_lock */
-static int br_handle_local_finish(struct sk_buff *skb)
+static int br_handle_local_finish(struct sock *sk, struct sk_buff *skb)
 {
 	struct net_bridge_port *p = br_port_get_rcu(skb->dev);
 	u16 vid = 0;
@@ -213,8 +278,8 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
 		}
 
 		/* Deliver packet to local host only */
-		if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, skb, skb->dev,
-			    NULL, br_handle_local_finish)) {
+		if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, NULL, skb,
+			    skb->dev, NULL, br_handle_local_finish)) {
 			return RX_HANDLER_CONSUMED; /* consumed by filter */
 		} else {
 			*pskb = skb;
@@ -238,7 +303,8 @@ forward:
 		if (ether_addr_equal(p->br->dev->dev_addr, dest))
 			skb->pkt_type = PACKET_HOST;
 
-		NF_HOOK(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL,
+		NF_HOOK(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, NULL, skb,
+			skb->dev, NULL,
 			br_handle_frame_finish);
 		break;
 	default:
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 5df05269d17a..e29ad70b3000 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -170,7 +170,7 @@ static int nlmsg_populate_mdb_fill(struct sk_buff *skb,
 	struct br_port_msg *bpm;
 	struct nlattr *nest, *nest2;
 
-	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*bpm), NLM_F_MULTI);
+	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*bpm), 0);
 	if (!nlh)
 		return -EMSGSIZE;
 
@@ -190,7 +190,8 @@ static int nlmsg_populate_mdb_fill(struct sk_buff *skb,
 
 	nla_nest_end(skb, nest2);
 	nla_nest_end(skb, nest);
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 end:
 	nla_nest_end(skb, nest);
@@ -276,7 +277,7 @@ static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct net_device *dev;
 	int err;
 
-	err = nlmsg_parse(nlh, sizeof(*bpm), tb, MDBA_SET_ENTRY, NULL);
+	err = nlmsg_parse(nlh, sizeof(*bpm), tb, MDBA_SET_ENTRY_MAX, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 648d79ccf462..ff667e18b2d6 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -813,10 +813,10 @@ static void __br_multicast_send_query(struct net_bridge *br,
 		return;
 
 	if (port) {
-		__skb_push(skb, sizeof(struct ethhdr));
 		skb->dev = port->dev;
-		NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev,
-			dev_queue_xmit);
+		NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, NULL, skb,
+			NULL, skb->dev,
+			br_dev_queue_push_xmit);
 	} else {
 		br_multicast_select_own_querier(br, ip, skb);
 		netif_rx(skb);
@@ -1072,7 +1072,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
 
 		err = br_ip6_multicast_add_group(br, port, &grec->grec_mca,
 						 vid);
-		if (!err)
+		if (err)
 			break;
 	}
 
@@ -1167,6 +1167,9 @@ static void br_multicast_add_router(struct net_bridge *br,
 	struct net_bridge_port *p;
 	struct hlist_node *slot = NULL;
 
+	if (!hlist_unhashed(&port->rlist))
+		return;
+
 	hlist_for_each_entry(p, &br->router_list, rlist) {
 		if ((unsigned long) port >= (unsigned long) p)
 			break;
@@ -1194,12 +1197,8 @@ static void br_multicast_mark_router(struct net_bridge *br,
 	if (port->multicast_router != 1)
 		return;
 
-	if (!hlist_unhashed(&port->rlist))
-		goto timer;
-
 	br_multicast_add_router(br, port);
 
-timer:
 	mod_timer(&port->multicast_router_timer,
 		  now + br->multicast_querier_interval);
 }
@@ -1822,7 +1821,7 @@ static void br_multicast_query_expired(struct net_bridge *br,
 	if (query->startup_sent < br->multicast_startup_query_count)
 		query->startup_sent++;
 
-	RCU_INIT_POINTER(querier, NULL);
+	RCU_INIT_POINTER(querier->port, NULL);
 	br_multicast_send_query(br, NULL, query);
 	spin_unlock(&br->multicast_lock);
 }
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 1a4f32c09ad5..60ddfbeb47f5 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -35,6 +35,7 @@
 #include <net/ip.h>
 #include <net/ipv6.h>
 #include <net/route.h>
+#include <net/netfilter/br_netfilter.h>
 
 #include <asm/uaccess.h>
 #include "br_private.h"
@@ -42,11 +43,6 @@
 #include <linux/sysctl.h>
 #endif
 
-#define skb_origaddr(skb)	 (((struct bridge_skb_cb *) \
-				 (skb->nf_bridge->data))->daddr.ipv4)
-#define store_orig_dstaddr(skb)	 (skb_origaddr(skb) = ip_hdr(skb)->daddr)
-#define dnat_took_place(skb)	 (skb_origaddr(skb) != ip_hdr(skb)->daddr)
-
 #ifdef CONFIG_SYSCTL
 static struct ctl_table_header *brnf_sysctl_header;
 static int brnf_call_iptables __read_mostly = 1;
@@ -65,17 +61,17 @@ static int brnf_pass_vlan_indev __read_mostly = 0;
 #endif
 
 #define IS_IP(skb) \
-	(!vlan_tx_tag_present(skb) && skb->protocol == htons(ETH_P_IP))
+	(!skb_vlan_tag_present(skb) && skb->protocol == htons(ETH_P_IP))
 
 #define IS_IPV6(skb) \
-	(!vlan_tx_tag_present(skb) && skb->protocol == htons(ETH_P_IPV6))
+	(!skb_vlan_tag_present(skb) && skb->protocol == htons(ETH_P_IPV6))
 
 #define IS_ARP(skb) \
-	(!vlan_tx_tag_present(skb) && skb->protocol == htons(ETH_P_ARP))
+	(!skb_vlan_tag_present(skb) && skb->protocol == htons(ETH_P_ARP))
 
 static inline __be16 vlan_proto(const struct sk_buff *skb)
 {
-	if (vlan_tx_tag_present(skb))
+	if (skb_vlan_tag_present(skb))
 		return skb->protocol;
 	else if (skb->protocol == htons(ETH_P_8021Q))
 		return vlan_eth_hdr(skb)->h_vlan_encapsulated_proto;
@@ -111,6 +107,24 @@ static inline __be16 pppoe_proto(const struct sk_buff *skb)
 	 pppoe_proto(skb) == htons(PPP_IPV6) && \
 	 brnf_filter_pppoe_tagged)
 
+/* largest possible L2 header, see br_nf_dev_queue_xmit() */
+#define NF_BRIDGE_MAX_MAC_HEADER_LENGTH (PPPOE_SES_HLEN + ETH_HLEN)
+
+#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4)
+struct brnf_frag_data {
+	char mac[NF_BRIDGE_MAX_MAC_HEADER_LENGTH];
+	u8 encap_size;
+	u8 size;
+};
+
+static DEFINE_PER_CPU(struct brnf_frag_data, brnf_frag_data_storage);
+#endif
+
+static struct nf_bridge_info *nf_bridge_info_get(const struct sk_buff *skb)
+{
+	return skb->nf_bridge;
+}
+
 static inline struct rtable *bridge_parent_rtable(const struct net_device *dev)
 {
 	struct net_bridge_port *port;
@@ -153,6 +167,18 @@ static inline struct nf_bridge_info *nf_bridge_unshare(struct sk_buff *skb)
 	return nf_bridge;
 }
 
+static unsigned int nf_bridge_encap_header_len(const struct sk_buff *skb)
+{
+	switch (skb->protocol) {
+	case __cpu_to_be16(ETH_P_8021Q):
+		return VLAN_HLEN;
+	case __cpu_to_be16(ETH_P_PPP_SES):
+		return PPPOE_SES_HLEN;
+	default:
+		return 0;
+	}
+}
+
 static inline void nf_bridge_push_encap_header(struct sk_buff *skb)
 {
 	unsigned int len = nf_bridge_encap_header_len(skb);
@@ -177,14 +203,6 @@ static inline void nf_bridge_pull_encap_header_rcsum(struct sk_buff *skb)
 	skb->network_header += len;
 }
 
-static inline void nf_bridge_save_header(struct sk_buff *skb)
-{
-	int header_size = ETH_HLEN + nf_bridge_encap_header_len(skb);
-
-	skb_copy_from_linear_data_offset(skb, -header_size,
-					 skb->nf_bridge->data, header_size);
-}
-
 /* When handing a packet over to the IP layer
  * check whether we have a skb that is in the
  * expected format
@@ -238,17 +256,31 @@ drop:
 	return -1;
 }
 
+static void nf_bridge_update_protocol(struct sk_buff *skb)
+{
+	switch (skb->nf_bridge->orig_proto) {
+	case BRNF_PROTO_8021Q:
+		skb->protocol = htons(ETH_P_8021Q);
+		break;
+	case BRNF_PROTO_PPPOE:
+		skb->protocol = htons(ETH_P_PPP_SES);
+		break;
+	case BRNF_PROTO_UNCHANGED:
+		break;
+	}
+}
+
 /* PF_BRIDGE/PRE_ROUTING *********************************************/
 /* Undo the changes made for ip6tables PREROUTING and continue the
  * bridge PRE_ROUTING hook. */
-static int br_nf_pre_routing_finish_ipv6(struct sk_buff *skb)
+static int br_nf_pre_routing_finish_ipv6(struct sock *sk, struct sk_buff *skb)
 {
-	struct nf_bridge_info *nf_bridge = skb->nf_bridge;
+	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 	struct rtable *rt;
 
-	if (nf_bridge->mask & BRNF_PKT_TYPE) {
+	if (nf_bridge->pkt_otherhost) {
 		skb->pkt_type = PACKET_OTHERHOST;
-		nf_bridge->mask ^= BRNF_PKT_TYPE;
+		nf_bridge->pkt_otherhost = false;
 	}
 	nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING;
 
@@ -262,7 +294,8 @@ static int br_nf_pre_routing_finish_ipv6(struct sk_buff *skb)
 	skb->dev = nf_bridge->physindev;
 	nf_bridge_update_protocol(skb);
 	nf_bridge_push_encap_header(skb);
-	NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL,
+	NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, sk, skb,
+		       skb->dev, NULL,
 		       br_handle_frame_finish, 1);
 
 	return 0;
@@ -273,9 +306,8 @@ static int br_nf_pre_routing_finish_ipv6(struct sk_buff *skb)
  * don't, we use the neighbour framework to find out. In both cases, we make
  * sure that br_handle_frame_finish() is called afterwards.
  */
-static int br_nf_pre_routing_finish_bridge(struct sk_buff *skb)
+static int br_nf_pre_routing_finish_bridge(struct sock *sk, struct sk_buff *skb)
 {
-	struct nf_bridge_info *nf_bridge = skb->nf_bridge;
 	struct neighbour *neigh;
 	struct dst_entry *dst;
 
@@ -285,12 +317,13 @@ static int br_nf_pre_routing_finish_bridge(struct sk_buff *skb)
 	dst = skb_dst(skb);
 	neigh = dst_neigh_lookup_skb(dst, skb);
 	if (neigh) {
+		struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 		int ret;
 
 		if (neigh->hh.hh_len) {
 			neigh_hh_bridge(&neigh->hh, skb);
 			skb->dev = nf_bridge->physindev;
-			ret = br_handle_frame_finish(skb);
+			ret = br_handle_frame_finish(sk, skb);
 		} else {
 			/* the neighbour function below overwrites the complete
 			 * MAC header, so we save the Ethernet source address and
@@ -298,7 +331,7 @@ static int br_nf_pre_routing_finish_bridge(struct sk_buff *skb)
 			 */
 			skb_copy_from_linear_data_offset(skb,
 							 -(ETH_HLEN-ETH_ALEN),
-							 skb->nf_bridge->data,
+							 nf_bridge->neigh_header,
 							 ETH_HLEN-ETH_ALEN);
 			/* tell br_dev_xmit to continue with forwarding */
 			nf_bridge->mask |= BRNF_BRIDGED_DNAT;
@@ -313,8 +346,15 @@ free_skb:
 	return 0;
 }
 
+static bool daddr_was_changed(const struct sk_buff *skb,
+			      const struct nf_bridge_info *nf_bridge)
+{
+	return ip_hdr(skb)->daddr != nf_bridge->ipv4_daddr;
+}
+
 /* This requires some explaining. If DNAT has taken place,
  * we will need to fix up the destination Ethernet address.
+ * This is also true when SNAT takes place (for the reply direction).
  *
  * There are two cases to consider:
  * 1. The packet was DNAT'ed to a device in the same bridge
@@ -351,11 +391,11 @@ free_skb:
  * device, we proceed as if ip_route_input() succeeded. If it differs from the
  * logical bridge port or if ip_route_output_key() fails we drop the packet.
  */
-static int br_nf_pre_routing_finish(struct sk_buff *skb)
+static int br_nf_pre_routing_finish(struct sock *sk, struct sk_buff *skb)
 {
 	struct net_device *dev = skb->dev;
 	struct iphdr *iph = ip_hdr(skb);
-	struct nf_bridge_info *nf_bridge = skb->nf_bridge;
+	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 	struct rtable *rt;
 	int err;
 	int frag_max_size;
@@ -363,12 +403,12 @@ static int br_nf_pre_routing_finish(struct sk_buff *skb)
 	frag_max_size = IPCB(skb)->frag_max_size;
 	BR_INPUT_SKB_CB(skb)->frag_max_size = frag_max_size;
 
-	if (nf_bridge->mask & BRNF_PKT_TYPE) {
+	if (nf_bridge->pkt_otherhost) {
 		skb->pkt_type = PACKET_OTHERHOST;
-		nf_bridge->mask ^= BRNF_PKT_TYPE;
+		nf_bridge->pkt_otherhost = false;
 	}
 	nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING;
-	if (dnat_took_place(skb)) {
+	if (daddr_was_changed(skb, nf_bridge)) {
 		if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) {
 			struct in_device *in_dev = __in_dev_get_rcu(dev);
 
@@ -404,7 +444,7 @@ bridged_dnat:
 				nf_bridge_push_encap_header(skb);
 				NF_HOOK_THRESH(NFPROTO_BRIDGE,
 					       NF_BR_PRE_ROUTING,
-					       skb, skb->dev, NULL,
+					       sk, skb, skb->dev, NULL,
 					       br_nf_pre_routing_finish_bridge,
 					       1);
 				return 0;
@@ -424,7 +464,8 @@ bridged_dnat:
 	skb->dev = nf_bridge->physindev;
 	nf_bridge_update_protocol(skb);
 	nf_bridge_push_encap_header(skb);
-	NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL,
+	NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, sk, skb,
+		       skb->dev, NULL,
 		       br_handle_frame_finish, 1);
 
 	return 0;
@@ -435,11 +476,11 @@ static struct net_device *brnf_get_logical_dev(struct sk_buff *skb, const struct
 	struct net_device *vlan, *br;
 
 	br = bridge_parent(dev);
-	if (brnf_pass_vlan_indev == 0 || !vlan_tx_tag_present(skb))
+	if (brnf_pass_vlan_indev == 0 || !skb_vlan_tag_present(skb))
 		return br;
 
 	vlan = __vlan_find_dev_deep_rcu(br, skb->vlan_proto,
-				    vlan_tx_tag_get(skb) & VLAN_VID_MASK);
+				    skb_vlan_tag_get(skb) & VLAN_VID_MASK);
 
 	return vlan ? vlan : br;
 }
@@ -447,20 +488,21 @@ static struct net_device *brnf_get_logical_dev(struct sk_buff *skb, const struct
 /* Some common code for IPv4/IPv6 */
 static struct net_device *setup_pre_routing(struct sk_buff *skb)
 {
-	struct nf_bridge_info *nf_bridge = skb->nf_bridge;
+	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 
 	if (skb->pkt_type == PACKET_OTHERHOST) {
 		skb->pkt_type = PACKET_HOST;
-		nf_bridge->mask |= BRNF_PKT_TYPE;
+		nf_bridge->pkt_otherhost = true;
 	}
 
 	nf_bridge->mask |= BRNF_NF_BRIDGE_PREROUTING;
 	nf_bridge->physindev = skb->dev;
 	skb->dev = brnf_get_logical_dev(skb, skb->dev);
+
 	if (skb->protocol == htons(ETH_P_8021Q))
-		nf_bridge->mask |= BRNF_8021Q;
+		nf_bridge->orig_proto = BRNF_PROTO_8021Q;
 	else if (skb->protocol == htons(ETH_P_PPP_SES))
-		nf_bridge->mask |= BRNF_PPPoE;
+		nf_bridge->orig_proto = BRNF_PROTO_PPPOE;
 
 	/* Must drop socket now because of tproxy. */
 	skb_orphan(skb);
@@ -526,9 +568,7 @@ bad:
  * to ip6tables, which doesn't support NAT, so things are fairly simple. */
 static unsigned int br_nf_pre_routing_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 *))
+					   const struct nf_hook_state *state)
 {
 	const struct ipv6hdr *hdr;
 	u32 pkt_len;
@@ -562,7 +602,8 @@ static unsigned int br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops,
 		return NF_DROP;
 
 	skb->protocol = htons(ETH_P_IPV6);
-	NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, skb, skb->dev, NULL,
+	NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, state->sk, skb,
+		skb->dev, NULL,
 		br_nf_pre_routing_finish_ipv6);
 
 	return NF_STOLEN;
@@ -576,10 +617,9 @@ static unsigned int br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops,
  * address to be able to detect DNAT afterwards. */
 static unsigned int br_nf_pre_routing(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 *))
+				      const struct nf_hook_state *state)
 {
+	struct nf_bridge_info *nf_bridge;
 	struct net_bridge_port *p;
 	struct net_bridge *br;
 	__u32 len = nf_bridge_encap_header_len(skb);
@@ -587,7 +627,7 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops,
 	if (unlikely(!pskb_may_pull(skb, len)))
 		return NF_DROP;
 
-	p = br_port_get_rcu(in);
+	p = br_port_get_rcu(state->in);
 	if (p == NULL)
 		return NF_DROP;
 	br = p->br;
@@ -597,7 +637,7 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops,
 			return NF_ACCEPT;
 
 		nf_bridge_pull_encap_header_rcsum(skb);
-		return br_nf_pre_routing_ipv6(ops, skb, in, out, okfn);
+		return br_nf_pre_routing_ipv6(ops, skb, state);
 	}
 
 	if (!brnf_call_iptables && !br->nf_call_iptables)
@@ -616,10 +656,14 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops,
 		return NF_DROP;
 	if (!setup_pre_routing(skb))
 		return NF_DROP;
-	store_orig_dstaddr(skb);
+
+	nf_bridge = nf_bridge_info_get(skb);
+	nf_bridge->ipv4_daddr = ip_hdr(skb)->daddr;
+
 	skb->protocol = htons(ETH_P_IP);
 
-	NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, skb, skb->dev, NULL,
+	NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, state->sk, skb,
+		skb->dev, NULL,
 		br_nf_pre_routing_finish);
 
 	return NF_STOLEN;
@@ -635,25 +679,30 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops,
  * prevent this from happening. */
 static unsigned int br_nf_local_in(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 *))
+				   const struct nf_hook_state *state)
 {
 	br_drop_fake_rtable(skb);
 	return NF_ACCEPT;
 }
 
 /* PF_BRIDGE/FORWARD *************************************************/
-static int br_nf_forward_finish(struct sk_buff *skb)
+static int br_nf_forward_finish(struct sock *sk, struct sk_buff *skb)
 {
-	struct nf_bridge_info *nf_bridge = skb->nf_bridge;
+	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 	struct net_device *in;
 
 	if (!IS_ARP(skb) && !IS_VLAN_ARP(skb)) {
+		int frag_max_size;
+
+		if (skb->protocol == htons(ETH_P_IP)) {
+			frag_max_size = IPCB(skb)->frag_max_size;
+			BR_INPUT_SKB_CB(skb)->frag_max_size = frag_max_size;
+		}
+
 		in = nf_bridge->physindev;
-		if (nf_bridge->mask & BRNF_PKT_TYPE) {
+		if (nf_bridge->pkt_otherhost) {
 			skb->pkt_type = PACKET_OTHERHOST;
-			nf_bridge->mask ^= BRNF_PKT_TYPE;
+			nf_bridge->pkt_otherhost = false;
 		}
 		nf_bridge_update_protocol(skb);
 	} else {
@@ -661,8 +710,8 @@ static int br_nf_forward_finish(struct sk_buff *skb)
 	}
 	nf_bridge_push_encap_header(skb);
 
-	NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_FORWARD, skb, in,
-		       skb->dev, br_forward_finish, 1);
+	NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_FORWARD, sk, skb,
+		       in, skb->dev, br_forward_finish, 1);
 	return 0;
 }
 
@@ -674,9 +723,7 @@ static int br_nf_forward_finish(struct sk_buff *skb)
  * bridge ports. */
 static unsigned int br_nf_forward_ip(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 *))
+				     const struct nf_hook_state *state)
 {
 	struct nf_bridge_info *nf_bridge;
 	struct net_device *parent;
@@ -690,7 +737,11 @@ static unsigned int br_nf_forward_ip(const struct nf_hook_ops *ops,
 	if (!nf_bridge_unshare(skb))
 		return NF_DROP;
 
-	parent = bridge_parent(out);
+	nf_bridge = nf_bridge_info_get(skb);
+	if (!nf_bridge)
+		return NF_DROP;
+
+	parent = bridge_parent(state->out);
 	if (!parent)
 		return NF_DROP;
 
@@ -703,40 +754,42 @@ static unsigned int br_nf_forward_ip(const struct nf_hook_ops *ops,
 
 	nf_bridge_pull_encap_header(skb);
 
-	nf_bridge = skb->nf_bridge;
 	if (skb->pkt_type == PACKET_OTHERHOST) {
 		skb->pkt_type = PACKET_HOST;
-		nf_bridge->mask |= BRNF_PKT_TYPE;
+		nf_bridge->pkt_otherhost = true;
 	}
 
-	if (pf == NFPROTO_IPV4 && br_parse_ip_options(skb))
-		return NF_DROP;
+	if (pf == NFPROTO_IPV4) {
+		int frag_max = BR_INPUT_SKB_CB(skb)->frag_max_size;
+
+		if (br_parse_ip_options(skb))
+			return NF_DROP;
+
+		IPCB(skb)->frag_max_size = frag_max;
+	}
 
-	/* The physdev module checks on this */
-	nf_bridge->mask |= BRNF_BRIDGED;
 	nf_bridge->physoutdev = skb->dev;
 	if (pf == NFPROTO_IPV4)
 		skb->protocol = htons(ETH_P_IP);
 	else
 		skb->protocol = htons(ETH_P_IPV6);
 
-	NF_HOOK(pf, NF_INET_FORWARD, skb, brnf_get_logical_dev(skb, in), parent,
-		br_nf_forward_finish);
+	NF_HOOK(pf, NF_INET_FORWARD, NULL, skb,
+		brnf_get_logical_dev(skb, state->in),
+		parent,	br_nf_forward_finish);
 
 	return NF_STOLEN;
 }
 
 static unsigned int br_nf_forward_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 *))
+				      const struct nf_hook_state *state)
 {
 	struct net_bridge_port *p;
 	struct net_bridge *br;
 	struct net_device **d = (struct net_device **)(skb->cb);
 
-	p = br_port_get_rcu(out);
+	p = br_port_get_rcu(state->out);
 	if (p == NULL)
 		return NF_ACCEPT;
 	br = p->br;
@@ -755,55 +808,93 @@ static unsigned int br_nf_forward_arp(const struct nf_hook_ops *ops,
 			nf_bridge_push_encap_header(skb);
 		return NF_ACCEPT;
 	}
-	*d = (struct net_device *)in;
-	NF_HOOK(NFPROTO_ARP, NF_ARP_FORWARD, skb, (struct net_device *)in,
-		(struct net_device *)out, br_nf_forward_finish);
+	*d = state->in;
+	NF_HOOK(NFPROTO_ARP, NF_ARP_FORWARD, state->sk, skb,
+		state->in, state->out, br_nf_forward_finish);
 
 	return NF_STOLEN;
 }
 
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4)
-static int br_nf_dev_queue_xmit(struct sk_buff *skb)
+static int br_nf_push_frag_xmit(struct sock *sk, struct sk_buff *skb)
+{
+	struct brnf_frag_data *data;
+	int err;
+
+	data = this_cpu_ptr(&brnf_frag_data_storage);
+	err = skb_cow_head(skb, data->size);
+
+	if (err) {
+		kfree_skb(skb);
+		return 0;
+	}
+
+	skb_copy_to_linear_data_offset(skb, -data->size, data->mac, data->size);
+	__skb_push(skb, data->encap_size);
+
+	return br_dev_queue_push_xmit(sk, skb);
+}
+
+static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb)
 {
 	int ret;
 	int frag_max_size;
+	unsigned int mtu_reserved;
 
+	if (skb_is_gso(skb) || skb->protocol != htons(ETH_P_IP))
+		return br_dev_queue_push_xmit(sk, skb);
+
+	mtu_reserved = nf_bridge_mtu_reduction(skb);
 	/* This is wrong! We should preserve the original fragment
 	 * boundaries by preserving frag_list rather than refragmenting.
 	 */
-	if (skb->protocol == htons(ETH_P_IP) &&
-	    skb->len + nf_bridge_mtu_reduction(skb) > skb->dev->mtu &&
-	    !skb_is_gso(skb)) {
+	if (skb->len + mtu_reserved > skb->dev->mtu) {
+		struct brnf_frag_data *data;
+
 		frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size;
 		if (br_parse_ip_options(skb))
 			/* Drop invalid packet */
 			return NF_DROP;
 		IPCB(skb)->frag_max_size = frag_max_size;
-		ret = ip_fragment(skb, br_dev_queue_push_xmit);
-	} else
-		ret = br_dev_queue_push_xmit(skb);
+
+		nf_bridge_update_protocol(skb);
+
+		data = this_cpu_ptr(&brnf_frag_data_storage);
+		data->encap_size = nf_bridge_encap_header_len(skb);
+		data->size = ETH_HLEN + data->encap_size;
+
+		skb_copy_from_linear_data_offset(skb, -data->size, data->mac,
+						 data->size);
+
+		ret = ip_fragment(sk, skb, br_nf_push_frag_xmit);
+	} else {
+		ret = br_dev_queue_push_xmit(sk, skb);
+	}
 
 	return ret;
 }
 #else
-static int br_nf_dev_queue_xmit(struct sk_buff *skb)
+static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb)
 {
-        return br_dev_queue_push_xmit(skb);
+        return br_dev_queue_push_xmit(sk, skb);
 }
 #endif
 
 /* PF_BRIDGE/POST_ROUTING ********************************************/
 static unsigned int br_nf_post_routing(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 *))
+				       const struct nf_hook_state *state)
 {
-	struct nf_bridge_info *nf_bridge = skb->nf_bridge;
+	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 	struct net_device *realoutdev = bridge_parent(skb->dev);
 	u_int8_t pf;
 
-	if (!nf_bridge || !(nf_bridge->mask & BRNF_BRIDGED))
+	/* if nf_bridge is set, but ->physoutdev is NULL, this packet came in
+	 * on a bridge, but was delivered locally and is now being routed:
+	 *
+	 * POST_ROUTING was already invoked from the ip stack.
+	 */
+	if (!nf_bridge || !nf_bridge->physoutdev)
 		return NF_ACCEPT;
 
 	if (!realoutdev)
@@ -820,17 +911,17 @@ static unsigned int br_nf_post_routing(const struct nf_hook_ops *ops,
 	 * about the value of skb->pkt_type. */
 	if (skb->pkt_type == PACKET_OTHERHOST) {
 		skb->pkt_type = PACKET_HOST;
-		nf_bridge->mask |= BRNF_PKT_TYPE;
+		nf_bridge->pkt_otherhost = true;
 	}
 
 	nf_bridge_pull_encap_header(skb);
-	nf_bridge_save_header(skb);
 	if (pf == NFPROTO_IPV4)
 		skb->protocol = htons(ETH_P_IP);
 	else
 		skb->protocol = htons(ETH_P_IPV6);
 
-	NF_HOOK(pf, NF_INET_POST_ROUTING, skb, NULL, realoutdev,
+	NF_HOOK(pf, NF_INET_POST_ROUTING, state->sk, skb,
+		NULL, realoutdev,
 		br_nf_dev_queue_xmit);
 
 	return NF_STOLEN;
@@ -841,9 +932,7 @@ static unsigned int br_nf_post_routing(const struct nf_hook_ops *ops,
  * for the second time. */
 static unsigned int ip_sabotage_in(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 *))
+				   const struct nf_hook_state *state)
 {
 	if (skb->nf_bridge &&
 	    !(skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING)) {
@@ -853,6 +942,44 @@ static unsigned int ip_sabotage_in(const struct nf_hook_ops *ops,
 	return NF_ACCEPT;
 }
 
+/* This is called when br_netfilter has called into iptables/netfilter,
+ * and DNAT has taken place on a bridge-forwarded packet.
+ *
+ * neigh->output has created a new MAC header, with local br0 MAC
+ * as saddr.
+ *
+ * This restores the original MAC saddr of the bridged packet
+ * before invoking bridge forward logic to transmit the packet.
+ */
+static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb)
+{
+	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
+
+	skb_pull(skb, ETH_HLEN);
+	nf_bridge->mask &= ~BRNF_BRIDGED_DNAT;
+
+	BUILD_BUG_ON(sizeof(nf_bridge->neigh_header) != (ETH_HLEN - ETH_ALEN));
+
+	skb_copy_to_linear_data_offset(skb, -(ETH_HLEN - ETH_ALEN),
+				       nf_bridge->neigh_header,
+				       ETH_HLEN - ETH_ALEN);
+	skb->dev = nf_bridge->physindev;
+	br_handle_frame_finish(NULL, skb);
+}
+
+static int br_nf_dev_xmit(struct sk_buff *skb)
+{
+	if (skb->nf_bridge && (skb->nf_bridge->mask & BRNF_BRIDGED_DNAT)) {
+		br_nf_pre_routing_finish_bridge_slow(skb);
+		return 1;
+	}
+	return 0;
+}
+
+static const struct nf_br_ops br_ops = {
+	.br_dev_xmit_hook =	br_nf_dev_xmit,
+};
+
 void br_netfilter_enable(void)
 {
 }
@@ -986,19 +1113,18 @@ static int __init br_netfilter_init(void)
 	if (brnf_sysctl_header == NULL) {
 		printk(KERN_WARNING
 		       "br_netfilter: can't register to sysctl.\n");
-		ret = -ENOMEM;
-		goto err1;
+		nf_unregister_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops));
+		return -ENOMEM;
 	}
 #endif
+	RCU_INIT_POINTER(nf_br_ops, &br_ops);
 	printk(KERN_NOTICE "Bridge firewalling registered\n");
 	return 0;
-err1:
-	nf_unregister_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops));
-	return ret;
 }
 
 static void __exit br_netfilter_fini(void)
 {
+	RCU_INIT_POINTER(nf_br_ops, NULL);
 	nf_unregister_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops));
 #ifdef CONFIG_SYSCTL
 	unregister_net_sysctl_table(brnf_sysctl_header);
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 2ff9706647f2..4b5c236998ff 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -16,11 +16,91 @@
 #include <net/rtnetlink.h>
 #include <net/net_namespace.h>
 #include <net/sock.h>
+#include <net/switchdev.h>
 #include <uapi/linux/if_bridge.h>
 
 #include "br_private.h"
 #include "br_private_stp.h"
 
+static int br_get_num_vlan_infos(const struct net_port_vlans *pv,
+				 u32 filter_mask)
+{
+	u16 vid_range_start = 0, vid_range_end = 0;
+	u16 vid_range_flags = 0;
+	u16 pvid, vid, flags;
+	int num_vlans = 0;
+
+	if (filter_mask & RTEXT_FILTER_BRVLAN)
+		return pv->num_vlans;
+
+	if (!(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED))
+		return 0;
+
+	/* Count number of vlan info's
+	 */
+	pvid = br_get_pvid(pv);
+	for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) {
+		flags = 0;
+		if (vid == pvid)
+			flags |= BRIDGE_VLAN_INFO_PVID;
+
+		if (test_bit(vid, pv->untagged_bitmap))
+			flags |= BRIDGE_VLAN_INFO_UNTAGGED;
+
+		if (vid_range_start == 0) {
+			goto initvars;
+		} else if ((vid - vid_range_end) == 1 &&
+			flags == vid_range_flags) {
+			vid_range_end = vid;
+			continue;
+		} else {
+			if ((vid_range_end - vid_range_start) > 0)
+				num_vlans += 2;
+			else
+				num_vlans += 1;
+		}
+initvars:
+		vid_range_start = vid;
+		vid_range_end = vid;
+		vid_range_flags = flags;
+	}
+
+	if (vid_range_start != 0) {
+		if ((vid_range_end - vid_range_start) > 0)
+			num_vlans += 2;
+		else
+			num_vlans += 1;
+	}
+
+	return num_vlans;
+}
+
+static size_t br_get_link_af_size_filtered(const struct net_device *dev,
+					   u32 filter_mask)
+{
+	struct net_port_vlans *pv;
+	int num_vlan_infos;
+
+	rcu_read_lock();
+	if (br_port_exists(dev))
+		pv = nbp_get_vlan_info(br_port_get_rcu(dev));
+	else if (dev->priv_flags & IFF_EBRIDGE)
+		pv = br_get_vlan_info((struct net_bridge *)netdev_priv(dev));
+	else
+		pv = NULL;
+	if (pv)
+		num_vlan_infos = br_get_num_vlan_infos(pv, filter_mask);
+	else
+		num_vlan_infos = 0;
+	rcu_read_unlock();
+
+	if (!num_vlan_infos)
+		return 0;
+
+	/* Each VLAN is returned in bridge_vlan_info along with flags */
+	return num_vlan_infos * nla_total_size(sizeof(struct bridge_vlan_info));
+}
+
 static inline size_t br_port_info_size(void)
 {
 	return nla_total_size(1)	/* IFLA_BRPORT_STATE  */
@@ -35,7 +115,7 @@ static inline size_t br_port_info_size(void)
 		+ 0;
 }
 
-static inline size_t br_nlmsg_size(void)
+static inline size_t br_nlmsg_size(struct net_device *dev, u32 filter_mask)
 {
 	return NLMSG_ALIGN(sizeof(struct ifinfomsg))
 		+ nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */
@@ -44,7 +124,9 @@ static inline size_t br_nlmsg_size(void)
 		+ nla_total_size(4) /* IFLA_MTU */
 		+ nla_total_size(4) /* IFLA_LINK */
 		+ nla_total_size(1) /* IFLA_OPERSTATE */
-		+ nla_total_size(br_port_info_size()); /* IFLA_PROTINFO */
+		+ nla_total_size(br_port_info_size()) /* IFLA_PROTINFO */
+		+ nla_total_size(br_get_link_af_size_filtered(dev,
+				 filter_mask)); /* IFLA_AF_SPEC */
 }
 
 static int br_port_fill_attrs(struct sk_buff *skb,
@@ -60,12 +142,129 @@ static int br_port_fill_attrs(struct sk_buff *skb,
 	    nla_put_u8(skb, IFLA_BRPORT_PROTECT, !!(p->flags & BR_ROOT_BLOCK)) ||
 	    nla_put_u8(skb, IFLA_BRPORT_FAST_LEAVE, !!(p->flags & BR_MULTICAST_FAST_LEAVE)) ||
 	    nla_put_u8(skb, IFLA_BRPORT_LEARNING, !!(p->flags & BR_LEARNING)) ||
-	    nla_put_u8(skb, IFLA_BRPORT_UNICAST_FLOOD, !!(p->flags & BR_FLOOD)))
+	    nla_put_u8(skb, IFLA_BRPORT_UNICAST_FLOOD, !!(p->flags & BR_FLOOD)) ||
+	    nla_put_u8(skb, IFLA_BRPORT_PROXYARP, !!(p->flags & BR_PROXYARP)) ||
+	    nla_put_u8(skb, IFLA_BRPORT_PROXYARP_WIFI,
+		       !!(p->flags & BR_PROXYARP_WIFI)))
 		return -EMSGSIZE;
 
 	return 0;
 }
 
+static int br_fill_ifvlaninfo_range(struct sk_buff *skb, u16 vid_start,
+				    u16 vid_end, u16 flags)
+{
+	struct  bridge_vlan_info vinfo;
+
+	if ((vid_end - vid_start) > 0) {
+		/* add range to skb */
+		vinfo.vid = vid_start;
+		vinfo.flags = flags | BRIDGE_VLAN_INFO_RANGE_BEGIN;
+		if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO,
+			    sizeof(vinfo), &vinfo))
+			goto nla_put_failure;
+
+		vinfo.flags &= ~BRIDGE_VLAN_INFO_RANGE_BEGIN;
+
+		vinfo.vid = vid_end;
+		vinfo.flags = flags | BRIDGE_VLAN_INFO_RANGE_END;
+		if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO,
+			    sizeof(vinfo), &vinfo))
+			goto nla_put_failure;
+	} else {
+		vinfo.vid = vid_start;
+		vinfo.flags = flags;
+		if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO,
+			    sizeof(vinfo), &vinfo))
+			goto nla_put_failure;
+	}
+
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
+static int br_fill_ifvlaninfo_compressed(struct sk_buff *skb,
+					 const struct net_port_vlans *pv)
+{
+	u16 vid_range_start = 0, vid_range_end = 0;
+	u16 vid_range_flags = 0;
+	u16 pvid, vid, flags;
+	int err = 0;
+
+	/* Pack IFLA_BRIDGE_VLAN_INFO's for every vlan
+	 * and mark vlan info with begin and end flags
+	 * if vlaninfo represents a range
+	 */
+	pvid = br_get_pvid(pv);
+	for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) {
+		flags = 0;
+		if (vid == pvid)
+			flags |= BRIDGE_VLAN_INFO_PVID;
+
+		if (test_bit(vid, pv->untagged_bitmap))
+			flags |= BRIDGE_VLAN_INFO_UNTAGGED;
+
+		if (vid_range_start == 0) {
+			goto initvars;
+		} else if ((vid - vid_range_end) == 1 &&
+			flags == vid_range_flags) {
+			vid_range_end = vid;
+			continue;
+		} else {
+			err = br_fill_ifvlaninfo_range(skb, vid_range_start,
+						       vid_range_end,
+						       vid_range_flags);
+			if (err)
+				return err;
+		}
+
+initvars:
+		vid_range_start = vid;
+		vid_range_end = vid;
+		vid_range_flags = flags;
+	}
+
+	if (vid_range_start != 0) {
+		/* Call it once more to send any left over vlans */
+		err = br_fill_ifvlaninfo_range(skb, vid_range_start,
+					       vid_range_end,
+					       vid_range_flags);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int br_fill_ifvlaninfo(struct sk_buff *skb,
+			      const struct net_port_vlans *pv)
+{
+	struct bridge_vlan_info vinfo;
+	u16 pvid, vid;
+
+	pvid = br_get_pvid(pv);
+	for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) {
+		vinfo.vid = vid;
+		vinfo.flags = 0;
+		if (vid == pvid)
+			vinfo.flags |= BRIDGE_VLAN_INFO_PVID;
+
+		if (test_bit(vid, pv->untagged_bitmap))
+			vinfo.flags |= BRIDGE_VLAN_INFO_UNTAGGED;
+
+		if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO,
+			    sizeof(vinfo), &vinfo))
+			goto nla_put_failure;
+	}
+
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
 /*
  * Create one netlink message for one interface
  * Contains port and master info as well as carrier and bridge state.
@@ -106,8 +305,8 @@ static int br_fill_ifinfo(struct sk_buff *skb,
 	    nla_put_u8(skb, IFLA_OPERSTATE, operstate) ||
 	    (dev->addr_len &&
 	     nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) ||
-	    (dev->ifindex != dev->iflink &&
-	     nla_put_u32(skb, IFLA_LINK, dev->iflink)))
+	    (dev->ifindex != dev_get_iflink(dev) &&
+	     nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev))))
 		goto nla_put_failure;
 
 	if (event == RTM_NEWLINK && port) {
@@ -120,12 +319,11 @@ static int br_fill_ifinfo(struct sk_buff *skb,
 	}
 
 	/* Check if  the VID information is requested */
-	if (filter_mask & RTEXT_FILTER_BRVLAN) {
-		struct nlattr *af;
+	if ((filter_mask & RTEXT_FILTER_BRVLAN) ||
+	    (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) {
 		const struct net_port_vlans *pv;
-		struct bridge_vlan_info vinfo;
-		u16 vid;
-		u16 pvid;
+		struct nlattr *af;
+		int err;
 
 		if (port)
 			pv = nbp_get_vlan_info(port);
@@ -139,26 +337,18 @@ static int br_fill_ifinfo(struct sk_buff *skb,
 		if (!af)
 			goto nla_put_failure;
 
-		pvid = br_get_pvid(pv);
-		for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) {
-			vinfo.vid = vid;
-			vinfo.flags = 0;
-			if (vid == pvid)
-				vinfo.flags |= BRIDGE_VLAN_INFO_PVID;
-
-			if (test_bit(vid, pv->untagged_bitmap))
-				vinfo.flags |= BRIDGE_VLAN_INFO_UNTAGGED;
-
-			if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO,
-				    sizeof(vinfo), &vinfo))
-				goto nla_put_failure;
-		}
-
+		if (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)
+			err = br_fill_ifvlaninfo_compressed(skb, pv);
+		else
+			err = br_fill_ifvlaninfo(skb, pv);
+		if (err)
+			goto nla_put_failure;
 		nla_nest_end(skb, af);
 	}
 
 done:
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
@@ -173,6 +363,7 @@ void br_ifinfo_notify(int event, struct net_bridge_port *port)
 	struct net *net;
 	struct sk_buff *skb;
 	int err = -ENOBUFS;
+	u32 filter = RTEXT_FILTER_BRVLAN_COMPRESSED;
 
 	if (!port)
 		return;
@@ -181,11 +372,11 @@ void br_ifinfo_notify(int event, struct net_bridge_port *port)
 	br_debug(port->br, "port %u(%s) event %d\n",
 		 (unsigned int)port->port_no, port->dev->name, event);
 
-	skb = nlmsg_new(br_nlmsg_size(), GFP_ATOMIC);
+	skb = nlmsg_new(br_nlmsg_size(port->dev, filter), GFP_ATOMIC);
 	if (skb == NULL)
 		goto errout;
 
-	err = br_fill_ifinfo(skb, port, 0, 0, event, 0, 0, port->dev);
+	err = br_fill_ifinfo(skb, port, 0, 0, event, 0, filter, port->dev);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in br_nlmsg_size() */
 		WARN_ON(err == -EMSGSIZE);
@@ -203,71 +394,101 @@ errout:
  * Dump information about all ports, in response to GETLINK
  */
 int br_getlink(struct sk_buff *skb, u32 pid, u32 seq,
-	       struct net_device *dev, u32 filter_mask)
+	       struct net_device *dev, u32 filter_mask, int nlflags)
 {
-	int err = 0;
 	struct net_bridge_port *port = br_port_get_rtnl(dev);
 
-	if (!port && !(filter_mask & RTEXT_FILTER_BRVLAN))
-		goto out;
+	if (!port && !(filter_mask & RTEXT_FILTER_BRVLAN) &&
+	    !(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED))
+		return 0;
+
+	return br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, nlflags,
+			      filter_mask, dev);
+}
+
+static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p,
+			int cmd, struct bridge_vlan_info *vinfo)
+{
+	int err = 0;
+
+	switch (cmd) {
+	case RTM_SETLINK:
+		if (p) {
+			err = nbp_vlan_add(p, vinfo->vid, vinfo->flags);
+			if (err)
+				break;
+
+			if (vinfo->flags & BRIDGE_VLAN_INFO_MASTER)
+				err = br_vlan_add(p->br, vinfo->vid,
+						  vinfo->flags);
+		} else {
+			err = br_vlan_add(br, vinfo->vid, vinfo->flags);
+		}
+		break;
+
+	case RTM_DELLINK:
+		if (p) {
+			nbp_vlan_delete(p, vinfo->vid);
+			if (vinfo->flags & BRIDGE_VLAN_INFO_MASTER)
+				br_vlan_delete(p->br, vinfo->vid);
+		} else {
+			br_vlan_delete(br, vinfo->vid);
+		}
+		break;
+	}
 
-	err = br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, NLM_F_MULTI,
-			     filter_mask, dev);
-out:
 	return err;
 }
 
-static const struct nla_policy ifla_br_policy[IFLA_MAX+1] = {
-	[IFLA_BRIDGE_FLAGS]	= { .type = NLA_U16 },
-	[IFLA_BRIDGE_MODE]	= { .type = NLA_U16 },
-	[IFLA_BRIDGE_VLAN_INFO]	= { .type = NLA_BINARY,
-				    .len = sizeof(struct bridge_vlan_info), },
-};
-
 static int br_afspec(struct net_bridge *br,
 		     struct net_bridge_port *p,
 		     struct nlattr *af_spec,
 		     int cmd)
 {
-	struct nlattr *tb[IFLA_BRIDGE_MAX+1];
+	struct bridge_vlan_info *vinfo_start = NULL;
+	struct bridge_vlan_info *vinfo = NULL;
+	struct nlattr *attr;
 	int err = 0;
+	int rem;
 
-	err = nla_parse_nested(tb, IFLA_BRIDGE_MAX, af_spec, ifla_br_policy);
-	if (err)
-		return err;
+	nla_for_each_nested(attr, af_spec, rem) {
+		if (nla_type(attr) != IFLA_BRIDGE_VLAN_INFO)
+			continue;
+		if (nla_len(attr) != sizeof(struct bridge_vlan_info))
+			return -EINVAL;
+		vinfo = nla_data(attr);
+		if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) {
+			if (vinfo_start)
+				return -EINVAL;
+			vinfo_start = vinfo;
+			continue;
+		}
 
-	if (tb[IFLA_BRIDGE_VLAN_INFO]) {
-		struct bridge_vlan_info *vinfo;
+		if (vinfo_start) {
+			struct bridge_vlan_info tmp_vinfo;
+			int v;
 
-		vinfo = nla_data(tb[IFLA_BRIDGE_VLAN_INFO]);
+			if (!(vinfo->flags & BRIDGE_VLAN_INFO_RANGE_END))
+				return -EINVAL;
 
-		if (!vinfo->vid || vinfo->vid >= VLAN_VID_MASK)
-			return -EINVAL;
+			if (vinfo->vid <= vinfo_start->vid)
+				return -EINVAL;
 
-		switch (cmd) {
-		case RTM_SETLINK:
-			if (p) {
-				err = nbp_vlan_add(p, vinfo->vid, vinfo->flags);
+			memcpy(&tmp_vinfo, vinfo_start,
+			       sizeof(struct bridge_vlan_info));
+
+			for (v = vinfo_start->vid; v <= vinfo->vid; v++) {
+				tmp_vinfo.vid = v;
+				err = br_vlan_info(br, p, cmd, &tmp_vinfo);
 				if (err)
 					break;
-
-				if (vinfo->flags & BRIDGE_VLAN_INFO_MASTER)
-					err = br_vlan_add(p->br, vinfo->vid,
-							  vinfo->flags);
-			} else
-				err = br_vlan_add(br, vinfo->vid, vinfo->flags);
-
-			break;
-
-		case RTM_DELLINK:
-			if (p) {
-				nbp_vlan_delete(p, vinfo->vid);
-				if (vinfo->flags & BRIDGE_VLAN_INFO_MASTER)
-					br_vlan_delete(p->br, vinfo->vid);
-			} else
-				br_vlan_delete(br, vinfo->vid);
-			break;
+			}
+			vinfo_start = NULL;
+		} else {
+			err = br_vlan_info(br, p, cmd, vinfo);
 		}
+		if (err)
+			break;
 	}
 
 	return err;
@@ -280,6 +501,7 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = {
 	[IFLA_BRPORT_MODE]	= { .type = NLA_U8 },
 	[IFLA_BRPORT_GUARD]	= { .type = NLA_U8 },
 	[IFLA_BRPORT_PROTECT]	= { .type = NLA_U8 },
+	[IFLA_BRPORT_FAST_LEAVE]= { .type = NLA_U8 },
 	[IFLA_BRPORT_LEARNING]	= { .type = NLA_U8 },
 	[IFLA_BRPORT_UNICAST_FLOOD] = { .type = NLA_U8 },
 };
@@ -332,6 +554,8 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[])
 	br_set_port_flag(p, tb, IFLA_BRPORT_PROTECT, BR_ROOT_BLOCK);
 	br_set_port_flag(p, tb, IFLA_BRPORT_LEARNING, BR_LEARNING);
 	br_set_port_flag(p, tb, IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD);
+	br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP, BR_PROXYARP);
+	br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP_WIFI, BR_PROXYARP_WIFI);
 
 	if (tb[IFLA_BRPORT_COST]) {
 		err = br_stp_set_path_cost(p, nla_get_u32(tb[IFLA_BRPORT_COST]));
@@ -356,13 +580,13 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[])
 }
 
 /* Change state and parameters on port. */
-int br_setlink(struct net_device *dev, struct nlmsghdr *nlh)
+int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags)
 {
 	struct nlattr *protinfo;
 	struct nlattr *afspec;
 	struct net_bridge_port *p;
 	struct nlattr *tb[IFLA_BRPORT_MAX + 1];
-	int err = 0;
+	int err = 0, ret_offload = 0;
 
 	protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_PROTINFO);
 	afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
@@ -404,19 +628,28 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh)
 				afspec, RTM_SETLINK);
 	}
 
+	if (p && !(flags & BRIDGE_FLAGS_SELF)) {
+		/* set bridge attributes in hardware if supported
+		 */
+		ret_offload = netdev_switch_port_bridge_setlink(dev, nlh,
+								flags);
+		if (ret_offload && ret_offload != -EOPNOTSUPP)
+			br_warn(p->br, "error setting attrs on port %u(%s)\n",
+				(unsigned int)p->port_no, p->dev->name);
+	}
+
 	if (err == 0)
 		br_ifinfo_notify(RTM_NEWLINK, p);
-
 out:
 	return err;
 }
 
 /* Delete port information */
-int br_dellink(struct net_device *dev, struct nlmsghdr *nlh)
+int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags)
 {
 	struct nlattr *afspec;
 	struct net_bridge_port *p;
-	int err;
+	int err = 0, ret_offload = 0;
 
 	afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
 	if (!afspec)
@@ -429,6 +662,21 @@ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh)
 
 	err = br_afspec((struct net_bridge *)netdev_priv(dev), p,
 			afspec, RTM_DELLINK);
+	if (err == 0)
+		/* Send RTM_NEWLINK because userspace
+		 * expects RTM_NEWLINK for vlan dels
+		 */
+		br_ifinfo_notify(RTM_NEWLINK, p);
+
+	if (p && !(flags & BRIDGE_FLAGS_SELF)) {
+		/* del bridge attributes in hardware
+		 */
+		ret_offload = netdev_switch_port_bridge_dellink(dev, nlh,
+								flags);
+		if (ret_offload && ret_offload != -EOPNOTSUPP)
+			br_warn(p->br, "error deleting attrs on port %u (%s)\n",
+				(unsigned int)p->port_no, p->dev->name);
+	}
 
 	return err;
 }
@@ -485,6 +733,9 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = {
 	[IFLA_BR_FORWARD_DELAY]	= { .type = NLA_U32 },
 	[IFLA_BR_HELLO_TIME]	= { .type = NLA_U32 },
 	[IFLA_BR_MAX_AGE]	= { .type = NLA_U32 },
+	[IFLA_BR_AGEING_TIME] = { .type = NLA_U32 },
+	[IFLA_BR_STP_STATE] = { .type = NLA_U32 },
+	[IFLA_BR_PRIORITY] = { .type = NLA_U16 },
 };
 
 static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
@@ -514,6 +765,24 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
 			return err;
 	}
 
+	if (data[IFLA_BR_AGEING_TIME]) {
+		u32 ageing_time = nla_get_u32(data[IFLA_BR_AGEING_TIME]);
+
+		br->ageing_time = clock_t_to_jiffies(ageing_time);
+	}
+
+	if (data[IFLA_BR_STP_STATE]) {
+		u32 stp_enabled = nla_get_u32(data[IFLA_BR_STP_STATE]);
+
+		br_stp_set_enabled(br, stp_enabled);
+	}
+
+	if (data[IFLA_BR_PRIORITY]) {
+		u32 priority = nla_get_u16(data[IFLA_BR_PRIORITY]);
+
+		br_stp_set_bridge_priority(br, priority);
+	}
+
 	return 0;
 }
 
@@ -522,6 +791,9 @@ static size_t br_get_size(const struct net_device *brdev)
 	return nla_total_size(sizeof(u32)) +	/* IFLA_BR_FORWARD_DELAY  */
 	       nla_total_size(sizeof(u32)) +	/* IFLA_BR_HELLO_TIME */
 	       nla_total_size(sizeof(u32)) +	/* IFLA_BR_MAX_AGE */
+	       nla_total_size(sizeof(u32)) +    /* IFLA_BR_AGEING_TIME */
+	       nla_total_size(sizeof(u32)) +    /* IFLA_BR_STP_STATE */
+	       nla_total_size(sizeof(u16)) +    /* IFLA_BR_PRIORITY */
 	       0;
 }
 
@@ -531,10 +803,16 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev)
 	u32 forward_delay = jiffies_to_clock_t(br->forward_delay);
 	u32 hello_time = jiffies_to_clock_t(br->hello_time);
 	u32 age_time = jiffies_to_clock_t(br->max_age);
+	u32 ageing_time = jiffies_to_clock_t(br->ageing_time);
+	u32 stp_enabled = br->stp_enabled;
+	u16 priority = (br->bridge_id.prio[0] << 8) | br->bridge_id.prio[1];
 
 	if (nla_put_u32(skb, IFLA_BR_FORWARD_DELAY, forward_delay) ||
 	    nla_put_u32(skb, IFLA_BR_HELLO_TIME, hello_time) ||
-	    nla_put_u32(skb, IFLA_BR_MAX_AGE, age_time))
+	    nla_put_u32(skb, IFLA_BR_MAX_AGE, age_time) ||
+	    nla_put_u32(skb, IFLA_BR_AGEING_TIME, ageing_time) ||
+	    nla_put_u32(skb, IFLA_BR_STP_STATE, stp_enabled) ||
+	    nla_put_u16(skb, IFLA_BR_PRIORITY, priority))
 		return -EMSGSIZE;
 
 	return 0;
@@ -558,7 +836,7 @@ static size_t br_get_link_af_size(const struct net_device *dev)
 	return pv->num_vlans * nla_total_size(sizeof(struct bridge_vlan_info));
 }
 
-static struct rtnl_af_ops br_af_ops = {
+static struct rtnl_af_ops br_af_ops __read_mostly = {
 	.family			= AF_BRIDGE,
 	.get_link_af_size	= br_get_link_af_size,
 };
diff --git a/net/bridge/br_nf_core.c b/net/bridge/br_nf_core.c
index 387cb3bd017c..20cbb727df4d 100644
--- a/net/bridge/br_nf_core.c
+++ b/net/bridge/br_nf_core.c
@@ -54,7 +54,6 @@ static unsigned int fake_mtu(const struct dst_entry *dst)
 
 static struct dst_ops fake_dst_ops = {
 	.family		= AF_INET,
-	.protocol	= cpu_to_be16(ETH_P_IP),
 	.update_pmtu	= fake_update_pmtu,
 	.redirect	= fake_redirect,
 	.cow_metrics	= fake_cow_metrics,
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 4d783d071305..3362c29400f1 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -98,9 +98,10 @@ struct net_bridge_fdb_entry
 	unsigned long			updated;
 	unsigned long			used;
 	mac_addr			addr;
-	unsigned char			is_local;
-	unsigned char			is_static;
-	unsigned char			added_by_user;
+	unsigned char			is_local:1,
+					is_static:1,
+					added_by_user:1,
+					added_by_external_learn:1;
 	__u16				vlan_id;
 };
 
@@ -163,15 +164,6 @@ struct net_bridge_port
 	struct rcu_head			rcu;
 
 	unsigned long 			flags;
-#define BR_HAIRPIN_MODE		0x00000001
-#define BR_BPDU_GUARD           0x00000002
-#define BR_ROOT_BLOCK		0x00000004
-#define BR_MULTICAST_FAST_LEAVE	0x00000008
-#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_own_query	ip4_own_query;
@@ -313,6 +305,7 @@ struct br_input_skb_cb {
 #endif
 
 	u16 frag_max_size;
+	bool proxyarp_replied;
 
 #ifdef CONFIG_BRIDGE_VLAN_FILTERING
 	bool vlan_filtered;
@@ -403,20 +396,24 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
 		   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);
+		  struct net_device *dev, const unsigned char *addr, u16 vid);
 int br_fdb_add(struct ndmsg *nlh, struct nlattr *tb[], struct net_device *dev,
-	       const unsigned char *addr, u16 nlh_flags);
+	       const unsigned char *addr, u16 vid, u16 nlh_flags);
 int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
 		struct net_device *dev, struct net_device *fdev, 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);
+int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p,
+			      const unsigned char *addr, u16 vid);
+int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p,
+			      const unsigned char *addr, u16 vid);
 
 /* br_forward.c */
 void br_deliver(const struct net_bridge_port *to, struct sk_buff *skb);
-int br_dev_queue_push_xmit(struct sk_buff *skb);
+int br_dev_queue_push_xmit(struct sock *sk, struct sk_buff *skb);
 void br_forward(const struct net_bridge_port *to,
 		struct sk_buff *skb, struct sk_buff *skb0);
-int br_forward_finish(struct sk_buff *skb);
+int br_forward_finish(struct sock *sk, struct sk_buff *skb);
 void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb, bool unicast);
 void br_flood_forward(struct net_bridge *br, struct sk_buff *skb,
 		      struct sk_buff *skb2, bool unicast);
@@ -434,7 +431,7 @@ 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);
+int br_handle_frame_finish(struct sock *sk, struct sk_buff *skb);
 rx_handler_result_t br_handle_frame(struct sk_buff **pskb);
 
 static inline bool br_rx_handler_check_rcu(const struct net_device *dev)
@@ -636,8 +633,8 @@ static inline int br_vlan_get_tag(const struct sk_buff *skb, u16 *vid)
 {
 	int err = 0;
 
-	if (vlan_tx_tag_present(skb))
-		*vid = vlan_tx_tag_get(skb) & VLAN_VID_MASK;
+	if (skb_vlan_tag_present(skb))
+		*vid = skb_vlan_tag_get(skb) & VLAN_VID_MASK;
 	else {
 		*vid = 0;
 		err = -EINVAL;
@@ -766,6 +763,11 @@ static inline int br_vlan_enabled(struct net_bridge *br)
 }
 #endif
 
+struct nf_br_ops {
+	int (*br_dev_xmit_hook)(struct sk_buff *skb);
+};
+extern const struct nf_br_ops __rcu *nf_br_ops;
+
 /* br_netfilter.c */
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 int br_nf_core_init(void);
@@ -823,10 +825,10 @@ extern struct rtnl_link_ops br_link_ops;
 int br_netlink_init(void);
 void br_netlink_fini(void);
 void br_ifinfo_notify(int event, struct net_bridge_port *port);
-int br_setlink(struct net_device *dev, struct nlmsghdr *nlmsg);
-int br_dellink(struct net_device *dev, struct nlmsghdr *nlmsg);
+int br_setlink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags);
+int br_dellink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags);
 int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev,
-	       u32 filter_mask);
+	       u32 filter_mask, int nlflags);
 
 #ifdef CONFIG_SYSFS
 /* br_sysfs_if.c */
diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c
index 2b047bcf42a4..fb3ebe615513 100644
--- a/net/bridge/br_stp.c
+++ b/net/bridge/br_stp.c
@@ -12,6 +12,7 @@
  */
 #include <linux/kernel.h>
 #include <linux/rculist.h>
+#include <net/switchdev.h>
 
 #include "br_private.h"
 #include "br_private_stp.h"
@@ -38,7 +39,13 @@ void br_log_state(const struct net_bridge_port *p)
 
 void br_set_state(struct net_bridge_port *p, unsigned int state)
 {
+	int err;
+
 	p->state = state;
+	err = netdev_switch_port_stp_update(p->dev, state);
+	if (err && err != -EOPNOTSUPP)
+		br_warn(p->br, "error setting offload STP state on port %u(%s)\n",
+				(unsigned int) p->port_no, p->dev->name);
 }
 
 /* called under bridge lock */
diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c
index bdb459d21ad8..534fc4cd263e 100644
--- a/net/bridge/br_stp_bpdu.c
+++ b/net/bridge/br_stp_bpdu.c
@@ -54,8 +54,9 @@ static void br_send_bpdu(struct net_bridge_port *p,
 
 	skb_reset_mac_header(skb);
 
-	NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev,
-		dev_queue_xmit);
+	NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, NULL, skb,
+		NULL, skb->dev,
+		dev_queue_xmit_sk);
 }
 
 static inline void br_set_ticks(unsigned char *dest, int j)
diff --git a/net/bridge/br_stp_timer.c b/net/bridge/br_stp_timer.c
index 4fcaa67750fd..7caf7fae2d5b 100644
--- a/net/bridge/br_stp_timer.c
+++ b/net/bridge/br_stp_timer.c
@@ -97,7 +97,9 @@ static void br_forward_delay_timer_expired(unsigned long arg)
 		netif_carrier_on(br->dev);
 	}
 	br_log_state(p);
+	rcu_read_lock();
 	br_ifinfo_notify(RTM_NEWLINK, p);
+	rcu_read_unlock();
 	spin_unlock(&br->lock);
 }
 
diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c
index e561cd59b8a6..4905845a94e9 100644
--- a/net/bridge/br_sysfs_if.c
+++ b/net/bridge/br_sysfs_if.c
@@ -170,6 +170,8 @@ BRPORT_ATTR_FLAG(bpdu_guard, BR_BPDU_GUARD);
 BRPORT_ATTR_FLAG(root_block, BR_ROOT_BLOCK);
 BRPORT_ATTR_FLAG(learning, BR_LEARNING);
 BRPORT_ATTR_FLAG(unicast_flood, BR_FLOOD);
+BRPORT_ATTR_FLAG(proxyarp, BR_PROXYARP);
+BRPORT_ATTR_FLAG(proxyarp_wifi, BR_PROXYARP_WIFI);
 
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
 static ssize_t show_multicast_router(struct net_bridge_port *p, char *buf)
@@ -213,6 +215,8 @@ static const struct brport_attribute *brport_attrs[] = {
 	&brport_attr_multicast_router,
 	&brport_attr_multicast_fast_leave,
 #endif
+	&brport_attr_proxyarp,
+	&brport_attr_proxyarp_wifi,
 	NULL
 };
 
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 150048fb99b0..13013fe8db24 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -187,7 +187,7 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
 	 * sent from vlan device on the bridge device, it does not have
 	 * HW accelerated vlan tag.
 	 */
-	if (unlikely(!vlan_tx_tag_present(skb) &&
+	if (unlikely(!skb_vlan_tag_present(skb) &&
 		     skb->protocol == proto)) {
 		skb = skb_vlan_untag(skb);
 		if (unlikely(!skb))
@@ -199,8 +199,8 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
 		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));
+			skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto,
+							skb_vlan_tag_get(skb));
 			if (unlikely(!skb))
 				return false;
 
diff --git a/net/bridge/netfilter/ebt_vlan.c b/net/bridge/netfilter/ebt_vlan.c
index 8d3f8c7651f0..618568888128 100644
--- a/net/bridge/netfilter/ebt_vlan.c
+++ b/net/bridge/netfilter/ebt_vlan.c
@@ -45,8 +45,8 @@ ebt_vlan_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	/* VLAN encapsulated Type/Length field, given from orig frame */
 	__be16 encap;
 
-	if (vlan_tx_tag_present(skb)) {
-		TCI = vlan_tx_tag_get(skb);
+	if (skb_vlan_tag_present(skb)) {
+		TCI = skb_vlan_tag_get(skb);
 		encap = skb->protocol;
 	} else {
 		const struct vlan_hdr *fp;
diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c
index ce205aabf9c5..8a3f63b2e807 100644
--- a/net/bridge/netfilter/ebtable_filter.c
+++ b/net/bridge/netfilter/ebtable_filter.c
@@ -58,20 +58,18 @@ static const struct ebt_table frame_filter = {
 
 static unsigned int
 ebt_in_hook(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 *))
+	    const struct nf_hook_state *state)
 {
-	return ebt_do_table(ops->hooknum, skb, in, out,
-			    dev_net(in)->xt.frame_filter);
+	return ebt_do_table(ops->hooknum, skb, state->in, state->out,
+			    dev_net(state->in)->xt.frame_filter);
 }
 
 static unsigned int
 ebt_out_hook(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 *))
+	     const struct nf_hook_state *state)
 {
-	return ebt_do_table(ops->hooknum, skb, in, out,
-			    dev_net(out)->xt.frame_filter);
+	return ebt_do_table(ops->hooknum, skb, state->in, state->out,
+			    dev_net(state->out)->xt.frame_filter);
 }
 
 static struct nf_hook_ops ebt_ops_filter[] __read_mostly = {
diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c
index a0ac2984fb6c..c5ef5b1ab678 100644
--- a/net/bridge/netfilter/ebtable_nat.c
+++ b/net/bridge/netfilter/ebtable_nat.c
@@ -58,20 +58,18 @@ static struct ebt_table frame_nat = {
 
 static unsigned int
 ebt_nat_in(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 *))
+	   const struct nf_hook_state *state)
 {
-	return ebt_do_table(ops->hooknum, skb, in, out,
-			    dev_net(in)->xt.frame_nat);
+	return ebt_do_table(ops->hooknum, skb, state->in, state->out,
+			    dev_net(state->in)->xt.frame_nat);
 }
 
 static unsigned int
 ebt_nat_out(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 *))
+	    const struct nf_hook_state *state)
 {
-	return ebt_do_table(ops->hooknum, skb, in, out,
-			    dev_net(out)->xt.frame_nat);
+	return ebt_do_table(ops->hooknum, skb, state->in, state->out,
+			    dev_net(state->out)->xt.frame_nat);
 }
 
 static struct nf_hook_ops ebt_ops_nat[] __read_mostly = {
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 54df89edcf20..c2cabbe6fa58 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -133,7 +133,7 @@ ebt_basic_match(const struct ebt_entry *e, const struct sk_buff *skb,
 	__be16 ethproto;
 	int verdict, i;
 
-	if (vlan_tx_tag_present(skb))
+	if (skb_vlan_tag_present(skb))
 		ethproto = htons(ETH_P_8021Q);
 	else
 		ethproto = h->h_proto;
diff --git a/net/bridge/netfilter/nf_tables_bridge.c b/net/bridge/netfilter/nf_tables_bridge.c
index 074c557ab505..a343e62442b1 100644
--- a/net/bridge/netfilter/nf_tables_bridge.c
+++ b/net/bridge/netfilter/nf_tables_bridge.c
@@ -13,17 +13,99 @@
 #include <linux/module.h>
 #include <linux/netfilter_bridge.h>
 #include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_bridge.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <net/netfilter/nf_tables_ipv4.h>
+#include <net/netfilter/nf_tables_ipv6.h>
+
+int nft_bridge_iphdr_validate(struct sk_buff *skb)
+{
+	struct iphdr *iph;
+	u32 len;
+
+	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+		return 0;
+
+	iph = ip_hdr(skb);
+	if (iph->ihl < 5 || iph->version != 4)
+		return 0;
+
+	len = ntohs(iph->tot_len);
+	if (skb->len < len)
+		return 0;
+	else if (len < (iph->ihl*4))
+		return 0;
+
+	if (!pskb_may_pull(skb, iph->ihl*4))
+		return 0;
+
+	return 1;
+}
+EXPORT_SYMBOL_GPL(nft_bridge_iphdr_validate);
+
+int nft_bridge_ip6hdr_validate(struct sk_buff *skb)
+{
+	struct ipv6hdr *hdr;
+	u32 pkt_len;
+
+	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
+		return 0;
+
+	hdr = ipv6_hdr(skb);
+	if (hdr->version != 6)
+		return 0;
+
+	pkt_len = ntohs(hdr->payload_len);
+	if (pkt_len + sizeof(struct ipv6hdr) > skb->len)
+		return 0;
+
+	return 1;
+}
+EXPORT_SYMBOL_GPL(nft_bridge_ip6hdr_validate);
+
+static inline void nft_bridge_set_pktinfo_ipv4(struct nft_pktinfo *pkt,
+					       const struct nf_hook_ops *ops,
+					       struct sk_buff *skb,
+					       const struct nf_hook_state *state)
+{
+	if (nft_bridge_iphdr_validate(skb))
+		nft_set_pktinfo_ipv4(pkt, ops, skb, state);
+	else
+		nft_set_pktinfo(pkt, ops, skb, state);
+}
+
+static inline void nft_bridge_set_pktinfo_ipv6(struct nft_pktinfo *pkt,
+					       const struct nf_hook_ops *ops,
+					       struct sk_buff *skb,
+					       const struct nf_hook_state *state)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	if (nft_bridge_ip6hdr_validate(skb) &&
+	    nft_set_pktinfo_ipv6(pkt, ops, skb, state) == 0)
+		return;
+#endif
+	nft_set_pktinfo(pkt, ops, skb, state);
+}
 
 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 *))
+		    const struct nf_hook_state *state)
 {
 	struct nft_pktinfo pkt;
 
-	nft_set_pktinfo(&pkt, ops, skb, in, out);
+	switch (eth_hdr(skb)->h_proto) {
+	case htons(ETH_P_IP):
+		nft_bridge_set_pktinfo_ipv4(&pkt, ops, skb, state);
+		break;
+	case htons(ETH_P_IPV6):
+		nft_bridge_set_pktinfo_ipv6(&pkt, ops, skb, state);
+		break;
+	default:
+		nft_set_pktinfo(&pkt, ops, skb, state);
+		break;
+	}
 
 	return nft_do_chain(&pkt, ops);
 }
diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c
index 4f02109d708f..a21269b83f16 100644
--- a/net/bridge/netfilter/nft_meta_bridge.c
+++ b/net/bridge/netfilter/nft_meta_bridge.c
@@ -19,12 +19,12 @@
 #include "../br_private.h"
 
 static void nft_meta_bridge_get_eval(const struct nft_expr *expr,
-				     struct nft_data data[NFT_REG_MAX + 1],
+				     struct nft_regs *regs,
 				     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];
+	u32 *dest = &regs->data[priv->dreg];
 	const struct net_bridge_port *p;
 
 	switch (priv->key) {
@@ -40,12 +40,12 @@ static void nft_meta_bridge_get_eval(const struct nft_expr *expr,
 		goto out;
 	}
 
-	strncpy((char *)dest->data, p->br->dev->name, sizeof(dest->data));
+	strncpy((char *)dest, p->br->dev->name, IFNAMSIZ);
 	return;
 out:
-	return nft_meta_get_eval(expr, data, pkt);
+	return nft_meta_get_eval(expr, regs, pkt);
 err:
-	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+	regs->verdict.code = NFT_BREAK;
 }
 
 static int nft_meta_bridge_get_init(const struct nft_ctx *ctx,
@@ -53,27 +53,21 @@ static int nft_meta_bridge_get_init(const struct nft_ctx *ctx,
 				    const struct nlattr * const tb[])
 {
 	struct nft_meta *priv = nft_expr_priv(expr);
-	int err;
+	unsigned int len;
 
 	priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY]));
 	switch (priv->key) {
 	case NFT_META_BRI_IIFNAME:
 	case NFT_META_BRI_OIFNAME:
+		len = IFNAMSIZ;
 		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;
+	priv->dreg = nft_parse_register(tb[NFTA_META_DREG]);
+	return nft_validate_register_store(ctx, priv->dreg, NULL,
+					   NFT_DATA_VALUE, len);
 }
 
 static struct nft_expr_type nft_meta_bridge_type;
diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c
index 48da2c54a69e..858d848564ee 100644
--- a/net/bridge/netfilter/nft_reject_bridge.c
+++ b/net/bridge/netfilter/nft_reject_bridge.c
@@ -14,12 +14,14 @@
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
 #include <net/netfilter/nft_reject.h>
+#include <net/netfilter/nf_tables_bridge.h>
 #include <net/netfilter/ipv4/nf_reject.h>
 #include <net/netfilter/ipv6/nf_reject.h>
 #include <linux/ip.h>
 #include <net/ip.h>
 #include <net/ip6_checksum.h>
 #include <linux/netfilter_bridge.h>
+#include <linux/netfilter_ipv6.h>
 #include "../br_private.h"
 
 static void nft_reject_br_push_etherhdr(struct sk_buff *oldskb,
@@ -35,38 +37,19 @@ static void nft_reject_br_push_etherhdr(struct sk_buff *oldskb,
 	skb_pull(nskb, ETH_HLEN);
 }
 
-static int nft_reject_iphdr_validate(struct sk_buff *oldskb)
-{
-	struct iphdr *iph;
-	u32 len;
-
-	if (!pskb_may_pull(oldskb, sizeof(struct iphdr)))
-		return 0;
-
-	iph = ip_hdr(oldskb);
-	if (iph->ihl < 5 || iph->version != 4)
-		return 0;
-
-	len = ntohs(iph->tot_len);
-	if (oldskb->len < len)
-		return 0;
-	else if (len < (iph->ihl*4))
-		return 0;
-
-	if (!pskb_may_pull(oldskb, iph->ihl*4))
-		return 0;
-
-	return 1;
-}
-
-static void nft_reject_br_send_v4_tcp_reset(struct sk_buff *oldskb, int hook)
+/* We cannot use oldskb->dev, it can be either bridge device (NF_BRIDGE INPUT)
+ * or the bridge port (NF_BRIDGE PREROUTING).
+ */
+static void nft_reject_br_send_v4_tcp_reset(struct sk_buff *oldskb,
+					    const struct net_device *dev,
+					    int hook)
 {
 	struct sk_buff *nskb;
 	struct iphdr *niph;
 	const struct tcphdr *oth;
 	struct tcphdr _oth;
 
-	if (!nft_reject_iphdr_validate(oldskb))
+	if (!nft_bridge_iphdr_validate(oldskb))
 		return;
 
 	oth = nf_reject_ip_tcphdr_get(oldskb, &_oth, hook);
@@ -88,11 +71,12 @@ static void nft_reject_br_send_v4_tcp_reset(struct sk_buff *oldskb, int hook)
 
 	nft_reject_br_push_etherhdr(oldskb, nskb);
 
-	br_deliver(br_port_get_rcu(oldskb->dev), nskb);
+	br_deliver(br_port_get_rcu(dev), nskb);
 }
 
-static void nft_reject_br_send_v4_unreach(struct sk_buff *oldskb, int hook,
-					  u8 code)
+static void nft_reject_br_send_v4_unreach(struct sk_buff *oldskb,
+					  const struct net_device *dev,
+					  int hook, u8 code)
 {
 	struct sk_buff *nskb;
 	struct iphdr *niph;
@@ -100,8 +84,9 @@ static void nft_reject_br_send_v4_unreach(struct sk_buff *oldskb, int hook,
 	unsigned int len;
 	void *payload;
 	__wsum csum;
+	u8 proto;
 
-	if (!nft_reject_iphdr_validate(oldskb))
+	if (oldskb->csum_bad || !nft_bridge_iphdr_validate(oldskb))
 		return;
 
 	/* IP header checks: fragment. */
@@ -114,7 +99,17 @@ static void nft_reject_br_send_v4_unreach(struct sk_buff *oldskb, int hook,
 	if (!pskb_may_pull(oldskb, len))
 		return;
 
-	if (nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), 0))
+	if (pskb_trim_rcsum(oldskb, ntohs(ip_hdr(oldskb)->tot_len)))
+		return;
+
+	if (ip_hdr(oldskb)->protocol == IPPROTO_TCP ||
+	    ip_hdr(oldskb)->protocol == IPPROTO_UDP)
+		proto = ip_hdr(oldskb)->protocol;
+	else
+		proto = 0;
+
+	if (!skb_csum_unnecessary(oldskb) &&
+	    nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), proto))
 		return;
 
 	nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct icmphdr) +
@@ -143,30 +138,13 @@ static void nft_reject_br_send_v4_unreach(struct sk_buff *oldskb, int hook,
 
 	nft_reject_br_push_etherhdr(oldskb, nskb);
 
-	br_deliver(br_port_get_rcu(oldskb->dev), nskb);
-}
-
-static int nft_reject_ip6hdr_validate(struct sk_buff *oldskb)
-{
-	struct ipv6hdr *hdr;
-	u32 pkt_len;
-
-	if (!pskb_may_pull(oldskb, sizeof(struct ipv6hdr)))
-		return 0;
-
-	hdr = ipv6_hdr(oldskb);
-	if (hdr->version != 6)
-		return 0;
-
-	pkt_len = ntohs(hdr->payload_len);
-	if (pkt_len + sizeof(struct ipv6hdr) > oldskb->len)
-		return 0;
-
-	return 1;
+	br_deliver(br_port_get_rcu(dev), nskb);
 }
 
 static void nft_reject_br_send_v6_tcp_reset(struct net *net,
-					    struct sk_buff *oldskb, int hook)
+					    struct sk_buff *oldskb,
+					    const struct net_device *dev,
+					    int hook)
 {
 	struct sk_buff *nskb;
 	const struct tcphdr *oth;
@@ -174,7 +152,7 @@ static void nft_reject_br_send_v6_tcp_reset(struct net *net,
 	unsigned int otcplen;
 	struct ipv6hdr *nip6h;
 
-	if (!nft_reject_ip6hdr_validate(oldskb))
+	if (!nft_bridge_ip6hdr_validate(oldskb))
 		return;
 
 	oth = nf_reject_ip6_tcphdr_get(oldskb, &_oth, &otcplen, hook);
@@ -194,12 +172,37 @@ static void nft_reject_br_send_v6_tcp_reset(struct net *net,
 
 	nft_reject_br_push_etherhdr(oldskb, nskb);
 
-	br_deliver(br_port_get_rcu(oldskb->dev), nskb);
+	br_deliver(br_port_get_rcu(dev), nskb);
+}
+
+static bool reject6_br_csum_ok(struct sk_buff *skb, int hook)
+{
+	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
+	int thoff;
+	__be16 fo;
+	u8 proto = ip6h->nexthdr;
+
+	if (skb->csum_bad)
+		return false;
+
+	if (skb_csum_unnecessary(skb))
+		return true;
+
+	if (ip6h->payload_len &&
+	    pskb_trim_rcsum(skb, ntohs(ip6h->payload_len) + sizeof(*ip6h)))
+		return false;
+
+	thoff = ipv6_skip_exthdr(skb, ((u8*)(ip6h+1) - skb->data), &proto, &fo);
+	if (thoff < 0 || thoff >= skb->len || (fo & htons(~0x7)) != 0)
+		return false;
+
+	return nf_ip6_checksum(skb, hook, thoff, proto) == 0;
 }
 
 static void nft_reject_br_send_v6_unreach(struct net *net,
-					  struct sk_buff *oldskb, int hook,
-					  u8 code)
+					  struct sk_buff *oldskb,
+					  const struct net_device *dev,
+					  int hook, u8 code)
 {
 	struct sk_buff *nskb;
 	struct ipv6hdr *nip6h;
@@ -207,7 +210,7 @@ static void nft_reject_br_send_v6_unreach(struct net *net,
 	unsigned int len;
 	void *payload;
 
-	if (!nft_reject_ip6hdr_validate(oldskb))
+	if (!nft_bridge_ip6hdr_validate(oldskb))
 		return;
 
 	/* Include "As much of invoking packet as possible without the ICMPv6
@@ -218,6 +221,9 @@ static void nft_reject_br_send_v6_unreach(struct net *net,
 	if (!pskb_may_pull(oldskb, len))
 		return;
 
+	if (!reject6_br_csum_ok(oldskb, hook))
+		return;
+
 	nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct icmp6hdr) +
 			 LL_MAX_HEADER + len, GFP_ATOMIC);
 	if (!nskb)
@@ -247,12 +253,12 @@ static void nft_reject_br_send_v6_unreach(struct net *net,
 
 	nft_reject_br_push_etherhdr(oldskb, nskb);
 
-	br_deliver(br_port_get_rcu(oldskb->dev), nskb);
+	br_deliver(br_port_get_rcu(dev), nskb);
 }
 
 static void nft_reject_bridge_eval(const struct nft_expr *expr,
-				 struct nft_data data[NFT_REG_MAX + 1],
-				 const struct nft_pktinfo *pkt)
+				   struct nft_regs *regs,
+				   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);
@@ -266,16 +272,16 @@ static void nft_reject_bridge_eval(const struct nft_expr *expr,
 	case htons(ETH_P_IP):
 		switch (priv->type) {
 		case NFT_REJECT_ICMP_UNREACH:
-			nft_reject_br_send_v4_unreach(pkt->skb,
+			nft_reject_br_send_v4_unreach(pkt->skb, pkt->in,
 						      pkt->ops->hooknum,
 						      priv->icmp_code);
 			break;
 		case NFT_REJECT_TCP_RST:
-			nft_reject_br_send_v4_tcp_reset(pkt->skb,
+			nft_reject_br_send_v4_tcp_reset(pkt->skb, pkt->in,
 							pkt->ops->hooknum);
 			break;
 		case NFT_REJECT_ICMPX_UNREACH:
-			nft_reject_br_send_v4_unreach(pkt->skb,
+			nft_reject_br_send_v4_unreach(pkt->skb, pkt->in,
 						      pkt->ops->hooknum,
 						      nft_reject_icmp_code(priv->icmp_code));
 			break;
@@ -284,16 +290,16 @@ static void nft_reject_bridge_eval(const struct nft_expr *expr,
 	case htons(ETH_P_IPV6):
 		switch (priv->type) {
 		case NFT_REJECT_ICMP_UNREACH:
-			nft_reject_br_send_v6_unreach(net, pkt->skb,
+			nft_reject_br_send_v6_unreach(net, pkt->skb, pkt->in,
 						      pkt->ops->hooknum,
 						      priv->icmp_code);
 			break;
 		case NFT_REJECT_TCP_RST:
-			nft_reject_br_send_v6_tcp_reset(net, pkt->skb,
+			nft_reject_br_send_v6_tcp_reset(net, pkt->skb, pkt->in,
 							pkt->ops->hooknum);
 			break;
 		case NFT_REJECT_ICMPX_UNREACH:
-			nft_reject_br_send_v6_unreach(net, pkt->skb,
+			nft_reject_br_send_v6_unreach(net, pkt->skb, pkt->in,
 						      pkt->ops->hooknum,
 						      nft_reject_icmpv6_code(priv->icmp_code));
 			break;
@@ -304,25 +310,15 @@ static void nft_reject_bridge_eval(const struct nft_expr *expr,
 		break;
 	}
 out:
-	data[NFT_REG_VERDICT].verdict = NF_DROP;
+	regs->verdict.code = NF_DROP;
 }
 
-static int nft_reject_bridge_validate_hooks(const struct nft_chain *chain)
+static int nft_reject_bridge_validate(const struct nft_ctx *ctx,
+				      const struct nft_expr *expr,
+				      const struct nft_data **data)
 {
-	struct nft_base_chain *basechain;
-
-	if (chain->flags & NFT_BASE_CHAIN) {
-		basechain = nft_base_chain(chain);
-
-		switch (basechain->ops[0].hooknum) {
-		case NF_BR_PRE_ROUTING:
-		case NF_BR_LOCAL_IN:
-			break;
-		default:
-			return -EOPNOTSUPP;
-		}
-	}
-	return 0;
+	return nft_chain_validate_hooks(ctx->chain, (1 << NF_BR_PRE_ROUTING) |
+						    (1 << NF_BR_LOCAL_IN));
 }
 
 static int nft_reject_bridge_init(const struct nft_ctx *ctx,
@@ -332,7 +328,7 @@ static int nft_reject_bridge_init(const struct nft_ctx *ctx,
 	struct nft_reject *priv = nft_expr_priv(expr);
 	int icmp_code, err;
 
-	err = nft_reject_bridge_validate_hooks(ctx->chain);
+	err = nft_reject_bridge_validate(ctx, expr, NULL);
 	if (err < 0)
 		return err;
 
@@ -375,6 +371,8 @@ static int nft_reject_bridge_dump(struct sk_buff *skb,
 		if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code))
 			goto nla_put_failure;
 		break;
+	default:
+		break;
 	}
 
 	return 0;
@@ -383,13 +381,6 @@ nla_put_failure:
 	return -1;
 }
 
-static int nft_reject_bridge_validate(const struct nft_ctx *ctx,
-				      const struct nft_expr *expr,
-				      const struct nft_data **data)
-{
-	return nft_reject_bridge_validate_hooks(ctx->chain);
-}
-
 static struct nft_expr_type nft_reject_bridge_type;
 static const struct nft_expr_ops nft_reject_bridge_ops = {
 	.type		= &nft_reject_bridge_type,
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 43f750e88e19..112ad784838a 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -271,8 +271,8 @@ static void caif_check_flow_release(struct sock *sk)
  * Copied from unix_dgram_recvmsg, but removed credit checks,
  * changed locking, address handling and added MSG_TRUNC.
  */
-static int caif_seqpkt_recvmsg(struct kiocb *iocb, struct socket *sock,
-			       struct msghdr *m, size_t len, int flags)
+static int caif_seqpkt_recvmsg(struct socket *sock, struct msghdr *m,
+			       size_t len, int flags)
 
 {
 	struct sock *sk = sock->sk;
@@ -281,7 +281,7 @@ static int caif_seqpkt_recvmsg(struct kiocb *iocb, struct socket *sock,
 	int copylen;
 
 	ret = -EOPNOTSUPP;
-	if (m->msg_flags&MSG_OOB)
+	if (flags & MSG_OOB)
 		goto read_error;
 
 	skb = skb_recv_datagram(sk, flags, 0 , &ret);
@@ -293,7 +293,7 @@ static int caif_seqpkt_recvmsg(struct kiocb *iocb, struct socket *sock,
 		copylen = len;
 	}
 
-	ret = skb_copy_datagram_iovec(skb, 0, m->msg_iov, copylen);
+	ret = skb_copy_datagram_msg(skb, 0, m, copylen);
 	if (ret)
 		goto out_free;
 
@@ -330,6 +330,10 @@ static long caif_stream_data_wait(struct sock *sk, long timeo)
 		release_sock(sk);
 		timeo = schedule_timeout(timeo);
 		lock_sock(sk);
+
+		if (sock_flag(sk, SOCK_DEAD))
+			break;
+
 		clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
 	}
 
@@ -343,9 +347,8 @@ static long caif_stream_data_wait(struct sock *sk, long timeo)
  * Copied from unix_stream_recvmsg, but removed credit checks,
  * changed locking calls, changed address handling.
  */
-static int caif_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
-			       struct msghdr *msg, size_t size,
-			       int flags)
+static int caif_stream_recvmsg(struct socket *sock, struct msghdr *msg,
+			       size_t size, int flags)
 {
 	struct sock *sk = sock->sk;
 	int copied = 0;
@@ -374,6 +377,10 @@ static int caif_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 		struct sk_buff *skb;
 
 		lock_sock(sk);
+		if (sock_flag(sk, SOCK_DEAD)) {
+			err = -ECONNRESET;
+			goto unlock;
+		}
 		skb = skb_dequeue(&sk->sk_receive_queue);
 		caif_check_flow_release(sk);
 
@@ -418,7 +425,7 @@ unlock:
 		}
 		release_sock(sk);
 		chunk = min_t(unsigned int, skb->len, size);
-		if (memcpy_toiovec(msg->msg_iov, skb->data, chunk)) {
+		if (memcpy_to_msg(msg, skb->data, chunk)) {
 			skb_queue_head(&sk->sk_receive_queue, skb);
 			if (copied == 0)
 				copied = -EFAULT;
@@ -511,8 +518,8 @@ static int transmit_skb(struct sk_buff *skb, struct caifsock *cf_sk,
 }
 
 /* Copied from af_unix:unix_dgram_sendmsg, and adapted to CAIF */
-static int caif_seqpkt_sendmsg(struct kiocb *kiocb, struct socket *sock,
-			       struct msghdr *msg, size_t len)
+static int caif_seqpkt_sendmsg(struct socket *sock, struct msghdr *msg,
+			       size_t len)
 {
 	struct sock *sk = sock->sk;
 	struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
@@ -535,7 +542,7 @@ static int caif_seqpkt_sendmsg(struct kiocb *kiocb, struct socket *sock,
 		goto err;
 
 	ret = -EINVAL;
-	if (unlikely(msg->msg_iov->iov_base == NULL))
+	if (unlikely(msg->msg_iter.iov->iov_base == NULL))
 		goto err;
 	noblock = msg->msg_flags & MSG_DONTWAIT;
 
@@ -566,7 +573,7 @@ static int caif_seqpkt_sendmsg(struct kiocb *kiocb, struct socket *sock,
 
 	skb_reserve(skb, cf_sk->headroom);
 
-	ret = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
+	ret = memcpy_from_msg(skb_put(skb, len), msg, len);
 
 	if (ret)
 		goto err;
@@ -586,8 +593,8 @@ err:
  * Changed removed permission handling and added waiting for flow on
  * and other minor adaptations.
  */
-static int caif_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
-			       struct msghdr *msg, size_t len)
+static int caif_stream_sendmsg(struct socket *sock, struct msghdr *msg,
+			       size_t len)
 {
 	struct sock *sk = sock->sk;
 	struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
@@ -641,7 +648,7 @@ static int caif_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 		 */
 		size = min_t(int, size, skb_tailroom(skb));
 
-		err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size);
+		err = memcpy_from_msg(skb_put(skb, size), msg, size);
 		if (err) {
 			kfree_skb(skb);
 			goto out_err;
diff --git a/net/caif/cffrml.c b/net/caif/cffrml.c
index 8bc7caa28e64..434ba8557826 100644
--- a/net/caif/cffrml.c
+++ b/net/caif/cffrml.c
@@ -84,7 +84,7 @@ static int cffrml_receive(struct cflayer *layr, struct cfpkt *pkt)
 	u16 tmp;
 	u16 len;
 	u16 hdrchks;
-	u16 pktchks;
+	int pktchks;
 	struct cffrml *this;
 	this = container_obj(layr);
 
diff --git a/net/caif/cfpkt_skbuff.c b/net/caif/cfpkt_skbuff.c
index 1be0b521ac49..f6c3b2137eea 100644
--- a/net/caif/cfpkt_skbuff.c
+++ b/net/caif/cfpkt_skbuff.c
@@ -255,9 +255,9 @@ inline u16 cfpkt_getlen(struct cfpkt *pkt)
 	return skb->len;
 }
 
-inline u16 cfpkt_iterate(struct cfpkt *pkt,
-			 u16 (*iter_func)(u16, void *, u16),
-			 u16 data)
+int cfpkt_iterate(struct cfpkt *pkt,
+		  u16 (*iter_func)(u16, void *, u16),
+		  u16 data)
 {
 	/*
 	 * Don't care about the performance hit of linearizing,
diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c
index 4589ff67bfa9..67a4a36febd1 100644
--- a/net/caif/chnl_net.c
+++ b/net/caif/chnl_net.c
@@ -470,7 +470,6 @@ static int ipcaif_newlink(struct net *src_net, struct net_device *dev,
 	ASSERT_RTNL();
 	caifdev = netdev_priv(dev);
 	caif_netlink_parms(data, &caifdev->conn_req);
-	dev_net_set(caifdev->netdev, src_net);
 
 	ret = register_netdevice(dev);
 	if (ret)
diff --git a/net/can/af_can.c b/net/can/af_can.c
index ce82337521f6..32d710eaf1fc 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -64,9 +64,6 @@
 
 #include "af_can.h"
 
-static __initconst const char banner[] = KERN_INFO
-	"can: controller area network core (" CAN_VERSION_STRING ")\n";
-
 MODULE_DESCRIPTION("Controller Area Network PF_CAN core");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Urs Thuermann <urs.thuermann@volkswagen.de>, "
@@ -262,6 +259,9 @@ int can_send(struct sk_buff *skb, int loop)
 		goto inval_skb;
 	}
 
+	skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+	skb_reset_mac_header(skb);
 	skb_reset_network_header(skb);
 	skb_reset_transport_header(skb);
 
@@ -524,7 +524,7 @@ static void can_rx_delete_receiver(struct rcu_head *rp)
 
 /**
  * can_rx_unregister - unsubscribe CAN frames from a specific interface
- * @dev: pointer to netdevice (NULL => unsubcribe from 'all' CAN devices list)
+ * @dev: pointer to netdevice (NULL => unsubscribe from 'all' CAN devices list)
  * @can_id: CAN identifier
  * @mask: CAN mask
  * @func: callback function on filter match
@@ -896,7 +896,7 @@ static __init int can_init(void)
 		     offsetof(struct can_frame, data) !=
 		     offsetof(struct canfd_frame, data));
 
-	printk(banner);
+	pr_info("can: controller area network core (" CAN_VERSION_STRING ")\n");
 
 	memset(&can_rx_alldev_list, 0, sizeof(can_rx_alldev_list));
 
diff --git a/net/can/bcm.c b/net/can/bcm.c
index dcb75c0e66c1..b523453585be 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -78,8 +78,6 @@
 		     (CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG))
 
 #define CAN_BCM_VERSION CAN_VERSION
-static __initconst const char banner[] = KERN_INFO
-	"can: broadcast manager protocol (rev " CAN_BCM_VERSION " t)\n";
 
 MODULE_DESCRIPTION("PF_CAN broadcast manager protocol");
 MODULE_LICENSE("Dual BSD/GPL");
@@ -330,7 +328,7 @@ static void bcm_send_to_user(struct bcm_op *op, struct bcm_msg_head *head,
 	 *  containing the interface index.
 	 */
 
-	BUILD_BUG_ON(sizeof(skb->cb) < sizeof(struct sockaddr_can));
+	sock_skb_cb_check_size(sizeof(struct sockaddr_can));
 	addr = (struct sockaddr_can *)skb->cb;
 	memset(addr, 0, sizeof(*addr));
 	addr->can_family  = AF_CAN;
@@ -441,7 +439,7 @@ static void bcm_rx_update_and_send(struct bcm_op *op,
 	/* mark as used and throttled by default */
 	lastdata->can_dlc |= (RX_RECV|RX_THR);
 
-	/* throtteling mode inactive ? */
+	/* throttling mode inactive ? */
 	if (!op->kt_ival2.tv64) {
 		/* send RX_CHANGED to the user immediately */
 		bcm_rx_changed(op, lastdata);
@@ -452,7 +450,7 @@ static void bcm_rx_update_and_send(struct bcm_op *op,
 	if (hrtimer_active(&op->thrtimer))
 		return;
 
-	/* first receiption with enabled throttling mode */
+	/* first reception with enabled throttling mode */
 	if (!op->kt_lastmsg.tv64)
 		goto rx_changed_settime;
 
@@ -480,7 +478,7 @@ static void bcm_rx_cmp_to_index(struct bcm_op *op, unsigned int index,
 				const struct can_frame *rxdata)
 {
 	/*
-	 * no one uses the MSBs of can_dlc for comparation,
+	 * no one uses the MSBs of can_dlc for comparison,
 	 * so we use it here to detect the first time of reception
 	 */
 
@@ -510,7 +508,7 @@ static void bcm_rx_cmp_to_index(struct bcm_op *op, unsigned int index,
 }
 
 /*
- * bcm_rx_starttimer - enable timeout monitoring for CAN frame receiption
+ * bcm_rx_starttimer - enable timeout monitoring for CAN frame reception
  */
 static void bcm_rx_starttimer(struct bcm_op *op)
 {
@@ -539,7 +537,7 @@ static void bcm_rx_timeout_tsklet(unsigned long data)
 }
 
 /*
- * bcm_rx_timeout_handler - when the (cyclic) CAN frame receiption timed out
+ * bcm_rx_timeout_handler - when the (cyclic) CAN frame reception timed out
  */
 static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer)
 {
@@ -627,7 +625,7 @@ static enum hrtimer_restart bcm_rx_thr_handler(struct hrtimer *hrtimer)
 }
 
 /*
- * bcm_rx_handler - handle a CAN frame receiption
+ * bcm_rx_handler - handle a CAN frame reception
  */
 static void bcm_rx_handler(struct sk_buff *skb, void *data)
 {
@@ -858,8 +856,7 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 
 		/* update can_frames content */
 		for (i = 0; i < msg_head->nframes; i++) {
-			err = memcpy_fromiovec((u8 *)&op->frames[i],
-					       msg->msg_iov, CFSIZ);
+			err = memcpy_from_msg((u8 *)&op->frames[i], msg, CFSIZ);
 
 			if (op->frames[i].can_dlc > 8)
 				err = -EINVAL;
@@ -894,8 +891,7 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 			op->frames = &op->sframe;
 
 		for (i = 0; i < msg_head->nframes; i++) {
-			err = memcpy_fromiovec((u8 *)&op->frames[i],
-					       msg->msg_iov, CFSIZ);
+			err = memcpy_from_msg((u8 *)&op->frames[i], msg, CFSIZ);
 
 			if (op->frames[i].can_dlc > 8)
 				err = -EINVAL;
@@ -1024,9 +1020,8 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 
 		if (msg_head->nframes) {
 			/* update can_frames content */
-			err = memcpy_fromiovec((u8 *)op->frames,
-					       msg->msg_iov,
-					       msg_head->nframes * CFSIZ);
+			err = memcpy_from_msg((u8 *)op->frames, msg,
+					      msg_head->nframes * CFSIZ);
 			if (err < 0)
 				return err;
 
@@ -1072,8 +1067,8 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		}
 
 		if (msg_head->nframes) {
-			err = memcpy_fromiovec((u8 *)op->frames, msg->msg_iov,
-					       msg_head->nframes * CFSIZ);
+			err = memcpy_from_msg((u8 *)op->frames, msg,
+					      msg_head->nframes * CFSIZ);
 			if (err < 0) {
 				if (op->frames != &op->sframe)
 					kfree(op->frames);
@@ -1209,7 +1204,7 @@ static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk)
 
 	can_skb_reserve(skb);
 
-	err = memcpy_fromiovec(skb_put(skb, CFSIZ), msg->msg_iov, CFSIZ);
+	err = memcpy_from_msg(skb_put(skb, CFSIZ), msg, CFSIZ);
 	if (err < 0) {
 		kfree_skb(skb);
 		return err;
@@ -1236,8 +1231,7 @@ static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk)
 /*
  * bcm_sendmsg - process BCM commands (opcodes) from the userspace
  */
-static int bcm_sendmsg(struct kiocb *iocb, struct socket *sock,
-		       struct msghdr *msg, size_t size)
+static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 {
 	struct sock *sk = sock->sk;
 	struct bcm_sock *bo = bcm_sk(sk);
@@ -1285,7 +1279,7 @@ static int bcm_sendmsg(struct kiocb *iocb, struct socket *sock,
 
 	/* read message head information */
 
-	ret = memcpy_fromiovec((u8 *)&msg_head, msg->msg_iov, MHSIZ);
+	ret = memcpy_from_msg((u8 *)&msg_head, msg, MHSIZ);
 	if (ret < 0)
 		return ret;
 
@@ -1540,8 +1534,8 @@ static int bcm_connect(struct socket *sock, struct sockaddr *uaddr, int len,
 	return 0;
 }
 
-static int bcm_recvmsg(struct kiocb *iocb, struct socket *sock,
-		       struct msghdr *msg, size_t size, int flags)
+static int bcm_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+		       int flags)
 {
 	struct sock *sk = sock->sk;
 	struct sk_buff *skb;
@@ -1558,7 +1552,7 @@ static int bcm_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (skb->len < size)
 		size = skb->len;
 
-	err = memcpy_toiovec(msg->msg_iov, skb->data, size);
+	err = memcpy_to_msg(msg, skb->data, size);
 	if (err < 0) {
 		skb_free_datagram(sk, skb);
 		return err;
@@ -1615,7 +1609,7 @@ static int __init bcm_module_init(void)
 {
 	int err;
 
-	printk(banner);
+	pr_info("can: broadcast manager protocol (rev " CAN_BCM_VERSION " t)\n");
 
 	err = can_proto_register(&bcm_can_proto);
 	if (err < 0) {
diff --git a/net/can/gw.c b/net/can/gw.c
index 050a2110d43f..a6f448e18ea8 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -361,7 +361,7 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data)
 	 * The Controller Area Network controllers only accept CAN frames with
 	 * correct CRCs - which are not visible in the controller registers.
 	 * According to skbuff.h documentation the csum_start element for IP
-	 * checksums is undefined/unsued when ip_summed == CHECKSUM_UNNECESSARY.
+	 * checksums is undefined/unused when ip_summed == CHECKSUM_UNNECESSARY.
 	 * Only CAN skbs can be processed here which already have this property.
 	 */
 
@@ -575,7 +575,8 @@ static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj, int type,
 			goto cancel;
 	}
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 cancel:
 	nlmsg_cancel(skb, nlh);
diff --git a/net/can/raw.c b/net/can/raw.c
index 081e81fd017f..31b9748cbb4e 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -56,8 +56,6 @@
 #include <net/net_namespace.h>
 
 #define CAN_RAW_VERSION CAN_VERSION
-static __initconst const char banner[] =
-	KERN_INFO "can: raw protocol (rev " CAN_RAW_VERSION ")\n";
 
 MODULE_DESCRIPTION("PF_CAN raw protocol");
 MODULE_LICENSE("Dual BSD/GPL");
@@ -76,6 +74,12 @@ MODULE_ALIAS("can-proto-1");
  * storing the single filter in dfilter, to avoid using dynamic memory.
  */
 
+struct uniqframe {
+	ktime_t tstamp;
+	const struct sk_buff *skb;
+	unsigned int join_rx_count;
+};
+
 struct raw_sock {
 	struct sock sk;
 	int bound;
@@ -84,10 +88,12 @@ struct raw_sock {
 	int loopback;
 	int recv_own_msgs;
 	int fd_frames;
+	int join_filters;
 	int count;                 /* number of active filters */
 	struct can_filter dfilter; /* default/single filter */
 	struct can_filter *filter; /* pointer to filter(s) */
 	can_err_mask_t err_mask;
+	struct uniqframe __percpu *uniq;
 };
 
 /*
@@ -97,8 +103,8 @@ struct raw_sock {
  */
 static inline unsigned int *raw_flags(struct sk_buff *skb)
 {
-	BUILD_BUG_ON(sizeof(skb->cb) <= (sizeof(struct sockaddr_can) +
-					 sizeof(unsigned int)));
+	sock_skb_cb_check_size(sizeof(struct sockaddr_can) +
+			       sizeof(unsigned int));
 
 	/* return pointer after struct sockaddr_can */
 	return (unsigned int *)(&((struct sockaddr_can *)skb->cb)[1]);
@@ -125,6 +131,26 @@ static void raw_rcv(struct sk_buff *oskb, void *data)
 	if (!ro->fd_frames && oskb->len != CAN_MTU)
 		return;
 
+	/* eliminate multiple filter matches for the same skb */
+	if (this_cpu_ptr(ro->uniq)->skb == oskb &&
+	    ktime_equal(this_cpu_ptr(ro->uniq)->tstamp, oskb->tstamp)) {
+		if (ro->join_filters) {
+			this_cpu_inc(ro->uniq->join_rx_count);
+			/* drop frame until all enabled filters matched */
+			if (this_cpu_ptr(ro->uniq)->join_rx_count < ro->count)
+				return;
+		} else {
+			return;
+		}
+	} else {
+		this_cpu_ptr(ro->uniq)->skb = oskb;
+		this_cpu_ptr(ro->uniq)->tstamp = oskb->tstamp;
+		this_cpu_ptr(ro->uniq)->join_rx_count = 1;
+		/* drop first frame to check all enabled filters? */
+		if (ro->join_filters && ro->count > 1)
+			return;
+	}
+
 	/* clone the given skb to be able to enqueue it into the rcv queue */
 	skb = skb_clone(oskb, GFP_ATOMIC);
 	if (!skb)
@@ -137,7 +163,7 @@ static void raw_rcv(struct sk_buff *oskb, void *data)
 	 *  containing the interface index.
 	 */
 
-	BUILD_BUG_ON(sizeof(skb->cb) < sizeof(struct sockaddr_can));
+	sock_skb_cb_check_size(sizeof(struct sockaddr_can));
 	addr = (struct sockaddr_can *)skb->cb;
 	memset(addr, 0, sizeof(*addr));
 	addr->can_family  = AF_CAN;
@@ -298,6 +324,12 @@ static int raw_init(struct sock *sk)
 	ro->loopback         = 1;
 	ro->recv_own_msgs    = 0;
 	ro->fd_frames        = 0;
+	ro->join_filters     = 0;
+
+	/* alloc_percpu provides zero'ed memory */
+	ro->uniq = alloc_percpu(struct uniqframe);
+	if (unlikely(!ro->uniq))
+		return -ENOMEM;
 
 	/* set notifier */
 	ro->notifier.notifier_call = raw_notifier;
@@ -341,6 +373,7 @@ static int raw_release(struct socket *sock)
 	ro->ifindex = 0;
 	ro->bound   = 0;
 	ro->count   = 0;
+	free_percpu(ro->uniq);
 
 	sock_orphan(sk);
 	sock->sk = NULL;
@@ -585,6 +618,15 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 
 		break;
 
+	case CAN_RAW_JOIN_FILTERS:
+		if (optlen != sizeof(ro->join_filters))
+			return -EINVAL;
+
+		if (copy_from_user(&ro->join_filters, optval, optlen))
+			return -EFAULT;
+
+		break;
+
 	default:
 		return -ENOPROTOOPT;
 	}
@@ -649,6 +691,12 @@ static int raw_getsockopt(struct socket *sock, int level, int optname,
 		val = &ro->fd_frames;
 		break;
 
+	case CAN_RAW_JOIN_FILTERS:
+		if (len > sizeof(int))
+			len = sizeof(int);
+		val = &ro->join_filters;
+		break;
+
 	default:
 		return -ENOPROTOOPT;
 	}
@@ -660,8 +708,7 @@ static int raw_getsockopt(struct socket *sock, int level, int optname,
 	return 0;
 }
 
-static int raw_sendmsg(struct kiocb *iocb, struct socket *sock,
-		       struct msghdr *msg, size_t size)
+static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 {
 	struct sock *sk = sock->sk;
 	struct raw_sock *ro = raw_sk(sk);
@@ -703,7 +750,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct socket *sock,
 	can_skb_reserve(skb);
 	can_skb_prv(skb)->ifindex = dev->ifindex;
 
-	err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size);
+	err = memcpy_from_msg(skb_put(skb, size), msg, size);
 	if (err < 0)
 		goto free_skb;
 
@@ -730,8 +777,8 @@ send_failed:
 	return err;
 }
 
-static int raw_recvmsg(struct kiocb *iocb, struct socket *sock,
-		       struct msghdr *msg, size_t size, int flags)
+static int raw_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+		       int flags)
 {
 	struct sock *sk = sock->sk;
 	struct sk_buff *skb;
@@ -750,7 +797,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct socket *sock,
 	else
 		size = skb->len;
 
-	err = memcpy_toiovec(msg->msg_iov, skb->data, size);
+	err = memcpy_to_msg(msg, skb->data, size);
 	if (err < 0) {
 		skb_free_datagram(sk, skb);
 		return err;
@@ -810,7 +857,7 @@ static __init int raw_module_init(void)
 {
 	int err;
 
-	printk(banner);
+	pr_info("can: raw protocol (rev " CAN_RAW_VERSION ")\n");
 
 	err = can_proto_register(&raw_can_proto);
 	if (err < 0)
diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c
index 7e38b729696a..ba6eb17226da 100644
--- a/net/ceph/auth_x.c
+++ b/net/ceph/auth_x.c
@@ -8,6 +8,7 @@
 
 #include <linux/ceph/decode.h>
 #include <linux/ceph/auth.h>
+#include <linux/ceph/messenger.h>
 
 #include "crypto.h"
 #include "auth_x.h"
@@ -293,6 +294,11 @@ static int ceph_x_build_authorizer(struct ceph_auth_client *ac,
 	dout("build_authorizer for %s %p\n",
 	     ceph_entity_type_name(th->service), au);
 
+	ceph_crypto_key_destroy(&au->session_key);
+	ret = ceph_crypto_key_clone(&au->session_key, &th->session_key);
+	if (ret)
+		return ret;
+
 	maxlen = sizeof(*msg_a) + sizeof(msg_b) +
 		ceph_x_encrypt_buflen(ticket_blob_len);
 	dout("  need len %d\n", maxlen);
@@ -302,8 +308,10 @@ static int ceph_x_build_authorizer(struct ceph_auth_client *ac,
 	}
 	if (!au->buf) {
 		au->buf = ceph_buffer_new(maxlen, GFP_NOFS);
-		if (!au->buf)
+		if (!au->buf) {
+			ceph_crypto_key_destroy(&au->session_key);
 			return -ENOMEM;
+		}
 	}
 	au->service = th->service;
 	au->secret_id = th->secret_id;
@@ -329,7 +337,7 @@ static int ceph_x_build_authorizer(struct ceph_auth_client *ac,
 	get_random_bytes(&au->nonce, sizeof(au->nonce));
 	msg_b.struct_v = 1;
 	msg_b.nonce = cpu_to_le64(au->nonce);
-	ret = ceph_x_encrypt(&th->session_key, &msg_b, sizeof(msg_b),
+	ret = ceph_x_encrypt(&au->session_key, &msg_b, sizeof(msg_b),
 			     p, end - p);
 	if (ret < 0)
 		goto out_buf;
@@ -560,6 +568,8 @@ static int ceph_x_create_authorizer(
 	auth->authorizer_buf_len = au->buf->vec.iov_len;
 	auth->authorizer_reply_buf = au->reply_buf;
 	auth->authorizer_reply_buf_len = sizeof (au->reply_buf);
+	auth->sign_message = ac->ops->sign_message;
+	auth->check_message_signature = ac->ops->check_message_signature;
 
 	return 0;
 }
@@ -588,17 +598,13 @@ static int ceph_x_verify_authorizer_reply(struct ceph_auth_client *ac,
 					  struct ceph_authorizer *a, size_t len)
 {
 	struct ceph_x_authorizer *au = (void *)a;
-	struct ceph_x_ticket_handler *th;
 	int ret = 0;
 	struct ceph_x_authorize_reply reply;
 	void *preply = &reply;
 	void *p = au->reply_buf;
 	void *end = p + sizeof(au->reply_buf);
 
-	th = get_ticket_handler(ac, au->service);
-	if (IS_ERR(th))
-		return PTR_ERR(th);
-	ret = ceph_x_decrypt(&th->session_key, &p, end, &preply, sizeof(reply));
+	ret = ceph_x_decrypt(&au->session_key, &p, end, &preply, sizeof(reply));
 	if (ret < 0)
 		return ret;
 	if (ret != sizeof(reply))
@@ -618,6 +624,7 @@ static void ceph_x_destroy_authorizer(struct ceph_auth_client *ac,
 {
 	struct ceph_x_authorizer *au = (void *)a;
 
+	ceph_crypto_key_destroy(&au->session_key);
 	ceph_buffer_put(au->buf);
 	kfree(au);
 }
@@ -663,6 +670,59 @@ static void ceph_x_invalidate_authorizer(struct ceph_auth_client *ac,
 		memset(&th->validity, 0, sizeof(th->validity));
 }
 
+static int calcu_signature(struct ceph_x_authorizer *au,
+			   struct ceph_msg *msg, __le64 *sig)
+{
+	int ret;
+	char tmp_enc[40];
+	__le32 tmp[5] = {
+		cpu_to_le32(16), msg->hdr.crc, msg->footer.front_crc,
+		msg->footer.middle_crc, msg->footer.data_crc,
+	};
+	ret = ceph_x_encrypt(&au->session_key, &tmp, sizeof(tmp),
+			     tmp_enc, sizeof(tmp_enc));
+	if (ret < 0)
+		return ret;
+	*sig = *(__le64*)(tmp_enc + 4);
+	return 0;
+}
+
+static int ceph_x_sign_message(struct ceph_auth_handshake *auth,
+			       struct ceph_msg *msg)
+{
+	int ret;
+	if (!auth->authorizer)
+		return 0;
+	ret = calcu_signature((struct ceph_x_authorizer *)auth->authorizer,
+			      msg, &msg->footer.sig);
+	if (ret < 0)
+		return ret;
+	msg->footer.flags |= CEPH_MSG_FOOTER_SIGNED;
+	return 0;
+}
+
+static int ceph_x_check_message_signature(struct ceph_auth_handshake *auth,
+					  struct ceph_msg *msg)
+{
+	__le64 sig_check;
+	int ret;
+
+	if (!auth->authorizer)
+		return 0;
+	ret = calcu_signature((struct ceph_x_authorizer *)auth->authorizer,
+			      msg, &sig_check);
+	if (ret < 0)
+		return ret;
+	if (sig_check == msg->footer.sig)
+		return 0;
+	if (msg->footer.flags & CEPH_MSG_FOOTER_SIGNED)
+		dout("ceph_x_check_message_signature %p has signature %llx "
+		     "expect %llx\n", msg, msg->footer.sig, sig_check);
+	else
+		dout("ceph_x_check_message_signature %p sender did not set "
+		     "CEPH_MSG_FOOTER_SIGNED\n", msg);
+	return -EBADMSG;
+}
 
 static const struct ceph_auth_client_ops ceph_x_ops = {
 	.name = "x",
@@ -677,6 +737,8 @@ static const struct ceph_auth_client_ops ceph_x_ops = {
 	.invalidate_authorizer = ceph_x_invalidate_authorizer,
 	.reset =  ceph_x_reset,
 	.destroy = ceph_x_destroy,
+	.sign_message = ceph_x_sign_message,
+	.check_message_signature = ceph_x_check_message_signature,
 };
 
 
diff --git a/net/ceph/auth_x.h b/net/ceph/auth_x.h
index 65ee72082d99..e8b7c6917d47 100644
--- a/net/ceph/auth_x.h
+++ b/net/ceph/auth_x.h
@@ -26,6 +26,7 @@ struct ceph_x_ticket_handler {
 
 
 struct ceph_x_authorizer {
+	struct ceph_crypto_key session_key;
 	struct ceph_buffer *buf;
 	unsigned int service;
 	u64 nonce;
diff --git a/net/ceph/buffer.c b/net/ceph/buffer.c
index 621b5f65407f..add5f921a0ff 100644
--- a/net/ceph/buffer.c
+++ b/net/ceph/buffer.c
@@ -6,7 +6,7 @@
 
 #include <linux/ceph/buffer.h>
 #include <linux/ceph/decode.h>
-#include <linux/ceph/libceph.h> /* for ceph_kv{malloc,free} */
+#include <linux/ceph/libceph.h> /* for ceph_kvmalloc */
 
 struct ceph_buffer *ceph_buffer_new(size_t len, gfp_t gfp)
 {
@@ -35,7 +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);
-	ceph_kvfree(b->vec.iov_base);
+	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 58fbfe134f93..79e8f71aef5b 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -184,14 +184,6 @@ void *ceph_kvmalloc(size_t size, gfp_t flags)
 	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)
 {
@@ -245,6 +237,10 @@ enum {
 	Opt_noshare,
 	Opt_crc,
 	Opt_nocrc,
+	Opt_cephx_require_signatures,
+	Opt_nocephx_require_signatures,
+	Opt_tcp_nodelay,
+	Opt_notcp_nodelay,
 };
 
 static match_table_t opt_tokens = {
@@ -263,6 +259,10 @@ static match_table_t opt_tokens = {
 	{Opt_noshare, "noshare"},
 	{Opt_crc, "crc"},
 	{Opt_nocrc, "nocrc"},
+	{Opt_cephx_require_signatures, "cephx_require_signatures"},
+	{Opt_nocephx_require_signatures, "nocephx_require_signatures"},
+	{Opt_tcp_nodelay, "tcp_nodelay"},
+	{Opt_notcp_nodelay, "notcp_nodelay"},
 	{-1, NULL}
 };
 
@@ -462,6 +462,20 @@ ceph_parse_options(char *options, const char *dev_name,
 			opt->flags |= CEPH_OPT_NOCRC;
 			break;
 
+		case Opt_cephx_require_signatures:
+			opt->flags &= ~CEPH_OPT_NOMSGAUTH;
+			break;
+		case Opt_nocephx_require_signatures:
+			opt->flags |= CEPH_OPT_NOMSGAUTH;
+			break;
+
+		case Opt_tcp_nodelay:
+			opt->flags |= CEPH_OPT_TCP_NODELAY;
+			break;
+		case Opt_notcp_nodelay:
+			opt->flags &= ~CEPH_OPT_TCP_NODELAY;
+			break;
+
 		default:
 			BUG_ON(token);
 		}
@@ -476,6 +490,43 @@ out:
 }
 EXPORT_SYMBOL(ceph_parse_options);
 
+int ceph_print_client_options(struct seq_file *m, struct ceph_client *client)
+{
+	struct ceph_options *opt = client->options;
+	size_t pos = m->count;
+
+	if (opt->name)
+		seq_printf(m, "name=%s,", opt->name);
+	if (opt->key)
+		seq_puts(m, "secret=<hidden>,");
+
+	if (opt->flags & CEPH_OPT_FSID)
+		seq_printf(m, "fsid=%pU,", &opt->fsid);
+	if (opt->flags & CEPH_OPT_NOSHARE)
+		seq_puts(m, "noshare,");
+	if (opt->flags & CEPH_OPT_NOCRC)
+		seq_puts(m, "nocrc,");
+	if (opt->flags & CEPH_OPT_NOMSGAUTH)
+		seq_puts(m, "nocephx_require_signatures,");
+	if ((opt->flags & CEPH_OPT_TCP_NODELAY) == 0)
+		seq_puts(m, "notcp_nodelay,");
+
+	if (opt->mount_timeout != CEPH_MOUNT_TIMEOUT_DEFAULT)
+		seq_printf(m, "mount_timeout=%d,", opt->mount_timeout);
+	if (opt->osd_idle_ttl != CEPH_OSD_IDLE_TTL_DEFAULT)
+		seq_printf(m, "osd_idle_ttl=%d,", opt->osd_idle_ttl);
+	if (opt->osd_keepalive_timeout != CEPH_OSD_KEEPALIVE_DEFAULT)
+		seq_printf(m, "osdkeepalivetimeout=%d,",
+			   opt->osd_keepalive_timeout);
+
+	/* drop redundant comma */
+	if (m->count != pos)
+		m->count--;
+
+	return 0;
+}
+EXPORT_SYMBOL(ceph_print_client_options);
+
 u64 ceph_client_id(struct ceph_client *client)
 {
 	return client->monc.auth->global_id;
@@ -504,6 +555,9 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private,
 	init_waitqueue_head(&client->auth_wq);
 	client->auth_err = 0;
 
+	if (!ceph_test_opt(client, NOMSGAUTH))
+		required_features |= CEPH_FEATURE_MSG_AUTH;
+
 	client->extra_mon_dispatch = NULL;
 	client->supported_features = CEPH_FEATURES_SUPPORTED_DEFAULT |
 		supported_features;
@@ -513,10 +567,12 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private,
 	/* msgr */
 	if (ceph_test_opt(client, MYIP))
 		myaddr = &client->options->my_addr;
+
 	ceph_messenger_init(&client->msgr, myaddr,
 		client->supported_features,
 		client->required_features,
-		ceph_test_opt(client, NOCRC));
+		ceph_test_opt(client, NOCRC),
+		ceph_test_opt(client, TCP_NODELAY));
 
 	/* subsystems */
 	err = ceph_monc_init(&client->monc, client);
diff --git a/net/ceph/ceph_strings.c b/net/ceph/ceph_strings.c
index 30560202f57b..139a9cb19b0c 100644
--- a/net/ceph/ceph_strings.c
+++ b/net/ceph/ceph_strings.c
@@ -42,17 +42,3 @@ const char *ceph_osd_state_name(int s)
 		return "???";
 	}
 }
-
-const char *ceph_pool_op_name(int op)
-{
-	switch (op) {
-	case POOL_OP_CREATE: return "create";
-	case POOL_OP_DELETE: return "delete";
-	case POOL_OP_AUID_CHANGE: return "auid change";
-	case POOL_OP_CREATE_SNAP: return "create snap";
-	case POOL_OP_DELETE_SNAP: return "delete snap";
-	case POOL_OP_CREATE_UNMANAGED_SNAP: return "create unmanaged snap";
-	case POOL_OP_DELETE_UNMANAGED_SNAP: return "delete unmanaged snap";
-	}
-	return "???";
-}
diff --git a/net/ceph/crush/crush.c b/net/ceph/crush/crush.c
index 16bc199d9a62..9d84ce4ea0df 100644
--- a/net/ceph/crush/crush.c
+++ b/net/ceph/crush/crush.c
@@ -17,6 +17,7 @@ const char *crush_bucket_alg_name(int alg)
 	case CRUSH_BUCKET_LIST: return "list";
 	case CRUSH_BUCKET_TREE: return "tree";
 	case CRUSH_BUCKET_STRAW: return "straw";
+	case CRUSH_BUCKET_STRAW2: return "straw2";
 	default: return "unknown";
 	}
 }
@@ -40,6 +41,8 @@ int crush_get_bucket_item_weight(const struct crush_bucket *b, int p)
 		return ((struct crush_bucket_tree *)b)->node_weights[crush_calc_tree_node(p)];
 	case CRUSH_BUCKET_STRAW:
 		return ((struct crush_bucket_straw *)b)->item_weights[p];
+	case CRUSH_BUCKET_STRAW2:
+		return ((struct crush_bucket_straw2 *)b)->item_weights[p];
 	}
 	return 0;
 }
@@ -77,6 +80,14 @@ void crush_destroy_bucket_straw(struct crush_bucket_straw *b)
 	kfree(b);
 }
 
+void crush_destroy_bucket_straw2(struct crush_bucket_straw2 *b)
+{
+	kfree(b->item_weights);
+	kfree(b->h.perm);
+	kfree(b->h.items);
+	kfree(b);
+}
+
 void crush_destroy_bucket(struct crush_bucket *b)
 {
 	switch (b->alg) {
@@ -92,6 +103,9 @@ void crush_destroy_bucket(struct crush_bucket *b)
 	case CRUSH_BUCKET_STRAW:
 		crush_destroy_bucket_straw((struct crush_bucket_straw *)b);
 		break;
+	case CRUSH_BUCKET_STRAW2:
+		crush_destroy_bucket_straw2((struct crush_bucket_straw2 *)b);
+		break;
 	}
 }
 
diff --git a/net/ceph/crush/crush_ln_table.h b/net/ceph/crush/crush_ln_table.h
new file mode 100644
index 000000000000..6192c7fc958c
--- /dev/null
+++ b/net/ceph/crush/crush_ln_table.h
@@ -0,0 +1,166 @@
+/*
+ * Ceph - scalable distributed file system
+ *
+ * Copyright (C) 2015 Intel Corporation All Rights Reserved
+ *
+ * This is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License version 2.1, as published by the Free Software
+ * Foundation.  See file COPYING.
+ *
+ */
+
+#if defined(__linux__)
+#include <linux/types.h>
+#elif defined(__FreeBSD__)
+#include <sys/types.h>
+#endif
+
+#ifndef CEPH_CRUSH_LN_H
+#define CEPH_CRUSH_LN_H
+
+
+// RH_LH_tbl[2*k] = 2^48/(1.0+k/128.0)
+// RH_LH_tbl[2*k+1] = 2^48*log2(1.0+k/128.0)
+
+static int64_t __RH_LH_tbl[128*2+2] = {
+  0x0001000000000000ll, 0x0000000000000000ll, 0x0000fe03f80fe040ll, 0x000002dfca16dde1ll,
+  0x0000fc0fc0fc0fc1ll, 0x000005b9e5a170b4ll, 0x0000fa232cf25214ll, 0x0000088e68ea899all,
+  0x0000f83e0f83e0f9ll, 0x00000b5d69bac77ell, 0x0000f6603d980f67ll, 0x00000e26fd5c8555ll,
+  0x0000f4898d5f85bcll, 0x000010eb389fa29fll, 0x0000f2b9d6480f2cll, 0x000013aa2fdd27f1ll,
+  0x0000f0f0f0f0f0f1ll, 0x00001663f6fac913ll, 0x0000ef2eb71fc435ll, 0x00001918a16e4633ll,
+  0x0000ed7303b5cc0fll, 0x00001bc84240adabll, 0x0000ebbdb2a5c162ll, 0x00001e72ec117fa5ll,
+  0x0000ea0ea0ea0ea1ll, 0x00002118b119b4f3ll, 0x0000e865ac7b7604ll, 0x000023b9a32eaa56ll,
+  0x0000e6c2b4481cd9ll, 0x00002655d3c4f15cll, 0x0000e525982af70dll, 0x000028ed53f307eell,
+  0x0000e38e38e38e39ll, 0x00002b803473f7adll, 0x0000e1fc780e1fc8ll, 0x00002e0e85a9de04ll,
+  0x0000e070381c0e08ll, 0x0000309857a05e07ll, 0x0000dee95c4ca038ll, 0x0000331dba0efce1ll,
+  0x0000dd67c8a60dd7ll, 0x0000359ebc5b69d9ll, 0x0000dbeb61eed19dll, 0x0000381b6d9bb29bll,
+  0x0000da740da740dbll, 0x00003a93dc9864b2ll, 0x0000d901b2036407ll, 0x00003d0817ce9cd4ll,
+  0x0000d79435e50d7all, 0x00003f782d7204d0ll, 0x0000d62b80d62b81ll, 0x000041e42b6ec0c0ll,
+  0x0000d4c77b03531ell, 0x0000444c1f6b4c2dll, 0x0000d3680d3680d4ll, 0x000046b016ca47c1ll,
+  0x0000d20d20d20d21ll, 0x000049101eac381cll, 0x0000d0b69fcbd259ll, 0x00004b6c43f1366all,
+  0x0000cf6474a8819fll, 0x00004dc4933a9337ll, 0x0000ce168a772509ll, 0x0000501918ec6c11ll,
+  0x0000cccccccccccdll, 0x00005269e12f346ell, 0x0000cb8727c065c4ll, 0x000054b6f7f1325all,
+  0x0000ca4587e6b750ll, 0x0000570068e7ef5all, 0x0000c907da4e8712ll, 0x000059463f919deell,
+  0x0000c7ce0c7ce0c8ll, 0x00005b8887367433ll, 0x0000c6980c6980c7ll, 0x00005dc74ae9fbecll,
+  0x0000c565c87b5f9ell, 0x00006002958c5871ll, 0x0000c4372f855d83ll, 0x0000623a71cb82c8ll,
+  0x0000c30c30c30c31ll, 0x0000646eea247c5cll, 0x0000c1e4bbd595f7ll, 0x000066a008e4788cll,
+  0x0000c0c0c0c0c0c1ll, 0x000068cdd829fd81ll, 0x0000bfa02fe80bfbll, 0x00006af861e5fc7dll,
+  0x0000be82fa0be830ll, 0x00006d1fafdce20all, 0x0000bd6910470767ll, 0x00006f43cba79e40ll,
+  0x0000bc52640bc527ll, 0x00007164beb4a56dll, 0x0000bb3ee721a54ell, 0x000073829248e961ll,
+  0x0000ba2e8ba2e8bbll, 0x0000759d4f80cba8ll, 0x0000b92143fa36f6ll, 0x000077b4ff5108d9ll,
+  0x0000b81702e05c0cll, 0x000079c9aa879d53ll, 0x0000b70fbb5a19bfll, 0x00007bdb59cca388ll,
+  0x0000b60b60b60b61ll, 0x00007dea15a32c1bll, 0x0000b509e68a9b95ll, 0x00007ff5e66a0ffell,
+  0x0000b40b40b40b41ll, 0x000081fed45cbccbll, 0x0000b30f63528918ll, 0x00008404e793fb81ll,
+  0x0000b21642c8590cll, 0x000086082806b1d5ll, 0x0000b11fd3b80b12ll, 0x000088089d8a9e47ll,
+  0x0000b02c0b02c0b1ll, 0x00008a064fd50f2all, 0x0000af3addc680b0ll, 0x00008c01467b94bbll,
+  0x0000ae4c415c9883ll, 0x00008df988f4ae80ll, 0x0000ad602b580ad7ll, 0x00008fef1e987409ll,
+  0x0000ac7691840ac8ll, 0x000091e20ea1393ell, 0x0000ab8f69e2835all, 0x000093d2602c2e5fll,
+  0x0000aaaaaaaaaaabll, 0x000095c01a39fbd6ll, 0x0000a9c84a47a080ll, 0x000097ab43af59f9ll,
+  0x0000a8e83f5717c1ll, 0x00009993e355a4e5ll, 0x0000a80a80a80a81ll, 0x00009b79ffdb6c8bll,
+  0x0000a72f0539782all, 0x00009d5d9fd5010bll, 0x0000a655c4392d7cll, 0x00009f3ec9bcfb80ll,
+  0x0000a57eb50295fbll, 0x0000a11d83f4c355ll, 0x0000a4a9cf1d9684ll, 0x0000a2f9d4c51039ll,
+  0x0000a3d70a3d70a4ll, 0x0000a4d3c25e68dcll, 0x0000a3065e3fae7dll, 0x0000a6ab52d99e76ll,
+  0x0000a237c32b16d0ll, 0x0000a8808c384547ll, 0x0000a16b312ea8fdll, 0x0000aa5374652a1cll,
+  0x0000a0a0a0a0a0a1ll, 0x0000ac241134c4e9ll, 0x00009fd809fd80a0ll, 0x0000adf26865a8a1ll,
+  0x00009f1165e72549ll, 0x0000afbe7fa0f04dll, 0x00009e4cad23dd60ll, 0x0000b1885c7aa982ll,
+  0x00009d89d89d89d9ll, 0x0000b35004723c46ll, 0x00009cc8e160c3fcll, 0x0000b5157cf2d078ll,
+  0x00009c09c09c09c1ll, 0x0000b6d8cb53b0call, 0x00009b4c6f9ef03bll, 0x0000b899f4d8ab63ll,
+  0x00009a90e7d95bc7ll, 0x0000ba58feb2703all, 0x000099d722dabde6ll, 0x0000bc15edfeed32ll,
+  0x0000991f1a515886ll, 0x0000bdd0c7c9a817ll, 0x00009868c809868dll, 0x0000bf89910c1678ll,
+  0x000097b425ed097cll, 0x0000c1404eadf383ll, 0x000097012e025c05ll, 0x0000c2f5058593d9ll,
+  0x0000964fda6c0965ll, 0x0000c4a7ba58377cll, 0x000095a02568095bll, 0x0000c65871da59ddll,
+  0x000094f2094f2095ll, 0x0000c80730b00016ll, 0x0000944580944581ll, 0x0000c9b3fb6d0559ll,
+  0x0000939a85c4093all, 0x0000cb5ed69565afll, 0x000092f113840498ll, 0x0000cd07c69d8702ll,
+  0x0000924924924925ll, 0x0000ceaecfea8085ll, 0x000091a2b3c4d5e7ll, 0x0000d053f6d26089ll,
+  0x000090fdbc090fdcll, 0x0000d1f73f9c70c0ll, 0x0000905a38633e07ll, 0x0000d398ae817906ll,
+  0x00008fb823ee08fcll, 0x0000d53847ac00a6ll, 0x00008f1779d9fdc4ll, 0x0000d6d60f388e41ll,
+  0x00008e78356d1409ll, 0x0000d8720935e643ll, 0x00008dda5202376all, 0x0000da0c39a54804ll,
+  0x00008d3dcb08d3ddll, 0x0000dba4a47aa996ll, 0x00008ca29c046515ll, 0x0000dd3b4d9cf24bll,
+  0x00008c08c08c08c1ll, 0x0000ded038e633f3ll, 0x00008b70344a139cll, 0x0000e0636a23e2eell,
+  0x00008ad8f2fba939ll, 0x0000e1f4e5170d02ll, 0x00008a42f870566all, 0x0000e384ad748f0ell,
+  0x000089ae4089ae41ll, 0x0000e512c6e54998ll, 0x0000891ac73ae982ll, 0x0000e69f35065448ll,
+  0x0000888888888889ll, 0x0000e829fb693044ll, 0x000087f78087f781ll, 0x0000e9b31d93f98ell,
+  0x00008767ab5f34e5ll, 0x0000eb3a9f019750ll, 0x000086d905447a35ll, 0x0000ecc08321eb30ll,
+  0x0000864b8a7de6d2ll, 0x0000ee44cd59ffabll, 0x000085bf37612cefll, 0x0000efc781043579ll,
+  0x0000853408534086ll, 0x0000f148a170700all, 0x000084a9f9c8084bll, 0x0000f2c831e44116ll,
+  0x0000842108421085ll, 0x0000f446359b1353ll, 0x0000839930523fbfll, 0x0000f5c2afc65447ll,
+  0x000083126e978d50ll, 0x0000f73da38d9d4all, 0x0000828cbfbeb9a1ll, 0x0000f8b7140edbb1ll,
+  0x0000820820820821ll, 0x0000fa2f045e7832ll, 0x000081848da8faf1ll, 0x0000fba577877d7dll,
+  0x0000810204081021ll, 0x0000fd1a708bbe11ll, 0x0000808080808081ll, 0x0000fe8df263f957ll,
+  0x0000800000000000ll, 0x0000ffff00000000ll,
+  };
+
+
+    // LL_tbl[k] = 2^48*log2(1.0+k/2^15);
+static int64_t __LL_tbl[256] = {
+  0x0000000000000000ull, 0x00000002e2a60a00ull, 0x000000070cb64ec5ull, 0x00000009ef50ce67ull,
+  0x0000000cd1e588fdull, 0x0000000fb4747e9cull, 0x0000001296fdaf5eull, 0x0000001579811b58ull,
+  0x000000185bfec2a1ull, 0x0000001b3e76a552ull, 0x0000001e20e8c380ull, 0x0000002103551d43ull,
+  0x00000023e5bbb2b2ull, 0x00000026c81c83e4ull, 0x00000029aa7790f0ull, 0x0000002c8cccd9edull,
+  0x0000002f6f1c5ef2ull, 0x0000003251662017ull, 0x0000003533aa1d71ull, 0x0000003815e8571aull,
+  0x0000003af820cd26ull, 0x0000003dda537faeull, 0x00000040bc806ec8ull, 0x000000439ea79a8cull,
+  0x0000004680c90310ull, 0x0000004962e4a86cull, 0x0000004c44fa8ab6ull, 0x0000004f270aaa06ull,
+  0x0000005209150672ull, 0x00000054eb19a013ull, 0x00000057cd1876fdull, 0x0000005aaf118b4aull,
+  0x0000005d9104dd0full, 0x0000006072f26c64ull, 0x0000006354da3960ull, 0x0000006636bc441aull,
+  0x0000006918988ca8ull, 0x0000006bfa6f1322ull, 0x0000006edc3fd79full, 0x00000071be0ada35ull,
+  0x000000749fd01afdull, 0x00000077818f9a0cull, 0x0000007a6349577aull, 0x0000007d44fd535eull,
+  0x0000008026ab8dceull, 0x00000083085406e3ull, 0x00000085e9f6beb2ull, 0x00000088cb93b552ull,
+  0x0000008bad2aeadcull, 0x0000008e8ebc5f65ull, 0x0000009170481305ull, 0x0000009451ce05d3ull,
+  0x00000097334e37e5ull, 0x0000009a14c8a953ull, 0x0000009cf63d5a33ull, 0x0000009fd7ac4a9dull,
+  0x000000a2b07f3458ull, 0x000000a59a78ea6aull, 0x000000a87bd699fbull, 0x000000ab5d2e8970ull,
+  0x000000ae3e80b8e3ull, 0x000000b11fcd2869ull, 0x000000b40113d818ull, 0x000000b6e254c80aull,
+  0x000000b9c38ff853ull, 0x000000bca4c5690cull, 0x000000bf85f51a4aull, 0x000000c2671f0c26ull,
+  0x000000c548433eb6ull, 0x000000c82961b211ull, 0x000000cb0a7a664dull, 0x000000cdeb8d5b82ull,
+  0x000000d0cc9a91c8ull, 0x000000d3ada20933ull, 0x000000d68ea3c1ddull, 0x000000d96f9fbbdbull,
+  0x000000dc5095f744ull, 0x000000df31867430ull, 0x000000e2127132b5ull, 0x000000e4f35632eaull,
+  0x000000e7d43574e6ull, 0x000000eab50ef8c1ull, 0x000000ed95e2be90ull, 0x000000f076b0c66cull,
+  0x000000f35779106aull, 0x000000f6383b9ca2ull, 0x000000f918f86b2aull, 0x000000fbf9af7c1aull,
+  0x000000feda60cf88ull, 0x00000101bb0c658cull, 0x000001049bb23e3cull, 0x000001077c5259afull,
+  0x0000010a5cecb7fcull, 0x0000010d3d81593aull, 0x000001101e103d7full, 0x00000112fe9964e4ull,
+  0x00000115df1ccf7eull, 0x00000118bf9a7d64ull, 0x0000011ba0126eadull, 0x0000011e8084a371ull,
+  0x0000012160f11bc6ull, 0x000001244157d7c3ull, 0x0000012721b8d77full, 0x0000012a02141b10ull,
+  0x0000012ce269a28eull, 0x0000012fc2b96e0full, 0x00000132a3037daaull, 0x000001358347d177ull,
+  0x000001386386698cull, 0x0000013b43bf45ffull, 0x0000013e23f266e9ull, 0x00000141041fcc5eull,
+  0x00000143e4477678ull, 0x00000146c469654bull, 0x00000149a48598f0ull, 0x0000014c849c117cull,
+  0x0000014f64accf08ull, 0x0000015244b7d1a9ull, 0x0000015524bd1976ull, 0x0000015804bca687ull,
+  0x0000015ae4b678f2ull, 0x0000015dc4aa90ceull, 0x00000160a498ee31ull, 0x0000016384819134ull,
+  0x00000166646479ecull, 0x000001694441a870ull, 0x0000016c24191cd7ull, 0x0000016df6ca19bdull,
+  0x00000171e3b6d7aaull, 0x00000174c37d1e44ull, 0x00000177a33dab1cull, 0x0000017a82f87e49ull,
+  0x0000017d62ad97e2ull, 0x00000180425cf7feull, 0x00000182b07f3458ull, 0x0000018601aa8c19ull,
+  0x00000188e148c046ull, 0x0000018bc0e13b52ull, 0x0000018ea073fd52ull, 0x000001918001065dull,
+  0x000001945f88568bull, 0x000001973f09edf2ull, 0x0000019a1e85ccaaull, 0x0000019cfdfbf2c8ull,
+  0x0000019fdd6c6063ull, 0x000001a2bcd71593ull, 0x000001a59c3c126eull, 0x000001a87b9b570bull,
+  0x000001ab5af4e380ull, 0x000001ae3a48b7e5ull, 0x000001b11996d450ull, 0x000001b3f8df38d9ull,
+  0x000001b6d821e595ull, 0x000001b9b75eda9bull, 0x000001bc96961803ull, 0x000001bf75c79de3ull,
+  0x000001c254f36c51ull, 0x000001c534198365ull, 0x000001c81339e336ull, 0x000001caf2548bd9ull,
+  0x000001cdd1697d67ull, 0x000001d0b078b7f5ull, 0x000001d38f823b9aull, 0x000001d66e86086dull,
+  0x000001d94d841e86ull, 0x000001dc2c7c7df9ull, 0x000001df0b6f26dfull, 0x000001e1ea5c194eull,
+  0x000001e4c943555dull, 0x000001e7a824db23ull, 0x000001ea8700aab5ull, 0x000001ed65d6c42bull,
+  0x000001f044a7279dull, 0x000001f32371d51full, 0x000001f60236cccaull, 0x000001f8e0f60eb3ull,
+  0x000001fbbfaf9af3ull, 0x000001fe9e63719eull, 0x000002017d1192ccull, 0x000002045bb9fe94ull,
+  0x000002073a5cb50dull, 0x00000209c06e6212ull, 0x0000020cf791026aull, 0x0000020fd622997cull,
+  0x00000212b07f3458ull, 0x000002159334a8d8ull, 0x0000021871b52150ull, 0x0000021b502fe517ull,
+  0x0000021d6a73a78full, 0x000002210d144eeeull, 0x00000223eb7df52cull, 0x00000226c9e1e713ull,
+  0x00000229a84024bbull, 0x0000022c23679b4eull, 0x0000022f64eb83a8ull, 0x000002324338a51bull,
+  0x00000235218012a9ull, 0x00000237ffc1cc69ull, 0x0000023a2c3b0ea4ull, 0x0000023d13ee805bull,
+  0x0000024035e9221full, 0x00000243788faf25ull, 0x0000024656b4e735ull, 0x00000247ed646bfeull,
+  0x0000024c12ee3d98ull, 0x0000024ef1025c1aull, 0x00000251cf10c799ull, 0x0000025492644d65ull,
+  0x000002578b1c85eeull, 0x0000025a6919d8f0ull, 0x0000025d13ee805bull, 0x0000026025036716ull,
+  0x0000026296453882ull, 0x00000265e0d62b53ull, 0x00000268beb701f3ull, 0x0000026b9c92265eull,
+  0x0000026d32f798a9ull, 0x00000271583758ebull, 0x000002743601673bull, 0x0000027713c5c3b0ull,
+  0x00000279f1846e5full, 0x0000027ccf3d6761ull, 0x0000027e6580aecbull, 0x000002828a9e44b3ull,
+  0x0000028568462932ull, 0x00000287bdbf5255ull, 0x0000028b2384de4aull, 0x0000028d13ee805bull,
+  0x0000029035e9221full, 0x0000029296453882ull, 0x0000029699bdfb61ull, 0x0000029902a37aabull,
+  0x0000029c54b864c9ull, 0x0000029deabd1083ull, 0x000002a20f9c0bb5ull, 0x000002a4c7605d61ull,
+  0x000002a7bdbf5255ull, 0x000002a96056dafcull, 0x000002ac3daf14efull, 0x000002af1b019ecaull,
+  0x000002b296453882ull, 0x000002b5d022d80full, 0x000002b8fa471cb3ull, 0x000002ba9012e713ull,
+  0x000002bd6d4901ccull, 0x000002c04a796cf6ull, 0x000002c327a428a6ull, 0x000002c61a5e8f4cull,
+  0x000002c8e1e891f6ull, 0x000002cbbf023fc2ull, 0x000002ce9c163e6eull, 0x000002d179248e13ull,
+  0x000002d4562d2ec6ull, 0x000002d73330209dull, 0x000002da102d63b0ull, 0x000002dced24f814ull,
+};
+
+
+
+
+#endif
diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c
index a1ef53c04415..5b47736d27d9 100644
--- a/net/ceph/crush/mapper.c
+++ b/net/ceph/crush/mapper.c
@@ -20,7 +20,7 @@
 
 #include <linux/crush/crush.h>
 #include <linux/crush/hash.h>
-#include <linux/crush/mapper.h>
+#include "crush_ln_table.h"
 
 /*
  * Implement the core CRUSH mapping algorithm.
@@ -238,6 +238,102 @@ static int bucket_straw_choose(struct crush_bucket_straw *bucket,
 	return bucket->h.items[high];
 }
 
+// compute 2^44*log2(input+1)
+uint64_t crush_ln(unsigned xin)
+{
+    unsigned x=xin, x1;
+    int iexpon, index1, index2;
+    uint64_t RH, LH, LL, xl64, result;
+
+    x++;
+
+    // normalize input
+    iexpon = 15;
+    while(!(x&0x18000)) { x<<=1; iexpon--; }
+
+    index1 = (x>>8)<<1;
+    // RH ~ 2^56/index1
+    RH = __RH_LH_tbl[index1 - 256];
+    // LH ~ 2^48 * log2(index1/256)
+    LH = __RH_LH_tbl[index1 + 1 - 256];
+
+    // RH*x ~ 2^48 * (2^15 + xf), xf<2^8
+    xl64 = (int64_t)x * RH;
+    xl64 >>= 48;
+    x1 = xl64;
+
+    result = iexpon;
+    result <<= (12 + 32);
+
+    index2 = x1 & 0xff;
+    // LL ~ 2^48*log2(1.0+index2/2^15)
+    LL = __LL_tbl[index2];
+
+    LH = LH + LL;
+
+    LH >>= (48-12 - 32);
+    result += LH;
+
+    return result;
+}
+
+
+/*
+ * straw2
+ *
+ * for reference, see:
+ *
+ * http://en.wikipedia.org/wiki/Exponential_distribution#Distribution_of_the_minimum_of_exponential_random_variables
+ *
+ */
+
+static int bucket_straw2_choose(struct crush_bucket_straw2 *bucket,
+				int x, int r)
+{
+	unsigned i, high = 0;
+	unsigned u;
+	unsigned w;
+	__s64 ln, draw, high_draw = 0;
+
+	for (i = 0; i < bucket->h.size; i++) {
+		w = bucket->item_weights[i];
+		if (w) {
+			u = crush_hash32_3(bucket->h.hash, x,
+					   bucket->h.items[i], r);
+			u &= 0xffff;
+
+			/*
+			 * for some reason slightly less than 0x10000 produces
+			 * a slightly more accurate distribution... probably a
+			 * rounding effect.
+			 *
+			 * the natural log lookup table maps [0,0xffff]
+			 * (corresponding to real numbers [1/0x10000, 1] to
+			 * [0, 0xffffffffffff] (corresponding to real numbers
+			 * [-11.090355,0]).
+			 */
+			ln = crush_ln(u) - 0x1000000000000ll;
+
+			/*
+			 * divide by 16.16 fixed-point weight.  note
+			 * that the ln value is negative, so a larger
+			 * weight means a larger (less negative) value
+			 * for draw.
+			 */
+			draw = div64_s64(ln, w);
+		} else {
+			draw = S64_MIN;
+		}
+
+		if (i == 0 || draw > high_draw) {
+			high = i;
+			high_draw = draw;
+		}
+	}
+	return bucket->h.items[high];
+}
+
+
 static int crush_bucket_choose(struct crush_bucket *in, int x, int r)
 {
 	dprintk(" crush_bucket_choose %d x=%d r=%d\n", in->id, x, r);
@@ -255,12 +351,16 @@ static int crush_bucket_choose(struct crush_bucket *in, int x, int r)
 	case CRUSH_BUCKET_STRAW:
 		return bucket_straw_choose((struct crush_bucket_straw *)in,
 					   x, r);
+	case CRUSH_BUCKET_STRAW2:
+		return bucket_straw2_choose((struct crush_bucket_straw2 *)in,
+					    x, r);
 	default:
 		dprintk("unknown bucket %d alg %d\n", in->id, in->alg);
 		return in->items[0];
 	}
 }
 
+
 /*
  * true if device is marked "out" (failed, fully offloaded)
  * of the cluster
@@ -290,6 +390,7 @@ static int is_out(const struct crush_map *map,
  * @type: the type of item to choose
  * @out: pointer to output vector
  * @outpos: our position in that vector
+ * @out_size: size of the out vector
  * @tries: number of attempts to make
  * @recurse_tries: number of attempts to have recursive chooseleaf make
  * @local_retries: localized retries
@@ -304,6 +405,7 @@ static int crush_choose_firstn(const struct crush_map *map,
 			       const __u32 *weight, int weight_max,
 			       int x, int numrep, int type,
 			       int *out, int outpos,
+			       int out_size,
 			       unsigned int tries,
 			       unsigned int recurse_tries,
 			       unsigned int local_retries,
@@ -322,6 +424,7 @@ static int crush_choose_firstn(const struct crush_map *map,
 	int item = 0;
 	int itemtype;
 	int collide, reject;
+	int count = out_size;
 
 	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" : "",
@@ -329,7 +432,7 @@ static int crush_choose_firstn(const struct crush_map *map,
 		tries, recurse_tries, local_retries, local_fallback_retries,
 		parent_r);
 
-	for (rep = outpos; rep < numrep; rep++) {
+	for (rep = outpos; rep < numrep && count > 0 ; rep++) {
 		/* keep trying until we get a non-out, non-colliding item */
 		ftotal = 0;
 		skip_rep = 0;
@@ -403,7 +506,7 @@ static int crush_choose_firstn(const struct crush_map *map,
 							 map->buckets[-1-item],
 							 weight, weight_max,
 							 x, outpos+1, 0,
-							 out2, outpos,
+							 out2, outpos, count,
 							 recurse_tries, 0,
 							 local_retries,
 							 local_fallback_retries,
@@ -463,6 +566,7 @@ reject:
 		dprintk("CHOOSE got %d\n", item);
 		out[outpos] = item;
 		outpos++;
+		count--;
 	}
 
 	dprintk("CHOOSE returns %d\n", outpos);
@@ -654,6 +758,7 @@ int crush_do_rule(const struct crush_map *map,
 	__u32 step;
 	int i, j;
 	int numrep;
+	int out_size;
 	/*
 	 * the original choose_total_tries value was off by one (it
 	 * counted "retries" and not "tries").  add one.
@@ -761,6 +866,7 @@ int crush_do_rule(const struct crush_map *map,
 						x, numrep,
 						curstep->arg2,
 						o+osize, j,
+						result_max-osize,
 						choose_tries,
 						recurse_tries,
 						choose_local_retries,
@@ -770,11 +876,13 @@ int crush_do_rule(const struct crush_map *map,
 						c+osize,
 						0);
 				} else {
+					out_size = ((numrep < (result_max-osize)) ?
+                                                    numrep : (result_max-osize));
 					crush_choose_indep(
 						map,
 						map->buckets[-1-w[i]],
 						weight, weight_max,
-						x, numrep, numrep,
+						x, out_size, numrep,
 						curstep->arg2,
 						o+osize, j,
 						choose_tries,
@@ -783,7 +891,7 @@ int crush_do_rule(const struct crush_map *map,
 						recurse_to_leaf,
 						c+osize,
 						0);
-					osize += numrep;
+					osize += out_size;
 				}
 			}
 
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
index d2d525529f87..593dc2eabcc8 100644
--- a/net/ceph/debugfs.c
+++ b/net/ceph/debugfs.c
@@ -22,6 +22,7 @@
  *      .../monmap      - current monmap
  *      .../osdc        - active osd requests
  *      .../monc        - mon client state
+ *      .../client_options - libceph-only (i.e. not rbd or cephfs) options
  *      .../dentry_lru  - dump contents of dentry lru
  *      .../caps        - expose cap (reservation) stats
  *      .../bdi         - symlink to ../../bdi/something
@@ -127,8 +128,6 @@ static int monc_show(struct seq_file *s, void *p)
 		op = le16_to_cpu(req->request->hdr.type);
 		if (op == CEPH_MSG_STATFS)
 			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
@@ -179,10 +178,24 @@ static int osdc_show(struct seq_file *s, void *pp)
 	return 0;
 }
 
+static int client_options_show(struct seq_file *s, void *p)
+{
+	struct ceph_client *client = s->private;
+	int ret;
+
+	ret = ceph_print_client_options(s, client);
+	if (ret)
+		return ret;
+
+	seq_putc(s, '\n');
+	return 0;
+}
+
 CEPH_DEFINE_SHOW_FUNC(monmap_show)
 CEPH_DEFINE_SHOW_FUNC(osdmap_show)
 CEPH_DEFINE_SHOW_FUNC(monc_show)
 CEPH_DEFINE_SHOW_FUNC(osdc_show)
+CEPH_DEFINE_SHOW_FUNC(client_options_show)
 
 int ceph_debugfs_init(void)
 {
@@ -244,6 +257,14 @@ int ceph_debugfs_client_init(struct ceph_client *client)
 	if (!client->debugfs_osdmap)
 		goto out;
 
+	client->debugfs_options = debugfs_create_file("client_options",
+					0600,
+					client->debugfs_dir,
+					client,
+					&client_options_show_fops);
+	if (!client->debugfs_options)
+		goto out;
+
 	return 0;
 
 out:
@@ -254,6 +275,7 @@ out:
 void ceph_debugfs_client_cleanup(struct ceph_client *client)
 {
 	dout("ceph_debugfs_client_cleanup %p\n", client);
+	debugfs_remove(client->debugfs_options);
 	debugfs_remove(client->debugfs_osdmap);
 	debugfs_remove(client->debugfs_monmap);
 	debugfs_remove(client->osdc.debugfs_file);
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 8d1653caffdb..967080a9f043 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -484,7 +484,7 @@ static int ceph_tcp_connect(struct ceph_connection *con)
 			       IPPROTO_TCP, &sock);
 	if (ret)
 		return ret;
-	sock->sk->sk_allocation = GFP_NOFS | __GFP_MEMALLOC;
+	sock->sk->sk_allocation = GFP_NOFS;
 
 #ifdef CONFIG_LOCKDEP
 	lockdep_set_class(&sock->sk->sk_lock, &socket_class);
@@ -505,12 +505,18 @@ static int ceph_tcp_connect(struct ceph_connection *con)
 		pr_err("connect %s error %d\n",
 		       ceph_pr_addr(&con->peer_addr.in_addr), ret);
 		sock_release(sock);
-		con->error_msg = "connect error";
-
 		return ret;
 	}
 
-	sk_set_memalloc(sock->sk);
+	if (con->msgr->tcp_nodelay) {
+		int optval = 1;
+
+		ret = kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY,
+					(char *)&optval, sizeof(optval));
+		if (ret)
+			pr_err("kernel_setsockopt(TCP_NODELAY) failed: %d",
+			       ret);
+	}
 
 	con->sock = sock;
 	return 0;
@@ -1196,8 +1202,18 @@ static void prepare_write_message_footer(struct ceph_connection *con)
 	dout("prepare_write_message_footer %p\n", con);
 	con->out_kvec_is_msg = true;
 	con->out_kvec[v].iov_base = &m->footer;
-	con->out_kvec[v].iov_len = sizeof(m->footer);
-	con->out_kvec_bytes += sizeof(m->footer);
+	if (con->peer_features & CEPH_FEATURE_MSG_AUTH) {
+		if (con->ops->sign_message)
+			con->ops->sign_message(con, m);
+		else
+			m->footer.sig = 0;
+		con->out_kvec[v].iov_len = sizeof(m->footer);
+		con->out_kvec_bytes += sizeof(m->footer);
+	} else {
+		m->old_footer.flags = m->footer.flags;
+		con->out_kvec[v].iov_len = sizeof(m->old_footer);
+		con->out_kvec_bytes += sizeof(m->old_footer);
+	}
 	con->out_kvec_left++;
 	con->out_more = m->more_to_follow;
 	con->out_msg_done = true;
@@ -2127,12 +2143,10 @@ static int process_connect(struct ceph_connection *con)
 		 * to WAIT.  This shouldn't happen if we are the
 		 * client.
 		 */
-		pr_err("process_connect got WAIT as client\n");
 		con->error_msg = "protocol error, got WAIT as client";
 		return -1;
 
 	default:
-		pr_err("connect protocol error, will retry\n");
 		con->error_msg = "protocol error, garbage tag during connect";
 		return -1;
 	}
@@ -2249,6 +2263,7 @@ static int read_partial_message(struct ceph_connection *con)
 	int ret;
 	unsigned int front_len, middle_len, data_len;
 	bool do_datacrc = !con->msgr->nocrc;
+	bool need_sign = (con->peer_features & CEPH_FEATURE_MSG_AUTH);
 	u64 seq;
 	u32 crc;
 
@@ -2263,8 +2278,7 @@ static int read_partial_message(struct ceph_connection *con)
 
 	crc = crc32c(0, &con->in_hdr, offsetof(struct ceph_msg_header, crc));
 	if (cpu_to_le32(crc) != con->in_hdr.crc) {
-		pr_err("read_partial_message bad hdr "
-		       " crc %u != expected %u\n",
+		pr_err("read_partial_message bad hdr crc %u != expected %u\n",
 		       crc, con->in_hdr.crc);
 		return -EBADMSG;
 	}
@@ -2294,7 +2308,7 @@ static int read_partial_message(struct ceph_connection *con)
 		pr_err("read_partial_message bad seq %lld expected %lld\n",
 		       seq, con->in_seq + 1);
 		con->error_msg = "bad message sequence # for incoming message";
-		return -EBADMSG;
+		return -EBADE;
 	}
 
 	/* allocate message? */
@@ -2361,12 +2375,21 @@ static int read_partial_message(struct ceph_connection *con)
 	}
 
 	/* footer */
-	size = sizeof (m->footer);
+	if (need_sign)
+		size = sizeof(m->footer);
+	else
+		size = sizeof(m->old_footer);
+
 	end += size;
 	ret = read_partial(con, end, size, &m->footer);
 	if (ret <= 0)
 		return ret;
 
+	if (!need_sign) {
+		m->footer.flags = m->old_footer.flags;
+		m->footer.sig = 0;
+	}
+
 	dout("read_partial_message got msg %p %d (%u) + %d (%u) + %d (%u)\n",
 	     m, front_len, m->footer.front_crc, middle_len,
 	     m->footer.middle_crc, data_len, m->footer.data_crc);
@@ -2390,6 +2413,12 @@ static int read_partial_message(struct ceph_connection *con)
 		return -EBADMSG;
 	}
 
+	if (need_sign && con->ops->check_message_signature &&
+	    con->ops->check_message_signature(con, m)) {
+		pr_err("read_partial_message %p signature check failed\n", m);
+		return -EBADMSG;
+	}
+
 	return 1; /* done! */
 }
 
@@ -2626,6 +2655,8 @@ more:
 			switch (ret) {
 			case -EBADMSG:
 				con->error_msg = "bad crc";
+				/* fall through */
+			case -EBADE:
 				ret = -EIO;
 				break;
 			case -EIO:
@@ -2772,11 +2803,8 @@ static void con_work(struct work_struct *work)
 {
 	struct ceph_connection *con = container_of(work, struct ceph_connection,
 						   work.work);
-	unsigned long pflags = current->flags;
 	bool fault;
 
-	current->flags |= PF_MEMALLOC;
-
 	mutex_lock(&con->mutex);
 	while (true) {
 		int ret;
@@ -2807,7 +2835,8 @@ static void con_work(struct work_struct *work)
 		if (ret < 0) {
 			if (ret == -EAGAIN)
 				continue;
-			con->error_msg = "socket error on read";
+			if (!con->error_msg)
+				con->error_msg = "socket error on read";
 			fault = true;
 			break;
 		}
@@ -2816,7 +2845,8 @@ static void con_work(struct work_struct *work)
 		if (ret < 0) {
 			if (ret == -EAGAIN)
 				continue;
-			con->error_msg = "socket error on write";
+			if (!con->error_msg)
+				con->error_msg = "socket error on write";
 			fault = true;
 		}
 
@@ -2830,8 +2860,6 @@ static void con_work(struct work_struct *work)
 		con_fault_finish(con);
 
 	con->ops->put(con);
-
-	tsk_restore_flags(current, pflags, PF_MEMALLOC);
 }
 
 /*
@@ -2840,11 +2868,13 @@ static void con_work(struct work_struct *work)
  */
 static void con_fault(struct ceph_connection *con)
 {
-	pr_warn("%s%lld %s %s\n", ENTITY_NAME(con->peer_name),
-		ceph_pr_addr(&con->peer_addr.in_addr), con->error_msg);
 	dout("fault %p state %lu to peer %s\n",
 	     con, con->state, ceph_pr_addr(&con->peer_addr.in_addr));
 
+	pr_warn("%s%lld %s %s\n", ENTITY_NAME(con->peer_name),
+		ceph_pr_addr(&con->peer_addr.in_addr), con->error_msg);
+	con->error_msg = NULL;
+
 	WARN_ON(con->state != CON_STATE_CONNECTING &&
 	       con->state != CON_STATE_NEGOTIATING &&
 	       con->state != CON_STATE_OPEN);
@@ -2896,7 +2926,8 @@ void ceph_messenger_init(struct ceph_messenger *msgr,
 			struct ceph_entity_addr *myaddr,
 			u64 supported_features,
 			u64 required_features,
-			bool nocrc)
+			bool nocrc,
+			bool tcp_nodelay)
 {
 	msgr->supported_features = supported_features;
 	msgr->required_features = required_features;
@@ -2911,6 +2942,7 @@ void ceph_messenger_init(struct ceph_messenger *msgr,
 	get_random_bytes(&msgr->inst.addr.nonce, sizeof(msgr->inst.addr.nonce));
 	encode_my_addr(msgr);
 	msgr->nocrc = nocrc;
+	msgr->tcp_nodelay = tcp_nodelay;
 
 	atomic_set(&msgr->stopping, 0);
 
@@ -3264,8 +3296,8 @@ static int ceph_con_in_msg_alloc(struct ceph_connection *con, int *skip)
 		 */
 		if (*skip)
 			return 0;
-		con->error_msg = "error allocating memory for incoming message";
 
+		con->error_msg = "error allocating memory for incoming message";
 		return -ENOMEM;
 	}
 	memcpy(&con->in_msg->hdr, &con->in_hdr, sizeof(con->in_hdr));
@@ -3288,7 +3320,7 @@ static int ceph_con_in_msg_alloc(struct ceph_connection *con, int *skip)
 static void ceph_msg_free(struct ceph_msg *m)
 {
 	dout("%s %p\n", __func__, m);
-	ceph_kvfree(m->front.iov_base);
+	kvfree(m->front.iov_base);
 	kmem_cache_free(ceph_msg_cache, m);
 }
 
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index a83062ceeec9..2b3cf05e87b0 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -410,7 +410,7 @@ out_unlocked:
 }
 
 /*
- * generic requests (e.g., statfs, poolop)
+ * generic requests (currently statfs, mon_get_version)
  */
 static struct ceph_mon_generic_request *__lookup_generic_req(
 	struct ceph_mon_client *monc, u64 tid)
@@ -569,7 +569,7 @@ static void handle_statfs_reply(struct ceph_mon_client *monc,
 	return;
 
 bad:
-	pr_err("corrupt generic reply, tid %llu\n", tid);
+	pr_err("corrupt statfs reply, tid %llu\n", tid);
 	ceph_msg_dump(msg);
 }
 
@@ -588,7 +588,6 @@ int ceph_monc_do_statfs(struct ceph_mon_client *monc, struct ceph_statfs *buf)
 
 	kref_init(&req->kref);
 	req->buf = buf;
-	req->buf_len = sizeof(*buf);
 	init_completion(&req->completion);
 
 	err = -ENOMEM;
@@ -611,7 +610,7 @@ int ceph_monc_do_statfs(struct ceph_mon_client *monc, struct ceph_statfs *buf)
 	err = do_generic_request(monc, req);
 
 out:
-	kref_put(&req->kref, release_generic_request);
+	put_generic_request(req);
 	return err;
 }
 EXPORT_SYMBOL(ceph_monc_do_statfs);
@@ -647,7 +646,7 @@ static void handle_get_version_reply(struct ceph_mon_client *monc,
 
 	return;
 bad:
-	pr_err("corrupt mon_get_version reply\n");
+	pr_err("corrupt mon_get_version reply, tid %llu\n", tid);
 	ceph_msg_dump(msg);
 }
 
@@ -670,7 +669,6 @@ int ceph_monc_do_get_version(struct ceph_mon_client *monc, const char *what,
 
 	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,
@@ -701,134 +699,12 @@ int ceph_monc_do_get_version(struct ceph_mon_client *monc, const char *what,
 
 	mutex_unlock(&monc->mutex);
 out:
-	kref_put(&req->kref, release_generic_request);
+	put_generic_request(req);
 	return err;
 }
 EXPORT_SYMBOL(ceph_monc_do_get_version);
 
 /*
- * pool ops
- */
-static int get_poolop_reply_buf(const char *src, size_t src_len,
-				char *dst, size_t dst_len)
-{
-	u32 buf_len;
-
-	if (src_len != sizeof(u32) + dst_len)
-		return -EINVAL;
-
-	buf_len = le32_to_cpu(*(u32 *)src);
-	if (buf_len != dst_len)
-		return -EINVAL;
-
-	memcpy(dst, src + sizeof(u32), dst_len);
-	return 0;
-}
-
-static void handle_poolop_reply(struct ceph_mon_client *monc,
-				struct ceph_msg *msg)
-{
-	struct ceph_mon_generic_request *req;
-	struct ceph_mon_poolop_reply *reply = msg->front.iov_base;
-	u64 tid = le64_to_cpu(msg->hdr.tid);
-
-	if (msg->front.iov_len < sizeof(*reply))
-		goto bad;
-	dout("handle_poolop_reply %p tid %llu\n", msg, tid);
-
-	mutex_lock(&monc->mutex);
-	req = __lookup_generic_req(monc, tid);
-	if (req) {
-		if (req->buf_len &&
-		    get_poolop_reply_buf(msg->front.iov_base + sizeof(*reply),
-				     msg->front.iov_len - sizeof(*reply),
-				     req->buf, req->buf_len) < 0) {
-			mutex_unlock(&monc->mutex);
-			goto bad;
-		}
-		req->result = le32_to_cpu(reply->reply_code);
-		get_generic_request(req);
-	}
-	mutex_unlock(&monc->mutex);
-	if (req) {
-		complete(&req->completion);
-		put_generic_request(req);
-	}
-	return;
-
-bad:
-	pr_err("corrupt generic reply, tid %llu\n", tid);
-	ceph_msg_dump(msg);
-}
-
-/*
- * Do a synchronous pool op.
- */
-static int do_poolop(struct ceph_mon_client *monc, u32 op,
-			u32 pool, u64 snapid,
-			char *buf, int len)
-{
-	struct ceph_mon_generic_request *req;
-	struct ceph_mon_poolop *h;
-	int err;
-
-	req = kzalloc(sizeof(*req), GFP_NOFS);
-	if (!req)
-		return -ENOMEM;
-
-	kref_init(&req->kref);
-	req->buf = buf;
-	req->buf_len = len;
-	init_completion(&req->completion);
-
-	err = -ENOMEM;
-	req->request = ceph_msg_new(CEPH_MSG_POOLOP, sizeof(*h), GFP_NOFS,
-				    true);
-	if (!req->request)
-		goto out;
-	req->reply = ceph_msg_new(CEPH_MSG_POOLOP_REPLY, 1024, GFP_NOFS,
-				  true);
-	if (!req->reply)
-		goto out;
-
-	/* fill out request */
-	req->request->hdr.version = cpu_to_le16(2);
-	h = req->request->front.iov_base;
-	h->monhdr.have_version = 0;
-	h->monhdr.session_mon = cpu_to_le16(-1);
-	h->monhdr.session_mon_tid = 0;
-	h->fsid = monc->monmap->fsid;
-	h->pool = cpu_to_le32(pool);
-	h->op = cpu_to_le32(op);
-	h->auid = 0;
-	h->snapid = cpu_to_le64(snapid);
-	h->name_len = 0;
-
-	err = do_generic_request(monc, req);
-
-out:
-	kref_put(&req->kref, release_generic_request);
-	return err;
-}
-
-int ceph_monc_create_snapid(struct ceph_mon_client *monc,
-			    u32 pool, u64 *snapid)
-{
-	return do_poolop(monc,  POOL_OP_CREATE_UNMANAGED_SNAP,
-				   pool, 0, (char *)snapid, sizeof(*snapid));
-
-}
-EXPORT_SYMBOL(ceph_monc_create_snapid);
-
-int ceph_monc_delete_snapid(struct ceph_mon_client *monc,
-			    u32 pool, u64 snapid)
-{
-	return do_poolop(monc,  POOL_OP_CREATE_UNMANAGED_SNAP,
-				   pool, snapid, NULL, 0);
-
-}
-
-/*
  * Resend pending generic requests.
  */
 static void __resend_generic_request(struct ceph_mon_client *monc)
@@ -1112,10 +988,6 @@ static void dispatch(struct ceph_connection *con, struct ceph_msg *msg)
 		handle_get_version_reply(monc, msg);
 		break;
 
-	case CEPH_MSG_POOLOP_REPLY:
-		handle_poolop_reply(monc, msg);
-		break;
-
 	case CEPH_MSG_MON_MAP:
 		ceph_monc_handle_map(monc, msg);
 		break;
@@ -1154,7 +1026,6 @@ static struct ceph_msg *mon_alloc_msg(struct ceph_connection *con,
 	case CEPH_MSG_MON_SUBSCRIBE_ACK:
 		m = ceph_msg_get(monc->m_subscribe_ack);
 		break;
-	case CEPH_MSG_POOLOP_REPLY:
 	case CEPH_MSG_STATFS_REPLY:
 		return get_generic_reply(con, hdr, skip);
 	case CEPH_MSG_AUTH_REPLY:
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 6f164289bde8..c4ec9239249a 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -292,6 +292,10 @@ static void osd_req_op_data_release(struct ceph_osd_request *osd_req,
 		ceph_osd_data_release(&op->cls.request_data);
 		ceph_osd_data_release(&op->cls.response_data);
 		break;
+	case CEPH_OSD_OP_SETXATTR:
+	case CEPH_OSD_OP_CMPXATTR:
+		ceph_osd_data_release(&op->xattr.osd_data);
+		break;
 	default:
 		break;
 	}
@@ -476,8 +480,7 @@ void osd_req_op_extent_init(struct ceph_osd_request *osd_req,
 	size_t payload_len = 0;
 
 	BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE &&
-	       opcode != CEPH_OSD_OP_DELETE && opcode != CEPH_OSD_OP_ZERO &&
-	       opcode != CEPH_OSD_OP_TRUNCATE);
+	       opcode != CEPH_OSD_OP_ZERO && opcode != CEPH_OSD_OP_TRUNCATE);
 
 	op->extent.offset = offset;
 	op->extent.length = length;
@@ -545,6 +548,39 @@ void osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which,
 }
 EXPORT_SYMBOL(osd_req_op_cls_init);
 
+int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int which,
+			  u16 opcode, const char *name, const void *value,
+			  size_t size, u8 cmp_op, u8 cmp_mode)
+{
+	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which, opcode);
+	struct ceph_pagelist *pagelist;
+	size_t payload_len;
+
+	BUG_ON(opcode != CEPH_OSD_OP_SETXATTR && opcode != CEPH_OSD_OP_CMPXATTR);
+
+	pagelist = kmalloc(sizeof(*pagelist), GFP_NOFS);
+	if (!pagelist)
+		return -ENOMEM;
+
+	ceph_pagelist_init(pagelist);
+
+	payload_len = strlen(name);
+	op->xattr.name_len = payload_len;
+	ceph_pagelist_append(pagelist, name, payload_len);
+
+	op->xattr.value_len = size;
+	ceph_pagelist_append(pagelist, value, size);
+	payload_len += size;
+
+	op->xattr.cmp_op = cmp_op;
+	op->xattr.cmp_mode = cmp_mode;
+
+	ceph_osd_data_pagelist_init(&op->xattr.osd_data, pagelist);
+	op->payload_len = payload_len;
+	return 0;
+}
+EXPORT_SYMBOL(osd_req_op_xattr_init);
+
 void osd_req_op_watch_init(struct ceph_osd_request *osd_req,
 				unsigned int which, u16 opcode,
 				u64 cookie, u64 version, int flag)
@@ -626,7 +662,6 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req,
 	case CEPH_OSD_OP_READ:
 	case CEPH_OSD_OP_WRITE:
 	case CEPH_OSD_OP_ZERO:
-	case CEPH_OSD_OP_DELETE:
 	case CEPH_OSD_OP_TRUNCATE:
 		if (src->op == CEPH_OSD_OP_WRITE)
 			request_data_len = src->extent.length;
@@ -676,6 +711,19 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req,
 		dst->alloc_hint.expected_write_size =
 		    cpu_to_le64(src->alloc_hint.expected_write_size);
 		break;
+	case CEPH_OSD_OP_SETXATTR:
+	case CEPH_OSD_OP_CMPXATTR:
+		dst->xattr.name_len = cpu_to_le32(src->xattr.name_len);
+		dst->xattr.value_len = cpu_to_le32(src->xattr.value_len);
+		dst->xattr.cmp_op = src->xattr.cmp_op;
+		dst->xattr.cmp_mode = src->xattr.cmp_mode;
+		osd_data = &src->xattr.osd_data;
+		ceph_osdc_msg_data_add(req->r_request, osd_data);
+		request_data_len = osd_data->pagelist->length;
+		break;
+	case CEPH_OSD_OP_CREATE:
+	case CEPH_OSD_OP_DELETE:
+		break;
 	default:
 		pr_err("unsupported osd opcode %s\n",
 			ceph_osd_op_name(src->op));
@@ -705,7 +753,8 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req,
 struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 					       struct ceph_file_layout *layout,
 					       struct ceph_vino vino,
-					       u64 off, u64 *plen, int num_ops,
+					       u64 off, u64 *plen,
+					       unsigned int which, int num_ops,
 					       int opcode, int flags,
 					       struct ceph_snap_context *snapc,
 					       u32 truncate_seq,
@@ -716,13 +765,11 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 	u64 objnum = 0;
 	u64 objoff = 0;
 	u64 objlen = 0;
-	u32 object_size;
-	u64 object_base;
 	int r;
 
 	BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE &&
-	       opcode != CEPH_OSD_OP_DELETE && opcode != CEPH_OSD_OP_ZERO &&
-	       opcode != CEPH_OSD_OP_TRUNCATE);
+	       opcode != CEPH_OSD_OP_ZERO && opcode != CEPH_OSD_OP_TRUNCATE &&
+	       opcode != CEPH_OSD_OP_CREATE && opcode != CEPH_OSD_OP_DELETE);
 
 	req = ceph_osdc_alloc_request(osdc, snapc, num_ops, use_mempool,
 					GFP_NOFS);
@@ -738,29 +785,24 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 		return ERR_PTR(r);
 	}
 
-	object_size = le32_to_cpu(layout->fl_object_size);
-	object_base = off - objoff;
-	if (!(truncate_seq == 1 && truncate_size == -1ULL)) {
-		if (truncate_size <= object_base) {
-			truncate_size = 0;
-		} else {
-			truncate_size -= object_base;
-			if (truncate_size > object_size)
-				truncate_size = object_size;
+	if (opcode == CEPH_OSD_OP_CREATE || opcode == CEPH_OSD_OP_DELETE) {
+		osd_req_op_init(req, which, opcode);
+	} else {
+		u32 object_size = le32_to_cpu(layout->fl_object_size);
+		u32 object_base = off - objoff;
+		if (!(truncate_seq == 1 && truncate_size == -1ULL)) {
+			if (truncate_size <= object_base) {
+				truncate_size = 0;
+			} else {
+				truncate_size -= object_base;
+				if (truncate_size > object_size)
+					truncate_size = object_size;
+			}
 		}
+		osd_req_op_extent_init(req, which, opcode, objoff, objlen,
+				       truncate_size, truncate_seq);
 	}
 
-	osd_req_op_extent_init(req, 0, opcode, objoff, objlen,
-				truncate_size, truncate_seq);
-
-	/*
-	 * A second op in the ops array means the caller wants to
-	 * also issue a include a 'startsync' command so that the
-	 * osd will flush data quickly.
-	 */
-	if (num_ops > 1)
-		osd_req_op_init(req, 1, CEPH_OSD_OP_STARTSYNC);
-
 	req->r_base_oloc.pool = ceph_file_layout_pg_pool(*layout);
 
 	snprintf(req->r_base_oid.name, sizeof(req->r_base_oid.name),
@@ -993,10 +1035,11 @@ static void put_osd(struct ceph_osd *osd)
 {
 	dout("put_osd %p %d -> %d\n", osd, atomic_read(&osd->o_ref),
 	     atomic_read(&osd->o_ref) - 1);
-	if (atomic_dec_and_test(&osd->o_ref) && osd->o_auth.authorizer) {
+	if (atomic_dec_and_test(&osd->o_ref)) {
 		struct ceph_auth_client *ac = osd->o_osdc->client->monc.auth;
 
-		ceph_auth_destroy_authorizer(ac, osd->o_auth.authorizer);
+		if (osd->o_auth.authorizer)
+			ceph_auth_destroy_authorizer(ac, osd->o_auth.authorizer);
 		kfree(osd);
 	}
 }
@@ -1006,14 +1049,24 @@ static void put_osd(struct ceph_osd *osd)
  */
 static void __remove_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd)
 {
-	dout("__remove_osd %p\n", osd);
+	dout("%s %p osd%d\n", __func__, osd, osd->o_osd);
 	WARN_ON(!list_empty(&osd->o_requests));
 	WARN_ON(!list_empty(&osd->o_linger_requests));
 
-	rb_erase(&osd->o_node, &osdc->osds);
 	list_del_init(&osd->o_osd_lru);
-	ceph_con_close(&osd->o_con);
-	put_osd(osd);
+	rb_erase(&osd->o_node, &osdc->osds);
+	RB_CLEAR_NODE(&osd->o_node);
+}
+
+static void remove_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd)
+{
+	dout("%s %p osd%d\n", __func__, osd, osd->o_osd);
+
+	if (!RB_EMPTY_NODE(&osd->o_node)) {
+		ceph_con_close(&osd->o_con);
+		__remove_osd(osdc, osd);
+		put_osd(osd);
+	}
 }
 
 static void remove_all_osds(struct ceph_osd_client *osdc)
@@ -1023,7 +1076,7 @@ static void remove_all_osds(struct ceph_osd_client *osdc)
 	while (!RB_EMPTY_ROOT(&osdc->osds)) {
 		struct ceph_osd *osd = rb_entry(rb_first(&osdc->osds),
 						struct ceph_osd, o_node);
-		__remove_osd(osdc, osd);
+		remove_osd(osdc, osd);
 	}
 	mutex_unlock(&osdc->request_mutex);
 }
@@ -1064,7 +1117,7 @@ static void remove_old_osds(struct ceph_osd_client *osdc)
 	list_for_each_entry_safe(osd, nosd, &osdc->osd_lru, o_osd_lru) {
 		if (time_before(jiffies, osd->lru_ttl))
 			break;
-		__remove_osd(osdc, osd);
+		remove_osd(osdc, osd);
 	}
 	mutex_unlock(&osdc->request_mutex);
 }
@@ -1079,8 +1132,7 @@ static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd)
 	dout("__reset_osd %p osd%d\n", osd, osd->o_osd);
 	if (list_empty(&osd->o_requests) &&
 	    list_empty(&osd->o_linger_requests)) {
-		__remove_osd(osdc, osd);
-
+		remove_osd(osdc, osd);
 		return -ENODEV;
 	}
 
@@ -1254,8 +1306,6 @@ static void __unregister_linger_request(struct ceph_osd_client *osdc,
 		if (list_empty(&req->r_osd_item))
 			req->r_osd = NULL;
 	}
-
-	list_del_init(&req->r_req_lru_item); /* can be on notarget */
 	ceph_osdc_put_request(req);
 }
 
@@ -1884,6 +1934,7 @@ static void reset_changed_osds(struct ceph_osd_client *osdc)
 {
 	struct rb_node *p, *n;
 
+	dout("%s %p\n", __func__, osdc);
 	for (p = rb_first(&osdc->osds); p; p = n) {
 		struct ceph_osd *osd = rb_entry(p, struct ceph_osd, o_node);
 
@@ -1964,20 +2015,29 @@ static void kick_requests(struct ceph_osd_client *osdc, bool 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 */
 		if (err < 0)
 			continue;  /* hrm! */
-		if (req->r_osd == NULL) {
-			dout("tid %llu maps to no valid osd\n", req->r_tid);
-			needmap++;  /* request a newer map */
-			continue;
-		}
+		if (req->r_osd == NULL || err > 0) {
+			if (req->r_osd == NULL) {
+				dout("lingering %p tid %llu maps to no osd\n",
+				     req, req->r_tid);
+				/*
+				 * A homeless lingering request makes
+				 * no sense, as it's job is to keep
+				 * a particular OSD connection open.
+				 * Request a newer map and kick the
+				 * request, knowing that it won't be
+				 * resent until we actually get a map
+				 * that can tell us where to send it.
+				 */
+				needmap++;
+			}
 
-		dout("kicking lingering %p tid %llu osd%d\n", req, req->r_tid,
-		     req->r_osd ? req->r_osd->o_osd : -1);
-		__register_request(osdc, req);
-		__unregister_linger_request(osdc, req);
+			dout("kicking lingering %p tid %llu osd%d\n", req,
+			     req->r_tid, req->r_osd ? req->r_osd->o_osd : -1);
+			__register_request(osdc, req);
+			__unregister_linger_request(osdc, req);
+		}
 	}
 	reset_changed_osds(osdc);
 	mutex_unlock(&osdc->request_mutex);
@@ -2626,7 +2686,7 @@ int ceph_osdc_readpages(struct ceph_osd_client *osdc,
 
 	dout("readpages on ino %llx.%llx on %llu~%llu\n", vino.ino,
 	     vino.snap, off, *plen);
-	req = ceph_osdc_new_request(osdc, layout, vino, off, plen, 1,
+	req = ceph_osdc_new_request(osdc, layout, vino, off, plen, 0, 1,
 				    CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ,
 				    NULL, truncate_seq, truncate_size,
 				    false);
@@ -2669,7 +2729,7 @@ int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino,
 	int page_align = off & ~PAGE_MASK;
 
 	BUG_ON(vino.snap != CEPH_NOSNAP);	/* snapshots aren't writeable */
-	req = ceph_osdc_new_request(osdc, layout, vino, off, &len, 1,
+	req = ceph_osdc_new_request(osdc, layout, vino, off, &len, 0, 1,
 				    CEPH_OSD_OP_WRITE,
 				    CEPH_OSD_FLAG_ONDISK | CEPH_OSD_FLAG_WRITE,
 				    snapc, truncate_seq, truncate_size,
@@ -2920,6 +2980,20 @@ static int invalidate_authorizer(struct ceph_connection *con)
 	return ceph_monc_validate_auth(&osdc->client->monc);
 }
 
+static int sign_message(struct ceph_connection *con, struct ceph_msg *msg)
+{
+	struct ceph_osd *o = con->private;
+	struct ceph_auth_handshake *auth = &o->o_auth;
+	return ceph_auth_sign_message(auth, msg);
+}
+
+static int check_message_signature(struct ceph_connection *con, struct ceph_msg *msg)
+{
+	struct ceph_osd *o = con->private;
+	struct ceph_auth_handshake *auth = &o->o_auth;
+	return ceph_auth_check_message_signature(auth, msg);
+}
+
 static const struct ceph_connection_operations osd_con_ops = {
 	.get = get_osd_con,
 	.put = put_osd_con,
@@ -2928,5 +3002,7 @@ static const struct ceph_connection_operations osd_con_ops = {
 	.verify_authorizer_reply = verify_authorizer_reply,
 	.invalidate_authorizer = invalidate_authorizer,
 	.alloc_msg = alloc_msg,
+	.sign_message = sign_message,
+	.check_message_signature = check_message_signature,
 	.fault = osd_reset,
 };
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index b8c3fde5b04f..15796696d64e 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -122,6 +122,22 @@ bad:
 	return -EINVAL;
 }
 
+static int crush_decode_straw2_bucket(void **p, void *end,
+				      struct crush_bucket_straw2 *b)
+{
+	int j;
+	dout("crush_decode_straw2_bucket %p to %p\n", *p, end);
+	b->item_weights = kcalloc(b->h.size, sizeof(u32), GFP_NOFS);
+	if (b->item_weights == NULL)
+		return -ENOMEM;
+	ceph_decode_need(p, end, b->h.size * sizeof(u32), bad);
+	for (j = 0; j < b->h.size; j++)
+		b->item_weights[j] = ceph_decode_32(p);
+	return 0;
+bad:
+	return -EINVAL;
+}
+
 static int skip_name_map(void **p, void *end)
 {
         int len;
@@ -204,6 +220,9 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
 		case CRUSH_BUCKET_STRAW:
 			size = sizeof(struct crush_bucket_straw);
 			break;
+		case CRUSH_BUCKET_STRAW2:
+			size = sizeof(struct crush_bucket_straw2);
+			break;
 		default:
 			err = -EINVAL;
 			goto bad;
@@ -261,6 +280,12 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
 			if (err < 0)
 				goto bad;
 			break;
+		case CRUSH_BUCKET_STRAW2:
+			err = crush_decode_straw2_bucket(p, end,
+				(struct crush_bucket_straw2 *)b);
+			if (err < 0)
+				goto bad;
+			break;
 		}
 	}
 
diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c
index 555013034f7a..096d91447e06 100644
--- a/net/ceph/pagevec.c
+++ b/net/ceph/pagevec.c
@@ -23,17 +23,15 @@ struct page **ceph_get_direct_page_vector(const void __user *data,
 	if (!pages)
 		return ERR_PTR(-ENOMEM);
 
-	down_read(&current->mm->mmap_sem);
 	while (got < num_pages) {
-		rc = get_user_pages(current, current->mm,
+		rc = get_user_pages_unlocked(current, current->mm,
 		    (unsigned long)data + ((unsigned long)got * PAGE_SIZE),
-		    num_pages - got, write_page, 0, pages + got, NULL);
+		    num_pages - got, write_page, 0, pages + got);
 		if (rc < 0)
 			break;
 		BUG_ON(rc == 0);
 		got += rc;
 	}
-	up_read(&current->mm->mmap_sem);
 	if (rc < 0)
 		goto fail;
 	return pages;
diff --git a/net/compat.c b/net/compat.c
index bc8aeefddf3f..5cfd26a0006f 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -31,81 +31,59 @@
 #include <asm/uaccess.h>
 #include <net/compat.h>
 
-static inline int iov_from_user_compat_to_kern(struct iovec *kiov,
-					  struct compat_iovec __user *uiov32,
-					  int niov)
+int get_compat_msghdr(struct msghdr *kmsg,
+		      struct compat_msghdr __user *umsg,
+		      struct sockaddr __user **save_addr,
+		      struct iovec **iov)
 {
-	int tot_len = 0;
-
-	while (niov > 0) {
-		compat_uptr_t buf;
-		compat_size_t len;
-
-		if (get_user(len, &uiov32->iov_len) ||
-		    get_user(buf, &uiov32->iov_base))
-			return -EFAULT;
-
-		if (len > INT_MAX - tot_len)
-			len = INT_MAX - tot_len;
-
-		tot_len += len;
-		kiov->iov_base = compat_ptr(buf);
-		kiov->iov_len = (__kernel_size_t) len;
-		uiov32++;
-		kiov++;
-		niov--;
-	}
-	return tot_len;
-}
-
-int get_compat_msghdr(struct msghdr *kmsg, struct compat_msghdr __user *umsg)
-{
-	compat_uptr_t tmp1, tmp2, tmp3;
+	compat_uptr_t uaddr, uiov, tmp3;
+	compat_size_t nr_segs;
+	ssize_t err;
 
 	if (!access_ok(VERIFY_READ, umsg, sizeof(*umsg)) ||
-	    __get_user(tmp1, &umsg->msg_name) ||
+	    __get_user(uaddr, &umsg->msg_name) ||
 	    __get_user(kmsg->msg_namelen, &umsg->msg_namelen) ||
-	    __get_user(tmp2, &umsg->msg_iov) ||
-	    __get_user(kmsg->msg_iovlen, &umsg->msg_iovlen) ||
+	    __get_user(uiov, &umsg->msg_iov) ||
+	    __get_user(nr_segs, &umsg->msg_iovlen) ||
 	    __get_user(tmp3, &umsg->msg_control) ||
 	    __get_user(kmsg->msg_controllen, &umsg->msg_controllen) ||
 	    __get_user(kmsg->msg_flags, &umsg->msg_flags))
 		return -EFAULT;
+
+	if (!uaddr)
+		kmsg->msg_namelen = 0;
+
+	if (kmsg->msg_namelen < 0)
+		return -EINVAL;
+
 	if (kmsg->msg_namelen > sizeof(struct sockaddr_storage))
 		kmsg->msg_namelen = sizeof(struct sockaddr_storage);
-	kmsg->msg_name = compat_ptr(tmp1);
-	kmsg->msg_iov = compat_ptr(tmp2);
 	kmsg->msg_control = compat_ptr(tmp3);
-	return 0;
-}
 
-/* I've named the args so it is easy to tell whose space the pointers are in. */
-int verify_compat_iovec(struct msghdr *kern_msg, struct iovec *kern_iov,
-		   struct sockaddr_storage *kern_address, int mode)
-{
-	int tot_len;
+	if (save_addr)
+		*save_addr = compat_ptr(uaddr);
 
-	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,
-						      kern_address);
+	if (uaddr && kmsg->msg_namelen) {
+		if (!save_addr) {
+			err = move_addr_to_kernel(compat_ptr(uaddr),
+						  kmsg->msg_namelen,
+						  kmsg->msg_name);
 			if (err < 0)
 				return err;
 		}
-		kern_msg->msg_name = kern_address;
 	} else {
-		kern_msg->msg_name = NULL;
-		kern_msg->msg_namelen = 0;
+		kmsg->msg_name = NULL;
+		kmsg->msg_namelen = 0;
 	}
 
-	tot_len = iov_from_user_compat_to_kern(kern_iov,
-					  (struct compat_iovec __user *)kern_msg->msg_iov,
-					  kern_msg->msg_iovlen);
-	if (tot_len >= 0)
-		kern_msg->msg_iov = kern_iov;
+	if (nr_segs > UIO_MAXIOV)
+		return -EMSGSIZE;
+
+	kmsg->msg_iocb = NULL;
 
-	return tot_len;
+	return compat_import_iovec(save_addr ? READ : WRITE,
+				   compat_ptr(uiov), nr_segs,
+				   UIO_FASTIOV, iov, &kmsg->msg_iter);
 }
 
 /* Bleech... */
@@ -535,25 +513,25 @@ COMPAT_SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname,
 struct compat_group_req {
 	__u32				 gr_interface;
 	struct __kernel_sockaddr_storage gr_group
-		__attribute__ ((aligned(4)));
+		__aligned(4);
 } __packed;
 
 struct compat_group_source_req {
 	__u32				 gsr_interface;
 	struct __kernel_sockaddr_storage gsr_group
-		__attribute__ ((aligned(4)));
+		__aligned(4);
 	struct __kernel_sockaddr_storage gsr_source
-		__attribute__ ((aligned(4)));
+		__aligned(4);
 } __packed;
 
 struct compat_group_filter {
 	__u32				 gf_interface;
 	struct __kernel_sockaddr_storage gf_group
-		__attribute__ ((aligned(4)));
+		__aligned(4);
 	__u32				 gf_fmode;
 	__u32				 gf_numsrc;
 	struct __kernel_sockaddr_storage gf_slist[1]
-		__attribute__ ((aligned(4)));
+		__aligned(4);
 } __packed;
 
 #define __COMPAT_GF0_SIZE (sizeof(struct compat_group_filter) - \
@@ -738,25 +716,19 @@ static unsigned char nas[21] = {
 
 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);
+	return __sys_sendmsg(fd, (struct user_msghdr __user *)msg, flags | MSG_CMSG_COMPAT);
 }
 
 COMPAT_SYSCALL_DEFINE4(sendmmsg, int, fd, struct compat_mmsghdr __user *, mmsg,
 		       unsigned int, vlen, unsigned int, flags)
 {
-	if (flags & MSG_CMSG_COMPAT)
-		return -EINVAL;
 	return __sys_sendmmsg(fd, (struct mmsghdr __user *)mmsg, vlen,
 			      flags | MSG_CMSG_COMPAT);
 }
 
 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);
+	return __sys_recvmsg(fd, (struct user_msghdr __user *)msg, flags | MSG_CMSG_COMPAT);
 }
 
 COMPAT_SYSCALL_DEFINE4(recv, int, fd, void __user *, buf, compat_size_t, len, unsigned int, flags)
@@ -778,9 +750,6 @@ COMPAT_SYSCALL_DEFINE5(recvmmsg, int, fd, struct compat_mmsghdr __user *, mmsg,
 	int datagrams;
 	struct timespec ktspec;
 
-	if (flags & MSG_CMSG_COMPAT)
-		return -EINVAL;
-
 	if (timeout == NULL)
 		return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen,
 				      flags | MSG_CMSG_COMPAT, NULL);
diff --git a/net/core/Makefile b/net/core/Makefile
index 235e6c50708d..fec0856dd6c0 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -2,7 +2,7 @@
 # Makefile for the Linux networking core.
 #
 
-obj-y := sock.o request_sock.o skbuff.o iovec.o datagram.o stream.o scm.o \
+obj-y := sock.o request_sock.o skbuff.o datagram.o stream.o scm.o \
 	 gen_stats.o gen_estimator.o net_namespace.o secure_seq.o flow_dissector.o
 
 obj-$(CONFIG_SYSCTL) += sysctl_net_core.o
diff --git a/net/core/datagram.c b/net/core/datagram.c
index fdbc9a81d4c2..b80fb91bb3f7 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -49,6 +49,7 @@
 #include <linux/spinlock.h>
 #include <linux/slab.h>
 #include <linux/pagemap.h>
+#include <linux/uio.h>
 
 #include <net/protocol.h>
 #include <linux/skbuff.h>
@@ -309,16 +310,14 @@ int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags)
 EXPORT_SYMBOL(skb_kill_datagram);
 
 /**
- *	skb_copy_datagram_iovec - Copy a datagram to an iovec.
+ *	skb_copy_datagram_iter - Copy a datagram to an iovec iterator.
  *	@skb: buffer to copy
  *	@offset: offset in the buffer to start copying from
- *	@to: io vector to copy to
+ *	@to: iovec iterator to copy to
  *	@len: amount of data to copy from buffer to iovec
- *
- *	Note: the iovec is modified during the copy.
  */
-int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset,
-			    struct iovec *to, int len)
+int skb_copy_datagram_iter(const struct sk_buff *skb, int offset,
+			   struct iov_iter *to, int len)
 {
 	int start = skb_headlen(skb);
 	int i, copy = start - offset;
@@ -330,8 +329,8 @@ int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset,
 	if (copy > 0) {
 		if (copy > len)
 			copy = len;
-		if (memcpy_toiovec(to, skb->data + offset, copy))
-			goto fault;
+		if (copy_to_iter(skb->data + offset, copy, to) != copy)
+			goto short_copy;
 		if ((len -= copy) == 0)
 			return 0;
 		offset += copy;
@@ -346,18 +345,12 @@ int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset,
 
 		end = start + skb_frag_size(frag);
 		if ((copy = end - offset) > 0) {
-			int err;
-			u8  *vaddr;
-			struct page *page = skb_frag_page(frag);
-
 			if (copy > len)
 				copy = len;
-			vaddr = kmap(page);
-			err = memcpy_toiovec(to, vaddr + frag->page_offset +
-					     offset - start, copy);
-			kunmap(page);
-			if (err)
-				goto fault;
+			if (copy_page_to_iter(skb_frag_page(frag),
+					      frag->page_offset + offset -
+					      start, copy, to) != copy)
+				goto short_copy;
 			if (!(len -= copy))
 				return 0;
 			offset += copy;
@@ -374,9 +367,8 @@ int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset,
 		if ((copy = end - offset) > 0) {
 			if (copy > len)
 				copy = len;
-			if (skb_copy_datagram_iovec(frag_iter,
-						    offset - start,
-						    to, copy))
+			if (skb_copy_datagram_iter(frag_iter, offset - start,
+						   to, copy))
 				goto fault;
 			if ((len -= copy) == 0)
 				return 0;
@@ -387,113 +379,33 @@ int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset,
 	if (!len)
 		return 0;
 
+	/* This is not really a user copy fault, but rather someone
+	 * gave us a bogus length on the skb.  We should probably
+	 * print a warning here as it may indicate a kernel bug.
+	 */
+
 fault:
 	return -EFAULT;
-}
-EXPORT_SYMBOL(skb_copy_datagram_iovec);
 
-/**
- *	skb_copy_datagram_const_iovec - Copy a datagram to an iovec.
- *	@skb: buffer to copy
- *	@offset: offset in the buffer to start copying from
- *	@to: io vector to copy to
- *	@to_offset: offset in the io vector to start copying to
- *	@len: amount of data to copy from buffer to iovec
- *
- *	Returns 0 or -EFAULT.
- *	Note: the iovec is not modified during the copy.
- */
-int skb_copy_datagram_const_iovec(const struct sk_buff *skb, int offset,
-				  const struct iovec *to, int to_offset,
-				  int len)
-{
-	int start = skb_headlen(skb);
-	int i, copy = start - offset;
-	struct sk_buff *frag_iter;
+short_copy:
+	if (iov_iter_count(to))
+		goto fault;
 
-	/* Copy header. */
-	if (copy > 0) {
-		if (copy > len)
-			copy = len;
-		if (memcpy_toiovecend(to, skb->data + offset, to_offset, copy))
-			goto fault;
-		if ((len -= copy) == 0)
-			return 0;
-		offset += copy;
-		to_offset += copy;
-	}
-
-	/* Copy paged appendix. Hmm... why does this look so complicated? */
-	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
-		int end;
-		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
-
-		WARN_ON(start > offset + len);
-
-		end = start + skb_frag_size(frag);
-		if ((copy = end - offset) > 0) {
-			int err;
-			u8  *vaddr;
-			struct page *page = skb_frag_page(frag);
-
-			if (copy > len)
-				copy = len;
-			vaddr = kmap(page);
-			err = memcpy_toiovecend(to, vaddr + frag->page_offset +
-						offset - start, to_offset, copy);
-			kunmap(page);
-			if (err)
-				goto fault;
-			if (!(len -= copy))
-				return 0;
-			offset += copy;
-			to_offset += copy;
-		}
-		start = end;
-	}
-
-	skb_walk_frags(skb, frag_iter) {
-		int end;
-
-		WARN_ON(start > offset + len);
-
-		end = start + frag_iter->len;
-		if ((copy = end - offset) > 0) {
-			if (copy > len)
-				copy = len;
-			if (skb_copy_datagram_const_iovec(frag_iter,
-							  offset - start,
-							  to, to_offset,
-							  copy))
-				goto fault;
-			if ((len -= copy) == 0)
-				return 0;
-			offset += copy;
-			to_offset += copy;
-		}
-		start = end;
-	}
-	if (!len)
-		return 0;
-
-fault:
-	return -EFAULT;
+	return 0;
 }
-EXPORT_SYMBOL(skb_copy_datagram_const_iovec);
+EXPORT_SYMBOL(skb_copy_datagram_iter);
 
 /**
- *	skb_copy_datagram_from_iovec - Copy a datagram from an iovec.
+ *	skb_copy_datagram_from_iter - Copy a datagram from an iov_iter.
  *	@skb: buffer to copy
  *	@offset: offset in the buffer to start copying to
- *	@from: io vector to copy to
- *	@from_offset: offset in the io vector to start copying from
+ *	@from: the copy source
  *	@len: amount of data to copy to buffer from iovec
  *
  *	Returns 0 or -EFAULT.
- *	Note: the iovec is not modified during the copy.
  */
-int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset,
-				 const struct iovec *from, int from_offset,
+int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset,
+				 struct iov_iter *from,
 				 int len)
 {
 	int start = skb_headlen(skb);
@@ -504,13 +416,11 @@ int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset,
 	if (copy > 0) {
 		if (copy > len)
 			copy = len;
-		if (memcpy_fromiovecend(skb->data + offset, from, from_offset,
-					copy))
+		if (copy_from_iter(skb->data + offset, copy, from) != copy)
 			goto fault;
 		if ((len -= copy) == 0)
 			return 0;
 		offset += copy;
-		from_offset += copy;
 	}
 
 	/* Copy paged appendix. Hmm... why does this look so complicated? */
@@ -522,24 +432,19 @@ int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset,
 
 		end = start + skb_frag_size(frag);
 		if ((copy = end - offset) > 0) {
-			int err;
-			u8  *vaddr;
-			struct page *page = skb_frag_page(frag);
+			size_t copied;
 
 			if (copy > len)
 				copy = len;
-			vaddr = kmap(page);
-			err = memcpy_fromiovecend(vaddr + frag->page_offset +
-						  offset - start,
-						  from, from_offset, copy);
-			kunmap(page);
-			if (err)
+			copied = copy_page_from_iter(skb_frag_page(frag),
+					  frag->page_offset + offset - start,
+					  copy, from);
+			if (copied != copy)
 				goto fault;
 
 			if (!(len -= copy))
 				return 0;
 			offset += copy;
-			from_offset += copy;
 		}
 		start = end;
 	}
@@ -553,16 +458,13 @@ int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset,
 		if ((copy = end - offset) > 0) {
 			if (copy > len)
 				copy = len;
-			if (skb_copy_datagram_from_iovec(frag_iter,
-							 offset - start,
-							 from,
-							 from_offset,
-							 copy))
+			if (skb_copy_datagram_from_iter(frag_iter,
+							offset - start,
+							from, copy))
 				goto fault;
 			if ((len -= copy) == 0)
 				return 0;
 			offset += copy;
-			from_offset += copy;
 		}
 		start = end;
 	}
@@ -572,101 +474,82 @@ int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset,
 fault:
 	return -EFAULT;
 }
-EXPORT_SYMBOL(skb_copy_datagram_from_iovec);
+EXPORT_SYMBOL(skb_copy_datagram_from_iter);
 
 /**
- *	zerocopy_sg_from_iovec - Build a zerocopy datagram from an iovec
+ *	zerocopy_sg_from_iter - Build a zerocopy datagram from an iov_iter
  *	@skb: buffer to copy
- *	@from: io vector to copy from
- *	@offset: offset in the io vector to start copying from
- *	@count: amount of vectors to copy to buffer from
+ *	@from: the source to copy from
  *
  *	The function will first copy up to headlen, and then pin the userspace
  *	pages and build frags through them.
  *
  *	Returns 0, -EFAULT or -EMSGSIZE.
- *	Note: the iovec is not modified during the copy
  */
-int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from,
-				  int offset, size_t count)
+int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from)
 {
-	int len = iov_length(from, count) - offset;
+	int len = iov_iter_count(from);
 	int copy = min_t(int, skb_headlen(skb), len);
-	int size;
-	int i = 0;
+	int frag = 0;
 
 	/* copy up to skb headlen */
-	if (skb_copy_datagram_from_iovec(skb, 0, from, offset, copy))
+	if (skb_copy_datagram_from_iter(skb, 0, from, copy))
 		return -EFAULT;
 
-	if (len == copy)
-		return 0;
-
-	offset += copy;
-	while (count--) {
-		struct page *page[MAX_SKB_FRAGS];
-		int num_pages;
-		unsigned long base;
+	while (iov_iter_count(from)) {
+		struct page *pages[MAX_SKB_FRAGS];
+		size_t start;
+		ssize_t copied;
 		unsigned long truesize;
+		int n = 0;
 
-		/* Skip over from offset and copied */
-		if (offset >= from->iov_len) {
-			offset -= from->iov_len;
-			++from;
-			continue;
-		}
-		len = from->iov_len - offset;
-		base = (unsigned long)from->iov_base + offset;
-		size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT;
-		if (i + size > MAX_SKB_FRAGS)
+		if (frag == MAX_SKB_FRAGS)
 			return -EMSGSIZE;
-		num_pages = get_user_pages_fast(base, size, 0, &page[i]);
-		if (num_pages != size) {
-			release_pages(&page[i], num_pages, 0);
+
+		copied = iov_iter_get_pages(from, pages, ~0U,
+					    MAX_SKB_FRAGS - frag, &start);
+		if (copied < 0)
 			return -EFAULT;
-		}
-		truesize = size * PAGE_SIZE;
-		skb->data_len += len;
-		skb->len += len;
+
+		iov_iter_advance(from, copied);
+
+		truesize = PAGE_ALIGN(copied + start);
+		skb->data_len += copied;
+		skb->len += copied;
 		skb->truesize += truesize;
 		atomic_add(truesize, &skb->sk->sk_wmem_alloc);
-		while (len) {
-			int off = base & ~PAGE_MASK;
-			int size = min_t(int, len, PAGE_SIZE - off);
-			skb_fill_page_desc(skb, i, page[i], off, size);
-			base += size;
-			len -= size;
-			i++;
+		while (copied) {
+			int size = min_t(int, copied, PAGE_SIZE - start);
+			skb_fill_page_desc(skb, frag++, pages[n], start, size);
+			start = 0;
+			copied -= size;
+			n++;
 		}
-		offset = 0;
-		++from;
 	}
 	return 0;
 }
-EXPORT_SYMBOL(zerocopy_sg_from_iovec);
+EXPORT_SYMBOL(zerocopy_sg_from_iter);
 
 static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset,
-				      u8 __user *to, int len,
+				      struct iov_iter *to, int len,
 				      __wsum *csump)
 {
 	int start = skb_headlen(skb);
 	int i, copy = start - offset;
 	struct sk_buff *frag_iter;
 	int pos = 0;
+	int n;
 
 	/* Copy header. */
 	if (copy > 0) {
-		int err = 0;
 		if (copy > len)
 			copy = len;
-		*csump = csum_and_copy_to_user(skb->data + offset, to, copy,
-					       *csump, &err);
-		if (err)
+		n = csum_and_copy_to_iter(skb->data + offset, copy, csump, to);
+		if (n != copy)
 			goto fault;
 		if ((len -= copy) == 0)
 			return 0;
 		offset += copy;
-		to += copy;
 		pos = copy;
 	}
 
@@ -678,26 +561,22 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset,
 
 		end = start + skb_frag_size(frag);
 		if ((copy = end - offset) > 0) {
-			__wsum csum2;
-			int err = 0;
-			u8  *vaddr;
+			__wsum csum2 = 0;
 			struct page *page = skb_frag_page(frag);
+			u8  *vaddr = kmap(page);
 
 			if (copy > len)
 				copy = len;
-			vaddr = kmap(page);
-			csum2 = csum_and_copy_to_user(vaddr +
-							frag->page_offset +
-							offset - start,
-						      to, copy, 0, &err);
+			n = csum_and_copy_to_iter(vaddr + frag->page_offset +
+						  offset - start, copy,
+						  &csum2, to);
 			kunmap(page);
-			if (err)
+			if (n != copy)
 				goto fault;
 			*csump = csum_block_add(*csump, csum2, pos);
 			if (!(len -= copy))
 				return 0;
 			offset += copy;
-			to += copy;
 			pos += copy;
 		}
 		start = end;
@@ -722,7 +601,6 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset,
 			if ((len -= copy) == 0)
 				return 0;
 			offset += copy;
-			to += copy;
 			pos += copy;
 		}
 		start = end;
@@ -775,20 +653,19 @@ __sum16 __skb_checksum_complete(struct sk_buff *skb)
 EXPORT_SYMBOL(__skb_checksum_complete);
 
 /**
- *	skb_copy_and_csum_datagram_iovec - Copy and checksum skb to user iovec.
+ *	skb_copy_and_csum_datagram_msg - Copy and checksum skb to user iovec.
  *	@skb: skbuff
  *	@hlen: hardware length
- *	@iov: io vector
+ *	@msg: destination
  *
  *	Caller _must_ check that skb will fit to this iovec.
  *
  *	Returns: 0       - success.
  *		 -EINVAL - checksum failure.
- *		 -EFAULT - fault during copy. Beware, in this case iovec
- *			   can be modified!
+ *		 -EFAULT - fault during copy.
  */
-int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb,
-				     int hlen, struct iovec *iov)
+int skb_copy_and_csum_datagram_msg(struct sk_buff *skb,
+				   int hlen, struct msghdr *msg)
 {
 	__wsum csum;
 	int chunk = skb->len - hlen;
@@ -796,28 +673,20 @@ int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb,
 	if (!chunk)
 		return 0;
 
-	/* Skip filled elements.
-	 * Pretty silly, look at memcpy_toiovec, though 8)
-	 */
-	while (!iov->iov_len)
-		iov++;
-
-	if (iov->iov_len < chunk) {
+	if (msg_data_left(msg) < chunk) {
 		if (__skb_checksum_complete(skb))
 			goto csum_error;
-		if (skb_copy_datagram_iovec(skb, hlen, iov, chunk))
+		if (skb_copy_datagram_msg(skb, hlen, msg, chunk))
 			goto fault;
 	} else {
 		csum = csum_partial(skb->data, hlen, skb->csum);
-		if (skb_copy_and_csum_datagram(skb, hlen, iov->iov_base,
+		if (skb_copy_and_csum_datagram(skb, hlen, &msg->msg_iter,
 					       chunk, &csum))
 			goto fault;
 		if (csum_fold(csum))
 			goto csum_error;
 		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE))
 			netdev_rx_csum_fault(skb->dev);
-		iov->iov_len -= chunk;
-		iov->iov_base += chunk;
 	}
 	return 0;
 csum_error:
@@ -825,7 +694,7 @@ csum_error:
 fault:
 	return -EFAULT;
 }
-EXPORT_SYMBOL(skb_copy_and_csum_datagram_iovec);
+EXPORT_SYMBOL(skb_copy_and_csum_datagram_msg);
 
 /**
  * 	datagram_poll - generic datagram poll
diff --git a/net/core/dev.c b/net/core/dev.c
index 945bbd001359..aa82f9ab6a36 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -118,6 +118,7 @@
 #include <linux/if_vlan.h>
 #include <linux/ip.h>
 #include <net/ip.h>
+#include <net/mpls.h>
 #include <linux/ipv6.h>
 #include <linux/in.h>
 #include <linux/jhash.h>
@@ -133,6 +134,7 @@
 #include <linux/vmalloc.h>
 #include <linux/if_macvlan.h>
 #include <linux/errqueue.h>
+#include <linux/hrtimer.h>
 
 #include "net-sysfs.h"
 
@@ -369,9 +371,10 @@ static inline void netdev_set_addr_lockdep_class(struct net_device *dev)
 static inline struct list_head *ptype_head(const struct packet_type *pt)
 {
 	if (pt->type == htons(ETH_P_ALL))
-		return &ptype_all;
+		return pt->dev ? &pt->dev->ptype_all : &ptype_all;
 	else
-		return &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK];
+		return pt->dev ? &pt->dev->ptype_specific :
+				 &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK];
 }
 
 /**
@@ -657,6 +660,27 @@ __setup("netdev=", netdev_boot_setup);
 *******************************************************************************/
 
 /**
+ *	dev_get_iflink	- get 'iflink' value of a interface
+ *	@dev: targeted interface
+ *
+ *	Indicates the ifindex the interface is linked to.
+ *	Physical interfaces have the same 'ifindex' and 'iflink' values.
+ */
+
+int dev_get_iflink(const struct net_device *dev)
+{
+	if (dev->netdev_ops && dev->netdev_ops->ndo_get_iflink)
+		return dev->netdev_ops->ndo_get_iflink(dev);
+
+	/* If dev->rtnl_link_ops is set, it's a virtual interface. */
+	if (dev->rtnl_link_ops)
+		return 0;
+
+	return dev->ifindex;
+}
+EXPORT_SYMBOL(dev_get_iflink);
+
+/**
  *	__dev_get_by_name	- find a device by its name
  *	@net: the applicable net namespace
  *	@name: name to find
@@ -943,7 +967,7 @@ bool dev_valid_name(const char *name)
 		return false;
 
 	while (*name) {
-		if (*name == '/' || isspace(*name))
+		if (*name == '/' || *name == ':' || isspace(*name))
 			return false;
 		name++;
 	}
@@ -1382,7 +1406,7 @@ static int __dev_close(struct net_device *dev)
 	return retval;
 }
 
-static int dev_close_many(struct list_head *head)
+int dev_close_many(struct list_head *head, bool unlink)
 {
 	struct net_device *dev, *tmp;
 
@@ -1396,11 +1420,13 @@ static int dev_close_many(struct list_head *head)
 	list_for_each_entry_safe(dev, tmp, head, close_list) {
 		rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING, GFP_KERNEL);
 		call_netdevice_notifiers(NETDEV_DOWN, dev);
-		list_del_init(&dev->close_list);
+		if (unlink)
+			list_del_init(&dev->close_list);
 	}
 
 	return 0;
 }
+EXPORT_SYMBOL(dev_close_many);
 
 /**
  *	dev_close - shutdown an interface.
@@ -1417,7 +1443,7 @@ int dev_close(struct net_device *dev)
 		LIST_HEAD(single);
 
 		list_add(&dev->close_list, &single);
-		dev_close_many(&single);
+		dev_close_many(&single, true);
 		list_del(&single);
 	}
 	return 0;
@@ -1435,22 +1461,17 @@ EXPORT_SYMBOL(dev_close);
  */
 void dev_disable_lro(struct net_device *dev)
 {
-	/*
-	 * If we're trying to disable lro on a vlan device
-	 * use the underlying physical device instead
-	 */
-	if (is_vlan_dev(dev))
-		dev = vlan_dev_real_dev(dev);
-
-	/* the same for macvlan devices */
-	if (netif_is_macvlan(dev))
-		dev = macvlan_dev_real_dev(dev);
+	struct net_device *lower_dev;
+	struct list_head *iter;
 
 	dev->wanted_features &= ~NETIF_F_LRO;
 	netdev_update_features(dev);
 
 	if (unlikely(dev->features & NETIF_F_LRO))
 		netdev_WARN(dev, "failed to disable LRO!\n");
+
+	netdev_for_each_lower_dev(dev, lower_dev, iter)
+		dev_disable_lro(lower_dev);
 }
 EXPORT_SYMBOL(dev_disable_lro);
 
@@ -1609,6 +1630,22 @@ int call_netdevice_notifiers(unsigned long val, struct net_device *dev)
 }
 EXPORT_SYMBOL(call_netdevice_notifiers);
 
+#ifdef CONFIG_NET_CLS_ACT
+static struct static_key ingress_needed __read_mostly;
+
+void net_inc_ingress_queue(void)
+{
+	static_key_slow_inc(&ingress_needed);
+}
+EXPORT_SYMBOL_GPL(net_inc_ingress_queue);
+
+void net_dec_ingress_queue(void)
+{
+	static_key_slow_dec(&ingress_needed);
+}
+EXPORT_SYMBOL_GPL(net_dec_ingress_queue);
+#endif
+
 static struct static_key netstamp_needed __read_mostly;
 #ifdef HAVE_JUMP_LABEL
 /* We are not allowed to call static_key_slow_dec() from irq context
@@ -1681,22 +1718,17 @@ 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))) {
+	if (skb_orphan_frags(skb, GFP_ATOMIC) ||
+	    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->priority = 0;
 	skb->protocol = eth_type_trans(skb, dev);
+	skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
 
 	return 0;
 }
@@ -1736,6 +1768,24 @@ static inline int deliver_skb(struct sk_buff *skb,
 	return pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
 }
 
+static inline void deliver_ptype_list_skb(struct sk_buff *skb,
+					  struct packet_type **pt,
+					  struct net_device *orig_dev,
+					  __be16 type,
+					  struct list_head *ptype_list)
+{
+	struct packet_type *ptype, *pt_prev = *pt;
+
+	list_for_each_entry_rcu(ptype, ptype_list, list) {
+		if (ptype->type != type)
+			continue;
+		if (pt_prev)
+			deliver_skb(skb, pt_prev, orig_dev);
+		pt_prev = ptype;
+	}
+	*pt = pt_prev;
+}
+
 static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb)
 {
 	if (!ptype->af_packet_priv || !skb->sk)
@@ -1759,45 +1809,54 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
 	struct packet_type *ptype;
 	struct sk_buff *skb2 = NULL;
 	struct packet_type *pt_prev = NULL;
+	struct list_head *ptype_list = &ptype_all;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(ptype, &ptype_all, list) {
+again:
+	list_for_each_entry_rcu(ptype, ptype_list, list) {
 		/* Never send packets back to the socket
 		 * they originated from - MvS (miquels@drinkel.ow.org)
 		 */
-		if ((ptype->dev == dev || !ptype->dev) &&
-		    (!skb_loop_sk(ptype, skb))) {
-			if (pt_prev) {
-				deliver_skb(skb2, pt_prev, skb->dev);
-				pt_prev = ptype;
-				continue;
-			}
+		if (skb_loop_sk(ptype, skb))
+			continue;
 
-			skb2 = skb_clone(skb, GFP_ATOMIC);
-			if (!skb2)
-				break;
+		if (pt_prev) {
+			deliver_skb(skb2, pt_prev, skb->dev);
+			pt_prev = ptype;
+			continue;
+		}
 
-			net_timestamp_set(skb2);
+		/* need to clone skb, done only once */
+		skb2 = skb_clone(skb, GFP_ATOMIC);
+		if (!skb2)
+			goto out_unlock;
 
-			/* skb->nh should be correctly
-			   set by sender, so that the second statement is
-			   just protection against buggy protocols.
-			 */
-			skb_reset_mac_header(skb2);
-
-			if (skb_network_header(skb2) < skb2->data ||
-			    skb_network_header(skb2) > skb_tail_pointer(skb2)) {
-				net_crit_ratelimited("protocol %04x is buggy, dev %s\n",
-						     ntohs(skb2->protocol),
-						     dev->name);
-				skb_reset_network_header(skb2);
-			}
+		net_timestamp_set(skb2);
 
-			skb2->transport_header = skb2->network_header;
-			skb2->pkt_type = PACKET_OUTGOING;
-			pt_prev = ptype;
+		/* skb->nh should be correctly
+		 * set by sender, so that the second statement is
+		 * just protection against buggy protocols.
+		 */
+		skb_reset_mac_header(skb2);
+
+		if (skb_network_header(skb2) < skb2->data ||
+		    skb_network_header(skb2) > skb_tail_pointer(skb2)) {
+			net_crit_ratelimited("protocol %04x is buggy, dev %s\n",
+					     ntohs(skb2->protocol),
+					     dev->name);
+			skb_reset_network_header(skb2);
 		}
+
+		skb2->transport_header = skb2->network_header;
+		skb2->pkt_type = PACKET_OUTGOING;
+		pt_prev = ptype;
 	}
+
+	if (ptype_list == &ptype_all) {
+		ptype_list = &dev->ptype_all;
+		goto again;
+	}
+out_unlock:
 	if (pt_prev)
 		pt_prev->func(skb2, skb->dev, pt_prev, skb->dev);
 	rcu_read_unlock();
@@ -2354,7 +2413,6 @@ EXPORT_SYMBOL(skb_checksum_help);
 
 __be16 skb_network_protocol(struct sk_buff *skb, int *depth)
 {
-	unsigned int vlan_depth = skb->mac_len;
 	__be16 type = skb->protocol;
 
 	/* Tunnel gso handlers can set protocol to ethernet. */
@@ -2368,35 +2426,7 @@ __be16 skb_network_protocol(struct sk_buff *skb, int *depth)
 		type = eth->h_proto;
 	}
 
-	/* 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 (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;
-
-			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;
+	return __vlan_get_protocol(skb, type, depth);
 }
 
 /**
@@ -2525,12 +2555,12 @@ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
 /* If MPLS offload request, verify we are testing hardware MPLS features
  * instead of standard features for the netdev.
  */
-#ifdef CONFIG_NET_MPLS_GSO
+#if IS_ENABLED(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))
+	if (eth_p_mpls(type))
 		features &= skb->dev->mpls_features;
 
 	return features;
@@ -2563,37 +2593,49 @@ static netdev_features_t harmonize_features(struct sk_buff *skb,
 	return features;
 }
 
+netdev_features_t passthru_features_check(struct sk_buff *skb,
+					  struct net_device *dev,
+					  netdev_features_t features)
+{
+	return features;
+}
+EXPORT_SYMBOL(passthru_features_check);
+
+static netdev_features_t dflt_features_check(const struct sk_buff *skb,
+					     struct net_device *dev,
+					     netdev_features_t features)
+{
+	return vlan_features_check(skb, features);
+}
+
 netdev_features_t netif_skb_features(struct sk_buff *skb)
 {
-	const struct net_device *dev = skb->dev;
+	struct net_device *dev = skb->dev;
 	netdev_features_t features = dev->features;
 	u16 gso_segs = skb_shinfo(skb)->gso_segs;
-	__be16 protocol = skb->protocol;
 
 	if (gso_segs > dev->gso_max_segs || gso_segs < dev->gso_min_segs)
 		features &= ~NETIF_F_GSO_MASK;
 
-	if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) {
-		struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
-		protocol = veh->h_vlan_encapsulated_proto;
-	} else if (!vlan_tx_tag_present(skb)) {
-		return harmonize_features(skb, features);
-	}
-
-	features = netdev_intersect_features(features,
-					     dev->vlan_features |
-					     NETIF_F_HW_VLAN_CTAG_TX |
-					     NETIF_F_HW_VLAN_STAG_TX);
+	/* If encapsulation offload request, verify we are testing
+	 * hardware encapsulation features instead of standard
+	 * features for the netdev
+	 */
+	if (skb->encapsulation)
+		features &= dev->hw_enc_features;
 
-	if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD))
+	if (skb_vlan_tagged(skb))
 		features = netdev_intersect_features(features,
-						     NETIF_F_SG |
-						     NETIF_F_HIGHDMA |
-						     NETIF_F_FRAGLIST |
-						     NETIF_F_GEN_CSUM |
+						     dev->vlan_features |
 						     NETIF_F_HW_VLAN_CTAG_TX |
 						     NETIF_F_HW_VLAN_STAG_TX);
 
+	if (dev->netdev_ops->ndo_features_check)
+		features &= dev->netdev_ops->ndo_features_check(skb, dev,
+								features);
+	else
+		features &= dflt_features_check(skb, dev, features);
+
 	return harmonize_features(skb, features);
 }
 EXPORT_SYMBOL(netif_skb_features);
@@ -2604,7 +2646,7 @@ static int xmit_one(struct sk_buff *skb, struct net_device *dev,
 	unsigned int len;
 	int rc;
 
-	if (!list_empty(&ptype_all))
+	if (!list_empty(&ptype_all) || !list_empty(&dev->ptype_all))
 		dev_queue_xmit_nit(skb, dev);
 
 	len = skb->len;
@@ -2646,13 +2688,9 @@ out:
 static struct sk_buff *validate_xmit_vlan(struct sk_buff *skb,
 					  netdev_features_t features)
 {
-	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 (skb)
-			skb->vlan_tci = 0;
-	}
+	if (skb_vlan_tag_present(skb) &&
+	    !vlan_hw_offload_capable(features, skb->vlan_proto))
+		skb = __vlan_hwaccel_push_inside(skb);
 	return skb;
 }
 
@@ -2668,19 +2706,12 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device
 	if (unlikely(!skb))
 		goto out_null;
 
-	/* If encapsulation offload request, verify we are testing
-	 * hardware encapsulation features instead of standard
-	 * features for the netdev
-	 */
-	if (skb->encapsulation)
-		features &= dev->hw_enc_features;
-
-	if (netif_needs_gso(dev, skb, features)) {
+	if (netif_needs_gso(skb, features)) {
 		struct sk_buff *segs;
 
 		segs = skb_gso_segment(skb, features);
 		if (IS_ERR(segs)) {
-			segs = NULL;
+			goto out_kfree_skb;
 		} else if (segs) {
 			consume_skb(skb);
 			skb = segs;
@@ -2848,14 +2879,16 @@ static void skb_update_prio(struct sk_buff *skb)
 #define skb_update_prio(skb)
 #endif
 
-static DEFINE_PER_CPU(int, xmit_recursion);
+DEFINE_PER_CPU(int, xmit_recursion);
+EXPORT_SYMBOL(xmit_recursion);
+
 #define RECURSION_LIMIT 10
 
 /**
  *	dev_loopback_xmit - loop back @skb
  *	@skb: buffer to transmit
  */
-int dev_loopback_xmit(struct sk_buff *skb)
+int dev_loopback_xmit(struct sock *sk, struct sk_buff *skb)
 {
 	skb_reset_mac_header(skb);
 	__skb_pull(skb, skb_network_offset(skb));
@@ -2993,11 +3026,11 @@ out:
 	return rc;
 }
 
-int dev_queue_xmit(struct sk_buff *skb)
+int dev_queue_xmit_sk(struct sock *sk, struct sk_buff *skb)
 {
 	return __dev_queue_xmit(skb, NULL);
 }
-EXPORT_SYMBOL(dev_queue_xmit);
+EXPORT_SYMBOL(dev_queue_xmit_sk);
 
 int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv)
 {
@@ -3030,6 +3063,8 @@ static inline void ____napi_schedule(struct softnet_data *sd,
 /* One global table that all flow-based protocols share. */
 struct rps_sock_flow_table __rcu *rps_sock_flow_table __read_mostly;
 EXPORT_SYMBOL(rps_sock_flow_table);
+u32 rps_cpu_mask __read_mostly;
+EXPORT_SYMBOL(rps_cpu_mask);
 
 struct static_key rps_needed __read_mostly;
 
@@ -3037,7 +3072,7 @@ static struct rps_dev_flow *
 set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 	    struct rps_dev_flow *rflow, u16 next_cpu)
 {
-	if (next_cpu != RPS_NO_CPU) {
+	if (next_cpu < nr_cpu_ids) {
 #ifdef CONFIG_RFS_ACCEL
 		struct netdev_rx_queue *rxqueue;
 		struct rps_dev_flow_table *flow_table;
@@ -3086,16 +3121,17 @@ set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		       struct rps_dev_flow **rflowp)
 {
-	struct netdev_rx_queue *rxqueue;
-	struct rps_map *map;
+	const struct rps_sock_flow_table *sock_flow_table;
+	struct netdev_rx_queue *rxqueue = dev->_rx;
 	struct rps_dev_flow_table *flow_table;
-	struct rps_sock_flow_table *sock_flow_table;
+	struct rps_map *map;
 	int cpu = -1;
-	u16 tcpu;
+	u32 tcpu;
 	u32 hash;
 
 	if (skb_rx_queue_recorded(skb)) {
 		u16 index = skb_get_rx_queue(skb);
+
 		if (unlikely(index >= dev->real_num_rx_queues)) {
 			WARN_ONCE(dev->real_num_rx_queues > 1,
 				  "%s received packet on queue %u, but number "
@@ -3103,44 +3139,45 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 				  dev->name, index, dev->real_num_rx_queues);
 			goto done;
 		}
-		rxqueue = dev->_rx + index;
-	} else
-		rxqueue = dev->_rx;
+		rxqueue += index;
+	}
 
+	/* Avoid computing hash if RFS/RPS is not active for this rxqueue */
+
+	flow_table = rcu_dereference(rxqueue->rps_flow_table);
 	map = rcu_dereference(rxqueue->rps_map);
-	if (map) {
-		if (map->len == 1 &&
-		    !rcu_access_pointer(rxqueue->rps_flow_table)) {
-			tcpu = map->cpus[0];
-			if (cpu_online(tcpu))
-				cpu = tcpu;
-			goto done;
-		}
-	} else if (!rcu_access_pointer(rxqueue->rps_flow_table)) {
+	if (!flow_table && !map)
 		goto done;
-	}
 
 	skb_reset_network_header(skb);
 	hash = skb_get_hash(skb);
 	if (!hash)
 		goto done;
 
-	flow_table = rcu_dereference(rxqueue->rps_flow_table);
 	sock_flow_table = rcu_dereference(rps_sock_flow_table);
 	if (flow_table && sock_flow_table) {
-		u16 next_cpu;
 		struct rps_dev_flow *rflow;
+		u32 next_cpu;
+		u32 ident;
+
+		/* First check into global flow table if there is a match */
+		ident = sock_flow_table->ents[hash & sock_flow_table->mask];
+		if ((ident ^ hash) & ~rps_cpu_mask)
+			goto try_rps;
+
+		next_cpu = ident & rps_cpu_mask;
 
+		/* OK, now we know there is a match,
+		 * we can look at the local (per receive queue) flow table
+		 */
 		rflow = &flow_table->flows[hash & flow_table->mask];
 		tcpu = rflow->cpu;
 
-		next_cpu = sock_flow_table->ents[hash & sock_flow_table->mask];
-
 		/*
 		 * If the desired CPU (where last recvmsg was done) is
 		 * different from current CPU (one in the rx-queue flow
 		 * table entry), switch if one of the following holds:
-		 *   - Current CPU is unset (equal to RPS_NO_CPU).
+		 *   - Current CPU is unset (>= nr_cpu_ids).
 		 *   - Current CPU is offline.
 		 *   - The current CPU's queue tail has advanced beyond the
 		 *     last packet that was enqueued using this table entry.
@@ -3148,20 +3185,22 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		 *     have been dequeued, thus preserving in order delivery.
 		 */
 		if (unlikely(tcpu != next_cpu) &&
-		    (tcpu == RPS_NO_CPU || !cpu_online(tcpu) ||
+		    (tcpu >= nr_cpu_ids || !cpu_online(tcpu) ||
 		     ((int)(per_cpu(softnet_data, tcpu).input_queue_head -
 		      rflow->last_qtail)) >= 0)) {
 			tcpu = next_cpu;
 			rflow = set_rps_cpu(dev, skb, rflow, next_cpu);
 		}
 
-		if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) {
+		if (tcpu < nr_cpu_ids && cpu_online(tcpu)) {
 			*rflowp = rflow;
 			cpu = tcpu;
 			goto done;
 		}
 	}
 
+try_rps:
+
 	if (map) {
 		tcpu = map->cpus[reciprocal_scale(hash, map->len)];
 		if (cpu_online(tcpu)) {
@@ -3194,14 +3233,14 @@ bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index,
 	struct rps_dev_flow_table *flow_table;
 	struct rps_dev_flow *rflow;
 	bool expire = true;
-	int cpu;
+	unsigned int cpu;
 
 	rcu_read_lock();
 	flow_table = rcu_dereference(rxqueue->rps_flow_table);
 	if (flow_table && flow_id <= flow_table->mask) {
 		rflow = &flow_table->flows[flow_id];
 		cpu = ACCESS_ONCE(rflow->cpu);
-		if (rflow->filter == filter_id && cpu != RPS_NO_CPU &&
+		if (rflow->filter == filter_id && cpu < nr_cpu_ids &&
 		    ((int)(per_cpu(softnet_data, cpu).input_queue_head -
 			   rflow->last_qtail) <
 		     (int)(10 * flow_table->mask)))
@@ -3304,7 +3343,7 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
 	rps_lock(sd);
 	qlen = skb_queue_len(&sd->input_pkt_queue);
 	if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) {
-		if (skb_queue_len(&sd->input_pkt_queue)) {
+		if (qlen) {
 enqueue:
 			__skb_queue_tail(&sd->input_pkt_queue, skb);
 			input_queue_tail_incr_save(sd, qtail);
@@ -3517,7 +3556,7 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb,
 	struct netdev_queue *rxq = rcu_dereference(skb->dev->ingress_queue);
 
 	if (!rxq || rcu_access_pointer(rxq->qdisc) == &noop_qdisc)
-		goto out;
+		return skb;
 
 	if (*pt_prev) {
 		*ret = deliver_skb(skb, *pt_prev, orig_dev);
@@ -3531,8 +3570,6 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb,
 		return NULL;
 	}
 
-out:
-	skb->tc_verd = 0;
 	return skb;
 }
 #endif
@@ -3613,7 +3650,6 @@ static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc)
 	struct packet_type *ptype, *pt_prev;
 	rx_handler_func_t *rx_handler;
 	struct net_device *orig_dev;
-	struct net_device *null_or_dev;
 	bool deliver_exact = false;
 	int ret = NET_RX_DROP;
 	__be16 type;
@@ -3656,25 +3692,32 @@ another_round:
 		goto skip_taps;
 
 	list_for_each_entry_rcu(ptype, &ptype_all, list) {
-		if (!ptype->dev || ptype->dev == skb->dev) {
-			if (pt_prev)
-				ret = deliver_skb(skb, pt_prev, orig_dev);
-			pt_prev = ptype;
-		}
+		if (pt_prev)
+			ret = deliver_skb(skb, pt_prev, orig_dev);
+		pt_prev = ptype;
+	}
+
+	list_for_each_entry_rcu(ptype, &skb->dev->ptype_all, list) {
+		if (pt_prev)
+			ret = deliver_skb(skb, pt_prev, orig_dev);
+		pt_prev = ptype;
 	}
 
 skip_taps:
 #ifdef CONFIG_NET_CLS_ACT
-	skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
-	if (!skb)
-		goto unlock;
+	if (static_key_false(&ingress_needed)) {
+		skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
+		if (!skb)
+			goto unlock;
+	}
+
+	skb->tc_verd = 0;
 ncls:
 #endif
-
 	if (pfmemalloc && !skb_pfmemalloc_protocol(skb))
 		goto drop;
 
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		if (pt_prev) {
 			ret = deliver_skb(skb, pt_prev, orig_dev);
 			pt_prev = NULL;
@@ -3706,8 +3749,8 @@ ncls:
 		}
 	}
 
-	if (unlikely(vlan_tx_tag_present(skb))) {
-		if (vlan_tx_tag_get_id(skb))
+	if (unlikely(skb_vlan_tag_present(skb))) {
+		if (skb_vlan_tag_get_id(skb))
 			skb->pkt_type = PACKET_OTHERHOST;
 		/* Note: we might in the future use prio bits
 		 * and set skb->priority like in vlan_do_receive()
@@ -3716,19 +3759,21 @@ ncls:
 		skb->vlan_tci = 0;
 	}
 
+	type = skb->protocol;
+
 	/* deliver only exact match when indicated */
-	null_or_dev = deliver_exact ? skb->dev : NULL;
+	if (likely(!deliver_exact)) {
+		deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type,
+				       &ptype_base[ntohs(type) &
+						   PTYPE_HASH_MASK]);
+	}
 
-	type = skb->protocol;
-	list_for_each_entry_rcu(ptype,
-			&ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) {
-		if (ptype->type == type &&
-		    (ptype->dev == null_or_dev || ptype->dev == skb->dev ||
-		     ptype->dev == orig_dev)) {
-			if (pt_prev)
-				ret = deliver_skb(skb, pt_prev, orig_dev);
-			pt_prev = ptype;
-		}
+	deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type,
+			       &orig_dev->ptype_specific);
+
+	if (unlikely(skb->dev != orig_dev)) {
+		deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type,
+				       &skb->dev->ptype_specific);
 	}
 
 	if (pt_prev) {
@@ -3818,13 +3863,13 @@ static int netif_receive_skb_internal(struct sk_buff *skb)
  *	NET_RX_SUCCESS: no congestion
  *	NET_RX_DROP: packet was dropped
  */
-int netif_receive_skb(struct sk_buff *skb)
+int netif_receive_skb_sk(struct sock *sk, struct sk_buff *skb)
 {
 	trace_netif_receive_skb_entry(skb);
 
 	return netif_receive_skb_internal(skb);
 }
-EXPORT_SYMBOL(netif_receive_skb);
+EXPORT_SYMBOL(netif_receive_skb_sk);
 
 /* Network device is going away, flush any packets still pending
  * Called with irqs disabled.
@@ -4013,6 +4058,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 		NAPI_GRO_CB(skb)->flush = 0;
 		NAPI_GRO_CB(skb)->free = 0;
 		NAPI_GRO_CB(skb)->udp_mark = 0;
+		NAPI_GRO_CB(skb)->gro_remcsum_start = 0;
 
 		/* Setup for GRO checksum validation */
 		switch (skb->ip_summed) {
@@ -4179,7 +4225,7 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi)
 	struct sk_buff *skb = napi->skb;
 
 	if (!skb) {
-		skb = netdev_alloc_skb_ip_align(napi->dev, GRO_MAX_HEAD);
+		skb = napi_alloc_skb(napi, GRO_MAX_HEAD);
 		napi->skb = skb;
 	}
 	return skb;
@@ -4316,20 +4362,28 @@ static void net_rps_action_and_irq_enable(struct softnet_data *sd)
 		local_irq_enable();
 }
 
+static bool sd_has_rps_ipi_waiting(struct softnet_data *sd)
+{
+#ifdef CONFIG_RPS
+	return sd->rps_ipi_list != NULL;
+#else
+	return false;
+#endif
+}
+
 static int process_backlog(struct napi_struct *napi, int quota)
 {
 	int work = 0;
 	struct softnet_data *sd = container_of(napi, struct softnet_data, backlog);
 
-#ifdef CONFIG_RPS
 	/* Check if we have pending ipi, its better to send them now,
 	 * not waiting net_rx_action() end.
 	 */
-	if (sd->rps_ipi_list) {
+	if (sd_has_rps_ipi_waiting(sd)) {
 		local_irq_disable();
 		net_rps_action_and_irq_enable(sd);
 	}
-#endif
+
 	napi->weight = weight_p;
 	local_irq_disable();
 	while (1) {
@@ -4356,7 +4410,6 @@ static int process_backlog(struct napi_struct *napi, int quota)
 			 * 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);
 
@@ -4376,7 +4429,8 @@ static int process_backlog(struct napi_struct *napi, int quota)
  * __napi_schedule - schedule for receive
  * @n: entry to schedule
  *
- * The entry's receive function will be scheduled to run
+ * The entry's receive function will be scheduled to run.
+ * Consider using __napi_schedule_irqoff() if hard irqs are masked.
  */
 void __napi_schedule(struct napi_struct *n)
 {
@@ -4388,18 +4442,29 @@ void __napi_schedule(struct napi_struct *n)
 }
 EXPORT_SYMBOL(__napi_schedule);
 
+/**
+ * __napi_schedule_irqoff - schedule for receive
+ * @n: entry to schedule
+ *
+ * Variant of __napi_schedule() assuming hard irqs are masked
+ */
+void __napi_schedule_irqoff(struct napi_struct *n)
+{
+	____napi_schedule(this_cpu_ptr(&softnet_data), n);
+}
+EXPORT_SYMBOL(__napi_schedule_irqoff);
+
 void __napi_complete(struct napi_struct *n)
 {
 	BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state));
-	BUG_ON(n->gro_list);
 
-	list_del(&n->poll_list);
+	list_del_init(&n->poll_list);
 	smp_mb__before_atomic();
 	clear_bit(NAPI_STATE_SCHED, &n->state);
 }
 EXPORT_SYMBOL(__napi_complete);
 
-void napi_complete(struct napi_struct *n)
+void napi_complete_done(struct napi_struct *n, int work_done)
 {
 	unsigned long flags;
 
@@ -4410,12 +4475,28 @@ void napi_complete(struct napi_struct *n)
 	if (unlikely(test_bit(NAPI_STATE_NPSVC, &n->state)))
 		return;
 
-	napi_gro_flush(n, false);
-	local_irq_save(flags);
-	__napi_complete(n);
-	local_irq_restore(flags);
+	if (n->gro_list) {
+		unsigned long timeout = 0;
+
+		if (work_done)
+			timeout = n->dev->gro_flush_timeout;
+
+		if (timeout)
+			hrtimer_start(&n->timer, ns_to_ktime(timeout),
+				      HRTIMER_MODE_REL_PINNED);
+		else
+			napi_gro_flush(n, false);
+	}
+	if (likely(list_empty(&n->poll_list))) {
+		WARN_ON_ONCE(!test_and_clear_bit(NAPI_STATE_SCHED, &n->state));
+	} else {
+		/* If n->poll_list is not empty, we need to mask irqs */
+		local_irq_save(flags);
+		__napi_complete(n);
+		local_irq_restore(flags);
+	}
 }
-EXPORT_SYMBOL(napi_complete);
+EXPORT_SYMBOL(napi_complete_done);
 
 /* must be called under rcu_read_lock(), as we dont take a reference */
 struct napi_struct *napi_by_id(unsigned int napi_id)
@@ -4469,10 +4550,23 @@ void napi_hash_del(struct napi_struct *napi)
 }
 EXPORT_SYMBOL_GPL(napi_hash_del);
 
+static enum hrtimer_restart napi_watchdog(struct hrtimer *timer)
+{
+	struct napi_struct *napi;
+
+	napi = container_of(timer, struct napi_struct, timer);
+	if (napi->gro_list)
+		napi_schedule(napi);
+
+	return HRTIMER_NORESTART;
+}
+
 void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
 		    int (*poll)(struct napi_struct *, int), int weight)
 {
 	INIT_LIST_HEAD(&napi->poll_list);
+	hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
+	napi->timer.function = napi_watchdog;
 	napi->gro_count = 0;
 	napi->gro_list = NULL;
 	napi->skb = NULL;
@@ -4491,6 +4585,20 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
 }
 EXPORT_SYMBOL(netif_napi_add);
 
+void napi_disable(struct napi_struct *n)
+{
+	might_sleep();
+	set_bit(NAPI_STATE_DISABLE, &n->state);
+
+	while (test_and_set_bit(NAPI_STATE_SCHED, &n->state))
+		msleep(1);
+
+	hrtimer_cancel(&n->timer);
+
+	clear_bit(NAPI_STATE_DISABLE, &n->state);
+}
+EXPORT_SYMBOL(napi_disable);
+
 void netif_napi_del(struct napi_struct *napi)
 {
 	list_del_init(&napi->dev_list);
@@ -4502,91 +4610,112 @@ void netif_napi_del(struct napi_struct *napi)
 }
 EXPORT_SYMBOL(netif_napi_del);
 
-static void net_rx_action(struct softirq_action *h)
+static int napi_poll(struct napi_struct *n, struct list_head *repoll)
 {
-	struct softnet_data *sd = this_cpu_ptr(&softnet_data);
-	unsigned long time_limit = jiffies + 2;
-	int budget = netdev_budget;
 	void *have;
+	int work, weight;
 
-	local_irq_disable();
+	list_del_init(&n->poll_list);
 
-	while (!list_empty(&sd->poll_list)) {
-		struct napi_struct *n;
-		int work, weight;
+	have = netpoll_poll_lock(n);
 
-		/* If softirq window is exhuasted then punt.
-		 * Allow this to run for 2 jiffies since which will allow
-		 * an average latency of 1.5/HZ.
-		 */
-		if (unlikely(budget <= 0 || time_after_eq(jiffies, time_limit)))
-			goto softnet_break;
+	weight = n->weight;
 
-		local_irq_enable();
+	/* This NAPI_STATE_SCHED test is for avoiding a race
+	 * with netpoll's poll_napi().  Only the entity which
+	 * obtains the lock and sees NAPI_STATE_SCHED set will
+	 * actually make the ->poll() call.  Therefore we avoid
+	 * accidentally calling ->poll() when NAPI is not scheduled.
+	 */
+	work = 0;
+	if (test_bit(NAPI_STATE_SCHED, &n->state)) {
+		work = n->poll(n, weight);
+		trace_napi_poll(n);
+	}
 
-		/* Even though interrupts have been re-enabled, this
-		 * access is safe because interrupts can only add new
-		 * entries to the tail of this list, and only ->poll()
-		 * calls can remove this head entry from the list.
-		 */
-		n = list_first_entry(&sd->poll_list, struct napi_struct, poll_list);
+	WARN_ON_ONCE(work > weight);
 
-		have = netpoll_poll_lock(n);
+	if (likely(work < weight))
+		goto out_unlock;
 
-		weight = n->weight;
+	/* Drivers must not modify the NAPI state if they
+	 * consume the entire weight.  In such cases this code
+	 * still "owns" the NAPI instance and therefore can
+	 * move the instance around on the list at-will.
+	 */
+	if (unlikely(napi_disable_pending(n))) {
+		napi_complete(n);
+		goto out_unlock;
+	}
 
-		/* This NAPI_STATE_SCHED test is for avoiding a race
-		 * with netpoll's poll_napi().  Only the entity which
-		 * obtains the lock and sees NAPI_STATE_SCHED set will
-		 * actually make the ->poll() call.  Therefore we avoid
-		 * accidentally calling ->poll() when NAPI is not scheduled.
+	if (n->gro_list) {
+		/* flush too old packets
+		 * If HZ < 1000, flush all packets.
 		 */
-		work = 0;
-		if (test_bit(NAPI_STATE_SCHED, &n->state)) {
-			work = n->poll(n, weight);
-			trace_napi_poll(n);
-		}
+		napi_gro_flush(n, HZ >= 1000);
+	}
 
-		WARN_ON_ONCE(work > weight);
+	/* Some drivers may have called napi_schedule
+	 * prior to exhausting their budget.
+	 */
+	if (unlikely(!list_empty(&n->poll_list))) {
+		pr_warn_once("%s: Budget exhausted after napi rescheduled\n",
+			     n->dev ? n->dev->name : "backlog");
+		goto out_unlock;
+	}
 
-		budget -= work;
+	list_add_tail(&n->poll_list, repoll);
 
-		local_irq_disable();
+out_unlock:
+	netpoll_poll_unlock(have);
 
-		/* Drivers must not modify the NAPI state if they
-		 * consume the entire weight.  In such cases this code
-		 * still "owns" the NAPI instance and therefore can
-		 * move the instance around on the list at-will.
-		 */
-		if (unlikely(work == weight)) {
-			if (unlikely(napi_disable_pending(n))) {
-				local_irq_enable();
-				napi_complete(n);
-				local_irq_disable();
-			} else {
-				if (n->gro_list) {
-					/* flush too old packets
-					 * If HZ < 1000, flush all packets.
-					 */
-					local_irq_enable();
-					napi_gro_flush(n, HZ >= 1000);
-					local_irq_disable();
-				}
-				list_move_tail(&n->poll_list, &sd->poll_list);
-			}
+	return work;
+}
+
+static void net_rx_action(struct softirq_action *h)
+{
+	struct softnet_data *sd = this_cpu_ptr(&softnet_data);
+	unsigned long time_limit = jiffies + 2;
+	int budget = netdev_budget;
+	LIST_HEAD(list);
+	LIST_HEAD(repoll);
+
+	local_irq_disable();
+	list_splice_init(&sd->poll_list, &list);
+	local_irq_enable();
+
+	for (;;) {
+		struct napi_struct *n;
+
+		if (list_empty(&list)) {
+			if (!sd_has_rps_ipi_waiting(sd) && list_empty(&repoll))
+				return;
+			break;
 		}
 
-		netpoll_poll_unlock(have);
+		n = list_first_entry(&list, struct napi_struct, poll_list);
+		budget -= napi_poll(n, &repoll);
+
+		/* If softirq window is exhausted then punt.
+		 * Allow this to run for 2 jiffies since which will allow
+		 * an average latency of 1.5/HZ.
+		 */
+		if (unlikely(budget <= 0 ||
+			     time_after_eq(jiffies, time_limit))) {
+			sd->time_squeeze++;
+			break;
+		}
 	}
-out:
-	net_rps_action_and_irq_enable(sd);
 
-	return;
+	local_irq_disable();
 
-softnet_break:
-	sd->time_squeeze++;
-	__raise_softirq_irqoff(NET_RX_SOFTIRQ);
-	goto out;
+	list_splice_tail_init(&sd->poll_list, &list);
+	list_splice_tail(&repoll, &list);
+	list_splice(&list, &sd->poll_list);
+	if (!list_empty(&sd->poll_list))
+		__raise_softirq_irqoff(NET_RX_SOFTIRQ);
+
+	net_rps_action_and_irq_enable(sd);
 }
 
 struct netdev_adjacent {
@@ -5073,7 +5202,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 	if (__netdev_find_adj(upper_dev, dev, &upper_dev->all_adj_list.upper))
 		return -EBUSY;
 
-	if (__netdev_find_adj(dev, upper_dev, &dev->all_adj_list.upper))
+	if (__netdev_find_adj(dev, upper_dev, &dev->adj_list.upper))
 		return -EEXIST;
 
 	if (master && netdev_master_upper_dev_get(dev))
@@ -5238,7 +5367,27 @@ void netdev_upper_dev_unlink(struct net_device *dev,
 }
 EXPORT_SYMBOL(netdev_upper_dev_unlink);
 
-void netdev_adjacent_add_links(struct net_device *dev)
+/**
+ * netdev_bonding_info_change - Dispatch event about slave change
+ * @dev: device
+ * @bonding_info: info to dispatch
+ *
+ * Send NETDEV_BONDING_INFO to netdev notifiers with info.
+ * The caller must hold the RTNL lock.
+ */
+void netdev_bonding_info_change(struct net_device *dev,
+				struct netdev_bonding_info *bonding_info)
+{
+	struct netdev_notifier_bonding_info	info;
+
+	memcpy(&info.bonding_info, bonding_info,
+	       sizeof(struct netdev_bonding_info));
+	call_netdevice_notifiers_info(NETDEV_BONDING_INFO, dev,
+				      &info.info);
+}
+EXPORT_SYMBOL(netdev_bonding_info_change);
+
+static void netdev_adjacent_add_links(struct net_device *dev)
 {
 	struct netdev_adjacent *iter;
 
@@ -5263,7 +5412,7 @@ void netdev_adjacent_add_links(struct net_device *dev)
 	}
 }
 
-void netdev_adjacent_del_links(struct net_device *dev)
+static void netdev_adjacent_del_links(struct net_device *dev)
 {
 	struct netdev_adjacent *iter;
 
@@ -5786,7 +5935,7 @@ EXPORT_SYMBOL(dev_change_carrier);
  *	Get device physical port ID
  */
 int dev_get_phys_port_id(struct net_device *dev,
-			 struct netdev_phys_port_id *ppid)
+			 struct netdev_phys_item_id *ppid)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 
@@ -5797,6 +5946,24 @@ int dev_get_phys_port_id(struct net_device *dev,
 EXPORT_SYMBOL(dev_get_phys_port_id);
 
 /**
+ *	dev_get_phys_port_name - Get device physical port name
+ *	@dev: device
+ *	@name: port name
+ *
+ *	Get device physical port name
+ */
+int dev_get_phys_port_name(struct net_device *dev,
+			   char *name, size_t len)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+
+	if (!ops->ndo_get_phys_port_name)
+		return -EOPNOTSUPP;
+	return ops->ndo_get_phys_port_name(dev, name, len);
+}
+EXPORT_SYMBOL(dev_get_phys_port_name);
+
+/**
  *	dev_new_index	-	allocate an ifindex
  *	@net: the applicable net namespace
  *
@@ -5853,7 +6020,7 @@ static void rollback_registered_many(struct list_head *head)
 	/* If device is running, close it first. */
 	list_for_each_entry(dev, head, unreg_list)
 		list_add_tail(&dev->close_list, &close_head);
-	dev_close_many(&close_head);
+	dev_close_many(&close_head, true);
 
 	list_for_each_entry(dev, head, unreg_list) {
 		/* And unlink it from device chain. */
@@ -5865,6 +6032,8 @@ static void rollback_registered_many(struct list_head *head)
 	synchronize_net();
 
 	list_for_each_entry(dev, head, unreg_list) {
+		struct sk_buff *skb = NULL;
+
 		/* Shutdown queueing discipline. */
 		dev_shutdown(dev);
 
@@ -5874,6 +6043,11 @@ 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)
+			skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U,
+						     GFP_KERNEL);
+
 		/*
 		 *	Flush the unicast and multicast chains
 		 */
@@ -5883,9 +6057,8 @@ 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);
+		if (skb)
+			rtmsg_ifinfo_send(skb, dev, GFP_KERNEL);
 
 		/* Notifier chain MUST detach us all upper devices. */
 		WARN_ON(netdev_has_any_upper_dev(dev));
@@ -6081,13 +6254,16 @@ static int netif_alloc_rx_queues(struct net_device *dev)
 {
 	unsigned int i, count = dev->num_rx_queues;
 	struct netdev_rx_queue *rx;
+	size_t sz = count * sizeof(*rx);
 
 	BUG_ON(count < 1);
 
-	rx = kcalloc(count, sizeof(struct netdev_rx_queue), GFP_KERNEL);
-	if (!rx)
-		return -ENOMEM;
-
+	rx = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
+	if (!rx) {
+		rx = vzalloc(sz);
+		if (!rx)
+			return -ENOMEM;
+	}
 	dev->_rx = rx;
 
 	for (i = 0; i < count; i++)
@@ -6171,8 +6347,6 @@ int register_netdevice(struct net_device *dev)
 	spin_lock_init(&dev->addr_list_lock);
 	netdev_set_addr_lockdep_class(dev);
 
-	dev->iflink = -1;
-
 	ret = dev_get_valid_name(net, dev, dev->name);
 	if (ret < 0)
 		goto out;
@@ -6202,9 +6376,6 @@ int register_netdevice(struct net_device *dev)
 	else if (__dev_get_by_index(net, dev->ifindex))
 		goto err_uninit;
 
-	if (dev->iflink == -1)
-		dev->iflink = dev->ifindex;
-
 	/* Transfer changeable features to wanted_features and enable
 	 * software offloads (GSO and GRO).
 	 */
@@ -6485,6 +6656,8 @@ void netdev_run_todo(void)
 
 		/* paranoia */
 		BUG_ON(netdev_refcnt_read(dev));
+		BUG_ON(!list_empty(&dev->ptype_all));
+		BUG_ON(!list_empty(&dev->ptype_specific));
 		WARN_ON(rcu_access_pointer(dev->ip_ptr));
 		WARN_ON(rcu_access_pointer(dev->ip6_ptr));
 		WARN_ON(dev->dn_ptr);
@@ -6565,7 +6738,7 @@ struct netdev_queue *dev_ingress_queue_create(struct net_device *dev)
 	if (!queue)
 		return NULL;
 	netdev_init_one_queue(dev, queue, NULL);
-	queue->qdisc = &noop_qdisc;
+	RCU_INIT_POINTER(queue->qdisc, &noop_qdisc);
 	queue->qdisc_sleeping = &noop_qdisc;
 	rcu_assign_pointer(dev->ingress_queue, queue);
 #endif
@@ -6667,6 +6840,8 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	INIT_LIST_HEAD(&dev->adj_list.lower);
 	INIT_LIST_HEAD(&dev->all_adj_list.upper);
 	INIT_LIST_HEAD(&dev->all_adj_list.lower);
+	INIT_LIST_HEAD(&dev->ptype_all);
+	INIT_LIST_HEAD(&dev->ptype_specific);
 	dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM;
 	setup(dev);
 
@@ -6713,11 +6888,9 @@ void free_netdev(struct net_device *dev)
 {
 	struct napi_struct *p, *n;
 
-	release_net(dev_net(dev));
-
 	netif_free_tx_queues(dev);
 #ifdef CONFIG_SYSFS
-	kfree(dev->_rx);
+	kvfree(dev->_rx);
 #endif
 
 	kfree(rcu_dereference_protected(dev->ingress_queue, 1));
@@ -6915,12 +7088,8 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
 	dev_net_set(dev, net);
 
 	/* If there is an ifindex conflict assign a new one */
-	if (__dev_get_by_index(net, dev->ifindex)) {
-		int iflink = (dev->iflink == dev->ifindex);
+	if (__dev_get_by_index(net, dev->ifindex))
 		dev->ifindex = dev_new_index(net);
-		if (iflink)
-			dev->iflink = dev->ifindex;
-	}
 
 	/* Send a netdev-add uevent to the new namespace */
 	kobject_uevent(&dev->dev.kobj, KOBJ_ADD);
@@ -6981,10 +7150,20 @@ static int dev_cpu_callback(struct notifier_block *nfb,
 		oldsd->output_queue = NULL;
 		oldsd->output_queue_tailp = &oldsd->output_queue;
 	}
-	/* Append NAPI poll list from offline CPU. */
-	if (!list_empty(&oldsd->poll_list)) {
-		list_splice_init(&oldsd->poll_list, &sd->poll_list);
-		raise_softirq_irqoff(NET_RX_SOFTIRQ);
+	/* Append NAPI poll list from offline CPU, with one exception :
+	 * process_backlog() must be called by cpu owning percpu backlog.
+	 * We properly handle process_queue & input_pkt_queue later.
+	 */
+	while (!list_empty(&oldsd->poll_list)) {
+		struct napi_struct *napi = list_first_entry(&oldsd->poll_list,
+							    struct napi_struct,
+							    poll_list);
+
+		list_del_init(&napi->poll_list);
+		if (napi->poll == process_backlog)
+			napi->state = 0;
+		else
+			____napi_schedule(sd, napi);
 	}
 
 	raise_softirq_irqoff(NET_TX_SOFTIRQ);
@@ -6992,11 +7171,11 @@ 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_internal(skb);
+		netif_rx_ni(skb);
 		input_queue_head_incr(oldsd);
 	}
-	while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) {
-		netif_rx_internal(skb);
+	while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) {
+		netif_rx_ni(skb);
 		input_queue_head_incr(oldsd);
 	}
 
@@ -7200,11 +7379,10 @@ static void __net_exit rtnl_lock_unregistering(struct list_head *net_list)
 	 */
 	struct net *net;
 	bool unregistering;
-	DEFINE_WAIT(wait);
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
+	add_wait_queue(&netdev_unregistering_wq, &wait);
 	for (;;) {
-		prepare_to_wait(&netdev_unregistering_wq, &wait,
-				TASK_UNINTERRUPTIBLE);
 		unregistering = false;
 		rtnl_lock();
 		list_for_each_entry(net, net_list, exit_list) {
@@ -7216,9 +7394,10 @@ static void __net_exit rtnl_lock_unregistering(struct list_head *net_list)
 		if (!unregistering)
 			break;
 		__rtnl_unlock();
-		schedule();
+
+		wait_woken(&wait, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
 	}
-	finish_wait(&netdev_unregistering_wq, &wait);
+	remove_wait_queue(&netdev_unregistering_wq, &wait);
 }
 
 static void __net_exit default_device_exit_batch(struct list_head *net_list)
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index b6b230600b97..c0548d268e1a 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -278,8 +278,8 @@ int __hw_addr_sync_dev(struct netdev_hw_addr_list *list,
 EXPORT_SYMBOL(__hw_addr_sync_dev);
 
 /**
- *  __hw_addr_unsync_dev - Remove synchonized addresses from device
- *  @list: address list to remove syncronized addresses from
+ *  __hw_addr_unsync_dev - Remove synchronized addresses from device
+ *  @list: address list to remove synchronized addresses from
  *  @dev:  device to sync
  *  @unsync: function to call if address should be removed
  *
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 72e899a3efda..b94b1d293506 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -142,10 +142,12 @@ static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cm
 
 	case SIOCGIFHWADDR:
 		if (!dev->addr_len)
-			memset(ifr->ifr_hwaddr.sa_data, 0, sizeof ifr->ifr_hwaddr.sa_data);
+			memset(ifr->ifr_hwaddr.sa_data, 0,
+			       sizeof(ifr->ifr_hwaddr.sa_data));
 		else
 			memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr,
-			       min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len));
+			       min(sizeof(ifr->ifr_hwaddr.sa_data),
+				   (size_t)dev->addr_len));
 		ifr->ifr_hwaddr.sa_family = dev->type;
 		return 0;
 
@@ -265,7 +267,8 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
 		if (ifr->ifr_hwaddr.sa_family != dev->type)
 			return -EINVAL;
 		memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data,
-		       min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len));
+		       min(sizeof(ifr->ifr_hwaddr.sa_data),
+			   (size_t)dev->addr_len));
 		call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
 		return 0;
 
diff --git a/net/core/dst.c b/net/core/dst.c
index a028409ee438..e956ce6d1378 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -327,30 +327,6 @@ void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old)
 }
 EXPORT_SYMBOL(__dst_destroy_metrics_generic);
 
-/**
- * __skb_dst_set_noref - sets skb dst, without a reference
- * @skb: buffer
- * @dst: dst entry
- * @force: if force is set, use noref version even for DST_NOCACHE entries
- *
- * Sets skb dst, assuming a reference was not taken on dst
- * skb_dst_drop() should not dst_release() this dst
- */
-void __skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst, bool force)
-{
-	WARN_ON(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
-	/* If dst not in cache, we must take a reference, because
-	 * dst_release() will destroy dst as soon as its refcount becomes zero
-	 */
-	if (unlikely((dst->flags & DST_NOCACHE) && !force)) {
-		dst_hold(dst);
-		skb_dst_set(skb, dst);
-	} else {
-		skb->_skb_refdst = (unsigned long)dst | SKB_DST_NOREF;
-	}
-}
-EXPORT_SYMBOL(__skb_dst_set_noref);
-
 /* Dirty hack. We did it in 2.2 (in __dst_free),
  * we have _very_ good reasons not to repeat
  * this mistake in 2.3, but we have no choice
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 06dfb293e5aa..1d00b8922902 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -25,6 +25,7 @@
 #include <linux/slab.h>
 #include <linux/rtnetlink.h>
 #include <linux/sched.h>
+#include <linux/net.h>
 
 /*
  * Some useful ethtool_ops methods that're device independent.
@@ -84,7 +85,6 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
 	[NETIF_F_GSO_IPIP_BIT] =	 "tx-ipip-segmentation",
 	[NETIF_F_GSO_SIT_BIT] =		 "tx-sit-segmentation",
 	[NETIF_F_GSO_UDP_TUNNEL_BIT] =	 "tx-udp_tnl-segmentation",
-	[NETIF_F_GSO_MPLS_BIT] =	 "tx-mpls-segmentation",
 
 	[NETIF_F_FCOE_CRC_BIT] =         "tx-checksum-fcoe-crc",
 	[NETIF_F_SCTP_CSUM_BIT] =        "tx-checksum-sctp",
@@ -98,6 +98,13 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
 	[NETIF_F_RXALL_BIT] =            "rx-all",
 	[NETIF_F_HW_L2FW_DOFFLOAD_BIT] = "l2-fwd-offload",
 	[NETIF_F_BUSY_POLL_BIT] =        "busy-poll",
+	[NETIF_F_HW_SWITCH_OFFLOAD_BIT] = "hw-switch-offload",
+};
+
+static const char
+rss_hash_func_strings[ETH_RSS_HASH_FUNCS_COUNT][ETH_GSTRING_LEN] = {
+	[ETH_RSS_HASH_TOP_BIT] =	"toeplitz",
+	[ETH_RSS_HASH_XOR_BIT] =	"xor",
 };
 
 static int ethtool_get_features(struct net_device *dev, void __user *useraddr)
@@ -185,6 +192,9 @@ static int __ethtool_get_sset_count(struct net_device *dev, int sset)
 	if (sset == ETH_SS_FEATURES)
 		return ARRAY_SIZE(netdev_features_strings);
 
+	if (sset == ETH_SS_RSS_HASH_FUNCS)
+		return ARRAY_SIZE(rss_hash_func_strings);
+
 	if (ops->get_sset_count && ops->get_strings)
 		return ops->get_sset_count(dev, sset);
 	else
@@ -199,6 +209,9 @@ static void __ethtool_get_strings(struct net_device *dev,
 	if (stringset == ETH_SS_FEATURES)
 		memcpy(data, netdev_features_strings,
 			sizeof(netdev_features_strings));
+	else if (stringset == ETH_SS_RSS_HASH_FUNCS)
+		memcpy(data, rss_hash_func_strings,
+		       sizeof(rss_hash_func_strings));
 	else
 		/* ops->get_strings is valid because checked earlier */
 		ops->get_strings(dev, stringset, data);
@@ -574,6 +587,16 @@ static int ethtool_copy_validate_indir(u32 *indir, void __user *useraddr,
 	return 0;
 }
 
+u8 netdev_rss_key[NETDEV_RSS_KEY_LEN];
+
+void netdev_rss_key_fill(void *buffer, size_t len)
+{
+	BUG_ON(len > sizeof(netdev_rss_key));
+	net_get_random_once(netdev_rss_key, sizeof(netdev_rss_key));
+	memcpy(buffer, netdev_rss_key, len);
+}
+EXPORT_SYMBOL(netdev_rss_key_fill);
+
 static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev,
 						     void __user *useraddr)
 {
@@ -608,7 +631,7 @@ static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev,
 	if (!indir)
 		return -ENOMEM;
 
-	ret = dev->ethtool_ops->get_rxfh(dev, indir, NULL);
+	ret = dev->ethtool_ops->get_rxfh(dev, indir, NULL, NULL);
 	if (ret)
 		goto out;
 
@@ -669,7 +692,7 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev,
 			goto out;
 	}
 
-	ret = ops->set_rxfh(dev, indir, NULL);
+	ret = ops->set_rxfh(dev, indir, NULL, ETH_RSS_HASH_NO_CHANGE);
 
 out:
 	kfree(indir);
@@ -687,12 +710,11 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev,
 	u32 total_size;
 	u32 indir_bytes;
 	u32 *indir = NULL;
+	u8 dev_hfunc = 0;
 	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)
+	if (!ops->get_rxfh)
 		return -EOPNOTSUPP;
 
 	if (ops->get_rxfh_indir_size)
@@ -700,16 +722,14 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *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])
+	if (rxfh.rss_context || rxfh.rsvd8[0] || rxfh.rsvd8[1] ||
+	    rxfh.rsvd8[2] || rxfh.rsvd32)
 		return -EINVAL;
 
 	rxfh.indir_size = dev_indir_size;
@@ -717,13 +737,6 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev,
 	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;
@@ -740,14 +753,19 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev,
 	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;
-	}
+	ret = dev->ethtool_ops->get_rxfh(dev, indir, hkey, &dev_hfunc);
+	if (ret)
+		goto out;
 
+	if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh, hfunc),
+			 &dev_hfunc, sizeof(rxfh.hfunc))) {
+		ret = -EFAULT;
+	} else if (copy_to_user(useraddr +
+			      offsetof(struct ethtool_rxfh, rss_config[0]),
+			      rss_config, total_size)) {
+		ret = -EFAULT;
+	}
+out:
 	kfree(rss_config);
 
 	return ret;
@@ -766,33 +784,31 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 	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)
+	if (!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;
+		dev_key_size = ops->get_rxfh_key_size(dev);
 
 	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])
+	if (rxfh.rss_context || rxfh.rsvd8[0] || rxfh.rsvd8[1] ||
+	    rxfh.rsvd8[2] || rxfh.rsvd32)
 		return -EINVAL;
 
-	/* If either indir or hash key is valid, proceed further.
-	 * It is not valid to request that both be unchanged.
+	/* If either indir, hash key or function is valid, proceed further.
+	 * Must request at least one change: indir size, hash key or function.
 	 */
 	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))
+	     rxfh.key_size == 0 && rxfh.hfunc == ETH_RSS_HASH_NO_CHANGE))
 		return -EINVAL;
 
 	if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE)
@@ -835,7 +851,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 		}
 	}
 
-	ret = ops->set_rxfh(dev, indir, hkey);
+	ret = ops->set_rxfh(dev, indir, hkey, rxfh.hfunc);
 
 out:
 	kfree(rss_config);
@@ -1582,20 +1598,31 @@ static int ethtool_get_ts_info(struct net_device *dev, void __user *useraddr)
 	return err;
 }
 
+static int __ethtool_get_module_info(struct net_device *dev,
+				     struct ethtool_modinfo *modinfo)
+{
+	const struct ethtool_ops *ops = dev->ethtool_ops;
+	struct phy_device *phydev = dev->phydev;
+
+	if (phydev && phydev->drv && phydev->drv->module_info)
+		return phydev->drv->module_info(phydev, modinfo);
+
+	if (ops->get_module_info)
+		return ops->get_module_info(dev, modinfo);
+
+	return -EOPNOTSUPP;
+}
+
 static int ethtool_get_module_info(struct net_device *dev,
 				   void __user *useraddr)
 {
 	int ret;
 	struct ethtool_modinfo modinfo;
-	const struct ethtool_ops *ops = dev->ethtool_ops;
-
-	if (!ops->get_module_info)
-		return -EOPNOTSUPP;
 
 	if (copy_from_user(&modinfo, useraddr, sizeof(modinfo)))
 		return -EFAULT;
 
-	ret = ops->get_module_info(dev, &modinfo);
+	ret = __ethtool_get_module_info(dev, &modinfo);
 	if (ret)
 		return ret;
 
@@ -1605,21 +1632,33 @@ static int ethtool_get_module_info(struct net_device *dev,
 	return 0;
 }
 
+static int __ethtool_get_module_eeprom(struct net_device *dev,
+				       struct ethtool_eeprom *ee, u8 *data)
+{
+	const struct ethtool_ops *ops = dev->ethtool_ops;
+	struct phy_device *phydev = dev->phydev;
+
+	if (phydev && phydev->drv && phydev->drv->module_eeprom)
+		return phydev->drv->module_eeprom(phydev, ee, data);
+
+	if (ops->get_module_eeprom)
+		return ops->get_module_eeprom(dev, ee, data);
+
+	return -EOPNOTSUPP;
+}
+
 static int ethtool_get_module_eeprom(struct net_device *dev,
 				     void __user *useraddr)
 {
 	int ret;
 	struct ethtool_modinfo modinfo;
-	const struct ethtool_ops *ops = dev->ethtool_ops;
-
-	if (!ops->get_module_info || !ops->get_module_eeprom)
-		return -EOPNOTSUPP;
 
-	ret = ops->get_module_info(dev, &modinfo);
+	ret = __ethtool_get_module_info(dev, &modinfo);
 	if (ret)
 		return ret;
 
-	return ethtool_get_any_eeprom(dev, useraddr, ops->get_module_eeprom,
+	return ethtool_get_any_eeprom(dev, useraddr,
+				      __ethtool_get_module_eeprom,
 				      modinfo.eeprom_len);
 }
 
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 185c341fafbd..9a12668f7d62 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -31,7 +31,7 @@ int fib_default_rule_add(struct fib_rules_ops *ops,
 	r->pref = pref;
 	r->table = table;
 	r->flags = flags;
-	r->fr_net = hold_net(ops->fro_net);
+	r->fr_net = ops->fro_net;
 
 	r->suppress_prefixlen = -1;
 	r->suppress_ifgroup = -1;
@@ -116,7 +116,6 @@ static int __fib_rules_register(struct fib_rules_ops *ops)
 		if (ops->family == o->family)
 			goto errout;
 
-	hold_net(net);
 	list_add_tail_rcu(&ops->list, &net->rules_ops);
 	err = 0;
 errout:
@@ -160,25 +159,16 @@ static void fib_rules_cleanup_ops(struct fib_rules_ops *ops)
 	}
 }
 
-static void fib_rules_put_rcu(struct rcu_head *head)
-{
-	struct fib_rules_ops *ops = container_of(head, struct fib_rules_ops, rcu);
-	struct net *net = ops->fro_net;
-
-	release_net(net);
-	kfree(ops);
-}
-
 void fib_rules_unregister(struct fib_rules_ops *ops)
 {
 	struct net *net = ops->fro_net;
 
 	spin_lock(&net->rules_mod_lock);
 	list_del_rcu(&ops->list);
-	fib_rules_cleanup_ops(ops);
 	spin_unlock(&net->rules_mod_lock);
 
-	call_rcu(&ops->rcu, fib_rules_put_rcu);
+	fib_rules_cleanup_ops(ops);
+	kfree_rcu(ops, rcu);
 }
 EXPORT_SYMBOL_GPL(fib_rules_unregister);
 
@@ -303,7 +293,7 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh)
 		err = -ENOMEM;
 		goto errout;
 	}
-	rule->fr_net = hold_net(net);
+	rule->fr_net = net;
 
 	if (tb[FRA_PRIORITY])
 		rule->pref = nla_get_u32(tb[FRA_PRIORITY]);
@@ -423,7 +413,6 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh)
 	return 0;
 
 errout_free:
-	release_net(rule->fr_net);
 	kfree(rule);
 errout:
 	rules_ops_put(ops);
@@ -492,6 +481,12 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh)
 			goto errout;
 		}
 
+		if (ops->delete) {
+			err = ops->delete(rule);
+			if (err)
+				goto errout;
+		}
+
 		list_del_rcu(&rule->list);
 
 		if (rule->action == FR_ACT_GOTO) {
@@ -517,8 +512,6 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh)
 
 		notify_rule_change(RTM_DELRULE, rule, ops, nlh,
 				   NETLINK_CB(skb).portid);
-		if (ops->delete)
-			ops->delete(rule);
 		fib_rule_put(rule);
 		flush_route_cache(ops);
 		rules_ops_put(ops);
@@ -609,7 +602,8 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
 	if (ops->fill(rule, skb, frh) < 0)
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
diff --git a/net/core/filter.c b/net/core/filter.c
index 647b12265e18..bf831a85c315 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -44,6 +44,7 @@
 #include <linux/ratelimit.h>
 #include <linux/seccomp.h>
 #include <linux/if_vlan.h>
+#include <linux/bpf.h>
 
 /**
  *	sk_filter - run a packet through a socket filter
@@ -149,10 +150,62 @@ static u64 __get_random_u32(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
 	return prandom_u32();
 }
 
+static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg,
+			      struct bpf_insn *insn_buf)
+{
+	struct bpf_insn *insn = insn_buf;
+
+	switch (skb_field) {
+	case SKF_AD_MARK:
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);
+
+		*insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
+				      offsetof(struct sk_buff, mark));
+		break;
+
+	case SKF_AD_PKTTYPE:
+		*insn++ = BPF_LDX_MEM(BPF_B, dst_reg, src_reg, PKT_TYPE_OFFSET());
+		*insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, PKT_TYPE_MAX);
+#ifdef __BIG_ENDIAN_BITFIELD
+		*insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, 5);
+#endif
+		break;
+
+	case SKF_AD_QUEUE:
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2);
+
+		*insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg,
+				      offsetof(struct sk_buff, queue_mapping));
+		break;
+
+	case SKF_AD_VLAN_TAG:
+	case SKF_AD_VLAN_TAG_PRESENT:
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
+		BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000);
+
+		/* dst_reg = *(u16 *) (src_reg + offsetof(vlan_tci)) */
+		*insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg,
+				      offsetof(struct sk_buff, vlan_tci));
+		if (skb_field == SKF_AD_VLAN_TAG) {
+			*insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg,
+						~VLAN_TAG_PRESENT);
+		} else {
+			/* dst_reg >>= 12 */
+			*insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, 12);
+			/* dst_reg &= 1 */
+			*insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, 1);
+		}
+		break;
+	}
+
+	return insn - insn_buf;
+}
+
 static bool convert_bpf_extensions(struct sock_filter *fp,
 				   struct bpf_insn **insnp)
 {
 	struct bpf_insn *insn = *insnp;
+	u32 cnt;
 
 	switch (fp->k) {
 	case SKF_AD_OFF + SKF_AD_PROTOCOL:
@@ -166,13 +219,8 @@ static bool convert_bpf_extensions(struct sock_filter *fp,
 		break;
 
 	case SKF_AD_OFF + SKF_AD_PKTTYPE:
-		*insn++ = BPF_LDX_MEM(BPF_B, BPF_REG_A, BPF_REG_CTX,
-				      PKT_TYPE_OFFSET());
-		*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
+		cnt = convert_skb_access(SKF_AD_PKTTYPE, BPF_REG_A, BPF_REG_CTX, insn);
+		insn += cnt - 1;
 		break;
 
 	case SKF_AD_OFF + SKF_AD_IFINDEX:
@@ -196,10 +244,8 @@ static bool convert_bpf_extensions(struct sock_filter *fp,
 		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));
+		cnt = convert_skb_access(SKF_AD_MARK, BPF_REG_A, BPF_REG_CTX, insn);
+		insn += cnt - 1;
 		break;
 
 	case SKF_AD_OFF + SKF_AD_RXHASH:
@@ -210,29 +256,30 @@ static bool convert_bpf_extensions(struct sock_filter *fp,
 		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));
+		cnt = convert_skb_access(SKF_AD_QUEUE, BPF_REG_A, BPF_REG_CTX, insn);
+		insn += cnt - 1;
 		break;
 
 	case SKF_AD_OFF + SKF_AD_VLAN_TAG:
+		cnt = convert_skb_access(SKF_AD_VLAN_TAG,
+					 BPF_REG_A, BPF_REG_CTX, insn);
+		insn += cnt - 1;
+		break;
+
 	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);
+		cnt = convert_skb_access(SKF_AD_VLAN_TAG_PRESENT,
+					 BPF_REG_A, BPF_REG_CTX, insn);
+		insn += cnt - 1;
+		break;
+
+	case SKF_AD_OFF + SKF_AD_VLAN_TPID:
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_proto) != 2);
 
-		/* A = *(u16 *) (CTX + offsetof(vlan_tci)) */
+		/* A = *(u16 *) (CTX + offsetof(vlan_proto)) */
 		*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);
-		}
+				      offsetof(struct sk_buff, vlan_proto));
+		/* 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_PAY_OFFSET:
@@ -530,7 +577,7 @@ do_pass:
 			*insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, fp->k);
 			break;
 
-		/* Unkown instruction. */
+		/* Unknown instruction. */
 		default:
 			goto err;
 		}
@@ -813,8 +860,12 @@ static void bpf_release_orig_filter(struct bpf_prog *fp)
 
 static void __bpf_prog_release(struct bpf_prog *prog)
 {
-	bpf_release_orig_filter(prog);
-	bpf_prog_free(prog);
+	if (prog->type == BPF_PROG_TYPE_SOCKET_FILTER) {
+		bpf_prog_put(prog);
+	} else {
+		bpf_release_orig_filter(prog);
+		bpf_prog_free(prog);
+	}
 }
 
 static void __sk_filter_release(struct sk_filter *fp)
@@ -1014,6 +1065,32 @@ void bpf_prog_destroy(struct bpf_prog *fp)
 }
 EXPORT_SYMBOL_GPL(bpf_prog_destroy);
 
+static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk)
+{
+	struct sk_filter *fp, *old_fp;
+
+	fp = kmalloc(sizeof(*fp), GFP_KERNEL);
+	if (!fp)
+		return -ENOMEM;
+
+	fp->prog = prog;
+	atomic_set(&fp->refcnt, 0);
+
+	if (!sk_filter_charge(sk, fp)) {
+		kfree(fp);
+		return -ENOMEM;
+	}
+
+	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;
+}
+
 /**
  *	sk_attach_filter - attach a socket filter
  *	@fprog: the filter program
@@ -1026,7 +1103,6 @@ EXPORT_SYMBOL_GPL(bpf_prog_destroy);
  */
 int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 {
-	struct sk_filter *fp, *old_fp;
 	unsigned int fsize = bpf_classic_proglen(fprog);
 	unsigned int bpf_fsize = bpf_prog_size(fprog->len);
 	struct bpf_prog *prog;
@@ -1063,30 +1139,358 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
-	fp = kmalloc(sizeof(*fp), GFP_KERNEL);
-	if (!fp) {
+	err = __sk_attach_prog(prog, sk);
+	if (err < 0) {
 		__bpf_prog_release(prog);
-		return -ENOMEM;
+		return err;
 	}
-	fp->prog = prog;
 
-	atomic_set(&fp->refcnt, 0);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(sk_attach_filter);
 
-	if (!sk_filter_charge(sk, fp)) {
-		__sk_filter_release(fp);
-		return -ENOMEM;
+int sk_attach_bpf(u32 ufd, struct sock *sk)
+{
+	struct bpf_prog *prog;
+	int err;
+
+	if (sock_flag(sk, SOCK_FILTER_LOCKED))
+		return -EPERM;
+
+	prog = bpf_prog_get(ufd);
+	if (IS_ERR(prog))
+		return PTR_ERR(prog);
+
+	if (prog->type != BPF_PROG_TYPE_SOCKET_FILTER) {
+		bpf_prog_put(prog);
+		return -EINVAL;
 	}
 
-	old_fp = rcu_dereference_protected(sk->sk_filter,
-					   sock_owned_by_user(sk));
-	rcu_assign_pointer(sk->sk_filter, fp);
+	err = __sk_attach_prog(prog, sk);
+	if (err < 0) {
+		bpf_prog_put(prog);
+		return err;
+	}
 
-	if (old_fp)
-		sk_filter_uncharge(sk, old_fp);
+	return 0;
+}
 
+/**
+ *	bpf_skb_clone_not_writable - is the header of a clone not writable
+ *	@skb: buffer to check
+ *	@len: length up to which to write, can be negative
+ *
+ *	Returns true if modifying the header part of the cloned buffer
+ *	does require the data to be copied. I.e. this version works with
+ *	negative lengths needed for eBPF case!
+ */
+static bool bpf_skb_clone_unwritable(const struct sk_buff *skb, int len)
+{
+	return skb_header_cloned(skb) ||
+	       (int) skb_headroom(skb) + len > skb->hdr_len;
+}
+
+#define BPF_RECOMPUTE_CSUM(flags)	((flags) & 1)
+
+static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags)
+{
+	struct sk_buff *skb = (struct sk_buff *) (long) r1;
+	int offset = (int) r2;
+	void *from = (void *) (long) r3;
+	unsigned int len = (unsigned int) r4;
+	char buf[16];
+	void *ptr;
+
+	/* bpf verifier guarantees that:
+	 * 'from' pointer points to bpf program stack
+	 * 'len' bytes of it were initialized
+	 * 'len' > 0
+	 * 'skb' is a valid pointer to 'struct sk_buff'
+	 *
+	 * so check for invalid 'offset' and too large 'len'
+	 */
+	if (unlikely((u32) offset > 0xffff || len > sizeof(buf)))
+		return -EFAULT;
+
+	offset -= skb->data - skb_mac_header(skb);
+	if (unlikely(skb_cloned(skb) &&
+		     bpf_skb_clone_unwritable(skb, offset + len)))
+		return -EFAULT;
+
+	ptr = skb_header_pointer(skb, offset, len, buf);
+	if (unlikely(!ptr))
+		return -EFAULT;
+
+	if (BPF_RECOMPUTE_CSUM(flags))
+		skb_postpull_rcsum(skb, ptr, len);
+
+	memcpy(ptr, from, len);
+
+	if (ptr == buf)
+		/* skb_store_bits cannot return -EFAULT here */
+		skb_store_bits(skb, offset, ptr, len);
+
+	if (BPF_RECOMPUTE_CSUM(flags) && skb->ip_summed == CHECKSUM_COMPLETE)
+		skb->csum = csum_add(skb->csum, csum_partial(ptr, len, 0));
 	return 0;
 }
-EXPORT_SYMBOL_GPL(sk_attach_filter);
+
+const struct bpf_func_proto bpf_skb_store_bytes_proto = {
+	.func		= bpf_skb_store_bytes,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_PTR_TO_STACK,
+	.arg4_type	= ARG_CONST_STACK_SIZE,
+	.arg5_type	= ARG_ANYTHING,
+};
+
+#define BPF_HEADER_FIELD_SIZE(flags)	((flags) & 0x0f)
+#define BPF_IS_PSEUDO_HEADER(flags)	((flags) & 0x10)
+
+static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags)
+{
+	struct sk_buff *skb = (struct sk_buff *) (long) r1;
+	int offset = (int) r2;
+	__sum16 sum, *ptr;
+
+	if (unlikely((u32) offset > 0xffff))
+		return -EFAULT;
+
+	offset -= skb->data - skb_mac_header(skb);
+	if (unlikely(skb_cloned(skb) &&
+		     bpf_skb_clone_unwritable(skb, offset + sizeof(sum))))
+		return -EFAULT;
+
+	ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum);
+	if (unlikely(!ptr))
+		return -EFAULT;
+
+	switch (BPF_HEADER_FIELD_SIZE(flags)) {
+	case 2:
+		csum_replace2(ptr, from, to);
+		break;
+	case 4:
+		csum_replace4(ptr, from, to);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (ptr == &sum)
+		/* skb_store_bits guaranteed to not return -EFAULT here */
+		skb_store_bits(skb, offset, ptr, sizeof(sum));
+
+	return 0;
+}
+
+const struct bpf_func_proto bpf_l3_csum_replace_proto = {
+	.func		= bpf_l3_csum_replace,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_ANYTHING,
+	.arg5_type	= ARG_ANYTHING,
+};
+
+static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags)
+{
+	struct sk_buff *skb = (struct sk_buff *) (long) r1;
+	u32 is_pseudo = BPF_IS_PSEUDO_HEADER(flags);
+	int offset = (int) r2;
+	__sum16 sum, *ptr;
+
+	if (unlikely((u32) offset > 0xffff))
+		return -EFAULT;
+
+	offset -= skb->data - skb_mac_header(skb);
+	if (unlikely(skb_cloned(skb) &&
+		     bpf_skb_clone_unwritable(skb, offset + sizeof(sum))))
+		return -EFAULT;
+
+	ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum);
+	if (unlikely(!ptr))
+		return -EFAULT;
+
+	switch (BPF_HEADER_FIELD_SIZE(flags)) {
+	case 2:
+		inet_proto_csum_replace2(ptr, skb, from, to, is_pseudo);
+		break;
+	case 4:
+		inet_proto_csum_replace4(ptr, skb, from, to, is_pseudo);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (ptr == &sum)
+		/* skb_store_bits guaranteed to not return -EFAULT here */
+		skb_store_bits(skb, offset, ptr, sizeof(sum));
+
+	return 0;
+}
+
+const struct bpf_func_proto bpf_l4_csum_replace_proto = {
+	.func		= bpf_l4_csum_replace,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_ANYTHING,
+	.arg5_type	= ARG_ANYTHING,
+};
+
+static const struct bpf_func_proto *
+sk_filter_func_proto(enum bpf_func_id func_id)
+{
+	switch (func_id) {
+	case BPF_FUNC_map_lookup_elem:
+		return &bpf_map_lookup_elem_proto;
+	case BPF_FUNC_map_update_elem:
+		return &bpf_map_update_elem_proto;
+	case BPF_FUNC_map_delete_elem:
+		return &bpf_map_delete_elem_proto;
+	case BPF_FUNC_get_prandom_u32:
+		return &bpf_get_prandom_u32_proto;
+	case BPF_FUNC_get_smp_processor_id:
+		return &bpf_get_smp_processor_id_proto;
+	default:
+		return NULL;
+	}
+}
+
+static const struct bpf_func_proto *
+tc_cls_act_func_proto(enum bpf_func_id func_id)
+{
+	switch (func_id) {
+	case BPF_FUNC_skb_store_bytes:
+		return &bpf_skb_store_bytes_proto;
+	case BPF_FUNC_l3_csum_replace:
+		return &bpf_l3_csum_replace_proto;
+	case BPF_FUNC_l4_csum_replace:
+		return &bpf_l4_csum_replace_proto;
+	default:
+		return sk_filter_func_proto(func_id);
+	}
+}
+
+static bool sk_filter_is_valid_access(int off, int size,
+				      enum bpf_access_type type)
+{
+	/* only read is allowed */
+	if (type != BPF_READ)
+		return false;
+
+	/* check bounds */
+	if (off < 0 || off >= sizeof(struct __sk_buff))
+		return false;
+
+	/* disallow misaligned access */
+	if (off % size != 0)
+		return false;
+
+	/* all __sk_buff fields are __u32 */
+	if (size != 4)
+		return false;
+
+	return true;
+}
+
+static u32 sk_filter_convert_ctx_access(int dst_reg, int src_reg, int ctx_off,
+					struct bpf_insn *insn_buf)
+{
+	struct bpf_insn *insn = insn_buf;
+
+	switch (ctx_off) {
+	case offsetof(struct __sk_buff, len):
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4);
+
+		*insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
+				      offsetof(struct sk_buff, len));
+		break;
+
+	case offsetof(struct __sk_buff, protocol):
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2);
+
+		*insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg,
+				      offsetof(struct sk_buff, protocol));
+		break;
+
+	case offsetof(struct __sk_buff, vlan_proto):
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_proto) != 2);
+
+		*insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg,
+				      offsetof(struct sk_buff, vlan_proto));
+		break;
+
+	case offsetof(struct __sk_buff, priority):
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, priority) != 4);
+
+		*insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
+				      offsetof(struct sk_buff, priority));
+		break;
+
+	case offsetof(struct __sk_buff, mark):
+		return convert_skb_access(SKF_AD_MARK, dst_reg, src_reg, insn);
+
+	case offsetof(struct __sk_buff, pkt_type):
+		return convert_skb_access(SKF_AD_PKTTYPE, dst_reg, src_reg, insn);
+
+	case offsetof(struct __sk_buff, queue_mapping):
+		return convert_skb_access(SKF_AD_QUEUE, dst_reg, src_reg, insn);
+
+	case offsetof(struct __sk_buff, vlan_present):
+		return convert_skb_access(SKF_AD_VLAN_TAG_PRESENT,
+					  dst_reg, src_reg, insn);
+
+	case offsetof(struct __sk_buff, vlan_tci):
+		return convert_skb_access(SKF_AD_VLAN_TAG,
+					  dst_reg, src_reg, insn);
+	}
+
+	return insn - insn_buf;
+}
+
+static const struct bpf_verifier_ops sk_filter_ops = {
+	.get_func_proto = sk_filter_func_proto,
+	.is_valid_access = sk_filter_is_valid_access,
+	.convert_ctx_access = sk_filter_convert_ctx_access,
+};
+
+static const struct bpf_verifier_ops tc_cls_act_ops = {
+	.get_func_proto = tc_cls_act_func_proto,
+	.is_valid_access = sk_filter_is_valid_access,
+	.convert_ctx_access = sk_filter_convert_ctx_access,
+};
+
+static struct bpf_prog_type_list sk_filter_type __read_mostly = {
+	.ops = &sk_filter_ops,
+	.type = BPF_PROG_TYPE_SOCKET_FILTER,
+};
+
+static struct bpf_prog_type_list sched_cls_type __read_mostly = {
+	.ops = &tc_cls_act_ops,
+	.type = BPF_PROG_TYPE_SCHED_CLS,
+};
+
+static struct bpf_prog_type_list sched_act_type __read_mostly = {
+	.ops = &tc_cls_act_ops,
+	.type = BPF_PROG_TYPE_SCHED_ACT,
+};
+
+static int __init register_sk_filter_ops(void)
+{
+	bpf_register_prog_type(&sk_filter_type);
+	bpf_register_prog_type(&sched_cls_type);
+	bpf_register_prog_type(&sched_act_type);
+
+	return 0;
+}
+late_initcall(register_sk_filter_ops);
 
 int sk_detach_filter(struct sock *sk)
 {
diff --git a/net/core/flow.c b/net/core/flow.c
index a0348fde1fdf..1033725be40b 100644
--- a/net/core/flow.c
+++ b/net/core/flow.c
@@ -379,7 +379,7 @@ done:
 static void flow_cache_flush_task(struct work_struct *work)
 {
 	struct netns_xfrm *xfrm = container_of(work, struct netns_xfrm,
-						flow_cache_gc_work);
+						flow_cache_flush_work);
 	struct net *net = container_of(xfrm, struct net, xfrm);
 
 	flow_cache_flush(net);
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 45084938c403..2c35c02a931e 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -178,6 +178,20 @@ ipv6:
 			return false;
 		}
 	}
+	case htons(ETH_P_TIPC): {
+		struct {
+			__be32 pre[3];
+			__be32 srcnode;
+		} *hdr, _hdr;
+		hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
+		if (!hdr)
+			return false;
+		flow->src = hdr->srcnode;
+		flow->dst = 0;
+		flow->n_proto = proto;
+		flow->thoff = (u16)nhoff;
+		return true;
+	}
 	case htons(ETH_P_FCOE):
 		flow->thoff = (u16)(nhoff + FCOE_HEADER_LEN);
 		/* fall through */
@@ -408,7 +422,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
 	dev_maps = rcu_dereference(dev->xps_maps);
 	if (dev_maps) {
 		map = rcu_dereference(
-		    dev_maps->cpu_map[raw_smp_processor_id()]);
+		    dev_maps->cpu_map[skb->sender_cpu - 1]);
 		if (map) {
 			if (map->len == 1)
 				queue_index = map->queues[0];
@@ -454,6 +468,11 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev,
 {
 	int queue_index = 0;
 
+#ifdef CONFIG_XPS
+	if (skb->sender_cpu == 0)
+		skb->sender_cpu = raw_smp_processor_id() + 1;
+#endif
+
 	if (dev->real_num_tx_queues != 1) {
 		const struct net_device_ops *ops = dev->netdev_ops;
 		if (ops->ndo_select_queue)
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index 0c08062d1796..1e2f46a69d50 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -32,6 +32,9 @@ gnet_stats_copy(struct gnet_dump *d, int type, void *buf, int size)
 	return 0;
 
 nla_put_failure:
+	kfree(d->xstats);
+	d->xstats = NULL;
+	d->xstats_len = 0;
 	spin_unlock_bh(d->lock);
 	return -1;
 }
@@ -305,7 +308,9 @@ int
 gnet_stats_copy_app(struct gnet_dump *d, void *st, int len)
 {
 	if (d->compat_xstats) {
-		d->xstats = st;
+		d->xstats = kmemdup(st, len, GFP_ATOMIC);
+		if (!d->xstats)
+			goto err_out;
 		d->xstats_len = len;
 	}
 
@@ -313,6 +318,11 @@ gnet_stats_copy_app(struct gnet_dump *d, void *st, int len)
 		return gnet_stats_copy(d, TCA_STATS_APP, st, len);
 
 	return 0;
+
+err_out:
+	d->xstats_len = 0;
+	spin_unlock_bh(d->lock);
+	return -1;
 }
 EXPORT_SYMBOL(gnet_stats_copy_app);
 
@@ -345,6 +355,9 @@ gnet_stats_finish_copy(struct gnet_dump *d)
 			return -1;
 	}
 
+	kfree(d->xstats);
+	d->xstats = NULL;
+	d->xstats_len = 0;
 	spin_unlock_bh(d->lock);
 	return 0;
 }
diff --git a/net/core/iovec.c b/net/core/iovec.c
deleted file mode 100644
index e1ec45ab1e63..000000000000
--- a/net/core/iovec.c
+++ /dev/null
@@ -1,184 +0,0 @@
-/*
- *	iovec manipulation routines.
- *
- *
- *		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.
- *
- *	Fixes:
- *		Andrew Lunn	:	Errors in iovec copying.
- *		Pedro Roque	:	Added memcpy_fromiovecend and
- *					csum_..._fromiovecend.
- *		Andi Kleen	:	fixed error handling for 2.1
- *		Alexey Kuznetsov:	2.1 optimisations
- *		Andi Kleen	:	Fix csum*fromiovecend for IPv6.
- */
-
-#include <linux/errno.h>
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/net.h>
-#include <linux/in6.h>
-#include <asm/uaccess.h>
-#include <asm/byteorder.h>
-#include <net/checksum.h>
-#include <net/sock.h>
-
-/*
- *	Verify iovec. The caller must ensure that the iovec is big enough
- *	to hold the message iovec.
- *
- *	Save time not doing access_ok. copy_*_user will make this work
- *	in any case.
- */
-
-int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *address, int mode)
-{
-	int size, ct, err;
-
-	if (m->msg_name && m->msg_namelen) {
-		if (mode == VERIFY_READ) {
-			void __user *namep;
-			namep = (void __user __force *) m->msg_name;
-			err = move_addr_to_kernel(namep, m->msg_namelen,
-						  address);
-			if (err < 0)
-				return err;
-		}
-		m->msg_name = address;
-	} else {
-		m->msg_name = NULL;
-		m->msg_namelen = 0;
-	}
-
-	size = m->msg_iovlen * sizeof(struct iovec);
-	if (copy_from_user(iov, (void __user __force *) m->msg_iov, size))
-		return -EFAULT;
-
-	m->msg_iov = iov;
-	err = 0;
-
-	for (ct = 0; ct < m->msg_iovlen; ct++) {
-		size_t len = iov[ct].iov_len;
-
-		if (len > INT_MAX - err) {
-			len = INT_MAX - err;
-			iov[ct].iov_len = len;
-		}
-		err += len;
-	}
-
-	return err;
-}
-
-/*
- *	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
- *
- *	ip_build_xmit must ensure that when fragmenting only the last
- *	call to this function will be unaligned also.
- */
-int csum_partial_copy_fromiovecend(unsigned char *kdata, struct iovec *iov,
-				 int offset, unsigned int len, __wsum *csump)
-{
-	__wsum csum = *csump;
-	int partial_cnt = 0, err = 0;
-
-	/* 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;
-
-		/* There is a remnant from previous iov. */
-		if (partial_cnt) {
-			int par_len = 4 - partial_cnt;
-
-			/* iov component is too short ... */
-			if (par_len > copy) {
-				if (copy_from_user(kdata, base, copy))
-					goto out_fault;
-				kdata += copy;
-				base += copy;
-				partial_cnt += copy;
-				len -= copy;
-				iov++;
-				if (len)
-					continue;
-				*csump = csum_partial(kdata - partial_cnt,
-							 partial_cnt, csum);
-				goto out;
-			}
-			if (copy_from_user(kdata, base, par_len))
-				goto out_fault;
-			csum = csum_partial(kdata - partial_cnt, 4, csum);
-			kdata += par_len;
-			base  += par_len;
-			copy  -= par_len;
-			len   -= par_len;
-			partial_cnt = 0;
-		}
-
-		if (len > copy) {
-			partial_cnt = copy % 4;
-			if (partial_cnt) {
-				copy -= partial_cnt;
-				if (copy_from_user(kdata + copy, base + copy,
-						partial_cnt))
-					goto out_fault;
-			}
-		}
-
-		if (copy) {
-			csum = csum_and_copy_from_user(base, kdata, copy,
-							csum, &err);
-			if (err)
-				goto out;
-		}
-		len   -= copy + partial_cnt;
-		kdata += copy + partial_cnt;
-		iov++;
-	}
-	*csump = csum;
-out:
-	return err;
-
-out_fault:
-	err = -EFAULT;
-	goto out;
-}
-EXPORT_SYMBOL(csum_partial_copy_fromiovecend);
-
-unsigned long iov_pages(const struct iovec *iov, int offset,
-			unsigned long nr_segs)
-{
-	unsigned long seg, base;
-	int pages = 0, len, size;
-
-	while (nr_segs && (offset >= iov->iov_len)) {
-		offset -= iov->iov_len;
-		++iov;
-		--nr_segs;
-	}
-
-	for (seg = 0; seg < nr_segs; seg++) {
-		base = (unsigned long)iov[seg].iov_base + offset;
-		len = iov[seg].iov_len - offset;
-		size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT;
-		pages += size;
-		offset = 0;
-	}
-
-	return pages;
-}
-EXPORT_SYMBOL(iov_pages);
diff --git a/net/core/link_watch.c b/net/core/link_watch.c
index bd0767e6b2b3..982861607f88 100644
--- a/net/core/link_watch.c
+++ b/net/core/link_watch.c
@@ -21,7 +21,7 @@
 #include <linux/spinlock.h>
 #include <linux/workqueue.h>
 #include <linux/bitops.h>
-#include <asm/types.h>
+#include <linux/types.h>
 
 
 enum lw_bits {
@@ -40,7 +40,7 @@ static DEFINE_SPINLOCK(lweventlist_lock);
 static unsigned char default_operstate(const struct net_device *dev)
 {
 	if (!netif_carrier_ok(dev))
-		return (dev->ifindex != dev->iflink ?
+		return (dev->ifindex != dev_get_iflink(dev) ?
 			IF_OPER_LOWERLAYERDOWN : IF_OPER_DOWN);
 
 	if (netif_dormant(dev))
@@ -89,7 +89,7 @@ static bool linkwatch_urgent_event(struct net_device *dev)
 	if (!netif_running(dev))
 		return false;
 
-	if (dev->ifindex != dev->iflink)
+	if (dev->ifindex != dev_get_iflink(dev))
 		return true;
 
 	if (dev->priv_flags & IFF_TEAM_PORT)
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index ef31fef25e5a..3de654256028 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -56,7 +56,6 @@ static void __neigh_notify(struct neighbour *n, int type, int flags);
 static void neigh_update_notify(struct neighbour *neigh);
 static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev);
 
-static struct neigh_table *neigh_tables;
 #ifdef CONFIG_PROC_FS
 static const struct file_operations neigh_stat_seq_fops;
 #endif
@@ -87,13 +86,8 @@ static const struct file_operations neigh_stat_seq_fops;
    the most complicated procedure, which we allow is dev->hard_header.
    It is supposed, that dev->hard_header is simplistic and does
    not make callbacks to neighbour tables.
-
-   The last lock is neigh_tbl_lock. It is pure SMP lock, protecting
-   list of neighbour tables. This list is used only in process context,
  */
 
-static DEFINE_RWLOCK(neigh_tbl_lock);
-
 static int neigh_blackhole(struct neighbour *neigh, struct sk_buff *skb)
 {
 	kfree_skb(skb);
@@ -403,25 +397,15 @@ struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey,
 			       struct net_device *dev)
 {
 	struct neighbour *n;
-	int key_len = tbl->key_len;
-	u32 hash_val;
-	struct neigh_hash_table *nht;
 
 	NEIGH_CACHE_STAT_INC(tbl, lookups);
 
 	rcu_read_lock_bh();
-	nht = rcu_dereference_bh(tbl->nht);
-	hash_val = tbl->hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift);
-
-	for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]);
-	     n != NULL;
-	     n = rcu_dereference_bh(n->next)) {
-		if (dev == n->dev && !memcmp(n->primary_key, pkey, key_len)) {
-			if (!atomic_inc_not_zero(&n->refcnt))
-				n = NULL;
-			NEIGH_CACHE_STAT_INC(tbl, hits);
-			break;
-		}
+	n = __neigh_lookup_noref(tbl, pkey, dev);
+	if (n) {
+		if (!atomic_inc_not_zero(&n->refcnt))
+			n = NULL;
+		NEIGH_CACHE_STAT_INC(tbl, hits);
 	}
 
 	rcu_read_unlock_bh();
@@ -607,7 +591,7 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl,
 	if (!n)
 		goto out;
 
-	write_pnet(&n->net, hold_net(net));
+	write_pnet(&n->net, net);
 	memcpy(n->key, pkey, key_len);
 	n->dev = dev;
 	if (dev)
@@ -616,7 +600,6 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl,
 	if (tbl->pconstructor && tbl->pconstructor(n)) {
 		if (dev)
 			dev_put(dev);
-		release_net(net);
 		kfree(n);
 		n = NULL;
 		goto out;
@@ -650,7 +633,6 @@ int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *pkey,
 				tbl->pdestructor(n);
 			if (n->dev)
 				dev_put(n->dev);
-			release_net(pneigh_net(n));
 			kfree(n);
 			return 0;
 		}
@@ -673,7 +655,6 @@ static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
 					tbl->pdestructor(n);
 				if (n->dev)
 					dev_put(n->dev);
-				release_net(pneigh_net(n));
 				kfree(n);
 				continue;
 			}
@@ -773,7 +754,7 @@ static void neigh_periodic_work(struct work_struct *work)
 	if (time_after(jiffies, tbl->last_rand + 300 * HZ)) {
 		struct neigh_parms *p;
 		tbl->last_rand = jiffies;
-		for (p = &tbl->parms; p; p = p->next)
+		list_for_each_entry(p, &tbl->parms_list, list)
 			p->reachable_time =
 				neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME));
 	}
@@ -836,10 +817,9 @@ out:
 static __inline__ int neigh_max_probes(struct neighbour *n)
 {
 	struct neigh_parms *p = n->parms;
-	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;
+	return NEIGH_VAR(p, UCAST_PROBES) + NEIGH_VAR(p, APP_PROBES) +
+	       (n->nud_state & NUD_PROBE ? NEIGH_VAR(p, MCAST_REPROBES) :
+	        NEIGH_VAR(p, MCAST_PROBES));
 }
 
 static void neigh_invalidate(struct neighbour *neigh)
@@ -1269,10 +1249,10 @@ struct neighbour *neigh_event_ns(struct neigh_table *tbl,
 EXPORT_SYMBOL(neigh_event_ns);
 
 /* called with read_lock_bh(&n->lock); */
-static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst)
+static void neigh_hh_init(struct neighbour *n)
 {
-	struct net_device *dev = dst->dev;
-	__be16 prot = dst->ops->protocol;
+	struct net_device *dev = n->dev;
+	__be16 prot = n->tbl->protocol;
 	struct hh_cache	*hh = &n->hh;
 
 	write_lock_bh(&n->lock);
@@ -1286,43 +1266,19 @@ static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst)
 	write_unlock_bh(&n->lock);
 }
 
-/* This function can be used in contexts, where only old dev_queue_xmit
- * worked, f.e. if you want to override normal output path (eql, shaper),
- * but resolution is not made yet.
- */
-
-int neigh_compat_output(struct neighbour *neigh, struct sk_buff *skb)
-{
-	struct net_device *dev = skb->dev;
-
-	__skb_pull(skb, skb_network_offset(skb));
-
-	if (dev_hard_header(skb, dev, ntohs(skb->protocol), NULL, NULL,
-			    skb->len) < 0 &&
-	    dev_rebuild_header(skb))
-		return 0;
-
-	return dev_queue_xmit(skb);
-}
-EXPORT_SYMBOL(neigh_compat_output);
-
 /* Slow and careful. */
 
 int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb)
 {
-	struct dst_entry *dst = skb_dst(skb);
 	int rc = 0;
 
-	if (!dst)
-		goto discard;
-
 	if (!neigh_event_send(neigh, skb)) {
 		int err;
 		struct net_device *dev = neigh->dev;
 		unsigned int seq;
 
 		if (dev->header_ops->cache && !neigh->hh.hh_len)
-			neigh_hh_init(neigh, dst);
+			neigh_hh_init(neigh);
 
 		do {
 			__skb_pull(skb, skb_network_offset(skb));
@@ -1338,8 +1294,6 @@ int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb)
 	}
 out:
 	return rc;
-discard:
-	neigh_dbg(1, "%s: dst=%p neigh=%p\n", __func__, dst, neigh);
 out_kfree_skb:
 	rc = -EINVAL;
 	kfree_skb(skb);
@@ -1446,7 +1400,7 @@ static inline struct neigh_parms *lookup_neigh_parms(struct neigh_table *tbl,
 {
 	struct neigh_parms *p;
 
-	for (p = &tbl->parms; p; p = p->next) {
+	list_for_each_entry(p, &tbl->parms_list, list) {
 		if ((p->dev && p->dev->ifindex == ifindex && net_eq(neigh_parms_net(p), net)) ||
 		    (!p->dev && !ifindex && net_eq(net, &init_net)))
 			return p;
@@ -1470,19 +1424,17 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev,
 				neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME));
 		dev_hold(dev);
 		p->dev = dev;
-		write_pnet(&p->net, hold_net(net));
+		write_pnet(&p->net, net);
 		p->sysctl_table = NULL;
 
 		if (ops->ndo_neigh_setup && ops->ndo_neigh_setup(dev, p)) {
-			release_net(net);
 			dev_put(dev);
 			kfree(p);
 			return NULL;
 		}
 
 		write_lock_bh(&tbl->lock);
-		p->next		= tbl->parms.next;
-		tbl->parms.next = p;
+		list_add(&p->list, &tbl->parms.list);
 		write_unlock_bh(&tbl->lock);
 
 		neigh_parms_data_state_cleanall(p);
@@ -1501,40 +1453,34 @@ static void neigh_rcu_free_parms(struct rcu_head *head)
 
 void neigh_parms_release(struct neigh_table *tbl, struct neigh_parms *parms)
 {
-	struct neigh_parms **p;
-
 	if (!parms || parms == &tbl->parms)
 		return;
 	write_lock_bh(&tbl->lock);
-	for (p = &tbl->parms.next; *p; p = &(*p)->next) {
-		if (*p == parms) {
-			*p = parms->next;
-			parms->dead = 1;
-			write_unlock_bh(&tbl->lock);
-			if (parms->dev)
-				dev_put(parms->dev);
-			call_rcu(&parms->rcu_head, neigh_rcu_free_parms);
-			return;
-		}
-	}
+	list_del(&parms->list);
+	parms->dead = 1;
 	write_unlock_bh(&tbl->lock);
-	neigh_dbg(1, "%s: not found\n", __func__);
+	if (parms->dev)
+		dev_put(parms->dev);
+	call_rcu(&parms->rcu_head, neigh_rcu_free_parms);
 }
 EXPORT_SYMBOL(neigh_parms_release);
 
 static void neigh_parms_destroy(struct neigh_parms *parms)
 {
-	release_net(neigh_parms_net(parms));
 	kfree(parms);
 }
 
 static struct lock_class_key neigh_table_proxy_queue_class;
 
-static void neigh_table_init_no_netlink(struct neigh_table *tbl)
+static struct neigh_table *neigh_tables[NEIGH_NR_TABLES] __read_mostly;
+
+void neigh_table_init(int index, struct neigh_table *tbl)
 {
 	unsigned long now = jiffies;
 	unsigned long phsize;
 
+	INIT_LIST_HEAD(&tbl->parms_list);
+	list_add(&tbl->parms.list, &tbl->parms_list);
 	write_pnet(&tbl->parms.net, &init_net);
 	atomic_set(&tbl->parms.refcnt, 1);
 	tbl->parms.reachable_time =
@@ -1574,34 +1520,14 @@ static void neigh_table_init_no_netlink(struct neigh_table *tbl)
 
 	tbl->last_flush = now;
 	tbl->last_rand	= now + tbl->parms.reachable_time * 20;
-}
-
-void neigh_table_init(struct neigh_table *tbl)
-{
-	struct neigh_table *tmp;
-
-	neigh_table_init_no_netlink(tbl);
-	write_lock(&neigh_tbl_lock);
-	for (tmp = neigh_tables; tmp; tmp = tmp->next) {
-		if (tmp->family == tbl->family)
-			break;
-	}
-	tbl->next	= neigh_tables;
-	neigh_tables	= tbl;
-	write_unlock(&neigh_tbl_lock);
 
-	if (unlikely(tmp)) {
-		pr_err("Registering multiple tables for family %d\n",
-		       tbl->family);
-		dump_stack();
-	}
+	neigh_tables[index] = tbl;
 }
 EXPORT_SYMBOL(neigh_table_init);
 
-int neigh_table_clear(struct neigh_table *tbl)
+int neigh_table_clear(int index, struct neigh_table *tbl)
 {
-	struct neigh_table **tp;
-
+	neigh_tables[index] = NULL;
 	/* It is not clean... Fix it to unload IPv6 module safely */
 	cancel_delayed_work_sync(&tbl->gc_work);
 	del_timer_sync(&tbl->proxy_timer);
@@ -1609,14 +1535,6 @@ int neigh_table_clear(struct neigh_table *tbl)
 	neigh_ifdown(tbl, NULL);
 	if (atomic_read(&tbl->entries))
 		pr_crit("neighbour leakage\n");
-	write_lock(&neigh_tbl_lock);
-	for (tp = &neigh_tables; *tp; tp = &(*tp)->next) {
-		if (*tp == tbl) {
-			*tp = tbl->next;
-			break;
-		}
-	}
-	write_unlock(&neigh_tbl_lock);
 
 	call_rcu(&rcu_dereference_protected(tbl->nht, 1)->rcu,
 		 neigh_hash_free_rcu);
@@ -1634,12 +1552,32 @@ int neigh_table_clear(struct neigh_table *tbl)
 }
 EXPORT_SYMBOL(neigh_table_clear);
 
+static struct neigh_table *neigh_find_table(int family)
+{
+	struct neigh_table *tbl = NULL;
+
+	switch (family) {
+	case AF_INET:
+		tbl = neigh_tables[NEIGH_ARP_TABLE];
+		break;
+	case AF_INET6:
+		tbl = neigh_tables[NEIGH_ND_TABLE];
+		break;
+	case AF_DECnet:
+		tbl = neigh_tables[NEIGH_DN_TABLE];
+		break;
+	}
+
+	return tbl;
+}
+
 static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ndmsg *ndm;
 	struct nlattr *dst_attr;
 	struct neigh_table *tbl;
+	struct neighbour *neigh;
 	struct net_device *dev = NULL;
 	int err = -EINVAL;
 
@@ -1660,39 +1598,31 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh)
 		}
 	}
 
-	read_lock(&neigh_tbl_lock);
-	for (tbl = neigh_tables; tbl; tbl = tbl->next) {
-		struct neighbour *neigh;
-
-		if (tbl->family != ndm->ndm_family)
-			continue;
-		read_unlock(&neigh_tbl_lock);
-
-		if (nla_len(dst_attr) < tbl->key_len)
-			goto out;
+	tbl = neigh_find_table(ndm->ndm_family);
+	if (tbl == NULL)
+		return -EAFNOSUPPORT;
 
-		if (ndm->ndm_flags & NTF_PROXY) {
-			err = pneigh_delete(tbl, net, nla_data(dst_attr), dev);
-			goto out;
-		}
+	if (nla_len(dst_attr) < tbl->key_len)
+		goto out;
 
-		if (dev == NULL)
-			goto out;
+	if (ndm->ndm_flags & NTF_PROXY) {
+		err = pneigh_delete(tbl, net, nla_data(dst_attr), dev);
+		goto out;
+	}
 
-		neigh = neigh_lookup(tbl, nla_data(dst_attr), dev);
-		if (neigh == NULL) {
-			err = -ENOENT;
-			goto out;
-		}
+	if (dev == NULL)
+		goto out;
 
-		err = neigh_update(neigh, NULL, NUD_FAILED,
-				   NEIGH_UPDATE_F_OVERRIDE |
-				   NEIGH_UPDATE_F_ADMIN);
-		neigh_release(neigh);
+	neigh = neigh_lookup(tbl, nla_data(dst_attr), dev);
+	if (neigh == NULL) {
+		err = -ENOENT;
 		goto out;
 	}
-	read_unlock(&neigh_tbl_lock);
-	err = -EAFNOSUPPORT;
+
+	err = neigh_update(neigh, NULL, NUD_FAILED,
+			   NEIGH_UPDATE_F_OVERRIDE |
+			   NEIGH_UPDATE_F_ADMIN);
+	neigh_release(neigh);
 
 out:
 	return err;
@@ -1700,11 +1630,14 @@ out:
 
 static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
+	int flags = NEIGH_UPDATE_F_ADMIN | NEIGH_UPDATE_F_OVERRIDE;
 	struct net *net = sock_net(skb->sk);
 	struct ndmsg *ndm;
 	struct nlattr *tb[NDA_MAX+1];
 	struct neigh_table *tbl;
 	struct net_device *dev = NULL;
+	struct neighbour *neigh;
+	void *dst, *lladdr;
 	int err;
 
 	ASSERT_RTNL();
@@ -1728,70 +1661,60 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 			goto out;
 	}
 
-	read_lock(&neigh_tbl_lock);
-	for (tbl = neigh_tables; tbl; tbl = tbl->next) {
-		int flags = NEIGH_UPDATE_F_ADMIN | NEIGH_UPDATE_F_OVERRIDE;
-		struct neighbour *neigh;
-		void *dst, *lladdr;
+	tbl = neigh_find_table(ndm->ndm_family);
+	if (tbl == NULL)
+		return -EAFNOSUPPORT;
 
-		if (tbl->family != ndm->ndm_family)
-			continue;
-		read_unlock(&neigh_tbl_lock);
+	if (nla_len(tb[NDA_DST]) < tbl->key_len)
+		goto out;
+	dst = nla_data(tb[NDA_DST]);
+	lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL;
 
-		if (nla_len(tb[NDA_DST]) < tbl->key_len)
-			goto out;
-		dst = nla_data(tb[NDA_DST]);
-		lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL;
+	if (ndm->ndm_flags & NTF_PROXY) {
+		struct pneigh_entry *pn;
+
+		err = -ENOBUFS;
+		pn = pneigh_lookup(tbl, net, dst, dev, 1);
+		if (pn) {
+			pn->flags = ndm->ndm_flags;
+			err = 0;
+		}
+		goto out;
+	}
 
-		if (ndm->ndm_flags & NTF_PROXY) {
-			struct pneigh_entry *pn;
+	if (dev == NULL)
+		goto out;
 
-			err = -ENOBUFS;
-			pn = pneigh_lookup(tbl, net, dst, dev, 1);
-			if (pn) {
-				pn->flags = ndm->ndm_flags;
-				err = 0;
-			}
+	neigh = neigh_lookup(tbl, dst, dev);
+	if (neigh == NULL) {
+		if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
+			err = -ENOENT;
 			goto out;
 		}
 
-		if (dev == NULL)
+		neigh = __neigh_lookup_errno(tbl, dst, dev);
+		if (IS_ERR(neigh)) {
+			err = PTR_ERR(neigh);
+			goto out;
+		}
+	} else {
+		if (nlh->nlmsg_flags & NLM_F_EXCL) {
+			err = -EEXIST;
+			neigh_release(neigh);
 			goto out;
-
-		neigh = neigh_lookup(tbl, dst, dev);
-		if (neigh == NULL) {
-			if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
-				err = -ENOENT;
-				goto out;
-			}
-
-			neigh = __neigh_lookup_errno(tbl, dst, dev);
-			if (IS_ERR(neigh)) {
-				err = PTR_ERR(neigh);
-				goto out;
-			}
-		} else {
-			if (nlh->nlmsg_flags & NLM_F_EXCL) {
-				err = -EEXIST;
-				neigh_release(neigh);
-				goto out;
-			}
-
-			if (!(nlh->nlmsg_flags & NLM_F_REPLACE))
-				flags &= ~NEIGH_UPDATE_F_OVERRIDE;
 		}
 
-		if (ndm->ndm_flags & NTF_USE) {
-			neigh_event_send(neigh, NULL);
-			err = 0;
-		} else
-			err = neigh_update(neigh, lladdr, ndm->ndm_state, flags);
-		neigh_release(neigh);
-		goto out;
+		if (!(nlh->nlmsg_flags & NLM_F_REPLACE))
+			flags &= ~NEIGH_UPDATE_F_OVERRIDE;
 	}
 
-	read_unlock(&neigh_tbl_lock);
-	err = -EAFNOSUPPORT;
+	if (ndm->ndm_flags & NTF_USE) {
+		neigh_event_send(neigh, NULL);
+		err = 0;
+	} else
+		err = neigh_update(neigh, lladdr, ndm->ndm_state, flags);
+	neigh_release(neigh);
+
 out:
 	return err;
 }
@@ -1818,6 +1741,8 @@ static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms)
 			NEIGH_VAR(parms, UCAST_PROBES)) ||
 	    nla_put_u32(skb, NDTPA_MCAST_PROBES,
 			NEIGH_VAR(parms, MCAST_PROBES)) ||
+	    nla_put_u32(skb, NDTPA_MCAST_REPROBES,
+			NEIGH_VAR(parms, MCAST_REPROBES)) ||
 	    nla_put_msecs(skb, NDTPA_REACHABLE_TIME, parms->reachable_time) ||
 	    nla_put_msecs(skb, NDTPA_BASE_REACHABLE_TIME,
 			  NEIGH_VAR(parms, BASE_REACHABLE_TIME)) ||
@@ -1919,7 +1844,8 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl,
 		goto nla_put_failure;
 
 	read_unlock_bh(&tbl->lock);
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	read_unlock_bh(&tbl->lock);
@@ -1952,7 +1878,8 @@ static int neightbl_fill_param_info(struct sk_buff *skb,
 		goto errout;
 
 	read_unlock_bh(&tbl->lock);
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 errout:
 	read_unlock_bh(&tbl->lock);
 	nlmsg_cancel(skb, nlh);
@@ -1975,6 +1902,7 @@ static const struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] = {
 	[NDTPA_APP_PROBES]		= { .type = NLA_U32 },
 	[NDTPA_UCAST_PROBES]		= { .type = NLA_U32 },
 	[NDTPA_MCAST_PROBES]		= { .type = NLA_U32 },
+	[NDTPA_MCAST_REPROBES]		= { .type = NLA_U32 },
 	[NDTPA_BASE_REACHABLE_TIME]	= { .type = NLA_U64 },
 	[NDTPA_GC_STALETIME]		= { .type = NLA_U64 },
 	[NDTPA_DELAY_PROBE_TIME]	= { .type = NLA_U64 },
@@ -1990,7 +1918,8 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct neigh_table *tbl;
 	struct ndtmsg *ndtmsg;
 	struct nlattr *tb[NDTA_MAX+1];
-	int err;
+	bool found = false;
+	int err, tidx;
 
 	err = nlmsg_parse(nlh, sizeof(*ndtmsg), tb, NDTA_MAX,
 			  nl_neightbl_policy);
@@ -2003,19 +1932,21 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
 	}
 
 	ndtmsg = nlmsg_data(nlh);
-	read_lock(&neigh_tbl_lock);
-	for (tbl = neigh_tables; tbl; tbl = tbl->next) {
+
+	for (tidx = 0; tidx < NEIGH_NR_TABLES; tidx++) {
+		tbl = neigh_tables[tidx];
+		if (!tbl)
+			continue;
 		if (ndtmsg->ndtm_family && tbl->family != ndtmsg->ndtm_family)
 			continue;
-
-		if (nla_strcmp(tb[NDTA_NAME], tbl->id) == 0)
+		if (nla_strcmp(tb[NDTA_NAME], tbl->id) == 0) {
+			found = true;
 			break;
+		}
 	}
 
-	if (tbl == NULL) {
-		err = -ENOENT;
-		goto errout_locked;
-	}
+	if (!found)
+		return -ENOENT;
 
 	/*
 	 * We acquire tbl->lock to be nice to the periodic timers and
@@ -2072,9 +2003,19 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
 				NEIGH_VAR_SET(p, MCAST_PROBES,
 					      nla_get_u32(tbp[i]));
 				break;
+			case NDTPA_MCAST_REPROBES:
+				NEIGH_VAR_SET(p, MCAST_REPROBES,
+					      nla_get_u32(tbp[i]));
+				break;
 			case NDTPA_BASE_REACHABLE_TIME:
 				NEIGH_VAR_SET(p, BASE_REACHABLE_TIME,
 					      nla_get_msecs(tbp[i]));
+				/* update reachable_time as well, otherwise, the change will
+				 * only be effective after the next time neigh_periodic_work
+				 * decides to recompute it (can be multiple minutes)
+				 */
+				p->reachable_time =
+					neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME));
 				break;
 			case NDTPA_GC_STALETIME:
 				NEIGH_VAR_SET(p, GC_STALETIME,
@@ -2126,8 +2067,6 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 errout_tbl_lock:
 	write_unlock_bh(&tbl->lock);
-errout_locked:
-	read_unlock(&neigh_tbl_lock);
 errout:
 	return err;
 }
@@ -2142,19 +2081,24 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
 
 	family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family;
 
-	read_lock(&neigh_tbl_lock);
-	for (tbl = neigh_tables, tidx = 0; tbl; tbl = tbl->next, tidx++) {
+	for (tidx = 0; tidx < NEIGH_NR_TABLES; tidx++) {
 		struct neigh_parms *p;
 
+		tbl = neigh_tables[tidx];
+		if (!tbl)
+			continue;
+
 		if (tidx < tbl_skip || (family && tbl->family != family))
 			continue;
 
 		if (neightbl_fill_info(skb, tbl, NETLINK_CB(cb->skb).portid,
 				       cb->nlh->nlmsg_seq, RTM_NEWNEIGHTBL,
-				       NLM_F_MULTI) <= 0)
+				       NLM_F_MULTI) < 0)
 			break;
 
-		for (nidx = 0, p = tbl->parms.next; p; p = p->next) {
+		nidx = 0;
+		p = list_next_entry(&tbl->parms, list);
+		list_for_each_entry_from(p, &tbl->parms_list, list) {
 			if (!net_eq(neigh_parms_net(p), net))
 				continue;
 
@@ -2165,7 +2109,7 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
 						     NETLINK_CB(cb->skb).portid,
 						     cb->nlh->nlmsg_seq,
 						     RTM_NEWNEIGHTBL,
-						     NLM_F_MULTI) <= 0)
+						     NLM_F_MULTI) < 0)
 				goto out;
 		next:
 			nidx++;
@@ -2174,7 +2118,6 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
 		neigh_skip = 0;
 	}
 out:
-	read_unlock(&neigh_tbl_lock);
 	cb->args[0] = tidx;
 	cb->args[1] = nidx;
 
@@ -2226,7 +2169,8 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh,
 	    nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci))
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
@@ -2256,7 +2200,8 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn,
 	if (nla_put(skb, NDA_DST, tbl->key_len, pn->key))
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
@@ -2294,7 +2239,7 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
 			if (neigh_fill_info(skb, n, NETLINK_CB(cb->skb).portid,
 					    cb->nlh->nlmsg_seq,
 					    RTM_NEWNEIGH,
-					    NLM_F_MULTI) <= 0) {
+					    NLM_F_MULTI) < 0) {
 				rc = -1;
 				goto out;
 			}
@@ -2331,7 +2276,7 @@ static int pneigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
 			if (pneigh_fill_info(skb, n, NETLINK_CB(cb->skb).portid,
 					    cb->nlh->nlmsg_seq,
 					    RTM_NEWNEIGH,
-					    NLM_F_MULTI, tbl) <= 0) {
+					    NLM_F_MULTI, tbl) < 0) {
 				read_unlock_bh(&tbl->lock);
 				rc = -1;
 				goto out;
@@ -2357,7 +2302,6 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
 	int proxy = 0;
 	int err;
 
-	read_lock(&neigh_tbl_lock);
 	family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family;
 
 	/* check for full ndmsg structure presence, family member is
@@ -2369,8 +2313,11 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
 
 	s_t = cb->args[0];
 
-	for (tbl = neigh_tables, t = 0; tbl;
-	     tbl = tbl->next, t++) {
+	for (t = 0; t < NEIGH_NR_TABLES; t++) {
+		tbl = neigh_tables[t];
+
+		if (!tbl)
+			continue;
 		if (t < s_t || (family && tbl->family != family))
 			continue;
 		if (t > s_t)
@@ -2383,7 +2330,6 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
 		if (err < 0)
 			break;
 	}
-	read_unlock(&neigh_tbl_lock);
 
 	cb->args[0] = t;
 	return skb->len;
@@ -2446,6 +2392,40 @@ void __neigh_for_each_release(struct neigh_table *tbl,
 }
 EXPORT_SYMBOL(__neigh_for_each_release);
 
+int neigh_xmit(int index, struct net_device *dev,
+	       const void *addr, struct sk_buff *skb)
+{
+	int err = -EAFNOSUPPORT;
+	if (likely(index < NEIGH_NR_TABLES)) {
+		struct neigh_table *tbl;
+		struct neighbour *neigh;
+
+		tbl = neigh_tables[index];
+		if (!tbl)
+			goto out;
+		neigh = __neigh_lookup_noref(tbl, addr, dev);
+		if (!neigh)
+			neigh = __neigh_create(tbl, addr, dev, false);
+		err = PTR_ERR(neigh);
+		if (IS_ERR(neigh))
+			goto out_kfree_skb;
+		err = neigh->output(neigh, skb);
+	}
+	else if (index == NEIGH_LINK_TABLE) {
+		err = dev_hard_header(skb, dev, ntohs(skb->protocol),
+				      addr, NULL, skb->len);
+		if (err < 0)
+			goto out_kfree_skb;
+		err = dev_queue_xmit(skb);
+	}
+out:
+	return err;
+out_kfree_skb:
+	kfree_skb(skb);
+	goto out;
+}
+EXPORT_SYMBOL(neigh_xmit);
+
 #ifdef CONFIG_PROC_FS
 
 static struct neighbour *neigh_get_first(struct seq_file *seq)
@@ -2950,6 +2930,31 @@ static int neigh_proc_dointvec_unres_qlen(struct ctl_table *ctl, int write,
 	return ret;
 }
 
+static int neigh_proc_base_reachable_time(struct ctl_table *ctl, int write,
+					  void __user *buffer,
+					  size_t *lenp, loff_t *ppos)
+{
+	struct neigh_parms *p = ctl->extra2;
+	int ret;
+
+	if (strcmp(ctl->procname, "base_reachable_time") == 0)
+		ret = neigh_proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos);
+	else if (strcmp(ctl->procname, "base_reachable_time_ms") == 0)
+		ret = neigh_proc_dointvec_ms_jiffies(ctl, write, buffer, lenp, ppos);
+	else
+		ret = -1;
+
+	if (write && ret == 0) {
+		/* update reachable_time as well, otherwise, the change will
+		 * only be effective after the next time neigh_periodic_work
+		 * decides to recompute it
+		 */
+		p->reachable_time =
+			neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME));
+	}
+	return ret;
+}
+
 #define NEIGH_PARMS_DATA_OFFSET(index)	\
 	(&((struct neigh_parms *) 0)->data[index])
 
@@ -2988,6 +2993,7 @@ static struct neigh_sysctl_table {
 		NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(MCAST_PROBES, "mcast_solicit"),
 		NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(UCAST_PROBES, "ucast_solicit"),
 		NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(APP_PROBES, "app_solicit"),
+		NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(MCAST_REPROBES, "mcast_resolicit"),
 		NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(RETRANS_TIME, "retrans_time"),
 		NEIGH_SYSCTL_JIFFIES_ENTRY(BASE_REACHABLE_TIME, "base_reachable_time"),
 		NEIGH_SYSCTL_JIFFIES_ENTRY(DELAY_PROBE_TIME, "delay_first_probe_time"),
@@ -3076,6 +3082,19 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p,
 		t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].proc_handler = handler;
 		/* ReachableTime (in milliseconds) */
 		t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].proc_handler = handler;
+	} else {
+		/* Those handlers will update p->reachable_time after
+		 * base_reachable_time(_ms) is set to ensure the new timer starts being
+		 * applied after the next neighbour update instead of waiting for
+		 * neigh_periodic_work to update its value (can be multiple minutes)
+		 * So any handler that replaces them should do this as well
+		 */
+		/* ReachableTime */
+		t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].proc_handler =
+			neigh_proc_base_reachable_time;
+		/* ReachableTime (in milliseconds) */
+		t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].proc_handler =
+			neigh_proc_base_reachable_time;
 	}
 
 	/* Don't export sysctls to unprivileged users */
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 9dd06699b09c..4238d6da5c60 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -12,6 +12,7 @@
 #include <linux/capability.h>
 #include <linux/kernel.h>
 #include <linux/netdevice.h>
+#include <net/switchdev.h>
 #include <linux/if_arp.h>
 #include <linux/slab.h>
 #include <linux/nsproxy.h>
@@ -22,6 +23,7 @@
 #include <linux/export.h>
 #include <linux/jiffies.h>
 #include <linux/pm_runtime.h>
+#include <linux/of.h>
 
 #include "net-sysfs.h"
 
@@ -107,11 +109,19 @@ 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);
 NETDEVICE_SHOW_RO(ifindex, fmt_dec);
 NETDEVICE_SHOW_RO(type, fmt_dec);
 NETDEVICE_SHOW_RO(link_mode, fmt_dec);
 
+static ssize_t iflink_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
+{
+	struct net_device *ndev = to_net_dev(dev);
+
+	return sprintf(buf, fmt_dec, dev_get_iflink(ndev));
+}
+static DEVICE_ATTR_RO(iflink);
+
 static ssize_t format_name_assign_type(const struct net_device *dev, char *buf)
 {
 	return sprintf(buf, fmt_dec, dev->name_assign_type);
@@ -325,6 +335,23 @@ static ssize_t tx_queue_len_store(struct device *dev,
 }
 NETDEVICE_SHOW_RW(tx_queue_len, fmt_ulong);
 
+static int change_gro_flush_timeout(struct net_device *dev, unsigned long val)
+{
+	dev->gro_flush_timeout = val;
+	return 0;
+}
+
+static ssize_t gro_flush_timeout_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t len)
+{
+	if (!capable(CAP_NET_ADMIN))
+		return -EPERM;
+
+	return netdev_store(dev, attr, buf, len, change_gro_flush_timeout);
+}
+NETDEVICE_SHOW_RW(gro_flush_timeout, fmt_ulong);
+
 static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr,
 			     const char *buf, size_t len)
 {
@@ -387,7 +414,7 @@ static ssize_t phys_port_id_show(struct device *dev,
 		return restart_syscall();
 
 	if (dev_isalive(netdev)) {
-		struct netdev_phys_port_id ppid;
+		struct netdev_phys_item_id ppid;
 
 		ret = dev_get_phys_port_id(netdev, &ppid);
 		if (!ret)
@@ -399,6 +426,50 @@ static ssize_t phys_port_id_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(phys_port_id);
 
+static ssize_t phys_port_name_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct net_device *netdev = to_net_dev(dev);
+	ssize_t ret = -EINVAL;
+
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	if (dev_isalive(netdev)) {
+		char name[IFNAMSIZ];
+
+		ret = dev_get_phys_port_name(netdev, name, sizeof(name));
+		if (!ret)
+			ret = sprintf(buf, "%s\n", name);
+	}
+	rtnl_unlock();
+
+	return ret;
+}
+static DEVICE_ATTR_RO(phys_port_name);
+
+static ssize_t phys_switch_id_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct net_device *netdev = to_net_dev(dev);
+	ssize_t ret = -EINVAL;
+
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	if (dev_isalive(netdev)) {
+		struct netdev_phys_item_id ppid;
+
+		ret = netdev_switch_parent_id_get(netdev, &ppid);
+		if (!ret)
+			ret = sprintf(buf, "%*phN\n", ppid.id_len, ppid.id);
+	}
+	rtnl_unlock();
+
+	return ret;
+}
+static DEVICE_ATTR_RO(phys_switch_id);
+
 static struct attribute *net_class_attrs[] = {
 	&dev_attr_netdev_group.attr,
 	&dev_attr_type.attr,
@@ -422,7 +493,10 @@ static struct attribute *net_class_attrs[] = {
 	&dev_attr_mtu.attr,
 	&dev_attr_flags.attr,
 	&dev_attr_tx_queue_len.attr,
+	&dev_attr_gro_flush_timeout.attr,
 	&dev_attr_phys_port_id.attr,
+	&dev_attr_phys_port_name.attr,
+	&dev_attr_phys_switch_id.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(net_class);
@@ -572,8 +646,7 @@ static ssize_t show_rps_map(struct netdev_rx_queue *queue,
 {
 	struct rps_map *map;
 	cpumask_var_t mask;
-	size_t len = 0;
-	int i;
+	int i, len;
 
 	if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
 		return -ENOMEM;
@@ -584,17 +657,11 @@ static ssize_t show_rps_map(struct netdev_rx_queue *queue,
 		for (i = 0; i < map->len; i++)
 			cpumask_set_cpu(map->cpus[i], mask);
 
-	len += cpumask_scnprintf(buf + len, PAGE_SIZE, mask);
-	if (PAGE_SIZE - len < 3) {
-		rcu_read_unlock();
-		free_cpumask_var(mask);
-		return -EINVAL;
-	}
+	len = snprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(mask));
 	rcu_read_unlock();
-
 	free_cpumask_var(mask);
-	len += sprintf(buf + len, "\n");
-	return len;
+
+	return len < PAGE_SIZE ? len : -EINVAL;
 }
 
 static ssize_t store_rps_map(struct netdev_rx_queue *queue,
@@ -915,6 +982,60 @@ static ssize_t show_trans_timeout(struct netdev_queue *queue,
 	return sprintf(buf, "%lu", trans_timeout);
 }
 
+#ifdef CONFIG_XPS
+static inline 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;
+
+	BUG_ON(i >= dev->num_tx_queues);
+
+	return i;
+}
+
+static ssize_t show_tx_maxrate(struct netdev_queue *queue,
+			       struct netdev_queue_attribute *attribute,
+			       char *buf)
+{
+	return sprintf(buf, "%lu\n", queue->tx_maxrate);
+}
+
+static ssize_t set_tx_maxrate(struct netdev_queue *queue,
+			      struct netdev_queue_attribute *attribute,
+			      const char *buf, size_t len)
+{
+	struct net_device *dev = queue->dev;
+	int err, index = get_netdev_queue_index(queue);
+	u32 rate = 0;
+
+	err = kstrtou32(buf, 10, &rate);
+	if (err < 0)
+		return err;
+
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	err = -EOPNOTSUPP;
+	if (dev->netdev_ops->ndo_set_tx_maxrate)
+		err = dev->netdev_ops->ndo_set_tx_maxrate(dev, index, rate);
+
+	rtnl_unlock();
+	if (!err) {
+		queue->tx_maxrate = rate;
+		return len;
+	}
+	return err;
+}
+
+static struct netdev_queue_attribute queue_tx_maxrate =
+	__ATTR(tx_maxrate, S_IRUGO | S_IWUSR,
+	       show_tx_maxrate, set_tx_maxrate);
+#endif
+
 static struct netdev_queue_attribute queue_trans_timeout =
 	__ATTR(tx_timeout, S_IRUGO, show_trans_timeout, NULL);
 
@@ -1029,18 +1150,6 @@ static struct attribute_group dql_group = {
 #endif /* CONFIG_BQL */
 
 #ifdef CONFIG_XPS
-static unsigned int get_netdev_queue_index(struct netdev_queue *queue)
-{
-	struct net_device *dev = queue->dev;
-	unsigned int i;
-
-	i = queue - dev->_tx;
-	BUG_ON(i >= dev->num_tx_queues);
-
-	return i;
-}
-
-
 static ssize_t show_xps_map(struct netdev_queue *queue,
 			    struct netdev_queue_attribute *attribute, char *buf)
 {
@@ -1048,8 +1157,7 @@ static ssize_t show_xps_map(struct netdev_queue *queue,
 	struct xps_dev_maps *dev_maps;
 	cpumask_var_t mask;
 	unsigned long index;
-	size_t len = 0;
-	int i;
+	int i, len;
 
 	if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
 		return -ENOMEM;
@@ -1075,15 +1183,9 @@ static ssize_t show_xps_map(struct netdev_queue *queue,
 	}
 	rcu_read_unlock();
 
-	len += cpumask_scnprintf(buf + len, PAGE_SIZE, mask);
-	if (PAGE_SIZE - len < 3) {
-		free_cpumask_var(mask);
-		return -EINVAL;
-	}
-
+	len = snprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(mask));
 	free_cpumask_var(mask);
-	len += sprintf(buf + len, "\n");
-	return len;
+	return len < PAGE_SIZE ? len : -EINVAL;
 }
 
 static ssize_t store_xps_map(struct netdev_queue *queue,
@@ -1124,6 +1226,7 @@ static struct attribute *netdev_queue_default_attrs[] = {
 	&queue_trans_timeout.attr,
 #ifdef CONFIG_XPS
 	&xps_cpus_attribute.attr,
+	&queue_tx_maxrate.attr,
 #endif
 	NULL
 };
@@ -1346,6 +1449,30 @@ static struct class net_class = {
 	.namespace = net_namespace,
 };
 
+#ifdef CONFIG_OF_NET
+static int of_dev_node_match(struct device *dev, const void *data)
+{
+	int ret = 0;
+
+	if (dev->parent)
+		ret = dev->parent->of_node == data;
+
+	return ret == 0 ? dev->of_node == data : ret;
+}
+
+struct net_device *of_find_net_device_by_node(struct device_node *np)
+{
+	struct device *dev;
+
+	dev = class_find_device(&net_class, NULL, np, of_dev_node_match);
+	if (!dev)
+		return NULL;
+
+	return to_net_dev(dev);
+}
+EXPORT_SYMBOL(of_find_net_device_by_node);
+#endif
+
 /* Delete sysfs entries but hold kobject reference until after all
  * netdev references are gone.
  */
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 7f155175bba8..572af0011997 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -15,6 +15,9 @@
 #include <linux/file.h>
 #include <linux/export.h>
 #include <linux/user_namespace.h>
+#include <linux/net_namespace.h>
+#include <net/sock.h>
+#include <net/netlink.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 
@@ -144,6 +147,86 @@ static void ops_free_list(const struct pernet_operations *ops,
 	}
 }
 
+static void rtnl_net_notifyid(struct net *net, struct net *peer, int cmd,
+			      int id);
+static int alloc_netid(struct net *net, struct net *peer, int reqid)
+{
+	int min = 0, max = 0, id;
+
+	ASSERT_RTNL();
+
+	if (reqid >= 0) {
+		min = reqid;
+		max = reqid + 1;
+	}
+
+	id = idr_alloc(&net->netns_ids, peer, min, max, GFP_KERNEL);
+	if (id >= 0)
+		rtnl_net_notifyid(net, peer, RTM_NEWNSID, id);
+
+	return id;
+}
+
+/* This function is used by idr_for_each(). If net is equal to peer, the
+ * function returns the id so that idr_for_each() stops. Because we cannot
+ * returns the id 0 (idr_for_each() will not stop), we return the magic value
+ * NET_ID_ZERO (-1) for it.
+ */
+#define NET_ID_ZERO -1
+static int net_eq_idr(int id, void *net, void *peer)
+{
+	if (net_eq(net, peer))
+		return id ? : NET_ID_ZERO;
+	return 0;
+}
+
+static int __peernet2id(struct net *net, struct net *peer, bool alloc)
+{
+	int id = idr_for_each(&net->netns_ids, net_eq_idr, peer);
+
+	ASSERT_RTNL();
+
+	/* Magic value for id 0. */
+	if (id == NET_ID_ZERO)
+		return 0;
+	if (id > 0)
+		return id;
+
+	if (alloc)
+		return alloc_netid(net, peer, -1);
+
+	return -ENOENT;
+}
+
+/* This function returns the id of a peer netns. If no id is assigned, one will
+ * be allocated and returned.
+ */
+int peernet2id(struct net *net, struct net *peer)
+{
+	bool alloc = atomic_read(&peer->count) == 0 ? false : true;
+	int id;
+
+	id = __peernet2id(net, peer, alloc);
+	return id >= 0 ? id : NETNSA_NSID_NOT_ASSIGNED;
+}
+EXPORT_SYMBOL(peernet2id);
+
+struct net *get_net_ns_by_id(struct net *net, int id)
+{
+	struct net *peer;
+
+	if (id < 0)
+		return NULL;
+
+	rcu_read_lock();
+	peer = idr_find(&net->netns_ids, id);
+	if (peer)
+		get_net(peer);
+	rcu_read_unlock();
+
+	return peer;
+}
+
 /*
  * setup_net runs the initializers for the network namespace object.
  */
@@ -158,10 +241,7 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
 	atomic_set(&net->passive, 1);
 	net->dev_base_seq = 1;
 	net->user_ns = user_ns;
-
-#ifdef NETNS_REFCNT_DEBUG
-	atomic_set(&net->use_count, 0);
-#endif
+	idr_init(&net->netns_ids);
 
 	list_for_each_entry(ops, &pernet_list, list) {
 		error = ops_init(ops, net);
@@ -217,13 +297,6 @@ out_free:
 
 static void net_free(struct net *net)
 {
-#ifdef NETNS_REFCNT_DEBUG
-	if (unlikely(atomic_read(&net->use_count) != 0)) {
-		pr_emerg("network namespace not free! Usage: %d\n",
-			 atomic_read(&net->use_count));
-		return;
-	}
-#endif
 	kfree(rcu_access_pointer(net->gen));
 	kmem_cache_free(net_cachep, net);
 }
@@ -288,6 +361,16 @@ static void cleanup_net(struct work_struct *work)
 	list_for_each_entry(net, &net_kill_list, cleanup_list) {
 		list_del_rcu(&net->list);
 		list_add_tail(&net->exit_list, &net_exit_list);
+		for_each_net(tmp) {
+			int id = __peernet2id(tmp, net, false);
+
+			if (id >= 0) {
+				rtnl_net_notifyid(tmp, net, RTM_DELNSID, id);
+				idr_remove(&tmp->netns_ids, id);
+			}
+		}
+		idr_destroy(&net->netns_ids);
+
 	}
 	rtnl_unlock();
 
@@ -337,17 +420,17 @@ EXPORT_SYMBOL_GPL(__put_net);
 
 struct net *get_net_ns_by_fd(int fd)
 {
-	struct proc_ns *ei;
 	struct file *file;
+	struct ns_common *ns;
 	struct net *net;
 
 	file = proc_ns_fget(fd);
 	if (IS_ERR(file))
 		return ERR_CAST(file);
 
-	ei = get_proc_ns(file_inode(file));
-	if (ei->ns_ops == &netns_operations)
-		net = get_net(ei->ns);
+	ns = get_proc_ns(file_inode(file));
+	if (ns->ops == &netns_operations)
+		net = get_net(container_of(ns, struct net, ns));
 	else
 		net = ERR_PTR(-EINVAL);
 
@@ -361,6 +444,7 @@ struct net *get_net_ns_by_fd(int fd)
 	return ERR_PTR(-EINVAL);
 }
 #endif
+EXPORT_SYMBOL_GPL(get_net_ns_by_fd);
 
 struct net *get_net_ns_by_pid(pid_t pid)
 {
@@ -386,12 +470,15 @@ EXPORT_SYMBOL_GPL(get_net_ns_by_pid);
 
 static __net_init int net_ns_net_init(struct net *net)
 {
-	return proc_alloc_inum(&net->proc_inum);
+#ifdef CONFIG_NET_NS
+	net->ns.ops = &netns_operations;
+#endif
+	return ns_alloc_inum(&net->ns);
 }
 
 static __net_exit void net_ns_net_exit(struct net *net)
 {
-	proc_free_inum(net->proc_inum);
+	ns_free_inum(&net->ns);
 }
 
 static struct pernet_operations __net_initdata net_ns_ops = {
@@ -399,6 +486,204 @@ static struct pernet_operations __net_initdata net_ns_ops = {
 	.exit = net_ns_net_exit,
 };
 
+static struct nla_policy rtnl_net_policy[NETNSA_MAX + 1] = {
+	[NETNSA_NONE]		= { .type = NLA_UNSPEC },
+	[NETNSA_NSID]		= { .type = NLA_S32 },
+	[NETNSA_PID]		= { .type = NLA_U32 },
+	[NETNSA_FD]		= { .type = NLA_U32 },
+};
+
+static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh)
+{
+	struct net *net = sock_net(skb->sk);
+	struct nlattr *tb[NETNSA_MAX + 1];
+	struct net *peer;
+	int nsid, err;
+
+	err = nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX,
+			  rtnl_net_policy);
+	if (err < 0)
+		return err;
+	if (!tb[NETNSA_NSID])
+		return -EINVAL;
+	nsid = nla_get_s32(tb[NETNSA_NSID]);
+
+	if (tb[NETNSA_PID])
+		peer = get_net_ns_by_pid(nla_get_u32(tb[NETNSA_PID]));
+	else if (tb[NETNSA_FD])
+		peer = get_net_ns_by_fd(nla_get_u32(tb[NETNSA_FD]));
+	else
+		return -EINVAL;
+	if (IS_ERR(peer))
+		return PTR_ERR(peer);
+
+	if (__peernet2id(net, peer, false) >= 0) {
+		err = -EEXIST;
+		goto out;
+	}
+
+	err = alloc_netid(net, peer, nsid);
+	if (err > 0)
+		err = 0;
+out:
+	put_net(peer);
+	return err;
+}
+
+static int rtnl_net_get_size(void)
+{
+	return NLMSG_ALIGN(sizeof(struct rtgenmsg))
+	       + nla_total_size(sizeof(s32)) /* NETNSA_NSID */
+	       ;
+}
+
+static int rtnl_net_fill(struct sk_buff *skb, u32 portid, u32 seq, int flags,
+			 int cmd, struct net *net, struct net *peer,
+			 int nsid)
+{
+	struct nlmsghdr *nlh;
+	struct rtgenmsg *rth;
+	int id;
+
+	ASSERT_RTNL();
+
+	nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rth), flags);
+	if (!nlh)
+		return -EMSGSIZE;
+
+	rth = nlmsg_data(nlh);
+	rth->rtgen_family = AF_UNSPEC;
+
+	if (nsid >= 0) {
+		id = nsid;
+	} else {
+		id = __peernet2id(net, peer, false);
+		if  (id < 0)
+			id = NETNSA_NSID_NOT_ASSIGNED;
+	}
+	if (nla_put_s32(skb, NETNSA_NSID, id))
+		goto nla_put_failure;
+
+	nlmsg_end(skb, nlh);
+	return 0;
+
+nla_put_failure:
+	nlmsg_cancel(skb, nlh);
+	return -EMSGSIZE;
+}
+
+static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh)
+{
+	struct net *net = sock_net(skb->sk);
+	struct nlattr *tb[NETNSA_MAX + 1];
+	struct sk_buff *msg;
+	struct net *peer;
+	int err;
+
+	err = nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX,
+			  rtnl_net_policy);
+	if (err < 0)
+		return err;
+	if (tb[NETNSA_PID])
+		peer = get_net_ns_by_pid(nla_get_u32(tb[NETNSA_PID]));
+	else if (tb[NETNSA_FD])
+		peer = get_net_ns_by_fd(nla_get_u32(tb[NETNSA_FD]));
+	else
+		return -EINVAL;
+
+	if (IS_ERR(peer))
+		return PTR_ERR(peer);
+
+	msg = nlmsg_new(rtnl_net_get_size(), GFP_KERNEL);
+	if (!msg) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	err = rtnl_net_fill(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0,
+			    RTM_NEWNSID, net, peer, -1);
+	if (err < 0)
+		goto err_out;
+
+	err = rtnl_unicast(msg, net, NETLINK_CB(skb).portid);
+	goto out;
+
+err_out:
+	nlmsg_free(msg);
+out:
+	put_net(peer);
+	return err;
+}
+
+struct rtnl_net_dump_cb {
+	struct net *net;
+	struct sk_buff *skb;
+	struct netlink_callback *cb;
+	int idx;
+	int s_idx;
+};
+
+static int rtnl_net_dumpid_one(int id, void *peer, void *data)
+{
+	struct rtnl_net_dump_cb *net_cb = (struct rtnl_net_dump_cb *)data;
+	int ret;
+
+	if (net_cb->idx < net_cb->s_idx)
+		goto cont;
+
+	ret = rtnl_net_fill(net_cb->skb, NETLINK_CB(net_cb->cb->skb).portid,
+			    net_cb->cb->nlh->nlmsg_seq, NLM_F_MULTI,
+			    RTM_NEWNSID, net_cb->net, peer, id);
+	if (ret < 0)
+		return ret;
+
+cont:
+	net_cb->idx++;
+	return 0;
+}
+
+static int rtnl_net_dumpid(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct net *net = sock_net(skb->sk);
+	struct rtnl_net_dump_cb net_cb = {
+		.net = net,
+		.skb = skb,
+		.cb = cb,
+		.idx = 0,
+		.s_idx = cb->args[0],
+	};
+
+	ASSERT_RTNL();
+
+	idr_for_each(&net->netns_ids, rtnl_net_dumpid_one, &net_cb);
+
+	cb->args[0] = net_cb.idx;
+	return skb->len;
+}
+
+static void rtnl_net_notifyid(struct net *net, struct net *peer, int cmd,
+			      int id)
+{
+	struct sk_buff *msg;
+	int err = -ENOMEM;
+
+	msg = nlmsg_new(rtnl_net_get_size(), GFP_KERNEL);
+	if (!msg)
+		goto out;
+
+	err = rtnl_net_fill(msg, 0, 0, 0, cmd, net, peer, id);
+	if (err < 0)
+		goto err_out;
+
+	rtnl_notify(msg, net, 0, RTNLGRP_NSID, NULL, 0);
+	return;
+
+err_out:
+	nlmsg_free(msg);
+out:
+	rtnl_set_sk_err(net, RTNLGRP_NSID, err);
+}
+
 static int __init net_ns_init(void)
 {
 	struct net_generic *ng;
@@ -432,6 +717,10 @@ static int __init net_ns_init(void)
 
 	register_pernet_subsys(&net_ns_ops);
 
+	rtnl_register(PF_UNSPEC, RTM_NEWNSID, rtnl_net_newid, NULL, NULL);
+	rtnl_register(PF_UNSPEC, RTM_GETNSID, rtnl_net_getid, rtnl_net_dumpid,
+		      NULL);
+
 	return 0;
 }
 
@@ -629,7 +918,7 @@ void unregister_pernet_device(struct pernet_operations *ops)
 EXPORT_SYMBOL_GPL(unregister_pernet_device);
 
 #ifdef CONFIG_NET_NS
-static void *netns_get(struct task_struct *task)
+static struct ns_common *netns_get(struct task_struct *task)
 {
 	struct net *net = NULL;
 	struct nsproxy *nsproxy;
@@ -640,17 +929,22 @@ static void *netns_get(struct task_struct *task)
 		net = get_net(nsproxy->net_ns);
 	task_unlock(task);
 
-	return net;
+	return net ? &net->ns : NULL;
+}
+
+static inline struct net *to_net_ns(struct ns_common *ns)
+{
+	return container_of(ns, struct net, ns);
 }
 
-static void netns_put(void *ns)
+static void netns_put(struct ns_common *ns)
 {
-	put_net(ns);
+	put_net(to_net_ns(ns));
 }
 
-static int netns_install(struct nsproxy *nsproxy, void *ns)
+static int netns_install(struct nsproxy *nsproxy, struct ns_common *ns)
 {
-	struct net *net = ns;
+	struct net *net = to_net_ns(ns);
 
 	if (!ns_capable(net->user_ns, CAP_SYS_ADMIN) ||
 	    !ns_capable(current_user_ns(), CAP_SYS_ADMIN))
@@ -661,18 +955,11 @@ static int netns_install(struct nsproxy *nsproxy, void *ns)
 	return 0;
 }
 
-static unsigned int netns_inum(void *ns)
-{
-	struct net *net = ns;
-	return net->proc_inum;
-}
-
 const struct proc_ns_operations netns_operations = {
 	.name		= "net",
 	.type		= CLONE_NEWNET,
 	.get		= netns_get,
 	.put		= netns_put,
 	.install	= netns_install,
-	.inum		= netns_inum,
 };
 #endif
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index e6645b4f330a..c126a878c47c 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -77,10 +77,9 @@ static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	features = netif_skb_features(skb);
 
-	if (vlan_tx_tag_present(skb) &&
+	if (skb_vlan_tag_present(skb) &&
 	    !vlan_hw_offload_capable(features, skb->vlan_proto)) {
-		skb = __vlan_put_tag(skb, skb->vlan_proto,
-				     vlan_tx_tag_get(skb));
+		skb = __vlan_hwaccel_push_inside(skb);
 		if (unlikely(!skb)) {
 			/* This is actually a packet drop, but we
 			 * don't want the code that calls this
@@ -88,7 +87,6 @@ static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev,
 			 */
 			goto out;
 		}
-		skb->vlan_tci = 0;
 	}
 
 	status = netdev_start_xmit(skb, dev, txq, false);
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 443256bdcddc..54817d365366 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -97,7 +97,7 @@
  * New xmit() return, do_div and misc clean up by Stephen Hemminger
  * <shemminger@osdl.org> 040923
  *
- * Randy Dunlap fixed u64 printk compiler waring
+ * Randy Dunlap fixed u64 printk compiler warning
  *
  * Remove FCS from BW calculation.  Lennert Buytenhek <buytenh@wantstofly.org>
  * New time handling. Lennert Buytenhek <buytenh@wantstofly.org> 041213
@@ -1134,6 +1134,9 @@ static ssize_t pktgen_if_write(struct file *file,
 			return len;
 
 		i += len;
+		if ((value > 1) &&
+		    (!(pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING)))
+			return -ENOTSUPP;
 		pkt_dev->burst = value < 1 ? 1 : value;
 		sprintf(pg_result, "OK: burst=%d", pkt_dev->burst);
 		return count;
@@ -2209,8 +2212,6 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until)
 		do {
 			set_current_state(TASK_INTERRUPTIBLE);
 			hrtimer_start_expires(&t.timer, HRTIMER_MODE_ABS);
-			if (!hrtimer_active(&t.timer))
-				t.task = NULL;
 
 			if (likely(t.task))
 				schedule();
@@ -2842,25 +2843,25 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
 	skb->dev = odev;
 	skb->pkt_type = PACKET_HOST;
 
+	pktgen_finalize_skb(pkt_dev, skb, datalen);
+
 	if (!(pkt_dev->flags & F_UDPCSUM)) {
 		skb->ip_summed = CHECKSUM_NONE;
 	} else if (odev->features & NETIF_F_V4_CSUM) {
 		skb->ip_summed = CHECKSUM_PARTIAL;
 		skb->csum = 0;
-		udp4_hwcsum(skb, udph->source, udph->dest);
+		udp4_hwcsum(skb, iph->saddr, iph->daddr);
 	} else {
-		__wsum csum = udp_csum(skb);
+		__wsum csum = skb_checksum(skb, skb_transport_offset(skb), datalen + 8, 0);
 
 		/* add protocol-dependent pseudo-header */
-		udph->check = csum_tcpudp_magic(udph->source, udph->dest,
+		udph->check = csum_tcpudp_magic(iph->saddr, iph->daddr,
 						datalen + 8, IPPROTO_UDP, csum);
 
 		if (udph->check == 0)
 			udph->check = CSUM_MANGLED_0;
 	}
 
-	pktgen_finalize_skb(pkt_dev, skb, datalen);
-
 #ifdef CONFIG_XFRM
 	if (!process_ipsec(pkt_dev, skb, protocol))
 		return NULL;
@@ -2976,6 +2977,8 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
 	skb->dev = odev;
 	skb->pkt_type = PACKET_HOST;
 
+	pktgen_finalize_skb(pkt_dev, skb, datalen);
+
 	if (!(pkt_dev->flags & F_UDPCSUM)) {
 		skb->ip_summed = CHECKSUM_NONE;
 	} else if (odev->features & NETIF_F_V6_CSUM) {
@@ -2984,7 +2987,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
 		skb->csum_offset = offsetof(struct udphdr, check);
 		udph->check = ~csum_ipv6_magic(&iph->saddr, &iph->daddr, udplen, IPPROTO_UDP, 0);
 	} else {
-		__wsum csum = udp_csum(skb);
+		__wsum csum = skb_checksum(skb, skb_transport_offset(skb), udplen, 0);
 
 		/* add protocol-dependent pseudo-header */
 		udph->check = csum_ipv6_magic(&iph->saddr, &iph->daddr, udplen, IPPROTO_UDP, csum);
@@ -2993,8 +2996,6 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
 			udph->check = CSUM_MANGLED_0;
 	}
 
-	pktgen_finalize_skb(pkt_dev, skb, datalen);
-
 	return skb;
 }
 
@@ -3728,8 +3729,7 @@ static int pktgen_remove_device(struct pktgen_thread *t,
 	/* Remove proc before if_list entry, because add_device uses
 	 * list to determine if interface already exist, avoid race
 	 * with proc_create_data() */
-	if (pkt_dev->entry)
-		proc_remove(pkt_dev->entry);
+	proc_remove(pkt_dev->entry);
 
 	/* And update the thread if_list */
 	_rem_dev_from_if_list(t, pkt_dev);
diff --git a/net/core/request_sock.c b/net/core/request_sock.c
index 04db318e6218..87b22c0bc08c 100644
--- a/net/core/request_sock.c
+++ b/net/core/request_sock.c
@@ -58,14 +58,14 @@ int reqsk_queue_alloc(struct request_sock_queue *queue,
 		return -ENOMEM;
 
 	get_random_bytes(&lopt->hash_rnd, sizeof(lopt->hash_rnd));
-	rwlock_init(&queue->syn_wait_lock);
+	spin_lock_init(&queue->syn_wait_lock);
 	queue->rskq_accept_head = NULL;
 	lopt->nr_table_entries = nr_table_entries;
 	lopt->max_qlen_log = ilog2(nr_table_entries);
 
-	write_lock_bh(&queue->syn_wait_lock);
+	spin_lock_bh(&queue->syn_wait_lock);
 	queue->listen_opt = lopt;
-	write_unlock_bh(&queue->syn_wait_lock);
+	spin_unlock_bh(&queue->syn_wait_lock);
 
 	return 0;
 }
@@ -81,10 +81,10 @@ static inline struct listen_sock *reqsk_queue_yank_listen_sk(
 {
 	struct listen_sock *lopt;
 
-	write_lock_bh(&queue->syn_wait_lock);
+	spin_lock_bh(&queue->syn_wait_lock);
 	lopt = queue->listen_opt;
 	queue->listen_opt = NULL;
-	write_unlock_bh(&queue->syn_wait_lock);
+	spin_unlock_bh(&queue->syn_wait_lock);
 
 	return lopt;
 }
@@ -94,21 +94,26 @@ void reqsk_queue_destroy(struct request_sock_queue *queue)
 	/* make all the listen_opt local to us */
 	struct listen_sock *lopt = reqsk_queue_yank_listen_sk(queue);
 
-	if (lopt->qlen != 0) {
+	if (listen_sock_qlen(lopt) != 0) {
 		unsigned int i;
 
 		for (i = 0; i < lopt->nr_table_entries; i++) {
 			struct request_sock *req;
 
+			spin_lock_bh(&queue->syn_wait_lock);
 			while ((req = lopt->syn_table[i]) != NULL) {
 				lopt->syn_table[i] = req->dl_next;
-				lopt->qlen--;
-				reqsk_free(req);
+				atomic_inc(&lopt->qlen_dec);
+				if (del_timer(&req->rsk_timer))
+					reqsk_put(req);
+				reqsk_put(req);
 			}
+			spin_unlock_bh(&queue->syn_wait_lock);
 		}
 	}
 
-	WARN_ON(lopt->qlen != 0);
+	if (WARN_ON(listen_sock_qlen(lopt) != 0))
+		pr_err("qlen %u\n", listen_sock_qlen(lopt));
 	kvfree(lopt);
 }
 
@@ -153,24 +158,22 @@ void reqsk_queue_destroy(struct request_sock_queue *queue)
  * case might also exist in tcp_v4_hnd_req() that will trigger this locking
  * order.
  *
- * When a TFO req is created, it needs to sock_hold its listener to prevent
- * the latter data structure from going away.
- *
- * This function also sets "treq->listener" to NULL and unreference listener
- * socket. treq->listener is used by the listener so it is protected by the
+ * This function also sets "treq->tfo_listener" to false.
+ * treq->tfo_listener is used by the listener so it is protected by the
  * fastopenq->lock in this function.
  */
 void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req,
 			   bool reset)
 {
-	struct sock *lsk = tcp_rsk(req)->listener;
-	struct fastopen_queue *fastopenq =
-	    inet_csk(lsk)->icsk_accept_queue.fastopenq;
+	struct sock *lsk = req->rsk_listener;
+	struct fastopen_queue *fastopenq;
+
+	fastopenq = inet_csk(lsk)->icsk_accept_queue.fastopenq;
 
 	tcp_sk(sk)->fastopen_rsk = NULL;
 	spin_lock_bh(&fastopenq->lock);
 	fastopenq->qlen--;
-	tcp_rsk(req)->listener = NULL;
+	tcp_rsk(req)->tfo_listener = false;
 	if (req->sk)	/* the child socket hasn't been accepted yet */
 		goto out;
 
@@ -179,8 +182,7 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req,
 		 * special RST handling below.
 		 */
 		spin_unlock_bh(&fastopenq->lock);
-		sock_put(lsk);
-		reqsk_free(req);
+		reqsk_put(req);
 		return;
 	}
 	/* Wait for 60secs before removing a req that has triggered RST.
@@ -190,7 +192,7 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req,
 	 *
 	 * For more details see CoNext'11 "TCP Fast Open" paper.
 	 */
-	req->expires = jiffies + 60*HZ;
+	req->rsk_timer.expires = jiffies + 60*HZ;
 	if (fastopenq->rskq_rst_head == NULL)
 		fastopenq->rskq_rst_head = req;
 	else
@@ -201,5 +203,4 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req,
 	fastopenq->qlen++;
 out:
 	spin_unlock_bh(&fastopenq->lock);
-	sock_put(lsk);
 }
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index a6882686ca3a..8de36824018d 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -36,6 +36,7 @@
 #include <linux/mutex.h>
 #include <linux/if_addr.h>
 #include <linux/if_bridge.h>
+#include <linux/if_vlan.h>
 #include <linux/pci.h>
 #include <linux/etherdevice.h>
 
@@ -43,11 +44,13 @@
 
 #include <linux/inet.h>
 #include <linux/netdevice.h>
+#include <net/switchdev.h>
 #include <net/ip.h>
 #include <net/protocol.h>
 #include <net/arp.h>
 #include <net/route.h>
 #include <net/udp.h>
+#include <net/tcp.h>
 #include <net/sock.h>
 #include <net/pkt_sched.h>
 #include <net/fib_rules.h>
@@ -365,11 +368,10 @@ static void rtnl_lock_unregistering_all(void)
 {
 	struct net *net;
 	bool unregistering;
-	DEFINE_WAIT(wait);
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
+	add_wait_queue(&netdev_unregistering_wq, &wait);
 	for (;;) {
-		prepare_to_wait(&netdev_unregistering_wq, &wait,
-				TASK_UNINTERRUPTIBLE);
 		unregistering = false;
 		rtnl_lock();
 		for_each_net(net) {
@@ -381,9 +383,10 @@ static void rtnl_lock_unregistering_all(void)
 		if (!unregistering)
 			break;
 		__rtnl_unlock();
-		schedule();
+
+		wait_woken(&wait, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
 	}
-	finish_wait(&netdev_unregistering_wq, &wait);
+	remove_wait_queue(&netdev_unregistering_wq, &wait);
 }
 
 /**
@@ -667,9 +670,19 @@ int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics)
 
 	for (i = 0; i < RTAX_MAX; i++) {
 		if (metrics[i]) {
+			if (i == RTAX_CC_ALGO - 1) {
+				char tmp[TCP_CA_NAME_MAX], *name;
+
+				name = tcp_ca_get_name_by_key(metrics[i], tmp);
+				if (!name)
+					continue;
+				if (nla_put_string(skb, i + 1, name))
+					goto nla_put_failure;
+			} else {
+				if (nla_put_u32(skb, i + 1, metrics[i]))
+					goto nla_put_failure;
+			}
 			valid++;
-			if (nla_put_u32(skb, i+1, metrics[i]))
-				goto nla_put_failure;
 		}
 	}
 
@@ -805,7 +818,8 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev,
 			 nla_total_size(sizeof(struct ifla_vf_vlan)) +
 			 nla_total_size(sizeof(struct ifla_vf_spoofchk)) +
 			 nla_total_size(sizeof(struct ifla_vf_rate)) +
-			 nla_total_size(sizeof(struct ifla_vf_link_state)));
+			 nla_total_size(sizeof(struct ifla_vf_link_state)) +
+			 nla_total_size(sizeof(struct ifla_vf_rss_query_en)));
 		return size;
 	} else
 		return 0;
@@ -862,13 +876,15 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + nla_total_size(1) /* IFLA_OPERSTATE */
 	       + nla_total_size(1) /* IFLA_LINKMODE */
 	       + nla_total_size(4) /* IFLA_CARRIER_CHANGES */
+	       + nla_total_size(4) /* IFLA_LINK_NETNSID */
 	       + 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, 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 */
+	       + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_PORT_ID */
+	       + nla_total_size(MAX_PHYS_ITEM_ID_LEN); /* IFLA_PHYS_SWITCH_ID */
 }
 
 static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev)
@@ -952,7 +968,7 @@ static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev,
 static int rtnl_phys_port_id_fill(struct sk_buff *skb, struct net_device *dev)
 {
 	int err;
-	struct netdev_phys_port_id ppid;
+	struct netdev_phys_item_id ppid;
 
 	err = dev_get_phys_port_id(dev, &ppid);
 	if (err) {
@@ -967,6 +983,42 @@ static int rtnl_phys_port_id_fill(struct sk_buff *skb, struct net_device *dev)
 	return 0;
 }
 
+static int rtnl_phys_port_name_fill(struct sk_buff *skb, struct net_device *dev)
+{
+	char name[IFNAMSIZ];
+	int err;
+
+	err = dev_get_phys_port_name(dev, name, sizeof(name));
+	if (err) {
+		if (err == -EOPNOTSUPP)
+			return 0;
+		return err;
+	}
+
+	if (nla_put(skb, IFLA_PHYS_PORT_NAME, strlen(name), name))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev)
+{
+	int err;
+	struct netdev_phys_item_id psid;
+
+	err = netdev_switch_parent_id_get(dev, &psid);
+	if (err) {
+		if (err == -EOPNOTSUPP)
+			return 0;
+		return err;
+	}
+
+	if (nla_put(skb, IFLA_PHYS_SWITCH_ID, psid.id_len, psid.id))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
 static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			    int type, u32 pid, u32 seq, u32 change,
 			    unsigned int flags, u32 ext_filter_mask)
@@ -1004,8 +1056,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 #ifdef CONFIG_RPS
 	    nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) ||
 #endif
-	    (dev->ifindex != dev->iflink &&
-	     nla_put_u32(skb, IFLA_LINK, dev->iflink)) ||
+	    (dev->ifindex != dev_get_iflink(dev) &&
+	     nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev))) ||
 	    (upper_dev &&
 	     nla_put_u32(skb, IFLA_MASTER, upper_dev->ifindex)) ||
 	    nla_put_u8(skb, IFLA_CARRIER, netif_carrier_ok(dev)) ||
@@ -1039,6 +1091,12 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 	if (rtnl_phys_port_id_fill(skb, dev))
 		goto nla_put_failure;
 
+	if (rtnl_phys_port_name_fill(skb, dev))
+		goto nla_put_failure;
+
+	if (rtnl_phys_switch_id_fill(skb, dev))
+		goto nla_put_failure;
+
 	attr = nla_reserve(skb, IFLA_STATS,
 			sizeof(struct rtnl_link_stats));
 	if (attr == NULL)
@@ -1075,14 +1133,16 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			struct ifla_vf_tx_rate vf_tx_rate;
 			struct ifla_vf_spoofchk vf_spoofchk;
 			struct ifla_vf_link_state vf_linkstate;
+			struct ifla_vf_rss_query_en vf_rss_query_en;
 
 			/*
 			 * Not all SR-IOV capable drivers support the
-			 * spoofcheck query.  Preset to -1 so the user
-			 * space tool can detect that the driver didn't
-			 * report anything.
+			 * spoofcheck and "RSS query enable" query.  Preset to
+			 * -1 so the user space tool can detect that the driver
+			 * didn't report anything.
 			 */
 			ivi.spoofchk = -1;
+			ivi.rss_query_en = -1;
 			memset(ivi.mac, 0, sizeof(ivi.mac));
 			/* The default value for VF link state is "auto"
 			 * IFLA_VF_LINK_STATE_AUTO which equals zero
@@ -1095,7 +1155,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 				vf_rate.vf =
 				vf_tx_rate.vf =
 				vf_spoofchk.vf =
-				vf_linkstate.vf = ivi.vf;
+				vf_linkstate.vf =
+				vf_rss_query_en.vf = ivi.vf;
 
 			memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac));
 			vf_vlan.vlan = ivi.vlan;
@@ -1105,6 +1166,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			vf_rate.max_tx_rate = ivi.max_tx_rate;
 			vf_spoofchk.setting = ivi.spoofchk;
 			vf_linkstate.link_state = ivi.linkstate;
+			vf_rss_query_en.setting = ivi.rss_query_en;
 			vf = nla_nest_start(skb, IFLA_VF_INFO);
 			if (!vf) {
 				nla_nest_cancel(skb, vfinfo);
@@ -1119,7 +1181,10 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			    nla_put(skb, IFLA_VF_SPOOFCHK, sizeof(vf_spoofchk),
 				    &vf_spoofchk) ||
 			    nla_put(skb, IFLA_VF_LINK_STATE, sizeof(vf_linkstate),
-				    &vf_linkstate))
+				    &vf_linkstate) ||
+			    nla_put(skb, IFLA_VF_RSS_QUERY_EN,
+				    sizeof(vf_rss_query_en),
+				    &vf_rss_query_en))
 				goto nla_put_failure;
 			nla_nest_end(skb, vf);
 		}
@@ -1134,6 +1199,18 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			goto nla_put_failure;
 	}
 
+	if (dev->rtnl_link_ops &&
+	    dev->rtnl_link_ops->get_link_net) {
+		struct net *link_net = dev->rtnl_link_ops->get_link_net(dev);
+
+		if (!net_eq(dev_net(dev), link_net)) {
+			int id = peernet2id(dev_net(dev), link_net);
+
+			if (nla_put_s32(skb, IFLA_LINK_NETNSID, id))
+				goto nla_put_failure;
+		}
+	}
+
 	if (!(af_spec = nla_nest_start(skb, IFLA_AF_SPEC)))
 		goto nla_put_failure;
 
@@ -1164,7 +1241,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 
 	nla_nest_end(skb, af_spec);
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
@@ -1196,8 +1274,10 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_PROMISCUITY]	= { .type = NLA_U32 },
 	[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_PHYS_PORT_ID]	= { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN },
 	[IFLA_CARRIER_CHANGES]	= { .type = NLA_U32 },  /* ignored */
+	[IFLA_PHYS_SWITCH_ID]	= { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN },
+	[IFLA_LINK_NETNSID]	= { .type = NLA_S32 },
 };
 
 static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
@@ -1212,18 +1292,13 @@ static const struct nla_policy ifla_vfinfo_policy[IFLA_VF_INFO_MAX+1] = {
 };
 
 static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = {
-	[IFLA_VF_MAC]		= { .type = NLA_BINARY,
-				    .len = sizeof(struct ifla_vf_mac) },
-	[IFLA_VF_VLAN]		= { .type = NLA_BINARY,
-				    .len = sizeof(struct ifla_vf_vlan) },
-	[IFLA_VF_TX_RATE]	= { .type = NLA_BINARY,
-				    .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) },
+	[IFLA_VF_MAC]		= { .len = sizeof(struct ifla_vf_mac) },
+	[IFLA_VF_VLAN]		= { .len = sizeof(struct ifla_vf_vlan) },
+	[IFLA_VF_TX_RATE]	= { .len = sizeof(struct ifla_vf_tx_rate) },
+	[IFLA_VF_SPOOFCHK]	= { .len = sizeof(struct ifla_vf_spoofchk) },
+	[IFLA_VF_RATE]		= { .len = sizeof(struct ifla_vf_rate) },
+	[IFLA_VF_LINK_STATE]	= { .len = sizeof(struct ifla_vf_link_state) },
+	[IFLA_VF_RSS_QUERY_EN]	= { .len = sizeof(struct ifla_vf_rss_query_en) },
 };
 
 static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = {
@@ -1255,7 +1330,6 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 	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.
@@ -1277,7 +1351,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 	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) {
+		hlist_for_each_entry(dev, head, index_hlist) {
 			if (idx < s_idx)
 				goto cont;
 			err = rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
@@ -1290,7 +1364,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 			 */
 			WARN_ON((err == -EMSGSIZE) && (skb->len == 0));
 
-			if (err <= 0)
+			if (err < 0)
 				goto out;
 
 			nl_dump_check_consistent(cb, nlmsg_hdr(skb));
@@ -1299,7 +1373,6 @@ cont:
 		}
 	}
 out:
-	rcu_read_unlock();
 	cb->args[1] = idx;
 	cb->args[0] = h;
 
@@ -1436,6 +1509,17 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr *attr)
 								 ivl->link_state);
 			break;
 		}
+		case IFLA_VF_RSS_QUERY_EN: {
+			struct ifla_vf_rss_query_en *ivrssq_en;
+
+			ivrssq_en = nla_data(vf);
+			err = -EOPNOTSUPP;
+			if (ops->ndo_set_vf_rss_query_en)
+				err = ops->ndo_set_vf_rss_query_en(dev,
+							    ivrssq_en->vf,
+							    ivrssq_en->setting);
+			break;
+		}
 		default:
 			err = -EINVAL;
 			break;
@@ -1498,6 +1582,7 @@ static int do_setlink(const struct sk_buff *skb,
 			goto errout;
 		}
 		if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) {
+			put_net(net);
 			err = -EPERM;
 			goto errout;
 		}
@@ -1771,6 +1856,42 @@ errout:
 	return err;
 }
 
+static int rtnl_group_dellink(const struct net *net, int group)
+{
+	struct net_device *dev, *aux;
+	LIST_HEAD(list_kill);
+	bool found = false;
+
+	if (!group)
+		return -EPERM;
+
+	for_each_netdev(net, dev) {
+		if (dev->group == group) {
+			const struct rtnl_link_ops *ops;
+
+			found = true;
+			ops = dev->rtnl_link_ops;
+			if (!ops || !ops->dellink)
+				return -EOPNOTSUPP;
+		}
+	}
+
+	if (!found)
+		return -ENODEV;
+
+	for_each_netdev_safe(net, dev, aux) {
+		if (dev->group == group) {
+			const struct rtnl_link_ops *ops;
+
+			ops = dev->rtnl_link_ops;
+			ops->dellink(dev, &list_kill);
+		}
+	}
+	unregister_netdevice_many(&list_kill);
+
+	return 0;
+}
+
 static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
@@ -1794,6 +1915,8 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
 		dev = __dev_get_by_index(net, ifm->ifi_index);
 	else if (tb[IFLA_IFNAME])
 		dev = __dev_get_by_name(net, ifname);
+	else if (tb[IFLA_GROUP])
+		return rtnl_group_dellink(net, nla_get_u32(tb[IFLA_GROUP]));
 	else
 		return -EINVAL;
 
@@ -1829,7 +1952,7 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm)
 EXPORT_SYMBOL(rtnl_configure_link);
 
 struct net_device *rtnl_create_link(struct net *net,
-	char *ifname, unsigned char name_assign_type,
+	const char *ifname, unsigned char name_assign_type,
 	const struct rtnl_link_ops *ops, struct nlattr *tb[])
 {
 	int err;
@@ -1888,10 +2011,10 @@ static int rtnl_group_changelink(const struct sk_buff *skb,
 		struct ifinfomsg *ifm,
 		struct nlattr **tb)
 {
-	struct net_device *dev;
+	struct net_device *dev, *aux;
 	int err;
 
-	for_each_netdev(net, dev) {
+	for_each_netdev_safe(net, dev, aux) {
 		if (dev->group == group) {
 			err = do_setlink(skb, dev, ifm, tb, NULL, 0);
 			if (err < 0)
@@ -1966,11 +2089,11 @@ replay:
 	}
 
 	if (1) {
-		struct nlattr *attr[ops ? ops->maxtype + 1 : 0];
-		struct nlattr *slave_attr[m_ops ? m_ops->slave_maxtype + 1 : 0];
+		struct nlattr *attr[ops ? ops->maxtype + 1 : 1];
+		struct nlattr *slave_attr[m_ops ? m_ops->slave_maxtype + 1 : 1];
 		struct nlattr **data = NULL;
 		struct nlattr **slave_data = NULL;
-		struct net *dest_net;
+		struct net *dest_net, *link_net = NULL;
 
 		if (ops) {
 			if (ops->maxtype && linkinfo[IFLA_INFO_DATA]) {
@@ -2076,7 +2199,25 @@ replay:
 		if (IS_ERR(dest_net))
 			return PTR_ERR(dest_net);
 
-		dev = rtnl_create_link(dest_net, ifname, name_assign_type, ops, tb);
+		err = -EPERM;
+		if (!netlink_ns_capable(skb, dest_net->user_ns, CAP_NET_ADMIN))
+			goto out;
+
+		if (tb[IFLA_LINK_NETNSID]) {
+			int id = nla_get_s32(tb[IFLA_LINK_NETNSID]);
+
+			link_net = get_net_ns_by_id(dest_net, id);
+			if (!link_net) {
+				err =  -EINVAL;
+				goto out;
+			}
+			err = -EPERM;
+			if (!netlink_ns_capable(skb, link_net->user_ns, CAP_NET_ADMIN))
+				goto out;
+		}
+
+		dev = rtnl_create_link(link_net ? : dest_net, ifname,
+				       name_assign_type, ops, tb);
 		if (IS_ERR(dev)) {
 			err = PTR_ERR(dev);
 			goto out;
@@ -2085,7 +2226,7 @@ replay:
 		dev->ifindex = ifm->ifi_index;
 
 		if (ops->newlink) {
-			err = ops->newlink(net, dev, tb, data);
+			err = ops->newlink(link_net ? : net, dev, tb, data);
 			/* Drivers should call free_netdev() in ->destructor
 			 * and unregister it on failure after registration
 			 * so that device could be finally freed in rtnl_unlock.
@@ -2105,10 +2246,27 @@ replay:
 		}
 		err = rtnl_configure_link(dev, ifm);
 		if (err < 0)
-			unregister_netdevice(dev);
+			goto out_unregister;
+		if (link_net) {
+			err = dev_change_net_namespace(dev, dest_net, ifname);
+			if (err < 0)
+				goto out_unregister;
+		}
 out:
+		if (link_net)
+			put_net(link_net);
 		put_net(dest_net);
 		return err;
+out_unregister:
+		if (ops->newlink) {
+			LIST_HEAD(list_kill);
+
+			ops->dellink(dev, &list_kill);
+			unregister_netdevice_many(&list_kill);
+		} else {
+			unregister_netdevice(dev);
+		}
+		goto out;
 	}
 }
 
@@ -2220,8 +2378,8 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
-void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change,
-		  gfp_t flags)
+struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
+				       unsigned int change, gfp_t flags)
 {
 	struct net *net = dev_net(dev);
 	struct sk_buff *skb;
@@ -2239,17 +2397,37 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change,
 		kfree_skb(skb);
 		goto errout;
 	}
-	rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, flags);
-	return;
+	return skb;
 errout:
 	if (err < 0)
 		rtnl_set_sk_err(net, RTNLGRP_LINK, err);
+	return NULL;
+}
+
+void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags)
+{
+	struct net *net = dev_net(dev);
+
+	rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, flags);
+}
+
+void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change,
+		  gfp_t flags)
+{
+	struct sk_buff *skb;
+
+	if (dev->reg_state != NETREG_REGISTERED)
+		return;
+
+	skb = rtmsg_ifinfo_build_skb(type, dev, change, flags);
+	if (skb)
+		rtmsg_ifinfo_send(skb, dev, flags);
 }
 EXPORT_SYMBOL(rtmsg_ifinfo);
 
 static int nlmsg_populate_fdb_fill(struct sk_buff *skb,
 				   struct net_device *dev,
-				   u8 *addr, u32 pid, u32 seq,
+				   u8 *addr, u16 vid, u32 pid, u32 seq,
 				   int type, unsigned int flags,
 				   int nlflags)
 {
@@ -2271,8 +2449,12 @@ static int nlmsg_populate_fdb_fill(struct sk_buff *skb,
 
 	if (nla_put(skb, NDA_LLADDR, ETH_ALEN, addr))
 		goto nla_put_failure;
+	if (vid)
+		if (nla_put(skb, NDA_VLAN, sizeof(u16), &vid))
+			goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
@@ -2284,7 +2466,7 @@ static inline size_t rtnl_fdb_nlmsg_size(void)
 	return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN);
 }
 
-static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, int type)
+static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, u16 vid, int type)
 {
 	struct net *net = dev_net(dev);
 	struct sk_buff *skb;
@@ -2294,7 +2476,8 @@ 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, 0);
+	err = nlmsg_populate_fdb_fill(skb, dev, addr, vid,
+				      0, 0, type, NTF_SELF, 0);
 	if (err < 0) {
 		kfree_skb(skb);
 		goto errout;
@@ -2312,7 +2495,7 @@ errout:
 int ndo_dflt_fdb_add(struct ndmsg *ndm,
 		     struct nlattr *tb[],
 		     struct net_device *dev,
-		     const unsigned char *addr,
+		     const unsigned char *addr, u16 vid,
 		     u16 flags)
 {
 	int err = -EINVAL;
@@ -2325,6 +2508,11 @@ int ndo_dflt_fdb_add(struct ndmsg *ndm,
 		return err;
 	}
 
+	if (vid) {
+		pr_info("%s: vlans aren't supported yet for dev_uc|mc_add()\n", dev->name);
+		return err;
+	}
+
 	if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr))
 		err = dev_uc_add_excl(dev, addr);
 	else if (is_multicast_ether_addr(addr))
@@ -2338,6 +2526,28 @@ int ndo_dflt_fdb_add(struct ndmsg *ndm,
 }
 EXPORT_SYMBOL(ndo_dflt_fdb_add);
 
+static int fdb_vid_parse(struct nlattr *vlan_attr, u16 *p_vid)
+{
+	u16 vid = 0;
+
+	if (vlan_attr) {
+		if (nla_len(vlan_attr) != sizeof(u16)) {
+			pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid vlan\n");
+			return -EINVAL;
+		}
+
+		vid = nla_get_u16(vlan_attr);
+
+		if (!vid || vid >= VLAN_VID_MASK) {
+			pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid vlan id %d\n",
+				vid);
+			return -EINVAL;
+		}
+	}
+	*p_vid = vid;
+	return 0;
+}
+
 static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
@@ -2345,6 +2555,7 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct nlattr *tb[NDA_MAX+1];
 	struct net_device *dev;
 	u8 *addr;
+	u16 vid;
 	int err;
 
 	err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL);
@@ -2370,6 +2581,10 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	addr = nla_data(tb[NDA_LLADDR]);
 
+	err = fdb_vid_parse(tb[NDA_VLAN], &vid);
+	if (err)
+		return err;
+
 	err = -EOPNOTSUPP;
 
 	/* Support fdb on master device the net/bridge default case */
@@ -2378,7 +2593,8 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 		struct net_device *br_dev = netdev_master_upper_dev_get(dev);
 		const struct net_device_ops *ops = br_dev->netdev_ops;
 
-		err = ops->ndo_fdb_add(ndm, tb, dev, addr, nlh->nlmsg_flags);
+		err = ops->ndo_fdb_add(ndm, tb, dev, addr, vid,
+				       nlh->nlmsg_flags);
 		if (err)
 			goto out;
 		else
@@ -2389,13 +2605,14 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if ((ndm->ndm_flags & NTF_SELF)) {
 		if (dev->netdev_ops->ndo_fdb_add)
 			err = dev->netdev_ops->ndo_fdb_add(ndm, tb, dev, addr,
+							   vid,
 							   nlh->nlmsg_flags);
 		else
-			err = ndo_dflt_fdb_add(ndm, tb, dev, addr,
+			err = ndo_dflt_fdb_add(ndm, tb, dev, addr, vid,
 					       nlh->nlmsg_flags);
 
 		if (!err) {
-			rtnl_fdb_notify(dev, addr, RTM_NEWNEIGH);
+			rtnl_fdb_notify(dev, addr, vid, RTM_NEWNEIGH);
 			ndm->ndm_flags &= ~NTF_SELF;
 		}
 	}
@@ -2409,7 +2626,7 @@ out:
 int ndo_dflt_fdb_del(struct ndmsg *ndm,
 		     struct nlattr *tb[],
 		     struct net_device *dev,
-		     const unsigned char *addr)
+		     const unsigned char *addr, u16 vid)
 {
 	int err = -EINVAL;
 
@@ -2438,6 +2655,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct net_device *dev;
 	int err = -EINVAL;
 	__u8 *addr;
+	u16 vid;
 
 	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
@@ -2465,6 +2683,10 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	addr = nla_data(tb[NDA_LLADDR]);
 
+	err = fdb_vid_parse(tb[NDA_VLAN], &vid);
+	if (err)
+		return err;
+
 	err = -EOPNOTSUPP;
 
 	/* Support fdb on master device the net/bridge default case */
@@ -2474,7 +2696,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
 		const struct net_device_ops *ops = br_dev->netdev_ops;
 
 		if (ops->ndo_fdb_del)
-			err = ops->ndo_fdb_del(ndm, tb, dev, addr);
+			err = ops->ndo_fdb_del(ndm, tb, dev, addr, vid);
 
 		if (err)
 			goto out;
@@ -2485,12 +2707,13 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
 	/* Embedded bridge, macvlan, and any other device support */
 	if (ndm->ndm_flags & NTF_SELF) {
 		if (dev->netdev_ops->ndo_fdb_del)
-			err = dev->netdev_ops->ndo_fdb_del(ndm, tb, dev, addr);
+			err = dev->netdev_ops->ndo_fdb_del(ndm, tb, dev, addr,
+							   vid);
 		else
-			err = ndo_dflt_fdb_del(ndm, tb, dev, addr);
+			err = ndo_dflt_fdb_del(ndm, tb, dev, addr, vid);
 
 		if (!err) {
-			rtnl_fdb_notify(dev, addr, RTM_DELNEIGH);
+			rtnl_fdb_notify(dev, addr, vid, RTM_DELNEIGH);
 			ndm->ndm_flags &= ~NTF_SELF;
 		}
 	}
@@ -2515,7 +2738,7 @@ static int nlmsg_populate_fdb(struct sk_buff *skb,
 		if (*idx < cb->args[0])
 			goto skip;
 
-		err = nlmsg_populate_fdb_fill(skb, dev, ha->addr,
+		err = nlmsg_populate_fdb_fill(skb, dev, ha->addr, 0,
 					      portid, seq,
 					      RTM_NEWNEIGH, NTF_SELF,
 					      NLM_F_MULTI);
@@ -2558,7 +2781,6 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct net_device *dev;
 	struct nlattr *tb[IFLA_MAX+1];
-	struct net_device *bdev = NULL;
 	struct net_device *br_dev = NULL;
 	const struct net_device_ops *ops = NULL;
 	const struct net_device_ops *cops = NULL;
@@ -2582,7 +2804,6 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
 			return -ENODEV;
 
 		ops = br_dev->netdev_ops;
-		bdev = br_dev;
 	}
 
 	for_each_netdev(net, dev) {
@@ -2595,7 +2816,6 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
 				cops = br_dev->netdev_ops;
 			}
 
-			bdev = dev;
 		} else {
 			if (dev != br_dev &&
 			    !(dev->priv_flags & IFF_BRIDGE_PORT))
@@ -2605,7 +2825,6 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
 			    !(dev->priv_flags & IFF_EBRIDGE))
 				continue;
 
-			bdev = br_dev;
 			cops = ops;
 		}
 
@@ -2615,10 +2834,11 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
 							 idx);
 		}
 
-		idx = ndo_dflt_fdb_dump(skb, cb, dev, NULL, idx);
 		if (dev->netdev_ops->ndo_fdb_dump)
-			idx = dev->netdev_ops->ndo_fdb_dump(skb, cb, bdev, dev,
+			idx = dev->netdev_ops->ndo_fdb_dump(skb, cb, dev, NULL,
 							    idx);
+		else
+			idx = ndo_dflt_fdb_dump(skb, cb, dev, NULL, idx);
 
 		cops = NULL;
 	}
@@ -2627,16 +2847,26 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
+static int brport_nla_put_flag(struct sk_buff *skb, u32 flags, u32 mask,
+			       unsigned int attrnum, unsigned int flag)
+{
+	if (mask & flag)
+		return nla_put_u8(skb, attrnum, !!(flags & flag));
+	return 0;
+}
+
 int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
-			    struct net_device *dev, u16 mode)
+			    struct net_device *dev, u16 mode,
+			    u32 flags, u32 mask, int nlflags)
 {
 	struct nlmsghdr *nlh;
 	struct ifinfomsg *ifm;
 	struct nlattr *br_afspec;
+	struct nlattr *protinfo;
 	u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN;
 	struct net_device *br_dev = netdev_master_upper_dev_get(dev);
 
-	nlh = nlmsg_put(skb, pid, seq, RTM_NEWLINK, sizeof(*ifm), NLM_F_MULTI);
+	nlh = nlmsg_put(skb, pid, seq, RTM_NEWLINK, sizeof(*ifm), nlflags);
 	if (nlh == NULL)
 		return -EMSGSIZE;
 
@@ -2656,22 +2886,56 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 	     nla_put_u32(skb, IFLA_MASTER, br_dev->ifindex)) ||
 	    (dev->addr_len &&
 	     nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) ||
-	    (dev->ifindex != dev->iflink &&
-	     nla_put_u32(skb, IFLA_LINK, dev->iflink)))
+	    (dev->ifindex != dev_get_iflink(dev) &&
+	     nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev))))
 		goto nla_put_failure;
 
 	br_afspec = nla_nest_start(skb, IFLA_AF_SPEC);
 	if (!br_afspec)
 		goto nla_put_failure;
 
-	if (nla_put_u16(skb, IFLA_BRIDGE_FLAGS, BRIDGE_FLAGS_SELF) ||
-	    nla_put_u16(skb, IFLA_BRIDGE_MODE, mode)) {
+	if (nla_put_u16(skb, IFLA_BRIDGE_FLAGS, BRIDGE_FLAGS_SELF)) {
 		nla_nest_cancel(skb, br_afspec);
 		goto nla_put_failure;
 	}
+
+	if (mode != BRIDGE_MODE_UNDEF) {
+		if (nla_put_u16(skb, IFLA_BRIDGE_MODE, mode)) {
+			nla_nest_cancel(skb, br_afspec);
+			goto nla_put_failure;
+		}
+	}
 	nla_nest_end(skb, br_afspec);
 
-	return nlmsg_end(skb, nlh);
+	protinfo = nla_nest_start(skb, IFLA_PROTINFO | NLA_F_NESTED);
+	if (!protinfo)
+		goto nla_put_failure;
+
+	if (brport_nla_put_flag(skb, flags, mask,
+				IFLA_BRPORT_MODE, BR_HAIRPIN_MODE) ||
+	    brport_nla_put_flag(skb, flags, mask,
+				IFLA_BRPORT_GUARD, BR_BPDU_GUARD) ||
+	    brport_nla_put_flag(skb, flags, mask,
+				IFLA_BRPORT_FAST_LEAVE,
+				BR_MULTICAST_FAST_LEAVE) ||
+	    brport_nla_put_flag(skb, flags, mask,
+				IFLA_BRPORT_PROTECT, BR_ROOT_BLOCK) ||
+	    brport_nla_put_flag(skb, flags, mask,
+				IFLA_BRPORT_LEARNING, BR_LEARNING) ||
+	    brport_nla_put_flag(skb, flags, mask,
+				IFLA_BRPORT_LEARNING_SYNC, BR_LEARNING_SYNC) ||
+	    brport_nla_put_flag(skb, flags, mask,
+				IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD) ||
+	    brport_nla_put_flag(skb, flags, mask,
+				IFLA_BRPORT_PROXYARP, BR_PROXYARP)) {
+		nla_nest_cancel(skb, protinfo);
+		goto nla_put_failure;
+	}
+
+	nla_nest_end(skb, protinfo);
+
+	nlmsg_end(skb, nlh);
+	return 0;
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
 	return -EMSGSIZE;
@@ -2685,13 +2949,20 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb)
 	int idx = 0;
 	u32 portid = NETLINK_CB(cb->skb).portid;
 	u32 seq = cb->nlh->nlmsg_seq;
-	struct nlattr *extfilt;
 	u32 filter_mask = 0;
 
-	extfilt = nlmsg_find_attr(cb->nlh, sizeof(struct ifinfomsg),
-				  IFLA_EXT_MASK);
-	if (extfilt)
-		filter_mask = nla_get_u32(extfilt);
+	if (nlmsg_len(cb->nlh) > sizeof(struct ifinfomsg)) {
+		struct nlattr *extfilt;
+
+		extfilt = nlmsg_find_attr(cb->nlh, sizeof(struct ifinfomsg),
+					  IFLA_EXT_MASK);
+		if (extfilt) {
+			if (nla_len(extfilt) < sizeof(filter_mask))
+				return -EINVAL;
+
+			filter_mask = nla_get_u32(extfilt);
+		}
+	}
 
 	rcu_read_lock();
 	for_each_netdev_rcu(net, dev) {
@@ -2701,7 +2972,8 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb)
 		if (br_dev && br_dev->netdev_ops->ndo_bridge_getlink) {
 			if (idx >= cb->args[0] &&
 			    br_dev->netdev_ops->ndo_bridge_getlink(
-				    skb, portid, seq, dev, filter_mask) < 0)
+				    skb, portid, seq, dev, filter_mask,
+				    NLM_F_MULTI) < 0)
 				break;
 			idx++;
 		}
@@ -2709,7 +2981,8 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb)
 		if (ops->ndo_bridge_getlink) {
 			if (idx >= cb->args[0] &&
 			    ops->ndo_bridge_getlink(skb, portid, seq, dev,
-						    filter_mask) < 0)
+						    filter_mask,
+						    NLM_F_MULTI) < 0)
 				break;
 			idx++;
 		}
@@ -2735,39 +3008,35 @@ static inline size_t bridge_nlmsg_size(void)
 		+ nla_total_size(sizeof(u16));	/* IFLA_BRIDGE_MODE */
 }
 
-static int rtnl_bridge_notify(struct net_device *dev, u16 flags)
+static int rtnl_bridge_notify(struct net_device *dev)
 {
 	struct net *net = dev_net(dev);
-	struct net_device *br_dev = netdev_master_upper_dev_get(dev);
 	struct sk_buff *skb;
 	int err = -EOPNOTSUPP;
 
+	if (!dev->netdev_ops->ndo_bridge_getlink)
+		return 0;
+
 	skb = nlmsg_new(bridge_nlmsg_size(), GFP_ATOMIC);
 	if (!skb) {
 		err = -ENOMEM;
 		goto errout;
 	}
 
-	if ((!flags || (flags & BRIDGE_FLAGS_MASTER)) &&
-	    br_dev && br_dev->netdev_ops->ndo_bridge_getlink) {
-		err = br_dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev, 0);
-		if (err < 0)
-			goto errout;
-	}
+	err = dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev, 0, 0);
+	if (err < 0)
+		goto errout;
 
-	if ((flags & BRIDGE_FLAGS_SELF) &&
-	    dev->netdev_ops->ndo_bridge_getlink) {
-		err = dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev, 0);
-		if (err < 0)
-			goto errout;
-	}
+	if (!skb->len)
+		goto errout;
 
 	rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC);
 	return 0;
 errout:
 	WARN_ON(err == -EMSGSIZE);
 	kfree_skb(skb);
-	rtnl_set_sk_err(net, RTNLGRP_LINK, err);
+	if (err)
+		rtnl_set_sk_err(net, RTNLGRP_LINK, err);
 	return err;
 }
 
@@ -2778,7 +3047,7 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct net_device *dev;
 	struct nlattr *br_spec, *attr = NULL;
 	int rem, err = -EOPNOTSUPP;
-	u16 oflags, flags = 0;
+	u16 flags = 0;
 	bool have_flags = false;
 
 	if (nlmsg_len(nlh) < sizeof(*ifm))
@@ -2798,6 +3067,9 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (br_spec) {
 		nla_for_each_nested(attr, br_spec, rem) {
 			if (nla_type(attr) == IFLA_BRIDGE_FLAGS) {
+				if (nla_len(attr) < sizeof(flags))
+					return -EINVAL;
+
 				have_flags = true;
 				flags = nla_get_u16(attr);
 				break;
@@ -2805,8 +3077,6 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh)
 		}
 	}
 
-	oflags = flags;
-
 	if (!flags || (flags & BRIDGE_FLAGS_MASTER)) {
 		struct net_device *br_dev = netdev_master_upper_dev_get(dev);
 
@@ -2815,7 +3085,7 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh)
 			goto out;
 		}
 
-		err = br_dev->netdev_ops->ndo_bridge_setlink(dev, nlh);
+		err = br_dev->netdev_ops->ndo_bridge_setlink(dev, nlh, flags);
 		if (err)
 			goto out;
 
@@ -2826,17 +3096,20 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh)
 		if (!dev->netdev_ops->ndo_bridge_setlink)
 			err = -EOPNOTSUPP;
 		else
-			err = dev->netdev_ops->ndo_bridge_setlink(dev, nlh);
-
-		if (!err)
+			err = dev->netdev_ops->ndo_bridge_setlink(dev, nlh,
+								  flags);
+		if (!err) {
 			flags &= ~BRIDGE_FLAGS_SELF;
+
+			/* Generate event to notify upper layer of bridge
+			 * change
+			 */
+			err = rtnl_bridge_notify(dev);
+		}
 	}
 
 	if (have_flags)
 		memcpy(nla_data(attr), &flags, sizeof(flags));
-	/* Generate event to notify upper layer of bridge change */
-	if (!err)
-		err = rtnl_bridge_notify(dev, oflags);
 out:
 	return err;
 }
@@ -2848,7 +3121,7 @@ static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct net_device *dev;
 	struct nlattr *br_spec, *attr = NULL;
 	int rem, err = -EOPNOTSUPP;
-	u16 oflags, flags = 0;
+	u16 flags = 0;
 	bool have_flags = false;
 
 	if (nlmsg_len(nlh) < sizeof(*ifm))
@@ -2868,6 +3141,9 @@ static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (br_spec) {
 		nla_for_each_nested(attr, br_spec, rem) {
 			if (nla_type(attr) == IFLA_BRIDGE_FLAGS) {
+				if (nla_len(attr) < sizeof(flags))
+					return -EINVAL;
+
 				have_flags = true;
 				flags = nla_get_u16(attr);
 				break;
@@ -2875,8 +3151,6 @@ static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
 		}
 	}
 
-	oflags = flags;
-
 	if (!flags || (flags & BRIDGE_FLAGS_MASTER)) {
 		struct net_device *br_dev = netdev_master_upper_dev_get(dev);
 
@@ -2885,7 +3159,7 @@ static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
 			goto out;
 		}
 
-		err = br_dev->netdev_ops->ndo_bridge_dellink(dev, nlh);
+		err = br_dev->netdev_ops->ndo_bridge_dellink(dev, nlh, flags);
 		if (err)
 			goto out;
 
@@ -2896,17 +3170,21 @@ static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
 		if (!dev->netdev_ops->ndo_bridge_dellink)
 			err = -EOPNOTSUPP;
 		else
-			err = dev->netdev_ops->ndo_bridge_dellink(dev, nlh);
+			err = dev->netdev_ops->ndo_bridge_dellink(dev, nlh,
+								  flags);
 
-		if (!err)
+		if (!err) {
 			flags &= ~BRIDGE_FLAGS_SELF;
+
+			/* Generate event to notify upper layer of bridge
+			 * change
+			 */
+			err = rtnl_bridge_notify(dev);
+		}
 	}
 
 	if (have_flags)
 		memcpy(nla_data(attr), &flags, sizeof(flags));
-	/* Generate event to notify upper layer of bridge change */
-	if (!err)
-		err = rtnl_bridge_notify(dev, oflags);
 out:
 	return err;
 }
@@ -2996,6 +3274,7 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi
 	case NETDEV_UNREGISTER_FINAL:
 	case NETDEV_RELEASE:
 	case NETDEV_JOIN:
+	case NETDEV_BONDING_INFO:
 		break;
 	default:
 		rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL);
diff --git a/net/core/scm.c b/net/core/scm.c
index b442e7e25e60..3b6899b7d810 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -129,8 +129,7 @@ int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p)
 	struct cmsghdr *cmsg;
 	int err;
 
-	for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg))
-	{
+	for_each_cmsghdr(cmsg, msg) {
 		err = -EINVAL;
 
 		/* Verify that cmsg_len is at least sizeof(struct cmsghdr) */
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c16615bfb61e..41ec02242ea7 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -74,6 +74,8 @@
 #include <asm/uaccess.h>
 #include <trace/events/skb.h>
 #include <linux/highmem.h>
+#include <linux/capability.h>
+#include <linux/user_namespace.h>
 
 struct kmem_cache *skbuff_head_cache __read_mostly;
 static struct kmem_cache *skbuff_fclone_cache __read_mostly;
@@ -265,7 +267,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 		skb->fclone = SKB_FCLONE_ORIG;
 		atomic_set(&fclones->fclone_ref, 1);
 
-		fclones->skb2.fclone = SKB_FCLONE_FREE;
+		fclones->skb2.fclone = SKB_FCLONE_CLONE;
 		fclones->skb2.pfmemalloc = pfmemalloc;
 	}
 out:
@@ -278,13 +280,14 @@ nodata:
 EXPORT_SYMBOL(__alloc_skb);
 
 /**
- * build_skb - build a network buffer
+ * __build_skb - build a network buffer
  * @data: data buffer provided by caller
- * @frag_size: size of fragment, or 0 if head was kmalloced
+ * @frag_size: size of data, or 0 if head was kmalloced
  *
  * Allocate a new &sk_buff. Caller provides space holding head and
  * skb_shared_info. @data must have been allocated by kmalloc() only if
- * @frag_size is 0, otherwise data should come from the page allocator.
+ * @frag_size is 0, otherwise data should come from the page allocator
+ *  or vmalloc()
  * The return is the new skb buffer.
  * On a failure the return is %NULL, and @data is not freed.
  * Notes :
@@ -295,7 +298,7 @@ EXPORT_SYMBOL(__alloc_skb);
  *  before giving packet to stack.
  *  RX rings only contains data buffers, not full skbs.
  */
-struct sk_buff *build_skb(void *data, unsigned int frag_size)
+struct sk_buff *__build_skb(void *data, unsigned int frag_size)
 {
 	struct skb_shared_info *shinfo;
 	struct sk_buff *skb;
@@ -309,7 +312,6 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
 
 	memset(skb, 0, offsetof(struct sk_buff, tail));
 	skb->truesize = SKB_TRUESIZE(size);
-	skb->head_frag = frag_size != 0;
 	atomic_set(&skb->users, 1);
 	skb->head = data;
 	skb->data = data;
@@ -326,6 +328,23 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
 
 	return skb;
 }
+
+/* build_skb() is wrapper over __build_skb(), that specifically
+ * takes care of skb->head and skb->pfmemalloc
+ * This means that if @frag_size is not zero, then @data must be backed
+ * by a page fragment, not kmalloc() or vmalloc()
+ */
+struct sk_buff *build_skb(void *data, unsigned int frag_size)
+{
+	struct sk_buff *skb = __build_skb(data, frag_size);
+
+	if (skb && frag_size) {
+		skb->head_frag = 1;
+		if (virt_to_head_page(data)->pfmemalloc)
+			skb->pfmemalloc = 1;
+	}
+	return skb;
+}
 EXPORT_SYMBOL(build_skb);
 
 struct netdev_alloc_cache {
@@ -336,59 +355,86 @@ struct netdev_alloc_cache {
 	unsigned int		pagecnt_bias;
 };
 static DEFINE_PER_CPU(struct netdev_alloc_cache, netdev_alloc_cache);
+static DEFINE_PER_CPU(struct netdev_alloc_cache, napi_alloc_cache);
 
-static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
+static struct page *__page_frag_refill(struct netdev_alloc_cache *nc,
+				       gfp_t gfp_mask)
 {
-	struct netdev_alloc_cache *nc;
-	void *data = NULL;
-	int order;
-	unsigned long flags;
+	const unsigned int order = NETDEV_FRAG_PAGE_MAX_ORDER;
+	struct page *page = NULL;
+	gfp_t gfp = gfp_mask;
+
+	if (order) {
+		gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY |
+			    __GFP_NOMEMALLOC;
+		page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, order);
+		nc->frag.size = PAGE_SIZE << (page ? order : 0);
+	}
 
-	local_irq_save(flags);
-	nc = this_cpu_ptr(&netdev_alloc_cache);
-	if (unlikely(!nc->frag.page)) {
+	if (unlikely(!page))
+		page = alloc_pages_node(NUMA_NO_NODE, gfp, 0);
+
+	nc->frag.page = page;
+
+	return page;
+}
+
+static void *__alloc_page_frag(struct netdev_alloc_cache __percpu *cache,
+			       unsigned int fragsz, gfp_t gfp_mask)
+{
+	struct netdev_alloc_cache *nc = this_cpu_ptr(cache);
+	struct page *page = nc->frag.page;
+	unsigned int size;
+	int offset;
+
+	if (unlikely(!page)) {
 refill:
-		for (order = NETDEV_FRAG_PAGE_MAX_ORDER; ;) {
-			gfp_t gfp = gfp_mask;
+		page = __page_frag_refill(nc, gfp_mask);
+		if (!page)
+			return NULL;
+
+		/* if size can vary use frag.size else just use PAGE_SIZE */
+		size = NETDEV_FRAG_PAGE_MAX_ORDER ? nc->frag.size : PAGE_SIZE;
 
-			if (order)
-				gfp |= __GFP_COMP | __GFP_NOWARN;
-			nc->frag.page = alloc_pages(gfp, order);
-			if (likely(nc->frag.page))
-				break;
-			if (--order < 0)
-				goto end;
-		}
-		nc->frag.size = PAGE_SIZE << order;
 		/* Even if we own the page, we do not use atomic_set().
 		 * This would break get_page_unless_zero() users.
 		 */
-		atomic_add(NETDEV_PAGECNT_MAX_BIAS - 1,
-			   &nc->frag.page->_count);
-		nc->pagecnt_bias = NETDEV_PAGECNT_MAX_BIAS;
-		nc->frag.offset = 0;
+		atomic_add(size - 1, &page->_count);
+
+		/* reset page count bias and offset to start of new frag */
+		nc->pagecnt_bias = size;
+		nc->frag.offset = size;
 	}
 
-	if (nc->frag.offset + fragsz > nc->frag.size) {
-		if (atomic_read(&nc->frag.page->_count) != nc->pagecnt_bias) {
-			if (!atomic_sub_and_test(nc->pagecnt_bias,
-						 &nc->frag.page->_count))
-				goto refill;
-			/* OK, page count is 0, we can safely set it */
-			atomic_set(&nc->frag.page->_count,
-				   NETDEV_PAGECNT_MAX_BIAS);
-		} else {
-			atomic_add(NETDEV_PAGECNT_MAX_BIAS - nc->pagecnt_bias,
-				   &nc->frag.page->_count);
-		}
-		nc->pagecnt_bias = NETDEV_PAGECNT_MAX_BIAS;
-		nc->frag.offset = 0;
+	offset = nc->frag.offset - fragsz;
+	if (unlikely(offset < 0)) {
+		if (!atomic_sub_and_test(nc->pagecnt_bias, &page->_count))
+			goto refill;
+
+		/* if size can vary use frag.size else just use PAGE_SIZE */
+		size = NETDEV_FRAG_PAGE_MAX_ORDER ? nc->frag.size : PAGE_SIZE;
+
+		/* OK, page count is 0, we can safely set it */
+		atomic_set(&page->_count, size);
+
+		/* reset page count bias and offset to start of new frag */
+		nc->pagecnt_bias = size;
+		offset = size - fragsz;
 	}
 
-	data = page_address(nc->frag.page) + nc->frag.offset;
-	nc->frag.offset += fragsz;
 	nc->pagecnt_bias--;
-end:
+	nc->frag.offset = offset;
+
+	return page_address(page) + offset;
+}
+
+static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
+{
+	unsigned long flags;
+	void *data;
+
+	local_irq_save(flags);
+	data = __alloc_page_frag(&netdev_alloc_cache, fragsz, gfp_mask);
 	local_irq_restore(flags);
 	return data;
 }
@@ -406,11 +452,25 @@ void *netdev_alloc_frag(unsigned int fragsz)
 }
 EXPORT_SYMBOL(netdev_alloc_frag);
 
+static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
+{
+	return __alloc_page_frag(&napi_alloc_cache, fragsz, gfp_mask);
+}
+
+void *napi_alloc_frag(unsigned int fragsz)
+{
+	return __napi_alloc_frag(fragsz, GFP_ATOMIC | __GFP_COLD);
+}
+EXPORT_SYMBOL(napi_alloc_frag);
+
 /**
- *	__netdev_alloc_skb - allocate an skbuff for rx on a specific device
- *	@dev: network device to receive on
+ *	__alloc_rx_skb - allocate an skbuff for rx
  *	@length: length to allocate
  *	@gfp_mask: get_free_pages mask, passed to alloc_skb
+ *	@flags:	If SKB_ALLOC_RX is set, __GFP_MEMALLOC will be used for
+ *		allocations in case we have to fallback to __alloc_skb()
+ *		If SKB_ALLOC_NAPI is set, page fragment will be allocated
+ *		from napi_cache instead of netdev_cache.
  *
  *	Allocate a new &sk_buff and assign it a usage count of one. The
  *	buffer has unspecified headroom built in. Users should allocate
@@ -419,11 +479,11 @@ EXPORT_SYMBOL(netdev_alloc_frag);
  *
  *	%NULL is returned if there is no free memory.
  */
-struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
-				   unsigned int length, gfp_t gfp_mask)
+static struct sk_buff *__alloc_rx_skb(unsigned int length, gfp_t gfp_mask,
+				      int flags)
 {
 	struct sk_buff *skb = NULL;
-	unsigned int fragsz = SKB_DATA_ALIGN(length + NET_SKB_PAD) +
+	unsigned int fragsz = SKB_DATA_ALIGN(length) +
 			      SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
 	if (fragsz <= PAGE_SIZE && !(gfp_mask & (__GFP_WAIT | GFP_DMA))) {
@@ -432,7 +492,9 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
 		if (sk_memalloc_socks())
 			gfp_mask |= __GFP_MEMALLOC;
 
-		data = __netdev_alloc_frag(fragsz, gfp_mask);
+		data = (flags & SKB_ALLOC_NAPI) ?
+			__napi_alloc_frag(fragsz, gfp_mask) :
+			__netdev_alloc_frag(fragsz, gfp_mask);
 
 		if (likely(data)) {
 			skb = build_skb(data, fragsz);
@@ -440,17 +502,72 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
 				put_page(virt_to_head_page(data));
 		}
 	} else {
-		skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask,
+		skb = __alloc_skb(length, gfp_mask,
 				  SKB_ALLOC_RX, NUMA_NO_NODE);
 	}
+	return skb;
+}
+
+/**
+ *	__netdev_alloc_skb - allocate an skbuff for rx on a specific device
+ *	@dev: network device to receive on
+ *	@length: length to allocate
+ *	@gfp_mask: get_free_pages mask, passed to alloc_skb
+ *
+ *	Allocate a new &sk_buff and assign it a usage count of one. The
+ *	buffer has NET_SKB_PAD headroom built in. Users should allocate
+ *	the headroom they think they need without accounting for the
+ *	built in space. The built in space is used for optimisations.
+ *
+ *	%NULL is returned if there is no free memory.
+ */
+struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
+				   unsigned int length, gfp_t gfp_mask)
+{
+	struct sk_buff *skb;
+
+	length += NET_SKB_PAD;
+	skb = __alloc_rx_skb(length, gfp_mask, 0);
+
 	if (likely(skb)) {
 		skb_reserve(skb, NET_SKB_PAD);
 		skb->dev = dev;
 	}
+
 	return skb;
 }
 EXPORT_SYMBOL(__netdev_alloc_skb);
 
+/**
+ *	__napi_alloc_skb - allocate skbuff for rx in a specific NAPI instance
+ *	@napi: napi instance this buffer was allocated for
+ *	@length: length to allocate
+ *	@gfp_mask: get_free_pages mask, passed to alloc_skb and alloc_pages
+ *
+ *	Allocate a new sk_buff for use in NAPI receive.  This buffer will
+ *	attempt to allocate the head from a special reserved region used
+ *	only for NAPI Rx allocation.  By doing this we can save several
+ *	CPU cycles by avoiding having to disable and re-enable IRQs.
+ *
+ *	%NULL is returned if there is no free memory.
+ */
+struct sk_buff *__napi_alloc_skb(struct napi_struct *napi,
+				 unsigned int length, gfp_t gfp_mask)
+{
+	struct sk_buff *skb;
+
+	length += NET_SKB_PAD + NET_IP_ALIGN;
+	skb = __alloc_rx_skb(length, gfp_mask, SKB_ALLOC_NAPI);
+
+	if (likely(skb)) {
+		skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
+		skb->dev = napi->dev;
+	}
+
+	return skb;
+}
+EXPORT_SYMBOL(__napi_alloc_skb);
+
 void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
 		     int size, unsigned int truesize)
 {
@@ -541,33 +658,27 @@ static void kfree_skbmem(struct sk_buff *skb)
 	switch (skb->fclone) {
 	case SKB_FCLONE_UNAVAILABLE:
 		kmem_cache_free(skbuff_head_cache, skb);
-		break;
+		return;
 
 	case SKB_FCLONE_ORIG:
 		fclones = container_of(skb, struct sk_buff_fclones, skb1);
-		if (atomic_dec_and_test(&fclones->fclone_ref))
-			kmem_cache_free(skbuff_fclone_cache, fclones);
+
+		/* We usually free the clone (TX completion) before original skb
+		 * This test would have no chance to be true for the clone,
+		 * while here, branch prediction will be good.
+		 */
+		if (atomic_read(&fclones->fclone_ref) == 1)
+			goto fastpath;
 		break;
 
-	case SKB_FCLONE_CLONE:
+	default: /* SKB_FCLONE_CLONE */
 		fclones = container_of(skb, struct sk_buff_fclones, skb2);
-
-		/* Warning : We must perform the atomic_dec_and_test() before
-		 * setting skb->fclone back to SKB_FCLONE_FREE, otherwise
-		 * skb_clone() could set clone_ref to 2 before our decrement.
-		 * Anyway, if we are going to free the structure, no need to
-		 * rewrite skb->fclone.
-		 */
-		if (atomic_dec_and_test(&fclones->fclone_ref)) {
-			kmem_cache_free(skbuff_fclone_cache, fclones);
-		} else {
-			/* The clone portion is available for
-			 * fast-cloning again.
-			 */
-			skb->fclone = SKB_FCLONE_FREE;
-		}
 		break;
 	}
+	if (!atomic_dec_and_test(&fclones->fclone_ref))
+		return;
+fastpath:
+	kmem_cache_free(skbuff_fclone_cache, fclones);
 }
 
 static void skb_release_head_state(struct sk_buff *skb)
@@ -586,13 +697,6 @@ static void skb_release_head_state(struct sk_buff *skb)
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	nf_bridge_put(skb->nf_bridge);
 #endif
-/* XXX: IS this still necessary? - JHS */
-#ifdef CONFIG_NET_SCHED
-	skb->tc_index = 0;
-#ifdef CONFIG_NET_CLS_ACT
-	skb->tc_verd = 0;
-#endif
-#endif
 }
 
 /* Free everything but the sk_buff shell. */
@@ -739,6 +843,9 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	CHECK_SKB_FIELD(napi_id);
 #endif
+#ifdef CONFIG_XPS
+	CHECK_SKB_FIELD(sender_cpu);
+#endif
 #ifdef CONFIG_NET_SCHED
 	CHECK_SKB_FIELD(tc_index);
 #ifdef CONFIG_NET_CLS_ACT
@@ -879,18 +986,14 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
 	struct sk_buff_fclones *fclones = container_of(skb,
 						       struct sk_buff_fclones,
 						       skb1);
-	struct sk_buff *n = &fclones->skb2;
+	struct sk_buff *n;
 
 	if (skb_orphan_frags(skb, gfp_mask))
 		return NULL;
 
 	if (skb->fclone == SKB_FCLONE_ORIG &&
-	    n->fclone == SKB_FCLONE_FREE) {
-		n->fclone = SKB_FCLONE_CLONE;
-		/* As our fastclone was free, clone_ref must be 1 at this point.
-		 * We could use atomic_inc() here, but it is faster
-		 * to set the final value.
-		 */
+	    atomic_read(&fclones->fclone_ref) == 1) {
+		n = &fclones->skb2;
 		atomic_set(&fclones->fclone_ref, 2);
 	} else {
 		if (skb_pfmemalloc(skb))
@@ -2780,7 +2883,6 @@ static void skb_ts_finish(struct ts_config *conf, struct ts_state *state)
  * @from: search offset
  * @to: search limit
  * @config: textsearch configuration
- * @state: uninitialized textsearch state variable
  *
  * Finds a pattern in the skb data according to the specified
  * textsearch configuration. Use textsearch_next() to retrieve
@@ -2788,17 +2890,17 @@ static void skb_ts_finish(struct ts_config *conf, struct ts_state *state)
  * to the first occurrence or UINT_MAX if no match was found.
  */
 unsigned int skb_find_text(struct sk_buff *skb, unsigned int from,
-			   unsigned int to, struct ts_config *config,
-			   struct ts_state *state)
+			   unsigned int to, struct ts_config *config)
 {
+	struct ts_state state;
 	unsigned int ret;
 
 	config->get_next_block = skb_ts_get_next_block;
 	config->finish = skb_ts_finish;
 
-	skb_prepare_seq_read(skb, from, to, TS_SKB_CB(state));
+	skb_prepare_seq_read(skb, from, to, TS_SKB_CB(&state));
 
-	ret = textsearch_find(config, state);
+	ret = textsearch_find(config, &state);
 	return (ret <= to - from ? ret : UINT_MAX);
 }
 EXPORT_SYMBOL(skb_find_text);
@@ -3013,7 +3115,7 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 		if (nskb->len == len + doffset)
 			goto perform_csum_check;
 
-		if (!sg) {
+		if (!sg && !nskb->remcsum_offload) {
 			nskb->ip_summed = CHECKSUM_NONE;
 			nskb->csum = skb_copy_and_csum_bits(head_skb, offset,
 							    skb_put(nskb, len),
@@ -3085,7 +3187,7 @@ skip_fraglist:
 		nskb->truesize += nskb->data_len;
 
 perform_csum_check:
-		if (!csum) {
+		if (!csum && !nskb->remcsum_offload) {
 			nskb->csum = skb_checksum(nskb, doffset,
 						  nskb->len - doffset, 0);
 			nskb->ip_summed = CHECKSUM_NONE;
@@ -3099,6 +3201,16 @@ perform_csum_check:
 	 * (see validate_xmit_skb_list() for example)
 	 */
 	segs->prev = tail;
+
+	/* Following permits correct backpressure, for protocols
+	 * using skb_set_owner_w().
+	 * Idea is to tranfert ownership from head_skb to last segment.
+	 */
+	if (head_skb->destructor == sock_wfree) {
+		swap(tail->truesize, head_skb->truesize);
+		swap(tail->destructor, head_skb->destructor);
+		swap(tail->sk, head_skb->sk);
+	}
 	return segs;
 
 err:
@@ -3112,10 +3224,9 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 	struct skb_shared_info *pinfo, *skbinfo = skb_shinfo(skb);
 	unsigned int offset = skb_gro_offset(skb);
 	unsigned int headlen = skb_headlen(skb);
-	struct sk_buff *nskb, *lp, *p = *head;
 	unsigned int len = skb_gro_len(skb);
+	struct sk_buff *lp, *p = *head;
 	unsigned int delta_truesize;
-	unsigned int headroom;
 
 	if (unlikely(p->len + len >= 65536))
 		return -E2BIG;
@@ -3182,48 +3293,6 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 		NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD;
 		goto done;
 	}
-	/* switch back to head shinfo */
-	pinfo = skb_shinfo(p);
-
-	if (pinfo->frag_list)
-		goto merge;
-	if (skb_gro_len(p) != pinfo->gso_size)
-		return -E2BIG;
-
-	headroom = skb_headroom(p);
-	nskb = alloc_skb(headroom + skb_gro_offset(p), GFP_ATOMIC);
-	if (unlikely(!nskb))
-		return -ENOMEM;
-
-	__copy_skb_header(nskb, p);
-	nskb->mac_len = p->mac_len;
-
-	skb_reserve(nskb, headroom);
-	__skb_put(nskb, skb_gro_offset(p));
-
-	skb_set_mac_header(nskb, skb_mac_header(p) - p->data);
-	skb_set_network_header(nskb, skb_network_offset(p));
-	skb_set_transport_header(nskb, skb_transport_offset(p));
-
-	__skb_pull(p, skb_gro_offset(p));
-	memcpy(skb_mac_header(nskb), skb_mac_header(p),
-	       p->data - skb_mac_header(p));
-
-	skb_shinfo(nskb)->frag_list = p;
-	skb_shinfo(nskb)->gso_size = pinfo->gso_size;
-	pinfo->gso_size = 0;
-	__skb_header_release(p);
-	NAPI_GRO_CB(nskb)->last = p;
-
-	nskb->data_len += p->len;
-	nskb->truesize += p->truesize;
-	nskb->len += p->len;
-
-	*head = nskb;
-	nskb->next = p->next;
-	p->next = NULL;
-
-	p = nskb;
 
 merge:
 	delta_truesize = skb->truesize;
@@ -3526,13 +3595,14 @@ struct sk_buff *sock_dequeue_err_skb(struct sock *sk)
 {
 	struct sk_buff_head *q = &sk->sk_error_queue;
 	struct sk_buff *skb, *skb_next;
+	unsigned long flags;
 	int err = 0;
 
-	spin_lock_bh(&q->lock);
+	spin_lock_irqsave(&q->lock, flags);
 	skb = __skb_dequeue(q);
 	if (skb && (skb_next = skb_peek(q)))
 		err = SKB_EXT_ERR(skb_next)->ee.ee_errno;
-	spin_unlock_bh(&q->lock);
+	spin_unlock_irqrestore(&q->lock, flags);
 
 	sk->sk_err = err;
 	if (err)
@@ -3600,11 +3670,28 @@ static void __skb_complete_tx_timestamp(struct sk_buff *skb,
 		kfree_skb(skb);
 }
 
+static bool skb_may_tx_timestamp(struct sock *sk, bool tsonly)
+{
+	bool ret;
+
+	if (likely(sysctl_tstamp_allow_data || tsonly))
+		return true;
+
+	read_lock_bh(&sk->sk_callback_lock);
+	ret = sk->sk_socket && sk->sk_socket->file &&
+	      file_ns_capable(sk->sk_socket->file, &init_user_ns, CAP_NET_RAW);
+	read_unlock_bh(&sk->sk_callback_lock);
+	return ret;
+}
+
 void skb_complete_tx_timestamp(struct sk_buff *skb,
 			       struct skb_shared_hwtstamps *hwtstamps)
 {
 	struct sock *sk = skb->sk;
 
+	if (!skb_may_tx_timestamp(sk, false))
+		return;
+
 	/* take a reference to prevent skb_orphan() from freeing the socket */
 	sock_hold(sk);
 
@@ -3620,19 +3707,32 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
 		     struct sock *sk, int tstype)
 {
 	struct sk_buff *skb;
+	bool tsonly;
 
 	if (!sk)
 		return;
 
-	if (hwtstamps)
-		*skb_hwtstamps(orig_skb) = *hwtstamps;
-	else
-		orig_skb->tstamp = ktime_get_real();
+	tsonly = sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TSONLY;
+	if (!skb_may_tx_timestamp(sk, tsonly))
+		return;
 
-	skb = skb_clone(orig_skb, GFP_ATOMIC);
+	if (tsonly)
+		skb = alloc_skb(0, GFP_ATOMIC);
+	else
+		skb = skb_clone(orig_skb, GFP_ATOMIC);
 	if (!skb)
 		return;
 
+	if (tsonly) {
+		skb_shinfo(skb)->tx_flags = skb_shinfo(orig_skb)->tx_flags;
+		skb_shinfo(skb)->tskey = skb_shinfo(orig_skb)->tskey;
+	}
+
+	if (hwtstamps)
+		*skb_hwtstamps(skb) = *hwtstamps;
+	else
+		skb->tstamp = ktime_get_real();
+
 	__skb_complete_tx_timestamp(skb, sk, tstype);
 }
 EXPORT_SYMBOL_GPL(__skb_tstamp_tx);
@@ -3670,7 +3770,6 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked)
 }
 EXPORT_SYMBOL_GPL(skb_complete_wifi_ack);
 
-
 /**
  * skb_partial_csum_set - set up and verify partial csum values for packet
  * @skb: the skb to set
@@ -4043,17 +4142,21 @@ EXPORT_SYMBOL(skb_try_coalesce);
  */
 void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 {
-	if (xnet)
-		skb_orphan(skb);
 	skb->tstamp.tv64 = 0;
 	skb->pkt_type = PACKET_HOST;
 	skb->skb_iif = 0;
 	skb->ignore_df = 0;
 	skb_dst_drop(skb);
-	skb->mark = 0;
+	skb_sender_cpu_clear(skb);
 	secpath_reset(skb);
 	nf_reset(skb);
 	nf_reset_trace(skb);
+
+	if (!xnet)
+		return;
+
+	skb_orphan(skb);
+	skb->mark = 0;
 }
 EXPORT_SYMBOL_GPL(skb_scrub_packet);
 
@@ -4106,7 +4209,7 @@ struct sk_buff *skb_vlan_untag(struct sk_buff *skb)
 	struct vlan_hdr *vhdr;
 	u16 vlan_tci;
 
-	if (unlikely(vlan_tx_tag_present(skb))) {
+	if (unlikely(skb_vlan_tag_present(skb))) {
 		/* vlan_tci is already set-up so leave this for another time */
 		return skb;
 	}
@@ -4141,6 +4244,113 @@ err_free:
 }
 EXPORT_SYMBOL(skb_vlan_untag);
 
+int skb_ensure_writable(struct sk_buff *skb, int write_len)
+{
+	if (!pskb_may_pull(skb, write_len))
+		return -ENOMEM;
+
+	if (!skb_cloned(skb) || skb_clone_writable(skb, write_len))
+		return 0;
+
+	return pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
+}
+EXPORT_SYMBOL(skb_ensure_writable);
+
+/* remove VLAN header from packet and update csum accordingly. */
+static int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci)
+{
+	struct vlan_hdr *vhdr;
+	unsigned int offset = skb->data - skb_mac_header(skb);
+	int err;
+
+	__skb_push(skb, offset);
+	err = skb_ensure_writable(skb, VLAN_ETH_HLEN);
+	if (unlikely(err))
+		goto pull;
+
+	skb_postpull_rcsum(skb, skb->data + (2 * ETH_ALEN), VLAN_HLEN);
+
+	vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN);
+	*vlan_tci = ntohs(vhdr->h_vlan_TCI);
+
+	memmove(skb->data + VLAN_HLEN, skb->data, 2 * ETH_ALEN);
+	__skb_pull(skb, VLAN_HLEN);
+
+	vlan_set_encap_proto(skb, vhdr);
+	skb->mac_header += VLAN_HLEN;
+
+	if (skb_network_offset(skb) < ETH_HLEN)
+		skb_set_network_header(skb, ETH_HLEN);
+
+	skb_reset_mac_len(skb);
+pull:
+	__skb_pull(skb, offset);
+
+	return err;
+}
+
+int skb_vlan_pop(struct sk_buff *skb)
+{
+	u16 vlan_tci;
+	__be16 vlan_proto;
+	int err;
+
+	if (likely(skb_vlan_tag_present(skb))) {
+		skb->vlan_tci = 0;
+	} else {
+		if (unlikely((skb->protocol != htons(ETH_P_8021Q) &&
+			      skb->protocol != htons(ETH_P_8021AD)) ||
+			     skb->len < VLAN_ETH_HLEN))
+			return 0;
+
+		err = __skb_vlan_pop(skb, &vlan_tci);
+		if (err)
+			return err;
+	}
+	/* move next vlan tag to hw accel tag */
+	if (likely((skb->protocol != htons(ETH_P_8021Q) &&
+		    skb->protocol != htons(ETH_P_8021AD)) ||
+		   skb->len < VLAN_ETH_HLEN))
+		return 0;
+
+	vlan_proto = skb->protocol;
+	err = __skb_vlan_pop(skb, &vlan_tci);
+	if (unlikely(err))
+		return err;
+
+	__vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci);
+	return 0;
+}
+EXPORT_SYMBOL(skb_vlan_pop);
+
+int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci)
+{
+	if (skb_vlan_tag_present(skb)) {
+		unsigned int offset = skb->data - skb_mac_header(skb);
+		int err;
+
+		/* __vlan_insert_tag expect skb->data pointing to mac header.
+		 * So change skb->data before calling it and change back to
+		 * original position later
+		 */
+		__skb_push(skb, offset);
+		err = __vlan_insert_tag(skb, skb->vlan_proto,
+					skb_vlan_tag_get(skb));
+		if (err)
+			return err;
+		skb->protocol = skb->vlan_proto;
+		skb->mac_len += VLAN_HLEN;
+		__skb_pull(skb, offset);
+
+		if (skb->ip_summed == CHECKSUM_COMPLETE)
+			skb->csum = csum_add(skb->csum, csum_partial(skb->data
+					+ (2 * ETH_ALEN), VLAN_HLEN, 0));
+	}
+	__vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci);
+	return 0;
+}
+EXPORT_SYMBOL(skb_vlan_push);
+
 /**
  * alloc_skb_with_frags - allocate skb with page frags
  *
@@ -4188,7 +4398,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
 
 		while (order) {
 			if (npages >= 1 << order) {
-				page = alloc_pages(gfp_mask |
+				page = alloc_pages((gfp_mask & ~__GFP_WAIT) |
 						   __GFP_COMP |
 						   __GFP_NOWARN |
 						   __GFP_NORETRY,
diff --git a/net/core/sock.c b/net/core/sock.c
index 15e0c67b1069..dc30dc5bb1b8 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -325,6 +325,8 @@ __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;
 int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512);
 EXPORT_SYMBOL(sysctl_optmem_max);
 
+int sysctl_tstamp_allow_data __read_mostly = 1;
+
 struct static_key memalloc_socks = STATIC_KEY_INIT_FALSE;
 EXPORT_SYMBOL_GPL(memalloc_socks);
 
@@ -352,15 +354,12 @@ void sk_clear_memalloc(struct sock *sk)
 
 	/*
 	 * SOCK_MEMALLOC is allowed to ignore rmem limits to ensure forward
-	 * progress of swapping. However, if SOCK_MEMALLOC is cleared while
-	 * it has rmem allocations there is a risk that the user of the
-	 * socket cannot make forward progress due to exceeding the rmem
-	 * limits. By rights, sk_clear_memalloc() should only be called
-	 * on sockets being torn down but warn and reset the accounting if
-	 * that assumption breaks.
+	 * progress of swapping. SOCK_MEMALLOC may be cleared while
+	 * it has rmem allocations due to the last swapfile being deactivated
+	 * but there is a risk that the socket is unusable due to exceeding
+	 * the rmem limits. Reclaim the reserves and obey rmem limits again.
 	 */
-	if (WARN_ON(sk->sk_forward_alloc))
-		sk_mem_reclaim(sk);
+	sk_mem_reclaim(sk);
 }
 EXPORT_SYMBOL_GPL(sk_clear_memalloc);
 
@@ -464,7 +463,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	skb_dst_force(skb);
 
 	spin_lock_irqsave(&list->lock, flags);
-	skb->dropcount = atomic_read(&sk->sk_drops);
+	sock_skb_set_dropcount(sk, skb);
 	__skb_queue_tail(list, skb);
 	spin_unlock_irqrestore(&list->lock, flags);
 
@@ -651,6 +650,25 @@ static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool)
 		sock_reset_flag(sk, bit);
 }
 
+bool sk_mc_loop(struct sock *sk)
+{
+	if (dev_recursion_level())
+		return false;
+	if (!sk)
+		return true;
+	switch (sk->sk_family) {
+	case AF_INET:
+		return inet_sk(sk)->mc_loop;
+#if IS_ENABLED(CONFIG_IPV6)
+	case AF_INET6:
+		return inet6_sk(sk)->mc_loop;
+#endif
+	}
+	WARN_ON(1);
+	return true;
+}
+EXPORT_SYMBOL(sk_mc_loop);
+
 /*
  *	This is meant for all protocols to use and covers goings on
  *	at the socket level. Everything here is generic.
@@ -840,6 +858,7 @@ set_rcvbuf:
 			ret = -EINVAL;
 			break;
 		}
+
 		if (val & SOF_TIMESTAMPING_OPT_ID &&
 		    !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) {
 			if (sk->sk_protocol == IPPROTO_TCP) {
@@ -888,6 +907,19 @@ set_rcvbuf:
 		}
 		break;
 
+	case SO_ATTACH_BPF:
+		ret = -EINVAL;
+		if (optlen == sizeof(u32)) {
+			u32 ufd;
+
+			ret = -EFAULT;
+			if (copy_from_user(&ufd, optval, sizeof(ufd)))
+				break;
+
+			ret = sk_attach_bpf(ufd, sk);
+		}
+		break;
+
 	case SO_DETACH_FILTER:
 		ret = sk_detach_filter(sk);
 		break;
@@ -912,8 +944,6 @@ set_rcvbuf:
 			sk->sk_mark = val;
 		break;
 
-		/* We implement the SO_SNDLOWAT etc to
-		   not be settable (1003.1g 5.3) */
 	case SO_RXQ_OVFL:
 		sock_valbool_flag(sk, SOCK_RXQ_OVFL, valbool);
 		break;
@@ -1213,7 +1243,14 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		v.val = sk->sk_max_pacing_rate;
 		break;
 
+	case SO_INCOMING_CPU:
+		v.val = sk->sk_incoming_cpu;
+		break;
+
 	default:
+		/* We implement the SO_SNDLOWAT etc to not be settable
+		 * (1003.1g 7).
+		 */
 		return -ENOPROTOOPT;
 	}
 
@@ -1435,7 +1472,6 @@ void sk_release_kernel(struct sock *sk)
 
 	sock_hold(sk);
 	sock_release(sk->sk_socket);
-	release_net(sock_net(sk));
 	sock_net_set(sk, get_net(&init_net));
 	sock_put(sk);
 }
@@ -1517,6 +1553,8 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 
 		newsk->sk_err	   = 0;
 		newsk->sk_priority = 0;
+		newsk->sk_incoming_cpu = raw_smp_processor_id();
+		atomic64_set(&newsk->sk_cookie, 0);
 		/*
 		 * Before updating sk_refcnt, we must commit prior changes to memory
 		 * (Documentation/RCU/rculist_nulls.txt for details)
@@ -1634,25 +1672,16 @@ void sock_rfree(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(sock_rfree);
 
+/*
+ * Buffer destructor for skbs that are not used directly in read or write
+ * path, e.g. for error handler skbs. Automatically called from kfree_skb.
+ */
 void sock_efree(struct sk_buff *skb)
 {
 	sock_put(skb->sk);
 }
 EXPORT_SYMBOL(sock_efree);
 
-#ifdef CONFIG_INET
-void sock_edemux(struct sk_buff *skb)
-{
-	struct sock *sk = skb->sk;
-
-	if (sk->sk_state == TCP_TIME_WAIT)
-		inet_twsk_put(inet_twsk(sk));
-	else
-		sock_put(sk);
-}
-EXPORT_SYMBOL(sock_edemux);
-#endif
-
 kuid_t sock_i_uid(struct sock *sk)
 {
 	kuid_t uid;
@@ -1713,18 +1742,34 @@ void *sock_kmalloc(struct sock *sk, int size, gfp_t priority)
 }
 EXPORT_SYMBOL(sock_kmalloc);
 
-/*
- * Free an option memory block.
+/* Free an option memory block. Note, we actually want the inline
+ * here as this allows gcc to detect the nullify and fold away the
+ * condition entirely.
  */
-void sock_kfree_s(struct sock *sk, void *mem, int size)
+static inline void __sock_kfree_s(struct sock *sk, void *mem, int size,
+				  const bool nullify)
 {
 	if (WARN_ON_ONCE(!mem))
 		return;
-	kfree(mem);
+	if (nullify)
+		kzfree(mem);
+	else
+		kfree(mem);
 	atomic_sub(size, &sk->sk_omem_alloc);
 }
+
+void sock_kfree_s(struct sock *sk, void *mem, int size)
+{
+	__sock_kfree_s(sk, mem, size, false);
+}
 EXPORT_SYMBOL(sock_kfree_s);
 
+void sock_kzfree_s(struct sock *sk, void *mem, int size)
+{
+	__sock_kfree_s(sk, mem, size, true);
+}
+EXPORT_SYMBOL(sock_kzfree_s);
+
 /* It is almost wait_for_tcp_memory minus release_sock/lock_sock.
    I think, these locks should be removed for datagram sockets.
  */
@@ -1835,7 +1880,7 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t gfp)
 
 	pfrag->offset = 0;
 	if (SKB_FRAG_PAGE_ORDER) {
-		pfrag->page = alloc_pages(gfp | __GFP_COMP |
+		pfrag->page = alloc_pages((gfp & ~__GFP_WAIT) | __GFP_COMP |
 					  __GFP_NOWARN | __GFP_NORETRY,
 					  SKB_FRAG_PAGE_ORDER);
 		if (likely(pfrag->page)) {
@@ -2126,15 +2171,14 @@ int sock_no_getsockopt(struct socket *sock, int level, int optname,
 }
 EXPORT_SYMBOL(sock_no_getsockopt);
 
-int sock_no_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m,
-		    size_t len)
+int sock_no_sendmsg(struct socket *sock, struct msghdr *m, size_t len)
 {
 	return -EOPNOTSUPP;
 }
 EXPORT_SYMBOL(sock_no_sendmsg);
 
-int sock_no_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m,
-		    size_t len, int flags)
+int sock_no_recvmsg(struct socket *sock, struct msghdr *m, size_t len,
+		    int flags)
 {
 	return -EOPNOTSUPP;
 }
@@ -2457,7 +2501,7 @@ int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len,
 		msg->msg_flags |= MSG_TRUNC;
 		copied = len;
 	}
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (err)
 		goto out_free_skb;
 
@@ -2506,14 +2550,14 @@ int compat_sock_common_getsockopt(struct socket *sock, int level, int optname,
 EXPORT_SYMBOL(compat_sock_common_getsockopt);
 #endif
 
-int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock,
-			struct msghdr *msg, size_t size, int flags)
+int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+			int flags)
 {
 	struct sock *sk = sock->sk;
 	int addr_len = 0;
 	int err;
 
-	err = sk->sk_prot->recvmsg(iocb, sk, msg, size, flags & MSG_DONTWAIT,
+	err = sk->sk_prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT,
 				   flags & ~MSG_DONTWAIT, &addr_len);
 	if (err >= 0)
 		msg->msg_namelen = addr_len;
@@ -2690,6 +2734,42 @@ static inline void release_proto_idx(struct proto *prot)
 }
 #endif
 
+static void req_prot_cleanup(struct request_sock_ops *rsk_prot)
+{
+	if (!rsk_prot)
+		return;
+	kfree(rsk_prot->slab_name);
+	rsk_prot->slab_name = NULL;
+	if (rsk_prot->slab) {
+		kmem_cache_destroy(rsk_prot->slab);
+		rsk_prot->slab = NULL;
+	}
+}
+
+static int req_prot_init(const struct proto *prot)
+{
+	struct request_sock_ops *rsk_prot = prot->rsk_prot;
+
+	if (!rsk_prot)
+		return 0;
+
+	rsk_prot->slab_name = kasprintf(GFP_KERNEL, "request_sock_%s",
+					prot->name);
+	if (!rsk_prot->slab_name)
+		return -ENOMEM;
+
+	rsk_prot->slab = kmem_cache_create(rsk_prot->slab_name,
+					   rsk_prot->obj_size, 0,
+					   0, NULL);
+
+	if (!rsk_prot->slab) {
+		pr_crit("%s: Can't create request sock SLAB cache!\n",
+			prot->name);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
 int proto_register(struct proto *prot, int alloc_slab)
 {
 	if (alloc_slab) {
@@ -2703,21 +2783,8 @@ int proto_register(struct proto *prot, int alloc_slab)
 			goto out;
 		}
 
-		if (prot->rsk_prot != NULL) {
-			prot->rsk_prot->slab_name = kasprintf(GFP_KERNEL, "request_sock_%s", prot->name);
-			if (prot->rsk_prot->slab_name == NULL)
-				goto out_free_sock_slab;
-
-			prot->rsk_prot->slab = kmem_cache_create(prot->rsk_prot->slab_name,
-								 prot->rsk_prot->obj_size, 0,
-								 SLAB_HWCACHE_ALIGN, NULL);
-
-			if (prot->rsk_prot->slab == NULL) {
-				pr_crit("%s: Can't create request sock SLAB cache!\n",
-					prot->name);
-				goto out_free_request_sock_slab_name;
-			}
-		}
+		if (req_prot_init(prot))
+			goto out_free_request_sock_slab;
 
 		if (prot->twsk_prot != NULL) {
 			prot->twsk_prot->twsk_slab_name = kasprintf(GFP_KERNEL, "tw_sock_%s", prot->name);
@@ -2729,8 +2796,7 @@ int proto_register(struct proto *prot, int alloc_slab)
 				kmem_cache_create(prot->twsk_prot->twsk_slab_name,
 						  prot->twsk_prot->twsk_obj_size,
 						  0,
-						  SLAB_HWCACHE_ALIGN |
-							prot->slab_flags,
+						  prot->slab_flags,
 						  NULL);
 			if (prot->twsk_prot->twsk_slab == NULL)
 				goto out_free_timewait_sock_slab_name;
@@ -2746,14 +2812,8 @@ int proto_register(struct proto *prot, int alloc_slab)
 out_free_timewait_sock_slab_name:
 	kfree(prot->twsk_prot->twsk_slab_name);
 out_free_request_sock_slab:
-	if (prot->rsk_prot && prot->rsk_prot->slab) {
-		kmem_cache_destroy(prot->rsk_prot->slab);
-		prot->rsk_prot->slab = NULL;
-	}
-out_free_request_sock_slab_name:
-	if (prot->rsk_prot)
-		kfree(prot->rsk_prot->slab_name);
-out_free_sock_slab:
+	req_prot_cleanup(prot->rsk_prot);
+
 	kmem_cache_destroy(prot->slab);
 	prot->slab = NULL;
 out:
@@ -2773,11 +2833,7 @@ void proto_unregister(struct proto *prot)
 		prot->slab = NULL;
 	}
 
-	if (prot->rsk_prot != NULL && prot->rsk_prot->slab != NULL) {
-		kmem_cache_destroy(prot->rsk_prot->slab);
-		kfree(prot->rsk_prot->slab_name);
-		prot->rsk_prot->slab = NULL;
-	}
+	req_prot_cleanup(prot->rsk_prot);
 
 	if (prot->twsk_prot != NULL && prot->twsk_prot->twsk_slab != NULL) {
 		kmem_cache_destroy(prot->twsk_prot->twsk_slab);
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index ad704c757bb4..74dddf84adcd 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -13,22 +13,39 @@ static const struct sock_diag_handler *sock_diag_handlers[AF_MAX];
 static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh);
 static DEFINE_MUTEX(sock_diag_table_mutex);
 
-int sock_diag_check_cookie(void *sk, __u32 *cookie)
+static u64 sock_gen_cookie(struct sock *sk)
 {
-	if ((cookie[0] != INET_DIAG_NOCOOKIE ||
-	     cookie[1] != INET_DIAG_NOCOOKIE) &&
-	    ((u32)(unsigned long)sk != cookie[0] ||
-	     (u32)((((unsigned long)sk) >> 31) >> 1) != cookie[1]))
-		return -ESTALE;
-	else
+	while (1) {
+		u64 res = atomic64_read(&sk->sk_cookie);
+
+		if (res)
+			return res;
+		res = atomic64_inc_return(&sock_net(sk)->cookie_gen);
+		atomic64_cmpxchg(&sk->sk_cookie, 0, res);
+	}
+}
+
+int sock_diag_check_cookie(struct sock *sk, const __u32 *cookie)
+{
+	u64 res;
+
+	if (cookie[0] == INET_DIAG_NOCOOKIE && cookie[1] == INET_DIAG_NOCOOKIE)
 		return 0;
+
+	res = sock_gen_cookie(sk);
+	if ((u32)res != cookie[0] || (u32)(res >> 32) != cookie[1])
+		return -ESTALE;
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(sock_diag_check_cookie);
 
-void sock_diag_save_cookie(void *sk, __u32 *cookie)
+void sock_diag_save_cookie(struct sock *sk, __u32 *cookie)
 {
-	cookie[0] = (u32)(unsigned long)sk;
-	cookie[1] = (u32)(((unsigned long)sk >> 31) >> 1);
+	u64 res = sock_gen_cookie(sk);
+
+	cookie[0] = (u32)res;
+	cookie[1] = (u32)(res >> 32);
 }
 EXPORT_SYMBOL_GPL(sock_diag_save_cookie);
 
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index cf9cd13509a7..95b6139d710c 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -24,7 +24,10 @@
 
 static int zero = 0;
 static int one = 1;
-static int ushort_max = USHRT_MAX;
+static int min_sndbuf = SOCK_MIN_SNDBUF;
+static int min_rcvbuf = SOCK_MIN_RCVBUF;
+
+static int net_msg_warn;	/* Unused, but still a sysctl */
 
 #ifdef CONFIG_RPS
 static int rps_sock_flow_sysctl(struct ctl_table *table, int write,
@@ -50,7 +53,7 @@ static int rps_sock_flow_sysctl(struct ctl_table *table, int write,
 
 	if (write) {
 		if (size) {
-			if (size > 1<<30) {
+			if (size > 1<<29) {
 				/* Enforce limit to prevent overflow */
 				mutex_unlock(&sock_flow_mutex);
 				return -EINVAL;
@@ -63,7 +66,7 @@ static int rps_sock_flow_sysctl(struct ctl_table *table, int write,
 					mutex_unlock(&sock_flow_mutex);
 					return -ENOMEM;
 				}
-
+				rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1;
 				sock_table->mask = size - 1;
 			} else
 				sock_table = orig_sock_table;
@@ -153,7 +156,7 @@ write_unlock:
 		rcu_read_unlock();
 
 		len = min(sizeof(kbuf) - 1, *lenp);
-		len = cpumask_scnprintf(kbuf, len, mask);
+		len = scnprintf(kbuf, len, "%*pb", cpumask_pr_args(mask));
 		if (!len) {
 			*lenp = 0;
 			goto done;
@@ -215,6 +218,18 @@ static int set_default_qdisc(struct ctl_table *table, int write,
 }
 #endif
 
+static int proc_do_rss_key(struct ctl_table *table, int write,
+			   void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table fake_table;
+	char buf[NETDEV_RSS_KEY_LEN * 3];
+
+	snprintf(buf, sizeof(buf), "%*phC", NETDEV_RSS_KEY_LEN, netdev_rss_key);
+	fake_table.data = buf;
+	fake_table.maxlen = sizeof(buf);
+	return proc_dostring(&fake_table, write, buffer, lenp, ppos);
+}
+
 static struct ctl_table net_core_table[] = {
 #ifdef CONFIG_NET
 	{
@@ -223,7 +238,7 @@ static struct ctl_table net_core_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one,
+		.extra1		= &min_sndbuf,
 	},
 	{
 		.procname	= "rmem_max",
@@ -231,7 +246,7 @@ static struct ctl_table net_core_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one,
+		.extra1		= &min_rcvbuf,
 	},
 	{
 		.procname	= "wmem_default",
@@ -239,7 +254,7 @@ static struct ctl_table net_core_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one,
+		.extra1		= &min_sndbuf,
 	},
 	{
 		.procname	= "rmem_default",
@@ -247,7 +262,7 @@ static struct ctl_table net_core_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one,
+		.extra1		= &min_rcvbuf,
 	},
 	{
 		.procname	= "dev_weight",
@@ -263,6 +278,13 @@ static struct ctl_table net_core_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "netdev_rss_key",
+		.data		= &netdev_rss_key,
+		.maxlen		= sizeof(int),
+		.mode		= 0444,
+		.proc_handler	= proc_do_rss_key,
+	},
 #ifdef CONFIG_BPF_JIT
 	{
 		.procname	= "bpf_jit_enable",
@@ -300,6 +322,15 @@ static struct ctl_table net_core_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "tstamp_allow_data",
+		.data		= &sysctl_tstamp_allow_data,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one
+	},
 #ifdef CONFIG_RPS
 	{
 		.procname	= "rps_sock_flow_entries",
@@ -371,7 +402,6 @@ static struct ctl_table netns_core_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.extra1		= &zero,
-		.extra2		= &ushort_max,
 		.proc_handler	= proc_dointvec_minmax
 	},
 	{ }
diff --git a/net/core/utils.c b/net/core/utils.c
index efc76dd9dcd1..7b803884c162 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -33,9 +33,6 @@
 #include <asm/byteorder.h>
 #include <asm/uaccess.h>
 
-int net_msg_warn __read_mostly = 1;
-EXPORT_SYMBOL(net_msg_warn);
-
 DEFINE_RATELIMIT_STATE(net_ratelimit_state, 5 * HZ, 10);
 /*
  * All net warning printk()s should be guarded by this function.
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index ca11d283bbeb..5b21f6f88e97 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -177,6 +177,8 @@ static const struct nla_policy dcbnl_ieee_policy[DCB_ATTR_IEEE_MAX + 1] = {
 	[DCB_ATTR_IEEE_PFC]	    = {.len = sizeof(struct ieee_pfc)},
 	[DCB_ATTR_IEEE_APP_TABLE]   = {.type = NLA_NESTED},
 	[DCB_ATTR_IEEE_MAXRATE]   = {.len = sizeof(struct ieee_maxrate)},
+	[DCB_ATTR_IEEE_QCN]         = {.len = sizeof(struct ieee_qcn)},
+	[DCB_ATTR_IEEE_QCN_STATS]   = {.len = sizeof(struct ieee_qcn_stats)},
 };
 
 static const struct nla_policy dcbnl_ieee_app[DCB_ATTR_IEEE_APP_MAX + 1] = {
@@ -1030,7 +1032,7 @@ nla_put_failure:
 	return err;
 }
 
-/* Handle IEEE 802.1Qaz GET commands. */
+/* Handle IEEE 802.1Qaz/802.1Qau/802.1Qbb GET commands. */
 static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev)
 {
 	struct nlattr *ieee, *app;
@@ -1067,6 +1069,32 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev)
 		}
 	}
 
+	if (ops->ieee_getqcn) {
+		struct ieee_qcn qcn;
+
+		memset(&qcn, 0, sizeof(qcn));
+		err = ops->ieee_getqcn(netdev, &qcn);
+		if (!err) {
+			err = nla_put(skb, DCB_ATTR_IEEE_QCN,
+				      sizeof(qcn), &qcn);
+			if (err)
+				return -EMSGSIZE;
+		}
+	}
+
+	if (ops->ieee_getqcnstats) {
+		struct ieee_qcn_stats qcn_stats;
+
+		memset(&qcn_stats, 0, sizeof(qcn_stats));
+		err = ops->ieee_getqcnstats(netdev, &qcn_stats);
+		if (!err) {
+			err = nla_put(skb, DCB_ATTR_IEEE_QCN_STATS,
+				      sizeof(qcn_stats), &qcn_stats);
+			if (err)
+				return -EMSGSIZE;
+		}
+	}
+
 	if (ops->ieee_getpfc) {
 		struct ieee_pfc pfc;
 		memset(&pfc, 0, sizeof(pfc));
@@ -1080,13 +1108,13 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev)
 	if (!app)
 		return -EMSGSIZE;
 
-	spin_lock(&dcb_lock);
+	spin_lock_bh(&dcb_lock);
 	list_for_each_entry(itr, &dcb_app_list, list) {
 		if (itr->ifindex == netdev->ifindex) {
 			err = nla_put(skb, DCB_ATTR_IEEE_APP, sizeof(itr->app),
 					 &itr->app);
 			if (err) {
-				spin_unlock(&dcb_lock);
+				spin_unlock_bh(&dcb_lock);
 				return -EMSGSIZE;
 			}
 		}
@@ -1097,7 +1125,7 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev)
 	else
 		dcbx = -EOPNOTSUPP;
 
-	spin_unlock(&dcb_lock);
+	spin_unlock_bh(&dcb_lock);
 	nla_nest_end(skb, app);
 
 	/* get peer info if available */
@@ -1234,7 +1262,7 @@ static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev)
 	}
 
 	/* local app */
-	spin_lock(&dcb_lock);
+	spin_lock_bh(&dcb_lock);
 	app = nla_nest_start(skb, DCB_ATTR_CEE_APP_TABLE);
 	if (!app)
 		goto dcb_unlock;
@@ -1271,7 +1299,7 @@ static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev)
 	else
 		dcbx = -EOPNOTSUPP;
 
-	spin_unlock(&dcb_lock);
+	spin_unlock_bh(&dcb_lock);
 
 	/* features flags */
 	if (ops->getfeatcfg) {
@@ -1326,7 +1354,7 @@ static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev)
 	return 0;
 
 dcb_unlock:
-	spin_unlock(&dcb_lock);
+	spin_unlock_bh(&dcb_lock);
 nla_put_failure:
 	return err;
 }
@@ -1379,8 +1407,9 @@ int dcbnl_cee_notify(struct net_device *dev, int event, int cmd,
 }
 EXPORT_SYMBOL(dcbnl_cee_notify);
 
-/* Handle IEEE 802.1Qaz SET commands. If any requested operation can not
- * be completed the entire msg is aborted and error value is returned.
+/* Handle IEEE 802.1Qaz/802.1Qau/802.1Qbb SET commands.
+ * If any requested operation can not be completed
+ * the entire msg is aborted and error value is returned.
  * No attempt is made to reconcile the case where only part of the
  * cmd can be completed.
  */
@@ -1417,6 +1446,15 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh,
 			goto err;
 	}
 
+	if (ieee[DCB_ATTR_IEEE_QCN] && ops->ieee_setqcn) {
+		struct ieee_qcn *qcn =
+			nla_data(ieee[DCB_ATTR_IEEE_QCN]);
+
+		err = ops->ieee_setqcn(netdev, qcn);
+		if (err)
+			goto err;
+	}
+
 	if (ieee[DCB_ATTR_IEEE_PFC] && ops->ieee_setpfc) {
 		struct ieee_pfc *pfc = nla_data(ieee[DCB_ATTR_IEEE_PFC]);
 		err = ops->ieee_setpfc(netdev, pfc);
@@ -1762,10 +1800,10 @@ u8 dcb_getapp(struct net_device *dev, struct dcb_app *app)
 	struct dcb_app_type *itr;
 	u8 prio = 0;
 
-	spin_lock(&dcb_lock);
+	spin_lock_bh(&dcb_lock);
 	if ((itr = dcb_app_lookup(app, dev->ifindex, 0)))
 		prio = itr->app.priority;
-	spin_unlock(&dcb_lock);
+	spin_unlock_bh(&dcb_lock);
 
 	return prio;
 }
@@ -1789,7 +1827,7 @@ int dcb_setapp(struct net_device *dev, struct dcb_app *new)
 	if (dev->dcbnl_ops->getdcbx)
 		event.dcbx = dev->dcbnl_ops->getdcbx(dev);
 
-	spin_lock(&dcb_lock);
+	spin_lock_bh(&dcb_lock);
 	/* Search for existing match and replace */
 	if ((itr = dcb_app_lookup(new, dev->ifindex, 0))) {
 		if (new->priority)
@@ -1804,7 +1842,7 @@ int dcb_setapp(struct net_device *dev, struct dcb_app *new)
 	if (new->priority)
 		err = dcb_app_add(new, dev->ifindex);
 out:
-	spin_unlock(&dcb_lock);
+	spin_unlock_bh(&dcb_lock);
 	if (!err)
 		call_dcbevent_notifiers(DCB_APP_EVENT, &event);
 	return err;
@@ -1823,10 +1861,10 @@ u8 dcb_ieee_getapp_mask(struct net_device *dev, struct dcb_app *app)
 	struct dcb_app_type *itr;
 	u8 prio = 0;
 
-	spin_lock(&dcb_lock);
+	spin_lock_bh(&dcb_lock);
 	if ((itr = dcb_app_lookup(app, dev->ifindex, 0)))
 		prio |= 1 << itr->app.priority;
-	spin_unlock(&dcb_lock);
+	spin_unlock_bh(&dcb_lock);
 
 	return prio;
 }
@@ -1850,7 +1888,7 @@ int dcb_ieee_setapp(struct net_device *dev, struct dcb_app *new)
 	if (dev->dcbnl_ops->getdcbx)
 		event.dcbx = dev->dcbnl_ops->getdcbx(dev);
 
-	spin_lock(&dcb_lock);
+	spin_lock_bh(&dcb_lock);
 	/* Search for existing match and abort if found */
 	if (dcb_app_lookup(new, dev->ifindex, new->priority)) {
 		err = -EEXIST;
@@ -1859,7 +1897,7 @@ int dcb_ieee_setapp(struct net_device *dev, struct dcb_app *new)
 
 	err = dcb_app_add(new, dev->ifindex);
 out:
-	spin_unlock(&dcb_lock);
+	spin_unlock_bh(&dcb_lock);
 	if (!err)
 		call_dcbevent_notifiers(DCB_APP_EVENT, &event);
 	return err;
@@ -1882,7 +1920,7 @@ int dcb_ieee_delapp(struct net_device *dev, struct dcb_app *del)
 	if (dev->dcbnl_ops->getdcbx)
 		event.dcbx = dev->dcbnl_ops->getdcbx(dev);
 
-	spin_lock(&dcb_lock);
+	spin_lock_bh(&dcb_lock);
 	/* Search for existing match and remove it. */
 	if ((itr = dcb_app_lookup(del, dev->ifindex, del->priority))) {
 		list_del(&itr->list);
@@ -1890,7 +1928,7 @@ int dcb_ieee_delapp(struct net_device *dev, struct dcb_app *del)
 		err = 0;
 	}
 
-	spin_unlock(&dcb_lock);
+	spin_unlock_bh(&dcb_lock);
 	if (!err)
 		call_dcbevent_notifiers(DCB_APP_EVENT, &event);
 	return err;
@@ -1902,12 +1940,12 @@ static void dcb_flushapp(void)
 	struct dcb_app_type *app;
 	struct dcb_app_type *tmp;
 
-	spin_lock(&dcb_lock);
+	spin_lock_bh(&dcb_lock);
 	list_for_each_entry_safe(app, tmp, &dcb_app_list, list) {
 		list_del(&app->list);
 		kfree(app);
 	}
-	spin_unlock(&dcb_lock);
+	spin_unlock_bh(&dcb_lock);
 }
 
 static int __init dcbnl_init(void)
diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c
index ba07824af4c0..bd9e718c2a20 100644
--- a/net/dccp/ackvec.c
+++ b/net/dccp/ackvec.c
@@ -218,7 +218,7 @@ static void dccp_ackvec_add_new(struct dccp_ackvec *av, u32 num_packets,
 		 * different underlying data structure.
 		 */
 		for (num_packets = num_cells = 1; lost_packets; ++num_cells) {
-			u8 len = min(lost_packets, (u32)DCCPAV_MAX_RUNLEN);
+			u8 len = min_t(u32, lost_packets, DCCPAV_MAX_RUNLEN);
 
 			av->av_buf_head = __ackvec_idx_sub(av->av_buf_head, 1);
 			av->av_buf[av->av_buf_head] = DCCPAV_NOT_RECEIVED | len;
diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index c67816647cce..bebc735f5afc 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -22,8 +22,8 @@
 /*
  * 	DCCP - specific warning and debugging macros.
  */
-#define DCCP_WARN(fmt, a...) LIMIT_NETDEBUG(KERN_WARNING "%s: " fmt,       \
-							__func__, ##a)
+#define DCCP_WARN(fmt, ...)						\
+	net_warn_ratelimited("%s: " fmt, __func__, ##__VA_ARGS__)
 #define DCCP_CRIT(fmt, a...) printk(KERN_CRIT fmt " at %s:%d/%s()\n", ##a, \
 					 __FILE__, __LINE__, __func__)
 #define DCCP_BUG(a...)       do { DCCP_CRIT("BUG: " a); dump_stack(); } while(0)
@@ -280,8 +280,7 @@ struct sock *dccp_v4_request_recv_sock(struct sock *sk, struct sk_buff *skb,
 				       struct request_sock *req,
 				       struct dst_entry *dst);
 struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
-			    struct request_sock *req,
-			    struct request_sock **prev);
+			    struct request_sock *req);
 
 int dccp_child_process(struct sock *parent, struct sock *child,
 		       struct sk_buff *skb);
@@ -310,16 +309,15 @@ int compat_dccp_setsockopt(struct sock *sk, int level, int optname,
 			   char __user *optval, unsigned int optlen);
 #endif
 int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg);
-int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
-		 size_t size);
-int dccp_recvmsg(struct kiocb *iocb, struct sock *sk,
-		 struct msghdr *msg, size_t len, int nonblock, int flags,
-		 int *addr_len);
+int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
+int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
+		 int flags, int *addr_len);
 void dccp_shutdown(struct sock *sk, int how);
 int inet_dccp_listen(struct socket *sock, int backlog);
 unsigned int dccp_poll(struct file *file, struct socket *sock,
 		       poll_table *wait);
 int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
+void dccp_req_err(struct sock *sk, u64 seq);
 
 struct sk_buff *dccp_ctl_make_reset(struct sock *sk, struct sk_buff *skb);
 int dccp_send_reset(struct sock *sk, enum dccp_reset_codes code);
diff --git a/net/dccp/diag.c b/net/dccp/diag.c
index 028fc43aacbd..5a45f8de5d99 100644
--- a/net/dccp/diag.c
+++ b/net/dccp/diag.c
@@ -49,13 +49,14 @@ static void dccp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
 }
 
 static void dccp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
-		struct inet_diag_req_v2 *r, struct nlattr *bc)
+			   const struct inet_diag_req_v2 *r, struct nlattr *bc)
 {
 	inet_diag_dump_icsk(&dccp_hashinfo, skb, cb, r, bc);
 }
 
-static int dccp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh,
-		struct inet_diag_req_v2 *req)
+static int dccp_diag_dump_one(struct sk_buff *in_skb,
+			      const struct nlmsghdr *nlh,
+			      const struct inet_diag_req_v2 *req)
 {
 	return inet_diag_dump_one_icsk(&dccp_hashinfo, in_skb, nlh, req);
 }
diff --git a/net/dccp/feat.c b/net/dccp/feat.c
index 9733ddbc96cb..1704948e6a12 100644
--- a/net/dccp/feat.c
+++ b/net/dccp/feat.c
@@ -478,7 +478,7 @@ static struct dccp_feat_entry *
  * @fn_list: feature-negotiation list to update
  * @feat: one of %dccp_feature_numbers
  * @local: whether local (1) or remote (0) @feat_num is meant
- * @needs_mandatory: whether to use Mandatory feature negotiation options
+ * @mandatory: whether to use Mandatory feature negotiation options
  * @fval: pointer to NN/SP value to be inserted (will be copied)
  */
 static int dccp_feat_push_change(struct list_head *fn_list, u8 feat, u8 local,
@@ -1050,7 +1050,7 @@ static u8 dccp_feat_prefer(u8 preferred_value, u8 *array, u8 array_len)
 
 /**
  * dccp_feat_reconcile  -  Reconcile SP preference lists
- *  @fval: SP list to reconcile into
+ *  @fv: SP list to reconcile into
  *  @arr: received SP preference list
  *  @len: length of @arr in bytes
  *  @is_server: whether this side is the server (and @fv is the server's list)
diff --git a/net/dccp/input.c b/net/dccp/input.c
index 3c8ec7d4a34e..3bd14e885396 100644
--- a/net/dccp/input.c
+++ b/net/dccp/input.c
@@ -537,7 +537,7 @@ static int dccp_rcv_respond_partopen_state_process(struct sock *sk,
 	case DCCP_PKT_DATAACK:
 	case DCCP_PKT_ACK:
 		/*
-		 * FIXME: we should be reseting the PARTOPEN (DELACK) timer
+		 * FIXME: we should be resetting the PARTOPEN (DELACK) timer
 		 * here but only if we haven't used the DELACK timer for
 		 * something else, like sending a delayed ack for a TIMESTAMP
 		 * echo, etc, for now were not clearing it, sending an extra
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 6ca645c4b48e..ccf4c5629b3c 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -89,10 +89,9 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 
 	if (inet->inet_saddr == 0)
 		inet->inet_saddr = fl4->saddr;
-	inet->inet_rcv_saddr = inet->inet_saddr;
-
+	sk_rcv_saddr_set(sk, inet->inet_saddr);
 	inet->inet_dport = usin->sin_port;
-	inet->inet_daddr = daddr;
+	sk_daddr_set(sk, daddr);
 
 	inet_csk(sk)->icsk_ext_hdr_len = 0;
 	if (inet_opt)
@@ -140,7 +139,6 @@ failure:
 	inet->inet_dport = 0;
 	goto out;
 }
-
 EXPORT_SYMBOL_GPL(dccp_v4_connect);
 
 /*
@@ -197,6 +195,32 @@ static void dccp_do_redirect(struct sk_buff *skb, struct sock *sk)
 		dst->ops->redirect(dst, sk, skb);
 }
 
+void dccp_req_err(struct sock *sk, u64 seq)
+	{
+	struct request_sock *req = inet_reqsk(sk);
+	struct net *net = sock_net(sk);
+
+	/*
+	 * ICMPs are not backlogged, hence we cannot get an established
+	 * socket here.
+	 */
+	WARN_ON(req->sk);
+
+	if (!between48(seq, dccp_rsk(req)->dreq_iss, dccp_rsk(req)->dreq_gss)) {
+		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
+		reqsk_put(req);
+	} else {
+		/*
+		 * Still in RESPOND, just remove it silently.
+		 * There is no good way to pass the error to the newly
+		 * created socket, and POSIX does not want network
+		 * errors returned from accept().
+		 */
+		inet_csk_reqsk_queue_drop(req->rsk_listener, req);
+	}
+}
+EXPORT_SYMBOL(dccp_req_err);
+
 /*
  * This routine is called by the ICMP module when it gets some sort of error
  * condition. If err < 0 then the socket should be closed and the error
@@ -229,10 +253,11 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
 		return;
 	}
 
-	sk = inet_lookup(net, &dccp_hashinfo,
-			iph->daddr, dh->dccph_dport,
-			iph->saddr, dh->dccph_sport, inet_iif(skb));
-	if (sk == NULL) {
+	sk = __inet_lookup_established(net, &dccp_hashinfo,
+				       iph->daddr, dh->dccph_dport,
+				       iph->saddr, ntohs(dh->dccph_sport),
+				       inet_iif(skb));
+	if (!sk) {
 		ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS);
 		return;
 	}
@@ -241,6 +266,9 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
 		inet_twsk_put(inet_twsk(sk));
 		return;
 	}
+	seq = dccp_hdr_seq(dh);
+	if (sk->sk_state == DCCP_NEW_SYN_RECV)
+		return dccp_req_err(sk, seq);
 
 	bh_lock_sock(sk);
 	/* If too many ICMPs get dropped on busy
@@ -253,7 +281,6 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
 		goto out;
 
 	dp = dccp_sk(sk);
-	seq = dccp_hdr_seq(dh);
 	if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) &&
 	    !between48(seq, dp->dccps_awl, dp->dccps_awh)) {
 		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
@@ -290,35 +317,6 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
 	}
 
 	switch (sk->sk_state) {
-		struct request_sock *req , **prev;
-	case DCCP_LISTEN:
-		if (sock_owned_by_user(sk))
-			goto out;
-		req = inet_csk_search_req(sk, &prev, dh->dccph_dport,
-					  iph->daddr, iph->saddr);
-		if (!req)
-			goto out;
-
-		/*
-		 * ICMPs are not backlogged, hence we cannot get an established
-		 * socket here.
-		 */
-		WARN_ON(req->sk);
-
-		if (!between48(seq, dccp_rsk(req)->dreq_iss,
-				    dccp_rsk(req)->dreq_gss)) {
-			NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
-			goto out;
-		}
-		/*
-		 * Still in RESPOND, just remove it silently.
-		 * There is no good way to pass the error to the newly
-		 * created socket, and POSIX does not want network
-		 * errors returned from accept().
-		 */
-		inet_csk_reqsk_queue_drop(sk, req, prev);
-		goto out;
-
 	case DCCP_REQUESTING:
 	case DCCP_RESPOND:
 		if (!sock_owned_by_user(sk)) {
@@ -376,7 +374,6 @@ void dccp_v4_send_check(struct sock *sk, struct sk_buff *skb)
 						 inet->inet_saddr,
 						 inet->inet_daddr);
 }
-
 EXPORT_SYMBOL_GPL(dccp_v4_send_check);
 
 static inline u64 dccp_v4_init_sequence(const struct sk_buff *skb)
@@ -410,8 +407,8 @@ struct sock *dccp_v4_request_recv_sock(struct sock *sk, struct sk_buff *skb,
 
 	newinet		   = inet_sk(newsk);
 	ireq		   = inet_rsk(req);
-	newinet->inet_daddr	= ireq->ir_rmt_addr;
-	newinet->inet_rcv_saddr = ireq->ir_loc_addr;
+	sk_daddr_set(newsk, ireq->ir_rmt_addr);
+	sk_rcv_saddr_set(newsk, ireq->ir_loc_addr);
 	newinet->inet_saddr	= ireq->ir_loc_addr;
 	newinet->inet_opt	= ireq->opt;
 	ireq->opt	   = NULL;
@@ -444,7 +441,6 @@ put_and_exit:
 	dccp_done(newsk);
 	goto exit;
 }
-
 EXPORT_SYMBOL_GPL(dccp_v4_request_recv_sock);
 
 static struct sock *dccp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
@@ -452,14 +448,15 @@ static struct sock *dccp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
 	const struct dccp_hdr *dh = dccp_hdr(skb);
 	const struct iphdr *iph = ip_hdr(skb);
 	struct sock *nsk;
-	struct request_sock **prev;
 	/* Find possible connection requests. */
-	struct request_sock *req = inet_csk_search_req(sk, &prev,
-						       dh->dccph_sport,
+	struct request_sock *req = inet_csk_search_req(sk, dh->dccph_sport,
 						       iph->saddr, iph->daddr);
-	if (req != NULL)
-		return dccp_check_req(sk, skb, req, prev);
-
+	if (req) {
+		nsk = dccp_check_req(sk, skb, req);
+		if (!nsk)
+			reqsk_put(req);
+		return nsk;
+	}
 	nsk = inet_lookup_established(sock_net(sk), &dccp_hashinfo,
 				      iph->saddr, dh->dccph_sport,
 				      iph->daddr, dh->dccph_dport,
@@ -578,7 +575,7 @@ static void dccp_v4_reqsk_destructor(struct request_sock *req)
 	kfree(inet_rsk(req)->opt);
 }
 
-void dccp_syn_ack_timeout(struct sock *sk, struct request_sock *req)
+void dccp_syn_ack_timeout(const struct request_sock *req)
 {
 }
 EXPORT_SYMBOL(dccp_syn_ack_timeout);
@@ -627,7 +624,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 	if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1)
 		goto drop;
 
-	req = inet_reqsk_alloc(&dccp_request_sock_ops);
+	req = inet_reqsk_alloc(&dccp_request_sock_ops, sk);
 	if (req == NULL)
 		goto drop;
 
@@ -642,8 +639,10 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 		goto drop_and_free;
 
 	ireq = inet_rsk(req);
-	ireq->ir_loc_addr = ip_hdr(skb)->daddr;
-	ireq->ir_rmt_addr = ip_hdr(skb)->saddr;
+	sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
+	sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr);
+	ireq->ireq_family = AF_INET;
+	ireq->ir_iif = sk->sk_bound_dev_if;
 
 	/*
 	 * Step 3: Process LISTEN state
@@ -670,7 +669,6 @@ drop:
 	DCCP_INC_STATS_BH(DCCP_MIB_ATTEMPTFAILS);
 	return -1;
 }
-
 EXPORT_SYMBOL_GPL(dccp_v4_conn_request);
 
 int dccp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
@@ -729,7 +727,6 @@ discard:
 	kfree_skb(skb);
 	return 0;
 }
-
 EXPORT_SYMBOL_GPL(dccp_v4_do_rcv);
 
 /**
@@ -802,7 +799,6 @@ int dccp_invalid_packet(struct sk_buff *skb)
 
 	return 0;
 }
-
 EXPORT_SYMBOL_GPL(dccp_invalid_packet);
 
 /* this is called when real data arrives */
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 6bcaa33cd804..5165571f397a 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -40,19 +40,6 @@
 static const struct inet_connection_sock_af_ops dccp_ipv6_mapped;
 static const struct inet_connection_sock_af_ops dccp_ipv6_af_ops;
 
-static void dccp_v6_hash(struct sock *sk)
-{
-	if (sk->sk_state != DCCP_CLOSED) {
-		if (inet_csk(sk)->icsk_af_ops == &dccp_ipv6_mapped) {
-			inet_hash(sk);
-			return;
-		}
-		local_bh_disable();
-		__inet6_hash(sk, NULL);
-		local_bh_enable();
-	}
-}
-
 /* add pseudo-header to DCCP checksum stored in skb->csum */
 static inline __sum16 dccp_v6_csum_finish(struct sk_buff *skb,
 				      const struct in6_addr *saddr,
@@ -98,11 +85,12 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		return;
 	}
 
-	sk = inet6_lookup(net, &dccp_hashinfo,
-			&hdr->daddr, dh->dccph_dport,
-			&hdr->saddr, dh->dccph_sport, inet6_iif(skb));
+	sk = __inet6_lookup_established(net, &dccp_hashinfo,
+					&hdr->daddr, dh->dccph_dport,
+					&hdr->saddr, ntohs(dh->dccph_sport),
+					inet6_iif(skb));
 
-	if (sk == NULL) {
+	if (!sk) {
 		ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev),
 				   ICMP6_MIB_INERRORS);
 		return;
@@ -112,6 +100,9 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		inet_twsk_put(inet_twsk(sk));
 		return;
 	}
+	seq = dccp_hdr_seq(dh);
+	if (sk->sk_state == DCCP_NEW_SYN_RECV)
+		return dccp_req_err(sk, seq);
 
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk))
@@ -121,7 +112,6 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		goto out;
 
 	dp = dccp_sk(sk);
-	seq = dccp_hdr_seq(dh);
 	if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) &&
 	    !between48(seq, dp->dccps_awl, dp->dccps_awh)) {
 		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
@@ -162,32 +152,6 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 	/* Might be for an request_sock */
 	switch (sk->sk_state) {
-		struct request_sock *req, **prev;
-	case DCCP_LISTEN:
-		if (sock_owned_by_user(sk))
-			goto out;
-
-		req = inet6_csk_search_req(sk, &prev, dh->dccph_dport,
-					   &hdr->daddr, &hdr->saddr,
-					   inet6_iif(skb));
-		if (req == NULL)
-			goto out;
-
-		/*
-		 * ICMPs are not backlogged, hence we cannot get an established
-		 * socket here.
-		 */
-		WARN_ON(req->sk != NULL);
-
-		if (!between48(seq, dccp_rsk(req)->dreq_iss,
-				    dccp_rsk(req)->dreq_gss)) {
-			NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
-			goto out;
-		}
-
-		inet_csk_reqsk_queue_drop(sk, req, prev);
-		goto out;
-
 	case DCCP_REQUESTING:
 	case DCCP_RESPOND:  /* Cannot happen.
 			       It can, it SYNs are crossed. --ANK */
@@ -330,17 +294,17 @@ static struct sock *dccp_v6_hnd_req(struct sock *sk,struct sk_buff *skb)
 {
 	const struct dccp_hdr *dh = dccp_hdr(skb);
 	const struct ipv6hdr *iph = ipv6_hdr(skb);
+	struct request_sock *req;
 	struct sock *nsk;
-	struct request_sock **prev;
-	/* Find possible connection requests. */
-	struct request_sock *req = inet6_csk_search_req(sk, &prev,
-							dh->dccph_sport,
-							&iph->saddr,
-							&iph->daddr,
-							inet6_iif(skb));
-	if (req != NULL)
-		return dccp_check_req(sk, skb, req, prev);
 
+	req = inet6_csk_search_req(sk, dh->dccph_sport, &iph->saddr,
+				   &iph->daddr, inet6_iif(skb));
+	if (req) {
+		nsk = dccp_check_req(sk, skb, req);
+		if (!nsk)
+			reqsk_put(req);
+		return nsk;
+	}
 	nsk = __inet6_lookup_established(sock_net(sk), &dccp_hashinfo,
 					 &iph->saddr, dh->dccph_sport,
 					 &iph->daddr, ntohs(dh->dccph_dport),
@@ -386,7 +350,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1)
 		goto drop;
 
-	req = inet_reqsk_alloc(&dccp6_request_sock_ops);
+	req = inet_reqsk_alloc(&dccp6_request_sock_ops, sk);
 	if (req == NULL)
 		goto drop;
 
@@ -403,6 +367,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	ireq = inet_rsk(req);
 	ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
 	ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
+	ireq->ireq_family = AF_INET6;
 
 	if (ipv6_opt_accepted(sk, skb, IP6CB(skb)) ||
 	    np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
@@ -469,11 +434,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 
 		memcpy(newnp, np, sizeof(struct ipv6_pinfo));
 
-		ipv6_addr_set_v4mapped(newinet->inet_daddr, &newsk->sk_v6_daddr);
-
-		ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr);
-
-		newsk->sk_v6_rcv_saddr = newnp->saddr;
+		newnp->saddr = newsk->sk_v6_rcv_saddr;
 
 		inet_csk(newsk)->icsk_af_ops = &dccp_ipv6_mapped;
 		newsk->sk_backlog_rcv = dccp_v4_do_rcv;
@@ -591,7 +552,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 		dccp_done(newsk);
 		goto out;
 	}
-	__inet6_hash(newsk, NULL);
+	__inet_hash(newsk, NULL);
 
 	return newsk;
 
@@ -916,9 +877,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 			sk->sk_backlog_rcv = dccp_v6_do_rcv;
 			goto failure;
 		}
-		ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr);
-		ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, &sk->sk_v6_rcv_saddr);
-
+		np->saddr = sk->sk_v6_rcv_saddr;
 		return err;
 	}
 
@@ -1061,7 +1020,7 @@ static struct proto dccp_v6_prot = {
 	.sendmsg	   = dccp_sendmsg,
 	.recvmsg	   = dccp_recvmsg,
 	.backlog_rcv	   = dccp_v6_do_rcv,
-	.hash		   = dccp_v6_hash,
+	.hash		   = inet_hash,
 	.unhash		   = inet_unhash,
 	.accept		   = inet_csk_accept,
 	.get_port	   = inet_csk_get_port,
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index b50dc436db1f..30addee2dd03 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -27,28 +27,16 @@
 
 struct inet_timewait_death_row dccp_death_row = {
 	.sysctl_max_tw_buckets = NR_FILE * 2,
-	.period		= DCCP_TIMEWAIT_LEN / INET_TWDR_TWKILL_SLOTS,
-	.death_lock	= __SPIN_LOCK_UNLOCKED(dccp_death_row.death_lock),
 	.hashinfo	= &dccp_hashinfo,
-	.tw_timer	= TIMER_INITIALIZER(inet_twdr_hangman, 0,
-					    (unsigned long)&dccp_death_row),
-	.twkill_work	= __WORK_INITIALIZER(dccp_death_row.twkill_work,
-					     inet_twdr_twkill_work),
-/* Short-time timewait calendar */
-
-	.twcal_hand	= -1,
-	.twcal_timer	= TIMER_INITIALIZER(inet_twdr_twcal_tick, 0,
-					    (unsigned long)&dccp_death_row),
 };
 
 EXPORT_SYMBOL_GPL(dccp_death_row);
 
 void dccp_time_wait(struct sock *sk, int state, int timeo)
 {
-	struct inet_timewait_sock *tw = NULL;
+	struct inet_timewait_sock *tw;
 
-	if (dccp_death_row.tw_count < dccp_death_row.sysctl_max_tw_buckets)
-		tw = inet_twsk_alloc(sk, state);
+	tw = inet_twsk_alloc(sk, &dccp_death_row, state);
 
 	if (tw != NULL) {
 		const struct inet_connection_sock *icsk = inet_csk(sk);
@@ -71,8 +59,7 @@ void dccp_time_wait(struct sock *sk, int state, int timeo)
 		if (state == DCCP_TIME_WAIT)
 			timeo = DCCP_TIMEWAIT_LEN;
 
-		inet_twsk_schedule(tw, &dccp_death_row, timeo,
-				   DCCP_TIMEWAIT_LEN);
+		inet_twsk_schedule(tw, timeo);
 		inet_twsk_put(tw);
 	} else {
 		/* Sorry, if we're out of memory, just CLOSE this
@@ -152,8 +139,7 @@ EXPORT_SYMBOL_GPL(dccp_create_openreq_child);
  * as an request_sock.
  */
 struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
-			    struct request_sock *req,
-			    struct request_sock **prev)
+			    struct request_sock *req)
 {
 	struct sock *child = NULL;
 	struct dccp_request_sock *dreq = dccp_rsk(req);
@@ -200,8 +186,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
 	if (child == NULL)
 		goto listen_overflow;
 
-	inet_csk_reqsk_queue_unlink(sk, req, prev);
-	inet_csk_reqsk_queue_removed(sk, req);
+	inet_csk_reqsk_queue_drop(sk, req);
 	inet_csk_reqsk_queue_add(sk, req, child);
 out:
 	return child;
@@ -212,7 +197,7 @@ drop:
 	if (dccp_hdr(skb)->dccph_type != DCCP_PKT_RESET)
 		req->rsk_ops->send_reset(sk, skb);
 
-	inet_csk_reqsk_queue_drop(sk, req, prev);
+	inet_csk_reqsk_queue_drop(sk, req);
 	goto out;
 }
 
diff --git a/net/dccp/probe.c b/net/dccp/probe.c
index 595ddf0459db..d8346d0eadeb 100644
--- a/net/dccp/probe.c
+++ b/net/dccp/probe.c
@@ -72,8 +72,7 @@ static void printl(const char *fmt, ...)
 	wake_up(&dccpw.wait);
 }
 
-static int jdccp_sendmsg(struct kiocb *iocb, struct sock *sk,
-			 struct msghdr *msg, size_t size)
+static int jdccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 {
 	const struct inet_sock *inet = inet_sk(sk);
 	struct ccid3_hc_tx_sock *hc = NULL;
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 5ab6627cf370..52a94016526d 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -703,7 +703,7 @@ EXPORT_SYMBOL_GPL(compat_dccp_getsockopt);
 
 static int dccp_msghdr_parse(struct msghdr *msg, struct sk_buff *skb)
 {
-	struct cmsghdr *cmsg = CMSG_FIRSTHDR(msg);
+	struct cmsghdr *cmsg;
 
 	/*
 	 * Assign an (opaque) qpolicy priority value to skb->priority.
@@ -717,8 +717,7 @@ static int dccp_msghdr_parse(struct msghdr *msg, struct sk_buff *skb)
 	 */
 	skb->priority = 0;
 
-	for (; cmsg != NULL; cmsg = CMSG_NXTHDR(msg, cmsg)) {
-
+	for_each_cmsghdr(cmsg, msg) {
 		if (!CMSG_OK(msg, cmsg))
 			return -EINVAL;
 
@@ -742,8 +741,7 @@ static int dccp_msghdr_parse(struct msghdr *msg, struct sk_buff *skb)
 	return 0;
 }
 
-int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
-		 size_t len)
+int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 {
 	const struct dccp_sock *dp = dccp_sk(sk);
 	const int flags = msg->msg_flags;
@@ -781,7 +779,7 @@ int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		goto out_release;
 
 	skb_reserve(skb, sk->sk_prot->max_header);
-	rc = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
+	rc = memcpy_from_msg(skb_put(skb, len), msg, len);
 	if (rc != 0)
 		goto out_discard;
 
@@ -807,8 +805,8 @@ out_discard:
 
 EXPORT_SYMBOL_GPL(dccp_sendmsg);
 
-int dccp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
-		 size_t len, int nonblock, int flags, int *addr_len)
+int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
+		 int flags, int *addr_len)
 {
 	const struct dccp_hdr *dh;
 	long timeo;
@@ -896,7 +894,7 @@ verify_sock_status:
 		else if (len < skb->len)
 			msg->msg_flags |= MSG_TRUNC;
 
-		if (skb_copy_datagram_iovec(skb, 0, msg->msg_iov, len)) {
+		if (skb_copy_datagram_msg(skb, 0, msg, len)) {
 			/* Exception. Bailout! */
 			len = -EFAULT;
 			break;
diff --git a/net/dccp/timer.c b/net/dccp/timer.c
index 1cd46a345cb0..3ef7acef3ce8 100644
--- a/net/dccp/timer.c
+++ b/net/dccp/timer.c
@@ -161,33 +161,11 @@ out:
 	sock_put(sk);
 }
 
-/*
- *	Timer for listening sockets
- */
-static void dccp_response_timer(struct sock *sk)
-{
-	inet_csk_reqsk_queue_prune(sk, TCP_SYNQ_INTERVAL, DCCP_TIMEOUT_INIT,
-				   DCCP_RTO_MAX);
-}
-
 static void dccp_keepalive_timer(unsigned long data)
 {
 	struct sock *sk = (struct sock *)data;
 
-	/* Only process if socket is not in use. */
-	bh_lock_sock(sk);
-	if (sock_owned_by_user(sk)) {
-		/* Try again later. */
-		inet_csk_reset_keepalive_timer(sk, HZ / 20);
-		goto out;
-	}
-
-	if (sk->sk_state == DCCP_LISTEN) {
-		dccp_response_timer(sk);
-		goto out;
-	}
-out:
-	bh_unlock_sock(sk);
+	pr_err("dccp should not use a keepalive timer !\n");
 	sock_put(sk);
 }
 
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 25733d538147..754484b3cd0e 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -1669,8 +1669,8 @@ static int dn_data_ready(struct sock *sk, struct sk_buff_head *q, int flags, int
 }
 
 
-static int dn_recvmsg(struct kiocb *iocb, struct socket *sock,
-	struct msghdr *msg, size_t size, int flags)
+static int dn_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+		      int flags)
 {
 	struct sock *sk = sock->sk;
 	struct dn_scp *scp = DN_SK(sk);
@@ -1760,7 +1760,7 @@ static int dn_recvmsg(struct kiocb *iocb, struct socket *sock,
 		if ((chunk + copied) > size)
 			chunk = size - copied;
 
-		if (memcpy_toiovec(msg->msg_iov, skb->data, chunk)) {
+		if (memcpy_to_msg(msg, skb->data, chunk)) {
 			rv = -EFAULT;
 			break;
 		}
@@ -1905,8 +1905,7 @@ static inline struct sk_buff *dn_alloc_send_pskb(struct sock *sk,
 	return skb;
 }
 
-static int dn_sendmsg(struct kiocb *iocb, struct socket *sock,
-		      struct msghdr *msg, size_t size)
+static int dn_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 {
 	struct sock *sk = sock->sk;
 	struct dn_scp *scp = DN_SK(sk);
@@ -2032,7 +2031,7 @@ static int dn_sendmsg(struct kiocb *iocb, struct socket *sock,
 
 		skb_reserve(skb, 64 + DN_MAX_NSP_DATA_HEADER);
 
-		if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) {
+		if (memcpy_from_msg(skb_put(skb, len), msg, len)) {
 			err = -EFAULT;
 			goto out;
 		}
diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c
index 4400da7739da..b2c26b081134 100644
--- a/net/decnet/dn_dev.c
+++ b/net/decnet/dn_dev.c
@@ -702,7 +702,8 @@ static int dn_nl_fill_ifaddr(struct sk_buff *skb, struct dn_ifaddr *ifa,
 	     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);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c
index d332aefb0846..df4803437888 100644
--- a/net/decnet/dn_fib.c
+++ b/net/decnet/dn_fib.c
@@ -298,7 +298,8 @@ struct dn_fib_info *dn_fib_create_info(const struct rtmsg *r, struct nlattr *att
 			int type = nla_type(attr);
 
 			if (type) {
-				if (type > RTAX_MAX || nla_len(attr) < 4)
+				if (type > RTAX_MAX || type == RTAX_CC_ALGO ||
+				    nla_len(attr) < 4)
 					goto err_inval;
 
 				fi->fib_metrics[type-1] = nla_get_u32(attr);
diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c
index c8121ceddb9e..4507b188fc51 100644
--- a/net/decnet/dn_neigh.c
+++ b/net/decnet/dn_neigh.c
@@ -49,41 +49,17 @@
 #include <net/dn_route.h>
 
 static int dn_neigh_construct(struct neighbour *);
-static void dn_long_error_report(struct neighbour *, struct sk_buff *);
-static void dn_short_error_report(struct neighbour *, struct sk_buff *);
-static int dn_long_output(struct neighbour *, struct sk_buff *);
-static int dn_short_output(struct neighbour *, struct sk_buff *);
-static int dn_phase3_output(struct neighbour *, struct sk_buff *);
-
-
-/*
- * For talking to broadcast devices: Ethernet & PPP
- */
-static const struct neigh_ops dn_long_ops = {
-	.family =		AF_DECnet,
-	.error_report =		dn_long_error_report,
-	.output =		dn_long_output,
-	.connected_output =	dn_long_output,
-};
+static void dn_neigh_error_report(struct neighbour *, struct sk_buff *);
+static int dn_neigh_output(struct neighbour *neigh, struct sk_buff *skb);
 
 /*
- * For talking to pointopoint and multidrop devices: DDCMP and X.25
+ * Operations for adding the link layer header.
  */
-static const struct neigh_ops dn_short_ops = {
+static const struct neigh_ops dn_neigh_ops = {
 	.family =		AF_DECnet,
-	.error_report =		dn_short_error_report,
-	.output =		dn_short_output,
-	.connected_output =	dn_short_output,
-};
-
-/*
- * For talking to DECnet phase III nodes
- */
-static const struct neigh_ops dn_phase3_ops = {
-	.family =		AF_DECnet,
-	.error_report =		dn_short_error_report, /* Can use short version here */
-	.output =		dn_phase3_output,
-	.connected_output =	dn_phase3_output,
+	.error_report =		dn_neigh_error_report,
+	.output =		dn_neigh_output,
+	.connected_output =	dn_neigh_output,
 };
 
 static u32 dn_neigh_hash(const void *pkey,
@@ -93,11 +69,18 @@ static u32 dn_neigh_hash(const void *pkey,
 	return jhash_2words(*(__u16 *)pkey, 0, hash_rnd[0]);
 }
 
+static bool dn_key_eq(const struct neighbour *neigh, const void *pkey)
+{
+	return neigh_key_eq16(neigh, pkey);
+}
+
 struct neigh_table dn_neigh_table = {
 	.family =			PF_DECnet,
 	.entry_size =			NEIGH_ENTRY_SIZE(sizeof(struct dn_neigh)),
 	.key_len =			sizeof(__le16),
+	.protocol =			cpu_to_be16(ETH_P_DNA_RT),
 	.hash =				dn_neigh_hash,
+	.key_eq =			dn_key_eq,
 	.constructor =			dn_neigh_construct,
 	.id =				"dn_neigh_cache",
 	.parms ={
@@ -146,16 +129,9 @@ static int dn_neigh_construct(struct neighbour *neigh)
 
 	__neigh_parms_put(neigh->parms);
 	neigh->parms = neigh_parms_clone(parms);
-
-	if (dn_db->use_long)
-		neigh->ops = &dn_long_ops;
-	else
-		neigh->ops = &dn_short_ops;
 	rcu_read_unlock();
 
-	if (dn->flags & DN_NDFLAG_P3)
-		neigh->ops = &dn_phase3_ops;
-
+	neigh->ops = &dn_neigh_ops;
 	neigh->nud_state = NUD_NOARP;
 	neigh->output = neigh->ops->connected_output;
 
@@ -187,24 +163,16 @@ static int dn_neigh_construct(struct neighbour *neigh)
 	return 0;
 }
 
-static void dn_long_error_report(struct neighbour *neigh, struct sk_buff *skb)
-{
-	printk(KERN_DEBUG "dn_long_error_report: called\n");
-	kfree_skb(skb);
-}
-
-
-static void dn_short_error_report(struct neighbour *neigh, struct sk_buff *skb)
+static void dn_neigh_error_report(struct neighbour *neigh, struct sk_buff *skb)
 {
-	printk(KERN_DEBUG "dn_short_error_report: called\n");
+	printk(KERN_DEBUG "dn_neigh_error_report: called\n");
 	kfree_skb(skb);
 }
 
-static int dn_neigh_output_packet(struct sk_buff *skb)
+static int dn_neigh_output(struct neighbour *neigh, struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 	struct dn_route *rt = (struct dn_route *)dst;
-	struct neighbour *neigh = rt->n;
 	struct net_device *dev = neigh->dev;
 	char mac_addr[ETH_ALEN];
 	unsigned int seq;
@@ -226,7 +194,20 @@ static int dn_neigh_output_packet(struct sk_buff *skb)
 	return err;
 }
 
-static int dn_long_output(struct neighbour *neigh, struct sk_buff *skb)
+static int dn_neigh_output_packet(struct sock *sk, struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	struct dn_route *rt = (struct dn_route *)dst;
+	struct neighbour *neigh = rt->n;
+
+	return neigh->output(neigh, skb);
+}
+
+/*
+ * For talking to broadcast devices: Ethernet & PPP
+ */
+static int dn_long_output(struct neighbour *neigh, struct sock *sk,
+			  struct sk_buff *skb)
 {
 	struct net_device *dev = neigh->dev;
 	int headroom = dev->hard_header_len + sizeof(struct dn_long_packet) + 3;
@@ -265,11 +246,15 @@ static int dn_long_output(struct neighbour *neigh, struct sk_buff *skb)
 
 	skb_reset_network_header(skb);
 
-	return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, skb, NULL,
-		       neigh->dev, dn_neigh_output_packet);
+	return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, sk, skb,
+		       NULL, neigh->dev, dn_neigh_output_packet);
 }
 
-static int dn_short_output(struct neighbour *neigh, struct sk_buff *skb)
+/*
+ * For talking to pointopoint and multidrop devices: DDCMP and X.25
+ */
+static int dn_short_output(struct neighbour *neigh, struct sock *sk,
+			   struct sk_buff *skb)
 {
 	struct net_device *dev = neigh->dev;
 	int headroom = dev->hard_header_len + sizeof(struct dn_short_packet) + 2;
@@ -301,15 +286,17 @@ static int dn_short_output(struct neighbour *neigh, struct sk_buff *skb)
 
 	skb_reset_network_header(skb);
 
-	return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, skb, NULL,
-		       neigh->dev, dn_neigh_output_packet);
+	return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, sk, skb,
+		       NULL, neigh->dev, dn_neigh_output_packet);
 }
 
 /*
- * Phase 3 output is the same is short output, execpt that
+ * For talking to DECnet phase III nodes
+ * Phase 3 output is the same as short output, execpt that
  * it clears the area bits before transmission.
  */
-static int dn_phase3_output(struct neighbour *neigh, struct sk_buff *skb)
+static int dn_phase3_output(struct neighbour *neigh, struct sock *sk,
+			    struct sk_buff *skb)
 {
 	struct net_device *dev = neigh->dev;
 	int headroom = dev->hard_header_len + sizeof(struct dn_short_packet) + 2;
@@ -340,8 +327,34 @@ static int dn_phase3_output(struct neighbour *neigh, struct sk_buff *skb)
 
 	skb_reset_network_header(skb);
 
-	return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, skb, NULL,
-		       neigh->dev, dn_neigh_output_packet);
+	return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, sk, skb,
+		       NULL, neigh->dev, dn_neigh_output_packet);
+}
+
+int dn_to_neigh_output(struct sock *sk, struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	struct dn_route *rt = (struct dn_route *) dst;
+	struct neighbour *neigh = rt->n;
+	struct dn_neigh *dn = (struct dn_neigh *)neigh;
+	struct dn_dev *dn_db;
+	bool use_long;
+
+	rcu_read_lock();
+	dn_db = rcu_dereference(neigh->dev->dn_ptr);
+	if (dn_db == NULL) {
+		rcu_read_unlock();
+		return -EINVAL;
+	}
+	use_long = dn_db->use_long;
+	rcu_read_unlock();
+
+	if (dn->flags & DN_NDFLAG_P3)
+		return dn_phase3_output(neigh, sk, skb);
+	if (use_long)
+		return dn_long_output(neigh, sk, skb);
+	else
+		return dn_short_output(neigh, sk, skb);
 }
 
 /*
@@ -362,7 +375,7 @@ void dn_neigh_pointopoint_hello(struct sk_buff *skb)
 /*
  * Ethernet router hello message received
  */
-int dn_neigh_router_hello(struct sk_buff *skb)
+int dn_neigh_router_hello(struct sock *sk, struct sk_buff *skb)
 {
 	struct rtnode_hello_message *msg = (struct rtnode_hello_message *)skb->data;
 
@@ -424,7 +437,7 @@ int dn_neigh_router_hello(struct sk_buff *skb)
 /*
  * Endnode hello message received
  */
-int dn_neigh_endnode_hello(struct sk_buff *skb)
+int dn_neigh_endnode_hello(struct sock *sk, struct sk_buff *skb)
 {
 	struct endnode_hello_message *msg = (struct endnode_hello_message *)skb->data;
 	struct neighbour *neigh;
@@ -591,7 +604,7 @@ static const struct file_operations dn_neigh_seq_fops = {
 
 void __init dn_neigh_init(void)
 {
-	neigh_table_init(&dn_neigh_table);
+	neigh_table_init(NEIGH_DN_TABLE, &dn_neigh_table);
 	proc_create("decnet_neigh", S_IRUGO, init_net.proc_net,
 		    &dn_neigh_seq_fops);
 }
@@ -599,5 +612,5 @@ void __init dn_neigh_init(void)
 void __exit dn_neigh_cleanup(void)
 {
 	remove_proc_entry("decnet_neigh", init_net.proc_net);
-	neigh_table_clear(&dn_neigh_table);
+	neigh_table_clear(NEIGH_DN_TABLE, &dn_neigh_table);
 }
diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c
index fe5f01485d33..a321eac9fd0c 100644
--- a/net/decnet/dn_nsp_in.c
+++ b/net/decnet/dn_nsp_in.c
@@ -714,7 +714,7 @@ out:
 	return ret;
 }
 
-static int dn_nsp_rx_packet(struct sk_buff *skb)
+static int dn_nsp_rx_packet(struct sock *sk2, struct sk_buff *skb)
 {
 	struct dn_skb_cb *cb = DN_SKB_CB(skb);
 	struct sock *sk = NULL;
@@ -814,7 +814,8 @@ free_out:
 
 int dn_nsp_rx(struct sk_buff *skb)
 {
-	return NF_HOOK(NFPROTO_DECNET, NF_DN_LOCAL_IN, skb, skb->dev, NULL,
+	return NF_HOOK(NFPROTO_DECNET, NF_DN_LOCAL_IN, NULL, skb,
+		       skb->dev, NULL,
 		       dn_nsp_rx_packet);
 }
 
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index daccc4a36d80..03227ffd19ce 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -136,7 +136,6 @@ int decnet_dst_gc_interval = 2;
 
 static struct dst_ops dn_dst_ops = {
 	.family =		PF_DECnet,
-	.protocol =		cpu_to_be16(ETH_P_DNA_RT),
 	.gc_thresh =		128,
 	.gc =			dn_dst_gc,
 	.check =		dn_dst_check,
@@ -513,7 +512,7 @@ static int dn_return_long(struct sk_buff *skb)
  *
  * Returns: result of input function if route is found, error code otherwise
  */
-static int dn_route_rx_packet(struct sk_buff *skb)
+static int dn_route_rx_packet(struct sock *sk, struct sk_buff *skb)
 {
 	struct dn_skb_cb *cb;
 	int err;
@@ -574,7 +573,8 @@ static int dn_route_rx_long(struct sk_buff *skb)
 	ptr++;
 	cb->hops = *ptr++; /* Visit Count */
 
-	return NF_HOOK(NFPROTO_DECNET, NF_DN_PRE_ROUTING, skb, skb->dev, NULL,
+	return NF_HOOK(NFPROTO_DECNET, NF_DN_PRE_ROUTING, NULL, skb,
+		       skb->dev, NULL,
 		       dn_route_rx_packet);
 
 drop_it:
@@ -601,7 +601,8 @@ static int dn_route_rx_short(struct sk_buff *skb)
 	ptr += 2;
 	cb->hops = *ptr & 0x3f;
 
-	return NF_HOOK(NFPROTO_DECNET, NF_DN_PRE_ROUTING, skb, skb->dev, NULL,
+	return NF_HOOK(NFPROTO_DECNET, NF_DN_PRE_ROUTING, NULL, skb,
+		       skb->dev, NULL,
 		       dn_route_rx_packet);
 
 drop_it:
@@ -609,7 +610,7 @@ drop_it:
 	return NET_RX_DROP;
 }
 
-static int dn_route_discard(struct sk_buff *skb)
+static int dn_route_discard(struct sock *sk, struct sk_buff *skb)
 {
 	/*
 	 * I know we drop the packet here, but thats considered success in
@@ -619,7 +620,7 @@ static int dn_route_discard(struct sk_buff *skb)
 	return NET_RX_SUCCESS;
 }
 
-static int dn_route_ptp_hello(struct sk_buff *skb)
+static int dn_route_ptp_hello(struct sock *sk, struct sk_buff *skb)
 {
 	dn_dev_hello(skb);
 	dn_neigh_pointopoint_hello(skb);
@@ -705,22 +706,22 @@ int dn_route_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type
 		switch (flags & DN_RT_CNTL_MSK) {
 		case DN_RT_PKT_HELO:
 			return NF_HOOK(NFPROTO_DECNET, NF_DN_HELLO,
-				       skb, skb->dev, NULL,
+				       NULL, skb, skb->dev, NULL,
 				       dn_route_ptp_hello);
 
 		case DN_RT_PKT_L1RT:
 		case DN_RT_PKT_L2RT:
 			return NF_HOOK(NFPROTO_DECNET, NF_DN_ROUTE,
-				       skb, skb->dev, NULL,
+				       NULL, skb, skb->dev, NULL,
 				       dn_route_discard);
 		case DN_RT_PKT_ERTH:
 			return NF_HOOK(NFPROTO_DECNET, NF_DN_HELLO,
-				       skb, skb->dev, NULL,
+				       NULL, skb, skb->dev, NULL,
 				       dn_neigh_router_hello);
 
 		case DN_RT_PKT_EEDH:
 			return NF_HOOK(NFPROTO_DECNET, NF_DN_HELLO,
-				       skb, skb->dev, NULL,
+				       NULL, skb, skb->dev, NULL,
 				       dn_neigh_endnode_hello);
 		}
 	} else {
@@ -743,15 +744,6 @@ out:
 	return NET_RX_DROP;
 }
 
-static int dn_to_neigh_output(struct sk_buff *skb)
-{
-	struct dst_entry *dst = skb_dst(skb);
-	struct dn_route *rt = (struct dn_route *) dst;
-	struct neighbour *n = rt->n;
-
-	return n->output(n, skb);
-}
-
 static int dn_output(struct sock *sk, struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
@@ -778,7 +770,8 @@ static int dn_output(struct sock *sk, struct sk_buff *skb)
 	cb->rt_flags |= DN_RT_F_IE;
 	cb->hops = 0;
 
-	return NF_HOOK(NFPROTO_DECNET, NF_DN_LOCAL_OUT, skb, NULL, dev,
+	return NF_HOOK(NFPROTO_DECNET, NF_DN_LOCAL_OUT, sk, skb,
+		       NULL, dev,
 		       dn_to_neigh_output);
 
 error:
@@ -826,7 +819,8 @@ static int dn_forward(struct sk_buff *skb)
 	if (rt->rt_flags & RTCF_DOREDIRECT)
 		cb->rt_flags |= DN_RT_F_IE;
 
-	return NF_HOOK(NFPROTO_DECNET, NF_DN_FORWARD, skb, dev, skb->dev,
+	return NF_HOOK(NFPROTO_DECNET, NF_DN_FORWARD, NULL, skb,
+		       dev, skb->dev,
 		       dn_to_neigh_output);
 
 drop:
@@ -1062,7 +1056,7 @@ source_ok:
 	if (decnet_debug_level & 16)
 		printk(KERN_DEBUG
 		       "dn_route_output_slow: initial checks complete."
-		       " dst=%o4x src=%04x oif=%d try_hard=%d\n",
+		       " dst=%04x src=%04x oif=%d try_hard=%d\n",
 		       le16_to_cpu(fld.daddr), le16_to_cpu(fld.saddr),
 		       fld.flowidn_oif, try_hard);
 
@@ -1616,7 +1610,8 @@ static int dn_rt_fill_info(struct sk_buff *skb, u32 portid, u32 seq,
 	    nla_put_u32(skb, RTA_IIF, rt->fld.flowidn_iif) < 0)
 		goto errout;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 errout:
 	nlmsg_cancel(skb, nlh);
@@ -1709,9 +1704,6 @@ static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 		rt->rt_flags |= RTCF_NOTIFY;
 
 	err = dn_rt_fill_info(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWROUTE, 0, 0);
-
-	if (err == 0)
-		goto out_free;
 	if (err < 0) {
 		err = -EMSGSIZE;
 		goto out_free;
@@ -1762,7 +1754,7 @@ int dn_cache_dump(struct sk_buff *skb, struct netlink_callback *cb)
 			skb_dst_set(skb, dst_clone(&rt->dst));
 			if (dn_rt_fill_info(skb, NETLINK_CB(cb->skb).portid,
 					cb->nlh->nlmsg_seq, RTM_NEWROUTE,
-					1, NLM_F_MULTI) <= 0) {
+					1, NLM_F_MULTI) < 0) {
 				skb_dst_drop(skb);
 				rcu_read_unlock_bh();
 				goto done;
diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c
index faf7cc3483fe..9d66a0f72f90 100644
--- a/net/decnet/dn_rules.c
+++ b/net/decnet/dn_rules.c
@@ -248,7 +248,9 @@ void __init dn_fib_rules_init(void)
 
 void __exit dn_fib_rules_cleanup(void)
 {
+	rtnl_lock();
 	fib_rules_unregister(dn_fib_rules_ops);
+	rtnl_unlock();
 	rcu_barrier();
 }
 
diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c
index 86e3807052e9..1540b506e3e0 100644
--- a/net/decnet/dn_table.c
+++ b/net/decnet/dn_table.c
@@ -29,6 +29,7 @@
 #include <linux/route.h> /* RTF_xxx */
 #include <net/neighbour.h>
 #include <net/netlink.h>
+#include <net/tcp.h>
 #include <net/dst.h>
 #include <net/flow.h>
 #include <net/fib_rules.h>
@@ -273,7 +274,8 @@ static inline size_t dn_fib_nlmsg_size(struct dn_fib_info *fi)
 	size_t payload = NLMSG_ALIGN(sizeof(struct rtmsg))
 			 + nla_total_size(4) /* RTA_TABLE */
 			 + nla_total_size(2) /* RTA_DST */
-			 + nla_total_size(4); /* RTA_PRIORITY */
+			 + nla_total_size(4) /* RTA_PRIORITY */
+			 + nla_total_size(TCP_CA_NAME_MAX); /* RTAX_CC_ALGO */
 
 	/* space for nested metrics */
 	payload += nla_total_size((RTAX_MAX * nla_total_size(4)));
@@ -365,7 +367,8 @@ static int dn_fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 		nla_nest_end(skb, mp_head);
 	}
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 errout:
 	nlmsg_cancel(skb, nlh);
diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c
index e4d9560a910b..af34fc9bdf69 100644
--- a/net/decnet/netfilter/dn_rtmsg.c
+++ b/net/decnet/netfilter/dn_rtmsg.c
@@ -89,9 +89,7 @@ static void dnrmg_send_peer(struct sk_buff *skb)
 
 static unsigned int dnrmg_hook(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 *))
+			const struct nf_hook_state *state)
 {
 	dnrmg_send_peer(skb);
 	return NF_ACCEPT;
diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig
index a585fd6352eb..ff7736f7ff42 100644
--- a/net/dsa/Kconfig
+++ b/net/dsa/Kconfig
@@ -5,12 +5,26 @@ config HAVE_NET_DSA
 # Drivers must select NET_DSA and the appropriate tagging format
 
 config NET_DSA
-	tristate
-	depends on HAVE_NET_DSA
+	tristate "Distributed Switch Architecture"
+	depends on HAVE_NET_DSA && NET_SWITCHDEV
 	select PHYLIB
+	---help---
+	  Say Y if you want to enable support for the hardware switches supported
+	  by the Distributed Switch Architecture.
 
 if NET_DSA
 
+config NET_DSA_HWMON
+	bool "Distributed Switch Architecture HWMON support"
+	default y
+	depends on HWMON && !(NET_DSA=y && HWMON=m)
+	---help---
+	  Say Y if you want to expose thermal sensor data on switches supported
+	  by the Distributed Switch Architecture.
+
+	  Some of those switches contain thermal sensors. This data is available
+	  via the hwmon sysfs interface and exposes the onboard sensors.
+
 # tagging formats
 config NET_DSA_TAG_BRCM
 	bool
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 6317b41c99b0..392e29a0227d 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -9,6 +9,9 @@
  * (at your option) any later version.
  */
 
+#include <linux/ctype.h>
+#include <linux/device.h>
+#include <linux/hwmon.h>
 #include <linux/list.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
@@ -17,6 +20,8 @@
 #include <linux/of.h>
 #include <linux/of_mdio.h>
 #include <linux/of_platform.h>
+#include <linux/of_net.h>
+#include <linux/sysfs.h>
 #include "dsa_priv.h"
 
 char dsa_driver_version[] = "0.1";
@@ -71,45 +76,114 @@ dsa_switch_probe(struct device *host_dev, int sw_addr, char **_name)
 	return ret;
 }
 
+/* hwmon support ************************************************************/
 
-/* basic switch operations **************************************************/
-static struct dsa_switch *
-dsa_switch_setup(struct dsa_switch_tree *dst, int index,
-		 struct device *parent, struct device *host_dev)
+#ifdef CONFIG_NET_DSA_HWMON
+
+static ssize_t temp1_input_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
-	struct dsa_chip_data *pd = dst->pd->chip + index;
-	struct dsa_switch_driver *drv;
-	struct dsa_switch *ds;
+	struct dsa_switch *ds = dev_get_drvdata(dev);
+	int temp, ret;
+
+	ret = ds->drv->get_temp(ds, &temp);
+	if (ret < 0)
+		return ret;
+
+	return sprintf(buf, "%d\n", temp * 1000);
+}
+static DEVICE_ATTR_RO(temp1_input);
+
+static ssize_t temp1_max_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	struct dsa_switch *ds = dev_get_drvdata(dev);
+	int temp, ret;
+
+	ret = ds->drv->get_temp_limit(ds, &temp);
+	if (ret < 0)
+		return ret;
+
+	return sprintf(buf, "%d\n", temp * 1000);
+}
+
+static ssize_t temp1_max_store(struct device *dev,
+			       struct device_attribute *attr, const char *buf,
+			       size_t count)
+{
+	struct dsa_switch *ds = dev_get_drvdata(dev);
+	int temp, ret;
+
+	ret = kstrtoint(buf, 0, &temp);
+	if (ret < 0)
+		return ret;
+
+	ret = ds->drv->set_temp_limit(ds, DIV_ROUND_CLOSEST(temp, 1000));
+	if (ret < 0)
+		return ret;
+
+	return count;
+}
+static DEVICE_ATTR_RW(temp1_max);
+
+static ssize_t temp1_max_alarm_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	struct dsa_switch *ds = dev_get_drvdata(dev);
+	bool alarm;
 	int ret;
-	char *name;
-	int i;
-	bool valid_name_found = false;
 
-	/*
-	 * Probe for switch model.
-	 */
-	drv = dsa_switch_probe(host_dev, pd->sw_addr, &name);
-	if (drv == NULL) {
-		printk(KERN_ERR "%s[%d]: could not detect attached switch\n",
-		       dst->master_netdev->name, index);
-		return ERR_PTR(-EINVAL);
+	ret = ds->drv->get_temp_alarm(ds, &alarm);
+	if (ret < 0)
+		return ret;
+
+	return sprintf(buf, "%d\n", alarm);
+}
+static DEVICE_ATTR_RO(temp1_max_alarm);
+
+static struct attribute *dsa_hwmon_attrs[] = {
+	&dev_attr_temp1_input.attr,	/* 0 */
+	&dev_attr_temp1_max.attr,	/* 1 */
+	&dev_attr_temp1_max_alarm.attr,	/* 2 */
+	NULL
+};
+
+static umode_t dsa_hwmon_attrs_visible(struct kobject *kobj,
+				       struct attribute *attr, int index)
+{
+	struct device *dev = container_of(kobj, struct device, kobj);
+	struct dsa_switch *ds = dev_get_drvdata(dev);
+	struct dsa_switch_driver *drv = ds->drv;
+	umode_t mode = attr->mode;
+
+	if (index == 1) {
+		if (!drv->get_temp_limit)
+			mode = 0;
+		else if (!drv->set_temp_limit)
+			mode &= ~S_IWUSR;
+	} else if (index == 2 && !drv->get_temp_alarm) {
+		mode = 0;
 	}
-	printk(KERN_INFO "%s[%d]: detected a %s switch\n",
-		dst->master_netdev->name, index, name);
+	return mode;
+}
 
+static const struct attribute_group dsa_hwmon_group = {
+	.attrs = dsa_hwmon_attrs,
+	.is_visible = dsa_hwmon_attrs_visible,
+};
+__ATTRIBUTE_GROUPS(dsa_hwmon);
 
-	/*
-	 * Allocate and initialise switch state.
-	 */
-	ds = kzalloc(sizeof(*ds) + drv->priv_size, GFP_KERNEL);
-	if (ds == NULL)
-		return ERR_PTR(-ENOMEM);
+#endif /* CONFIG_NET_DSA_HWMON */
 
-	ds->dst = dst;
-	ds->index = index;
-	ds->pd = dst->pd->chip + index;
-	ds->drv = drv;
-	ds->master_dev = host_dev;
+/* basic switch operations **************************************************/
+static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent)
+{
+	struct dsa_switch_driver *drv = ds->drv;
+	struct dsa_switch_tree *dst = ds->dst;
+	struct dsa_chip_data *pd = ds->pd;
+	bool valid_name_found = false;
+	int index = ds->index;
+	int i, ret;
 
 	/*
 	 * Validate supplied switch configuration.
@@ -123,7 +197,8 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index,
 
 		if (!strcmp(name, "cpu")) {
 			if (dst->cpu_switch != -1) {
-				printk(KERN_ERR "multiple cpu ports?!\n");
+				netdev_err(dst->master_netdev,
+					   "multiple cpu ports?!\n");
 				ret = -EINVAL;
 				goto out;
 			}
@@ -153,7 +228,7 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index,
 	 * switch.
 	 */
 	if (dst->cpu_switch == index) {
-		switch (drv->tag_protocol) {
+		switch (ds->tag_protocol) {
 #ifdef CONFIG_NET_DSA_TAG_DSA
 		case DSA_TAG_PROTO_DSA:
 			dst->rcv = dsa_netdev_ops.rcv;
@@ -181,7 +256,7 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index,
 			goto out;
 		}
 
-		dst->tag_protocol = drv->tag_protocol;
+		dst->tag_protocol = ds->tag_protocol;
 	}
 
 	/*
@@ -211,34 +286,101 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index,
 	 * Create network devices for physical switch ports.
 	 */
 	for (i = 0; i < DSA_MAX_PORTS; i++) {
-		struct net_device *slave_dev;
-
 		if (!(ds->phys_port_mask & (1 << i)))
 			continue;
 
-		slave_dev = dsa_slave_create(ds, parent, i, pd->port_names[i]);
-		if (slave_dev == NULL) {
-			printk(KERN_ERR "%s[%d]: can't create dsa "
-			       "slave device for port %d(%s)\n",
-			       dst->master_netdev->name,
-			       index, i, pd->port_names[i]);
-			continue;
+		ret = dsa_slave_create(ds, parent, i, pd->port_names[i]);
+		if (ret < 0) {
+			netdev_err(dst->master_netdev, "[%d]: can't create dsa slave device for port %d(%s)\n",
+				   index, i, pd->port_names[i]);
+			ret = 0;
 		}
+	}
 
-		ds->ports[i] = slave_dev;
+#ifdef CONFIG_NET_DSA_HWMON
+	/* If the switch provides a temperature sensor,
+	 * register with hardware monitoring subsystem.
+	 * Treat registration error as non-fatal and ignore it.
+	 */
+	if (drv->get_temp) {
+		const char *netname = netdev_name(dst->master_netdev);
+		char hname[IFNAMSIZ + 1];
+		int i, j;
+
+		/* Create valid hwmon 'name' attribute */
+		for (i = j = 0; i < IFNAMSIZ && netname[i]; i++) {
+			if (isalnum(netname[i]))
+				hname[j++] = netname[i];
+		}
+		hname[j] = '\0';
+		scnprintf(ds->hwmon_name, sizeof(ds->hwmon_name), "%s_dsa%d",
+			  hname, index);
+		ds->hwmon_dev = hwmon_device_register_with_groups(NULL,
+					ds->hwmon_name, ds, dsa_hwmon_groups);
+		if (IS_ERR(ds->hwmon_dev))
+			ds->hwmon_dev = NULL;
 	}
+#endif /* CONFIG_NET_DSA_HWMON */
 
-	return ds;
+	return ret;
 
 out_free:
 	mdiobus_free(ds->slave_mii_bus);
 out:
 	kfree(ds);
-	return ERR_PTR(ret);
+	return ret;
+}
+
+static struct dsa_switch *
+dsa_switch_setup(struct dsa_switch_tree *dst, int index,
+		 struct device *parent, struct device *host_dev)
+{
+	struct dsa_chip_data *pd = dst->pd->chip + index;
+	struct dsa_switch_driver *drv;
+	struct dsa_switch *ds;
+	int ret;
+	char *name;
+
+	/*
+	 * Probe for switch model.
+	 */
+	drv = dsa_switch_probe(host_dev, pd->sw_addr, &name);
+	if (drv == NULL) {
+		netdev_err(dst->master_netdev, "[%d]: could not detect attached switch\n",
+			   index);
+		return ERR_PTR(-EINVAL);
+	}
+	netdev_info(dst->master_netdev, "[%d]: detected a %s switch\n",
+		    index, name);
+
+
+	/*
+	 * Allocate and initialise switch state.
+	 */
+	ds = kzalloc(sizeof(*ds) + drv->priv_size, GFP_KERNEL);
+	if (ds == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	ds->dst = dst;
+	ds->index = index;
+	ds->pd = pd;
+	ds->drv = drv;
+	ds->tag_protocol = drv->tag_protocol;
+	ds->master_dev = host_dev;
+
+	ret = dsa_switch_setup_one(ds, parent);
+	if (ret)
+		return ERR_PTR(ret);
+
+	return ds;
 }
 
 static void dsa_switch_destroy(struct dsa_switch *ds)
 {
+#ifdef CONFIG_NET_DSA_HWMON
+	if (ds->hwmon_dev)
+		hwmon_device_unregister(ds->hwmon_dev);
+#endif
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -248,7 +390,7 @@ static int dsa_switch_suspend(struct dsa_switch *ds)
 
 	/* Suspend slave network devices */
 	for (i = 0; i < DSA_MAX_PORTS; i++) {
-		if (!(ds->phys_port_mask & (1 << i)))
+		if (!dsa_is_port_initialized(ds, i))
 			continue;
 
 		ret = dsa_slave_suspend(ds->ports[i]);
@@ -274,7 +416,7 @@ static int dsa_switch_resume(struct dsa_switch *ds)
 
 	/* Resume slave network devices */
 	for (i = 0; i < DSA_MAX_PORTS; i++) {
-		if (!(ds->phys_port_mask & (1 << i)))
+		if (!dsa_is_port_initialized(ds, i))
 			continue;
 
 		ret = dsa_slave_resume(ds->ports[i]);
@@ -371,12 +513,10 @@ static struct net_device *dev_to_net_device(struct device *dev)
 #ifdef CONFIG_OF
 static int dsa_of_setup_routing_table(struct dsa_platform_data *pd,
 					struct dsa_chip_data *cd,
-					int chip_index,
+					int chip_index, int port_index,
 					struct device_node *link)
 {
-	int ret;
 	const __be32 *reg;
-	int link_port_addr;
 	int link_sw_addr;
 	struct device_node *parent_sw;
 	int len;
@@ -389,6 +529,10 @@ static int dsa_of_setup_routing_table(struct dsa_platform_data *pd,
 	if (!reg || (len != sizeof(*reg) * 2))
 		return -EINVAL;
 
+	/*
+	 * Get the destination switch number from the second field of its 'reg'
+	 * property, i.e. for "reg = <0x19 1>" sw_addr is '1'.
+	 */
 	link_sw_addr = be32_to_cpup(reg + 1);
 
 	if (link_sw_addr >= pd->nr_chips)
@@ -396,7 +540,8 @@ static int dsa_of_setup_routing_table(struct dsa_platform_data *pd,
 
 	/* First time routing table allocation */
 	if (!cd->rtable) {
-		cd->rtable = kmalloc(pd->nr_chips * sizeof(s8), GFP_KERNEL);
+		cd->rtable = kmalloc_array(pd->nr_chips, sizeof(s8),
+					   GFP_KERNEL);
 		if (!cd->rtable)
 			return -ENOMEM;
 
@@ -404,20 +549,9 @@ static int dsa_of_setup_routing_table(struct dsa_platform_data *pd,
 		memset(cd->rtable, -1, pd->nr_chips * sizeof(s8));
 	}
 
-	reg = of_get_property(link, "reg", NULL);
-	if (!reg) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	link_port_addr = be32_to_cpup(reg);
-
-	cd->rtable[link_sw_addr] = link_port_addr;
+	cd->rtable[link_sw_addr] = port_index;
 
 	return 0;
-out:
-	kfree(cd->rtable);
-	return ret;
 }
 
 static void dsa_of_free_platform_data(struct dsa_platform_data *pd)
@@ -436,17 +570,18 @@ static void dsa_of_free_platform_data(struct dsa_platform_data *pd)
 	kfree(pd->chip);
 }
 
-static int dsa_of_probe(struct platform_device *pdev)
+static int dsa_of_probe(struct device *dev)
 {
-	struct device_node *np = pdev->dev.of_node;
+	struct device_node *np = dev->of_node;
 	struct device_node *child, *mdio, *ethernet, *port, *link;
 	struct mii_bus *mdio_bus;
-	struct platform_device *ethernet_dev;
+	struct net_device *ethernet_dev;
 	struct dsa_platform_data *pd;
 	struct dsa_chip_data *cd;
 	const char *port_name;
 	int chip_index, port_index;
 	const unsigned int *sw_addr, *port_reg;
+	u32 eeprom_len;
 	int ret;
 
 	mdio = of_parse_phandle(np, "dsa,mii-bus", 0);
@@ -455,28 +590,28 @@ static int dsa_of_probe(struct platform_device *pdev)
 
 	mdio_bus = of_mdio_find_bus(mdio);
 	if (!mdio_bus)
-		return -EINVAL;
+		return -EPROBE_DEFER;
 
 	ethernet = of_parse_phandle(np, "dsa,ethernet", 0);
 	if (!ethernet)
 		return -EINVAL;
 
-	ethernet_dev = of_find_device_by_node(ethernet);
+	ethernet_dev = of_find_net_device_by_node(ethernet);
 	if (!ethernet_dev)
-		return -ENODEV;
+		return -EPROBE_DEFER;
 
 	pd = kzalloc(sizeof(*pd), GFP_KERNEL);
 	if (!pd)
 		return -ENOMEM;
 
-	pdev->dev.platform_data = pd;
-	pd->netdev = &ethernet_dev->dev;
-	pd->nr_chips = of_get_child_count(np);
+	dev->platform_data = pd;
+	pd->of_netdev = ethernet_dev;
+	pd->nr_chips = of_get_available_child_count(np);
 	if (pd->nr_chips > DSA_MAX_SWITCHES)
 		pd->nr_chips = DSA_MAX_SWITCHES;
 
-	pd->chip = kzalloc(pd->nr_chips * sizeof(struct dsa_chip_data),
-			GFP_KERNEL);
+	pd->chip = kcalloc(pd->nr_chips, sizeof(struct dsa_chip_data),
+			   GFP_KERNEL);
 	if (!pd->chip) {
 		ret = -ENOMEM;
 		goto out_free;
@@ -498,6 +633,9 @@ static int dsa_of_probe(struct platform_device *pdev)
 		if (cd->sw_addr > PHY_MAX_ADDR)
 			continue;
 
+		if (!of_property_read_u32(child, "eeprom-length", &eeprom_len))
+			cd->eeprom_len = eeprom_len;
+
 		for_each_available_child_of_node(child, port) {
 			port_reg = of_get_property(port, "reg", NULL);
 			if (!port_reg)
@@ -523,7 +661,7 @@ static int dsa_of_probe(struct platform_device *pdev)
 			if (!strcmp(port_name, "dsa") && link &&
 					pd->nr_chips > 1) {
 				ret = dsa_of_setup_routing_table(pd, cd,
-						chip_index, link);
+						chip_index, port_index, link);
 				if (ret)
 					goto out_free_chip;
 			}
@@ -539,74 +677,35 @@ out_free_chip:
 	dsa_of_free_platform_data(pd);
 out_free:
 	kfree(pd);
-	pdev->dev.platform_data = NULL;
+	dev->platform_data = NULL;
 	return ret;
 }
 
-static void dsa_of_remove(struct platform_device *pdev)
+static void dsa_of_remove(struct device *dev)
 {
-	struct dsa_platform_data *pd = pdev->dev.platform_data;
+	struct dsa_platform_data *pd = dev->platform_data;
 
-	if (!pdev->dev.of_node)
+	if (!dev->of_node)
 		return;
 
 	dsa_of_free_platform_data(pd);
 	kfree(pd);
 }
 #else
-static inline int dsa_of_probe(struct platform_device *pdev)
+static inline int dsa_of_probe(struct device *dev)
 {
 	return 0;
 }
 
-static inline void dsa_of_remove(struct platform_device *pdev)
+static inline void dsa_of_remove(struct device *dev)
 {
 }
 #endif
 
-static int dsa_probe(struct platform_device *pdev)
+static void dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev,
+			  struct device *parent, struct dsa_platform_data *pd)
 {
-	static int dsa_version_printed;
-	struct dsa_platform_data *pd = pdev->dev.platform_data;
-	struct net_device *dev;
-	struct dsa_switch_tree *dst;
-	int i, ret;
-
-	if (!dsa_version_printed++)
-		printk(KERN_NOTICE "Distributed Switch Architecture "
-			"driver version %s\n", dsa_driver_version);
-
-	if (pdev->dev.of_node) {
-		ret = dsa_of_probe(pdev);
-		if (ret)
-			return ret;
-
-		pd = pdev->dev.platform_data;
-	}
-
-	if (pd == NULL || pd->netdev == NULL)
-		return -EINVAL;
-
-	dev = dev_to_net_device(pd->netdev);
-	if (dev == NULL) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	if (dev->dsa_ptr != NULL) {
-		dev_put(dev);
-		ret = -EEXIST;
-		goto out;
-	}
-
-	dst = kzalloc(sizeof(*dst), GFP_KERNEL);
-	if (dst == NULL) {
-		dev_put(dev);
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	platform_set_drvdata(pdev, dst);
+	int i;
 
 	dst->pd = pd;
 	dst->master_netdev = dev;
@@ -616,11 +715,10 @@ static int dsa_probe(struct platform_device *pdev)
 	for (i = 0; i < pd->nr_chips; i++) {
 		struct dsa_switch *ds;
 
-		ds = dsa_switch_setup(dst, i, &pdev->dev, pd->chip[i].host_dev);
+		ds = dsa_switch_setup(dst, i, parent, pd->chip[i].host_dev);
 		if (IS_ERR(ds)) {
-			printk(KERN_ERR "%s[%d]: couldn't create dsa switch "
-				"instance (error %ld)\n", dev->name, i,
-				PTR_ERR(ds));
+			netdev_err(dev, "[%d]: couldn't create dsa switch instance (error %ld)\n",
+				   i, PTR_ERR(ds));
 			continue;
 		}
 
@@ -645,18 +743,67 @@ static int dsa_probe(struct platform_device *pdev)
 		dst->link_poll_timer.expires = round_jiffies(jiffies + HZ);
 		add_timer(&dst->link_poll_timer);
 	}
+}
+
+static int dsa_probe(struct platform_device *pdev)
+{
+	struct dsa_platform_data *pd = pdev->dev.platform_data;
+	struct net_device *dev;
+	struct dsa_switch_tree *dst;
+	int ret;
+
+	pr_notice_once("Distributed Switch Architecture driver version %s\n",
+		       dsa_driver_version);
+
+	if (pdev->dev.of_node) {
+		ret = dsa_of_probe(&pdev->dev);
+		if (ret)
+			return ret;
+
+		pd = pdev->dev.platform_data;
+	}
+
+	if (pd == NULL || (pd->netdev == NULL && pd->of_netdev == NULL))
+		return -EINVAL;
+
+	if (pd->of_netdev) {
+		dev = pd->of_netdev;
+		dev_hold(dev);
+	} else {
+		dev = dev_to_net_device(pd->netdev);
+	}
+	if (dev == NULL) {
+		ret = -EPROBE_DEFER;
+		goto out;
+	}
+
+	if (dev->dsa_ptr != NULL) {
+		dev_put(dev);
+		ret = -EEXIST;
+		goto out;
+	}
+
+	dst = kzalloc(sizeof(*dst), GFP_KERNEL);
+	if (dst == NULL) {
+		dev_put(dev);
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	platform_set_drvdata(pdev, dst);
+
+	dsa_setup_dst(dst, dev, &pdev->dev, pd);
 
 	return 0;
 
 out:
-	dsa_of_remove(pdev);
+	dsa_of_remove(&pdev->dev);
 
 	return ret;
 }
 
-static int dsa_remove(struct platform_device *pdev)
+static void dsa_remove_dst(struct dsa_switch_tree *dst)
 {
-	struct dsa_switch_tree *dst = platform_get_drvdata(pdev);
 	int i;
 
 	if (dst->link_poll_needed)
@@ -670,8 +817,14 @@ static int dsa_remove(struct platform_device *pdev)
 		if (ds != NULL)
 			dsa_switch_destroy(ds);
 	}
+}
 
-	dsa_of_remove(pdev);
+static int dsa_remove(struct platform_device *pdev)
+{
+	struct dsa_switch_tree *dst = platform_get_drvdata(pdev);
+
+	dsa_remove_dst(dst);
+	dsa_of_remove(&pdev->dev);
 
 	return 0;
 }
@@ -698,6 +851,10 @@ static struct packet_type dsa_pack_type __read_mostly = {
 	.func	= dsa_switch_rcv,
 };
 
+static struct notifier_block dsa_netdevice_nb __read_mostly = {
+	.notifier_call	= dsa_slave_netdevice_event,
+};
+
 #ifdef CONFIG_PM_SLEEP
 static int dsa_suspend(struct device *d)
 {
@@ -747,7 +904,6 @@ static struct platform_driver dsa_driver = {
 	.shutdown	= dsa_shutdown,
 	.driver = {
 		.name	= "dsa",
-		.owner	= THIS_MODULE,
 		.of_match_table = dsa_of_match_table,
 		.pm	= &dsa_pm_ops,
 	},
@@ -757,6 +913,8 @@ static int __init dsa_init_module(void)
 {
 	int rc;
 
+	register_netdevice_notifier(&dsa_netdevice_nb);
+
 	rc = platform_driver_register(&dsa_driver);
 	if (rc)
 		return rc;
@@ -769,6 +927,7 @@ module_init(dsa_init_module);
 
 static void __exit dsa_cleanup_module(void)
 {
+	unregister_netdevice_notifier(&dsa_netdevice_nb);
 	dev_remove_pack(&dsa_pack_type);
 	platform_driver_unregister(&dsa_driver);
 }
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index dc9756d3154c..d5f1f9b862ea 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -45,6 +45,8 @@ struct dsa_slave_priv {
 	int			old_link;
 	int			old_pause;
 	int			old_duplex;
+
+	struct net_device	*bridge_dev;
 };
 
 /* dsa.c */
@@ -53,11 +55,12 @@ extern char dsa_driver_version[];
 /* slave.c */
 extern const struct dsa_device_ops notag_netdev_ops;
 void dsa_slave_mii_bus_init(struct dsa_switch *ds);
-struct net_device *dsa_slave_create(struct dsa_switch *ds,
-				    struct device *parent,
-				    int port, char *name);
+int dsa_slave_create(struct dsa_switch *ds, struct device *parent,
+		     int port, char *name);
 int dsa_slave_suspend(struct net_device *slave_dev);
 int dsa_slave_resume(struct net_device *slave_dev);
+int dsa_slave_netdevice_event(struct notifier_block *unused,
+			      unsigned long event, void *ptr);
 
 /* tag_dsa.c */
 extern const struct dsa_device_ops dsa_netdev_ops;
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index ab03e00ffe8f..827cda560a55 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -10,10 +10,14 @@
 
 #include <linux/list.h>
 #include <linux/etherdevice.h>
+#include <linux/netdevice.h>
 #include <linux/phy.h>
 #include <linux/phy_fixed.h>
 #include <linux/of_net.h>
 #include <linux/of_mdio.h>
+#include <net/rtnetlink.h>
+#include <net/switchdev.h>
+#include <linux/if_bridge.h>
 #include "dsa_priv.h"
 
 /* slave mii_bus handling ***************************************************/
@@ -46,17 +50,21 @@ void dsa_slave_mii_bus_init(struct dsa_switch *ds)
 	snprintf(ds->slave_mii_bus->id, MII_BUS_ID_SIZE, "dsa-%d:%.2x",
 			ds->index, ds->pd->sw_addr);
 	ds->slave_mii_bus->parent = ds->master_dev;
+	ds->slave_mii_bus->phy_mask = ~ds->phys_mii_mask;
 }
 
 
 /* slave device handling ****************************************************/
-static int dsa_slave_init(struct net_device *dev)
+static int dsa_slave_get_iflink(const struct net_device *dev)
 {
 	struct dsa_slave_priv *p = netdev_priv(dev);
 
-	dev->iflink = p->parent->dst->master_netdev->ifindex;
+	return p->parent->dst->master_netdev->ifindex;
+}
 
-	return 0;
+static inline bool dsa_port_is_bridged(struct dsa_slave_priv *p)
+{
+	return !!p->bridge_dev;
 }
 
 static int dsa_slave_open(struct net_device *dev)
@@ -64,6 +72,8 @@ static int dsa_slave_open(struct net_device *dev)
 	struct dsa_slave_priv *p = netdev_priv(dev);
 	struct net_device *master = p->parent->dst->master_netdev;
 	struct dsa_switch *ds = p->parent;
+	u8 stp_state = dsa_port_is_bridged(p) ?
+			BR_STATE_BLOCKING : BR_STATE_FORWARDING;
 	int err;
 
 	if (!(master->flags & IFF_UP))
@@ -92,6 +102,9 @@ static int dsa_slave_open(struct net_device *dev)
 			goto clear_promisc;
 	}
 
+	if (ds->drv->port_stp_update)
+		ds->drv->port_stp_update(ds, p->port, stp_state);
+
 	if (p->phy)
 		phy_start(p->phy);
 
@@ -132,6 +145,9 @@ static int dsa_slave_close(struct net_device *dev)
 	if (ds->drv->port_disable)
 		ds->drv->port_disable(ds, p->port, p->phy);
 
+	if (ds->drv->port_stp_update)
+		ds->drv->port_stp_update(ds, p->port, BR_STATE_DISABLED);
+
 	return 0;
 }
 
@@ -183,6 +199,105 @@ out:
 	return 0;
 }
 
+static int dsa_slave_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
+			     struct net_device *dev,
+			     const unsigned char *addr, u16 vid, u16 nlm_flags)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+	int ret = -EOPNOTSUPP;
+
+	if (ds->drv->fdb_add)
+		ret = ds->drv->fdb_add(ds, p->port, addr, vid);
+
+	return ret;
+}
+
+static int dsa_slave_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
+			     struct net_device *dev,
+			     const unsigned char *addr, u16 vid)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+	int ret = -EOPNOTSUPP;
+
+	if (ds->drv->fdb_del)
+		ret = ds->drv->fdb_del(ds, p->port, addr, vid);
+
+	return ret;
+}
+
+static int dsa_slave_fill_info(struct net_device *dev, struct sk_buff *skb,
+			       const unsigned char *addr, u16 vid,
+			       bool is_static,
+			       u32 portid, u32 seq, int type,
+			       unsigned int flags)
+{
+	struct nlmsghdr *nlh;
+	struct ndmsg *ndm;
+
+	nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags);
+	if (!nlh)
+		return -EMSGSIZE;
+
+	ndm = nlmsg_data(nlh);
+	ndm->ndm_family	 = AF_BRIDGE;
+	ndm->ndm_pad1    = 0;
+	ndm->ndm_pad2    = 0;
+	ndm->ndm_flags	 = NTF_EXT_LEARNED;
+	ndm->ndm_type	 = 0;
+	ndm->ndm_ifindex = dev->ifindex;
+	ndm->ndm_state   = is_static ? NUD_NOARP : NUD_REACHABLE;
+
+	if (nla_put(skb, NDA_LLADDR, ETH_ALEN, addr))
+		goto nla_put_failure;
+
+	if (vid && nla_put_u16(skb, NDA_VLAN, vid))
+		goto nla_put_failure;
+
+	nlmsg_end(skb, nlh);
+	return 0;
+
+nla_put_failure:
+	nlmsg_cancel(skb, nlh);
+	return -EMSGSIZE;
+}
+
+/* Dump information about entries, in response to GETNEIGH */
+static int dsa_slave_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
+			      struct net_device *dev,
+			      struct net_device *filter_dev, int idx)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+	unsigned char addr[ETH_ALEN] = { 0 };
+	int ret;
+
+	if (!ds->drv->fdb_getnext)
+		return -EOPNOTSUPP;
+
+	for (; ; idx++) {
+		bool is_static;
+
+		ret = ds->drv->fdb_getnext(ds, p->port, addr, &is_static);
+		if (ret < 0)
+			break;
+
+		if (idx < cb->args[0])
+			continue;
+
+		ret = dsa_slave_fill_info(dev, skb, addr, 0,
+					  is_static,
+					  NETLINK_CB(cb->skb).portid,
+					  cb->nlh->nlmsg_seq,
+					  RTM_NEWNEIGH, NLM_F_MULTI);
+		if (ret < 0)
+			break;
+	}
+
+	return idx;
+}
+
 static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
 	struct dsa_slave_priv *p = netdev_priv(dev);
@@ -193,6 +308,92 @@ static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	return -EOPNOTSUPP;
 }
 
+/* Return a bitmask of all ports being currently bridged within a given bridge
+ * device. Note that on leave, the mask will still return the bitmask of ports
+ * currently bridged, prior to port removal, and this is exactly what we want.
+ */
+static u32 dsa_slave_br_port_mask(struct dsa_switch *ds,
+				  struct net_device *bridge)
+{
+	struct dsa_slave_priv *p;
+	unsigned int port;
+	u32 mask = 0;
+
+	for (port = 0; port < DSA_MAX_PORTS; port++) {
+		if (!dsa_is_port_initialized(ds, port))
+			continue;
+
+		p = netdev_priv(ds->ports[port]);
+
+		if (ds->ports[port]->priv_flags & IFF_BRIDGE_PORT &&
+		    p->bridge_dev == bridge)
+			mask |= 1 << port;
+	}
+
+	return mask;
+}
+
+static int dsa_slave_stp_update(struct net_device *dev, u8 state)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+	int ret = -EOPNOTSUPP;
+
+	if (ds->drv->port_stp_update)
+		ret = ds->drv->port_stp_update(ds, p->port, state);
+
+	return ret;
+}
+
+static int dsa_slave_bridge_port_join(struct net_device *dev,
+				      struct net_device *br)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+	int ret = -EOPNOTSUPP;
+
+	p->bridge_dev = br;
+
+	if (ds->drv->port_join_bridge)
+		ret = ds->drv->port_join_bridge(ds, p->port,
+						dsa_slave_br_port_mask(ds, br));
+
+	return ret;
+}
+
+static int dsa_slave_bridge_port_leave(struct net_device *dev)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+	int ret = -EOPNOTSUPP;
+
+
+	if (ds->drv->port_leave_bridge)
+		ret = ds->drv->port_leave_bridge(ds, p->port,
+						 dsa_slave_br_port_mask(ds, p->bridge_dev));
+
+	p->bridge_dev = NULL;
+
+	/* Port left the bridge, put in BR_STATE_DISABLED by the bridge layer,
+	 * so allow it to be in BR_STATE_FORWARDING to be kept functional
+	 */
+	dsa_slave_stp_update(dev, BR_STATE_FORWARDING);
+
+	return ret;
+}
+
+static int dsa_slave_parent_id_get(struct net_device *dev,
+				   struct netdev_phys_item_id *psid)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+
+	psid->id_len = sizeof(ds->index);
+	memcpy(&psid->id, &ds->index, psid->id_len);
+
+	return 0;
+}
+
 static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct dsa_slave_priv *p = netdev_priv(dev);
@@ -249,6 +450,27 @@ static void dsa_slave_get_drvinfo(struct net_device *dev,
 	strlcpy(drvinfo->bus_info, "platform", sizeof(drvinfo->bus_info));
 }
 
+static int dsa_slave_get_regs_len(struct net_device *dev)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+
+	if (ds->drv->get_regs_len)
+		return ds->drv->get_regs_len(ds, p->port);
+
+	return -EOPNOTSUPP;
+}
+
+static void
+dsa_slave_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *_p)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+
+	if (ds->drv->get_regs)
+		ds->drv->get_regs(ds, p->port, regs, _p);
+}
+
 static int dsa_slave_nway_reset(struct net_device *dev)
 {
 	struct dsa_slave_priv *p = netdev_priv(dev);
@@ -271,6 +493,44 @@ static u32 dsa_slave_get_link(struct net_device *dev)
 	return -EOPNOTSUPP;
 }
 
+static int dsa_slave_get_eeprom_len(struct net_device *dev)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+
+	if (ds->pd->eeprom_len)
+		return ds->pd->eeprom_len;
+
+	if (ds->drv->get_eeprom_len)
+		return ds->drv->get_eeprom_len(ds);
+
+	return 0;
+}
+
+static int dsa_slave_get_eeprom(struct net_device *dev,
+				struct ethtool_eeprom *eeprom, u8 *data)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+
+	if (ds->drv->get_eeprom)
+		return ds->drv->get_eeprom(ds, eeprom, data);
+
+	return -EOPNOTSUPP;
+}
+
+static int dsa_slave_set_eeprom(struct net_device *dev,
+				struct ethtool_eeprom *eeprom, u8 *data)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+
+	if (ds->drv->set_eeprom)
+		return ds->drv->set_eeprom(ds, eeprom, data);
+
+	return -EOPNOTSUPP;
+}
+
 static void dsa_slave_get_strings(struct net_device *dev,
 				  uint32_t stringset, uint8_t *data)
 {
@@ -385,8 +645,13 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = {
 	.get_settings		= dsa_slave_get_settings,
 	.set_settings		= dsa_slave_set_settings,
 	.get_drvinfo		= dsa_slave_get_drvinfo,
+	.get_regs_len		= dsa_slave_get_regs_len,
+	.get_regs		= dsa_slave_get_regs,
 	.nway_reset		= dsa_slave_nway_reset,
 	.get_link		= dsa_slave_get_link,
+	.get_eeprom_len		= dsa_slave_get_eeprom_len,
+	.get_eeprom		= dsa_slave_get_eeprom,
+	.set_eeprom		= dsa_slave_set_eeprom,
 	.get_strings		= dsa_slave_get_strings,
 	.get_ethtool_stats	= dsa_slave_get_ethtool_stats,
 	.get_sset_count		= dsa_slave_get_sset_count,
@@ -397,14 +662,22 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = {
 };
 
 static const struct net_device_ops dsa_slave_netdev_ops = {
-	.ndo_init		= dsa_slave_init,
 	.ndo_open	 	= dsa_slave_open,
 	.ndo_stop		= dsa_slave_close,
 	.ndo_start_xmit		= dsa_slave_xmit,
 	.ndo_change_rx_flags	= dsa_slave_change_rx_flags,
 	.ndo_set_rx_mode	= dsa_slave_set_rx_mode,
 	.ndo_set_mac_address	= dsa_slave_set_mac_address,
+	.ndo_fdb_add		= dsa_slave_fdb_add,
+	.ndo_fdb_del		= dsa_slave_fdb_del,
+	.ndo_fdb_dump		= dsa_slave_fdb_dump,
 	.ndo_do_ioctl		= dsa_slave_ioctl,
+	.ndo_get_iflink		= dsa_slave_get_iflink,
+};
+
+static const struct swdev_ops dsa_slave_swdev_ops = {
+	.swdev_parent_id_get = dsa_slave_parent_id_get,
+	.swdev_port_stp_update = dsa_slave_stp_update,
 };
 
 static void dsa_slave_adjust_link(struct net_device *dev)
@@ -448,7 +721,25 @@ static int dsa_slave_fixed_link_update(struct net_device *dev,
 }
 
 /* slave device setup *******************************************************/
-static void dsa_slave_phy_setup(struct dsa_slave_priv *p,
+static int dsa_slave_phy_connect(struct dsa_slave_priv *p,
+				 struct net_device *slave_dev,
+				 int addr)
+{
+	struct dsa_switch *ds = p->parent;
+
+	p->phy = ds->slave_mii_bus->phy_map[addr];
+	if (!p->phy)
+		return -ENODEV;
+
+	/* Use already configured phy mode */
+	p->phy_interface = p->phy->interface;
+	phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link,
+			   p->phy_interface);
+
+	return 0;
+}
+
+static int dsa_slave_phy_setup(struct dsa_slave_priv *p,
 				struct net_device *slave_dev)
 {
 	struct dsa_switch *ds = p->parent;
@@ -456,10 +747,13 @@ static void dsa_slave_phy_setup(struct dsa_slave_priv *p,
 	struct device_node *phy_dn, *port_dn;
 	bool phy_is_fixed = false;
 	u32 phy_flags = 0;
-	int ret;
+	int mode, ret;
 
 	port_dn = cd->port_dn[p->port];
-	p->phy_interface = of_get_phy_mode(port_dn);
+	mode = of_get_phy_mode(port_dn);
+	if (mode < 0)
+		mode = PHY_INTERFACE_MODE_NA;
+	p->phy_interface = mode;
 
 	phy_dn = of_parse_phandle(port_dn, "phy-handle", 0);
 	if (of_phy_is_fixed_link(port_dn)) {
@@ -468,8 +762,8 @@ static void dsa_slave_phy_setup(struct dsa_slave_priv *p,
 		 */
 		ret = of_phy_register_fixed_link(port_dn);
 		if (ret) {
-			pr_err("failed to register fixed PHY\n");
-			return;
+			netdev_err(slave_dev, "failed to register fixed PHY\n");
+			return ret;
 		}
 		phy_is_fixed = true;
 		phy_dn = port_dn;
@@ -478,10 +772,25 @@ static void dsa_slave_phy_setup(struct dsa_slave_priv *p,
 	if (ds->drv->get_phy_flags)
 		phy_flags = ds->drv->get_phy_flags(ds, p->port);
 
-	if (phy_dn)
-		p->phy = of_phy_connect(slave_dev, phy_dn,
-					dsa_slave_adjust_link, phy_flags,
-					p->phy_interface);
+	if (phy_dn) {
+		ret = of_mdio_parse_addr(&slave_dev->dev, phy_dn);
+		/* If this PHY address is part of phys_mii_mask, which means
+		 * that we need to divert reads and writes to/from it, then we
+		 * want to bind this device using the slave MII bus created by
+		 * DSA to make that happen.
+		 */
+		if (!phy_is_fixed && ret >= 0 &&
+		    (ds->phys_mii_mask & (1 << ret))) {
+			ret = dsa_slave_phy_connect(p, slave_dev, ret);
+			if (ret)
+				return ret;
+		} else {
+			p->phy = of_phy_connect(slave_dev, phy_dn,
+						dsa_slave_adjust_link,
+						phy_flags,
+						p->phy_interface);
+		}
+	}
 
 	if (p->phy && phy_is_fixed)
 		fixed_phy_set_link_update(p->phy, dsa_slave_fixed_link_update);
@@ -490,13 +799,15 @@ static void dsa_slave_phy_setup(struct dsa_slave_priv *p,
 	 * MDIO bus instead
 	 */
 	if (!p->phy) {
-		p->phy = ds->slave_mii_bus->phy_map[p->port];
-		phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link,
-				   p->phy_interface);
+		ret = dsa_slave_phy_connect(p, slave_dev, p->port);
+		if (ret)
+			return ret;
 	} else {
-		pr_info("attached PHY at address %d [%s]\n",
-			p->phy->addr, p->phy->drv->name);
+		netdev_info(slave_dev, "attached PHY at address %d [%s]\n",
+			    p->phy->addr, p->phy->drv->name);
 	}
+
+	return 0;
 }
 
 int dsa_slave_suspend(struct net_device *slave_dev)
@@ -530,9 +841,8 @@ int dsa_slave_resume(struct net_device *slave_dev)
 	return 0;
 }
 
-struct net_device *
-dsa_slave_create(struct dsa_switch *ds, struct device *parent,
-		 int port, char *name)
+int dsa_slave_create(struct dsa_switch *ds, struct device *parent,
+		     int port, char *name)
 {
 	struct net_device *master = ds->dst->master_netdev;
 	struct net_device *slave_dev;
@@ -542,13 +852,14 @@ dsa_slave_create(struct dsa_switch *ds, struct device *parent,
 	slave_dev = alloc_netdev(sizeof(struct dsa_slave_priv), name,
 				 NET_NAME_UNKNOWN, ether_setup);
 	if (slave_dev == NULL)
-		return slave_dev;
+		return -ENOMEM;
 
 	slave_dev->features = master->vlan_features;
 	slave_dev->ethtool_ops = &dsa_slave_ethtool_ops;
 	eth_hw_addr_inherit(slave_dev, master);
 	slave_dev->tx_queue_len = 0;
 	slave_dev->netdev_ops = &dsa_slave_netdev_ops;
+	slave_dev->swdev_ops = &dsa_slave_swdev_ops;
 
 	SET_NETDEV_DEV(slave_dev, parent);
 	slave_dev->dev.of_node = ds->pd->port_dn[port];
@@ -589,30 +900,67 @@ dsa_slave_create(struct dsa_switch *ds, struct device *parent,
 	p->old_link = -1;
 	p->old_duplex = -1;
 
-	dsa_slave_phy_setup(p, slave_dev);
+	ret = dsa_slave_phy_setup(p, slave_dev);
+	if (ret) {
+		free_netdev(slave_dev);
+		return ret;
+	}
 
+	ds->ports[port] = slave_dev;
 	ret = register_netdev(slave_dev);
 	if (ret) {
-		printk(KERN_ERR "%s: error %d registering interface %s\n",
-				master->name, ret, slave_dev->name);
+		netdev_err(master, "error %d registering interface %s\n",
+			   ret, slave_dev->name);
+		phy_disconnect(p->phy);
+		ds->ports[port] = NULL;
 		free_netdev(slave_dev);
-		return NULL;
+		return ret;
 	}
 
 	netif_carrier_off(slave_dev);
 
-	if (p->phy != NULL) {
-		if (ds->drv->get_phy_flags)
-			p->phy->dev_flags |= ds->drv->get_phy_flags(ds, port);
+	return 0;
+}
+
+static bool dsa_slave_dev_check(struct net_device *dev)
+{
+	return dev->netdev_ops == &dsa_slave_netdev_ops;
+}
+
+static int dsa_slave_master_changed(struct net_device *dev)
+{
+	struct net_device *master = netdev_master_upper_dev_get(dev);
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	int err = 0;
 
-		phy_attach(slave_dev, dev_name(&p->phy->dev),
-			   PHY_INTERFACE_MODE_GMII);
+	if (master && master->rtnl_link_ops &&
+	    !strcmp(master->rtnl_link_ops->kind, "bridge"))
+		err = dsa_slave_bridge_port_join(dev, master);
+	else if (dsa_port_is_bridged(p))
+		err = dsa_slave_bridge_port_leave(dev);
 
-		p->phy->autoneg = AUTONEG_ENABLE;
-		p->phy->speed = 0;
-		p->phy->duplex = 0;
-		p->phy->advertising = p->phy->supported | ADVERTISED_Autoneg;
+	return err;
+}
+
+int dsa_slave_netdevice_event(struct notifier_block *unused,
+			      unsigned long event, void *ptr)
+{
+	struct net_device *dev;
+	int err = 0;
+
+	switch (event) {
+	case NETDEV_CHANGEUPPER:
+		dev = netdev_notifier_info_to_dev(ptr);
+		if (!dsa_slave_dev_check(dev))
+			goto out;
+
+		err = dsa_slave_master_changed(dev);
+		if (err)
+			netdev_warn(dev, "failed to reflect master change\n");
+
+		break;
 	}
 
-	return slave_dev;
+out:
+	return NOTIFY_DONE;
 }
diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c
index ce90c8bdc658..2dab27063273 100644
--- a/net/dsa/tag_dsa.c
+++ b/net/dsa/tag_dsa.c
@@ -63,8 +63,6 @@ static netdev_tx_t dsa_xmit(struct sk_buff *skb, struct net_device *dev)
 		dsa_header[3] = 0x00;
 	}
 
-	skb->protocol = htons(ETH_P_DSA);
-
 	skb->dev = p->parent->dst->master_netdev;
 	dev_queue_xmit(skb);
 
diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c
index 94fcce778679..9aeda596f7ec 100644
--- a/net/dsa/tag_edsa.c
+++ b/net/dsa/tag_edsa.c
@@ -76,8 +76,6 @@ static netdev_tx_t edsa_xmit(struct sk_buff *skb, struct net_device *dev)
 		edsa_header[7] = 0x00;
 	}
 
-	skb->protocol = htons(ETH_P_EDSA);
-
 	skb->dev = p->parent->dst->master_netdev;
 	dev_queue_xmit(skb);
 
diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c
index 115fdca34077..e268f9db8893 100644
--- a/net/dsa/tag_trailer.c
+++ b/net/dsa/tag_trailer.c
@@ -57,8 +57,6 @@ static netdev_tx_t trailer_xmit(struct sk_buff *skb, struct net_device *dev)
 	trailer[2] = 0x10;
 	trailer[3] = 0x00;
 
-	nskb->protocol = htons(ETH_P_TRAILER);
-
 	nskb->dev = p->parent->dst->master_netdev;
 	dev_queue_xmit(nskb);
 
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index 33a140e15834..f3bad41d725f 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -104,7 +104,7 @@ int eth_header(struct sk_buff *skb, struct net_device *dev,
 	 */
 
 	if (dev->flags & (IFF_LOOPBACK | IFF_NOARP)) {
-		memset(eth->h_dest, 0, ETH_ALEN);
+		eth_zero_addr(eth->h_dest);
 		return ETH_HLEN;
 	}
 
@@ -113,39 +113,6 @@ int eth_header(struct sk_buff *skb, struct net_device *dev,
 EXPORT_SYMBOL(eth_header);
 
 /**
- * eth_rebuild_header- rebuild the Ethernet MAC header.
- * @skb: socket buffer to update
- *
- * This is called after an ARP or IPV6 ndisc it's resolution on this
- * sk_buff. We now let protocol (ARP) fill in the other fields.
- *
- * This routine CANNOT use cached dst->neigh!
- * Really, it is used only when dst->neigh is wrong.
- */
-int eth_rebuild_header(struct sk_buff *skb)
-{
-	struct ethhdr *eth = (struct ethhdr *)skb->data;
-	struct net_device *dev = skb->dev;
-
-	switch (eth->h_proto) {
-#ifdef CONFIG_INET
-	case htons(ETH_P_IP):
-		return arp_find(eth->h_dest, skb);
-#endif
-	default:
-		netdev_dbg(dev,
-		       "%s: unable to resolve type %X addresses.\n",
-		       dev->name, ntohs(eth->h_proto));
-
-		memcpy(eth->h_source, dev->dev_addr, ETH_ALEN);
-		break;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(eth_rebuild_header);
-
-/**
  * eth_get_headlen - determine the the length of header for an ethernet frame
  * @data: pointer to start of frame
  * @len: total length of frame
@@ -369,7 +336,6 @@ EXPORT_SYMBOL(eth_validate_addr);
 const struct header_ops eth_header_ops ____cacheline_aligned = {
 	.create		= eth_header,
 	.parse		= eth_header_parse,
-	.rebuild	= eth_rebuild_header,
 	.cache		= eth_header_cache,
 	.cache_update	= eth_header_cache_update,
 };
@@ -391,7 +357,7 @@ void ether_setup(struct net_device *dev)
 	dev->flags		= IFF_BROADCAST|IFF_MULTICAST;
 	dev->priv_flags		|= IFF_TX_SKB_SHARING;
 
-	memset(dev->broadcast, 0xFF, ETH_ALEN);
+	eth_broadcast_addr(dev->broadcast);
 
 }
 EXPORT_SYMBOL(ether_setup);
@@ -424,3 +390,95 @@ ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len)
 	return scnprintf(buf, PAGE_SIZE, "%*phC\n", len, addr);
 }
 EXPORT_SYMBOL(sysfs_format_mac);
+
+struct sk_buff **eth_gro_receive(struct sk_buff **head,
+				 struct sk_buff *skb)
+{
+	struct sk_buff *p, **pp = NULL;
+	struct ethhdr *eh, *eh2;
+	unsigned int hlen, off_eth;
+	const struct packet_offload *ptype;
+	__be16 type;
+	int flush = 1;
+
+	off_eth = skb_gro_offset(skb);
+	hlen = off_eth + sizeof(*eh);
+	eh = skb_gro_header_fast(skb, off_eth);
+	if (skb_gro_header_hard(skb, hlen)) {
+		eh = skb_gro_header_slow(skb, hlen, off_eth);
+		if (unlikely(!eh))
+			goto out;
+	}
+
+	flush = 0;
+
+	for (p = *head; p; p = p->next) {
+		if (!NAPI_GRO_CB(p)->same_flow)
+			continue;
+
+		eh2 = (struct ethhdr *)(p->data + off_eth);
+		if (compare_ether_header(eh, eh2)) {
+			NAPI_GRO_CB(p)->same_flow = 0;
+			continue;
+		}
+	}
+
+	type = eh->h_proto;
+
+	rcu_read_lock();
+	ptype = gro_find_receive_by_type(type);
+	if (ptype == NULL) {
+		flush = 1;
+		goto out_unlock;
+	}
+
+	skb_gro_pull(skb, sizeof(*eh));
+	skb_gro_postpull_rcsum(skb, eh, sizeof(*eh));
+	pp = ptype->callbacks.gro_receive(head, skb);
+
+out_unlock:
+	rcu_read_unlock();
+out:
+	NAPI_GRO_CB(skb)->flush |= flush;
+
+	return pp;
+}
+EXPORT_SYMBOL(eth_gro_receive);
+
+int eth_gro_complete(struct sk_buff *skb, int nhoff)
+{
+	struct ethhdr *eh = (struct ethhdr *)(skb->data + nhoff);
+	__be16 type = eh->h_proto;
+	struct packet_offload *ptype;
+	int err = -ENOSYS;
+
+	if (skb->encapsulation)
+		skb_set_inner_mac_header(skb, nhoff);
+
+	rcu_read_lock();
+	ptype = gro_find_complete_by_type(type);
+	if (ptype != NULL)
+		err = ptype->callbacks.gro_complete(skb, nhoff +
+						    sizeof(struct ethhdr));
+
+	rcu_read_unlock();
+	return err;
+}
+EXPORT_SYMBOL(eth_gro_complete);
+
+static struct packet_offload eth_packet_offload __read_mostly = {
+	.type = cpu_to_be16(ETH_P_TEB),
+	.callbacks = {
+		.gro_receive = eth_gro_receive,
+		.gro_complete = eth_gro_complete,
+	},
+};
+
+static int __init eth_offload_init(void)
+{
+	dev_add_offload(&eth_packet_offload);
+
+	return 0;
+}
+
+fs_initcall(eth_offload_init);
diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index a138d75751df..44d27469ae55 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -359,8 +359,11 @@ static void hsr_dev_destroy(struct net_device *hsr_dev)
 	struct hsr_port *port;
 
 	hsr = netdev_priv(hsr_dev);
+
+	rtnl_lock();
 	hsr_for_each_port(hsr, port)
 		hsr_del_port(port);
+	rtnl_unlock();
 
 	del_timer_sync(&hsr->prune_timer);
 	del_timer_sync(&hsr->announce_timer);
diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c
index 779d28b65417..cd37d0011b42 100644
--- a/net/hsr/hsr_main.c
+++ b/net/hsr/hsr_main.c
@@ -36,6 +36,10 @@ static int hsr_netdev_notify(struct notifier_block *nb, unsigned long event,
 			return NOTIFY_DONE;	/* Not an HSR device */
 		hsr = netdev_priv(dev);
 		port = hsr_port_get_hsr(hsr, HSR_PT_MASTER);
+		if (port == NULL) {
+			/* Resend of notification concerning removed device? */
+			return NOTIFY_DONE;
+		}
 	} else {
 		hsr = port->hsr;
 	}
diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c
index a348dcbcd683..7d37366cc695 100644
--- a/net/hsr/hsr_slave.c
+++ b/net/hsr/hsr_slave.c
@@ -181,8 +181,10 @@ void hsr_del_port(struct hsr_port *port)
 	list_del_rcu(&port->port_list);
 
 	if (port != master) {
-		netdev_update_features(master->dev);
-		dev_set_mtu(master->dev, hsr_get_max_mtu(hsr));
+		if (master != NULL) {
+			netdev_update_features(master->dev);
+			dev_set_mtu(master->dev, hsr_get_max_mtu(hsr));
+		}
 		netdev_rx_handler_unregister(port->dev);
 		dev_set_promiscuity(port->dev, -1);
 	}
@@ -192,5 +194,7 @@ void hsr_del_port(struct hsr_port *port)
 	 */
 
 	synchronize_rcu();
-	dev_put(port->dev);
+
+	if (port != master)
+		dev_put(port->dev);
 }
diff --git a/net/ieee802154/6lowpan/6lowpan_i.h b/net/ieee802154/6lowpan/6lowpan_i.h
new file mode 100644
index 000000000000..e50f69da78eb
--- /dev/null
+++ b/net/ieee802154/6lowpan/6lowpan_i.h
@@ -0,0 +1,72 @@
+#ifndef __IEEE802154_6LOWPAN_I_H__
+#define __IEEE802154_6LOWPAN_I_H__
+
+#include <linux/list.h>
+
+#include <net/ieee802154_netdev.h>
+#include <net/inet_frag.h>
+
+struct lowpan_create_arg {
+	u16 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;
+
+	u16			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;
+	}
+}
+
+struct lowpan_dev_record {
+	struct net_device *ldev;
+	struct list_head list;
+};
+
+/* 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 */
+	u16			fragment_tag;
+};
+
+static inline struct
+lowpan_dev_info *lowpan_dev_info(const struct net_device *dev)
+{
+	return netdev_priv(dev);
+}
+
+extern struct list_head lowpan_devices;
+
+int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type);
+void lowpan_net_frag_exit(void);
+int lowpan_net_frag_init(void);
+
+void lowpan_rx_init(void);
+void lowpan_rx_exit(void);
+
+int lowpan_header_create(struct sk_buff *skb, struct net_device *dev,
+			 unsigned short type, const void *_daddr,
+			 const void *_saddr, unsigned int len);
+netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *dev);
+
+#endif /* __IEEE802154_6LOWPAN_I_H__ */
diff --git a/net/ieee802154/6lowpan/Kconfig b/net/ieee802154/6lowpan/Kconfig
new file mode 100644
index 000000000000..d24f985b0bfd
--- /dev/null
+++ b/net/ieee802154/6lowpan/Kconfig
@@ -0,0 +1,5 @@
+config IEEE802154_6LOWPAN
+	tristate "6lowpan support over IEEE 802.15.4"
+	depends on 6LOWPAN
+	---help---
+	  IPv6 compression over IEEE 802.15.4.
diff --git a/net/ieee802154/6lowpan/Makefile b/net/ieee802154/6lowpan/Makefile
new file mode 100644
index 000000000000..6bfb270a81a6
--- /dev/null
+++ b/net/ieee802154/6lowpan/Makefile
@@ -0,0 +1,3 @@
+obj-$(CONFIG_IEEE802154_6LOWPAN) += ieee802154_6lowpan.o
+
+ieee802154_6lowpan-y := core.o rx.o reassembly.o tx.o
diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c
new file mode 100644
index 000000000000..0ae5822ef944
--- /dev/null
+++ b/net/ieee802154/6lowpan/core.c
@@ -0,0 +1,306 @@
+/* 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/module.h>
+#include <linux/netdevice.h>
+#include <linux/ieee802154.h>
+
+#include <net/ipv6.h>
+
+#include "6lowpan_i.h"
+
+LIST_HEAD(lowpan_devices);
+static int lowpan_open_count;
+
+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,
+};
+
+static struct ieee802154_mlme_ops lowpan_mlme = {
+	.get_pan_id = lowpan_get_pan_id,
+	.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_6LOWPAN;
+	/* Frame Control + Sequence Number + Address fields + Security Header */
+	dev->hard_header_len	= 2 + 1 + 20 + 14;
+	dev->needed_tailroom	= 2; /* FCS */
+	dev->mtu		= IPV6_MIN_MTU;
+	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;
+	dev->features		|= NETIF_F_NETNS_LOCAL;
+}
+
+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_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;
+	int ret;
+
+	ASSERT_RTNL();
+
+	pr_debug("adding new link\n");
+
+	if (!tb[IFLA_LINK] ||
+	    !net_eq(dev_net(dev), &init_net))
+		return -EINVAL;
+	/* find and hold real wpan device */
+	real_dev = dev_get_by_index(dev_net(dev), 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 hardware 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);
+
+	ret = register_netdevice(dev);
+	if (ret >= 0) {
+		if (!lowpan_open_count)
+			lowpan_rx_init();
+		lowpan_open_count++;
+	}
+
+	return ret;
+}
+
+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();
+
+	lowpan_open_count--;
+	if (!lowpan_open_count)
+		lowpan_rx_exit();
+
+	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 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;
+
+	err = register_netdevice_notifier(&lowpan_dev_notifier);
+	if (err < 0)
+		goto out_pack;
+
+	return 0;
+
+out_pack:
+	lowpan_netlink_fini();
+out_frag:
+	lowpan_net_frag_exit();
+out:
+	return err;
+}
+
+static void __exit lowpan_cleanup_module(void)
+{
+	lowpan_netlink_fini();
+
+	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/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index 7cfcd6885225..f46e4d1306f2 100644
--- a/net/ieee802154/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -28,12 +28,12 @@
 #include <net/ipv6.h>
 #include <net/inet_frag.h>
 
-#include "reassembly.h"
+#include "6lowpan_i.h"
 
 static const char lowpan_frags_cache_name[] = "lowpan-frags";
 
 struct lowpan_frag_info {
-	__be16 d_tag;
+	u16 d_tag;
 	u16 d_size;
 	u8 d_offset;
 };
@@ -48,7 +48,7 @@ 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,
+static unsigned int lowpan_hash_frag(u16 tag, u16 d_size,
 				     const struct ieee802154_addr *saddr,
 				     const struct ieee802154_addr *daddr)
 {
@@ -330,11 +330,13 @@ static int lowpan_get_frag_info(struct sk_buff *skb, const u8 frag_type,
 {
 	bool fail;
 	u8 pattern = 0, low = 0;
+	__be16 d_tag = 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);
+	fail |= lowpan_fetch_skb(skb, &d_tag, 2);
+	frag_info->d_tag = ntohs(d_tag);
 
 	if (frag_type == LOWPAN_DISPATCH_FRAGN) {
 		fail |= lowpan_fetch_skb(skb, &frag_info->d_offset, 1);
diff --git a/net/ieee802154/6lowpan/rx.c b/net/ieee802154/6lowpan/rx.c
new file mode 100644
index 000000000000..4be1d289ab2d
--- /dev/null
+++ b/net/ieee802154/6lowpan/rx.c
@@ -0,0 +1,171 @@
+/* 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.
+ */
+
+#include <linux/if_arp.h>
+
+#include <net/6lowpan.h>
+#include <net/ieee802154_netdev.h>
+
+#include "6lowpan_i.h"
+
+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;
+
+	skb->protocol = htons(ETH_P_IPV6);
+	skb->pkt_type = PACKET_HOST;
+
+	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) {
+				kfree_skb(skb);
+				rcu_read_unlock();
+				return NET_RX_DROP;
+			}
+
+			skb_cp->dev = entry->ldev;
+			stat = netif_rx(skb_cp);
+			if (stat == NET_RX_DROP)
+				break;
+		}
+	rcu_read_unlock();
+
+	consume_skb(skb);
+
+	return stat;
+}
+
+static int
+iphc_decompress(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)
+		return -EINVAL;
+
+	if (lowpan_fetch_skb_u8(skb, &iphc0))
+		return -EINVAL;
+
+	if (lowpan_fetch_skb_u8(skb, &iphc1))
+		return -EINVAL;
+
+	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_header_decompress(skb, skb->dev, sap, sa.addr_type,
+					IEEE802154_ADDR_LEN, dap, da.addr_type,
+					IEEE802154_ADDR_LEN, iphc0, iphc1);
+}
+
+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 (skb->pkt_type == PACKET_OTHERHOST)
+		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) {
+		/* Pull off the 1-byte of 6lowpan header. */
+		skb_pull(skb, 1);
+		return lowpan_give_skb_to_devices(skb, NULL);
+	} else {
+		switch (skb->data[0] & 0xe0) {
+		case LOWPAN_DISPATCH_IPHC:	/* ipv6 datagram */
+			ret = iphc_decompress(skb, &hdr);
+			if (ret < 0)
+				goto drop_skb;
+
+			return lowpan_give_skb_to_devices(skb, NULL);
+		case LOWPAN_DISPATCH_FRAG1:	/* first fragment header */
+			ret = lowpan_frag_rcv(skb, LOWPAN_DISPATCH_FRAG1);
+			if (ret == 1) {
+				ret = iphc_decompress(skb, &hdr);
+				if (ret < 0)
+					goto drop_skb;
+
+				return lowpan_give_skb_to_devices(skb, NULL);
+			} else if (ret == -1) {
+				return NET_RX_DROP;
+			} else {
+				return NET_RX_SUCCESS;
+			}
+		case LOWPAN_DISPATCH_FRAGN:	/* next fragments headers */
+			ret = lowpan_frag_rcv(skb, LOWPAN_DISPATCH_FRAGN);
+			if (ret == 1) {
+				ret = iphc_decompress(skb, &hdr);
+				if (ret < 0)
+					goto drop_skb;
+
+				return lowpan_give_skb_to_devices(skb, NULL);
+			} else if (ret == -1) {
+				return NET_RX_DROP;
+			} else {
+				return NET_RX_SUCCESS;
+			}
+		default:
+			break;
+		}
+	}
+
+drop_skb:
+	kfree_skb(skb);
+drop:
+	return NET_RX_DROP;
+}
+
+static struct packet_type lowpan_packet_type = {
+	.type = htons(ETH_P_IEEE802154),
+	.func = lowpan_rcv,
+};
+
+void lowpan_rx_init(void)
+{
+	dev_add_pack(&lowpan_packet_type);
+}
+
+void lowpan_rx_exit(void)
+{
+	dev_remove_pack(&lowpan_packet_type);
+}
diff --git a/net/ieee802154/6lowpan/tx.c b/net/ieee802154/6lowpan/tx.c
new file mode 100644
index 000000000000..2349070bd534
--- /dev/null
+++ b/net/ieee802154/6lowpan/tx.c
@@ -0,0 +1,271 @@
+/* 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.
+ */
+
+#include <net/6lowpan.h>
+#include <net/ieee802154_netdev.h>
+
+#include "6lowpan_i.h"
+
+/* don't save pan id, it's intra pan */
+struct lowpan_addr {
+	u8 mode;
+	union {
+		/* IPv6 needs big endian here */
+		__be64 extended_addr;
+		__be16 short_addr;
+	} u;
+};
+
+struct lowpan_addr_info {
+	struct lowpan_addr daddr;
+	struct lowpan_addr saddr;
+};
+
+static inline struct
+lowpan_addr_info *lowpan_skb_priv(const struct sk_buff *skb)
+{
+	WARN_ON_ONCE(skb_headroom(skb) < sizeof(struct lowpan_addr_info));
+	return (struct lowpan_addr_info *)(skb->data -
+			sizeof(struct lowpan_addr_info));
+}
+
+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 lowpan_addr_info *info;
+
+	/* 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);
+
+	info = lowpan_skb_priv(skb);
+
+	/* TODO: Currently we only support extended_addr */
+	info->daddr.mode = IEEE802154_ADDR_LONG;
+	memcpy(&info->daddr.u.extended_addr, daddr,
+	       sizeof(info->daddr.u.extended_addr));
+	info->saddr.mode = IEEE802154_ADDR_LONG;
+	memcpy(&info->saddr.u.extended_addr, saddr,
+	       sizeof(info->daddr.u.extended_addr));
+
+	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 = htons(lowpan_dev_info(dev)->fragment_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__, ntohs(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__, ntohs(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 int lowpan_header(struct sk_buff *skb, struct net_device *dev)
+{
+	struct ieee802154_addr sa, da;
+	struct ieee802154_mac_cb *cb = mac_cb_init(skb);
+	struct lowpan_addr_info info;
+	void *daddr, *saddr;
+
+	memcpy(&info, lowpan_skb_priv(skb), sizeof(info));
+
+	/* TODO: Currently we only support extended_addr */
+	daddr = &info.daddr.u.extended_addr;
+	saddr = &info.saddr.u.extended_addr;
+
+	lowpan_header_compress(skb, dev, ETH_P_IPV6, daddr, saddr, skb->len);
+
+	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((const u8 *)daddr)) {
+		da.mode = IEEE802154_ADDR_SHORT;
+		da.short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST);
+		cb->ackreq = false;
+	} else {
+		da.mode = IEEE802154_ADDR_LONG;
+		da.extended_addr = ieee802154_devaddr_from_raw(daddr);
+		cb->ackreq = true;
+	}
+
+	return dev_hard_header(skb, lowpan_dev_info(dev)->real_dev,
+			ETH_P_IPV6, (void *)&da, (void *)&sa, 0);
+}
+
+netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct ieee802154_hdr wpan_hdr;
+	int max_single, ret;
+
+	pr_debug("package xmit\n");
+
+	/* We must take a copy of the skb before we modify/replace the ipv6
+	 * header as the header could be used elsewhere
+	 */
+	skb = skb_unshare(skb, GFP_ATOMIC);
+	if (!skb)
+		return NET_XMIT_DROP;
+
+	ret = lowpan_header(skb, dev);
+	if (ret < 0) {
+		kfree_skb(skb);
+		return NET_XMIT_DROP;
+	}
+
+	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;
+	}
+}
diff --git a/net/ieee802154/6lowpan_rtnl.c b/net/ieee802154/6lowpan_rtnl.c
deleted file mode 100644
index 44136297b673..000000000000
--- a/net/ieee802154/6lowpan_rtnl.c
+++ /dev/null
@@ -1,732 +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.
- */
-
-/* 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;
-};
-
-/* don't save pan id, it's intra pan */
-struct lowpan_addr {
-	u8 mode;
-	union {
-		/* IPv6 needs big endian here */
-		__be64 extended_addr;
-		__be16 short_addr;
-	} u;
-};
-
-struct lowpan_addr_info {
-	struct lowpan_addr daddr;
-	struct lowpan_addr saddr;
-};
-
-static inline struct
-lowpan_dev_info *lowpan_dev_info(const struct net_device *dev)
-{
-	return netdev_priv(dev);
-}
-
-static inline struct
-lowpan_addr_info *lowpan_skb_priv(const struct sk_buff *skb)
-{
-	WARN_ON_ONCE(skb_headroom(skb) < sizeof(struct lowpan_addr_info));
-	return (struct lowpan_addr_info *)(skb->data -
-			sizeof(struct lowpan_addr_info));
-}
-
-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 lowpan_addr_info *info;
-
-	/* 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);
-
-	info = lowpan_skb_priv(skb);
-
-	/* TODO: Currently we only support extended_addr */
-	info->daddr.mode = IEEE802154_ADDR_LONG;
-	memcpy(&info->daddr.u.extended_addr, daddr,
-	       sizeof(info->daddr.u.extended_addr));
-	info->saddr.mode = IEEE802154_ADDR_LONG;
-	memcpy(&info->saddr.u.extended_addr, saddr,
-	       sizeof(info->daddr.u.extended_addr));
-
-	return 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 int lowpan_header(struct sk_buff *skb, struct net_device *dev)
-{
-	struct ieee802154_addr sa, da;
-	struct ieee802154_mac_cb *cb = mac_cb_init(skb);
-	struct lowpan_addr_info info;
-	void *daddr, *saddr;
-
-	memcpy(&info, lowpan_skb_priv(skb), sizeof(info));
-
-	/* TODO: Currently we only support extended_addr */
-	daddr = &info.daddr.u.extended_addr;
-	saddr = &info.saddr.u.extended_addr;
-
-	lowpan_header_compress(skb, dev, ETH_P_IPV6, daddr, saddr, skb->len);
-
-	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((const u8 *)daddr)) {
-		da.mode = IEEE802154_ADDR_SHORT;
-		da.short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST);
-		cb->ackreq = false;
-	} else {
-		da.mode = IEEE802154_ADDR_LONG;
-		da.extended_addr = ieee802154_devaddr_from_raw(daddr);
-		cb->ackreq = true;
-	}
-
-	return dev_hard_header(skb, lowpan_dev_info(dev)->real_dev,
-			ETH_P_IPV6, (void *)&da, (void *)&sa, 0);
-}
-
-static netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *dev)
-{
-	struct ieee802154_hdr wpan_hdr;
-	int max_single, ret;
-
-	pr_debug("package xmit\n");
-
-	/* We must take a copy of the skb before we modify/replace the ipv6
-	 * header as the header could be used elsewhere
-	 */
-	skb = skb_unshare(skb, GFP_ATOMIC);
-	if (!skb)
-		return NET_XMIT_DROP;
-
-	ret = lowpan_header(skb, dev);
-	if (ret < 0) {
-		kfree_skb(skb);
-		return NET_XMIT_DROP;
-	}
-
-	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		= IPV6_MIN_MTU;
-	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 c0d4154d144f..1370d5b0041b 100644
--- a/net/ieee802154/Kconfig
+++ b/net/ieee802154/Kconfig
@@ -1,4 +1,4 @@
-config IEEE802154
+menuconfig IEEE802154
 	tristate "IEEE Std 802.15.4 Low-Rate Wireless Personal Area Networks support"
 	---help---
 	  IEEE Std 802.15.4 defines a low data rate, low power and low
@@ -10,8 +10,16 @@ config IEEE802154
 	  Say Y here to compile LR-WPAN support into the kernel or say M to
 	  compile it as modules.
 
-config IEEE802154_6LOWPAN
-	tristate "6lowpan support over IEEE 802.15.4"
-	depends on IEEE802154 && 6LOWPAN
+if IEEE802154
+
+config IEEE802154_SOCKET
+	tristate "IEEE 802.15.4 socket interface"
+	default y
 	---help---
-	  IPv6 compression over IEEE 802.15.4.
+	  Socket interface for IEEE 802.15.4. Contains DGRAM sockets interface
+	  for 802.15.4 dataframes. Also RAW socket interface to build MAC
+	  header from userspace.
+
+source "net/ieee802154/6lowpan/Kconfig"
+
+endif
diff --git a/net/ieee802154/Makefile b/net/ieee802154/Makefile
index 3914b1ed4274..4adfd4d5471b 100644
--- a/net/ieee802154/Makefile
+++ b/net/ieee802154/Makefile
@@ -1,9 +1,11 @@
-obj-$(CONFIG_IEEE802154) += ieee802154.o af_802154.o
-obj-$(CONFIG_IEEE802154_6LOWPAN) += ieee802154_6lowpan.o
+obj-$(CONFIG_IEEE802154) += ieee802154.o
+obj-$(CONFIG_IEEE802154_SOCKET) += ieee802154_socket.o
+obj-y += 6lowpan/
 
-ieee802154_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
+ieee802154-y := netlink.o nl-mac.o nl-phy.o nl_policy.o core.o \
+                header_ops.o sysfs.o nl802154.o trace.o
+ieee802154_socket-y := socket.o
+
+CFLAGS_trace.o := -I$(src)
 
 ccflags-y += -D__CHECK_ENDIAN__
diff --git a/net/ieee802154/af802154.h b/net/ieee802154/af802154.h
deleted file mode 100644
index 8330a09bfc95..000000000000
--- a/net/ieee802154/af802154.h
+++ /dev/null
@@ -1,37 +0,0 @@
-/*
- * Internal interfaces for ieee 802.15.4 address family.
- *
- * Copyright 2007, 2008, 2009 Siemens AG
- *
- * 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.
- *
- * Written by:
- * Sergey Lapin <slapin@ossfans.org>
- * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
- */
-
-#ifndef AF802154_H
-#define AF802154_H
-
-struct sk_buff;
-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,
-				      const struct ieee802154_addr *addr);
-
-#endif
diff --git a/net/ieee802154/af_ieee802154.c b/net/ieee802154/af_ieee802154.c
deleted file mode 100644
index 29e0de63001b..000000000000
--- a/net/ieee802154/af_ieee802154.c
+++ /dev/null
@@ -1,373 +0,0 @@
-/*
- * IEEE802154.4 socket interface
- *
- * Copyright 2007, 2008 Siemens AG
- *
- * 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.
- *
- * Written by:
- * Sergey Lapin <slapin@ossfans.org>
- * Maxim Gorbachyov <maxim.gorbachev@siemens.com>
- */
-
-#include <linux/net.h>
-#include <linux/capability.h>
-#include <linux/module.h>
-#include <linux/if_arp.h>
-#include <linux/if.h>
-#include <linux/termios.h>	/* For TIOCOUTQ/INQ */
-#include <linux/list.h>
-#include <linux/slab.h>
-#include <net/datalink.h>
-#include <net/psnap.h>
-#include <net/sock.h>
-#include <net/tcp_states.h>
-#include <net/route.h>
-
-#include <net/af_ieee802154.h>
-#include <net/ieee802154_netdev.h>
-
-#include "af802154.h"
-
-/* Utility function for families */
-struct net_device*
-ieee802154_get_dev(struct net *net, const struct ieee802154_addr *addr)
-{
-	struct net_device *dev = NULL;
-	struct net_device *tmp;
-	__le16 pan_id, short_addr;
-	u8 hwaddr[IEEE802154_ADDR_LEN];
-
-	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, hwaddr);
-		if (dev)
-			dev_hold(dev);
-		rcu_read_unlock();
-		break;
-	case IEEE802154_ADDR_SHORT:
-		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();
-
-		for_each_netdev(net, tmp) {
-			if (tmp->type != ARPHRD_IEEE802154)
-				continue;
-
-			pan_id = ieee802154_mlme_ops(tmp)->get_pan_id(tmp);
-			short_addr =
-				ieee802154_mlme_ops(tmp)->get_short_addr(tmp);
-
-			if (pan_id == addr->pan_id &&
-			    short_addr == addr->short_addr) {
-				dev = tmp;
-				dev_hold(dev);
-				break;
-			}
-		}
-
-		rtnl_unlock();
-		break;
-	default:
-		pr_warn("Unsupported ieee802154 address type: %d\n",
-			addr->mode);
-		break;
-	}
-
-	return dev;
-}
-
-static int ieee802154_sock_release(struct socket *sock)
-{
-	struct sock *sk = sock->sk;
-
-	if (sk) {
-		sock->sk = NULL;
-		sk->sk_prot->close(sk, 0);
-	}
-	return 0;
-}
-static int ieee802154_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
-				   struct msghdr *msg, size_t len)
-{
-	struct sock *sk = sock->sk;
-
-	return sk->sk_prot->sendmsg(iocb, sk, msg, len);
-}
-
-static int ieee802154_sock_bind(struct socket *sock, struct sockaddr *uaddr,
-				int addr_len)
-{
-	struct sock *sk = sock->sk;
-
-	if (sk->sk_prot->bind)
-		return sk->sk_prot->bind(sk, uaddr, addr_len);
-
-	return sock_no_bind(sock, uaddr, addr_len);
-}
-
-static int ieee802154_sock_connect(struct socket *sock, struct sockaddr *uaddr,
-				   int addr_len, int flags)
-{
-	struct sock *sk = sock->sk;
-
-	if (addr_len < sizeof(uaddr->sa_family))
-		return -EINVAL;
-
-	if (uaddr->sa_family == AF_UNSPEC)
-		return sk->sk_prot->disconnect(sk, flags);
-
-	return sk->sk_prot->connect(sk, uaddr, addr_len);
-}
-
-static int ieee802154_dev_ioctl(struct sock *sk, struct ifreq __user *arg,
-				unsigned int cmd)
-{
-	struct ifreq ifr;
-	int ret = -ENOIOCTLCMD;
-	struct net_device *dev;
-
-	if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
-		return -EFAULT;
-
-	ifr.ifr_name[IFNAMSIZ-1] = 0;
-
-	dev_load(sock_net(sk), ifr.ifr_name);
-	dev = dev_get_by_name(sock_net(sk), ifr.ifr_name);
-
-	if (!dev)
-		return -ENODEV;
-
-	if (dev->type == ARPHRD_IEEE802154 && dev->netdev_ops->ndo_do_ioctl)
-		ret = dev->netdev_ops->ndo_do_ioctl(dev, &ifr, cmd);
-
-	if (!ret && copy_to_user(arg, &ifr, sizeof(struct ifreq)))
-		ret = -EFAULT;
-	dev_put(dev);
-
-	return ret;
-}
-
-static int ieee802154_sock_ioctl(struct socket *sock, unsigned int cmd,
-				 unsigned long arg)
-{
-	struct sock *sk = sock->sk;
-
-	switch (cmd) {
-	case SIOCGSTAMP:
-		return sock_get_timestamp(sk, (struct timeval __user *)arg);
-	case SIOCGSTAMPNS:
-		return sock_get_timestampns(sk, (struct timespec __user *)arg);
-	case SIOCGIFADDR:
-	case SIOCSIFADDR:
-		return ieee802154_dev_ioctl(sk, (struct ifreq __user *)arg,
-				cmd);
-	default:
-		if (!sk->sk_prot->ioctl)
-			return -ENOIOCTLCMD;
-		return sk->sk_prot->ioctl(sk, cmd, arg);
-	}
-}
-
-static const struct proto_ops ieee802154_raw_ops = {
-	.family		   = PF_IEEE802154,
-	.owner		   = THIS_MODULE,
-	.release	   = ieee802154_sock_release,
-	.bind		   = ieee802154_sock_bind,
-	.connect	   = ieee802154_sock_connect,
-	.socketpair	   = sock_no_socketpair,
-	.accept		   = sock_no_accept,
-	.getname	   = sock_no_getname,
-	.poll		   = datagram_poll,
-	.ioctl		   = ieee802154_sock_ioctl,
-	.listen		   = sock_no_listen,
-	.shutdown	   = sock_no_shutdown,
-	.setsockopt	   = sock_common_setsockopt,
-	.getsockopt	   = sock_common_getsockopt,
-	.sendmsg	   = ieee802154_sock_sendmsg,
-	.recvmsg	   = sock_common_recvmsg,
-	.mmap		   = sock_no_mmap,
-	.sendpage	   = sock_no_sendpage,
-#ifdef CONFIG_COMPAT
-	.compat_setsockopt = compat_sock_common_setsockopt,
-	.compat_getsockopt = compat_sock_common_getsockopt,
-#endif
-};
-
-static const struct proto_ops ieee802154_dgram_ops = {
-	.family		   = PF_IEEE802154,
-	.owner		   = THIS_MODULE,
-	.release	   = ieee802154_sock_release,
-	.bind		   = ieee802154_sock_bind,
-	.connect	   = ieee802154_sock_connect,
-	.socketpair	   = sock_no_socketpair,
-	.accept		   = sock_no_accept,
-	.getname	   = sock_no_getname,
-	.poll		   = datagram_poll,
-	.ioctl		   = ieee802154_sock_ioctl,
-	.listen		   = sock_no_listen,
-	.shutdown	   = sock_no_shutdown,
-	.setsockopt	   = sock_common_setsockopt,
-	.getsockopt	   = sock_common_getsockopt,
-	.sendmsg	   = ieee802154_sock_sendmsg,
-	.recvmsg	   = sock_common_recvmsg,
-	.mmap		   = sock_no_mmap,
-	.sendpage	   = sock_no_sendpage,
-#ifdef CONFIG_COMPAT
-	.compat_setsockopt = compat_sock_common_setsockopt,
-	.compat_getsockopt = compat_sock_common_getsockopt,
-#endif
-};
-
-
-/* Create a socket. Initialise the socket, blank the addresses
- * set the state.
- */
-static int ieee802154_create(struct net *net, struct socket *sock,
-			     int protocol, int kern)
-{
-	struct sock *sk;
-	int rc;
-	struct proto *proto;
-	const struct proto_ops *ops;
-
-	if (!net_eq(net, &init_net))
-		return -EAFNOSUPPORT;
-
-	switch (sock->type) {
-	case SOCK_RAW:
-		proto = &ieee802154_raw_prot;
-		ops = &ieee802154_raw_ops;
-		break;
-	case SOCK_DGRAM:
-		proto = &ieee802154_dgram_prot;
-		ops = &ieee802154_dgram_ops;
-		break;
-	default:
-		rc = -ESOCKTNOSUPPORT;
-		goto out;
-	}
-
-	rc = -ENOMEM;
-	sk = sk_alloc(net, PF_IEEE802154, GFP_KERNEL, proto);
-	if (!sk)
-		goto out;
-	rc = 0;
-
-	sock->ops = ops;
-
-	sock_init_data(sock, sk);
-	/* FIXME: sk->sk_destruct */
-	sk->sk_family = PF_IEEE802154;
-
-	/* Checksums on by default */
-	sock_set_flag(sk, SOCK_ZAPPED);
-
-	if (sk->sk_prot->hash)
-		sk->sk_prot->hash(sk);
-
-	if (sk->sk_prot->init) {
-		rc = sk->sk_prot->init(sk);
-		if (rc)
-			sk_common_release(sk);
-	}
-out:
-	return rc;
-}
-
-static const struct net_proto_family ieee802154_family_ops = {
-	.family		= PF_IEEE802154,
-	.create		= ieee802154_create,
-	.owner		= THIS_MODULE,
-};
-
-static int ieee802154_rcv(struct sk_buff *skb, struct net_device *dev,
-			  struct packet_type *pt, struct net_device *orig_dev)
-{
-	if (!netif_running(dev))
-		goto drop;
-	pr_debug("got frame, type %d, dev %p\n", dev->type, dev);
-#ifdef DEBUG
-	print_hex_dump_bytes("ieee802154_rcv ",
-			     DUMP_PREFIX_NONE, skb->data, skb->len);
-#endif
-
-	if (!net_eq(dev_net(dev), &init_net))
-		goto drop;
-
-	ieee802154_raw_deliver(dev, skb);
-
-	if (dev->type != ARPHRD_IEEE802154)
-		goto drop;
-
-	if (skb->pkt_type != PACKET_OTHERHOST)
-		return ieee802154_dgram_deliver(dev, skb);
-
-drop:
-	kfree_skb(skb);
-	return NET_RX_DROP;
-}
-
-
-static struct packet_type ieee802154_packet_type = {
-	.type = htons(ETH_P_IEEE802154),
-	.func = ieee802154_rcv,
-};
-
-static int __init af_ieee802154_init(void)
-{
-	int rc = -EINVAL;
-
-	rc = proto_register(&ieee802154_raw_prot, 1);
-	if (rc)
-		goto out;
-
-	rc = proto_register(&ieee802154_dgram_prot, 1);
-	if (rc)
-		goto err_dgram;
-
-	/* Tell SOCKET that we are alive */
-	rc = sock_register(&ieee802154_family_ops);
-	if (rc)
-		goto err_sock;
-	dev_add_pack(&ieee802154_packet_type);
-
-	rc = 0;
-	goto out;
-
-err_sock:
-	proto_unregister(&ieee802154_dgram_prot);
-err_dgram:
-	proto_unregister(&ieee802154_raw_prot);
-out:
-	return rc;
-}
-static void __exit af_ieee802154_remove(void)
-{
-	dev_remove_pack(&ieee802154_packet_type);
-	sock_unregister(PF_IEEE802154);
-	proto_unregister(&ieee802154_dgram_prot);
-	proto_unregister(&ieee802154_raw_prot);
-}
-
-module_init(af_ieee802154_init);
-module_exit(af_ieee802154_remove);
-
-MODULE_LICENSE("GPL");
-MODULE_ALIAS_NETPROTO(PF_IEEE802154);
diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c
new file mode 100644
index 000000000000..2ee00e8a0308
--- /dev/null
+++ b/net/ieee802154/core.c
@@ -0,0 +1,325 @@
+/*
+ * Copyright (C) 2007, 2008, 2009 Siemens AG
+ *
+ * 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.
+ *
+ */
+
+#include <linux/slab.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/device.h>
+
+#include <net/cfg802154.h>
+#include <net/rtnetlink.h>
+
+#include "ieee802154.h"
+#include "nl802154.h"
+#include "sysfs.h"
+#include "core.h"
+
+/* name for sysfs, %d is appended */
+#define PHY_NAME "phy"
+
+/* RCU-protected (and RTNL for writers) */
+LIST_HEAD(cfg802154_rdev_list);
+int cfg802154_rdev_list_generation;
+
+static int wpan_phy_match(struct device *dev, const void *data)
+{
+	return !strcmp(dev_name(dev), (const char *)data);
+}
+
+struct wpan_phy *wpan_phy_find(const char *str)
+{
+	struct device *dev;
+
+	if (WARN_ON(!str))
+		return NULL;
+
+	dev = class_find_device(&wpan_phy_class, NULL, str, wpan_phy_match);
+	if (!dev)
+		return NULL;
+
+	return container_of(dev, struct wpan_phy, dev);
+}
+EXPORT_SYMBOL(wpan_phy_find);
+
+struct wpan_phy_iter_data {
+	int (*fn)(struct wpan_phy *phy, void *data);
+	void *data;
+};
+
+static int wpan_phy_iter(struct device *dev, void *_data)
+{
+	struct wpan_phy_iter_data *wpid = _data;
+	struct wpan_phy *phy = container_of(dev, struct wpan_phy, dev);
+
+	return wpid->fn(phy, wpid->data);
+}
+
+int wpan_phy_for_each(int (*fn)(struct wpan_phy *phy, void *data),
+		      void *data)
+{
+	struct wpan_phy_iter_data wpid = {
+		.fn = fn,
+		.data = data,
+	};
+
+	return class_for_each_device(&wpan_phy_class, NULL,
+			&wpid, wpan_phy_iter);
+}
+EXPORT_SYMBOL(wpan_phy_for_each);
+
+struct cfg802154_registered_device *
+cfg802154_rdev_by_wpan_phy_idx(int wpan_phy_idx)
+{
+	struct cfg802154_registered_device *result = NULL, *rdev;
+
+	ASSERT_RTNL();
+
+	list_for_each_entry(rdev, &cfg802154_rdev_list, list) {
+		if (rdev->wpan_phy_idx == wpan_phy_idx) {
+			result = rdev;
+			break;
+		}
+	}
+
+	return result;
+}
+
+struct wpan_phy *
+wpan_phy_new(const struct cfg802154_ops *ops, size_t priv_size)
+{
+	static atomic_t wpan_phy_counter = ATOMIC_INIT(0);
+	struct cfg802154_registered_device *rdev;
+	size_t alloc_size;
+
+	alloc_size = sizeof(*rdev) + priv_size;
+	rdev = kzalloc(alloc_size, GFP_KERNEL);
+	if (!rdev)
+		return NULL;
+
+	rdev->ops = ops;
+
+	rdev->wpan_phy_idx = atomic_inc_return(&wpan_phy_counter);
+
+	if (unlikely(rdev->wpan_phy_idx < 0)) {
+		/* ugh, wrapped! */
+		atomic_dec(&wpan_phy_counter);
+		kfree(rdev);
+		return NULL;
+	}
+
+	/* atomic_inc_return makes it start at 1, make it start at 0 */
+	rdev->wpan_phy_idx--;
+
+	mutex_init(&rdev->wpan_phy.pib_lock);
+
+	INIT_LIST_HEAD(&rdev->wpan_dev_list);
+	device_initialize(&rdev->wpan_phy.dev);
+	dev_set_name(&rdev->wpan_phy.dev, PHY_NAME "%d", rdev->wpan_phy_idx);
+
+	rdev->wpan_phy.dev.class = &wpan_phy_class;
+	rdev->wpan_phy.dev.platform_data = rdev;
+
+	init_waitqueue_head(&rdev->dev_wait);
+
+	return &rdev->wpan_phy;
+}
+EXPORT_SYMBOL(wpan_phy_new);
+
+int wpan_phy_register(struct wpan_phy *phy)
+{
+	struct cfg802154_registered_device *rdev = wpan_phy_to_rdev(phy);
+	int ret;
+
+	rtnl_lock();
+	ret = device_add(&phy->dev);
+	if (ret) {
+		rtnl_unlock();
+		return ret;
+	}
+
+	list_add_rcu(&rdev->list, &cfg802154_rdev_list);
+	cfg802154_rdev_list_generation++;
+
+	/* TODO phy registered lock */
+	rtnl_unlock();
+
+	/* TODO nl802154 phy notify */
+
+	return 0;
+}
+EXPORT_SYMBOL(wpan_phy_register);
+
+void wpan_phy_unregister(struct wpan_phy *phy)
+{
+	struct cfg802154_registered_device *rdev = wpan_phy_to_rdev(phy);
+
+	wait_event(rdev->dev_wait, ({
+		int __count;
+		rtnl_lock();
+		__count = rdev->opencount;
+		rtnl_unlock();
+		__count == 0; }));
+
+	rtnl_lock();
+	/* TODO nl802154 phy notify */
+	/* TODO phy registered lock */
+
+	WARN_ON(!list_empty(&rdev->wpan_dev_list));
+
+	/* First remove the hardware from everywhere, this makes
+	 * it impossible to find from userspace.
+	 */
+	list_del_rcu(&rdev->list);
+	synchronize_rcu();
+
+	cfg802154_rdev_list_generation++;
+
+	device_del(&phy->dev);
+
+	rtnl_unlock();
+}
+EXPORT_SYMBOL(wpan_phy_unregister);
+
+void wpan_phy_free(struct wpan_phy *phy)
+{
+	put_device(&phy->dev);
+}
+EXPORT_SYMBOL(wpan_phy_free);
+
+void cfg802154_dev_free(struct cfg802154_registered_device *rdev)
+{
+	kfree(rdev);
+}
+
+static void
+cfg802154_update_iface_num(struct cfg802154_registered_device *rdev,
+			   int iftype, int num)
+{
+	ASSERT_RTNL();
+
+	rdev->num_running_ifaces += num;
+}
+
+static int cfg802154_netdev_notifier_call(struct notifier_block *nb,
+					  unsigned long state, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
+	struct cfg802154_registered_device *rdev;
+
+	if (!wpan_dev)
+		return NOTIFY_DONE;
+
+	rdev = wpan_phy_to_rdev(wpan_dev->wpan_phy);
+
+	/* TODO WARN_ON unspec type */
+
+	switch (state) {
+		/* TODO NETDEV_DEVTYPE */
+	case NETDEV_REGISTER:
+		dev->features |= NETIF_F_NETNS_LOCAL;
+		wpan_dev->identifier = ++rdev->wpan_dev_id;
+		list_add_rcu(&wpan_dev->list, &rdev->wpan_dev_list);
+		rdev->devlist_generation++;
+
+		wpan_dev->netdev = dev;
+		break;
+	case NETDEV_DOWN:
+		cfg802154_update_iface_num(rdev, wpan_dev->iftype, -1);
+
+		rdev->opencount--;
+		wake_up(&rdev->dev_wait);
+		break;
+	case NETDEV_UP:
+		cfg802154_update_iface_num(rdev, wpan_dev->iftype, 1);
+
+		rdev->opencount++;
+		break;
+	case NETDEV_UNREGISTER:
+		/* It is possible to get NETDEV_UNREGISTER
+		 * multiple times. To detect that, check
+		 * that the interface is still on the list
+		 * of registered interfaces, and only then
+		 * remove and clean it up.
+		 */
+		if (!list_empty(&wpan_dev->list)) {
+			list_del_rcu(&wpan_dev->list);
+			rdev->devlist_generation++;
+		}
+		/* synchronize (so that we won't find this netdev
+		 * from other code any more) and then clear the list
+		 * head so that the above code can safely check for
+		 * !list_empty() to avoid double-cleanup.
+		 */
+		synchronize_rcu();
+		INIT_LIST_HEAD(&wpan_dev->list);
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block cfg802154_netdev_notifier = {
+	.notifier_call = cfg802154_netdev_notifier_call,
+};
+
+static int __init wpan_phy_class_init(void)
+{
+	int rc;
+
+	rc = wpan_phy_sysfs_init();
+	if (rc)
+		goto err;
+
+	rc = register_netdevice_notifier(&cfg802154_netdev_notifier);
+	if (rc)
+		goto err_nl;
+
+	rc = ieee802154_nl_init();
+	if (rc)
+		goto err_notifier;
+
+	rc = nl802154_init();
+	if (rc)
+		goto err_ieee802154_nl;
+
+	return 0;
+
+err_ieee802154_nl:
+	ieee802154_nl_exit();
+
+err_notifier:
+	unregister_netdevice_notifier(&cfg802154_netdev_notifier);
+err_nl:
+	wpan_phy_sysfs_exit();
+err:
+	return rc;
+}
+subsys_initcall(wpan_phy_class_init);
+
+static void __exit wpan_phy_class_exit(void)
+{
+	nl802154_exit();
+	ieee802154_nl_exit();
+	unregister_netdevice_notifier(&cfg802154_netdev_notifier);
+	wpan_phy_sysfs_exit();
+}
+module_exit(wpan_phy_class_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("IEEE 802.15.4 configuration interface");
+MODULE_AUTHOR("Dmitry Eremin-Solenikov");
+
diff --git a/net/ieee802154/core.h b/net/ieee802154/core.h
new file mode 100644
index 000000000000..f3e95580caee
--- /dev/null
+++ b/net/ieee802154/core.h
@@ -0,0 +1,46 @@
+#ifndef __IEEE802154_CORE_H
+#define __IEEE802154_CORE_H
+
+#include <net/cfg802154.h>
+
+struct cfg802154_registered_device {
+	const struct cfg802154_ops *ops;
+	struct list_head list;
+
+	/* wpan_phy index, internal only */
+	int wpan_phy_idx;
+
+	/* also protected by devlist_mtx */
+	int opencount;
+	wait_queue_head_t dev_wait;
+
+	/* protected by RTNL only */
+	int num_running_ifaces;
+
+	/* associated wpan interfaces, protected by rtnl or RCU */
+	struct list_head wpan_dev_list;
+	int devlist_generation, wpan_dev_id;
+
+	/* must be last because of the way we do wpan_phy_priv(),
+	 * and it should at least be aligned to NETDEV_ALIGN
+	 */
+	struct wpan_phy wpan_phy __aligned(NETDEV_ALIGN);
+};
+
+static inline struct cfg802154_registered_device *
+wpan_phy_to_rdev(struct wpan_phy *wpan_phy)
+{
+	BUG_ON(!wpan_phy);
+	return container_of(wpan_phy, struct cfg802154_registered_device,
+			    wpan_phy);
+}
+
+extern struct list_head cfg802154_rdev_list;
+extern int cfg802154_rdev_list_generation;
+
+/* free object */
+void cfg802154_dev_free(struct cfg802154_registered_device *rdev);
+struct cfg802154_registered_device *
+cfg802154_rdev_by_wpan_phy_idx(int wpan_phy_idx);
+
+#endif /* __IEEE802154_CORE_H */
diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c
deleted file mode 100644
index ef2ad8aaef13..000000000000
--- a/net/ieee802154/dgram.c
+++ /dev/null
@@ -1,554 +0,0 @@
-/*
- * IEEE 802.15.4 dgram socket interface
- *
- * Copyright 2007, 2008 Siemens AG
- *
- * 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.
- *
- * Written by:
- * Sergey Lapin <slapin@ossfans.org>
- * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
- */
-
-#include <linux/capability.h>
-#include <linux/net.h>
-#include <linux/module.h>
-#include <linux/if_arp.h>
-#include <linux/list.h>
-#include <linux/slab.h>
-#include <net/sock.h>
-#include <net/af_ieee802154.h>
-#include <net/ieee802154.h>
-#include <net/ieee802154_netdev.h>
-
-#include <asm/ioctls.h>
-
-#include "af802154.h"
-
-static HLIST_HEAD(dgram_head);
-static DEFINE_RWLOCK(dgram_lock);
-
-struct dgram_sock {
-	struct sock sk;
-
-	struct ieee802154_addr src_addr;
-	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)
-{
-	return container_of(sk, struct dgram_sock, sk);
-}
-
-static void dgram_hash(struct sock *sk)
-{
-	write_lock_bh(&dgram_lock);
-	sk_add_node(sk, &dgram_head);
-	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
-	write_unlock_bh(&dgram_lock);
-}
-
-static void dgram_unhash(struct sock *sk)
-{
-	write_lock_bh(&dgram_lock);
-	if (sk_del_node_init(sk))
-		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
-	write_unlock_bh(&dgram_lock);
-}
-
-static int dgram_init(struct sock *sk)
-{
-	struct dgram_sock *ro = dgram_sk(sk);
-
-	ro->want_ack = 1;
-	return 0;
-}
-
-static void dgram_close(struct sock *sk, long timeout)
-{
-	sk_common_release(sk);
-}
-
-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;
-
-	lock_sock(sk);
-
-	ro->bound = 0;
-
-	if (len < sizeof(*addr))
-		goto out;
-
-	if (addr->family != AF_IEEE802154)
-		goto out;
-
-	ieee802154_addr_from_sa(&haddr, &addr->addr);
-	dev = ieee802154_get_dev(sock_net(sk), &haddr);
-	if (!dev) {
-		err = -ENODEV;
-		goto out;
-	}
-
-	if (dev->type != ARPHRD_IEEE802154) {
-		err = -ENODEV;
-		goto out_put;
-	}
-
-	ro->src_addr = haddr;
-
-	ro->bound = 1;
-	err = 0;
-out_put:
-	dev_put(dev);
-out:
-	release_sock(sk);
-
-	return err;
-}
-
-static int dgram_ioctl(struct sock *sk, int cmd, unsigned long arg)
-{
-	switch (cmd) {
-	case SIOCOUTQ:
-	{
-		int amount = sk_wmem_alloc_get(sk);
-
-		return put_user(amount, (int __user *)arg);
-	}
-
-	case SIOCINQ:
-	{
-		struct sk_buff *skb;
-		unsigned long amount;
-
-		amount = 0;
-		spin_lock_bh(&sk->sk_receive_queue.lock);
-		skb = skb_peek(&sk->sk_receive_queue);
-		if (skb != NULL) {
-			/* We will only return the amount
-			 * of this packet since that is all
-			 * that will be read.
-			 */
-			amount = skb->len - ieee802154_hdr_length(skb);
-		}
-		spin_unlock_bh(&sk->sk_receive_queue.lock);
-		return put_user(amount, (int __user *)arg);
-	}
-
-	}
-
-	return -ENOIOCTLCMD;
-}
-
-/* FIXME: autobind */
-static int dgram_connect(struct sock *sk, struct sockaddr *uaddr,
-			 int len)
-{
-	struct sockaddr_ieee802154 *addr = (struct sockaddr_ieee802154 *)uaddr;
-	struct dgram_sock *ro = dgram_sk(sk);
-	int err = 0;
-
-	if (len < sizeof(*addr))
-		return -EINVAL;
-
-	if (addr->family != AF_IEEE802154)
-		return -EINVAL;
-
-	lock_sock(sk);
-
-	if (!ro->bound) {
-		err = -ENETUNREACH;
-		goto out;
-	}
-
-	ieee802154_addr_from_sa(&ro->dst_addr, &addr->addr);
-	ro->connected = 1;
-
-out:
-	release_sock(sk);
-	return err;
-}
-
-static int dgram_disconnect(struct sock *sk, int flags)
-{
-	struct dgram_sock *ro = dgram_sk(sk);
-
-	lock_sock(sk);
-	ro->connected = 0;
-	release_sock(sk);
-
-	return 0;
-}
-
-static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk,
-			 struct msghdr *msg, size_t size)
-{
-	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;
-
-	if (msg->msg_flags & MSG_OOB) {
-		pr_debug("msg->msg_flags = 0x%x\n", msg->msg_flags);
-		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
-		dev = ieee802154_get_dev(sock_net(sk), &ro->src_addr);
-
-	if (!dev) {
-		pr_debug("no dev\n");
-		err = -ENXIO;
-		goto out;
-	}
-	mtu = dev->mtu;
-	pr_debug("name = %s, mtu = %u\n", dev->name, mtu);
-
-	if (size > mtu) {
-		pr_debug("size = %Zu, mtu = %u\n", size, mtu);
-		err = -EMSGSIZE;
-		goto out_dev;
-	}
-
-	hlen = LL_RESERVED_SPACE(dev);
-	tlen = dev->needed_tailroom;
-	skb = sock_alloc_send_skb(sk, hlen + tlen + size,
-				  msg->msg_flags & MSG_DONTWAIT,
-				  &err);
-	if (!skb)
-		goto out_dev;
-
-	skb_reserve(skb, hlen);
-
-	skb_reset_network_header(skb);
-
-	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;
-
-	err = dev_hard_header(skb, dev, ETH_P_IEEE802154, &dst_addr,
-			      ro->bound ? &ro->src_addr : NULL, size);
-	if (err < 0)
-		goto out_skb;
-
-	err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size);
-	if (err < 0)
-		goto out_skb;
-
-	skb->dev = dev;
-	skb->sk  = sk;
-	skb->protocol = htons(ETH_P_IEEE802154);
-
-	dev_put(dev);
-
-	err = dev_queue_xmit(skb);
-	if (err > 0)
-		err = net_xmit_errno(err);
-
-	return err ?: size;
-
-out_skb:
-	kfree_skb(skb);
-out_dev:
-	dev_put(dev);
-out:
-	return err;
-}
-
-static int dgram_recvmsg(struct kiocb *iocb, struct sock *sk,
-			 struct msghdr *msg, size_t len, int noblock,
-			 int flags, int *addr_len)
-{
-	size_t copied = 0;
-	int err = -EOPNOTSUPP;
-	struct sk_buff *skb;
-	DECLARE_SOCKADDR(struct sockaddr_ieee802154 *, saddr, msg->msg_name);
-
-	skb = skb_recv_datagram(sk, flags, noblock, &err);
-	if (!skb)
-		goto out;
-
-	copied = skb->len;
-	if (len < copied) {
-		msg->msg_flags |= MSG_TRUNC;
-		copied = len;
-	}
-
-	/* FIXME: skip headers if necessary ?! */
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
-	if (err)
-		goto done;
-
-	sock_recv_ts_and_drops(msg, sk, skb);
-
-	if (saddr) {
-		saddr->family = AF_IEEE802154;
-		ieee802154_addr_to_sa(&saddr->addr, &mac_cb(skb)->source);
-		*addr_len = sizeof(*saddr);
-	}
-
-	if (flags & MSG_TRUNC)
-		copied = skb->len;
-done:
-	skb_free_datagram(sk, skb);
-out:
-	if (err)
-		return err;
-	return copied;
-}
-
-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;
-	}
-
-	return NET_RX_SUCCESS;
-}
-
-static inline bool
-ieee802154_match_sock(__le64 hw_addr, __le16 pan_id, __le16 short_addr,
-		      struct dgram_sock *ro)
-{
-	if (!ro->bound)
-		return true;
-
-	if (ro->src_addr.mode == IEEE802154_ADDR_LONG &&
-	    hw_addr == ro->src_addr.extended_addr)
-		return true;
-
-	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 false;
-}
-
-int ieee802154_dgram_deliver(struct net_device *dev, struct sk_buff *skb)
-{
-	struct sock *sk, *prev = NULL;
-	int ret = NET_RX_SUCCESS;
-	__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(hw_addr, pan_id, short_addr,
-					  dgram_sk(sk))) {
-			if (prev) {
-				struct sk_buff *clone;
-
-				clone = skb_clone(skb, GFP_ATOMIC);
-				if (clone)
-					dgram_rcv_skb(prev, clone);
-			}
-
-			prev = sk;
-		}
-	}
-
-	if (prev) {
-		dgram_rcv_skb(prev, skb);
-	} else {
-		kfree_skb(skb);
-		ret = NET_RX_DROP;
-	}
-	read_unlock(&dgram_lock);
-
-	return ret;
-}
-
-static int dgram_getsockopt(struct sock *sk, int level, int optname,
-			    char __user *optval, int __user *optlen)
-{
-	struct dgram_sock *ro = dgram_sk(sk);
-
-	int val, len;
-
-	if (level != SOL_IEEE802154)
-		return -EOPNOTSUPP;
-
-	if (get_user(len, optlen))
-		return -EFAULT;
-
-	len = min_t(unsigned int, len, sizeof(int));
-
-	switch (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;
-	}
-
-	if (put_user(len, optlen))
-		return -EFAULT;
-	if (copy_to_user(optval, &val, len))
-		return -EFAULT;
-	return 0;
-}
-
-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;
-
-	if (optlen < sizeof(int))
-		return -EINVAL;
-
-	if (get_user(val, (int __user *)optval))
-		return -EFAULT;
-
-	lock_sock(sk);
-
-	switch (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;
-	}
-
-	release_sock(sk);
-	return err;
-}
-
-struct proto ieee802154_dgram_prot = {
-	.name		= "IEEE-802.15.4-MAC",
-	.owner		= THIS_MODULE,
-	.obj_size	= sizeof(struct dgram_sock),
-	.init		= dgram_init,
-	.close		= dgram_close,
-	.bind		= dgram_bind,
-	.sendmsg	= dgram_sendmsg,
-	.recvmsg	= dgram_recvmsg,
-	.hash		= dgram_hash,
-	.unhash		= dgram_unhash,
-	.connect	= dgram_connect,
-	.disconnect	= dgram_disconnect,
-	.ioctl		= dgram_ioctl,
-	.getsockopt	= dgram_getsockopt,
-	.setsockopt	= dgram_setsockopt,
-};
-
diff --git a/net/ieee802154/header_ops.c b/net/ieee802154/header_ops.c
index c09294e39ca6..a051b6993177 100644
--- a/net/ieee802154/header_ops.c
+++ b/net/ieee802154/header_ops.c
@@ -14,8 +14,9 @@
  * Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
  */
 
+#include <linux/ieee802154.h>
+
 #include <net/mac802154.h>
-#include <net/ieee802154.h>
 #include <net/ieee802154_netdev.h>
 
 static int
diff --git a/net/ieee802154/ieee802154.h b/net/ieee802154/ieee802154.h
index 5d352f86979e..a5d7515b7f62 100644
--- a/net/ieee802154/ieee802154.h
+++ b/net/ieee802154/ieee802154.h
@@ -10,16 +10,12 @@
  * 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.
- *
  */
 #ifndef IEEE_802154_LOCAL_H
 #define IEEE_802154_LOCAL_H
 
 int __init ieee802154_nl_init(void);
-void __exit ieee802154_nl_exit(void);
+void ieee802154_nl_exit(void);
 
 #define IEEE802154_OP(_cmd, _func)			\
 	{						\
diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c
index 9222966f5e6d..c8133c07ceee 100644
--- a/net/ieee802154/netlink.c
+++ b/net/ieee802154/netlink.c
@@ -1,5 +1,5 @@
 /*
- * Netlink inteface for IEEE 802.15.4 stack
+ * Netlink interface for IEEE 802.15.4 stack
  *
  * Copyright 2007, 2008 Siemens AG
  *
@@ -12,10 +12,6 @@
  * 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.
- *
  * Written by:
  * Sergey Lapin <slapin@ossfans.org>
  * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
@@ -67,17 +63,13 @@ int ieee802154_nl_mcast(struct sk_buff *msg, unsigned int group)
 	struct nlmsghdr *nlh = nlmsg_hdr(msg);
 	void *hdr = genlmsg_data(nlmsg_data(nlh));
 
-	if (genlmsg_end(msg, hdr) < 0)
-		goto out;
+	genlmsg_end(msg, hdr);
 
 	return genlmsg_multicast(&nl802154_family, msg, 0, group, GFP_ATOMIC);
-out:
-	nlmsg_free(msg);
-	return -ENOBUFS;
 }
 
 struct sk_buff *ieee802154_nl_new_reply(struct genl_info *info,
-		int flags, u8 req)
+					int flags, u8 req)
 {
 	void *hdr;
 	struct sk_buff *msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
@@ -100,13 +92,9 @@ int ieee802154_nl_reply(struct sk_buff *msg, struct genl_info *info)
 	struct nlmsghdr *nlh = nlmsg_hdr(msg);
 	void *hdr = genlmsg_data(nlmsg_data(nlh));
 
-	if (genlmsg_end(msg, hdr) < 0)
-		goto out;
+	genlmsg_end(msg, hdr);
 
 	return genlmsg_reply(msg, info);
-out:
-	nlmsg_free(msg);
-	return -ENOBUFS;
 }
 
 static const struct genl_ops ieee8021154_ops[] = {
@@ -151,7 +139,6 @@ static const struct genl_multicast_group ieee802154_mcgrps[] = {
 	[IEEE802154_BEACON_MCGRP] = { .name = IEEE802154_MCAST_BEACON_NAME, },
 };
 
-
 int __init ieee802154_nl_init(void)
 {
 	return genl_register_family_with_ops_groups(&nl802154_family,
@@ -159,7 +146,7 @@ int __init ieee802154_nl_init(void)
 						    ieee802154_mcgrps);
 }
 
-void __exit ieee802154_nl_exit(void)
+void ieee802154_nl_exit(void)
 {
 	genl_unregister_family(&nl802154_family);
 }
diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c
index c6bfe22bfa5e..2b4955d7aae5 100644
--- a/net/ieee802154/nl-mac.c
+++ b/net/ieee802154/nl-mac.c
@@ -1,5 +1,5 @@
 /*
- * Netlink inteface for IEEE 802.15.4 stack
+ * Netlink interface for IEEE 802.15.4 stack
  *
  * Copyright 2007, 2008 Siemens AG
  *
@@ -12,10 +12,6 @@
  * 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.
- *
  * Written by:
  * Sergey Lapin <slapin@ossfans.org>
  * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
@@ -26,16 +22,15 @@
 #include <linux/kernel.h>
 #include <linux/if_arp.h>
 #include <linux/netdevice.h>
+#include <linux/ieee802154.h>
 #include <net/netlink.h>
 #include <net/genetlink.h>
 #include <net/sock.h>
 #include <linux/nl802154.h>
 #include <linux/export.h>
 #include <net/af_ieee802154.h>
-#include <net/nl802154.h>
-#include <net/ieee802154.h>
 #include <net/ieee802154_netdev.h>
-#include <net/wpan-phy.h>
+#include <net/cfg802154.h>
 
 #include "ieee802154.h"
 
@@ -59,186 +54,7 @@ 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)
-{
-	struct sk_buff *msg;
-
-	pr_debug("%s\n", __func__);
-
-	if (addr->mode != IEEE802154_ADDR_LONG) {
-		pr_err("%s: received non-long source address!\n", __func__);
-		return -EINVAL;
-	}
-
-	msg = ieee802154_nl_create(0, IEEE802154_ASSOCIATE_INDIC);
-	if (!msg)
-		return -ENOBUFS;
-
-	if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) ||
-	    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_hwaddr(msg, IEEE802154_ATTR_SRC_HW_ADDR,
-			   addr->extended_addr) ||
-	    nla_put_u8(msg, IEEE802154_ATTR_CAPABILITY, cap))
-		goto nla_put_failure;
-
-	return ieee802154_nl_mcast(msg, IEEE802154_COORD_MCGRP);
-
-nla_put_failure:
-	nlmsg_free(msg);
-	return -ENOBUFS;
-}
-EXPORT_SYMBOL(ieee802154_nl_assoc_indic);
-
-int ieee802154_nl_assoc_confirm(struct net_device *dev, __le16 short_addr,
-				u8 status)
-{
-	struct sk_buff *msg;
-
-	pr_debug("%s\n", __func__);
-
-	msg = ieee802154_nl_create(0, IEEE802154_ASSOCIATE_CONF);
-	if (!msg)
-		return -ENOBUFS;
-
-	if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) ||
-	    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_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);
-
-nla_put_failure:
-	nlmsg_free(msg);
-	return -ENOBUFS;
-}
-EXPORT_SYMBOL(ieee802154_nl_assoc_confirm);
-
-int ieee802154_nl_disassoc_indic(struct net_device *dev,
-				 struct ieee802154_addr *addr,
-				 u8 reason)
-{
-	struct sk_buff *msg;
-
-	pr_debug("%s\n", __func__);
-
-	msg = ieee802154_nl_create(0, IEEE802154_DISASSOCIATE_INDIC);
-	if (!msg)
-		return -ENOBUFS;
-
-	if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) ||
-	    nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) ||
-	    nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN,
-		    dev->dev_addr))
-		goto nla_put_failure;
-	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_shortaddr(msg, IEEE802154_ATTR_SRC_SHORT_ADDR,
-				      addr->short_addr))
-			goto nla_put_failure;
-	}
-	if (nla_put_u8(msg, IEEE802154_ATTR_REASON, reason))
-		goto nla_put_failure;
-	return ieee802154_nl_mcast(msg, IEEE802154_COORD_MCGRP);
-
-nla_put_failure:
-	nlmsg_free(msg);
-	return -ENOBUFS;
-}
-EXPORT_SYMBOL(ieee802154_nl_disassoc_indic);
-
-int ieee802154_nl_disassoc_confirm(struct net_device *dev, u8 status)
-{
-	struct sk_buff *msg;
-
-	pr_debug("%s\n", __func__);
-
-	msg = ieee802154_nl_create(0, IEEE802154_DISASSOCIATE_CONF);
-	if (!msg)
-		return -ENOBUFS;
-
-	if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) ||
-	    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_u8(msg, IEEE802154_ATTR_STATUS, status))
-		goto nla_put_failure;
-	return ieee802154_nl_mcast(msg, IEEE802154_COORD_MCGRP);
-
-nla_put_failure:
-	nlmsg_free(msg);
-	return -ENOBUFS;
-}
-EXPORT_SYMBOL(ieee802154_nl_disassoc_confirm);
-
-int ieee802154_nl_beacon_indic(struct net_device *dev, __le16 panid,
-			       __le16 coord_addr)
-{
-	struct sk_buff *msg;
-
-	pr_debug("%s\n", __func__);
-
-	msg = ieee802154_nl_create(0, IEEE802154_BEACON_NOTIFY_INDIC);
-	if (!msg)
-		return -ENOBUFS;
-
-	if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) ||
-	    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_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);
-
-nla_put_failure:
-	nlmsg_free(msg);
-	return -ENOBUFS;
-}
-EXPORT_SYMBOL(ieee802154_nl_beacon_indic);
-
-int ieee802154_nl_scan_confirm(struct net_device *dev,
-			       u8 status, u8 scan_type,
-			       u32 unscanned, u8 page,
-			       u8 *edl/* , struct list_head *pan_desc_list */)
-{
-	struct sk_buff *msg;
-
-	pr_debug("%s\n", __func__);
-
-	msg = ieee802154_nl_create(0, IEEE802154_SCAN_CONF);
-	if (!msg)
-		return -ENOBUFS;
-
-	if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) ||
-	    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_u8(msg, IEEE802154_ATTR_STATUS, status) ||
-	    nla_put_u8(msg, IEEE802154_ATTR_SCAN_TYPE, scan_type) ||
-	    nla_put_u32(msg, IEEE802154_ATTR_CHANNELS, unscanned) ||
-	    nla_put_u8(msg, IEEE802154_ATTR_PAGE, page) ||
-	    (edl &&
-	     nla_put(msg, IEEE802154_ATTR_ED_LIST, 27, edl)))
-		goto nla_put_failure;
-	return ieee802154_nl_mcast(msg, IEEE802154_COORD_MCGRP);
-
-nla_put_failure:
-	nlmsg_free(msg);
-	return -ENOBUFS;
-}
-EXPORT_SYMBOL(ieee802154_nl_scan_confirm);
-
-int ieee802154_nl_start_confirm(struct net_device *dev, u8 status)
+static int ieee802154_nl_start_confirm(struct net_device *dev, u8 status)
 {
 	struct sk_buff *msg;
 
@@ -260,7 +76,6 @@ nla_put_failure:
 	nlmsg_free(msg);
 	return -ENOBUFS;
 }
-EXPORT_SYMBOL(ieee802154_nl_start_confirm);
 
 static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 portid,
 				    u32 seq, int flags, struct net_device *dev)
@@ -278,8 +93,9 @@ static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 portid,
 		goto out;
 
 	ops = ieee802154_mlme_ops(dev);
-	phy = ops->get_phy(dev);
+	phy = dev->ieee802154_ptr->wpan_phy;
 	BUG_ON(!phy);
+	get_device(&phy->dev);
 
 	short_addr = ops->get_short_addr(dev);
 	pan_id = ops->get_pan_id(dev);
@@ -296,13 +112,15 @@ static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 portid,
 	if (ops->get_mac_params) {
 		struct ieee802154_mac_params params;
 
+		rtnl_lock();
 		ops->get_mac_params(dev, &params);
+		rtnl_unlock();
 
 		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) ||
+			       params.cca.mode) ||
 		    nla_put_s32(msg, IEEE802154_ATTR_CCA_ED_LEVEL,
 				params.cca_ed_level) ||
 		    nla_put_u8(msg, IEEE802154_ATTR_CSMA_RETRIES,
@@ -317,7 +135,8 @@ static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 portid,
 	}
 
 	wpan_phy_put(phy);
-	return genlmsg_end(msg, hdr);
+	genlmsg_end(msg, hdr);
+	return 0;
 
 nla_put_failure:
 	wpan_phy_put(phy);
@@ -347,7 +166,10 @@ static struct net_device *ieee802154_nl_get_dev(struct genl_info *info)
 	if (!dev)
 		return NULL;
 
-	if (dev->type != ARPHRD_IEEE802154) {
+	/* Check on mtu is currently a hacked solution because lowpan
+	 * and wpan have the same ARPHRD type.
+	 */
+	if (dev->type != ARPHRD_IEEE802154 || dev->mtu != IEEE802154_MTU) {
 		dev_put(dev);
 		return NULL;
 	}
@@ -481,7 +303,7 @@ int ieee802154_start_req(struct sk_buff *skb, struct genl_info *info)
 	u8 channel, bcn_ord, sf_ord;
 	u8 page;
 	int pan_coord, blx, coord_realign;
-	int ret = -EOPNOTSUPP;
+	int ret = -EBUSY;
 
 	if (!info->attrs[IEEE802154_ATTR_COORD_PAN_ID] ||
 	    !info->attrs[IEEE802154_ATTR_COORD_SHORT_ADDR] ||
@@ -497,9 +319,15 @@ int ieee802154_start_req(struct sk_buff *skb, struct genl_info *info)
 	dev = ieee802154_nl_get_dev(info);
 	if (!dev)
 		return -ENODEV;
-	if (!ieee802154_mlme_ops(dev)->start_req)
+
+	if (netif_running(dev))
 		goto out;
 
+	if (!ieee802154_mlme_ops(dev)->start_req) {
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
+
 	addr.mode = IEEE802154_ADDR_SHORT;
 	addr.short_addr = nla_get_shortaddr(
 			info->attrs[IEEE802154_ATTR_COORD_SHORT_ADDR]);
@@ -518,15 +346,21 @@ int ieee802154_start_req(struct sk_buff *skb, struct genl_info *info)
 	else
 		page = 0;
 
-
 	if (addr.short_addr == cpu_to_le16(IEEE802154_ADDR_BROADCAST)) {
 		ieee802154_nl_start_confirm(dev, IEEE802154_NO_SHORT_ADDRESS);
 		dev_put(dev);
 		return -EINVAL;
 	}
 
+	rtnl_lock();
 	ret = ieee802154_mlme_ops(dev)->start_req(dev, &addr, channel, page,
 		bcn_ord, sf_ord, pan_coord, blx, coord_realign);
+	rtnl_unlock();
+
+	/* FIXME: add validation for unused parameters to be sane
+	 * for SoftMAC
+	 */
+	ieee802154_nl_start_confirm(dev, IEEE802154_SUCCESS);
 
 out:
 	dev_put(dev);
@@ -562,7 +396,6 @@ int ieee802154_scan_req(struct sk_buff *skb, struct genl_info *info)
 	else
 		page = 0;
 
-
 	ret = ieee802154_mlme_ops(dev)->scan_req(dev, type, channels,
 						 page, duration);
 
@@ -616,7 +449,11 @@ int ieee802154_dump_iface(struct sk_buff *skb, struct netlink_callback *cb)
 
 	idx = 0;
 	for_each_netdev(net, dev) {
-		if (idx < s_idx || (dev->type != ARPHRD_IEEE802154))
+		/* Check on mtu is currently a hacked solution because lowpan
+		 * and wpan have the same ARPHRD type.
+		 */
+		if (idx < s_idx || dev->type != ARPHRD_IEEE802154 ||
+		    dev->mtu != IEEE802154_MTU)
 			goto cont;
 
 		if (ieee802154_nl_fill_iface(skb, NETLINK_CB(cb->skb).portid,
@@ -666,22 +503,10 @@ int ieee802154_set_macparams(struct sk_buff *skb, struct genl_info *info)
 	    !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;
-	}
+	phy = dev->ieee802154_ptr->wpan_phy;
+	get_device(&phy->dev);
 
+	rtnl_lock();
 	ops->get_mac_params(dev, &params);
 
 	if (info->attrs[IEEE802154_ATTR_TXPOWER])
@@ -691,7 +516,7 @@ int ieee802154_set_macparams(struct sk_buff *skb, struct genl_info *info)
 		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]);
+		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]);
@@ -709,20 +534,18 @@ int ieee802154_set_macparams(struct sk_buff *skb, struct genl_info *info)
 		params.frame_retries = nla_get_s8(info->attrs[IEEE802154_ATTR_FRAME_RETRIES]);
 
 	rc = ops->set_mac_params(dev, &params);
+	rtnl_unlock();
 
 	wpan_phy_put(phy);
 	dev_put(dev);
-	return rc;
 
-out_phy:
-	wpan_phy_put(phy);
+	return 0;
+
 out:
 	dev_put(dev);
 	return rc;
 }
 
-
-
 static int
 ieee802154_llsec_parse_key_id(struct genl_info *info,
 			      struct ieee802154_llsec_key_id *desc)
@@ -938,8 +761,6 @@ out:
 	return rc;
 }
 
-
-
 struct llsec_dump_data {
 	struct sk_buff *skb;
 	int s_idx, s_idx2;
@@ -962,7 +783,11 @@ ieee802154_llsec_dump_table(struct sk_buff *skb, struct netlink_callback *cb,
 	int rc;
 
 	for_each_netdev(net, dev) {
-		if (idx < first_dev || dev->type != ARPHRD_IEEE802154)
+		/* Check on mtu is currently a hacked solution because lowpan
+		 * and wpan have the same ARPHRD type.
+		 */
+		if (idx < first_dev || dev->type != ARPHRD_IEEE802154 ||
+		    dev->mtu != IEEE802154_MTU)
 			goto skip;
 
 		data.ops = ieee802154_mlme_ops(dev);
@@ -1012,8 +837,6 @@ ieee802154_nl_llsec_change(struct sk_buff *skb, struct genl_info *info,
 	return rc;
 }
 
-
-
 static int
 ieee802154_llsec_parse_key(struct genl_info *info,
 			   struct ieee802154_llsec_key *key)
@@ -1158,8 +981,6 @@ 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)
@@ -1290,8 +1111,6 @@ 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);
@@ -1406,8 +1225,6 @@ int ieee802154_llsec_dump_devkeys(struct sk_buff *skb,
 	return ieee802154_llsec_dump_table(skb, cb, llsec_iter_devkeys);
 }
 
-
-
 static int
 llsec_parse_seclevel(struct genl_info *info,
 		     struct ieee802154_llsec_seclevel *sl)
diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c
index 972baf83411a..346c6665d25e 100644
--- a/net/ieee802154/nl-phy.c
+++ b/net/ieee802154/nl-phy.c
@@ -1,5 +1,5 @@
 /*
- * Netlink inteface for IEEE 802.15.4 stack
+ * Netlink interface for IEEE 802.15.4 stack
  *
  * Copyright 2007, 2008 Siemens AG
  *
@@ -12,10 +12,6 @@
  * 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.
- *
  * Written by:
  * Sergey Lapin <slapin@ossfans.org>
  * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
@@ -27,13 +23,15 @@
 #include <linux/if_arp.h>
 #include <net/netlink.h>
 #include <net/genetlink.h>
-#include <net/wpan-phy.h>
+#include <net/cfg802154.h>
 #include <net/af_ieee802154.h>
 #include <net/ieee802154_netdev.h>
 #include <net/rtnetlink.h> /* for rtnl_{un,}lock */
 #include <linux/nl802154.h>
 
 #include "ieee802154.h"
+#include "rdev-ops.h"
+#include "core.h"
 
 static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 portid,
 				  u32 seq, int flags, struct wpan_phy *phy)
@@ -67,7 +65,8 @@ static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 portid,
 		goto nla_put_failure;
 	mutex_unlock(&phy->pib_lock);
 	kfree(buf);
-	return genlmsg_end(msg, hdr);
+	genlmsg_end(msg, hdr);
+	return 0;
 
 nla_put_failure:
 	mutex_unlock(&phy->pib_lock);
@@ -96,7 +95,6 @@ int ieee802154_list_phy(struct sk_buff *skb, struct genl_info *info)
 	if (name[nla_len(info->attrs[IEEE802154_ATTR_PHY_NAME]) - 1] != '\0')
 		return -EINVAL; /* phy name should be null-terminated */
 
-
 	phy = wpan_phy_find(name);
 	if (!phy)
 		return -ENODEV;
@@ -177,6 +175,7 @@ int ieee802154_add_iface(struct sk_buff *skb, struct genl_info *info)
 	int rc = -ENOBUFS;
 	struct net_device *dev;
 	int type = __IEEE802154_DEV_INVALID;
+	unsigned char name_assign_type;
 
 	pr_debug("%s\n", __func__);
 
@@ -192,8 +191,10 @@ int ieee802154_add_iface(struct sk_buff *skb, struct genl_info *info)
 		if (devname[nla_len(info->attrs[IEEE802154_ATTR_DEV_NAME]) - 1]
 				!= '\0')
 			return -EINVAL; /* phy name should be null-terminated */
+		name_assign_type = NET_NAME_USER;
 	} else  {
 		devname = "wpan%d";
+		name_assign_type = NET_NAME_ENUM;
 	}
 
 	if (strlen(devname) >= IFNAMSIZ)
@@ -207,11 +208,6 @@ int ieee802154_add_iface(struct sk_buff *skb, struct genl_info *info)
 	if (!msg)
 		goto out_dev;
 
-	if (!phy->add_iface) {
-		rc = -EINVAL;
-		goto nla_put_failure;
-	}
-
 	if (info->attrs[IEEE802154_ATTR_HW_ADDR] &&
 	    nla_len(info->attrs[IEEE802154_ATTR_HW_ADDR]) !=
 			IEEE802154_ADDR_LEN) {
@@ -227,11 +223,13 @@ int ieee802154_add_iface(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
-	dev = phy->add_iface(phy, devname, type);
+	dev = rdev_add_virtual_intf_deprecated(wpan_phy_to_rdev(phy), devname,
+					       name_assign_type, type);
 	if (IS_ERR(dev)) {
 		rc = PTR_ERR(dev);
 		goto nla_put_failure;
 	}
+	dev_hold(dev);
 
 	if (info->attrs[IEEE802154_ATTR_HW_ADDR]) {
 		struct sockaddr addr;
@@ -261,7 +259,7 @@ int ieee802154_add_iface(struct sk_buff *skb, struct genl_info *info)
 
 dev_unregister:
 	rtnl_lock(); /* del_iface must be called with RTNL lock */
-	phy->del_iface(phy, dev);
+	rdev_del_virtual_intf_deprecated(wpan_phy_to_rdev(phy), dev);
 	dev_put(dev);
 	rtnl_unlock();
 nla_put_failure:
@@ -292,8 +290,9 @@ int ieee802154_del_iface(struct sk_buff *skb, struct genl_info *info)
 	if (!dev)
 		return -ENODEV;
 
-	phy = ieee802154_mlme_ops(dev)->get_phy(dev);
+	phy = dev->ieee802154_ptr->wpan_phy;
 	BUG_ON(!phy);
+	get_device(&phy->dev);
 
 	rc = -EINVAL;
 	/* phy name is optional, but should be checked if it's given */
@@ -323,13 +322,8 @@ int ieee802154_del_iface(struct sk_buff *skb, struct genl_info *info)
 	if (!msg)
 		goto out_dev;
 
-	if (!phy->del_iface) {
-		rc = -EINVAL;
-		goto nla_put_failure;
-	}
-
 	rtnl_lock();
-	phy->del_iface(phy, dev);
+	rdev_del_virtual_intf_deprecated(wpan_phy_to_rdev(phy), dev);
 
 	/* We don't have device anymore */
 	dev_put(dev);
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
new file mode 100644
index 000000000000..f3c12f6a4a39
--- /dev/null
+++ b/net/ieee802154/nl802154.c
@@ -0,0 +1,999 @@
+/* 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.
+ *
+ * Authors:
+ * Alexander Aring <aar@pengutronix.de>
+ *
+ * Based on: net/wireless/nl80211.c
+ */
+
+#include <linux/rtnetlink.h>
+
+#include <net/cfg802154.h>
+#include <net/genetlink.h>
+#include <net/mac802154.h>
+#include <net/netlink.h>
+#include <net/nl802154.h>
+#include <net/sock.h>
+
+#include "nl802154.h"
+#include "rdev-ops.h"
+#include "core.h"
+
+static int nl802154_pre_doit(const struct genl_ops *ops, struct sk_buff *skb,
+			     struct genl_info *info);
+
+static void nl802154_post_doit(const struct genl_ops *ops, struct sk_buff *skb,
+			       struct genl_info *info);
+
+/* the netlink family */
+static struct genl_family nl802154_fam = {
+	.id = GENL_ID_GENERATE,		/* don't bother with a hardcoded ID */
+	.name = NL802154_GENL_NAME,	/* have users key off the name instead */
+	.hdrsize = 0,			/* no private header */
+	.version = 1,			/* no particular meaning now */
+	.maxattr = NL802154_ATTR_MAX,
+	.netnsok = true,
+	.pre_doit = nl802154_pre_doit,
+	.post_doit = nl802154_post_doit,
+};
+
+/* multicast groups */
+enum nl802154_multicast_groups {
+	NL802154_MCGRP_CONFIG,
+};
+
+static const struct genl_multicast_group nl802154_mcgrps[] = {
+	[NL802154_MCGRP_CONFIG] = { .name = "config", },
+};
+
+/* returns ERR_PTR values */
+static struct wpan_dev *
+__cfg802154_wpan_dev_from_attrs(struct net *netns, struct nlattr **attrs)
+{
+	struct cfg802154_registered_device *rdev;
+	struct wpan_dev *result = NULL;
+	bool have_ifidx = attrs[NL802154_ATTR_IFINDEX];
+	bool have_wpan_dev_id = attrs[NL802154_ATTR_WPAN_DEV];
+	u64 wpan_dev_id;
+	int wpan_phy_idx = -1;
+	int ifidx = -1;
+
+	ASSERT_RTNL();
+
+	if (!have_ifidx && !have_wpan_dev_id)
+		return ERR_PTR(-EINVAL);
+
+	if (have_ifidx)
+		ifidx = nla_get_u32(attrs[NL802154_ATTR_IFINDEX]);
+	if (have_wpan_dev_id) {
+		wpan_dev_id = nla_get_u64(attrs[NL802154_ATTR_WPAN_DEV]);
+		wpan_phy_idx = wpan_dev_id >> 32;
+	}
+
+	list_for_each_entry(rdev, &cfg802154_rdev_list, list) {
+		struct wpan_dev *wpan_dev;
+
+		/* TODO netns compare */
+
+		if (have_wpan_dev_id && rdev->wpan_phy_idx != wpan_phy_idx)
+			continue;
+
+		list_for_each_entry(wpan_dev, &rdev->wpan_dev_list, list) {
+			if (have_ifidx && wpan_dev->netdev &&
+			    wpan_dev->netdev->ifindex == ifidx) {
+				result = wpan_dev;
+				break;
+			}
+			if (have_wpan_dev_id &&
+			    wpan_dev->identifier == (u32)wpan_dev_id) {
+				result = wpan_dev;
+				break;
+			}
+		}
+
+		if (result)
+			break;
+	}
+
+	if (result)
+		return result;
+
+	return ERR_PTR(-ENODEV);
+}
+
+static struct cfg802154_registered_device *
+__cfg802154_rdev_from_attrs(struct net *netns, struct nlattr **attrs)
+{
+	struct cfg802154_registered_device *rdev = NULL, *tmp;
+	struct net_device *netdev;
+
+	ASSERT_RTNL();
+
+	if (!attrs[NL802154_ATTR_WPAN_PHY] &&
+	    !attrs[NL802154_ATTR_IFINDEX] &&
+	    !attrs[NL802154_ATTR_WPAN_DEV])
+		return ERR_PTR(-EINVAL);
+
+	if (attrs[NL802154_ATTR_WPAN_PHY])
+		rdev = cfg802154_rdev_by_wpan_phy_idx(
+				nla_get_u32(attrs[NL802154_ATTR_WPAN_PHY]));
+
+	if (attrs[NL802154_ATTR_WPAN_DEV]) {
+		u64 wpan_dev_id = nla_get_u64(attrs[NL802154_ATTR_WPAN_DEV]);
+		struct wpan_dev *wpan_dev;
+		bool found = false;
+
+		tmp = cfg802154_rdev_by_wpan_phy_idx(wpan_dev_id >> 32);
+		if (tmp) {
+			/* make sure wpan_dev exists */
+			list_for_each_entry(wpan_dev, &tmp->wpan_dev_list, list) {
+				if (wpan_dev->identifier != (u32)wpan_dev_id)
+					continue;
+				found = true;
+				break;
+			}
+
+			if (!found)
+				tmp = NULL;
+
+			if (rdev && tmp != rdev)
+				return ERR_PTR(-EINVAL);
+			rdev = tmp;
+		}
+	}
+
+	if (attrs[NL802154_ATTR_IFINDEX]) {
+		int ifindex = nla_get_u32(attrs[NL802154_ATTR_IFINDEX]);
+
+		netdev = __dev_get_by_index(netns, ifindex);
+		if (netdev) {
+			if (netdev->ieee802154_ptr)
+				tmp = wpan_phy_to_rdev(
+						netdev->ieee802154_ptr->wpan_phy);
+			else
+				tmp = NULL;
+
+			/* not wireless device -- return error */
+			if (!tmp)
+				return ERR_PTR(-EINVAL);
+
+			/* mismatch -- return error */
+			if (rdev && tmp != rdev)
+				return ERR_PTR(-EINVAL);
+
+			rdev = tmp;
+		}
+	}
+
+	if (!rdev)
+		return ERR_PTR(-ENODEV);
+
+	/* TODO netns compare */
+
+	return rdev;
+}
+
+/* This function returns a pointer to the driver
+ * that the genl_info item that is passed refers to.
+ *
+ * The result of this can be a PTR_ERR and hence must
+ * be checked with IS_ERR() for errors.
+ */
+static struct cfg802154_registered_device *
+cfg802154_get_dev_from_info(struct net *netns, struct genl_info *info)
+{
+	return __cfg802154_rdev_from_attrs(netns, info->attrs);
+}
+
+/* policy for the attributes */
+static const struct nla_policy nl802154_policy[NL802154_ATTR_MAX+1] = {
+	[NL802154_ATTR_WPAN_PHY] = { .type = NLA_U32 },
+	[NL802154_ATTR_WPAN_PHY_NAME] = { .type = NLA_NUL_STRING,
+					  .len = 20-1 },
+
+	[NL802154_ATTR_IFINDEX] = { .type = NLA_U32 },
+	[NL802154_ATTR_IFTYPE] = { .type = NLA_U32 },
+	[NL802154_ATTR_IFNAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ-1 },
+
+	[NL802154_ATTR_WPAN_DEV] = { .type = NLA_U64 },
+
+	[NL802154_ATTR_PAGE] = { .type = NLA_U8, },
+	[NL802154_ATTR_CHANNEL] = { .type = NLA_U8, },
+
+	[NL802154_ATTR_TX_POWER] = { .type = NLA_S8, },
+
+	[NL802154_ATTR_CCA_MODE] = { .type = NLA_U32, },
+	[NL802154_ATTR_CCA_OPT] = { .type = NLA_U32, },
+
+	[NL802154_ATTR_SUPPORTED_CHANNEL] = { .type = NLA_U32, },
+
+	[NL802154_ATTR_PAN_ID] = { .type = NLA_U16, },
+	[NL802154_ATTR_EXTENDED_ADDR] = { .type = NLA_U64 },
+	[NL802154_ATTR_SHORT_ADDR] = { .type = NLA_U16, },
+
+	[NL802154_ATTR_MIN_BE] = { .type = NLA_U8, },
+	[NL802154_ATTR_MAX_BE] = { .type = NLA_U8, },
+	[NL802154_ATTR_MAX_CSMA_BACKOFFS] = { .type = NLA_U8, },
+
+	[NL802154_ATTR_MAX_FRAME_RETRIES] = { .type = NLA_S8, },
+
+	[NL802154_ATTR_LBT_MODE] = { .type = NLA_U8, },
+};
+
+/* message building helper */
+static inline void *nl802154hdr_put(struct sk_buff *skb, u32 portid, u32 seq,
+				    int flags, u8 cmd)
+{
+	/* since there is no private header just add the generic one */
+	return genlmsg_put(skb, portid, seq, &nl802154_fam, flags, cmd);
+}
+
+static int
+nl802154_send_wpan_phy_channels(struct cfg802154_registered_device *rdev,
+				struct sk_buff *msg)
+{
+	struct nlattr *nl_page;
+	unsigned long page;
+
+	nl_page = nla_nest_start(msg, NL802154_ATTR_CHANNELS_SUPPORTED);
+	if (!nl_page)
+		return -ENOBUFS;
+
+	for (page = 0; page <= IEEE802154_MAX_PAGE; page++) {
+		if (nla_put_u32(msg, NL802154_ATTR_SUPPORTED_CHANNEL,
+				rdev->wpan_phy.channels_supported[page]))
+			return -ENOBUFS;
+	}
+	nla_nest_end(msg, nl_page);
+
+	return 0;
+}
+
+static int nl802154_send_wpan_phy(struct cfg802154_registered_device *rdev,
+				  enum nl802154_commands cmd,
+				  struct sk_buff *msg, u32 portid, u32 seq,
+				  int flags)
+{
+	void *hdr;
+
+	hdr = nl802154hdr_put(msg, portid, seq, flags, cmd);
+	if (!hdr)
+		return -ENOBUFS;
+
+	if (nla_put_u32(msg, NL802154_ATTR_WPAN_PHY, rdev->wpan_phy_idx) ||
+	    nla_put_string(msg, NL802154_ATTR_WPAN_PHY_NAME,
+			   wpan_phy_name(&rdev->wpan_phy)) ||
+	    nla_put_u32(msg, NL802154_ATTR_GENERATION,
+			cfg802154_rdev_list_generation))
+		goto nla_put_failure;
+
+	if (cmd != NL802154_CMD_NEW_WPAN_PHY)
+		goto finish;
+
+	/* DUMP PHY PIB */
+
+	/* current channel settings */
+	if (nla_put_u8(msg, NL802154_ATTR_PAGE,
+		       rdev->wpan_phy.current_page) ||
+	    nla_put_u8(msg, NL802154_ATTR_CHANNEL,
+		       rdev->wpan_phy.current_channel))
+		goto nla_put_failure;
+
+	/* supported channels array */
+	if (nl802154_send_wpan_phy_channels(rdev, msg))
+		goto nla_put_failure;
+
+	/* cca mode */
+	if (nla_put_u32(msg, NL802154_ATTR_CCA_MODE,
+			rdev->wpan_phy.cca.mode))
+		goto nla_put_failure;
+
+	if (rdev->wpan_phy.cca.mode == NL802154_CCA_ENERGY_CARRIER) {
+		if (nla_put_u32(msg, NL802154_ATTR_CCA_OPT,
+				rdev->wpan_phy.cca.opt))
+			goto nla_put_failure;
+	}
+
+	if (nla_put_s8(msg, NL802154_ATTR_TX_POWER,
+		       rdev->wpan_phy.transmit_power))
+		goto nla_put_failure;
+
+finish:
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	return -EMSGSIZE;
+}
+
+struct nl802154_dump_wpan_phy_state {
+	s64 filter_wpan_phy;
+	long start;
+
+};
+
+static int nl802154_dump_wpan_phy_parse(struct sk_buff *skb,
+					struct netlink_callback *cb,
+					struct nl802154_dump_wpan_phy_state *state)
+{
+	struct nlattr **tb = nl802154_fam.attrbuf;
+	int ret = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl802154_fam.hdrsize,
+			      tb, nl802154_fam.maxattr, nl802154_policy);
+
+	/* TODO check if we can handle error here,
+	 * we have no backward compatibility
+	 */
+	if (ret)
+		return 0;
+
+	if (tb[NL802154_ATTR_WPAN_PHY])
+		state->filter_wpan_phy = nla_get_u32(tb[NL802154_ATTR_WPAN_PHY]);
+	if (tb[NL802154_ATTR_WPAN_DEV])
+		state->filter_wpan_phy = nla_get_u64(tb[NL802154_ATTR_WPAN_DEV]) >> 32;
+	if (tb[NL802154_ATTR_IFINDEX]) {
+		struct net_device *netdev;
+		struct cfg802154_registered_device *rdev;
+		int ifidx = nla_get_u32(tb[NL802154_ATTR_IFINDEX]);
+
+		/* TODO netns */
+		netdev = __dev_get_by_index(&init_net, ifidx);
+		if (!netdev)
+			return -ENODEV;
+		if (netdev->ieee802154_ptr) {
+			rdev = wpan_phy_to_rdev(
+					netdev->ieee802154_ptr->wpan_phy);
+			state->filter_wpan_phy = rdev->wpan_phy_idx;
+		}
+	}
+
+	return 0;
+}
+
+static int
+nl802154_dump_wpan_phy(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	int idx = 0, ret;
+	struct nl802154_dump_wpan_phy_state *state = (void *)cb->args[0];
+	struct cfg802154_registered_device *rdev;
+
+	rtnl_lock();
+	if (!state) {
+		state = kzalloc(sizeof(*state), GFP_KERNEL);
+		if (!state) {
+			rtnl_unlock();
+			return -ENOMEM;
+		}
+		state->filter_wpan_phy = -1;
+		ret = nl802154_dump_wpan_phy_parse(skb, cb, state);
+		if (ret) {
+			kfree(state);
+			rtnl_unlock();
+			return ret;
+		}
+		cb->args[0] = (long)state;
+	}
+
+	list_for_each_entry(rdev, &cfg802154_rdev_list, list) {
+		/* TODO net ns compare */
+		if (++idx <= state->start)
+			continue;
+		if (state->filter_wpan_phy != -1 &&
+		    state->filter_wpan_phy != rdev->wpan_phy_idx)
+			continue;
+		/* attempt to fit multiple wpan_phy data chunks into the skb */
+		ret = nl802154_send_wpan_phy(rdev,
+					     NL802154_CMD_NEW_WPAN_PHY,
+					     skb,
+					     NETLINK_CB(cb->skb).portid,
+					     cb->nlh->nlmsg_seq, NLM_F_MULTI);
+		if (ret < 0) {
+			if ((ret == -ENOBUFS || ret == -EMSGSIZE) &&
+			    !skb->len && cb->min_dump_alloc < 4096) {
+				cb->min_dump_alloc = 4096;
+				rtnl_unlock();
+				return 1;
+			}
+			idx--;
+			break;
+		}
+		break;
+	}
+	rtnl_unlock();
+
+	state->start = idx;
+
+	return skb->len;
+}
+
+static int nl802154_dump_wpan_phy_done(struct netlink_callback *cb)
+{
+	kfree((void *)cb->args[0]);
+	return 0;
+}
+
+static int nl802154_get_wpan_phy(struct sk_buff *skb, struct genl_info *info)
+{
+	struct sk_buff *msg;
+	struct cfg802154_registered_device *rdev = info->user_ptr[0];
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	if (nl802154_send_wpan_phy(rdev, NL802154_CMD_NEW_WPAN_PHY, msg,
+				   info->snd_portid, info->snd_seq, 0) < 0) {
+		nlmsg_free(msg);
+		return -ENOBUFS;
+	}
+
+	return genlmsg_reply(msg, info);
+}
+
+static inline u64 wpan_dev_id(struct wpan_dev *wpan_dev)
+{
+	return (u64)wpan_dev->identifier |
+	       ((u64)wpan_phy_to_rdev(wpan_dev->wpan_phy)->wpan_phy_idx << 32);
+}
+
+static int
+nl802154_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flags,
+		    struct cfg802154_registered_device *rdev,
+		    struct wpan_dev *wpan_dev)
+{
+	struct net_device *dev = wpan_dev->netdev;
+	void *hdr;
+
+	hdr = nl802154hdr_put(msg, portid, seq, flags,
+			      NL802154_CMD_NEW_INTERFACE);
+	if (!hdr)
+		return -1;
+
+	if (dev &&
+	    (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex) ||
+	     nla_put_string(msg, NL802154_ATTR_IFNAME, dev->name)))
+		goto nla_put_failure;
+
+	if (nla_put_u32(msg, NL802154_ATTR_WPAN_PHY, rdev->wpan_phy_idx) ||
+	    nla_put_u32(msg, NL802154_ATTR_IFTYPE, wpan_dev->iftype) ||
+	    nla_put_u64(msg, NL802154_ATTR_WPAN_DEV, wpan_dev_id(wpan_dev)) ||
+	    nla_put_u32(msg, NL802154_ATTR_GENERATION,
+			rdev->devlist_generation ^
+			(cfg802154_rdev_list_generation << 2)))
+		goto nla_put_failure;
+
+	/* address settings */
+	if (nla_put_le64(msg, NL802154_ATTR_EXTENDED_ADDR,
+			 wpan_dev->extended_addr) ||
+	    nla_put_le16(msg, NL802154_ATTR_SHORT_ADDR,
+			 wpan_dev->short_addr) ||
+	    nla_put_le16(msg, NL802154_ATTR_PAN_ID, wpan_dev->pan_id))
+		goto nla_put_failure;
+
+	/* ARET handling */
+	if (nla_put_s8(msg, NL802154_ATTR_MAX_FRAME_RETRIES,
+		       wpan_dev->frame_retries) ||
+	    nla_put_u8(msg, NL802154_ATTR_MAX_BE, wpan_dev->max_be) ||
+	    nla_put_u8(msg, NL802154_ATTR_MAX_CSMA_BACKOFFS,
+		       wpan_dev->csma_retries) ||
+	    nla_put_u8(msg, NL802154_ATTR_MIN_BE, wpan_dev->min_be))
+		goto nla_put_failure;
+
+	/* listen before transmit */
+	if (nla_put_u8(msg, NL802154_ATTR_LBT_MODE, wpan_dev->lbt))
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	return -EMSGSIZE;
+}
+
+static int
+nl802154_dump_interface(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	int wp_idx = 0;
+	int if_idx = 0;
+	int wp_start = cb->args[0];
+	int if_start = cb->args[1];
+	struct cfg802154_registered_device *rdev;
+	struct wpan_dev *wpan_dev;
+
+	rtnl_lock();
+	list_for_each_entry(rdev, &cfg802154_rdev_list, list) {
+		/* TODO netns compare */
+		if (wp_idx < wp_start) {
+			wp_idx++;
+			continue;
+		}
+		if_idx = 0;
+
+		list_for_each_entry(wpan_dev, &rdev->wpan_dev_list, list) {
+			if (if_idx < if_start) {
+				if_idx++;
+				continue;
+			}
+			if (nl802154_send_iface(skb, NETLINK_CB(cb->skb).portid,
+						cb->nlh->nlmsg_seq, NLM_F_MULTI,
+						rdev, wpan_dev) < 0) {
+				goto out;
+			}
+			if_idx++;
+		}
+
+		wp_idx++;
+	}
+out:
+	rtnl_unlock();
+
+	cb->args[0] = wp_idx;
+	cb->args[1] = if_idx;
+
+	return skb->len;
+}
+
+static int nl802154_get_interface(struct sk_buff *skb, struct genl_info *info)
+{
+	struct sk_buff *msg;
+	struct cfg802154_registered_device *rdev = info->user_ptr[0];
+	struct wpan_dev *wdev = info->user_ptr[1];
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	if (nl802154_send_iface(msg, info->snd_portid, info->snd_seq, 0,
+				rdev, wdev) < 0) {
+		nlmsg_free(msg);
+		return -ENOBUFS;
+	}
+
+	return genlmsg_reply(msg, info);
+}
+
+static int nl802154_new_interface(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg802154_registered_device *rdev = info->user_ptr[0];
+	enum nl802154_iftype type = NL802154_IFTYPE_UNSPEC;
+	__le64 extended_addr = cpu_to_le64(0x0000000000000000ULL);
+
+	/* TODO avoid failing a new interface
+	 * creation due to pending removal?
+	 */
+
+	if (!info->attrs[NL802154_ATTR_IFNAME])
+		return -EINVAL;
+
+	if (info->attrs[NL802154_ATTR_IFTYPE]) {
+		type = nla_get_u32(info->attrs[NL802154_ATTR_IFTYPE]);
+		if (type > NL802154_IFTYPE_MAX)
+			return -EINVAL;
+	}
+
+	/* TODO add nla_get_le64 to netlink */
+	if (info->attrs[NL802154_ATTR_EXTENDED_ADDR])
+		extended_addr = (__force __le64)nla_get_u64(
+				info->attrs[NL802154_ATTR_EXTENDED_ADDR]);
+
+	if (!rdev->ops->add_virtual_intf)
+		return -EOPNOTSUPP;
+
+	return rdev_add_virtual_intf(rdev,
+				     nla_data(info->attrs[NL802154_ATTR_IFNAME]),
+				     NET_NAME_USER, type, extended_addr);
+}
+
+static int nl802154_del_interface(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg802154_registered_device *rdev = info->user_ptr[0];
+	struct wpan_dev *wpan_dev = info->user_ptr[1];
+
+	if (!rdev->ops->del_virtual_intf)
+		return -EOPNOTSUPP;
+
+	/* If we remove a wpan device without a netdev then clear
+	 * user_ptr[1] so that nl802154_post_doit won't dereference it
+	 * to check if it needs to do dev_put(). Otherwise it crashes
+	 * since the wpan_dev has been freed, unlike with a netdev where
+	 * we need the dev_put() for the netdev to really be freed.
+	 */
+	if (!wpan_dev->netdev)
+		info->user_ptr[1] = NULL;
+
+	return rdev_del_virtual_intf(rdev, wpan_dev);
+}
+
+static int nl802154_set_channel(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg802154_registered_device *rdev = info->user_ptr[0];
+	u8 channel, page;
+
+	if (!info->attrs[NL802154_ATTR_PAGE] ||
+	    !info->attrs[NL802154_ATTR_CHANNEL])
+		return -EINVAL;
+
+	page = nla_get_u8(info->attrs[NL802154_ATTR_PAGE]);
+	channel = nla_get_u8(info->attrs[NL802154_ATTR_CHANNEL]);
+
+	/* check 802.15.4 constraints */
+	if (page > IEEE802154_MAX_PAGE || channel > IEEE802154_MAX_CHANNEL)
+		return -EINVAL;
+
+	return rdev_set_channel(rdev, page, channel);
+}
+
+static int nl802154_set_cca_mode(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg802154_registered_device *rdev = info->user_ptr[0];
+	struct wpan_phy_cca cca;
+
+	if (!info->attrs[NL802154_ATTR_CCA_MODE])
+		return -EINVAL;
+
+	cca.mode = nla_get_u32(info->attrs[NL802154_ATTR_CCA_MODE]);
+	/* checking 802.15.4 constraints */
+	if (cca.mode < NL802154_CCA_ENERGY || cca.mode > NL802154_CCA_ATTR_MAX)
+		return -EINVAL;
+
+	if (cca.mode == NL802154_CCA_ENERGY_CARRIER) {
+		if (!info->attrs[NL802154_ATTR_CCA_OPT])
+			return -EINVAL;
+
+		cca.opt = nla_get_u32(info->attrs[NL802154_ATTR_CCA_OPT]);
+		if (cca.opt > NL802154_CCA_OPT_ATTR_MAX)
+			return -EINVAL;
+	}
+
+	return rdev_set_cca_mode(rdev, &cca);
+}
+
+static int nl802154_set_pan_id(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg802154_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+	struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
+	__le16 pan_id;
+
+	/* conflict here while tx/rx calls */
+	if (netif_running(dev))
+		return -EBUSY;
+
+	/* don't change address fields on monitor */
+	if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR)
+		return -EINVAL;
+
+	if (!info->attrs[NL802154_ATTR_PAN_ID])
+		return -EINVAL;
+
+	pan_id = nla_get_le16(info->attrs[NL802154_ATTR_PAN_ID]);
+
+	return rdev_set_pan_id(rdev, wpan_dev, pan_id);
+}
+
+static int nl802154_set_short_addr(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg802154_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+	struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
+	__le16 short_addr;
+
+	/* conflict here while tx/rx calls */
+	if (netif_running(dev))
+		return -EBUSY;
+
+	/* don't change address fields on monitor */
+	if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR)
+		return -EINVAL;
+
+	if (!info->attrs[NL802154_ATTR_SHORT_ADDR])
+		return -EINVAL;
+
+	short_addr = nla_get_le16(info->attrs[NL802154_ATTR_SHORT_ADDR]);
+
+	return rdev_set_short_addr(rdev, wpan_dev, short_addr);
+}
+
+static int
+nl802154_set_backoff_exponent(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg802154_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+	struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
+	u8 min_be, max_be;
+
+	/* should be set on netif open inside phy settings */
+	if (netif_running(dev))
+		return -EBUSY;
+
+	if (!info->attrs[NL802154_ATTR_MIN_BE] ||
+	    !info->attrs[NL802154_ATTR_MAX_BE])
+		return -EINVAL;
+
+	min_be = nla_get_u8(info->attrs[NL802154_ATTR_MIN_BE]);
+	max_be = nla_get_u8(info->attrs[NL802154_ATTR_MAX_BE]);
+
+	/* check 802.15.4 constraints */
+	if (max_be < 3 || max_be > 8 || min_be > max_be)
+		return -EINVAL;
+
+	return rdev_set_backoff_exponent(rdev, wpan_dev, min_be, max_be);
+}
+
+static int
+nl802154_set_max_csma_backoffs(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg802154_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+	struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
+	u8 max_csma_backoffs;
+
+	/* conflict here while other running iface settings */
+	if (netif_running(dev))
+		return -EBUSY;
+
+	if (!info->attrs[NL802154_ATTR_MAX_CSMA_BACKOFFS])
+		return -EINVAL;
+
+	max_csma_backoffs = nla_get_u8(
+			info->attrs[NL802154_ATTR_MAX_CSMA_BACKOFFS]);
+
+	/* check 802.15.4 constraints */
+	if (max_csma_backoffs > 5)
+		return -EINVAL;
+
+	return rdev_set_max_csma_backoffs(rdev, wpan_dev, max_csma_backoffs);
+}
+
+static int
+nl802154_set_max_frame_retries(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg802154_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+	struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
+	s8 max_frame_retries;
+
+	if (netif_running(dev))
+		return -EBUSY;
+
+	if (!info->attrs[NL802154_ATTR_MAX_FRAME_RETRIES])
+		return -EINVAL;
+
+	max_frame_retries = nla_get_s8(
+			info->attrs[NL802154_ATTR_MAX_FRAME_RETRIES]);
+
+	/* check 802.15.4 constraints */
+	if (max_frame_retries < -1 || max_frame_retries > 7)
+		return -EINVAL;
+
+	return rdev_set_max_frame_retries(rdev, wpan_dev, max_frame_retries);
+}
+
+static int nl802154_set_lbt_mode(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg802154_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+	struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
+	bool mode;
+
+	if (netif_running(dev))
+		return -EBUSY;
+
+	if (!info->attrs[NL802154_ATTR_LBT_MODE])
+		return -EINVAL;
+
+	mode = !!nla_get_u8(info->attrs[NL802154_ATTR_LBT_MODE]);
+	return rdev_set_lbt_mode(rdev, wpan_dev, mode);
+}
+
+#define NL802154_FLAG_NEED_WPAN_PHY	0x01
+#define NL802154_FLAG_NEED_NETDEV	0x02
+#define NL802154_FLAG_NEED_RTNL		0x04
+#define NL802154_FLAG_CHECK_NETDEV_UP	0x08
+#define NL802154_FLAG_NEED_NETDEV_UP	(NL802154_FLAG_NEED_NETDEV |\
+					 NL802154_FLAG_CHECK_NETDEV_UP)
+#define NL802154_FLAG_NEED_WPAN_DEV	0x10
+#define NL802154_FLAG_NEED_WPAN_DEV_UP	(NL802154_FLAG_NEED_WPAN_DEV |\
+					 NL802154_FLAG_CHECK_NETDEV_UP)
+
+static int nl802154_pre_doit(const struct genl_ops *ops, struct sk_buff *skb,
+			     struct genl_info *info)
+{
+	struct cfg802154_registered_device *rdev;
+	struct wpan_dev *wpan_dev;
+	struct net_device *dev;
+	bool rtnl = ops->internal_flags & NL802154_FLAG_NEED_RTNL;
+
+	if (rtnl)
+		rtnl_lock();
+
+	if (ops->internal_flags & NL802154_FLAG_NEED_WPAN_PHY) {
+		rdev = cfg802154_get_dev_from_info(genl_info_net(info), info);
+		if (IS_ERR(rdev)) {
+			if (rtnl)
+				rtnl_unlock();
+			return PTR_ERR(rdev);
+		}
+		info->user_ptr[0] = rdev;
+	} else if (ops->internal_flags & NL802154_FLAG_NEED_NETDEV ||
+		   ops->internal_flags & NL802154_FLAG_NEED_WPAN_DEV) {
+		ASSERT_RTNL();
+		wpan_dev = __cfg802154_wpan_dev_from_attrs(genl_info_net(info),
+							   info->attrs);
+		if (IS_ERR(wpan_dev)) {
+			if (rtnl)
+				rtnl_unlock();
+			return PTR_ERR(wpan_dev);
+		}
+
+		dev = wpan_dev->netdev;
+		rdev = wpan_phy_to_rdev(wpan_dev->wpan_phy);
+
+		if (ops->internal_flags & NL802154_FLAG_NEED_NETDEV) {
+			if (!dev) {
+				if (rtnl)
+					rtnl_unlock();
+				return -EINVAL;
+			}
+
+			info->user_ptr[1] = dev;
+		} else {
+			info->user_ptr[1] = wpan_dev;
+		}
+
+		if (dev) {
+			if (ops->internal_flags & NL802154_FLAG_CHECK_NETDEV_UP &&
+			    !netif_running(dev)) {
+				if (rtnl)
+					rtnl_unlock();
+				return -ENETDOWN;
+			}
+
+			dev_hold(dev);
+		}
+
+		info->user_ptr[0] = rdev;
+	}
+
+	return 0;
+}
+
+static void nl802154_post_doit(const struct genl_ops *ops, struct sk_buff *skb,
+			       struct genl_info *info)
+{
+	if (info->user_ptr[1]) {
+		if (ops->internal_flags & NL802154_FLAG_NEED_WPAN_DEV) {
+			struct wpan_dev *wpan_dev = info->user_ptr[1];
+
+			if (wpan_dev->netdev)
+				dev_put(wpan_dev->netdev);
+		} else {
+			dev_put(info->user_ptr[1]);
+		}
+	}
+
+	if (ops->internal_flags & NL802154_FLAG_NEED_RTNL)
+		rtnl_unlock();
+}
+
+static const struct genl_ops nl802154_ops[] = {
+	{
+		.cmd = NL802154_CMD_GET_WPAN_PHY,
+		.doit = nl802154_get_wpan_phy,
+		.dumpit = nl802154_dump_wpan_phy,
+		.done = nl802154_dump_wpan_phy_done,
+		.policy = nl802154_policy,
+		/* can be retrieved by unprivileged users */
+		.internal_flags = NL802154_FLAG_NEED_WPAN_PHY |
+				  NL802154_FLAG_NEED_RTNL,
+	},
+	{
+		.cmd = NL802154_CMD_GET_INTERFACE,
+		.doit = nl802154_get_interface,
+		.dumpit = nl802154_dump_interface,
+		.policy = nl802154_policy,
+		/* can be retrieved by unprivileged users */
+		.internal_flags = NL802154_FLAG_NEED_WPAN_DEV |
+				  NL802154_FLAG_NEED_RTNL,
+	},
+	{
+		.cmd = NL802154_CMD_NEW_INTERFACE,
+		.doit = nl802154_new_interface,
+		.policy = nl802154_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL802154_FLAG_NEED_WPAN_PHY |
+				  NL802154_FLAG_NEED_RTNL,
+	},
+	{
+		.cmd = NL802154_CMD_DEL_INTERFACE,
+		.doit = nl802154_del_interface,
+		.policy = nl802154_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL802154_FLAG_NEED_WPAN_DEV |
+				  NL802154_FLAG_NEED_RTNL,
+	},
+	{
+		.cmd = NL802154_CMD_SET_CHANNEL,
+		.doit = nl802154_set_channel,
+		.policy = nl802154_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL802154_FLAG_NEED_WPAN_PHY |
+				  NL802154_FLAG_NEED_RTNL,
+	},
+	{
+		.cmd = NL802154_CMD_SET_CCA_MODE,
+		.doit = nl802154_set_cca_mode,
+		.policy = nl802154_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL802154_FLAG_NEED_WPAN_PHY |
+				  NL802154_FLAG_NEED_RTNL,
+	},
+	{
+		.cmd = NL802154_CMD_SET_PAN_ID,
+		.doit = nl802154_set_pan_id,
+		.policy = nl802154_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL802154_FLAG_NEED_NETDEV |
+				  NL802154_FLAG_NEED_RTNL,
+	},
+	{
+		.cmd = NL802154_CMD_SET_SHORT_ADDR,
+		.doit = nl802154_set_short_addr,
+		.policy = nl802154_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL802154_FLAG_NEED_NETDEV |
+				  NL802154_FLAG_NEED_RTNL,
+	},
+	{
+		.cmd = NL802154_CMD_SET_BACKOFF_EXPONENT,
+		.doit = nl802154_set_backoff_exponent,
+		.policy = nl802154_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL802154_FLAG_NEED_NETDEV |
+				  NL802154_FLAG_NEED_RTNL,
+	},
+	{
+		.cmd = NL802154_CMD_SET_MAX_CSMA_BACKOFFS,
+		.doit = nl802154_set_max_csma_backoffs,
+		.policy = nl802154_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL802154_FLAG_NEED_NETDEV |
+				  NL802154_FLAG_NEED_RTNL,
+	},
+	{
+		.cmd = NL802154_CMD_SET_MAX_FRAME_RETRIES,
+		.doit = nl802154_set_max_frame_retries,
+		.policy = nl802154_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL802154_FLAG_NEED_NETDEV |
+				  NL802154_FLAG_NEED_RTNL,
+	},
+	{
+		.cmd = NL802154_CMD_SET_LBT_MODE,
+		.doit = nl802154_set_lbt_mode,
+		.policy = nl802154_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL802154_FLAG_NEED_NETDEV |
+				  NL802154_FLAG_NEED_RTNL,
+	},
+};
+
+/* initialisation/exit functions */
+int nl802154_init(void)
+{
+	return genl_register_family_with_ops_groups(&nl802154_fam, nl802154_ops,
+						    nl802154_mcgrps);
+}
+
+void nl802154_exit(void)
+{
+	genl_unregister_family(&nl802154_fam);
+}
diff --git a/net/ieee802154/nl802154.h b/net/ieee802154/nl802154.h
new file mode 100644
index 000000000000..3846a89d0958
--- /dev/null
+++ b/net/ieee802154/nl802154.h
@@ -0,0 +1,7 @@
+#ifndef __IEEE802154_NL802154_H
+#define __IEEE802154_NL802154_H
+
+int nl802154_init(void);
+void nl802154_exit(void);
+
+#endif /* __IEEE802154_NL802154_H */
diff --git a/net/ieee802154/nl_policy.c b/net/ieee802154/nl_policy.c
index 3a703ab88348..35c432668454 100644
--- a/net/ieee802154/nl_policy.c
+++ b/net/ieee802154/nl_policy.c
@@ -12,10 +12,6 @@
  * 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.
- *
  */
 
 #include <linux/kernel.h>
diff --git a/net/ieee802154/raw.c b/net/ieee802154/raw.c
deleted file mode 100644
index 9d1f64806f02..000000000000
--- a/net/ieee802154/raw.c
+++ /dev/null
@@ -1,275 +0,0 @@
-/*
- * Raw IEEE 802.15.4 sockets
- *
- * Copyright 2007, 2008 Siemens AG
- *
- * 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.
- *
- * Written by:
- * Sergey Lapin <slapin@ossfans.org>
- * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
- */
-
-#include <linux/net.h>
-#include <linux/module.h>
-#include <linux/if_arp.h>
-#include <linux/list.h>
-#include <linux/slab.h>
-#include <net/sock.h>
-#include <net/af_ieee802154.h>
-#include <net/ieee802154_netdev.h>
-
-#include "af802154.h"
-
-static HLIST_HEAD(raw_head);
-static DEFINE_RWLOCK(raw_lock);
-
-static void raw_hash(struct sock *sk)
-{
-	write_lock_bh(&raw_lock);
-	sk_add_node(sk, &raw_head);
-	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
-	write_unlock_bh(&raw_lock);
-}
-
-static void raw_unhash(struct sock *sk)
-{
-	write_lock_bh(&raw_lock);
-	if (sk_del_node_init(sk))
-		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
-	write_unlock_bh(&raw_lock);
-}
-
-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)
-{
-	struct ieee802154_addr addr;
-	struct sockaddr_ieee802154 *uaddr = (struct sockaddr_ieee802154 *)_uaddr;
-	int err = 0;
-	struct net_device *dev = NULL;
-
-	if (len < sizeof(*uaddr))
-		return -EINVAL;
-
-	uaddr = (struct sockaddr_ieee802154 *)_uaddr;
-	if (uaddr->family != AF_IEEE802154)
-		return -EINVAL;
-
-	lock_sock(sk);
-
-	ieee802154_addr_from_sa(&addr, &uaddr->addr);
-	dev = ieee802154_get_dev(sock_net(sk), &addr);
-	if (!dev) {
-		err = -ENODEV;
-		goto out;
-	}
-
-	if (dev->type != ARPHRD_IEEE802154) {
-		err = -ENODEV;
-		goto out_put;
-	}
-
-	sk->sk_bound_dev_if = dev->ifindex;
-	sk_dst_reset(sk);
-
-out_put:
-	dev_put(dev);
-out:
-	release_sock(sk);
-
-	return err;
-}
-
-static int raw_connect(struct sock *sk, struct sockaddr *uaddr,
-		       int addr_len)
-{
-	return -ENOTSUPP;
-}
-
-static int raw_disconnect(struct sock *sk, int flags)
-{
-	return 0;
-}
-
-static int raw_sendmsg(struct kiocb *iocb, struct sock *sk,
-		       struct msghdr *msg, size_t size)
-{
-	struct net_device *dev;
-	unsigned int mtu;
-	struct sk_buff *skb;
-	int hlen, tlen;
-	int err;
-
-	if (msg->msg_flags & MSG_OOB) {
-		pr_debug("msg->msg_flags = 0x%x\n", msg->msg_flags);
-		return -EOPNOTSUPP;
-	}
-
-	lock_sock(sk);
-	if (!sk->sk_bound_dev_if)
-		dev = dev_getfirstbyhwtype(sock_net(sk), ARPHRD_IEEE802154);
-	else
-		dev = dev_get_by_index(sock_net(sk), sk->sk_bound_dev_if);
-	release_sock(sk);
-
-	if (!dev) {
-		pr_debug("no dev\n");
-		err = -ENXIO;
-		goto out;
-	}
-
-	mtu = dev->mtu;
-	pr_debug("name = %s, mtu = %u\n", dev->name, mtu);
-
-	if (size > mtu) {
-		pr_debug("size = %Zu, mtu = %u\n", size, mtu);
-		err = -EINVAL;
-		goto out_dev;
-	}
-
-	hlen = LL_RESERVED_SPACE(dev);
-	tlen = dev->needed_tailroom;
-	skb = sock_alloc_send_skb(sk, hlen + tlen + size,
-				  msg->msg_flags & MSG_DONTWAIT, &err);
-	if (!skb)
-		goto out_dev;
-
-	skb_reserve(skb, hlen);
-
-	skb_reset_mac_header(skb);
-	skb_reset_network_header(skb);
-
-	err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size);
-	if (err < 0)
-		goto out_skb;
-
-	skb->dev = dev;
-	skb->sk  = sk;
-	skb->protocol = htons(ETH_P_IEEE802154);
-
-	dev_put(dev);
-
-	err = dev_queue_xmit(skb);
-	if (err > 0)
-		err = net_xmit_errno(err);
-
-	return err ?: size;
-
-out_skb:
-	kfree_skb(skb);
-out_dev:
-	dev_put(dev);
-out:
-	return err;
-}
-
-static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
-		       size_t len, int noblock, int flags, int *addr_len)
-{
-	size_t copied = 0;
-	int err = -EOPNOTSUPP;
-	struct sk_buff *skb;
-
-	skb = skb_recv_datagram(sk, flags, noblock, &err);
-	if (!skb)
-		goto out;
-
-	copied = skb->len;
-	if (len < copied) {
-		msg->msg_flags |= MSG_TRUNC;
-		copied = len;
-	}
-
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
-	if (err)
-		goto done;
-
-	sock_recv_ts_and_drops(msg, sk, skb);
-
-	if (flags & MSG_TRUNC)
-		copied = skb->len;
-done:
-	skb_free_datagram(sk, skb);
-out:
-	if (err)
-		return err;
-	return copied;
-}
-
-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;
-	}
-
-	return NET_RX_SUCCESS;
-}
-
-
-void ieee802154_raw_deliver(struct net_device *dev, struct sk_buff *skb)
-{
-	struct sock *sk;
-
-	read_lock(&raw_lock);
-	sk_for_each(sk, &raw_head) {
-		bh_lock_sock(sk);
-		if (!sk->sk_bound_dev_if ||
-		    sk->sk_bound_dev_if == dev->ifindex) {
-			struct sk_buff *clone;
-
-			clone = skb_clone(skb, GFP_ATOMIC);
-			if (clone)
-				raw_rcv_skb(sk, clone);
-		}
-		bh_unlock_sock(sk);
-	}
-	read_unlock(&raw_lock);
-}
-
-static int raw_getsockopt(struct sock *sk, int level, int optname,
-			  char __user *optval, int __user *optlen)
-{
-	return -EOPNOTSUPP;
-}
-
-static int raw_setsockopt(struct sock *sk, int level, int optname,
-			  char __user *optval, unsigned int optlen)
-{
-	return -EOPNOTSUPP;
-}
-
-struct proto ieee802154_raw_prot = {
-	.name		= "IEEE-802.15.4-RAW",
-	.owner		= THIS_MODULE,
-	.obj_size	= sizeof(struct sock),
-	.close		= raw_close,
-	.bind		= raw_bind,
-	.sendmsg	= raw_sendmsg,
-	.recvmsg	= raw_recvmsg,
-	.hash		= raw_hash,
-	.unhash		= raw_unhash,
-	.connect	= raw_connect,
-	.disconnect	= raw_disconnect,
-	.getsockopt	= raw_getsockopt,
-	.setsockopt	= raw_setsockopt,
-};
diff --git a/net/ieee802154/rdev-ops.h b/net/ieee802154/rdev-ops.h
new file mode 100644
index 000000000000..7b5a9dd94fe5
--- /dev/null
+++ b/net/ieee802154/rdev-ops.h
@@ -0,0 +1,155 @@
+#ifndef __CFG802154_RDEV_OPS
+#define __CFG802154_RDEV_OPS
+
+#include <net/cfg802154.h>
+
+#include "core.h"
+#include "trace.h"
+
+static inline struct net_device *
+rdev_add_virtual_intf_deprecated(struct cfg802154_registered_device *rdev,
+				 const char *name,
+				 unsigned char name_assign_type,
+				 int type)
+{
+	return rdev->ops->add_virtual_intf_deprecated(&rdev->wpan_phy, name,
+						      name_assign_type, type);
+}
+
+static inline void
+rdev_del_virtual_intf_deprecated(struct cfg802154_registered_device *rdev,
+				 struct net_device *dev)
+{
+	rdev->ops->del_virtual_intf_deprecated(&rdev->wpan_phy, dev);
+}
+
+static inline int
+rdev_add_virtual_intf(struct cfg802154_registered_device *rdev, char *name,
+		      unsigned char name_assign_type,
+		      enum nl802154_iftype type, __le64 extended_addr)
+{
+	int ret;
+
+	trace_802154_rdev_add_virtual_intf(&rdev->wpan_phy, name, type,
+					   extended_addr);
+	ret = rdev->ops->add_virtual_intf(&rdev->wpan_phy, name,
+					  name_assign_type, type,
+					  extended_addr);
+	trace_802154_rdev_return_int(&rdev->wpan_phy, ret);
+	return ret;
+}
+
+static inline int
+rdev_del_virtual_intf(struct cfg802154_registered_device *rdev,
+		      struct wpan_dev *wpan_dev)
+{
+	int ret;
+
+	trace_802154_rdev_del_virtual_intf(&rdev->wpan_phy, wpan_dev);
+	ret = rdev->ops->del_virtual_intf(&rdev->wpan_phy, wpan_dev);
+	trace_802154_rdev_return_int(&rdev->wpan_phy, ret);
+	return ret;
+}
+
+static inline int
+rdev_set_channel(struct cfg802154_registered_device *rdev, u8 page, u8 channel)
+{
+	int ret;
+
+	trace_802154_rdev_set_channel(&rdev->wpan_phy, page, channel);
+	ret = rdev->ops->set_channel(&rdev->wpan_phy, page, channel);
+	trace_802154_rdev_return_int(&rdev->wpan_phy, ret);
+	return ret;
+}
+
+static inline int
+rdev_set_cca_mode(struct cfg802154_registered_device *rdev,
+		  const struct wpan_phy_cca *cca)
+{
+	int ret;
+
+	trace_802154_rdev_set_cca_mode(&rdev->wpan_phy, cca);
+	ret = rdev->ops->set_cca_mode(&rdev->wpan_phy, cca);
+	trace_802154_rdev_return_int(&rdev->wpan_phy, ret);
+	return ret;
+}
+
+static inline int
+rdev_set_pan_id(struct cfg802154_registered_device *rdev,
+		struct wpan_dev *wpan_dev, __le16 pan_id)
+{
+	int ret;
+
+	trace_802154_rdev_set_pan_id(&rdev->wpan_phy, wpan_dev, pan_id);
+	ret = rdev->ops->set_pan_id(&rdev->wpan_phy, wpan_dev, pan_id);
+	trace_802154_rdev_return_int(&rdev->wpan_phy, ret);
+	return ret;
+}
+
+static inline int
+rdev_set_short_addr(struct cfg802154_registered_device *rdev,
+		    struct wpan_dev *wpan_dev, __le16 short_addr)
+{
+	int ret;
+
+	trace_802154_rdev_set_short_addr(&rdev->wpan_phy, wpan_dev, short_addr);
+	ret = rdev->ops->set_short_addr(&rdev->wpan_phy, wpan_dev, short_addr);
+	trace_802154_rdev_return_int(&rdev->wpan_phy, ret);
+	return ret;
+}
+
+static inline int
+rdev_set_backoff_exponent(struct cfg802154_registered_device *rdev,
+			  struct wpan_dev *wpan_dev, u8 min_be, u8 max_be)
+{
+	int ret;
+
+	trace_802154_rdev_set_backoff_exponent(&rdev->wpan_phy, wpan_dev,
+					       min_be, max_be);
+	ret = rdev->ops->set_backoff_exponent(&rdev->wpan_phy, wpan_dev,
+					      min_be, max_be);
+	trace_802154_rdev_return_int(&rdev->wpan_phy, ret);
+	return ret;
+}
+
+static inline int
+rdev_set_max_csma_backoffs(struct cfg802154_registered_device *rdev,
+			   struct wpan_dev *wpan_dev, u8 max_csma_backoffs)
+{
+	int ret;
+
+	trace_802154_rdev_set_csma_backoffs(&rdev->wpan_phy, wpan_dev,
+					    max_csma_backoffs);
+	ret = rdev->ops->set_max_csma_backoffs(&rdev->wpan_phy, wpan_dev,
+					       max_csma_backoffs);
+	trace_802154_rdev_return_int(&rdev->wpan_phy, ret);
+	return ret;
+}
+
+static inline int
+rdev_set_max_frame_retries(struct cfg802154_registered_device *rdev,
+			   struct wpan_dev *wpan_dev, s8 max_frame_retries)
+{
+	int ret;
+
+	trace_802154_rdev_set_max_frame_retries(&rdev->wpan_phy, wpan_dev,
+						max_frame_retries);
+	ret = rdev->ops->set_max_frame_retries(&rdev->wpan_phy, wpan_dev,
+					       max_frame_retries);
+	trace_802154_rdev_return_int(&rdev->wpan_phy, ret);
+	return ret;
+}
+
+static inline int
+rdev_set_lbt_mode(struct cfg802154_registered_device *rdev,
+		  struct wpan_dev *wpan_dev, bool mode)
+{
+	int ret;
+
+	trace_802154_rdev_set_lbt_mode(&rdev->wpan_phy, wpan_dev, mode);
+	ret = rdev->ops->set_lbt_mode(&rdev->wpan_phy, wpan_dev, mode);
+	trace_802154_rdev_return_int(&rdev->wpan_phy, ret);
+	return ret;
+}
+
+#endif /* __CFG802154_RDEV_OPS */
diff --git a/net/ieee802154/reassembly.h b/net/ieee802154/reassembly.h
deleted file mode 100644
index 74e4a7c98191..000000000000
--- a/net/ieee802154/reassembly.h
+++ /dev/null
@@ -1,41 +0,0 @@
-#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/socket.c b/net/ieee802154/socket.c
new file mode 100644
index 000000000000..b60c65f70346
--- /dev/null
+++ b/net/ieee802154/socket.c
@@ -0,0 +1,1122 @@
+/*
+ * IEEE802154.4 socket interface
+ *
+ * Copyright 2007, 2008 Siemens AG
+ *
+ * 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:
+ * Sergey Lapin <slapin@ossfans.org>
+ * Maxim Gorbachyov <maxim.gorbachev@siemens.com>
+ */
+
+#include <linux/net.h>
+#include <linux/capability.h>
+#include <linux/module.h>
+#include <linux/if_arp.h>
+#include <linux/if.h>
+#include <linux/termios.h>	/* For TIOCOUTQ/INQ */
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <net/datalink.h>
+#include <net/psnap.h>
+#include <net/sock.h>
+#include <net/tcp_states.h>
+#include <net/route.h>
+
+#include <net/af_ieee802154.h>
+#include <net/ieee802154_netdev.h>
+
+/* Utility function for families */
+static struct net_device*
+ieee802154_get_dev(struct net *net, const struct ieee802154_addr *addr)
+{
+	struct net_device *dev = NULL;
+	struct net_device *tmp;
+	__le16 pan_id, short_addr;
+	u8 hwaddr[IEEE802154_ADDR_LEN];
+
+	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, hwaddr);
+		if (dev)
+			dev_hold(dev);
+		rcu_read_unlock();
+		break;
+	case IEEE802154_ADDR_SHORT:
+		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();
+
+		for_each_netdev(net, tmp) {
+			if (tmp->type != ARPHRD_IEEE802154)
+				continue;
+
+			pan_id = ieee802154_mlme_ops(tmp)->get_pan_id(tmp);
+			short_addr =
+				ieee802154_mlme_ops(tmp)->get_short_addr(tmp);
+
+			if (pan_id == addr->pan_id &&
+			    short_addr == addr->short_addr) {
+				dev = tmp;
+				dev_hold(dev);
+				break;
+			}
+		}
+
+		rtnl_unlock();
+		break;
+	default:
+		pr_warn("Unsupported ieee802154 address type: %d\n",
+			addr->mode);
+		break;
+	}
+
+	return dev;
+}
+
+static int ieee802154_sock_release(struct socket *sock)
+{
+	struct sock *sk = sock->sk;
+
+	if (sk) {
+		sock->sk = NULL;
+		sk->sk_prot->close(sk, 0);
+	}
+	return 0;
+}
+
+static int ieee802154_sock_sendmsg(struct socket *sock, struct msghdr *msg,
+				   size_t len)
+{
+	struct sock *sk = sock->sk;
+
+	return sk->sk_prot->sendmsg(sk, msg, len);
+}
+
+static int ieee802154_sock_bind(struct socket *sock, struct sockaddr *uaddr,
+				int addr_len)
+{
+	struct sock *sk = sock->sk;
+
+	if (sk->sk_prot->bind)
+		return sk->sk_prot->bind(sk, uaddr, addr_len);
+
+	return sock_no_bind(sock, uaddr, addr_len);
+}
+
+static int ieee802154_sock_connect(struct socket *sock, struct sockaddr *uaddr,
+				   int addr_len, int flags)
+{
+	struct sock *sk = sock->sk;
+
+	if (addr_len < sizeof(uaddr->sa_family))
+		return -EINVAL;
+
+	if (uaddr->sa_family == AF_UNSPEC)
+		return sk->sk_prot->disconnect(sk, flags);
+
+	return sk->sk_prot->connect(sk, uaddr, addr_len);
+}
+
+static int ieee802154_dev_ioctl(struct sock *sk, struct ifreq __user *arg,
+				unsigned int cmd)
+{
+	struct ifreq ifr;
+	int ret = -ENOIOCTLCMD;
+	struct net_device *dev;
+
+	if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
+		return -EFAULT;
+
+	ifr.ifr_name[IFNAMSIZ-1] = 0;
+
+	dev_load(sock_net(sk), ifr.ifr_name);
+	dev = dev_get_by_name(sock_net(sk), ifr.ifr_name);
+
+	if (!dev)
+		return -ENODEV;
+
+	if (dev->type == ARPHRD_IEEE802154 && dev->netdev_ops->ndo_do_ioctl)
+		ret = dev->netdev_ops->ndo_do_ioctl(dev, &ifr, cmd);
+
+	if (!ret && copy_to_user(arg, &ifr, sizeof(struct ifreq)))
+		ret = -EFAULT;
+	dev_put(dev);
+
+	return ret;
+}
+
+static int ieee802154_sock_ioctl(struct socket *sock, unsigned int cmd,
+				 unsigned long arg)
+{
+	struct sock *sk = sock->sk;
+
+	switch (cmd) {
+	case SIOCGSTAMP:
+		return sock_get_timestamp(sk, (struct timeval __user *)arg);
+	case SIOCGSTAMPNS:
+		return sock_get_timestampns(sk, (struct timespec __user *)arg);
+	case SIOCGIFADDR:
+	case SIOCSIFADDR:
+		return ieee802154_dev_ioctl(sk, (struct ifreq __user *)arg,
+				cmd);
+	default:
+		if (!sk->sk_prot->ioctl)
+			return -ENOIOCTLCMD;
+		return sk->sk_prot->ioctl(sk, cmd, arg);
+	}
+}
+
+/* RAW Sockets (802.15.4 created in userspace) */
+static HLIST_HEAD(raw_head);
+static DEFINE_RWLOCK(raw_lock);
+
+static void raw_hash(struct sock *sk)
+{
+	write_lock_bh(&raw_lock);
+	sk_add_node(sk, &raw_head);
+	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
+	write_unlock_bh(&raw_lock);
+}
+
+static void raw_unhash(struct sock *sk)
+{
+	write_lock_bh(&raw_lock);
+	if (sk_del_node_init(sk))
+		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
+	write_unlock_bh(&raw_lock);
+}
+
+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)
+{
+	struct ieee802154_addr addr;
+	struct sockaddr_ieee802154 *uaddr = (struct sockaddr_ieee802154 *)_uaddr;
+	int err = 0;
+	struct net_device *dev = NULL;
+
+	if (len < sizeof(*uaddr))
+		return -EINVAL;
+
+	uaddr = (struct sockaddr_ieee802154 *)_uaddr;
+	if (uaddr->family != AF_IEEE802154)
+		return -EINVAL;
+
+	lock_sock(sk);
+
+	ieee802154_addr_from_sa(&addr, &uaddr->addr);
+	dev = ieee802154_get_dev(sock_net(sk), &addr);
+	if (!dev) {
+		err = -ENODEV;
+		goto out;
+	}
+
+	if (dev->type != ARPHRD_IEEE802154) {
+		err = -ENODEV;
+		goto out_put;
+	}
+
+	sk->sk_bound_dev_if = dev->ifindex;
+	sk_dst_reset(sk);
+
+out_put:
+	dev_put(dev);
+out:
+	release_sock(sk);
+
+	return err;
+}
+
+static int raw_connect(struct sock *sk, struct sockaddr *uaddr,
+		       int addr_len)
+{
+	return -ENOTSUPP;
+}
+
+static int raw_disconnect(struct sock *sk, int flags)
+{
+	return 0;
+}
+
+static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
+{
+	struct net_device *dev;
+	unsigned int mtu;
+	struct sk_buff *skb;
+	int hlen, tlen;
+	int err;
+
+	if (msg->msg_flags & MSG_OOB) {
+		pr_debug("msg->msg_flags = 0x%x\n", msg->msg_flags);
+		return -EOPNOTSUPP;
+	}
+
+	lock_sock(sk);
+	if (!sk->sk_bound_dev_if)
+		dev = dev_getfirstbyhwtype(sock_net(sk), ARPHRD_IEEE802154);
+	else
+		dev = dev_get_by_index(sock_net(sk), sk->sk_bound_dev_if);
+	release_sock(sk);
+
+	if (!dev) {
+		pr_debug("no dev\n");
+		err = -ENXIO;
+		goto out;
+	}
+
+	mtu = dev->mtu;
+	pr_debug("name = %s, mtu = %u\n", dev->name, mtu);
+
+	if (size > mtu) {
+		pr_debug("size = %Zu, mtu = %u\n", size, mtu);
+		err = -EINVAL;
+		goto out_dev;
+	}
+
+	hlen = LL_RESERVED_SPACE(dev);
+	tlen = dev->needed_tailroom;
+	skb = sock_alloc_send_skb(sk, hlen + tlen + size,
+				  msg->msg_flags & MSG_DONTWAIT, &err);
+	if (!skb)
+		goto out_dev;
+
+	skb_reserve(skb, hlen);
+
+	skb_reset_mac_header(skb);
+	skb_reset_network_header(skb);
+
+	err = memcpy_from_msg(skb_put(skb, size), msg, size);
+	if (err < 0)
+		goto out_skb;
+
+	skb->dev = dev;
+	skb->sk  = sk;
+	skb->protocol = htons(ETH_P_IEEE802154);
+
+	dev_put(dev);
+
+	err = dev_queue_xmit(skb);
+	if (err > 0)
+		err = net_xmit_errno(err);
+
+	return err ?: size;
+
+out_skb:
+	kfree_skb(skb);
+out_dev:
+	dev_put(dev);
+out:
+	return err;
+}
+
+static int raw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+		       int noblock, int flags, int *addr_len)
+{
+	size_t copied = 0;
+	int err = -EOPNOTSUPP;
+	struct sk_buff *skb;
+
+	skb = skb_recv_datagram(sk, flags, noblock, &err);
+	if (!skb)
+		goto out;
+
+	copied = skb->len;
+	if (len < copied) {
+		msg->msg_flags |= MSG_TRUNC;
+		copied = len;
+	}
+
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
+	if (err)
+		goto done;
+
+	sock_recv_ts_and_drops(msg, sk, skb);
+
+	if (flags & MSG_TRUNC)
+		copied = skb->len;
+done:
+	skb_free_datagram(sk, skb);
+out:
+	if (err)
+		return err;
+	return copied;
+}
+
+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;
+	}
+
+	return NET_RX_SUCCESS;
+}
+
+static void ieee802154_raw_deliver(struct net_device *dev, struct sk_buff *skb)
+{
+	struct sock *sk;
+
+	read_lock(&raw_lock);
+	sk_for_each(sk, &raw_head) {
+		bh_lock_sock(sk);
+		if (!sk->sk_bound_dev_if ||
+		    sk->sk_bound_dev_if == dev->ifindex) {
+			struct sk_buff *clone;
+
+			clone = skb_clone(skb, GFP_ATOMIC);
+			if (clone)
+				raw_rcv_skb(sk, clone);
+		}
+		bh_unlock_sock(sk);
+	}
+	read_unlock(&raw_lock);
+}
+
+static int raw_getsockopt(struct sock *sk, int level, int optname,
+			  char __user *optval, int __user *optlen)
+{
+	return -EOPNOTSUPP;
+}
+
+static int raw_setsockopt(struct sock *sk, int level, int optname,
+			  char __user *optval, unsigned int optlen)
+{
+	return -EOPNOTSUPP;
+}
+
+static struct proto ieee802154_raw_prot = {
+	.name		= "IEEE-802.15.4-RAW",
+	.owner		= THIS_MODULE,
+	.obj_size	= sizeof(struct sock),
+	.close		= raw_close,
+	.bind		= raw_bind,
+	.sendmsg	= raw_sendmsg,
+	.recvmsg	= raw_recvmsg,
+	.hash		= raw_hash,
+	.unhash		= raw_unhash,
+	.connect	= raw_connect,
+	.disconnect	= raw_disconnect,
+	.getsockopt	= raw_getsockopt,
+	.setsockopt	= raw_setsockopt,
+};
+
+static const struct proto_ops ieee802154_raw_ops = {
+	.family		   = PF_IEEE802154,
+	.owner		   = THIS_MODULE,
+	.release	   = ieee802154_sock_release,
+	.bind		   = ieee802154_sock_bind,
+	.connect	   = ieee802154_sock_connect,
+	.socketpair	   = sock_no_socketpair,
+	.accept		   = sock_no_accept,
+	.getname	   = sock_no_getname,
+	.poll		   = datagram_poll,
+	.ioctl		   = ieee802154_sock_ioctl,
+	.listen		   = sock_no_listen,
+	.shutdown	   = sock_no_shutdown,
+	.setsockopt	   = sock_common_setsockopt,
+	.getsockopt	   = sock_common_getsockopt,
+	.sendmsg	   = ieee802154_sock_sendmsg,
+	.recvmsg	   = sock_common_recvmsg,
+	.mmap		   = sock_no_mmap,
+	.sendpage	   = sock_no_sendpage,
+#ifdef CONFIG_COMPAT
+	.compat_setsockopt = compat_sock_common_setsockopt,
+	.compat_getsockopt = compat_sock_common_getsockopt,
+#endif
+};
+
+/* DGRAM Sockets (802.15.4 dataframes) */
+static HLIST_HEAD(dgram_head);
+static DEFINE_RWLOCK(dgram_lock);
+
+struct dgram_sock {
+	struct sock sk;
+
+	struct ieee802154_addr src_addr;
+	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)
+{
+	return container_of(sk, struct dgram_sock, sk);
+}
+
+static void dgram_hash(struct sock *sk)
+{
+	write_lock_bh(&dgram_lock);
+	sk_add_node(sk, &dgram_head);
+	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
+	write_unlock_bh(&dgram_lock);
+}
+
+static void dgram_unhash(struct sock *sk)
+{
+	write_lock_bh(&dgram_lock);
+	if (sk_del_node_init(sk))
+		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
+	write_unlock_bh(&dgram_lock);
+}
+
+static int dgram_init(struct sock *sk)
+{
+	struct dgram_sock *ro = dgram_sk(sk);
+
+	ro->want_ack = 1;
+	return 0;
+}
+
+static void dgram_close(struct sock *sk, long timeout)
+{
+	sk_common_release(sk);
+}
+
+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;
+
+	lock_sock(sk);
+
+	ro->bound = 0;
+
+	if (len < sizeof(*addr))
+		goto out;
+
+	if (addr->family != AF_IEEE802154)
+		goto out;
+
+	ieee802154_addr_from_sa(&haddr, &addr->addr);
+	dev = ieee802154_get_dev(sock_net(sk), &haddr);
+	if (!dev) {
+		err = -ENODEV;
+		goto out;
+	}
+
+	if (dev->type != ARPHRD_IEEE802154) {
+		err = -ENODEV;
+		goto out_put;
+	}
+
+	ro->src_addr = haddr;
+
+	ro->bound = 1;
+	err = 0;
+out_put:
+	dev_put(dev);
+out:
+	release_sock(sk);
+
+	return err;
+}
+
+static int dgram_ioctl(struct sock *sk, int cmd, unsigned long arg)
+{
+	switch (cmd) {
+	case SIOCOUTQ:
+	{
+		int amount = sk_wmem_alloc_get(sk);
+
+		return put_user(amount, (int __user *)arg);
+	}
+
+	case SIOCINQ:
+	{
+		struct sk_buff *skb;
+		unsigned long amount;
+
+		amount = 0;
+		spin_lock_bh(&sk->sk_receive_queue.lock);
+		skb = skb_peek(&sk->sk_receive_queue);
+		if (skb) {
+			/* We will only return the amount
+			 * of this packet since that is all
+			 * that will be read.
+			 */
+			amount = skb->len - ieee802154_hdr_length(skb);
+		}
+		spin_unlock_bh(&sk->sk_receive_queue.lock);
+		return put_user(amount, (int __user *)arg);
+	}
+	}
+
+	return -ENOIOCTLCMD;
+}
+
+/* FIXME: autobind */
+static int dgram_connect(struct sock *sk, struct sockaddr *uaddr,
+			 int len)
+{
+	struct sockaddr_ieee802154 *addr = (struct sockaddr_ieee802154 *)uaddr;
+	struct dgram_sock *ro = dgram_sk(sk);
+	int err = 0;
+
+	if (len < sizeof(*addr))
+		return -EINVAL;
+
+	if (addr->family != AF_IEEE802154)
+		return -EINVAL;
+
+	lock_sock(sk);
+
+	if (!ro->bound) {
+		err = -ENETUNREACH;
+		goto out;
+	}
+
+	ieee802154_addr_from_sa(&ro->dst_addr, &addr->addr);
+	ro->connected = 1;
+
+out:
+	release_sock(sk);
+	return err;
+}
+
+static int dgram_disconnect(struct sock *sk, int flags)
+{
+	struct dgram_sock *ro = dgram_sk(sk);
+
+	lock_sock(sk);
+	ro->connected = 0;
+	release_sock(sk);
+
+	return 0;
+}
+
+static int dgram_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
+{
+	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;
+
+	if (msg->msg_flags & MSG_OOB) {
+		pr_debug("msg->msg_flags = 0x%x\n", msg->msg_flags);
+		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
+		dev = ieee802154_get_dev(sock_net(sk), &ro->src_addr);
+
+	if (!dev) {
+		pr_debug("no dev\n");
+		err = -ENXIO;
+		goto out;
+	}
+	mtu = dev->mtu;
+	pr_debug("name = %s, mtu = %u\n", dev->name, mtu);
+
+	if (size > mtu) {
+		pr_debug("size = %Zu, mtu = %u\n", size, mtu);
+		err = -EMSGSIZE;
+		goto out_dev;
+	}
+
+	hlen = LL_RESERVED_SPACE(dev);
+	tlen = dev->needed_tailroom;
+	skb = sock_alloc_send_skb(sk, hlen + tlen + size,
+				  msg->msg_flags & MSG_DONTWAIT,
+				  &err);
+	if (!skb)
+		goto out_dev;
+
+	skb_reserve(skb, hlen);
+
+	skb_reset_network_header(skb);
+
+	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;
+
+	err = dev_hard_header(skb, dev, ETH_P_IEEE802154, &dst_addr,
+			      ro->bound ? &ro->src_addr : NULL, size);
+	if (err < 0)
+		goto out_skb;
+
+	err = memcpy_from_msg(skb_put(skb, size), msg, size);
+	if (err < 0)
+		goto out_skb;
+
+	skb->dev = dev;
+	skb->sk  = sk;
+	skb->protocol = htons(ETH_P_IEEE802154);
+
+	dev_put(dev);
+
+	err = dev_queue_xmit(skb);
+	if (err > 0)
+		err = net_xmit_errno(err);
+
+	return err ?: size;
+
+out_skb:
+	kfree_skb(skb);
+out_dev:
+	dev_put(dev);
+out:
+	return err;
+}
+
+static int dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+			 int noblock, int flags, int *addr_len)
+{
+	size_t copied = 0;
+	int err = -EOPNOTSUPP;
+	struct sk_buff *skb;
+	DECLARE_SOCKADDR(struct sockaddr_ieee802154 *, saddr, msg->msg_name);
+
+	skb = skb_recv_datagram(sk, flags, noblock, &err);
+	if (!skb)
+		goto out;
+
+	copied = skb->len;
+	if (len < copied) {
+		msg->msg_flags |= MSG_TRUNC;
+		copied = len;
+	}
+
+	/* FIXME: skip headers if necessary ?! */
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
+	if (err)
+		goto done;
+
+	sock_recv_ts_and_drops(msg, sk, skb);
+
+	if (saddr) {
+		saddr->family = AF_IEEE802154;
+		ieee802154_addr_to_sa(&saddr->addr, &mac_cb(skb)->source);
+		*addr_len = sizeof(*saddr);
+	}
+
+	if (flags & MSG_TRUNC)
+		copied = skb->len;
+done:
+	skb_free_datagram(sk, skb);
+out:
+	if (err)
+		return err;
+	return copied;
+}
+
+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;
+	}
+
+	return NET_RX_SUCCESS;
+}
+
+static inline bool
+ieee802154_match_sock(__le64 hw_addr, __le16 pan_id, __le16 short_addr,
+		      struct dgram_sock *ro)
+{
+	if (!ro->bound)
+		return true;
+
+	if (ro->src_addr.mode == IEEE802154_ADDR_LONG &&
+	    hw_addr == ro->src_addr.extended_addr)
+		return true;
+
+	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 false;
+}
+
+static int ieee802154_dgram_deliver(struct net_device *dev, struct sk_buff *skb)
+{
+	struct sock *sk, *prev = NULL;
+	int ret = NET_RX_SUCCESS;
+	__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(hw_addr, pan_id, short_addr,
+					  dgram_sk(sk))) {
+			if (prev) {
+				struct sk_buff *clone;
+
+				clone = skb_clone(skb, GFP_ATOMIC);
+				if (clone)
+					dgram_rcv_skb(prev, clone);
+			}
+
+			prev = sk;
+		}
+	}
+
+	if (prev) {
+		dgram_rcv_skb(prev, skb);
+	} else {
+		kfree_skb(skb);
+		ret = NET_RX_DROP;
+	}
+	read_unlock(&dgram_lock);
+
+	return ret;
+}
+
+static int dgram_getsockopt(struct sock *sk, int level, int optname,
+			    char __user *optval, int __user *optlen)
+{
+	struct dgram_sock *ro = dgram_sk(sk);
+
+	int val, len;
+
+	if (level != SOL_IEEE802154)
+		return -EOPNOTSUPP;
+
+	if (get_user(len, optlen))
+		return -EFAULT;
+
+	len = min_t(unsigned int, len, sizeof(int));
+
+	switch (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;
+	}
+
+	if (put_user(len, optlen))
+		return -EFAULT;
+	if (copy_to_user(optval, &val, len))
+		return -EFAULT;
+	return 0;
+}
+
+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;
+
+	if (optlen < sizeof(int))
+		return -EINVAL;
+
+	if (get_user(val, (int __user *)optval))
+		return -EFAULT;
+
+	lock_sock(sk);
+
+	switch (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;
+	}
+
+	release_sock(sk);
+	return err;
+}
+
+static struct proto ieee802154_dgram_prot = {
+	.name		= "IEEE-802.15.4-MAC",
+	.owner		= THIS_MODULE,
+	.obj_size	= sizeof(struct dgram_sock),
+	.init		= dgram_init,
+	.close		= dgram_close,
+	.bind		= dgram_bind,
+	.sendmsg	= dgram_sendmsg,
+	.recvmsg	= dgram_recvmsg,
+	.hash		= dgram_hash,
+	.unhash		= dgram_unhash,
+	.connect	= dgram_connect,
+	.disconnect	= dgram_disconnect,
+	.ioctl		= dgram_ioctl,
+	.getsockopt	= dgram_getsockopt,
+	.setsockopt	= dgram_setsockopt,
+};
+
+static const struct proto_ops ieee802154_dgram_ops = {
+	.family		   = PF_IEEE802154,
+	.owner		   = THIS_MODULE,
+	.release	   = ieee802154_sock_release,
+	.bind		   = ieee802154_sock_bind,
+	.connect	   = ieee802154_sock_connect,
+	.socketpair	   = sock_no_socketpair,
+	.accept		   = sock_no_accept,
+	.getname	   = sock_no_getname,
+	.poll		   = datagram_poll,
+	.ioctl		   = ieee802154_sock_ioctl,
+	.listen		   = sock_no_listen,
+	.shutdown	   = sock_no_shutdown,
+	.setsockopt	   = sock_common_setsockopt,
+	.getsockopt	   = sock_common_getsockopt,
+	.sendmsg	   = ieee802154_sock_sendmsg,
+	.recvmsg	   = sock_common_recvmsg,
+	.mmap		   = sock_no_mmap,
+	.sendpage	   = sock_no_sendpage,
+#ifdef CONFIG_COMPAT
+	.compat_setsockopt = compat_sock_common_setsockopt,
+	.compat_getsockopt = compat_sock_common_getsockopt,
+#endif
+};
+
+/* Create a socket. Initialise the socket, blank the addresses
+ * set the state.
+ */
+static int ieee802154_create(struct net *net, struct socket *sock,
+			     int protocol, int kern)
+{
+	struct sock *sk;
+	int rc;
+	struct proto *proto;
+	const struct proto_ops *ops;
+
+	if (!net_eq(net, &init_net))
+		return -EAFNOSUPPORT;
+
+	switch (sock->type) {
+	case SOCK_RAW:
+		proto = &ieee802154_raw_prot;
+		ops = &ieee802154_raw_ops;
+		break;
+	case SOCK_DGRAM:
+		proto = &ieee802154_dgram_prot;
+		ops = &ieee802154_dgram_ops;
+		break;
+	default:
+		rc = -ESOCKTNOSUPPORT;
+		goto out;
+	}
+
+	rc = -ENOMEM;
+	sk = sk_alloc(net, PF_IEEE802154, GFP_KERNEL, proto);
+	if (!sk)
+		goto out;
+	rc = 0;
+
+	sock->ops = ops;
+
+	sock_init_data(sock, sk);
+	/* FIXME: sk->sk_destruct */
+	sk->sk_family = PF_IEEE802154;
+
+	/* Checksums on by default */
+	sock_set_flag(sk, SOCK_ZAPPED);
+
+	if (sk->sk_prot->hash)
+		sk->sk_prot->hash(sk);
+
+	if (sk->sk_prot->init) {
+		rc = sk->sk_prot->init(sk);
+		if (rc)
+			sk_common_release(sk);
+	}
+out:
+	return rc;
+}
+
+static const struct net_proto_family ieee802154_family_ops = {
+	.family		= PF_IEEE802154,
+	.create		= ieee802154_create,
+	.owner		= THIS_MODULE,
+};
+
+static int ieee802154_rcv(struct sk_buff *skb, struct net_device *dev,
+			  struct packet_type *pt, struct net_device *orig_dev)
+{
+	if (!netif_running(dev))
+		goto drop;
+	pr_debug("got frame, type %d, dev %p\n", dev->type, dev);
+#ifdef DEBUG
+	print_hex_dump_bytes("ieee802154_rcv ",
+			     DUMP_PREFIX_NONE, skb->data, skb->len);
+#endif
+
+	if (!net_eq(dev_net(dev), &init_net))
+		goto drop;
+
+	ieee802154_raw_deliver(dev, skb);
+
+	if (dev->type != ARPHRD_IEEE802154)
+		goto drop;
+
+	if (skb->pkt_type != PACKET_OTHERHOST)
+		return ieee802154_dgram_deliver(dev, skb);
+
+drop:
+	kfree_skb(skb);
+	return NET_RX_DROP;
+}
+
+static struct packet_type ieee802154_packet_type = {
+	.type = htons(ETH_P_IEEE802154),
+	.func = ieee802154_rcv,
+};
+
+static int __init af_ieee802154_init(void)
+{
+	int rc = -EINVAL;
+
+	rc = proto_register(&ieee802154_raw_prot, 1);
+	if (rc)
+		goto out;
+
+	rc = proto_register(&ieee802154_dgram_prot, 1);
+	if (rc)
+		goto err_dgram;
+
+	/* Tell SOCKET that we are alive */
+	rc = sock_register(&ieee802154_family_ops);
+	if (rc)
+		goto err_sock;
+	dev_add_pack(&ieee802154_packet_type);
+
+	rc = 0;
+	goto out;
+
+err_sock:
+	proto_unregister(&ieee802154_dgram_prot);
+err_dgram:
+	proto_unregister(&ieee802154_raw_prot);
+out:
+	return rc;
+}
+
+static void __exit af_ieee802154_remove(void)
+{
+	dev_remove_pack(&ieee802154_packet_type);
+	sock_unregister(PF_IEEE802154);
+	proto_unregister(&ieee802154_dgram_prot);
+	proto_unregister(&ieee802154_raw_prot);
+}
+
+module_init(af_ieee802154_init);
+module_exit(af_ieee802154_remove);
+
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NETPROTO(PF_IEEE802154);
diff --git a/net/ieee802154/sysfs.c b/net/ieee802154/sysfs.c
new file mode 100644
index 000000000000..133b4280660c
--- /dev/null
+++ b/net/ieee802154/sysfs.c
@@ -0,0 +1,79 @@
+/* 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.
+ *
+ * Authors:
+ * Alexander Aring <aar@pengutronix.de>
+ *
+ * Based on: net/wireless/sysfs.c
+ */
+
+#include <linux/device.h>
+
+#include <net/cfg802154.h>
+
+#include "core.h"
+#include "sysfs.h"
+
+static inline struct cfg802154_registered_device *
+dev_to_rdev(struct device *dev)
+{
+	return container_of(dev, struct cfg802154_registered_device,
+			    wpan_phy.dev);
+}
+
+#define SHOW_FMT(name, fmt, member)					\
+static ssize_t name ## _show(struct device *dev,			\
+			     struct device_attribute *attr,		\
+			     char *buf)					\
+{									\
+	return sprintf(buf, fmt "\n", dev_to_rdev(dev)->member);	\
+}									\
+static DEVICE_ATTR_RO(name)
+
+SHOW_FMT(index, "%d", wpan_phy_idx);
+
+static ssize_t name_show(struct device *dev,
+			 struct device_attribute *attr,
+			 char *buf)
+{
+	struct wpan_phy *wpan_phy = &dev_to_rdev(dev)->wpan_phy;
+
+	return sprintf(buf, "%s\n", dev_name(&wpan_phy->dev));
+}
+static DEVICE_ATTR_RO(name);
+
+static void wpan_phy_release(struct device *dev)
+{
+	struct cfg802154_registered_device *rdev = dev_to_rdev(dev);
+
+	cfg802154_dev_free(rdev);
+}
+
+static struct attribute *pmib_attrs[] = {
+	&dev_attr_index.attr,
+	&dev_attr_name.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(pmib);
+
+struct class wpan_phy_class = {
+	.name = "ieee802154",
+	.dev_release = wpan_phy_release,
+	.dev_groups = pmib_groups,
+};
+
+int wpan_phy_sysfs_init(void)
+{
+	return class_register(&wpan_phy_class);
+}
+
+void wpan_phy_sysfs_exit(void)
+{
+	class_unregister(&wpan_phy_class);
+}
diff --git a/net/ieee802154/sysfs.h b/net/ieee802154/sysfs.h
new file mode 100644
index 000000000000..aa42e39ecbec
--- /dev/null
+++ b/net/ieee802154/sysfs.h
@@ -0,0 +1,9 @@
+#ifndef __IEEE802154_SYSFS_H
+#define __IEEE802154_SYSFS_H
+
+int wpan_phy_sysfs_init(void);
+void wpan_phy_sysfs_exit(void);
+
+extern struct class wpan_phy_class;
+
+#endif /* __IEEE802154_SYSFS_H */
diff --git a/net/ieee802154/trace.c b/net/ieee802154/trace.c
new file mode 100644
index 000000000000..95f997fad755
--- /dev/null
+++ b/net/ieee802154/trace.c
@@ -0,0 +1,7 @@
+#include <linux/module.h>
+
+#ifndef __CHECKER__
+#define CREATE_TRACE_POINTS
+#include "trace.h"
+
+#endif
diff --git a/net/ieee802154/trace.h b/net/ieee802154/trace.h
new file mode 100644
index 000000000000..5ac25eb6ed17
--- /dev/null
+++ b/net/ieee802154/trace.h
@@ -0,0 +1,247 @@
+/* Based on net/wireless/tracing.h */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM cfg802154
+
+#if !defined(__RDEV_CFG802154_OPS_TRACE) || defined(TRACE_HEADER_MULTI_READ)
+#define __RDEV_CFG802154_OPS_TRACE
+
+#include <linux/tracepoint.h>
+
+#include <net/cfg802154.h>
+
+#define MAXNAME		32
+#define WPAN_PHY_ENTRY	__array(char, wpan_phy_name, MAXNAME)
+#define WPAN_PHY_ASSIGN	strlcpy(__entry->wpan_phy_name,	 \
+				wpan_phy_name(wpan_phy), \
+				MAXNAME)
+#define WPAN_PHY_PR_FMT	"%s"
+#define WPAN_PHY_PR_ARG	__entry->wpan_phy_name
+
+#define WPAN_DEV_ENTRY	__field(u32, identifier)
+#define WPAN_DEV_ASSIGN	(__entry->identifier) = (!IS_ERR_OR_NULL(wpan_dev) \
+					 ? wpan_dev->identifier : 0)
+#define WPAN_DEV_PR_FMT	"wpan_dev(%u)"
+#define WPAN_DEV_PR_ARG	(__entry->identifier)
+
+#define WPAN_CCA_ENTRY	__field(enum nl802154_cca_modes, cca_mode) \
+			__field(enum nl802154_cca_opts, cca_opt)
+#define WPAN_CCA_ASSIGN \
+	do {					 \
+		(__entry->cca_mode) = cca->mode; \
+		(__entry->cca_opt) = cca->opt;	 \
+	} while (0)
+#define WPAN_CCA_PR_FMT	"cca_mode: %d, cca_opt: %d"
+#define WPAN_CCA_PR_ARG __entry->cca_mode, __entry->cca_opt
+
+#define BOOL_TO_STR(bo) (bo) ? "true" : "false"
+
+/*************************************************************
+ *			rdev->ops traces		     *
+ *************************************************************/
+
+TRACE_EVENT(802154_rdev_add_virtual_intf,
+	TP_PROTO(struct wpan_phy *wpan_phy, char *name,
+		 enum nl802154_iftype type, __le64 extended_addr),
+	TP_ARGS(wpan_phy, name, type, extended_addr),
+	TP_STRUCT__entry(
+		WPAN_PHY_ENTRY
+		__string(vir_intf_name, name ? name : "<noname>")
+		__field(enum nl802154_iftype, type)
+		__field(__le64, extended_addr)
+	),
+	TP_fast_assign(
+		WPAN_PHY_ASSIGN;
+		__assign_str(vir_intf_name, name ? name : "<noname>");
+		__entry->type = type;
+		__entry->extended_addr = extended_addr;
+	),
+	TP_printk(WPAN_PHY_PR_FMT ", virtual intf name: %s, type: %d, ea %llx",
+		  WPAN_PHY_PR_ARG, __get_str(vir_intf_name), __entry->type,
+		  __le64_to_cpu(__entry->extended_addr))
+);
+
+TRACE_EVENT(802154_rdev_del_virtual_intf,
+	TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev),
+	TP_ARGS(wpan_phy, wpan_dev),
+	TP_STRUCT__entry(
+		WPAN_PHY_ENTRY
+		WPAN_DEV_ENTRY
+	),
+	TP_fast_assign(
+		WPAN_PHY_ASSIGN;
+		WPAN_DEV_ASSIGN;
+	),
+	TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT, WPAN_PHY_PR_ARG,
+		  WPAN_DEV_PR_ARG)
+);
+
+TRACE_EVENT(802154_rdev_set_channel,
+	TP_PROTO(struct wpan_phy *wpan_phy, u8 page, u8 channel),
+	TP_ARGS(wpan_phy, page, channel),
+	TP_STRUCT__entry(
+		WPAN_PHY_ENTRY
+		__field(u8, page)
+		__field(u8, channel)
+	),
+	TP_fast_assign(
+		WPAN_PHY_ASSIGN;
+		__entry->page = page;
+		__entry->channel = channel;
+	),
+	TP_printk(WPAN_PHY_PR_FMT ", page: %d, channel: %d", WPAN_PHY_PR_ARG,
+		  __entry->page, __entry->channel)
+);
+
+TRACE_EVENT(802154_rdev_set_cca_mode,
+	TP_PROTO(struct wpan_phy *wpan_phy, const struct wpan_phy_cca *cca),
+	TP_ARGS(wpan_phy, cca),
+	TP_STRUCT__entry(
+		WPAN_PHY_ENTRY
+		WPAN_CCA_ENTRY
+	),
+	TP_fast_assign(
+		WPAN_PHY_ASSIGN;
+		WPAN_CCA_ASSIGN;
+	),
+	TP_printk(WPAN_PHY_PR_FMT ", " WPAN_CCA_PR_FMT, WPAN_PHY_PR_ARG,
+		  WPAN_CCA_PR_ARG)
+);
+
+DECLARE_EVENT_CLASS(802154_le16_template,
+	TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
+		 __le16 le16arg),
+	TP_ARGS(wpan_phy, wpan_dev, le16arg),
+	TP_STRUCT__entry(
+		WPAN_PHY_ENTRY
+		WPAN_DEV_ENTRY
+		__field(__le16, le16arg)
+	),
+	TP_fast_assign(
+		WPAN_PHY_ASSIGN;
+		WPAN_DEV_ASSIGN;
+		__entry->le16arg = le16arg;
+	),
+	TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT ", pan id: 0x%04x",
+		  WPAN_PHY_PR_ARG, WPAN_DEV_PR_ARG,
+		  __le16_to_cpu(__entry->le16arg))
+);
+
+DEFINE_EVENT(802154_le16_template, 802154_rdev_set_pan_id,
+	TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
+		 __le16 le16arg),
+	TP_ARGS(wpan_phy, wpan_dev, le16arg)
+);
+
+DEFINE_EVENT_PRINT(802154_le16_template, 802154_rdev_set_short_addr,
+	TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
+		 __le16 le16arg),
+	TP_ARGS(wpan_phy, wpan_dev, le16arg),
+	TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT ", sa: 0x%04x",
+		  WPAN_PHY_PR_ARG, WPAN_DEV_PR_ARG,
+		  __le16_to_cpu(__entry->le16arg))
+);
+
+TRACE_EVENT(802154_rdev_set_backoff_exponent,
+	TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
+		 u8 min_be, u8 max_be),
+	TP_ARGS(wpan_phy, wpan_dev, min_be, max_be),
+	TP_STRUCT__entry(
+		WPAN_PHY_ENTRY
+		WPAN_DEV_ENTRY
+		__field(u8, min_be)
+		__field(u8, max_be)
+	),
+	TP_fast_assign(
+		WPAN_PHY_ASSIGN;
+		WPAN_DEV_ASSIGN;
+		__entry->min_be = min_be;
+		__entry->max_be = max_be;
+	),
+
+	TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT
+		  ", min be: %d, max_be: %d", WPAN_PHY_PR_ARG,
+		  WPAN_DEV_PR_ARG, __entry->min_be, __entry->max_be)
+);
+
+TRACE_EVENT(802154_rdev_set_csma_backoffs,
+	TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
+		 u8 max_csma_backoffs),
+	TP_ARGS(wpan_phy, wpan_dev, max_csma_backoffs),
+	TP_STRUCT__entry(
+		WPAN_PHY_ENTRY
+		WPAN_DEV_ENTRY
+		__field(u8, max_csma_backoffs)
+	),
+	TP_fast_assign(
+		WPAN_PHY_ASSIGN;
+		WPAN_DEV_ASSIGN;
+		__entry->max_csma_backoffs = max_csma_backoffs;
+	),
+
+	TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT
+		  ", max csma backoffs: %d", WPAN_PHY_PR_ARG,
+		  WPAN_DEV_PR_ARG, __entry->max_csma_backoffs)
+);
+
+TRACE_EVENT(802154_rdev_set_max_frame_retries,
+	TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
+		 s8 max_frame_retries),
+	TP_ARGS(wpan_phy, wpan_dev, max_frame_retries),
+	TP_STRUCT__entry(
+		WPAN_PHY_ENTRY
+		WPAN_DEV_ENTRY
+		__field(s8, max_frame_retries)
+	),
+	TP_fast_assign(
+		WPAN_PHY_ASSIGN;
+		WPAN_DEV_ASSIGN;
+		__entry->max_frame_retries = max_frame_retries;
+	),
+
+	TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT
+		  ", max frame retries: %d", WPAN_PHY_PR_ARG,
+		  WPAN_DEV_PR_ARG, __entry->max_frame_retries)
+);
+
+TRACE_EVENT(802154_rdev_set_lbt_mode,
+	TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
+		 bool mode),
+	TP_ARGS(wpan_phy, wpan_dev, mode),
+	TP_STRUCT__entry(
+		WPAN_PHY_ENTRY
+		WPAN_DEV_ENTRY
+		__field(bool, mode)
+	),
+	TP_fast_assign(
+		WPAN_PHY_ASSIGN;
+		WPAN_DEV_ASSIGN;
+		__entry->mode = mode;
+	),
+	TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT
+		", lbt mode: %s", WPAN_PHY_PR_ARG,
+		WPAN_DEV_PR_ARG, BOOL_TO_STR(__entry->mode))
+);
+
+TRACE_EVENT(802154_rdev_return_int,
+	TP_PROTO(struct wpan_phy *wpan_phy, int ret),
+	TP_ARGS(wpan_phy, ret),
+	TP_STRUCT__entry(
+		WPAN_PHY_ENTRY
+		__field(int, ret)
+	),
+	TP_fast_assign(
+		WPAN_PHY_ASSIGN;
+		__entry->ret = ret;
+	),
+	TP_printk(WPAN_PHY_PR_FMT ", returned: %d", WPAN_PHY_PR_ARG,
+		  __entry->ret)
+);
+
+#endif /* !__RDEV_CFG802154_OPS_TRACE || TRACE_HEADER_MULTI_READ */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace
+#include <trace/define_trace.h>
diff --git a/net/ieee802154/wpan-class.c b/net/ieee802154/wpan-class.c
deleted file mode 100644
index 4955e0fe5883..000000000000
--- a/net/ieee802154/wpan-class.c
+++ /dev/null
@@ -1,230 +0,0 @@
-/*
- * Copyright (C) 2007, 2008, 2009 Siemens AG
- *
- * 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.
- *
- */
-
-#include <linux/slab.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/device.h>
-
-#include <net/wpan-phy.h>
-
-#include "ieee802154.h"
-
-#define MASTER_SHOW_COMPLEX(name, format_string, args...)		\
-static ssize_t name ## _show(struct device *dev,			\
-			    struct device_attribute *attr, char *buf)	\
-{									\
-	struct wpan_phy *phy = container_of(dev, struct wpan_phy, dev);	\
-	int ret;							\
-									\
-	mutex_lock(&phy->pib_lock);					\
-	ret = snprintf(buf, PAGE_SIZE, format_string "\n", args);	\
-	mutex_unlock(&phy->pib_lock);					\
-	return ret;							\
-}									\
-static DEVICE_ATTR_RO(name);
-
-#define MASTER_SHOW(field, format_string)				\
-	MASTER_SHOW_COMPLEX(field, format_string, phy->field)
-
-MASTER_SHOW(current_channel, "%d");
-MASTER_SHOW(current_page, "%d");
-MASTER_SHOW(transmit_power, "%d +- 1 dB");
-MASTER_SHOW(cca_mode, "%d");
-
-static ssize_t channels_supported_show(struct device *dev,
-				       struct device_attribute *attr,
-				       char *buf)
-{
-	struct wpan_phy *phy = container_of(dev, struct wpan_phy, dev);
-	int ret;
-	int i, len = 0;
-
-	mutex_lock(&phy->pib_lock);
-	for (i = 0; i < 32; i++) {
-		ret = snprintf(buf + len, PAGE_SIZE - len,
-			       "%#09x\n", phy->channels_supported[i]);
-		if (ret < 0)
-			break;
-		len += ret;
-	}
-	mutex_unlock(&phy->pib_lock);
-	return len;
-}
-static DEVICE_ATTR_RO(channels_supported);
-
-static struct attribute *pmib_attrs[] = {
-	&dev_attr_current_channel.attr,
-	&dev_attr_current_page.attr,
-	&dev_attr_channels_supported.attr,
-	&dev_attr_transmit_power.attr,
-	&dev_attr_cca_mode.attr,
-	NULL,
-};
-ATTRIBUTE_GROUPS(pmib);
-
-static void wpan_phy_release(struct device *d)
-{
-	struct wpan_phy *phy = container_of(d, struct wpan_phy, dev);
-
-	kfree(phy);
-}
-
-static struct class wpan_phy_class = {
-	.name = "ieee802154",
-	.dev_release = wpan_phy_release,
-	.dev_groups = pmib_groups,
-};
-
-static DEFINE_MUTEX(wpan_phy_mutex);
-static int wpan_phy_idx;
-
-static int wpan_phy_match(struct device *dev, const void *data)
-{
-	return !strcmp(dev_name(dev), (const char *)data);
-}
-
-struct wpan_phy *wpan_phy_find(const char *str)
-{
-	struct device *dev;
-
-	if (WARN_ON(!str))
-		return NULL;
-
-	dev = class_find_device(&wpan_phy_class, NULL, str, wpan_phy_match);
-	if (!dev)
-		return NULL;
-
-	return container_of(dev, struct wpan_phy, dev);
-}
-EXPORT_SYMBOL(wpan_phy_find);
-
-struct wpan_phy_iter_data {
-	int (*fn)(struct wpan_phy *phy, void *data);
-	void *data;
-};
-
-static int wpan_phy_iter(struct device *dev, void *_data)
-{
-	struct wpan_phy_iter_data *wpid = _data;
-	struct wpan_phy *phy = container_of(dev, struct wpan_phy, dev);
-
-	return wpid->fn(phy, wpid->data);
-}
-
-int wpan_phy_for_each(int (*fn)(struct wpan_phy *phy, void *data),
-		      void *data)
-{
-	struct wpan_phy_iter_data wpid = {
-		.fn = fn,
-		.data = data,
-	};
-
-	return class_for_each_device(&wpan_phy_class, NULL,
-			&wpid, wpan_phy_iter);
-}
-EXPORT_SYMBOL(wpan_phy_for_each);
-
-static int wpan_phy_idx_valid(int idx)
-{
-	return idx >= 0;
-}
-
-struct wpan_phy *wpan_phy_alloc(size_t priv_size)
-{
-	struct wpan_phy *phy = kzalloc(sizeof(*phy) + priv_size,
-			GFP_KERNEL);
-
-	if (!phy)
-		goto out;
-	mutex_lock(&wpan_phy_mutex);
-	phy->idx = wpan_phy_idx++;
-	if (unlikely(!wpan_phy_idx_valid(phy->idx))) {
-		wpan_phy_idx--;
-		mutex_unlock(&wpan_phy_mutex);
-		kfree(phy);
-		goto out;
-	}
-	mutex_unlock(&wpan_phy_mutex);
-
-	mutex_init(&phy->pib_lock);
-
-	device_initialize(&phy->dev);
-	dev_set_name(&phy->dev, "wpan-phy%d", phy->idx);
-
-	phy->dev.class = &wpan_phy_class;
-
-	phy->current_channel = -1; /* not initialised */
-	phy->current_page = 0; /* for compatibility */
-
-	return phy;
-
-out:
-	return NULL;
-}
-EXPORT_SYMBOL(wpan_phy_alloc);
-
-int wpan_phy_register(struct wpan_phy *phy)
-{
-	return device_add(&phy->dev);
-}
-EXPORT_SYMBOL(wpan_phy_register);
-
-void wpan_phy_unregister(struct wpan_phy *phy)
-{
-	device_del(&phy->dev);
-}
-EXPORT_SYMBOL(wpan_phy_unregister);
-
-void wpan_phy_free(struct wpan_phy *phy)
-{
-	put_device(&phy->dev);
-}
-EXPORT_SYMBOL(wpan_phy_free);
-
-static int __init wpan_phy_class_init(void)
-{
-	int rc;
-
-	rc = class_register(&wpan_phy_class);
-	if (rc)
-		goto err;
-
-	rc = ieee802154_nl_init();
-	if (rc)
-		goto err_nl;
-
-	return 0;
-err_nl:
-	class_unregister(&wpan_phy_class);
-err:
-	return rc;
-}
-subsys_initcall(wpan_phy_class_init);
-
-static void __exit wpan_phy_class_exit(void)
-{
-	ieee802154_nl_exit();
-	class_unregister(&wpan_phy_class);
-}
-module_exit(wpan_phy_class_exit);
-
-MODULE_LICENSE("GPL v2");
-MODULE_DESCRIPTION("IEEE 802.15.4 configuration interface");
-MODULE_AUTHOR("Dmitry Eremin-Solenikov");
-
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index e682b48e0709..bd2901604842 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -322,6 +322,15 @@ config NET_FOU
 	  network mechanisms and optimizations for UDP (such as ECMP
 	  and RSS) can be leveraged to provide better service.
 
+config NET_FOU_IP_TUNNELS
+	bool "IP: FOU encapsulation of IP tunnels"
+	depends on NET_IPIP || NET_IPGRE || IPV6_SIT
+	select NET_FOU
+	---help---
+	  Allow configuration of FOU or GUE encapsulation for IP tunnels.
+	  When this option is enabled IP tunnels can be configured to use
+	  FOU or GUE encapsulation.
+
 config GENEVE
 	tristate "Generic Network Virtualization Encapsulation (Geneve)"
 	depends on INET
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 8b7fe5b03906..8b47a4d79d04 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -217,7 +217,7 @@ int inet_listen(struct socket *sock, int backlog)
 		 * shutdown() (rather than close()).
 		 */
 		if ((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) != 0 &&
-		    inet_csk(sk)->icsk_accept_queue.fastopenq == NULL) {
+		    !inet_csk(sk)->icsk_accept_queue.fastopenq) {
 			if ((sysctl_tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) != 0)
 				err = fastopen_init_queue(sk, backlog);
 			else if ((sysctl_tcp_fastopen &
@@ -314,11 +314,11 @@ lookup_protocol:
 	answer_flags = answer->flags;
 	rcu_read_unlock();
 
-	WARN_ON(answer_prot->slab == NULL);
+	WARN_ON(!answer_prot->slab);
 
 	err = -ENOBUFS;
 	sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot);
-	if (sk == NULL)
+	if (!sk)
 		goto out;
 
 	err = 0;
@@ -395,8 +395,6 @@ int inet_release(struct socket *sock)
 	if (sk) {
 		long timeout;
 
-		sock_rps_reset_flow(sk);
-
 		/* Applications forget to leave groups before exiting */
 		ip_mc_drop_socket(sk);
 
@@ -718,8 +716,7 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr,
 }
 EXPORT_SYMBOL(inet_getname);
 
-int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
-		 size_t size)
+int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 {
 	struct sock *sk = sock->sk;
 
@@ -730,7 +727,7 @@ int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
 	    inet_autobind(sk))
 		return -EAGAIN;
 
-	return sk->sk_prot->sendmsg(iocb, sk, msg, size);
+	return sk->sk_prot->sendmsg(sk, msg, size);
 }
 EXPORT_SYMBOL(inet_sendmsg);
 
@@ -752,8 +749,8 @@ ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset,
 }
 EXPORT_SYMBOL(inet_sendpage);
 
-int inet_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
-		 size_t size, int flags)
+int inet_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+		 int flags)
 {
 	struct sock *sk = sock->sk;
 	int addr_len = 0;
@@ -761,7 +758,7 @@ int inet_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
 
 	sock_rps_record_flow(sk);
 
-	err = sk->sk_prot->recvmsg(iocb, sk, msg, size, flags & MSG_DONTWAIT,
+	err = sk->sk_prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT,
 				   flags & ~MSG_DONTWAIT, &addr_len);
 	if (err >= 0)
 		msg->msg_namelen = addr_len;
@@ -1222,7 +1219,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 		       SKB_GSO_TCPV6 |
 		       SKB_GSO_UDP_TUNNEL |
 		       SKB_GSO_UDP_TUNNEL_CSUM |
-		       SKB_GSO_MPLS |
+		       SKB_GSO_TUNNEL_REMCSUM |
 		       0)))
 		goto out;
 
@@ -1272,7 +1269,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 		if (udpfrag) {
 			iph->id = htons(id);
 			iph->frag_off = htons(offset >> 3);
-			if (skb->next != NULL)
+			if (skb->next)
 				iph->frag_off |= htons(IP_MF);
 			offset += skb->len - nhoff - ihl;
 		} else {
@@ -1386,6 +1383,17 @@ out:
 	return pp;
 }
 
+int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
+{
+	if (sk->sk_family == AF_INET)
+		return ip_recv_error(sk, msg, len, addr_len);
+#if IS_ENABLED(CONFIG_IPV6)
+	if (sk->sk_family == AF_INET6)
+		return pingv6_ops.ipv6_recv_error(sk, msg, len, addr_len);
+#endif
+	return -EINVAL;
+}
+
 static int inet_gro_complete(struct sk_buff *skb, int nhoff)
 {
 	__be16 newlen = htons(skb->len - nhoff);
@@ -1666,7 +1674,7 @@ static int __init inet_init(void)
 	struct list_head *r;
 	int rc = -EINVAL;
 
-	BUILD_BUG_ON(sizeof(struct inet_skb_parm) > FIELD_SIZEOF(struct sk_buff, cb));
+	sock_skb_cb_check_size(sizeof(struct inet_skb_parm));
 
 	rc = proto_register(&tcp_prot, 1);
 	if (rc)
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 16acb59d665e..933a92820d26 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -122,6 +122,7 @@
  *	Interface to generic neighbour cache.
  */
 static u32 arp_hash(const void *pkey, const struct net_device *dev, __u32 *hash_rnd);
+static bool arp_key_eq(const struct neighbour *n, const void *pkey);
 static int arp_constructor(struct neighbour *neigh);
 static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb);
 static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb);
@@ -149,18 +150,12 @@ static const struct neigh_ops arp_direct_ops = {
 	.connected_output =	neigh_direct_output,
 };
 
-static const struct neigh_ops arp_broken_ops = {
-	.family =		AF_INET,
-	.solicit =		arp_solicit,
-	.error_report =		arp_error_report,
-	.output =		neigh_compat_output,
-	.connected_output =	neigh_compat_output,
-};
-
 struct neigh_table arp_tbl = {
 	.family		= AF_INET,
 	.key_len	= 4,
+	.protocol	= cpu_to_be16(ETH_P_IP),
 	.hash		= arp_hash,
+	.key_eq		= arp_key_eq,
 	.constructor	= arp_constructor,
 	.proxy_redo	= parp_redo,
 	.id		= "arp_cache",
@@ -216,7 +211,12 @@ static u32 arp_hash(const void *pkey,
 		    const struct net_device *dev,
 		    __u32 *hash_rnd)
 {
-	return arp_hashfn(*(u32 *)pkey, dev, *hash_rnd);
+	return arp_hashfn(pkey, dev, hash_rnd);
+}
+
+static bool arp_key_eq(const struct neighbour *neigh, const void *pkey)
+{
+	return neigh_key_eq32(neigh, pkey);
 }
 
 static int arp_constructor(struct neighbour *neigh)
@@ -228,7 +228,7 @@ static int arp_constructor(struct neighbour *neigh)
 
 	rcu_read_lock();
 	in_dev = __in_dev_get_rcu(dev);
-	if (in_dev == NULL) {
+	if (!in_dev) {
 		rcu_read_unlock();
 		return -EINVAL;
 	}
@@ -260,35 +260,6 @@ static int arp_constructor(struct neighbour *neigh)
 		   in old paradigm.
 		 */
 
-#if 1
-		/* So... these "amateur" devices are hopeless.
-		   The only thing, that I can say now:
-		   It is very sad that we need to keep ugly obsolete
-		   code to make them happy.
-
-		   They should be moved to more reasonable state, now
-		   they use rebuild_header INSTEAD OF hard_start_xmit!!!
-		   Besides that, they are sort of out of date
-		   (a lot of redundant clones/copies, useless in 2.1),
-		   I wonder why people believe that they work.
-		 */
-		switch (dev->type) {
-		default:
-			break;
-		case ARPHRD_ROSE:
-#if IS_ENABLED(CONFIG_AX25)
-		case ARPHRD_AX25:
-#if IS_ENABLED(CONFIG_NETROM)
-		case ARPHRD_NETROM:
-#endif
-			neigh->ops = &arp_broken_ops;
-			neigh->output = neigh->ops->output;
-			return 0;
-#else
-			break;
-#endif
-		}
-#endif
 		if (neigh->type == RTN_MULTICAST) {
 			neigh->nud_state = NUD_NOARP;
 			arp_mc_map(addr, neigh->ha, dev, 1);
@@ -433,71 +404,6 @@ static int arp_filter(__be32 sip, __be32 tip, struct net_device *dev)
 	return flag;
 }
 
-/* OBSOLETE FUNCTIONS */
-
-/*
- *	Find an arp mapping in the cache. If not found, post a request.
- *
- *	It is very UGLY routine: it DOES NOT use skb->dst->neighbour,
- *	even if it exists. It is supposed that skb->dev was mangled
- *	by a virtual device (eql, shaper). Nobody but broken devices
- *	is allowed to use this function, it is scheduled to be removed. --ANK
- */
-
-static int arp_set_predefined(int addr_hint, unsigned char *haddr,
-			      __be32 paddr, struct net_device *dev)
-{
-	switch (addr_hint) {
-	case RTN_LOCAL:
-		pr_debug("arp called for own IP address\n");
-		memcpy(haddr, dev->dev_addr, dev->addr_len);
-		return 1;
-	case RTN_MULTICAST:
-		arp_mc_map(paddr, haddr, dev, 1);
-		return 1;
-	case RTN_BROADCAST:
-		memcpy(haddr, dev->broadcast, dev->addr_len);
-		return 1;
-	}
-	return 0;
-}
-
-
-int arp_find(unsigned char *haddr, struct sk_buff *skb)
-{
-	struct net_device *dev = skb->dev;
-	__be32 paddr;
-	struct neighbour *n;
-
-	if (!skb_dst(skb)) {
-		pr_debug("arp_find is called with dst==NULL\n");
-		kfree_skb(skb);
-		return 1;
-	}
-
-	paddr = rt_nexthop(skb_rtable(skb), ip_hdr(skb)->daddr);
-	if (arp_set_predefined(inet_addr_type(dev_net(dev), paddr), haddr,
-			       paddr, dev))
-		return 0;
-
-	n = __neigh_lookup(&arp_tbl, &paddr, dev, 1);
-
-	if (n) {
-		n->used = jiffies;
-		if (n->nud_state & NUD_VALID || neigh_event_send(n, skb) == 0) {
-			neigh_ha_snapshot(haddr, n, dev);
-			neigh_release(n);
-			return 0;
-		}
-		neigh_release(n);
-	} else
-		kfree_skb(skb);
-	return 1;
-}
-EXPORT_SYMBOL(arp_find);
-
-/* END OF OBSOLETE FUNCTIONS */
-
 /*
  * Check if we can use proxy ARP for this path
  */
@@ -569,7 +475,7 @@ static inline int arp_fwd_pvlan(struct in_device *in_dev,
  */
 
 /*
- *	Create an arp packet. If (dest_hw == NULL), we create a broadcast
+ *	Create an arp packet. If dest_hw is not set, we create a broadcast
  *	message.
  */
 struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip,
@@ -589,7 +495,7 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip,
 	 */
 
 	skb = alloc_skb(arp_hdr_len(dev) + hlen + tlen, GFP_ATOMIC);
-	if (skb == NULL)
+	if (!skb)
 		return NULL;
 
 	skb_reserve(skb, hlen);
@@ -597,9 +503,9 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip,
 	arp = (struct arphdr *) skb_put(skb, arp_hdr_len(dev));
 	skb->dev = dev;
 	skb->protocol = htons(ETH_P_ARP);
-	if (src_hw == NULL)
+	if (!src_hw)
 		src_hw = dev->dev_addr;
-	if (dest_hw == NULL)
+	if (!dest_hw)
 		dest_hw = dev->broadcast;
 
 	/*
@@ -663,7 +569,7 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip,
 		break;
 #endif
 	default:
-		if (target_hw != NULL)
+		if (target_hw)
 			memcpy(arp_ptr, target_hw, dev->addr_len);
 		else
 			memset(arp_ptr, 0, dev->addr_len);
@@ -685,7 +591,8 @@ EXPORT_SYMBOL(arp_create);
 void arp_xmit(struct sk_buff *skb)
 {
 	/* Send it off, maybe filter it using firewalling first.  */
-	NF_HOOK(NFPROTO_ARP, NF_ARP_OUT, skb, NULL, skb->dev, dev_queue_xmit);
+	NF_HOOK(NFPROTO_ARP, NF_ARP_OUT, NULL, skb,
+		NULL, skb->dev, dev_queue_xmit_sk);
 }
 EXPORT_SYMBOL(arp_xmit);
 
@@ -708,7 +615,7 @@ void arp_send(int type, int ptype, __be32 dest_ip,
 
 	skb = arp_create(type, ptype, dest_ip, dev, src_ip,
 			 dest_hw, src_hw, target_hw);
-	if (skb == NULL)
+	if (!skb)
 		return;
 
 	arp_xmit(skb);
@@ -719,7 +626,7 @@ EXPORT_SYMBOL(arp_send);
  *	Process an arp request.
  */
 
-static int arp_process(struct sk_buff *skb)
+static int arp_process(struct sock *sk, struct sk_buff *skb)
 {
 	struct net_device *dev = skb->dev;
 	struct in_device *in_dev = __in_dev_get_rcu(dev);
@@ -738,7 +645,7 @@ static int arp_process(struct sk_buff *skb)
 	 * is ARP'able.
 	 */
 
-	if (in_dev == NULL)
+	if (!in_dev)
 		goto out;
 
 	arp = arp_hdr(skb);
@@ -902,7 +809,7 @@ static int arp_process(struct sk_buff *skb)
 		is_garp = arp->ar_op == htons(ARPOP_REQUEST) && tip == sip &&
 			  inet_addr_type(net, sip) == RTN_UNICAST;
 
-		if (n == NULL &&
+		if (!n &&
 		    ((arp->ar_op == htons(ARPOP_REPLY)  &&
 		      inet_addr_type(net, sip) == RTN_UNICAST) || is_garp))
 			n = __neigh_lookup(&arp_tbl, &sip, dev, 1);
@@ -940,7 +847,7 @@ out:
 
 static void parp_redo(struct sk_buff *skb)
 {
-	arp_process(skb);
+	arp_process(NULL, skb);
 }
 
 
@@ -973,7 +880,8 @@ static int arp_rcv(struct sk_buff *skb, struct net_device *dev,
 
 	memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb));
 
-	return NF_HOOK(NFPROTO_ARP, NF_ARP_IN, skb, dev, NULL, arp_process);
+	return NF_HOOK(NFPROTO_ARP, NF_ARP_IN, NULL, skb,
+		       dev, NULL, arp_process);
 
 consumeskb:
 	consume_skb(skb);
@@ -994,7 +902,7 @@ out_of_mem:
 
 static int arp_req_set_proxy(struct net *net, struct net_device *dev, int on)
 {
-	if (dev == NULL) {
+	if (!dev) {
 		IPV4_DEVCONF_ALL(net, PROXY_ARP) = on;
 		return 0;
 	}
@@ -1020,7 +928,7 @@ static int arp_req_set_public(struct net *net, struct arpreq *r,
 			return -ENODEV;
 	}
 	if (mask) {
-		if (pneigh_lookup(&arp_tbl, net, &ip, dev, 1) == NULL)
+		if (!pneigh_lookup(&arp_tbl, net, &ip, dev, 1))
 			return -ENOBUFS;
 		return 0;
 	}
@@ -1041,7 +949,7 @@ static int arp_req_set(struct net *net, struct arpreq *r,
 	ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr;
 	if (r->arp_flags & ATF_PERM)
 		r->arp_flags |= ATF_COM;
-	if (dev == NULL) {
+	if (!dev) {
 		struct rtable *rt = ip_route_output(net, ip, 0, RTO_ONLINK, 0);
 
 		if (IS_ERR(rt))
@@ -1161,7 +1069,7 @@ static int arp_req_delete(struct net *net, struct arpreq *r,
 		return arp_req_delete_public(net, r, dev);
 
 	ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr;
-	if (dev == NULL) {
+	if (!dev) {
 		struct rtable *rt = ip_route_output(net, ip, 0, RTO_ONLINK, 0);
 		if (IS_ERR(rt))
 			return PTR_ERR(rt);
@@ -1210,7 +1118,7 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 	if (r.arp_dev[0]) {
 		err = -ENODEV;
 		dev = __dev_get_by_name(net, r.arp_dev);
-		if (dev == NULL)
+		if (!dev)
 			goto out;
 
 		/* Mmmm... It is wrong... ARPHRD_NETROM==0 */
@@ -1292,7 +1200,7 @@ static int arp_proc_init(void);
 
 void __init arp_init(void)
 {
-	neigh_table_init(&arp_tbl);
+	neigh_table_init(NEIGH_ARP_TABLE, &arp_tbl);
 
 	dev_add_pack(&arp_packet_type);
 	arp_proc_init();
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 4715f25dfe03..bdb2a07ec363 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -50,7 +50,7 @@
 #include <net/netlabel.h>
 #include <net/cipso_ipv4.h>
 #include <linux/atomic.h>
-#include <asm/bug.h>
+#include <linux/bug.h>
 #include <asm/unaligned.h>
 
 /* List of available DOI definitions */
@@ -72,6 +72,7 @@ struct cipso_v4_map_cache_bkt {
 	u32 size;
 	struct list_head list;
 };
+
 struct cipso_v4_map_cache_entry {
 	u32 hash;
 	unsigned char *key;
@@ -82,7 +83,8 @@ struct cipso_v4_map_cache_entry {
 	u32 activity;
 	struct list_head list;
 };
-static struct cipso_v4_map_cache_bkt *cipso_v4_cache = NULL;
+
+static struct cipso_v4_map_cache_bkt *cipso_v4_cache;
 
 /* Restricted bitmap (tag #1) flags */
 int cipso_v4_rbm_optfmt = 0;
@@ -253,7 +255,7 @@ static int __init cipso_v4_cache_init(void)
 	cipso_v4_cache = kcalloc(CIPSO_V4_CACHE_BUCKETS,
 				 sizeof(struct cipso_v4_map_cache_bkt),
 				 GFP_KERNEL);
-	if (cipso_v4_cache == NULL)
+	if (!cipso_v4_cache)
 		return -ENOMEM;
 
 	for (iter = 0; iter < CIPSO_V4_CACHE_BUCKETS; iter++) {
@@ -337,7 +339,7 @@ static int cipso_v4_cache_check(const unsigned char *key,
 			secattr->cache = entry->lsm_data;
 			secattr->flags |= NETLBL_SECATTR_CACHE;
 			secattr->type = NETLBL_NLTYPE_CIPSOV4;
-			if (prev_entry == NULL) {
+			if (!prev_entry) {
 				spin_unlock_bh(&cipso_v4_cache[bkt].lock);
 				return 0;
 			}
@@ -376,27 +378,25 @@ static int cipso_v4_cache_check(const unsigned char *key,
  * negative values on failure.
  *
  */
-int cipso_v4_cache_add(const struct sk_buff *skb,
+int cipso_v4_cache_add(const unsigned char *cipso_ptr,
 		       const struct netlbl_lsm_secattr *secattr)
 {
 	int ret_val = -EPERM;
 	u32 bkt;
 	struct cipso_v4_map_cache_entry *entry = NULL;
 	struct cipso_v4_map_cache_entry *old_entry = NULL;
-	unsigned char *cipso_ptr;
 	u32 cipso_ptr_len;
 
 	if (!cipso_v4_cache_enabled || cipso_v4_cache_bucketsize <= 0)
 		return 0;
 
-	cipso_ptr = CIPSO_V4_OPTPTR(skb);
 	cipso_ptr_len = cipso_ptr[1];
 
 	entry = kzalloc(sizeof(*entry), GFP_ATOMIC);
-	if (entry == NULL)
+	if (!entry)
 		return -ENOMEM;
 	entry->key = kmemdup(cipso_ptr, cipso_ptr_len, GFP_ATOMIC);
-	if (entry->key == NULL) {
+	if (!entry->key) {
 		ret_val = -ENOMEM;
 		goto cache_add_failure;
 	}
@@ -502,7 +502,7 @@ int cipso_v4_doi_add(struct cipso_v4_doi *doi_def,
 	atomic_set(&doi_def->refcount, 1);
 
 	spin_lock(&cipso_v4_doi_list_lock);
-	if (cipso_v4_doi_search(doi_def->doi) != NULL) {
+	if (cipso_v4_doi_search(doi_def->doi)) {
 		spin_unlock(&cipso_v4_doi_list_lock);
 		ret_val = -EEXIST;
 		goto doi_add_return;
@@ -513,7 +513,7 @@ int cipso_v4_doi_add(struct cipso_v4_doi *doi_def,
 
 doi_add_return:
 	audit_buf = netlbl_audit_start(AUDIT_MAC_CIPSOV4_ADD, audit_info);
-	if (audit_buf != NULL) {
+	if (audit_buf) {
 		const char *type_str;
 		switch (doi_type) {
 		case CIPSO_V4_MAP_TRANS:
@@ -539,7 +539,7 @@ doi_add_return:
 
 /**
  * cipso_v4_doi_free - Frees a DOI definition
- * @entry: the entry's RCU field
+ * @doi_def: the DOI definition
  *
  * Description:
  * This function frees all of the memory associated with a DOI definition.
@@ -547,7 +547,7 @@ doi_add_return:
  */
 void cipso_v4_doi_free(struct cipso_v4_doi *doi_def)
 {
-	if (doi_def == NULL)
+	if (!doi_def)
 		return;
 
 	switch (doi_def->type) {
@@ -598,7 +598,7 @@ int cipso_v4_doi_remove(u32 doi, struct netlbl_audit *audit_info)
 
 	spin_lock(&cipso_v4_doi_list_lock);
 	doi_def = cipso_v4_doi_search(doi);
-	if (doi_def == NULL) {
+	if (!doi_def) {
 		spin_unlock(&cipso_v4_doi_list_lock);
 		ret_val = -ENOENT;
 		goto doi_remove_return;
@@ -617,7 +617,7 @@ int cipso_v4_doi_remove(u32 doi, struct netlbl_audit *audit_info)
 
 doi_remove_return:
 	audit_buf = netlbl_audit_start(AUDIT_MAC_CIPSOV4_DEL, audit_info);
-	if (audit_buf != NULL) {
+	if (audit_buf) {
 		audit_log_format(audit_buf,
 				 " cipso_doi=%u res=%u",
 				 doi, ret_val == 0 ? 1 : 0);
@@ -644,7 +644,7 @@ struct cipso_v4_doi *cipso_v4_doi_getdef(u32 doi)
 
 	rcu_read_lock();
 	doi_def = cipso_v4_doi_search(doi);
-	if (doi_def == NULL)
+	if (!doi_def)
 		goto doi_getdef_return;
 	if (!atomic_inc_not_zero(&doi_def->refcount))
 		doi_def = NULL;
@@ -664,7 +664,7 @@ doi_getdef_return:
  */
 void cipso_v4_doi_putdef(struct cipso_v4_doi *doi_def)
 {
-	if (doi_def == NULL)
+	if (!doi_def)
 		return;
 
 	if (!atomic_dec_and_test(&doi_def->refcount))
@@ -1577,6 +1577,33 @@ static int cipso_v4_parsetag_loc(const struct cipso_v4_doi *doi_def,
 }
 
 /**
+ * cipso_v4_optptr - Find the CIPSO option in the packet
+ * @skb: the packet
+ *
+ * Description:
+ * Parse the packet's IP header looking for a CIPSO option.  Returns a pointer
+ * to the start of the CIPSO option on success, NULL if one if not found.
+ *
+ */
+unsigned char *cipso_v4_optptr(const struct sk_buff *skb)
+{
+	const struct iphdr *iph = ip_hdr(skb);
+	unsigned char *optptr = (unsigned char *)&(ip_hdr(skb)[1]);
+	int optlen;
+	int taglen;
+
+	for (optlen = iph->ihl*4 - sizeof(struct iphdr); optlen > 0; ) {
+		if (optptr[0] == IPOPT_CIPSO)
+			return optptr;
+		taglen = optptr[1];
+		optlen -= taglen;
+		optptr += taglen;
+	}
+
+	return NULL;
+}
+
+/**
  * cipso_v4_validate - Validate a CIPSO option
  * @option: the start of the option, on error it is set to point to the error
  *
@@ -1615,7 +1642,7 @@ int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option)
 
 	rcu_read_lock();
 	doi_def = cipso_v4_doi_search(get_unaligned_be32(&opt[2]));
-	if (doi_def == NULL) {
+	if (!doi_def) {
 		err_offset = 2;
 		goto validate_return_locked;
 	}
@@ -1709,7 +1736,7 @@ int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option)
 			 * not the loopback device drop the packet. Further,
 			 * there is no legitimate reason for setting this from
 			 * userspace so reject it if skb is NULL. */
-			if (skb == NULL || !(skb->dev->flags & IFF_LOOPBACK)) {
+			if (!skb || !(skb->dev->flags & IFF_LOOPBACK)) {
 				err_offset = opt_iter;
 				goto validate_return_locked;
 			}
@@ -1870,7 +1897,7 @@ int cipso_v4_sock_setattr(struct sock *sk,
 	 * defined yet but it is not a problem as the only users of these
 	 * "lite" PF_INET sockets are functions which do an accept() call
 	 * afterwards so we will label the socket as part of the accept(). */
-	if (sk == NULL)
+	if (!sk)
 		return 0;
 
 	/* We allocate the maximum CIPSO option size here so we are probably
@@ -1878,7 +1905,7 @@ int cipso_v4_sock_setattr(struct sock *sk,
 	 * on and after all we are only talking about 40 bytes. */
 	buf_len = CIPSO_V4_OPT_LEN_MAX;
 	buf = kmalloc(buf_len, GFP_ATOMIC);
-	if (buf == NULL) {
+	if (!buf) {
 		ret_val = -ENOMEM;
 		goto socket_setattr_failure;
 	}
@@ -1894,7 +1921,7 @@ int cipso_v4_sock_setattr(struct sock *sk,
 	 * set the IPOPT_CIPSO option. */
 	opt_len = (buf_len + 3) & ~3;
 	opt = kzalloc(sizeof(*opt) + opt_len, GFP_ATOMIC);
-	if (opt == NULL) {
+	if (!opt) {
 		ret_val = -ENOMEM;
 		goto socket_setattr_failure;
 	}
@@ -1954,7 +1981,7 @@ int cipso_v4_req_setattr(struct request_sock *req,
 	 * on and after all we are only talking about 40 bytes. */
 	buf_len = CIPSO_V4_OPT_LEN_MAX;
 	buf = kmalloc(buf_len, GFP_ATOMIC);
-	if (buf == NULL) {
+	if (!buf) {
 		ret_val = -ENOMEM;
 		goto req_setattr_failure;
 	}
@@ -1970,7 +1997,7 @@ int cipso_v4_req_setattr(struct request_sock *req,
 	 * set the IPOPT_CIPSO option. */
 	opt_len = (buf_len + 3) & ~3;
 	opt = kzalloc(sizeof(*opt) + opt_len, GFP_ATOMIC);
-	if (opt == NULL) {
+	if (!opt) {
 		ret_val = -ENOMEM;
 		goto req_setattr_failure;
 	}
@@ -2075,7 +2102,7 @@ void cipso_v4_sock_delattr(struct sock *sk)
 
 	sk_inet = inet_sk(sk);
 	opt = rcu_dereference_protected(sk_inet->inet_opt, 1);
-	if (opt == NULL || opt->opt.cipso == 0)
+	if (!opt || opt->opt.cipso == 0)
 		return;
 
 	hdr_delta = cipso_v4_delopt(&sk_inet->inet_opt);
@@ -2101,7 +2128,7 @@ void cipso_v4_req_delattr(struct request_sock *req)
 
 	req_inet = inet_rsk(req);
 	opt = req_inet->opt;
-	if (opt == NULL || opt->opt.cipso == 0)
+	if (!opt || opt->opt.cipso == 0)
 		return;
 
 	cipso_v4_delopt(&req_inet->opt);
@@ -2117,8 +2144,8 @@ void cipso_v4_req_delattr(struct request_sock *req)
  * on success and negative values on failure.
  *
  */
-static int cipso_v4_getattr(const unsigned char *cipso,
-			    struct netlbl_lsm_secattr *secattr)
+int cipso_v4_getattr(const unsigned char *cipso,
+		     struct netlbl_lsm_secattr *secattr)
 {
 	int ret_val = -ENOMSG;
 	u32 doi;
@@ -2130,7 +2157,7 @@ static int cipso_v4_getattr(const unsigned char *cipso,
 	doi = get_unaligned_be32(&cipso[2]);
 	rcu_read_lock();
 	doi_def = cipso_v4_doi_search(doi);
-	if (doi_def == NULL)
+	if (!doi_def)
 		goto getattr_return;
 	/* XXX - This code assumes only one tag per CIPSO option which isn't
 	 * really a good assumption to make but since we only support the MAC
@@ -2303,22 +2330,6 @@ int cipso_v4_skbuff_delattr(struct sk_buff *skb)
 	return 0;
 }
 
-/**
- * cipso_v4_skbuff_getattr - Get the security attributes from the CIPSO option
- * @skb: the packet
- * @secattr: the security attributes
- *
- * Description:
- * Parse the given packet's CIPSO option and return the security attributes.
- * Returns zero on success and negative values on failure.
- *
- */
-int cipso_v4_skbuff_getattr(const struct sk_buff *skb,
-			    struct netlbl_lsm_secattr *secattr)
-{
-	return cipso_v4_getattr(CIPSO_V4_OPTPTR(skb), secattr);
-}
-
 /*
  * Setup Functions
  */
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 214882e7d6de..419d23c53ec7 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -107,7 +107,7 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = {
 
 static struct hlist_head inet_addr_lst[IN4_ADDR_HSIZE];
 
-static u32 inet_addr_hash(struct net *net, __be32 addr)
+static u32 inet_addr_hash(const struct net *net, __be32 addr)
 {
 	u32 val = (__force u32) addr ^ net_hash_mix(net);
 
@@ -548,6 +548,26 @@ struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix,
 	return NULL;
 }
 
+static int ip_mc_config(struct sock *sk, bool join, const struct in_ifaddr *ifa)
+{
+	struct ip_mreqn mreq = {
+		.imr_multiaddr.s_addr = ifa->ifa_address,
+		.imr_ifindex = ifa->ifa_dev->dev->ifindex,
+	};
+	int ret;
+
+	ASSERT_RTNL();
+
+	lock_sock(sk);
+	if (join)
+		ret = ip_mc_join_group(sk, &mreq);
+	else
+		ret = ip_mc_leave_group(sk, &mreq);
+	release_sock(sk);
+
+	return ret;
+}
+
 static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
@@ -565,7 +585,7 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	ifm = nlmsg_data(nlh);
 	in_dev = inetdev_by_index(net, ifm->ifa_index);
-	if (in_dev == NULL) {
+	if (!in_dev) {
 		err = -ENODEV;
 		goto errout;
 	}
@@ -573,7 +593,7 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
 	for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL;
 	     ifap = &ifa->ifa_next) {
 		if (tb[IFA_LOCAL] &&
-		    ifa->ifa_local != nla_get_be32(tb[IFA_LOCAL]))
+		    ifa->ifa_local != nla_get_in_addr(tb[IFA_LOCAL]))
 			continue;
 
 		if (tb[IFA_LABEL] && nla_strcmp(tb[IFA_LABEL], ifa->ifa_label))
@@ -581,9 +601,11 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 		if (tb[IFA_ADDRESS] &&
 		    (ifm->ifa_prefixlen != ifa->ifa_prefixlen ||
-		    !inet_ifa_match(nla_get_be32(tb[IFA_ADDRESS]), ifa)))
+		    !inet_ifa_match(nla_get_in_addr(tb[IFA_ADDRESS]), ifa)))
 			continue;
 
+		if (ipv4_is_multicast(ifa->ifa_address))
+			ip_mc_config(net->ipv4.mc_autojoin_sk, false, ifa);
 		__inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).portid);
 		return 0;
 	}
@@ -733,21 +755,21 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh,
 
 	ifm = nlmsg_data(nlh);
 	err = -EINVAL;
-	if (ifm->ifa_prefixlen > 32 || tb[IFA_LOCAL] == NULL)
+	if (ifm->ifa_prefixlen > 32 || !tb[IFA_LOCAL])
 		goto errout;
 
 	dev = __dev_get_by_index(net, ifm->ifa_index);
 	err = -ENODEV;
-	if (dev == NULL)
+	if (!dev)
 		goto errout;
 
 	in_dev = __in_dev_get_rtnl(dev);
 	err = -ENOBUFS;
-	if (in_dev == NULL)
+	if (!in_dev)
 		goto errout;
 
 	ifa = inet_alloc_ifa();
-	if (ifa == NULL)
+	if (!ifa)
 		/*
 		 * A potential indev allocation can be left alive, it stays
 		 * assigned to its device and is destroy with it.
@@ -758,7 +780,7 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh,
 	neigh_parms_data_state_setall(in_dev->arp_parms);
 	in_dev_hold(in_dev);
 
-	if (tb[IFA_ADDRESS] == NULL)
+	if (!tb[IFA_ADDRESS])
 		tb[IFA_ADDRESS] = tb[IFA_LOCAL];
 
 	INIT_HLIST_NODE(&ifa->hash);
@@ -769,11 +791,11 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh,
 	ifa->ifa_scope = ifm->ifa_scope;
 	ifa->ifa_dev = in_dev;
 
-	ifa->ifa_local = nla_get_be32(tb[IFA_LOCAL]);
-	ifa->ifa_address = nla_get_be32(tb[IFA_ADDRESS]);
+	ifa->ifa_local = nla_get_in_addr(tb[IFA_LOCAL]);
+	ifa->ifa_address = nla_get_in_addr(tb[IFA_ADDRESS]);
 
 	if (tb[IFA_BROADCAST])
-		ifa->ifa_broadcast = nla_get_be32(tb[IFA_BROADCAST]);
+		ifa->ifa_broadcast = nla_get_in_addr(tb[IFA_BROADCAST]);
 
 	if (tb[IFA_LABEL])
 		nla_strlcpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ);
@@ -838,6 +860,15 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
 		 * userspace already relies on not having to provide this.
 		 */
 		set_ifa_lifetime(ifa, valid_lft, prefered_lft);
+		if (ifa->ifa_flags & IFA_F_MCAUTOJOIN) {
+			int ret = ip_mc_config(net->ipv4.mc_autojoin_sk,
+					       true, ifa);
+
+			if (ret < 0) {
+				inet_free_ifa(ifa);
+				return ret;
+			}
+		}
 		return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid);
 	} else {
 		inet_free_ifa(ifa);
@@ -1186,7 +1217,7 @@ __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope)
 no_in_dev:
 
 	/* Not loopback addresses on loopback should be preferred
-	   in this case. It is importnat that lo is the first interface
+	   in this case. It is important that lo is the first interface
 	   in dev_base list.
 	 */
 	for_each_netdev_rcu(net, dev) {
@@ -1259,7 +1290,7 @@ __be32 inet_confirm_addr(struct net *net, struct in_device *in_dev,
 	__be32 addr = 0;
 	struct net_device *dev;
 
-	if (in_dev != NULL)
+	if (in_dev)
 		return confirm_addr_indev(in_dev, dst, local, scope);
 
 	rcu_read_lock();
@@ -1309,7 +1340,7 @@ static void inetdev_changename(struct net_device *dev, struct in_device *in_dev)
 		if (named++ == 0)
 			goto skip;
 		dot = strchr(old, ':');
-		if (dot == NULL) {
+		if (!dot) {
 			sprintf(old, ":%d", named);
 			dot = old;
 		}
@@ -1478,7 +1509,7 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa,
 	u32 preferred, valid;
 
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*ifm), flags);
-	if (nlh == NULL)
+	if (!nlh)
 		return -EMSGSIZE;
 
 	ifm = nlmsg_data(nlh);
@@ -1510,11 +1541,11 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa,
 		valid = INFINITY_LIFE_TIME;
 	}
 	if ((ifa->ifa_address &&
-	     nla_put_be32(skb, IFA_ADDRESS, ifa->ifa_address)) ||
+	     nla_put_in_addr(skb, IFA_ADDRESS, ifa->ifa_address)) ||
 	    (ifa->ifa_local &&
-	     nla_put_be32(skb, IFA_LOCAL, ifa->ifa_local)) ||
+	     nla_put_in_addr(skb, IFA_LOCAL, ifa->ifa_local)) ||
 	    (ifa->ifa_broadcast &&
-	     nla_put_be32(skb, IFA_BROADCAST, ifa->ifa_broadcast)) ||
+	     nla_put_in_addr(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) ||
@@ -1522,7 +1553,8 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa,
 			  preferred, valid))
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
@@ -1566,7 +1598,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
 				if (inet_fill_ifaddr(skb, ifa,
 					     NETLINK_CB(cb->skb).portid,
 					     cb->nlh->nlmsg_seq,
-					     RTM_NEWADDR, NLM_F_MULTI) <= 0) {
+					     RTM_NEWADDR, NLM_F_MULTI) < 0) {
 					rcu_read_unlock();
 					goto done;
 				}
@@ -1596,7 +1628,7 @@ static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh,
 
 	net = dev_net(ifa->ifa_dev->dev);
 	skb = nlmsg_new(inet_nlmsg_size(), GFP_KERNEL);
-	if (skb == NULL)
+	if (!skb)
 		goto errout;
 
 	err = inet_fill_ifaddr(skb, ifa, portid, seq, event, 0);
@@ -1633,7 +1665,7 @@ static int inet_fill_link_af(struct sk_buff *skb, const struct net_device *dev)
 		return -ENODATA;
 
 	nla = nla_reserve(skb, IFLA_INET_CONF, IPV4_DEVCONF_MAX * 4);
-	if (nla == NULL)
+	if (!nla)
 		return -EMSGSIZE;
 
 	for (i = 0; i < IPV4_DEVCONF_MAX; i++)
@@ -1722,7 +1754,7 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
 
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct netconfmsg),
 			flags);
-	if (nlh == NULL)
+	if (!nlh)
 		return -EMSGSIZE;
 
 	ncm = nlmsg_data(nlh);
@@ -1749,7 +1781,8 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
 			IPV4_DEVCONF(*devconf, PROXY_ARP)) < 0)
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
@@ -1763,7 +1796,7 @@ void inet_netconf_notify_devconf(struct net *net, int type, int ifindex,
 	int err = -ENOBUFS;
 
 	skb = nlmsg_new(inet_netconf_msgsize_devconf(type), GFP_ATOMIC);
-	if (skb == NULL)
+	if (!skb)
 		goto errout;
 
 	err = inet_netconf_fill_devconf(skb, ifindex, devconf, 0, 0,
@@ -1820,10 +1853,10 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb,
 		break;
 	default:
 		dev = __dev_get_by_index(net, ifindex);
-		if (dev == NULL)
+		if (!dev)
 			goto errout;
 		in_dev = __in_dev_get_rtnl(dev);
-		if (in_dev == NULL)
+		if (!in_dev)
 			goto errout;
 		devconf = &in_dev->cnf;
 		break;
@@ -1831,7 +1864,7 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb,
 
 	err = -ENOBUFS;
 	skb = nlmsg_new(inet_netconf_msgsize_devconf(-1), GFP_ATOMIC);
-	if (skb == NULL)
+	if (!skb)
 		goto errout;
 
 	err = inet_netconf_fill_devconf(skb, ifindex, devconf,
@@ -1881,7 +1914,7 @@ static int inet_netconf_dump_devconf(struct sk_buff *skb,
 						      cb->nlh->nlmsg_seq,
 						      RTM_NEWNETCONF,
 						      NLM_F_MULTI,
-						      -1) <= 0) {
+						      -1) < 0) {
 				rcu_read_unlock();
 				goto done;
 			}
@@ -1897,7 +1930,7 @@ cont:
 					      NETLINK_CB(cb->skb).portid,
 					      cb->nlh->nlmsg_seq,
 					      RTM_NEWNETCONF, NLM_F_MULTI,
-					      -1) <= 0)
+					      -1) < 0)
 			goto done;
 		else
 			h++;
@@ -1908,7 +1941,7 @@ cont:
 					      NETLINK_CB(cb->skb).portid,
 					      cb->nlh->nlmsg_seq,
 					      RTM_NEWNETCONF, NLM_F_MULTI,
-					      -1) <= 0)
+					      -1) < 0)
 			goto done;
 		else
 			h++;
@@ -2182,7 +2215,7 @@ static void __devinet_sysctl_unregister(struct ipv4_devconf *cnf)
 {
 	struct devinet_sysctl_table *t = cnf->sysctl;
 
-	if (t == NULL)
+	if (!t)
 		return;
 
 	cnf->sysctl = NULL;
@@ -2243,16 +2276,16 @@ static __net_init int devinet_init_net(struct net *net)
 
 	if (!net_eq(net, &init_net)) {
 		all = kmemdup(all, sizeof(ipv4_devconf), GFP_KERNEL);
-		if (all == NULL)
+		if (!all)
 			goto err_alloc_all;
 
 		dflt = kmemdup(dflt, sizeof(ipv4_devconf_dflt), GFP_KERNEL);
-		if (dflt == NULL)
+		if (!dflt)
 			goto err_alloc_dflt;
 
 #ifdef CONFIG_SYSCTL
 		tbl = kmemdup(tbl, sizeof(ctl_forward_entry), GFP_KERNEL);
-		if (tbl == NULL)
+		if (!tbl)
 			goto err_alloc_ctl;
 
 		tbl[0].data = &all->data[IPV4_DEVCONF_FORWARDING - 1];
@@ -2272,7 +2305,7 @@ static __net_init int devinet_init_net(struct net *net)
 
 	err = -ENOMEM;
 	forw_hdr = register_net_sysctl(net, "net/ipv4", tbl);
-	if (forw_hdr == NULL)
+	if (!forw_hdr)
 		goto err_reg_ctl;
 	net->ipv4.forw_hdr = forw_hdr;
 #endif
@@ -2320,7 +2353,7 @@ static __net_initdata struct pernet_operations devinet_ops = {
 	.exit = devinet_exit_net,
 };
 
-static struct rtnl_af_ops inet_af_ops = {
+static struct rtnl_af_ops inet_af_ops __read_mostly = {
 	.family		  = AF_INET,
 	.fill_link_af	  = inet_fill_link_af,
 	.get_link_af_size = inet_get_link_af_size,
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 360b565918c4..477937465a20 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -49,7 +49,7 @@ static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int seqhilen)
 		len = ALIGN(len, crypto_tfm_ctx_alignment());
 	}
 
-	len += sizeof(struct aead_givcrypt_request) + crypto_aead_reqsize(aead);
+	len += sizeof(struct aead_request) + crypto_aead_reqsize(aead);
 	len = ALIGN(len, __alignof__(struct scatterlist));
 
 	len += sizeof(struct scatterlist) * nfrags;
@@ -68,17 +68,6 @@ static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int seqhilen)
 			 crypto_aead_alignmask(aead) + 1) : tmp + seqhilen;
 }
 
-static inline struct aead_givcrypt_request *esp_tmp_givreq(
-	struct crypto_aead *aead, u8 *iv)
-{
-	struct aead_givcrypt_request *req;
-
-	req = (void *)PTR_ALIGN(iv + crypto_aead_ivsize(aead),
-				crypto_tfm_ctx_alignment());
-	aead_givcrypt_set_tfm(req, aead);
-	return req;
-}
-
 static inline struct aead_request *esp_tmp_req(struct crypto_aead *aead, u8 *iv)
 {
 	struct aead_request *req;
@@ -97,14 +86,6 @@ static inline struct scatterlist *esp_req_sg(struct crypto_aead *aead,
 			     __alignof__(struct scatterlist));
 }
 
-static inline struct scatterlist *esp_givreq_sg(
-	struct crypto_aead *aead, struct aead_givcrypt_request *req)
-{
-	return (void *)ALIGN((unsigned long)(req + 1) +
-			     crypto_aead_reqsize(aead),
-			     __alignof__(struct scatterlist));
-}
-
 static void esp_output_done(struct crypto_async_request *base, int err)
 {
 	struct sk_buff *skb = base->data;
@@ -113,14 +94,37 @@ static void esp_output_done(struct crypto_async_request *base, int err)
 	xfrm_output_resume(skb, err);
 }
 
+/* Move ESP header back into place. */
+static void esp_restore_header(struct sk_buff *skb, unsigned int offset)
+{
+	struct ip_esp_hdr *esph = (void *)(skb->data + offset);
+	void *tmp = ESP_SKB_CB(skb)->tmp;
+	__be32 *seqhi = esp_tmp_seqhi(tmp);
+
+	esph->seq_no = esph->spi;
+	esph->spi = *seqhi;
+}
+
+static void esp_output_restore_header(struct sk_buff *skb)
+{
+	esp_restore_header(skb, skb_transport_offset(skb) - sizeof(__be32));
+}
+
+static void esp_output_done_esn(struct crypto_async_request *base, int err)
+{
+	struct sk_buff *skb = base->data;
+
+	esp_output_restore_header(skb);
+	esp_output_done(base, err);
+}
+
 static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 {
 	int err;
 	struct ip_esp_hdr *esph;
 	struct crypto_aead *aead;
-	struct aead_givcrypt_request *req;
+	struct aead_request *req;
 	struct scatterlist *sg;
-	struct scatterlist *asg;
 	struct sk_buff *trailer;
 	void *tmp;
 	u8 *iv;
@@ -129,17 +133,19 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	int clen;
 	int alen;
 	int plen;
+	int ivlen;
 	int tfclen;
 	int nfrags;
 	int assoclen;
-	int sglists;
 	int seqhilen;
 	__be32 *seqhi;
+	__be64 seqno;
 
 	/* skb is pure payload to encrypt */
 
 	aead = x->data;
 	alen = crypto_aead_authsize(aead);
+	ivlen = crypto_aead_ivsize(aead);
 
 	tfclen = 0;
 	if (x->tfcpad) {
@@ -160,16 +166,14 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	nfrags = err;
 
 	assoclen = sizeof(*esph);
-	sglists = 1;
 	seqhilen = 0;
 
 	if (x->props.flags & XFRM_STATE_ESN) {
-		sglists += 2;
 		seqhilen += sizeof(__be32);
 		assoclen += seqhilen;
 	}
 
-	tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen);
+	tmp = esp_alloc_tmp(aead, nfrags, seqhilen);
 	if (!tmp) {
 		err = -ENOMEM;
 		goto error;
@@ -177,9 +181,8 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 
 	seqhi = esp_tmp_seqhi(tmp);
 	iv = esp_tmp_iv(aead, tmp, seqhilen);
-	req = esp_tmp_givreq(aead, iv);
-	asg = esp_givreq_sg(aead, req);
-	sg = asg + sglists;
+	req = esp_tmp_req(aead, iv);
+	sg = esp_req_sg(aead, req);
 
 	/* Fill padding... */
 	tail = skb_tail_pointer(trailer);
@@ -235,36 +238,53 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 		*skb_mac_header(skb) = IPPROTO_UDP;
 	}
 
-	esph->spi = x->id.spi;
 	esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
 
+	aead_request_set_callback(req, 0, esp_output_done, skb);
+
+	/* For ESN we move the header forward by 4 bytes to
+	 * accomodate the high bits.  We will move it back after
+	 * encryption.
+	 */
+	if ((x->props.flags & XFRM_STATE_ESN)) {
+		esph = (void *)(skb_transport_header(skb) - sizeof(__be32));
+		*seqhi = esph->spi;
+		esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
+		aead_request_set_callback(req, 0, esp_output_done_esn, skb);
+	}
+
+	esph->spi = x->id.spi;
+
 	sg_init_table(sg, nfrags);
 	skb_to_sgvec(skb, sg,
-		     esph->enc_data + crypto_aead_ivsize(aead) - skb->data,
-		     clen + alen);
+		     (unsigned char *)esph - skb->data,
+		     assoclen + ivlen + clen + alen);
 
-	if ((x->props.flags & XFRM_STATE_ESN)) {
-		sg_init_table(asg, 3);
-		sg_set_buf(asg, &esph->spi, sizeof(__be32));
-		*seqhi = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
-		sg_set_buf(asg + 1, seqhi, seqhilen);
-		sg_set_buf(asg + 2, &esph->seq_no, sizeof(__be32));
-	} else
-		sg_init_one(asg, esph, sizeof(*esph));
-
-	aead_givcrypt_set_callback(req, 0, esp_output_done, skb);
-	aead_givcrypt_set_crypt(req, sg, sg, clen, iv);
-	aead_givcrypt_set_assoc(req, asg, assoclen);
-	aead_givcrypt_set_giv(req, esph->enc_data,
-			      XFRM_SKB_CB(skb)->seq.output.low);
+	aead_request_set_crypt(req, sg, sg, ivlen + clen, iv);
+	aead_request_set_ad(req, assoclen);
+
+	seqno = cpu_to_be64(XFRM_SKB_CB(skb)->seq.output.low +
+			    ((u64)XFRM_SKB_CB(skb)->seq.output.hi << 32));
+
+	memset(iv, 0, ivlen);
+	memcpy(iv + ivlen - min(ivlen, 8), (u8 *)&seqno + 8 - min(ivlen, 8),
+	       min(ivlen, 8));
 
 	ESP_SKB_CB(skb)->tmp = tmp;
-	err = crypto_aead_givencrypt(req);
-	if (err == -EINPROGRESS)
+	err = crypto_aead_encrypt(req);
+
+	switch (err) {
+	case -EINPROGRESS:
 		goto error;
 
-	if (err == -EBUSY)
+	case -EBUSY:
 		err = NET_XMIT_DROP;
+		break;
+
+	case 0:
+		if ((x->props.flags & XFRM_STATE_ESN))
+			esp_output_restore_header(skb);
+	}
 
 	kfree(tmp);
 
@@ -363,6 +383,20 @@ static void esp_input_done(struct crypto_async_request *base, int err)
 	xfrm_input_resume(skb, esp_input_done2(skb, err));
 }
 
+static void esp_input_restore_header(struct sk_buff *skb)
+{
+	esp_restore_header(skb, 0);
+	__skb_pull(skb, 4);
+}
+
+static void esp_input_done_esn(struct crypto_async_request *base, int err)
+{
+	struct sk_buff *skb = base->data;
+
+	esp_input_restore_header(skb);
+	esp_input_done(base, err);
+}
+
 /*
  * Note: detecting truncated vs. non-truncated authentication data is very
  * expensive, so we only support truncated data, which is the recommended
@@ -374,40 +408,39 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb)
 	struct crypto_aead *aead = x->data;
 	struct aead_request *req;
 	struct sk_buff *trailer;
-	int elen = skb->len - sizeof(*esph) - crypto_aead_ivsize(aead);
+	int ivlen = crypto_aead_ivsize(aead);
+	int elen = skb->len - sizeof(*esph) - ivlen;
 	int nfrags;
 	int assoclen;
-	int sglists;
 	int seqhilen;
 	__be32 *seqhi;
 	void *tmp;
 	u8 *iv;
 	struct scatterlist *sg;
-	struct scatterlist *asg;
 	int err = -EINVAL;
 
-	if (!pskb_may_pull(skb, sizeof(*esph) + crypto_aead_ivsize(aead)))
+	if (!pskb_may_pull(skb, sizeof(*esph) + ivlen))
 		goto out;
 
 	if (elen <= 0)
 		goto out;
 
-	if ((err = skb_cow_data(skb, 0, &trailer)) < 0)
+	err = skb_cow_data(skb, 0, &trailer);
+	if (err < 0)
 		goto out;
+
 	nfrags = err;
 
 	assoclen = sizeof(*esph);
-	sglists = 1;
 	seqhilen = 0;
 
 	if (x->props.flags & XFRM_STATE_ESN) {
-		sglists += 2;
 		seqhilen += sizeof(__be32);
 		assoclen += seqhilen;
 	}
 
 	err = -ENOMEM;
-	tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen);
+	tmp = esp_alloc_tmp(aead, nfrags, seqhilen);
 	if (!tmp)
 		goto out;
 
@@ -415,36 +448,39 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb)
 	seqhi = esp_tmp_seqhi(tmp);
 	iv = esp_tmp_iv(aead, tmp, seqhilen);
 	req = esp_tmp_req(aead, iv);
-	asg = esp_req_sg(aead, req);
-	sg = asg + sglists;
+	sg = esp_req_sg(aead, req);
 
 	skb->ip_summed = CHECKSUM_NONE;
 
 	esph = (struct ip_esp_hdr *)skb->data;
 
-	/* Get ivec. This can be wrong, check against another impls. */
-	iv = esph->enc_data;
-
-	sg_init_table(sg, nfrags);
-	skb_to_sgvec(skb, sg, sizeof(*esph) + crypto_aead_ivsize(aead), elen);
+	aead_request_set_callback(req, 0, esp_input_done, skb);
 
+	/* For ESN we move the header forward by 4 bytes to
+	 * accomodate the high bits.  We will move it back after
+	 * decryption.
+	 */
 	if ((x->props.flags & XFRM_STATE_ESN)) {
-		sg_init_table(asg, 3);
-		sg_set_buf(asg, &esph->spi, sizeof(__be32));
-		*seqhi = XFRM_SKB_CB(skb)->seq.input.hi;
-		sg_set_buf(asg + 1, seqhi, seqhilen);
-		sg_set_buf(asg + 2, &esph->seq_no, sizeof(__be32));
-	} else
-		sg_init_one(asg, esph, sizeof(*esph));
+		esph = (void *)skb_push(skb, 4);
+		*seqhi = esph->spi;
+		esph->spi = esph->seq_no;
+		esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.input.hi);
+		aead_request_set_callback(req, 0, esp_input_done_esn, skb);
+	}
 
-	aead_request_set_callback(req, 0, esp_input_done, skb);
-	aead_request_set_crypt(req, sg, sg, elen, iv);
-	aead_request_set_assoc(req, asg, assoclen);
+	sg_init_table(sg, nfrags);
+	skb_to_sgvec(skb, sg, 0, skb->len);
+
+	aead_request_set_crypt(req, sg, sg, elen + ivlen, iv);
+	aead_request_set_ad(req, assoclen);
 
 	err = crypto_aead_decrypt(req);
 	if (err == -EINPROGRESS)
 		goto out;
 
+	if ((x->props.flags & XFRM_STATE_ESN))
+		esp_input_restore_header(skb);
+
 	err = esp_input_done2(skb, err);
 
 out:
@@ -516,10 +552,16 @@ static void esp_destroy(struct xfrm_state *x)
 
 static int esp_init_aead(struct xfrm_state *x)
 {
+	char aead_name[CRYPTO_MAX_ALG_NAME];
 	struct crypto_aead *aead;
 	int err;
 
-	aead = crypto_alloc_aead(x->aead->alg_name, 0, 0);
+	err = -ENAMETOOLONG;
+	if (snprintf(aead_name, CRYPTO_MAX_ALG_NAME, "%s(%s)",
+		     x->geniv, x->aead->alg_name) >= CRYPTO_MAX_ALG_NAME)
+		goto error;
+
+	aead = crypto_alloc_aead(aead_name, 0, 0);
 	err = PTR_ERR(aead);
 	if (IS_ERR(aead))
 		goto error;
@@ -551,22 +593,26 @@ static int esp_init_authenc(struct xfrm_state *x)
 	int err;
 
 	err = -EINVAL;
-	if (x->ealg == NULL)
+	if (!x->ealg)
 		goto error;
 
 	err = -ENAMETOOLONG;
 
 	if ((x->props.flags & XFRM_STATE_ESN)) {
 		if (snprintf(authenc_name, CRYPTO_MAX_ALG_NAME,
-			     "authencesn(%s,%s)",
+			     "%s%sauthencesn(%s,%s)%s",
+			     x->geniv ?: "", x->geniv ? "(" : "",
 			     x->aalg ? x->aalg->alg_name : "digest_null",
-			     x->ealg->alg_name) >= CRYPTO_MAX_ALG_NAME)
+			     x->ealg->alg_name,
+			     x->geniv ? ")" : "") >= CRYPTO_MAX_ALG_NAME)
 			goto error;
 	} else {
 		if (snprintf(authenc_name, CRYPTO_MAX_ALG_NAME,
-			     "authenc(%s,%s)",
+			     "%s%sauthenc(%s,%s)%s",
+			     x->geniv ?: "", x->geniv ? "(" : "",
 			     x->aalg ? x->aalg->alg_name : "digest_null",
-			     x->ealg->alg_name) >= CRYPTO_MAX_ALG_NAME)
+			     x->ealg->alg_name,
+			     x->geniv ? ")" : "") >= CRYPTO_MAX_ALG_NAME)
 			goto error;
 	}
 
@@ -601,12 +647,12 @@ static int esp_init_authenc(struct xfrm_state *x)
 		BUG_ON(!aalg_desc);
 
 		err = -EINVAL;
-		if (aalg_desc->uinfo.auth.icv_fullbits/8 !=
+		if (aalg_desc->uinfo.auth.icv_fullbits / 8 !=
 		    crypto_aead_authsize(aead)) {
-			NETDEBUG(KERN_INFO "ESP: %s digestsize %u != %hu\n",
-				 x->aalg->alg_name,
-				 crypto_aead_authsize(aead),
-				 aalg_desc->uinfo.auth.icv_fullbits/8);
+			pr_info("ESP: %s digestsize %u != %hu\n",
+				x->aalg->alg_name,
+				crypto_aead_authsize(aead),
+				aalg_desc->uinfo.auth.icv_fullbits / 8);
 			goto free_key;
 		}
 
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 23104a3f2924..872494e6e6eb 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -52,12 +52,12 @@ static int __net_init fib4_rules_init(struct net *net)
 {
 	struct fib_table *local_table, *main_table;
 
-	local_table = fib_trie_table(RT_TABLE_LOCAL);
-	if (local_table == NULL)
+	main_table  = fib_trie_table(RT_TABLE_MAIN, NULL);
+	if (!main_table)
 		return -ENOMEM;
 
-	main_table  = fib_trie_table(RT_TABLE_MAIN);
-	if (main_table == NULL)
+	local_table = fib_trie_table(RT_TABLE_LOCAL, main_table);
+	if (!local_table)
 		goto fail;
 
 	hlist_add_head_rcu(&local_table->tb_hlist,
@@ -67,14 +67,14 @@ static int __net_init fib4_rules_init(struct net *net)
 	return 0;
 
 fail:
-	kfree(local_table);
+	fib_free_table(main_table);
 	return -ENOMEM;
 }
 #else
 
 struct fib_table *fib_new_table(struct net *net, u32 id)
 {
-	struct fib_table *tb;
+	struct fib_table *tb, *alias = NULL;
 	unsigned int h;
 
 	if (id == 0)
@@ -83,23 +83,23 @@ struct fib_table *fib_new_table(struct net *net, u32 id)
 	if (tb)
 		return tb;
 
-	tb = fib_trie_table(id);
+	if (id == RT_TABLE_LOCAL)
+		alias = fib_new_table(net, RT_TABLE_MAIN);
+
+	tb = fib_trie_table(id, alias);
 	if (!tb)
 		return NULL;
 
 	switch (id) {
 	case RT_TABLE_LOCAL:
-		net->ipv4.fib_local = tb;
+		rcu_assign_pointer(net->ipv4.fib_local, tb);
 		break;
-
 	case RT_TABLE_MAIN:
-		net->ipv4.fib_main = tb;
+		rcu_assign_pointer(net->ipv4.fib_main, tb);
 		break;
-
 	case RT_TABLE_DEFAULT:
-		net->ipv4.fib_default = tb;
+		rcu_assign_pointer(net->ipv4.fib_default, tb);
 		break;
-
 	default:
 		break;
 	}
@@ -109,6 +109,7 @@ struct fib_table *fib_new_table(struct net *net, u32 id)
 	return tb;
 }
 
+/* caller must hold either rtnl or rcu read lock */
 struct fib_table *fib_get_table(struct net *net, u32 id)
 {
 	struct fib_table *tb;
@@ -119,29 +120,71 @@ struct fib_table *fib_get_table(struct net *net, u32 id)
 		id = RT_TABLE_MAIN;
 	h = id & (FIB_TABLE_HASHSZ - 1);
 
-	rcu_read_lock();
 	head = &net->ipv4.fib_table_hash[h];
 	hlist_for_each_entry_rcu(tb, head, tb_hlist) {
-		if (tb->tb_id == id) {
-			rcu_read_unlock();
+		if (tb->tb_id == id)
 			return tb;
-		}
 	}
-	rcu_read_unlock();
 	return NULL;
 }
 #endif /* CONFIG_IP_MULTIPLE_TABLES */
 
+static void fib_replace_table(struct net *net, struct fib_table *old,
+			      struct fib_table *new)
+{
+#ifdef CONFIG_IP_MULTIPLE_TABLES
+	switch (new->tb_id) {
+	case RT_TABLE_LOCAL:
+		rcu_assign_pointer(net->ipv4.fib_local, new);
+		break;
+	case RT_TABLE_MAIN:
+		rcu_assign_pointer(net->ipv4.fib_main, new);
+		break;
+	case RT_TABLE_DEFAULT:
+		rcu_assign_pointer(net->ipv4.fib_default, new);
+		break;
+	default:
+		break;
+	}
+
+#endif
+	/* replace the old table in the hlist */
+	hlist_replace_rcu(&old->tb_hlist, &new->tb_hlist);
+}
+
+int fib_unmerge(struct net *net)
+{
+	struct fib_table *old, *new;
+
+	/* attempt to fetch local table if it has been allocated */
+	old = fib_get_table(net, RT_TABLE_LOCAL);
+	if (!old)
+		return 0;
+
+	new = fib_trie_unmerge(old);
+	if (!new)
+		return -ENOMEM;
+
+	/* replace merged table with clean table */
+	if (new != old) {
+		fib_replace_table(net, old, new);
+		fib_free_table(old);
+	}
+
+	return 0;
+}
+
 static void fib_flush(struct net *net)
 {
 	int flushed = 0;
-	struct fib_table *tb;
-	struct hlist_head *head;
 	unsigned int h;
 
 	for (h = 0; h < FIB_TABLE_HASHSZ; h++) {
-		head = &net->ipv4.fib_table_hash[h];
-		hlist_for_each_entry(tb, head, tb_hlist)
+		struct hlist_head *head = &net->ipv4.fib_table_hash[h];
+		struct hlist_node *tmp;
+		struct fib_table *tb;
+
+		hlist_for_each_entry_safe(tb, tmp, head, tb_hlist)
 			flushed += fib_table_flush(tb);
 	}
 
@@ -149,6 +192,19 @@ static void fib_flush(struct net *net)
 		rt_cache_flush(net);
 }
 
+void fib_flush_external(struct net *net)
+{
+	struct fib_table *tb;
+	struct hlist_head *head;
+	unsigned int h;
+
+	for (h = 0; h < FIB_TABLE_HASHSZ; h++) {
+		head = &net->ipv4.fib_table_hash[h];
+		hlist_for_each_entry(tb, head, tb_hlist)
+			fib_table_flush_external(tb);
+	}
+}
+
 /*
  * Find address type as if only "dev" was present in the system. If
  * on_dev is NULL then all interfaces are taken into consideration.
@@ -167,16 +223,18 @@ static inline unsigned int __inet_dev_addr_type(struct net *net,
 	if (ipv4_is_multicast(addr))
 		return RTN_MULTICAST;
 
+	rcu_read_lock();
+
 	local_table = fib_get_table(net, RT_TABLE_LOCAL);
 	if (local_table) {
 		ret = RTN_UNICAST;
-		rcu_read_lock();
 		if (!fib_table_lookup(local_table, &fl4, &res, FIB_LOOKUP_NOREF)) {
 			if (!dev || dev == res.fi->fib_dev)
 				ret = res.type;
 		}
-		rcu_read_unlock();
 	}
+
+	rcu_read_unlock();
 	return ret;
 }
 
@@ -428,7 +486,7 @@ static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt,
 			for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next)
 				if (strcmp(ifa->ifa_label, devname) == 0)
 					break;
-			if (ifa == NULL)
+			if (!ifa)
 				return -ENODEV;
 			cfg->fc_prefsrc = ifa->ifa_local;
 		}
@@ -456,7 +514,7 @@ static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt,
 		int len = 0;
 
 		mx = kzalloc(3 * nla_total_size(4), GFP_KERNEL);
-		if (mx == NULL)
+		if (!mx)
 			return -ENOMEM;
 
 		if (rt->rt_flags & RTF_MTU)
@@ -618,7 +676,7 @@ static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 		goto errout;
 
 	tb = fib_get_table(net, cfg.fc_table);
-	if (tb == NULL) {
+	if (!tb) {
 		err = -ESRCH;
 		goto errout;
 	}
@@ -640,7 +698,7 @@ static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 		goto errout;
 
 	tb = fib_new_table(net, cfg.fc_table);
-	if (tb == NULL) {
+	if (!tb) {
 		err = -ENOBUFS;
 		goto errout;
 	}
@@ -666,10 +724,12 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 	s_h = cb->args[0];
 	s_e = cb->args[1];
 
+	rcu_read_lock();
+
 	for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) {
 		e = 0;
 		head = &net->ipv4.fib_table_hash[h];
-		hlist_for_each_entry(tb, head, tb_hlist) {
+		hlist_for_each_entry_rcu(tb, head, tb_hlist) {
 			if (e < s_e)
 				goto next;
 			if (dumped)
@@ -683,6 +743,8 @@ next:
 		}
 	}
 out:
+	rcu_read_unlock();
+
 	cb->args[1] = e;
 	cb->args[0] = h;
 
@@ -717,7 +779,7 @@ static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifad
 	else
 		tb = fib_new_table(net, RT_TABLE_LOCAL);
 
-	if (tb == NULL)
+	if (!tb)
 		return;
 
 	cfg.fc_table = tb->tb_id;
@@ -744,7 +806,7 @@ void fib_add_ifaddr(struct in_ifaddr *ifa)
 
 	if (ifa->ifa_flags & IFA_F_SECONDARY) {
 		prim = inet_ifa_byprefix(in_dev, prefix, mask);
-		if (prim == NULL) {
+		if (!prim) {
 			pr_warn("%s: bug: prim == NULL\n", __func__);
 			return;
 		}
@@ -798,7 +860,7 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
 
 	if (ifa->ifa_flags & IFA_F_SECONDARY) {
 		prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask);
-		if (prim == NULL) {
+		if (!prim) {
 			pr_warn("%s: bug: prim == NULL\n", __func__);
 			return;
 		}
@@ -919,7 +981,7 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
 #undef BRD1_OK
 }
 
-static void nl_fib_lookup(struct fib_result_nl *frn, struct fib_table *tb)
+static void nl_fib_lookup(struct net *net, struct fib_result_nl *frn)
 {
 
 	struct fib_result       res;
@@ -929,6 +991,11 @@ static void nl_fib_lookup(struct fib_result_nl *frn, struct fib_table *tb)
 		.flowi4_tos = frn->fl_tos,
 		.flowi4_scope = frn->fl_scope,
 	};
+	struct fib_table *tb;
+
+	rcu_read_lock();
+
+	tb = fib_get_table(net, frn->tb_id_in);
 
 	frn->err = -ENOENT;
 	if (tb) {
@@ -945,6 +1012,8 @@ static void nl_fib_lookup(struct fib_result_nl *frn, struct fib_table *tb)
 		}
 		local_bh_enable();
 	}
+
+	rcu_read_unlock();
 }
 
 static void nl_fib_input(struct sk_buff *skb)
@@ -952,7 +1021,6 @@ static void nl_fib_input(struct sk_buff *skb)
 	struct net *net;
 	struct fib_result_nl *frn;
 	struct nlmsghdr *nlh;
-	struct fib_table *tb;
 	u32 portid;
 
 	net = sock_net(skb->sk);
@@ -962,14 +1030,12 @@ static void nl_fib_input(struct sk_buff *skb)
 		return;
 
 	skb = netlink_skb_clone(skb, GFP_KERNEL);
-	if (skb == NULL)
+	if (!skb)
 		return;
 	nlh = nlmsg_hdr(skb);
 
 	frn = (struct fib_result_nl *) nlmsg_data(nlh);
-	tb = fib_get_table(net, frn->tb_id_in);
-
-	nl_fib_lookup(frn, tb);
+	nl_fib_lookup(net, frn);
 
 	portid = NETLINK_CB(skb).portid;      /* netlink portid */
 	NETLINK_CB(skb).portid = 0;        /* from kernel */
@@ -985,7 +1051,7 @@ static int __net_init nl_fib_lookup_init(struct net *net)
 	};
 
 	sk = netlink_kernel_create(net, NETLINK_FIB_LOOKUP, &cfg);
-	if (sk == NULL)
+	if (!sk)
 		return -EAFNOSUPPORT;
 	net->ipv4.fibnl = sk;
 	return 0;
@@ -1023,7 +1089,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event,
 	case NETDEV_DOWN:
 		fib_del_ifaddr(ifa, NULL);
 		atomic_inc(&net->ipv4.dev_addr_genid);
-		if (ifa->ifa_dev->ifa_list == NULL) {
+		if (!ifa->ifa_dev->ifa_list) {
 			/* Last address was deleted from this interface.
 			 * Disable IP.
 			 */
@@ -1091,7 +1157,7 @@ static int __net_init ip_fib_net_init(struct net *net)
 	size = max_t(size_t, size, L1_CACHE_BYTES);
 
 	net->ipv4.fib_table_hash = kzalloc(size, GFP_KERNEL);
-	if (net->ipv4.fib_table_hash == NULL)
+	if (!net->ipv4.fib_table_hash)
 		return -ENOMEM;
 
 	err = fib4_rules_init(net);
@@ -1108,23 +1174,27 @@ static void ip_fib_net_exit(struct net *net)
 {
 	unsigned int i;
 
+	rtnl_lock();
 #ifdef CONFIG_IP_MULTIPLE_TABLES
-	fib4_rules_exit(net);
+	RCU_INIT_POINTER(net->ipv4.fib_local, NULL);
+	RCU_INIT_POINTER(net->ipv4.fib_main, NULL);
+	RCU_INIT_POINTER(net->ipv4.fib_default, NULL);
 #endif
-
-	rtnl_lock();
 	for (i = 0; i < FIB_TABLE_HASHSZ; i++) {
-		struct fib_table *tb;
-		struct hlist_head *head;
+		struct hlist_head *head = &net->ipv4.fib_table_hash[i];
 		struct hlist_node *tmp;
+		struct fib_table *tb;
 
-		head = &net->ipv4.fib_table_hash[i];
 		hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) {
 			hlist_del(&tb->tb_hlist);
 			fib_table_flush(tb);
 			fib_free_table(tb);
 		}
 	}
+
+#ifdef CONFIG_IP_MULTIPLE_TABLES
+	fib4_rules_exit(net);
+#endif
 	rtnl_unlock();
 	kfree(net->ipv4.fib_table_hash);
 }
diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h
index 1e4f6600b31d..c6211ed60b03 100644
--- a/net/ipv4/fib_lookup.h
+++ b/net/ipv4/fib_lookup.h
@@ -6,11 +6,13 @@
 #include <net/ip_fib.h>
 
 struct fib_alias {
-	struct list_head	fa_list;
+	struct hlist_node	fa_list;
 	struct fib_info		*fa_info;
 	u8			fa_tos;
 	u8			fa_type;
 	u8			fa_state;
+	u8			fa_slen;
+	u32			tb_id;
 	struct rcu_head		rcu;
 };
 
@@ -32,7 +34,6 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, u32 tb_id,
 		  unsigned int);
 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);
 
 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 f2e15738534d..56151982f74e 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -62,6 +62,10 @@ int __fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res)
 	else
 		res->tclassid = 0;
 #endif
+
+	if (err == -ESRCH)
+		err = -ENETUNREACH;
+
 	return err;
 }
 EXPORT_SYMBOL_GPL(__fib_lookup);
@@ -77,27 +81,25 @@ static int fib4_rule_action(struct fib_rule *rule, struct flowi *flp,
 		break;
 
 	case FR_ACT_UNREACHABLE:
-		err = -ENETUNREACH;
-		goto errout;
+		return -ENETUNREACH;
 
 	case FR_ACT_PROHIBIT:
-		err = -EACCES;
-		goto errout;
+		return -EACCES;
 
 	case FR_ACT_BLACKHOLE:
 	default:
-		err = -EINVAL;
-		goto errout;
+		return -EINVAL;
 	}
 
+	rcu_read_lock();
+
 	tbl = fib_get_table(rule->fr_net, rule->table);
-	if (!tbl)
-		goto errout;
+	if (tbl)
+		err = fib_table_lookup(tbl, &flp->u.ip4,
+				       (struct fib_result *)arg->result,
+				       arg->flags);
 
-	err = fib_table_lookup(tbl, &flp->u.ip4, (struct fib_result *) arg->result, arg->flags);
-	if (err > 0)
-		err = -EAGAIN;
-errout:
+	rcu_read_unlock();
 	return err;
 }
 
@@ -151,7 +153,7 @@ static struct fib_table *fib_empty_table(struct net *net)
 	u32 id;
 
 	for (id = 1; id <= RT_TABLE_MAX; id++)
-		if (fib_get_table(net, id) == NULL)
+		if (!fib_get_table(net, id))
 			return fib_new_table(net, id);
 	return NULL;
 }
@@ -172,12 +174,17 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 	if (frh->tos & ~IPTOS_TOS_MASK)
 		goto errout;
 
+	/* split local/main if they are not already split */
+	err = fib_unmerge(net);
+	if (err)
+		goto errout;
+
 	if (rule->table == RT_TABLE_UNSPEC) {
 		if (rule->action == FR_ACT_TO_TBL) {
 			struct fib_table *table;
 
 			table = fib_empty_table(net);
-			if (table == NULL) {
+			if (!table) {
 				err = -ENOBUFS;
 				goto errout;
 			}
@@ -187,10 +194,10 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 	}
 
 	if (frh->src_len)
-		rule4->src = nla_get_be32(tb[FRA_SRC]);
+		rule4->src = nla_get_in_addr(tb[FRA_SRC]);
 
 	if (frh->dst_len)
-		rule4->dst = nla_get_be32(tb[FRA_DST]);
+		rule4->dst = nla_get_in_addr(tb[FRA_DST]);
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	if (tb[FRA_FLOW]) {
@@ -207,21 +214,31 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 	rule4->tos = frh->tos;
 
 	net->ipv4.fib_has_custom_rules = true;
+	fib_flush_external(rule->fr_net);
+
 	err = 0;
 errout:
 	return err;
 }
 
-static void fib4_rule_delete(struct fib_rule *rule)
+static int fib4_rule_delete(struct fib_rule *rule)
 {
 	struct net *net = rule->fr_net;
-#ifdef CONFIG_IP_ROUTE_CLASSID
-	struct fib4_rule *rule4 = (struct fib4_rule *) rule;
+	int err;
 
-	if (rule4->tclassid)
+	/* split local/main if they are not already split */
+	err = fib_unmerge(net);
+	if (err)
+		goto errout;
+
+#ifdef CONFIG_IP_ROUTE_CLASSID
+	if (((struct fib4_rule *)rule)->tclassid)
 		net->ipv4.fib_num_tclassid_users--;
 #endif
 	net->ipv4.fib_has_custom_rules = true;
+	fib_flush_external(rule->fr_net);
+errout:
+	return err;
 }
 
 static int fib4_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,
@@ -243,10 +260,10 @@ static int fib4_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,
 		return 0;
 #endif
 
-	if (frh->src_len && (rule4->src != nla_get_be32(tb[FRA_SRC])))
+	if (frh->src_len && (rule4->src != nla_get_in_addr(tb[FRA_SRC])))
 		return 0;
 
-	if (frh->dst_len && (rule4->dst != nla_get_be32(tb[FRA_DST])))
+	if (frh->dst_len && (rule4->dst != nla_get_in_addr(tb[FRA_DST])))
 		return 0;
 
 	return 1;
@@ -262,9 +279,9 @@ static int fib4_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
 	frh->tos = rule4->tos;
 
 	if ((rule4->dst_len &&
-	     nla_put_be32(skb, FRA_DST, rule4->dst)) ||
+	     nla_put_in_addr(skb, FRA_DST, rule4->dst)) ||
 	    (rule4->src_len &&
-	     nla_put_be32(skb, FRA_SRC, rule4->src)))
+	     nla_put_in_addr(skb, FRA_SRC, rule4->src)))
 		goto nla_put_failure;
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	if (rule4->tclassid &&
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index f99f41bd15b8..8d695b6659c7 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -213,7 +213,6 @@ static void free_fib_info_rcu(struct rcu_head *head)
 		rt_fibinfo_free(&nexthop_nh->nh_rth_input);
 	} endfor_nexthops(fi);
 
-	release_net(fi->fib_net);
 	if (fi->fib_metrics != (u32 *) dst_default_metrics)
 		kfree(fi->fib_metrics);
 	kfree(fi);
@@ -360,7 +359,8 @@ static inline size_t fib_nlmsg_size(struct fib_info *fi)
 			 + nla_total_size(4) /* RTA_TABLE */
 			 + nla_total_size(4) /* RTA_DST */
 			 + nla_total_size(4) /* RTA_PRIORITY */
-			 + nla_total_size(4); /* RTA_PREFSRC */
+			 + nla_total_size(4) /* RTA_PREFSRC */
+			 + nla_total_size(TCP_CA_NAME_MAX); /* RTAX_CC_ALGO */
 
 	/* space for nested metrics */
 	payload += nla_total_size((RTAX_MAX * nla_total_size(4)));
@@ -390,7 +390,7 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa,
 	int err = -ENOBUFS;
 
 	skb = nlmsg_new(fib_nlmsg_size(fa->fa_info), GFP_KERNEL);
-	if (skb == NULL)
+	if (!skb)
 		goto errout;
 
 	err = fib_dump_info(skb, info->portid, seq, event, tb_id,
@@ -410,24 +410,6 @@ errout:
 		rtnl_set_sk_err(info->nl_net, RTNLGRP_IPV4_ROUTE, err);
 }
 
-/* Return the first fib alias matching TOS with
- * priority less than or equal to PRIO.
- */
-struct fib_alias *fib_find_alias(struct list_head *fah, u8 tos, u32 prio)
-{
-	if (fah) {
-		struct fib_alias *fa;
-		list_for_each_entry(fa, fah, fa_list) {
-			if (fa->fa_tos > tos)
-				continue;
-			if (fa->fa_info->fib_priority >= prio ||
-			    fa->fa_tos < tos)
-				return fa;
-		}
-	}
-	return NULL;
-}
-
 static int fib_detect_death(struct fib_info *fi, int order,
 			    struct fib_info **last_resort, int *last_idx,
 			    int dflt)
@@ -486,7 +468,7 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
 			struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
 
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
-			nexthop_nh->nh_gw = nla ? nla_get_be32(nla) : 0;
+			nexthop_nh->nh_gw = nla ? nla_get_in_addr(nla) : 0;
 #ifdef CONFIG_IP_ROUTE_CLASSID
 			nla = nla_find(attrs, attrlen, RTA_FLOW);
 			nexthop_nh->nh_tclassid = nla ? nla_get_u32(nla) : 0;
@@ -521,7 +503,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi)
 	}
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-	if (cfg->fc_mp == NULL)
+	if (!cfg->fc_mp)
 		return 0;
 
 	rtnh = cfg->fc_mp;
@@ -541,7 +523,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi)
 			struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
 
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
-			if (nla && nla_get_be32(nla) != nh->nh_gw)
+			if (nla && nla_get_in_addr(nla) != nh->nh_gw)
 				return 1;
 #ifdef CONFIG_IP_ROUTE_CLASSID
 			nla = nla_find(attrs, attrlen, RTA_FLOW);
@@ -664,7 +646,7 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi,
 		rcu_read_lock();
 		err = -ENODEV;
 		in_dev = inetdev_by_index(net, nh->nh_oif);
-		if (in_dev == NULL)
+		if (!in_dev)
 			goto out;
 		err = -ENETDOWN;
 		if (!(in_dev->dev->flags & IFF_UP))
@@ -821,7 +803,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 	}
 
 	fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL);
-	if (fi == NULL)
+	if (!fi)
 		goto failure;
 	fib_info_cnt++;
 	if (cfg->fc_mx) {
@@ -831,7 +813,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 	} else
 		fi->fib_metrics = (u32 *) dst_default_metrics;
 
-	fi->fib_net = hold_net(net);
+	fi->fib_net = net;
 	fi->fib_protocol = cfg->fc_protocol;
 	fi->fib_scope = cfg->fc_scope;
 	fi->fib_flags = cfg->fc_flags;
@@ -859,7 +841,16 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 
 				if (type > RTAX_MAX)
 					goto err_inval;
-				val = nla_get_u32(nla);
+				if (type == RTAX_CC_ALGO) {
+					char tmp[TCP_CA_NAME_MAX];
+
+					nla_strlcpy(tmp, nla, sizeof(tmp));
+					val = tcp_ca_get_key_by_name(tmp);
+					if (val == TCP_CA_UNSPEC)
+						goto err_inval;
+				} else {
+					val = nla_get_u32(nla);
+				}
 				if (type == RTAX_ADVMSS && val > 65535 - 40)
 					val = 65535 - 40;
 				if (type == RTAX_MTU && val > 65535 - 15)
@@ -930,7 +921,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 		nh->nh_scope = RT_SCOPE_NOWHERE;
 		nh->nh_dev = dev_get_by_index(net, fi->fib_nh->nh_oif);
 		err = -ENODEV;
-		if (nh->nh_dev == NULL)
+		if (!nh->nh_dev)
 			goto failure;
 	} else {
 		change_nexthops(fi) {
@@ -1004,7 +995,7 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 	struct rtmsg *rtm;
 
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*rtm), flags);
-	if (nlh == NULL)
+	if (!nlh)
 		return -EMSGSIZE;
 
 	rtm = nlmsg_data(nlh);
@@ -1024,7 +1015,7 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 	rtm->rtm_protocol = fi->fib_protocol;
 
 	if (rtm->rtm_dst_len &&
-	    nla_put_be32(skb, RTA_DST, dst))
+	    nla_put_in_addr(skb, RTA_DST, dst))
 		goto nla_put_failure;
 	if (fi->fib_priority &&
 	    nla_put_u32(skb, RTA_PRIORITY, fi->fib_priority))
@@ -1033,11 +1024,11 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 		goto nla_put_failure;
 
 	if (fi->fib_prefsrc &&
-	    nla_put_be32(skb, RTA_PREFSRC, fi->fib_prefsrc))
+	    nla_put_in_addr(skb, RTA_PREFSRC, fi->fib_prefsrc))
 		goto nla_put_failure;
 	if (fi->fib_nhs == 1) {
 		if (fi->fib_nh->nh_gw &&
-		    nla_put_be32(skb, RTA_GATEWAY, fi->fib_nh->nh_gw))
+		    nla_put_in_addr(skb, RTA_GATEWAY, fi->fib_nh->nh_gw))
 			goto nla_put_failure;
 		if (fi->fib_nh->nh_oif &&
 		    nla_put_u32(skb, RTA_OIF, fi->fib_nh->nh_oif))
@@ -1054,12 +1045,12 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 		struct nlattr *mp;
 
 		mp = nla_nest_start(skb, RTA_MULTIPATH);
-		if (mp == NULL)
+		if (!mp)
 			goto nla_put_failure;
 
 		for_nexthops(fi) {
 			rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh));
-			if (rtnh == NULL)
+			if (!rtnh)
 				goto nla_put_failure;
 
 			rtnh->rtnh_flags = nh->nh_flags & 0xFF;
@@ -1067,7 +1058,7 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 			rtnh->rtnh_ifindex = nh->nh_oif;
 
 			if (nh->nh_gw &&
-			    nla_put_be32(skb, RTA_GATEWAY, nh->nh_gw))
+			    nla_put_in_addr(skb, RTA_GATEWAY, nh->nh_gw))
 				goto nla_put_failure;
 #ifdef CONFIG_IP_ROUTE_CLASSID
 			if (nh->nh_tclassid &&
@@ -1081,7 +1072,8 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 		nla_nest_end(skb, mp);
 	}
 #endif
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
@@ -1101,7 +1093,7 @@ int fib_sync_down_addr(struct net *net, __be32 local)
 	struct hlist_head *head = &fib_info_laddrhash[hash];
 	struct fib_info *fi;
 
-	if (fib_info_laddrhash == NULL || local == 0)
+	if (!fib_info_laddrhash || local == 0)
 		return 0;
 
 	hlist_for_each_entry(fi, head, fib_lhash) {
@@ -1170,12 +1162,12 @@ int fib_sync_down_dev(struct net_device *dev, int force)
 void fib_select_default(struct fib_result *res)
 {
 	struct fib_info *fi = NULL, *last_resort = NULL;
-	struct list_head *fa_head = res->fa_head;
+	struct hlist_head *fa_head = res->fa_head;
 	struct fib_table *tb = res->table;
 	int order = -1, last_idx = -1;
 	struct fib_alias *fa;
 
-	list_for_each_entry_rcu(fa, fa_head, fa_list) {
+	hlist_for_each_entry_rcu(fa, fa_head, fa_list) {
 		struct fib_info *next_fi = fa->fa_info;
 
 		if (next_fi->fib_scope != res->scope ||
@@ -1190,7 +1182,7 @@ void fib_select_default(struct fib_result *res)
 
 		fib_alias_accessed(fa);
 
-		if (fi == NULL) {
+		if (!fi) {
 			if (next_fi != res->fi)
 				break;
 		} else if (!fib_detect_death(fi, order, &last_resort,
@@ -1203,7 +1195,7 @@ void fib_select_default(struct fib_result *res)
 		order++;
 	}
 
-	if (order <= 0 || fi == NULL) {
+	if (order <= 0 || !fi) {
 		tb->tb_default = -1;
 		goto out;
 	}
@@ -1259,7 +1251,7 @@ int fib_sync_up(struct net_device *dev)
 				alive++;
 				continue;
 			}
-			if (nexthop_nh->nh_dev == NULL ||
+			if (!nexthop_nh->nh_dev ||
 			    !(nexthop_nh->nh_dev->flags & IFF_UP))
 				continue;
 			if (nexthop_nh->nh_dev != dev ||
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index e9cb2588e416..09b62e17dd8c 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -79,56 +79,45 @@
 #include <net/tcp.h>
 #include <net/sock.h>
 #include <net/ip_fib.h>
+#include <net/switchdev.h>
 #include "fib_lookup.h"
 
 #define MAX_STAT_DEPTH 32
 
-#define KEYLENGTH (8*sizeof(t_key))
+#define KEYLENGTH	(8*sizeof(t_key))
+#define KEY_MAX		((t_key)~0)
 
 typedef unsigned int t_key;
 
-#define T_TNODE 0
-#define T_LEAF  1
-#define NODE_TYPE_MASK	0x1UL
-#define NODE_TYPE(node) ((node)->parent & NODE_TYPE_MASK)
+#define IS_TRIE(n)	((n)->pos >= KEYLENGTH)
+#define IS_TNODE(n)	((n)->bits)
+#define IS_LEAF(n)	(!(n)->bits)
 
-#define IS_TNODE(n) (!(n->parent & T_LEAF))
-#define IS_LEAF(n) (n->parent & T_LEAF)
-
-struct rt_trie_node {
-	unsigned long parent;
-	t_key key;
-};
-
-struct leaf {
-	unsigned long parent;
-	t_key key;
-	struct hlist_head list;
-	struct rcu_head rcu;
-};
-
-struct leaf_info {
-	struct hlist_node hlist;
-	int plen;
-	u32 mask_plen; /* ntohl(inet_make_mask(plen)) */
-	struct list_head falh;
-	struct rcu_head rcu;
-};
-
-struct tnode {
-	unsigned long parent;
+struct key_vector {
 	t_key key;
 	unsigned char pos;		/* 2log(KEYLENGTH) bits needed */
 	unsigned char bits;		/* 2log(KEYLENGTH) bits needed */
-	unsigned int full_children;	/* KEYLENGTH bits needed */
-	unsigned int empty_children;	/* KEYLENGTH bits needed */
+	unsigned char slen;
 	union {
-		struct rcu_head rcu;
-		struct tnode *tnode_free;
+		/* This list pointer if valid if (pos | bits) == 0 (LEAF) */
+		struct hlist_head leaf;
+		/* This array is valid if (pos | bits) > 0 (TNODE) */
+		struct key_vector __rcu *tnode[0];
 	};
-	struct rt_trie_node __rcu *child[0];
 };
 
+struct tnode {
+	struct rcu_head rcu;
+	t_key empty_children;		/* KEYLENGTH bits needed */
+	t_key full_children;		/* KEYLENGTH bits needed */
+	struct key_vector __rcu *parent;
+	struct key_vector kv[1];
+#define tn_bits kv[0].bits
+};
+
+#define TNODE_SIZE(n)	offsetof(struct tnode, kv[0].tnode[n])
+#define LEAF_SIZE	TNODE_SIZE(1)
+
 #ifdef CONFIG_IP_FIB_TRIE_STATS
 struct trie_use_stats {
 	unsigned int gets;
@@ -151,19 +140,13 @@ struct trie_stat {
 };
 
 struct trie {
-	struct rt_trie_node __rcu *trie;
+	struct key_vector kv[1];
 #ifdef CONFIG_IP_FIB_TRIE_STATS
-	struct trie_use_stats stats;
+	struct trie_use_stats __percpu *stats;
 #endif
 };
 
-static void tnode_put_child_reorg(struct tnode *tn, int i, struct rt_trie_node *n,
-				  int wasfull);
-static struct rt_trie_node *resize(struct trie *t, struct tnode *tn);
-static struct tnode *inflate(struct trie *t, struct tnode *tn);
-static struct tnode *halve(struct trie *t, struct tnode *tn);
-/* tnodes to free after resize(); protected by RTNL */
-static struct tnode *tnode_free_head;
+static struct key_vector *resize(struct trie *t, struct key_vector *tn);
 static size_t tnode_free_size;
 
 /*
@@ -176,170 +159,106 @@ static const int sync_pages = 128;
 static struct kmem_cache *fn_alias_kmem __read_mostly;
 static struct kmem_cache *trie_leaf_kmem __read_mostly;
 
-/*
- * caller must hold RTNL
- */
-static inline struct tnode *node_parent(const struct rt_trie_node *node)
+static inline struct tnode *tn_info(struct key_vector *kv)
 {
-	unsigned long parent;
-
-	parent = rcu_dereference_index_check(node->parent, lockdep_rtnl_is_held());
-
-	return (struct tnode *)(parent & ~NODE_TYPE_MASK);
+	return container_of(kv, struct tnode, kv[0]);
 }
 
-/*
- * caller must hold RCU read lock or RTNL
- */
-static inline struct tnode *node_parent_rcu(const struct rt_trie_node *node)
-{
-	unsigned long parent;
-
-	parent = rcu_dereference_index_check(node->parent, rcu_read_lock_held() ||
-							   lockdep_rtnl_is_held());
+/* caller must hold RTNL */
+#define node_parent(tn) rtnl_dereference(tn_info(tn)->parent)
+#define get_child(tn, i) rtnl_dereference((tn)->tnode[i])
 
-	return (struct tnode *)(parent & ~NODE_TYPE_MASK);
-}
+/* caller must hold RCU read lock or RTNL */
+#define node_parent_rcu(tn) rcu_dereference_rtnl(tn_info(tn)->parent)
+#define get_child_rcu(tn, i) rcu_dereference_rtnl((tn)->tnode[i])
 
-/* Same as rcu_assign_pointer
- * but that macro() assumes that value is a pointer.
- */
-static inline void node_set_parent(struct rt_trie_node *node, struct tnode *ptr)
+/* wrapper for rcu_assign_pointer */
+static inline void node_set_parent(struct key_vector *n, struct key_vector *tp)
 {
-	smp_wmb();
-	node->parent = (unsigned long)ptr | NODE_TYPE(node);
+	if (n)
+		rcu_assign_pointer(tn_info(n)->parent, tp);
 }
 
-/*
- * caller must hold RTNL
- */
-static inline struct rt_trie_node *tnode_get_child(const struct tnode *tn, unsigned int i)
-{
-	BUG_ON(i >= 1U << tn->bits);
-
-	return rtnl_dereference(tn->child[i]);
-}
+#define NODE_INIT_PARENT(n, p) RCU_INIT_POINTER(tn_info(n)->parent, p)
 
-/*
- * caller must hold RCU read lock or RTNL
+/* This provides us with the number of children in this node, in the case of a
+ * leaf this will return 0 meaning none of the children are accessible.
  */
-static inline struct rt_trie_node *tnode_get_child_rcu(const struct tnode *tn, unsigned int i)
+static inline unsigned long child_length(const struct key_vector *tn)
 {
-	BUG_ON(i >= 1U << tn->bits);
-
-	return rcu_dereference_rtnl(tn->child[i]);
+	return (1ul << tn->bits) & ~(1ul);
 }
 
-static inline int tnode_child_length(const struct tnode *tn)
-{
-	return 1 << tn->bits;
-}
+#define get_cindex(key, kv) (((key) ^ (kv)->key) >> (kv)->pos)
 
-static inline t_key mask_pfx(t_key k, unsigned int l)
+static inline unsigned long get_index(t_key key, struct key_vector *kv)
 {
-	return (l == 0) ? 0 : k >> (KEYLENGTH-l) << (KEYLENGTH-l);
-}
+	unsigned long index = key ^ kv->key;
 
-static inline t_key tkey_extract_bits(t_key a, unsigned int offset, unsigned int bits)
-{
-	if (offset < KEYLENGTH)
-		return ((t_key)(a << offset)) >> (KEYLENGTH - bits);
-	else
+	if ((BITS_PER_LONG <= KEYLENGTH) && (KEYLENGTH == kv->pos))
 		return 0;
-}
-
-static inline int tkey_equals(t_key a, t_key b)
-{
-	return a == b;
-}
 
-static inline int tkey_sub_equals(t_key a, int offset, int bits, t_key b)
-{
-	if (bits == 0 || offset >= KEYLENGTH)
-		return 1;
-	bits = bits > KEYLENGTH ? KEYLENGTH : bits;
-	return ((a ^ b) << offset) >> (KEYLENGTH - bits) == 0;
+	return index >> kv->pos;
 }
 
-static inline int tkey_mismatch(t_key a, int offset, t_key b)
-{
-	t_key diff = a ^ b;
-	int i = offset;
-
-	if (!diff)
-		return 0;
-	while ((diff << i) >> (KEYLENGTH-1) == 0)
-		i++;
-	return i;
-}
-
-/*
-  To understand this stuff, an understanding of keys and all their bits is
-  necessary. Every node in the trie has a key associated with it, but not
-  all of the bits in that key are significant.
-
-  Consider a node 'n' and its parent 'tp'.
-
-  If n is a leaf, every bit in its key is significant. Its presence is
-  necessitated by path compression, since during a tree traversal (when
-  searching for a leaf - unless we are doing an insertion) we will completely
-  ignore all skipped bits we encounter. Thus we need to verify, at the end of
-  a potentially successful search, that we have indeed been walking the
-  correct key path.
-
-  Note that we can never "miss" the correct key in the tree if present by
-  following the wrong path. Path compression ensures that segments of the key
-  that are the same for all keys with a given prefix are skipped, but the
-  skipped part *is* identical for each node in the subtrie below the skipped
-  bit! trie_insert() in this implementation takes care of that - note the
-  call to tkey_sub_equals() in trie_insert().
-
-  if n is an internal node - a 'tnode' here, the various parts of its key
-  have many different meanings.
-
-  Example:
-  _________________________________________________________________
-  | i | i | i | i | i | i | i | N | N | N | S | S | S | S | S | C |
-  -----------------------------------------------------------------
-    0   1   2   3   4   5   6   7   8   9  10  11  12  13  14  15
-
-  _________________________________________________________________
-  | C | C | C | u | u | u | u | u | u | u | u | u | u | u | u | u |
-  -----------------------------------------------------------------
-   16  17  18  19  20  21  22  23  24  25  26  27  28  29  30  31
-
-  tp->pos = 7
-  tp->bits = 3
-  n->pos = 15
-  n->bits = 4
-
-  First, let's just ignore the bits that come before the parent tp, that is
-  the bits from 0 to (tp->pos-1). They are *known* but at this point we do
-  not use them for anything.
-
-  The bits from (tp->pos) to (tp->pos + tp->bits - 1) - "N", above - are the
-  index into the parent's child array. That is, they will be used to find
-  'n' among tp's children.
-
-  The bits from (tp->pos + tp->bits) to (n->pos - 1) - "S" - are skipped bits
-  for the node n.
-
-  All the bits we have seen so far are significant to the node n. The rest
-  of the bits are really not needed or indeed known in n->key.
-
-  The bits from (n->pos) to (n->pos + n->bits - 1) - "C" - are the index into
-  n's child array, and will of course be different for each child.
-
-
-  The rest of the bits, from (n->pos + n->bits) onward, are completely unknown
-  at this point.
-
-*/
-
-static inline void check_tnode(const struct tnode *tn)
-{
-	WARN_ON(tn && tn->pos+tn->bits > 32);
-}
+/* To understand this stuff, an understanding of keys and all their bits is
+ * necessary. Every node in the trie has a key associated with it, but not
+ * all of the bits in that key are significant.
+ *
+ * Consider a node 'n' and its parent 'tp'.
+ *
+ * If n is a leaf, every bit in its key is significant. Its presence is
+ * necessitated by path compression, since during a tree traversal (when
+ * searching for a leaf - unless we are doing an insertion) we will completely
+ * ignore all skipped bits we encounter. Thus we need to verify, at the end of
+ * a potentially successful search, that we have indeed been walking the
+ * correct key path.
+ *
+ * Note that we can never "miss" the correct key in the tree if present by
+ * following the wrong path. Path compression ensures that segments of the key
+ * that are the same for all keys with a given prefix are skipped, but the
+ * skipped part *is* identical for each node in the subtrie below the skipped
+ * bit! trie_insert() in this implementation takes care of that.
+ *
+ * if n is an internal node - a 'tnode' here, the various parts of its key
+ * have many different meanings.
+ *
+ * Example:
+ * _________________________________________________________________
+ * | i | i | i | i | i | i | i | N | N | N | S | S | S | S | S | C |
+ * -----------------------------------------------------------------
+ *  31  30  29  28  27  26  25  24  23  22  21  20  19  18  17  16
+ *
+ * _________________________________________________________________
+ * | C | C | C | u | u | u | u | u | u | u | u | u | u | u | u | u |
+ * -----------------------------------------------------------------
+ *  15  14  13  12  11  10   9   8   7   6   5   4   3   2   1   0
+ *
+ * tp->pos = 22
+ * tp->bits = 3
+ * n->pos = 13
+ * n->bits = 4
+ *
+ * First, let's just ignore the bits that come before the parent tp, that is
+ * the bits from (tp->pos + tp->bits) to 31. They are *known* but at this
+ * point we do not use them for anything.
+ *
+ * The bits from (tp->pos) to (tp->pos + tp->bits - 1) - "N", above - are the
+ * index into the parent's child array. That is, they will be used to find
+ * 'n' among tp's children.
+ *
+ * The bits from (n->pos + n->bits) to (tn->pos - 1) - "S" - are skipped bits
+ * for the node n.
+ *
+ * All the bits we have seen so far are significant to the node n. The rest
+ * of the bits are really not needed or indeed known in n->key.
+ *
+ * The bits from (n->pos) to (n->pos + n->bits - 1) - "C" - are the index into
+ * n's child array, and will of course be different for each child.
+ *
+ * The rest of the bits, from 0 to (n->pos + n->bits), are completely unknown
+ * at this point.
+ */
 
 static const int halve_threshold = 25;
 static const int inflate_threshold = 50;
@@ -357,859 +276,841 @@ static inline void alias_free_mem_rcu(struct fib_alias *fa)
 	call_rcu(&fa->rcu, __alias_free_mem);
 }
 
-static void __leaf_free_rcu(struct rcu_head *head)
-{
-	struct leaf *l = container_of(head, struct leaf, rcu);
-	kmem_cache_free(trie_leaf_kmem, l);
-}
+#define TNODE_KMALLOC_MAX \
+	ilog2((PAGE_SIZE - TNODE_SIZE(0)) / sizeof(struct key_vector *))
+#define TNODE_VMALLOC_MAX \
+	ilog2((SIZE_MAX - TNODE_SIZE(0)) / sizeof(struct key_vector *))
 
-static inline void free_leaf(struct leaf *l)
+static void __node_free_rcu(struct rcu_head *head)
 {
-	call_rcu(&l->rcu, __leaf_free_rcu);
-}
+	struct tnode *n = container_of(head, struct tnode, rcu);
 
-static inline void free_leaf_info(struct leaf_info *leaf)
-{
-	kfree_rcu(leaf, rcu);
+	if (!n->tn_bits)
+		kmem_cache_free(trie_leaf_kmem, n);
+	else if (n->tn_bits <= TNODE_KMALLOC_MAX)
+		kfree(n);
+	else
+		vfree(n);
 }
 
-static struct tnode *tnode_alloc(size_t size)
+#define node_free(n) call_rcu(&tn_info(n)->rcu, __node_free_rcu)
+
+static struct tnode *tnode_alloc(int bits)
 {
+	size_t size;
+
+	/* verify bits is within bounds */
+	if (bits > TNODE_VMALLOC_MAX)
+		return NULL;
+
+	/* determine size and verify it is non-zero and didn't overflow */
+	size = TNODE_SIZE(1ul << bits);
+
 	if (size <= PAGE_SIZE)
 		return kzalloc(size, GFP_KERNEL);
 	else
 		return vzalloc(size);
 }
 
-static void __tnode_free_rcu(struct rcu_head *head)
+static inline void empty_child_inc(struct key_vector *n)
 {
-	struct tnode *tn = container_of(head, struct tnode, rcu);
-	size_t size = sizeof(struct tnode) +
-		      (sizeof(struct rt_trie_node *) << tn->bits);
-
-	if (size <= PAGE_SIZE)
-		kfree(tn);
-	else
-		vfree(tn);
+	++tn_info(n)->empty_children ? : ++tn_info(n)->full_children;
 }
 
-static inline void tnode_free(struct tnode *tn)
+static inline void empty_child_dec(struct key_vector *n)
 {
-	if (IS_LEAF(tn))
-		free_leaf((struct leaf *) tn);
-	else
-		call_rcu(&tn->rcu, __tnode_free_rcu);
+	tn_info(n)->empty_children-- ? : tn_info(n)->full_children--;
 }
 
-static void tnode_free_safe(struct tnode *tn)
+static struct key_vector *leaf_new(t_key key, struct fib_alias *fa)
 {
-	BUG_ON(IS_LEAF(tn));
-	tn->tnode_free = tnode_free_head;
-	tnode_free_head = tn;
-	tnode_free_size += sizeof(struct tnode) +
-			   (sizeof(struct rt_trie_node *) << tn->bits);
-}
+	struct tnode *kv = kmem_cache_alloc(trie_leaf_kmem, GFP_KERNEL);
+	struct key_vector *l = kv->kv;
 
-static void tnode_free_flush(void)
-{
-	struct tnode *tn;
+	if (!kv)
+		return NULL;
 
-	while ((tn = tnode_free_head)) {
-		tnode_free_head = tn->tnode_free;
-		tn->tnode_free = NULL;
-		tnode_free(tn);
-	}
+	/* initialize key vector */
+	l->key = key;
+	l->pos = 0;
+	l->bits = 0;
+	l->slen = fa->fa_slen;
 
-	if (tnode_free_size >= PAGE_SIZE * sync_pages) {
-		tnode_free_size = 0;
-		synchronize_rcu();
-	}
-}
+	/* link leaf to fib alias */
+	INIT_HLIST_HEAD(&l->leaf);
+	hlist_add_head(&fa->fa_list, &l->leaf);
 
-static struct leaf *leaf_new(void)
-{
-	struct leaf *l = kmem_cache_alloc(trie_leaf_kmem, GFP_KERNEL);
-	if (l) {
-		l->parent = T_LEAF;
-		INIT_HLIST_HEAD(&l->list);
-	}
 	return l;
 }
 
-static struct leaf_info *leaf_info_new(int plen)
+static struct key_vector *tnode_new(t_key key, int pos, int bits)
 {
-	struct leaf_info *li = kmalloc(sizeof(struct leaf_info),  GFP_KERNEL);
-	if (li) {
-		li->plen = plen;
-		li->mask_plen = ntohl(inet_make_mask(plen));
-		INIT_LIST_HEAD(&li->falh);
-	}
-	return li;
-}
+	struct tnode *tnode = tnode_alloc(bits);
+	unsigned int shift = pos + bits;
+	struct key_vector *tn = tnode->kv;
 
-static struct tnode *tnode_new(t_key key, int pos, int bits)
-{
-	size_t sz = sizeof(struct tnode) + (sizeof(struct rt_trie_node *) << bits);
-	struct tnode *tn = tnode_alloc(sz);
+	/* verify bits and pos their msb bits clear and values are valid */
+	BUG_ON(!bits || (shift > KEYLENGTH));
 
-	if (tn) {
-		tn->parent = T_TNODE;
-		tn->pos = pos;
-		tn->bits = bits;
-		tn->key = key;
-		tn->full_children = 0;
-		tn->empty_children = 1<<bits;
-	}
+	pr_debug("AT %p s=%zu %zu\n", tnode, TNODE_SIZE(0),
+		 sizeof(struct key_vector *) << bits);
 
-	pr_debug("AT %p s=%zu %zu\n", tn, sizeof(struct tnode),
-		 sizeof(struct rt_trie_node *) << bits);
-	return tn;
-}
+	if (!tnode)
+		return NULL;
 
-/*
- * Check whether a tnode 'n' is "full", i.e. it is an internal node
- * and no bits are skipped. See discussion in dyntree paper p. 6
- */
+	if (bits == KEYLENGTH)
+		tnode->full_children = 1;
+	else
+		tnode->empty_children = 1ul << bits;
 
-static inline int tnode_full(const struct tnode *tn, const struct rt_trie_node *n)
-{
-	if (n == NULL || IS_LEAF(n))
-		return 0;
+	tn->key = (shift < KEYLENGTH) ? (key >> shift) << shift : 0;
+	tn->pos = pos;
+	tn->bits = bits;
+	tn->slen = pos;
 
-	return ((struct tnode *) n)->pos == tn->pos + tn->bits;
+	return tn;
 }
 
-static inline void put_child(struct tnode *tn, int i,
-			     struct rt_trie_node *n)
+/* Check whether a tnode 'n' is "full", i.e. it is an internal node
+ * and no bits are skipped. See discussion in dyntree paper p. 6
+ */
+static inline int tnode_full(struct key_vector *tn, struct key_vector *n)
 {
-	tnode_put_child_reorg(tn, i, n, -1);
+	return n && ((n->pos + n->bits) == tn->pos) && IS_TNODE(n);
 }
 
- /*
-  * Add a child at position i overwriting the old value.
-  * Update the value of full_children and empty_children.
-  */
-
-static void tnode_put_child_reorg(struct tnode *tn, int i, struct rt_trie_node *n,
-				  int wasfull)
+/* Add a child at position i overwriting the old value.
+ * Update the value of full_children and empty_children.
+ */
+static void put_child(struct key_vector *tn, unsigned long i,
+		      struct key_vector *n)
 {
-	struct rt_trie_node *chi = rtnl_dereference(tn->child[i]);
-	int isfull;
+	struct key_vector *chi = get_child(tn, i);
+	int isfull, wasfull;
 
-	BUG_ON(i >= 1<<tn->bits);
+	BUG_ON(i >= child_length(tn));
 
-	/* update emptyChildren */
-	if (n == NULL && chi != NULL)
-		tn->empty_children++;
-	else if (n != NULL && chi == NULL)
-		tn->empty_children--;
+	/* update emptyChildren, overflow into fullChildren */
+	if (!n && chi)
+		empty_child_inc(tn);
+	if (n && !chi)
+		empty_child_dec(tn);
 
 	/* update fullChildren */
-	if (wasfull == -1)
-		wasfull = tnode_full(tn, chi);
-
+	wasfull = tnode_full(tn, chi);
 	isfull = tnode_full(tn, n);
+
 	if (wasfull && !isfull)
-		tn->full_children--;
+		tn_info(tn)->full_children--;
 	else if (!wasfull && isfull)
-		tn->full_children++;
+		tn_info(tn)->full_children++;
 
-	if (n)
-		node_set_parent(n, tn);
+	if (n && (tn->slen < n->slen))
+		tn->slen = n->slen;
 
-	rcu_assign_pointer(tn->child[i], n);
+	rcu_assign_pointer(tn->tnode[i], n);
 }
 
-#define MAX_WORK 10
-static struct rt_trie_node *resize(struct trie *t, struct tnode *tn)
+static void update_children(struct key_vector *tn)
 {
-	int i;
-	struct tnode *old_tn;
-	int inflate_threshold_use;
-	int halve_threshold_use;
-	int max_work;
+	unsigned long i;
 
-	if (!tn)
-		return NULL;
+	/* update all of the child parent pointers */
+	for (i = child_length(tn); i;) {
+		struct key_vector *inode = get_child(tn, --i);
 
-	pr_debug("In tnode_resize %p inflate_threshold=%d threshold=%d\n",
-		 tn, inflate_threshold, halve_threshold);
+		if (!inode)
+			continue;
 
-	/* No children */
-	if (tn->empty_children == tnode_child_length(tn)) {
-		tnode_free_safe(tn);
-		return NULL;
+		/* Either update the children of a tnode that
+		 * already belongs to us or update the child
+		 * to point to ourselves.
+		 */
+		if (node_parent(inode) == tn)
+			update_children(inode);
+		else
+			node_set_parent(inode, tn);
 	}
-	/* One child */
-	if (tn->empty_children == tnode_child_length(tn) - 1)
-		goto one_child;
-	/*
-	 * Double as long as the resulting node has a number of
-	 * nonempty nodes that are above the threshold.
-	 */
-
-	/*
-	 * From "Implementing a dynamic compressed trie" by Stefan Nilsson of
-	 * the Helsinki University of Technology and Matti Tikkanen of Nokia
-	 * Telecommunications, page 6:
-	 * "A node is doubled if the ratio of non-empty children to all
-	 * children in the *doubled* node is at least 'high'."
-	 *
-	 * 'high' in this instance is the variable 'inflate_threshold'. It
-	 * is expressed as a percentage, so we multiply it with
-	 * tnode_child_length() and instead of multiplying by 2 (since the
-	 * child array will be doubled by inflate()) and multiplying
-	 * the left-hand side by 100 (to handle the percentage thing) we
-	 * multiply the left-hand side by 50.
-	 *
-	 * The left-hand side may look a bit weird: tnode_child_length(tn)
-	 * - tn->empty_children is of course the number of non-null children
-	 * in the current node. tn->full_children is the number of "full"
-	 * children, that is non-null tnodes with a skip value of 0.
-	 * All of those will be doubled in the resulting inflated tnode, so
-	 * we just count them one extra time here.
-	 *
-	 * A clearer way to write this would be:
-	 *
-	 * to_be_doubled = tn->full_children;
-	 * not_to_be_doubled = tnode_child_length(tn) - tn->empty_children -
-	 *     tn->full_children;
-	 *
-	 * new_child_length = tnode_child_length(tn) * 2;
-	 *
-	 * new_fill_factor = 100 * (not_to_be_doubled + 2*to_be_doubled) /
-	 *      new_child_length;
-	 * if (new_fill_factor >= inflate_threshold)
-	 *
-	 * ...and so on, tho it would mess up the while () loop.
-	 *
-	 * anyway,
-	 * 100 * (not_to_be_doubled + 2*to_be_doubled) / new_child_length >=
-	 *      inflate_threshold
-	 *
-	 * avoid a division:
-	 * 100 * (not_to_be_doubled + 2*to_be_doubled) >=
-	 *      inflate_threshold * new_child_length
-	 *
-	 * expand not_to_be_doubled and to_be_doubled, and shorten:
-	 * 100 * (tnode_child_length(tn) - tn->empty_children +
-	 *    tn->full_children) >= inflate_threshold * new_child_length
-	 *
-	 * expand new_child_length:
-	 * 100 * (tnode_child_length(tn) - tn->empty_children +
-	 *    tn->full_children) >=
-	 *      inflate_threshold * tnode_child_length(tn) * 2
-	 *
-	 * shorten again:
-	 * 50 * (tn->full_children + tnode_child_length(tn) -
-	 *    tn->empty_children) >= inflate_threshold *
-	 *    tnode_child_length(tn)
-	 *
-	 */
+}
 
-	check_tnode(tn);
+static inline void put_child_root(struct key_vector *tp, t_key key,
+				  struct key_vector *n)
+{
+	if (IS_TRIE(tp))
+		rcu_assign_pointer(tp->tnode[0], n);
+	else
+		put_child(tp, get_index(key, tp), n);
+}
 
-	/* Keep root node larger  */
+static inline void tnode_free_init(struct key_vector *tn)
+{
+	tn_info(tn)->rcu.next = NULL;
+}
 
-	if (!node_parent((struct rt_trie_node *)tn)) {
-		inflate_threshold_use = inflate_threshold_root;
-		halve_threshold_use = halve_threshold_root;
-	} else {
-		inflate_threshold_use = inflate_threshold;
-		halve_threshold_use = halve_threshold;
-	}
+static inline void tnode_free_append(struct key_vector *tn,
+				     struct key_vector *n)
+{
+	tn_info(n)->rcu.next = tn_info(tn)->rcu.next;
+	tn_info(tn)->rcu.next = &tn_info(n)->rcu;
+}
 
-	max_work = MAX_WORK;
-	while ((tn->full_children > 0 &&  max_work-- &&
-		50 * (tn->full_children + tnode_child_length(tn)
-		      - tn->empty_children)
-		>= inflate_threshold_use * tnode_child_length(tn))) {
+static void tnode_free(struct key_vector *tn)
+{
+	struct callback_head *head = &tn_info(tn)->rcu;
 
-		old_tn = tn;
-		tn = inflate(t, tn);
+	while (head) {
+		head = head->next;
+		tnode_free_size += TNODE_SIZE(1ul << tn->bits);
+		node_free(tn);
 
-		if (IS_ERR(tn)) {
-			tn = old_tn;
-#ifdef CONFIG_IP_FIB_TRIE_STATS
-			t->stats.resize_node_skipped++;
-#endif
-			break;
-		}
+		tn = container_of(head, struct tnode, rcu)->kv;
 	}
 
-	check_tnode(tn);
-
-	/* Return if at least one inflate is run */
-	if (max_work != MAX_WORK)
-		return (struct rt_trie_node *) tn;
-
-	/*
-	 * Halve as long as the number of empty children in this
-	 * node is above threshold.
-	 */
-
-	max_work = MAX_WORK;
-	while (tn->bits > 1 &&  max_work-- &&
-	       100 * (tnode_child_length(tn) - tn->empty_children) <
-	       halve_threshold_use * tnode_child_length(tn)) {
-
-		old_tn = tn;
-		tn = halve(t, tn);
-		if (IS_ERR(tn)) {
-			tn = old_tn;
-#ifdef CONFIG_IP_FIB_TRIE_STATS
-			t->stats.resize_node_skipped++;
-#endif
-			break;
-		}
+	if (tnode_free_size >= PAGE_SIZE * sync_pages) {
+		tnode_free_size = 0;
+		synchronize_rcu();
 	}
+}
 
+static struct key_vector *replace(struct trie *t,
+				  struct key_vector *oldtnode,
+				  struct key_vector *tn)
+{
+	struct key_vector *tp = node_parent(oldtnode);
+	unsigned long i;
 
-	/* Only one child remains */
-	if (tn->empty_children == tnode_child_length(tn) - 1) {
-one_child:
-		for (i = 0; i < tnode_child_length(tn); i++) {
-			struct rt_trie_node *n;
-
-			n = rtnl_dereference(tn->child[i]);
-			if (!n)
-				continue;
-
-			/* compress one level */
+	/* setup the parent pointer out of and back into this node */
+	NODE_INIT_PARENT(tn, tp);
+	put_child_root(tp, tn->key, tn);
 
-			node_set_parent(n, NULL);
-			tnode_free_safe(tn);
-			return n;
-		}
-	}
-	return (struct rt_trie_node *) tn;
-}
+	/* update all of the child parent pointers */
+	update_children(tn);
 
+	/* all pointers should be clean so we are done */
+	tnode_free(oldtnode);
 
-static void tnode_clean_free(struct tnode *tn)
-{
-	int i;
-	struct tnode *tofree;
+	/* resize children now that oldtnode is freed */
+	for (i = child_length(tn); i;) {
+		struct key_vector *inode = get_child(tn, --i);
 
-	for (i = 0; i < tnode_child_length(tn); i++) {
-		tofree = (struct tnode *)rtnl_dereference(tn->child[i]);
-		if (tofree)
-			tnode_free(tofree);
+		/* resize child node */
+		if (tnode_full(tn, inode))
+			tn = resize(t, inode);
 	}
-	tnode_free(tn);
+
+	return tp;
 }
 
-static struct tnode *inflate(struct trie *t, struct tnode *tn)
+static struct key_vector *inflate(struct trie *t,
+				  struct key_vector *oldtnode)
 {
-	struct tnode *oldtnode = tn;
-	int olen = tnode_child_length(tn);
-	int i;
+	struct key_vector *tn;
+	unsigned long i;
+	t_key m;
 
 	pr_debug("In inflate\n");
 
-	tn = tnode_new(oldtnode->key, oldtnode->pos, oldtnode->bits + 1);
-
+	tn = tnode_new(oldtnode->key, oldtnode->pos - 1, oldtnode->bits + 1);
 	if (!tn)
-		return ERR_PTR(-ENOMEM);
-
-	/*
-	 * Preallocate and store tnodes before the actual work so we
-	 * don't get into an inconsistent state if memory allocation
-	 * fails. In case of failure we return the oldnode and  inflate
-	 * of tnode is ignored.
-	 */
-
-	for (i = 0; i < olen; i++) {
-		struct tnode *inode;
+		goto notnode;
 
-		inode = (struct tnode *) tnode_get_child(oldtnode, i);
-		if (inode &&
-		    IS_TNODE(inode) &&
-		    inode->pos == oldtnode->pos + oldtnode->bits &&
-		    inode->bits > 1) {
-			struct tnode *left, *right;
-			t_key m = ~0U << (KEYLENGTH - 1) >> inode->pos;
-
-			left = tnode_new(inode->key&(~m), inode->pos + 1,
-					 inode->bits - 1);
-			if (!left)
-				goto nomem;
-
-			right = tnode_new(inode->key|m, inode->pos + 1,
-					  inode->bits - 1);
-
-			if (!right) {
-				tnode_free(left);
-				goto nomem;
-			}
-
-			put_child(tn, 2*i, (struct rt_trie_node *) left);
-			put_child(tn, 2*i+1, (struct rt_trie_node *) right);
-		}
-	}
+	/* prepare oldtnode to be freed */
+	tnode_free_init(oldtnode);
 
-	for (i = 0; i < olen; i++) {
-		struct tnode *inode;
-		struct rt_trie_node *node = tnode_get_child(oldtnode, i);
-		struct tnode *left, *right;
-		int size, j;
+	/* Assemble all of the pointers in our cluster, in this case that
+	 * represents all of the pointers out of our allocated nodes that
+	 * point to existing tnodes and the links between our allocated
+	 * nodes.
+	 */
+	for (i = child_length(oldtnode), m = 1u << tn->pos; i;) {
+		struct key_vector *inode = get_child(oldtnode, --i);
+		struct key_vector *node0, *node1;
+		unsigned long j, k;
 
 		/* An empty child */
-		if (node == NULL)
+		if (!inode)
 			continue;
 
 		/* A leaf or an internal node with skipped bits */
-
-		if (IS_LEAF(node) || ((struct tnode *) node)->pos >
-		   tn->pos + tn->bits - 1) {
-			put_child(tn,
-				tkey_extract_bits(node->key, oldtnode->pos, oldtnode->bits + 1),
-				node);
+		if (!tnode_full(oldtnode, inode)) {
+			put_child(tn, get_index(inode->key, tn), inode);
 			continue;
 		}
 
-		/* An internal node with two children */
-		inode = (struct tnode *) node;
+		/* drop the node in the old tnode free list */
+		tnode_free_append(oldtnode, inode);
 
+		/* An internal node with two children */
 		if (inode->bits == 1) {
-			put_child(tn, 2*i, rtnl_dereference(inode->child[0]));
-			put_child(tn, 2*i+1, rtnl_dereference(inode->child[1]));
-
-			tnode_free_safe(inode);
+			put_child(tn, 2 * i + 1, get_child(inode, 1));
+			put_child(tn, 2 * i, get_child(inode, 0));
 			continue;
 		}
 
-		/* An internal node with more than two children */
-
 		/* We will replace this node 'inode' with two new
-		 * ones, 'left' and 'right', each with half of the
+		 * ones, 'node0' and 'node1', each with half of the
 		 * original children. The two new nodes will have
 		 * a position one bit further down the key and this
 		 * means that the "significant" part of their keys
 		 * (see the discussion near the top of this file)
 		 * will differ by one bit, which will be "0" in
-		 * left's key and "1" in right's key. Since we are
+		 * node0's key and "1" in node1's key. Since we are
 		 * moving the key position by one step, the bit that
 		 * we are moving away from - the bit at position
-		 * (inode->pos) - is the one that will differ between
-		 * left and right. So... we synthesize that bit in the
-		 * two  new keys.
-		 * The mask 'm' below will be a single "one" bit at
-		 * the position (inode->pos)
-		 */
-
-		/* Use the old key, but set the new significant
-		 *   bit to zero.
+		 * (tn->pos) - is the one that will differ between
+		 * node0 and node1. So... we synthesize that bit in the
+		 * two new keys.
 		 */
-
-		left = (struct tnode *) tnode_get_child(tn, 2*i);
-		put_child(tn, 2*i, NULL);
-
-		BUG_ON(!left);
-
-		right = (struct tnode *) tnode_get_child(tn, 2*i+1);
-		put_child(tn, 2*i+1, NULL);
-
-		BUG_ON(!right);
-
-		size = tnode_child_length(left);
-		for (j = 0; j < size; j++) {
-			put_child(left, j, rtnl_dereference(inode->child[j]));
-			put_child(right, j, rtnl_dereference(inode->child[j + size]));
+		node1 = tnode_new(inode->key | m, inode->pos, inode->bits - 1);
+		if (!node1)
+			goto nomem;
+		node0 = tnode_new(inode->key, inode->pos, inode->bits - 1);
+
+		tnode_free_append(tn, node1);
+		if (!node0)
+			goto nomem;
+		tnode_free_append(tn, node0);
+
+		/* populate child pointers in new nodes */
+		for (k = child_length(inode), j = k / 2; j;) {
+			put_child(node1, --j, get_child(inode, --k));
+			put_child(node0, j, get_child(inode, j));
+			put_child(node1, --j, get_child(inode, --k));
+			put_child(node0, j, get_child(inode, j));
 		}
-		put_child(tn, 2*i, resize(t, left));
-		put_child(tn, 2*i+1, resize(t, right));
 
-		tnode_free_safe(inode);
+		/* link new nodes to parent */
+		NODE_INIT_PARENT(node1, tn);
+		NODE_INIT_PARENT(node0, tn);
+
+		/* link parent to nodes */
+		put_child(tn, 2 * i + 1, node1);
+		put_child(tn, 2 * i, node0);
 	}
-	tnode_free_safe(oldtnode);
-	return tn;
+
+	/* setup the parent pointers into and out of this node */
+	return replace(t, oldtnode, tn);
 nomem:
-	tnode_clean_free(tn);
-	return ERR_PTR(-ENOMEM);
+	/* all pointers should be clean so we are done */
+	tnode_free(tn);
+notnode:
+	return NULL;
 }
 
-static struct tnode *halve(struct trie *t, struct tnode *tn)
+static struct key_vector *halve(struct trie *t,
+				struct key_vector *oldtnode)
 {
-	struct tnode *oldtnode = tn;
-	struct rt_trie_node *left, *right;
-	int i;
-	int olen = tnode_child_length(tn);
+	struct key_vector *tn;
+	unsigned long i;
 
 	pr_debug("In halve\n");
 
-	tn = tnode_new(oldtnode->key, oldtnode->pos, oldtnode->bits - 1);
-
+	tn = tnode_new(oldtnode->key, oldtnode->pos + 1, oldtnode->bits - 1);
 	if (!tn)
-		return ERR_PTR(-ENOMEM);
+		goto notnode;
+
+	/* prepare oldtnode to be freed */
+	tnode_free_init(oldtnode);
 
-	/*
-	 * Preallocate and store tnodes before the actual work so we
-	 * don't get into an inconsistent state if memory allocation
-	 * fails. In case of failure we return the oldnode and halve
-	 * of tnode is ignored.
+	/* Assemble all of the pointers in our cluster, in this case that
+	 * represents all of the pointers out of our allocated nodes that
+	 * point to existing tnodes and the links between our allocated
+	 * nodes.
 	 */
+	for (i = child_length(oldtnode); i;) {
+		struct key_vector *node1 = get_child(oldtnode, --i);
+		struct key_vector *node0 = get_child(oldtnode, --i);
+		struct key_vector *inode;
 
-	for (i = 0; i < olen; i += 2) {
-		left = tnode_get_child(oldtnode, i);
-		right = tnode_get_child(oldtnode, i+1);
+		/* At least one of the children is empty */
+		if (!node1 || !node0) {
+			put_child(tn, i / 2, node1 ? : node0);
+			continue;
+		}
 
 		/* Two nonempty children */
-		if (left && right) {
-			struct tnode *newn;
+		inode = tnode_new(node0->key, oldtnode->pos, 1);
+		if (!inode)
+			goto nomem;
+		tnode_free_append(tn, inode);
+
+		/* initialize pointers out of node */
+		put_child(inode, 1, node1);
+		put_child(inode, 0, node0);
+		NODE_INIT_PARENT(inode, tn);
+
+		/* link parent to node */
+		put_child(tn, i / 2, inode);
+	}
 
-			newn = tnode_new(left->key, tn->pos + tn->bits, 1);
+	/* setup the parent pointers into and out of this node */
+	return replace(t, oldtnode, tn);
+nomem:
+	/* all pointers should be clean so we are done */
+	tnode_free(tn);
+notnode:
+	return NULL;
+}
 
-			if (!newn)
-				goto nomem;
+static struct key_vector *collapse(struct trie *t,
+				   struct key_vector *oldtnode)
+{
+	struct key_vector *n, *tp;
+	unsigned long i;
 
-			put_child(tn, i/2, (struct rt_trie_node *)newn);
-		}
+	/* scan the tnode looking for that one child that might still exist */
+	for (n = NULL, i = child_length(oldtnode); !n && i;)
+		n = get_child(oldtnode, --i);
 
-	}
+	/* compress one level */
+	tp = node_parent(oldtnode);
+	put_child_root(tp, oldtnode->key, n);
+	node_set_parent(n, tp);
 
-	for (i = 0; i < olen; i += 2) {
-		struct tnode *newBinNode;
+	/* drop dead node */
+	node_free(oldtnode);
 
-		left = tnode_get_child(oldtnode, i);
-		right = tnode_get_child(oldtnode, i+1);
+	return tp;
+}
 
-		/* At least one of the children is empty */
-		if (left == NULL) {
-			if (right == NULL)    /* Both are empty */
-				continue;
-			put_child(tn, i/2, right);
-			continue;
-		}
+static unsigned char update_suffix(struct key_vector *tn)
+{
+	unsigned char slen = tn->pos;
+	unsigned long stride, i;
+
+	/* search though the list of children looking for nodes that might
+	 * have a suffix greater than the one we currently have.  This is
+	 * why we start with a stride of 2 since a stride of 1 would
+	 * represent the nodes with suffix length equal to tn->pos
+	 */
+	for (i = 0, stride = 0x2ul ; i < child_length(tn); i += stride) {
+		struct key_vector *n = get_child(tn, i);
 
-		if (right == NULL) {
-			put_child(tn, i/2, left);
+		if (!n || (n->slen <= slen))
 			continue;
-		}
 
-		/* Two nonempty children */
-		newBinNode = (struct tnode *) tnode_get_child(tn, i/2);
-		put_child(tn, i/2, NULL);
-		put_child(newBinNode, 0, left);
-		put_child(newBinNode, 1, right);
-		put_child(tn, i/2, resize(t, newBinNode));
+		/* update stride and slen based on new value */
+		stride <<= (n->slen - slen);
+		slen = n->slen;
+		i &= ~(stride - 1);
+
+		/* if slen covers all but the last bit we can stop here
+		 * there will be nothing longer than that since only node
+		 * 0 and 1 << (bits - 1) could have that as their suffix
+		 * length.
+		 */
+		if ((slen + 1) >= (tn->pos + tn->bits))
+			break;
 	}
-	tnode_free_safe(oldtnode);
-	return tn;
-nomem:
-	tnode_clean_free(tn);
-	return ERR_PTR(-ENOMEM);
-}
 
-/* readside must use rcu_read_lock currently dump routines
- via get_fa_head and dump */
+	tn->slen = slen;
 
-static struct leaf_info *find_leaf_info(struct leaf *l, int plen)
+	return slen;
+}
+
+/* From "Implementing a dynamic compressed trie" by Stefan Nilsson of
+ * the Helsinki University of Technology and Matti Tikkanen of Nokia
+ * Telecommunications, page 6:
+ * "A node is doubled if the ratio of non-empty children to all
+ * children in the *doubled* node is at least 'high'."
+ *
+ * 'high' in this instance is the variable 'inflate_threshold'. It
+ * is expressed as a percentage, so we multiply it with
+ * child_length() and instead of multiplying by 2 (since the
+ * child array will be doubled by inflate()) and multiplying
+ * the left-hand side by 100 (to handle the percentage thing) we
+ * multiply the left-hand side by 50.
+ *
+ * The left-hand side may look a bit weird: child_length(tn)
+ * - tn->empty_children is of course the number of non-null children
+ * in the current node. tn->full_children is the number of "full"
+ * children, that is non-null tnodes with a skip value of 0.
+ * All of those will be doubled in the resulting inflated tnode, so
+ * we just count them one extra time here.
+ *
+ * A clearer way to write this would be:
+ *
+ * to_be_doubled = tn->full_children;
+ * not_to_be_doubled = child_length(tn) - tn->empty_children -
+ *     tn->full_children;
+ *
+ * new_child_length = child_length(tn) * 2;
+ *
+ * new_fill_factor = 100 * (not_to_be_doubled + 2*to_be_doubled) /
+ *      new_child_length;
+ * if (new_fill_factor >= inflate_threshold)
+ *
+ * ...and so on, tho it would mess up the while () loop.
+ *
+ * anyway,
+ * 100 * (not_to_be_doubled + 2*to_be_doubled) / new_child_length >=
+ *      inflate_threshold
+ *
+ * avoid a division:
+ * 100 * (not_to_be_doubled + 2*to_be_doubled) >=
+ *      inflate_threshold * new_child_length
+ *
+ * expand not_to_be_doubled and to_be_doubled, and shorten:
+ * 100 * (child_length(tn) - tn->empty_children +
+ *    tn->full_children) >= inflate_threshold * new_child_length
+ *
+ * expand new_child_length:
+ * 100 * (child_length(tn) - tn->empty_children +
+ *    tn->full_children) >=
+ *      inflate_threshold * child_length(tn) * 2
+ *
+ * shorten again:
+ * 50 * (tn->full_children + child_length(tn) -
+ *    tn->empty_children) >= inflate_threshold *
+ *    child_length(tn)
+ *
+ */
+static inline bool should_inflate(struct key_vector *tp, struct key_vector *tn)
 {
-	struct hlist_head *head = &l->list;
-	struct leaf_info *li;
+	unsigned long used = child_length(tn);
+	unsigned long threshold = used;
 
-	hlist_for_each_entry_rcu(li, head, hlist)
-		if (li->plen == plen)
-			return li;
+	/* Keep root node larger */
+	threshold *= IS_TRIE(tp) ? inflate_threshold_root : inflate_threshold;
+	used -= tn_info(tn)->empty_children;
+	used += tn_info(tn)->full_children;
 
-	return NULL;
+	/* if bits == KEYLENGTH then pos = 0, and will fail below */
+
+	return (used > 1) && tn->pos && ((50 * used) >= threshold);
 }
 
-static inline struct list_head *get_fa_head(struct leaf *l, int plen)
+static inline bool should_halve(struct key_vector *tp, struct key_vector *tn)
 {
-	struct leaf_info *li = find_leaf_info(l, plen);
+	unsigned long used = child_length(tn);
+	unsigned long threshold = used;
 
-	if (!li)
-		return NULL;
+	/* Keep root node larger */
+	threshold *= IS_TRIE(tp) ? halve_threshold_root : halve_threshold;
+	used -= tn_info(tn)->empty_children;
+
+	/* if bits == KEYLENGTH then used = 100% on wrap, and will fail below */
 
-	return &li->falh;
+	return (used > 1) && (tn->bits > 1) && ((100 * used) < threshold);
 }
 
-static void insert_leaf_info(struct hlist_head *head, struct leaf_info *new)
+static inline bool should_collapse(struct key_vector *tn)
 {
-	struct leaf_info *li = NULL, *last = NULL;
+	unsigned long used = child_length(tn);
 
-	if (hlist_empty(head)) {
-		hlist_add_head_rcu(&new->hlist, head);
-	} else {
-		hlist_for_each_entry(li, head, hlist) {
-			if (new->plen > li->plen)
-				break;
+	used -= tn_info(tn)->empty_children;
 
-			last = li;
-		}
-		if (last)
-			hlist_add_behind_rcu(&new->hlist, &last->hlist);
-		else
-			hlist_add_before_rcu(&new->hlist, &li->hlist);
-	}
-}
+	/* account for bits == KEYLENGTH case */
+	if ((tn->bits == KEYLENGTH) && tn_info(tn)->full_children)
+		used -= KEY_MAX;
 
-/* rcu_read_lock needs to be hold by caller from readside */
+	/* One child or none, time to drop us from the trie */
+	return used < 2;
+}
 
-static struct leaf *
-fib_find_node(struct trie *t, u32 key)
+#define MAX_WORK 10
+static struct key_vector *resize(struct trie *t, struct key_vector *tn)
 {
-	int pos;
-	struct tnode *tn;
-	struct rt_trie_node *n;
-
-	pos = 0;
-	n = rcu_dereference_rtnl(t->trie);
+#ifdef CONFIG_IP_FIB_TRIE_STATS
+	struct trie_use_stats __percpu *stats = t->stats;
+#endif
+	struct key_vector *tp = node_parent(tn);
+	unsigned long cindex = get_index(tn->key, tp);
+	int max_work = MAX_WORK;
 
-	while (n != NULL &&  NODE_TYPE(n) == T_TNODE) {
-		tn = (struct tnode *) n;
+	pr_debug("In tnode_resize %p inflate_threshold=%d threshold=%d\n",
+		 tn, inflate_threshold, halve_threshold);
 
-		check_tnode(tn);
+	/* track the tnode via the pointer from the parent instead of
+	 * doing it ourselves.  This way we can let RCU fully do its
+	 * thing without us interfering
+	 */
+	BUG_ON(tn != get_child(tp, cindex));
 
-		if (tkey_sub_equals(tn->key, pos, tn->pos-pos, key)) {
-			pos = tn->pos + tn->bits;
-			n = tnode_get_child_rcu(tn,
-						tkey_extract_bits(key,
-								  tn->pos,
-								  tn->bits));
-		} else
+	/* Double as long as the resulting node has a number of
+	 * nonempty nodes that are above the threshold.
+	 */
+	while (should_inflate(tp, tn) && max_work) {
+		tp = inflate(t, tn);
+		if (!tp) {
+#ifdef CONFIG_IP_FIB_TRIE_STATS
+			this_cpu_inc(stats->resize_node_skipped);
+#endif
 			break;
+		}
+
+		max_work--;
+		tn = get_child(tp, cindex);
 	}
-	/* Case we have found a leaf. Compare prefixes */
 
-	if (n != NULL && IS_LEAF(n) && tkey_equals(key, n->key))
-		return (struct leaf *)n;
+	/* update parent in case inflate failed */
+	tp = node_parent(tn);
 
-	return NULL;
-}
+	/* Return if at least one inflate is run */
+	if (max_work != MAX_WORK)
+		return tp;
 
-static void trie_rebalance(struct trie *t, struct tnode *tn)
-{
-	int wasfull;
-	t_key cindex, key;
-	struct tnode *tp;
+	/* Halve as long as the number of empty children in this
+	 * node is above threshold.
+	 */
+	while (should_halve(tp, tn) && max_work) {
+		tp = halve(t, tn);
+		if (!tp) {
+#ifdef CONFIG_IP_FIB_TRIE_STATS
+			this_cpu_inc(stats->resize_node_skipped);
+#endif
+			break;
+		}
+
+		max_work--;
+		tn = get_child(tp, cindex);
+	}
 
-	key = tn->key;
+	/* Only one child remains */
+	if (should_collapse(tn))
+		return collapse(t, tn);
 
-	while (tn != NULL && (tp = node_parent((struct rt_trie_node *)tn)) != NULL) {
-		cindex = tkey_extract_bits(key, tp->pos, tp->bits);
-		wasfull = tnode_full(tp, tnode_get_child(tp, cindex));
-		tn = (struct tnode *)resize(t, tn);
+	/* update parent in case halve failed */
+	tp = node_parent(tn);
 
-		tnode_put_child_reorg(tp, cindex,
-				      (struct rt_trie_node *)tn, wasfull);
+	/* Return if at least one deflate was run */
+	if (max_work != MAX_WORK)
+		return tp;
 
-		tp = node_parent((struct rt_trie_node *) tn);
-		if (!tp)
-			rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn);
+	/* push the suffix length to the parent node */
+	if (tn->slen > tn->pos) {
+		unsigned char slen = update_suffix(tn);
 
-		tnode_free_flush();
-		if (!tp)
-			break;
-		tn = tp;
+		if (slen > tp->slen)
+			tp->slen = slen;
 	}
 
-	/* Handle last (top) tnode */
-	if (IS_TNODE(tn))
-		tn = (struct tnode *)resize(t, tn);
-
-	rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn);
-	tnode_free_flush();
+	return tp;
 }
 
-/* only used from updater-side */
-
-static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen)
+static void leaf_pull_suffix(struct key_vector *tp, struct key_vector *l)
 {
-	int pos, newpos;
-	struct tnode *tp = NULL, *tn = NULL;
-	struct rt_trie_node *n;
-	struct leaf *l;
-	int missbit;
-	struct list_head *fa_head = NULL;
-	struct leaf_info *li;
-	t_key cindex;
-
-	pos = 0;
-	n = rtnl_dereference(t->trie);
+	while ((tp->slen > tp->pos) && (tp->slen > l->slen)) {
+		if (update_suffix(tp) > l->slen)
+			break;
+		tp = node_parent(tp);
+	}
+}
 
-	/* If we point to NULL, stop. Either the tree is empty and we should
-	 * just put a new leaf in if, or we have reached an empty child slot,
-	 * and we should just put our new leaf in that.
-	 * If we point to a T_TNODE, check if it matches our key. Note that
-	 * a T_TNODE might be skipping any number of bits - its 'pos' need
-	 * not be the parent's 'pos'+'bits'!
-	 *
-	 * If it does match the current key, get pos/bits from it, extract
-	 * the index from our key, push the T_TNODE and walk the tree.
-	 *
-	 * If it doesn't, we have to replace it with a new T_TNODE.
-	 *
-	 * If we point to a T_LEAF, it might or might not have the same key
-	 * as we do. If it does, just change the value, update the T_LEAF's
-	 * value, and return it.
-	 * If it doesn't, we need to replace it with a T_TNODE.
+static void leaf_push_suffix(struct key_vector *tn, struct key_vector *l)
+{
+	/* if this is a new leaf then tn will be NULL and we can sort
+	 * out parent suffix lengths as a part of trie_rebalance
 	 */
+	while (tn->slen < l->slen) {
+		tn->slen = l->slen;
+		tn = node_parent(tn);
+	}
+}
 
-	while (n != NULL &&  NODE_TYPE(n) == T_TNODE) {
-		tn = (struct tnode *) n;
+/* rcu_read_lock needs to be hold by caller from readside */
+static struct key_vector *fib_find_node(struct trie *t,
+					struct key_vector **tp, u32 key)
+{
+	struct key_vector *pn, *n = t->kv;
+	unsigned long index = 0;
 
-		check_tnode(tn);
+	do {
+		pn = n;
+		n = get_child_rcu(n, index);
 
-		if (tkey_sub_equals(tn->key, pos, tn->pos-pos, key)) {
-			tp = tn;
-			pos = tn->pos + tn->bits;
-			n = tnode_get_child(tn,
-					    tkey_extract_bits(key,
-							      tn->pos,
-							      tn->bits));
+		if (!n)
+			break;
 
-			BUG_ON(n && node_parent(n) != tn);
-		} else
+		index = get_cindex(key, n);
+
+		/* This bit of code is a bit tricky but it combines multiple
+		 * checks into a single check.  The prefix consists of the
+		 * prefix plus zeros for the bits in the cindex. The index
+		 * is the difference between the key and this value.  From
+		 * this we can actually derive several pieces of data.
+		 *   if (index >= (1ul << bits))
+		 *     we have a mismatch in skip bits and failed
+		 *   else
+		 *     we know the value is cindex
+		 *
+		 * This check is safe even if bits == KEYLENGTH due to the
+		 * fact that we can only allocate a node with 32 bits if a
+		 * long is greater than 32 bits.
+		 */
+		if (index >= (1ul << n->bits)) {
+			n = NULL;
 			break;
-	}
+		}
 
-	/*
-	 * n  ----> NULL, LEAF or TNODE
-	 *
-	 * tp is n's (parent) ----> NULL or TNODE
-	 */
+		/* keep searching until we find a perfect match leaf or NULL */
+	} while (IS_TNODE(n));
 
-	BUG_ON(tp && IS_LEAF(tp));
+	*tp = pn;
 
-	/* Case 1: n is a leaf. Compare prefixes */
+	return n;
+}
 
-	if (n != NULL && IS_LEAF(n) && tkey_equals(key, n->key)) {
-		l = (struct leaf *) n;
-		li = leaf_info_new(plen);
+/* Return the first fib alias matching TOS with
+ * priority less than or equal to PRIO.
+ */
+static struct fib_alias *fib_find_alias(struct hlist_head *fah, u8 slen,
+					u8 tos, u32 prio, u32 tb_id)
+{
+	struct fib_alias *fa;
 
-		if (!li)
-			return NULL;
+	if (!fah)
+		return NULL;
 
-		fa_head = &li->falh;
-		insert_leaf_info(&l->list, li);
-		goto done;
+	hlist_for_each_entry(fa, fah, fa_list) {
+		if (fa->fa_slen < slen)
+			continue;
+		if (fa->fa_slen != slen)
+			break;
+		if (fa->tb_id > tb_id)
+			continue;
+		if (fa->tb_id != tb_id)
+			break;
+		if (fa->fa_tos > tos)
+			continue;
+		if (fa->fa_info->fib_priority >= prio || fa->fa_tos < tos)
+			return fa;
 	}
-	l = leaf_new();
 
+	return NULL;
+}
+
+static void trie_rebalance(struct trie *t, struct key_vector *tn)
+{
+	while (!IS_TRIE(tn))
+		tn = resize(t, tn);
+}
+
+static int fib_insert_node(struct trie *t, struct key_vector *tp,
+			   struct fib_alias *new, t_key key)
+{
+	struct key_vector *n, *l;
+
+	l = leaf_new(key, new);
 	if (!l)
-		return NULL;
+		goto noleaf;
 
-	l->key = key;
-	li = leaf_info_new(plen);
+	/* retrieve child from parent node */
+	n = get_child(tp, get_index(key, tp));
 
-	if (!li) {
-		free_leaf(l);
-		return NULL;
-	}
+	/* Case 2: n is a LEAF or a TNODE and the key doesn't match.
+	 *
+	 *  Add a new tnode here
+	 *  first tnode need some special handling
+	 *  leaves us in position for handling as case 3
+	 */
+	if (n) {
+		struct key_vector *tn;
 
-	fa_head = &li->falh;
-	insert_leaf_info(&l->list, li);
+		tn = tnode_new(key, __fls(key ^ n->key), 1);
+		if (!tn)
+			goto notnode;
 
-	if (t->trie && n == NULL) {
-		/* Case 2: n is NULL, and will just insert a new leaf */
+		/* initialize routes out of node */
+		NODE_INIT_PARENT(tn, tp);
+		put_child(tn, get_index(key, tn) ^ 1, n);
 
-		node_set_parent((struct rt_trie_node *)l, tp);
+		/* start adding routes into the node */
+		put_child_root(tp, key, tn);
+		node_set_parent(n, tn);
 
-		cindex = tkey_extract_bits(key, tp->pos, tp->bits);
-		put_child(tp, cindex, (struct rt_trie_node *)l);
-	} else {
-		/* Case 3: n is a LEAF or a TNODE and the key doesn't match. */
-		/*
-		 *  Add a new tnode here
-		 *  first tnode need some special handling
-		 */
+		/* parent now has a NULL spot where the leaf can go */
+		tp = tn;
+	}
 
-		if (n) {
-			pos = tp ? tp->pos+tp->bits : 0;
-			newpos = tkey_mismatch(key, pos, n->key);
-			tn = tnode_new(n->key, newpos, 1);
-		} else {
-			newpos = 0;
-			tn = tnode_new(key, newpos, 1); /* First tnode */
-		}
+	/* Case 3: n is NULL, and will just insert a new leaf */
+	NODE_INIT_PARENT(l, tp);
+	put_child_root(tp, key, l);
+	trie_rebalance(t, tp);
 
-		if (!tn) {
-			free_leaf_info(li);
-			free_leaf(l);
-			return NULL;
-		}
+	return 0;
+notnode:
+	node_free(l);
+noleaf:
+	return -ENOMEM;
+}
 
-		node_set_parent((struct rt_trie_node *)tn, tp);
+static int fib_insert_alias(struct trie *t, struct key_vector *tp,
+			    struct key_vector *l, struct fib_alias *new,
+			    struct fib_alias *fa, t_key key)
+{
+	if (!l)
+		return fib_insert_node(t, tp, new, key);
 
-		missbit = tkey_extract_bits(key, newpos, 1);
-		put_child(tn, missbit, (struct rt_trie_node *)l);
-		put_child(tn, 1-missbit, n);
+	if (fa) {
+		hlist_add_before_rcu(&new->fa_list, &fa->fa_list);
+	} else {
+		struct fib_alias *last;
 
-		if (tp) {
-			cindex = tkey_extract_bits(key, tp->pos, tp->bits);
-			put_child(tp, cindex, (struct rt_trie_node *)tn);
-		} else {
-			rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn);
-			tp = tn;
+		hlist_for_each_entry(last, &l->leaf, fa_list) {
+			if (new->fa_slen < last->fa_slen)
+				break;
+			if ((new->fa_slen == last->fa_slen) &&
+			    (new->tb_id > last->tb_id))
+				break;
+			fa = last;
 		}
-	}
 
-	if (tp && tp->pos + tp->bits > 32)
-		pr_warn("fib_trie tp=%p pos=%d, bits=%d, key=%0x plen=%d\n",
-			tp, tp->pos, tp->bits, key, plen);
+		if (fa)
+			hlist_add_behind_rcu(&new->fa_list, &fa->fa_list);
+		else
+			hlist_add_head_rcu(&new->fa_list, &l->leaf);
+	}
 
-	/* Rebalance the trie */
+	/* if we added to the tail node then we need to update slen */
+	if (l->slen < new->fa_slen) {
+		l->slen = new->fa_slen;
+		leaf_push_suffix(tp, l);
+	}
 
-	trie_rebalance(t, tp);
-done:
-	return fa_head;
+	return 0;
 }
 
-/*
- * Caller must hold RTNL.
- */
+/* Caller must hold RTNL. */
 int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
 {
-	struct trie *t = (struct trie *) tb->tb_data;
+	struct trie *t = (struct trie *)tb->tb_data;
 	struct fib_alias *fa, *new_fa;
-	struct list_head *fa_head = NULL;
+	struct key_vector *l, *tp;
 	struct fib_info *fi;
-	int plen = cfg->fc_dst_len;
+	u8 plen = cfg->fc_dst_len;
+	u8 slen = KEYLENGTH - plen;
 	u8 tos = cfg->fc_tos;
-	u32 key, mask;
+	u32 key;
 	int err;
-	struct leaf *l;
 
-	if (plen > 32)
+	if (plen > KEYLENGTH)
 		return -EINVAL;
 
 	key = ntohl(cfg->fc_dst);
 
 	pr_debug("Insert table=%u %08x/%d\n", tb->tb_id, key, plen);
 
-	mask = ntohl(inet_make_mask(plen));
-
-	if (key & ~mask)
+	if ((plen < KEYLENGTH) && (key << plen))
 		return -EINVAL;
 
-	key = key & mask;
-
 	fi = fib_create_info(cfg);
 	if (IS_ERR(fi)) {
 		err = PTR_ERR(fi);
 		goto err;
 	}
 
-	l = fib_find_node(t, key);
-	fa = NULL;
-
-	if (l) {
-		fa_head = get_fa_head(l, plen);
-		fa = fib_find_alias(fa_head, tos, fi->fib_priority);
-	}
+	l = fib_find_node(t, &tp, key);
+	fa = l ? fib_find_alias(&l->leaf, slen, tos, fi->fib_priority,
+				tb->tb_id) : NULL;
 
 	/* Now fa, if non-NULL, points to the first fib alias
 	 * with the same keys [prefix,tos,priority], if such key already
 	 * exists or to the node before which we will insert new one.
 	 *
 	 * If fa is NULL, we will need to allocate a new one and
-	 * insert to the head of f.
-	 *
-	 * If f is NULL, no fib node matched the destination key
-	 * and we need to allocate a new one of those as well.
+	 * insert to the tail of the section matching the suffix length
+	 * of the new alias.
 	 */
 
 	if (fa && fa->fa_tos == tos &&
@@ -1227,9 +1128,10 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
 		 */
 		fa_match = NULL;
 		fa_first = fa;
-		fa = list_entry(fa->fa_list.prev, struct fib_alias, fa_list);
-		list_for_each_entry_continue(fa, fa_head, fa_list) {
-			if (fa->fa_tos != tos)
+		hlist_for_each_entry_from(fa, fa_list) {
+			if ((fa->fa_slen != slen) ||
+			    (fa->tb_id != tb->tb_id) ||
+			    (fa->fa_tos != tos))
 				break;
 			if (fa->fa_info->fib_priority != fi->fib_priority)
 				break;
@@ -1252,7 +1154,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
 			}
 			err = -ENOBUFS;
 			new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL);
-			if (new_fa == NULL)
+			if (!new_fa)
 				goto out;
 
 			fi_drop = fa->fa_info;
@@ -1261,8 +1163,22 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
 			new_fa->fa_type = cfg->fc_type;
 			state = fa->fa_state;
 			new_fa->fa_state = state & ~FA_S_ACCESSED;
+			new_fa->fa_slen = fa->fa_slen;
+			new_fa->tb_id = tb->tb_id;
+
+			err = netdev_switch_fib_ipv4_add(key, plen, fi,
+							 new_fa->fa_tos,
+							 cfg->fc_type,
+							 cfg->fc_nlflags,
+							 tb->tb_id);
+			if (err) {
+				netdev_switch_fib_ipv4_abort(fi);
+				kmem_cache_free(fn_alias_kmem, new_fa);
+				goto out;
+			}
+
+			hlist_replace_rcu(&fa->fa_list, &new_fa->fa_list);
 
-			list_replace_rcu(&fa->fa_list, &new_fa->fa_list);
 			alias_free_mem_rcu(fa);
 
 			fib_release_info(fi_drop);
@@ -1289,37 +1205,42 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
 
 	err = -ENOBUFS;
 	new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL);
-	if (new_fa == NULL)
+	if (!new_fa)
 		goto out;
 
 	new_fa->fa_info = fi;
 	new_fa->fa_tos = tos;
 	new_fa->fa_type = cfg->fc_type;
 	new_fa->fa_state = 0;
-	/*
-	 * Insert new entry to the list.
-	 */
-
-	if (!fa_head) {
-		fa_head = fib_insert_node(t, key, plen);
-		if (unlikely(!fa_head)) {
-			err = -ENOMEM;
-			goto out_free_new_fa;
-		}
+	new_fa->fa_slen = slen;
+	new_fa->tb_id = tb->tb_id;
+
+	/* (Optionally) offload fib entry to switch hardware. */
+	err = netdev_switch_fib_ipv4_add(key, plen, fi, tos,
+					 cfg->fc_type,
+					 cfg->fc_nlflags,
+					 tb->tb_id);
+	if (err) {
+		netdev_switch_fib_ipv4_abort(fi);
+		goto out_free_new_fa;
 	}
 
+	/* Insert new entry to the list. */
+	err = fib_insert_alias(t, tp, l, new_fa, fa, key);
+	if (err)
+		goto out_sw_fib_del;
+
 	if (!plen)
 		tb->tb_num_default++;
 
-	list_add_tail_rcu(&new_fa->fa_list,
-			  (fa ? &fa->fa_list : fa_head));
-
 	rt_cache_flush(cfg->fc_nlinfo.nl_net);
-	rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id,
+	rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, new_fa->tb_id,
 		  &cfg->fc_nlinfo, 0);
 succeeded:
 	return 0;
 
+out_sw_fib_del:
+	netdev_switch_fib_ipv4_del(key, plen, fi, tos, cfg->fc_type, tb->tb_id);
 out_free_new_fa:
 	kmem_cache_free(fn_alias_kmem, new_fa);
 out:
@@ -1328,333 +1249,257 @@ err:
 	return err;
 }
 
-/* should be called with rcu_read_lock */
-static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l,
-		      t_key key,  const struct flowi4 *flp,
-		      struct fib_result *res, int fib_flags)
+static inline t_key prefix_mismatch(t_key key, struct key_vector *n)
 {
-	struct leaf_info *li;
-	struct hlist_head *hhead = &l->list;
-
-	hlist_for_each_entry_rcu(li, hhead, hlist) {
-		struct fib_alias *fa;
-
-		if (l->key != (key & li->mask_plen))
-			continue;
-
-		list_for_each_entry_rcu(fa, &li->falh, fa_list) {
-			struct fib_info *fi = fa->fa_info;
-			int nhsel, err;
+	t_key prefix = n->key;
 
-			if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos)
-				continue;
-			if (fi->fib_dead)
-				continue;
-			if (fa->fa_info->fib_scope < flp->flowi4_scope)
-				continue;
-			fib_alias_accessed(fa);
-			err = fib_props[fa->fa_type].error;
-			if (err) {
-#ifdef CONFIG_IP_FIB_TRIE_STATS
-				t->stats.semantic_match_passed++;
-#endif
-				return err;
-			}
-			if (fi->fib_flags & RTNH_F_DEAD)
-				continue;
-			for (nhsel = 0; nhsel < fi->fib_nhs; nhsel++) {
-				const struct fib_nh *nh = &fi->fib_nh[nhsel];
-
-				if (nh->nh_flags & RTNH_F_DEAD)
-					continue;
-				if (flp->flowi4_oif && flp->flowi4_oif != nh->nh_oif)
-					continue;
-
-#ifdef CONFIG_IP_FIB_TRIE_STATS
-				t->stats.semantic_match_passed++;
-#endif
-				res->prefixlen = li->plen;
-				res->nh_sel = nhsel;
-				res->type = fa->fa_type;
-				res->scope = fa->fa_info->fib_scope;
-				res->fi = fi;
-				res->table = tb;
-				res->fa_head = &li->falh;
-				if (!(fib_flags & FIB_LOOKUP_NOREF))
-					atomic_inc(&fi->fib_clntref);
-				return 0;
-			}
-		}
-
-#ifdef CONFIG_IP_FIB_TRIE_STATS
-		t->stats.semantic_match_miss++;
-#endif
-	}
-
-	return 1;
+	return (key ^ prefix) & (prefix | -prefix);
 }
 
+/* should be called with rcu_read_lock */
 int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp,
 		     struct fib_result *res, int fib_flags)
 {
 	struct trie *t = (struct trie *) tb->tb_data;
-	int ret;
-	struct rt_trie_node *n;
-	struct tnode *pn;
-	unsigned int pos, bits;
-	t_key key = ntohl(flp->daddr);
-	unsigned int chopped_off;
-	t_key cindex = 0;
-	unsigned int current_prefix_length = KEYLENGTH;
-	struct tnode *cn;
-	t_key pref_mismatch;
-
-	rcu_read_lock();
-
-	n = rcu_dereference(t->trie);
-	if (!n)
-		goto failed;
-
 #ifdef CONFIG_IP_FIB_TRIE_STATS
-	t->stats.gets++;
+	struct trie_use_stats __percpu *stats = t->stats;
 #endif
+	const t_key key = ntohl(flp->daddr);
+	struct key_vector *n, *pn;
+	struct fib_alias *fa;
+	unsigned long index;
+	t_key cindex;
 
-	/* Just a leaf? */
-	if (IS_LEAF(n)) {
-		ret = check_leaf(tb, t, (struct leaf *)n, key, flp, res, fib_flags);
-		goto found;
-	}
-
-	pn = (struct tnode *) n;
-	chopped_off = 0;
-
-	while (pn) {
-		pos = pn->pos;
-		bits = pn->bits;
-
-		if (!chopped_off)
-			cindex = tkey_extract_bits(mask_pfx(key, current_prefix_length),
-						   pos, bits);
+	pn = t->kv;
+	cindex = 0;
 
-		n = tnode_get_child_rcu(pn, cindex);
+	n = get_child_rcu(pn, cindex);
+	if (!n)
+		return -EAGAIN;
 
-		if (n == NULL) {
 #ifdef CONFIG_IP_FIB_TRIE_STATS
-			t->stats.null_node_hit++;
+	this_cpu_inc(stats->gets);
 #endif
-			goto backtrace;
-		}
 
-		if (IS_LEAF(n)) {
-			ret = check_leaf(tb, t, (struct leaf *)n, key, flp, res, fib_flags);
-			if (ret > 0)
-				goto backtrace;
-			goto found;
-		}
-
-		cn = (struct tnode *)n;
-
-		/*
-		 * It's a tnode, and we can do some extra checks here if we
-		 * like, to avoid descending into a dead-end branch.
-		 * This tnode is in the parent's child array at index
-		 * key[p_pos..p_pos+p_bits] but potentially with some bits
-		 * chopped off, so in reality the index may be just a
-		 * subprefix, padded with zero at the end.
-		 * We can also take a look at any skipped bits in this
-		 * tnode - everything up to p_pos is supposed to be ok,
-		 * and the non-chopped bits of the index (se previous
-		 * paragraph) are also guaranteed ok, but the rest is
-		 * considered unknown.
+	/* Step 1: Travel to the longest prefix match in the trie */
+	for (;;) {
+		index = get_cindex(key, n);
+
+		/* This bit of code is a bit tricky but it combines multiple
+		 * checks into a single check.  The prefix consists of the
+		 * prefix plus zeros for the "bits" in the prefix. The index
+		 * is the difference between the key and this value.  From
+		 * this we can actually derive several pieces of data.
+		 *   if (index >= (1ul << bits))
+		 *     we have a mismatch in skip bits and failed
+		 *   else
+		 *     we know the value is cindex
 		 *
-		 * The skipped bits are key[pos+bits..cn->pos].
-		 */
-
-		/* If current_prefix_length < pos+bits, we are already doing
-		 * actual prefix  matching, which means everything from
-		 * pos+(bits-chopped_off) onward must be zero along some
-		 * branch of this subtree - otherwise there is *no* valid
-		 * prefix present. Here we can only check the skipped
-		 * bits. Remember, since we have already indexed into the
-		 * parent's child array, we know that the bits we chopped of
-		 * *are* zero.
+		 * This check is safe even if bits == KEYLENGTH due to the
+		 * fact that we can only allocate a node with 32 bits if a
+		 * long is greater than 32 bits.
 		 */
+		if (index >= (1ul << n->bits))
+			break;
 
-		/* NOTA BENE: Checking only skipped bits
-		   for the new node here */
+		/* we have found a leaf. Prefixes have already been compared */
+		if (IS_LEAF(n))
+			goto found;
 
-		if (current_prefix_length < pos+bits) {
-			if (tkey_extract_bits(cn->key, current_prefix_length,
-						cn->pos - current_prefix_length)
-			    || !(cn->child[0]))
-				goto backtrace;
+		/* only record pn and cindex if we are going to be chopping
+		 * bits later.  Otherwise we are just wasting cycles.
+		 */
+		if (n->slen > n->pos) {
+			pn = n;
+			cindex = index;
 		}
 
-		/*
-		 * If chopped_off=0, the index is fully validated and we
-		 * only need to look at the skipped bits for this, the new,
-		 * tnode. What we actually want to do is to find out if
-		 * these skipped bits match our key perfectly, or if we will
-		 * have to count on finding a matching prefix further down,
-		 * because if we do, we would like to have some way of
-		 * verifying the existence of such a prefix at this point.
-		 */
+		n = get_child_rcu(n, index);
+		if (unlikely(!n))
+			goto backtrace;
+	}
 
-		/* The only thing we can do at this point is to verify that
-		 * any such matching prefix can indeed be a prefix to our
-		 * key, and if the bits in the node we are inspecting that
-		 * do not match our key are not ZERO, this cannot be true.
-		 * Thus, find out where there is a mismatch (before cn->pos)
-		 * and verify that all the mismatching bits are zero in the
-		 * new tnode's key.
-		 */
+	/* Step 2: Sort out leaves and begin backtracing for longest prefix */
+	for (;;) {
+		/* record the pointer where our next node pointer is stored */
+		struct key_vector __rcu **cptr = n->tnode;
 
-		/*
-		 * Note: We aren't very concerned about the piece of
-		 * the key that precede pn->pos+pn->bits, since these
-		 * have already been checked. The bits after cn->pos
-		 * aren't checked since these are by definition
-		 * "unknown" at this point. Thus, what we want to see
-		 * is if we are about to enter the "prefix matching"
-		 * state, and in that case verify that the skipped
-		 * bits that will prevail throughout this subtree are
-		 * zero, as they have to be if we are to find a
-		 * matching prefix.
+		/* This test verifies that none of the bits that differ
+		 * between the key and the prefix exist in the region of
+		 * the lsb and higher in the prefix.
 		 */
+		if (unlikely(prefix_mismatch(key, n)) || (n->slen == n->pos))
+			goto backtrace;
 
-		pref_mismatch = mask_pfx(cn->key ^ key, cn->pos);
+		/* exit out and process leaf */
+		if (unlikely(IS_LEAF(n)))
+			break;
 
-		/*
-		 * In short: If skipped bits in this node do not match
-		 * the search key, enter the "prefix matching"
-		 * state.directly.
+		/* Don't bother recording parent info.  Since we are in
+		 * prefix match mode we will have to come back to wherever
+		 * we started this traversal anyway
 		 */
-		if (pref_mismatch) {
-			/* fls(x) = __fls(x) + 1 */
-			int mp = KEYLENGTH - __fls(pref_mismatch) - 1;
-
-			if (tkey_extract_bits(cn->key, mp, cn->pos - mp) != 0)
-				goto backtrace;
 
-			if (current_prefix_length >= cn->pos)
-				current_prefix_length = mp;
-		}
+		while ((n = rcu_dereference(*cptr)) == NULL) {
+backtrace:
+#ifdef CONFIG_IP_FIB_TRIE_STATS
+			if (!n)
+				this_cpu_inc(stats->null_node_hit);
+#endif
+			/* If we are at cindex 0 there are no more bits for
+			 * us to strip at this level so we must ascend back
+			 * up one level to see if there are any more bits to
+			 * be stripped there.
+			 */
+			while (!cindex) {
+				t_key pkey = pn->key;
+
+				/* If we don't have a parent then there is
+				 * nothing for us to do as we do not have any
+				 * further nodes to parse.
+				 */
+				if (IS_TRIE(pn))
+					return -EAGAIN;
+#ifdef CONFIG_IP_FIB_TRIE_STATS
+				this_cpu_inc(stats->backtrack);
+#endif
+				/* Get Child's index */
+				pn = node_parent_rcu(pn);
+				cindex = get_index(pkey, pn);
+			}
 
-		pn = (struct tnode *)n; /* Descend */
-		chopped_off = 0;
-		continue;
+			/* strip the least significant bit from the cindex */
+			cindex &= cindex - 1;
 
-backtrace:
-		chopped_off++;
+			/* grab pointer for next child node */
+			cptr = &pn->tnode[cindex];
+		}
+	}
 
-		/* As zero don't change the child key (cindex) */
-		while ((chopped_off <= pn->bits)
-		       && !(cindex & (1<<(chopped_off-1))))
-			chopped_off++;
+found:
+	/* this line carries forward the xor from earlier in the function */
+	index = key ^ n->key;
 
-		/* Decrease current_... with bits chopped off */
-		if (current_prefix_length > pn->pos + pn->bits - chopped_off)
-			current_prefix_length = pn->pos + pn->bits
-				- chopped_off;
+	/* Step 3: Process the leaf, if that fails fall back to backtracing */
+	hlist_for_each_entry_rcu(fa, &n->leaf, fa_list) {
+		struct fib_info *fi = fa->fa_info;
+		int nhsel, err;
 
-		/*
-		 * Either we do the actual chop off according or if we have
-		 * chopped off all bits in this tnode walk up to our parent.
-		 */
+		if ((index >= (1ul << fa->fa_slen)) &&
+		    ((BITS_PER_LONG > KEYLENGTH) || (fa->fa_slen != KEYLENGTH)))
+			continue;
+		if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos)
+			continue;
+		if (fi->fib_dead)
+			continue;
+		if (fa->fa_info->fib_scope < flp->flowi4_scope)
+			continue;
+		fib_alias_accessed(fa);
+		err = fib_props[fa->fa_type].error;
+		if (unlikely(err < 0)) {
+#ifdef CONFIG_IP_FIB_TRIE_STATS
+			this_cpu_inc(stats->semantic_match_passed);
+#endif
+			return err;
+		}
+		if (fi->fib_flags & RTNH_F_DEAD)
+			continue;
+		for (nhsel = 0; nhsel < fi->fib_nhs; nhsel++) {
+			const struct fib_nh *nh = &fi->fib_nh[nhsel];
 
-		if (chopped_off <= pn->bits) {
-			cindex &= ~(1 << (chopped_off-1));
-		} else {
-			struct tnode *parent = node_parent_rcu((struct rt_trie_node *) pn);
-			if (!parent)
-				goto failed;
+			if (nh->nh_flags & RTNH_F_DEAD)
+				continue;
+			if (flp->flowi4_oif && flp->flowi4_oif != nh->nh_oif)
+				continue;
 
-			/* Get Child's index */
-			cindex = tkey_extract_bits(pn->key, parent->pos, parent->bits);
-			pn = parent;
-			chopped_off = 0;
+			if (!(fib_flags & FIB_LOOKUP_NOREF))
+				atomic_inc(&fi->fib_clntref);
 
+			res->prefixlen = KEYLENGTH - fa->fa_slen;
+			res->nh_sel = nhsel;
+			res->type = fa->fa_type;
+			res->scope = fi->fib_scope;
+			res->fi = fi;
+			res->table = tb;
+			res->fa_head = &n->leaf;
 #ifdef CONFIG_IP_FIB_TRIE_STATS
-			t->stats.backtrack++;
+			this_cpu_inc(stats->semantic_match_passed);
 #endif
-			goto backtrace;
+			return err;
 		}
 	}
-failed:
-	ret = 1;
-found:
-	rcu_read_unlock();
-	return ret;
+#ifdef CONFIG_IP_FIB_TRIE_STATS
+	this_cpu_inc(stats->semantic_match_miss);
+#endif
+	goto backtrace;
 }
 EXPORT_SYMBOL_GPL(fib_table_lookup);
 
-/*
- * Remove the leaf and return parent.
- */
-static void trie_leaf_remove(struct trie *t, struct leaf *l)
+static void fib_remove_alias(struct trie *t, struct key_vector *tp,
+			     struct key_vector *l, struct fib_alias *old)
 {
-	struct tnode *tp = node_parent((struct rt_trie_node *) l);
+	/* record the location of the previous list_info entry */
+	struct hlist_node **pprev = old->fa_list.pprev;
+	struct fib_alias *fa = hlist_entry(pprev, typeof(*fa), fa_list.next);
 
-	pr_debug("entering trie_leaf_remove(%p)\n", l);
+	/* remove the fib_alias from the list */
+	hlist_del_rcu(&old->fa_list);
 
-	if (tp) {
-		t_key cindex = tkey_extract_bits(l->key, tp->pos, tp->bits);
-		put_child(tp, cindex, NULL);
+	/* if we emptied the list this leaf will be freed and we can sort
+	 * out parent suffix lengths as a part of trie_rebalance
+	 */
+	if (hlist_empty(&l->leaf)) {
+		put_child_root(tp, l->key, NULL);
+		node_free(l);
 		trie_rebalance(t, tp);
-	} else
-		RCU_INIT_POINTER(t->trie, NULL);
+		return;
+	}
+
+	/* only access fa if it is pointing at the last valid hlist_node */
+	if (*pprev)
+		return;
 
-	free_leaf(l);
+	/* update the trie with the latest suffix length */
+	l->slen = fa->fa_slen;
+	leaf_pull_suffix(tp, l);
 }
 
-/*
- * Caller must hold RTNL.
- */
+/* Caller must hold RTNL. */
 int fib_table_delete(struct fib_table *tb, struct fib_config *cfg)
 {
 	struct trie *t = (struct trie *) tb->tb_data;
-	u32 key, mask;
-	int plen = cfg->fc_dst_len;
-	u8 tos = cfg->fc_tos;
 	struct fib_alias *fa, *fa_to_delete;
-	struct list_head *fa_head;
-	struct leaf *l;
-	struct leaf_info *li;
+	struct key_vector *l, *tp;
+	u8 plen = cfg->fc_dst_len;
+	u8 slen = KEYLENGTH - plen;
+	u8 tos = cfg->fc_tos;
+	u32 key;
 
-	if (plen > 32)
+	if (plen > KEYLENGTH)
 		return -EINVAL;
 
 	key = ntohl(cfg->fc_dst);
-	mask = ntohl(inet_make_mask(plen));
 
-	if (key & ~mask)
+	if ((plen < KEYLENGTH) && (key << plen))
 		return -EINVAL;
 
-	key = key & mask;
-	l = fib_find_node(t, key);
-
+	l = fib_find_node(t, &tp, key);
 	if (!l)
 		return -ESRCH;
 
-	li = find_leaf_info(l, plen);
-
-	if (!li)
-		return -ESRCH;
-
-	fa_head = &li->falh;
-	fa = fib_find_alias(fa_head, tos, 0);
-
+	fa = fib_find_alias(&l->leaf, slen, tos, 0, tb->tb_id);
 	if (!fa)
 		return -ESRCH;
 
 	pr_debug("Deleting %08x/%d tos=%d t=%p\n", key, plen, tos, t);
 
 	fa_to_delete = NULL;
-	fa = list_entry(fa->fa_list.prev, struct fib_alias, fa_list);
-	list_for_each_entry_continue(fa, fa_head, fa_list) {
+	hlist_for_each_entry_from(fa, fa_list) {
 		struct fib_info *fi = fa->fa_info;
 
-		if (fa->fa_tos != tos)
+		if ((fa->fa_slen != slen) ||
+		    (fa->tb_id != tb->tb_id) ||
+		    (fa->fa_tos != tos))
 			break;
 
 		if ((!cfg->fc_type || fa->fa_type == cfg->fc_type) &&
@@ -1673,225 +1518,397 @@ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg)
 	if (!fa_to_delete)
 		return -ESRCH;
 
-	fa = fa_to_delete;
-	rtmsg_fib(RTM_DELROUTE, htonl(key), fa, plen, tb->tb_id,
-		  &cfg->fc_nlinfo, 0);
+	netdev_switch_fib_ipv4_del(key, plen, fa_to_delete->fa_info, tos,
+				   cfg->fc_type, tb->tb_id);
 
-	list_del_rcu(&fa->fa_list);
+	rtmsg_fib(RTM_DELROUTE, htonl(key), fa_to_delete, plen, tb->tb_id,
+		  &cfg->fc_nlinfo, 0);
 
 	if (!plen)
 		tb->tb_num_default--;
 
-	if (list_empty(fa_head)) {
-		hlist_del_rcu(&li->hlist);
-		free_leaf_info(li);
-	}
-
-	if (hlist_empty(&l->list))
-		trie_leaf_remove(t, l);
+	fib_remove_alias(t, tp, l, fa_to_delete);
 
-	if (fa->fa_state & FA_S_ACCESSED)
+	if (fa_to_delete->fa_state & FA_S_ACCESSED)
 		rt_cache_flush(cfg->fc_nlinfo.nl_net);
 
-	fib_release_info(fa->fa_info);
-	alias_free_mem_rcu(fa);
+	fib_release_info(fa_to_delete->fa_info);
+	alias_free_mem_rcu(fa_to_delete);
 	return 0;
 }
 
-static int trie_flush_list(struct list_head *head)
+/* Scan for the next leaf starting at the provided key value */
+static struct key_vector *leaf_walk_rcu(struct key_vector **tn, t_key key)
 {
-	struct fib_alias *fa, *fa_node;
-	int found = 0;
+	struct key_vector *pn, *n = *tn;
+	unsigned long cindex;
 
-	list_for_each_entry_safe(fa, fa_node, head, fa_list) {
-		struct fib_info *fi = fa->fa_info;
+	/* this loop is meant to try and find the key in the trie */
+	do {
+		/* record parent and next child index */
+		pn = n;
+		cindex = key ? get_index(key, pn) : 0;
 
-		if (fi && (fi->fib_flags & RTNH_F_DEAD)) {
-			list_del_rcu(&fa->fa_list);
-			fib_release_info(fa->fa_info);
-			alias_free_mem_rcu(fa);
-			found++;
+		if (cindex >> pn->bits)
+			break;
+
+		/* descend into the next child */
+		n = get_child_rcu(pn, cindex++);
+		if (!n)
+			break;
+
+		/* guarantee forward progress on the keys */
+		if (IS_LEAF(n) && (n->key >= key))
+			goto found;
+	} while (IS_TNODE(n));
+
+	/* this loop will search for the next leaf with a greater key */
+	while (!IS_TRIE(pn)) {
+		/* if we exhausted the parent node we will need to climb */
+		if (cindex >= (1ul << pn->bits)) {
+			t_key pkey = pn->key;
+
+			pn = node_parent_rcu(pn);
+			cindex = get_index(pkey, pn) + 1;
+			continue;
 		}
+
+		/* grab the next available node */
+		n = get_child_rcu(pn, cindex++);
+		if (!n)
+			continue;
+
+		/* no need to compare keys since we bumped the index */
+		if (IS_LEAF(n))
+			goto found;
+
+		/* Rescan start scanning in new node */
+		pn = n;
+		cindex = 0;
 	}
-	return found;
+
+	*tn = pn;
+	return NULL; /* Root of trie */
+found:
+	/* if we are at the limit for keys just return NULL for the tnode */
+	*tn = pn;
+	return n;
 }
 
-static int trie_flush_leaf(struct leaf *l)
+static void fib_trie_free(struct fib_table *tb)
 {
-	int found = 0;
-	struct hlist_head *lih = &l->list;
+	struct trie *t = (struct trie *)tb->tb_data;
+	struct key_vector *pn = t->kv;
+	unsigned long cindex = 1;
 	struct hlist_node *tmp;
-	struct leaf_info *li = NULL;
+	struct fib_alias *fa;
+
+	/* walk trie in reverse order and free everything */
+	for (;;) {
+		struct key_vector *n;
+
+		if (!(cindex--)) {
+			t_key pkey = pn->key;
+
+			if (IS_TRIE(pn))
+				break;
+
+			n = pn;
+			pn = node_parent(pn);
+
+			/* drop emptied tnode */
+			put_child_root(pn, n->key, NULL);
+			node_free(n);
 
-	hlist_for_each_entry_safe(li, tmp, lih, hlist) {
-		found += trie_flush_list(&li->falh);
+			cindex = get_index(pkey, pn);
 
-		if (list_empty(&li->falh)) {
-			hlist_del_rcu(&li->hlist);
-			free_leaf_info(li);
+			continue;
+		}
+
+		/* grab the next available node */
+		n = get_child(pn, cindex);
+		if (!n)
+			continue;
+
+		if (IS_TNODE(n)) {
+			/* record pn and cindex for leaf walking */
+			pn = n;
+			cindex = 1ul << n->bits;
+
+			continue;
+		}
+
+		hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) {
+			hlist_del_rcu(&fa->fa_list);
+			alias_free_mem_rcu(fa);
 		}
+
+		put_child_root(pn, n->key, NULL);
+		node_free(n);
 	}
-	return found;
+
+#ifdef CONFIG_IP_FIB_TRIE_STATS
+	free_percpu(t->stats);
+#endif
+	kfree(tb);
 }
 
-/*
- * Scan for the next right leaf starting at node p->child[idx]
- * Since we have back pointer, no recursion necessary.
- */
-static struct leaf *leaf_walk_rcu(struct tnode *p, struct rt_trie_node *c)
+struct fib_table *fib_trie_unmerge(struct fib_table *oldtb)
 {
-	do {
-		t_key idx;
+	struct trie *ot = (struct trie *)oldtb->tb_data;
+	struct key_vector *l, *tp = ot->kv;
+	struct fib_table *local_tb;
+	struct fib_alias *fa;
+	struct trie *lt;
+	t_key key = 0;
 
-		if (c)
-			idx = tkey_extract_bits(c->key, p->pos, p->bits) + 1;
-		else
-			idx = 0;
+	if (oldtb->tb_data == oldtb->__data)
+		return oldtb;
+
+	local_tb = fib_trie_table(RT_TABLE_LOCAL, NULL);
+	if (!local_tb)
+		return NULL;
 
-		while (idx < 1u << p->bits) {
-			c = tnode_get_child_rcu(p, idx++);
-			if (!c)
+	lt = (struct trie *)local_tb->tb_data;
+
+	while ((l = leaf_walk_rcu(&tp, key)) != NULL) {
+		struct key_vector *local_l = NULL, *local_tp;
+
+		hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) {
+			struct fib_alias *new_fa;
+
+			if (local_tb->tb_id != fa->tb_id)
 				continue;
 
-			if (IS_LEAF(c))
-				return (struct leaf *) c;
+			/* clone fa for new local table */
+			new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL);
+			if (!new_fa)
+				goto out;
+
+			memcpy(new_fa, fa, sizeof(*fa));
 
-			/* Rescan start scanning in new node */
-			p = (struct tnode *) c;
-			idx = 0;
+			/* insert clone into table */
+			if (!local_l)
+				local_l = fib_find_node(lt, &local_tp, l->key);
+
+			if (fib_insert_alias(lt, local_tp, local_l, new_fa,
+					     NULL, l->key))
+				goto out;
 		}
 
-		/* Node empty, walk back up to parent */
-		c = (struct rt_trie_node *) p;
-	} while ((p = node_parent_rcu(c)) != NULL);
+		/* stop loop if key wrapped back to 0 */
+		key = l->key + 1;
+		if (key < l->key)
+			break;
+	}
 
-	return NULL; /* Root of trie */
+	return local_tb;
+out:
+	fib_trie_free(local_tb);
+
+	return NULL;
 }
 
-static struct leaf *trie_firstleaf(struct trie *t)
+/* Caller must hold RTNL */
+void fib_table_flush_external(struct fib_table *tb)
 {
-	struct tnode *n = (struct tnode *)rcu_dereference_rtnl(t->trie);
+	struct trie *t = (struct trie *)tb->tb_data;
+	struct key_vector *pn = t->kv;
+	unsigned long cindex = 1;
+	struct hlist_node *tmp;
+	struct fib_alias *fa;
 
-	if (!n)
-		return NULL;
+	/* walk trie in reverse order */
+	for (;;) {
+		unsigned char slen = 0;
+		struct key_vector *n;
 
-	if (IS_LEAF(n))          /* trie is just a leaf */
-		return (struct leaf *) n;
+		if (!(cindex--)) {
+			t_key pkey = pn->key;
 
-	return leaf_walk_rcu(n, NULL);
-}
+			/* cannot resize the trie vector */
+			if (IS_TRIE(pn))
+				break;
 
-static struct leaf *trie_nextleaf(struct leaf *l)
-{
-	struct rt_trie_node *c = (struct rt_trie_node *) l;
-	struct tnode *p = node_parent_rcu(c);
+			/* resize completed node */
+			pn = resize(t, pn);
+			cindex = get_index(pkey, pn);
 
-	if (!p)
-		return NULL;	/* trie with just one leaf */
+			continue;
+		}
 
-	return leaf_walk_rcu(p, c);
-}
+		/* grab the next available node */
+		n = get_child(pn, cindex);
+		if (!n)
+			continue;
 
-static struct leaf *trie_leafindex(struct trie *t, int index)
-{
-	struct leaf *l = trie_firstleaf(t);
+		if (IS_TNODE(n)) {
+			/* record pn and cindex for leaf walking */
+			pn = n;
+			cindex = 1ul << n->bits;
 
-	while (l && index-- > 0)
-		l = trie_nextleaf(l);
+			continue;
+		}
 
-	return l;
-}
+		hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) {
+			struct fib_info *fi = fa->fa_info;
+
+			/* if alias was cloned to local then we just
+			 * need to remove the local copy from main
+			 */
+			if (tb->tb_id != fa->tb_id) {
+				hlist_del_rcu(&fa->fa_list);
+				alias_free_mem_rcu(fa);
+				continue;
+			}
 
+			/* record local slen */
+			slen = fa->fa_slen;
 
-/*
- * Caller must hold RTNL.
- */
+			if (!fi || !(fi->fib_flags & RTNH_F_OFFLOAD))
+				continue;
+
+			netdev_switch_fib_ipv4_del(n->key,
+						   KEYLENGTH - fa->fa_slen,
+						   fi, fa->fa_tos,
+						   fa->fa_type, tb->tb_id);
+		}
+
+		/* update leaf slen */
+		n->slen = slen;
+
+		if (hlist_empty(&n->leaf)) {
+			put_child_root(pn, n->key, NULL);
+			node_free(n);
+		} else {
+			leaf_pull_suffix(pn, n);
+		}
+	}
+}
+
+/* Caller must hold RTNL. */
 int fib_table_flush(struct fib_table *tb)
 {
-	struct trie *t = (struct trie *) tb->tb_data;
-	struct leaf *l, *ll = NULL;
+	struct trie *t = (struct trie *)tb->tb_data;
+	struct key_vector *pn = t->kv;
+	unsigned long cindex = 1;
+	struct hlist_node *tmp;
+	struct fib_alias *fa;
 	int found = 0;
 
-	for (l = trie_firstleaf(t); l; l = trie_nextleaf(l)) {
-		found += trie_flush_leaf(l);
+	/* walk trie in reverse order */
+	for (;;) {
+		unsigned char slen = 0;
+		struct key_vector *n;
 
-		if (ll && hlist_empty(&ll->list))
-			trie_leaf_remove(t, ll);
-		ll = l;
-	}
+		if (!(cindex--)) {
+			t_key pkey = pn->key;
+
+			/* cannot resize the trie vector */
+			if (IS_TRIE(pn))
+				break;
+
+			/* resize completed node */
+			pn = resize(t, pn);
+			cindex = get_index(pkey, pn);
+
+			continue;
+		}
+
+		/* grab the next available node */
+		n = get_child(pn, cindex);
+		if (!n)
+			continue;
+
+		if (IS_TNODE(n)) {
+			/* record pn and cindex for leaf walking */
+			pn = n;
+			cindex = 1ul << n->bits;
 
-	if (ll && hlist_empty(&ll->list))
-		trie_leaf_remove(t, ll);
+			continue;
+		}
+
+		hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) {
+			struct fib_info *fi = fa->fa_info;
+
+			if (!fi || !(fi->fib_flags & RTNH_F_DEAD)) {
+				slen = fa->fa_slen;
+				continue;
+			}
+
+			netdev_switch_fib_ipv4_del(n->key,
+						   KEYLENGTH - fa->fa_slen,
+						   fi, fa->fa_tos,
+						   fa->fa_type, tb->tb_id);
+			hlist_del_rcu(&fa->fa_list);
+			fib_release_info(fa->fa_info);
+			alias_free_mem_rcu(fa);
+			found++;
+		}
+
+		/* update leaf slen */
+		n->slen = slen;
+
+		if (hlist_empty(&n->leaf)) {
+			put_child_root(pn, n->key, NULL);
+			node_free(n);
+		} else {
+			leaf_pull_suffix(pn, n);
+		}
+	}
 
 	pr_debug("trie_flush found=%d\n", found);
 	return found;
 }
 
-void fib_free_table(struct fib_table *tb)
+static void __trie_free_rcu(struct rcu_head *head)
 {
+	struct fib_table *tb = container_of(head, struct fib_table, rcu);
+#ifdef CONFIG_IP_FIB_TRIE_STATS
+	struct trie *t = (struct trie *)tb->tb_data;
+
+	if (tb->tb_data == tb->__data)
+		free_percpu(t->stats);
+#endif /* CONFIG_IP_FIB_TRIE_STATS */
 	kfree(tb);
 }
 
-static int fn_trie_dump_fa(t_key key, int plen, struct list_head *fah,
-			   struct fib_table *tb,
-			   struct sk_buff *skb, struct netlink_callback *cb)
+void fib_free_table(struct fib_table *tb)
 {
-	int i, s_i;
+	call_rcu(&tb->rcu, __trie_free_rcu);
+}
+
+static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb,
+			     struct sk_buff *skb, struct netlink_callback *cb)
+{
+	__be32 xkey = htonl(l->key);
 	struct fib_alias *fa;
-	__be32 xkey = htonl(key);
+	int i, s_i;
 
-	s_i = cb->args[5];
+	s_i = cb->args[4];
 	i = 0;
 
 	/* rcu_read_lock is hold by caller */
-
-	list_for_each_entry_rcu(fa, fah, fa_list) {
+	hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) {
 		if (i < s_i) {
 			i++;
 			continue;
 		}
 
+		if (tb->tb_id != fa->tb_id) {
+			i++;
+			continue;
+		}
+
 		if (fib_dump_info(skb, NETLINK_CB(cb->skb).portid,
 				  cb->nlh->nlmsg_seq,
 				  RTM_NEWROUTE,
 				  tb->tb_id,
 				  fa->fa_type,
 				  xkey,
-				  plen,
+				  KEYLENGTH - fa->fa_slen,
 				  fa->fa_tos,
 				  fa->fa_info, NLM_F_MULTI) < 0) {
-			cb->args[5] = i;
-			return -1;
-		}
-		i++;
-	}
-	cb->args[5] = i;
-	return skb->len;
-}
-
-static int fn_trie_dump_leaf(struct leaf *l, struct fib_table *tb,
-			struct sk_buff *skb, struct netlink_callback *cb)
-{
-	struct leaf_info *li;
-	int i, s_i;
-
-	s_i = cb->args[4];
-	i = 0;
-
-	/* rcu_read_lock is hold by caller */
-	hlist_for_each_entry_rcu(li, &l->list, hlist) {
-		if (i < s_i) {
-			i++;
-			continue;
-		}
-
-		if (i > s_i)
-			cb->args[5] = 0;
-
-		if (list_empty(&li->falh))
-			continue;
-
-		if (fn_trie_dump_fa(l->key, li->plen, &li->falh, tb, skb, cb) < 0) {
 			cb->args[4] = i;
 			return -1;
 		}
@@ -1902,44 +1919,38 @@ static int fn_trie_dump_leaf(struct leaf *l, struct fib_table *tb,
 	return skb->len;
 }
 
+/* rcu_read_lock needs to be hold by caller from readside */
 int fib_table_dump(struct fib_table *tb, struct sk_buff *skb,
 		   struct netlink_callback *cb)
 {
-	struct leaf *l;
-	struct trie *t = (struct trie *) tb->tb_data;
-	t_key key = cb->args[2];
-	int count = cb->args[3];
-
-	rcu_read_lock();
+	struct trie *t = (struct trie *)tb->tb_data;
+	struct key_vector *l, *tp = t->kv;
 	/* Dump starting at last key.
 	 * Note: 0.0.0.0/0 (ie default) is first key.
 	 */
-	if (count == 0)
-		l = trie_firstleaf(t);
-	else {
-		/* Normally, continue from last key, but if that is missing
-		 * fallback to using slow rescan
-		 */
-		l = fib_find_node(t, key);
-		if (!l)
-			l = trie_leafindex(t, count);
-	}
+	int count = cb->args[2];
+	t_key key = cb->args[3];
 
-	while (l) {
-		cb->args[2] = l->key;
+	while ((l = leaf_walk_rcu(&tp, key)) != NULL) {
 		if (fn_trie_dump_leaf(l, tb, skb, cb) < 0) {
-			cb->args[3] = count;
-			rcu_read_unlock();
+			cb->args[3] = key;
+			cb->args[2] = count;
 			return -1;
 		}
 
 		++count;
-		l = trie_nextleaf(l);
+		key = l->key + 1;
+
 		memset(&cb->args[4], 0,
 		       sizeof(cb->args) - 4*sizeof(cb->args[0]));
+
+		/* stop loop if key wrapped back to 0 */
+		if (key < l->key)
+			break;
 	}
-	cb->args[3] = count;
-	rcu_read_unlock();
+
+	cb->args[3] = key;
+	cb->args[2] = count;
 
 	return skb->len;
 }
@@ -1951,28 +1962,41 @@ void __init fib_trie_init(void)
 					  0, SLAB_PANIC, NULL);
 
 	trie_leaf_kmem = kmem_cache_create("ip_fib_trie",
-					   max(sizeof(struct leaf),
-					       sizeof(struct leaf_info)),
+					   LEAF_SIZE,
 					   0, SLAB_PANIC, NULL);
 }
 
-
-struct fib_table *fib_trie_table(u32 id)
+struct fib_table *fib_trie_table(u32 id, struct fib_table *alias)
 {
 	struct fib_table *tb;
 	struct trie *t;
+	size_t sz = sizeof(*tb);
+
+	if (!alias)
+		sz += sizeof(struct trie);
 
-	tb = kmalloc(sizeof(struct fib_table) + sizeof(struct trie),
-		     GFP_KERNEL);
-	if (tb == NULL)
+	tb = kzalloc(sz, GFP_KERNEL);
+	if (!tb)
 		return NULL;
 
 	tb->tb_id = id;
 	tb->tb_default = -1;
 	tb->tb_num_default = 0;
+	tb->tb_data = (alias ? alias->__data : tb->__data);
+
+	if (alias)
+		return tb;
 
 	t = (struct trie *) tb->tb_data;
-	memset(t, 0, sizeof(*t));
+	t->kv[0].pos = KEYLENGTH;
+	t->kv[0].slen = KEYLENGTH;
+#ifdef CONFIG_IP_FIB_TRIE_STATS
+	t->stats = alloc_percpu(struct trie_use_stats);
+	if (!t->stats) {
+		kfree(tb);
+		tb = NULL;
+	}
+#endif
 
 	return tb;
 }
@@ -1982,74 +2006,72 @@ struct fib_table *fib_trie_table(u32 id)
 struct fib_trie_iter {
 	struct seq_net_private p;
 	struct fib_table *tb;
-	struct tnode *tnode;
+	struct key_vector *tnode;
 	unsigned int index;
 	unsigned int depth;
 };
 
-static struct rt_trie_node *fib_trie_get_next(struct fib_trie_iter *iter)
+static struct key_vector *fib_trie_get_next(struct fib_trie_iter *iter)
 {
-	struct tnode *tn = iter->tnode;
-	unsigned int cindex = iter->index;
-	struct tnode *p;
-
-	/* A single entry routing table */
-	if (!tn)
-		return NULL;
+	unsigned long cindex = iter->index;
+	struct key_vector *pn = iter->tnode;
+	t_key pkey;
 
 	pr_debug("get_next iter={node=%p index=%d depth=%d}\n",
 		 iter->tnode, iter->index, iter->depth);
-rescan:
-	while (cindex < (1<<tn->bits)) {
-		struct rt_trie_node *n = tnode_get_child_rcu(tn, cindex);
 
-		if (n) {
+	while (!IS_TRIE(pn)) {
+		while (cindex < child_length(pn)) {
+			struct key_vector *n = get_child_rcu(pn, cindex++);
+
+			if (!n)
+				continue;
+
 			if (IS_LEAF(n)) {
-				iter->tnode = tn;
-				iter->index = cindex + 1;
+				iter->tnode = pn;
+				iter->index = cindex;
 			} else {
 				/* push down one level */
-				iter->tnode = (struct tnode *) n;
+				iter->tnode = n;
 				iter->index = 0;
 				++iter->depth;
 			}
+
 			return n;
 		}
 
-		++cindex;
-	}
-
-	/* Current node exhausted, pop back up */
-	p = node_parent_rcu((struct rt_trie_node *)tn);
-	if (p) {
-		cindex = tkey_extract_bits(tn->key, p->pos, p->bits)+1;
-		tn = p;
+		/* Current node exhausted, pop back up */
+		pkey = pn->key;
+		pn = node_parent_rcu(pn);
+		cindex = get_index(pkey, pn) + 1;
 		--iter->depth;
-		goto rescan;
 	}
 
-	/* got root? */
+	/* record root node so further searches know we are done */
+	iter->tnode = pn;
+	iter->index = 0;
+
 	return NULL;
 }
 
-static struct rt_trie_node *fib_trie_get_first(struct fib_trie_iter *iter,
-				       struct trie *t)
+static struct key_vector *fib_trie_get_first(struct fib_trie_iter *iter,
+					     struct trie *t)
 {
-	struct rt_trie_node *n;
+	struct key_vector *n, *pn = t->kv;
 
 	if (!t)
 		return NULL;
 
-	n = rcu_dereference(t->trie);
+	n = rcu_dereference(pn->tnode[0]);
 	if (!n)
 		return NULL;
 
 	if (IS_TNODE(n)) {
-		iter->tnode = (struct tnode *) n;
+		iter->tnode = n;
 		iter->index = 0;
 		iter->depth = 1;
 	} else {
-		iter->tnode = NULL;
+		iter->tnode = pn;
 		iter->index = 0;
 		iter->depth = 0;
 	}
@@ -2059,7 +2081,7 @@ static struct rt_trie_node *fib_trie_get_first(struct fib_trie_iter *iter,
 
 static void trie_collect_stats(struct trie *t, struct trie_stat *s)
 {
-	struct rt_trie_node *n;
+	struct key_vector *n;
 	struct fib_trie_iter iter;
 
 	memset(s, 0, sizeof(*s));
@@ -2067,27 +2089,20 @@ static void trie_collect_stats(struct trie *t, struct trie_stat *s)
 	rcu_read_lock();
 	for (n = fib_trie_get_first(&iter, t); n; n = fib_trie_get_next(&iter)) {
 		if (IS_LEAF(n)) {
-			struct leaf *l = (struct leaf *)n;
-			struct leaf_info *li;
+			struct fib_alias *fa;
 
 			s->leaves++;
 			s->totdepth += iter.depth;
 			if (iter.depth > s->maxdepth)
 				s->maxdepth = iter.depth;
 
-			hlist_for_each_entry_rcu(li, &l->list, hlist)
+			hlist_for_each_entry_rcu(fa, &n->leaf, fa_list)
 				++s->prefixes;
 		} else {
-			const struct tnode *tn = (const struct tnode *) n;
-			int i;
-
 			s->tnodes++;
-			if (tn->bits < MAX_STAT_DEPTH)
-				s->nodesizes[tn->bits]++;
-
-			for (i = 0; i < (1<<tn->bits); i++)
-				if (!tn->child[i])
-					s->nullpointers++;
+			if (n->bits < MAX_STAT_DEPTH)
+				s->nodesizes[n->bits]++;
+			s->nullpointers += tn_info(n)->empty_children;
 		}
 	}
 	rcu_read_unlock();
@@ -2110,13 +2125,13 @@ static void trie_show_stats(struct seq_file *seq, struct trie_stat *stat)
 	seq_printf(seq, "\tMax depth:      %u\n", stat->maxdepth);
 
 	seq_printf(seq, "\tLeaves:         %u\n", stat->leaves);
-	bytes = sizeof(struct leaf) * stat->leaves;
+	bytes = LEAF_SIZE * stat->leaves;
 
 	seq_printf(seq, "\tPrefixes:       %u\n", stat->prefixes);
-	bytes += sizeof(struct leaf_info) * stat->prefixes;
+	bytes += sizeof(struct fib_alias) * stat->prefixes;
 
 	seq_printf(seq, "\tInternal nodes: %u\n\t", stat->tnodes);
-	bytes += sizeof(struct tnode) * stat->tnodes;
+	bytes += TNODE_SIZE(0) * stat->tnodes;
 
 	max = MAX_STAT_DEPTH;
 	while (max > 0 && stat->nodesizes[max-1] == 0)
@@ -2131,25 +2146,38 @@ static void trie_show_stats(struct seq_file *seq, struct trie_stat *stat)
 	seq_putc(seq, '\n');
 	seq_printf(seq, "\tPointers: %u\n", pointers);
 
-	bytes += sizeof(struct rt_trie_node *) * pointers;
+	bytes += sizeof(struct key_vector *) * pointers;
 	seq_printf(seq, "Null ptrs: %u\n", stat->nullpointers);
 	seq_printf(seq, "Total size: %u  kB\n", (bytes + 1023) / 1024);
 }
 
 #ifdef CONFIG_IP_FIB_TRIE_STATS
 static void trie_show_usage(struct seq_file *seq,
-			    const struct trie_use_stats *stats)
+			    const struct trie_use_stats __percpu *stats)
 {
+	struct trie_use_stats s = { 0 };
+	int cpu;
+
+	/* loop through all of the CPUs and gather up the stats */
+	for_each_possible_cpu(cpu) {
+		const struct trie_use_stats *pcpu = per_cpu_ptr(stats, cpu);
+
+		s.gets += pcpu->gets;
+		s.backtrack += pcpu->backtrack;
+		s.semantic_match_passed += pcpu->semantic_match_passed;
+		s.semantic_match_miss += pcpu->semantic_match_miss;
+		s.null_node_hit += pcpu->null_node_hit;
+		s.resize_node_skipped += pcpu->resize_node_skipped;
+	}
+
 	seq_printf(seq, "\nCounters:\n---------\n");
-	seq_printf(seq, "gets = %u\n", stats->gets);
-	seq_printf(seq, "backtracks = %u\n", stats->backtrack);
+	seq_printf(seq, "gets = %u\n", s.gets);
+	seq_printf(seq, "backtracks = %u\n", s.backtrack);
 	seq_printf(seq, "semantic match passed = %u\n",
-		   stats->semantic_match_passed);
-	seq_printf(seq, "semantic match miss = %u\n",
-		   stats->semantic_match_miss);
-	seq_printf(seq, "null node hit= %u\n", stats->null_node_hit);
-	seq_printf(seq, "skipped node resize = %u\n\n",
-		   stats->resize_node_skipped);
+		   s.semantic_match_passed);
+	seq_printf(seq, "semantic match miss = %u\n", s.semantic_match_miss);
+	seq_printf(seq, "null node hit= %u\n", s.null_node_hit);
+	seq_printf(seq, "skipped node resize = %u\n\n", s.resize_node_skipped);
 }
 #endif /*  CONFIG_IP_FIB_TRIE_STATS */
 
@@ -2172,7 +2200,7 @@ static int fib_triestat_seq_show(struct seq_file *seq, void *v)
 	seq_printf(seq,
 		   "Basic info: size of leaf:"
 		   " %Zd bytes, size of tnode: %Zd bytes.\n",
-		   sizeof(struct leaf), sizeof(struct tnode));
+		   LEAF_SIZE, TNODE_SIZE(0));
 
 	for (h = 0; h < FIB_TABLE_HASHSZ; h++) {
 		struct hlist_head *head = &net->ipv4.fib_table_hash[h];
@@ -2190,7 +2218,7 @@ static int fib_triestat_seq_show(struct seq_file *seq, void *v)
 			trie_collect_stats(t, &stat);
 			trie_show_stats(seq, &stat);
 #ifdef CONFIG_IP_FIB_TRIE_STATS
-			trie_show_usage(seq, &t->stats);
+			trie_show_usage(seq, t->stats);
 #endif
 		}
 	}
@@ -2211,7 +2239,7 @@ static const struct file_operations fib_triestat_fops = {
 	.release = single_release_net,
 };
 
-static struct rt_trie_node *fib_trie_get_idx(struct seq_file *seq, loff_t pos)
+static struct key_vector *fib_trie_get_idx(struct seq_file *seq, loff_t pos)
 {
 	struct fib_trie_iter *iter = seq->private;
 	struct net *net = seq_file_net(seq);
@@ -2223,7 +2251,7 @@ static struct rt_trie_node *fib_trie_get_idx(struct seq_file *seq, loff_t pos)
 		struct fib_table *tb;
 
 		hlist_for_each_entry_rcu(tb, head, tb_hlist) {
-			struct rt_trie_node *n;
+			struct key_vector *n;
 
 			for (n = fib_trie_get_first(iter,
 						    (struct trie *) tb->tb_data);
@@ -2252,7 +2280,7 @@ static void *fib_trie_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	struct fib_table *tb = iter->tb;
 	struct hlist_node *tb_node;
 	unsigned int h;
-	struct rt_trie_node *n;
+	struct key_vector *n;
 
 	++*pos;
 	/* next node in same table */
@@ -2338,44 +2366,39 @@ static inline const char *rtn_type(char *buf, size_t len, unsigned int t)
 static int fib_trie_seq_show(struct seq_file *seq, void *v)
 {
 	const struct fib_trie_iter *iter = seq->private;
-	struct rt_trie_node *n = v;
+	struct key_vector *n = v;
 
-	if (!node_parent_rcu(n))
+	if (IS_TRIE(node_parent_rcu(n)))
 		fib_table_print(seq, iter->tb);
 
 	if (IS_TNODE(n)) {
-		struct tnode *tn = (struct tnode *) n;
-		__be32 prf = htonl(mask_pfx(tn->key, tn->pos));
+		__be32 prf = htonl(n->key);
 
 		seq_indent(seq, iter->depth-1);
-		seq_printf(seq, "  +-- %pI4/%d %d %d %d\n",
-			   &prf, tn->pos, tn->bits, tn->full_children,
-			   tn->empty_children);
-
+		seq_printf(seq, "  +-- %pI4/%zu %u %u %u\n",
+			   &prf, KEYLENGTH - n->pos - n->bits, n->bits,
+			   tn_info(n)->full_children,
+			   tn_info(n)->empty_children);
 	} else {
-		struct leaf *l = (struct leaf *) n;
-		struct leaf_info *li;
-		__be32 val = htonl(l->key);
+		__be32 val = htonl(n->key);
+		struct fib_alias *fa;
 
 		seq_indent(seq, iter->depth);
 		seq_printf(seq, "  |-- %pI4\n", &val);
 
-		hlist_for_each_entry_rcu(li, &l->list, hlist) {
-			struct fib_alias *fa;
-
-			list_for_each_entry_rcu(fa, &li->falh, fa_list) {
-				char buf1[32], buf2[32];
-
-				seq_indent(seq, iter->depth+1);
-				seq_printf(seq, "  /%d %s %s", li->plen,
-					   rtn_scope(buf1, sizeof(buf1),
-						     fa->fa_info->fib_scope),
-					   rtn_type(buf2, sizeof(buf2),
-						    fa->fa_type));
-				if (fa->fa_tos)
-					seq_printf(seq, " tos=%d", fa->fa_tos);
-				seq_putc(seq, '\n');
-			}
+		hlist_for_each_entry_rcu(fa, &n->leaf, fa_list) {
+			char buf1[32], buf2[32];
+
+			seq_indent(seq, iter->depth + 1);
+			seq_printf(seq, "  /%zu %s %s",
+				   KEYLENGTH - fa->fa_slen,
+				   rtn_scope(buf1, sizeof(buf1),
+					     fa->fa_info->fib_scope),
+				   rtn_type(buf2, sizeof(buf2),
+					    fa->fa_type));
+			if (fa->fa_tos)
+				seq_printf(seq, " tos=%d", fa->fa_tos);
+			seq_putc(seq, '\n');
 		}
 	}
 
@@ -2405,31 +2428,47 @@ static const struct file_operations fib_trie_fops = {
 
 struct fib_route_iter {
 	struct seq_net_private p;
-	struct trie *main_trie;
+	struct fib_table *main_tb;
+	struct key_vector *tnode;
 	loff_t	pos;
 	t_key	key;
 };
 
-static struct leaf *fib_route_get_idx(struct fib_route_iter *iter, loff_t pos)
+static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter,
+					    loff_t pos)
 {
-	struct leaf *l = NULL;
-	struct trie *t = iter->main_trie;
+	struct fib_table *tb = iter->main_tb;
+	struct key_vector *l, **tp = &iter->tnode;
+	struct trie *t;
+	t_key key;
 
-	/* use cache location of last found key */
-	if (iter->pos > 0 && pos >= iter->pos && (l = fib_find_node(t, iter->key)))
+	/* use cache location of next-to-find key */
+	if (iter->pos > 0 && pos >= iter->pos) {
 		pos -= iter->pos;
-	else {
+		key = iter->key;
+	} else {
+		t = (struct trie *)tb->tb_data;
+		iter->tnode = t->kv;
 		iter->pos = 0;
-		l = trie_firstleaf(t);
+		key = 0;
 	}
 
-	while (l && pos-- > 0) {
+	while ((l = leaf_walk_rcu(tp, key)) != NULL) {
+		key = l->key + 1;
 		iter->pos++;
-		l = trie_nextleaf(l);
+
+		if (pos-- <= 0)
+			break;
+
+		l = NULL;
+
+		/* handle unlikely case of a key wrap */
+		if (!key)
+			break;
 	}
 
 	if (l)
-		iter->key = pos;	/* remember it */
+		iter->key = key;	/* remember it */
 	else
 		iter->pos = 0;		/* forget it */
 
@@ -2441,37 +2480,46 @@ static void *fib_route_seq_start(struct seq_file *seq, loff_t *pos)
 {
 	struct fib_route_iter *iter = seq->private;
 	struct fib_table *tb;
+	struct trie *t;
 
 	rcu_read_lock();
+
 	tb = fib_get_table(seq_file_net(seq), RT_TABLE_MAIN);
 	if (!tb)
 		return NULL;
 
-	iter->main_trie = (struct trie *) tb->tb_data;
-	if (*pos == 0)
-		return SEQ_START_TOKEN;
-	else
-		return fib_route_get_idx(iter, *pos - 1);
+	iter->main_tb = tb;
+
+	if (*pos != 0)
+		return fib_route_get_idx(iter, *pos);
+
+	t = (struct trie *)tb->tb_data;
+	iter->tnode = t->kv;
+	iter->pos = 0;
+	iter->key = 0;
+
+	return SEQ_START_TOKEN;
 }
 
 static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct fib_route_iter *iter = seq->private;
-	struct leaf *l = v;
+	struct key_vector *l = NULL;
+	t_key key = iter->key;
 
 	++*pos;
-	if (v == SEQ_START_TOKEN) {
-		iter->pos = 0;
-		l = trie_firstleaf(iter->main_trie);
-	} else {
+
+	/* only allow key of 0 for start of sequence */
+	if ((v == SEQ_START_TOKEN) || key)
+		l = leaf_walk_rcu(&iter->tnode, key);
+
+	if (l) {
+		iter->key = l->key + 1;
 		iter->pos++;
-		l = trie_nextleaf(l);
+	} else {
+		iter->pos = 0;
 	}
 
-	if (l)
-		iter->key = l->key;
-	else
-		iter->pos = 0;
 	return l;
 }
 
@@ -2503,8 +2551,11 @@ static unsigned int fib_flag_trans(int type, __be32 mask, const struct fib_info
  */
 static int fib_route_seq_show(struct seq_file *seq, void *v)
 {
-	struct leaf *l = v;
-	struct leaf_info *li;
+	struct fib_route_iter *iter = seq->private;
+	struct fib_table *tb = iter->main_tb;
+	struct fib_alias *fa;
+	struct key_vector *l = v;
+	__be32 prefix;
 
 	if (v == SEQ_START_TOKEN) {
 		seq_printf(seq, "%-127s\n", "Iface\tDestination\tGateway "
@@ -2513,45 +2564,43 @@ static int fib_route_seq_show(struct seq_file *seq, void *v)
 		return 0;
 	}
 
-	hlist_for_each_entry_rcu(li, &l->list, hlist) {
-		struct fib_alias *fa;
-		__be32 mask, prefix;
+	prefix = htonl(l->key);
 
-		mask = inet_make_mask(li->plen);
-		prefix = htonl(l->key);
+	hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) {
+		const struct fib_info *fi = fa->fa_info;
+		__be32 mask = inet_make_mask(KEYLENGTH - fa->fa_slen);
+		unsigned int flags = fib_flag_trans(fa->fa_type, mask, fi);
 
-		list_for_each_entry_rcu(fa, &li->falh, fa_list) {
-			const struct fib_info *fi = fa->fa_info;
-			unsigned int flags = fib_flag_trans(fa->fa_type, mask, fi);
+		if ((fa->fa_type == RTN_BROADCAST) ||
+		    (fa->fa_type == RTN_MULTICAST))
+			continue;
 
-			if (fa->fa_type == RTN_BROADCAST
-			    || fa->fa_type == RTN_MULTICAST)
-				continue;
+		if (fa->tb_id != tb->tb_id)
+			continue;
 
-			seq_setwidth(seq, 127);
-
-			if (fi)
-				seq_printf(seq,
-					 "%s\t%08X\t%08X\t%04X\t%d\t%u\t"
-					 "%d\t%08X\t%d\t%u\t%u",
-					 fi->fib_dev ? fi->fib_dev->name : "*",
-					 prefix,
-					 fi->fib_nh->nh_gw, flags, 0, 0,
-					 fi->fib_priority,
-					 mask,
-					 (fi->fib_advmss ?
-					  fi->fib_advmss + 40 : 0),
-					 fi->fib_window,
-					 fi->fib_rtt >> 3);
-			else
-				seq_printf(seq,
-					 "*\t%08X\t%08X\t%04X\t%d\t%u\t"
-					 "%d\t%08X\t%d\t%u\t%u",
-					 prefix, 0, flags, 0, 0, 0,
-					 mask, 0, 0, 0);
-
-			seq_pad(seq, '\n');
-		}
+		seq_setwidth(seq, 127);
+
+		if (fi)
+			seq_printf(seq,
+				   "%s\t%08X\t%08X\t%04X\t%d\t%u\t"
+				   "%d\t%08X\t%d\t%u\t%u",
+				   fi->fib_dev ? fi->fib_dev->name : "*",
+				   prefix,
+				   fi->fib_nh->nh_gw, flags, 0, 0,
+				   fi->fib_priority,
+				   mask,
+				   (fi->fib_advmss ?
+				    fi->fib_advmss + 40 : 0),
+				   fi->fib_window,
+				   fi->fib_rtt >> 3);
+		else
+			seq_printf(seq,
+				   "*\t%08X\t%08X\t%04X\t%d\t%u\t"
+				   "%d\t%08X\t%d\t%u\t%u",
+				   prefix, 0, flags, 0, 0, 0,
+				   mask, 0, 0, 0);
+
+		seq_pad(seq, '\n');
 	}
 
 	return 0;
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 606c520ffd5a..34968cd5c146 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -16,43 +16,48 @@
 #include <uapi/linux/fou.h>
 #include <uapi/linux/genetlink.h>
 
-static DEFINE_SPINLOCK(fou_lock);
-static LIST_HEAD(fou_list);
-
 struct fou {
 	struct socket *sock;
 	u8 protocol;
-	u16 port;
+	u8 flags;
+	__be16 port;
+	u16 type;
 	struct udp_offload udp_offloads;
 	struct list_head list;
 };
 
+#define FOU_F_REMCSUM_NOPARTIAL BIT(0)
+
 struct fou_cfg {
 	u16 type;
 	u8 protocol;
+	u8 flags;
 	struct udp_port_cfg udp_config;
 };
 
+static unsigned int fou_net_id;
+
+struct fou_net {
+	struct list_head fou_list;
+	struct mutex fou_lock;
+};
+
 static inline struct fou *fou_from_sock(struct sock *sk)
 {
 	return sk->sk_user_data;
 }
 
-static int fou_udp_encap_recv_deliver(struct sk_buff *skb,
-				      u8 protocol, size_t len)
+static void fou_recv_pull(struct sk_buff *skb, size_t len)
 {
 	struct iphdr *iph = ip_hdr(skb);
 
 	/* Remove 'len' bytes from the packet (UDP header and
-	 * FOU header if present), modify the protocol to the one
-	 * we found, and then call rcv_encap.
+	 * FOU header if present).
 	 */
 	iph->tot_len = htons(ntohs(iph->tot_len) - len);
 	__skb_pull(skb, len);
 	skb_postpull_rcsum(skb, udp_hdr(skb), len);
 	skb_reset_transport_header(skb);
-
-	return -protocol;
 }
 
 static int fou_udp_recv(struct sock *sk, struct sk_buff *skb)
@@ -62,16 +67,44 @@ static int fou_udp_recv(struct sock *sk, struct sk_buff *skb)
 	if (!fou)
 		return 1;
 
-	return fou_udp_encap_recv_deliver(skb, fou->protocol,
-					  sizeof(struct udphdr));
+	fou_recv_pull(skb, sizeof(struct udphdr));
+
+	return -fou->protocol;
+}
+
+static struct guehdr *gue_remcsum(struct sk_buff *skb, struct guehdr *guehdr,
+				  void *data, size_t hdrlen, u8 ipproto,
+				  bool nopartial)
+{
+	__be16 *pd = data;
+	size_t start = ntohs(pd[0]);
+	size_t offset = ntohs(pd[1]);
+	size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start);
+
+	if (!pskb_may_pull(skb, plen))
+		return NULL;
+	guehdr = (struct guehdr *)&udp_hdr(skb)[1];
+
+	skb_remcsum_process(skb, (void *)guehdr + hdrlen,
+			    start, offset, nopartial);
+
+	return guehdr;
+}
+
+static int gue_control_message(struct sk_buff *skb, struct guehdr *guehdr)
+{
+	/* No support yet */
+	kfree_skb(skb);
+	return 0;
 }
 
 static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
 {
 	struct fou *fou = fou_from_sock(sk);
-	size_t len;
+	size_t len, optlen, hdrlen;
 	struct guehdr *guehdr;
-	struct udphdr *uh;
+	void *data;
+	u16 doffset = 0;
 
 	if (!fou)
 		return 1;
@@ -80,32 +113,68 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
 	if (!pskb_may_pull(skb, len))
 		goto drop;
 
-	uh = udp_hdr(skb);
-	guehdr = (struct guehdr *)&uh[1];
+	guehdr = (struct guehdr *)&udp_hdr(skb)[1];
+
+	optlen = guehdr->hlen << 2;
+	len += optlen;
 
-	len += guehdr->hlen << 2;
 	if (!pskb_may_pull(skb, len))
 		goto drop;
 
-	uh = udp_hdr(skb);
-	guehdr = (struct guehdr *)&uh[1];
+	/* guehdr may change after pull */
+	guehdr = (struct guehdr *)&udp_hdr(skb)[1];
 
-	if (guehdr->version != 0)
-		goto drop;
+	hdrlen = sizeof(struct guehdr) + optlen;
 
-	if (guehdr->flags) {
-		/* No support yet */
+	if (guehdr->version != 0 || validate_gue_flags(guehdr, optlen))
 		goto drop;
+
+	hdrlen = sizeof(struct guehdr) + optlen;
+
+	ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(skb)->tot_len) - len);
+
+	/* Pull csum through the guehdr now . This can be used if
+	 * there is a remote checksum offload.
+	 */
+	skb_postpull_rcsum(skb, udp_hdr(skb), len);
+
+	data = &guehdr[1];
+
+	if (guehdr->flags & GUE_FLAG_PRIV) {
+		__be32 flags = *(__be32 *)(data + doffset);
+
+		doffset += GUE_LEN_PRIV;
+
+		if (flags & GUE_PFLAG_REMCSUM) {
+			guehdr = gue_remcsum(skb, guehdr, data + doffset,
+					     hdrlen, guehdr->proto_ctype,
+					     !!(fou->flags &
+						FOU_F_REMCSUM_NOPARTIAL));
+			if (!guehdr)
+				goto drop;
+
+			data = &guehdr[1];
+
+			doffset += GUE_PLEN_REMCSUM;
+		}
 	}
 
-	return fou_udp_encap_recv_deliver(skb, guehdr->next_hdr, len);
+	if (unlikely(guehdr->control))
+		return gue_control_message(skb, guehdr);
+
+	__skb_pull(skb, sizeof(struct udphdr) + hdrlen);
+	skb_reset_transport_header(skb);
+
+	return -guehdr->proto_ctype;
+
 drop:
 	kfree_skb(skb);
 	return 0;
 }
 
 static struct sk_buff **fou_gro_receive(struct sk_buff **head,
-					struct sk_buff *skb)
+					struct sk_buff *skb,
+					struct udp_offload *uoff)
 {
 	const struct net_offload *ops;
 	struct sk_buff **pp = NULL;
@@ -126,7 +195,8 @@ out_unlock:
 	return pp;
 }
 
-static int fou_gro_complete(struct sk_buff *skb, int nhoff)
+static int fou_gro_complete(struct sk_buff *skb, int nhoff,
+			    struct udp_offload *uoff)
 {
 	const struct net_offload *ops;
 	u8 proto = NAPI_GRO_CB(skb)->proto;
@@ -149,45 +219,109 @@ out_unlock:
 	return err;
 }
 
+static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off,
+				      struct guehdr *guehdr, void *data,
+				      size_t hdrlen, u8 ipproto,
+				      struct gro_remcsum *grc, bool nopartial)
+{
+	__be16 *pd = data;
+	size_t start = ntohs(pd[0]);
+	size_t offset = ntohs(pd[1]);
+	size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start);
+
+	if (skb->remcsum_offload)
+		return NULL;
+
+	if (!NAPI_GRO_CB(skb)->csum_valid)
+		return NULL;
+
+	/* Pull checksum that will be written */
+	if (skb_gro_header_hard(skb, off + plen)) {
+		guehdr = skb_gro_header_slow(skb, off + plen, off);
+		if (!guehdr)
+			return NULL;
+	}
+
+	skb_gro_remcsum_process(skb, (void *)guehdr + hdrlen,
+				start, offset, grc, nopartial);
+
+	skb->remcsum_offload = 1;
+
+	return guehdr;
+}
+
 static struct sk_buff **gue_gro_receive(struct sk_buff **head,
-					struct sk_buff *skb)
+					struct sk_buff *skb,
+					struct udp_offload *uoff)
 {
 	const struct net_offload **offloads;
 	const struct net_offload *ops;
 	struct sk_buff **pp = NULL;
 	struct sk_buff *p;
-	u8 proto;
 	struct guehdr *guehdr;
-	unsigned int hlen, guehlen;
-	unsigned int off;
+	size_t len, optlen, hdrlen, off;
+	void *data;
+	u16 doffset = 0;
 	int flush = 1;
+	struct fou *fou = container_of(uoff, struct fou, udp_offloads);
+	struct gro_remcsum grc;
+
+	skb_gro_remcsum_init(&grc);
 
 	off = skb_gro_offset(skb);
-	hlen = off + sizeof(*guehdr);
+	len = off + sizeof(*guehdr);
+
 	guehdr = skb_gro_header_fast(skb, off);
-	if (skb_gro_header_hard(skb, hlen)) {
-		guehdr = skb_gro_header_slow(skb, hlen, off);
+	if (skb_gro_header_hard(skb, len)) {
+		guehdr = skb_gro_header_slow(skb, len, off);
 		if (unlikely(!guehdr))
 			goto out;
 	}
 
-	proto = guehdr->next_hdr;
+	optlen = guehdr->hlen << 2;
+	len += optlen;
 
-	rcu_read_lock();
-	offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
-	ops = rcu_dereference(offloads[proto]);
-	if (WARN_ON(!ops || !ops->callbacks.gro_receive))
-		goto out_unlock;
+	if (skb_gro_header_hard(skb, len)) {
+		guehdr = skb_gro_header_slow(skb, len, off);
+		if (unlikely(!guehdr))
+			goto out;
+	}
 
-	guehlen = sizeof(*guehdr) + (guehdr->hlen << 2);
+	if (unlikely(guehdr->control) || guehdr->version != 0 ||
+	    validate_gue_flags(guehdr, optlen))
+		goto out;
 
-	hlen = off + guehlen;
-	if (skb_gro_header_hard(skb, hlen)) {
-		guehdr = skb_gro_header_slow(skb, hlen, off);
-		if (unlikely(!guehdr))
-			goto out_unlock;
+	hdrlen = sizeof(*guehdr) + optlen;
+
+	/* Adjust NAPI_GRO_CB(skb)->csum to account for guehdr,
+	 * this is needed if there is a remote checkcsum offload.
+	 */
+	skb_gro_postpull_rcsum(skb, guehdr, hdrlen);
+
+	data = &guehdr[1];
+
+	if (guehdr->flags & GUE_FLAG_PRIV) {
+		__be32 flags = *(__be32 *)(data + doffset);
+
+		doffset += GUE_LEN_PRIV;
+
+		if (flags & GUE_PFLAG_REMCSUM) {
+			guehdr = gue_gro_remcsum(skb, off, guehdr,
+						 data + doffset, hdrlen,
+						 guehdr->proto_ctype, &grc,
+						 !!(fou->flags &
+						    FOU_F_REMCSUM_NOPARTIAL));
+			if (!guehdr)
+				goto out;
+
+			data = &guehdr[1];
+
+			doffset += GUE_PLEN_REMCSUM;
+		}
 	}
 
+	skb_gro_pull(skb, hdrlen);
+
 	flush = 0;
 
 	for (p = *head; p; p = p->next) {
@@ -199,7 +333,7 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head,
 		guehdr2 = (struct guehdr *)(p->data + off);
 
 		/* Compare base GUE header to be equal (covers
-		 * hlen, version, next_hdr, and flags.
+		 * hlen, version, proto_ctype, and flags.
 		 */
 		if (guehdr->word != guehdr2->word) {
 			NAPI_GRO_CB(p)->same_flow = 0;
@@ -214,10 +348,11 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head,
 		}
 	}
 
-	skb_gro_pull(skb, guehlen);
-
-	/* Adjusted NAPI_GRO_CB(skb)->csum after skb_gro_pull()*/
-	skb_gro_postpull_rcsum(skb, guehdr, guehlen);
+	rcu_read_lock();
+	offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
+	ops = rcu_dereference(offloads[guehdr->proto_ctype]);
+	if (WARN_ON(!ops || !ops->callbacks.gro_receive))
+		goto out_unlock;
 
 	pp = ops->callbacks.gro_receive(head, skb);
 
@@ -225,11 +360,13 @@ out_unlock:
 	rcu_read_unlock();
 out:
 	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_gro_remcsum_cleanup(skb, &grc);
 
 	return pp;
 }
 
-static int gue_gro_complete(struct sk_buff *skb, int nhoff)
+static int gue_gro_complete(struct sk_buff *skb, int nhoff,
+			    struct udp_offload *uoff)
 {
 	const struct net_offload **offloads;
 	struct guehdr *guehdr = (struct guehdr *)(skb->data + nhoff);
@@ -238,7 +375,7 @@ static int gue_gro_complete(struct sk_buff *skb, int nhoff)
 	u8 proto;
 	int err = -ENOENT;
 
-	proto = guehdr->next_hdr;
+	proto = guehdr->proto_ctype;
 
 	guehlen = sizeof(*guehdr) + (guehdr->hlen << 2);
 
@@ -255,20 +392,21 @@ out_unlock:
 	return err;
 }
 
-static int fou_add_to_port_list(struct fou *fou)
+static int fou_add_to_port_list(struct net *net, struct fou *fou)
 {
+	struct fou_net *fn = net_generic(net, fou_net_id);
 	struct fou *fout;
 
-	spin_lock(&fou_lock);
-	list_for_each_entry(fout, &fou_list, list) {
+	mutex_lock(&fn->fou_lock);
+	list_for_each_entry(fout, &fn->fou_list, list) {
 		if (fou->port == fout->port) {
-			spin_unlock(&fou_lock);
+			mutex_unlock(&fn->fou_lock);
 			return -EALREADY;
 		}
 	}
 
-	list_add(&fou->list, &fou_list);
-	spin_unlock(&fou_lock);
+	list_add(&fou->list, &fn->fou_list);
+	mutex_unlock(&fn->fou_lock);
 
 	return 0;
 }
@@ -278,14 +416,10 @@ static void fou_release(struct fou *fou)
 	struct socket *sock = fou->sock;
 	struct sock *sk = sock->sk;
 
-	udp_del_offload(&fou->udp_offloads);
-
+	if (sk->sk_family == AF_INET)
+		udp_del_offload(&fou->udp_offloads);
 	list_del(&fou->list);
-
-	/* Remove hooks into tunnel socket */
-	sk->sk_user_data = NULL;
-
-	sock_release(sock);
+	udp_tunnel_sock_release(sock);
 
 	kfree(fou);
 }
@@ -315,10 +449,10 @@ static int gue_encap_init(struct sock *sk, struct fou *fou, struct fou_cfg *cfg)
 static int fou_create(struct net *net, struct fou_cfg *cfg,
 		      struct socket **sockp)
 {
-	struct fou *fou = NULL;
-	int err;
 	struct socket *sock = NULL;
+	struct fou *fou = NULL;
 	struct sock *sk;
+	int err;
 
 	/* Open UDP socket */
 	err = udp_sock_create(net, &cfg->udp_config, &sock);
@@ -334,6 +468,7 @@ static int fou_create(struct net *net, struct fou_cfg *cfg,
 
 	sk = sock->sk;
 
+	fou->flags = cfg->flags;
 	fou->port = cfg->udp_config.local_udp_port;
 
 	/* Initial for fou type */
@@ -353,13 +488,15 @@ static int fou_create(struct net *net, struct fou_cfg *cfg,
 		goto error;
 	}
 
+	fou->type = cfg->type;
+
 	udp_sk(sk)->encap_type = 1;
 	udp_encap_enable();
 
 	sk->sk_user_data = fou;
 	fou->sock = sock;
 
-	udp_set_convert_csum(sk, true);
+	inet_inc_convert_csum(sk);
 
 	sk->sk_allocation = GFP_ATOMIC;
 
@@ -369,7 +506,7 @@ static int fou_create(struct net *net, struct fou_cfg *cfg,
 			goto error;
 	}
 
-	err = fou_add_to_port_list(fou);
+	err = fou_add_to_port_list(net, fou);
 	if (err)
 		goto error;
 
@@ -381,27 +518,27 @@ static int fou_create(struct net *net, struct fou_cfg *cfg,
 error:
 	kfree(fou);
 	if (sock)
-		sock_release(sock);
+		udp_tunnel_sock_release(sock);
 
 	return err;
 }
 
 static int fou_destroy(struct net *net, struct fou_cfg *cfg)
 {
-	struct fou *fou;
-	u16 port = cfg->udp_config.local_udp_port;
+	struct fou_net *fn = net_generic(net, fou_net_id);
+	__be16 port = cfg->udp_config.local_udp_port;
 	int err = -EINVAL;
+	struct fou *fou;
 
-	spin_lock(&fou_lock);
-	list_for_each_entry(fou, &fou_list, list) {
+	mutex_lock(&fn->fou_lock);
+	list_for_each_entry(fou, &fn->fou_list, list) {
 		if (fou->port == port) {
-			udp_del_offload(&fou->udp_offloads);
 			fou_release(fou);
 			err = 0;
 			break;
 		}
 	}
-	spin_unlock(&fou_lock);
+	mutex_unlock(&fn->fou_lock);
 
 	return err;
 }
@@ -420,6 +557,7 @@ static struct nla_policy fou_nl_policy[FOU_ATTR_MAX + 1] = {
 	[FOU_ATTR_AF] = { .type = NLA_U8, },
 	[FOU_ATTR_IPPROTO] = { .type = NLA_U8, },
 	[FOU_ATTR_TYPE] = { .type = NLA_U8, },
+	[FOU_ATTR_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG, },
 };
 
 static int parse_nl_config(struct genl_info *info,
@@ -439,7 +577,7 @@ static int parse_nl_config(struct genl_info *info,
 	}
 
 	if (info->attrs[FOU_ATTR_PORT]) {
-		u16 port = nla_get_u16(info->attrs[FOU_ATTR_PORT]);
+		__be16 port = nla_get_be16(info->attrs[FOU_ATTR_PORT]);
 
 		cfg->udp_config.local_udp_port = port;
 	}
@@ -450,11 +588,15 @@ static int parse_nl_config(struct genl_info *info,
 	if (info->attrs[FOU_ATTR_TYPE])
 		cfg->type = nla_get_u8(info->attrs[FOU_ATTR_TYPE]);
 
+	if (info->attrs[FOU_ATTR_REMCSUM_NOPARTIAL])
+		cfg->flags |= FOU_F_REMCSUM_NOPARTIAL;
+
 	return 0;
 }
 
 static int fou_nl_cmd_add_port(struct sk_buff *skb, struct genl_info *info)
 {
+	struct net *net = genl_info_net(info);
 	struct fou_cfg cfg;
 	int err;
 
@@ -462,16 +604,119 @@ static int fou_nl_cmd_add_port(struct sk_buff *skb, struct genl_info *info)
 	if (err)
 		return err;
 
-	return fou_create(&init_net, &cfg, NULL);
+	return fou_create(net, &cfg, NULL);
 }
 
 static int fou_nl_cmd_rm_port(struct sk_buff *skb, struct genl_info *info)
 {
+	struct net *net = genl_info_net(info);
 	struct fou_cfg cfg;
+	int err;
+
+	err = parse_nl_config(info, &cfg);
+	if (err)
+		return err;
+
+	return fou_destroy(net, &cfg);
+}
+
+static int fou_fill_info(struct fou *fou, struct sk_buff *msg)
+{
+	if (nla_put_u8(msg, FOU_ATTR_AF, fou->sock->sk->sk_family) ||
+	    nla_put_be16(msg, FOU_ATTR_PORT, fou->port) ||
+	    nla_put_u8(msg, FOU_ATTR_IPPROTO, fou->protocol) ||
+	    nla_put_u8(msg, FOU_ATTR_TYPE, fou->type))
+		return -1;
+
+	if (fou->flags & FOU_F_REMCSUM_NOPARTIAL)
+		if (nla_put_flag(msg, FOU_ATTR_REMCSUM_NOPARTIAL))
+			return -1;
+	return 0;
+}
+
+static int fou_dump_info(struct fou *fou, u32 portid, u32 seq,
+			 u32 flags, struct sk_buff *skb, u8 cmd)
+{
+	void *hdr;
+
+	hdr = genlmsg_put(skb, portid, seq, &fou_nl_family, flags, cmd);
+	if (!hdr)
+		return -ENOMEM;
+
+	if (fou_fill_info(fou, skb) < 0)
+		goto nla_put_failure;
+
+	genlmsg_end(skb, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(skb, hdr);
+	return -EMSGSIZE;
+}
+
+static int fou_nl_cmd_get_port(struct sk_buff *skb, struct genl_info *info)
+{
+	struct net *net = genl_info_net(info);
+	struct fou_net *fn = net_generic(net, fou_net_id);
+	struct sk_buff *msg;
+	struct fou_cfg cfg;
+	struct fou *fout;
+	__be16 port;
+	int ret;
+
+	ret = parse_nl_config(info, &cfg);
+	if (ret)
+		return ret;
+	port = cfg.udp_config.local_udp_port;
+	if (port == 0)
+		return -EINVAL;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	ret = -ESRCH;
+	mutex_lock(&fn->fou_lock);
+	list_for_each_entry(fout, &fn->fou_list, list) {
+		if (port == fout->port) {
+			ret = fou_dump_info(fout, info->snd_portid,
+					    info->snd_seq, 0, msg,
+					    info->genlhdr->cmd);
+			break;
+		}
+	}
+	mutex_unlock(&fn->fou_lock);
+	if (ret < 0)
+		goto out_free;
+
+	return genlmsg_reply(msg, info);
+
+out_free:
+	nlmsg_free(msg);
+	return ret;
+}
+
+static int fou_nl_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct net *net = sock_net(skb->sk);
+	struct fou_net *fn = net_generic(net, fou_net_id);
+	struct fou *fout;
+	int idx = 0, ret;
 
-	parse_nl_config(info, &cfg);
+	mutex_lock(&fn->fou_lock);
+	list_for_each_entry(fout, &fn->fou_list, list) {
+		if (idx++ < cb->args[0])
+			continue;
+		ret = fou_dump_info(fout, NETLINK_CB(cb->skb).portid,
+				    cb->nlh->nlmsg_seq, NLM_F_MULTI,
+				    skb, FOU_CMD_GET);
+		if (ret)
+			break;
+	}
+	mutex_unlock(&fn->fou_lock);
 
-	return fou_destroy(&init_net, &cfg);
+	cb->args[0] = idx;
+	return skb->len;
 }
 
 static const struct genl_ops fou_nl_ops[] = {
@@ -487,30 +732,265 @@ static const struct genl_ops fou_nl_ops[] = {
 		.policy = fou_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
+	{
+		.cmd = FOU_CMD_GET,
+		.doit = fou_nl_cmd_get_port,
+		.dumpit = fou_nl_dump,
+		.policy = fou_nl_policy,
+	},
+};
+
+size_t fou_encap_hlen(struct ip_tunnel_encap *e)
+{
+	return sizeof(struct udphdr);
+}
+EXPORT_SYMBOL(fou_encap_hlen);
+
+size_t gue_encap_hlen(struct ip_tunnel_encap *e)
+{
+	size_t len;
+	bool need_priv = false;
+
+	len = sizeof(struct udphdr) + sizeof(struct guehdr);
+
+	if (e->flags & TUNNEL_ENCAP_FLAG_REMCSUM) {
+		len += GUE_PLEN_REMCSUM;
+		need_priv = true;
+	}
+
+	len += need_priv ? GUE_LEN_PRIV : 0;
+
+	return len;
+}
+EXPORT_SYMBOL(gue_encap_hlen);
+
+static void fou_build_udp(struct sk_buff *skb, struct ip_tunnel_encap *e,
+			  struct flowi4 *fl4, u8 *protocol, __be16 sport)
+{
+	struct udphdr *uh;
+
+	skb_push(skb, sizeof(struct udphdr));
+	skb_reset_transport_header(skb);
+
+	uh = udp_hdr(skb);
+
+	uh->dest = e->dport;
+	uh->source = sport;
+	uh->len = htons(skb->len);
+	uh->check = 0;
+	udp_set_csum(!(e->flags & TUNNEL_ENCAP_FLAG_CSUM), skb,
+		     fl4->saddr, fl4->daddr, skb->len);
+
+	*protocol = IPPROTO_UDP;
+}
+
+int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
+		     u8 *protocol, struct flowi4 *fl4)
+{
+	bool csum = !!(e->flags & TUNNEL_ENCAP_FLAG_CSUM);
+	int type = csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
+	__be16 sport;
+
+	skb = iptunnel_handle_offloads(skb, csum, type);
+
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
+	sport = e->sport ? : udp_flow_src_port(dev_net(skb->dev),
+					       skb, 0, 0, false);
+	fou_build_udp(skb, e, fl4, protocol, sport);
+
+	return 0;
+}
+EXPORT_SYMBOL(fou_build_header);
+
+int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
+		     u8 *protocol, struct flowi4 *fl4)
+{
+	bool csum = !!(e->flags & TUNNEL_ENCAP_FLAG_CSUM);
+	int type = csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
+	struct guehdr *guehdr;
+	size_t hdrlen, optlen = 0;
+	__be16 sport;
+	void *data;
+	bool need_priv = false;
+
+	if ((e->flags & TUNNEL_ENCAP_FLAG_REMCSUM) &&
+	    skb->ip_summed == CHECKSUM_PARTIAL) {
+		csum = false;
+		optlen += GUE_PLEN_REMCSUM;
+		type |= SKB_GSO_TUNNEL_REMCSUM;
+		need_priv = true;
+	}
+
+	optlen += need_priv ? GUE_LEN_PRIV : 0;
+
+	skb = iptunnel_handle_offloads(skb, csum, type);
+
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
+	/* Get source port (based on flow hash) before skb_push */
+	sport = e->sport ? : udp_flow_src_port(dev_net(skb->dev),
+					       skb, 0, 0, false);
+
+	hdrlen = sizeof(struct guehdr) + optlen;
+
+	skb_push(skb, hdrlen);
+
+	guehdr = (struct guehdr *)skb->data;
+
+	guehdr->control = 0;
+	guehdr->version = 0;
+	guehdr->hlen = optlen >> 2;
+	guehdr->flags = 0;
+	guehdr->proto_ctype = *protocol;
+
+	data = &guehdr[1];
+
+	if (need_priv) {
+		__be32 *flags = data;
+
+		guehdr->flags |= GUE_FLAG_PRIV;
+		*flags = 0;
+		data += GUE_LEN_PRIV;
+
+		if (type & SKB_GSO_TUNNEL_REMCSUM) {
+			u16 csum_start = skb_checksum_start_offset(skb);
+			__be16 *pd = data;
+
+			if (csum_start < hdrlen)
+				return -EINVAL;
+
+			csum_start -= hdrlen;
+			pd[0] = htons(csum_start);
+			pd[1] = htons(csum_start + skb->csum_offset);
+
+			if (!skb_is_gso(skb)) {
+				skb->ip_summed = CHECKSUM_NONE;
+				skb->encapsulation = 0;
+			}
+
+			*flags |= GUE_PFLAG_REMCSUM;
+			data += GUE_PLEN_REMCSUM;
+		}
+
+	}
+
+	fou_build_udp(skb, e, fl4, protocol, sport);
+
+	return 0;
+}
+EXPORT_SYMBOL(gue_build_header);
+
+#ifdef CONFIG_NET_FOU_IP_TUNNELS
+
+static const struct ip_tunnel_encap_ops fou_iptun_ops = {
+	.encap_hlen = fou_encap_hlen,
+	.build_header = fou_build_header,
+};
+
+static const struct ip_tunnel_encap_ops gue_iptun_ops = {
+	.encap_hlen = gue_encap_hlen,
+	.build_header = gue_build_header,
+};
+
+static int ip_tunnel_encap_add_fou_ops(void)
+{
+	int ret;
+
+	ret = ip_tunnel_encap_add_ops(&fou_iptun_ops, TUNNEL_ENCAP_FOU);
+	if (ret < 0) {
+		pr_err("can't add fou ops\n");
+		return ret;
+	}
+
+	ret = ip_tunnel_encap_add_ops(&gue_iptun_ops, TUNNEL_ENCAP_GUE);
+	if (ret < 0) {
+		pr_err("can't add gue ops\n");
+		ip_tunnel_encap_del_ops(&fou_iptun_ops, TUNNEL_ENCAP_FOU);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void ip_tunnel_encap_del_fou_ops(void)
+{
+	ip_tunnel_encap_del_ops(&fou_iptun_ops, TUNNEL_ENCAP_FOU);
+	ip_tunnel_encap_del_ops(&gue_iptun_ops, TUNNEL_ENCAP_GUE);
+}
+
+#else
+
+static int ip_tunnel_encap_add_fou_ops(void)
+{
+	return 0;
+}
+
+static void ip_tunnel_encap_del_fou_ops(void)
+{
+}
+
+#endif
+
+static __net_init int fou_init_net(struct net *net)
+{
+	struct fou_net *fn = net_generic(net, fou_net_id);
+
+	INIT_LIST_HEAD(&fn->fou_list);
+	mutex_init(&fn->fou_lock);
+	return 0;
+}
+
+static __net_exit void fou_exit_net(struct net *net)
+{
+	struct fou_net *fn = net_generic(net, fou_net_id);
+	struct fou *fou, *next;
+
+	/* Close all the FOU sockets */
+	mutex_lock(&fn->fou_lock);
+	list_for_each_entry_safe(fou, next, &fn->fou_list, list)
+		fou_release(fou);
+	mutex_unlock(&fn->fou_lock);
+}
+
+static struct pernet_operations fou_net_ops = {
+	.init = fou_init_net,
+	.exit = fou_exit_net,
+	.id   = &fou_net_id,
+	.size = sizeof(struct fou_net),
 };
 
 static int __init fou_init(void)
 {
 	int ret;
 
+	ret = register_pernet_device(&fou_net_ops);
+	if (ret)
+		goto exit;
+
 	ret = genl_register_family_with_ops(&fou_nl_family,
 					    fou_nl_ops);
+	if (ret < 0)
+		goto unregister;
+
+	ret = ip_tunnel_encap_add_fou_ops();
+	if (ret == 0)
+		return 0;
 
+	genl_unregister_family(&fou_nl_family);
+unregister:
+	unregister_pernet_device(&fou_net_ops);
+exit:
 	return ret;
 }
 
 static void __exit fou_fini(void)
 {
-	struct fou *fou, *next;
-
+	ip_tunnel_encap_del_fou_ops();
 	genl_unregister_family(&fou_nl_family);
-
-	/* Close all the FOU sockets */
-
-	spin_lock(&fou_lock);
-	list_for_each_entry_safe(fou, next, &fou_list, list)
-		fou_release(fou);
-	spin_unlock(&fou_lock);
+	unregister_pernet_device(&fou_net_ops);
 }
 
 module_init(fou_init);
diff --git a/net/ipv4/geneve.c b/net/ipv4/geneve.c
index dedb21e99914..8986e63f3bda 100644
--- a/net/ipv4/geneve.c
+++ b/net/ipv4/geneve.c
@@ -17,7 +17,7 @@
 #include <linux/errno.h>
 #include <linux/slab.h>
 #include <linux/skbuff.h>
-#include <linux/rculist.h>
+#include <linux/list.h>
 #include <linux/netdevice.h>
 #include <linux/in.h>
 #include <linux/ip.h>
@@ -26,8 +26,8 @@
 #include <linux/etherdevice.h>
 #include <linux/if_ether.h>
 #include <linux/if_vlan.h>
-#include <linux/hash.h>
 #include <linux/ethtool.h>
+#include <linux/mutex.h>
 #include <net/arp.h>
 #include <net/ndisc.h>
 #include <net/ip.h>
@@ -50,38 +50,30 @@
 #include <net/ip6_checksum.h>
 #endif
 
-#define PORT_HASH_BITS 8
-#define PORT_HASH_SIZE (1<<PORT_HASH_BITS)
+/* Protects sock_list and refcounts. */
+static DEFINE_MUTEX(geneve_mutex);
 
 /* per-network namespace private data for this module */
 struct geneve_net {
-	struct hlist_head	sock_list[PORT_HASH_SIZE];
-	spinlock_t		sock_lock;   /* Protects sock_list */
+	struct list_head	sock_list;
 };
 
 static int geneve_net_id;
 
-static struct workqueue_struct *geneve_wq;
-
 static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb)
 {
 	return (struct genevehdr *)(udp_hdr(skb) + 1);
 }
 
-static struct hlist_head *gs_head(struct net *net, __be16 port)
+static struct geneve_sock *geneve_find_sock(struct net *net,
+					    sa_family_t family, __be16 port)
 {
 	struct geneve_net *gn = net_generic(net, geneve_net_id);
-
-	return &gn->sock_list[hash_32(ntohs(port), PORT_HASH_BITS)];
-}
-
-/* Find geneve socket based on network namespace and UDP port */
-static struct geneve_sock *geneve_find_sock(struct net *net, __be16 port)
-{
 	struct geneve_sock *gs;
 
-	hlist_for_each_entry_rcu(gs, gs_head(net, port), hlist) {
-		if (inet_sk(gs->sock->sk)->inet_sport == port)
+	list_for_each_entry(gs, &gn->sock_list, list) {
+		if (inet_sk(gs->sock->sk)->inet_sport == port &&
+		    inet_sk(gs->sock->sk)->sk.sk_family == family)
 			return gs;
 	}
 
@@ -104,7 +96,7 @@ static void geneve_build_header(struct genevehdr *geneveh,
 	memcpy(geneveh->options, options, options_len);
 }
 
-/* Transmit a fully formated Geneve frame.
+/* Transmit a fully formatted Geneve frame.
  *
  * When calling this function. The skb->data should point
  * to the geneve header which is fully formed.
@@ -115,42 +107,136 @@ int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt,
 		    struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos,
 		    __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port,
 		    __be16 tun_flags, u8 vni[3], u8 opt_len, u8 *opt,
-		    bool xnet)
+		    bool csum, bool xnet)
 {
 	struct genevehdr *gnvh;
 	int min_headroom;
 	int err;
 
-	skb = udp_tunnel_handle_offloads(skb, !gs->sock->sk->sk_no_check_tx);
-
 	min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
 			+ GENEVE_BASE_HLEN + opt_len + sizeof(struct iphdr)
-			+ (vlan_tx_tag_present(skb) ? VLAN_HLEN : 0);
+			+ (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0);
 
 	err = skb_cow_head(skb, min_headroom);
-	if (unlikely(err))
+	if (unlikely(err)) {
+		kfree_skb(skb);
 		return err;
-
-	if (vlan_tx_tag_present(skb)) {
-		if (unlikely(!__vlan_put_tag(skb,
-					     skb->vlan_proto,
-					     vlan_tx_tag_get(skb)))) {
-			err = -ENOMEM;
-			return err;
-		}
-		skb->vlan_tci = 0;
 	}
 
+	skb = vlan_hwaccel_push_inside(skb);
+	if (unlikely(!skb))
+		return -ENOMEM;
+
+	skb = udp_tunnel_handle_offloads(skb, csum);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
 	gnvh = (struct genevehdr *)__skb_push(skb, sizeof(*gnvh) + opt_len);
 	geneve_build_header(gnvh, tun_flags, vni, opt_len, opt);
 
 	skb_set_inner_protocol(skb, htons(ETH_P_TEB));
 
-	return udp_tunnel_xmit_skb(gs->sock, rt, skb, src, dst,
-				   tos, ttl, df, src_port, dst_port, xnet);
+	return udp_tunnel_xmit_skb(rt, gs->sock->sk, skb, src, dst,
+				   tos, ttl, df, src_port, dst_port, xnet,
+				   !csum);
 }
 EXPORT_SYMBOL_GPL(geneve_xmit_skb);
 
+static int geneve_hlen(struct genevehdr *gh)
+{
+	return sizeof(*gh) + gh->opt_len * 4;
+}
+
+static struct sk_buff **geneve_gro_receive(struct sk_buff **head,
+					   struct sk_buff *skb,
+					   struct udp_offload *uoff)
+{
+	struct sk_buff *p, **pp = NULL;
+	struct genevehdr *gh, *gh2;
+	unsigned int hlen, gh_len, off_gnv;
+	const struct packet_offload *ptype;
+	__be16 type;
+	int flush = 1;
+
+	off_gnv = skb_gro_offset(skb);
+	hlen = off_gnv + sizeof(*gh);
+	gh = skb_gro_header_fast(skb, off_gnv);
+	if (skb_gro_header_hard(skb, hlen)) {
+		gh = skb_gro_header_slow(skb, hlen, off_gnv);
+		if (unlikely(!gh))
+			goto out;
+	}
+
+	if (gh->ver != GENEVE_VER || gh->oam)
+		goto out;
+	gh_len = geneve_hlen(gh);
+
+	hlen = off_gnv + gh_len;
+	if (skb_gro_header_hard(skb, hlen)) {
+		gh = skb_gro_header_slow(skb, hlen, off_gnv);
+		if (unlikely(!gh))
+			goto out;
+	}
+
+	flush = 0;
+
+	for (p = *head; p; p = p->next) {
+		if (!NAPI_GRO_CB(p)->same_flow)
+			continue;
+
+		gh2 = (struct genevehdr *)(p->data + off_gnv);
+		if (gh->opt_len != gh2->opt_len ||
+		    memcmp(gh, gh2, gh_len)) {
+			NAPI_GRO_CB(p)->same_flow = 0;
+			continue;
+		}
+	}
+
+	type = gh->proto_type;
+
+	rcu_read_lock();
+	ptype = gro_find_receive_by_type(type);
+	if (!ptype) {
+		flush = 1;
+		goto out_unlock;
+	}
+
+	skb_gro_pull(skb, gh_len);
+	skb_gro_postpull_rcsum(skb, gh, gh_len);
+	pp = ptype->callbacks.gro_receive(head, skb);
+
+out_unlock:
+	rcu_read_unlock();
+out:
+	NAPI_GRO_CB(skb)->flush |= flush;
+
+	return pp;
+}
+
+static int geneve_gro_complete(struct sk_buff *skb, int nhoff,
+			       struct udp_offload *uoff)
+{
+	struct genevehdr *gh;
+	struct packet_offload *ptype;
+	__be16 type;
+	int gh_len;
+	int err = -ENOSYS;
+
+	udp_tunnel_gro_complete(skb, nhoff);
+
+	gh = (struct genevehdr *)(skb->data + nhoff);
+	gh_len = geneve_hlen(gh);
+	type = gh->proto_type;
+
+	rcu_read_lock();
+	ptype = gro_find_complete_by_type(type);
+	if (ptype)
+		err = ptype->callbacks.gro_complete(skb, nhoff + gh_len);
+
+	rcu_read_unlock();
+	return err;
+}
+
 static void geneve_notify_add_rx_port(struct geneve_sock *gs)
 {
 	struct sock *sk = gs->sock->sk;
@@ -165,6 +251,15 @@ static void geneve_notify_add_rx_port(struct geneve_sock *gs)
 	}
 }
 
+static void geneve_notify_del_rx_port(struct geneve_sock *gs)
+{
+	struct sock *sk = gs->sock->sk;
+	sa_family_t sa_family = sk->sk_family;
+
+	if (sa_family == AF_INET)
+		udp_del_offload(&gs->udp_offloads);
+}
+
 /* Callback from net/ipv4/udp.c to receive packets */
 static int geneve_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 {
@@ -207,15 +302,6 @@ error:
 	return 1;
 }
 
-static void geneve_del_work(struct work_struct *work)
-{
-	struct geneve_sock *gs = container_of(work, struct geneve_sock,
-					      del_work);
-
-	udp_tunnel_sock_release(gs->sock);
-	kfree_rcu(gs, rcu);
-}
-
 static struct socket *geneve_create_sock(struct net *net, bool ipv6,
 					 __be16 port)
 {
@@ -256,8 +342,6 @@ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port,
 	if (!gs)
 		return ERR_PTR(-ENOMEM);
 
-	INIT_WORK(&gs->del_work, geneve_del_work);
-
 	sock = geneve_create_sock(net, ipv6, port);
 	if (IS_ERR(sock)) {
 		kfree(gs);
@@ -265,19 +349,15 @@ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port,
 	}
 
 	gs->sock = sock;
-	atomic_set(&gs->refcnt, 1);
+	gs->refcnt = 1;
 	gs->rcv = rcv;
 	gs->rcv_data = data;
 
 	/* Initialize the geneve udp offloads structure */
 	gs->udp_offloads.port = port;
-	gs->udp_offloads.callbacks.gro_receive = NULL;
-	gs->udp_offloads.callbacks.gro_complete = NULL;
-
-	spin_lock(&gn->sock_lock);
-	hlist_add_head_rcu(&gs->hlist, gs_head(net, port));
+	gs->udp_offloads.callbacks.gro_receive  = geneve_gro_receive;
+	gs->udp_offloads.callbacks.gro_complete = geneve_gro_complete;
 	geneve_notify_add_rx_port(gs);
-	spin_unlock(&gn->sock_lock);
 
 	/* Mark socket as an encapsulation socket */
 	tunnel_cfg.sk_user_data = gs;
@@ -286,6 +366,8 @@ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port,
 	tunnel_cfg.encap_destroy = NULL;
 	setup_udp_tunnel_sock(net, sock, &tunnel_cfg);
 
+	list_add(&gs->list, &gn->sock_list);
+
 	return gs;
 }
 
@@ -295,52 +377,52 @@ struct geneve_sock *geneve_sock_add(struct net *net, __be16 port,
 {
 	struct geneve_sock *gs;
 
-	gs = geneve_socket_create(net, port, rcv, data, ipv6);
-	if (!IS_ERR(gs))
-		return gs;
+	mutex_lock(&geneve_mutex);
 
-	if (no_share)	/* Return error if sharing is not allowed. */
-		return ERR_PTR(-EINVAL);
-
-	gs = geneve_find_sock(net, port);
+	gs = geneve_find_sock(net, ipv6 ? AF_INET6 : AF_INET, port);
 	if (gs) {
-		if (gs->rcv == rcv)
-			atomic_inc(&gs->refcnt);
+		if (!no_share && gs->rcv == rcv)
+			gs->refcnt++;
 		else
 			gs = ERR_PTR(-EBUSY);
 	} else {
-		gs = ERR_PTR(-EINVAL);
+		gs = geneve_socket_create(net, port, rcv, data, ipv6);
 	}
 
+	mutex_unlock(&geneve_mutex);
+
 	return gs;
 }
 EXPORT_SYMBOL_GPL(geneve_sock_add);
 
 void geneve_sock_release(struct geneve_sock *gs)
 {
-	if (!atomic_dec_and_test(&gs->refcnt))
-		return;
+	mutex_lock(&geneve_mutex);
 
-	queue_work(geneve_wq, &gs->del_work);
+	if (--gs->refcnt)
+		goto unlock;
+
+	list_del(&gs->list);
+	geneve_notify_del_rx_port(gs);
+	udp_tunnel_sock_release(gs->sock);
+	kfree_rcu(gs, rcu);
+
+unlock:
+	mutex_unlock(&geneve_mutex);
 }
 EXPORT_SYMBOL_GPL(geneve_sock_release);
 
 static __net_init int geneve_init_net(struct net *net)
 {
 	struct geneve_net *gn = net_generic(net, geneve_net_id);
-	unsigned int h;
 
-	spin_lock_init(&gn->sock_lock);
-
-	for (h = 0; h < PORT_HASH_SIZE; ++h)
-		INIT_HLIST_HEAD(&gn->sock_list[h]);
+	INIT_LIST_HEAD(&gn->sock_list);
 
 	return 0;
 }
 
 static struct pernet_operations geneve_net_ops = {
 	.init = geneve_init_net,
-	.exit = NULL,
 	.id   = &geneve_net_id,
 	.size = sizeof(struct geneve_net),
 };
@@ -349,10 +431,6 @@ static int __init geneve_init_module(void)
 {
 	int rc;
 
-	geneve_wq = alloc_workqueue("geneve", 0, 0);
-	if (!geneve_wq)
-		return -ENOMEM;
-
 	rc = register_pernet_subsys(&geneve_net_ops);
 	if (rc)
 		return rc;
@@ -361,11 +439,10 @@ static int __init geneve_init_module(void)
 
 	return 0;
 }
-late_initcall(geneve_init_module);
+module_init(geneve_init_module);
 
 static void __exit geneve_cleanup_module(void)
 {
-	destroy_workqueue(geneve_wq);
 	unregister_pernet_subsys(&geneve_net_ops);
 }
 module_exit(geneve_cleanup_module);
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index bb5947b0ce2d..5aa46d4b44ef 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -149,7 +149,7 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head,
 
 	rcu_read_lock();
 	ptype = gro_find_receive_by_type(type);
-	if (ptype == NULL)
+	if (!ptype)
 		goto out_unlock;
 
 	grehlen = GRE_HEADER_SECTION;
@@ -243,10 +243,13 @@ static int gre_gro_complete(struct sk_buff *skb, int nhoff)
 
 	rcu_read_lock();
 	ptype = gro_find_complete_by_type(type);
-	if (ptype != NULL)
+	if (ptype)
 		err = ptype->callbacks.gro_complete(skb, nhoff + grehlen);
 
 	rcu_read_unlock();
+
+	skb_set_inner_mac_header(skb, nhoff + grehlen);
+
 	return err;
 }
 
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 5882f584910e..f5203fba6236 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -190,7 +190,7 @@ EXPORT_SYMBOL(icmp_err_convert);
  */
 
 struct icmp_control {
-	void (*handler)(struct sk_buff *skb);
+	bool (*handler)(struct sk_buff *skb);
 	short   error;		/* This ICMP is classed as an error message */
 };
 
@@ -205,7 +205,7 @@ static const struct icmp_control icmp_pointers[NR_ICMP_TYPES+1];
  */
 static struct sock *icmp_sk(struct net *net)
 {
-	return net->ipv4.icmp_sk[smp_processor_id()];
+	return *this_cpu_ptr(net->ipv4.icmp_sk);
 }
 
 static inline struct sock *icmp_xmit_lock(struct net *net)
@@ -399,7 +399,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 		return;
 
 	sk = icmp_xmit_lock(net);
-	if (sk == NULL)
+	if (!sk)
 		return;
 	inet = inet_sk(sk);
 
@@ -609,7 +609,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 						 skb_in->data,
 						 sizeof(_inner_type),
 						 &_inner_type);
-			if (itp == NULL)
+			if (!itp)
 				goto out;
 
 			/*
@@ -627,7 +627,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 		return;
 
 	sk = icmp_xmit_lock(net);
-	if (sk == NULL)
+	if (!sk)
 		goto out_free;
 
 	/*
@@ -746,7 +746,7 @@ static bool icmp_tag_validation(int proto)
  *	ICMP_PARAMETERPROB.
  */
 
-static void icmp_unreach(struct sk_buff *skb)
+static bool icmp_unreach(struct sk_buff *skb)
 {
 	const struct iphdr *iph;
 	struct icmphdr *icmph;
@@ -784,8 +784,8 @@ static void icmp_unreach(struct sk_buff *skb)
 			 */
 			switch (net->ipv4.sysctl_ip_no_pmtu_disc) {
 			default:
-				LIMIT_NETDEBUG(KERN_INFO pr_fmt("%pI4: fragmentation needed and DF set\n"),
-					       &iph->daddr);
+				net_dbg_ratelimited("%pI4: fragmentation needed and DF set\n",
+						    &iph->daddr);
 				break;
 			case 2:
 				goto out;
@@ -798,8 +798,8 @@ static void icmp_unreach(struct sk_buff *skb)
 			}
 			break;
 		case ICMP_SR_FAILED:
-			LIMIT_NETDEBUG(KERN_INFO pr_fmt("%pI4: Source Route Failed\n"),
-				       &iph->daddr);
+			net_dbg_ratelimited("%pI4: Source Route Failed\n",
+					    &iph->daddr);
 			break;
 		default:
 			break;
@@ -839,10 +839,10 @@ static void icmp_unreach(struct sk_buff *skb)
 	icmp_socket_deliver(skb, info);
 
 out:
-	return;
+	return true;
 out_err:
 	ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS);
-	goto out;
+	return false;
 }
 
 
@@ -850,17 +850,20 @@ out_err:
  *	Handle ICMP_REDIRECT.
  */
 
-static void icmp_redirect(struct sk_buff *skb)
+static bool icmp_redirect(struct sk_buff *skb)
 {
 	if (skb->len < sizeof(struct iphdr)) {
 		ICMP_INC_STATS_BH(dev_net(skb->dev), ICMP_MIB_INERRORS);
-		return;
+		return false;
 	}
 
-	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
-		return;
+	if (!pskb_may_pull(skb, sizeof(struct iphdr))) {
+		/* there aught to be a stat */
+		return false;
+	}
 
 	icmp_socket_deliver(skb, icmp_hdr(skb)->un.gateway);
+	return true;
 }
 
 /*
@@ -875,7 +878,7 @@ static void icmp_redirect(struct sk_buff *skb)
  *	See also WRT handling of options once they are done and working.
  */
 
-static void icmp_echo(struct sk_buff *skb)
+static bool icmp_echo(struct sk_buff *skb)
 {
 	struct net *net;
 
@@ -891,6 +894,8 @@ static void icmp_echo(struct sk_buff *skb)
 		icmp_param.head_len	   = sizeof(struct icmphdr);
 		icmp_reply(&icmp_param, skb);
 	}
+	/* should there be an ICMP stat for ignored echos? */
+	return true;
 }
 
 /*
@@ -900,7 +905,7 @@ static void icmp_echo(struct sk_buff *skb)
  *		  MUST be accurate to a few minutes.
  *		  MUST be updated at least at 15Hz.
  */
-static void icmp_timestamp(struct sk_buff *skb)
+static bool icmp_timestamp(struct sk_buff *skb)
 {
 	struct timespec tv;
 	struct icmp_bxm icmp_param;
@@ -927,15 +932,17 @@ static void icmp_timestamp(struct sk_buff *skb)
 	icmp_param.data_len	   = 0;
 	icmp_param.head_len	   = sizeof(struct icmphdr) + 12;
 	icmp_reply(&icmp_param, skb);
-out:
-	return;
+	return true;
+
 out_err:
 	ICMP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), ICMP_MIB_INERRORS);
-	goto out;
+	return false;
 }
 
-static void icmp_discard(struct sk_buff *skb)
+static bool icmp_discard(struct sk_buff *skb)
 {
+	/* pretend it was a success */
+	return true;
 }
 
 /*
@@ -946,6 +953,7 @@ int icmp_rcv(struct sk_buff *skb)
 	struct icmphdr *icmph;
 	struct rtable *rt = skb_rtable(skb);
 	struct net *net = dev_net(rt->dst.dev);
+	bool success;
 
 	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
 		struct sec_path *sp = skb_sec_path(skb);
@@ -1012,7 +1020,12 @@ int icmp_rcv(struct sk_buff *skb)
 		}
 	}
 
-	icmp_pointers[icmph->type].handler(skb);
+	success = icmp_pointers[icmph->type].handler(skb);
+
+	if (success)  {
+		consume_skb(skb);
+		return 0;
+	}
 
 drop:
 	kfree_skb(skb);
@@ -1127,8 +1140,8 @@ static void __net_exit icmp_sk_exit(struct net *net)
 	int i;
 
 	for_each_possible_cpu(i)
-		inet_ctl_sock_destroy(net->ipv4.icmp_sk[i]);
-	kfree(net->ipv4.icmp_sk);
+		inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.icmp_sk, i));
+	free_percpu(net->ipv4.icmp_sk);
 	net->ipv4.icmp_sk = NULL;
 }
 
@@ -1136,9 +1149,8 @@ static int __net_init icmp_sk_init(struct net *net)
 {
 	int i, err;
 
-	net->ipv4.icmp_sk =
-		kzalloc(nr_cpu_ids * sizeof(struct sock *), GFP_KERNEL);
-	if (net->ipv4.icmp_sk == NULL)
+	net->ipv4.icmp_sk = alloc_percpu(struct sock *);
+	if (!net->ipv4.icmp_sk)
 		return -ENOMEM;
 
 	for_each_possible_cpu(i) {
@@ -1149,7 +1161,7 @@ static int __net_init icmp_sk_init(struct net *net)
 		if (err < 0)
 			goto fail;
 
-		net->ipv4.icmp_sk[i] = sk;
+		*per_cpu_ptr(net->ipv4.icmp_sk, i) = sk;
 
 		/* Enough space for 2 64K ICMP packets, including
 		 * sk_buff/skb_shared_info struct overhead.
@@ -1190,8 +1202,8 @@ static int __net_init icmp_sk_init(struct net *net)
 
 fail:
 	for_each_possible_cpu(i)
-		inet_ctl_sock_destroy(net->ipv4.icmp_sk[i]);
-	kfree(net->ipv4.icmp_sk);
+		inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.icmp_sk, i));
+	free_percpu(net->ipv4.icmp_sk);
 	return err;
 }
 
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index fb70e3ecc3e4..a3a697f5ffba 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -97,6 +97,7 @@
 #include <net/route.h>
 #include <net/sock.h>
 #include <net/checksum.h>
+#include <net/inet_common.h>
 #include <linux/netfilter_ipv4.h>
 #ifdef CONFIG_IP_MROUTE
 #include <linux/mroute.h>
@@ -112,17 +113,17 @@
 #ifdef CONFIG_IP_MULTICAST
 /* Parameter names and values are taken from igmp-v2-06 draft */
 
-#define IGMP_V1_Router_Present_Timeout		(400*HZ)
-#define IGMP_V2_Router_Present_Timeout		(400*HZ)
-#define IGMP_V2_Unsolicited_Report_Interval	(10*HZ)
-#define IGMP_V3_Unsolicited_Report_Interval	(1*HZ)
-#define IGMP_Query_Response_Interval		(10*HZ)
-#define IGMP_Query_Robustness_Variable		2
+#define IGMP_V1_ROUTER_PRESENT_TIMEOUT		(400*HZ)
+#define IGMP_V2_ROUTER_PRESENT_TIMEOUT		(400*HZ)
+#define IGMP_V2_UNSOLICITED_REPORT_INTERVAL	(10*HZ)
+#define IGMP_V3_UNSOLICITED_REPORT_INTERVAL	(1*HZ)
+#define IGMP_QUERY_RESPONSE_INTERVAL		(10*HZ)
+#define IGMP_QUERY_ROBUSTNESS_VARIABLE		2
 
 
-#define IGMP_Initial_Report_Delay		(1)
+#define IGMP_INITIAL_REPORT_DELAY		(1)
 
-/* IGMP_Initial_Report_Delay is not from IGMP specs!
+/* IGMP_INITIAL_REPORT_DELAY is not from IGMP specs!
  * IGMP specs require to report membership immediately after
  * joining a group, but we delay the first report by a
  * small interval. It seems more natural and still does not
@@ -318,9 +319,7 @@ igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted)
 	return scount;
 }
 
-#define igmp_skb_size(skb) (*(unsigned int *)((skb)->cb))
-
-static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size)
+static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
 {
 	struct sk_buff *skb;
 	struct rtable *rt;
@@ -330,6 +329,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size)
 	struct flowi4 fl4;
 	int hlen = LL_RESERVED_SPACE(dev);
 	int tlen = dev->needed_tailroom;
+	unsigned int size = mtu;
 
 	while (1) {
 		skb = alloc_skb(size + hlen + tlen,
@@ -341,7 +341,6 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size)
 			return NULL;
 	}
 	skb->priority = TC_PRIO_CONTROL;
-	igmp_skb_size(skb) = size;
 
 	rt = ip_route_output_ports(net, &fl4, NULL, IGMPV3_ALL_MCR, 0,
 				   0, 0,
@@ -354,6 +353,8 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size)
 	skb_dst_set(skb, &rt->dst);
 	skb->dev = dev;
 
+	skb->reserved_tailroom = skb_end_offset(skb) -
+				 min(mtu, skb_end_offset(skb));
 	skb_reserve(skb, hlen);
 
 	skb_reset_network_header(skb);
@@ -369,7 +370,7 @@ 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, NULL);
+	ip_select_ident(net, skb, NULL);
 	((u8 *)&pip[1])[0] = IPOPT_RA;
 	((u8 *)&pip[1])[1] = 4;
 	((u8 *)&pip[1])[2] = 0;
@@ -423,8 +424,7 @@ static struct sk_buff *add_grhead(struct sk_buff *skb, struct ip_mc_list *pmc,
 	return skb;
 }
 
-#define AVAILABLE(skb) ((skb) ? ((skb)->dev ? igmp_skb_size(skb) - (skb)->len : \
-	skb_tailroom(skb)) : 0)
+#define AVAILABLE(skb)	((skb) ? skb_availroom(skb) : 0)
 
 static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
 	int type, int gdeleted, int sdeleted)
@@ -692,7 +692,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc,
 	hlen = LL_RESERVED_SPACE(dev);
 	tlen = dev->needed_tailroom;
 	skb = alloc_skb(IGMP_SIZE + hlen + tlen, GFP_ATOMIC);
-	if (skb == NULL) {
+	if (!skb) {
 		ip_rt_put(rt);
 		return -1;
 	}
@@ -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, NULL);
+	ip_select_ident(net, skb, NULL);
 	((u8 *)&iph[1])[0] = IPOPT_RA;
 	((u8 *)&iph[1])[1] = 4;
 	((u8 *)&iph[1])[2] = 0;
@@ -879,15 +879,15 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb,
 		if (ih->code == 0) {
 			/* Alas, old v1 router presents here. */
 
-			max_delay = IGMP_Query_Response_Interval;
+			max_delay = IGMP_QUERY_RESPONSE_INTERVAL;
 			in_dev->mr_v1_seen = jiffies +
-				IGMP_V1_Router_Present_Timeout;
+				IGMP_V1_ROUTER_PRESENT_TIMEOUT;
 			group = 0;
 		} else {
 			/* v2 router present */
 			max_delay = ih->code*(HZ/IGMP_TIMER_SCALE);
 			in_dev->mr_v2_seen = jiffies +
-				IGMP_V2_Router_Present_Timeout;
+				IGMP_V2_ROUTER_PRESENT_TIMEOUT;
 		}
 		/* cancel the interface change timer */
 		in_dev->mr_ifc_count = 0;
@@ -899,7 +899,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb,
 		return true;	/* ignore bogus packet; freed by caller */
 	} else if (IGMP_V1_SEEN(in_dev)) {
 		/* This is a v3 query with v1 queriers present */
-		max_delay = IGMP_Query_Response_Interval;
+		max_delay = IGMP_QUERY_RESPONSE_INTERVAL;
 		group = 0;
 	} else if (IGMP_V2_SEEN(in_dev)) {
 		/* this is a v3 query with v2 queriers present;
@@ -981,7 +981,7 @@ int igmp_rcv(struct sk_buff *skb)
 	int len = skb->len;
 	bool dropped = true;
 
-	if (in_dev == NULL)
+	if (!in_dev)
 		goto drop;
 
 	if (!pskb_may_pull(skb, sizeof(struct igmphdr)))
@@ -1218,7 +1218,7 @@ static void igmp_group_added(struct ip_mc_list *im)
 		return;
 	if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) {
 		spin_lock_bh(&im->lock);
-		igmp_start_timer(im, IGMP_Initial_Report_Delay);
+		igmp_start_timer(im, IGMP_INITIAL_REPORT_DELAY);
 		spin_unlock_bh(&im->lock);
 		return;
 	}
@@ -1541,7 +1541,7 @@ static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr)
 int sysctl_igmp_max_memberships __read_mostly = IP_MAX_MEMBERSHIPS;
 int sysctl_igmp_max_msf __read_mostly = IP_MAX_MSF;
 #ifdef CONFIG_IP_MULTICAST
-int sysctl_igmp_qrv __read_mostly = IGMP_Query_Robustness_Variable;
+int sysctl_igmp_qrv __read_mostly = IGMP_QUERY_ROBUSTNESS_VARIABLE;
 #endif
 
 static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode,
@@ -1850,30 +1850,28 @@ static void ip_mc_clear_src(struct ip_mc_list *pmc)
 	pmc->sfcount[MCAST_EXCLUDE] = 1;
 }
 
-
-/*
- * Join a multicast group
+/* Join a multicast group
  */
-int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr)
+
+int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr)
 {
-	int err;
 	__be32 addr = imr->imr_multiaddr.s_addr;
-	struct ip_mc_socklist *iml = NULL, *i;
+	struct ip_mc_socklist *iml, *i;
 	struct in_device *in_dev;
 	struct inet_sock *inet = inet_sk(sk);
 	struct net *net = sock_net(sk);
 	int ifindex;
 	int count = 0;
+	int err;
+
+	ASSERT_RTNL();
 
 	if (!ipv4_is_multicast(addr))
 		return -EINVAL;
 
-	rtnl_lock();
-
 	in_dev = ip_mc_find_dev(net, imr);
 
 	if (!in_dev) {
-		iml = NULL;
 		err = -ENODEV;
 		goto done;
 	}
@@ -1890,7 +1888,7 @@ int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr)
 	if (count >= sysctl_igmp_max_memberships)
 		goto done;
 	iml = sock_kmalloc(sk, sizeof(*iml), GFP_KERNEL);
-	if (iml == NULL)
+	if (!iml)
 		goto done;
 
 	memcpy(&iml->multi, imr, sizeof(*imr));
@@ -1901,7 +1899,6 @@ int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr)
 	ip_mc_inc_group(in_dev, addr);
 	err = 0;
 done:
-	rtnl_unlock();
 	return err;
 }
 EXPORT_SYMBOL(ip_mc_join_group);
@@ -1912,7 +1909,7 @@ static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml,
 	struct ip_sf_socklist *psf = rtnl_dereference(iml->sflist);
 	int err;
 
-	if (psf == NULL) {
+	if (!psf) {
 		/* any-source empty exclude case */
 		return ip_mc_del_src(in_dev, &iml->multi.imr_multiaddr.s_addr,
 			iml->sfmode, 0, NULL, 0);
@@ -1926,10 +1923,6 @@ static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml,
 	return err;
 }
 
-/*
- *	Ask a socket to leave a group.
- */
-
 int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr)
 {
 	struct inet_sock *inet = inet_sk(sk);
@@ -1941,7 +1934,8 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr)
 	u32 ifindex;
 	int ret = -EADDRNOTAVAIL;
 
-	rtnl_lock();
+	ASSERT_RTNL();
+
 	in_dev = ip_mc_find_dev(net, imr);
 	if (!in_dev) {
 		ret = -ENODEV;
@@ -1965,14 +1959,13 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr)
 		*imlp = iml->next_rcu;
 
 		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;
 	}
 out:
-	rtnl_unlock();
 	return ret;
 }
 EXPORT_SYMBOL(ip_mc_leave_group);
@@ -1994,7 +1987,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct
 	if (!ipv4_is_multicast(addr))
 		return -EINVAL;
 
-	rtnl_lock();
+	ASSERT_RTNL();
 
 	imr.imr_multiaddr.s_addr = mreqs->imr_multiaddr;
 	imr.imr_address.s_addr = mreqs->imr_interface;
@@ -2108,9 +2101,8 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct
 	ip_mc_add_src(in_dev, &mreqs->imr_multiaddr, omode, 1,
 		&mreqs->imr_sourceaddr, 1);
 done:
-	rtnl_unlock();
 	if (leavegroup)
-		return ip_mc_leave_group(sk, &imr);
+		err = ip_mc_leave_group(sk, &imr);
 	return err;
 }
 
@@ -2132,7 +2124,7 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex)
 	    msf->imsf_fmode != MCAST_EXCLUDE)
 		return -EINVAL;
 
-	rtnl_lock();
+	ASSERT_RTNL();
 
 	imr.imr_multiaddr.s_addr = msf->imsf_multiaddr;
 	imr.imr_address.s_addr = msf->imsf_interface;
@@ -2194,7 +2186,6 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex)
 	pmc->sfmode = msf->imsf_fmode;
 	err = 0;
 done:
-	rtnl_unlock();
 	if (leavegroup)
 		err = ip_mc_leave_group(sk, &imr);
 	return err;
@@ -2369,7 +2360,7 @@ void ip_mc_drop_socket(struct sock *sk)
 	struct ip_mc_socklist *iml;
 	struct net *net = sock_net(sk);
 
-	if (inet->mc_list == NULL)
+	if (!inet->mc_list)
 		return;
 
 	rtnl_lock();
@@ -2379,7 +2370,7 @@ void ip_mc_drop_socket(struct sock *sk)
 		inet->mc_list = iml->next_rcu;
 		in_dev = inetdev_by_index(net, iml->multi.imr_ifindex);
 		(void) ip_mc_leave_src(sk, iml, in_dev);
-		if (in_dev != NULL)
+		if (in_dev)
 			ip_mc_dec_group(in_dev, iml->multi.imr_multiaddr.s_addr);
 		/* decrease mem now to avoid the memleak warning */
 		atomic_sub(sizeof(*iml), &sk->sk_omem_alloc);
@@ -2596,13 +2587,13 @@ static inline struct ip_sf_list *igmp_mcf_get_first(struct seq_file *seq)
 	for_each_netdev_rcu(net, state->dev) {
 		struct in_device *idev;
 		idev = __in_dev_get_rcu(state->dev);
-		if (unlikely(idev == NULL))
+		if (unlikely(!idev))
 			continue;
 		im = rcu_dereference(idev->mc_list);
-		if (likely(im != NULL)) {
+		if (likely(im)) {
 			spin_lock_bh(&im->lock);
 			psf = im->sources;
-			if (likely(psf != NULL)) {
+			if (likely(psf)) {
 				state->im = im;
 				state->idev = idev;
 				break;
@@ -2672,7 +2663,7 @@ static void igmp_mcf_seq_stop(struct seq_file *seq, void *v)
 	__releases(rcu)
 {
 	struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq);
-	if (likely(state->im != NULL)) {
+	if (likely(state->im)) {
 		spin_unlock_bh(&state->im->lock);
 		state->im = NULL;
 	}
@@ -2687,11 +2678,7 @@ static int igmp_mcf_seq_show(struct seq_file *seq, void *v)
 	struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq);
 
 	if (v == SEQ_START_TOKEN) {
-		seq_printf(seq,
-			   "%3s %6s "
-			   "%10s %10s %6s %6s\n", "Idx",
-			   "Device", "MCA",
-			   "SRC", "INC", "EXC");
+		seq_puts(seq, "Idx Device        MCA        SRC    INC    EXC\n");
 	} else {
 		seq_printf(seq,
 			   "%3d %6.6s 0x%08x "
@@ -2729,6 +2716,7 @@ static const struct file_operations igmp_mcf_seq_fops = {
 static int __net_init igmp_net_init(struct net *net)
 {
 	struct proc_dir_entry *pde;
+	int err;
 
 	pde = proc_create("igmp", S_IRUGO, net->proc_net, &igmp_mc_seq_fops);
 	if (!pde)
@@ -2737,8 +2725,18 @@ static int __net_init igmp_net_init(struct net *net)
 			  &igmp_mcf_seq_fops);
 	if (!pde)
 		goto out_mcfilter;
+	err = inet_ctl_sock_create(&net->ipv4.mc_autojoin_sk, AF_INET,
+				   SOCK_DGRAM, 0, net);
+	if (err < 0) {
+		pr_err("Failed to initialize the IGMP autojoin socket (err %d)\n",
+		       err);
+		goto out_sock;
+	}
+
 	return 0;
 
+out_sock:
+	remove_proc_entry("mcfilter", net->proc_net);
 out_mcfilter:
 	remove_proc_entry("igmp", net->proc_net);
 out_igmp:
@@ -2749,6 +2747,7 @@ static void __net_exit igmp_net_exit(struct net *net)
 {
 	remove_proc_entry("mcfilter", net->proc_net);
 	remove_proc_entry("igmp", net->proc_net);
+	inet_ctl_sock_destroy(net->ipv4.mc_autojoin_sk);
 }
 
 static struct pernet_operations igmp_net_ops = {
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 14d02ea905b6..8976ca423a07 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -23,6 +23,7 @@
 #include <net/route.h>
 #include <net/tcp_states.h>
 #include <net/xfrm.h>
+#include <net/tcp.h>
 
 #ifdef INET_CSK_DEBUG
 const char inet_csk_timer_bug_msg[] = "inet_csk BUG: unknown timer value\n";
@@ -268,6 +269,7 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo)
 		release_sock(sk);
 		if (reqsk_queue_empty(&icsk->icsk_accept_queue))
 			timeo = schedule_timeout(timeo);
+		sched_annotate_sleep();
 		lock_sock(sk);
 		err = 0;
 		if (!reqsk_queue_empty(&icsk->icsk_accept_queue))
@@ -293,8 +295,8 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct request_sock_queue *queue = &icsk->icsk_accept_queue;
-	struct sock *newsk;
 	struct request_sock *req;
+	struct sock *newsk;
 	int error;
 
 	lock_sock(sk);
@@ -323,9 +325,11 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err)
 	newsk = req->sk;
 
 	sk_acceptq_removed(sk);
-	if (sk->sk_protocol == IPPROTO_TCP && queue->fastopenq != NULL) {
+	if (sk->sk_protocol == IPPROTO_TCP &&
+	    tcp_rsk(req)->tfo_listener &&
+	    queue->fastopenq) {
 		spin_lock_bh(&queue->fastopenq->lock);
-		if (tcp_rsk(req)->listener) {
+		if (tcp_rsk(req)->tfo_listener) {
 			/* We are still waiting for the final ACK from 3WHS
 			 * so can't free req now. Instead, we set req->sk to
 			 * NULL to signify that the child socket is taken
@@ -340,7 +344,7 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err)
 out:
 	release_sock(sk);
 	if (req)
-		__reqsk_free(req);
+		reqsk_put(req);
 	return newsk;
 out_err:
 	newsk = NULL;
@@ -399,18 +403,17 @@ struct dst_entry *inet_csk_route_req(struct sock *sk,
 				     struct flowi4 *fl4,
 				     const struct request_sock *req)
 {
-	struct rtable *rt;
 	const struct inet_request_sock *ireq = inet_rsk(req);
-	struct ip_options_rcu *opt = inet_rsk(req)->opt;
-	struct net *net = sock_net(sk);
-	int flags = inet_sk_flowi_flags(sk);
+	struct net *net = read_pnet(&ireq->ireq_net);
+	struct ip_options_rcu *opt = ireq->opt;
+	struct rtable *rt;
 
-	flowi4_init_output(fl4, sk->sk_bound_dev_if, ireq->ir_mark,
+	flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
-			   sk->sk_protocol,
-			   flags,
+			   sk->sk_protocol, inet_sk_flowi_flags(sk),
 			   (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
-			   ireq->ir_loc_addr, ireq->ir_rmt_port, inet_sk(sk)->inet_sport);
+			   ireq->ir_loc_addr, ireq->ir_rmt_port,
+			   htons(ireq->ir_num));
 	security_req_classify_flow(req, flowi4_to_flowi(fl4));
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
@@ -432,9 +435,9 @@ struct dst_entry *inet_csk_route_child_sock(struct sock *sk,
 					    const struct request_sock *req)
 {
 	const struct inet_request_sock *ireq = inet_rsk(req);
+	struct net *net = read_pnet(&ireq->ireq_net);
 	struct inet_sock *newinet = inet_sk(newsk);
 	struct ip_options_rcu *opt;
-	struct net *net = sock_net(sk);
 	struct flowi4 *fl4;
 	struct rtable *rt;
 
@@ -442,11 +445,12 @@ 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, inet_rsk(req)->ir_mark,
+	flowi4_init_output(fl4, ireq->ir_iif, ireq->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,
-			   ireq->ir_loc_addr, ireq->ir_rmt_port, inet_sk(sk)->inet_sport);
+			   ireq->ir_loc_addr, ireq->ir_rmt_port,
+			   htons(ireq->ir_num));
 	security_req_classify_flow(req, flowi4_to_flowi(fl4));
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
@@ -474,33 +478,37 @@ static inline u32 inet_synq_hash(const __be32 raddr, const __be16 rport,
 #if IS_ENABLED(CONFIG_IPV6)
 #define AF_INET_FAMILY(fam) ((fam) == AF_INET)
 #else
-#define AF_INET_FAMILY(fam) 1
+#define AF_INET_FAMILY(fam) true
 #endif
 
-struct request_sock *inet_csk_search_req(const struct sock *sk,
-					 struct request_sock ***prevp,
-					 const __be16 rport, const __be32 raddr,
+/* Note: this is temporary :
+ * req sock will no longer be in listener hash table
+*/
+struct request_sock *inet_csk_search_req(struct sock *sk,
+					 const __be16 rport,
+					 const __be32 raddr,
 					 const __be32 laddr)
 {
-	const struct inet_connection_sock *icsk = inet_csk(sk);
+	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt;
-	struct request_sock *req, **prev;
+	struct request_sock *req;
+	u32 hash = inet_synq_hash(raddr, rport, lopt->hash_rnd,
+				  lopt->nr_table_entries);
 
-	for (prev = &lopt->syn_table[inet_synq_hash(raddr, rport, lopt->hash_rnd,
-						    lopt->nr_table_entries)];
-	     (req = *prev) != NULL;
-	     prev = &req->dl_next) {
+	spin_lock(&icsk->icsk_accept_queue.syn_wait_lock);
+	for (req = lopt->syn_table[hash]; req != NULL; req = req->dl_next) {
 		const struct inet_request_sock *ireq = inet_rsk(req);
 
 		if (ireq->ir_rmt_port == rport &&
 		    ireq->ir_rmt_addr == raddr &&
 		    ireq->ir_loc_addr == laddr &&
 		    AF_INET_FAMILY(req->rsk_ops->family)) {
+			atomic_inc(&req->rsk_refcnt);
 			WARN_ON(req->sk);
-			*prevp = prev;
 			break;
 		}
 	}
+	spin_unlock(&icsk->icsk_accept_queue.syn_wait_lock);
 
 	return req;
 }
@@ -556,23 +564,58 @@ int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req)
 }
 EXPORT_SYMBOL(inet_rtx_syn_ack);
 
-void inet_csk_reqsk_queue_prune(struct sock *parent,
-				const unsigned long interval,
-				const unsigned long timeout,
-				const unsigned long max_rto)
+/* return true if req was found in the syn_table[] */
+static bool reqsk_queue_unlink(struct request_sock_queue *queue,
+			       struct request_sock *req)
+{
+	struct listen_sock *lopt = queue->listen_opt;
+	struct request_sock **prev;
+	bool found = false;
+
+	spin_lock(&queue->syn_wait_lock);
+
+	for (prev = &lopt->syn_table[req->rsk_hash]; *prev != NULL;
+	     prev = &(*prev)->dl_next) {
+		if (*prev == req) {
+			*prev = req->dl_next;
+			found = true;
+			break;
+		}
+	}
+
+	spin_unlock(&queue->syn_wait_lock);
+	if (del_timer(&req->rsk_timer))
+		reqsk_put(req);
+	return found;
+}
+
+void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req)
 {
-	struct inet_connection_sock *icsk = inet_csk(parent);
+	if (reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req)) {
+		reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
+		reqsk_put(req);
+	}
+}
+EXPORT_SYMBOL(inet_csk_reqsk_queue_drop);
+
+static void reqsk_timer_handler(unsigned long data)
+{
+	struct request_sock *req = (struct request_sock *)data;
+	struct sock *sk_listener = req->rsk_listener;
+	struct inet_connection_sock *icsk = inet_csk(sk_listener);
 	struct request_sock_queue *queue = &icsk->icsk_accept_queue;
 	struct listen_sock *lopt = queue->listen_opt;
-	int max_retries = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries;
-	int thresh = max_retries;
-	unsigned long now = jiffies;
-	struct request_sock **reqp, *req;
-	int i, budget;
+	int qlen, expire = 0, resend = 0;
+	int max_retries, thresh;
+	u8 defer_accept;
 
-	if (lopt == NULL || lopt->qlen == 0)
+	if (sk_listener->sk_state != TCP_LISTEN || !lopt) {
+		reqsk_put(req);
 		return;
+	}
 
+	max_retries = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries;
+	thresh = max_retries;
 	/* Normally all the openreqs are young and become mature
 	 * (i.e. converted to established socket) for first timeout.
 	 * If synack was not acknowledged for 1 second, it means
@@ -590,67 +633,65 @@ void inet_csk_reqsk_queue_prune(struct sock *parent,
 	 * embrions; and abort old ones without pity, if old
 	 * ones are about to clog our table.
 	 */
-	if (lopt->qlen>>(lopt->max_qlen_log-1)) {
-		int young = (lopt->qlen_young<<1);
+	qlen = listen_sock_qlen(lopt);
+	if (qlen >> (lopt->max_qlen_log - 1)) {
+		int young = listen_sock_young(lopt) << 1;
 
 		while (thresh > 2) {
-			if (lopt->qlen < young)
+			if (qlen < young)
 				break;
 			thresh--;
 			young <<= 1;
 		}
 	}
+	defer_accept = READ_ONCE(queue->rskq_defer_accept);
+	if (defer_accept)
+		max_retries = defer_accept;
+	syn_ack_recalc(req, thresh, max_retries, defer_accept,
+		       &expire, &resend);
+	req->rsk_ops->syn_ack_timeout(req);
+	if (!expire &&
+	    (!resend ||
+	     !inet_rtx_syn_ack(sk_listener, req) ||
+	     inet_rsk(req)->acked)) {
+		unsigned long timeo;
+
+		if (req->num_timeout++ == 0)
+			atomic_inc(&lopt->young_dec);
+		timeo = min(TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX);
+		mod_timer_pinned(&req->rsk_timer, jiffies + timeo);
+		return;
+	}
+	inet_csk_reqsk_queue_drop(sk_listener, req);
+	reqsk_put(req);
+}
 
-	if (queue->rskq_defer_accept)
-		max_retries = queue->rskq_defer_accept;
-
-	budget = 2 * (lopt->nr_table_entries / (timeout / interval));
-	i = lopt->clock_hand;
-
-	do {
-		reqp=&lopt->syn_table[i];
-		while ((req = *reqp) != NULL) {
-			if (time_after_eq(now, req->expires)) {
-				int expire = 0, resend = 0;
-
-				syn_ack_recalc(req, thresh, max_retries,
-					       queue->rskq_defer_accept,
-					       &expire, &resend);
-				req->rsk_ops->syn_ack_timeout(parent, req);
-				if (!expire &&
-				    (!resend ||
-				     !inet_rtx_syn_ack(parent, req) ||
-				     inet_rsk(req)->acked)) {
-					unsigned long timeo;
-
-					if (req->num_timeout++ == 0)
-						lopt->qlen_young--;
-					timeo = min(timeout << req->num_timeout,
-						    max_rto);
-					req->expires = now + timeo;
-					reqp = &req->dl_next;
-					continue;
-				}
-
-				/* Drop this request */
-				inet_csk_reqsk_queue_unlink(parent, req, reqp);
-				reqsk_queue_removed(queue, req);
-				reqsk_free(req);
-				continue;
-			}
-			reqp = &req->dl_next;
-		}
+void reqsk_queue_hash_req(struct request_sock_queue *queue,
+			  u32 hash, struct request_sock *req,
+			  unsigned long timeout)
+{
+	struct listen_sock *lopt = queue->listen_opt;
 
-		i = (i + 1) & (lopt->nr_table_entries - 1);
+	req->num_retrans = 0;
+	req->num_timeout = 0;
+	req->sk = NULL;
 
-	} while (--budget > 0);
+	/* before letting lookups find us, make sure all req fields
+	 * are committed to memory and refcnt initialized.
+	 */
+	smp_wmb();
+	atomic_set(&req->rsk_refcnt, 2);
+	setup_timer(&req->rsk_timer, reqsk_timer_handler, (unsigned long)req);
+	req->rsk_hash = hash;
 
-	lopt->clock_hand = i;
+	spin_lock(&queue->syn_wait_lock);
+	req->dl_next = lopt->syn_table[hash];
+	lopt->syn_table[hash] = req;
+	spin_unlock(&queue->syn_wait_lock);
 
-	if (lopt->qlen)
-		inet_csk_reset_keepalive_timer(parent, interval);
+	mod_timer_pinned(&req->rsk_timer, jiffies + timeout);
 }
-EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_prune);
+EXPORT_SYMBOL(reqsk_queue_hash_req);
 
 /**
  *	inet_csk_clone_lock - clone an inet socket, and lock its clone
@@ -666,7 +707,7 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
 {
 	struct sock *newsk = sk_clone_lock(sk, priority);
 
-	if (newsk != NULL) {
+	if (newsk) {
 		struct inet_connection_sock *newicsk = inet_csk(newsk);
 
 		newsk->sk_state = TCP_SYN_RECV;
@@ -678,6 +719,8 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
 		newsk->sk_write_space = sk_stream_write_space;
 
 		newsk->sk_mark = inet_rsk(req)->ir_mark;
+		atomic64_set(&newsk->sk_cookie,
+			     atomic64_read(&inet_rsk(req)->ir_cookie));
 
 		newicsk->icsk_retransmits = 0;
 		newicsk->icsk_backoff	  = 0;
@@ -784,8 +827,6 @@ void inet_csk_listen_stop(struct sock *sk)
 	struct request_sock *acc_req;
 	struct request_sock *req;
 
-	inet_csk_delete_keepalive_timer(sk);
-
 	/* make all the listen_opt local to us */
 	acc_req = reqsk_queue_yank_acceptq(queue);
 
@@ -815,9 +856,9 @@ void inet_csk_listen_stop(struct sock *sk)
 
 		percpu_counter_inc(sk->sk_prot->orphan_count);
 
-		if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->listener) {
+		if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) {
 			BUG_ON(tcp_sk(child)->fastopen_rsk != req);
-			BUG_ON(sk != tcp_rsk(req)->listener);
+			BUG_ON(sk != req->rsk_listener);
 
 			/* Paranoid, to prevent race condition if
 			 * an inbound pkt destined for child is
@@ -826,7 +867,6 @@ void inet_csk_listen_stop(struct sock *sk)
 			 * tcp_v4_destroy_sock().
 			 */
 			tcp_sk(child)->fastopen_rsk = NULL;
-			sock_put(sk);
 		}
 		inet_csk_destroy_sock(child);
 
@@ -835,9 +875,9 @@ void inet_csk_listen_stop(struct sock *sk)
 		sock_put(child);
 
 		sk_acceptq_removed(sk);
-		__reqsk_free(req);
+		reqsk_put(req);
 	}
-	if (queue->fastopenq != NULL) {
+	if (queue->fastopenq) {
 		/* Free all the reqs queued in rskq_rst_head. */
 		spin_lock_bh(&queue->fastopenq->lock);
 		acc_req = queue->fastopenq->rskq_rst_head;
@@ -845,7 +885,7 @@ void inet_csk_listen_stop(struct sock *sk)
 		spin_unlock_bh(&queue->fastopenq->lock);
 		while ((req = acc_req) != NULL) {
 			acc_req = req->dl_next;
-			__reqsk_free(req);
+			reqsk_put(req);
 		}
 	}
 	WARN_ON(sk->sk_ack_backlog);
@@ -869,7 +909,7 @@ int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname,
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 
-	if (icsk->icsk_af_ops->compat_getsockopt != NULL)
+	if (icsk->icsk_af_ops->compat_getsockopt)
 		return icsk->icsk_af_ops->compat_getsockopt(sk, level, optname,
 							    optval, optlen);
 	return icsk->icsk_af_ops->getsockopt(sk, level, optname,
@@ -882,7 +922,7 @@ int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname,
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 
-	if (icsk->icsk_af_ops->compat_setsockopt != NULL)
+	if (icsk->icsk_af_ops->compat_setsockopt)
 		return icsk->icsk_af_ops->compat_setsockopt(sk, level, optname,
 							    optval, optlen);
 	return icsk->icsk_af_ops->setsockopt(sk, level, optname,
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index e34dccbc4d70..4d32262c7502 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -38,16 +38,12 @@
 static const struct inet_diag_handler **inet_diag_table;
 
 struct inet_diag_entry {
-	__be32 *saddr;
-	__be32 *daddr;
+	const __be32 *saddr;
+	const __be32 *daddr;
 	u16 sport;
 	u16 dport;
 	u16 family;
 	u16 userlocks;
-#if IS_ENABLED(CONFIG_IPV6)
-	struct in6_addr saddr_storage;	/* for IPv4-mapped-IPv6 addresses */
-	struct in6_addr daddr_storage;	/* for IPv4-mapped-IPv6 addresses */
-#endif
 };
 
 static DEFINE_MUTEX(inet_diag_table_mutex);
@@ -65,28 +61,66 @@ static const struct inet_diag_handler *inet_diag_lock_handler(int proto)
 	return inet_diag_table[proto];
 }
 
-static inline void inet_diag_unlock_handler(
-	const struct inet_diag_handler *handler)
+static void inet_diag_unlock_handler(const struct inet_diag_handler *handler)
 {
 	mutex_unlock(&inet_diag_table_mutex);
 }
 
+static void inet_diag_msg_common_fill(struct inet_diag_msg *r, struct sock *sk)
+{
+	r->idiag_family = sk->sk_family;
+
+	r->id.idiag_sport = htons(sk->sk_num);
+	r->id.idiag_dport = sk->sk_dport;
+	r->id.idiag_if = sk->sk_bound_dev_if;
+	sock_diag_save_cookie(sk, r->id.idiag_cookie);
+
+#if IS_ENABLED(CONFIG_IPV6)
+	if (sk->sk_family == AF_INET6) {
+		*(struct in6_addr *)r->id.idiag_src = sk->sk_v6_rcv_saddr;
+		*(struct in6_addr *)r->id.idiag_dst = sk->sk_v6_daddr;
+	} else
+#endif
+	{
+	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] = sk->sk_rcv_saddr;
+	r->id.idiag_dst[0] = sk->sk_daddr;
+	}
+}
+
+static size_t inet_sk_attr_size(void)
+{
+	return	  nla_total_size(sizeof(struct tcp_info))
+		+ nla_total_size(1) /* INET_DIAG_SHUTDOWN */
+		+ nla_total_size(1) /* INET_DIAG_TOS */
+		+ nla_total_size(1) /* INET_DIAG_TCLASS */
+		+ nla_total_size(sizeof(struct inet_diag_meminfo))
+		+ nla_total_size(sizeof(struct inet_diag_msg))
+		+ nla_total_size(SK_MEMINFO_VARS * sizeof(u32))
+		+ nla_total_size(TCP_CA_NAME_MAX)
+		+ nla_total_size(sizeof(struct tcpvegas_info))
+		+ 64;
+}
+
 int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
-			      struct sk_buff *skb, struct inet_diag_req_v2 *req,
-			      struct user_namespace *user_ns,		      	
-			      u32 portid, u32 seq, u16 nlmsg_flags,
-			      const struct nlmsghdr *unlh)
+		      struct sk_buff *skb, const struct inet_diag_req_v2 *req,
+		      struct user_namespace *user_ns,
+		      u32 portid, u32 seq, u16 nlmsg_flags,
+		      const struct nlmsghdr *unlh)
 {
 	const struct inet_sock *inet = inet_sk(sk);
+	const struct tcp_congestion_ops *ca_ops;
+	const struct inet_diag_handler *handler;
+	int ext = req->idiag_ext;
 	struct inet_diag_msg *r;
 	struct nlmsghdr  *nlh;
 	struct nlattr *attr;
 	void *info = NULL;
-	const struct inet_diag_handler *handler;
-	int ext = req->idiag_ext;
 
 	handler = inet_diag_table[req->sdiag_protocol];
-	BUG_ON(handler == NULL);
+	BUG_ON(!handler);
 
 	nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r),
 			nlmsg_flags);
@@ -94,25 +128,13 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 		return -EMSGSIZE;
 
 	r = nlmsg_data(nlh);
-	BUG_ON(sk->sk_state == TCP_TIME_WAIT);
+	BUG_ON(!sk_fullsock(sk));
 
-	r->idiag_family = sk->sk_family;
+	inet_diag_msg_common_fill(r, sk);
 	r->idiag_state = sk->sk_state;
 	r->idiag_timer = 0;
 	r->idiag_retrans = 0;
 
-	r->id.idiag_if = sk->sk_bound_dev_if;
-	sock_diag_save_cookie(sk, r->id.idiag_cookie);
-
-	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;
-
 	if (nla_put_u8(skb, INET_DIAG_SHUTDOWN, sk->sk_shutdown))
 		goto errout;
 
@@ -125,10 +147,6 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 
 #if IS_ENABLED(CONFIG_IPV6)
 	if (r->idiag_family == AF_INET6) {
-
-		*(struct in6_addr *)r->id.idiag_src = sk->sk_v6_rcv_saddr;
-		*(struct in6_addr *)r->id.idiag_dst = sk->sk_v6_daddr;
-
 		if (ext & (1 << (INET_DIAG_TCLASS - 1)))
 			if (nla_put_u8(skb, INET_DIAG_TCLASS,
 				       inet6_sk(sk)->tclass) < 0)
@@ -155,7 +173,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 		if (sock_diag_put_meminfo(sk, skb, INET_DIAG_SKMEMINFO))
 			goto errout;
 
-	if (icsk == NULL) {
+	if (!icsk) {
 		handler->idiag_get_info(sk, r, NULL);
 		goto out;
 	}
@@ -191,19 +209,37 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 		info = nla_data(attr);
 	}
 
-	if ((ext & (1 << (INET_DIAG_CONG - 1))) && icsk->icsk_ca_ops)
-		if (nla_put_string(skb, INET_DIAG_CONG,
-				   icsk->icsk_ca_ops->name) < 0)
+	if (ext & (1 << (INET_DIAG_CONG - 1))) {
+		int err = 0;
+
+		rcu_read_lock();
+		ca_ops = READ_ONCE(icsk->icsk_ca_ops);
+		if (ca_ops)
+			err = nla_put_string(skb, INET_DIAG_CONG, ca_ops->name);
+		rcu_read_unlock();
+		if (err < 0)
 			goto errout;
+	}
 
 	handler->idiag_get_info(sk, r, info);
 
-	if (sk->sk_state < TCP_TIME_WAIT &&
-	    icsk->icsk_ca_ops && icsk->icsk_ca_ops->get_info)
-		icsk->icsk_ca_ops->get_info(sk, ext, skb);
+	if (sk->sk_state < TCP_TIME_WAIT) {
+		union tcp_cc_info info;
+		size_t sz = 0;
+		int attr;
+
+		rcu_read_lock();
+		ca_ops = READ_ONCE(icsk->icsk_ca_ops);
+		if (ca_ops && ca_ops->get_info)
+			sz = ca_ops->get_info(sk, ext, &attr, &info);
+		rcu_read_unlock();
+		if (sz && nla_put(skb, attr, sz, &info) < 0)
+			goto errout;
+	}
 
 out:
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 errout:
 	nlmsg_cancel(skb, nlh);
@@ -212,23 +248,25 @@ errout:
 EXPORT_SYMBOL_GPL(inet_sk_diag_fill);
 
 static int inet_csk_diag_fill(struct sock *sk,
-			      struct sk_buff *skb, struct inet_diag_req_v2 *req,
+			      struct sk_buff *skb,
+			      const struct inet_diag_req_v2 *req,
 			      struct user_namespace *user_ns,
 			      u32 portid, u32 seq, u16 nlmsg_flags,
 			      const struct nlmsghdr *unlh)
 {
-	return inet_sk_diag_fill(sk, inet_csk(sk),
-			skb, req, user_ns, portid, seq, nlmsg_flags, unlh);
+	return inet_sk_diag_fill(sk, inet_csk(sk), skb, req,
+				 user_ns, portid, seq, nlmsg_flags, unlh);
 }
 
-static int inet_twsk_diag_fill(struct inet_timewait_sock *tw,
-			       struct sk_buff *skb, struct inet_diag_req_v2 *req,
+static int inet_twsk_diag_fill(struct sock *sk,
+			       struct sk_buff *skb,
 			       u32 portid, u32 seq, u16 nlmsg_flags,
 			       const struct nlmsghdr *unlh)
 {
-	s32 tmo;
+	struct inet_timewait_sock *tw = inet_twsk(sk);
 	struct inet_diag_msg *r;
 	struct nlmsghdr *nlh;
+	long tmo;
 
 	nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r),
 			nlmsg_flags);
@@ -238,25 +276,13 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw,
 	r = nlmsg_data(nlh);
 	BUG_ON(tw->tw_state != TCP_TIME_WAIT);
 
-	tmo = tw->tw_ttd - inet_tw_time_stamp();
+	tmo = tw->tw_timer.expires - jiffies;
 	if (tmo < 0)
 		tmo = 0;
 
-	r->idiag_family	      = tw->tw_family;
+	inet_diag_msg_common_fill(r, sk);
 	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);
@@ -264,69 +290,98 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw,
 	r->idiag_wqueue	      = 0;
 	r->idiag_uid	      = 0;
 	r->idiag_inode	      = 0;
-#if IS_ENABLED(CONFIG_IPV6)
-	if (tw->tw_family == AF_INET6) {
-		*(struct in6_addr *)r->id.idiag_src = tw->tw_v6_rcv_saddr;
-		*(struct in6_addr *)r->id.idiag_dst = tw->tw_v6_daddr;
-	}
-#endif
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
+}
+
+static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb,
+			      u32 portid, u32 seq, u16 nlmsg_flags,
+			      const struct nlmsghdr *unlh)
+{
+	struct inet_diag_msg *r;
+	struct nlmsghdr *nlh;
+	long tmo;
+
+	nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r),
+			nlmsg_flags);
+	if (!nlh)
+		return -EMSGSIZE;
+
+	r = nlmsg_data(nlh);
+	inet_diag_msg_common_fill(r, sk);
+	r->idiag_state = TCP_SYN_RECV;
+	r->idiag_timer = 1;
+	r->idiag_retrans = inet_reqsk(sk)->num_retrans;
+
+	BUILD_BUG_ON(offsetof(struct inet_request_sock, ir_cookie) !=
+		     offsetof(struct sock, sk_cookie));
+
+	tmo = inet_reqsk(sk)->rsk_timer.expires - jiffies;
+	r->idiag_expires = (tmo >= 0) ? jiffies_to_msecs(tmo) : 0;
+	r->idiag_rqueue	= 0;
+	r->idiag_wqueue	= 0;
+	r->idiag_uid	= 0;
+	r->idiag_inode	= 0;
+
+	nlmsg_end(skb, nlh);
+	return 0;
 }
 
 static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
-			struct inet_diag_req_v2 *r,
+			const struct inet_diag_req_v2 *r,
 			struct user_namespace *user_ns,
 			u32 portid, u32 seq, u16 nlmsg_flags,
 			const struct nlmsghdr *unlh)
 {
 	if (sk->sk_state == TCP_TIME_WAIT)
-		return inet_twsk_diag_fill(inet_twsk(sk), skb, r, portid, seq,
+		return inet_twsk_diag_fill(sk, skb, portid, seq,
 					   nlmsg_flags, unlh);
 
+	if (sk->sk_state == TCP_NEW_SYN_RECV)
+		return inet_req_diag_fill(sk, skb, portid, seq,
+					  nlmsg_flags, unlh);
+
 	return inet_csk_diag_fill(sk, skb, r, user_ns, portid, seq,
 				  nlmsg_flags, unlh);
 }
 
-int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_skb,
-		const struct nlmsghdr *nlh, struct inet_diag_req_v2 *req)
+int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo,
+			    struct sk_buff *in_skb,
+			    const struct nlmsghdr *nlh,
+			    const struct inet_diag_req_v2 *req)
 {
-	int err;
-	struct sock *sk;
-	struct sk_buff *rep;
 	struct net *net = sock_net(in_skb->sk);
+	struct sk_buff *rep;
+	struct sock *sk;
+	int err;
 
 	err = -EINVAL;
-	if (req->sdiag_family == AF_INET) {
+	if (req->sdiag_family == AF_INET)
 		sk = inet_lookup(net, hashinfo, req->id.idiag_dst[0],
 				 req->id.idiag_dport, req->id.idiag_src[0],
 				 req->id.idiag_sport, req->id.idiag_if);
-	}
 #if IS_ENABLED(CONFIG_IPV6)
-	else if (req->sdiag_family == AF_INET6) {
+	else if (req->sdiag_family == AF_INET6)
 		sk = inet6_lookup(net, hashinfo,
 				  (struct in6_addr *)req->id.idiag_dst,
 				  req->id.idiag_dport,
 				  (struct in6_addr *)req->id.idiag_src,
 				  req->id.idiag_sport,
 				  req->id.idiag_if);
-	}
 #endif
-	else {
+	else
 		goto out_nosk;
-	}
 
 	err = -ENOENT;
-	if (sk == NULL)
+	if (!sk)
 		goto out_nosk;
 
 	err = sock_diag_check_cookie(sk, req->id.idiag_cookie);
 	if (err)
 		goto out;
 
-	rep = nlmsg_new(sizeof(struct inet_diag_msg) +
-			sizeof(struct inet_diag_meminfo) +
-			sizeof(struct tcp_info) + 64, GFP_KERNEL);
+	rep = nlmsg_new(inet_sk_attr_size(), GFP_KERNEL);
 	if (!rep) {
 		err = -ENOMEM;
 		goto out;
@@ -357,7 +412,7 @@ EXPORT_SYMBOL_GPL(inet_diag_dump_one_icsk);
 
 static int inet_diag_get_exact(struct sk_buff *in_skb,
 			       const struct nlmsghdr *nlh,
-			       struct inet_diag_req_v2 *req)
+			       const struct inet_diag_req_v2 *req)
 {
 	const struct inet_diag_handler *handler;
 	int err;
@@ -398,9 +453,8 @@ static int bitstring_match(const __be32 *a1, const __be32 *a2, int bits)
 	return 1;
 }
 
-
 static int inet_diag_bc_run(const struct nlattr *_bc,
-		const struct inet_diag_entry *entry)
+			    const struct inet_diag_entry *entry)
 {
 	const void *bc = nla_data(_bc);
 	int len = nla_len(_bc);
@@ -432,10 +486,10 @@ static int inet_diag_bc_run(const struct nlattr *_bc,
 			break;
 		case INET_DIAG_BC_S_COND:
 		case INET_DIAG_BC_D_COND: {
-			struct inet_diag_hostcond *cond;
-			__be32 *addr;
+			const struct inet_diag_hostcond *cond;
+			const __be32 *addr;
 
-			cond = (struct inet_diag_hostcond *)(op + 1);
+			cond = (const struct inet_diag_hostcond *)(op + 1);
 			if (cond->port != -1 &&
 			    cond->port != (op->code == INET_DIAG_BC_S_COND ?
 					     entry->sport : entry->dport)) {
@@ -484,29 +538,36 @@ static int inet_diag_bc_run(const struct nlattr *_bc,
 	return len == 0;
 }
 
+/* This helper is available for all sockets (ESTABLISH, TIMEWAIT, SYN_RECV)
+ */
+static void entry_fill_addrs(struct inet_diag_entry *entry,
+			     const struct sock *sk)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	if (sk->sk_family == AF_INET6) {
+		entry->saddr = sk->sk_v6_rcv_saddr.s6_addr32;
+		entry->daddr = sk->sk_v6_daddr.s6_addr32;
+	} else
+#endif
+	{
+		entry->saddr = &sk->sk_rcv_saddr;
+		entry->daddr = &sk->sk_daddr;
+	}
+}
+
 int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk)
 {
-	struct inet_diag_entry entry;
 	struct inet_sock *inet = inet_sk(sk);
+	struct inet_diag_entry entry;
 
-	if (bc == NULL)
+	if (!bc)
 		return 1;
 
 	entry.family = sk->sk_family;
-#if IS_ENABLED(CONFIG_IPV6)
-	if (entry.family == AF_INET6) {
-
-		entry.saddr = sk->sk_v6_rcv_saddr.s6_addr32;
-		entry.daddr = sk->sk_v6_daddr.s6_addr32;
-	} else
-#endif
-	{
-		entry.saddr = &inet->inet_rcv_saddr;
-		entry.daddr = &inet->inet_daddr;
-	}
+	entry_fill_addrs(&entry, sk);
 	entry.sport = inet->inet_num;
 	entry.dport = ntohs(inet->inet_dport);
-	entry.userlocks = sk->sk_userlocks;
+	entry.userlocks = sk_fullsock(sk) ? sk->sk_userlocks : 0;
 
 	return inet_diag_bc_run(bc, &entry);
 }
@@ -533,8 +594,8 @@ static int valid_cc(const void *bc, int len, int cc)
 static bool valid_hostcond(const struct inet_diag_bc_op *op, int len,
 			   int *min_len)
 {
-	int addr_len;
 	struct inet_diag_hostcond *cond;
+	int addr_len;
 
 	/* Check hostcond space. */
 	*min_len += sizeof(struct inet_diag_hostcond);
@@ -568,8 +629,8 @@ static bool valid_hostcond(const struct inet_diag_bc_op *op, int len,
 }
 
 /* Validate a port comparison operator. */
-static inline bool valid_port_comparison(const struct inet_diag_bc_op *op,
-					 int len, int *min_len)
+static bool valid_port_comparison(const struct inet_diag_bc_op *op,
+				  int len, int *min_len)
 {
 	/* Port comparisons put the port in a follow-on inet_diag_bc_op. */
 	*min_len += sizeof(struct inet_diag_bc_op);
@@ -584,10 +645,9 @@ static int inet_diag_bc_audit(const void *bytecode, int bytecode_len)
 	int  len = bytecode_len;
 
 	while (len > 0) {
-		const struct inet_diag_bc_op *op = bc;
 		int min_len = sizeof(struct inet_diag_bc_op);
+		const struct inet_diag_bc_op *op = bc;
 
-//printk("BC: %d %d %d {%d} / %d\n", op->code, op->yes, op->no, op[1].no, len);
 		switch (op->code) {
 		case INET_DIAG_BC_S_COND:
 		case INET_DIAG_BC_D_COND:
@@ -628,7 +688,7 @@ static int inet_diag_bc_audit(const void *bytecode, int bytecode_len)
 static int inet_csk_diag_dump(struct sock *sk,
 			      struct sk_buff *skb,
 			      struct netlink_callback *cb,
-			      struct inet_diag_req_v2 *r,
+			      const struct inet_diag_req_v2 *r,
 			      const struct nlattr *bc)
 {
 	if (!inet_diag_bc_sk(bc, sk))
@@ -640,138 +700,42 @@ static int inet_csk_diag_dump(struct sock *sk,
 				  cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh);
 }
 
-static int inet_twsk_diag_dump(struct sock *sk,
-			       struct sk_buff *skb,
-			       struct netlink_callback *cb,
-			       struct inet_diag_req_v2 *r,
-			       const struct nlattr *bc)
+static void twsk_build_assert(void)
 {
-	struct inet_timewait_sock *tw = inet_twsk(sk);
-
-	if (bc != NULL) {
-		struct inet_diag_entry entry;
+	BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_family) !=
+		     offsetof(struct sock, sk_family));
 
-		entry.family = tw->tw_family;
-#if IS_ENABLED(CONFIG_IPV6)
-		if (tw->tw_family == AF_INET6) {
-			entry.saddr = tw->tw_v6_rcv_saddr.s6_addr32;
-			entry.daddr = tw->tw_v6_daddr.s6_addr32;
-		} else
-#endif
-		{
-			entry.saddr = &tw->tw_rcv_saddr;
-			entry.daddr = &tw->tw_daddr;
-		}
-		entry.sport = tw->tw_num;
-		entry.dport = ntohs(tw->tw_dport);
-		entry.userlocks = 0;
+	BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_num) !=
+		     offsetof(struct inet_sock, inet_num));
 
-		if (!inet_diag_bc_run(bc, &entry))
-			return 0;
-	}
+	BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_dport) !=
+		     offsetof(struct inet_sock, inet_dport));
 
-	return inet_twsk_diag_fill(tw, skb, r,
-				   NETLINK_CB(cb->skb).portid,
-				   cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh);
-}
+	BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_rcv_saddr) !=
+		     offsetof(struct inet_sock, inet_rcv_saddr));
 
-/* Get the IPv4, IPv6, or IPv4-mapped-IPv6 local and remote addresses
- * from a request_sock. For IPv4-mapped-IPv6 we must map IPv4 to IPv6.
- */
-static inline void inet_diag_req_addrs(const struct sock *sk,
-				       const struct request_sock *req,
-				       struct inet_diag_entry *entry)
-{
-	struct inet_request_sock *ireq = inet_rsk(req);
+	BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_daddr) !=
+		     offsetof(struct inet_sock, inet_daddr));
 
 #if IS_ENABLED(CONFIG_IPV6)
-	if (sk->sk_family == AF_INET6) {
-		if (req->rsk_ops->family == AF_INET6) {
-			entry->saddr = ireq->ir_v6_loc_addr.s6_addr32;
-			entry->daddr = ireq->ir_v6_rmt_addr.s6_addr32;
-		} else if (req->rsk_ops->family == AF_INET) {
-			ipv6_addr_set_v4mapped(ireq->ir_loc_addr,
-					       &entry->saddr_storage);
-			ipv6_addr_set_v4mapped(ireq->ir_rmt_addr,
-					       &entry->daddr_storage);
-			entry->saddr = entry->saddr_storage.s6_addr32;
-			entry->daddr = entry->daddr_storage.s6_addr32;
-		}
-	} else
-#endif
-	{
-		entry->saddr = &ireq->ir_loc_addr;
-		entry->daddr = &ireq->ir_rmt_addr;
-	}
-}
-
-static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk,
-			      struct request_sock *req,
-			      struct user_namespace *user_ns,
-			      u32 portid, u32 seq,
-			      const struct nlmsghdr *unlh)
-{
-	const struct inet_request_sock *ireq = inet_rsk(req);
-	struct inet_sock *inet = inet_sk(sk);
-	struct inet_diag_msg *r;
-	struct nlmsghdr *nlh;
-	long tmo;
-
-	nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r),
-			NLM_F_MULTI);
-	if (!nlh)
-		return -EMSGSIZE;
-
-	r = nlmsg_data(nlh);
-	r->idiag_family = sk->sk_family;
-	r->idiag_state = TCP_SYN_RECV;
-	r->idiag_timer = 1;
-	r->idiag_retrans = req->num_retrans;
-
-	r->id.idiag_if = sk->sk_bound_dev_if;
-	sock_diag_save_cookie(req, r->id.idiag_cookie);
-
-	tmo = req->expires - jiffies;
-	if (tmo < 0)
-		tmo = 0;
+	BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_v6_rcv_saddr) !=
+		     offsetof(struct sock, sk_v6_rcv_saddr));
 
-	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;
-	r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk));
-	r->idiag_inode = 0;
-#if IS_ENABLED(CONFIG_IPV6)
-	if (r->idiag_family == AF_INET6) {
-		struct inet_diag_entry entry;
-		inet_diag_req_addrs(sk, req, &entry);
-		memcpy(r->id.idiag_src, entry.saddr, sizeof(struct in6_addr));
-		memcpy(r->id.idiag_dst, entry.daddr, sizeof(struct in6_addr));
-	}
+	BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_v6_daddr) !=
+		     offsetof(struct sock, sk_v6_daddr));
 #endif
-
-	return nlmsg_end(skb, nlh);
 }
 
 static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk,
 			       struct netlink_callback *cb,
-			       struct inet_diag_req_v2 *r,
+			       const struct inet_diag_req_v2 *r,
 			       const struct nlattr *bc)
 {
-	struct inet_diag_entry entry;
 	struct inet_connection_sock *icsk = inet_csk(sk);
-	struct listen_sock *lopt;
 	struct inet_sock *inet = inet_sk(sk);
-	int j, s_j;
-	int reqnum, s_reqnum;
+	struct inet_diag_entry entry;
+	int j, s_j, reqnum, s_reqnum;
+	struct listen_sock *lopt;
 	int err = 0;
 
 	s_j = cb->args[3];
@@ -782,13 +746,13 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk,
 
 	entry.family = sk->sk_family;
 
-	read_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
+	spin_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
 
 	lopt = icsk->icsk_accept_queue.listen_opt;
-	if (!lopt || !lopt->qlen)
+	if (!lopt || !listen_sock_qlen(lopt))
 		goto out;
 
-	if (bc != NULL) {
+	if (bc) {
 		entry.sport = inet->inet_num;
 		entry.userlocks = sk->sk_userlocks;
 	}
@@ -807,17 +771,18 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk,
 				continue;
 
 			if (bc) {
-				inet_diag_req_addrs(sk, req, &entry);
+				/* Note: entry.sport and entry.userlocks are already set */
+				entry_fill_addrs(&entry, req_to_sk(req));
 				entry.dport = ntohs(ireq->ir_rmt_port);
 
 				if (!inet_diag_bc_run(bc, &entry))
 					continue;
 			}
 
-			err = inet_diag_fill_req(skb, sk, req,
-					       sk_user_ns(NETLINK_CB(cb->skb).sk),
-					       NETLINK_CB(cb->skb).portid,
-					       cb->nlh->nlmsg_seq, cb->nlh);
+			err = inet_req_diag_fill(req_to_sk(req), skb,
+						 NETLINK_CB(cb->skb).portid,
+						 cb->nlh->nlmsg_seq,
+						 NLM_F_MULTI, cb->nlh);
 			if (err < 0) {
 				cb->args[3] = j + 1;
 				cb->args[4] = reqnum;
@@ -829,17 +794,17 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk,
 	}
 
 out:
-	read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
+	spin_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
 
 	return err;
 }
 
 void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb,
-		struct netlink_callback *cb, struct inet_diag_req_v2 *r, struct nlattr *bc)
+			 struct netlink_callback *cb,
+			 const struct inet_diag_req_v2 *r, struct nlattr *bc)
 {
-	int i, num;
-	int s_i, s_num;
 	struct net *net = sock_net(skb->sk);
+	int i, num, s_i, s_num;
 
 	s_i = cb->args[1];
 	s_num = num = cb->args[2];
@@ -849,9 +814,9 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb,
 			goto skip_listen_ht;
 
 		for (i = s_i; i < INET_LHTABLE_SIZE; i++) {
-			struct sock *sk;
-			struct hlist_nulls_node *node;
 			struct inet_listen_hashbucket *ilb;
+			struct hlist_nulls_node *node;
+			struct sock *sk;
 
 			num = 0;
 			ilb = &hashinfo->listening_hash[i];
@@ -868,7 +833,7 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb,
 				}
 
 				if (r->sdiag_family != AF_UNSPEC &&
-						sk->sk_family != r->sdiag_family)
+				    sk->sk_family != r->sdiag_family)
 					goto next_listen;
 
 				if (r->id.idiag_sport != inet->inet_sport &&
@@ -916,8 +881,8 @@ skip_listen_ht:
 	for (i = s_i; i <= hashinfo->ehash_mask; i++) {
 		struct inet_ehash_bucket *head = &hashinfo->ehash[i];
 		spinlock_t *lock = inet_ehash_lockp(hashinfo, i);
-		struct sock *sk;
 		struct hlist_nulls_node *node;
+		struct sock *sk;
 
 		num = 0;
 
@@ -929,8 +894,7 @@ skip_listen_ht:
 
 		spin_lock_bh(lock);
 		sk_nulls_for_each(sk, node, &head->chain) {
-			int res;
-			int state;
+			int state, res;
 
 			if (!net_eq(sock_net(sk), net))
 				continue;
@@ -949,10 +913,16 @@ skip_listen_ht:
 			if (r->id.idiag_dport != sk->sk_dport &&
 			    r->id.idiag_dport)
 				goto next_normal;
-			if (sk->sk_state == TCP_TIME_WAIT)
-				res = inet_twsk_diag_dump(sk, skb, cb, r, bc);
-			else
-				res = inet_csk_diag_dump(sk, skb, cb, r, bc);
+			twsk_build_assert();
+
+			if (!inet_diag_bc_sk(bc, sk))
+				goto next_normal;
+
+			res = sk_diag_fill(sk, skb, r,
+					   sk_user_ns(NETLINK_CB(cb->skb).sk),
+					   NETLINK_CB(cb->skb).portid,
+					   cb->nlh->nlmsg_seq, NLM_F_MULTI,
+					   cb->nlh);
 			if (res < 0) {
 				spin_unlock_bh(lock);
 				goto done;
@@ -973,7 +943,8 @@ out:
 EXPORT_SYMBOL_GPL(inet_diag_dump_icsk);
 
 static int __inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
-		struct inet_diag_req_v2 *r, struct nlattr *bc)
+			    const struct inet_diag_req_v2 *r,
+			    struct nlattr *bc)
 {
 	const struct inet_diag_handler *handler;
 	int err = 0;
@@ -990,8 +961,8 @@ static int __inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
 
 static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
 {
-	struct nlattr *bc = NULL;
 	int hdrlen = sizeof(struct inet_diag_req_v2);
+	struct nlattr *bc = NULL;
 
 	if (nlmsg_attrlen(cb->nlh, hdrlen))
 		bc = nlmsg_find_attr(cb->nlh, hdrlen, INET_DIAG_REQ_BYTECODE);
@@ -999,7 +970,7 @@ static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	return __inet_diag_dump(skb, cb, nlmsg_data(cb->nlh), bc);
 }
 
-static inline int inet_diag_type2proto(int type)
+static int inet_diag_type2proto(int type)
 {
 	switch (type) {
 	case TCPDIAG_GETSOCK:
@@ -1011,12 +982,13 @@ static inline int inet_diag_type2proto(int type)
 	}
 }
 
-static int inet_diag_dump_compat(struct sk_buff *skb, struct netlink_callback *cb)
+static int inet_diag_dump_compat(struct sk_buff *skb,
+				 struct netlink_callback *cb)
 {
 	struct inet_diag_req *rc = nlmsg_data(cb->nlh);
+	int hdrlen = sizeof(struct inet_diag_req);
 	struct inet_diag_req_v2 req;
 	struct nlattr *bc = NULL;
-	int hdrlen = sizeof(struct inet_diag_req);
 
 	req.sdiag_family = AF_UNSPEC; /* compatibility */
 	req.sdiag_protocol = inet_diag_type2proto(cb->nlh->nlmsg_type);
@@ -1031,7 +1003,7 @@ static int inet_diag_dump_compat(struct sk_buff *skb, struct netlink_callback *c
 }
 
 static int inet_diag_get_exact_compat(struct sk_buff *in_skb,
-			       const struct nlmsghdr *nlh)
+				      const struct nlmsghdr *nlh)
 {
 	struct inet_diag_req *rc = nlmsg_data(nlh);
 	struct inet_diag_req_v2 req;
@@ -1060,7 +1032,7 @@ static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 			attr = nlmsg_find_attr(nlh, hdrlen,
 					       INET_DIAG_REQ_BYTECODE);
-			if (attr == NULL ||
+			if (!attr ||
 			    nla_len(attr) < sizeof(struct inet_diag_bc_op) ||
 			    inet_diag_bc_audit(nla_data(attr), nla_len(attr)))
 				return -EINVAL;
@@ -1087,9 +1059,10 @@ static int inet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h)
 	if (h->nlmsg_flags & NLM_F_DUMP) {
 		if (nlmsg_attrlen(h, hdrlen)) {
 			struct nlattr *attr;
+
 			attr = nlmsg_find_attr(h, hdrlen,
 					       INET_DIAG_REQ_BYTECODE);
-			if (attr == NULL ||
+			if (!attr ||
 			    nla_len(attr) < sizeof(struct inet_diag_bc_op) ||
 			    inet_diag_bc_audit(nla_data(attr), nla_len(attr)))
 				return -EINVAL;
@@ -1125,7 +1098,7 @@ int inet_diag_register(const struct inet_diag_handler *h)
 
 	mutex_lock(&inet_diag_table_mutex);
 	err = -EEXIST;
-	if (inet_diag_table[type] == NULL) {
+	if (!inet_diag_table[type]) {
 		inet_diag_table[type] = h;
 		err = 0;
 	}
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 19419b60cb37..5e346a082e5f 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -385,7 +385,7 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
 	}
 
 	q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC);
-	if (q == NULL)
+	if (!q)
 		return NULL;
 
 	q->net = nf;
@@ -406,7 +406,7 @@ static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf,
 	struct inet_frag_queue *q;
 
 	q = inet_frag_alloc(nf, f, arg);
-	if (q == NULL)
+	if (!q)
 		return NULL;
 
 	return inet_frag_intern(nf, q, f, arg);
@@ -458,6 +458,6 @@ void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
 		". Dropping fragment.\n";
 
 	if (PTR_ERR(q) == -ENOBUFS)
-		LIMIT_NETDEBUG(KERN_WARNING "%s%s", prefix, msg);
+		net_dbg_ratelimited("%s%s", prefix, msg);
 }
 EXPORT_SYMBOL(inet_frag_maybe_warn_overflow);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 9111a4e22155..c6fb80bd5826 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -24,9 +24,9 @@
 #include <net/secure_seq.h>
 #include <net/ip.h>
 
-static unsigned int inet_ehashfn(struct net *net, const __be32 laddr,
-				 const __u16 lport, const __be32 faddr,
-				 const __be16 fport)
+static u32 inet_ehashfn(const struct net *net, const __be32 laddr,
+			const __u16 lport, const __be32 faddr,
+			const __be16 fport)
 {
 	static u32 inet_ehash_secret __read_mostly;
 
@@ -36,17 +36,21 @@ static unsigned int inet_ehashfn(struct net *net, const __be32 laddr,
 			      inet_ehash_secret + net_hash_mix(net));
 }
 
-
-static unsigned int inet_sk_ehashfn(const struct sock *sk)
+/* This function handles inet_sock, but also timewait and request sockets
+ * for IPv4/IPv6.
+ */
+u32 sk_ehashfn(const struct sock *sk)
 {
-	const struct inet_sock *inet = inet_sk(sk);
-	const __be32 laddr = inet->inet_rcv_saddr;
-	const __u16 lport = inet->inet_num;
-	const __be32 faddr = inet->inet_daddr;
-	const __be16 fport = inet->inet_dport;
-	struct net *net = sock_net(sk);
-
-	return inet_ehashfn(net, laddr, lport, faddr, fport);
+#if IS_ENABLED(CONFIG_IPV6)
+	if (sk->sk_family == AF_INET6 &&
+	    !ipv6_addr_v4mapped(&sk->sk_v6_daddr))
+		return inet6_ehashfn(sock_net(sk),
+				     &sk->sk_v6_rcv_saddr, sk->sk_num,
+				     &sk->sk_v6_daddr, sk->sk_dport);
+#endif
+	return inet_ehashfn(sock_net(sk),
+			    sk->sk_rcv_saddr, sk->sk_num,
+			    sk->sk_daddr, sk->sk_dport);
 }
 
 /*
@@ -60,8 +64,8 @@ struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep,
 {
 	struct inet_bind_bucket *tb = kmem_cache_alloc(cachep, GFP_ATOMIC);
 
-	if (tb != NULL) {
-		write_pnet(&tb->ib_net, hold_net(net));
+	if (tb) {
+		write_pnet(&tb->ib_net, net);
 		tb->port      = snum;
 		tb->fastreuse = 0;
 		tb->fastreuseport = 0;
@@ -79,7 +83,6 @@ void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket
 {
 	if (hlist_empty(&tb->owners)) {
 		__hlist_del(&tb->node);
-		release_net(ib_net(tb));
 		kmem_cache_free(cachep, tb);
 	}
 }
@@ -263,11 +266,19 @@ void sock_gen_put(struct sock *sk)
 
 	if (sk->sk_state == TCP_TIME_WAIT)
 		inet_twsk_free(inet_twsk(sk));
+	else if (sk->sk_state == TCP_NEW_SYN_RECV)
+		reqsk_free(inet_reqsk(sk));
 	else
 		sk_free(sk);
 }
 EXPORT_SYMBOL_GPL(sock_gen_put);
 
+void sock_edemux(struct sk_buff *skb)
+{
+	sock_gen_put(skb->sk);
+}
+EXPORT_SYMBOL(sock_edemux);
+
 struct sock *__inet_lookup_established(struct net *net,
 				  struct inet_hashinfo *hashinfo,
 				  const __be32 saddr, const __be16 sport,
@@ -377,7 +388,7 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row,
 		*twp = tw;
 	} else if (tw) {
 		/* Silly. Should hash-dance instead... */
-		inet_twsk_deschedule(tw, death_row);
+		inet_twsk_deschedule(tw);
 
 		inet_twsk_put(tw);
 	}
@@ -400,13 +411,13 @@ int __inet_hash_nolisten(struct sock *sk, struct inet_timewait_sock *tw)
 {
 	struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
 	struct hlist_nulls_head *list;
-	spinlock_t *lock;
 	struct inet_ehash_bucket *head;
+	spinlock_t *lock;
 	int twrefcnt = 0;
 
 	WARN_ON(!sk_unhashed(sk));
 
-	sk->sk_hash = inet_sk_ehashfn(sk);
+	sk->sk_hash = sk_ehashfn(sk);
 	head = inet_ehash_bucket(hashinfo, sk->sk_hash);
 	list = &head->chain;
 	lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
@@ -423,15 +434,13 @@ int __inet_hash_nolisten(struct sock *sk, struct inet_timewait_sock *tw)
 }
 EXPORT_SYMBOL_GPL(__inet_hash_nolisten);
 
-static void __inet_hash(struct sock *sk)
+int __inet_hash(struct sock *sk, struct inet_timewait_sock *tw)
 {
 	struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
 	struct inet_listen_hashbucket *ilb;
 
-	if (sk->sk_state != TCP_LISTEN) {
-		__inet_hash_nolisten(sk, NULL);
-		return;
-	}
+	if (sk->sk_state != TCP_LISTEN)
+		return __inet_hash_nolisten(sk, tw);
 
 	WARN_ON(!sk_unhashed(sk));
 	ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)];
@@ -440,13 +449,15 @@ static void __inet_hash(struct sock *sk)
 	__sk_nulls_add_node_rcu(sk, &ilb->head);
 	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
 	spin_unlock(&ilb->lock);
+	return 0;
 }
+EXPORT_SYMBOL(__inet_hash);
 
 void inet_hash(struct sock *sk)
 {
 	if (sk->sk_state != TCP_CLOSE) {
 		local_bh_disable();
-		__inet_hash(sk);
+		__inet_hash(sk, NULL);
 		local_bh_enable();
 	}
 }
@@ -477,8 +488,7 @@ EXPORT_SYMBOL_GPL(inet_unhash);
 int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 		struct sock *sk, u32 port_offset,
 		int (*check_established)(struct inet_timewait_death_row *,
-			struct sock *, __u16, struct inet_timewait_sock **),
-		int (*hash)(struct sock *sk, struct inet_timewait_sock *twp))
+			struct sock *, __u16, struct inet_timewait_sock **))
 {
 	struct inet_hashinfo *hinfo = death_row->hashinfo;
 	const unsigned short snum = inet_sk(sk)->inet_num;
@@ -548,14 +558,14 @@ ok:
 		inet_bind_hash(sk, tb, port);
 		if (sk_unhashed(sk)) {
 			inet_sk(sk)->inet_sport = htons(port);
-			twrefcnt += hash(sk, tw);
+			twrefcnt += __inet_hash_nolisten(sk, tw);
 		}
 		if (tw)
 			twrefcnt += inet_twsk_bind_unhash(tw, hinfo);
 		spin_unlock(&head->lock);
 
 		if (tw) {
-			inet_twsk_deschedule(tw, death_row);
+			inet_twsk_deschedule(tw);
 			while (twrefcnt) {
 				twrefcnt--;
 				inet_twsk_put(tw);
@@ -570,7 +580,7 @@ ok:
 	tb  = inet_csk(sk)->icsk_bind_hash;
 	spin_lock_bh(&head->lock);
 	if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) {
-		hash(sk, NULL);
+		__inet_hash_nolisten(sk, NULL);
 		spin_unlock_bh(&head->lock);
 		return 0;
 	} else {
@@ -590,7 +600,7 @@ int inet_hash_connect(struct inet_timewait_death_row *death_row,
 		      struct sock *sk)
 {
 	return __inet_hash_connect(death_row, sk, inet_sk_port_offset(sk),
-			__inet_check_established, __inet_hash_nolisten);
+				   __inet_check_established);
 }
 EXPORT_SYMBOL_GPL(inet_hash_connect);
 
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 6d592f8555fb..00ec8d5d7e7e 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -67,9 +67,9 @@ int inet_twsk_bind_unhash(struct inet_timewait_sock *tw,
 }
 
 /* Must be called with locally disabled BHs. */
-static void __inet_twsk_kill(struct inet_timewait_sock *tw,
-			     struct inet_hashinfo *hashinfo)
+static void inet_twsk_kill(struct inet_timewait_sock *tw)
 {
+	struct inet_hashinfo *hashinfo = tw->tw_dr->hashinfo;
 	struct inet_bind_hashbucket *bhead;
 	int refcnt;
 	/* Unlink from established hashes. */
@@ -89,6 +89,8 @@ static void __inet_twsk_kill(struct inet_timewait_sock *tw,
 
 	BUG_ON(refcnt >= atomic_read(&tw->tw_refcnt));
 	atomic_sub(refcnt, &tw->tw_refcnt);
+	atomic_dec(&tw->tw_dr->tw_count);
+	inet_twsk_put(tw);
 }
 
 void inet_twsk_free(struct inet_timewait_sock *tw)
@@ -98,7 +100,6 @@ void inet_twsk_free(struct inet_timewait_sock *tw)
 #ifdef SOCK_REFCNT_DEBUG
 	pr_debug("%s timewait_sock %p released\n", tw->tw_prot->name, tw);
 #endif
-	release_net(twsk_net(tw));
 	kmem_cache_free(tw->tw_prot->twsk_prot->twsk_slab, tw);
 	module_put(owner);
 }
@@ -169,16 +170,34 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
 }
 EXPORT_SYMBOL_GPL(__inet_twsk_hashdance);
 
-struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, const int state)
+void tw_timer_handler(unsigned long data)
 {
-	struct inet_timewait_sock *tw =
-		kmem_cache_alloc(sk->sk_prot_creator->twsk_prot->twsk_slab,
-				 GFP_ATOMIC);
-	if (tw != NULL) {
+	struct inet_timewait_sock *tw = (struct inet_timewait_sock *)data;
+
+	if (tw->tw_kill)
+		NET_INC_STATS_BH(twsk_net(tw), LINUX_MIB_TIMEWAITKILLED);
+	else
+		NET_INC_STATS_BH(twsk_net(tw), LINUX_MIB_TIMEWAITED);
+	inet_twsk_kill(tw);
+}
+
+struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
+					   struct inet_timewait_death_row *dr,
+					   const int state)
+{
+	struct inet_timewait_sock *tw;
+
+	if (atomic_read(&dr->tw_count) >= dr->sysctl_max_tw_buckets)
+		return NULL;
+
+	tw = kmem_cache_alloc(sk->sk_prot_creator->twsk_prot->twsk_slab,
+			      GFP_ATOMIC);
+	if (tw) {
 		const struct inet_sock *inet = inet_sk(sk);
 
 		kmemcheck_annotate_bitfield(tw, flags);
 
+		tw->tw_dr	    = dr;
 		/* Give us an identity. */
 		tw->tw_daddr	    = inet->inet_daddr;
 		tw->tw_rcv_saddr    = inet->inet_rcv_saddr;
@@ -195,14 +214,16 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, const int stat
 		tw->tw_ipv6only	    = 0;
 		tw->tw_transparent  = inet->transparent;
 		tw->tw_prot	    = sk->sk_prot_creator;
-		twsk_net_set(tw, hold_net(sock_net(sk)));
+		atomic64_set(&tw->tw_cookie, atomic64_read(&sk->sk_cookie));
+		twsk_net_set(tw, sock_net(sk));
+		setup_timer(&tw->tw_timer, tw_timer_handler, (unsigned long)tw);
 		/*
 		 * Because we use RCU lookups, we should not set tw_refcnt
 		 * to a non null value before everything is setup for this
 		 * timewait socket.
 		 */
 		atomic_set(&tw->tw_refcnt, 0);
-		inet_twsk_dead_node_init(tw);
+
 		__module_get(tw->tw_prot->owner);
 	}
 
@@ -210,139 +231,20 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, const int stat
 }
 EXPORT_SYMBOL_GPL(inet_twsk_alloc);
 
-/* Returns non-zero if quota exceeded.  */
-static int inet_twdr_do_twkill_work(struct inet_timewait_death_row *twdr,
-				    const int slot)
-{
-	struct inet_timewait_sock *tw;
-	unsigned int killed;
-	int ret;
-
-	/* NOTE: compare this to previous version where lock
-	 * was released after detaching chain. It was racy,
-	 * because tw buckets are scheduled in not serialized context
-	 * in 2.3 (with netfilter), and with softnet it is common, because
-	 * soft irqs are not sequenced.
-	 */
-	killed = 0;
-	ret = 0;
-rescan:
-	inet_twsk_for_each_inmate(tw, &twdr->cells[slot]) {
-		__inet_twsk_del_dead_node(tw);
-		spin_unlock(&twdr->death_lock);
-		__inet_twsk_kill(tw, twdr->hashinfo);
-#ifdef CONFIG_NET_NS
-		NET_INC_STATS_BH(twsk_net(tw), LINUX_MIB_TIMEWAITED);
-#endif
-		inet_twsk_put(tw);
-		killed++;
-		spin_lock(&twdr->death_lock);
-		if (killed > INET_TWDR_TWKILL_QUOTA) {
-			ret = 1;
-			break;
-		}
-
-		/* While we dropped twdr->death_lock, another cpu may have
-		 * killed off the next TW bucket in the list, therefore
-		 * do a fresh re-read of the hlist head node with the
-		 * lock reacquired.  We still use the hlist traversal
-		 * macro in order to get the prefetches.
-		 */
-		goto rescan;
-	}
-
-	twdr->tw_count -= killed;
-#ifndef CONFIG_NET_NS
-	NET_ADD_STATS_BH(&init_net, LINUX_MIB_TIMEWAITED, killed);
-#endif
-	return ret;
-}
-
-void inet_twdr_hangman(unsigned long data)
-{
-	struct inet_timewait_death_row *twdr;
-	unsigned int need_timer;
-
-	twdr = (struct inet_timewait_death_row *)data;
-	spin_lock(&twdr->death_lock);
-
-	if (twdr->tw_count == 0)
-		goto out;
-
-	need_timer = 0;
-	if (inet_twdr_do_twkill_work(twdr, twdr->slot)) {
-		twdr->thread_slots |= (1 << twdr->slot);
-		schedule_work(&twdr->twkill_work);
-		need_timer = 1;
-	} else {
-		/* We purged the entire slot, anything left?  */
-		if (twdr->tw_count)
-			need_timer = 1;
-		twdr->slot = ((twdr->slot + 1) & (INET_TWDR_TWKILL_SLOTS - 1));
-	}
-	if (need_timer)
-		mod_timer(&twdr->tw_timer, jiffies + twdr->period);
-out:
-	spin_unlock(&twdr->death_lock);
-}
-EXPORT_SYMBOL_GPL(inet_twdr_hangman);
-
-void inet_twdr_twkill_work(struct work_struct *work)
-{
-	struct inet_timewait_death_row *twdr =
-		container_of(work, struct inet_timewait_death_row, twkill_work);
-	int i;
-
-	BUILD_BUG_ON((INET_TWDR_TWKILL_SLOTS - 1) >
-			(sizeof(twdr->thread_slots) * 8));
-
-	while (twdr->thread_slots) {
-		spin_lock_bh(&twdr->death_lock);
-		for (i = 0; i < INET_TWDR_TWKILL_SLOTS; i++) {
-			if (!(twdr->thread_slots & (1 << i)))
-				continue;
-
-			while (inet_twdr_do_twkill_work(twdr, i) != 0) {
-				if (need_resched()) {
-					spin_unlock_bh(&twdr->death_lock);
-					schedule();
-					spin_lock_bh(&twdr->death_lock);
-				}
-			}
-
-			twdr->thread_slots &= ~(1 << i);
-		}
-		spin_unlock_bh(&twdr->death_lock);
-	}
-}
-EXPORT_SYMBOL_GPL(inet_twdr_twkill_work);
-
 /* These are always called from BH context.  See callers in
  * tcp_input.c to verify this.
  */
 
 /* This is for handling early-kills of TIME_WAIT sockets. */
-void inet_twsk_deschedule(struct inet_timewait_sock *tw,
-			  struct inet_timewait_death_row *twdr)
+void inet_twsk_deschedule(struct inet_timewait_sock *tw)
 {
-	spin_lock(&twdr->death_lock);
-	if (inet_twsk_del_dead_node(tw)) {
-		inet_twsk_put(tw);
-		if (--twdr->tw_count == 0)
-			del_timer(&twdr->tw_timer);
-	}
-	spin_unlock(&twdr->death_lock);
-	__inet_twsk_kill(tw, twdr->hashinfo);
+	if (del_timer_sync(&tw->tw_timer))
+		inet_twsk_kill(tw);
 }
 EXPORT_SYMBOL(inet_twsk_deschedule);
 
-void inet_twsk_schedule(struct inet_timewait_sock *tw,
-		       struct inet_timewait_death_row *twdr,
-		       const int timeo, const int timewait_len)
+void inet_twsk_schedule(struct inet_timewait_sock *tw, const int timeo)
 {
-	struct hlist_head *list;
-	int slot;
-
 	/* timeout := RTO * 3.5
 	 *
 	 * 3.5 = 1+2+0.5 to wait for two retransmits.
@@ -367,115 +269,15 @@ void inet_twsk_schedule(struct inet_timewait_sock *tw,
 	 * is greater than TS tick!) and detect old duplicates with help
 	 * of PAWS.
 	 */
-	slot = (timeo + (1 << INET_TWDR_RECYCLE_TICK) - 1) >> INET_TWDR_RECYCLE_TICK;
 
-	spin_lock(&twdr->death_lock);
-
-	/* Unlink it, if it was scheduled */
-	if (inet_twsk_del_dead_node(tw))
-		twdr->tw_count--;
-	else
+	tw->tw_kill = timeo <= 4*HZ;
+	if (!mod_timer_pinned(&tw->tw_timer, jiffies + timeo)) {
 		atomic_inc(&tw->tw_refcnt);
-
-	if (slot >= INET_TWDR_RECYCLE_SLOTS) {
-		/* Schedule to slow timer */
-		if (timeo >= timewait_len) {
-			slot = INET_TWDR_TWKILL_SLOTS - 1;
-		} else {
-			slot = DIV_ROUND_UP(timeo, twdr->period);
-			if (slot >= INET_TWDR_TWKILL_SLOTS)
-				slot = INET_TWDR_TWKILL_SLOTS - 1;
-		}
-		tw->tw_ttd = inet_tw_time_stamp() + timeo;
-		slot = (twdr->slot + slot) & (INET_TWDR_TWKILL_SLOTS - 1);
-		list = &twdr->cells[slot];
-	} else {
-		tw->tw_ttd = inet_tw_time_stamp() + (slot << INET_TWDR_RECYCLE_TICK);
-
-		if (twdr->twcal_hand < 0) {
-			twdr->twcal_hand = 0;
-			twdr->twcal_jiffie = jiffies;
-			twdr->twcal_timer.expires = twdr->twcal_jiffie +
-					      (slot << INET_TWDR_RECYCLE_TICK);
-			add_timer(&twdr->twcal_timer);
-		} else {
-			if (time_after(twdr->twcal_timer.expires,
-				       jiffies + (slot << INET_TWDR_RECYCLE_TICK)))
-				mod_timer(&twdr->twcal_timer,
-					  jiffies + (slot << INET_TWDR_RECYCLE_TICK));
-			slot = (twdr->twcal_hand + slot) & (INET_TWDR_RECYCLE_SLOTS - 1);
-		}
-		list = &twdr->twcal_row[slot];
+		atomic_inc(&tw->tw_dr->tw_count);
 	}
-
-	hlist_add_head(&tw->tw_death_node, list);
-
-	if (twdr->tw_count++ == 0)
-		mod_timer(&twdr->tw_timer, jiffies + twdr->period);
-	spin_unlock(&twdr->death_lock);
 }
 EXPORT_SYMBOL_GPL(inet_twsk_schedule);
 
-void inet_twdr_twcal_tick(unsigned long data)
-{
-	struct inet_timewait_death_row *twdr;
-	int n, slot;
-	unsigned long j;
-	unsigned long now = jiffies;
-	int killed = 0;
-	int adv = 0;
-
-	twdr = (struct inet_timewait_death_row *)data;
-
-	spin_lock(&twdr->death_lock);
-	if (twdr->twcal_hand < 0)
-		goto out;
-
-	slot = twdr->twcal_hand;
-	j = twdr->twcal_jiffie;
-
-	for (n = 0; n < INET_TWDR_RECYCLE_SLOTS; n++) {
-		if (time_before_eq(j, now)) {
-			struct hlist_node *safe;
-			struct inet_timewait_sock *tw;
-
-			inet_twsk_for_each_inmate_safe(tw, safe,
-						       &twdr->twcal_row[slot]) {
-				__inet_twsk_del_dead_node(tw);
-				__inet_twsk_kill(tw, twdr->hashinfo);
-#ifdef CONFIG_NET_NS
-				NET_INC_STATS_BH(twsk_net(tw), LINUX_MIB_TIMEWAITKILLED);
-#endif
-				inet_twsk_put(tw);
-				killed++;
-			}
-		} else {
-			if (!adv) {
-				adv = 1;
-				twdr->twcal_jiffie = j;
-				twdr->twcal_hand = slot;
-			}
-
-			if (!hlist_empty(&twdr->twcal_row[slot])) {
-				mod_timer(&twdr->twcal_timer, j);
-				goto out;
-			}
-		}
-		j += 1 << INET_TWDR_RECYCLE_TICK;
-		slot = (slot + 1) & (INET_TWDR_RECYCLE_SLOTS - 1);
-	}
-	twdr->twcal_hand = -1;
-
-out:
-	if ((twdr->tw_count -= killed) == 0)
-		del_timer(&twdr->tw_timer);
-#ifndef CONFIG_NET_NS
-	NET_ADD_STATS_BH(&init_net, LINUX_MIB_TIMEWAITKILLED, killed);
-#endif
-	spin_unlock(&twdr->death_lock);
-}
-EXPORT_SYMBOL_GPL(inet_twdr_twcal_tick);
-
 void inet_twsk_purge(struct inet_hashinfo *hashinfo,
 		     struct inet_timewait_death_row *twdr, int family)
 {
@@ -487,6 +289,7 @@ void inet_twsk_purge(struct inet_hashinfo *hashinfo,
 	for (slot = 0; slot <= hashinfo->ehash_mask; slot++) {
 		struct inet_ehash_bucket *head = &hashinfo->ehash[slot];
 restart_rcu:
+		cond_resched();
 		rcu_read_lock();
 restart:
 		sk_nulls_for_each_rcu(sk, node, &head->chain) {
@@ -508,7 +311,7 @@ restart:
 
 			rcu_read_unlock();
 			local_bh_disable();
-			inet_twsk_deschedule(tw, twdr);
+			inet_twsk_deschedule(tw);
 			local_bh_enable();
 			inet_twsk_put(tw);
 			goto restart_rcu;
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 3a83ce5efa80..3674484946a5 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -57,7 +57,7 @@ static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
 }
 
 
-static int ip_forward_finish(struct sk_buff *skb)
+static int ip_forward_finish(struct sock *sk, struct sk_buff *skb)
 {
 	struct ip_options *opt	= &(IPCB(skb)->opt);
 
@@ -67,7 +67,8 @@ static int ip_forward_finish(struct sk_buff *skb)
 	if (unlikely(opt->optlen))
 		ip_forward_options(skb);
 
-	return dst_output(skb);
+	skb_sender_cpu_clear(skb);
+	return dst_output_sk(sk, skb);
 }
 
 int ip_forward(struct sk_buff *skb)
@@ -81,6 +82,9 @@ int ip_forward(struct sk_buff *skb)
 	if (skb->pkt_type != PACKET_HOST)
 		goto drop;
 
+	if (unlikely(skb->sk))
+		goto drop;
+
 	if (skb_warn_if_lro(skb))
 		goto drop;
 
@@ -129,13 +133,14 @@ int ip_forward(struct sk_buff *skb)
 	 *	We now generate an ICMP HOST REDIRECT giving the route
 	 *	we calculated.
 	 */
-	if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr && !skb_sec_path(skb))
+	if (IPCB(skb)->flags & IPSKB_DOREDIRECT && !opt->srr &&
+	    !skb_sec_path(skb))
 		ip_rt_send_redirect(skb);
 
 	skb->priority = rt_tos2priority(iph->tos);
 
-	return NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, skb, skb->dev,
-		       rt->dst.dev, ip_forward_finish);
+	return NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, NULL, skb,
+		       skb->dev, rt->dst.dev, ip_forward_finish);
 
 sr_failed:
 	/*
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 2811cc18701a..cc1da6d9cb35 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -80,7 +80,7 @@ struct ipq {
 	struct inet_peer *peer;
 };
 
-static inline u8 ip4_frag_ecn(u8 tos)
+static u8 ip4_frag_ecn(u8 tos)
 {
 	return 1 << (tos & INET_ECN_MASK);
 }
@@ -148,7 +148,7 @@ static void ip4_frag_init(struct inet_frag_queue *q, const void *a)
 		inet_getpeer_v4(net->ipv4.peers, arg->iph->saddr, 1) : NULL;
 }
 
-static __inline__ void ip4_frag_free(struct inet_frag_queue *q)
+static void ip4_frag_free(struct inet_frag_queue *q)
 {
 	struct ipq *qp;
 
@@ -160,7 +160,7 @@ static __inline__ void ip4_frag_free(struct inet_frag_queue *q)
 
 /* Destruction primitives. */
 
-static __inline__ void ipq_put(struct ipq *ipq)
+static void ipq_put(struct ipq *ipq)
 {
 	inet_frag_put(&ipq->q, &ip4_frags);
 }
@@ -236,7 +236,7 @@ out:
 /* Find the correct entry in the "incomplete datagrams" queue for
  * this IP datagram, and create new one, if nothing is found.
  */
-static inline struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user)
+static struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user)
 {
 	struct inet_frag_queue *q;
 	struct ip4_create_arg arg;
@@ -256,7 +256,7 @@ static inline struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user)
 }
 
 /* Is the fragment too far ahead to be part of ipq? */
-static inline int ip_frag_too_far(struct ipq *qp)
+static int ip_frag_too_far(struct ipq *qp)
 {
 	struct inet_peer *peer = qp->peer;
 	unsigned int max = sysctl_ipfrag_max_dist;
@@ -372,7 +372,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 		goto err;
 
 	err = -ENOMEM;
-	if (pskb_pull(skb, ihl) == NULL)
+	if (!pskb_pull(skb, ihl))
 		goto err;
 
 	err = pskb_trim_rcsum(skb, end - offset);
@@ -537,7 +537,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 		qp->q.fragments = head;
 	}
 
-	WARN_ON(head == NULL);
+	WARN_ON(!head);
 	WARN_ON(FRAG_CB(head)->offset != 0);
 
 	/* Allocate a new buffer for the datagram. */
@@ -559,7 +559,8 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 		struct sk_buff *clone;
 		int i, plen = 0;
 
-		if ((clone = alloc_skb(0, GFP_ATOMIC)) == NULL)
+		clone = alloc_skb(0, GFP_ATOMIC);
+		if (!clone)
 			goto out_nomem;
 		clone->next = head->next;
 		head->next = clone;
@@ -618,8 +619,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 	return 0;
 
 out_nomem:
-	LIMIT_NETDEBUG(KERN_ERR pr_fmt("queue_glue: no memory for gluing queue %p\n"),
-		       qp);
+	net_dbg_ratelimited("queue_glue: no memory for gluing queue %p\n", qp);
 	err = -ENOMEM;
 	goto out_fail;
 out_oversize:
@@ -639,7 +639,8 @@ int ip_defrag(struct sk_buff *skb, u32 user)
 	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS);
 
 	/* Lookup (or create) queue header */
-	if ((qp = ip_find(net, ip_hdr(skb), user)) != NULL) {
+	qp = ip_find(net, ip_hdr(skb), user);
+	if (qp) {
 		int ret;
 
 		spin_lock(&qp->q.lock);
@@ -660,27 +661,30 @@ EXPORT_SYMBOL(ip_defrag);
 struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user)
 {
 	struct iphdr iph;
+	int netoff;
 	u32 len;
 
 	if (skb->protocol != htons(ETH_P_IP))
 		return skb;
 
-	if (!skb_copy_bits(skb, 0, &iph, sizeof(iph)))
+	netoff = skb_network_offset(skb);
+
+	if (skb_copy_bits(skb, netoff, &iph, sizeof(iph)) < 0)
 		return skb;
 
 	if (iph.ihl < 5 || iph.version != 4)
 		return skb;
 
 	len = ntohs(iph.tot_len);
-	if (skb->len < len || len < (iph.ihl * 4))
+	if (skb->len < netoff + len || len < (iph.ihl * 4))
 		return skb;
 
 	if (ip_is_fragment(&iph)) {
 		skb = skb_share_check(skb, GFP_ATOMIC);
 		if (skb) {
-			if (!pskb_may_pull(skb, iph.ihl*4))
+			if (!pskb_may_pull(skb, netoff + iph.ihl * 4))
 				return skb;
-			if (pskb_trim_rcsum(skb, len))
+			if (pskb_trim_rcsum(skb, netoff + len))
 				return skb;
 			memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
 			if (ip_defrag(skb, user))
@@ -752,7 +756,7 @@ static int __net_init ip4_frags_ns_ctl_register(struct net *net)
 	table = ip4_frags_ns_ctl_table;
 	if (!net_eq(net, &init_net)) {
 		table = kmemdup(table, sizeof(ip4_frags_ns_ctl_table), GFP_KERNEL);
-		if (table == NULL)
+		if (!table)
 			goto err_alloc;
 
 		table[0].data = &net->ipv4.frags.high_thresh;
@@ -768,7 +772,7 @@ static int __net_init ip4_frags_ns_ctl_register(struct net *net)
 	}
 
 	hdr = register_net_sysctl(net, "net/ipv4", table);
-	if (hdr == NULL)
+	if (!hdr)
 		goto err_reg;
 
 	net->ipv4.frags_hdr = hdr;
@@ -795,16 +799,16 @@ static void __init ip4_frags_ctl_register(void)
 	register_net_sysctl(&init_net, "net/ipv4", ip4_frags_ctl_table);
 }
 #else
-static inline int ip4_frags_ns_ctl_register(struct net *net)
+static int ip4_frags_ns_ctl_register(struct net *net)
 {
 	return 0;
 }
 
-static inline void ip4_frags_ns_ctl_unregister(struct net *net)
+static void ip4_frags_ns_ctl_unregister(struct net *net)
 {
 }
 
-static inline void __init ip4_frags_ctl_register(void)
+static void __init ip4_frags_ctl_register(void)
 {
 }
 #endif
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 12055fdbe716..5fd706473c73 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -182,7 +182,7 @@ static int ipgre_err(struct sk_buff *skb, u32 info,
 	t = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags,
 			     iph->daddr, iph->saddr, tpi->key);
 
-	if (t == NULL)
+	if (!t)
 		return PACKET_REJECT;
 
 	if (t->parms.iph.daddr == 0 ||
@@ -252,10 +252,6 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb,
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	const struct iphdr *tnl_params;
 
-	skb = gre_handle_offloads(skb, !!(tunnel->parms.o_flags&TUNNEL_CSUM));
-	if (IS_ERR(skb))
-		goto out;
-
 	if (dev->header_ops) {
 		/* Need space for new headers */
 		if (skb_cow_head(skb, dev->needed_headroom -
@@ -268,6 +264,7 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb,
 		 * to gre header.
 		 */
 		skb_pull(skb, tunnel->hlen + sizeof(struct iphdr));
+		skb_reset_mac_header(skb);
 	} else {
 		if (skb_cow_head(skb, dev->needed_headroom))
 			goto free_skb;
@@ -275,6 +272,10 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb,
 		tnl_params = &tunnel->parms.iph;
 	}
 
+	skb = gre_handle_offloads(skb, !!(tunnel->parms.o_flags&TUNNEL_CSUM));
+	if (IS_ERR(skb))
+		goto out;
+
 	__gre_xmit(skb, dev, tnl_params, skb->protocol);
 
 	return NETDEV_TX_OK;
@@ -422,7 +423,7 @@ static int ipgre_open(struct net_device *dev)
 			return -EADDRNOTAVAIL;
 		dev = rt->dst.dev;
 		ip_rt_put(rt);
-		if (__in_dev_get_rtnl(dev) == NULL)
+		if (!__in_dev_get_rtnl(dev))
 			return -EADDRNOTAVAIL;
 		t->mlink = dev->ifindex;
 		ip_mc_inc_group(__in_dev_get_rtnl(dev), t->parms.iph.daddr);
@@ -455,6 +456,7 @@ static const struct net_device_ops ipgre_netdev_ops = {
 	.ndo_do_ioctl		= ipgre_tunnel_ioctl,
 	.ndo_change_mtu		= ip_tunnel_change_mtu,
 	.ndo_get_stats64	= ip_tunnel_get_stats64,
+	.ndo_get_iflink		= ip_tunnel_get_iflink,
 };
 
 #define GRE_FEATURES (NETIF_F_SG |		\
@@ -620,10 +622,10 @@ static void ipgre_netlink_parms(struct nlattr *data[], struct nlattr *tb[],
 		parms->o_key = nla_get_be32(data[IFLA_GRE_OKEY]);
 
 	if (data[IFLA_GRE_LOCAL])
-		parms->iph.saddr = nla_get_be32(data[IFLA_GRE_LOCAL]);
+		parms->iph.saddr = nla_get_in_addr(data[IFLA_GRE_LOCAL]);
 
 	if (data[IFLA_GRE_REMOTE])
-		parms->iph.daddr = nla_get_be32(data[IFLA_GRE_REMOTE]);
+		parms->iph.daddr = nla_get_in_addr(data[IFLA_GRE_REMOTE]);
 
 	if (data[IFLA_GRE_TTL])
 		parms->iph.ttl = nla_get_u8(data[IFLA_GRE_TTL]);
@@ -658,12 +660,12 @@ static bool ipgre_netlink_encap_parms(struct nlattr *data[],
 
 	if (data[IFLA_GRE_ENCAP_SPORT]) {
 		ret = true;
-		ipencap->sport = nla_get_u16(data[IFLA_GRE_ENCAP_SPORT]);
+		ipencap->sport = nla_get_be16(data[IFLA_GRE_ENCAP_SPORT]);
 	}
 
 	if (data[IFLA_GRE_ENCAP_DPORT]) {
 		ret = true;
-		ipencap->dport = nla_get_u16(data[IFLA_GRE_ENCAP_DPORT]);
+		ipencap->dport = nla_get_be16(data[IFLA_GRE_ENCAP_DPORT]);
 	}
 
 	return ret;
@@ -672,6 +674,7 @@ static bool ipgre_netlink_encap_parms(struct nlattr *data[],
 static int gre_tap_init(struct net_device *dev)
 {
 	__gre_tunnel_init(dev);
+	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 
 	return ip_tunnel_init(dev);
 }
@@ -684,6 +687,7 @@ static const struct net_device_ops gre_tap_netdev_ops = {
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_change_mtu		= ip_tunnel_change_mtu,
 	.ndo_get_stats64	= ip_tunnel_get_stats64,
+	.ndo_get_iflink		= ip_tunnel_get_iflink,
 };
 
 static void ipgre_tap_setup(struct net_device *dev)
@@ -774,8 +778,8 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_be16(skb, IFLA_GRE_OFLAGS, tnl_flags_to_gre_flags(p->o_flags)) ||
 	    nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) ||
 	    nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) ||
-	    nla_put_be32(skb, IFLA_GRE_LOCAL, p->iph.saddr) ||
-	    nla_put_be32(skb, IFLA_GRE_REMOTE, p->iph.daddr) ||
+	    nla_put_in_addr(skb, IFLA_GRE_LOCAL, p->iph.saddr) ||
+	    nla_put_in_addr(skb, IFLA_GRE_REMOTE, p->iph.daddr) ||
 	    nla_put_u8(skb, IFLA_GRE_TTL, p->iph.ttl) ||
 	    nla_put_u8(skb, IFLA_GRE_TOS, p->iph.tos) ||
 	    nla_put_u8(skb, IFLA_GRE_PMTUDISC,
@@ -784,12 +788,12 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 
 	if (nla_put_u16(skb, IFLA_GRE_ENCAP_TYPE,
 			t->encap.type) ||
-	    nla_put_u16(skb, IFLA_GRE_ENCAP_SPORT,
-			t->encap.sport) ||
-	    nla_put_u16(skb, IFLA_GRE_ENCAP_DPORT,
-			t->encap.dport) ||
+	    nla_put_be16(skb, IFLA_GRE_ENCAP_SPORT,
+			 t->encap.sport) ||
+	    nla_put_be16(skb, IFLA_GRE_ENCAP_DPORT,
+			 t->encap.dport) ||
 	    nla_put_u16(skb, IFLA_GRE_ENCAP_FLAGS,
-			t->encap.dport))
+			t->encap.flags))
 		goto nla_put_failure;
 
 	return 0;
@@ -827,6 +831,7 @@ static struct rtnl_link_ops ipgre_link_ops __read_mostly = {
 	.dellink	= ip_tunnel_dellink,
 	.get_size	= ipgre_get_size,
 	.fill_info	= ipgre_fill_info,
+	.get_link_net	= ip_tunnel_get_link_net,
 };
 
 static struct rtnl_link_ops ipgre_tap_ops __read_mostly = {
@@ -841,6 +846,7 @@ static struct rtnl_link_ops ipgre_tap_ops __read_mostly = {
 	.dellink	= ip_tunnel_dellink,
 	.get_size	= ipgre_get_size,
 	.fill_info	= ipgre_fill_info,
+	.get_link_net	= ip_tunnel_get_link_net,
 };
 
 static int __net_init ipgre_tap_init_net(struct net *net)
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 3d4da2c16b6a..2db4c8773c1b 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -187,7 +187,7 @@ bool ip_call_ra_chain(struct sk_buff *skb)
 	return false;
 }
 
-static int ip_local_deliver_finish(struct sk_buff *skb)
+static int ip_local_deliver_finish(struct sock *sk, struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb->dev);
 
@@ -203,7 +203,7 @@ static int ip_local_deliver_finish(struct sk_buff *skb)
 		raw = raw_local_deliver(skb, protocol);
 
 		ipprot = rcu_dereference(inet_protos[protocol]);
-		if (ipprot != NULL) {
+		if (ipprot) {
 			int ret;
 
 			if (!ipprot->no_policy) {
@@ -253,7 +253,8 @@ int ip_local_deliver(struct sk_buff *skb)
 			return 0;
 	}
 
-	return NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_IN, skb, skb->dev, NULL,
+	return NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_IN, NULL, skb,
+		       skb->dev, NULL,
 		       ip_local_deliver_finish);
 }
 
@@ -309,12 +310,12 @@ drop:
 int sysctl_ip_early_demux __read_mostly = 1;
 EXPORT_SYMBOL(sysctl_ip_early_demux);
 
-static int ip_rcv_finish(struct sk_buff *skb)
+static int ip_rcv_finish(struct sock *sk, struct sk_buff *skb)
 {
 	const struct iphdr *iph = ip_hdr(skb);
 	struct rtable *rt;
 
-	if (sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) {
+	if (sysctl_ip_early_demux && !skb_dst(skb) && !skb->sk) {
 		const struct net_protocol *ipprot;
 		int protocol = iph->protocol;
 
@@ -387,7 +388,8 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
 
 	IP_UPD_PO_STATS_BH(dev_net(dev), IPSTATS_MIB_IN, skb->len);
 
-	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) {
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (!skb) {
 		IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INDISCARDS);
 		goto out;
 	}
@@ -450,7 +452,8 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
 	/* Must drop socket now because of tproxy. */
 	skb_orphan(skb);
 
-	return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, skb, dev, NULL,
+	return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, NULL, skb,
+		       dev, NULL,
 		       ip_rcv_finish);
 
 csum_error:
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index 5b3d91be2db0..bd246792360b 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -264,7 +264,7 @@ int ip_options_compile(struct net *net,
 	unsigned char *iph;
 	int optlen, l;
 
-	if (skb != NULL) {
+	if (skb) {
 		rt = skb_rtable(skb);
 		optptr = (unsigned char *)&(ip_hdr(skb)[1]);
 	} else
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index bc6471d4abcd..c65b93a7b711 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -91,14 +91,19 @@ void ip_send_check(struct iphdr *iph)
 }
 EXPORT_SYMBOL(ip_send_check);
 
-int __ip_local_out(struct sk_buff *skb)
+int __ip_local_out_sk(struct sock *sk, struct sk_buff *skb)
 {
 	struct iphdr *iph = ip_hdr(skb);
 
 	iph->tot_len = htons(skb->len);
 	ip_send_check(iph);
-	return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, skb, NULL,
-		       skb_dst(skb)->dev, dst_output);
+	return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, sk, skb, NULL,
+		       skb_dst(skb)->dev, dst_output_sk);
+}
+
+int __ip_local_out(struct sk_buff *skb)
+{
+	return __ip_local_out_sk(skb->sk, skb);
 }
 
 int ip_local_out_sk(struct sock *sk, struct sk_buff *skb)
@@ -148,7 +153,7 @@ 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, sk);
+	ip_select_ident(sock_net(sk), skb, sk);
 
 	if (opt && opt->opt.optlen) {
 		iph->ihl += opt->opt.optlen>>2;
@@ -163,7 +168,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
 }
 EXPORT_SYMBOL_GPL(ip_build_and_send_pkt);
 
-static inline int ip_finish_output2(struct sk_buff *skb)
+static inline int ip_finish_output2(struct sock *sk, struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 	struct rtable *rt = (struct rtable *)dst;
@@ -182,7 +187,7 @@ static inline int ip_finish_output2(struct sk_buff *skb)
 		struct sk_buff *skb2;
 
 		skb2 = skb_realloc_headroom(skb, LL_RESERVED_SPACE(dev));
-		if (skb2 == NULL) {
+		if (!skb2) {
 			kfree_skb(skb);
 			return -ENOMEM;
 		}
@@ -211,7 +216,7 @@ static inline int ip_finish_output2(struct sk_buff *skb)
 	return -EINVAL;
 }
 
-static int ip_finish_output_gso(struct sk_buff *skb)
+static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb)
 {
 	netdev_features_t features;
 	struct sk_buff *segs;
@@ -220,7 +225,7 @@ static int ip_finish_output_gso(struct sk_buff *skb)
 	/* 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);
+		return ip_finish_output2(sk, skb);
 
 	/* Slowpath -  GSO segment length is exceeding the dst MTU.
 	 *
@@ -243,7 +248,7 @@ static int ip_finish_output_gso(struct sk_buff *skb)
 		int err;
 
 		segs->next = NULL;
-		err = ip_fragment(segs, ip_finish_output2);
+		err = ip_fragment(sk, segs, ip_finish_output2);
 
 		if (err && ret == 0)
 			ret = err;
@@ -253,22 +258,22 @@ static int ip_finish_output_gso(struct sk_buff *skb)
 	return ret;
 }
 
-static int ip_finish_output(struct sk_buff *skb)
+static int ip_finish_output(struct sock *sk, struct sk_buff *skb)
 {
 #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
 	/* Policy lookup after SNAT yielded a new policy */
-	if (skb_dst(skb)->xfrm != NULL) {
+	if (skb_dst(skb)->xfrm) {
 		IPCB(skb)->flags |= IPSKB_REROUTED;
-		return dst_output(skb);
+		return dst_output_sk(sk, skb);
 	}
 #endif
 	if (skb_is_gso(skb))
-		return ip_finish_output_gso(skb);
+		return ip_finish_output_gso(sk, skb);
 
 	if (skb->len > ip_skb_dst_mtu(skb))
-		return ip_fragment(skb, ip_finish_output2);
+		return ip_fragment(sk, skb, ip_finish_output2);
 
-	return ip_finish_output2(skb);
+	return ip_finish_output2(sk, skb);
 }
 
 int ip_mc_output(struct sock *sk, struct sk_buff *skb)
@@ -307,7 +312,7 @@ int ip_mc_output(struct sock *sk, struct sk_buff *skb)
 			struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);
 			if (newskb)
 				NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING,
-					newskb, NULL, newskb->dev,
+					sk, newskb, NULL, newskb->dev,
 					dev_loopback_xmit);
 		}
 
@@ -322,11 +327,11 @@ int ip_mc_output(struct sock *sk, struct sk_buff *skb)
 	if (rt->rt_flags&RTCF_BROADCAST) {
 		struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);
 		if (newskb)
-			NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, newskb,
+			NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, sk, newskb,
 				NULL, newskb->dev, dev_loopback_xmit);
 	}
 
-	return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb, NULL,
+	return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, sk, skb, NULL,
 			    skb->dev, ip_finish_output,
 			    !(IPCB(skb)->flags & IPSKB_REROUTED));
 }
@@ -340,7 +345,8 @@ int ip_output(struct sock *sk, struct sk_buff *skb)
 	skb->dev = dev;
 	skb->protocol = htons(ETH_P_IP);
 
-	return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb, NULL, dev,
+	return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, sk, skb,
+			    NULL, dev,
 			    ip_finish_output,
 			    !(IPCB(skb)->flags & IPSKB_REROUTED));
 }
@@ -376,12 +382,12 @@ int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl)
 	inet_opt = rcu_dereference(inet->inet_opt);
 	fl4 = &fl->u.ip4;
 	rt = skb_rtable(skb);
-	if (rt != NULL)
+	if (rt)
 		goto packet_routed;
 
 	/* Make sure we can route this packet. */
 	rt = (struct rtable *)__sk_dst_check(sk, 0);
-	if (rt == NULL) {
+	if (!rt) {
 		__be32 daddr;
 
 		/* Use correct destination address if we have options. */
@@ -430,7 +436,8 @@ packet_routed:
 		ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0);
 	}
 
-	ip_select_ident_segs(skb, sk, skb_shinfo(skb)->gso_segs ?: 1);
+	ip_select_ident_segs(sock_net(sk), skb, sk,
+			     skb_shinfo(skb)->gso_segs ?: 1);
 
 	/* TODO : should we use skb->sk here instead of sk ? */
 	skb->priority = sk->sk_priority;
@@ -448,7 +455,6 @@ no_route:
 }
 EXPORT_SYMBOL(ip_queue_xmit);
 
-
 static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 {
 	to->pkt_type = from->pkt_type;
@@ -479,7 +485,8 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
  *	single device frame, and queue such a frame for sending.
  */
 
-int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
+int ip_fragment(struct sock *sk, struct sk_buff *skb,
+		int (*output)(struct sock *, struct sk_buff *))
 {
 	struct iphdr *iph;
 	int ptr;
@@ -586,13 +593,13 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 					ip_options_fragment(frag);
 				offset += skb->len - hlen;
 				iph->frag_off = htons(offset>>3);
-				if (frag->next != NULL)
+				if (frag->next)
 					iph->frag_off |= htons(IP_MF);
 				/* Ready, complete checksum */
 				ip_send_check(iph);
 			}
 
-			err = output(skb);
+			err = output(sk, skb);
 
 			if (!err)
 				IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGCREATES);
@@ -636,10 +643,7 @@ slow_path:
 	left = skb->len - hlen;		/* Space per frame */
 	ptr = hlen;		/* Where to start from */
 
-	/* for bridged IP traffic encapsulated inside f.e. a vlan header,
-	 * we need to make room for the encapsulating header
-	 */
-	ll_rs = LL_RESERVED_SPACE_EXTRA(rt->dst.dev, nf_bridge_pad(skb));
+	ll_rs = LL_RESERVED_SPACE(rt->dst.dev);
 
 	/*
 	 *	Fragment the datagram.
@@ -662,12 +666,10 @@ slow_path:
 		if (len < left)	{
 			len &= ~7;
 		}
-		/*
-		 *	Allocate buffer.
-		 */
 
-		if ((skb2 = alloc_skb(len+hlen+ll_rs, GFP_ATOMIC)) == NULL) {
-			NETDEBUG(KERN_INFO "IP: frag: no memory for new fragment!\n");
+		/* Allocate buffer */
+		skb2 = alloc_skb(len + hlen + ll_rs, GFP_ATOMIC);
+		if (!skb2) {
 			err = -ENOMEM;
 			goto fail;
 		}
@@ -734,7 +736,7 @@ slow_path:
 
 		ip_send_check(iph);
 
-		err = output(skb2);
+		err = output(sk, skb2);
 		if (err)
 			goto fail;
 
@@ -754,14 +756,14 @@ EXPORT_SYMBOL(ip_fragment);
 int
 ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb)
 {
-	struct iovec *iov = from;
+	struct msghdr *msg = from;
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		if (memcpy_fromiovecend(to, iov, offset, len) < 0)
+		if (copy_from_iter(to, len, &msg->msg_iter) != len)
 			return -EFAULT;
 	} else {
 		__wsum csum = 0;
-		if (csum_partial_copy_fromiovecend(to, iov, offset, len, &csum) < 0)
+		if (csum_and_copy_from_iter(to, len, &csum, &msg->msg_iter) != len)
 			return -EFAULT;
 		skb->csum = csum_block_add(skb->csum, csum, odd);
 	}
@@ -794,12 +796,13 @@ static inline int ip_ufo_append_data(struct sock *sk,
 	 * device, so create one single skb packet containing complete
 	 * udp datagram
 	 */
-	if ((skb = skb_peek_tail(queue)) == NULL) {
+	skb = skb_peek_tail(queue);
+	if (!skb) {
 		skb = sock_alloc_send_skb(sk,
 			hh_len + fragheaderlen + transhdrlen + 20,
 			(flags & MSG_DONTWAIT), &err);
 
-		if (skb == NULL)
+		if (!skb)
 			return err;
 
 		/* reserve space for Hardware header */
@@ -816,7 +819,6 @@ static inline int ip_ufo_append_data(struct sock *sk,
 
 		skb->csum = 0;
 
-
 		__skb_queue_tail(queue, skb);
 	} else if (skb_is_gso(skb)) {
 		goto append;
@@ -890,7 +892,8 @@ static int __ip_append_data(struct sock *sk,
 	cork->length += length;
 	if (((length > mtu) || (skb && skb_is_gso(skb))) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
-	    (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len) {
+	    (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
+	    (sk->sk_type == SOCK_DGRAM)) {
 		err = ip_ufo_append_data(sk, queue, getfrag, from, length,
 					 hh_len, fragheaderlen, transhdrlen,
 					 maxfraglen, flags);
@@ -964,10 +967,10 @@ alloc_new_skb:
 					skb = sock_wmalloc(sk,
 							   alloclen + hh_len + 15, 1,
 							   sk->sk_allocation);
-				if (unlikely(skb == NULL))
+				if (unlikely(!skb))
 					err = -ENOBUFS;
 			}
-			if (skb == NULL)
+			if (!skb)
 				goto error;
 
 			/*
@@ -1091,10 +1094,10 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 	 */
 	opt = ipc->opt;
 	if (opt) {
-		if (cork->opt == NULL) {
+		if (!cork->opt) {
 			cork->opt = kmalloc(sizeof(struct ip_options) + 40,
 					    sk->sk_allocation);
-			if (unlikely(cork->opt == NULL))
+			if (unlikely(!cork->opt))
 				return -ENOBUFS;
 		}
 		memcpy(cork->opt, &opt->opt, sizeof(struct ip_options) + opt->opt.optlen);
@@ -1201,7 +1204,8 @@ ssize_t	ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
 		return -EMSGSIZE;
 	}
 
-	if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL)
+	skb = skb_peek_tail(&sk->sk_write_queue);
+	if (!skb)
 		return -EINVAL;
 
 	cork->length += size;
@@ -1212,7 +1216,6 @@ ssize_t	ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
 		skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
 	}
 
-
 	while (size > 0) {
 		int i;
 
@@ -1332,7 +1335,8 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	__be16 df = 0;
 	__u8 ttl;
 
-	if ((skb = __skb_dequeue(queue)) == NULL)
+	skb = __skb_dequeue(queue);
+	if (!skb)
 		goto out;
 	tail_skb = &(skb_shinfo(skb)->frag_list);
 
@@ -1383,7 +1387,7 @@ 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, sk);
+	ip_select_ident(net, skb, sk);
 
 	if (opt) {
 		iph->ihl += opt->optlen>>2;
@@ -1506,23 +1510,8 @@ static int ip_reply_glue_bits(void *dptr, char *to, int offset,
 /*
  *	Generic function to send a packet as reply to another packet.
  *	Used to send some TCP resets/acks so far.
- *
- *	Use a fake percpu inet socket to avoid false sharing and contention.
  */
-static DEFINE_PER_CPU(struct inet_sock, unicast_sock) = {
-	.sk = {
-		.__sk_common = {
-			.skc_refcnt = ATOMIC_INIT(1),
-		},
-		.sk_wmem_alloc	= ATOMIC_INIT(1),
-		.sk_allocation	= GFP_ATOMIC,
-		.sk_flags	= (1UL << SOCK_USE_WRITE_QUEUE),
-	},
-	.pmtudisc	= IP_PMTUDISC_WANT,
-	.uc_ttl		= -1,
-};
-
-void ip_send_unicast_reply(struct net *net, struct sk_buff *skb,
+void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 			   const struct ip_options *sopt,
 			   __be32 daddr, __be32 saddr,
 			   const struct ip_reply_arg *arg,
@@ -1532,9 +1521,8 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb,
 	struct ipcm_cookie ipc;
 	struct flowi4 fl4;
 	struct rtable *rt = skb_rtable(skb);
+	struct net *net = sock_net(sk);
 	struct sk_buff *nskb;
-	struct sock *sk;
-	struct inet_sock *inet;
 	int err;
 
 	if (__ip_options_echo(&replyopts.opt.opt, skb, sopt))
@@ -1565,15 +1553,11 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb,
 	if (IS_ERR(rt))
 		return;
 
-	inet = &get_cpu_var(unicast_sock);
+	inet_sk(sk)->tos = arg->tos;
 
-	inet->tos = arg->tos;
-	sk = &inet->sk;
 	sk->sk_priority = skb->priority;
 	sk->sk_protocol = ip_hdr(skb)->protocol;
 	sk->sk_bound_dev_if = arg->bound_dev_if;
-	sock_net_set(sk, net);
-	__skb_queue_head_init(&sk->sk_write_queue);
 	sk->sk_sndbuf = sysctl_wmem_default;
 	err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base,
 			     len, 0, &ipc, &rt, MSG_DONTWAIT);
@@ -1589,13 +1573,10 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb,
 			  arg->csumoffset) = csum_fold(csum_add(nskb->csum,
 								arg->csum));
 		nskb->ip_summed = CHECKSUM_NONE;
-		skb_orphan(nskb);
 		skb_set_queue_mapping(nskb, skb_get_queue_mapping(skb));
 		ip_push_pending_frames(sk, &fl4);
 	}
 out:
-	put_cpu_var(unicast_sock);
-
 	ip_rt_put(rt);
 }
 
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 9daf2177dc00..7cfb0893f263 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -37,6 +37,7 @@
 #include <net/route.h>
 #include <net/xfrm.h>
 #include <net/compat.h>
+#include <net/checksum.h>
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/transp_v6.h>
 #endif
@@ -45,14 +46,6 @@
 #include <linux/errqueue.h>
 #include <asm/uaccess.h>
 
-#define IP_CMSG_PKTINFO		1
-#define IP_CMSG_TTL		2
-#define IP_CMSG_TOS		4
-#define IP_CMSG_RECVOPTS	8
-#define IP_CMSG_RETOPTS		16
-#define IP_CMSG_PASSSEC		32
-#define IP_CMSG_ORIGDSTADDR     64
-
 /*
  *	SOL_IP control messages.
  */
@@ -104,6 +97,20 @@ static void ip_cmsg_recv_retopts(struct msghdr *msg, struct sk_buff *skb)
 	put_cmsg(msg, SOL_IP, IP_RETOPTS, opt->optlen, opt->__data);
 }
 
+static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb,
+				  int offset)
+{
+	__wsum csum = skb->csum;
+
+	if (skb->ip_summed != CHECKSUM_COMPLETE)
+		return;
+
+	if (offset != 0)
+		csum = csum_sub(csum, csum_partial(skb->data, offset, 0));
+
+	put_cmsg(msg, SOL_IP, IP_CHECKSUM, sizeof(__wsum), &csum);
+}
+
 static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb)
 {
 	char *secdata;
@@ -144,47 +151,73 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
 	put_cmsg(msg, SOL_IP, IP_ORIGDSTADDR, sizeof(sin), &sin);
 }
 
-void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb)
+void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb,
+			 int offset)
 {
 	struct inet_sock *inet = inet_sk(skb->sk);
 	unsigned int flags = inet->cmsg_flags;
 
 	/* Ordered by supposed usage frequency */
-	if (flags & 1)
+	if (flags & IP_CMSG_PKTINFO) {
 		ip_cmsg_recv_pktinfo(msg, skb);
-	if ((flags >>= 1) == 0)
-		return;
 
-	if (flags & 1)
+		flags &= ~IP_CMSG_PKTINFO;
+		if (!flags)
+			return;
+	}
+
+	if (flags & IP_CMSG_TTL) {
 		ip_cmsg_recv_ttl(msg, skb);
-	if ((flags >>= 1) == 0)
-		return;
 
-	if (flags & 1)
+		flags &= ~IP_CMSG_TTL;
+		if (!flags)
+			return;
+	}
+
+	if (flags & IP_CMSG_TOS) {
 		ip_cmsg_recv_tos(msg, skb);
-	if ((flags >>= 1) == 0)
-		return;
 
-	if (flags & 1)
+		flags &= ~IP_CMSG_TOS;
+		if (!flags)
+			return;
+	}
+
+	if (flags & IP_CMSG_RECVOPTS) {
 		ip_cmsg_recv_opts(msg, skb);
-	if ((flags >>= 1) == 0)
-		return;
 
-	if (flags & 1)
+		flags &= ~IP_CMSG_RECVOPTS;
+		if (!flags)
+			return;
+	}
+
+	if (flags & IP_CMSG_RETOPTS) {
 		ip_cmsg_recv_retopts(msg, skb);
-	if ((flags >>= 1) == 0)
-		return;
 
-	if (flags & 1)
+		flags &= ~IP_CMSG_RETOPTS;
+		if (!flags)
+			return;
+	}
+
+	if (flags & IP_CMSG_PASSSEC) {
 		ip_cmsg_recv_security(msg, skb);
 
-	if ((flags >>= 1) == 0)
-		return;
-	if (flags & 1)
+		flags &= ~IP_CMSG_PASSSEC;
+		if (!flags)
+			return;
+	}
+
+	if (flags & IP_CMSG_ORIGDSTADDR) {
 		ip_cmsg_recv_dstaddr(msg, skb);
 
+		flags &= ~IP_CMSG_ORIGDSTADDR;
+		if (!flags)
+			return;
+	}
+
+	if (flags & IP_CMSG_CHECKSUM)
+		ip_cmsg_recv_checksum(msg, skb, offset);
 }
-EXPORT_SYMBOL(ip_cmsg_recv);
+EXPORT_SYMBOL(ip_cmsg_recv_offset);
 
 int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc,
 		 bool allow_ipv6)
@@ -192,7 +225,7 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc,
 	int err, val;
 	struct cmsghdr *cmsg;
 
-	for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) {
+	for_each_cmsghdr(cmsg, msg) {
 		if (!CMSG_OK(msg, cmsg))
 			return -EINVAL;
 #if IS_ENABLED(CONFIG_IPV6)
@@ -318,7 +351,7 @@ int ip_ra_control(struct sock *sk, unsigned char on,
 			return 0;
 		}
 	}
-	if (new_ra == NULL) {
+	if (!new_ra) {
 		spin_unlock_bh(&ip_ra_lock);
 		return -ENOBUFS;
 	}
@@ -354,7 +387,7 @@ void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err,
 				   skb_network_header(skb);
 	serr->port = port;
 
-	if (skb_pull(skb, payload - skb->data) != NULL) {
+	if (skb_pull(skb, payload - skb->data)) {
 		skb_reset_transport_header(skb);
 		if (sock_queue_err_skb(sk, skb) == 0)
 			return;
@@ -399,6 +432,37 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 inf
 		kfree_skb(skb);
 }
 
+/* IPv4 supports cmsg on all imcp errors and some timestamps
+ *
+ * Timestamp code paths do not initialize the fields expected by cmsg:
+ * the PKTINFO fields in skb->cb[]. Fill those in here.
+ */
+static bool ipv4_datagram_support_cmsg(const struct sock *sk,
+				       struct sk_buff *skb,
+				       int ee_origin)
+{
+	struct in_pktinfo *info;
+
+	if (ee_origin == SO_EE_ORIGIN_ICMP)
+		return true;
+
+	if (ee_origin == SO_EE_ORIGIN_LOCAL)
+		return false;
+
+	/* Support IP_PKTINFO on tstamp packets if requested, to correlate
+	 * timestamp with egress dev. Not possible for packets without dev
+	 * or without payload (SOF_TIMESTAMPING_OPT_TSONLY).
+	 */
+	if ((!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG)) ||
+	    (!skb->dev))
+		return false;
+
+	info = PKTINFO_SKB_CB(skb);
+	info->ipi_spec_dst.s_addr = ip_hdr(skb)->saddr;
+	info->ipi_ifindex = skb->dev->ifindex;
+	return true;
+}
+
 /*
  *	Handle MSG_ERRQUEUE
  */
@@ -414,9 +478,11 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 	int err;
 	int copied;
 
+	WARN_ON_ONCE(sk->sk_family == AF_INET6);
+
 	err = -EAGAIN;
 	skb = sock_dequeue_err_skb(sk);
-	if (skb == NULL)
+	if (!skb)
 		goto out;
 
 	copied = skb->len;
@@ -424,7 +490,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 		msg->msg_flags |= MSG_TRUNC;
 		copied = len;
 	}
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (err)
 		goto out_free_skb;
 
@@ -432,7 +498,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 
 	serr = SKB_EXT_ERR(skb);
 
-	if (sin) {
+	if (sin && serr->port) {
 		sin->sin_family = AF_INET;
 		sin->sin_addr.s_addr = *(__be32 *)(skb_network_header(skb) +
 						   serr->addr_offset);
@@ -443,15 +509,12 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 
 	memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));
 	sin = &errhdr.offender;
-	sin->sin_family = AF_UNSPEC;
-	if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP) {
-		struct inet_sock *inet = inet_sk(sk);
+	memset(sin, 0, sizeof(*sin));
 
+	if (ipv4_datagram_support_cmsg(sk, skb, serr->ee.ee_origin)) {
 		sin->sin_family = AF_INET;
 		sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
-		sin->sin_port = 0;
-		memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
-		if (inet->cmsg_flags)
+		if (inet_sk(sk)->cmsg_flags)
 			ip_cmsg_recv(msg, skb);
 	}
 
@@ -473,12 +536,34 @@ out:
  *	Socket option code for IP. This is the end of the line after any
  *	TCP,UDP etc options on an IP socket.
  */
+static bool setsockopt_needs_rtnl(int optname)
+{
+	switch (optname) {
+	case IP_ADD_MEMBERSHIP:
+	case IP_ADD_SOURCE_MEMBERSHIP:
+	case IP_BLOCK_SOURCE:
+	case IP_DROP_MEMBERSHIP:
+	case IP_DROP_SOURCE_MEMBERSHIP:
+	case IP_MSFILTER:
+	case IP_UNBLOCK_SOURCE:
+	case MCAST_BLOCK_SOURCE:
+	case MCAST_MSFILTER:
+	case MCAST_JOIN_GROUP:
+	case MCAST_JOIN_SOURCE_GROUP:
+	case MCAST_LEAVE_GROUP:
+	case MCAST_LEAVE_SOURCE_GROUP:
+	case MCAST_UNBLOCK_SOURCE:
+		return true;
+	}
+	return false;
+}
 
 static int do_ip_setsockopt(struct sock *sk, int level,
 			    int optname, char __user *optval, unsigned int optlen)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	int val = 0, err;
+	bool needs_rtnl = setsockopt_needs_rtnl(optname);
 
 	switch (optname) {
 	case IP_PKTINFO:
@@ -502,6 +587,7 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 	case IP_MULTICAST_ALL:
 	case IP_MULTICAST_LOOP:
 	case IP_RECVORIGDSTADDR:
+	case IP_CHECKSUM:
 		if (optlen >= sizeof(int)) {
 			if (get_user(val, (int __user *) optval))
 				return -EFAULT;
@@ -520,6 +606,8 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 		return ip_mroute_setsockopt(sk, optname, optval, optlen);
 
 	err = 0;
+	if (needs_rtnl)
+		rtnl_lock();
 	lock_sock(sk);
 
 	switch (optname) {
@@ -599,6 +687,19 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 		else
 			inet->cmsg_flags &= ~IP_CMSG_ORIGDSTADDR;
 		break;
+	case IP_CHECKSUM:
+		if (val) {
+			if (!(inet->cmsg_flags & IP_CMSG_CHECKSUM)) {
+				inet_inc_convert_csum(sk);
+				inet->cmsg_flags |= IP_CMSG_CHECKSUM;
+			}
+		} else {
+			if (inet->cmsg_flags & IP_CMSG_CHECKSUM) {
+				inet_dec_convert_csum(sk);
+				inet->cmsg_flags &= ~IP_CMSG_CHECKSUM;
+			}
+		}
+		break;
 	case IP_TOS:	/* This sets both TOS and Precedence */
 		if (sk->sk_type == SOCK_STREAM) {
 			val &= ~INET_ECN_MASK;
@@ -1041,15 +1142,19 @@ mc_msf_out:
 		break;
 	}
 	release_sock(sk);
+	if (needs_rtnl)
+		rtnl_unlock();
 	return err;
 
 e_inval:
 	release_sock(sk);
+	if (needs_rtnl)
+		rtnl_unlock();
 	return -EINVAL;
 }
 
 /**
- * ipv4_pktinfo_prepare - transfert some info from rtable to skb
+ * ipv4_pktinfo_prepare - transfer some info from rtable to skb
  * @sk: socket
  * @skb: buffer
  *
@@ -1202,6 +1307,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	case IP_RECVORIGDSTADDR:
 		val = (inet->cmsg_flags & IP_CMSG_ORIGDSTADDR) != 0;
 		break;
+	case IP_CHECKSUM:
+		val = (inet->cmsg_flags & IP_CMSG_CHECKSUM) != 0;
+		break;
 	case IP_TOS:
 		val = inet->tos;
 		break;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 0bb8e141eacc..4c2c3ba4ba65 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -56,7 +56,6 @@
 #include <net/netns/generic.h>
 #include <net/rtnetlink.h>
 #include <net/udp.h>
-#include <net/gue.h>
 
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ipv6.h>
@@ -390,7 +389,6 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
 		hlen = tdev->hard_header_len + tdev->needed_headroom;
 		mtu = tdev->mtu;
 	}
-	dev->iflink = tunnel->parms.link;
 
 	dev->needed_headroom = t_hlen + hlen;
 	mtu -= (dev->hard_header_len + t_hlen);
@@ -491,18 +489,57 @@ EXPORT_SYMBOL_GPL(ip_tunnel_rcv);
 
 static int ip_encap_hlen(struct ip_tunnel_encap *e)
 {
-	switch (e->type) {
-	case TUNNEL_ENCAP_NONE:
+	const struct ip_tunnel_encap_ops *ops;
+	int hlen = -EINVAL;
+
+	if (e->type == TUNNEL_ENCAP_NONE)
 		return 0;
-	case TUNNEL_ENCAP_FOU:
-		return sizeof(struct udphdr);
-	case TUNNEL_ENCAP_GUE:
-		return sizeof(struct udphdr) + sizeof(struct guehdr);
-	default:
+
+	if (e->type >= MAX_IPTUN_ENCAP_OPS)
 		return -EINVAL;
-	}
+
+	rcu_read_lock();
+	ops = rcu_dereference(iptun_encaps[e->type]);
+	if (likely(ops && ops->encap_hlen))
+		hlen = ops->encap_hlen(e);
+	rcu_read_unlock();
+
+	return hlen;
 }
 
+const struct ip_tunnel_encap_ops __rcu *
+		iptun_encaps[MAX_IPTUN_ENCAP_OPS] __read_mostly;
+
+int ip_tunnel_encap_add_ops(const struct ip_tunnel_encap_ops *ops,
+			    unsigned int num)
+{
+	if (num >= MAX_IPTUN_ENCAP_OPS)
+		return -ERANGE;
+
+	return !cmpxchg((const struct ip_tunnel_encap_ops **)
+			&iptun_encaps[num],
+			NULL, ops) ? 0 : -1;
+}
+EXPORT_SYMBOL(ip_tunnel_encap_add_ops);
+
+int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *ops,
+			    unsigned int num)
+{
+	int ret;
+
+	if (num >= MAX_IPTUN_ENCAP_OPS)
+		return -ERANGE;
+
+	ret = (cmpxchg((const struct ip_tunnel_encap_ops **)
+		       &iptun_encaps[num],
+		       ops, NULL) == ops) ? 0 : -1;
+
+	synchronize_net();
+
+	return ret;
+}
+EXPORT_SYMBOL(ip_tunnel_encap_del_ops);
+
 int ip_tunnel_encap_setup(struct ip_tunnel *t,
 			  struct ip_tunnel_encap *ipencap)
 {
@@ -526,63 +563,25 @@ int ip_tunnel_encap_setup(struct ip_tunnel *t,
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_encap_setup);
 
-static int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
-			    size_t hdr_len, u8 *protocol, struct flowi4 *fl4)
-{
-	struct udphdr *uh;
-	__be16 sport;
-	bool csum = !!(e->flags & TUNNEL_ENCAP_FLAG_CSUM);
-	int type = csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
-
-	skb = iptunnel_handle_offloads(skb, csum, type);
-
-	if (IS_ERR(skb))
-		return PTR_ERR(skb);
-
-	/* Get length and hash before making space in skb */
-
-	sport = e->sport ? : udp_flow_src_port(dev_net(skb->dev),
-					       skb, 0, 0, false);
-
-	skb_push(skb, hdr_len);
-
-	skb_reset_transport_header(skb);
-	uh = udp_hdr(skb);
-
-	if (e->type == TUNNEL_ENCAP_GUE) {
-		struct guehdr *guehdr = (struct guehdr *)&uh[1];
-
-		guehdr->version = 0;
-		guehdr->hlen = 0;
-		guehdr->flags = 0;
-		guehdr->next_hdr = *protocol;
-	}
-
-	uh->dest = e->dport;
-	uh->source = sport;
-	uh->len = htons(skb->len);
-	uh->check = 0;
-	udp_set_csum(!(e->flags & TUNNEL_ENCAP_FLAG_CSUM), skb,
-		     fl4->saddr, fl4->daddr, skb->len);
-
-	*protocol = IPPROTO_UDP;
-
-	return 0;
-}
-
 int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t,
 		    u8 *protocol, struct flowi4 *fl4)
 {
-	switch (t->encap.type) {
-	case TUNNEL_ENCAP_NONE:
+	const struct ip_tunnel_encap_ops *ops;
+	int ret = -EINVAL;
+
+	if (t->encap.type == TUNNEL_ENCAP_NONE)
 		return 0;
-	case TUNNEL_ENCAP_FOU:
-	case TUNNEL_ENCAP_GUE:
-		return fou_build_header(skb, &t->encap, t->encap_hlen,
-					protocol, fl4);
-	default:
+
+	if (t->encap.type >= MAX_IPTUN_ENCAP_OPS)
 		return -EINVAL;
-	}
+
+	rcu_read_lock();
+	ops = rcu_dereference(iptun_encaps[t->encap.type]);
+	if (likely(ops && ops->build_header))
+		ret = ops->build_header(skb, &t->encap, protocol, fl4);
+	rcu_read_unlock();
+
+	return ret;
 }
 EXPORT_SYMBOL(ip_tunnel_encap);
 
@@ -655,7 +654,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	if (dst == 0) {
 		/* NBMA tunnel */
 
-		if (skb_dst(skb) == NULL) {
+		if (!skb_dst(skb)) {
 			dev->stats.tx_fifo_errors++;
 			goto tx_error;
 		}
@@ -673,7 +672,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 
 			neigh = dst_neigh_lookup(skb_dst(skb),
 						 &ipv6_hdr(skb)->daddr);
-			if (neigh == NULL)
+			if (!neigh)
 				goto tx_error;
 
 			addr6 = (const struct in6_addr *)&neigh->primary_key;
@@ -783,7 +782,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		return;
 	}
 
-	err = iptunnel_xmit(skb->sk, rt, skb, fl4.saddr, fl4.daddr, protocol,
+	err = iptunnel_xmit(NULL, 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);
 
@@ -844,7 +843,7 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd)
 	case SIOCGETTUNNEL:
 		if (dev == itn->fb_tunnel_dev) {
 			t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type);
-			if (t == NULL)
+			if (!t)
 				t = netdev_priv(dev);
 		}
 		memcpy(p, &t->parms, sizeof(*p));
@@ -877,7 +876,7 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd)
 			break;
 		}
 		if (dev != itn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
-			if (t != NULL) {
+			if (t) {
 				if (t->dev != dev) {
 					err = -EEXIST;
 					break;
@@ -915,7 +914,7 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd)
 		if (dev == itn->fb_tunnel_dev) {
 			err = -ENOENT;
 			t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type);
-			if (t == NULL)
+			if (!t)
 				goto done;
 			err = -EPERM;
 			if (t == netdev_priv(itn->fb_tunnel_dev))
@@ -972,6 +971,22 @@ void ip_tunnel_dellink(struct net_device *dev, struct list_head *head)
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_dellink);
 
+struct net *ip_tunnel_get_link_net(const struct net_device *dev)
+{
+	struct ip_tunnel *tunnel = netdev_priv(dev);
+
+	return tunnel->net;
+}
+EXPORT_SYMBOL(ip_tunnel_get_link_net);
+
+int ip_tunnel_get_iflink(const struct net_device *dev)
+{
+	struct ip_tunnel *tunnel = netdev_priv(dev);
+
+	return tunnel->parms.link;
+}
+EXPORT_SYMBOL(ip_tunnel_get_iflink);
+
 int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id,
 				  struct rtnl_link_ops *ops, char *devname)
 {
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 88c386cf7d85..ce63ab21b6cd 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -74,7 +74,8 @@ int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
 	iph->daddr	=	dst;
 	iph->saddr	=	src;
 	iph->ttl	=	ttl;
-	__ip_select_ident(iph, skb_shinfo(skb)->gso_segs ?: 1);
+	__ip_select_ident(dev_net(rt->dst.dev), iph,
+			  skb_shinfo(skb)->gso_segs ?: 1);
 
 	err = ip_local_out_sk(sk, skb);
 	if (unlikely(net_xmit_eval(err)))
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 3e861011e4a3..0c152087ca15 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -60,12 +60,11 @@ static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi,
 
 	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
 				  iph->saddr, iph->daddr, 0);
-	if (tunnel != NULL) {
+	if (tunnel) {
 		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);
 	}
@@ -91,6 +90,8 @@ static int vti_rcv_cb(struct sk_buff *skb, int err)
 	struct pcpu_sw_netstats *tstats;
 	struct xfrm_state *x;
 	struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4;
+	u32 orig_mark = skb->mark;
+	int ret;
 
 	if (!tunnel)
 		return 1;
@@ -107,7 +108,11 @@ static int vti_rcv_cb(struct sk_buff *skb, int err)
 	x = xfrm_input_state(skb);
 	family = x->inner_mode->afinfo->family;
 
-	if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family))
+	skb->mark = be32_to_cpu(tunnel->parms.i_key);
+	ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family);
+	skb->mark = orig_mark;
+
+	if (!ret)
 		return -EPERM;
 
 	skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(skb->dev)));
@@ -216,8 +221,6 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	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);
@@ -233,6 +236,9 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 		return NETDEV_TX_OK;
 	}
 
+	/* override mark with tunnel output key */
+	fl.flowi_mark = be32_to_cpu(tunnel->parms.o_key);
+
 	return vti_xmit(skb, dev, &fl);
 }
 
@@ -341,6 +347,7 @@ static const struct net_device_ops vti_netdev_ops = {
 	.ndo_do_ioctl	= vti_tunnel_ioctl,
 	.ndo_change_mtu	= ip_tunnel_change_mtu,
 	.ndo_get_stats64 = ip_tunnel_get_stats64,
+	.ndo_get_iflink = ip_tunnel_get_iflink,
 };
 
 static void vti_tunnel_setup(struct net_device *dev)
@@ -361,7 +368,6 @@ static int vti_tunnel_init(struct net_device *dev)
 	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_LLTX;
 	netif_keep_dst(dev);
@@ -456,10 +462,10 @@ static void vti_netlink_parms(struct nlattr *data[],
 		parms->o_key = nla_get_be32(data[IFLA_VTI_OKEY]);
 
 	if (data[IFLA_VTI_LOCAL])
-		parms->iph.saddr = nla_get_be32(data[IFLA_VTI_LOCAL]);
+		parms->iph.saddr = nla_get_in_addr(data[IFLA_VTI_LOCAL]);
 
 	if (data[IFLA_VTI_REMOTE])
-		parms->iph.daddr = nla_get_be32(data[IFLA_VTI_REMOTE]);
+		parms->iph.daddr = nla_get_in_addr(data[IFLA_VTI_REMOTE]);
 
 }
 
@@ -505,8 +511,8 @@ static int vti_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	nla_put_u32(skb, IFLA_VTI_LINK, p->link);
 	nla_put_be32(skb, IFLA_VTI_IKEY, p->i_key);
 	nla_put_be32(skb, IFLA_VTI_OKEY, p->o_key);
-	nla_put_be32(skb, IFLA_VTI_LOCAL, p->iph.saddr);
-	nla_put_be32(skb, IFLA_VTI_REMOTE, p->iph.daddr);
+	nla_put_in_addr(skb, IFLA_VTI_LOCAL, p->iph.saddr);
+	nla_put_in_addr(skb, IFLA_VTI_REMOTE, p->iph.daddr);
 
 	return 0;
 }
@@ -528,8 +534,10 @@ static struct rtnl_link_ops vti_link_ops __read_mostly = {
 	.validate	= vti_tunnel_validate,
 	.newlink	= vti_newlink,
 	.changelink	= vti_changelink,
+	.dellink        = ip_tunnel_dellink,
 	.get_size	= vti_get_size,
 	.fill_info	= vti_fill_info,
+	.get_link_net	= ip_tunnel_get_link_net,
 };
 
 static int __init vti_init(void)
diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c
index c0855d50a3fa..d97f4f2787f5 100644
--- a/net/ipv4/ipcomp.c
+++ b/net/ipv4/ipcomp.c
@@ -63,7 +63,7 @@ static struct xfrm_state *ipcomp_tunnel_create(struct xfrm_state *x)
 	struct xfrm_state *t;
 
 	t = xfrm_state_alloc(net);
-	if (t == NULL)
+	if (!t)
 		goto out;
 
 	t->id.proto = IPPROTO_IPIP;
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 648fa1490ea7..8e7328c6a390 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -115,7 +115,7 @@
  */
 int ic_set_manually __initdata = 0;		/* IPconfig parameters set manually */
 
-static int ic_enable __initdata = 0;		/* IP config enabled? */
+static int ic_enable __initdata;		/* IP config enabled? */
 
 /* Protocol choice */
 int ic_proto_enabled __initdata = 0
@@ -130,7 +130,7 @@ int ic_proto_enabled __initdata = 0
 #endif
 			;
 
-static int ic_host_name_set __initdata = 0;	/* Host name set by us? */
+static int ic_host_name_set __initdata;	/* Host name set by us? */
 
 __be32 ic_myaddr = NONE;		/* My IP address */
 static __be32 ic_netmask = NONE;	/* Netmask for local subnet */
@@ -160,17 +160,17 @@ static u8 ic_domain[64];		/* DNS (not NIS) domain name */
 static char user_dev_name[IFNAMSIZ] __initdata = { 0, };
 
 /* Protocols supported by available interfaces */
-static int ic_proto_have_if __initdata = 0;
+static int ic_proto_have_if __initdata;
 
 /* MTU for boot device */
-static int ic_dev_mtu __initdata = 0;
+static int ic_dev_mtu __initdata;
 
 #ifdef IPCONFIG_DYNAMIC
 static DEFINE_SPINLOCK(ic_recv_lock);
-static volatile int ic_got_reply __initdata = 0;    /* Proto(s) that replied */
+static volatile int ic_got_reply __initdata;    /* Proto(s) that replied */
 #endif
 #ifdef IPCONFIG_DHCP
-static int ic_dhcp_msgtype __initdata = 0;	/* DHCP msg type received */
+static int ic_dhcp_msgtype __initdata;	/* DHCP msg type received */
 #endif
 
 
@@ -186,8 +186,8 @@ struct ic_device {
 	__be32 xid;
 };
 
-static struct ic_device *ic_first_dev __initdata = NULL;/* List of open device */
-static struct net_device *ic_dev __initdata = NULL;	/* Selected device */
+static struct ic_device *ic_first_dev __initdata;	/* List of open device */
+static struct net_device *ic_dev __initdata;		/* Selected device */
 
 static bool __init ic_is_init_dev(struct net_device *dev)
 {
@@ -209,9 +209,9 @@ static int __init ic_open_devs(void)
 	last = &ic_first_dev;
 	rtnl_lock();
 
-	/* bring loopback device up first */
+	/* bring loopback and DSA master network devices up first */
 	for_each_netdev(&init_net, dev) {
-		if (!(dev->flags & IFF_LOOPBACK))
+		if (!(dev->flags & IFF_LOOPBACK) && !netdev_uses_dsa(dev))
 			continue;
 		if (dev_change_flags(dev, dev->flags | IFF_UP) < 0)
 			pr_err("IP-Config: Failed to open %s\n", dev->name);
@@ -306,7 +306,7 @@ static void __init ic_close_devs(void)
 	while ((d = next)) {
 		next = d->next;
 		dev = d->dev;
-		if (dev != ic_dev) {
+		if (dev != ic_dev && !netdev_uses_dsa(dev)) {
 			DBG(("IP-Config: Downing %s\n", dev->name));
 			dev_change_flags(dev, d->flags);
 		}
@@ -498,13 +498,14 @@ ic_rarp_recv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt
 	struct arphdr *rarp;
 	unsigned char *rarp_ptr;
 	__be32 sip, tip;
-	unsigned char *sha, *tha;		/* s for "source", t for "target" */
+	unsigned char *tha;		/* t for "target" */
 	struct ic_device *d;
 
 	if (!net_eq(dev_net(dev), &init_net))
 		goto drop;
 
-	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (!skb)
 		return NET_RX_DROP;
 
 	if (!pskb_may_pull(skb, sizeof(struct arphdr)))
@@ -549,7 +550,6 @@ ic_rarp_recv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt
 		goto drop_unlock;	/* should never happen */
 
 	/* Extract variable-width fields */
-	sha = rarp_ptr;
 	rarp_ptr += dev->addr_len;
 	memcpy(&sip, rarp_ptr, 4);
 	rarp_ptr += 4;
@@ -959,7 +959,8 @@ static int __init ic_bootp_recv(struct sk_buff *skb, struct net_device *dev, str
 	if (skb->pkt_type == PACKET_OTHERHOST)
 		goto drop;
 
-	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (!skb)
 		return NET_RX_DROP;
 
 	if (!pskb_may_pull(skb,
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 37096d64730e..ff96396ebec5 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -144,7 +144,7 @@ static int ipip_err(struct sk_buff *skb, u32 info)
 	err = -ENOENT;
 	t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
 			     iph->daddr, iph->saddr, 0);
-	if (t == NULL)
+	if (!t)
 		goto out;
 
 	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
@@ -272,6 +272,7 @@ static const struct net_device_ops ipip_netdev_ops = {
 	.ndo_do_ioctl	= ipip_tunnel_ioctl,
 	.ndo_change_mtu = ip_tunnel_change_mtu,
 	.ndo_get_stats64 = ip_tunnel_get_stats64,
+	.ndo_get_iflink = ip_tunnel_get_iflink,
 };
 
 #define IPIP_FEATURES (NETIF_F_SG |		\
@@ -286,7 +287,6 @@ static void ipip_tunnel_setup(struct net_device *dev)
 
 	dev->type		= ARPHRD_TUNNEL;
 	dev->flags		= IFF_NOARP;
-	dev->iflink		= 0;
 	dev->addr_len		= 4;
 	dev->features		|= NETIF_F_LLTX;
 	netif_keep_dst(dev);
@@ -325,10 +325,10 @@ static void ipip_netlink_parms(struct nlattr *data[],
 		parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]);
 
 	if (data[IFLA_IPTUN_LOCAL])
-		parms->iph.saddr = nla_get_be32(data[IFLA_IPTUN_LOCAL]);
+		parms->iph.saddr = nla_get_in_addr(data[IFLA_IPTUN_LOCAL]);
 
 	if (data[IFLA_IPTUN_REMOTE])
-		parms->iph.daddr = nla_get_be32(data[IFLA_IPTUN_REMOTE]);
+		parms->iph.daddr = nla_get_in_addr(data[IFLA_IPTUN_REMOTE]);
 
 	if (data[IFLA_IPTUN_TTL]) {
 		parms->iph.ttl = nla_get_u8(data[IFLA_IPTUN_TTL]);
@@ -366,12 +366,12 @@ static bool ipip_netlink_encap_parms(struct nlattr *data[],
 
 	if (data[IFLA_IPTUN_ENCAP_SPORT]) {
 		ret = true;
-		ipencap->sport = nla_get_u16(data[IFLA_IPTUN_ENCAP_SPORT]);
+		ipencap->sport = nla_get_be16(data[IFLA_IPTUN_ENCAP_SPORT]);
 	}
 
 	if (data[IFLA_IPTUN_ENCAP_DPORT]) {
 		ret = true;
-		ipencap->dport = nla_get_u16(data[IFLA_IPTUN_ENCAP_DPORT]);
+		ipencap->dport = nla_get_be16(data[IFLA_IPTUN_ENCAP_DPORT]);
 	}
 
 	return ret;
@@ -450,8 +450,8 @@ static int ipip_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	struct ip_tunnel_parm *parm = &tunnel->parms;
 
 	if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) ||
-	    nla_put_be32(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) ||
-	    nla_put_be32(skb, IFLA_IPTUN_REMOTE, parm->iph.daddr) ||
+	    nla_put_in_addr(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) ||
+	    nla_put_in_addr(skb, IFLA_IPTUN_REMOTE, parm->iph.daddr) ||
 	    nla_put_u8(skb, IFLA_IPTUN_TTL, parm->iph.ttl) ||
 	    nla_put_u8(skb, IFLA_IPTUN_TOS, parm->iph.tos) ||
 	    nla_put_u8(skb, IFLA_IPTUN_PMTUDISC,
@@ -460,12 +460,12 @@ static int ipip_fill_info(struct sk_buff *skb, const struct net_device *dev)
 
 	if (nla_put_u16(skb, IFLA_IPTUN_ENCAP_TYPE,
 			tunnel->encap.type) ||
-	    nla_put_u16(skb, IFLA_IPTUN_ENCAP_SPORT,
-			tunnel->encap.sport) ||
-	    nla_put_u16(skb, IFLA_IPTUN_ENCAP_DPORT,
-			tunnel->encap.dport) ||
+	    nla_put_be16(skb, IFLA_IPTUN_ENCAP_SPORT,
+			 tunnel->encap.sport) ||
+	    nla_put_be16(skb, IFLA_IPTUN_ENCAP_DPORT,
+			 tunnel->encap.dport) ||
 	    nla_put_u16(skb, IFLA_IPTUN_ENCAP_FLAGS,
-			tunnel->encap.dport))
+			tunnel->encap.flags))
 		goto nla_put_failure;
 
 	return 0;
@@ -498,6 +498,7 @@ static struct rtnl_link_ops ipip_link_ops __read_mostly = {
 	.dellink	= ip_tunnel_dellink,
 	.get_size	= ipip_get_size,
 	.fill_info	= ipip_fill_info,
+	.get_link_net	= ip_tunnel_get_link_net,
 };
 
 static struct xfrm_tunnel ipip_handler __read_mostly = {
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index c8034587859d..3a2c0162c3ba 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -73,9 +73,7 @@
 
 struct mr_table {
 	struct list_head	list;
-#ifdef CONFIG_NET_NS
-	struct net		*net;
-#endif
+	possible_net_t		net;
 	u32			id;
 	struct sock __rcu	*mroute_sk;
 	struct timer_list	ipmr_expire_timer;
@@ -191,7 +189,7 @@ static int ipmr_rule_action(struct fib_rule *rule, struct flowi *flp,
 	}
 
 	mrt = ipmr_get_table(rule->fr_net, rule->table);
-	if (mrt == NULL)
+	if (!mrt)
 		return -EAGAIN;
 	res->mrt = mrt;
 	return 0;
@@ -255,7 +253,7 @@ static int __net_init ipmr_rules_init(struct net *net)
 	INIT_LIST_HEAD(&net->ipv4.mr_tables);
 
 	mrt = ipmr_new_table(net, RT_TABLE_DEFAULT);
-	if (mrt == NULL) {
+	if (!mrt) {
 		err = -ENOMEM;
 		goto err1;
 	}
@@ -268,7 +266,7 @@ static int __net_init ipmr_rules_init(struct net *net)
 	return 0;
 
 err2:
-	kfree(mrt);
+	ipmr_free_table(mrt);
 err1:
 	fib_rules_unregister(ops);
 	return err;
@@ -278,11 +276,13 @@ static void __net_exit ipmr_rules_exit(struct net *net)
 {
 	struct mr_table *mrt, *next;
 
+	rtnl_lock();
 	list_for_each_entry_safe(mrt, next, &net->ipv4.mr_tables, list) {
 		list_del(&mrt->list);
 		ipmr_free_table(mrt);
 	}
 	fib_rules_unregister(net->ipv4.mr_rules_ops);
+	rtnl_unlock();
 }
 #else
 #define ipmr_for_each_table(mrt, net) \
@@ -308,7 +308,10 @@ static int __net_init ipmr_rules_init(struct net *net)
 
 static void __net_exit ipmr_rules_exit(struct net *net)
 {
+	rtnl_lock();
 	ipmr_free_table(net->ipv4.mrt);
+	net->ipv4.mrt = NULL;
+	rtnl_unlock();
 }
 #endif
 
@@ -318,11 +321,11 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id)
 	unsigned int i;
 
 	mrt = ipmr_get_table(net, id);
-	if (mrt != NULL)
+	if (mrt)
 		return mrt;
 
 	mrt = kzalloc(sizeof(*mrt), GFP_KERNEL);
-	if (mrt == NULL)
+	if (!mrt)
 		return NULL;
 	write_pnet(&mrt->net, net);
 	mrt->id = id;
@@ -424,7 +427,7 @@ struct net_device *ipmr_new_tunnel(struct net *net, struct vifctl *v)
 			dev->flags |= IFF_MULTICAST;
 
 			in_dev = __in_dev_get_rtnl(dev);
-			if (in_dev == NULL)
+			if (!in_dev)
 				goto failure;
 
 			ipv4_devconf_setall(in_dev);
@@ -475,8 +478,14 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev)
 	return NETDEV_TX_OK;
 }
 
+static int reg_vif_get_iflink(const struct net_device *dev)
+{
+	return 0;
+}
+
 static const struct net_device_ops reg_vif_netdev_ops = {
 	.ndo_start_xmit	= reg_vif_xmit,
+	.ndo_get_iflink = reg_vif_get_iflink,
 };
 
 static void reg_vif_setup(struct net_device *dev)
@@ -502,7 +511,7 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt)
 
 	dev = alloc_netdev(0, name, NET_NAME_UNKNOWN, reg_vif_setup);
 
-	if (dev == NULL)
+	if (!dev)
 		return NULL;
 
 	dev_net_set(dev, net);
@@ -511,7 +520,6 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt)
 		free_netdev(dev);
 		return NULL;
 	}
-	dev->iflink = 0;
 
 	rcu_read_lock();
 	in_dev = __in_dev_get_rcu(dev);
@@ -759,7 +767,7 @@ static int vif_add(struct net *net, struct mr_table *mrt,
 	case 0:
 		if (vifc->vifc_flags == VIFF_USE_IFINDEX) {
 			dev = dev_get_by_index(net, vifc->vifc_lcl_ifindex);
-			if (dev && __in_dev_get_rtnl(dev) == NULL) {
+			if (dev && !__in_dev_get_rtnl(dev)) {
 				dev_put(dev);
 				return -EADDRNOTAVAIL;
 			}
@@ -803,7 +811,7 @@ static int vif_add(struct net *net, struct mr_table *mrt,
 	v->pkt_out = 0;
 	v->link = dev->ifindex;
 	if (v->flags & (VIFF_TUNNEL | VIFF_REGISTER))
-		v->link = dev->iflink;
+		v->link = dev_get_iflink(dev);
 
 	/* And finish update writing critical data */
 	write_lock_bh(&mrt_lock);
@@ -1005,7 +1013,7 @@ static int ipmr_cache_report(struct mr_table *mrt,
 
 	rcu_read_lock();
 	mroute_sk = rcu_dereference(mrt->mroute_sk);
-	if (mroute_sk == NULL) {
+	if (!mroute_sk) {
 		rcu_read_unlock();
 		kfree_skb(skb);
 		return -EINVAL;
@@ -1158,7 +1166,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
 		return -EINVAL;
 
 	c = ipmr_cache_alloc();
-	if (c == NULL)
+	if (!c)
 		return -ENOMEM;
 
 	c->mfc_origin = mfc->mfcc_origin.s_addr;
@@ -1280,7 +1288,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
 		return -EOPNOTSUPP;
 
 	mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT);
-	if (mrt == NULL)
+	if (!mrt)
 		return -ENOENT;
 
 	if (optname != MRT_INIT) {
@@ -1443,7 +1451,7 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int
 		return -EOPNOTSUPP;
 
 	mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT);
-	if (mrt == NULL)
+	if (!mrt)
 		return -ENOENT;
 
 	if (optname != MRT_VERSION &&
@@ -1489,7 +1497,7 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg)
 	struct mr_table *mrt;
 
 	mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT);
-	if (mrt == NULL)
+	if (!mrt)
 		return -ENOENT;
 
 	switch (cmd) {
@@ -1563,7 +1571,7 @@ int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg)
 	struct mr_table *mrt;
 
 	mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT);
-	if (mrt == NULL)
+	if (!mrt)
 		return -ENOENT;
 
 	switch (cmd) {
@@ -1644,7 +1652,8 @@ static struct notifier_block ip_mr_notifier = {
  *	important for multicast video.
  */
 
-static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr)
+static void ip_encap(struct net *net, struct sk_buff *skb,
+		     __be32 saddr, __be32 daddr)
 {
 	struct iphdr *iph;
 	const struct iphdr *old_iph = ip_hdr(skb);
@@ -1663,14 +1672,14 @@ 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, NULL);
+	ip_select_ident(net, skb, NULL);
 	ip_send_check(iph);
 
 	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
 	nf_reset(skb);
 }
 
-static inline int ipmr_forward_finish(struct sk_buff *skb)
+static inline int ipmr_forward_finish(struct sock *sk, struct sk_buff *skb)
 {
 	struct ip_options *opt = &(IPCB(skb)->opt);
 
@@ -1680,7 +1689,7 @@ static inline int ipmr_forward_finish(struct sk_buff *skb)
 	if (unlikely(opt->optlen))
 		ip_forward_options(skb);
 
-	return dst_output(skb);
+	return dst_output_sk(sk, skb);
 }
 
 /*
@@ -1697,7 +1706,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
 	struct flowi4 fl4;
 	int    encap = 0;
 
-	if (vif->dev == NULL)
+	if (!vif->dev)
 		goto out_free;
 
 #ifdef CONFIG_IP_PIMSM
@@ -1760,7 +1769,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
 	 * What do we do with netfilter? -- RR
 	 */
 	if (vif->flags & VIFF_TUNNEL) {
-		ip_encap(skb, vif->local, vif->remote);
+		ip_encap(net, skb, vif->local, vif->remote);
 		/* FIXME: extra output firewall step used to be here. --RR */
 		vif->dev->stats.tx_packets++;
 		vif->dev->stats.tx_bytes += skb->len;
@@ -1779,7 +1788,8 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
 	 * not mrouter) cannot join to more than one interface - it will
 	 * result in receiving multiple packets.
 	 */
-	NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, skb, skb->dev, dev,
+	NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, NULL, skb,
+		skb->dev, dev,
 		ipmr_forward_finish);
 	return;
 
@@ -1988,7 +1998,7 @@ int ip_mr_input(struct sk_buff *skb)
 
 	/* already under rcu_read_lock() */
 	cache = ipmr_cache_find(mrt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr);
-	if (cache == NULL) {
+	if (!cache) {
 		int vif = ipmr_find_vif(mrt, skb->dev);
 
 		if (vif >= 0)
@@ -1999,13 +2009,13 @@ int ip_mr_input(struct sk_buff *skb)
 	/*
 	 *	No usable cache entry
 	 */
-	if (cache == NULL) {
+	if (!cache) {
 		int vif;
 
 		if (local) {
 			struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
 			ip_local_deliver(skb);
-			if (skb2 == NULL)
+			if (!skb2)
 				return -ENOBUFS;
 			skb = skb2;
 		}
@@ -2064,7 +2074,7 @@ static int __pim_rcv(struct mr_table *mrt, struct sk_buff *skb,
 		reg_dev = mrt->vif_table[mrt->mroute_reg_vif_num].dev;
 	read_unlock(&mrt_lock);
 
-	if (reg_dev == NULL)
+	if (!reg_dev)
 		return 1;
 
 	skb->mac_header = skb->network_header;
@@ -2194,18 +2204,18 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb,
 	int err;
 
 	mrt = ipmr_get_table(net, RT_TABLE_DEFAULT);
-	if (mrt == NULL)
+	if (!mrt)
 		return -ENOENT;
 
 	rcu_read_lock();
 	cache = ipmr_cache_find(mrt, saddr, daddr);
-	if (cache == NULL && skb->dev) {
+	if (!cache && skb->dev) {
 		int vif = ipmr_find_vif(mrt, skb->dev);
 
 		if (vif >= 0)
 			cache = ipmr_cache_find_any(mrt, daddr, vif);
 	}
-	if (cache == NULL) {
+	if (!cache) {
 		struct sk_buff *skb2;
 		struct iphdr *iph;
 		struct net_device *dev;
@@ -2263,7 +2273,7 @@ static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 	int err;
 
 	nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags);
-	if (nlh == NULL)
+	if (!nlh)
 		return -EMSGSIZE;
 
 	rtm = nlmsg_data(nlh);
@@ -2282,15 +2292,16 @@ static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 		rtm->rtm_protocol = RTPROT_MROUTED;
 	rtm->rtm_flags    = 0;
 
-	if (nla_put_be32(skb, RTA_SRC, c->mfc_origin) ||
-	    nla_put_be32(skb, RTA_DST, c->mfc_mcastgrp))
+	if (nla_put_in_addr(skb, RTA_SRC, c->mfc_origin) ||
+	    nla_put_in_addr(skb, RTA_DST, c->mfc_mcastgrp))
 		goto nla_put_failure;
 	err = __ipmr_fill_mroute(mrt, skb, c, rtm);
 	/* do not break the dump if cache is unresolved */
 	if (err < 0 && err != -ENOENT)
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
@@ -2327,7 +2338,7 @@ static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc,
 
 	skb = nlmsg_new(mroute_msgsize(mfc->mfc_parent >= MAXVIFS, mrt->maxvif),
 			GFP_ATOMIC);
-	if (skb == NULL)
+	if (!skb)
 		goto errout;
 
 	err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0);
@@ -2442,7 +2453,7 @@ static void *ipmr_vif_seq_start(struct seq_file *seq, loff_t *pos)
 	struct mr_table *mrt;
 
 	mrt = ipmr_get_table(net, RT_TABLE_DEFAULT);
-	if (mrt == NULL)
+	if (!mrt)
 		return ERR_PTR(-ENOENT);
 
 	iter->mrt = mrt;
@@ -2561,7 +2572,7 @@ static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos)
 	struct mr_table *mrt;
 
 	mrt = ipmr_get_table(net, RT_TABLE_DEFAULT);
-	if (mrt == NULL)
+	if (!mrt)
 		return ERR_PTR(-ENOENT);
 
 	it->mrt = mrt;
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index 7ebd6e37875c..65de0684e22a 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -94,7 +94,7 @@ static void nf_ip_saveroute(const struct sk_buff *skb,
 {
 	struct ip_rt_info *rt_info = nf_queue_entry_reroute(entry);
 
-	if (entry->hook == NF_INET_LOCAL_OUT) {
+	if (entry->state.hook == NF_INET_LOCAL_OUT) {
 		const struct iphdr *iph = ip_hdr(skb);
 
 		rt_info->tos = iph->tos;
@@ -109,7 +109,7 @@ static int nf_ip_reroute(struct sk_buff *skb,
 {
 	const struct ip_rt_info *rt_info = nf_queue_entry_reroute(entry);
 
-	if (entry->hook == NF_INET_LOCAL_OUT) {
+	if (entry->state.hook == NF_INET_LOCAL_OUT) {
 		const struct iphdr *iph = ip_hdr(skb);
 
 		if (!(iph->tos == rt_info->tos &&
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 4c019d5c3f57..fb20f363151f 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -36,24 +36,16 @@ config NF_CONNTRACK_PROC_COMPAT
 
 	  If unsure, say Y.
 
-config NF_LOG_ARP
-	tristate "ARP packet logging"
-	default m if NETFILTER_ADVANCED=n
-	select NF_LOG_COMMON
-
-config NF_LOG_IPV4
-	tristate "IPv4 packet logging"
-	default m if NETFILTER_ADVANCED=n
-	select NF_LOG_COMMON
+if NF_TABLES
 
 config NF_TABLES_IPV4
-	depends on NF_TABLES
 	tristate "IPv4 nf_tables support"
 	help
 	  This option enables the IPv4 support for nf_tables.
 
+if NF_TABLES_IPV4
+
 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
@@ -61,22 +53,34 @@ config NFT_CHAIN_ROUTE_IPV4
 	  fields such as the source, destination, type of service and
 	  the packet mark.
 
-config NF_REJECT_IPV4
-	tristate "IPv4 packet rejection"
-	default m if NETFILTER_ADVANCED=n
-
 config NFT_REJECT_IPV4
-	depends on NF_TABLES_IPV4
 	select NF_REJECT_IPV4
 	default NFT_REJECT
 	tristate
 
+endif # NF_TABLES_IPV4
+
 config NF_TABLES_ARP
-	depends on NF_TABLES
 	tristate "ARP nf_tables support"
 	help
 	  This option enables the ARP support for nf_tables.
 
+endif # NF_TABLES
+
+config NF_LOG_ARP
+	tristate "ARP packet logging"
+	default m if NETFILTER_ADVANCED=n
+	select NF_LOG_COMMON
+
+config NF_LOG_IPV4
+	tristate "IPv4 packet logging"
+	default m if NETFILTER_ADVANCED=n
+	select NF_LOG_COMMON
+
+config NF_REJECT_IPV4
+	tristate "IPv4 packet rejection"
+	default m if NETFILTER_ADVANCED=n
+
 config NF_NAT_IPV4
 	tristate "IPv4 NAT"
 	depends on NF_CONNTRACK_IPV4
@@ -113,6 +117,15 @@ config NFT_MASQ_IPV4
 	  This is the expression that provides IPv4 masquerading support for
 	  nf_tables.
 
+config NFT_REDIR_IPV4
+	tristate "IPv4 redirect support for nf_tables"
+	depends on NF_TABLES_IPV4
+	depends on NFT_REDIR
+	select NF_NAT_REDIRECT
+	help
+	  This is the expression that provides IPv4 redirect support for
+	  nf_tables.
+
 config NF_NAT_SNMP_BASIC
 	tristate "Basic SNMP-ALG support"
 	depends on NF_CONNTRACK_SNMP
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index f4cef5af0969..7fe6c703528f 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -40,6 +40,7 @@ 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_NFT_MASQ_IPV4) += nft_masq_ipv4.o
+obj-$(CONFIG_NFT_REDIR_IPV4) += nft_redir_ipv4.o
 obj-$(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 f95b6f93814b..a61200754f4b 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -248,8 +248,7 @@ struct arpt_entry *arpt_next_entry(const struct arpt_entry *entry)
 
 unsigned int arpt_do_table(struct sk_buff *skb,
 			   unsigned int hook,
-			   const struct net_device *in,
-			   const struct net_device *out,
+			   const struct nf_hook_state *state,
 			   struct xt_table *table)
 {
 	static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long))));
@@ -265,8 +264,8 @@ unsigned int arpt_do_table(struct sk_buff *skb,
 	if (!pskb_may_pull(skb, arp_hdr_len(skb->dev)))
 		return NF_DROP;
 
-	indev = in ? in->name : nulldevname;
-	outdev = out ? out->name : nulldevname;
+	indev = state->in ? state->in->name : nulldevname;
+	outdev = state->out ? state->out->name : nulldevname;
 
 	local_bh_disable();
 	addend = xt_write_recseq_begin();
@@ -281,8 +280,8 @@ unsigned int arpt_do_table(struct sk_buff *skb,
 	e = get_entry(table_base, private->hook_entry[hook]);
 	back = get_entry(table_base, private->underflow[hook]);
 
-	acpar.in      = in;
-	acpar.out     = out;
+	acpar.in      = state->in;
+	acpar.out     = state->out;
 	acpar.hooknum = hook;
 	acpar.family  = NFPROTO_ARP;
 	acpar.hotdrop = false;
@@ -1076,6 +1075,9 @@ static int do_replace(struct net *net, const void __user *user,
 	/* overflow check */
 	if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
 		return -ENOMEM;
+	if (tmp.num_counters == 0)
+		return -EINVAL;
+
 	tmp.name[sizeof(tmp.name)-1] = 0;
 
 	newinfo = xt_alloc_table_info(tmp.size);
@@ -1500,6 +1502,9 @@ static int compat_do_replace(struct net *net, void __user *user,
 		return -ENOMEM;
 	if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
 		return -ENOMEM;
+	if (tmp.num_counters == 0)
+		return -EINVAL;
+
 	tmp.name[sizeof(tmp.name)-1] = 0;
 
 	newinfo = xt_alloc_table_info(tmp.size);
diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c
index 802ddecb30b8..93876d03120c 100644
--- a/net/ipv4/netfilter/arptable_filter.c
+++ b/net/ipv4/netfilter/arptable_filter.c
@@ -28,12 +28,11 @@ static const struct xt_table packet_filter = {
 /* The work comes in here from netfilter.c */
 static unsigned int
 arptable_filter_hook(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 *))
+		     const struct nf_hook_state *state)
 {
-	const struct net *net = dev_net((in != NULL) ? in : out);
+	const struct net *net = dev_net(state->in ? state->in : state->out);
 
-	return arpt_do_table(skb, ops->hooknum, in, out,
+	return arpt_do_table(skb, ops->hooknum, state,
 			     net->ipv4.arptable_filter);
 }
 
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 99e810f84671..2d0e265fef6e 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -272,9 +272,9 @@ static void trace_packet(const struct sk_buff *skb,
 		    &chainname, &comment, &rulenum) != 0)
 			break;
 
-	nf_log_packet(net, AF_INET, hook, skb, in, out, &trace_loginfo,
-		      "TRACE: %s:%s:%s:%u ",
-		      tablename, chainname, comment, rulenum);
+	nf_log_trace(net, AF_INET, hook, skb, in, out, &trace_loginfo,
+		     "TRACE: %s:%s:%s:%u ",
+		     tablename, chainname, comment, rulenum);
 }
 #endif
 
@@ -288,8 +288,7 @@ struct ipt_entry *ipt_next_entry(const struct ipt_entry *entry)
 unsigned int
 ipt_do_table(struct sk_buff *skb,
 	     unsigned int hook,
-	     const struct net_device *in,
-	     const struct net_device *out,
+	     const struct nf_hook_state *state,
 	     struct xt_table *table)
 {
 	static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long))));
@@ -306,8 +305,8 @@ ipt_do_table(struct sk_buff *skb,
 
 	/* Initialization */
 	ip = ip_hdr(skb);
-	indev = in ? in->name : nulldevname;
-	outdev = out ? out->name : nulldevname;
+	indev = state->in ? state->in->name : nulldevname;
+	outdev = state->out ? state->out->name : nulldevname;
 	/* We handle fragments by dealing with the first fragment as
 	 * if it was a normal packet.  All other fragments are treated
 	 * normally, except that they will NEVER match rules that ask
@@ -317,8 +316,8 @@ ipt_do_table(struct sk_buff *skb,
 	acpar.fragoff = ntohs(ip->frag_off) & IP_OFFSET;
 	acpar.thoff   = ip_hdrlen(skb);
 	acpar.hotdrop = false;
-	acpar.in      = in;
-	acpar.out     = out;
+	acpar.in      = state->in;
+	acpar.out     = state->out;
 	acpar.family  = NFPROTO_IPV4;
 	acpar.hooknum = hook;
 
@@ -370,7 +369,7 @@ ipt_do_table(struct sk_buff *skb,
 #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
 		/* The packet is traced: log it */
 		if (unlikely(skb->nf_trace))
-			trace_packet(skb, hook, in, out,
+			trace_packet(skb, hook, state->in, state->out,
 				     table->name, private, e);
 #endif
 		/* Standard target? */
@@ -1263,6 +1262,9 @@ do_replace(struct net *net, const void __user *user, unsigned int len)
 	/* overflow check */
 	if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
 		return -ENOMEM;
+	if (tmp.num_counters == 0)
+		return -EINVAL;
+
 	tmp.name[sizeof(tmp.name)-1] = 0;
 
 	newinfo = xt_alloc_table_info(tmp.size);
@@ -1810,6 +1812,9 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len)
 		return -ENOMEM;
 	if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
 		return -ENOMEM;
+	if (tmp.num_counters == 0)
+		return -EINVAL;
+
 	tmp.name[sizeof(tmp.name)-1] = 0;
 
 	newinfo = xt_alloc_table_info(tmp.size);
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index e90f83a3415b..771ab3d01ad3 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -418,6 +418,13 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par)
 	if (ret < 0)
 		pr_info("cannot load conntrack support for proto=%u\n",
 			par->family);
+
+	if (!par->net->xt.clusterip_deprecated_warning) {
+		pr_info("ipt_CLUSTERIP is deprecated and it will removed soon, "
+			"use xt_cluster instead\n");
+		par->net->xt.clusterip_deprecated_warning = true;
+	}
+
 	return ret;
 }
 
@@ -497,14 +504,12 @@ static void arp_print(struct arp_payload *payload)
 static unsigned int
 arp_mangle(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 *))
+	   const struct nf_hook_state *state)
 {
 	struct arphdr *arp = arp_hdr(skb);
 	struct arp_payload *payload;
 	struct clusterip_config *c;
-	struct net *net = dev_net(in ? in : out);
+	struct net *net = dev_net(state->in ? state->in : state->out);
 
 	/* we don't care about non-ethernet and non-ipv4 ARP */
 	if (arp->ar_hrd != htons(ARPHRD_ETHER) ||
@@ -529,10 +534,10 @@ arp_mangle(const struct nf_hook_ops *ops,
 	 * addresses on different interfacs.  However, in the CLUSTERIP case
 	 * this wouldn't work, since we didn't subscribe the mcast group on
 	 * other interfaces */
-	if (c->dev != out) {
+	if (c->dev != state->out) {
 		pr_debug("not mangling arp reply on different "
 			 "interface: cip'%s'-skb'%s'\n",
-			 c->dev->name, out->name);
+			 c->dev->name, state->out->name);
 		clusterip_config_put(c);
 		return NF_ACCEPT;
 	}
diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c
index 8f48f5517e33..87907d4bd259 100644
--- a/net/ipv4/netfilter/ipt_REJECT.c
+++ b/net/ipv4/netfilter/ipt_REJECT.c
@@ -34,31 +34,32 @@ static unsigned int
 reject_tg(struct sk_buff *skb, const struct xt_action_param *par)
 {
 	const struct ipt_reject_info *reject = par->targinfo;
+	int hook = par->hooknum;
 
 	switch (reject->with) {
 	case IPT_ICMP_NET_UNREACHABLE:
-		nf_send_unreach(skb, ICMP_NET_UNREACH);
+		nf_send_unreach(skb, ICMP_NET_UNREACH, hook);
 		break;
 	case IPT_ICMP_HOST_UNREACHABLE:
-		nf_send_unreach(skb, ICMP_HOST_UNREACH);
+		nf_send_unreach(skb, ICMP_HOST_UNREACH, hook);
 		break;
 	case IPT_ICMP_PROT_UNREACHABLE:
-		nf_send_unreach(skb, ICMP_PROT_UNREACH);
+		nf_send_unreach(skb, ICMP_PROT_UNREACH, hook);
 		break;
 	case IPT_ICMP_PORT_UNREACHABLE:
-		nf_send_unreach(skb, ICMP_PORT_UNREACH);
+		nf_send_unreach(skb, ICMP_PORT_UNREACH, hook);
 		break;
 	case IPT_ICMP_NET_PROHIBITED:
-		nf_send_unreach(skb, ICMP_NET_ANO);
+		nf_send_unreach(skb, ICMP_NET_ANO, hook);
 		break;
 	case IPT_ICMP_HOST_PROHIBITED:
-		nf_send_unreach(skb, ICMP_HOST_ANO);
+		nf_send_unreach(skb, ICMP_HOST_ANO, hook);
 		break;
 	case IPT_ICMP_ADMIN_PROHIBITED:
-		nf_send_unreach(skb, ICMP_PKT_FILTERED);
+		nf_send_unreach(skb, ICMP_PKT_FILTERED, hook);
 		break;
 	case IPT_TCP_RESET:
-		nf_send_reset(skb, par->hooknum);
+		nf_send_reset(skb, hook);
 	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 a313c3fbeb46..e9e67793055f 100644
--- a/net/ipv4/netfilter/ipt_SYNPROXY.c
+++ b/net/ipv4/netfilter/ipt_SYNPROXY.c
@@ -300,11 +300,9 @@ synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par)
 
 static unsigned int ipv4_synproxy_hook(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 *))
+				       const struct nf_hook_state *nhs)
 {
-	struct synproxy_net *snet = synproxy_pernet(dev_net(in ? : out));
+	struct synproxy_net *snet = synproxy_pernet(dev_net(nhs->in ? : nhs->out));
 	enum ip_conntrack_info ctinfo;
 	struct nf_conn *ct;
 	struct nf_conn_synproxy *synproxy;
diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c
index e08a74a243a8..a0f3beca52d2 100644
--- a/net/ipv4/netfilter/iptable_filter.c
+++ b/net/ipv4/netfilter/iptable_filter.c
@@ -34,8 +34,7 @@ static const struct xt_table packet_filter = {
 
 static unsigned int
 iptable_filter_hook(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 *))
+		    const struct nf_hook_state *state)
 {
 	const struct net *net;
 
@@ -45,9 +44,8 @@ iptable_filter_hook(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		/* root is playing with raw sockets. */
 		return NF_ACCEPT;
 
-	net = dev_net((in != NULL) ? in : out);
-	return ipt_do_table(skb, ops->hooknum, in, out,
-			    net->ipv4.iptable_filter);
+	net = dev_net(state->in ? state->in : state->out);
+	return ipt_do_table(skb, ops->hooknum, state, net->ipv4.iptable_filter);
 }
 
 static struct nf_hook_ops *filter_ops __read_mostly;
diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c
index 6a5079c34bb3..62cbb8c5f4a8 100644
--- a/net/ipv4/netfilter/iptable_mangle.c
+++ b/net/ipv4/netfilter/iptable_mangle.c
@@ -37,8 +37,9 @@ static const struct xt_table packet_mangler = {
 };
 
 static unsigned int
-ipt_mangle_out(struct sk_buff *skb, const struct net_device *out)
+ipt_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state)
 {
+	struct net_device *out = state->out;
 	unsigned int ret;
 	const struct iphdr *iph;
 	u_int8_t tos;
@@ -58,7 +59,7 @@ ipt_mangle_out(struct sk_buff *skb, const struct net_device *out)
 	daddr = iph->daddr;
 	tos = iph->tos;
 
-	ret = ipt_do_table(skb, NF_INET_LOCAL_OUT, NULL, out,
+	ret = ipt_do_table(skb, NF_INET_LOCAL_OUT, state,
 			   dev_net(out)->ipv4.iptable_mangle);
 	/* Reroute for ANY change. */
 	if (ret != NF_DROP && ret != NF_STOLEN) {
@@ -81,18 +82,16 @@ ipt_mangle_out(struct sk_buff *skb, const struct net_device *out)
 static unsigned int
 iptable_mangle_hook(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 *))
+		     const struct nf_hook_state *state)
 {
 	if (ops->hooknum == NF_INET_LOCAL_OUT)
-		return ipt_mangle_out(skb, out);
+		return ipt_mangle_out(skb, state);
 	if (ops->hooknum == NF_INET_POST_ROUTING)
-		return ipt_do_table(skb, ops->hooknum, in, out,
-				    dev_net(out)->ipv4.iptable_mangle);
+		return ipt_do_table(skb, ops->hooknum, state,
+				    dev_net(state->out)->ipv4.iptable_mangle);
 	/* PREROUTING/INPUT/FORWARD: */
-	return ipt_do_table(skb, ops->hooknum, in, out,
-			    dev_net(in)->ipv4.iptable_mangle);
+	return ipt_do_table(skb, ops->hooknum, state,
+			    dev_net(state->in)->ipv4.iptable_mangle);
 }
 
 static struct nf_hook_ops *mangle_ops __read_mostly;
diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c
index 6b67d7e9a75d..0d4d9cdf98a4 100644
--- a/net/ipv4/netfilter/iptable_nat.c
+++ b/net/ipv4/netfilter/iptable_nat.c
@@ -30,49 +30,40 @@ static const struct xt_table nf_nat_ipv4_table = {
 
 static unsigned int iptable_nat_do_chain(const struct nf_hook_ops *ops,
 					 struct sk_buff *skb,
-					 const struct net_device *in,
-					 const struct net_device *out,
+					 const struct nf_hook_state *state,
 					 struct nf_conn *ct)
 {
 	struct net *net = nf_ct_net(ct);
 
-	return ipt_do_table(skb, ops->hooknum, in, out, net->ipv4.nat_table);
+	return ipt_do_table(skb, ops->hooknum, state, net->ipv4.nat_table);
 }
 
 static unsigned int iptable_nat_ipv4_fn(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 *))
+					const struct nf_hook_state *state)
 {
-	return nf_nat_ipv4_fn(ops, skb, in, out, iptable_nat_do_chain);
+	return nf_nat_ipv4_fn(ops, skb, state, iptable_nat_do_chain);
 }
 
 static unsigned int iptable_nat_ipv4_in(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 *))
+					const struct nf_hook_state *state)
 {
-	return nf_nat_ipv4_in(ops, skb, in, out, iptable_nat_do_chain);
+	return nf_nat_ipv4_in(ops, skb, state, iptable_nat_do_chain);
 }
 
 static unsigned int iptable_nat_ipv4_out(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 *))
+					 const struct nf_hook_state *state)
 {
-	return nf_nat_ipv4_out(ops, skb, in, out, iptable_nat_do_chain);
+	return nf_nat_ipv4_out(ops, skb, state, iptable_nat_do_chain);
 }
 
 static unsigned int iptable_nat_ipv4_local_fn(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 *))
+					      const struct nf_hook_state *state)
 {
-	return nf_nat_ipv4_local_fn(ops, skb, in, out, iptable_nat_do_chain);
+	return nf_nat_ipv4_local_fn(ops, skb, state, iptable_nat_do_chain);
 }
 
 static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = {
diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c
index b2f7e8f98316..0356e6da4bb7 100644
--- a/net/ipv4/netfilter/iptable_raw.c
+++ b/net/ipv4/netfilter/iptable_raw.c
@@ -21,8 +21,7 @@ static const struct xt_table packet_raw = {
 /* The work comes in here from netfilter.c. */
 static unsigned int
 iptable_raw_hook(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 *))
+		 const struct nf_hook_state *state)
 {
 	const struct net *net;
 
@@ -32,8 +31,8 @@ iptable_raw_hook(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		/* root is playing with raw sockets. */
 		return NF_ACCEPT;
 
-	net = dev_net((in != NULL) ? in : out);
-	return ipt_do_table(skb, ops->hooknum, in, out, net->ipv4.iptable_raw);
+	net = dev_net(state->in ? state->in : state->out);
+	return ipt_do_table(skb, ops->hooknum, state, net->ipv4.iptable_raw);
 }
 
 static struct nf_hook_ops *rawtable_ops __read_mostly;
diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c
index c86647ed2078..4bce3980ccd9 100644
--- a/net/ipv4/netfilter/iptable_security.c
+++ b/net/ipv4/netfilter/iptable_security.c
@@ -38,9 +38,7 @@ static const struct xt_table security_table = {
 
 static unsigned int
 iptable_security_hook(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 *))
+		      const struct nf_hook_state *state)
 {
 	const struct net *net;
 
@@ -50,8 +48,8 @@ iptable_security_hook(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		/* Somebody is playing with raw sockets. */
 		return NF_ACCEPT;
 
-	net = dev_net((in != NULL) ? in : out);
-	return ipt_do_table(skb, ops->hooknum, in, out,
+	net = dev_net(state->in ? state->in : state->out);
+	return ipt_do_table(skb, ops->hooknum, state,
 			    net->ipv4.iptable_security);
 }
 
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index a054fe083431..30ad9554b5e9 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -56,11 +56,11 @@ static bool ipv4_invert_tuple(struct nf_conntrack_tuple *tuple,
 	return true;
 }
 
-static int ipv4_print_tuple(struct seq_file *s,
+static void ipv4_print_tuple(struct seq_file *s,
 			    const struct nf_conntrack_tuple *tuple)
 {
-	return seq_printf(s, "src=%pI4 dst=%pI4 ",
-			  &tuple->src.u3.ip, &tuple->dst.u3.ip);
+	seq_printf(s, "src=%pI4 dst=%pI4 ",
+		   &tuple->src.u3.ip, &tuple->dst.u3.ip);
 }
 
 static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
@@ -94,9 +94,7 @@ static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
 
 static unsigned int ipv4_helper(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 *))
+				const struct nf_hook_state *state)
 {
 	struct nf_conn *ct;
 	enum ip_conntrack_info ctinfo;
@@ -123,9 +121,7 @@ static unsigned int ipv4_helper(const struct nf_hook_ops *ops,
 
 static unsigned int ipv4_confirm(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 *))
+				 const struct nf_hook_state *state)
 {
 	struct nf_conn *ct;
 	enum ip_conntrack_info ctinfo;
@@ -149,24 +145,20 @@ out:
 
 static unsigned int ipv4_conntrack_in(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 *))
+				      const struct nf_hook_state *state)
 {
-	return nf_conntrack_in(dev_net(in), PF_INET, ops->hooknum, skb);
+	return nf_conntrack_in(dev_net(state->in), PF_INET, ops->hooknum, skb);
 }
 
 static unsigned int ipv4_conntrack_local(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 *))
+					 const struct nf_hook_state *state)
 {
 	/* root is playing with raw sockets. */
 	if (skb->len < sizeof(struct iphdr) ||
 	    ip_hdrlen(skb) < sizeof(struct iphdr))
 		return NF_ACCEPT;
-	return nf_conntrack_in(dev_net(out), PF_INET, ops->hooknum, skb);
+	return nf_conntrack_in(dev_net(state->out), PF_INET, ops->hooknum, skb);
 }
 
 /* Connection tracking may drop packets, but never alters them, so
@@ -322,8 +314,8 @@ getorigdst(struct sock *sk, int optval, void __user *user, int *len)
 static int ipv4_tuple_to_nlattr(struct sk_buff *skb,
 				const struct nf_conntrack_tuple *tuple)
 {
-	if (nla_put_be32(skb, CTA_IP_V4_SRC, tuple->src.u3.ip) ||
-	    nla_put_be32(skb, CTA_IP_V4_DST, tuple->dst.u3.ip))
+	if (nla_put_in_addr(skb, CTA_IP_V4_SRC, tuple->src.u3.ip) ||
+	    nla_put_in_addr(skb, CTA_IP_V4_DST, tuple->dst.u3.ip))
 		goto nla_put_failure;
 	return 0;
 
@@ -342,8 +334,8 @@ static int ipv4_nlattr_to_tuple(struct nlattr *tb[],
 	if (!tb[CTA_IP_V4_SRC] || !tb[CTA_IP_V4_DST])
 		return -EINVAL;
 
-	t->src.u3.ip = nla_get_be32(tb[CTA_IP_V4_SRC]);
-	t->dst.u3.ip = nla_get_be32(tb[CTA_IP_V4_DST]);
+	t->src.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_SRC]);
+	t->dst.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_DST]);
 
 	return 0;
 }
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
index 4c48e434bb1f..f0dfe92a00d6 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
@@ -94,7 +94,7 @@ static void ct_seq_stop(struct seq_file *s, void *v)
 }
 
 #ifdef CONFIG_NF_CONNTRACK_SECMARK
-static int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct)
+static void ct_show_secctx(struct seq_file *s, const struct nf_conn *ct)
 {
 	int ret;
 	u32 len;
@@ -102,17 +102,15 @@ static int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct)
 
 	ret = security_secid_to_secctx(ct->secmark, &secctx, &len);
 	if (ret)
-		return 0;
+		return;
 
-	ret = seq_printf(s, "secctx=%s ", secctx);
+	seq_printf(s, "secctx=%s ", secctx);
 
 	security_release_secctx(secctx, len);
-	return ret;
 }
 #else
-static inline int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct)
+static inline void ct_show_secctx(struct seq_file *s, const struct nf_conn *ct)
 {
-	return 0;
 }
 #endif
 
@@ -141,47 +139,52 @@ static int ct_seq_show(struct seq_file *s, void *v)
 	NF_CT_ASSERT(l4proto);
 
 	ret = -ENOSPC;
-	if (seq_printf(s, "%-8s %u %ld ",
-		      l4proto->name, nf_ct_protonum(ct),
-		      timer_pending(&ct->timeout)
-		      ? (long)(ct->timeout.expires - jiffies)/HZ : 0) != 0)
-		goto release;
+	seq_printf(s, "%-8s %u %ld ",
+		   l4proto->name, nf_ct_protonum(ct),
+		   timer_pending(&ct->timeout)
+		   ? (long)(ct->timeout.expires - jiffies)/HZ : 0);
 
-	if (l4proto->print_conntrack && l4proto->print_conntrack(s, ct))
+	if (l4proto->print_conntrack)
+		l4proto->print_conntrack(s, ct);
+
+	if (seq_has_overflowed(s))
 		goto release;
 
-	if (print_tuple(s, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
-			l3proto, l4proto))
+	print_tuple(s, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
+		    l3proto, l4proto);
+
+	if (seq_has_overflowed(s))
 		goto release;
 
 	if (seq_print_acct(s, ct, IP_CT_DIR_ORIGINAL))
 		goto release;
 
 	if (!(test_bit(IPS_SEEN_REPLY_BIT, &ct->status)))
-		if (seq_printf(s, "[UNREPLIED] "))
-			goto release;
+		seq_printf(s, "[UNREPLIED] ");
+
+	print_tuple(s, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
+		    l3proto, l4proto);
 
-	if (print_tuple(s, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
-			l3proto, l4proto))
+	if (seq_has_overflowed(s))
 		goto release;
 
 	if (seq_print_acct(s, ct, IP_CT_DIR_REPLY))
 		goto release;
 
 	if (test_bit(IPS_ASSURED_BIT, &ct->status))
-		if (seq_printf(s, "[ASSURED] "))
-			goto release;
+		seq_printf(s, "[ASSURED] ");
 
 #ifdef CONFIG_NF_CONNTRACK_MARK
-	if (seq_printf(s, "mark=%u ", ct->mark))
-		goto release;
+	seq_printf(s, "mark=%u ", ct->mark);
 #endif
 
-	if (ct_show_secctx(s, ct))
-		goto release;
+	ct_show_secctx(s, ct);
+
+	seq_printf(s, "use=%u\n", atomic_read(&ct->ct_general.use));
 
-	if (seq_printf(s, "use=%u\n", atomic_read(&ct->ct_general.use)))
+	if (seq_has_overflowed(s))
 		goto release;
+
 	ret = 0;
 release:
 	nf_ct_put(ct);
@@ -297,7 +300,9 @@ static int exp_seq_show(struct seq_file *s, void *v)
 		    __nf_ct_l3proto_find(exp->tuple.src.l3num),
 		    __nf_ct_l4proto_find(exp->tuple.src.l3num,
 					 exp->tuple.dst.protonum));
-	return seq_putc(s, '\n');
+	seq_putc(s, '\n');
+
+	return 0;
 }
 
 static const struct seq_operations exp_seq_ops = {
diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
index b91b2641adda..80d5554b9a88 100644
--- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
+++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
@@ -72,13 +72,13 @@ static bool icmp_invert_tuple(struct nf_conntrack_tuple *tuple,
 }
 
 /* Print out the per-protocol part of the tuple. */
-static int icmp_print_tuple(struct seq_file *s,
+static void icmp_print_tuple(struct seq_file *s,
 			    const struct nf_conntrack_tuple *tuple)
 {
-	return seq_printf(s, "type=%u code=%u id=%u ",
-			  tuple->dst.u.icmp.type,
-			  tuple->dst.u.icmp.code,
-			  ntohs(tuple->src.u.icmp.id));
+	seq_printf(s, "type=%u code=%u id=%u ",
+		   tuple->dst.u.icmp.type,
+		   tuple->dst.u.icmp.code,
+		   ntohs(tuple->src.u.icmp.id));
 }
 
 static unsigned int *icmp_get_timeouts(struct net *net)
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index 7e5ca6f2d0cd..c88b7d434718 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -63,9 +63,7 @@ static enum ip_defrag_users nf_ct_defrag_user(unsigned int hooknum,
 
 static unsigned int ipv4_conntrack_defrag(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 *))
+					  const struct nf_hook_state *state)
 {
 	struct sock *sk = skb->sk;
 	struct inet_sock *inet = inet_sk(skb->sk);
diff --git a/net/ipv4/netfilter/nf_log_arp.c b/net/ipv4/netfilter/nf_log_arp.c
index ccfc78db12ee..e7ad950cf9ef 100644
--- a/net/ipv4/netfilter/nf_log_arp.c
+++ b/net/ipv4/netfilter/nf_log_arp.c
@@ -11,6 +11,9 @@
  * published by the Free Software Foundation.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/spinlock.h>
 #include <linux/skbuff.h>
@@ -26,7 +29,7 @@ static struct nf_loginfo default_loginfo = {
 	.type	= NF_LOG_TYPE_LOG,
 	.u = {
 		.log = {
-			.level	  = 5,
+			.level	  = LOGLEVEL_NOTICE,
 			.logflags = NF_LOG_MASK,
 		},
 	},
@@ -74,12 +77,12 @@ static void dump_arp_packet(struct nf_log_buf *m,
 		       ap->mac_src, ap->ip_src, ap->mac_dst, ap->ip_dst);
 }
 
-void nf_log_arp_packet(struct net *net, u_int8_t pf,
-		      unsigned int hooknum, const struct sk_buff *skb,
-		      const struct net_device *in,
-		      const struct net_device *out,
-		      const struct nf_loginfo *loginfo,
-		      const char *prefix)
+static void nf_log_arp_packet(struct net *net, u_int8_t pf,
+			      unsigned int hooknum, const struct sk_buff *skb,
+			      const struct net_device *in,
+			      const struct net_device *out,
+			      const struct nf_loginfo *loginfo,
+			      const char *prefix)
 {
 	struct nf_log_buf *m;
 
@@ -130,8 +133,17 @@ static int __init nf_log_arp_init(void)
 	if (ret < 0)
 		return ret;
 
-	nf_log_register(NFPROTO_ARP, &nf_arp_logger);
+	ret = nf_log_register(NFPROTO_ARP, &nf_arp_logger);
+	if (ret < 0) {
+		pr_err("failed to register logger\n");
+		goto err1;
+	}
+
 	return 0;
+
+err1:
+	unregister_pernet_subsys(&nf_log_arp_net_ops);
+	return ret;
 }
 
 static void __exit nf_log_arp_exit(void)
diff --git a/net/ipv4/netfilter/nf_log_ipv4.c b/net/ipv4/netfilter/nf_log_ipv4.c
index 078bdca1b607..076aadda0473 100644
--- a/net/ipv4/netfilter/nf_log_ipv4.c
+++ b/net/ipv4/netfilter/nf_log_ipv4.c
@@ -6,6 +6,9 @@
  * published by the Free Software Foundation.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/spinlock.h>
 #include <linux/skbuff.h>
@@ -25,7 +28,7 @@ static struct nf_loginfo default_loginfo = {
 	.type	= NF_LOG_TYPE_LOG,
 	.u = {
 		.log = {
-			.level	  = 5,
+			.level	  = LOGLEVEL_NOTICE,
 			.logflags = NF_LOG_MASK,
 		},
 	},
@@ -366,8 +369,17 @@ static int __init nf_log_ipv4_init(void)
 	if (ret < 0)
 		return ret;
 
-	nf_log_register(NFPROTO_IPV4, &nf_ip_logger);
+	ret = nf_log_register(NFPROTO_IPV4, &nf_ip_logger);
+	if (ret < 0) {
+		pr_err("failed to register logger\n");
+		goto err1;
+	}
+
 	return 0;
+
+err1:
+	unregister_pernet_subsys(&nf_log_ipv4_net_ops);
+	return ret;
 }
 
 static void __exit nf_log_ipv4_exit(void)
diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
index fc37711e11f3..e59cc05c09e9 100644
--- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
@@ -256,11 +256,10 @@ EXPORT_SYMBOL_GPL(nf_nat_icmp_reply_translation);
 
 unsigned int
 nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
-	       const struct net_device *in, const struct net_device *out,
+	       const struct nf_hook_state *state,
 	       unsigned int (*do_chain)(const struct nf_hook_ops *ops,
 					struct sk_buff *skb,
-					const struct net_device *in,
-					const struct net_device *out,
+					const struct nf_hook_state *state,
 					struct nf_conn *ct))
 {
 	struct nf_conn *ct;
@@ -309,7 +308,7 @@ nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		if (!nf_nat_initialized(ct, maniptype)) {
 			unsigned int ret;
 
-			ret = do_chain(ops, skb, in, out, ct);
+			ret = do_chain(ops, skb, state, ct);
 			if (ret != NF_ACCEPT)
 				return ret;
 
@@ -323,7 +322,8 @@ nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
 			pr_debug("Already setup manip %s for ct %p\n",
 				 maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST",
 				 ct);
-			if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
+			if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat,
+					       state->out))
 				goto oif_changed;
 		}
 		break;
@@ -332,7 +332,7 @@ nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		/* ESTABLISHED */
 		NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
 			     ctinfo == IP_CT_ESTABLISHED_REPLY);
-		if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
+		if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, state->out))
 			goto oif_changed;
 	}
 
@@ -346,17 +346,16 @@ EXPORT_SYMBOL_GPL(nf_nat_ipv4_fn);
 
 unsigned int
 nf_nat_ipv4_in(const struct nf_hook_ops *ops, struct sk_buff *skb,
-	       const struct net_device *in, const struct net_device *out,
+	       const struct nf_hook_state *state,
 	       unsigned int (*do_chain)(const struct nf_hook_ops *ops,
 					 struct sk_buff *skb,
-					 const struct net_device *in,
-					 const struct net_device *out,
+					 const struct nf_hook_state *state,
 					 struct nf_conn *ct))
 {
 	unsigned int ret;
 	__be32 daddr = ip_hdr(skb)->daddr;
 
-	ret = nf_nat_ipv4_fn(ops, skb, in, out, do_chain);
+	ret = nf_nat_ipv4_fn(ops, skb, state, do_chain);
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    daddr != ip_hdr(skb)->daddr)
 		skb_dst_drop(skb);
@@ -367,11 +366,10 @@ EXPORT_SYMBOL_GPL(nf_nat_ipv4_in);
 
 unsigned int
 nf_nat_ipv4_out(const struct nf_hook_ops *ops, struct sk_buff *skb,
-		const struct net_device *in, const struct net_device *out,
+		const struct nf_hook_state *state,
 		unsigned int (*do_chain)(const struct nf_hook_ops *ops,
 					  struct sk_buff *skb,
-					  const struct net_device *in,
-					  const struct net_device *out,
+					  const struct nf_hook_state *state,
 					  struct nf_conn *ct))
 {
 #ifdef CONFIG_XFRM
@@ -386,7 +384,7 @@ nf_nat_ipv4_out(const struct nf_hook_ops *ops, struct sk_buff *skb,
 	    ip_hdrlen(skb) < sizeof(struct iphdr))
 		return NF_ACCEPT;
 
-	ret = nf_nat_ipv4_fn(ops, skb, in, out, do_chain);
+	ret = nf_nat_ipv4_fn(ops, skb, state, do_chain);
 #ifdef CONFIG_XFRM
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    !(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
@@ -410,11 +408,10 @@ EXPORT_SYMBOL_GPL(nf_nat_ipv4_out);
 
 unsigned int
 nf_nat_ipv4_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
-		     const struct net_device *in, const struct net_device *out,
+		     const struct nf_hook_state *state,
 		     unsigned int (*do_chain)(const struct nf_hook_ops *ops,
 					       struct sk_buff *skb,
-					       const struct net_device *in,
-					       const struct net_device *out,
+					       const struct nf_hook_state *state,
 					       struct nf_conn *ct))
 {
 	const struct nf_conn *ct;
@@ -427,7 +424,7 @@ nf_nat_ipv4_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
 	    ip_hdrlen(skb) < sizeof(struct iphdr))
 		return NF_ACCEPT;
 
-	ret = nf_nat_ipv4_fn(ops, skb, in, out, do_chain);
+	ret = nf_nat_ipv4_fn(ops, skb, state, do_chain);
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
 		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index 1baaa83dfe5c..3262e41ff76f 100644
--- a/net/ipv4/netfilter/nf_reject_ipv4.c
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -11,7 +11,9 @@
 #include <net/tcp.h>
 #include <net/route.h>
 #include <net/dst.h>
+#include <net/netfilter/ipv4/nf_reject.h>
 #include <linux/netfilter_ipv4.h>
+#include <linux/netfilter_bridge.h>
 #include <net/netfilter/ipv4/nf_reject.h>
 
 const struct tcphdr *nf_reject_ip_tcphdr_get(struct sk_buff *oldskb,
@@ -42,7 +44,7 @@ EXPORT_SYMBOL_GPL(nf_reject_ip_tcphdr_get);
 
 struct iphdr *nf_reject_iphdr_put(struct sk_buff *nskb,
 				  const struct sk_buff *oldskb,
-				  __be16 protocol, int ttl)
+				  __u8 protocol, int ttl)
 {
 	struct iphdr *niph, *oiph = ip_hdr(oldskb);
 
@@ -145,7 +147,8 @@ void nf_send_reset(struct sk_buff *oldskb, int hook)
 	 */
 	if (oldskb->nf_bridge) {
 		struct ethhdr *oeth = eth_hdr(oldskb);
-		nskb->dev = oldskb->nf_bridge->physindev;
+
+		nskb->dev = nf_bridge_get_physindev(oldskb);
 		niph->tot_len = htons(nskb->len);
 		ip_send_check(niph);
 		if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol),
@@ -163,4 +166,27 @@ void nf_send_reset(struct sk_buff *oldskb, int hook)
 }
 EXPORT_SYMBOL_GPL(nf_send_reset);
 
+void nf_send_unreach(struct sk_buff *skb_in, int code, int hook)
+{
+	struct iphdr *iph = ip_hdr(skb_in);
+	u8 proto;
+
+	if (skb_in->csum_bad || iph->frag_off & htons(IP_OFFSET))
+		return;
+
+	if (skb_csum_unnecessary(skb_in)) {
+		icmp_send(skb_in, ICMP_DEST_UNREACH, code, 0);
+		return;
+	}
+
+	if (iph->protocol == IPPROTO_TCP || iph->protocol == IPPROTO_UDP)
+		proto = iph->protocol;
+	else
+		proto = 0;
+
+	if (nf_ip_checksum(skb_in, hook, ip_hdrlen(skb_in), proto) == 0)
+		icmp_send(skb_in, ICMP_DEST_UNREACH, code, 0);
+}
+EXPORT_SYMBOL_GPL(nf_send_unreach);
+
 MODULE_LICENSE("GPL");
diff --git a/net/ipv4/netfilter/nf_tables_arp.c b/net/ipv4/netfilter/nf_tables_arp.c
index 19412a4063fb..8412268bbad1 100644
--- a/net/ipv4/netfilter/nf_tables_arp.c
+++ b/net/ipv4/netfilter/nf_tables_arp.c
@@ -17,13 +17,11 @@
 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 *))
+		  const struct nf_hook_state *state)
 {
 	struct nft_pktinfo pkt;
 
-	nft_set_pktinfo(&pkt, ops, skb, in, out);
+	nft_set_pktinfo(&pkt, ops, skb, state);
 
 	return nft_do_chain(&pkt, ops);
 }
diff --git a/net/ipv4/netfilter/nf_tables_ipv4.c b/net/ipv4/netfilter/nf_tables_ipv4.c
index 6820c8c40842..aa180d3a69a5 100644
--- a/net/ipv4/netfilter/nf_tables_ipv4.c
+++ b/net/ipv4/netfilter/nf_tables_ipv4.c
@@ -20,22 +20,18 @@
 
 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 *))
+				      const struct nf_hook_state *state)
 {
 	struct nft_pktinfo pkt;
 
-	nft_set_pktinfo_ipv4(&pkt, ops, skb, in, out);
+	nft_set_pktinfo_ipv4(&pkt, ops, skb, state);
 
 	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 *))
+				    const struct nf_hook_state *state)
 {
 	if (unlikely(skb->len < sizeof(struct iphdr) ||
 		     ip_hdr(skb)->ihl < sizeof(struct iphdr) / 4)) {
@@ -45,7 +41,7 @@ static unsigned int nft_ipv4_output(const struct nf_hook_ops *ops,
 		return NF_ACCEPT;
 	}
 
-	return nft_do_chain_ipv4(ops, skb, in, out, okfn);
+	return nft_do_chain_ipv4(ops, skb, state);
 }
 
 struct nft_af_info nft_af_ipv4 __read_mostly = {
diff --git a/net/ipv4/netfilter/nft_chain_nat_ipv4.c b/net/ipv4/netfilter/nft_chain_nat_ipv4.c
index df547bf50078..bf5c30ae14e4 100644
--- a/net/ipv4/netfilter/nft_chain_nat_ipv4.c
+++ b/net/ipv4/netfilter/nft_chain_nat_ipv4.c
@@ -28,51 +28,42 @@
 
 static unsigned int nft_nat_do_chain(const struct nf_hook_ops *ops,
 				      struct sk_buff *skb,
-				      const struct net_device *in,
-				      const struct net_device *out,
+				      const struct nf_hook_state *state,
 				      struct nf_conn *ct)
 {
 	struct nft_pktinfo pkt;
 
-	nft_set_pktinfo_ipv4(&pkt, ops, skb, in, out);
+	nft_set_pktinfo_ipv4(&pkt, ops, skb, state);
 
 	return nft_do_chain(&pkt, ops);
 }
 
 static unsigned int nft_nat_ipv4_fn(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 *))
+				    const struct nf_hook_state *state)
 {
-	return nf_nat_ipv4_fn(ops, skb, in, out, nft_nat_do_chain);
+	return nf_nat_ipv4_fn(ops, skb, state, nft_nat_do_chain);
 }
 
 static unsigned int nft_nat_ipv4_in(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 *))
+				    const struct nf_hook_state *state)
 {
-	return nf_nat_ipv4_in(ops, skb, in, out, nft_nat_do_chain);
+	return nf_nat_ipv4_in(ops, skb, state, nft_nat_do_chain);
 }
 
 static unsigned int nft_nat_ipv4_out(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 *))
+				     const struct nf_hook_state *state)
 {
-	return nf_nat_ipv4_out(ops, skb, in, out, nft_nat_do_chain);
+	return nf_nat_ipv4_out(ops, skb, state, nft_nat_do_chain);
 }
 
 static unsigned int nft_nat_ipv4_local_fn(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 *))
+					  const struct nf_hook_state *state)
 {
-	return nf_nat_ipv4_local_fn(ops, skb, in, out, nft_nat_do_chain);
+	return nf_nat_ipv4_local_fn(ops, skb, state, nft_nat_do_chain);
 }
 
 static const struct nf_chain_type nft_chain_nat_ipv4 = {
diff --git a/net/ipv4/netfilter/nft_chain_route_ipv4.c b/net/ipv4/netfilter/nft_chain_route_ipv4.c
index 125b66766c0a..e335b0afdaf3 100644
--- a/net/ipv4/netfilter/nft_chain_route_ipv4.c
+++ b/net/ipv4/netfilter/nft_chain_route_ipv4.c
@@ -23,9 +23,7 @@
 
 static unsigned int nf_route_table_hook(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 *))
+					const struct nf_hook_state *state)
 {
 	unsigned int ret;
 	struct nft_pktinfo pkt;
@@ -39,7 +37,7 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops,
 	    ip_hdrlen(skb) < sizeof(struct iphdr))
 		return NF_ACCEPT;
 
-	nft_set_pktinfo_ipv4(&pkt, ops, skb, in, out);
+	nft_set_pktinfo_ipv4(&pkt, ops, skb, state);
 
 	mark = skb->mark;
 	iph = ip_hdr(skb);
diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c
index c1023c445920..40e414c4ca56 100644
--- a/net/ipv4/netfilter/nft_masq_ipv4.c
+++ b/net/ipv4/netfilter/nft_masq_ipv4.c
@@ -17,19 +17,17 @@
 #include <net/netfilter/ipv4/nf_nat_masquerade.h>
 
 static void nft_masq_ipv4_eval(const struct nft_expr *expr,
-			       struct nft_data data[NFT_REG_MAX + 1],
+			       struct nft_regs *regs,
 			       const struct nft_pktinfo *pkt)
 {
 	struct nft_masq *priv = nft_expr_priv(expr);
 	struct nf_nat_range range;
-	unsigned int verdict;
 
+	memset(&range, 0, sizeof(range));
 	range.flags = priv->flags;
 
-	verdict = nf_nat_masquerade_ipv4(pkt->skb, pkt->ops->hooknum,
-					 &range, pkt->out);
-
-	data[NFT_REG_VERDICT].verdict = verdict;
+	regs->verdict.code = nf_nat_masquerade_ipv4(pkt->skb, pkt->ops->hooknum,
+						    &range, pkt->out);
 }
 
 static struct nft_expr_type nft_masq_ipv4_type;
diff --git a/net/ipv4/netfilter/nft_redir_ipv4.c b/net/ipv4/netfilter/nft_redir_ipv4.c
new file mode 100644
index 000000000000..d8d795df9c13
--- /dev/null
+++ b/net/ipv4/netfilter/nft_redir_ipv4.c
@@ -0,0 +1,76 @@
+/*
+ * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo.borrero.glez@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.
+ */
+
+#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/nf_nat.h>
+#include <net/netfilter/nf_nat_redirect.h>
+#include <net/netfilter/nft_redir.h>
+
+static void nft_redir_ipv4_eval(const struct nft_expr *expr,
+				struct nft_regs *regs,
+				const struct nft_pktinfo *pkt)
+{
+	struct nft_redir *priv = nft_expr_priv(expr);
+	struct nf_nat_ipv4_multi_range_compat mr;
+
+	memset(&mr, 0, sizeof(mr));
+	if (priv->sreg_proto_min) {
+		mr.range[0].min.all =
+			*(__be16 *)&regs->data[priv->sreg_proto_min];
+		mr.range[0].max.all =
+			*(__be16 *)&regs->data[priv->sreg_proto_max];
+		mr.range[0].flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
+	}
+
+	mr.range[0].flags |= priv->flags;
+
+	regs->verdict.code = nf_nat_redirect_ipv4(pkt->skb, &mr,
+						  pkt->ops->hooknum);
+}
+
+static struct nft_expr_type nft_redir_ipv4_type;
+static const struct nft_expr_ops nft_redir_ipv4_ops = {
+	.type		= &nft_redir_ipv4_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_redir)),
+	.eval		= nft_redir_ipv4_eval,
+	.init		= nft_redir_init,
+	.dump		= nft_redir_dump,
+	.validate	= nft_redir_validate,
+};
+
+static struct nft_expr_type nft_redir_ipv4_type __read_mostly = {
+	.family		= NFPROTO_IPV4,
+	.name		= "redir",
+	.ops		= &nft_redir_ipv4_ops,
+	.policy		= nft_redir_policy,
+	.maxattr	= NFTA_REDIR_MAX,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nft_redir_ipv4_module_init(void)
+{
+	return nft_register_expr(&nft_redir_ipv4_type);
+}
+
+static void __exit nft_redir_ipv4_module_exit(void)
+{
+	nft_unregister_expr(&nft_redir_ipv4_type);
+}
+
+module_init(nft_redir_ipv4_module_init);
+module_exit(nft_redir_ipv4_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>");
+MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "redir");
diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c
index ed33299c56d1..b07e58b51158 100644
--- a/net/ipv4/netfilter/nft_reject_ipv4.c
+++ b/net/ipv4/netfilter/nft_reject_ipv4.c
@@ -19,24 +19,26 @@
 #include <net/netfilter/ipv4/nf_reject.h>
 #include <net/netfilter/nft_reject.h>
 
-void nft_reject_ipv4_eval(const struct nft_expr *expr,
-			  struct nft_data data[NFT_REG_MAX + 1],
-			  const struct nft_pktinfo *pkt)
+static void nft_reject_ipv4_eval(const struct nft_expr *expr,
+				 struct nft_regs *regs,
+				 const struct nft_pktinfo *pkt)
 {
 	struct nft_reject *priv = nft_expr_priv(expr);
 
 	switch (priv->type) {
 	case NFT_REJECT_ICMP_UNREACH:
-		nf_send_unreach(pkt->skb, priv->icmp_code);
+		nf_send_unreach(pkt->skb, priv->icmp_code,
+				pkt->ops->hooknum);
 		break;
 	case NFT_REJECT_TCP_RST:
 		nf_send_reset(pkt->skb, pkt->ops->hooknum);
 		break;
+	default:
+		break;
 	}
 
-	data[NFT_REG_VERDICT].verdict = NF_DROP;
+	regs->verdict.code = NF_DROP;
 }
-EXPORT_SYMBOL_GPL(nft_reject_ipv4_eval);
 
 static struct nft_expr_type nft_reject_ipv4_type;
 static const struct nft_expr_ops nft_reject_ipv4_ops = {
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 57f7c9804139..05ff44b758df 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -64,11 +64,11 @@ EXPORT_SYMBOL_GPL(pingv6_ops);
 
 static u16 ping_port_rover;
 
-static inline int ping_hashfn(struct net *net, unsigned int num, unsigned int mask)
+static inline u32 ping_hashfn(const struct net *net, u32 num, u32 mask)
 {
-	int res = (num + net_hash_mix(net)) & mask;
+	u32 res = (num + net_hash_mix(net)) & mask;
 
-	pr_debug("hash(%d) = %d\n", num, res);
+	pr_debug("hash(%u) = %u\n", num, res);
 	return res;
 }
 EXPORT_SYMBOL_GPL(ping_hash);
@@ -158,6 +158,7 @@ void ping_unhash(struct sock *sk)
 	if (sk_hashed(sk)) {
 		write_lock_bh(&ping_table.lock);
 		hlist_nulls_del(&sk->sk_nulls_node);
+		sk_nulls_node_init(&sk->sk_nulls_node);
 		sock_put(sk);
 		isk->inet_num = 0;
 		isk->inet_sport = 0;
@@ -217,6 +218,8 @@ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident)
 					     &ipv6_hdr(skb)->daddr))
 				continue;
 #endif
+		} else {
+			continue;
 		}
 
 		if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)
@@ -257,6 +260,9 @@ int ping_init_sock(struct sock *sk)
 	kgid_t low, high;
 	int ret = 0;
 
+	if (sk->sk_family == AF_INET6)
+		sk->sk_ipv6only = 1;
+
 	inet_get_ping_group_range_net(net, &low, &high);
 	if (gid_lte(low, group) && gid_lte(group, high))
 		return 0;
@@ -303,6 +309,11 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
 		if (addr_len < sizeof(*addr))
 			return -EINVAL;
 
+		if (addr->sin_family != AF_INET &&
+		    !(addr->sin_family == AF_UNSPEC &&
+		      addr->sin_addr.s_addr == htonl(INADDR_ANY)))
+			return -EAFNOSUPPORT;
+
 		pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n",
 			 sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port));
 
@@ -328,7 +339,7 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
 			return -EINVAL;
 
 		if (addr->sin6_family != AF_INET6)
-			return -EINVAL;
+			return -EAFNOSUPPORT;
 
 		pr_debug("ping_check_bind_addr(sk=%p,addr=%pI6c,port=%d)\n",
 			 sk, addr->sin6_addr.s6_addr, ntohs(addr->sin6_port));
@@ -506,7 +517,7 @@ void ping_err(struct sk_buff *skb, int offset, u32 info)
 		 ntohs(icmph->un.echo.sequence));
 
 	sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id));
-	if (sk == NULL) {
+	if (!sk) {
 		pr_debug("no socket, dropping\n");
 		return;	/* No socket for error */
 	}
@@ -597,18 +608,18 @@ int ping_getfrag(void *from, char *to,
 	struct pingfakehdr *pfh = (struct pingfakehdr *)from;
 
 	if (offset == 0) {
-		if (fraglen < sizeof(struct icmphdr))
+		fraglen -= sizeof(struct icmphdr);
+		if (fraglen < 0)
 			BUG();
-		if (csum_partial_copy_fromiovecend(to + sizeof(struct icmphdr),
-			    pfh->iov, 0, fraglen - sizeof(struct icmphdr),
-			    &pfh->wcheck))
+		if (csum_and_copy_from_iter(to + sizeof(struct icmphdr),
+			    fraglen, &pfh->wcheck,
+			    &pfh->msg->msg_iter) != fraglen)
 			return -EFAULT;
 	} else if (offset < sizeof(struct icmphdr)) {
 			BUG();
 	} else {
-		if (csum_partial_copy_fromiovecend
-				(to, pfh->iov, offset - sizeof(struct icmphdr),
-				 fraglen, &pfh->wcheck))
+		if (csum_and_copy_from_iter(to, fraglen, &pfh->wcheck,
+					    &pfh->msg->msg_iter) != fraglen)
 			return -EFAULT;
 	}
 
@@ -660,7 +671,7 @@ int ping_common_sendmsg(int family, struct msghdr *msg, size_t len,
 	 *	Fetch the ICMP header provided by the userland.
 	 *	iovec is modified! The ICMP header is consumed.
 	 */
-	if (memcpy_fromiovec(user_icmph, msg->msg_iov, icmph_len))
+	if (memcpy_from_msg(user_icmph, msg, icmph_len))
 		return -EFAULT;
 
 	if (family == AF_INET) {
@@ -682,8 +693,7 @@ int ping_common_sendmsg(int family, struct msghdr *msg, size_t len,
 }
 EXPORT_SYMBOL_GPL(ping_common_sendmsg);
 
-static int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
-			   size_t len)
+static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 {
 	struct net *net = sock_net(sk);
 	struct flowi4 fl4;
@@ -714,7 +724,7 @@ static int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
 		if (msg->msg_namelen < sizeof(*usin))
 			return -EINVAL;
 		if (usin->sin_family != AF_INET)
-			return -EINVAL;
+			return -EAFNOSUPPORT;
 		daddr = usin->sin_addr.s_addr;
 		/* no remote port */
 	} else {
@@ -809,7 +819,7 @@ back_from_confirm:
 	pfh.icmph.checksum = 0;
 	pfh.icmph.un.echo.id = inet->inet_sport;
 	pfh.icmph.un.echo.sequence = user_icmph.un.echo.sequence;
-	pfh.iov = msg->msg_iov;
+	pfh.msg = msg;
 	pfh.wcheck = 0;
 	pfh.family = AF_INET;
 
@@ -839,8 +849,8 @@ do_confirm:
 	goto out;
 }
 
-int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
-		 size_t len, int noblock, int flags, int *addr_len)
+int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
+		 int flags, int *addr_len)
 {
 	struct inet_sock *isk = inet_sk(sk);
 	int family = sk->sk_family;
@@ -853,16 +863,8 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	if (flags & MSG_OOB)
 		goto out;
 
-	if (flags & MSG_ERRQUEUE) {
-		if (family == AF_INET) {
-			return ip_recv_error(sk, msg, len, addr_len);
-#if IS_ENABLED(CONFIG_IPV6)
-		} else if (family == AF_INET6) {
-			return pingv6_ops.ipv6_recv_error(sk, msg, len,
-							  addr_len);
-#endif
-		}
-	}
+	if (flags & MSG_ERRQUEUE)
+		return inet_recv_error(sk, msg, len, addr_len);
 
 	skb = skb_recv_datagram(sk, flags, noblock, &err);
 	if (!skb)
@@ -875,7 +877,7 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	}
 
 	/* Don't bother checking the checksum */
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (err)
 		goto done;
 
@@ -955,7 +957,7 @@ EXPORT_SYMBOL_GPL(ping_queue_rcv_skb);
  *	All we need to do is get the socket.
  */
 
-void ping_rcv(struct sk_buff *skb)
+bool ping_rcv(struct sk_buff *skb)
 {
 	struct sock *sk;
 	struct net *net = dev_net(skb->dev);
@@ -970,15 +972,18 @@ void ping_rcv(struct sk_buff *skb)
 	skb_push(skb, skb->data - (u8 *)icmph);
 
 	sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id));
-	if (sk != NULL) {
+	if (sk) {
+		struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
+
 		pr_debug("rcv on socket %p\n", sk);
-		ping_queue_rcv_skb(sk, skb_get(skb));
+		if (skb2)
+			ping_queue_rcv_skb(sk, skb2);
 		sock_put(sk);
-		return;
+		return true;
 	}
 	pr_debug("no socket, dropping\n");
 
-	/* We're called from icmp_rcv(). kfree_skb() is done there. */
+	return false;
 }
 EXPORT_SYMBOL_GPL(ping_rcv);
 
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 8e3eb39f84e7..e1f3b911dd1e 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -63,7 +63,7 @@ static int sockstat_seq_show(struct seq_file *seq, void *v)
 	socket_seq_show(seq);
 	seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %ld\n",
 		   sock_prot_inuse_get(net, &tcp_prot), orphans,
-		   tcp_death_row.tw_count, sockets,
+		   atomic_read(&tcp_death_row.tw_count), sockets,
 		   proto_memory_allocated(&tcp_prot));
 	seq_printf(seq, "UDP: inuse %d mem %ld\n",
 		   sock_prot_inuse_get(net, &udp_prot),
@@ -181,6 +181,7 @@ static const struct snmp_mib snmp4_udp_list[] = {
 	SNMP_MIB_ITEM("RcvbufErrors", UDP_MIB_RCVBUFERRORS),
 	SNMP_MIB_ITEM("SndbufErrors", UDP_MIB_SNDBUFERRORS),
 	SNMP_MIB_ITEM("InCsumErrors", UDP_MIB_CSUMERRORS),
+	SNMP_MIB_ITEM("IgnoredMulti", UDP_MIB_IGNOREDMULTI),
 	SNMP_MIB_SENTINEL
 };
 
@@ -287,6 +288,16 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("TCPWantZeroWindowAdv", LINUX_MIB_TCPWANTZEROWINDOWADV),
 	SNMP_MIB_ITEM("TCPSynRetrans", LINUX_MIB_TCPSYNRETRANS),
 	SNMP_MIB_ITEM("TCPOrigDataSent", LINUX_MIB_TCPORIGDATASENT),
+	SNMP_MIB_ITEM("TCPHystartTrainDetect", LINUX_MIB_TCPHYSTARTTRAINDETECT),
+	SNMP_MIB_ITEM("TCPHystartTrainCwnd", LINUX_MIB_TCPHYSTARTTRAINCWND),
+	SNMP_MIB_ITEM("TCPHystartDelayDetect", LINUX_MIB_TCPHYSTARTDELAYDETECT),
+	SNMP_MIB_ITEM("TCPHystartDelayCwnd", LINUX_MIB_TCPHYSTARTDELAYCWND),
+	SNMP_MIB_ITEM("TCPACKSkippedSynRecv", LINUX_MIB_TCPACKSKIPPEDSYNRECV),
+	SNMP_MIB_ITEM("TCPACKSkippedPAWS", LINUX_MIB_TCPACKSKIPPEDPAWS),
+	SNMP_MIB_ITEM("TCPACKSkippedSeq", LINUX_MIB_TCPACKSKIPPEDSEQ),
+	SNMP_MIB_ITEM("TCPACKSkippedFinWait2", LINUX_MIB_TCPACKSKIPPEDFINWAIT2),
+	SNMP_MIB_ITEM("TCPACKSkippedTimeWait", LINUX_MIB_TCPACKSKIPPEDTIMEWAIT),
+	SNMP_MIB_ITEM("TCPACKSkippedChallenge", LINUX_MIB_TCPACKSKIPPEDCHALLENGE),
 	SNMP_MIB_SENTINEL
 };
 
@@ -296,12 +307,12 @@ static void icmpmsg_put_line(struct seq_file *seq, unsigned long *vals,
 	int j;
 
 	if (count) {
-		seq_printf(seq, "\nIcmpMsg:");
+		seq_puts(seq, "\nIcmpMsg:");
 		for (j = 0; j < count; ++j)
 			seq_printf(seq, " %sType%u",
 				type[j] & 0x100 ? "Out" : "In",
 				type[j] & 0xff);
-		seq_printf(seq, "\nIcmpMsg:");
+		seq_puts(seq, "\nIcmpMsg:");
 		for (j = 0; j < count; ++j)
 			seq_printf(seq, " %lu", vals[j]);
 	}
@@ -342,7 +353,7 @@ static void icmp_put(struct seq_file *seq)
 	seq_puts(seq, "\nIcmp: InMsgs InErrors InCsumErrors");
 	for (i = 0; icmpmibmap[i].name != NULL; i++)
 		seq_printf(seq, " In%s", icmpmibmap[i].name);
-	seq_printf(seq, " OutMsgs OutErrors");
+	seq_puts(seq, " OutMsgs OutErrors");
 	for (i = 0; icmpmibmap[i].name != NULL; i++)
 		seq_printf(seq, " Out%s", icmpmibmap[i].name);
 	seq_printf(seq, "\nIcmp: %lu %lu %lu",
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 739db3100c23..561cd4b8fc6e 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -46,7 +46,6 @@
 #include <linux/stddef.h>
 #include <linux/slab.h>
 #include <linux/errno.h>
-#include <linux/aio.h>
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/spinlock.h>
@@ -79,6 +78,16 @@
 #include <linux/netfilter.h>
 #include <linux/netfilter_ipv4.h>
 #include <linux/compat.h>
+#include <linux/uio.h>
+
+struct raw_frag_vec {
+	struct msghdr *msg;
+	union {
+		struct icmphdr icmph;
+		char c[1];
+	} hdr;
+	int hlen;
+};
 
 static struct raw_hashinfo raw_v4_hashinfo = {
 	.lock = __RW_LOCK_UNLOCKED(raw_v4_hashinfo.lock),
@@ -283,7 +292,7 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info)
 
 	read_lock(&raw_v4_hashinfo.lock);
 	raw_sk = sk_head(&raw_v4_hashinfo.ht[hash]);
-	if (raw_sk != NULL) {
+	if (raw_sk) {
 		iph = (const struct iphdr *)skb->data;
 		net = dev_net(skb->dev);
 
@@ -327,7 +336,7 @@ int raw_rcv(struct sock *sk, struct sk_buff *skb)
 }
 
 static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
-			   void *from, size_t length,
+			   struct msghdr *msg, size_t length,
 			   struct rtable **rtp,
 			   unsigned int flags)
 {
@@ -353,7 +362,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 	skb = sock_alloc_send_skb(sk,
 				  length + hlen + tlen + 15,
 				  flags & MSG_DONTWAIT, &err);
-	if (skb == NULL)
+	if (!skb)
 		goto error;
 	skb_reserve(skb, hlen);
 
@@ -372,7 +381,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 
 	skb->transport_header = skb->network_header;
 	err = -EFAULT;
-	if (memcpy_fromiovecend((void *)iph, from, 0, length))
+	if (memcpy_from_msg(iph, msg, length))
 		goto error_free;
 
 	iphlen = iph->ihl * 4;
@@ -394,7 +403,7 @@ 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, NULL);
+			ip_select_ident(net, skb, NULL);
 
 		iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
 	}
@@ -402,8 +411,8 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 		icmp_out_count(net, ((struct icmphdr *)
 			skb_transport_header(skb))->type);
 
-	err = NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_OUT, skb, NULL,
-		      rt->dst.dev, dst_output);
+	err = NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_OUT, sk, skb,
+		      NULL, rt->dst.dev, dst_output_sk);
 	if (err > 0)
 		err = net_xmit_errno(err);
 	if (err)
@@ -420,55 +429,58 @@ error:
 	return err;
 }
 
-static int raw_probe_proto_opt(struct flowi4 *fl4, struct msghdr *msg)
+static int raw_probe_proto_opt(struct raw_frag_vec *rfv, struct flowi4 *fl4)
 {
-	struct iovec *iov;
-	u8 __user *type = NULL;
-	u8 __user *code = NULL;
-	int probed = 0;
-	unsigned int i;
+	int err;
 
-	if (!msg->msg_iov)
+	if (fl4->flowi4_proto != IPPROTO_ICMP)
 		return 0;
 
-	for (i = 0; i < msg->msg_iovlen; i++) {
-		iov = &msg->msg_iov[i];
-		if (!iov)
-			continue;
-
-		switch (fl4->flowi4_proto) {
-		case IPPROTO_ICMP:
-			/* check if one-byte field is readable or not. */
-			if (iov->iov_base && iov->iov_len < 1)
-				break;
-
-			if (!type) {
-				type = iov->iov_base;
-				/* check if code field is readable or not. */
-				if (iov->iov_len > 1)
-					code = type + 1;
-			} else if (!code)
-				code = iov->iov_base;
-
-			if (type && code) {
-				if (get_user(fl4->fl4_icmp_type, type) ||
-				    get_user(fl4->fl4_icmp_code, code))
-					return -EFAULT;
-				probed = 1;
-			}
-			break;
-		default:
-			probed = 1;
-			break;
-		}
-		if (probed)
-			break;
-	}
+	/* We only need the first two bytes. */
+	rfv->hlen = 2;
+
+	err = memcpy_from_msg(rfv->hdr.c, rfv->msg, rfv->hlen);
+	if (err)
+		return err;
+
+	fl4->fl4_icmp_type = rfv->hdr.icmph.type;
+	fl4->fl4_icmp_code = rfv->hdr.icmph.code;
+
 	return 0;
 }
 
-static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
-		       size_t len)
+static int raw_getfrag(void *from, char *to, int offset, int len, int odd,
+		       struct sk_buff *skb)
+{
+	struct raw_frag_vec *rfv = from;
+
+	if (offset < rfv->hlen) {
+		int copy = min(rfv->hlen - offset, len);
+
+		if (skb->ip_summed == CHECKSUM_PARTIAL)
+			memcpy(to, rfv->hdr.c + offset, copy);
+		else
+			skb->csum = csum_block_add(
+				skb->csum,
+				csum_partial_copy_nocheck(rfv->hdr.c + offset,
+							  to, copy, 0),
+				odd);
+
+		odd = 0;
+		offset += copy;
+		to += copy;
+		len -= copy;
+
+		if (!len)
+			return 0;
+	}
+
+	offset -= rfv->hlen;
+
+	return ip_generic_getfrag(rfv->msg, to, offset, len, odd, skb);
+}
+
+static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct ipcm_cookie ipc;
@@ -480,6 +492,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	u8  tos;
 	int err;
 	struct ip_options_data opt_copy;
+	struct raw_frag_vec rfv;
 
 	err = -EMSGSIZE;
 	if (len > 0xFFFF)
@@ -585,7 +598,10 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 			   daddr, saddr, 0, 0);
 
 	if (!inet->hdrincl) {
-		err = raw_probe_proto_opt(&fl4, msg);
+		rfv.msg = msg;
+		rfv.hlen = 0;
+
+		err = raw_probe_proto_opt(&rfv, &fl4);
 		if (err)
 			goto done;
 	}
@@ -607,7 +623,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 back_from_confirm:
 
 	if (inet->hdrincl)
-		err = raw_send_hdrinc(sk, &fl4, msg->msg_iov, len,
+		err = raw_send_hdrinc(sk, &fl4, msg, len,
 				      &rt, msg->msg_flags);
 
 	 else {
@@ -616,8 +632,8 @@ back_from_confirm:
 		if (!ipc.addr)
 			ipc.addr = fl4.daddr;
 		lock_sock(sk);
-		err = ip_append_data(sk, &fl4, ip_generic_getfrag,
-				     msg->msg_iov, len, 0,
+		err = ip_append_data(sk, &fl4, raw_getfrag,
+				     &rfv, len, 0,
 				     &ipc, &rt, msg->msg_flags);
 		if (err)
 			ip_flush_pending_frames(sk);
@@ -691,8 +707,8 @@ out:	return ret;
  *	we return it, otherwise we block.
  */
 
-static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
-		       size_t len, int noblock, int flags, int *addr_len)
+static int raw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+		       int noblock, int flags, int *addr_len)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	size_t copied = 0;
@@ -718,7 +734,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		copied = len;
 	}
 
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (err)
 		goto done;
 
@@ -855,7 +871,7 @@ static int raw_ioctl(struct sock *sk, int cmd, unsigned long arg)
 
 		spin_lock_bh(&sk->sk_receive_queue.lock);
 		skb = skb_peek(&sk->sk_receive_queue);
-		if (skb != NULL)
+		if (skb)
 			amount = skb->len;
 		spin_unlock_bh(&sk->sk_receive_queue.lock);
 		return put_user(amount, (int __user *)arg);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 6a2155b02602..f45f2a12f37b 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -152,7 +152,6 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
 
 static struct dst_ops ipv4_dst_ops = {
 	.family =		AF_INET,
-	.protocol =		cpu_to_be16(ETH_P_IP),
 	.check =		ipv4_dst_check,
 	.default_advmss =	ipv4_default_advmss,
 	.mtu =			ipv4_mtu,
@@ -483,7 +482,7 @@ u32 ip_idents_reserve(u32 hash, int segs)
 }
 EXPORT_SYMBOL(ip_idents_reserve);
 
-void __ip_select_ident(struct iphdr *iph, int segs)
+void __ip_select_ident(struct net *net, struct iphdr *iph, int segs)
 {
 	static u32 ip_idents_hashrnd __read_mostly;
 	u32 hash, id;
@@ -492,7 +491,7 @@ void __ip_select_ident(struct iphdr *iph, int segs)
 
 	hash = jhash_3words((__force u32)iph->daddr,
 			    (__force u32)iph->saddr,
-			    iph->protocol,
+			    iph->protocol ^ net_hash_mix(net),
 			    ip_idents_hashrnd);
 	id = ip_idents_reserve(hash, segs);
 	iph->id = htons(id);
@@ -903,6 +902,10 @@ static int ip_error(struct sk_buff *skb)
 	bool send;
 	int code;
 
+	/* IP on this device is disabled. */
+	if (!in_dev)
+		goto out;
+
 	net = dev_net(rt->dst.dev);
 	if (!IN_DEV_FORWARD(in_dev)) {
 		switch (rt->dst.error) {
@@ -963,7 +966,7 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 	if (dst_metric_locked(dst, RTAX_MTU))
 		return;
 
-	if (dst->dev->mtu < mtu)
+	if (ipv4_mtu(dst) < mtu)
 		return;
 
 	if (mtu < ip_rt_min_pmtu)
@@ -1054,7 +1057,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 	__build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
 
 	rt = (struct rtable *)odst;
-	if (odst->obsolete && odst->ops->check(odst, 0) == NULL) {
+	if (odst->obsolete && !odst->ops->check(odst, 0)) {
 		rt = ip_route_output_flow(sock_net(sk), &fl4, sk);
 		if (IS_ERR(rt))
 			goto out;
@@ -1325,14 +1328,22 @@ static bool rt_cache_route(struct fib_nh *nh, struct rtable *rt)
 	return ret;
 }
 
-static DEFINE_SPINLOCK(rt_uncached_lock);
-static LIST_HEAD(rt_uncached_list);
+struct uncached_list {
+	spinlock_t		lock;
+	struct list_head	head;
+};
+
+static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt_uncached_list);
 
 static void rt_add_uncached_list(struct rtable *rt)
 {
-	spin_lock_bh(&rt_uncached_lock);
-	list_add_tail(&rt->rt_uncached, &rt_uncached_list);
-	spin_unlock_bh(&rt_uncached_lock);
+	struct uncached_list *ul = raw_cpu_ptr(&rt_uncached_list);
+
+	rt->rt_uncached_list = ul;
+
+	spin_lock_bh(&ul->lock);
+	list_add_tail(&rt->rt_uncached, &ul->head);
+	spin_unlock_bh(&ul->lock);
 }
 
 static void ipv4_dst_destroy(struct dst_entry *dst)
@@ -1340,27 +1351,32 @@ static void ipv4_dst_destroy(struct dst_entry *dst)
 	struct rtable *rt = (struct rtable *) dst;
 
 	if (!list_empty(&rt->rt_uncached)) {
-		spin_lock_bh(&rt_uncached_lock);
+		struct uncached_list *ul = rt->rt_uncached_list;
+
+		spin_lock_bh(&ul->lock);
 		list_del(&rt->rt_uncached);
-		spin_unlock_bh(&rt_uncached_lock);
+		spin_unlock_bh(&ul->lock);
 	}
 }
 
 void rt_flush_dev(struct net_device *dev)
 {
-	if (!list_empty(&rt_uncached_list)) {
-		struct net *net = dev_net(dev);
-		struct rtable *rt;
+	struct net *net = dev_net(dev);
+	struct rtable *rt;
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu);
 
-		spin_lock_bh(&rt_uncached_lock);
-		list_for_each_entry(rt, &rt_uncached_list, rt_uncached) {
+		spin_lock_bh(&ul->lock);
+		list_for_each_entry(rt, &ul->head, rt_uncached) {
 			if (rt->dst.dev != dev)
 				continue;
 			rt->dst.dev = net->loopback_dev;
 			dev_hold(rt->dst.dev);
 			dev_put(dev);
 		}
-		spin_unlock_bh(&rt_uncached_lock);
+		spin_unlock_bh(&ul->lock);
 	}
 }
 
@@ -1435,7 +1451,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 
 	/* Primary sanity checks. */
 
-	if (in_dev == NULL)
+	if (!in_dev)
 		return -EINVAL;
 
 	if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) ||
@@ -1538,7 +1554,7 @@ static int __mkroute_input(struct sk_buff *skb,
 
 	/* get a working reference to the output device */
 	out_dev = __in_dev_get_rcu(FIB_RES_DEV(*res));
-	if (out_dev == NULL) {
+	if (!out_dev) {
 		net_crit_ratelimited("Bug in ip_route_input_slow(). Please report.\n");
 		return -EINVAL;
 	}
@@ -1554,11 +1570,10 @@ static int __mkroute_input(struct sk_buff *skb,
 
 	do_cache = res->fi && !itag;
 	if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) &&
+	    skb->protocol == htons(ETH_P_IP) &&
 	    (IN_DEV_SHARED_MEDIA(out_dev) ||
-	     inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) {
-		flags |= RTCF_DOREDIRECT;
-		do_cache = false;
-	}
+	     inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res))))
+		IPCB(skb)->flags |= IPSKB_DOREDIRECT;
 
 	if (skb->protocol != htons(ETH_P_IP)) {
 		/* Not IP (i.e. ARP). Do not create route, if it is
@@ -1577,7 +1592,7 @@ static int __mkroute_input(struct sk_buff *skb,
 
 	fnhe = find_exception(&FIB_RES_NH(*res), daddr);
 	if (do_cache) {
-		if (fnhe != NULL)
+		if (fnhe)
 			rth = rcu_dereference(fnhe->fnhe_rth_input);
 		else
 			rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
@@ -2040,7 +2055,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
 		     ipv4_is_lbcast(fl4->daddr))) {
 			/* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */
 			dev_out = __ip_dev_find(net, fl4->saddr, false);
-			if (dev_out == NULL)
+			if (!dev_out)
 				goto out;
 
 			/* Special hack: user can direct multicasts
@@ -2073,7 +2088,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
 	if (fl4->flowi4_oif) {
 		dev_out = dev_get_by_index_rcu(net, fl4->flowi4_oif);
 		rth = ERR_PTR(-ENODEV);
-		if (dev_out == NULL)
+		if (!dev_out)
 			goto out;
 
 		/* RACE: Check return value of inet_select_addr instead. */
@@ -2210,7 +2225,6 @@ static u32 *ipv4_rt_blackhole_cow_metrics(struct dst_entry *dst,
 
 static struct dst_ops ipv4_dst_blackhole_ops = {
 	.family			=	AF_INET,
-	.protocol		=	cpu_to_be16(ETH_P_IP),
 	.check			=	ipv4_blackhole_dst_check,
 	.mtu			=	ipv4_blackhole_mtu,
 	.default_advmss		=	ipv4_default_advmss,
@@ -2286,7 +2300,7 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src,
 	u32 metrics[RTAX_MAX];
 
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*r), flags);
-	if (nlh == NULL)
+	if (!nlh)
 		return -EMSGSIZE;
 
 	r = nlmsg_data(nlh);
@@ -2303,12 +2317,14 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src,
 	r->rtm_flags	= (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED;
 	if (rt->rt_flags & RTCF_NOTIFY)
 		r->rtm_flags |= RTM_F_NOTIFY;
+	if (IPCB(skb)->flags & IPSKB_DOREDIRECT)
+		r->rtm_flags |= RTCF_DOREDIRECT;
 
-	if (nla_put_be32(skb, RTA_DST, dst))
+	if (nla_put_in_addr(skb, RTA_DST, dst))
 		goto nla_put_failure;
 	if (src) {
 		r->rtm_src_len = 32;
-		if (nla_put_be32(skb, RTA_SRC, src))
+		if (nla_put_in_addr(skb, RTA_SRC, src))
 			goto nla_put_failure;
 	}
 	if (rt->dst.dev &&
@@ -2321,11 +2337,11 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src,
 #endif
 	if (!rt_is_input_route(rt) &&
 	    fl4->saddr != src) {
-		if (nla_put_be32(skb, RTA_PREFSRC, fl4->saddr))
+		if (nla_put_in_addr(skb, RTA_PREFSRC, fl4->saddr))
 			goto nla_put_failure;
 	}
 	if (rt->rt_uses_gateway &&
-	    nla_put_be32(skb, RTA_GATEWAY, rt->rt_gateway))
+	    nla_put_in_addr(skb, RTA_GATEWAY, rt->rt_gateway))
 		goto nla_put_failure;
 
 	expires = rt->dst.expires;
@@ -2377,7 +2393,8 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src,
 	if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, error) < 0)
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
@@ -2405,7 +2422,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	rtm = nlmsg_data(nlh);
 
 	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
-	if (skb == NULL) {
+	if (!skb) {
 		err = -ENOBUFS;
 		goto errout;
 	}
@@ -2420,8 +2437,8 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	ip_hdr(skb)->protocol = IPPROTO_ICMP;
 	skb_reserve(skb, MAX_HEADER + sizeof(struct iphdr));
 
-	src = tb[RTA_SRC] ? nla_get_be32(tb[RTA_SRC]) : 0;
-	dst = tb[RTA_DST] ? nla_get_be32(tb[RTA_DST]) : 0;
+	src = tb[RTA_SRC] ? nla_get_in_addr(tb[RTA_SRC]) : 0;
+	dst = tb[RTA_DST] ? nla_get_in_addr(tb[RTA_DST]) : 0;
 	iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0;
 	mark = tb[RTA_MARK] ? nla_get_u32(tb[RTA_MARK]) : 0;
 
@@ -2436,7 +2453,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 		struct net_device *dev;
 
 		dev = __dev_get_by_index(net, iif);
-		if (dev == NULL) {
+		if (!dev) {
 			err = -ENODEV;
 			goto errout_free;
 		}
@@ -2469,7 +2486,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	err = rt_fill_info(net, dst, src, &fl4, skb,
 			   NETLINK_CB(in_skb).portid, nlh->nlmsg_seq,
 			   RTM_NEWROUTE, 0, 0);
-	if (err <= 0)
+	if (err < 0)
 		goto errout_free;
 
 	err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid);
@@ -2635,7 +2652,7 @@ static __net_init int sysctl_route_net_init(struct net *net)
 	tbl = ipv4_route_flush_table;
 	if (!net_eq(net, &init_net)) {
 		tbl = kmemdup(tbl, sizeof(ipv4_route_flush_table), GFP_KERNEL);
-		if (tbl == NULL)
+		if (!tbl)
 			goto err_dup;
 
 		/* Don't export sysctls to unprivileged users */
@@ -2645,7 +2662,7 @@ static __net_init int sysctl_route_net_init(struct net *net)
 	tbl[0].extra1 = net;
 
 	net->ipv4.route_hdr = register_net_sysctl(net, "net/ipv4/route", tbl);
-	if (net->ipv4.route_hdr == NULL)
+	if (!net->ipv4.route_hdr)
 		goto err_reg;
 	return 0;
 
@@ -2717,6 +2734,7 @@ struct ip_rt_acct __percpu *ip_rt_acct __read_mostly;
 int __init ip_rt_init(void)
 {
 	int rc = 0;
+	int cpu;
 
 	ip_idents = kmalloc(IP_IDENTS_SZ * sizeof(*ip_idents), GFP_KERNEL);
 	if (!ip_idents)
@@ -2724,6 +2742,12 @@ int __init ip_rt_init(void)
 
 	prandom_bytes(ip_idents, IP_IDENTS_SZ * sizeof(*ip_idents));
 
+	for_each_possible_cpu(cpu) {
+		struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu);
+
+		INIT_LIST_HEAD(&ul->head);
+		spin_lock_init(&ul->lock);
+	}
 #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 32b98d0207b4..df849e5a10f1 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -19,10 +19,6 @@
 #include <net/tcp.h>
 #include <net/route.h>
 
-/* Timestamps: lowest bits store TCP options */
-#define TSBITS 6
-#define TSMASK (((__u32)1 << TSBITS) - 1)
-
 extern int sysctl_tcp_syncookies;
 
 static u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS] __read_mostly;
@@ -30,6 +26,30 @@ static u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS] __read_mostly;
 #define COOKIEBITS 24	/* Upper bits store count */
 #define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
 
+/* TCP Timestamp: 6 lowest bits of timestamp sent in the cookie SYN-ACK
+ * stores TCP options:
+ *
+ * MSB                               LSB
+ * | 31 ...   6 |  5  |  4   | 3 2 1 0 |
+ * |  Timestamp | ECN | SACK | WScale  |
+ *
+ * When we receive a valid cookie-ACK, we look at the echoed tsval (if
+ * any) to figure out which TCP options we should use for the rebuilt
+ * connection.
+ *
+ * A WScale setting of '0xf' (which is an invalid scaling value)
+ * means that original syn did not include the TCP window scaling option.
+ */
+#define TS_OPT_WSCALE_MASK	0xf
+#define TS_OPT_SACK		BIT(4)
+#define TS_OPT_ECN		BIT(5)
+/* There is no TS_OPT_TIMESTAMP:
+ * if ACK contains timestamp option, we already know it was
+ * requested/supported by the syn/synack exchange.
+ */
+#define TSBITS	6
+#define TSMASK	(((__u32)1 << TSBITS) - 1)
+
 static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS],
 		      ipv4_cookie_scratch);
 
@@ -67,9 +87,11 @@ __u32 cookie_init_timestamp(struct request_sock *req)
 
 	ireq = inet_rsk(req);
 
-	options = ireq->wscale_ok ? ireq->snd_wscale : 0xf;
-	options |= ireq->sack_ok << 4;
-	options |= ireq->ecn_ok << 5;
+	options = ireq->wscale_ok ? ireq->snd_wscale : TS_OPT_WSCALE_MASK;
+	if (ireq->sack_ok)
+		options |= TS_OPT_SACK;
+	if (ireq->ecn_ok)
+		options |= TS_OPT_ECN;
 
 	ts = ts_now & ~TSMASK;
 	ts |= options;
@@ -197,19 +219,20 @@ int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th,
 }
 EXPORT_SYMBOL_GPL(__cookie_v4_check);
 
-static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
-					   struct request_sock *req,
-					   struct dst_entry *dst)
+static struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
+				    struct request_sock *req,
+				    struct dst_entry *dst)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct sock *child;
 
 	child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst);
-	if (child)
+	if (child) {
+		atomic_set(&req->rsk_refcnt, 1);
 		inet_csk_reqsk_queue_add(sk, req, child);
-	else
+	} else {
 		reqsk_free(req);
-
+	}
 	return child;
 }
 
@@ -219,16 +242,13 @@ static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
  * additional tcp options in the timestamp.
  * This extracts these options from the timestamp echo.
  *
- * The lowest 4 bits store snd_wscale.
- * next 2 bits indicate SACK and ECN support.
- *
- * return false if we decode an option that should not be.
+ * return false if we decode a tcp option that is disabled
+ * on the host.
  */
-bool cookie_check_timestamp(struct tcp_options_received *tcp_opt,
-			struct net *net, bool *ecn_ok)
+bool cookie_timestamp_decode(struct tcp_options_received *tcp_opt)
 {
 	/* echoed timestamp, lowest bits contain options */
-	u32 options = tcp_opt->rcv_tsecr & TSMASK;
+	u32 options = tcp_opt->rcv_tsecr;
 
 	if (!tcp_opt->saw_tstamp)  {
 		tcp_clear_options(tcp_opt);
@@ -238,22 +258,35 @@ bool cookie_check_timestamp(struct tcp_options_received *tcp_opt,
 	if (!sysctl_tcp_timestamps)
 		return false;
 
-	tcp_opt->sack_ok = (options & (1 << 4)) ? TCP_SACK_SEEN : 0;
-	*ecn_ok = (options >> 5) & 1;
-	if (*ecn_ok && !net->ipv4.sysctl_tcp_ecn)
-		return false;
+	tcp_opt->sack_ok = (options & TS_OPT_SACK) ? TCP_SACK_SEEN : 0;
 
 	if (tcp_opt->sack_ok && !sysctl_tcp_sack)
 		return false;
 
-	if ((options & 0xf) == 0xf)
+	if ((options & TS_OPT_WSCALE_MASK) == TS_OPT_WSCALE_MASK)
 		return true; /* no window scaling */
 
 	tcp_opt->wscale_ok = 1;
-	tcp_opt->snd_wscale = options & 0xf;
+	tcp_opt->snd_wscale = options & TS_OPT_WSCALE_MASK;
+
 	return sysctl_tcp_window_scaling != 0;
 }
-EXPORT_SYMBOL(cookie_check_timestamp);
+EXPORT_SYMBOL(cookie_timestamp_decode);
+
+bool cookie_ecn_ok(const struct tcp_options_received *tcp_opt,
+		   const struct net *net, const struct dst_entry *dst)
+{
+	bool ecn_ok = tcp_opt->rcv_tsecr & TS_OPT_ECN;
+
+	if (!ecn_ok)
+		return false;
+
+	if (net->ipv4.sysctl_tcp_ecn)
+		return true;
+
+	return dst_feature(dst, RTAX_FEATURE_ECN);
+}
+EXPORT_SYMBOL(cookie_ecn_ok);
 
 struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 {
@@ -269,14 +302,16 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	int mss;
 	struct rtable *rt;
 	__u8 rcv_wscale;
-	bool ecn_ok = false;
 	struct flowi4 fl4;
 
 	if (!sysctl_tcp_syncookies || !th->ack || th->rst)
 		goto out;
 
-	if (tcp_synq_no_recent_overflow(sk) ||
-	    (mss = __cookie_v4_check(ip_hdr(skb), th, cookie)) == 0) {
+	if (tcp_synq_no_recent_overflow(sk))
+		goto out;
+
+	mss = __cookie_v4_check(ip_hdr(skb), th, cookie);
+	if (mss == 0) {
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESFAILED);
 		goto out;
 	}
@@ -287,11 +322,11 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	memset(&tcp_opt, 0, sizeof(tcp_opt));
 	tcp_parse_options(skb, &tcp_opt, 0, NULL);
 
-	if (!cookie_check_timestamp(&tcp_opt, sock_net(sk), &ecn_ok))
+	if (!cookie_timestamp_decode(&tcp_opt))
 		goto out;
 
 	ret = NULL;
-	req = inet_reqsk_alloc(&tcp_request_sock_ops); /* for safety */
+	req = inet_reqsk_alloc(&tcp_request_sock_ops, sk); /* for safety */
 	if (!req)
 		goto out;
 
@@ -302,17 +337,18 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	req->mss		= mss;
 	ireq->ir_num		= ntohs(th->dest);
 	ireq->ir_rmt_port	= th->source;
-	ireq->ir_loc_addr	= ip_hdr(skb)->daddr;
-	ireq->ir_rmt_addr	= ip_hdr(skb)->saddr;
+	sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
+	sk_daddr_set(req_to_sk(req), 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;
 	ireq->wscale_ok		= tcp_opt.wscale_ok;
 	ireq->tstamp_ok		= tcp_opt.saw_tstamp;
 	req->ts_recent		= tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
 	treq->snt_synack	= tcp_opt.saw_tstamp ? tcp_opt.rcv_tsecr : 0;
-	treq->listener		= NULL;
+	treq->tfo_listener	= false;
+
+	ireq->ir_iif = sk->sk_bound_dev_if;
 
 	/* We throwed the options of the initial SYN away, so we hope
 	 * the ACK carries the same options again (see RFC1122 4.2.3.8)
@@ -324,7 +360,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 		goto out;
 	}
 
-	req->expires	= 0UL;
 	req->num_retrans = 0;
 
 	/*
@@ -354,6 +389,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 				  dst_metric(&rt->dst, RTAX_INITRWND));
 
 	ireq->rcv_wscale  = rcv_wscale;
+	ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, sock_net(sk), &rt->dst);
 
 	ret = get_cookie_sock(sk, skb, req, &rt->dst);
 	/* ip_queue_xmit() depends on our flow being setup
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index b3c53c8b331e..c3852a7ff3c7 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -496,6 +496,13 @@ static struct ctl_table ipv4_table[] = {
 		.proc_handler	= proc_dointvec
 	},
 	{
+		.procname	= "tcp_max_reordering",
+		.data		= &sysctl_tcp_max_reordering,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
 		.procname	= "tcp_dsack",
 		.data		= &sysctl_tcp_dsack,
 		.maxlen		= sizeof(int),
@@ -597,20 +604,6 @@ static struct ctl_table ipv4_table[] = {
 		.proc_handler	= proc_tcp_congestion_control,
 	},
 	{
-		.procname	= "tcp_mtu_probing",
-		.data		= &sysctl_tcp_mtu_probing,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "tcp_base_mss",
-		.data		= &sysctl_tcp_base_mss,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
 		.procname	= "tcp_workaround_signed_windows",
 		.data		= &sysctl_tcp_workaround_signed_windows,
 		.maxlen		= sizeof(int),
@@ -722,6 +715,13 @@ static struct ctl_table ipv4_table[] = {
 		.extra2		= &one,
 	},
 	{
+		.procname	= "tcp_invalid_ratelimit",
+		.data		= &sysctl_tcp_invalid_ratelimit,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_ms_jiffies,
+	},
+	{
 		.procname	= "icmp_msgs_per_sec",
 		.data		= &sysctl_icmp_msgs_per_sec,
 		.maxlen		= sizeof(int),
@@ -869,6 +869,34 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "tcp_mtu_probing",
+		.data		= &init_net.ipv4.sysctl_tcp_mtu_probing,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "tcp_base_mss",
+		.data		= &init_net.ipv4.sysctl_tcp_base_mss,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "tcp_probe_threshold",
+		.data		= &init_net.ipv4.sysctl_tcp_probe_threshold,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "tcp_probe_interval",
+		.data		= &init_net.ipv4.sysctl_tcp_probe_interval,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 	{ }
 };
 
@@ -881,7 +909,7 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
 		int i;
 
 		table = kmemdup(table, sizeof(ipv4_net_table), GFP_KERNEL);
-		if (table == NULL)
+		if (!table)
 			goto err_alloc;
 
 		/* Update the variables to point into the current struct net */
@@ -890,7 +918,7 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
 	}
 
 	net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table);
-	if (net->ipv4.ipv4_hdr == NULL)
+	if (!net->ipv4.ipv4_hdr)
 		goto err_reg;
 
 	net->ipv4.sysctl_local_reserved_ports = kzalloc(65536 / 8, GFP_KERNEL);
@@ -928,7 +956,7 @@ static __init int sysctl_ipv4_init(void)
 	struct ctl_table_header *hdr;
 
 	hdr = register_net_sysctl(&init_net, "net/ipv4", ipv4_table);
-	if (hdr == NULL)
+	if (!hdr)
 		return -ENOMEM;
 
 	if (register_pernet_subsys(&ipv4_sysctl_ops)) {
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 39ec0c379545..f1377f2a0472 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -252,6 +252,7 @@
 #include <linux/types.h>
 #include <linux/fcntl.h>
 #include <linux/poll.h>
+#include <linux/inet_diag.h>
 #include <linux/init.h>
 #include <linux/fs.h>
 #include <linux/skbuff.h>
@@ -401,6 +402,7 @@ void tcp_init_sock(struct sock *sk)
 	tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
 	tp->snd_cwnd_clamp = ~0;
 	tp->mss_cache = TCP_MSS_DEFAULT;
+	u64_stats_init(&tp->syncp);
 
 	tp->reordering = sysctl_tcp_reordering;
 	tcp_enable_early_retrans(tp);
@@ -496,7 +498,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 
 	/* Connected or passive Fast Open socket? */
 	if (sk->sk_state != TCP_SYN_SENT &&
-	    (sk->sk_state != TCP_SYN_RECV || tp->fastopen_rsk != NULL)) {
+	    (sk->sk_state != TCP_SYN_RECV || tp->fastopen_rsk)) {
 		int target = sock_rcvlowat(sk, 0, INT_MAX);
 
 		if (tp->urg_seq == tp->copied_seq &&
@@ -520,8 +522,10 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 
 				/* Race breaker. If space is freed after
 				 * wspace test but before the flags are set,
-				 * IO signal will be lost.
+				 * IO signal will be lost. Memory barrier
+				 * pairs with the input side.
 				 */
+				smp_mb__after_atomic();
 				if (sk_stream_is_writeable(sk))
 					mask |= POLLOUT | POLLWRNORM;
 			}
@@ -835,47 +839,25 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now,
 				       int large_allowed)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	u32 xmit_size_goal, old_size_goal;
-
-	xmit_size_goal = mss_now;
-
-	if (large_allowed && sk_can_gso(sk)) {
-		u32 gso_size, hlen;
-
-		/* Maybe we should/could use sk->sk_prot->max_header here ? */
-		hlen = inet_csk(sk)->icsk_af_ops->net_header_len +
-		       inet_csk(sk)->icsk_ext_hdr_len +
-		       tp->tcp_header_len;
-
-		/* Goal is to send at least one packet per ms,
-		 * not one big TSO packet every 100 ms.
-		 * This preserves ACK clocking and is consistent
-		 * with tcp_tso_should_defer() heuristic.
-		 */
-		gso_size = sk->sk_pacing_rate / (2 * MSEC_PER_SEC);
-		gso_size = max_t(u32, gso_size,
-				 sysctl_tcp_min_tso_segs * mss_now);
-
-		xmit_size_goal = min_t(u32, gso_size,
-				       sk->sk_gso_max_size - 1 - hlen);
-
-		xmit_size_goal = tcp_bound_to_half_wnd(tp, xmit_size_goal);
-
-		/* We try hard to avoid divides here */
-		old_size_goal = tp->xmit_size_goal_segs * mss_now;
-
-		if (likely(old_size_goal <= xmit_size_goal &&
-			   old_size_goal + mss_now > xmit_size_goal)) {
-			xmit_size_goal = old_size_goal;
-		} else {
-			tp->xmit_size_goal_segs =
-				min_t(u16, xmit_size_goal / mss_now,
-				      sk->sk_gso_max_segs);
-			xmit_size_goal = tp->xmit_size_goal_segs * mss_now;
-		}
+	u32 new_size_goal, size_goal;
+
+	if (!large_allowed || !sk_can_gso(sk))
+		return mss_now;
+
+	/* Note : tcp_tso_autosize() will eventually split this later */
+	new_size_goal = sk->sk_gso_max_size - 1 - MAX_TCP_HEADER;
+	new_size_goal = tcp_bound_to_half_wnd(tp, new_size_goal);
+
+	/* We try hard to avoid divides here */
+	size_goal = tp->gso_segs * mss_now;
+	if (unlikely(new_size_goal < size_goal ||
+		     new_size_goal >= size_goal + mss_now)) {
+		tp->gso_segs = min_t(u16, new_size_goal / mss_now,
+				     sk->sk_gso_max_segs);
+		size_goal = tp->gso_segs * mss_now;
 	}
 
-	return max(xmit_size_goal, mss_now);
+	return max(size_goal, mss_now);
 }
 
 static int tcp_send_mss(struct sock *sk, int *size_goal, int flags)
@@ -1050,7 +1032,7 @@ static inline int select_size(const struct sock *sk, bool sg)
 
 void tcp_free_fastopen_req(struct tcp_sock *tp)
 {
-	if (tp->fastopen_req != NULL) {
+	if (tp->fastopen_req) {
 		kfree(tp->fastopen_req);
 		tp->fastopen_req = NULL;
 	}
@@ -1064,12 +1046,12 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 
 	if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE))
 		return -EOPNOTSUPP;
-	if (tp->fastopen_req != NULL)
+	if (tp->fastopen_req)
 		return -EALREADY; /* Another Fast Open is in progress */
 
 	tp->fastopen_req = kzalloc(sizeof(struct tcp_fastopen_request),
 				   sk->sk_allocation);
-	if (unlikely(tp->fastopen_req == NULL))
+	if (unlikely(!tp->fastopen_req))
 		return -ENOBUFS;
 	tp->fastopen_req->data = msg;
 	tp->fastopen_req->size = size;
@@ -1082,14 +1064,12 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 	return err;
 }
 
-int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
-		size_t size)
+int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 {
-	struct iovec *iov;
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
-	int iovlen, flags, err, copied = 0;
-	int mss_now = 0, size_goal, copied_syn = 0, offset = 0;
+	int flags, err, copied = 0;
+	int mss_now = 0, size_goal, copied_syn = 0;
 	bool sg;
 	long timeo;
 
@@ -1102,7 +1082,6 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 			goto out;
 		else if (err)
 			goto out_err;
-		offset = copied_syn;
 	}
 
 	timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
@@ -1136,8 +1115,6 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	mss_now = tcp_send_mss(sk, &size_goal, flags);
 
 	/* Ok commence sending. */
-	iovlen = msg->msg_iovlen;
-	iov = msg->msg_iov;
 	copied = 0;
 
 	err = -EPIPE;
@@ -1146,151 +1123,134 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 
 	sg = !!(sk->sk_route_caps & NETIF_F_SG);
 
-	while (--iovlen >= 0) {
-		size_t seglen = iov->iov_len;
-		unsigned char __user *from = iov->iov_base;
+	while (msg_data_left(msg)) {
+		int copy = 0;
+		int max = size_goal;
 
-		iov++;
-		if (unlikely(offset > 0)) {  /* Skip bytes copied in SYN */
-			if (offset >= seglen) {
-				offset -= seglen;
-				continue;
-			}
-			seglen -= offset;
-			from += offset;
-			offset = 0;
+		skb = tcp_write_queue_tail(sk);
+		if (tcp_send_head(sk)) {
+			if (skb->ip_summed == CHECKSUM_NONE)
+				max = mss_now;
+			copy = max - skb->len;
 		}
 
-		while (seglen > 0) {
-			int copy = 0;
-			int max = size_goal;
-
-			skb = tcp_write_queue_tail(sk);
-			if (tcp_send_head(sk)) {
-				if (skb->ip_summed == CHECKSUM_NONE)
-					max = mss_now;
-				copy = max - skb->len;
-			}
-
-			if (copy <= 0) {
+		if (copy <= 0) {
 new_segment:
-				/* Allocate new segment. If the interface is SG,
-				 * allocate skb fitting to single page.
-				 */
-				if (!sk_stream_memory_free(sk))
-					goto wait_for_sndbuf;
+			/* Allocate new segment. If the interface is SG,
+			 * allocate skb fitting to single page.
+			 */
+			if (!sk_stream_memory_free(sk))
+				goto wait_for_sndbuf;
+
+			skb = sk_stream_alloc_skb(sk,
+						  select_size(sk, sg),
+						  sk->sk_allocation);
+			if (!skb)
+				goto wait_for_memory;
 
-				skb = sk_stream_alloc_skb(sk,
-							  select_size(sk, sg),
-							  sk->sk_allocation);
-				if (!skb)
-					goto wait_for_memory;
+			/*
+			 * Check whether we can use HW checksum.
+			 */
+			if (sk->sk_route_caps & NETIF_F_ALL_CSUM)
+				skb->ip_summed = CHECKSUM_PARTIAL;
 
-				/*
-				 * Check whether we can use HW checksum.
-				 */
-				if (sk->sk_route_caps & NETIF_F_ALL_CSUM)
-					skb->ip_summed = CHECKSUM_PARTIAL;
+			skb_entail(sk, skb);
+			copy = size_goal;
+			max = size_goal;
 
-				skb_entail(sk, skb);
-				copy = size_goal;
-				max = size_goal;
+			/* All packets are restored as if they have
+			 * already been sent. skb_mstamp isn't set to
+			 * avoid wrong rtt estimation.
+			 */
+			if (tp->repair)
+				TCP_SKB_CB(skb)->sacked |= TCPCB_REPAIRED;
+		}
 
-				/* All packets are restored as if they have
-				 * already been sent. skb_mstamp isn't set to
-				 * avoid wrong rtt estimation.
-				 */
-				if (tp->repair)
-					TCP_SKB_CB(skb)->sacked |= TCPCB_REPAIRED;
-			}
+		/* Try to append data to the end of skb. */
+		if (copy > msg_data_left(msg))
+			copy = msg_data_left(msg);
+
+		/* Where to copy to? */
+		if (skb_availroom(skb) > 0) {
+			/* We have some space in skb head. Superb! */
+			copy = min_t(int, copy, skb_availroom(skb));
+			err = skb_add_data_nocache(sk, skb, &msg->msg_iter, copy);
+			if (err)
+				goto do_fault;
+		} else {
+			bool merge = true;
+			int i = skb_shinfo(skb)->nr_frags;
+			struct page_frag *pfrag = sk_page_frag(sk);
 
-			/* Try to append data to the end of skb. */
-			if (copy > seglen)
-				copy = seglen;
-
-			/* Where to copy to? */
-			if (skb_availroom(skb) > 0) {
-				/* We have some space in skb head. Superb! */
-				copy = min_t(int, copy, skb_availroom(skb));
-				err = skb_add_data_nocache(sk, skb, from, copy);
-				if (err)
-					goto do_fault;
-			} else {
-				bool merge = true;
-				int i = skb_shinfo(skb)->nr_frags;
-				struct page_frag *pfrag = sk_page_frag(sk);
-
-				if (!sk_page_frag_refill(sk, pfrag))
-					goto wait_for_memory;
-
-				if (!skb_can_coalesce(skb, i, pfrag->page,
-						      pfrag->offset)) {
-					if (i == MAX_SKB_FRAGS || !sg) {
-						tcp_mark_push(tp, skb);
-						goto new_segment;
-					}
-					merge = false;
-				}
+			if (!sk_page_frag_refill(sk, pfrag))
+				goto wait_for_memory;
 
-				copy = min_t(int, copy, pfrag->size - pfrag->offset);
-
-				if (!sk_wmem_schedule(sk, copy))
-					goto wait_for_memory;
-
-				err = skb_copy_to_page_nocache(sk, from, skb,
-							       pfrag->page,
-							       pfrag->offset,
-							       copy);
-				if (err)
-					goto do_error;
-
-				/* Update the skb. */
-				if (merge) {
-					skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
-				} else {
-					skb_fill_page_desc(skb, i, pfrag->page,
-							   pfrag->offset, copy);
-					get_page(pfrag->page);
+			if (!skb_can_coalesce(skb, i, pfrag->page,
+					      pfrag->offset)) {
+				if (i == MAX_SKB_FRAGS || !sg) {
+					tcp_mark_push(tp, skb);
+					goto new_segment;
 				}
-				pfrag->offset += copy;
+				merge = false;
 			}
 
-			if (!copied)
-				TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
+			copy = min_t(int, copy, pfrag->size - pfrag->offset);
 
-			tp->write_seq += copy;
-			TCP_SKB_CB(skb)->end_seq += copy;
-			tcp_skb_pcount_set(skb, 0);
+			if (!sk_wmem_schedule(sk, copy))
+				goto wait_for_memory;
 
-			from += copy;
-			copied += copy;
-			if ((seglen -= copy) == 0 && iovlen == 0) {
-				tcp_tx_timestamp(sk, skb);
-				goto out;
+			err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb,
+						       pfrag->page,
+						       pfrag->offset,
+						       copy);
+			if (err)
+				goto do_error;
+
+			/* Update the skb. */
+			if (merge) {
+				skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
+			} else {
+				skb_fill_page_desc(skb, i, pfrag->page,
+						   pfrag->offset, copy);
+				get_page(pfrag->page);
 			}
+			pfrag->offset += copy;
+		}
 
-			if (skb->len < max || (flags & MSG_OOB) || unlikely(tp->repair))
-				continue;
+		if (!copied)
+			TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
 
-			if (forced_push(tp)) {
-				tcp_mark_push(tp, skb);
-				__tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_PUSH);
-			} else if (skb == tcp_send_head(sk))
-				tcp_push_one(sk, mss_now);
+		tp->write_seq += copy;
+		TCP_SKB_CB(skb)->end_seq += copy;
+		tcp_skb_pcount_set(skb, 0);
+
+		copied += copy;
+		if (!msg_data_left(msg)) {
+			tcp_tx_timestamp(sk, skb);
+			goto out;
+		}
+
+		if (skb->len < max || (flags & MSG_OOB) || unlikely(tp->repair))
 			continue;
 
+		if (forced_push(tp)) {
+			tcp_mark_push(tp, skb);
+			__tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_PUSH);
+		} else if (skb == tcp_send_head(sk))
+			tcp_push_one(sk, mss_now);
+		continue;
+
 wait_for_sndbuf:
-			set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 wait_for_memory:
-			if (copied)
-				tcp_push(sk, flags & ~MSG_MORE, mss_now,
-					 TCP_NAGLE_PUSH, size_goal);
+		if (copied)
+			tcp_push(sk, flags & ~MSG_MORE, mss_now,
+				 TCP_NAGLE_PUSH, size_goal);
 
-			if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
-				goto do_error;
+		if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
+			goto do_error;
 
-			mss_now = tcp_send_mss(sk, &size_goal, flags);
-		}
+		mss_now = tcp_send_mss(sk, &size_goal, flags);
 	}
 
 out:
@@ -1349,7 +1309,7 @@ static int tcp_recv_urg(struct sock *sk, struct msghdr *msg, int len, int flags)
 
 		if (len > 0) {
 			if (!(flags & MSG_TRUNC))
-				err = memcpy_toiovec(msg->msg_iov, &c, 1);
+				err = memcpy_to_msg(msg, &c, 1);
 			len = 1;
 		} else
 			msg->msg_flags |= MSG_TRUNC;
@@ -1377,7 +1337,7 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
 	/* XXX -- need to support SO_PEEK_OFF */
 
 	skb_queue_walk(&sk->sk_write_queue, skb) {
-		err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, skb->len);
+		err = skb_copy_datagram_msg(skb, 0, msg, skb->len);
 		if (err)
 			break;
 
@@ -1582,8 +1542,8 @@ EXPORT_SYMBOL(tcp_read_sock);
  *	Probably, code can be easily improved even more.
  */
 
-int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
-		size_t len, int nonblock, int flags, int *addr_len)
+int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
+		int flags, int *addr_len)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	int copied = 0;
@@ -1598,7 +1558,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	u32 urg_hole = 0;
 
 	if (unlikely(flags & MSG_ERRQUEUE))
-		return ip_recv_error(sk, msg, len, addr_len);
+		return inet_recv_error(sk, msg, len, addr_len);
 
 	if (sk_can_busy_loop(sk) && skb_queue_empty(&sk->sk_receive_queue) &&
 	    (sk->sk_state == TCP_ESTABLISHED))
@@ -1729,7 +1689,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 			if (!user_recv && !(flags & (MSG_TRUNC | MSG_PEEK))) {
 				user_recv = current;
 				tp->ucopy.task = user_recv;
-				tp->ucopy.iov = msg->msg_iov;
+				tp->ucopy.msg = msg;
 			}
 
 			tp->ucopy.len = len;
@@ -1833,8 +1793,7 @@ do_prequeue:
 		}
 
 		if (!(flags & MSG_TRUNC)) {
-			err = skb_copy_datagram_iovec(skb, offset,
-						      msg->msg_iov, used);
+			err = skb_copy_datagram_msg(skb, offset, msg, used);
 			if (err) {
 				/* Exception. Bailout! */
 				if (!copied)
@@ -1958,18 +1917,19 @@ EXPORT_SYMBOL_GPL(tcp_set_state);
 
 static const unsigned char new_state[16] = {
   /* current state:        new state:      action:	*/
-  /* (Invalid)		*/ TCP_CLOSE,
-  /* TCP_ESTABLISHED	*/ TCP_FIN_WAIT1 | TCP_ACTION_FIN,
-  /* TCP_SYN_SENT	*/ TCP_CLOSE,
-  /* TCP_SYN_RECV	*/ TCP_FIN_WAIT1 | TCP_ACTION_FIN,
-  /* TCP_FIN_WAIT1	*/ TCP_FIN_WAIT1,
-  /* TCP_FIN_WAIT2	*/ TCP_FIN_WAIT2,
-  /* TCP_TIME_WAIT	*/ TCP_CLOSE,
-  /* TCP_CLOSE		*/ TCP_CLOSE,
-  /* TCP_CLOSE_WAIT	*/ TCP_LAST_ACK  | TCP_ACTION_FIN,
-  /* TCP_LAST_ACK	*/ TCP_LAST_ACK,
-  /* TCP_LISTEN		*/ TCP_CLOSE,
-  /* TCP_CLOSING	*/ TCP_CLOSING,
+  [0 /* (Invalid) */]	= TCP_CLOSE,
+  [TCP_ESTABLISHED]	= TCP_FIN_WAIT1 | TCP_ACTION_FIN,
+  [TCP_SYN_SENT]	= TCP_CLOSE,
+  [TCP_SYN_RECV]	= TCP_FIN_WAIT1 | TCP_ACTION_FIN,
+  [TCP_FIN_WAIT1]	= TCP_FIN_WAIT1,
+  [TCP_FIN_WAIT2]	= TCP_FIN_WAIT2,
+  [TCP_TIME_WAIT]	= TCP_CLOSE,
+  [TCP_CLOSE]		= TCP_CLOSE,
+  [TCP_CLOSE_WAIT]	= TCP_LAST_ACK  | TCP_ACTION_FIN,
+  [TCP_LAST_ACK]	= TCP_LAST_ACK,
+  [TCP_LISTEN]		= TCP_CLOSE,
+  [TCP_CLOSING]		= TCP_CLOSING,
+  [TCP_NEW_SYN_RECV]	= TCP_CLOSE,	/* should not happen ! */
 };
 
 static int tcp_close_state(struct sock *sk)
@@ -2182,7 +2142,7 @@ adjudge_to_death:
 		 * aborted (e.g., closed with unread data) before 3WHS
 		 * finishes.
 		 */
-		if (req != NULL)
+		if (req)
 			reqsk_fastopen_remove(sk, req, false);
 		inet_csk_destroy_sock(sk);
 	}
@@ -2634,11 +2594,13 @@ EXPORT_SYMBOL(compat_tcp_setsockopt);
 #endif
 
 /* Return information about state of tcp endpoint in API format. */
-void tcp_get_info(const struct sock *sk, struct tcp_info *info)
+void tcp_get_info(struct sock *sk, struct tcp_info *info)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	u32 now = tcp_time_stamp;
+	unsigned int start;
+	u32 rate;
 
 	memset(info, 0, sizeof(*info));
 
@@ -2699,10 +2661,17 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info)
 
 	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;
+	rate = READ_ONCE(sk->sk_pacing_rate);
+	info->tcpi_pacing_rate = rate != ~0U ? rate : ~0ULL;
+
+	rate = READ_ONCE(sk->sk_max_pacing_rate);
+	info->tcpi_max_pacing_rate = rate != ~0U ? rate : ~0ULL;
+
+	do {
+		start = u64_stats_fetch_begin_irq(&tp->syncp);
+		info->tcpi_bytes_acked = tp->bytes_acked;
+		info->tcpi_bytes_received = tp->bytes_received;
+	} while (u64_stats_fetch_retry_irq(&tp->syncp, start));
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);
 
@@ -2774,6 +2743,26 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 			return -EFAULT;
 		return 0;
 	}
+	case TCP_CC_INFO: {
+		const struct tcp_congestion_ops *ca_ops;
+		union tcp_cc_info info;
+		size_t sz = 0;
+		int attr;
+
+		if (get_user(len, optlen))
+			return -EFAULT;
+
+		ca_ops = icsk->icsk_ca_ops;
+		if (ca_ops && ca_ops->get_info)
+			sz = ca_ops->get_info(sk, ~0U, &attr, &info);
+
+		len = min_t(unsigned int, len, sz);
+		if (put_user(len, optlen))
+			return -EFAULT;
+		if (copy_to_user(optval, &info, len))
+			return -EFAULT;
+		return 0;
+	}
 	case TCP_QUICKACK:
 		val = !icsk->icsk_ack.pingpong;
 		break;
@@ -2820,7 +2809,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		break;
 
 	case TCP_FASTOPEN:
-		if (icsk->icsk_accept_queue.fastopenq != NULL)
+		if (icsk->icsk_accept_queue.fastopenq)
 			val = icsk->icsk_accept_queue.fastopenq->max_qlen;
 		else
 			val = 0;
@@ -3004,7 +2993,7 @@ void tcp_done(struct sock *sk)
 
 	tcp_set_state(sk, TCP_CLOSE);
 	tcp_clear_xmit_timers(sk);
-	if (req != NULL)
+	if (req)
 		reqsk_fastopen_remove(sk, req, false);
 
 	sk->sk_shutdown = SHUTDOWN_MASK;
@@ -3045,12 +3034,11 @@ static void __init tcp_init_mem(void)
 
 void __init tcp_init(void)
 {
-	struct sk_buff *skb = NULL;
 	unsigned long limit;
 	int max_rshare, max_wshare, cnt;
 	unsigned int i;
 
-	BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb));
+	sock_skb_cb_check_size(sizeof(struct tcp_skb_cb));
 
 	percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL);
 	percpu_counter_init(&tcp_orphan_count, 0, GFP_KERNEL);
diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c
index bb395d46a389..c037644eafb7 100644
--- a/net/ipv4/tcp_bic.c
+++ b/net/ipv4/tcp_bic.c
@@ -150,7 +150,7 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 		tcp_slow_start(tp, acked);
 	else {
 		bictcp_update(ca, tp->snd_cwnd);
-		tcp_cong_avoid_ai(tp, ca->cnt);
+		tcp_cong_avoid_ai(tp, ca->cnt, 1);
 	}
 }
 
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index b1c5970d47a1..84be008c945c 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -1,5 +1,5 @@
 /*
- * Plugable TCP congestion control support and newReno
+ * Pluggable TCP congestion control support and newReno
  * congestion control.
  * Based on ideas from I/O scheduler support and Web100.
  *
@@ -13,6 +13,7 @@
 #include <linux/types.h>
 #include <linux/list.h>
 #include <linux/gfp.h>
+#include <linux/jhash.h>
 #include <net/tcp.h>
 
 static DEFINE_SPINLOCK(tcp_cong_list_lock);
@@ -31,6 +32,34 @@ static struct tcp_congestion_ops *tcp_ca_find(const char *name)
 	return NULL;
 }
 
+/* Must be called with rcu lock held */
+static const struct tcp_congestion_ops *__tcp_ca_find_autoload(const char *name)
+{
+	const struct tcp_congestion_ops *ca = tcp_ca_find(name);
+#ifdef CONFIG_MODULES
+	if (!ca && capable(CAP_NET_ADMIN)) {
+		rcu_read_unlock();
+		request_module("tcp_%s", name);
+		rcu_read_lock();
+		ca = tcp_ca_find(name);
+	}
+#endif
+	return ca;
+}
+
+/* Simple linear search, not much in here. */
+struct tcp_congestion_ops *tcp_ca_find_key(u32 key)
+{
+	struct tcp_congestion_ops *e;
+
+	list_for_each_entry_rcu(e, &tcp_cong_list, list) {
+		if (e->key == key)
+			return e;
+	}
+
+	return NULL;
+}
+
 /*
  * Attach new congestion control algorithm to the list
  * of available options.
@@ -45,13 +74,16 @@ int tcp_register_congestion_control(struct tcp_congestion_ops *ca)
 		return -EINVAL;
 	}
 
+	ca->key = jhash(ca->name, sizeof(ca->name), strlen(ca->name));
+
 	spin_lock(&tcp_cong_list_lock);
-	if (tcp_ca_find(ca->name)) {
-		pr_notice("%s already registered\n", ca->name);
+	if (ca->key == TCP_CA_UNSPEC || tcp_ca_find_key(ca->key)) {
+		pr_notice("%s already registered or non-unique key\n",
+			  ca->name);
 		ret = -EEXIST;
 	} else {
 		list_add_tail_rcu(&ca->list, &tcp_cong_list);
-		pr_info("%s registered\n", ca->name);
+		pr_debug("%s registered\n", ca->name);
 	}
 	spin_unlock(&tcp_cong_list_lock);
 
@@ -70,9 +102,50 @@ void tcp_unregister_congestion_control(struct tcp_congestion_ops *ca)
 	spin_lock(&tcp_cong_list_lock);
 	list_del_rcu(&ca->list);
 	spin_unlock(&tcp_cong_list_lock);
+
+	/* Wait for outstanding readers to complete before the
+	 * module gets removed entirely.
+	 *
+	 * A try_module_get() should fail by now as our module is
+	 * in "going" state since no refs are held anymore and
+	 * module_exit() handler being called.
+	 */
+	synchronize_rcu();
 }
 EXPORT_SYMBOL_GPL(tcp_unregister_congestion_control);
 
+u32 tcp_ca_get_key_by_name(const char *name)
+{
+	const struct tcp_congestion_ops *ca;
+	u32 key;
+
+	might_sleep();
+
+	rcu_read_lock();
+	ca = __tcp_ca_find_autoload(name);
+	key = ca ? ca->key : TCP_CA_UNSPEC;
+	rcu_read_unlock();
+
+	return key;
+}
+EXPORT_SYMBOL_GPL(tcp_ca_get_key_by_name);
+
+char *tcp_ca_get_name_by_key(u32 key, char *buffer)
+{
+	const struct tcp_congestion_ops *ca;
+	char *ret = NULL;
+
+	rcu_read_lock();
+	ca = tcp_ca_find_key(key);
+	if (ca)
+		ret = strncpy(buffer, ca->name,
+			      TCP_CA_NAME_MAX);
+	rcu_read_unlock();
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(tcp_ca_get_name_by_key);
+
 /* Assign choice of congestion control. */
 void tcp_assign_congestion_control(struct sock *sk)
 {
@@ -107,6 +180,19 @@ void tcp_init_congestion_control(struct sock *sk)
 		icsk->icsk_ca_ops->init(sk);
 }
 
+static void tcp_reinit_congestion_control(struct sock *sk,
+					  const struct tcp_congestion_ops *ca)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+
+	tcp_cleanup_congestion_control(sk);
+	icsk->icsk_ca_ops = ca;
+	icsk->icsk_ca_setsockopt = 1;
+
+	if (sk->sk_state != TCP_CLOSE && icsk->icsk_ca_ops->init)
+		icsk->icsk_ca_ops->init(sk);
+}
+
 /* Manage refcounts on socket close. */
 void tcp_cleanup_congestion_control(struct sock *sk)
 {
@@ -241,42 +327,28 @@ out:
 int tcp_set_congestion_control(struct sock *sk, const char *name)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
-	struct tcp_congestion_ops *ca;
+	const struct tcp_congestion_ops *ca;
 	int err = 0;
 
-	rcu_read_lock();
-	ca = tcp_ca_find(name);
+	if (icsk->icsk_ca_dst_locked)
+		return -EPERM;
 
-	/* no change asking for existing value */
-	if (ca == icsk->icsk_ca_ops)
+	rcu_read_lock();
+	ca = __tcp_ca_find_autoload(name);
+	/* No change asking for existing value */
+	if (ca == icsk->icsk_ca_ops) {
+		icsk->icsk_ca_setsockopt = 1;
 		goto out;
-
-#ifdef CONFIG_MODULES
-	/* not found attempt to autoload module */
-	if (!ca && capable(CAP_NET_ADMIN)) {
-		rcu_read_unlock();
-		request_module("tcp_%s", name);
-		rcu_read_lock();
-		ca = tcp_ca_find(name);
 	}
-#endif
 	if (!ca)
 		err = -ENOENT;
-
 	else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) ||
 		   ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)))
 		err = -EPERM;
-
 	else if (!try_module_get(ca->owner))
 		err = -EBUSY;
-
-	else {
-		tcp_cleanup_congestion_control(sk);
-		icsk->icsk_ca_ops = ca;
-
-		if (sk->sk_state != TCP_CLOSE && icsk->icsk_ca_ops->init)
-			icsk->icsk_ca_ops->init(sk);
-	}
+	else
+		tcp_reinit_congestion_control(sk, ca);
  out:
 	rcu_read_unlock();
 	return err;
@@ -291,26 +363,38 @@ int tcp_set_congestion_control(struct sock *sk, const char *name)
  * ABC caps N to 2. Slow start exits when cwnd grows over ssthresh and
  * returns the leftover acks to adjust cwnd in congestion avoidance mode.
  */
-void tcp_slow_start(struct tcp_sock *tp, u32 acked)
+u32 tcp_slow_start(struct tcp_sock *tp, u32 acked)
 {
 	u32 cwnd = tp->snd_cwnd + acked;
 
 	if (cwnd > tp->snd_ssthresh)
 		cwnd = tp->snd_ssthresh + 1;
+	acked -= cwnd - tp->snd_cwnd;
 	tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp);
+
+	return acked;
 }
 EXPORT_SYMBOL_GPL(tcp_slow_start);
 
-/* In theory this is tp->snd_cwnd += 1 / tp->snd_cwnd (or alternative w) */
-void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w)
+/* In theory this is tp->snd_cwnd += 1 / tp->snd_cwnd (or alternative w),
+ * for every packet that was ACKed.
+ */
+void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked)
 {
+	/* If credits accumulated at a higher w, apply them gently now. */
 	if (tp->snd_cwnd_cnt >= w) {
-		if (tp->snd_cwnd < tp->snd_cwnd_clamp)
-			tp->snd_cwnd++;
 		tp->snd_cwnd_cnt = 0;
-	} else {
-		tp->snd_cwnd_cnt++;
+		tp->snd_cwnd++;
 	}
+
+	tp->snd_cwnd_cnt += acked;
+	if (tp->snd_cwnd_cnt >= w) {
+		u32 delta = tp->snd_cwnd_cnt / w;
+
+		tp->snd_cwnd_cnt -= delta * w;
+		tp->snd_cwnd += delta;
+	}
+	tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_cwnd_clamp);
 }
 EXPORT_SYMBOL_GPL(tcp_cong_avoid_ai);
 
@@ -329,11 +413,13 @@ void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 		return;
 
 	/* In "safe" area, increase. */
-	if (tp->snd_cwnd <= tp->snd_ssthresh)
-		tcp_slow_start(tp, acked);
+	if (tp->snd_cwnd <= tp->snd_ssthresh) {
+		acked = tcp_slow_start(tp, acked);
+		if (!acked)
+			return;
+	}
 	/* In dangerous area, increase slowly. */
-	else
-		tcp_cong_avoid_ai(tp, tp->snd_cwnd);
+	tcp_cong_avoid_ai(tp, tp->snd_cwnd, acked);
 }
 EXPORT_SYMBOL_GPL(tcp_reno_cong_avoid);
 
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 20de0118c98e..06d3d665a9fd 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -93,9 +93,7 @@ struct bictcp {
 	u32	epoch_start;	/* beginning of an epoch */
 	u32	ack_cnt;	/* number of acks */
 	u32	tcp_cwnd;	/* estimated tcp cwnd */
-#define ACK_RATIO_SHIFT	4
-#define ACK_RATIO_LIMIT (32u << ACK_RATIO_SHIFT)
-	u16	delayed_ack;	/* estimate the ratio of Packets/ACKs << 4 */
+	u16	unused;
 	u8	sample_cnt;	/* number of samples to decide curr_rtt */
 	u8	found;		/* the exit point is found? */
 	u32	round_start;	/* beginning of each round */
@@ -114,7 +112,6 @@ static inline void bictcp_reset(struct bictcp *ca)
 	ca->bic_K = 0;
 	ca->delay_min = 0;
 	ca->epoch_start = 0;
-	ca->delayed_ack = 2 << ACK_RATIO_SHIFT;
 	ca->ack_cnt = 0;
 	ca->tcp_cwnd = 0;
 	ca->found = 0;
@@ -205,23 +202,30 @@ static u32 cubic_root(u64 a)
 /*
  * Compute congestion window to use.
  */
-static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
+static inline void bictcp_update(struct bictcp *ca, u32 cwnd, u32 acked)
 {
 	u32 delta, bic_target, max_cnt;
 	u64 offs, t;
 
-	ca->ack_cnt++;	/* count the number of ACKs */
+	ca->ack_cnt += acked;	/* count the number of ACKed packets */
 
 	if (ca->last_cwnd == cwnd &&
 	    (s32)(tcp_time_stamp - ca->last_time) <= HZ / 32)
 		return;
 
+	/* The CUBIC function can update ca->cnt at most once per jiffy.
+	 * On all cwnd reduction events, ca->epoch_start is set to 0,
+	 * which will force a recalculation of ca->cnt.
+	 */
+	if (ca->epoch_start && tcp_time_stamp == ca->last_time)
+		goto tcp_friendliness;
+
 	ca->last_cwnd = cwnd;
 	ca->last_time = tcp_time_stamp;
 
 	if (ca->epoch_start == 0) {
 		ca->epoch_start = tcp_time_stamp;	/* record beginning */
-		ca->ack_cnt = 1;			/* start counting */
+		ca->ack_cnt = acked;			/* start counting */
 		ca->tcp_cwnd = cwnd;			/* syn with cubic */
 
 		if (ca->last_max_cwnd <= cwnd) {
@@ -283,6 +287,7 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
 	if (ca->last_max_cwnd == 0 && ca->cnt > 20)
 		ca->cnt = 20;	/* increase cwnd 5% per RTT */
 
+tcp_friendliness:
 	/* TCP Friendly */
 	if (tcp_friendliness) {
 		u32 scale = beta_scale;
@@ -301,9 +306,10 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
 		}
 	}
 
-	ca->cnt = (ca->cnt << ACK_RATIO_SHIFT) / ca->delayed_ack;
-	if (ca->cnt == 0)			/* cannot be zero */
-		ca->cnt = 1;
+	/* The maximum rate of cwnd increase CUBIC allows is 1 packet per
+	 * 2 packets ACKed, meaning cwnd grows at 1.5x per RTT.
+	 */
+	ca->cnt = max(ca->cnt, 2U);
 }
 
 static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
@@ -317,11 +323,12 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 	if (tp->snd_cwnd <= tp->snd_ssthresh) {
 		if (hystart && after(ack, ca->end_seq))
 			bictcp_hystart_reset(sk);
-		tcp_slow_start(tp, acked);
-	} else {
-		bictcp_update(ca, tp->snd_cwnd);
-		tcp_cong_avoid_ai(tp, ca->cnt);
+		acked = tcp_slow_start(tp, acked);
+		if (!acked)
+			return;
 	}
+	bictcp_update(ca, tp->snd_cwnd, acked);
+	tcp_cong_avoid_ai(tp, ca->cnt, acked);
 }
 
 static u32 bictcp_recalc_ssthresh(struct sock *sk)
@@ -363,16 +370,28 @@ static void hystart_update(struct sock *sk, u32 delay)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct bictcp *ca = inet_csk_ca(sk);
 
-	if (!(ca->found & hystart_detect)) {
+	if (ca->found & hystart_detect)
+		return;
+
+	if (hystart_detect & HYSTART_ACK_TRAIN) {
 		u32 now = bictcp_clock();
 
 		/* first detection parameter - ack-train detection */
 		if ((s32)(now - ca->last_ack) <= hystart_ack_delta) {
 			ca->last_ack = now;
-			if ((s32)(now - ca->round_start) > ca->delay_min >> 4)
+			if ((s32)(now - ca->round_start) > ca->delay_min >> 4) {
 				ca->found |= HYSTART_ACK_TRAIN;
+				NET_INC_STATS_BH(sock_net(sk),
+						 LINUX_MIB_TCPHYSTARTTRAINDETECT);
+				NET_ADD_STATS_BH(sock_net(sk),
+						 LINUX_MIB_TCPHYSTARTTRAINCWND,
+						 tp->snd_cwnd);
+				tp->snd_ssthresh = tp->snd_cwnd;
+			}
 		}
+	}
 
+	if (hystart_detect & HYSTART_DELAY) {
 		/* obtain the minimum delay of more than sampling packets */
 		if (ca->sample_cnt < HYSTART_MIN_SAMPLES) {
 			if (ca->curr_rtt == 0 || ca->curr_rtt > delay)
@@ -381,15 +400,16 @@ static void hystart_update(struct sock *sk, u32 delay)
 			ca->sample_cnt++;
 		} else {
 			if (ca->curr_rtt > ca->delay_min +
-			    HYSTART_DELAY_THRESH(ca->delay_min>>4))
+			    HYSTART_DELAY_THRESH(ca->delay_min >> 3)) {
 				ca->found |= HYSTART_DELAY;
+				NET_INC_STATS_BH(sock_net(sk),
+						 LINUX_MIB_TCPHYSTARTDELAYDETECT);
+				NET_ADD_STATS_BH(sock_net(sk),
+						 LINUX_MIB_TCPHYSTARTDELAYCWND,
+						 tp->snd_cwnd);
+				tp->snd_ssthresh = tp->snd_cwnd;
+			}
 		}
-		/*
-		 * Either one of two conditions are met,
-		 * we exit from slow start immediately.
-		 */
-		if (ca->found & hystart_detect)
-			tp->snd_ssthresh = tp->snd_cwnd;
 	}
 }
 
@@ -398,20 +418,10 @@ static void hystart_update(struct sock *sk, u32 delay)
  */
 static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us)
 {
-	const struct inet_connection_sock *icsk = inet_csk(sk);
 	const struct tcp_sock *tp = tcp_sk(sk);
 	struct bictcp *ca = inet_csk_ca(sk);
 	u32 delay;
 
-	if (icsk->icsk_ca_state == TCP_CA_Open) {
-		u32 ratio = ca->delayed_ack;
-
-		ratio -= ca->delayed_ack >> ACK_RATIO_SHIFT;
-		ratio += cnt;
-
-		ca->delayed_ack = clamp(ratio, 1U, ACK_RATIO_LIMIT);
-	}
-
 	/* Some calls are for duplicates without timetamps */
 	if (rtt_us < 0)
 		return;
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index b504371af742..4c41c1287197 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -277,7 +277,8 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
 	}
 }
 
-static void dctcp_get_info(struct sock *sk, u32 ext, struct sk_buff *skb)
+static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr,
+			     union tcp_cc_info *info)
 {
 	const struct dctcp *ca = inet_csk_ca(sk);
 
@@ -286,19 +287,19 @@ static void dctcp_get_info(struct sock *sk, u32 ext, struct sk_buff *skb)
 	 */
 	if (ext & (1 << (INET_DIAG_DCTCPINFO - 1)) ||
 	    ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
-		struct tcp_dctcp_info info;
-
-		memset(&info, 0, sizeof(info));
+		memset(info, 0, sizeof(struct tcp_dctcp_info));
 		if (inet_csk(sk)->icsk_ca_ops != &dctcp_reno) {
-			info.dctcp_enabled = 1;
-			info.dctcp_ce_state = (u16) ca->ce_state;
-			info.dctcp_alpha = ca->dctcp_alpha;
-			info.dctcp_ab_ecn = ca->acked_bytes_ecn;
-			info.dctcp_ab_tot = ca->acked_bytes_total;
+			info->dctcp.dctcp_enabled = 1;
+			info->dctcp.dctcp_ce_state = (u16) ca->ce_state;
+			info->dctcp.dctcp_alpha = ca->dctcp_alpha;
+			info->dctcp.dctcp_ab_ecn = ca->acked_bytes_ecn;
+			info->dctcp.dctcp_ab_tot = ca->acked_bytes_total;
 		}
 
-		nla_put(skb, INET_DIAG_DCTCPINFO, sizeof(info), &info);
+		*attr = INET_DIAG_DCTCPINFO;
+		return sizeof(*info);
 	}
+	return 0;
 }
 
 static struct tcp_congestion_ops dctcp __read_mostly = {
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index 0d73f9ddb55b..79b34a0f4a4a 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -29,18 +29,18 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
 		r->idiag_rqueue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0);
 		r->idiag_wqueue = tp->write_seq - tp->snd_una;
 	}
-	if (info != NULL)
+	if (info)
 		tcp_get_info(sk, info);
 }
 
 static void tcp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
-			  struct inet_diag_req_v2 *r, struct nlattr *bc)
+			  const struct inet_diag_req_v2 *r, struct nlattr *bc)
 {
 	inet_diag_dump_icsk(&tcp_hashinfo, skb, cb, r, bc);
 }
 
 static int tcp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh,
-			     struct inet_diag_req_v2 *req)
+			     const struct inet_diag_req_v2 *req)
 {
 	return inet_diag_dump_one_icsk(&tcp_hashinfo, in_skb, nlh, req);
 }
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 815c85e3b1e0..46b087a27503 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -134,13 +134,14 @@ static bool tcp_fastopen_create_child(struct sock *sk,
 	struct tcp_sock *tp;
 	struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
 	struct sock *child;
+	u32 end_seq;
 
 	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)
+	if (!child)
 		return false;
 
 	spin_lock(&queue->fastopenq->lock);
@@ -154,12 +155,7 @@ static bool tcp_fastopen_create_child(struct sock *sk,
 	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;
+	tcp_rsk(req)->tfo_listener = true;
 
 	/* RFC1323: The window in SYN & SYN/ACK segments is never
 	 * scaled. So correct it appropriately.
@@ -173,6 +169,7 @@ static bool tcp_fastopen_create_child(struct sock *sk,
 	inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS,
 				  TCP_TIMEOUT_INIT, TCP_RTO_MAX);
 
+	atomic_set(&req->rsk_refcnt, 1);
 	/* Add the child socket directly into the accept queue */
 	inet_csk_reqsk_queue_add(sk, req, child);
 
@@ -185,27 +182,46 @@ static bool tcp_fastopen_create_child(struct sock *sk,
 
 	/* Queue the data carried in the SYN packet. We need to first
 	 * bump skb's refcnt because the caller will attempt to free it.
+	 * Note that IPv6 might also have used skb_get() trick
+	 * in tcp_v6_conn_request() to keep this SYN around (treq->pktopts)
+	 * So we need to eventually get a clone of the packet,
+	 * before inserting it in sk_receive_queue.
 	 *
 	 * 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;
+	end_seq = TCP_SKB_CB(skb)->end_seq;
+	if (end_seq != TCP_SKB_CB(skb)->seq + 1) {
+		struct sk_buff *skb2;
+
+		if (unlikely(skb_shared(skb)))
+			skb2 = skb_clone(skb, GFP_ATOMIC);
+		else
+			skb2 = skb_get(skb);
+
+		if (likely(skb2)) {
+			skb_dst_drop(skb2);
+			__skb_pull(skb2, tcp_hdrlen(skb));
+			skb_set_owner_r(skb2, child);
+			__skb_queue_tail(&child->sk_receive_queue, skb2);
+			tp->syn_data_acked = 1;
+
+			/* u64_stats_update_begin(&tp->syncp) not needed here,
+			 * as we certainly are not changing upper 32bit value (0)
+			 */
+			tp->bytes_received = end_seq - TCP_SKB_CB(skb)->seq - 1;
+		} else {
+			end_seq = TCP_SKB_CB(skb)->seq + 1;
+		}
 	}
-	tcp_rsk(req)->rcv_nxt = tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+	tcp_rsk(req)->rcv_nxt = tp->rcv_nxt = end_seq;
 	sk->sk_data_ready(sk);
 	bh_unlock_sock(child);
 	sock_put(child);
-	WARN_ON(req->sk == NULL);
+	WARN_ON(!req->sk);
 	return true;
 }
-EXPORT_SYMBOL(tcp_fastopen_create_child);
 
 static bool tcp_fastopen_queue_check(struct sock *sk)
 {
@@ -222,14 +238,14 @@ static bool tcp_fastopen_queue_check(struct sock *sk)
 	 * 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)
+	if (!fastopenq || 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)) {
+		if (!req1 || time_after(req1->rsk_timer.expires, jiffies)) {
 			spin_unlock(&fastopenq->lock);
 			NET_INC_STATS_BH(sock_net(sk),
 					 LINUX_MIB_TCPFASTOPENLISTENOVERFLOW);
@@ -238,7 +254,7 @@ static bool tcp_fastopen_queue_check(struct sock *sk)
 		fastopenq->rskq_rst_head = req1->dl_next;
 		fastopenq->qlen--;
 		spin_unlock(&fastopenq->lock);
-		reqsk_free(req1);
+		reqsk_put(req1);
 	}
 	return true;
 }
@@ -255,6 +271,9 @@ bool tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
 	struct tcp_fastopen_cookie valid_foc = { .len = -1 };
 	bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1;
 
+	if (foc->len == 0) /* Client requests a cookie */
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENCOOKIEREQD);
+
 	if (!((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) &&
 	      (syn_data || foc->len >= 0) &&
 	      tcp_fastopen_queue_check(sk))) {
@@ -265,7 +284,8 @@ bool tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
 	if (syn_data && (sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD))
 		goto fastopen;
 
-	if (tcp_fastopen_cookie_gen(req, skb, &valid_foc) &&
+	if (foc->len >= 0 &&  /* Client presents or requests a cookie */
+	    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)) {
@@ -284,11 +304,11 @@ fastopen:
 					 LINUX_MIB_TCPFASTOPENPASSIVE);
 			return true;
 		}
-	}
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVEFAIL);
+	} else if (foc->len > 0) /* Client presents an invalid cookie */
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVEFAIL);
 
-	NET_INC_STATS_BH(sock_net(sk), foc->len ?
-			 LINUX_MIB_TCPFASTOPENPASSIVEFAIL :
-			 LINUX_MIB_TCPFASTOPENCOOKIEREQD);
+	valid_foc.exp = foc->exp;
 	*foc = valid_foc;
 	return false;
 }
diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c
index 1d5a30a90adf..f71002e4db0b 100644
--- a/net/ipv4/tcp_illinois.c
+++ b/net/ipv4/tcp_illinois.c
@@ -300,26 +300,27 @@ static u32 tcp_illinois_ssthresh(struct sock *sk)
 }
 
 /* Extract info for Tcp socket info provided via netlink. */
-static void tcp_illinois_info(struct sock *sk, u32 ext,
-			      struct sk_buff *skb)
+static size_t tcp_illinois_info(struct sock *sk, u32 ext, int *attr,
+				union tcp_cc_info *info)
 {
 	const struct illinois *ca = inet_csk_ca(sk);
 
 	if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
-		struct tcpvegas_info info = {
-			.tcpv_enabled = 1,
-			.tcpv_rttcnt = ca->cnt_rtt,
-			.tcpv_minrtt = ca->base_rtt,
-		};
+		info->vegas.tcpv_enabled = 1;
+		info->vegas.tcpv_rttcnt = ca->cnt_rtt;
+		info->vegas.tcpv_minrtt = ca->base_rtt;
+		info->vegas.tcpv_rtt = 0;
 
-		if (info.tcpv_rttcnt > 0) {
+		if (info->vegas.tcpv_rttcnt > 0) {
 			u64 t = ca->sum_rtt;
 
-			do_div(t, info.tcpv_rttcnt);
-			info.tcpv_rtt = t;
+			do_div(t, info->vegas.tcpv_rttcnt);
+			info->vegas.tcpv_rtt = t;
 		}
-		nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info);
+		*attr = INET_DIAG_VEGASINFO;
+		return sizeof(struct tcpvegas_info);
 	}
+	return 0;
 }
 
 static struct tcp_congestion_ops tcp_illinois __read_mostly = {
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 88fa2d160685..c9ab964189a0 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -81,6 +81,7 @@ int sysctl_tcp_window_scaling __read_mostly = 1;
 int sysctl_tcp_sack __read_mostly = 1;
 int sysctl_tcp_fack __read_mostly = 1;
 int sysctl_tcp_reordering __read_mostly = TCP_FASTRETRANS_THRESH;
+int sysctl_tcp_max_reordering __read_mostly = 300;
 EXPORT_SYMBOL(sysctl_tcp_reordering);
 int sysctl_tcp_dsack __read_mostly = 1;
 int sysctl_tcp_app_win __read_mostly = 31;
@@ -99,6 +100,7 @@ int sysctl_tcp_thin_dupack __read_mostly;
 
 int sysctl_tcp_moderate_rcvbuf __read_mostly = 1;
 int sysctl_tcp_early_retrans __read_mostly = 3;
+int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2;
 
 #define FLAG_DATA		0x01 /* Incoming frame contained data.		*/
 #define FLAG_WIN_UPDATE		0x02 /* Incoming ACK was a window update.	*/
@@ -833,7 +835,7 @@ static void tcp_update_reordering(struct sock *sk, const int metric,
 	if (metric > tp->reordering) {
 		int mib_idx;
 
-		tp->reordering = min(TCP_MAX_REORDERING, metric);
+		tp->reordering = min(sysctl_tcp_max_reordering, metric);
 
 		/* This exciting event is worth to be remembered. 8) */
 		if (ts)
@@ -864,7 +866,7 @@ static void tcp_update_reordering(struct sock *sk, const int metric,
 /* This must be called before lost_out is incremented */
 static void tcp_verify_retransmit_hint(struct tcp_sock *tp, struct sk_buff *skb)
 {
-	if ((tp->retransmit_skb_hint == NULL) ||
+	if (!tp->retransmit_skb_hint ||
 	    before(TCP_SKB_CB(skb)->seq,
 		   TCP_SKB_CB(tp->retransmit_skb_hint)->seq))
 		tp->retransmit_skb_hint = skb;
@@ -1254,7 +1256,7 @@ static u8 tcp_sacktag_one(struct sock *sk,
 		fack_count += pcount;
 
 		/* Lost marker hint past SACKed? Tweak RFC3517 cnt */
-		if (!tcp_is_fack(tp) && (tp->lost_skb_hint != NULL) &&
+		if (!tcp_is_fack(tp) && tp->lost_skb_hint &&
 		    before(start_seq, TCP_SKB_CB(tp->lost_skb_hint)->seq))
 			tp->lost_cnt_hint += pcount;
 
@@ -1533,7 +1535,7 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk,
 		if (!before(TCP_SKB_CB(skb)->seq, end_seq))
 			break;
 
-		if ((next_dup != NULL) &&
+		if (next_dup  &&
 		    before(TCP_SKB_CB(skb)->seq, next_dup->end_seq)) {
 			in_sack = tcp_match_skb_to_sack(sk, skb,
 							next_dup->start_seq,
@@ -1549,7 +1551,7 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk,
 		if (in_sack <= 0) {
 			tmp = tcp_shift_skb_data(sk, skb, state,
 						 start_seq, end_seq, dup_sack);
-			if (tmp != NULL) {
+			if (tmp) {
 				if (tmp != skb) {
 					skb = tmp;
 					continue;
@@ -1612,7 +1614,7 @@ static struct sk_buff *tcp_maybe_skipping_dsack(struct sk_buff *skb,
 						struct tcp_sacktag_state *state,
 						u32 skip_to_seq)
 {
-	if (next_dup == NULL)
+	if (!next_dup)
 		return skb;
 
 	if (before(next_dup->start_seq, skip_to_seq)) {
@@ -1781,7 +1783,7 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
 			if (tcp_highest_sack_seq(tp) == cache->end_seq) {
 				/* ...but better entrypoint exists! */
 				skb = tcp_highest_sack(sk);
-				if (skb == NULL)
+				if (!skb)
 					break;
 				state.fack_count = tp->fackets_out;
 				cache++;
@@ -1796,7 +1798,7 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
 
 		if (!before(start_seq, tcp_highest_sack_seq(tp))) {
 			skb = tcp_highest_sack(sk);
-			if (skb == NULL)
+			if (!skb)
 				break;
 			state.fack_count = tp->fackets_out;
 		}
@@ -1818,14 +1820,12 @@ advance_sp:
 	for (j = 0; j < used_sacks; j++)
 		tp->recv_sack_cache[i++] = sp[j];
 
-	tcp_mark_lost_retrans(sk);
-
-	tcp_verify_left_out(tp);
-
 	if ((state.reord < tp->fackets_out) &&
 	    ((inet_csk(sk)->icsk_ca_state != TCP_CA_Loss) || tp->undo_marker))
 		tcp_update_reordering(sk, tp->fackets_out - state.reord, 0);
 
+	tcp_mark_lost_retrans(sk);
+	tcp_verify_left_out(tp);
 out:
 
 #if FASTRETRANS_DEBUG > 0
@@ -2698,16 +2698,21 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack)
 	struct tcp_sock *tp = tcp_sk(sk);
 	bool recovered = !before(tp->snd_una, tp->high_seq);
 
+	if ((flag & FLAG_SND_UNA_ADVANCED) &&
+	    tcp_try_undo_loss(sk, false))
+		return;
+
 	if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */
 		/* 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))
+		if ((flag & FLAG_ORIG_SACK_ACKED) &&
+		    tcp_try_undo_loss(sk, true))
 			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 */
+		if (after(tp->snd_nxt, tp->high_seq)) {
+			if (flag & FLAG_DATA_SACKED || is_dupack)
+				tp->frto = 0; /* Step 3.a. loss was real */
 		} else if (flag & FLAG_SND_UNA_ADVANCED && !recovered) {
 			tp->high_seq = tp->snd_nxt;
 			__tcp_push_pending_frames(sk, tcp_current_mss(sk),
@@ -2732,8 +2737,6 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack)
 		else if (flag & FLAG_SND_UNA_ADVANCED)
 			tcp_reset_reno_sack(tp);
 	}
-	if (tcp_try_undo_loss(sk, false))
-		return;
 	tcp_xmit_retransmit_queue(sk);
 }
 
@@ -3097,14 +3100,13 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 			if (sacked & TCPCB_SACKED_RETRANS)
 				tp->retrans_out -= acked_pcount;
 			flag |= FLAG_RETRANS_DATA_ACKED;
-		} else {
+		} else if (!(sacked & TCPCB_SACKED_ACKED)) {
 			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);
+			reord = min(pkts_acked, reord);
 			if (!after(scb->end_seq, tp->high_seq))
 				flag |= FLAG_ORIG_SACK_ACKED;
 		}
@@ -3182,8 +3184,10 @@ 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)
-			ca_ops->pkts_acked(sk, pkts_acked, ca_seq_rtt_us);
+		if (ca_ops->pkts_acked) {
+			long rtt_us = min_t(ulong, ca_seq_rtt_us, sack_rtt_us);
+			ca_ops->pkts_acked(sk, pkts_acked, rtt_us);
+		}
 
 	} else if (skb && rtt_update && sack_rtt_us >= 0 &&
 		   sack_rtt_us > skb_mstamp_us_delta(&now, &skb->skb_mstamp)) {
@@ -3277,6 +3281,28 @@ static inline bool tcp_may_update_window(const struct tcp_sock *tp,
 		(ack_seq == tp->snd_wl1 && nwin > tp->snd_wnd);
 }
 
+/* If we update tp->snd_una, also update tp->bytes_acked */
+static void tcp_snd_una_update(struct tcp_sock *tp, u32 ack)
+{
+	u32 delta = ack - tp->snd_una;
+
+	u64_stats_update_begin(&tp->syncp);
+	tp->bytes_acked += delta;
+	u64_stats_update_end(&tp->syncp);
+	tp->snd_una = ack;
+}
+
+/* If we update tp->rcv_nxt, also update tp->bytes_received */
+static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq)
+{
+	u32 delta = seq - tp->rcv_nxt;
+
+	u64_stats_update_begin(&tp->syncp);
+	tp->bytes_received += delta;
+	u64_stats_update_end(&tp->syncp);
+	tp->rcv_nxt = seq;
+}
+
 /* Update our send window.
  *
  * Window update algorithm, described in RFC793/RFC1122 (used in linux-2.2
@@ -3312,19 +3338,58 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32
 		}
 	}
 
-	tp->snd_una = ack;
+	tcp_snd_una_update(tp, ack);
 
 	return flag;
 }
 
+/* Return true if we're currently rate-limiting out-of-window ACKs and
+ * thus shouldn't send a dupack right now. We rate-limit dupacks in
+ * response to out-of-window SYNs or ACKs to mitigate ACK loops or DoS
+ * attacks that send repeated SYNs or ACKs for the same connection. To
+ * do this, we do not send a duplicate SYNACK or ACK if the remote
+ * endpoint is sending out-of-window SYNs or pure ACKs at a high rate.
+ */
+bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb,
+			  int mib_idx, u32 *last_oow_ack_time)
+{
+	/* Data packets without SYNs are not likely part of an ACK loop. */
+	if ((TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) &&
+	    !tcp_hdr(skb)->syn)
+		goto not_rate_limited;
+
+	if (*last_oow_ack_time) {
+		s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time);
+
+		if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) {
+			NET_INC_STATS_BH(net, mib_idx);
+			return true;	/* rate-limited: don't send yet! */
+		}
+	}
+
+	*last_oow_ack_time = tcp_time_stamp;
+
+not_rate_limited:
+	return false;	/* not rate-limited: go ahead, send dupack now! */
+}
+
 /* RFC 5961 7 [ACK Throttling] */
-static void tcp_send_challenge_ack(struct sock *sk)
+static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb)
 {
 	/* unprotected vars, we dont care of overwrites */
 	static u32 challenge_timestamp;
 	static unsigned int challenge_count;
-	u32 now = jiffies / HZ;
+	struct tcp_sock *tp = tcp_sk(sk);
+	u32 now;
+
+	/* First check our per-socket dupack rate limit. */
+	if (tcp_oow_rate_limited(sock_net(sk), skb,
+				 LINUX_MIB_TCPACKSKIPPEDCHALLENGE,
+				 &tp->last_oow_ack_time))
+		return;
 
+	/* Then check the check host-wide RFC 5961 rate limit. */
+	now = jiffies / HZ;
 	if (now != challenge_timestamp) {
 		challenge_timestamp = now;
 		challenge_count = 0;
@@ -3357,34 +3422,34 @@ static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
 }
 
 /* This routine deals with acks during a TLP episode.
+ * We mark the end of a TLP episode on receiving TLP dupack or when
+ * ack is after tlp_high_seq.
  * Ref: loss detection algorithm in draft-dukkipati-tcpm-tcp-loss-probe.
  */
 static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	bool is_tlp_dupack = (ack == tp->tlp_high_seq) &&
-			     !(flag & (FLAG_SND_UNA_ADVANCED |
-				       FLAG_NOT_DUP | FLAG_DATA_SACKED));
 
-	/* Mark the end of TLP episode on receiving TLP dupack or when
-	 * ack is after tlp_high_seq.
-	 */
-	if (is_tlp_dupack) {
-		tp->tlp_high_seq = 0;
+	if (before(ack, tp->tlp_high_seq))
 		return;
-	}
 
-	if (after(ack, tp->tlp_high_seq)) {
+	if (flag & FLAG_DSACKING_ACK) {
+		/* This DSACK means original and TLP probe arrived; no loss */
+		tp->tlp_high_seq = 0;
+	} else if (after(ack, tp->tlp_high_seq)) {
+		/* ACK advances: there was a loss, so reduce cwnd. Reset
+		 * tlp_high_seq in tcp_init_cwnd_reduction()
+		 */
+		tcp_init_cwnd_reduction(sk);
+		tcp_set_ca_state(sk, TCP_CA_CWR);
+		tcp_end_cwnd_reduction(sk);
+		tcp_try_keep_open(sk);
+		NET_INC_STATS_BH(sock_net(sk),
+				 LINUX_MIB_TCPLOSSPROBERECOVERY);
+	} else if (!(flag & (FLAG_SND_UNA_ADVANCED |
+			     FLAG_NOT_DUP | FLAG_DATA_SACKED))) {
+		/* Pure dupack: original and TLP probe arrived; no loss */
 		tp->tlp_high_seq = 0;
-		/* Don't reduce cwnd if DSACK arrives for TLP retrans. */
-		if (!(flag & FLAG_DSACKING_ACK)) {
-			tcp_init_cwnd_reduction(sk);
-			tcp_set_ca_state(sk, TCP_CA_CWR);
-			tcp_end_cwnd_reduction(sk);
-			tcp_try_keep_open(sk);
-			NET_INC_STATS_BH(sock_net(sk),
-					 LINUX_MIB_TCPLOSSPROBERECOVERY);
-		}
 	}
 }
 
@@ -3420,7 +3485,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	if (before(ack, prior_snd_una)) {
 		/* RFC 5961 5.2 [Blind Data Injection Attack].[Mitigation] */
 		if (before(ack, prior_snd_una - tp->max_window)) {
-			tcp_send_challenge_ack(sk);
+			tcp_send_challenge_ack(sk, skb);
 			return -1;
 		}
 		goto old_ack;
@@ -3455,7 +3520,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 		 * Note, we use the fact that SND.UNA>=SND.WL2.
 		 */
 		tcp_update_wl(tp, ack_seq);
-		tp->snd_una = ack;
+		tcp_snd_una_update(tp, ack);
 		flag |= FLAG_WIN_UPDATE;
 
 		tcp_in_ack_event(sk, CA_ACK_WIN_UPDATE);
@@ -3559,6 +3624,23 @@ old_ack:
 	return 0;
 }
 
+static void tcp_parse_fastopen_option(int len, const unsigned char *cookie,
+				      bool syn, struct tcp_fastopen_cookie *foc,
+				      bool exp_opt)
+{
+	/* Valid only in SYN or SYN-ACK with an even length.  */
+	if (!foc || !syn || len < 0 || (len & 1))
+		return;
+
+	if (len >= TCP_FASTOPEN_COOKIE_MIN &&
+	    len <= TCP_FASTOPEN_COOKIE_MAX)
+		memcpy(foc->val, cookie, len);
+	else if (len != 0)
+		len = -1;
+	foc->len = len;
+	foc->exp = exp_opt;
+}
+
 /* Look for tcp options. Normally only called on SYN and SYNACK packets.
  * But, this can also be called on packets in the established flow when
  * the fast version below fails.
@@ -3648,21 +3730,22 @@ void tcp_parse_options(const struct sk_buff *skb,
 				 */
 				break;
 #endif
+			case TCPOPT_FASTOPEN:
+				tcp_parse_fastopen_option(
+					opsize - TCPOLEN_FASTOPEN_BASE,
+					ptr, th->syn, foc, false);
+				break;
+
 			case TCPOPT_EXP:
 				/* Fast Open option shares code 254 using a
-				 * 16 bits magic number. It's valid only in
-				 * SYN or SYN-ACK with an even size.
+				 * 16 bits magic number.
 				 */
-				if (opsize < TCPOLEN_EXP_FASTOPEN_BASE ||
-				    get_unaligned_be16(ptr) != TCPOPT_FASTOPEN_MAGIC ||
-				    foc == NULL || !th->syn || (opsize & 1))
-					break;
-				foc->len = opsize - TCPOLEN_EXP_FASTOPEN_BASE;
-				if (foc->len >= TCP_FASTOPEN_COOKIE_MIN &&
-				    foc->len <= TCP_FASTOPEN_COOKIE_MAX)
-					memcpy(foc->val, ptr + 2, foc->len);
-				else if (foc->len != 0)
-					foc->len = -1;
+				if (opsize >= TCPOLEN_EXP_FASTOPEN_BASE &&
+				    get_unaligned_be16(ptr) ==
+				    TCPOPT_FASTOPEN_MAGIC)
+					tcp_parse_fastopen_option(opsize -
+						TCPOLEN_EXP_FASTOPEN_BASE,
+						ptr + 2, th->syn, foc, true);
 				break;
 
 			}
@@ -4176,7 +4259,7 @@ static void tcp_ofo_queue(struct sock *sk)
 
 		tail = skb_peek_tail(&sk->sk_receive_queue);
 		eaten = tail && tcp_try_coalesce(sk, tail, skb, &fragstolen);
-		tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+		tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
 		if (!eaten)
 			__skb_queue_tail(&sk->sk_receive_queue, skb);
 		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
@@ -4344,7 +4427,7 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int
 	__skb_pull(skb, hdrlen);
 	eaten = (tail &&
 		 tcp_try_coalesce(sk, tail, skb, fragstolen)) ? 1 : 0;
-	tcp_sk(sk)->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+	tcp_rcv_nxt_update(tcp_sk(sk), TCP_SKB_CB(skb)->end_seq);
 	if (!eaten) {
 		__skb_queue_tail(&sk->sk_receive_queue, skb);
 		skb_set_owner_r(skb, sk);
@@ -4367,7 +4450,7 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
 	if (tcp_try_rmem_schedule(sk, skb, skb->truesize))
 		goto err_free;
 
-	if (memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size))
+	if (memcpy_from_msg(skb_put(skb, size), msg, size))
 		goto err_free;
 
 	TCP_SKB_CB(skb)->seq = tcp_sk(sk)->rcv_nxt;
@@ -4420,7 +4503,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 			__set_current_state(TASK_RUNNING);
 
 			local_bh_enable();
-			if (!skb_copy_datagram_iovec(skb, 0, tp->ucopy.iov, chunk)) {
+			if (!skb_copy_datagram_msg(skb, 0, tp->ucopy.msg, chunk)) {
 				tp->ucopy.len -= chunk;
 				tp->copied_seq += chunk;
 				eaten = (chunk == skb->len);
@@ -4437,7 +4520,7 @@ queue_and_out:
 
 			eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen);
 		}
-		tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+		tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
 		if (skb->len)
 			tcp_event_data_recv(sk, skb);
 		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
@@ -4626,7 +4709,7 @@ static void tcp_collapse_ofo_queue(struct sock *sk)
 	struct sk_buff *head;
 	u32 start, end;
 
-	if (skb == NULL)
+	if (!skb)
 		return;
 
 	start = TCP_SKB_CB(skb)->seq;
@@ -4757,7 +4840,7 @@ static bool tcp_should_expand_sndbuf(const struct sock *sk)
 		return false;
 
 	/* If we filled the congestion window, do not expand.  */
-	if (tp->packets_out >= tp->snd_cwnd)
+	if (tcp_packets_in_flight(tp) >= tp->snd_cwnd)
 		return false;
 
 	return true;
@@ -4785,6 +4868,8 @@ static void tcp_check_space(struct sock *sk)
 {
 	if (sock_flag(sk, SOCK_QUEUE_SHRUNK)) {
 		sock_reset_flag(sk, SOCK_QUEUE_SHRUNK);
+		/* pairs with tcp_poll() */
+		smp_mb__after_atomic();
 		if (sk->sk_socket &&
 		    test_bit(SOCK_NOSPACE, &sk->sk_socket->flags))
 			tcp_new_space(sk);
@@ -4940,10 +5025,9 @@ static int tcp_copy_to_iovec(struct sock *sk, struct sk_buff *skb, int hlen)
 
 	local_bh_enable();
 	if (skb_csum_unnecessary(skb))
-		err = skb_copy_datagram_iovec(skb, hlen, tp->ucopy.iov, chunk);
+		err = skb_copy_datagram_msg(skb, hlen, tp->ucopy.msg, chunk);
 	else
-		err = skb_copy_and_csum_datagram_iovec(skb, hlen,
-						       tp->ucopy.iov);
+		err = skb_copy_and_csum_datagram_msg(skb, hlen, tp->ucopy.msg);
 
 	if (!err) {
 		tp->ucopy.len -= chunk;
@@ -4990,7 +5074,10 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 	    tcp_paws_discard(sk, skb)) {
 		if (!th->rst) {
 			NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);
-			tcp_send_dupack(sk, skb);
+			if (!tcp_oow_rate_limited(sock_net(sk), skb,
+						  LINUX_MIB_TCPACKSKIPPEDPAWS,
+						  &tp->last_oow_ack_time))
+				tcp_send_dupack(sk, skb);
 			goto discard;
 		}
 		/* Reset is accepted even if it did not pass PAWS. */
@@ -5007,7 +5094,10 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 		if (!th->rst) {
 			if (th->syn)
 				goto syn_challenge;
-			tcp_send_dupack(sk, skb);
+			if (!tcp_oow_rate_limited(sock_net(sk), skb,
+						  LINUX_MIB_TCPACKSKIPPEDSEQ,
+						  &tp->last_oow_ack_time))
+				tcp_send_dupack(sk, skb);
 		}
 		goto discard;
 	}
@@ -5023,21 +5113,21 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 		if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt)
 			tcp_reset(sk);
 		else
-			tcp_send_challenge_ack(sk);
+			tcp_send_challenge_ack(sk, skb);
 		goto discard;
 	}
 
 	/* step 3: check security and precedence [ignored] */
 
 	/* step 4: Check for a SYN
-	 * RFC 5691 4.2 : Send a challenge ack
+	 * RFC 5961 4.2 : Send a challenge ack
 	 */
 	if (th->syn) {
 syn_challenge:
 		if (syn_inerr)
 			TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_INERRS);
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNCHALLENGE);
-		tcp_send_challenge_ack(sk);
+		tcp_send_challenge_ack(sk, skb);
 		goto discard;
 	}
 
@@ -5076,7 +5166,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (unlikely(sk->sk_rx_dst == NULL))
+	if (unlikely(!sk->sk_rx_dst))
 		inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb);
 	/*
 	 *	Header prediction.
@@ -5178,7 +5268,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 					tcp_rcv_rtt_measure_ts(sk, skb);
 
 					__skb_pull(skb, tcp_header_len);
-					tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+					tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
 					NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPHITSTOUSER);
 					eaten = 1;
 				}
@@ -5231,7 +5321,7 @@ slow_path:
 	if (len < (th->doff << 2) || tcp_checksum_complete_user(sk, skb))
 		goto csum_error;
 
-	if (!th->ack && !th->rst)
+	if (!th->ack && !th->rst && !th->syn)
 		goto discard;
 
 	/*
@@ -5273,7 +5363,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
 
 	tcp_set_state(sk, TCP_ESTABLISHED);
 
-	if (skb != NULL) {
+	if (skb) {
 		icsk->icsk_af_ops->sk_rx_dst_set(sk, skb);
 		security_inet_conn_established(sk, skb);
 	}
@@ -5311,8 +5401,8 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *data = tp->syn_data ? tcp_write_queue_head(sk) : NULL;
-	u16 mss = tp->rx_opt.mss_clamp;
-	bool syn_drop;
+	u16 mss = tp->rx_opt.mss_clamp, try_exp = 0;
+	bool syn_drop = false;
 
 	if (mss == tp->rx_opt.user_mss) {
 		struct tcp_options_received opt;
@@ -5324,16 +5414,25 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
 		mss = opt.mss_clamp;
 	}
 
-	if (!tp->syn_fastopen)  /* Ignore an unsolicited cookie */
+	if (!tp->syn_fastopen) {
+		/* Ignore an unsolicited cookie */
 		cookie->len = -1;
+	} else if (tp->total_retrans) {
+		/* SYN timed out and the SYN-ACK neither has a cookie nor
+		 * acknowledges data. Presumably the remote received only
+		 * the retransmitted (regular) SYNs: either the original
+		 * SYN-data or the corresponding SYN-ACK was dropped.
+		 */
+		syn_drop = (cookie->len < 0 && data);
+	} else if (cookie->len < 0 && !tp->syn_data) {
+		/* We requested a cookie but didn't get it. If we did not use
+		 * the (old) exp opt format then try so next time (try_exp=1).
+		 * Otherwise we go back to use the RFC7413 opt (try_exp=2).
+		 */
+		try_exp = tp->syn_fastopen_exp ? 2 : 1;
+	}
 
-	/* The SYN-ACK neither has cookie nor acknowledges the data. Presumably
-	 * the remote receives only the retransmitted (regular) SYNs: either
-	 * the original SYN-data or the corresponding SYN-ACK is lost.
-	 */
-	syn_drop = (cookie->len <= 0 && data && tp->total_retrans);
-
-	tcp_fastopen_cache_set(sk, mss, cookie, syn_drop);
+	tcp_fastopen_cache_set(sk, mss, cookie, syn_drop, try_exp);
 
 	if (data) { /* Retransmit unacked data in SYN */
 		tcp_for_write_queue_from(data, sk) {
@@ -5642,15 +5741,15 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 	}
 
 	req = tp->fastopen_rsk;
-	if (req != NULL) {
+	if (req) {
 		WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV &&
 		    sk->sk_state != TCP_FIN_WAIT1);
 
-		if (tcp_check_req(sk, skb, req, NULL, true) == NULL)
+		if (!tcp_check_req(sk, skb, req, true))
 			goto discard;
 	}
 
-	if (!th->ack && !th->rst)
+	if (!th->ack && !th->rst && !th->syn)
 		goto discard;
 
 	if (!tcp_validate_incoming(sk, skb, th, 0))
@@ -5732,7 +5831,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 		 * ACK we have received, this would have acknowledged
 		 * our SYNACK so stop the SYNACK timer.
 		 */
-		if (req != NULL) {
+		if (req) {
 			/* Return RST if ack_seq is invalid.
 			 * Note that RFC793 only says to generate a
 			 * DUPACK for it but for TCP Fast Open it seems
@@ -5853,12 +5952,12 @@ static inline void pr_drop_req(struct request_sock *req, __u16 port, int family)
 	struct inet_request_sock *ireq = inet_rsk(req);
 
 	if (family == AF_INET)
-		LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("drop open request from %pI4/%u\n"),
-			       &ireq->ir_rmt_addr, port);
+		net_dbg_ratelimited("drop open request from %pI4/%u\n",
+				    &ireq->ir_rmt_addr, port);
 #if IS_ENABLED(CONFIG_IPV6)
 	else if (family == AF_INET6)
-		LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("drop open request from %pI6/%u\n"),
-			       &ireq->ir_v6_rmt_addr, port);
+		net_dbg_ratelimited("drop open request from %pI6/%u\n",
+				    &ireq->ir_v6_rmt_addr, port);
 #endif
 }
 
@@ -5867,35 +5966,107 @@ static inline void pr_drop_req(struct request_sock *req, __u16 port, int family)
  * If we receive a SYN packet with these bits set, it means a
  * network is playing bad games with TOS bits. In order to
  * avoid possible false congestion notifications, we disable
- * TCP ECN negociation.
+ * TCP ECN negotiation.
  *
  * Exception: tcp_ca wants ECN. This is required for DCTCP
- * congestion control; it requires setting ECT on all packets,
- * including SYN. We inverse the test in this case: If our
- * local socket wants ECN, but peer only set ece/cwr (but not
- * ECT in IP header) its probably a non-DCTCP aware sender.
+ * congestion control: Linux DCTCP asserts ECT on all packets,
+ * including SYN, which is most optimal solution; however,
+ * others, such as FreeBSD do not.
  */
 static void tcp_ecn_create_request(struct request_sock *req,
 				   const struct sk_buff *skb,
-				   const struct sock *listen_sk)
+				   const struct sock *listen_sk,
+				   const struct dst_entry *dst)
 {
 	const struct tcphdr *th = tcp_hdr(skb);
 	const struct net *net = sock_net(listen_sk);
 	bool th_ecn = th->ece && th->cwr;
-	bool ect, need_ecn;
+	bool ect, ecn_ok;
 
 	if (!th_ecn)
 		return;
 
 	ect = !INET_ECN_is_not_ect(TCP_SKB_CB(skb)->ip_dsfield);
-	need_ecn = tcp_ca_needs_ecn(listen_sk);
+	ecn_ok = net->ipv4.sysctl_tcp_ecn || dst_feature(dst, RTAX_FEATURE_ECN);
 
-	if (!ect && !need_ecn && net->ipv4.sysctl_tcp_ecn)
-		inet_rsk(req)->ecn_ok = 1;
-	else if (ect && need_ecn)
+	if ((!ect && ecn_ok) || tcp_ca_needs_ecn(listen_sk))
 		inet_rsk(req)->ecn_ok = 1;
 }
 
+static void tcp_openreq_init(struct request_sock *req,
+			     const struct tcp_options_received *rx_opt,
+			     struct sk_buff *skb, const struct sock *sk)
+{
+	struct inet_request_sock *ireq = inet_rsk(req);
+
+	req->rcv_wnd = 0;		/* So that tcp_send_synack() knows! */
+	req->cookie_ts = 0;
+	tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq;
+	tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
+	tcp_rsk(req)->snt_synack = tcp_time_stamp;
+	tcp_rsk(req)->last_oow_ack_time = 0;
+	req->mss = rx_opt->mss_clamp;
+	req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0;
+	ireq->tstamp_ok = rx_opt->tstamp_ok;
+	ireq->sack_ok = rx_opt->sack_ok;
+	ireq->snd_wscale = rx_opt->snd_wscale;
+	ireq->wscale_ok = rx_opt->wscale_ok;
+	ireq->acked = 0;
+	ireq->ecn_ok = 0;
+	ireq->ir_rmt_port = tcp_hdr(skb)->source;
+	ireq->ir_num = ntohs(tcp_hdr(skb)->dest);
+	ireq->ir_mark = inet_request_mark(sk, skb);
+}
+
+struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops,
+				      struct sock *sk_listener)
+{
+	struct request_sock *req = reqsk_alloc(ops, sk_listener);
+
+	if (req) {
+		struct inet_request_sock *ireq = inet_rsk(req);
+
+		kmemcheck_annotate_bitfield(ireq, flags);
+		ireq->opt = NULL;
+		atomic64_set(&ireq->ir_cookie, 0);
+		ireq->ireq_state = TCP_NEW_SYN_RECV;
+		write_pnet(&ireq->ireq_net, sock_net(sk_listener));
+		ireq->ireq_family = sk_listener->sk_family;
+	}
+
+	return req;
+}
+EXPORT_SYMBOL(inet_reqsk_alloc);
+
+/*
+ * Return true if a syncookie should be sent
+ */
+static bool tcp_syn_flood_action(struct sock *sk,
+				 const struct sk_buff *skb,
+				 const char *proto)
+{
+	const char *msg = "Dropping request";
+	bool want_cookie = false;
+	struct listen_sock *lopt;
+
+#ifdef CONFIG_SYN_COOKIES
+	if (sysctl_tcp_syncookies) {
+		msg = "Sending cookies";
+		want_cookie = true;
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDOCOOKIES);
+	} else
+#endif
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP);
+
+	lopt = inet_csk(sk)->icsk_accept_queue.listen_opt;
+	if (!lopt->synflood_warned && sysctl_tcp_syncookies != 2) {
+		lopt->synflood_warned = 1;
+		pr_info("%s: Possible SYN flooding on port %d. %s.  Check SNMP counters.\n",
+			proto, ntohs(tcp_hdr(skb)->dest), msg);
+	}
+	return want_cookie;
+}
+
 int tcp_conn_request(struct request_sock_ops *rsk_ops,
 		     const struct tcp_request_sock_ops *af_ops,
 		     struct sock *sk, struct sk_buff *skb)
@@ -5933,7 +6104,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 		goto drop;
 	}
 
-	req = inet_reqsk_alloc(rsk_ops);
+	req = inet_reqsk_alloc(rsk_ops, sk);
 	if (!req)
 		goto drop;
 
@@ -5950,18 +6121,15 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	tmp_opt.tstamp_ok = tmp_opt.saw_tstamp;
 	tcp_openreq_init(req, &tmp_opt, skb, sk);
 
+	/* Note: tcp_v6_init_req() might override ir_iif for link locals */
+	inet_rsk(req)->ir_iif = sk->sk_bound_dev_if;
+
 	af_ops->init_req(req, sk, skb);
 
 	if (security_inet_conn_request(sk, skb, req))
 		goto drop_and_free;
 
-	if (!want_cookie || tmp_opt.tstamp_ok)
-		tcp_ecn_create_request(req, skb, sk);
-
-	if (want_cookie) {
-		isn = cookie_init_sequence(af_ops, sk, skb, &req->mss);
-		req->cookie_ts = tmp_opt.tstamp_ok;
-	} else if (!isn) {
+	if (!want_cookie && !isn) {
 		/* VJ's idea. We save last timestamp seen
 		 * from the destination in peer table, when entering
 		 * state TIME-WAIT, and check against it before
@@ -6009,6 +6177,15 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 			goto drop_and_free;
 	}
 
+	tcp_ecn_create_request(req, skb, sk, dst);
+
+	if (want_cookie) {
+		isn = cookie_init_sequence(af_ops, sk, skb, &req->mss);
+		req->cookie_ts = tmp_opt.tstamp_ok;
+		if (!tmp_opt.tstamp_ok)
+			inet_rsk(req)->ecn_ok = 0;
+	}
+
 	tcp_rsk(req)->snt_isn = isn;
 	tcp_openreq_init_rwin(req, sk, dst);
 	fastopen = !want_cookie &&
@@ -6019,7 +6196,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 		if (err || want_cookie)
 			goto drop_and_free;
 
-		tcp_rsk(req)->listener = NULL;
+		tcp_rsk(req)->tfo_listener = false;
 		af_ops->queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
 	}
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 9c7d7621466b..fc1c658ec6c1 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -122,7 +122,7 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 	   and use initial timestamp retrieved from peer table.
 	 */
 	if (tcptw->tw_ts_recent_stamp &&
-	    (twp == NULL || (sysctl_tcp_tw_reuse &&
+	    (!twp || (sysctl_tcp_tw_reuse &&
 			     get_seconds() - tcptw->tw_ts_recent_stamp > 1))) {
 		tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
 		if (tp->write_seq == 0)
@@ -189,7 +189,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 
 	if (!inet->inet_saddr)
 		inet->inet_saddr = fl4->saddr;
-	inet->inet_rcv_saddr = inet->inet_saddr;
+	sk_rcv_saddr_set(sk, inet->inet_saddr);
 
 	if (tp->rx_opt.ts_recent_stamp && inet->inet_daddr != daddr) {
 		/* Reset inherited state */
@@ -204,7 +204,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 		tcp_fetch_timewait_stamp(sk, &rt->dst);
 
 	inet->inet_dport = usin->sin_port;
-	inet->inet_daddr = daddr;
+	sk_daddr_set(sk, daddr);
 
 	inet_csk(sk)->icsk_ext_hdr_len = 0;
 	if (inet_opt)
@@ -310,6 +310,34 @@ static void do_redirect(struct sk_buff *skb, struct sock *sk)
 		dst->ops->redirect(dst, sk, skb);
 }
 
+
+/* handle ICMP messages on TCP_NEW_SYN_RECV request sockets */
+void tcp_req_err(struct sock *sk, u32 seq)
+{
+	struct request_sock *req = inet_reqsk(sk);
+	struct net *net = sock_net(sk);
+
+	/* ICMPs are not backlogged, hence we cannot get
+	 * an established socket here.
+	 */
+	WARN_ON(req->sk);
+
+	if (seq != tcp_rsk(req)->snt_isn) {
+		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
+		reqsk_put(req);
+	} else {
+		/*
+		 * Still in SYN_RECV, just remove it silently.
+		 * There is no good way to pass the error to the newly
+		 * created socket, and POSIX does not want network
+		 * errors returned from accept().
+		 */
+		NET_INC_STATS_BH(net, LINUX_MIB_LISTENDROPS);
+		inet_csk_reqsk_queue_drop(req->rsk_listener, req);
+	}
+}
+EXPORT_SYMBOL(tcp_req_err);
+
 /*
  * This routine is called by the ICMP module when it gets some
  * sort of error condition.  If err < 0 then the socket should
@@ -343,8 +371,9 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 	int err;
 	struct net *net = dev_net(icmp_skb->dev);
 
-	sk = inet_lookup(net, &tcp_hashinfo, iph->daddr, th->dest,
-			iph->saddr, th->source, inet_iif(icmp_skb));
+	sk = __inet_lookup_established(net, &tcp_hashinfo, iph->daddr,
+				       th->dest, iph->saddr, ntohs(th->source),
+				       inet_iif(icmp_skb));
 	if (!sk) {
 		ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS);
 		return;
@@ -353,6 +382,9 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 		inet_twsk_put(inet_twsk(sk));
 		return;
 	}
+	seq = ntohl(th->seq);
+	if (sk->sk_state == TCP_NEW_SYN_RECV)
+		return tcp_req_err(sk, seq);
 
 	bh_lock_sock(sk);
 	/* If too many ICMPs get dropped on busy
@@ -374,7 +406,6 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 
 	icsk = inet_csk(sk);
 	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;
@@ -458,42 +489,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 	}
 
 	switch (sk->sk_state) {
-		struct request_sock *req, **prev;
-	case TCP_LISTEN:
-		if (sock_owned_by_user(sk))
-			goto out;
-
-		req = inet_csk_search_req(sk, &prev, th->dest,
-					  iph->daddr, iph->saddr);
-		if (!req)
-			goto out;
-
-		/* ICMPs are not backlogged, hence we cannot get
-		   an established socket here.
-		 */
-		WARN_ON(req->sk);
-
-		if (seq != tcp_rsk(req)->snt_isn) {
-			NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
-			goto out;
-		}
-
-		/*
-		 * Still in SYN_RECV, just remove it silently.
-		 * There is no good way to pass the error to the newly
-		 * created socket, and POSIX does not want network
-		 * errors returned from accept().
-		 */
-		inet_csk_reqsk_queue_drop(sk, req, prev);
-		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
-		goto out;
-
 	case TCP_SYN_SENT:
 	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)
+		if (fastopen && !fastopen->sk)
 			break;
 
 		if (!sock_owned_by_user(sk)) {
@@ -598,7 +599,10 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 	if (th->rst)
 		return;
 
-	if (skb_rtable(skb)->rt_type != RTN_LOCAL)
+	/* If sk not NULL, it means we did a successful lookup and incoming
+	 * route had to be correct. prequeue might have dropped our dst.
+	 */
+	if (!sk && skb_rtable(skb)->rt_type != RTN_LOCAL)
 		return;
 
 	/* Swap the send and the receive. */
@@ -620,6 +624,7 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 	arg.iov[0].iov_base = (unsigned char *)&rep;
 	arg.iov[0].iov_len  = sizeof(rep.th);
 
+	net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev);
 #ifdef CONFIG_TCP_MD5SIG
 	hash_location = tcp_parse_md5sig_option(th);
 	if (!sk && hash_location) {
@@ -630,7 +635,7 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 		 * Incoming packet is checked with md5 hash with finding key,
 		 * no RST generated if md5 hash doesn't match.
 		 */
-		sk1 = __inet_lookup_listener(dev_net(skb_dst(skb)->dev),
+		sk1 = __inet_lookup_listener(net,
 					     &tcp_hashinfo, ip_hdr(skb)->saddr,
 					     th->source, ip_hdr(skb)->daddr,
 					     ntohs(th->source), inet_iif(skb));
@@ -643,7 +648,7 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 		if (!key)
 			goto release_sk1;
 
-		genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, NULL, skb);
+		genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, skb);
 		if (genhash || memcmp(hash_location, newhash, 16) != 0)
 			goto release_sk1;
 	} else {
@@ -678,9 +683,9 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 	if (sk)
 		arg.bound_dev_if = sk->sk_bound_dev_if;
 
-	net = dev_net(skb_dst(skb)->dev);
 	arg.tos = ip_hdr(skb)->tos;
-	ip_send_unicast_reply(net, skb, &TCP_SKB_CB(skb)->header.h4.opt,
+	ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
+			      skb, &TCP_SKB_CB(skb)->header.h4.opt,
 			      ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
 			      &arg, arg.iov[0].iov_len);
 
@@ -764,7 +769,8 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
 	if (oif)
 		arg.bound_dev_if = oif;
 	arg.tos = tos;
-	ip_send_unicast_reply(net, skb, &TCP_SKB_CB(skb)->header.h4.opt,
+	ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
+			      skb, &TCP_SKB_CB(skb)->header.h4.opt,
 			      ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
 			      &arg, arg.iov[0].iov_len);
 
@@ -850,35 +856,6 @@ static void tcp_v4_reqsk_destructor(struct request_sock *req)
 	kfree(inet_rsk(req)->opt);
 }
 
-/*
- * Return true if a syncookie should be sent
- */
-bool tcp_syn_flood_action(struct sock *sk,
-			 const struct sk_buff *skb,
-			 const char *proto)
-{
-	const char *msg = "Dropping request";
-	bool want_cookie = false;
-	struct listen_sock *lopt;
-
-#ifdef CONFIG_SYN_COOKIES
-	if (sysctl_tcp_syncookies) {
-		msg = "Sending cookies";
-		want_cookie = true;
-		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDOCOOKIES);
-	} else
-#endif
-		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP);
-
-	lopt = inet_csk(sk)->icsk_accept_queue.listen_opt;
-	if (!lopt->synflood_warned && sysctl_tcp_syncookies != 2) {
-		lopt->synflood_warned = 1;
-		pr_info("%s: Possible SYN flooding on port %d. %s.  Check SNMP counters.\n",
-			proto, ntohs(tcp_hdr(skb)->dest), msg);
-	}
-	return want_cookie;
-}
-EXPORT_SYMBOL(tcp_syn_flood_action);
 
 #ifdef CONFIG_TCP_MD5SIG
 /*
@@ -892,10 +869,10 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk,
 					 const union tcp_md5_addr *addr,
 					 int family)
 {
-	struct tcp_sock *tp = tcp_sk(sk);
+	const struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_md5sig_key *key;
 	unsigned int size = sizeof(struct in_addr);
-	struct tcp_md5sig_info *md5sig;
+	const struct tcp_md5sig_info *md5sig;
 
 	/* caller either holds rcu_read_lock() or socket lock */
 	md5sig = rcu_dereference_check(tp->md5sig_info,
@@ -918,24 +895,15 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk,
 EXPORT_SYMBOL(tcp_md5_do_lookup);
 
 struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk,
-					 struct sock *addr_sk)
+					 const struct sock *addr_sk)
 {
-	union tcp_md5_addr *addr;
+	const union tcp_md5_addr *addr;
 
-	addr = (union tcp_md5_addr *)&inet_sk(addr_sk)->inet_daddr;
+	addr = (const union tcp_md5_addr *)&addr_sk->sk_daddr;
 	return tcp_md5_do_lookup(sk, addr, AF_INET);
 }
 EXPORT_SYMBOL(tcp_v4_md5_lookup);
 
-static struct tcp_md5sig_key *tcp_v4_reqsk_md5_lookup(struct sock *sk,
-						      struct request_sock *req)
-{
-	union tcp_md5_addr *addr;
-
-	addr = (union tcp_md5_addr *)&inet_rsk(req)->ir_rmt_addr;
-	return tcp_md5_do_lookup(sk, addr, AF_INET);
-}
-
 /* This can be called on a newly created socket, from other files */
 int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 		   int family, const u8 *newkey, u8 newkeylen, gfp_t gfp)
@@ -1096,8 +1064,8 @@ clear_hash_noput:
 	return 1;
 }
 
-int tcp_v4_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key,
-			const struct sock *sk, const struct request_sock *req,
+int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key,
+			const struct sock *sk,
 			const struct sk_buff *skb)
 {
 	struct tcp_md5sig_pool *hp;
@@ -1105,12 +1073,9 @@ int tcp_v4_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key,
 	const struct tcphdr *th = tcp_hdr(skb);
 	__be32 saddr, daddr;
 
-	if (sk) {
-		saddr = inet_sk(sk)->inet_saddr;
-		daddr = inet_sk(sk)->inet_daddr;
-	} else if (req) {
-		saddr = inet_rsk(req)->ir_loc_addr;
-		daddr = inet_rsk(req)->ir_rmt_addr;
+	if (sk) { /* valid for establish/request sockets */
+		saddr = sk->sk_rcv_saddr;
+		daddr = sk->sk_daddr;
 	} else {
 		const struct iphdr *iph = ip_hdr(skb);
 		saddr = iph->saddr;
@@ -1147,8 +1112,9 @@ clear_hash_noput:
 }
 EXPORT_SYMBOL(tcp_v4_md5_hash_skb);
 
-static bool __tcp_v4_inbound_md5_hash(struct sock *sk,
-				      const struct sk_buff *skb)
+/* Called with rcu_read_lock() */
+static bool tcp_v4_inbound_md5_hash(struct sock *sk,
+				    const struct sk_buff *skb)
 {
 	/*
 	 * This gets called for each TCP segment that arrives
@@ -1188,7 +1154,7 @@ static bool __tcp_v4_inbound_md5_hash(struct sock *sk,
 	 */
 	genhash = tcp_v4_md5_hash_skb(newhash,
 				      hash_expected,
-				      NULL, NULL, skb);
+				      NULL, skb);
 
 	if (genhash || memcmp(hash_location, newhash, 16) != 0) {
 		net_info_ratelimited("MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s\n",
@@ -1200,28 +1166,16 @@ static bool __tcp_v4_inbound_md5_hash(struct sock *sk,
 	}
 	return false;
 }
-
-static bool tcp_v4_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb)
-{
-	bool ret;
-
-	rcu_read_lock();
-	ret = __tcp_v4_inbound_md5_hash(sk, skb);
-	rcu_read_unlock();
-
-	return ret;
-}
-
 #endif
 
-static void tcp_v4_init_req(struct request_sock *req, struct sock *sk,
+static void tcp_v4_init_req(struct request_sock *req, struct sock *sk_listener,
 			    struct sk_buff *skb)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 
-	ireq->ir_loc_addr = ip_hdr(skb)->daddr;
-	ireq->ir_rmt_addr = ip_hdr(skb)->saddr;
-	ireq->no_srccheck = inet_sk(sk)->transparent;
+	sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
+	sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr);
+	ireq->no_srccheck = inet_sk(sk_listener)->transparent;
 	ireq->opt = tcp_v4_save_options(skb);
 }
 
@@ -1254,7 +1208,7 @@ struct request_sock_ops tcp_request_sock_ops __read_mostly = {
 static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
 	.mss_clamp	=	TCP_MSS_DEFAULT,
 #ifdef CONFIG_TCP_MD5SIG
-	.md5_lookup	=	tcp_v4_reqsk_md5_lookup,
+	.req_md5_lookup	=	tcp_v4_md5_lookup,
 	.calc_md5_hash	=	tcp_v4_md5_hash_skb,
 #endif
 	.init_req	=	tcp_v4_init_req,
@@ -1313,8 +1267,8 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	newtp		      = tcp_sk(newsk);
 	newinet		      = inet_sk(newsk);
 	ireq		      = inet_rsk(req);
-	newinet->inet_daddr   = ireq->ir_rmt_addr;
-	newinet->inet_rcv_saddr = ireq->ir_loc_addr;
+	sk_daddr_set(newsk, ireq->ir_rmt_addr);
+	sk_rcv_saddr_set(newsk, ireq->ir_loc_addr);
 	newinet->inet_saddr	      = ireq->ir_loc_addr;
 	inet_opt	      = ireq->opt;
 	rcu_assign_pointer(newinet->inet_opt, inet_opt);
@@ -1337,6 +1291,8 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	}
 	sk_setup_caps(newsk, dst);
 
+	tcp_ca_openreq_child(newsk, dst);
+
 	tcp_sync_mss(newsk, dst_mtu(dst));
 	newtp->advmss = dst_metric_advmss(dst);
 	if (tcp_sk(sk)->rx_opt.user_mss &&
@@ -1349,7 +1305,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	/* Copy over the MD5 key from the original socket */
 	key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&newinet->inet_daddr,
 				AF_INET);
-	if (key != NULL) {
+	if (key) {
 		/*
 		 * We're using one, so create a matching key
 		 * on the newsk structure. If we fail to get
@@ -1384,15 +1340,18 @@ EXPORT_SYMBOL(tcp_v4_syn_recv_sock);
 
 static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
 {
-	struct tcphdr *th = tcp_hdr(skb);
+	const struct tcphdr *th = tcp_hdr(skb);
 	const struct iphdr *iph = ip_hdr(skb);
+	struct request_sock *req;
 	struct sock *nsk;
-	struct request_sock **prev;
-	/* Find possible connection requests. */
-	struct request_sock *req = inet_csk_search_req(sk, &prev, th->source,
-						       iph->saddr, iph->daddr);
-	if (req)
-		return tcp_check_req(sk, skb, req, prev, false);
+
+	req = inet_csk_search_req(sk, th->source, iph->saddr, iph->daddr);
+	if (req) {
+		nsk = tcp_check_req(sk, skb, req, false);
+		if (!nsk)
+			reqsk_put(req);
+		return nsk;
+	}
 
 	nsk = inet_lookup_established(sock_net(sk), &tcp_hashinfo, iph->saddr,
 			th->source, iph->daddr, th->dest, inet_iif(skb));
@@ -1429,9 +1388,10 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
 		struct dst_entry *dst = sk->sk_rx_dst;
 
 		sock_rps_save_rxhash(sk, skb);
+		sk_mark_napi_id(sk, skb);
 		if (dst) {
 			if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif ||
-			    dst->ops->check(dst, 0) == NULL) {
+			    !dst->ops->check(dst, 0)) {
 				dst_release(dst);
 				sk->sk_rx_dst = NULL;
 			}
@@ -1450,6 +1410,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
 
 		if (nsk != sk) {
 			sock_rps_save_rxhash(nsk, skb);
+			sk_mark_napi_id(sk, skb);
 			if (tcp_child_process(sk, nsk, skb)) {
 				rsk = nsk;
 				goto reset;
@@ -1508,8 +1469,8 @@ void tcp_v4_early_demux(struct sk_buff *skb)
 	if (sk) {
 		skb->sk = sk;
 		skb->destructor = sock_edemux;
-		if (sk->sk_state != TCP_TIME_WAIT) {
-			struct dst_entry *dst = sk->sk_rx_dst;
+		if (sk_fullsock(sk)) {
+			struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst);
 
 			if (dst)
 				dst = dst_check(dst, 0);
@@ -1661,7 +1622,7 @@ process:
 	if (sk_filter(sk, skb))
 		goto discard_and_relse;
 
-	sk_mark_napi_id(sk, skb);
+	sk_incoming_cpu_update(sk);
 	skb->dev = NULL;
 
 	bh_lock_sock_nested(sk);
@@ -1725,7 +1686,7 @@ do_time_wait:
 							iph->daddr, th->dest,
 							inet_iif(skb));
 		if (sk2) {
-			inet_twsk_deschedule(inet_twsk(sk), &tcp_death_row);
+			inet_twsk_deschedule(inet_twsk(sk));
 			inet_twsk_put(inet_twsk(sk));
 			sk = sk2;
 			goto process;
@@ -1837,7 +1798,7 @@ void tcp_v4_destroy_sock(struct sock *sk)
 	if (inet_csk(sk)->icsk_bind_hash)
 		inet_put_port(sk);
 
-	BUG_ON(tp->fastopen_rsk != NULL);
+	BUG_ON(tp->fastopen_rsk);
 
 	/* If socket is aborted during connect operation */
 	tcp_free_fastopen_req(tp);
@@ -1895,13 +1856,13 @@ get_req:
 		}
 		sk	  = sk_nulls_next(st->syn_wait_sk);
 		st->state = TCP_SEQ_STATE_LISTENING;
-		read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
+		spin_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
 	} else {
 		icsk = inet_csk(sk);
-		read_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
+		spin_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
 		if (reqsk_queue_len(&icsk->icsk_accept_queue))
 			goto start_req;
-		read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
+		spin_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
 		sk = sk_nulls_next(sk);
 	}
 get_sk:
@@ -1913,7 +1874,7 @@ get_sk:
 			goto out;
 		}
 		icsk = inet_csk(sk);
-		read_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
+		spin_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
 		if (reqsk_queue_len(&icsk->icsk_accept_queue)) {
 start_req:
 			st->uid		= sock_i_uid(sk);
@@ -1922,7 +1883,7 @@ start_req:
 			st->sbucket	= 0;
 			goto get_req;
 		}
-		read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
+		spin_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
 	}
 	spin_unlock_bh(&ilb->lock);
 	st->offset = 0;
@@ -2141,7 +2102,7 @@ static void tcp_seq_stop(struct seq_file *seq, void *v)
 	case TCP_SEQ_STATE_OPENREQ:
 		if (v) {
 			struct inet_connection_sock *icsk = inet_csk(st->syn_wait_sk);
-			read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
+			spin_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
 		}
 	case TCP_SEQ_STATE_LISTENING:
 		if (v != SEQ_START_TOKEN)
@@ -2195,17 +2156,17 @@ void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo)
 }
 EXPORT_SYMBOL(tcp_proc_unregister);
 
-static void get_openreq4(const struct sock *sk, const struct request_sock *req,
+static void get_openreq4(const struct request_sock *req,
 			 struct seq_file *f, int i, kuid_t uid)
 {
 	const struct inet_request_sock *ireq = inet_rsk(req);
-	long delta = req->expires - jiffies;
+	long delta = req->rsk_timer.expires - jiffies;
 
 	seq_printf(f, "%4d: %08X:%04X %08X:%04X"
 		" %02X %08X:%08X %02X:%08lX %08X %5u %8d %u %d %pK",
 		i,
 		ireq->ir_loc_addr,
-		ntohs(inet_sk(sk)->inet_sport),
+		ireq->ir_num,
 		ireq->ir_rmt_addr,
 		ntohs(ireq->ir_rmt_port),
 		TCP_SYN_RECV,
@@ -2216,7 +2177,7 @@ static void get_openreq4(const struct sock *sk, const struct request_sock *req,
 		from_kuid_munged(seq_user_ns(f), uid),
 		0,  /* non standard timer */
 		0, /* open_requests have no inode */
-		atomic_read(&sk->sk_refcnt),
+		0,
 		req);
 }
 
@@ -2282,9 +2243,9 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
 static void get_timewait4_sock(const struct inet_timewait_sock *tw,
 			       struct seq_file *f, int i)
 {
+	long delta = tw->tw_timer.expires - jiffies;
 	__be32 dest, src;
 	__u16 destp, srcp;
-	s32 delta = tw->tw_ttd - inet_tw_time_stamp();
 
 	dest  = tw->tw_daddr;
 	src   = tw->tw_rcv_saddr;
@@ -2323,7 +2284,7 @@ static int tcp4_seq_show(struct seq_file *seq, void *v)
 			get_tcp4_sock(v, seq, st->num);
 		break;
 	case TCP_SEQ_STATE_OPENREQ:
-		get_openreq4(st->syn_wait_sk, v, seq, st->num, st->uid);
+		get_openreq4(v, seq, st->num, st->uid);
 		break;
 	}
 out:
@@ -2423,14 +2384,42 @@ struct proto tcp_prot = {
 };
 EXPORT_SYMBOL(tcp_prot);
 
+static void __net_exit tcp_sk_exit(struct net *net)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu));
+	free_percpu(net->ipv4.tcp_sk);
+}
+
 static int __net_init tcp_sk_init(struct net *net)
 {
+	int res, cpu;
+
+	net->ipv4.tcp_sk = alloc_percpu(struct sock *);
+	if (!net->ipv4.tcp_sk)
+		return -ENOMEM;
+
+	for_each_possible_cpu(cpu) {
+		struct sock *sk;
+
+		res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW,
+					   IPPROTO_TCP, net);
+		if (res)
+			goto fail;
+		*per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk;
+	}
 	net->ipv4.sysctl_tcp_ecn = 2;
+	net->ipv4.sysctl_tcp_base_mss = TCP_BASE_MSS;
+	net->ipv4.sysctl_tcp_probe_threshold = TCP_PROBE_THRESHOLD;
+	net->ipv4.sysctl_tcp_probe_interval = TCP_PROBE_INTERVAL;
 	return 0;
-}
 
-static void __net_exit tcp_sk_exit(struct net *net)
-{
+fail:
+	tcp_sk_exit(net);
+
+	return res;
 }
 
 static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
index 1d191357bf88..2379c1b4efb2 100644
--- a/net/ipv4/tcp_memcontrol.c
+++ b/net/ipv4/tcp_memcontrol.c
@@ -9,13 +9,13 @@
 int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 {
 	/*
-	 * The root cgroup does not use res_counters, but rather,
+	 * The root cgroup does not use page_counters, but rather,
 	 * rely on the data already collected by the network
 	 * subsystem
 	 */
-	struct res_counter *res_parent = NULL;
-	struct cg_proto *cg_proto, *parent_cg;
 	struct mem_cgroup *parent = parent_mem_cgroup(memcg);
+	struct page_counter *counter_parent = NULL;
+	struct cg_proto *cg_proto, *parent_cg;
 
 	cg_proto = tcp_prot.proto_cgroup(memcg);
 	if (!cg_proto)
@@ -29,9 +29,9 @@ int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 
 	parent_cg = tcp_prot.proto_cgroup(parent);
 	if (parent_cg)
-		res_parent = &parent_cg->memory_allocated;
+		counter_parent = &parent_cg->memory_allocated;
 
-	res_counter_init(&cg_proto->memory_allocated, res_parent);
+	page_counter_init(&cg_proto->memory_allocated, counter_parent);
 	percpu_counter_init(&cg_proto->sockets_allocated, 0, GFP_KERNEL);
 
 	return 0;
@@ -47,10 +47,14 @@ void tcp_destroy_cgroup(struct mem_cgroup *memcg)
 		return;
 
 	percpu_counter_destroy(&cg_proto->sockets_allocated);
+
+	if (test_bit(MEMCG_SOCK_ACTIVATED, &cg_proto->flags))
+		static_key_slow_dec(&memcg_socket_limit_enabled);
+
 }
 EXPORT_SYMBOL(tcp_destroy_cgroup);
 
-static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
+static int tcp_update_limit(struct mem_cgroup *memcg, unsigned long nr_pages)
 {
 	struct cg_proto *cg_proto;
 	int i;
@@ -60,20 +64,17 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
 	if (!cg_proto)
 		return -EINVAL;
 
-	if (val > RES_COUNTER_MAX)
-		val = RES_COUNTER_MAX;
-
-	ret = res_counter_set_limit(&cg_proto->memory_allocated, val);
+	ret = page_counter_limit(&cg_proto->memory_allocated, nr_pages);
 	if (ret)
 		return ret;
 
 	for (i = 0; i < 3; i++)
-		cg_proto->sysctl_mem[i] = min_t(long, val >> PAGE_SHIFT,
+		cg_proto->sysctl_mem[i] = min_t(long, nr_pages,
 						sysctl_tcp_mem[i]);
 
-	if (val == RES_COUNTER_MAX)
+	if (nr_pages == PAGE_COUNTER_MAX)
 		clear_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags);
-	else if (val != RES_COUNTER_MAX) {
+	else {
 		/*
 		 * The active bit needs to be written after the static_key
 		 * update. This is what guarantees that the socket activation
@@ -102,11 +103,20 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
 	return 0;
 }
 
+enum {
+	RES_USAGE,
+	RES_LIMIT,
+	RES_MAX_USAGE,
+	RES_FAILCNT,
+};
+
+static DEFINE_MUTEX(tcp_limit_mutex);
+
 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(of_css(of));
-	unsigned long long val;
+	unsigned long nr_pages;
 	int ret = 0;
 
 	buf = strstrip(buf);
@@ -114,10 +124,12 @@ static ssize_t tcp_cgroup_write(struct kernfs_open_file *of,
 	switch (of_cft(of)->private) {
 	case RES_LIMIT:
 		/* see memcontrol.c */
-		ret = res_counter_memparse_write_strategy(buf, &val);
+		ret = page_counter_memparse(buf, "-1", &nr_pages);
 		if (ret)
 			break;
-		ret = tcp_update_limit(memcg, val);
+		mutex_lock(&tcp_limit_mutex);
+		ret = tcp_update_limit(memcg, nr_pages);
+		mutex_unlock(&tcp_limit_mutex);
 		break;
 	default:
 		ret = -EINVAL;
@@ -126,43 +138,36 @@ static ssize_t tcp_cgroup_write(struct kernfs_open_file *of,
 	return ret ?: nbytes;
 }
 
-static u64 tcp_read_stat(struct mem_cgroup *memcg, int type, u64 default_val)
-{
-	struct cg_proto *cg_proto;
-
-	cg_proto = tcp_prot.proto_cgroup(memcg);
-	if (!cg_proto)
-		return default_val;
-
-	return res_counter_read_u64(&cg_proto->memory_allocated, type);
-}
-
-static u64 tcp_read_usage(struct mem_cgroup *memcg)
-{
-	struct cg_proto *cg_proto;
-
-	cg_proto = tcp_prot.proto_cgroup(memcg);
-	if (!cg_proto)
-		return atomic_long_read(&tcp_memory_allocated) << PAGE_SHIFT;
-
-	return res_counter_read_u64(&cg_proto->memory_allocated, RES_USAGE);
-}
-
 static u64 tcp_cgroup_read(struct cgroup_subsys_state *css, struct cftype *cft)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+	struct cg_proto *cg_proto = tcp_prot.proto_cgroup(memcg);
 	u64 val;
 
 	switch (cft->private) {
 	case RES_LIMIT:
-		val = tcp_read_stat(memcg, RES_LIMIT, RES_COUNTER_MAX);
+		if (!cg_proto)
+			return PAGE_COUNTER_MAX;
+		val = cg_proto->memory_allocated.limit;
+		val *= PAGE_SIZE;
 		break;
 	case RES_USAGE:
-		val = tcp_read_usage(memcg);
+		if (!cg_proto)
+			val = atomic_long_read(&tcp_memory_allocated);
+		else
+			val = page_counter_read(&cg_proto->memory_allocated);
+		val *= PAGE_SIZE;
 		break;
 	case RES_FAILCNT:
+		if (!cg_proto)
+			return 0;
+		val = cg_proto->memory_allocated.failcnt;
+		break;
 	case RES_MAX_USAGE:
-		val = tcp_read_stat(memcg, cft->private, 0);
+		if (!cg_proto)
+			return 0;
+		val = cg_proto->memory_allocated.watermark;
+		val *= PAGE_SIZE;
 		break;
 	default:
 		BUG();
@@ -183,10 +188,10 @@ static ssize_t tcp_cgroup_reset(struct kernfs_open_file *of,
 
 	switch (of_cft(of)->private) {
 	case RES_MAX_USAGE:
-		res_counter_reset_max(&cg_proto->memory_allocated);
+		page_counter_reset_watermark(&cg_proto->memory_allocated);
 		break;
 	case RES_FAILCNT:
-		res_counter_reset_failcnt(&cg_proto->memory_allocated);
+		cg_proto->memory_allocated.failcnt = 0;
 		break;
 	}
 
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index ed9c9a91851c..a51d63a43e33 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -28,7 +28,8 @@ static struct tcp_metrics_block *__tcp_get_metrics(const struct inetpeer_addr *s
 
 struct tcp_fastopen_metrics {
 	u16	mss;
-	u16	syn_loss:10;		/* Recurring Fast Open SYN losses */
+	u16	syn_loss:10,		/* Recurring Fast Open SYN losses */
+		try_exp:2;		/* Request w/ exp. option (once) */
 	unsigned long	last_syn_loss;	/* Last Fast Open SYN loss */
 	struct	tcp_fastopen_cookie	cookie;
 };
@@ -40,6 +41,7 @@ struct tcp_fastopen_metrics {
 
 struct tcp_metrics_block {
 	struct tcp_metrics_block __rcu	*tcpm_next;
+	possible_net_t			tcpm_net;
 	struct inetpeer_addr		tcpm_saddr;
 	struct inetpeer_addr		tcpm_daddr;
 	unsigned long			tcpm_stamp;
@@ -52,6 +54,11 @@ struct tcp_metrics_block {
 	struct rcu_head			rcu_head;
 };
 
+static inline struct net *tm_net(struct tcp_metrics_block *tm)
+{
+	return read_pnet(&tm->tcpm_net);
+}
+
 static bool tcp_metric_locked(struct tcp_metrics_block *tm,
 			      enum tcp_metric_index idx)
 {
@@ -74,23 +81,20 @@ static void tcp_metric_set(struct tcp_metrics_block *tm,
 static bool addr_same(const struct inetpeer_addr *a,
 		      const struct inetpeer_addr *b)
 {
-	const struct in6_addr *a6, *b6;
-
 	if (a->family != b->family)
 		return false;
 	if (a->family == AF_INET)
 		return a->addr.a4 == b->addr.a4;
-
-	a6 = (const struct in6_addr *) &a->addr.a6[0];
-	b6 = (const struct in6_addr *) &b->addr.a6[0];
-
-	return ipv6_addr_equal(a6, b6);
+	return ipv6_addr_equal(&a->addr.in6, &b->addr.in6);
 }
 
 struct tcpm_hash_bucket {
 	struct tcp_metrics_block __rcu	*chain;
 };
 
+static struct tcpm_hash_bucket	*tcp_metrics_hash __read_mostly;
+static unsigned int		tcp_metrics_hash_log __read_mostly;
+
 static DEFINE_SPINLOCK(tcp_metrics_lock);
 
 static void tcpm_suck_dst(struct tcp_metrics_block *tm,
@@ -128,6 +132,8 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm,
 	if (fastopen_clear) {
 		tm->tcpm_fastopen.mss = 0;
 		tm->tcpm_fastopen.syn_loss = 0;
+		tm->tcpm_fastopen.try_exp = 0;
+		tm->tcpm_fastopen.cookie.exp = false;
 		tm->tcpm_fastopen.cookie.len = 0;
 	}
 }
@@ -143,6 +149,9 @@ static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst
 #define TCP_METRICS_RECLAIM_DEPTH	5
 #define TCP_METRICS_RECLAIM_PTR		(struct tcp_metrics_block *) 0x1UL
 
+#define deref_locked(p)	\
+	rcu_dereference_protected(p, lockdep_is_held(&tcp_metrics_lock))
+
 static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst,
 					  struct inetpeer_addr *saddr,
 					  struct inetpeer_addr *daddr,
@@ -171,9 +180,9 @@ static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst,
 	if (unlikely(reclaim)) {
 		struct tcp_metrics_block *oldest;
 
-		oldest = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain);
-		for (tm = rcu_dereference(oldest->tcpm_next); tm;
-		     tm = rcu_dereference(tm->tcpm_next)) {
+		oldest = deref_locked(tcp_metrics_hash[hash].chain);
+		for (tm = deref_locked(oldest->tcpm_next); tm;
+		     tm = deref_locked(tm->tcpm_next)) {
 			if (time_before(tm->tcpm_stamp, oldest->tcpm_stamp))
 				oldest = tm;
 		}
@@ -183,14 +192,15 @@ static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst,
 		if (!tm)
 			goto out_unlock;
 	}
+	write_pnet(&tm->tcpm_net, net);
 	tm->tcpm_saddr = *saddr;
 	tm->tcpm_daddr = *daddr;
 
 	tcpm_suck_dst(tm, dst, true);
 
 	if (likely(!reclaim)) {
-		tm->tcpm_next = net->ipv4.tcp_metrics_hash[hash].chain;
-		rcu_assign_pointer(net->ipv4.tcp_metrics_hash[hash].chain, tm);
+		tm->tcpm_next = tcp_metrics_hash[hash].chain;
+		rcu_assign_pointer(tcp_metrics_hash[hash].chain, tm);
 	}
 
 out_unlock:
@@ -214,10 +224,11 @@ static struct tcp_metrics_block *__tcp_get_metrics(const struct inetpeer_addr *s
 	struct tcp_metrics_block *tm;
 	int depth = 0;
 
-	for (tm = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain); tm;
+	for (tm = rcu_dereference(tcp_metrics_hash[hash].chain); tm;
 	     tm = rcu_dereference(tm->tcpm_next)) {
 		if (addr_same(&tm->tcpm_saddr, saddr) &&
-		    addr_same(&tm->tcpm_daddr, daddr))
+		    addr_same(&tm->tcpm_daddr, daddr) &&
+		    net_eq(tm_net(tm), net))
 			break;
 		depth++;
 	}
@@ -242,8 +253,8 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req,
 		break;
 #if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
-		*(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;
+		saddr.addr.in6 = inet_rsk(req)->ir_v6_loc_addr;
+		daddr.addr.in6 = inet_rsk(req)->ir_v6_rmt_addr;
 		hash = ipv6_addr_hash(&inet_rsk(req)->ir_v6_rmt_addr);
 		break;
 #endif
@@ -252,12 +263,14 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req,
 	}
 
 	net = dev_net(dst->dev);
-	hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log);
+	hash ^= net_hash_mix(net);
+	hash = hash_32(hash, tcp_metrics_hash_log);
 
-	for (tm = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain); tm;
+	for (tm = rcu_dereference(tcp_metrics_hash[hash].chain); tm;
 	     tm = rcu_dereference(tm->tcpm_next)) {
 		if (addr_same(&tm->tcpm_saddr, &saddr) &&
-		    addr_same(&tm->tcpm_daddr, &daddr))
+		    addr_same(&tm->tcpm_daddr, &daddr) &&
+		    net_eq(tm_net(tm), net))
 			break;
 	}
 	tcpm_check_stamp(tm, dst);
@@ -288,9 +301,9 @@ static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock
 			hash = (__force unsigned int) daddr.addr.a4;
 		} else {
 			saddr.family = AF_INET6;
-			*(struct in6_addr *)saddr.addr.a6 = tw->tw_v6_rcv_saddr;
+			saddr.addr.in6 = tw->tw_v6_rcv_saddr;
 			daddr.family = AF_INET6;
-			*(struct in6_addr *)daddr.addr.a6 = tw->tw_v6_daddr;
+			daddr.addr.in6 = tw->tw_v6_daddr;
 			hash = ipv6_addr_hash(&tw->tw_v6_daddr);
 		}
 	}
@@ -299,12 +312,14 @@ static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock
 		return NULL;
 
 	net = twsk_net(tw);
-	hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log);
+	hash ^= net_hash_mix(net);
+	hash = hash_32(hash, tcp_metrics_hash_log);
 
-	for (tm = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain); tm;
+	for (tm = rcu_dereference(tcp_metrics_hash[hash].chain); tm;
 	     tm = rcu_dereference(tm->tcpm_next)) {
 		if (addr_same(&tm->tcpm_saddr, &saddr) &&
-		    addr_same(&tm->tcpm_daddr, &daddr))
+		    addr_same(&tm->tcpm_daddr, &daddr) &&
+		    net_eq(tm_net(tm), net))
 			break;
 	}
 	return tm;
@@ -336,9 +351,9 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk,
 			hash = (__force unsigned int) daddr.addr.a4;
 		} else {
 			saddr.family = AF_INET6;
-			*(struct in6_addr *)saddr.addr.a6 = sk->sk_v6_rcv_saddr;
+			saddr.addr.in6 = sk->sk_v6_rcv_saddr;
 			daddr.family = AF_INET6;
-			*(struct in6_addr *)daddr.addr.a6 = sk->sk_v6_daddr;
+			daddr.addr.in6 = sk->sk_v6_daddr;
 			hash = ipv6_addr_hash(&sk->sk_v6_daddr);
 		}
 	}
@@ -347,7 +362,8 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk,
 		return NULL;
 
 	net = dev_net(dst->dev);
-	hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log);
+	hash ^= net_hash_mix(net);
+	hash = hash_32(hash, tcp_metrics_hash_log);
 
 	tm = __tcp_get_metrics(&saddr, &daddr, net, hash);
 	if (tm == TCP_METRICS_RECLAIM_PTR)
@@ -492,7 +508,7 @@ void tcp_init_metrics(struct sock *sk)
 	struct tcp_metrics_block *tm;
 	u32 val, crtt = 0; /* cached RTT scaled by 8 */
 
-	if (dst == NULL)
+	if (!dst)
 		goto reset;
 
 	dst_confirm(dst);
@@ -700,6 +716,8 @@ void tcp_fastopen_cache_get(struct sock *sk, u16 *mss,
 			if (tfom->mss)
 				*mss = tfom->mss;
 			*cookie = tfom->cookie;
+			if (cookie->len <= 0 && tfom->try_exp == 1)
+				cookie->exp = true;
 			*syn_loss = tfom->syn_loss;
 			*last_syn_loss = *syn_loss ? tfom->last_syn_loss : 0;
 		} while (read_seqretry(&fastopen_seqlock, seq));
@@ -708,7 +726,8 @@ void tcp_fastopen_cache_get(struct sock *sk, u16 *mss,
 }
 
 void tcp_fastopen_cache_set(struct sock *sk, u16 mss,
-			    struct tcp_fastopen_cookie *cookie, bool syn_lost)
+			    struct tcp_fastopen_cookie *cookie, bool syn_lost,
+			    u16 try_exp)
 {
 	struct dst_entry *dst = __sk_dst_get(sk);
 	struct tcp_metrics_block *tm;
@@ -725,6 +744,9 @@ void tcp_fastopen_cache_set(struct sock *sk, u16 mss,
 			tfom->mss = mss;
 		if (cookie && cookie->len > 0)
 			tfom->cookie = *cookie;
+		else if (try_exp > tfom->try_exp &&
+			 tfom->cookie.len <= 0 && !tfom->cookie.exp)
+			tfom->try_exp = try_exp;
 		if (syn_lost) {
 			++tfom->syn_loss;
 			tfom->last_syn_loss = jiffies;
@@ -773,19 +795,19 @@ static int tcp_metrics_fill_info(struct sk_buff *msg,
 
 	switch (tm->tcpm_daddr.family) {
 	case AF_INET:
-		if (nla_put_be32(msg, TCP_METRICS_ATTR_ADDR_IPV4,
-				tm->tcpm_daddr.addr.a4) < 0)
+		if (nla_put_in_addr(msg, TCP_METRICS_ATTR_ADDR_IPV4,
+				    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)
+		if (nla_put_in_addr(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_daddr.addr.a6) < 0)
+		if (nla_put_in6_addr(msg, TCP_METRICS_ATTR_ADDR_IPV6,
+				     &tm->tcpm_daddr.addr.in6) < 0)
 			goto nla_put_failure;
-		if (nla_put(msg, TCP_METRICS_ATTR_SADDR_IPV6, 16,
-			    tm->tcpm_saddr.addr.a6) < 0)
+		if (nla_put_in6_addr(msg, TCP_METRICS_ATTR_SADDR_IPV6,
+				     &tm->tcpm_saddr.addr.in6) < 0)
 			goto nla_put_failure;
 		break;
 	default:
@@ -886,7 +908,8 @@ static int tcp_metrics_dump_info(struct sk_buff *skb,
 	if (tcp_metrics_fill_info(skb, tm) < 0)
 		goto nla_put_failure;
 
-	return genlmsg_end(skb, hdr);
+	genlmsg_end(skb, hdr);
+	return 0;
 
 nla_put_failure:
 	genlmsg_cancel(skb, hdr);
@@ -897,17 +920,19 @@ static int tcp_metrics_nl_dump(struct sk_buff *skb,
 			       struct netlink_callback *cb)
 {
 	struct net *net = sock_net(skb->sk);
-	unsigned int max_rows = 1U << net->ipv4.tcp_metrics_hash_log;
+	unsigned int max_rows = 1U << tcp_metrics_hash_log;
 	unsigned int row, s_row = cb->args[0];
 	int s_col = cb->args[1], col = s_col;
 
 	for (row = s_row; row < max_rows; row++, s_col = 0) {
 		struct tcp_metrics_block *tm;
-		struct tcpm_hash_bucket *hb = net->ipv4.tcp_metrics_hash + row;
+		struct tcpm_hash_bucket *hb = tcp_metrics_hash + row;
 
 		rcu_read_lock();
 		for (col = 0, tm = rcu_dereference(hb->chain); tm;
 		     tm = rcu_dereference(tm->tcpm_next), col++) {
+			if (!net_eq(tm_net(tm), net))
+				continue;
 			if (col < s_col)
 				continue;
 			if (tcp_metrics_dump_info(skb, cb, tm) < 0) {
@@ -932,7 +957,7 @@ static int __parse_nl_addr(struct genl_info *info, struct inetpeer_addr *addr,
 	a = info->attrs[v4];
 	if (a) {
 		addr->family = AF_INET;
-		addr->addr.a4 = nla_get_be32(a);
+		addr->addr.a4 = nla_get_in_addr(a);
 		if (hash)
 			*hash = (__force unsigned int) addr->addr.a4;
 		return 0;
@@ -942,9 +967,9 @@ static int __parse_nl_addr(struct genl_info *info, struct inetpeer_addr *addr,
 		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));
+		addr->addr.in6 = nla_get_in6_addr(a);
 		if (hash)
-			*hash = ipv6_addr_hash((struct in6_addr *) addr->addr.a6);
+			*hash = ipv6_addr_hash(&addr->addr.in6);
 		return 0;
 	}
 	return optional ? 1 : -EAFNOSUPPORT;
@@ -993,13 +1018,15 @@ static int tcp_metrics_nl_cmd_get(struct sk_buff *skb, struct genl_info *info)
 	if (!reply)
 		goto nla_put_failure;
 
-	hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log);
+	hash ^= net_hash_mix(net);
+	hash = hash_32(hash, tcp_metrics_hash_log);
 	ret = -ESRCH;
 	rcu_read_lock();
-	for (tm = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain); tm;
+	for (tm = rcu_dereference(tcp_metrics_hash[hash].chain); tm;
 	     tm = rcu_dereference(tm->tcpm_next)) {
 		if (addr_same(&tm->tcpm_daddr, &daddr) &&
-		    (!src || addr_same(&tm->tcpm_saddr, &saddr))) {
+		    (!src || addr_same(&tm->tcpm_saddr, &saddr)) &&
+		    net_eq(tm_net(tm), net)) {
 			ret = tcp_metrics_fill_info(msg, tm);
 			break;
 		}
@@ -1019,34 +1046,27 @@ out_free:
 	return ret;
 }
 
-#define deref_locked_genl(p)	\
-	rcu_dereference_protected(p, lockdep_genl_is_held() && \
-				     lockdep_is_held(&tcp_metrics_lock))
-
-#define deref_genl(p)	rcu_dereference_protected(p, lockdep_genl_is_held())
-
-static int tcp_metrics_flush_all(struct net *net)
+static void tcp_metrics_flush_all(struct net *net)
 {
-	unsigned int max_rows = 1U << net->ipv4.tcp_metrics_hash_log;
-	struct tcpm_hash_bucket *hb = net->ipv4.tcp_metrics_hash;
+	unsigned int max_rows = 1U << tcp_metrics_hash_log;
+	struct tcpm_hash_bucket *hb = tcp_metrics_hash;
 	struct tcp_metrics_block *tm;
 	unsigned int row;
 
 	for (row = 0; row < max_rows; row++, hb++) {
+		struct tcp_metrics_block __rcu **pp;
 		spin_lock_bh(&tcp_metrics_lock);
-		tm = deref_locked_genl(hb->chain);
-		if (tm)
-			hb->chain = NULL;
-		spin_unlock_bh(&tcp_metrics_lock);
-		while (tm) {
-			struct tcp_metrics_block *next;
-
-			next = deref_genl(tm->tcpm_next);
-			kfree_rcu(tm, rcu_head);
-			tm = next;
+		pp = &hb->chain;
+		for (tm = deref_locked(*pp); tm; tm = deref_locked(*pp)) {
+			if (net_eq(tm_net(tm), net)) {
+				*pp = tm->tcpm_next;
+				kfree_rcu(tm, rcu_head);
+			} else {
+				pp = &tm->tcpm_next;
+			}
 		}
+		spin_unlock_bh(&tcp_metrics_lock);
 	}
-	return 0;
 }
 
 static int tcp_metrics_nl_cmd_del(struct sk_buff *skb, struct genl_info *info)
@@ -1063,19 +1083,23 @@ static int tcp_metrics_nl_cmd_del(struct sk_buff *skb, struct genl_info *info)
 	ret = parse_nl_addr(info, &daddr, &hash, 1);
 	if (ret < 0)
 		return ret;
-	if (ret > 0)
-		return tcp_metrics_flush_all(net);
+	if (ret > 0) {
+		tcp_metrics_flush_all(net);
+		return 0;
+	}
 	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;
+	hash ^= net_hash_mix(net);
+	hash = hash_32(hash, tcp_metrics_hash_log);
+	hb = tcp_metrics_hash + hash;
 	pp = &hb->chain;
 	spin_lock_bh(&tcp_metrics_lock);
-	for (tm = deref_locked_genl(*pp); tm; tm = deref_locked_genl(*pp)) {
+	for (tm = deref_locked(*pp); tm; tm = deref_locked(*pp)) {
 		if (addr_same(&tm->tcpm_daddr, &daddr) &&
-		    (!src || addr_same(&tm->tcpm_saddr, &saddr))) {
+		    (!src || addr_same(&tm->tcpm_saddr, &saddr)) &&
+		    net_eq(tm_net(tm), net)) {
 			*pp = tm->tcpm_next;
 			kfree_rcu(tm, rcu_head);
 			found = true;
@@ -1125,6 +1149,9 @@ static int __net_init tcp_net_metrics_init(struct net *net)
 	size_t size;
 	unsigned int slots;
 
+	if (!net_eq(net, &init_net))
+		return 0;
+
 	slots = tcpmhash_entries;
 	if (!slots) {
 		if (totalram_pages >= 128 * 1024)
@@ -1133,14 +1160,14 @@ static int __net_init tcp_net_metrics_init(struct net *net)
 			slots = 8 * 1024;
 	}
 
-	net->ipv4.tcp_metrics_hash_log = order_base_2(slots);
-	size = sizeof(struct tcpm_hash_bucket) << net->ipv4.tcp_metrics_hash_log;
+	tcp_metrics_hash_log = order_base_2(slots);
+	size = sizeof(struct tcpm_hash_bucket) << tcp_metrics_hash_log;
 
-	net->ipv4.tcp_metrics_hash = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
-	if (!net->ipv4.tcp_metrics_hash)
-		net->ipv4.tcp_metrics_hash = vzalloc(size);
+	tcp_metrics_hash = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
+	if (!tcp_metrics_hash)
+		tcp_metrics_hash = vzalloc(size);
 
-	if (!net->ipv4.tcp_metrics_hash)
+	if (!tcp_metrics_hash)
 		return -ENOMEM;
 
 	return 0;
@@ -1148,19 +1175,7 @@ static int __net_init tcp_net_metrics_init(struct net *net)
 
 static void __net_exit tcp_net_metrics_exit(struct net *net)
 {
-	unsigned int i;
-
-	for (i = 0; i < (1U << net->ipv4.tcp_metrics_hash_log) ; i++) {
-		struct tcp_metrics_block *tm, *next;
-
-		tm = rcu_dereference_protected(net->ipv4.tcp_metrics_hash[i].chain, 1);
-		while (tm) {
-			next = rcu_dereference_protected(tm->tcpm_next, 1);
-			kfree(tm);
-			tm = next;
-		}
-	}
-	kvfree(net->ipv4.tcp_metrics_hash);
+	tcp_metrics_flush_all(net);
 }
 
 static __net_initdata struct pernet_operations tcp_net_metrics_ops = {
@@ -1174,16 +1189,10 @@ void __init tcp_metrics_init(void)
 
 	ret = register_pernet_subsys(&tcp_net_metrics_ops);
 	if (ret < 0)
-		goto cleanup;
+		panic("Could not allocate the tcp_metrics hash table\n");
+
 	ret = genl_register_family_with_ops(&tcp_metrics_nl_family,
 					    tcp_metrics_nl_ops);
 	if (ret < 0)
-		goto cleanup_subsys;
-	return;
-
-cleanup_subsys:
-	unregister_pernet_subsys(&tcp_net_metrics_ops);
-
-cleanup:
-	return;
+		panic("Could not register tcp_metrics generic netlink\n");
 }
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 63d2680b65db..17e7339ee5ca 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -34,18 +34,7 @@ int sysctl_tcp_abort_on_overflow __read_mostly;
 
 struct inet_timewait_death_row tcp_death_row = {
 	.sysctl_max_tw_buckets = NR_FILE * 2,
-	.period		= TCP_TIMEWAIT_LEN / INET_TWDR_TWKILL_SLOTS,
-	.death_lock	= __SPIN_LOCK_UNLOCKED(tcp_death_row.death_lock),
 	.hashinfo	= &tcp_hashinfo,
-	.tw_timer	= TIMER_INITIALIZER(inet_twdr_hangman, 0,
-					    (unsigned long)&tcp_death_row),
-	.twkill_work	= __WORK_INITIALIZER(tcp_death_row.twkill_work,
-					     inet_twdr_twkill_work),
-/* Short-time timewait calendar */
-
-	.twcal_hand	= -1,
-	.twcal_timer	= TIMER_INITIALIZER(inet_twdr_twcal_tick, 0,
-					    (unsigned long)&tcp_death_row),
 };
 EXPORT_SYMBOL_GPL(tcp_death_row);
 
@@ -58,6 +47,25 @@ static bool tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win)
 	return seq == e_win && seq == end_seq;
 }
 
+static enum tcp_tw_status
+tcp_timewait_check_oow_rate_limit(struct inet_timewait_sock *tw,
+				  const struct sk_buff *skb, int mib_idx)
+{
+	struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
+
+	if (!tcp_oow_rate_limited(twsk_net(tw), skb, mib_idx,
+				  &tcptw->tw_last_oow_ack_time)) {
+		/* Send ACK. Note, we do not put the bucket,
+		 * it will be released by caller.
+		 */
+		return TCP_TW_ACK;
+	}
+
+	/* We are rate-limiting, so just release the tw sock and drop skb. */
+	inet_twsk_put(tw);
+	return TCP_TW_SUCCESS;
+}
+
 /*
  * * Main purpose of TIME-WAIT state is to close connection gracefully,
  *   when one of ends sits in LAST-ACK or CLOSING retransmitting FIN
@@ -116,7 +124,8 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 		    !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq,
 				   tcptw->tw_rcv_nxt,
 				   tcptw->tw_rcv_nxt + tcptw->tw_rcv_wnd))
-			return TCP_TW_ACK;
+			return tcp_timewait_check_oow_rate_limit(
+				tw, skb, LINUX_MIB_TCPACKSKIPPEDFINWAIT2);
 
 		if (th->rst)
 			goto kill;
@@ -138,7 +147,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 		if (!th->fin ||
 		    TCP_SKB_CB(skb)->end_seq != tcptw->tw_rcv_nxt + 1) {
 kill_with_rst:
-			inet_twsk_deschedule(tw, &tcp_death_row);
+			inet_twsk_deschedule(tw);
 			inet_twsk_put(tw);
 			return TCP_TW_RST;
 		}
@@ -154,11 +163,9 @@ kill_with_rst:
 		if (tcp_death_row.sysctl_tw_recycle &&
 		    tcptw->tw_ts_recent_stamp &&
 		    tcp_tw_remember_stamp(tw))
-			inet_twsk_schedule(tw, &tcp_death_row, tw->tw_timeout,
-					   TCP_TIMEWAIT_LEN);
+			inet_twsk_schedule(tw, tw->tw_timeout);
 		else
-			inet_twsk_schedule(tw, &tcp_death_row, TCP_TIMEWAIT_LEN,
-					   TCP_TIMEWAIT_LEN);
+			inet_twsk_schedule(tw, TCP_TIMEWAIT_LEN);
 		return TCP_TW_ACK;
 	}
 
@@ -191,13 +198,12 @@ kill_with_rst:
 			 */
 			if (sysctl_tcp_rfc1337 == 0) {
 kill:
-				inet_twsk_deschedule(tw, &tcp_death_row);
+				inet_twsk_deschedule(tw);
 				inet_twsk_put(tw);
 				return TCP_TW_SUCCESS;
 			}
 		}
-		inet_twsk_schedule(tw, &tcp_death_row, TCP_TIMEWAIT_LEN,
-				   TCP_TIMEWAIT_LEN);
+		inet_twsk_schedule(tw, TCP_TIMEWAIT_LEN);
 
 		if (tmp_opt.saw_tstamp) {
 			tcptw->tw_ts_recent	  = tmp_opt.rcv_tsval;
@@ -247,13 +253,10 @@ kill:
 		 * Do not reschedule in the last case.
 		 */
 		if (paws_reject || th->ack)
-			inet_twsk_schedule(tw, &tcp_death_row, TCP_TIMEWAIT_LEN,
-					   TCP_TIMEWAIT_LEN);
+			inet_twsk_schedule(tw, TCP_TIMEWAIT_LEN);
 
-		/* Send ACK. Note, we do not put the bucket,
-		 * it will be released by caller.
-		 */
-		return TCP_TW_ACK;
+		return tcp_timewait_check_oow_rate_limit(
+			tw, skb, LINUX_MIB_TCPACKSKIPPEDTIMEWAIT);
 	}
 	inet_twsk_put(tw);
 	return TCP_TW_SUCCESS;
@@ -265,18 +268,17 @@ EXPORT_SYMBOL(tcp_timewait_state_process);
  */
 void tcp_time_wait(struct sock *sk, int state, int timeo)
 {
-	struct inet_timewait_sock *tw = NULL;
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	const struct tcp_sock *tp = tcp_sk(sk);
+	struct inet_timewait_sock *tw;
 	bool recycle_ok = false;
 
 	if (tcp_death_row.sysctl_tw_recycle && tp->rx_opt.ts_recent_stamp)
 		recycle_ok = tcp_remember_stamp(sk);
 
-	if (tcp_death_row.tw_count < tcp_death_row.sysctl_max_tw_buckets)
-		tw = inet_twsk_alloc(sk, state);
+	tw = inet_twsk_alloc(sk, &tcp_death_row, state);
 
-	if (tw != NULL) {
+	if (tw) {
 		struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
 		const int rto = (icsk->icsk_rto << 2) - (icsk->icsk_rto >> 1);
 		struct inet_sock *inet = inet_sk(sk);
@@ -289,6 +291,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 		tcptw->tw_ts_recent	= tp->rx_opt.ts_recent;
 		tcptw->tw_ts_recent_stamp = tp->rx_opt.ts_recent_stamp;
 		tcptw->tw_ts_offset	= tp->tsoffset;
+		tcptw->tw_last_oow_ack_time = 0;
 
 #if IS_ENABLED(CONFIG_IPV6)
 		if (tw->tw_family == PF_INET6) {
@@ -297,7 +300,7 @@ 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_flowlabel = be32_to_cpu(np->flow_label & IPV6_FLOWLABEL_MASK);
 			tw->tw_ipv6only = sk->sk_ipv6only;
 		}
 #endif
@@ -313,7 +316,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 			struct tcp_md5sig_key *key;
 			tcptw->tw_md5_key = NULL;
 			key = tp->af_specific->md5_lookup(sk, sk);
-			if (key != NULL) {
+			if (key) {
 				tcptw->tw_md5_key = kmemdup(key, sizeof(*key), GFP_ATOMIC);
 				if (tcptw->tw_md5_key && !tcp_alloc_md5sig_pool())
 					BUG();
@@ -336,8 +339,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 				timeo = TCP_TIMEWAIT_LEN;
 		}
 
-		inet_twsk_schedule(tw, &tcp_death_row, timeo,
-				   TCP_TIMEWAIT_LEN);
+		inet_twsk_schedule(tw, timeo);
 		inet_twsk_put(tw);
 	} else {
 		/* Sorry, if we're out of memory, just CLOSE this
@@ -399,6 +401,35 @@ static void tcp_ecn_openreq_child(struct tcp_sock *tp,
 	tp->ecn_flags = inet_rsk(req)->ecn_ok ? TCP_ECN_OK : 0;
 }
 
+void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+	u32 ca_key = dst_metric(dst, RTAX_CC_ALGO);
+	bool ca_got_dst = false;
+
+	if (ca_key != TCP_CA_UNSPEC) {
+		const struct tcp_congestion_ops *ca;
+
+		rcu_read_lock();
+		ca = tcp_ca_find_key(ca_key);
+		if (likely(ca && try_module_get(ca->owner))) {
+			icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst);
+			icsk->icsk_ca_ops = ca;
+			ca_got_dst = true;
+		}
+		rcu_read_unlock();
+	}
+
+	/* If no valid choice made yet, assign current system default ca. */
+	if (!ca_got_dst &&
+	    (!icsk->icsk_ca_setsockopt ||
+	     !try_module_get(icsk->icsk_ca_ops->owner)))
+		tcp_assign_congestion_control(sk);
+
+	tcp_set_ca_state(sk, TCP_CA_Open);
+}
+EXPORT_SYMBOL_GPL(tcp_ca_openreq_child);
+
 /* This is not only more efficient than what we used to do, it eliminates
  * a lot of code duplication between IPv4/IPv6 SYN recv processing. -DaveM
  *
@@ -409,7 +440,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
 {
 	struct sock *newsk = inet_csk_clone_lock(sk, req, GFP_ATOMIC);
 
-	if (newsk != NULL) {
+	if (newsk) {
 		const struct inet_request_sock *ireq = inet_rsk(req);
 		struct tcp_request_sock *treq = tcp_rsk(req);
 		struct inet_connection_sock *newicsk = inet_csk(newsk);
@@ -441,6 +472,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
 		tcp_enable_early_retrans(newtp);
 		newtp->tlp_high_seq = 0;
 		newtp->lsndtime = treq->snt_synack;
+		newtp->last_oow_ack_time = 0;
 		newtp->total_retrans = req->num_retrans;
 
 		/* So many TCP implementations out there (incorrectly) count the
@@ -451,10 +483,6 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
 		newtp->snd_cwnd = TCP_INIT_CWND;
 		newtp->snd_cwnd_cnt = 0;
 
-		if (!try_module_get(newicsk->icsk_ca_ops->owner))
-			tcp_assign_congestion_control(newsk);
-
-		tcp_set_ca_state(newsk, TCP_CA_Open);
 		tcp_init_xmit_timers(newsk);
 		__skb_queue_head_init(&newtp->out_of_order_queue);
 		newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1;
@@ -530,7 +558,6 @@ EXPORT_SYMBOL(tcp_create_openreq_child);
 
 struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 			   struct request_sock *req,
-			   struct request_sock **prev,
 			   bool fastopen)
 {
 	struct tcp_options_received tmp_opt;
@@ -583,9 +610,20 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 		 * Reset timer after retransmitting SYNACK, similar to
 		 * the idea of fast retransmit in recovery.
 		 */
-		if (!inet_rtx_syn_ack(sk, req))
-			req->expires = min(TCP_TIMEOUT_INIT << req->num_timeout,
-					   TCP_RTO_MAX) + jiffies;
+		if (!tcp_oow_rate_limited(sock_net(sk), skb,
+					  LINUX_MIB_TCPACKSKIPPEDSYNRECV,
+					  &tcp_rsk(req)->last_oow_ack_time) &&
+
+		    !inet_rtx_syn_ack(sk, req)) {
+			unsigned long expires = jiffies;
+
+			expires += min(TCP_TIMEOUT_INIT << req->num_timeout,
+				       TCP_RTO_MAX);
+			if (!fastopen)
+				mod_timer_pending(&req->rsk_timer, expires);
+			else
+				req->rsk_timer.expires = expires;
+		}
 		return NULL;
 	}
 
@@ -717,13 +755,14 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 	 * socket is created, wait for troubles.
 	 */
 	child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL);
-	if (child == NULL)
+	if (!child)
 		goto listen_overflow;
 
-	inet_csk_reqsk_queue_unlink(sk, req, prev);
-	inet_csk_reqsk_queue_removed(sk, req);
-
+	inet_csk_reqsk_queue_drop(sk, req);
 	inet_csk_reqsk_queue_add(sk, req, child);
+	/* Warning: caller must not call reqsk_put(req);
+	 * child stole last reference on it.
+	 */
 	return child;
 
 listen_overflow:
@@ -745,7 +784,7 @@ embryonic_reset:
 		tcp_reset(sk);
 	}
 	if (!fastopen) {
-		inet_csk_reqsk_queue_drop(sk, req, prev);
+		inet_csk_reqsk_queue_drop(sk, req);
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_EMBRYONICRSTS);
 	}
 	return NULL;
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 5b90f2f447a5..3f7c2fca5431 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -29,8 +29,8 @@ static void tcp_gso_tstamp(struct sk_buff *skb, unsigned int ts_seq,
 	}
 }
 
-struct sk_buff *tcp4_gso_segment(struct sk_buff *skb,
-				 netdev_features_t features)
+static struct sk_buff *tcp4_gso_segment(struct sk_buff *skb,
+					netdev_features_t features)
 {
 	if (!pskb_may_pull(skb, sizeof(struct tcphdr)))
 		return ERR_PTR(-EINVAL);
@@ -94,9 +94,9 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 			       SKB_GSO_GRE_CSUM |
 			       SKB_GSO_IPIP |
 			       SKB_GSO_SIT |
-			       SKB_GSO_MPLS |
 			       SKB_GSO_UDP_TUNNEL |
 			       SKB_GSO_UDP_TUNNEL_CSUM |
+			       SKB_GSO_TUNNEL_REMCSUM |
 			       0) ||
 			     !(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))))
 			goto out;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index a3d453b94747..a369e8a70b2c 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -59,9 +59,6 @@ int sysctl_tcp_limit_output_bytes __read_mostly = 131072;
  */
 int sysctl_tcp_tso_win_divisor __read_mostly = 3;
 
-int sysctl_tcp_mtu_probing __read_mostly = 0;
-int sysctl_tcp_base_mss __read_mostly = TCP_BASE_MSS;
-
 /* By default, RFC2861 behavior.  */
 int sysctl_tcp_slow_start_after_idle __read_mostly = 1;
 
@@ -333,10 +330,19 @@ static void tcp_ecn_send_synack(struct sock *sk, struct sk_buff *skb)
 static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	bool use_ecn = sock_net(sk)->ipv4.sysctl_tcp_ecn == 1 ||
+		       tcp_ca_needs_ecn(sk);
+
+	if (!use_ecn) {
+		const struct dst_entry *dst = __sk_dst_get(sk);
+
+		if (dst && dst_feature(dst, RTAX_FEATURE_ECN))
+			use_ecn = true;
+	}
 
 	tp->ecn_flags = 0;
-	if (sock_net(sk)->ipv4.sysctl_tcp_ecn == 1 ||
-	    tcp_ca_needs_ecn(sk)) {
+
+	if (use_ecn) {
 		TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR;
 		tp->ecn_flags = TCP_ECN_OK;
 		if (tcp_ca_needs_ecn(sk))
@@ -512,17 +518,26 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
 
 	if (unlikely(OPTION_FAST_OPEN_COOKIE & options)) {
 		struct tcp_fastopen_cookie *foc = opts->fastopen_cookie;
+		u8 *p = (u8 *)ptr;
+		u32 len; /* Fast Open option length */
+
+		if (foc->exp) {
+			len = TCPOLEN_EXP_FASTOPEN_BASE + foc->len;
+			*ptr = htonl((TCPOPT_EXP << 24) | (len << 16) |
+				     TCPOPT_FASTOPEN_MAGIC);
+			p += TCPOLEN_EXP_FASTOPEN_BASE;
+		} else {
+			len = TCPOLEN_FASTOPEN_BASE + foc->len;
+			*p++ = TCPOPT_FASTOPEN;
+			*p++ = len;
+		}
 
-		*ptr++ = htonl((TCPOPT_EXP << 24) |
-			       ((TCPOLEN_EXP_FASTOPEN_BASE + foc->len) << 16) |
-			       TCPOPT_FASTOPEN_MAGIC);
-
-		memcpy(ptr, foc->val, foc->len);
-		if ((foc->len & 3) == 2) {
-			u8 *align = ((u8 *)ptr) + foc->len;
-			align[0] = align[1] = TCPOPT_NOP;
+		memcpy(p, foc->val, foc->len);
+		if ((len & 3) == 2) {
+			p[foc->len] = TCPOPT_NOP;
+			p[foc->len + 1] = TCPOPT_NOP;
 		}
-		ptr += (foc->len + 3) >> 2;
+		ptr += (len + 3) >> 2;
 	}
 }
 
@@ -559,7 +574,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 	opts->mss = tcp_advertise_mss(sk);
 	remaining -= TCPOLEN_MSS_ALIGNED;
 
-	if (likely(sysctl_tcp_timestamps && *md5 == NULL)) {
+	if (likely(sysctl_tcp_timestamps && !*md5)) {
 		opts->options |= OPTION_TS;
 		opts->tsval = tcp_skb_timestamp(skb) + tp->tsoffset;
 		opts->tsecr = tp->rx_opt.ts_recent;
@@ -577,13 +592,17 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 	}
 
 	if (fastopen && fastopen->cookie.len >= 0) {
-		u32 need = TCPOLEN_EXP_FASTOPEN_BASE + fastopen->cookie.len;
+		u32 need = fastopen->cookie.len;
+
+		need += fastopen->cookie.exp ? TCPOLEN_EXP_FASTOPEN_BASE :
+					       TCPOLEN_FASTOPEN_BASE;
 		need = (need + 3) & ~3U;  /* Align to 32 bits */
 		if (remaining >= need) {
 			opts->options |= OPTION_FAST_OPEN_COOKIE;
 			opts->fastopen_cookie = &fastopen->cookie;
 			remaining -= need;
 			tp->syn_fastopen = 1;
+			tp->syn_fastopen_exp = fastopen->cookie.exp ? 1 : 0;
 		}
 	}
 
@@ -595,15 +614,14 @@ static unsigned int tcp_synack_options(struct sock *sk,
 				   struct request_sock *req,
 				   unsigned int mss, struct sk_buff *skb,
 				   struct tcp_out_options *opts,
-				   struct tcp_md5sig_key **md5,
+				   const struct tcp_md5sig_key *md5,
 				   struct tcp_fastopen_cookie *foc)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	unsigned int remaining = MAX_TCP_OPTION_SPACE;
 
 #ifdef CONFIG_TCP_MD5SIG
-	*md5 = tcp_rsk(req)->af_specific->md5_lookup(sk, req);
-	if (*md5) {
+	if (md5) {
 		opts->options |= OPTION_MD5;
 		remaining -= TCPOLEN_MD5SIG_ALIGNED;
 
@@ -614,8 +632,6 @@ static unsigned int tcp_synack_options(struct sock *sk,
 		 */
 		ireq->tstamp_ok &= !ireq->sack_ok;
 	}
-#else
-	*md5 = NULL;
 #endif
 
 	/* We always send an MSS option. */
@@ -639,7 +655,10 @@ static unsigned int tcp_synack_options(struct sock *sk,
 			remaining -= TCPOLEN_SACKPERM_ALIGNED;
 	}
 	if (foc != NULL && foc->len >= 0) {
-		u32 need = TCPOLEN_EXP_FASTOPEN_BASE + foc->len;
+		u32 need = foc->len;
+
+		need += foc->exp ? TCPOLEN_EXP_FASTOPEN_BASE :
+				   TCPOLEN_FASTOPEN_BASE;
 		need = (need + 3) & ~3U;  /* Align to 32 bits */
 		if (remaining >= need) {
 			opts->options |= OPTION_FAST_OPEN_COOKIE;
@@ -939,7 +958,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 
 	skb_orphan(skb);
 	skb->sk = sk;
-	skb->destructor = tcp_wfree;
+	skb->destructor = skb_is_tcp_pure_ack(skb) ? sock_wfree : tcp_wfree;
 	skb_set_hash_from_sk(skb, sk);
 	atomic_add(skb->truesize, &sk->sk_wmem_alloc);
 
@@ -983,7 +1002,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	if (md5) {
 		sk_nocaps_add(sk, NETIF_F_GSO_MASK);
 		tp->af_specific->calc_md5_hash(opts.hash_location,
-					       md5, sk, NULL, skb);
+					       md5, sk, skb);
 	}
 #endif
 
@@ -1145,7 +1164,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
 
 	/* Get a new skb... force flag on. */
 	buff = sk_stream_alloc_skb(sk, nsize, gfp);
-	if (buff == NULL)
+	if (!buff)
 		return -ENOMEM; /* We'll just try again later. */
 
 	sk->sk_wmem_queued += buff->truesize;
@@ -1341,12 +1360,15 @@ void tcp_mtup_init(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct net *net = sock_net(sk);
 
-	icsk->icsk_mtup.enabled = sysctl_tcp_mtu_probing > 1;
+	icsk->icsk_mtup.enabled = net->ipv4.sysctl_tcp_mtu_probing > 1;
 	icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp + sizeof(struct tcphdr) +
 			       icsk->icsk_af_ops->net_header_len;
-	icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, sysctl_tcp_base_mss);
+	icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, net->ipv4.sysctl_tcp_base_mss);
 	icsk->icsk_mtup.probe_size = 0;
+	if (icsk->icsk_mtup.enabled)
+		icsk->icsk_mtup.probe_timestamp = tcp_time_stamp;
 }
 EXPORT_SYMBOL(tcp_mtup_init);
 
@@ -1515,6 +1537,27 @@ static bool tcp_nagle_check(bool partial, const struct tcp_sock *tp,
 		((nonagle & TCP_NAGLE_CORK) ||
 		 (!nonagle && tp->packets_out && tcp_minshall_check(tp)));
 }
+
+/* Return how many segs we'd like on a TSO packet,
+ * to send one TSO packet per ms
+ */
+static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now)
+{
+	u32 bytes, segs;
+
+	bytes = min(sk->sk_pacing_rate >> 10,
+		    sk->sk_gso_max_size - 1 - MAX_TCP_HEADER);
+
+	/* Goal is to send at least one packet per ms,
+	 * not one big TSO packet every 100 ms.
+	 * This preserves ACK clocking and is consistent
+	 * with tcp_tso_should_defer() heuristic.
+	 */
+	segs = max_t(u32, bytes / mss_now, sysctl_tcp_min_tso_segs);
+
+	return min_t(u32, segs, sk->sk_gso_max_segs);
+}
+
 /* 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,
@@ -1553,7 +1596,7 @@ static unsigned int tcp_mss_split_point(const struct sock *sk,
 static inline unsigned int tcp_cwnd_test(const struct tcp_sock *tp,
 					 const struct sk_buff *skb)
 {
-	u32 in_flight, cwnd;
+	u32 in_flight, cwnd, halfcwnd;
 
 	/* Don't be strict about the congestion window for the final FIN.  */
 	if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) &&
@@ -1562,10 +1605,14 @@ static inline unsigned int tcp_cwnd_test(const struct tcp_sock *tp,
 
 	in_flight = tcp_packets_in_flight(tp);
 	cwnd = tp->snd_cwnd;
-	if (in_flight < cwnd)
-		return (cwnd - in_flight);
+	if (in_flight >= cwnd)
+		return 0;
 
-	return 0;
+	/* For better scheduling, ensure we have at least
+	 * 2 GSO packets in flight.
+	 */
+	halfcwnd = max(cwnd >> 1, 1U);
+	return min(halfcwnd, cwnd - in_flight);
 }
 
 /* Initialize TSO state of a skb.
@@ -1676,7 +1723,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
 		return tcp_fragment(sk, skb, len, mss_now, gfp);
 
 	buff = sk_stream_alloc_skb(sk, 0, gfp);
-	if (unlikely(buff == NULL))
+	if (unlikely(!buff))
 		return -ENOMEM;
 
 	sk->sk_wmem_queued += buff->truesize;
@@ -1718,22 +1765,25 @@ 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,
-				 bool *is_cwnd_limited)
+				 bool *is_cwnd_limited, u32 max_segs)
 {
-	struct tcp_sock *tp = tcp_sk(sk);
 	const struct inet_connection_sock *icsk = inet_csk(sk);
-	u32 send_win, cong_win, limit, in_flight;
+	u32 age, send_win, cong_win, limit, in_flight;
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct skb_mstamp now;
+	struct sk_buff *head;
 	int win_divisor;
 
 	if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
 		goto send_now;
 
-	if (icsk->icsk_ca_state != TCP_CA_Open)
+	if (!((1 << icsk->icsk_ca_state) & (TCPF_CA_Open | TCPF_CA_CWR)))
 		goto send_now;
 
-	/* Defer for less than two clock ticks. */
-	if (tp->tso_deferred &&
-	    (((u32)jiffies << 1) >> 1) - (tp->tso_deferred >> 1) > 1)
+	/* Avoid bursty behavior by allowing defer
+	 * only if the last write was recent.
+	 */
+	if ((s32)(tcp_time_stamp - tp->lsndtime) > 0)
 		goto send_now;
 
 	in_flight = tcp_packets_in_flight(tp);
@@ -1748,8 +1798,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 	limit = min(send_win, cong_win);
 
 	/* If a full-sized TSO skb can be sent, do it. */
-	if (limit >= min_t(unsigned int, sk->sk_gso_max_size,
-			   tp->xmit_size_goal_segs * tp->mss_cache))
+	if (limit >= max_segs * tp->mss_cache)
 		goto send_now;
 
 	/* Middle in queue won't get any more data, full sendable already? */
@@ -1776,11 +1825,14 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 			goto send_now;
 	}
 
-	/* Ok, it looks like it is advisable to defer.
-	 * Do not rearm the timer if already set to not break TCP ACK clocking.
-	 */
-	if (!tp->tso_deferred)
-		tp->tso_deferred = 1 | (jiffies << 1);
+	head = tcp_write_queue_head(sk);
+	skb_mstamp_get(&now);
+	age = skb_mstamp_us_delta(&now, &head->skb_mstamp);
+	/* If next ACK is likely to come too late (half srtt), do not defer */
+	if (age < (tp->srtt_us >> 4))
+		goto send_now;
+
+	/* Ok, it looks like it is advisable to defer. */
 
 	if (cong_win < send_win && cong_win < skb->len)
 		*is_cwnd_limited = true;
@@ -1788,10 +1840,34 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 	return true;
 
 send_now:
-	tp->tso_deferred = 0;
 	return false;
 }
 
+static inline void tcp_mtu_check_reprobe(struct sock *sk)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct net *net = sock_net(sk);
+	u32 interval;
+	s32 delta;
+
+	interval = net->ipv4.sysctl_tcp_probe_interval;
+	delta = tcp_time_stamp - icsk->icsk_mtup.probe_timestamp;
+	if (unlikely(delta >= interval * HZ)) {
+		int mss = tcp_current_mss(sk);
+
+		/* Update current search range */
+		icsk->icsk_mtup.probe_size = 0;
+		icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp +
+			sizeof(struct tcphdr) +
+			icsk->icsk_af_ops->net_header_len;
+		icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss);
+
+		/* Update probe time stamp */
+		icsk->icsk_mtup.probe_timestamp = tcp_time_stamp;
+	}
+}
+
 /* Create a new MTU probe if we are ready.
  * MTU probe is regularly attempting to increase the path MTU by
  * deliberately sending larger packets.  This discovers routing
@@ -1806,11 +1882,13 @@ static int tcp_mtu_probe(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct sk_buff *skb, *nskb, *next;
+	struct net *net = sock_net(sk);
 	int len;
 	int probe_size;
 	int size_needed;
 	int copy;
 	int mss_now;
+	int interval;
 
 	/* Not currently probing/verifying,
 	 * not in recovery,
@@ -1823,12 +1901,25 @@ static int tcp_mtu_probe(struct sock *sk)
 	    tp->rx_opt.num_sacks || tp->rx_opt.dsack)
 		return -1;
 
-	/* Very simple search strategy: just double the MSS. */
+	/* Use binary search for probe_size between tcp_mss_base,
+	 * and current mss_clamp. if (search_high - search_low)
+	 * smaller than a threshold, backoff from probing.
+	 */
 	mss_now = tcp_current_mss(sk);
-	probe_size = 2 * tp->mss_cache;
+	probe_size = tcp_mtu_to_mss(sk, (icsk->icsk_mtup.search_high +
+				    icsk->icsk_mtup.search_low) >> 1);
 	size_needed = probe_size + (tp->reordering + 1) * tp->mss_cache;
-	if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high)) {
-		/* TODO: set timer for probe_converge_event */
+	interval = icsk->icsk_mtup.search_high - icsk->icsk_mtup.search_low;
+	/* When misfortune happens, we are reprobing actively,
+	 * and then reprobe timer has expired. We stick with current
+	 * probing process by not resetting search range to its orignal.
+	 */
+	if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high) ||
+		interval < net->ipv4.sysctl_tcp_probe_threshold) {
+		/* Check whether enough time has elaplased for
+		 * another round of probing.
+		 */
+		tcp_mtu_check_reprobe(sk);
 		return -1;
 	}
 
@@ -1850,7 +1941,8 @@ static int tcp_mtu_probe(struct sock *sk)
 	}
 
 	/* We're allowed to probe.  Build it now. */
-	if ((nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC)) == NULL)
+	nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC);
+	if (!nskb)
 		return -1;
 	sk->sk_wmem_queued += nskb->truesize;
 	sk_mem_charge(sk, nskb->truesize);
@@ -1946,6 +2038,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 	int cwnd_quota;
 	int result;
 	bool is_cwnd_limited = false;
+	u32 max_segs;
 
 	sent_pkts = 0;
 
@@ -1959,6 +2052,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		}
 	}
 
+	max_segs = tcp_tso_autosize(sk, mss_now);
 	while ((skb = tcp_send_head(sk))) {
 		unsigned int limit;
 
@@ -1984,17 +2078,30 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now)))
 			break;
 
-		if (tso_segs == 1) {
+		if (tso_segs == 1 || !max_segs) {
 			if (unlikely(!tcp_nagle_test(tp, skb, mss_now,
 						     (tcp_skb_is_last(sk, skb) ?
 						      nonagle : TCP_NAGLE_PUSH))))
 				break;
 		} else {
 			if (!push_one &&
-			    tcp_tso_should_defer(sk, skb, &is_cwnd_limited))
+			    tcp_tso_should_defer(sk, skb, &is_cwnd_limited,
+						 max_segs))
 				break;
 		}
 
+		limit = mss_now;
+		if (tso_segs > 1 && max_segs && !tcp_urg_mode(tp))
+			limit = tcp_mss_split_point(sk, skb, mss_now,
+						    min_t(unsigned int,
+							  cwnd_quota,
+							  max_segs),
+						    nonagle);
+
+		if (skb->len > limit &&
+		    unlikely(tso_fragment(sk, skb, limit, mss_now, gfp)))
+			break;
+
 		/* TCP Small Queues :
 		 * Control number of packets in qdisc/devices to two packets / or ~1 ms.
 		 * This allows for :
@@ -2005,8 +2112,8 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		 * of queued bytes to ensure line rate.
 		 * One example is wifi aggregation (802.11 AMPDU)
 		 */
-		limit = max_t(unsigned int, sysctl_tcp_limit_output_bytes,
-			      sk->sk_pacing_rate >> 10);
+		limit = max(2 * skb->truesize, sk->sk_pacing_rate >> 10);
+		limit = min_t(u32, limit, sysctl_tcp_limit_output_bytes);
 
 		if (atomic_read(&sk->sk_wmem_alloc) > limit) {
 			set_bit(TSQ_THROTTLED, &tp->tsq_flags);
@@ -2019,18 +2126,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 				break;
 		}
 
-		limit = mss_now;
-		if (tso_segs > 1 && !tcp_urg_mode(tp))
-			limit = tcp_mss_split_point(sk, skb, mss_now,
-						    min_t(unsigned int,
-							  cwnd_quota,
-							  sk->sk_gso_max_segs),
-						    nonagle);
-
-		if (skb->len > limit &&
-		    unlikely(tso_fragment(sk, skb, limit, mss_now, gfp)))
-			break;
-
 		if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp)))
 			break;
 
@@ -2145,7 +2240,7 @@ void tcp_send_loss_probe(struct sock *sk)
 	int mss = tcp_current_mss(sk);
 	int err = -1;
 
-	if (tcp_send_head(sk) != NULL) {
+	if (tcp_send_head(sk)) {
 		err = tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC);
 		goto rearm_timer;
 	}
@@ -2655,7 +2750,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
 		if (skb == tcp_send_head(sk))
 			break;
 		/* we could do better than to assign each time */
-		if (hole == NULL)
+		if (!hole)
 			tp->retransmit_skb_hint = skb;
 
 		/* Assume this retransmit will generate
@@ -2679,7 +2774,7 @@ begin_fwd:
 			if (!tcp_can_forward_retransmit(sk))
 				break;
 			/* Backtrack if necessary to non-L'ed skb */
-			if (hole != NULL) {
+			if (hole) {
 				skb = hole;
 				hole = NULL;
 			}
@@ -2687,7 +2782,7 @@ begin_fwd:
 			goto begin_fwd;
 
 		} else if (!(sacked & TCPCB_LOST)) {
-			if (hole == NULL && !(sacked & (TCPCB_SACKED_RETRANS|TCPCB_SACKED_ACKED)))
+			if (!hole && !(sacked & (TCPCB_SACKED_RETRANS|TCPCB_SACKED_ACKED)))
 				hole = skb;
 			continue;
 
@@ -2717,43 +2812,65 @@ begin_fwd:
 	}
 }
 
-/* Send a fin.  The caller locks the socket for us.  This cannot be
- * allowed to fail queueing a FIN frame under any circumstances.
+/* We allow to exceed memory limits for FIN packets to expedite
+ * connection tear down and (memory) recovery.
+ * Otherwise tcp_send_fin() could be tempted to either delay FIN
+ * or even be forced to close flow without any FIN.
+ */
+static void sk_forced_wmem_schedule(struct sock *sk, int size)
+{
+	int amt, status;
+
+	if (size <= sk->sk_forward_alloc)
+		return;
+	amt = sk_mem_pages(size);
+	sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
+	sk_memory_allocated_add(sk, amt, &status);
+}
+
+/* Send a FIN. The caller locks the socket for us.
+ * We should try to send a FIN packet really hard, but eventually give up.
  */
 void tcp_send_fin(struct sock *sk)
 {
+	struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct sk_buff *skb = tcp_write_queue_tail(sk);
-	int mss_now;
 
-	/* Optimization, tack on the FIN if we have a queue of
-	 * unsent frames.  But be careful about outgoing SACKS
-	 * and IP options.
+	/* Optimization, tack on the FIN if we have one skb in write queue and
+	 * this skb was not yet sent, or we are under memory pressure.
+	 * Note: in the latter case, FIN packet will be sent after a timeout,
+	 * as TCP stack thinks it has already been transmitted.
 	 */
-	mss_now = tcp_current_mss(sk);
-
-	if (tcp_send_head(sk) != NULL) {
-		TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_FIN;
-		TCP_SKB_CB(skb)->end_seq++;
+	if (tskb && (tcp_send_head(sk) || sk_under_memory_pressure(sk))) {
+coalesce:
+		TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN;
+		TCP_SKB_CB(tskb)->end_seq++;
 		tp->write_seq++;
+		if (!tcp_send_head(sk)) {
+			/* This means tskb was already sent.
+			 * Pretend we included the FIN on previous transmit.
+			 * We need to set tp->snd_nxt to the value it would have
+			 * if FIN had been sent. This is because retransmit path
+			 * does not change tp->snd_nxt.
+			 */
+			tp->snd_nxt++;
+			return;
+		}
 	} else {
-		/* Socket is locked, keep trying until memory is available. */
-		for (;;) {
-			skb = alloc_skb_fclone(MAX_TCP_HEADER,
-					       sk->sk_allocation);
-			if (skb)
-				break;
-			yield();
+		skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation);
+		if (unlikely(!skb)) {
+			if (tskb)
+				goto coalesce;
+			return;
 		}
-
-		/* Reserve space for headers and prepare control bits. */
 		skb_reserve(skb, MAX_TCP_HEADER);
+		sk_forced_wmem_schedule(sk, skb->truesize);
 		/* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
 		tcp_init_nondata_skb(skb, tp->write_seq,
 				     TCPHDR_ACK | TCPHDR_FIN);
 		tcp_queue_skb(sk, skb);
 	}
-	__tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_OFF);
+	__tcp_push_pending_frames(sk, tcp_current_mss(sk), TCP_NAGLE_OFF);
 }
 
 /* We get here when a process closes a file descriptor (either due to
@@ -2794,14 +2911,14 @@ int tcp_send_synack(struct sock *sk)
 	struct sk_buff *skb;
 
 	skb = tcp_write_queue_head(sk);
-	if (skb == NULL || !(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
+	if (!skb || !(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
 		pr_debug("%s: wrong queue state\n", __func__);
 		return -EFAULT;
 	}
 	if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK)) {
 		if (skb_cloned(skb)) {
 			struct sk_buff *nskb = skb_copy(skb, GFP_ATOMIC);
-			if (nskb == NULL)
+			if (!nskb)
 				return -ENOMEM;
 			tcp_unlink_write_queue(skb, sk);
 			__skb_header_release(nskb);
@@ -2836,7 +2953,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcphdr *th;
 	struct sk_buff *skb;
-	struct tcp_md5sig_key *md5;
+	struct tcp_md5sig_key *md5 = NULL;
 	int tcp_header_size;
 	int mss;
 
@@ -2849,7 +2966,6 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	skb_reserve(skb, MAX_TCP_HEADER);
 
 	skb_dst_set(skb, dst);
-	security_skb_owned_by(skb, sk);
 
 	mss = dst_metric_advmss(dst);
 	if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss)
@@ -2862,7 +2978,12 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	else
 #endif
 	skb_mstamp_get(&skb->skb_mstamp);
-	tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, &md5,
+
+#ifdef CONFIG_TCP_MD5SIG
+	rcu_read_lock();
+	md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req));
+#endif
+	tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5,
 					     foc) + sizeof(*th);
 
 	skb_push(skb, tcp_header_size);
@@ -2893,16 +3014,37 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 
 #ifdef CONFIG_TCP_MD5SIG
 	/* Okay, we have all we need - do the md5 hash if needed */
-	if (md5) {
+	if (md5)
 		tcp_rsk(req)->af_specific->calc_md5_hash(opts.hash_location,
-					       md5, NULL, req, skb);
-	}
+					       md5, req_to_sk(req), skb);
+	rcu_read_unlock();
 #endif
 
+	/* Do not fool tcpdump (if any), clean our debris */
+	skb->tstamp.tv64 = 0;
 	return skb;
 }
 EXPORT_SYMBOL(tcp_make_synack);
 
+static void tcp_ca_dst_init(struct sock *sk, const struct dst_entry *dst)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+	const struct tcp_congestion_ops *ca;
+	u32 ca_key = dst_metric(dst, RTAX_CC_ALGO);
+
+	if (ca_key == TCP_CA_UNSPEC)
+		return;
+
+	rcu_read_lock();
+	ca = tcp_ca_find_key(ca_key);
+	if (likely(ca && try_module_get(ca->owner))) {
+		module_put(icsk->icsk_ca_ops->owner);
+		icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst);
+		icsk->icsk_ca_ops = ca;
+	}
+	rcu_read_unlock();
+}
+
 /* Do all connect socket setups that can be done AF independent. */
 static void tcp_connect_init(struct sock *sk)
 {
@@ -2917,7 +3059,7 @@ static void tcp_connect_init(struct sock *sk)
 		(sysctl_tcp_timestamps ? TCPOLEN_TSTAMP_ALIGNED : 0);
 
 #ifdef CONFIG_TCP_MD5SIG
-	if (tp->af_specific->md5_lookup(sk, sk) != NULL)
+	if (tp->af_specific->md5_lookup(sk, sk))
 		tp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED;
 #endif
 
@@ -2928,6 +3070,8 @@ static void tcp_connect_init(struct sock *sk)
 	tcp_mtup_init(sk);
 	tcp_sync_mss(sk, dst_mtu(dst));
 
+	tcp_ca_dst_init(sk, dst);
+
 	if (!tp->window_clamp)
 		tp->window_clamp = dst_metric(dst, RTAX_WINDOW);
 	tp->advmss = dst_metric_advmss(dst);
@@ -2998,9 +3142,9 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_fastopen_request *fo = tp->fastopen_req;
-	int syn_loss = 0, space, i, err = 0, iovlen = fo->data->msg_iovlen;
-	struct sk_buff *syn_data = NULL, *data;
+	int syn_loss = 0, space, err = 0, copied;
 	unsigned long last_syn_loss = 0;
+	struct sk_buff *syn_data;
 
 	tp->rx_opt.mss_clamp = tp->advmss;  /* If MSS is not cached */
 	tcp_fastopen_cache_get(sk, &tp->rx_opt.mss_clamp, &fo->cookie,
@@ -3031,48 +3175,45 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 	/* 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)
+	syn_data = sk_stream_alloc_skb(sk, space, sk->sk_allocation);
+	if (!syn_data)
 		goto fallback;
+	syn_data->ip_summed = CHECKSUM_PARTIAL;
+	memcpy(syn_data->cb, syn->cb, sizeof(syn->cb));
+	copied = copy_from_iter(skb_put(syn_data, space), space,
+				&fo->data->msg_iter);
+	if (unlikely(!copied)) {
+		kfree_skb(syn_data);
+		goto fallback;
+	}
+	if (copied != space) {
+		skb_trim(syn_data, copied);
+		space = copied;
+	}
 
-	for (i = 0; i < iovlen && syn_data->len < space; ++i) {
-		struct iovec *iov = &fo->data->msg_iov[i];
-		unsigned char __user *from = iov->iov_base;
-		int len = iov->iov_len;
+	/* No more data pending in inet_wait_for_connect() */
+	if (space == fo->size)
+		fo->data = NULL;
+	fo->copied = space;
 
-		if (syn_data->len + len > space)
-			len = space - syn_data->len;
-		else if (i + 1 == iovlen)
-			/* No more data pending in inet_wait_for_connect() */
-			fo->data = NULL;
+	tcp_connect_queue_skb(sk, syn_data);
 
-		if (skb_add_data(syn_data, from, len))
-			goto fallback;
-	}
+	err = tcp_transmit_skb(sk, syn_data, 1, sk->sk_allocation);
 
-	/* Queue a data-only packet after the regular SYN for retransmission */
-	data = pskb_copy(syn_data, sk->sk_allocation);
-	if (data == NULL)
-		goto fallback;
-	TCP_SKB_CB(data)->seq++;
-	TCP_SKB_CB(data)->tcp_flags &= ~TCPHDR_SYN;
-	TCP_SKB_CB(data)->tcp_flags = (TCPHDR_ACK|TCPHDR_PSH);
-	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;
+	syn->skb_mstamp = syn_data->skb_mstamp;
 
-	if (tcp_transmit_skb(sk, syn_data, 0, sk->sk_allocation) == 0) {
+	/* Now full SYN+DATA was cloned and sent (or not),
+	 * remove the SYN from the original skb (syn_data)
+	 * we keep in write queue in case of a retransmit, as we
+	 * also have the SYN packet (with no data) in the same queue.
+	 */
+	TCP_SKB_CB(syn_data)->seq++;
+	TCP_SKB_CB(syn_data)->tcp_flags = TCPHDR_ACK | TCPHDR_PSH;
+	if (!err) {
 		tp->syn_data = (fo->copied > 0);
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT);
 		goto done;
 	}
-	syn_data = NULL;
 
 fallback:
 	/* Send a regular SYN with Fast Open cookie request option */
@@ -3081,7 +3222,6 @@ fallback:
 	err = tcp_transmit_skb(sk, syn, 1, sk->sk_allocation);
 	if (err)
 		tp->syn_fastopen = 0;
-	kfree_skb(syn_data);
 done:
 	fo->cookie.len = -1;  /* Exclude Fast Open option for SYN retries */
 	return err;
@@ -3101,13 +3241,10 @@ int tcp_connect(struct sock *sk)
 		return 0;
 	}
 
-	buff = alloc_skb_fclone(MAX_TCP_HEADER + 15, sk->sk_allocation);
-	if (unlikely(buff == NULL))
+	buff = sk_stream_alloc_skb(sk, 0, sk->sk_allocation);
+	if (unlikely(!buff))
 		return -ENOBUFS;
 
-	/* Reserve space for headers. */
-	skb_reserve(buff, MAX_TCP_HEADER);
-
 	tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN);
 	tp->retrans_stamp = tcp_time_stamp;
 	tcp_connect_queue_skb(sk, buff);
@@ -3208,7 +3345,7 @@ void tcp_send_ack(struct sock *sk)
 	 * sock.
 	 */
 	buff = alloc_skb(MAX_TCP_HEADER, sk_gfp_atomic(sk, GFP_ATOMIC));
-	if (buff == NULL) {
+	if (!buff) {
 		inet_csk_schedule_ack(sk);
 		inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN;
 		inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
@@ -3220,6 +3357,14 @@ void tcp_send_ack(struct sock *sk)
 	skb_reserve(buff, MAX_TCP_HEADER);
 	tcp_init_nondata_skb(buff, tcp_acceptable_seq(sk), TCPHDR_ACK);
 
+	/* We do not want pure acks influencing TCP Small Queues or fq/pacing
+	 * too much.
+	 * SKB_TRUESIZE(max(1 .. 66, MAX_TCP_HEADER)) is unfortunately ~784
+	 * We also avoid tcp_wfree() overhead (cache line miss accessing
+	 * tp->tsq_flags) by using regular sock_wfree()
+	 */
+	skb_set_tcp_pure_ack(buff);
+
 	/* Send it off, this clears delayed acks for us. */
 	skb_mstamp_get(&buff->skb_mstamp);
 	tcp_transmit_skb(sk, buff, 0, sk_gfp_atomic(sk, GFP_ATOMIC));
@@ -3244,7 +3389,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent)
 
 	/* We don't queue it, tcp_transmit_skb() sets ownership. */
 	skb = alloc_skb(MAX_TCP_HEADER, sk_gfp_atomic(sk, GFP_ATOMIC));
-	if (skb == NULL)
+	if (!skb)
 		return -1;
 
 	/* Reserve space for headers and set control bits. */
@@ -3275,8 +3420,8 @@ int tcp_write_wakeup(struct sock *sk)
 	if (sk->sk_state == TCP_CLOSE)
 		return -1;
 
-	if ((skb = tcp_send_head(sk)) != NULL &&
-	    before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp))) {
+	skb = tcp_send_head(sk);
+	if (skb && before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp))) {
 		int err;
 		unsigned int mss = tcp_current_mss(sk);
 		unsigned int seg_size = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq;
diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c
index 6824afb65d93..333bcb2415ff 100644
--- a/net/ipv4/tcp_scalable.c
+++ b/net/ipv4/tcp_scalable.c
@@ -25,7 +25,8 @@ static void tcp_scalable_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 	if (tp->snd_cwnd <= tp->snd_ssthresh)
 		tcp_slow_start(tp, acked);
 	else
-		tcp_cong_avoid_ai(tp, min(tp->snd_cwnd, TCP_SCALABLE_AI_CNT));
+		tcp_cong_avoid_ai(tp, min(tp->snd_cwnd, TCP_SCALABLE_AI_CNT),
+				  1);
 }
 
 static u32 tcp_scalable_ssthresh(struct sock *sk)
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 9b21ae8b2e31..8c65dc147d8b 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -101,17 +101,21 @@ static int tcp_orphan_retries(struct sock *sk, int alive)
 
 static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk)
 {
+	struct net *net = sock_net(sk);
+
 	/* Black hole detection */
-	if (sysctl_tcp_mtu_probing) {
+	if (net->ipv4.sysctl_tcp_mtu_probing) {
 		if (!icsk->icsk_mtup.enabled) {
 			icsk->icsk_mtup.enabled = 1;
+			icsk->icsk_mtup.probe_timestamp = tcp_time_stamp;
 			tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
 		} else {
+			struct net *net = sock_net(sk);
 			struct tcp_sock *tp = tcp_sk(sk);
 			int mss;
 
 			mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1;
-			mss = min(sysctl_tcp_base_mss, mss);
+			mss = min(net->ipv4.sysctl_tcp_base_mss, mss);
 			mss = max(mss, 68 - tp->tcp_header_len);
 			icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss);
 			tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
@@ -163,7 +167,7 @@ static int tcp_write_timeout(struct sock *sk)
 		if (icsk->icsk_retransmits) {
 			dst_negative_advice(sk);
 			if (tp->syn_fastopen || tp->syn_data)
-				tcp_fastopen_cache_set(sk, 0, NULL, true);
+				tcp_fastopen_cache_set(sk, 0, NULL, true, 0);
 			if (tp->syn_data)
 				NET_INC_STATS_BH(sock_net(sk),
 						 LINUX_MIB_TCPFASTOPENACTIVEFAIL);
@@ -323,7 +327,7 @@ static void tcp_fastopen_synack_timer(struct sock *sk)
 	struct request_sock *req;
 
 	req = tcp_sk(sk)->fastopen_rsk;
-	req->rsk_ops->syn_ack_timeout(sk, req);
+	req->rsk_ops->syn_ack_timeout(req);
 
 	if (req->num_timeout >= max_retries) {
 		tcp_write_err(sk);
@@ -374,17 +378,19 @@ void tcp_retransmit_timer(struct sock *sk)
 		 */
 		struct inet_sock *inet = inet_sk(sk);
 		if (sk->sk_family == AF_INET) {
-			LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("Peer %pI4:%u/%u unexpectedly shrunk window %u:%u (repaired)\n"),
-				       &inet->inet_daddr,
-				       ntohs(inet->inet_dport), inet->inet_num,
-				       tp->snd_una, tp->snd_nxt);
+			net_dbg_ratelimited("Peer %pI4:%u/%u unexpectedly shrunk window %u:%u (repaired)\n",
+					    &inet->inet_daddr,
+					    ntohs(inet->inet_dport),
+					    inet->inet_num,
+					    tp->snd_una, tp->snd_nxt);
 		}
 #if IS_ENABLED(CONFIG_IPV6)
 		else if (sk->sk_family == AF_INET6) {
-			LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n"),
-				       &sk->sk_v6_daddr,
-				       ntohs(inet->inet_dport), inet->inet_num,
-				       tp->snd_una, tp->snd_nxt);
+			net_dbg_ratelimited("Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n",
+					    &sk->sk_v6_daddr,
+					    ntohs(inet->inet_dport),
+					    inet->inet_num,
+					    tp->snd_una, tp->snd_nxt);
 		}
 #endif
 		if (tcp_time_stamp - tp->rcv_tstamp > TCP_RTO_MAX) {
@@ -533,19 +539,11 @@ static void tcp_write_timer(unsigned long data)
 	sock_put(sk);
 }
 
-/*
- *	Timer for listening sockets
- */
-
-static void tcp_synack_timer(struct sock *sk)
+void tcp_syn_ack_timeout(const struct request_sock *req)
 {
-	inet_csk_reqsk_queue_prune(sk, TCP_SYNQ_INTERVAL,
-				   TCP_TIMEOUT_INIT, TCP_RTO_MAX);
-}
+	struct net *net = read_pnet(&inet_rsk(req)->ireq_net);
 
-void tcp_syn_ack_timeout(struct sock *sk, struct request_sock *req)
-{
-	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPTIMEOUTS);
+	NET_INC_STATS_BH(net, LINUX_MIB_TCPTIMEOUTS);
 }
 EXPORT_SYMBOL(tcp_syn_ack_timeout);
 
@@ -577,7 +575,7 @@ static void tcp_keepalive_timer (unsigned long data)
 	}
 
 	if (sk->sk_state == TCP_LISTEN) {
-		tcp_synack_timer(sk);
+		pr_err("Hmm... keepalive on a LISTEN ???\n");
 		goto out;
 	}
 
diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c
index a6afde666ab1..a6cea1d5e20d 100644
--- a/net/ipv4/tcp_vegas.c
+++ b/net/ipv4/tcp_vegas.c
@@ -286,19 +286,21 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 }
 
 /* Extract info for Tcp socket info provided via netlink. */
-void tcp_vegas_get_info(struct sock *sk, u32 ext, struct sk_buff *skb)
+size_t tcp_vegas_get_info(struct sock *sk, u32 ext, int *attr,
+			  union tcp_cc_info *info)
 {
 	const struct vegas *ca = inet_csk_ca(sk);
+
 	if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
-		struct tcpvegas_info info = {
-			.tcpv_enabled = ca->doing_vegas_now,
-			.tcpv_rttcnt = ca->cntRTT,
-			.tcpv_rtt = ca->baseRTT,
-			.tcpv_minrtt = ca->minRTT,
-		};
-
-		nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info);
+		info->vegas.tcpv_enabled = ca->doing_vegas_now,
+		info->vegas.tcpv_rttcnt = ca->cntRTT,
+		info->vegas.tcpv_rtt = ca->baseRTT,
+		info->vegas.tcpv_minrtt = ca->minRTT,
+
+		*attr = INET_DIAG_VEGASINFO;
+		return sizeof(struct tcpvegas_info);
 	}
+	return 0;
 }
 EXPORT_SYMBOL_GPL(tcp_vegas_get_info);
 
diff --git a/net/ipv4/tcp_vegas.h b/net/ipv4/tcp_vegas.h
index 0531b99d8637..ef9da5306c68 100644
--- a/net/ipv4/tcp_vegas.h
+++ b/net/ipv4/tcp_vegas.h
@@ -19,6 +19,7 @@ void tcp_vegas_init(struct sock *sk);
 void tcp_vegas_state(struct sock *sk, u8 ca_state);
 void tcp_vegas_pkts_acked(struct sock *sk, u32 cnt, s32 rtt_us);
 void tcp_vegas_cwnd_event(struct sock *sk, enum tcp_ca_event event);
-void tcp_vegas_get_info(struct sock *sk, u32 ext, struct sk_buff *skb);
+size_t tcp_vegas_get_info(struct sock *sk, u32 ext, int *attr,
+			  union tcp_cc_info *info);
 
 #endif	/* __TCP_VEGAS_H */
diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c
index a4d2d2d88dca..112151eeee45 100644
--- a/net/ipv4/tcp_veno.c
+++ b/net/ipv4/tcp_veno.c
@@ -159,7 +159,7 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 				/* In the "non-congestive state", increase cwnd
 				 *  every rtt.
 				 */
-				tcp_cong_avoid_ai(tp, tp->snd_cwnd);
+				tcp_cong_avoid_ai(tp, tp->snd_cwnd, 1);
 			} else {
 				/* In the "congestive state", increase cwnd
 				 * every other rtt.
diff --git a/net/ipv4/tcp_westwood.c b/net/ipv4/tcp_westwood.c
index bb63fba47d47..c10732e39837 100644
--- a/net/ipv4/tcp_westwood.c
+++ b/net/ipv4/tcp_westwood.c
@@ -256,20 +256,21 @@ static void tcp_westwood_event(struct sock *sk, enum tcp_ca_event event)
 }
 
 /* Extract info for Tcp socket info provided via netlink. */
-static void tcp_westwood_info(struct sock *sk, u32 ext,
-			      struct sk_buff *skb)
+static size_t tcp_westwood_info(struct sock *sk, u32 ext, int *attr,
+				union tcp_cc_info *info)
 {
 	const struct westwood *ca = inet_csk_ca(sk);
 
 	if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
-		struct tcpvegas_info info = {
-			.tcpv_enabled = 1,
-			.tcpv_rtt = jiffies_to_usecs(ca->rtt),
-			.tcpv_minrtt = jiffies_to_usecs(ca->rtt_min),
-		};
+		info->vegas.tcpv_enabled = 1;
+		info->vegas.tcpv_rttcnt	= 0;
+		info->vegas.tcpv_rtt	= jiffies_to_usecs(ca->rtt),
+		info->vegas.tcpv_minrtt	= jiffies_to_usecs(ca->rtt_min),
 
-		nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info);
+		*attr = INET_DIAG_VEGASINFO;
+		return sizeof(struct tcpvegas_info);
 	}
+	return 0;
 }
 
 static struct tcp_congestion_ops tcp_westwood __read_mostly = {
diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index cd7273218598..17d35662930d 100644
--- a/net/ipv4/tcp_yeah.c
+++ b/net/ipv4/tcp_yeah.c
@@ -92,7 +92,7 @@ static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 
 	} else {
 		/* Reno */
-		tcp_cong_avoid_ai(tp, tp->snd_cwnd);
+		tcp_cong_avoid_ai(tp, tp->snd_cwnd, 1);
 	}
 
 	/* The key players are v_vegas.beg_snd_una and v_beg_snd_nxt.
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index cd0db5471bb5..83aa604f9273 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -90,6 +90,7 @@
 #include <linux/socket.h>
 #include <linux/sockios.h>
 #include <linux/igmp.h>
+#include <linux/inetdevice.h>
 #include <linux/in.h>
 #include <linux/errno.h>
 #include <linux/timer.h>
@@ -144,7 +145,7 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num,
 	struct hlist_nulls_node *node;
 	kuid_t uid = sock_i_uid(sk);
 
-	sk_nulls_for_each(sk2, node, &hslot->head)
+	sk_nulls_for_each(sk2, node, &hslot->head) {
 		if (net_eq(sock_net(sk2), net) &&
 		    sk2 != sk &&
 		    (bitmap || udp_sk(sk2)->udp_port_hash == num) &&
@@ -152,14 +153,13 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num,
 		    (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if ||
 		     sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
 		    (!sk2->sk_reuseport || !sk->sk_reuseport ||
-		      !uid_eq(uid, sock_i_uid(sk2))) &&
-		    (*saddr_comp)(sk, sk2)) {
-			if (bitmap)
-				__set_bit(udp_sk(sk2)->udp_port_hash >> log,
-					  bitmap);
-			else
+		     !uid_eq(uid, sock_i_uid(sk2))) &&
+		    saddr_comp(sk, sk2)) {
+			if (!bitmap)
 				return 1;
+			__set_bit(udp_sk(sk2)->udp_port_hash >> log, bitmap);
 		}
+	}
 	return 0;
 }
 
@@ -168,10 +168,10 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num,
  * can insert/delete a socket with local_port == num
  */
 static int udp_lib_lport_inuse2(struct net *net, __u16 num,
-			       struct udp_hslot *hslot2,
-			       struct sock *sk,
-			       int (*saddr_comp)(const struct sock *sk1,
-						 const struct sock *sk2))
+				struct udp_hslot *hslot2,
+				struct sock *sk,
+				int (*saddr_comp)(const struct sock *sk1,
+						  const struct sock *sk2))
 {
 	struct sock *sk2;
 	struct hlist_nulls_node *node;
@@ -179,7 +179,7 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num,
 	int res = 0;
 
 	spin_lock(&hslot2->lock);
-	udp_portaddr_for_each_entry(sk2, node, &hslot2->head)
+	udp_portaddr_for_each_entry(sk2, node, &hslot2->head) {
 		if (net_eq(sock_net(sk2), net) &&
 		    sk2 != sk &&
 		    (udp_sk(sk2)->udp_port_hash == num) &&
@@ -187,11 +187,12 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num,
 		    (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if ||
 		     sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
 		    (!sk2->sk_reuseport || !sk->sk_reuseport ||
-		      !uid_eq(uid, sock_i_uid(sk2))) &&
-		    (*saddr_comp)(sk, sk2)) {
+		     !uid_eq(uid, sock_i_uid(sk2))) &&
+		    saddr_comp(sk, sk2)) {
 			res = 1;
 			break;
 		}
+	}
 	spin_unlock(&hslot2->lock);
 	return res;
 }
@@ -206,8 +207,8 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num,
  *                   with NULL address
  */
 int udp_lib_get_port(struct sock *sk, unsigned short snum,
-		       int (*saddr_comp)(const struct sock *sk1,
-					 const struct sock *sk2),
+		     int (*saddr_comp)(const struct sock *sk1,
+				       const struct sock *sk2),
 		     unsigned int hash2_nulladdr)
 {
 	struct udp_hslot *hslot, *hslot2;
@@ -318,8 +319,8 @@ static int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2)
 		   inet1->inet_rcv_saddr == inet2->inet_rcv_saddr));
 }
 
-static unsigned int udp4_portaddr_hash(struct net *net, __be32 saddr,
-				       unsigned int port)
+static u32 udp4_portaddr_hash(const struct net *net, __be32 saddr,
+			      unsigned int port)
 {
 	return jhash_1word((__force u32)saddr, net_hash_mix(net)) ^ port;
 }
@@ -336,38 +337,45 @@ int udp_v4_get_port(struct sock *sk, unsigned short snum)
 	return udp_lib_get_port(sk, snum, ipv4_rcv_saddr_equal, hash2_nulladdr);
 }
 
-static inline int compute_score(struct sock *sk, struct net *net, __be32 saddr,
-			 unsigned short hnum,
-			 __be16 sport, __be32 daddr, __be16 dport, int dif)
+static inline int compute_score(struct sock *sk, struct net *net,
+				__be32 saddr, unsigned short hnum, __be16 sport,
+				__be32 daddr, __be16 dport, int dif)
 {
-	int score = -1;
+	int score;
+	struct inet_sock *inet;
 
-	if (net_eq(sock_net(sk), net) && udp_sk(sk)->udp_port_hash == hnum &&
-			!ipv6_only_sock(sk)) {
-		struct inet_sock *inet = inet_sk(sk);
+	if (!net_eq(sock_net(sk), net) ||
+	    udp_sk(sk)->udp_port_hash != hnum ||
+	    ipv6_only_sock(sk))
+		return -1;
 
-		score = (sk->sk_family == PF_INET ? 2 : 1);
-		if (inet->inet_rcv_saddr) {
-			if (inet->inet_rcv_saddr != daddr)
-				return -1;
-			score += 4;
-		}
-		if (inet->inet_daddr) {
-			if (inet->inet_daddr != saddr)
-				return -1;
-			score += 4;
-		}
-		if (inet->inet_dport) {
-			if (inet->inet_dport != sport)
-				return -1;
-			score += 4;
-		}
-		if (sk->sk_bound_dev_if) {
-			if (sk->sk_bound_dev_if != dif)
-				return -1;
-			score += 4;
-		}
+	score = (sk->sk_family == PF_INET) ? 2 : 1;
+	inet = inet_sk(sk);
+
+	if (inet->inet_rcv_saddr) {
+		if (inet->inet_rcv_saddr != daddr)
+			return -1;
+		score += 4;
 	}
+
+	if (inet->inet_daddr) {
+		if (inet->inet_daddr != saddr)
+			return -1;
+		score += 4;
+	}
+
+	if (inet->inet_dport) {
+		if (inet->inet_dport != sport)
+			return -1;
+		score += 4;
+	}
+
+	if (sk->sk_bound_dev_if) {
+		if (sk->sk_bound_dev_if != dif)
+			return -1;
+		score += 4;
+	}
+
 	return score;
 }
 
@@ -378,39 +386,45 @@ static inline int compute_score2(struct sock *sk, struct net *net,
 				 __be32 saddr, __be16 sport,
 				 __be32 daddr, unsigned int hnum, int dif)
 {
-	int score = -1;
+	int score;
+	struct inet_sock *inet;
+
+	if (!net_eq(sock_net(sk), net) ||
+	    ipv6_only_sock(sk))
+		return -1;
 
-	if (net_eq(sock_net(sk), net) && !ipv6_only_sock(sk)) {
-		struct inet_sock *inet = inet_sk(sk);
+	inet = inet_sk(sk);
 
-		if (inet->inet_rcv_saddr != daddr)
+	if (inet->inet_rcv_saddr != daddr ||
+	    inet->inet_num != hnum)
+		return -1;
+
+	score = (sk->sk_family == PF_INET) ? 2 : 1;
+
+	if (inet->inet_daddr) {
+		if (inet->inet_daddr != saddr)
 			return -1;
-		if (inet->inet_num != hnum)
+		score += 4;
+	}
+
+	if (inet->inet_dport) {
+		if (inet->inet_dport != sport)
 			return -1;
+		score += 4;
+	}
 
-		score = (sk->sk_family == PF_INET ? 2 : 1);
-		if (inet->inet_daddr) {
-			if (inet->inet_daddr != saddr)
-				return -1;
-			score += 4;
-		}
-		if (inet->inet_dport) {
-			if (inet->inet_dport != sport)
-				return -1;
-			score += 4;
-		}
-		if (sk->sk_bound_dev_if) {
-			if (sk->sk_bound_dev_if != dif)
-				return -1;
-			score += 4;
-		}
+	if (sk->sk_bound_dev_if) {
+		if (sk->sk_bound_dev_if != dif)
+			return -1;
+		score += 4;
 	}
+
 	return score;
 }
 
-static unsigned int udp_ehashfn(struct net *net, const __be32 laddr,
-				 const __u16 lport, const __be32 faddr,
-				 const __be16 fport)
+static u32 udp_ehashfn(const struct net *net, const __be32 laddr,
+		       const __u16 lport, const __be32 faddr,
+		       const __be16 fport)
 {
 	static u32 udp_ehash_secret __read_mostly;
 
@@ -420,7 +434,6 @@ static unsigned int udp_ehashfn(struct net *net, const __be32 laddr,
 			      udp_ehash_secret + net_hash_mix(net));
 }
 
-
 /* called with read_rcu_lock() */
 static struct sock *udp4_lib_lookup2(struct net *net,
 		__be32 saddr, __be16 sport,
@@ -620,7 +633,7 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
 
 	sk = __udp4_lib_lookup(net, iph->daddr, uh->dest,
 			iph->saddr, uh->source, skb->dev->ifindex, udptable);
-	if (sk == NULL) {
+	if (!sk) {
 		ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS);
 		return;	/* No socket for error */
 	}
@@ -860,8 +873,7 @@ out:
 }
 EXPORT_SYMBOL(udp_push_pending_frames);
 
-int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
-		size_t len)
+int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct udp_sock *up = udp_sk(sk);
@@ -999,7 +1011,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	if (connected)
 		rt = (struct rtable *)sk_dst_check(sk, 0);
 
-	if (rt == NULL) {
+	if (!rt) {
 		struct net *net = sock_net(sk);
 
 		fl4 = &fl4_stack;
@@ -1036,7 +1048,7 @@ back_from_confirm:
 
 	/* Lockless fast path for the non-corking case. */
 	if (!corkreq) {
-		skb = ip_make_skb(sk, fl4, getfrag, msg->msg_iov, ulen,
+		skb = ip_make_skb(sk, fl4, getfrag, msg, ulen,
 				  sizeof(struct udphdr), &ipc, &rt,
 				  msg->msg_flags);
 		err = PTR_ERR(skb);
@@ -1051,7 +1063,7 @@ back_from_confirm:
 		/* ... which is an evident application bug. --ANK */
 		release_sock(sk);
 
-		LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("cork app bug 2\n"));
+		net_dbg_ratelimited("cork app bug 2\n");
 		err = -EINVAL;
 		goto out;
 	}
@@ -1067,7 +1079,7 @@ back_from_confirm:
 
 do_append_data:
 	up->len += ulen;
-	err = ip_append_data(sk, fl4, getfrag, msg->msg_iov, ulen,
+	err = ip_append_data(sk, fl4, getfrag, msg, ulen,
 			     sizeof(struct udphdr), &ipc, &rt,
 			     corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags);
 	if (err)
@@ -1123,7 +1135,7 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset,
 		 * sendpage interface can't pass.
 		 * This will succeed only when the socket is connected.
 		 */
-		ret = udp_sendmsg(NULL, sk, &msg, 0);
+		ret = udp_sendmsg(sk, &msg, 0);
 		if (ret < 0)
 			return ret;
 	}
@@ -1133,7 +1145,7 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset,
 	if (unlikely(!up->pending)) {
 		release_sock(sk);
 
-		LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("udp cork app bug 3\n"));
+		net_dbg_ratelimited("udp cork app bug 3\n");
 		return -EINVAL;
 	}
 
@@ -1159,7 +1171,6 @@ out:
 	return ret;
 }
 
-
 /**
  *	first_packet_length	- return length of first packet in receive queue
  *	@sk: socket
@@ -1241,8 +1252,8 @@ EXPORT_SYMBOL(udp_ioctl);
  * 	return it, otherwise we block.
  */
 
-int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
-		size_t len, int noblock, int flags, int *addr_len)
+int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
+		int flags, int *addr_len)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name);
@@ -1281,12 +1292,11 @@ try_again:
 	}
 
 	if (skb_csum_unnecessary(skb))
-		err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr),
-					      msg->msg_iov, copied);
+		err = skb_copy_datagram_msg(skb, sizeof(struct udphdr),
+					    msg, copied);
 	else {
-		err = skb_copy_and_csum_datagram_iovec(skb,
-						       sizeof(struct udphdr),
-						       msg->msg_iov);
+		err = skb_copy_and_csum_datagram_msg(skb, sizeof(struct udphdr),
+						     msg);
 
 		if (err == -EINVAL)
 			goto csum_copy_err;
@@ -1317,7 +1327,7 @@ try_again:
 		*addr_len = sizeof(*sin);
 	}
 	if (inet->cmsg_flags)
-		ip_cmsg_recv(msg, skb);
+		ip_cmsg_recv_offset(msg, skb, sizeof(struct udphdr));
 
 	err = copied;
 	if (flags & MSG_TRUNC)
@@ -1336,15 +1346,12 @@ csum_copy_err:
 	}
 	unlock_sock_fast(sk, slow);
 
-	if (noblock)
-		return -EAGAIN;
-
-	/* starting over for a new packet */
+	/* starting over for a new packet, but check if we need to yield */
+	cond_resched();
 	msg->msg_flags &= ~MSG_TRUNC;
 	goto try_again;
 }
 
-
 int udp_disconnect(struct sock *sk, int flags)
 {
 	struct inet_sock *inet = inet_sk(sk);
@@ -1445,6 +1452,7 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	if (inet_sk(sk)->inet_daddr) {
 		sock_rps_save_rxhash(sk, skb);
 		sk_mark_napi_id(sk, skb);
+		sk_incoming_cpu_update(sk);
 	}
 
 	rc = sock_queue_rcv_skb(sk, skb);
@@ -1510,7 +1518,7 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 
 		/* if we're overly short, let UDP handle it */
 		encap_rcv = ACCESS_ONCE(up->encap_rcv);
-		if (skb->len > sizeof(struct udphdr) && encap_rcv != NULL) {
+		if (skb->len > sizeof(struct udphdr) && encap_rcv) {
 			int ret;
 
 			/* Verify checksum before giving to encap */
@@ -1546,8 +1554,8 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		 * provided by the application."
 		 */
 		if (up->pcrlen == 0) {          /* full coverage was set  */
-			LIMIT_NETDEBUG(KERN_WARNING "UDPLite: partial coverage %d while full coverage %d requested\n",
-				       UDP_SKB_CB(skb)->cscov, skb->len);
+			net_dbg_ratelimited("UDPLite: partial coverage %d while full coverage %d requested\n",
+					    UDP_SKB_CB(skb)->cscov, skb->len);
 			goto drop;
 		}
 		/* The next case involves violating the min. coverage requested
@@ -1557,8 +1565,8 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		 * Therefore the above ...()->partial_cov statement is essential.
 		 */
 		if (UDP_SKB_CB(skb)->cscov  <  up->pcrlen) {
-			LIMIT_NETDEBUG(KERN_WARNING "UDPLite: coverage %d too small, need min %d\n",
-				       UDP_SKB_CB(skb)->cscov, up->pcrlen);
+			net_dbg_ratelimited("UDPLite: coverage %d too small, need min %d\n",
+					    UDP_SKB_CB(skb)->cscov, up->pcrlen);
 			goto drop;
 		}
 	}
@@ -1567,7 +1575,6 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	    udp_lib_checksum_complete(skb))
 		goto csum_error;
 
-
 	if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) {
 		UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS,
 				 is_udplite);
@@ -1597,7 +1604,6 @@ drop:
 	return -1;
 }
 
-
 static void flush_stack(struct sock **stack, unsigned int count,
 			struct sk_buff *skb, unsigned int final)
 {
@@ -1607,7 +1613,7 @@ static void flush_stack(struct sock **stack, unsigned int count,
 
 	for (i = 0; i < count; i++) {
 		sk = stack[i];
-		if (likely(skb1 == NULL))
+		if (likely(!skb1))
 			skb1 = (i == final) ? skb : skb_clone(skb, GFP_ATOMIC);
 
 		if (!skb1) {
@@ -1647,7 +1653,8 @@ static void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
 static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 				    struct udphdr  *uh,
 				    __be32 saddr, __be32 daddr,
-				    struct udp_table *udptable)
+				    struct udp_table *udptable,
+				    int proto)
 {
 	struct sock *sk, *stack[256 / sizeof(struct sock *)];
 	struct hlist_nulls_node *node;
@@ -1656,6 +1663,7 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 	int dif = skb->dev->ifindex;
 	unsigned int count = 0, offset = offsetof(typeof(*sk), sk_nulls_node);
 	unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10);
+	bool inner_flushed = false;
 
 	if (use_hash2) {
 		hash2_any = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum) &
@@ -1674,6 +1682,7 @@ start_lookup:
 					dif, hnum)) {
 			if (unlikely(count == ARRAY_SIZE(stack))) {
 				flush_stack(stack, count, skb, ~0);
+				inner_flushed = true;
 				count = 0;
 			}
 			stack[count++] = sk;
@@ -1695,7 +1704,10 @@ start_lookup:
 	if (count) {
 		flush_stack(stack, count, skb, count - 1);
 	} else {
-		kfree_skb(skb);
+		if (!inner_flushed)
+			UDP_INC_STATS_BH(net, UDP_MIB_IGNOREDMULTI,
+					 proto == IPPROTO_UDPLITE);
+		consume_skb(skb);
 	}
 	return 0;
 }
@@ -1777,18 +1789,17 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		if (ret > 0)
 			return -ret;
 		return 0;
-	} else {
-		if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST))
-			return __udp4_lib_mcast_deliver(net, skb, uh,
-					saddr, daddr, udptable);
-
-		sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
 	}
 
-	if (sk != NULL) {
+	if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST))
+		return __udp4_lib_mcast_deliver(net, skb, uh,
+						saddr, daddr, udptable, proto);
+
+	sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
+	if (sk) {
 		int ret;
 
-		if (udp_sk(sk)->convert_csum && uh->check && !IS_UDPLITE(sk))
+		if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk))
 			skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
 						 inet_compute_pseudo);
 
@@ -1822,11 +1833,11 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	return 0;
 
 short_packet:
-	LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: short packet: From %pI4:%u %d/%d to %pI4:%u\n",
-		       proto == IPPROTO_UDPLITE ? "Lite" : "",
-		       &saddr, ntohs(uh->source),
-		       ulen, skb->len,
-		       &daddr, ntohs(uh->dest));
+	net_dbg_ratelimited("UDP%s: short packet: From %pI4:%u %d/%d to %pI4:%u\n",
+			    proto == IPPROTO_UDPLITE ? "Lite" : "",
+			    &saddr, ntohs(uh->source),
+			    ulen, skb->len,
+			    &daddr, ntohs(uh->dest));
 	goto drop;
 
 csum_error:
@@ -1834,10 +1845,10 @@ csum_error:
 	 * RFC1122: OK.  Discards the bad packet silently (as far as
 	 * the network is concerned, anyway) as per 4.1.3.4 (MUST).
 	 */
-	LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: bad checksum. From %pI4:%u to %pI4:%u ulen %d\n",
-		       proto == IPPROTO_UDPLITE ? "Lite" : "",
-		       &saddr, ntohs(uh->source), &daddr, ntohs(uh->dest),
-		       ulen);
+	net_dbg_ratelimited("UDP%s: bad checksum. From %pI4:%u to %pI4:%u ulen %d\n",
+			    proto == IPPROTO_UDPLITE ? "Lite" : "",
+			    &saddr, ntohs(uh->source), &daddr, ntohs(uh->dest),
+			    ulen);
 	UDP_INC_STATS_BH(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE);
 drop:
 	UDP_INC_STATS_BH(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE);
@@ -1950,6 +1961,7 @@ void udp_v4_early_demux(struct sk_buff *skb)
 	struct sock *sk;
 	struct dst_entry *dst;
 	int dif = skb->dev->ifindex;
+	int ours;
 
 	/* validate the packet */
 	if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr)))
@@ -1959,14 +1971,24 @@ void udp_v4_early_demux(struct sk_buff *skb)
 	uh = udp_hdr(skb);
 
 	if (skb->pkt_type == PACKET_BROADCAST ||
-	    skb->pkt_type == PACKET_MULTICAST)
+	    skb->pkt_type == PACKET_MULTICAST) {
+		struct in_device *in_dev = __in_dev_get_rcu(skb->dev);
+
+		if (!in_dev)
+			return;
+
+		ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr,
+				       iph->protocol);
+		if (!ours)
+			return;
 		sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr,
 						   uh->source, iph->saddr, dif);
-	else if (skb->pkt_type == PACKET_HOST)
+	} else if (skb->pkt_type == PACKET_HOST) {
 		sk = __udp4_lib_demux_lookup(net, uh->dest, iph->daddr,
 					     uh->source, iph->saddr, dif);
-	else
+	} else {
 		return;
+	}
 
 	if (!sk)
 		return;
@@ -2027,7 +2049,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 		} else {
 			up->corkflag = 0;
 			lock_sock(sk);
-			(*push_pending_frames)(sk);
+			push_pending_frames(sk);
 			release_sock(sk);
 		}
 		break;
@@ -2507,6 +2529,16 @@ void __init udp_table_init(struct udp_table *table, const char *name)
 	}
 }
 
+u32 udp_flow_hashrnd(void)
+{
+	static u32 hashrnd __read_mostly;
+
+	net_get_random_once(&hashrnd, sizeof(hashrnd));
+
+	return hashrnd;
+}
+EXPORT_SYMBOL(udp_flow_hashrnd);
+
 void __init udp_init(void)
 {
 	unsigned long limit;
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index 7927db0a9279..b763c39ae1d7 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -18,8 +18,9 @@
 #include <linux/sock_diag.h>
 
 static int sk_diag_dump(struct sock *sk, struct sk_buff *skb,
-		struct netlink_callback *cb, struct inet_diag_req_v2 *req,
-		struct nlattr *bc)
+			struct netlink_callback *cb,
+			const struct inet_diag_req_v2 *req,
+			struct nlattr *bc)
 {
 	if (!inet_diag_bc_sk(bc, sk))
 		return 0;
@@ -31,7 +32,8 @@ static int sk_diag_dump(struct sock *sk, struct sk_buff *skb,
 }
 
 static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb,
-		const struct nlmsghdr *nlh, struct inet_diag_req_v2 *req)
+			const struct nlmsghdr *nlh,
+			const struct inet_diag_req_v2 *req)
 {
 	int err = -EINVAL;
 	struct sock *sk;
@@ -56,7 +58,7 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb,
 		goto out_nosk;
 
 	err = -ENOENT;
-	if (sk == NULL)
+	if (!sk)
 		goto out_nosk;
 
 	err = sock_diag_check_cookie(sk, req->id.idiag_cookie);
@@ -90,8 +92,9 @@ out_nosk:
 	return err;
 }
 
-static void udp_dump(struct udp_table *table, struct sk_buff *skb, struct netlink_callback *cb,
-		struct inet_diag_req_v2 *r, struct nlattr *bc)
+static void udp_dump(struct udp_table *table, struct sk_buff *skb,
+		     struct netlink_callback *cb,
+		     const struct inet_diag_req_v2 *r, struct nlattr *bc)
 {
 	int num, s_num, slot, s_slot;
 	struct net *net = sock_net(skb->sk);
@@ -99,11 +102,13 @@ static void udp_dump(struct udp_table *table, struct sk_buff *skb, struct netlin
 	s_slot = cb->args[0];
 	num = s_num = cb->args[1];
 
-	for (slot = s_slot; slot <= table->mask; num = s_num = 0, slot++) {
+	for (slot = s_slot; slot <= table->mask; s_num = 0, slot++) {
 		struct sock *sk;
 		struct hlist_nulls_node *node;
 		struct udp_hslot *hslot = &table->hash[slot];
 
+		num = 0;
+
 		if (hlist_nulls_empty(&hslot->head))
 			continue;
 
@@ -142,13 +147,13 @@ done:
 }
 
 static void udp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
-		struct inet_diag_req_v2 *r, struct nlattr *bc)
+			  const struct inet_diag_req_v2 *r, struct nlattr *bc)
 {
 	udp_dump(&udp_table, skb, cb, r, bc);
 }
 
 static int udp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh,
-		struct inet_diag_req_v2 *req)
+			     const struct inet_diag_req_v2 *req)
 {
 	return udp_dump_one(&udp_table, in_skb, nlh, req);
 }
@@ -168,13 +173,14 @@ static const struct inet_diag_handler udp_diag_handler = {
 };
 
 static void udplite_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
-		struct inet_diag_req_v2 *r, struct nlattr *bc)
+			      const struct inet_diag_req_v2 *r,
+			      struct nlattr *bc)
 {
 	udp_dump(&udplite_table, skb, cb, r, bc);
 }
 
 static int udplite_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh,
-		struct inet_diag_req_v2 *req)
+				 const struct inet_diag_req_v2 *req)
 {
 	return udp_dump_one(&udplite_table, in_skb, nlh, req);
 }
diff --git a/net/ipv4/udp_impl.h b/net/ipv4/udp_impl.h
index f3c27899f62b..7e0fe4bdd967 100644
--- a/net/ipv4/udp_impl.h
+++ b/net/ipv4/udp_impl.h
@@ -21,8 +21,8 @@ int compat_udp_setsockopt(struct sock *sk, int level, int optname,
 int compat_udp_getsockopt(struct sock *sk, int level, int optname,
 			  char __user *optval, int __user *optlen);
 #endif
-int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
-		size_t len, int noblock, int flags, int *addr_len);
+int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
+		int flags, int *addr_len);
 int udp_sendpage(struct sock *sk, struct page *page, int offset, size_t size,
 		 int flags);
 int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 6480cea7aa53..f9386160cbee 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -29,7 +29,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 	netdev_features_t features,
 	struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb,
 					     netdev_features_t features),
-	__be16 new_protocol)
+	__be16 new_protocol, bool is_ipv6)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	u16 mac_offset = skb->mac_header;
@@ -39,7 +39,10 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 	netdev_features_t enc_features;
 	int udp_offset, outer_hlen;
 	unsigned int oldlen;
-	bool need_csum;
+	bool need_csum = !!(skb_shinfo(skb)->gso_type &
+			    SKB_GSO_UDP_TUNNEL_CSUM);
+	bool remcsum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TUNNEL_REMCSUM);
+	bool offload_csum = false, dont_encap = (need_csum || remcsum);
 
 	oldlen = (u16)~skb->len;
 
@@ -52,10 +55,13 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 	skb_set_network_header(skb, skb_inner_network_offset(skb));
 	skb->mac_len = skb_inner_network_offset(skb);
 	skb->protocol = new_protocol;
+	skb->encap_hdr_csum = need_csum;
+	skb->remcsum_offload = remcsum;
 
-	need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM);
-	if (need_csum)
-		skb->encap_hdr_csum = 1;
+	/* Try to offload checksum if possible */
+	offload_csum = !!(need_csum &&
+			  (skb->dev->features &
+			   (is_ipv6 ? NETIF_F_V6_CSUM : NETIF_F_V4_CSUM)));
 
 	/* segment inner packet. */
 	enc_features = skb->dev->hw_enc_features & features;
@@ -72,11 +78,21 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 	do {
 		struct udphdr *uh;
 		int len;
-
-		skb_reset_inner_headers(skb);
-		skb->encapsulation = 1;
+		__be32 delta;
+
+		if (dont_encap) {
+			skb->encapsulation = 0;
+			skb->ip_summed = CHECKSUM_NONE;
+		} else {
+			/* Only set up inner headers if we might be offloading
+			 * inner checksum.
+			 */
+			skb_reset_inner_headers(skb);
+			skb->encapsulation = 1;
+		}
 
 		skb->mac_len = mac_len;
+		skb->protocol = protocol;
 
 		skb_push(skb, outer_hlen);
 		skb_reset_mac_header(skb);
@@ -86,19 +102,36 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 		uh = udp_hdr(skb);
 		uh->len = htons(len);
 
-		if (need_csum) {
-			__be32 delta = htonl(oldlen + len);
+		if (!need_csum)
+			continue;
 
-			uh->check = ~csum_fold((__force __wsum)
-					       ((__force u32)uh->check +
-						(__force u32)delta));
+		delta = htonl(oldlen + len);
+
+		uh->check = ~csum_fold((__force __wsum)
+				       ((__force u32)uh->check +
+					(__force u32)delta));
+		if (offload_csum) {
+			skb->ip_summed = CHECKSUM_PARTIAL;
+			skb->csum_start = skb_transport_header(skb) - skb->head;
+			skb->csum_offset = offsetof(struct udphdr, check);
+		} else if (remcsum) {
+			/* Need to calculate checksum from scratch,
+			 * inner checksums are never when doing
+			 * remote_checksum_offload.
+			 */
+
+			skb->csum = skb_checksum(skb, udp_offset,
+						 skb->len - udp_offset,
+						 0);
+			uh->check = csum_fold(skb->csum);
+			if (uh->check == 0)
+				uh->check = CSUM_MANGLED_0;
+		} else {
 			uh->check = gso_make_checksum(skb, ~uh->check);
 
 			if (uh->check == 0)
 				uh->check = CSUM_MANGLED_0;
 		}
-
-		skb->protocol = protocol;
 	} while ((skb = skb->next));
 out:
 	return segs;
@@ -134,7 +167,7 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
 	}
 
 	segs = __skb_udp_tunnel_segment(skb, features, gso_inner_segment,
-					protocol);
+					protocol, is_ipv6);
 
 out_unlock:
 	rcu_read_unlock();
@@ -172,9 +205,9 @@ 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_TUNNEL_REMCSUM |
 				      SKB_GSO_IPIP |
-				      SKB_GSO_GRE | SKB_GSO_GRE_CSUM |
-				      SKB_GSO_MPLS) ||
+				      SKB_GSO_GRE | SKB_GSO_GRE_CSUM) ||
 			     !(type & (SKB_GSO_UDP))))
 			goto out;
 
@@ -252,7 +285,7 @@ void udp_del_offload(struct udp_offload *uo)
 	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)
+	if (uo_priv)
 		call_rcu(&uo_priv->rcu, udp_offload_free_routine);
 }
 EXPORT_SYMBOL(udp_del_offload);
@@ -306,7 +339,8 @@ unflush:
 	skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */
 	skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));
 	NAPI_GRO_CB(skb)->proto = uo_priv->offload->ipproto;
-	pp = uo_priv->offload->callbacks.gro_receive(head, skb);
+	pp = uo_priv->offload->callbacks.gro_receive(head, skb,
+						     uo_priv->offload);
 
 out_unlock:
 	rcu_read_unlock();
@@ -360,12 +394,21 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff)
 			break;
 	}
 
-	if (uo_priv != NULL) {
+	if (uo_priv) {
 		NAPI_GRO_CB(skb)->proto = uo_priv->offload->ipproto;
-		err = uo_priv->offload->callbacks.gro_complete(skb, nhoff + sizeof(struct udphdr));
+		err = uo_priv->offload->callbacks.gro_complete(skb,
+				nhoff + sizeof(struct udphdr),
+				uo_priv->offload);
 	}
 
 	rcu_read_unlock();
+
+	if (skb->remcsum_offload)
+		skb_shinfo(skb)->gso_type |= SKB_GSO_TUNNEL_REMCSUM;
+
+	skb->encapsulation = 1;
+	skb_set_inner_mac_header(skb, nhoff + sizeof(struct udphdr));
+
 	return err;
 }
 
@@ -374,9 +417,13 @@ static int udp4_gro_complete(struct sk_buff *skb, int nhoff)
 	const struct iphdr *iph = ip_hdr(skb);
 	struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
 
-	if (uh->check)
+	if (uh->check) {
+		skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;
 		uh->check = ~udp_v4_check(skb->len - nhoff, iph->saddr,
 					  iph->daddr, 0);
+	} else {
+		skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL;
+	}
 
 	return udp_gro_complete(skb, nhoff);
 }
diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c
index 1671263e5fa0..6bb98cc193c9 100644
--- a/net/ipv4/udp_tunnel.c
+++ b/net/ipv4/udp_tunnel.c
@@ -63,7 +63,7 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
 	inet_sk(sk)->mc_loop = 0;
 
 	/* Enable CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE conversion */
-	udp_set_convert_csum(sk, true);
+	inet_inc_convert_csum(sk);
 
 	rcu_assign_sk_user_data(sk, cfg->sk_user_data);
 
@@ -75,10 +75,10 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
 }
 EXPORT_SYMBOL_GPL(setup_udp_tunnel_sock);
 
-int udp_tunnel_xmit_skb(struct socket *sock, struct rtable *rt,
-			struct sk_buff *skb, __be32 src, __be32 dst,
-			__u8 tos, __u8 ttl, __be16 df, __be16 src_port,
-			__be16 dst_port, bool xnet)
+int udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb,
+			__be32 src, __be32 dst, __u8 tos, __u8 ttl,
+			__be16 df, __be16 src_port, __be16 dst_port,
+			bool xnet, bool nocheck)
 {
 	struct udphdr *uh;
 
@@ -90,9 +90,9 @@ int udp_tunnel_xmit_skb(struct socket *sock, struct rtable *rt,
 	uh->source = src_port;
 	uh->len = htons(skb->len);
 
-	udp_set_csum(sock->sk->sk_no_check_tx, skb, src, dst, skb->len);
+	udp_set_csum(nocheck, skb, src, dst, skb->len);
 
-	return iptunnel_xmit(sock->sk, rt, skb, src, dst, IPPROTO_UDP,
+	return iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP,
 			     tos, ttl, df, xnet);
 }
 EXPORT_SYMBOL_GPL(udp_tunnel_xmit_skb);
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index aac6197b7a71..60b032f58ccc 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -22,9 +22,9 @@ int xfrm4_extract_input(struct xfrm_state *x, struct sk_buff *skb)
 	return xfrm4_extract_header(skb);
 }
 
-static inline int xfrm4_rcv_encap_finish(struct sk_buff *skb)
+static inline int xfrm4_rcv_encap_finish(struct sock *sk, struct sk_buff *skb)
 {
-	if (skb_dst(skb) == NULL) {
+	if (!skb_dst(skb)) {
 		const struct iphdr *iph = ip_hdr(skb);
 
 		if (ip_route_input_noref(skb, iph->daddr, iph->saddr,
@@ -52,7 +52,8 @@ int xfrm4_transport_finish(struct sk_buff *skb, int async)
 	iph->tot_len = htons(skb->len);
 	ip_send_check(iph);
 
-	NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, skb, skb->dev, NULL,
+	NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, NULL, skb,
+		skb->dev, NULL,
 		xfrm4_rcv_encap_finish);
 	return 0;
 }
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index 91771a7c802f..35feda676464 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -63,7 +63,7 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
 
 	top_iph->saddr = x->props.saddr.a4;
 	top_iph->daddr = x->id.daddr.a4;
-	ip_select_ident(skb, NULL);
+	ip_select_ident(dev_net(dst->dev), skb, NULL);
 
 	return 0;
 }
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index d5f6bd9a210a..2878dbfffeb7 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -63,40 +63,40 @@ int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
 		return err;
 
 	IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE;
+	skb->protocol = htons(ETH_P_IP);
 
 	return x->outer_mode->output2(x, skb);
 }
 EXPORT_SYMBOL(xfrm4_prepare_output);
 
-int xfrm4_output_finish(struct sk_buff *skb)
+int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb)
 {
 	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
-	skb->protocol = htons(ETH_P_IP);
 
 #ifdef CONFIG_NETFILTER
 	IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED;
 #endif
 
-	return xfrm_output(skb);
+	return xfrm_output(sk, skb);
 }
 
-static int __xfrm4_output(struct sk_buff *skb)
+static int __xfrm4_output(struct sock *sk, struct sk_buff *skb)
 {
 	struct xfrm_state *x = skb_dst(skb)->xfrm;
 
 #ifdef CONFIG_NETFILTER
 	if (!x) {
 		IPCB(skb)->flags |= IPSKB_REROUTED;
-		return dst_output(skb);
+		return dst_output_sk(sk, skb);
 	}
 #endif
 
-	return x->outer_mode->afinfo->output_finish(skb);
+	return x->outer_mode->afinfo->output_finish(sk, skb);
 }
 
 int xfrm4_output(struct sock *sk, struct sk_buff *skb)
 {
-	return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb,
+	return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, sk, skb,
 			    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 6156f68a1e90..bff69746e05f 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -232,7 +232,6 @@ static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 
 static struct dst_ops xfrm4_dst_ops = {
 	.family =		AF_INET,
-	.protocol =		cpu_to_be16(ETH_P_IP),
 	.gc =			xfrm4_garbage_collect,
 	.update_pmtu =		xfrm4_update_pmtu,
 	.redirect =		xfrm4_redirect,
@@ -299,7 +298,7 @@ static void __net_exit xfrm4_net_exit(struct net *net)
 {
 	struct ctl_table *table;
 
-	if (net->ipv4.xfrm4_hdr == NULL)
+	if (!net->ipv4.xfrm4_hdr)
 		return;
 
 	table = net->ipv4.xfrm4_hdr->ctl_table_arg;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 0169ccf5aa4f..37b70e82bff8 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -46,6 +46,7 @@
 #include <linux/socket.h>
 #include <linux/sockios.h>
 #include <linux/net.h>
+#include <linux/inet.h>
 #include <linux/in6.h>
 #include <linux/netdevice.h>
 #include <linux/if_addr.h>
@@ -102,6 +103,9 @@
 
 #define	INFINITY_LIFE_TIME	0xFFFFFFFF
 
+#define IPV6_MAX_STRLEN \
+	sizeof("ffff:ffff:ffff:ffff:ffff:ffff:255.255.255.255")
+
 static inline u32 cstamp_delta(unsigned long cstamp)
 {
 	return (cstamp - INITIAL_JIFFIES) * 100UL / HZ;
@@ -127,6 +131,9 @@ static void ipv6_regen_rndid(unsigned long data);
 
 static int ipv6_generate_eui64(u8 *eui, struct net_device *dev);
 static int ipv6_count_addresses(struct inet6_dev *idev);
+static int ipv6_generate_stable_address(struct in6_addr *addr,
+					u8 dad_count,
+					const struct inet6_dev *idev);
 
 /*
  *	Configured unicast address hash table
@@ -201,6 +208,10 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
 	.disable_ipv6		= 0,
 	.accept_dad		= 1,
 	.suppress_frag_ndisc	= 1,
+	.accept_ra_mtu		= 1,
+	.stable_secret		= {
+		.initialized = false,
+	}
 };
 
 static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
@@ -238,6 +249,10 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
 	.disable_ipv6		= 0,
 	.accept_dad		= 1,
 	.suppress_frag_ndisc	= 1,
+	.accept_ra_mtu		= 1,
+	.stable_secret		= {
+		.initialized = false,
+	},
 };
 
 /* Check if a valid qdisc is available */
@@ -319,7 +334,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
 		return ERR_PTR(-EINVAL);
 
 	ndev = kzalloc(sizeof(struct inet6_dev), GFP_KERNEL);
-	if (ndev == NULL)
+	if (!ndev)
 		return ERR_PTR(err);
 
 	rwlock_init(&ndev->lock);
@@ -331,7 +346,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
 	ndev->cnf.mtu6 = dev->mtu;
 	ndev->cnf.sysctl = NULL;
 	ndev->nd_parms = neigh_parms_alloc(dev, &nd_tbl);
-	if (ndev->nd_parms == NULL) {
+	if (!ndev->nd_parms) {
 		kfree(ndev);
 		return ERR_PTR(err);
 	}
@@ -466,7 +481,7 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
 
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct netconfmsg),
 			flags);
-	if (nlh == NULL)
+	if (!nlh)
 		return -EMSGSIZE;
 
 	ncm = nlmsg_data(nlh);
@@ -489,7 +504,8 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
 	    nla_put_s32(skb, NETCONFA_PROXY_NEIGH, devconf->proxy_ndp) < 0)
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
@@ -503,7 +519,7 @@ void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex,
 	int err = -ENOBUFS;
 
 	skb = nlmsg_new(inet6_netconf_msgsize_devconf(type), GFP_ATOMIC);
-	if (skb == NULL)
+	if (!skb)
 		goto errout;
 
 	err = inet6_netconf_fill_devconf(skb, ifindex, devconf, 0, 0,
@@ -558,10 +574,10 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb,
 		break;
 	default:
 		dev = __dev_get_by_index(net, ifindex);
-		if (dev == NULL)
+		if (!dev)
 			goto errout;
 		in6_dev = __in6_dev_get(dev);
-		if (in6_dev == NULL)
+		if (!in6_dev)
 			goto errout;
 		devconf = &in6_dev->cnf;
 		break;
@@ -569,7 +585,7 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb,
 
 	err = -ENOBUFS;
 	skb = nlmsg_new(inet6_netconf_msgsize_devconf(-1), GFP_ATOMIC);
-	if (skb == NULL)
+	if (!skb)
 		goto errout;
 
 	err = inet6_netconf_fill_devconf(skb, ifindex, devconf,
@@ -619,7 +635,7 @@ static int inet6_netconf_dump_devconf(struct sk_buff *skb,
 						       cb->nlh->nlmsg_seq,
 						       RTM_NEWNETCONF,
 						       NLM_F_MULTI,
-						       -1) <= 0) {
+						       -1) < 0) {
 				rcu_read_unlock();
 				goto done;
 			}
@@ -635,7 +651,7 @@ cont:
 					       NETLINK_CB(cb->skb).portid,
 					       cb->nlh->nlmsg_seq,
 					       RTM_NEWNETCONF, NLM_F_MULTI,
-					       -1) <= 0)
+					       -1) < 0)
 			goto done;
 		else
 			h++;
@@ -646,7 +662,7 @@ cont:
 					       NETLINK_CB(cb->skb).portid,
 					       cb->nlh->nlmsg_seq,
 					       RTM_NEWNETCONF, NLM_F_MULTI,
-					       -1) <= 0)
+					       -1) < 0)
 			goto done;
 		else
 			h++;
@@ -838,7 +854,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
 
 	ifa = kzalloc(sizeof(struct inet6_ifaddr), GFP_ATOMIC);
 
-	if (ifa == NULL) {
+	if (!ifa) {
 		ADBG("ipv6_add_addr: malloc failed\n");
 		err = -ENOBUFS;
 		goto out;
@@ -857,7 +873,6 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
 		ifa->peer_addr = *peer_addr;
 
 	spin_lock_init(&ifa->lock);
-	spin_lock_init(&ifa->state_lock);
 	INIT_DELAYED_WORK(&ifa->dad_work, addrconf_dad_work);
 	INIT_HLIST_NODE(&ifa->addr_lst);
 	ifa->scope = scope;
@@ -1000,10 +1015,10 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
 
 	ASSERT_RTNL();
 
-	spin_lock_bh(&ifp->state_lock);
+	spin_lock_bh(&ifp->lock);
 	state = ifp->state;
 	ifp->state = INET6_IFADDR_STATE_DEAD;
-	spin_unlock_bh(&ifp->state_lock);
+	spin_unlock_bh(&ifp->lock);
 
 	if (state == INET6_IFADDR_STATE_DEAD)
 		goto out;
@@ -1170,6 +1185,9 @@ enum {
 	IPV6_SADDR_RULE_PRIVACY,
 	IPV6_SADDR_RULE_ORCHID,
 	IPV6_SADDR_RULE_PREFIX,
+#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
+	IPV6_SADDR_RULE_NOT_OPTIMISTIC,
+#endif
 	IPV6_SADDR_RULE_MAX
 };
 
@@ -1197,6 +1215,15 @@ static inline int ipv6_saddr_preferred(int type)
 	return 0;
 }
 
+static inline bool ipv6_use_optimistic_addr(struct inet6_dev *idev)
+{
+#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
+	return idev && idev->cnf.optimistic_dad && idev->cnf.use_optimistic;
+#else
+	return false;
+#endif
+}
+
 static int ipv6_get_saddr_eval(struct net *net,
 			       struct ipv6_saddr_score *score,
 			       struct ipv6_saddr_dst *dst,
@@ -1257,10 +1284,16 @@ static int ipv6_get_saddr_eval(struct net *net,
 		score->scopedist = ret;
 		break;
 	case IPV6_SADDR_RULE_PREFERRED:
+	    {
 		/* Rule 3: Avoid deprecated and optimistic addresses */
+		u8 avoid = IFA_F_DEPRECATED;
+
+		if (!ipv6_use_optimistic_addr(score->ifa->idev))
+			avoid |= IFA_F_OPTIMISTIC;
 		ret = ipv6_saddr_preferred(score->addr_type) ||
-		      !(score->ifa->flags & (IFA_F_DEPRECATED|IFA_F_OPTIMISTIC));
+		      !(score->ifa->flags & avoid);
 		break;
+	    }
 #ifdef CONFIG_IPV6_MIP6
 	case IPV6_SADDR_RULE_HOA:
 	    {
@@ -1306,6 +1339,14 @@ static int ipv6_get_saddr_eval(struct net *net,
 			ret = score->ifa->prefix_len;
 		score->matchlen = ret;
 		break;
+#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
+	case IPV6_SADDR_RULE_NOT_OPTIMISTIC:
+		/* Optimistic addresses still have lower precedence than other
+		 * preferred addresses.
+		 */
+		ret = !(score->ifa->flags & IFA_F_OPTIMISTIC);
+		break;
+#endif
 	default:
 		ret = 0;
 	}
@@ -1385,10 +1426,8 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev,
 
 			if (unlikely(score->addr_type == IPV6_ADDR_ANY ||
 				     score->addr_type & IPV6_ADDR_MULTICAST)) {
-				LIMIT_NETDEBUG(KERN_DEBUG
-					       "ADDRCONF: unspecified / multicast address "
-					       "assigned as unicast address on %s",
-					       dev->name);
+				net_dbg_ratelimited("ADDRCONF: unspecified / multicast address assigned as unicast address on %s",
+						    dev->name);
 				continue;
 			}
 
@@ -1495,16 +1534,31 @@ static int ipv6_count_addresses(struct inet6_dev *idev)
 int ipv6_chk_addr(struct net *net, const struct in6_addr *addr,
 		  const struct net_device *dev, int strict)
 {
+	return ipv6_chk_addr_and_flags(net, addr, dev, strict, IFA_F_TENTATIVE);
+}
+EXPORT_SYMBOL(ipv6_chk_addr);
+
+int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr,
+			    const struct net_device *dev, int strict,
+			    u32 banned_flags)
+{
 	struct inet6_ifaddr *ifp;
 	unsigned int hash = inet6_addr_hash(addr);
+	u32 ifp_flags;
 
 	rcu_read_lock_bh();
 	hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) {
 		if (!net_eq(dev_net(ifp->idev->dev), net))
 			continue;
+		/* Decouple optimistic from tentative for evaluation here.
+		 * Ban optimistic addresses explicitly, when required.
+		 */
+		ifp_flags = (ifp->flags&IFA_F_OPTIMISTIC)
+			    ? (ifp->flags&~IFA_F_TENTATIVE)
+			    : ifp->flags;
 		if (ipv6_addr_equal(&ifp->addr, addr) &&
-		    !(ifp->flags&IFA_F_TENTATIVE) &&
-		    (dev == NULL || ifp->idev->dev == dev ||
+		    !(ifp_flags&banned_flags) &&
+		    (!dev || ifp->idev->dev == dev ||
 		     !(ifp->scope&(IFA_LINK|IFA_HOST) || strict))) {
 			rcu_read_unlock_bh();
 			return 1;
@@ -1514,7 +1568,7 @@ int ipv6_chk_addr(struct net *net, const struct in6_addr *addr,
 	rcu_read_unlock_bh();
 	return 0;
 }
-EXPORT_SYMBOL(ipv6_chk_addr);
+EXPORT_SYMBOL(ipv6_chk_addr_and_flags);
 
 static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr,
 			       struct net_device *dev)
@@ -1526,7 +1580,7 @@ static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr,
 		if (!net_eq(dev_net(ifp->idev->dev), net))
 			continue;
 		if (ipv6_addr_equal(&ifp->addr, addr)) {
-			if (dev == NULL || ifp->idev->dev == dev)
+			if (!dev || ifp->idev->dev == dev)
 				return true;
 		}
 	}
@@ -1595,7 +1649,7 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add
 		if (!net_eq(dev_net(ifp->idev->dev), net))
 			continue;
 		if (ipv6_addr_equal(&ifp->addr, addr)) {
-			if (dev == NULL || ifp->idev->dev == dev ||
+			if (!dev || ifp->idev->dev == dev ||
 			    !(ifp->scope&(IFA_LINK|IFA_HOST) || strict)) {
 				result = ifp;
 				in6_ifa_hold(ifp);
@@ -1644,19 +1698,21 @@ static int addrconf_dad_end(struct inet6_ifaddr *ifp)
 {
 	int err = -ENOENT;
 
-	spin_lock_bh(&ifp->state_lock);
+	spin_lock_bh(&ifp->lock);
 	if (ifp->state == INET6_IFADDR_STATE_DAD) {
 		ifp->state = INET6_IFADDR_STATE_POSTDAD;
 		err = 0;
 	}
-	spin_unlock_bh(&ifp->state_lock);
+	spin_unlock_bh(&ifp->lock);
 
 	return err;
 }
 
 void addrconf_dad_failure(struct inet6_ifaddr *ifp)
 {
+	struct in6_addr addr;
 	struct inet6_dev *idev = ifp->idev;
+	struct net *net = dev_net(ifp->idev->dev);
 
 	if (addrconf_dad_end(ifp)) {
 		in6_ifa_put(ifp);
@@ -1666,9 +1722,57 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp)
 	net_info_ratelimited("%s: IPv6 duplicate address %pI6c detected!\n",
 			     ifp->idev->dev->name, &ifp->addr);
 
-	if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6) {
-		struct in6_addr addr;
+	spin_lock_bh(&ifp->lock);
+
+	if (ifp->flags & IFA_F_STABLE_PRIVACY) {
+		int scope = ifp->scope;
+		u32 flags = ifp->flags;
+		struct in6_addr new_addr;
+		struct inet6_ifaddr *ifp2;
+		u32 valid_lft, preferred_lft;
+		int pfxlen = ifp->prefix_len;
+		int retries = ifp->stable_privacy_retry + 1;
+
+		if (retries > net->ipv6.sysctl.idgen_retries) {
+			net_info_ratelimited("%s: privacy stable address generation failed because of DAD conflicts!\n",
+					     ifp->idev->dev->name);
+			goto errdad;
+		}
+
+		new_addr = ifp->addr;
+		if (ipv6_generate_stable_address(&new_addr, retries,
+						 idev))
+			goto errdad;
+
+		valid_lft = ifp->valid_lft;
+		preferred_lft = ifp->prefered_lft;
 
+		spin_unlock_bh(&ifp->lock);
+
+		if (idev->cnf.max_addresses &&
+		    ipv6_count_addresses(idev) >=
+		    idev->cnf.max_addresses)
+			goto lock_errdad;
+
+		net_info_ratelimited("%s: generating new stable privacy address because of DAD conflict\n",
+				     ifp->idev->dev->name);
+
+		ifp2 = ipv6_add_addr(idev, &new_addr, NULL, pfxlen,
+				     scope, flags, valid_lft,
+				     preferred_lft);
+		if (IS_ERR(ifp2))
+			goto lock_errdad;
+
+		spin_lock_bh(&ifp2->lock);
+		ifp2->stable_privacy_retry = retries;
+		ifp2->state = INET6_IFADDR_STATE_PREDAD;
+		spin_unlock_bh(&ifp2->lock);
+
+		addrconf_mod_dad_work(ifp2, net->ipv6.sysctl.idgen_delay);
+		in6_ifa_put(ifp2);
+lock_errdad:
+		spin_lock_bh(&ifp->lock);
+	} else if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6) {
 		addr.s6_addr32[0] = htonl(0xfe800000);
 		addr.s6_addr32[1] = 0;
 
@@ -1682,10 +1786,10 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp)
 		}
 	}
 
-	spin_lock_bh(&ifp->state_lock);
+errdad:
 	/* transition from _POSTDAD to _ERRDAD */
 	ifp->state = INET6_IFADDR_STATE_ERRDAD;
-	spin_unlock_bh(&ifp->state_lock);
+	spin_unlock_bh(&ifp->lock);
 
 	addrconf_mod_dad_work(ifp, 0);
 }
@@ -2010,7 +2114,7 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
 	struct fib6_table *table;
 
 	table = fib6_get_table(dev_net(dev), RT6_TABLE_PREFIX);
-	if (table == NULL)
+	if (!table)
 		return NULL;
 
 	read_lock_bh(&table->tb6_lock);
@@ -2144,6 +2248,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
 	__u32 valid_lft;
 	__u32 prefered_lft;
 	int addr_type;
+	u32 addr_flags = 0;
 	struct inet6_dev *in6_dev;
 	struct net *net = dev_net(dev);
 
@@ -2173,7 +2278,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
 
 	in6_dev = in6_dev_get(dev);
 
-	if (in6_dev == NULL) {
+	if (!in6_dev) {
 		net_dbg_ratelimited("addrconf: device %s not configured\n",
 				    dev->name);
 		return;
@@ -2250,6 +2355,12 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
 				       in6_dev->token.s6_addr + 8, 8);
 				read_unlock_bh(&in6_dev->lock);
 				tokenized = true;
+			} else if (in6_dev->addr_gen_mode ==
+				   IN6_ADDR_GEN_MODE_STABLE_PRIVACY &&
+				   !ipv6_generate_stable_address(&addr, 0,
+								 in6_dev)) {
+				addr_flags |= IFA_F_STABLE_PRIVACY;
+				goto ok;
 			} else if (ipv6_generate_eui64(addr.s6_addr + 8, dev) &&
 				   ipv6_inherit_eui64(addr.s6_addr + 8, in6_dev)) {
 				in6_dev_put(in6_dev);
@@ -2266,9 +2377,8 @@ ok:
 
 		ifp = ipv6_get_ifaddr(net, &addr, dev, 1);
 
-		if (ifp == NULL && valid_lft) {
+		if (!ifp && valid_lft) {
 			int max_addresses = in6_dev->cnf.max_addresses;
-			u32 addr_flags = 0;
 
 #ifdef CONFIG_IPV6_OPTIMISTIC_DAD
 			if (in6_dev->cnf.optimistic_dad &&
@@ -2308,15 +2418,15 @@ ok:
 			u32 stored_lft;
 
 			/* update lifetime (RFC2462 5.5.3 e) */
-			spin_lock(&ifp->lock);
+			spin_lock_bh(&ifp->lock);
 			now = jiffies;
 			if (ifp->valid_lft > (now - ifp->tstamp) / HZ)
 				stored_lft = ifp->valid_lft - (now - ifp->tstamp) / HZ;
 			else
 				stored_lft = 0;
 			if (!update_lft && !create && stored_lft) {
-				const u32 minimum_lft = min(
-					stored_lft, (u32)MIN_VALID_LIFETIME);
+				const u32 minimum_lft = min_t(u32,
+					stored_lft, MIN_VALID_LIFETIME);
 				valid_lft = max(valid_lft, minimum_lft);
 
 				/* RFC4862 Section 5.5.3e:
@@ -2338,12 +2448,12 @@ ok:
 				ifp->tstamp = now;
 				flags = ifp->flags;
 				ifp->flags &= ~IFA_F_DEPRECATED;
-				spin_unlock(&ifp->lock);
+				spin_unlock_bh(&ifp->lock);
 
 				if (!(flags&IFA_F_TENTATIVE))
 					ipv6_ifa_notify(0, ifp);
 			} else
-				spin_unlock(&ifp->lock);
+				spin_unlock_bh(&ifp->lock);
 
 			manage_tempaddrs(in6_dev, ifp, valid_lft, prefered_lft,
 					 create, now);
@@ -2376,7 +2486,7 @@ int addrconf_set_dstaddr(struct net *net, void __user *arg)
 	dev = __dev_get_by_index(net, ireq.ifr6_ifindex);
 
 	err = -ENODEV;
-	if (dev == NULL)
+	if (!dev)
 		goto err_exit;
 
 #if IS_ENABLED(CONFIG_IPV6_SIT)
@@ -2422,6 +2532,23 @@ err_exit:
 	return err;
 }
 
+static int ipv6_mc_config(struct sock *sk, bool join,
+			  const struct in6_addr *addr, int ifindex)
+{
+	int ret;
+
+	ASSERT_RTNL();
+
+	lock_sock(sk);
+	if (join)
+		ret = ipv6_sock_mc_join(sk, ifindex, addr);
+	else
+		ret = ipv6_sock_mc_drop(sk, ifindex, addr);
+	release_sock(sk);
+
+	return ret;
+}
+
 /*
  *	Manual configuration of address on an interface
  */
@@ -2434,10 +2561,10 @@ static int inet6_addr_add(struct net *net, int ifindex,
 	struct inet6_ifaddr *ifp;
 	struct inet6_dev *idev;
 	struct net_device *dev;
+	unsigned long timeout;
+	clock_t expires;
 	int scope;
 	u32 flags;
-	clock_t expires;
-	unsigned long timeout;
 
 	ASSERT_RTNL();
 
@@ -2459,6 +2586,14 @@ static int inet6_addr_add(struct net *net, int ifindex,
 	if (IS_ERR(idev))
 		return PTR_ERR(idev);
 
+	if (ifa_flags & IFA_F_MCAUTOJOIN) {
+		int ret = ipv6_mc_config(net->ipv6.mc_autojoin_sk,
+					 true, pfx, ifindex);
+
+		if (ret < 0)
+			return ret;
+	}
+
 	scope = ipv6_addr_scope(pfx);
 
 	timeout = addrconf_timeout_fixup(valid_lft, HZ);
@@ -2500,6 +2635,9 @@ static int inet6_addr_add(struct net *net, int ifindex,
 		in6_ifa_put(ifp);
 		addrconf_verify_rtnl();
 		return 0;
+	} else if (ifa_flags & IFA_F_MCAUTOJOIN) {
+		ipv6_mc_config(net->ipv6.mc_autojoin_sk,
+			       false, pfx, ifindex);
 	}
 
 	return PTR_ERR(ifp);
@@ -2519,7 +2657,8 @@ static int inet6_addr_del(struct net *net, int ifindex, u32 ifa_flags,
 	if (!dev)
 		return -ENODEV;
 
-	if ((idev = __in6_dev_get(dev)) == NULL)
+	idev = __in6_dev_get(dev);
+	if (!idev)
 		return -ENXIO;
 
 	read_lock_bh(&idev->lock);
@@ -2535,6 +2674,10 @@ static int inet6_addr_del(struct net *net, int ifindex, u32 ifa_flags,
 						 jiffies);
 			ipv6_del_addr(ifp);
 			addrconf_verify_rtnl();
+			if (ipv6_addr_is_multicast(pfx)) {
+				ipv6_mc_config(net->ipv6.mc_autojoin_sk,
+					       false, pfx, dev->ifindex);
+			}
 			return 0;
 		}
 	}
@@ -2666,7 +2809,8 @@ static void init_loopback(struct net_device *dev)
 
 	ASSERT_RTNL();
 
-	if ((idev = ipv6_find_idev(dev)) == NULL) {
+	idev = ipv6_find_idev(dev);
+	if (!idev) {
 		pr_debug("%s: add_dev failed\n", __func__);
 		return;
 	}
@@ -2713,10 +2857,11 @@ static void init_loopback(struct net_device *dev)
 	}
 }
 
-static void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr *addr)
+static void addrconf_add_linklocal(struct inet6_dev *idev,
+				   const struct in6_addr *addr, u32 flags)
 {
 	struct inet6_ifaddr *ifp;
-	u32 addr_flags = IFA_F_PERMANENT;
+	u32 addr_flags = flags | IFA_F_PERMANENT;
 
 #ifdef CONFIG_IPV6_OPTIMISTIC_DAD
 	if (idev->cnf.optimistic_dad &&
@@ -2724,7 +2869,6 @@ static void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr
 		addr_flags |= IFA_F_OPTIMISTIC;
 #endif
 
-
 	ifp = ipv6_add_addr(idev, addr, NULL, 64, IFA_LINK, addr_flags,
 			    INFINITY_LIFE_TIME, INFINITY_LIFE_TIME);
 	if (!IS_ERR(ifp)) {
@@ -2734,18 +2878,103 @@ static void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr
 	}
 }
 
+static bool ipv6_reserved_interfaceid(struct in6_addr address)
+{
+	if ((address.s6_addr32[2] | address.s6_addr32[3]) == 0)
+		return true;
+
+	if (address.s6_addr32[2] == htonl(0x02005eff) &&
+	    ((address.s6_addr32[3] & htonl(0xfe000000)) == htonl(0xfe000000)))
+		return true;
+
+	if (address.s6_addr32[2] == htonl(0xfdffffff) &&
+	    ((address.s6_addr32[3] & htonl(0xffffff80)) == htonl(0xffffff80)))
+		return true;
+
+	return false;
+}
+
+static int ipv6_generate_stable_address(struct in6_addr *address,
+					u8 dad_count,
+					const struct inet6_dev *idev)
+{
+	static DEFINE_SPINLOCK(lock);
+	static __u32 digest[SHA_DIGEST_WORDS];
+	static __u32 workspace[SHA_WORKSPACE_WORDS];
+
+	static union {
+		char __data[SHA_MESSAGE_BYTES];
+		struct {
+			struct in6_addr secret;
+			__be32 prefix[2];
+			unsigned char hwaddr[MAX_ADDR_LEN];
+			u8 dad_count;
+		} __packed;
+	} data;
+
+	struct in6_addr secret;
+	struct in6_addr temp;
+	struct net *net = dev_net(idev->dev);
+
+	BUILD_BUG_ON(sizeof(data.__data) != sizeof(data));
+
+	if (idev->cnf.stable_secret.initialized)
+		secret = idev->cnf.stable_secret.secret;
+	else if (net->ipv6.devconf_dflt->stable_secret.initialized)
+		secret = net->ipv6.devconf_dflt->stable_secret.secret;
+	else
+		return -1;
+
+retry:
+	spin_lock_bh(&lock);
+
+	sha_init(digest);
+	memset(&data, 0, sizeof(data));
+	memset(workspace, 0, sizeof(workspace));
+	memcpy(data.hwaddr, idev->dev->perm_addr, idev->dev->addr_len);
+	data.prefix[0] = address->s6_addr32[0];
+	data.prefix[1] = address->s6_addr32[1];
+	data.secret = secret;
+	data.dad_count = dad_count;
+
+	sha_transform(digest, data.__data, workspace);
+
+	temp = *address;
+	temp.s6_addr32[2] = (__force __be32)digest[0];
+	temp.s6_addr32[3] = (__force __be32)digest[1];
+
+	spin_unlock_bh(&lock);
+
+	if (ipv6_reserved_interfaceid(temp)) {
+		dad_count++;
+		if (dad_count > dev_net(idev->dev)->ipv6.sysctl.idgen_retries)
+			return -1;
+		goto retry;
+	}
+
+	*address = temp;
+	return 0;
+}
+
 static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route)
 {
-	if (idev->addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64) {
-		struct in6_addr addr;
+	struct in6_addr addr;
 
-		ipv6_addr_set(&addr,  htonl(0xFE800000), 0, 0, 0);
+	ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0);
+
+	if (idev->addr_gen_mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY) {
+		if (!ipv6_generate_stable_address(&addr, 0, idev))
+			addrconf_add_linklocal(idev, &addr,
+					       IFA_F_STABLE_PRIVACY);
+		else if (prefix_route)
+			addrconf_prefix_route(&addr, 64, idev->dev, 0, 0);
+	} else if (idev->addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64) {
 		/* addrconf_add_linklocal also adds a prefix_route and we
 		 * only need to care about prefix routes if ipv6_generate_eui64
 		 * couldn't generate one.
 		 */
 		if (ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) == 0)
-			addrconf_add_linklocal(idev, &addr);
+			addrconf_add_linklocal(idev, &addr, 0);
 		else if (prefix_route)
 			addrconf_prefix_route(&addr, 64, idev->dev, 0, 0);
 	}
@@ -2789,7 +3018,8 @@ static void addrconf_sit_config(struct net_device *dev)
 	 * our v4 addrs in the tunnel
 	 */
 
-	if ((idev = ipv6_find_idev(dev)) == NULL) {
+	idev = ipv6_find_idev(dev);
+	if (!idev) {
 		pr_debug("%s: add_dev failed\n", __func__);
 		return;
 	}
@@ -2813,7 +3043,8 @@ static void addrconf_gre_config(struct net_device *dev)
 
 	ASSERT_RTNL();
 
-	if ((idev = ipv6_find_idev(dev)) == NULL) {
+	idev = ipv6_find_idev(dev);
+	if (!idev) {
 		pr_debug("%s: add_dev failed\n", __func__);
 		return;
 	}
@@ -3010,7 +3241,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 	neigh_ifdown(&nd_tbl, dev);
 
 	idev = __in6_dev_get(dev);
-	if (idev == NULL)
+	if (!idev)
 		return -ENODEV;
 
 	/*
@@ -3081,10 +3312,10 @@ restart:
 
 		write_unlock_bh(&idev->lock);
 
-		spin_lock_bh(&ifa->state_lock);
+		spin_lock_bh(&ifa->lock);
 		state = ifa->state;
 		ifa->state = INET6_IFADDR_STATE_DEAD;
-		spin_unlock_bh(&ifa->state_lock);
+		spin_unlock_bh(&ifa->lock);
 
 		if (state != INET6_IFADDR_STATE_DEAD) {
 			__ipv6_ifa_notify(RTM_DELADDR, ifa);
@@ -3222,8 +3453,15 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
 	 * Optimistic nodes can start receiving
 	 * Frames right away
 	 */
-	if (ifp->flags & IFA_F_OPTIMISTIC)
+	if (ifp->flags & IFA_F_OPTIMISTIC) {
 		ip6_ins_rt(ifp->rt);
+		if (ipv6_use_optimistic_addr(idev)) {
+			/* Because optimistic nodes can use this address,
+			 * notify listeners. If DAD fails, RTM_DELADDR is sent.
+			 */
+			ipv6_ifa_notify(RTM_NEWADDR, ifp);
+		}
+	}
 
 	addrconf_dad_kick(ifp);
 out:
@@ -3235,12 +3473,12 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp)
 {
 	bool begin_dad = false;
 
-	spin_lock_bh(&ifp->state_lock);
+	spin_lock_bh(&ifp->lock);
 	if (ifp->state != INET6_IFADDR_STATE_DEAD) {
 		ifp->state = INET6_IFADDR_STATE_PREDAD;
 		begin_dad = true;
 	}
-	spin_unlock_bh(&ifp->state_lock);
+	spin_unlock_bh(&ifp->lock);
 
 	if (begin_dad)
 		addrconf_mod_dad_work(ifp, 0);
@@ -3262,7 +3500,7 @@ static void addrconf_dad_work(struct work_struct *w)
 
 	rtnl_lock();
 
-	spin_lock_bh(&ifp->state_lock);
+	spin_lock_bh(&ifp->lock);
 	if (ifp->state == INET6_IFADDR_STATE_PREDAD) {
 		action = DAD_BEGIN;
 		ifp->state = INET6_IFADDR_STATE_DAD;
@@ -3270,7 +3508,7 @@ static void addrconf_dad_work(struct work_struct *w)
 		action = DAD_ABORT;
 		ifp->state = INET6_IFADDR_STATE_POSTDAD;
 	}
-	spin_unlock_bh(&ifp->state_lock);
+	spin_unlock_bh(&ifp->lock);
 
 	if (action == DAD_BEGIN) {
 		addrconf_dad_begin(ifp);
@@ -3758,7 +3996,7 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	ifm = nlmsg_data(nlh);
 	pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer_pfx);
-	if (pfx == NULL)
+	if (!pfx)
 		return -EINVAL;
 
 	ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) : ifm->ifa_flags;
@@ -3870,7 +4108,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	ifm = nlmsg_data(nlh);
 	pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer_pfx);
-	if (pfx == NULL)
+	if (!pfx)
 		return -EINVAL;
 
 	if (tb[IFA_CACHEINFO]) {
@@ -3885,17 +4123,17 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
 	}
 
 	dev =  __dev_get_by_index(net, ifm->ifa_index);
-	if (dev == NULL)
+	if (!dev)
 		return -ENODEV;
 
 	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_F_NOPREFIXROUTE;
+		     IFA_F_NOPREFIXROUTE | IFA_F_MCAUTOJOIN;
 
 	ifa = ipv6_get_ifaddr(net, pfx, dev, 1);
-	if (ifa == NULL) {
+	if (!ifa) {
 		/*
 		 * It would be best to check for !NLM_F_CREATE here but
 		 * userspace already relies on not having to provide this.
@@ -3970,7 +4208,7 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa,
 	u32 preferred, valid;
 
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags);
-	if (nlh == NULL)
+	if (!nlh)
 		return -EMSGSIZE;
 
 	put_ifaddrmsg(nlh, ifa->prefix_len, ifa->flags, rt_scope(ifa->scope),
@@ -3999,11 +4237,11 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa,
 	}
 
 	if (!ipv6_addr_any(&ifa->peer_addr)) {
-		if (nla_put(skb, IFA_LOCAL, 16, &ifa->addr) < 0 ||
-		    nla_put(skb, IFA_ADDRESS, 16, &ifa->peer_addr) < 0)
+		if (nla_put_in6_addr(skb, IFA_LOCAL, &ifa->addr) < 0 ||
+		    nla_put_in6_addr(skb, IFA_ADDRESS, &ifa->peer_addr) < 0)
 			goto error;
 	} else
-		if (nla_put(skb, IFA_ADDRESS, 16, &ifa->addr) < 0)
+		if (nla_put_in6_addr(skb, IFA_ADDRESS, &ifa->addr) < 0)
 			goto error;
 
 	if (put_cacheinfo(skb, ifa->cstamp, ifa->tstamp, preferred, valid) < 0)
@@ -4012,7 +4250,8 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa,
 	if (nla_put_u32(skb, IFA_FLAGS, ifa->flags) < 0)
 		goto error;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 error:
 	nlmsg_cancel(skb, nlh);
@@ -4030,18 +4269,19 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca,
 		scope = RT_SCOPE_SITE;
 
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags);
-	if (nlh == NULL)
+	if (!nlh)
 		return -EMSGSIZE;
 
 	put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex);
-	if (nla_put(skb, IFA_MULTICAST, 16, &ifmca->mca_addr) < 0 ||
+	if (nla_put_in6_addr(skb, IFA_MULTICAST, &ifmca->mca_addr) < 0 ||
 	    put_cacheinfo(skb, ifmca->mca_cstamp, ifmca->mca_tstamp,
 			  INFINITY_LIFE_TIME, INFINITY_LIFE_TIME) < 0) {
 		nlmsg_cancel(skb, nlh);
 		return -EMSGSIZE;
 	}
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 }
 
 static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca,
@@ -4055,18 +4295,19 @@ static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca,
 		scope = RT_SCOPE_SITE;
 
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags);
-	if (nlh == NULL)
+	if (!nlh)
 		return -EMSGSIZE;
 
 	put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex);
-	if (nla_put(skb, IFA_ANYCAST, 16, &ifaca->aca_addr) < 0 ||
+	if (nla_put_in6_addr(skb, IFA_ANYCAST, &ifaca->aca_addr) < 0 ||
 	    put_cacheinfo(skb, ifaca->aca_cstamp, ifaca->aca_tstamp,
 			  INFINITY_LIFE_TIME, INFINITY_LIFE_TIME) < 0) {
 		nlmsg_cancel(skb, nlh);
 		return -EMSGSIZE;
 	}
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 }
 
 enum addr_type_t {
@@ -4099,7 +4340,7 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb,
 						cb->nlh->nlmsg_seq,
 						RTM_NEWADDR,
 						NLM_F_MULTI);
-			if (err <= 0)
+			if (err < 0)
 				break;
 			nl_dump_check_consistent(cb, nlmsg_hdr(skb));
 		}
@@ -4116,7 +4357,7 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb,
 						  cb->nlh->nlmsg_seq,
 						  RTM_GETMULTICAST,
 						  NLM_F_MULTI);
-			if (err <= 0)
+			if (err < 0)
 				break;
 		}
 		break;
@@ -4131,7 +4372,7 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb,
 						  cb->nlh->nlmsg_seq,
 						  RTM_GETANYCAST,
 						  NLM_F_MULTI);
-			if (err <= 0)
+			if (err < 0)
 				break;
 		}
 		break;
@@ -4174,7 +4415,7 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb,
 				goto cont;
 
 			if (in6_dump_addrs(idev, skb, cb, type,
-					   s_ip_idx, &ip_idx) <= 0)
+					   s_ip_idx, &ip_idx) < 0)
 				goto done;
 cont:
 			idx++;
@@ -4227,7 +4468,7 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 		goto errout;
 
 	addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer);
-	if (addr == NULL) {
+	if (!addr) {
 		err = -EINVAL;
 		goto errout;
 	}
@@ -4270,7 +4511,7 @@ static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa)
 	int err = -ENOBUFS;
 
 	skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_ATOMIC);
-	if (skb == NULL)
+	if (!skb)
 		goto errout;
 
 	err = inet6_fill_ifaddr(skb, ifa, 0, 0, event, 0);
@@ -4330,6 +4571,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
 	array[DEVCONF_ACCEPT_SOURCE_ROUTE] = cnf->accept_source_route;
 #ifdef CONFIG_IPV6_OPTIMISTIC_DAD
 	array[DEVCONF_OPTIMISTIC_DAD] = cnf->optimistic_dad;
+	array[DEVCONF_USE_OPTIMISTIC] = cnf->use_optimistic;
 #endif
 #ifdef CONFIG_IPV6_MROUTE
 	array[DEVCONF_MC_FORWARDING] = cnf->mc_forwarding;
@@ -4340,6 +4582,8 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
 	array[DEVCONF_NDISC_NOTIFY] = cnf->ndisc_notify;
 	array[DEVCONF_SUPPRESS_FRAG_NDISC] = cnf->suppress_frag_ndisc;
 	array[DEVCONF_ACCEPT_RA_FROM_LOCAL] = cnf->accept_ra_from_local;
+	array[DEVCONF_ACCEPT_RA_MTU] = cnf->accept_ra_mtu;
+	/* we omit DEVCONF_STABLE_SECRET for now */
 }
 
 static inline size_t inet6_ifla6_size(void)
@@ -4420,24 +4664,24 @@ static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev)
 	if (nla_put(skb, IFLA_INET6_CACHEINFO, sizeof(ci), &ci))
 		goto nla_put_failure;
 	nla = nla_reserve(skb, IFLA_INET6_CONF, DEVCONF_MAX * sizeof(s32));
-	if (nla == NULL)
+	if (!nla)
 		goto nla_put_failure;
 	ipv6_store_devconf(&idev->cnf, nla_data(nla), nla_len(nla));
 
 	/* XXX - MC not implemented */
 
 	nla = nla_reserve(skb, IFLA_INET6_STATS, IPSTATS_MIB_MAX * sizeof(u64));
-	if (nla == NULL)
+	if (!nla)
 		goto nla_put_failure;
 	snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_STATS, nla_len(nla));
 
 	nla = nla_reserve(skb, IFLA_INET6_ICMP6STATS, ICMP6_MIB_MAX * sizeof(u64));
-	if (nla == NULL)
+	if (!nla)
 		goto nla_put_failure;
 	snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_ICMP6STATS, nla_len(nla));
 
 	nla = nla_reserve(skb, IFLA_INET6_TOKEN, sizeof(struct in6_addr));
-	if (nla == NULL)
+	if (!nla)
 		goto nla_put_failure;
 
 	if (nla_put_u8(skb, IFLA_INET6_ADDR_GEN_MODE, idev->addr_gen_mode))
@@ -4483,7 +4727,7 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token)
 
 	ASSERT_RTNL();
 
-	if (token == NULL)
+	if (!token)
 		return -EINVAL;
 	if (ipv6_addr_any(token))
 		return -EINVAL;
@@ -4536,6 +4780,22 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token)
 	return 0;
 }
 
+static const struct nla_policy inet6_af_policy[IFLA_INET6_MAX + 1] = {
+	[IFLA_INET6_ADDR_GEN_MODE]	= { .type = NLA_U8 },
+	[IFLA_INET6_TOKEN]		= { .len = sizeof(struct in6_addr) },
+};
+
+static int inet6_validate_link_af(const struct net_device *dev,
+				  const struct nlattr *nla)
+{
+	struct nlattr *tb[IFLA_INET6_MAX + 1];
+
+	if (dev && !__in6_dev_get(dev))
+		return -EAFNOSUPPORT;
+
+	return nla_parse_nested(tb, IFLA_INET6_MAX, nla, inet6_af_policy);
+}
+
 static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla)
 {
 	int err = -EINVAL;
@@ -4558,8 +4818,15 @@ static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla)
 		u8 mode = nla_get_u8(tb[IFLA_INET6_ADDR_GEN_MODE]);
 
 		if (mode != IN6_ADDR_GEN_MODE_EUI64 &&
-		    mode != IN6_ADDR_GEN_MODE_NONE)
+		    mode != IN6_ADDR_GEN_MODE_NONE &&
+		    mode != IN6_ADDR_GEN_MODE_STABLE_PRIVACY)
+			return -EINVAL;
+
+		if (mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY &&
+		    !idev->cnf.stable_secret.initialized &&
+		    !dev_net(dev)->ipv6.devconf_dflt->stable_secret.initialized)
 			return -EINVAL;
+
 		idev->addr_gen_mode = mode;
 		err = 0;
 	}
@@ -4576,7 +4843,7 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev,
 	void *protoinfo;
 
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*hdr), flags);
-	if (nlh == NULL)
+	if (!nlh)
 		return -EMSGSIZE;
 
 	hdr = nlmsg_data(nlh);
@@ -4591,18 +4858,19 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev,
 	    (dev->addr_len &&
 	     nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) ||
 	    nla_put_u32(skb, IFLA_MTU, dev->mtu) ||
-	    (dev->ifindex != dev->iflink &&
-	     nla_put_u32(skb, IFLA_LINK, dev->iflink)))
+	    (dev->ifindex != dev_get_iflink(dev) &&
+	     nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev))))
 		goto nla_put_failure;
 	protoinfo = nla_nest_start(skb, IFLA_PROTINFO);
-	if (protoinfo == NULL)
+	if (!protoinfo)
 		goto nla_put_failure;
 
 	if (inet6_fill_ifla6_attrs(skb, idev) < 0)
 		goto nla_put_failure;
 
 	nla_nest_end(skb, protoinfo);
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
@@ -4634,7 +4902,7 @@ static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 			if (inet6_fill_ifinfo(skb, idev,
 					      NETLINK_CB(cb->skb).portid,
 					      cb->nlh->nlmsg_seq,
-					      RTM_NEWLINK, NLM_F_MULTI) <= 0)
+					      RTM_NEWLINK, NLM_F_MULTI) < 0)
 				goto out;
 cont:
 			idx++;
@@ -4655,7 +4923,7 @@ void inet6_ifinfo_notify(int event, struct inet6_dev *idev)
 	int err = -ENOBUFS;
 
 	skb = nlmsg_new(inet6_if_nlmsg_size(), GFP_ATOMIC);
-	if (skb == NULL)
+	if (!skb)
 		goto errout;
 
 	err = inet6_fill_ifinfo(skb, idev, 0, 0, event, 0);
@@ -4688,7 +4956,7 @@ static int inet6_fill_prefix(struct sk_buff *skb, struct inet6_dev *idev,
 	struct prefix_cacheinfo	ci;
 
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*pmsg), flags);
-	if (nlh == NULL)
+	if (!nlh)
 		return -EMSGSIZE;
 
 	pmsg = nlmsg_data(nlh);
@@ -4711,7 +4979,8 @@ static int inet6_fill_prefix(struct sk_buff *skb, struct inet6_dev *idev,
 	ci.valid_time = ntohl(pinfo->valid);
 	if (nla_put(skb, PREFIX_CACHEINFO, sizeof(ci), &ci))
 		goto nla_put_failure;
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
@@ -4726,7 +4995,7 @@ static void inet6_prefix_notify(int event, struct inet6_dev *idev,
 	int err = -ENOBUFS;
 
 	skb = nlmsg_new(inet6_prefix_nlmsg_size(), GFP_ATOMIC);
-	if (skb == NULL)
+	if (!skb)
 		goto errout;
 
 	err = inet6_fill_prefix(skb, idev, pinfo, 0, 0, event, 0);
@@ -4827,6 +5096,21 @@ int addrconf_sysctl_forward(struct ctl_table *ctl, int write,
 	return ret;
 }
 
+static
+int addrconf_sysctl_mtu(struct ctl_table *ctl, int write,
+			void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct inet6_dev *idev = ctl->extra1;
+	int min_mtu = IPV6_MIN_MTU;
+	struct ctl_table lctl;
+
+	lctl = *ctl;
+	lctl.extra1 = &min_mtu;
+	lctl.extra2 = idev ? &idev->dev->mtu : NULL;
+
+	return proc_dointvec_minmax(&lctl, write, buffer, lenp, ppos);
+}
+
 static void dev_disable_change(struct inet6_dev *idev)
 {
 	struct netdev_notifier_info info;
@@ -4951,6 +5235,74 @@ int addrconf_sysctl_proxy_ndp(struct ctl_table *ctl, int write,
 	return ret;
 }
 
+static int addrconf_sysctl_stable_secret(struct ctl_table *ctl, int write,
+					 void __user *buffer, size_t *lenp,
+					 loff_t *ppos)
+{
+	int err;
+	struct in6_addr addr;
+	char str[IPV6_MAX_STRLEN];
+	struct ctl_table lctl = *ctl;
+	struct net *net = ctl->extra2;
+	struct ipv6_stable_secret *secret = ctl->data;
+
+	if (&net->ipv6.devconf_all->stable_secret == ctl->data)
+		return -EIO;
+
+	lctl.maxlen = IPV6_MAX_STRLEN;
+	lctl.data = str;
+
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	if (!write && !secret->initialized) {
+		err = -EIO;
+		goto out;
+	}
+
+	if (!write) {
+		err = snprintf(str, sizeof(str), "%pI6",
+			       &secret->secret);
+		if (err >= sizeof(str)) {
+			err = -EIO;
+			goto out;
+		}
+	}
+
+	err = proc_dostring(&lctl, write, buffer, lenp, ppos);
+	if (err || !write)
+		goto out;
+
+	if (in6_pton(str, -1, addr.in6_u.u6_addr8, -1, NULL) != 1) {
+		err = -EIO;
+		goto out;
+	}
+
+	secret->initialized = true;
+	secret->secret = addr;
+
+	if (&net->ipv6.devconf_dflt->stable_secret == ctl->data) {
+		struct net_device *dev;
+
+		for_each_netdev(net, dev) {
+			struct inet6_dev *idev = __in6_dev_get(dev);
+
+			if (idev) {
+				idev->addr_gen_mode =
+					IN6_ADDR_GEN_MODE_STABLE_PRIVACY;
+			}
+		}
+	} else {
+		struct inet6_dev *idev = ctl->extra1;
+
+		idev->addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY;
+	}
+
+out:
+	rtnl_unlock();
+
+	return err;
+}
 
 static struct addrconf_sysctl_table
 {
@@ -4978,7 +5330,7 @@ static struct addrconf_sysctl_table
 			.data		= &ipv6_devconf.mtu6,
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
-			.proc_handler	= proc_dointvec,
+			.proc_handler	= addrconf_sysctl_mtu,
 		},
 		{
 			.procname	= "accept_ra",
@@ -5156,6 +5508,14 @@ static struct addrconf_sysctl_table
 			.proc_handler   = proc_dointvec,
 
 		},
+		{
+			.procname       = "use_optimistic",
+			.data           = &ipv6_devconf.use_optimistic,
+			.maxlen         = sizeof(int),
+			.mode           = 0644,
+			.proc_handler   = proc_dointvec,
+
+		},
 #endif
 #ifdef CONFIG_IPV6_MROUTE
 		{
@@ -5209,6 +5569,20 @@ static struct addrconf_sysctl_table
 			.proc_handler	= proc_dointvec,
 		},
 		{
+			.procname	= "accept_ra_mtu",
+			.data		= &ipv6_devconf.accept_ra_mtu,
+			.maxlen		= sizeof(int),
+			.mode		= 0644,
+			.proc_handler	= proc_dointvec,
+		},
+		{
+			.procname	= "stable_secret",
+			.data		= &ipv6_devconf.stable_secret,
+			.maxlen		= IPV6_MAX_STRLEN,
+			.mode		= 0600,
+			.proc_handler	= addrconf_sysctl_stable_secret,
+		},
+		{
 			/* sentinel */
 		}
 	},
@@ -5222,7 +5596,7 @@ static int __addrconf_sysctl_register(struct net *net, char *dev_name,
 	char path[sizeof("net/ipv6/conf/") + IFNAMSIZ];
 
 	t = kmemdup(&addrconf_sysctl, sizeof(*t), GFP_KERNEL);
-	if (t == NULL)
+	if (!t)
 		goto out;
 
 	for (i = 0; t->addrconf_vars[i].data; i++) {
@@ -5234,7 +5608,7 @@ static int __addrconf_sysctl_register(struct net *net, char *dev_name,
 	snprintf(path, sizeof(path), "net/ipv6/conf/%s", dev_name);
 
 	t->sysctl_header = register_net_sysctl(net, path, t->addrconf_vars);
-	if (t->sysctl_header == NULL)
+	if (!t->sysctl_header)
 		goto free;
 
 	p->sysctl = t;
@@ -5250,7 +5624,7 @@ static void __addrconf_sysctl_unregister(struct ipv6_devconf *p)
 {
 	struct addrconf_sysctl_table *t;
 
-	if (p->sysctl == NULL)
+	if (!p->sysctl)
 		return;
 
 	t = p->sysctl;
@@ -5293,17 +5667,20 @@ static int __net_init addrconf_init_net(struct net *net)
 	struct ipv6_devconf *all, *dflt;
 
 	all = kmemdup(&ipv6_devconf, sizeof(ipv6_devconf), GFP_KERNEL);
-	if (all == NULL)
+	if (!all)
 		goto err_alloc_all;
 
 	dflt = kmemdup(&ipv6_devconf_dflt, sizeof(ipv6_devconf_dflt), GFP_KERNEL);
-	if (dflt == NULL)
+	if (!dflt)
 		goto err_alloc_dflt;
 
 	/* these will be inherited by all namespaces */
 	dflt->autoconf = ipv6_defaults.autoconf;
 	dflt->disable_ipv6 = ipv6_defaults.disable_ipv6;
 
+	dflt->stable_secret.initialized = false;
+	all->stable_secret.initialized = false;
+
 	net->ipv6.devconf_all = all;
 	net->ipv6.devconf_dflt = dflt;
 
@@ -5336,10 +5713,8 @@ static void __net_exit addrconf_exit_net(struct net *net)
 	__addrconf_sysctl_unregister(net->ipv6.devconf_dflt);
 	__addrconf_sysctl_unregister(net->ipv6.devconf_all);
 #endif
-	if (!net_eq(net, &init_net)) {
-		kfree(net->ipv6.devconf_dflt);
-		kfree(net->ipv6.devconf_all);
-	}
+	kfree(net->ipv6.devconf_dflt);
+	kfree(net->ipv6.devconf_all);
 }
 
 static struct pernet_operations addrconf_ops = {
@@ -5347,10 +5722,11 @@ static struct pernet_operations addrconf_ops = {
 	.exit = addrconf_exit_net,
 };
 
-static struct rtnl_af_ops inet6_ops = {
+static struct rtnl_af_ops inet6_ops __read_mostly = {
 	.family		  = AF_INET6,
 	.fill_link_af	  = inet6_fill_link_af,
 	.get_link_af_size = inet6_get_link_af_size,
+	.validate_link_af = inet6_validate_link_af,
 	.set_link_af	  = inet6_set_link_af,
 };
 
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index 98cc4cd570e2..ca09bf49ac68 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -133,6 +133,14 @@ static void snmp6_free_dev(struct inet6_dev *idev)
 	free_percpu(idev->stats.ipv6);
 }
 
+static void in6_dev_finish_destroy_rcu(struct rcu_head *head)
+{
+	struct inet6_dev *idev = container_of(head, struct inet6_dev, rcu);
+
+	snmp6_free_dev(idev);
+	kfree(idev);
+}
+
 /* Nobody refers to this device, we may destroy it. */
 
 void in6_dev_finish_destroy(struct inet6_dev *idev)
@@ -140,7 +148,7 @@ void in6_dev_finish_destroy(struct inet6_dev *idev)
 	struct net_device *dev = idev->dev;
 
 	WARN_ON(!list_empty(&idev->addr_list));
-	WARN_ON(idev->mc_list != NULL);
+	WARN_ON(idev->mc_list);
 	WARN_ON(timer_pending(&idev->rs_timer));
 
 #ifdef NET_REFCNT_DEBUG
@@ -151,7 +159,6 @@ void in6_dev_finish_destroy(struct inet6_dev *idev)
 		pr_warn("Freeing alive inet6 device %p\n", idev);
 		return;
 	}
-	snmp6_free_dev(idev);
-	kfree_rcu(idev, rcu);
+	call_rcu(&idev->rcu, in6_dev_finish_destroy_rcu);
 }
 EXPORT_SYMBOL(in6_dev_finish_destroy);
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index fd0dc47f471d..882124ebb438 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -29,9 +29,7 @@
  * Policy Table
  */
 struct ip6addrlbl_entry {
-#ifdef CONFIG_NET_NS
-	struct net *lbl_net;
-#endif
+	possible_net_t lbl_net;
 	struct in6_addr prefix;
 	int prefixlen;
 	int ifindex;
@@ -129,9 +127,6 @@ static const __net_initconst struct ip6addrlbl_init_table
 /* Object management */
 static inline void ip6addrlbl_free(struct ip6addrlbl_entry *p)
 {
-#ifdef CONFIG_NET_NS
-	release_net(p->lbl_net);
-#endif
 	kfree(p);
 }
 
@@ -240,9 +235,7 @@ static struct ip6addrlbl_entry *ip6addrlbl_alloc(struct net *net,
 	newp->addrtype = addrtype;
 	newp->label = label;
 	INIT_HLIST_NODE(&newp->list);
-#ifdef CONFIG_NET_NS
-	newp->lbl_net = hold_net(net);
-#endif
+	write_pnet(&newp->lbl_net, net);
 	atomic_set(&newp->refcnt, 1);
 	return newp;
 }
@@ -484,13 +477,14 @@ static int ip6addrlbl_fill(struct sk_buff *skb,
 
 	ip6addrlbl_putmsg(nlh, p->prefixlen, p->ifindex, lseq);
 
-	if (nla_put(skb, IFAL_ADDRESS, 16, &p->prefix) < 0 ||
+	if (nla_put_in6_addr(skb, IFAL_ADDRESS, &p->prefix) < 0 ||
 	    nla_put_u32(skb, IFAL_LABEL, p->label) < 0) {
 		nlmsg_cancel(skb, nlh);
 		return -EMSGSIZE;
 	}
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 }
 
 static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb)
@@ -510,7 +504,7 @@ static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb)
 					      cb->nlh->nlmsg_seq,
 					      RTM_NEWADDRLABEL,
 					      NLM_F_MULTI);
-			if (err <= 0)
+			if (err < 0)
 				break;
 		}
 		idx++;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index e8c4400f23e9..eef63b394c5a 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -164,11 +164,11 @@ lookup_protocol:
 	answer_flags = answer->flags;
 	rcu_read_unlock();
 
-	WARN_ON(answer_prot->slab == NULL);
+	WARN_ON(!answer_prot->slab);
 
 	err = -ENOBUFS;
 	sk = sk_alloc(net, PF_INET6, GFP_KERNEL, answer_prot);
-	if (sk == NULL)
+	if (!sk)
 		goto out;
 
 	sock_init_data(sock, sk);
@@ -391,7 +391,7 @@ int inet6_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
 
-	if (sk == NULL)
+	if (!sk)
 		return -EINVAL;
 
 	/* Free mc lists */
@@ -413,11 +413,11 @@ void inet6_destroy_sock(struct sock *sk)
 	/* Release rx options */
 
 	skb = xchg(&np->pktoptions, NULL);
-	if (skb != NULL)
+	if (skb)
 		kfree_skb(skb);
 
 	skb = xchg(&np->rxpmtu, NULL);
-	if (skb != NULL)
+	if (skb)
 		kfree_skb(skb);
 
 	/* Free flowlabels */
@@ -426,7 +426,7 @@ void inet6_destroy_sock(struct sock *sk)
 	/* Free tx options */
 
 	opt = xchg(&np->opt, NULL);
-	if (opt != NULL)
+	if (opt)
 		sock_kfree_s(sk, opt, opt->tot_len);
 }
 EXPORT_SYMBOL_GPL(inet6_destroy_sock);
@@ -640,7 +640,7 @@ int inet6_sk_rebuild_header(struct sock *sk)
 
 	dst = __sk_dst_check(sk, np->dst_cookie);
 
-	if (dst == NULL) {
+	if (!dst) {
 		struct inet_sock *inet = inet_sk(sk);
 		struct in6_addr *final_p, final;
 		struct flowi6 fl6;
@@ -766,6 +766,8 @@ static int __net_init inet6_net_init(struct net *net)
 	net->ipv6.sysctl.icmpv6_time = 1*HZ;
 	net->ipv6.sysctl.flowlabel_consistency = 1;
 	net->ipv6.sysctl.auto_flowlabels = 0;
+	net->ipv6.sysctl.idgen_retries = 3;
+	net->ipv6.sysctl.idgen_delay = 1 * HZ;
 	atomic_set(&net->ipv6.fib6_sernum, 1);
 
 	err = ipv6_init_mibs(net);
@@ -824,7 +826,7 @@ static int __init inet6_init(void)
 	struct list_head *r;
 	int err = 0;
 
-	BUILD_BUG_ON(sizeof(struct inet6_skb_parm) > FIELD_SIZEOF(struct sk_buff, cb));
+	sock_skb_cb_check_size(sizeof(struct inet6_skb_parm));
 
 	/* Register the socket-side information for inet6_create.  */
 	for (r = &inetsw6[0]; r < &inetsw6[SOCK_MAX]; ++r)
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index 6d16eb0e0c7f..ed7d4e3f9c10 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -272,10 +272,9 @@ static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len, int dir)
 				ipv6_rearrange_destopt(iph, exthdr.opth);
 		case NEXTHDR_HOP:
 			if (!zero_out_mutable_opts(exthdr.opth)) {
-				LIMIT_NETDEBUG(
-					KERN_WARNING "overrun %sopts\n",
-					nexthdr == NEXTHDR_HOP ?
-						"hop" : "dest");
+				net_dbg_ratelimited("overrun %sopts\n",
+						    nexthdr == NEXTHDR_HOP ?
+						    "hop" : "dest");
 				return -EINVAL;
 			}
 			break;
@@ -354,7 +353,8 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb)
 	ahp = x->data;
 	ahash = ahp->ahash;
 
-	if ((err = skb_cow_data(skb, 0, &trailer)) < 0)
+	err = skb_cow_data(skb, 0, &trailer);
+	if (err < 0)
 		goto out;
 	nfrags = err;
 
@@ -560,8 +560,8 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb)
 	if (!pskb_may_pull(skb, ah_hlen))
 		goto out;
 
-
-	if ((err = skb_cow_data(skb, 0, &trailer)) < 0)
+	err = skb_cow_data(skb, 0, &trailer);
+	if (err < 0)
 		goto out;
 	nfrags = err;
 
@@ -681,7 +681,7 @@ static int ah6_init_state(struct xfrm_state *x)
 		goto error;
 
 	ahp = kzalloc(sizeof(*ahp), GFP_KERNEL);
-	if (ahp == NULL)
+	if (!ahp)
 		return -ENOMEM;
 
 	ahash = crypto_alloc_ahash(x->aalg->alg_name, 0, 0);
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index baf2742d1ec4..514ac259f543 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -60,6 +60,8 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	int	ishost = !net->ipv6.devconf_all->forwarding;
 	int	err = 0;
 
+	ASSERT_RTNL();
+
 	if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 	if (ipv6_addr_is_multicast(addr))
@@ -68,12 +70,11 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 		return -EINVAL;
 
 	pac = sock_kmalloc(sk, sizeof(struct ipv6_ac_socklist), GFP_KERNEL);
-	if (pac == NULL)
+	if (!pac)
 		return -ENOMEM;
 	pac->acl_next = NULL;
 	pac->acl_addr = *addr;
 
-	rtnl_lock();
 	if (ifindex == 0) {
 		struct rt6_info *rt;
 
@@ -92,7 +93,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	} else
 		dev = __dev_get_by_index(net, ifindex);
 
-	if (dev == NULL) {
+	if (!dev) {
 		err = -ENODEV;
 		goto error;
 	}
@@ -130,7 +131,6 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	}
 
 error:
-	rtnl_unlock();
 	if (pac)
 		sock_kfree_s(sk, pac, sizeof(*pac));
 	return err;
@@ -146,7 +146,8 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	struct ipv6_ac_socklist *pac, *prev_pac;
 	struct net *net = sock_net(sk);
 
-	rtnl_lock();
+	ASSERT_RTNL();
+
 	prev_pac = NULL;
 	for (pac = np->ipv6_ac_list; pac; pac = pac->acl_next) {
 		if ((ifindex == 0 || pac->acl_ifindex == ifindex) &&
@@ -154,10 +155,8 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
 			break;
 		prev_pac = pac;
 	}
-	if (!pac) {
-		rtnl_unlock();
+	if (!pac)
 		return -ENOENT;
-	}
 	if (prev_pac)
 		prev_pac->acl_next = pac->acl_next;
 	else
@@ -166,7 +165,6 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	dev = __dev_get_by_index(net, pac->acl_ifindex);
 	if (dev)
 		ipv6_dev_ac_dec(dev, &pac->acl_addr);
-	rtnl_unlock();
 
 	sock_kfree_s(sk, pac, sizeof(*pac));
 	return 0;
@@ -224,7 +222,7 @@ static struct ifacaddr6 *aca_alloc(struct rt6_info *rt,
 	struct ifacaddr6 *aca;
 
 	aca = kzalloc(sizeof(*aca), GFP_ATOMIC);
-	if (aca == NULL)
+	if (!aca)
 		return NULL;
 
 	aca->aca_addr = *addr;
@@ -270,7 +268,7 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr)
 		goto out;
 	}
 	aca = aca_alloc(rt, addr);
-	if (aca == NULL) {
+	if (!aca) {
 		ip6_rt_put(rt);
 		err = -ENOMEM;
 		goto out;
@@ -339,7 +337,7 @@ static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr)
 {
 	struct inet6_dev *idev = __in6_dev_get(dev);
 
-	if (idev == NULL)
+	if (!idev)
 		return -ENODEV;
 	return __ipv6_dev_ac_dec(idev, addr);
 }
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 2cdc38338be3..762a58c772b8 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -71,7 +71,7 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 		fl6.flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK;
 		if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) {
 			flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
-			if (flowlabel == NULL)
+			if (!flowlabel)
 				return -EINVAL;
 		}
 	}
@@ -325,6 +325,36 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu)
 	kfree_skb(skb);
 }
 
+/* IPv6 supports cmsg on all origins aside from SO_EE_ORIGIN_LOCAL.
+ *
+ * At one point, excluding local errors was a quick test to identify icmp/icmp6
+ * errors. This is no longer true, but the test remained, so the v6 stack,
+ * unlike v4, also honors cmsg requests on all wifi and timestamp errors.
+ *
+ * Timestamp code paths do not initialize the fields expected by cmsg:
+ * the PKTINFO fields in skb->cb[]. Fill those in here.
+ */
+static bool ip6_datagram_support_cmsg(struct sk_buff *skb,
+				      struct sock_exterr_skb *serr)
+{
+	if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP ||
+	    serr->ee.ee_origin == SO_EE_ORIGIN_ICMP6)
+		return true;
+
+	if (serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL)
+		return false;
+
+	if (!skb->dev)
+		return false;
+
+	if (skb->protocol == htons(ETH_P_IPV6))
+		IP6CB(skb)->iif = skb->dev->ifindex;
+	else
+		PKTINFO_SKB_CB(skb)->ipi_ifindex = skb->dev->ifindex;
+
+	return true;
+}
+
 /*
  *	Handle MSG_ERRQUEUE
  */
@@ -343,7 +373,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 
 	err = -EAGAIN;
 	skb = sock_dequeue_err_skb(sk);
-	if (skb == NULL)
+	if (!skb)
 		goto out;
 
 	copied = skb->len;
@@ -351,7 +381,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 		msg->msg_flags |= MSG_TRUNC;
 		copied = len;
 	}
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (err)
 		goto out_free_skb;
 
@@ -359,7 +389,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 
 	serr = SKB_EXT_ERR(skb);
 
-	if (sin) {
+	if (sin && serr->port) {
 		const unsigned char *nh = skb_network_header(skb);
 		sin->sin6_family = AF_INET6;
 		sin->sin6_flowinfo = 0;
@@ -383,11 +413,10 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 
 	memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));
 	sin = &errhdr.offender;
-	sin->sin6_family = AF_UNSPEC;
-	if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) {
+	memset(sin, 0, sizeof(*sin));
+
+	if (ip6_datagram_support_cmsg(skb, serr)) {
 		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)) {
@@ -398,12 +427,9 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 				ipv6_iface_scope_id(&sin->sin6_addr,
 						    IP6CB(skb)->iif);
 		} else {
-			struct inet_sock *inet = inet_sk(sk);
-
 			ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr,
 					       &sin->sin6_addr);
-			sin->sin6_scope_id = 0;
-			if (inet->cmsg_flags)
+			if (inet_sk(sk)->cmsg_flags)
 				ip_cmsg_recv(msg, skb);
 		}
 	}
@@ -437,7 +463,7 @@ int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len,
 
 	err = -EAGAIN;
 	skb = xchg(&np->rxpmtu, NULL);
-	if (skb == NULL)
+	if (!skb)
 		goto out;
 
 	copied = skb->len;
@@ -445,7 +471,7 @@ int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len,
 		msg->msg_flags |= MSG_TRUNC;
 		copied = len;
 	}
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (err)
 		goto out_free_skb;
 
@@ -491,7 +517,10 @@ void ip6_datagram_recv_common_ctl(struct sock *sk, struct msghdr *msg,
 			ipv6_addr_set_v4mapped(ip_hdr(skb)->daddr,
 					       &src_info.ipi6_addr);
 		}
-		put_cmsg(msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info);
+
+		if (src_info.ipi6_ifindex >= 0)
+			put_cmsg(msg, SOL_IPV6, IPV6_PKTINFO,
+				 sizeof(src_info), &src_info);
 	}
 }
 
@@ -640,7 +669,7 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
 	int len;
 	int err = 0;
 
-	for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) {
+	for_each_cmsghdr(cmsg, msg) {
 		int addr_type;
 
 		if (!CMSG_OK(msg, cmsg)) {
@@ -893,8 +922,8 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
 			break;
 		    }
 		default:
-			LIMIT_NETDEBUG(KERN_DEBUG "invalid cmsg type: %d\n",
-				       cmsg->cmsg_type);
+			net_dbg_ratelimited("invalid cmsg type: %d\n",
+					    cmsg->cmsg_type);
 			err = -EINVAL;
 			goto exit_f;
 		}
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 83fc3a385a26..060a60b2f8a6 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -76,7 +76,7 @@ static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int seqihlen)
 		len = ALIGN(len, crypto_tfm_ctx_alignment());
 	}
 
-	len += sizeof(struct aead_givcrypt_request) + crypto_aead_reqsize(aead);
+	len += sizeof(struct aead_request) + crypto_aead_reqsize(aead);
 	len = ALIGN(len, __alignof__(struct scatterlist));
 
 	len += sizeof(struct scatterlist) * nfrags;
@@ -96,17 +96,6 @@ static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int seqhilen)
 			 crypto_aead_alignmask(aead) + 1) : tmp + seqhilen;
 }
 
-static inline struct aead_givcrypt_request *esp_tmp_givreq(
-	struct crypto_aead *aead, u8 *iv)
-{
-	struct aead_givcrypt_request *req;
-
-	req = (void *)PTR_ALIGN(iv + crypto_aead_ivsize(aead),
-				crypto_tfm_ctx_alignment());
-	aead_givcrypt_set_tfm(req, aead);
-	return req;
-}
-
 static inline struct aead_request *esp_tmp_req(struct crypto_aead *aead, u8 *iv)
 {
 	struct aead_request *req;
@@ -125,14 +114,6 @@ static inline struct scatterlist *esp_req_sg(struct crypto_aead *aead,
 			     __alignof__(struct scatterlist));
 }
 
-static inline struct scatterlist *esp_givreq_sg(
-	struct crypto_aead *aead, struct aead_givcrypt_request *req)
-{
-	return (void *)ALIGN((unsigned long)(req + 1) +
-			     crypto_aead_reqsize(aead),
-			     __alignof__(struct scatterlist));
-}
-
 static void esp_output_done(struct crypto_async_request *base, int err)
 {
 	struct sk_buff *skb = base->data;
@@ -141,32 +122,57 @@ static void esp_output_done(struct crypto_async_request *base, int err)
 	xfrm_output_resume(skb, err);
 }
 
+/* Move ESP header back into place. */
+static void esp_restore_header(struct sk_buff *skb, unsigned int offset)
+{
+	struct ip_esp_hdr *esph = (void *)(skb->data + offset);
+	void *tmp = ESP_SKB_CB(skb)->tmp;
+	__be32 *seqhi = esp_tmp_seqhi(tmp);
+
+	esph->seq_no = esph->spi;
+	esph->spi = *seqhi;
+}
+
+static void esp_output_restore_header(struct sk_buff *skb)
+{
+	esp_restore_header(skb, skb_transport_offset(skb) - sizeof(__be32));
+}
+
+static void esp_output_done_esn(struct crypto_async_request *base, int err)
+{
+	struct sk_buff *skb = base->data;
+
+	esp_output_restore_header(skb);
+	esp_output_done(base, err);
+}
+
 static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
 {
 	int err;
 	struct ip_esp_hdr *esph;
 	struct crypto_aead *aead;
-	struct aead_givcrypt_request *req;
+	struct aead_request *req;
 	struct scatterlist *sg;
-	struct scatterlist *asg;
 	struct sk_buff *trailer;
 	void *tmp;
 	int blksize;
 	int clen;
 	int alen;
 	int plen;
+	int ivlen;
 	int tfclen;
 	int nfrags;
 	int assoclen;
-	int sglists;
 	int seqhilen;
 	u8 *iv;
 	u8 *tail;
 	__be32 *seqhi;
+	__be64 seqno;
 
 	/* skb is pure payload to encrypt */
 	aead = x->data;
 	alen = crypto_aead_authsize(aead);
+	ivlen = crypto_aead_ivsize(aead);
 
 	tfclen = 0;
 	if (x->tfcpad) {
@@ -187,16 +193,14 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
 	nfrags = err;
 
 	assoclen = sizeof(*esph);
-	sglists = 1;
 	seqhilen = 0;
 
 	if (x->props.flags & XFRM_STATE_ESN) {
-		sglists += 2;
 		seqhilen += sizeof(__be32);
 		assoclen += seqhilen;
 	}
 
-	tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen);
+	tmp = esp_alloc_tmp(aead, nfrags, seqhilen);
 	if (!tmp) {
 		err = -ENOMEM;
 		goto error;
@@ -204,9 +208,8 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
 
 	seqhi = esp_tmp_seqhi(tmp);
 	iv = esp_tmp_iv(aead, tmp, seqhilen);
-	req = esp_tmp_givreq(aead, iv);
-	asg = esp_givreq_sg(aead, req);
-	sg = asg + sglists;
+	req = esp_tmp_req(aead, iv);
+	sg = esp_req_sg(aead, req);
 
 	/* Fill padding... */
 	tail = skb_tail_pointer(trailer);
@@ -227,36 +230,53 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
 	esph = ip_esp_hdr(skb);
 	*skb_mac_header(skb) = IPPROTO_ESP;
 
-	esph->spi = x->id.spi;
 	esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
 
+	aead_request_set_callback(req, 0, esp_output_done, skb);
+
+	/* For ESN we move the header forward by 4 bytes to
+	 * accomodate the high bits.  We will move it back after
+	 * encryption.
+	 */
+	if ((x->props.flags & XFRM_STATE_ESN)) {
+		esph = (void *)(skb_transport_header(skb) - sizeof(__be32));
+		*seqhi = esph->spi;
+		esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
+		aead_request_set_callback(req, 0, esp_output_done_esn, skb);
+	}
+
+	esph->spi = x->id.spi;
+
 	sg_init_table(sg, nfrags);
 	skb_to_sgvec(skb, sg,
-		     esph->enc_data + crypto_aead_ivsize(aead) - skb->data,
-		     clen + alen);
+		     (unsigned char *)esph - skb->data,
+		     assoclen + ivlen + clen + alen);
 
-	if ((x->props.flags & XFRM_STATE_ESN)) {
-		sg_init_table(asg, 3);
-		sg_set_buf(asg, &esph->spi, sizeof(__be32));
-		*seqhi = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
-		sg_set_buf(asg + 1, seqhi, seqhilen);
-		sg_set_buf(asg + 2, &esph->seq_no, sizeof(__be32));
-	} else
-		sg_init_one(asg, esph, sizeof(*esph));
-
-	aead_givcrypt_set_callback(req, 0, esp_output_done, skb);
-	aead_givcrypt_set_crypt(req, sg, sg, clen, iv);
-	aead_givcrypt_set_assoc(req, asg, assoclen);
-	aead_givcrypt_set_giv(req, esph->enc_data,
-			      XFRM_SKB_CB(skb)->seq.output.low);
+	aead_request_set_crypt(req, sg, sg, ivlen + clen, iv);
+	aead_request_set_ad(req, assoclen);
+
+	seqno = cpu_to_be64(XFRM_SKB_CB(skb)->seq.output.low +
+			    ((u64)XFRM_SKB_CB(skb)->seq.output.hi << 32));
+
+	memset(iv, 0, ivlen);
+	memcpy(iv + ivlen - min(ivlen, 8), (u8 *)&seqno + 8 - min(ivlen, 8),
+	       min(ivlen, 8));
 
 	ESP_SKB_CB(skb)->tmp = tmp;
-	err = crypto_aead_givencrypt(req);
-	if (err == -EINPROGRESS)
+	err = crypto_aead_encrypt(req);
+
+	switch (err) {
+	case -EINPROGRESS:
 		goto error;
 
-	if (err == -EBUSY)
+	case -EBUSY:
 		err = NET_XMIT_DROP;
+		break;
+
+	case 0:
+		if ((x->props.flags & XFRM_STATE_ESN))
+			esp_output_restore_header(skb);
+	}
 
 	kfree(tmp);
 
@@ -286,8 +306,8 @@ static int esp_input_done2(struct sk_buff *skb, int err)
 	err = -EINVAL;
 	padlen = nexthdr[0];
 	if (padlen + 2 + alen >= elen) {
-		LIMIT_NETDEBUG(KERN_WARNING "ipsec esp packet is garbage "
-			       "padlen=%d, elen=%d\n", padlen + 2, elen - alen);
+		net_dbg_ratelimited("ipsec esp packet is garbage padlen=%d, elen=%d\n",
+				    padlen + 2, elen - alen);
 		goto out;
 	}
 
@@ -317,25 +337,38 @@ static void esp_input_done(struct crypto_async_request *base, int err)
 	xfrm_input_resume(skb, esp_input_done2(skb, err));
 }
 
+static void esp_input_restore_header(struct sk_buff *skb)
+{
+	esp_restore_header(skb, 0);
+	__skb_pull(skb, 4);
+}
+
+static void esp_input_done_esn(struct crypto_async_request *base, int err)
+{
+	struct sk_buff *skb = base->data;
+
+	esp_input_restore_header(skb);
+	esp_input_done(base, err);
+}
+
 static int esp6_input(struct xfrm_state *x, struct sk_buff *skb)
 {
 	struct ip_esp_hdr *esph;
 	struct crypto_aead *aead = x->data;
 	struct aead_request *req;
 	struct sk_buff *trailer;
-	int elen = skb->len - sizeof(*esph) - crypto_aead_ivsize(aead);
+	int ivlen = crypto_aead_ivsize(aead);
+	int elen = skb->len - sizeof(*esph) - ivlen;
 	int nfrags;
 	int assoclen;
-	int sglists;
 	int seqhilen;
 	int ret = 0;
 	void *tmp;
 	__be32 *seqhi;
 	u8 *iv;
 	struct scatterlist *sg;
-	struct scatterlist *asg;
 
-	if (!pskb_may_pull(skb, sizeof(*esph) + crypto_aead_ivsize(aead))) {
+	if (!pskb_may_pull(skb, sizeof(*esph) + ivlen)) {
 		ret = -EINVAL;
 		goto out;
 	}
@@ -345,7 +378,8 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb)
 		goto out;
 	}
 
-	if ((nfrags = skb_cow_data(skb, 0, &trailer)) < 0) {
+	nfrags = skb_cow_data(skb, 0, &trailer);
+	if (nfrags < 0) {
 		ret = -EINVAL;
 		goto out;
 	}
@@ -353,16 +387,14 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb)
 	ret = -ENOMEM;
 
 	assoclen = sizeof(*esph);
-	sglists = 1;
 	seqhilen = 0;
 
 	if (x->props.flags & XFRM_STATE_ESN) {
-		sglists += 2;
 		seqhilen += sizeof(__be32);
 		assoclen += seqhilen;
 	}
 
-	tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen);
+	tmp = esp_alloc_tmp(aead, nfrags, seqhilen);
 	if (!tmp)
 		goto out;
 
@@ -370,36 +402,39 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb)
 	seqhi = esp_tmp_seqhi(tmp);
 	iv = esp_tmp_iv(aead, tmp, seqhilen);
 	req = esp_tmp_req(aead, iv);
-	asg = esp_req_sg(aead, req);
-	sg = asg + sglists;
+	sg = esp_req_sg(aead, req);
 
 	skb->ip_summed = CHECKSUM_NONE;
 
 	esph = (struct ip_esp_hdr *)skb->data;
 
-	/* Get ivec. This can be wrong, check against another impls. */
-	iv = esph->enc_data;
-
-	sg_init_table(sg, nfrags);
-	skb_to_sgvec(skb, sg, sizeof(*esph) + crypto_aead_ivsize(aead), elen);
+	aead_request_set_callback(req, 0, esp_input_done, skb);
 
+	/* For ESN we move the header forward by 4 bytes to
+	 * accomodate the high bits.  We will move it back after
+	 * decryption.
+	 */
 	if ((x->props.flags & XFRM_STATE_ESN)) {
-		sg_init_table(asg, 3);
-		sg_set_buf(asg, &esph->spi, sizeof(__be32));
-		*seqhi = XFRM_SKB_CB(skb)->seq.input.hi;
-		sg_set_buf(asg + 1, seqhi, seqhilen);
-		sg_set_buf(asg + 2, &esph->seq_no, sizeof(__be32));
-	} else
-		sg_init_one(asg, esph, sizeof(*esph));
+		esph = (void *)skb_push(skb, 4);
+		*seqhi = esph->spi;
+		esph->spi = esph->seq_no;
+		esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.input.hi);
+		aead_request_set_callback(req, 0, esp_input_done_esn, skb);
+	}
 
-	aead_request_set_callback(req, 0, esp_input_done, skb);
-	aead_request_set_crypt(req, sg, sg, elen, iv);
-	aead_request_set_assoc(req, asg, assoclen);
+	sg_init_table(sg, nfrags);
+	skb_to_sgvec(skb, sg, 0, skb->len);
+
+	aead_request_set_crypt(req, sg, sg, elen + ivlen, iv);
+	aead_request_set_ad(req, assoclen);
 
 	ret = crypto_aead_decrypt(req);
 	if (ret == -EINPROGRESS)
 		goto out;
 
+	if ((x->props.flags & XFRM_STATE_ESN))
+		esp_input_restore_header(skb);
+
 	ret = esp_input_done2(skb, ret);
 
 out:
@@ -459,10 +494,16 @@ static void esp6_destroy(struct xfrm_state *x)
 
 static int esp_init_aead(struct xfrm_state *x)
 {
+	char aead_name[CRYPTO_MAX_ALG_NAME];
 	struct crypto_aead *aead;
 	int err;
 
-	aead = crypto_alloc_aead(x->aead->alg_name, 0, 0);
+	err = -ENAMETOOLONG;
+	if (snprintf(aead_name, CRYPTO_MAX_ALG_NAME, "%s(%s)",
+		     x->geniv, x->aead->alg_name) >= CRYPTO_MAX_ALG_NAME)
+		goto error;
+
+	aead = crypto_alloc_aead(aead_name, 0, 0);
 	err = PTR_ERR(aead);
 	if (IS_ERR(aead))
 		goto error;
@@ -494,22 +535,26 @@ static int esp_init_authenc(struct xfrm_state *x)
 	int err;
 
 	err = -EINVAL;
-	if (x->ealg == NULL)
+	if (!x->ealg)
 		goto error;
 
 	err = -ENAMETOOLONG;
 
 	if ((x->props.flags & XFRM_STATE_ESN)) {
 		if (snprintf(authenc_name, CRYPTO_MAX_ALG_NAME,
-			     "authencesn(%s,%s)",
+			     "%s%sauthencesn(%s,%s)%s",
+			     x->geniv ?: "", x->geniv ? "(" : "",
 			     x->aalg ? x->aalg->alg_name : "digest_null",
-			     x->ealg->alg_name) >= CRYPTO_MAX_ALG_NAME)
+			     x->ealg->alg_name,
+			     x->geniv ? ")" : "") >= CRYPTO_MAX_ALG_NAME)
 			goto error;
 	} else {
 		if (snprintf(authenc_name, CRYPTO_MAX_ALG_NAME,
-			     "authenc(%s,%s)",
+			     "%s%sauthenc(%s,%s)%s",
+			     x->geniv ?: "", x->geniv ? "(" : "",
 			     x->aalg ? x->aalg->alg_name : "digest_null",
-			     x->ealg->alg_name) >= CRYPTO_MAX_ALG_NAME)
+			     x->ealg->alg_name,
+			     x->geniv ? ")" : "") >= CRYPTO_MAX_ALG_NAME)
 			goto error;
 	}
 
@@ -544,12 +589,12 @@ static int esp_init_authenc(struct xfrm_state *x)
 		BUG_ON(!aalg_desc);
 
 		err = -EINVAL;
-		if (aalg_desc->uinfo.auth.icv_fullbits/8 !=
+		if (aalg_desc->uinfo.auth.icv_fullbits / 8 !=
 		    crypto_aead_authsize(aead)) {
-			NETDEBUG(KERN_INFO "ESP: %s digestsize %u != %hu\n",
-				 x->aalg->alg_name,
-				 crypto_aead_authsize(aead),
-				 aalg_desc->uinfo.auth.icv_fullbits/8);
+			pr_info("ESP: %s digestsize %u != %hu\n",
+				x->aalg->alg_name,
+				crypto_aead_authsize(aead),
+				aalg_desc->uinfo.auth.icv_fullbits / 8);
 			goto free_key;
 		}
 
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index bfde361b6134..a7bbbe45570b 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -47,7 +47,7 @@
 #include <net/xfrm.h>
 #endif
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  *	Parsing tlv encoded headers.
@@ -184,7 +184,7 @@ static bool ipv6_dest_hao(struct sk_buff *skb, int optoff)
 	int ret;
 
 	if (opt->dsthao) {
-		LIMIT_NETDEBUG(KERN_DEBUG "hao duplicated\n");
+		net_dbg_ratelimited("hao duplicated\n");
 		goto discard;
 	}
 	opt->dsthao = opt->dst1;
@@ -193,14 +193,14 @@ static bool ipv6_dest_hao(struct sk_buff *skb, int optoff)
 	hao = (struct ipv6_destopt_hao *)(skb_network_header(skb) + optoff);
 
 	if (hao->length != 16) {
-		LIMIT_NETDEBUG(
-			KERN_DEBUG "hao invalid option length = %d\n", hao->length);
+		net_dbg_ratelimited("hao invalid option length = %d\n",
+				    hao->length);
 		goto discard;
 	}
 
 	if (!(ipv6_addr_type(&hao->addr) & IPV6_ADDR_UNICAST)) {
-		LIMIT_NETDEBUG(
-			KERN_DEBUG "hao is not an unicast addr: %pI6\n", &hao->addr);
+		net_dbg_ratelimited("hao is not an unicast addr: %pI6\n",
+				    &hao->addr);
 		goto discard;
 	}
 
@@ -551,8 +551,8 @@ static bool ipv6_hop_ra(struct sk_buff *skb, int optoff)
 		memcpy(&IP6CB(skb)->ra, nh + optoff + 2, sizeof(IP6CB(skb)->ra));
 		return true;
 	}
-	LIMIT_NETDEBUG(KERN_DEBUG "ipv6_hop_ra: wrong RA length %d\n",
-		       nh[optoff + 1]);
+	net_dbg_ratelimited("ipv6_hop_ra: wrong RA length %d\n",
+			    nh[optoff + 1]);
 	kfree_skb(skb);
 	return false;
 }
@@ -566,8 +566,8 @@ static bool ipv6_hop_jumbo(struct sk_buff *skb, int optoff)
 	u32 pkt_len;
 
 	if (nh[optoff + 1] != 4 || (optoff & 3) != 2) {
-		LIMIT_NETDEBUG(KERN_DEBUG "ipv6_hop_jumbo: wrong jumbo opt length/alignment %d\n",
-			       nh[optoff+1]);
+		net_dbg_ratelimited("ipv6_hop_jumbo: wrong jumbo opt length/alignment %d\n",
+				    nh[optoff+1]);
 		IP6_INC_STATS_BH(net, ipv6_skb_idev(skb),
 				 IPSTATS_MIB_INHDRERRORS);
 		goto drop;
diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index 8af3eb57f438..5c5d23e59da5 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -82,7 +82,7 @@ int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp,
 		if (nexthdr == NEXTHDR_NONE)
 			return -1;
 		hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr);
-		if (hp == NULL)
+		if (!hp)
 			return -1;
 		if (nexthdr == NEXTHDR_FRAGMENT) {
 			__be16 _frag_off, *fp;
@@ -91,7 +91,7 @@ int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp,
 							       frag_off),
 						sizeof(_frag_off),
 						&_frag_off);
-			if (fp == NULL)
+			if (!fp)
 				return -1;
 
 			*frag_offp = *fp;
@@ -218,7 +218,7 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
 		}
 
 		hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr);
-		if (hp == NULL)
+		if (!hp)
 			return -EBADMSG;
 
 		if (nexthdr == NEXTHDR_ROUTING) {
@@ -226,7 +226,7 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
 
 			rh = skb_header_pointer(skb, start, sizeof(_rh),
 						&_rh);
-			if (rh == NULL)
+			if (!rh)
 				return -EBADMSG;
 
 			if (flags && (*flags & IP6_FH_F_SKIP_RH) &&
@@ -245,7 +245,7 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
 							       frag_off),
 						sizeof(_frag_off),
 						&_frag_off);
-			if (fp == NULL)
+			if (!fp)
 				return -EBADMSG;
 
 			_frag_off = ntohs(*fp) & ~0x7;
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index b4d5e1d97c1b..2367a16eae58 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -104,6 +104,7 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
 				goto again;
 			flp6->saddr = saddr;
 		}
+		err = rt->dst.error;
 		goto out;
 	}
 again:
@@ -198,12 +199,10 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 	}
 
 	if (frh->src_len)
-		nla_memcpy(&rule6->src.addr, tb[FRA_SRC],
-			   sizeof(struct in6_addr));
+		rule6->src.addr = nla_get_in6_addr(tb[FRA_SRC]);
 
 	if (frh->dst_len)
-		nla_memcpy(&rule6->dst.addr, tb[FRA_DST],
-			   sizeof(struct in6_addr));
+		rule6->dst.addr = nla_get_in6_addr(tb[FRA_DST]);
 
 	rule6->src.plen = frh->src_len;
 	rule6->dst.plen = frh->dst_len;
@@ -249,11 +248,9 @@ static int fib6_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
 	frh->tos = rule6->tclass;
 
 	if ((rule6->dst.plen &&
-	     nla_put(skb, FRA_DST, sizeof(struct in6_addr),
-		     &rule6->dst.addr)) ||
+	     nla_put_in6_addr(skb, FRA_DST, &rule6->dst.addr)) ||
 	    (rule6->src.plen &&
-	     nla_put(skb, FRA_SRC, sizeof(struct in6_addr),
-		     &rule6->src.addr)))
+	     nla_put_in6_addr(skb, FRA_SRC, &rule6->src.addr)))
 		goto nla_put_failure;
 	return 0;
 
@@ -298,19 +295,16 @@ static int __net_init fib6_rules_net_init(struct net *net)
 	ops = fib_rules_register(&fib6_rules_ops_template, net);
 	if (IS_ERR(ops))
 		return PTR_ERR(ops);
-	net->ipv6.fib6_rules_ops = ops;
-
 
-	err = fib_default_rule_add(net->ipv6.fib6_rules_ops, 0,
-				   RT6_TABLE_LOCAL, 0);
+	err = fib_default_rule_add(ops, 0, RT6_TABLE_LOCAL, 0);
 	if (err)
 		goto out_fib6_rules_ops;
 
-	err = fib_default_rule_add(net->ipv6.fib6_rules_ops,
-				   0x7FFE, RT6_TABLE_MAIN, 0);
+	err = fib_default_rule_add(ops, 0x7FFE, RT6_TABLE_MAIN, 0);
 	if (err)
 		goto out_fib6_rules_ops;
 
+	net->ipv6.fib6_rules_ops = ops;
 out:
 	return err;
 
@@ -321,7 +315,9 @@ out_fib6_rules_ops:
 
 static void __net_exit fib6_rules_net_exit(struct net *net)
 {
+	rtnl_lock();
 	fib_rules_unregister(net->ipv6.fib6_rules_ops);
+	rtnl_unlock();
 }
 
 static struct pernet_operations fib6_rules_net_ops = {
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 97ae70077a4f..2c2b5d51f15c 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -160,8 +160,7 @@ static bool is_ineligible(const struct sk_buff *skb)
 		tp = skb_header_pointer(skb,
 			ptr+offsetof(struct icmp6hdr, icmp6_type),
 			sizeof(_type), &_type);
-		if (tp == NULL ||
-		    !(*tp & ICMPV6_INFOMSG_MASK))
+		if (!tp || !(*tp & ICMPV6_INFOMSG_MASK))
 			return true;
 	}
 	return false;
@@ -231,7 +230,7 @@ static bool opt_unrec(struct sk_buff *skb, __u32 offset)
 
 	offset += skb_network_offset(skb);
 	op = skb_header_pointer(skb, offset, sizeof(_optval), &_optval);
-	if (op == NULL)
+	if (!op)
 		return true;
 	return (*op & 0xC0) == 0x80;
 }
@@ -243,7 +242,8 @@ int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
 	struct icmp6hdr *icmp6h;
 	int err = 0;
 
-	if ((skb = skb_peek(&sk->sk_write_queue)) == NULL)
+	skb = skb_peek(&sk->sk_write_queue);
+	if (!skb)
 		goto out;
 
 	icmp6h = icmp6_hdr(skb);
@@ -338,7 +338,7 @@ static struct dst_entry *icmpv6_route_lookup(struct net *net,
 	 * anycast.
 	 */
 	if (((struct rt6_info *)dst)->rt6i_flags & RTF_ANYCAST) {
-		LIMIT_NETDEBUG(KERN_DEBUG "icmp6_send: acast source\n");
+		net_dbg_ratelimited("icmp6_send: acast source\n");
 		dst_release(dst);
 		return ERR_PTR(-EINVAL);
 	}
@@ -426,7 +426,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	 *	Dest addr check
 	 */
 
-	if ((addr_type & IPV6_ADDR_MULTICAST || skb->pkt_type != PACKET_HOST)) {
+	if (addr_type & IPV6_ADDR_MULTICAST || skb->pkt_type != PACKET_HOST) {
 		if (type != ICMPV6_PKT_TOOBIG &&
 		    !(type == ICMPV6_PARAMPROB &&
 		      code == ICMPV6_UNK_OPTION &&
@@ -452,7 +452,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	 *	and anycast addresses will be checked later.
 	 */
 	if ((addr_type == IPV6_ADDR_ANY) || (addr_type & IPV6_ADDR_MULTICAST)) {
-		LIMIT_NETDEBUG(KERN_DEBUG "icmp6_send: addr_any/mcast source\n");
+		net_dbg_ratelimited("icmp6_send: addr_any/mcast source\n");
 		return;
 	}
 
@@ -460,7 +460,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	 *	Never answer to a ICMP packet.
 	 */
 	if (is_ineligible(skb)) {
-		LIMIT_NETDEBUG(KERN_DEBUG "icmp6_send: no reply to icmp error\n");
+		net_dbg_ratelimited("icmp6_send: no reply to icmp error\n");
 		return;
 	}
 
@@ -478,7 +478,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
 
 	sk = icmpv6_xmit_lock(net);
-	if (sk == NULL)
+	if (!sk)
 		return;
 	sk->sk_mark = mark;
 	np = inet6_sk(sk);
@@ -509,7 +509,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	len = skb->len - msg.offset;
 	len = min_t(unsigned int, len, IPV6_MIN_MTU - sizeof(struct ipv6hdr) - sizeof(struct icmp6hdr));
 	if (len < 0) {
-		LIMIT_NETDEBUG(KERN_DEBUG "icmp: len problem\n");
+		net_dbg_ratelimited("icmp: len problem\n");
 		goto out_dst_release;
 	}
 
@@ -581,7 +581,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
 
 	sk = icmpv6_xmit_lock(net);
-	if (sk == NULL)
+	if (!sk)
 		return;
 	sk->sk_mark = mark;
 	np = inet6_sk(sk);
@@ -679,6 +679,7 @@ static int icmpv6_rcv(struct sk_buff *skb)
 	const struct in6_addr *saddr, *daddr;
 	struct icmp6hdr *hdr;
 	u8 type;
+	bool success = false;
 
 	if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
 		struct sec_path *sp = skb_sec_path(skb);
@@ -706,9 +707,8 @@ static int icmpv6_rcv(struct sk_buff *skb)
 	daddr = &ipv6_hdr(skb)->daddr;
 
 	if (skb_checksum_validate(skb, IPPROTO_ICMPV6, ip6_compute_pseudo)) {
-		LIMIT_NETDEBUG(KERN_DEBUG
-			       "ICMPv6 checksum failed [%pI6c > %pI6c]\n",
-			       saddr, daddr);
+		net_dbg_ratelimited("ICMPv6 checksum failed [%pI6c > %pI6c]\n",
+				    saddr, daddr);
 		goto csum_error;
 	}
 
@@ -727,7 +727,7 @@ static int icmpv6_rcv(struct sk_buff *skb)
 		break;
 
 	case ICMPV6_ECHO_REPLY:
-		ping_rcv(skb);
+		success = ping_rcv(skb);
 		break;
 
 	case ICMPV6_PKT_TOOBIG:
@@ -781,7 +781,7 @@ static int icmpv6_rcv(struct sk_buff *skb)
 		if (type & ICMPV6_INFOMSG_MASK)
 			break;
 
-		LIMIT_NETDEBUG(KERN_DEBUG "icmpv6: msg of unknown type\n");
+		net_dbg_ratelimited("icmpv6: msg of unknown type\n");
 
 		/*
 		 * error of unknown type.
@@ -791,7 +791,14 @@ static int icmpv6_rcv(struct sk_buff *skb)
 		icmpv6_notify(skb, type, hdr->icmp6_code, hdr->icmp6_mtu);
 	}
 
-	kfree_skb(skb);
+	/* until the v6 path can be better sorted assume failure and
+	 * preserve the status quo behaviour for the rest of the paths to here
+	 */
+	if (success)
+		consume_skb(skb);
+	else
+		kfree_skb(skb);
+
 	return 0;
 
 csum_error:
@@ -831,7 +838,7 @@ static int __net_init icmpv6_sk_init(struct net *net)
 
 	net->ipv6.icmp_sk =
 		kzalloc(nr_cpu_ids * sizeof(struct sock *), GFP_KERNEL);
-	if (net->ipv6.icmp_sk == NULL)
+	if (!net->ipv6.icmp_sk)
 		return -ENOMEM;
 
 	for_each_possible_cpu(i) {
@@ -1009,4 +1016,3 @@ struct ctl_table * __net_init ipv6_icmp_sysctl_init(struct net *net)
 	return table;
 }
 #endif
-
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 29b32206e494..6927f3fb5597 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -112,22 +112,20 @@ static u32 inet6_synq_hash(const struct in6_addr *raddr, const __be16 rport,
 	return c & (synq_hsize - 1);
 }
 
-struct request_sock *inet6_csk_search_req(const struct sock *sk,
-					  struct request_sock ***prevp,
+struct request_sock *inet6_csk_search_req(struct sock *sk,
 					  const __be16 rport,
 					  const struct in6_addr *raddr,
 					  const struct in6_addr *laddr,
 					  const int iif)
 {
-	const struct inet_connection_sock *icsk = inet_csk(sk);
+	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt;
-	struct request_sock *req, **prev;
+	struct request_sock *req;
+	u32 hash = inet6_synq_hash(raddr, rport, lopt->hash_rnd,
+				   lopt->nr_table_entries);
 
-	for (prev = &lopt->syn_table[inet6_synq_hash(raddr, rport,
-						     lopt->hash_rnd,
-						     lopt->nr_table_entries)];
-	     (req = *prev) != NULL;
-	     prev = &req->dl_next) {
+	spin_lock(&icsk->icsk_accept_queue.syn_wait_lock);
+	for (req = lopt->syn_table[hash]; req != NULL; req = req->dl_next) {
 		const struct inet_request_sock *ireq = inet_rsk(req);
 
 		if (ireq->ir_rmt_port == rport &&
@@ -135,13 +133,14 @@ struct request_sock *inet6_csk_search_req(const struct sock *sk,
 		    ipv6_addr_equal(&ireq->ir_v6_rmt_addr, raddr) &&
 		    ipv6_addr_equal(&ireq->ir_v6_loc_addr, laddr) &&
 		    (!ireq->ir_iif || ireq->ir_iif == iif)) {
+			atomic_inc(&req->rsk_refcnt);
 			WARN_ON(req->sk != NULL);
-			*prevp = prev;
-			return req;
+			break;
 		}
 	}
+	spin_unlock(&icsk->icsk_accept_queue.syn_wait_lock);
 
-	return NULL;
+	return req;
 }
 EXPORT_SYMBOL_GPL(inet6_csk_search_req);
 
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 051dffb49c90..871641bc1ed4 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -23,11 +23,9 @@
 #include <net/secure_seq.h>
 #include <net/ip.h>
 
-static unsigned int inet6_ehashfn(struct net *net,
-				  const struct in6_addr *laddr,
-				  const u16 lport,
-				  const struct in6_addr *faddr,
-				  const __be16 fport)
+u32 inet6_ehashfn(const struct net *net,
+		  const struct in6_addr *laddr, const u16 lport,
+		  const struct in6_addr *faddr, const __be16 fport)
 {
 	static u32 inet6_ehash_secret __read_mostly;
 	static u32 ipv6_hash_secret __read_mostly;
@@ -44,54 +42,6 @@ static unsigned int inet6_ehashfn(struct net *net,
 			       inet6_ehash_secret + net_hash_mix(net));
 }
 
-static int inet6_sk_ehashfn(const struct sock *sk)
-{
-	const struct inet_sock *inet = inet_sk(sk);
-	const struct in6_addr *laddr = &sk->sk_v6_rcv_saddr;
-	const struct in6_addr *faddr = &sk->sk_v6_daddr;
-	const __u16 lport = inet->inet_num;
-	const __be16 fport = inet->inet_dport;
-	struct net *net = sock_net(sk);
-
-	return inet6_ehashfn(net, laddr, lport, faddr, fport);
-}
-
-int __inet6_hash(struct sock *sk, struct inet_timewait_sock *tw)
-{
-	struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
-	int twrefcnt = 0;
-
-	WARN_ON(!sk_unhashed(sk));
-
-	if (sk->sk_state == TCP_LISTEN) {
-		struct inet_listen_hashbucket *ilb;
-
-		ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)];
-		spin_lock(&ilb->lock);
-		__sk_nulls_add_node_rcu(sk, &ilb->head);
-		spin_unlock(&ilb->lock);
-	} else {
-		unsigned int hash;
-		struct hlist_nulls_head *list;
-		spinlock_t *lock;
-
-		sk->sk_hash = hash = inet6_sk_ehashfn(sk);
-		list = &inet_ehash_bucket(hashinfo, hash)->chain;
-		lock = inet_ehash_lockp(hashinfo, hash);
-		spin_lock(lock);
-		__sk_nulls_add_node_rcu(sk, list);
-		if (tw) {
-			WARN_ON(sk->sk_hash != tw->tw_hash);
-			twrefcnt = inet_twsk_unhash(tw);
-		}
-		spin_unlock(lock);
-	}
-
-	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
-	return twrefcnt;
-}
-EXPORT_SYMBOL(__inet6_hash);
-
 /*
  * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so
  * we need not check it for TCP lookups anymore, thanks Alexey. -DaveM
@@ -296,7 +246,7 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row,
 		*twp = tw;
 	} else if (tw) {
 		/* Silly. Should hash-dance instead... */
-		inet_twsk_deschedule(tw, death_row);
+		inet_twsk_deschedule(tw);
 
 		inet_twsk_put(tw);
 	}
@@ -320,6 +270,6 @@ int inet6_hash_connect(struct inet_timewait_death_row *death_row,
 		       struct sock *sk)
 {
 	return __inet_hash_connect(death_row, sk, inet6_sk_port_offset(sk),
-			__inet6_check_established, __inet6_hash);
+				   __inet6_check_established);
 }
 EXPORT_SYMBOL_GPL(inet6_hash_connect);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index b2d1838897c9..bde57b113009 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -277,7 +277,6 @@ static int fib6_dump_node(struct fib6_walker *w)
 			w->leaf = rt;
 			return 1;
 		}
-		WARN_ON(res == 0);
 	}
 	w->leaf = NULL;
 	return 0;
@@ -630,33 +629,59 @@ static 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)
+static void fib6_copy_metrics(u32 *mp, const struct mx6_config *mxc)
 {
-	struct nlattr *nla;
-	int remaining;
-	u32 *mp;
+	int i;
+
+	for (i = 0; i < RTAX_MAX; i++) {
+		if (test_bit(i, mxc->mx_valid))
+			mp[i] = mxc->mx[i];
+	}
+}
+
+static int fib6_commit_metrics(struct dst_entry *dst, struct mx6_config *mxc)
+{
+	if (!mxc->mx)
+		return 0;
 
 	if (dst->flags & DST_HOST) {
-		mp = dst_metrics_write_ptr(dst);
-	} else {
-		mp = kzalloc(sizeof(u32) * RTAX_MAX, GFP_ATOMIC);
-		if (!mp)
+		u32 *mp = dst_metrics_write_ptr(dst);
+
+		if (unlikely(!mp))
 			return -ENOMEM;
-		dst_init_metrics(dst, mp, 0);
-	}
 
-	nla_for_each_attr(nla, mx, mx_len, remaining) {
-		int type = nla_type(nla);
+		fib6_copy_metrics(mp, mxc);
+	} else {
+		dst_init_metrics(dst, mxc->mx, false);
+
+		/* We've stolen mx now. */
+		mxc->mx = NULL;
+	}
 
-		if (type) {
-			if (type > RTAX_MAX)
-				return -EINVAL;
+	return 0;
+}
 
-			mp[type - 1] = nla_get_u32(nla);
+static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn,
+			  struct net *net)
+{
+	if (atomic_read(&rt->rt6i_ref) != 1) {
+		/* This route is used as dummy address holder in some split
+		 * nodes. It is not leaked, but it still holds other resources,
+		 * which must be released in time. So, scan ascendant nodes
+		 * and replace dummy references to this route with references
+		 * to still alive ones.
+		 */
+		while (fn) {
+			if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) {
+				fn->leaf = fib6_find_prefix(net, fn);
+				atomic_inc(&fn->leaf->rt6i_ref);
+				rt6_release(rt);
+			}
+			fn = fn->parent;
 		}
+		/* No more references are possible at this point. */
+		BUG_ON(atomic_read(&rt->rt6i_ref) != 1);
 	}
-	return 0;
 }
 
 /*
@@ -664,10 +689,11 @@ static int fib6_commit_metrics(struct dst_entry *dst,
  */
 
 static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
-			    struct nl_info *info, struct nlattr *mx, int mx_len)
+			    struct nl_info *info, struct mx6_config *mxc)
 {
 	struct rt6_info *iter = NULL;
 	struct rt6_info **ins;
+	struct rt6_info **fallback_ins = NULL;
 	int replace = (info->nlh &&
 		       (info->nlh->nlmsg_flags & NLM_F_REPLACE));
 	int add = (!info->nlh ||
@@ -691,8 +717,13 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 			    (info->nlh->nlmsg_flags & NLM_F_EXCL))
 				return -EEXIST;
 			if (replace) {
-				found++;
-				break;
+				if (rt_can_ecmp == rt6_qualify_for_ecmp(iter)) {
+					found++;
+					break;
+				}
+				if (rt_can_ecmp)
+					fallback_ins = fallback_ins ?: ins;
+				goto next_iter;
 			}
 
 			if (iter->dst.dev == rt->dst.dev &&
@@ -728,9 +759,17 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 		if (iter->rt6i_metric > rt->rt6i_metric)
 			break;
 
+next_iter:
 		ins = &iter->dst.rt6_next;
 	}
 
+	if (fallback_ins && !found) {
+		/* No ECMP-able route found, replace first non-ECMP one */
+		ins = fallback_ins;
+		iter = *ins;
+		found++;
+	}
+
 	/* Reset round-robin state, if necessary */
 	if (ins == &fn->leaf)
 		fn->rr_ptr = NULL;
@@ -773,11 +812,10 @@ 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;
-		}
+		err = fib6_commit_metrics(&rt->dst, mxc);
+		if (err)
+			return err;
+
 		rt->dst.rt6_next = iter;
 		*ins = rt;
 		rt->rt6i_node = fn;
@@ -791,27 +829,49 @@ add:
 		}
 
 	} else {
+		int nsiblings;
+
 		if (!found) {
 			if (add)
 				goto 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;
-		}
+
+		err = fib6_commit_metrics(&rt->dst, mxc);
+		if (err)
+			return err;
+
 		*ins = rt;
 		rt->rt6i_node = fn;
 		rt->dst.rt6_next = iter->dst.rt6_next;
 		atomic_inc(&rt->rt6i_ref);
 		inet6_rt_notify(RTM_NEWROUTE, rt, info);
-		rt6_release(iter);
 		if (!(fn->fn_flags & RTN_RTINFO)) {
 			info->nl_net->ipv6.rt6_stats->fib_route_nodes++;
 			fn->fn_flags |= RTN_RTINFO;
 		}
+		nsiblings = iter->rt6i_nsiblings;
+		fib6_purge_rt(iter, fn, info->nl_net);
+		rt6_release(iter);
+
+		if (nsiblings) {
+			/* Replacing an ECMP route, remove all siblings */
+			ins = &rt->dst.rt6_next;
+			iter = *ins;
+			while (iter) {
+				if (rt6_qualify_for_ecmp(iter)) {
+					*ins = iter->dst.rt6_next;
+					fib6_purge_rt(iter, fn, info->nl_net);
+					rt6_release(iter);
+					nsiblings--;
+				} else {
+					ins = &iter->dst.rt6_next;
+				}
+				iter = *ins;
+			}
+			WARN_ON(nsiblings != 0);
+		}
 	}
 
 	return 0;
@@ -838,8 +898,8 @@ 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,
-	     struct nlattr *mx, int mx_len)
+int fib6_add(struct fib6_node *root, struct rt6_info *rt,
+	     struct nl_info *info, struct mx6_config *mxc)
 {
 	struct fib6_node *fn, *pn = NULL;
 	int err = -ENOMEM;
@@ -934,7 +994,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
 	}
 #endif
 
-	err = fib6_add_rt2node(fn, rt, info, mx, mx_len);
+	err = fib6_add_rt2node(fn, rt, info, mxc);
 	if (!err) {
 		fib6_start_gc(info->nl_net, rt);
 		if (!(rt->rt6i_flags & RTF_CACHE))
@@ -1181,7 +1241,7 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
 
 		WARN_ON(fn->fn_flags & RTN_RTINFO);
 		WARN_ON(fn->fn_flags & RTN_TL_ROOT);
-		WARN_ON(fn->leaf != NULL);
+		WARN_ON(fn->leaf);
 
 		children = 0;
 		child = NULL;
@@ -1322,24 +1382,7 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp,
 		fn = fib6_repair_tree(net, fn);
 	}
 
-	if (atomic_read(&rt->rt6i_ref) != 1) {
-		/* This route is used as dummy address holder in some split
-		 * nodes. It is not leaked, but it still holds other resources,
-		 * which must be released in time. So, scan ascendant nodes
-		 * and replace dummy references to this route with references
-		 * to still alive ones.
-		 */
-		while (fn) {
-			if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) {
-				fn->leaf = fib6_find_prefix(net, fn);
-				atomic_inc(&fn->leaf->rt6i_ref);
-				rt6_release(rt);
-			}
-			fn = fn->parent;
-		}
-		/* No more references are possible at this point. */
-		BUG_ON(atomic_read(&rt->rt6i_ref) != 1);
-	}
+	fib6_purge_rt(rt, fn, net);
 
 	inet6_rt_notify(RTM_DELROUTE, rt, info);
 	rt6_release(rt);
@@ -1353,7 +1396,7 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info)
 
 #if RT6_DEBUG >= 2
 	if (rt->dst.obsolete > 0) {
-		WARN_ON(fn != NULL);
+		WARN_ON(fn);
 		return -ENOENT;
 	}
 #endif
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 3dd7d4ebd7cd..d491125011c4 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -100,7 +100,6 @@ static void fl_free(struct ip6_flowlabel *fl)
 	if (fl) {
 		if (fl->share == IPV6_FL_S_PROCESS)
 			put_pid(fl->owner.pid);
-		release_net(fl->fl_net);
 		kfree(fl->opt);
 		kfree_rcu(fl, rcu);
 	}
@@ -172,7 +171,7 @@ static void __net_exit ip6_fl_purge(struct net *net)
 {
 	int i;
 
-	spin_lock(&ip6_fl_lock);
+	spin_lock_bh(&ip6_fl_lock);
 	for (i = 0; i <= FL_HASH_MASK; i++) {
 		struct ip6_flowlabel *fl;
 		struct ip6_flowlabel __rcu **flp;
@@ -190,7 +189,7 @@ static void __net_exit ip6_fl_purge(struct net *net)
 			flp = &fl->next;
 		}
 	}
-	spin_unlock(&ip6_fl_lock);
+	spin_unlock_bh(&ip6_fl_lock);
 }
 
 static struct ip6_flowlabel *fl_intern(struct net *net,
@@ -206,7 +205,7 @@ static struct ip6_flowlabel *fl_intern(struct net *net,
 			fl->label = htonl(prandom_u32())&IPV6_FLOWLABEL_MASK;
 			if (fl->label) {
 				lfl = __fl_lookup(net, fl->label);
-				if (lfl == NULL)
+				if (!lfl)
 					break;
 			}
 		}
@@ -220,7 +219,7 @@ static struct ip6_flowlabel *fl_intern(struct net *net,
 		 * with the same label can only appear on another sock
 		 */
 		lfl = __fl_lookup(net, fl->label);
-		if (lfl != NULL) {
+		if (lfl) {
 			atomic_inc(&lfl->users);
 			spin_unlock_bh(&ip6_fl_lock);
 			return lfl;
@@ -298,10 +297,10 @@ struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space,
 {
 	struct ipv6_txoptions *fl_opt = fl->opt;
 
-	if (fopt == NULL || fopt->opt_flen == 0)
+	if (!fopt || fopt->opt_flen == 0)
 		return fl_opt;
 
-	if (fl_opt != NULL) {
+	if (fl_opt) {
 		opt_space->hopopt = fl_opt->hopopt;
 		opt_space->dst0opt = fl_opt->dst0opt;
 		opt_space->srcrt = fl_opt->srcrt;
@@ -367,7 +366,7 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq,
 
 	err = -ENOMEM;
 	fl = kzalloc(sizeof(*fl), GFP_KERNEL);
-	if (fl == NULL)
+	if (!fl)
 		goto done;
 
 	if (olen > 0) {
@@ -377,7 +376,7 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq,
 
 		err = -ENOMEM;
 		fl->opt = kmalloc(sizeof(*fl->opt) + olen, GFP_KERNEL);
-		if (fl->opt == NULL)
+		if (!fl->opt)
 			goto done;
 
 		memset(fl->opt, 0, sizeof(*fl->opt));
@@ -403,7 +402,7 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq,
 		}
 	}
 
-	fl->fl_net = hold_net(net);
+	fl->fl_net = net;
 	fl->expires = jiffies;
 	err = fl6_renew(fl, freq->flr_linger, freq->flr_expires);
 	if (err)
@@ -597,7 +596,7 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
 			return -EINVAL;
 
 		fl = fl_create(net, sk, &freq, optval, optlen, &err);
-		if (fl == NULL)
+		if (!fl)
 			return err;
 		sfl1 = kmalloc(sizeof(*sfl1), GFP_KERNEL);
 
@@ -617,7 +616,7 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
 			}
 			rcu_read_unlock_bh();
 
-			if (fl1 == NULL)
+			if (!fl1)
 				fl1 = fl_lookup(net, freq.flr_label);
 			if (fl1) {
 recheck:
@@ -634,7 +633,7 @@ recheck:
 					goto release;
 
 				err = -ENOMEM;
-				if (sfl1 == NULL)
+				if (!sfl1)
 					goto release;
 				if (fl->linger > fl1->linger)
 					fl1->linger = fl->linger;
@@ -654,11 +653,15 @@ release:
 			goto done;
 
 		err = -ENOMEM;
-		if (sfl1 == NULL || (err = mem_check(sk)) != 0)
+		if (!sfl1)
+			goto done;
+
+		err = mem_check(sk);
+		if (err != 0)
 			goto done;
 
 		fl1 = fl_intern(net, fl, freq.flr_label);
-		if (fl1 != NULL)
+		if (fl1)
 			goto recheck;
 
 		if (!freq.flr_label) {
@@ -769,10 +772,9 @@ static void ip6fl_seq_stop(struct seq_file *seq, void *v)
 static int ip6fl_seq_show(struct seq_file *seq, void *v)
 {
 	struct ip6fl_iter_state *state = ip6fl_seq_private(seq);
-	if (v == SEQ_START_TOKEN)
-		seq_printf(seq, "%-5s %-1s %-6s %-6s %-6s %-8s %-32s %s\n",
-			   "Label", "S", "Owner", "Users", "Linger", "Expires", "Dst", "Opt");
-	else {
+	if (v == SEQ_START_TOKEN) {
+		seq_puts(seq, "Label S Owner  Users  Linger Expires  Dst                              Opt\n");
+	} else {
 		struct ip6_flowlabel *fl = v;
 		seq_printf(seq,
 			   "%05X %-1d %-6d %-6d %-6ld %-8ld %pi6 %-4d\n",
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 4564e1fca3eb..a38d3ac0f18f 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -223,7 +223,7 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev,
 		}
 	}
 
-	if (cand != NULL)
+	if (cand)
 		return cand;
 
 	dev = ign->fb_tunnel_dev;
@@ -395,7 +395,7 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 				flags & GRE_KEY ?
 				*(((__be32 *)p) + (grehlen / 4) - 1) : 0,
 				p[1]);
-	if (t == NULL)
+	if (!t)
 		return;
 
 	switch (type) {
@@ -417,7 +417,7 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		if (code == ICMPV6_HDR_FIELD)
 			teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data);
 
-		if (teli && teli == info - 2) {
+		if (teli && teli == be32_to_cpu(info) - 2) {
 			tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->data[teli];
 			if (tel->encap_limit == 0) {
 				net_warn_ratelimited("%s: Too small encapsulation limit or routing loop in tunnel!\n",
@@ -429,7 +429,7 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		}
 		break;
 	case ICMPV6_PKT_TOOBIG:
-		mtu = info - offset;
+		mtu = be32_to_cpu(info) - offset;
 		if (mtu < IPV6_MIN_MTU)
 			mtu = IPV6_MIN_MTU;
 		t->dev->mtu = mtu;
@@ -502,11 +502,11 @@ static int ip6gre_rcv(struct sk_buff *skb)
 
 		skb->protocol = gre_proto;
 		/* WCCP version 1 and 2 protocol decoding.
-		 * - Change protocol to IP
+		 * - Change protocol to IPv6
 		 * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header
 		 */
 		if (flags == 0 && gre_proto == htons(ETH_P_WCCP)) {
-			skb->protocol = htons(ETH_P_IP);
+			skb->protocol = htons(ETH_P_IPV6);
 			if ((*(h + offset) & 0xF0) != 0x40)
 				offset += 4;
 		}
@@ -760,7 +760,7 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb,
 
 	skb_set_inner_protocol(skb, protocol);
 
-	ip6tunnel_xmit(skb, dev);
+	ip6tunnel_xmit(NULL, skb, dev);
 	if (ndst)
 		ip6_tnl_dst_store(tunnel, ndst);
 	return 0;
@@ -902,7 +902,7 @@ static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb,
 	struct net_device_stats *stats = &t->dev->stats;
 	int ret;
 
-	if (!ip6_tnl_xmit_ctl(t))
+	if (!ip6_tnl_xmit_ctl(t, &t->parms.laddr, &t->parms.raddr))
 		goto tx_err;
 
 	switch (skb->protocol) {
@@ -980,7 +980,7 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu)
 						 &p->raddr, &p->laddr,
 						 p->link, strict);
 
-		if (rt == NULL)
+		if (!rt)
 			return;
 
 		if (rt->dst.dev) {
@@ -1073,7 +1073,7 @@ 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)
+			if (!t)
 				t = netdev_priv(dev);
 		}
 		memset(&p, 0, sizeof(p));
@@ -1105,7 +1105,7 @@ static int ip6gre_tunnel_ioctl(struct net_device *dev,
 		t = ip6gre_tunnel_locate(net, &p1, cmd == SIOCADDTUNNEL);
 
 		if (dev != ign->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
-			if (t != NULL) {
+			if (t) {
 				if (t->dev != dev) {
 					err = -EEXIST;
 					break;
@@ -1144,7 +1144,7 @@ static int ip6gre_tunnel_ioctl(struct net_device *dev,
 			err = -ENOENT;
 			ip6gre_tnl_parm_from_user(&p1, &p);
 			t = ip6gre_tunnel_locate(net, &p1, 0);
-			if (t == NULL)
+			if (!t)
 				goto done;
 			err = -EPERM;
 			if (t == netdev_priv(ign->fb_tunnel_dev))
@@ -1216,6 +1216,7 @@ static const struct net_device_ops ip6gre_netdev_ops = {
 	.ndo_do_ioctl		= ip6gre_tunnel_ioctl,
 	.ndo_change_mtu		= ip6gre_tunnel_change_mtu,
 	.ndo_get_stats64	= ip_tunnel_get_stats64,
+	.ndo_get_iflink		= ip6_tnl_get_iflink,
 };
 
 static void ip6gre_dev_free(struct net_device *dev)
@@ -1238,7 +1239,6 @@ static void ip6gre_tunnel_setup(struct net_device *dev)
 	if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
 		dev->mtu -= 8;
 	dev->flags |= IFF_NOARP;
-	dev->iflink = 0;
 	dev->addr_len = sizeof(struct in6_addr);
 	netif_keep_dst(dev);
 }
@@ -1246,7 +1246,6 @@ static void ip6gre_tunnel_setup(struct net_device *dev)
 static int ip6gre_tunnel_init(struct net_device *dev)
 {
 	struct ip6_tnl *tunnel;
-	int i;
 
 	tunnel = netdev_priv(dev);
 
@@ -1260,18 +1259,10 @@ 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_sw_netstats);
+	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!dev->tstats)
 		return -ENOMEM;
 
-	for_each_possible_cpu(i) {
-		struct pcpu_sw_netstats *ip6gre_tunnel_stats;
-		ip6gre_tunnel_stats = per_cpu_ptr(dev->tstats, i);
-		u64_stats_init(&ip6gre_tunnel_stats->syncp);
-	}
-
-	dev->iflink = tunnel->parms.link;
-
 	return 0;
 }
 
@@ -1313,7 +1304,7 @@ static void ip6gre_destroy_tunnels(struct net *net, struct list_head *head)
 
 			t = rtnl_dereference(ign->tunnels[prio][h]);
 
-			while (t != NULL) {
+			while (t) {
 				/* If dev is in the same netns, it has already
 				 * been added to the list by the previous loop.
 				 */
@@ -1412,7 +1403,7 @@ static int ip6gre_tap_validate(struct nlattr *tb[], struct nlattr *data[])
 		goto out;
 
 	if (data[IFLA_GRE_REMOTE]) {
-		nla_memcpy(&daddr, data[IFLA_GRE_REMOTE], sizeof(struct in6_addr));
+		daddr = nla_get_in6_addr(data[IFLA_GRE_REMOTE]);
 		if (ipv6_addr_any(&daddr))
 			return -EINVAL;
 	}
@@ -1446,10 +1437,10 @@ static void ip6gre_netlink_parms(struct nlattr *data[],
 		parms->o_key = nla_get_be32(data[IFLA_GRE_OKEY]);
 
 	if (data[IFLA_GRE_LOCAL])
-		nla_memcpy(&parms->laddr, data[IFLA_GRE_LOCAL], sizeof(struct in6_addr));
+		parms->laddr = nla_get_in6_addr(data[IFLA_GRE_LOCAL]);
 
 	if (data[IFLA_GRE_REMOTE])
-		nla_memcpy(&parms->raddr, data[IFLA_GRE_REMOTE], sizeof(struct in6_addr));
+		parms->raddr = nla_get_in6_addr(data[IFLA_GRE_REMOTE]);
 
 	if (data[IFLA_GRE_TTL])
 		parms->hop_limit = nla_get_u8(data[IFLA_GRE_TTL]);
@@ -1480,8 +1471,6 @@ static int ip6gre_tap_init(struct net_device *dev)
 	if (!dev->tstats)
 		return -ENOMEM;
 
-	dev->iflink = tunnel->parms.link;
-
 	return 0;
 }
 
@@ -1493,6 +1482,7 @@ static const struct net_device_ops ip6gre_tap_netdev_ops = {
 	.ndo_validate_addr = eth_validate_addr,
 	.ndo_change_mtu = ip6gre_tunnel_change_mtu,
 	.ndo_get_stats64 = ip_tunnel_get_stats64,
+	.ndo_get_iflink = ip6_tnl_get_iflink,
 };
 
 static void ip6gre_tap_setup(struct net_device *dev)
@@ -1503,7 +1493,6 @@ static void ip6gre_tap_setup(struct net_device *dev)
 	dev->netdev_ops = &ip6gre_tap_netdev_ops;
 	dev->destructor = ip6gre_dev_free;
 
-	dev->iflink = 0;
 	dev->features |= NETIF_F_NETNS_LOCAL;
 }
 
@@ -1622,8 +1611,8 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_be16(skb, IFLA_GRE_OFLAGS, p->o_flags) ||
 	    nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) ||
 	    nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) ||
-	    nla_put(skb, IFLA_GRE_LOCAL, sizeof(struct in6_addr), &p->laddr) ||
-	    nla_put(skb, IFLA_GRE_REMOTE, sizeof(struct in6_addr), &p->raddr) ||
+	    nla_put_in6_addr(skb, IFLA_GRE_LOCAL, &p->laddr) ||
+	    nla_put_in6_addr(skb, IFLA_GRE_REMOTE, &p->raddr) ||
 	    nla_put_u8(skb, IFLA_GRE_TTL, p->hop_limit) ||
 	    /*nla_put_u8(skb, IFLA_GRE_TOS, t->priority) ||*/
 	    nla_put_u8(skb, IFLA_GRE_ENCAP_LIMIT, p->encap_limit) ||
@@ -1662,6 +1651,7 @@ static struct rtnl_link_ops ip6gre_link_ops __read_mostly = {
 	.dellink	= ip6gre_dellink,
 	.get_size	= ip6gre_get_size,
 	.fill_info	= ip6gre_fill_info,
+	.get_link_net	= ip6_tnl_get_link_net,
 };
 
 static struct rtnl_link_ops ip6gre_tap_ops __read_mostly = {
@@ -1675,6 +1665,7 @@ static struct rtnl_link_ops ip6gre_tap_ops __read_mostly = {
 	.changelink	= ip6gre_changelink,
 	.get_size	= ip6gre_get_size,
 	.fill_info	= ip6gre_fill_info,
+	.get_link_net	= ip6_tnl_get_link_net,
 };
 
 /*
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index a3084ab5df6c..f2e464eba5ef 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -46,8 +46,7 @@
 #include <net/xfrm.h>
 #include <net/inet_ecn.h>
 
-
-int ip6_rcv_finish(struct sk_buff *skb)
+int ip6_rcv_finish(struct sock *sk, struct sk_buff *skb)
 {
 	if (sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) {
 		const struct inet6_protocol *ipprot;
@@ -183,7 +182,8 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt
 	/* Must drop socket now because of tproxy. */
 	skb_orphan(skb);
 
-	return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, skb, dev, NULL,
+	return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, NULL, skb,
+		       dev, NULL,
 		       ip6_rcv_finish);
 err:
 	IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INHDRERRORS);
@@ -198,7 +198,7 @@ drop:
  */
 
 
-static int ip6_input_finish(struct sk_buff *skb)
+static int ip6_input_finish(struct sock *sk, struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb_dst(skb)->dev);
 	const struct inet6_protocol *ipprot;
@@ -220,7 +220,8 @@ resubmit:
 	nexthdr = skb_network_header(skb)[nhoff];
 
 	raw = raw6_local_deliver(skb, nexthdr);
-	if ((ipprot = rcu_dereference(inet6_protos[nexthdr])) != NULL) {
+	ipprot = rcu_dereference(inet6_protos[nexthdr]);
+	if (ipprot) {
 		int ret;
 
 		if (ipprot->flags & INET6_PROTO_FINAL) {
@@ -276,7 +277,8 @@ discard:
 
 int ip6_input(struct sk_buff *skb)
 {
-	return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_IN, skb, skb->dev, NULL,
+	return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_IN, NULL, skb,
+		       skb->dev, NULL,
 		       ip6_input_finish);
 }
 
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index a071563a7e6e..e893cd18612f 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -69,7 +69,8 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 	int nhoff;
 
 	if (unlikely(skb_shinfo(skb)->gso_type &
-		     ~(SKB_GSO_UDP |
+		     ~(SKB_GSO_TCPV4 |
+		       SKB_GSO_UDP |
 		       SKB_GSO_DODGY |
 		       SKB_GSO_TCP_ECN |
 		       SKB_GSO_GRE |
@@ -78,7 +79,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 		       SKB_GSO_SIT |
 		       SKB_GSO_UDP_TUNNEL |
 		       SKB_GSO_UDP_TUNNEL_CSUM |
-		       SKB_GSO_MPLS |
+		       SKB_GSO_TUNNEL_REMCSUM |
 		       SKB_GSO_TCPV6 |
 		       0)))
 		goto out;
@@ -123,7 +124,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 			unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr);
 			fptr = (struct frag_hdr *)((u8 *)ipv6h + unfrag_ip6hlen);
 			fptr->frag_off = htons(offset);
-			if (skb->next != NULL)
+			if (skb->next)
 				fptr->frag_off |= htons(IP6_MF);
 			offset += (ntohs(ipv6h->payload_len) -
 				   sizeof(struct frag_hdr));
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 8e950c250ada..bc09cb97b840 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -56,7 +56,7 @@
 #include <net/checksum.h>
 #include <linux/mroute6.h>
 
-static int ip6_finish_output2(struct sk_buff *skb)
+static int ip6_finish_output2(struct sock *sk, struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *dev = dst->dev;
@@ -70,7 +70,7 @@ static int ip6_finish_output2(struct sk_buff *skb)
 	if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) {
 		struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
 
-		if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(skb->sk) &&
+		if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(sk) &&
 		    ((mroute6_socket(dev_net(dev), skb) &&
 		     !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) ||
 		     ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr,
@@ -82,7 +82,7 @@ static int ip6_finish_output2(struct sk_buff *skb)
 			 */
 			if (newskb)
 				NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING,
-					newskb, NULL, newskb->dev,
+					sk, newskb, NULL, newskb->dev,
 					dev_loopback_xmit);
 
 			if (ipv6_hdr(skb)->hop_limit == 0) {
@@ -122,14 +122,14 @@ static int ip6_finish_output2(struct sk_buff *skb)
 	return -EINVAL;
 }
 
-static int ip6_finish_output(struct sk_buff *skb)
+static int ip6_finish_output(struct sock *sk, struct sk_buff *skb)
 {
 	if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
 	    dst_allfrag(skb_dst(skb)) ||
 	    (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size))
-		return ip6_fragment(skb, ip6_finish_output2);
+		return ip6_fragment(sk, skb, ip6_finish_output2);
 	else
-		return ip6_finish_output2(skb);
+		return ip6_finish_output2(sk, skb);
 }
 
 int ip6_output(struct sock *sk, struct sk_buff *skb)
@@ -143,7 +143,8 @@ int ip6_output(struct sock *sk, struct sk_buff *skb)
 		return 0;
 	}
 
-	return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb, NULL, dev,
+	return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, sk, skb,
+			    NULL, dev,
 			    ip6_finish_output,
 			    !(IP6CB(skb)->flags & IP6SKB_REROUTED));
 }
@@ -177,7 +178,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 
 		if (skb_headroom(skb) < head_room) {
 			struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room);
-			if (skb2 == NULL) {
+			if (!skb2) {
 				IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
 					      IPSTATS_MIB_OUTDISCARDS);
 				kfree_skb(skb);
@@ -223,8 +224,8 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	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,
-			       dst->dev, dst_output);
+		return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, sk, skb,
+			       NULL, dst->dev, dst_output_sk);
 	}
 
 	skb->dev = dst->dev;
@@ -316,9 +317,10 @@ static int ip6_forward_proxy_check(struct sk_buff *skb)
 	return 0;
 }
 
-static inline int ip6_forward_finish(struct sk_buff *skb)
+static inline int ip6_forward_finish(struct sock *sk, struct sk_buff *skb)
 {
-	return dst_output(skb);
+	skb_sender_cpu_clear(skb);
+	return dst_output_sk(sk, skb);
 }
 
 static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
@@ -510,7 +512,8 @@ int ip6_forward(struct sk_buff *skb)
 
 	IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
 	IP6_ADD_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len);
-	return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, skb, skb->dev, dst->dev,
+	return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, NULL, skb,
+		       skb->dev, dst->dev,
 		       ip6_forward_finish);
 
 error:
@@ -537,25 +540,13 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	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 *))
+int ip6_fragment(struct sock *sk, struct sk_buff *skb,
+		 int (*output)(struct sock *, struct sk_buff *))
 {
 	struct sk_buff *frag;
 	struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
-	struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL;
+	struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ?
+				inet6_sk(skb->sk) : NULL;
 	struct ipv6hdr *tmp_hdr;
 	struct frag_hdr *fh;
 	unsigned int mtu, hlen, left, len;
@@ -641,7 +632,7 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 		skb_reset_network_header(skb);
 		memcpy(skb_network_header(skb), tmp_hdr, hlen);
 
-		ipv6_select_ident(fh, rt);
+		ipv6_select_ident(net, fh, rt);
 		fh->nexthdr = nexthdr;
 		fh->reserved = 0;
 		fh->frag_off = htons(IP6_MF);
@@ -670,7 +661,7 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 				fh->nexthdr = nexthdr;
 				fh->reserved = 0;
 				fh->frag_off = htons(offset);
-				if (frag->next != NULL)
+				if (frag->next)
 					fh->frag_off |= htons(IP6_MF);
 				fh->identification = frag_id;
 				ipv6_hdr(frag)->payload_len =
@@ -679,7 +670,7 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 				ip6_copy_metadata(frag, skb);
 			}
 
-			err = output(skb);
+			err = output(sk, skb);
 			if (!err)
 				IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
 					      IPSTATS_MIB_FRAGCREATES);
@@ -747,13 +738,11 @@ slow_path:
 		if (len < left)	{
 			len &= ~7;
 		}
-		/*
-		 *	Allocate buffer.
-		 */
 
-		if ((frag = alloc_skb(len + hlen + sizeof(struct frag_hdr) +
-				      hroom + troom, GFP_ATOMIC)) == NULL) {
-			NETDEBUG(KERN_INFO "IPv6: frag: no memory for new fragment!\n");
+		/* Allocate buffer */
+		frag = alloc_skb(len + hlen + sizeof(struct frag_hdr) +
+				 hroom + troom, GFP_ATOMIC);
+		if (!frag) {
 			IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
 				      IPSTATS_MIB_FRAGFAILS);
 			err = -ENOMEM;
@@ -790,7 +779,7 @@ slow_path:
 		fh->nexthdr = nexthdr;
 		fh->reserved = 0;
 		if (!frag_id) {
-			ipv6_select_ident(fh, rt);
+			ipv6_select_ident(net, fh, rt);
 			frag_id = fh->identification;
 		} else
 			fh->identification = frag_id;
@@ -814,7 +803,7 @@ slow_path:
 		/*
 		 *	Put this fragment into the sending queue.
 		 */
-		err = output(frag);
+		err = output(sk, frag);
 		if (err)
 			goto fail;
 
@@ -838,7 +827,7 @@ static inline int ip6_rt_check(const struct rt6key *rt_key,
 			       const struct in6_addr *addr_cache)
 {
 	return (rt_key->plen != 128 || !ipv6_addr_equal(fl_addr, &rt_key->addr)) &&
-		(addr_cache == NULL || !ipv6_addr_equal(fl_addr, addr_cache));
+		(!addr_cache || !ipv6_addr_equal(fl_addr, addr_cache));
 }
 
 static struct dst_entry *ip6_sk_dst_check(struct sock *sk,
@@ -897,21 +886,45 @@ static int ip6_dst_lookup_tail(struct sock *sk,
 #endif
 	int err;
 
-	if (*dst == NULL)
-		*dst = ip6_route_output(net, sk, fl6);
-
-	if ((err = (*dst)->error))
-		goto out_err_release;
+	/* The correct way to handle this would be to do
+	 * ip6_route_get_saddr, and then ip6_route_output; however,
+	 * the route-specific preferred source forces the
+	 * ip6_route_output call _before_ ip6_route_get_saddr.
+	 *
+	 * In source specific routing (no src=any default route),
+	 * ip6_route_output will fail given src=any saddr, though, so
+	 * that's why we try it again later.
+	 */
+	if (ipv6_addr_any(&fl6->saddr) && (!*dst || !(*dst)->error)) {
+		struct rt6_info *rt;
+		bool had_dst = *dst != NULL;
 
-	if (ipv6_addr_any(&fl6->saddr)) {
-		struct rt6_info *rt = (struct rt6_info *) *dst;
+		if (!had_dst)
+			*dst = ip6_route_output(net, sk, fl6);
+		rt = (*dst)->error ? NULL : (struct rt6_info *)*dst;
 		err = ip6_route_get_saddr(net, rt, &fl6->daddr,
 					  sk ? inet6_sk(sk)->srcprefs : 0,
 					  &fl6->saddr);
 		if (err)
 			goto out_err_release;
+
+		/* If we had an erroneous initial result, pretend it
+		 * never existed and let the SA-enabled version take
+		 * over.
+		 */
+		if (!had_dst && (*dst)->error) {
+			dst_release(*dst);
+			*dst = NULL;
+		}
 	}
 
+	if (!*dst)
+		*dst = ip6_route_output(net, sk, fl6);
+
+	err = (*dst)->error;
+	if (err)
+		goto out_err_release;
+
 #ifdef CONFIG_IPV6_OPTIMISTIC_DAD
 	/*
 	 * Here if the dst entry we've looked up
@@ -948,7 +961,8 @@ static int ip6_dst_lookup_tail(struct sock *sk,
 			memcpy(&fl_gw6, fl6, sizeof(struct flowi6));
 			memset(&fl_gw6.daddr, 0, sizeof(struct in6_addr));
 			*dst = ip6_route_output(net, sk, &fl_gw6);
-			if ((err = (*dst)->error))
+			err = (*dst)->error;
+			if (err)
 				goto out_err_release;
 		}
 	}
@@ -1041,6 +1055,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
 EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow);
 
 static inline int ip6_ufo_append_data(struct sock *sk,
+			struct sk_buff_head *queue,
 			int getfrag(void *from, char *to, int offset, int len,
 			int odd, struct sk_buff *skb),
 			void *from, int length, int hh_len, int fragheaderlen,
@@ -1056,11 +1071,12 @@ static inline int ip6_ufo_append_data(struct sock *sk,
 	 * device, so create one single skb packet containing complete
 	 * udp datagram
 	 */
-	if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL) {
+	skb = skb_peek_tail(queue);
+	if (!skb) {
 		skb = sock_alloc_send_skb(sk,
 			hh_len + fragheaderlen + transhdrlen + 20,
 			(flags & MSG_DONTWAIT), &err);
-		if (skb == NULL)
+		if (!skb)
 			return err;
 
 		/* reserve space for Hardware header */
@@ -1078,7 +1094,7 @@ static inline int ip6_ufo_append_data(struct sock *sk,
 		skb->protocol = htons(ETH_P_IPV6);
 		skb->csum = 0;
 
-		__skb_queue_tail(&sk->sk_write_queue, skb);
+		__skb_queue_tail(queue, skb);
 	} else if (skb_is_gso(skb)) {
 		goto append;
 	}
@@ -1090,7 +1106,7 @@ static inline int ip6_ufo_append_data(struct sock *sk,
 	skb_shinfo(skb)->gso_size = (mtu - fragheaderlen -
 				     sizeof(struct frag_hdr)) & ~7;
 	skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
-	ipv6_select_ident(&fhdr, rt);
+	ipv6_select_ident(sock_net(sk), &fhdr, rt);
 	skb_shinfo(skb)->ip6_frag_id = fhdr.identification;
 
 append:
@@ -1118,7 +1134,7 @@ static void ip6_append_data_mtu(unsigned int *mtu,
 				unsigned int orig_mtu)
 {
 	if (!(rt->dst.flags & DST_XFRM_TUNNEL)) {
-		if (skb == NULL) {
+		if (!skb) {
 			/* first fragment, reserve header_len */
 			*mtu = orig_mtu - rt->dst.header_len;
 
@@ -1134,99 +1150,106 @@ static void ip6_append_data_mtu(unsigned int *mtu,
 	}
 }
 
-int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
-	int offset, int len, int odd, struct sk_buff *skb),
-	void *from, int length, int transhdrlen,
-	int hlimit, int tclass, struct ipv6_txoptions *opt, struct flowi6 *fl6,
-	struct rt6_info *rt, unsigned int flags, int dontfrag)
+static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
+			  struct inet6_cork *v6_cork,
+			  int hlimit, int tclass, struct ipv6_txoptions *opt,
+			  struct rt6_info *rt, struct flowi6 *fl6)
 {
-	struct inet_sock *inet = inet_sk(sk);
 	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct inet_cork *cork;
+	unsigned int mtu;
+
+	/*
+	 * setup for corking
+	 */
+	if (opt) {
+		if (WARN_ON(v6_cork->opt))
+			return -EINVAL;
+
+		v6_cork->opt = kzalloc(opt->tot_len, sk->sk_allocation);
+		if (unlikely(!v6_cork->opt))
+			return -ENOBUFS;
+
+		v6_cork->opt->tot_len = opt->tot_len;
+		v6_cork->opt->opt_flen = opt->opt_flen;
+		v6_cork->opt->opt_nflen = opt->opt_nflen;
+
+		v6_cork->opt->dst0opt = ip6_opt_dup(opt->dst0opt,
+						    sk->sk_allocation);
+		if (opt->dst0opt && !v6_cork->opt->dst0opt)
+			return -ENOBUFS;
+
+		v6_cork->opt->dst1opt = ip6_opt_dup(opt->dst1opt,
+						    sk->sk_allocation);
+		if (opt->dst1opt && !v6_cork->opt->dst1opt)
+			return -ENOBUFS;
+
+		v6_cork->opt->hopopt = ip6_opt_dup(opt->hopopt,
+						   sk->sk_allocation);
+		if (opt->hopopt && !v6_cork->opt->hopopt)
+			return -ENOBUFS;
+
+		v6_cork->opt->srcrt = ip6_rthdr_dup(opt->srcrt,
+						    sk->sk_allocation);
+		if (opt->srcrt && !v6_cork->opt->srcrt)
+			return -ENOBUFS;
+
+		/* need source address above miyazawa*/
+	}
+	dst_hold(&rt->dst);
+	cork->base.dst = &rt->dst;
+	cork->fl.u.ip6 = *fl6;
+	v6_cork->hop_limit = hlimit;
+	v6_cork->tclass = tclass;
+	if (rt->dst.flags & DST_XFRM_TUNNEL)
+		mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
+		      rt->dst.dev->mtu : dst_mtu(&rt->dst);
+	else
+		mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
+		      rt->dst.dev->mtu : dst_mtu(rt->dst.path);
+	if (np->frag_size < mtu) {
+		if (np->frag_size)
+			mtu = np->frag_size;
+	}
+	cork->base.fragsize = mtu;
+	if (dst_allfrag(rt->dst.path))
+		cork->base.flags |= IPCORK_ALLFRAG;
+	cork->base.length = 0;
+
+	return 0;
+}
+
+static int __ip6_append_data(struct sock *sk,
+			     struct flowi6 *fl6,
+			     struct sk_buff_head *queue,
+			     struct inet_cork *cork,
+			     struct inet6_cork *v6_cork,
+			     struct page_frag *pfrag,
+			     int getfrag(void *from, char *to, int offset,
+					 int len, int odd, struct sk_buff *skb),
+			     void *from, int length, int transhdrlen,
+			     unsigned int flags, int dontfrag)
+{
 	struct sk_buff *skb, *skb_prev = NULL;
 	unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu;
-	int exthdrlen;
-	int dst_exthdrlen;
+	int exthdrlen = 0;
+	int dst_exthdrlen = 0;
 	int hh_len;
 	int copy;
 	int err;
 	int offset = 0;
 	__u8 tx_flags = 0;
 	u32 tskey = 0;
+	struct rt6_info *rt = (struct rt6_info *)cork->dst;
+	struct ipv6_txoptions *opt = v6_cork->opt;
+	int csummode = CHECKSUM_NONE;
 
-	if (flags&MSG_PROBE)
-		return 0;
-	cork = &inet->cork.base;
-	if (skb_queue_empty(&sk->sk_write_queue)) {
-		/*
-		 * setup for corking
-		 */
-		if (opt) {
-			if (WARN_ON(np->cork.opt))
-				return -EINVAL;
-
-			np->cork.opt = kzalloc(opt->tot_len, sk->sk_allocation);
-			if (unlikely(np->cork.opt == NULL))
-				return -ENOBUFS;
-
-			np->cork.opt->tot_len = opt->tot_len;
-			np->cork.opt->opt_flen = opt->opt_flen;
-			np->cork.opt->opt_nflen = opt->opt_nflen;
-
-			np->cork.opt->dst0opt = ip6_opt_dup(opt->dst0opt,
-							    sk->sk_allocation);
-			if (opt->dst0opt && !np->cork.opt->dst0opt)
-				return -ENOBUFS;
-
-			np->cork.opt->dst1opt = ip6_opt_dup(opt->dst1opt,
-							    sk->sk_allocation);
-			if (opt->dst1opt && !np->cork.opt->dst1opt)
-				return -ENOBUFS;
-
-			np->cork.opt->hopopt = ip6_opt_dup(opt->hopopt,
-							   sk->sk_allocation);
-			if (opt->hopopt && !np->cork.opt->hopopt)
-				return -ENOBUFS;
-
-			np->cork.opt->srcrt = ip6_rthdr_dup(opt->srcrt,
-							    sk->sk_allocation);
-			if (opt->srcrt && !np->cork.opt->srcrt)
-				return -ENOBUFS;
-
-			/* need source address above miyazawa*/
-		}
-		dst_hold(&rt->dst);
-		cork->dst = &rt->dst;
-		inet->cork.fl.u.ip6 = *fl6;
-		np->cork.hop_limit = hlimit;
-		np->cork.tclass = tclass;
-		if (rt->dst.flags & DST_XFRM_TUNNEL)
-			mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
-			      rt->dst.dev->mtu : dst_mtu(&rt->dst);
-		else
-			mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
-			      rt->dst.dev->mtu : dst_mtu(rt->dst.path);
-		if (np->frag_size < mtu) {
-			if (np->frag_size)
-				mtu = np->frag_size;
-		}
-		cork->fragsize = mtu;
-		if (dst_allfrag(rt->dst.path))
-			cork->flags |= IPCORK_ALLFRAG;
-		cork->length = 0;
-		exthdrlen = (opt ? opt->opt_flen : 0);
-		length += exthdrlen;
-		transhdrlen += exthdrlen;
+	skb = skb_peek_tail(queue);
+	if (!skb) {
+		exthdrlen = opt ? opt->opt_flen : 0;
 		dst_exthdrlen = rt->dst.header_len - rt->rt6i_nfheader_len;
-	} else {
-		rt = (struct rt6_info *)cork->dst;
-		fl6 = &inet->cork.fl.u.ip6;
-		opt = np->cork.opt;
-		transhdrlen = 0;
-		exthdrlen = 0;
-		dst_exthdrlen = 0;
-		mtu = cork->fragsize;
 	}
+
+	mtu = cork->fragsize;
 	orig_mtu = mtu;
 
 	hh_len = LL_RESERVED_SPACE(rt->dst.dev);
@@ -1275,6 +1298,16 @@ emsgsize:
 			tskey = sk->sk_tskey++;
 	}
 
+	/* If this is the first and only packet and device
+	 * supports checksum offloading, let's use it.
+	 * Use transhdrlen, same as IPv4, because partial
+	 * sums only work when transhdrlen is set.
+	 */
+	if (transhdrlen && sk->sk_protocol == IPPROTO_UDP &&
+	    length + fragheaderlen < mtu &&
+	    rt->dst.dev->features & NETIF_F_V6_CSUM &&
+	    !exthdrlen)
+		csummode = CHECKSUM_PARTIAL;
 	/*
 	 * Let's try using as much space as possible.
 	 * Use MTU if total length of the message fits into the MTU.
@@ -1291,13 +1324,13 @@ emsgsize:
 	 * --yoshfuji
 	 */
 
-	skb = skb_peek_tail(&sk->sk_write_queue);
 	cork->length += length;
 	if (((length > mtu) ||
 	     (skb && skb_is_gso(skb))) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
-	    (rt->dst.dev->features & NETIF_F_UFO)) {
-		err = ip6_ufo_append_data(sk, getfrag, from, length,
+	    (rt->dst.dev->features & NETIF_F_UFO) &&
+	    (sk->sk_type == SOCK_DGRAM)) {
+		err = ip6_ufo_append_data(sk, queue, getfrag, from, length,
 					  hh_len, fragheaderlen,
 					  transhdrlen, mtu, flags, rt);
 		if (err)
@@ -1327,7 +1360,7 @@ alloc_new_skb:
 			else
 				fraggap = 0;
 			/* update mtu and maxfraglen if necessary */
-			if (skb == NULL || skb_prev == NULL)
+			if (!skb || !skb_prev)
 				ip6_append_data_mtu(&mtu, &maxfraglen,
 						    fragheaderlen, skb, rt,
 						    orig_mtu);
@@ -1379,16 +1412,16 @@ alloc_new_skb:
 					skb = sock_wmalloc(sk,
 							   alloclen + hh_len, 1,
 							   sk->sk_allocation);
-				if (unlikely(skb == NULL))
+				if (unlikely(!skb))
 					err = -ENOBUFS;
 			}
-			if (skb == NULL)
+			if (!skb)
 				goto error;
 			/*
 			 *	Fill in the control structures
 			 */
 			skb->protocol = htons(ETH_P_IPV6);
-			skb->ip_summed = CHECKSUM_NONE;
+			skb->ip_summed = csummode;
 			skb->csum = 0;
 			/* reserve for fragmentation and ipsec header */
 			skb_reserve(skb, hh_len + sizeof(struct frag_hdr) +
@@ -1438,7 +1471,7 @@ alloc_new_skb:
 			/*
 			 * Put the packet on the pending queue
 			 */
-			__skb_queue_tail(&sk->sk_write_queue, skb);
+			__skb_queue_tail(queue, skb);
 			continue;
 		}
 
@@ -1457,7 +1490,6 @@ alloc_new_skb:
 			}
 		} else {
 			int i = skb_shinfo(skb)->nr_frags;
-			struct page_frag *pfrag = sk_page_frag(sk);
 
 			err = -ENOMEM;
 			if (!sk_page_frag_refill(sk, pfrag))
@@ -1500,50 +1532,89 @@ error:
 	IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
 	return err;
 }
+
+int ip6_append_data(struct sock *sk,
+		    int getfrag(void *from, char *to, int offset, int len,
+				int odd, struct sk_buff *skb),
+		    void *from, int length, int transhdrlen, int hlimit,
+		    int tclass, struct ipv6_txoptions *opt, struct flowi6 *fl6,
+		    struct rt6_info *rt, unsigned int flags, int dontfrag)
+{
+	struct inet_sock *inet = inet_sk(sk);
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	int exthdrlen;
+	int err;
+
+	if (flags&MSG_PROBE)
+		return 0;
+	if (skb_queue_empty(&sk->sk_write_queue)) {
+		/*
+		 * setup for corking
+		 */
+		err = ip6_setup_cork(sk, &inet->cork, &np->cork, hlimit,
+				     tclass, opt, rt, fl6);
+		if (err)
+			return err;
+
+		exthdrlen = (opt ? opt->opt_flen : 0);
+		length += exthdrlen;
+		transhdrlen += exthdrlen;
+	} else {
+		fl6 = &inet->cork.fl.u.ip6;
+		transhdrlen = 0;
+	}
+
+	return __ip6_append_data(sk, fl6, &sk->sk_write_queue, &inet->cork.base,
+				 &np->cork, sk_page_frag(sk), getfrag,
+				 from, length, transhdrlen, flags, dontfrag);
+}
 EXPORT_SYMBOL_GPL(ip6_append_data);
 
-static void ip6_cork_release(struct inet_sock *inet, struct ipv6_pinfo *np)
+static void ip6_cork_release(struct inet_cork_full *cork,
+			     struct inet6_cork *v6_cork)
 {
-	if (np->cork.opt) {
-		kfree(np->cork.opt->dst0opt);
-		kfree(np->cork.opt->dst1opt);
-		kfree(np->cork.opt->hopopt);
-		kfree(np->cork.opt->srcrt);
-		kfree(np->cork.opt);
-		np->cork.opt = NULL;
+	if (v6_cork->opt) {
+		kfree(v6_cork->opt->dst0opt);
+		kfree(v6_cork->opt->dst1opt);
+		kfree(v6_cork->opt->hopopt);
+		kfree(v6_cork->opt->srcrt);
+		kfree(v6_cork->opt);
+		v6_cork->opt = NULL;
 	}
 
-	if (inet->cork.base.dst) {
-		dst_release(inet->cork.base.dst);
-		inet->cork.base.dst = NULL;
-		inet->cork.base.flags &= ~IPCORK_ALLFRAG;
+	if (cork->base.dst) {
+		dst_release(cork->base.dst);
+		cork->base.dst = NULL;
+		cork->base.flags &= ~IPCORK_ALLFRAG;
 	}
-	memset(&inet->cork.fl, 0, sizeof(inet->cork.fl));
+	memset(&cork->fl, 0, sizeof(cork->fl));
 }
 
-int ip6_push_pending_frames(struct sock *sk)
+struct sk_buff *__ip6_make_skb(struct sock *sk,
+			       struct sk_buff_head *queue,
+			       struct inet_cork_full *cork,
+			       struct inet6_cork *v6_cork)
 {
 	struct sk_buff *skb, *tmp_skb;
 	struct sk_buff **tail_skb;
 	struct in6_addr final_dst_buf, *final_dst = &final_dst_buf;
-	struct inet_sock *inet = inet_sk(sk);
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct net *net = sock_net(sk);
 	struct ipv6hdr *hdr;
-	struct ipv6_txoptions *opt = np->cork.opt;
-	struct rt6_info *rt = (struct rt6_info *)inet->cork.base.dst;
-	struct flowi6 *fl6 = &inet->cork.fl.u.ip6;
+	struct ipv6_txoptions *opt = v6_cork->opt;
+	struct rt6_info *rt = (struct rt6_info *)cork->base.dst;
+	struct flowi6 *fl6 = &cork->fl.u.ip6;
 	unsigned char proto = fl6->flowi6_proto;
-	int err = 0;
 
-	if ((skb = __skb_dequeue(&sk->sk_write_queue)) == NULL)
+	skb = __skb_dequeue(queue);
+	if (!skb)
 		goto out;
 	tail_skb = &(skb_shinfo(skb)->frag_list);
 
 	/* move skb->data to ip header from ext header */
 	if (skb->data < skb_network_header(skb))
 		__skb_pull(skb, skb_network_offset(skb));
-	while ((tmp_skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) {
+	while ((tmp_skb = __skb_dequeue(queue)) != NULL) {
 		__skb_pull(tmp_skb, skb_network_header_len(skb));
 		*tail_skb = tmp_skb;
 		tail_skb = &(tmp_skb->next);
@@ -1568,10 +1639,10 @@ int ip6_push_pending_frames(struct sock *sk)
 	skb_reset_network_header(skb);
 	hdr = ipv6_hdr(skb);
 
-	ip6_flow_hdr(hdr, np->cork.tclass,
+	ip6_flow_hdr(hdr, v6_cork->tclass,
 		     ip6_make_flowlabel(net, skb, fl6->flowlabel,
 					np->autoflowlabel));
-	hdr->hop_limit = np->cork.hop_limit;
+	hdr->hop_limit = v6_cork->hop_limit;
 	hdr->nexthdr = proto;
 	hdr->saddr = fl6->saddr;
 	hdr->daddr = *final_dst;
@@ -1588,34 +1659,104 @@ int ip6_push_pending_frames(struct sock *sk)
 		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
 	}
 
+	ip6_cork_release(cork, v6_cork);
+out:
+	return skb;
+}
+
+int ip6_send_skb(struct sk_buff *skb)
+{
+	struct net *net = sock_net(skb->sk);
+	struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
+	int err;
+
 	err = ip6_local_out(skb);
 	if (err) {
 		if (err > 0)
 			err = net_xmit_errno(err);
 		if (err)
-			goto error;
+			IP6_INC_STATS(net, rt->rt6i_idev,
+				      IPSTATS_MIB_OUTDISCARDS);
 	}
 
-out:
-	ip6_cork_release(inet, np);
 	return err;
-error:
-	IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
-	goto out;
+}
+
+int ip6_push_pending_frames(struct sock *sk)
+{
+	struct sk_buff *skb;
+
+	skb = ip6_finish_skb(sk);
+	if (!skb)
+		return 0;
+
+	return ip6_send_skb(skb);
 }
 EXPORT_SYMBOL_GPL(ip6_push_pending_frames);
 
-void ip6_flush_pending_frames(struct sock *sk)
+static void __ip6_flush_pending_frames(struct sock *sk,
+				       struct sk_buff_head *queue,
+				       struct inet_cork_full *cork,
+				       struct inet6_cork *v6_cork)
 {
 	struct sk_buff *skb;
 
-	while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) {
+	while ((skb = __skb_dequeue_tail(queue)) != NULL) {
 		if (skb_dst(skb))
 			IP6_INC_STATS(sock_net(sk), ip6_dst_idev(skb_dst(skb)),
 				      IPSTATS_MIB_OUTDISCARDS);
 		kfree_skb(skb);
 	}
 
-	ip6_cork_release(inet_sk(sk), inet6_sk(sk));
+	ip6_cork_release(cork, v6_cork);
+}
+
+void ip6_flush_pending_frames(struct sock *sk)
+{
+	__ip6_flush_pending_frames(sk, &sk->sk_write_queue,
+				   &inet_sk(sk)->cork, &inet6_sk(sk)->cork);
 }
 EXPORT_SYMBOL_GPL(ip6_flush_pending_frames);
+
+struct sk_buff *ip6_make_skb(struct sock *sk,
+			     int getfrag(void *from, char *to, int offset,
+					 int len, int odd, struct sk_buff *skb),
+			     void *from, int length, int transhdrlen,
+			     int hlimit, int tclass,
+			     struct ipv6_txoptions *opt, struct flowi6 *fl6,
+			     struct rt6_info *rt, unsigned int flags,
+			     int dontfrag)
+{
+	struct inet_cork_full cork;
+	struct inet6_cork v6_cork;
+	struct sk_buff_head queue;
+	int exthdrlen = (opt ? opt->opt_flen : 0);
+	int err;
+
+	if (flags & MSG_PROBE)
+		return NULL;
+
+	__skb_queue_head_init(&queue);
+
+	cork.base.flags = 0;
+	cork.base.addr = 0;
+	cork.base.opt = NULL;
+	v6_cork.opt = NULL;
+	err = ip6_setup_cork(sk, &cork, &v6_cork, hlimit, tclass, opt, rt, fl6);
+	if (err)
+		return ERR_PTR(err);
+
+	if (dontfrag < 0)
+		dontfrag = inet6_sk(sk)->dontfrag;
+
+	err = __ip6_append_data(sk, fl6, &queue, &cork.base, &v6_cork,
+				&current->task_frag, getfrag, from,
+				length + exthdrlen, transhdrlen + exthdrlen,
+				flags, dontfrag);
+	if (err) {
+		__ip6_flush_pending_frames(sk, &queue, &cork, &v6_cork);
+		return ERR_PTR(err);
+	}
+
+	return __ip6_make_skb(sk, &queue, &cork, &v6_cork);
+}
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 9cb94cfa0ae7..5cafd92c2312 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -64,12 +64,6 @@ MODULE_LICENSE("GPL");
 MODULE_ALIAS_RTNL_LINK("ip6tnl");
 MODULE_ALIAS_NETDEV("ip6tnl0");
 
-#ifdef IP6_TNL_DEBUG
-#define IP6_TNL_TRACE(x...) pr_debug("%s:" x "\n", __func__)
-#else
-#define IP6_TNL_TRACE(x...) do {;} while(0)
-#endif
-
 #define HASH_SIZE_SHIFT  5
 #define HASH_SIZE (1 << HASH_SIZE_SHIFT)
 
@@ -137,7 +131,7 @@ struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t)
 	struct dst_entry *dst = t->dst_cache;
 
 	if (dst && dst->obsolete &&
-	    dst->ops->check(dst, t->dst_cookie) == NULL) {
+	    !dst->ops->check(dst, t->dst_cookie)) {
 		t->dst_cache = NULL;
 		dst_release(dst);
 		return NULL;
@@ -183,6 +177,7 @@ ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_
 	unsigned int hash = HASH(remote, local);
 	struct ip6_tnl *t;
 	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
+	struct in6_addr any;
 
 	for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
 		if (ipv6_addr_equal(local, &t->parms.laddr) &&
@@ -190,6 +185,22 @@ ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
+
+	memset(&any, 0, sizeof(any));
+	hash = HASH(&any, local);
+	for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
+		if (ipv6_addr_equal(local, &t->parms.laddr) &&
+		    (t->dev->flags & IFF_UP))
+			return t;
+	}
+
+	hash = HASH(remote, &any);
+	for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
+		if (ipv6_addr_equal(remote, &t->parms.raddr) &&
+		    (t->dev->flags & IFF_UP))
+			return t;
+	}
+
 	t = rcu_dereference(ip6n->tnls_wc[0]);
 	if (t && (t->dev->flags & IFF_UP))
 		return t;
@@ -297,7 +308,7 @@ out:
  *   Create tunnel matching given parameters.
  *
  * Return:
- *   created tunnel or NULL
+ *   created tunnel or error pointer
  **/
 
 static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p)
@@ -305,7 +316,7 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p)
 	struct net_device *dev;
 	struct ip6_tnl *t;
 	char name[IFNAMSIZ];
-	int err;
+	int err = -ENOMEM;
 
 	if (p->name[0])
 		strlcpy(name, p->name, IFNAMSIZ);
@@ -314,7 +325,7 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p)
 
 	dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN,
 			   ip6_tnl_dev_setup);
-	if (dev == NULL)
+	if (!dev)
 		goto failed;
 
 	dev_net_set(dev, net);
@@ -331,7 +342,7 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p)
 failed_free:
 	ip6_dev_free(dev);
 failed:
-	return NULL;
+	return ERR_PTR(err);
 }
 
 /**
@@ -345,7 +356,7 @@ failed:
  *   tunnel device is created and registered for use.
  *
  * Return:
- *   matching tunnel or NULL
+ *   matching tunnel or error pointer
  **/
 
 static struct ip6_tnl *ip6_tnl_locate(struct net *net,
@@ -363,13 +374,13 @@ static struct ip6_tnl *ip6_tnl_locate(struct net *net,
 		if (ipv6_addr_equal(local, &t->parms.laddr) &&
 		    ipv6_addr_equal(remote, &t->parms.raddr)) {
 			if (create)
-				return NULL;
+				return ERR_PTR(-EEXIST);
 
 			return t;
 		}
 	}
 	if (!create)
-		return NULL;
+		return ERR_PTR(-ENODEV);
 	return ip6_tnl_create(net, p);
 }
 
@@ -474,6 +485,7 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt,
 	int rel_msg = 0;
 	u8 rel_type = ICMPV6_DEST_UNREACH;
 	u8 rel_code = ICMPV6_ADDR_UNREACH;
+	u8 tproto;
 	__u32 rel_info = 0;
 	__u16 len;
 	int err = -ENOENT;
@@ -483,11 +495,12 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt,
 	   processing of the error. */
 
 	rcu_read_lock();
-	if ((t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->daddr,
-					&ipv6h->saddr)) == NULL)
+	t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->daddr, &ipv6h->saddr);
+	if (!t)
 		goto out;
 
-	if (t->parms.proto != ipproto && t->parms.proto != 0)
+	tproto = ACCESS_ONCE(t->parms.proto);
+	if (tproto != ipproto && tproto != 0)
 		goto out;
 
 	err = 0;
@@ -531,7 +544,8 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt,
 			mtu = IPV6_MIN_MTU;
 		t->dev->mtu = mtu;
 
-		if ((len = sizeof(*ipv6h) + ntohs(ipv6h->payload_len)) > mtu) {
+		len = sizeof(*ipv6h) + ntohs(ipv6h->payload_len);
+		if (len > mtu) {
 			rel_type = ICMPV6_PKT_TOOBIG;
 			rel_code = 0;
 			rel_info = mtu;
@@ -788,15 +802,16 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol,
 {
 	struct ip6_tnl *t;
 	const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+	u8 tproto;
 	int err;
 
 	rcu_read_lock();
-
-	if ((t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr,
-					&ipv6h->daddr)) != NULL) {
+	t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, &ipv6h->daddr);
+	if (t) {
 		struct pcpu_sw_netstats *tstats;
 
-		if (t->parms.proto != ipproto && t->parms.proto != 0) {
+		tproto = ACCESS_ONCE(t->parms.proto);
+		if (tproto != ipproto && tproto != 0) {
 			rcu_read_unlock();
 			goto discard;
 		}
@@ -902,24 +917,28 @@ ip6_tnl_addr_conflict(const struct ip6_tnl *t, const struct ipv6hdr *hdr)
 	return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr);
 }
 
-int ip6_tnl_xmit_ctl(struct ip6_tnl *t)
+int ip6_tnl_xmit_ctl(struct ip6_tnl *t,
+		     const struct in6_addr *laddr,
+		     const struct in6_addr *raddr)
 {
 	struct __ip6_tnl_parm *p = &t->parms;
 	int ret = 0;
 	struct net *net = t->net;
 
-	if (p->flags & IP6_TNL_F_CAP_XMIT) {
+	if ((p->flags & IP6_TNL_F_CAP_XMIT) ||
+	    ((p->flags & IP6_TNL_F_CAP_PER_PACKET) &&
+	     (ip6_tnl_get_cap(t, laddr, raddr) & IP6_TNL_F_CAP_XMIT))) {
 		struct net_device *ldev = NULL;
 
 		rcu_read_lock();
 		if (p->link)
 			ldev = dev_get_by_index_rcu(net, p->link);
 
-		if (unlikely(!ipv6_chk_addr(net, &p->laddr, ldev, 0)))
+		if (unlikely(!ipv6_chk_addr(net, laddr, ldev, 0)))
 			pr_warn("%s xmit: Local address not yet configured!\n",
 				p->name);
-		else if (!ipv6_addr_is_multicast(&p->raddr) &&
-			 unlikely(ipv6_chk_addr(net, &p->raddr, NULL, 0)))
+		else if (!ipv6_addr_is_multicast(raddr) &&
+			 unlikely(ipv6_chk_addr(net, raddr, NULL, 0)))
 			pr_warn("%s xmit: Routing loop! Remote address found on this node!\n",
 				p->name);
 		else
@@ -968,8 +987,34 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
 	u8 proto;
 	int err = -1;
 
-	if (!fl6->flowi6_mark)
+	/* NBMA tunnel */
+	if (ipv6_addr_any(&t->parms.raddr)) {
+		struct in6_addr *addr6;
+		struct neighbour *neigh;
+		int addr_type;
+
+		if (!skb_dst(skb))
+			goto tx_err_link_failure;
+
+		neigh = dst_neigh_lookup(skb_dst(skb),
+					 &ipv6_hdr(skb)->daddr);
+		if (!neigh)
+			goto tx_err_link_failure;
+
+		addr6 = (struct in6_addr *)&neigh->primary_key;
+		addr_type = ipv6_addr_type(addr6);
+
+		if (addr_type == IPV6_ADDR_ANY)
+			addr6 = &ipv6_hdr(skb)->daddr;
+
+		memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr));
+		neigh_release(neigh);
+	} else if (!fl6->flowi6_mark)
 		dst = ip6_tnl_dst_check(t);
+
+	if (!ip6_tnl_xmit_ctl(t, &fl6->saddr, &fl6->daddr))
+		goto tx_err_link_failure;
+
 	if (!dst) {
 		ndst = ip6_route_output(net, NULL, fl6);
 
@@ -1018,7 +1063,8 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
 	    (skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
 		struct sk_buff *new_skb;
 
-		if (!(new_skb = skb_realloc_headroom(skb, max_headroom)))
+		new_skb = skb_realloc_headroom(skb, max_headroom);
+		if (!new_skb)
 			goto tx_err_dst_release;
 
 		if (skb->sk)
@@ -1054,7 +1100,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
 	ipv6h->nexthdr = proto;
 	ipv6h->saddr = fl6->saddr;
 	ipv6h->daddr = fl6->daddr;
-	ip6tunnel_xmit(skb, dev);
+	ip6tunnel_xmit(NULL, skb, dev);
 	if (ndst)
 		ip6_tnl_dst_store(t, ndst);
 	return 0;
@@ -1075,10 +1121,11 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct flowi6 fl6;
 	__u8 dsfield;
 	__u32 mtu;
+	u8 tproto;
 	int err;
 
-	if ((t->parms.proto != IPPROTO_IPIP && t->parms.proto != 0) ||
-	    !ip6_tnl_xmit_ctl(t))
+	tproto = ACCESS_ONCE(t->parms.proto);
+	if (tproto != IPPROTO_IPIP && tproto != 0)
 		return -1;
 
 	if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
@@ -1117,10 +1164,12 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct flowi6 fl6;
 	__u8 dsfield;
 	__u32 mtu;
+	u8 tproto;
 	int err;
 
-	if ((t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) ||
-	    !ip6_tnl_xmit_ctl(t) || ip6_tnl_addr_conflict(t, ipv6h))
+	tproto = ACCESS_ONCE(t->parms.proto);
+	if ((tproto != IPPROTO_IPV6 && tproto != 0) ||
+	    ip6_tnl_addr_conflict(t, ipv6h))
 		return -1;
 
 	offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb));
@@ -1215,8 +1264,6 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
 	else
 		dev->flags &= ~IFF_POINTOPOINT;
 
-	dev->iflink = p->link;
-
 	if (p->flags & IP6_TNL_F_CAP_XMIT) {
 		int strict = (ipv6_addr_type(&p->raddr) &
 			      (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL));
@@ -1225,7 +1272,7 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
 						 &p->raddr, &p->laddr,
 						 p->link, strict);
 
-		if (rt == NULL)
+		if (!rt)
 			return;
 
 		if (rt->dst.dev) {
@@ -1282,6 +1329,14 @@ static int ip6_tnl_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p)
 	return err;
 }
 
+static int ip6_tnl0_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p)
+{
+	/* for default tnl0 device allow to change only the proto */
+	t->parms.proto = p->proto;
+	netdev_state_change(t->dev);
+	return 0;
+}
+
 static void
 ip6_tnl_parm_from_user(struct __ip6_tnl_parm *p, const struct ip6_tnl_parm *u)
 {
@@ -1357,7 +1412,7 @@ 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)
+			if (IS_ERR(t))
 				t = netdev_priv(dev);
 		} else {
 			memset(&p, 0, sizeof(p));
@@ -1381,25 +1436,28 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 			break;
 		ip6_tnl_parm_from_user(&p1, &p);
 		t = ip6_tnl_locate(net, &p1, cmd == SIOCADDTUNNEL);
-		if (dev != ip6n->fb_tnl_dev && cmd == SIOCCHGTUNNEL) {
-			if (t != NULL) {
+		if (cmd == SIOCCHGTUNNEL) {
+			if (!IS_ERR(t)) {
 				if (t->dev != dev) {
 					err = -EEXIST;
 					break;
 				}
 			} else
 				t = netdev_priv(dev);
-
-			err = ip6_tnl_update(t, &p1);
+			if (dev == ip6n->fb_tnl_dev)
+				err = ip6_tnl0_update(t, &p1);
+			else
+				err = ip6_tnl_update(t, &p1);
 		}
-		if (t) {
+		if (!IS_ERR(t)) {
 			err = 0;
 			ip6_tnl_parm_to_user(&p, &t->parms);
 			if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
 				err = -EFAULT;
 
-		} else
-			err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT);
+		} else {
+			err = PTR_ERR(t);
+		}
 		break;
 	case SIOCDELTUNNEL:
 		err = -EPERM;
@@ -1413,7 +1471,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 			err = -ENOENT;
 			ip6_tnl_parm_from_user(&p1, &p);
 			t = ip6_tnl_locate(net, &p1, 0);
-			if (t == NULL)
+			if (IS_ERR(t))
 				break;
 			err = -EPERM;
 			if (t->dev == ip6n->fb_tnl_dev)
@@ -1457,6 +1515,13 @@ ip6_tnl_change_mtu(struct net_device *dev, int new_mtu)
 	return 0;
 }
 
+int ip6_tnl_get_iflink(const struct net_device *dev)
+{
+	struct ip6_tnl *t = netdev_priv(dev);
+
+	return t->parms.link;
+}
+EXPORT_SYMBOL(ip6_tnl_get_iflink);
 
 static const struct net_device_ops ip6_tnl_netdev_ops = {
 	.ndo_init	= ip6_tnl_dev_init,
@@ -1465,6 +1530,7 @@ static const struct net_device_ops ip6_tnl_netdev_ops = {
 	.ndo_do_ioctl	= ip6_tnl_ioctl,
 	.ndo_change_mtu = ip6_tnl_change_mtu,
 	.ndo_get_stats	= ip6_get_stats,
+	.ndo_get_iflink = ip6_tnl_get_iflink,
 };
 
 
@@ -1580,12 +1646,10 @@ static void ip6_tnl_netlink_parms(struct nlattr *data[],
 		parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]);
 
 	if (data[IFLA_IPTUN_LOCAL])
-		nla_memcpy(&parms->laddr, data[IFLA_IPTUN_LOCAL],
-			   sizeof(struct in6_addr));
+		parms->laddr = nla_get_in6_addr(data[IFLA_IPTUN_LOCAL]);
 
 	if (data[IFLA_IPTUN_REMOTE])
-		nla_memcpy(&parms->raddr, data[IFLA_IPTUN_REMOTE],
-			   sizeof(struct in6_addr));
+		parms->raddr = nla_get_in6_addr(data[IFLA_IPTUN_REMOTE]);
 
 	if (data[IFLA_IPTUN_TTL])
 		parms->hop_limit = nla_get_u8(data[IFLA_IPTUN_TTL]);
@@ -1607,12 +1671,13 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev,
 			   struct nlattr *tb[], struct nlattr *data[])
 {
 	struct net *net = dev_net(dev);
-	struct ip6_tnl *nt;
+	struct ip6_tnl *nt, *t;
 
 	nt = netdev_priv(dev);
 	ip6_tnl_netlink_parms(data, &nt->parms);
 
-	if (ip6_tnl_locate(net, &nt->parms, 0))
+	t = ip6_tnl_locate(net, &nt->parms, 0);
+	if (!IS_ERR(t))
 		return -EEXIST;
 
 	return ip6_tnl_create2(dev);
@@ -1632,8 +1697,7 @@ static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[],
 	ip6_tnl_netlink_parms(data, &p);
 
 	t = ip6_tnl_locate(net, &p, 0);
-
-	if (t) {
+	if (!IS_ERR(t)) {
 		if (t->dev != dev)
 			return -EEXIST;
 	} else
@@ -1679,10 +1743,8 @@ static int ip6_tnl_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	struct __ip6_tnl_parm *parm = &tunnel->parms;
 
 	if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) ||
-	    nla_put(skb, IFLA_IPTUN_LOCAL, sizeof(struct in6_addr),
-		    &parm->laddr) ||
-	    nla_put(skb, IFLA_IPTUN_REMOTE, sizeof(struct in6_addr),
-		    &parm->raddr) ||
+	    nla_put_in6_addr(skb, IFLA_IPTUN_LOCAL, &parm->laddr) ||
+	    nla_put_in6_addr(skb, IFLA_IPTUN_REMOTE, &parm->raddr) ||
 	    nla_put_u8(skb, IFLA_IPTUN_TTL, parm->hop_limit) ||
 	    nla_put_u8(skb, IFLA_IPTUN_ENCAP_LIMIT, parm->encap_limit) ||
 	    nla_put_be32(skb, IFLA_IPTUN_FLOWINFO, parm->flowinfo) ||
@@ -1695,6 +1757,14 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
+struct net *ip6_tnl_get_link_net(const struct net_device *dev)
+{
+	struct ip6_tnl *tunnel = netdev_priv(dev);
+
+	return tunnel->net;
+}
+EXPORT_SYMBOL(ip6_tnl_get_link_net);
+
 static const struct nla_policy ip6_tnl_policy[IFLA_IPTUN_MAX + 1] = {
 	[IFLA_IPTUN_LINK]		= { .type = NLA_U32 },
 	[IFLA_IPTUN_LOCAL]		= { .len = sizeof(struct in6_addr) },
@@ -1718,6 +1788,7 @@ static struct rtnl_link_ops ip6_link_ops __read_mostly = {
 	.dellink	= ip6_tnl_dellink,
 	.get_size	= ip6_tnl_get_size,
 	.fill_info	= ip6_tnl_fill_info,
+	.get_link_net	= ip6_tnl_get_link_net,
 };
 
 static struct xfrm6_tunnel ip4ip6_handler __read_mostly = {
@@ -1746,7 +1817,7 @@ static void __net_exit ip6_tnl_destroy_tunnels(struct net *net)
 
 	for (h = 0; h < HASH_SIZE; h++) {
 		t = rtnl_dereference(ip6n->tnls_r_l[h]);
-		while (t != NULL) {
+		while (t) {
 			/* If dev is in the same netns, it has already
 			 * been added to the list by the previous loop.
 			 */
diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c
index b04ed72c4542..bba8903e871f 100644
--- a/net/ipv6/ip6_udp_tunnel.c
+++ b/net/ipv6/ip6_udp_tunnel.c
@@ -62,14 +62,15 @@ error:
 }
 EXPORT_SYMBOL_GPL(udp_sock_create6);
 
-int udp_tunnel6_xmit_skb(struct socket *sock, struct dst_entry *dst,
-			 struct sk_buff *skb, struct net_device *dev,
-			 struct in6_addr *saddr, struct in6_addr *daddr,
-			 __u8 prio, __u8 ttl, __be16 src_port, __be16 dst_port)
+int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk,
+			 struct sk_buff *skb,
+			 struct net_device *dev, struct in6_addr *saddr,
+			 struct in6_addr *daddr,
+			 __u8 prio, __u8 ttl, __be16 src_port,
+			 __be16 dst_port, bool nocheck)
 {
 	struct udphdr *uh;
 	struct ipv6hdr *ip6h;
-	struct sock *sk = sock->sk;
 
 	__skb_push(skb, sizeof(*uh));
 	skb_reset_transport_header(skb);
@@ -79,15 +80,13 @@ int udp_tunnel6_xmit_skb(struct socket *sock, struct dst_entry *dst,
 	uh->source = src_port;
 
 	uh->len = htons(skb->len);
-	uh->check = 0;
 
 	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
 	IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED
 			    | IPSKB_REROUTED);
 	skb_dst_set(skb, dst);
 
-	udp6_set_csum(udp_get_no_check6_tx(sk), skb, &inet6_sk(sk)->saddr,
-		      &sk->sk_v6_daddr, skb->len);
+	udp6_set_csum(nocheck, skb, saddr, daddr, skb->len);
 
 	__skb_push(skb, sizeof(*ip6h));
 	skb_reset_network_header(skb);
@@ -99,7 +98,7 @@ int udp_tunnel6_xmit_skb(struct socket *sock, struct dst_entry *dst,
 	ip6h->daddr	  = *daddr;
 	ip6h->saddr	  = *saddr;
 
-	ip6tunnel_xmit(skb, dev);
+	ip6tunnel_xmit(sk, skb, dev);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(udp_tunnel6_xmit_skb);
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 31089d153fd3..0224c032dca5 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -95,6 +95,7 @@ vti6_tnl_lookup(struct net *net, const struct in6_addr *remote,
 	unsigned int hash = HASH(remote, local);
 	struct ip6_tnl *t;
 	struct vti6_net *ip6n = net_generic(net, vti6_net_id);
+	struct in6_addr any;
 
 	for_each_vti6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
 		if (ipv6_addr_equal(local, &t->parms.laddr) &&
@@ -102,6 +103,22 @@ vti6_tnl_lookup(struct net *net, const struct in6_addr *remote,
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
+
+	memset(&any, 0, sizeof(any));
+	hash = HASH(&any, local);
+	for_each_vti6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
+		if (ipv6_addr_equal(local, &t->parms.laddr) &&
+		    (t->dev->flags & IFF_UP))
+			return t;
+	}
+
+	hash = HASH(remote, &any);
+	for_each_vti6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
+		if (ipv6_addr_equal(remote, &t->parms.raddr) &&
+		    (t->dev->flags & IFF_UP))
+			return t;
+	}
+
 	t = rcu_dereference(ip6n->tnls_wc[0]);
 	if (t && (t->dev->flags & IFF_UP))
 		return t;
@@ -201,7 +218,7 @@ static struct ip6_tnl *vti6_tnl_create(struct net *net, struct __ip6_tnl_parm *p
 		sprintf(name, "ip6_vti%%d");
 
 	dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, vti6_dev_setup);
-	if (dev == NULL)
+	if (!dev)
 		goto failed;
 
 	dev_net_set(dev, net);
@@ -271,8 +288,7 @@ static struct ip6_tnl *vti6_locate(struct net *net, struct __ip6_tnl_parm *p,
 static void vti6_dev_uninit(struct net_device *dev)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
-	struct net *net = dev_net(dev);
-	struct vti6_net *ip6n = net_generic(net, vti6_net_id);
+	struct vti6_net *ip6n = net_generic(t->net, vti6_net_id);
 
 	if (dev == ip6n->fb_tnl_dev)
 		RCU_INIT_POINTER(ip6n->tnls_wc[0], NULL);
@@ -287,8 +303,8 @@ 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) {
+	t = vti6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, &ipv6h->daddr);
+	if (t) {
 		if (t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) {
 			rcu_read_unlock();
 			goto discard;
@@ -306,7 +322,6 @@ static int vti6_rcv(struct sk_buff *skb)
 		}
 
 		XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = t;
-		skb->mark = be32_to_cpu(t->parms.i_key);
 
 		rcu_read_unlock();
 
@@ -326,6 +341,8 @@ static int vti6_rcv_cb(struct sk_buff *skb, int err)
 	struct pcpu_sw_netstats *tstats;
 	struct xfrm_state *x;
 	struct ip6_tnl *t = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6;
+	u32 orig_mark = skb->mark;
+	int ret;
 
 	if (!t)
 		return 1;
@@ -342,7 +359,11 @@ static int vti6_rcv_cb(struct sk_buff *skb, int err)
 	x = xfrm_input_state(skb);
 	family = x->inner_mode->afinfo->family;
 
-	if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family))
+	skb->mark = be32_to_cpu(t->parms.i_key);
+	ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family);
+	skb->mark = orig_mark;
+
+	if (!ret)
 		return -EPERM;
 
 	skb_scrub_packet(skb, !net_eq(t->net, dev_net(skb->dev)));
@@ -412,7 +433,9 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 	struct net_device_stats *stats = &t->dev->stats;
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *tdev;
+	struct xfrm_state *x;
 	int err = -1;
+	int mtu;
 
 	if (!dst)
 		goto tx_err_link_failure;
@@ -425,7 +448,12 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 		goto tx_err_link_failure;
 	}
 
-	if (!vti6_state_check(dst->xfrm, &t->parms.raddr, &t->parms.laddr))
+	x = dst->xfrm;
+	if (!vti6_state_check(x, &t->parms.raddr, &t->parms.laddr))
+		goto tx_err_link_failure;
+
+	if (!ip6_tnl_xmit_ctl(t, (const struct in6_addr *)&x->props.saddr,
+			      (const struct in6_addr *)&x->id.daddr))
 		goto tx_err_link_failure;
 
 	tdev = dst->dev;
@@ -441,6 +469,19 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 	skb_dst_set(skb, dst);
 	skb->dev = skb_dst(skb)->dev;
 
+	mtu = dst_mtu(dst);
+	if (!skb->ignore_df && skb->len > mtu) {
+		skb_dst(skb)->ops->update_pmtu(dst, NULL, skb, mtu);
+
+		if (skb->protocol == htons(ETH_P_IPV6))
+			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+		else
+			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
+				  htonl(mtu));
+
+		return -EMSGSIZE;
+	}
+
 	err = dst_output(skb);
 	if (net_xmit_eval(err) == 0) {
 		struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
@@ -473,14 +514,13 @@ vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	int ret;
 
 	memset(&fl, 0, sizeof(fl));
-	skb->mark = be32_to_cpu(t->parms.o_key);
 
 	switch (skb->protocol) {
 	case htons(ETH_P_IPV6):
 		ipv6h = ipv6_hdr(skb);
 
 		if ((t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) ||
-		    !ip6_tnl_xmit_ctl(t) || vti6_addr_conflict(t, ipv6h))
+		    vti6_addr_conflict(t, ipv6h))
 			goto tx_err;
 
 		xfrm_decode_session(skb, &fl, AF_INET6);
@@ -494,6 +534,9 @@ vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto tx_err;
 	}
 
+	/* override mark with tunnel output key */
+	fl.flowi_mark = be32_to_cpu(t->parms.o_key);
+
 	ret = vti6_xmit(skb, dev, &fl);
 	if (ret < 0)
 		goto tx_err;
@@ -578,8 +621,6 @@ static void vti6_link_config(struct ip6_tnl *t)
 		dev->flags |= IFF_POINTOPOINT;
 	else
 		dev->flags &= ~IFF_POINTOPOINT;
-
-	dev->iflink = p->link;
 }
 
 /**
@@ -693,7 +734,7 @@ vti6_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		} else {
 			memset(&p, 0, sizeof(p));
 		}
-		if (t == NULL)
+		if (!t)
 			t = netdev_priv(dev);
 		vti6_parm_to_user(&p, &t->parms);
 		if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
@@ -713,7 +754,7 @@ vti6_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		vti6_parm_from_user(&p1, &p);
 		t = vti6_locate(net, &p1, cmd == SIOCADDTUNNEL);
 		if (dev != ip6n->fb_tnl_dev && cmd == SIOCCHGTUNNEL) {
-			if (t != NULL) {
+			if (t) {
 				if (t->dev != dev) {
 					err = -EEXIST;
 					break;
@@ -744,7 +785,7 @@ vti6_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 			err = -ENOENT;
 			vti6_parm_from_user(&p1, &p);
 			t = vti6_locate(net, &p1, 0);
-			if (t == NULL)
+			if (!t)
 				break;
 			err = -EPERM;
 			if (t->dev == ip6n->fb_tnl_dev)
@@ -785,6 +826,7 @@ static const struct net_device_ops vti6_netdev_ops = {
 	.ndo_do_ioctl	= vti6_ioctl,
 	.ndo_change_mtu = vti6_change_mtu,
 	.ndo_get_stats64 = ip_tunnel_get_stats64,
+	.ndo_get_iflink = ip6_tnl_get_iflink,
 };
 
 /**
@@ -874,12 +916,10 @@ static void vti6_netlink_parms(struct nlattr *data[],
 		parms->link = nla_get_u32(data[IFLA_VTI_LINK]);
 
 	if (data[IFLA_VTI_LOCAL])
-		nla_memcpy(&parms->laddr, data[IFLA_VTI_LOCAL],
-			   sizeof(struct in6_addr));
+		parms->laddr = nla_get_in6_addr(data[IFLA_VTI_LOCAL]);
 
 	if (data[IFLA_VTI_REMOTE])
-		nla_memcpy(&parms->raddr, data[IFLA_VTI_REMOTE],
-			   sizeof(struct in6_addr));
+		parms->raddr = nla_get_in6_addr(data[IFLA_VTI_REMOTE]);
 
 	if (data[IFLA_VTI_IKEY])
 		parms->i_key = nla_get_be32(data[IFLA_VTI_IKEY]);
@@ -905,6 +945,15 @@ static int vti6_newlink(struct net *src_net, struct net_device *dev,
 	return vti6_tnl_create2(dev);
 }
 
+static void vti6_dellink(struct net_device *dev, struct list_head *head)
+{
+	struct net *net = dev_net(dev);
+	struct vti6_net *ip6n = net_generic(net, vti6_net_id);
+
+	if (dev != ip6n->fb_tnl_dev)
+		unregister_netdevice_queue(dev, head);
+}
+
 static int vti6_changelink(struct net_device *dev, struct nlattr *tb[],
 			   struct nlattr *data[])
 {
@@ -951,10 +1000,8 @@ static int vti6_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	struct __ip6_tnl_parm *parm = &tunnel->parms;
 
 	if (nla_put_u32(skb, IFLA_VTI_LINK, parm->link) ||
-	    nla_put(skb, IFLA_VTI_LOCAL, sizeof(struct in6_addr),
-		    &parm->laddr) ||
-	    nla_put(skb, IFLA_VTI_REMOTE, sizeof(struct in6_addr),
-		    &parm->raddr) ||
+	    nla_put_in6_addr(skb, IFLA_VTI_LOCAL, &parm->laddr) ||
+	    nla_put_in6_addr(skb, IFLA_VTI_REMOTE, &parm->raddr) ||
 	    nla_put_be32(skb, IFLA_VTI_IKEY, parm->i_key) ||
 	    nla_put_be32(skb, IFLA_VTI_OKEY, parm->o_key))
 		goto nla_put_failure;
@@ -980,9 +1027,11 @@ static struct rtnl_link_ops vti6_link_ops __read_mostly = {
 	.setup		= vti6_dev_setup,
 	.validate	= vti6_validate,
 	.newlink	= vti6_newlink,
+	.dellink	= vti6_dellink,
 	.changelink	= vti6_changelink,
 	.get_size	= vti6_get_size,
 	.fill_info	= vti6_fill_info,
+	.get_link_net	= ip6_tnl_get_link_net,
 };
 
 static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n)
@@ -993,7 +1042,7 @@ static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n)
 
 	for (h = 0; h < HASH_SIZE; h++) {
 		t = rtnl_dereference(ip6n->tnls_r_l[h]);
-		while (t != NULL) {
+		while (t) {
 			unregister_netdevice_queue(t->dev, &list);
 			t = rtnl_dereference(t->next);
 		}
@@ -1020,6 +1069,7 @@ static int __net_init vti6_init_net(struct net *net)
 	if (!ip6n->fb_tnl_dev)
 		goto err_alloc_dev;
 	dev_net_set(ip6n->fb_tnl_dev, net);
+	ip6n->fb_tnl_dev->rtnl_link_ops = &vti6_link_ops;
 
 	err = vti6_fb_tnl_dev_init(ip6n->fb_tnl_dev);
 	if (err < 0)
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 0171f08325c3..74ceb73c1c9a 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -56,9 +56,7 @@
 
 struct mr6_table {
 	struct list_head	list;
-#ifdef CONFIG_NET_NS
-	struct net		*net;
-#endif
+	possible_net_t		net;
 	u32			id;
 	struct sock		*mroute6_sk;
 	struct timer_list	ipmr_expire_timer;
@@ -175,7 +173,7 @@ static int ip6mr_rule_action(struct fib_rule *rule, struct flowi *flp,
 	}
 
 	mrt = ip6mr_get_table(rule->fr_net, rule->table);
-	if (mrt == NULL)
+	if (!mrt)
 		return -EAGAIN;
 	res->mrt = mrt;
 	return 0;
@@ -239,7 +237,7 @@ static int __net_init ip6mr_rules_init(struct net *net)
 	INIT_LIST_HEAD(&net->ipv6.mr6_tables);
 
 	mrt = ip6mr_new_table(net, RT6_TABLE_DFLT);
-	if (mrt == NULL) {
+	if (!mrt) {
 		err = -ENOMEM;
 		goto err1;
 	}
@@ -252,7 +250,7 @@ static int __net_init ip6mr_rules_init(struct net *net)
 	return 0;
 
 err2:
-	kfree(mrt);
+	ip6mr_free_table(mrt);
 err1:
 	fib_rules_unregister(ops);
 	return err;
@@ -267,8 +265,8 @@ static void __net_exit ip6mr_rules_exit(struct net *net)
 		list_del(&mrt->list);
 		ip6mr_free_table(mrt);
 	}
-	rtnl_unlock();
 	fib_rules_unregister(net->ipv6.mr6_rules_ops);
+	rtnl_unlock();
 }
 #else
 #define ip6mr_for_each_table(mrt, net) \
@@ -307,11 +305,11 @@ static struct mr6_table *ip6mr_new_table(struct net *net, u32 id)
 	unsigned int i;
 
 	mrt = ip6mr_get_table(net, id);
-	if (mrt != NULL)
+	if (mrt)
 		return mrt;
 
 	mrt = kzalloc(sizeof(*mrt), GFP_KERNEL);
-	if (mrt == NULL)
+	if (!mrt)
 		return NULL;
 	mrt->id = id;
 	write_pnet(&mrt->net, net);
@@ -336,7 +334,7 @@ static struct mr6_table *ip6mr_new_table(struct net *net, u32 id)
 
 static void ip6mr_free_table(struct mr6_table *mrt)
 {
-	del_timer(&mrt->ipmr_expire_timer);
+	del_timer_sync(&mrt->ipmr_expire_timer);
 	mroute_clean_tables(mrt);
 	kfree(mrt);
 }
@@ -410,7 +408,7 @@ static void *ip6mr_vif_seq_start(struct seq_file *seq, loff_t *pos)
 	struct mr6_table *mrt;
 
 	mrt = ip6mr_get_table(net, RT6_TABLE_DFLT);
-	if (mrt == NULL)
+	if (!mrt)
 		return ERR_PTR(-ENOENT);
 
 	iter->mrt = mrt;
@@ -494,7 +492,7 @@ static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos)
 	struct mr6_table *mrt;
 
 	mrt = ip6mr_get_table(net, RT6_TABLE_DFLT);
-	if (mrt == NULL)
+	if (!mrt)
 		return ERR_PTR(-ENOENT);
 
 	it->mrt = mrt;
@@ -667,7 +665,7 @@ static int pim6_rcv(struct sk_buff *skb)
 		dev_hold(reg_dev);
 	read_unlock(&mrt_lock);
 
-	if (reg_dev == NULL)
+	if (!reg_dev)
 		goto drop;
 
 	skb->mac_header = skb->network_header;
@@ -720,8 +718,14 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb,
 	return NETDEV_TX_OK;
 }
 
+static int reg_vif_get_iflink(const struct net_device *dev)
+{
+	return 0;
+}
+
 static const struct net_device_ops reg_vif_netdev_ops = {
 	.ndo_start_xmit	= reg_vif_xmit,
+	.ndo_get_iflink = reg_vif_get_iflink,
 };
 
 static void reg_vif_setup(struct net_device *dev)
@@ -745,7 +749,7 @@ static struct net_device *ip6mr_reg_vif(struct net *net, struct mr6_table *mrt)
 		sprintf(name, "pim6reg%u", mrt->id);
 
 	dev = alloc_netdev(0, name, NET_NAME_UNKNOWN, reg_vif_setup);
-	if (dev == NULL)
+	if (!dev)
 		return NULL;
 
 	dev_net_set(dev, net);
@@ -754,7 +758,6 @@ static struct net_device *ip6mr_reg_vif(struct net *net, struct mr6_table *mrt)
 		free_netdev(dev);
 		return NULL;
 	}
-	dev->iflink = 0;
 
 	if (dev_open(dev))
 		goto failure;
@@ -994,7 +997,7 @@ static int mif6_add(struct net *net, struct mr6_table *mrt,
 	v->pkt_out = 0;
 	v->link = dev->ifindex;
 	if (v->flags & MIFF_REGISTER)
-		v->link = dev->iflink;
+		v->link = dev_get_iflink(dev);
 
 	/* And finish update writing critical data */
 	write_lock_bh(&mrt_lock);
@@ -1074,7 +1077,7 @@ skip:
 static struct mfc6_cache *ip6mr_cache_alloc(void)
 {
 	struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL);
-	if (c == NULL)
+	if (!c)
 		return NULL;
 	c->mfc_un.res.minvif = MAXMIFS;
 	return c;
@@ -1083,7 +1086,7 @@ static struct mfc6_cache *ip6mr_cache_alloc(void)
 static struct mfc6_cache *ip6mr_cache_alloc_unres(void)
 {
 	struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC);
-	if (c == NULL)
+	if (!c)
 		return NULL;
 	skb_queue_head_init(&c->mfc_un.unres.unresolved);
 	c->mfc_un.unres.expires = jiffies + 10 * HZ;
@@ -1200,7 +1203,7 @@ static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt,
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
 	}
 
-	if (mrt->mroute6_sk == NULL) {
+	if (!mrt->mroute6_sk) {
 		kfree_skb(skb);
 		return -EINVAL;
 	}
@@ -1439,6 +1442,10 @@ reg_pernet_fail:
 
 void ip6_mr_cleanup(void)
 {
+	rtnl_unregister(RTNL_FAMILY_IP6MR, RTM_GETROUTE);
+#ifdef CONFIG_IPV6_PIMSM_V2
+	inet6_del_protocol(&pim6_protocol, IPPROTO_PIM);
+#endif
 	unregister_netdevice_notifier(&ip6_mr_notifier);
 	unregister_pernet_subsys(&ip6mr_net_ops);
 	kmem_cache_destroy(mrt_cachep);
@@ -1491,7 +1498,7 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt,
 		return -EINVAL;
 
 	c = ip6mr_cache_alloc();
-	if (c == NULL)
+	if (!c)
 		return -ENOMEM;
 
 	c->mf6c_origin = mfc->mf6cc_origin.sin6_addr;
@@ -1661,7 +1668,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
 	struct mr6_table *mrt;
 
 	mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT);
-	if (mrt == NULL)
+	if (!mrt)
 		return -ENOENT;
 
 	if (optname != MRT6_INIT) {
@@ -1810,7 +1817,7 @@ int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval,
 	struct mr6_table *mrt;
 
 	mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT);
-	if (mrt == NULL)
+	if (!mrt)
 		return -ENOENT;
 
 	switch (optname) {
@@ -1857,7 +1864,7 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg)
 	struct mr6_table *mrt;
 
 	mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT);
-	if (mrt == NULL)
+	if (!mrt)
 		return -ENOENT;
 
 	switch (cmd) {
@@ -1931,7 +1938,7 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg)
 	struct mr6_table *mrt;
 
 	mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT);
-	if (mrt == NULL)
+	if (!mrt)
 		return -ENOENT;
 
 	switch (cmd) {
@@ -1979,13 +1986,13 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg)
 }
 #endif
 
-static inline int ip6mr_forward2_finish(struct sk_buff *skb)
+static inline int ip6mr_forward2_finish(struct sock *sk, struct sk_buff *skb)
 {
 	IP6_INC_STATS_BH(dev_net(skb_dst(skb)->dev), ip6_dst_idev(skb_dst(skb)),
 			 IPSTATS_MIB_OUTFORWDATAGRAMS);
 	IP6_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), ip6_dst_idev(skb_dst(skb)),
 			 IPSTATS_MIB_OUTOCTETS, skb->len);
-	return dst_output(skb);
+	return dst_output_sk(sk, skb);
 }
 
 /*
@@ -2001,7 +2008,7 @@ static int ip6mr_forward2(struct net *net, struct mr6_table *mrt,
 	struct dst_entry *dst;
 	struct flowi6 fl6;
 
-	if (vif->dev == NULL)
+	if (!vif->dev)
 		goto out_free;
 
 #ifdef CONFIG_IPV6_PIMSM_V2
@@ -2057,7 +2064,8 @@ static int ip6mr_forward2(struct net *net, struct mr6_table *mrt,
 
 	IP6CB(skb)->flags |= IP6SKB_FORWARDED;
 
-	return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, skb, skb->dev, dev,
+	return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, NULL, skb,
+		       skb->dev, dev,
 		       ip6mr_forward2_finish);
 
 out_free:
@@ -2090,7 +2098,7 @@ static void ip6_mr_forward(struct net *net, struct mr6_table *mrt,
 	if (ipv6_addr_any(&cache->mf6c_origin) && true_vifi >= 0) {
 		struct mfc6_cache *cache_proxy;
 
-		/* For an (*,G) entry, we only check that the incomming
+		/* For an (*,G) entry, we only check that the incoming
 		 * interface is part of the static tree.
 		 */
 		cache_proxy = ip6mr_cache_find_any_parent(mrt, vif);
@@ -2190,7 +2198,7 @@ int ip6_mr_input(struct sk_buff *skb)
 	read_lock(&mrt_lock);
 	cache = ip6mr_cache_find(mrt,
 				 &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr);
-	if (cache == NULL) {
+	if (!cache) {
 		int vif = ip6mr_find_vif(mrt, skb->dev);
 
 		if (vif >= 0)
@@ -2202,7 +2210,7 @@ int ip6_mr_input(struct sk_buff *skb)
 	/*
 	 *	No usable cache entry
 	 */
-	if (cache == NULL) {
+	if (!cache) {
 		int vif;
 
 		vif = ip6mr_find_vif(mrt, skb->dev);
@@ -2241,13 +2249,13 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
 	    nla_put_u32(skb, RTA_IIF, mrt->vif6_table[c->mf6c_parent].dev->ifindex) < 0)
 		return -EMSGSIZE;
 	mp_attr = nla_nest_start(skb, RTA_MULTIPATH);
-	if (mp_attr == NULL)
+	if (!mp_attr)
 		return -EMSGSIZE;
 
 	for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) {
 		if (MIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) {
 			nhp = nla_reserve_nohdr(skb, sizeof(*nhp));
-			if (nhp == NULL) {
+			if (!nhp) {
 				nla_nest_cancel(skb, mp_attr);
 				return -EMSGSIZE;
 			}
@@ -2280,7 +2288,7 @@ int ip6mr_get_route(struct net *net,
 	struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
 
 	mrt = ip6mr_get_table(net, RT6_TABLE_DFLT);
-	if (mrt == NULL)
+	if (!mrt)
 		return -ENOENT;
 
 	read_lock(&mrt_lock);
@@ -2305,7 +2313,7 @@ int ip6mr_get_route(struct net *net,
 		}
 
 		dev = skb->dev;
-		if (dev == NULL || (vif = ip6mr_find_vif(mrt, dev)) < 0) {
+		if (!dev || (vif = ip6mr_find_vif(mrt, dev)) < 0) {
 			read_unlock(&mrt_lock);
 			return -ENODEV;
 		}
@@ -2357,7 +2365,7 @@ static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
 	int err;
 
 	nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags);
-	if (nlh == NULL)
+	if (!nlh)
 		return -EMSGSIZE;
 
 	rtm = nlmsg_data(nlh);
@@ -2376,15 +2384,16 @@ static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
 		rtm->rtm_protocol = RTPROT_MROUTED;
 	rtm->rtm_flags    = 0;
 
-	if (nla_put(skb, RTA_SRC, 16, &c->mf6c_origin) ||
-	    nla_put(skb, RTA_DST, 16, &c->mf6c_mcastgrp))
+	if (nla_put_in6_addr(skb, RTA_SRC, &c->mf6c_origin) ||
+	    nla_put_in6_addr(skb, RTA_DST, &c->mf6c_mcastgrp))
 		goto nla_put_failure;
 	err = __ip6mr_fill_mroute(mrt, skb, c, rtm);
 	/* do not break the dump if cache is unresolved */
 	if (err < 0 && err != -ENOENT)
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
@@ -2421,7 +2430,7 @@ static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc,
 
 	skb = nlmsg_new(mr6_msgsize(mfc->mf6c_parent >= MAXMIFS, mrt->maxvif),
 			GFP_ATOMIC);
-	if (skb == NULL)
+	if (!skb)
 		goto errout;
 
 	err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0);
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index e1a9583bb419..63e6956917c9 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -85,7 +85,7 @@ int ip6_ra_control(struct sock *sk, int sel)
 			return 0;
 		}
 	}
-	if (new_ra == NULL) {
+	if (!new_ra) {
 		write_unlock_bh(&ip6_ra_lock);
 		return -ENOBUFS;
 	}
@@ -110,17 +110,32 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk,
 			icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen;
 			icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie);
 		}
-		opt = xchg(&inet6_sk(sk)->opt, opt);
-	} else {
-		spin_lock(&sk->sk_dst_lock);
-		opt = xchg(&inet6_sk(sk)->opt, opt);
-		spin_unlock(&sk->sk_dst_lock);
 	}
+	opt = xchg(&inet6_sk(sk)->opt, opt);
 	sk_dst_reset(sk);
 
 	return opt;
 }
 
+static bool setsockopt_needs_rtnl(int optname)
+{
+	switch (optname) {
+	case IPV6_ADD_MEMBERSHIP:
+	case IPV6_DROP_MEMBERSHIP:
+	case IPV6_JOIN_ANYCAST:
+	case IPV6_LEAVE_ANYCAST:
+	case MCAST_JOIN_GROUP:
+	case MCAST_LEAVE_GROUP:
+	case MCAST_JOIN_SOURCE_GROUP:
+	case MCAST_LEAVE_SOURCE_GROUP:
+	case MCAST_BLOCK_SOURCE:
+	case MCAST_UNBLOCK_SOURCE:
+	case MCAST_MSFILTER:
+		return true;
+	}
+	return false;
+}
+
 static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		    char __user *optval, unsigned int optlen)
 {
@@ -128,8 +143,9 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 	struct net *net = sock_net(sk);
 	int val, valbool;
 	int retv = -ENOPROTOOPT;
+	bool needs_rtnl = setsockopt_needs_rtnl(optname);
 
-	if (optval == NULL)
+	if (!optval)
 		val = 0;
 	else {
 		if (optlen >= sizeof(int)) {
@@ -144,6 +160,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 	if (ip6_mroute_opt(optname))
 		return ip6_mroute_setsockopt(sk, optname, optval, optlen);
 
+	if (needs_rtnl)
+		rtnl_lock();
 	lock_sock(sk);
 
 	switch (optname) {
@@ -374,7 +392,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		 */
 		if (optlen == 0)
 			optval = NULL;
-		else if (optval == NULL)
+		else if (!optval)
 			goto e_inval;
 		else if (optlen < sizeof(struct ipv6_opt_hdr) ||
 			 optlen & 0x7 || optlen > 8 * 255)
@@ -425,7 +443,7 @@ sticky_done:
 
 		if (optlen == 0)
 			goto e_inval;
-		else if (optlen < sizeof(struct in6_pktinfo) || optval == NULL)
+		else if (optlen < sizeof(struct in6_pktinfo) || !optval)
 			goto e_inval;
 
 		if (copy_from_user(&pkt, optval, sizeof(struct in6_pktinfo))) {
@@ -464,7 +482,7 @@ sticky_done:
 
 		opt = sock_kmalloc(sk, sizeof(*opt) + optlen, GFP_KERNEL);
 		retv = -ENOBUFS;
-		if (opt == NULL)
+		if (!opt)
 			break;
 
 		memset(opt, 0, sizeof(*opt));
@@ -628,10 +646,10 @@ done:
 		psin6 = (struct sockaddr_in6 *)&greq.gr_group;
 		if (optname == MCAST_JOIN_GROUP)
 			retv = ipv6_sock_mc_join(sk, greq.gr_interface,
-				&psin6->sin6_addr);
+						 &psin6->sin6_addr);
 		else
 			retv = ipv6_sock_mc_drop(sk, greq.gr_interface,
-				&psin6->sin6_addr);
+						 &psin6->sin6_addr);
 		break;
 	}
 	case MCAST_JOIN_SOURCE_GROUP:
@@ -664,7 +682,7 @@ done:
 
 			psin6 = (struct sockaddr_in6 *)&greqs.gsr_group;
 			retv = ipv6_sock_mc_join(sk, greqs.gsr_interface,
-				&psin6->sin6_addr);
+						 &psin6->sin6_addr);
 			/* prior join w/ different source is ok */
 			if (retv && retv != -EADDRINUSE)
 				break;
@@ -841,11 +859,15 @@ pref_skip_coa:
 	}
 
 	release_sock(sk);
+	if (needs_rtnl)
+		rtnl_unlock();
 
 	return retv;
 
 e_inval:
 	release_sock(sk);
+	if (needs_rtnl)
+		rtnl_unlock();
 	return -EINVAL;
 }
 
@@ -1000,13 +1022,9 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		lock_sock(sk);
 		skb = np->pktoptions;
 		if (skb)
-			atomic_inc(&skb->users);
-		release_sock(sk);
-
-		if (skb) {
 			ip6_datagram_recv_ctl(sk, &msg, skb);
-			kfree_skb(skb);
-		} else {
+		release_sock(sk);
+		if (!skb) {
 			if (np->rxopt.bits.rxinfo) {
 				struct in6_pktinfo src_info;
 				src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif :
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 9648de2b6745..083b2927fc67 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -140,6 +140,8 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	struct net *net = sock_net(sk);
 	int err;
 
+	ASSERT_RTNL();
+
 	if (!ipv6_addr_is_multicast(addr))
 		return -EINVAL;
 
@@ -155,13 +157,12 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 
 	mc_lst = sock_kmalloc(sk, sizeof(struct ipv6_mc_socklist), GFP_KERNEL);
 
-	if (mc_lst == NULL)
+	if (!mc_lst)
 		return -ENOMEM;
 
 	mc_lst->next = NULL;
 	mc_lst->addr = *addr;
 
-	rtnl_lock();
 	if (ifindex == 0) {
 		struct rt6_info *rt;
 		rt = rt6_lookup(net, addr, NULL, 0, 0);
@@ -172,8 +173,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	} else
 		dev = __dev_get_by_index(net, ifindex);
 
-	if (dev == NULL) {
-		rtnl_unlock();
+	if (!dev) {
 		sock_kfree_s(sk, mc_lst, sizeof(*mc_lst));
 		return -ENODEV;
 	}
@@ -190,7 +190,6 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	err = ipv6_dev_mc_inc(dev, addr);
 
 	if (err) {
-		rtnl_unlock();
 		sock_kfree_s(sk, mc_lst, sizeof(*mc_lst));
 		return err;
 	}
@@ -198,10 +197,9 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	mc_lst->next = np->ipv6_mc_list;
 	rcu_assign_pointer(np->ipv6_mc_list, mc_lst);
 
-	rtnl_unlock();
-
 	return 0;
 }
+EXPORT_SYMBOL(ipv6_sock_mc_join);
 
 /*
  *	socket leave on multicast group
@@ -213,10 +211,11 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	struct ipv6_mc_socklist __rcu **lnk;
 	struct net *net = sock_net(sk);
 
+	ASSERT_RTNL();
+
 	if (!ipv6_addr_is_multicast(addr))
 		return -EINVAL;
 
-	rtnl_lock();
 	for (lnk = &np->ipv6_mc_list;
 	     (mc_lst = rtnl_dereference(*lnk)) != NULL;
 	      lnk = &mc_lst->next) {
@@ -227,7 +226,7 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
 			*lnk = mc_lst->next;
 
 			dev = __dev_get_by_index(net, mc_lst->ifindex);
-			if (dev != NULL) {
+			if (dev) {
 				struct inet6_dev *idev = __in6_dev_get(dev);
 
 				(void) ip6_mc_leave_src(sk, mc_lst, idev);
@@ -235,17 +234,16 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
 					__ipv6_dev_mc_dec(idev, &mc_lst->addr);
 			} else
 				(void) ip6_mc_leave_src(sk, mc_lst, NULL);
-			rtnl_unlock();
 
 			atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc);
 			kfree_rcu(mc_lst, rcu);
 			return 0;
 		}
 	}
-	rtnl_unlock();
 
 	return -EADDRNOTAVAIL;
 }
+EXPORT_SYMBOL(ipv6_sock_mc_drop);
 
 /* called with rcu_read_lock() */
 static struct inet6_dev *ip6_mc_find_dev_rcu(struct net *net,
@@ -438,7 +436,7 @@ done:
 	read_unlock_bh(&idev->lock);
 	rcu_read_unlock();
 	if (leavegroup)
-		return ipv6_sock_mc_drop(sk, pgsr->gsr_interface, group);
+		err = ipv6_sock_mc_drop(sk, pgsr->gsr_interface, group);
 	return err;
 }
 
@@ -825,7 +823,7 @@ static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev,
 	struct ifmcaddr6 *mc;
 
 	mc = kzalloc(sizeof(*mc), GFP_ATOMIC);
-	if (mc == NULL)
+	if (!mc)
 		return NULL;
 
 	setup_timer(&mc->mca_timer, igmp6_timer_handler, (unsigned long)mc);
@@ -862,7 +860,7 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr)
 	/* we need to take a reference on idev */
 	idev = in6_dev_get(dev);
 
-	if (idev == NULL)
+	if (!idev)
 		return -EINVAL;
 
 	write_lock_bh(&idev->lock);
@@ -1330,7 +1328,7 @@ int igmp6_event_query(struct sk_buff *skb)
 		return -EINVAL;
 
 	idev = __in6_dev_get(skb->dev);
-	if (idev == NULL)
+	if (!idev)
 		return 0;
 
 	mld = (struct mld_msg *)icmp6_hdr(skb);
@@ -1445,7 +1443,7 @@ int igmp6_event_report(struct sk_buff *skb)
 		return -EINVAL;
 
 	idev = __in6_dev_get(skb->dev);
-	if (idev == NULL)
+	if (!idev)
 		return -ENODEV;
 
 	/*
@@ -1550,7 +1548,7 @@ static void ip6_mc_hdr(struct sock *sk, struct sk_buff *skb,
 	hdr->daddr = *daddr;
 }
 
-static struct sk_buff *mld_newpack(struct inet6_dev *idev, int size)
+static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu)
 {
 	struct net_device *dev = idev->dev;
 	struct net *net = dev_net(dev);
@@ -1561,13 +1559,13 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, int size)
 	const struct in6_addr *saddr;
 	int hlen = LL_RESERVED_SPACE(dev);
 	int tlen = dev->needed_tailroom;
+	unsigned int size = mtu + hlen + tlen;
 	int err;
 	u8 ra[8] = { IPPROTO_ICMPV6, 0,
 		     IPV6_TLV_ROUTERALERT, 2, 0, 0,
 		     IPV6_TLV_PADN, 0 };
 
 	/* we assume size > sizeof(ra) here */
-	size += hlen + tlen;
 	/* limit our allocations to order-0 page */
 	size = min_t(int, size, SKB_MAX_ORDER(0, 0));
 	skb = sock_alloc_send_skb(sk, size, 1, &err);
@@ -1576,6 +1574,8 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, int size)
 		return NULL;
 
 	skb->priority = TC_PRIO_CONTROL;
+	skb->reserved_tailroom = skb_end_offset(skb) -
+				 min(mtu, skb_end_offset(skb));
 	skb_reserve(skb, hlen);
 
 	if (__ipv6_get_lladdr(idev, &addr_buf, IFA_F_TENTATIVE)) {
@@ -1644,8 +1644,9 @@ static void mld_sendpack(struct sk_buff *skb)
 
 	payload_len = skb->len;
 
-	err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, skb->dev,
-		      dst_output);
+	err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
+		      net->ipv6.igmp_sk, skb, NULL, skb->dev,
+		      dst_output_sk);
 out:
 	if (!err) {
 		ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT);
@@ -1690,8 +1691,7 @@ static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc,
 	return skb;
 }
 
-#define AVAILABLE(skb) ((skb) ? ((skb)->dev ? (skb)->dev->mtu - (skb)->len : \
-	skb_tailroom(skb)) : 0)
+#define AVAILABLE(skb)	((skb) ? skb_availroom(skb) : 0)
 
 static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
 	int type, int gdeleted, int sdeleted, int crsend)
@@ -1963,7 +1963,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type)
 
 	skb = sock_alloc_send_skb(sk, hlen + tlen + full_len, 1, &err);
 
-	if (skb == NULL) {
+	if (!skb) {
 		rcu_read_lock();
 		IP6_INC_STATS(net, __in6_dev_get(dev),
 			      IPSTATS_MIB_OUTDISCARDS);
@@ -2008,8 +2008,8 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type)
 	}
 
 	skb_dst_set(skb, dst);
-	err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, skb->dev,
-		      dst_output);
+	err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, sk, skb,
+		      NULL, skb->dev, dst_output_sk);
 out:
 	if (!err) {
 		ICMP6MSGOUT_INC_STATS(net, idev, type);
@@ -2612,7 +2612,7 @@ static struct ifmcaddr6 *igmp6_mc_get_next(struct seq_file *seq, struct ifmcaddr
 
 	im = im->next;
 	while (!im) {
-		if (likely(state->idev != NULL))
+		if (likely(state->idev))
 			read_unlock_bh(&state->idev->lock);
 
 		state->dev = next_net_device_rcu(state->dev);
@@ -2658,7 +2658,7 @@ static void igmp6_mc_seq_stop(struct seq_file *seq, void *v)
 {
 	struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq);
 
-	if (likely(state->idev != NULL)) {
+	if (likely(state->idev)) {
 		read_unlock_bh(&state->idev->lock);
 		state->idev = NULL;
 	}
@@ -2727,10 +2727,10 @@ static inline struct ip6_sf_list *igmp6_mcf_get_first(struct seq_file *seq)
 			continue;
 		read_lock_bh(&idev->lock);
 		im = idev->mc_list;
-		if (likely(im != NULL)) {
+		if (likely(im)) {
 			spin_lock_bh(&im->mca_lock);
 			psf = im->mca_sources;
-			if (likely(psf != NULL)) {
+			if (likely(psf)) {
 				state->im = im;
 				state->idev = idev;
 				break;
@@ -2751,7 +2751,7 @@ static struct ip6_sf_list *igmp6_mcf_get_next(struct seq_file *seq, struct ip6_s
 		spin_unlock_bh(&state->im->mca_lock);
 		state->im = state->im->next;
 		while (!state->im) {
-			if (likely(state->idev != NULL))
+			if (likely(state->idev))
 				read_unlock_bh(&state->idev->lock);
 
 			state->dev = next_net_device_rcu(state->dev);
@@ -2805,11 +2805,11 @@ static void igmp6_mcf_seq_stop(struct seq_file *seq, void *v)
 	__releases(RCU)
 {
 	struct igmp6_mcf_iter_state *state = igmp6_mcf_seq_private(seq);
-	if (likely(state->im != NULL)) {
+	if (likely(state->im)) {
 		spin_unlock_bh(&state->im->mca_lock);
 		state->im = NULL;
 	}
-	if (likely(state->idev != NULL)) {
+	if (likely(state->idev)) {
 		read_unlock_bh(&state->idev->lock);
 		state->idev = NULL;
 	}
@@ -2823,11 +2823,7 @@ static int igmp6_mcf_seq_show(struct seq_file *seq, void *v)
 	struct igmp6_mcf_iter_state *state = igmp6_mcf_seq_private(seq);
 
 	if (v == SEQ_START_TOKEN) {
-		seq_printf(seq,
-			   "%3s %6s "
-			   "%32s %32s %6s %6s\n", "Idx",
-			   "Device", "Multicast Address",
-			   "Source Address", "INC", "EXC");
+		seq_puts(seq, "Idx Device                Multicast Address                   Source Address    INC    EXC\n");
 	} else {
 		seq_printf(seq,
 			   "%3d %6.6s %pi6 %pi6 %6lu %6lu\n",
@@ -2910,20 +2906,32 @@ static int __net_init igmp6_net_init(struct net *net)
 
 	inet6_sk(net->ipv6.igmp_sk)->hop_limit = 1;
 
+	err = inet_ctl_sock_create(&net->ipv6.mc_autojoin_sk, PF_INET6,
+				   SOCK_RAW, IPPROTO_ICMPV6, net);
+	if (err < 0) {
+		pr_err("Failed to initialize the IGMP6 autojoin socket (err %d)\n",
+		       err);
+		goto out_sock_create;
+	}
+
 	err = igmp6_proc_init(net);
 	if (err)
-		goto out_sock_create;
-out:
-	return err;
+		goto out_sock_create_autojoin;
+
+	return 0;
 
+out_sock_create_autojoin:
+	inet_ctl_sock_destroy(net->ipv6.mc_autojoin_sk);
 out_sock_create:
 	inet_ctl_sock_destroy(net->ipv6.igmp_sk);
-	goto out;
+out:
+	return err;
 }
 
 static void __net_exit igmp6_net_exit(struct net *net)
 {
 	inet_ctl_sock_destroy(net->ipv6.igmp_sk);
+	inet_ctl_sock_destroy(net->ipv6.mc_autojoin_sk);
 	igmp6_proc_exit(net);
 }
 
diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c
index f61429d391d3..b9779d441b12 100644
--- a/net/ipv6/mip6.c
+++ b/net/ipv6/mip6.c
@@ -97,16 +97,17 @@ static int mip6_mh_filter(struct sock *sk, struct sk_buff *skb)
 		return -1;
 
 	if (mh->ip6mh_hdrlen < mip6_mh_len(mh->ip6mh_type)) {
-		LIMIT_NETDEBUG(KERN_DEBUG "mip6: MH message too short: %d vs >=%d\n",
-			       mh->ip6mh_hdrlen, mip6_mh_len(mh->ip6mh_type));
+		net_dbg_ratelimited("mip6: MH message too short: %d vs >=%d\n",
+				    mh->ip6mh_hdrlen,
+				    mip6_mh_len(mh->ip6mh_type));
 		mip6_param_prob(skb, 0, offsetof(struct ip6_mh, ip6mh_hdrlen) +
 				skb_network_header_len(skb));
 		return -1;
 	}
 
 	if (mh->ip6mh_proto != IPPROTO_NONE) {
-		LIMIT_NETDEBUG(KERN_DEBUG "mip6: MH invalid payload proto = %d\n",
-			       mh->ip6mh_proto);
+		net_dbg_ratelimited("mip6: MH invalid payload proto = %d\n",
+				    mh->ip6mh_proto);
 		mip6_param_prob(skb, 0, offsetof(struct ip6_mh, ip6mh_proto) +
 				skb_network_header_len(skb));
 		return -1;
@@ -288,7 +289,7 @@ static int mip6_destopt_offset(struct xfrm_state *x, struct sk_buff *skb,
 			 * XXX: packet if HAO exists.
 			 */
 			if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) {
-				LIMIT_NETDEBUG(KERN_WARNING "mip6: hao exists already, override\n");
+				net_dbg_ratelimited("mip6: hao exists already, override\n");
 				return offset;
 			}
 
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 4cb45c1079a2..96f153c0846b 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -84,6 +84,7 @@ do {								\
 static u32 ndisc_hash(const void *pkey,
 		      const struct net_device *dev,
 		      __u32 *hash_rnd);
+static bool ndisc_key_eq(const struct neighbour *neigh, const void *pkey);
 static int ndisc_constructor(struct neighbour *neigh);
 static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb);
 static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb);
@@ -117,7 +118,9 @@ static const struct neigh_ops ndisc_direct_ops = {
 struct neigh_table nd_tbl = {
 	.family =	AF_INET6,
 	.key_len =	sizeof(struct in6_addr),
+	.protocol =	cpu_to_be16(ETH_P_IPV6),
 	.hash =		ndisc_hash,
+	.key_eq =	ndisc_key_eq,
 	.constructor =	ndisc_constructor,
 	.pconstructor =	pndisc_constructor,
 	.pdestructor =	pndisc_destructor,
@@ -162,7 +165,8 @@ static void ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data)
 	memcpy(opt+2, data, data_len);
 	data_len += 2;
 	opt += data_len;
-	if ((space -= data_len) > 0)
+	space -= data_len;
+	if (space > 0)
 		memset(opt, 0, space);
 }
 
@@ -293,6 +297,11 @@ static u32 ndisc_hash(const void *pkey,
 	return ndisc_hashfn(pkey, dev, hash_rnd);
 }
 
+static bool ndisc_key_eq(const struct neighbour *n, const void *pkey)
+{
+	return neigh_key_eq128(n, pkey);
+}
+
 static int ndisc_constructor(struct neighbour *neigh)
 {
 	struct in6_addr *addr = (struct in6_addr *)&neigh->primary_key;
@@ -302,7 +311,7 @@ static int ndisc_constructor(struct neighbour *neigh)
 	bool is_multicast = ipv6_addr_is_multicast(addr);
 
 	in6_dev = in6_dev_get(dev);
-	if (in6_dev == NULL) {
+	if (!in6_dev) {
 		return -EINVAL;
 	}
 
@@ -347,7 +356,7 @@ static int pndisc_constructor(struct pneigh_entry *n)
 	struct in6_addr maddr;
 	struct net_device *dev = n->dev;
 
-	if (dev == NULL || __in6_dev_get(dev) == NULL)
+	if (!dev || !__in6_dev_get(dev))
 		return -EINVAL;
 	addrconf_addr_solict_mult(addr, &maddr);
 	ipv6_dev_mc_inc(dev, &maddr);
@@ -360,7 +369,7 @@ static void pndisc_destructor(struct pneigh_entry *n)
 	struct in6_addr maddr;
 	struct net_device *dev = n->dev;
 
-	if (dev == NULL || __in6_dev_get(dev) == NULL)
+	if (!dev || !__in6_dev_get(dev))
 		return;
 	addrconf_addr_solict_mult(addr, &maddr);
 	ipv6_dev_mc_dec(dev, &maddr);
@@ -454,8 +463,9 @@ static void ndisc_send_skb(struct sk_buff *skb,
 	idev = __in6_dev_get(dst->dev);
 	IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len);
 
-	err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, dst->dev,
-		      dst_output);
+	err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, sk, skb,
+		      NULL, dst->dev,
+		      dst_output_sk);
 	if (!err) {
 		ICMP6MSGOUT_INC_STATS(net, idev, type);
 		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
@@ -551,7 +561,7 @@ void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh,
 	int optlen = 0;
 	struct nd_msg *msg;
 
-	if (saddr == NULL) {
+	if (!saddr) {
 		if (ipv6_get_lladdr(dev, &addr_buf,
 				   (IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)))
 			return;
@@ -654,10 +664,12 @@ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb)
 	struct in6_addr *target = (struct in6_addr *)&neigh->primary_key;
 	int probes = atomic_read(&neigh->probes);
 
-	if (skb && ipv6_chk_addr(dev_net(dev), &ipv6_hdr(skb)->saddr, dev, 1))
+	if (skb && ipv6_chk_addr_and_flags(dev_net(dev), &ipv6_hdr(skb)->saddr,
+					   dev, 1,
+					   IFA_F_TENTATIVE|IFA_F_OPTIMISTIC))
 		saddr = &ipv6_hdr(skb)->saddr;
-
-	if ((probes -= NEIGH_VAR(neigh->parms, UCAST_PROBES)) < 0) {
+	probes -= NEIGH_VAR(neigh->parms, UCAST_PROBES);
+	if (probes < 0) {
 		if (!(neigh->nud_state & NUD_VALID)) {
 			ND_PRINTK(1, dbg,
 				  "%s: trying to ucast probe in NUD_INVALID: %pI6\n",
@@ -1019,13 +1031,13 @@ static void ndisc_ra_useropt(struct sk_buff *ra, struct nd_opt_hdr *opt)
 	size_t msg_size = base_size + nla_total_size(sizeof(struct in6_addr));
 
 	skb = nlmsg_new(msg_size, GFP_ATOMIC);
-	if (skb == NULL) {
+	if (!skb) {
 		err = -ENOBUFS;
 		goto errout;
 	}
 
 	nlh = nlmsg_put(skb, 0, 0, RTM_NEWNDUSEROPT, base_size, 0);
-	if (nlh == NULL) {
+	if (!nlh) {
 		goto nla_put_failure;
 	}
 
@@ -1038,8 +1050,7 @@ static void ndisc_ra_useropt(struct sk_buff *ra, struct nd_opt_hdr *opt)
 
 	memcpy(ndmsg + 1, opt, opt->nd_opt_len << 3);
 
-	if (nla_put(skb, NDUSEROPT_SRCADDR, sizeof(struct in6_addr),
-		    &ipv6_hdr(ra)->saddr))
+	if (nla_put_in6_addr(skb, NDUSEROPT_SRCADDR, &ipv6_hdr(ra)->saddr))
 		goto nla_put_failure;
 	nlmsg_end(skb, nlh);
 
@@ -1093,7 +1104,7 @@ static void ndisc_router_discovery(struct sk_buff *skb)
 	 */
 
 	in6_dev = __in6_dev_get(skb->dev);
-	if (in6_dev == NULL) {
+	if (!in6_dev) {
 		ND_PRINTK(0, err, "RA: can't find inet6 device for %s\n",
 			  skb->dev->name);
 		return;
@@ -1188,11 +1199,11 @@ static void ndisc_router_discovery(struct sk_buff *skb)
 
 	ND_PRINTK(3, info, "RA: rt: %p  lifetime: %d, for dev: %s\n",
 		  rt, lifetime, skb->dev->name);
-	if (rt == NULL && lifetime) {
+	if (!rt && lifetime) {
 		ND_PRINTK(3, info, "RA: adding default router\n");
 
 		rt = rt6_add_dflt_router(&ipv6_hdr(skb)->saddr, skb->dev, pref);
-		if (rt == NULL) {
+		if (!rt) {
 			ND_PRINTK(0, err,
 				  "RA: %s failed to add default route\n",
 				  __func__);
@@ -1200,7 +1211,7 @@ static void ndisc_router_discovery(struct sk_buff *skb)
 		}
 
 		neigh = dst_neigh_lookup(&rt->dst, &ipv6_hdr(skb)->saddr);
-		if (neigh == NULL) {
+		if (!neigh) {
 			ND_PRINTK(0, err,
 				  "RA: %s got default router without neighbour\n",
 				  __func__);
@@ -1215,7 +1226,14 @@ static void ndisc_router_discovery(struct sk_buff *skb)
 	if (rt)
 		rt6_set_expires(rt, jiffies + (HZ * lifetime));
 	if (ra_msg->icmph.icmp6_hop_limit) {
-		in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit;
+		/* Only set hop_limit on the interface if it is higher than
+		 * the current hop_limit.
+		 */
+		if (in6_dev->cnf.hop_limit < ra_msg->icmph.icmp6_hop_limit) {
+			in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit;
+		} else {
+			ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than current\n");
+		}
 		if (rt)
 			dst_metric_set(&rt->dst, RTAX_HOPLIMIT,
 				       ra_msg->icmph.icmp6_hop_limit);
@@ -1347,7 +1365,7 @@ skip_routeinfo:
 		}
 	}
 
-	if (ndopts.nd_opts_mtu) {
+	if (ndopts.nd_opts_mtu && in6_dev->cnf.accept_ra_mtu) {
 		__be32 n;
 		u32 mtu;
 
@@ -1763,7 +1781,7 @@ int __init ndisc_init(void)
 	/*
 	 * Initialize the neighbour table
 	 */
-	neigh_table_init(&nd_tbl);
+	neigh_table_init(NEIGH_ND_TABLE, &nd_tbl);
 
 #ifdef CONFIG_SYSCTL
 	err = neigh_sysctl_register(NULL, &nd_tbl.parms,
@@ -1796,6 +1814,6 @@ void ndisc_cleanup(void)
 #ifdef CONFIG_SYSCTL
 	neigh_sysctl_unregister(&nd_tbl.parms);
 #endif
-	neigh_table_clear(&nd_tbl);
+	neigh_table_clear(NEIGH_ND_TABLE, &nd_tbl);
 	unregister_pernet_subsys(&ndisc_net_ops);
 }
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index d38e6a8d8b9f..d958718b5031 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -36,7 +36,7 @@ int ip6_route_me_harder(struct sk_buff *skb)
 	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");
+		net_dbg_ratelimited("ip6_route_me_harder: No more route\n");
 		dst_release(dst);
 		return err;
 	}
@@ -84,7 +84,7 @@ static void nf_ip6_saveroute(const struct sk_buff *skb,
 {
 	struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry);
 
-	if (entry->hook == NF_INET_LOCAL_OUT) {
+	if (entry->state.hook == NF_INET_LOCAL_OUT) {
 		const struct ipv6hdr *iph = ipv6_hdr(skb);
 
 		rt_info->daddr = iph->daddr;
@@ -98,7 +98,7 @@ static int nf_ip6_reroute(struct sk_buff *skb,
 {
 	struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry);
 
-	if (entry->hook == NF_INET_LOCAL_OUT) {
+	if (entry->state.hook == NF_INET_LOCAL_OUT) {
 		const struct ipv6hdr *iph = ipv6_hdr(skb);
 		if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) ||
 		    !ipv6_addr_equal(&iph->saddr, &rt_info->saddr) ||
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 6af874fc187f..ca6998345b42 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -25,14 +25,16 @@ config NF_CONNTRACK_IPV6
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
+if NF_TABLES
+
 config NF_TABLES_IPV6
-	depends on NF_TABLES
 	tristate "IPv6 nf_tables support"
 	help
 	  This option enables the IPv6 support for nf_tables.
 
+if NF_TABLES_IPV6
+
 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
@@ -40,16 +42,18 @@ config NFT_CHAIN_ROUTE_IPV6
 	  fields such as the source, destination, flowlabel, hop-limit and
 	  the packet mark.
 
-config NF_REJECT_IPV6
-	tristate "IPv6 packet rejection"
-	default m if NETFILTER_ADVANCED=n
-
 config NFT_REJECT_IPV6
-	depends on NF_TABLES_IPV6
 	select NF_REJECT_IPV6
 	default NFT_REJECT
 	tristate
 
+endif # NF_TABLES_IPV6
+endif # NF_TABLES
+
+config NF_REJECT_IPV6
+	tristate "IPv6 packet rejection"
+	default m if NETFILTER_ADVANCED=n
+
 config NF_LOG_IPV6
 	tristate "IPv6 packet logging"
 	default m if NETFILTER_ADVANCED=n
@@ -91,6 +95,15 @@ config NFT_MASQ_IPV6
 	  This is the expression that provides IPv4 masquerading support for
 	  nf_tables.
 
+config NFT_REDIR_IPV6
+	tristate "IPv6 redirect support for nf_tables"
+	depends on NF_TABLES_IPV6
+	depends on NFT_REDIR
+	select NF_NAT_REDIRECT
+	help
+	  This is the expression that provides IPv4 redirect support for
+	  nf_tables.
+
 endif # NF_NAT_IPV6
 
 config IP6_NF_IPTABLES
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index fbb25f01143c..c36e0a5490de 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -36,6 +36,7 @@ obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o
 obj-$(CONFIG_NFT_CHAIN_NAT_IPV6) += nft_chain_nat_ipv6.o
 obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o
 obj-$(CONFIG_NFT_MASQ_IPV6) += nft_masq_ipv6.o
+obj-$(CONFIG_NFT_REDIR_IPV6) += nft_redir_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 e080fbbbc0e5..62f5b0d0bc9b 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -9,7 +9,10 @@
  * 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/kernel.h>
 #include <linux/capability.h>
 #include <linux/in.h>
 #include <linux/skbuff.h>
@@ -234,7 +237,7 @@ static struct nf_loginfo trace_loginfo = {
 	.type = NF_LOG_TYPE_LOG,
 	.u = {
 		.log = {
-			.level = 4,
+			.level = LOGLEVEL_WARNING,
 			.logflags = NF_LOG_MASK,
 		},
 	},
@@ -298,9 +301,9 @@ static void trace_packet(const struct sk_buff *skb,
 		    &chainname, &comment, &rulenum) != 0)
 			break;
 
-	nf_log_packet(net, AF_INET6, hook, skb, in, out, &trace_loginfo,
-		      "TRACE: %s:%s:%s:%u ",
-		      tablename, chainname, comment, rulenum);
+	nf_log_trace(net, AF_INET6, hook, skb, in, out, &trace_loginfo,
+		     "TRACE: %s:%s:%s:%u ",
+		     tablename, chainname, comment, rulenum);
 }
 #endif
 
@@ -314,8 +317,7 @@ ip6t_next_entry(const struct ip6t_entry *entry)
 unsigned int
 ip6t_do_table(struct sk_buff *skb,
 	      unsigned int hook,
-	      const struct net_device *in,
-	      const struct net_device *out,
+	      const struct nf_hook_state *state,
 	      struct xt_table *table)
 {
 	static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long))));
@@ -330,8 +332,8 @@ ip6t_do_table(struct sk_buff *skb,
 	unsigned int addend;
 
 	/* Initialization */
-	indev = in ? in->name : nulldevname;
-	outdev = out ? out->name : nulldevname;
+	indev = state->in ? state->in->name : nulldevname;
+	outdev = state->out ? state->out->name : nulldevname;
 	/* We handle fragments by dealing with the first fragment as
 	 * if it was a normal packet.  All other fragments are treated
 	 * normally, except that they will NEVER match rules that ask
@@ -339,8 +341,8 @@ ip6t_do_table(struct sk_buff *skb,
 	 * rule is also a fragment-specific rule, non-fragments won't
 	 * match it. */
 	acpar.hotdrop = false;
-	acpar.in      = in;
-	acpar.out     = out;
+	acpar.in      = state->in;
+	acpar.out     = state->out;
 	acpar.family  = NFPROTO_IPV6;
 	acpar.hooknum = hook;
 
@@ -390,7 +392,7 @@ ip6t_do_table(struct sk_buff *skb,
 #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
 		/* The packet is traced: log it */
 		if (unlikely(skb->nf_trace))
-			trace_packet(skb, hook, in, out,
+			trace_packet(skb, hook, state->in, state->out,
 				     table->name, private, e);
 #endif
 		/* Standard target? */
@@ -1273,6 +1275,9 @@ do_replace(struct net *net, const void __user *user, unsigned int len)
 	/* overflow check */
 	if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
 		return -ENOMEM;
+	if (tmp.num_counters == 0)
+		return -EINVAL;
+
 	tmp.name[sizeof(tmp.name)-1] = 0;
 
 	newinfo = xt_alloc_table_info(tmp.size);
@@ -1820,6 +1825,9 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len)
 		return -ENOMEM;
 	if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
 		return -ENOMEM;
+	if (tmp.num_counters == 0)
+		return -EINVAL;
+
 	tmp.name[sizeof(tmp.name)-1] = 0;
 
 	newinfo = xt_alloc_table_info(tmp.size);
diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c
index 544b0a9da1b5..12331efd49cf 100644
--- a/net/ipv6/netfilter/ip6t_REJECT.c
+++ b/net/ipv6/netfilter/ip6t_REJECT.c
@@ -83,7 +83,8 @@ static int reject_tg6_check(const struct xt_tgchk_param *par)
 		return -EINVAL;
 	} else if (rejinfo->with == IP6T_TCP_RESET) {
 		/* Must specify that it's a TCP packet */
-		if (e->ipv6.proto != IPPROTO_TCP ||
+		if (!(e->ipv6.flags & IP6T_F_PROTO) ||
+		    e->ipv6.proto != IPPROTO_TCP ||
 		    (e->ipv6.invflags & XT_INV_PROTO)) {
 			pr_info("TCP_RESET illegal for non-tcp\n");
 			return -EINVAL;
diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c
index a0d17270117c..6edb7b106de7 100644
--- a/net/ipv6/netfilter/ip6t_SYNPROXY.c
+++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c
@@ -315,11 +315,9 @@ synproxy_tg6(struct sk_buff *skb, const struct xt_action_param *par)
 
 static unsigned int ipv6_synproxy_hook(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 *))
+				       const struct nf_hook_state *nhs)
 {
-	struct synproxy_net *snet = synproxy_pernet(dev_net(in ? : out));
+	struct synproxy_net *snet = synproxy_pernet(dev_net(nhs->in ? : nhs->out));
 	enum ip_conntrack_info ctinfo;
 	struct nf_conn *ct;
 	struct nf_conn_synproxy *synproxy;
diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c
index ca7f6c128086..5c33d8abc077 100644
--- a/net/ipv6/netfilter/ip6table_filter.c
+++ b/net/ipv6/netfilter/ip6table_filter.c
@@ -33,13 +33,11 @@ static const struct xt_table packet_filter = {
 /* The work comes in here from netfilter.c. */
 static unsigned int
 ip6table_filter_hook(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 *))
+		     const struct nf_hook_state *state)
 {
-	const struct net *net = dev_net((in != NULL) ? in : out);
+	const struct net *net = dev_net(state->in ? state->in : state->out);
 
-	return ip6t_do_table(skb, ops->hooknum, in, out,
-			     net->ipv6.ip6table_filter);
+	return ip6t_do_table(skb, ops->hooknum, state, net->ipv6.ip6table_filter);
 }
 
 static struct nf_hook_ops *filter_ops __read_mostly;
diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c
index 307bbb782d14..b551f5b79fe2 100644
--- a/net/ipv6/netfilter/ip6table_mangle.c
+++ b/net/ipv6/netfilter/ip6table_mangle.c
@@ -32,7 +32,7 @@ static const struct xt_table packet_mangler = {
 };
 
 static unsigned int
-ip6t_mangle_out(struct sk_buff *skb, const struct net_device *out)
+ip6t_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state)
 {
 	unsigned int ret;
 	struct in6_addr saddr, daddr;
@@ -57,8 +57,8 @@ ip6t_mangle_out(struct sk_buff *skb, const struct net_device *out)
 	/* flowlabel and prio (includes version, which shouldn't change either */
 	flowlabel = *((u_int32_t *)ipv6_hdr(skb));
 
-	ret = ip6t_do_table(skb, NF_INET_LOCAL_OUT, NULL, out,
-			    dev_net(out)->ipv6.ip6table_mangle);
+	ret = ip6t_do_table(skb, NF_INET_LOCAL_OUT, state,
+			    dev_net(state->out)->ipv6.ip6table_mangle);
 
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    (!ipv6_addr_equal(&ipv6_hdr(skb)->saddr, &saddr) ||
@@ -77,17 +77,16 @@ ip6t_mangle_out(struct sk_buff *skb, const struct net_device *out)
 /* The work comes in here from netfilter.c. */
 static unsigned int
 ip6table_mangle_hook(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 *))
+		     const struct nf_hook_state *state)
 {
 	if (ops->hooknum == NF_INET_LOCAL_OUT)
-		return ip6t_mangle_out(skb, out);
+		return ip6t_mangle_out(skb, state);
 	if (ops->hooknum == NF_INET_POST_ROUTING)
-		return ip6t_do_table(skb, ops->hooknum, in, out,
-				     dev_net(out)->ipv6.ip6table_mangle);
+		return ip6t_do_table(skb, ops->hooknum, state,
+				     dev_net(state->out)->ipv6.ip6table_mangle);
 	/* INPUT/FORWARD */
-	return ip6t_do_table(skb, ops->hooknum, in, out,
-			     dev_net(in)->ipv6.ip6table_mangle);
+	return ip6t_do_table(skb, ops->hooknum, state,
+			     dev_net(state->in)->ipv6.ip6table_mangle);
 }
 
 static struct nf_hook_ops *mangle_ops __read_mostly;
diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c
index b0634ac996b7..c3a7f7af0ed4 100644
--- a/net/ipv6/netfilter/ip6table_nat.c
+++ b/net/ipv6/netfilter/ip6table_nat.c
@@ -32,49 +32,40 @@ static const struct xt_table nf_nat_ipv6_table = {
 
 static unsigned int ip6table_nat_do_chain(const struct nf_hook_ops *ops,
 					  struct sk_buff *skb,
-					  const struct net_device *in,
-					  const struct net_device *out,
+					  const struct nf_hook_state *state,
 					  struct nf_conn *ct)
 {
 	struct net *net = nf_ct_net(ct);
 
-	return ip6t_do_table(skb, ops->hooknum, in, out, net->ipv6.ip6table_nat);
+	return ip6t_do_table(skb, ops->hooknum, state, net->ipv6.ip6table_nat);
 }
 
 static unsigned int ip6table_nat_fn(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 *))
+				    const struct nf_hook_state *state)
 {
-	return nf_nat_ipv6_fn(ops, skb, in, out, ip6table_nat_do_chain);
+	return nf_nat_ipv6_fn(ops, skb, state, ip6table_nat_do_chain);
 }
 
 static unsigned int ip6table_nat_in(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 *))
+				    const struct nf_hook_state *state)
 {
-	return nf_nat_ipv6_in(ops, skb, in, out, ip6table_nat_do_chain);
+	return nf_nat_ipv6_in(ops, skb, state, ip6table_nat_do_chain);
 }
 
 static unsigned int ip6table_nat_out(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 *))
+				     const struct nf_hook_state *state)
 {
-	return nf_nat_ipv6_out(ops, skb, in, out, ip6table_nat_do_chain);
+	return nf_nat_ipv6_out(ops, skb, state, ip6table_nat_do_chain);
 }
 
 static unsigned int ip6table_nat_local_fn(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 *))
+					  const struct nf_hook_state *state)
 {
-	return nf_nat_ipv6_local_fn(ops, skb, in, out, ip6table_nat_do_chain);
+	return nf_nat_ipv6_local_fn(ops, skb, state, ip6table_nat_do_chain);
 }
 
 static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = {
diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c
index 5274740acecc..0b33caad2b69 100644
--- a/net/ipv6/netfilter/ip6table_raw.c
+++ b/net/ipv6/netfilter/ip6table_raw.c
@@ -20,13 +20,11 @@ static const struct xt_table packet_raw = {
 /* The work comes in here from netfilter.c. */
 static unsigned int
 ip6table_raw_hook(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 *))
+		  const struct nf_hook_state *state)
 {
-	const struct net *net = dev_net((in != NULL) ? in : out);
+	const struct net *net = dev_net(state->in ? state->in : state->out);
 
-	return ip6t_do_table(skb, ops->hooknum, in, out,
-			     net->ipv6.ip6table_raw);
+	return ip6t_do_table(skb, ops->hooknum, state, net->ipv6.ip6table_raw);
 }
 
 static struct nf_hook_ops *rawtable_ops __read_mostly;
diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c
index ab3b0219ecfa..fcef83c25f7b 100644
--- a/net/ipv6/netfilter/ip6table_security.c
+++ b/net/ipv6/netfilter/ip6table_security.c
@@ -37,13 +37,11 @@ static const struct xt_table security_table = {
 
 static unsigned int
 ip6table_security_hook(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 *))
+		       const struct nf_hook_state *state)
 {
-	const struct net *net = dev_net((in != NULL) ? in : out);
+	const struct net *net = dev_net(state->in ? state->in : state->out);
 
-	return ip6t_do_table(skb, ops->hooknum, in, out,
+	return ip6t_do_table(skb, ops->hooknum, state,
 			     net->ipv6.ip6table_security);
 }
 
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index 4cbc6b290dd5..4ba0c34c627b 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -60,11 +60,11 @@ static bool ipv6_invert_tuple(struct nf_conntrack_tuple *tuple,
 	return true;
 }
 
-static int ipv6_print_tuple(struct seq_file *s,
+static void ipv6_print_tuple(struct seq_file *s,
 			    const struct nf_conntrack_tuple *tuple)
 {
-	return seq_printf(s, "src=%pI6 dst=%pI6 ",
-			  tuple->src.u3.ip6, tuple->dst.u3.ip6);
+	seq_printf(s, "src=%pI6 dst=%pI6 ",
+		   tuple->src.u3.ip6, tuple->dst.u3.ip6);
 }
 
 static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
@@ -97,9 +97,7 @@ static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
 
 static unsigned int ipv6_helper(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 *))
+				const struct nf_hook_state *state)
 {
 	struct nf_conn *ct;
 	const struct nf_conn_help *help;
@@ -135,9 +133,7 @@ static unsigned int ipv6_helper(const struct nf_hook_ops *ops,
 
 static unsigned int ipv6_confirm(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 *))
+				 const struct nf_hook_state *state)
 {
 	struct nf_conn *ct;
 	enum ip_conntrack_info ctinfo;
@@ -171,25 +167,21 @@ out:
 
 static unsigned int ipv6_conntrack_in(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 *))
+				      const struct nf_hook_state *state)
 {
-	return nf_conntrack_in(dev_net(in), PF_INET6, ops->hooknum, skb);
+	return nf_conntrack_in(dev_net(state->in), PF_INET6, ops->hooknum, skb);
 }
 
 static unsigned int ipv6_conntrack_local(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 *))
+					 const struct nf_hook_state *state)
 {
 	/* root is playing with raw sockets. */
 	if (skb->len < sizeof(struct ipv6hdr)) {
 		net_notice_ratelimited("ipv6_conntrack_local: packet too short\n");
 		return NF_ACCEPT;
 	}
-	return nf_conntrack_in(dev_net(out), PF_INET6, ops->hooknum, skb);
+	return nf_conntrack_in(dev_net(state->out), PF_INET6, ops->hooknum, skb);
 }
 
 static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = {
@@ -290,10 +282,8 @@ ipv6_getorigdst(struct sock *sk, int optval, void __user *user, int *len)
 static int ipv6_tuple_to_nlattr(struct sk_buff *skb,
 				const struct nf_conntrack_tuple *tuple)
 {
-	if (nla_put(skb, CTA_IP_V6_SRC, sizeof(u_int32_t) * 4,
-		    &tuple->src.u3.ip6) ||
-	    nla_put(skb, CTA_IP_V6_DST, sizeof(u_int32_t) * 4,
-		    &tuple->dst.u3.ip6))
+	if (nla_put_in6_addr(skb, CTA_IP_V6_SRC, &tuple->src.u3.in6) ||
+	    nla_put_in6_addr(skb, CTA_IP_V6_DST, &tuple->dst.u3.in6))
 		goto nla_put_failure;
 	return 0;
 
@@ -312,10 +302,8 @@ static int ipv6_nlattr_to_tuple(struct nlattr *tb[],
 	if (!tb[CTA_IP_V6_SRC] || !tb[CTA_IP_V6_DST])
 		return -EINVAL;
 
-	memcpy(&t->src.u3.ip6, nla_data(tb[CTA_IP_V6_SRC]),
-	       sizeof(u_int32_t) * 4);
-	memcpy(&t->dst.u3.ip6, nla_data(tb[CTA_IP_V6_DST]),
-	       sizeof(u_int32_t) * 4);
+	t->src.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_SRC]);
+	t->dst.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_DST]);
 
 	return 0;
 }
diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
index b3807c5cb888..90388d606483 100644
--- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
@@ -84,13 +84,13 @@ static bool icmpv6_invert_tuple(struct nf_conntrack_tuple *tuple,
 }
 
 /* Print out the per-protocol part of the tuple. */
-static int icmpv6_print_tuple(struct seq_file *s,
+static void icmpv6_print_tuple(struct seq_file *s,
 			      const struct nf_conntrack_tuple *tuple)
 {
-	return seq_printf(s, "type=%u code=%u id=%u ",
-			  tuple->dst.u.icmp.type,
-			  tuple->dst.u.icmp.code,
-			  ntohs(tuple->src.u.icmp.id));
+	seq_printf(s, "type=%u code=%u id=%u ",
+		   tuple->dst.u.icmp.type,
+		   tuple->dst.u.icmp.code,
+		   ntohs(tuple->src.u.icmp.id));
 }
 
 static unsigned int *icmpv6_get_timeouts(struct net *net)
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index e70382e4dfb5..a45db0b4785c 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -54,9 +54,7 @@ static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum,
 
 static unsigned int ipv6_defrag(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 *))
+				const struct nf_hook_state *state)
 {
 	struct sk_buff *reasm;
 
@@ -77,9 +75,9 @@ static unsigned int ipv6_defrag(const struct nf_hook_ops *ops,
 
 	nf_ct_frag6_consume_orig(reasm);
 
-	NF_HOOK_THRESH(NFPROTO_IPV6, ops->hooknum, reasm,
-		       (struct net_device *) in, (struct net_device *) out,
-		       okfn, NF_IP6_PRI_CONNTRACK_DEFRAG + 1);
+	NF_HOOK_THRESH(NFPROTO_IPV6, ops->hooknum, state->sk, reasm,
+		       state->in, state->out,
+		       state->okfn, NF_IP6_PRI_CONNTRACK_DEFRAG + 1);
 
 	return NF_STOLEN;
 }
diff --git a/net/ipv6/netfilter/nf_log_ipv6.c b/net/ipv6/netfilter/nf_log_ipv6.c
index 7b17a0be93e7..8dd869642f45 100644
--- a/net/ipv6/netfilter/nf_log_ipv6.c
+++ b/net/ipv6/netfilter/nf_log_ipv6.c
@@ -6,6 +6,9 @@
  * published by the Free Software Foundation.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/spinlock.h>
 #include <linux/skbuff.h>
@@ -26,7 +29,7 @@ static struct nf_loginfo default_loginfo = {
 	.type	= NF_LOG_TYPE_LOG,
 	.u = {
 		.log = {
-			.level	  = 5,
+			.level	  = LOGLEVEL_NOTICE,
 			.logflags = NF_LOG_MASK,
 		},
 	},
@@ -398,8 +401,17 @@ static int __init nf_log_ipv6_init(void)
 	if (ret < 0)
 		return ret;
 
-	nf_log_register(NFPROTO_IPV6, &nf_ip6_logger);
+	ret = nf_log_register(NFPROTO_IPV6, &nf_ip6_logger);
+	if (ret < 0) {
+		pr_err("failed to register logger\n");
+		goto err1;
+	}
+
 	return 0;
+
+err1:
+	unregister_pernet_subsys(&nf_log_ipv6_net_ops);
+	return ret;
 }
 
 static void __exit nf_log_ipv6_exit(void)
@@ -412,6 +424,6 @@ module_init(nf_log_ipv6_init);
 module_exit(nf_log_ipv6_exit);
 
 MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
-MODULE_DESCRIPTION("Netfilter IPv4 packet logging");
+MODULE_DESCRIPTION("Netfilter IPv6 packet logging");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_NF_LOGGER(AF_INET6, 0);
diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
index c5812e1c1ffb..e76900e0aa92 100644
--- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
@@ -263,11 +263,10 @@ EXPORT_SYMBOL_GPL(nf_nat_icmpv6_reply_translation);
 
 unsigned int
 nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
-	       const struct net_device *in, const struct net_device *out,
+	       const struct nf_hook_state *state,
 	       unsigned int (*do_chain)(const struct nf_hook_ops *ops,
 					struct sk_buff *skb,
-					const struct net_device *in,
-					const struct net_device *out,
+					const struct nf_hook_state *state,
 					struct nf_conn *ct))
 {
 	struct nf_conn *ct;
@@ -318,7 +317,7 @@ nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		if (!nf_nat_initialized(ct, maniptype)) {
 			unsigned int ret;
 
-			ret = do_chain(ops, skb, in, out, ct);
+			ret = do_chain(ops, skb, state, ct);
 			if (ret != NF_ACCEPT)
 				return ret;
 
@@ -332,7 +331,7 @@ nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
 			pr_debug("Already setup manip %s for ct %p\n",
 				 maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST",
 				 ct);
-			if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
+			if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, state->out))
 				goto oif_changed;
 		}
 		break;
@@ -341,7 +340,7 @@ nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		/* ESTABLISHED */
 		NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
 			     ctinfo == IP_CT_ESTABLISHED_REPLY);
-		if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
+		if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, state->out))
 			goto oif_changed;
 	}
 
@@ -355,17 +354,16 @@ EXPORT_SYMBOL_GPL(nf_nat_ipv6_fn);
 
 unsigned int
 nf_nat_ipv6_in(const struct nf_hook_ops *ops, struct sk_buff *skb,
-	       const struct net_device *in, const struct net_device *out,
+	       const struct nf_hook_state *state,
 	       unsigned int (*do_chain)(const struct nf_hook_ops *ops,
 					struct sk_buff *skb,
-					const struct net_device *in,
-					const struct net_device *out,
+					const struct nf_hook_state *state,
 					struct nf_conn *ct))
 {
 	unsigned int ret;
 	struct in6_addr daddr = ipv6_hdr(skb)->daddr;
 
-	ret = nf_nat_ipv6_fn(ops, skb, in, out, do_chain);
+	ret = nf_nat_ipv6_fn(ops, skb, state, do_chain);
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr))
 		skb_dst_drop(skb);
@@ -376,11 +374,10 @@ EXPORT_SYMBOL_GPL(nf_nat_ipv6_in);
 
 unsigned int
 nf_nat_ipv6_out(const struct nf_hook_ops *ops, struct sk_buff *skb,
-		const struct net_device *in, const struct net_device *out,
+		const struct nf_hook_state *state,
 		unsigned int (*do_chain)(const struct nf_hook_ops *ops,
 					 struct sk_buff *skb,
-					 const struct net_device *in,
-					 const struct net_device *out,
+					 const struct nf_hook_state *state,
 					 struct nf_conn *ct))
 {
 #ifdef CONFIG_XFRM
@@ -394,7 +391,7 @@ nf_nat_ipv6_out(const struct nf_hook_ops *ops, struct sk_buff *skb,
 	if (skb->len < sizeof(struct ipv6hdr))
 		return NF_ACCEPT;
 
-	ret = nf_nat_ipv6_fn(ops, skb, in, out, do_chain);
+	ret = nf_nat_ipv6_fn(ops, skb, state, do_chain);
 #ifdef CONFIG_XFRM
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    !(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
@@ -418,11 +415,10 @@ EXPORT_SYMBOL_GPL(nf_nat_ipv6_out);
 
 unsigned int
 nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
-		     const struct net_device *in, const struct net_device *out,
+		     const struct nf_hook_state *state,
 		     unsigned int (*do_chain)(const struct nf_hook_ops *ops,
 					      struct sk_buff *skb,
-					      const struct net_device *in,
-					      const struct net_device *out,
+					      const struct nf_hook_state *state,
 					      struct nf_conn *ct))
 {
 	const struct nf_conn *ct;
@@ -434,7 +430,7 @@ nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
 	if (skb->len < sizeof(struct ipv6hdr))
 		return NF_ACCEPT;
 
-	ret = nf_nat_ipv6_fn(ops, skb, in, out, do_chain);
+	ret = nf_nat_ipv6_fn(ops, skb, state, do_chain);
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
 		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c
index 015eb8a80766..94b4c6dfb400 100644
--- a/net/ipv6/netfilter/nf_reject_ipv6.c
+++ b/net/ipv6/netfilter/nf_reject_ipv6.c
@@ -11,7 +11,9 @@
 #include <net/ip6_route.h>
 #include <net/ip6_fib.h>
 #include <net/ip6_checksum.h>
+#include <net/netfilter/ipv6/nf_reject.h>
 #include <linux/netfilter_ipv6.h>
+#include <linux/netfilter_bridge.h>
 #include <net/netfilter/ipv6/nf_reject.h>
 
 const struct tcphdr *nf_reject_ip6_tcphdr_get(struct sk_buff *oldskb,
@@ -64,7 +66,7 @@ EXPORT_SYMBOL_GPL(nf_reject_ip6_tcphdr_get);
 
 struct ipv6hdr *nf_reject_ip6hdr_put(struct sk_buff *nskb,
 				     const struct sk_buff *oldskb,
-				     __be16 protocol, int hoplimit)
+				     __u8 protocol, int hoplimit)
 {
 	struct ipv6hdr *ip6h;
 	const struct ipv6hdr *oip6h = ipv6_hdr(oldskb);
@@ -194,7 +196,8 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
 	 */
 	if (oldskb->nf_bridge) {
 		struct ethhdr *oeth = eth_hdr(oldskb);
-		nskb->dev = oldskb->nf_bridge->physindev;
+
+		nskb->dev = nf_bridge_get_physindev(oldskb);
 		nskb->protocol = htons(ETH_P_IPV6);
 		ip6h->payload_len = htons(sizeof(struct tcphdr));
 		if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol),
@@ -207,4 +210,39 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
 }
 EXPORT_SYMBOL_GPL(nf_send_reset6);
 
+static bool reject6_csum_ok(struct sk_buff *skb, int hook)
+{
+	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
+	int thoff;
+	__be16 fo;
+	u8 proto;
+
+	if (skb->csum_bad)
+		return false;
+
+	if (skb_csum_unnecessary(skb))
+		return true;
+
+	proto = ip6h->nexthdr;
+	thoff = ipv6_skip_exthdr(skb, ((u8*)(ip6h+1) - skb->data), &proto, &fo);
+
+	if (thoff < 0 || thoff >= skb->len || (fo & htons(~0x7)) != 0)
+		return false;
+
+	return nf_ip6_checksum(skb, hook, thoff, proto) == 0;
+}
+
+void nf_send_unreach6(struct net *net, struct sk_buff *skb_in,
+		      unsigned char code, unsigned int hooknum)
+{
+	if (!reject6_csum_ok(skb_in, hooknum))
+		return;
+
+	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);
+}
+EXPORT_SYMBOL_GPL(nf_send_unreach6);
+
 MODULE_LICENSE("GPL");
diff --git a/net/ipv6/netfilter/nf_tables_ipv6.c b/net/ipv6/netfilter/nf_tables_ipv6.c
index 0d812b31277d..c8148ba76d1a 100644
--- a/net/ipv6/netfilter/nf_tables_ipv6.c
+++ b/net/ipv6/netfilter/nf_tables_ipv6.c
@@ -18,14 +18,12 @@
 
 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 *))
+				      const struct nf_hook_state *state)
 {
 	struct nft_pktinfo pkt;
 
 	/* malformed packet, drop it */
-	if (nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out) < 0)
+	if (nft_set_pktinfo_ipv6(&pkt, ops, skb, state) < 0)
 		return NF_DROP;
 
 	return nft_do_chain(&pkt, ops);
@@ -33,9 +31,7 @@ static unsigned int nft_do_chain_ipv6(const struct nf_hook_ops *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 *))
+				    const struct nf_hook_state *state)
 {
 	if (unlikely(skb->len < sizeof(struct ipv6hdr))) {
 		if (net_ratelimit())
@@ -44,7 +40,7 @@ static unsigned int nft_ipv6_output(const struct nf_hook_ops *ops,
 		return NF_ACCEPT;
 	}
 
-	return nft_do_chain_ipv6(ops, skb, in, out, okfn);
+	return nft_do_chain_ipv6(ops, skb, state);
 }
 
 struct nft_af_info nft_af_ipv6 __read_mostly = {
diff --git a/net/ipv6/netfilter/nft_chain_nat_ipv6.c b/net/ipv6/netfilter/nft_chain_nat_ipv6.c
index 1c4b75dd425b..951bb458b7bd 100644
--- a/net/ipv6/netfilter/nft_chain_nat_ipv6.c
+++ b/net/ipv6/netfilter/nft_chain_nat_ipv6.c
@@ -26,51 +26,42 @@
 
 static unsigned int nft_nat_do_chain(const struct nf_hook_ops *ops,
 				     struct sk_buff *skb,
-				     const struct net_device *in,
-				     const struct net_device *out,
+				     const struct nf_hook_state *state,
 				     struct nf_conn *ct)
 {
 	struct nft_pktinfo pkt;
 
-	nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out);
+	nft_set_pktinfo_ipv6(&pkt, ops, skb, state);
 
 	return nft_do_chain(&pkt, ops);
 }
 
 static unsigned int nft_nat_ipv6_fn(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 *))
+				    const struct nf_hook_state *state)
 {
-	return nf_nat_ipv6_fn(ops, skb, in, out, nft_nat_do_chain);
+	return nf_nat_ipv6_fn(ops, skb, state, nft_nat_do_chain);
 }
 
 static unsigned int nft_nat_ipv6_in(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 *))
+				    const struct nf_hook_state *state)
 {
-	return nf_nat_ipv6_in(ops, skb, in, out, nft_nat_do_chain);
+	return nf_nat_ipv6_in(ops, skb, state, nft_nat_do_chain);
 }
 
 static unsigned int nft_nat_ipv6_out(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 *))
+				     const struct nf_hook_state *state)
 {
-	return nf_nat_ipv6_out(ops, skb, in, out, nft_nat_do_chain);
+	return nf_nat_ipv6_out(ops, skb, state, nft_nat_do_chain);
 }
 
 static unsigned int nft_nat_ipv6_local_fn(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 *))
+					  const struct nf_hook_state *state)
 {
-	return nf_nat_ipv6_local_fn(ops, skb, in, out, nft_nat_do_chain);
+	return nf_nat_ipv6_local_fn(ops, skb, state, nft_nat_do_chain);
 }
 
 static const struct nf_chain_type nft_chain_nat_ipv6 = {
diff --git a/net/ipv6/netfilter/nft_chain_route_ipv6.c b/net/ipv6/netfilter/nft_chain_route_ipv6.c
index 42031299585e..0dafdaac5e17 100644
--- a/net/ipv6/netfilter/nft_chain_route_ipv6.c
+++ b/net/ipv6/netfilter/nft_chain_route_ipv6.c
@@ -24,9 +24,7 @@
 
 static unsigned int nf_route_table_hook(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 *))
+					const struct nf_hook_state *state)
 {
 	unsigned int ret;
 	struct nft_pktinfo pkt;
@@ -35,7 +33,7 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops,
 	u32 mark, flowlabel;
 
 	/* malformed packet, drop it */
-	if (nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out) < 0)
+	if (nft_set_pktinfo_ipv6(&pkt, ops, skb, state) < 0)
 		return NF_DROP;
 
 	/* save source/dest address, mark, hoplimit, flowlabel, priority */
diff --git a/net/ipv6/netfilter/nft_masq_ipv6.c b/net/ipv6/netfilter/nft_masq_ipv6.c
index 8a7ac685076d..cd1ac1637a05 100644
--- a/net/ipv6/netfilter/nft_masq_ipv6.c
+++ b/net/ipv6/netfilter/nft_masq_ipv6.c
@@ -18,18 +18,16 @@
 #include <net/netfilter/ipv6/nf_nat_masquerade.h>
 
 static void nft_masq_ipv6_eval(const struct nft_expr *expr,
-			       struct nft_data data[NFT_REG_MAX + 1],
+			       struct nft_regs *regs,
 			       const struct nft_pktinfo *pkt)
 {
 	struct nft_masq *priv = nft_expr_priv(expr);
 	struct nf_nat_range range;
-	unsigned int verdict;
 
+	memset(&range, 0, sizeof(range));
 	range.flags = priv->flags;
 
-	verdict = nf_nat_masquerade_ipv6(pkt->skb, &range, pkt->out);
-
-	data[NFT_REG_VERDICT].verdict = verdict;
+	regs->verdict.code = nf_nat_masquerade_ipv6(pkt->skb, &range, pkt->out);
 }
 
 static struct nft_expr_type nft_masq_ipv6_type;
diff --git a/net/ipv6/netfilter/nft_redir_ipv6.c b/net/ipv6/netfilter/nft_redir_ipv6.c
new file mode 100644
index 000000000000..effd393bd517
--- /dev/null
+++ b/net/ipv6/netfilter/nft_redir_ipv6.c
@@ -0,0 +1,76 @@
+/*
+ * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo.borrero.glez@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.
+ */
+
+#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/nf_nat.h>
+#include <net/netfilter/nft_redir.h>
+#include <net/netfilter/nf_nat_redirect.h>
+
+static void nft_redir_ipv6_eval(const struct nft_expr *expr,
+				struct nft_regs *regs,
+				const struct nft_pktinfo *pkt)
+{
+	struct nft_redir *priv = nft_expr_priv(expr);
+	struct nf_nat_range range;
+
+	memset(&range, 0, sizeof(range));
+	if (priv->sreg_proto_min) {
+		range.min_proto.all =
+			*(__be16 *)&regs->data[priv->sreg_proto_min],
+		range.max_proto.all =
+			*(__be16 *)&regs->data[priv->sreg_proto_max],
+		range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
+	}
+
+	range.flags |= priv->flags;
+
+	regs->verdict.code = nf_nat_redirect_ipv6(pkt->skb, &range,
+						  pkt->ops->hooknum);
+}
+
+static struct nft_expr_type nft_redir_ipv6_type;
+static const struct nft_expr_ops nft_redir_ipv6_ops = {
+	.type		= &nft_redir_ipv6_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_redir)),
+	.eval		= nft_redir_ipv6_eval,
+	.init		= nft_redir_init,
+	.dump		= nft_redir_dump,
+	.validate	= nft_redir_validate,
+};
+
+static struct nft_expr_type nft_redir_ipv6_type __read_mostly = {
+	.family		= NFPROTO_IPV6,
+	.name		= "redir",
+	.ops		= &nft_redir_ipv6_ops,
+	.policy		= nft_redir_policy,
+	.maxattr	= NFTA_REDIR_MAX,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nft_redir_ipv6_module_init(void)
+{
+	return nft_register_expr(&nft_redir_ipv6_type);
+}
+
+static void __exit nft_redir_ipv6_module_exit(void)
+{
+	nft_unregister_expr(&nft_redir_ipv6_type);
+}
+
+module_init(nft_redir_ipv6_module_init);
+module_exit(nft_redir_ipv6_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>");
+MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "redir");
diff --git a/net/ipv6/netfilter/nft_reject_ipv6.c b/net/ipv6/netfilter/nft_reject_ipv6.c
index 0bc19fa87821..d0d1540ecf87 100644
--- a/net/ipv6/netfilter/nft_reject_ipv6.c
+++ b/net/ipv6/netfilter/nft_reject_ipv6.c
@@ -19,9 +19,9 @@
 #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)
+static void nft_reject_ipv6_eval(const struct nft_expr *expr,
+				 struct nft_regs *regs,
+				 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);
@@ -34,11 +34,12 @@ void nft_reject_ipv6_eval(const struct nft_expr *expr,
 	case NFT_REJECT_TCP_RST:
 		nf_send_reset6(net, pkt->skb, pkt->ops->hooknum);
 		break;
+	default:
+		break;
 	}
 
-	data[NFT_REG_VERDICT].verdict = NF_DROP;
+	regs->verdict.code = 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 = {
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index 97f41a3e68d9..85892af57364 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -9,6 +9,26 @@
 #include <net/addrconf.h>
 #include <net/secure_seq.h>
 
+static u32 __ipv6_select_ident(struct net *net, u32 hashrnd,
+			       struct in6_addr *dst, struct in6_addr *src)
+{
+	u32 hash, id;
+
+	hash = __ipv6_addr_jhash(dst, hashrnd);
+	hash = __ipv6_addr_jhash(src, hash);
+	hash ^= net_hash_mix(net);
+
+	/* Treat id of 0 as unset and if we get 0 back from ip_idents_reserve,
+	 * set the hight order instead thus minimizing possible future
+	 * collisions.
+	 */
+	id = ip_idents_reserve(hash, 1);
+	if (unlikely(!id))
+		id = 1 << 31;
+
+	return id;
+}
+
 /* This function exists only for tap drivers that must support broken
  * clients requesting UFO without specifying an IPv6 fragment ID.
  *
@@ -17,12 +37,12 @@
  *
  * The network header must be set before calling this.
  */
-void ipv6_proxy_select_ident(struct sk_buff *skb)
+void ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb)
 {
 	static u32 ip6_proxy_idents_hashrnd __read_mostly;
 	struct in6_addr buf[2];
 	struct in6_addr *addrs;
-	u32 hash, id;
+	u32 id;
 
 	addrs = skb_header_pointer(skb,
 				   skb_network_offset(skb) +
@@ -34,14 +54,26 @@ void ipv6_proxy_select_ident(struct sk_buff *skb)
 	net_get_random_once(&ip6_proxy_idents_hashrnd,
 			    sizeof(ip6_proxy_idents_hashrnd));
 
-	hash = __ipv6_addr_jhash(&addrs[1], ip6_proxy_idents_hashrnd);
-	hash = __ipv6_addr_jhash(&addrs[0], hash);
-
-	id = ip_idents_reserve(hash, 1);
+	id = __ipv6_select_ident(net, ip6_proxy_idents_hashrnd,
+				 &addrs[1], &addrs[0]);
 	skb_shinfo(skb)->ip6_frag_id = htonl(id);
 }
 EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident);
 
+void ipv6_select_ident(struct net *net, struct frag_hdr *fhdr,
+		       struct rt6_info *rt)
+{
+	static u32 ip6_idents_hashrnd __read_mostly;
+	u32 id;
+
+	net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd));
+
+	id = __ipv6_select_ident(net, ip6_idents_hashrnd, &rt->rt6i_dst.addr,
+				 &rt->rt6i_src.addr);
+	fhdr->identification = htonl(id);
+}
+EXPORT_SYMBOL(ipv6_select_ident);
+
 int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 {
 	u16 offset = sizeof(struct ipv6hdr);
@@ -104,7 +136,7 @@ int ip6_dst_hoplimit(struct dst_entry *dst)
 EXPORT_SYMBOL(ip6_dst_hoplimit);
 #endif
 
-int __ip6_local_out(struct sk_buff *skb)
+static int __ip6_local_out_sk(struct sock *sk, struct sk_buff *skb)
 {
 	int len;
 
@@ -114,19 +146,30 @@ int __ip6_local_out(struct sk_buff *skb)
 	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);
+	return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, sk, skb,
+		       NULL, skb_dst(skb)->dev, dst_output_sk);
+}
+
+int __ip6_local_out(struct sk_buff *skb)
+{
+	return __ip6_local_out_sk(skb->sk, skb);
 }
 EXPORT_SYMBOL_GPL(__ip6_local_out);
 
-int ip6_local_out(struct sk_buff *skb)
+int ip6_local_out_sk(struct sock *sk, struct sk_buff *skb)
 {
 	int err;
 
-	err = __ip6_local_out(skb);
+	err = __ip6_local_out_sk(sk, skb);
 	if (likely(err == 1))
-		err = dst_output(skb);
+		err = dst_output_sk(sk, skb);
 
 	return err;
 }
+EXPORT_SYMBOL_GPL(ip6_local_out_sk);
+
+int ip6_local_out(struct sk_buff *skb)
+{
+	return ip6_local_out_sk(skb->sk, skb);
+}
 EXPORT_SYMBOL_GPL(ip6_local_out);
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 5b7a1ed2aba9..263a5164a6f5 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -77,8 +77,7 @@ static int dummy_ipv6_chk_addr(struct net *net, const struct in6_addr *addr,
 	return 0;
 }
 
-int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
-		    size_t len)
+int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct ipv6_pinfo *np = inet6_sk(sk);
@@ -102,9 +101,10 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 
 	if (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) {
+		if (msg->msg_namelen < sizeof(*u))
 			return -EINVAL;
+		if (u->sin6_family != AF_INET6) {
+			return -EAFNOSUPPORT;
 		}
 		if (sk->sk_bound_dev_if &&
 		    sk->sk_bound_dev_if != u->sin6_scope_id) {
@@ -163,7 +163,7 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	pfh.icmph.checksum = 0;
 	pfh.icmph.un.echo.id = inet->inet_sport;
 	pfh.icmph.un.echo.sequence = user_icmph.icmp6_sequence;
-	pfh.iov = msg->msg_iov;
+	pfh.msg = msg;
 	pfh.wcheck = 0;
 	pfh.family = AF_INET6;
 
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index 1752cd0b4882..679253d0af84 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -136,6 +136,7 @@ static const struct snmp_mib snmp6_udp6_list[] = {
 	SNMP_MIB_ITEM("Udp6RcvbufErrors", UDP_MIB_RCVBUFERRORS),
 	SNMP_MIB_ITEM("Udp6SndbufErrors", UDP_MIB_SNDBUFERRORS),
 	SNMP_MIB_ITEM("Udp6InCsumErrors", UDP_MIB_CSUMERRORS),
+	SNMP_MIB_ITEM("Udp6IgnoredMulti", UDP_MIB_IGNOREDMULTI),
 	SNMP_MIB_SENTINEL
 };
 
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 896af8807979..8072bd4139b7 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -32,7 +32,7 @@
 #include <linux/netfilter_ipv6.h>
 #include <linux/skbuff.h>
 #include <linux/compat.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/ioctls.h>
 
 #include <net/net_namespace.h>
@@ -172,7 +172,7 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr)
 	read_lock(&raw_v6_hashinfo.lock);
 	sk = sk_head(&raw_v6_hashinfo.ht[hash]);
 
-	if (sk == NULL)
+	if (!sk)
 		goto out;
 
 	net = dev_net(skb->dev);
@@ -367,7 +367,7 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr,
 
 	read_lock(&raw_v6_hashinfo.lock);
 	sk = sk_head(&raw_v6_hashinfo.ht[hash]);
-	if (sk != NULL) {
+	if (sk) {
 		/* Note: ipv6_hdr(skb) != skb->data */
 		const struct ipv6hdr *ip6h = (const struct ipv6hdr *)skb->data;
 		saddr = &ip6h->saddr;
@@ -456,9 +456,8 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb)
  *	we return it, otherwise we block.
  */
 
-static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk,
-		  struct msghdr *msg, size_t len,
-		  int noblock, int flags, int *addr_len)
+static int rawv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+			 int noblock, int flags, int *addr_len)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
@@ -486,13 +485,13 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk,
 	}
 
 	if (skb_csum_unnecessary(skb)) {
-		err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+		err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	} else if (msg->msg_flags&MSG_TRUNC) {
 		if (__skb_checksum_complete(skb))
 			goto csum_copy_err;
-		err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+		err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	} else {
-		err = skb_copy_and_csum_datagram_iovec(skb, 0, msg->msg_iov);
+		err = skb_copy_and_csum_datagram_msg(skb, 0, msg);
 		if (err == -EINVAL)
 			goto csum_copy_err;
 	}
@@ -548,7 +547,8 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
 	if (!rp->checksum)
 		goto send;
 
-	if ((skb = skb_peek(&sk->sk_write_queue)) == NULL)
+	skb = skb_peek(&sk->sk_write_queue);
+	if (!skb)
 		goto out;
 
 	offset = rp->offset;
@@ -608,7 +608,7 @@ out:
 	return err;
 }
 
-static int rawv6_send_hdrinc(struct sock *sk, void *from, int length,
+static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
 			struct flowi6 *fl6, struct dst_entry **dstp,
 			unsigned int flags)
 {
@@ -630,7 +630,7 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length,
 	skb = sock_alloc_send_skb(sk,
 				  length + hlen + tlen + 15,
 				  flags & MSG_DONTWAIT, &err);
-	if (skb == NULL)
+	if (!skb)
 		goto error;
 	skb_reserve(skb, hlen);
 
@@ -647,13 +647,13 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length,
 	skb->ip_summed = CHECKSUM_NONE;
 
 	skb->transport_header = skb->network_header;
-	err = memcpy_fromiovecend((void *)iph, from, 0, length);
+	err = memcpy_from_msg(iph, msg, length);
 	if (err)
 		goto error_fault;
 
 	IP6_UPD_PO_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len);
-	err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL,
-		      rt->dst.dev, dst_output);
+	err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, sk, skb,
+		      NULL, rt->dst.dev, dst_output_sk);
 	if (err > 0)
 		err = net_xmit_errno(err);
 	if (err)
@@ -671,69 +671,65 @@ error:
 	return err;
 }
 
-static int rawv6_probe_proto_opt(struct flowi6 *fl6, struct msghdr *msg)
+struct raw6_frag_vec {
+	struct msghdr *msg;
+	int hlen;
+	char c[4];
+};
+
+static int rawv6_probe_proto_opt(struct raw6_frag_vec *rfv, struct flowi6 *fl6)
 {
-	struct iovec *iov;
-	u8 __user *type = NULL;
-	u8 __user *code = NULL;
-	u8 len = 0;
-	int probed = 0;
-	int i;
-
-	if (!msg->msg_iov)
-		return 0;
+	int err = 0;
+	switch (fl6->flowi6_proto) {
+	case IPPROTO_ICMPV6:
+		rfv->hlen = 2;
+		err = memcpy_from_msg(rfv->c, rfv->msg, rfv->hlen);
+		if (!err) {
+			fl6->fl6_icmp_type = rfv->c[0];
+			fl6->fl6_icmp_code = rfv->c[1];
+		}
+		break;
+	case IPPROTO_MH:
+		rfv->hlen = 4;
+		err = memcpy_from_msg(rfv->c, rfv->msg, rfv->hlen);
+		if (!err)
+			fl6->fl6_mh_type = rfv->c[2];
+	}
+	return err;
+}
 
-	for (i = 0; i < msg->msg_iovlen; i++) {
-		iov = &msg->msg_iov[i];
-		if (!iov)
-			continue;
+static int raw6_getfrag(void *from, char *to, int offset, int len, int odd,
+		       struct sk_buff *skb)
+{
+	struct raw6_frag_vec *rfv = from;
 
-		switch (fl6->flowi6_proto) {
-		case IPPROTO_ICMPV6:
-			/* check if one-byte field is readable or not. */
-			if (iov->iov_base && iov->iov_len < 1)
-				break;
-
-			if (!type) {
-				type = iov->iov_base;
-				/* check if code field is readable or not. */
-				if (iov->iov_len > 1)
-					code = type + 1;
-			} else if (!code)
-				code = iov->iov_base;
-
-			if (type && code) {
-				if (get_user(fl6->fl6_icmp_type, type) ||
-				    get_user(fl6->fl6_icmp_code, code))
-					return -EFAULT;
-				probed = 1;
-			}
-			break;
-		case IPPROTO_MH:
-			if (iov->iov_base && iov->iov_len < 1)
-				break;
-			/* check if type field is readable or not. */
-			if (iov->iov_len > 2 - len) {
-				u8 __user *p = iov->iov_base;
-				if (get_user(fl6->fl6_mh_type, &p[2 - len]))
-					return -EFAULT;
-				probed = 1;
-			} else
-				len += iov->iov_len;
+	if (offset < rfv->hlen) {
+		int copy = min(rfv->hlen - offset, len);
 
-			break;
-		default:
-			probed = 1;
-			break;
-		}
-		if (probed)
-			break;
+		if (skb->ip_summed == CHECKSUM_PARTIAL)
+			memcpy(to, rfv->c + offset, copy);
+		else
+			skb->csum = csum_block_add(
+				skb->csum,
+				csum_partial_copy_nocheck(rfv->c + offset,
+							  to, copy, 0),
+				odd);
+
+		odd = 0;
+		offset += copy;
+		to += copy;
+		len -= copy;
+
+		if (!len)
+			return 0;
 	}
-	return 0;
+
+	offset -= rfv->hlen;
+
+	return ip_generic_getfrag(rfv->msg, to, offset, len, odd, skb);
 }
 
-static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
-		   struct msghdr *msg, size_t len)
+static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 {
 	struct ipv6_txoptions opt_space;
 	DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
@@ -744,6 +740,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 	struct ipv6_txoptions *opt = NULL;
 	struct ip6_flowlabel *flowlabel = NULL;
 	struct dst_entry *dst = NULL;
+	struct raw6_frag_vec rfv;
 	struct flowi6 fl6;
 	int addr_len = msg->msg_namelen;
 	int hlimit = -1;
@@ -792,7 +789,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 			fl6.flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK;
 			if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) {
 				flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
-				if (flowlabel == NULL)
+				if (!flowlabel)
 					return -EINVAL;
 			}
 		}
@@ -834,20 +831,22 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 		}
 		if ((fl6.flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) {
 			flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
-			if (flowlabel == NULL)
+			if (!flowlabel)
 				return -EINVAL;
 		}
 		if (!(opt->opt_nflen|opt->opt_flen))
 			opt = NULL;
 	}
-	if (opt == NULL)
+	if (!opt)
 		opt = np->opt;
 	if (flowlabel)
 		opt = fl6_merge_options(&opt_space, flowlabel, opt);
 	opt = ipv6_fixup_options(&opt_space, opt);
 
 	fl6.flowi6_proto = proto;
-	err = rawv6_probe_proto_opt(&fl6, msg);
+	rfv.msg = msg;
+	rfv.hlen = 0;
+	err = rawv6_probe_proto_opt(&rfv, &fl6);
 	if (err)
 		goto out;
 
@@ -885,10 +884,10 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 
 back_from_confirm:
 	if (inet->hdrincl)
-		err = rawv6_send_hdrinc(sk, msg->msg_iov, len, &fl6, &dst, msg->msg_flags);
+		err = rawv6_send_hdrinc(sk, msg, len, &fl6, &dst, msg->msg_flags);
 	else {
 		lock_sock(sk);
-		err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov,
+		err = ip6_append_data(sk, raw6_getfrag, &rfv,
 			len, 0, hlimit, tclass, opt, &fl6, (struct rt6_info *)dst,
 			msg->msg_flags, dontfrag);
 
@@ -1131,7 +1130,7 @@ static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg)
 
 		spin_lock_bh(&sk->sk_receive_queue.lock);
 		skb = skb_peek(&sk->sk_receive_queue);
-		if (skb != NULL)
+		if (skb)
 			amount = skb_tail_pointer(skb) -
 				skb_transport_header(skb);
 		spin_unlock_bh(&sk->sk_receive_queue.lock);
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 1a157ca2ebc1..8ffa2c8cce77 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -69,7 +69,7 @@ struct ip6frag_skb_cb {
 
 #define FRAG6_CB(skb)	((struct ip6frag_skb_cb *)((skb)->cb))
 
-static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
+static u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
 {
 	return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK);
 }
@@ -178,7 +178,7 @@ static void ip6_frag_expire(unsigned long data)
 	ip6_expire_frag_queue(net, fq, &ip6_frags);
 }
 
-static __inline__ struct frag_queue *
+static struct frag_queue *
 fq_find(struct net *net, __be32 id, const struct in6_addr *src,
 	const struct in6_addr *dst, u8 ecn)
 {
@@ -429,7 +429,8 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
 		struct sk_buff *clone;
 		int i, plen = 0;
 
-		if ((clone = alloc_skb(0, GFP_ATOMIC)) == NULL)
+		clone = alloc_skb(0, GFP_ATOMIC);
+		if (!clone)
 			goto out_oom;
 		clone->next = head->next;
 		head->next = clone;
@@ -551,7 +552,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 
 	fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr,
 		     ip6_frag_ecn(hdr));
-	if (fq != NULL) {
+	if (fq) {
 		int ret;
 
 		spin_lock(&fq->q.lock);
@@ -631,7 +632,7 @@ static int __net_init ip6_frags_ns_sysctl_register(struct net *net)
 	table = ip6_frags_ns_ctl_table;
 	if (!net_eq(net, &init_net)) {
 		table = kmemdup(table, sizeof(ip6_frags_ns_ctl_table), GFP_KERNEL);
-		if (table == NULL)
+		if (!table)
 			goto err_alloc;
 
 		table[0].data = &net->ipv6.frags.high_thresh;
@@ -647,7 +648,7 @@ static int __net_init ip6_frags_ns_sysctl_register(struct net *net)
 	}
 
 	hdr = register_net_sysctl(net, "net/ipv6", table);
-	if (hdr == NULL)
+	if (!hdr)
 		goto err_reg;
 
 	net->ipv6.sysctl.frags_hdr = hdr;
@@ -684,21 +685,21 @@ static void ip6_frags_sysctl_unregister(void)
 	unregister_net_sysctl_table(ip6_ctl_header);
 }
 #else
-static inline int ip6_frags_ns_sysctl_register(struct net *net)
+static int ip6_frags_ns_sysctl_register(struct net *net)
 {
 	return 0;
 }
 
-static inline void ip6_frags_ns_sysctl_unregister(struct net *net)
+static void ip6_frags_ns_sysctl_unregister(struct net *net)
 {
 }
 
-static inline int ip6_frags_sysctl_register(void)
+static int ip6_frags_sysctl_register(void)
 {
 	return 0;
 }
 
-static inline void ip6_frags_sysctl_unregister(void)
+static void ip6_frags_sysctl_unregister(void)
 {
 }
 #endif
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index a318dd89b6d9..c73ae5039e46 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -141,7 +141,7 @@ static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old)
 	u32 *p = NULL;
 
 	if (!(rt->dst.flags & DST_HOST))
-		return NULL;
+		return dst_cow_metrics_generic(dst, old);
 
 	peer = rt6_get_peer_create(rt);
 	if (peer) {
@@ -194,7 +194,6 @@ static struct neighbour *ip6_neigh_lookup(const struct dst_entry *dst,
 
 static struct dst_ops ip6_dst_ops_template = {
 	.family			=	AF_INET6,
-	.protocol		=	cpu_to_be16(ETH_P_IPV6),
 	.gc			=	ip6_dst_gc,
 	.gc_thresh		=	1024,
 	.check			=	ip6_dst_check,
@@ -236,7 +235,6 @@ static u32 *ip6_rt_blackhole_cow_metrics(struct dst_entry *dst,
 
 static struct dst_ops ip6_dst_blackhole_ops = {
 	.family			=	AF_INET6,
-	.protocol		=	cpu_to_be16(ETH_P_IPV6),
 	.destroy		=	ip6_dst_destroy,
 	.check			=	ip6_dst_check,
 	.mtu			=	ip6_blackhole_mtu,
@@ -499,7 +497,7 @@ static void rt6_probe_deferred(struct work_struct *w)
 	addrconf_addr_solict_mult(&work->target, &mcaddr);
 	ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL);
 	dev_put(work->dev);
-	kfree(w);
+	kfree(work);
 }
 
 static void rt6_probe(struct rt6_info *rt)
@@ -772,23 +770,22 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
 }
 #endif
 
-#define BACKTRACK(__net, saddr)			\
-do { \
-	if (rt == __net->ipv6.ip6_null_entry) {	\
-		struct fib6_node *pn; \
-		while (1) { \
-			if (fn->fn_flags & RTN_TL_ROOT) \
-				goto out; \
-			pn = fn->parent; \
-			if (FIB6_SUBTREE(pn) && FIB6_SUBTREE(pn) != fn) \
-				fn = fib6_lookup(FIB6_SUBTREE(pn), NULL, saddr); \
-			else \
-				fn = pn; \
-			if (fn->fn_flags & RTN_RTINFO) \
-				goto restart; \
-		} \
-	} \
-} while (0)
+static struct fib6_node* fib6_backtrack(struct fib6_node *fn,
+					struct in6_addr *saddr)
+{
+	struct fib6_node *pn;
+	while (1) {
+		if (fn->fn_flags & RTN_TL_ROOT)
+			return NULL;
+		pn = fn->parent;
+		if (FIB6_SUBTREE(pn) && FIB6_SUBTREE(pn) != fn)
+			fn = fib6_lookup(FIB6_SUBTREE(pn), NULL, saddr);
+		else
+			fn = pn;
+		if (fn->fn_flags & RTN_RTINFO)
+			return fn;
+	}
+}
 
 static struct rt6_info *ip6_pol_route_lookup(struct net *net,
 					     struct fib6_table *table,
@@ -804,8 +801,11 @@ restart:
 	rt = rt6_device_match(net, rt, &fl6->saddr, fl6->flowi6_oif, flags);
 	if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0)
 		rt = rt6_multipath_select(rt, fl6, fl6->flowi6_oif, flags);
-	BACKTRACK(net, &fl6->saddr);
-out:
+	if (rt == net->ipv6.ip6_null_entry) {
+		fn = fib6_backtrack(fn, &fl6->saddr);
+		if (fn)
+			goto restart;
+	}
 	dst_use(&rt->dst, jiffies);
 	read_unlock_bh(&table->tb6_lock);
 	return rt;
@@ -851,14 +851,14 @@ EXPORT_SYMBOL(rt6_lookup);
  */
 
 static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info,
-			struct nlattr *mx, int mx_len)
+			struct mx6_config *mxc)
 {
 	int err;
 	struct fib6_table *table;
 
 	table = rt->rt6i_table;
 	write_lock_bh(&table->tb6_lock);
-	err = fib6_add(&table->tb6_root, rt, info, mx, mx_len);
+	err = fib6_add(&table->tb6_root, rt, info, mxc);
 	write_unlock_bh(&table->tb6_lock);
 
 	return err;
@@ -866,10 +866,10 @@ static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info,
 
 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, NULL, 0);
+	struct nl_info info = {	.nl_net = dev_net(rt->dst.dev), };
+	struct mx6_config mxc = { .mx = NULL, };
+
+	return __ip6_ins_rt(rt, &info, &mxc);
 }
 
 static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort,
@@ -915,33 +915,48 @@ static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort,
 static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif,
 				      struct flowi6 *fl6, int flags)
 {
-	struct fib6_node *fn;
+	struct fib6_node *fn, *saved_fn;
 	struct rt6_info *rt, *nrt;
 	int strict = 0;
 	int attempts = 3;
 	int err;
-	int reachable = net->ipv6.devconf_all->forwarding ? 0 : RT6_LOOKUP_F_REACHABLE;
 
 	strict |= flags & RT6_LOOKUP_F_IFACE;
+	if (net->ipv6.devconf_all->forwarding == 0)
+		strict |= RT6_LOOKUP_F_REACHABLE;
 
-relookup:
+redo_fib6_lookup_lock:
 	read_lock_bh(&table->tb6_lock);
 
-restart_2:
 	fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
+	saved_fn = fn;
 
-restart:
-	rt = rt6_select(fn, oif, strict | reachable);
+redo_rt6_select:
+	rt = rt6_select(fn, oif, strict);
 	if (rt->rt6i_nsiblings)
-		rt = rt6_multipath_select(rt, fl6, oif, strict | reachable);
-	BACKTRACK(net, &fl6->saddr);
-	if (rt == net->ipv6.ip6_null_entry ||
-	    rt->rt6i_flags & RTF_CACHE)
-		goto out;
+		rt = rt6_multipath_select(rt, fl6, oif, strict);
+	if (rt == net->ipv6.ip6_null_entry) {
+		fn = fib6_backtrack(fn, &fl6->saddr);
+		if (fn)
+			goto redo_rt6_select;
+		else if (strict & RT6_LOOKUP_F_REACHABLE) {
+			/* also consider unreachable route */
+			strict &= ~RT6_LOOKUP_F_REACHABLE;
+			fn = saved_fn;
+			goto redo_rt6_select;
+		} else {
+			dst_hold(&rt->dst);
+			read_unlock_bh(&table->tb6_lock);
+			goto out2;
+		}
+	}
 
 	dst_hold(&rt->dst);
 	read_unlock_bh(&table->tb6_lock);
 
+	if (rt->rt6i_flags & RTF_CACHE)
+		goto out2;
+
 	if (!(rt->rt6i_flags & (RTF_NONEXTHOP | RTF_GATEWAY)))
 		nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr);
 	else if (!(rt->dst.flags & DST_HOST))
@@ -967,15 +982,8 @@ restart:
 	 * released someone could insert this route.  Relookup.
 	 */
 	ip6_rt_put(rt);
-	goto relookup;
+	goto redo_fib6_lookup_lock;
 
-out:
-	if (reachable) {
-		reachable = 0;
-		goto restart_2;
-	}
-	dst_hold(&rt->dst);
-	read_unlock_bh(&table->tb6_lock);
 out2:
 	rt->dst.lastuse = jiffies;
 	rt->dst.__use++;
@@ -1150,12 +1158,9 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
 		struct net *net = dev_net(dst->dev);
 
 		rt6->rt6i_flags |= RTF_MODIFIED;
-		if (mtu < IPV6_MIN_MTU) {
-			u32 features = dst_metric(dst, RTAX_FEATURES);
+		if (mtu < IPV6_MIN_MTU)
 			mtu = IPV6_MIN_MTU;
-			features |= RTAX_FEATURE_ALLFRAG;
-			dst_metric_set(dst, RTAX_FEATURES, features);
-		}
+
 		dst_metric_set(dst, RTAX_MTU, mtu);
 		rt6_update_expires(rt6, net->ipv6.sysctl.ip6_rt_mtu_expires);
 	}
@@ -1237,7 +1242,13 @@ restart:
 		rt = net->ipv6.ip6_null_entry;
 		goto out;
 	}
-	BACKTRACK(net, &fl6->saddr);
+
+	if (rt == net->ipv6.ip6_null_entry) {
+		fn = fib6_backtrack(fn, &fl6->saddr);
+		if (fn)
+			goto restart;
+	}
+
 out:
 	dst_hold(&rt->dst);
 
@@ -1458,9 +1469,51 @@ out:
 	return entries > rt_max_size;
 }
 
-/*
- *
- */
+static int ip6_convert_metrics(struct mx6_config *mxc,
+			       const struct fib6_config *cfg)
+{
+	struct nlattr *nla;
+	int remaining;
+	u32 *mp;
+
+	if (!cfg->fc_mx)
+		return 0;
+
+	mp = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
+	if (unlikely(!mp))
+		return -ENOMEM;
+
+	nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
+		int type = nla_type(nla);
+
+		if (type) {
+			u32 val;
+
+			if (unlikely(type > RTAX_MAX))
+				goto err;
+			if (type == RTAX_CC_ALGO) {
+				char tmp[TCP_CA_NAME_MAX];
+
+				nla_strlcpy(tmp, nla, sizeof(tmp));
+				val = tcp_ca_get_key_by_name(tmp);
+				if (val == TCP_CA_UNSPEC)
+					goto err;
+			} else {
+				val = nla_get_u32(nla);
+			}
+
+			mp[type - 1] = val;
+			__set_bit(type - 1, mxc->mx_valid);
+		}
+	}
+
+	mxc->mx = mp;
+
+	return 0;
+ err:
+	kfree(mp);
+	return -EINVAL;
+}
 
 int ip6_route_add(struct fib6_config *cfg)
 {
@@ -1470,6 +1523,7 @@ int ip6_route_add(struct fib6_config *cfg)
 	struct net_device *dev = NULL;
 	struct inet6_dev *idev = NULL;
 	struct fib6_table *table;
+	struct mx6_config mxc = { .mx = NULL, };
 	int addr_type;
 
 	if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128)
@@ -1665,8 +1719,14 @@ install_route:
 
 	cfg->fc_nlinfo.nl_net = dev_net(dev);
 
-	return __ip6_ins_rt(rt, &cfg->fc_nlinfo, cfg->fc_mx, cfg->fc_mx_len);
+	err = ip6_convert_metrics(&mxc, cfg);
+	if (err)
+		goto out;
+
+	err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, &mxc);
 
+	kfree(mxc.mx);
+	return err;
 out:
 	if (dev)
 		dev_put(dev);
@@ -2185,9 +2245,10 @@ int ip6_route_get_saddr(struct net *net,
 			unsigned int prefs,
 			struct in6_addr *saddr)
 {
-	struct inet6_dev *idev = ip6_dst_idev((struct dst_entry *)rt);
+	struct inet6_dev *idev =
+		rt ? ip6_dst_idev((struct dst_entry *)rt) : NULL;
 	int err = 0;
-	if (rt->rt6i_prefsrc.plen)
+	if (rt && rt->rt6i_prefsrc.plen)
 		*saddr = rt->rt6i_prefsrc.addr;
 	else
 		err = ipv6_dev_get_saddr(net, idev ? idev->dev : NULL,
@@ -2338,6 +2399,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
 	[RTA_PRIORITY]          = { .type = NLA_U32 },
 	[RTA_METRICS]           = { .type = NLA_NESTED },
 	[RTA_MULTIPATH]		= { .len = sizeof(struct rtnexthop) },
+	[RTA_PREF]              = { .type = NLA_U8 },
 };
 
 static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -2345,6 +2407,7 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 {
 	struct rtmsg *rtm;
 	struct nlattr *tb[RTA_MAX+1];
+	unsigned int pref;
 	int err;
 
 	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy);
@@ -2376,7 +2439,7 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 	cfg->fc_nlinfo.nl_net = sock_net(skb->sk);
 
 	if (tb[RTA_GATEWAY]) {
-		nla_memcpy(&cfg->fc_gateway, tb[RTA_GATEWAY], 16);
+		cfg->fc_gateway = nla_get_in6_addr(tb[RTA_GATEWAY]);
 		cfg->fc_flags |= RTF_GATEWAY;
 	}
 
@@ -2399,7 +2462,7 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 	}
 
 	if (tb[RTA_PREFSRC])
-		nla_memcpy(&cfg->fc_prefsrc, tb[RTA_PREFSRC], 16);
+		cfg->fc_prefsrc = nla_get_in6_addr(tb[RTA_PREFSRC]);
 
 	if (tb[RTA_OIF])
 		cfg->fc_ifindex = nla_get_u32(tb[RTA_OIF]);
@@ -2420,6 +2483,14 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 		cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]);
 	}
 
+	if (tb[RTA_PREF]) {
+		pref = nla_get_u8(tb[RTA_PREF]);
+		if (pref != ICMPV6_ROUTER_PREF_LOW &&
+		    pref != ICMPV6_ROUTER_PREF_HIGH)
+			pref = ICMPV6_ROUTER_PREF_MEDIUM;
+		cfg->fc_flags |= RTF_PREF(pref);
+	}
+
 	err = 0;
 errout:
 	return err;
@@ -2433,9 +2504,9 @@ static int ip6_route_multipath(struct fib6_config *cfg, int add)
 	int attrlen;
 	int err = 0, last_err = 0;
 
+	remaining = cfg->fc_mp_len;
 beginning:
 	rtnh = (struct rtnexthop *)cfg->fc_mp;
-	remaining = cfg->fc_mp_len;
 
 	/* Parse a Multipath Entry */
 	while (rtnh_ok(rtnh, remaining)) {
@@ -2449,7 +2520,7 @@ beginning:
 
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
 			if (nla) {
-				nla_memcpy(&r_cfg.fc_gateway, nla, 16);
+				r_cfg.fc_gateway = nla_get_in6_addr(nla);
 				r_cfg.fc_flags |= RTF_GATEWAY;
 			}
 		}
@@ -2465,15 +2536,19 @@ beginning:
 				 * next hops that have been already added.
 				 */
 				add = 0;
+				remaining = cfg->fc_mp_len - remaining;
 				goto beginning;
 			}
 		}
 		/* Because each route is added like a single route we remove
-		 * this flag after the first nexthop (if there is a collision,
-		 * we have already fail to add the first nexthop:
-		 * fib6_add_rt2node() has reject it).
+		 * these flags after the first nexthop: if there is a collision,
+		 * we have already failed to add the first nexthop:
+		 * fib6_add_rt2node() has rejected it; when replacing, old
+		 * nexthops have been replaced by first new, the rest should
+		 * be added to it.
 		 */
-		cfg->fc_nlinfo.nlh->nlmsg_flags &= ~NLM_F_EXCL;
+		cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL |
+						     NLM_F_REPLACE);
 		rtnh = rtnh_next(rtnh, &remaining);
 	}
 
@@ -2522,7 +2597,9 @@ static inline size_t rt6_nlmsg_size(void)
 	       + nla_total_size(4) /* RTA_OIF */
 	       + nla_total_size(4) /* RTA_PRIORITY */
 	       + RTAX_MAX * nla_total_size(4) /* RTA_METRICS */
-	       + nla_total_size(sizeof(struct rta_cacheinfo));
+	       + nla_total_size(sizeof(struct rta_cacheinfo))
+	       + nla_total_size(TCP_CA_NAME_MAX) /* RTAX_CC_ALGO */
+	       + nla_total_size(1); /* RTA_PREF */
 }
 
 static int rt6_fill_node(struct net *net,
@@ -2597,19 +2674,19 @@ static int rt6_fill_node(struct net *net,
 		rtm->rtm_flags |= RTM_F_CLONED;
 
 	if (dst) {
-		if (nla_put(skb, RTA_DST, 16, dst))
+		if (nla_put_in6_addr(skb, RTA_DST, dst))
 			goto nla_put_failure;
 		rtm->rtm_dst_len = 128;
 	} else if (rtm->rtm_dst_len)
-		if (nla_put(skb, RTA_DST, 16, &rt->rt6i_dst.addr))
+		if (nla_put_in6_addr(skb, RTA_DST, &rt->rt6i_dst.addr))
 			goto nla_put_failure;
 #ifdef CONFIG_IPV6_SUBTREES
 	if (src) {
-		if (nla_put(skb, RTA_SRC, 16, src))
+		if (nla_put_in6_addr(skb, RTA_SRC, src))
 			goto nla_put_failure;
 		rtm->rtm_src_len = 128;
 	} else if (rtm->rtm_src_len &&
-		   nla_put(skb, RTA_SRC, 16, &rt->rt6i_src.addr))
+		   nla_put_in6_addr(skb, RTA_SRC, &rt->rt6i_src.addr))
 		goto nla_put_failure;
 #endif
 	if (iif) {
@@ -2633,14 +2710,14 @@ static int rt6_fill_node(struct net *net,
 	} else if (dst) {
 		struct in6_addr saddr_buf;
 		if (ip6_route_get_saddr(net, rt, dst, 0, &saddr_buf) == 0 &&
-		    nla_put(skb, RTA_PREFSRC, 16, &saddr_buf))
+		    nla_put_in6_addr(skb, RTA_PREFSRC, &saddr_buf))
 			goto nla_put_failure;
 	}
 
 	if (rt->rt6i_prefsrc.plen) {
 		struct in6_addr saddr_buf;
 		saddr_buf = rt->rt6i_prefsrc.addr;
-		if (nla_put(skb, RTA_PREFSRC, 16, &saddr_buf))
+		if (nla_put_in6_addr(skb, RTA_PREFSRC, &saddr_buf))
 			goto nla_put_failure;
 	}
 
@@ -2648,7 +2725,7 @@ static int rt6_fill_node(struct net *net,
 		goto nla_put_failure;
 
 	if (rt->rt6i_flags & RTF_GATEWAY) {
-		if (nla_put(skb, RTA_GATEWAY, 16, &rt->rt6i_gateway) < 0)
+		if (nla_put_in6_addr(skb, RTA_GATEWAY, &rt->rt6i_gateway) < 0)
 			goto nla_put_failure;
 	}
 
@@ -2663,7 +2740,11 @@ static int rt6_fill_node(struct net *net,
 	if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, rt->dst.error) < 0)
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->rt6i_flags)))
+		goto nla_put_failure;
+
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index a24557a1c1d8..ac35a28599be 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -118,7 +118,7 @@ static struct ip_tunnel *ipip6_tunnel_lookup(struct net *net,
 			return t;
 	}
 	t = rcu_dereference(sitn->tunnels_wc[0]);
-	if ((t != NULL) && (t->dev->flags & IFF_UP))
+	if (t && (t->dev->flags & IFF_UP))
 		return t;
 	return NULL;
 }
@@ -251,7 +251,7 @@ static struct ip_tunnel *ipip6_tunnel_locate(struct net *net,
 
 	dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN,
 			   ipip6_tunnel_setup);
-	if (dev == NULL)
+	if (!dev)
 		return NULL;
 
 	dev_net_set(dev, net);
@@ -555,7 +555,7 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
 				skb->dev,
 				iph->daddr,
 				iph->saddr);
-	if (t == NULL)
+	if (!t)
 		goto out;
 
 	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
@@ -671,7 +671,7 @@ 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) {
+	if (tunnel) {
 		struct pcpu_sw_netstats *tstats;
 
 		if (tunnel->parms.iph.protocol != IPPROTO_IPV6 &&
@@ -733,7 +733,7 @@ static int ipip_rcv(struct sk_buff *skb)
 	iph = ip_hdr(skb);
 	tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev,
 				     iph->saddr, iph->daddr);
-	if (tunnel != NULL) {
+	if (tunnel) {
 		if (tunnel->parms.iph.protocol != IPPROTO_IPIP &&
 		    tunnel->parms.iph.protocol != 0)
 			goto drop;
@@ -838,7 +838,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		if (skb_dst(skb))
 			neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr);
 
-		if (neigh == NULL) {
+		if (!neigh) {
 			net_dbg_ratelimited("nexthop == NULL\n");
 			goto tx_error;
 		}
@@ -867,7 +867,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		if (skb_dst(skb))
 			neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr);
 
-		if (neigh == NULL) {
+		if (!neigh) {
 			net_dbg_ratelimited("nexthop == NULL\n");
 			goto tx_error;
 		}
@@ -983,7 +983,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 
 	skb_set_inner_ipproto(skb, IPPROTO_IPV6);
 
-	err = iptunnel_xmit(skb->sk, rt, skb, fl4.saddr, fl4.daddr,
+	err = iptunnel_xmit(NULL, 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);
@@ -1076,7 +1076,6 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev)
 		if (dev->mtu < IPV6_MIN_MTU)
 			dev->mtu = IPV6_MIN_MTU;
 	}
-	dev->iflink = tunnel->parms.link;
 }
 
 static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p)
@@ -1158,7 +1157,7 @@ ipip6_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 				break;
 			}
 			t = ipip6_tunnel_locate(net, &p, 0);
-			if (t == NULL)
+			if (!t)
 				t = netdev_priv(dev);
 		}
 
@@ -1206,7 +1205,7 @@ ipip6_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		t = ipip6_tunnel_locate(net, &p, cmd == SIOCADDTUNNEL);
 
 		if (dev != sitn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
-			if (t != NULL) {
+			if (t) {
 				if (t->dev != dev) {
 					err = -EEXIST;
 					break;
@@ -1241,7 +1240,8 @@ ipip6_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
 				goto done;
 			err = -ENOENT;
-			if ((t = ipip6_tunnel_locate(net, &p, 0)) == NULL)
+			t = ipip6_tunnel_locate(net, &p, 0);
+			if (!t)
 				goto done;
 			err = -EPERM;
 			if (t == netdev_priv(sitn->fb_tunnel_dev))
@@ -1335,6 +1335,7 @@ static const struct net_device_ops ipip6_netdev_ops = {
 	.ndo_do_ioctl	= ipip6_tunnel_ioctl,
 	.ndo_change_mtu	= ipip6_tunnel_change_mtu,
 	.ndo_get_stats64 = ip_tunnel_get_stats64,
+	.ndo_get_iflink = ip_tunnel_get_iflink,
 };
 
 static void ipip6_dev_free(struct net_device *dev)
@@ -1365,7 +1366,6 @@ static void ipip6_tunnel_setup(struct net_device *dev)
 	dev->mtu		= ETH_DATA_LEN - t_hlen;
 	dev->flags		= IFF_NOARP;
 	netif_keep_dst(dev);
-	dev->iflink		= 0;
 	dev->addr_len		= 4;
 	dev->features		|= NETIF_F_LLTX;
 	dev->features		|= SIT_FEATURES;
@@ -1505,12 +1505,12 @@ static bool ipip6_netlink_encap_parms(struct nlattr *data[],
 
 	if (data[IFLA_IPTUN_ENCAP_SPORT]) {
 		ret = true;
-		ipencap->sport = nla_get_u16(data[IFLA_IPTUN_ENCAP_SPORT]);
+		ipencap->sport = nla_get_be16(data[IFLA_IPTUN_ENCAP_SPORT]);
 	}
 
 	if (data[IFLA_IPTUN_ENCAP_DPORT]) {
 		ret = true;
-		ipencap->dport = nla_get_u16(data[IFLA_IPTUN_ENCAP_DPORT]);
+		ipencap->dport = nla_get_be16(data[IFLA_IPTUN_ENCAP_DPORT]);
 	}
 
 	return ret;
@@ -1529,8 +1529,7 @@ static bool ipip6_netlink_6rd_parms(struct nlattr *data[],
 
 	if (data[IFLA_IPTUN_6RD_PREFIX]) {
 		ret = true;
-		nla_memcpy(&ip6rd->prefix, data[IFLA_IPTUN_6RD_PREFIX],
-			   sizeof(struct in6_addr));
+		ip6rd->prefix = nla_get_in6_addr(data[IFLA_IPTUN_6RD_PREFIX]);
 	}
 
 	if (data[IFLA_IPTUN_6RD_RELAY_PREFIX]) {
@@ -1682,8 +1681,8 @@ static int ipip6_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	struct ip_tunnel_parm *parm = &tunnel->parms;
 
 	if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) ||
-	    nla_put_be32(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) ||
-	    nla_put_be32(skb, IFLA_IPTUN_REMOTE, parm->iph.daddr) ||
+	    nla_put_in_addr(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) ||
+	    nla_put_in_addr(skb, IFLA_IPTUN_REMOTE, parm->iph.daddr) ||
 	    nla_put_u8(skb, IFLA_IPTUN_TTL, parm->iph.ttl) ||
 	    nla_put_u8(skb, IFLA_IPTUN_TOS, parm->iph.tos) ||
 	    nla_put_u8(skb, IFLA_IPTUN_PMTUDISC,
@@ -1693,10 +1692,10 @@ static int ipip6_fill_info(struct sk_buff *skb, const struct net_device *dev)
 		goto nla_put_failure;
 
 #ifdef CONFIG_IPV6_SIT_6RD
-	if (nla_put(skb, IFLA_IPTUN_6RD_PREFIX, sizeof(struct in6_addr),
-		    &tunnel->ip6rd.prefix) ||
-	    nla_put_be32(skb, IFLA_IPTUN_6RD_RELAY_PREFIX,
-			 tunnel->ip6rd.relay_prefix) ||
+	if (nla_put_in6_addr(skb, IFLA_IPTUN_6RD_PREFIX,
+			     &tunnel->ip6rd.prefix) ||
+	    nla_put_in_addr(skb, IFLA_IPTUN_6RD_RELAY_PREFIX,
+			    tunnel->ip6rd.relay_prefix) ||
 	    nla_put_u16(skb, IFLA_IPTUN_6RD_PREFIXLEN,
 			tunnel->ip6rd.prefixlen) ||
 	    nla_put_u16(skb, IFLA_IPTUN_6RD_RELAY_PREFIXLEN,
@@ -1706,12 +1705,12 @@ static int ipip6_fill_info(struct sk_buff *skb, const struct net_device *dev)
 
 	if (nla_put_u16(skb, IFLA_IPTUN_ENCAP_TYPE,
 			tunnel->encap.type) ||
-	    nla_put_u16(skb, IFLA_IPTUN_ENCAP_SPORT,
+	    nla_put_be16(skb, IFLA_IPTUN_ENCAP_SPORT,
 			tunnel->encap.sport) ||
-	    nla_put_u16(skb, IFLA_IPTUN_ENCAP_DPORT,
+	    nla_put_be16(skb, IFLA_IPTUN_ENCAP_DPORT,
 			tunnel->encap.dport) ||
 	    nla_put_u16(skb, IFLA_IPTUN_ENCAP_FLAGS,
-			tunnel->encap.dport))
+			tunnel->encap.flags))
 		goto nla_put_failure;
 
 	return 0;
@@ -1762,6 +1761,7 @@ static struct rtnl_link_ops sit_link_ops __read_mostly = {
 	.get_size	= ipip6_get_size,
 	.fill_info	= ipip6_fill_info,
 	.dellink	= ipip6_dellink,
+	.get_link_net	= ip_tunnel_get_link_net,
 };
 
 static struct xfrm_tunnel sit_handler __read_mostly = {
@@ -1793,7 +1793,7 @@ static void __net_exit sit_destroy_tunnels(struct net *net,
 			struct ip_tunnel *t;
 
 			t = rtnl_dereference(sitn->tunnels[prio][h]);
-			while (t != NULL) {
+			while (t) {
 				/* If dev is in the same netns, it has already
 				 * been added to the list by the previous loop.
 				 */
@@ -1836,8 +1836,8 @@ static int __net_init sit_init_net(struct net *net)
 		goto err_dev_free;
 
 	ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn);
-
-	if ((err = register_netdev(sitn->fb_tunnel_dev)))
+	err = register_netdev(sitn->fb_tunnel_dev);
+	if (err)
 		goto err_reg_dev;
 
 	t = netdev_priv(sitn->fb_tunnel_dev);
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 2f25cb6347ca..21bc2eb53c57 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -49,11 +49,12 @@ static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 	struct sock *child;
 
 	child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst);
-	if (child)
+	if (child) {
+		atomic_set(&req->rsk_refcnt, 1);
 		inet_csk_reqsk_queue_add(sk, req, child);
-	else
+	} else {
 		reqsk_free(req);
-
+	}
 	return child;
 }
 
@@ -166,13 +167,15 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	int mss;
 	struct dst_entry *dst;
 	__u8 rcv_wscale;
-	bool ecn_ok = false;
 
 	if (!sysctl_tcp_syncookies || !th->ack || th->rst)
 		goto out;
 
-	if (tcp_synq_no_recent_overflow(sk) ||
-		(mss = __cookie_v6_check(ipv6_hdr(skb), th, cookie)) == 0) {
+	if (tcp_synq_no_recent_overflow(sk))
+		goto out;
+
+	mss = __cookie_v6_check(ipv6_hdr(skb), th, cookie);
+	if (mss == 0) {
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESFAILED);
 		goto out;
 	}
@@ -183,17 +186,17 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	memset(&tcp_opt, 0, sizeof(tcp_opt));
 	tcp_parse_options(skb, &tcp_opt, 0, NULL);
 
-	if (!cookie_check_timestamp(&tcp_opt, sock_net(sk), &ecn_ok))
+	if (!cookie_timestamp_decode(&tcp_opt))
 		goto out;
 
 	ret = NULL;
-	req = inet_reqsk_alloc(&tcp6_request_sock_ops);
+	req = inet_reqsk_alloc(&tcp6_request_sock_ops, sk);
 	if (!req)
 		goto out;
 
 	ireq = inet_rsk(req);
 	treq = tcp_rsk(req);
-	treq->listener = NULL;
+	treq->tfo_listener = false;
 
 	if (security_inet_conn_request(sk, skb, req))
 		goto out_free;
@@ -218,9 +221,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 
 	ireq->ir_mark = inet_request_mark(sk, skb);
 
-	req->expires = 0UL;
 	req->num_retrans = 0;
-	ireq->ecn_ok		= ecn_ok;
 	ireq->snd_wscale	= tcp_opt.snd_wscale;
 	ireq->sack_ok		= tcp_opt.sack_ok;
 	ireq->wscale_ok		= tcp_opt.wscale_ok;
@@ -261,6 +262,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 				  dst_metric(dst, RTAX_INITRWND));
 
 	ireq->rcv_wscale = rcv_wscale;
+	ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, sock_net(sk), dst);
 
 	ret = get_cookie_sock(sk, skb, req, dst);
 out:
@@ -269,4 +271,3 @@ out_free:
 	reqsk_free(req);
 	return NULL;
 }
-
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index c5c10fafcfe2..abcc79f649b3 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -54,6 +54,20 @@ static struct ctl_table ipv6_table_template[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "idgen_retries",
+		.data		= &init_net.ipv6.sysctl.idgen_retries,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "idgen_delay",
+		.data		= &init_net.ipv6.sysctl.idgen_delay,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
 	{ }
 };
 
@@ -93,6 +107,8 @@ static int __net_init ipv6_sysctl_net_init(struct net *net)
 	ipv6_table[2].data = &net->ipv6.sysctl.flowlabel_consistency;
 	ipv6_table[3].data = &net->ipv6.sysctl.auto_flowlabels;
 	ipv6_table[4].data = &net->ipv6.sysctl.fwmark_reflect;
+	ipv6_table[5].data = &net->ipv6.sysctl.idgen_retries;
+	ipv6_table[6].data = &net->ipv6.sysctl.idgen_delay;
 
 	ipv6_route_table = ipv6_route_sysctl_init(net);
 	if (!ipv6_route_table)
@@ -163,7 +179,7 @@ int ipv6_sysctl_register(void)
 	int err = -ENOMEM;
 
 	ip6_header = register_net_sysctl(&init_net, "net/ipv6", ipv6_rotable);
-	if (ip6_header == NULL)
+	if (!ip6_header)
 		goto out;
 
 	err = register_pernet_subsys(&ipv6_sysctl_net_ops);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index ace29b60813c..3adffb300238 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -104,19 +104,6 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 	}
 }
 
-static void tcp_v6_hash(struct sock *sk)
-{
-	if (sk->sk_state != TCP_CLOSE) {
-		if (inet_csk(sk)->icsk_af_ops == &ipv6_mapped) {
-			tcp_prot.hash(sk);
-			return;
-		}
-		local_bh_disable();
-		__inet6_hash(sk, NULL);
-		local_bh_enable();
-	}
-}
-
 static __u32 tcp_v6_init_sequence(const struct sk_buff *skb)
 {
 	return secure_tcpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32,
@@ -154,7 +141,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 		if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) {
 			struct ip6_flowlabel *flowlabel;
 			flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
-			if (flowlabel == NULL)
+			if (!flowlabel)
 				return -EINVAL;
 			fl6_sock_release(flowlabel);
 		}
@@ -233,11 +220,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 			tp->af_specific = &tcp_sock_ipv6_specific;
 #endif
 			goto failure;
-		} else {
-			ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr);
-			ipv6_addr_set_v4mapped(inet->inet_rcv_saddr,
-					       &sk->sk_v6_rcv_saddr);
 		}
+		np->saddr = sk->sk_v6_rcv_saddr;
 
 		return err;
 	}
@@ -263,7 +247,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 		goto failure;
 	}
 
-	if (saddr == NULL) {
+	if (!saddr) {
 		saddr = &fl6.saddr;
 		sk->sk_v6_rcv_saddr = *saddr;
 	}
@@ -340,18 +324,20 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 {
 	const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
 	const struct tcphdr *th = (struct tcphdr *)(skb->data+offset);
+	struct net *net = dev_net(skb->dev);
+	struct request_sock *fastopen;
 	struct ipv6_pinfo *np;
-	struct sock *sk;
-	int err;
 	struct tcp_sock *tp;
-	struct request_sock *fastopen;
 	__u32 seq, snd_una;
-	struct net *net = dev_net(skb->dev);
+	struct sock *sk;
+	int err;
 
-	sk = inet6_lookup(net, &tcp_hashinfo, &hdr->daddr,
-			th->dest, &hdr->saddr, th->source, skb->dev->ifindex);
+	sk = __inet6_lookup_established(net, &tcp_hashinfo,
+					&hdr->daddr, th->dest,
+					&hdr->saddr, ntohs(th->source),
+					skb->dev->ifindex);
 
-	if (sk == NULL) {
+	if (!sk) {
 		ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev),
 				   ICMP6_MIB_INERRORS);
 		return;
@@ -361,6 +347,9 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		inet_twsk_put(inet_twsk(sk));
 		return;
 	}
+	seq = ntohl(th->seq);
+	if (sk->sk_state == TCP_NEW_SYN_RECV)
+		return tcp_req_err(sk, seq);
 
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG)
@@ -375,7 +364,6 @@ 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;
@@ -419,37 +407,12 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 	/* Might be for an request_sock */
 	switch (sk->sk_state) {
-		struct request_sock *req, **prev;
-	case TCP_LISTEN:
-		if (sock_owned_by_user(sk))
-			goto out;
-
-		/* Note : We use inet6_iif() here, not tcp_v6_iif() */
-		req = inet6_csk_search_req(sk, &prev, th->dest, &hdr->daddr,
-					   &hdr->saddr, inet6_iif(skb));
-		if (!req)
-			goto out;
-
-		/* ICMPs are not backlogged, hence we cannot get
-		 * an established socket here.
-		 */
-		WARN_ON(req->sk != NULL);
-
-		if (seq != tcp_rsk(req)->snt_isn) {
-			NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
-			goto out;
-		}
-
-		inet_csk_reqsk_queue_drop(sk, req, prev);
-		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
-		goto out;
-
 	case TCP_SYN_SENT:
 	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)
+		if (fastopen && !fastopen->sk)
 			break;
 
 		if (!sock_owned_by_user(sk)) {
@@ -497,7 +460,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst,
 				    &ireq->ir_v6_rmt_addr);
 
 		fl6->daddr = ireq->ir_v6_rmt_addr;
-		if (np->repflow && (ireq->pktopts != NULL))
+		if (np->repflow && ireq->pktopts)
 			fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
 
 		skb_set_queue_mapping(skb, queue_mapping);
@@ -523,17 +486,11 @@ static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk,
 }
 
 static struct tcp_md5sig_key *tcp_v6_md5_lookup(struct sock *sk,
-						struct sock *addr_sk)
+						const struct sock *addr_sk)
 {
 	return tcp_v6_md5_do_lookup(sk, &addr_sk->sk_v6_daddr);
 }
 
-static struct tcp_md5sig_key *tcp_v6_reqsk_md5_lookup(struct sock *sk,
-						      struct request_sock *req)
-{
-	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)
 {
@@ -619,9 +576,9 @@ clear_hash_noput:
 	return 1;
 }
 
-static int tcp_v6_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key,
+static int tcp_v6_md5_hash_skb(char *md5_hash,
+			       const struct tcp_md5sig_key *key,
 			       const struct sock *sk,
-			       const struct request_sock *req,
 			       const struct sk_buff *skb)
 {
 	const struct in6_addr *saddr, *daddr;
@@ -629,12 +586,9 @@ static int tcp_v6_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key,
 	struct hash_desc *desc;
 	const struct tcphdr *th = tcp_hdr(skb);
 
-	if (sk) {
-		saddr = &inet6_sk(sk)->saddr;
+	if (sk) { /* valid for establish/request sockets */
+		saddr = &sk->sk_v6_rcv_saddr;
 		daddr = &sk->sk_v6_daddr;
-	} else if (req) {
-		saddr = &inet_rsk(req)->ir_v6_loc_addr;
-		daddr = &inet_rsk(req)->ir_v6_rmt_addr;
 	} else {
 		const struct ipv6hdr *ip6h = ipv6_hdr(skb);
 		saddr = &ip6h->saddr;
@@ -670,8 +624,7 @@ clear_hash_noput:
 	return 1;
 }
 
-static int __tcp_v6_inbound_md5_hash(struct sock *sk,
-				     const struct sk_buff *skb)
+static bool tcp_v6_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb)
 {
 	const __u8 *hash_location = NULL;
 	struct tcp_md5sig_key *hash_expected;
@@ -685,44 +638,32 @@ static int __tcp_v6_inbound_md5_hash(struct sock *sk,
 
 	/* We've parsed the options - do we have a hash? */
 	if (!hash_expected && !hash_location)
-		return 0;
+		return false;
 
 	if (hash_expected && !hash_location) {
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND);
-		return 1;
+		return true;
 	}
 
 	if (!hash_expected && hash_location) {
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED);
-		return 1;
+		return true;
 	}
 
 	/* check the signature */
 	genhash = tcp_v6_md5_hash_skb(newhash,
 				      hash_expected,
-				      NULL, NULL, skb);
+				      NULL, skb);
 
 	if (genhash || memcmp(hash_location, newhash, 16) != 0) {
 		net_info_ratelimited("MD5 Hash %s for [%pI6c]:%u->[%pI6c]:%u\n",
 				     genhash ? "failed" : "mismatch",
 				     &ip6h->saddr, ntohs(th->source),
 				     &ip6h->daddr, ntohs(th->dest));
-		return 1;
+		return true;
 	}
-	return 0;
+	return false;
 }
-
-static int tcp_v6_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb)
-{
-	int ret;
-
-	rcu_read_lock();
-	ret = __tcp_v6_inbound_md5_hash(sk, skb);
-	rcu_read_unlock();
-
-	return ret;
-}
-
 #endif
 
 static void tcp_v6_init_req(struct request_sock *req, struct sock *sk,
@@ -734,8 +675,6 @@ static void tcp_v6_init_req(struct request_sock *req, struct sock *sk,
 	ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
 	ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
 
-	ireq->ir_iif = sk->sk_bound_dev_if;
-
 	/* So that link locals have meaning */
 	if (!sk->sk_bound_dev_if &&
 	    ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
@@ -774,7 +713,7 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
 	.mss_clamp	=	IPV6_MIN_MTU - sizeof(struct tcphdr) -
 				sizeof(struct ipv6hdr),
 #ifdef CONFIG_TCP_MD5SIG
-	.md5_lookup	=	tcp_v6_reqsk_md5_lookup,
+	.req_md5_lookup	=	tcp_v6_md5_lookup,
 	.calc_md5_hash	=	tcp_v6_md5_hash_skb,
 #endif
 	.init_req	=	tcp_v6_init_req,
@@ -787,16 +726,16 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
 	.queue_hash_add =	inet6_csk_reqsk_queue_hash_add,
 };
 
-static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
-				 u32 tsval, u32 tsecr, int oif,
-				 struct tcp_md5sig_key *key, int rst, u8 tclass,
-				 u32 label)
+static void tcp_v6_send_response(struct sock *sk, struct sk_buff *skb, u32 seq,
+				 u32 ack, u32 win, 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;
 	struct sk_buff *buff;
 	struct flowi6 fl6;
-	struct net *net = dev_net(skb_dst(skb)->dev);
+	struct net *net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev);
 	struct sock *ctl_sk = net->ipv6.tcp_sk;
 	unsigned int tot_len = sizeof(struct tcphdr);
 	struct dst_entry *dst;
@@ -811,7 +750,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
 
 	buff = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + tot_len,
 			 GFP_ATOMIC);
-	if (buff == NULL)
+	if (!buff)
 		return;
 
 	skb_reserve(buff, MAX_HEADER + sizeof(struct ipv6hdr) + tot_len);
@@ -903,7 +842,10 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb)
 	if (th->rst)
 		return;
 
-	if (!ipv6_unicast_destination(skb))
+	/* If sk not NULL, it means we did a successful lookup and incoming
+	 * route had to be correct. prequeue might have dropped our dst.
+	 */
+	if (!sk && !ipv6_unicast_destination(skb))
 		return;
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -928,7 +870,7 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb)
 		if (!key)
 			goto release_sk1;
 
-		genhash = tcp_v6_md5_hash_skb(newhash, key, NULL, NULL, skb);
+		genhash = tcp_v6_md5_hash_skb(newhash, key, NULL, skb);
 		if (genhash || memcmp(hash_location, newhash, 16) != 0)
 			goto release_sk1;
 	} else {
@@ -943,7 +885,7 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb)
 			  (th->doff << 2);
 
 	oif = sk ? sk->sk_bound_dev_if : 0;
-	tcp_v6_send_response(skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, 0);
+	tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, 0);
 
 #ifdef CONFIG_TCP_MD5SIG
 release_sk1:
@@ -954,13 +896,13 @@ release_sk1:
 #endif
 }
 
-static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
-			    u32 win, u32 tsval, u32 tsecr, int oif,
+static void tcp_v6_send_ack(struct sock *sk, struct sk_buff *skb, u32 seq,
+			    u32 ack, 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, oif, key, 0, tclass,
-			     label);
+	tcp_v6_send_response(sk, skb, seq, ack, win, tsval, tsecr, oif, key, 0,
+			     tclass, label);
 }
 
 static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
@@ -968,11 +910,11 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
 	struct inet_timewait_sock *tw = inet_twsk(sk);
 	struct tcp_timewait_sock *tcptw = tcp_twsk(sk);
 
-	tcp_v6_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
+	tcp_v6_send_ack(sk, 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, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw),
-			tw->tw_tclass, (tw->tw_flowlabel << 12));
+			tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel));
 
 	inet_twsk_put(tw);
 }
@@ -983,10 +925,10 @@ static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
 	/* 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_v6_send_ack(sk, 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_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);
 }
@@ -994,17 +936,20 @@ static void tcp_v6_reqsk_send_ack(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);
+	struct request_sock *req;
 	struct sock *nsk;
 
 	/* Find possible connection requests. */
-	req = inet6_csk_search_req(sk, &prev, th->source,
+	req = inet6_csk_search_req(sk, th->source,
 				   &ipv6_hdr(skb)->saddr,
 				   &ipv6_hdr(skb)->daddr, tcp_v6_iif(skb));
-	if (req)
-		return tcp_check_req(sk, skb, req, prev, false);
-
+	if (req) {
+		nsk = tcp_check_req(sk, skb, req, false);
+		if (!nsk)
+			reqsk_put(req);
+		return nsk;
+	}
 	nsk = __inet6_lookup_established(sock_net(sk), &tcp_hashinfo,
 					 &ipv6_hdr(skb)->saddr, th->source,
 					 &ipv6_hdr(skb)->daddr, ntohs(th->dest),
@@ -1064,7 +1009,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 
 		newsk = tcp_v4_syn_recv_sock(sk, skb, req, dst);
 
-		if (newsk == NULL)
+		if (!newsk)
 			return NULL;
 
 		newtcp6sk = (struct tcp6_sock *)newsk;
@@ -1076,11 +1021,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 
 		memcpy(newnp, np, sizeof(struct ipv6_pinfo));
 
-		ipv6_addr_set_v4mapped(newinet->inet_daddr, &newsk->sk_v6_daddr);
-
-		ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr);
-
-		newsk->sk_v6_rcv_saddr = newnp->saddr;
+		newnp->saddr = newsk->sk_v6_rcv_saddr;
 
 		inet_csk(newsk)->icsk_af_ops = &ipv6_mapped;
 		newsk->sk_backlog_rcv = tcp_v4_do_rcv;
@@ -1125,7 +1066,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	}
 
 	newsk = tcp_create_openreq_child(sk, req, skb);
-	if (newsk == NULL)
+	if (!newsk)
 		goto out_nonewsk;
 
 	/*
@@ -1167,7 +1108,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 
 	/* Clone pktoptions received with SYN */
 	newnp->pktoptions = NULL;
-	if (ireq->pktopts != NULL) {
+	if (ireq->pktopts) {
 		newnp->pktoptions = skb_clone(ireq->pktopts,
 					      sk_gfp_atomic(sk, GFP_ATOMIC));
 		consume_skb(ireq->pktopts);
@@ -1196,6 +1137,8 @@ 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_ca_openreq_child(newsk, dst);
+
 	tcp_sync_mss(newsk, dst_mtu(dst));
 	newtp->advmss = dst_metric_advmss(dst);
 	if (tcp_sk(sk)->rx_opt.user_mss &&
@@ -1210,7 +1153,7 @@ 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 */
 	key = tcp_v6_md5_do_lookup(sk, &newsk->sk_v6_daddr);
-	if (key != NULL) {
+	if (key) {
 		/* 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
@@ -1227,7 +1170,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 		tcp_done(newsk);
 		goto out;
 	}
-	__inet6_hash(newsk, NULL);
+	__inet_hash(newsk, NULL);
 
 	return newsk;
 
@@ -1293,6 +1236,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
 		struct dst_entry *dst = sk->sk_rx_dst;
 
 		sock_rps_save_rxhash(sk, skb);
+		sk_mark_napi_id(sk, skb);
 		if (dst) {
 			if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif ||
 			    dst->ops->check(dst, np->rx_dst_cookie) == NULL) {
@@ -1322,6 +1266,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
 		 */
 		if (nsk != sk) {
 			sock_rps_save_rxhash(nsk, skb);
+			sk_mark_napi_id(sk, skb);
 			if (tcp_child_process(sk, nsk, skb))
 				goto reset;
 			if (opt_skb)
@@ -1382,6 +1327,37 @@ ipv6_pktoptions:
 	return 0;
 }
 
+static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr,
+			   const struct tcphdr *th)
+{
+	/* This is tricky: we move IP6CB at its correct location into
+	 * TCP_SKB_CB(). It must be done after xfrm6_policy_check(), because
+	 * _decode_session6() uses IP6CB().
+	 * barrier() makes sure compiler won't play aliasing games.
+	 */
+	memmove(&TCP_SKB_CB(skb)->header.h6, IP6CB(skb),
+		sizeof(struct inet6_skb_parm));
+	barrier();
+
+	TCP_SKB_CB(skb)->seq = ntohl(th->seq);
+	TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
+				    skb->len - th->doff*4);
+	TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
+	TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
+	TCP_SKB_CB(skb)->tcp_tw_isn = 0;
+	TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr);
+	TCP_SKB_CB(skb)->sacked = 0;
+}
+
+static void tcp_v6_restore_cb(struct sk_buff *skb)
+{
+	/* We need to move header back to the beginning if xfrm6_policy_check()
+	 * and tcp_v6_fill_cb() are going to be called again.
+	 */
+	memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6,
+		sizeof(struct inet6_skb_parm));
+}
+
 static int tcp_v6_rcv(struct sk_buff *skb)
 {
 	const struct tcphdr *th;
@@ -1413,24 +1389,9 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 
 	th = tcp_hdr(skb);
 	hdr = ipv6_hdr(skb);
-	/* This is tricky : We move IPCB at its correct location into TCP_SKB_CB()
-	 * barrier() makes sure compiler wont play fool^Waliasing games.
-	 */
-	memmove(&TCP_SKB_CB(skb)->header.h6, IP6CB(skb),
-		sizeof(struct inet6_skb_parm));
-	barrier();
-
-	TCP_SKB_CB(skb)->seq = ntohl(th->seq);
-	TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
-				    skb->len - th->doff*4);
-	TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
-	TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
-	TCP_SKB_CB(skb)->tcp_tw_isn = 0;
-	TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr);
-	TCP_SKB_CB(skb)->sacked = 0;
 
 	sk = __inet6_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest,
-				tcp_v6_iif(skb));
+				inet6_iif(skb));
 	if (!sk)
 		goto no_tcp_socket;
 
@@ -1446,6 +1407,8 @@ process:
 	if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
 		goto discard_and_relse;
 
+	tcp_v6_fill_cb(skb, hdr, th);
+
 #ifdef CONFIG_TCP_MD5SIG
 	if (tcp_v6_inbound_md5_hash(sk, skb))
 		goto discard_and_relse;
@@ -1454,7 +1417,7 @@ process:
 	if (sk_filter(sk, skb))
 		goto discard_and_relse;
 
-	sk_mark_napi_id(sk, skb);
+	sk_incoming_cpu_update(sk);
 	skb->dev = NULL;
 
 	bh_lock_sock_nested(sk);
@@ -1477,6 +1440,8 @@ no_tcp_socket:
 	if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
 		goto discard_it;
 
+	tcp_v6_fill_cb(skb, hdr, th);
+
 	if (skb->len < (th->doff<<2) || tcp_checksum_complete(skb)) {
 csum_error:
 		TCP_INC_STATS_BH(net, TCP_MIB_CSUMERRORS);
@@ -1500,6 +1465,8 @@ do_time_wait:
 		goto discard_it;
 	}
 
+	tcp_v6_fill_cb(skb, hdr, th);
+
 	if (skb->len < (th->doff<<2)) {
 		inet_twsk_put(inet_twsk(sk));
 		goto bad_packet;
@@ -1518,11 +1485,12 @@ do_time_wait:
 					    &ipv6_hdr(skb)->saddr, th->source,
 					    &ipv6_hdr(skb)->daddr,
 					    ntohs(th->dest), tcp_v6_iif(skb));
-		if (sk2 != NULL) {
+		if (sk2) {
 			struct inet_timewait_sock *tw = inet_twsk(sk);
-			inet_twsk_deschedule(tw, &tcp_death_row);
+			inet_twsk_deschedule(tw);
 			inet_twsk_put(tw);
 			sk = sk2;
+			tcp_v6_restore_cb(skb);
 			goto process;
 		}
 		/* Fall through to ACK */
@@ -1531,6 +1499,7 @@ do_time_wait:
 		tcp_v6_timewait_ack(sk, skb);
 		break;
 	case TCP_TW_RST:
+		tcp_v6_restore_cb(skb);
 		goto no_tcp_socket;
 	case TCP_TW_SUCCESS:
 		;
@@ -1564,8 +1533,8 @@ static void tcp_v6_early_demux(struct sk_buff *skb)
 	if (sk) {
 		skb->sk = sk;
 		skb->destructor = sock_edemux;
-		if (sk->sk_state != TCP_TIME_WAIT) {
-			struct dst_entry *dst = sk->sk_rx_dst;
+		if (sk_fullsock(sk)) {
+			struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst);
 
 			if (dst)
 				dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie);
@@ -1669,9 +1638,9 @@ static void tcp_v6_destroy_sock(struct sock *sk)
 #ifdef CONFIG_PROC_FS
 /* Proc filesystem TCPv6 sock list dumping. */
 static void get_openreq6(struct seq_file *seq,
-			 const struct sock *sk, struct request_sock *req, int i, kuid_t uid)
+			 struct request_sock *req, int i, kuid_t uid)
 {
-	int ttd = req->expires - jiffies;
+	long ttd = req->rsk_timer.expires - jiffies;
 	const struct in6_addr *src = &inet_rsk(req)->ir_v6_loc_addr;
 	const struct in6_addr *dest = &inet_rsk(req)->ir_v6_rmt_addr;
 
@@ -1760,9 +1729,9 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 static void get_timewait6_sock(struct seq_file *seq,
 			       struct inet_timewait_sock *tw, int i)
 {
+	long delta = tw->tw_timer.expires - jiffies;
 	const struct in6_addr *dest, *src;
 	__u16 destp, srcp;
-	s32 delta = tw->tw_ttd - inet_tw_time_stamp();
 
 	dest = &tw->tw_v6_daddr;
 	src  = &tw->tw_v6_rcv_saddr;
@@ -1807,7 +1776,7 @@ static int tcp6_seq_show(struct seq_file *seq, void *v)
 			get_tcp6_sock(seq, v, st->num);
 		break;
 	case TCP_SEQ_STATE_OPENREQ:
-		get_openreq6(seq, st->syn_wait_sk, v, st->num, st->uid);
+		get_openreq6(seq, v, st->num, st->uid);
 		break;
 	}
 out:
@@ -1871,7 +1840,7 @@ struct proto tcpv6_prot = {
 	.sendpage		= tcp_sendpage,
 	.backlog_rcv		= tcp_v6_do_rcv,
 	.release_cb		= tcp_release_cb,
-	.hash			= tcp_v6_hash,
+	.hash			= inet_hash,
 	.unhash			= inet_unhash,
 	.get_port		= inet_csk_get_port,
 	.enter_memory_pressure	= tcp_enter_memory_pressure,
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index c1ab77105b4c..d883c9204c01 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -41,8 +41,8 @@ static int tcp6_gro_complete(struct sk_buff *skb, int thoff)
 	return tcp_gro_complete(skb);
 }
 
-struct sk_buff *tcp6_gso_segment(struct sk_buff *skb,
-				 netdev_features_t features)
+static struct sk_buff *tcp6_gso_segment(struct sk_buff *skb,
+					netdev_features_t features)
 {
 	struct tcphdr *th;
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index f6ba535b6feb..e51fc3eee6db 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -53,11 +53,11 @@
 #include <trace/events/skb.h>
 #include "udp_impl.h"
 
-static unsigned int udp6_ehashfn(struct net *net,
-				  const struct in6_addr *laddr,
-				  const u16 lport,
-				  const struct in6_addr *faddr,
-				  const __be16 fport)
+static u32 udp6_ehashfn(const struct net *net,
+			const struct in6_addr *laddr,
+			const u16 lport,
+			const struct in6_addr *faddr,
+			const __be16 fport)
 {
 	static u32 udp6_ehash_secret __read_mostly;
 	static u32 udp_ipv6_hash_secret __read_mostly;
@@ -104,9 +104,9 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2)
 	return 0;
 }
 
-static unsigned int udp6_portaddr_hash(struct net *net,
-				       const struct in6_addr *addr6,
-				       unsigned int port)
+static u32 udp6_portaddr_hash(const struct net *net,
+			      const struct in6_addr *addr6,
+			      unsigned int port)
 {
 	unsigned int hash, mix = net_hash_mix(net);
 
@@ -120,7 +120,6 @@ static unsigned int udp6_portaddr_hash(struct net *net,
 	return hash ^ port;
 }
 
-
 int udp_v6_get_port(struct sock *sk, unsigned short snum)
 {
 	unsigned int hash2_nulladdr =
@@ -148,72 +147,85 @@ static inline int compute_score(struct sock *sk, struct net *net,
 				const struct in6_addr *daddr, __be16 dport,
 				int dif)
 {
-	int score = -1;
+	int score;
+	struct inet_sock *inet;
 
-	if (net_eq(sock_net(sk), net) && udp_sk(sk)->udp_port_hash == hnum &&
-			sk->sk_family == PF_INET6) {
-		struct inet_sock *inet = inet_sk(sk);
+	if (!net_eq(sock_net(sk), net) ||
+	    udp_sk(sk)->udp_port_hash != hnum ||
+	    sk->sk_family != PF_INET6)
+		return -1;
 
-		score = 0;
-		if (inet->inet_dport) {
-			if (inet->inet_dport != sport)
-				return -1;
-			score++;
-		}
-		if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
-			if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
-				return -1;
-			score++;
-		}
-		if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
-			if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr))
-				return -1;
-			score++;
-		}
-		if (sk->sk_bound_dev_if) {
-			if (sk->sk_bound_dev_if != dif)
-				return -1;
-			score++;
-		}
+	score = 0;
+	inet = inet_sk(sk);
+
+	if (inet->inet_dport) {
+		if (inet->inet_dport != sport)
+			return -1;
+		score++;
 	}
+
+	if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
+		if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
+			return -1;
+		score++;
+	}
+
+	if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
+		if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr))
+			return -1;
+		score++;
+	}
+
+	if (sk->sk_bound_dev_if) {
+		if (sk->sk_bound_dev_if != dif)
+			return -1;
+		score++;
+	}
+
 	return score;
 }
 
 #define SCORE2_MAX (1 + 1 + 1)
 static inline int compute_score2(struct sock *sk, struct net *net,
-				const struct in6_addr *saddr, __be16 sport,
-				const struct in6_addr *daddr, unsigned short hnum,
-				int dif)
+				 const struct in6_addr *saddr, __be16 sport,
+				 const struct in6_addr *daddr,
+				 unsigned short hnum, int dif)
 {
-	int score = -1;
+	int score;
+	struct inet_sock *inet;
 
-	if (net_eq(sock_net(sk), net) && udp_sk(sk)->udp_port_hash == hnum &&
-			sk->sk_family == PF_INET6) {
-		struct inet_sock *inet = inet_sk(sk);
+	if (!net_eq(sock_net(sk), net) ||
+	    udp_sk(sk)->udp_port_hash != hnum ||
+	    sk->sk_family != PF_INET6)
+		return -1;
 
-		if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
+	if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
+		return -1;
+
+	score = 0;
+	inet = inet_sk(sk);
+
+	if (inet->inet_dport) {
+		if (inet->inet_dport != sport)
 			return -1;
-		score = 0;
-		if (inet->inet_dport) {
-			if (inet->inet_dport != sport)
-				return -1;
-			score++;
-		}
-		if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
-			if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr))
-				return -1;
-			score++;
-		}
-		if (sk->sk_bound_dev_if) {
-			if (sk->sk_bound_dev_if != dif)
-				return -1;
-			score++;
-		}
+		score++;
 	}
+
+	if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
+		if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr))
+			return -1;
+		score++;
+	}
+
+	if (sk->sk_bound_dev_if) {
+		if (sk->sk_bound_dev_if != dif)
+			return -1;
+		score++;
+	}
+
 	return score;
 }
 
-
 /* called with read_rcu_lock() */
 static struct sock *udp6_lib_lookup2(struct net *net,
 		const struct in6_addr *saddr, __be16 sport,
@@ -357,7 +369,8 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb,
 	struct sock *sk;
 	const struct ipv6hdr *iph = ipv6_hdr(skb);
 
-	if (unlikely(sk = skb_steal_sock(skb)))
+	sk = skb_steal_sock(skb);
+	if (unlikely(sk))
 		return sk;
 	return __udp6_lib_lookup(dev_net(skb_dst(skb)->dev), &iph->saddr, sport,
 				 &iph->daddr, dport, inet6_iif(skb),
@@ -371,14 +384,12 @@ struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be
 }
 EXPORT_SYMBOL_GPL(udp6_lib_lookup);
 
-
 /*
  *	This should be easy, if there is something there we
  *	return it, otherwise we block.
  */
 
-int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk,
-		  struct msghdr *msg, size_t len,
+int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		  int noblock, int flags, int *addr_len)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
@@ -424,10 +435,10 @@ try_again:
 	}
 
 	if (skb_csum_unnecessary(skb))
-		err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr),
-					      msg->msg_iov, copied);
+		err = skb_copy_datagram_msg(skb, sizeof(struct udphdr),
+					    msg, copied);
 	else {
-		err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov);
+		err = skb_copy_and_csum_datagram_msg(skb, sizeof(struct udphdr), msg);
 		if (err == -EINVAL)
 			goto csum_copy_err;
 	}
@@ -514,10 +525,8 @@ csum_copy_err:
 	}
 	unlock_sock_fast(sk, slow);
 
-	if (noblock)
-		return -EAGAIN;
-
-	/* starting over for a new packet */
+	/* starting over for a new packet, but check if we need to yield */
+	cond_resched();
 	msg->msg_flags &= ~MSG_TRUNC;
 	goto try_again;
 }
@@ -537,7 +546,7 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 	sk = __udp6_lib_lookup(net, daddr, uh->dest,
 			       saddr, uh->source, inet6_iif(skb), udptable);
-	if (sk == NULL) {
+	if (!sk) {
 		ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev),
 				   ICMP6_MIB_INERRORS);
 		return;
@@ -577,6 +586,7 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
 		sock_rps_save_rxhash(sk, skb);
 		sk_mark_napi_id(sk, skb);
+		sk_incoming_cpu_update(sk);
 	}
 
 	rc = sock_queue_rcv_skb(sk, skb);
@@ -634,7 +644,7 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 
 		/* if we're overly short, let UDP handle it */
 		encap_rcv = ACCESS_ONCE(up->encap_rcv);
-		if (skb->len > sizeof(struct udphdr) && encap_rcv != NULL) {
+		if (skb->len > sizeof(struct udphdr) && encap_rcv) {
 			int ret;
 
 			/* Verify checksum before giving to encap */
@@ -659,15 +669,13 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	if ((is_udplite & UDPLITE_RECV_CC)  &&  UDP_SKB_CB(skb)->partial_cov) {
 
 		if (up->pcrlen == 0) {          /* full coverage was set  */
-			LIMIT_NETDEBUG(KERN_WARNING "UDPLITE6: partial coverage"
-				" %d while full coverage %d requested\n",
-				UDP_SKB_CB(skb)->cscov, skb->len);
+			net_dbg_ratelimited("UDPLITE6: partial coverage %d while full coverage %d requested\n",
+					    UDP_SKB_CB(skb)->cscov, skb->len);
 			goto drop;
 		}
 		if (UDP_SKB_CB(skb)->cscov  <  up->pcrlen) {
-			LIMIT_NETDEBUG(KERN_WARNING "UDPLITE6: coverage %d "
-						    "too small, need min %d\n",
-				       UDP_SKB_CB(skb)->cscov, up->pcrlen);
+			net_dbg_ratelimited("UDPLITE6: coverage %d too small, need min %d\n",
+					    UDP_SKB_CB(skb)->cscov, up->pcrlen);
 			goto drop;
 		}
 	}
@@ -721,7 +729,9 @@ static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk,
 	    (inet->inet_dport && inet->inet_dport != rmt_port) ||
 	    (!ipv6_addr_any(&sk->sk_v6_daddr) &&
 		    !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) ||
-	    (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif))
+	    (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) ||
+	    (!ipv6_addr_any(&sk->sk_v6_rcv_saddr) &&
+		    !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)))
 		return false;
 	if (!inet6_mc_check(sk, loc_addr, rmt_addr))
 		return false;
@@ -737,7 +747,7 @@ static void flush_stack(struct sock **stack, unsigned int count,
 
 	for (i = 0; i < count; i++) {
 		sk = stack[i];
-		if (likely(skb1 == NULL))
+		if (likely(!skb1))
 			skb1 = (i == final) ? skb : skb_clone(skb, GFP_ATOMIC);
 		if (!skb1) {
 			atomic_inc(&sk->sk_drops);
@@ -760,9 +770,9 @@ 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));
+	net_dbg_ratelimited("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));
 }
 
 /*
@@ -771,7 +781,7 @@ static void udp6_csum_zero_error(struct sk_buff *skb)
  */
 static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 		const struct in6_addr *saddr, const struct in6_addr *daddr,
-		struct udp_table *udptable)
+		struct udp_table *udptable, int proto)
 {
 	struct sock *sk, *stack[256 / sizeof(struct sock *)];
 	const struct udphdr *uh = udp_hdr(skb);
@@ -781,6 +791,7 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 	int dif = inet6_iif(skb);
 	unsigned int count = 0, offset = offsetof(typeof(*sk), sk_nulls_node);
 	unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10);
+	bool inner_flushed = false;
 
 	if (use_hash2) {
 		hash2_any = udp6_portaddr_hash(net, &in6addr_any, hnum) &
@@ -803,6 +814,7 @@ start_lookup:
 		    (uh->check || udp_sk(sk)->no_check6_rx)) {
 			if (unlikely(count == ARRAY_SIZE(stack))) {
 				flush_stack(stack, count, skb, ~0);
+				inner_flushed = true;
 				count = 0;
 			}
 			stack[count++] = sk;
@@ -821,7 +833,10 @@ start_lookup:
 	if (count) {
 		flush_stack(stack, count, skb, count - 1);
 	} else {
-		kfree_skb(skb);
+		if (!inner_flushed)
+			UDP_INC_STATS_BH(net, UDP_MIB_IGNOREDMULTI,
+					 proto == IPPROTO_UDPLITE);
+		consume_skb(skb);
 	}
 	return 0;
 }
@@ -873,7 +888,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	 */
 	if (ipv6_addr_is_multicast(daddr))
 		return __udp6_lib_mcast_deliver(net, skb,
-				saddr, daddr, udptable);
+				saddr, daddr, udptable, proto);
 
 	/* Unicast */
 
@@ -882,7 +897,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	 * for sock caches... i'll skip this for now.
 	 */
 	sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
-	if (sk != NULL) {
+	if (sk) {
 		int ret;
 
 		if (!uh->check && !udp_sk(sk)->no_check6_rx) {
@@ -891,7 +906,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 			goto csum_error;
 		}
 
-		if (udp_sk(sk)->convert_csum && uh->check && !IS_UDPLITE(sk))
+		if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk))
 			skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
 						 ip6_compute_pseudo);
 
@@ -925,14 +940,11 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	return 0;
 
 short_packet:
-	LIMIT_NETDEBUG(KERN_DEBUG "UDP%sv6: short packet: From [%pI6c]:%u %d/%d to [%pI6c]:%u\n",
-		       proto == IPPROTO_UDPLITE ? "-Lite" : "",
-		       saddr,
-		       ntohs(uh->source),
-		       ulen,
-		       skb->len,
-		       daddr,
-		       ntohs(uh->dest));
+	net_dbg_ratelimited("UDP%sv6: short packet: From [%pI6c]:%u %d/%d to [%pI6c]:%u\n",
+			    proto == IPPROTO_UDPLITE ? "-Lite" : "",
+			    saddr, ntohs(uh->source),
+			    ulen, skb->len,
+			    daddr, ntohs(uh->dest));
 	goto discard;
 csum_error:
 	UDP6_INC_STATS_BH(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE);
@@ -975,9 +987,10 @@ static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb,
 {
 	unsigned int offset;
 	struct udphdr *uh = udp_hdr(skb);
+	struct sk_buff *frags = skb_shinfo(skb)->frag_list;
 	__wsum csum = 0;
 
-	if (skb_queue_len(&sk->sk_write_queue) == 1) {
+	if (!frags) {
 		/* Only one fragment on the socket.  */
 		skb->csum_start = skb_transport_header(skb) - skb->head;
 		skb->csum_offset = offsetof(struct udphdr, check);
@@ -993,9 +1006,9 @@ static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb,
 
 		skb->ip_summed = CHECKSUM_NONE;
 
-		skb_queue_walk(&sk->sk_write_queue, skb) {
-			csum = csum_add(csum, skb->csum);
-		}
+		do {
+			csum = csum_add(csum, frags->csum);
+		} while ((frags = frags->next));
 
 		uh->check = csum_ipv6_magic(saddr, daddr, len, IPPROTO_UDP,
 					    csum);
@@ -1008,25 +1021,15 @@ static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb,
  *	Sending
  */
 
-static int udp_v6_push_pending_frames(struct sock *sk)
+static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6)
 {
-	struct sk_buff *skb;
+	struct sock *sk = skb->sk;
 	struct udphdr *uh;
-	struct udp_sock  *up = udp_sk(sk);
-	struct inet_sock *inet = inet_sk(sk);
-	struct flowi6 *fl6;
 	int err = 0;
 	int is_udplite = IS_UDPLITE(sk);
 	__wsum csum = 0;
-
-	if (up->pending == AF_INET)
-		return udp_push_pending_frames(sk);
-
-	fl6 = &inet->cork.fl.u.ip6;
-
-	/* Grab the skbuff where UDP header space exists. */
-	if ((skb = skb_peek(&sk->sk_write_queue)) == NULL)
-		goto out;
+	int offset = skb_transport_offset(skb);
+	int len = skb->len - offset;
 
 	/*
 	 * Create a UDP header
@@ -1034,29 +1037,28 @@ static int udp_v6_push_pending_frames(struct sock *sk)
 	uh = udp_hdr(skb);
 	uh->source = fl6->fl6_sport;
 	uh->dest = fl6->fl6_dport;
-	uh->len = htons(up->len);
+	uh->len = htons(len);
 	uh->check = 0;
 
 	if (is_udplite)
-		csum = udplite_csum_outgoing(sk, skb);
-	else if (up->no_check6_tx) {   /* UDP csum disabled */
+		csum = udplite_csum(skb);
+	else if (udp_sk(sk)->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);
+		udp6_hwcsum_outgoing(sk, skb, &fl6->saddr, &fl6->daddr, len);
 		goto send;
 	} else
-		csum = udp_csum_outgoing(sk, skb);
+		csum = udp_csum(skb);
 
 	/* add protocol-dependent pseudo-header */
 	uh->check = csum_ipv6_magic(&fl6->saddr, &fl6->daddr,
-				    up->len, fl6->flowi6_proto, csum);
+				    len, fl6->flowi6_proto, csum);
 	if (uh->check == 0)
 		uh->check = CSUM_MANGLED_0;
 
 send:
-	err = ip6_push_pending_frames(sk);
+	err = ip6_send_skb(skb);
 	if (err) {
 		if (err == -ENOBUFS && !inet6_sk(sk)->recverr) {
 			UDP6_INC_STATS_USER(sock_net(sk),
@@ -1066,14 +1068,37 @@ send:
 	} else
 		UDP6_INC_STATS_USER(sock_net(sk),
 				    UDP_MIB_OUTDATAGRAMS, is_udplite);
+	return err;
+}
+
+static int udp_v6_push_pending_frames(struct sock *sk)
+{
+	struct sk_buff *skb;
+	struct udp_sock  *up = udp_sk(sk);
+	struct flowi6 fl6;
+	int err = 0;
+
+	if (up->pending == AF_INET)
+		return udp_push_pending_frames(sk);
+
+	/* ip6_finish_skb will release the cork, so make a copy of
+	 * fl6 here.
+	 */
+	fl6 = inet_sk(sk)->cork.fl.u.ip6;
+
+	skb = ip6_finish_skb(sk);
+	if (!skb)
+		goto out;
+
+	err = udp_v6_send_skb(skb, &fl6);
+
 out:
 	up->len = 0;
 	up->pending = 0;
 	return err;
 }
 
-int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk,
-		  struct msghdr *msg, size_t len)
+int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 {
 	struct ipv6_txoptions opt_space;
 	struct udp_sock *up = udp_sk(sk);
@@ -1135,12 +1160,12 @@ int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 do_udp_sendmsg:
 			if (__ipv6_only_sock(sk))
 				return -ENETUNREACH;
-			return udp_sendmsg(iocb, sk, msg, len);
+			return udp_sendmsg(sk, msg, len);
 		}
 	}
 
 	if (up->pending == AF_INET)
-		return udp_sendmsg(iocb, sk, msg, len);
+		return udp_sendmsg(sk, msg, len);
 
 	/* Rough check on arithmetic overflow,
 	   better check is made in ip6_append_data().
@@ -1148,6 +1173,7 @@ do_udp_sendmsg:
 	if (len > INT_MAX - sizeof(struct udphdr))
 		return -EMSGSIZE;
 
+	getfrag  =  is_udplite ?  udplite_getfrag : ip_generic_getfrag;
 	if (up->pending) {
 		/*
 		 * There are pending frames.
@@ -1179,7 +1205,7 @@ do_udp_sendmsg:
 			fl6.flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK;
 			if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) {
 				flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
-				if (flowlabel == NULL)
+				if (!flowlabel)
 					return -EINVAL;
 			}
 		}
@@ -1227,14 +1253,14 @@ do_udp_sendmsg:
 		}
 		if ((fl6.flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) {
 			flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
-			if (flowlabel == NULL)
+			if (!flowlabel)
 				return -EINVAL;
 		}
 		if (!(opt->opt_nflen|opt->opt_flen))
 			opt = NULL;
 		connected = 0;
 	}
-	if (opt == NULL)
+	if (!opt)
 		opt = np->opt;
 	if (flowlabel)
 		opt = fl6_merge_options(&opt_space, flowlabel, opt);
@@ -1278,13 +1304,27 @@ do_udp_sendmsg:
 		goto do_confirm;
 back_from_confirm:
 
+	/* Lockless fast path for the non-corking case */
+	if (!corkreq) {
+		struct sk_buff *skb;
+
+		skb = ip6_make_skb(sk, getfrag, msg, ulen,
+				   sizeof(struct udphdr), hlimit, tclass, opt,
+				   &fl6, (struct rt6_info *)dst,
+				   msg->msg_flags, dontfrag);
+		err = PTR_ERR(skb);
+		if (!IS_ERR_OR_NULL(skb))
+			err = udp_v6_send_skb(skb, &fl6);
+		goto release_dst;
+	}
+
 	lock_sock(sk);
 	if (unlikely(up->pending)) {
 		/* The socket is already corked while preparing it. */
 		/* ... which is an evident application bug. --ANK */
 		release_sock(sk);
 
-		LIMIT_NETDEBUG(KERN_DEBUG "udp cork app bug 2\n");
+		net_dbg_ratelimited("udp cork app bug 2\n");
 		err = -EINVAL;
 		goto out;
 	}
@@ -1295,8 +1335,7 @@ do_append_data:
 	if (dontfrag < 0)
 		dontfrag = np->dontfrag;
 	up->len += ulen;
-	getfrag  =  is_udplite ?  udplite_getfrag : ip_generic_getfrag;
-	err = ip6_append_data(sk, getfrag, msg->msg_iov, ulen,
+	err = ip6_append_data(sk, getfrag, msg, ulen,
 		sizeof(struct udphdr), hlimit, tclass, opt, &fl6,
 		(struct rt6_info *)dst,
 		corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags, dontfrag);
@@ -1307,6 +1346,11 @@ do_append_data:
 	else if (unlikely(skb_queue_empty(&sk->sk_write_queue)))
 		up->pending = 0;
 
+	if (err > 0)
+		err = np->recverr ? net_xmit_errno(err) : 0;
+	release_sock(sk);
+
+release_dst:
 	if (dst) {
 		if (connected) {
 			ip6_dst_store(sk, dst,
@@ -1323,9 +1367,6 @@ do_append_data:
 		dst = NULL;
 	}
 
-	if (err > 0)
-		err = np->recverr ? net_xmit_errno(err) : 0;
-	release_sock(sk);
 out:
 	dst_release(dst);
 	fl6_sock_release(flowlabel);
@@ -1512,7 +1553,6 @@ static struct inet_protosw udpv6_protosw = {
 	.flags =     INET_PROTOSW_PERMANENT,
 };
 
-
 int __init udpv6_init(void)
 {
 	int ret;
diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h
index c779c3c90b9d..0682c031ccdc 100644
--- a/net/ipv6/udp_impl.h
+++ b/net/ipv6/udp_impl.h
@@ -23,10 +23,9 @@ int compat_udpv6_setsockopt(struct sock *sk, int level, int optname,
 int compat_udpv6_getsockopt(struct sock *sk, int level, int optname,
 			    char __user *optval, int __user *optlen);
 #endif
-int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
-		  size_t len);
-int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
-		  size_t len, int noblock, int flags, int *addr_len);
+int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len);
+int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
+		  int flags, int *addr_len);
 int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
 void udpv6_destroy_sock(struct sock *sk);
 
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 6b8f543f6ac6..7441e1e63893 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -42,16 +42,20 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 				      SKB_GSO_DODGY |
 				      SKB_GSO_UDP_TUNNEL |
 				      SKB_GSO_UDP_TUNNEL_CSUM |
+				      SKB_GSO_TUNNEL_REMCSUM |
 				      SKB_GSO_GRE |
 				      SKB_GSO_GRE_CSUM |
 				      SKB_GSO_IPIP |
-				      SKB_GSO_SIT |
-				      SKB_GSO_MPLS) ||
+				      SKB_GSO_SIT) ||
 			     !(type & (SKB_GSO_UDP))))
 			goto out;
 
 		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
 
+		/* Set the IPv6 fragment id if not set yet */
+		if (!skb_shinfo(skb)->ip6_frag_id)
+			ipv6_proxy_select_ident(dev_net(skb->dev), skb);
+
 		segs = NULL;
 		goto out;
 	}
@@ -108,6 +112,8 @@ 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;
+		if (!skb_shinfo(skb)->ip6_frag_id)
+			ipv6_proxy_select_ident(dev_net(skb->dev), skb);
 		fptr->identification = skb_shinfo(skb)->ip6_frag_id;
 
 		/* Fragment the skb. ipv6 header and the remaining fields of the
@@ -153,9 +159,13 @@ static int udp6_gro_complete(struct sk_buff *skb, int nhoff)
 	const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
 	struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
 
-	if (uh->check)
+	if (uh->check) {
+		skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;
 		uh->check = ~udp_v6_check(skb->len - nhoff, &ipv6h->saddr,
 					  &ipv6h->daddr, 0);
+	} else {
+		skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL;
+	}
 
 	return udp_gro_complete(skb, nhoff);
 }
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index f48fbe4d16f5..74bd17882a2f 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -42,7 +42,8 @@ int xfrm6_transport_finish(struct sk_buff *skb, int async)
 	ipv6_hdr(skb)->payload_len = htons(skb->len);
 	__skb_push(skb, skb->data - skb_network_header(skb));
 
-	NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, skb, skb->dev, NULL,
+	NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, NULL, skb,
+		skb->dev, NULL,
 		ip6_rcv_finish);
 	return -1;
 }
diff --git a/net/ipv6/xfrm6_mode_beet.c b/net/ipv6/xfrm6_mode_beet.c
index 9949a356d62c..1e205c3253ac 100644
--- a/net/ipv6/xfrm6_mode_beet.c
+++ b/net/ipv6/xfrm6_mode_beet.c
@@ -95,8 +95,8 @@ static int xfrm6_beet_input(struct xfrm_state *x, struct sk_buff *skb)
 
 	ip6h = ipv6_hdr(skb);
 	ip6h->payload_len = htons(skb->len - size);
-	ip6h->daddr = *(struct in6_addr *)&x->sel.daddr.a6;
-	ip6h->saddr = *(struct in6_addr *)&x->sel.saddr.a6;
+	ip6h->daddr = x->sel.daddr.in6;
+	ip6h->saddr = x->sel.saddr.in6;
 	err = 0;
 out:
 	return err;
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index ca3f29b98ae5..09c76a7b474d 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -114,24 +114,24 @@ int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
 		return err;
 
 	skb->ignore_df = 1;
+	skb->protocol = htons(ETH_P_IPV6);
 
 	return x->outer_mode->output2(x, skb);
 }
 EXPORT_SYMBOL(xfrm6_prepare_output);
 
-int xfrm6_output_finish(struct sk_buff *skb)
+int xfrm6_output_finish(struct sock *sk, 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
 
-	return xfrm_output(skb);
+	return xfrm_output(sk, skb);
 }
 
-static int __xfrm6_output(struct sk_buff *skb)
+static int __xfrm6_output(struct sock *sk, struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 	struct xfrm_state *x = dst->xfrm;
@@ -140,7 +140,7 @@ static int __xfrm6_output(struct sk_buff *skb)
 #ifdef CONFIG_NETFILTER
 	if (!x) {
 		IP6CB(skb)->flags |= IP6SKB_REROUTED;
-		return dst_output(skb);
+		return dst_output_sk(sk, skb);
 	}
 #endif
 
@@ -160,14 +160,15 @@ static int __xfrm6_output(struct sk_buff *skb)
 	if (x->props.mode == XFRM_MODE_TUNNEL &&
 	    ((skb->len > mtu && !skb_is_gso(skb)) ||
 		dst_allfrag(skb_dst(skb)))) {
-			return ip6_fragment(skb, x->outer_mode->afinfo->output_finish);
+		return ip6_fragment(sk, skb,
+				    x->outer_mode->afinfo->output_finish);
 	}
-	return x->outer_mode->afinfo->output_finish(skb);
+	return x->outer_mode->afinfo->output_finish(sk, skb);
 }
 
 int xfrm6_output(struct sock *sk, struct sk_buff *skb)
 {
-	return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb,
+	return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, sk, 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 5f983644373a..f337a908a76a 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -61,9 +61,7 @@ static int xfrm6_get_saddr(struct net *net,
 		return -EHOSTUNREACH;
 
 	dev = ip6_dst_idev(dst)->dev;
-	ipv6_dev_get_saddr(dev_net(dev), dev,
-			   (struct in6_addr *)&daddr->a6, 0,
-			   (struct in6_addr *)&saddr->a6);
+	ipv6_dev_get_saddr(dev_net(dev), dev, &daddr->in6, 0, &saddr->in6);
 	dst_release(dst);
 	return 0;
 }
@@ -130,12 +128,18 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 {
 	struct flowi6 *fl6 = &fl->u.ip6;
 	int onlyproto = 0;
-	u16 offset = skb_network_header_len(skb);
 	const struct ipv6hdr *hdr = ipv6_hdr(skb);
+	u16 offset = sizeof(*hdr);
 	struct ipv6_opt_hdr *exthdr;
 	const unsigned char *nh = skb_network_header(skb);
-	u8 nexthdr = nh[IP6CB(skb)->nhoff];
+	u16 nhoff = IP6CB(skb)->nhoff;
 	int oif = 0;
+	u8 nexthdr;
+
+	if (!nhoff)
+		nhoff = offsetof(struct ipv6hdr, nexthdr);
+
+	nexthdr = nh[nhoff];
 
 	if (skb_dst(skb))
 		oif = skb_dst(skb)->dev->ifindex;
@@ -194,6 +198,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 
 #if IS_ENABLED(CONFIG_IPV6_MIP6)
 		case IPPROTO_MH:
+			offset += ipv6_optlen(exthdr);
 			if (!onlyproto && pskb_may_pull(skb, nh + offset + 3 - skb->data)) {
 				struct ip6_mh *mh;
 
@@ -286,7 +291,6 @@ static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 
 static struct dst_ops xfrm6_dst_ops = {
 	.family =		AF_INET6,
-	.protocol =		cpu_to_be16(ETH_P_IPV6),
 	.gc =			xfrm6_garbage_collect,
 	.update_pmtu =		xfrm6_update_pmtu,
 	.redirect =		xfrm6_redirect,
@@ -364,7 +368,7 @@ static void __net_exit xfrm6_net_exit(struct net *net)
 {
 	struct ctl_table *table;
 
-	if (net->ipv6.sysctl.xfrm6_hdr == NULL)
+	if (!net->ipv6.sysctl.xfrm6_hdr)
 		return;
 
 	table = net->ipv6.sysctl.xfrm6_hdr->ctl_table_arg;
diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c
index 91729b807c7d..4ea5d7497b5f 100644
--- a/net/ipx/af_ipx.c
+++ b/net/ipx/af_ipx.c
@@ -306,7 +306,7 @@ void ipxitf_down(struct ipx_interface *intrfc)
 	spin_unlock_bh(&ipx_interfaces_lock);
 }
 
-static __inline__ void __ipxitf_put(struct ipx_interface *intrfc)
+static void __ipxitf_put(struct ipx_interface *intrfc)
 {
 	if (atomic_dec_and_test(&intrfc->refcnt))
 		__ipxitf_down(intrfc);
@@ -1688,8 +1688,7 @@ out:
 	return rc;
 }
 
-static int ipx_sendmsg(struct kiocb *iocb, struct socket *sock,
-	struct msghdr *msg, size_t len)
+static int ipx_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 {
 	struct sock *sk = sock->sk;
 	struct ipx_sock *ipxs = ipx_sk(sk);
@@ -1745,8 +1744,7 @@ static int ipx_sendmsg(struct kiocb *iocb, struct socket *sock,
 		memcpy(usipx->sipx_node, ipxs->dest_addr.node, IPX_NODE_LEN);
 	}
 
-	rc = ipxrtr_route_packet(sk, usipx, msg->msg_iov, len,
-				 flags & MSG_DONTWAIT);
+	rc = ipxrtr_route_packet(sk, usipx, msg, len, flags & MSG_DONTWAIT);
 	if (rc >= 0)
 		rc = len;
 out:
@@ -1755,8 +1753,8 @@ out:
 }
 
 
-static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock,
-		struct msghdr *msg, size_t size, int flags)
+static int ipx_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+		       int flags)
 {
 	struct sock *sk = sock->sk;
 	struct ipx_sock *ipxs = ipx_sk(sk);
@@ -1764,6 +1762,7 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock,
 	struct ipxhdr *ipx = NULL;
 	struct sk_buff *skb;
 	int copied, rc;
+	bool locked = true;
 
 	lock_sock(sk);
 	/* put the autobinding in */
@@ -1790,6 +1789,8 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (sock_flag(sk, SOCK_ZAPPED))
 		goto out;
 
+	release_sock(sk);
+	locked = false;
 	skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
 				flags & MSG_DONTWAIT, &rc);
 	if (!skb) {
@@ -1805,8 +1806,7 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock,
 		msg->msg_flags |= MSG_TRUNC;
 	}
 
-	rc = skb_copy_datagram_iovec(skb, sizeof(struct ipxhdr), msg->msg_iov,
-				     copied);
+	rc = skb_copy_datagram_msg(skb, sizeof(struct ipxhdr), msg, copied);
 	if (rc)
 		goto out_free;
 	if (skb->tstamp.tv64)
@@ -1826,7 +1826,8 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock,
 out_free:
 	skb_free_datagram(sk, skb);
 out:
-	release_sock(sk);
+	if (locked)
+		release_sock(sk);
 	return rc;
 }
 
diff --git a/net/ipx/ipx_proc.c b/net/ipx/ipx_proc.c
index e15c16a517e7..c1d247ebe916 100644
--- a/net/ipx/ipx_proc.c
+++ b/net/ipx/ipx_proc.c
@@ -45,7 +45,7 @@ static int ipx_seq_interface_show(struct seq_file *seq, void *v)
 	}
 
 	i = list_entry(v, struct ipx_interface, node);
-	seq_printf(seq, "%08lX   ", (unsigned long int)ntohl(i->if_netnum));
+	seq_printf(seq, "%08X   ", ntohl(i->if_netnum));
 	seq_printf(seq, "%02X%02X%02X%02X%02X%02X   ",
 			i->if_node[0], i->if_node[1], i->if_node[2],
 			i->if_node[3], i->if_node[4], i->if_node[5]);
@@ -87,10 +87,10 @@ static int ipx_seq_route_show(struct seq_file *seq, void *v)
 
 	rt = list_entry(v, struct ipx_route, node);
 
-	seq_printf(seq, "%08lX   ", (unsigned long int)ntohl(rt->ir_net));
+	seq_printf(seq, "%08X   ", ntohl(rt->ir_net));
 	if (rt->ir_routed)
-		seq_printf(seq, "%08lX     %02X%02X%02X%02X%02X%02X\n",
-			   (long unsigned int)ntohl(rt->ir_intrfc->if_netnum),
+		seq_printf(seq, "%08X     %02X%02X%02X%02X%02X%02X\n",
+			   ntohl(rt->ir_intrfc->if_netnum),
 			   rt->ir_router_node[0], rt->ir_router_node[1],
 			   rt->ir_router_node[2], rt->ir_router_node[3],
 			   rt->ir_router_node[4], rt->ir_router_node[5]);
@@ -194,19 +194,19 @@ static int ipx_seq_socket_show(struct seq_file *seq, void *v)
 	s = v;
 	ipxs = ipx_sk(s);
 #ifdef CONFIG_IPX_INTERN
-	seq_printf(seq, "%08lX:%02X%02X%02X%02X%02X%02X:%04X  ",
-		   (unsigned long)ntohl(ipxs->intrfc->if_netnum),
+	seq_printf(seq, "%08X:%02X%02X%02X%02X%02X%02X:%04X  ",
+		   ntohl(ipxs->intrfc->if_netnum),
 		   ipxs->node[0], ipxs->node[1], ipxs->node[2], ipxs->node[3],
 		   ipxs->node[4], ipxs->node[5], ntohs(ipxs->port));
 #else
-	seq_printf(seq, "%08lX:%04X  ", (unsigned long) ntohl(ipxs->intrfc->if_netnum),
+	seq_printf(seq, "%08X:%04X  ", ntohl(ipxs->intrfc->if_netnum),
 		   ntohs(ipxs->port));
 #endif	/* CONFIG_IPX_INTERN */
 	if (s->sk_state != TCP_ESTABLISHED)
 		seq_printf(seq, "%-28s", "Not_Connected");
 	else {
-		seq_printf(seq, "%08lX:%02X%02X%02X%02X%02X%02X:%04X  ",
-			   (unsigned long)ntohl(ipxs->dest_addr.net),
+		seq_printf(seq, "%08X:%02X%02X%02X%02X%02X%02X:%04X  ",
+			   ntohl(ipxs->dest_addr.net),
 			   ipxs->dest_addr.node[0], ipxs->dest_addr.node[1],
 			   ipxs->dest_addr.node[2], ipxs->dest_addr.node[3],
 			   ipxs->dest_addr.node[4], ipxs->dest_addr.node[5],
diff --git a/net/ipx/ipx_route.c b/net/ipx/ipx_route.c
index 67e7ad3d46b1..3e2a32a9f3bd 100644
--- a/net/ipx/ipx_route.c
+++ b/net/ipx/ipx_route.c
@@ -165,7 +165,7 @@ int ipxrtr_route_skb(struct sk_buff *skb)
  * Route an outgoing frame from a socket.
  */
 int ipxrtr_route_packet(struct sock *sk, struct sockaddr_ipx *usipx,
-			struct iovec *iov, size_t len, int noblock)
+			struct msghdr *msg, size_t len, int noblock)
 {
 	struct sk_buff *skb;
 	struct ipx_sock *ipxs = ipx_sk(sk);
@@ -229,7 +229,7 @@ int ipxrtr_route_packet(struct sock *sk, struct sockaddr_ipx *usipx,
 	memcpy(ipx->ipx_dest.node, usipx->sipx_node, IPX_NODE_LEN);
 	ipx->ipx_dest.sock		= usipx->sipx_port;
 
-	rc = memcpy_fromiovec(skb_put(skb, len), iov, len);
+	rc = memcpy_from_msg(skb_put(skb, len), msg, len);
 	if (rc) {
 		kfree_skb(skb);
 		goto out_put;
diff --git a/net/ipx/sysctl_net_ipx.c b/net/ipx/sysctl_net_ipx.c
index ad7c03dedaab..0dafcc561ed6 100644
--- a/net/ipx/sysctl_net_ipx.c
+++ b/net/ipx/sysctl_net_ipx.c
@@ -9,14 +9,12 @@
 #include <linux/mm.h>
 #include <linux/sysctl.h>
 #include <net/net_namespace.h>
+#include <net/ipx.h>
 
 #ifndef CONFIG_SYSCTL
 #error This file should not be compiled without CONFIG_SYSCTL defined
 #endif
 
-/* From af_ipx.c */
-extern int sysctl_ipx_pprop_broadcasting;
-
 static struct ctl_table ipx_table[] = {
 	{
 		.procname	= "ipx_pprop_broadcasting",
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index 3f3a6cbdceb7..ee0ea25c8e7a 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -84,14 +84,12 @@ static int irda_data_indication(void *instance, void *sap, struct sk_buff *skb)
 	struct sock *sk;
 	int err;
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	self = instance;
 	sk = instance;
 
 	err = sock_queue_rcv_skb(sk, skb);
 	if (err) {
-		IRDA_DEBUG(1, "%s(), error: no more mem!\n", __func__);
+		pr_debug("%s(), error: no more mem!\n", __func__);
 		self->rx_flow = FLOW_STOP;
 
 		/* When we return error, TTP will need to requeue the skb */
@@ -115,7 +113,7 @@ static void irda_disconnect_indication(void *instance, void *sap,
 
 	self = instance;
 
-	IRDA_DEBUG(2, "%s(%p)\n", __func__, self);
+	pr_debug("%s(%p)\n", __func__, self);
 
 	/* Don't care about it, but let's not leak it */
 	if(skb)
@@ -123,8 +121,8 @@ static void irda_disconnect_indication(void *instance, void *sap,
 
 	sk = instance;
 	if (sk == NULL) {
-		IRDA_DEBUG(0, "%s(%p) : BUG : sk is NULL\n",
-			   __func__, self);
+		pr_debug("%s(%p) : BUG : sk is NULL\n",
+			 __func__, self);
 		return;
 	}
 
@@ -180,7 +178,7 @@ static void irda_connect_confirm(void *instance, void *sap,
 
 	self = instance;
 
-	IRDA_DEBUG(2, "%s(%p)\n", __func__, self);
+	pr_debug("%s(%p)\n", __func__, self);
 
 	sk = instance;
 	if (sk == NULL) {
@@ -201,16 +199,16 @@ static void irda_connect_confirm(void *instance, void *sap,
 	switch (sk->sk_type) {
 	case SOCK_STREAM:
 		if (max_sdu_size != 0) {
-			IRDA_ERROR("%s: max_sdu_size must be 0\n",
-				   __func__);
+			net_err_ratelimited("%s: max_sdu_size must be 0\n",
+					    __func__);
 			return;
 		}
 		self->max_data_size = irttp_get_max_seg_size(self->tsap);
 		break;
 	case SOCK_SEQPACKET:
 		if (max_sdu_size == 0) {
-			IRDA_ERROR("%s: max_sdu_size cannot be 0\n",
-				   __func__);
+			net_err_ratelimited("%s: max_sdu_size cannot be 0\n",
+					    __func__);
 			return;
 		}
 		self->max_data_size = max_sdu_size;
@@ -219,8 +217,8 @@ static void irda_connect_confirm(void *instance, void *sap,
 		self->max_data_size = irttp_get_max_seg_size(self->tsap);
 	}
 
-	IRDA_DEBUG(2, "%s(), max_data_size=%d\n", __func__,
-		   self->max_data_size);
+	pr_debug("%s(), max_data_size=%d\n", __func__,
+		 self->max_data_size);
 
 	memcpy(&self->qos_tx, qos, sizeof(struct qos_info));
 
@@ -244,7 +242,7 @@ static void irda_connect_indication(void *instance, void *sap,
 
 	self = instance;
 
-	IRDA_DEBUG(2, "%s(%p)\n", __func__, self);
+	pr_debug("%s(%p)\n", __func__, self);
 
 	sk = instance;
 	if (sk == NULL) {
@@ -262,8 +260,8 @@ static void irda_connect_indication(void *instance, void *sap,
 	switch (sk->sk_type) {
 	case SOCK_STREAM:
 		if (max_sdu_size != 0) {
-			IRDA_ERROR("%s: max_sdu_size must be 0\n",
-				   __func__);
+			net_err_ratelimited("%s: max_sdu_size must be 0\n",
+					    __func__);
 			kfree_skb(skb);
 			return;
 		}
@@ -271,8 +269,8 @@ static void irda_connect_indication(void *instance, void *sap,
 		break;
 	case SOCK_SEQPACKET:
 		if (max_sdu_size == 0) {
-			IRDA_ERROR("%s: max_sdu_size cannot be 0\n",
-				   __func__);
+			net_err_ratelimited("%s: max_sdu_size cannot be 0\n",
+					    __func__);
 			kfree_skb(skb);
 			return;
 		}
@@ -282,8 +280,8 @@ static void irda_connect_indication(void *instance, void *sap,
 		self->max_data_size = irttp_get_max_seg_size(self->tsap);
 	}
 
-	IRDA_DEBUG(2, "%s(), max_data_size=%d\n", __func__,
-		   self->max_data_size);
+	pr_debug("%s(), max_data_size=%d\n", __func__,
+		 self->max_data_size);
 
 	memcpy(&self->qos_tx, qos, sizeof(struct qos_info));
 
@@ -301,12 +299,10 @@ static void irda_connect_response(struct irda_sock *self)
 {
 	struct sk_buff *skb;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	skb = alloc_skb(TTP_MAX_HEADER + TTP_SAR_HEADER, GFP_KERNEL);
 	if (skb == NULL) {
-		IRDA_DEBUG(0, "%s() Unable to allocate sk_buff!\n",
-			   __func__);
+		pr_debug("%s() Unable to allocate sk_buff!\n",
+			 __func__);
 		return;
 	}
 
@@ -327,26 +323,24 @@ static void irda_flow_indication(void *instance, void *sap, LOCAL_FLOW flow)
 	struct irda_sock *self;
 	struct sock *sk;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	self = instance;
 	sk = instance;
 	BUG_ON(sk == NULL);
 
 	switch (flow) {
 	case FLOW_STOP:
-		IRDA_DEBUG(1, "%s(), IrTTP wants us to slow down\n",
-			   __func__);
+		pr_debug("%s(), IrTTP wants us to slow down\n",
+			 __func__);
 		self->tx_flow = flow;
 		break;
 	case FLOW_START:
 		self->tx_flow = flow;
-		IRDA_DEBUG(1, "%s(), IrTTP wants us to start again\n",
-			   __func__);
+		pr_debug("%s(), IrTTP wants us to start again\n",
+			 __func__);
 		wake_up_interruptible(sk_sleep(sk));
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), Unknown flow command!\n", __func__);
+		pr_debug("%s(), Unknown flow command!\n", __func__);
 		/* Unknown flow command, better stop */
 		self->tx_flow = flow;
 		break;
@@ -368,11 +362,11 @@ static void irda_getvalue_confirm(int result, __u16 obj_id,
 
 	self = priv;
 	if (!self) {
-		IRDA_WARNING("%s: lost myself!\n", __func__);
+		net_warn_ratelimited("%s: lost myself!\n", __func__);
 		return;
 	}
 
-	IRDA_DEBUG(2, "%s(%p)\n", __func__, self);
+	pr_debug("%s(%p)\n", __func__, self);
 
 	/* We probably don't need to make any more queries */
 	iriap_close(self->iriap);
@@ -380,8 +374,8 @@ static void irda_getvalue_confirm(int result, __u16 obj_id,
 
 	/* Check if request succeeded */
 	if (result != IAS_SUCCESS) {
-		IRDA_DEBUG(1, "%s(), IAS query failed! (%d)\n", __func__,
-			   result);
+		pr_debug("%s(), IAS query failed! (%d)\n", __func__,
+			 result);
 
 		self->errno = result;	/* We really need it later */
 
@@ -413,11 +407,9 @@ static void irda_selective_discovery_indication(discinfo_t *discovery,
 {
 	struct irda_sock *self;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	self = priv;
 	if (!self) {
-		IRDA_WARNING("%s: lost myself!\n", __func__);
+		net_warn_ratelimited("%s: lost myself!\n", __func__);
 		return;
 	}
 
@@ -440,8 +432,6 @@ static void irda_discovery_timeout(u_long priv)
 {
 	struct irda_sock *self;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	self = (struct irda_sock *) priv;
 	BUG_ON(self == NULL);
 
@@ -465,7 +455,7 @@ static int irda_open_tsap(struct irda_sock *self, __u8 tsap_sel, char *name)
 	notify_t notify;
 
 	if (self->tsap) {
-		IRDA_DEBUG(0, "%s: busy!\n", __func__);
+		pr_debug("%s: busy!\n", __func__);
 		return -EBUSY;
 	}
 
@@ -483,8 +473,8 @@ static int irda_open_tsap(struct irda_sock *self, __u8 tsap_sel, char *name)
 	self->tsap = irttp_open_tsap(tsap_sel, DEFAULT_INITIAL_CREDIT,
 				     &notify);
 	if (self->tsap == NULL) {
-		IRDA_DEBUG(0, "%s(), Unable to allocate TSAP!\n",
-			   __func__);
+		pr_debug("%s(), Unable to allocate TSAP!\n",
+			 __func__);
 		return -ENOMEM;
 	}
 	/* Remember which TSAP selector we actually got */
@@ -505,7 +495,7 @@ static int irda_open_lsap(struct irda_sock *self, int pid)
 	notify_t notify;
 
 	if (self->lsap) {
-		IRDA_WARNING("%s(), busy!\n", __func__);
+		net_warn_ratelimited("%s(), busy!\n", __func__);
 		return -EBUSY;
 	}
 
@@ -517,7 +507,7 @@ static int irda_open_lsap(struct irda_sock *self, int pid)
 
 	self->lsap = irlmp_open_lsap(LSAP_CONNLESS, &notify, pid);
 	if (self->lsap == NULL) {
-		IRDA_DEBUG( 0, "%s(), Unable to allocate LSAP!\n", __func__);
+		pr_debug("%s(), Unable to allocate LSAP!\n", __func__);
 		return -ENOMEM;
 	}
 
@@ -538,11 +528,11 @@ static int irda_open_lsap(struct irda_sock *self, int pid)
  */
 static int irda_find_lsap_sel(struct irda_sock *self, char *name)
 {
-	IRDA_DEBUG(2, "%s(%p, %s)\n", __func__, self, name);
+	pr_debug("%s(%p, %s)\n", __func__, self, name);
 
 	if (self->iriap) {
-		IRDA_WARNING("%s(): busy with a previous query\n",
-			     __func__);
+		net_warn_ratelimited("%s(): busy with a previous query\n",
+				     __func__);
 		return -EBUSY;
 	}
 
@@ -577,8 +567,8 @@ static int irda_find_lsap_sel(struct irda_sock *self, char *name)
 	/* Get the remote TSAP selector */
 	switch (self->ias_result->type) {
 	case IAS_INTEGER:
-		IRDA_DEBUG(4, "%s() int=%d\n",
-			   __func__, self->ias_result->t.integer);
+		pr_debug("%s() int=%d\n",
+			 __func__, self->ias_result->t.integer);
 
 		if (self->ias_result->t.integer != -1)
 			self->dtsap_sel = self->ias_result->t.integer;
@@ -587,7 +577,7 @@ static int irda_find_lsap_sel(struct irda_sock *self, char *name)
 		break;
 	default:
 		self->dtsap_sel = 0;
-		IRDA_DEBUG(0, "%s(), bad type!\n", __func__);
+		pr_debug("%s(), bad type!\n", __func__);
 		break;
 	}
 	if (self->ias_result)
@@ -625,7 +615,7 @@ static int irda_discover_daddr_and_lsap_sel(struct irda_sock *self, char *name)
 	__u32	daddr = DEV_ADDR_ANY;	/* Address we found the service on */
 	__u8	dtsap_sel = 0x0;	/* TSAP associated with it */
 
-	IRDA_DEBUG(2, "%s(), name=%s\n", __func__, name);
+	pr_debug("%s(), name=%s\n", __func__, name);
 
 	/* Ask lmp for the current discovery log
 	 * Note : we have to use irlmp_get_discoveries(), as opposed
@@ -646,8 +636,8 @@ static int irda_discover_daddr_and_lsap_sel(struct irda_sock *self, char *name)
 		/* Try the address in the log */
 		self->daddr = discoveries[i].daddr;
 		self->saddr = 0x0;
-		IRDA_DEBUG(1, "%s(), trying daddr = %08x\n",
-			   __func__, self->daddr);
+		pr_debug("%s(), trying daddr = %08x\n",
+			 __func__, self->daddr);
 
 		/* Query remote LM-IAS for this service */
 		err = irda_find_lsap_sel(self, name);
@@ -655,8 +645,8 @@ static int irda_discover_daddr_and_lsap_sel(struct irda_sock *self, char *name)
 		case 0:
 			/* We found the requested service */
 			if(daddr != DEV_ADDR_ANY) {
-				IRDA_DEBUG(1, "%s(), discovered service ''%s'' in two different devices !!!\n",
-					   __func__, name);
+				pr_debug("%s(), discovered service ''%s'' in two different devices !!!\n",
+					 __func__, name);
 				self->daddr = DEV_ADDR_ANY;
 				kfree(discoveries);
 				return -ENOTUNIQ;
@@ -670,7 +660,8 @@ static int irda_discover_daddr_and_lsap_sel(struct irda_sock *self, char *name)
 			break;
 		default:
 			/* Something bad did happen :-( */
-			IRDA_DEBUG(0, "%s(), unexpected IAS query failure\n", __func__);
+			pr_debug("%s(), unexpected IAS query failure\n",
+				 __func__);
 			self->daddr = DEV_ADDR_ANY;
 			kfree(discoveries);
 			return -EHOSTUNREACH;
@@ -681,8 +672,8 @@ static int irda_discover_daddr_and_lsap_sel(struct irda_sock *self, char *name)
 
 	/* Check out what we found */
 	if(daddr == DEV_ADDR_ANY) {
-		IRDA_DEBUG(1, "%s(), cannot discover service ''%s'' in any device !!!\n",
-			   __func__, name);
+		pr_debug("%s(), cannot discover service ''%s'' in any device !!!\n",
+			 __func__, name);
 		self->daddr = DEV_ADDR_ANY;
 		return -EADDRNOTAVAIL;
 	}
@@ -692,8 +683,8 @@ static int irda_discover_daddr_and_lsap_sel(struct irda_sock *self, char *name)
 	self->saddr = 0x0;
 	self->dtsap_sel = dtsap_sel;
 
-	IRDA_DEBUG(1, "%s(), discovered requested service ''%s'' at address %08x\n",
-		   __func__, name, self->daddr);
+	pr_debug("%s(), discovered requested service ''%s'' at address %08x\n",
+		 __func__, name, self->daddr);
 
 	return 0;
 }
@@ -725,8 +716,8 @@ static int irda_getname(struct socket *sock, struct sockaddr *uaddr,
 		saddr.sir_addr = self->saddr;
 	}
 
-	IRDA_DEBUG(1, "%s(), tsap_sel = %#x\n", __func__, saddr.sir_lsap_sel);
-	IRDA_DEBUG(1, "%s(), addr = %08x\n", __func__, saddr.sir_addr);
+	pr_debug("%s(), tsap_sel = %#x\n", __func__, saddr.sir_lsap_sel);
+	pr_debug("%s(), addr = %08x\n", __func__, saddr.sir_addr);
 
 	/* uaddr_len come to us uninitialised */
 	*uaddr_len = sizeof (struct sockaddr_irda);
@@ -746,8 +737,6 @@ static int irda_listen(struct socket *sock, int backlog)
 	struct sock *sk = sock->sk;
 	int err = -EOPNOTSUPP;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	lock_sock(sk);
 
 	if ((sk->sk_type != SOCK_STREAM) && (sk->sk_type != SOCK_SEQPACKET) &&
@@ -779,7 +768,7 @@ static int irda_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	struct irda_sock *self = irda_sk(sk);
 	int err;
 
-	IRDA_DEBUG(2, "%s(%p)\n", __func__, self);
+	pr_debug("%s(%p)\n", __func__, self);
 
 	if (addr_len != sizeof(struct sockaddr_irda))
 		return -EINVAL;
@@ -792,7 +781,8 @@ static int irda_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		self->pid = addr->sir_lsap_sel;
 		err = -EOPNOTSUPP;
 		if (self->pid & 0x80) {
-			IRDA_DEBUG(0, "%s(), extension in PID not supp!\n", __func__);
+			pr_debug("%s(), extension in PID not supp!\n",
+				 __func__);
 			goto out;
 		}
 		err = irda_open_lsap(self, self->pid);
@@ -845,8 +835,6 @@ static int irda_accept(struct socket *sock, struct socket *newsock, int flags)
 	struct sk_buff *skb;
 	int err;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	err = irda_create(sock_net(sk), newsock, sk->sk_protocol, 0);
 	if (err)
 		return err;
@@ -911,7 +899,7 @@ static int irda_accept(struct socket *sock, struct socket *newsock, int flags)
 	new->tsap = irttp_dup(self->tsap, new);
 	err = -EPERM; /* value does not seem to make sense. -arnd */
 	if (!new->tsap) {
-		IRDA_DEBUG(0, "%s(), dup failed!\n", __func__);
+		pr_debug("%s(), dup failed!\n", __func__);
 		kfree_skb(skb);
 		goto out;
 	}
@@ -971,7 +959,7 @@ static int irda_connect(struct socket *sock, struct sockaddr *uaddr,
 	struct irda_sock *self = irda_sk(sk);
 	int err;
 
-	IRDA_DEBUG(2, "%s(%p)\n", __func__, self);
+	pr_debug("%s(%p)\n", __func__, self);
 
 	lock_sock(sk);
 	/* Don't allow connect for Ultra sockets */
@@ -1007,13 +995,13 @@ static int irda_connect(struct socket *sock, struct sockaddr *uaddr,
 		/* Try to find one suitable */
 		err = irda_discover_daddr_and_lsap_sel(self, addr->sir_name);
 		if (err) {
-			IRDA_DEBUG(0, "%s(), auto-connect failed!\n", __func__);
+			pr_debug("%s(), auto-connect failed!\n", __func__);
 			goto out;
 		}
 	} else {
 		/* Use the one provided by the user */
 		self->daddr = addr->sir_addr;
-		IRDA_DEBUG(1, "%s(), daddr = %08x\n", __func__, self->daddr);
+		pr_debug("%s(), daddr = %08x\n", __func__, self->daddr);
 
 		/* If we don't have a valid service name, we assume the
 		 * user want to connect on a specific LSAP. Prevent
@@ -1023,7 +1011,7 @@ static int irda_connect(struct socket *sock, struct sockaddr *uaddr,
 			/* Query remote LM-IAS using service name */
 			err = irda_find_lsap_sel(self, addr->sir_name);
 			if (err) {
-				IRDA_DEBUG(0, "%s(), connect failed!\n", __func__);
+				pr_debug("%s(), connect failed!\n", __func__);
 				goto out;
 			}
 		} else {
@@ -1048,7 +1036,7 @@ static int irda_connect(struct socket *sock, struct sockaddr *uaddr,
 				    self->saddr, self->daddr, NULL,
 				    self->max_sdu_size_rx, NULL);
 	if (err) {
-		IRDA_DEBUG(0, "%s(), connect failed!\n", __func__);
+		pr_debug("%s(), connect failed!\n", __func__);
 		goto out;
 	}
 
@@ -1098,8 +1086,6 @@ static int irda_create(struct net *net, struct socket *sock, int protocol,
 	struct sock *sk;
 	struct irda_sock *self;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	if (net != &init_net)
 		return -EAFNOSUPPORT;
 
@@ -1119,7 +1105,7 @@ static int irda_create(struct net *net, struct socket *sock, int protocol,
 		return -ENOMEM;
 
 	self = irda_sk(sk);
-	IRDA_DEBUG(2, "%s() : self is %p\n", __func__, self);
+	pr_debug("%s() : self is %p\n", __func__, self);
 
 	init_waitqueue_head(&self->query_wait);
 
@@ -1181,7 +1167,7 @@ static int irda_create(struct net *net, struct socket *sock, int protocol,
  */
 static void irda_destroy_socket(struct irda_sock *self)
 {
-	IRDA_DEBUG(2, "%s(%p)\n", __func__, self);
+	pr_debug("%s(%p)\n", __func__, self);
 
 	/* Unregister with IrLMP */
 	irlmp_unregister_client(self->ckey);
@@ -1218,8 +1204,6 @@ static int irda_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	if (sk == NULL)
 		return 0;
 
@@ -1272,21 +1256,20 @@ static int irda_release(struct socket *sock)
 }
 
 /*
- * Function irda_sendmsg (iocb, sock, msg, len)
+ * Function irda_sendmsg (sock, msg, len)
  *
  *    Send message down to TinyTP. This function is used for both STREAM and
  *    SEQPACK services. This is possible since it forces the client to
  *    fragment the message if necessary
  */
-static int irda_sendmsg(struct kiocb *iocb, struct socket *sock,
-			struct msghdr *msg, size_t len)
+static int irda_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 {
 	struct sock *sk = sock->sk;
 	struct irda_sock *self;
 	struct sk_buff *skb;
 	int err = -EPIPE;
 
-	IRDA_DEBUG(4, "%s(), len=%zd\n", __func__, len);
+	pr_debug("%s(), len=%zd\n", __func__, len);
 
 	/* Note : socket.c set MSG_EOR on SEQPACKET sockets */
 	if (msg->msg_flags & ~(MSG_DONTWAIT | MSG_EOR | MSG_CMSG_COMPAT |
@@ -1322,8 +1305,8 @@ static int irda_sendmsg(struct kiocb *iocb, struct socket *sock,
 
 	/* Check that we don't send out too big frames */
 	if (len > self->max_data_size) {
-		IRDA_DEBUG(2, "%s(), Chopping frame from %zd to %d bytes!\n",
-			   __func__, len, self->max_data_size);
+		pr_debug("%s(), Chopping frame from %zd to %d bytes!\n",
+			 __func__, len, self->max_data_size);
 		len = self->max_data_size;
 	}
 
@@ -1335,7 +1318,7 @@ static int irda_sendmsg(struct kiocb *iocb, struct socket *sock,
 	skb_reserve(skb, self->max_header_size + 16);
 	skb_reset_transport_header(skb);
 	skb_put(skb, len);
-	err = memcpy_fromiovec(skb_transport_header(skb), msg->msg_iov, len);
+	err = memcpy_from_msg(skb_transport_header(skb), msg, len);
 	if (err) {
 		kfree_skb(skb);
 		goto out_err;
@@ -1347,7 +1330,7 @@ static int irda_sendmsg(struct kiocb *iocb, struct socket *sock,
 	 */
 	err = irttp_data_request(self->tsap, skb);
 	if (err) {
-		IRDA_DEBUG(0, "%s(), err=%d\n", __func__, err);
+		pr_debug("%s(), err=%d\n", __func__, err);
 		goto out_err;
 	}
 
@@ -1364,13 +1347,13 @@ out:
 }
 
 /*
- * Function irda_recvmsg_dgram (iocb, sock, msg, size, flags)
+ * Function irda_recvmsg_dgram (sock, msg, size, flags)
  *
  *    Try to receive message and copy it to user. The frame is discarded
  *    after being read, regardless of how much the user actually read
  */
-static int irda_recvmsg_dgram(struct kiocb *iocb, struct socket *sock,
-			      struct msghdr *msg, size_t size, int flags)
+static int irda_recvmsg_dgram(struct socket *sock, struct msghdr *msg,
+			      size_t size, int flags)
 {
 	struct sock *sk = sock->sk;
 	struct irda_sock *self = irda_sk(sk);
@@ -1378,8 +1361,6 @@ static int irda_recvmsg_dgram(struct kiocb *iocb, struct socket *sock,
 	size_t copied;
 	int err;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
 				flags & MSG_DONTWAIT, &err);
 	if (!skb)
@@ -1389,12 +1370,12 @@ static int irda_recvmsg_dgram(struct kiocb *iocb, struct socket *sock,
 	copied = skb->len;
 
 	if (copied > size) {
-		IRDA_DEBUG(2, "%s(), Received truncated frame (%zd < %zd)!\n",
-			   __func__, copied, size);
+		pr_debug("%s(), Received truncated frame (%zd < %zd)!\n",
+			 __func__, copied, size);
 		copied = size;
 		msg->msg_flags |= MSG_TRUNC;
 	}
-	skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	skb_copy_datagram_msg(skb, 0, msg, copied);
 
 	skb_free_datagram(sk, skb);
 
@@ -1406,7 +1387,7 @@ static int irda_recvmsg_dgram(struct kiocb *iocb, struct socket *sock,
 	 */
 	if (self->rx_flow == FLOW_STOP) {
 		if ((atomic_read(&sk->sk_rmem_alloc) << 2) <= sk->sk_rcvbuf) {
-			IRDA_DEBUG(2, "%s(), Starting IrTTP\n", __func__);
+			pr_debug("%s(), Starting IrTTP\n", __func__);
 			self->rx_flow = FLOW_START;
 			irttp_flow_request(self->tsap, FLOW_START);
 		}
@@ -1416,10 +1397,10 @@ static int irda_recvmsg_dgram(struct kiocb *iocb, struct socket *sock,
 }
 
 /*
- * Function irda_recvmsg_stream (iocb, sock, msg, size, flags)
+ * Function irda_recvmsg_stream (sock, msg, size, flags)
  */
-static int irda_recvmsg_stream(struct kiocb *iocb, struct socket *sock,
-			       struct msghdr *msg, size_t size, int flags)
+static int irda_recvmsg_stream(struct socket *sock, struct msghdr *msg,
+			       size_t size, int flags)
 {
 	struct sock *sk = sock->sk;
 	struct irda_sock *self = irda_sk(sk);
@@ -1428,8 +1409,6 @@ static int irda_recvmsg_stream(struct kiocb *iocb, struct socket *sock,
 	int target, err;
 	long timeo;
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	if ((err = sock_error(sk)) < 0)
 		return err;
 
@@ -1486,7 +1465,7 @@ static int irda_recvmsg_stream(struct kiocb *iocb, struct socket *sock,
 		}
 
 		chunk = min_t(unsigned int, skb->len, size);
-		if (memcpy_toiovec(msg->msg_iov, skb->data, chunk)) {
+		if (memcpy_to_msg(msg, skb->data, chunk)) {
 			skb_queue_head(&sk->sk_receive_queue, skb);
 			if (copied == 0)
 				copied = -EFAULT;
@@ -1501,15 +1480,15 @@ static int irda_recvmsg_stream(struct kiocb *iocb, struct socket *sock,
 
 			/* put the skb back if we didn't use it up.. */
 			if (skb->len) {
-				IRDA_DEBUG(1, "%s(), back on q!\n",
-					   __func__);
+				pr_debug("%s(), back on q!\n",
+					 __func__);
 				skb_queue_head(&sk->sk_receive_queue, skb);
 				break;
 			}
 
 			kfree_skb(skb);
 		} else {
-			IRDA_DEBUG(0, "%s() questionable!?\n", __func__);
+			pr_debug("%s() questionable!?\n", __func__);
 
 			/* put message back and return */
 			skb_queue_head(&sk->sk_receive_queue, skb);
@@ -1525,7 +1504,7 @@ static int irda_recvmsg_stream(struct kiocb *iocb, struct socket *sock,
 	 */
 	if (self->rx_flow == FLOW_STOP) {
 		if ((atomic_read(&sk->sk_rmem_alloc) << 2) <= sk->sk_rcvbuf) {
-			IRDA_DEBUG(2, "%s(), Starting IrTTP\n", __func__);
+			pr_debug("%s(), Starting IrTTP\n", __func__);
 			self->rx_flow = FLOW_START;
 			irttp_flow_request(self->tsap, FLOW_START);
 		}
@@ -1535,21 +1514,21 @@ static int irda_recvmsg_stream(struct kiocb *iocb, struct socket *sock,
 }
 
 /*
- * Function irda_sendmsg_dgram (iocb, sock, msg, len)
+ * Function irda_sendmsg_dgram (sock, msg, len)
  *
  *    Send message down to TinyTP for the unreliable sequenced
  *    packet service...
  *
  */
-static int irda_sendmsg_dgram(struct kiocb *iocb, struct socket *sock,
-			      struct msghdr *msg, size_t len)
+static int irda_sendmsg_dgram(struct socket *sock, struct msghdr *msg,
+			      size_t len)
 {
 	struct sock *sk = sock->sk;
 	struct irda_sock *self;
 	struct sk_buff *skb;
 	int err;
 
-	IRDA_DEBUG(4, "%s(), len=%zd\n", __func__, len);
+	pr_debug("%s(), len=%zd\n", __func__, len);
 
 	if (msg->msg_flags & ~(MSG_DONTWAIT|MSG_CMSG_COMPAT))
 		return -EINVAL;
@@ -1573,9 +1552,8 @@ static int irda_sendmsg_dgram(struct kiocb *iocb, struct socket *sock,
 	 * service, so we have no fragmentation and no coalescence
 	 */
 	if (len > self->max_data_size) {
-		IRDA_DEBUG(0, "%s(), Warning to much data! "
-			   "Chopping frame from %zd to %d bytes!\n",
-			   __func__, len, self->max_data_size);
+		pr_debug("%s(), Warning too much data! Chopping frame from %zd to %d bytes!\n",
+			 __func__, len, self->max_data_size);
 		len = self->max_data_size;
 	}
 
@@ -1588,9 +1566,9 @@ static int irda_sendmsg_dgram(struct kiocb *iocb, struct socket *sock,
 	skb_reserve(skb, self->max_header_size);
 	skb_reset_transport_header(skb);
 
-	IRDA_DEBUG(4, "%s(), appending user data\n", __func__);
+	pr_debug("%s(), appending user data\n", __func__);
 	skb_put(skb, len);
-	err = memcpy_fromiovec(skb_transport_header(skb), msg->msg_iov, len);
+	err = memcpy_from_msg(skb_transport_header(skb), msg, len);
 	if (err) {
 		kfree_skb(skb);
 		goto out;
@@ -1602,7 +1580,7 @@ static int irda_sendmsg_dgram(struct kiocb *iocb, struct socket *sock,
 	 */
 	err = irttp_udata_request(self->tsap, skb);
 	if (err) {
-		IRDA_DEBUG(0, "%s(), err=%d\n", __func__, err);
+		pr_debug("%s(), err=%d\n", __func__, err);
 		goto out;
 	}
 
@@ -1615,14 +1593,14 @@ out:
 }
 
 /*
- * Function irda_sendmsg_ultra (iocb, sock, msg, len)
+ * Function irda_sendmsg_ultra (sock, msg, len)
  *
  *    Send message down to IrLMP for the unreliable Ultra
  *    packet service...
  */
 #ifdef CONFIG_IRDA_ULTRA
-static int irda_sendmsg_ultra(struct kiocb *iocb, struct socket *sock,
-			      struct msghdr *msg, size_t len)
+static int irda_sendmsg_ultra(struct socket *sock, struct msghdr *msg,
+			      size_t len)
 {
 	struct sock *sk = sock->sk;
 	struct irda_sock *self;
@@ -1631,7 +1609,7 @@ static int irda_sendmsg_ultra(struct kiocb *iocb, struct socket *sock,
 	struct sk_buff *skb;
 	int err;
 
-	IRDA_DEBUG(4, "%s(), len=%zd\n", __func__, len);
+	pr_debug("%s(), len=%zd\n", __func__, len);
 
 	err = -EINVAL;
 	if (msg->msg_flags & ~(MSG_DONTWAIT|MSG_CMSG_COMPAT))
@@ -1659,7 +1637,8 @@ static int irda_sendmsg_ultra(struct kiocb *iocb, struct socket *sock,
 
 		pid = addr->sir_lsap_sel;
 		if (pid & 0x80) {
-			IRDA_DEBUG(0, "%s(), extension in PID not supp!\n", __func__);
+			pr_debug("%s(), extension in PID not supp!\n",
+				 __func__);
 			err = -EOPNOTSUPP;
 			goto out;
 		}
@@ -1668,8 +1647,8 @@ static int irda_sendmsg_ultra(struct kiocb *iocb, struct socket *sock,
 		 * port. Jean II */
 		if ((self->lsap == NULL) ||
 		    (sk->sk_state != TCP_ESTABLISHED)) {
-			IRDA_DEBUG(0, "%s(), socket not bound to Ultra PID.\n",
-				   __func__);
+			pr_debug("%s(), socket not bound to Ultra PID.\n",
+				 __func__);
 			err = -ENOTCONN;
 			goto out;
 		}
@@ -1682,9 +1661,8 @@ static int irda_sendmsg_ultra(struct kiocb *iocb, struct socket *sock,
 	 * service, so we have no fragmentation and no coalescence
 	 */
 	if (len > self->max_data_size) {
-		IRDA_DEBUG(0, "%s(), Warning to much data! "
-			   "Chopping frame from %zd to %d bytes!\n",
-			   __func__, len, self->max_data_size);
+		pr_debug("%s(), Warning too much data! Chopping frame from %zd to %d bytes!\n",
+			 __func__, len, self->max_data_size);
 		len = self->max_data_size;
 	}
 
@@ -1697,9 +1675,9 @@ static int irda_sendmsg_ultra(struct kiocb *iocb, struct socket *sock,
 	skb_reserve(skb, self->max_header_size);
 	skb_reset_transport_header(skb);
 
-	IRDA_DEBUG(4, "%s(), appending user data\n", __func__);
+	pr_debug("%s(), appending user data\n", __func__);
 	skb_put(skb, len);
-	err = memcpy_fromiovec(skb_transport_header(skb), msg->msg_iov, len);
+	err = memcpy_from_msg(skb_transport_header(skb), msg, len);
 	if (err) {
 		kfree_skb(skb);
 		goto out;
@@ -1708,7 +1686,7 @@ static int irda_sendmsg_ultra(struct kiocb *iocb, struct socket *sock,
 	err = irlmp_connless_data_request((bound ? self->lsap : NULL),
 					  skb, pid);
 	if (err)
-		IRDA_DEBUG(0, "%s(), err=%d\n", __func__, err);
+		pr_debug("%s(), err=%d\n", __func__, err);
 out:
 	release_sock(sk);
 	return err ? : len;
@@ -1723,7 +1701,7 @@ static int irda_shutdown(struct socket *sock, int how)
 	struct sock *sk = sock->sk;
 	struct irda_sock *self = irda_sk(sk);
 
-	IRDA_DEBUG(1, "%s(%p)\n", __func__, self);
+	pr_debug("%s(%p)\n", __func__, self);
 
 	lock_sock(sk);
 
@@ -1762,8 +1740,6 @@ static unsigned int irda_poll(struct file * file, struct socket *sock,
 	struct irda_sock *self = irda_sk(sk);
 	unsigned int mask;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	poll_wait(file, sk_sleep(sk), wait);
 	mask = 0;
 
@@ -1771,13 +1747,13 @@ static unsigned int irda_poll(struct file * file, struct socket *sock,
 	if (sk->sk_err)
 		mask |= POLLERR;
 	if (sk->sk_shutdown & RCV_SHUTDOWN) {
-		IRDA_DEBUG(0, "%s(), POLLHUP\n", __func__);
+		pr_debug("%s(), POLLHUP\n", __func__);
 		mask |= POLLHUP;
 	}
 
 	/* Readable? */
 	if (!skb_queue_empty(&sk->sk_receive_queue)) {
-		IRDA_DEBUG(4, "Socket is readable\n");
+		pr_debug("Socket is readable\n");
 		mask |= POLLIN | POLLRDNORM;
 	}
 
@@ -1785,7 +1761,7 @@ static unsigned int irda_poll(struct file * file, struct socket *sock,
 	switch (sk->sk_type) {
 	case SOCK_STREAM:
 		if (sk->sk_state == TCP_CLOSE) {
-			IRDA_DEBUG(0, "%s(), POLLHUP\n", __func__);
+			pr_debug("%s(), POLLHUP\n", __func__);
 			mask |= POLLHUP;
 		}
 
@@ -1823,7 +1799,7 @@ static int irda_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 	struct sock *sk = sock->sk;
 	int err;
 
-	IRDA_DEBUG(4, "%s(), cmd=%#x\n", __func__, cmd);
+	pr_debug("%s(), cmd=%#x\n", __func__, cmd);
 
 	err = -EINVAL;
 	switch (cmd) {
@@ -1864,7 +1840,7 @@ static int irda_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 	case SIOCSIFMETRIC:
 		break;
 	default:
-		IRDA_DEBUG(1, "%s(), doing device ioctl!\n", __func__);
+		pr_debug("%s(), doing device ioctl!\n", __func__);
 		err = -ENOIOCTLCMD;
 	}
 
@@ -1900,7 +1876,7 @@ static int irda_setsockopt(struct socket *sock, int level, int optname,
 	struct ias_attrib *	ias_attr;	/* Attribute in IAS object */
 	int opt, free_ias = 0, err = 0;
 
-	IRDA_DEBUG(2, "%s(%p)\n", __func__, self);
+	pr_debug("%s(%p)\n", __func__, self);
 
 	if (level != SOL_IRLMP)
 		return -ENOPROTOOPT;
@@ -2100,7 +2076,8 @@ static int irda_setsockopt(struct socket *sock, int level, int optname,
 
 		/* Check is the user space own the object */
 		if(ias_attr->value->owner != IAS_USER_ATTR) {
-			IRDA_DEBUG(1, "%s(), attempting to delete a kernel attribute\n", __func__);
+			pr_debug("%s(), attempting to delete a kernel attribute\n",
+				 __func__);
 			kfree(ias_opt);
 			err = -EPERM;
 			goto out;
@@ -2123,12 +2100,12 @@ static int irda_setsockopt(struct socket *sock, int level, int optname,
 
 		/* Only possible for a seqpacket service (TTP with SAR) */
 		if (sk->sk_type != SOCK_SEQPACKET) {
-			IRDA_DEBUG(2, "%s(), setting max_sdu_size = %d\n",
-				   __func__, opt);
+			pr_debug("%s(), setting max_sdu_size = %d\n",
+				 __func__, opt);
 			self->max_sdu_size_rx = opt;
 		} else {
-			IRDA_WARNING("%s: not allowed to set MAXSDUSIZE for this socket type!\n",
-				     __func__);
+			net_warn_ratelimited("%s: not allowed to set MAXSDUSIZE for this socket type!\n",
+					     __func__);
 			err = -ENOPROTOOPT;
 			goto out;
 		}
@@ -2256,7 +2233,7 @@ static int irda_getsockopt(struct socket *sock, int level, int optname,
 	int err = 0;
 	int offset, total;
 
-	IRDA_DEBUG(2, "%s(%p)\n", __func__, self);
+	pr_debug("%s(%p)\n", __func__, self);
 
 	if (level != SOL_IRLMP)
 		return -ENOPROTOOPT;
@@ -2439,8 +2416,8 @@ bed:
 
 		/* Check that we can proceed with IAP */
 		if (self->iriap) {
-			IRDA_WARNING("%s: busy with a previous query\n",
-				     __func__);
+			net_warn_ratelimited("%s: busy with a previous query\n",
+					     __func__);
 			kfree(ias_opt);
 			err = -EBUSY;
 			goto out;
@@ -2544,7 +2521,8 @@ bed:
 
 		/* Wait until a node is discovered */
 		if (!self->cachedaddr) {
-			IRDA_DEBUG(1, "%s(), nothing discovered yet, going to sleep...\n", __func__);
+			pr_debug("%s(), nothing discovered yet, going to sleep...\n",
+				 __func__);
 
 			/* Set watchdog timer to expire in <val> ms. */
 			self->errno = 0;
@@ -2560,14 +2538,14 @@ bed:
 			/* If watchdog is still activated, kill it! */
 			del_timer(&(self->watchdog));
 
-			IRDA_DEBUG(1, "%s(), ...waking up !\n", __func__);
+			pr_debug("%s(), ...waking up !\n", __func__);
 
 			if (err != 0)
 				goto out;
 		}
 		else
-			IRDA_DEBUG(1, "%s(), found immediately !\n",
-				   __func__);
+			pr_debug("%s(), found immediately !\n",
+				 __func__);
 
 		/* Tell IrLMP that we have been notified */
 		irlmp_update_client(self->ckey, self->mask.word,
diff --git a/net/irda/discovery.c b/net/irda/discovery.c
index 6786e7f193d2..364d70aed068 100644
--- a/net/irda/discovery.c
+++ b/net/irda/discovery.c
@@ -112,8 +112,6 @@ void irlmp_add_discovery_log(hashbin_t *cachelog, hashbin_t *log)
 {
 	discovery_t *discovery;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	/*
 	 *  If log is missing this means that IrLAP was unable to perform the
 	 *  discovery, so restart discovery again with just the half timeout
@@ -159,8 +157,6 @@ void irlmp_expire_discoveries(hashbin_t *log, __u32 saddr, int force)
 	int			i = 0;		/* How many we expired */
 
 	IRDA_ASSERT(log != NULL, return;);
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	spin_lock_irqsave(&log->hb_spinlock, flags);
 
 	discovery = (discovery_t *) hashbin_get_first(log);
@@ -232,10 +228,10 @@ void irlmp_dump_discoveries(hashbin_t *log)
 
 	discovery = (discovery_t *) hashbin_get_first(log);
 	while (discovery != NULL) {
-		IRDA_DEBUG(0, "Discovery:\n");
-		IRDA_DEBUG(0, "  daddr=%08x\n", discovery->data.daddr);
-		IRDA_DEBUG(0, "  saddr=%08x\n", discovery->data.saddr);
-		IRDA_DEBUG(0, "  nickname=%s\n", discovery->data.info);
+		pr_debug("Discovery:\n");
+		pr_debug("  daddr=%08x\n", discovery->data.daddr);
+		pr_debug("  saddr=%08x\n", discovery->data.saddr);
+		pr_debug("  nickname=%s\n", discovery->data.info);
 
 		discovery = (discovery_t *) hashbin_get_next(log);
 	}
diff --git a/net/irda/ircomm/ircomm_core.c b/net/irda/ircomm/ircomm_core.c
index 4490a675b1bb..3af219545f6d 100644
--- a/net/irda/ircomm/ircomm_core.c
+++ b/net/irda/ircomm/ircomm_core.c
@@ -69,7 +69,8 @@ static int __init ircomm_init(void)
 {
 	ircomm = hashbin_new(HB_LOCK);
 	if (ircomm == NULL) {
-		IRDA_ERROR("%s(), can't allocate hashbin!\n", __func__);
+		net_err_ratelimited("%s(), can't allocate hashbin!\n",
+				    __func__);
 		return -ENOMEM;
 	}
 
@@ -83,15 +84,13 @@ static int __init ircomm_init(void)
 	}
 #endif /* CONFIG_PROC_FS */
 
-	IRDA_MESSAGE("IrCOMM protocol (Dag Brattli)\n");
+	net_info_ratelimited("IrCOMM protocol (Dag Brattli)\n");
 
 	return 0;
 }
 
 static void __exit ircomm_cleanup(void)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	hashbin_delete(ircomm, (FREE_FUNC) __ircomm_close);
 
 #ifdef CONFIG_PROC_FS
@@ -110,8 +109,8 @@ struct ircomm_cb *ircomm_open(notify_t *notify, __u8 service_type, int line)
 	struct ircomm_cb *self = NULL;
 	int ret;
 
-	IRDA_DEBUG(2, "%s(), service_type=0x%02x\n", __func__ ,
-		   service_type);
+	pr_debug("%s(), service_type=0x%02x\n", __func__ ,
+		 service_type);
 
 	IRDA_ASSERT(ircomm != NULL, return NULL;);
 
@@ -154,8 +153,6 @@ EXPORT_SYMBOL(ircomm_open);
  */
 static int __ircomm_close(struct ircomm_cb *self)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	/* Disconnect link if any */
 	ircomm_do_event(self, IRCOMM_DISCONNECT_REQUEST, NULL, NULL);
 
@@ -190,8 +187,6 @@ int ircomm_close(struct ircomm_cb *self)
 	IRDA_ASSERT(self != NULL, return -EIO;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return -EIO;);
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	entry = hashbin_remove(ircomm, self->line, NULL);
 
 	IRDA_ASSERT(entry == self, return -1;);
@@ -215,8 +210,6 @@ int ircomm_connect_request(struct ircomm_cb *self, __u8 dlsap_sel,
 	struct ircomm_info info;
 	int ret;
 
-	IRDA_DEBUG(2 , "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return -1;);
 
@@ -242,8 +235,6 @@ EXPORT_SYMBOL(ircomm_connect_request);
 void ircomm_connect_indication(struct ircomm_cb *self, struct sk_buff *skb,
 			       struct ircomm_info *info)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	/*
 	 * If there are any data hiding in the control channel, we must
 	 * deliver it first. The side effect is that the control channel
@@ -254,7 +245,7 @@ void ircomm_connect_indication(struct ircomm_cb *self, struct sk_buff *skb,
 						info->qos, info->max_data_size,
 						info->max_header_size, skb);
 	else {
-		IRDA_DEBUG(0, "%s(), missing handler\n", __func__ );
+		pr_debug("%s(), missing handler\n", __func__);
 	}
 }
 
@@ -271,8 +262,6 @@ int ircomm_connect_response(struct ircomm_cb *self, struct sk_buff *userdata)
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return -1;);
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	ret = ircomm_do_event(self, IRCOMM_CONNECT_RESPONSE, userdata, NULL);
 
 	return ret;
@@ -289,15 +278,13 @@ EXPORT_SYMBOL(ircomm_connect_response);
 void ircomm_connect_confirm(struct ircomm_cb *self, struct sk_buff *skb,
 			    struct ircomm_info *info)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	if (self->notify.connect_confirm )
 		self->notify.connect_confirm(self->notify.instance,
 					     self, info->qos,
 					     info->max_data_size,
 					     info->max_header_size, skb);
 	else {
-		IRDA_DEBUG(0, "%s(), missing handler\n", __func__ );
+		pr_debug("%s(), missing handler\n", __func__);
 	}
 }
 
@@ -311,8 +298,6 @@ int ircomm_data_request(struct ircomm_cb *self, struct sk_buff *skb)
 {
 	int ret;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -EFAULT;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return -EFAULT;);
 	IRDA_ASSERT(skb != NULL, return -EFAULT;);
@@ -332,14 +317,12 @@ EXPORT_SYMBOL(ircomm_data_request);
  */
 void ircomm_data_indication(struct ircomm_cb *self, struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(skb->len > 0, return;);
 
 	if (self->notify.data_indication)
 		self->notify.data_indication(self->notify.instance, self, skb);
 	else {
-		IRDA_DEBUG(0, "%s(), missing handler\n", __func__ );
+		pr_debug("%s(), missing handler\n", __func__);
 	}
 }
 
@@ -364,8 +347,8 @@ void ircomm_process_data(struct ircomm_cb *self, struct sk_buff *skb)
 	 * fine
 	 */
 	if (unlikely(skb->len < (clen + 1))) {
-		IRDA_DEBUG(2, "%s() throwing away illegal frame\n",
-			   __func__ );
+		pr_debug("%s() throwing away illegal frame\n",
+			 __func__);
 		return;
 	}
 
@@ -383,8 +366,8 @@ void ircomm_process_data(struct ircomm_cb *self, struct sk_buff *skb)
 	if (skb->len)
 		ircomm_data_indication(self, skb);
 	else {
-		IRDA_DEBUG(4, "%s(), data was control info only!\n",
-			   __func__ );
+		pr_debug("%s(), data was control info only!\n",
+			 __func__);
 	}
 }
 
@@ -398,8 +381,6 @@ int ircomm_control_request(struct ircomm_cb *self, struct sk_buff *skb)
 {
 	int ret;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -EFAULT;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return -EFAULT;);
 	IRDA_ASSERT(skb != NULL, return -EFAULT;);
@@ -420,8 +401,6 @@ EXPORT_SYMBOL(ircomm_control_request);
 static void ircomm_control_indication(struct ircomm_cb *self,
 				      struct sk_buff *skb, int clen)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	/* Use udata for delivering data on the control channel */
 	if (self->notify.udata_indication) {
 		struct sk_buff *ctrl_skb;
@@ -441,7 +420,7 @@ static void ircomm_control_indication(struct ircomm_cb *self,
 		 * see ircomm_tty_control_indication(). */
 		dev_kfree_skb(ctrl_skb);
 	} else {
-		IRDA_DEBUG(0, "%s(), missing handler\n", __func__ );
+		pr_debug("%s(), missing handler\n", __func__);
 	}
 }
 
@@ -456,8 +435,6 @@ int ircomm_disconnect_request(struct ircomm_cb *self, struct sk_buff *userdata)
 	struct ircomm_info info;
 	int ret;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return -1;);
 
@@ -477,15 +454,13 @@ EXPORT_SYMBOL(ircomm_disconnect_request);
 void ircomm_disconnect_indication(struct ircomm_cb *self, struct sk_buff *skb,
 				  struct ircomm_info *info)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(info != NULL, return;);
 
 	if (self->notify.disconnect_indication) {
 		self->notify.disconnect_indication(self->notify.instance, self,
 						   info->reason, skb);
 	} else {
-		IRDA_DEBUG(0, "%s(), missing handler\n", __func__ );
+		pr_debug("%s(), missing handler\n", __func__);
 	}
 }
 
@@ -497,8 +472,6 @@ void ircomm_disconnect_indication(struct ircomm_cb *self, struct sk_buff *skb,
  */
 void ircomm_flow_request(struct ircomm_cb *self, LOCAL_FLOW flow)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return;);
 
diff --git a/net/irda/ircomm/ircomm_event.c b/net/irda/ircomm/ircomm_event.c
index b172c6522328..b0730ac9f388 100644
--- a/net/irda/ircomm/ircomm_event.c
+++ b/net/irda/ircomm/ircomm_event.c
@@ -54,8 +54,7 @@ const char *const ircomm_state[] = {
 	"IRCOMM_CONN",
 };
 
-#ifdef CONFIG_IRDA_DEBUG
-static const char *const ircomm_event[] = {
+static const char *const ircomm_event[] __maybe_unused = {
 	"IRCOMM_CONNECT_REQUEST",
 	"IRCOMM_CONNECT_RESPONSE",
 	"IRCOMM_TTP_CONNECT_INDICATION",
@@ -73,7 +72,6 @@ static const char *const ircomm_event[] = {
 	"IRCOMM_CONTROL_REQUEST",
 	"IRCOMM_CONTROL_INDICATION",
 };
-#endif /* CONFIG_IRDA_DEBUG */
 
 static int (*state[])(struct ircomm_cb *self, IRCOMM_EVENT event,
 		      struct sk_buff *skb, struct ircomm_info *info) =
@@ -106,8 +104,8 @@ static int ircomm_state_idle(struct ircomm_cb *self, IRCOMM_EVENT event,
 		ircomm_connect_indication(self, skb, info);
 		break;
 	default:
-		IRDA_DEBUG(4, "%s(), unknown event: %s\n", __func__ ,
-			   ircomm_event[event]);
+		pr_debug("%s(), unknown event: %s\n", __func__ ,
+			 ircomm_event[event]);
 		ret = -EINVAL;
 	}
 	return ret;
@@ -136,8 +134,8 @@ static int ircomm_state_waiti(struct ircomm_cb *self, IRCOMM_EVENT event,
 		ircomm_disconnect_indication(self, skb, info);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), unknown event: %s\n", __func__ ,
-			   ircomm_event[event]);
+		pr_debug("%s(), unknown event: %s\n", __func__ ,
+			 ircomm_event[event]);
 		ret = -EINVAL;
 	}
 	return ret;
@@ -169,8 +167,8 @@ static int ircomm_state_waitr(struct ircomm_cb *self, IRCOMM_EVENT event,
 		ircomm_disconnect_indication(self, skb, info);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), unknown event = %s\n", __func__ ,
-			   ircomm_event[event]);
+		pr_debug("%s(), unknown event = %s\n", __func__ ,
+			 ircomm_event[event]);
 		ret = -EINVAL;
 	}
 	return ret;
@@ -211,8 +209,8 @@ static int ircomm_state_conn(struct ircomm_cb *self, IRCOMM_EVENT event,
 		ret = self->issue.disconnect_request(self, skb, info);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), unknown event = %s\n", __func__ ,
-			   ircomm_event[event]);
+		pr_debug("%s(), unknown event = %s\n", __func__ ,
+			 ircomm_event[event]);
 		ret = -EINVAL;
 	}
 	return ret;
@@ -227,8 +225,8 @@ static int ircomm_state_conn(struct ircomm_cb *self, IRCOMM_EVENT event,
 int ircomm_do_event(struct ircomm_cb *self, IRCOMM_EVENT event,
 		    struct sk_buff *skb, struct ircomm_info *info)
 {
-	IRDA_DEBUG(4, "%s: state=%s, event=%s\n", __func__ ,
-		   ircomm_state[self->state], ircomm_event[event]);
+	pr_debug("%s: state=%s, event=%s\n", __func__ ,
+		 ircomm_state[self->state], ircomm_event[event]);
 
 	return (*state[self->state])(self, event, skb, info);
 }
@@ -243,6 +241,6 @@ void ircomm_next_state(struct ircomm_cb *self, IRCOMM_STATE state)
 {
 	self->state = state;
 
-	IRDA_DEBUG(4, "%s: next state=%s, service type=%d\n", __func__ ,
-		   ircomm_state[self->state], self->service_type);
+	pr_debug("%s: next state=%s, service type=%d\n", __func__ ,
+		 ircomm_state[self->state], self->service_type);
 }
diff --git a/net/irda/ircomm/ircomm_lmp.c b/net/irda/ircomm/ircomm_lmp.c
index 6536114adf37..e4cc847bb933 100644
--- a/net/irda/ircomm/ircomm_lmp.c
+++ b/net/irda/ircomm/ircomm_lmp.c
@@ -52,8 +52,6 @@ static int ircomm_lmp_connect_request(struct ircomm_cb *self,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	/* Don't forget to refcount it - should be NULL anyway */
 	if(userdata)
 		skb_get(userdata);
@@ -74,8 +72,6 @@ static int ircomm_lmp_connect_response(struct ircomm_cb *self,
 {
 	struct sk_buff *tx_skb;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	/* Any userdata supplied? */
 	if (userdata == NULL) {
 		tx_skb = alloc_skb(LMP_MAX_HEADER, GFP_ATOMIC);
@@ -107,8 +103,6 @@ static int ircomm_lmp_disconnect_request(struct ircomm_cb *self,
 	struct sk_buff *tx_skb;
 	int ret;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	if (!userdata) {
 		tx_skb = alloc_skb(LMP_MAX_HEADER, GFP_ATOMIC);
 		if (!tx_skb)
@@ -144,13 +138,11 @@ static void ircomm_lmp_flow_control(struct sk_buff *skb)
 
 	cb = (struct irda_skb_cb *) skb->cb;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	line = cb->line;
 
 	self = (struct ircomm_cb *) hashbin_lock_find(ircomm, line, NULL);
 	if (!self) {
-		IRDA_DEBUG(2, "%s(), didn't find myself\n", __func__ );
+		pr_debug("%s(), didn't find myself\n", __func__);
 		return;
 	}
 
@@ -160,7 +152,7 @@ static void ircomm_lmp_flow_control(struct sk_buff *skb)
 	self->pkt_count--;
 
 	if ((self->pkt_count < 2) && (self->flow_status == FLOW_STOP)) {
-		IRDA_DEBUG(2, "%s(), asking TTY to start again!\n", __func__ );
+		pr_debug("%s(), asking TTY to start again!\n", __func__);
 		self->flow_status = FLOW_START;
 		if (self->notify.flow_indication)
 			self->notify.flow_indication(self->notify.instance,
@@ -187,7 +179,7 @@ static int ircomm_lmp_data_request(struct ircomm_cb *self,
 
 	cb->line = self->line;
 
-	IRDA_DEBUG(4, "%s(), sending frame\n", __func__ );
+	pr_debug("%s(), sending frame\n", __func__);
 
 	/* Don't forget to refcount it - see ircomm_tty_do_softint() */
 	skb_get(skb);
@@ -196,7 +188,7 @@ static int ircomm_lmp_data_request(struct ircomm_cb *self,
 	skb->destructor = ircomm_lmp_flow_control;
 
 	if ((self->pkt_count++ > 7) && (self->flow_status == FLOW_START)) {
-		IRDA_DEBUG(2, "%s(), asking TTY to slow down!\n", __func__ );
+		pr_debug("%s(), asking TTY to slow down!\n", __func__);
 		self->flow_status = FLOW_STOP;
 		if (self->notify.flow_indication)
 			self->notify.flow_indication(self->notify.instance,
@@ -204,7 +196,7 @@ static int ircomm_lmp_data_request(struct ircomm_cb *self,
 	}
 	ret = irlmp_data_request(self->lsap, skb);
 	if (ret) {
-		IRDA_ERROR("%s(), failed\n", __func__);
+		net_err_ratelimited("%s(), failed\n", __func__);
 		/* irlmp_data_request already free the packet */
 	}
 
@@ -222,8 +214,6 @@ static int ircomm_lmp_data_indication(void *instance, void *sap,
 {
 	struct ircomm_cb *self = (struct ircomm_cb *) instance;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return -1;);
 	IRDA_ASSERT(skb != NULL, return -1;);
@@ -252,8 +242,6 @@ static void ircomm_lmp_connect_confirm(void *instance, void *sap,
 	struct ircomm_cb *self = (struct ircomm_cb *) instance;
 	struct ircomm_info info;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return;);
 	IRDA_ASSERT(skb != NULL, return;);
@@ -285,8 +273,6 @@ static void ircomm_lmp_connect_indication(void *instance, void *sap,
 	struct ircomm_cb *self = (struct ircomm_cb *)instance;
 	struct ircomm_info info;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return;);
 	IRDA_ASSERT(skb != NULL, return;);
@@ -315,8 +301,6 @@ static void ircomm_lmp_disconnect_indication(void *instance, void *sap,
 	struct ircomm_cb *self = (struct ircomm_cb *) instance;
 	struct ircomm_info info;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return;);
 
@@ -338,8 +322,6 @@ int ircomm_open_lsap(struct ircomm_cb *self)
 {
 	notify_t notify;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	/* Register callbacks */
 	irda_notify_init(&notify);
 	notify.data_indication       = ircomm_lmp_data_indication;
@@ -351,7 +333,7 @@ int ircomm_open_lsap(struct ircomm_cb *self)
 
 	self->lsap = irlmp_open_lsap(LSAP_ANY, &notify, 0);
 	if (!self->lsap) {
-		IRDA_DEBUG(0,"%sfailed to allocate tsap\n", __func__ );
+		pr_debug("%sfailed to allocate tsap\n", __func__);
 		return -1;
 	}
 	self->slsap_sel = self->lsap->slsap_sel;
diff --git a/net/irda/ircomm/ircomm_param.c b/net/irda/ircomm/ircomm_param.c
index f80b1a6a244b..3c4caa60c926 100644
--- a/net/irda/ircomm/ircomm_param.c
+++ b/net/irda/ircomm/ircomm_param.c
@@ -61,12 +61,12 @@ static int ircomm_param_dte(void *instance, irda_param_t *param, int get);
 static int ircomm_param_dce(void *instance, irda_param_t *param, int get);
 static int ircomm_param_poll(void *instance, irda_param_t *param, int get);
 
-static pi_minor_info_t pi_minor_call_table_common[] = {
+static const pi_minor_info_t pi_minor_call_table_common[] = {
 	{ ircomm_param_service_type, PV_INT_8_BITS },
 	{ ircomm_param_port_type,    PV_INT_8_BITS },
 	{ ircomm_param_port_name,    PV_STRING }
 };
-static pi_minor_info_t pi_minor_call_table_non_raw[] = {
+static const pi_minor_info_t pi_minor_call_table_non_raw[] = {
 	{ ircomm_param_data_rate,    PV_INT_32_BITS | PV_BIG_ENDIAN },
 	{ ircomm_param_data_format,  PV_INT_8_BITS },
 	{ ircomm_param_flow_control, PV_INT_8_BITS },
@@ -74,13 +74,13 @@ static pi_minor_info_t pi_minor_call_table_non_raw[] = {
 	{ ircomm_param_enq_ack,      PV_INT_16_BITS },
 	{ ircomm_param_line_status,  PV_INT_8_BITS }
 };
-static pi_minor_info_t pi_minor_call_table_9_wire[] = {
+static const pi_minor_info_t pi_minor_call_table_9_wire[] = {
 	{ ircomm_param_dte,          PV_INT_8_BITS },
 	{ ircomm_param_dce,          PV_INT_8_BITS },
 	{ ircomm_param_poll,         PV_NO_VALUE },
 };
 
-static pi_major_info_t pi_major_call_table[] = {
+static const pi_major_info_t pi_major_call_table[] = {
 	{ pi_minor_call_table_common,  3 },
 	{ pi_minor_call_table_non_raw, 6 },
 	{ pi_minor_call_table_9_wire,  3 }
@@ -101,8 +101,6 @@ int ircomm_param_request(struct ircomm_tty_cb *self, __u8 pi, int flush)
 	struct sk_buff *skb;
 	int count;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return -1;);
 
@@ -130,7 +128,8 @@ int ircomm_param_request(struct ircomm_tty_cb *self, __u8 pi, int flush)
 	count = irda_param_insert(self, pi, skb_tail_pointer(skb),
 				  skb_tailroom(skb), &ircomm_param_info);
 	if (count < 0) {
-		IRDA_WARNING("%s(), no room for parameter!\n", __func__);
+		net_warn_ratelimited("%s(), no room for parameter!\n",
+				     __func__);
 		spin_unlock_irqrestore(&self->spinlock, flags);
 		return -1;
 	}
@@ -138,7 +137,7 @@ int ircomm_param_request(struct ircomm_tty_cb *self, __u8 pi, int flush)
 
 	spin_unlock_irqrestore(&self->spinlock, flags);
 
-	IRDA_DEBUG(2, "%s(), skb->len=%d\n", __func__ , skb->len);
+	pr_debug("%s(), skb->len=%d\n", __func__ , skb->len);
 
 	if (flush) {
 		/* ircomm_tty_do_softint will take care of the rest */
@@ -172,12 +171,11 @@ static int ircomm_param_service_type(void *instance, irda_param_t *param,
 	/* Find all common service types */
 	service_type &= self->service_type;
 	if (!service_type) {
-		IRDA_DEBUG(2,
-			   "%s(), No common service type to use!\n", __func__ );
+		pr_debug("%s(), No common service type to use!\n", __func__);
 		return -1;
 	}
-	IRDA_DEBUG(0, "%s(), services in common=%02x\n", __func__ ,
-		   service_type);
+	pr_debug("%s(), services in common=%02x\n", __func__ ,
+		 service_type);
 
 	/*
 	 * Now choose a preferred service type of those available
@@ -191,8 +189,8 @@ static int ircomm_param_service_type(void *instance, irda_param_t *param,
 	else if (service_type & IRCOMM_3_WIRE_RAW)
 		self->settings.service_type = IRCOMM_3_WIRE_RAW;
 
-	IRDA_DEBUG(0, "%s(), resulting service type=0x%02x\n", __func__ ,
-		   self->settings.service_type);
+	pr_debug("%s(), resulting service type=0x%02x\n", __func__ ,
+		 self->settings.service_type);
 
 	/*
 	 * Now the line is ready for some communication. Check if we are a
@@ -234,8 +232,8 @@ static int ircomm_param_port_type(void *instance, irda_param_t *param, int get)
 	else {
 		self->settings.port_type = (__u8) param->pv.i;
 
-		IRDA_DEBUG(0, "%s(), port type=%d\n", __func__ ,
-			   self->settings.port_type);
+		pr_debug("%s(), port type=%d\n", __func__ ,
+			 self->settings.port_type);
 	}
 	return 0;
 }
@@ -254,9 +252,9 @@ static int ircomm_param_port_name(void *instance, irda_param_t *param, int get)
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return -1;);
 
 	if (get) {
-		IRDA_DEBUG(0, "%s(), not imp!\n", __func__ );
+		pr_debug("%s(), not imp!\n", __func__);
 	} else {
-		IRDA_DEBUG(0, "%s(), port-name=%s\n", __func__ , param->pv.c);
+		pr_debug("%s(), port-name=%s\n", __func__ , param->pv.c);
 		strncpy(self->settings.port_name, param->pv.c, 32);
 	}
 
@@ -281,7 +279,7 @@ static int ircomm_param_data_rate(void *instance, irda_param_t *param, int get)
 	else
 		self->settings.data_rate = param->pv.i;
 
-	IRDA_DEBUG(2, "%s(), data rate = %d\n", __func__ , param->pv.i);
+	pr_debug("%s(), data rate = %d\n", __func__ , param->pv.i);
 
 	return 0;
 }
@@ -327,7 +325,7 @@ static int ircomm_param_flow_control(void *instance, irda_param_t *param,
 	else
 		self->settings.flow_control = (__u8) param->pv.i;
 
-	IRDA_DEBUG(1, "%s(), flow control = 0x%02x\n", __func__ , (__u8) param->pv.i);
+	pr_debug("%s(), flow control = 0x%02x\n", __func__ , (__u8)param->pv.i);
 
 	return 0;
 }
@@ -353,8 +351,8 @@ static int ircomm_param_xon_xoff(void *instance, irda_param_t *param, int get)
 		self->settings.xonxoff[1] = (__u16) param->pv.i >> 8;
 	}
 
-	IRDA_DEBUG(0, "%s(), XON/XOFF = 0x%02x,0x%02x\n", __func__ ,
-		   param->pv.i & 0xff, param->pv.i >> 8);
+	pr_debug("%s(), XON/XOFF = 0x%02x,0x%02x\n", __func__ ,
+		 param->pv.i & 0xff, param->pv.i >> 8);
 
 	return 0;
 }
@@ -380,8 +378,8 @@ static int ircomm_param_enq_ack(void *instance, irda_param_t *param, int get)
 		self->settings.enqack[1] = (__u16) param->pv.i >> 8;
 	}
 
-	IRDA_DEBUG(0, "%s(), ENQ/ACK = 0x%02x,0x%02x\n", __func__ ,
-		   param->pv.i & 0xff, param->pv.i >> 8);
+	pr_debug("%s(), ENQ/ACK = 0x%02x,0x%02x\n", __func__ ,
+		 param->pv.i & 0xff, param->pv.i >> 8);
 
 	return 0;
 }
@@ -395,7 +393,7 @@ static int ircomm_param_enq_ack(void *instance, irda_param_t *param, int get)
 static int ircomm_param_line_status(void *instance, irda_param_t *param,
 				    int get)
 {
-	IRDA_DEBUG(2, "%s(), not impl.\n", __func__ );
+	pr_debug("%s(), not impl.\n", __func__);
 
 	return 0;
 }
@@ -456,7 +454,7 @@ static int ircomm_param_dce(void *instance, irda_param_t *param, int get)
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) instance;
 	__u8 dce;
 
-	IRDA_DEBUG(1, "%s(), dce = 0x%02x\n", __func__ , (__u8) param->pv.i);
+	pr_debug("%s(), dce = 0x%02x\n", __func__ , (__u8)param->pv.i);
 
 	dce = (__u8) param->pv.i;
 
@@ -468,7 +466,7 @@ static int ircomm_param_dce(void *instance, irda_param_t *param, int get)
 	/* Check if any of the settings have changed */
 	if (dce & 0x0f) {
 		if (dce & IRCOMM_DELTA_CTS) {
-			IRDA_DEBUG(2, "%s(), CTS\n", __func__ );
+			pr_debug("%s(), CTS\n", __func__);
 		}
 	}
 
diff --git a/net/irda/ircomm/ircomm_ttp.c b/net/irda/ircomm/ircomm_ttp.c
index d362d711b79c..4b81e0934770 100644
--- a/net/irda/ircomm/ircomm_ttp.c
+++ b/net/irda/ircomm/ircomm_ttp.c
@@ -76,8 +76,6 @@ int ircomm_open_tsap(struct ircomm_cb *self)
 {
 	notify_t notify;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	/* Register callbacks */
 	irda_notify_init(&notify);
 	notify.data_indication       = ircomm_ttp_data_indication;
@@ -91,7 +89,7 @@ int ircomm_open_tsap(struct ircomm_cb *self)
 	self->tsap = irttp_open_tsap(LSAP_ANY, DEFAULT_INITIAL_CREDIT,
 				     &notify);
 	if (!self->tsap) {
-		IRDA_DEBUG(0, "%sfailed to allocate tsap\n", __func__ );
+		pr_debug("%sfailed to allocate tsap\n", __func__);
 		return -1;
 	}
 	self->slsap_sel = self->tsap->stsap_sel;
@@ -119,8 +117,6 @@ static int ircomm_ttp_connect_request(struct ircomm_cb *self,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	/* Don't forget to refcount it - should be NULL anyway */
 	if(userdata)
 		skb_get(userdata);
@@ -143,8 +139,6 @@ static int ircomm_ttp_connect_response(struct ircomm_cb *self,
 {
 	int ret;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	/* Don't forget to refcount it - should be NULL anyway */
 	if(userdata)
 		skb_get(userdata);
@@ -171,7 +165,7 @@ static int ircomm_ttp_data_request(struct ircomm_cb *self,
 
 	IRDA_ASSERT(skb != NULL, return -1;);
 
-	IRDA_DEBUG(2, "%s(), clen=%d\n", __func__ , clen);
+	pr_debug("%s(), clen=%d\n", __func__ , clen);
 
 	/*
 	 * Insert clen field, currently we either send data only, or control
@@ -188,7 +182,7 @@ static int ircomm_ttp_data_request(struct ircomm_cb *self,
 
 	ret = irttp_data_request(self->tsap, skb);
 	if (ret) {
-		IRDA_ERROR("%s(), failed\n", __func__);
+		net_err_ratelimited("%s(), failed\n", __func__);
 		/* irttp_data_request already free the packet */
 	}
 
@@ -206,8 +200,6 @@ static int ircomm_ttp_data_indication(void *instance, void *sap,
 {
 	struct ircomm_cb *self = (struct ircomm_cb *) instance;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return -1;);
 	IRDA_ASSERT(skb != NULL, return -1;);
@@ -229,16 +221,14 @@ static void ircomm_ttp_connect_confirm(void *instance, void *sap,
 	struct ircomm_cb *self = (struct ircomm_cb *) instance;
 	struct ircomm_info info;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return;);
 	IRDA_ASSERT(skb != NULL, return;);
 	IRDA_ASSERT(qos != NULL, goto out;);
 
 	if (max_sdu_size != TTP_SAR_DISABLE) {
-		IRDA_ERROR("%s(), SAR not allowed for IrCOMM!\n",
-			   __func__);
+		net_err_ratelimited("%s(), SAR not allowed for IrCOMM!\n",
+				    __func__);
 		goto out;
 	}
 
@@ -270,16 +260,14 @@ static void ircomm_ttp_connect_indication(void *instance, void *sap,
 	struct ircomm_cb *self = (struct ircomm_cb *)instance;
 	struct ircomm_info info;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return;);
 	IRDA_ASSERT(skb != NULL, return;);
 	IRDA_ASSERT(qos != NULL, goto out;);
 
 	if (max_sdu_size != TTP_SAR_DISABLE) {
-		IRDA_ERROR("%s(), SAR not allowed for IrCOMM!\n",
-			   __func__);
+		net_err_ratelimited("%s(), SAR not allowed for IrCOMM!\n",
+				    __func__);
 		goto out;
 	}
 
@@ -329,8 +317,6 @@ static void ircomm_ttp_disconnect_indication(void *instance, void *sap,
 	struct ircomm_cb *self = (struct ircomm_cb *) instance;
 	struct ircomm_info info;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return;);
 
@@ -354,8 +340,6 @@ static void ircomm_ttp_flow_indication(void *instance, void *sap,
 {
 	struct ircomm_cb *self = (struct ircomm_cb *) instance;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_MAGIC, return;);
 
diff --git a/net/irda/ircomm/ircomm_tty.c b/net/irda/ircomm/ircomm_tty.c
index 61ceb4cdb4a2..683346d2d633 100644
--- a/net/irda/ircomm/ircomm_tty.c
+++ b/net/irda/ircomm/ircomm_tty.c
@@ -147,7 +147,8 @@ static int __init ircomm_tty_init(void)
 		return -ENOMEM;
 	ircomm_tty = hashbin_new(HB_LOCK);
 	if (ircomm_tty == NULL) {
-		IRDA_ERROR("%s(), can't allocate hashbin!\n", __func__);
+		net_err_ratelimited("%s(), can't allocate hashbin!\n",
+				    __func__);
 		put_tty_driver(driver);
 		return -ENOMEM;
 	}
@@ -163,8 +164,8 @@ static int __init ircomm_tty_init(void)
 	driver->flags           = TTY_DRIVER_REAL_RAW;
 	tty_set_operations(driver, &ops);
 	if (tty_register_driver(driver)) {
-		IRDA_ERROR("%s(): Couldn't register serial driver\n",
-			   __func__);
+		net_err_ratelimited("%s(): Couldn't register serial driver\n",
+				    __func__);
 		put_tty_driver(driver);
 		return -1;
 	}
@@ -173,8 +174,6 @@ static int __init ircomm_tty_init(void)
 
 static void __exit __ircomm_tty_cleanup(struct ircomm_tty_cb *self)
 {
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
@@ -195,12 +194,10 @@ static void __exit ircomm_tty_cleanup(void)
 {
 	int ret;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	ret = tty_unregister_driver(driver);
 	if (ret) {
-		IRDA_ERROR("%s(), failed to unregister driver\n",
-			   __func__);
+		net_err_ratelimited("%s(), failed to unregister driver\n",
+				    __func__);
 		return;
 	}
 
@@ -219,14 +216,12 @@ static int ircomm_tty_startup(struct ircomm_tty_cb *self)
 	notify_t notify;
 	int ret = -ENODEV;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return -1;);
 
 	/* Check if already open */
 	if (test_and_set_bit(ASYNCB_INITIALIZED, &self->port.flags)) {
-		IRDA_DEBUG(2, "%s(), already open so break out!\n", __func__ );
+		pr_debug("%s(), already open so break out!\n", __func__);
 		return 0;
 	}
 
@@ -256,7 +251,7 @@ static int ircomm_tty_startup(struct ircomm_tty_cb *self)
 	/* Connect IrCOMM link with remote device */
 	ret = ircomm_tty_attach_cable(self);
 	if (ret < 0) {
-		IRDA_ERROR("%s(), error attaching cable!\n", __func__);
+		net_err_ratelimited("%s(), error attaching cable!\n", __func__);
 		goto err;
 	}
 
@@ -281,8 +276,6 @@ static int ircomm_tty_block_til_ready(struct ircomm_tty_cb *self,
 	int		do_clocal = 0;
 	unsigned long	flags;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	/*
 	 * If non-blocking mode is set, or the port is not enabled,
 	 * then make the check up front and then exit.
@@ -297,12 +290,12 @@ static int ircomm_tty_block_til_ready(struct ircomm_tty_cb *self,
 		if (tty->termios.c_cflag & CBAUD)
 			tty_port_raise_dtr_rts(port);
 		port->flags |= ASYNC_NORMAL_ACTIVE;
-		IRDA_DEBUG(1, "%s(), O_NONBLOCK requested!\n", __func__ );
+		pr_debug("%s(), O_NONBLOCK requested!\n", __func__);
 		return 0;
 	}
 
 	if (tty->termios.c_cflag & CLOCAL) {
-		IRDA_DEBUG(1, "%s(), doing CLOCAL!\n", __func__ );
+		pr_debug("%s(), doing CLOCAL!\n", __func__);
 		do_clocal = 1;
 	}
 
@@ -316,8 +309,8 @@ static int ircomm_tty_block_til_ready(struct ircomm_tty_cb *self,
 	retval = 0;
 	add_wait_queue(&port->open_wait, &wait);
 
-	IRDA_DEBUG(2, "%s(%d):block_til_ready before block on %s open_count=%d\n",
-	      __FILE__, __LINE__, tty->driver->name, port->count);
+	pr_debug("%s(%d):block_til_ready before block on %s open_count=%d\n",
+		 __FILE__, __LINE__, tty->driver->name, port->count);
 
 	spin_lock_irqsave(&port->lock, flags);
 	port->count--;
@@ -354,8 +347,8 @@ static int ircomm_tty_block_til_ready(struct ircomm_tty_cb *self,
 			break;
 		}
 
-		IRDA_DEBUG(1, "%s(%d):block_til_ready blocking on %s open_count=%d\n",
-		      __FILE__, __LINE__, tty->driver->name, port->count);
+		pr_debug("%s(%d):block_til_ready blocking on %s open_count=%d\n",
+			 __FILE__, __LINE__, tty->driver->name, port->count);
 
 		schedule();
 	}
@@ -369,8 +362,8 @@ static int ircomm_tty_block_til_ready(struct ircomm_tty_cb *self,
 	port->blocked_open--;
 	spin_unlock_irqrestore(&port->lock, flags);
 
-	IRDA_DEBUG(1, "%s(%d):block_til_ready after blocking on %s open_count=%d\n",
-	      __FILE__, __LINE__, tty->driver->name, port->count);
+	pr_debug("%s(%d):block_til_ready after blocking on %s open_count=%d\n",
+		 __FILE__, __LINE__, tty->driver->name, port->count);
 
 	if (!retval)
 		port->flags |= ASYNC_NORMAL_ACTIVE;
@@ -389,10 +382,8 @@ static int ircomm_tty_install(struct tty_driver *driver, struct tty_struct *tty)
 	if (!self) {
 		/* No, so make new instance */
 		self = kzalloc(sizeof(struct ircomm_tty_cb), GFP_KERNEL);
-		if (self == NULL) {
-			IRDA_ERROR("%s(), kmalloc failed!\n", __func__);
+		if (self == NULL)
 			return -ENOMEM;
-		}
 
 		tty_port_init(&self->port);
 		self->port.ops = &ircomm_port_ops;
@@ -440,16 +431,14 @@ static int ircomm_tty_open(struct tty_struct *tty, struct file *filp)
 	unsigned long	flags;
 	int ret;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	/* ++ is not atomic, so this should be protected - Jean II */
 	spin_lock_irqsave(&self->port.lock, flags);
 	self->port.count++;
 	spin_unlock_irqrestore(&self->port.lock, flags);
 	tty_port_tty_set(&self->port, tty);
 
-	IRDA_DEBUG(1, "%s(), %s%d, count = %d\n", __func__ , tty->driver->name,
-		   self->line, self->port.count);
+	pr_debug("%s(), %s%d, count = %d\n", __func__ , tty->driver->name,
+		 self->line, self->port.count);
 
 	/* Not really used by us, but lets do it anyway */
 	self->port.low_latency = (self->port.flags & ASYNC_LOW_LATENCY) ? 1 : 0;
@@ -469,8 +458,8 @@ static int ircomm_tty_open(struct tty_struct *tty, struct file *filp)
 
 		if (wait_event_interruptible(self->port.close_wait,
 				!test_bit(ASYNCB_CLOSING, &self->port.flags))) {
-			IRDA_WARNING("%s - got signal while blocking on ASYNC_CLOSING!\n",
-				     __func__);
+			net_warn_ratelimited("%s - got signal while blocking on ASYNC_CLOSING!\n",
+					     __func__);
 			return -ERESTARTSYS;
 		}
 
@@ -488,9 +477,9 @@ static int ircomm_tty_open(struct tty_struct *tty, struct file *filp)
 		self->settings.service_type = IRCOMM_9_WIRE; /* 9 wire as default */
 		/* Jan Kiszka -> add DSR/RI -> Conform to IrCOMM spec */
 		self->settings.dce = IRCOMM_CTS | IRCOMM_CD | IRCOMM_DSR | IRCOMM_RI; /* Default line settings */
-		IRDA_DEBUG(2, "%s(), IrCOMM device\n", __func__ );
+		pr_debug("%s(), IrCOMM device\n", __func__);
 	} else {
-		IRDA_DEBUG(2, "%s(), IrLPT device\n", __func__ );
+		pr_debug("%s(), IrLPT device\n", __func__);
 		self->service_type = IRCOMM_3_WIRE_RAW;
 		self->settings.service_type = IRCOMM_3_WIRE_RAW; /* Default */
 	}
@@ -501,9 +490,8 @@ static int ircomm_tty_open(struct tty_struct *tty, struct file *filp)
 
 	ret = ircomm_tty_block_til_ready(self, tty, filp);
 	if (ret) {
-		IRDA_DEBUG(2,
-		      "%s(), returning after block_til_ready with %d\n", __func__ ,
-		      ret);
+		pr_debug("%s(), returning after block_til_ready with %d\n",
+			 __func__, ret);
 
 		return ret;
 	}
@@ -521,8 +509,6 @@ static void ircomm_tty_close(struct tty_struct *tty, struct file *filp)
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) tty->driver_data;
 	struct tty_port *port = &self->port;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
@@ -572,8 +558,6 @@ static void ircomm_tty_do_softint(struct work_struct *work)
 	unsigned long flags;
 	struct sk_buff *skb, *ctrl_skb;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	if (!self || self->magic != IRCOMM_TTY_MAGIC)
 		return;
 
@@ -639,8 +623,8 @@ static int ircomm_tty_write(struct tty_struct *tty,
 	int len = 0;
 	int size;
 
-	IRDA_DEBUG(2, "%s(), count=%d, hw_stopped=%d\n", __func__ , count,
-		   tty->hw_stopped);
+	pr_debug("%s(), count=%d, hw_stopped=%d\n", __func__ , count,
+		 tty->hw_stopped);
 
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return -1;);
@@ -662,7 +646,7 @@ static int ircomm_tty_write(struct tty_struct *tty,
 	 * we don't mess up the original "safe skb" (see tx_data_size).
 	 * Jean II */
 	if (self->max_header_size == IRCOMM_TTY_HDR_UNINITIALISED) {
-		IRDA_DEBUG(1, "%s() : not initialised\n", __func__);
+		pr_debug("%s() : not initialised\n", __func__);
 #ifdef IRCOMM_NO_TX_BEFORE_INIT
 		/* We didn't consume anything, TTY will retry */
 		return 0;
@@ -791,7 +775,7 @@ static int ircomm_tty_write_room(struct tty_struct *tty)
 			ret = self->max_data_size;
 		spin_unlock_irqrestore(&self->spinlock, flags);
 	}
-	IRDA_DEBUG(2, "%s(), ret=%d\n", __func__ , ret);
+	pr_debug("%s(), ret=%d\n", __func__ , ret);
 
 	return ret;
 }
@@ -808,15 +792,15 @@ static void ircomm_tty_wait_until_sent(struct tty_struct *tty, int timeout)
 	unsigned long orig_jiffies, poll_time;
 	unsigned long flags;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
 	orig_jiffies = jiffies;
 
 	/* Set poll time to 200 ms */
-	poll_time = IRDA_MIN(timeout, msecs_to_jiffies(200));
+	poll_time = msecs_to_jiffies(200);
+	if (timeout)
+		poll_time = min_t(unsigned long, timeout, poll_time);
 
 	spin_lock_irqsave(&self->spinlock, flags);
 	while (self->tx_skb && self->tx_skb->len) {
@@ -829,7 +813,7 @@ static void ircomm_tty_wait_until_sent(struct tty_struct *tty, int timeout)
 			break;
 	}
 	spin_unlock_irqrestore(&self->spinlock, flags);
-	current->state = TASK_RUNNING;
+	__set_current_state(TASK_RUNNING);
 }
 
 /*
@@ -843,8 +827,6 @@ static void ircomm_tty_throttle(struct tty_struct *tty)
 {
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) tty->driver_data;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
@@ -874,8 +856,6 @@ static void ircomm_tty_unthrottle(struct tty_struct *tty)
 {
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) tty->driver_data;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
@@ -889,7 +869,7 @@ static void ircomm_tty_unthrottle(struct tty_struct *tty)
 		self->settings.dte |= (IRCOMM_RTS|IRCOMM_DELTA_RTS);
 
 		ircomm_param_request(self, IRCOMM_DTE, TRUE);
-		IRDA_DEBUG(1, "%s(), FLOW_START\n", __func__ );
+		pr_debug("%s(), FLOW_START\n", __func__);
 	}
 	ircomm_flow_request(self->ircomm, FLOW_START);
 }
@@ -926,8 +906,6 @@ static void ircomm_tty_shutdown(struct ircomm_tty_cb *self)
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	if (!test_and_clear_bit(ASYNCB_INITIALIZED, &self->port.flags))
 		return;
 
@@ -970,8 +948,6 @@ static void ircomm_tty_hangup(struct tty_struct *tty)
 	struct tty_port *port = &self->port;
 	unsigned long	flags;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
@@ -999,7 +975,7 @@ static void ircomm_tty_hangup(struct tty_struct *tty)
  */
 static void ircomm_tty_send_xchar(struct tty_struct *tty, char ch)
 {
-	IRDA_DEBUG(0, "%s(), not impl\n", __func__ );
+	pr_debug("%s(), not impl\n", __func__);
 }
 
 /*
@@ -1043,8 +1019,6 @@ void ircomm_tty_check_modem_status(struct ircomm_tty_cb *self)
 	struct tty_struct *tty;
 	int status;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
@@ -1056,15 +1030,13 @@ void ircomm_tty_check_modem_status(struct ircomm_tty_cb *self)
 		/*wake_up_interruptible(&self->delta_msr_wait);*/
 	}
 	if ((self->port.flags & ASYNC_CHECK_CD) && (status & IRCOMM_DELTA_CD)) {
-		IRDA_DEBUG(2,
-			   "%s(), ircomm%d CD now %s...\n", __func__ , self->line,
-			   (status & IRCOMM_CD) ? "on" : "off");
+		pr_debug("%s(), ircomm%d CD now %s...\n", __func__ , self->line,
+			 (status & IRCOMM_CD) ? "on" : "off");
 
 		if (status & IRCOMM_CD) {
 			wake_up_interruptible(&self->port.open_wait);
 		} else {
-			IRDA_DEBUG(2,
-				   "%s(), Doing serial hangup..\n", __func__ );
+			pr_debug("%s(), Doing serial hangup..\n", __func__);
 			if (tty)
 				tty_hangup(tty);
 
@@ -1075,8 +1047,7 @@ void ircomm_tty_check_modem_status(struct ircomm_tty_cb *self)
 	if (tty && tty_port_cts_enabled(&self->port)) {
 		if (tty->hw_stopped) {
 			if (status & IRCOMM_CTS) {
-				IRDA_DEBUG(2,
-					   "%s(), CTS tx start...\n", __func__ );
+				pr_debug("%s(), CTS tx start...\n", __func__);
 				tty->hw_stopped = 0;
 
 				/* Wake up processes blocked on open */
@@ -1087,8 +1058,7 @@ void ircomm_tty_check_modem_status(struct ircomm_tty_cb *self)
 			}
 		} else {
 			if (!(status & IRCOMM_CTS)) {
-				IRDA_DEBUG(2,
-					   "%s(), CTS tx stop...\n", __func__ );
+				pr_debug("%s(), CTS tx stop...\n", __func__);
 				tty->hw_stopped = 1;
 			}
 		}
@@ -1109,15 +1079,13 @@ static int ircomm_tty_data_indication(void *instance, void *sap,
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) instance;
 	struct tty_struct *tty;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return -1;);
 	IRDA_ASSERT(skb != NULL, return -1;);
 
 	tty = tty_port_tty_get(&self->port);
 	if (!tty) {
-		IRDA_DEBUG(0, "%s(), no tty!\n", __func__ );
+		pr_debug("%s(), no tty!\n", __func__);
 		return 0;
 	}
 
@@ -1128,7 +1096,7 @@ static int ircomm_tty_data_indication(void *instance, void *sap,
 	 * params, we can just as well declare the hardware for running.
 	 */
 	if (tty->hw_stopped && (self->flow == FLOW_START)) {
-		IRDA_DEBUG(0, "%s(), polling for line settings!\n", __func__ );
+		pr_debug("%s(), polling for line settings!\n", __func__);
 		ircomm_param_request(self, IRCOMM_POLL, TRUE);
 
 		/* We can just as well declare the hardware for running */
@@ -1161,8 +1129,6 @@ static int ircomm_tty_control_indication(void *instance, void *sap,
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) instance;
 	int clen;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return -1;);
 	IRDA_ASSERT(skb != NULL, return -1;);
@@ -1197,7 +1163,7 @@ static void ircomm_tty_flow_indication(void *instance, void *sap,
 
 	switch (cmd) {
 	case FLOW_START:
-		IRDA_DEBUG(2, "%s(), hw start!\n", __func__ );
+		pr_debug("%s(), hw start!\n", __func__);
 		if (tty)
 			tty->hw_stopped = 0;
 
@@ -1206,7 +1172,7 @@ static void ircomm_tty_flow_indication(void *instance, void *sap,
 		break;
 	default:  /* If we get here, something is very wrong, better stop */
 	case FLOW_STOP:
-		IRDA_DEBUG(2, "%s(), hw stopped!\n", __func__ );
+		pr_debug("%s(), hw stopped!\n", __func__);
 		if (tty)
 			tty->hw_stopped = 1;
 		break;
diff --git a/net/irda/ircomm/ircomm_tty_attach.c b/net/irda/ircomm/ircomm_tty_attach.c
index 2ee87bf387cc..61137f8b5293 100644
--- a/net/irda/ircomm/ircomm_tty_attach.c
+++ b/net/irda/ircomm/ircomm_tty_attach.c
@@ -89,8 +89,7 @@ const char *const ircomm_tty_state[] = {
 	"*** ERROR *** ",
 };
 
-#ifdef CONFIG_IRDA_DEBUG
-static const char *const ircomm_tty_event[] = {
+static const char *const ircomm_tty_event[] __maybe_unused = {
 	"IRCOMM_TTY_ATTACH_CABLE",
 	"IRCOMM_TTY_DETACH_CABLE",
 	"IRCOMM_TTY_DATA_REQUEST",
@@ -106,7 +105,6 @@ static const char *const ircomm_tty_event[] = {
 	"IRCOMM_TTY_GOT_LSAPSEL",
 	"*** ERROR ****",
 };
-#endif /* CONFIG_IRDA_DEBUG */
 
 static int (*state[])(struct ircomm_tty_cb *self, IRCOMM_TTY_EVENT event,
 		      struct sk_buff *skb, struct ircomm_tty_info *info) =
@@ -130,14 +128,12 @@ int ircomm_tty_attach_cable(struct ircomm_tty_cb *self)
 {
 	struct tty_struct *tty;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return -1;);
 
 	/* Check if somebody has already connected to us */
 	if (ircomm_is_connected(self->ircomm)) {
-		IRDA_DEBUG(0, "%s(), already connected!\n", __func__ );
+		pr_debug("%s(), already connected!\n", __func__);
 		return 0;
 	}
 
@@ -163,8 +159,6 @@ int ircomm_tty_attach_cable(struct ircomm_tty_cb *self)
  */
 void ircomm_tty_detach_cable(struct ircomm_tty_cb *self)
 {
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
@@ -212,8 +206,6 @@ static void ircomm_tty_ias_register(struct ircomm_tty_cb *self)
 	__u8 oct_seq[6];
 	__u16 hints;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
@@ -313,17 +305,17 @@ int ircomm_tty_send_initial_parameters(struct ircomm_tty_cb *self)
 	 * Set default values, but only if the application for some reason
 	 * haven't set them already
 	 */
-	IRDA_DEBUG(2, "%s(), data-rate = %d\n", __func__ ,
-		   self->settings.data_rate);
+	pr_debug("%s(), data-rate = %d\n", __func__ ,
+		 self->settings.data_rate);
 	if (!self->settings.data_rate)
 		self->settings.data_rate = 9600;
-	IRDA_DEBUG(2, "%s(), data-format = %d\n", __func__ ,
-		   self->settings.data_format);
+	pr_debug("%s(), data-format = %d\n", __func__ ,
+		 self->settings.data_format);
 	if (!self->settings.data_format)
 		self->settings.data_format = IRCOMM_WSIZE_8;  /* 8N1 */
 
-	IRDA_DEBUG(2, "%s(), flow-control = %d\n", __func__ ,
-		   self->settings.flow_control);
+	pr_debug("%s(), flow-control = %d\n", __func__ ,
+		 self->settings.flow_control);
 	/*self->settings.flow_control = IRCOMM_RTS_CTS_IN|IRCOMM_RTS_CTS_OUT;*/
 
 	/* Do not set delta values for the initial parameters */
@@ -367,8 +359,6 @@ static void ircomm_tty_discovery_indication(discinfo_t *discovery,
 	struct ircomm_tty_cb *self;
 	struct ircomm_tty_info info;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	/* Important note :
 	 * We need to drop all passive discoveries.
 	 * The LSAP management of IrComm is deficient and doesn't deal
@@ -404,8 +394,6 @@ void ircomm_tty_disconnect_indication(void *instance, void *sap,
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) instance;
 	struct tty_struct *tty;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
@@ -436,8 +424,6 @@ static void ircomm_tty_getvalue_confirm(int result, __u16 obj_id,
 {
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) priv;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
@@ -447,13 +433,13 @@ static void ircomm_tty_getvalue_confirm(int result, __u16 obj_id,
 
 	/* Check if request succeeded */
 	if (result != IAS_SUCCESS) {
-		IRDA_DEBUG(4, "%s(), got NULL value!\n", __func__ );
+		pr_debug("%s(), got NULL value!\n", __func__);
 		return;
 	}
 
 	switch (value->type) {
 	case IAS_OCT_SEQ:
-		IRDA_DEBUG(2, "%s(), got octet sequence\n", __func__ );
+		pr_debug("%s(), got octet sequence\n", __func__);
 
 		irda_param_extract_all(self, value->t.oct_seq, value->len,
 				       &ircomm_param_info);
@@ -463,21 +449,21 @@ static void ircomm_tty_getvalue_confirm(int result, __u16 obj_id,
 		break;
 	case IAS_INTEGER:
 		/* Got LSAP selector */
-		IRDA_DEBUG(2, "%s(), got lsapsel = %d\n", __func__ ,
-			   value->t.integer);
+		pr_debug("%s(), got lsapsel = %d\n", __func__ ,
+			 value->t.integer);
 
 		if (value->t.integer == -1) {
-			IRDA_DEBUG(0, "%s(), invalid value!\n", __func__ );
+			pr_debug("%s(), invalid value!\n", __func__);
 		} else
 			self->dlsap_sel = value->t.integer;
 
 		ircomm_tty_do_event(self, IRCOMM_TTY_GOT_LSAPSEL, NULL, NULL);
 		break;
 	case IAS_MISSING:
-		IRDA_DEBUG(0, "%s(), got IAS_MISSING\n", __func__ );
+		pr_debug("%s(), got IAS_MISSING\n", __func__);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), got unknown type!\n", __func__ );
+		pr_debug("%s(), got unknown type!\n", __func__);
 		break;
 	}
 	irias_delete_value(value);
@@ -497,8 +483,6 @@ void ircomm_tty_connect_confirm(void *instance, void *sap,
 {
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) instance;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
@@ -528,8 +512,6 @@ void ircomm_tty_connect_indication(void *instance, void *sap,
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) instance;
 	int clen;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
@@ -559,8 +541,6 @@ void ircomm_tty_link_established(struct ircomm_tty_cb *self)
 {
 	struct tty_struct *tty;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
@@ -578,10 +558,10 @@ void ircomm_tty_link_established(struct ircomm_tty_cb *self)
 	 */
 	if (tty_port_cts_enabled(&self->port) &&
 			((self->settings.dce & IRCOMM_CTS) == 0)) {
-		IRDA_DEBUG(0, "%s(), waiting for CTS ...\n", __func__ );
+		pr_debug("%s(), waiting for CTS ...\n", __func__);
 		goto put;
 	} else {
-		IRDA_DEBUG(1, "%s(), starting hardware!\n", __func__ );
+		pr_debug("%s(), starting hardware!\n", __func__);
 
 		tty->hw_stopped = 0;
 
@@ -621,8 +601,6 @@ static void ircomm_tty_watchdog_timer_expired(void *data)
 {
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) data;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
@@ -642,8 +620,8 @@ int ircomm_tty_do_event(struct ircomm_tty_cb *self, IRCOMM_TTY_EVENT event,
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return -1;);
 
-	IRDA_DEBUG(2, "%s: state=%s, event=%s\n", __func__ ,
-		   ircomm_tty_state[self->state], ircomm_tty_event[event]);
+	pr_debug("%s: state=%s, event=%s\n", __func__ ,
+		 ircomm_tty_state[self->state], ircomm_tty_event[event]);
 
 	return (*state[self->state])(self, event, skb, info);
 }
@@ -660,8 +638,8 @@ static inline void ircomm_tty_next_state(struct ircomm_tty_cb *self, IRCOMM_TTY_
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
 
-	IRDA_DEBUG(2, "%s: next state=%s, service type=%d\n", __func__ ,
-		   ircomm_tty_state[self->state], self->service_type);
+	pr_debug("%s: next state=%s, service type=%d\n", __func__ ,
+	ircomm_tty_state[self->state], self->service_type);
 	*/
 	self->state = state;
 }
@@ -679,8 +657,8 @@ static int ircomm_tty_state_idle(struct ircomm_tty_cb *self,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(2, "%s: state=%s, event=%s\n", __func__ ,
-		   ircomm_tty_state[self->state], ircomm_tty_event[event]);
+	pr_debug("%s: state=%s, event=%s\n", __func__ ,
+		 ircomm_tty_state[self->state], ircomm_tty_event[event]);
 	switch (event) {
 	case IRCOMM_TTY_ATTACH_CABLE:
 		/* Try to discover any remote devices */
@@ -694,8 +672,8 @@ static int ircomm_tty_state_idle(struct ircomm_tty_cb *self,
 		self->saddr = info->saddr;
 
 		if (self->iriap) {
-			IRDA_WARNING("%s(), busy with a previous query\n",
-				     __func__);
+			net_warn_ratelimited("%s(), busy with a previous query\n",
+					     __func__);
 			return -EBUSY;
 		}
 
@@ -723,8 +701,8 @@ static int ircomm_tty_state_idle(struct ircomm_tty_cb *self,
 		ircomm_tty_next_state(self, IRCOMM_TTY_IDLE);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), unknown event: %s\n", __func__ ,
-			   ircomm_tty_event[event]);
+		pr_debug("%s(), unknown event: %s\n", __func__ ,
+			 ircomm_tty_event[event]);
 		ret = -EINVAL;
 	}
 	return ret;
@@ -743,8 +721,8 @@ static int ircomm_tty_state_search(struct ircomm_tty_cb *self,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(2, "%s: state=%s, event=%s\n", __func__ ,
-		   ircomm_tty_state[self->state], ircomm_tty_event[event]);
+	pr_debug("%s: state=%s, event=%s\n", __func__ ,
+		 ircomm_tty_state[self->state], ircomm_tty_event[event]);
 
 	switch (event) {
 	case IRCOMM_TTY_DISCOVERY_INDICATION:
@@ -752,8 +730,8 @@ static int ircomm_tty_state_search(struct ircomm_tty_cb *self,
 		self->saddr = info->saddr;
 
 		if (self->iriap) {
-			IRDA_WARNING("%s(), busy with a previous query\n",
-				     __func__);
+			net_warn_ratelimited("%s(), busy with a previous query\n",
+					     __func__);
 			return -EBUSY;
 		}
 
@@ -796,8 +774,8 @@ static int ircomm_tty_state_search(struct ircomm_tty_cb *self,
 		ircomm_tty_next_state(self, IRCOMM_TTY_IDLE);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), unknown event: %s\n", __func__ ,
-			   ircomm_tty_event[event]);
+		pr_debug("%s(), unknown event: %s\n", __func__ ,
+			 ircomm_tty_event[event]);
 		ret = -EINVAL;
 	}
 	return ret;
@@ -816,14 +794,14 @@ static int ircomm_tty_state_query_parameters(struct ircomm_tty_cb *self,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(2, "%s: state=%s, event=%s\n", __func__ ,
-		   ircomm_tty_state[self->state], ircomm_tty_event[event]);
+	pr_debug("%s: state=%s, event=%s\n", __func__ ,
+		 ircomm_tty_state[self->state], ircomm_tty_event[event]);
 
 	switch (event) {
 	case IRCOMM_TTY_GOT_PARAMETERS:
 		if (self->iriap) {
-			IRDA_WARNING("%s(), busy with a previous query\n",
-				     __func__);
+			net_warn_ratelimited("%s(), busy with a previous query\n",
+					     __func__);
 			return -EBUSY;
 		}
 
@@ -854,8 +832,8 @@ static int ircomm_tty_state_query_parameters(struct ircomm_tty_cb *self,
 		ircomm_tty_next_state(self, IRCOMM_TTY_IDLE);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), unknown event: %s\n", __func__ ,
-			   ircomm_tty_event[event]);
+		pr_debug("%s(), unknown event: %s\n", __func__ ,
+			 ircomm_tty_event[event]);
 		ret = -EINVAL;
 	}
 	return ret;
@@ -874,8 +852,8 @@ static int ircomm_tty_state_query_lsap_sel(struct ircomm_tty_cb *self,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(2, "%s: state=%s, event=%s\n", __func__ ,
-		   ircomm_tty_state[self->state], ircomm_tty_event[event]);
+	pr_debug("%s: state=%s, event=%s\n", __func__ ,
+		 ircomm_tty_state[self->state], ircomm_tty_event[event]);
 
 	switch (event) {
 	case IRCOMM_TTY_GOT_LSAPSEL:
@@ -903,8 +881,8 @@ static int ircomm_tty_state_query_lsap_sel(struct ircomm_tty_cb *self,
 		ircomm_tty_next_state(self, IRCOMM_TTY_IDLE);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), unknown event: %s\n", __func__ ,
-			   ircomm_tty_event[event]);
+		pr_debug("%s(), unknown event: %s\n", __func__ ,
+			 ircomm_tty_event[event]);
 		ret = -EINVAL;
 	}
 	return ret;
@@ -923,8 +901,8 @@ static int ircomm_tty_state_setup(struct ircomm_tty_cb *self,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(2, "%s: state=%s, event=%s\n", __func__ ,
-		   ircomm_tty_state[self->state], ircomm_tty_event[event]);
+	pr_debug("%s: state=%s, event=%s\n", __func__ ,
+		 ircomm_tty_state[self->state], ircomm_tty_event[event]);
 
 	switch (event) {
 	case IRCOMM_TTY_CONNECT_CONFIRM:
@@ -957,8 +935,8 @@ static int ircomm_tty_state_setup(struct ircomm_tty_cb *self,
 		ircomm_tty_next_state(self, IRCOMM_TTY_IDLE);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), unknown event: %s\n", __func__ ,
-			   ircomm_tty_event[event]);
+		pr_debug("%s(), unknown event: %s\n", __func__ ,
+			 ircomm_tty_event[event]);
 		ret = -EINVAL;
 	}
 	return ret;
@@ -995,13 +973,13 @@ static int ircomm_tty_state_ready(struct ircomm_tty_cb *self,
 			self->settings.dce = IRCOMM_DELTA_CD;
 			ircomm_tty_check_modem_status(self);
 		} else {
-			IRDA_DEBUG(0, "%s(), hanging up!\n", __func__ );
+			pr_debug("%s(), hanging up!\n", __func__);
 			tty_port_tty_hangup(&self->port, false);
 		}
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), unknown event: %s\n", __func__ ,
-			   ircomm_tty_event[event]);
+		pr_debug("%s(), unknown event: %s\n", __func__ ,
+			 ircomm_tty_event[event]);
 		ret = -EINVAL;
 	}
 	return ret;
diff --git a/net/irda/ircomm/ircomm_tty_ioctl.c b/net/irda/ircomm/ircomm_tty_ioctl.c
index ce943853c38d..75ccdbd0728e 100644
--- a/net/irda/ircomm/ircomm_tty_ioctl.c
+++ b/net/irda/ircomm/ircomm_tty_ioctl.c
@@ -56,8 +56,6 @@ static void ircomm_tty_change_speed(struct ircomm_tty_cb *self,
 	unsigned int cflag, cval;
 	int baud;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	if (!self->ircomm)
 		return;
 
@@ -93,7 +91,8 @@ static void ircomm_tty_change_speed(struct ircomm_tty_cb *self,
 		self->settings.flow_control |= IRCOMM_RTS_CTS_IN;
 		/* This got me. Bummer. Jean II */
 		if (self->service_type == IRCOMM_3_WIRE_RAW)
-			IRDA_WARNING("%s(), enabling RTS/CTS on link that doesn't support it (3-wire-raw)\n", __func__);
+			net_warn_ratelimited("%s(), enabling RTS/CTS on link that doesn't support it (3-wire-raw)\n",
+					     __func__);
 	} else {
 		self->port.flags &= ~ASYNC_CTS_FLOW;
 		self->settings.flow_control &= ~IRCOMM_RTS_CTS_IN;
@@ -149,8 +148,6 @@ void ircomm_tty_set_termios(struct tty_struct *tty,
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) tty->driver_data;
 	unsigned int cflag = tty->termios.c_cflag;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	if ((cflag == old_termios->c_cflag) &&
 	    (RELEVANT_IFLAG(tty->termios.c_iflag) ==
 	     RELEVANT_IFLAG(old_termios->c_iflag)))
@@ -198,8 +195,6 @@ int ircomm_tty_tiocmget(struct tty_struct *tty)
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) tty->driver_data;
 	unsigned int result;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	if (tty->flags & (1 << TTY_IO_ERROR))
 		return -EIO;
 
@@ -223,8 +218,6 @@ int ircomm_tty_tiocmset(struct tty_struct *tty,
 {
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) tty->driver_data;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	if (tty->flags & (1 << TTY_IO_ERROR))
 		return -EIO;
 
@@ -265,8 +258,6 @@ static int ircomm_tty_get_serial_info(struct ircomm_tty_cb *self,
 	if (!retinfo)
 		return -EFAULT;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	memset(&info, 0, sizeof(info));
 	info.line = self->line;
 	info.flags = self->port.flags;
@@ -301,8 +292,6 @@ static int ircomm_tty_set_serial_info(struct ircomm_tty_cb *self,
 	struct serial_struct new_serial;
 	struct ircomm_tty_cb old_state, *state;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	if (copy_from_user(&new_serial,new_info,sizeof(new_serial)))
 		return -EFAULT;
 
@@ -375,8 +364,6 @@ int ircomm_tty_ioctl(struct tty_struct *tty,
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) tty->driver_data;
 	int ret = 0;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	if ((cmd != TIOCGSERIAL) && (cmd != TIOCSSERIAL) &&
 	    (cmd != TIOCSERCONFIG) && (cmd != TIOCSERGSTRUCT) &&
 	    (cmd != TIOCMIWAIT) && (cmd != TIOCGICOUNT)) {
@@ -392,11 +379,11 @@ int ircomm_tty_ioctl(struct tty_struct *tty,
 		ret = ircomm_tty_set_serial_info(self, (struct serial_struct __user *) arg);
 		break;
 	case TIOCMIWAIT:
-		IRDA_DEBUG(0, "(), TIOCMIWAIT, not impl!\n");
+		pr_debug("(), TIOCMIWAIT, not impl!\n");
 		break;
 
 	case TIOCGICOUNT:
-		IRDA_DEBUG(0, "%s(), TIOCGICOUNT not impl!\n", __func__ );
+		pr_debug("%s(), TIOCGICOUNT not impl!\n", __func__);
 #if 0
 		save_flags(flags); cli();
 		cnow = driver->icount;
diff --git a/net/irda/irda_device.c b/net/irda/irda_device.c
index 9e0d909390fd..856736656a30 100644
--- a/net/irda/irda_device.c
+++ b/net/irda/irda_device.c
@@ -63,14 +63,14 @@ int __init irda_device_init( void)
 {
 	dongles = hashbin_new(HB_NOLOCK);
 	if (dongles == NULL) {
-		IRDA_WARNING("IrDA: Can't allocate dongles hashbin!\n");
+		net_warn_ratelimited("IrDA: Can't allocate dongles hashbin!\n");
 		return -ENOMEM;
 	}
 	spin_lock_init(&dongles->hb_spinlock);
 
 	tasks = hashbin_new(HB_LOCK);
 	if (tasks == NULL) {
-		IRDA_WARNING("IrDA: Can't allocate tasks hashbin!\n");
+		net_warn_ratelimited("IrDA: Can't allocate tasks hashbin!\n");
 		hashbin_delete(dongles, NULL);
 		return -ENOMEM;
 	}
@@ -84,14 +84,12 @@ int __init irda_device_init( void)
 static void leftover_dongle(void *arg)
 {
 	struct dongle_reg *reg = arg;
-	IRDA_WARNING("IrDA: Dongle type %x not unregistered\n",
-		     reg->type);
+	net_warn_ratelimited("IrDA: Dongle type %x not unregistered\n",
+			     reg->type);
 }
 
 void irda_device_cleanup(void)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	hashbin_delete(tasks, (FREE_FUNC) __irda_task_delete);
 
 	hashbin_delete(dongles, leftover_dongle);
@@ -107,7 +105,7 @@ void irda_device_set_media_busy(struct net_device *dev, int status)
 {
 	struct irlap_cb *self;
 
-	IRDA_DEBUG(4, "%s(%s)\n", __func__, status ? "TRUE" : "FALSE");
+	pr_debug("%s(%s)\n", __func__, status ? "TRUE" : "FALSE");
 
 	self = (struct irlap_cb *) dev->atalk_ptr;
 
@@ -127,7 +125,7 @@ void irda_device_set_media_busy(struct net_device *dev, int status)
 			irlap_start_mbusy_timer(self, SMALLBUSY_TIMEOUT);
 		else
 			irlap_start_mbusy_timer(self, MEDIABUSY_TIMEOUT);
-		IRDA_DEBUG( 4, "Media busy!\n");
+		pr_debug("Media busy!\n");
 	} else {
 		self->media_busy = FALSE;
 		irlap_stop_mbusy_timer(self);
@@ -147,11 +145,9 @@ int irda_device_is_receiving(struct net_device *dev)
 	struct if_irda_req req;
 	int ret;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	if (!dev->netdev_ops->ndo_do_ioctl) {
-		IRDA_ERROR("%s: do_ioctl not impl. by device driver\n",
-			   __func__);
+		net_err_ratelimited("%s: do_ioctl not impl. by device driver\n",
+				    __func__);
 		return -1;
 	}
 
@@ -192,8 +188,6 @@ static int irda_task_kick(struct irda_task *task)
 	int count = 0;
 	int timeout;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	IRDA_ASSERT(task != NULL, return -1;);
 	IRDA_ASSERT(task->magic == IRDA_TASK_MAGIC, return -1;);
 
@@ -201,15 +195,15 @@ static int irda_task_kick(struct irda_task *task)
 	do {
 		timeout = task->function(task);
 		if (count++ > 100) {
-			IRDA_ERROR("%s: error in task handler!\n",
-				   __func__);
+			net_err_ratelimited("%s: error in task handler!\n",
+					    __func__);
 			irda_task_delete(task);
 			return TRUE;
 		}
 	} while ((timeout == 0) && (task->state != IRDA_TASK_DONE));
 
 	if (timeout < 0) {
-		IRDA_ERROR("%s: Error executing task!\n", __func__);
+		net_err_ratelimited("%s: Error executing task!\n", __func__);
 		irda_task_delete(task);
 		return TRUE;
 	}
@@ -241,8 +235,8 @@ static int irda_task_kick(struct irda_task *task)
 				 irda_task_timer_expired);
 		finished = FALSE;
 	} else {
-		IRDA_DEBUG(0, "%s(), not finished, and no timeout!\n",
-			   __func__);
+		pr_debug("%s(), not finished, and no timeout!\n",
+			 __func__);
 		finished = FALSE;
 	}
 
@@ -259,8 +253,6 @@ static void irda_task_timer_expired(void *data)
 {
 	struct irda_task *task;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	task = data;
 
 	irda_task_kick(task);
diff --git a/net/irda/iriap.c b/net/irda/iriap.c
index e1b37f5a2691..4a7ae32afa09 100644
--- a/net/irda/iriap.c
+++ b/net/irda/iriap.c
@@ -43,9 +43,8 @@
 #include <net/irda/iriap_event.h>
 #include <net/irda/iriap.h>
 
-#ifdef CONFIG_IRDA_DEBUG
 /* FIXME: This one should go in irlmp.c */
-static const char *const ias_charset_types[] = {
+static const char *const ias_charset_types[] __maybe_unused = {
 	"CS_ASCII",
 	"CS_ISO_8859_1",
 	"CS_ISO_8859_2",
@@ -58,7 +57,6 @@ static const char *const ias_charset_types[] = {
 	"CS_ISO_8859_9",
 	"CS_UNICODE"
 };
-#endif	/* CONFIG_IRDA_DEBUG */
 
 static hashbin_t *iriap = NULL;
 static void *service_handle;
@@ -110,8 +108,8 @@ int __init iriap_init(void)
 	/* Object repository - defined in irias_object.c */
 	irias_objects = hashbin_new(HB_LOCK);
 	if (!irias_objects) {
-		IRDA_WARNING("%s: Can't allocate irias_objects hashbin!\n",
-			     __func__);
+		net_warn_ratelimited("%s: Can't allocate irias_objects hashbin!\n",
+				     __func__);
 		hashbin_delete(iriap, NULL);
 		return -ENOMEM;
 	}
@@ -145,7 +143,7 @@ int __init iriap_init(void)
 	 */
 	server = iriap_open(LSAP_IAS, IAS_SERVER, NULL, NULL);
 	if (!server) {
-		IRDA_DEBUG(0, "%s(), unable to open server\n", __func__);
+		pr_debug("%s(), unable to open server\n", __func__);
 		return -1;
 	}
 	iriap_register_lsap(server, LSAP_IAS, IAS_SERVER);
@@ -177,13 +175,9 @@ struct iriap_cb *iriap_open(__u8 slsap_sel, int mode, void *priv,
 {
 	struct iriap_cb *self;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	self = kzalloc(sizeof(*self), GFP_ATOMIC);
-	if (!self) {
-		IRDA_WARNING("%s: Unable to kmalloc!\n", __func__);
+	if (!self)
 		return NULL;
-	}
 
 	/*
 	 *  Initialize instance
@@ -223,8 +217,6 @@ EXPORT_SYMBOL(iriap_open);
  */
 static void __iriap_close(struct iriap_cb *self)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IAS_MAGIC, return;);
 
@@ -247,8 +239,6 @@ void iriap_close(struct iriap_cb *self)
 {
 	struct iriap_cb *entry;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IAS_MAGIC, return;);
 
@@ -268,8 +258,6 @@ static int iriap_register_lsap(struct iriap_cb *self, __u8 slsap_sel, int mode)
 {
 	notify_t notify;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	irda_notify_init(&notify);
 	notify.connect_confirm       = iriap_connect_confirm;
 	notify.connect_indication    = iriap_connect_indication;
@@ -283,7 +271,8 @@ static int iriap_register_lsap(struct iriap_cb *self, __u8 slsap_sel, int mode)
 
 	self->lsap = irlmp_open_lsap(slsap_sel, &notify, 0);
 	if (self->lsap == NULL) {
-		IRDA_ERROR("%s: Unable to allocated LSAP!\n", __func__);
+		net_err_ratelimited("%s: Unable to allocated LSAP!\n",
+				    __func__);
 		return -1;
 	}
 	self->slsap_sel = self->lsap->slsap_sel;
@@ -303,8 +292,8 @@ static void iriap_disconnect_indication(void *instance, void *sap,
 {
 	struct iriap_cb *self;
 
-	IRDA_DEBUG(4, "%s(), reason=%s [%d]\n", __func__,
-		   irlmp_reason_str(reason), reason);
+	pr_debug("%s(), reason=%s [%d]\n", __func__,
+		 irlmp_reason_str(reason), reason);
 
 	self = instance;
 
@@ -320,7 +309,7 @@ static void iriap_disconnect_indication(void *instance, void *sap,
 		dev_kfree_skb(skb);
 
 	if (self->mode == IAS_CLIENT) {
-		IRDA_DEBUG(4, "%s(), disconnect as client\n", __func__);
+		pr_debug("%s(), disconnect as client\n", __func__);
 
 
 		iriap_do_client_event(self, IAP_LM_DISCONNECT_INDICATION,
@@ -333,7 +322,7 @@ static void iriap_disconnect_indication(void *instance, void *sap,
 		if (self->confirm)
 			self->confirm(IAS_DISCONNECT, 0, NULL, self->priv);
 	} else {
-		IRDA_DEBUG(4, "%s(), disconnect as server\n", __func__);
+		pr_debug("%s(), disconnect as server\n", __func__);
 		iriap_do_server_event(self, IAP_LM_DISCONNECT_INDICATION,
 				      NULL);
 		iriap_close(self);
@@ -347,16 +336,13 @@ static void iriap_disconnect_request(struct iriap_cb *self)
 {
 	struct sk_buff *tx_skb;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IAS_MAGIC, return;);
 
 	tx_skb = alloc_skb(LMP_MAX_HEADER, GFP_ATOMIC);
 	if (tx_skb == NULL) {
-		IRDA_DEBUG(0,
-			   "%s(), Could not allocate an sk_buff of length %d\n",
-			   __func__, LMP_MAX_HEADER);
+		pr_debug("%s(), Could not allocate an sk_buff of length %d\n",
+			 __func__, LMP_MAX_HEADER);
 		return;
 	}
 
@@ -461,14 +447,14 @@ static void iriap_getvaluebyclass_confirm(struct iriap_cb *self,
 	len = get_unaligned_be16(fp + n);
 	n += 2;
 
-	IRDA_DEBUG(4, "%s(), len=%d\n", __func__, len);
+	pr_debug("%s(), len=%d\n", __func__, len);
 
 	/* Get object ID, MSB first */
 	obj_id = get_unaligned_be16(fp + n);
 	n += 2;
 
 	type = fp[n++];
-	IRDA_DEBUG(4, "%s(), Value type = %d\n", __func__, type);
+	pr_debug("%s(), Value type = %d\n", __func__, type);
 
 	switch (type) {
 	case IAS_INTEGER:
@@ -477,7 +463,7 @@ static void iriap_getvaluebyclass_confirm(struct iriap_cb *self,
 		value = irias_new_integer_value(tmp_cpu32);
 
 		/*  Legal values restricted to 0x01-0x6f, page 15 irttp */
-		IRDA_DEBUG(4, "%s(), lsap=%d\n", __func__, value->t.integer);
+		pr_debug("%s(), lsap=%d\n", __func__, value->t.integer);
 		break;
 	case IAS_STRING:
 		charset = fp[n++];
@@ -496,11 +482,11 @@ static void iriap_getvaluebyclass_confirm(struct iriap_cb *self,
 /*		case CS_ISO_8859_9: */
 /*		case CS_UNICODE: */
 		default:
-			IRDA_DEBUG(0, "%s(), charset [%d] %s, not supported\n",
-				   __func__, charset,
-				   charset < ARRAY_SIZE(ias_charset_types) ?
-					ias_charset_types[charset] :
-					"(unknown)");
+			pr_debug("%s(), charset [%d] %s, not supported\n",
+				 __func__, charset,
+				 charset < ARRAY_SIZE(ias_charset_types) ?
+				 ias_charset_types[charset] :
+				 "(unknown)");
 
 			/* Aborting, close connection! */
 			iriap_disconnect_request(self);
@@ -508,12 +494,12 @@ static void iriap_getvaluebyclass_confirm(struct iriap_cb *self,
 			/* break; */
 		}
 		value_len = fp[n++];
-		IRDA_DEBUG(4, "%s(), strlen=%d\n", __func__, value_len);
+		pr_debug("%s(), strlen=%d\n", __func__, value_len);
 
 		/* Make sure the string is null-terminated */
 		if (n + value_len < skb->len)
 			fp[n + value_len] = 0x00;
-		IRDA_DEBUG(4, "Got string %s\n", fp+n);
+		pr_debug("Got string %s\n", fp+n);
 
 		/* Will truncate to IAS_MAX_STRING bytes */
 		value = irias_new_string_value(fp+n);
@@ -539,7 +525,7 @@ static void iriap_getvaluebyclass_confirm(struct iriap_cb *self,
 	if (self->confirm)
 		self->confirm(IAS_SUCCESS, obj_id, value, self->priv);
 	else {
-		IRDA_DEBUG(0, "%s(), missing handler!\n", __func__);
+		pr_debug("%s(), missing handler!\n", __func__);
 		irias_delete_value(value);
 	}
 }
@@ -561,8 +547,6 @@ static void iriap_getvaluebyclass_response(struct iriap_cb *self,
 	__be16 tmp_be16;
 	__u8 *fp;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IAS_MAGIC, return;);
 	IRDA_ASSERT(value != NULL, return;);
@@ -623,12 +607,12 @@ static void iriap_getvaluebyclass_response(struct iriap_cb *self,
 		memcpy(fp+n, value->t.oct_seq, value->len); n+=value->len;
 		break;
 	case IAS_MISSING:
-		IRDA_DEBUG( 3, "%s: sending IAS_MISSING\n", __func__);
+		pr_debug("%s: sending IAS_MISSING\n", __func__);
 		skb_put(tx_skb, 1);
 		fp[n++] = value->type;
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), type not implemented!\n", __func__);
+		pr_debug("%s(), type not implemented!\n", __func__);
 		break;
 	}
 	iriap_do_r_connect_event(self, IAP_CALL_RESPONSE, tx_skb);
@@ -655,8 +639,6 @@ static void iriap_getvaluebyclass_indication(struct iriap_cb *self,
 	__u8 *fp;
 	int n;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IAS_MAGIC, return;);
 	IRDA_ASSERT(skb != NULL, return;);
@@ -678,20 +660,20 @@ static void iriap_getvaluebyclass_indication(struct iriap_cb *self,
 	memcpy(attr, fp+n, attr_len); n+=attr_len;
 	attr[attr_len] = '\0';
 
-	IRDA_DEBUG(4, "LM-IAS: Looking up %s: %s\n", name, attr);
+	pr_debug("LM-IAS: Looking up %s: %s\n", name, attr);
 	obj = irias_find_object(name);
 
 	if (obj == NULL) {
-		IRDA_DEBUG(2, "LM-IAS: Object %s not found\n", name);
+		pr_debug("LM-IAS: Object %s not found\n", name);
 		iriap_getvaluebyclass_response(self, 0x1235, IAS_CLASS_UNKNOWN,
 					       &irias_missing);
 		return;
 	}
-	IRDA_DEBUG(4, "LM-IAS: found %s, id=%d\n", obj->name, obj->id);
+	pr_debug("LM-IAS: found %s, id=%d\n", obj->name, obj->id);
 
 	attrib = irias_find_attrib(obj, attr);
 	if (attrib == NULL) {
-		IRDA_DEBUG(2, "LM-IAS: Attribute %s not found\n", attr);
+		pr_debug("LM-IAS: Attribute %s not found\n", attr);
 		iriap_getvaluebyclass_response(self, obj->id,
 					       IAS_ATTRIB_UNKNOWN,
 					       &irias_missing);
@@ -714,8 +696,6 @@ void iriap_send_ack(struct iriap_cb *self)
 	struct sk_buff *tx_skb;
 	__u8 *frame;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IAS_MAGIC, return;);
 
@@ -745,7 +725,7 @@ void iriap_connect_request(struct iriap_cb *self)
 				    self->saddr, self->daddr,
 				    NULL, NULL);
 	if (ret < 0) {
-		IRDA_DEBUG(0, "%s(), connect failed!\n", __func__);
+		pr_debug("%s(), connect failed!\n", __func__);
 		self->confirm(IAS_DISCONNECT, 0, NULL, self->priv);
 	}
 }
@@ -793,8 +773,6 @@ static void iriap_connect_indication(void *instance, void *sap,
 {
 	struct iriap_cb *self, *new;
 
-	IRDA_DEBUG(1, "%s()\n", __func__);
-
 	self = instance;
 
 	IRDA_ASSERT(skb != NULL, return;);
@@ -804,14 +782,14 @@ static void iriap_connect_indication(void *instance, void *sap,
 	/* Start new server */
 	new = iriap_open(LSAP_IAS, IAS_SERVER, NULL, NULL);
 	if (!new) {
-		IRDA_DEBUG(0, "%s(), open failed\n", __func__);
+		pr_debug("%s(), open failed\n", __func__);
 		goto out;
 	}
 
 	/* Now attach up the new "socket" */
 	new->lsap = irlmp_dup(self->lsap, new);
 	if (!new->lsap) {
-		IRDA_DEBUG(0, "%s(), dup failed!\n", __func__);
+		pr_debug("%s(), dup failed!\n", __func__);
 		goto out;
 	}
 
@@ -841,8 +819,6 @@ static int iriap_data_indication(void *instance, void *sap,
 	__u8  *frame;
 	__u8  opcode;
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	self = instance;
 
 	IRDA_ASSERT(skb != NULL, return 0;);
@@ -853,21 +829,20 @@ static int iriap_data_indication(void *instance, void *sap,
 
 	if (self->mode == IAS_SERVER) {
 		/* Call server */
-		IRDA_DEBUG(4, "%s(), Calling server!\n", __func__);
+		pr_debug("%s(), Calling server!\n", __func__);
 		iriap_do_r_connect_event(self, IAP_RECV_F_LST, skb);
 		goto out;
 	}
 	opcode = frame[0];
 	if (~opcode & IAP_LST) {
-		IRDA_WARNING("%s:, IrIAS multiframe commands or "
-			     "results is not implemented yet!\n",
-			     __func__);
+		net_warn_ratelimited("%s:, IrIAS multiframe commands or results is not implemented yet!\n",
+				     __func__);
 		goto out;
 	}
 
 	/* Check for ack frames since they don't contain any data */
 	if (opcode & IAP_ACK) {
-		IRDA_DEBUG(0, "%s() Got ack frame!\n", __func__);
+		pr_debug("%s() Got ack frame!\n", __func__);
 		goto out;
 	}
 
@@ -875,7 +850,7 @@ static int iriap_data_indication(void *instance, void *sap,
 
 	switch (opcode) {
 	case GET_INFO_BASE:
-		IRDA_DEBUG(0, "IrLMP GetInfoBaseDetails not implemented!\n");
+		pr_debug("IrLMP GetInfoBaseDetails not implemented!\n");
 		break;
 	case GET_VALUE_BY_CLASS:
 		iriap_do_call_event(self, IAP_RECV_F_LST, NULL);
@@ -885,7 +860,7 @@ static int iriap_data_indication(void *instance, void *sap,
 			iriap_getvaluebyclass_confirm(self, skb);
 			break;
 		case IAS_CLASS_UNKNOWN:
-			IRDA_DEBUG(1, "%s(), No such class!\n", __func__);
+			pr_debug("%s(), No such class!\n", __func__);
 			/* Finished, close connection! */
 			iriap_disconnect_request(self);
 
@@ -898,7 +873,7 @@ static int iriap_data_indication(void *instance, void *sap,
 					      self->priv);
 			break;
 		case IAS_ATTRIB_UNKNOWN:
-			IRDA_DEBUG(1, "%s(), No such attribute!\n", __func__);
+			pr_debug("%s(), No such attribute!\n", __func__);
 			/* Finished, close connection! */
 			iriap_disconnect_request(self);
 
@@ -913,8 +888,8 @@ static int iriap_data_indication(void *instance, void *sap,
 		}
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), Unknown op-code: %02x\n", __func__,
-			   opcode);
+		pr_debug("%s(), Unknown op-code: %02x\n", __func__,
+			 opcode);
 		break;
 	}
 
@@ -935,8 +910,6 @@ void iriap_call_indication(struct iriap_cb *self, struct sk_buff *skb)
 	__u8 *fp;
 	__u8 opcode;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IAS_MAGIC, return;);
 	IRDA_ASSERT(skb != NULL, return;);
@@ -945,16 +918,16 @@ void iriap_call_indication(struct iriap_cb *self, struct sk_buff *skb)
 
 	opcode = fp[0];
 	if (~opcode & 0x80) {
-		IRDA_WARNING("%s: IrIAS multiframe commands or results "
-			     "is not implemented yet!\n", __func__);
+		net_warn_ratelimited("%s: IrIAS multiframe commands or results is not implemented yet!\n",
+				     __func__);
 		return;
 	}
 	opcode &= 0x7f; /* Mask away LST bit */
 
 	switch (opcode) {
 	case GET_INFO_BASE:
-		IRDA_WARNING("%s: GetInfoBaseDetails not implemented yet!\n",
-			     __func__);
+		net_warn_ratelimited("%s: GetInfoBaseDetails not implemented yet!\n",
+				     __func__);
 		break;
 	case GET_VALUE_BY_CLASS:
 		iriap_getvaluebyclass_indication(self, skb);
diff --git a/net/irda/iriap_event.c b/net/irda/iriap_event.c
index 703774e29e32..e6098b2e048a 100644
--- a/net/irda/iriap_event.c
+++ b/net/irda/iriap_event.c
@@ -187,7 +187,7 @@ static void state_s_disconnect(struct iriap_cb *self, IRIAP_EVENT event,
 	case IAP_LM_DISCONNECT_INDICATION:
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), Unknown event %d\n", __func__, event);
+		pr_debug("%s(), Unknown event %d\n", __func__, event);
 		break;
 	}
 }
@@ -219,7 +219,7 @@ static void state_s_connecting(struct iriap_cb *self, IRIAP_EVENT event,
 		iriap_next_client_state(self, S_DISCONNECT);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), Unknown event %d\n", __func__, event);
+		pr_debug("%s(), Unknown event %d\n", __func__, event);
 		break;
 	}
 }
@@ -243,7 +243,7 @@ static void state_s_call(struct iriap_cb *self, IRIAP_EVENT event,
 		iriap_next_client_state(self, S_DISCONNECT);
 		break;
 	default:
-		IRDA_DEBUG(0, "state_s_call: Unknown event %d\n", event);
+		pr_debug("state_s_call: Unknown event %d\n", event);
 		break;
 	}
 }
@@ -271,7 +271,7 @@ static void state_s_make_call(struct iriap_cb *self, IRIAP_EVENT event,
 		iriap_next_call_state(self, S_OUTSTANDING);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), Unknown event %d\n", __func__, event);
+		pr_debug("%s(), Unknown event %d\n", __func__, event);
 		break;
 	}
 }
@@ -285,7 +285,7 @@ static void state_s_make_call(struct iriap_cb *self, IRIAP_EVENT event,
 static void state_s_calling(struct iriap_cb *self, IRIAP_EVENT event,
 			    struct sk_buff *skb)
 {
-	IRDA_DEBUG(0, "%s(), Not implemented\n", __func__);
+	pr_debug("%s(), Not implemented\n", __func__);
 }
 
 /*
@@ -307,7 +307,7 @@ static void state_s_outstanding(struct iriap_cb *self, IRIAP_EVENT event,
 		iriap_next_call_state(self, S_WAIT_FOR_CALL);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), Unknown event %d\n", __func__, event);
+		pr_debug("%s(), Unknown event %d\n", __func__, event);
 		break;
 	}
 }
@@ -320,7 +320,7 @@ static void state_s_outstanding(struct iriap_cb *self, IRIAP_EVENT event,
 static void state_s_replying(struct iriap_cb *self, IRIAP_EVENT event,
 			     struct sk_buff *skb)
 {
-	IRDA_DEBUG(0, "%s(), Not implemented\n", __func__);
+	pr_debug("%s(), Not implemented\n", __func__);
 }
 
 /*
@@ -332,7 +332,7 @@ static void state_s_replying(struct iriap_cb *self, IRIAP_EVENT event,
 static void state_s_wait_for_call(struct iriap_cb *self, IRIAP_EVENT event,
 				  struct sk_buff *skb)
 {
-	IRDA_DEBUG(0, "%s(), Not implemented\n", __func__);
+	pr_debug("%s(), Not implemented\n", __func__);
 }
 
 
@@ -345,7 +345,7 @@ static void state_s_wait_for_call(struct iriap_cb *self, IRIAP_EVENT event,
 static void state_s_wait_active(struct iriap_cb *self, IRIAP_EVENT event,
 				struct sk_buff *skb)
 {
-	IRDA_DEBUG(0, "%s(), Not implemented\n", __func__);
+	pr_debug("%s(), Not implemented\n", __func__);
 }
 
 /**************************************************************************
@@ -368,10 +368,8 @@ static void state_r_disconnect(struct iriap_cb *self, IRIAP_EVENT event,
 	switch (event) {
 	case IAP_LM_CONNECT_INDICATION:
 		tx_skb = alloc_skb(LMP_MAX_HEADER, GFP_ATOMIC);
-		if (tx_skb == NULL) {
-			IRDA_WARNING("%s: unable to malloc!\n", __func__);
+		if (tx_skb == NULL)
 			return;
-		}
 
 		/* Reserve space for MUX_CONTROL and LAP header */
 		skb_reserve(tx_skb, LMP_MAX_HEADER);
@@ -388,7 +386,7 @@ static void state_r_disconnect(struct iriap_cb *self, IRIAP_EVENT event,
 		iriap_next_r_connect_state(self, R_RECEIVING);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), unknown event %d\n", __func__, event);
+		pr_debug("%s(), unknown event %d\n", __func__, event);
 		break;
 	}
 }
@@ -399,8 +397,6 @@ static void state_r_disconnect(struct iriap_cb *self, IRIAP_EVENT event,
 static void state_r_call(struct iriap_cb *self, IRIAP_EVENT event,
 			 struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	switch (event) {
 	case IAP_LM_DISCONNECT_INDICATION:
 		/* Abort call */
@@ -408,7 +404,7 @@ static void state_r_call(struct iriap_cb *self, IRIAP_EVENT event,
 		iriap_next_r_connect_state(self, R_WAITING);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), unknown event!\n", __func__);
+		pr_debug("%s(), unknown event!\n", __func__);
 		break;
 	}
 }
@@ -423,13 +419,13 @@ static void state_r_call(struct iriap_cb *self, IRIAP_EVENT event,
 static void state_r_waiting(struct iriap_cb *self, IRIAP_EVENT event,
 			    struct sk_buff *skb)
 {
-	IRDA_DEBUG(0, "%s(), Not implemented\n", __func__);
+	pr_debug("%s(), Not implemented\n", __func__);
 }
 
 static void state_r_wait_active(struct iriap_cb *self, IRIAP_EVENT event,
 				struct sk_buff *skb)
 {
-	IRDA_DEBUG(0, "%s(), Not implemented\n", __func__);
+	pr_debug("%s(), Not implemented\n", __func__);
 }
 
 /*
@@ -441,8 +437,6 @@ static void state_r_wait_active(struct iriap_cb *self, IRIAP_EVENT event,
 static void state_r_receiving(struct iriap_cb *self, IRIAP_EVENT event,
 			      struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	switch (event) {
 	case IAP_RECV_F_LST:
 		iriap_next_r_connect_state(self, R_EXECUTE);
@@ -450,7 +444,7 @@ static void state_r_receiving(struct iriap_cb *self, IRIAP_EVENT event,
 		iriap_call_indication(self, skb);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), unknown event!\n", __func__);
+		pr_debug("%s(), unknown event!\n", __func__);
 		break;
 	}
 }
@@ -464,8 +458,6 @@ static void state_r_receiving(struct iriap_cb *self, IRIAP_EVENT event,
 static void state_r_execute(struct iriap_cb *self, IRIAP_EVENT event,
 			    struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(skb != NULL, return;);
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IAS_MAGIC, return;);
@@ -485,7 +477,7 @@ static void state_r_execute(struct iriap_cb *self, IRIAP_EVENT event,
 		irlmp_data_request(self->lsap, skb);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), unknown event!\n", __func__);
+		pr_debug("%s(), unknown event!\n", __func__);
 		break;
 	}
 }
@@ -493,7 +485,7 @@ static void state_r_execute(struct iriap_cb *self, IRIAP_EVENT event,
 static void state_r_returning(struct iriap_cb *self, IRIAP_EVENT event,
 			      struct sk_buff *skb)
 {
-	IRDA_DEBUG(0, "%s(), event=%d\n", __func__, event);
+	pr_debug("%s(), event=%d\n", __func__, event);
 
 	switch (event) {
 	case IAP_RECV_F_LST:
diff --git a/net/irda/irias_object.c b/net/irda/irias_object.c
index f07ed9fd5792..53b86d0e1630 100644
--- a/net/irda/irias_object.c
+++ b/net/irda/irias_object.c
@@ -48,20 +48,18 @@ struct ias_object *irias_new_object( char *name, int id)
 {
 	struct ias_object *obj;
 
-	IRDA_DEBUG( 4, "%s()\n", __func__);
-
 	obj = kzalloc(sizeof(struct ias_object), GFP_ATOMIC);
 	if (obj == NULL) {
-		IRDA_WARNING("%s(), Unable to allocate object!\n",
-			     __func__);
+		net_warn_ratelimited("%s(), Unable to allocate object!\n",
+				     __func__);
 		return NULL;
 	}
 
 	obj->magic = IAS_OBJECT_MAGIC;
 	obj->name = kstrndup(name, IAS_MAX_CLASSNAME, GFP_ATOMIC);
 	if (!obj->name) {
-		IRDA_WARNING("%s(), Unable to allocate name!\n",
-			     __func__);
+		net_warn_ratelimited("%s(), Unable to allocate name!\n",
+				     __func__);
 		kfree(obj);
 		return NULL;
 	}
@@ -73,8 +71,8 @@ struct ias_object *irias_new_object( char *name, int id)
 	obj->attribs = hashbin_new(HB_LOCK);
 
 	if (obj->attribs == NULL) {
-		IRDA_WARNING("%s(), Unable to allocate attribs!\n",
-			     __func__);
+		net_warn_ratelimited("%s(), Unable to allocate attribs!\n",
+				     __func__);
 		kfree(obj->name);
 		kfree(obj);
 		return NULL;
@@ -134,8 +132,8 @@ int irias_delete_object(struct ias_object *obj)
 	/* Remove from list */
 	node = hashbin_remove_this(irias_objects, (irda_queue_t *) obj);
 	if (!node)
-		IRDA_DEBUG( 0, "%s(), object already removed!\n",
-			    __func__);
+		pr_debug("%s(), object already removed!\n",
+			 __func__);
 
 	/* Destroy */
 	__irias_delete_object(obj);
@@ -269,8 +267,8 @@ int irias_object_change_attribute(char *obj_name, char *attrib_name,
 	/* Find object */
 	obj = hashbin_lock_find(irias_objects, 0, obj_name);
 	if (obj == NULL) {
-		IRDA_WARNING("%s: Unable to find object: %s\n", __func__,
-			     obj_name);
+		net_warn_ratelimited("%s: Unable to find object: %s\n",
+				     __func__, obj_name);
 		return -1;
 	}
 
@@ -280,15 +278,15 @@ int irias_object_change_attribute(char *obj_name, char *attrib_name,
 	/* Find attribute */
 	attrib = hashbin_find(obj->attribs, 0, attrib_name);
 	if (attrib == NULL) {
-		IRDA_WARNING("%s: Unable to find attribute: %s\n",
-			     __func__, attrib_name);
+		net_warn_ratelimited("%s: Unable to find attribute: %s\n",
+				     __func__, attrib_name);
 		spin_unlock_irqrestore(&obj->attribs->hb_spinlock, flags);
 		return -1;
 	}
 
 	if ( attrib->value->type != new_value->type) {
-		IRDA_DEBUG( 0, "%s(), changing value type not allowed!\n",
-			    __func__);
+		pr_debug("%s(), changing value type not allowed!\n",
+			 __func__);
 		spin_unlock_irqrestore(&obj->attribs->hb_spinlock, flags);
 		return -1;
 	}
@@ -322,8 +320,8 @@ void irias_add_integer_attrib(struct ias_object *obj, char *name, int value,
 
 	attrib = kzalloc(sizeof(struct ias_attrib), GFP_ATOMIC);
 	if (attrib == NULL) {
-		IRDA_WARNING("%s: Unable to allocate attribute!\n",
-			     __func__);
+		net_warn_ratelimited("%s: Unable to allocate attribute!\n",
+				     __func__);
 		return;
 	}
 
@@ -333,8 +331,8 @@ void irias_add_integer_attrib(struct ias_object *obj, char *name, int value,
 	/* Insert value */
 	attrib->value = irias_new_integer_value(value);
 	if (!attrib->name || !attrib->value) {
-		IRDA_WARNING("%s: Unable to allocate attribute!\n",
-			     __func__);
+		net_warn_ratelimited("%s: Unable to allocate attribute!\n",
+				     __func__);
 		if (attrib->value)
 			irias_delete_value(attrib->value);
 		kfree(attrib->name);
@@ -366,8 +364,8 @@ void irias_add_octseq_attrib(struct ias_object *obj, char *name, __u8 *octets,
 
 	attrib = kzalloc(sizeof(struct ias_attrib), GFP_ATOMIC);
 	if (attrib == NULL) {
-		IRDA_WARNING("%s: Unable to allocate attribute!\n",
-			     __func__);
+		net_warn_ratelimited("%s: Unable to allocate attribute!\n",
+				     __func__);
 		return;
 	}
 
@@ -376,8 +374,8 @@ void irias_add_octseq_attrib(struct ias_object *obj, char *name, __u8 *octets,
 
 	attrib->value = irias_new_octseq_value( octets, len);
 	if (!attrib->name || !attrib->value) {
-		IRDA_WARNING("%s: Unable to allocate attribute!\n",
-			     __func__);
+		net_warn_ratelimited("%s: Unable to allocate attribute!\n",
+				     __func__);
 		if (attrib->value)
 			irias_delete_value(attrib->value);
 		kfree(attrib->name);
@@ -408,8 +406,8 @@ void irias_add_string_attrib(struct ias_object *obj, char *name, char *value,
 
 	attrib = kzalloc(sizeof( struct ias_attrib), GFP_ATOMIC);
 	if (attrib == NULL) {
-		IRDA_WARNING("%s: Unable to allocate attribute!\n",
-			     __func__);
+		net_warn_ratelimited("%s: Unable to allocate attribute!\n",
+				     __func__);
 		return;
 	}
 
@@ -418,8 +416,8 @@ void irias_add_string_attrib(struct ias_object *obj, char *name, char *value,
 
 	attrib->value = irias_new_string_value(value);
 	if (!attrib->name || !attrib->value) {
-		IRDA_WARNING("%s: Unable to allocate attribute!\n",
-			     __func__);
+		net_warn_ratelimited("%s: Unable to allocate attribute!\n",
+				     __func__);
 		if (attrib->value)
 			irias_delete_value(attrib->value);
 		kfree(attrib->name);
@@ -442,10 +440,8 @@ struct ias_value *irias_new_integer_value(int integer)
 	struct ias_value *value;
 
 	value = kzalloc(sizeof(struct ias_value), GFP_ATOMIC);
-	if (value == NULL) {
-		IRDA_WARNING("%s: Unable to kmalloc!\n", __func__);
+	if (value == NULL)
 		return NULL;
-	}
 
 	value->type = IAS_INTEGER;
 	value->len = 4;
@@ -467,16 +463,14 @@ struct ias_value *irias_new_string_value(char *string)
 	struct ias_value *value;
 
 	value = kzalloc(sizeof(struct ias_value), GFP_ATOMIC);
-	if (value == NULL) {
-		IRDA_WARNING("%s: Unable to kmalloc!\n", __func__);
+	if (value == NULL)
 		return NULL;
-	}
 
 	value->type = IAS_STRING;
 	value->charset = CS_ASCII;
 	value->t.string = kstrndup(string, IAS_MAX_STRING, GFP_ATOMIC);
 	if (!value->t.string) {
-		IRDA_WARNING("%s: Unable to kmalloc!\n", __func__);
+		net_warn_ratelimited("%s: Unable to kmalloc!\n", __func__);
 		kfree(value);
 		return NULL;
 	}
@@ -498,10 +492,8 @@ struct ias_value *irias_new_octseq_value(__u8 *octseq , int len)
 	struct ias_value *value;
 
 	value = kzalloc(sizeof(struct ias_value), GFP_ATOMIC);
-	if (value == NULL) {
-		IRDA_WARNING("%s: Unable to kmalloc!\n", __func__);
+	if (value == NULL)
 		return NULL;
-	}
 
 	value->type = IAS_OCT_SEQ;
 	/* Check length */
@@ -511,7 +503,7 @@ struct ias_value *irias_new_octseq_value(__u8 *octseq , int len)
 
 	value->t.oct_seq = kmemdup(octseq, len, GFP_ATOMIC);
 	if (value->t.oct_seq == NULL){
-		IRDA_WARNING("%s: Unable to kmalloc!\n", __func__);
+		net_warn_ratelimited("%s: Unable to kmalloc!\n", __func__);
 		kfree(value);
 		return NULL;
 	}
@@ -523,10 +515,8 @@ struct ias_value *irias_new_missing_value(void)
 	struct ias_value *value;
 
 	value = kzalloc(sizeof(struct ias_value), GFP_ATOMIC);
-	if (value == NULL) {
-		IRDA_WARNING("%s: Unable to kmalloc!\n", __func__);
+	if (value == NULL)
 		return NULL;
-	}
 
 	value->type = IAS_MISSING;
 
@@ -541,8 +531,6 @@ struct ias_value *irias_new_missing_value(void)
  */
 void irias_delete_value(struct ias_value *value)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(value != NULL, return;);
 
 	switch (value->type) {
@@ -559,7 +547,7 @@ void irias_delete_value(struct ias_value *value)
 		 kfree(value->t.oct_seq);
 		 break;
 	default:
-		IRDA_DEBUG(0, "%s(), Unknown value type!\n", __func__);
+		pr_debug("%s(), Unknown value type!\n", __func__);
 		break;
 	}
 	kfree(value);
diff --git a/net/irda/irlan/irlan_client.c b/net/irda/irlan/irlan_client.c
index 42cf1390ce9c..c5837a40c78e 100644
--- a/net/irda/irlan/irlan_client.c
+++ b/net/irda/irlan/irlan_client.c
@@ -72,8 +72,6 @@ static void irlan_client_kick_timer_expired(void *data)
 {
 	struct irlan_cb *self = (struct irlan_cb *) data;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
@@ -91,8 +89,6 @@ static void irlan_client_kick_timer_expired(void *data)
 
 static void irlan_client_start_kick_timer(struct irlan_cb *self, int timeout)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	irda_start_timer(&self->client.kick_timer, timeout, (void *) self,
 			 irlan_client_kick_timer_expired);
 }
@@ -105,8 +101,6 @@ static void irlan_client_start_kick_timer(struct irlan_cb *self, int timeout)
  */
 void irlan_client_wakeup(struct irlan_cb *self, __u32 saddr, __u32 daddr)
 {
-	IRDA_DEBUG(1, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
@@ -117,7 +111,7 @@ void irlan_client_wakeup(struct irlan_cb *self, __u32 saddr, __u32 daddr)
 	if ((self->client.state != IRLAN_IDLE) ||
 	    (self->provider.access_type == ACCESS_DIRECT))
 	{
-			IRDA_DEBUG(0, "%s(), already awake!\n", __func__ );
+		pr_debug("%s(), already awake!\n", __func__);
 			return;
 	}
 
@@ -126,7 +120,7 @@ void irlan_client_wakeup(struct irlan_cb *self, __u32 saddr, __u32 daddr)
 	self->daddr = daddr;
 
 	if (self->disconnect_reason == LM_USER_REQUEST) {
-			IRDA_DEBUG(0, "%s(), still stopped by user\n", __func__ );
+		pr_debug("%s(), still stopped by user\n", __func__);
 			return;
 	}
 
@@ -153,8 +147,6 @@ void irlan_client_discovery_indication(discinfo_t *discovery,
 	struct irlan_cb *self;
 	__u32 saddr, daddr;
 
-	IRDA_DEBUG(1, "%s()\n", __func__ );
-
 	IRDA_ASSERT(discovery != NULL, return;);
 
 	/*
@@ -175,8 +167,8 @@ void irlan_client_discovery_indication(discinfo_t *discovery,
 	if (self) {
 		IRDA_ASSERT(self->magic == IRLAN_MAGIC, goto out;);
 
-		IRDA_DEBUG(1, "%s(), Found instance (%08x)!\n", __func__ ,
-		      daddr);
+		pr_debug("%s(), Found instance (%08x)!\n", __func__ ,
+			 daddr);
 
 		irlan_client_wakeup(self, saddr, daddr);
 	}
@@ -195,8 +187,6 @@ static int irlan_client_ctrl_data_indication(void *instance, void *sap,
 {
 	struct irlan_cb *self;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	self = instance;
 
 	IRDA_ASSERT(self != NULL, return -1;);
@@ -206,7 +196,7 @@ static int irlan_client_ctrl_data_indication(void *instance, void *sap,
 	irlan_do_client_event(self, IRLAN_DATA_INDICATION, skb);
 
 	/* Ready for a new command */
-	IRDA_DEBUG(2, "%s(), clearing tx_busy\n", __func__ );
+	pr_debug("%s(), clearing tx_busy\n", __func__);
 	self->client.tx_busy = FALSE;
 
 	/* Check if we have some queued commands waiting to be sent */
@@ -223,7 +213,7 @@ static void irlan_client_ctrl_disconnect_indication(void *instance, void *sap,
 	struct tsap_cb *tsap;
 	struct sk_buff *skb;
 
-	IRDA_DEBUG(4, "%s(), reason=%d\n", __func__ , reason);
+	pr_debug("%s(), reason=%d\n", __func__ , reason);
 
 	self = instance;
 	tsap = sap;
@@ -255,8 +245,6 @@ static void irlan_client_open_ctrl_tsap(struct irlan_cb *self)
 	struct tsap_cb *tsap;
 	notify_t notify;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
@@ -275,7 +263,7 @@ static void irlan_client_open_ctrl_tsap(struct irlan_cb *self)
 
 	tsap = irttp_open_tsap(LSAP_ANY, DEFAULT_INITIAL_CREDIT, &notify);
 	if (!tsap) {
-		IRDA_DEBUG(2, "%s(), Got no tsap!\n", __func__ );
+		pr_debug("%s(), Got no tsap!\n", __func__);
 		return;
 	}
 	self->client.tsap_ctrl = tsap;
@@ -295,8 +283,6 @@ static void irlan_client_ctrl_connect_confirm(void *instance, void *sap,
 {
 	struct irlan_cb *self;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	self = instance;
 
 	IRDA_ASSERT(self != NULL, return;);
@@ -323,34 +309,34 @@ static void print_ret_code(__u8 code)
 		printk(KERN_INFO "Success\n");
 		break;
 	case 1:
-		IRDA_WARNING("IrLAN: Insufficient resources\n");
+		net_warn_ratelimited("IrLAN: Insufficient resources\n");
 		break;
 	case 2:
-		IRDA_WARNING("IrLAN: Invalid command format\n");
+		net_warn_ratelimited("IrLAN: Invalid command format\n");
 		break;
 	case 3:
-		IRDA_WARNING("IrLAN: Command not supported\n");
+		net_warn_ratelimited("IrLAN: Command not supported\n");
 		break;
 	case 4:
-		IRDA_WARNING("IrLAN: Parameter not supported\n");
+		net_warn_ratelimited("IrLAN: Parameter not supported\n");
 		break;
 	case 5:
-		IRDA_WARNING("IrLAN: Value not supported\n");
+		net_warn_ratelimited("IrLAN: Value not supported\n");
 		break;
 	case 6:
-		IRDA_WARNING("IrLAN: Not open\n");
+		net_warn_ratelimited("IrLAN: Not open\n");
 		break;
 	case 7:
-		IRDA_WARNING("IrLAN: Authentication required\n");
+		net_warn_ratelimited("IrLAN: Authentication required\n");
 		break;
 	case 8:
-		IRDA_WARNING("IrLAN: Invalid password\n");
+		net_warn_ratelimited("IrLAN: Invalid password\n");
 		break;
 	case 9:
-		IRDA_WARNING("IrLAN: Protocol error\n");
+		net_warn_ratelimited("IrLAN: Protocol error\n");
 		break;
 	case 255:
-		IRDA_WARNING("IrLAN: Asynchronous status\n");
+		net_warn_ratelimited("IrLAN: Asynchronous status\n");
 		break;
 	}
 }
@@ -374,13 +360,13 @@ void irlan_client_parse_response(struct irlan_cb *self, struct sk_buff *skb)
 
 	IRDA_ASSERT(skb != NULL, return;);
 
-	IRDA_DEBUG(4, "%s() skb->len=%d\n", __func__ , (int) skb->len);
+	pr_debug("%s() skb->len=%d\n", __func__ , (int)skb->len);
 
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
 	if (!skb) {
-		IRDA_ERROR("%s(), Got NULL skb!\n", __func__);
+		net_err_ratelimited("%s(), Got NULL skb!\n", __func__);
 		return;
 	}
 	frame = skb->data;
@@ -405,7 +391,7 @@ void irlan_client_parse_response(struct irlan_cb *self, struct sk_buff *skb)
 	/* How many parameters? */
 	count = frame[1];
 
-	IRDA_DEBUG(4, "%s(), got %d parameters\n", __func__ , count);
+	pr_debug("%s(), got %d parameters\n", __func__ , count);
 
 	ptr = frame+2;
 
@@ -413,7 +399,7 @@ void irlan_client_parse_response(struct irlan_cb *self, struct sk_buff *skb)
 	for (i=0; i<count;i++) {
 		ret = irlan_extract_param(ptr, name, value, &val_len);
 		if (ret < 0) {
-			IRDA_DEBUG(2, "%s(), IrLAN, Error!\n", __func__ );
+			pr_debug("%s(), IrLAN, Error!\n", __func__);
 			break;
 		}
 		ptr += ret;
@@ -437,7 +423,7 @@ static void irlan_check_response_param(struct irlan_cb *self, char *param,
 	__u8 *bytes;
 	int i;
 
-	IRDA_DEBUG(4, "%s(), parm=%s\n", __func__ , param);
+	pr_debug("%s(), parm=%s\n", __func__ , param);
 
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
@@ -475,13 +461,13 @@ static void irlan_check_response_param(struct irlan_cb *self, char *param,
 		else if (strcmp(value, "HOSTED") == 0)
 			self->client.access_type = ACCESS_HOSTED;
 		else {
-			IRDA_DEBUG(2, "%s(), unknown access type!\n", __func__ );
+			pr_debug("%s(), unknown access type!\n", __func__);
 		}
 	}
 	/* IRLAN version */
 	if (strcmp(param, "IRLAN_VER") == 0) {
-		IRDA_DEBUG(4, "IrLAN version %d.%d\n", (__u8) value[0],
-		      (__u8) value[1]);
+		pr_debug("IrLAN version %d.%d\n", (__u8)value[0],
+			 (__u8)value[1]);
 
 		self->version[0] = value[0];
 		self->version[1] = value[1];
@@ -490,37 +476,37 @@ static void irlan_check_response_param(struct irlan_cb *self, char *param,
 	/* Which remote TSAP to use for data channel */
 	if (strcmp(param, "DATA_CHAN") == 0) {
 		self->dtsap_sel_data = value[0];
-		IRDA_DEBUG(4, "Data TSAP = %02x\n", self->dtsap_sel_data);
+		pr_debug("Data TSAP = %02x\n", self->dtsap_sel_data);
 		return;
 	}
 	if (strcmp(param, "CON_ARB") == 0) {
 		memcpy(&tmp_cpu, value, 2); /* Align value */
 		le16_to_cpus(&tmp_cpu);     /* Convert to host order */
 		self->client.recv_arb_val = tmp_cpu;
-		IRDA_DEBUG(2, "%s(), receive arb val=%d\n", __func__ ,
-			   self->client.recv_arb_val);
+		pr_debug("%s(), receive arb val=%d\n", __func__ ,
+			 self->client.recv_arb_val);
 	}
 	if (strcmp(param, "MAX_FRAME") == 0) {
 		memcpy(&tmp_cpu, value, 2); /* Align value */
 		le16_to_cpus(&tmp_cpu);     /* Convert to host order */
 		self->client.max_frame = tmp_cpu;
-		IRDA_DEBUG(4, "%s(), max frame=%d\n", __func__ ,
-			   self->client.max_frame);
+		pr_debug("%s(), max frame=%d\n", __func__ ,
+			 self->client.max_frame);
 	}
 
 	/* RECONNECT_KEY, in case the link goes down! */
 	if (strcmp(param, "RECONNECT_KEY") == 0) {
-		IRDA_DEBUG(4, "Got reconnect key: ");
+		pr_debug("Got reconnect key: ");
 		/* for (i = 0; i < val_len; i++) */
 /* 			printk("%02x", value[i]); */
 		memcpy(self->client.reconnect_key, value, val_len);
 		self->client.key_len = val_len;
-		IRDA_DEBUG(4, "\n");
+		pr_debug("\n");
 	}
 	/* FILTER_ENTRY, have we got an ethernet address? */
 	if (strcmp(param, "FILTER_ENTRY") == 0) {
 		bytes = value;
-		IRDA_DEBUG(4, "Ethernet address = %pM\n", bytes);
+		pr_debug("Ethernet address = %pM\n", bytes);
 		for (i = 0; i < 6; i++)
 			self->dev->dev_addr[i] = bytes[i];
 	}
@@ -537,8 +523,6 @@ void irlan_client_get_value_confirm(int result, __u16 obj_id,
 {
 	struct irlan_cb *self;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(priv != NULL, return;);
 
 	self = priv;
@@ -550,7 +534,7 @@ void irlan_client_get_value_confirm(int result, __u16 obj_id,
 
 	/* Check if request succeeded */
 	if (result != IAS_SUCCESS) {
-		IRDA_DEBUG(2, "%s(), got NULL value!\n", __func__ );
+		pr_debug("%s(), got NULL value!\n", __func__);
 		irlan_do_client_event(self, IRLAN_IAS_PROVIDER_NOT_AVAIL,
 				      NULL);
 		return;
@@ -568,7 +552,7 @@ void irlan_client_get_value_confirm(int result, __u16 obj_id,
 		irias_delete_value(value);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), unknown type!\n", __func__ );
+		pr_debug("%s(), unknown type!\n", __func__);
 		break;
 	}
 	irlan_do_client_event(self, IRLAN_IAS_PROVIDER_NOT_AVAIL, NULL);
diff --git a/net/irda/irlan/irlan_client_event.c b/net/irda/irlan/irlan_client_event.c
index 8d5a8ebc444f..cc93fabbbb19 100644
--- a/net/irda/irlan/irlan_client_event.c
+++ b/net/irda/irlan/irlan_client_event.c
@@ -92,16 +92,14 @@ void irlan_do_client_event(struct irlan_cb *self, IRLAN_EVENT event,
 static int irlan_client_state_idle(struct irlan_cb *self, IRLAN_EVENT event,
 				   struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return -1;);
 
 	switch (event) {
 	case IRLAN_DISCOVERY_INDICATION:
 		if (self->client.iriap) {
-			IRDA_WARNING("%s(), busy with a previous query\n",
-				     __func__);
+			net_warn_ratelimited("%s(), busy with a previous query\n",
+					     __func__);
 			return -EBUSY;
 		}
 
@@ -114,10 +112,10 @@ static int irlan_client_state_idle(struct irlan_cb *self, IRLAN_EVENT event,
 					      "IrLAN", "IrDA:TinyTP:LsapSel");
 		break;
 	case IRLAN_WATCHDOG_TIMEOUT:
-		IRDA_DEBUG(2, "%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__ );
+		pr_debug("%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__);
 		break;
 	default:
-		IRDA_DEBUG(4, "%s(), Unknown event %d\n", __func__ , event);
+		pr_debug("%s(), Unknown event %d\n", __func__ , event);
 		break;
 	}
 	if (skb)
@@ -136,8 +134,6 @@ static int irlan_client_state_idle(struct irlan_cb *self, IRLAN_EVENT event,
 static int irlan_client_state_query(struct irlan_cb *self, IRLAN_EVENT event,
 				    struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return -1;);
 
@@ -154,7 +150,7 @@ static int irlan_client_state_query(struct irlan_cb *self, IRLAN_EVENT event,
 		irlan_next_client_state(self, IRLAN_CONN);
 		break;
 	case IRLAN_IAS_PROVIDER_NOT_AVAIL:
-		IRDA_DEBUG(2, "%s(), IAS_PROVIDER_NOT_AVAIL\n", __func__ );
+		pr_debug("%s(), IAS_PROVIDER_NOT_AVAIL\n", __func__);
 		irlan_next_client_state(self, IRLAN_IDLE);
 
 		/* Give the client a kick! */
@@ -167,10 +163,10 @@ static int irlan_client_state_query(struct irlan_cb *self, IRLAN_EVENT event,
 		irlan_next_client_state(self, IRLAN_IDLE);
 		break;
 	case IRLAN_WATCHDOG_TIMEOUT:
-		IRDA_DEBUG(2, "%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__ );
+		pr_debug("%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown event %d\n", __func__ , event);
+		pr_debug("%s(), Unknown event %d\n", __func__ , event);
 		break;
 	}
 	if (skb)
@@ -189,8 +185,6 @@ static int irlan_client_state_query(struct irlan_cb *self, IRLAN_EVENT event,
 static int irlan_client_state_conn(struct irlan_cb *self, IRLAN_EVENT event,
 				   struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 
 	switch (event) {
@@ -204,10 +198,10 @@ static int irlan_client_state_conn(struct irlan_cb *self, IRLAN_EVENT event,
 		irlan_next_client_state(self, IRLAN_IDLE);
 		break;
 	case IRLAN_WATCHDOG_TIMEOUT:
-		IRDA_DEBUG(2, "%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__ );
+		pr_debug("%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown event %d\n", __func__ , event);
+		pr_debug("%s(), Unknown event %d\n", __func__ , event);
 		break;
 	}
 	if (skb)
@@ -224,8 +218,6 @@ static int irlan_client_state_conn(struct irlan_cb *self, IRLAN_EVENT event,
 static int irlan_client_state_info(struct irlan_cb *self, IRLAN_EVENT event,
 				   struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 
 	switch (event) {
@@ -244,10 +236,10 @@ static int irlan_client_state_info(struct irlan_cb *self, IRLAN_EVENT event,
 		irlan_next_client_state(self, IRLAN_IDLE);
 		break;
 	case IRLAN_WATCHDOG_TIMEOUT:
-		IRDA_DEBUG(2, "%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__ );
+		pr_debug("%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown event %d\n", __func__ , event);
+		pr_debug("%s(), Unknown event %d\n", __func__ , event);
 		break;
 	}
 	if (skb)
@@ -266,8 +258,6 @@ static int irlan_client_state_info(struct irlan_cb *self, IRLAN_EVENT event,
 static int irlan_client_state_media(struct irlan_cb *self, IRLAN_EVENT event,
 				    struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 
 	switch(event) {
@@ -281,10 +271,10 @@ static int irlan_client_state_media(struct irlan_cb *self, IRLAN_EVENT event,
 		irlan_next_client_state(self, IRLAN_IDLE);
 		break;
 	case IRLAN_WATCHDOG_TIMEOUT:
-		IRDA_DEBUG(2, "%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__ );
+		pr_debug("%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown event %d\n", __func__ , event);
+		pr_debug("%s(), Unknown event %d\n", __func__ , event);
 		break;
 	}
 	if (skb)
@@ -305,8 +295,6 @@ static int irlan_client_state_open(struct irlan_cb *self, IRLAN_EVENT event,
 {
 	struct qos_info qos;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 
 	switch(event) {
@@ -344,7 +332,7 @@ static int irlan_client_state_open(struct irlan_cb *self, IRLAN_EVENT event,
 			irlan_next_client_state(self, IRLAN_DATA);
 			break;
 		default:
-			IRDA_DEBUG(2, "%s(), unknown access type!\n", __func__ );
+			pr_debug("%s(), unknown access type!\n", __func__);
 			break;
 		}
 		break;
@@ -353,10 +341,10 @@ static int irlan_client_state_open(struct irlan_cb *self, IRLAN_EVENT event,
 		irlan_next_client_state(self, IRLAN_IDLE);
 		break;
 	case IRLAN_WATCHDOG_TIMEOUT:
-		IRDA_DEBUG(2, "%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__ );
+		pr_debug("%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown event %d\n", __func__ , event);
+		pr_debug("%s(), Unknown event %d\n", __func__ , event);
 		break;
 	}
 
@@ -376,8 +364,6 @@ static int irlan_client_state_open(struct irlan_cb *self, IRLAN_EVENT event,
 static int irlan_client_state_wait(struct irlan_cb *self, IRLAN_EVENT event,
 				   struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 
 	switch(event) {
@@ -390,10 +376,10 @@ static int irlan_client_state_wait(struct irlan_cb *self, IRLAN_EVENT event,
 		irlan_next_client_state(self, IRLAN_IDLE);
 		break;
 	case IRLAN_WATCHDOG_TIMEOUT:
-		IRDA_DEBUG(2, "%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__ );
+		pr_debug("%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown event %d\n", __func__ , event);
+		pr_debug("%s(), Unknown event %d\n", __func__ , event);
 		break;
 	}
 	if (skb)
@@ -407,8 +393,6 @@ static int irlan_client_state_arb(struct irlan_cb *self, IRLAN_EVENT event,
 {
 	struct qos_info qos;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 
 	switch(event) {
@@ -429,7 +413,7 @@ static int irlan_client_state_arb(struct irlan_cb *self, IRLAN_EVENT event,
 		} else if (self->client.recv_arb_val >
 			   self->provider.send_arb_val)
 		{
-			IRDA_DEBUG(2, "%s(), lost the battle :-(\n", __func__ );
+			pr_debug("%s(), lost the battle :-(\n", __func__);
 		}
 		break;
 	case IRLAN_DATA_CONNECT_INDICATION:
@@ -440,10 +424,10 @@ static int irlan_client_state_arb(struct irlan_cb *self, IRLAN_EVENT event,
 		irlan_next_client_state(self, IRLAN_IDLE);
 		break;
 	case IRLAN_WATCHDOG_TIMEOUT:
-		IRDA_DEBUG(2, "%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__ );
+		pr_debug("%s(), IRLAN_WATCHDOG_TIMEOUT\n", __func__);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown event %d\n", __func__ , event);
+		pr_debug("%s(), Unknown event %d\n", __func__ , event);
 		break;
 	}
 	if (skb)
@@ -462,8 +446,6 @@ static int irlan_client_state_arb(struct irlan_cb *self, IRLAN_EVENT event,
 static int irlan_client_state_data(struct irlan_cb *self, IRLAN_EVENT event,
 				   struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return -1;);
 
@@ -476,7 +458,7 @@ static int irlan_client_state_data(struct irlan_cb *self, IRLAN_EVENT event,
 		irlan_next_client_state(self, IRLAN_IDLE);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown event %d\n", __func__ , event);
+		pr_debug("%s(), Unknown event %d\n", __func__ , event);
 		break;
 	}
 	if (skb)
@@ -494,8 +476,6 @@ static int irlan_client_state_data(struct irlan_cb *self, IRLAN_EVENT event,
 static int irlan_client_state_close(struct irlan_cb *self, IRLAN_EVENT event,
 				    struct sk_buff *skb)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	if (skb)
 		dev_kfree_skb(skb);
 
@@ -511,8 +491,6 @@ static int irlan_client_state_close(struct irlan_cb *self, IRLAN_EVENT event,
 static int irlan_client_state_sync(struct irlan_cb *self, IRLAN_EVENT event,
 				   struct sk_buff *skb)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	if (skb)
 		dev_kfree_skb(skb);
 
diff --git a/net/irda/irlan/irlan_common.c b/net/irda/irlan/irlan_common.c
index 5a2d0a695529..481bbc2a4349 100644
--- a/net/irda/irlan/irlan_common.c
+++ b/net/irda/irlan/irlan_common.c
@@ -118,8 +118,6 @@ static int __init irlan_init(void)
 	struct irlan_cb *new;
 	__u16 hints;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 #ifdef CONFIG_PROC_FS
 	{ struct proc_dir_entry *proc;
 	proc = proc_create("irlan", 0, proc_irda, &irlan_fops);
@@ -130,7 +128,6 @@ static int __init irlan_init(void)
 	}
 #endif /* CONFIG_PROC_FS */
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
 	hints = irlmp_service_to_hint(S_LAN);
 
 	/* Register with IrLMP as a client */
@@ -173,8 +170,6 @@ static void __exit irlan_cleanup(void)
 {
 	struct irlan_cb *self, *next;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	irlmp_unregister_client(ckey);
 	irlmp_unregister_service(skey);
 
@@ -201,8 +196,6 @@ static struct irlan_cb __init *irlan_open(__u32 saddr, __u32 daddr)
 	struct net_device *dev;
 	struct irlan_cb *self;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	/* Create network device with irlan */
 	dev = alloc_irlandev(eth ? "eth%d" : "irlan%d");
 	if (!dev)
@@ -245,8 +238,8 @@ static struct irlan_cb __init *irlan_open(__u32 saddr, __u32 daddr)
 	irlan_next_provider_state(self, IRLAN_IDLE);
 
 	if (register_netdev(dev)) {
-		IRDA_DEBUG(2, "%s(), register_netdev() failed!\n",
-			   __func__ );
+		pr_debug("%s(), register_netdev() failed!\n",
+			 __func__);
 		self = NULL;
 		free_netdev(dev);
 	} else {
@@ -266,8 +259,6 @@ static struct irlan_cb __init *irlan_open(__u32 saddr, __u32 daddr)
  */
 static void __irlan_close(struct irlan_cb *self)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	ASSERT_RTNL();
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
@@ -314,8 +305,6 @@ static void irlan_connect_indication(void *instance, void *sap,
 	struct irlan_cb *self;
 	struct tsap_cb *tsap;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	self = instance;
 	tsap = sap;
 
@@ -326,7 +315,7 @@ static void irlan_connect_indication(void *instance, void *sap,
 	self->max_sdu_size = max_sdu_size;
 	self->max_header_size = max_header_size;
 
-	IRDA_DEBUG(0, "%s: We are now connected!\n", __func__);
+	pr_debug("%s: We are now connected!\n", __func__);
 
 	del_timer(&self->watchdog_timer);
 
@@ -370,7 +359,7 @@ static void irlan_connect_confirm(void *instance, void *sap,
 
 	/* TODO: we could set the MTU depending on the max_sdu_size */
 
-	IRDA_DEBUG(0, "%s: We are now connected!\n", __func__);
+	pr_debug("%s: We are now connected!\n", __func__);
 	del_timer(&self->watchdog_timer);
 
 	/*
@@ -403,7 +392,7 @@ static void irlan_disconnect_indication(void *instance,
 	struct irlan_cb *self;
 	struct tsap_cb *tsap;
 
-	IRDA_DEBUG(0, "%s(), reason=%d\n", __func__ , reason);
+	pr_debug("%s(), reason=%d\n", __func__ , reason);
 
 	self = instance;
 	tsap = sap;
@@ -415,29 +404,30 @@ static void irlan_disconnect_indication(void *instance,
 
 	IRDA_ASSERT(tsap == self->tsap_data, return;);
 
-	IRDA_DEBUG(2, "IrLAN, data channel disconnected by peer!\n");
+	pr_debug("IrLAN, data channel disconnected by peer!\n");
 
 	/* Save reason so we know if we should try to reconnect or not */
 	self->disconnect_reason = reason;
 
 	switch (reason) {
 	case LM_USER_REQUEST: /* User request */
-		IRDA_DEBUG(2, "%s(), User requested\n", __func__ );
+		pr_debug("%s(), User requested\n", __func__);
 		break;
 	case LM_LAP_DISCONNECT: /* Unexpected IrLAP disconnect */
-		IRDA_DEBUG(2, "%s(), Unexpected IrLAP disconnect\n", __func__ );
+		pr_debug("%s(), Unexpected IrLAP disconnect\n", __func__);
 		break;
 	case LM_CONNECT_FAILURE: /* Failed to establish IrLAP connection */
-		IRDA_DEBUG(2, "%s(), IrLAP connect failed\n", __func__ );
+		pr_debug("%s(), IrLAP connect failed\n", __func__);
 		break;
 	case LM_LAP_RESET:  /* IrLAP reset */
-		IRDA_DEBUG(2, "%s(), IrLAP reset\n", __func__ );
+		pr_debug("%s(), IrLAP reset\n", __func__);
 		break;
 	case LM_INIT_DISCONNECT:
-		IRDA_DEBUG(2, "%s(), IrLMP connect failed\n", __func__ );
+		pr_debug("%s(), IrLMP connect failed\n", __func__);
 		break;
 	default:
-		IRDA_ERROR("%s(), Unknown disconnect reason\n", __func__);
+		net_err_ratelimited("%s(), Unknown disconnect reason\n",
+				    __func__);
 		break;
 	}
 
@@ -459,8 +449,6 @@ void irlan_open_data_tsap(struct irlan_cb *self)
 	struct tsap_cb *tsap;
 	notify_t notify;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
@@ -481,7 +469,7 @@ void irlan_open_data_tsap(struct irlan_cb *self)
 
 	tsap = irttp_open_tsap(LSAP_ANY, DEFAULT_INITIAL_CREDIT, &notify);
 	if (!tsap) {
-		IRDA_DEBUG(2, "%s(), Got no tsap!\n", __func__ );
+		pr_debug("%s(), Got no tsap!\n", __func__);
 		return;
 	}
 	self->tsap_data = tsap;
@@ -495,8 +483,6 @@ void irlan_open_data_tsap(struct irlan_cb *self)
 
 void irlan_close_tsaps(struct irlan_cb *self)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
@@ -585,8 +571,6 @@ int irlan_run_ctrl_tx_queue(struct irlan_cb *self)
 {
 	struct sk_buff *skb;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	if (irda_lock(&self->client.tx_busy) == FALSE)
 		return -EBUSY;
 
@@ -604,7 +588,7 @@ int irlan_run_ctrl_tx_queue(struct irlan_cb *self)
 		dev_kfree_skb(skb);
 		return -1;
 	}
-	IRDA_DEBUG(2, "%s(), sending ...\n", __func__ );
+	pr_debug("%s(), sending ...\n", __func__);
 
 	return irttp_data_request(self->client.tsap_ctrl, skb);
 }
@@ -617,8 +601,6 @@ int irlan_run_ctrl_tx_queue(struct irlan_cb *self)
  */
 static void irlan_ctrl_data_request(struct irlan_cb *self, struct sk_buff *skb)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	/* Queue command */
 	skb_queue_tail(&self->client.txq, skb);
 
@@ -637,8 +619,6 @@ void irlan_get_provider_info(struct irlan_cb *self)
 	struct sk_buff *skb;
 	__u8 *frame;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
@@ -670,8 +650,6 @@ void irlan_open_data_channel(struct irlan_cb *self)
 	struct sk_buff *skb;
 	__u8 *frame;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
@@ -705,8 +683,6 @@ void irlan_close_data_channel(struct irlan_cb *self)
 	struct sk_buff *skb;
 	__u8 *frame;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
@@ -746,8 +722,6 @@ static void irlan_open_unicast_addr(struct irlan_cb *self)
 	struct sk_buff *skb;
 	__u8 *frame;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
@@ -788,8 +762,6 @@ void irlan_set_broadcast_filter(struct irlan_cb *self, int status)
 	struct sk_buff *skb;
 	__u8 *frame;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
@@ -832,8 +804,6 @@ void irlan_set_multicast_filter(struct irlan_cb *self, int status)
 	struct sk_buff *skb;
 	__u8 *frame;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
@@ -877,8 +847,6 @@ static void irlan_get_unicast_addr(struct irlan_cb *self)
 	struct sk_buff *skb;
 	__u8 *frame;
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
@@ -917,8 +885,6 @@ void irlan_get_media_char(struct irlan_cb *self)
 	struct sk_buff *skb;
 	__u8 *frame;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
@@ -1005,7 +971,7 @@ static int __irlan_insert_param(struct sk_buff *skb, char *param, int type,
 	int n=0;
 
 	if (skb == NULL) {
-		IRDA_DEBUG(2, "%s(), Got NULL skb\n", __func__ );
+		pr_debug("%s(), Got NULL skb\n", __func__);
 		return 0;
 	}
 
@@ -1022,7 +988,7 @@ static int __irlan_insert_param(struct sk_buff *skb, char *param, int type,
 		IRDA_ASSERT(value_len > 0, return 0;);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown parameter type!\n", __func__ );
+		pr_debug("%s(), Unknown parameter type!\n", __func__);
 		return 0;
 	}
 
@@ -1031,7 +997,7 @@ static int __irlan_insert_param(struct sk_buff *skb, char *param, int type,
 
 	/* Make space for data */
 	if (skb_tailroom(skb) < (param_len+value_len+3)) {
-		IRDA_DEBUG(2, "%s(), No more space at end of skb\n", __func__ );
+		pr_debug("%s(), No more space at end of skb\n", __func__);
 		return 0;
 	}
 	skb_put(skb, param_len+value_len+3);
@@ -1078,13 +1044,11 @@ int irlan_extract_param(__u8 *buf, char *name, char *value, __u16 *len)
 	__u16 val_len;
 	int n=0;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	/* get length of parameter name (1 byte) */
 	name_len = buf[n++];
 
 	if (name_len > 254) {
-		IRDA_DEBUG(2, "%s(), name_len > 254\n", __func__ );
+		pr_debug("%s(), name_len > 254\n", __func__);
 		return -RSP_INVALID_COMMAND_FORMAT;
 	}
 
@@ -1101,7 +1065,7 @@ int irlan_extract_param(__u8 *buf, char *name, char *value, __u16 *len)
 	le16_to_cpus(&val_len); n+=2;
 
 	if (val_len >= 1016) {
-		IRDA_DEBUG(2, "%s(), parameter length to long\n", __func__ );
+		pr_debug("%s(), parameter length to long\n", __func__);
 		return -RSP_INVALID_COMMAND_FORMAT;
 	}
 	*len = val_len;
@@ -1111,8 +1075,8 @@ int irlan_extract_param(__u8 *buf, char *name, char *value, __u16 *len)
 	value[val_len] = '\0';
 	n+=val_len;
 
-	IRDA_DEBUG(4, "Parameter: %s ", name);
-	IRDA_DEBUG(4, "Value: %s\n", value);
+	pr_debug("Parameter: %s ", name);
+	pr_debug("Value: %s\n", value);
 
 	return n;
 }
diff --git a/net/irda/irlan/irlan_eth.c b/net/irda/irlan/irlan_eth.c
index dc13f1a45f2f..fcfbe579434a 100644
--- a/net/irda/irlan/irlan_eth.c
+++ b/net/irda/irlan/irlan_eth.c
@@ -110,8 +110,6 @@ static int irlan_eth_open(struct net_device *dev)
 {
 	struct irlan_cb *self = netdev_priv(dev);
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* Ready to play! */
 	netif_stop_queue(dev); /* Wait until data link is ready */
 
@@ -137,8 +135,6 @@ static int irlan_eth_close(struct net_device *dev)
 {
 	struct irlan_cb *self = netdev_priv(dev);
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* Stop device */
 	netif_stop_queue(dev);
 
@@ -231,8 +227,8 @@ int irlan_eth_receive(void *instance, void *sap, struct sk_buff *skb)
 		return 0;
 	}
 	if (skb->len < ETH_HLEN) {
-		IRDA_DEBUG(0, "%s() : IrLAN frame too short (%d)\n",
-			   __func__, skb->len);
+		pr_debug("%s() : IrLAN frame too short (%d)\n",
+			 __func__, skb->len);
 		dev->stats.rx_dropped++;
 		dev_kfree_skb(skb);
 		return 0;
@@ -281,9 +277,9 @@ void irlan_eth_flow_indication(void *instance, void *sap, LOCAL_FLOW flow)
 
 	IRDA_ASSERT(dev != NULL, return;);
 
-	IRDA_DEBUG(0, "%s() : flow %s ; running %d\n", __func__,
-		   flow == FLOW_STOP ? "FLOW_STOP" : "FLOW_START",
-		   netif_running(dev));
+	pr_debug("%s() : flow %s ; running %d\n", __func__,
+		 flow == FLOW_STOP ? "FLOW_STOP" : "FLOW_START",
+		 netif_running(dev));
 
 	switch (flow) {
 	case FLOW_STOP:
@@ -310,32 +306,30 @@ static void irlan_eth_set_multicast_list(struct net_device *dev)
 {
 	struct irlan_cb *self = netdev_priv(dev);
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* Check if data channel has been connected yet */
 	if (self->client.state != IRLAN_DATA) {
-		IRDA_DEBUG(1, "%s(), delaying!\n", __func__);
+		pr_debug("%s(), delaying!\n", __func__);
 		return;
 	}
 
 	if (dev->flags & IFF_PROMISC) {
 		/* Enable promiscuous mode */
-		IRDA_WARNING("Promiscuous mode not implemented by IrLAN!\n");
+		net_warn_ratelimited("Promiscuous mode not implemented by IrLAN!\n");
 	} else if ((dev->flags & IFF_ALLMULTI) ||
 		 netdev_mc_count(dev) > HW_MAX_ADDRS) {
 		/* Disable promiscuous mode, use normal mode. */
-		IRDA_DEBUG(4, "%s(), Setting multicast filter\n", __func__);
+		pr_debug("%s(), Setting multicast filter\n", __func__);
 		/* hardware_set_filter(NULL); */
 
 		irlan_set_multicast_filter(self, TRUE);
 	} else if (!netdev_mc_empty(dev)) {
-		IRDA_DEBUG(4, "%s(), Setting multicast filter\n", __func__);
+		pr_debug("%s(), Setting multicast filter\n", __func__);
 		/* Walk the address list, and load the filter */
 		/* hardware_set_filter(dev->mc_list); */
 
 		irlan_set_multicast_filter(self, TRUE);
 	} else {
-		IRDA_DEBUG(4, "%s(), Clearing multicast filter\n", __func__);
+		pr_debug("%s(), Clearing multicast filter\n", __func__);
 		irlan_set_multicast_filter(self, FALSE);
 	}
 
diff --git a/net/irda/irlan/irlan_event.c b/net/irda/irlan/irlan_event.c
index 43f16040a6fe..9a1cc11c16f6 100644
--- a/net/irda/irlan/irlan_event.c
+++ b/net/irda/irlan/irlan_event.c
@@ -40,7 +40,7 @@ const char * const irlan_state[] = {
 
 void irlan_next_client_state(struct irlan_cb *self, IRLAN_STATE state)
 {
-	IRDA_DEBUG(2, "%s(), %s\n", __func__ , irlan_state[state]);
+	pr_debug("%s(), %s\n", __func__ , irlan_state[state]);
 
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
@@ -50,7 +50,7 @@ void irlan_next_client_state(struct irlan_cb *self, IRLAN_STATE state)
 
 void irlan_next_provider_state(struct irlan_cb *self, IRLAN_STATE state)
 {
-	IRDA_DEBUG(2, "%s(), %s\n", __func__ , irlan_state[state]);
+	pr_debug("%s(), %s\n", __func__ , irlan_state[state]);
 
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
diff --git a/net/irda/irlan/irlan_filter.c b/net/irda/irlan/irlan_filter.c
index 7977be7caf0f..e755e90b2f26 100644
--- a/net/irda/irlan/irlan_filter.c
+++ b/net/irda/irlan/irlan_filter.c
@@ -43,7 +43,7 @@ void irlan_filter_request(struct irlan_cb *self, struct sk_buff *skb)
 	if ((self->provider.filter_type == IRLAN_DIRECTED) &&
 	    (self->provider.filter_operation == DYNAMIC))
 	{
-		IRDA_DEBUG(0, "Giving peer a dynamic Ethernet address\n");
+		pr_debug("Giving peer a dynamic Ethernet address\n");
 		self->provider.mac_address[0] = 0x40;
 		self->provider.mac_address[1] = 0x00;
 		self->provider.mac_address[2] = 0x00;
@@ -73,7 +73,7 @@ void irlan_filter_request(struct irlan_cb *self, struct sk_buff *skb)
 	if ((self->provider.filter_type == IRLAN_DIRECTED) &&
 	    (self->provider.filter_mode == FILTER))
 	{
-		IRDA_DEBUG(0, "Directed filter on\n");
+		pr_debug("Directed filter on\n");
 		skb->data[0] = 0x00; /* Success */
 		skb->data[1] = 0x00;
 		return;
@@ -81,7 +81,7 @@ void irlan_filter_request(struct irlan_cb *self, struct sk_buff *skb)
 	if ((self->provider.filter_type == IRLAN_DIRECTED) &&
 	    (self->provider.filter_mode == NONE))
 	{
-		IRDA_DEBUG(0, "Directed filter off\n");
+		pr_debug("Directed filter off\n");
 		skb->data[0] = 0x00; /* Success */
 		skb->data[1] = 0x00;
 		return;
@@ -90,7 +90,7 @@ void irlan_filter_request(struct irlan_cb *self, struct sk_buff *skb)
 	if ((self->provider.filter_type == IRLAN_BROADCAST) &&
 	    (self->provider.filter_mode == FILTER))
 	{
-		IRDA_DEBUG(0, "Broadcast filter on\n");
+		pr_debug("Broadcast filter on\n");
 		skb->data[0] = 0x00; /* Success */
 		skb->data[1] = 0x00;
 		return;
@@ -98,7 +98,7 @@ void irlan_filter_request(struct irlan_cb *self, struct sk_buff *skb)
 	if ((self->provider.filter_type == IRLAN_BROADCAST) &&
 	    (self->provider.filter_mode == NONE))
 	{
-		IRDA_DEBUG(0, "Broadcast filter off\n");
+		pr_debug("Broadcast filter off\n");
 		skb->data[0] = 0x00; /* Success */
 		skb->data[1] = 0x00;
 		return;
@@ -106,7 +106,7 @@ void irlan_filter_request(struct irlan_cb *self, struct sk_buff *skb)
 	if ((self->provider.filter_type == IRLAN_MULTICAST) &&
 	    (self->provider.filter_mode == FILTER))
 	{
-		IRDA_DEBUG(0, "Multicast filter on\n");
+		pr_debug("Multicast filter on\n");
 		skb->data[0] = 0x00; /* Success */
 		skb->data[1] = 0x00;
 		return;
@@ -114,7 +114,7 @@ void irlan_filter_request(struct irlan_cb *self, struct sk_buff *skb)
 	if ((self->provider.filter_type == IRLAN_MULTICAST) &&
 	    (self->provider.filter_mode == NONE))
 	{
-		IRDA_DEBUG(0, "Multicast filter off\n");
+		pr_debug("Multicast filter off\n");
 		skb->data[0] = 0x00; /* Success */
 		skb->data[1] = 0x00;
 		return;
@@ -122,7 +122,7 @@ void irlan_filter_request(struct irlan_cb *self, struct sk_buff *skb)
 	if ((self->provider.filter_type == IRLAN_MULTICAST) &&
 	    (self->provider.filter_operation == GET))
 	{
-		IRDA_DEBUG(0, "Multicast filter get\n");
+		pr_debug("Multicast filter get\n");
 		skb->data[0] = 0x00; /* Success? */
 		skb->data[1] = 0x02;
 		irlan_insert_string_param(skb, "FILTER_MODE", "NONE");
@@ -132,7 +132,7 @@ void irlan_filter_request(struct irlan_cb *self, struct sk_buff *skb)
 	skb->data[0] = 0x00; /* Command not supported */
 	skb->data[1] = 0x00;
 
-	IRDA_DEBUG(0, "Not implemented!\n");
+	pr_debug("Not implemented!\n");
 }
 
 /*
@@ -143,18 +143,15 @@ void irlan_filter_request(struct irlan_cb *self, struct sk_buff *skb)
  */
 void irlan_check_command_param(struct irlan_cb *self, char *param, char *value)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
-	IRDA_DEBUG(4, "%s, %s\n", param, value);
+	pr_debug("%s, %s\n", param, value);
 
 	/*
 	 *  This is experimental!! DB.
 	 */
 	 if (strcmp(param, "MODE") == 0) {
-		IRDA_DEBUG(0, "%s()\n", __func__ );
 		self->use_udata = TRUE;
 		return;
 	}
diff --git a/net/irda/irlan/irlan_provider.c b/net/irda/irlan/irlan_provider.c
index 4664855222f4..15c292cf2644 100644
--- a/net/irda/irlan/irlan_provider.c
+++ b/net/irda/irlan/irlan_provider.c
@@ -70,8 +70,6 @@ static int irlan_provider_data_indication(void *instance, void *sap,
 	struct irlan_cb *self;
 	__u8 code;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	self = instance;
 
 	IRDA_ASSERT(self != NULL, return -1;);
@@ -82,32 +80,32 @@ static int irlan_provider_data_indication(void *instance, void *sap,
 	code = skb->data[0];
 	switch(code) {
 	case CMD_GET_PROVIDER_INFO:
-		IRDA_DEBUG(4, "Got GET_PROVIDER_INFO command!\n");
+		pr_debug("Got GET_PROVIDER_INFO command!\n");
 		irlan_do_provider_event(self, IRLAN_GET_INFO_CMD, skb);
 		break;
 
 	case CMD_GET_MEDIA_CHAR:
-		IRDA_DEBUG(4, "Got GET_MEDIA_CHAR command!\n");
+		pr_debug("Got GET_MEDIA_CHAR command!\n");
 		irlan_do_provider_event(self, IRLAN_GET_MEDIA_CMD, skb);
 		break;
 	case CMD_OPEN_DATA_CHANNEL:
-		IRDA_DEBUG(4, "Got OPEN_DATA_CHANNEL command!\n");
+		pr_debug("Got OPEN_DATA_CHANNEL command!\n");
 		irlan_do_provider_event(self, IRLAN_OPEN_DATA_CMD, skb);
 		break;
 	case CMD_FILTER_OPERATION:
-		IRDA_DEBUG(4, "Got FILTER_OPERATION command!\n");
+		pr_debug("Got FILTER_OPERATION command!\n");
 		irlan_do_provider_event(self, IRLAN_FILTER_CONFIG_CMD, skb);
 		break;
 	case CMD_RECONNECT_DATA_CHAN:
-		IRDA_DEBUG(2, "%s(), Got RECONNECT_DATA_CHAN command\n", __func__ );
-		IRDA_DEBUG(2, "%s(), NOT IMPLEMENTED\n", __func__ );
+		pr_debug("%s(), Got RECONNECT_DATA_CHAN command\n", __func__);
+		pr_debug("%s(), NOT IMPLEMENTED\n", __func__);
 		break;
 	case CMD_CLOSE_DATA_CHAN:
-		IRDA_DEBUG(2, "Got CLOSE_DATA_CHAN command!\n");
-		IRDA_DEBUG(2, "%s(), NOT IMPLEMENTED\n", __func__ );
+		pr_debug("Got CLOSE_DATA_CHAN command!\n");
+		pr_debug("%s(), NOT IMPLEMENTED\n", __func__);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown command!\n", __func__ );
+		pr_debug("%s(), Unknown command!\n", __func__);
 		break;
 	}
 	return 0;
@@ -128,8 +126,6 @@ static void irlan_provider_connect_indication(void *instance, void *sap,
 	struct irlan_cb *self;
 	struct tsap_cb *tsap;
 
-	IRDA_DEBUG(0, "%s()\n", __func__ );
-
 	self = instance;
 	tsap = sap;
 
@@ -179,7 +175,7 @@ static void irlan_provider_disconnect_indication(void *instance, void *sap,
 	struct irlan_cb *self;
 	struct tsap_cb *tsap;
 
-	IRDA_DEBUG(4, "%s(), reason=%d\n", __func__ , reason);
+	pr_debug("%s(), reason=%d\n", __func__ , reason);
 
 	self = instance;
 	tsap = sap;
@@ -233,7 +229,7 @@ int irlan_provider_parse_command(struct irlan_cb *self, int cmd,
 
 	IRDA_ASSERT(skb != NULL, return -RSP_PROTOCOL_ERROR;);
 
-	IRDA_DEBUG(4, "%s(), skb->len=%d\n", __func__ , (int)skb->len);
+	pr_debug("%s(), skb->len=%d\n", __func__ , (int)skb->len);
 
 	IRDA_ASSERT(self != NULL, return -RSP_PROTOCOL_ERROR;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return -RSP_PROTOCOL_ERROR;);
@@ -255,7 +251,7 @@ int irlan_provider_parse_command(struct irlan_cb *self, int cmd,
 	/* How many parameters? */
 	count = frame[1];
 
-	IRDA_DEBUG(4, "Got %d parameters\n", count);
+	pr_debug("Got %d parameters\n", count);
 
 	ptr = frame+2;
 
@@ -263,7 +259,7 @@ int irlan_provider_parse_command(struct irlan_cb *self, int cmd,
 	for (i=0; i<count;i++) {
 		ret = irlan_extract_param(ptr, name, value, &val_len);
 		if (ret < 0) {
-			IRDA_DEBUG(2, "%s(), IrLAN, Error!\n", __func__ );
+			pr_debug("%s(), IrLAN, Error!\n", __func__);
 			break;
 		}
 		ptr+=ret;
@@ -288,8 +284,6 @@ void irlan_provider_send_reply(struct irlan_cb *self, int command,
 {
 	struct sk_buff *skb;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
 
@@ -320,7 +314,7 @@ void irlan_provider_send_reply(struct irlan_cb *self, int command,
 			irlan_insert_string_param(skb, "MEDIA", "802.5");
 			break;
 		default:
-			IRDA_DEBUG(2, "%s(), unknown media type!\n", __func__ );
+			pr_debug("%s(), unknown media type!\n", __func__);
 			break;
 		}
 		irlan_insert_short_param(skb, "IRLAN_VER", 0x0101);
@@ -344,7 +338,7 @@ void irlan_provider_send_reply(struct irlan_cb *self, int command,
 			irlan_insert_string_param(skb, "ACCESS_TYPE", "HOSTED");
 			break;
 		default:
-			IRDA_DEBUG(2, "%s(), Unknown access type\n", __func__ );
+			pr_debug("%s(), Unknown access type\n", __func__);
 			break;
 		}
 		irlan_insert_short_param(skb, "MAX_FRAME", 0x05ee);
@@ -364,7 +358,7 @@ void irlan_provider_send_reply(struct irlan_cb *self, int command,
 		irlan_filter_request(self, skb);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown command!\n", __func__ );
+		pr_debug("%s(), Unknown command!\n", __func__);
 		break;
 	}
 
@@ -382,8 +376,6 @@ int irlan_provider_open_ctrl_tsap(struct irlan_cb *self)
 	struct tsap_cb *tsap;
 	notify_t notify;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return -1;);
 
@@ -403,7 +395,7 @@ int irlan_provider_open_ctrl_tsap(struct irlan_cb *self)
 
 	tsap = irttp_open_tsap(LSAP_ANY, 1, &notify);
 	if (!tsap) {
-		IRDA_DEBUG(2, "%s(), Got no tsap!\n", __func__ );
+		pr_debug("%s(), Got no tsap!\n", __func__);
 		return -1;
 	}
 	self->provider.tsap_ctrl = tsap;
diff --git a/net/irda/irlan/irlan_provider_event.c b/net/irda/irlan/irlan_provider_event.c
index 01a9d7c993ee..9c4f7f51d6b5 100644
--- a/net/irda/irlan/irlan_provider_event.c
+++ b/net/irda/irlan/irlan_provider_event.c
@@ -72,8 +72,6 @@ void irlan_do_provider_event(struct irlan_cb *self, IRLAN_EVENT event,
 static int irlan_provider_state_idle(struct irlan_cb *self, IRLAN_EVENT event,
 				     struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 
 	switch(event) {
@@ -82,7 +80,7 @@ static int irlan_provider_state_idle(struct irlan_cb *self, IRLAN_EVENT event,
 	     irlan_next_provider_state( self, IRLAN_INFO);
 	     break;
 	default:
-		IRDA_DEBUG(4, "%s(), Unknown event %d\n", __func__ , event);
+		pr_debug("%s(), Unknown event %d\n", __func__ , event);
 		break;
 	}
 	if (skb)
@@ -101,8 +99,6 @@ static int irlan_provider_state_info(struct irlan_cb *self, IRLAN_EVENT event,
 {
 	int ret;
 
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 
 	switch(event) {
@@ -147,7 +143,7 @@ static int irlan_provider_state_info(struct irlan_cb *self, IRLAN_EVENT event,
 		irlan_next_provider_state(self, IRLAN_IDLE);
 		break;
 	default:
-		IRDA_DEBUG( 0, "%s(), Unknown event %d\n", __func__ , event);
+		pr_debug("%s(), Unknown event %d\n", __func__ , event);
 		break;
 	}
 	if (skb)
@@ -166,8 +162,6 @@ static int irlan_provider_state_info(struct irlan_cb *self, IRLAN_EVENT event,
 static int irlan_provider_state_open(struct irlan_cb *self, IRLAN_EVENT event,
 				     struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 
 	switch(event) {
@@ -186,7 +180,7 @@ static int irlan_provider_state_open(struct irlan_cb *self, IRLAN_EVENT event,
 		irlan_next_provider_state(self, IRLAN_IDLE);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown event %d\n", __func__ , event);
+		pr_debug("%s(), Unknown event %d\n", __func__ , event);
 		break;
 	}
 	if (skb)
@@ -205,8 +199,6 @@ static int irlan_provider_state_open(struct irlan_cb *self, IRLAN_EVENT event,
 static int irlan_provider_state_data(struct irlan_cb *self, IRLAN_EVENT event,
 				     struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__ );
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == IRLAN_MAGIC, return -1;);
 
@@ -221,7 +213,7 @@ static int irlan_provider_state_data(struct irlan_cb *self, IRLAN_EVENT event,
 		irlan_next_provider_state(self, IRLAN_IDLE);
 		break;
 	default:
-		IRDA_DEBUG( 0, "%s(), Unknown event %d\n", __func__ , event);
+		pr_debug("%s(), Unknown event %d\n", __func__ , event);
 		break;
 	}
 	if (skb)
diff --git a/net/irda/irlap.c b/net/irda/irlap.c
index a778df55f5d6..1cde711bcab5 100644
--- a/net/irda/irlap.c
+++ b/net/irda/irlap.c
@@ -60,8 +60,7 @@ static void __irlap_close(struct irlap_cb *self);
 static void irlap_init_qos_capabilities(struct irlap_cb *self,
 					struct qos_info *qos_user);
 
-#ifdef CONFIG_IRDA_DEBUG
-static const char *const lap_reasons[] = {
+static const char *const lap_reasons[] __maybe_unused = {
 	"ERROR, NOT USED",
 	"LAP_DISC_INDICATION",
 	"LAP_NO_RESPONSE",
@@ -71,7 +70,6 @@ static const char *const lap_reasons[] = {
 	"LAP_PRIMARY_CONFLICT",
 	"ERROR, NOT USED",
 };
-#endif	/* CONFIG_IRDA_DEBUG */
 
 int __init irlap_init(void)
 {
@@ -85,8 +83,8 @@ int __init irlap_init(void)
 	/* Allocate master array */
 	irlap = hashbin_new(HB_LOCK);
 	if (irlap == NULL) {
-		IRDA_ERROR("%s: can't allocate irlap hashbin!\n",
-			   __func__);
+		net_err_ratelimited("%s: can't allocate irlap hashbin!\n",
+				    __func__);
 		return -ENOMEM;
 	}
 
@@ -111,8 +109,6 @@ struct irlap_cb *irlap_open(struct net_device *dev, struct qos_info *qos,
 {
 	struct irlap_cb *self;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	/* Initialize the irlap structure. */
 	self = kzalloc(sizeof(struct irlap_cb), GFP_KERNEL);
 	if (self == NULL)
@@ -213,8 +209,6 @@ void irlap_close(struct irlap_cb *self)
 {
 	struct irlap_cb *lap;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 
@@ -229,7 +223,7 @@ void irlap_close(struct irlap_cb *self)
 	/* Be sure that we manage to remove ourself from the hash */
 	lap = hashbin_remove(irlap, self->saddr, NULL);
 	if (!lap) {
-		IRDA_DEBUG(1, "%s(), Didn't find myself!\n", __func__);
+		pr_debug("%s(), Didn't find myself!\n", __func__);
 		return;
 	}
 	__irlap_close(lap);
@@ -244,8 +238,6 @@ EXPORT_SYMBOL(irlap_close);
  */
 void irlap_connect_indication(struct irlap_cb *self, struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 
@@ -263,8 +255,6 @@ void irlap_connect_indication(struct irlap_cb *self, struct sk_buff *skb)
  */
 void irlap_connect_response(struct irlap_cb *self, struct sk_buff *userdata)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	irlap_do_event(self, CONNECT_RESPONSE, userdata, NULL);
 }
 
@@ -278,7 +268,7 @@ void irlap_connect_response(struct irlap_cb *self, struct sk_buff *userdata)
 void irlap_connect_request(struct irlap_cb *self, __u32 daddr,
 			   struct qos_info *qos_user, int sniff)
 {
-	IRDA_DEBUG(3, "%s(), daddr=0x%08x\n", __func__, daddr);
+	pr_debug("%s(), daddr=0x%08x\n", __func__, daddr);
 
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
@@ -305,8 +295,6 @@ void irlap_connect_request(struct irlap_cb *self, __u32 daddr,
  */
 void irlap_connect_confirm(struct irlap_cb *self, struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 
@@ -342,8 +330,6 @@ void irlap_data_request(struct irlap_cb *self, struct sk_buff *skb,
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	IRDA_ASSERT(skb_headroom(skb) >= (LAP_ADDR_HEADER+LAP_CTRL_HEADER),
 		    return;);
 	skb_push(skb, LAP_ADDR_HEADER+LAP_CTRL_HEADER);
@@ -389,8 +375,6 @@ void irlap_unitdata_request(struct irlap_cb *self, struct sk_buff *skb)
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	IRDA_ASSERT(skb_headroom(skb) >= (LAP_ADDR_HEADER+LAP_CTRL_HEADER),
 	       return;);
 	skb_push(skb, LAP_ADDR_HEADER+LAP_CTRL_HEADER);
@@ -415,8 +399,6 @@ void irlap_unitdata_request(struct irlap_cb *self, struct sk_buff *skb)
 #ifdef CONFIG_IRDA_ULTRA
 void irlap_unitdata_indication(struct irlap_cb *self, struct sk_buff *skb)
 {
-	IRDA_DEBUG(1, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 	IRDA_ASSERT(skb != NULL, return;);
@@ -435,8 +417,6 @@ void irlap_unitdata_indication(struct irlap_cb *self, struct sk_buff *skb)
  */
 void irlap_disconnect_request(struct irlap_cb *self)
 {
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 
@@ -456,7 +436,7 @@ void irlap_disconnect_request(struct irlap_cb *self)
 		irlap_do_event(self, DISCONNECT_REQUEST, NULL, NULL);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), disconnect pending!\n", __func__);
+		pr_debug("%s(), disconnect pending!\n", __func__);
 		self->disconnect_pending = TRUE;
 		break;
 	}
@@ -470,7 +450,7 @@ void irlap_disconnect_request(struct irlap_cb *self)
  */
 void irlap_disconnect_indication(struct irlap_cb *self, LAP_REASON reason)
 {
-	IRDA_DEBUG(1, "%s(), reason=%s\n", __func__, lap_reasons[reason]);
+	pr_debug("%s(), reason=%s\n", __func__, lap_reasons[reason]);
 
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
@@ -480,7 +460,7 @@ void irlap_disconnect_indication(struct irlap_cb *self, LAP_REASON reason)
 
 	switch (reason) {
 	case LAP_RESET_INDICATION:
-		IRDA_DEBUG(1, "%s(), Sending reset request!\n", __func__);
+		pr_debug("%s(), Sending reset request!\n", __func__);
 		irlap_do_event(self, RESET_REQUEST, NULL, NULL);
 		break;
 	case LAP_NO_RESPONSE:	   /* FALLTHROUGH */
@@ -491,7 +471,8 @@ void irlap_disconnect_indication(struct irlap_cb *self, LAP_REASON reason)
 						 reason, NULL);
 		break;
 	default:
-		IRDA_ERROR("%s: Unknown reason %d\n", __func__, reason);
+		net_err_ratelimited("%s: Unknown reason %d\n",
+				    __func__, reason);
 	}
 }
 
@@ -509,7 +490,7 @@ void irlap_discovery_request(struct irlap_cb *self, discovery_t *discovery)
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 	IRDA_ASSERT(discovery != NULL, return;);
 
-	IRDA_DEBUG(4, "%s(), nslots = %d\n", __func__, discovery->nslots);
+	pr_debug("%s(), nslots = %d\n", __func__, discovery->nslots);
 
 	IRDA_ASSERT((discovery->nslots == 1) || (discovery->nslots == 6) ||
 		    (discovery->nslots == 8) || (discovery->nslots == 16),
@@ -517,8 +498,8 @@ void irlap_discovery_request(struct irlap_cb *self, discovery_t *discovery)
 
 	/* Discovery is only possible in NDM mode */
 	if (self->state != LAP_NDM) {
-		IRDA_DEBUG(4, "%s(), discovery only possible in NDM mode\n",
-			   __func__);
+		pr_debug("%s(), discovery only possible in NDM mode\n",
+			 __func__);
 		irlap_discovery_confirm(self, NULL);
 		/* Note : in theory, if we are not in NDM, we could postpone
 		 * the discovery like we do for connection request.
@@ -540,8 +521,8 @@ void irlap_discovery_request(struct irlap_cb *self, discovery_t *discovery)
 	self->discovery_log = hashbin_new(HB_NOLOCK);
 
 	if (self->discovery_log == NULL) {
-		IRDA_WARNING("%s(), Unable to allocate discovery log!\n",
-			     __func__);
+		net_warn_ratelimited("%s(), Unable to allocate discovery log!\n",
+				     __func__);
 		return;
 	}
 
@@ -552,7 +533,7 @@ void irlap_discovery_request(struct irlap_cb *self, discovery_t *discovery)
 	info.discovery = discovery;
 
 	/* sysctl_slot_timeout bounds are checked in irsysctl.c - Jean II */
-	self->slot_timeout = sysctl_slot_timeout * HZ / 1000;
+	self->slot_timeout = msecs_to_jiffies(sysctl_slot_timeout);
 
 	irlap_do_event(self, DISCOVERY_REQUEST, NULL, &info);
 }
@@ -596,8 +577,6 @@ void irlap_discovery_confirm(struct irlap_cb *self, hashbin_t *discovery_log)
  */
 void irlap_discovery_indication(struct irlap_cb *self, discovery_t *discovery)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 	IRDA_ASSERT(discovery != NULL, return;);
@@ -625,10 +604,10 @@ void irlap_status_indication(struct irlap_cb *self, int quality_of_link)
 {
 	switch (quality_of_link) {
 	case STATUS_NO_ACTIVITY:
-		IRDA_MESSAGE("IrLAP, no activity on link!\n");
+		net_info_ratelimited("IrLAP, no activity on link!\n");
 		break;
 	case STATUS_NOISY:
-		IRDA_MESSAGE("IrLAP, noisy link!\n");
+		net_info_ratelimited("IrLAP, noisy link!\n");
 		break;
 	default:
 		break;
@@ -642,8 +621,6 @@ void irlap_status_indication(struct irlap_cb *self, int quality_of_link)
  */
 void irlap_reset_indication(struct irlap_cb *self)
 {
-	IRDA_DEBUG(1, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 
@@ -658,7 +635,6 @@ void irlap_reset_indication(struct irlap_cb *self)
  */
 void irlap_reset_confirm(void)
 {
-	IRDA_DEBUG(1, "%s()\n", __func__);
 }
 
 /*
@@ -758,7 +734,7 @@ int irlap_validate_nr_received(struct irlap_cb *self, int nr)
 {
 	/*  nr as expected?  */
 	if (nr == self->vs) {
-		IRDA_DEBUG(4, "%s(), expected!\n", __func__);
+		pr_debug("%s(), expected!\n", __func__);
 		return NR_EXPECTED;
 	}
 
@@ -786,8 +762,6 @@ int irlap_validate_nr_received(struct irlap_cb *self, int nr)
  */
 void irlap_initiate_connection_state(struct irlap_cb *self)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 
@@ -869,7 +843,7 @@ static void irlap_change_speed(struct irlap_cb *self, __u32 speed, int now)
 {
 	struct sk_buff *skb;
 
-	IRDA_DEBUG(0, "%s(), setting speed to %d\n", __func__, speed);
+	pr_debug("%s(), setting speed to %d\n", __func__, speed);
 
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
@@ -912,7 +886,7 @@ static void irlap_init_qos_capabilities(struct irlap_cb *self,
 	 *  user may not have set all of them.
 	 */
 	if (qos_user) {
-		IRDA_DEBUG(1, "%s(), Found user specified QoS!\n", __func__);
+		pr_debug("%s(), Found user specified QoS!\n", __func__);
 
 		if (qos_user->baud_rate.bits)
 			self->qos_rx.baud_rate.bits &= qos_user->baud_rate.bits;
@@ -942,8 +916,6 @@ static void irlap_init_qos_capabilities(struct irlap_cb *self,
  */
 void irlap_apply_default_connection_parameters(struct irlap_cb *self)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 
@@ -1005,8 +977,6 @@ void irlap_apply_default_connection_parameters(struct irlap_cb *self)
  */
 void irlap_apply_connection_parameters(struct irlap_cb *self, int now)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 
@@ -1045,13 +1015,15 @@ void irlap_apply_connection_parameters(struct irlap_cb *self, int now)
 	 * Or, this is how much we can keep the pf bit in primary mode.
 	 * Therefore, it must be lower or equal than our *OWN* max turn around.
 	 * Jean II */
-	self->poll_timeout = self->qos_tx.max_turn_time.value * HZ / 1000;
+	self->poll_timeout = msecs_to_jiffies(
+				self->qos_tx.max_turn_time.value);
 	/* The Final timeout applies only to the primary station.
 	 * It defines the maximum time the primary wait (mostly in RECV mode)
 	 * for an answer from the secondary station before polling it again.
 	 * Therefore, it must be greater or equal than our *PARTNER*
 	 * max turn around time - Jean II */
-	self->final_timeout = self->qos_rx.max_turn_time.value * HZ / 1000;
+	self->final_timeout = msecs_to_jiffies(
+				self->qos_rx.max_turn_time.value);
 	/* The Watchdog Bit timeout applies only to the secondary station.
 	 * It defines the maximum time the secondary wait (mostly in RECV mode)
 	 * for poll from the primary station before getting annoyed.
@@ -1085,12 +1057,12 @@ void irlap_apply_connection_parameters(struct irlap_cb *self, int now)
 		self->N1 = sysctl_warn_noreply_time * 1000 /
 		  self->qos_rx.max_turn_time.value;
 
-	IRDA_DEBUG(4, "Setting N1 = %d\n", self->N1);
+	pr_debug("Setting N1 = %d\n", self->N1);
 
 	/* Set N2 to match our own disconnect time */
 	self->N2 = self->qos_tx.link_disc_time.value * 1000 /
 		self->qos_rx.max_turn_time.value;
-	IRDA_DEBUG(4, "Setting N2 = %d\n", self->N2);
+	pr_debug("Setting N2 = %d\n", self->N2);
 }
 
 #ifdef CONFIG_PROC_FS
diff --git a/net/irda/irlap_event.c b/net/irda/irlap_event.c
index ccd214f9d196..0e1b4d79f745 100644
--- a/net/irda/irlap_event.c
+++ b/net/irda/irlap_event.c
@@ -78,8 +78,7 @@ static int irlap_state_sclose (struct irlap_cb *self, IRLAP_EVENT event,
 static int irlap_state_reset_check(struct irlap_cb *, IRLAP_EVENT event,
 				   struct sk_buff *, struct irlap_info *);
 
-#ifdef CONFIG_IRDA_DEBUG
-static const char *const irlap_event[] = {
+static const char *const irlap_event[] __maybe_unused = {
 	"DISCOVERY_REQUEST",
 	"CONNECT_REQUEST",
 	"CONNECT_RESPONSE",
@@ -119,7 +118,6 @@ static const char *const irlap_event[] = {
 	"BACKOFF_TIMER_EXPIRED",
 	"MEDIA_BUSY_TIMER_EXPIRED",
 };
-#endif	/* CONFIG_IRDA_DEBUG */
 
 const char *const irlap_state[] = {
 	"LAP_NDM",
@@ -218,7 +216,7 @@ static void irlap_start_poll_timer(struct irlap_cb *self, int timeout)
 	} else
 		self->fast_RR = FALSE;
 
-	IRDA_DEBUG(3, "%s(), timeout=%d (%ld)\n", __func__, timeout, jiffies);
+	pr_debug("%s(), timeout=%d (%ld)\n", __func__, timeout, jiffies);
 #endif /* CONFIG_IRDA_FAST_RR */
 
 	if (timeout == 0)
@@ -242,8 +240,8 @@ void irlap_do_event(struct irlap_cb *self, IRLAP_EVENT event,
 	if (!self || self->magic != LAP_MAGIC)
 		return;
 
-	IRDA_DEBUG(3, "%s(), event = %s, state = %s\n", __func__,
-		   irlap_event[event], irlap_state[self->state]);
+	pr_debug("%s(), event = %s, state = %s\n", __func__,
+		 irlap_event[event], irlap_state[self->state]);
 
 	ret = (*state[self->state])(self, event, skb, info);
 
@@ -260,8 +258,8 @@ void irlap_do_event(struct irlap_cb *self, IRLAP_EVENT event,
 		 * try to disconnect link if we send any data frames, since
 		 * that will change the state away form XMIT
 		 */
-		IRDA_DEBUG(2, "%s() : queue len = %d\n", __func__,
-			   skb_queue_len(&self->txq));
+		pr_debug("%s() : queue len = %d\n", __func__,
+			 skb_queue_len(&self->txq));
 
 		if (!skb_queue_empty(&self->txq)) {
 			/* Prevent race conditions with irlap_data_request() */
@@ -340,8 +338,8 @@ static int irlap_state_ndm(struct irlap_cb *self, IRLAP_EVENT event,
 			/* Note : this will never happen, because we test
 			 * media busy in irlap_connect_request() and
 			 * postpone the event... - Jean II */
-			IRDA_DEBUG(0, "%s(), CONNECT_REQUEST: media busy!\n",
-				   __func__);
+			pr_debug("%s(), CONNECT_REQUEST: media busy!\n",
+				 __func__);
 
 			/* Always switch state before calling upper layers */
 			irlap_next_state(self, LAP_NDM);
@@ -367,16 +365,16 @@ static int irlap_state_ndm(struct irlap_cb *self, IRLAP_EVENT event,
 
 			irlap_connect_indication(self, skb);
 		} else {
-			IRDA_DEBUG(0, "%s(), SNRM frame does not "
-				   "contain an I field!\n", __func__);
+			pr_debug("%s(), SNRM frame does not contain an I field!\n",
+				 __func__);
 		}
 		break;
 	case DISCOVERY_REQUEST:
 		IRDA_ASSERT(info != NULL, return -1;);
 
 		if (self->media_busy) {
-			IRDA_DEBUG(1, "%s(), DISCOVERY_REQUEST: media busy!\n",
-				   __func__);
+			pr_debug("%s(), DISCOVERY_REQUEST: media busy!\n",
+				 __func__);
 			/* irlap->log.condition = MEDIA_BUSY; */
 
 			/* This will make IrLMP try again */
@@ -442,7 +440,8 @@ static int irlap_state_ndm(struct irlap_cb *self, IRLAP_EVENT event,
 		 * those cases...
 		 * Jean II
 		 */
-			IRDA_DEBUG(1, "%s(), Receiving final discovery request, missed the discovery slots :-(\n", __func__);
+			pr_debug("%s(), Receiving final discovery request, missed the discovery slots :-(\n",
+				 __func__);
 
 			/* Last discovery request -> in the log */
 			irlap_discovery_indication(self, info->discovery);
@@ -520,8 +519,8 @@ static int irlap_state_ndm(struct irlap_cb *self, IRLAP_EVENT event,
 	case RECV_UI_FRAME:
 		/* Only accept broadcast frames in NDM mode */
 		if (info->caddr != CBROADCAST) {
-			IRDA_DEBUG(0, "%s(), not a broadcast frame!\n",
-				   __func__);
+			pr_debug("%s(), not a broadcast frame!\n",
+				 __func__);
 		} else
 			irlap_unitdata_indication(self, skb);
 		break;
@@ -537,11 +536,11 @@ static int irlap_state_ndm(struct irlap_cb *self, IRLAP_EVENT event,
 		irlap_send_test_frame(self, CBROADCAST, info->daddr, skb);
 		break;
 	case RECV_TEST_RSP:
-		IRDA_DEBUG(0, "%s() not implemented!\n", __func__);
+		pr_debug("%s() not implemented!\n", __func__);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown event %s\n", __func__,
-			   irlap_event[event]);
+		pr_debug("%s(), Unknown event %s\n", __func__,
+			 irlap_event[event]);
 
 		ret = -1;
 		break;
@@ -568,13 +567,12 @@ static int irlap_state_query(struct irlap_cb *self, IRLAP_EVENT event,
 		IRDA_ASSERT(info != NULL, return -1;);
 		IRDA_ASSERT(info->discovery != NULL, return -1;);
 
-		IRDA_DEBUG(4, "%s(), daddr=%08x\n", __func__,
-			   info->discovery->data.daddr);
+		pr_debug("%s(), daddr=%08x\n", __func__,
+			 info->discovery->data.daddr);
 
 		if (!self->discovery_log) {
-			IRDA_WARNING("%s: discovery log is gone! "
-				     "maybe the discovery timeout has been set"
-				     " too short?\n", __func__);
+			net_warn_ratelimited("%s: discovery log is gone! maybe the discovery timeout has been set too short?\n",
+					     __func__);
 			break;
 		}
 		hashbin_insert(self->discovery_log,
@@ -599,7 +597,8 @@ static int irlap_state_query(struct irlap_cb *self, IRLAP_EVENT event,
 
 		IRDA_ASSERT(info != NULL, return -1;);
 
-		IRDA_DEBUG(1, "%s(), Receiving discovery request (s = %d) while performing discovery :-(\n", __func__, info->s);
+		pr_debug("%s(), Receiving discovery request (s = %d) while performing discovery :-(\n",
+			 __func__, info->s);
 
 		/* Last discovery request ? */
 		if (info->s == 0xff)
@@ -613,8 +612,8 @@ static int irlap_state_query(struct irlap_cb *self, IRLAP_EVENT event,
 		 * timing requirements.
 		 */
 		if (irda_device_is_receiving(self->netdev) && !self->add_wait) {
-			IRDA_DEBUG(2, "%s(), device is slow to answer, "
-				   "waiting some more!\n", __func__);
+			pr_debug("%s(), device is slow to answer, waiting some more!\n",
+				 __func__);
 			irlap_start_slot_timer(self, msecs_to_jiffies(10));
 			self->add_wait = TRUE;
 			return ret;
@@ -650,8 +649,8 @@ static int irlap_state_query(struct irlap_cb *self, IRLAP_EVENT event,
 		}
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown event %s\n", __func__,
-			   irlap_event[event]);
+		pr_debug("%s(), Unknown event %s\n", __func__,
+			 irlap_event[event]);
 
 		ret = -1;
 		break;
@@ -672,15 +671,13 @@ static int irlap_state_reply(struct irlap_cb *self, IRLAP_EVENT event,
 	discovery_t *discovery_rsp;
 	int ret=0;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return -1;);
 
 	switch (event) {
 	case QUERY_TIMER_EXPIRED:
-		IRDA_DEBUG(0, "%s(), QUERY_TIMER_EXPIRED <%ld>\n",
-			   __func__, jiffies);
+		pr_debug("%s(), QUERY_TIMER_EXPIRED <%ld>\n",
+			 __func__, jiffies);
 		irlap_next_state(self, LAP_NDM);
 		break;
 	case RECV_DISCOVERY_XID_CMD:
@@ -718,8 +715,8 @@ static int irlap_state_reply(struct irlap_cb *self, IRLAP_EVENT event,
 		}
 		break;
 	default:
-		IRDA_DEBUG(1, "%s(), Unknown event %d, %s\n", __func__,
-			   event, irlap_event[event]);
+		pr_debug("%s(), Unknown event %d, %s\n", __func__,
+			 event, irlap_event[event]);
 
 		ret = -1;
 		break;
@@ -739,7 +736,7 @@ static int irlap_state_conn(struct irlap_cb *self, IRLAP_EVENT event,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(4, "%s(), event=%s\n", __func__, irlap_event[ event]);
+	pr_debug("%s(), event=%s\n", __func__, irlap_event[event]);
 
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return -1;);
@@ -799,20 +796,20 @@ static int irlap_state_conn(struct irlap_cb *self, IRLAP_EVENT event,
 
 		break;
 	case RECV_DISCOVERY_XID_CMD:
-		IRDA_DEBUG(3, "%s(), event RECV_DISCOVER_XID_CMD!\n",
-			   __func__);
+		pr_debug("%s(), event RECV_DISCOVER_XID_CMD!\n",
+			 __func__);
 		irlap_next_state(self, LAP_NDM);
 
 		break;
 	case DISCONNECT_REQUEST:
-		IRDA_DEBUG(0, "%s(), Disconnect request!\n", __func__);
+		pr_debug("%s(), Disconnect request!\n", __func__);
 		irlap_send_dm_frame(self);
 		irlap_next_state( self, LAP_NDM);
 		irlap_disconnect_indication(self, LAP_DISC_INDICATION);
 		break;
 	default:
-		IRDA_DEBUG(1, "%s(), Unknown event %d, %s\n", __func__,
-			   event, irlap_event[event]);
+		pr_debug("%s(), Unknown event %d, %s\n", __func__,
+			 event, irlap_event[event]);
 
 		ret = -1;
 		break;
@@ -833,8 +830,6 @@ static int irlap_state_setup(struct irlap_cb *self, IRLAP_EVENT event,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return -1;);
 
@@ -862,7 +857,7 @@ static int irlap_state_setup(struct irlap_cb *self, IRLAP_EVENT event,
 		self->retry_count++;
 		break;
 	case RECV_SNRM_CMD:
-		IRDA_DEBUG(4, "%s(), SNRM battle!\n", __func__);
+		pr_debug("%s(), SNRM battle!\n", __func__);
 
 		IRDA_ASSERT(skb != NULL, return 0;);
 		IRDA_ASSERT(info != NULL, return 0;);
@@ -949,8 +944,8 @@ static int irlap_state_setup(struct irlap_cb *self, IRLAP_EVENT event,
 		irlap_disconnect_indication(self, LAP_DISC_INDICATION);
 		break;
 	default:
-		IRDA_DEBUG(1, "%s(), Unknown event %d, %s\n", __func__,
-			   event, irlap_event[event]);
+		pr_debug("%s(), Unknown event %d, %s\n", __func__,
+			 event, irlap_event[event]);
 
 		ret = -1;
 		break;
@@ -967,7 +962,7 @@ static int irlap_state_setup(struct irlap_cb *self, IRLAP_EVENT event,
 static int irlap_state_offline(struct irlap_cb *self, IRLAP_EVENT event,
 			       struct sk_buff *skb, struct irlap_info *info)
 {
-	IRDA_DEBUG( 0, "%s(), Unknown event\n", __func__);
+	pr_debug("%s(), Unknown event\n", __func__);
 
 	return -1;
 }
@@ -1030,8 +1025,8 @@ static int irlap_state_xmit_p(struct irlap_cb *self, IRLAP_EVENT event,
 			 *  speed and turn-around-time.
 			 */
 			if((!nextfit) && (skb->len > self->bytes_left)) {
-				IRDA_DEBUG(0, "%s(), Not allowed to transmit"
-					   " more bytes!\n", __func__);
+				pr_debug("%s(), Not allowed to transmit more bytes!\n",
+					 __func__);
 				/* Requeue the skb */
 				skb_queue_head(&self->txq, skb_get(skb));
 				/*
@@ -1082,8 +1077,8 @@ static int irlap_state_xmit_p(struct irlap_cb *self, IRLAP_EVENT event,
 			self->fast_RR = FALSE;
 #endif /* CONFIG_IRDA_FAST_RR */
 		} else {
-			IRDA_DEBUG(4, "%s(), Unable to send! remote busy?\n",
-				   __func__);
+			pr_debug("%s(), Unable to send! remote busy?\n",
+				 __func__);
 			skb_queue_head(&self->txq, skb_get(skb));
 
 			/*
@@ -1094,8 +1089,8 @@ static int irlap_state_xmit_p(struct irlap_cb *self, IRLAP_EVENT event,
 		}
 		break;
 	case POLL_TIMER_EXPIRED:
-		IRDA_DEBUG(3, "%s(), POLL_TIMER_EXPIRED <%ld>\n",
-			    __func__, jiffies);
+		pr_debug("%s(), POLL_TIMER_EXPIRED <%ld>\n",
+			 __func__, jiffies);
 		irlap_send_rr_frame(self, CMD_FRAME);
 		/* Return to NRM properly - Jean II  */
 		self->window = self->window_size;
@@ -1120,8 +1115,8 @@ static int irlap_state_xmit_p(struct irlap_cb *self, IRLAP_EVENT event,
 		 * when we return... - Jean II */
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), Unknown event %s\n",
-			   __func__, irlap_event[event]);
+		pr_debug("%s(), Unknown event %s\n",
+			 __func__, irlap_event[event]);
 
 		ret = -EINVAL;
 		break;
@@ -1139,8 +1134,6 @@ static int irlap_state_pclose(struct irlap_cb *self, IRLAP_EVENT event,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(1, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return -1;);
 
@@ -1174,7 +1167,7 @@ static int irlap_state_pclose(struct irlap_cb *self, IRLAP_EVENT event,
 		}
 		break;
 	default:
-		IRDA_DEBUG(1, "%s(), Unknown event %d\n", __func__, event);
+		pr_debug("%s(), Unknown event %d\n", __func__, event);
 
 		ret = -1;
 		break;
@@ -1296,9 +1289,8 @@ static int irlap_state_nrm_p(struct irlap_cb *self, IRLAP_EVENT event,
 				/* Keep state */
 				irlap_next_state(self, LAP_NRM_P);
 			} else {
-				IRDA_DEBUG(4,
-				       "%s(), missing or duplicate frame!\n",
-					   __func__);
+				pr_debug("%s(), missing or duplicate frame!\n",
+					 __func__);
 
 				/* Update Nr received */
 				irlap_update_nr_received(self, info->nr);
@@ -1367,8 +1359,8 @@ static int irlap_state_nrm_p(struct irlap_cb *self, IRLAP_EVENT event,
 		if ((ns_status == NS_UNEXPECTED) &&
 		    (nr_status == NR_UNEXPECTED))
 		{
-			IRDA_DEBUG(4, "%s(), unexpected nr and ns!\n",
-				   __func__);
+			pr_debug("%s(), unexpected nr and ns!\n",
+				 __func__);
 			if (info->pf) {
 				/* Resend rejected frames */
 				irlap_resend_rejected_frames(self, CMD_FRAME);
@@ -1408,9 +1400,9 @@ static int irlap_state_nrm_p(struct irlap_cb *self, IRLAP_EVENT event,
 			}
 			break;
 		}
-		IRDA_DEBUG(1, "%s(), Not implemented!\n", __func__);
-		IRDA_DEBUG(1, "%s(), event=%s, ns_status=%d, nr_status=%d\n",
-		       __func__, irlap_event[event], ns_status, nr_status);
+		pr_debug("%s(), Not implemented!\n", __func__);
+		pr_debug("%s(), event=%s, ns_status=%d, nr_status=%d\n",
+			 __func__, irlap_event[event], ns_status, nr_status);
 		break;
 	case RECV_UI_FRAME:
 		/* Poll bit cleared? */
@@ -1421,7 +1413,8 @@ static int irlap_state_nrm_p(struct irlap_cb *self, IRLAP_EVENT event,
 			del_timer(&self->final_timer);
 			irlap_data_indication(self, skb, TRUE);
 			irlap_next_state(self, LAP_XMIT_P);
-			IRDA_DEBUG(1, "%s: RECV_UI_FRAME: next state %s\n", __func__, irlap_state[self->state]);
+			pr_debug("%s: RECV_UI_FRAME: next state %s\n",
+				 __func__, irlap_state[self->state]);
 			irlap_start_poll_timer(self, self->poll_timeout);
 		}
 		break;
@@ -1464,10 +1457,9 @@ static int irlap_state_nrm_p(struct irlap_cb *self, IRLAP_EVENT event,
 			/* Update Nr received */
 			irlap_update_nr_received(self, info->nr);
 
-			IRDA_DEBUG(4, "RECV_RR_FRAME: Retrans:%d, nr=%d, va=%d, "
-			      "vs=%d, vr=%d\n",
-			      self->retry_count, info->nr, self->va,
-			      self->vs, self->vr);
+			pr_debug("RECV_RR_FRAME: Retrans:%d, nr=%d, va=%d, vs=%d, vr=%d\n",
+				 self->retry_count, info->nr, self->va,
+				 self->vs, self->vr);
 
 			/* Resend rejected frames */
 			irlap_resend_rejected_frames(self, CMD_FRAME);
@@ -1475,8 +1467,8 @@ static int irlap_state_nrm_p(struct irlap_cb *self, IRLAP_EVENT event,
 
 			irlap_next_state(self, LAP_NRM_P);
 		} else if (ret == NR_INVALID) {
-			IRDA_DEBUG(1, "%s(), Received RR with "
-				   "invalid nr !\n", __func__);
+			pr_debug("%s(), Received RR with invalid nr !\n",
+				 __func__);
 
 			irlap_next_state(self, LAP_RESET_WAIT);
 
@@ -1512,8 +1504,7 @@ static int irlap_state_nrm_p(struct irlap_cb *self, IRLAP_EVENT event,
 		 *  we only do this once for each frame.
 		 */
 		if (irda_device_is_receiving(self->netdev) && !self->add_wait) {
-			IRDA_DEBUG(1, "FINAL_TIMER_EXPIRED when receiving a "
-			      "frame! Waiting a little bit more!\n");
+			pr_debug("FINAL_TIMER_EXPIRED when receiving a frame! Waiting a little bit more!\n");
 			irlap_start_final_timer(self, msecs_to_jiffies(300));
 
 			/*
@@ -1530,18 +1521,18 @@ static int irlap_state_nrm_p(struct irlap_cb *self, IRLAP_EVENT event,
 		if (self->retry_count < self->N2) {
 			if (skb_peek(&self->wx_list) == NULL) {
 				/* Retry sending the pf bit to the secondary */
-				IRDA_DEBUG(4, "nrm_p: resending rr");
+				pr_debug("nrm_p: resending rr");
 				irlap_wait_min_turn_around(self, &self->qos_tx);
 				irlap_send_rr_frame(self, CMD_FRAME);
 			} else {
-				IRDA_DEBUG(4, "nrm_p: resend frames");
+				pr_debug("nrm_p: resend frames");
 				irlap_resend_rejected_frames(self, CMD_FRAME);
 			}
 
 			irlap_start_final_timer(self, self->final_timeout);
 			self->retry_count++;
-			IRDA_DEBUG(4, "irlap_state_nrm_p: FINAL_TIMER_EXPIRED:"
-				   " retry_count=%d\n", self->retry_count);
+			pr_debug("irlap_state_nrm_p: FINAL_TIMER_EXPIRED: retry_count=%d\n",
+				 self->retry_count);
 
 			/* Early warning event. I'm using a pretty liberal
 			 * interpretation of the spec and generate an event
@@ -1581,7 +1572,7 @@ static int irlap_state_nrm_p(struct irlap_cb *self, IRLAP_EVENT event,
 		irlap_start_final_timer(self, 2 * self->final_timeout);
 		break;
 	case RECV_RD_RSP:
-		IRDA_DEBUG(1, "%s(), RECV_RD_RSP\n", __func__);
+		pr_debug("%s(), RECV_RD_RSP\n", __func__);
 
 		irlap_flush_all_queues(self);
 		irlap_next_state(self, LAP_XMIT_P);
@@ -1589,8 +1580,8 @@ static int irlap_state_nrm_p(struct irlap_cb *self, IRLAP_EVENT event,
 		irlap_disconnect_request(self);
 		break;
 	default:
-		IRDA_DEBUG(1, "%s(), Unknown event %s\n",
-			    __func__, irlap_event[event]);
+		pr_debug("%s(), Unknown event %s\n",
+			 __func__, irlap_event[event]);
 
 		ret = -1;
 		break;
@@ -1610,7 +1601,7 @@ static int irlap_state_reset_wait(struct irlap_cb *self, IRLAP_EVENT event,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(3, "%s(), event = %s\n", __func__, irlap_event[event]);
+	pr_debug("%s(), event = %s\n", __func__, irlap_event[event]);
 
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return -1;);
@@ -1636,8 +1627,8 @@ static int irlap_state_reset_wait(struct irlap_cb *self, IRLAP_EVENT event,
 		irlap_next_state( self, LAP_PCLOSE);
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown event %s\n", __func__,
-			   irlap_event[event]);
+		pr_debug("%s(), Unknown event %s\n", __func__,
+			 irlap_event[event]);
 
 		ret = -1;
 		break;
@@ -1657,7 +1648,7 @@ static int irlap_state_reset(struct irlap_cb *self, IRLAP_EVENT event,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(3, "%s(), event = %s\n", __func__, irlap_event[event]);
+	pr_debug("%s(), event = %s\n", __func__, irlap_event[event]);
 
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return -1;);
@@ -1715,7 +1706,7 @@ static int irlap_state_reset(struct irlap_cb *self, IRLAP_EVENT event,
 		 * state
 		 */
 		if (!info) {
-			IRDA_DEBUG(3, "%s(), RECV_SNRM_CMD\n", __func__);
+			pr_debug("%s(), RECV_SNRM_CMD\n", __func__);
 			irlap_initiate_connection_state(self);
 			irlap_wait_min_turn_around(self, &self->qos_tx);
 			irlap_send_ua_response_frame(self, &self->qos_rx);
@@ -1723,14 +1714,13 @@ static int irlap_state_reset(struct irlap_cb *self, IRLAP_EVENT event,
 			irlap_start_wd_timer(self, self->wd_timeout);
 			irlap_next_state(self, LAP_NDM);
 		} else {
-			IRDA_DEBUG(0,
-				   "%s(), SNRM frame contained an I field!\n",
-				   __func__);
+			pr_debug("%s(), SNRM frame contained an I field!\n",
+				 __func__);
 		}
 		break;
 	default:
-		IRDA_DEBUG(1, "%s(), Unknown event %s\n",
-			   __func__, irlap_event[event]);
+		pr_debug("%s(), Unknown event %s\n",
+			 __func__, irlap_event[event]);
 
 		ret = -1;
 		break;
@@ -1750,7 +1740,7 @@ static int irlap_state_xmit_s(struct irlap_cb *self, IRLAP_EVENT event,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(4, "%s(), event=%s\n", __func__, irlap_event[event]);
+	pr_debug("%s(), event=%s\n", __func__, irlap_event[event]);
 
 	IRDA_ASSERT(self != NULL, return -ENODEV;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return -EBADR;);
@@ -1786,8 +1776,8 @@ static int irlap_state_xmit_s(struct irlap_cb *self, IRLAP_EVENT event,
 			 *  speed and turn-around-time.
 			 */
 			if((!nextfit) && (skb->len > self->bytes_left)) {
-				IRDA_DEBUG(0, "%s(), Not allowed to transmit"
-					   " more bytes!\n", __func__);
+				pr_debug("%s(), Not allowed to transmit more bytes!\n",
+					 __func__);
 				/* Requeue the skb */
 				skb_queue_head(&self->txq, skb_get(skb));
 
@@ -1833,7 +1823,7 @@ static int irlap_state_xmit_s(struct irlap_cb *self, IRLAP_EVENT event,
 				ret = -EPROTO;
 			}
 		} else {
-			IRDA_DEBUG(2, "%s(), Unable to send!\n", __func__);
+			pr_debug("%s(), Unable to send!\n", __func__);
 			skb_queue_head(&self->txq, skb_get(skb));
 			ret = -EPROTO;
 		}
@@ -1849,8 +1839,8 @@ static int irlap_state_xmit_s(struct irlap_cb *self, IRLAP_EVENT event,
 		 * when we return... - Jean II */
 		break;
 	default:
-		IRDA_DEBUG(2, "%s(), Unknown event %s\n", __func__,
-			   irlap_event[event]);
+		pr_debug("%s(), Unknown event %s\n", __func__,
+			 irlap_event[event]);
 
 		ret = -EINVAL;
 		break;
@@ -1872,7 +1862,7 @@ static int irlap_state_nrm_s(struct irlap_cb *self, IRLAP_EVENT event,
 	int nr_status;
 	int ret = 0;
 
-	IRDA_DEBUG(4, "%s(), event=%s\n", __func__, irlap_event[ event]);
+	pr_debug("%s(), event=%s\n", __func__, irlap_event[event]);
 
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return -1;);
@@ -1880,10 +1870,9 @@ static int irlap_state_nrm_s(struct irlap_cb *self, IRLAP_EVENT event,
 	switch (event) {
 	case RECV_I_CMD: /* Optimize for the common case */
 		/* FIXME: must check for remote_busy below */
-		IRDA_DEBUG(4, "%s(), event=%s nr=%d, vs=%d, ns=%d, "
-			   "vr=%d, pf=%d\n", __func__,
-			   irlap_event[event], info->nr,
-			   self->vs, info->ns, self->vr, info->pf);
+		pr_debug("%s(), event=%s nr=%d, vs=%d, ns=%d, vr=%d, pf=%d\n",
+			 __func__, irlap_event[event], info->nr,
+			 self->vs, info->ns, self->vr, info->pf);
 
 		self->retry_count = 0;
 
@@ -1983,7 +1972,7 @@ static int irlap_state_nrm_s(struct irlap_cb *self, IRLAP_EVENT event,
 		if ((ns_status == NS_EXPECTED) && (nr_status == NR_UNEXPECTED))
 		{
 			if (info->pf) {
-				IRDA_DEBUG(4, "RECV_I_RSP: frame(s) lost\n");
+				pr_debug("RECV_I_RSP: frame(s) lost\n");
 
 				self->vr = (self->vr + 1) % 8;
 
@@ -2020,10 +2009,10 @@ static int irlap_state_nrm_s(struct irlap_cb *self, IRLAP_EVENT event,
 		}
 
 		if (ret == NR_INVALID) {
-			IRDA_DEBUG(0, "NRM_S, NR_INVALID not implemented!\n");
+			pr_debug("NRM_S, NR_INVALID not implemented!\n");
 		}
 		if (ret == NS_INVALID) {
-			IRDA_DEBUG(0, "NRM_S, NS_INVALID not implemented!\n");
+			pr_debug("NRM_S, NS_INVALID not implemented!\n");
 		}
 		break;
 	case RECV_UI_FRAME:
@@ -2112,22 +2101,21 @@ static int irlap_state_nrm_s(struct irlap_cb *self, IRLAP_EVENT event,
 			/* Keep state */
 			irlap_next_state(self, LAP_NRM_S);
 		} else {
-			IRDA_DEBUG(1, "%s(), invalid nr not implemented!\n",
-				   __func__);
+			pr_debug("%s(), invalid nr not implemented!\n",
+				 __func__);
 		}
 		break;
 	case RECV_SNRM_CMD:
 		/* SNRM frame is not allowed to contain an I-field */
 		if (!info) {
 			del_timer(&self->wd_timer);
-			IRDA_DEBUG(1, "%s(), received SNRM cmd\n", __func__);
+			pr_debug("%s(), received SNRM cmd\n", __func__);
 			irlap_next_state(self, LAP_RESET_CHECK);
 
 			irlap_reset_indication(self);
 		} else {
-			IRDA_DEBUG(0,
-				   "%s(), SNRM frame contained an I-field!\n",
-				   __func__);
+			pr_debug("%s(), SNRM frame contained an I-field!\n",
+				 __func__);
 
 		}
 		break;
@@ -2159,8 +2147,8 @@ static int irlap_state_nrm_s(struct irlap_cb *self, IRLAP_EVENT event,
 		 *   which explain why we use (self->N2 / 2) here !!!
 		 * Jean II
 		 */
-		IRDA_DEBUG(1, "%s(), retry_count = %d\n", __func__,
-			   self->retry_count);
+		pr_debug("%s(), retry_count = %d\n", __func__,
+			 self->retry_count);
 
 		if (self->retry_count < (self->N2 / 2)) {
 			/* No retry, just wait for primary */
@@ -2212,8 +2200,8 @@ static int irlap_state_nrm_s(struct irlap_cb *self, IRLAP_EVENT event,
 		irlap_send_test_frame(self, self->caddr, info->daddr, skb);
 		break;
 	default:
-		IRDA_DEBUG(1, "%s(), Unknown event %d, (%s)\n", __func__,
-			   event, irlap_event[event]);
+		pr_debug("%s(), Unknown event %d, (%s)\n", __func__,
+			 event, irlap_event[event]);
 
 		ret = -EINVAL;
 		break;
@@ -2227,8 +2215,6 @@ static int irlap_state_nrm_s(struct irlap_cb *self, IRLAP_EVENT event,
 static int irlap_state_sclose(struct irlap_cb *self, IRLAP_EVENT event,
 			      struct sk_buff *skb, struct irlap_info *info)
 {
-	IRDA_DEBUG(1, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return -ENODEV;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return -EBADR;);
 
@@ -2284,8 +2270,8 @@ static int irlap_state_sclose(struct irlap_cb *self, IRLAP_EVENT event,
 			break;		/* stay in SCLOSE */
 		}
 
-		IRDA_DEBUG(1, "%s(), Unknown event %d, (%s)\n", __func__,
-			   event, irlap_event[event]);
+		pr_debug("%s(), Unknown event %d, (%s)\n", __func__,
+			 event, irlap_event[event]);
 
 		break;
 	}
@@ -2299,7 +2285,7 @@ static int irlap_state_reset_check( struct irlap_cb *self, IRLAP_EVENT event,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(1, "%s(), event=%s\n", __func__, irlap_event[event]);
+	pr_debug("%s(), event=%s\n", __func__, irlap_event[event]);
 
 	IRDA_ASSERT(self != NULL, return -ENODEV;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return -EBADR;);
@@ -2320,8 +2306,8 @@ static int irlap_state_reset_check( struct irlap_cb *self, IRLAP_EVENT event,
 		irlap_next_state(self, LAP_SCLOSE);
 		break;
 	default:
-		IRDA_DEBUG(1, "%s(), Unknown event %d, (%s)\n", __func__,
-			   event, irlap_event[event]);
+		pr_debug("%s(), Unknown event %d, (%s)\n", __func__,
+			 event, irlap_event[event]);
 
 		ret = -EINVAL;
 		break;
diff --git a/net/irda/irlap_frame.c b/net/irda/irlap_frame.c
index a37998c6273d..b936b1251a66 100644
--- a/net/irda/irlap_frame.c
+++ b/net/irda/irlap_frame.c
@@ -103,8 +103,8 @@ void irlap_queue_xmit(struct irlap_cb *self, struct sk_buff *skb)
 	irlap_insert_info(self, skb);
 
 	if (unlikely(self->mode & IRDA_MODE_MONITOR)) {
-		IRDA_DEBUG(3, "%s(): %s is in monitor mode\n", __func__,
-			   self->netdev->name);
+		pr_debug("%s(): %s is in monitor mode\n", __func__,
+			 self->netdev->name);
 		dev_kfree_skb(skb);
 		return;
 	}
@@ -182,8 +182,8 @@ static void irlap_recv_snrm_cmd(struct irlap_cb *self, struct sk_buff *skb,
 
 		/* Check if the new connection address is valid */
 		if ((info->caddr == 0x00) || (info->caddr == 0xfe)) {
-			IRDA_DEBUG(3, "%s(), invalid connection address!\n",
-				   __func__);
+			pr_debug("%s(), invalid connection address!\n",
+				 __func__);
 			return;
 		}
 
@@ -193,8 +193,8 @@ static void irlap_recv_snrm_cmd(struct irlap_cb *self, struct sk_buff *skb,
 
 		/* Only accept if addressed directly to us */
 		if (info->saddr != self->saddr) {
-			IRDA_DEBUG(2, "%s(), not addressed to us!\n",
-				   __func__);
+			pr_debug("%s(), not addressed to us!\n",
+				 __func__);
 			return;
 		}
 		irlap_do_event(self, RECV_SNRM_CMD, skb, info);
@@ -216,7 +216,7 @@ void irlap_send_ua_response_frame(struct irlap_cb *self, struct qos_info *qos)
 	struct ua_frame *frame;
 	int ret;
 
-	IRDA_DEBUG(2, "%s() <%ld>\n", __func__, jiffies);
+	pr_debug("%s() <%ld>\n", __func__, jiffies);
 
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
@@ -291,8 +291,6 @@ void irlap_send_disc_frame(struct irlap_cb *self)
 	struct sk_buff *tx_skb = NULL;
 	struct disc_frame *frame;
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 
@@ -322,8 +320,8 @@ void irlap_send_discovery_xid_frame(struct irlap_cb *self, int S, __u8 s,
 	__u32 bcast = BROADCAST;
 	__u8 *info;
 
-	IRDA_DEBUG(4, "%s(), s=%d, S=%d, command=%d\n", __func__,
-		   s, S, command);
+	pr_debug("%s(), s=%d, S=%d, command=%d\n", __func__,
+		 s, S, command);
 
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
@@ -415,13 +413,11 @@ static void irlap_recv_discovery_xid_rsp(struct irlap_cb *self,
 	__u8 *discovery_info;
 	char *text;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 
 	if (!pskb_may_pull(skb, sizeof(struct xid_frame))) {
-		IRDA_ERROR("%s: frame too short!\n", __func__);
+		net_err_ratelimited("%s: frame too short!\n", __func__);
 		return;
 	}
 
@@ -432,13 +428,13 @@ static void irlap_recv_discovery_xid_rsp(struct irlap_cb *self,
 
 	/* Make sure frame is addressed to us */
 	if ((info->saddr != self->saddr) && (info->saddr != BROADCAST)) {
-		IRDA_DEBUG(0, "%s(), frame is not addressed to us!\n",
-			   __func__);
+		pr_debug("%s(), frame is not addressed to us!\n",
+			 __func__);
 		return;
 	}
 
 	if ((discovery = kzalloc(sizeof(discovery_t), GFP_ATOMIC)) == NULL) {
-		IRDA_WARNING("%s: kmalloc failed!\n", __func__);
+		net_warn_ratelimited("%s: kmalloc failed!\n", __func__);
 		return;
 	}
 
@@ -446,15 +442,15 @@ static void irlap_recv_discovery_xid_rsp(struct irlap_cb *self,
 	discovery->data.saddr = self->saddr;
 	discovery->timestamp = jiffies;
 
-	IRDA_DEBUG(4, "%s(), daddr=%08x\n", __func__,
-		   discovery->data.daddr);
+	pr_debug("%s(), daddr=%08x\n", __func__,
+		 discovery->data.daddr);
 
 	discovery_info = skb_pull(skb, sizeof(struct xid_frame));
 
 	/* Get info returned from peer */
 	discovery->data.hints[0] = discovery_info[0];
 	if (discovery_info[0] & HINT_EXTENSION) {
-		IRDA_DEBUG(4, "EXTENSION\n");
+		pr_debug("EXTENSION\n");
 		discovery->data.hints[1] = discovery_info[1];
 		discovery->data.charset = discovery_info[2];
 		text = (char *) &discovery_info[3];
@@ -492,7 +488,7 @@ static void irlap_recv_discovery_xid_cmd(struct irlap_cb *self,
 	char *text;
 
 	if (!pskb_may_pull(skb, sizeof(struct xid_frame))) {
-		IRDA_ERROR("%s: frame too short!\n", __func__);
+		net_err_ratelimited("%s: frame too short!\n", __func__);
 		return;
 	}
 
@@ -503,8 +499,8 @@ static void irlap_recv_discovery_xid_cmd(struct irlap_cb *self,
 
 	/* Make sure frame is addressed to us */
 	if ((info->saddr != self->saddr) && (info->saddr != BROADCAST)) {
-		IRDA_DEBUG(0, "%s(), frame is not addressed to us!\n",
-			   __func__);
+		pr_debug("%s(), frame is not addressed to us!\n",
+			 __func__);
 		return;
 	}
 
@@ -536,8 +532,8 @@ static void irlap_recv_discovery_xid_cmd(struct irlap_cb *self,
 		/* Check if things are sane at this point... */
 		if((discovery_info == NULL) ||
 		   !pskb_may_pull(skb, 3)) {
-			IRDA_ERROR("%s: discovery frame too short!\n",
-				   __func__);
+			net_err_ratelimited("%s: discovery frame too short!\n",
+					    __func__);
 			return;
 		}
 
@@ -545,10 +541,8 @@ static void irlap_recv_discovery_xid_cmd(struct irlap_cb *self,
 		 *  We now have some discovery info to deliver!
 		 */
 		discovery = kzalloc(sizeof(discovery_t), GFP_ATOMIC);
-		if (!discovery) {
-			IRDA_WARNING("%s: unable to malloc!\n", __func__);
+		if (!discovery)
 			return;
-		}
 
 		discovery->data.daddr = info->daddr;
 		discovery->data.saddr = self->saddr;
@@ -658,7 +652,7 @@ static void irlap_recv_rnr_frame(struct irlap_cb *self, struct sk_buff *skb,
 {
 	info->nr = skb->data[1] >> 5;
 
-	IRDA_DEBUG(4, "%s(), nr=%d, %ld\n", __func__, info->nr, jiffies);
+	pr_debug("%s(), nr=%d, %ld\n", __func__, info->nr, jiffies);
 
 	if (command)
 		irlap_do_event(self, RECV_RNR_CMD, skb, info);
@@ -669,8 +663,6 @@ static void irlap_recv_rnr_frame(struct irlap_cb *self, struct sk_buff *skb,
 static void irlap_recv_rej_frame(struct irlap_cb *self, struct sk_buff *skb,
 				 struct irlap_info *info, int command)
 {
-	IRDA_DEBUG(0, "%s()\n", __func__);
-
 	info->nr = skb->data[1] >> 5;
 
 	/* Check if this is a command or a response frame */
@@ -683,8 +675,6 @@ static void irlap_recv_rej_frame(struct irlap_cb *self, struct sk_buff *skb,
 static void irlap_recv_srej_frame(struct irlap_cb *self, struct sk_buff *skb,
 				  struct irlap_info *info, int command)
 {
-	IRDA_DEBUG(0, "%s()\n", __func__);
-
 	info->nr = skb->data[1] >> 5;
 
 	/* Check if this is a command or a response frame */
@@ -697,8 +687,6 @@ static void irlap_recv_srej_frame(struct irlap_cb *self, struct sk_buff *skb,
 static void irlap_recv_disc_frame(struct irlap_cb *self, struct sk_buff *skb,
 				  struct irlap_info *info, int command)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/* Check if this is a command or a response frame */
 	if (command)
 		irlap_do_event(self, RECV_DISC_CMD, skb, info);
@@ -756,7 +744,7 @@ void irlap_send_data_primary(struct irlap_cb *self, struct sk_buff *skb)
 
 		irlap_send_i_frame( self, tx_skb, CMD_FRAME);
 	} else {
-		IRDA_DEBUG(4, "%s(), sending unreliable frame\n", __func__);
+		pr_debug("%s(), sending unreliable frame\n", __func__);
 		irlap_send_ui_frame(self, skb_get(skb), self->caddr, CMD_FRAME);
 		self->window -= 1;
 	}
@@ -809,7 +797,7 @@ void irlap_send_data_primary_poll(struct irlap_cb *self, struct sk_buff *skb)
 		irlap_next_state(self, LAP_NRM_P);
 		irlap_send_i_frame(self, tx_skb, CMD_FRAME);
 	} else {
-		IRDA_DEBUG(4, "%s(), sending unreliable frame\n", __func__);
+		pr_debug("%s(), sending unreliable frame\n", __func__);
 
 		if (self->ack_required) {
 			irlap_send_ui_frame(self, skb_get(skb), self->caddr, CMD_FRAME);
@@ -836,7 +824,9 @@ void irlap_send_data_primary_poll(struct irlap_cb *self, struct sk_buff *skb)
 	 * See max_line_capacities[][] in qos.c for details. Jean II */
 	transmission_time -= (self->final_timeout * self->bytes_left
 			      / self->line_capacity);
-	IRDA_DEBUG(4, "%s() adjusting transmission_time : ft=%d, bl=%d, lc=%d -> tt=%d\n", __func__, self->final_timeout, self->bytes_left, self->line_capacity, transmission_time);
+	pr_debug("%s() adjusting transmission_time : ft=%d, bl=%d, lc=%d -> tt=%d\n",
+		 __func__, self->final_timeout, self->bytes_left,
+		 self->line_capacity, transmission_time);
 
 	/* We are allowed to transmit a maximum number of bytes again. */
 	self->bytes_left = self->line_capacity;
@@ -997,7 +987,7 @@ void irlap_resend_rejected_frames(struct irlap_cb *self, int command)
 		/* tx_skb = skb_clone( skb, GFP_ATOMIC); */
 		tx_skb = skb_copy(skb, GFP_ATOMIC);
 		if (!tx_skb) {
-			IRDA_DEBUG(0, "%s(), unable to copy\n", __func__);
+			pr_debug("%s(), unable to copy\n", __func__);
 			return;
 		}
 
@@ -1020,7 +1010,7 @@ void irlap_resend_rejected_frames(struct irlap_cb *self, int command)
 	 */
 	while (!skb_queue_empty(&self->txq)) {
 
-		IRDA_DEBUG(0, "%s(), sending additional frames!\n", __func__);
+		pr_debug("%s(), sending additional frames!\n", __func__);
 		if (self->window > 0) {
 			skb = skb_dequeue( &self->txq);
 			IRDA_ASSERT(skb != NULL, return;);
@@ -1060,7 +1050,7 @@ void irlap_resend_rejected_frame(struct irlap_cb *self, int command)
 		/* tx_skb = skb_clone( skb, GFP_ATOMIC); */
 		tx_skb = skb_copy(skb, GFP_ATOMIC);
 		if (!tx_skb) {
-			IRDA_DEBUG(0, "%s(), unable to copy\n", __func__);
+			pr_debug("%s(), unable to copy\n", __func__);
 			return;
 		}
 
@@ -1083,8 +1073,6 @@ void irlap_resend_rejected_frame(struct irlap_cb *self, int command)
 void irlap_send_ui_frame(struct irlap_cb *self, struct sk_buff *skb,
 			 __u8 caddr, int command)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 	IRDA_ASSERT(skb != NULL, return;);
@@ -1143,8 +1131,6 @@ static inline void irlap_recv_i_frame(struct irlap_cb *self,
 static void irlap_recv_ui_frame(struct irlap_cb *self, struct sk_buff *skb,
 				struct irlap_info *info)
 {
-	IRDA_DEBUG( 4, "%s()\n", __func__);
-
 	info->pf = skb->data[1] & PF_BIT;      /* Final bit */
 
 	irlap_do_event(self, RECV_UI_FRAME, skb, info);
@@ -1162,15 +1148,13 @@ static void irlap_recv_frmr_frame(struct irlap_cb *self, struct sk_buff *skb,
 	__u8 *frame;
 	int w, x, y, z;
 
-	IRDA_DEBUG(0, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
 	IRDA_ASSERT(skb != NULL, return;);
 	IRDA_ASSERT(info != NULL, return;);
 
 	if (!pskb_may_pull(skb, 4)) {
-		IRDA_ERROR("%s: frame too short!\n", __func__);
+		net_err_ratelimited("%s: frame too short!\n", __func__);
 		return;
 	}
 
@@ -1186,21 +1170,16 @@ static void irlap_recv_frmr_frame(struct irlap_cb *self, struct sk_buff *skb,
 	z = frame[3] & 0x08;
 
 	if (w) {
-		IRDA_DEBUG(0, "Rejected control field is undefined or not "
-		      "implemented.\n");
+		pr_debug("Rejected control field is undefined or not implemented\n");
 	}
 	if (x) {
-		IRDA_DEBUG(0, "Rejected control field was invalid because it "
-		      "contained a non permitted I field.\n");
+		pr_debug("Rejected control field was invalid because it contained a non permitted I field\n");
 	}
 	if (y) {
-		IRDA_DEBUG(0, "Received I field exceeded the maximum negotiated "
-		      "for the existing connection or exceeded the maximum "
-		      "this station supports if no connection exists.\n");
+		pr_debug("Received I field exceeded the maximum negotiated for the existing connection or exceeded the maximum this station supports if no connection exists\n");
 	}
 	if (z) {
-		IRDA_DEBUG(0, "Rejected control field control field contained an "
-		      "invalid Nr count.\n");
+		pr_debug("Rejected control field control field contained an invalid Nr count\n");
 	}
 	irlap_do_event(self, RECV_FRMR_RSP, skb, info);
 }
@@ -1256,10 +1235,8 @@ static void irlap_recv_test_frame(struct irlap_cb *self, struct sk_buff *skb,
 {
 	struct test_frame *frame;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	if (!pskb_may_pull(skb, sizeof(*frame))) {
-		IRDA_ERROR("%s: frame too short!\n", __func__);
+		net_err_ratelimited("%s: frame too short!\n", __func__);
 		return;
 	}
 	frame = (struct test_frame *) skb->data;
@@ -1267,8 +1244,8 @@ static void irlap_recv_test_frame(struct irlap_cb *self, struct sk_buff *skb,
 	/* Broadcast frames must carry saddr and daddr fields */
 	if (info->caddr == CBROADCAST) {
 		if (skb->len < sizeof(struct test_frame)) {
-			IRDA_DEBUG(0, "%s() test frame too short!\n",
-				   __func__);
+			pr_debug("%s() test frame too short!\n",
+				 __func__);
 			return;
 		}
 
@@ -1328,13 +1305,13 @@ int irlap_driver_rcv(struct sk_buff *skb, struct net_device *dev,
 	 * share and non linear skbs. This should never happen, so
 	 * we don't need to be clever about it. Jean II */
 	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) {
-		IRDA_ERROR("%s: can't clone shared skb!\n", __func__);
+		net_err_ratelimited("%s: can't clone shared skb!\n", __func__);
 		goto err;
 	}
 
 	/* Check if frame is large enough for parsing */
 	if (!pskb_may_pull(skb, 2)) {
-		IRDA_ERROR("%s: frame too short!\n", __func__);
+		net_err_ratelimited("%s: frame too short!\n", __func__);
 		goto err;
 	}
 
@@ -1348,8 +1325,8 @@ int irlap_driver_rcv(struct sk_buff *skb, struct net_device *dev,
 
 	/*  First we check if this frame has a valid connection address */
 	if ((info.caddr != self->caddr) && (info.caddr != CBROADCAST)) {
-		IRDA_DEBUG(0, "%s(), wrong connection address!\n",
-			   __func__);
+		pr_debug("%s(), wrong connection address!\n",
+			 __func__);
 		goto out;
 	}
 	/*
@@ -1383,8 +1360,8 @@ int irlap_driver_rcv(struct sk_buff *skb, struct net_device *dev,
 			irlap_recv_srej_frame(self, skb, &info, command);
 			break;
 		default:
-			IRDA_WARNING("%s: Unknown S-frame %02x received!\n",
-				__func__, info.control);
+			net_warn_ratelimited("%s: Unknown S-frame %02x received!\n",
+					     __func__, info.control);
 			break;
 		}
 		goto out;
@@ -1421,8 +1398,8 @@ int irlap_driver_rcv(struct sk_buff *skb, struct net_device *dev,
 		irlap_recv_ui_frame(self, skb, &info);
 		break;
 	default:
-		IRDA_WARNING("%s: Unknown frame %02x received!\n",
-				__func__, info.control);
+		net_warn_ratelimited("%s: Unknown frame %02x received!\n",
+				     __func__, info.control);
 		break;
 	}
 out:
diff --git a/net/irda/irlmp.c b/net/irda/irlmp.c
index a5f28d421ea8..a26c401ef4a4 100644
--- a/net/irda/irlmp.c
+++ b/net/irda/irlmp.c
@@ -83,7 +83,6 @@ const char *irlmp_reason_str(LM_REASON reason)
  */
 int __init irlmp_init(void)
 {
-	IRDA_DEBUG(1, "%s()\n", __func__);
 	/* Initialize the irlmp structure. */
 	irlmp = kzalloc( sizeof(struct irlmp_cb), GFP_KERNEL);
 	if (irlmp == NULL)
@@ -170,10 +169,8 @@ struct lsap_cb *irlmp_open_lsap(__u8 slsap_sel, notify_t *notify, __u8 pid)
 
 	/* Allocate new instance of a LSAP connection */
 	self = kzalloc(sizeof(struct lsap_cb), GFP_ATOMIC);
-	if (self == NULL) {
-		IRDA_ERROR("%s: can't allocate memory\n", __func__);
+	if (self == NULL)
 		return NULL;
-	}
 
 	self->magic = LMP_LSAP_MAGIC;
 	self->slsap_sel = slsap_sel;
@@ -209,8 +206,6 @@ EXPORT_SYMBOL(irlmp_open_lsap);
  */
 static void __irlmp_close_lsap(struct lsap_cb *self)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return;);
 
@@ -269,9 +264,8 @@ void irlmp_close_lsap(struct lsap_cb *self)
 				      NULL);
 	}
 	if (!lsap) {
-		IRDA_DEBUG(0,
-		     "%s(), Looks like somebody has removed me already!\n",
-			   __func__);
+		pr_debug("%s(), Looks like somebody has removed me already!\n",
+			 __func__);
 		return;
 	}
 	__irlmp_close_lsap(self);
@@ -297,10 +291,8 @@ void irlmp_register_link(struct irlap_cb *irlap, __u32 saddr, notify_t *notify)
 	 *  Allocate new instance of a LSAP connection
 	 */
 	lap = kzalloc(sizeof(struct lap_cb), GFP_KERNEL);
-	if (lap == NULL) {
-		IRDA_ERROR("%s: unable to kmalloc\n", __func__);
+	if (lap == NULL)
 		return;
-	}
 
 	lap->irlap = irlap;
 	lap->magic = LMP_LAP_MAGIC;
@@ -311,7 +303,8 @@ void irlmp_register_link(struct irlap_cb *irlap, __u32 saddr, notify_t *notify)
 #endif
 	lap->lsaps = hashbin_new(HB_LOCK);
 	if (lap->lsaps == NULL) {
-		IRDA_WARNING("%s(), unable to kmalloc lsaps\n", __func__);
+		net_warn_ratelimited("%s(), unable to kmalloc lsaps\n",
+				     __func__);
 		kfree(lap);
 		return;
 	}
@@ -343,8 +336,6 @@ void irlmp_unregister_link(__u32 saddr)
 {
 	struct lap_cb *link;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	/* We must remove ourselves from the hashbin *first*. This ensure
 	 * that no more LSAPs will be open on this link and no discovery
 	 * will be triggered anymore. Jean II */
@@ -386,9 +377,8 @@ int irlmp_connect_request(struct lsap_cb *self, __u8 dlsap_sel,
 	IRDA_ASSERT(self != NULL, return -EBADR;);
 	IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return -EBADR;);
 
-	IRDA_DEBUG(2,
-	      "%s(), slsap_sel=%02x, dlsap_sel=%02x, saddr=%08x, daddr=%08x\n",
-	      __func__, self->slsap_sel, dlsap_sel, saddr, daddr);
+	pr_debug("%s(), slsap_sel=%02x, dlsap_sel=%02x, saddr=%08x, daddr=%08x\n",
+		 __func__, self->slsap_sel, dlsap_sel, saddr, daddr);
 
 	if (test_bit(0, &self->connected)) {
 		ret = -EISCONN;
@@ -432,7 +422,7 @@ int irlmp_connect_request(struct lsap_cb *self, __u8 dlsap_sel,
 		if (daddr != DEV_ADDR_ANY)
 			discovery = hashbin_find(irlmp->cachelog, daddr, NULL);
 		else {
-			IRDA_DEBUG(2, "%s(), no daddr\n", __func__);
+			pr_debug("%s(), no daddr\n", __func__);
 			discovery = (discovery_t *)
 				hashbin_get_first(irlmp->cachelog);
 		}
@@ -445,7 +435,7 @@ int irlmp_connect_request(struct lsap_cb *self, __u8 dlsap_sel,
 	}
 	lap = hashbin_lock_find(irlmp->links, saddr, NULL);
 	if (lap == NULL) {
-		IRDA_DEBUG(1, "%s(), Unable to find a usable link!\n", __func__);
+		pr_debug("%s(), Unable to find a usable link!\n", __func__);
 		ret = -EHOSTUNREACH;
 		goto err;
 	}
@@ -460,14 +450,15 @@ int irlmp_connect_request(struct lsap_cb *self, __u8 dlsap_sel,
 			 * disconnected yet (waiting for timeout in LAP).
 			 * Maybe we could give LAP a bit of help in this case.
 			 */
-			IRDA_DEBUG(0, "%s(), sorry, but I'm waiting for LAP to timeout!\n", __func__);
+			pr_debug("%s(), sorry, but I'm waiting for LAP to timeout!\n",
+				 __func__);
 			ret = -EAGAIN;
 			goto err;
 		}
 
 		/* LAP is already connected to a different node, and LAP
 		 * can only talk to one node at a time */
-		IRDA_DEBUG(0, "%s(), sorry, but link is busy!\n", __func__);
+		pr_debug("%s(), sorry, but link is busy!\n", __func__);
 		ret = -EBUSY;
 		goto err;
 	}
@@ -528,8 +519,8 @@ void irlmp_connect_indication(struct lsap_cb *self, struct sk_buff *skb)
 	IRDA_ASSERT(skb != NULL, return;);
 	IRDA_ASSERT(self->lap != NULL, return;);
 
-	IRDA_DEBUG(2, "%s(), slsap_sel=%02x, dlsap_sel=%02x\n",
-		   __func__, self->slsap_sel, self->dlsap_sel);
+	pr_debug("%s(), slsap_sel=%02x, dlsap_sel=%02x\n",
+		 __func__, self->slsap_sel, self->dlsap_sel);
 
 	/* Note : self->lap is set in irlmp_link_data_indication(),
 	 * (case CONNECT_CMD:) because we have no way to set it here.
@@ -569,8 +560,8 @@ int irlmp_connect_response(struct lsap_cb *self, struct sk_buff *userdata)
 	/* We set the connected bit and move the lsap to the connected list
 	 * in the state machine itself. Jean II */
 
-	IRDA_DEBUG(2, "%s(), slsap_sel=%02x, dlsap_sel=%02x\n",
-		   __func__, self->slsap_sel, self->dlsap_sel);
+	pr_debug("%s(), slsap_sel=%02x, dlsap_sel=%02x\n",
+		 __func__, self->slsap_sel, self->dlsap_sel);
 
 	/* Make room for MUX control header (3 bytes) */
 	IRDA_ASSERT(skb_headroom(userdata) >= LMP_CONTROL_HEADER, return -1;);
@@ -596,8 +587,6 @@ void irlmp_connect_confirm(struct lsap_cb *self, struct sk_buff *skb)
 	int lap_header_size;
 	int max_seg_size;
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	IRDA_ASSERT(skb != NULL, return;);
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return;);
@@ -609,8 +598,8 @@ void irlmp_connect_confirm(struct lsap_cb *self, struct sk_buff *skb)
 	lap_header_size = IRLAP_GET_HEADER_SIZE(self->lap->irlap);
 	max_header_size = LMP_HEADER + lap_header_size;
 
-	IRDA_DEBUG(2, "%s(), max_header_size=%d\n",
-		   __func__, max_header_size);
+	pr_debug("%s(), max_header_size=%d\n",
+		 __func__, max_header_size);
 
 	/* Hide LMP_CONTROL_HEADER header from layer above */
 	skb_pull(skb, LMP_CONTROL_HEADER);
@@ -636,16 +625,14 @@ struct lsap_cb *irlmp_dup(struct lsap_cb *orig, void *instance)
 	struct lsap_cb *new;
 	unsigned long flags;
 
-	IRDA_DEBUG(1, "%s()\n", __func__);
-
 	spin_lock_irqsave(&irlmp->unconnected_lsaps->hb_spinlock, flags);
 
 	/* Only allowed to duplicate unconnected LSAP's, and only LSAPs
 	 * that have received a connect indication. Jean II */
 	if ((!hashbin_find(irlmp->unconnected_lsaps, (long) orig, NULL)) ||
 	    (orig->lap == NULL)) {
-		IRDA_DEBUG(0, "%s(), invalid LSAP (wrong state)\n",
-			   __func__);
+		pr_debug("%s(), invalid LSAP (wrong state)\n",
+			 __func__);
 		spin_unlock_irqrestore(&irlmp->unconnected_lsaps->hb_spinlock,
 				       flags);
 		return NULL;
@@ -654,7 +641,7 @@ struct lsap_cb *irlmp_dup(struct lsap_cb *orig, void *instance)
 	/* Allocate a new instance */
 	new = kmemdup(orig, sizeof(*new), GFP_ATOMIC);
 	if (!new)  {
-		IRDA_DEBUG(0, "%s(), unable to kmalloc\n", __func__);
+		pr_debug("%s(), unable to kmalloc\n", __func__);
 		spin_unlock_irqrestore(&irlmp->unconnected_lsaps->hb_spinlock,
 				       flags);
 		return NULL;
@@ -700,7 +687,7 @@ int irlmp_disconnect_request(struct lsap_cb *self, struct sk_buff *userdata)
 	 * and us that might mess up the hashbins below. This fixes it.
 	 * Jean II */
 	if (! test_and_clear_bit(0, &self->connected)) {
-		IRDA_DEBUG(0, "%s(), already disconnected!\n", __func__);
+		pr_debug("%s(), already disconnected!\n", __func__);
 		dev_kfree_skb(userdata);
 		return -1;
 	}
@@ -754,20 +741,20 @@ void irlmp_disconnect_indication(struct lsap_cb *self, LM_REASON reason,
 {
 	struct lsap_cb *lsap;
 
-	IRDA_DEBUG(1, "%s(), reason=%s [%d]\n", __func__,
-		   irlmp_reason_str(reason), reason);
+	pr_debug("%s(), reason=%s [%d]\n", __func__,
+		 irlmp_reason_str(reason), reason);
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return;);
 
-	IRDA_DEBUG(3, "%s(), slsap_sel=%02x, dlsap_sel=%02x\n",
-		   __func__, self->slsap_sel, self->dlsap_sel);
+	pr_debug("%s(), slsap_sel=%02x, dlsap_sel=%02x\n",
+		 __func__, self->slsap_sel, self->dlsap_sel);
 
 	/* Already disconnected ?
 	 * There is a race condition between irlmp_disconnect_request()
 	 * and us that might mess up the hashbins below. This fixes it.
 	 * Jean II */
 	if (! test_and_clear_bit(0, &self->connected)) {
-		IRDA_DEBUG(0, "%s(), already disconnected!\n", __func__);
+		pr_debug("%s(), already disconnected!\n", __func__);
 		return;
 	}
 
@@ -800,7 +787,7 @@ void irlmp_disconnect_indication(struct lsap_cb *self, LM_REASON reason,
 		self->notify.disconnect_indication(self->notify.instance,
 						   self, reason, skb);
 	} else {
-		IRDA_DEBUG(0, "%s(), no handler\n", __func__);
+		pr_debug("%s(), no handler\n", __func__);
 	}
 }
 
@@ -852,8 +839,8 @@ void irlmp_do_discovery(int nslots)
 
 	/* Make sure the value is sane */
 	if ((nslots != 1) && (nslots != 6) && (nslots != 8) && (nslots != 16)){
-		IRDA_WARNING("%s: invalid value for number of slots!\n",
-			     __func__);
+		net_warn_ratelimited("%s: invalid value for number of slots!\n",
+				     __func__);
 		nslots = sysctl_discovery_slots = 8;
 	}
 
@@ -971,8 +958,6 @@ irlmp_notify_client(irlmp_client_t *client,
 	int	number;			/* Number of nodes in the log */
 	int	i;
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	/* Check if client wants or not partial/selective log (optimisation) */
 	if (!client->disco_callback)
 		return;
@@ -1022,8 +1007,6 @@ void irlmp_discovery_confirm(hashbin_t *log, DISCOVERY_MODE mode)
 	irlmp_client_t *client;
 	irlmp_client_t *client_next;
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	IRDA_ASSERT(log != NULL, return;);
 
 	if (!(HASHBIN_GET_SIZE(log)))
@@ -1057,8 +1040,6 @@ void irlmp_discovery_expiry(discinfo_t *expiries, int number)
 	irlmp_client_t *client_next;
 	int		i;
 
-	IRDA_DEBUG(3, "%s()\n", __func__);
-
 	IRDA_ASSERT(expiries != NULL, return;);
 
 	/* For each client - notify callback may touch client list */
@@ -1091,8 +1072,6 @@ void irlmp_discovery_expiry(discinfo_t *expiries, int number)
  */
 discovery_t *irlmp_get_discovery_response(void)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(irlmp != NULL, return NULL;);
 
 	put_unaligned(irlmp->hints.word, (__u16 *)irlmp->discovery_rsp.data.hints);
@@ -1169,8 +1148,6 @@ int irlmp_udata_request(struct lsap_cb *self, struct sk_buff *userdata)
 {
 	int	ret;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(userdata != NULL, return -1;);
 
 	/* Make room for MUX header */
@@ -1193,8 +1170,6 @@ int irlmp_udata_request(struct lsap_cb *self, struct sk_buff *userdata)
  */
 void irlmp_udata_indication(struct lsap_cb *self, struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return;);
 	IRDA_ASSERT(skb != NULL, return;);
@@ -1220,8 +1195,6 @@ int irlmp_connless_data_request(struct lsap_cb *self, struct sk_buff *userdata,
 	struct sk_buff *clone_skb;
 	struct lap_cb *lap;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(userdata != NULL, return -1;);
 
 	/* Make room for MUX and PID header */
@@ -1271,8 +1244,6 @@ int irlmp_connless_data_request(struct lsap_cb *self, struct sk_buff *userdata,
 #ifdef CONFIG_IRDA_ULTRA
 void irlmp_connless_data_indication(struct lsap_cb *self, struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return;);
 	IRDA_ASSERT(skb != NULL, return;);
@@ -1314,7 +1285,7 @@ void irlmp_status_indication(struct lap_cb *self,
 			curr->notify.status_indication(curr->notify.instance,
 						       link, lock);
 		else
-			IRDA_DEBUG(2, "%s(), no handler\n", __func__);
+			pr_debug("%s(), no handler\n", __func__);
 
 		curr = next;
 	}
@@ -1342,7 +1313,7 @@ void irlmp_flow_indication(struct lap_cb *self, LOCAL_FLOW flow)
 	/* Get the number of lsap. That's the only safe way to know
 	 * that we have looped around... - Jean II */
 	lsap_todo = HASHBIN_GET_SIZE(self->lsaps);
-	IRDA_DEBUG(4, "%s() : %d lsaps to scan\n", __func__, lsap_todo);
+	pr_debug("%s() : %d lsaps to scan\n", __func__, lsap_todo);
 
 	/* Poll lsap in order until the queue is full or until we
 	 * tried them all.
@@ -1361,14 +1332,16 @@ void irlmp_flow_indication(struct lap_cb *self, LOCAL_FLOW flow)
 		/* Uh-oh... Paranoia */
 		if(curr == NULL)
 			break;
-		IRDA_DEBUG(4, "%s() : curr is %p, next was %p and is now %p, still %d to go - queue len = %d\n", __func__, curr, next, self->flow_next, lsap_todo, IRLAP_GET_TX_QUEUE_LEN(self->irlap));
+		pr_debug("%s() : curr is %p, next was %p and is now %p, still %d to go - queue len = %d\n",
+			 __func__, curr, next, self->flow_next, lsap_todo,
+			 IRLAP_GET_TX_QUEUE_LEN(self->irlap));
 
 		/* Inform lsap user that it can send one more packet. */
 		if (curr->notify.flow_indication != NULL)
 			curr->notify.flow_indication(curr->notify.instance,
 						     curr, flow);
 		else
-			IRDA_DEBUG(1, "%s(), no handler\n", __func__);
+			pr_debug("%s(), no handler\n", __func__);
 	}
 }
 
@@ -1389,32 +1362,30 @@ __u8 *irlmp_hint_to_service(__u8 *hint)
 	 * since we currently only support 2 hint bytes
 	 */
 	service = kmalloc(16, GFP_ATOMIC);
-	if (!service) {
-		IRDA_DEBUG(1, "%s(), Unable to kmalloc!\n", __func__);
+	if (!service)
 		return NULL;
-	}
 
 	if (!hint[0]) {
-		IRDA_DEBUG(1, "<None>\n");
+		pr_debug("<None>\n");
 		kfree(service);
 		return NULL;
 	}
 	if (hint[0] & HINT_PNP)
-		IRDA_DEBUG(1, "PnP Compatible ");
+		pr_debug("PnP Compatible ");
 	if (hint[0] & HINT_PDA)
-		IRDA_DEBUG(1, "PDA/Palmtop ");
+		pr_debug("PDA/Palmtop ");
 	if (hint[0] & HINT_COMPUTER)
-		IRDA_DEBUG(1, "Computer ");
+		pr_debug("Computer ");
 	if (hint[0] & HINT_PRINTER) {
-		IRDA_DEBUG(1, "Printer ");
+		pr_debug("Printer ");
 		service[i++] = S_PRINTER;
 	}
 	if (hint[0] & HINT_MODEM)
-		IRDA_DEBUG(1, "Modem ");
+		pr_debug("Modem ");
 	if (hint[0] & HINT_FAX)
-		IRDA_DEBUG(1, "Fax ");
+		pr_debug("Fax ");
 	if (hint[0] & HINT_LAN) {
-		IRDA_DEBUG(1, "LAN Access ");
+		pr_debug("LAN Access ");
 		service[i++] = S_LAN;
 	}
 	/*
@@ -1424,22 +1395,22 @@ __u8 *irlmp_hint_to_service(__u8 *hint)
 	 */
 	if (hint[0] & HINT_EXTENSION) {
 		if (hint[1] & HINT_TELEPHONY) {
-			IRDA_DEBUG(1, "Telephony ");
+			pr_debug("Telephony ");
 			service[i++] = S_TELEPHONY;
 		}
 		if (hint[1] & HINT_FILE_SERVER)
-			IRDA_DEBUG(1, "File Server ");
+			pr_debug("File Server ");
 
 		if (hint[1] & HINT_COMM) {
-			IRDA_DEBUG(1, "IrCOMM ");
+			pr_debug("IrCOMM ");
 			service[i++] = S_COMM;
 		}
 		if (hint[1] & HINT_OBEX) {
-			IRDA_DEBUG(1, "IrOBEX ");
+			pr_debug("IrOBEX ");
 			service[i++] = S_OBEX;
 		}
 	}
-	IRDA_DEBUG(1, "\n");
+	pr_debug("\n");
 
 	/* So that client can be notified about any discovery */
 	service[i++] = S_ANY;
@@ -1492,14 +1463,13 @@ void *irlmp_register_service(__u16 hints)
 {
 	irlmp_service_t *service;
 
-	IRDA_DEBUG(4, "%s(), hints = %04x\n", __func__, hints);
+	pr_debug("%s(), hints = %04x\n", __func__, hints);
 
 	/* Make a new registration */
 	service = kmalloc(sizeof(irlmp_service_t), GFP_ATOMIC);
-	if (!service) {
-		IRDA_DEBUG(1, "%s(), Unable to kmalloc!\n", __func__);
+	if (!service)
 		return NULL;
-	}
+
 	service->hints.word = hints;
 	hashbin_insert(irlmp->services, (irda_queue_t *) service,
 		       (long) service, NULL);
@@ -1522,15 +1492,13 @@ int irlmp_unregister_service(void *handle)
 	irlmp_service_t *service;
 	unsigned long flags;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	if (!handle)
 		return -1;
 
 	/* Caller may call with invalid handle (it's legal) - Jean II */
 	service = hashbin_lock_find(irlmp->services, (long) handle, NULL);
 	if (!service) {
-		IRDA_DEBUG(1, "%s(), Unknown service!\n", __func__);
+		pr_debug("%s(), Unknown service!\n", __func__);
 		return -1;
 	}
 
@@ -1567,15 +1535,12 @@ void *irlmp_register_client(__u16 hint_mask, DISCOVERY_CALLBACK1 disco_clb,
 {
 	irlmp_client_t *client;
 
-	IRDA_DEBUG(1, "%s()\n", __func__);
 	IRDA_ASSERT(irlmp != NULL, return NULL;);
 
 	/* Make a new registration */
 	client = kmalloc(sizeof(irlmp_client_t), GFP_ATOMIC);
-	if (!client) {
-		IRDA_DEBUG( 1, "%s(), Unable to kmalloc!\n", __func__);
+	if (!client)
 		return NULL;
-	}
 
 	/* Register the details */
 	client->hint_mask.word = hint_mask;
@@ -1609,7 +1574,7 @@ int irlmp_update_client(void *handle, __u16 hint_mask,
 
 	client = hashbin_lock_find(irlmp->clients, (long) handle, NULL);
 	if (!client) {
-		IRDA_DEBUG(1, "%s(), Unknown client!\n", __func__);
+		pr_debug("%s(), Unknown client!\n", __func__);
 		return -1;
 	}
 
@@ -1632,19 +1597,17 @@ int irlmp_unregister_client(void *handle)
 {
 	struct irlmp_client *client;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	if (!handle)
 		return -1;
 
 	/* Caller may call with invalid handle (it's legal) - Jean II */
 	client = hashbin_lock_find(irlmp->clients, (long) handle, NULL);
 	if (!client) {
-		IRDA_DEBUG(1, "%s(), Unknown client!\n", __func__);
+		pr_debug("%s(), Unknown client!\n", __func__);
 		return -1;
 	}
 
-	IRDA_DEBUG(4, "%s(), removing client!\n", __func__);
+	pr_debug("%s(), removing client!\n", __func__);
 	hashbin_remove_this(irlmp->clients, (irda_queue_t *) client);
 	kfree(client);
 
@@ -1673,8 +1636,6 @@ static int irlmp_slsap_inuse(__u8 slsap_sel)
 	IRDA_ASSERT(irlmp->magic == LMP_MAGIC, return TRUE;);
 	IRDA_ASSERT(slsap_sel != LSAP_ANY, return TRUE;);
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 #ifdef CONFIG_IRDA_ULTRA
 	/* Accept all bindings to the connectionless LSAP */
 	if (slsap_sel == LSAP_CONNLESS)
@@ -1708,8 +1669,8 @@ static int irlmp_slsap_inuse(__u8 slsap_sel)
 				    goto errlsap;);
 
 			if ((self->slsap_sel == slsap_sel)) {
-				IRDA_DEBUG(4, "Source LSAP selector=%02x in use\n",
-					   self->slsap_sel);
+				pr_debug("Source LSAP selector=%02x in use\n",
+					 self->slsap_sel);
 				goto errlsap;
 			}
 			self = (struct lsap_cb*) hashbin_get_next(lap->lsaps);
@@ -1733,8 +1694,8 @@ static int irlmp_slsap_inuse(__u8 slsap_sel)
 	while (self != NULL) {
 		IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, goto erruncon;);
 		if ((self->slsap_sel == slsap_sel)) {
-			IRDA_DEBUG(4, "Source LSAP selector=%02x in use (unconnected)\n",
-				   self->slsap_sel);
+			pr_debug("Source LSAP selector=%02x in use (unconnected)\n",
+				 self->slsap_sel);
 			goto erruncon;
 		}
 		self = (struct lsap_cb*) hashbin_get_next(irlmp->unconnected_lsaps);
@@ -1799,8 +1760,8 @@ static __u8 irlmp_find_free_slsap(void)
 
 			/* Make sure we terminate the loop */
 			if (wrapped++) {
-				IRDA_ERROR("%s: no more free LSAPs !\n",
-					   __func__);
+				net_err_ratelimited("%s: no more free LSAPs !\n",
+						    __func__);
 				return 0;
 			}
 		}
@@ -1814,8 +1775,8 @@ static __u8 irlmp_find_free_slsap(void)
 
 	/* Got it ! */
 	lsap_sel = irlmp->last_lsap_sel;
-	IRDA_DEBUG(4, "%s(), found free lsap_sel=%02x\n",
-		   __func__, lsap_sel);
+	pr_debug("%s(), found free lsap_sel=%02x\n",
+		 __func__, lsap_sel);
 
 	return lsap_sel;
 }
@@ -1833,26 +1794,27 @@ LM_REASON irlmp_convert_lap_reason( LAP_REASON lap_reason)
 
 	switch (lap_reason) {
 	case LAP_DISC_INDICATION: /* Received a disconnect request from peer */
-		IRDA_DEBUG( 1, "%s(), LAP_DISC_INDICATION\n", __func__);
+		pr_debug("%s(), LAP_DISC_INDICATION\n", __func__);
 		reason = LM_USER_REQUEST;
 		break;
 	case LAP_NO_RESPONSE:    /* To many retransmits without response */
-		IRDA_DEBUG( 1, "%s(), LAP_NO_RESPONSE\n", __func__);
+		pr_debug("%s(), LAP_NO_RESPONSE\n", __func__);
 		reason = LM_LAP_DISCONNECT;
 		break;
 	case LAP_RESET_INDICATION:
-		IRDA_DEBUG( 1, "%s(), LAP_RESET_INDICATION\n", __func__);
+		pr_debug("%s(), LAP_RESET_INDICATION\n", __func__);
 		reason = LM_LAP_RESET;
 		break;
 	case LAP_FOUND_NONE:
 	case LAP_MEDIA_BUSY:
 	case LAP_PRIMARY_CONFLICT:
-		IRDA_DEBUG(1, "%s(), LAP_FOUND_NONE, LAP_MEDIA_BUSY or LAP_PRIMARY_CONFLICT\n", __func__);
+		pr_debug("%s(), LAP_FOUND_NONE, LAP_MEDIA_BUSY or LAP_PRIMARY_CONFLICT\n",
+			 __func__);
 		reason = LM_CONNECT_FAILURE;
 		break;
 	default:
-		IRDA_DEBUG(1, "%s(), Unknown IrLAP disconnect reason %d!\n",
-			   __func__, lap_reason);
+		pr_debug("%s(), Unknown IrLAP disconnect reason %d!\n",
+			 __func__, lap_reason);
 		reason = LM_LAP_DISCONNECT;
 		break;
 	}
diff --git a/net/irda/irlmp_event.c b/net/irda/irlmp_event.c
index 9505a7d06f1a..e306cf2c1e04 100644
--- a/net/irda/irlmp_event.c
+++ b/net/irda/irlmp_event.c
@@ -48,8 +48,7 @@ const char *const irlsap_state[] = {
 	"LSAP_SETUP_PEND",
 };
 
-#ifdef CONFIG_IRDA_DEBUG
-static const char *const irlmp_event[] = {
+static const char *const irlmp_event[] __maybe_unused = {
 	"LM_CONNECT_REQUEST",
 	"LM_CONNECT_CONFIRM",
 	"LM_CONNECT_RESPONSE",
@@ -75,7 +74,6 @@ static const char *const irlmp_event[] = {
 	"LM_LAP_DISCOVERY_CONFIRM",
 	"LM_LAP_IDLE_TIMEOUT",
 };
-#endif	/* CONFIG_IRDA_DEBUG */
 
 /* LAP Connection control proto declarations */
 static void irlmp_state_standby  (struct lap_cb *, IRLMP_EVENT,
@@ -120,7 +118,7 @@ static inline void irlmp_next_lap_state(struct lap_cb *self,
 					IRLMP_STATE state)
 {
 	/*
-	IRDA_DEBUG(4, "%s(), LMP LAP = %s\n", __func__, irlmp_state[state]);
+	  pr_debug("%s(), LMP LAP = %s\n", __func__, irlmp_state[state]);
 	*/
 	self->lap_state = state;
 }
@@ -130,7 +128,7 @@ static inline void irlmp_next_lsap_state(struct lsap_cb *self,
 {
 	/*
 	IRDA_ASSERT(self != NULL, return;);
-	IRDA_DEBUG(4, "%s(), LMP LSAP = %s\n", __func__, irlsap_state[state]);
+	pr_debug("%s(), LMP LSAP = %s\n", __func__, irlsap_state[state]);
 	*/
 	self->lsap_state = state;
 }
@@ -142,8 +140,8 @@ int irlmp_do_lsap_event(struct lsap_cb *self, IRLMP_EVENT event,
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return -1;);
 
-	IRDA_DEBUG(4, "%s(), EVENT = %s, STATE = %s\n",
-		__func__, irlmp_event[event], irlsap_state[ self->lsap_state]);
+	pr_debug("%s(), EVENT = %s, STATE = %s\n",
+		 __func__, irlmp_event[event], irlsap_state[self->lsap_state]);
 
 	return (*lsap_state[self->lsap_state]) (self, event, skb);
 }
@@ -160,17 +158,15 @@ void irlmp_do_lap_event(struct lap_cb *self, IRLMP_EVENT event,
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LMP_LAP_MAGIC, return;);
 
-	IRDA_DEBUG(4, "%s(), EVENT = %s, STATE = %s\n", __func__,
-		   irlmp_event[event],
-		   irlmp_state[self->lap_state]);
+	pr_debug("%s(), EVENT = %s, STATE = %s\n", __func__,
+		 irlmp_event[event],
+		 irlmp_state[self->lap_state]);
 
 	(*lap_state[self->lap_state]) (self, event, skb);
 }
 
 void irlmp_discovery_timer_expired(void *data)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	/* We always cleanup the log (active & passive discovery) */
 	irlmp_do_expiry();
 
@@ -184,8 +180,6 @@ void irlmp_watchdog_timer_expired(void *data)
 {
 	struct lsap_cb *self = (struct lsap_cb *) data;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return;);
 
@@ -196,8 +190,6 @@ void irlmp_idle_timer_expired(void *data)
 {
 	struct lap_cb *self = (struct lap_cb *) data;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LMP_LAP_MAGIC, return;);
 
@@ -256,7 +248,6 @@ irlmp_do_all_lsap_event(hashbin_t *	lsap_hashbin,
 static void irlmp_state_standby(struct lap_cb *self, IRLMP_EVENT event,
 				struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
 	IRDA_ASSERT(self->irlap != NULL, return;);
 
 	switch (event) {
@@ -276,7 +267,7 @@ static void irlmp_state_standby(struct lap_cb *self, IRLMP_EVENT event,
 		irlap_connect_response(self->irlap, skb);
 		break;
 	case LM_LAP_CONNECT_REQUEST:
-		IRDA_DEBUG(4, "%s() LS_CONNECT_REQUEST\n", __func__);
+		pr_debug("%s() LS_CONNECT_REQUEST\n", __func__);
 
 		irlmp_next_lap_state(self, LAP_U_CONNECT);
 
@@ -284,14 +275,14 @@ static void irlmp_state_standby(struct lap_cb *self, IRLMP_EVENT event,
 		irlap_connect_request(self->irlap, self->daddr, NULL, 0);
 		break;
 	case LM_LAP_DISCONNECT_INDICATION:
-		IRDA_DEBUG(4, "%s(), Error LM_LAP_DISCONNECT_INDICATION\n",
-			   __func__);
+		pr_debug("%s(), Error LM_LAP_DISCONNECT_INDICATION\n",
+			 __func__);
 
 		irlmp_next_lap_state(self, LAP_STANDBY);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), Unknown event %s\n",
-			   __func__, irlmp_event[event]);
+		pr_debug("%s(), Unknown event %s\n",
+			 __func__, irlmp_event[event]);
 		break;
 	}
 }
@@ -306,7 +297,7 @@ static void irlmp_state_standby(struct lap_cb *self, IRLMP_EVENT event,
 static void irlmp_state_u_connect(struct lap_cb *self, IRLMP_EVENT event,
 				  struct sk_buff *skb)
 {
-	IRDA_DEBUG(2, "%s(), event=%s\n", __func__, irlmp_event[event]);
+	pr_debug("%s(), event=%s\n", __func__, irlmp_event[event]);
 
 	switch (event) {
 	case LM_LAP_CONNECT_INDICATION:
@@ -326,7 +317,7 @@ static void irlmp_state_u_connect(struct lap_cb *self, IRLMP_EVENT event,
 		 * the lsaps may already have gone. This avoid getting stuck
 		 * forever in LAP_ACTIVE state - Jean II */
 		if (HASHBIN_GET_SIZE(self->lsaps) == 0) {
-			IRDA_DEBUG(0, "%s() NO LSAPs !\n",  __func__);
+			pr_debug("%s() NO LSAPs !\n",  __func__);
 			irlmp_start_idle_timer(self, LM_IDLE_TIMEOUT);
 		}
 		break;
@@ -344,12 +335,12 @@ static void irlmp_state_u_connect(struct lap_cb *self, IRLMP_EVENT event,
 		 * the lsaps may already have gone. This avoid getting stuck
 		 * forever in LAP_ACTIVE state - Jean II */
 		if (HASHBIN_GET_SIZE(self->lsaps) == 0) {
-			IRDA_DEBUG(0, "%s() NO LSAPs !\n",  __func__);
+			pr_debug("%s() NO LSAPs !\n",  __func__);
 			irlmp_start_idle_timer(self, LM_IDLE_TIMEOUT);
 		}
 		break;
 	case LM_LAP_DISCONNECT_INDICATION:
-		IRDA_DEBUG(4, "%s(), LM_LAP_DISCONNECT_INDICATION\n",  __func__);
+		pr_debug("%s(), LM_LAP_DISCONNECT_INDICATION\n",  __func__);
 		irlmp_next_lap_state(self, LAP_STANDBY);
 
 		/* Send disconnect event to all LSAPs using this link */
@@ -357,7 +348,7 @@ static void irlmp_state_u_connect(struct lap_cb *self, IRLMP_EVENT event,
 					LM_LAP_DISCONNECT_INDICATION);
 		break;
 	case LM_LAP_DISCONNECT_REQUEST:
-		IRDA_DEBUG(4, "%s(), LM_LAP_DISCONNECT_REQUEST\n",  __func__);
+		pr_debug("%s(), LM_LAP_DISCONNECT_REQUEST\n",  __func__);
 
 		/* One of the LSAP did timeout or was closed, if it was
 		 * the last one, try to get out of here - Jean II */
@@ -366,7 +357,7 @@ static void irlmp_state_u_connect(struct lap_cb *self, IRLMP_EVENT event,
 		}
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), Unknown event %s\n",
+		pr_debug("%s(), Unknown event %s\n",
 			 __func__, irlmp_event[event]);
 		break;
 	}
@@ -381,11 +372,9 @@ static void irlmp_state_u_connect(struct lap_cb *self, IRLMP_EVENT event,
 static void irlmp_state_active(struct lap_cb *self, IRLMP_EVENT event,
 			       struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	switch (event) {
 	case LM_LAP_CONNECT_REQUEST:
-		IRDA_DEBUG(4, "%s(), LS_CONNECT_REQUEST\n", __func__);
+		pr_debug("%s(), LS_CONNECT_REQUEST\n", __func__);
 
 		/*
 		 * IrLAP may have a pending disconnect. We tried to close
@@ -467,7 +456,7 @@ static void irlmp_state_active(struct lap_cb *self, IRLMP_EVENT event,
 		irlmp_do_expiry();
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), Unknown event %s\n",
+		pr_debug("%s(), Unknown event %s\n",
 			 __func__, irlmp_event[event]);
 		break;
 	}
@@ -490,8 +479,6 @@ static int irlmp_state_disconnected(struct lsap_cb *self, IRLMP_EVENT event,
 {
 	int ret = 0;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return -1;);
 
@@ -505,11 +492,11 @@ static int irlmp_state_disconnected(struct lsap_cb *self, IRLMP_EVENT event,
 		break;
 #endif /* CONFIG_IRDA_ULTRA */
 	case LM_CONNECT_REQUEST:
-		IRDA_DEBUG(4, "%s(), LM_CONNECT_REQUEST\n", __func__);
+		pr_debug("%s(), LM_CONNECT_REQUEST\n", __func__);
 
 		if (self->conn_skb) {
-			IRDA_WARNING("%s: busy with another request!\n",
-				     __func__);
+			net_warn_ratelimited("%s: busy with another request!\n",
+					     __func__);
 			return -EBUSY;
 		}
 		/* Don't forget to refcount it (see irlmp_connect_request()) */
@@ -525,8 +512,8 @@ static int irlmp_state_disconnected(struct lsap_cb *self, IRLMP_EVENT event,
 		break;
 	case LM_CONNECT_INDICATION:
 		if (self->conn_skb) {
-			IRDA_WARNING("%s: busy with another request!\n",
-				     __func__);
+			net_warn_ratelimited("%s: busy with another request!\n",
+					     __func__);
 			return -EBUSY;
 		}
 		/* Don't forget to refcount it (see irlap_driver_rcv()) */
@@ -551,8 +538,8 @@ static int irlmp_state_disconnected(struct lsap_cb *self, IRLMP_EVENT event,
 		irlmp_do_lap_event(self->lap, LM_LAP_CONNECT_REQUEST, NULL);
 		break;
 	default:
-		IRDA_DEBUG(1, "%s(), Unknown event %s on LSAP %#02x\n",
-			   __func__, irlmp_event[event], self->slsap_sel);
+		pr_debug("%s(), Unknown event %s on LSAP %#02x\n",
+			 __func__, irlmp_event[event], self->slsap_sel);
 		break;
 	}
 	return ret;
@@ -570,8 +557,6 @@ static int irlmp_state_connect(struct lsap_cb *self, IRLMP_EVENT event,
 	struct lsap_cb *lsap;
 	int ret = 0;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return -1;);
 
@@ -603,7 +588,7 @@ static int irlmp_state_connect(struct lsap_cb *self, IRLMP_EVENT event,
 	case LM_WATCHDOG_TIMEOUT:
 		/* May happen, who knows...
 		 * Jean II */
-		IRDA_DEBUG(0, "%s() WATCHDOG_TIMEOUT!\n",  __func__);
+		pr_debug("%s() WATCHDOG_TIMEOUT!\n",  __func__);
 
 		/* Disconnect, get out... - Jean II */
 		self->lap = NULL;
@@ -613,8 +598,8 @@ static int irlmp_state_connect(struct lsap_cb *self, IRLMP_EVENT event,
 	default:
 		/* LM_LAP_DISCONNECT_INDICATION : Should never happen, we
 		 * are *not* yet bound to the IrLAP link. Jean II */
-		IRDA_DEBUG(0, "%s(), Unknown event %s on LSAP %#02x\n",
-			   __func__, irlmp_event[event], self->slsap_sel);
+		pr_debug("%s(), Unknown event %s on LSAP %#02x\n",
+			 __func__, irlmp_event[event], self->slsap_sel);
 		break;
 	}
 	return ret;
@@ -632,8 +617,6 @@ static int irlmp_state_connect_pend(struct lsap_cb *self, IRLMP_EVENT event,
 	struct sk_buff *tx_skb;
 	int ret = 0;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return -1;);
 
@@ -642,17 +625,17 @@ static int irlmp_state_connect_pend(struct lsap_cb *self, IRLMP_EVENT event,
 		/* Keep state */
 		break;
 	case LM_CONNECT_RESPONSE:
-		IRDA_DEBUG(0, "%s(), LM_CONNECT_RESPONSE, "
-			   "no indication issued yet\n",  __func__);
+		pr_debug("%s(), LM_CONNECT_RESPONSE, no indication issued yet\n",
+			 __func__);
 		/* Keep state */
 		break;
 	case LM_DISCONNECT_REQUEST:
-		IRDA_DEBUG(0, "%s(), LM_DISCONNECT_REQUEST, "
-			   "not yet bound to IrLAP connection\n",  __func__);
+		pr_debug("%s(), LM_DISCONNECT_REQUEST, not yet bound to IrLAP connection\n",
+			 __func__);
 		/* Keep state */
 		break;
 	case LM_LAP_CONNECT_CONFIRM:
-		IRDA_DEBUG(4, "%s(), LS_CONNECT_CONFIRM\n",  __func__);
+		pr_debug("%s(), LS_CONNECT_CONFIRM\n",  __func__);
 		irlmp_next_lsap_state(self, LSAP_CONNECT);
 
 		tx_skb = self->conn_skb;
@@ -666,7 +649,7 @@ static int irlmp_state_connect_pend(struct lsap_cb *self, IRLMP_EVENT event,
 		/* Will happen in some rare cases because of a race condition.
 		 * Just make sure we don't stay there forever...
 		 * Jean II */
-		IRDA_DEBUG(0, "%s() WATCHDOG_TIMEOUT!\n",  __func__);
+		pr_debug("%s() WATCHDOG_TIMEOUT!\n",  __func__);
 
 		/* Go back to disconnected mode, keep the socket waiting */
 		self->lap = NULL;
@@ -679,8 +662,8 @@ static int irlmp_state_connect_pend(struct lsap_cb *self, IRLMP_EVENT event,
 	default:
 		/* LM_LAP_DISCONNECT_INDICATION : Should never happen, we
 		 * are *not* yet bound to the IrLAP link. Jean II */
-		IRDA_DEBUG(0, "%s(), Unknown event %s on LSAP %#02x\n",
-			   __func__, irlmp_event[event], self->slsap_sel);
+		pr_debug("%s(), Unknown event %s on LSAP %#02x\n",
+			 __func__, irlmp_event[event], self->slsap_sel);
 		break;
 	}
 	return ret;
@@ -698,8 +681,6 @@ static int irlmp_state_dtr(struct lsap_cb *self, IRLMP_EVENT event,
 	LM_REASON reason;
 	int ret = 0;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return -1;);
 	IRDA_ASSERT(self->lap != NULL, return -1;);
@@ -721,13 +702,13 @@ static int irlmp_state_dtr(struct lsap_cb *self, IRLMP_EVENT event,
 		irlmp_udata_indication(self, skb);
 		break;
 	case LM_CONNECT_REQUEST:
-		IRDA_DEBUG(0, "%s(), LM_CONNECT_REQUEST, "
-			   "error, LSAP already connected\n", __func__);
+		pr_debug("%s(), LM_CONNECT_REQUEST, error, LSAP already connected\n",
+			 __func__);
 		/* Keep state */
 		break;
 	case LM_CONNECT_RESPONSE:
-		IRDA_DEBUG(0, "%s(), LM_CONNECT_RESPONSE, "
-			   "error, LSAP already connected\n", __func__);
+		pr_debug("%s(), LM_CONNECT_RESPONSE, error, LSAP already connected\n",
+			 __func__);
 		/* Keep state */
 		break;
 	case LM_DISCONNECT_REQUEST:
@@ -739,8 +720,8 @@ static int irlmp_state_dtr(struct lsap_cb *self, IRLMP_EVENT event,
 
 		/* Try to close the LAP connection if its still there */
 		if (self->lap) {
-			IRDA_DEBUG(4, "%s(), trying to close IrLAP\n",
-				   __func__);
+			pr_debug("%s(), trying to close IrLAP\n",
+				 __func__);
 			irlmp_do_lap_event(self->lap,
 					   LM_LAP_DISCONNECT_REQUEST,
 					   NULL);
@@ -764,14 +745,14 @@ static int irlmp_state_dtr(struct lsap_cb *self, IRLMP_EVENT event,
 		reason = skb->data[3];
 
 		 /* Try to close the LAP connection */
-		IRDA_DEBUG(4, "%s(), trying to close IrLAP\n", __func__);
+		pr_debug("%s(), trying to close IrLAP\n", __func__);
 		irlmp_do_lap_event(self->lap, LM_LAP_DISCONNECT_REQUEST, NULL);
 
 		irlmp_disconnect_indication(self, reason, skb);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), Unknown event %s on LSAP %#02x\n",
-			   __func__, irlmp_event[event], self->slsap_sel);
+		pr_debug("%s(), Unknown event %s on LSAP %#02x\n",
+			 __func__, irlmp_event[event], self->slsap_sel);
 		break;
 	}
 	return ret;
@@ -793,8 +774,6 @@ static int irlmp_state_setup(struct lsap_cb *self, IRLMP_EVENT event,
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return -1;);
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	switch (event) {
 	case LM_CONNECT_CONFIRM:
 		irlmp_next_lsap_state(self, LSAP_DATA_TRANSFER_READY);
@@ -814,7 +793,7 @@ static int irlmp_state_setup(struct lsap_cb *self, IRLMP_EVENT event,
 		reason = skb->data[3];
 
 		 /* Try to close the LAP connection */
-		IRDA_DEBUG(4, "%s(), trying to close IrLAP\n",  __func__);
+		pr_debug("%s(), trying to close IrLAP\n",  __func__);
 		irlmp_do_lap_event(self->lap, LM_LAP_DISCONNECT_REQUEST, NULL);
 
 		irlmp_disconnect_indication(self, reason, skb);
@@ -832,7 +811,7 @@ static int irlmp_state_setup(struct lsap_cb *self, IRLMP_EVENT event,
 		irlmp_disconnect_indication(self, reason, skb);
 		break;
 	case LM_WATCHDOG_TIMEOUT:
-		IRDA_DEBUG(0, "%s() WATCHDOG_TIMEOUT!\n", __func__);
+		pr_debug("%s() WATCHDOG_TIMEOUT!\n", __func__);
 
 		IRDA_ASSERT(self->lap != NULL, return -1;);
 		irlmp_do_lap_event(self->lap, LM_LAP_DISCONNECT_REQUEST, NULL);
@@ -841,8 +820,8 @@ static int irlmp_state_setup(struct lsap_cb *self, IRLMP_EVENT event,
 		irlmp_disconnect_indication(self, LM_CONNECT_FAILURE, NULL);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), Unknown event %s on LSAP %#02x\n",
-			   __func__, irlmp_event[event], self->slsap_sel);
+		pr_debug("%s(), Unknown event %s on LSAP %#02x\n",
+			 __func__, irlmp_event[event], self->slsap_sel);
 		break;
 	}
 	return ret;
@@ -863,8 +842,6 @@ static int irlmp_state_setup_pend(struct lsap_cb *self, IRLMP_EVENT event,
 	LM_REASON reason;
 	int ret = 0;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(irlmp != NULL, return -1;);
 
@@ -883,7 +860,7 @@ static int irlmp_state_setup_pend(struct lsap_cb *self, IRLMP_EVENT event,
 		irlmp_next_lsap_state(self, LSAP_SETUP);
 		break;
 	case LM_WATCHDOG_TIMEOUT:
-		IRDA_DEBUG(0, "%s() : WATCHDOG_TIMEOUT !\n",  __func__);
+		pr_debug("%s() : WATCHDOG_TIMEOUT !\n",  __func__);
 
 		IRDA_ASSERT(self->lap != NULL, return -1;);
 		irlmp_do_lap_event(self->lap, LM_LAP_DISCONNECT_REQUEST, NULL);
@@ -901,8 +878,8 @@ static int irlmp_state_setup_pend(struct lsap_cb *self, IRLMP_EVENT event,
 		irlmp_disconnect_indication(self, reason, NULL);
 		break;
 	default:
-		IRDA_DEBUG(0, "%s(), Unknown event %s on LSAP %#02x\n",
-			   __func__, irlmp_event[event], self->slsap_sel);
+		pr_debug("%s(), Unknown event %s on LSAP %#02x\n",
+			 __func__, irlmp_event[event], self->slsap_sel);
 		break;
 	}
 	return ret;
diff --git a/net/irda/irlmp_frame.c b/net/irda/irlmp_frame.c
index 062e63b1c5c4..38b0f994bc7b 100644
--- a/net/irda/irlmp_frame.c
+++ b/net/irda/irlmp_frame.c
@@ -44,7 +44,7 @@ inline void irlmp_send_data_pdu(struct lap_cb *self, __u8 dlsap, __u8 slsap,
 	skb->data[1] = slsap;
 
 	if (expedited) {
-		IRDA_DEBUG(4, "%s(), sending expedited data\n", __func__);
+		pr_debug("%s(), sending expedited data\n", __func__);
 		irlap_data_request(self->irlap, skb, TRUE);
 	} else
 		irlap_data_request(self->irlap, skb, FALSE);
@@ -60,8 +60,6 @@ void irlmp_send_lcf_pdu(struct lap_cb *self, __u8 dlsap, __u8 slsap,
 {
 	__u8 *frame;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LMP_LAP_MAGIC, return;);
 	IRDA_ASSERT(skb != NULL, return;);
@@ -95,8 +93,6 @@ void irlmp_link_data_indication(struct lap_cb *self, struct sk_buff *skb,
 	__u8   dlsap_sel;   /* Destination LSAP address */
 	__u8   *fp;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LMP_LAP_MAGIC, return;);
 	IRDA_ASSERT(skb->len > 2, return;);
@@ -115,9 +111,8 @@ void irlmp_link_data_indication(struct lap_cb *self, struct sk_buff *skb,
 	 *  it in a different way than other established connections.
 	 */
 	if ((fp[0] & CONTROL_BIT) && (fp[2] == CONNECT_CMD)) {
-		IRDA_DEBUG(3, "%s(), incoming connection, "
-			   "source LSAP=%d, dest LSAP=%d\n",
-			   __func__, slsap_sel, dlsap_sel);
+		pr_debug("%s(), incoming connection, source LSAP=%d, dest LSAP=%d\n",
+			 __func__, slsap_sel, dlsap_sel);
 
 		/* Try to find LSAP among the unconnected LSAPs */
 		lsap = irlmp_find_lsap(self, dlsap_sel, slsap_sel, CONNECT_CMD,
@@ -125,7 +120,8 @@ void irlmp_link_data_indication(struct lap_cb *self, struct sk_buff *skb,
 
 		/* Maybe LSAP was already connected, so try one more time */
 		if (!lsap) {
-			IRDA_DEBUG(1, "%s(), incoming connection for LSAP already connected\n", __func__);
+			pr_debug("%s(), incoming connection for LSAP already connected\n",
+				 __func__);
 			lsap = irlmp_find_lsap(self, dlsap_sel, slsap_sel, 0,
 					       self->lsaps);
 		}
@@ -134,14 +130,14 @@ void irlmp_link_data_indication(struct lap_cb *self, struct sk_buff *skb,
 				       self->lsaps);
 
 	if (lsap == NULL) {
-		IRDA_DEBUG(2, "IrLMP, Sorry, no LSAP for received frame!\n");
-		IRDA_DEBUG(2, "%s(), slsap_sel = %02x, dlsap_sel = %02x\n",
-			   __func__, slsap_sel, dlsap_sel);
+		pr_debug("IrLMP, Sorry, no LSAP for received frame!\n");
+		pr_debug("%s(), slsap_sel = %02x, dlsap_sel = %02x\n",
+			 __func__, slsap_sel, dlsap_sel);
 		if (fp[0] & CONTROL_BIT) {
-			IRDA_DEBUG(2, "%s(), received control frame %02x\n",
-				   __func__, fp[2]);
+			pr_debug("%s(), received control frame %02x\n",
+				 __func__, fp[2]);
 		} else {
-			IRDA_DEBUG(2, "%s(), received data frame\n", __func__);
+			pr_debug("%s(), received data frame\n", __func__);
 		}
 		return;
 	}
@@ -159,20 +155,20 @@ void irlmp_link_data_indication(struct lap_cb *self, struct sk_buff *skb,
 			irlmp_do_lsap_event(lsap, LM_CONNECT_CONFIRM, skb);
 			break;
 		case DISCONNECT:
-			IRDA_DEBUG(4, "%s(), Disconnect indication!\n",
-				   __func__);
+			pr_debug("%s(), Disconnect indication!\n",
+				 __func__);
 			irlmp_do_lsap_event(lsap, LM_DISCONNECT_INDICATION,
 					    skb);
 			break;
 		case ACCESSMODE_CMD:
-			IRDA_DEBUG(0, "Access mode cmd not implemented!\n");
+			pr_debug("Access mode cmd not implemented!\n");
 			break;
 		case ACCESSMODE_CNF:
-			IRDA_DEBUG(0, "Access mode cnf not implemented!\n");
+			pr_debug("Access mode cnf not implemented!\n");
 			break;
 		default:
-			IRDA_DEBUG(0, "%s(), Unknown control frame %02x\n",
-				   __func__, fp[2]);
+			pr_debug("%s(), Unknown control frame %02x\n",
+				 __func__, fp[2]);
 			break;
 		}
 	} else if (unreliable) {
@@ -206,8 +202,6 @@ void irlmp_link_unitdata_indication(struct lap_cb *self, struct sk_buff *skb)
 	__u8   *fp;
 	unsigned long flags;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LMP_LAP_MAGIC, return;);
 	IRDA_ASSERT(skb->len > 2, return;);
@@ -223,14 +217,14 @@ void irlmp_link_unitdata_indication(struct lap_cb *self, struct sk_buff *skb)
 	pid       = fp[2];
 
 	if (pid & 0x80) {
-		IRDA_DEBUG(0, "%s(), extension in PID not supp!\n",
-			   __func__);
+		pr_debug("%s(), extension in PID not supp!\n",
+			 __func__);
 		return;
 	}
 
 	/* Check if frame is addressed to the connectionless LSAP */
 	if ((slsap_sel != LSAP_CONNLESS) || (dlsap_sel != LSAP_CONNLESS)) {
-		IRDA_DEBUG(0, "%s(), dropping frame!\n", __func__);
+		pr_debug("%s(), dropping frame!\n", __func__);
 		return;
 	}
 
@@ -254,7 +248,7 @@ void irlmp_link_unitdata_indication(struct lap_cb *self, struct sk_buff *skb)
 	if (lsap)
 		irlmp_connless_data_indication(lsap, skb);
 	else {
-		IRDA_DEBUG(0, "%s(), found no matching LSAP!\n", __func__);
+		pr_debug("%s(), found no matching LSAP!\n", __func__);
 	}
 }
 #endif /* CONFIG_IRDA_ULTRA */
@@ -270,8 +264,6 @@ void irlmp_link_disconnect_indication(struct lap_cb *lap,
 				      LAP_REASON reason,
 				      struct sk_buff *skb)
 {
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	IRDA_ASSERT(lap != NULL, return;);
 	IRDA_ASSERT(lap->magic == LMP_LAP_MAGIC, return;);
 
@@ -296,8 +288,6 @@ void irlmp_link_connect_indication(struct lap_cb *self, __u32 saddr,
 				   __u32 daddr, struct qos_info *qos,
 				   struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	/* Copy QoS settings for this session */
 	self->qos = qos;
 
@@ -317,8 +307,6 @@ void irlmp_link_connect_indication(struct lap_cb *self, __u32 saddr,
 void irlmp_link_connect_confirm(struct lap_cb *self, struct qos_info *qos,
 				struct sk_buff *skb)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LMP_LAP_MAGIC, return;);
 	IRDA_ASSERT(qos != NULL, return;);
@@ -383,8 +371,6 @@ void irlmp_link_discovery_indication(struct lap_cb *self,
  */
 void irlmp_link_discovery_confirm(struct lap_cb *self, hashbin_t *log)
 {
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LMP_LAP_MAGIC, return;);
 
diff --git a/net/irda/irmod.c b/net/irda/irmod.c
index 303a68d92731..c5e35b85c477 100644
--- a/net/irda/irmod.c
+++ b/net/irda/irmod.c
@@ -42,16 +42,6 @@
 #include <net/irda/irttp.h>		/* irttp_init */
 #include <net/irda/irda_device.h>	/* irda_device_init */
 
-/*
- * Module parameters
- */
-#ifdef CONFIG_IRDA_DEBUG
-unsigned int irda_debug = IRDA_DEBUG_LEVEL;
-module_param_named(debug, irda_debug, uint, 0);
-MODULE_PARM_DESC(debug, "IRDA debugging level");
-EXPORT_SYMBOL(irda_debug);
-#endif
-
 /* Packet type handler.
  * Tell the kernel how IrDA packets should be handled.
  */
@@ -90,8 +80,6 @@ static int __init irda_init(void)
 {
 	int ret = 0;
 
-	IRDA_DEBUG(0, "%s()\n", __func__);
-
 	/* Lower layer of the stack */
 	irlmp_init();
 	irlap_init();
diff --git a/net/irda/irnet/irnet_ppp.c b/net/irda/irnet/irnet_ppp.c
index 3c83a1e5ab03..1215693fdd22 100644
--- a/net/irda/irnet/irnet_ppp.c
+++ b/net/irda/irnet/irnet_ppp.c
@@ -305,7 +305,7 @@ irnet_ctrl_read(irnet_socket *	ap,
 
   /* Put ourselves on the wait queue to be woken up */
   add_wait_queue(&irnet_events.rwait, &wait);
-  current->state = TASK_INTERRUPTIBLE;
+  set_current_state(TASK_INTERRUPTIBLE);
   for(;;)
     {
       /* If there is unread events */
@@ -321,7 +321,7 @@ irnet_ctrl_read(irnet_socket *	ap,
       /* Yield and wait to be woken up */
       schedule();
     }
-  current->state = TASK_RUNNING;
+  __set_current_state(TASK_RUNNING);
   remove_wait_queue(&irnet_events.rwait, &wait);
 
   /* Did we got it ? */
diff --git a/net/irda/irnetlink.c b/net/irda/irnetlink.c
index a37b81fe0479..e15c40e86660 100644
--- a/net/irda/irnetlink.c
+++ b/net/irda/irnetlink.c
@@ -41,7 +41,7 @@ static struct net_device * ifname_to_netdev(struct net *net, struct genl_info *i
 
 	ifname = nla_data(info->attrs[IRDA_NL_ATTR_IFNAME]);
 
-	IRDA_DEBUG(5, "%s(): Looking for %s\n", __func__, ifname);
+	pr_debug("%s(): Looking for %s\n", __func__, ifname);
 
 	return dev_get_by_name(net, ifname);
 }
@@ -57,7 +57,7 @@ static int irda_nl_set_mode(struct sk_buff *skb, struct genl_info *info)
 
 	mode = nla_get_u32(info->attrs[IRDA_NL_ATTR_MODE]);
 
-	IRDA_DEBUG(5, "%s(): Switching to mode: %d\n", __func__, mode);
+	pr_debug("%s(): Switching to mode: %d\n", __func__, mode);
 
 	dev = ifname_to_netdev(&init_net, info);
 	if (!dev)
diff --git a/net/irda/irqueue.c b/net/irda/irqueue.c
index 7152624ed5f1..acbe61c7e683 100644
--- a/net/irda/irqueue.c
+++ b/net/irda/irqueue.c
@@ -233,8 +233,6 @@ static __u32 hash( const char* name)
 static void enqueue_first(irda_queue_t **queue, irda_queue_t* element)
 {
 
-	IRDA_DEBUG( 4, "%s()\n", __func__);
-
 	/*
 	 * Check if queue is empty.
 	 */
@@ -267,7 +265,7 @@ static irda_queue_t *dequeue_first(irda_queue_t **queue)
 {
 	irda_queue_t *ret;
 
-	IRDA_DEBUG( 4, "dequeue_first()\n");
+	pr_debug("dequeue_first()\n");
 
 	/*
 	 * Set return value
@@ -308,7 +306,7 @@ static irda_queue_t *dequeue_general(irda_queue_t **queue, irda_queue_t* element
 {
 	irda_queue_t *ret;
 
-	IRDA_DEBUG( 4, "dequeue_general()\n");
+	pr_debug("dequeue_general()\n");
 
 	/*
 	 * Set return value
@@ -452,8 +450,6 @@ void hashbin_insert(hashbin_t* hashbin, irda_queue_t* entry, long hashv,
 	unsigned long flags = 0;
 	int bin;
 
-	IRDA_DEBUG( 4, "%s()\n", __func__);
-
 	IRDA_ASSERT( hashbin != NULL, return;);
 	IRDA_ASSERT( hashbin->magic == HB_MAGIC, return;);
 
@@ -565,8 +561,6 @@ void* hashbin_remove( hashbin_t* hashbin, long hashv, const char* name)
 	unsigned long flags = 0;
 	irda_queue_t* entry;
 
-	IRDA_DEBUG( 4, "%s()\n", __func__);
-
 	IRDA_ASSERT( hashbin != NULL, return NULL;);
 	IRDA_ASSERT( hashbin->magic == HB_MAGIC, return NULL;);
 
@@ -658,8 +652,6 @@ void* hashbin_remove_this( hashbin_t* hashbin, irda_queue_t* entry)
 	int	bin;
 	long	hashv;
 
-	IRDA_DEBUG( 4, "%s()\n", __func__);
-
 	IRDA_ASSERT( hashbin != NULL, return NULL;);
 	IRDA_ASSERT( hashbin->magic == HB_MAGIC, return NULL;);
 	IRDA_ASSERT( entry != NULL, return NULL;);
@@ -719,7 +711,7 @@ void* hashbin_find( hashbin_t* hashbin, long hashv, const char* name )
 	int bin;
 	irda_queue_t* entry;
 
-	IRDA_DEBUG( 4, "hashbin_find()\n");
+	pr_debug("hashbin_find()\n");
 
 	IRDA_ASSERT( hashbin != NULL, return NULL;);
 	IRDA_ASSERT( hashbin->magic == HB_MAGIC, return NULL;);
diff --git a/net/irda/irsysctl.c b/net/irda/irsysctl.c
index d6a59651767a..873da5e7d428 100644
--- a/net/irda/irsysctl.c
+++ b/net/irda/irsysctl.c
@@ -126,15 +126,6 @@ static struct ctl_table irda_table[] = {
 		.mode		= 0644,
 		.proc_handler	= do_devname,
 	},
-#ifdef CONFIG_IRDA_DEBUG
-	{
-		.procname	= "debug",
-		.data		= &irda_debug,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-#endif
 #ifdef CONFIG_IRDA_FAST_RR
 	{
 		.procname	= "fast_poll_increase",
diff --git a/net/irda/irttp.c b/net/irda/irttp.c
index 85372cfa7b9f..b6ab41d5b3a3 100644
--- a/net/irda/irttp.c
+++ b/net/irda/irttp.c
@@ -71,11 +71,13 @@ static void irttp_status_indication(void *instance,
 				    LINK_STATUS link, LOCK_STATUS lock);
 
 /* Information for parsing parameters in IrTTP */
-static pi_minor_info_t pi_minor_call_table[] = {
+static const pi_minor_info_t pi_minor_call_table[] = {
 	{ NULL, 0 },                                             /* 0x00 */
 	{ irttp_param_max_sdu_size, PV_INTEGER | PV_BIG_ENDIAN } /* 0x01 */
 };
-static pi_major_info_t pi_major_call_table[] = { { pi_minor_call_table, 2 } };
+static const pi_major_info_t pi_major_call_table[] = {
+	{ pi_minor_call_table, 2 }
+};
 static pi_param_info_t param_info = { pi_major_call_table, 1, 0x0f, 4 };
 
 /************************ GLOBAL PROCEDURES ************************/
@@ -96,8 +98,8 @@ int __init irttp_init(void)
 
 	irttp->tsaps = hashbin_new(HB_LOCK);
 	if (!irttp->tsaps) {
-		IRDA_ERROR("%s: can't allocate IrTTP hashbin!\n",
-			   __func__);
+		net_err_ratelimited("%s: can't allocate IrTTP hashbin!\n",
+				    __func__);
 		kfree(irttp);
 		return -ENOMEM;
 	}
@@ -166,7 +168,7 @@ static void irttp_todo_expired(unsigned long data)
 	if (!self || self->magic != TTP_TSAP_MAGIC)
 		return;
 
-	IRDA_DEBUG(4, "%s(instance=%p)\n", __func__, self);
+	pr_debug("%s(instance=%p)\n", __func__, self);
 
 	/* Try to make some progress, especially on Tx side - Jean II */
 	irttp_run_rx_queue(self);
@@ -207,8 +209,6 @@ static void irttp_flush_queues(struct tsap_cb *self)
 {
 	struct sk_buff *skb;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return;);
 
@@ -240,8 +240,8 @@ static struct sk_buff *irttp_reassemble_skb(struct tsap_cb *self)
 	IRDA_ASSERT(self != NULL, return NULL;);
 	IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return NULL;);
 
-	IRDA_DEBUG(2, "%s(), self->rx_sdu_size=%d\n", __func__,
-		   self->rx_sdu_size);
+	pr_debug("%s(), self->rx_sdu_size=%d\n", __func__,
+		 self->rx_sdu_size);
 
 	skb = dev_alloc_skb(TTP_HEADER + self->rx_sdu_size);
 	if (!skb)
@@ -264,9 +264,8 @@ static struct sk_buff *irttp_reassemble_skb(struct tsap_cb *self)
 		dev_kfree_skb(frag);
 	}
 
-	IRDA_DEBUG(2,
-		   "%s(), frame len=%d, rx_sdu_size=%d, rx_max_sdu_size=%d\n",
-		   __func__, n, self->rx_sdu_size, self->rx_max_sdu_size);
+	pr_debug("%s(), frame len=%d, rx_sdu_size=%d, rx_max_sdu_size=%d\n",
+		 __func__, n, self->rx_sdu_size, self->rx_max_sdu_size);
 	/* Note : irttp_run_rx_queue() calculate self->rx_sdu_size
 	 * by summing the size of all fragments, so we should always
 	 * have n == self->rx_sdu_size, except in cases where we
@@ -295,8 +294,6 @@ static inline void irttp_fragment_skb(struct tsap_cb *self,
 	struct sk_buff *frag;
 	__u8 *frame;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return;);
 	IRDA_ASSERT(skb != NULL, return;);
@@ -305,7 +302,7 @@ static inline void irttp_fragment_skb(struct tsap_cb *self,
 	 *  Split frame into a number of segments
 	 */
 	while (skb->len > self->max_seg_size) {
-		IRDA_DEBUG(2, "%s(), fragmenting ...\n", __func__);
+		pr_debug("%s(), fragmenting ...\n", __func__);
 
 		/* Make new segment */
 		frag = alloc_skb(self->max_seg_size+self->max_header_size,
@@ -330,7 +327,7 @@ static inline void irttp_fragment_skb(struct tsap_cb *self,
 		skb_queue_tail(&self->tx_queue, frag);
 	}
 	/* Queue what is left of the original skb */
-	IRDA_DEBUG(2, "%s(), queuing last segment\n", __func__);
+	pr_debug("%s(), queuing last segment\n", __func__);
 
 	frame = skb_push(skb, TTP_HEADER);
 	frame[0] = 0x00; /* Clear more bit */
@@ -361,7 +358,7 @@ static int irttp_param_max_sdu_size(void *instance, irda_param_t *param,
 	else
 		self->tx_max_sdu_size = param->pv.i;
 
-	IRDA_DEBUG(1, "%s(), MaxSduSize=%d\n", __func__, param->pv.i);
+	pr_debug("%s(), MaxSduSize=%d\n", __func__, param->pv.i);
 
 	return 0;
 }
@@ -402,15 +399,13 @@ struct tsap_cb *irttp_open_tsap(__u8 stsap_sel, int credit, notify_t *notify)
 	 * JeanII */
 	if ((stsap_sel != LSAP_ANY) &&
 	   ((stsap_sel < 0x01) || (stsap_sel >= 0x70))) {
-		IRDA_DEBUG(0, "%s(), invalid tsap!\n", __func__);
+		pr_debug("%s(), invalid tsap!\n", __func__);
 		return NULL;
 	}
 
 	self = kzalloc(sizeof(struct tsap_cb), GFP_ATOMIC);
-	if (self == NULL) {
-		IRDA_DEBUG(0, "%s(), unable to kmalloc!\n", __func__);
+	if (self == NULL)
 		return NULL;
-	}
 
 	/* Initialize internal objects */
 	irttp_init_tsap(self);
@@ -440,7 +435,7 @@ struct tsap_cb *irttp_open_tsap(__u8 stsap_sel, int credit, notify_t *notify)
 	 */
 	lsap = irlmp_open_lsap(stsap_sel, &ttp_notify, 0);
 	if (lsap == NULL) {
-		IRDA_DEBUG(0, "%s: unable to allocate LSAP!!\n", __func__);
+		pr_debug("%s: unable to allocate LSAP!!\n", __func__);
 		__irttp_close_tsap(self);
 		return NULL;
 	}
@@ -451,7 +446,7 @@ struct tsap_cb *irttp_open_tsap(__u8 stsap_sel, int credit, notify_t *notify)
 	 *  the stsap_sel we have might not be valid anymore
 	 */
 	self->stsap_sel = lsap->slsap_sel;
-	IRDA_DEBUG(4, "%s(), stsap_sel=%02x\n", __func__, self->stsap_sel);
+	pr_debug("%s(), stsap_sel=%02x\n", __func__, self->stsap_sel);
 
 	self->notify = *notify;
 	self->lsap = lsap;
@@ -509,8 +504,6 @@ int irttp_close_tsap(struct tsap_cb *self)
 {
 	struct tsap_cb *tsap;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return -1;);
 
@@ -518,8 +511,8 @@ int irttp_close_tsap(struct tsap_cb *self)
 	if (self->connected) {
 		/* Check if disconnect is not pending */
 		if (!test_bit(0, &self->disconnect_pend)) {
-			IRDA_WARNING("%s: TSAP still connected!\n",
-				     __func__);
+			net_warn_ratelimited("%s: TSAP still connected!\n",
+					     __func__);
 			irttp_disconnect_request(self, NULL, P_NORMAL);
 		}
 		self->close_pend = TRUE;
@@ -558,8 +551,6 @@ int irttp_udata_request(struct tsap_cb *self, struct sk_buff *skb)
 	IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return -1;);
 	IRDA_ASSERT(skb != NULL, return -1;);
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	/* Take shortcut on zero byte packets */
 	if (skb->len == 0) {
 		ret = 0;
@@ -568,13 +559,14 @@ int irttp_udata_request(struct tsap_cb *self, struct sk_buff *skb)
 
 	/* Check that nothing bad happens */
 	if (!self->connected) {
-		IRDA_WARNING("%s(), Not connected\n", __func__);
+		net_warn_ratelimited("%s(), Not connected\n", __func__);
 		ret = -ENOTCONN;
 		goto err;
 	}
 
 	if (skb->len > self->max_seg_size) {
-		IRDA_ERROR("%s(), UData is too large for IrLAP!\n", __func__);
+		net_err_ratelimited("%s(), UData is too large for IrLAP!\n",
+				    __func__);
 		ret = -EMSGSIZE;
 		goto err;
 	}
@@ -606,8 +598,8 @@ int irttp_data_request(struct tsap_cb *self, struct sk_buff *skb)
 	IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return -1;);
 	IRDA_ASSERT(skb != NULL, return -1;);
 
-	IRDA_DEBUG(2, "%s() : queue len = %d\n", __func__,
-		   skb_queue_len(&self->tx_queue));
+	pr_debug("%s() : queue len = %d\n", __func__,
+		 skb_queue_len(&self->tx_queue));
 
 	/* Take shortcut on zero byte packets */
 	if (skb->len == 0) {
@@ -617,7 +609,7 @@ int irttp_data_request(struct tsap_cb *self, struct sk_buff *skb)
 
 	/* Check that nothing bad happens */
 	if (!self->connected) {
-		IRDA_WARNING("%s: Not connected\n", __func__);
+		net_warn_ratelimited("%s: Not connected\n", __func__);
 		ret = -ENOTCONN;
 		goto err;
 	}
@@ -627,8 +619,8 @@ int irttp_data_request(struct tsap_cb *self, struct sk_buff *skb)
 	 *  inside an IrLAP frame
 	 */
 	if ((self->tx_max_sdu_size == 0) && (skb->len > self->max_seg_size)) {
-		IRDA_ERROR("%s: SAR disabled, and data is too large for IrLAP!\n",
-			   __func__);
+		net_err_ratelimited("%s: SAR disabled, and data is too large for IrLAP!\n",
+				    __func__);
 		ret = -EMSGSIZE;
 		goto err;
 	}
@@ -640,8 +632,8 @@ int irttp_data_request(struct tsap_cb *self, struct sk_buff *skb)
 	if ((self->tx_max_sdu_size != 0) &&
 	    (self->tx_max_sdu_size != TTP_SAR_UNBOUND) &&
 	    (skb->len > self->tx_max_sdu_size)) {
-		IRDA_ERROR("%s: SAR enabled, but data is larger than TxMaxSduSize!\n",
-			   __func__);
+		net_err_ratelimited("%s: SAR enabled, but data is larger than TxMaxSduSize!\n",
+				    __func__);
 		ret = -EMSGSIZE;
 		goto err;
 	}
@@ -719,9 +711,9 @@ static void irttp_run_tx_queue(struct tsap_cb *self)
 	unsigned long flags;
 	int n;
 
-	IRDA_DEBUG(2, "%s() : send_credit = %d, queue_len = %d\n",
-		   __func__,
-		   self->send_credit, skb_queue_len(&self->tx_queue));
+	pr_debug("%s() : send_credit = %d, queue_len = %d\n",
+		 __func__,
+		 self->send_credit, skb_queue_len(&self->tx_queue));
 
 	/* Get exclusive access to the tx queue, otherwise don't touch it */
 	if (irda_lock(&self->tx_queue_lock) == FALSE)
@@ -826,9 +818,9 @@ static inline void irttp_give_credit(struct tsap_cb *self)
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return;);
 
-	IRDA_DEBUG(4, "%s() send=%d,avail=%d,remote=%d\n",
-		   __func__,
-		   self->send_credit, self->avail_credit, self->remote_credit);
+	pr_debug("%s() send=%d,avail=%d,remote=%d\n",
+		 __func__,
+		 self->send_credit, self->avail_credit, self->remote_credit);
 
 	/* Give credit to peer */
 	tx_skb = alloc_skb(TTP_MAX_HEADER, GFP_ATOMIC);
@@ -876,8 +868,6 @@ static int irttp_udata_indication(void *instance, void *sap,
 	struct tsap_cb *self;
 	int err;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	self = instance;
 
 	IRDA_ASSERT(self != NULL, return -1;);
@@ -993,8 +983,6 @@ static void irttp_status_indication(void *instance,
 {
 	struct tsap_cb *self;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	self = instance;
 
 	IRDA_ASSERT(self != NULL, return;);
@@ -1011,7 +999,7 @@ static void irttp_status_indication(void *instance,
 		self->notify.status_indication(self->notify.instance,
 					       link, lock);
 	else
-		IRDA_DEBUG(2, "%s(), no handler\n", __func__);
+		pr_debug("%s(), no handler\n", __func__);
 }
 
 /*
@@ -1029,7 +1017,7 @@ static void irttp_flow_indication(void *instance, void *sap, LOCAL_FLOW flow)
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return;);
 
-	IRDA_DEBUG(4, "%s(instance=%p)\n", __func__, self);
+	pr_debug("%s(instance=%p)\n", __func__, self);
 
 	/* We are "polled" directly from LAP, and the LAP want to fill
 	 * its Tx window. We want to do our best to send it data, so that
@@ -1067,18 +1055,16 @@ static void irttp_flow_indication(void *instance, void *sap, LOCAL_FLOW flow)
  */
 void irttp_flow_request(struct tsap_cb *self, LOCAL_FLOW flow)
 {
-	IRDA_DEBUG(1, "%s()\n", __func__);
-
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return;);
 
 	switch (flow) {
 	case FLOW_STOP:
-		IRDA_DEBUG(1, "%s(), flow stop\n", __func__);
+		pr_debug("%s(), flow stop\n", __func__);
 		self->rx_sdu_busy = TRUE;
 		break;
 	case FLOW_START:
-		IRDA_DEBUG(1, "%s(), flow start\n", __func__);
+		pr_debug("%s(), flow start\n", __func__);
 		self->rx_sdu_busy = FALSE;
 
 		/* Client say he can accept more data, try to free our
@@ -1087,7 +1073,7 @@ void irttp_flow_request(struct tsap_cb *self, LOCAL_FLOW flow)
 
 		break;
 	default:
-		IRDA_DEBUG(1, "%s(), Unknown flow command!\n", __func__);
+		pr_debug("%s(), Unknown flow command!\n", __func__);
 	}
 }
 EXPORT_SYMBOL(irttp_flow_request);
@@ -1107,7 +1093,7 @@ int irttp_connect_request(struct tsap_cb *self, __u8 dtsap_sel,
 	__u8 *frame;
 	__u8 n;
 
-	IRDA_DEBUG(4, "%s(), max_sdu_size=%d\n", __func__, max_sdu_size);
+	pr_debug("%s(), max_sdu_size=%d\n", __func__, max_sdu_size);
 
 	IRDA_ASSERT(self != NULL, return -EBADR;);
 	IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return -EBADR;);
@@ -1205,8 +1191,6 @@ static void irttp_connect_confirm(void *instance, void *sap,
 	__u8 plen;
 	__u8 n;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	self = instance;
 
 	IRDA_ASSERT(self != NULL, return;);
@@ -1221,15 +1205,15 @@ static void irttp_connect_confirm(void *instance, void *sap,
 	 *  negotiated QoS for the link.
 	 */
 	if (qos) {
-		IRDA_DEBUG(4, "IrTTP, Negotiated BAUD_RATE: %02x\n",
-		       qos->baud_rate.bits);
-		IRDA_DEBUG(4, "IrTTP, Negotiated BAUD_RATE: %d bps.\n",
-		       qos->baud_rate.value);
+		pr_debug("IrTTP, Negotiated BAUD_RATE: %02x\n",
+			 qos->baud_rate.bits);
+		pr_debug("IrTTP, Negotiated BAUD_RATE: %d bps.\n",
+			 qos->baud_rate.value);
 	}
 
 	n = skb->data[0] & 0x7f;
 
-	IRDA_DEBUG(4, "%s(), Initial send_credit=%d\n", __func__, n);
+	pr_debug("%s(), Initial send_credit=%d\n", __func__, n);
 
 	self->send_credit = n;
 	self->tx_max_sdu_size = 0;
@@ -1249,8 +1233,8 @@ static void irttp_connect_confirm(void *instance, void *sap,
 
 		/* Any errors in the parameter list? */
 		if (ret < 0) {
-			IRDA_WARNING("%s: error extracting parameters\n",
-				     __func__);
+			net_warn_ratelimited("%s: error extracting parameters\n",
+					     __func__);
 			dev_kfree_skb(skb);
 
 			/* Do not accept this connection attempt */
@@ -1260,11 +1244,11 @@ static void irttp_connect_confirm(void *instance, void *sap,
 		skb_pull(skb, IRDA_MIN(skb->len, plen+1));
 	}
 
-	IRDA_DEBUG(4, "%s() send=%d,avail=%d,remote=%d\n", __func__,
-	      self->send_credit, self->avail_credit, self->remote_credit);
+	pr_debug("%s() send=%d,avail=%d,remote=%d\n", __func__,
+		 self->send_credit, self->avail_credit, self->remote_credit);
 
-	IRDA_DEBUG(2, "%s(), MaxSduSize=%d\n", __func__,
-		   self->tx_max_sdu_size);
+	pr_debug("%s(), MaxSduSize=%d\n", __func__,
+		 self->tx_max_sdu_size);
 
 	if (self->notify.connect_confirm) {
 		self->notify.connect_confirm(self->notify.instance, self, qos,
@@ -1302,7 +1286,7 @@ static void irttp_connect_indication(void *instance, void *sap,
 	self->max_seg_size = max_seg_size - TTP_HEADER;
 	self->max_header_size = max_header_size+TTP_HEADER;
 
-	IRDA_DEBUG(4, "%s(), TSAP sel=%02x\n", __func__, self->stsap_sel);
+	pr_debug("%s(), TSAP sel=%02x\n", __func__, self->stsap_sel);
 
 	/* Need to update dtsap_sel if its equal to LSAP_ANY */
 	self->dtsap_sel = lsap->dlsap_sel;
@@ -1326,8 +1310,8 @@ static void irttp_connect_indication(void *instance, void *sap,
 
 		/* Any errors in the parameter list? */
 		if (ret < 0) {
-			IRDA_WARNING("%s: error extracting parameters\n",
-				     __func__);
+			net_warn_ratelimited("%s: error extracting parameters\n",
+					     __func__);
 			dev_kfree_skb(skb);
 
 			/* Do not accept this connection attempt */
@@ -1364,8 +1348,8 @@ int irttp_connect_response(struct tsap_cb *self, __u32 max_sdu_size,
 	IRDA_ASSERT(self != NULL, return -1;);
 	IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return -1;);
 
-	IRDA_DEBUG(4, "%s(), Source TSAP selector=%02x\n", __func__,
-		   self->stsap_sel);
+	pr_debug("%s(), Source TSAP selector=%02x\n", __func__,
+		 self->stsap_sel);
 
 	/* Any userdata supplied? */
 	if (userdata == NULL) {
@@ -1446,14 +1430,12 @@ struct tsap_cb *irttp_dup(struct tsap_cb *orig, void *instance)
 	struct tsap_cb *new;
 	unsigned long flags;
 
-	IRDA_DEBUG(1, "%s()\n", __func__);
-
 	/* Protect our access to the old tsap instance */
 	spin_lock_irqsave(&irttp->tsaps->hb_spinlock, flags);
 
 	/* Find the old instance */
 	if (!hashbin_find(irttp->tsaps, (long) orig, NULL)) {
-		IRDA_DEBUG(0, "%s(), unable to find TSAP\n", __func__);
+		pr_debug("%s(), unable to find TSAP\n", __func__);
 		spin_unlock_irqrestore(&irttp->tsaps->hb_spinlock, flags);
 		return NULL;
 	}
@@ -1461,7 +1443,7 @@ struct tsap_cb *irttp_dup(struct tsap_cb *orig, void *instance)
 	/* Allocate a new instance */
 	new = kmemdup(orig, sizeof(struct tsap_cb), GFP_ATOMIC);
 	if (!new) {
-		IRDA_DEBUG(0, "%s(), unable to kmalloc\n", __func__);
+		pr_debug("%s(), unable to kmalloc\n", __func__);
 		spin_unlock_irqrestore(&irttp->tsaps->hb_spinlock, flags);
 		return NULL;
 	}
@@ -1473,7 +1455,7 @@ struct tsap_cb *irttp_dup(struct tsap_cb *orig, void *instance)
 	/* Try to dup the LSAP (may fail if we were too slow) */
 	new->lsap = irlmp_dup(orig->lsap, new);
 	if (!new->lsap) {
-		IRDA_DEBUG(0, "%s(), dup failed!\n", __func__);
+		pr_debug("%s(), dup failed!\n", __func__);
 		kfree(new);
 		return NULL;
 	}
@@ -1508,7 +1490,7 @@ int irttp_disconnect_request(struct tsap_cb *self, struct sk_buff *userdata,
 
 	/* Already disconnected? */
 	if (!self->connected) {
-		IRDA_DEBUG(4, "%s(), already disconnected!\n", __func__);
+		pr_debug("%s(), already disconnected!\n", __func__);
 		if (userdata)
 			dev_kfree_skb(userdata);
 		return -1;
@@ -1520,8 +1502,8 @@ int irttp_disconnect_request(struct tsap_cb *self, struct sk_buff *userdata,
 	 * for following a disconnect_indication() (i.e. net_bh).
 	 * Jean II */
 	if (test_and_set_bit(0, &self->disconnect_pend)) {
-		IRDA_DEBUG(0, "%s(), disconnect already pending\n",
-			   __func__);
+		pr_debug("%s(), disconnect already pending\n",
+			 __func__);
 		if (userdata)
 			dev_kfree_skb(userdata);
 
@@ -1540,7 +1522,7 @@ int irttp_disconnect_request(struct tsap_cb *self, struct sk_buff *userdata,
 			 *  disconnecting right now since the data will
 			 *  not have any usable connection to be sent on
 			 */
-			IRDA_DEBUG(1, "%s(): High priority!!()\n", __func__);
+			pr_debug("%s(): High priority!!()\n", __func__);
 			irttp_flush_queues(self);
 		} else if (priority == P_NORMAL) {
 			/*
@@ -1561,7 +1543,7 @@ int irttp_disconnect_request(struct tsap_cb *self, struct sk_buff *userdata,
 	 * be sent at the LMP level (so even if the peer has its Tx queue
 	 * full of data). - Jean II */
 
-	IRDA_DEBUG(1, "%s(), Disconnecting ...\n", __func__);
+	pr_debug("%s(), Disconnecting ...\n", __func__);
 	self->connected = FALSE;
 
 	if (!userdata) {
@@ -1597,8 +1579,6 @@ static void irttp_disconnect_indication(void *instance, void *sap,
 {
 	struct tsap_cb *self;
 
-	IRDA_DEBUG(4, "%s()\n", __func__);
-
 	self = instance;
 
 	IRDA_ASSERT(self != NULL, return;);
@@ -1657,7 +1637,7 @@ static void irttp_do_data_indication(struct tsap_cb *self, struct sk_buff *skb)
 	 * give an error back
 	 */
 	if (err) {
-		IRDA_DEBUG(0, "%s() requeueing skb!\n", __func__);
+		pr_debug("%s() requeueing skb!\n", __func__);
 
 		/* Make sure we take a break */
 		self->rx_sdu_busy = TRUE;
@@ -1682,8 +1662,8 @@ static void irttp_run_rx_queue(struct tsap_cb *self)
 	struct sk_buff *skb;
 	int more = 0;
 
-	IRDA_DEBUG(2, "%s() send=%d,avail=%d,remote=%d\n", __func__,
-		   self->send_credit, self->avail_credit, self->remote_credit);
+	pr_debug("%s() send=%d,avail=%d,remote=%d\n", __func__,
+		 self->send_credit, self->avail_credit, self->remote_credit);
 
 	/* Get exclusive access to the rx queue, otherwise don't touch it */
 	if (irda_lock(&self->rx_queue_lock) == FALSE)
@@ -1722,8 +1702,8 @@ static void irttp_run_rx_queue(struct tsap_cb *self)
 			 *  limits of the maximum size of the rx_sdu
 			 */
 			if (self->rx_sdu_size <= self->rx_max_sdu_size) {
-				IRDA_DEBUG(4, "%s(), queueing frag\n",
-					   __func__);
+				pr_debug("%s(), queueing frag\n",
+					 __func__);
 				skb_queue_tail(&self->rx_fragments, skb);
 			} else {
 				/* Free the part of the SDU that is too big */
@@ -1752,7 +1732,7 @@ static void irttp_run_rx_queue(struct tsap_cb *self)
 			/* Now we can deliver the reassembled skb */
 			irttp_do_data_indication(self, skb);
 		} else {
-			IRDA_DEBUG(1, "%s(), Truncated frame\n", __func__);
+			pr_debug("%s(), Truncated frame\n", __func__);
 
 			/* Free the part of the SDU that is too big */
 			dev_kfree_skb(skb);
diff --git a/net/irda/parameters.c b/net/irda/parameters.c
index 6d0869716bf6..16ce32ffe004 100644
--- a/net/irda/parameters.c
+++ b/net/irda/parameters.c
@@ -52,7 +52,7 @@ static int irda_insert_no_value(void *self, __u8 *buf, int len, __u8 pi,
 static int irda_param_unpack(__u8 *buf, char *fmt, ...);
 
 /* Parameter value call table. Must match PV_TYPE */
-static PV_HANDLER pv_extract_table[] = {
+static const PV_HANDLER pv_extract_table[] = {
 	irda_extract_integer, /* Handler for any length integers */
 	irda_extract_integer, /* Handler for 8  bits integers */
 	irda_extract_integer, /* Handler for 16 bits integers */
@@ -62,7 +62,7 @@ static PV_HANDLER pv_extract_table[] = {
 	irda_extract_no_value /* Handler for no value parameters */
 };
 
-static PV_HANDLER pv_insert_table[] = {
+static const PV_HANDLER pv_insert_table[] = {
 	irda_insert_integer, /* Handler for any length integers */
 	irda_insert_integer, /* Handler for 8  bits integers */
 	irda_insert_integer, /* Handler for 16 bits integers */
@@ -146,24 +146,24 @@ static int irda_insert_integer(void *self, __u8 *buf, int len, __u8 pi,
 	 */
 	if (p.pl == 0) {
 		if (p.pv.i < 0xff) {
-			IRDA_DEBUG(2, "%s(), using 1 byte\n", __func__);
+			pr_debug("%s(), using 1 byte\n", __func__);
 			p.pl = 1;
 		} else if (p.pv.i < 0xffff) {
-			IRDA_DEBUG(2, "%s(), using 2 bytes\n", __func__);
+			pr_debug("%s(), using 2 bytes\n", __func__);
 			p.pl = 2;
 		} else {
-			IRDA_DEBUG(2, "%s(), using 4 bytes\n", __func__);
+			pr_debug("%s(), using 4 bytes\n", __func__);
 			p.pl = 4; /* Default length */
 		}
 	}
 	/* Check if buffer is long enough for insertion */
 	if (len < (2+p.pl)) {
-		IRDA_WARNING("%s: buffer too short for insertion!\n",
-			     __func__);
+		net_warn_ratelimited("%s: buffer too short for insertion!\n",
+				     __func__);
 		return -1;
 	}
-	IRDA_DEBUG(2, "%s(), pi=%#x, pl=%d, pi=%d\n", __func__,
-		   p.pi, p.pl, p.pv.i);
+	pr_debug("%s(), pi=%#x, pl=%d, pi=%d\n", __func__,
+		 p.pi, p.pl, p.pv.i);
 	switch (p.pl) {
 	case 1:
 		n += irda_param_pack(buf, "bbb", p.pi, p.pl, (__u8) p.pv.i);
@@ -184,8 +184,8 @@ static int irda_insert_integer(void *self, __u8 *buf, int len, __u8 pi,
 
 		break;
 	default:
-		IRDA_WARNING("%s: length %d not supported\n",
-			     __func__, p.pl);
+		net_warn_ratelimited("%s: length %d not supported\n",
+				     __func__, p.pl);
 		/* Skip parameter */
 		return -1;
 	}
@@ -214,9 +214,8 @@ static int irda_extract_integer(void *self, __u8 *buf, int len, __u8 pi,
 
 	/* Check if buffer is long enough for parsing */
 	if (len < (2+p.pl)) {
-		IRDA_WARNING("%s: buffer too short for parsing! "
-			     "Need %d bytes, but len is only %d\n",
-			     __func__, p.pl, len);
+		net_warn_ratelimited("%s: buffer too short for parsing! Need %d bytes, but len is only %d\n",
+				     __func__, p.pl, len);
 		return -1;
 	}
 
@@ -226,9 +225,8 @@ static int irda_extract_integer(void *self, __u8 *buf, int len, __u8 pi,
 	 * PV_INTEGER means that the handler is flexible.
 	 */
 	if (((type & PV_MASK) != PV_INTEGER) && ((type & PV_MASK) != p.pl)) {
-		IRDA_ERROR("%s: invalid parameter length! "
-			   "Expected %d bytes, but value had %d bytes!\n",
-			   __func__, type & PV_MASK, p.pl);
+		net_err_ratelimited("%s: invalid parameter length! Expected %d bytes, but value had %d bytes!\n",
+				    __func__, type & PV_MASK, p.pl);
 
 		/* Most parameters are bit/byte fields or little endian,
 		 * so it's ok to only extract a subset of it (the subset
@@ -265,15 +263,15 @@ static int irda_extract_integer(void *self, __u8 *buf, int len, __u8 pi,
 			le32_to_cpus(&p.pv.i);
 		break;
 	default:
-		IRDA_WARNING("%s: length %d not supported\n",
-			     __func__, p.pl);
+		net_warn_ratelimited("%s: length %d not supported\n",
+				     __func__, p.pl);
 
 		/* Skip parameter */
 		return p.pl+2;
 	}
 
-	IRDA_DEBUG(2, "%s(), pi=%#x, pl=%d, pi=%d\n", __func__,
-		   p.pi, p.pl, p.pv.i);
+	pr_debug("%s(), pi=%#x, pl=%d, pi=%d\n", __func__,
+		 p.pi, p.pl, p.pv.i);
 	/* Call handler for this parameter */
 	err = (*func)(self, &p, PV_PUT);
 	if (err < 0)
@@ -292,21 +290,18 @@ static int irda_extract_string(void *self, __u8 *buf, int len, __u8 pi,
 	irda_param_t p;
 	int err;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	p.pi = pi;     /* In case handler needs to know */
 	p.pl = buf[1]; /* Extract length of value */
 	if (p.pl > 32)
 		p.pl = 32;
 
-	IRDA_DEBUG(2, "%s(), pi=%#x, pl=%d\n", __func__,
-		   p.pi, p.pl);
+	pr_debug("%s(), pi=%#x, pl=%d\n", __func__,
+		 p.pi, p.pl);
 
 	/* Check if buffer is long enough for parsing */
 	if (len < (2+p.pl)) {
-		IRDA_WARNING("%s: buffer too short for parsing! "
-			     "Need %d bytes, but len is only %d\n",
-			     __func__, p.pl, len);
+		net_warn_ratelimited("%s: buffer too short for parsing! Need %d bytes, but len is only %d\n",
+				     __func__, p.pl, len);
 		return -1;
 	}
 
@@ -314,8 +309,8 @@ static int irda_extract_string(void *self, __u8 *buf, int len, __u8 pi,
 	 * checked that the buffer is long enough */
 	strncpy(str, buf+2, p.pl);
 
-	IRDA_DEBUG(2, "%s(), str=0x%02x 0x%02x\n", __func__,
-		   (__u8) str[0], (__u8) str[1]);
+	pr_debug("%s(), str=0x%02x 0x%02x\n",
+		 __func__, (__u8)str[0], (__u8)str[1]);
 
 	/* Null terminate string */
 	str[p.pl] = '\0';
@@ -343,13 +338,12 @@ static int irda_extract_octseq(void *self, __u8 *buf, int len, __u8 pi,
 
 	/* Check if buffer is long enough for parsing */
 	if (len < (2+p.pl)) {
-		IRDA_WARNING("%s: buffer too short for parsing! "
-			     "Need %d bytes, but len is only %d\n",
-			     __func__, p.pl, len);
+		net_warn_ratelimited("%s: buffer too short for parsing! Need %d bytes, but len is only %d\n",
+				     __func__, p.pl, len);
 		return -1;
 	}
 
-	IRDA_DEBUG(0, "%s(), not impl\n", __func__);
+	pr_debug("%s(), not impl\n", __func__);
 
 	return p.pl+2; /* Extracted pl+2 bytes */
 }
@@ -455,7 +449,7 @@ static int irda_param_unpack(__u8 *buf, char *fmt, ...)
 int irda_param_insert(void *self, __u8 pi, __u8 *buf, int len,
 		      pi_param_info_t *info)
 {
-	pi_minor_info_t *pi_minor_info;
+	const pi_minor_info_t *pi_minor_info;
 	__u8 pi_minor;
 	__u8 pi_major;
 	int type;
@@ -472,8 +466,8 @@ int irda_param_insert(void *self, __u8 pi, __u8 *buf, int len,
 	if ((pi_major > info->len-1) ||
 	    (pi_minor > info->tables[pi_major].len-1))
 	{
-		IRDA_DEBUG(0, "%s(), no handler for parameter=0x%02x\n",
-			   __func__, pi);
+		pr_debug("%s(), no handler for parameter=0x%02x\n",
+			 __func__, pi);
 
 		/* Skip this parameter */
 		return -1;
@@ -487,7 +481,8 @@ int irda_param_insert(void *self, __u8 pi, __u8 *buf, int len,
 
 	/*  Check if handler has been implemented */
 	if (!pi_minor_info->func) {
-		IRDA_MESSAGE("%s: no handler for pi=%#x\n", __func__, pi);
+		net_info_ratelimited("%s: no handler for pi=%#x\n",
+				     __func__, pi);
 		/* Skip this parameter */
 		return -1;
 	}
@@ -509,7 +504,7 @@ EXPORT_SYMBOL(irda_param_insert);
 static int irda_param_extract(void *self, __u8 *buf, int len,
 			      pi_param_info_t *info)
 {
-	pi_minor_info_t *pi_minor_info;
+	const pi_minor_info_t *pi_minor_info;
 	__u8 pi_minor;
 	__u8 pi_major;
 	int type;
@@ -526,8 +521,8 @@ static int irda_param_extract(void *self, __u8 *buf, int len,
 	if ((pi_major > info->len-1) ||
 	    (pi_minor > info->tables[pi_major].len-1))
 	{
-		IRDA_DEBUG(0, "%s(), no handler for parameter=0x%02x\n",
-			   __func__, buf[0]);
+		pr_debug("%s(), no handler for parameter=0x%02x\n",
+			 __func__, buf[0]);
 
 		/* Skip this parameter */
 		return 2 + buf[n + 1];  /* Continue */
@@ -539,13 +534,13 @@ static int irda_param_extract(void *self, __u8 *buf, int len,
 	/* Find expected data type for this parameter identifier (pi)*/
 	type = pi_minor_info->type;
 
-	IRDA_DEBUG(3, "%s(), pi=[%d,%d], type=%d\n", __func__,
-		   pi_major, pi_minor, type);
+	pr_debug("%s(), pi=[%d,%d], type=%d\n", __func__,
+		 pi_major, pi_minor, type);
 
 	/*  Check if handler has been implemented */
 	if (!pi_minor_info->func) {
-		IRDA_MESSAGE("%s: no handler for pi=%#x\n",
-			     __func__, buf[n]);
+		net_info_ratelimited("%s: no handler for pi=%#x\n",
+				     __func__, buf[n]);
 		/* Skip this parameter */
 		return 2 + buf[n + 1]; /* Continue */
 	}
diff --git a/net/irda/qos.c b/net/irda/qos.c
index 11a7cc0cbc28..25ba8509ad3e 100644
--- a/net/irda/qos.c
+++ b/net/irda/qos.c
@@ -122,7 +122,7 @@ static __u32 max_line_capacities[10][4] = {
 	{ 800000, 400000, 160000, 80000 }, /* 16000000 bps */
 };
 
-static pi_minor_info_t pi_minor_call_table_type_0[] = {
+static const pi_minor_info_t pi_minor_call_table_type_0[] = {
 	{ NULL, 0 },
 /* 01 */{ irlap_param_baud_rate,       PV_INTEGER | PV_LITTLE_ENDIAN },
 	{ NULL, 0 },
@@ -134,7 +134,7 @@ static pi_minor_info_t pi_minor_call_table_type_0[] = {
 /* 08 */{ irlap_param_link_disconnect, PV_INT_8_BITS }
 };
 
-static pi_minor_info_t pi_minor_call_table_type_1[] = {
+static const pi_minor_info_t pi_minor_call_table_type_1[] = {
 	{ NULL, 0 },
 	{ NULL, 0 },
 /* 82 */{ irlap_param_max_turn_time,   PV_INT_8_BITS },
@@ -144,7 +144,7 @@ static pi_minor_info_t pi_minor_call_table_type_1[] = {
 /* 86 */{ irlap_param_min_turn_time,   PV_INT_8_BITS },
 };
 
-static pi_major_info_t pi_major_call_table[] = {
+static const pi_major_info_t pi_major_call_table[] = {
 	{ pi_minor_call_table_type_0, 9 },
 	{ pi_minor_call_table_type_1, 7 },
 };
@@ -200,8 +200,8 @@ static int msb_index (__u16 word)
 	 * able to check precisely what's going on. If a end user sees this,
 	 * it's very likely the peer. - Jean II */
 	if (word == 0) {
-		IRDA_WARNING("%s(), Detected buggy peer, adjust null PV to 0x1!\n",
-			 __func__);
+		net_warn_ratelimited("%s(), Detected buggy peer, adjust null PV to 0x1!\n",
+				     __func__);
 		/* The only safe choice (we don't know the array size) */
 		word = 0x1;
 	}
@@ -342,8 +342,6 @@ static void irlap_adjust_qos_settings(struct qos_info *qos)
 	__u32 line_capacity;
 	int index;
 
-	IRDA_DEBUG(2, "%s()\n", __func__);
-
 	/*
 	 * Make sure the mintt is sensible.
 	 * Main culprit : Ericsson T39. - Jean II
@@ -351,8 +349,8 @@ static void irlap_adjust_qos_settings(struct qos_info *qos)
 	if (sysctl_min_tx_turn_time > qos->min_turn_time.value) {
 		int i;
 
-		IRDA_WARNING("%s(), Detected buggy peer, adjust mtt to %dus!\n",
-			 __func__, sysctl_min_tx_turn_time);
+		net_warn_ratelimited("%s(), Detected buggy peer, adjust mtt to %dus!\n",
+				     __func__, sysctl_min_tx_turn_time);
 
 		/* We don't really need bits, but easier this way */
 		i = value_highest_bit(sysctl_min_tx_turn_time, min_turn_times,
@@ -368,9 +366,8 @@ static void irlap_adjust_qos_settings(struct qos_info *qos)
 	if ((qos->baud_rate.value < 115200) &&
 	    (qos->max_turn_time.value < 500))
 	{
-		IRDA_DEBUG(0,
-			   "%s(), adjusting max turn time from %d to 500 ms\n",
-			   __func__, qos->max_turn_time.value);
+		pr_debug("%s(), adjusting max turn time from %d to 500 ms\n",
+			 __func__, qos->max_turn_time.value);
 		qos->max_turn_time.value = 500;
 	}
 
@@ -385,8 +382,8 @@ static void irlap_adjust_qos_settings(struct qos_info *qos)
 #ifdef CONFIG_IRDA_DYNAMIC_WINDOW
 	while ((qos->data_size.value > line_capacity) && (index > 0)) {
 		qos->data_size.value = data_sizes[index--];
-		IRDA_DEBUG(2, "%s(), reducing data size to %d\n",
-			   __func__, qos->data_size.value);
+		pr_debug("%s(), reducing data size to %d\n",
+			 __func__, qos->data_size.value);
 	}
 #else /* Use method described in section 6.6.11 of IrLAP */
 	while (irlap_requested_line_capacity(qos) > line_capacity) {
@@ -395,15 +392,15 @@ static void irlap_adjust_qos_settings(struct qos_info *qos)
 		/* Must be able to send at least one frame */
 		if (qos->window_size.value > 1) {
 			qos->window_size.value--;
-			IRDA_DEBUG(2, "%s(), reducing window size to %d\n",
-				   __func__, qos->window_size.value);
+			pr_debug("%s(), reducing window size to %d\n",
+				 __func__, qos->window_size.value);
 		} else if (index > 1) {
 			qos->data_size.value = data_sizes[index--];
-			IRDA_DEBUG(2, "%s(), reducing data size to %d\n",
-				   __func__, qos->data_size.value);
+			pr_debug("%s(), reducing data size to %d\n",
+				 __func__, qos->data_size.value);
 		} else {
-			IRDA_WARNING("%s(), nothing more we can do!\n",
-				     __func__);
+			net_warn_ratelimited("%s(), nothing more we can do!\n",
+					     __func__);
 		}
 	}
 #endif /* CONFIG_IRDA_DYNAMIC_WINDOW */
@@ -440,20 +437,20 @@ int irlap_qos_negotiate(struct irlap_cb *self, struct sk_buff *skb)
 
 	irlap_adjust_qos_settings(&self->qos_tx);
 
-	IRDA_DEBUG(2, "Setting BAUD_RATE to %d bps.\n",
-		   self->qos_tx.baud_rate.value);
-	IRDA_DEBUG(2, "Setting DATA_SIZE to %d bytes\n",
-		   self->qos_tx.data_size.value);
-	IRDA_DEBUG(2, "Setting WINDOW_SIZE to %d\n",
-		   self->qos_tx.window_size.value);
-	IRDA_DEBUG(2, "Setting XBOFS to %d\n",
-		   self->qos_tx.additional_bofs.value);
-	IRDA_DEBUG(2, "Setting MAX_TURN_TIME to %d ms.\n",
-		   self->qos_tx.max_turn_time.value);
-	IRDA_DEBUG(2, "Setting MIN_TURN_TIME to %d usecs.\n",
-		   self->qos_tx.min_turn_time.value);
-	IRDA_DEBUG(2, "Setting LINK_DISC to %d secs.\n",
-		   self->qos_tx.link_disc_time.value);
+	pr_debug("Setting BAUD_RATE to %d bps.\n",
+		 self->qos_tx.baud_rate.value);
+	pr_debug("Setting DATA_SIZE to %d bytes\n",
+		 self->qos_tx.data_size.value);
+	pr_debug("Setting WINDOW_SIZE to %d\n",
+		 self->qos_tx.window_size.value);
+	pr_debug("Setting XBOFS to %d\n",
+		 self->qos_tx.additional_bofs.value);
+	pr_debug("Setting MAX_TURN_TIME to %d ms.\n",
+		 self->qos_tx.max_turn_time.value);
+	pr_debug("Setting MIN_TURN_TIME to %d usecs.\n",
+		 self->qos_tx.min_turn_time.value);
+	pr_debug("Setting LINK_DISC to %d secs.\n",
+		 self->qos_tx.link_disc_time.value);
 	return ret;
 }
 
@@ -537,17 +534,17 @@ static int irlap_param_baud_rate(void *instance, irda_param_t *param, int get)
 
 	if (get) {
 		param->pv.i = self->qos_rx.baud_rate.bits;
-		IRDA_DEBUG(2, "%s(), baud rate = 0x%02x\n",
-			   __func__, param->pv.i);
+		pr_debug("%s(), baud rate = 0x%02x\n",
+			 __func__, param->pv.i);
 	} else {
 		/*
 		 *  Stations must agree on baud rate, so calculate
 		 *  intersection
 		 */
-		IRDA_DEBUG(2, "Requested BAUD_RATE: 0x%04x\n", (__u16) param->pv.i);
+		pr_debug("Requested BAUD_RATE: 0x%04x\n", (__u16)param->pv.i);
 		final = (__u16) param->pv.i & self->qos_rx.baud_rate.bits;
 
-		IRDA_DEBUG(2, "Final BAUD_RATE: 0x%04x\n", final);
+		pr_debug("Final BAUD_RATE: 0x%04x\n", final);
 		self->qos_tx.baud_rate.bits = final;
 		self->qos_rx.baud_rate.bits = final;
 	}
@@ -578,10 +575,10 @@ static int irlap_param_link_disconnect(void *instance, irda_param_t *param,
 		 *  Stations must agree on link disconnect/threshold
 		 *  time.
 		 */
-		IRDA_DEBUG(2, "LINK_DISC: %02x\n", (__u8) param->pv.i);
+		pr_debug("LINK_DISC: %02x\n", (__u8)param->pv.i);
 		final = (__u8) param->pv.i & self->qos_rx.link_disc_time.bits;
 
-		IRDA_DEBUG(2, "Final LINK_DISC: %02x\n", final);
+		pr_debug("Final LINK_DISC: %02x\n", final);
 		self->qos_tx.link_disc_time.bits = final;
 		self->qos_rx.link_disc_time.bits = final;
 	}
@@ -710,8 +707,8 @@ __u32 irlap_max_line_capacity(__u32 speed, __u32 max_turn_time)
 	__u32 line_capacity;
 	int i,j;
 
-	IRDA_DEBUG(2, "%s(), speed=%d, max_turn_time=%d\n",
-		   __func__, speed, max_turn_time);
+	pr_debug("%s(), speed=%d, max_turn_time=%d\n",
+		 __func__, speed, max_turn_time);
 
 	i = value_index(speed, baud_rates, 10);
 	j = value_index(max_turn_time, max_turn_times, 4);
@@ -721,8 +718,8 @@ __u32 irlap_max_line_capacity(__u32 speed, __u32 max_turn_time)
 
 	line_capacity = max_line_capacities[i][j];
 
-	IRDA_DEBUG(2, "%s(), line capacity=%d bytes\n",
-		   __func__, line_capacity);
+	pr_debug("%s(), line capacity=%d bytes\n",
+		 __func__, line_capacity);
 
 	return line_capacity;
 }
@@ -737,8 +734,8 @@ static __u32 irlap_requested_line_capacity(struct qos_info *qos)
 		irlap_min_turn_time_in_bytes(qos->baud_rate.value,
 					     qos->min_turn_time.value);
 
-	IRDA_DEBUG(2, "%s(), requested line capacity=%d\n",
-		   __func__, line_capacity);
+	pr_debug("%s(), requested line capacity=%d\n",
+		 __func__, line_capacity);
 
 	return line_capacity;
 }
diff --git a/net/irda/wrapper.c b/net/irda/wrapper.c
index fd0995b1323a..40a0f993bf13 100644
--- a/net/irda/wrapper.c
+++ b/net/irda/wrapper.c
@@ -106,17 +106,17 @@ int async_wrap_skb(struct sk_buff *skb, __u8 *tx_buff, int buffsize)
 		 * Nothing to worry about, but we set the default number of
 		 * BOF's
 		 */
-		IRDA_DEBUG(1, "%s(), wrong magic in skb!\n", __func__);
+		pr_debug("%s(), wrong magic in skb!\n", __func__);
 		xbofs = 10;
 	} else
 		xbofs = cb->xbofs + cb->xbofs_delay;
 
-	IRDA_DEBUG(4, "%s(), xbofs=%d\n", __func__, xbofs);
+	pr_debug("%s(), xbofs=%d\n", __func__, xbofs);
 
 	/* Check that we never use more than 115 + 48 xbofs */
 	if (xbofs > 163) {
-		IRDA_DEBUG(0, "%s(), too many xbofs (%d)\n", __func__,
-			   xbofs);
+		pr_debug("%s(), too many xbofs (%d)\n", __func__,
+			 xbofs);
 		xbofs = 163;
 	}
 
@@ -134,8 +134,8 @@ int async_wrap_skb(struct sk_buff *skb, __u8 *tx_buff, int buffsize)
 		 *  transmitted after this point is 5.
 		 */
 		if(n >= (buffsize-5)) {
-			IRDA_ERROR("%s(), tx buffer overflow (n=%d)\n",
-				   __func__, n);
+			net_err_ratelimited("%s(), tx buffer overflow (n=%d)\n",
+					    __func__, n);
 			return n;
 		}
 
@@ -286,8 +286,8 @@ async_unwrap_bof(struct net_device *dev,
 	case INSIDE_FRAME:
 		/* Not supposed to happen, the previous frame is not
 		 * finished - Jean II */
-		IRDA_DEBUG(1, "%s(), Discarding incomplete frame\n",
-			   __func__);
+		pr_debug("%s(), Discarding incomplete frame\n",
+			 __func__);
 		stats->rx_errors++;
 		stats->rx_missed_errors++;
 		irda_device_set_media_busy(dev, TRUE);
@@ -360,7 +360,7 @@ async_unwrap_eof(struct net_device *dev,
 			/* Wrong CRC, discard frame!  */
 			irda_device_set_media_busy(dev, TRUE);
 
-			IRDA_DEBUG(1, "%s(), crc error\n", __func__);
+			pr_debug("%s(), crc error\n", __func__);
 			stats->rx_errors++;
 			stats->rx_crc_errors++;
 		}
@@ -386,7 +386,7 @@ async_unwrap_ce(struct net_device *dev,
 		break;
 
 	case LINK_ESCAPE:
-		IRDA_WARNING("%s: state not defined\n", __func__);
+		net_warn_ratelimited("%s: state not defined\n", __func__);
 		break;
 
 	case BEGIN_FRAME:
@@ -420,8 +420,8 @@ async_unwrap_other(struct net_device *dev,
 			rx_buff->fcs = irda_fcs(rx_buff->fcs, byte);
 #endif
 		} else {
-			IRDA_DEBUG(1, "%s(), Rx buffer overflow, aborting\n",
-				   __func__);
+			pr_debug("%s(), Rx buffer overflow, aborting\n",
+				 __func__);
 			rx_buff->state = OUTSIDE_FRAME;
 		}
 		break;
@@ -439,8 +439,8 @@ async_unwrap_other(struct net_device *dev,
 #endif
 			rx_buff->state = INSIDE_FRAME;
 		} else {
-			IRDA_DEBUG(1, "%s(), Rx buffer overflow, aborting\n",
-				   __func__);
+			pr_debug("%s(), Rx buffer overflow, aborting\n",
+				 __func__);
 			rx_buff->state = OUTSIDE_FRAME;
 		}
 		break;
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index a089b6b91650..6daa52a18d40 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1026,8 +1026,8 @@ static int iucv_send_iprm(struct iucv_path *path, struct iucv_message *msg,
 				 (void *) prmdata, 8);
 }
 
-static int iucv_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
-			     struct msghdr *msg, size_t len)
+static int iucv_sock_sendmsg(struct socket *sock, struct msghdr *msg,
+			     size_t len)
 {
 	struct sock *sk = sock->sk;
 	struct iucv_sock *iucv = iucv_sk(sk);
@@ -1070,9 +1070,7 @@ static int iucv_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 	txmsg.class = 0;
 
 	/* iterate over control messages */
-	for (cmsg = CMSG_FIRSTHDR(msg); cmsg;
-		cmsg = CMSG_NXTHDR(msg, cmsg)) {
-
+	for_each_cmsghdr(cmsg, msg) {
 		if (!CMSG_OK(msg, cmsg)) {
 			err = -EINVAL;
 			goto out;
@@ -1116,13 +1114,11 @@ static int iucv_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 			noblock, &err);
 	else
 		skb = sock_alloc_send_skb(sk, len, noblock, &err);
-	if (!skb) {
-		err = -ENOMEM;
+	if (!skb)
 		goto out;
-	}
 	if (iucv->transport == AF_IUCV_TRANS_HIPER)
 		skb_reserve(skb, sizeof(struct af_iucv_trans_hdr) + ETH_HLEN);
-	if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) {
+	if (memcpy_from_msg(skb_put(skb, len), msg, len)) {
 		err = -EFAULT;
 		goto fail;
 	}
@@ -1319,8 +1315,8 @@ static void iucv_process_message_q(struct sock *sk)
 	}
 }
 
-static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
-			     struct msghdr *msg, size_t len, int flags)
+static int iucv_sock_recvmsg(struct socket *sock, struct msghdr *msg,
+			     size_t len, int flags)
 {
 	int noblock = flags & MSG_DONTWAIT;
 	struct sock *sk = sock->sk;
@@ -1355,7 +1351,7 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 		sk->sk_shutdown = sk->sk_shutdown | RCV_SHUTDOWN;
 
 	cskb = skb;
-	if (skb_copy_datagram_iovec(cskb, offset, msg->msg_iov, copied)) {
+	if (skb_copy_datagram_msg(cskb, offset, msg, copied)) {
 		if (!(flags & MSG_PEEK))
 			skb_queue_head(&sk->sk_receive_queue, skb);
 		return -EFAULT;
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 1847ec4e3930..3c5b8ce38ef4 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -709,7 +709,7 @@ static unsigned int pfkey_sockaddr_fill(const xfrm_address_t *xaddr, __be16 port
 		sin6->sin6_family = AF_INET6;
 		sin6->sin6_port = port;
 		sin6->sin6_flowinfo = 0;
-		sin6->sin6_addr = *(struct in6_addr *)xaddr->a6;
+		sin6->sin6_addr = xaddr->in6;
 		sin6->sin6_scope_id = 0;
 		return 128;
 	    }
@@ -1190,6 +1190,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net,
 				memcpy(x->ealg->alg_key, key+1, keysize);
 			}
 			x->props.ealgo = sa->sadb_sa_encrypt;
+			x->geniv = a->uinfo.encr.geniv;
 		}
 	}
 	/* x->algo.flags = sa->sadb_sa_flags; */
@@ -3588,8 +3589,7 @@ static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 }
 #endif
 
-static int pfkey_sendmsg(struct kiocb *kiocb,
-			 struct socket *sock, struct msghdr *msg, size_t len)
+static int pfkey_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 {
 	struct sock *sk = sock->sk;
 	struct sk_buff *skb = NULL;
@@ -3611,7 +3611,7 @@ static int pfkey_sendmsg(struct kiocb *kiocb,
 		goto out;
 
 	err = -EFAULT;
-	if (memcpy_fromiovec(skb_put(skb,len), msg->msg_iov, len))
+	if (memcpy_from_msg(skb_put(skb,len), msg, len))
 		goto out;
 
 	hdr = pfkey_get_base_msg(skb, &err);
@@ -3630,8 +3630,7 @@ out:
 	return err ? : len;
 }
 
-static int pfkey_recvmsg(struct kiocb *kiocb,
-			 struct socket *sock, struct msghdr *msg, size_t len,
+static int pfkey_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 			 int flags)
 {
 	struct sock *sk = sock->sk;
@@ -3654,7 +3653,7 @@ static int pfkey_recvmsg(struct kiocb *kiocb,
 	}
 
 	skb_reset_transport_header(skb);
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (err)
 		goto out_free;
 
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 895348e44c7d..a29a504492af 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1871,6 +1871,7 @@ static int __init l2tp_init(void)
 	l2tp_wq = alloc_workqueue("l2tp", WQ_UNBOUND, 0);
 	if (!l2tp_wq) {
 		pr_err("alloc_workqueue failed\n");
+		unregister_pernet_device(&l2tp_net_ops);
 		rc = -ENOMEM;
 		goto out;
 	}
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index edb78e69efe4..4b552873b556 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -74,7 +74,7 @@ static int l2tp_eth_dev_init(struct net_device *dev)
 
 	priv->dev = dev;
 	eth_hw_addr_random(dev);
-	memset(&dev->broadcast[0], 0xff, 6);
+	eth_broadcast_addr(dev->broadcast);
 	dev->qdisc_tx_busylock = &l2tp_eth_tx_busylock;
 	return 0;
 }
@@ -126,6 +126,7 @@ static struct net_device_ops l2tp_eth_netdev_ops = {
 	.ndo_uninit		= l2tp_eth_dev_uninit,
 	.ndo_start_xmit		= l2tp_eth_dev_xmit,
 	.ndo_get_stats64	= l2tp_eth_get_stats64,
+	.ndo_set_mac_address	= eth_mac_addr,
 };
 
 static void l2tp_eth_dev_setup(struct net_device *dev)
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 369a9822488c..79649937ec71 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -385,7 +385,7 @@ drop:
 /* Userspace will call sendmsg() on the tunnel socket to send L2TP
  * control frames.
  */
-static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len)
+static int l2tp_ip_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 {
 	struct sk_buff *skb;
 	int rc;
@@ -441,7 +441,7 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
 	*((__be32 *) skb_put(skb, 4)) = 0;
 
 	/* Copy user data into skb */
-	rc = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
+	rc = memcpy_from_msg(skb_put(skb, len), msg, len);
 	if (rc < 0) {
 		kfree_skb(skb);
 		goto error;
@@ -506,7 +506,7 @@ no_route:
 	goto out;
 }
 
-static int l2tp_ip_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
+static int l2tp_ip_recvmsg(struct sock *sk, struct msghdr *msg,
 			   size_t len, int noblock, int flags, int *addr_len)
 {
 	struct inet_sock *inet = inet_sk(sk);
@@ -528,7 +528,7 @@ static int l2tp_ip_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
 		copied = len;
 	}
 
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (err)
 		goto done;
 
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 0edb263cc002..d1ded3777815 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -480,8 +480,7 @@ out:
 /* Userspace will call sendmsg() on the tunnel socket to send L2TP
  * control frames.
  */
-static int l2tp_ip6_sendmsg(struct kiocb *iocb, struct sock *sk,
-			    struct msghdr *msg, size_t len)
+static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 {
 	struct ipv6_txoptions opt_space;
 	DECLARE_SOCKADDR(struct sockaddr_l2tpip6 *, lsa, msg->msg_name);
@@ -619,7 +618,7 @@ static int l2tp_ip6_sendmsg(struct kiocb *iocb, struct sock *sk,
 
 back_from_confirm:
 	lock_sock(sk);
-	err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov,
+	err = ip6_append_data(sk, ip_generic_getfrag, msg,
 			      ulen, transhdrlen, hlimit, tclass, opt,
 			      &fl6, (struct rt6_info *)dst,
 			      msg->msg_flags, dontfrag);
@@ -643,9 +642,8 @@ do_confirm:
 	goto done;
 }
 
-static int l2tp_ip6_recvmsg(struct kiocb *iocb, struct sock *sk,
-			    struct msghdr *msg, size_t len, int noblock,
-			    int flags, int *addr_len)
+static int l2tp_ip6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+			    int noblock, int flags, int *addr_len)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	DECLARE_SOCKADDR(struct sockaddr_l2tpip6 *, lsa, msg->msg_name);
@@ -672,7 +670,7 @@ static int l2tp_ip6_recvmsg(struct kiocb *iocb, struct sock *sk,
 		copied = len;
 	}
 
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (err)
 		goto done;
 
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 0ac907adb2f4..9e13c2ff8789 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -40,6 +40,18 @@ static struct genl_family l2tp_nl_family = {
 	.netnsok	= true,
 };
 
+static const struct genl_multicast_group l2tp_multicast_group[] = {
+	{
+		.name = L2TP_GENL_MCGROUP,
+	},
+};
+
+static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq,
+			       int flags, struct l2tp_tunnel *tunnel, u8 cmd);
+static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq,
+				int flags, struct l2tp_session *session,
+				u8 cmd);
+
 /* Accessed under genl lock */
 static const struct l2tp_nl_cmd_ops *l2tp_nl_cmd_ops[__L2TP_PWTYPE_MAX];
 
@@ -97,6 +109,52 @@ out:
 	return ret;
 }
 
+static int l2tp_tunnel_notify(struct genl_family *family,
+			      struct genl_info *info,
+			      struct l2tp_tunnel *tunnel,
+			      u8 cmd)
+{
+	struct sk_buff *msg;
+	int ret;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	ret = l2tp_nl_tunnel_send(msg, info->snd_portid, info->snd_seq,
+				  NLM_F_ACK, tunnel, cmd);
+
+	if (ret >= 0)
+		return genlmsg_multicast_allns(family, msg, 0,	0, GFP_ATOMIC);
+
+	nlmsg_free(msg);
+
+	return ret;
+}
+
+static int l2tp_session_notify(struct genl_family *family,
+			       struct genl_info *info,
+			       struct l2tp_session *session,
+			       u8 cmd)
+{
+	struct sk_buff *msg;
+	int ret;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	ret = l2tp_nl_session_send(msg, info->snd_portid, info->snd_seq,
+				   NLM_F_ACK, session, cmd);
+
+	if (ret >= 0)
+		return genlmsg_multicast_allns(family, msg, 0,	0, GFP_ATOMIC);
+
+	nlmsg_free(msg);
+
+	return ret;
+}
+
 static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info)
 {
 	u32 tunnel_id;
@@ -147,9 +205,9 @@ static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info
 #endif
 		if (info->attrs[L2TP_ATTR_IP_SADDR] &&
 		    info->attrs[L2TP_ATTR_IP_DADDR]) {
-			cfg.local_ip.s_addr = nla_get_be32(
+			cfg.local_ip.s_addr = nla_get_in_addr(
 				info->attrs[L2TP_ATTR_IP_SADDR]);
-			cfg.peer_ip.s_addr = nla_get_be32(
+			cfg.peer_ip.s_addr = nla_get_in_addr(
 				info->attrs[L2TP_ATTR_IP_DADDR]);
 		} else {
 			ret = -EINVAL;
@@ -188,6 +246,9 @@ static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info
 		break;
 	}
 
+	if (ret >= 0)
+		ret = l2tp_tunnel_notify(&l2tp_nl_family, info,
+					 tunnel, L2TP_CMD_TUNNEL_CREATE);
 out:
 	return ret;
 }
@@ -211,6 +272,9 @@ static int l2tp_nl_cmd_tunnel_delete(struct sk_buff *skb, struct genl_info *info
 		goto out;
 	}
 
+	l2tp_tunnel_notify(&l2tp_nl_family, info,
+			   tunnel, L2TP_CMD_TUNNEL_DELETE);
+
 	(void) l2tp_tunnel_delete(tunnel);
 
 out:
@@ -239,12 +303,15 @@ static int l2tp_nl_cmd_tunnel_modify(struct sk_buff *skb, struct genl_info *info
 	if (info->attrs[L2TP_ATTR_DEBUG])
 		tunnel->debug = nla_get_u32(info->attrs[L2TP_ATTR_DEBUG]);
 
+	ret = l2tp_tunnel_notify(&l2tp_nl_family, info,
+				 tunnel, L2TP_CMD_TUNNEL_MODIFY);
+
 out:
 	return ret;
 }
 
 static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int flags,
-			       struct l2tp_tunnel *tunnel)
+			       struct l2tp_tunnel *tunnel, u8 cmd)
 {
 	void *hdr;
 	struct nlattr *nest;
@@ -254,8 +321,7 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla
 	struct ipv6_pinfo *np = NULL;
 #endif
 
-	hdr = genlmsg_put(skb, portid, seq, &l2tp_nl_family, flags,
-			  L2TP_CMD_TUNNEL_GET);
+	hdr = genlmsg_put(skb, portid, seq, &l2tp_nl_family, flags, cmd);
 	if (!hdr)
 		return -EMSGSIZE;
 
@@ -310,21 +376,24 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla
 	case L2TP_ENCAPTYPE_IP:
 #if IS_ENABLED(CONFIG_IPV6)
 		if (np) {
-			if (nla_put(skb, L2TP_ATTR_IP6_SADDR, sizeof(np->saddr),
-				    &np->saddr) ||
-			    nla_put(skb, L2TP_ATTR_IP6_DADDR, sizeof(sk->sk_v6_daddr),
-				    &sk->sk_v6_daddr))
+			if (nla_put_in6_addr(skb, L2TP_ATTR_IP6_SADDR,
+					     &np->saddr) ||
+			    nla_put_in6_addr(skb, L2TP_ATTR_IP6_DADDR,
+					     &sk->sk_v6_daddr))
 				goto nla_put_failure;
 		} else
 #endif
-		if (nla_put_be32(skb, L2TP_ATTR_IP_SADDR, inet->inet_saddr) ||
-		    nla_put_be32(skb, L2TP_ATTR_IP_DADDR, inet->inet_daddr))
+		if (nla_put_in_addr(skb, L2TP_ATTR_IP_SADDR,
+				    inet->inet_saddr) ||
+		    nla_put_in_addr(skb, L2TP_ATTR_IP_DADDR,
+				    inet->inet_daddr))
 			goto nla_put_failure;
 		break;
 	}
 
 out:
-	return genlmsg_end(skb, hdr);
+	genlmsg_end(skb, hdr);
+	return 0;
 
 nla_put_failure:
 	genlmsg_cancel(skb, hdr);
@@ -359,7 +428,7 @@ static int l2tp_nl_cmd_tunnel_get(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	ret = l2tp_nl_tunnel_send(msg, info->snd_portid, info->snd_seq,
-				  NLM_F_ACK, tunnel);
+				  NLM_F_ACK, tunnel, L2TP_CMD_TUNNEL_GET);
 	if (ret < 0)
 		goto err_out;
 
@@ -385,7 +454,7 @@ static int l2tp_nl_cmd_tunnel_dump(struct sk_buff *skb, struct netlink_callback
 
 		if (l2tp_nl_tunnel_send(skb, NETLINK_CB(cb->skb).portid,
 					cb->nlh->nlmsg_seq, NLM_F_MULTI,
-					tunnel) <= 0)
+					tunnel, L2TP_CMD_TUNNEL_GET) < 0)
 			goto out;
 
 		ti++;
@@ -539,6 +608,13 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf
 		ret = (*l2tp_nl_cmd_ops[cfg.pw_type]->session_create)(net, tunnel_id,
 			session_id, peer_session_id, &cfg);
 
+	if (ret >= 0) {
+		session = l2tp_session_find(net, tunnel, session_id);
+		if (session)
+			ret = l2tp_session_notify(&l2tp_nl_family, info, session,
+						  L2TP_CMD_SESSION_CREATE);
+	}
+
 out:
 	return ret;
 }
@@ -555,6 +631,9 @@ static int l2tp_nl_cmd_session_delete(struct sk_buff *skb, struct genl_info *inf
 		goto out;
 	}
 
+	l2tp_session_notify(&l2tp_nl_family, info,
+			    session, L2TP_CMD_SESSION_DELETE);
+
 	pw_type = session->pwtype;
 	if (pw_type < __L2TP_PWTYPE_MAX)
 		if (l2tp_nl_cmd_ops[pw_type] && l2tp_nl_cmd_ops[pw_type]->session_delete)
@@ -601,12 +680,15 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf
 	if (info->attrs[L2TP_ATTR_MRU])
 		session->mru = nla_get_u16(info->attrs[L2TP_ATTR_MRU]);
 
+	ret = l2tp_session_notify(&l2tp_nl_family, info,
+				  session, L2TP_CMD_SESSION_MODIFY);
+
 out:
 	return ret;
 }
 
 static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int flags,
-				struct l2tp_session *session)
+				struct l2tp_session *session, u8 cmd)
 {
 	void *hdr;
 	struct nlattr *nest;
@@ -615,7 +697,7 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl
 
 	sk = tunnel->sock;
 
-	hdr = genlmsg_put(skb, portid, seq, &l2tp_nl_family, flags, L2TP_CMD_SESSION_GET);
+	hdr = genlmsg_put(skb, portid, seq, &l2tp_nl_family, flags, cmd);
 	if (!hdr)
 		return -EMSGSIZE;
 
@@ -673,7 +755,8 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl
 		goto nla_put_failure;
 	nla_nest_end(skb, nest);
 
-	return genlmsg_end(skb, hdr);
+	genlmsg_end(skb, hdr);
+	return 0;
 
  nla_put_failure:
 	genlmsg_cancel(skb, hdr);
@@ -699,7 +782,7 @@ static int l2tp_nl_cmd_session_get(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	ret = l2tp_nl_session_send(msg, info->snd_portid, info->snd_seq,
-				   0, session);
+				   0, session, L2TP_CMD_SESSION_GET);
 	if (ret < 0)
 		goto err_out;
 
@@ -737,7 +820,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback
 
 		if (l2tp_nl_session_send(skb, NETLINK_CB(cb->skb).portid,
 					 cb->nlh->nlmsg_seq, NLM_F_MULTI,
-					 session) <= 0)
+					 session, L2TP_CMD_SESSION_GET) < 0)
 			break;
 
 		si++;
@@ -896,7 +979,9 @@ EXPORT_SYMBOL_GPL(l2tp_nl_unregister_ops);
 static int l2tp_nl_init(void)
 {
 	pr_info("L2TP netlink interface\n");
-	return genl_register_family_with_ops(&l2tp_nl_family, l2tp_nl_ops);
+	return genl_register_family_with_ops_groups(&l2tp_nl_family,
+						    l2tp_nl_ops,
+						    l2tp_multicast_group);
 }
 
 static void l2tp_nl_cleanup(void)
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index b704a9356208..e9b0dec56b8e 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -185,9 +185,8 @@ static int pppol2tp_recv_payload_hook(struct sk_buff *skb)
 
 /* Receive message. This is the recvmsg for the PPPoL2TP socket.
  */
-static int pppol2tp_recvmsg(struct kiocb *iocb, struct socket *sock,
-			    struct msghdr *msg, size_t len,
-			    int flags)
+static int pppol2tp_recvmsg(struct socket *sock, struct msghdr *msg,
+			    size_t len, int flags)
 {
 	int err;
 	struct sk_buff *skb;
@@ -208,7 +207,7 @@ static int pppol2tp_recvmsg(struct kiocb *iocb, struct socket *sock,
 	else if (len < skb->len)
 		msg->msg_flags |= MSG_TRUNC;
 
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, len);
+	err = skb_copy_datagram_msg(skb, 0, msg, len);
 	if (likely(err == 0))
 		err = len;
 
@@ -295,7 +294,7 @@ static void pppol2tp_session_sock_put(struct l2tp_session *session)
  * when a user application does a sendmsg() on the session socket. L2TP and
  * PPP headers must be inserted into the user's data.
  */
-static int pppol2tp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m,
+static int pppol2tp_sendmsg(struct socket *sock, struct msghdr *m,
 			    size_t total_len)
 {
 	static const unsigned char ppph[2] = { 0xff, 0x03 };
@@ -346,8 +345,7 @@ static int pppol2tp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msgh
 	skb_put(skb, 2);
 
 	/* Copy user data into skb */
-	error = memcpy_fromiovec(skb_put(skb, total_len), m->msg_iov,
-				 total_len);
+	error = memcpy_from_msg(skb_put(skb, total_len), m, total_len);
 	if (error < 0) {
 		kfree_skb(skb);
 		goto error_put_sess_tun;
diff --git a/net/lapb/lapb_iface.c b/net/lapb/lapb_iface.c
index 3cdaa046c1bc..fc60d9d738b5 100644
--- a/net/lapb/lapb_iface.c
+++ b/net/lapb/lapb_iface.c
@@ -73,6 +73,7 @@ static void __lapb_remove_cb(struct lapb_cb *lapb)
 		lapb_put(lapb);
 	}
 }
+EXPORT_SYMBOL(lapb_register);
 
 /*
  *	Add a socket to the bound sockets list.
@@ -195,6 +196,7 @@ out:
 	write_unlock_bh(&lapb_list_lock);
 	return rc;
 }
+EXPORT_SYMBOL(lapb_unregister);
 
 int lapb_getparms(struct net_device *dev, struct lapb_parms_struct *parms)
 {
@@ -227,6 +229,7 @@ int lapb_getparms(struct net_device *dev, struct lapb_parms_struct *parms)
 out:
 	return rc;
 }
+EXPORT_SYMBOL(lapb_getparms);
 
 int lapb_setparms(struct net_device *dev, struct lapb_parms_struct *parms)
 {
@@ -262,6 +265,7 @@ out_put:
 out:
 	return rc;
 }
+EXPORT_SYMBOL(lapb_setparms);
 
 int lapb_connect_request(struct net_device *dev)
 {
@@ -290,6 +294,7 @@ out_put:
 out:
 	return rc;
 }
+EXPORT_SYMBOL(lapb_connect_request);
 
 int lapb_disconnect_request(struct net_device *dev)
 {
@@ -334,6 +339,7 @@ out_put:
 out:
 	return rc;
 }
+EXPORT_SYMBOL(lapb_disconnect_request);
 
 int lapb_data_request(struct net_device *dev, struct sk_buff *skb)
 {
@@ -355,6 +361,7 @@ out_put:
 out:
 	return rc;
 }
+EXPORT_SYMBOL(lapb_data_request);
 
 int lapb_data_received(struct net_device *dev, struct sk_buff *skb)
 {
@@ -369,6 +376,7 @@ int lapb_data_received(struct net_device *dev, struct sk_buff *skb)
 
 	return rc;
 }
+EXPORT_SYMBOL(lapb_data_received);
 
 void lapb_connect_confirmation(struct lapb_cb *lapb, int reason)
 {
@@ -415,15 +423,6 @@ int lapb_data_transmit(struct lapb_cb *lapb, struct sk_buff *skb)
 	return used;
 }
 
-EXPORT_SYMBOL(lapb_register);
-EXPORT_SYMBOL(lapb_unregister);
-EXPORT_SYMBOL(lapb_getparms);
-EXPORT_SYMBOL(lapb_setparms);
-EXPORT_SYMBOL(lapb_connect_request);
-EXPORT_SYMBOL(lapb_disconnect_request);
-EXPORT_SYMBOL(lapb_data_request);
-EXPORT_SYMBOL(lapb_data_received);
-
 static int __init lapb_init(void)
 {
 	return 0;
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index bb9cbc17d926..17a8dff06090 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -704,8 +704,8 @@ out:
  *	Copy received data to the socket user.
  *	Returns non-negative upon success, negative otherwise.
  */
-static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock,
-			  struct msghdr *msg, size_t len, int flags)
+static int llc_ui_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+			  int flags)
 {
 	DECLARE_SOCKADDR(struct sockaddr_llc *, uaddr, msg->msg_name);
 	const int nonblock = flags & MSG_DONTWAIT;
@@ -819,8 +819,7 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock,
 			used = len;
 
 		if (!(flags & MSG_TRUNC)) {
-			int rc = skb_copy_datagram_iovec(skb, offset,
-							 msg->msg_iov, used);
+			int rc = skb_copy_datagram_msg(skb, offset, msg, used);
 			if (rc) {
 				/* Exception. Bailout! */
 				if (!copied)
@@ -879,8 +878,7 @@ copy_uaddr:
  *	Transmit data provided by the socket user.
  *	Returns non-negative upon success, negative otherwise.
  */
-static int llc_ui_sendmsg(struct kiocb *iocb, struct socket *sock,
-			  struct msghdr *msg, size_t len)
+static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 {
 	struct sock *sk = sock->sk;
 	struct llc_sock *llc = llc_sk(sk);
@@ -922,7 +920,7 @@ static int llc_ui_sendmsg(struct kiocb *iocb, struct socket *sock,
 	skb->dev      = llc->dev;
 	skb->protocol = llc_proto_type(addr->sllc_arphrd);
 	skb_reserve(skb, hdrlen);
-	rc = memcpy_fromiovec(skb_put(skb, copied), msg->msg_iov, copied);
+	rc = memcpy_from_msg(skb_put(skb, copied), msg, copied);
 	if (rc)
 		goto out;
 	if (sk->sk_type == SOCK_DGRAM || addr->sllc_ua) {
diff --git a/net/llc/llc_c_st.c b/net/llc/llc_c_st.c
index 818a9428823b..2467573b5f84 100644
--- a/net/llc/llc_c_st.c
+++ b/net/llc/llc_c_st.c
@@ -33,7 +33,7 @@
  * LLC_CONN_STATE_AWAIT_REJ states
  */
 /* State transitions for LLC_CONN_EV_DISC_REQ event */
-static llc_conn_action_t llc_common_actions_1[] = {
+static const llc_conn_action_t llc_common_actions_1[] = {
 	[0] = llc_conn_ac_send_disc_cmd_p_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_stop_other_timers,
@@ -50,7 +50,7 @@ static struct llc_conn_state_trans llc_common_state_trans_1 = {
 };
 
 /* State transitions for LLC_CONN_EV_RESET_REQ event */
-static llc_conn_action_t llc_common_actions_2[] = {
+static const llc_conn_action_t llc_common_actions_2[] = {
 	[0] = llc_conn_ac_send_sabme_cmd_p_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_stop_other_timers,
@@ -67,7 +67,7 @@ static struct llc_conn_state_trans llc_common_state_trans_2 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_SABME_CMD_Pbit_SET_X event */
-static llc_conn_action_t llc_common_actions_3[] = {
+static const llc_conn_action_t llc_common_actions_3[] = {
 	[0] = llc_conn_ac_stop_all_timers,
 	[1] = llc_conn_ac_set_vs_0,
 	[2] = llc_conn_ac_set_vr_0,
@@ -87,7 +87,7 @@ static struct llc_conn_state_trans llc_common_state_trans_3 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_DISC_CMD_Pbit_SET_X event */
-static llc_conn_action_t llc_common_actions_4[] = {
+static const llc_conn_action_t llc_common_actions_4[] = {
 	[0] = llc_conn_ac_stop_all_timers,
 	[1] = llc_conn_ac_send_ua_rsp_f_set_p,
 	[2] = llc_conn_ac_disc_ind,
@@ -103,7 +103,7 @@ static struct llc_conn_state_trans llc_common_state_trans_4 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_FRMR_RSP_Fbit_SET_X event */
-static llc_conn_action_t llc_common_actions_5[] = {
+static const llc_conn_action_t llc_common_actions_5[] = {
 	[0] = llc_conn_ac_send_sabme_cmd_p_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_stop_other_timers,
@@ -122,7 +122,7 @@ static struct llc_conn_state_trans llc_common_state_trans_5 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_DM_RSP_Fbit_SET_X event */
-static llc_conn_action_t llc_common_actions_6[] = {
+static const llc_conn_action_t llc_common_actions_6[] = {
 	[0] = llc_conn_ac_disc_ind,
 	[1] = llc_conn_ac_stop_all_timers,
 	[2] = llc_conn_disc,
@@ -137,7 +137,7 @@ static struct llc_conn_state_trans llc_common_state_trans_6 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_ZZZ_CMD_Pbit_SET_X_INVAL_Nr event */
-static llc_conn_action_t llc_common_actions_7a[] = {
+static const llc_conn_action_t llc_common_actions_7a[] = {
 	[0] = llc_conn_ac_send_frmr_rsp_f_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_stop_other_timers,
@@ -153,7 +153,7 @@ static struct llc_conn_state_trans llc_common_state_trans_7a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_X_INVAL_Ns event */
-static llc_conn_action_t llc_common_actions_7b[] = {
+static const llc_conn_action_t llc_common_actions_7b[] = {
 	[0] = llc_conn_ac_send_frmr_rsp_f_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_stop_other_timers,
@@ -169,7 +169,7 @@ static struct llc_conn_state_trans llc_common_state_trans_7b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_ZZZ_RSP_Fbit_SET_X_INVAL_Nr event */
-static llc_conn_action_t llc_common_actions_8a[] = {
+static const llc_conn_action_t llc_common_actions_8a[] = {
 	[0] = llc_conn_ac_send_frmr_rsp_f_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_stop_other_timers,
@@ -185,7 +185,7 @@ static struct llc_conn_state_trans llc_common_state_trans_8a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_X_INVAL_Ns event */
-static llc_conn_action_t llc_common_actions_8b[] = {
+static const llc_conn_action_t llc_common_actions_8b[] = {
 	[0] = llc_conn_ac_send_frmr_rsp_f_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_stop_other_timers,
@@ -201,7 +201,7 @@ static struct llc_conn_state_trans llc_common_state_trans_8b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_BAD_PDU event */
-static llc_conn_action_t llc_common_actions_8c[] = {
+static const llc_conn_action_t llc_common_actions_8c[] = {
 	[0] = llc_conn_ac_send_frmr_rsp_f_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_stop_other_timers,
@@ -217,7 +217,7 @@ static struct llc_conn_state_trans llc_common_state_trans_8c = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_UA_RSP_Fbit_SET_X event */
-static llc_conn_action_t llc_common_actions_9[] = {
+static const llc_conn_action_t llc_common_actions_9[] = {
 	[0] = llc_conn_ac_send_frmr_rsp_f_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_stop_other_timers,
@@ -234,12 +234,12 @@ static struct llc_conn_state_trans llc_common_state_trans_9 = {
 
 /* State transitions for LLC_CONN_EV_RX_XXX_RSP_Fbit_SET_1 event */
 #if 0
-static llc_conn_ev_qfyr_t llc_common_ev_qfyrs_10[] = {
+static const llc_conn_ev_qfyr_t llc_common_ev_qfyrs_10[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_common_actions_10[] = {
+static const llc_conn_action_t llc_common_actions_10[] = {
 	[0] = llc_conn_ac_send_frmr_rsp_f_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_stop_other_timers,
@@ -256,12 +256,12 @@ static struct llc_conn_state_trans llc_common_state_trans_10 = {
 #endif
 
 /* State transitions for LLC_CONN_EV_P_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_common_ev_qfyrs_11a[] = {
+static const llc_conn_ev_qfyr_t llc_common_ev_qfyrs_11a[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_gte_n2,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_common_actions_11a[] = {
+static const llc_conn_action_t llc_common_actions_11a[] = {
 	[0] = llc_conn_ac_send_sabme_cmd_p_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_stop_other_timers,
@@ -278,12 +278,12 @@ static struct llc_conn_state_trans llc_common_state_trans_11a = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_common_ev_qfyrs_11b[] = {
+static const llc_conn_ev_qfyr_t llc_common_ev_qfyrs_11b[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_gte_n2,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_common_actions_11b[] = {
+static const llc_conn_action_t llc_common_actions_11b[] = {
 	[0] = llc_conn_ac_send_sabme_cmd_p_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_stop_other_timers,
@@ -300,12 +300,12 @@ static struct llc_conn_state_trans llc_common_state_trans_11b = {
 };
 
 /* State transitions for LLC_CONN_EV_REJ_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_common_ev_qfyrs_11c[] = {
+static const llc_conn_ev_qfyr_t llc_common_ev_qfyrs_11c[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_gte_n2,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_common_actions_11c[] = {
+static const llc_conn_action_t llc_common_actions_11c[] = {
 	[0] = llc_conn_ac_send_sabme_cmd_p_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_stop_other_timers,
@@ -322,12 +322,12 @@ static struct llc_conn_state_trans llc_common_state_trans_11c = {
 };
 
 /* State transitions for LLC_CONN_EV_BUSY_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_common_ev_qfyrs_11d[] = {
+static const llc_conn_ev_qfyr_t llc_common_ev_qfyrs_11d[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_gte_n2,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_common_actions_11d[] = {
+static const llc_conn_action_t llc_common_actions_11d[] = {
 	[0] = llc_conn_ac_send_sabme_cmd_p_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_stop_other_timers,
@@ -351,7 +351,7 @@ static struct llc_conn_state_trans llc_common_state_trans_end;
 
 /* LLC_CONN_STATE_ADM transitions */
 /* State transitions for LLC_CONN_EV_CONN_REQ event */
-static llc_conn_action_t llc_adm_actions_1[] = {
+static const llc_conn_action_t llc_adm_actions_1[] = {
 	[0] = llc_conn_ac_send_sabme_cmd_p_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_set_retry_cnt_0,
@@ -367,7 +367,7 @@ static struct llc_conn_state_trans llc_adm_state_trans_1 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_SABME_CMD_Pbit_SET_X event */
-static llc_conn_action_t llc_adm_actions_2[] = {
+static const llc_conn_action_t llc_adm_actions_2[] = {
 	[0] = llc_conn_ac_send_ua_rsp_f_set_p,
 	[1] = llc_conn_ac_set_vs_0,
 	[2] = llc_conn_ac_set_vr_0,
@@ -386,7 +386,7 @@ static struct llc_conn_state_trans llc_adm_state_trans_2 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_DISC_CMD_Pbit_SET_X event */
-static llc_conn_action_t llc_adm_actions_3[] = {
+static const llc_conn_action_t llc_adm_actions_3[] = {
 	[0] = llc_conn_ac_send_dm_rsp_f_set_p,
 	[1] = llc_conn_disc,
 	[2] = NULL,
@@ -400,7 +400,7 @@ static struct llc_conn_state_trans llc_adm_state_trans_3 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_XXX_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_adm_actions_4[] = {
+static const llc_conn_action_t llc_adm_actions_4[] = {
 	[0] = llc_conn_ac_send_dm_rsp_f_set_1,
 	[1] = llc_conn_disc,
 	[2] = NULL,
@@ -414,7 +414,7 @@ static struct llc_conn_state_trans llc_adm_state_trans_4 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_XXX_YYY event */
-static llc_conn_action_t llc_adm_actions_5[] = {
+static const llc_conn_action_t llc_adm_actions_5[] = {
 	[0] = llc_conn_disc,
 	[1] = NULL,
 };
@@ -445,7 +445,7 @@ static struct llc_conn_state_trans *llc_adm_state_transitions[] = {
 
 /* LLC_CONN_STATE_SETUP transitions */
 /* State transitions for LLC_CONN_EV_RX_SABME_CMD_Pbit_SET_X event */
-static llc_conn_action_t llc_setup_actions_1[] = {
+static const llc_conn_action_t llc_setup_actions_1[] = {
 	[0] = llc_conn_ac_send_ua_rsp_f_set_p,
 	[1] = llc_conn_ac_set_vs_0,
 	[2] = llc_conn_ac_set_vr_0,
@@ -461,13 +461,13 @@ static struct llc_conn_state_trans llc_setup_state_trans_1 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_UA_RSP_Fbit_SET_X event */
-static llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_2[] = {
+static const llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_2[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_f,
 	[1] = llc_conn_ev_qlfy_set_status_conn,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_setup_actions_2[] = {
+static const llc_conn_action_t llc_setup_actions_2[] = {
 	[0] = llc_conn_ac_stop_ack_timer,
 	[1] = llc_conn_ac_set_vs_0,
 	[2] = llc_conn_ac_set_vr_0,
@@ -485,13 +485,13 @@ static struct llc_conn_state_trans llc_setup_state_trans_2 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_3[] = {
+static const llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_3[] = {
 	[0] = llc_conn_ev_qlfy_s_flag_eq_1,
 	[1] = llc_conn_ev_qlfy_set_status_conn,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_setup_actions_3[] = {
+static const llc_conn_action_t llc_setup_actions_3[] = {
 	[0] = llc_conn_ac_set_p_flag_0,
 	[1] = llc_conn_ac_set_remote_busy_0,
 	[2] = llc_conn_ac_conn_confirm,
@@ -506,12 +506,12 @@ static struct llc_conn_state_trans llc_setup_state_trans_3 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_DISC_CMD_Pbit_SET_X event */
-static llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_4[] = {
+static const llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_4[] = {
 	[0] = llc_conn_ev_qlfy_set_status_disc,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_setup_actions_4[] = {
+static const llc_conn_action_t llc_setup_actions_4[] = {
 	[0] = llc_conn_ac_send_dm_rsp_f_set_p,
 	[1] = llc_conn_ac_stop_ack_timer,
 	[2] = llc_conn_ac_conn_confirm,
@@ -527,12 +527,12 @@ static struct llc_conn_state_trans llc_setup_state_trans_4 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_DM_RSP_Fbit_SET_X event */
-static llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_5[] = {
+static const llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_5[] = {
 	[0] = llc_conn_ev_qlfy_set_status_disc,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_setup_actions_5[] = {
+static const llc_conn_action_t llc_setup_actions_5[] = {
 	[0] = llc_conn_ac_stop_ack_timer,
 	[1] = llc_conn_ac_conn_confirm,
 	[2] = llc_conn_disc,
@@ -547,13 +547,13 @@ static struct llc_conn_state_trans llc_setup_state_trans_5 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_7[] = {
+static const llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_7[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[1] = llc_conn_ev_qlfy_s_flag_eq_0,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_setup_actions_7[] = {
+static const llc_conn_action_t llc_setup_actions_7[] = {
 	[0] = llc_conn_ac_send_sabme_cmd_p_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_inc_retry_cnt_by_1,
@@ -568,14 +568,14 @@ static struct llc_conn_state_trans llc_setup_state_trans_7 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_8[] = {
+static const llc_conn_ev_qfyr_t llc_setup_ev_qfyrs_8[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_gte_n2,
 	[1] = llc_conn_ev_qlfy_s_flag_eq_0,
 	[2] = llc_conn_ev_qlfy_set_status_failed,
 	[3] = NULL,
 };
 
-static llc_conn_action_t llc_setup_actions_8[] = {
+static const llc_conn_action_t llc_setup_actions_8[] = {
 	[0] = llc_conn_ac_conn_confirm,
 	[1] = llc_conn_disc,
 	[2] = NULL,
@@ -609,14 +609,14 @@ static struct llc_conn_state_trans *llc_setup_state_transitions[] = {
 
 /* LLC_CONN_STATE_NORMAL transitions */
 /* State transitions for LLC_CONN_EV_DATA_REQ event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_1[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_1[] = {
 	[0] = llc_conn_ev_qlfy_remote_busy_eq_0,
 	[1] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[2] = llc_conn_ev_qlfy_last_frame_eq_0,
 	[3] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_1[] = {
+static const llc_conn_action_t llc_normal_actions_1[] = {
 	[0] = llc_conn_ac_send_i_as_ack,
 	[1] = llc_conn_ac_start_ack_tmr_if_not_running,
 	[2] = NULL,
@@ -630,14 +630,14 @@ static struct llc_conn_state_trans llc_normal_state_trans_1 = {
 };
 
 /* State transitions for LLC_CONN_EV_DATA_REQ event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_2[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_2[] = {
 	[0] = llc_conn_ev_qlfy_remote_busy_eq_0,
 	[1] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[2] = llc_conn_ev_qlfy_last_frame_eq_1,
 	[3] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_2[] = {
+static const llc_conn_action_t llc_normal_actions_2[] = {
 	[0] = llc_conn_ac_send_i_cmd_p_set_1,
 	[1] = llc_conn_ac_start_p_timer,
 	[2] = NULL,
@@ -651,14 +651,14 @@ static struct llc_conn_state_trans llc_normal_state_trans_2 = {
 };
 
 /* State transitions for LLC_CONN_EV_DATA_REQ event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_2_1[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_2_1[] = {
 	[0] = llc_conn_ev_qlfy_remote_busy_eq_1,
 	[1] = llc_conn_ev_qlfy_set_status_remote_busy,
 	[2] = NULL,
 };
 
 /* just one member, NULL, .bss zeroes it */
-static llc_conn_action_t llc_normal_actions_2_1[1];
+static const llc_conn_action_t llc_normal_actions_2_1[1];
 
 static struct llc_conn_state_trans llc_normal_state_trans_2_1 = {
 	.ev	       = llc_conn_ev_data_req,
@@ -668,12 +668,12 @@ static struct llc_conn_state_trans llc_normal_state_trans_2_1 = {
 };
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_DETECTED event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_3[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_3[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_3[] = {
+static const llc_conn_action_t llc_normal_actions_3[] = {
 	[0] = llc_conn_ac_rst_sendack_flag,
 	[1] = llc_conn_ac_send_rnr_xxx_x_set_0,
 	[2] = llc_conn_ac_set_data_flag_0,
@@ -688,12 +688,12 @@ static struct llc_conn_state_trans llc_normal_state_trans_3 = {
 };
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_DETECTED event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_4[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_4[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_4[] = {
+static const llc_conn_action_t llc_normal_actions_4[] = {
 	[0] = llc_conn_ac_rst_sendack_flag,
 	[1] = llc_conn_ac_send_rnr_xxx_x_set_0,
 	[2] = llc_conn_ac_set_data_flag_0,
@@ -708,12 +708,12 @@ static struct llc_conn_state_trans llc_normal_state_trans_4 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0_UNEXPD_Ns event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_5a[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_5a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_5a[] = {
+static const llc_conn_action_t llc_normal_actions_5a[] = {
 	[0] = llc_conn_ac_rst_sendack_flag,
 	[1] = llc_conn_ac_send_rej_xxx_x_set_0,
 	[2] = llc_conn_ac_upd_nr_received,
@@ -731,12 +731,12 @@ static struct llc_conn_state_trans llc_normal_state_trans_5a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_0_UNEXPD_Ns event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_5b[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_5b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_5b[] = {
+static const llc_conn_action_t llc_normal_actions_5b[] = {
 	[0] = llc_conn_ac_rst_sendack_flag,
 	[1] = llc_conn_ac_send_rej_xxx_x_set_0,
 	[2] = llc_conn_ac_upd_nr_received,
@@ -754,12 +754,12 @@ static struct llc_conn_state_trans llc_normal_state_trans_5b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_1_UNEXPD_Ns event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_5c[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_5c[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_5c[] = {
+static const llc_conn_action_t llc_normal_actions_5c[] = {
 	[0] = llc_conn_ac_rst_sendack_flag,
 	[1] = llc_conn_ac_send_rej_xxx_x_set_0,
 	[2] = llc_conn_ac_upd_nr_received,
@@ -777,12 +777,12 @@ static struct llc_conn_state_trans llc_normal_state_trans_5c = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0_UNEXPD_Ns event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_6a[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_6a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_6a[] = {
+static const llc_conn_action_t llc_normal_actions_6a[] = {
 	[0] = llc_conn_ac_rst_sendack_flag,
 	[1] = llc_conn_ac_send_rej_xxx_x_set_0,
 	[2] = llc_conn_ac_upd_nr_received,
@@ -798,12 +798,12 @@ static struct llc_conn_state_trans llc_normal_state_trans_6a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_0_UNEXPD_Ns event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_6b[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_6b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_6b[] = {
+static const llc_conn_action_t llc_normal_actions_6b[] = {
 	[0] = llc_conn_ac_rst_sendack_flag,
 	[1] = llc_conn_ac_send_rej_xxx_x_set_0,
 	[2] = llc_conn_ac_upd_nr_received,
@@ -819,7 +819,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_6b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_1_UNEXPD_Ns event */
-static llc_conn_action_t llc_normal_actions_7[] = {
+static const llc_conn_action_t llc_normal_actions_7[] = {
 	[0] = llc_conn_ac_rst_sendack_flag,
 	[1] = llc_conn_ac_send_rej_rsp_f_set_1,
 	[2] = llc_conn_ac_upd_nr_received,
@@ -835,12 +835,12 @@ static struct llc_conn_state_trans llc_normal_state_trans_7 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_X event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_8a[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_8a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_f,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_8[] = {
+static const llc_conn_action_t llc_normal_actions_8[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_upd_p_flag,
@@ -858,7 +858,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_8a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_8b[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_8b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
@@ -871,12 +871,12 @@ static struct llc_conn_state_trans llc_normal_state_trans_8b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_9a[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_9a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_9a[] = {
+static const llc_conn_action_t llc_normal_actions_9a[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_data_ind,
@@ -892,12 +892,12 @@ static struct llc_conn_state_trans llc_normal_state_trans_9a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_9b[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_9b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_9b[] = {
+static const llc_conn_action_t llc_normal_actions_9b[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_data_ind,
@@ -913,7 +913,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_9b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_normal_actions_10[] = {
+static const llc_conn_action_t llc_normal_actions_10[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_send_ack_rsp_f_set_1,
 	[2] = llc_conn_ac_rst_sendack_flag,
@@ -930,7 +930,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_10 = {
 };
 
 /* State transitions for * LLC_CONN_EV_RX_RR_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_normal_actions_11a[] = {
+static const llc_conn_action_t llc_normal_actions_11a[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -945,7 +945,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_11a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_normal_actions_11b[] = {
+static const llc_conn_action_t llc_normal_actions_11b[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -960,12 +960,12 @@ static struct llc_conn_state_trans llc_normal_state_trans_11b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_RSP_Fbit_SET_1 event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_11c[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_11c[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_11c[] = {
+static const llc_conn_action_t llc_normal_actions_11c[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_inc_tx_win_size,
@@ -981,7 +981,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_11c = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_normal_actions_12[] = {
+static const llc_conn_action_t llc_normal_actions_12[] = {
 	[0] = llc_conn_ac_send_ack_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_adjust_npta_by_rr,
@@ -998,7 +998,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_12 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_normal_actions_13a[] = {
+static const llc_conn_action_t llc_normal_actions_13a[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -1013,7 +1013,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_13a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_normal_actions_13b[] = {
+static const llc_conn_action_t llc_normal_actions_13b[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -1028,12 +1028,12 @@ static struct llc_conn_state_trans llc_normal_state_trans_13b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_1 event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_13c[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_13c[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_13c[] = {
+static const llc_conn_action_t llc_normal_actions_13c[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -1048,7 +1048,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_13c = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_normal_actions_14[] = {
+static const llc_conn_action_t llc_normal_actions_14[] = {
 	[0] = llc_conn_ac_send_rr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_adjust_npta_by_rnr,
@@ -1065,12 +1065,12 @@ static struct llc_conn_state_trans llc_normal_state_trans_14 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_15a[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_15a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_15a[] = {
+static const llc_conn_action_t llc_normal_actions_15a[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_p_flag,
@@ -1088,12 +1088,12 @@ static struct llc_conn_state_trans llc_normal_state_trans_15a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_X event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_15b[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_15b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_f,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_15b[] = {
+static const llc_conn_action_t llc_normal_actions_15b[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_p_flag,
@@ -1111,12 +1111,12 @@ static struct llc_conn_state_trans llc_normal_state_trans_15b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_16a[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_16a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_16a[] = {
+static const llc_conn_action_t llc_normal_actions_16a[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_dec_tx_win_size,
@@ -1133,12 +1133,12 @@ static struct llc_conn_state_trans llc_normal_state_trans_16a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_16b[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_16b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_16b[] = {
+static const llc_conn_action_t llc_normal_actions_16b[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_dec_tx_win_size,
@@ -1155,7 +1155,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_16b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_normal_actions_17[] = {
+static const llc_conn_action_t llc_normal_actions_17[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_dec_tx_win_size,
@@ -1172,12 +1172,12 @@ static struct llc_conn_state_trans llc_normal_state_trans_17 = {
 };
 
 /* State transitions for LLC_CONN_EV_INIT_P_F_CYCLE event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_18[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_18[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_18[] = {
+static const llc_conn_action_t llc_normal_actions_18[] = {
 	[0] = llc_conn_ac_send_rr_cmd_p_set_1,
 	[1] = llc_conn_ac_start_p_timer,
 	[2] = NULL,
@@ -1191,12 +1191,12 @@ static struct llc_conn_state_trans llc_normal_state_trans_18 = {
 };
 
 /* State transitions for LLC_CONN_EV_P_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_19[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_19[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_19[] = {
+static const llc_conn_action_t llc_normal_actions_19[] = {
 	[0] = llc_conn_ac_rst_sendack_flag,
 	[1] = llc_conn_ac_send_rr_cmd_p_set_1,
 	[2] = llc_conn_ac_rst_vs,
@@ -1213,13 +1213,13 @@ static struct llc_conn_state_trans llc_normal_state_trans_19 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_20a[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_20a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_20a[] = {
+static const llc_conn_action_t llc_normal_actions_20a[] = {
 	[0] = llc_conn_ac_rst_sendack_flag,
 	[1] = llc_conn_ac_send_rr_cmd_p_set_1,
 	[2] = llc_conn_ac_rst_vs,
@@ -1236,13 +1236,13 @@ static struct llc_conn_state_trans llc_normal_state_trans_20a = {
 };
 
 /* State transitions for LLC_CONN_EV_BUSY_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_20b[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_20b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_20b[] = {
+static const llc_conn_action_t llc_normal_actions_20b[] = {
 	[0] = llc_conn_ac_rst_sendack_flag,
 	[1] = llc_conn_ac_send_rr_cmd_p_set_1,
 	[2] = llc_conn_ac_rst_vs,
@@ -1259,12 +1259,12 @@ static struct llc_conn_state_trans llc_normal_state_trans_20b = {
 };
 
 /* State transitions for LLC_CONN_EV_TX_BUFF_FULL event */
-static llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_21[] = {
+static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_21[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_normal_actions_21[] = {
+static const llc_conn_action_t llc_normal_actions_21[] = {
 	[0] = llc_conn_ac_send_rr_cmd_p_set_1,
 	[1] = llc_conn_ac_start_p_timer,
 	[2] = NULL,
@@ -1342,13 +1342,13 @@ static struct llc_conn_state_trans *llc_normal_state_transitions[] = {
 
 /* LLC_CONN_STATE_BUSY transitions */
 /* State transitions for LLC_CONN_EV_DATA_REQ event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_1[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_1[] = {
 	[0] = llc_conn_ev_qlfy_remote_busy_eq_0,
 	[1] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_1[] = {
+static const llc_conn_action_t llc_busy_actions_1[] = {
 	[0] = llc_conn_ac_send_i_xxx_x_set_0,
 	[1] = llc_conn_ac_start_ack_tmr_if_not_running,
 	[2] = NULL,
@@ -1362,13 +1362,13 @@ static struct llc_conn_state_trans llc_busy_state_trans_1 = {
 };
 
 /* State transitions for LLC_CONN_EV_DATA_REQ event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_2[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_2[] = {
 	[0] = llc_conn_ev_qlfy_remote_busy_eq_0,
 	[1] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_2[] = {
+static const llc_conn_action_t llc_busy_actions_2[] = {
 	[0] = llc_conn_ac_send_i_xxx_x_set_0,
 	[1] = llc_conn_ac_start_ack_tmr_if_not_running,
 	[2] = NULL,
@@ -1382,14 +1382,14 @@ static struct llc_conn_state_trans llc_busy_state_trans_2 = {
 };
 
 /* State transitions for LLC_CONN_EV_DATA_REQ event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_2_1[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_2_1[] = {
 	[0] = llc_conn_ev_qlfy_remote_busy_eq_1,
 	[1] = llc_conn_ev_qlfy_set_status_remote_busy,
 	[2] = NULL,
 };
 
 /* just one member, NULL, .bss zeroes it */
-static llc_conn_action_t llc_busy_actions_2_1[1];
+static const llc_conn_action_t llc_busy_actions_2_1[1];
 
 static struct llc_conn_state_trans llc_busy_state_trans_2_1 = {
 	.ev	       = llc_conn_ev_data_req,
@@ -1399,13 +1399,13 @@ static struct llc_conn_state_trans llc_busy_state_trans_2_1 = {
 };
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_CLEARED event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_3[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_3[] = {
 	[0] = llc_conn_ev_qlfy_data_flag_eq_1,
 	[1] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_3[] = {
+static const llc_conn_action_t llc_busy_actions_3[] = {
 	[0] = llc_conn_ac_send_rej_xxx_x_set_0,
 	[1] = llc_conn_ac_start_rej_timer,
 	[2] = NULL,
@@ -1419,13 +1419,13 @@ static struct llc_conn_state_trans llc_busy_state_trans_3 = {
 };
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_CLEARED event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_4[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_4[] = {
 	[0] = llc_conn_ev_qlfy_data_flag_eq_1,
 	[1] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_4[] = {
+static const llc_conn_action_t llc_busy_actions_4[] = {
 	[0] = llc_conn_ac_send_rej_xxx_x_set_0,
 	[1] = llc_conn_ac_start_rej_timer,
 	[2] = NULL,
@@ -1439,13 +1439,13 @@ static struct llc_conn_state_trans llc_busy_state_trans_4 = {
 };
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_CLEARED event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_5[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_5[] = {
 	[0] = llc_conn_ev_qlfy_data_flag_eq_0,
 	[1] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_5[] = {
+static const llc_conn_action_t llc_busy_actions_5[] = {
 	[0] = llc_conn_ac_send_rr_xxx_x_set_0,
 	[1] = NULL,
 };
@@ -1458,13 +1458,13 @@ static struct llc_conn_state_trans llc_busy_state_trans_5 = {
 };
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_CLEARED event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_6[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_6[] = {
 	[0] = llc_conn_ev_qlfy_data_flag_eq_0,
 	[1] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_6[] = {
+static const llc_conn_action_t llc_busy_actions_6[] = {
 	[0] = llc_conn_ac_send_rr_xxx_x_set_0,
 	[1] = NULL,
 };
@@ -1477,13 +1477,13 @@ static struct llc_conn_state_trans llc_busy_state_trans_6 = {
 };
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_CLEARED event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_7[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_7[] = {
 	[0] = llc_conn_ev_qlfy_data_flag_eq_2,
 	[1] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_7[] = {
+static const llc_conn_action_t llc_busy_actions_7[] = {
 	[0] = llc_conn_ac_send_rr_xxx_x_set_0,
 	[1] = NULL,
 };
@@ -1496,13 +1496,13 @@ static struct llc_conn_state_trans llc_busy_state_trans_7 = {
 };
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_CLEARED event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_8[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_8[] = {
 	[0] = llc_conn_ev_qlfy_data_flag_eq_2,
 	[1] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_8[] = {
+static const llc_conn_action_t llc_busy_actions_8[] = {
 	[0] = llc_conn_ac_send_rr_xxx_x_set_0,
 	[1] = NULL,
 };
@@ -1515,12 +1515,12 @@ static struct llc_conn_state_trans llc_busy_state_trans_8 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_X_UNEXPD_Ns event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_9a[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_9a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_f,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_9a[] = {
+static const llc_conn_action_t llc_busy_actions_9a[] = {
 	[0] = llc_conn_ac_opt_send_rnr_xxx_x_set_0,
 	[1] = llc_conn_ac_upd_p_flag,
 	[2] = llc_conn_ac_upd_nr_received,
@@ -1537,12 +1537,12 @@ static struct llc_conn_state_trans llc_busy_state_trans_9a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0_UNEXPD_Ns event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_9b[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_9b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_9b[] = {
+static const llc_conn_action_t llc_busy_actions_9b[] = {
 	[0] = llc_conn_ac_opt_send_rnr_xxx_x_set_0,
 	[1] = llc_conn_ac_upd_p_flag,
 	[2] = llc_conn_ac_upd_nr_received,
@@ -1559,12 +1559,12 @@ static struct llc_conn_state_trans llc_busy_state_trans_9b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_0_UNEXPD_Ns event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_10a[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_10a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_10a[] = {
+static const llc_conn_action_t llc_busy_actions_10a[] = {
 	[0] = llc_conn_ac_opt_send_rnr_xxx_x_set_0,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_set_data_flag_1_if_data_flag_eq_0,
@@ -1579,12 +1579,12 @@ static struct llc_conn_state_trans llc_busy_state_trans_10a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0_UNEXPD_Ns event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_10b[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_10b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_10b[] = {
+static const llc_conn_action_t llc_busy_actions_10b[] = {
 	[0] = llc_conn_ac_opt_send_rnr_xxx_x_set_0,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_set_data_flag_1_if_data_flag_eq_0,
@@ -1599,7 +1599,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_10b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_1_UNEXPD_Ns event */
-static llc_conn_action_t llc_busy_actions_11[] = {
+static const llc_conn_action_t llc_busy_actions_11[] = {
 	[0] = llc_conn_ac_send_rnr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_set_data_flag_1_if_data_flag_eq_0,
@@ -1614,7 +1614,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_11 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_busy_actions_12[] = {
+static const llc_conn_action_t llc_busy_actions_12[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_send_rnr_rsp_f_set_1,
@@ -1632,12 +1632,12 @@ static struct llc_conn_state_trans llc_busy_state_trans_12 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_X event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_13a[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_13a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_f,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_13a[] = {
+static const llc_conn_action_t llc_busy_actions_13a[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_upd_p_flag,
@@ -1657,12 +1657,12 @@ static struct llc_conn_state_trans llc_busy_state_trans_13a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_13b[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_13b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_13b[] = {
+static const llc_conn_action_t llc_busy_actions_13b[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_upd_p_flag,
@@ -1682,12 +1682,12 @@ static struct llc_conn_state_trans llc_busy_state_trans_13b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_14a[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_14a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_14a[] = {
+static const llc_conn_action_t llc_busy_actions_14a[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_opt_send_rnr_xxx_x_set_0,
@@ -1705,12 +1705,12 @@ static struct llc_conn_state_trans llc_busy_state_trans_14a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_14b[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_14b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_14b[] = {
+static const llc_conn_action_t llc_busy_actions_14b[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_opt_send_rnr_xxx_x_set_0,
@@ -1728,7 +1728,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_14b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_busy_actions_15a[] = {
+static const llc_conn_action_t llc_busy_actions_15a[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -1743,7 +1743,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_15a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_busy_actions_15b[] = {
+static const llc_conn_action_t llc_busy_actions_15b[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -1758,12 +1758,12 @@ static struct llc_conn_state_trans llc_busy_state_trans_15b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_RSP_Fbit_SET_1 event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_15c[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_15c[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_15c[] = {
+static const llc_conn_action_t llc_busy_actions_15c[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -1778,7 +1778,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_15c = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_busy_actions_16[] = {
+static const llc_conn_action_t llc_busy_actions_16[] = {
 	[0] = llc_conn_ac_send_rnr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -1793,7 +1793,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_16 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_busy_actions_17a[] = {
+static const llc_conn_action_t llc_busy_actions_17a[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -1808,7 +1808,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_17a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_busy_actions_17b[] = {
+static const llc_conn_action_t llc_busy_actions_17b[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -1823,12 +1823,12 @@ static struct llc_conn_state_trans llc_busy_state_trans_17b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_1 event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_17c[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_17c[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_17c[] = {
+static const llc_conn_action_t llc_busy_actions_17c[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -1843,7 +1843,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_17c = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_busy_actions_18[] = {
+static const llc_conn_action_t llc_busy_actions_18[] = {
 	[0] = llc_conn_ac_send_rnr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -1858,12 +1858,12 @@ static struct llc_conn_state_trans llc_busy_state_trans_18 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_19a[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_19a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_19a[] = {
+static const llc_conn_action_t llc_busy_actions_19a[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_p_flag,
@@ -1880,12 +1880,12 @@ static struct llc_conn_state_trans llc_busy_state_trans_19a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_X event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_19b[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_19b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_f,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_19b[] = {
+static const llc_conn_action_t llc_busy_actions_19b[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_p_flag,
@@ -1902,12 +1902,12 @@ static struct llc_conn_state_trans llc_busy_state_trans_19b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_20a[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_20a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_20a[] = {
+static const llc_conn_action_t llc_busy_actions_20a[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_resend_i_xxx_x_set_0,
@@ -1923,12 +1923,12 @@ static struct llc_conn_state_trans llc_busy_state_trans_20a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_20b[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_20b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_20b[] = {
+static const llc_conn_action_t llc_busy_actions_20b[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_resend_i_xxx_x_set_0,
@@ -1944,7 +1944,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_20b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_busy_actions_21[] = {
+static const llc_conn_action_t llc_busy_actions_21[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_send_rnr_rsp_f_set_1,
@@ -1961,12 +1961,12 @@ static struct llc_conn_state_trans llc_busy_state_trans_21 = {
 };
 
 /* State transitions for LLC_CONN_EV_INIT_P_F_CYCLE event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_22[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_22[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_22[] = {
+static const llc_conn_action_t llc_busy_actions_22[] = {
 	[0] = llc_conn_ac_send_rnr_cmd_p_set_1,
 	[1] = llc_conn_ac_start_p_timer,
 	[2] = NULL,
@@ -1980,12 +1980,12 @@ static struct llc_conn_state_trans llc_busy_state_trans_22 = {
 };
 
 /* State transitions for LLC_CONN_EV_P_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_23[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_23[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_23[] = {
+static const llc_conn_action_t llc_busy_actions_23[] = {
 	[0] = llc_conn_ac_send_rnr_cmd_p_set_1,
 	[1] = llc_conn_ac_rst_vs,
 	[2] = llc_conn_ac_start_p_timer,
@@ -2001,13 +2001,13 @@ static struct llc_conn_state_trans llc_busy_state_trans_23 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_24a[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_24a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_24a[] = {
+static const llc_conn_action_t llc_busy_actions_24a[] = {
 	[0] = llc_conn_ac_send_rnr_cmd_p_set_1,
 	[1] = llc_conn_ac_start_p_timer,
 	[2] = llc_conn_ac_inc_retry_cnt_by_1,
@@ -2023,13 +2023,13 @@ static struct llc_conn_state_trans llc_busy_state_trans_24a = {
 };
 
 /* State transitions for LLC_CONN_EV_BUSY_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_24b[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_24b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_24b[] = {
+static const llc_conn_action_t llc_busy_actions_24b[] = {
 	[0] = llc_conn_ac_send_rnr_cmd_p_set_1,
 	[1] = llc_conn_ac_start_p_timer,
 	[2] = llc_conn_ac_inc_retry_cnt_by_1,
@@ -2045,13 +2045,13 @@ static struct llc_conn_state_trans llc_busy_state_trans_24b = {
 };
 
 /* State transitions for LLC_CONN_EV_REJ_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_25[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_25[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_25[] = {
+static const llc_conn_action_t llc_busy_actions_25[] = {
 	[0] = llc_conn_ac_send_rnr_cmd_p_set_1,
 	[1] = llc_conn_ac_start_p_timer,
 	[2] = llc_conn_ac_inc_retry_cnt_by_1,
@@ -2068,13 +2068,13 @@ static struct llc_conn_state_trans llc_busy_state_trans_25 = {
 };
 
 /* State transitions for LLC_CONN_EV_REJ_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_26[] = {
+static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_26[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_busy_actions_26[] = {
+static const llc_conn_action_t llc_busy_actions_26[] = {
 	[0] = llc_conn_ac_set_data_flag_1,
 	[1] = NULL,
 };
@@ -2155,13 +2155,13 @@ static struct llc_conn_state_trans *llc_busy_state_transitions[] = {
 
 /* LLC_CONN_STATE_REJ transitions */
 /* State transitions for LLC_CONN_EV_DATA_REQ event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_1[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_1[] = {
 	[0] = llc_conn_ev_qlfy_remote_busy_eq_0,
 	[1] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_1[] = {
+static const llc_conn_action_t llc_reject_actions_1[] = {
 	[0] = llc_conn_ac_send_i_xxx_x_set_0,
 	[1] = NULL,
 };
@@ -2174,13 +2174,13 @@ static struct llc_conn_state_trans llc_reject_state_trans_1 = {
 };
 
 /* State transitions for LLC_CONN_EV_DATA_REQ event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_2[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_2[] = {
 	[0] = llc_conn_ev_qlfy_remote_busy_eq_0,
 	[1] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_2[] = {
+static const llc_conn_action_t llc_reject_actions_2[] = {
 	[0] = llc_conn_ac_send_i_xxx_x_set_0,
 	[1] = NULL,
 };
@@ -2193,14 +2193,14 @@ static struct llc_conn_state_trans llc_reject_state_trans_2 = {
 };
 
 /* State transitions for LLC_CONN_EV_DATA_REQ event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_2_1[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_2_1[] = {
 	[0] = llc_conn_ev_qlfy_remote_busy_eq_1,
 	[1] = llc_conn_ev_qlfy_set_status_remote_busy,
 	[2] = NULL,
 };
 
 /* just one member, NULL, .bss zeroes it */
-static llc_conn_action_t llc_reject_actions_2_1[1];
+static const llc_conn_action_t llc_reject_actions_2_1[1];
 
 static struct llc_conn_state_trans llc_reject_state_trans_2_1 = {
 	.ev	       = llc_conn_ev_data_req,
@@ -2211,12 +2211,12 @@ static struct llc_conn_state_trans llc_reject_state_trans_2_1 = {
 
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_DETECTED event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_3[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_3[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_3[] = {
+static const llc_conn_action_t llc_reject_actions_3[] = {
 	[0] = llc_conn_ac_send_rnr_xxx_x_set_0,
 	[1] = llc_conn_ac_set_data_flag_2,
 	[2] = NULL,
@@ -2230,12 +2230,12 @@ static struct llc_conn_state_trans llc_reject_state_trans_3 = {
 };
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_DETECTED event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_4[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_4[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_4[] = {
+static const llc_conn_action_t llc_reject_actions_4[] = {
 	[0] = llc_conn_ac_send_rnr_xxx_x_set_0,
 	[1] = llc_conn_ac_set_data_flag_2,
 	[2] = NULL,
@@ -2249,7 +2249,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_4 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0_UNEXPD_Ns event */
-static llc_conn_action_t llc_reject_actions_5a[] = {
+static const llc_conn_action_t llc_reject_actions_5a[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_p_flag,
 	[2] = llc_conn_ac_clear_remote_busy_if_f_eq_1,
@@ -2264,7 +2264,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_5a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_0_UNEXPD_Ns event */
-static llc_conn_action_t llc_reject_actions_5b[] = {
+static const llc_conn_action_t llc_reject_actions_5b[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_p_flag,
 	[2] = llc_conn_ac_clear_remote_busy_if_f_eq_1,
@@ -2279,12 +2279,12 @@ static struct llc_conn_state_trans llc_reject_state_trans_5b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_1_UNEXPD_Ns event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_5c[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_5c[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_5c[] = {
+static const llc_conn_action_t llc_reject_actions_5c[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_p_flag,
 	[2] = llc_conn_ac_clear_remote_busy_if_f_eq_1,
@@ -2299,7 +2299,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_5c = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_1_UNEXPD_Ns event */
-static llc_conn_action_t llc_reject_actions_6[] = {
+static const llc_conn_action_t llc_reject_actions_6[] = {
 	[0] = llc_conn_ac_send_rr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = NULL,
@@ -2313,12 +2313,12 @@ static struct llc_conn_state_trans llc_reject_state_trans_6 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_X event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_7a[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_7a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_f,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_7a[] = {
+static const llc_conn_action_t llc_reject_actions_7a[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_upd_p_flag,
@@ -2338,12 +2338,12 @@ static struct llc_conn_state_trans llc_reject_state_trans_7a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_7b[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_7b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_7b[] = {
+static const llc_conn_action_t llc_reject_actions_7b[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_upd_p_flag,
@@ -2362,12 +2362,12 @@ static struct llc_conn_state_trans llc_reject_state_trans_7b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_8a[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_8a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_8a[] = {
+static const llc_conn_action_t llc_reject_actions_8a[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_send_ack_xxx_x_set_0,
@@ -2384,12 +2384,12 @@ static struct llc_conn_state_trans llc_reject_state_trans_8a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_8b[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_8b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_8b[] = {
+static const llc_conn_action_t llc_reject_actions_8b[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_send_ack_xxx_x_set_0,
@@ -2406,7 +2406,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_8b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_reject_actions_9[] = {
+static const llc_conn_action_t llc_reject_actions_9[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_send_ack_rsp_f_set_1,
@@ -2423,7 +2423,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_9 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_reject_actions_10a[] = {
+static const llc_conn_action_t llc_reject_actions_10a[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -2438,7 +2438,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_10a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_reject_actions_10b[] = {
+static const llc_conn_action_t llc_reject_actions_10b[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -2453,12 +2453,12 @@ static struct llc_conn_state_trans llc_reject_state_trans_10b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_RSP_Fbit_SET_1 event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_10c[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_10c[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_10c[] = {
+static const llc_conn_action_t llc_reject_actions_10c[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -2473,7 +2473,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_10c = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_reject_actions_11[] = {
+static const llc_conn_action_t llc_reject_actions_11[] = {
 	[0] = llc_conn_ac_send_ack_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -2488,7 +2488,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_11 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_reject_actions_12a[] = {
+static const llc_conn_action_t llc_reject_actions_12a[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -2503,7 +2503,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_12a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_reject_actions_12b[] = {
+static const llc_conn_action_t llc_reject_actions_12b[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -2518,12 +2518,12 @@ static struct llc_conn_state_trans llc_reject_state_trans_12b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_1 event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_12c[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_12c[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_12c[] = {
+static const llc_conn_action_t llc_reject_actions_12c[] = {
 	[0] = llc_conn_ac_upd_p_flag,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -2538,7 +2538,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_12c = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_reject_actions_13[] = {
+static const llc_conn_action_t llc_reject_actions_13[] = {
 	[0] = llc_conn_ac_send_rr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -2553,12 +2553,12 @@ static struct llc_conn_state_trans llc_reject_state_trans_13 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_14a[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_14a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_14a[] = {
+static const llc_conn_action_t llc_reject_actions_14a[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_p_flag,
@@ -2575,12 +2575,12 @@ static struct llc_conn_state_trans llc_reject_state_trans_14a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_X event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_14b[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_14b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_f,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_14b[] = {
+static const llc_conn_action_t llc_reject_actions_14b[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_p_flag,
@@ -2597,12 +2597,12 @@ static struct llc_conn_state_trans llc_reject_state_trans_14b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_15a[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_15a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_15a[] = {
+static const llc_conn_action_t llc_reject_actions_15a[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_resend_i_xxx_x_set_0,
@@ -2618,12 +2618,12 @@ static struct llc_conn_state_trans llc_reject_state_trans_15a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_0 event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_15b[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_15b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_1,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_15b[] = {
+static const llc_conn_action_t llc_reject_actions_15b[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_resend_i_xxx_x_set_0,
@@ -2639,7 +2639,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_15b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_reject_actions_16[] = {
+static const llc_conn_action_t llc_reject_actions_16[] = {
 	[0] = llc_conn_ac_set_vs_nr,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_resend_i_rsp_f_set_1,
@@ -2655,12 +2655,12 @@ static struct llc_conn_state_trans llc_reject_state_trans_16 = {
 };
 
 /* State transitions for LLC_CONN_EV_INIT_P_F_CYCLE event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_17[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_17[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_17[] = {
+static const llc_conn_action_t llc_reject_actions_17[] = {
 	[0] = llc_conn_ac_send_rr_cmd_p_set_1,
 	[1] = llc_conn_ac_start_p_timer,
 	[2] = NULL,
@@ -2674,13 +2674,13 @@ static struct llc_conn_state_trans llc_reject_state_trans_17 = {
 };
 
 /* State transitions for LLC_CONN_EV_REJ_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_18[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_18[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_18[] = {
+static const llc_conn_action_t llc_reject_actions_18[] = {
 	[0] = llc_conn_ac_send_rej_cmd_p_set_1,
 	[1] = llc_conn_ac_start_p_timer,
 	[2] = llc_conn_ac_start_rej_timer,
@@ -2696,12 +2696,12 @@ static struct llc_conn_state_trans llc_reject_state_trans_18 = {
 };
 
 /* State transitions for LLC_CONN_EV_P_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_19[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_19[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_19[] = {
+static const llc_conn_action_t llc_reject_actions_19[] = {
 	[0] = llc_conn_ac_send_rr_cmd_p_set_1,
 	[1] = llc_conn_ac_start_p_timer,
 	[2] = llc_conn_ac_start_rej_timer,
@@ -2718,13 +2718,13 @@ static struct llc_conn_state_trans llc_reject_state_trans_19 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_20a[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_20a[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_20a[] = {
+static const llc_conn_action_t llc_reject_actions_20a[] = {
 	[0] = llc_conn_ac_send_rr_cmd_p_set_1,
 	[1] = llc_conn_ac_start_p_timer,
 	[2] = llc_conn_ac_start_rej_timer,
@@ -2741,13 +2741,13 @@ static struct llc_conn_state_trans llc_reject_state_trans_20a = {
 };
 
 /* State transitions for LLC_CONN_EV_BUSY_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_20b[] = {
+static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_20b[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_0,
 	[1] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_reject_actions_20b[] = {
+static const llc_conn_action_t llc_reject_actions_20b[] = {
 	[0] = llc_conn_ac_send_rr_cmd_p_set_1,
 	[1] = llc_conn_ac_start_p_timer,
 	[2] = llc_conn_ac_start_rej_timer,
@@ -2826,13 +2826,13 @@ static struct llc_conn_state_trans *llc_reject_state_transitions[] = {
 
 /* LLC_CONN_STATE_AWAIT transitions */
 /* State transitions for LLC_CONN_EV_DATA_REQ event */
-static llc_conn_ev_qfyr_t llc_await_ev_qfyrs_1_0[] = {
+static const llc_conn_ev_qfyr_t llc_await_ev_qfyrs_1_0[] = {
 	[0] = llc_conn_ev_qlfy_set_status_refuse,
 	[1] = NULL,
 };
 
 /* just one member, NULL, .bss zeroes it */
-static llc_conn_action_t llc_await_actions_1_0[1];
+static const llc_conn_action_t llc_await_actions_1_0[1];
 
 static struct llc_conn_state_trans llc_await_state_trans_1_0 = {
 	.ev	       = llc_conn_ev_data_req,
@@ -2842,7 +2842,7 @@ static struct llc_conn_state_trans llc_await_state_trans_1_0 = {
 };
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_DETECTED event */
-static llc_conn_action_t llc_await_actions_1[] = {
+static const llc_conn_action_t llc_await_actions_1[] = {
 	[0] = llc_conn_ac_send_rnr_xxx_x_set_0,
 	[1] = llc_conn_ac_set_data_flag_0,
 	[2] = NULL,
@@ -2856,7 +2856,7 @@ static struct llc_conn_state_trans llc_await_state_trans_1 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_1_UNEXPD_Ns event */
-static llc_conn_action_t llc_await_actions_2[] = {
+static const llc_conn_action_t llc_await_actions_2[] = {
 	[0] = llc_conn_ac_send_rej_xxx_x_set_0,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -2875,7 +2875,7 @@ static struct llc_conn_state_trans llc_await_state_trans_2 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0_UNEXPD_Ns event */
-static llc_conn_action_t llc_await_actions_3a[] = {
+static const llc_conn_action_t llc_await_actions_3a[] = {
 	[0] = llc_conn_ac_send_rej_xxx_x_set_0,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -2891,7 +2891,7 @@ static struct llc_conn_state_trans llc_await_state_trans_3a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_0_UNEXPD_Ns event */
-static llc_conn_action_t llc_await_actions_3b[] = {
+static const llc_conn_action_t llc_await_actions_3b[] = {
 	[0] = llc_conn_ac_send_rej_xxx_x_set_0,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -2907,7 +2907,7 @@ static struct llc_conn_state_trans llc_await_state_trans_3b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_1_UNEXPD_Ns event */
-static llc_conn_action_t llc_await_actions_4[] = {
+static const llc_conn_action_t llc_await_actions_4[] = {
 	[0] = llc_conn_ac_send_rej_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -2924,7 +2924,7 @@ static struct llc_conn_state_trans llc_await_state_trans_4 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_1 event */
-static llc_conn_action_t llc_await_actions_5[] = {
+static const llc_conn_action_t llc_await_actions_5[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_stop_p_timer,
@@ -2943,7 +2943,7 @@ static struct llc_conn_state_trans llc_await_state_trans_5 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_await_actions_6a[] = {
+static const llc_conn_action_t llc_await_actions_6a[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_send_rr_xxx_x_set_0,
@@ -2960,7 +2960,7 @@ static struct llc_conn_state_trans llc_await_state_trans_6a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_await_actions_6b[] = {
+static const llc_conn_action_t llc_await_actions_6b[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_send_rr_xxx_x_set_0,
@@ -2977,7 +2977,7 @@ static struct llc_conn_state_trans llc_await_state_trans_6b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_await_actions_7[] = {
+static const llc_conn_action_t llc_await_actions_7[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_send_rr_rsp_f_set_1,
@@ -2994,7 +2994,7 @@ static struct llc_conn_state_trans llc_await_state_trans_7 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_RSP_Fbit_SET_1 event */
-static llc_conn_action_t llc_await_actions_8a[] = {
+static const llc_conn_action_t llc_await_actions_8a[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_stop_p_timer,
@@ -3011,7 +3011,7 @@ static struct llc_conn_state_trans llc_await_state_trans_8a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_1 event */
-static llc_conn_action_t llc_await_actions_8b[] = {
+static const llc_conn_action_t llc_await_actions_8b[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_stop_p_timer,
@@ -3028,7 +3028,7 @@ static struct llc_conn_state_trans llc_await_state_trans_8b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_await_actions_9a[] = {
+static const llc_conn_action_t llc_await_actions_9a[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -3043,7 +3043,7 @@ static struct llc_conn_state_trans llc_await_state_trans_9a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_await_actions_9b[] = {
+static const llc_conn_action_t llc_await_actions_9b[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -3058,7 +3058,7 @@ static struct llc_conn_state_trans llc_await_state_trans_9b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_await_actions_9c[] = {
+static const llc_conn_action_t llc_await_actions_9c[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -3073,7 +3073,7 @@ static struct llc_conn_state_trans llc_await_state_trans_9c = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_await_actions_9d[] = {
+static const llc_conn_action_t llc_await_actions_9d[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -3088,7 +3088,7 @@ static struct llc_conn_state_trans llc_await_state_trans_9d = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_await_actions_10a[] = {
+static const llc_conn_action_t llc_await_actions_10a[] = {
 	[0] = llc_conn_ac_send_rr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -3104,7 +3104,7 @@ static struct llc_conn_state_trans llc_await_state_trans_10a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_await_actions_10b[] = {
+static const llc_conn_action_t llc_await_actions_10b[] = {
 	[0] = llc_conn_ac_send_rr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -3120,7 +3120,7 @@ static struct llc_conn_state_trans llc_await_state_trans_10b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_1 event */
-static llc_conn_action_t llc_await_actions_11[] = {
+static const llc_conn_action_t llc_await_actions_11[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_stop_p_timer,
@@ -3136,7 +3136,7 @@ static struct llc_conn_state_trans llc_await_state_trans_11 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_await_actions_12a[] = {
+static const llc_conn_action_t llc_await_actions_12a[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -3151,7 +3151,7 @@ static struct llc_conn_state_trans llc_await_state_trans_12a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_await_actions_12b[] = {
+static const llc_conn_action_t llc_await_actions_12b[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -3166,7 +3166,7 @@ static struct llc_conn_state_trans llc_await_state_trans_12b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_await_actions_13[] = {
+static const llc_conn_action_t llc_await_actions_13[] = {
 	[0] = llc_conn_ac_send_rr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -3182,12 +3182,12 @@ static struct llc_conn_state_trans llc_await_state_trans_13 = {
 };
 
 /* State transitions for LLC_CONN_EV_P_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_await_ev_qfyrs_14[] = {
+static const llc_conn_ev_qfyr_t llc_await_ev_qfyrs_14[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_await_actions_14[] = {
+static const llc_conn_action_t llc_await_actions_14[] = {
 	[0] = llc_conn_ac_send_rr_cmd_p_set_1,
 	[1] = llc_conn_ac_start_p_timer,
 	[2] = llc_conn_ac_inc_retry_cnt_by_1,
@@ -3255,13 +3255,13 @@ static struct llc_conn_state_trans *llc_await_state_transitions[] = {
 
 /* LLC_CONN_STATE_AWAIT_BUSY transitions */
 /* State transitions for LLC_CONN_EV_DATA_CONN_REQ event */
-static llc_conn_ev_qfyr_t llc_await_busy_ev_qfyrs_1_0[] = {
+static const llc_conn_ev_qfyr_t llc_await_busy_ev_qfyrs_1_0[] = {
 	[0] = llc_conn_ev_qlfy_set_status_refuse,
 	[1] = NULL,
 };
 
 /* just one member, NULL, .bss zeroes it */
-static llc_conn_action_t llc_await_busy_actions_1_0[1];
+static const llc_conn_action_t llc_await_busy_actions_1_0[1];
 
 static struct llc_conn_state_trans llc_await_busy_state_trans_1_0 = {
 	.ev	       = llc_conn_ev_data_req,
@@ -3271,12 +3271,12 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_1_0 = {
 };
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_CLEARED event */
-static llc_conn_ev_qfyr_t llc_await_busy_ev_qfyrs_1[] = {
+static const llc_conn_ev_qfyr_t llc_await_busy_ev_qfyrs_1[] = {
 	[0] = llc_conn_ev_qlfy_data_flag_eq_1,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_await_busy_actions_1[] = {
+static const llc_conn_action_t llc_await_busy_actions_1[] = {
 	[0] = llc_conn_ac_send_rej_xxx_x_set_0,
 	[1] = llc_conn_ac_start_rej_timer,
 	[2] = NULL,
@@ -3290,12 +3290,12 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_1 = {
 };
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_CLEARED event */
-static llc_conn_ev_qfyr_t llc_await_busy_ev_qfyrs_2[] = {
+static const llc_conn_ev_qfyr_t llc_await_busy_ev_qfyrs_2[] = {
 	[0] = llc_conn_ev_qlfy_data_flag_eq_0,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_await_busy_actions_2[] = {
+static const llc_conn_action_t llc_await_busy_actions_2[] = {
 	[0] = llc_conn_ac_send_rr_xxx_x_set_0,
 	[1] = NULL,
 };
@@ -3308,12 +3308,12 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_2 = {
 };
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_CLEARED event */
-static llc_conn_ev_qfyr_t llc_await_busy_ev_qfyrs_3[] = {
+static const llc_conn_ev_qfyr_t llc_await_busy_ev_qfyrs_3[] = {
 	[0] = llc_conn_ev_qlfy_data_flag_eq_2,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_await_busy_actions_3[] = {
+static const llc_conn_action_t llc_await_busy_actions_3[] = {
 	[0] = llc_conn_ac_send_rr_xxx_x_set_0,
 	[1] = NULL,
 };
@@ -3326,7 +3326,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_3 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_1_UNEXPD_Ns event */
-static llc_conn_action_t llc_await_busy_actions_4[] = {
+static const llc_conn_action_t llc_await_busy_actions_4[] = {
 	[0] = llc_conn_ac_opt_send_rnr_xxx_x_set_0,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -3345,7 +3345,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_4 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0_UNEXPD_Ns event */
-static llc_conn_action_t llc_await_busy_actions_5a[] = {
+static const llc_conn_action_t llc_await_busy_actions_5a[] = {
 	[0] = llc_conn_ac_opt_send_rnr_xxx_x_set_0,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -3361,7 +3361,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_5a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_0_UNEXPD_Ns event */
-static llc_conn_action_t llc_await_busy_actions_5b[] = {
+static const llc_conn_action_t llc_await_busy_actions_5b[] = {
 	[0] = llc_conn_ac_opt_send_rnr_xxx_x_set_0,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -3377,7 +3377,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_5b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_1_UNEXPD_Ns event */
-static llc_conn_action_t llc_await_busy_actions_6[] = {
+static const llc_conn_action_t llc_await_busy_actions_6[] = {
 	[0] = llc_conn_ac_send_rnr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -3393,7 +3393,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_6 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_1 event */
-static llc_conn_action_t llc_await_busy_actions_7[] = {
+static const llc_conn_action_t llc_await_busy_actions_7[] = {
 	[0] = llc_conn_ac_opt_send_rnr_xxx_x_set_0,
 	[1] = llc_conn_ac_inc_vr_by_1,
 	[2] = llc_conn_ac_data_ind,
@@ -3414,7 +3414,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_7 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_await_busy_actions_8a[] = {
+static const llc_conn_action_t llc_await_busy_actions_8a[] = {
 	[0] = llc_conn_ac_opt_send_rnr_xxx_x_set_0,
 	[1] = llc_conn_ac_inc_vr_by_1,
 	[2] = llc_conn_ac_data_ind,
@@ -3432,7 +3432,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_8a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_await_busy_actions_8b[] = {
+static const llc_conn_action_t llc_await_busy_actions_8b[] = {
 	[0] = llc_conn_ac_opt_send_rnr_xxx_x_set_0,
 	[1] = llc_conn_ac_inc_vr_by_1,
 	[2] = llc_conn_ac_data_ind,
@@ -3450,7 +3450,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_8b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_await_busy_actions_9[] = {
+static const llc_conn_action_t llc_await_busy_actions_9[] = {
 	[0] = llc_conn_ac_send_rnr_rsp_f_set_1,
 	[1] = llc_conn_ac_inc_vr_by_1,
 	[2] = llc_conn_ac_data_ind,
@@ -3468,7 +3468,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_9 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_RSP_Fbit_SET_1 event */
-static llc_conn_action_t llc_await_busy_actions_10a[] = {
+static const llc_conn_action_t llc_await_busy_actions_10a[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_stop_p_timer,
@@ -3485,7 +3485,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_10a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_1 event */
-static llc_conn_action_t llc_await_busy_actions_10b[] = {
+static const llc_conn_action_t llc_await_busy_actions_10b[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_stop_p_timer,
@@ -3502,7 +3502,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_10b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_await_busy_actions_11a[] = {
+static const llc_conn_action_t llc_await_busy_actions_11a[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -3517,7 +3517,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_11a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_await_busy_actions_11b[] = {
+static const llc_conn_action_t llc_await_busy_actions_11b[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -3532,7 +3532,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_11b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_await_busy_actions_11c[] = {
+static const llc_conn_action_t llc_await_busy_actions_11c[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -3547,7 +3547,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_11c = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_await_busy_actions_11d[] = {
+static const llc_conn_action_t llc_await_busy_actions_11d[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -3562,7 +3562,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_11d = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_await_busy_actions_12a[] = {
+static const llc_conn_action_t llc_await_busy_actions_12a[] = {
 	[0] = llc_conn_ac_send_rnr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -3578,7 +3578,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_12a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_await_busy_actions_12b[] = {
+static const llc_conn_action_t llc_await_busy_actions_12b[] = {
 	[0] = llc_conn_ac_send_rnr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -3594,7 +3594,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_12b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_1 event */
-static llc_conn_action_t llc_await_busy_actions_13[] = {
+static const llc_conn_action_t llc_await_busy_actions_13[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_stop_p_timer,
@@ -3610,7 +3610,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_13 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_await_busy_actions_14a[] = {
+static const llc_conn_action_t llc_await_busy_actions_14a[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -3625,7 +3625,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_14a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_await_busy_actions_14b[] = {
+static const llc_conn_action_t llc_await_busy_actions_14b[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -3640,7 +3640,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_14b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_await_busy_actions_15[] = {
+static const llc_conn_action_t llc_await_busy_actions_15[] = {
 	[0] = llc_conn_ac_send_rnr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -3656,12 +3656,12 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_15 = {
 };
 
 /* State transitions for LLC_CONN_EV_P_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_await_busy_ev_qfyrs_16[] = {
+static const llc_conn_ev_qfyr_t llc_await_busy_ev_qfyrs_16[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_await_busy_actions_16[] = {
+static const llc_conn_action_t llc_await_busy_actions_16[] = {
 	[0] = llc_conn_ac_send_rnr_cmd_p_set_1,
 	[1] = llc_conn_ac_start_p_timer,
 	[2] = llc_conn_ac_inc_retry_cnt_by_1,
@@ -3731,13 +3731,13 @@ static struct llc_conn_state_trans *llc_await_busy_state_transitions[] = {
 
 /* ----------------- LLC_CONN_STATE_AWAIT_REJ transitions --------------- */
 /* State transitions for LLC_CONN_EV_DATA_CONN_REQ event */
-static llc_conn_ev_qfyr_t llc_await_reject_ev_qfyrs_1_0[] = {
+static const llc_conn_ev_qfyr_t llc_await_reject_ev_qfyrs_1_0[] = {
 	[0] = llc_conn_ev_qlfy_set_status_refuse,
 	[1] = NULL,
 };
 
 /* just one member, NULL, .bss zeroes it */
-static llc_conn_action_t llc_await_reject_actions_1_0[1];
+static const llc_conn_action_t llc_await_reject_actions_1_0[1];
 
 static struct llc_conn_state_trans llc_await_reject_state_trans_1_0 = {
 	.ev	       = llc_conn_ev_data_req,
@@ -3747,7 +3747,7 @@ static struct llc_conn_state_trans llc_await_reject_state_trans_1_0 = {
 };
 
 /* State transitions for LLC_CONN_EV_LOCAL_BUSY_DETECTED event */
-static llc_conn_action_t llc_await_rejct_actions_1[] = {
+static const llc_conn_action_t llc_await_rejct_actions_1[] = {
 	[0] = llc_conn_ac_send_rnr_xxx_x_set_0,
 	[1] = llc_conn_ac_set_data_flag_2,
 	[2] = NULL
@@ -3761,7 +3761,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_1 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0_UNEXPD_Ns event */
-static llc_conn_action_t llc_await_rejct_actions_2a[] = {
+static const llc_conn_action_t llc_await_rejct_actions_2a[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = NULL
@@ -3775,7 +3775,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_2a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_0_UNEXPD_Ns event */
-static llc_conn_action_t llc_await_rejct_actions_2b[] = {
+static const llc_conn_action_t llc_await_rejct_actions_2b[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = NULL
@@ -3789,7 +3789,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_2b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_1_UNEXPD_Ns event */
-static llc_conn_action_t llc_await_rejct_actions_3[] = {
+static const llc_conn_action_t llc_await_rejct_actions_3[] = {
 	[0] = llc_conn_ac_send_rr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -3804,7 +3804,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_3 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_1 event */
-static llc_conn_action_t llc_await_rejct_actions_4[] = {
+static const llc_conn_action_t llc_await_rejct_actions_4[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_stop_p_timer,
@@ -3824,7 +3824,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_4 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_await_rejct_actions_5a[] = {
+static const llc_conn_action_t llc_await_rejct_actions_5a[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_send_rr_xxx_x_set_0,
@@ -3842,7 +3842,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_5a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_await_rejct_actions_5b[] = {
+static const llc_conn_action_t llc_await_rejct_actions_5b[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_send_rr_xxx_x_set_0,
@@ -3860,7 +3860,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_5b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_await_rejct_actions_6[] = {
+static const llc_conn_action_t llc_await_rejct_actions_6[] = {
 	[0] = llc_conn_ac_inc_vr_by_1,
 	[1] = llc_conn_ac_data_ind,
 	[2] = llc_conn_ac_send_rr_rsp_f_set_1,
@@ -3878,7 +3878,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_6 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_RSP_Fbit_SET_1 event */
-static llc_conn_action_t llc_await_rejct_actions_7a[] = {
+static const llc_conn_action_t llc_await_rejct_actions_7a[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_stop_p_timer,
@@ -3895,7 +3895,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_7a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_1 event */
-static llc_conn_action_t llc_await_rejct_actions_7b[] = {
+static const llc_conn_action_t llc_await_rejct_actions_7b[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_stop_p_timer,
@@ -3912,7 +3912,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_7b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_I_RSP_Fbit_SET_1_UNEXPD_Ns event */
-static llc_conn_action_t llc_await_rejct_actions_7c[] = {
+static const llc_conn_action_t llc_await_rejct_actions_7c[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_stop_p_timer,
@@ -3929,7 +3929,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_7c = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_await_rejct_actions_8a[] = {
+static const llc_conn_action_t llc_await_rejct_actions_8a[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -3944,7 +3944,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_8a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_await_rejct_actions_8b[] = {
+static const llc_conn_action_t llc_await_rejct_actions_8b[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -3959,7 +3959,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_8b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_await_rejct_actions_8c[] = {
+static const llc_conn_action_t llc_await_rejct_actions_8c[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -3974,7 +3974,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_8c = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_await_rejct_actions_8d[] = {
+static const llc_conn_action_t llc_await_rejct_actions_8d[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_clear_remote_busy,
@@ -3989,7 +3989,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_8d = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RR_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_await_rejct_actions_9a[] = {
+static const llc_conn_action_t llc_await_rejct_actions_9a[] = {
 	[0] = llc_conn_ac_send_rr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -4005,7 +4005,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_9a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_await_rejct_actions_9b[] = {
+static const llc_conn_action_t llc_await_rejct_actions_9b[] = {
 	[0] = llc_conn_ac_send_rr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -4021,7 +4021,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_9b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_1 event */
-static llc_conn_action_t llc_await_rejct_actions_10[] = {
+static const llc_conn_action_t llc_await_rejct_actions_10[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_stop_p_timer,
@@ -4037,7 +4037,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_10 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_0 event */
-static llc_conn_action_t llc_await_rejct_actions_11a[] = {
+static const llc_conn_action_t llc_await_rejct_actions_11a[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -4052,7 +4052,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_11a = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_0 event */
-static llc_conn_action_t llc_await_rejct_actions_11b[] = {
+static const llc_conn_action_t llc_await_rejct_actions_11b[] = {
 	[0] = llc_conn_ac_upd_nr_received,
 	[1] = llc_conn_ac_upd_vs,
 	[2] = llc_conn_ac_set_remote_busy,
@@ -4067,7 +4067,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_11b = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_1 event */
-static llc_conn_action_t llc_await_rejct_actions_12[] = {
+static const llc_conn_action_t llc_await_rejct_actions_12[] = {
 	[0] = llc_conn_ac_send_rr_rsp_f_set_1,
 	[1] = llc_conn_ac_upd_nr_received,
 	[2] = llc_conn_ac_upd_vs,
@@ -4083,12 +4083,12 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_12 = {
 };
 
 /* State transitions for LLC_CONN_EV_P_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_await_rejct_ev_qfyrs_13[] = {
+static const llc_conn_ev_qfyr_t llc_await_rejct_ev_qfyrs_13[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_await_rejct_actions_13[] = {
+static const llc_conn_action_t llc_await_rejct_actions_13[] = {
 	[0] = llc_conn_ac_send_rej_cmd_p_set_1,
 	[1] = llc_conn_ac_stop_p_timer,
 	[2] = llc_conn_ac_inc_retry_cnt_by_1,
@@ -4157,13 +4157,13 @@ static struct llc_conn_state_trans *llc_await_rejct_state_transitions[] = {
 /* LLC_CONN_STATE_D_CONN transitions */
 /* State transitions for LLC_CONN_EV_RX_SABME_CMD_Pbit_SET_X event,
  * cause_flag = 1 */
-static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_1[] = {
+static const llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_1[] = {
 	[0] = llc_conn_ev_qlfy_cause_flag_eq_1,
 	[1] = llc_conn_ev_qlfy_set_status_conflict,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_d_conn_actions_1[] = {
+static const llc_conn_action_t llc_d_conn_actions_1[] = {
 	[0] = llc_conn_ac_send_dm_rsp_f_set_p,
 	[1] = llc_conn_ac_stop_ack_timer,
 	[2] = llc_conn_ac_disc_confirm,
@@ -4181,13 +4181,13 @@ static struct llc_conn_state_trans llc_d_conn_state_trans_1 = {
 /* State transitions for LLC_CONN_EV_RX_SABME_CMD_Pbit_SET_X event,
  * cause_flag = 0
  */
-static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_1_1[] = {
+static const llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_1_1[] = {
 	[0] = llc_conn_ev_qlfy_cause_flag_eq_0,
 	[1] = llc_conn_ev_qlfy_set_status_conflict,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_d_conn_actions_1_1[] = {
+static const llc_conn_action_t llc_d_conn_actions_1_1[] = {
 	[0] = llc_conn_ac_send_dm_rsp_f_set_p,
 	[1] = llc_conn_ac_stop_ack_timer,
 	[2] = llc_conn_disc,
@@ -4204,14 +4204,14 @@ static struct llc_conn_state_trans llc_d_conn_state_trans_1_1 = {
 /* State transitions for LLC_CONN_EV_RX_UA_RSP_Fbit_SET_X event,
  * cause_flag = 1
  */
-static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_2[] = {
+static const llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_2[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_f,
 	[1] = llc_conn_ev_qlfy_cause_flag_eq_1,
 	[2] = llc_conn_ev_qlfy_set_status_disc,
 	[3] = NULL,
 };
 
-static llc_conn_action_t llc_d_conn_actions_2[] = {
+static const llc_conn_action_t llc_d_conn_actions_2[] = {
 	[0] = llc_conn_ac_stop_ack_timer,
 	[1] = llc_conn_ac_disc_confirm,
 	[2] = llc_conn_disc,
@@ -4228,14 +4228,14 @@ static struct llc_conn_state_trans llc_d_conn_state_trans_2 = {
 /* State transitions for LLC_CONN_EV_RX_UA_RSP_Fbit_SET_X event,
  * cause_flag = 0
  */
-static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_2_1[] = {
+static const llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_2_1[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_f,
 	[1] = llc_conn_ev_qlfy_cause_flag_eq_0,
 	[2] = llc_conn_ev_qlfy_set_status_disc,
 	[3] = NULL,
 };
 
-static llc_conn_action_t llc_d_conn_actions_2_1[] = {
+static const llc_conn_action_t llc_d_conn_actions_2_1[] = {
 	[0] = llc_conn_ac_stop_ack_timer,
 	[1] = llc_conn_disc,
 	[2] = NULL,
@@ -4249,7 +4249,7 @@ static struct llc_conn_state_trans llc_d_conn_state_trans_2_1 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_DISC_CMD_Pbit_SET_X event */
-static llc_conn_action_t llc_d_conn_actions_3[] = {
+static const llc_conn_action_t llc_d_conn_actions_3[] = {
 	[0] = llc_conn_ac_send_ua_rsp_f_set_p,
 	[1] = NULL,
 };
@@ -4264,13 +4264,13 @@ static struct llc_conn_state_trans llc_d_conn_state_trans_3 = {
 /* State transitions for LLC_CONN_EV_RX_DM_RSP_Fbit_SET_X event,
  * cause_flag = 1
  */
-static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_4[] = {
+static const llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_4[] = {
 	[0] = llc_conn_ev_qlfy_cause_flag_eq_1,
 	[1] = llc_conn_ev_qlfy_set_status_disc,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_d_conn_actions_4[] = {
+static const llc_conn_action_t llc_d_conn_actions_4[] = {
 	[0] = llc_conn_ac_stop_ack_timer,
 	[1] = llc_conn_ac_disc_confirm,
 	[2] = llc_conn_disc,
@@ -4287,13 +4287,13 @@ static struct llc_conn_state_trans llc_d_conn_state_trans_4 = {
 /* State transitions for LLC_CONN_EV_RX_DM_RSP_Fbit_SET_X event,
  * cause_flag = 0
  */
-static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_4_1[] = {
+static const llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_4_1[] = {
 	[0] = llc_conn_ev_qlfy_cause_flag_eq_0,
 	[1] = llc_conn_ev_qlfy_set_status_disc,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_d_conn_actions_4_1[] = {
+static const llc_conn_action_t llc_d_conn_actions_4_1[] = {
 	[0] = llc_conn_ac_stop_ack_timer,
 	[1] = llc_conn_disc,
 	[2] = NULL,
@@ -4310,13 +4310,13 @@ static struct llc_conn_state_trans llc_d_conn_state_trans_4_1 = {
  * State transition for
  * LLC_CONN_EV_DATA_CONN_REQ event
  */
-static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_5[] = {
+static const llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_5[] = {
 	[0] = llc_conn_ev_qlfy_set_status_refuse,
 	[1] = NULL,
 };
 
 /* just one member, NULL, .bss zeroes it */
-static llc_conn_action_t llc_d_conn_actions_5[1];
+static const llc_conn_action_t llc_d_conn_actions_5[1];
 
 static struct llc_conn_state_trans llc_d_conn_state_trans_5 = {
 	.ev	       = llc_conn_ev_data_req,
@@ -4326,12 +4326,12 @@ static struct llc_conn_state_trans llc_d_conn_state_trans_5 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_6[] = {
+static const llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_6[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_d_conn_actions_6[] = {
+static const llc_conn_action_t llc_d_conn_actions_6[] = {
 	[0] = llc_conn_ac_send_disc_cmd_p_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_inc_retry_cnt_by_1,
@@ -4346,14 +4346,14 @@ static struct llc_conn_state_trans llc_d_conn_state_trans_6 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event, cause_flag = 1 */
-static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_7[] = {
+static const llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_7[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_gte_n2,
 	[1] = llc_conn_ev_qlfy_cause_flag_eq_1,
 	[2] = llc_conn_ev_qlfy_set_status_failed,
 	[3] = NULL,
 };
 
-static llc_conn_action_t llc_d_conn_actions_7[] = {
+static const llc_conn_action_t llc_d_conn_actions_7[] = {
 	[0] = llc_conn_ac_disc_confirm,
 	[1] = llc_conn_disc,
 	[2] = NULL,
@@ -4367,14 +4367,14 @@ static struct llc_conn_state_trans llc_d_conn_state_trans_7 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event, cause_flag = 0 */
-static llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_8[] = {
+static const llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_8[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_gte_n2,
 	[1] = llc_conn_ev_qlfy_cause_flag_eq_0,
 	[2] = llc_conn_ev_qlfy_set_status_failed,
 	[3] = NULL,
 };
 
-static llc_conn_action_t llc_d_conn_actions_8[] = {
+static const llc_conn_action_t llc_d_conn_actions_8[] = {
 	[0] = llc_conn_disc,
 	[1] = NULL,
 };
@@ -4411,7 +4411,7 @@ static struct llc_conn_state_trans *llc_d_conn_state_transitions[] = {
 
 /* LLC_CONN_STATE_RESET transitions */
 /* State transitions for LLC_CONN_EV_RX_SABME_CMD_Pbit_SET_X event */
-static llc_conn_action_t llc_rst_actions_1[] = {
+static const llc_conn_action_t llc_rst_actions_1[] = {
 	[0] = llc_conn_ac_set_vs_0,
 	[1] = llc_conn_ac_set_vr_0,
 	[2] = llc_conn_ac_set_s_flag_1,
@@ -4429,14 +4429,14 @@ static struct llc_conn_state_trans llc_rst_state_trans_1 = {
 /* State transitions for LLC_CONN_EV_RX_UA_RSP_Fbit_SET_X event,
  * cause_flag = 1
  */
-static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_2[] = {
+static const llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_2[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_f,
 	[1] = llc_conn_ev_qlfy_cause_flag_eq_1,
 	[2] = llc_conn_ev_qlfy_set_status_conn,
 	[3] = NULL,
 };
 
-static llc_conn_action_t llc_rst_actions_2[] = {
+static const llc_conn_action_t llc_rst_actions_2[] = {
 	[0] = llc_conn_ac_stop_ack_timer,
 	[1] = llc_conn_ac_set_vs_0,
 	[2] = llc_conn_ac_set_vr_0,
@@ -4457,14 +4457,14 @@ static struct llc_conn_state_trans llc_rst_state_trans_2 = {
 /* State transitions for LLC_CONN_EV_RX_UA_RSP_Fbit_SET_X event,
  * cause_flag = 0
  */
-static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_2_1[] = {
+static const llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_2_1[] = {
 	[0] = llc_conn_ev_qlfy_p_flag_eq_f,
 	[1] = llc_conn_ev_qlfy_cause_flag_eq_0,
 	[2] = llc_conn_ev_qlfy_set_status_rst_done,
 	[3] = NULL,
 };
 
-static llc_conn_action_t llc_rst_actions_2_1[] = {
+static const llc_conn_action_t llc_rst_actions_2_1[] = {
 	[0] = llc_conn_ac_stop_ack_timer,
 	[1] = llc_conn_ac_set_vs_0,
 	[2] = llc_conn_ac_set_vr_0,
@@ -4483,13 +4483,13 @@ static struct llc_conn_state_trans llc_rst_state_trans_2_1 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_3[] = {
+static const llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_3[] = {
 	[0] = llc_conn_ev_qlfy_s_flag_eq_1,
 	[1] = llc_conn_ev_qlfy_set_status_rst_done,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_rst_actions_3[] = {
+static const llc_conn_action_t llc_rst_actions_3[] = {
 	[0] = llc_conn_ac_set_p_flag_0,
 	[1] = llc_conn_ac_set_remote_busy_0,
 	[2] = NULL,
@@ -4505,12 +4505,12 @@ static struct llc_conn_state_trans llc_rst_state_trans_3 = {
 /* State transitions for LLC_CONN_EV_RX_DISC_CMD_Pbit_SET_X event,
  * cause_flag = 1
  */
-static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_4[] = {
+static const llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_4[] = {
 	[0] = llc_conn_ev_qlfy_cause_flag_eq_1,
 	[1] = llc_conn_ev_qlfy_set_status_disc,
 	[2] = NULL,
 };
-static llc_conn_action_t llc_rst_actions_4[] = {
+static const llc_conn_action_t llc_rst_actions_4[] = {
 	[0] = llc_conn_ac_send_dm_rsp_f_set_p,
 	[1] = llc_conn_ac_disc_ind,
 	[2] = llc_conn_ac_stop_ack_timer,
@@ -4528,13 +4528,13 @@ static struct llc_conn_state_trans llc_rst_state_trans_4 = {
 /* State transitions for LLC_CONN_EV_RX_DISC_CMD_Pbit_SET_X event,
  * cause_flag = 0
  */
-static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_4_1[] = {
+static const llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_4_1[] = {
 	[0] = llc_conn_ev_qlfy_cause_flag_eq_0,
 	[1] = llc_conn_ev_qlfy_set_status_refuse,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_rst_actions_4_1[] = {
+static const llc_conn_action_t llc_rst_actions_4_1[] = {
 	[0] = llc_conn_ac_send_dm_rsp_f_set_p,
 	[1] = llc_conn_ac_stop_ack_timer,
 	[2] = llc_conn_disc,
@@ -4551,13 +4551,13 @@ static struct llc_conn_state_trans llc_rst_state_trans_4_1 = {
 /* State transitions for LLC_CONN_EV_RX_DM_RSP_Fbit_SET_X event,
  * cause_flag = 1
  */
-static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_5[] = {
+static const llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_5[] = {
 	[0] = llc_conn_ev_qlfy_cause_flag_eq_1,
 	[1] = llc_conn_ev_qlfy_set_status_disc,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_rst_actions_5[] = {
+static const llc_conn_action_t llc_rst_actions_5[] = {
 	[0] = llc_conn_ac_disc_ind,
 	[1] = llc_conn_ac_stop_ack_timer,
 	[2] = llc_conn_disc,
@@ -4574,13 +4574,13 @@ static struct llc_conn_state_trans llc_rst_state_trans_5 = {
 /* State transitions for LLC_CONN_EV_RX_DM_RSP_Fbit_SET_X event,
  * cause_flag = 0
  */
-static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_5_1[] = {
+static const llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_5_1[] = {
 	[0] = llc_conn_ev_qlfy_cause_flag_eq_0,
 	[1] = llc_conn_ev_qlfy_set_status_refuse,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_rst_actions_5_1[] = {
+static const llc_conn_action_t llc_rst_actions_5_1[] = {
 	[0] = llc_conn_ac_stop_ack_timer,
 	[1] = llc_conn_disc,
 	[2] = NULL,
@@ -4594,13 +4594,13 @@ static struct llc_conn_state_trans llc_rst_state_trans_5_1 = {
 };
 
 /* State transitions for DATA_CONN_REQ event */
-static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_6[] = {
+static const llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_6[] = {
 	[0] = llc_conn_ev_qlfy_set_status_refuse,
 	[1] = NULL,
 };
 
 /* just one member, NULL, .bss zeroes it */
-static llc_conn_action_t llc_rst_actions_6[1];
+static const llc_conn_action_t llc_rst_actions_6[1];
 
 static struct llc_conn_state_trans llc_rst_state_trans_6 = {
 	.ev	       = llc_conn_ev_data_req,
@@ -4610,13 +4610,13 @@ static struct llc_conn_state_trans llc_rst_state_trans_6 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_7[] = {
+static const llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_7[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[1] = llc_conn_ev_qlfy_s_flag_eq_0,
 	[2] = NULL,
 };
 
-static llc_conn_action_t llc_rst_actions_7[] = {
+static const llc_conn_action_t llc_rst_actions_7[] = {
 	[0] = llc_conn_ac_send_sabme_cmd_p_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_inc_retry_cnt_by_1,
@@ -4631,14 +4631,14 @@ static struct llc_conn_state_trans llc_rst_state_trans_7 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_8[] = {
+static const llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_8[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_gte_n2,
 	[1] = llc_conn_ev_qlfy_s_flag_eq_0,
 	[2] = llc_conn_ev_qlfy_cause_flag_eq_1,
 	[3] = llc_conn_ev_qlfy_set_status_failed,
 	[4] = NULL,
 };
-static llc_conn_action_t llc_rst_actions_8[] = {
+static const llc_conn_action_t llc_rst_actions_8[] = {
 	[0] = llc_conn_ac_disc_ind,
 	[1] = llc_conn_disc,
 	[2] = NULL,
@@ -4652,14 +4652,14 @@ static struct llc_conn_state_trans llc_rst_state_trans_8 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_8_1[] = {
+static const llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_8_1[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_gte_n2,
 	[1] = llc_conn_ev_qlfy_s_flag_eq_0,
 	[2] = llc_conn_ev_qlfy_cause_flag_eq_0,
 	[3] = llc_conn_ev_qlfy_set_status_failed,
 	[4] = NULL,
 };
-static llc_conn_action_t llc_rst_actions_8_1[] = {
+static const llc_conn_action_t llc_rst_actions_8_1[] = {
 	[0] = llc_conn_ac_disc_ind,
 	[1] = llc_conn_disc,
 	[2] = NULL,
@@ -4698,7 +4698,7 @@ static struct llc_conn_state_trans *llc_rst_state_transitions[] = {
 
 /* LLC_CONN_STATE_ERROR transitions */
 /* State transitions for LLC_CONN_EV_RX_SABME_CMD_Pbit_SET_X event */
-static llc_conn_action_t llc_error_actions_1[] = {
+static const llc_conn_action_t llc_error_actions_1[] = {
 	[0] = llc_conn_ac_set_vs_0,
 	[1] = llc_conn_ac_set_vr_0,
 	[2] = llc_conn_ac_send_ua_rsp_f_set_p,
@@ -4718,7 +4718,7 @@ static struct llc_conn_state_trans llc_error_state_trans_1 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_DISC_CMD_Pbit_SET_X event */
-static llc_conn_action_t llc_error_actions_2[] = {
+static const llc_conn_action_t llc_error_actions_2[] = {
 	[0] = llc_conn_ac_send_ua_rsp_f_set_p,
 	[1] = llc_conn_ac_disc_ind,
 	[2] = llc_conn_ac_stop_ack_timer,
@@ -4734,7 +4734,7 @@ static struct llc_conn_state_trans llc_error_state_trans_2 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_DM_RSP_Fbit_SET_X event */
-static llc_conn_action_t llc_error_actions_3[] = {
+static const llc_conn_action_t llc_error_actions_3[] = {
 	[0] = llc_conn_ac_disc_ind,
 	[1] = llc_conn_ac_stop_ack_timer,
 	[2] = llc_conn_disc,
@@ -4749,7 +4749,7 @@ static struct llc_conn_state_trans llc_error_state_trans_3 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_FRMR_RSP_Fbit_SET_X event */
-static llc_conn_action_t llc_error_actions_4[] = {
+static const llc_conn_action_t llc_error_actions_4[] = {
 	[0] = llc_conn_ac_send_sabme_cmd_p_set_x,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_set_retry_cnt_0,
@@ -4765,7 +4765,7 @@ static struct llc_conn_state_trans llc_error_state_trans_4 = {
 };
 
 /* State transitions for LLC_CONN_EV_RX_XXX_CMD_Pbit_SET_X event */
-static llc_conn_action_t llc_error_actions_5[] = {
+static const llc_conn_action_t llc_error_actions_5[] = {
 	[0] = llc_conn_ac_resend_frmr_rsp_f_set_p,
 	[1] = NULL,
 };
@@ -4786,12 +4786,12 @@ static struct llc_conn_state_trans llc_error_state_trans_6 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_error_ev_qfyrs_7[] = {
+static const llc_conn_ev_qfyr_t llc_error_ev_qfyrs_7[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_lt_n2,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_error_actions_7[] = {
+static const llc_conn_action_t llc_error_actions_7[] = {
 	[0] = llc_conn_ac_resend_frmr_rsp_f_set_0,
 	[1] = llc_conn_ac_start_ack_timer,
 	[2] = llc_conn_ac_inc_retry_cnt_by_1,
@@ -4806,12 +4806,12 @@ static struct llc_conn_state_trans llc_error_state_trans_7 = {
 };
 
 /* State transitions for LLC_CONN_EV_ACK_TMR_EXP event */
-static llc_conn_ev_qfyr_t llc_error_ev_qfyrs_8[] = {
+static const llc_conn_ev_qfyr_t llc_error_ev_qfyrs_8[] = {
 	[0] = llc_conn_ev_qlfy_retry_cnt_gte_n2,
 	[1] = NULL,
 };
 
-static llc_conn_action_t llc_error_actions_8[] = {
+static const llc_conn_action_t llc_error_actions_8[] = {
 	[0] = llc_conn_ac_send_sabme_cmd_p_set_x,
 	[1] = llc_conn_ac_set_s_flag_0,
 	[2] = llc_conn_ac_start_ack_timer,
@@ -4828,13 +4828,13 @@ static struct llc_conn_state_trans llc_error_state_trans_8 = {
 };
 
 /* State transitions for LLC_CONN_EV_DATA_CONN_REQ event */
-static llc_conn_ev_qfyr_t llc_error_ev_qfyrs_9[] = {
+static const llc_conn_ev_qfyr_t llc_error_ev_qfyrs_9[] = {
 	[0] = llc_conn_ev_qlfy_set_status_refuse,
 	[1] = NULL,
 };
 
 /* just one member, NULL, .bss zeroes it */
-static llc_conn_action_t llc_error_actions_9[1];
+static const llc_conn_action_t llc_error_actions_9[1];
 
 static struct llc_conn_state_trans llc_error_state_trans_9 = {
 	.ev	       = llc_conn_ev_data_req,
@@ -4866,7 +4866,7 @@ static struct llc_conn_state_trans *llc_error_state_transitions[] = {
 
 /* LLC_CONN_STATE_TEMP transitions */
 /* State transitions for LLC_CONN_EV_DISC_REQ event */
-static llc_conn_action_t llc_temp_actions_1[] = {
+static const llc_conn_action_t llc_temp_actions_1[] = {
 	[0] = llc_conn_ac_stop_all_timers,
 	[1] = llc_conn_ac_send_disc_cmd_p_set_x,
 	[2] = llc_conn_disc,
diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index 42dc2e45c921..81a61fce3afb 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -406,7 +406,7 @@ static struct llc_conn_state_trans *llc_qualify_conn_ev(struct sock *sk,
 							struct sk_buff *skb)
 {
 	struct llc_conn_state_trans **next_trans;
-	llc_conn_ev_qfyr_t *next_qualifier;
+	const llc_conn_ev_qfyr_t *next_qualifier;
 	struct llc_conn_state_ev *ev = llc_conn_ev(skb);
 	struct llc_sock *llc = llc_sk(sk);
 	struct llc_conn_state *curr_state =
@@ -454,7 +454,7 @@ static int llc_exec_conn_trans_actions(struct sock *sk,
 				       struct sk_buff *skb)
 {
 	int rc = 0;
-	llc_conn_action_t *next_action;
+	const llc_conn_action_t *next_action;
 
 	for (next_action = trans->ev_actions;
 	     next_action && *next_action; next_action++) {
diff --git a/net/llc/llc_if.c b/net/llc/llc_if.c
index 25c31c0a3fdb..6daf391b3e84 100644
--- a/net/llc/llc_if.c
+++ b/net/llc/llc_if.c
@@ -15,7 +15,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/netdevice.h>
-#include <asm/errno.h>
+#include <linux/errno.h>
 #include <net/llc_if.h>
 #include <net/llc_sap.h>
 #include <net/llc_s_ev.h>
diff --git a/net/llc/llc_s_st.c b/net/llc/llc_s_st.c
index 135f7d80069e..308c616883a4 100644
--- a/net/llc/llc_s_st.c
+++ b/net/llc/llc_s_st.c
@@ -29,7 +29,7 @@ static struct llc_sap_state_trans llc_sap_state_trans_end;
 /* state LLC_SAP_STATE_INACTIVE transition for
  * LLC_SAP_EV_ACTIVATION_REQ event
  */
-static llc_sap_action_t llc_sap_inactive_state_actions_1[] = {
+static const llc_sap_action_t llc_sap_inactive_state_actions_1[] = {
 	[0] = llc_sap_action_report_status,
 	[1] = NULL,
 };
@@ -47,7 +47,7 @@ static struct llc_sap_state_trans *llc_sap_inactive_state_transitions[] = {
 };
 
 /* state LLC_SAP_STATE_ACTIVE transition for LLC_SAP_EV_RX_UI event */
-static llc_sap_action_t llc_sap_active_state_actions_1[] = {
+static const llc_sap_action_t llc_sap_active_state_actions_1[] = {
 	[0] = llc_sap_action_unitdata_ind,
 	[1] = NULL,
 };
@@ -59,7 +59,7 @@ static struct llc_sap_state_trans llc_sap_active_state_trans_1 = {
 };
 
 /* state LLC_SAP_STATE_ACTIVE transition for LLC_SAP_EV_UNITDATA_REQ event */
-static llc_sap_action_t llc_sap_active_state_actions_2[] = {
+static const llc_sap_action_t llc_sap_active_state_actions_2[] = {
 	[0] = llc_sap_action_send_ui,
 	[1] = NULL,
 };
@@ -71,7 +71,7 @@ static struct llc_sap_state_trans llc_sap_active_state_trans_2 = {
 };
 
 /* state LLC_SAP_STATE_ACTIVE transition for LLC_SAP_EV_XID_REQ event */
-static llc_sap_action_t llc_sap_active_state_actions_3[] = {
+static const llc_sap_action_t llc_sap_active_state_actions_3[] = {
 	[0] = llc_sap_action_send_xid_c,
 	[1] = NULL,
 };
@@ -83,7 +83,7 @@ static struct llc_sap_state_trans llc_sap_active_state_trans_3 = {
 };
 
 /* state LLC_SAP_STATE_ACTIVE transition for LLC_SAP_EV_RX_XID_C event */
-static llc_sap_action_t llc_sap_active_state_actions_4[] = {
+static const llc_sap_action_t llc_sap_active_state_actions_4[] = {
 	[0] = llc_sap_action_send_xid_r,
 	[1] = NULL,
 };
@@ -95,7 +95,7 @@ static struct llc_sap_state_trans llc_sap_active_state_trans_4 = {
 };
 
 /* state LLC_SAP_STATE_ACTIVE transition for LLC_SAP_EV_RX_XID_R event */
-static llc_sap_action_t llc_sap_active_state_actions_5[] = {
+static const llc_sap_action_t llc_sap_active_state_actions_5[] = {
 	[0] = llc_sap_action_xid_ind,
 	[1] = NULL,
 };
@@ -107,7 +107,7 @@ static struct llc_sap_state_trans llc_sap_active_state_trans_5 = {
 };
 
 /* state LLC_SAP_STATE_ACTIVE transition for LLC_SAP_EV_TEST_REQ event */
-static llc_sap_action_t llc_sap_active_state_actions_6[] = {
+static const llc_sap_action_t llc_sap_active_state_actions_6[] = {
 	[0] = llc_sap_action_send_test_c,
 	[1] = NULL,
 };
@@ -119,7 +119,7 @@ static struct llc_sap_state_trans llc_sap_active_state_trans_6 = {
 };
 
 /* state LLC_SAP_STATE_ACTIVE transition for LLC_SAP_EV_RX_TEST_C event */
-static llc_sap_action_t llc_sap_active_state_actions_7[] = {
+static const llc_sap_action_t llc_sap_active_state_actions_7[] = {
 	[0] = llc_sap_action_send_test_r,
 	[1] = NULL,
 };
@@ -131,7 +131,7 @@ static struct llc_sap_state_trans llc_sap_active_state_trans_7 = {
 };
 
 /* state LLC_SAP_STATE_ACTIVE transition for LLC_SAP_EV_RX_TEST_R event */
-static llc_sap_action_t llc_sap_active_state_actions_8[] = {
+static const llc_sap_action_t llc_sap_active_state_actions_8[] = {
 	[0] = llc_sap_action_test_ind,
 	[1] = NULL,
 };
@@ -145,7 +145,7 @@ static struct llc_sap_state_trans llc_sap_active_state_trans_8 = {
 /* state LLC_SAP_STATE_ACTIVE transition for
  * LLC_SAP_EV_DEACTIVATION_REQ event
  */
-static llc_sap_action_t llc_sap_active_state_actions_9[] = {
+static const llc_sap_action_t llc_sap_active_state_actions_9[] = {
 	[0] = llc_sap_action_report_status,
 	[1] = NULL,
 };
diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c
index 06033f6c845f..d0e1e804ebd7 100644
--- a/net/llc/llc_sap.c
+++ b/net/llc/llc_sap.c
@@ -146,7 +146,7 @@ static int llc_exec_sap_trans_actions(struct llc_sap *sap,
 				      struct sk_buff *skb)
 {
 	int rc = 0;
-	llc_sap_action_t *next_action = trans->ev_actions;
+	const llc_sap_action_t *next_action = trans->ev_actions;
 
 	for (; next_action && *next_action; next_action++)
 		if ((*next_action)(sap, skb))
diff --git a/net/llc/sysctl_net_llc.c b/net/llc/sysctl_net_llc.c
index 612a5ddaf93b..799bafc2af39 100644
--- a/net/llc/sysctl_net_llc.c
+++ b/net/llc/sysctl_net_llc.c
@@ -18,28 +18,28 @@ static struct ctl_table llc2_timeout_table[] = {
 	{
 		.procname	= "ack",
 		.data		= &sysctl_llc2_ack_timeout,
-		.maxlen		= sizeof(long),
+		.maxlen		= sizeof(sysctl_llc2_ack_timeout),
 		.mode		= 0644,
 		.proc_handler   = proc_dointvec_jiffies,
 	},
 	{
 		.procname	= "busy",
 		.data		= &sysctl_llc2_busy_timeout,
-		.maxlen		= sizeof(long),
+		.maxlen		= sizeof(sysctl_llc2_busy_timeout),
 		.mode		= 0644,
 		.proc_handler   = proc_dointvec_jiffies,
 	},
 	{
 		.procname	= "p",
 		.data		= &sysctl_llc2_p_timeout,
-		.maxlen		= sizeof(long),
+		.maxlen		= sizeof(sysctl_llc2_p_timeout),
 		.mode		= 0644,
 		.proc_handler   = proc_dointvec_jiffies,
 	},
 	{
 		.procname	= "rej",
 		.data		= &sysctl_llc2_rej_timeout,
-		.maxlen		= sizeof(long),
+		.maxlen		= sizeof(sysctl_llc2_rej_timeout),
 		.mode		= 0644,
 		.proc_handler   = proc_dointvec_jiffies,
 	},
diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig
index aeb6a483b3bc..64a012a0c6e5 100644
--- a/net/mac80211/Kconfig
+++ b/net/mac80211/Kconfig
@@ -5,6 +5,7 @@ config MAC80211
 	select CRYPTO_ARC4
 	select CRYPTO_AES
 	select CRYPTO_CCM
+	select CRYPTO_GCM
 	select CRC32
 	select AVERAGE
 	---help---
@@ -33,6 +34,13 @@ config MAC80211_RC_MINSTREL_HT
 	---help---
 	  This option enables the 'minstrel_ht' TX rate control algorithm
 
+config MAC80211_RC_MINSTREL_VHT
+	bool "Minstrel 802.11ac support" if EXPERT
+	depends on MAC80211_RC_MINSTREL_HT
+	default n
+	---help---
+	  This option enables VHT in the 'minstrel_ht' TX rate control algorithm
+
 choice
 	prompt "Default rate control algorithm"
 	depends on MAC80211_HAS_RC
@@ -169,6 +177,17 @@ config MAC80211_HT_DEBUG
 
 	  Do not select this option.
 
+config MAC80211_OCB_DEBUG
+	bool "Verbose OCB debugging"
+	depends on MAC80211_DEBUG_MENU
+	---help---
+	  Selecting this option causes mac80211 to print out
+	  very verbose OCB debugging messages. It should not
+	  be selected on production systems as those messages
+	  are remotely triggerable.
+
+	  Do not select this option.
+
 config MAC80211_IBSS_DEBUG
 	bool "Verbose IBSS debugging"
 	depends on MAC80211_DEBUG_MENU
diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile
index 7273d2796dd1..3275f01881be 100644
--- a/net/mac80211/Makefile
+++ b/net/mac80211/Makefile
@@ -15,7 +15,9 @@ mac80211-y := \
 	michael.o \
 	tkip.o \
 	aes_ccm.o \
+	aes_gcm.o \
 	aes_cmac.o \
+	aes_gmac.o \
 	cfg.o \
 	ethtool.o \
 	rx.o \
@@ -27,7 +29,8 @@ mac80211-y := \
 	event.o \
 	chan.o \
 	trace.o mlme.o \
-	tdls.o
+	tdls.o \
+	ocb.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 ec24378caaaf..7663c28ba353 100644
--- a/net/mac80211/aes_ccm.c
+++ b/net/mac80211/aes_ccm.c
@@ -11,18 +11,18 @@
 
 #include <linux/kernel.h>
 #include <linux/types.h>
-#include <linux/crypto.h>
 #include <linux/err.h>
-#include <crypto/aes.h>
+#include <crypto/aead.h>
 
 #include <net/mac80211.h>
 #include "key.h"
 #include "aes_ccm.h"
 
 void ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
-			       u8 *data, size_t data_len, u8 *mic)
+			       u8 *data, size_t data_len, u8 *mic,
+			       size_t mic_len)
 {
-	struct scatterlist assoc, pt, ct[2];
+	struct scatterlist sg[3];
 
 	char aead_req_data[sizeof(struct aead_request) +
 			   crypto_aead_reqsize(tfm)]
@@ -31,45 +31,48 @@ void ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
 
 	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));
-	sg_init_table(ct, 2);
-	sg_set_buf(&ct[0], data, data_len);
-	sg_set_buf(&ct[1], mic, IEEE80211_CCMP_MIC_LEN);
+	sg_init_table(sg, 3);
+	sg_set_buf(&sg[0], &aad[2], be16_to_cpup((__be16 *)aad));
+	sg_set_buf(&sg[1], data, data_len);
+	sg_set_buf(&sg[2], mic, mic_len);
 
 	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);
+	aead_request_set_crypt(aead_req, sg, sg, data_len, b_0);
+	aead_request_set_ad(aead_req, sg[0].length);
 
 	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)
+			      u8 *data, size_t data_len, u8 *mic,
+			      size_t mic_len)
 {
-	struct scatterlist assoc, pt, ct[2];
+	struct scatterlist sg[3];
 	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;
 
+	if (data_len == 0)
+		return -EINVAL;
+
 	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));
-	sg_init_table(ct, 2);
-	sg_set_buf(&ct[0], data, data_len);
-	sg_set_buf(&ct[1], mic, IEEE80211_CCMP_MIC_LEN);
+	sg_init_table(sg, 3);
+	sg_set_buf(&sg[0], &aad[2], be16_to_cpup((__be16 *)aad));
+	sg_set_buf(&sg[1], data, data_len);
+	sg_set_buf(&sg[2], mic, mic_len);
 
 	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);
+	aead_request_set_crypt(aead_req, sg, sg, data_len + mic_len, b_0);
+	aead_request_set_ad(aead_req, sg[0].length);
 
 	return crypto_aead_decrypt(aead_req);
 }
 
-struct crypto_aead *ieee80211_aes_key_setup_encrypt(const u8 key[])
+struct crypto_aead *ieee80211_aes_key_setup_encrypt(const u8 key[],
+						    size_t key_len,
+						    size_t mic_len)
 {
 	struct crypto_aead *tfm;
 	int err;
@@ -78,12 +81,16 @@ struct crypto_aead *ieee80211_aes_key_setup_encrypt(const u8 key[])
 	if (IS_ERR(tfm))
 		return tfm;
 
-	err = crypto_aead_setkey(tfm, key, WLAN_KEY_LEN_CCMP);
-	if (!err)
-		err = crypto_aead_setauthsize(tfm, IEEE80211_CCMP_MIC_LEN);
-	if (!err)
-		return tfm;
+	err = crypto_aead_setkey(tfm, key, key_len);
+	if (err)
+		goto free_aead;
+	err = crypto_aead_setauthsize(tfm, mic_len);
+	if (err)
+		goto free_aead;
+
+	return tfm;
 
+free_aead:
 	crypto_free_aead(tfm);
 	return ERR_PTR(err);
 }
diff --git a/net/mac80211/aes_ccm.h b/net/mac80211/aes_ccm.h
index 2c7ab1948a2e..6a73d1e4d186 100644
--- a/net/mac80211/aes_ccm.h
+++ b/net/mac80211/aes_ccm.h
@@ -12,11 +12,15 @@
 
 #include <linux/crypto.h>
 
-struct crypto_aead *ieee80211_aes_key_setup_encrypt(const u8 key[]);
+struct crypto_aead *ieee80211_aes_key_setup_encrypt(const u8 key[],
+						    size_t key_len,
+						    size_t mic_len);
 void ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
-			       u8 *data, size_t data_len, u8 *mic);
+			       u8 *data, size_t data_len, u8 *mic,
+			       size_t mic_len);
 int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
-			      u8 *data, size_t data_len, u8 *mic);
+			      u8 *data, size_t data_len, u8 *mic,
+			      size_t mic_len);
 void ieee80211_aes_key_free(struct crypto_aead *tfm);
 
 #endif /* AES_CCM_H */
diff --git a/net/mac80211/aes_cmac.c b/net/mac80211/aes_cmac.c
index 9b9009f99551..4192806be3d3 100644
--- a/net/mac80211/aes_cmac.c
+++ b/net/mac80211/aes_cmac.c
@@ -18,8 +18,8 @@
 #include "key.h"
 #include "aes_cmac.h"
 
-#define AES_CMAC_KEY_LEN 16
 #define CMAC_TLEN 8 /* CMAC TLen = 64 bits (8 octets) */
+#define CMAC_TLEN_256 16 /* CMAC TLen = 128 bits (16 octets) */
 #define AAD_LEN 20
 
 
@@ -35,9 +35,9 @@ static void gf_mulx(u8 *pad)
 		pad[AES_BLOCK_SIZE - 1] ^= 0x87;
 }
 
-
-static void aes_128_cmac_vector(struct crypto_cipher *tfm, size_t num_elem,
-				const u8 *addr[], const size_t *len, u8 *mac)
+static void aes_cmac_vector(struct crypto_cipher *tfm, size_t num_elem,
+			    const u8 *addr[], const size_t *len, u8 *mac,
+			    size_t mac_len)
 {
 	u8 cbc[AES_BLOCK_SIZE], pad[AES_BLOCK_SIZE];
 	const u8 *pos, *end;
@@ -88,7 +88,7 @@ static void aes_128_cmac_vector(struct crypto_cipher *tfm, size_t num_elem,
 	for (i = 0; i < AES_BLOCK_SIZE; i++)
 		pad[i] ^= cbc[i];
 	crypto_cipher_encrypt_one(tfm, pad, pad);
-	memcpy(mac, pad, CMAC_TLEN);
+	memcpy(mac, pad, mac_len);
 }
 
 
@@ -107,17 +107,35 @@ void ieee80211_aes_cmac(struct crypto_cipher *tfm, const u8 *aad,
 	addr[2] = zero;
 	len[2] = CMAC_TLEN;
 
-	aes_128_cmac_vector(tfm, 3, addr, len, mic);
+	aes_cmac_vector(tfm, 3, addr, len, mic, CMAC_TLEN);
 }
 
+void ieee80211_aes_cmac_256(struct crypto_cipher *tfm, const u8 *aad,
+			    const u8 *data, size_t data_len, u8 *mic)
+{
+	const u8 *addr[3];
+	size_t len[3];
+	u8 zero[CMAC_TLEN_256];
+
+	memset(zero, 0, CMAC_TLEN_256);
+	addr[0] = aad;
+	len[0] = AAD_LEN;
+	addr[1] = data;
+	len[1] = data_len - CMAC_TLEN_256;
+	addr[2] = zero;
+	len[2] = CMAC_TLEN_256;
+
+	aes_cmac_vector(tfm, 3, addr, len, mic, CMAC_TLEN_256);
+}
 
-struct crypto_cipher *ieee80211_aes_cmac_key_setup(const u8 key[])
+struct crypto_cipher *ieee80211_aes_cmac_key_setup(const u8 key[],
+						   size_t key_len)
 {
 	struct crypto_cipher *tfm;
 
 	tfm = crypto_alloc_cipher("aes", 0, CRYPTO_ALG_ASYNC);
 	if (!IS_ERR(tfm))
-		crypto_cipher_setkey(tfm, key, AES_CMAC_KEY_LEN);
+		crypto_cipher_setkey(tfm, key, key_len);
 
 	return tfm;
 }
diff --git a/net/mac80211/aes_cmac.h b/net/mac80211/aes_cmac.h
index 0ce6487af795..3702041f44fd 100644
--- a/net/mac80211/aes_cmac.h
+++ b/net/mac80211/aes_cmac.h
@@ -11,9 +11,12 @@
 
 #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[],
+						   size_t key_len);
 void ieee80211_aes_cmac(struct crypto_cipher *tfm, const u8 *aad,
 			const u8 *data, size_t data_len, u8 *mic);
+void ieee80211_aes_cmac_256(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);
 
 #endif /* AES_CMAC_H */
diff --git a/net/mac80211/aes_gcm.c b/net/mac80211/aes_gcm.c
new file mode 100644
index 000000000000..3afe361fd27c
--- /dev/null
+++ b/net/mac80211/aes_gcm.c
@@ -0,0 +1,96 @@
+/*
+ * Copyright 2014-2015, Qualcomm Atheros, Inc.
+ *
+ * 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/types.h>
+#include <linux/err.h>
+#include <crypto/aead.h>
+
+#include <net/mac80211.h>
+#include "key.h"
+#include "aes_gcm.h"
+
+void ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
+			       u8 *data, size_t data_len, u8 *mic)
+{
+	struct scatterlist sg[3];
+
+	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_table(sg, 3);
+	sg_set_buf(&sg[0], &aad[2], be16_to_cpup((__be16 *)aad));
+	sg_set_buf(&sg[1], data, data_len);
+	sg_set_buf(&sg[2], mic, IEEE80211_GCMP_MIC_LEN);
+
+	aead_request_set_tfm(aead_req, tfm);
+	aead_request_set_crypt(aead_req, sg, sg, data_len, j_0);
+	aead_request_set_ad(aead_req, sg[0].length);
+
+	crypto_aead_encrypt(aead_req);
+}
+
+int ieee80211_aes_gcm_decrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
+			      u8 *data, size_t data_len, u8 *mic)
+{
+	struct scatterlist sg[3];
+	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;
+
+	if (data_len == 0)
+		return -EINVAL;
+
+	memset(aead_req, 0, sizeof(aead_req_data));
+
+	sg_init_table(sg, 3);
+	sg_set_buf(&sg[0], &aad[2], be16_to_cpup((__be16 *)aad));
+	sg_set_buf(&sg[1], data, data_len);
+	sg_set_buf(&sg[2], mic, IEEE80211_GCMP_MIC_LEN);
+
+	aead_request_set_tfm(aead_req, tfm);
+	aead_request_set_crypt(aead_req, sg, sg,
+			       data_len + IEEE80211_GCMP_MIC_LEN, j_0);
+	aead_request_set_ad(aead_req, sg[0].length);
+
+	return crypto_aead_decrypt(aead_req);
+}
+
+struct crypto_aead *ieee80211_aes_gcm_key_setup_encrypt(const u8 key[],
+							size_t key_len)
+{
+	struct crypto_aead *tfm;
+	int err;
+
+	tfm = crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(tfm))
+		return tfm;
+
+	err = crypto_aead_setkey(tfm, key, key_len);
+	if (err)
+		goto free_aead;
+	err = crypto_aead_setauthsize(tfm, IEEE80211_GCMP_MIC_LEN);
+	if (err)
+		goto free_aead;
+
+	return tfm;
+
+free_aead:
+	crypto_free_aead(tfm);
+	return ERR_PTR(err);
+}
+
+void ieee80211_aes_gcm_key_free(struct crypto_aead *tfm)
+{
+	crypto_free_aead(tfm);
+}
diff --git a/net/mac80211/aes_gcm.h b/net/mac80211/aes_gcm.h
new file mode 100644
index 000000000000..1347fda6b76a
--- /dev/null
+++ b/net/mac80211/aes_gcm.h
@@ -0,0 +1,22 @@
+/*
+ * Copyright 2014-2015, Qualcomm Atheros, Inc.
+ *
+ * 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.
+ */
+
+#ifndef AES_GCM_H
+#define AES_GCM_H
+
+#include <linux/crypto.h>
+
+void ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
+			       u8 *data, size_t data_len, u8 *mic);
+int ieee80211_aes_gcm_decrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
+			      u8 *data, size_t data_len, u8 *mic);
+struct crypto_aead *ieee80211_aes_gcm_key_setup_encrypt(const u8 key[],
+							size_t key_len);
+void ieee80211_aes_gcm_key_free(struct crypto_aead *tfm);
+
+#endif /* AES_GCM_H */
diff --git a/net/mac80211/aes_gmac.c b/net/mac80211/aes_gmac.c
new file mode 100644
index 000000000000..3ddd927aaf30
--- /dev/null
+++ b/net/mac80211/aes_gmac.c
@@ -0,0 +1,82 @@
+/*
+ * AES-GMAC for IEEE 802.11 BIP-GMAC-128 and BIP-GMAC-256
+ * Copyright 2015, Qualcomm Atheros, Inc.
+ *
+ * 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/types.h>
+#include <linux/err.h>
+#include <crypto/aead.h>
+#include <crypto/aes.h>
+
+#include <net/mac80211.h>
+#include "key.h"
+#include "aes_gmac.h"
+
+#define GMAC_MIC_LEN 16
+#define GMAC_NONCE_LEN 12
+#define AAD_LEN 20
+
+int ieee80211_aes_gmac(struct crypto_aead *tfm, const u8 *aad, u8 *nonce,
+		       const u8 *data, size_t data_len, u8 *mic)
+{
+	struct scatterlist sg[4];
+	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;
+	u8 zero[GMAC_MIC_LEN], iv[AES_BLOCK_SIZE];
+
+	if (data_len < GMAC_MIC_LEN)
+		return -EINVAL;
+
+	memset(aead_req, 0, sizeof(aead_req_data));
+
+	memset(zero, 0, GMAC_MIC_LEN);
+	sg_init_table(sg, 4);
+	sg_set_buf(&sg[0], aad, AAD_LEN);
+	sg_set_buf(&sg[1], data, data_len - GMAC_MIC_LEN);
+	sg_set_buf(&sg[2], zero, GMAC_MIC_LEN);
+	sg_set_buf(&sg[3], mic, GMAC_MIC_LEN);
+
+	memcpy(iv, nonce, GMAC_NONCE_LEN);
+	memset(iv + GMAC_NONCE_LEN, 0, sizeof(iv) - GMAC_NONCE_LEN);
+	iv[AES_BLOCK_SIZE - 1] = 0x01;
+
+	aead_request_set_tfm(aead_req, tfm);
+	aead_request_set_crypt(aead_req, sg, sg, 0, iv);
+	aead_request_set_ad(aead_req, AAD_LEN + data_len);
+
+	crypto_aead_encrypt(aead_req);
+
+	return 0;
+}
+
+struct crypto_aead *ieee80211_aes_gmac_key_setup(const u8 key[],
+						 size_t key_len)
+{
+	struct crypto_aead *tfm;
+	int err;
+
+	tfm = crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(tfm))
+		return tfm;
+
+	err = crypto_aead_setkey(tfm, key, key_len);
+	if (!err)
+		err = crypto_aead_setauthsize(tfm, GMAC_MIC_LEN);
+	if (!err)
+		return tfm;
+
+	crypto_free_aead(tfm);
+	return ERR_PTR(err);
+}
+
+void ieee80211_aes_gmac_key_free(struct crypto_aead *tfm)
+{
+	crypto_free_aead(tfm);
+}
diff --git a/net/mac80211/aes_gmac.h b/net/mac80211/aes_gmac.h
new file mode 100644
index 000000000000..d328204d73a8
--- /dev/null
+++ b/net/mac80211/aes_gmac.h
@@ -0,0 +1,20 @@
+/*
+ * Copyright 2015, Qualcomm Atheros, Inc.
+ *
+ * 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.
+ */
+
+#ifndef AES_GMAC_H
+#define AES_GMAC_H
+
+#include <linux/crypto.h>
+
+struct crypto_aead *ieee80211_aes_gmac_key_setup(const u8 key[],
+						 size_t key_len);
+int ieee80211_aes_gmac(struct crypto_aead *tfm, const u8 *aad, u8 *nonce,
+		       const u8 *data, size_t data_len, u8 *mic);
+void ieee80211_aes_gmac_key_free(struct crypto_aead *tfm);
+
+#endif /* AES_GMAC_H */
diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c
index a48bad468880..5c564a68fb50 100644
--- a/net/mac80211/agg-rx.c
+++ b/net/mac80211/agg-rx.c
@@ -49,8 +49,6 @@ static void ieee80211_free_tid_rx(struct rcu_head *h)
 		container_of(h, struct tid_ampdu_rx, rcu_head);
 	int i;
 
-	del_timer_sync(&tid_rx->reorder_timer);
-
 	for (i = 0; i < tid_rx->buf_size; i++)
 		__skb_queue_purge(&tid_rx->reorder_buf[i]);
 	kfree(tid_rx->reorder_buf);
@@ -93,6 +91,12 @@ void ___ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid,
 
 	del_timer_sync(&tid_rx->session_timer);
 
+	/* make sure ieee80211_sta_reorder_release() doesn't re-arm the timer */
+	spin_lock_bh(&tid_rx->reorder_lock);
+	tid_rx->removed = true;
+	spin_unlock_bh(&tid_rx->reorder_lock);
+	del_timer_sync(&tid_rx->reorder_timer);
+
 	call_rcu(&tid_rx->rcu_head, ieee80211_free_tid_rx);
 }
 
@@ -234,6 +238,14 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta,
 	int i, ret = -EOPNOTSUPP;
 	u16 status = WLAN_STATUS_REQUEST_DECLINED;
 
+	if (!sta->sta.ht_cap.ht_supported) {
+		ht_dbg(sta->sdata,
+		       "STA %pM erroneously requests BA session on tid %d w/o QoS\n",
+		       sta->sta.addr, tid);
+		/* send a response anyway, it's an error case if we get here */
+		goto end_no_lock;
+	}
+
 	if (test_sta_flag(sta, WLAN_STA_BLOCK_BA)) {
 		ht_dbg(sta->sdata,
 		       "Suspend in progress - Denying ADDBA request (%pM tid %d)\n",
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index d6986f3aa5c4..cce9d425c718 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -149,11 +149,6 @@ void ieee80211_assign_tid_tx(struct sta_info *sta, int tid,
 	rcu_assign_pointer(sta->ampdu_mlme.tid_tx[tid], tid_tx);
 }
 
-static inline int ieee80211_ac_from_tid(int tid)
-{
-	return ieee802_1d_to_ac[tid & 7];
-}
-
 /*
  * When multiple aggregation sessions on multiple stations
  * are being created/destroyed simultaneously, we need to
@@ -193,6 +188,43 @@ ieee80211_wake_queue_agg(struct ieee80211_sub_if_data *sdata, int tid)
 	__release(agg_queue);
 }
 
+static void
+ieee80211_agg_stop_txq(struct sta_info *sta, int tid)
+{
+	struct ieee80211_txq *txq = sta->sta.txq[tid];
+	struct txq_info *txqi;
+
+	if (!txq)
+		return;
+
+	txqi = to_txq_info(txq);
+
+	/* Lock here to protect against further seqno updates on dequeue */
+	spin_lock_bh(&txqi->queue.lock);
+	set_bit(IEEE80211_TXQ_STOP, &txqi->flags);
+	spin_unlock_bh(&txqi->queue.lock);
+}
+
+static void
+ieee80211_agg_start_txq(struct sta_info *sta, int tid, bool enable)
+{
+	struct ieee80211_txq *txq = sta->sta.txq[tid];
+	struct txq_info *txqi;
+
+	if (!txq)
+		return;
+
+	txqi = to_txq_info(txq);
+
+	if (enable)
+		set_bit(IEEE80211_TXQ_AMPDU, &txqi->flags);
+	else
+		clear_bit(IEEE80211_TXQ_AMPDU, &txqi->flags);
+
+	clear_bit(IEEE80211_TXQ_STOP, &txqi->flags);
+	drv_wake_tx_queue(sta->sdata->local, txqi);
+}
+
 /*
  * splice packets from the STA's pending to the local pending,
  * requires a call to ieee80211_agg_splice_finish later
@@ -252,6 +284,7 @@ static void ieee80211_remove_tid_tx(struct sta_info *sta, int tid)
 	ieee80211_assign_tid_tx(sta, tid, NULL);
 
 	ieee80211_agg_splice_finish(sta->sdata, tid);
+	ieee80211_agg_start_txq(sta, tid, false);
 
 	kfree_rcu(tid_tx, rcu_head);
 }
@@ -423,6 +456,8 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid)
 	 */
 	clear_bit(HT_AGG_STATE_WANT_START, &tid_tx->state);
 
+	ieee80211_agg_stop_txq(sta, tid);
+
 	/*
 	 * Make sure no packets are being processed. This ensures that
 	 * we have a valid starting sequence number and that in-flight
@@ -445,6 +480,8 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid)
 		ieee80211_agg_splice_finish(sdata, tid);
 		spin_unlock_bh(&sta->lock);
 
+		ieee80211_agg_start_txq(sta, tid, false);
+
 		kfree_rcu(tid_tx, rcu_head);
 		return;
 	}
@@ -516,6 +553,13 @@ int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid,
 
 	trace_api_start_tx_ba_session(pubsta, tid);
 
+	if (WARN(sta->reserved_tid == tid,
+		 "Requested to start BA session on reserved tid=%d", tid))
+		return -EINVAL;
+
+	if (!pubsta->ht_cap.ht_supported)
+		return -EINVAL;
+
 	if (WARN_ON_ONCE(!local->ops->ampdu_action))
 		return -EINVAL;
 
@@ -667,6 +711,8 @@ static void ieee80211_agg_tx_operational(struct ieee80211_local *local,
 	ieee80211_agg_splice_finish(sta->sdata, tid);
 
 	spin_unlock_bh(&sta->lock);
+
+	ieee80211_agg_start_txq(sta, tid, true);
 }
 
 void ieee80211_start_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u16 tid)
@@ -770,6 +816,9 @@ int ieee80211_stop_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid)
 		goto unlock;
 	}
 
+	WARN(sta->reserved_tid == tid,
+	     "Requested to stop BA session on reserved tid=%d", tid);
+
 	if (test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state)) {
 		/* already in progress stopping it */
 		ret = 0;
@@ -791,6 +840,7 @@ void ieee80211_stop_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u8 tid)
 	struct ieee80211_local *local = sdata->local;
 	struct sta_info *sta;
 	struct tid_ampdu_tx *tid_tx;
+	bool send_delba = false;
 
 	trace_api_stop_tx_ba_cb(sdata, ra, tid);
 
@@ -822,13 +872,17 @@ void ieee80211_stop_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u8 tid)
 	}
 
 	if (tid_tx->stop_initiator == WLAN_BACK_INITIATOR && tid_tx->tx_stop)
-		ieee80211_send_delba(sta->sdata, ra, tid,
-			WLAN_BACK_INITIATOR, WLAN_REASON_QSTA_NOT_USE);
+		send_delba = true;
 
 	ieee80211_remove_tid_tx(sta, tid);
 
  unlock_sta:
 	spin_unlock_bh(&sta->lock);
+
+	if (send_delba)
+		ieee80211_send_delba(sdata, ra, tid,
+			WLAN_BACK_INITIATOR, WLAN_REASON_QSTA_NOT_USE);
+
 	mutex_unlock(&sta->ampdu_mlme.mtx);
  unlock:
 	mutex_unlock(&local->sta_mtx);
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 343da1e35025..ff347a0eebd4 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -20,9 +20,11 @@
 #include "cfg.h"
 #include "rate.h"
 #include "mesh.h"
+#include "wme.h"
 
 static struct wireless_dev *ieee80211_add_iface(struct wiphy *wiphy,
 						const char *name,
+						unsigned char name_assign_type,
 						enum nl80211_iftype type,
 						u32 *flags,
 						struct vif_params *params)
@@ -32,7 +34,7 @@ static struct wireless_dev *ieee80211_add_iface(struct wiphy *wiphy,
 	struct ieee80211_sub_if_data *sdata;
 	int err;
 
-	err = ieee80211_if_add(local, name, &wdev, type, params);
+	err = ieee80211_if_add(local, name, name_assign_type, &wdev, type, params);
 	if (err)
 		return ERR_PTR(err);
 
@@ -161,8 +163,13 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev,
 			return -EINVAL;
 		break;
 	case WLAN_CIPHER_SUITE_CCMP:
+	case WLAN_CIPHER_SUITE_CCMP_256:
 	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
 	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
 		break;
 	default:
 		cs = ieee80211_cs_get(local, params->cipher, sdata->vif.type);
@@ -190,7 +197,7 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev,
 		 * receive the key. When wpa_supplicant has roamed
 		 * using FT, it attempts to set the key before
 		 * association has completed, this rejects that attempt
-		 * so it will set the key again after assocation.
+		 * so it will set the key again after association.
 		 *
 		 * TODO: accept the key if we have a station entry and
 		 *       add it to the device after the station.
@@ -229,6 +236,7 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev,
 	case NUM_NL80211_IFTYPES:
 	case NL80211_IFTYPE_P2P_CLIENT:
 	case NL80211_IFTYPE_P2P_GO:
+	case NL80211_IFTYPE_OCB:
 		/* shouldn't happen */
 		WARN_ON_ONCE(1);
 		break;
@@ -346,6 +354,7 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev,
 		params.seq_len = 6;
 		break;
 	case WLAN_CIPHER_SUITE_CCMP:
+	case WLAN_CIPHER_SUITE_CCMP_256:
 		pn64 = atomic64_read(&key->u.ccmp.tx_pn);
 		seq[0] = pn64;
 		seq[1] = pn64 >> 8;
@@ -357,6 +366,7 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev,
 		params.seq_len = 6;
 		break;
 	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 		pn64 = atomic64_read(&key->u.aes_cmac.tx_pn);
 		seq[0] = pn64;
 		seq[1] = pn64 >> 8;
@@ -367,6 +377,30 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev,
 		params.seq = seq;
 		params.seq_len = 6;
 		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		pn64 = atomic64_read(&key->u.aes_gmac.tx_pn);
+		seq[0] = pn64;
+		seq[1] = pn64 >> 8;
+		seq[2] = pn64 >> 16;
+		seq[3] = pn64 >> 24;
+		seq[4] = pn64 >> 32;
+		seq[5] = pn64 >> 40;
+		params.seq = seq;
+		params.seq_len = 6;
+		break;
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		pn64 = atomic64_read(&key->u.gcmp.tx_pn);
+		seq[0] = pn64;
+		seq[1] = pn64 >> 8;
+		seq[2] = pn64 >> 16;
+		seq[3] = pn64 >> 24;
+		seq[4] = pn64 >> 32;
+		seq[5] = pn64 >> 40;
+		params.seq = seq;
+		params.seq_len = 6;
+		break;
 	}
 
 	params.key = key->conf.key;
@@ -426,11 +460,13 @@ void sta_set_rate_info_tx(struct sta_info *sta,
 		rinfo->legacy = DIV_ROUND_UP(brate, 1 << shift);
 	}
 	if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)
-		rinfo->flags |= RATE_INFO_FLAGS_40_MHZ_WIDTH;
-	if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH)
-		rinfo->flags |= RATE_INFO_FLAGS_80_MHZ_WIDTH;
-	if (rate->flags & IEEE80211_TX_RC_160_MHZ_WIDTH)
-		rinfo->flags |= RATE_INFO_FLAGS_160_MHZ_WIDTH;
+		rinfo->bw = RATE_INFO_BW_40;
+	else if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH)
+		rinfo->bw = RATE_INFO_BW_80;
+	else if (rate->flags & IEEE80211_TX_RC_160_MHZ_WIDTH)
+		rinfo->bw = RATE_INFO_BW_160;
+	else
+		rinfo->bw = RATE_INFO_BW_20;
 	if (rate->flags & IEEE80211_TX_RC_SHORT_GI)
 		rinfo->flags |= RATE_INFO_FLAGS_SHORT_GI;
 }
@@ -457,16 +493,21 @@ void sta_set_rate_info_rx(struct sta_info *sta, struct rate_info *rinfo)
 		rinfo->legacy = DIV_ROUND_UP(brate, 1 << shift);
 	}
 
-	if (sta->last_rx_rate_flag & RX_FLAG_40MHZ)
-		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_vht_flag & RX_VHT_FLAG_80MHZ)
-		rinfo->flags |= RATE_INFO_FLAGS_80_MHZ_WIDTH;
-	if (sta->last_rx_rate_vht_flag & RX_VHT_FLAG_80P80MHZ)
-		rinfo->flags |= RATE_INFO_FLAGS_80P80_MHZ_WIDTH;
-	if (sta->last_rx_rate_vht_flag & RX_VHT_FLAG_160MHZ)
-		rinfo->flags |= RATE_INFO_FLAGS_160_MHZ_WIDTH;
+
+	if (sta->last_rx_rate_flag & RX_FLAG_5MHZ)
+		rinfo->bw = RATE_INFO_BW_5;
+	else if (sta->last_rx_rate_flag & RX_FLAG_10MHZ)
+		rinfo->bw = RATE_INFO_BW_10;
+	else if (sta->last_rx_rate_flag & RX_FLAG_40MHZ)
+		rinfo->bw = RATE_INFO_BW_40;
+	else if (sta->last_rx_rate_vht_flag & RX_VHT_FLAG_80MHZ)
+		rinfo->bw = RATE_INFO_BW_80;
+	else if (sta->last_rx_rate_vht_flag & RX_VHT_FLAG_160MHZ)
+		rinfo->bw = RATE_INFO_BW_160;
+	else
+		rinfo->bw = RATE_INFO_BW_20;
 }
 
 static int ieee80211_dump_station(struct wiphy *wiphy, struct net_device *dev,
@@ -676,7 +717,8 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 		      BSS_CHANGED_BEACON_ENABLED |
 		      BSS_CHANGED_BEACON |
 		      BSS_CHANGED_SSID |
-		      BSS_CHANGED_P2P_PS;
+		      BSS_CHANGED_P2P_PS |
+		      BSS_CHANGED_TXPOWER;
 	int err;
 
 	old = sdata_dereference(sdata->u.ap.beacon, sdata);
@@ -936,6 +978,14 @@ static int sta_apply_auth_flags(struct ieee80211_local *local,
 	if (mask & BIT(NL80211_STA_FLAG_ASSOCIATED) &&
 	    set & BIT(NL80211_STA_FLAG_ASSOCIATED) &&
 	    !test_sta_flag(sta, WLAN_STA_ASSOC)) {
+		/*
+		 * When peer becomes associated, init rate control as
+		 * well. Some drivers require rate control initialized
+		 * before drv_sta_state() is called.
+		 */
+		if (test_sta_flag(sta, WLAN_STA_TDLS_PEER))
+			rate_control_rate_init(sta);
+
 		ret = sta_info_move_state(sta, IEEE80211_STA_ASSOC);
 		if (ret)
 			return ret;
@@ -1009,6 +1059,10 @@ static int sta_apply_parameters(struct ieee80211_local *local,
 		}
 	}
 
+	if (mask & BIT(NL80211_STA_FLAG_WME) &&
+	    local->hw.queues >= IEEE80211_NUM_ACS)
+		sta->sta.wme = set & BIT(NL80211_STA_FLAG_WME);
+
 	/* auth flags will be set later for TDLS stations */
 	if (!test_sta_flag(sta, WLAN_STA_TDLS_PEER)) {
 		ret = sta_apply_auth_flags(local, sta, mask, set);
@@ -1023,10 +1077,8 @@ static int sta_apply_parameters(struct ieee80211_local *local,
 			clear_sta_flag(sta, WLAN_STA_SHORT_PREAMBLE);
 	}
 
-	if (mask & BIT(NL80211_STA_FLAG_WME))
-		sta->sta.wme = set & BIT(NL80211_STA_FLAG_WME);
-
 	if (mask & BIT(NL80211_STA_FLAG_MFP)) {
+		sta->sta.mfp = !!(set & BIT(NL80211_STA_FLAG_MFP));
 		if (set & BIT(NL80211_STA_FLAG_MFP))
 			set_sta_flag(sta, WLAN_STA_MFP);
 		else
@@ -1040,6 +1092,13 @@ static int sta_apply_parameters(struct ieee80211_local *local,
 			clear_sta_flag(sta, WLAN_STA_TDLS_PEER);
 	}
 
+	/* mark TDLS channel switch support, if the AP allows it */
+	if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) &&
+	    !sdata->u.mgd.tdls_chan_switch_prohibited &&
+	    params->ext_capab_len >= 4 &&
+	    params->ext_capab[3] & WLAN_EXT_CAPA4_TDLS_CHAN_SWITCH)
+		set_sta_flag(sta, WLAN_STA_TDLS_CHAN_SWITCH);
+
 	if (params->sta_modify_mask & STATION_PARAM_APPLY_UAPSD) {
 		sta->sta.uapsd_queues = params->uapsd_queues;
 		sta->sta.max_sp = params->max_sp;
@@ -1225,14 +1284,14 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev,
 }
 
 static int ieee80211_del_station(struct wiphy *wiphy, struct net_device *dev,
-				 const u8 *mac)
+				 struct station_del_parameters *params)
 {
 	struct ieee80211_sub_if_data *sdata;
 
 	sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 
-	if (mac)
-		return sta_info_destroy_addr_bss(sdata, mac);
+	if (params->mac)
+		return sta_info_destroy_addr_bss(sdata, params->mac);
 
 	sta_info_flush(sdata);
 	return 0;
@@ -1329,11 +1388,6 @@ static int ieee80211_change_station(struct wiphy *wiphy,
 	if (err)
 		goto out_err;
 
-	/* When peer becomes authorized, init rate control as well */
-	if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) &&
-	    test_sta_flag(sta, WLAN_STA_AUTHORIZED))
-		rate_control_rate_init(sta);
-
 	mutex_unlock(&local->sta_mtx);
 
 	if ((sdata->vif.type == NL80211_IFTYPE_AP ||
@@ -1440,7 +1494,7 @@ static void mpath_set_pinfo(struct mesh_path *mpath, u8 *next_hop,
 	if (next_hop_sta)
 		memcpy(next_hop, next_hop_sta->sta.addr, ETH_ALEN);
 	else
-		memset(next_hop, 0, ETH_ALEN);
+		eth_zero_addr(next_hop);
 
 	memset(pinfo, 0, sizeof(*pinfo));
 
@@ -1516,6 +1570,57 @@ static int ieee80211_dump_mpath(struct wiphy *wiphy, struct net_device *dev,
 	return 0;
 }
 
+static void mpp_set_pinfo(struct mesh_path *mpath, u8 *mpp,
+			  struct mpath_info *pinfo)
+{
+	memset(pinfo, 0, sizeof(*pinfo));
+	memcpy(mpp, mpath->mpp, ETH_ALEN);
+
+	pinfo->generation = mpp_paths_generation;
+}
+
+static int ieee80211_get_mpp(struct wiphy *wiphy, struct net_device *dev,
+			     u8 *dst, u8 *mpp, struct mpath_info *pinfo)
+
+{
+	struct ieee80211_sub_if_data *sdata;
+	struct mesh_path *mpath;
+
+	sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+
+	rcu_read_lock();
+	mpath = mpp_path_lookup(sdata, dst);
+	if (!mpath) {
+		rcu_read_unlock();
+		return -ENOENT;
+	}
+	memcpy(dst, mpath->dst, ETH_ALEN);
+	mpp_set_pinfo(mpath, mpp, pinfo);
+	rcu_read_unlock();
+	return 0;
+}
+
+static int ieee80211_dump_mpp(struct wiphy *wiphy, struct net_device *dev,
+			      int idx, u8 *dst, u8 *mpp,
+			      struct mpath_info *pinfo)
+{
+	struct ieee80211_sub_if_data *sdata;
+	struct mesh_path *mpath;
+
+	sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+
+	rcu_read_lock();
+	mpath = mpp_path_lookup_by_idx(sdata, idx);
+	if (!mpath) {
+		rcu_read_unlock();
+		return -ENOENT;
+	}
+	memcpy(dst, mpath->dst, ETH_ALEN);
+	mpp_set_pinfo(mpath, mpp, pinfo);
+	rcu_read_unlock();
+	return 0;
+}
+
 static int ieee80211_get_mesh_config(struct wiphy *wiphy,
 				struct net_device *dev,
 				struct mesh_config *conf)
@@ -1966,6 +2071,17 @@ static int ieee80211_leave_ibss(struct wiphy *wiphy, struct net_device *dev)
 	return ieee80211_ibss_leave(IEEE80211_DEV_TO_SUB_IF(dev));
 }
 
+static int ieee80211_join_ocb(struct wiphy *wiphy, struct net_device *dev,
+			      struct ocb_setup *setup)
+{
+	return ieee80211_ocb_join(IEEE80211_DEV_TO_SUB_IF(dev), setup);
+}
+
+static int ieee80211_leave_ocb(struct wiphy *wiphy, struct net_device *dev)
+{
+	return ieee80211_ocb_leave(IEEE80211_DEV_TO_SUB_IF(dev));
+}
+
 static int ieee80211_set_mcast_rate(struct wiphy *wiphy, struct net_device *dev,
 				    int rate[IEEE80211_NUM_BANDS])
 {
@@ -2031,6 +2147,8 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy,
 {
 	struct ieee80211_local *local = wiphy_priv(wiphy);
 	struct ieee80211_sub_if_data *sdata;
+	enum nl80211_tx_power_setting txp_type = type;
+	bool update_txp_type = false;
 
 	if (wdev) {
 		sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
@@ -2038,6 +2156,7 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy,
 		switch (type) {
 		case NL80211_TX_POWER_AUTOMATIC:
 			sdata->user_power_level = IEEE80211_UNSET_POWER_LEVEL;
+			txp_type = NL80211_TX_POWER_LIMITED;
 			break;
 		case NL80211_TX_POWER_LIMITED:
 		case NL80211_TX_POWER_FIXED:
@@ -2047,7 +2166,12 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy,
 			break;
 		}
 
-		ieee80211_recalc_txpower(sdata);
+		if (txp_type != sdata->vif.bss_conf.txpower_type) {
+			update_txp_type = true;
+			sdata->vif.bss_conf.txpower_type = txp_type;
+		}
+
+		ieee80211_recalc_txpower(sdata, update_txp_type);
 
 		return 0;
 	}
@@ -2055,6 +2179,7 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy,
 	switch (type) {
 	case NL80211_TX_POWER_AUTOMATIC:
 		local->user_power_level = IEEE80211_UNSET_POWER_LEVEL;
+		txp_type = NL80211_TX_POWER_LIMITED;
 		break;
 	case NL80211_TX_POWER_LIMITED:
 	case NL80211_TX_POWER_FIXED:
@@ -2065,10 +2190,14 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy,
 	}
 
 	mutex_lock(&local->iflist_mtx);
-	list_for_each_entry(sdata, &local->interfaces, list)
+	list_for_each_entry(sdata, &local->interfaces, list) {
 		sdata->user_power_level = local->user_power_level;
+		if (txp_type != sdata->vif.bss_conf.txpower_type)
+			update_txp_type = true;
+		sdata->vif.bss_conf.txpower_type = txp_type;
+	}
 	list_for_each_entry(sdata, &local->interfaces, list)
-		ieee80211_recalc_txpower(sdata);
+		ieee80211_recalc_txpower(sdata, update_txp_type);
 	mutex_unlock(&local->iflist_mtx);
 
 	return 0;
@@ -2081,6 +2210,9 @@ static int ieee80211_get_tx_power(struct wiphy *wiphy,
 	struct ieee80211_local *local = wiphy_priv(wiphy);
 	struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
 
+	if (local->ops->get_txpower)
+		return drv_get_txpower(local, sdata, dbm);
+
 	if (!local->use_chanctx)
 		*dbm = local->hw.conf.power_level;
 	else
@@ -2147,7 +2279,6 @@ int __ieee80211_request_smps_ap(struct ieee80211_sub_if_data *sdata,
 {
 	struct sta_info *sta;
 	enum ieee80211_smps_mode old_req;
-	int i;
 
 	if (WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_AP))
 		return -EINVAL;
@@ -2171,52 +2302,44 @@ int __ieee80211_request_smps_ap(struct ieee80211_sub_if_data *sdata,
 	}
 
 	ht_dbg(sdata,
-	       "SMSP %d requested in AP mode, sending Action frame to %d stations\n",
+	       "SMPS %d requested in AP mode, sending Action frame to %d stations\n",
 	       smps_mode, atomic_read(&sdata->u.ap.num_mcast_sta));
 
 	mutex_lock(&sdata->local->sta_mtx);
-	for (i = 0; i < STA_HASH_SIZE; i++) {
-		for (sta = rcu_dereference_protected(sdata->local->sta_hash[i],
-				lockdep_is_held(&sdata->local->sta_mtx));
-		     sta;
-		     sta = rcu_dereference_protected(sta->hnext,
-				lockdep_is_held(&sdata->local->sta_mtx))) {
-			/*
-			 * Only stations associated to our AP and
-			 * associated VLANs
-			 */
-			if (sta->sdata->bss != &sdata->u.ap)
-				continue;
+	list_for_each_entry(sta, &sdata->local->sta_list, list) {
+		/*
+		 * Only stations associated to our AP and
+		 * associated VLANs
+		 */
+		if (sta->sdata->bss != &sdata->u.ap)
+			continue;
 
-			/* This station doesn't support MIMO - skip it */
-			if (sta_info_tx_streams(sta) == 1)
-				continue;
+		/* This station doesn't support MIMO - skip it */
+		if (sta_info_tx_streams(sta) == 1)
+			continue;
 
-			/*
-			 * Don't wake up a STA just to send the action frame
-			 * unless we are getting more restrictive.
-			 */
-			if (test_sta_flag(sta, WLAN_STA_PS_STA) &&
-			    !ieee80211_smps_is_restrictive(sta->known_smps_mode,
-							   smps_mode)) {
-				ht_dbg(sdata,
-				       "Won't send SMPS to sleeping STA %pM\n",
-				       sta->sta.addr);
-				continue;
-			}
+		/*
+		 * Don't wake up a STA just to send the action frame
+		 * unless we are getting more restrictive.
+		 */
+		if (test_sta_flag(sta, WLAN_STA_PS_STA) &&
+		    !ieee80211_smps_is_restrictive(sta->known_smps_mode,
+						   smps_mode)) {
+			ht_dbg(sdata, "Won't send SMPS to sleeping STA %pM\n",
+			       sta->sta.addr);
+			continue;
+		}
 
-			/*
-			 * If the STA is not authorized, wait until it gets
-			 * authorized and the action frame will be sent then.
-			 */
-			if (!test_sta_flag(sta, WLAN_STA_AUTHORIZED))
-				continue;
+		/*
+		 * If the STA is not authorized, wait until it gets
+		 * authorized and the action frame will be sent then.
+		 */
+		if (!test_sta_flag(sta, WLAN_STA_AUTHORIZED))
+			continue;
 
-			ht_dbg(sdata, "Sending SMPS to %pM\n", sta->sta.addr);
-			ieee80211_send_smps_action(sdata, smps_mode,
-						   sta->sta.addr,
-						   sdata->vif.bss_conf.bssid);
-		}
+		ht_dbg(sdata, "Sending SMPS to %pM\n", sta->sta.addr);
+		ieee80211_send_smps_action(sdata, smps_mode, sta->sta.addr,
+					   sdata->vif.bss_conf.bssid);
 	}
 	mutex_unlock(&sdata->local->sta_mtx);
 
@@ -2372,51 +2495,22 @@ static bool ieee80211_coalesce_started_roc(struct ieee80211_local *local,
 					   struct ieee80211_roc_work *new_roc,
 					   struct ieee80211_roc_work *cur_roc)
 {
-	unsigned long j = jiffies;
-	unsigned long cur_roc_end = cur_roc->hw_start_time +
-				    msecs_to_jiffies(cur_roc->duration);
-	struct ieee80211_roc_work *next_roc;
-	int new_dur;
+	unsigned long now = jiffies;
+	unsigned long remaining = cur_roc->hw_start_time +
+				  msecs_to_jiffies(cur_roc->duration) -
+				  now;
 
 	if (WARN_ON(!cur_roc->started || !cur_roc->hw_begun))
 		return false;
 
-	if (time_after(j + IEEE80211_ROC_MIN_LEFT, cur_roc_end))
+	/* if it doesn't fit entirely, schedule a new one */
+	if (new_roc->duration > jiffies_to_msecs(remaining))
 		return false;
 
 	ieee80211_handle_roc_started(new_roc);
 
-	new_dur = new_roc->duration - jiffies_to_msecs(cur_roc_end - j);
-
-	/* cur_roc is long enough - add new_roc to the dependents list. */
-	if (new_dur <= 0) {
-		list_add_tail(&new_roc->list, &cur_roc->dependents);
-		return true;
-	}
-
-	new_roc->duration = new_dur;
-
-	/*
-	 * if cur_roc was already coalesced before, we might
-	 * want to extend the next roc instead of adding
-	 * a new one.
-	 */
-	next_roc = list_entry(cur_roc->list.next,
-			      struct ieee80211_roc_work, list);
-	if (&next_roc->list != &local->roc_list &&
-	    next_roc->chan == new_roc->chan &&
-	    next_roc->sdata == new_roc->sdata &&
-	    !WARN_ON(next_roc->started)) {
-		list_add_tail(&new_roc->list, &next_roc->dependents);
-		next_roc->duration = max(next_roc->duration,
-					 new_roc->duration);
-		next_roc->type = max(next_roc->type, new_roc->type);
-		return true;
-	}
-
-	/* add right after cur_roc */
-	list_add(&new_roc->list, &cur_roc->list);
-
+	/* add to dependents so we send the expired event properly */
+	list_add_tail(&new_roc->list, &cur_roc->dependents);
 	return true;
 }
 
@@ -2482,7 +2576,7 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local,
 
 	/* if there's one pending or we're scanning, queue this one */
 	if (!list_empty(&local->roc_list) ||
-	    local->scanning || local->radar_detect_enabled)
+	    local->scanning || ieee80211_is_radar_required(local))
 		goto out_check_combine;
 
 	/* if not HW assist, just queue & schedule work */
@@ -2529,17 +2623,9 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local,
 			 * In the offloaded ROC case, if it hasn't begun, add
 			 * this new one to the dependent list to be handled
 			 * when the master one begins. If it has begun,
-			 * check that there's still a minimum time left and
-			 * if so, start this one, transmitting the frame, but
-			 * add it to the list directly after this one with
-			 * a reduced time so we'll ask the driver to execute
-			 * it right after finishing the previous one, in the
-			 * hope that it'll also be executed right afterwards,
-			 * effectively extending the old one.
-			 * If there's no minimum time left, just add it to the
-			 * normal list.
-			 * TODO: the ROC type is ignored here, assuming that it
-			 * is better to immediately use the current ROC.
+			 * check if it fits entirely within the existing one,
+			 * in which case it will just be dependent as well.
+			 * Otherwise, schedule it by itself.
 			 */
 			if (!tmp->hw_begun) {
 				list_add_tail(&roc->list, &tmp->dependents);
@@ -2850,11 +2936,7 @@ static int __ieee80211_csa_finalize(struct ieee80211_sub_if_data *sdata)
 		if (sdata->reserved_ready)
 			return 0;
 
-		err = ieee80211_vif_use_reserved_context(sdata);
-		if (err)
-			return err;
-
-		return 0;
+		return ieee80211_vif_use_reserved_context(sdata);
 	}
 
 	if (!cfg80211_chandef_identical(&sdata->vif.bss_conf.chandef,
@@ -2868,7 +2950,6 @@ static int __ieee80211_csa_finalize(struct ieee80211_sub_if_data *sdata)
 		return err;
 
 	ieee80211_bss_info_change_notify(sdata, changed);
-	cfg80211_ch_switch_notify(sdata->dev, &sdata->csa_chandef);
 
 	if (sdata->csa_block_tx) {
 		ieee80211_wake_vif_queues(local, sdata,
@@ -2876,6 +2957,12 @@ static int __ieee80211_csa_finalize(struct ieee80211_sub_if_data *sdata)
 		sdata->csa_block_tx = false;
 	}
 
+	err = drv_post_channel_switch(sdata);
+	if (err)
+		return err;
+
+	cfg80211_ch_switch_notify(sdata->dev, &sdata->csa_chandef);
+
 	return 0;
 }
 
@@ -3053,9 +3140,11 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_channel_switch ch_switch;
 	struct ieee80211_chanctx_conf *conf;
 	struct ieee80211_chanctx *chanctx;
-	int err, changed = 0;
+	u32 changed = 0;
+	int err;
 
 	sdata_assert_lock(sdata);
 	lockdep_assert_held(&local->mtx);
@@ -3088,6 +3177,16 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
 		goto out;
 	}
 
+	ch_switch.timestamp = 0;
+	ch_switch.device_timestamp = 0;
+	ch_switch.block_tx = params->block_tx;
+	ch_switch.chandef = params->chandef;
+	ch_switch.count = params->count;
+
+	err = drv_pre_channel_switch(sdata, &ch_switch);
+	if (err)
+		goto out;
+
 	err = ieee80211_vif_reserve_chanctx(sdata, &params->chandef,
 					    chanctx->mode,
 					    params->radar_required);
@@ -3115,6 +3214,9 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
 		ieee80211_stop_vif_queues(local, sdata,
 					  IEEE80211_QUEUE_STOP_REASON_CSA);
 
+	cfg80211_ch_switch_started_notify(sdata->dev, &sdata->csa_chandef,
+					  params->count);
+
 	if (changed) {
 		ieee80211_bss_info_change_notify(sdata, changed);
 		drv_channel_switch_beacon(sdata, &params->chandef);
@@ -3431,6 +3533,7 @@ static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev,
 
 	info->flags |= IEEE80211_TX_CTL_REQ_TX_STATUS |
 		       IEEE80211_TX_INTFL_NL80211_FRAME_TX;
+	info->band = band;
 
 	skb_set_queue_mapping(skb, IEEE80211_AC_VO);
 	skb->priority = 7;
@@ -3438,7 +3541,7 @@ static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev,
 		nullfunc->qos_ctrl = cpu_to_le16(7);
 
 	local_bh_disable();
-	ieee80211_xmit(sdata, skb, band);
+	ieee80211_xmit(sdata, sta, skb);
 	local_bh_enable();
 	rcu_read_unlock();
 
@@ -3521,6 +3624,76 @@ static int ieee80211_set_ap_chanwidth(struct wiphy *wiphy,
 	return ret;
 }
 
+static int ieee80211_add_tx_ts(struct wiphy *wiphy, struct net_device *dev,
+			       u8 tsid, const u8 *peer, u8 up,
+			       u16 admitted_time)
+{
+	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+	int ac = ieee802_1d_to_ac[up];
+
+	if (sdata->vif.type != NL80211_IFTYPE_STATION)
+		return -EOPNOTSUPP;
+
+	if (!(sdata->wmm_acm & BIT(up)))
+		return -EINVAL;
+
+	if (ifmgd->tx_tspec[ac].admitted_time)
+		return -EBUSY;
+
+	if (admitted_time) {
+		ifmgd->tx_tspec[ac].admitted_time = 32 * admitted_time;
+		ifmgd->tx_tspec[ac].tsid = tsid;
+		ifmgd->tx_tspec[ac].up = up;
+	}
+
+	return 0;
+}
+
+static int ieee80211_del_tx_ts(struct wiphy *wiphy, struct net_device *dev,
+			       u8 tsid, const u8 *peer)
+{
+	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+	struct ieee80211_local *local = wiphy_priv(wiphy);
+	int ac;
+
+	for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
+		struct ieee80211_sta_tx_tspec *tx_tspec = &ifmgd->tx_tspec[ac];
+
+		/* skip unused entries */
+		if (!tx_tspec->admitted_time)
+			continue;
+
+		if (tx_tspec->tsid != tsid)
+			continue;
+
+		/* due to this new packets will be reassigned to non-ACM ACs */
+		tx_tspec->up = -1;
+
+		/* Make sure that all packets have been sent to avoid to
+		 * restore the QoS params on packets that are still on the
+		 * queues.
+		 */
+		synchronize_net();
+		ieee80211_flush_queues(local, sdata, false);
+
+		/* restore the normal QoS parameters
+		 * (unconditionally to avoid races)
+		 */
+		tx_tspec->action = TX_TSPEC_ACTION_STOP_DOWNGRADE;
+		tx_tspec->downgraded = false;
+		ieee80211_sta_handle_tspec_ac_params(sdata);
+
+		/* finally clear all the data */
+		memset(tx_tspec, 0, sizeof(*tx_tspec));
+
+		return 0;
+	}
+
+	return -ENOENT;
+}
+
 const struct cfg80211_ops mac80211_config_ops = {
 	.add_virtual_intf = ieee80211_add_iface,
 	.del_virtual_intf = ieee80211_del_iface,
@@ -3547,11 +3720,15 @@ const struct cfg80211_ops mac80211_config_ops = {
 	.change_mpath = ieee80211_change_mpath,
 	.get_mpath = ieee80211_get_mpath,
 	.dump_mpath = ieee80211_dump_mpath,
+	.get_mpp = ieee80211_get_mpp,
+	.dump_mpp = ieee80211_dump_mpp,
 	.update_mesh_config = ieee80211_update_mesh_config,
 	.get_mesh_config = ieee80211_get_mesh_config,
 	.join_mesh = ieee80211_join_mesh,
 	.leave_mesh = ieee80211_leave_mesh,
 #endif
+	.join_ocb = ieee80211_join_ocb,
+	.leave_ocb = ieee80211_leave_ocb,
 	.change_bss = ieee80211_change_bss,
 	.set_txq_params = ieee80211_set_txq_params,
 	.set_monitor_channel = ieee80211_set_monitor_channel,
@@ -3587,6 +3764,8 @@ const struct cfg80211_ops mac80211_config_ops = {
 	.set_rekey_data = ieee80211_set_rekey_data,
 	.tdls_oper = ieee80211_tdls_oper,
 	.tdls_mgmt = ieee80211_tdls_mgmt,
+	.tdls_channel_switch = ieee80211_tdls_channel_switch,
+	.tdls_cancel_channel_switch = ieee80211_tdls_cancel_channel_switch,
 	.probe_client = ieee80211_probe_client,
 	.set_noack_map = ieee80211_set_noack_map,
 #ifdef CONFIG_PM
@@ -3597,4 +3776,6 @@ const struct cfg80211_ops mac80211_config_ops = {
 	.channel_switch = ieee80211_channel_switch,
 	.set_qos_map = ieee80211_set_qos_map,
 	.set_ap_chanwidth = ieee80211_set_ap_chanwidth,
+	.add_tx_ts = ieee80211_add_tx_ts,
+	.del_tx_ts = ieee80211_del_tx_ts,
 };
diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index 4c74e8da64b9..5bcd4e5589d3 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -270,6 +270,7 @@ ieee80211_get_chanctx_max_required_bw(struct ieee80211_local *local,
 		case NL80211_IFTYPE_ADHOC:
 		case NL80211_IFTYPE_WDS:
 		case NL80211_IFTYPE_MESH_POINT:
+		case NL80211_IFTYPE_OCB:
 			width = vif->bss_conf.chandef.width;
 			break;
 		case NL80211_IFTYPE_UNSPECIFIED:
@@ -387,7 +388,7 @@ ieee80211_find_chanctx(struct ieee80211_local *local,
 	return NULL;
 }
 
-static bool ieee80211_is_radar_required(struct ieee80211_local *local)
+bool ieee80211_is_radar_required(struct ieee80211_local *local)
 {
 	struct ieee80211_sub_if_data *sdata;
 
@@ -405,6 +406,34 @@ static bool ieee80211_is_radar_required(struct ieee80211_local *local)
 	return false;
 }
 
+static bool
+ieee80211_chanctx_radar_required(struct ieee80211_local *local,
+				 struct ieee80211_chanctx *ctx)
+{
+	struct ieee80211_chanctx_conf *conf = &ctx->conf;
+	struct ieee80211_sub_if_data *sdata;
+	bool required = false;
+
+	lockdep_assert_held(&local->chanctx_mtx);
+	lockdep_assert_held(&local->mtx);
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(sdata, &local->interfaces, list) {
+		if (!ieee80211_sdata_running(sdata))
+			continue;
+		if (rcu_access_pointer(sdata->vif.chanctx_conf) != conf)
+			continue;
+		if (!sdata->radar_required)
+			continue;
+
+		required = true;
+		break;
+	}
+	rcu_read_unlock();
+
+	return required;
+}
+
 static struct ieee80211_chanctx *
 ieee80211_alloc_chanctx(struct ieee80211_local *local,
 			const struct cfg80211_chan_def *chandef,
@@ -424,7 +453,7 @@ ieee80211_alloc_chanctx(struct ieee80211_local *local,
 	ctx->conf.rx_chains_static = 1;
 	ctx->conf.rx_chains_dynamic = 1;
 	ctx->mode = mode;
-	ctx->conf.radar_enabled = ieee80211_is_radar_required(local);
+	ctx->conf.radar_enabled = false;
 	ieee80211_recalc_chanctx_min_def(local, ctx);
 
 	return ctx;
@@ -566,16 +595,15 @@ static void ieee80211_recalc_radar_chanctx(struct ieee80211_local *local,
 	bool radar_enabled;
 
 	lockdep_assert_held(&local->chanctx_mtx);
-	/* for setting local->radar_detect_enabled */
+	/* for ieee80211_is_radar_required */
 	lockdep_assert_held(&local->mtx);
 
-	radar_enabled = ieee80211_is_radar_required(local);
+	radar_enabled = ieee80211_chanctx_radar_required(local, chanctx);
 
 	if (radar_enabled == chanctx->conf.radar_enabled)
 		return;
 
 	chanctx->conf.radar_enabled = radar_enabled;
-	local->radar_detect_enabled = chanctx->conf.radar_enabled;
 
 	if (!local->use_chanctx) {
 		local->hw.conf.radar_enabled = chanctx->conf.radar_enabled;
@@ -627,7 +655,7 @@ out:
 	}
 
 	if (new_ctx && ieee80211_chanctx_num_assigned(local, new_ctx) > 0) {
-		ieee80211_recalc_txpower(sdata);
+		ieee80211_recalc_txpower(sdata, false);
 		ieee80211_recalc_chanctx_min_def(local, new_ctx);
 	}
 
@@ -674,6 +702,7 @@ void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local,
 		case NL80211_IFTYPE_ADHOC:
 		case NL80211_IFTYPE_WDS:
 		case NL80211_IFTYPE_MESH_POINT:
+		case NL80211_IFTYPE_OCB:
 			break;
 		default:
 			WARN_ON_ONCE(1);
@@ -909,6 +938,7 @@ ieee80211_vif_chanctx_reservation_complete(struct ieee80211_sub_if_data *sdata)
 	case NL80211_IFTYPE_ADHOC:
 	case NL80211_IFTYPE_AP:
 	case NL80211_IFTYPE_MESH_POINT:
+	case NL80211_IFTYPE_OCB:
 		ieee80211_queue_work(&sdata->local->hw,
 				     &sdata->csa_finalize_work);
 		break;
@@ -929,6 +959,21 @@ ieee80211_vif_chanctx_reservation_complete(struct ieee80211_sub_if_data *sdata)
 	}
 }
 
+static void
+ieee80211_vif_update_chandef(struct ieee80211_sub_if_data *sdata,
+			     const struct cfg80211_chan_def *chandef)
+{
+	struct ieee80211_sub_if_data *vlan;
+
+	sdata->vif.bss_conf.chandef = *chandef;
+
+	if (sdata->vif.type != NL80211_IFTYPE_AP)
+		return;
+
+	list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list)
+		vlan->vif.bss_conf.chandef = *chandef;
+}
+
 static int
 ieee80211_vif_use_reserved_reassign(struct ieee80211_sub_if_data *sdata)
 {
@@ -991,7 +1036,11 @@ ieee80211_vif_use_reserved_reassign(struct ieee80211_sub_if_data *sdata)
 	if (sdata->vif.bss_conf.chandef.width != sdata->reserved_chandef.width)
 		changed = BSS_CHANGED_BANDWIDTH;
 
-	sdata->vif.bss_conf.chandef = sdata->reserved_chandef;
+	ieee80211_vif_update_chandef(sdata, &sdata->reserved_chandef);
+
+	ieee80211_recalc_smps_chanctx(local, new_ctx);
+	ieee80211_recalc_radar_chanctx(local, new_ctx);
+	ieee80211_recalc_chanctx_min_def(local, new_ctx);
 
 	if (changed)
 		ieee80211_bss_info_change_notify(sdata, changed);
@@ -1333,12 +1382,12 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local)
 			    sdata->reserved_chandef.width)
 				changed = BSS_CHANGED_BANDWIDTH;
 
-			sdata->vif.bss_conf.chandef = sdata->reserved_chandef;
+			ieee80211_vif_update_chandef(sdata, &sdata->reserved_chandef);
 			if (changed)
 				ieee80211_bss_info_change_notify(sdata,
 								 changed);
 
-			ieee80211_recalc_txpower(sdata);
+			ieee80211_recalc_txpower(sdata, false);
 		}
 
 		ieee80211_recalc_chanctx_chantype(local, ctx);
@@ -1459,6 +1508,8 @@ static void __ieee80211_vif_release_channel(struct ieee80211_sub_if_data *sdata)
 	if (ieee80211_chanctx_refcount(local, ctx) == 0)
 		ieee80211_free_chanctx(local, ctx);
 
+	sdata->radar_required = false;
+
 	/* Unreserving may ready an in-place reservation. */
 	if (use_reserved_switch)
 		ieee80211_vif_use_reserved_switch(local);
@@ -1504,7 +1555,7 @@ int ieee80211_vif_use_channel(struct ieee80211_sub_if_data *sdata,
 		goto out;
 	}
 
-	sdata->vif.bss_conf.chandef = *chandef;
+	ieee80211_vif_update_chandef(sdata, chandef);
 
 	ret = ieee80211_assign_vif_chanctx(sdata, ctx);
 	if (ret) {
@@ -1517,6 +1568,9 @@ int ieee80211_vif_use_channel(struct ieee80211_sub_if_data *sdata,
 	ieee80211_recalc_smps_chanctx(local, ctx);
 	ieee80211_recalc_radar_chanctx(local, ctx);
  out:
+	if (ret)
+		sdata->radar_required = false;
+
 	mutex_unlock(&local->chanctx_mtx);
 	return ret;
 }
@@ -1634,7 +1688,7 @@ int ieee80211_vif_change_bandwidth(struct ieee80211_sub_if_data *sdata,
 		}
 		break;
 	case IEEE80211_CHANCTX_WILL_BE_REPLACED:
-		/* TODO: Perhaps the bandwith change could be treated as a
+		/* TODO: Perhaps the bandwidth change could be treated as a
 		 * reservation itself? */
 		ret = -EBUSY;
 		goto out;
@@ -1646,7 +1700,7 @@ int ieee80211_vif_change_bandwidth(struct ieee80211_sub_if_data *sdata,
 		break;
 	}
 
-	sdata->vif.bss_conf.chandef = *chandef;
+	ieee80211_vif_update_chandef(sdata, chandef);
 
 	ieee80211_recalc_chanctx_chantype(local, ctx);
 
diff --git a/net/mac80211/debug.h b/net/mac80211/debug.h
index 493d68061f0c..1956b3115dd5 100644
--- a/net/mac80211/debug.h
+++ b/net/mac80211/debug.h
@@ -2,6 +2,12 @@
 #define __MAC80211_DEBUG_H
 #include <net/cfg80211.h>
 
+#ifdef CONFIG_MAC80211_OCB_DEBUG
+#define MAC80211_OCB_DEBUG 1
+#else
+#define MAC80211_OCB_DEBUG 0
+#endif
+
 #ifdef CONFIG_MAC80211_IBSS_DEBUG
 #define MAC80211_IBSS_DEBUG 1
 #else
@@ -131,6 +137,10 @@ do {									\
 	_sdata_dbg(MAC80211_HT_DEBUG && net_ratelimit(),		\
 		   sdata, fmt, ##__VA_ARGS__)
 
+#define ocb_dbg(sdata, fmt, ...)					\
+	_sdata_dbg(MAC80211_OCB_DEBUG,					\
+		   sdata, fmt, ##__VA_ARGS__)
+
 #define ibss_dbg(sdata, fmt, ...)					\
 	_sdata_dbg(MAC80211_IBSS_DEBUG,					\
 		   sdata, fmt, ##__VA_ARGS__)
diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c
index 54a189f0393e..23813ebb349c 100644
--- a/net/mac80211/debugfs.c
+++ b/net/mac80211/debugfs.c
@@ -18,172 +18,6 @@
 
 #define DEBUGFS_FORMAT_BUFFER_SIZE 100
 
-#define TX_LATENCY_BIN_DELIMTER_C ','
-#define TX_LATENCY_BIN_DELIMTER_S ","
-#define TX_LATENCY_BINS_DISABLED "enable(bins disabled)\n"
-#define TX_LATENCY_DISABLED "disable\n"
-
-
-/*
- * Display if Tx latency statistics & bins are enabled/disabled
- */
-static ssize_t sta_tx_latency_stat_read(struct file *file,
-					char __user *userbuf,
-					size_t count, loff_t *ppos)
-{
-	struct ieee80211_local *local = file->private_data;
-	struct ieee80211_tx_latency_bin_ranges  *tx_latency;
-	char *buf;
-	int bufsz, i, ret;
-	int pos = 0;
-
-	rcu_read_lock();
-
-	tx_latency = rcu_dereference(local->tx_latency);
-
-	if (tx_latency && tx_latency->n_ranges) {
-		bufsz = tx_latency->n_ranges * 15;
-		buf = kzalloc(bufsz, GFP_ATOMIC);
-		if (!buf)
-			goto err;
-
-		for (i = 0; i < tx_latency->n_ranges; i++)
-			pos += scnprintf(buf + pos, bufsz - pos, "%d,",
-					 tx_latency->ranges[i]);
-		pos += scnprintf(buf + pos, bufsz - pos, "\n");
-	} else if (tx_latency) {
-		bufsz = sizeof(TX_LATENCY_BINS_DISABLED) + 1;
-		buf = kzalloc(bufsz, GFP_ATOMIC);
-		if (!buf)
-			goto err;
-
-		pos += scnprintf(buf + pos, bufsz - pos, "%s\n",
-				 TX_LATENCY_BINS_DISABLED);
-	} else {
-		bufsz = sizeof(TX_LATENCY_DISABLED) + 1;
-		buf = kzalloc(bufsz, GFP_ATOMIC);
-		if (!buf)
-			goto err;
-
-		pos += scnprintf(buf + pos, bufsz - pos, "%s\n",
-				 TX_LATENCY_DISABLED);
-	}
-
-	rcu_read_unlock();
-
-	ret = simple_read_from_buffer(userbuf, count, ppos, buf, pos);
-	kfree(buf);
-
-	return ret;
-err:
-	rcu_read_unlock();
-	return -ENOMEM;
-}
-
-/*
- * Receive input from user regarding Tx latency statistics
- * The input should indicate if Tx latency statistics and bins are
- * enabled/disabled.
- * If bins are enabled input should indicate the amount of different bins and
- * their ranges. Each bin will count how many Tx frames transmitted within the
- * appropriate latency.
- * Legal input is:
- * a) "enable(bins disabled)" - to enable only general statistics
- * b) "a,b,c,d,...z" - to enable general statistics and bins, where all are
- * numbers and a < b < c < d.. < z
- * c) "disable" - disable all statistics
- * NOTE: must configure Tx latency statistics bins before stations connected.
- */
-
-static ssize_t sta_tx_latency_stat_write(struct file *file,
-					 const char __user *userbuf,
-					 size_t count, loff_t *ppos)
-{
-	struct ieee80211_local *local = file->private_data;
-	char buf[128] = {};
-	char *bins = buf;
-	char *token;
-	int buf_size, i, alloc_size;
-	int prev_bin = 0;
-	int n_ranges = 0;
-	int ret = count;
-	struct ieee80211_tx_latency_bin_ranges  *tx_latency;
-
-	if (sizeof(buf) <= count)
-		return -EINVAL;
-	buf_size = count;
-	if (copy_from_user(buf, userbuf, buf_size))
-		return -EFAULT;
-
-	mutex_lock(&local->sta_mtx);
-
-	/* cannot change config once we have stations */
-	if (local->num_sta)
-		goto unlock;
-
-	tx_latency =
-		rcu_dereference_protected(local->tx_latency,
-					  lockdep_is_held(&local->sta_mtx));
-
-	/* disable Tx statistics */
-	if (!strcmp(buf, TX_LATENCY_DISABLED)) {
-		if (!tx_latency)
-			goto unlock;
-		RCU_INIT_POINTER(local->tx_latency, NULL);
-		synchronize_rcu();
-		kfree(tx_latency);
-		goto unlock;
-	}
-
-	/* Tx latency already enabled */
-	if (tx_latency)
-		goto unlock;
-
-	if (strcmp(TX_LATENCY_BINS_DISABLED, buf)) {
-		/* check how many bins and between what ranges user requested */
-		token = buf;
-		while (*token != '\0') {
-			if (*token == TX_LATENCY_BIN_DELIMTER_C)
-				n_ranges++;
-			token++;
-		}
-		n_ranges++;
-	}
-
-	alloc_size = sizeof(struct ieee80211_tx_latency_bin_ranges) +
-		     n_ranges * sizeof(u32);
-	tx_latency = kzalloc(alloc_size, GFP_ATOMIC);
-	if (!tx_latency) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
-	tx_latency->n_ranges = n_ranges;
-	for (i = 0; i < n_ranges; i++) { /* setting bin ranges */
-		token = strsep(&bins, TX_LATENCY_BIN_DELIMTER_S);
-		sscanf(token, "%d", &tx_latency->ranges[i]);
-		/* bins values should be in ascending order */
-		if (prev_bin >= tx_latency->ranges[i]) {
-			ret = -EINVAL;
-			kfree(tx_latency);
-			goto unlock;
-		}
-		prev_bin = tx_latency->ranges[i];
-	}
-	rcu_assign_pointer(local->tx_latency, tx_latency);
-
-unlock:
-	mutex_unlock(&local->sta_mtx);
-
-	return ret;
-}
-
-static const struct file_operations stats_tx_latency_ops = {
-	.write = sta_tx_latency_stat_write,
-	.read = sta_tx_latency_stat_read,
-	.open = simple_open,
-	.llseek = generic_file_llseek,
-};
-
 int mac80211_format_buffer(char __user *userbuf, size_t count,
 				  loff_t *ppos, char *fmt, ...)
 {
@@ -303,8 +137,6 @@ static ssize_t hwflags_read(struct file *file, char __user *user_buf,
 		sf += scnprintf(buf + sf, mxln - sf, "SUPPORTS_DYNAMIC_PS\n");
 	if (local->hw.flags & IEEE80211_HW_MFP_CAPABLE)
 		sf += scnprintf(buf + sf, mxln - sf, "MFP_CAPABLE\n");
-	if (local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD)
-		sf += scnprintf(buf + sf, mxln - sf, "SUPPORTS_UAPSD\n");
 	if (local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS)
 		sf += scnprintf(buf + sf, mxln - sf,
 				"REPORTS_TX_ACK_STATUS\n");
@@ -442,8 +274,6 @@ void debugfs_hw_add(struct ieee80211_local *local)
 #ifdef CONFIG_MAC80211_DEBUG_COUNTERS
 	DEBUGFS_STATS_ADD(tx_handlers_drop, local->tx_handlers_drop);
 	DEBUGFS_STATS_ADD(tx_handlers_queued, local->tx_handlers_queued);
-	DEBUGFS_STATS_ADD(tx_handlers_drop_unencrypted,
-		local->tx_handlers_drop_unencrypted);
 	DEBUGFS_STATS_ADD(tx_handlers_drop_fragment,
 		local->tx_handlers_drop_fragment);
 	DEBUGFS_STATS_ADD(tx_handlers_drop_wep,
@@ -477,6 +307,4 @@ void debugfs_hw_add(struct ieee80211_local *local)
 	DEBUGFS_DEVSTATS_ADD(dot11RTSFailureCount);
 	DEBUGFS_DEVSTATS_ADD(dot11FCSErrorCount);
 	DEBUGFS_DEVSTATS_ADD(dot11RTSSuccessCount);
-
-	DEBUGFS_DEVSTATS_ADD(tx_latency);
 }
diff --git a/net/mac80211/debugfs_key.c b/net/mac80211/debugfs_key.c
index 1521cabad3d6..71ac1b5f4da5 100644
--- a/net/mac80211/debugfs_key.c
+++ b/net/mac80211/debugfs_key.c
@@ -94,17 +94,33 @@ static ssize_t key_tx_spec_read(struct file *file, char __user *userbuf,
 				key->u.tkip.tx.iv16);
 		break;
 	case WLAN_CIPHER_SUITE_CCMP:
+	case WLAN_CIPHER_SUITE_CCMP_256:
 		pn = atomic64_read(&key->u.ccmp.tx_pn);
 		len = scnprintf(buf, sizeof(buf), "%02x%02x%02x%02x%02x%02x\n",
 				(u8)(pn >> 40), (u8)(pn >> 32), (u8)(pn >> 24),
 				(u8)(pn >> 16), (u8)(pn >> 8), (u8)pn);
 		break;
 	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 		pn = atomic64_read(&key->u.aes_cmac.tx_pn);
 		len = scnprintf(buf, sizeof(buf), "%02x%02x%02x%02x%02x%02x\n",
 				(u8)(pn >> 40), (u8)(pn >> 32), (u8)(pn >> 24),
 				(u8)(pn >> 16), (u8)(pn >> 8), (u8)pn);
 		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		pn = atomic64_read(&key->u.aes_gmac.tx_pn);
+		len = scnprintf(buf, sizeof(buf), "%02x%02x%02x%02x%02x%02x\n",
+				(u8)(pn >> 40), (u8)(pn >> 32), (u8)(pn >> 24),
+				(u8)(pn >> 16), (u8)(pn >> 8), (u8)pn);
+		break;
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		pn = atomic64_read(&key->u.gcmp.tx_pn);
+		len = scnprintf(buf, sizeof(buf), "%02x%02x%02x%02x%02x%02x\n",
+				(u8)(pn >> 40), (u8)(pn >> 32), (u8)(pn >> 24),
+				(u8)(pn >> 16), (u8)(pn >> 8), (u8)pn);
+		break;
 	default:
 		return 0;
 	}
@@ -134,6 +150,7 @@ static ssize_t key_rx_spec_read(struct file *file, char __user *userbuf,
 		len = p - buf;
 		break;
 	case WLAN_CIPHER_SUITE_CCMP:
+	case WLAN_CIPHER_SUITE_CCMP_256:
 		for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++) {
 			rpn = key->u.ccmp.rx_pn[i];
 			p += scnprintf(p, sizeof(buf)+buf-p,
@@ -144,6 +161,7 @@ static ssize_t key_rx_spec_read(struct file *file, char __user *userbuf,
 		len = p - buf;
 		break;
 	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 		rpn = key->u.aes_cmac.rx_pn;
 		p += scnprintf(p, sizeof(buf)+buf-p,
 			       "%02x%02x%02x%02x%02x%02x\n",
@@ -151,6 +169,26 @@ static ssize_t key_rx_spec_read(struct file *file, char __user *userbuf,
 			       rpn[3], rpn[4], rpn[5]);
 		len = p - buf;
 		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		rpn = key->u.aes_gmac.rx_pn;
+		p += scnprintf(p, sizeof(buf)+buf-p,
+			       "%02x%02x%02x%02x%02x%02x\n",
+			       rpn[0], rpn[1], rpn[2],
+			       rpn[3], rpn[4], rpn[5]);
+		len = p - buf;
+		break;
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++) {
+			rpn = key->u.gcmp.rx_pn[i];
+			p += scnprintf(p, sizeof(buf)+buf-p,
+				       "%02x%02x%02x%02x%02x%02x\n",
+				       rpn[0], rpn[1], rpn[2],
+				       rpn[3], rpn[4], rpn[5]);
+		}
+		len = p - buf;
+		break;
 	default:
 		return 0;
 	}
@@ -167,12 +205,23 @@ static ssize_t key_replays_read(struct file *file, char __user *userbuf,
 
 	switch (key->conf.cipher) {
 	case WLAN_CIPHER_SUITE_CCMP:
+	case WLAN_CIPHER_SUITE_CCMP_256:
 		len = scnprintf(buf, sizeof(buf), "%u\n", key->u.ccmp.replays);
 		break;
 	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 		len = scnprintf(buf, sizeof(buf), "%u\n",
 				key->u.aes_cmac.replays);
 		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		len = scnprintf(buf, sizeof(buf), "%u\n",
+				key->u.aes_gmac.replays);
+		break;
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		len = scnprintf(buf, sizeof(buf), "%u\n", key->u.gcmp.replays);
+		break;
 	default:
 		return 0;
 	}
@@ -189,9 +238,15 @@ static ssize_t key_icverrors_read(struct file *file, char __user *userbuf,
 
 	switch (key->conf.cipher) {
 	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 		len = scnprintf(buf, sizeof(buf), "%u\n",
 				key->u.aes_cmac.icverrors);
 		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		len = scnprintf(buf, sizeof(buf), "%u\n",
+				key->u.aes_gmac.icverrors);
+		break;
 	default:
 		return 0;
 	}
@@ -300,10 +355,8 @@ void ieee80211_debugfs_key_update_default(struct ieee80211_sub_if_data *sdata)
 
 	lockdep_assert_held(&sdata->local->key_mtx);
 
-	if (sdata->debugfs.default_unicast_key) {
-		debugfs_remove(sdata->debugfs.default_unicast_key);
-		sdata->debugfs.default_unicast_key = NULL;
-	}
+	debugfs_remove(sdata->debugfs.default_unicast_key);
+	sdata->debugfs.default_unicast_key = NULL;
 
 	if (sdata->default_unicast_key) {
 		key = key_mtx_dereference(sdata->local,
@@ -314,10 +367,8 @@ void ieee80211_debugfs_key_update_default(struct ieee80211_sub_if_data *sdata)
 					       sdata->vif.debugfs_dir, buf);
 	}
 
-	if (sdata->debugfs.default_multicast_key) {
-		debugfs_remove(sdata->debugfs.default_multicast_key);
-		sdata->debugfs.default_multicast_key = NULL;
-	}
+	debugfs_remove(sdata->debugfs.default_multicast_key);
+	sdata->debugfs.default_multicast_key = NULL;
 
 	if (sdata->default_multicast_key) {
 		key = key_mtx_dereference(sdata->local,
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index c68896adfa96..29236e832e44 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -177,7 +177,6 @@ static ssize_t ieee80211_if_write_##name(struct file *file,		\
 	IEEE80211_IF_FILE_R(name)
 
 /* common attributes */
-IEEE80211_IF_FILE(drop_unencrypted, drop_unencrypted, DEC);
 IEEE80211_IF_FILE(rc_rateidx_mask_2ghz, rc_rateidx_mask[IEEE80211_BAND_2GHZ],
 		  HEX);
 IEEE80211_IF_FILE(rc_rateidx_mask_5ghz, rc_rateidx_mask[IEEE80211_BAND_5GHZ],
@@ -562,7 +561,6 @@ IEEE80211_IF_FILE(dot11MeshAwakeWindowDuration,
 
 static void add_common_files(struct ieee80211_sub_if_data *sdata)
 {
-	DEBUGFS_ADD(drop_unencrypted);
 	DEBUGFS_ADD(rc_rateidx_mask_2ghz);
 	DEBUGFS_ADD(rc_rateidx_mask_5ghz);
 	DEBUGFS_ADD(rc_rateidx_mcs_mask_2ghz);
diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c
index bafe48916229..252859e90e8a 100644
--- a/net/mac80211/debugfs_sta.c
+++ b/net/mac80211/debugfs_sta.c
@@ -39,13 +39,6 @@ static const struct file_operations sta_ ##name## _ops = {		\
 	.llseek = generic_file_llseek,					\
 }
 
-#define STA_OPS_W(name)							\
-static const struct file_operations sta_ ##name## _ops = {		\
-	.write = sta_##name##_write,					\
-	.open = simple_open,						\
-	.llseek = generic_file_llseek,					\
-}
-
 #define STA_OPS_RW(name)						\
 static const struct file_operations sta_ ##name## _ops = {		\
 	.read = sta_##name##_read,					\
@@ -74,7 +67,7 @@ static ssize_t sta_flags_read(struct file *file, char __user *userbuf,
 	test_sta_flag(sta, WLAN_STA_##flg) ? #flg "\n" : ""
 
 	int res = scnprintf(buf, sizeof(buf),
-			    "%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s",
+			    "%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s",
 			    TEST(AUTH), TEST(ASSOC), TEST(PS_STA),
 			    TEST(PS_DRIVER), TEST(AUTHORIZED),
 			    TEST(SHORT_PREAMBLE),
@@ -82,10 +75,11 @@ static ssize_t sta_flags_read(struct file *file, char __user *userbuf,
 			    TEST(WDS), TEST(CLEAR_PS_FILT),
 			    TEST(MFP), TEST(BLOCK_BA), TEST(PSPOLL),
 			    TEST(UAPSD), TEST(SP), TEST(TDLS_PEER),
-			    TEST(TDLS_PEER_AUTH), TEST(4ADDR_EVENT),
-			    TEST(INSERTED), TEST(RATE_CONTROL),
-			    TEST(TOFFSET_KNOWN), TEST(MPSP_OWNER),
-			    TEST(MPSP_RECIPIENT));
+			    TEST(TDLS_PEER_AUTH), TEST(TDLS_INITIATOR),
+			    TEST(TDLS_CHAN_SWITCH), TEST(TDLS_OFF_CHANNEL),
+			    TEST(4ADDR_EVENT), TEST(INSERTED),
+			    TEST(RATE_CONTROL), TEST(TOFFSET_KNOWN),
+			    TEST(MPSP_OWNER), TEST(MPSP_RECIPIENT));
 #undef TEST
 	return simple_read_from_buffer(userbuf, count, ppos, buf, res);
 }
@@ -397,131 +391,6 @@ static ssize_t sta_last_rx_rate_read(struct file *file, char __user *userbuf,
 }
 STA_OPS(last_rx_rate);
 
-static int
-sta_tx_latency_stat_header(struct ieee80211_tx_latency_bin_ranges *tx_latency,
-			   char *buf, int pos, int bufsz)
-{
-	int i;
-	int range_count = tx_latency->n_ranges;
-	u32 *bin_ranges = tx_latency->ranges;
-
-	pos += scnprintf(buf + pos, bufsz - pos,
-			  "Station\t\t\tTID\tMax\tAvg");
-	if (range_count) {
-		pos += scnprintf(buf + pos, bufsz - pos,
-				  "\t<=%d", bin_ranges[0]);
-		for (i = 0; i < range_count - 1; i++)
-			pos += scnprintf(buf + pos, bufsz - pos, "\t%d-%d",
-					  bin_ranges[i], bin_ranges[i+1]);
-		pos += scnprintf(buf + pos, bufsz - pos,
-				  "\t%d<", bin_ranges[range_count - 1]);
-	}
-
-	pos += scnprintf(buf + pos, bufsz - pos, "\n");
-
-	return pos;
-}
-
-static int
-sta_tx_latency_stat_table(struct ieee80211_tx_latency_bin_ranges *tx_lat_range,
-			  struct ieee80211_tx_latency_stat *tx_lat,
-			  char *buf, int pos, int bufsz, int tid)
-{
-	u32 avg = 0;
-	int j;
-	int bin_count = tx_lat->bin_count;
-
-	pos += scnprintf(buf + pos, bufsz - pos, "\t\t\t%d", tid);
-	/* make sure you don't divide in 0 */
-	if (tx_lat->counter)
-		avg = tx_lat->sum / tx_lat->counter;
-
-	pos += scnprintf(buf + pos, bufsz - pos, "\t%d\t%d",
-			  tx_lat->max, avg);
-
-	if (tx_lat_range->n_ranges && tx_lat->bins)
-		for (j = 0; j < bin_count; j++)
-			pos += scnprintf(buf + pos, bufsz - pos,
-					  "\t%d", tx_lat->bins[j]);
-	pos += scnprintf(buf + pos, bufsz - pos, "\n");
-
-	return pos;
-}
-
-/*
- * Output Tx latency statistics station && restart all statistics information
- */
-static ssize_t sta_tx_latency_stat_read(struct file *file,
-					char __user *userbuf,
-					size_t count, loff_t *ppos)
-{
-	struct sta_info *sta = file->private_data;
-	struct ieee80211_local *local = sta->local;
-	struct ieee80211_tx_latency_bin_ranges *tx_latency;
-	char *buf;
-	int bufsz, ret, i;
-	int pos = 0;
-
-	bufsz = 20 * IEEE80211_NUM_TIDS *
-		sizeof(struct ieee80211_tx_latency_stat);
-	buf = kzalloc(bufsz, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	rcu_read_lock();
-
-	tx_latency = rcu_dereference(local->tx_latency);
-
-	if (!sta->tx_lat) {
-		pos += scnprintf(buf + pos, bufsz - pos,
-				 "Tx latency statistics are not enabled\n");
-		goto unlock;
-	}
-
-	pos = sta_tx_latency_stat_header(tx_latency, buf, pos, bufsz);
-
-	pos += scnprintf(buf + pos, bufsz - pos, "%pM\n", sta->sta.addr);
-	for (i = 0; i < IEEE80211_NUM_TIDS; i++)
-		pos = sta_tx_latency_stat_table(tx_latency, &sta->tx_lat[i],
-						buf, pos, bufsz, i);
-unlock:
-	rcu_read_unlock();
-
-	ret = simple_read_from_buffer(userbuf, count, ppos, buf, pos);
-	kfree(buf);
-
-	return ret;
-}
-STA_OPS(tx_latency_stat);
-
-static ssize_t sta_tx_latency_stat_reset_write(struct file *file,
-					       const char __user *userbuf,
-					       size_t count, loff_t *ppos)
-{
-	u32 *bins;
-	int bin_count;
-	struct sta_info *sta = file->private_data;
-	int i;
-
-	if (!sta->tx_lat)
-		return -EINVAL;
-
-	for (i = 0; i < IEEE80211_NUM_TIDS; i++) {
-		bins = sta->tx_lat[i].bins;
-		bin_count = sta->tx_lat[i].bin_count;
-
-		sta->tx_lat[i].max = 0;
-		sta->tx_lat[i].sum = 0;
-		sta->tx_lat[i].counter = 0;
-
-		if (bin_count)
-			memset(bins, 0, bin_count * sizeof(u32));
-	}
-
-	return count;
-}
-STA_OPS_W(tx_latency_stat_reset);
-
 #define DEBUGFS_ADD(name) \
 	debugfs_create_file(#name, 0400, \
 		sta->debugfs.dir, sta, &sta_ ##name## _ops);
@@ -575,8 +444,6 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta)
 	DEBUGFS_ADD(last_ack_signal);
 	DEBUGFS_ADD(current_tx_rate);
 	DEBUGFS_ADD(last_rx_rate);
-	DEBUGFS_ADD(tx_latency_stat);
-	DEBUGFS_ADD(tx_latency_stat_reset);
 
 	DEBUGFS_ADD_COUNTER(rx_packets, rx_packets);
 	DEBUGFS_ADD_COUNTER(tx_packets, tx_packets);
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 196d48c68134..26e1ca8a474a 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -214,7 +214,8 @@ static inline void drv_bss_info_changed(struct ieee80211_local *local,
 				    BSS_CHANGED_BEACON_ENABLED) &&
 			 sdata->vif.type != NL80211_IFTYPE_AP &&
 			 sdata->vif.type != NL80211_IFTYPE_ADHOC &&
-			 sdata->vif.type != NL80211_IFTYPE_MESH_POINT))
+			 sdata->vif.type != NL80211_IFTYPE_MESH_POINT &&
+			 sdata->vif.type != NL80211_IFTYPE_OCB))
 		return;
 
 	if (WARN_ON_ONCE(sdata->vif.type == NL80211_IFTYPE_P2P_DEVICE ||
@@ -379,23 +380,26 @@ static inline int drv_sched_scan_stop(struct ieee80211_local *local,
 	return ret;
 }
 
-static inline void drv_sw_scan_start(struct ieee80211_local *local)
+static inline void drv_sw_scan_start(struct ieee80211_local *local,
+				     struct ieee80211_sub_if_data *sdata,
+				     const u8 *mac_addr)
 {
 	might_sleep();
 
-	trace_drv_sw_scan_start(local);
+	trace_drv_sw_scan_start(local, sdata, mac_addr);
 	if (local->ops->sw_scan_start)
-		local->ops->sw_scan_start(&local->hw);
+		local->ops->sw_scan_start(&local->hw, &sdata->vif, mac_addr);
 	trace_drv_return_void(local);
 }
 
-static inline void drv_sw_scan_complete(struct ieee80211_local *local)
+static inline void drv_sw_scan_complete(struct ieee80211_local *local,
+					struct ieee80211_sub_if_data *sdata)
 {
 	might_sleep();
 
-	trace_drv_sw_scan_complete(local);
+	trace_drv_sw_scan_complete(local, sdata);
 	if (local->ops->sw_scan_complete)
-		local->ops->sw_scan_complete(&local->hw);
+		local->ops->sw_scan_complete(&local->hw, &sdata->vif);
 	trace_drv_return_void(local);
 }
 
@@ -620,6 +624,36 @@ static inline void drv_sta_rc_update(struct ieee80211_local *local,
 	trace_drv_return_void(local);
 }
 
+static inline void drv_sta_rate_tbl_update(struct ieee80211_local *local,
+					   struct ieee80211_sub_if_data *sdata,
+					   struct ieee80211_sta *sta)
+{
+	sdata = get_bss_sdata(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
+
+	trace_drv_sta_rate_tbl_update(local, sdata, sta);
+	if (local->ops->sta_rate_tbl_update)
+		local->ops->sta_rate_tbl_update(&local->hw, &sdata->vif, sta);
+
+	trace_drv_return_void(local);
+}
+
+static inline void drv_sta_statistics(struct ieee80211_local *local,
+				      struct ieee80211_sub_if_data *sdata,
+				      struct ieee80211_sta *sta,
+				      struct station_info *sinfo)
+{
+	sdata = get_bss_sdata(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
+
+	trace_drv_sta_statistics(local, sdata, sta);
+	if (local->ops->sta_statistics)
+		local->ops->sta_statistics(&local->hw, &sdata->vif, sta, sinfo);
+	trace_drv_return_void(local);
+}
+
 static inline int drv_conf_tx(struct ieee80211_local *local,
 			      struct ieee80211_sub_if_data *sdata, u16 ac,
 			      const struct ieee80211_tx_queue_params *params)
@@ -631,6 +665,12 @@ static inline int drv_conf_tx(struct ieee80211_local *local,
 	if (!check_sdata_in_driver(sdata))
 		return -EIO;
 
+	if (WARN_ONCE(params->cw_min == 0 ||
+		      params->cw_min > params->cw_max,
+		      "%s: invalid CW_min/CW_max: %d/%d\n",
+		      sdata->name, params->cw_min, params->cw_max))
+		return -EINVAL;
+
 	trace_drv_conf_tx(local, sdata, ac, params);
 	if (local->ops->conf_tx)
 		ret = local->ops->conf_tx(&local->hw, &sdata->vif,
@@ -764,12 +804,13 @@ static inline void drv_flush(struct ieee80211_local *local,
 }
 
 static inline void drv_channel_switch(struct ieee80211_local *local,
-				     struct ieee80211_channel_switch *ch_switch)
+				      struct ieee80211_sub_if_data *sdata,
+				      struct ieee80211_channel_switch *ch_switch)
 {
 	might_sleep();
 
-	trace_drv_channel_switch(local, ch_switch);
-	local->ops->channel_switch(&local->hw, ch_switch);
+	trace_drv_channel_switch(local, sdata, ch_switch);
+	local->ops->channel_switch(&local->hw, &sdata->vif, ch_switch);
 	trace_drv_return_void(local);
 }
 
@@ -900,13 +941,13 @@ static inline void drv_set_rekey_data(struct ieee80211_local *local,
 	trace_drv_return_void(local);
 }
 
-static inline void drv_rssi_callback(struct ieee80211_local *local,
-				     struct ieee80211_sub_if_data *sdata,
-				     const enum ieee80211_rssi_event event)
+static inline void drv_event_callback(struct ieee80211_local *local,
+				      struct ieee80211_sub_if_data *sdata,
+				      const struct ieee80211_event *event)
 {
-	trace_drv_rssi_callback(local, sdata, event);
-	if (local->ops->rssi_callback)
-		local->ops->rssi_callback(&local->hw, &sdata->vif, event);
+	trace_drv_event_callback(local, sdata, event);
+	if (local->ops->event_callback)
+		local->ops->event_callback(&local->hw, &sdata->vif, event);
 	trace_drv_return_void(local);
 }
 
@@ -940,21 +981,6 @@ drv_allow_buffered_frames(struct ieee80211_local *local,
 	trace_drv_return_void(local);
 }
 
-static inline int drv_get_rssi(struct ieee80211_local *local,
-				struct ieee80211_sub_if_data *sdata,
-				struct ieee80211_sta *sta,
-				s8 *rssi_dbm)
-{
-	int ret;
-
-	might_sleep();
-
-	ret = local->ops->get_rssi(&local->hw, &sdata->vif, sta, rssi_dbm);
-	trace_drv_get_rssi(local, sta, *rssi_dbm, ret);
-
-	return ret;
-}
-
 static inline void drv_mgd_prepare_tx(struct ieee80211_local *local,
 				      struct ieee80211_sub_if_data *sdata)
 {
@@ -1144,13 +1170,15 @@ static inline void drv_stop_ap(struct ieee80211_local *local,
 	trace_drv_return_void(local);
 }
 
-static inline void drv_restart_complete(struct ieee80211_local *local)
+static inline void
+drv_reconfig_complete(struct ieee80211_local *local,
+		      enum ieee80211_reconfig_type reconfig_type)
 {
 	might_sleep();
 
-	trace_drv_restart_complete(local);
-	if (local->ops->restart_complete)
-		local->ops->restart_complete(&local->hw);
+	trace_drv_reconfig_complete(local, reconfig_type);
+	if (local->ops->reconfig_complete)
+		local->ops->reconfig_complete(&local->hw, reconfig_type);
 	trace_drv_return_void(local);
 }
 
@@ -1196,6 +1224,40 @@ drv_channel_switch_beacon(struct ieee80211_sub_if_data *sdata,
 	}
 }
 
+static inline int
+drv_pre_channel_switch(struct ieee80211_sub_if_data *sdata,
+		       struct ieee80211_channel_switch *ch_switch)
+{
+	struct ieee80211_local *local = sdata->local;
+	int ret = 0;
+
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
+
+	trace_drv_pre_channel_switch(local, sdata, ch_switch);
+	if (local->ops->pre_channel_switch)
+		ret = local->ops->pre_channel_switch(&local->hw, &sdata->vif,
+						     ch_switch);
+	trace_drv_return_int(local, ret);
+	return ret;
+}
+
+static inline int
+drv_post_channel_switch(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_local *local = sdata->local;
+	int ret = 0;
+
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
+
+	trace_drv_post_channel_switch(local, sdata);
+	if (local->ops->post_channel_switch)
+		ret = local->ops->post_channel_switch(&local->hw, &sdata->vif);
+	trace_drv_return_int(local, ret);
+	return ret;
+}
+
 static inline int drv_join_ibss(struct ieee80211_local *local,
 				struct ieee80211_sub_if_data *sdata)
 {
@@ -1238,4 +1300,83 @@ static inline u32 drv_get_expected_throughput(struct ieee80211_local *local,
 	return ret;
 }
 
+static inline int drv_get_txpower(struct ieee80211_local *local,
+				  struct ieee80211_sub_if_data *sdata, int *dbm)
+{
+	int ret;
+
+	if (!local->ops->get_txpower)
+		return -EOPNOTSUPP;
+
+	ret = local->ops->get_txpower(&local->hw, &sdata->vif, dbm);
+	trace_drv_get_txpower(local, sdata, *dbm, ret);
+
+	return ret;
+}
+
+static inline int
+drv_tdls_channel_switch(struct ieee80211_local *local,
+			struct ieee80211_sub_if_data *sdata,
+			struct ieee80211_sta *sta, u8 oper_class,
+			struct cfg80211_chan_def *chandef,
+			struct sk_buff *tmpl_skb, u32 ch_sw_tm_ie)
+{
+	int ret;
+
+	might_sleep();
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
+
+	if (!local->ops->tdls_channel_switch)
+		return -EOPNOTSUPP;
+
+	trace_drv_tdls_channel_switch(local, sdata, sta, oper_class, chandef);
+	ret = local->ops->tdls_channel_switch(&local->hw, &sdata->vif, sta,
+					      oper_class, chandef, tmpl_skb,
+					      ch_sw_tm_ie);
+	trace_drv_return_int(local, ret);
+	return ret;
+}
+
+static inline void
+drv_tdls_cancel_channel_switch(struct ieee80211_local *local,
+			       struct ieee80211_sub_if_data *sdata,
+			       struct ieee80211_sta *sta)
+{
+	might_sleep();
+	if (!check_sdata_in_driver(sdata))
+		return;
+
+	if (!local->ops->tdls_cancel_channel_switch)
+		return;
+
+	trace_drv_tdls_cancel_channel_switch(local, sdata, sta);
+	local->ops->tdls_cancel_channel_switch(&local->hw, &sdata->vif, sta);
+	trace_drv_return_void(local);
+}
+
+static inline void
+drv_tdls_recv_channel_switch(struct ieee80211_local *local,
+			     struct ieee80211_sub_if_data *sdata,
+			     struct ieee80211_tdls_ch_sw_params *params)
+{
+	trace_drv_tdls_recv_channel_switch(local, sdata, params);
+	if (local->ops->tdls_recv_channel_switch)
+		local->ops->tdls_recv_channel_switch(&local->hw, &sdata->vif,
+						     params);
+	trace_drv_return_void(local);
+}
+
+static inline void drv_wake_tx_queue(struct ieee80211_local *local,
+				     struct txq_info *txq)
+{
+	struct ieee80211_sub_if_data *sdata = vif_to_sdata(txq->txq.vif);
+
+	if (!check_sdata_in_driver(sdata))
+		return;
+
+	trace_drv_wake_tx_queue(local, sdata, txq);
+	local->ops->wake_tx_queue(&local->hw, &txq->txq);
+}
+
 #endif /* __MAC80211_DRIVER_OPS */
diff --git a/net/mac80211/ethtool.c b/net/mac80211/ethtool.c
index ebfc8091557b..52bcea6ad9e8 100644
--- a/net/mac80211/ethtool.c
+++ b/net/mac80211/ethtool.c
@@ -117,16 +117,16 @@ static void ieee80211_get_stats(struct net_device *dev,
 		data[i++] = sta->sta_state;
 
 
-		if (sinfo.filled & STATION_INFO_TX_BITRATE)
+		if (sinfo.filled & BIT(NL80211_STA_INFO_TX_BITRATE))
 			data[i] = 100000 *
 				cfg80211_calculate_bitrate(&sinfo.txrate);
 		i++;
-		if (sinfo.filled & STATION_INFO_RX_BITRATE)
+		if (sinfo.filled & BIT(NL80211_STA_INFO_RX_BITRATE))
 			data[i] = 100000 *
 				cfg80211_calculate_bitrate(&sinfo.rxrate);
 		i++;
 
-		if (sinfo.filled & STATION_INFO_SIGNAL_AVG)
+		if (sinfo.filled & BIT(NL80211_STA_INFO_SIGNAL_AVG))
 			data[i] = (u8)sinfo.signal_avg;
 		i++;
 	} else {
@@ -175,24 +175,24 @@ do_survey:
 		data[i++] = (u8)survey.noise;
 	else
 		data[i++] = -1LL;
-	if (survey.filled & SURVEY_INFO_CHANNEL_TIME)
-		data[i++] = survey.channel_time;
+	if (survey.filled & SURVEY_INFO_TIME)
+		data[i++] = survey.time;
 	else
 		data[i++] = -1LL;
-	if (survey.filled & SURVEY_INFO_CHANNEL_TIME_BUSY)
-		data[i++] = survey.channel_time_busy;
+	if (survey.filled & SURVEY_INFO_TIME_BUSY)
+		data[i++] = survey.time_busy;
 	else
 		data[i++] = -1LL;
-	if (survey.filled & SURVEY_INFO_CHANNEL_TIME_EXT_BUSY)
-		data[i++] = survey.channel_time_ext_busy;
+	if (survey.filled & SURVEY_INFO_TIME_EXT_BUSY)
+		data[i++] = survey.time_ext_busy;
 	else
 		data[i++] = -1LL;
-	if (survey.filled & SURVEY_INFO_CHANNEL_TIME_RX)
-		data[i++] = survey.channel_time_rx;
+	if (survey.filled & SURVEY_INFO_TIME_RX)
+		data[i++] = survey.time_rx;
 	else
 		data[i++] = -1LL;
-	if (survey.filled & SURVEY_INFO_CHANNEL_TIME_TX)
-		data[i++] = survey.channel_time_tx;
+	if (survey.filled & SURVEY_INFO_TIME_TX)
+		data[i++] = survey.time_tx;
 	else
 		data[i++] = -1LL;
 
diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c
index ff630be2ca75..7a76ce639d58 100644
--- a/net/mac80211/ht.c
+++ b/net/mac80211/ht.c
@@ -252,8 +252,6 @@ bool ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_sub_if_data *sdata,
 		break;
 	}
 
-	if (bw != sta->sta.bandwidth)
-		changed = true;
 	sta->sta.bandwidth = bw;
 
 	sta->cur_max_bandwidth =
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index 509bc157ce55..bfef1b215050 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -188,6 +188,16 @@ ieee80211_ibss_build_presp(struct ieee80211_sub_if_data *sdata,
 		 */
 		pos = ieee80211_ie_build_ht_oper(pos, &sband->ht_cap,
 						 chandef, 0);
+
+		/* add VHT capability and information IEs */
+		if (chandef->width != NL80211_CHAN_WIDTH_20 &&
+		    chandef->width != NL80211_CHAN_WIDTH_40 &&
+		    sband->vht_cap.vht_supported) {
+			pos = ieee80211_ie_build_vht_cap(pos, &sband->vht_cap,
+							 sband->vht_cap.cap);
+			pos = ieee80211_ie_build_vht_oper(pos, &sband->vht_cap,
+							  chandef);
+		}
 	}
 
 	if (local->hw.queues >= IEEE80211_NUM_ACS)
@@ -249,8 +259,6 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 	if (presp)
 		kfree_rcu(presp, rcu_head);
 
-	sdata->drop_unencrypted = capability & WLAN_CAPABILITY_PRIVACY ? 1 : 0;
-
 	/* make a copy of the chandef, it could be modified below. */
 	chandef = *req_chandef;
 	chan = chandef.chan;
@@ -417,6 +425,11 @@ static void ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 					NL80211_CHAN_WIDTH_20_NOHT);
 		chandef.width = sdata->u.ibss.chandef.width;
 		break;
+	case NL80211_CHAN_WIDTH_80:
+	case NL80211_CHAN_WIDTH_160:
+		chandef = sdata->u.ibss.chandef;
+		chandef.chan = cbss->channel;
+		break;
 	default:
 		/* fall back to 20 MHz for unsupported modes */
 		cfg80211_chandef_create(&chandef, cbss->channel,
@@ -470,22 +483,19 @@ int ieee80211_ibss_csa_beacon(struct ieee80211_sub_if_data *sdata,
 	struct beacon_data *presp, *old_presp;
 	struct cfg80211_bss *cbss;
 	const struct cfg80211_bss_ies *ies;
-	u16 capability;
+	u16 capability = 0;
 	u64 tsf;
 	int ret = 0;
 
 	sdata_assert_lock(sdata);
 
-	capability = WLAN_CAPABILITY_IBSS;
-
 	if (ifibss->privacy)
-		capability |= WLAN_CAPABILITY_PRIVACY;
+		capability = WLAN_CAPABILITY_PRIVACY;
 
 	cbss = cfg80211_get_bss(sdata->local->hw.wiphy, ifibss->chandef.chan,
 				ifibss->bssid, ifibss->ssid,
-				ifibss->ssid_len, WLAN_CAPABILITY_IBSS |
-				WLAN_CAPABILITY_PRIVACY,
-				capability);
+				ifibss->ssid_len, IEEE80211_BSS_TYPE_IBSS,
+				IEEE80211_PRIVACY(ifibss->privacy));
 
 	if (WARN_ON(!cbss)) {
 		ret = -EINVAL;
@@ -525,23 +535,17 @@ 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, changed = 0;
-	u16 capability;
 
 	sdata_assert_lock(sdata);
 
 	/* update cfg80211 bss information with the new channel */
 	if (!is_zero_ether_addr(ifibss->bssid)) {
-		capability = WLAN_CAPABILITY_IBSS;
-
-		if (ifibss->privacy)
-			capability |= WLAN_CAPABILITY_PRIVACY;
-
 		cbss = cfg80211_get_bss(sdata->local->hw.wiphy,
 					ifibss->chandef.chan,
 					ifibss->bssid, ifibss->ssid,
-					ifibss->ssid_len, WLAN_CAPABILITY_IBSS |
-					WLAN_CAPABILITY_PRIVACY,
-					capability);
+					ifibss->ssid_len,
+					IEEE80211_BSS_TYPE_IBSS,
+					IEEE80211_PRIVACY(ifibss->privacy));
 		/* XXX: should not really modify cfg80211 data */
 		if (cbss) {
 			cbss->channel = sdata->csa_chandef.chan;
@@ -682,19 +686,13 @@ static void ieee80211_ibss_disconnect(struct ieee80211_sub_if_data *sdata)
 	struct cfg80211_bss *cbss;
 	struct beacon_data *presp;
 	struct sta_info *sta;
-	u16 capability;
 
 	if (!is_zero_ether_addr(ifibss->bssid)) {
-		capability = WLAN_CAPABILITY_IBSS;
-
-		if (ifibss->privacy)
-			capability |= WLAN_CAPABILITY_PRIVACY;
-
 		cbss = cfg80211_get_bss(local->hw.wiphy, ifibss->chandef.chan,
 					ifibss->bssid, ifibss->ssid,
-					ifibss->ssid_len, WLAN_CAPABILITY_IBSS |
-					WLAN_CAPABILITY_PRIVACY,
-					capability);
+					ifibss->ssid_len,
+					IEEE80211_BSS_TYPE_IBSS,
+					IEEE80211_PRIVACY(ifibss->privacy));
 
 		if (cbss) {
 			cfg80211_unlink_bss(local->hw.wiphy, cbss);
@@ -980,103 +978,140 @@ static void ieee80211_rx_mgmt_auth_ibss(struct ieee80211_sub_if_data *sdata,
 			    mgmt->sa, sdata->u.ibss.bssid, NULL, 0, 0, 0);
 }
 
-static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata,
-				  struct ieee80211_mgmt *mgmt, size_t len,
-				  struct ieee80211_rx_status *rx_status,
-				  struct ieee802_11_elems *elems)
+static void ieee80211_update_sta_info(struct ieee80211_sub_if_data *sdata,
+				      struct ieee80211_mgmt *mgmt, size_t len,
+				      struct ieee80211_rx_status *rx_status,
+				      struct ieee802_11_elems *elems,
+				      struct ieee80211_channel *channel)
 {
-	struct ieee80211_local *local = sdata->local;
-	struct cfg80211_bss *cbss;
-	struct ieee80211_bss *bss;
 	struct sta_info *sta;
-	struct ieee80211_channel *channel;
-	u64 beacon_timestamp, rx_timestamp;
-	u32 supp_rates = 0;
 	enum ieee80211_band band = rx_status->band;
 	enum nl80211_bss_scan_width scan_width;
+	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_supported_band *sband = local->hw.wiphy->bands[band];
 	bool rates_updated = false;
+	u32 supp_rates = 0;
 
-	channel = ieee80211_get_channel(local->hw.wiphy, rx_status->freq);
-	if (!channel)
+	if (sdata->vif.type != NL80211_IFTYPE_ADHOC)
 		return;
 
-	if (sdata->vif.type == NL80211_IFTYPE_ADHOC &&
-	    ether_addr_equal(mgmt->bssid, sdata->u.ibss.bssid)) {
+	if (!ether_addr_equal(mgmt->bssid, sdata->u.ibss.bssid))
+		return;
 
-		rcu_read_lock();
-		sta = sta_info_get(sdata, mgmt->sa);
-
-		if (elems->supp_rates) {
-			supp_rates = ieee80211_sta_get_rates(sdata, elems,
-							     band, NULL);
-			if (sta) {
-				u32 prev_rates;
-
-				prev_rates = sta->sta.supp_rates[band];
-				/* make sure mandatory rates are always added */
-				scan_width = NL80211_BSS_CHAN_WIDTH_20;
-				if (rx_status->flag & RX_FLAG_5MHZ)
-					scan_width = NL80211_BSS_CHAN_WIDTH_5;
-				if (rx_status->flag & RX_FLAG_10MHZ)
-					scan_width = NL80211_BSS_CHAN_WIDTH_10;
-
-				sta->sta.supp_rates[band] = supp_rates |
-					ieee80211_mandatory_rates(sband,
-								  scan_width);
-				if (sta->sta.supp_rates[band] != prev_rates) {
-					ibss_dbg(sdata,
-						 "updated supp_rates set for %pM based on beacon/probe_resp (0x%x -> 0x%x)\n",
-						 sta->sta.addr, prev_rates,
-						 sta->sta.supp_rates[band]);
-					rates_updated = true;
-				}
-			} else {
-				rcu_read_unlock();
-				sta = ieee80211_ibss_add_sta(sdata, mgmt->bssid,
-						mgmt->sa, supp_rates);
+	rcu_read_lock();
+	sta = sta_info_get(sdata, mgmt->sa);
+
+	if (elems->supp_rates) {
+		supp_rates = ieee80211_sta_get_rates(sdata, elems,
+						     band, NULL);
+		if (sta) {
+			u32 prev_rates;
+
+			prev_rates = sta->sta.supp_rates[band];
+			/* make sure mandatory rates are always added */
+			scan_width = NL80211_BSS_CHAN_WIDTH_20;
+			if (rx_status->flag & RX_FLAG_5MHZ)
+				scan_width = NL80211_BSS_CHAN_WIDTH_5;
+			if (rx_status->flag & RX_FLAG_10MHZ)
+				scan_width = NL80211_BSS_CHAN_WIDTH_10;
+
+			sta->sta.supp_rates[band] = supp_rates |
+				ieee80211_mandatory_rates(sband, scan_width);
+			if (sta->sta.supp_rates[band] != prev_rates) {
+				ibss_dbg(sdata,
+					 "updated supp_rates set for %pM based on beacon/probe_resp (0x%x -> 0x%x)\n",
+					 sta->sta.addr, prev_rates,
+					 sta->sta.supp_rates[band]);
+				rates_updated = true;
 			}
+		} else {
+			rcu_read_unlock();
+			sta = ieee80211_ibss_add_sta(sdata, mgmt->bssid,
+						     mgmt->sa, supp_rates);
 		}
+	}
 
-		if (sta && elems->wmm_info)
-			sta->sta.wme = true;
-
-		if (sta && elems->ht_operation && elems->ht_cap_elem &&
-		    sdata->u.ibss.chandef.width != NL80211_CHAN_WIDTH_20_NOHT &&
-		    sdata->u.ibss.chandef.width != NL80211_CHAN_WIDTH_5 &&
-		    sdata->u.ibss.chandef.width != NL80211_CHAN_WIDTH_10) {
-			/* we both use HT */
-			struct ieee80211_ht_cap htcap_ie;
-			struct cfg80211_chan_def chandef;
-
-			ieee80211_ht_oper_to_chandef(channel,
-						     elems->ht_operation,
-						     &chandef);
-
-			memcpy(&htcap_ie, elems->ht_cap_elem, sizeof(htcap_ie));
-
-			/*
-			 * fall back to HT20 if we don't use or use
-			 * the other extension channel
-			 */
-			if (chandef.center_freq1 !=
-			    sdata->u.ibss.chandef.center_freq1)
-				htcap_ie.cap_info &=
-					cpu_to_le16(~IEEE80211_HT_CAP_SUP_WIDTH_20_40);
-
-			rates_updated |= ieee80211_ht_cap_ie_to_sta_ht_cap(
-						sdata, sband, &htcap_ie, sta);
+	if (sta && elems->wmm_info && local->hw.queues >= IEEE80211_NUM_ACS)
+		sta->sta.wme = true;
+
+	if (sta && elems->ht_operation && elems->ht_cap_elem &&
+	    sdata->u.ibss.chandef.width != NL80211_CHAN_WIDTH_20_NOHT &&
+	    sdata->u.ibss.chandef.width != NL80211_CHAN_WIDTH_5 &&
+	    sdata->u.ibss.chandef.width != NL80211_CHAN_WIDTH_10) {
+		/* we both use HT */
+		struct ieee80211_ht_cap htcap_ie;
+		struct cfg80211_chan_def chandef;
+		enum ieee80211_sta_rx_bandwidth bw = sta->sta.bandwidth;
+
+		ieee80211_ht_oper_to_chandef(channel,
+					     elems->ht_operation,
+					     &chandef);
+
+		memcpy(&htcap_ie, elems->ht_cap_elem, sizeof(htcap_ie));
+		rates_updated |= ieee80211_ht_cap_ie_to_sta_ht_cap(sdata, sband,
+								   &htcap_ie,
+								   sta);
+
+		if (elems->vht_operation && elems->vht_cap_elem &&
+		    sdata->u.ibss.chandef.width != NL80211_CHAN_WIDTH_20 &&
+		    sdata->u.ibss.chandef.width != NL80211_CHAN_WIDTH_40) {
+			/* we both use VHT */
+			struct ieee80211_vht_cap cap_ie;
+			struct ieee80211_sta_vht_cap cap = sta->sta.vht_cap;
+
+			ieee80211_vht_oper_to_chandef(channel,
+						      elems->vht_operation,
+						      &chandef);
+			memcpy(&cap_ie, elems->vht_cap_elem, sizeof(cap_ie));
+			ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband,
+							    &cap_ie, sta);
+			if (memcmp(&cap, &sta->sta.vht_cap, sizeof(cap)))
+				rates_updated |= true;
 		}
 
-		if (sta && rates_updated) {
-			drv_sta_rc_update(local, sdata, &sta->sta,
-					  IEEE80211_RC_SUPP_RATES_CHANGED);
-			rate_control_rate_init(sta);
-		}
+		if (bw != sta->sta.bandwidth)
+			rates_updated |= true;
 
-		rcu_read_unlock();
+		if (!cfg80211_chandef_compatible(&sdata->u.ibss.chandef,
+						 &chandef))
+			WARN_ON_ONCE(1);
 	}
 
+	if (sta && rates_updated) {
+		u32 changed = IEEE80211_RC_SUPP_RATES_CHANGED;
+		u8 rx_nss = sta->sta.rx_nss;
+
+		/* Force rx_nss recalculation */
+		sta->sta.rx_nss = 0;
+		rate_control_rate_init(sta);
+		if (sta->sta.rx_nss != rx_nss)
+			changed |= IEEE80211_RC_NSS_CHANGED;
+
+		drv_sta_rc_update(local, sdata, &sta->sta, changed);
+	}
+
+	rcu_read_unlock();
+}
+
+static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata,
+				  struct ieee80211_mgmt *mgmt, size_t len,
+				  struct ieee80211_rx_status *rx_status,
+				  struct ieee802_11_elems *elems)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct cfg80211_bss *cbss;
+	struct ieee80211_bss *bss;
+	struct ieee80211_channel *channel;
+	u64 beacon_timestamp, rx_timestamp;
+	u32 supp_rates = 0;
+	enum ieee80211_band band = rx_status->band;
+
+	channel = ieee80211_get_channel(local->hw.wiphy, rx_status->freq);
+	if (!channel)
+		return;
+
+	ieee80211_update_sta_info(sdata, mgmt, len, rx_status, elems, channel);
+
 	bss = ieee80211_bss_info_update(local, rx_status, mgmt, len, elems,
 					channel);
 	if (!bss)
@@ -1266,7 +1301,7 @@ static void ieee80211_sta_merge_ibss(struct ieee80211_sub_if_data *sdata)
 
 	scan_width = cfg80211_chandef_to_scan_width(&ifibss->chandef);
 	ieee80211_request_ibss_scan(sdata, ifibss->ssid, ifibss->ssid_len,
-				    NULL, scan_width);
+				    NULL, 0, scan_width);
 }
 
 static void ieee80211_sta_create_ibss(struct ieee80211_sub_if_data *sdata)
@@ -1297,14 +1332,82 @@ static void ieee80211_sta_create_ibss(struct ieee80211_sub_if_data *sdata)
 
 	if (ifibss->privacy)
 		capability |= WLAN_CAPABILITY_PRIVACY;
-	else
-		sdata->drop_unencrypted = 0;
 
 	__ieee80211_sta_join_ibss(sdata, bssid, sdata->vif.bss_conf.beacon_int,
 				  &ifibss->chandef, ifibss->basic_rates,
 				  capability, 0, true);
 }
 
+static unsigned ibss_setup_channels(struct wiphy *wiphy,
+				    struct ieee80211_channel **channels,
+				    unsigned int channels_max,
+				    u32 center_freq, u32 width)
+{
+	struct ieee80211_channel *chan = NULL;
+	unsigned int n_chan = 0;
+	u32 start_freq, end_freq, freq;
+
+	if (width <= 20) {
+		start_freq = center_freq;
+		end_freq = center_freq;
+	} else {
+		start_freq = center_freq - width / 2 + 10;
+		end_freq = center_freq + width / 2 - 10;
+	}
+
+	for (freq = start_freq; freq <= end_freq; freq += 20) {
+		chan = ieee80211_get_channel(wiphy, freq);
+		if (!chan)
+			continue;
+		if (n_chan >= channels_max)
+			return n_chan;
+
+		channels[n_chan] = chan;
+		n_chan++;
+	}
+
+	return n_chan;
+}
+
+static unsigned int
+ieee80211_ibss_setup_scan_channels(struct wiphy *wiphy,
+				   const struct cfg80211_chan_def *chandef,
+				   struct ieee80211_channel **channels,
+				   unsigned int channels_max)
+{
+	unsigned int n_chan = 0;
+	u32 width, cf1, cf2 = 0;
+
+	switch (chandef->width) {
+	case NL80211_CHAN_WIDTH_40:
+		width = 40;
+		break;
+	case NL80211_CHAN_WIDTH_80P80:
+		cf2 = chandef->center_freq2;
+		/* fall through */
+	case NL80211_CHAN_WIDTH_80:
+		width = 80;
+		break;
+	case NL80211_CHAN_WIDTH_160:
+		width = 160;
+		break;
+	default:
+		width = 20;
+		break;
+	}
+
+	cf1 = chandef->center_freq1;
+
+	n_chan = ibss_setup_channels(wiphy, channels, channels_max, cf1, width);
+
+	if (cf2)
+		n_chan += ibss_setup_channels(wiphy, &channels[n_chan],
+					      channels_max - n_chan, cf2,
+					      width);
+
+	return n_chan;
+}
+
 /*
  * This function is called with state == IEEE80211_IBSS_MLME_SEARCH
  */
@@ -1318,7 +1421,6 @@ static void ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata)
 	const u8 *bssid = NULL;
 	enum nl80211_bss_scan_width scan_width;
 	int active_ibss;
-	u16 capability;
 
 	sdata_assert_lock(sdata);
 
@@ -1328,9 +1430,6 @@ static void ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata)
 	if (active_ibss)
 		return;
 
-	capability = WLAN_CAPABILITY_IBSS;
-	if (ifibss->privacy)
-		capability |= WLAN_CAPABILITY_PRIVACY;
 	if (ifibss->fixed_bssid)
 		bssid = ifibss->bssid;
 	if (ifibss->fixed_channel)
@@ -1339,8 +1438,8 @@ static void ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata)
 		bssid = ifibss->bssid;
 	cbss = cfg80211_get_bss(local->hw.wiphy, chan, bssid,
 				ifibss->ssid, ifibss->ssid_len,
-				WLAN_CAPABILITY_IBSS | WLAN_CAPABILITY_PRIVACY,
-				capability);
+				IEEE80211_BSS_TYPE_IBSS,
+				IEEE80211_PRIVACY(ifibss->privacy));
 
 	if (cbss) {
 		struct ieee80211_bss *bss;
@@ -1374,11 +1473,18 @@ static void ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata)
 	/* Selected IBSS not found in current scan results - try to scan */
 	if (time_after(jiffies, ifibss->last_scan_completed +
 					IEEE80211_SCAN_INTERVAL)) {
+		struct ieee80211_channel *channels[8];
+		unsigned int num;
+
 		sdata_info(sdata, "Trigger new scan to find an IBSS to join\n");
 
+		num = ieee80211_ibss_setup_scan_channels(local->hw.wiphy,
+							 &ifibss->chandef,
+							 channels,
+							 ARRAY_SIZE(channels));
 		scan_width = cfg80211_chandef_to_scan_width(&ifibss->chandef);
 		ieee80211_request_ibss_scan(sdata, ifibss->ssid,
-					    ifibss->ssid_len, chan,
+					    ifibss->ssid_len, channels, num,
 					    scan_width);
 	} else {
 		int interval = IEEE80211_SCAN_INTERVAL;
@@ -1735,7 +1841,7 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata)
 
 	ieee80211_ibss_disconnect(sdata);
 	ifibss->ssid_len = 0;
-	memset(ifibss->bssid, 0, ETH_ALEN);
+	eth_zero_addr(ifibss->bssid);
 
 	/* remove beacon */
 	kfree(sdata->u.ibss.ie);
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 8c68da30595d..c0a9187bc3a9 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -26,6 +26,7 @@
 #include <linux/etherdevice.h>
 #include <linux/leds.h>
 #include <linux/idr.h>
+#include <linux/rhashtable.h>
 #include <net/ieee80211_radiotap.h>
 #include <net/cfg80211.h>
 #include <net/mac80211.h>
@@ -58,13 +59,24 @@ struct ieee80211_local;
 #define IEEE80211_UNSET_POWER_LEVEL	INT_MIN
 
 /*
- * Some APs experience problems when working with U-APSD. Decrease the
- * probability of that happening by using legacy mode for all ACs but VO.
- * The AP that caused us trouble was a Cisco 4410N. It ignores our
- * setting, and always treats non-VO ACs as legacy.
+ * Some APs experience problems when working with U-APSD. Decreasing the
+ * probability of that happening by using legacy mode for all ACs but VO isn't
+ * enough.
+ *
+ * Cisco 4410N originally forced us to enable VO by default only because it
+ * treated non-VO ACs as legacy.
+ *
+ * However some APs (notably Netgear R7000) silently reclassify packets to
+ * different ACs. Since u-APSD ACs require trigger frames for frame retrieval
+ * clients would never see some frames (e.g. ARP responses) or would fetch them
+ * accidentally after a long time.
+ *
+ * It makes little sense to enable u-APSD queues by default because it needs
+ * userspace applications to be aware of it to actually take advantage of the
+ * possible additional powersavings. Implicitly depending on driver autotrigger
+ * frame support doesn't make much sense.
  */
-#define IEEE80211_DEFAULT_UAPSD_QUEUES \
-	IEEE80211_WMM_IE_STA_QOSINFO_AC_VO
+#define IEEE80211_DEFAULT_UAPSD_QUEUES 0
 
 #define IEEE80211_DEFAULT_MAX_SP_LEN		\
 	IEEE80211_WMM_IE_STA_QOSINFO_SP_ALL
@@ -131,7 +143,7 @@ enum ieee80211_bss_corrupt_data_flags {
  *
  * These are bss flags that are attached to a bss in the
  * @valid_data field of &struct ieee80211_bss.  They show which parts
- * of the data structure were recieved as a result of an un-corrupted
+ * of the data structure were received as a result of an un-corrupted
  * beacon/probe response.
  */
 enum ieee80211_bss_valid_data_flags {
@@ -193,6 +205,8 @@ enum ieee80211_packet_rx_flags {
  * @IEEE80211_RX_CMNTR: received on cooked monitor already
  * @IEEE80211_RX_BEACON_REPORTED: This frame was already reported
  *	to cfg80211_report_obss_beacon().
+ * @IEEE80211_RX_REORDER_TIMER: this frame is released by the
+ *	reorder buffer timeout timer, not the normal RX path
  *
  * These flags are used across handling multiple interfaces
  * for a single frame.
@@ -200,6 +214,7 @@ enum ieee80211_packet_rx_flags {
 enum ieee80211_rx_flags {
 	IEEE80211_RX_CMNTR		= BIT(0),
 	IEEE80211_RX_BEACON_REPORTED	= BIT(1),
+	IEEE80211_RX_REORDER_TIMER	= BIT(2),
 };
 
 struct ieee80211_rx_data {
@@ -313,12 +328,6 @@ struct mesh_preq_queue {
 	u8 flags;
 };
 
-#if HZ/100 == 0
-#define IEEE80211_ROC_MIN_LEFT	1
-#else
-#define IEEE80211_ROC_MIN_LEFT	(HZ/100)
-#endif
-
 struct ieee80211_roc_work {
 	struct list_head list;
 	struct list_head dependents;
@@ -399,6 +408,24 @@ struct ieee80211_mgd_assoc_data {
 	u8 ie[];
 };
 
+struct ieee80211_sta_tx_tspec {
+	/* timestamp of the first packet in the time slice */
+	unsigned long time_slice_start;
+
+	u32 admitted_time; /* in usecs, unlike over the air */
+	u8 tsid;
+	s8 up; /* signed to be able to invalidate with -1 during teardown */
+
+	/* consumed TX time in microseconds in the time slice */
+	u32 consumed_tx_time;
+	enum {
+		TX_TSPEC_ACTION_NONE = 0,
+		TX_TSPEC_ACTION_DOWNGRADE,
+		TX_TSPEC_ACTION_STOP_DOWNGRADE,
+	} action;
+	bool downgraded;
+};
+
 struct ieee80211_if_managed {
 	struct timer_list timer;
 	struct timer_list conn_mon_timer;
@@ -434,6 +461,9 @@ struct ieee80211_if_managed {
 
 	unsigned int flags;
 
+	bool csa_waiting_bcn;
+	bool csa_ignored_same_chan;
+
 	bool beacon_crc_valid;
 	u32 beacon_crc;
 
@@ -505,8 +535,23 @@ struct ieee80211_if_managed {
 	struct ieee80211_vht_cap vht_capa; /* configured VHT overrides */
 	struct ieee80211_vht_cap vht_capa_mask; /* Valid parts of vht_capa */
 
+	/* TDLS support */
 	u8 tdls_peer[ETH_ALEN] __aligned(2);
 	struct delayed_work tdls_peer_del_work;
+	struct sk_buff *orig_teardown_skb; /* The original teardown skb */
+	struct sk_buff *teardown_skb; /* A copy to send through the AP */
+	spinlock_t teardown_lock; /* To lock changing teardown_skb */
+	bool tdls_chan_switch_prohibited;
+
+	/* WMM-AC TSPEC support */
+	struct ieee80211_sta_tx_tspec tx_tspec[IEEE80211_NUM_ACS];
+	/* Use a separate work struct so that we can do something here
+	 * while the sdata->work is flushing the queues, for example.
+	 * otherwise, in scenarios where we hardly get any traffic out
+	 * on the BE queue, but there's a lot of VO traffic, we might
+	 * get stuck in a downgraded situation and flush takes forever.
+	 */
+	struct delayed_work tx_tspec_wk;
 };
 
 struct ieee80211_if_ibss {
@@ -547,6 +592,25 @@ struct ieee80211_if_ibss {
 };
 
 /**
+ * struct ieee80211_if_ocb - OCB mode state
+ *
+ * @housekeeping_timer: timer for periodic invocation of a housekeeping task
+ * @wrkq_flags: OCB deferred task action
+ * @incomplete_lock: delayed STA insertion lock
+ * @incomplete_stations: list of STAs waiting for delayed insertion
+ * @joined: indication if the interface is connected to an OCB network
+ */
+struct ieee80211_if_ocb {
+	struct timer_list housekeeping_timer;
+	unsigned long wrkq_flags;
+
+	spinlock_t incomplete_lock;
+	struct list_head incomplete_stations;
+
+	bool joined;
+};
+
+/**
  * struct ieee80211_mesh_sync_ops - Extensible synchronization framework interface
  *
  * these declarations define the interface, which enables
@@ -744,6 +808,19 @@ struct mac80211_qos_map {
 	struct rcu_head rcu_head;
 };
 
+enum txq_info_flags {
+	IEEE80211_TXQ_STOP,
+	IEEE80211_TXQ_AMPDU,
+};
+
+struct txq_info {
+	struct sk_buff_head queue;
+	unsigned long flags;
+
+	/* keep last! */
+	struct ieee80211_txq txq;
+};
+
 struct ieee80211_sub_if_data {
 	struct list_head list;
 
@@ -764,8 +841,6 @@ struct ieee80211_sub_if_data {
 
 	unsigned long state;
 
-	int drop_unencrypted;
-
 	char name[IFNAMSIZ];
 
 	/* Fragment table for host-based reassembly */
@@ -788,6 +863,7 @@ struct ieee80211_sub_if_data {
 	bool control_port_no_encrypt;
 	int encrypt_headroom;
 
+	atomic_t txqs_len[IEEE80211_NUM_ACS];
 	struct ieee80211_tx_queue_params tx_conf[IEEE80211_NUM_ACS];
 	struct mac80211_qos_map __rcu *qos_map;
 
@@ -839,6 +915,7 @@ struct ieee80211_sub_if_data {
 		struct ieee80211_if_managed mgd;
 		struct ieee80211_if_ibss ibss;
 		struct ieee80211_if_mesh mesh;
+		struct ieee80211_if_ocb ocb;
 		u32 mntr_flags;
 	} u;
 
@@ -938,6 +1015,7 @@ enum sdata_queue_type {
 	IEEE80211_SDATA_QUEUE_AGG_STOP		= 2,
 	IEEE80211_SDATA_QUEUE_RX_AGG_START	= 3,
 	IEEE80211_SDATA_QUEUE_RX_AGG_STOP	= 4,
+	IEEE80211_SDATA_QUEUE_TDLS_CHSW		= 5,
 };
 
 enum {
@@ -955,6 +1033,7 @@ enum queue_stop_reason {
 	IEEE80211_QUEUE_STOP_REASON_OFFCHANNEL,
 	IEEE80211_QUEUE_STOP_REASON_FLUSH,
 	IEEE80211_QUEUE_STOP_REASON_TDLS_TEARDOWN,
+	IEEE80211_QUEUE_STOP_REASON_RESERVE_TID,
 
 	IEEE80211_QUEUE_STOP_REASONS,
 };
@@ -973,24 +1052,6 @@ struct tpt_led_trigger {
 };
 #endif
 
-/*
- * struct ieee80211_tx_latency_bin_ranges - Tx latency statistics bins ranges
- *
- * Measuring Tx latency statistics. Counts how many Tx frames transmitted in a
- * certain latency range (in Milliseconds). Each station that uses these
- * ranges will have bins to count the amount of frames received in that range.
- * The user can configure the ranges via debugfs.
- * If ranges is NULL then Tx latency statistics bins are disabled for all
- * stations.
- *
- * @n_ranges: number of ranges that are taken in account
- * @ranges: the ranges that the user requested or NULL if disabled.
- */
-struct ieee80211_tx_latency_bin_ranges {
-	int n_ranges;
-	u32 ranges[];
-};
-
 /**
  * mac80211 scan flags - currently active scan mode
  *
@@ -1111,8 +1172,6 @@ struct ieee80211_local {
 	/* wowlan is enabled -- don't reconfig on resume */
 	bool wowlan;
 
-	/* DFS/radar detection is enabled */
-	bool radar_detect_enabled;
 	struct work_struct radar_detected_work;
 
 	/* number of RX chains the hardware has */
@@ -1140,16 +1199,10 @@ struct ieee80211_local {
 	spinlock_t tim_lock;
 	unsigned long num_sta;
 	struct list_head sta_list;
-	struct sta_info __rcu *sta_hash[STA_HASH_SIZE];
+	struct rhashtable sta_hash;
 	struct timer_list sta_cleanup;
 	int sta_generation;
 
-	/*
-	 * Tx latency statistics parameters for all stations.
-	 * Can enable via debugfs (NULL when disabled).
-	 */
-	struct ieee80211_tx_latency_bin_ranges __rcu *tx_latency;
-
 	struct sk_buff_head pending[IEEE80211_MAX_QUEUES];
 	struct tasklet_struct tx_pending_tasklet;
 
@@ -1181,7 +1234,7 @@ struct ieee80211_local {
 	unsigned long scanning;
 	struct cfg80211_ssid scan_ssid;
 	struct cfg80211_scan_request *int_scan_req;
-	struct cfg80211_scan_request *scan_req;
+	struct cfg80211_scan_request __rcu *scan_req;
 	struct ieee80211_scan_request *hw_scan_req;
 	struct cfg80211_chan_def scan_chandef;
 	enum ieee80211_band hw_scan_band;
@@ -1191,7 +1244,8 @@ 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;
+	struct cfg80211_sched_scan_request __rcu *sched_scan_req;
+	u8 scan_addr[ETH_ALEN];
 
 	unsigned long leave_oper_channel_time;
 	enum mac80211_scan_state next_scan_state;
@@ -1230,7 +1284,6 @@ struct ieee80211_local {
 	/* TX/RX handler statistics */
 	unsigned int tx_handlers_drop;
 	unsigned int tx_handlers_queued;
-	unsigned int tx_handlers_drop_unencrypted;
 	unsigned int tx_handlers_drop_fragment;
 	unsigned int tx_handlers_drop_wep;
 	unsigned int tx_handlers_drop_not_assoc;
@@ -1307,6 +1360,9 @@ struct ieee80211_local {
 	/* virtual monitor interface */
 	struct ieee80211_sub_if_data __rcu *monitor_sdata;
 	struct cfg80211_chan_def monitor_chandef;
+
+	/* extended capabilities provided by mac80211 */
+	u8 ext_capa[8];
 };
 
 static inline struct ieee80211_sub_if_data *
@@ -1342,6 +1398,9 @@ struct ieee802_11_elems {
 	size_t total_len;
 
 	/* pointers to IEs */
+	const struct ieee80211_tdls_lnkie *lnk_id;
+	const struct ieee80211_ch_switch_timing *ch_sw_timing;
+	const u8 *ext_capab;
 	const u8 *ssid;
 	const u8 *supp_rates;
 	const u8 *ds_params;
@@ -1376,6 +1435,7 @@ struct ieee802_11_elems {
 	const struct ieee80211_mesh_chansw_params_ie *mesh_chansw_params_ie;
 
 	/* length of them, respectively */
+	u8 ext_capab_len;
 	u8 ssid_len;
 	u8 supp_rates_len;
 	u8 tim_len;
@@ -1401,6 +1461,10 @@ static inline struct ieee80211_local *hw_to_local(
 	return container_of(hw, struct ieee80211_local, hw);
 }
 
+static inline struct txq_info *to_txq_info(struct ieee80211_txq *txq)
+{
+	return container_of(txq, struct txq_info, txq);
+}
 
 static inline int ieee80211_bssid_match(const u8 *raddr, const u8 *addr)
 {
@@ -1454,6 +1518,7 @@ 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);
+void ieee80211_sta_handle_tspec_ac_params(struct ieee80211_sub_if_data *sdata);
 
 /* IBSS code */
 void ieee80211_ibss_notify_scan_completed(struct ieee80211_local *local);
@@ -1471,6 +1536,15 @@ int ieee80211_ibss_csa_beacon(struct ieee80211_sub_if_data *sdata,
 int ieee80211_ibss_finish_csa(struct ieee80211_sub_if_data *sdata);
 void ieee80211_ibss_stop(struct ieee80211_sub_if_data *sdata);
 
+/* OCB code */
+void ieee80211_ocb_work(struct ieee80211_sub_if_data *sdata);
+void ieee80211_ocb_rx_no_sta(struct ieee80211_sub_if_data *sdata,
+			     const u8 *bssid, const u8 *addr, u32 supp_rates);
+void ieee80211_ocb_setup_sdata(struct ieee80211_sub_if_data *sdata);
+int ieee80211_ocb_join(struct ieee80211_sub_if_data *sdata,
+		       struct ocb_setup *setup);
+int ieee80211_ocb_leave(struct ieee80211_sub_if_data *sdata);
+
 /* mesh code */
 void ieee80211_mesh_work(struct ieee80211_sub_if_data *sdata);
 void ieee80211_mesh_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata,
@@ -1483,7 +1557,8 @@ int ieee80211_mesh_finish_csa(struct ieee80211_sub_if_data *sdata);
 void ieee80211_scan_work(struct work_struct *work);
 int ieee80211_request_ibss_scan(struct ieee80211_sub_if_data *sdata,
 				const u8 *ssid, u8 ssid_len,
-				struct ieee80211_channel *chan,
+				struct ieee80211_channel **channels,
+				unsigned int n_channels,
 				enum nl80211_bss_scan_width scan_width);
 int ieee80211_request_scan(struct ieee80211_sub_if_data *sdata,
 			   struct cfg80211_scan_request *req);
@@ -1532,6 +1607,7 @@ int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
 int ieee80211_iface_init(void);
 void ieee80211_iface_exit(void);
 int ieee80211_if_add(struct ieee80211_local *local, const char *name,
+		     unsigned char name_assign_type,
 		     struct wireless_dev **new_wdev, enum nl80211_iftype type,
 		     struct vif_params *params);
 int ieee80211_if_change_type(struct ieee80211_sub_if_data *sdata,
@@ -1548,7 +1624,8 @@ int ieee80211_add_virtual_monitor(struct ieee80211_local *local);
 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);
+void ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata,
+			      bool update_bss);
 
 static inline bool ieee80211_sdata_running(struct ieee80211_sub_if_data *sdata)
 {
@@ -1562,8 +1639,14 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb,
 					 struct net_device *dev);
 netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
 				       struct net_device *dev);
+void __ieee80211_subif_start_xmit(struct sk_buff *skb,
+				  struct net_device *dev,
+				  u32 info_flags);
 void ieee80211_purge_tx_queue(struct ieee80211_hw *hw,
 			      struct sk_buff_head *skbs);
+struct sk_buff *
+ieee80211_build_data_template(struct ieee80211_sub_if_data *sdata,
+			      struct sk_buff *skb, u32 info_flags);
 
 /* HT */
 void ieee80211_apply_htcap_overrides(struct ieee80211_sub_if_data *sdata,
@@ -1623,6 +1706,7 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata,
 				    struct ieee80211_supported_band *sband,
 				    const struct ieee80211_vht_cap *vht_cap_ie,
 				    struct sta_info *sta);
+enum ieee80211_sta_rx_bandwidth ieee80211_sta_cap_rx_bw(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,
@@ -1671,7 +1755,8 @@ static inline int __ieee80211_resume(struct ieee80211_hw *hw)
 {
 	struct ieee80211_local *local = hw_to_local(hw);
 
-	WARN(test_bit(SCAN_HW_SCANNING, &local->scanning),
+	WARN(test_bit(SCAN_HW_SCANNING, &local->scanning) &&
+	     !test_bit(SCAN_COMPLETED, &local->scanning),
 		"%s: resume with hardware scan still in progress\n",
 		wiphy_name(hw->wiphy));
 
@@ -1690,8 +1775,8 @@ void mac80211_ev_michael_mic_failure(struct ieee80211_sub_if_data *sdata, int ke
 				     gfp_t gfp);
 void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata,
 			       bool bss_notify);
-void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb,
-		    enum ieee80211_band band);
+void ieee80211_xmit(struct ieee80211_sub_if_data *sdata,
+		    struct sta_info *sta, struct sk_buff *skb);
 
 void __ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata,
 				 struct sk_buff *skb, int tid,
@@ -1757,6 +1842,13 @@ static inline bool ieee80211_rx_reorder_ready(struct sk_buff_head *frames)
 	return true;
 }
 
+extern const int ieee802_1d_to_ac[8];
+
+static inline int ieee80211_ac_from_tid(int tid)
+{
+	return ieee802_1d_to_ac[tid & 7];
+}
+
 void ieee80211_dynamic_ps_enable_work(struct work_struct *work);
 void ieee80211_dynamic_ps_disable_work(struct work_struct *work);
 void ieee80211_dynamic_ps_timer(unsigned long data);
@@ -1766,7 +1858,7 @@ void ieee80211_send_nullfunc(struct ieee80211_local *local,
 void ieee80211_sta_rx_notify(struct ieee80211_sub_if_data *sdata,
 			     struct ieee80211_hdr *hdr);
 void ieee80211_sta_tx_notify(struct ieee80211_sub_if_data *sdata,
-			     struct ieee80211_hdr *hdr, bool ack);
+			     struct ieee80211_hdr *hdr, bool ack, u16 tx_time);
 
 void ieee80211_wake_queues_by_reason(struct ieee80211_hw *hw,
 				     unsigned long queues,
@@ -1794,8 +1886,44 @@ void ieee80211_add_pending_skb(struct ieee80211_local *local,
 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);
+			    struct ieee80211_sub_if_data *sdata, bool drop);
+void __ieee80211_flush_queues(struct ieee80211_local *local,
+			      struct ieee80211_sub_if_data *sdata,
+			      unsigned int queues, bool drop);
+
+static inline bool ieee80211_can_run_worker(struct ieee80211_local *local)
+{
+	/*
+	 * If quiescing is set, we are racing with __ieee80211_suspend.
+	 * __ieee80211_suspend flushes the workers after setting quiescing,
+	 * and we check quiescing / suspended before enqueing new workers.
+	 * We should abort the worker to avoid the races below.
+	 */
+	if (local->quiescing)
+		return false;
 
+	/*
+	 * We might already be suspended if the following scenario occurs:
+	 * __ieee80211_suspend		Control path
+	 *
+	 *				if (local->quiescing)
+	 *					return;
+	 * local->quiescing = true;
+	 * flush_workqueue();
+	 *				queue_work(...);
+	 * local->suspended = true;
+	 * local->quiescing = false;
+	 *				worker starts running...
+	 */
+	if (local->suspended)
+		return false;
+
+	return true;
+}
+
+void ieee80211_init_tx_queue(struct ieee80211_sub_if_data *sdata,
+			     struct sta_info *sta,
+			     struct txq_info *txq, int tid);
 void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata,
 			 u16 transaction, u16 auth_alg, u16 status,
 			 const u8 *extra, size_t extra_len, const u8 *bssid,
@@ -1811,12 +1939,14 @@ int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer,
 			     u8 bands_used, u32 *rate_masks,
 			     struct cfg80211_chan_def *chandef);
 struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata,
-					  u8 *dst, u32 ratemask,
+					  const u8 *src, const u8 *dst,
+					  u32 ratemask,
 					  struct ieee80211_channel *chan,
 					  const u8 *ssid, size_t ssid_len,
 					  const u8 *ie, size_t ie_len,
 					  bool directed);
-void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata, u8 *dst,
+void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata,
+			      const u8 *src, const u8 *dst,
 			      const u8 *ssid, size_t ssid_len,
 			      const u8 *ie, size_t ie_len,
 			      u32 ratemask, bool directed, u32 tx_flags,
@@ -1832,8 +1962,6 @@ int __ieee80211_request_smps_ap(struct ieee80211_sub_if_data *sdata,
 void ieee80211_recalc_smps(struct ieee80211_sub_if_data *sdata);
 void ieee80211_recalc_min_chandef(struct ieee80211_sub_if_data *sdata);
 
-size_t ieee80211_ie_split(const u8 *ies, size_t ielen,
-			  const u8 *ids, int n_ids, size_t offset);
 size_t ieee80211_ie_split_vendor(const u8 *ies, size_t ielen, size_t offset);
 u8 *ieee80211_ie_build_ht_cap(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap,
 			      u16 cap);
@@ -1842,6 +1970,8 @@ u8 *ieee80211_ie_build_ht_oper(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap,
 			       u16 prot_mode);
 u8 *ieee80211_ie_build_vht_cap(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap,
 			       u32 cap);
+u8 *ieee80211_ie_build_vht_oper(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap,
+				const struct cfg80211_chan_def *chandef);
 int ieee80211_parse_bitrates(struct cfg80211_chan_def *chandef,
 			     const struct ieee80211_supported_band *sband,
 			     const u8 *srates, int srates_len, u32 *rates);
@@ -1857,6 +1987,9 @@ u8 *ieee80211_add_wmm_info_ie(u8 *buf, u8 qosinfo);
 void ieee80211_ht_oper_to_chandef(struct ieee80211_channel *control_chan,
 				  const struct ieee80211_ht_operation *ht_oper,
 				  struct cfg80211_chan_def *chandef);
+void ieee80211_vht_oper_to_chandef(struct ieee80211_channel *control_chan,
+				   const struct ieee80211_vht_operation *oper,
+				   struct cfg80211_chan_def *chandef);
 u32 ieee80211_chandef_downgrade(struct cfg80211_chan_def *c);
 
 int __must_check
@@ -1887,6 +2020,7 @@ void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local,
 				   struct ieee80211_chanctx *chanctx);
 void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local,
 				      struct ieee80211_chanctx *ctx);
+bool ieee80211_is_radar_required(struct ieee80211_local *local);
 
 void ieee80211_dfs_cac_timer(unsigned long data);
 void ieee80211_dfs_cac_timer_work(struct work_struct *work);
@@ -1920,6 +2054,14 @@ int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev,
 int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev,
 			const u8 *peer, enum nl80211_tdls_operation oper);
 void ieee80211_tdls_peer_del_work(struct work_struct *wk);
+int ieee80211_tdls_channel_switch(struct wiphy *wiphy, struct net_device *dev,
+				  const u8 *addr, u8 oper_class,
+				  struct cfg80211_chan_def *chandef);
+void ieee80211_tdls_cancel_channel_switch(struct wiphy *wiphy,
+					  struct net_device *dev,
+					  const u8 *addr);
+void ieee80211_process_tdls_channel_switch(struct ieee80211_sub_if_data *sdata,
+					   struct sk_buff *skb);
 
 extern const struct ethtool_ops ieee80211_ethtool_ops;
 
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 653f5eb07a27..84cef600c573 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -73,9 +73,10 @@ bool __ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata)
 	return false;
 }
 
-void ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata)
+void ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata,
+			      bool update_bss)
 {
-	if (__ieee80211_recalc_txpower(sdata))
+	if (__ieee80211_recalc_txpower(sdata) || update_bss)
 		ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_TXPOWER);
 }
 
@@ -93,7 +94,7 @@ static u32 __ieee80211_idle_on(struct ieee80211_local *local)
 	if (local->hw.conf.flags & IEEE80211_CONF_IDLE)
 		return 0;
 
-	ieee80211_flush_queues(local, NULL);
+	ieee80211_flush_queues(local, NULL, false);
 
 	local->hw.conf.flags |= IEEE80211_CONF_IDLE;
 	return IEEE80211_CONF_CHANGE_IDLE;
@@ -259,6 +260,15 @@ static int ieee80211_check_concurrent_iface(struct ieee80211_sub_if_data *sdata,
 	list_for_each_entry(nsdata, &local->interfaces, list) {
 		if (nsdata != sdata && ieee80211_sdata_running(nsdata)) {
 			/*
+			 * Only OCB and monitor mode may coexist
+			 */
+			if ((sdata->vif.type == NL80211_IFTYPE_OCB &&
+			     nsdata->vif.type != NL80211_IFTYPE_MONITOR) ||
+			    (sdata->vif.type != NL80211_IFTYPE_MONITOR &&
+			     nsdata->vif.type == NL80211_IFTYPE_OCB))
+				return -EBUSY;
+
+			/*
 			 * Allow only a single IBSS interface to be up at any
 			 * time. This is restricted because beacon distribution
 			 * cannot work properly if both are in the same IBSS.
@@ -511,6 +521,13 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
 		sdata->vif.cab_queue = master->vif.cab_queue;
 		memcpy(sdata->vif.hw_queue, master->vif.hw_queue,
 		       sizeof(sdata->vif.hw_queue));
+		sdata->vif.bss_conf.chandef = master->vif.bss_conf.chandef;
+
+		mutex_lock(&local->key_mtx);
+		sdata->crypto_tx_tailroom_needed_cnt +=
+			master->crypto_tx_tailroom_needed_cnt;
+		mutex_unlock(&local->key_mtx);
+
 		break;
 		}
 	case NL80211_IFTYPE_AP:
@@ -521,6 +538,7 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
 	case NL80211_IFTYPE_MONITOR:
 	case NL80211_IFTYPE_ADHOC:
 	case NL80211_IFTYPE_P2P_DEVICE:
+	case NL80211_IFTYPE_OCB:
 		/* no special treatment */
 		break;
 	case NL80211_IFTYPE_UNSPECIFIED:
@@ -631,6 +649,7 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
 		case NL80211_IFTYPE_ADHOC:
 		case NL80211_IFTYPE_AP:
 		case NL80211_IFTYPE_MESH_POINT:
+		case NL80211_IFTYPE_OCB:
 			netif_carrier_off(dev);
 			break;
 		case NL80211_IFTYPE_WDS:
@@ -806,13 +825,15 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
 	 * (because if we remove a STA after ops->remove_interface()
 	 * the driver will have removed the vif info already!)
 	 *
-	 * This is relevant only in WDS mode, in all other modes we've
-	 * already removed all stations when disconnecting or similar,
-	 * so warn otherwise.
+	 * In WDS mode a station must exist here and be flushed, for
+	 * AP_VLANs stations may exist since there's nothing else that
+	 * would have removed them, but in other modes there shouldn't
+	 * be any stations.
 	 */
 	flushed = sta_info_flush(sdata);
-	WARN_ON_ONCE((sdata->vif.type != NL80211_IFTYPE_WDS && flushed > 0) ||
-		     (sdata->vif.type == NL80211_IFTYPE_WDS && flushed != 1));
+	WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_AP_VLAN &&
+		     ((sdata->vif.type != NL80211_IFTYPE_WDS && flushed > 0) ||
+		      (sdata->vif.type == NL80211_IFTYPE_WDS && flushed != 1)));
 
 	/* don't count this interface for promisc/allmulti while it is down */
 	if (sdata->flags & IEEE80211_SDATA_ALLMULTI)
@@ -844,6 +865,8 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
 	sdata_lock(sdata);
 	mutex_lock(&local->mtx);
 	sdata->vif.csa_active = false;
+	if (sdata->vif.type == NL80211_IFTYPE_STATION)
+		sdata->u.mgd.csa_waiting_bcn = false;
 	if (sdata->csa_block_tx) {
 		ieee80211_wake_vif_queues(local, sdata,
 					  IEEE80211_QUEUE_STOP_REASON_CSA);
@@ -954,6 +977,13 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
 	}
 	spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
 
+	if (sdata->vif.txq) {
+		struct txq_info *txqi = to_txq_info(sdata->vif.txq);
+
+		ieee80211_purge_tx_queue(&local->hw, &txqi->queue);
+		atomic_set(&sdata->txqs_len[txqi->txq.ac], 0);
+	}
+
 	if (local->open_count == 0)
 		ieee80211_clear_tx_pending(local);
 
@@ -1155,12 +1185,7 @@ static void ieee80211_iface_work(struct work_struct *work)
 	if (local->scanning)
 		return;
 
-	/*
-	 * ieee80211_queue_work() should have picked up most cases,
-	 * here we'll pick the rest.
-	 */
-	if (WARN(local->suspended,
-		 "interface work scheduled while going to suspend\n"))
+	if (!ieee80211_can_run_worker(local))
 		return;
 
 	/* first process frames */
@@ -1195,6 +1220,8 @@ static void ieee80211_iface_work(struct work_struct *work)
 							WLAN_BACK_RECIPIENT, 0,
 							false);
 			mutex_unlock(&local->sta_mtx);
+		} else if (skb->pkt_type == IEEE80211_SDATA_QUEUE_TDLS_CHSW) {
+			ieee80211_process_tdls_channel_switch(sdata, skb);
 		} else if (ieee80211_is_action(mgmt->frame_control) &&
 			   mgmt->u.action.category == WLAN_CATEGORY_BACK) {
 			int len = skb->len;
@@ -1285,6 +1312,9 @@ static void ieee80211_iface_work(struct work_struct *work)
 			break;
 		ieee80211_mesh_work(sdata);
 		break;
+	case NL80211_IFTYPE_OCB:
+		ieee80211_ocb_work(sdata);
+		break;
 	default:
 		break;
 	}
@@ -1304,6 +1334,9 @@ static void ieee80211_recalc_smps_work(struct work_struct *work)
 static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata,
 				  enum nl80211_iftype type)
 {
+	static const u8 bssid_wildcard[ETH_ALEN] = {0xff, 0xff, 0xff,
+						    0xff, 0xff, 0xff};
+
 	/* clear type-dependent union */
 	memset(&sdata->u, 0, sizeof(sdata->u));
 
@@ -1355,6 +1388,10 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata,
 		sdata->vif.bss_conf.bssid = sdata->u.mgd.bssid;
 		ieee80211_sta_setup_sdata(sdata);
 		break;
+	case NL80211_IFTYPE_OCB:
+		sdata->vif.bss_conf.bssid = bssid_wildcard;
+		ieee80211_ocb_setup_sdata(sdata);
+		break;
 	case NL80211_IFTYPE_ADHOC:
 		sdata->vif.bss_conf.bssid = sdata->u.ibss.bssid;
 		ieee80211_ibss_setup_sdata(sdata);
@@ -1402,6 +1439,7 @@ static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata,
 	case NL80211_IFTYPE_AP:
 	case NL80211_IFTYPE_STATION:
 	case NL80211_IFTYPE_ADHOC:
+	case NL80211_IFTYPE_OCB:
 		/*
 		 * Could maybe also all others here?
 		 * Just not sure how that interacts
@@ -1417,6 +1455,7 @@ static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata,
 	case NL80211_IFTYPE_AP:
 	case NL80211_IFTYPE_STATION:
 	case NL80211_IFTYPE_ADHOC:
+	case NL80211_IFTYPE_OCB:
 		/*
 		 * Could probably support everything
 		 * but WDS here (WDS do_open can fail
@@ -1484,7 +1523,6 @@ int ieee80211_if_change_type(struct ieee80211_sub_if_data *sdata,
 	}
 
 	/* reset some values that shouldn't be kept across type changes */
-	sdata->drop_unencrypted = 0;
 	if (type == NL80211_IFTYPE_STATION)
 		sdata->u.mgd.use_4addr = false;
 
@@ -1625,11 +1663,13 @@ static void ieee80211_assign_perm_addr(struct ieee80211_local *local,
 }
 
 int ieee80211_if_add(struct ieee80211_local *local, const char *name,
+		     unsigned char name_assign_type,
 		     struct wireless_dev **new_wdev, enum nl80211_iftype type,
 		     struct vif_params *params)
 {
 	struct net_device *ndev = NULL;
 	struct ieee80211_sub_if_data *sdata = NULL;
+	struct txq_info *txqi;
 	int ret, i;
 	int txqs = 1;
 
@@ -1649,11 +1689,19 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name,
 		ieee80211_assign_perm_addr(local, wdev->address, type);
 		memcpy(sdata->vif.addr, wdev->address, ETH_ALEN);
 	} else {
+		int size = ALIGN(sizeof(*sdata) + local->hw.vif_data_size,
+				 sizeof(void *));
+		int txq_size = 0;
+
+		if (local->ops->wake_tx_queue)
+			txq_size += sizeof(struct txq_info) +
+				    local->hw.txq_data_size;
+
 		if (local->hw.queues >= IEEE80211_NUM_ACS)
 			txqs = IEEE80211_NUM_ACS;
 
-		ndev = alloc_netdev_mqs(sizeof(*sdata) + local->hw.vif_data_size,
-					name, NET_NAME_UNKNOWN,
+		ndev = alloc_netdev_mqs(size + txq_size,
+					name, name_assign_type,
 					ieee80211_if_setup, txqs, 1);
 		if (!ndev)
 			return -ENOMEM;
@@ -1675,7 +1723,10 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name,
 		}
 
 		ieee80211_assign_perm_addr(local, ndev->perm_addr, type);
-		memcpy(ndev->dev_addr, ndev->perm_addr, ETH_ALEN);
+		if (params && is_valid_ether_addr(params->macaddr))
+			memcpy(ndev->dev_addr, params->macaddr, ETH_ALEN);
+		else
+			memcpy(ndev->dev_addr, ndev->perm_addr, ETH_ALEN);
 		SET_NETDEV_DEV(ndev, wiphy_dev(local->hw.wiphy));
 
 		/* don't use IEEE80211_DEV_TO_SUB_IF -- it checks too much */
@@ -1684,6 +1735,11 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name,
 		memcpy(sdata->vif.addr, ndev->dev_addr, ETH_ALEN);
 		memcpy(sdata->name, ndev->name, IFNAMSIZ);
 
+		if (txq_size) {
+			txqi = netdev_priv(ndev) + size;
+			ieee80211_init_tx_queue(sdata, NULL, txqi, 0);
+		}
+
 		sdata->dev = ndev;
 	}
 
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index 4712150dc210..a907f2d5c12d 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -24,6 +24,8 @@
 #include "debugfs_key.h"
 #include "aes_ccm.h"
 #include "aes_cmac.h"
+#include "aes_gmac.h"
+#include "aes_gcm.h"
 
 
 /**
@@ -56,6 +58,22 @@ static void assert_key_lock(struct ieee80211_local *local)
 	lockdep_assert_held(&local->key_mtx);
 }
 
+static void
+update_vlan_tailroom_need_count(struct ieee80211_sub_if_data *sdata, int delta)
+{
+	struct ieee80211_sub_if_data *vlan;
+
+	if (sdata->vif.type != NL80211_IFTYPE_AP)
+		return;
+
+	mutex_lock(&sdata->local->mtx);
+
+	list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list)
+		vlan->crypto_tx_tailroom_needed_cnt += delta;
+
+	mutex_unlock(&sdata->local->mtx);
+}
+
 static void increment_tailroom_need_count(struct ieee80211_sub_if_data *sdata)
 {
 	/*
@@ -77,6 +95,8 @@ static void increment_tailroom_need_count(struct ieee80211_sub_if_data *sdata)
 	 * http://mid.gmane.org/1308590980.4322.19.camel@jlt3.sipsolutions.net
 	 */
 
+	update_vlan_tailroom_need_count(sdata, 1);
+
 	if (!sdata->crypto_tx_tailroom_needed_cnt++) {
 		/*
 		 * Flush all XMIT packets currently using HW encryption or no
@@ -86,16 +106,34 @@ static void increment_tailroom_need_count(struct ieee80211_sub_if_data *sdata)
 	}
 }
 
+static void decrease_tailroom_need_count(struct ieee80211_sub_if_data *sdata,
+					 int delta)
+{
+	WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt < delta);
+
+	update_vlan_tailroom_need_count(sdata, -delta);
+	sdata->crypto_tx_tailroom_needed_cnt -= delta;
+}
+
 static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key)
 {
 	struct ieee80211_sub_if_data *sdata;
 	struct sta_info *sta;
-	int ret;
+	int ret = -EOPNOTSUPP;
 
 	might_sleep();
 
-	if (key->flags & KEY_FLAG_TAINTED)
+	if (key->flags & KEY_FLAG_TAINTED) {
+		/* If we get here, it's during resume and the key is
+		 * tainted so shouldn't be used/programmed any more.
+		 * However, its flags may still indicate that it was
+		 * programmed into the device (since we're in resume)
+		 * so clear that flag now to avoid trying to remove
+		 * it again later.
+		 */
+		key->flags &= ~KEY_FLAG_UPLOADED_TO_HARDWARE;
 		return -EINVAL;
+	}
 
 	if (!key->local->ops->set_key)
 		goto out_unsupported;
@@ -131,8 +169,9 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key)
 	if (!ret) {
 		key->flags |= KEY_FLAG_UPLOADED_TO_HARDWARE;
 
-		if (!(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC))
-			sdata->crypto_tx_tailroom_needed_cnt--;
+		if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) ||
+		      (key->conf.flags & IEEE80211_KEY_FLAG_RESERVE_TAILROOM)))
+			decrease_tailroom_need_count(sdata, 1);
 
 		WARN_ON((key->conf.flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE) &&
 			(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV));
@@ -140,7 +179,7 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key)
 		return 0;
 	}
 
-	if (ret != -ENOSPC && ret != -EOPNOTSUPP)
+	if (ret != -ENOSPC && ret != -EOPNOTSUPP && ret != 1)
 		sdata_err(sdata,
 			  "failed to set key (%d, %pM) to hardware (%d)\n",
 			  key->conf.keyidx,
@@ -152,8 +191,18 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key)
 	case WLAN_CIPHER_SUITE_WEP104:
 	case WLAN_CIPHER_SUITE_TKIP:
 	case WLAN_CIPHER_SUITE_CCMP:
+	case WLAN_CIPHER_SUITE_CCMP_256:
 	case WLAN_CIPHER_SUITE_AES_CMAC:
-		/* all of these we can do in software */
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		/* all of these we can do in software - if driver can */
+		if (ret == 1)
+			return 0;
+		if (key->local->hw.flags & IEEE80211_HW_SW_CRYPTO_CONTROL)
+			return -EINVAL;
 		return 0;
 	default:
 		return -EINVAL;
@@ -179,7 +228,8 @@ static void ieee80211_key_disable_hw_accel(struct ieee80211_key *key)
 	sta = key->sta;
 	sdata = key->sdata;
 
-	if (!(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC))
+	if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) ||
+	      (key->conf.flags & IEEE80211_KEY_FLAG_RESERVE_TAILROOM)))
 		increment_tailroom_need_count(sdata);
 
 	ret = drv_set_key(key->local, DISABLE_KEY, sdata,
@@ -371,7 +421,26 @@ ieee80211_key_alloc(u32 cipher, int idx, size_t key_len,
 		 * Initialize AES key state here as an optimization so that
 		 * it does not need to be initialized for every packet.
 		 */
-		key->u.ccmp.tfm = ieee80211_aes_key_setup_encrypt(key_data);
+		key->u.ccmp.tfm = ieee80211_aes_key_setup_encrypt(
+			key_data, key_len, IEEE80211_CCMP_MIC_LEN);
+		if (IS_ERR(key->u.ccmp.tfm)) {
+			err = PTR_ERR(key->u.ccmp.tfm);
+			kfree(key);
+			return ERR_PTR(err);
+		}
+		break;
+	case WLAN_CIPHER_SUITE_CCMP_256:
+		key->conf.iv_len = IEEE80211_CCMP_256_HDR_LEN;
+		key->conf.icv_len = IEEE80211_CCMP_256_MIC_LEN;
+		for (i = 0; seq && i < IEEE80211_NUM_TIDS + 1; i++)
+			for (j = 0; j < IEEE80211_CCMP_256_PN_LEN; j++)
+				key->u.ccmp.rx_pn[i][j] =
+					seq[IEEE80211_CCMP_256_PN_LEN - j - 1];
+		/* Initialize AES key state here as an optimization so that
+		 * it does not need to be initialized for every packet.
+		 */
+		key->u.ccmp.tfm = ieee80211_aes_key_setup_encrypt(
+			key_data, key_len, IEEE80211_CCMP_256_MIC_LEN);
 		if (IS_ERR(key->u.ccmp.tfm)) {
 			err = PTR_ERR(key->u.ccmp.tfm);
 			kfree(key);
@@ -379,8 +448,12 @@ ieee80211_key_alloc(u32 cipher, int idx, size_t key_len,
 		}
 		break;
 	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 		key->conf.iv_len = 0;
-		key->conf.icv_len = sizeof(struct ieee80211_mmie);
+		if (cipher == WLAN_CIPHER_SUITE_AES_CMAC)
+			key->conf.icv_len = sizeof(struct ieee80211_mmie);
+		else
+			key->conf.icv_len = sizeof(struct ieee80211_mmie_16);
 		if (seq)
 			for (j = 0; j < IEEE80211_CMAC_PN_LEN; j++)
 				key->u.aes_cmac.rx_pn[j] =
@@ -390,13 +463,51 @@ ieee80211_key_alloc(u32 cipher, int idx, size_t key_len,
 		 * it does not need to be initialized for every packet.
 		 */
 		key->u.aes_cmac.tfm =
-			ieee80211_aes_cmac_key_setup(key_data);
+			ieee80211_aes_cmac_key_setup(key_data, key_len);
 		if (IS_ERR(key->u.aes_cmac.tfm)) {
 			err = PTR_ERR(key->u.aes_cmac.tfm);
 			kfree(key);
 			return ERR_PTR(err);
 		}
 		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		key->conf.iv_len = 0;
+		key->conf.icv_len = sizeof(struct ieee80211_mmie_16);
+		if (seq)
+			for (j = 0; j < IEEE80211_GMAC_PN_LEN; j++)
+				key->u.aes_gmac.rx_pn[j] =
+					seq[IEEE80211_GMAC_PN_LEN - j - 1];
+		/* Initialize AES key state here as an optimization so that
+		 * it does not need to be initialized for every packet.
+		 */
+		key->u.aes_gmac.tfm =
+			ieee80211_aes_gmac_key_setup(key_data, key_len);
+		if (IS_ERR(key->u.aes_gmac.tfm)) {
+			err = PTR_ERR(key->u.aes_gmac.tfm);
+			kfree(key);
+			return ERR_PTR(err);
+		}
+		break;
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		key->conf.iv_len = IEEE80211_GCMP_HDR_LEN;
+		key->conf.icv_len = IEEE80211_GCMP_MIC_LEN;
+		for (i = 0; seq && i < IEEE80211_NUM_TIDS + 1; i++)
+			for (j = 0; j < IEEE80211_GCMP_PN_LEN; j++)
+				key->u.gcmp.rx_pn[i][j] =
+					seq[IEEE80211_GCMP_PN_LEN - j - 1];
+		/* Initialize AES key state here as an optimization so that
+		 * it does not need to be initialized for every packet.
+		 */
+		key->u.gcmp.tfm = ieee80211_aes_gcm_key_setup_encrypt(key_data,
+								      key_len);
+		if (IS_ERR(key->u.gcmp.tfm)) {
+			err = PTR_ERR(key->u.gcmp.tfm);
+			kfree(key);
+			return ERR_PTR(err);
+		}
+		break;
 	default:
 		if (cs) {
 			size_t len = (seq_len > MAX_PN_LEN) ?
@@ -408,6 +519,7 @@ ieee80211_key_alloc(u32 cipher, int idx, size_t key_len,
 				for (j = 0; j < len; j++)
 					key->u.gen.rx_pn[i][j] =
 							seq[len - j - 1];
+			key->flags |= KEY_FLAG_CIPHER_SCHEME;
 		}
 	}
 	memcpy(key->conf.key, key_data, key_len);
@@ -418,10 +530,24 @@ ieee80211_key_alloc(u32 cipher, int idx, size_t key_len,
 
 static void ieee80211_key_free_common(struct ieee80211_key *key)
 {
-	if (key->conf.cipher == WLAN_CIPHER_SUITE_CCMP)
+	switch (key->conf.cipher) {
+	case WLAN_CIPHER_SUITE_CCMP:
+	case WLAN_CIPHER_SUITE_CCMP_256:
 		ieee80211_aes_key_free(key->u.ccmp.tfm);
-	if (key->conf.cipher == WLAN_CIPHER_SUITE_AES_CMAC)
+		break;
+	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 		ieee80211_aes_cmac_key_free(key->u.aes_cmac.tfm);
+		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		ieee80211_aes_gmac_key_free(key->u.aes_gmac.tfm);
+		break;
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		ieee80211_aes_gcm_key_free(key->u.gcmp.tfm);
+		break;
+	}
 	kzfree(key);
 }
 
@@ -442,7 +568,7 @@ static void __ieee80211_key_destroy(struct ieee80211_key *key,
 			schedule_delayed_work(&sdata->dec_tailroom_needed_wk,
 					      HZ/2);
 		} else {
-			sdata->crypto_tx_tailroom_needed_cnt--;
+			decrease_tailroom_need_count(sdata, 1);
 		}
 	}
 
@@ -532,6 +658,7 @@ void ieee80211_key_free(struct ieee80211_key *key, bool delay_tailroom)
 void ieee80211_enable_keys(struct ieee80211_sub_if_data *sdata)
 {
 	struct ieee80211_key *key;
+	struct ieee80211_sub_if_data *vlan;
 
 	ASSERT_RTNL();
 
@@ -540,7 +667,14 @@ void ieee80211_enable_keys(struct ieee80211_sub_if_data *sdata)
 
 	mutex_lock(&sdata->local->key_mtx);
 
-	sdata->crypto_tx_tailroom_needed_cnt = 0;
+	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);
+	}
 
 	list_for_each_entry(key, &sdata->key_list, list) {
 		increment_tailroom_need_count(sdata);
@@ -550,6 +684,22 @@ void ieee80211_enable_keys(struct ieee80211_sub_if_data *sdata)
 	mutex_unlock(&sdata->local->key_mtx);
 }
 
+void ieee80211_reset_crypto_tx_tailroom(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_sub_if_data *vlan;
+
+	mutex_lock(&sdata->local->key_mtx);
+
+	sdata->crypto_tx_tailroom_needed_cnt = 0;
+
+	if (sdata->vif.type == NL80211_IFTYPE_AP) {
+		list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list)
+			vlan->crypto_tx_tailroom_needed_cnt = 0;
+	}
+
+	mutex_unlock(&sdata->local->key_mtx);
+}
+
 void ieee80211_iter_keys(struct ieee80211_hw *hw,
 			 struct ieee80211_vif *vif,
 			 void (*iter)(struct ieee80211_hw *hw,
@@ -589,8 +739,8 @@ static void ieee80211_free_keys_iface(struct ieee80211_sub_if_data *sdata,
 {
 	struct ieee80211_key *key, *tmp;
 
-	sdata->crypto_tx_tailroom_needed_cnt -=
-		sdata->crypto_tx_tailroom_pending_dec;
+	decrease_tailroom_need_count(sdata,
+				     sdata->crypto_tx_tailroom_pending_dec);
 	sdata->crypto_tx_tailroom_pending_dec = 0;
 
 	ieee80211_debugfs_key_remove_mgmt_default(sdata);
@@ -610,6 +760,7 @@ void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata,
 {
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_sub_if_data *vlan;
+	struct ieee80211_sub_if_data *master;
 	struct ieee80211_key *key, *tmp;
 	LIST_HEAD(keys);
 
@@ -629,8 +780,20 @@ void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata,
 	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_VLAN) {
+		if (sdata->bss) {
+			master = container_of(sdata->bss,
+					      struct ieee80211_sub_if_data,
+					      u.ap);
+
+			WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt !=
+				     master->crypto_tx_tailroom_needed_cnt);
+		}
+	} else {
+		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 ||
@@ -647,7 +810,7 @@ void ieee80211_free_sta_keys(struct ieee80211_local *local,
 	int i;
 
 	mutex_lock(&local->key_mtx);
-	for (i = 0; i < NUM_DEFAULT_KEYS; i++) {
+	for (i = 0; i < ARRAY_SIZE(sta->gtk); i++) {
 		key = key_mtx_dereference(local, sta->gtk[i]);
 		if (!key)
 			continue;
@@ -694,8 +857,8 @@ void ieee80211_delayed_tailroom_dec(struct work_struct *wk)
 	 */
 
 	mutex_lock(&sdata->local->key_mtx);
-	sdata->crypto_tx_tailroom_needed_cnt -=
-		sdata->crypto_tx_tailroom_pending_dec;
+	decrease_tailroom_need_count(sdata,
+				     sdata->crypto_tx_tailroom_pending_dec);
 	sdata->crypto_tx_tailroom_pending_dec = 0;
 	mutex_unlock(&sdata->local->key_mtx);
 }
@@ -728,6 +891,7 @@ void ieee80211_get_key_tx_seq(struct ieee80211_key_conf *keyconf,
 		seq->tkip.iv16 = key->u.tkip.tx.iv16;
 		break;
 	case WLAN_CIPHER_SUITE_CCMP:
+	case WLAN_CIPHER_SUITE_CCMP_256:
 		pn64 = atomic64_read(&key->u.ccmp.tx_pn);
 		seq->ccmp.pn[5] = pn64;
 		seq->ccmp.pn[4] = pn64 >> 8;
@@ -737,6 +901,7 @@ void ieee80211_get_key_tx_seq(struct ieee80211_key_conf *keyconf,
 		seq->ccmp.pn[0] = pn64 >> 40;
 		break;
 	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 		pn64 = atomic64_read(&key->u.aes_cmac.tx_pn);
 		seq->ccmp.pn[5] = pn64;
 		seq->ccmp.pn[4] = pn64 >> 8;
@@ -745,6 +910,26 @@ void ieee80211_get_key_tx_seq(struct ieee80211_key_conf *keyconf,
 		seq->ccmp.pn[1] = pn64 >> 32;
 		seq->ccmp.pn[0] = pn64 >> 40;
 		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		pn64 = atomic64_read(&key->u.aes_gmac.tx_pn);
+		seq->ccmp.pn[5] = pn64;
+		seq->ccmp.pn[4] = pn64 >> 8;
+		seq->ccmp.pn[3] = pn64 >> 16;
+		seq->ccmp.pn[2] = pn64 >> 24;
+		seq->ccmp.pn[1] = pn64 >> 32;
+		seq->ccmp.pn[0] = pn64 >> 40;
+		break;
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		pn64 = atomic64_read(&key->u.gcmp.tx_pn);
+		seq->gcmp.pn[5] = pn64;
+		seq->gcmp.pn[4] = pn64 >> 8;
+		seq->gcmp.pn[3] = pn64 >> 16;
+		seq->gcmp.pn[2] = pn64 >> 24;
+		seq->gcmp.pn[1] = pn64 >> 32;
+		seq->gcmp.pn[0] = pn64 >> 40;
+		break;
 	default:
 		WARN_ON(1);
 	}
@@ -767,6 +952,7 @@ void ieee80211_get_key_rx_seq(struct ieee80211_key_conf *keyconf,
 		seq->tkip.iv16 = key->u.tkip.rx[tid].iv16;
 		break;
 	case WLAN_CIPHER_SUITE_CCMP:
+	case WLAN_CIPHER_SUITE_CCMP_256:
 		if (WARN_ON(tid < -1 || tid >= IEEE80211_NUM_TIDS))
 			return;
 		if (tid < 0)
@@ -776,11 +962,29 @@ void ieee80211_get_key_rx_seq(struct ieee80211_key_conf *keyconf,
 		memcpy(seq->ccmp.pn, pn, IEEE80211_CCMP_PN_LEN);
 		break;
 	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 		if (WARN_ON(tid != 0))
 			return;
 		pn = key->u.aes_cmac.rx_pn;
 		memcpy(seq->aes_cmac.pn, pn, IEEE80211_CMAC_PN_LEN);
 		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		if (WARN_ON(tid != 0))
+			return;
+		pn = key->u.aes_gmac.rx_pn;
+		memcpy(seq->aes_gmac.pn, pn, IEEE80211_GMAC_PN_LEN);
+		break;
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		if (WARN_ON(tid < -1 || tid >= IEEE80211_NUM_TIDS))
+			return;
+		if (tid < 0)
+			pn = key->u.gcmp.rx_pn[IEEE80211_NUM_TIDS];
+		else
+			pn = key->u.gcmp.rx_pn[tid];
+		memcpy(seq->gcmp.pn, pn, IEEE80211_GCMP_PN_LEN);
+		break;
 	}
 }
 EXPORT_SYMBOL(ieee80211_get_key_rx_seq);
@@ -799,6 +1003,7 @@ void ieee80211_set_key_tx_seq(struct ieee80211_key_conf *keyconf,
 		key->u.tkip.tx.iv16 = seq->tkip.iv16;
 		break;
 	case WLAN_CIPHER_SUITE_CCMP:
+	case WLAN_CIPHER_SUITE_CCMP_256:
 		pn64 = (u64)seq->ccmp.pn[5] |
 		       ((u64)seq->ccmp.pn[4] << 8) |
 		       ((u64)seq->ccmp.pn[3] << 16) |
@@ -808,6 +1013,7 @@ void ieee80211_set_key_tx_seq(struct ieee80211_key_conf *keyconf,
 		atomic64_set(&key->u.ccmp.tx_pn, pn64);
 		break;
 	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 		pn64 = (u64)seq->aes_cmac.pn[5] |
 		       ((u64)seq->aes_cmac.pn[4] << 8) |
 		       ((u64)seq->aes_cmac.pn[3] << 16) |
@@ -816,6 +1022,26 @@ void ieee80211_set_key_tx_seq(struct ieee80211_key_conf *keyconf,
 		       ((u64)seq->aes_cmac.pn[0] << 40);
 		atomic64_set(&key->u.aes_cmac.tx_pn, pn64);
 		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		pn64 = (u64)seq->aes_gmac.pn[5] |
+		       ((u64)seq->aes_gmac.pn[4] << 8) |
+		       ((u64)seq->aes_gmac.pn[3] << 16) |
+		       ((u64)seq->aes_gmac.pn[2] << 24) |
+		       ((u64)seq->aes_gmac.pn[1] << 32) |
+		       ((u64)seq->aes_gmac.pn[0] << 40);
+		atomic64_set(&key->u.aes_gmac.tx_pn, pn64);
+		break;
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		pn64 = (u64)seq->gcmp.pn[5] |
+		       ((u64)seq->gcmp.pn[4] << 8) |
+		       ((u64)seq->gcmp.pn[3] << 16) |
+		       ((u64)seq->gcmp.pn[2] << 24) |
+		       ((u64)seq->gcmp.pn[1] << 32) |
+		       ((u64)seq->gcmp.pn[0] << 40);
+		atomic64_set(&key->u.gcmp.tx_pn, pn64);
+		break;
 	default:
 		WARN_ON(1);
 		break;
@@ -839,6 +1065,7 @@ void ieee80211_set_key_rx_seq(struct ieee80211_key_conf *keyconf,
 		key->u.tkip.rx[tid].iv16 = seq->tkip.iv16;
 		break;
 	case WLAN_CIPHER_SUITE_CCMP:
+	case WLAN_CIPHER_SUITE_CCMP_256:
 		if (WARN_ON(tid < -1 || tid >= IEEE80211_NUM_TIDS))
 			return;
 		if (tid < 0)
@@ -848,11 +1075,29 @@ void ieee80211_set_key_rx_seq(struct ieee80211_key_conf *keyconf,
 		memcpy(pn, seq->ccmp.pn, IEEE80211_CCMP_PN_LEN);
 		break;
 	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 		if (WARN_ON(tid != 0))
 			return;
 		pn = key->u.aes_cmac.rx_pn;
 		memcpy(pn, seq->aes_cmac.pn, IEEE80211_CMAC_PN_LEN);
 		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		if (WARN_ON(tid != 0))
+			return;
+		pn = key->u.aes_gmac.rx_pn;
+		memcpy(pn, seq->aes_gmac.pn, IEEE80211_GMAC_PN_LEN);
+		break;
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		if (WARN_ON(tid < -1 || tid >= IEEE80211_NUM_TIDS))
+			return;
+		if (tid < 0)
+			pn = key->u.gcmp.rx_pn[IEEE80211_NUM_TIDS];
+		else
+			pn = key->u.gcmp.rx_pn[tid];
+		memcpy(pn, seq->gcmp.pn, IEEE80211_GCMP_PN_LEN);
+		break;
 	default:
 		WARN_ON(1);
 		break;
@@ -875,7 +1120,8 @@ void ieee80211_remove_key(struct ieee80211_key_conf *keyconf)
 	if (key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE) {
 		key->flags &= ~KEY_FLAG_UPLOADED_TO_HARDWARE;
 
-		if (!(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC))
+		if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) ||
+		      (key->conf.flags & IEEE80211_KEY_FLAG_RESERVE_TAILROOM)))
 			increment_tailroom_need_count(key->sdata);
 	}
 
diff --git a/net/mac80211/key.h b/net/mac80211/key.h
index 19db68663d75..96557dd1e77d 100644
--- a/net/mac80211/key.h
+++ b/net/mac80211/key.h
@@ -30,10 +30,12 @@ struct sta_info;
  * @KEY_FLAG_UPLOADED_TO_HARDWARE: Indicates that this key is present
  *	in the hardware for TX crypto hardware acceleration.
  * @KEY_FLAG_TAINTED: Key is tainted and packets should be dropped.
+ * @KEY_FLAG_CIPHER_SCHEME: This key is for a hardware cipher scheme
  */
 enum ieee80211_internal_key_flags {
 	KEY_FLAG_UPLOADED_TO_HARDWARE	= BIT(0),
 	KEY_FLAG_TAINTED		= BIT(1),
+	KEY_FLAG_CIPHER_SCHEME		= BIT(2),
 };
 
 enum ieee80211_internal_tkip_state {
@@ -95,6 +97,24 @@ struct ieee80211_key {
 			u32 icverrors; /* dot11RSNAStatsCMACICVErrors */
 		} aes_cmac;
 		struct {
+			atomic64_t tx_pn;
+			u8 rx_pn[IEEE80211_GMAC_PN_LEN];
+			struct crypto_aead *tfm;
+			u32 replays; /* dot11RSNAStatsCMACReplays */
+			u32 icverrors; /* dot11RSNAStatsCMACICVErrors */
+		} aes_gmac;
+		struct {
+			atomic64_t tx_pn;
+			/* Last received packet number. The first
+			 * IEEE80211_NUM_TIDS counters are used with Data
+			 * frames and the last counter is used with Robust
+			 * Management frames.
+			 */
+			u8 rx_pn[IEEE80211_NUM_TIDS + 1][IEEE80211_GCMP_PN_LEN];
+			struct crypto_aead *tfm;
+			u32 replays; /* dot11RSNAStatsGCMPReplays */
+		} gcmp;
+		struct {
 			/* generic cipher scheme */
 			u8 rx_pn[IEEE80211_NUM_TIDS + 1][MAX_PN_LEN];
 		} gen;
@@ -141,6 +161,7 @@ void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata,
 void ieee80211_free_sta_keys(struct ieee80211_local *local,
 			     struct sta_info *sta);
 void ieee80211_enable_keys(struct ieee80211_sub_if_data *sdata);
+void ieee80211_reset_crypto_tx_tailroom(struct ieee80211_sub_if_data *sdata);
 
 #define key_mtx_dereference(local, ref) \
 	rcu_dereference_protected(ref, lockdep_is_held(&((local)->key_mtx)))
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 0de7c93bf62b..df3051d96aff 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -478,13 +478,9 @@ static const struct ieee80211_vht_cap mac80211_vht_capa_mod_mask = {
 	},
 };
 
-static const u8 extended_capabilities[] = {
-	0, 0, 0, 0, 0, 0, 0,
-	WLAN_EXT_CAPA8_OPMODE_NOTIF,
-};
-
-struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len,
-					const struct ieee80211_ops *ops)
+struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len,
+					   const struct ieee80211_ops *ops,
+					   const char *requested_name)
 {
 	struct ieee80211_local *local;
 	int priv_size, i;
@@ -524,7 +520,7 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len,
 	 */
 	priv_size = ALIGN(sizeof(*local), NETDEV_ALIGN) + priv_data_len;
 
-	wiphy = wiphy_new(&mac80211_config_ops, priv_size);
+	wiphy = wiphy_new_nm(&mac80211_config_ops, priv_size, requested_name);
 
 	if (!wiphy)
 		return NULL;
@@ -539,10 +535,6 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len,
 			WIPHY_FLAG_REPORTS_OBSS |
 			WIPHY_FLAG_OFFCHAN_TX;
 
-	wiphy->extended_capabilities = extended_capabilities;
-	wiphy->extended_capabilities_mask = extended_capabilities;
-	wiphy->extended_capabilities_len = ARRAY_SIZE(extended_capabilities);
-
 	if (ops->remain_on_channel)
 		wiphy->flags |= WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL;
 
@@ -550,6 +542,7 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len,
 			   NL80211_FEATURE_SAE |
 			   NL80211_FEATURE_HT_IBSS |
 			   NL80211_FEATURE_VIF_TXPOWER |
+			   NL80211_FEATURE_MAC_ON_CREATE |
 			   NL80211_FEATURE_USERSPACE_MPM;
 
 	if (!ops->hw_scan)
@@ -564,6 +557,9 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len,
 
 	local = wiphy_priv(wiphy);
 
+	if (sta_info_init(local))
+		goto err_free;
+
 	local->hw.wiphy = wiphy;
 
 	local->hw.priv = (char *)local + ALIGN(sizeof(*local), NETDEV_ALIGN);
@@ -591,6 +587,13 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len,
 	wiphy->ht_capa_mod_mask = &mac80211_ht_capa_mod_mask;
 	wiphy->vht_capa_mod_mask = &mac80211_vht_capa_mod_mask;
 
+	local->ext_capa[7] = WLAN_EXT_CAPA8_OPMODE_NOTIF;
+
+	wiphy->extended_capabilities = local->ext_capa;
+	wiphy->extended_capabilities_mask = local->ext_capa;
+	wiphy->extended_capabilities_len =
+		ARRAY_SIZE(local->ext_capa);
+
 	INIT_LIST_HEAD(&local->interfaces);
 
 	__hw_addr_init(&local->mc_list);
@@ -629,8 +632,6 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len,
 	spin_lock_init(&local->ack_status_lock);
 	idr_init(&local->ack_status_frames);
 
-	sta_info_init(local);
-
 	for (i = 0; i < IEEE80211_MAX_QUEUES; i++) {
 		skb_queue_head_init(&local->pending[i]);
 		atomic_set(&local->agg_queue_stop[i], 0);
@@ -650,15 +651,17 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len,
 	ieee80211_roc_setup(local);
 
 	return &local->hw;
+ err_free:
+	wiphy_free(wiphy);
+	return NULL;
 }
-EXPORT_SYMBOL(ieee80211_alloc_hw);
+EXPORT_SYMBOL(ieee80211_alloc_hw_nm);
 
 static int ieee80211_init_cipher_suites(struct ieee80211_local *local)
 {
 	bool have_wep = !(IS_ERR(local->wep_tx_tfm) ||
 			  IS_ERR(local->wep_rx_tfm));
 	bool have_mfp = local->hw.flags & IEEE80211_HW_MFP_CAPABLE;
-	const struct ieee80211_cipher_scheme *cs = local->hw.cipher_schemes;
 	int n_suites = 0, r = 0, w = 0;
 	u32 *suites;
 	static const u32 cipher_suites[] = {
@@ -667,79 +670,109 @@ static int ieee80211_init_cipher_suites(struct ieee80211_local *local)
 		WLAN_CIPHER_SUITE_WEP104,
 		WLAN_CIPHER_SUITE_TKIP,
 		WLAN_CIPHER_SUITE_CCMP,
+		WLAN_CIPHER_SUITE_CCMP_256,
+		WLAN_CIPHER_SUITE_GCMP,
+		WLAN_CIPHER_SUITE_GCMP_256,
 
 		/* keep last -- depends on hw flags! */
-		WLAN_CIPHER_SUITE_AES_CMAC
+		WLAN_CIPHER_SUITE_AES_CMAC,
+		WLAN_CIPHER_SUITE_BIP_CMAC_256,
+		WLAN_CIPHER_SUITE_BIP_GMAC_128,
+		WLAN_CIPHER_SUITE_BIP_GMAC_256,
 	};
 
-	/* Driver specifies the ciphers, we have nothing to do... */
-	if (local->hw.wiphy->cipher_suites && have_wep)
-		return 0;
+	if (local->hw.flags & IEEE80211_HW_SW_CRYPTO_CONTROL ||
+	    local->hw.wiphy->cipher_suites) {
+		/* If the driver advertises, or doesn't support SW crypto,
+		 * we only need to remove WEP if necessary.
+		 */
+		if (have_wep)
+			return 0;
+
+		/* well if it has _no_ ciphers ... fine */
+		if (!local->hw.wiphy->n_cipher_suites)
+			return 0;
 
-	/* Set up cipher suites if driver relies on mac80211 cipher defs */
-	if (!local->hw.wiphy->cipher_suites && !cs) {
+		/* Driver provides cipher suites, but we need to exclude WEP */
+		suites = kmemdup(local->hw.wiphy->cipher_suites,
+				 sizeof(u32) * local->hw.wiphy->n_cipher_suites,
+				 GFP_KERNEL);
+		if (!suites)
+			return -ENOMEM;
+
+		for (r = 0; r < local->hw.wiphy->n_cipher_suites; r++) {
+			u32 suite = local->hw.wiphy->cipher_suites[r];
+
+			if (suite == WLAN_CIPHER_SUITE_WEP40 ||
+			    suite == WLAN_CIPHER_SUITE_WEP104)
+				continue;
+			suites[w++] = suite;
+		}
+	} else if (!local->hw.cipher_schemes) {
+		/* If the driver doesn't have cipher schemes, there's nothing
+		 * else to do other than assign the (software supported and
+		 * perhaps offloaded) cipher suites.
+		 */
 		local->hw.wiphy->cipher_suites = cipher_suites;
 		local->hw.wiphy->n_cipher_suites = ARRAY_SIZE(cipher_suites);
 
 		if (!have_mfp)
-			local->hw.wiphy->n_cipher_suites--;
+			local->hw.wiphy->n_cipher_suites -= 4;
 
 		if (!have_wep) {
 			local->hw.wiphy->cipher_suites += 2;
 			local->hw.wiphy->n_cipher_suites -= 2;
 		}
 
+		/* not dynamically allocated, so just return */
 		return 0;
-	}
+	} else {
+		const struct ieee80211_cipher_scheme *cs;
 
-	if (!local->hw.wiphy->cipher_suites) {
-		/*
-		 * Driver specifies cipher schemes only
-		 * We start counting ciphers defined by schemes, TKIP and CCMP
+		cs = local->hw.cipher_schemes;
+
+		/* Driver specifies cipher schemes only (but not cipher suites
+		 * including the schemes)
+		 *
+		 * We start counting ciphers defined by schemes, TKIP, CCMP,
+		 * CCMP-256, GCMP, and GCMP-256
 		 */
-		n_suites = local->hw.n_cipher_schemes + 2;
+		n_suites = local->hw.n_cipher_schemes + 5;
 
 		/* check if we have WEP40 and WEP104 */
 		if (have_wep)
 			n_suites += 2;
 
-		/* check if we have AES_CMAC */
+		/* check if we have AES_CMAC, BIP-CMAC-256, BIP-GMAC-128,
+		 * BIP-GMAC-256
+		 */
 		if (have_mfp)
-			n_suites++;
+			n_suites += 4;
 
 		suites = kmalloc(sizeof(u32) * n_suites, GFP_KERNEL);
 		if (!suites)
 			return -ENOMEM;
 
 		suites[w++] = WLAN_CIPHER_SUITE_CCMP;
+		suites[w++] = WLAN_CIPHER_SUITE_CCMP_256;
 		suites[w++] = WLAN_CIPHER_SUITE_TKIP;
+		suites[w++] = WLAN_CIPHER_SUITE_GCMP;
+		suites[w++] = WLAN_CIPHER_SUITE_GCMP_256;
 
 		if (have_wep) {
 			suites[w++] = WLAN_CIPHER_SUITE_WEP40;
 			suites[w++] = WLAN_CIPHER_SUITE_WEP104;
 		}
 
-		if (have_mfp)
+		if (have_mfp) {
 			suites[w++] = WLAN_CIPHER_SUITE_AES_CMAC;
+			suites[w++] = WLAN_CIPHER_SUITE_BIP_CMAC_256;
+			suites[w++] = WLAN_CIPHER_SUITE_BIP_GMAC_128;
+			suites[w++] = WLAN_CIPHER_SUITE_BIP_GMAC_256;
+		}
 
 		for (r = 0; r < local->hw.n_cipher_schemes; r++)
 			suites[w++] = cs[r].cipher;
-	} else {
-		/* Driver provides cipher suites, but we need to exclude WEP */
-		suites = kmemdup(local->hw.wiphy->cipher_suites,
-				 sizeof(u32) * local->hw.wiphy->n_cipher_suites,
-				 GFP_KERNEL);
-		if (!suites)
-			return -ENOMEM;
-
-		for (r = 0; r < local->hw.wiphy->n_cipher_suites; r++) {
-			u32 suite = local->hw.wiphy->cipher_suites[r];
-
-			if (suite == WLAN_CIPHER_SUITE_WEP40 ||
-			    suite == WLAN_CIPHER_SUITE_WEP104)
-				continue;
-			suites[w++] = suite;
-		}
 	}
 
 	local->hw.wiphy->cipher_suites = suites;
@@ -764,6 +797,12 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 	     local->hw.offchannel_tx_hw_queue >= local->hw.queues))
 		return -EINVAL;
 
+	if ((hw->wiphy->features & NL80211_FEATURE_TDLS_CHANNEL_SWITCH) &&
+	    (!local->ops->tdls_channel_switch ||
+	     !local->ops->tdls_cancel_channel_switch ||
+	     !local->ops->tdls_recv_channel_switch))
+		return -EOPNOTSUPP;
+
 #ifdef CONFIG_PM
 	if (hw->wiphy->wowlan && (!local->ops->suspend || !local->ops->resume))
 		return -EINVAL;
@@ -787,13 +826,14 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 		if (local->hw.wiphy->interface_modes & BIT(NL80211_IFTYPE_WDS))
 			return -EINVAL;
 
-		/* DFS currently not supported with channel context drivers */
+		/* DFS is not supported with multi-channel combinations yet */
 		for (i = 0; i < local->hw.wiphy->n_iface_combinations; i++) {
 			const struct ieee80211_iface_combination *comb;
 
 			comb = &local->hw.wiphy->iface_combinations[i];
 
-			if (comb->radar_detect_widths)
+			if (comb->radar_detect_widths &&
+			    comb->num_different_channels > 1)
 				return -EINVAL;
 		}
 	}
@@ -909,10 +949,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 		}
 	}
 
-	WARN((local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD)
-	     && (local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK),
-	     "U-APSD not supported with HW_PS_NULLFUNC_STACK\n");
-
 	/*
 	 * Calculate scan IE length -- we need this to alloc
 	 * memory and to subtract from the driver limit. It
@@ -958,6 +994,10 @@ 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;
 
+	/* mac80211 supports eCSA, if the driver supports STA CSA at all */
+	if (local->hw.flags & IEEE80211_HW_CHANCTX_STA_CSA)
+		local->ext_capa[0] |= WLAN_EXT_CAPA1_EXT_CHANNEL_SWITCHING;
+
 	local->hw.wiphy->max_num_csa_counters = IEEE80211_MAX_CSA_COUNTERS_NUM;
 
 	result = wiphy_register(local->hw.wiphy);
@@ -999,6 +1039,9 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 
 	local->dynamic_ps_forced_timeout = -1;
 
+	if (!local->hw.txq_ac_max_pending)
+		local->hw.txq_ac_max_pending = 64;
+
 	result = ieee80211_wep_init(local);
 	if (result < 0)
 		wiphy_debug(local->hw.wiphy, "Failed to initialize wep: %d\n",
@@ -1019,8 +1062,9 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 	}
 
 	/* add one default STA interface if supported */
-	if (local->hw.wiphy->interface_modes & BIT(NL80211_IFTYPE_STATION)) {
-		result = ieee80211_if_add(local, "wlan%d", NULL,
+	if (local->hw.wiphy->interface_modes & BIT(NL80211_IFTYPE_STATION) &&
+	    !(hw->flags & IEEE80211_HW_NO_AUTO_VIF)) {
+		result = ieee80211_if_add(local, "wlan%d", NET_NAME_ENUM, NULL,
 					  NL80211_IFTYPE_STATION, NULL);
 		if (result)
 			wiphy_warn(local->hw.wiphy,
@@ -1033,10 +1077,8 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 		ieee80211_max_network_latency;
 	result = pm_qos_add_notifier(PM_QOS_NETWORK_LATENCY,
 				     &local->network_latency_notifier);
-	if (result) {
-		rtnl_lock();
+	if (result)
 		goto fail_pm_qos;
-	}
 
 #ifdef CONFIG_INET
 	local->ifa_notifier.notifier_call = ieee80211_ifa_changed;
@@ -1064,15 +1106,15 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
  fail_ifa:
 	pm_qos_remove_notifier(PM_QOS_NETWORK_LATENCY,
 			       &local->network_latency_notifier);
-	rtnl_lock();
 #endif
  fail_pm_qos:
-	ieee80211_led_exit(local);
+	rtnl_lock();
+	rate_control_deinitialize(local);
 	ieee80211_remove_interfaces(local);
  fail_rate:
 	rtnl_unlock();
+	ieee80211_led_exit(local);
 	ieee80211_wep_free(local);
-	sta_info_stop(local);
 	destroy_workqueue(local->workqueue);
  fail_workqueue:
 	wiphy_unregister(local->hw.wiphy);
@@ -1138,7 +1180,6 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw)
 
 	destroy_workqueue(local->workqueue);
 	wiphy_unregister(local->hw.wiphy);
-	sta_info_stop(local);
 	ieee80211_wep_free(local);
 	ieee80211_led_exit(local);
 	kfree(local->int_scan_req);
@@ -1166,7 +1207,7 @@ void ieee80211_free_hw(struct ieee80211_hw *hw)
 		     ieee80211_free_ack_frame, NULL);
 	idr_destroy(&local->ack_status_frames);
 
-	kfree(rcu_access_pointer(local->tx_latency));
+	sta_info_stop(local);
 
 	wiphy_free(local->hw.wiphy);
 }
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 0c8b2a77d312..d4684242e78b 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -520,7 +520,7 @@ int ieee80211_fill_mesh_addresses(struct ieee80211_hdr *hdr, __le16 *fc,
 	} else {
 		*fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS | IEEE80211_FCTL_TODS);
 		/* RA TA DA SA */
-		memset(hdr->addr1, 0, ETH_ALEN);   /* RA is resolved later */
+		eth_zero_addr(hdr->addr1);   /* RA is resolved later */
 		memcpy(hdr->addr2, meshsa, ETH_ALEN);
 		memcpy(hdr->addr3, meshda, ETH_ALEN);
 		memcpy(hdr->addr4, meshsa, ETH_ALEN);
@@ -574,7 +574,8 @@ static void ieee80211_mesh_housekeeping(struct ieee80211_sub_if_data *sdata)
 	struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
 	u32 changed;
 
-	ieee80211_sta_expire(sdata, ifmsh->mshcfg.plink_timeout * HZ);
+	if (ifmsh->mshcfg.plink_timeout > 0)
+		ieee80211_sta_expire(sdata, ifmsh->mshcfg.plink_timeout * HZ);
 	mesh_path_expire(sdata);
 
 	changed = mesh_accept_plinks_update(sdata);
diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h
index f39a19f9090f..50c8473cf9dc 100644
--- a/net/mac80211/mesh.h
+++ b/net/mac80211/mesh.h
@@ -270,6 +270,8 @@ int mpp_path_add(struct ieee80211_sub_if_data *sdata,
 		 const u8 *dst, const u8 *mpp);
 struct mesh_path *
 mesh_path_lookup_by_idx(struct ieee80211_sub_if_data *sdata, int idx);
+struct mesh_path *
+mpp_path_lookup_by_idx(struct ieee80211_sub_if_data *sdata, int idx);
 void mesh_path_fix_nexthop(struct mesh_path *mpath, struct sta_info *next_hop);
 void mesh_path_expire(struct ieee80211_sub_if_data *sdata);
 void mesh_rx_path_sel_frame(struct ieee80211_sub_if_data *sdata,
@@ -317,6 +319,7 @@ void mesh_path_tx_root_frame(struct ieee80211_sub_if_data *sdata);
 
 bool mesh_action_is_path_sel(struct ieee80211_mgmt *mgmt);
 extern int mesh_paths_generation;
+extern int mpp_paths_generation;
 
 #ifdef CONFIG_MAC80211_MESH
 static inline
diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c
index a6699dceae7c..b890e225a8f1 100644
--- a/net/mac80211/mesh_pathtbl.c
+++ b/net/mac80211/mesh_pathtbl.c
@@ -44,6 +44,7 @@ static struct mesh_table __rcu *mesh_paths;
 static struct mesh_table __rcu *mpp_paths; /* Store paths for MPP&MAP */
 
 int mesh_paths_generation;
+int mpp_paths_generation;
 
 /* This lock will have the grow table function as writer and add / delete nodes
  * as readers. RCU provides sufficient protection only when reading the table
@@ -410,6 +411,33 @@ mesh_path_lookup_by_idx(struct ieee80211_sub_if_data *sdata, int idx)
 }
 
 /**
+ * mpp_path_lookup_by_idx - look up a path in the proxy path table by its index
+ * @idx: index
+ * @sdata: local subif, or NULL for all entries
+ *
+ * Returns: pointer to the proxy path structure, or NULL if not found.
+ *
+ * Locking: must be called within a read rcu section.
+ */
+struct mesh_path *
+mpp_path_lookup_by_idx(struct ieee80211_sub_if_data *sdata, int idx)
+{
+	struct mesh_table *tbl = rcu_dereference(mpp_paths);
+	struct mpath_node *node;
+	int i;
+	int j = 0;
+
+	for_each_mesh_entry(tbl, node, i) {
+		if (sdata && node->mpath->sdata != sdata)
+			continue;
+		if (j++ == idx)
+			return node->mpath;
+	}
+
+	return NULL;
+}
+
+/**
  * mesh_path_add_gate - add the given mpath to a mesh gate to our path table
  * @mpath: gate path to add to table
  */
@@ -691,6 +719,9 @@ int mpp_path_add(struct ieee80211_sub_if_data *sdata,
 
 	spin_unlock(&tbl->hashwlock[hash_idx]);
 	read_unlock_bh(&pathtbl_resize_lock);
+
+	mpp_paths_generation++;
+
 	if (grow) {
 		set_bit(MESH_WORK_GROW_MPP_TABLE,  &ifmsh->wrkq_flags);
 		ieee80211_queue_work(&local->hw, &sdata->work);
diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c
index b488e1859b18..60d737f144e3 100644
--- a/net/mac80211/mesh_plink.c
+++ b/net/mac80211/mesh_plink.c
@@ -17,7 +17,7 @@
 #define PLINK_GET_PLID(p) (p + 4)
 
 #define mod_plink_timer(s, t) (mod_timer(&s->plink_timer, \
-				jiffies + HZ * t / 1000))
+				jiffies + msecs_to_jiffies(t)))
 
 enum plink_event {
 	PLINK_UNDEFINED,
@@ -382,6 +382,7 @@ static void mesh_sta_info_init(struct ieee80211_sub_if_data *sdata,
 	enum ieee80211_band band = ieee80211_get_sdata_band(sdata);
 	struct ieee80211_supported_band *sband;
 	u32 rates, basic_rates = 0, changed = 0;
+	enum ieee80211_sta_rx_bandwidth bw = sta->sta.bandwidth;
 
 	sband = local->hw.wiphy->bands[band];
 	rates = ieee80211_sta_get_rates(sdata, elems, band, &basic_rates);
@@ -401,6 +402,9 @@ static void mesh_sta_info_init(struct ieee80211_sub_if_data *sdata,
 					      elems->ht_cap_elem, sta))
 		changed |= IEEE80211_RC_BW_CHANGED;
 
+	if (bw != sta->sta.bandwidth)
+		changed |= IEEE80211_RC_BW_CHANGED;
+
 	/* HT peer is operating 20MHz-only */
 	if (elems->ht_operation &&
 	    !(elems->ht_operation->ht_param &
@@ -621,9 +625,9 @@ static void mesh_plink_timer(unsigned long data)
 				    sta->llid, sta->plid, reason);
 }
 
-static inline void mesh_plink_timer_set(struct sta_info *sta, int timeout)
+static inline void mesh_plink_timer_set(struct sta_info *sta, u32 timeout)
 {
-	sta->plink_timer.expires = jiffies + (HZ * timeout / 1000);
+	sta->plink_timer.expires = jiffies + msecs_to_jiffies(timeout);
 	sta->plink_timer.data = (unsigned long) sta;
 	sta->plink_timer.function = mesh_plink_timer;
 	sta->plink_timeout = timeout;
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 93af0f1c9d99..26053bf2faa8 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -157,14 +157,18 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata,
 {
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
 	struct cfg80211_chan_def vht_chandef;
+	struct ieee80211_sta_ht_cap sta_ht_cap;
 	u32 ht_cfreq, ret;
 
+	memcpy(&sta_ht_cap, &sband->ht_cap, sizeof(sta_ht_cap));
+	ieee80211_apply_htcap_overrides(sdata, &sta_ht_cap);
+
 	chandef->chan = channel;
 	chandef->width = NL80211_CHAN_WIDTH_20_NOHT;
 	chandef->center_freq1 = channel->center_freq;
 	chandef->center_freq2 = 0;
 
-	if (!ht_cap || !ht_oper || !sband->ht_cap.ht_supported) {
+	if (!ht_cap || !ht_oper || !sta_ht_cap.ht_supported) {
 		ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_VHT;
 		goto out;
 	}
@@ -174,6 +178,7 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata,
 	if (!(ht_cap->cap_info &
 	      cpu_to_le16(IEEE80211_HT_CAP_SUP_WIDTH_20_40))) {
 		ret = IEEE80211_STA_DISABLE_40MHZ;
+		vht_chandef = *chandef;
 		goto out;
 	}
 
@@ -197,7 +202,7 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata,
 	}
 
 	/* check 40 MHz support, if we have it */
-	if (sband->ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40) {
+	if (sta_ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40) {
 		switch (ht_oper->ht_param & IEEE80211_HT_PARAM_CHA_SEC_OFFSET) {
 		case IEEE80211_HT_PARAM_CHA_SEC_ABOVE:
 			chandef->width = NL80211_CHAN_WIDTH_40;
@@ -552,13 +557,17 @@ static void ieee80211_add_vht_ie(struct ieee80211_sub_if_data *sdata,
 	cap = vht_cap.cap;
 
 	if (sdata->u.mgd.flags & IEEE80211_STA_DISABLE_80P80MHZ) {
-		cap &= ~IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ;
-		cap |= IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ;
+		u32 bw = cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK;
+
+		cap &= ~IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK;
+		if (bw == IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ ||
+		    bw == IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ)
+			cap |= IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ;
 	}
 
 	if (sdata->u.mgd.flags & IEEE80211_STA_DISABLE_160MHZ) {
 		cap &= ~IEEE80211_VHT_CAP_SHORT_GI_160;
-		cap &= ~IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ;
+		cap &= ~IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK;
 	}
 
 	/*
@@ -775,11 +784,30 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 			WLAN_EID_QOS_CAPA,
 			WLAN_EID_RRM_ENABLED_CAPABILITIES,
 			WLAN_EID_MOBILITY_DOMAIN,
+			WLAN_EID_FAST_BSS_TRANSITION,	/* reassoc only */
+			WLAN_EID_RIC_DATA,		/* reassoc only */
 			WLAN_EID_SUPPORTED_REGULATORY_CLASSES,
 		};
-		noffset = ieee80211_ie_split(assoc_data->ie, assoc_data->ie_len,
-					     before_ht, ARRAY_SIZE(before_ht),
-					     offset);
+		static const u8 after_ric[] = {
+			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,
+			/* 60GHz doesn't happen right now */
+			WLAN_EID_VHT_CAPABILITY,
+			WLAN_EID_OPMODE_NOTIF,
+		};
+
+		noffset = ieee80211_ie_split_ric(assoc_data->ie,
+						 assoc_data->ie_len,
+						 before_ht,
+						 ARRAY_SIZE(before_ht),
+						 after_ric,
+						 ARRAY_SIZE(after_ric),
+						 offset);
 		pos = skb_put(skb, noffset - offset);
 		memcpy(pos, assoc_data->ie + offset, noffset - offset);
 		offset = noffset;
@@ -813,6 +841,8 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 			WLAN_EID_TIM_BCAST_REQ,
 			WLAN_EID_INTERWORKING,
 		};
+
+		/* RIC already taken above, so no need to handle here anymore */
 		noffset = ieee80211_ie_split(assoc_data->ie, assoc_data->ie_len,
 					     before_vht, ARRAY_SIZE(before_vht),
 					     offset);
@@ -1001,14 +1031,7 @@ static void ieee80211_chswitch_work(struct work_struct *work)
 	/* XXX: shouldn't really modify cfg80211-owned data! */
 	ifmgd->associated->channel = sdata->csa_chandef.chan;
 
-	sdata->vif.csa_active = false;
-
-	/* XXX: wait for a beacon first? */
-	if (sdata->csa_block_tx) {
-		ieee80211_wake_vif_queues(local, sdata,
-					  IEEE80211_QUEUE_STOP_REASON_CSA);
-		sdata->csa_block_tx = false;
-	}
+	ifmgd->csa_waiting_bcn = true;
 
 	ieee80211_sta_reset_beacon_monitor(sdata);
 	ieee80211_sta_reset_conn_monitor(sdata);
@@ -1019,6 +1042,37 @@ out:
 	sdata_unlock(sdata);
 }
 
+static void ieee80211_chswitch_post_beacon(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+	int ret;
+
+	sdata_assert_lock(sdata);
+
+	WARN_ON(!sdata->vif.csa_active);
+
+	if (sdata->csa_block_tx) {
+		ieee80211_wake_vif_queues(local, sdata,
+					  IEEE80211_QUEUE_STOP_REASON_CSA);
+		sdata->csa_block_tx = false;
+	}
+
+	sdata->vif.csa_active = false;
+	ifmgd->csa_waiting_bcn = false;
+
+	ret = drv_post_channel_switch(sdata);
+	if (ret) {
+		sdata_info(sdata,
+			   "driver post channel switch failed, disconnecting\n");
+		ieee80211_queue_work(&local->hw,
+				     &ifmgd->csa_connection_drop_work);
+		return;
+	}
+
+	cfg80211_ch_switch_notify(sdata->dev, &sdata->reserved_chandef);
+}
+
 void ieee80211_chswitch_done(struct ieee80211_vif *vif, bool success)
 {
 	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
@@ -1046,7 +1100,8 @@ static void ieee80211_chswitch_timer(unsigned long data)
 
 static void
 ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
-				 u64 timestamp, struct ieee802_11_elems *elems,
+				 u64 timestamp, u32 device_timestamp,
+				 struct ieee802_11_elems *elems,
 				 bool beacon)
 {
 	struct ieee80211_local *local = sdata->local;
@@ -1056,6 +1111,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_chanctx *chanctx;
 	enum ieee80211_band current_band;
 	struct ieee80211_csa_ie csa_ie;
+	struct ieee80211_channel_switch ch_switch;
 	int res;
 
 	sdata_assert_lock(sdata);
@@ -1094,6 +1150,17 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 		return;
 	}
 
+	if (cfg80211_chandef_identical(&csa_ie.chandef,
+				       &sdata->vif.bss_conf.chandef)) {
+		if (ifmgd->csa_ignored_same_chan)
+			return;
+		sdata_info(sdata,
+			   "AP %pM tries to chanswitch to same channel, ignore\n",
+			   ifmgd->associated->bssid);
+		ifmgd->csa_ignored_same_chan = true;
+		return;
+	}
+
 	mutex_lock(&local->mtx);
 	mutex_lock(&local->chanctx_mtx);
 	conf = rcu_dereference_protected(sdata->vif.chanctx_conf,
@@ -1101,30 +1168,28 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 	if (!conf) {
 		sdata_info(sdata,
 			   "no channel context assigned to vif?, disconnecting\n");
-		ieee80211_queue_work(&local->hw,
-				     &ifmgd->csa_connection_drop_work);
-		mutex_unlock(&local->chanctx_mtx);
-		mutex_unlock(&local->mtx);
-		return;
+		goto drop_connection;
 	}
 
 	chanctx = container_of(conf, struct ieee80211_chanctx, conf);
 
-	if (local->use_chanctx) {
-		u32 num_chanctx = 0;
-		list_for_each_entry(chanctx, &local->chanctx_list, list)
-		       num_chanctx++;
+	if (local->use_chanctx &&
+	    !(local->hw.flags & IEEE80211_HW_CHANCTX_STA_CSA)) {
+		sdata_info(sdata,
+			   "driver doesn't support chan-switch with channel contexts\n");
+		goto drop_connection;
+	}
 
-		if (num_chanctx > 1 ||
-		    !(local->hw.flags & IEEE80211_HW_CHANCTX_STA_CSA)) {
-			sdata_info(sdata,
-				   "not handling chan-switch with channel contexts\n");
-			ieee80211_queue_work(&local->hw,
-					     &ifmgd->csa_connection_drop_work);
-			mutex_unlock(&local->chanctx_mtx);
-			mutex_unlock(&local->mtx);
-			return;
-		}
+	ch_switch.timestamp = timestamp;
+	ch_switch.device_timestamp = device_timestamp;
+	ch_switch.block_tx = csa_ie.mode;
+	ch_switch.chandef = csa_ie.chandef;
+	ch_switch.count = csa_ie.count;
+
+	if (drv_pre_channel_switch(sdata, &ch_switch)) {
+		sdata_info(sdata,
+			   "preparing for channel switch failed, disconnecting\n");
+		goto drop_connection;
 	}
 
 	res = ieee80211_vif_reserve_chanctx(sdata, &csa_ie.chandef,
@@ -1133,33 +1198,26 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 		sdata_info(sdata,
 			   "failed to reserve channel context for channel switch, disconnecting (err=%d)\n",
 			   res);
-		ieee80211_queue_work(&local->hw,
-				     &ifmgd->csa_connection_drop_work);
-		mutex_unlock(&local->chanctx_mtx);
-		mutex_unlock(&local->mtx);
-		return;
+		goto drop_connection;
 	}
 	mutex_unlock(&local->chanctx_mtx);
 
 	sdata->vif.csa_active = true;
 	sdata->csa_chandef = csa_ie.chandef;
 	sdata->csa_block_tx = csa_ie.mode;
+	ifmgd->csa_ignored_same_chan = false;
 
 	if (sdata->csa_block_tx)
 		ieee80211_stop_vif_queues(local, sdata,
 					  IEEE80211_QUEUE_STOP_REASON_CSA);
 	mutex_unlock(&local->mtx);
 
+	cfg80211_ch_switch_started_notify(sdata->dev, &csa_ie.chandef,
+					  csa_ie.count);
+
 	if (local->ops->channel_switch) {
 		/* use driver's channel switch callback */
-		struct ieee80211_channel_switch ch_switch = {
-			.timestamp = timestamp,
-			.block_tx = csa_ie.mode,
-			.chandef = csa_ie.chandef,
-			.count = csa_ie.count,
-		};
-
-		drv_channel_switch(local, &ch_switch);
+		drv_channel_switch(local, sdata, &ch_switch);
 		return;
 	}
 
@@ -1170,6 +1228,11 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 		mod_timer(&ifmgd->chswitch_timer,
 			  TU_TO_EXP_TIME((csa_ie.count - 1) *
 					 cbss->beacon_interval));
+	return;
+ drop_connection:
+	ieee80211_queue_work(&local->hw, &ifmgd->csa_connection_drop_work);
+	mutex_unlock(&local->chanctx_mtx);
+	mutex_unlock(&local->mtx);
 }
 
 static bool
@@ -1226,8 +1289,11 @@ ieee80211_find_80211h_pwr_constr(struct ieee80211_sub_if_data *sdata,
 		country_ie_len -= 3;
 	}
 
-	if (have_chan_pwr)
+	if (have_chan_pwr && pwr_constr_elem)
 		*pwr_reduction = *pwr_constr_elem;
+	else
+		*pwr_reduction = 0;
+
 	return have_chan_pwr;
 }
 
@@ -1256,10 +1322,11 @@ static u32 ieee80211_handle_pwr_constr(struct ieee80211_sub_if_data *sdata,
 	int chan_pwr = 0, pwr_reduction_80211h = 0;
 	int pwr_level_cisco, pwr_level_80211h;
 	int new_ap_level;
+	__le16 capab = mgmt->u.probe_resp.capab_info;
 
-	if (country_ie && pwr_constr_ie &&
-	    mgmt->u.probe_resp.capab_info &
-		cpu_to_le16(WLAN_CAPABILITY_SPECTRUM_MGMT)) {
+	if (country_ie &&
+	    (capab & cpu_to_le16(WLAN_CAPABILITY_SPECTRUM_MGMT) ||
+	     capab & cpu_to_le16(WLAN_CAPABILITY_RADIO_MEASURE))) {
 		has_80211h_pwr = ieee80211_find_80211h_pwr_constr(
 			sdata, channel, country_ie, country_ie_len,
 			pwr_constr_ie, &chan_pwr, &pwr_reduction_80211h);
@@ -1281,15 +1348,15 @@ static u32 ieee80211_handle_pwr_constr(struct ieee80211_sub_if_data *sdata,
 	 */
 	if (has_80211h_pwr &&
 	    (!has_cisco_pwr || pwr_level_80211h <= pwr_level_cisco)) {
-		sdata_info(sdata,
-			   "Limiting TX power to %d (%d - %d) dBm as advertised by %pM\n",
-			   pwr_level_80211h, chan_pwr, pwr_reduction_80211h,
-			   sdata->u.mgd.bssid);
+		sdata_dbg(sdata,
+			  "Limiting TX power to %d (%d - %d) dBm as advertised by %pM\n",
+			  pwr_level_80211h, chan_pwr, pwr_reduction_80211h,
+			  sdata->u.mgd.bssid);
 		new_ap_level = pwr_level_80211h;
 	} else {  /* has_cisco_pwr is always true here. */
-		sdata_info(sdata,
-			   "Limiting TX power to %d dBm as advertised by %pM\n",
-			   pwr_level_cisco, sdata->u.mgd.bssid);
+		sdata_dbg(sdata,
+			  "Limiting TX power to %d dBm as advertised by %pM\n",
+			  pwr_level_cisco, sdata->u.mgd.bssid);
 		new_ap_level = pwr_level_cisco;
 	}
 
@@ -1538,7 +1605,7 @@ void ieee80211_dynamic_ps_enable_work(struct work_struct *work)
 		} else {
 			ieee80211_send_nullfunc(local, sdata, 1);
 			/* Flush to get the tx status of nullfunc frame */
-			ieee80211_flush_queues(local, sdata);
+			ieee80211_flush_queues(local, sdata, false);
 		}
 	}
 
@@ -1555,9 +1622,6 @@ void ieee80211_dynamic_ps_timer(unsigned long data)
 {
 	struct ieee80211_local *local = (void *) data;
 
-	if (local->quiescing || local->suspended)
-		return;
-
 	ieee80211_queue_work(&local->hw, &local->dynamic_ps_enable_work);
 }
 
@@ -1580,6 +1644,95 @@ void ieee80211_dfs_cac_timer_work(struct work_struct *work)
 	mutex_unlock(&sdata->local->mtx);
 }
 
+static bool
+__ieee80211_sta_handle_tspec_ac_params(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+	bool ret = false;
+	int ac;
+
+	if (local->hw.queues < IEEE80211_NUM_ACS)
+		return false;
+
+	for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
+		struct ieee80211_sta_tx_tspec *tx_tspec = &ifmgd->tx_tspec[ac];
+		int non_acm_ac;
+		unsigned long now = jiffies;
+
+		if (tx_tspec->action == TX_TSPEC_ACTION_NONE &&
+		    tx_tspec->admitted_time &&
+		    time_after(now, tx_tspec->time_slice_start + HZ)) {
+			tx_tspec->consumed_tx_time = 0;
+			tx_tspec->time_slice_start = now;
+
+			if (tx_tspec->downgraded)
+				tx_tspec->action =
+					TX_TSPEC_ACTION_STOP_DOWNGRADE;
+		}
+
+		switch (tx_tspec->action) {
+		case TX_TSPEC_ACTION_STOP_DOWNGRADE:
+			/* take the original parameters */
+			if (drv_conf_tx(local, sdata, ac, &sdata->tx_conf[ac]))
+				sdata_err(sdata,
+					  "failed to set TX queue parameters for queue %d\n",
+					  ac);
+			tx_tspec->action = TX_TSPEC_ACTION_NONE;
+			tx_tspec->downgraded = false;
+			ret = true;
+			break;
+		case TX_TSPEC_ACTION_DOWNGRADE:
+			if (time_after(now, tx_tspec->time_slice_start + HZ)) {
+				tx_tspec->action = TX_TSPEC_ACTION_NONE;
+				ret = true;
+				break;
+			}
+			/* downgrade next lower non-ACM AC */
+			for (non_acm_ac = ac + 1;
+			     non_acm_ac < IEEE80211_NUM_ACS;
+			     non_acm_ac++)
+				if (!(sdata->wmm_acm & BIT(7 - 2 * non_acm_ac)))
+					break;
+			/* The loop will result in using BK even if it requires
+			 * admission control, such configuration makes no sense
+			 * and we have to transmit somehow - the AC selection
+			 * does the same thing.
+			 */
+			if (drv_conf_tx(local, sdata, ac,
+					&sdata->tx_conf[non_acm_ac]))
+				sdata_err(sdata,
+					  "failed to set TX queue parameters for queue %d\n",
+					  ac);
+			tx_tspec->action = TX_TSPEC_ACTION_NONE;
+			ret = true;
+			schedule_delayed_work(&ifmgd->tx_tspec_wk,
+				tx_tspec->time_slice_start + HZ - now + 1);
+			break;
+		case TX_TSPEC_ACTION_NONE:
+			/* nothing now */
+			break;
+		}
+	}
+
+	return ret;
+}
+
+void ieee80211_sta_handle_tspec_ac_params(struct ieee80211_sub_if_data *sdata)
+{
+	if (__ieee80211_sta_handle_tspec_ac_params(sdata))
+		ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_QOS);
+}
+
+static void ieee80211_sta_handle_tspec_ac_params_wk(struct work_struct *work)
+{
+	struct ieee80211_sub_if_data *sdata;
+
+	sdata = container_of(work, struct ieee80211_sub_if_data,
+			     u.mgd.tx_tspec_wk.work);
+	ieee80211_sta_handle_tspec_ac_params(sdata);
+}
+
 /* MLME */
 static bool ieee80211_sta_wmm_params(struct ieee80211_local *local,
 				     struct ieee80211_sub_if_data *sdata,
@@ -1664,12 +1817,14 @@ static bool ieee80211_sta_wmm_params(struct ieee80211_local *local,
 		params.uapsd = uapsd;
 
 		mlme_dbg(sdata,
-			 "WMM queue=%d aci=%d acm=%d aifs=%d cWmin=%d cWmax=%d txop=%d uapsd=%d\n",
+			 "WMM queue=%d aci=%d acm=%d aifs=%d cWmin=%d cWmax=%d txop=%d uapsd=%d, downgraded=%d\n",
 			 queue, aci, acm,
 			 params.aifs, params.cw_min, params.cw_max,
-			 params.txop, params.uapsd);
+			 params.txop, params.uapsd,
+			 ifmgd->tx_tspec[queue].downgraded);
 		sdata->tx_conf[queue] = params;
-		if (drv_conf_tx(local, sdata, queue, &params))
+		if (!ifmgd->tx_tspec[queue].downgraded &&
+		    drv_conf_tx(local, sdata, queue, &params))
 			sdata_err(sdata,
 				  "failed to set TX queue parameters for queue %d\n",
 				  queue);
@@ -1854,21 +2009,29 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
 	/* disable per-vif ps */
 	ieee80211_recalc_ps_vif(sdata);
 
-	/* flush out any pending frame (e.g. DELBA) before deauth/disassoc */
+	/* make sure ongoing transmission finishes */
+	synchronize_net();
+
+	/*
+	 * drop any frame before deauth/disassoc, this can be data or
+	 * management frame. Since we are disconnecting, we should not
+	 * insist sending these frames which can take time and delay
+	 * the disconnection and possible the roaming.
+	 */
 	if (tx)
-		ieee80211_flush_queues(local, sdata);
+		ieee80211_flush_queues(local, sdata, true);
 
 	/* deauthenticate/disassociate now */
 	if (tx || frame_buf)
 		ieee80211_send_deauth_disassoc(sdata, ifmgd->bssid, stype,
 					       reason, tx, frame_buf);
 
-	/* flush out frame */
+	/* flush out frame - make sure the deauth was actually sent */
 	if (tx)
-		ieee80211_flush_queues(local, sdata);
+		ieee80211_flush_queues(local, sdata, false);
 
 	/* clear bssid only after building the needed mgmt frames */
-	memset(ifmgd->bssid, 0, ETH_ALEN);
+	eth_zero_addr(ifmgd->bssid);
 
 	/* remove AP and TDLS peers */
 	sta_info_flush(sdata);
@@ -1924,6 +2087,8 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
 	ieee80211_vif_release_channel(sdata);
 
 	sdata->vif.csa_active = false;
+	ifmgd->csa_waiting_bcn = false;
+	ifmgd->csa_ignored_same_chan = false;
 	if (sdata->csa_block_tx) {
 		ieee80211_wake_vif_queues(local, sdata,
 					  IEEE80211_QUEUE_STOP_REASON_CSA);
@@ -1931,6 +2096,10 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
 	}
 	mutex_unlock(&local->mtx);
 
+	/* existing TX TSPEC sessions no longer exist */
+	memset(ifmgd->tx_tspec, 0, sizeof(ifmgd->tx_tspec));
+	cancel_delayed_work_sync(&ifmgd->tx_tspec_wk);
+
 	sdata->encrypt_headroom = IEEE80211_ENCRYPT_HEADROOM;
 }
 
@@ -1983,9 +2152,46 @@ out:
 	mutex_unlock(&local->mtx);
 }
 
+static void ieee80211_sta_tx_wmm_ac_notify(struct ieee80211_sub_if_data *sdata,
+					   struct ieee80211_hdr *hdr,
+					   u16 tx_time)
+{
+	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+	u16 tid = *ieee80211_get_qos_ctl(hdr) & IEEE80211_QOS_CTL_TID_MASK;
+	int ac = ieee80211_ac_from_tid(tid);
+	struct ieee80211_sta_tx_tspec *tx_tspec = &ifmgd->tx_tspec[ac];
+	unsigned long now = jiffies;
+
+	if (likely(!tx_tspec->admitted_time))
+		return;
+
+	if (time_after(now, tx_tspec->time_slice_start + HZ)) {
+		tx_tspec->consumed_tx_time = 0;
+		tx_tspec->time_slice_start = now;
+
+		if (tx_tspec->downgraded) {
+			tx_tspec->action = TX_TSPEC_ACTION_STOP_DOWNGRADE;
+			schedule_delayed_work(&ifmgd->tx_tspec_wk, 0);
+		}
+	}
+
+	if (tx_tspec->downgraded)
+		return;
+
+	tx_tspec->consumed_tx_time += tx_time;
+
+	if (tx_tspec->consumed_tx_time >= tx_tspec->admitted_time) {
+		tx_tspec->downgraded = true;
+		tx_tspec->action = TX_TSPEC_ACTION_DOWNGRADE;
+		schedule_delayed_work(&ifmgd->tx_tspec_wk, 0);
+	}
+}
+
 void ieee80211_sta_tx_notify(struct ieee80211_sub_if_data *sdata,
-			     struct ieee80211_hdr *hdr, bool ack)
+			     struct ieee80211_hdr *hdr, bool ack, u16 tx_time)
 {
+	ieee80211_sta_tx_wmm_ac_notify(sdata, hdr, tx_time);
+
 	if (!ieee80211_is_data(hdr->frame_control))
 	    return;
 
@@ -2040,7 +2246,8 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata)
 		else
 			ssid_len = ssid[1];
 
-		ieee80211_send_probe_req(sdata, dst, ssid + 2, ssid_len, NULL,
+		ieee80211_send_probe_req(sdata, sdata->vif.addr, dst,
+					 ssid + 2, ssid_len, NULL,
 					 0, (u32) -1, true, 0,
 					 ifmgd->associated->channel, false);
 		rcu_read_unlock();
@@ -2048,8 +2255,6 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata)
 
 	ifmgd->probe_timeout = jiffies + msecs_to_jiffies(probe_wait_ms);
 	run_again(sdata, ifmgd->probe_timeout);
-	if (sdata->local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS)
-		ieee80211_flush_queues(sdata->local, sdata);
 }
 
 static void ieee80211_mgd_probe_ap(struct ieee80211_sub_if_data *sdata,
@@ -2078,9 +2283,7 @@ static void ieee80211_mgd_probe_ap(struct ieee80211_sub_if_data *sdata,
 				     "detected beacon loss from AP (missed %d beacons) - probing\n",
 				     beacon_loss_count);
 
-		ieee80211_cqm_rssi_notify(&sdata->vif,
-					  NL80211_CQM_RSSI_BEACON_LOSS_EVENT,
-					  GFP_KERNEL);
+		ieee80211_cqm_beacon_loss_notify(&sdata->vif, GFP_KERNEL);
 	}
 
 	/*
@@ -2145,7 +2348,7 @@ struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw,
 	else
 		ssid_len = ssid[1];
 
-	skb = ieee80211_build_probe_req(sdata, cbss->bssid,
+	skb = ieee80211_build_probe_req(sdata, sdata->vif.addr, cbss->bssid,
 					(u32) -1, cbss->channel,
 					ssid + 2, ssid_len,
 					NULL, 0, true);
@@ -2155,6 +2358,24 @@ struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw,
 }
 EXPORT_SYMBOL(ieee80211_ap_probereq_get);
 
+static void ieee80211_report_disconnect(struct ieee80211_sub_if_data *sdata,
+					const u8 *buf, size_t len, bool tx,
+					u16 reason)
+{
+	struct ieee80211_event event = {
+		.type = MLME_EVENT,
+		.u.mlme.data = tx ? DEAUTH_TX_EVENT : DEAUTH_RX_EVENT,
+		.u.mlme.reason = reason,
+	};
+
+	if (tx)
+		cfg80211_tx_mlme_mgmt(sdata->dev, buf, len);
+	else
+		cfg80211_rx_mlme_mgmt(sdata->dev, buf, len);
+
+	drv_event_callback(sdata->local, sdata, &event);
+}
+
 static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata)
 {
 	struct ieee80211_local *local = sdata->local;
@@ -2172,6 +2393,7 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata)
 			       true, frame_buf);
 	mutex_lock(&local->mtx);
 	sdata->vif.csa_active = false;
+	ifmgd->csa_waiting_bcn = false;
 	if (sdata->csa_block_tx) {
 		ieee80211_wake_vif_queues(local, sdata,
 					  IEEE80211_QUEUE_STOP_REASON_CSA);
@@ -2179,8 +2401,9 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata)
 	}
 	mutex_unlock(&local->mtx);
 
-	cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf,
-			      IEEE80211_DEAUTH_FRAME_LEN);
+	ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), true,
+				    WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY);
+
 	sdata_unlock(sdata);
 }
 
@@ -2251,9 +2474,15 @@ static void ieee80211_destroy_auth_data(struct ieee80211_sub_if_data *sdata,
 	sdata_assert_lock(sdata);
 
 	if (!assoc) {
+		/*
+		 * we are not authenticated yet, the only timer that could be
+		 * running is the timeout for the authentication response which
+		 * which is not relevant anymore.
+		 */
+		del_timer_sync(&sdata->u.mgd.timer);
 		sta_info_destroy_addr(sdata, auth_data->bss->bssid);
 
-		memset(sdata->u.mgd.bssid, 0, ETH_ALEN);
+		eth_zero_addr(sdata->u.mgd.bssid);
 		ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BSSID);
 		sdata->u.mgd.flags = 0;
 		mutex_lock(&sdata->local->mtx);
@@ -2298,6 +2527,10 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata,
 	u8 bssid[ETH_ALEN];
 	u16 auth_alg, auth_transaction, status_code;
 	struct sta_info *sta;
+	struct ieee80211_event event = {
+		.type = MLME_EVENT,
+		.u.mlme.data = AUTH_EVENT,
+	};
 
 	sdata_assert_lock(sdata);
 
@@ -2330,6 +2563,9 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata,
 			   mgmt->sa, status_code);
 		ieee80211_destroy_auth_data(sdata, false);
 		cfg80211_rx_mlme_mgmt(sdata->dev, (u8 *)mgmt, len);
+		event.u.mlme.status = MLME_DENIED;
+		event.u.mlme.reason = status_code;
+		drv_event_callback(sdata->local, sdata, &event);
 		return;
 	}
 
@@ -2352,6 +2588,8 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata,
 		return;
 	}
 
+	event.u.mlme.status = MLME_SUCCESS;
+	drv_event_callback(sdata->local, sdata, &event);
 	sdata_info(sdata, "authenticated\n");
 	ifmgd->auth_data->done = true;
 	ifmgd->auth_data->timeout = jiffies + IEEE80211_AUTH_WAIT_ASSOC;
@@ -2470,7 +2708,7 @@ static void ieee80211_rx_mgmt_deauth(struct ieee80211_sub_if_data *sdata,
 
 	ieee80211_set_disassoc(sdata, 0, 0, false, NULL);
 
-	cfg80211_rx_mlme_mgmt(sdata->dev, (u8 *)mgmt, len);
+	ieee80211_report_disconnect(sdata, (u8 *)mgmt, len, false, reason_code);
 }
 
 
@@ -2496,7 +2734,7 @@ static void ieee80211_rx_mgmt_disassoc(struct ieee80211_sub_if_data *sdata,
 
 	ieee80211_set_disassoc(sdata, 0, 0, false, NULL);
 
-	cfg80211_rx_mlme_mgmt(sdata->dev, (u8 *)mgmt, len);
+	ieee80211_report_disconnect(sdata, (u8 *)mgmt, len, false, reason_code);
 }
 
 static void ieee80211_get_rates(struct ieee80211_supported_band *sband,
@@ -2558,9 +2796,15 @@ static void ieee80211_destroy_assoc_data(struct ieee80211_sub_if_data *sdata,
 	sdata_assert_lock(sdata);
 
 	if (!assoc) {
+		/*
+		 * we are not associated yet, the only timer that could be
+		 * running is the timeout for the association response which
+		 * which is not relevant anymore.
+		 */
+		del_timer_sync(&sdata->u.mgd.timer);
 		sta_info_destroy_addr(sdata, assoc_data->bss->bssid);
 
-		memset(sdata->u.mgd.bssid, 0, ETH_ALEN);
+		eth_zero_addr(sdata->u.mgd.bssid);
 		ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BSSID);
 		sdata->u.mgd.flags = 0;
 		mutex_lock(&sdata->local->mtx);
@@ -2618,6 +2862,9 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 	}
 
 	ifmgd->aid = aid;
+	ifmgd->tdls_chan_switch_prohibited =
+		elems.ext_capab && elems.ext_capab_len >= 5 &&
+		(elems.ext_capab[4] & WLAN_EXT_CAPA5_TDLS_CH_SW_PROHIBITED);
 
 	/*
 	 * Some APs are erroneously not including some information in their
@@ -2749,10 +2996,14 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 
 	rate_control_rate_init(sta);
 
-	if (ifmgd->flags & IEEE80211_STA_MFP_ENABLED)
+	if (ifmgd->flags & IEEE80211_STA_MFP_ENABLED) {
 		set_sta_flag(sta, WLAN_STA_MFP);
+		sta->sta.mfp = true;
+	} else {
+		sta->sta.mfp = false;
+	}
 
-	sta->sta.wme = elems.wmm_param;
+	sta->sta.wme = elems.wmm_param && local->hw.queues >= IEEE80211_NUM_ACS;
 
 	err = sta_info_move_state(sta, IEEE80211_STA_ASSOC);
 	if (!err && !(ifmgd->flags & IEEE80211_STA_CONTROL_PORT))
@@ -2822,6 +3073,10 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 	u8 *pos;
 	bool reassoc;
 	struct cfg80211_bss *bss;
+	struct ieee80211_event event = {
+		.type = MLME_EVENT,
+		.u.mlme.data = ASSOC_EVENT,
+	};
 
 	sdata_assert_lock(sdata);
 
@@ -2873,6 +3128,9 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 		sdata_info(sdata, "%pM denied association (code=%d)\n",
 			   mgmt->sa, status_code);
 		ieee80211_destroy_assoc_data(sdata, false);
+		event.u.mlme.status = MLME_DENIED;
+		event.u.mlme.reason = status_code;
+		drv_event_callback(sdata->local, sdata, &event);
 	} else {
 		if (!ieee80211_assoc_success(sdata, bss, mgmt, len)) {
 			/* oops -- internal error -- send timeout for now */
@@ -2880,6 +3138,8 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 			cfg80211_assoc_timeout(sdata->dev, bss);
 			return;
 		}
+		event.u.mlme.status = MLME_SUCCESS;
+		drv_event_callback(sdata->local, sdata, &event);
 		sdata_info(sdata, "associated\n");
 
 		/*
@@ -2984,7 +3244,8 @@ static const u64 care_about_ies =
 	(1ULL << WLAN_EID_CHANNEL_SWITCH) |
 	(1ULL << WLAN_EID_PWR_CONSTRAINT) |
 	(1ULL << WLAN_EID_HT_CAPABILITY) |
-	(1ULL << WLAN_EID_HT_OPERATION);
+	(1ULL << WLAN_EID_HT_OPERATION) |
+	(1ULL << WLAN_EID_EXT_CHANSWITCH_ANN);
 
 static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 				     struct ieee80211_mgmt *mgmt, size_t len,
@@ -3081,6 +3342,9 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 	    ifmgd->count_beacon_signal >= IEEE80211_SIGNAL_AVE_MIN_COUNT) {
 		int sig = ifmgd->ave_beacon_signal;
 		int last_sig = ifmgd->last_ave_beacon_signal;
+		struct ieee80211_event event = {
+			.type = RSSI_EVENT,
+		};
 
 		/*
 		 * if signal crosses either of the boundaries, invoke callback
@@ -3089,12 +3353,14 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 		if (sig > ifmgd->rssi_max_thold &&
 		    (last_sig <= ifmgd->rssi_min_thold || last_sig == 0)) {
 			ifmgd->last_ave_beacon_signal = sig;
-			drv_rssi_callback(local, sdata, RSSI_EVENT_HIGH);
+			event.u.rssi.data = RSSI_EVENT_HIGH;
+			drv_event_callback(local, sdata, &event);
 		} else if (sig < ifmgd->rssi_min_thold &&
 			   (last_sig >= ifmgd->rssi_max_thold ||
 			   last_sig == 0)) {
 			ifmgd->last_ave_beacon_signal = sig;
-			drv_rssi_callback(local, sdata, RSSI_EVENT_LOW);
+			event.u.rssi.data = RSSI_EVENT_LOW;
+			drv_event_callback(local, sdata, &event);
 		}
 	}
 
@@ -3196,6 +3462,29 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 		}
 	}
 
+	if (ifmgd->csa_waiting_bcn)
+		ieee80211_chswitch_post_beacon(sdata);
+
+	/*
+	 * Update beacon timing and dtim count on every beacon appearance. This
+	 * will allow the driver to use the most updated values. Do it before
+	 * comparing this one with last received beacon.
+	 * IMPORTANT: These parameters would possibly be out of sync by the time
+	 * the driver will use them. The synchronized view is currently
+	 * guaranteed only in certain callbacks.
+	 */
+	if (local->hw.flags & IEEE80211_HW_TIMING_BEACON_ONLY) {
+		sdata->vif.bss_conf.sync_tsf =
+			le64_to_cpu(mgmt->u.beacon.timestamp);
+		sdata->vif.bss_conf.sync_device_ts =
+			rx_status->device_timestamp;
+		if (elems.tim)
+			sdata->vif.bss_conf.sync_dtim_count =
+				elems.tim->dtim_count;
+		else
+			sdata->vif.bss_conf.sync_dtim_count = 0;
+	}
+
 	if (ncrc == ifmgd->beacon_crc && ifmgd->beacon_crc_valid)
 		return;
 	ifmgd->beacon_crc = ncrc;
@@ -3204,6 +3493,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 	ieee80211_rx_bss_info(sdata, mgmt, len, rx_status, &elems);
 
 	ieee80211_sta_process_chanswitch(sdata, rx_status->mactime,
+					 rx_status->device_timestamp,
 					 &elems, true);
 
 	if (!(ifmgd->flags & IEEE80211_STA_DISABLE_WMM) &&
@@ -3222,18 +3512,6 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 		else
 			bss_conf->dtim_period = 1;
 
-		if (local->hw.flags & IEEE80211_HW_TIMING_BEACON_ONLY) {
-			sdata->vif.bss_conf.sync_tsf =
-				le64_to_cpu(mgmt->u.beacon.timestamp);
-			sdata->vif.bss_conf.sync_device_ts =
-				rx_status->device_timestamp;
-			if (elems.tim)
-				sdata->vif.bss_conf.sync_dtim_count =
-					elems.tim->dtim_count;
-			else
-				sdata->vif.bss_conf.sync_dtim_count = 0;
-		}
-
 		changed |= BSS_CHANGED_BEACON_INFO;
 		ifmgd->have_beacon = true;
 
@@ -3264,8 +3542,9 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 		ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH,
 				       WLAN_REASON_DEAUTH_LEAVING,
 				       true, deauth_buf);
-		cfg80211_tx_mlme_mgmt(sdata->dev, deauth_buf,
-				      sizeof(deauth_buf));
+		ieee80211_report_disconnect(sdata, deauth_buf,
+					    sizeof(deauth_buf), true,
+					    WLAN_REASON_DEAUTH_LEAVING);
 		return;
 	}
 
@@ -3335,8 +3614,9 @@ void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata,
 				break;
 
 			ieee80211_sta_process_chanswitch(sdata,
-							 rx_status->mactime,
-							 &elems, false);
+						 rx_status->mactime,
+						 rx_status->device_timestamp,
+						 &elems, false);
 		} else if (mgmt->u.action.category == WLAN_CATEGORY_PUBLIC) {
 			ies_len = skb->len -
 				  offsetof(struct ieee80211_mgmt,
@@ -3357,8 +3637,9 @@ void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata,
 				&mgmt->u.action.u.ext_chan_switch.data;
 
 			ieee80211_sta_process_chanswitch(sdata,
-							 rx_status->mactime,
-							 &elems, false);
+						 rx_status->mactime,
+						 rx_status->device_timestamp,
+						 &elems, false);
 		}
 		break;
 	}
@@ -3381,8 +3662,8 @@ static void ieee80211_sta_connection_lost(struct ieee80211_sub_if_data *sdata,
 	ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH, reason,
 			       tx, frame_buf);
 
-	cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf,
-			      IEEE80211_DEAUTH_FRAME_LEN);
+	ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), true,
+				    reason);
 }
 
 static int ieee80211_probe_auth(struct ieee80211_sub_if_data *sdata)
@@ -3456,7 +3737,8 @@ static int ieee80211_probe_auth(struct ieee80211_sub_if_data *sdata)
 		 * Direct probe is sent to broadcast address as some APs
 		 * will not answer to direct packet in unassociated state.
 		 */
-		ieee80211_send_probe_req(sdata, NULL, ssidie + 2, ssidie[1],
+		ieee80211_send_probe_req(sdata, sdata->vif.addr, NULL,
+					 ssidie + 2, ssidie[1],
 					 NULL, 0, (u32) -1, true, 0,
 					 auth_data->bss->channel, false);
 		rcu_read_unlock();
@@ -3575,12 +3857,18 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata)
 			ieee80211_destroy_auth_data(sdata, false);
 		} else if (ieee80211_probe_auth(sdata)) {
 			u8 bssid[ETH_ALEN];
+			struct ieee80211_event event = {
+				.type = MLME_EVENT,
+				.u.mlme.data = AUTH_EVENT,
+				.u.mlme.status = MLME_TIMEOUT,
+			};
 
 			memcpy(bssid, ifmgd->auth_data->bss->bssid, ETH_ALEN);
 
 			ieee80211_destroy_auth_data(sdata, false);
 
 			cfg80211_auth_timeout(sdata->dev, bssid);
+			drv_event_callback(sdata->local, sdata, &event);
 		}
 	} else if (ifmgd->auth_data && ifmgd->auth_data->timeout_started)
 		run_again(sdata, ifmgd->auth_data->timeout);
@@ -3590,9 +3878,15 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata)
 		if ((ifmgd->assoc_data->need_beacon && !ifmgd->have_beacon) ||
 		    ieee80211_do_assoc(sdata)) {
 			struct cfg80211_bss *bss = ifmgd->assoc_data->bss;
+			struct ieee80211_event event = {
+				.type = MLME_EVENT,
+				.u.mlme.data = ASSOC_EVENT,
+				.u.mlme.status = MLME_TIMEOUT,
+			};
 
 			ieee80211_destroy_assoc_data(sdata, false);
 			cfg80211_assoc_timeout(sdata->dev, bss);
+			drv_event_callback(sdata->local, sdata, &event);
 		}
 	} else if (ifmgd->assoc_data && ifmgd->assoc_data->timeout_started)
 		run_again(sdata, ifmgd->assoc_data->timeout);
@@ -3664,12 +3958,9 @@ static void ieee80211_sta_bcn_mon_timer(unsigned long data)
 {
 	struct ieee80211_sub_if_data *sdata =
 		(struct ieee80211_sub_if_data *) data;
-	struct ieee80211_local *local = sdata->local;
-
-	if (local->quiescing)
-		return;
+	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
 
-	if (sdata->vif.csa_active)
+	if (sdata->vif.csa_active && !ifmgd->csa_waiting_bcn)
 		return;
 
 	sdata->u.mgd.connection_loss = false;
@@ -3684,10 +3975,7 @@ static void ieee80211_sta_conn_mon_timer(unsigned long data)
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
 	struct ieee80211_local *local = sdata->local;
 
-	if (local->quiescing)
-		return;
-
-	if (sdata->vif.csa_active)
+	if (sdata->vif.csa_active && !ifmgd->csa_waiting_bcn)
 		return;
 
 	ieee80211_queue_work(&local->hw, &ifmgd->monitor_work);
@@ -3749,6 +4037,34 @@ void ieee80211_mgd_quiesce(struct ieee80211_sub_if_data *sdata)
 				      IEEE80211_DEAUTH_FRAME_LEN);
 	}
 
+	/* This is a bit of a hack - we should find a better and more generic
+	 * solution to this. Normally when suspending, cfg80211 will in fact
+	 * deauthenticate. However, it doesn't (and cannot) stop an ongoing
+	 * auth (not so important) or assoc (this is the problem) process.
+	 *
+	 * As a consequence, it can happen that we are in the process of both
+	 * associating and suspending, and receive an association response
+	 * after cfg80211 has checked if it needs to disconnect, but before
+	 * we actually set the flag to drop incoming frames. This will then
+	 * cause the workqueue flush to process the association response in
+	 * the suspend, resulting in a successful association just before it
+	 * tries to remove the interface from the driver, which now though
+	 * has a channel context assigned ... this results in issues.
+	 *
+	 * To work around this (for now) simply deauth here again if we're
+	 * now connected.
+	 */
+	if (ifmgd->associated && !sdata->local->wowlan) {
+		u8 bssid[ETH_ALEN];
+		struct cfg80211_deauth_request req = {
+			.reason_code = WLAN_REASON_DEAUTH_LEAVING,
+			.bssid = bssid,
+		};
+
+		memcpy(bssid, ifmgd->associated->bssid, ETH_ALEN);
+		ieee80211_mgd_deauth(sdata, &req);
+	}
+
 	sdata_unlock(sdata);
 }
 
@@ -3799,6 +4115,8 @@ void ieee80211_sta_setup_sdata(struct ieee80211_sub_if_data *sdata)
 		    (unsigned long) sdata);
 	setup_timer(&ifmgd->chswitch_timer, ieee80211_chswitch_timer,
 		    (unsigned long) sdata);
+	INIT_DELAYED_WORK(&ifmgd->tx_tspec_wk,
+			  ieee80211_sta_handle_tspec_ac_params_wk);
 
 	ifmgd->flags = 0;
 	ifmgd->powersave = sdata->wdev.ps;
@@ -3810,6 +4128,11 @@ void ieee80211_sta_setup_sdata(struct ieee80211_sub_if_data *sdata)
 		ifmgd->req_smps = IEEE80211_SMPS_AUTOMATIC;
 	else
 		ifmgd->req_smps = IEEE80211_SMPS_OFF;
+
+	/* Setup TDLS data */
+	spin_lock_init(&ifmgd->teardown_lock);
+	ifmgd->teardown_skb = NULL;
+	ifmgd->orig_teardown_skb = NULL;
 }
 
 /* scan finished notification */
@@ -3990,9 +4313,13 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
 	struct ieee80211_bss *bss = (void *)cbss->priv;
 	struct sta_info *new_sta = NULL;
-	bool have_sta = false;
+	struct ieee80211_supported_band *sband;
+	struct ieee80211_sta_ht_cap sta_ht_cap;
+	bool have_sta = false, is_override = false;
 	int err;
 
+	sband = local->hw.wiphy->bands[cbss->channel->band];
+
 	if (WARN_ON(!ifmgd->auth_data && !ifmgd->assoc_data))
 		return -EINVAL;
 
@@ -4007,25 +4334,32 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata,
 		if (!new_sta)
 			return -ENOMEM;
 	}
+
+	memcpy(&sta_ht_cap, &sband->ht_cap, sizeof(sta_ht_cap));
+	ieee80211_apply_htcap_overrides(sdata, &sta_ht_cap);
+
+	is_override = (sta_ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40) !=
+		      (sband->ht_cap.cap &
+		       IEEE80211_HT_CAP_SUP_WIDTH_20_40);
+
+	if (new_sta || is_override) {
+		err = ieee80211_prep_channel(sdata, cbss);
+		if (err) {
+			if (new_sta)
+				sta_info_free(local, new_sta);
+			return -EINVAL;
+		}
+	}
+
 	if (new_sta) {
 		u32 rates = 0, basic_rates = 0;
 		bool have_higher_than_11mbit;
 		int min_rate = INT_MAX, min_rate_index = -1;
 		struct ieee80211_chanctx_conf *chanctx_conf;
-		struct ieee80211_supported_band *sband;
 		const struct cfg80211_bss_ies *ies;
-		int shift;
+		int shift = ieee80211_vif_get_shift(&sdata->vif);
 		u32 rate_flags;
 
-		sband = local->hw.wiphy->bands[cbss->channel->band];
-
-		err = ieee80211_prep_channel(sdata, cbss);
-		if (err) {
-			sta_info_free(local, new_sta);
-			return -EINVAL;
-		}
-		shift = ieee80211_vif_get_shift(&sdata->vif);
-
 		rcu_read_lock();
 		chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
 		if (WARN_ON(!chanctx_conf)) {
@@ -4119,6 +4453,10 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata,
 	} else
 		WARN_ON_ONCE(!ether_addr_equal(ifmgd->bssid, cbss->bssid));
 
+	/* Cancel scan to ensure that nothing interferes with connection */
+	if (local->scanning)
+		ieee80211_scan_cancel(local);
+
 	return 0;
 }
 
@@ -4207,8 +4545,9 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata,
 				       WLAN_REASON_UNSPECIFIED,
 				       false, frame_buf);
 
-		cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf,
-				      sizeof(frame_buf));
+		ieee80211_report_disconnect(sdata, frame_buf,
+					    sizeof(frame_buf), true,
+					    WLAN_REASON_UNSPECIFIED);
 	}
 
 	sdata_info(sdata, "authenticate with %pM\n", req->bss->bssid);
@@ -4228,7 +4567,7 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata,
 	return 0;
 
  err_clear:
-	memset(ifmgd->bssid, 0, ETH_ALEN);
+	eth_zero_addr(ifmgd->bssid);
 	ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BSSID);
 	ifmgd->auth_data = NULL;
  err_free:
@@ -4308,8 +4647,9 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 				       WLAN_REASON_UNSPECIFIED,
 				       false, frame_buf);
 
-		cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf,
-				      sizeof(frame_buf));
+		ieee80211_report_disconnect(sdata, frame_buf,
+					    sizeof(frame_buf), true,
+					    WLAN_REASON_UNSPECIFIED);
 	}
 
 	if (ifmgd->auth_data && !ifmgd->auth_data->done) {
@@ -4461,8 +4801,13 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 		ifmgd->flags |= IEEE80211_STA_DISABLE_VHT;
 	rcu_read_unlock();
 
+	if (WARN((sdata->vif.driver_flags & IEEE80211_VIF_SUPPORTS_UAPSD) &&
+		 (local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK),
+	     "U-APSD not supported with HW_PS_NULLFUNC_STACK\n"))
+		sdata->vif.driver_flags &= ~IEEE80211_VIF_SUPPORTS_UAPSD;
+
 	if (bss->wmm_used && bss->uapsd_supported &&
-	    (sdata->local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD)) {
+	    (sdata->vif.driver_flags & IEEE80211_VIF_SUPPORTS_UAPSD)) {
 		assoc_data->uapsd = true;
 		ifmgd->flags |= IEEE80211_STA_UAPSD_ENABLED;
 	} else {
@@ -4566,7 +4911,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 
 	return 0;
  err_clear:
-	memset(ifmgd->bssid, 0, ETH_ALEN);
+	eth_zero_addr(ifmgd->bssid);
 	ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BSSID);
 	ifmgd->assoc_data = NULL;
  err_free:
@@ -4594,8 +4939,9 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata,
 					       req->reason_code, tx,
 					       frame_buf);
 		ieee80211_destroy_auth_data(sdata, false);
-		cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf,
-				      IEEE80211_DEAUTH_FRAME_LEN);
+		ieee80211_report_disconnect(sdata, frame_buf,
+					    sizeof(frame_buf), true,
+					    req->reason_code);
 
 		return 0;
 	}
@@ -4609,8 +4955,9 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata,
 
 		ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH,
 				       req->reason_code, tx, frame_buf);
-		cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf,
-				      IEEE80211_DEAUTH_FRAME_LEN);
+		ieee80211_report_disconnect(sdata, frame_buf,
+					    sizeof(frame_buf), true,
+					    req->reason_code);
 		return 0;
 	}
 
@@ -4642,8 +4989,8 @@ int ieee80211_mgd_disassoc(struct ieee80211_sub_if_data *sdata,
 			       req->reason_code, !req->local_state_change,
 			       frame_buf);
 
-	cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf,
-			      IEEE80211_DEAUTH_FRAME_LEN);
+	ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), true,
+				    req->reason_code);
 
 	return 0;
 }
@@ -4672,6 +5019,13 @@ void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata)
 	}
 	if (ifmgd->auth_data)
 		ieee80211_destroy_auth_data(sdata, false);
+	spin_lock_bh(&ifmgd->teardown_lock);
+	if (ifmgd->teardown_skb) {
+		kfree_skb(ifmgd->teardown_skb);
+		ifmgd->teardown_skb = NULL;
+		ifmgd->orig_teardown_skb = NULL;
+	}
+	spin_unlock_bh(&ifmgd->teardown_lock);
 	del_timer_sync(&ifmgd->timer);
 	sdata_unlock(sdata);
 }
@@ -4687,3 +5041,13 @@ void ieee80211_cqm_rssi_notify(struct ieee80211_vif *vif,
 	cfg80211_cqm_rssi_notify(sdata->dev, rssi_event, gfp);
 }
 EXPORT_SYMBOL(ieee80211_cqm_rssi_notify);
+
+void ieee80211_cqm_beacon_loss_notify(struct ieee80211_vif *vif, gfp_t gfp)
+{
+	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
+
+	trace_api_cqm_beacon_loss_notify(sdata->local, sdata);
+
+	cfg80211_cqm_beacon_loss_notify(sdata->dev, gfp);
+}
+EXPORT_SYMBOL(ieee80211_cqm_beacon_loss_notify);
diff --git a/net/mac80211/ocb.c b/net/mac80211/ocb.c
new file mode 100644
index 000000000000..358d5f9d8207
--- /dev/null
+++ b/net/mac80211/ocb.c
@@ -0,0 +1,250 @@
+/*
+ * OCB mode implementation
+ *
+ * Copyright: (c) 2014 Czech Technical University in Prague
+ *            (c) 2014 Volkswagen Group Research
+ * Author:    Rostislav Lisovy <rostislav.lisovy@fel.cvut.cz>
+ * Funded by: Volkswagen Group Research
+ *
+ * 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/delay.h>
+#include <linux/if_ether.h>
+#include <linux/skbuff.h>
+#include <linux/if_arp.h>
+#include <linux/etherdevice.h>
+#include <linux/rtnetlink.h>
+#include <net/mac80211.h>
+#include <asm/unaligned.h>
+
+#include "ieee80211_i.h"
+#include "driver-ops.h"
+#include "rate.h"
+
+#define IEEE80211_OCB_HOUSEKEEPING_INTERVAL		(60 * HZ)
+#define IEEE80211_OCB_PEER_INACTIVITY_LIMIT		(240 * HZ)
+#define IEEE80211_OCB_MAX_STA_ENTRIES			128
+
+/**
+ * enum ocb_deferred_task_flags - mac80211 OCB deferred tasks
+ * @OCB_WORK_HOUSEKEEPING: run the periodic OCB housekeeping tasks
+ *
+ * These flags are used in @wrkq_flags field of &struct ieee80211_if_ocb
+ */
+enum ocb_deferred_task_flags {
+	OCB_WORK_HOUSEKEEPING,
+};
+
+void ieee80211_ocb_rx_no_sta(struct ieee80211_sub_if_data *sdata,
+			     const u8 *bssid, const u8 *addr,
+			     u32 supp_rates)
+{
+	struct ieee80211_if_ocb *ifocb = &sdata->u.ocb;
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_chanctx_conf *chanctx_conf;
+	struct ieee80211_supported_band *sband;
+	enum nl80211_bss_scan_width scan_width;
+	struct sta_info *sta;
+	int band;
+
+	/* XXX: Consider removing the least recently used entry and
+	 *      allow new one to be added.
+	 */
+	if (local->num_sta >= IEEE80211_OCB_MAX_STA_ENTRIES) {
+		net_info_ratelimited("%s: No room for a new OCB STA entry %pM\n",
+				     sdata->name, addr);
+		return;
+	}
+
+	ocb_dbg(sdata, "Adding new OCB station %pM\n", addr);
+
+	rcu_read_lock();
+	chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
+	if (WARN_ON_ONCE(!chanctx_conf)) {
+		rcu_read_unlock();
+		return;
+	}
+	band = chanctx_conf->def.chan->band;
+	scan_width = cfg80211_chandef_to_scan_width(&chanctx_conf->def);
+	rcu_read_unlock();
+
+	sta = sta_info_alloc(sdata, addr, GFP_ATOMIC);
+	if (!sta)
+		return;
+
+	sta->last_rx = jiffies;
+
+	/* Add only mandatory rates for now */
+	sband = local->hw.wiphy->bands[band];
+	sta->sta.supp_rates[band] =
+		ieee80211_mandatory_rates(sband, scan_width);
+
+	spin_lock(&ifocb->incomplete_lock);
+	list_add(&sta->list, &ifocb->incomplete_stations);
+	spin_unlock(&ifocb->incomplete_lock);
+	ieee80211_queue_work(&local->hw, &sdata->work);
+}
+
+static struct sta_info *ieee80211_ocb_finish_sta(struct sta_info *sta)
+	__acquires(RCU)
+{
+	struct ieee80211_sub_if_data *sdata = sta->sdata;
+	u8 addr[ETH_ALEN];
+
+	memcpy(addr, sta->sta.addr, ETH_ALEN);
+
+	ocb_dbg(sdata, "Adding new IBSS station %pM (dev=%s)\n",
+		addr, sdata->name);
+
+	sta_info_move_state(sta, IEEE80211_STA_AUTH);
+	sta_info_move_state(sta, IEEE80211_STA_ASSOC);
+	sta_info_move_state(sta, IEEE80211_STA_AUTHORIZED);
+
+	rate_control_rate_init(sta);
+
+	/* If it fails, maybe we raced another insertion? */
+	if (sta_info_insert_rcu(sta))
+		return sta_info_get(sdata, addr);
+	return sta;
+}
+
+static void ieee80211_ocb_housekeeping(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_if_ocb *ifocb = &sdata->u.ocb;
+
+	ocb_dbg(sdata, "Running ocb housekeeping\n");
+
+	ieee80211_sta_expire(sdata, IEEE80211_OCB_PEER_INACTIVITY_LIMIT);
+
+	mod_timer(&ifocb->housekeeping_timer,
+		  round_jiffies(jiffies + IEEE80211_OCB_HOUSEKEEPING_INTERVAL));
+}
+
+void ieee80211_ocb_work(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_if_ocb *ifocb = &sdata->u.ocb;
+	struct sta_info *sta;
+
+	if (ifocb->joined != true)
+		return;
+
+	sdata_lock(sdata);
+
+	spin_lock_bh(&ifocb->incomplete_lock);
+	while (!list_empty(&ifocb->incomplete_stations)) {
+		sta = list_first_entry(&ifocb->incomplete_stations,
+				       struct sta_info, list);
+		list_del(&sta->list);
+		spin_unlock_bh(&ifocb->incomplete_lock);
+
+		ieee80211_ocb_finish_sta(sta);
+		rcu_read_unlock();
+		spin_lock_bh(&ifocb->incomplete_lock);
+	}
+	spin_unlock_bh(&ifocb->incomplete_lock);
+
+	if (test_and_clear_bit(OCB_WORK_HOUSEKEEPING, &ifocb->wrkq_flags))
+		ieee80211_ocb_housekeeping(sdata);
+
+	sdata_unlock(sdata);
+}
+
+static void ieee80211_ocb_housekeeping_timer(unsigned long data)
+{
+	struct ieee80211_sub_if_data *sdata = (void *)data;
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_if_ocb *ifocb = &sdata->u.ocb;
+
+	set_bit(OCB_WORK_HOUSEKEEPING, &ifocb->wrkq_flags);
+
+	ieee80211_queue_work(&local->hw, &sdata->work);
+}
+
+void ieee80211_ocb_setup_sdata(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_if_ocb *ifocb = &sdata->u.ocb;
+
+	setup_timer(&ifocb->housekeeping_timer,
+		    ieee80211_ocb_housekeeping_timer,
+		    (unsigned long)sdata);
+	INIT_LIST_HEAD(&ifocb->incomplete_stations);
+	spin_lock_init(&ifocb->incomplete_lock);
+}
+
+int ieee80211_ocb_join(struct ieee80211_sub_if_data *sdata,
+		       struct ocb_setup *setup)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_if_ocb *ifocb = &sdata->u.ocb;
+	u32 changed = BSS_CHANGED_OCB;
+	int err;
+
+	if (ifocb->joined == true)
+		return -EINVAL;
+
+	sdata->flags |= IEEE80211_SDATA_OPERATING_GMODE;
+	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;
+
+	ieee80211_bss_info_change_notify(sdata, changed);
+
+	ifocb->joined = true;
+
+	set_bit(OCB_WORK_HOUSEKEEPING, &ifocb->wrkq_flags);
+	ieee80211_queue_work(&local->hw, &sdata->work);
+
+	netif_carrier_on(sdata->dev);
+	return 0;
+}
+
+int ieee80211_ocb_leave(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_if_ocb *ifocb = &sdata->u.ocb;
+	struct ieee80211_local *local = sdata->local;
+	struct sta_info *sta;
+
+	ifocb->joined = false;
+	sta_info_flush(sdata);
+
+	spin_lock_bh(&ifocb->incomplete_lock);
+	while (!list_empty(&ifocb->incomplete_stations)) {
+		sta = list_first_entry(&ifocb->incomplete_stations,
+				       struct sta_info, list);
+		list_del(&sta->list);
+		spin_unlock_bh(&ifocb->incomplete_lock);
+
+		sta_info_free(local, sta);
+		spin_lock_bh(&ifocb->incomplete_lock);
+	}
+	spin_unlock_bh(&ifocb->incomplete_lock);
+
+	netif_carrier_off(sdata->dev);
+	clear_bit(SDATA_STATE_OFFCHANNEL, &sdata->state);
+	ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_OCB);
+
+	mutex_lock(&sdata->local->mtx);
+	ieee80211_vif_release_channel(sdata);
+	mutex_unlock(&sdata->local->mtx);
+
+	skb_queue_purge(&sdata->skb_queue);
+
+	del_timer_sync(&sdata->u.ocb.housekeeping_timer);
+	/* If the timer fired while we waited for it, it will have
+	 * requeued the work. Now the work will be running again
+	 * but will not rearm the timer again because it checks
+	 * whether we are connected to the network or not -- at this
+	 * point we shouldn't be anymore.
+	 */
+
+	return 0;
+}
diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c
index ff20b2ebdb30..683f0e3cb124 100644
--- a/net/mac80211/offchannel.c
+++ b/net/mac80211/offchannel.c
@@ -121,7 +121,7 @@ void ieee80211_offchannel_stop_vifs(struct ieee80211_local *local)
 	ieee80211_stop_queues_by_reason(&local->hw, IEEE80211_MAX_QUEUE_MAP,
 					IEEE80211_QUEUE_STOP_REASON_OFFCHANNEL,
 					false);
-	ieee80211_flush_queues(local, NULL);
+	ieee80211_flush_queues(local, NULL, false);
 
 	mutex_lock(&local->iflist_mtx);
 	list_for_each_entry(sdata, &local->interfaces, list) {
@@ -398,7 +398,7 @@ void ieee80211_sw_roc_work(struct work_struct *work)
 		ieee80211_roc_notify_destroy(roc, !roc->abort);
 
 		if (started && !on_channel) {
-			ieee80211_flush_queues(local, NULL);
+			ieee80211_flush_queues(local, NULL, false);
 
 			local->tmp_channel = NULL;
 			ieee80211_hw_config(local, 0);
diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c
index 4c5192e0d66c..ac6ad6238e3a 100644
--- a/net/mac80211/pm.c
+++ b/net/mac80211/pm.c
@@ -41,7 +41,7 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
 	/* flush out all packets */
 	synchronize_net();
 
-	ieee80211_flush_queues(local, NULL);
+	ieee80211_flush_queues(local, NULL, true);
 
 	local->quiescing = true;
 	/* make quiescing visible to timers everywhere */
@@ -59,9 +59,26 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
 	cancel_work_sync(&local->dynamic_ps_enable_work);
 	del_timer_sync(&local->dynamic_ps_timer);
 
-	local->wowlan = wowlan && local->open_count;
+	local->wowlan = wowlan;
 	if (local->wowlan) {
-		int err = drv_suspend(local, wowlan);
+		int err;
+
+		/* Drivers don't expect to suspend while some operations like
+		 * authenticating or associating are in progress. It doesn't
+		 * make sense anyway to accept that, since the authentication
+		 * or association would never finish since the driver can't do
+		 * that on its own.
+		 * Thus, clean up in-progress auth/assoc first.
+		 */
+		list_for_each_entry(sdata, &local->interfaces, list) {
+			if (!ieee80211_sdata_running(sdata))
+				continue;
+			if (sdata->vif.type != NL80211_IFTYPE_STATION)
+				continue;
+			ieee80211_mgd_quiesce(sdata);
+		}
+
+		err = drv_suspend(local, wowlan);
 		if (err < 0) {
 			local->quiescing = false;
 			local->wowlan = false;
@@ -80,26 +97,19 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
 			return err;
 		} else if (err > 0) {
 			WARN_ON(err != 1);
+			/* cfg80211 will call back into mac80211 to disconnect
+			 * all interfaces, allow that to proceed properly
+			 */
+			ieee80211_wake_queues_by_reason(hw,
+					IEEE80211_MAX_QUEUE_MAP,
+					IEEE80211_QUEUE_STOP_REASON_SUSPEND,
+					false);
 			return err;
 		} else {
 			goto suspend;
 		}
 	}
 
-	/* tear down aggregation sessions and remove STAs */
-	mutex_lock(&local->sta_mtx);
-	list_for_each_entry(sta, &local->sta_list, list) {
-		if (sta->uploaded) {
-			enum ieee80211_sta_state state;
-
-			state = sta->sta_state;
-			for (; state > IEEE80211_STA_NOTEXIST; state--)
-				WARN_ON(drv_sta_state(local, sta->sdata, sta,
-						      state, state - 1));
-		}
-	}
-	mutex_unlock(&local->sta_mtx);
-
 	/* remove all interfaces that were created in the driver */
 	list_for_each_entry(sdata, &local->interfaces, list) {
 		if (!ieee80211_sdata_running(sdata))
@@ -111,6 +121,21 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
 		case NL80211_IFTYPE_STATION:
 			ieee80211_mgd_quiesce(sdata);
 			break;
+		case NL80211_IFTYPE_WDS:
+			/* tear down aggregation sessions and remove STAs */
+			mutex_lock(&local->sta_mtx);
+			sta = sdata->u.wds.sta;
+			if (sta && sta->uploaded) {
+				enum ieee80211_sta_state state;
+
+				state = sta->sta_state;
+				for (; state > IEEE80211_STA_NOTEXIST; state--)
+					WARN_ON(drv_sta_state(local, sta->sdata,
+							      sta, state,
+							      state - 1));
+			}
+			mutex_unlock(&local->sta_mtx);
+			break;
 		default:
 			break;
 		}
diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c
index 6081329784dd..d53355b011f5 100644
--- a/net/mac80211/rate.c
+++ b/net/mac80211/rate.c
@@ -385,7 +385,7 @@ static void rate_idx_match_mask(struct ieee80211_tx_rate *rate,
 			*rate = alt_rate;
 			return;
 		}
-	} else {
+	} else if (!(rate->flags & IEEE80211_TX_RC_VHT_MCS)) {
 		/* handle legacy rates */
 		if (rate_idx_match_legacy_mask(rate, sband->n_bitrates, mask))
 			return;
@@ -446,7 +446,8 @@ static void rate_fixup_ratelist(struct ieee80211_vif *vif,
 	 *
 	 * XXX: Should this check all retry rates?
 	 */
-	if (!(rates[0].flags & IEEE80211_TX_RC_MCS)) {
+	if (!(rates[0].flags &
+	      (IEEE80211_TX_RC_MCS | IEEE80211_TX_RC_VHT_MCS))) {
 		u32 basic_rates = vif->bss_conf.basic_rates;
 		s8 baserate = basic_rates ? ffs(basic_rates) - 1 : 0;
 
@@ -696,6 +697,7 @@ int rate_control_set_rates(struct ieee80211_hw *hw,
 			   struct ieee80211_sta *pubsta,
 			   struct ieee80211_sta_rates *rates)
 {
+	struct sta_info *sta = container_of(pubsta, struct sta_info, sta);
 	struct ieee80211_sta_rates *old;
 
 	/*
@@ -709,6 +711,8 @@ int rate_control_set_rates(struct ieee80211_hw *hw,
 	if (old)
 		kfree_rcu(old, rcu_head);
 
+	drv_sta_rate_tbl_update(hw_to_local(hw), sta->sdata, pubsta);
+
 	return 0;
 }
 EXPORT_SYMBOL(rate_control_set_rates);
diff --git a/net/mac80211/rate.h b/net/mac80211/rate.h
index 18babe302832..38652f09feaf 100644
--- a/net/mac80211/rate.h
+++ b/net/mac80211/rate.h
@@ -37,13 +37,35 @@ static inline void rate_control_tx_status(struct ieee80211_local *local,
 	struct rate_control_ref *ref = local->rate_ctrl;
 	struct ieee80211_sta *ista = &sta->sta;
 	void *priv_sta = sta->rate_ctrl_priv;
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 
 	if (!ref || !test_sta_flag(sta, WLAN_STA_RATE_CONTROL))
 		return;
 
-	ref->ops->tx_status(ref->priv, sband, ista, priv_sta, skb);
+	if (ref->ops->tx_status)
+		ref->ops->tx_status(ref->priv, sband, ista, priv_sta, skb);
+	else
+		ref->ops->tx_status_noskb(ref->priv, sband, ista, priv_sta, info);
 }
 
+static inline void
+rate_control_tx_status_noskb(struct ieee80211_local *local,
+			     struct ieee80211_supported_band *sband,
+			     struct sta_info *sta,
+			     struct ieee80211_tx_info *info)
+{
+	struct rate_control_ref *ref = local->rate_ctrl;
+	struct ieee80211_sta *ista = &sta->sta;
+	void *priv_sta = sta->rate_ctrl_priv;
+
+	if (!ref || !test_sta_flag(sta, WLAN_STA_RATE_CONTROL))
+		return;
+
+	if (WARN_ON_ONCE(!ref->ops->tx_status_noskb))
+		return;
+
+	ref->ops->tx_status_noskb(ref->priv, sband, ista, priv_sta, info);
+}
 
 static inline void rate_control_rate_init(struct sta_info *sta)
 {
diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c
index 2baa7ed8789d..247552a7f6c2 100644
--- a/net/mac80211/rc80211_minstrel.c
+++ b/net/mac80211/rc80211_minstrel.c
@@ -69,14 +69,39 @@ rix_to_ndx(struct minstrel_sta_info *mi, int rix)
 	return i;
 }
 
+/* return current EMWA throughput */
+int minstrel_get_tp_avg(struct minstrel_rate *mr, int prob_ewma)
+{
+	int usecs;
+
+	usecs = mr->perfect_tx_time;
+	if (!usecs)
+		usecs = 1000000;
+
+	/* reset thr. below 10% success */
+	if (mr->stats.prob_ewma < MINSTREL_FRAC(10, 100))
+		return 0;
+
+	if (prob_ewma > MINSTREL_FRAC(90, 100))
+		return MINSTREL_TRUNC(100000 * (MINSTREL_FRAC(90, 100) / usecs));
+	else
+		return MINSTREL_TRUNC(100000 * (prob_ewma / usecs));
+}
+
 /* find & sort topmost throughput rates */
 static inline void
 minstrel_sort_best_tp_rates(struct minstrel_sta_info *mi, int i, u8 *tp_list)
 {
 	int j = MAX_THR_RATES;
+	struct minstrel_rate_stats *tmp_mrs = &mi->r[j - 1].stats;
+	struct minstrel_rate_stats *cur_mrs = &mi->r[i].stats;
 
-	while (j > 0 && mi->r[i].stats.cur_tp > mi->r[tp_list[j - 1]].stats.cur_tp)
+	while (j > 0 && (minstrel_get_tp_avg(&mi->r[i], cur_mrs->prob_ewma) >
+	       minstrel_get_tp_avg(&mi->r[tp_list[j - 1]], tmp_mrs->prob_ewma))) {
 		j--;
+		tmp_mrs = &mi->r[tp_list[j - 1]].stats;
+	}
+
 	if (j < MAX_THR_RATES - 1)
 		memmove(&tp_list[j + 1], &tp_list[j], MAX_THR_RATES - (j + 1));
 	if (j < MAX_THR_RATES)
@@ -127,13 +152,47 @@ minstrel_update_rates(struct minstrel_priv *mp, struct minstrel_sta_info *mi)
 	rate_control_set_rates(mp->hw, mi->sta, ratetbl);
 }
 
+/*
+* Recalculate statistics and counters of a given rate
+*/
+void
+minstrel_calc_rate_stats(struct minstrel_rate_stats *mrs)
+{
+	if (unlikely(mrs->attempts > 0)) {
+		mrs->sample_skipped = 0;
+		mrs->cur_prob = MINSTREL_FRAC(mrs->success, mrs->attempts);
+		if (unlikely(!mrs->att_hist)) {
+			mrs->prob_ewma = mrs->cur_prob;
+		} else {
+			/* update exponential weighted moving variance */
+			mrs->prob_ewmsd = minstrel_ewmsd(mrs->prob_ewmsd,
+							 mrs->cur_prob,
+							 mrs->prob_ewma,
+							 EWMA_LEVEL);
+
+			/*update exponential weighted moving avarage */
+			mrs->prob_ewma = minstrel_ewma(mrs->prob_ewma,
+						       mrs->cur_prob,
+						       EWMA_LEVEL);
+		}
+		mrs->att_hist += mrs->attempts;
+		mrs->succ_hist += mrs->success;
+	} else {
+		mrs->sample_skipped++;
+	}
+
+	mrs->last_success = mrs->success;
+	mrs->last_attempts = mrs->attempts;
+	mrs->success = 0;
+	mrs->attempts = 0;
+}
+
 static void
 minstrel_update_stats(struct minstrel_priv *mp, struct minstrel_sta_info *mi)
 {
 	u8 tmp_tp_rate[MAX_THR_RATES];
 	u8 tmp_prob_rate = 0;
-	u32 usecs;
-	int i;
+	int i, tmp_cur_tp, tmp_prob_tp;
 
 	for (i = 0; i < MAX_THR_RATES; i++)
 	    tmp_tp_rate[i] = 0;
@@ -141,38 +200,15 @@ minstrel_update_stats(struct minstrel_priv *mp, struct minstrel_sta_info *mi)
 	for (i = 0; i < mi->n_rates; i++) {
 		struct minstrel_rate *mr = &mi->r[i];
 		struct minstrel_rate_stats *mrs = &mi->r[i].stats;
+		struct minstrel_rate_stats *tmp_mrs = &mi->r[tmp_prob_rate].stats;
 
-		usecs = mr->perfect_tx_time;
-		if (!usecs)
-			usecs = 1000000;
-
-		if (unlikely(mrs->attempts > 0)) {
-			mrs->sample_skipped = 0;
-			mrs->cur_prob = MINSTREL_FRAC(mrs->success,
-						      mrs->attempts);
-			mrs->succ_hist += mrs->success;
-			mrs->att_hist += mrs->attempts;
-			mrs->probability = minstrel_ewma(mrs->probability,
-							 mrs->cur_prob,
-							 EWMA_LEVEL);
-		} else
-			mrs->sample_skipped++;
-
-		mrs->last_success = mrs->success;
-		mrs->last_attempts = mrs->attempts;
-		mrs->success = 0;
-		mrs->attempts = 0;
-
-		/* Update throughput per rate, reset thr. below 10% success */
-		if (mrs->probability < MINSTREL_FRAC(10, 100))
-			mrs->cur_tp = 0;
-		else
-			mrs->cur_tp = mrs->probability * (1000000 / usecs);
+		/* Update statistics of success probability per rate */
+		minstrel_calc_rate_stats(mrs);
 
 		/* Sample less often below the 10% chance of success.
 		 * Sample less often above the 95% chance of success. */
-		if (mrs->probability > MINSTREL_FRAC(95, 100) ||
-		    mrs->probability < MINSTREL_FRAC(10, 100)) {
+		if (mrs->prob_ewma > MINSTREL_FRAC(95, 100) ||
+		    mrs->prob_ewma < MINSTREL_FRAC(10, 100)) {
 			mr->adjusted_retry_count = mrs->retry_count >> 1;
 			if (mr->adjusted_retry_count > 2)
 				mr->adjusted_retry_count = 2;
@@ -191,12 +227,15 @@ minstrel_update_stats(struct minstrel_priv *mp, struct minstrel_sta_info *mi)
 		 * (1) if any success probabilitiy >= 95%, out of those rates
 		 * 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 (mrs->probability >= MINSTREL_FRAC(95, 100)) {
-			if (mrs->cur_tp >= mi->r[tmp_prob_rate].stats.cur_tp)
+		 * highest success probability is chosen as max_prob_rate */
+		if (mrs->prob_ewma >= MINSTREL_FRAC(95, 100)) {
+			tmp_cur_tp = minstrel_get_tp_avg(mr, mrs->prob_ewma);
+			tmp_prob_tp = minstrel_get_tp_avg(&mi->r[tmp_prob_rate],
+							  tmp_mrs->prob_ewma);
+			if (tmp_cur_tp >= tmp_prob_tp)
 				tmp_prob_rate = i;
 		} else {
-			if (mrs->probability >= mi->r[tmp_prob_rate].stats.probability)
+			if (mrs->prob_ewma >= tmp_mrs->prob_ewma)
 				tmp_prob_rate = i;
 		}
 	}
@@ -215,7 +254,7 @@ minstrel_update_stats(struct minstrel_priv *mp, struct minstrel_sta_info *mi)
 #endif
 
 	/* Reset update timer */
-	mi->stats_update = jiffies;
+	mi->last_stats_update = jiffies;
 
 	minstrel_update_rates(mp, mi);
 }
@@ -223,11 +262,10 @@ 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 sk_buff *skb)
+		   struct ieee80211_tx_info *info)
 {
 	struct minstrel_priv *mp = priv;
 	struct minstrel_sta_info *mi = priv_sta;
-	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	struct ieee80211_tx_rate *ar = info->status.rates;
 	int i, ndx;
 	int success;
@@ -254,7 +292,7 @@ minstrel_tx_status(void *priv, struct ieee80211_supported_band *sband,
 	if (mi->sample_deferred > 0)
 		mi->sample_deferred--;
 
-	if (time_after(jiffies, mi->stats_update +
+	if (time_after(jiffies, mi->last_stats_update +
 				(mp->update_interval * HZ) / 1000))
 		minstrel_update_stats(mp, mi);
 }
@@ -264,12 +302,12 @@ static inline unsigned int
 minstrel_get_retry_count(struct minstrel_rate *mr,
 			 struct ieee80211_tx_info *info)
 {
-	unsigned int retry = mr->adjusted_retry_count;
+	u8 retry = mr->adjusted_retry_count;
 
 	if (info->control.use_rts)
-		retry = max(2U, min(mr->stats.retry_count_rtscts, retry));
+		retry = max_t(u8, 2, min(mr->stats.retry_count_rtscts, retry));
 	else if (info->control.use_cts_prot)
-		retry = max(2U, min(mr->retry_count_cts, retry));
+		retry = max_t(u8, 2, min(mr->retry_count_cts, retry));
 	return retry;
 }
 
@@ -374,7 +412,7 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta,
 		rate++;
 		mi->sample_deferred++;
 	} else {
-		if (!msr->sample_limit != 0)
+		if (!msr->sample_limit)
 			return;
 
 		mi->sample_packets++;
@@ -386,7 +424,7 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta,
 	 * has a probability of >95%, we shouldn't be attempting
 	 * to use it, as this only wastes precious airtime */
 	if (!mrr_capable &&
-	   (mi->r[ndx].stats.probability > MINSTREL_FRAC(95, 100)))
+	   (mi->r[ndx].stats.prob_ewma > MINSTREL_FRAC(95, 100)))
 		return;
 
 	mi->prev_sample = true;
@@ -520,7 +558,7 @@ minstrel_rate_init(void *priv, struct ieee80211_supported_band *sband,
 	}
 
 	mi->n_rates = n;
-	mi->stats_update = jiffies;
+	mi->last_stats_update = jiffies;
 
 	init_sample_table(mi);
 	minstrel_update_rates(mp, mi);
@@ -554,7 +592,7 @@ minstrel_alloc_sta(void *priv, struct ieee80211_sta *sta, gfp_t gfp)
 	if (!mi->sample_table)
 		goto error1;
 
-	mi->stats_update = jiffies;
+	mi->last_stats_update = jiffies;
 	return mi;
 
 error1:
@@ -664,17 +702,23 @@ minstrel_free(void *priv)
 static u32 minstrel_get_expected_throughput(void *priv_sta)
 {
 	struct minstrel_sta_info *mi = priv_sta;
+	struct minstrel_rate_stats *tmp_mrs;
 	int idx = mi->max_tp_rate[0];
+	int tmp_cur_tp;
 
 	/* convert pkt per sec in kbps (1200 is the average pkt size used for
 	 * computing cur_tp
 	 */
-	return MINSTREL_TRUNC(mi->r[idx].stats.cur_tp) * 1200 * 8 / 1024;
+	tmp_mrs = &mi->r[idx].stats;
+	tmp_cur_tp = minstrel_get_tp_avg(&mi->r[idx], tmp_mrs->prob_ewma);
+	tmp_cur_tp = tmp_cur_tp * 1200 * 8 / 1024;
+
+	return tmp_cur_tp;
 }
 
 const struct rate_control_ops mac80211_minstrel = {
 	.name = "minstrel",
-	.tx_status = minstrel_tx_status,
+	.tx_status_noskb = minstrel_tx_status,
 	.get_rate = minstrel_get_rate,
 	.rate_init = minstrel_rate_init,
 	.alloc = minstrel_alloc,
diff --git a/net/mac80211/rc80211_minstrel.h b/net/mac80211/rc80211_minstrel.h
index 97eca86a4af0..c230bbe93262 100644
--- a/net/mac80211/rc80211_minstrel.h
+++ b/net/mac80211/rc80211_minstrel.h
@@ -13,7 +13,6 @@
 #define EWMA_DIV	128
 #define SAMPLE_COLUMNS	10	/* number of columns in sample table */
 
-
 /* scaled fraction values */
 #define MINSTREL_SCALE  16
 #define MINSTREL_FRAC(val, div) (((val) << MINSTREL_SCALE) / div)
@@ -24,30 +23,55 @@
 
 /*
  * Perform EWMA (Exponentially Weighted Moving Average) calculation
-  */
+ */
 static inline int
 minstrel_ewma(int old, int new, int weight)
 {
-	return (new * (EWMA_DIV - weight) + old * weight) / EWMA_DIV;
+	int diff, incr;
+
+	diff = new - old;
+	incr = (EWMA_DIV - weight) * diff / EWMA_DIV;
+
+	return old + incr;
+}
+
+/*
+ * Perform EWMSD (Exponentially Weighted Moving Standard Deviation) calculation
+ */
+static inline int
+minstrel_ewmsd(int old_ewmsd, int cur_prob, int prob_ewma, int weight)
+{
+	int diff, incr, tmp_var;
+
+	/* calculate exponential weighted moving variance */
+	diff = MINSTREL_TRUNC((cur_prob - prob_ewma) * 1000000);
+	incr = (EWMA_DIV - weight) * diff / EWMA_DIV;
+	tmp_var = old_ewmsd * old_ewmsd;
+	tmp_var = weight * (tmp_var + diff * incr / 1000000) / EWMA_DIV;
+
+	/* return standard deviation */
+	return (u16) int_sqrt(tmp_var);
 }
 
 struct minstrel_rate_stats {
 	/* current / last sampling period attempts/success counters */
-	unsigned int attempts, last_attempts;
-	unsigned int success, last_success;
+	u16 attempts, last_attempts;
+	u16 success, last_success;
 
 	/* total attempts/success counters */
 	u64 att_hist, succ_hist;
 
-	/* current throughput */
-	unsigned int cur_tp;
-
-	/* packet delivery probabilities */
-	unsigned int cur_prob, probability;
+	/* statistis of packet delivery probability
+	 *  cur_prob  - current prob within last update intervall
+	 *  prob_ewma - exponential weighted moving average of prob
+	 *  prob_ewmsd - exp. weighted moving standard deviation of prob */
+	unsigned int cur_prob;
+	unsigned int prob_ewma;
+	u16 prob_ewmsd;
 
 	/* maximum retry counts */
-	unsigned int retry_count;
-	unsigned int retry_count_rtscts;
+	u8 retry_count;
+	u8 retry_count_rtscts;
 
 	u8 sample_skipped;
 	bool retry_updated;
@@ -55,14 +79,15 @@ struct minstrel_rate_stats {
 
 struct minstrel_rate {
 	int bitrate;
-	int rix;
+
+	s8 rix;
+	u8 retry_count_cts;
+	u8 adjusted_retry_count;
 
 	unsigned int perfect_tx_time;
 	unsigned int ack_time;
 
 	int sample_limit;
-	unsigned int retry_count_cts;
-	unsigned int adjusted_retry_count;
 
 	struct minstrel_rate_stats stats;
 };
@@ -70,7 +95,7 @@ struct minstrel_rate {
 struct minstrel_sta_info {
 	struct ieee80211_sta *sta;
 
-	unsigned long stats_update;
+	unsigned long last_stats_update;
 	unsigned int sp_ack_dur;
 	unsigned int rate_avg;
 
@@ -94,6 +119,7 @@ struct minstrel_sta_info {
 
 #ifdef CONFIG_MAC80211_DEBUGFS
 	struct dentry *dbg_stats;
+	struct dentry *dbg_stats_csv;
 #endif
 };
 
@@ -120,7 +146,6 @@ struct minstrel_priv {
 	u32 fixed_rate_idx;
 	struct dentry *dbg_fixed_rate;
 #endif
-
 };
 
 struct minstrel_debugfs_info {
@@ -132,8 +157,13 @@ 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);
 
+/* Recalculate success probabilities and counters for a given rate using EWMA */
+void minstrel_calc_rate_stats(struct minstrel_rate_stats *mrs);
+int minstrel_get_tp_avg(struct minstrel_rate *mr, int prob_ewma);
+
 /* debugfs */
 int minstrel_stats_open(struct inode *inode, struct file *file);
+int minstrel_stats_csv_open(struct inode *inode, struct file *file);
 ssize_t minstrel_stats_read(struct file *file, char __user *buf, size_t len, loff_t *ppos);
 int minstrel_stats_release(struct inode *inode, struct file *file);
 
diff --git a/net/mac80211/rc80211_minstrel_debugfs.c b/net/mac80211/rc80211_minstrel_debugfs.c
index 2acab1bcaa4b..1db5f7c3318a 100644
--- a/net/mac80211/rc80211_minstrel_debugfs.c
+++ b/net/mac80211/rc80211_minstrel_debugfs.c
@@ -54,12 +54,28 @@
 #include <net/mac80211.h>
 #include "rc80211_minstrel.h"
 
+ssize_t
+minstrel_stats_read(struct file *file, char __user *buf, size_t len, loff_t *ppos)
+{
+	struct minstrel_debugfs_info *ms;
+
+	ms = file->private_data;
+	return simple_read_from_buffer(buf, len, ppos, ms->buf, ms->len);
+}
+
+int
+minstrel_stats_release(struct inode *inode, struct file *file)
+{
+	kfree(file->private_data);
+	return 0;
+}
+
 int
 minstrel_stats_open(struct inode *inode, struct file *file)
 {
 	struct minstrel_sta_info *mi = inode->i_private;
 	struct minstrel_debugfs_info *ms;
-	unsigned int i, tp, prob, eprob;
+	unsigned int i, tp_max, tp_avg, prob, eprob;
 	char *p;
 
 	ms = kmalloc(2048, GFP_KERNEL);
@@ -68,8 +84,14 @@ minstrel_stats_open(struct inode *inode, struct file *file)
 
 	file->private_data = ms;
 	p = ms->buf;
-	p += sprintf(p, "rate          tpt eprob *prob"
-			"  *ok(*cum)        ok(      cum)\n");
+	p += sprintf(p, "\n");
+	p += sprintf(p, "best   __________rate_________    ______"
+			"statistics______    ________last_______    "
+			"______sum-of________\n");
+	p += sprintf(p, "rate  [name idx airtime max_tp]  [ ø(tp) ø(prob) "
+			"sd(prob)]  [prob.|retry|suc|att]  "
+			"[#success | #attempts]\n");
+
 	for (i = 0; i < mi->n_rates; i++) {
 		struct minstrel_rate *mr = &mi->r[i];
 		struct minstrel_rate_stats *mrs = &mi->r[i].stats;
@@ -79,18 +101,26 @@ minstrel_stats_open(struct inode *inode, struct file *file)
 		*(p++) = (i == mi->max_tp_rate[2]) ? 'C' : ' ';
 		*(p++) = (i == mi->max_tp_rate[3]) ? 'D' : ' ';
 		*(p++) = (i == mi->max_prob_rate) ? 'P' : ' ';
-		p += sprintf(p, "%3u%s", mr->bitrate / 2,
+
+		p += sprintf(p, " %3u%s ", mr->bitrate / 2,
 				(mr->bitrate & 1 ? ".5" : "  "));
+		p += sprintf(p, "%3u  ", i);
+		p += sprintf(p, "%6u ", mr->perfect_tx_time);
 
-		tp = MINSTREL_TRUNC(mrs->cur_tp / 10);
+		tp_max = minstrel_get_tp_avg(mr, MINSTREL_FRAC(100,100));
+		tp_avg = minstrel_get_tp_avg(mr, mrs->prob_ewma);
 		prob = MINSTREL_TRUNC(mrs->cur_prob * 1000);
-		eprob = MINSTREL_TRUNC(mrs->probability * 1000);
+		eprob = MINSTREL_TRUNC(mrs->prob_ewma * 1000);
 
-		p += sprintf(p, " %4u.%1u %3u.%1u %3u.%1u"
-				" %4u(%4u) %9llu(%9llu)\n",
-				tp / 10, tp % 10,
+		p += sprintf(p, "%4u.%1u   %4u.%1u   %3u.%1u    %3u.%1u"
+				"     %3u.%1u %3u   %3u %-3u   "
+				"%9llu   %-9llu\n",
+				tp_max / 10, tp_max % 10,
+				tp_avg / 10, tp_avg % 10,
 				eprob / 10, eprob % 10,
+				mrs->prob_ewmsd / 10, mrs->prob_ewmsd % 10,
 				prob / 10, prob % 10,
+				mrs->retry_count,
 				mrs->last_success,
 				mrs->last_attempts,
 				(unsigned long long)mrs->succ_hist,
@@ -107,25 +137,75 @@ minstrel_stats_open(struct inode *inode, struct file *file)
 	return 0;
 }
 
-ssize_t
-minstrel_stats_read(struct file *file, char __user *buf, size_t len, loff_t *ppos)
+static const struct file_operations minstrel_stat_fops = {
+	.owner = THIS_MODULE,
+	.open = minstrel_stats_open,
+	.read = minstrel_stats_read,
+	.release = minstrel_stats_release,
+	.llseek = default_llseek,
+};
+
+int
+minstrel_stats_csv_open(struct inode *inode, struct file *file)
 {
+	struct minstrel_sta_info *mi = inode->i_private;
 	struct minstrel_debugfs_info *ms;
+	unsigned int i, tp_max, tp_avg, prob, eprob;
+	char *p;
 
-	ms = file->private_data;
-	return simple_read_from_buffer(buf, len, ppos, ms->buf, ms->len);
-}
+	ms = kmalloc(2048, GFP_KERNEL);
+	if (!ms)
+		return -ENOMEM;
+
+	file->private_data = ms;
+	p = ms->buf;
+
+	for (i = 0; i < mi->n_rates; i++) {
+		struct minstrel_rate *mr = &mi->r[i];
+		struct minstrel_rate_stats *mrs = &mi->r[i].stats;
+
+		p += sprintf(p, "%s" ,((i == mi->max_tp_rate[0]) ? "A" : ""));
+		p += sprintf(p, "%s" ,((i == mi->max_tp_rate[1]) ? "B" : ""));
+		p += sprintf(p, "%s" ,((i == mi->max_tp_rate[2]) ? "C" : ""));
+		p += sprintf(p, "%s" ,((i == mi->max_tp_rate[3]) ? "D" : ""));
+		p += sprintf(p, "%s" ,((i == mi->max_prob_rate) ? "P" : ""));
+
+		p += sprintf(p, ",%u%s", mr->bitrate / 2,
+				(mr->bitrate & 1 ? ".5," : ","));
+		p += sprintf(p, "%u,", i);
+		p += sprintf(p, "%u,",mr->perfect_tx_time);
+
+		tp_max = minstrel_get_tp_avg(mr, MINSTREL_FRAC(100,100));
+		tp_avg = minstrel_get_tp_avg(mr, mrs->prob_ewma);
+		prob = MINSTREL_TRUNC(mrs->cur_prob * 1000);
+		eprob = MINSTREL_TRUNC(mrs->prob_ewma * 1000);
+
+		p += sprintf(p, "%u.%u,%u.%u,%u.%u,%u.%u,%u.%u,%u,%u,%u,"
+				"%llu,%llu,%d,%d\n",
+				tp_max / 10, tp_max % 10,
+				tp_avg / 10, tp_avg % 10,
+				eprob / 10, eprob % 10,
+				mrs->prob_ewmsd / 10, mrs->prob_ewmsd % 10,
+				prob / 10, prob % 10,
+				mrs->retry_count,
+				mrs->last_success,
+				mrs->last_attempts,
+				(unsigned long long)mrs->succ_hist,
+				(unsigned long long)mrs->att_hist,
+				mi->total_packets - mi->sample_packets,
+				mi->sample_packets);
+
+	}
+	ms->len = p - ms->buf;
+
+	WARN_ON(ms->len + sizeof(*ms) > 2048);
 
-int
-minstrel_stats_release(struct inode *inode, struct file *file)
-{
-	kfree(file->private_data);
 	return 0;
 }
 
-static const struct file_operations minstrel_stat_fops = {
+static const struct file_operations minstrel_stat_csv_fops = {
 	.owner = THIS_MODULE,
-	.open = minstrel_stats_open,
+	.open = minstrel_stats_csv_open,
 	.read = minstrel_stats_read,
 	.release = minstrel_stats_release,
 	.llseek = default_llseek,
@@ -138,6 +218,9 @@ minstrel_add_sta_debugfs(void *priv, void *priv_sta, struct dentry *dir)
 
 	mi->dbg_stats = debugfs_create_file("rc_stats", S_IRUGO, dir, mi,
 			&minstrel_stat_fops);
+
+	mi->dbg_stats_csv = debugfs_create_file("rc_stats_csv", S_IRUGO, dir,
+			mi, &minstrel_stat_csv_fops);
 }
 
 void
@@ -146,4 +229,6 @@ minstrel_remove_sta_debugfs(void *priv, void *priv_sta)
 	struct minstrel_sta_info *mi = priv_sta;
 
 	debugfs_remove(mi->dbg_stats);
+
+	debugfs_remove(mi->dbg_stats_csv);
 }
diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c
index df90ce2db00c..7430a1df2ab1 100644
--- a/net/mac80211/rc80211_minstrel_ht.c
+++ b/net/mac80211/rc80211_minstrel_ht.c
@@ -10,16 +10,18 @@
 #include <linux/skbuff.h>
 #include <linux/debugfs.h>
 #include <linux/random.h>
+#include <linux/moduleparam.h>
 #include <linux/ieee80211.h>
 #include <net/mac80211.h>
 #include "rate.h"
 #include "rc80211_minstrel.h"
 #include "rc80211_minstrel_ht.h"
 
+#define AVG_AMPDU_SIZE	16
 #define AVG_PKT_SIZE	1200
 
 /* Number of bits for an average sized packet */
-#define MCS_NBITS (AVG_PKT_SIZE << 3)
+#define MCS_NBITS ((AVG_PKT_SIZE * AVG_AMPDU_SIZE) << 3)
 
 /* Number of symbols for a packet with (bps) bits per symbol */
 #define MCS_NSYMS(bps) DIV_ROUND_UP(MCS_NBITS, (bps))
@@ -32,14 +34,20 @@
 	)
 
 /* Transmit duration for the raw data part of an average sized packet */
-#define MCS_DURATION(streams, sgi, bps) MCS_SYMBOL_TIME(sgi, MCS_NSYMS((streams) * (bps)))
+#define MCS_DURATION(streams, sgi, bps) \
+	(MCS_SYMBOL_TIME(sgi, MCS_NSYMS((streams) * (bps))) / AVG_AMPDU_SIZE)
+
+#define BW_20			0
+#define BW_40			1
+#define BW_80			2
 
 /*
  * Define group sort order: HT40 -> SGI -> #streams
  */
 #define GROUP_IDX(_streams, _sgi, _ht40)	\
+	MINSTREL_HT_GROUP_0 +			\
 	MINSTREL_MAX_STREAMS * 2 * _ht40 +	\
-	MINSTREL_MAX_STREAMS * _sgi +		\
+	MINSTREL_MAX_STREAMS * _sgi +	\
 	_streams - 1
 
 /* MCS rate information for an MCS group */
@@ -47,6 +55,7 @@
 	[GROUP_IDX(_streams, _sgi, _ht40)] = {				\
 	.streams = _streams,						\
 	.flags =							\
+		IEEE80211_TX_RC_MCS |					\
 		(_sgi ? IEEE80211_TX_RC_SHORT_GI : 0) |			\
 		(_ht40 ? IEEE80211_TX_RC_40_MHZ_WIDTH : 0),		\
 	.duration = {							\
@@ -61,6 +70,47 @@
 	}								\
 }
 
+#define VHT_GROUP_IDX(_streams, _sgi, _bw)				\
+	(MINSTREL_VHT_GROUP_0 +						\
+	 MINSTREL_MAX_STREAMS * 2 * (_bw) +				\
+	 MINSTREL_MAX_STREAMS * (_sgi) +				\
+	 (_streams) - 1)
+
+#define BW2VBPS(_bw, r3, r2, r1)					\
+	(_bw == BW_80 ? r3 : _bw == BW_40 ? r2 : r1)
+
+#define VHT_GROUP(_streams, _sgi, _bw)					\
+	[VHT_GROUP_IDX(_streams, _sgi, _bw)] = {			\
+	.streams = _streams,						\
+	.flags =							\
+		IEEE80211_TX_RC_VHT_MCS |				\
+		(_sgi ? IEEE80211_TX_RC_SHORT_GI : 0) |			\
+		(_bw == BW_80 ? IEEE80211_TX_RC_80_MHZ_WIDTH :		\
+		 _bw == BW_40 ? IEEE80211_TX_RC_40_MHZ_WIDTH : 0),	\
+	.duration = {							\
+		MCS_DURATION(_streams, _sgi,				\
+			     BW2VBPS(_bw,  117,  54,  26)),		\
+		MCS_DURATION(_streams, _sgi,				\
+			     BW2VBPS(_bw,  234, 108,  52)),		\
+		MCS_DURATION(_streams, _sgi,				\
+			     BW2VBPS(_bw,  351, 162,  78)),		\
+		MCS_DURATION(_streams, _sgi,				\
+			     BW2VBPS(_bw,  468, 216, 104)),		\
+		MCS_DURATION(_streams, _sgi,				\
+			     BW2VBPS(_bw,  702, 324, 156)),		\
+		MCS_DURATION(_streams, _sgi,				\
+			     BW2VBPS(_bw,  936, 432, 208)),		\
+		MCS_DURATION(_streams, _sgi,				\
+			     BW2VBPS(_bw, 1053, 486, 234)),		\
+		MCS_DURATION(_streams, _sgi,				\
+			     BW2VBPS(_bw, 1170, 540, 260)),		\
+		MCS_DURATION(_streams, _sgi,				\
+			     BW2VBPS(_bw, 1404, 648, 312)),		\
+		MCS_DURATION(_streams, _sgi,				\
+			     BW2VBPS(_bw, 1560, 720, 346))		\
+	}								\
+}
+
 #define CCK_DURATION(_bitrate, _short, _len)		\
 	(1000 * (10 /* SIFS */ +			\
 	 (_short ? 72 + 24 : 144 + 48) +		\
@@ -76,53 +126,96 @@
 	CCK_ACK_DURATION(55, _short),			\
 	CCK_ACK_DURATION(110, _short)
 
-#define CCK_GROUP						\
-	[MINSTREL_MAX_STREAMS * MINSTREL_STREAM_GROUPS] = {	\
-		.streams = 0,					\
-		.duration = {					\
-			CCK_DURATION_LIST(false),		\
-			CCK_DURATION_LIST(true)			\
-		}						\
+#define CCK_GROUP					\
+	[MINSTREL_CCK_GROUP] = {			\
+		.streams = 0,				\
+		.flags = 0,				\
+		.duration = {				\
+			CCK_DURATION_LIST(false),	\
+			CCK_DURATION_LIST(true)		\
+		}					\
 	}
 
+#ifdef CONFIG_MAC80211_RC_MINSTREL_VHT
+static bool minstrel_vht_only = true;
+module_param(minstrel_vht_only, bool, 0644);
+MODULE_PARM_DESC(minstrel_vht_only,
+		 "Use only VHT rates when VHT is supported by sta.");
+#endif
+
 /*
  * To enable sufficiently targeted rate sampling, MCS rates are divided into
  * groups, based on the number of streams and flags (HT40, SGI) that they
  * use.
  *
  * Sortorder has to be fixed for GROUP_IDX macro to be applicable:
- * HT40 -> SGI -> #streams
+ * BW -> SGI -> #streams
  */
 const struct mcs_group minstrel_mcs_groups[] = {
-	MCS_GROUP(1, 0, 0),
-	MCS_GROUP(2, 0, 0),
+	MCS_GROUP(1, 0, BW_20),
+	MCS_GROUP(2, 0, BW_20),
 #if MINSTREL_MAX_STREAMS >= 3
-	MCS_GROUP(3, 0, 0),
+	MCS_GROUP(3, 0, BW_20),
 #endif
 
-	MCS_GROUP(1, 1, 0),
-	MCS_GROUP(2, 1, 0),
+	MCS_GROUP(1, 1, BW_20),
+	MCS_GROUP(2, 1, BW_20),
 #if MINSTREL_MAX_STREAMS >= 3
-	MCS_GROUP(3, 1, 0),
+	MCS_GROUP(3, 1, BW_20),
 #endif
 
-	MCS_GROUP(1, 0, 1),
-	MCS_GROUP(2, 0, 1),
+	MCS_GROUP(1, 0, BW_40),
+	MCS_GROUP(2, 0, BW_40),
 #if MINSTREL_MAX_STREAMS >= 3
-	MCS_GROUP(3, 0, 1),
+	MCS_GROUP(3, 0, BW_40),
 #endif
 
-	MCS_GROUP(1, 1, 1),
-	MCS_GROUP(2, 1, 1),
+	MCS_GROUP(1, 1, BW_40),
+	MCS_GROUP(2, 1, BW_40),
 #if MINSTREL_MAX_STREAMS >= 3
-	MCS_GROUP(3, 1, 1),
+	MCS_GROUP(3, 1, BW_40),
 #endif
 
-	/* must be last */
-	CCK_GROUP
-};
+	CCK_GROUP,
 
-#define MINSTREL_CCK_GROUP	(ARRAY_SIZE(minstrel_mcs_groups) - 1)
+#ifdef CONFIG_MAC80211_RC_MINSTREL_VHT
+	VHT_GROUP(1, 0, BW_20),
+	VHT_GROUP(2, 0, BW_20),
+#if MINSTREL_MAX_STREAMS >= 3
+	VHT_GROUP(3, 0, BW_20),
+#endif
+
+	VHT_GROUP(1, 1, BW_20),
+	VHT_GROUP(2, 1, BW_20),
+#if MINSTREL_MAX_STREAMS >= 3
+	VHT_GROUP(3, 1, BW_20),
+#endif
+
+	VHT_GROUP(1, 0, BW_40),
+	VHT_GROUP(2, 0, BW_40),
+#if MINSTREL_MAX_STREAMS >= 3
+	VHT_GROUP(3, 0, BW_40),
+#endif
+
+	VHT_GROUP(1, 1, BW_40),
+	VHT_GROUP(2, 1, BW_40),
+#if MINSTREL_MAX_STREAMS >= 3
+	VHT_GROUP(3, 1, BW_40),
+#endif
+
+	VHT_GROUP(1, 0, BW_80),
+	VHT_GROUP(2, 0, BW_80),
+#if MINSTREL_MAX_STREAMS >= 3
+	VHT_GROUP(3, 0, BW_80),
+#endif
+
+	VHT_GROUP(1, 1, BW_80),
+	VHT_GROUP(2, 1, BW_80),
+#if MINSTREL_MAX_STREAMS >= 3
+	VHT_GROUP(3, 1, BW_80),
+#endif
+#endif
+};
 
 static u8 sample_table[SAMPLE_COLUMNS][MCS_GROUP_RATES] __read_mostly;
 
@@ -130,16 +223,64 @@ static void
 minstrel_ht_update_rates(struct minstrel_priv *mp, struct minstrel_ht_sta *mi);
 
 /*
+ * Some VHT MCSes are invalid (when Ndbps / Nes is not an integer)
+ * e.g for MCS9@20MHzx1Nss: Ndbps=8x52*(5/6) Nes=1
+ *
+ * Returns the valid mcs map for struct minstrel_mcs_group_data.supported
+ */
+static u16
+minstrel_get_valid_vht_rates(int bw, int nss, __le16 mcs_map)
+{
+	u16 mask = 0;
+
+	if (bw == BW_20) {
+		if (nss != 3 && nss != 6)
+			mask = BIT(9);
+	} else if (bw == BW_80) {
+		if (nss == 3 || nss == 7)
+			mask = BIT(6);
+		else if (nss == 6)
+			mask = BIT(9);
+	} else {
+		WARN_ON(bw != BW_40);
+	}
+
+	switch ((le16_to_cpu(mcs_map) >> (2 * (nss - 1))) & 3) {
+	case IEEE80211_VHT_MCS_SUPPORT_0_7:
+		mask |= 0x300;
+		break;
+	case IEEE80211_VHT_MCS_SUPPORT_0_8:
+		mask |= 0x200;
+		break;
+	case IEEE80211_VHT_MCS_SUPPORT_0_9:
+		break;
+	default:
+		mask = 0x3ff;
+	}
+
+	return 0x3ff & ~mask;
+}
+
+/*
  * Look up an MCS group index based on mac80211 rate information
  */
 static int
 minstrel_ht_get_group_idx(struct ieee80211_tx_rate *rate)
 {
-	return GROUP_IDX((rate->idx / MCS_GROUP_RATES) + 1,
+	return GROUP_IDX((rate->idx / 8) + 1,
 			 !!(rate->flags & IEEE80211_TX_RC_SHORT_GI),
 			 !!(rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH));
 }
 
+static int
+minstrel_vht_get_group_idx(struct ieee80211_tx_rate *rate)
+{
+	return VHT_GROUP_IDX(ieee80211_rate_get_vht_nss(rate),
+			     !!(rate->flags & IEEE80211_TX_RC_SHORT_GI),
+			     !!(rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH) +
+			     2*!!(rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH));
+}
+
 static struct minstrel_rate_stats *
 minstrel_ht_get_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi,
 		      struct ieee80211_tx_rate *rate)
@@ -149,6 +290,9 @@ minstrel_ht_get_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi,
 	if (rate->flags & IEEE80211_TX_RC_MCS) {
 		group = minstrel_ht_get_group_idx(rate);
 		idx = rate->idx % 8;
+	} else if (rate->flags & IEEE80211_TX_RC_VHT_MCS) {
+		group = minstrel_vht_get_group_idx(rate);
+		idx = ieee80211_rate_get_vht_mcs(rate);
 	} else {
 		group = MINSTREL_CCK_GROUP;
 
@@ -169,67 +313,35 @@ minstrel_get_ratestats(struct minstrel_ht_sta *mi, int index)
 	return &mi->groups[index / MCS_GROUP_RATES].rates[index % MCS_GROUP_RATES];
 }
 
-
 /*
- * Recalculate success probabilities and counters for a rate using EWMA
+ * Return current throughput based on the average A-MPDU length, taking into
+ * account the expected number of retransmissions and their expected length
  */
-static void
-minstrel_calc_rate_ewma(struct minstrel_rate_stats *mr)
+int
+minstrel_ht_get_tp_avg(struct minstrel_ht_sta *mi, int group, int rate,
+		       int prob_ewma)
 {
-	if (unlikely(mr->attempts > 0)) {
-		mr->sample_skipped = 0;
-		mr->cur_prob = MINSTREL_FRAC(mr->success, mr->attempts);
-		if (!mr->att_hist)
-			mr->probability = mr->cur_prob;
-		else
-			mr->probability = minstrel_ewma(mr->probability,
-				mr->cur_prob, EWMA_LEVEL);
-		mr->att_hist += mr->attempts;
-		mr->succ_hist += mr->success;
-	} else {
-		mr->sample_skipped++;
-	}
-	mr->last_success = mr->success;
-	mr->last_attempts = mr->attempts;
-	mr->success = 0;
-	mr->attempts = 0;
-}
-
-/*
- * Calculate throughput based on the average A-MPDU length, taking into account
- * the expected number of retransmissions and their expected length
- */
-static void
-minstrel_ht_calc_tp(struct minstrel_ht_sta *mi, int group, int rate)
-{
-	struct minstrel_rate_stats *mr;
 	unsigned int nsecs = 0;
-	unsigned int tp;
-	unsigned int prob;
-
-	mr = &mi->groups[group].rates[rate];
-	prob = mr->probability;
 
-	if (prob < MINSTREL_FRAC(1, 10)) {
-		mr->cur_tp = 0;
-		return;
-	}
-
-	/*
-	 * For the throughput calculation, limit the probability value to 90% to
-	 * account for collision related packet error rate fluctuation
-	 */
-	if (prob > MINSTREL_FRAC(9, 10))
-		prob = MINSTREL_FRAC(9, 10);
+	/* do not account throughput if sucess prob is below 10% */
+	if (prob_ewma < MINSTREL_FRAC(10, 100))
+		return 0;
 
 	if (group != MINSTREL_CCK_GROUP)
 		nsecs = 1000 * mi->overhead / MINSTREL_TRUNC(mi->avg_ampdu_len);
 
 	nsecs += minstrel_mcs_groups[group].duration[rate];
 
-	/* prob is scaled - see MINSTREL_FRAC above */
-	tp = 1000000 * ((prob * 1000) / nsecs);
-	mr->cur_tp = MINSTREL_TRUNC(tp);
+	/*
+	 * For the throughput calculation, limit the probability value to 90% to
+	 * account for collision related packet error rate fluctuation
+	 * (prob is scaled - see MINSTREL_FRAC above)
+	 */
+	if (prob_ewma > MINSTREL_FRAC(90, 100))
+		return MINSTREL_TRUNC(100000 * ((MINSTREL_FRAC(90, 100) * 1000)
+								      / nsecs));
+	else
+		return MINSTREL_TRUNC(100000 * ((prob_ewma * 1000) / nsecs));
 }
 
 /*
@@ -240,31 +352,29 @@ minstrel_ht_calc_tp(struct minstrel_ht_sta *mi, int group, int rate)
  * MCS groups, CCK rates do not provide aggregation and are therefore at last.
  */
 static void
-minstrel_ht_sort_best_tp_rates(struct minstrel_ht_sta *mi, u8 index,
-			       u8 *tp_list)
+minstrel_ht_sort_best_tp_rates(struct minstrel_ht_sta *mi, u16 index,
+			       u16 *tp_list)
 {
-	int cur_group, cur_idx, cur_thr, cur_prob;
-	int tmp_group, tmp_idx, tmp_thr, tmp_prob;
+	int cur_group, cur_idx, cur_tp_avg, cur_prob;
+	int tmp_group, tmp_idx, tmp_tp_avg, tmp_prob;
 	int j = MAX_THR_RATES;
 
 	cur_group = index / MCS_GROUP_RATES;
 	cur_idx = index  % MCS_GROUP_RATES;
-	cur_thr = mi->groups[cur_group].rates[cur_idx].cur_tp;
-	cur_prob = mi->groups[cur_group].rates[cur_idx].probability;
-
-	tmp_group = tp_list[j - 1] / MCS_GROUP_RATES;
-	tmp_idx = tp_list[j - 1] % MCS_GROUP_RATES;
-	tmp_thr = mi->groups[tmp_group].rates[tmp_idx].cur_tp;
-	tmp_prob = mi->groups[tmp_group].rates[tmp_idx].probability;
+	cur_prob = mi->groups[cur_group].rates[cur_idx].prob_ewma;
+	cur_tp_avg = minstrel_ht_get_tp_avg(mi, cur_group, cur_idx, cur_prob);
 
-	while (j > 0 && (cur_thr > tmp_thr ||
-	      (cur_thr == tmp_thr && cur_prob > tmp_prob))) {
-		j--;
+	do {
 		tmp_group = tp_list[j - 1] / MCS_GROUP_RATES;
 		tmp_idx = tp_list[j - 1] % MCS_GROUP_RATES;
-		tmp_thr = mi->groups[tmp_group].rates[tmp_idx].cur_tp;
-		tmp_prob = mi->groups[tmp_group].rates[tmp_idx].probability;
-	}
+		tmp_prob = mi->groups[tmp_group].rates[tmp_idx].prob_ewma;
+		tmp_tp_avg = minstrel_ht_get_tp_avg(mi, tmp_group, tmp_idx,
+						    tmp_prob);
+		if (cur_tp_avg < tmp_tp_avg ||
+		    (cur_tp_avg == tmp_tp_avg && cur_prob <= tmp_prob))
+			break;
+		j--;
+	} while (j > 0);
 
 	if (j < MAX_THR_RATES - 1) {
 		memmove(&tp_list[j + 1], &tp_list[j], (sizeof(*tp_list) *
@@ -278,19 +388,24 @@ minstrel_ht_sort_best_tp_rates(struct minstrel_ht_sta *mi, u8 index,
  * Find and set the topmost probability rate per sta and per group
  */
 static void
-minstrel_ht_set_best_prob_rate(struct minstrel_ht_sta *mi, u8 index)
+minstrel_ht_set_best_prob_rate(struct minstrel_ht_sta *mi, u16 index)
 {
 	struct minstrel_mcs_group_data *mg;
-	struct minstrel_rate_stats *mr;
-	int tmp_group, tmp_idx, tmp_tp, tmp_prob, max_tp_group;
+	struct minstrel_rate_stats *mrs;
+	int tmp_group, tmp_idx, tmp_tp_avg, tmp_prob;
+	int max_tp_group, cur_tp_avg, cur_group, cur_idx;
+	int max_gpr_group, max_gpr_idx;
+	int max_gpr_tp_avg, max_gpr_prob;
 
+	cur_group = index / MCS_GROUP_RATES;
+	cur_idx = index % MCS_GROUP_RATES;
 	mg = &mi->groups[index / MCS_GROUP_RATES];
-	mr = &mg->rates[index % MCS_GROUP_RATES];
+	mrs = &mg->rates[index % MCS_GROUP_RATES];
 
 	tmp_group = mi->max_prob_rate / MCS_GROUP_RATES;
 	tmp_idx = mi->max_prob_rate % MCS_GROUP_RATES;
-	tmp_tp = mi->groups[tmp_group].rates[tmp_idx].cur_tp;
-	tmp_prob = mi->groups[tmp_group].rates[tmp_idx].probability;
+	tmp_prob = mi->groups[tmp_group].rates[tmp_idx].prob_ewma;
+	tmp_tp_avg = minstrel_ht_get_tp_avg(mi, tmp_group, tmp_idx, tmp_prob);
 
 	/* if max_tp_rate[0] is from MCS_GROUP max_prob_rate get selected from
 	 * MCS_GROUP as well as CCK_GROUP rates do not allow aggregation */
@@ -299,15 +414,24 @@ minstrel_ht_set_best_prob_rate(struct minstrel_ht_sta *mi, u8 index)
 	    (max_tp_group != MINSTREL_CCK_GROUP))
 		return;
 
-	if (mr->probability > MINSTREL_FRAC(75, 100)) {
-		if (mr->cur_tp > tmp_tp)
+	if (mrs->prob_ewma > MINSTREL_FRAC(75, 100)) {
+		cur_tp_avg = minstrel_ht_get_tp_avg(mi, cur_group, cur_idx,
+						    mrs->prob_ewma);
+		if (cur_tp_avg > tmp_tp_avg)
 			mi->max_prob_rate = index;
-		if (mr->cur_tp > mg->rates[mg->max_group_prob_rate].cur_tp)
+
+		max_gpr_group = mg->max_group_prob_rate / MCS_GROUP_RATES;
+		max_gpr_idx = mg->max_group_prob_rate %	MCS_GROUP_RATES;
+		max_gpr_prob = mi->groups[max_gpr_group].rates[max_gpr_idx].prob_ewma;
+		max_gpr_tp_avg = minstrel_ht_get_tp_avg(mi, max_gpr_group,
+							max_gpr_idx,
+							max_gpr_prob);
+		if (cur_tp_avg > max_gpr_tp_avg)
 			mg->max_group_prob_rate = index;
 	} else {
-		if (mr->probability > tmp_prob)
+		if (mrs->prob_ewma > tmp_prob)
 			mi->max_prob_rate = index;
-		if (mr->probability > mg->rates[mg->max_group_prob_rate].probability)
+		if (mrs->prob_ewma > mg->rates[mg->max_group_prob_rate].prob_ewma)
 			mg->max_group_prob_rate = index;
 	}
 }
@@ -321,19 +445,21 @@ minstrel_ht_set_best_prob_rate(struct minstrel_ht_sta *mi, u8 index)
  */
 static void
 minstrel_ht_assign_best_tp_rates(struct minstrel_ht_sta *mi,
-				 u8 tmp_mcs_tp_rate[MAX_THR_RATES],
-				 u8 tmp_cck_tp_rate[MAX_THR_RATES])
+				 u16 tmp_mcs_tp_rate[MAX_THR_RATES],
+				 u16 tmp_cck_tp_rate[MAX_THR_RATES])
 {
-	unsigned int tmp_group, tmp_idx, tmp_cck_tp, tmp_mcs_tp;
+	unsigned int tmp_group, tmp_idx, tmp_cck_tp, tmp_mcs_tp, tmp_prob;
 	int i;
 
 	tmp_group = tmp_cck_tp_rate[0] / MCS_GROUP_RATES;
 	tmp_idx = tmp_cck_tp_rate[0] % MCS_GROUP_RATES;
-	tmp_cck_tp = mi->groups[tmp_group].rates[tmp_idx].cur_tp;
+	tmp_prob = mi->groups[tmp_group].rates[tmp_idx].prob_ewma;
+	tmp_cck_tp = minstrel_ht_get_tp_avg(mi, tmp_group, tmp_idx, tmp_prob);
 
 	tmp_group = tmp_mcs_tp_rate[0] / MCS_GROUP_RATES;
 	tmp_idx = tmp_mcs_tp_rate[0] % MCS_GROUP_RATES;
-	tmp_mcs_tp = mi->groups[tmp_group].rates[tmp_idx].cur_tp;
+	tmp_prob = mi->groups[tmp_group].rates[tmp_idx].prob_ewma;
+	tmp_mcs_tp = minstrel_ht_get_tp_avg(mi, tmp_group, tmp_idx, tmp_prob);
 
 	if (tmp_cck_tp > tmp_mcs_tp) {
 		for(i = 0; i < MAX_THR_RATES; i++) {
@@ -352,8 +478,7 @@ static inline void
 minstrel_ht_prob_rate_reduce_streams(struct minstrel_ht_sta *mi)
 {
 	struct minstrel_mcs_group_data *mg;
-	struct minstrel_rate_stats *mr;
-	int tmp_max_streams, group;
+	int tmp_max_streams, group, tmp_idx, tmp_prob;
 	int tmp_tp = 0;
 
 	tmp_max_streams = minstrel_mcs_groups[mi->max_tp_rate[0] /
@@ -362,11 +487,16 @@ minstrel_ht_prob_rate_reduce_streams(struct minstrel_ht_sta *mi)
 		mg = &mi->groups[group];
 		if (!mg->supported || group == MINSTREL_CCK_GROUP)
 			continue;
-		mr = minstrel_get_ratestats(mi, mg->max_group_prob_rate);
-		if (tmp_tp < mr->cur_tp &&
+
+		tmp_idx = mg->max_group_prob_rate % MCS_GROUP_RATES;
+		tmp_prob = mi->groups[group].rates[tmp_idx].prob_ewma;
+
+		if (tmp_tp < minstrel_ht_get_tp_avg(mi, group, tmp_idx, tmp_prob) &&
 		   (minstrel_mcs_groups[group].streams < tmp_max_streams)) {
 				mi->max_prob_rate = mg->max_group_prob_rate;
-				tmp_tp = mr->cur_tp;
+				tmp_tp = minstrel_ht_get_tp_avg(mi, group,
+								tmp_idx,
+								tmp_prob);
 		}
 	}
 }
@@ -384,10 +514,10 @@ static void
 minstrel_ht_update_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi)
 {
 	struct minstrel_mcs_group_data *mg;
-	struct minstrel_rate_stats *mr;
-	int group, i, j;
-	u8 tmp_mcs_tp_rate[MAX_THR_RATES], tmp_group_tp_rate[MAX_THR_RATES];
-	u8 tmp_cck_tp_rate[MAX_THR_RATES], index;
+	struct minstrel_rate_stats *mrs;
+	int group, i, j, cur_prob;
+	u16 tmp_mcs_tp_rate[MAX_THR_RATES], tmp_group_tp_rate[MAX_THR_RATES];
+	u16 tmp_cck_tp_rate[MAX_THR_RATES], index;
 
 	if (mi->ampdu_packets > 0) {
 		mi->avg_ampdu_len = minstrel_ewma(mi->avg_ampdu_len,
@@ -424,12 +554,12 @@ minstrel_ht_update_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi)
 
 			index = MCS_GROUP_RATES * group + i;
 
-			mr = &mg->rates[i];
-			mr->retry_updated = false;
-			minstrel_calc_rate_ewma(mr);
-			minstrel_ht_calc_tp(mi, group, i);
+			mrs = &mg->rates[i];
+			mrs->retry_updated = false;
+			minstrel_calc_rate_stats(mrs);
+			cur_prob = mrs->prob_ewma;
 
-			if (!mr->cur_tp)
+			if (minstrel_ht_get_tp_avg(mi, group, i, cur_prob) == 0)
 				continue;
 
 			/* Find max throughput rate set */
@@ -473,7 +603,7 @@ minstrel_ht_update_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi)
 #endif
 
 	/* Reset update timer */
-	mi->stats_update = jiffies;
+	mi->last_stats_update = jiffies;
 }
 
 static bool
@@ -485,7 +615,8 @@ minstrel_ht_txstat_valid(struct minstrel_priv *mp, struct ieee80211_tx_rate *rat
 	if (!rate->count)
 		return false;
 
-	if (rate->flags & IEEE80211_TX_RC_MCS)
+	if (rate->flags & IEEE80211_TX_RC_MCS ||
+	    rate->flags & IEEE80211_TX_RC_VHT_MCS)
 		return true;
 
 	return rate->idx == mp->cck_rates[0] ||
@@ -495,7 +626,7 @@ minstrel_ht_txstat_valid(struct minstrel_priv *mp, struct ieee80211_tx_rate *rat
 }
 
 static void
-minstrel_next_sample_idx(struct minstrel_ht_sta *mi)
+minstrel_set_next_sample_idx(struct minstrel_ht_sta *mi)
 {
 	struct minstrel_mcs_group_data *mg;
 
@@ -517,7 +648,7 @@ minstrel_next_sample_idx(struct minstrel_ht_sta *mi)
 }
 
 static void
-minstrel_downgrade_rate(struct minstrel_ht_sta *mi, u8 *idx, bool primary)
+minstrel_downgrade_rate(struct minstrel_ht_sta *mi, u16 *idx, bool primary)
 {
 	int group, orig_group;
 
@@ -547,6 +678,9 @@ minstrel_aggr_check(struct ieee80211_sta *pubsta, struct sk_buff *skb)
 	struct sta_info *sta = container_of(pubsta, struct sta_info, sta);
 	u16 tid;
 
+	if (skb_get_queue_mapping(skb) == IEEE80211_AC_VO)
+		return;
+
 	if (unlikely(!ieee80211_is_data_qos(hdr->frame_control)))
 		return;
 
@@ -557,20 +691,16 @@ minstrel_aggr_check(struct ieee80211_sta *pubsta, struct sk_buff *skb)
 	if (likely(sta->ampdu_mlme.tid_tx[tid]))
 		return;
 
-	if (skb_get_queue_mapping(skb) == IEEE80211_AC_VO)
-		return;
-
 	ieee80211_start_tx_ba_session(pubsta, tid, 5000);
 }
 
 static void
 minstrel_ht_tx_status(void *priv, struct ieee80211_supported_band *sband,
                       struct ieee80211_sta *sta, void *priv_sta,
-                      struct sk_buff *skb)
+                      struct ieee80211_tx_info *info)
 {
 	struct minstrel_ht_sta_priv *msp = priv_sta;
 	struct minstrel_ht_sta *mi = &msp->ht;
-	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	struct ieee80211_tx_rate *ar = info->status.rates;
 	struct minstrel_rate_stats *rate, *rate2;
 	struct minstrel_priv *mp = priv;
@@ -578,7 +708,8 @@ minstrel_ht_tx_status(void *priv, struct ieee80211_supported_band *sband,
 	int i;
 
 	if (!msp->is_ht)
-		return mac80211_minstrel.tx_status(priv, sband, sta, &msp->legacy, skb);
+		return mac80211_minstrel.tx_status_noskb(priv, sband, sta,
+							 &msp->legacy, info);
 
 	/* This packet was aggregated but doesn't carry status info */
 	if ((info->flags & IEEE80211_TX_CTL_AMPDU) &&
@@ -636,12 +767,10 @@ minstrel_ht_tx_status(void *priv, struct ieee80211_supported_band *sband,
 		update = true;
 	}
 
-	if (time_after(jiffies, mi->stats_update + (mp->update_interval / 2 * HZ) / 1000)) {
+	if (time_after(jiffies, mi->last_stats_update +
+				(mp->update_interval / 2 * HZ) / 1000)) {
 		update = true;
 		minstrel_ht_update_stats(mp, mi);
-		if (!(info->flags & IEEE80211_TX_CTL_AMPDU) &&
-		    mi->max_prob_rate / MCS_GROUP_RATES != MINSTREL_CCK_GROUP)
-			minstrel_aggr_check(sta, skb);
 	}
 
 	if (update)
@@ -652,7 +781,7 @@ static void
 minstrel_calc_retransmit(struct minstrel_priv *mp, struct minstrel_ht_sta *mi,
                          int index)
 {
-	struct minstrel_rate_stats *mr;
+	struct minstrel_rate_stats *mrs;
 	const struct mcs_group *group;
 	unsigned int tx_time, tx_time_rtscts, tx_time_data;
 	unsigned int cw = mp->cw_min;
@@ -661,16 +790,16 @@ minstrel_calc_retransmit(struct minstrel_priv *mp, struct minstrel_ht_sta *mi,
 	unsigned int ampdu_len = MINSTREL_TRUNC(mi->avg_ampdu_len);
 	unsigned int overhead = 0, overhead_rtscts = 0;
 
-	mr = minstrel_get_ratestats(mi, index);
-	if (mr->probability < MINSTREL_FRAC(1, 10)) {
-		mr->retry_count = 1;
-		mr->retry_count_rtscts = 1;
+	mrs = minstrel_get_ratestats(mi, index);
+	if (mrs->prob_ewma < MINSTREL_FRAC(1, 10)) {
+		mrs->retry_count = 1;
+		mrs->retry_count_rtscts = 1;
 		return;
 	}
 
-	mr->retry_count = 2;
-	mr->retry_count_rtscts = 2;
-	mr->retry_updated = true;
+	mrs->retry_count = 2;
+	mrs->retry_count_rtscts = 2;
+	mrs->retry_updated = true;
 
 	group = &minstrel_mcs_groups[index / MCS_GROUP_RATES];
 	tx_time_data = group->duration[index % MCS_GROUP_RATES] * ampdu_len / 1000;
@@ -701,9 +830,9 @@ minstrel_calc_retransmit(struct minstrel_priv *mp, struct minstrel_ht_sta *mi,
 		tx_time_rtscts += ctime + overhead_rtscts + tx_time_data;
 
 		if (tx_time_rtscts < mp->segment_size)
-			mr->retry_count_rtscts++;
+			mrs->retry_count_rtscts++;
 	} while ((tx_time < mp->segment_size) &&
-	         (++mr->retry_count < mp->max_retry));
+	         (++mrs->retry_count < mp->max_retry));
 }
 
 
@@ -712,31 +841,31 @@ minstrel_ht_set_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi,
                      struct ieee80211_sta_rates *ratetbl, int offset, int index)
 {
 	const struct mcs_group *group = &minstrel_mcs_groups[index / MCS_GROUP_RATES];
-	struct minstrel_rate_stats *mr;
+	struct minstrel_rate_stats *mrs;
 	u8 idx;
-	u16 flags;
+	u16 flags = group->flags;
 
-	mr = minstrel_get_ratestats(mi, index);
-	if (!mr->retry_updated)
+	mrs = minstrel_get_ratestats(mi, index);
+	if (!mrs->retry_updated)
 		minstrel_calc_retransmit(mp, mi, index);
 
-	if (mr->probability < MINSTREL_FRAC(20, 100) || !mr->retry_count) {
+	if (mrs->prob_ewma < MINSTREL_FRAC(20, 100) || !mrs->retry_count) {
 		ratetbl->rate[offset].count = 2;
 		ratetbl->rate[offset].count_rts = 2;
 		ratetbl->rate[offset].count_cts = 2;
 	} else {
-		ratetbl->rate[offset].count = mr->retry_count;
-		ratetbl->rate[offset].count_cts = mr->retry_count;
-		ratetbl->rate[offset].count_rts = mr->retry_count_rtscts;
+		ratetbl->rate[offset].count = mrs->retry_count;
+		ratetbl->rate[offset].count_cts = mrs->retry_count;
+		ratetbl->rate[offset].count_rts = mrs->retry_count_rtscts;
 	}
 
-	if (index / MCS_GROUP_RATES == MINSTREL_CCK_GROUP) {
+	if (index / MCS_GROUP_RATES == MINSTREL_CCK_GROUP)
 		idx = mp->cck_rates[index % ARRAY_SIZE(mp->cck_rates)];
-		flags = 0;
-	} else {
+	else if (flags & IEEE80211_TX_RC_VHT_MCS)
+		idx = ((group->streams - 1) << 4) |
+		      ((index % MCS_GROUP_RATES) & 0xF);
+	else
 		idx = index % MCS_GROUP_RATES + (group->streams - 1) * 8;
-		flags = IEEE80211_TX_RC_MCS | group->flags;
-	}
 
 	if (offset > 0) {
 		ratetbl->rate[offset].count = ratetbl->rate[offset].count_rts;
@@ -785,7 +914,7 @@ minstrel_get_duration(int index)
 static int
 minstrel_get_sample_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi)
 {
-	struct minstrel_rate_stats *mr;
+	struct minstrel_rate_stats *mrs;
 	struct minstrel_mcs_group_data *mg;
 	unsigned int sample_dur, sample_group, cur_max_tp_streams;
 	int sample_idx = 0;
@@ -801,12 +930,12 @@ minstrel_get_sample_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi)
 	sample_group = mi->sample_group;
 	mg = &mi->groups[sample_group];
 	sample_idx = sample_table[mg->column][mg->index];
-	minstrel_next_sample_idx(mi);
+	minstrel_set_next_sample_idx(mi);
 
 	if (!(mg->supported & BIT(sample_idx)))
 		return -1;
 
-	mr = &mg->rates[sample_idx];
+	mrs = &mg->rates[sample_idx];
 	sample_idx += sample_group * MCS_GROUP_RATES;
 
 	/*
@@ -823,7 +952,7 @@ minstrel_get_sample_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi)
 	 * Do not sample if the probability is already higher than 95%
 	 * to avoid wasting airtime.
 	 */
-	if (mr->probability > MINSTREL_FRAC(95, 100))
+	if (mrs->prob_ewma > MINSTREL_FRAC(95, 100))
 		return -1;
 
 	/*
@@ -838,7 +967,7 @@ minstrel_get_sample_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi)
 	    (cur_max_tp_streams - 1 <
 	     minstrel_mcs_groups[sample_group].streams ||
 	     sample_dur >= minstrel_get_duration(mi->max_prob_rate))) {
-		if (mr->sample_skipped < 20)
+		if (mrs->sample_skipped < 20)
 			return -1;
 
 		if (mi->sample_slow++ > 2)
@@ -883,6 +1012,10 @@ minstrel_ht_get_rate(void *priv, struct ieee80211_sta *sta, void *priv_sta,
 	if (!msp->is_ht)
 		return mac80211_minstrel.get_rate(priv, sta, &msp->legacy, txrc);
 
+	if (!(info->flags & IEEE80211_TX_CTL_AMPDU) &&
+	    mi->max_prob_rate / MCS_GROUP_RATES != MINSTREL_CCK_GROUP)
+		minstrel_aggr_check(sta, txrc->skb);
+
 	info->flags |= mi->tx_flags;
 	minstrel_ht_check_cck_shortpreamble(mp, mi, txrc->short_preamble);
 
@@ -916,13 +1049,15 @@ minstrel_ht_get_rate(void *priv, struct ieee80211_sta *sta, void *priv_sta,
 	if (sample_idx / MCS_GROUP_RATES == MINSTREL_CCK_GROUP) {
 		int idx = sample_idx % ARRAY_SIZE(mp->cck_rates);
 		rate->idx = mp->cck_rates[idx];
-		rate->flags = 0;
-		return;
+	} else if (sample_group->flags & IEEE80211_TX_RC_VHT_MCS) {
+		ieee80211_rate_set_vht(rate, sample_idx % MCS_GROUP_RATES,
+				       sample_group->streams);
+	} else {
+		rate->idx = sample_idx % MCS_GROUP_RATES +
+			    (sample_group->streams - 1) * 8;
 	}
 
-	rate->idx = sample_idx % MCS_GROUP_RATES +
-		    (sample_group->streams - 1) * 8;
-	rate->flags = IEEE80211_TX_RC_MCS | sample_group->flags;
+	rate->flags = sample_group->flags;
 }
 
 static void
@@ -962,6 +1097,8 @@ minstrel_ht_update_caps(void *priv, struct ieee80211_supported_band *sband,
 	struct minstrel_ht_sta *mi = &msp->ht;
 	struct ieee80211_mcs_info *mcs = &sta->ht_cap.mcs;
 	u16 sta_cap = sta->ht_cap.cap;
+	struct ieee80211_sta_vht_cap *vht_cap = &sta->vht_cap;
+	int use_vht;
 	int n_supported = 0;
 	int ack_dur;
 	int stbc;
@@ -971,14 +1108,20 @@ minstrel_ht_update_caps(void *priv, struct ieee80211_supported_band *sband,
 	if (!sta->ht_cap.ht_supported)
 		goto use_legacy;
 
-	BUILD_BUG_ON(ARRAY_SIZE(minstrel_mcs_groups) !=
-		MINSTREL_MAX_STREAMS * MINSTREL_STREAM_GROUPS + 1);
+	BUILD_BUG_ON(ARRAY_SIZE(minstrel_mcs_groups) != MINSTREL_GROUPS_NB);
+
+#ifdef CONFIG_MAC80211_RC_MINSTREL_VHT
+	if (vht_cap->vht_supported)
+		use_vht = vht_cap->vht_mcs.tx_mcs_map != cpu_to_le16(~0);
+	else
+#endif
+	use_vht = 0;
 
 	msp->is_ht = true;
 	memset(mi, 0, sizeof(*mi));
 
 	mi->sta = sta;
-	mi->stats_update = jiffies;
+	mi->last_stats_update = jiffies;
 
 	ack_dur = ieee80211_frame_duration(sband->band, 10, 60, 1, 1, 0);
 	mi->overhead = ieee80211_frame_duration(sband->band, 0, 60, 1, 1, 0);
@@ -997,22 +1140,28 @@ minstrel_ht_update_caps(void *priv, struct ieee80211_supported_band *sband,
 	}
 	mi->sample_tries = 4;
 
-	stbc = (sta_cap & IEEE80211_HT_CAP_RX_STBC) >>
-		IEEE80211_HT_CAP_RX_STBC_SHIFT;
-	mi->tx_flags |= stbc << IEEE80211_TX_CTL_STBC_SHIFT;
+	/* TODO tx_flags for vht - ATM the RC API is not fine-grained enough */
+	if (!use_vht) {
+		stbc = (sta_cap & IEEE80211_HT_CAP_RX_STBC) >>
+			IEEE80211_HT_CAP_RX_STBC_SHIFT;
+		mi->tx_flags |= stbc << IEEE80211_TX_CTL_STBC_SHIFT;
 
-	if (sta_cap & IEEE80211_HT_CAP_LDPC_CODING)
-		mi->tx_flags |= IEEE80211_TX_CTL_LDPC;
+		if (sta_cap & IEEE80211_HT_CAP_LDPC_CODING)
+			mi->tx_flags |= IEEE80211_TX_CTL_LDPC;
+	}
 
 	for (i = 0; i < ARRAY_SIZE(mi->groups); i++) {
+		u32 gflags = minstrel_mcs_groups[i].flags;
+		int bw, nss;
+
 		mi->groups[i].supported = 0;
 		if (i == MINSTREL_CCK_GROUP) {
 			minstrel_ht_update_cck(mp, mi, sband, sta);
 			continue;
 		}
 
-		if (minstrel_mcs_groups[i].flags & IEEE80211_TX_RC_SHORT_GI) {
-			if (minstrel_mcs_groups[i].flags & IEEE80211_TX_RC_40_MHZ_WIDTH) {
+		if (gflags & IEEE80211_TX_RC_SHORT_GI) {
+			if (gflags & IEEE80211_TX_RC_40_MHZ_WIDTH) {
 				if (!(sta_cap & IEEE80211_HT_CAP_SGI_40))
 					continue;
 			} else {
@@ -1021,17 +1170,51 @@ minstrel_ht_update_caps(void *priv, struct ieee80211_supported_band *sband,
 			}
 		}
 
-		if (minstrel_mcs_groups[i].flags & IEEE80211_TX_RC_40_MHZ_WIDTH &&
+		if (gflags & IEEE80211_TX_RC_40_MHZ_WIDTH &&
 		    sta->bandwidth < IEEE80211_STA_RX_BW_40)
 			continue;
 
+		nss = minstrel_mcs_groups[i].streams;
+
 		/* Mark MCS > 7 as unsupported if STA is in static SMPS mode */
-		if (sta->smps_mode == IEEE80211_SMPS_STATIC &&
-		    minstrel_mcs_groups[i].streams > 1)
+		if (sta->smps_mode == IEEE80211_SMPS_STATIC && nss > 1)
 			continue;
 
-		mi->groups[i].supported =
-			mcs->rx_mask[minstrel_mcs_groups[i].streams - 1];
+		/* HT rate */
+		if (gflags & IEEE80211_TX_RC_MCS) {
+#ifdef CONFIG_MAC80211_RC_MINSTREL_VHT
+			if (use_vht && minstrel_vht_only)
+				continue;
+#endif
+			mi->groups[i].supported = mcs->rx_mask[nss - 1];
+			if (mi->groups[i].supported)
+				n_supported++;
+			continue;
+		}
+
+		/* VHT rate */
+		if (!vht_cap->vht_supported ||
+		    WARN_ON(!(gflags & IEEE80211_TX_RC_VHT_MCS)) ||
+		    WARN_ON(gflags & IEEE80211_TX_RC_160_MHZ_WIDTH))
+			continue;
+
+		if (gflags & IEEE80211_TX_RC_80_MHZ_WIDTH) {
+			if (sta->bandwidth < IEEE80211_STA_RX_BW_80 ||
+			    ((gflags & IEEE80211_TX_RC_SHORT_GI) &&
+			     !(vht_cap->cap & IEEE80211_VHT_CAP_SHORT_GI_80))) {
+				continue;
+			}
+		}
+
+		if (gflags & IEEE80211_TX_RC_40_MHZ_WIDTH)
+			bw = BW_40;
+		else if (gflags & IEEE80211_TX_RC_80_MHZ_WIDTH)
+			bw = BW_80;
+		else
+			bw = BW_20;
+
+		mi->groups[i].supported = minstrel_get_valid_vht_rates(bw, nss,
+				vht_cap->vht_mcs.tx_mcs_map);
 
 		if (mi->groups[i].supported)
 			n_supported++;
@@ -1135,21 +1318,24 @@ 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;
+	int i, j, prob, tp_avg;
 
 	if (!msp->is_ht)
 		return mac80211_minstrel.get_expected_throughput(priv_sta);
 
 	i = mi->max_tp_rate[0] / MCS_GROUP_RATES;
 	j = mi->max_tp_rate[0] % MCS_GROUP_RATES;
+	prob = mi->groups[i].rates[j].prob_ewma;
+
+	/* convert tp_avg from pkt per second in kbps */
+	tp_avg = minstrel_ht_get_tp_avg(mi, i, j, prob) * AVG_PKT_SIZE * 8 / 1024;
 
-	/* convert cur_tp from pkt per second in kbps */
-	return mi->groups[i].rates[j].cur_tp * AVG_PKT_SIZE * 8 / 1024;
+	return tp_avg;
 }
 
 static const struct rate_control_ops mac80211_minstrel_ht = {
 	.name = "minstrel_ht",
-	.tx_status = minstrel_ht_tx_status,
+	.tx_status_noskb = minstrel_ht_tx_status,
 	.get_rate = minstrel_ht_get_rate,
 	.rate_init = minstrel_ht_rate_init,
 	.rate_update = minstrel_ht_rate_update,
diff --git a/net/mac80211/rc80211_minstrel_ht.h b/net/mac80211/rc80211_minstrel_ht.h
index 01570e0e014b..e8b52a94d24b 100644
--- a/net/mac80211/rc80211_minstrel_ht.h
+++ b/net/mac80211/rc80211_minstrel_ht.h
@@ -13,10 +13,32 @@
  * The number of streams can be changed to 2 to reduce code
  * size and memory footprint.
  */
-#define MINSTREL_MAX_STREAMS	3
-#define MINSTREL_STREAM_GROUPS	4
+#define MINSTREL_MAX_STREAMS		3
+#define MINSTREL_HT_STREAM_GROUPS	4 /* BW(=2) * SGI(=2) */
+#ifdef CONFIG_MAC80211_RC_MINSTREL_VHT
+#define MINSTREL_VHT_STREAM_GROUPS	6 /* BW(=3) * SGI(=2) */
+#else
+#define MINSTREL_VHT_STREAM_GROUPS	0
+#endif
 
-#define MCS_GROUP_RATES	8
+#define MINSTREL_HT_GROUPS_NB	(MINSTREL_MAX_STREAMS *		\
+				 MINSTREL_HT_STREAM_GROUPS)
+#define MINSTREL_VHT_GROUPS_NB	(MINSTREL_MAX_STREAMS *		\
+				 MINSTREL_VHT_STREAM_GROUPS)
+#define MINSTREL_CCK_GROUPS_NB	1
+#define MINSTREL_GROUPS_NB	(MINSTREL_HT_GROUPS_NB +	\
+				 MINSTREL_VHT_GROUPS_NB +	\
+				 MINSTREL_CCK_GROUPS_NB)
+
+#define MINSTREL_HT_GROUP_0	0
+#define MINSTREL_CCK_GROUP	(MINSTREL_HT_GROUP_0 + MINSTREL_HT_GROUPS_NB)
+#define MINSTREL_VHT_GROUP_0	(MINSTREL_CCK_GROUP + 1)
+
+#ifdef CONFIG_MAC80211_RC_MINSTREL_VHT
+#define MCS_GROUP_RATES		10
+#else
+#define MCS_GROUP_RATES		8
+#endif
 
 struct mcs_group {
 	u32 flags;
@@ -31,11 +53,11 @@ struct minstrel_mcs_group_data {
 	u8 column;
 
 	/* bitfield of supported MCS rates of this group */
-	u8 supported;
+	u16 supported;
 
 	/* sorted rate set within a MCS group*/
-	u8 max_group_tp_rate[MAX_THR_RATES];
-	u8 max_group_prob_rate;
+	u16 max_group_tp_rate[MAX_THR_RATES];
+	u16 max_group_prob_rate;
 
 	/* MCS rate statistics */
 	struct minstrel_rate_stats rates[MCS_GROUP_RATES];
@@ -52,11 +74,11 @@ struct minstrel_ht_sta {
 	unsigned int avg_ampdu_len;
 
 	/* overall sorted rate set */
-	u8 max_tp_rate[MAX_THR_RATES];
-	u8 max_prob_rate;
+	u16 max_tp_rate[MAX_THR_RATES];
+	u16 max_prob_rate;
 
 	/* time of last status update */
-	unsigned long stats_update;
+	unsigned long last_stats_update;
 
 	/* overhead time in usec for each frame */
 	unsigned int overhead;
@@ -80,7 +102,7 @@ struct minstrel_ht_sta {
 	u8 cck_supported_short;
 
 	/* MCS rate group info and statistics */
-	struct minstrel_mcs_group_data groups[MINSTREL_MAX_STREAMS * MINSTREL_STREAM_GROUPS + 1];
+	struct minstrel_mcs_group_data groups[MINSTREL_GROUPS_NB];
 };
 
 struct minstrel_ht_sta_priv {
@@ -90,6 +112,7 @@ struct minstrel_ht_sta_priv {
 	};
 #ifdef CONFIG_MAC80211_DEBUGFS
 	struct dentry *dbg_stats;
+	struct dentry *dbg_stats_csv;
 #endif
 	void *ratelist;
 	void *sample_table;
@@ -98,5 +121,7 @@ struct minstrel_ht_sta_priv {
 
 void minstrel_ht_add_sta_debugfs(void *priv, void *priv_sta, struct dentry *dir);
 void minstrel_ht_remove_sta_debugfs(void *priv, void *priv_sta);
+int minstrel_ht_get_tp_avg(struct minstrel_ht_sta *mi, int group, int rate,
+			   int prob_ewma);
 
 #endif
diff --git a/net/mac80211/rc80211_minstrel_ht_debugfs.c b/net/mac80211/rc80211_minstrel_ht_debugfs.c
index d537bec93754..6822ce0f95e5 100644
--- a/net/mac80211/rc80211_minstrel_ht_debugfs.c
+++ b/net/mac80211/rc80211_minstrel_ht_debugfs.c
@@ -18,33 +18,46 @@
 static char *
 minstrel_ht_stats_dump(struct minstrel_ht_sta *mi, int i, char *p)
 {
-	unsigned int max_mcs = MINSTREL_MAX_STREAMS * MINSTREL_STREAM_GROUPS;
 	const struct mcs_group *mg;
-	unsigned int j, tp, prob, eprob;
+	unsigned int j, tp_max, tp_avg, prob, eprob, tx_time;
 	char htmode = '2';
 	char gimode = 'L';
+	u32 gflags;
 
 	if (!mi->groups[i].supported)
 		return p;
 
 	mg = &minstrel_mcs_groups[i];
-	if (mg->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)
+	gflags = mg->flags;
+
+	if (gflags & IEEE80211_TX_RC_40_MHZ_WIDTH)
 		htmode = '4';
-	if (mg->flags & IEEE80211_TX_RC_SHORT_GI)
+	else if (gflags & IEEE80211_TX_RC_80_MHZ_WIDTH)
+		htmode = '8';
+	if (gflags & IEEE80211_TX_RC_SHORT_GI)
 		gimode = 'S';
 
 	for (j = 0; j < MCS_GROUP_RATES; j++) {
-		struct minstrel_rate_stats *mr = &mi->groups[i].rates[j];
+		struct minstrel_rate_stats *mrs = &mi->groups[i].rates[j];
 		static const int bitrates[4] = { 10, 20, 55, 110 };
 		int idx = i * MCS_GROUP_RATES + j;
 
 		if (!(mi->groups[i].supported & BIT(j)))
 			continue;
 
-		if (i == max_mcs)
-			p += sprintf(p, "CCK/%cP   ", j < 4 ? 'L' : 'S');
-		else
-			p += sprintf(p, "HT%c0/%cGI ", htmode, gimode);
+		if (gflags & IEEE80211_TX_RC_MCS) {
+			p += sprintf(p, "HT%c0  ", htmode);
+			p += sprintf(p, "%cGI  ", gimode);
+			p += sprintf(p, "%d  ", mg->streams);
+		} else if (gflags & IEEE80211_TX_RC_VHT_MCS) {
+			p += sprintf(p, "VHT%c0 ", htmode);
+			p += sprintf(p, "%cGI ", gimode);
+			p += sprintf(p, "%d  ", mg->streams);
+		} else {
+			p += sprintf(p, "CCK    ");
+			p += sprintf(p, "%cP  ", j < 4 ? 'L' : 'S');
+			p += sprintf(p, "1 ");
+		}
 
 		*(p++) = (idx == mi->max_tp_rate[0]) ? 'A' : ' ';
 		*(p++) = (idx == mi->max_tp_rate[1]) ? 'B' : ' ';
@@ -52,27 +65,40 @@ minstrel_ht_stats_dump(struct minstrel_ht_sta *mi, int i, char *p)
 		*(p++) = (idx == mi->max_tp_rate[3]) ? 'D' : ' ';
 		*(p++) = (idx == mi->max_prob_rate) ? 'P' : ' ';
 
-		if (i == max_mcs) {
-			int r = bitrates[j % 4];
-			p += sprintf(p, " %2u.%1uM", r / 10, r % 10);
+		if (gflags & IEEE80211_TX_RC_MCS) {
+			p += sprintf(p, "  MCS%-2u", (mg->streams - 1) * 8 + j);
+		} else if (gflags & IEEE80211_TX_RC_VHT_MCS) {
+			p += sprintf(p, "  MCS%-1u/%1u", j, mg->streams);
 		} else {
-			p += sprintf(p, " MCS%-2u", (mg->streams - 1) * 8 + j);
+			int r = bitrates[j % 4];
+
+			p += sprintf(p, "   %2u.%1uM", r / 10, r % 10);
 		}
 
-		tp = mr->cur_tp / 10;
-		prob = MINSTREL_TRUNC(mr->cur_prob * 1000);
-		eprob = MINSTREL_TRUNC(mr->probability * 1000);
+		p += sprintf(p, "  %3u  ", idx);
 
-		p += sprintf(p, " %4u.%1u %3u.%1u %3u.%1u "
-				"%3u %4u(%4u) %9llu(%9llu)\n",
-				tp / 10, tp % 10,
+		/* tx_time[rate(i)] in usec */
+		tx_time = DIV_ROUND_CLOSEST(mg->duration[j], 1000);
+		p += sprintf(p, "%6u  ", tx_time);
+
+		tp_max = minstrel_ht_get_tp_avg(mi, i, j, MINSTREL_FRAC(100, 100));
+		tp_avg = minstrel_ht_get_tp_avg(mi, i, j, mrs->prob_ewma);
+		prob = MINSTREL_TRUNC(mrs->cur_prob * 1000);
+		eprob = MINSTREL_TRUNC(mrs->prob_ewma * 1000);
+
+		p += sprintf(p, "%4u.%1u   %4u.%1u   %3u.%1u    %3u.%1u"
+				"     %3u.%1u %3u   %3u %-3u   "
+				"%9llu   %-9llu\n",
+				tp_max / 10, tp_max % 10,
+				tp_avg / 10, tp_avg % 10,
 				eprob / 10, eprob % 10,
+				mrs->prob_ewmsd / 10, mrs->prob_ewmsd % 10,
 				prob / 10, prob % 10,
-				mr->retry_count,
-				mr->last_success,
-				mr->last_attempts,
-				(unsigned long long)mr->succ_hist,
-				(unsigned long long)mr->att_hist);
+				mrs->retry_count,
+				mrs->last_success,
+				mrs->last_attempts,
+				(unsigned long long)mrs->succ_hist,
+				(unsigned long long)mrs->att_hist);
 	}
 
 	return p;
@@ -85,9 +111,8 @@ minstrel_ht_stats_open(struct inode *inode, struct file *file)
 	struct minstrel_ht_sta *mi = &msp->ht;
 	struct minstrel_debugfs_info *ms;
 	unsigned int i;
-	unsigned int max_mcs = MINSTREL_MAX_STREAMS * MINSTREL_STREAM_GROUPS;
-	char *p;
 	int ret;
+	char *p;
 
 	if (!msp->is_ht) {
 		inode->i_private = &msp->legacy;
@@ -96,30 +121,36 @@ minstrel_ht_stats_open(struct inode *inode, struct file *file)
 		return ret;
 	}
 
-	ms = kmalloc(8192, GFP_KERNEL);
+	ms = kmalloc(32768, GFP_KERNEL);
 	if (!ms)
 		return -ENOMEM;
 
 	file->private_data = ms;
 	p = ms->buf;
-	p += sprintf(p, "type           rate     tpt eprob *prob "
-			"ret  *ok(*cum)        ok(      cum)\n");
 
+	p += sprintf(p, "\n");
+	p += sprintf(p, "              best   ____________rate__________    "
+			"______statistics______    ________last_______    "
+			"______sum-of________\n");
+	p += sprintf(p, "mode guard #  rate  [name   idx airtime  max_tp]  "
+			"[ ø(tp) ø(prob) sd(prob)]  [prob.|retry|suc|att]  [#success | "
+			"#attempts]\n");
 
-	p = minstrel_ht_stats_dump(mi, max_mcs, p);
-	for (i = 0; i < max_mcs; i++)
+	p = minstrel_ht_stats_dump(mi, MINSTREL_CCK_GROUP, p);
+	for (i = 0; i < MINSTREL_CCK_GROUP; i++)
+		p = minstrel_ht_stats_dump(mi, i, p);
+	for (i++; i < ARRAY_SIZE(mi->groups); i++)
 		p = minstrel_ht_stats_dump(mi, i, p);
 
 	p += sprintf(p, "\nTotal packet count::    ideal %d      "
 			"lookaround %d\n",
 			max(0, (int) mi->total_packets - (int) mi->sample_packets),
 			mi->sample_packets);
-	p += sprintf(p, "Average A-MPDU length: %d.%d\n",
+	p += sprintf(p, "Average # of aggregated frames per A-MPDU: %d.%d\n",
 		MINSTREL_TRUNC(mi->avg_ampdu_len),
 		MINSTREL_TRUNC(mi->avg_ampdu_len * 10) % 10);
 	ms->len = p - ms->buf;
-
-	WARN_ON(ms->len + sizeof(*ms) > 8192);
+	WARN_ON(ms->len + sizeof(*ms) > 32768);
 
 	return nonseekable_open(inode, file);
 }
@@ -132,6 +163,143 @@ static const struct file_operations minstrel_ht_stat_fops = {
 	.llseek = no_llseek,
 };
 
+static char *
+minstrel_ht_stats_csv_dump(struct minstrel_ht_sta *mi, int i, char *p)
+{
+	const struct mcs_group *mg;
+	unsigned int j, tp_max, tp_avg, prob, eprob, tx_time;
+	char htmode = '2';
+	char gimode = 'L';
+	u32 gflags;
+
+	if (!mi->groups[i].supported)
+		return p;
+
+	mg = &minstrel_mcs_groups[i];
+	gflags = mg->flags;
+
+	if (gflags & IEEE80211_TX_RC_40_MHZ_WIDTH)
+		htmode = '4';
+	else if (gflags & IEEE80211_TX_RC_80_MHZ_WIDTH)
+		htmode = '8';
+	if (gflags & IEEE80211_TX_RC_SHORT_GI)
+		gimode = 'S';
+
+	for (j = 0; j < MCS_GROUP_RATES; j++) {
+		struct minstrel_rate_stats *mrs = &mi->groups[i].rates[j];
+		static const int bitrates[4] = { 10, 20, 55, 110 };
+		int idx = i * MCS_GROUP_RATES + j;
+
+		if (!(mi->groups[i].supported & BIT(j)))
+			continue;
+
+		if (gflags & IEEE80211_TX_RC_MCS) {
+			p += sprintf(p, "HT%c0,", htmode);
+			p += sprintf(p, "%cGI,", gimode);
+			p += sprintf(p, "%d,", mg->streams);
+		} else if (gflags & IEEE80211_TX_RC_VHT_MCS) {
+			p += sprintf(p, "VHT%c0,", htmode);
+			p += sprintf(p, "%cGI,", gimode);
+			p += sprintf(p, "%d,", mg->streams);
+		} else {
+			p += sprintf(p, "CCK,");
+			p += sprintf(p, "%cP,", j < 4 ? 'L' : 'S');
+			p += sprintf(p, "1,");
+		}
+
+		p += sprintf(p, "%s" ,((idx == mi->max_tp_rate[0]) ? "A" : ""));
+		p += sprintf(p, "%s" ,((idx == mi->max_tp_rate[1]) ? "B" : ""));
+		p += sprintf(p, "%s" ,((idx == mi->max_tp_rate[2]) ? "C" : ""));
+		p += sprintf(p, "%s" ,((idx == mi->max_tp_rate[3]) ? "D" : ""));
+		p += sprintf(p, "%s" ,((idx == mi->max_prob_rate) ? "P" : ""));
+
+		if (gflags & IEEE80211_TX_RC_MCS) {
+			p += sprintf(p, ",MCS%-2u,", (mg->streams - 1) * 8 + j);
+		} else if (gflags & IEEE80211_TX_RC_VHT_MCS) {
+			p += sprintf(p, ",MCS%-1u/%1u,", j, mg->streams);
+		} else {
+			int r = bitrates[j % 4];
+			p += sprintf(p, ",%2u.%1uM,", r / 10, r % 10);
+		}
+
+		p += sprintf(p, "%u,", idx);
+		tx_time = DIV_ROUND_CLOSEST(mg->duration[j], 1000);
+		p += sprintf(p, "%u,", tx_time);
+
+		tp_max = minstrel_ht_get_tp_avg(mi, i, j, MINSTREL_FRAC(100, 100));
+		tp_avg = minstrel_ht_get_tp_avg(mi, i, j, mrs->prob_ewma);
+		prob = MINSTREL_TRUNC(mrs->cur_prob * 1000);
+		eprob = MINSTREL_TRUNC(mrs->prob_ewma * 1000);
+
+		p += sprintf(p, "%u.%u,%u.%u,%u.%u,%u.%u,%u.%u,%u,%u,"
+				"%u,%llu,%llu,",
+				tp_max / 10, tp_max % 10,
+				tp_avg / 10, tp_avg % 10,
+				eprob / 10, eprob % 10,
+				mrs->prob_ewmsd / 10, mrs->prob_ewmsd % 10,
+				prob / 10, prob % 10,
+				mrs->retry_count,
+				mrs->last_success,
+				mrs->last_attempts,
+				(unsigned long long)mrs->succ_hist,
+				(unsigned long long)mrs->att_hist);
+		p += sprintf(p, "%d,%d,%d.%d\n",
+				max(0, (int) mi->total_packets -
+				(int) mi->sample_packets),
+				mi->sample_packets,
+				MINSTREL_TRUNC(mi->avg_ampdu_len),
+				MINSTREL_TRUNC(mi->avg_ampdu_len * 10) % 10);
+	}
+
+	return p;
+}
+
+static int
+minstrel_ht_stats_csv_open(struct inode *inode, struct file *file)
+{
+	struct minstrel_ht_sta_priv *msp = inode->i_private;
+	struct minstrel_ht_sta *mi = &msp->ht;
+	struct minstrel_debugfs_info *ms;
+	unsigned int i;
+	int ret;
+	char *p;
+
+	if (!msp->is_ht) {
+		inode->i_private = &msp->legacy;
+		ret = minstrel_stats_csv_open(inode, file);
+		inode->i_private = msp;
+		return ret;
+	}
+
+	ms = kmalloc(32768, GFP_KERNEL);
+
+	if (!ms)
+		return -ENOMEM;
+
+	file->private_data = ms;
+
+	p = ms->buf;
+
+	p = minstrel_ht_stats_csv_dump(mi, MINSTREL_CCK_GROUP, p);
+	for (i = 0; i < MINSTREL_CCK_GROUP; i++)
+		p = minstrel_ht_stats_csv_dump(mi, i, p);
+	for (i++; i < ARRAY_SIZE(mi->groups); i++)
+		p = minstrel_ht_stats_csv_dump(mi, i, p);
+
+	ms->len = p - ms->buf;
+	WARN_ON(ms->len + sizeof(*ms) > 32768);
+
+	return nonseekable_open(inode, file);
+}
+
+static const struct file_operations minstrel_ht_stat_csv_fops = {
+	.owner = THIS_MODULE,
+	.open = minstrel_ht_stats_csv_open,
+	.read = minstrel_stats_read,
+	.release = minstrel_stats_release,
+	.llseek = no_llseek,
+};
+
 void
 minstrel_ht_add_sta_debugfs(void *priv, void *priv_sta, struct dentry *dir)
 {
@@ -139,6 +307,8 @@ minstrel_ht_add_sta_debugfs(void *priv, void *priv_sta, struct dentry *dir)
 
 	msp->dbg_stats = debugfs_create_file("rc_stats", S_IRUGO, dir, msp,
 			&minstrel_ht_stat_fops);
+	msp->dbg_stats_csv = debugfs_create_file("rc_stats_csv", S_IRUGO,
+			     dir, msp, &minstrel_ht_stat_csv_fops);
 }
 
 void
@@ -147,4 +317,5 @@ minstrel_ht_remove_sta_debugfs(void *priv, void *priv_sta)
 	struct minstrel_ht_sta_priv *msp = priv_sta;
 
 	debugfs_remove(msp->dbg_stats);
+	debugfs_remove(msp->dbg_stats_csv);
 }
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index a37f9af634cb..5793f75c5ffd 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -39,7 +39,8 @@
  * only useful for monitoring.
  */
 static struct sk_buff *remove_monitor_info(struct ieee80211_local *local,
-					   struct sk_buff *skb)
+					   struct sk_buff *skb,
+					   unsigned int rtap_vendor_space)
 {
 	if (local->hw.flags & IEEE80211_HW_RX_INCLUDES_FCS) {
 		if (likely(skb->len > FCS_LEN))
@@ -52,20 +53,25 @@ static struct sk_buff *remove_monitor_info(struct ieee80211_local *local,
 		}
 	}
 
+	__pskb_pull(skb, rtap_vendor_space);
+
 	return skb;
 }
 
-static inline bool 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,
+				     unsigned int rtap_vendor_space)
 {
 	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
-	struct ieee80211_hdr *hdr = (void *)skb->data;
+	struct ieee80211_hdr *hdr;
+
+	hdr = (void *)(skb->data + rtap_vendor_space);
 
 	if (status->flag & (RX_FLAG_FAILED_FCS_CRC |
 			    RX_FLAG_FAILED_PLCP_CRC |
 			    RX_FLAG_AMPDU_IS_ZEROLEN))
 		return true;
 
-	if (unlikely(skb->len < 16 + present_fcs_len))
+	if (unlikely(skb->len < 16 + present_fcs_len + rtap_vendor_space))
 		return true;
 
 	if (ieee80211_is_ctl(hdr->frame_control) &&
@@ -77,8 +83,9 @@ static inline bool should_drop_frame(struct sk_buff *skb, int present_fcs_len)
 }
 
 static int
-ieee80211_rx_radiotap_space(struct ieee80211_local *local,
-			    struct ieee80211_rx_status *status)
+ieee80211_rx_radiotap_hdrlen(struct ieee80211_local *local,
+			     struct ieee80211_rx_status *status,
+			     struct sk_buff *skb)
 {
 	int len;
 
@@ -121,6 +128,21 @@ ieee80211_rx_radiotap_space(struct ieee80211_local *local,
 		len += 2 * hweight8(status->chains);
 	}
 
+	if (status->flag & RX_FLAG_RADIOTAP_VENDOR_DATA) {
+		struct ieee80211_vendor_radiotap *rtap = (void *)skb->data;
+
+		/* vendor presence bitmap */
+		len += 4;
+		/* alignment for fixed 6-byte vendor data header */
+		len = ALIGN(len, 2);
+		/* vendor data header */
+		len += 6;
+		if (WARN_ON(rtap->align == 0))
+			rtap->align = 1;
+		len = ALIGN(len, rtap->align);
+		len += rtap->len + rtap->pad;
+	}
+
 	return len;
 }
 
@@ -144,13 +166,20 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 	u16 channel_flags = 0;
 	int mpdulen, chain;
 	unsigned long chains = status->chains;
+	struct ieee80211_vendor_radiotap rtap = {};
+
+	if (status->flag & RX_FLAG_RADIOTAP_VENDOR_DATA) {
+		rtap = *(struct ieee80211_vendor_radiotap *)skb->data;
+		/* rtap.len and rtap.pad are undone immediately */
+		skb_pull(skb, sizeof(rtap) + rtap.len + rtap.pad);
+	}
 
 	mpdulen = skb->len;
 	if (!(has_fcs && (local->hw.flags & IEEE80211_HW_RX_INCLUDES_FCS)))
 		mpdulen += FCS_LEN;
 
 	rthdr = (struct ieee80211_radiotap_header *)skb_push(skb, rtap_len);
-	memset(rthdr, 0, rtap_len);
+	memset(rthdr, 0, rtap_len - rtap.len - rtap.pad);
 	it_present = &rthdr->it_present;
 
 	/* radiotap header, set always present flags */
@@ -172,6 +201,14 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 				 BIT(IEEE80211_RADIOTAP_DBM_ANTSIGNAL);
 	}
 
+	if (status->flag & RX_FLAG_RADIOTAP_VENDOR_DATA) {
+		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 = rtap.present;
+	}
+
 	put_unaligned_le32(it_present_val, it_present);
 
 	pos = (void *)(it_present + 1);
@@ -235,7 +272,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 	else if (rate && rate->flags & IEEE80211_RATE_ERP_G)
 		channel_flags |= IEEE80211_CHAN_OFDM | IEEE80211_CHAN_2GHZ;
 	else if (rate)
-		channel_flags |= IEEE80211_CHAN_OFDM | IEEE80211_CHAN_2GHZ;
+		channel_flags |= IEEE80211_CHAN_CCK | IEEE80211_CHAN_2GHZ;
 	else
 		channel_flags |= IEEE80211_CHAN_2GHZ;
 	put_unaligned_le16(channel_flags, pos);
@@ -324,9 +361,6 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 		u16 known = local->hw.radiotap_vht_details;
 
 		rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_VHT);
-		/* known field - how to handle 80+80? */
-		if (status->vht_flag & RX_VHT_FLAG_80P80MHZ)
-			known &= ~IEEE80211_RADIOTAP_VHT_KNOWN_BANDWIDTH;
 		put_unaligned_le16(known, pos);
 		pos += 2;
 		/* flags */
@@ -341,8 +375,6 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 		/* bandwidth */
 		if (status->vht_flag & RX_VHT_FLAG_80MHZ)
 			*pos++ = 4;
-		else if (status->vht_flag & RX_VHT_FLAG_80P80MHZ)
-			*pos++ = 0; /* marked not known above */
 		else if (status->vht_flag & RX_VHT_FLAG_160MHZ)
 			*pos++ = 11;
 		else if (status->flag & RX_FLAG_40MHZ)
@@ -366,6 +398,22 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 		*pos++ = status->chain_signal[chain];
 		*pos++ = chain;
 	}
+
+	if (status->flag & RX_FLAG_RADIOTAP_VENDOR_DATA) {
+		/* ensure 2 byte alignment for the vendor field as required */
+		if ((pos - (u8 *)rthdr) & 1)
+			*pos++ = 0;
+		*pos++ = rtap.oui[0];
+		*pos++ = rtap.oui[1];
+		*pos++ = rtap.oui[2];
+		*pos++ = rtap.subns;
+		put_unaligned_le16(rtap.len, pos);
+		pos += 2;
+		/* align the actual payload as requested */
+		while ((pos - (u8 *)rthdr) & (rtap.align - 1))
+			*pos++ = 0;
+		/* data (and possible padding) already follows */
+	}
 }
 
 /*
@@ -379,10 +427,17 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb,
 {
 	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(origskb);
 	struct ieee80211_sub_if_data *sdata;
-	int needed_headroom;
+	int rt_hdrlen, needed_headroom;
 	struct sk_buff *skb, *skb2;
 	struct net_device *prev_dev = NULL;
 	int present_fcs_len = 0;
+	unsigned int rtap_vendor_space = 0;
+
+	if (unlikely(status->flag & RX_FLAG_RADIOTAP_VENDOR_DATA)) {
+		struct ieee80211_vendor_radiotap *rtap = (void *)origskb->data;
+
+		rtap_vendor_space = sizeof(*rtap) + rtap->len + rtap->pad;
+	}
 
 	/*
 	 * First, we may need to make a copy of the skb because
@@ -396,25 +451,27 @@ 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 is in skb head */
-	if (!pskb_may_pull(origskb, 2)) {
+	/* ensure hdr->frame_control and vendor radiotap data are in skb head */
+	if (!pskb_may_pull(origskb, 2 + rtap_vendor_space)) {
 		dev_kfree_skb(origskb);
 		return NULL;
 	}
 
 	if (!local->monitors) {
-		if (should_drop_frame(origskb, present_fcs_len)) {
+		if (should_drop_frame(origskb, present_fcs_len,
+				      rtap_vendor_space)) {
 			dev_kfree_skb(origskb);
 			return NULL;
 		}
 
-		return remove_monitor_info(local, origskb);
+		return remove_monitor_info(local, origskb, rtap_vendor_space);
 	}
 
 	/* room for the radiotap header based on driver features */
-	needed_headroom = ieee80211_rx_radiotap_space(local, status);
+	rt_hdrlen = ieee80211_rx_radiotap_hdrlen(local, status, origskb);
+	needed_headroom = rt_hdrlen - rtap_vendor_space;
 
-	if (should_drop_frame(origskb, present_fcs_len)) {
+	if (should_drop_frame(origskb, present_fcs_len, rtap_vendor_space)) {
 		/* only need to expand headroom if necessary */
 		skb = origskb;
 		origskb = NULL;
@@ -438,15 +495,15 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb,
 		 */
 		skb = skb_copy_expand(origskb, needed_headroom, 0, GFP_ATOMIC);
 
-		origskb = remove_monitor_info(local, origskb);
+		origskb = remove_monitor_info(local, origskb,
+					      rtap_vendor_space);
 
 		if (!skb)
 			return origskb;
 	}
 
 	/* prepend radiotap information */
-	ieee80211_add_rx_radiotap_header(local, skb, rate, needed_headroom,
-					 true);
+	ieee80211_add_rx_radiotap_header(local, skb, rate, rt_hdrlen, true);
 
 	skb_reset_mac_header(skb);
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -590,6 +647,7 @@ static int ieee80211_get_mmie_keyidx(struct sk_buff *skb)
 {
 	struct ieee80211_mgmt *hdr = (struct ieee80211_mgmt *) skb->data;
 	struct ieee80211_mmie *mmie;
+	struct ieee80211_mmie_16 *mmie16;
 
 	if (skb->len < 24 + sizeof(*mmie) || !is_multicast_ether_addr(hdr->da))
 		return -1;
@@ -599,11 +657,18 @@ static int ieee80211_get_mmie_keyidx(struct sk_buff *skb)
 
 	mmie = (struct ieee80211_mmie *)
 		(skb->data + skb->len - sizeof(*mmie));
-	if (mmie->element_id != WLAN_EID_MMIE ||
-	    mmie->length != sizeof(*mmie) - 2)
-		return -1;
-
-	return le16_to_cpu(mmie->key_id);
+	if (mmie->element_id == WLAN_EID_MMIE &&
+	    mmie->length == sizeof(*mmie) - 2)
+		return le16_to_cpu(mmie->key_id);
+
+	mmie16 = (struct ieee80211_mmie_16 *)
+		(skb->data + skb->len - sizeof(*mmie16));
+	if (skb->len >= 24 + sizeof(*mmie16) &&
+	    mmie16->element_id == WLAN_EID_MMIE &&
+	    mmie16->length == sizeof(*mmie16) - 2)
+		return le16_to_cpu(mmie16->key_id);
+
+	return -1;
 }
 
 static int iwl80211_get_cs_keyid(const struct ieee80211_cipher_scheme *cs,
@@ -808,9 +873,10 @@ static void ieee80211_sta_reorder_release(struct ieee80211_sub_if_data *sdata,
 
  set_release_timer:
 
-		mod_timer(&tid_agg_rx->reorder_timer,
-			  tid_agg_rx->reorder_time[j] + 1 +
-			  HT_RX_REORDER_BUF_TIMEOUT);
+		if (!tid_agg_rx->removed)
+			mod_timer(&tid_agg_rx->reorder_timer,
+				  tid_agg_rx->reorder_time[j] + 1 +
+				  HT_RX_REORDER_BUF_TIMEOUT);
 	} else {
 		del_timer(&tid_agg_rx->reorder_timer);
 	}
@@ -985,7 +1051,7 @@ static void ieee80211_rx_reorder_ampdu(struct ieee80211_rx_data *rx,
 }
 
 static ieee80211_rx_result debug_noinline
-ieee80211_rx_h_check(struct ieee80211_rx_data *rx)
+ieee80211_rx_h_check_dup(struct ieee80211_rx_data *rx)
 {
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data;
 	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb);
@@ -994,10 +1060,16 @@ ieee80211_rx_h_check(struct ieee80211_rx_data *rx)
 	 * Drop duplicate 802.11 retransmissions
 	 * (IEEE 802.11-2012: 9.3.2.10 "Duplicate detection and recovery")
 	 */
-	if (rx->skb->len >= 24 && rx->sta &&
-	    !ieee80211_is_ctl(hdr->frame_control) &&
-	    !ieee80211_is_qos_nullfunc(hdr->frame_control) &&
-	    !is_multicast_ether_addr(hdr->addr1)) {
+
+	if (rx->skb->len < 24)
+		return RX_CONTINUE;
+
+	if (ieee80211_is_ctl(hdr->frame_control) ||
+	    ieee80211_is_qos_nullfunc(hdr->frame_control) ||
+	    is_multicast_ether_addr(hdr->addr1))
+		return RX_CONTINUE;
+
+	if (rx->sta) {
 		if (unlikely(ieee80211_has_retry(hdr->frame_control) &&
 			     rx->sta->last_seq_ctrl[rx->seqno_idx] ==
 			     hdr->seq_ctrl)) {
@@ -1011,6 +1083,14 @@ ieee80211_rx_h_check(struct ieee80211_rx_data *rx)
 		}
 	}
 
+	return RX_CONTINUE;
+}
+
+static ieee80211_rx_result debug_noinline
+ieee80211_rx_h_check(struct ieee80211_rx_data *rx)
+{
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data;
+
 	if (unlikely(rx->skb->len < 16)) {
 		I802_DEBUG_INC(rx->local->rx_handlers_drop_short);
 		return RX_DROP_MONITOR;
@@ -1032,6 +1112,7 @@ ieee80211_rx_h_check(struct ieee80211_rx_data *rx)
 		      ieee80211_is_pspoll(hdr->frame_control)) &&
 		     rx->sdata->vif.type != NL80211_IFTYPE_ADHOC &&
 		     rx->sdata->vif.type != NL80211_IFTYPE_WDS &&
+		     rx->sdata->vif.type != NL80211_IFTYPE_OCB &&
 		     (!rx->sta || !test_sta_flag(rx->sta, WLAN_STA_ASSOC)))) {
 		/*
 		 * accept port control frames from the AP even when it's not
@@ -1104,6 +1185,7 @@ static void sta_ps_start(struct sta_info *sta)
 	struct ieee80211_sub_if_data *sdata = sta->sdata;
 	struct ieee80211_local *local = sdata->local;
 	struct ps_data *ps;
+	int tid;
 
 	if (sta->sdata->vif.type == NL80211_IFTYPE_AP ||
 	    sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
@@ -1117,6 +1199,18 @@ static void sta_ps_start(struct sta_info *sta)
 		drv_sta_notify(local, sdata, STA_NOTIFY_SLEEP, &sta->sta);
 	ps_dbg(sdata, "STA %pM aid %d enters power save mode\n",
 	       sta->sta.addr, sta->sta.aid);
+
+	if (!sta->sta.txq[0])
+		return;
+
+	for (tid = 0; tid < ARRAY_SIZE(sta->sta.txq); tid++) {
+		struct txq_info *txqi = to_txq_info(sta->sta.txq[tid]);
+
+		if (!skb_queue_len(&txqi->queue))
+			set_bit(tid, &sta->txq_buffered_tids);
+		else
+			clear_bit(tid, &sta->txq_buffered_tids);
+	}
 }
 
 static void sta_ps_end(struct sta_info *sta)
@@ -1272,6 +1366,12 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx)
 				sta->last_rx_rate_vht_nss = status->vht_nss;
 			}
 		}
+	} else if (rx->sdata->vif.type == NL80211_IFTYPE_OCB) {
+		u8 *bssid = ieee80211_get_bssid(hdr, rx->skb->len,
+						NL80211_IFTYPE_OCB);
+		/* OCB uses wild-card BSSID */
+		if (is_broadcast_ether_addr(bssid))
+			sta->last_rx = jiffies;
 	} else if (!is_multicast_ether_addr(hdr->addr1)) {
 		/*
 		 * Mesh beacons will update last_rx when if they are found to
@@ -1572,11 +1672,27 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx)
 		result = ieee80211_crypto_tkip_decrypt(rx);
 		break;
 	case WLAN_CIPHER_SUITE_CCMP:
-		result = ieee80211_crypto_ccmp_decrypt(rx);
+		result = ieee80211_crypto_ccmp_decrypt(
+			rx, IEEE80211_CCMP_MIC_LEN);
+		break;
+	case WLAN_CIPHER_SUITE_CCMP_256:
+		result = ieee80211_crypto_ccmp_decrypt(
+			rx, IEEE80211_CCMP_256_MIC_LEN);
 		break;
 	case WLAN_CIPHER_SUITE_AES_CMAC:
 		result = ieee80211_crypto_aes_cmac_decrypt(rx);
 		break;
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
+		result = ieee80211_crypto_aes_cmac_256_decrypt(rx);
+		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		result = ieee80211_crypto_aes_gmac_decrypt(rx);
+		break;
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		result = ieee80211_crypto_gcmp_decrypt(rx);
+		break;
 	default:
 		result = ieee80211_crypto_hw_decrypt(rx);
 	}
@@ -1678,14 +1794,14 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx)
 	sc = le16_to_cpu(hdr->seq_ctrl);
 	frag = sc & IEEE80211_SCTL_FRAG;
 
-	if (likely(!ieee80211_has_morefrags(fc) && frag == 0))
-		goto out;
-
 	if (is_multicast_ether_addr(hdr->addr1)) {
 		rx->local->dot11MulticastReceivedFrameCount++;
-		goto out;
+		goto out_no_led;
 	}
 
+	if (likely(!ieee80211_has_morefrags(fc) && frag == 0))
+		goto out;
+
 	I802_DEBUG_INC(rx->local->rx_handlers_fragments);
 
 	if (skb_linearize(rx->skb))
@@ -1703,7 +1819,9 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx)
 		/* This is the first fragment of a new frame. */
 		entry = ieee80211_reassemble_add(rx->sdata, frag, seq,
 						 rx->seqno_idx, &(rx->skb));
-		if (rx->key && rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP &&
+		if (rx->key &&
+		    (rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP ||
+		     rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP_256) &&
 		    ieee80211_has_protected(fc)) {
 			int queue = rx->security_idx;
 			/* Store CCMP PN so that we can verify that the next
@@ -1732,7 +1850,9 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx)
 		int i;
 		u8 pn[IEEE80211_CCMP_PN_LEN], *rpn;
 		int queue;
-		if (!rx->key || rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP)
+		if (!rx->key ||
+		    (rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP &&
+		     rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP_256))
 			return RX_DROP_UNUSABLE;
 		memcpy(pn, entry->last_pn, IEEE80211_CCMP_PN_LEN);
 		for (i = IEEE80211_CCMP_PN_LEN - 1; i >= 0; i--) {
@@ -1776,9 +1896,10 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx)
 	status->rx_flags |= IEEE80211_RX_FRAGMENTED;
 
  out:
+	ieee80211_led_rx(rx->local);
+ out_no_led:
 	if (rx->sta)
 		rx->sta->rx_packets++;
-	ieee80211_led_rx(rx->local);
 	return RX_CONTINUE;
 }
 
@@ -1805,8 +1926,7 @@ static int ieee80211_drop_unencrypted(struct ieee80211_rx_data *rx, __le16 fc)
 	/* Drop unencrypted frames if key is set. */
 	if (unlikely(!ieee80211_has_protected(fc) &&
 		     !ieee80211_is_nullfunc(fc) &&
-		     ieee80211_is_data(fc) &&
-		     (rx->key || rx->sdata->drop_unencrypted)))
+		     ieee80211_is_data(fc) && rx->key))
 		return -EACCES;
 
 	return 0;
@@ -1936,6 +2056,9 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx)
 	struct sta_info *dsta;
 	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb);
 
+	dev->stats.rx_packets++;
+	dev->stats.rx_bytes += rx->skb->len;
+
 	skb = rx->skb;
 	xmit_skb = NULL;
 
@@ -1998,7 +2121,8 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx)
 		/* deliver to local stack */
 		skb->protocol = eth_type_trans(skb, dev);
 		memset(skb->cb, 0, sizeof(skb->cb));
-		if (rx->local->napi)
+		if (!(rx->flags & IEEE80211_RX_REORDER_TIMER) &&
+		    rx->local->napi)
 			napi_gro_receive(rx->local->napi, skb);
 		else
 			netif_receive_skb(skb);
@@ -2066,8 +2190,6 @@ ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx)
 			dev_kfree_skb(rx->skb);
 			continue;
 		}
-		dev->stats.rx_packets++;
-		dev->stats.rx_bytes += rx->skb->len;
 
 		ieee80211_deliver_skb(rx);
 	}
@@ -2107,6 +2229,9 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx)
 	hdr = (struct ieee80211_hdr *) skb->data;
 	mesh_hdr = (struct ieee80211s_hdr *) (skb->data + hdrlen);
 
+	if (ieee80211_drop_unencrypted(rx, hdr->frame_control))
+		return RX_DROP_MONITOR;
+
 	/* frame is in RMC, don't forward */
 	if (ieee80211_is_data(hdr->frame_control) &&
 	    is_multicast_ether_addr(hdr->addr1) &&
@@ -2230,6 +2355,15 @@ ieee80211_rx_h_data(struct ieee80211_rx_data *rx)
 	if (unlikely(!ieee80211_is_data_present(hdr->frame_control)))
 		return RX_DROP_MONITOR;
 
+	if (rx->sta) {
+		/* The seqno index has the same property as needed
+		 * for the rx_msdu field, i.e. it is IEEE80211_NUM_TIDS
+		 * for non-QoS-data frames. Here we know it's a data
+		 * frame, so count MSDUs.
+		 */
+		rx->sta->rx_msdu[rx->seqno_idx]++;
+	}
+
 	/*
 	 * Send unexpected-4addr-frame event to hostapd. For older versions,
 	 * also drop the frame to cooked monitor interfaces.
@@ -2250,6 +2384,27 @@ ieee80211_rx_h_data(struct ieee80211_rx_data *rx)
 	if (!ieee80211_frame_allowed(rx, fc))
 		return RX_DROP_MONITOR;
 
+	/* directly handle TDLS channel switch requests/responses */
+	if (unlikely(((struct ethhdr *)rx->skb->data)->h_proto ==
+						cpu_to_be16(ETH_P_TDLS))) {
+		struct ieee80211_tdls_data *tf = (void *)rx->skb->data;
+
+		if (pskb_may_pull(rx->skb,
+				  offsetof(struct ieee80211_tdls_data, u)) &&
+		    tf->payload_type == WLAN_TDLS_SNAP_RFTYPE &&
+		    tf->category == WLAN_CATEGORY_TDLS &&
+		    (tf->action_code == WLAN_TDLS_CHANNEL_SWITCH_REQUEST ||
+		     tf->action_code == WLAN_TDLS_CHANNEL_SWITCH_RESPONSE)) {
+			rx->skb->pkt_type = IEEE80211_SDATA_QUEUE_TDLS_CHSW;
+			skb_queue_tail(&sdata->skb_queue, rx->skb);
+			ieee80211_queue_work(&rx->local->hw, &sdata->work);
+			if (rx->sta)
+				rx->sta->rx_packets++;
+
+			return RX_QUEUED;
+		}
+	}
+
 	if (rx->sdata->vif.type == NL80211_IFTYPE_AP_VLAN &&
 	    unlikely(port_control) && sdata->bss) {
 		sdata = container_of(sdata->bss, struct ieee80211_sub_if_data,
@@ -2260,9 +2415,6 @@ ieee80211_rx_h_data(struct ieee80211_rx_data *rx)
 
 	rx->skb->dev = dev;
 
-	dev->stats.rx_packets++;
-	dev->stats.rx_bytes += rx->skb->len;
-
 	if (local->ps_sdata && local->hw.conf.dynamic_ps_timeout > 0 &&
 	    !is_multicast_ether_addr(
 		    ((struct ethhdr *)rx->skb->data)->h_dest) &&
@@ -2493,7 +2645,7 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx)
 		case WLAN_HT_ACTION_NOTIFY_CHANWIDTH: {
 			struct ieee80211_supported_band *sband;
 			u8 chanwidth = mgmt->u.action.u.ht_notify_cw.chanwidth;
-			enum ieee80211_sta_rx_bandwidth new_bw;
+			enum ieee80211_sta_rx_bandwidth max_bw, new_bw;
 
 			/* If it doesn't support 40 MHz it can't change ... */
 			if (!(rx->sta->sta.ht_cap.cap &
@@ -2501,13 +2653,18 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx)
 				goto handled;
 
 			if (chanwidth == IEEE80211_HT_CHANWIDTH_20MHZ)
-				new_bw = IEEE80211_STA_RX_BW_20;
+				max_bw = IEEE80211_STA_RX_BW_20;
 			else
-				new_bw = ieee80211_sta_cur_vht_bw(rx->sta);
+				max_bw = ieee80211_sta_cap_rx_bw(rx->sta);
+
+			/* set cur_max_bandwidth and recalc sta bw */
+			rx->sta->cur_max_bandwidth = max_bw;
+			new_bw = ieee80211_sta_cur_vht_bw(rx->sta);
 
 			if (rx->sta->sta.bandwidth == new_bw)
 				goto handled;
 
+			rx->sta->sta.bandwidth = new_bw;
 			sband = rx->local->hw.wiphy->bands[status->band];
 
 			rate_control_rate_update(local, sband, rx->sta,
@@ -2820,6 +2977,7 @@ ieee80211_rx_h_mgmt(struct ieee80211_rx_data *rx)
 
 	if (!ieee80211_vif_is_mesh(&sdata->vif) &&
 	    sdata->vif.type != NL80211_IFTYPE_ADHOC &&
+	    sdata->vif.type != NL80211_IFTYPE_OCB &&
 	    sdata->vif.type != NL80211_IFTYPE_STATION)
 		return RX_DROP_MONITOR;
 
@@ -2884,8 +3042,10 @@ static void ieee80211_rx_cooked_monitor(struct ieee80211_rx_data *rx,
 	if (!local->cooked_mntrs)
 		goto out_free_skb;
 
+	/* vendor data is long removed here */
+	status->flag &= ~RX_FLAG_RADIOTAP_VENDOR_DATA;
 	/* room for the radiotap header based on driver features */
-	needed_headroom = ieee80211_rx_radiotap_space(local, status);
+	needed_headroom = ieee80211_rx_radiotap_hdrlen(local, status, skb);
 
 	if (skb_headroom(skb) < needed_headroom &&
 	    pskb_expand_head(skb, needed_headroom, 0, GFP_ATOMIC))
@@ -2980,6 +3140,12 @@ static void ieee80211_rx_handlers(struct ieee80211_rx_data *rx,
 			goto rxh_next;  \
 	} while (0);
 
+	/* Lock here to avoid hitting all of the data used in the RX
+	 * path (e.g. key data, station data, ...) concurrently when
+	 * a frame is released from the reorder buffer due to timeout
+	 * from the timer, potentially concurrently with RX from the
+	 * driver.
+	 */
 	spin_lock_bh(&rx->local->rx_path_lock);
 
 	while ((skb = __skb_dequeue(frames))) {
@@ -3038,6 +3204,7 @@ static void ieee80211_invoke_rx_handlers(struct ieee80211_rx_data *rx)
 			goto rxh_next;  \
 	} while (0);
 
+	CALL_RXH(ieee80211_rx_h_check_dup)
 	CALL_RXH(ieee80211_rx_h_check)
 
 	ieee80211_rx_reorder_ampdu(rx, &reorder_release);
@@ -3065,7 +3232,7 @@ void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid)
 		/* This is OK -- must be QoS data frame */
 		.security_idx = tid,
 		.seqno_idx = tid,
-		.flags = 0,
+		.flags = IEEE80211_RX_REORDER_TIMER,
 	};
 	struct tid_ampdu_rx *tid_agg_rx;
 
@@ -3130,6 +3297,33 @@ static bool prepare_for_handlers(struct ieee80211_rx_data *rx,
 						 BIT(rate_idx));
 		}
 		break;
+	case NL80211_IFTYPE_OCB:
+		if (!bssid)
+			return false;
+		if (ieee80211_is_beacon(hdr->frame_control)) {
+			return false;
+		} else if (!is_broadcast_ether_addr(bssid)) {
+			ocb_dbg(sdata, "BSSID mismatch in OCB mode!\n");
+			return false;
+		} else if (!multicast &&
+			   !ether_addr_equal(sdata->dev->dev_addr,
+					     hdr->addr1)) {
+			/* if we are in promisc mode we also accept
+			 * packets not destined for us
+			 */
+			if (!(sdata->dev->flags & IFF_PROMISC))
+				return false;
+			rx->flags &= ~IEEE80211_RX_RA_MATCH;
+		} else if (!rx->sta) {
+			int rate_idx;
+			if (status->flag & RX_FLAG_HT)
+				rate_idx = 0; /* TODO: HT rates */
+			else
+				rate_idx = status->rate_idx;
+			ieee80211_ocb_rx_no_sta(sdata, bssid, hdr->addr2,
+						BIT(rate_idx));
+		}
+		break;
 	case NL80211_IFTYPE_MESH_POINT:
 		if (!multicast &&
 		    !ether_addr_equal(sdata->vif.addr, hdr->addr1)) {
@@ -3244,7 +3438,8 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw,
 	__le16 fc;
 	struct ieee80211_rx_data rx;
 	struct ieee80211_sub_if_data *prev;
-	struct sta_info *sta, *tmp, *prev_sta;
+	struct sta_info *sta, *prev_sta;
+	struct rhash_head *tmp;
 	int err = 0;
 
 	fc = ((struct ieee80211_hdr *)skb->data)->frame_control;
@@ -3279,9 +3474,13 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw,
 		ieee80211_scan_rx(local, skb);
 
 	if (ieee80211_is_data(fc)) {
+		const struct bucket_table *tbl;
+
 		prev_sta = NULL;
 
-		for_each_sta_info(local, hdr->addr2, sta, tmp) {
+		tbl = rht_dereference_rcu(local->sta_hash.tbl, &local->sta_hash);
+
+		for_each_sta_info(local, tbl, hdr->addr2, sta, tmp) {
 			if (!prev_sta) {
 				prev_sta = sta;
 				continue;
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index af0d094b2f2f..7bb6a9383f58 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -184,9 +184,21 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb)
 		return;
 
 	if (ieee80211_is_probe_resp(mgmt->frame_control)) {
-		/* ignore ProbeResp to foreign address */
-		if ((!sdata1 || !ether_addr_equal(mgmt->da, sdata1->vif.addr)) &&
-		    (!sdata2 || !ether_addr_equal(mgmt->da, sdata2->vif.addr)))
+		struct cfg80211_scan_request *scan_req;
+		struct cfg80211_sched_scan_request *sched_scan_req;
+
+		scan_req = rcu_dereference(local->scan_req);
+		sched_scan_req = rcu_dereference(local->sched_scan_req);
+
+		/* ignore ProbeResp to foreign address unless scanning
+		 * with randomised address
+		 */
+		if (!(sdata1 &&
+		      (ether_addr_equal(mgmt->da, sdata1->vif.addr) ||
+		       scan_req->flags & NL80211_SCAN_FLAG_RANDOM_ADDR)) &&
+		    !(sdata2 &&
+		      (ether_addr_equal(mgmt->da, sdata2->vif.addr) ||
+		       sched_scan_req->flags & NL80211_SCAN_FLAG_RANDOM_ADDR)))
 			return;
 
 		elements = mgmt->u.probe_resp.variable;
@@ -234,11 +246,14 @@ ieee80211_prepare_scan_chandef(struct cfg80211_chan_def *chandef,
 /* return false if no more work */
 static bool ieee80211_prep_hw_scan(struct ieee80211_local *local)
 {
-	struct cfg80211_scan_request *req = local->scan_req;
+	struct cfg80211_scan_request *req;
 	struct cfg80211_chan_def chandef;
 	u8 bands_used = 0;
 	int i, ielen, n_chans;
 
+	req = rcu_dereference_protected(local->scan_req,
+					lockdep_is_held(&local->mtx));
+
 	if (test_bit(SCAN_HW_CANCELLED, &local->scanning))
 		return false;
 
@@ -281,6 +296,9 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_local *local)
 					 bands_used, req->rates, &chandef);
 	local->hw_scan_req->req.ie_len = ielen;
 	local->hw_scan_req->req.no_cck = req->no_cck;
+	ether_addr_copy(local->hw_scan_req->req.mac_addr, req->mac_addr);
+	ether_addr_copy(local->hw_scan_req->req.mac_addr_mask,
+			req->mac_addr_mask);
 
 	return true;
 }
@@ -290,6 +308,8 @@ 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;
+	struct cfg80211_scan_request *scan_req;
+	struct ieee80211_sub_if_data *scan_sdata;
 
 	lockdep_assert_held(&local->mtx);
 
@@ -322,9 +342,15 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted)
 	kfree(local->hw_scan_req);
 	local->hw_scan_req = NULL;
 
-	if (local->scan_req != local->int_scan_req)
-		cfg80211_scan_done(local->scan_req, aborted);
-	local->scan_req = NULL;
+	scan_req = rcu_dereference_protected(local->scan_req,
+					     lockdep_is_held(&local->mtx));
+
+	if (scan_req != local->int_scan_req)
+		cfg80211_scan_done(scan_req, aborted);
+	RCU_INIT_POINTER(local->scan_req, NULL);
+
+	scan_sdata = rcu_dereference_protected(local->scan_sdata,
+					       lockdep_is_held(&local->mtx));
 	RCU_INIT_POINTER(local->scan_sdata, NULL);
 
 	local->scanning = 0;
@@ -335,7 +361,7 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted)
 
 	if (!hw_scan) {
 		ieee80211_configure_filter(local);
-		drv_sw_scan_complete(local);
+		drv_sw_scan_complete(local, scan_sdata);
 		ieee80211_offchannel_return(local);
 	}
 
@@ -361,7 +387,8 @@ void ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted)
 }
 EXPORT_SYMBOL(ieee80211_scan_completed);
 
-static int ieee80211_start_sw_scan(struct ieee80211_local *local)
+static int ieee80211_start_sw_scan(struct ieee80211_local *local,
+				   struct ieee80211_sub_if_data *sdata)
 {
 	/* Software scan is not supported in multi-channel cases */
 	if (local->use_chanctx)
@@ -380,7 +407,7 @@ static int ieee80211_start_sw_scan(struct ieee80211_local *local)
 	 * nullfunc frames and probe requests will be dropped in
 	 * ieee80211_tx_h_check_assoc().
 	 */
-	drv_sw_scan_start(local);
+	drv_sw_scan_start(local, sdata, local->scan_addr);
 
 	local->leave_oper_channel_time = jiffies;
 	local->next_scan_state = SCAN_DECISION;
@@ -389,7 +416,7 @@ static int ieee80211_start_sw_scan(struct ieee80211_local *local)
 	ieee80211_offchannel_stop_vifs(local);
 
 	/* ensure nullfunc is transmitted before leaving operating channel */
-	ieee80211_flush_queues(local, NULL);
+	ieee80211_flush_queues(local, NULL, false);
 
 	ieee80211_configure_filter(local);
 
@@ -405,7 +432,7 @@ static int ieee80211_start_sw_scan(struct ieee80211_local *local)
 static bool ieee80211_can_scan(struct ieee80211_local *local,
 			       struct ieee80211_sub_if_data *sdata)
 {
-	if (local->radar_detect_enabled)
+	if (ieee80211_is_radar_required(local))
 		return false;
 
 	if (!list_empty(&local->roc_list))
@@ -440,23 +467,26 @@ static void ieee80211_scan_state_send_probe(struct ieee80211_local *local,
 {
 	int i;
 	struct ieee80211_sub_if_data *sdata;
+	struct cfg80211_scan_request *scan_req;
 	enum ieee80211_band band = local->hw.conf.chandef.chan->band;
 	u32 tx_flags;
 
+	scan_req = rcu_dereference_protected(local->scan_req,
+					     lockdep_is_held(&local->mtx));
+
 	tx_flags = IEEE80211_TX_INTFL_OFFCHAN_TX_OK;
-	if (local->scan_req->no_cck)
+	if (scan_req->no_cck)
 		tx_flags |= IEEE80211_TX_CTL_NO_CCK_RATE;
 
 	sdata = rcu_dereference_protected(local->scan_sdata,
 					  lockdep_is_held(&local->mtx));
 
-	for (i = 0; i < local->scan_req->n_ssids; i++)
+	for (i = 0; i < scan_req->n_ssids; i++)
 		ieee80211_send_probe_req(
-			sdata, NULL,
-			local->scan_req->ssids[i].ssid,
-			local->scan_req->ssids[i].ssid_len,
-			local->scan_req->ie, local->scan_req->ie_len,
-			local->scan_req->rates[band], false,
+			sdata, local->scan_addr, NULL,
+			scan_req->ssids[i].ssid, scan_req->ssids[i].ssid_len,
+			scan_req->ie, scan_req->ie_len,
+			scan_req->rates[band], false,
 			tx_flags, local->hw.conf.chandef.chan, true);
 
 	/*
@@ -475,12 +505,12 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata,
 
 	lockdep_assert_held(&local->mtx);
 
-	if (local->scan_req)
+	if (local->scan_req || ieee80211_is_radar_required(local))
 		return -EBUSY;
 
 	if (!ieee80211_can_scan(local, sdata)) {
 		/* wait for the work to finish/time out */
-		local->scan_req = req;
+		rcu_assign_pointer(local->scan_req, req);
 		rcu_assign_pointer(local->scan_sdata, sdata);
 		return 0;
 	}
@@ -530,9 +560,16 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata,
 		 */
 	}
 
-	local->scan_req = req;
+	rcu_assign_pointer(local->scan_req, req);
 	rcu_assign_pointer(local->scan_sdata, sdata);
 
+	if (req->flags & NL80211_SCAN_FLAG_RANDOM_ADDR)
+		get_random_mask_addr(local->scan_addr,
+				     req->mac_addr,
+				     req->mac_addr_mask);
+	else
+		memcpy(local->scan_addr, sdata->vif.addr, ETH_ALEN);
+
 	if (local->ops->hw_scan) {
 		__set_bit(SCAN_HW_SCANNING, &local->scanning);
 	} else if ((req->n_channels == 1) &&
@@ -549,7 +586,7 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata,
 
 		/* Notify driver scan is starting, keep order of operations
 		 * same as normal software scan, in case that matters. */
-		drv_sw_scan_start(local);
+		drv_sw_scan_start(local, sdata, local->scan_addr);
 
 		ieee80211_configure_filter(local); /* accept probe-responses */
 
@@ -558,7 +595,7 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata,
 
 		if ((req->channels[0]->flags &
 		     IEEE80211_CHAN_NO_IR) ||
-		    !local->scan_req->n_ssids) {
+		    !req->n_ssids) {
 			next_delay = IEEE80211_PASSIVE_CHANNEL_TIME;
 		} else {
 			ieee80211_scan_state_send_probe(local, &next_delay);
@@ -579,8 +616,9 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata,
 	if (local->ops->hw_scan) {
 		WARN_ON(!ieee80211_prep_hw_scan(local));
 		rc = drv_hw_scan(local, sdata, local->hw_scan_req);
-	} else
-		rc = ieee80211_start_sw_scan(local);
+	} else {
+		rc = ieee80211_start_sw_scan(local, sdata);
+	}
 
 	if (rc) {
 		kfree(local->hw_scan_req);
@@ -617,6 +655,7 @@ static void ieee80211_scan_state_decision(struct ieee80211_local *local,
 	struct ieee80211_sub_if_data *sdata;
 	struct ieee80211_channel *next_chan;
 	enum mac80211_scan_state next_scan_state;
+	struct cfg80211_scan_request *scan_req;
 
 	/*
 	 * check if at least one STA interface is associated,
@@ -641,7 +680,10 @@ static void ieee80211_scan_state_decision(struct ieee80211_local *local,
 	}
 	mutex_unlock(&local->iflist_mtx);
 
-	next_chan = local->scan_req->channels[local->scan_channel_idx];
+	scan_req = rcu_dereference_protected(local->scan_req,
+					     lockdep_is_held(&local->mtx));
+
+	next_chan = scan_req->channels[local->scan_channel_idx];
 
 	/*
 	 * we're currently scanning a different channel, let's
@@ -656,7 +698,7 @@ static void ieee80211_scan_state_decision(struct ieee80211_local *local,
 				 local->leave_oper_channel_time + HZ / 8);
 
 	if (associated && !tx_empty) {
-		if (local->scan_req->flags & NL80211_SCAN_FLAG_LOW_PRIORITY)
+		if (scan_req->flags & NL80211_SCAN_FLAG_LOW_PRIORITY)
 			next_scan_state = SCAN_ABORT;
 		else
 			next_scan_state = SCAN_SUSPEND;
@@ -677,14 +719,18 @@ static void ieee80211_scan_state_set_channel(struct ieee80211_local *local,
 	int skip;
 	struct ieee80211_channel *chan;
 	enum nl80211_bss_scan_width oper_scan_width;
+	struct cfg80211_scan_request *scan_req;
+
+	scan_req = rcu_dereference_protected(local->scan_req,
+					     lockdep_is_held(&local->mtx));
 
 	skip = 0;
-	chan = local->scan_req->channels[local->scan_channel_idx];
+	chan = scan_req->channels[local->scan_channel_idx];
 
 	local->scan_chandef.chan = chan;
 	local->scan_chandef.center_freq1 = chan->center_freq;
 	local->scan_chandef.center_freq2 = 0;
-	switch (local->scan_req->scan_width) {
+	switch (scan_req->scan_width) {
 	case NL80211_BSS_CHAN_WIDTH_5:
 		local->scan_chandef.width = NL80211_CHAN_WIDTH_5;
 		break;
@@ -698,7 +744,7 @@ static void ieee80211_scan_state_set_channel(struct ieee80211_local *local,
 		oper_scan_width = cfg80211_chandef_to_scan_width(
 					&local->_oper_chandef);
 		if (chan == local->_oper_chandef.chan &&
-		    oper_scan_width == local->scan_req->scan_width)
+		    oper_scan_width == scan_req->scan_width)
 			local->scan_chandef = local->_oper_chandef;
 		else
 			local->scan_chandef.width = NL80211_CHAN_WIDTH_20_NOHT;
@@ -727,8 +773,7 @@ static void ieee80211_scan_state_set_channel(struct ieee80211_local *local,
 	 *
 	 * In any case, it is not necessary for a passive scan.
 	 */
-	if (chan->flags & IEEE80211_CHAN_NO_IR ||
-	    !local->scan_req->n_ssids) {
+	if (chan->flags & IEEE80211_CHAN_NO_IR || !scan_req->n_ssids) {
 		*next_delay = IEEE80211_PASSIVE_CHANNEL_TIME;
 		local->next_scan_state = SCAN_DECISION;
 		return;
@@ -760,7 +805,7 @@ static void ieee80211_scan_state_resume(struct ieee80211_local *local,
 	ieee80211_offchannel_stop_vifs(local);
 
 	if (local->ops->flush) {
-		ieee80211_flush_queues(local, NULL);
+		ieee80211_flush_queues(local, NULL, false);
 		*next_delay = 0;
 	} else
 		*next_delay = HZ / 10;
@@ -777,13 +822,21 @@ void ieee80211_scan_work(struct work_struct *work)
 	struct ieee80211_local *local =
 		container_of(work, struct ieee80211_local, scan_work.work);
 	struct ieee80211_sub_if_data *sdata;
+	struct cfg80211_scan_request *scan_req;
 	unsigned long next_delay = 0;
 	bool aborted;
 
 	mutex_lock(&local->mtx);
 
+	if (!ieee80211_can_run_worker(local)) {
+		aborted = true;
+		goto out_complete;
+	}
+
 	sdata = rcu_dereference_protected(local->scan_sdata,
 					  lockdep_is_held(&local->mtx));
+	scan_req = rcu_dereference_protected(local->scan_req,
+					     lockdep_is_held(&local->mtx));
 
 	/* When scanning on-channel, the first-callback means completed. */
 	if (test_bit(SCAN_ONCHANNEL_SCANNING, &local->scanning)) {
@@ -796,20 +849,19 @@ void ieee80211_scan_work(struct work_struct *work)
 		goto out_complete;
 	}
 
-	if (!sdata || !local->scan_req)
+	if (!sdata || !scan_req)
 		goto out;
 
-	if (local->scan_req && !local->scanning) {
-		struct cfg80211_scan_request *req = local->scan_req;
+	if (!local->scanning) {
 		int rc;
 
-		local->scan_req = NULL;
+		RCU_INIT_POINTER(local->scan_req, NULL);
 		RCU_INIT_POINTER(local->scan_sdata, NULL);
 
-		rc = __ieee80211_start_scan(sdata, req);
+		rc = __ieee80211_start_scan(sdata, scan_req);
 		if (rc) {
 			/* need to complete scan in cfg80211 */
-			local->scan_req = req;
+			rcu_assign_pointer(local->scan_req, scan_req);
 			aborted = true;
 			goto out_complete;
 		} else
@@ -829,7 +881,7 @@ void ieee80211_scan_work(struct work_struct *work)
 		switch (local->next_scan_state) {
 		case SCAN_DECISION:
 			/* if no more bands/channels left, complete scan */
-			if (local->scan_channel_idx >= local->scan_req->n_channels) {
+			if (local->scan_channel_idx >= scan_req->n_channels) {
 				aborted = false;
 				goto out_complete;
 			}
@@ -876,11 +928,12 @@ int ieee80211_request_scan(struct ieee80211_sub_if_data *sdata,
 
 int ieee80211_request_ibss_scan(struct ieee80211_sub_if_data *sdata,
 				const u8 *ssid, u8 ssid_len,
-				struct ieee80211_channel *chan,
+				struct ieee80211_channel **channels,
+				unsigned int n_channels,
 				enum nl80211_bss_scan_width scan_width)
 {
 	struct ieee80211_local *local = sdata->local;
-	int ret = -EBUSY;
+	int ret = -EBUSY, i, n_ch = 0;
 	enum ieee80211_band band;
 
 	mutex_lock(&local->mtx);
@@ -890,9 +943,8 @@ int ieee80211_request_ibss_scan(struct ieee80211_sub_if_data *sdata,
 		goto unlock;
 
 	/* fill internal scan request */
-	if (!chan) {
-		int i, max_n;
-		int n_ch = 0;
+	if (!channels) {
+		int max_n;
 
 		for (band = 0; band < IEEE80211_NUM_BANDS; band++) {
 			if (!local->hw.wiphy->bands[band])
@@ -917,12 +969,19 @@ int ieee80211_request_ibss_scan(struct ieee80211_sub_if_data *sdata,
 
 		local->int_scan_req->n_channels = n_ch;
 	} else {
-		if (WARN_ON_ONCE(chan->flags & (IEEE80211_CHAN_NO_IR |
-						IEEE80211_CHAN_DISABLED)))
+		for (i = 0; i < n_channels; i++) {
+			if (channels[i]->flags & (IEEE80211_CHAN_NO_IR |
+						  IEEE80211_CHAN_DISABLED))
+				continue;
+
+			local->int_scan_req->channels[n_ch] = channels[i];
+			n_ch++;
+		}
+
+		if (WARN_ON_ONCE(n_ch == 0))
 			goto unlock;
 
-		local->int_scan_req->channels[0] = chan;
-		local->int_scan_req->n_channels = 1;
+		local->int_scan_req->n_channels = n_ch;
 	}
 
 	local->int_scan_req->ssids = &local->scan_ssid;
@@ -1043,7 +1102,7 @@ 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) {
 		rcu_assign_pointer(local->sched_scan_sdata, sdata);
-		local->sched_scan_req = req;
+		rcu_assign_pointer(local->sched_scan_req, req);
 	}
 
 	kfree(ie);
@@ -1052,7 +1111,7 @@ 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;
+		RCU_INIT_POINTER(local->sched_scan_req, NULL);
 	}
 
 	return ret;
@@ -1090,7 +1149,7 @@ int ieee80211_request_sched_scan_stop(struct ieee80211_sub_if_data *sdata)
 	}
 
 	/* We don't want to restart sched scan anymore. */
-	local->sched_scan_req = NULL;
+	RCU_INIT_POINTER(local->sched_scan_req, NULL);
 
 	if (rcu_access_pointer(local->sched_scan_sdata)) {
 		ret = drv_sched_scan_stop(local, sdata);
@@ -1125,7 +1184,7 @@ void ieee80211_sched_scan_end(struct ieee80211_local *local)
 	RCU_INIT_POINTER(local->sched_scan_sdata, NULL);
 
 	/* If sched scan was aborted by the driver. */
-	local->sched_scan_req = NULL;
+	RCU_INIT_POINTER(local->sched_scan_req, NULL);
 
 	mutex_unlock(&local->mtx);
 
diff --git a/net/mac80211/spectmgmt.c b/net/mac80211/spectmgmt.c
index efeba56c913b..06e6ac8cc693 100644
--- a/net/mac80211/spectmgmt.c
+++ b/net/mac80211/spectmgmt.c
@@ -34,19 +34,15 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata,
 	struct cfg80211_chan_def new_vht_chandef = {};
 	const struct ieee80211_sec_chan_offs_ie *sec_chan_offs;
 	const struct ieee80211_wide_bw_chansw_ie *wide_bw_chansw_ie;
-	const struct ieee80211_ht_operation *ht_oper;
 	int secondary_channel_offset = -1;
 
 	sec_chan_offs = elems->sec_chan_offs;
 	wide_bw_chansw_ie = elems->wide_bw_chansw_ie;
-	ht_oper = elems->ht_operation;
 
 	if (sta_flags & (IEEE80211_STA_DISABLE_HT |
 			 IEEE80211_STA_DISABLE_40MHZ)) {
 		sec_chan_offs = NULL;
 		wide_bw_chansw_ie = NULL;
-		/* only used for bandwidth here */
-		ht_oper = NULL;
 	}
 
 	if (sta_flags & IEEE80211_STA_DISABLE_VHT)
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index de494df3bab8..2880f2ae99ab 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -64,32 +64,21 @@
  * freed before they are done using it.
  */
 
+static const struct rhashtable_params sta_rht_params = {
+	.nelem_hint = 3, /* start small */
+	.automatic_shrinking = true,
+	.head_offset = offsetof(struct sta_info, hash_node),
+	.key_offset = offsetof(struct sta_info, sta.addr),
+	.key_len = ETH_ALEN,
+	.hashfn = sta_addr_hash,
+};
+
 /* Caller must hold local->sta_mtx */
 static int sta_info_hash_del(struct ieee80211_local *local,
 			     struct sta_info *sta)
 {
-	struct sta_info *s;
-
-	s = rcu_dereference_protected(local->sta_hash[STA_HASH(sta->sta.addr)],
-				      lockdep_is_held(&local->sta_mtx));
-	if (!s)
-		return -ENOENT;
-	if (s == sta) {
-		rcu_assign_pointer(local->sta_hash[STA_HASH(sta->sta.addr)],
-				   s->hnext);
-		return 0;
-	}
-
-	while (rcu_access_pointer(s->hnext) &&
-	       rcu_access_pointer(s->hnext) != sta)
-		s = rcu_dereference_protected(s->hnext,
-					lockdep_is_held(&local->sta_mtx));
-	if (rcu_access_pointer(s->hnext)) {
-		rcu_assign_pointer(s->hnext, sta->hnext);
-		return 0;
-	}
-
-	return -ENOENT;
+	return rhashtable_remove_fast(&local->sta_hash, &sta->hash_node,
+				      sta_rht_params);
 }
 
 static void __cleanup_single_sta(struct sta_info *sta)
@@ -116,7 +105,16 @@ static void __cleanup_single_sta(struct sta_info *sta)
 		clear_sta_flag(sta, WLAN_STA_PS_DELIVER);
 
 		atomic_dec(&ps->num_sta_ps);
-		sta_info_recalc_tim(sta);
+	}
+
+	if (sta->sta.txq[0]) {
+		for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) {
+			struct txq_info *txqi = to_txq_info(sta->sta.txq[i]);
+			int n = skb_queue_len(&txqi->queue);
+
+			ieee80211_purge_tx_queue(&local->hw, &txqi->queue);
+			atomic_sub(n, &sdata->txqs_len[txqi->txq.ac]);
+		}
 	}
 
 	for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
@@ -161,17 +159,23 @@ struct sta_info *sta_info_get(struct ieee80211_sub_if_data *sdata,
 {
 	struct ieee80211_local *local = sdata->local;
 	struct sta_info *sta;
+	struct rhash_head *tmp;
+	const struct bucket_table *tbl;
 
-	sta = rcu_dereference_check(local->sta_hash[STA_HASH(addr)],
-				    lockdep_is_held(&local->sta_mtx));
-	while (sta) {
-		if (sta->sdata == sdata &&
-		    ether_addr_equal(sta->sta.addr, addr))
-			break;
-		sta = rcu_dereference_check(sta->hnext,
-					    lockdep_is_held(&local->sta_mtx));
+	rcu_read_lock();
+	tbl = rht_dereference_rcu(local->sta_hash.tbl, &local->sta_hash);
+
+	for_each_sta_info(local, tbl, addr, sta, tmp) {
+		if (sta->sdata == sdata) {
+			rcu_read_unlock();
+			/* this is safe as the caller must already hold
+			 * another rcu read section or the mutex
+			 */
+			return sta;
+		}
 	}
-	return sta;
+	rcu_read_unlock();
+	return NULL;
 }
 
 /*
@@ -183,18 +187,24 @@ struct sta_info *sta_info_get_bss(struct ieee80211_sub_if_data *sdata,
 {
 	struct ieee80211_local *local = sdata->local;
 	struct sta_info *sta;
+	struct rhash_head *tmp;
+	const struct bucket_table *tbl;
 
-	sta = rcu_dereference_check(local->sta_hash[STA_HASH(addr)],
-				    lockdep_is_held(&local->sta_mtx));
-	while (sta) {
-		if ((sta->sdata == sdata ||
-		     (sta->sdata->bss && sta->sdata->bss == sdata->bss)) &&
-		    ether_addr_equal(sta->sta.addr, addr))
-			break;
-		sta = rcu_dereference_check(sta->hnext,
-					    lockdep_is_held(&local->sta_mtx));
+	rcu_read_lock();
+	tbl = rht_dereference_rcu(local->sta_hash.tbl, &local->sta_hash);
+
+	for_each_sta_info(local, tbl, addr, sta, tmp) {
+		if (sta->sdata == sdata ||
+		    (sta->sdata->bss && sta->sdata->bss == sdata->bss)) {
+			rcu_read_unlock();
+			/* this is safe as the caller must already hold
+			 * another rcu read section or the mutex
+			 */
+			return sta;
+		}
 	}
-	return sta;
+	rcu_read_unlock();
+	return NULL;
 }
 
 struct sta_info *sta_info_get_by_idx(struct ieee80211_sub_if_data *sdata,
@@ -230,19 +240,13 @@ struct sta_info *sta_info_get_by_idx(struct ieee80211_sub_if_data *sdata,
  */
 void sta_info_free(struct ieee80211_local *local, struct sta_info *sta)
 {
-	int i;
-
 	if (sta->rate_ctrl)
 		rate_control_free_sta(sta);
 
-	if (sta->tx_lat) {
-		for (i = 0; i < IEEE80211_NUM_TIDS; i++)
-			kfree(sta->tx_lat[i].bins);
-		kfree(sta->tx_lat);
-	}
-
 	sta_dbg(sta->sdata, "Destroyed STA %pM\n", sta->sta.addr);
 
+	if (sta->sta.txq[0])
+		kfree(to_txq_info(sta->sta.txq[0]));
 	kfree(rcu_dereference_raw(sta->sta.rates));
 	kfree(sta);
 }
@@ -251,9 +255,8 @@ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta)
 static void sta_info_hash_add(struct ieee80211_local *local,
 			      struct sta_info *sta)
 {
-	lockdep_assert_held(&local->sta_mtx);
-	sta->hnext = local->sta_hash[STA_HASH(sta->sta.addr)];
-	rcu_assign_pointer(local->sta_hash[STA_HASH(sta->sta.addr)], sta);
+	rhashtable_insert_fast(&local->sta_hash, &sta->hash_node,
+			       sta_rht_params);
 }
 
 static void sta_deliver_ps_frames(struct work_struct *wk)
@@ -294,44 +297,15 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
 				const u8 *addr, gfp_t gfp)
 {
 	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_hw *hw = &local->hw;
 	struct sta_info *sta;
 	struct timespec uptime;
-	struct ieee80211_tx_latency_bin_ranges *tx_latency;
 	int i;
 
-	sta = kzalloc(sizeof(*sta) + local->hw.sta_data_size, gfp);
+	sta = kzalloc(sizeof(*sta) + hw->sta_data_size, gfp);
 	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_deliver_wk, sta_deliver_ps_frames);
@@ -351,14 +325,33 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
 
 	sta->sta_state = IEEE80211_STA_NONE;
 
+	/* Mark TID as unreserved */
+	sta->reserved_tid = IEEE80211_TID_UNRESERVED;
+
 	ktime_get_ts(&uptime);
 	sta->last_connected = uptime.tv_sec;
 	ewma_init(&sta->avg_signal, 1024, 8);
 	for (i = 0; i < ARRAY_SIZE(sta->chain_signal_avg); i++)
 		ewma_init(&sta->chain_signal_avg[i], 1024, 8);
 
+	if (local->ops->wake_tx_queue) {
+		void *txq_data;
+		int size = sizeof(struct txq_info) +
+			   ALIGN(hw->txq_data_size, sizeof(void *));
+
+		txq_data = kcalloc(ARRAY_SIZE(sta->sta.txq), size, gfp);
+		if (!txq_data)
+			goto free;
+
+		for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) {
+			struct txq_info *txq = txq_data + i * size;
+
+			ieee80211_init_tx_queue(sdata, sta, txq, i);
+		}
+	}
+
 	if (sta_prepare_rate_control(local, sta, gfp))
-		goto free;
+		goto free_txq;
 
 	for (i = 0; i < IEEE80211_NUM_TIDS; i++) {
 		/*
@@ -380,7 +373,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
 	if (sdata->vif.type == NL80211_IFTYPE_AP ||
 	    sdata->vif.type == NL80211_IFTYPE_AP_VLAN) {
 		struct ieee80211_supported_band *sband =
-			local->hw.wiphy->bands[ieee80211_get_sdata_band(sdata)];
+			hw->wiphy->bands[ieee80211_get_sdata_band(sdata)];
 		u8 smps = (sband->ht_cap.cap & IEEE80211_HT_CAP_SM_PS) >>
 				IEEE80211_HT_CAP_SM_PS_SHIFT;
 		/*
@@ -403,14 +396,13 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
 	}
 
 	sta_dbg(sdata, "Allocated STA %pM\n", sta->sta.addr);
+
 	return sta;
 
+free_txq:
+	if (sta->sta.txq[0])
+		kfree(to_txq_info(sta->sta.txq[0]));
 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;
 }
@@ -501,7 +493,7 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU)
 	/* make the station visible */
 	sta_info_hash_add(local, sta);
 
-	list_add_rcu(&sta->list, &local->sta_list);
+	list_add_tail_rcu(&sta->list, &local->sta_list);
 
 	/* notify driver */
 	err = sta_info_insert_drv_state(local, sdata, sta);
@@ -622,7 +614,7 @@ static unsigned long ieee80211_tids_for_ac(int ac)
 	}
 }
 
-void sta_info_recalc_tim(struct sta_info *sta)
+static void __sta_info_recalc_tim(struct sta_info *sta, bool ignore_pending)
 {
 	struct ieee80211_local *local = sta->local;
 	struct ps_data *ps;
@@ -664,6 +656,9 @@ void sta_info_recalc_tim(struct sta_info *sta)
 	if (ignore_for_tim == BIT(IEEE80211_NUM_ACS) - 1)
 		ignore_for_tim = 0;
 
+	if (ignore_pending)
+		ignore_for_tim = BIT(IEEE80211_NUM_ACS) - 1;
+
 	for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
 		unsigned long tids;
 
@@ -679,6 +674,8 @@ void sta_info_recalc_tim(struct sta_info *sta)
 
 		indicate_tim |=
 			sta->driver_buffered_tids & tids;
+		indicate_tim |=
+			sta->txq_buffered_tids & tids;
 	}
 
  done:
@@ -692,7 +689,7 @@ void sta_info_recalc_tim(struct sta_info *sta)
 	else
 		__bss_tim_clear(ps->tim, id);
 
-	if (local->ops->set_tim) {
+	if (local->ops->set_tim && !WARN_ON(sta->dead)) {
 		local->tim_in_locked_section = true;
 		drv_set_tim(local, &sta->sta, indicate_tim);
 		local->tim_in_locked_section = false;
@@ -702,6 +699,11 @@ out_unlock:
 	spin_unlock_bh(&local->tim_lock);
 }
 
+void sta_info_recalc_tim(struct sta_info *sta)
+{
+	__sta_info_recalc_tim(sta, false);
+}
+
 static bool sta_info_buffer_expired(struct sta_info *sta, struct sk_buff *skb)
 {
 	struct ieee80211_tx_info *info;
@@ -847,6 +849,15 @@ static int __must_check __sta_info_destroy_part1(struct sta_info *sta)
 	if (WARN_ON(ret))
 		return ret;
 
+	/*
+	 * for TDLS peers, make sure to return to the base channel before
+	 * removal.
+	 */
+	if (test_sta_flag(sta, WLAN_STA_TDLS_OFF_CHANNEL)) {
+		drv_tdls_cancel_channel_switch(local, sdata, &sta->sta);
+		clear_sta_flag(sta, WLAN_STA_TDLS_OFF_CHANNEL);
+	}
+
 	list_del_rcu(&sta->list);
 
 	drv_sta_pre_rcu_remove(local, sta->sdata, sta);
@@ -862,6 +873,7 @@ static void __sta_info_destroy_part2(struct sta_info *sta)
 {
 	struct ieee80211_local *local = sta->local;
 	struct ieee80211_sub_if_data *sdata = sta->sdata;
+	struct station_info sinfo = {};
 	int ret;
 
 	/*
@@ -875,6 +887,9 @@ static void __sta_info_destroy_part2(struct sta_info *sta)
 	/* now keys can no longer be reached */
 	ieee80211_free_sta_keys(local, sta);
 
+	/* disable TIM bit - last chance to tell driver */
+	__sta_info_recalc_tim(sta, true);
+
 	sta->dead = true;
 
 	local->num_sta--;
@@ -896,7 +911,8 @@ static void __sta_info_destroy_part2(struct sta_info *sta)
 
 	sta_dbg(sdata, "Removed STA %pM\n", sta->sta.addr);
 
-	cfg80211_del_sta(sdata->dev, sta->sta.addr, GFP_KERNEL);
+	sta_set_sinfo(sta, &sinfo);
+	cfg80211_del_sta_sinfo(sdata->dev, sta->sta.addr, &sinfo, GFP_KERNEL);
 
 	rate_control_remove_sta_debugfs(sta);
 	ieee80211_sta_debugfs_remove(sta);
@@ -968,19 +984,32 @@ static void sta_info_cleanup(unsigned long data)
 		  round_jiffies(jiffies + STA_INFO_CLEANUP_INTERVAL));
 }
 
-void sta_info_init(struct ieee80211_local *local)
+u32 sta_addr_hash(const void *key, u32 length, u32 seed)
+{
+	return jhash(key, ETH_ALEN, seed);
+}
+
+int sta_info_init(struct ieee80211_local *local)
 {
+	int err;
+
+	err = rhashtable_init(&local->sta_hash, &sta_rht_params);
+	if (err)
+		return err;
+
 	spin_lock_init(&local->tim_lock);
 	mutex_init(&local->sta_mtx);
 	INIT_LIST_HEAD(&local->sta_list);
 
 	setup_timer(&local->sta_cleanup, sta_info_cleanup,
 		    (unsigned long)local);
+	return 0;
 }
 
 void sta_info_stop(struct ieee80211_local *local)
 {
 	del_timer_sync(&local->sta_cleanup);
+	rhashtable_destroy(&local->sta_hash);
 }
 
 
@@ -1044,16 +1073,21 @@ void ieee80211_sta_expire(struct ieee80211_sub_if_data *sdata,
 }
 
 struct ieee80211_sta *ieee80211_find_sta_by_ifaddr(struct ieee80211_hw *hw,
-					       const u8 *addr,
-					       const u8 *localaddr)
+						   const u8 *addr,
+						   const u8 *localaddr)
 {
-	struct sta_info *sta, *nxt;
+	struct ieee80211_local *local = hw_to_local(hw);
+	struct sta_info *sta;
+	struct rhash_head *tmp;
+	const struct bucket_table *tbl;
+
+	tbl = rht_dereference_rcu(local->sta_hash.tbl, &local->sta_hash);
 
 	/*
 	 * Just return a random station if localaddr is NULL
 	 * ... first in list.
 	 */
-	for_each_sta_info(hw_to_local(hw), addr, sta, nxt) {
+	for_each_sta_info(local, tbl, addr, sta, tmp) {
 		if (localaddr &&
 		    !ether_addr_equal(sta->sdata->vif.addr, localaddr))
 			continue;
@@ -1091,7 +1125,7 @@ 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;
+	int filtered = 0, buffered = 0, ac, i;
 	unsigned long flags;
 	struct ps_data *ps;
 
@@ -1110,10 +1144,22 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
 
 	BUILD_BUG_ON(BITS_TO_LONGS(IEEE80211_NUM_TIDS) > 1);
 	sta->driver_buffered_tids = 0;
+	sta->txq_buffered_tids = 0;
 
 	if (!(local->hw.flags & IEEE80211_HW_AP_LINK_PS))
 		drv_sta_notify(local, sdata, STA_NOTIFY_AWAKE, &sta->sta);
 
+	if (sta->sta.txq[0]) {
+		for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) {
+			struct txq_info *txqi = to_txq_info(sta->sta.txq[i]);
+
+			if (!skb_queue_len(&txqi->queue))
+				continue;
+
+			drv_wake_tx_queue(local, txqi);
+		}
+	}
+
 	skb_queue_head_init(&pending);
 
 	/* sync with ieee80211_tx_h_unicast_ps_buf */
@@ -1231,10 +1277,11 @@ static void ieee80211_send_null_response(struct ieee80211_sub_if_data *sdata,
 	 * ends the poll/service period.
 	 */
 	info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER |
-		       IEEE80211_TX_CTL_PS_RESPONSE |
 		       IEEE80211_TX_STATUS_EOSP |
 		       IEEE80211_TX_CTL_REQ_TX_STATUS;
 
+	info->control.flags |= IEEE80211_TX_CTRL_PS_RESPONSE;
+
 	if (call_driver)
 		drv_allow_buffered_frames(local, sta, BIT(tid), 1,
 					  reason, false);
@@ -1249,7 +1296,8 @@ static void ieee80211_send_null_response(struct ieee80211_sub_if_data *sdata,
 		return;
 	}
 
-	ieee80211_xmit(sdata, skb, chanctx_conf->def.chan->band);
+	info->band = chanctx_conf->def.chan->band;
+	ieee80211_xmit(sdata, sta, skb);
 	rcu_read_unlock();
 }
 
@@ -1293,8 +1341,10 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta,
 		/* if we already have frames from software, then we can't also
 		 * release from hardware queues
 		 */
-		if (skb_queue_empty(&frames))
+		if (skb_queue_empty(&frames)) {
 			driver_release_tids |= sta->driver_buffered_tids & tids;
+			driver_release_tids |= sta->txq_buffered_tids & tids;
+		}
 
 		if (driver_release_tids) {
 			/* If the driver has data on more than one TID then
@@ -1382,8 +1432,8 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta,
 			 * STA may still remain is PS mode after this frame
 			 * exchange.
 			 */
-			info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER |
-				       IEEE80211_TX_CTL_PS_RESPONSE;
+			info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER;
+			info->control.flags |= IEEE80211_TX_CTRL_PS_RESPONSE;
 
 			/*
 			 * Use MoreData flag to indicate whether there are
@@ -1465,6 +1515,9 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta,
 
 		sta_info_recalc_tim(sta);
 	} else {
+		unsigned long tids = sta->txq_buffered_tids & driver_release_tids;
+		int tid;
+
 		/*
 		 * We need to release a frame that is buffered somewhere in the
 		 * driver ... it'll have to handle that.
@@ -1484,8 +1537,22 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta,
 		 * that the TID(s) became empty before returning here from the
 		 * release function.
 		 * Either way, however, when the driver tells us that the TID(s)
-		 * became empty we'll do the TIM recalculation.
+		 * became empty or we find that a txq became empty, we'll do the
+		 * TIM recalculation.
 		 */
+
+		if (!sta->sta.txq[0])
+			return;
+
+		for (tid = 0; tid < ARRAY_SIZE(sta->sta.txq); tid++) {
+			struct txq_info *txqi = to_txq_info(sta->sta.txq[tid]);
+
+			if (!(tids & BIT(tid)) || skb_queue_len(&txqi->queue))
+				continue;
+
+			sta_info_recalc_tim(sta);
+			break;
+		}
 	}
 }
 
@@ -1531,7 +1598,7 @@ void ieee80211_sta_ps_deliver_uapsd(struct sta_info *sta)
 		break;
 	case 0:
 		/* XXX: what is a good value? */
-		n_frames = 8;
+		n_frames = 128;
 		break;
 	}
 
@@ -1730,7 +1797,6 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo)
 	struct ieee80211_local *local = sdata->local;
 	struct rate_control_ref *ref = NULL;
 	struct timespec uptime;
-	u64 packets = 0;
 	u32 thr = 0;
 	int i, ac;
 
@@ -1739,49 +1805,90 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo)
 
 	sinfo->generation = sdata->local->sta_generation;
 
-	sinfo->filled = STATION_INFO_INACTIVE_TIME |
-			STATION_INFO_RX_BYTES64 |
-			STATION_INFO_TX_BYTES64 |
-			STATION_INFO_RX_PACKETS |
-			STATION_INFO_TX_PACKETS |
-			STATION_INFO_TX_RETRIES |
-			STATION_INFO_TX_FAILED |
-			STATION_INFO_TX_BITRATE |
-			STATION_INFO_RX_BITRATE |
-			STATION_INFO_RX_DROP_MISC |
-			STATION_INFO_BSS_PARAM |
-			STATION_INFO_CONNECTED_TIME |
-			STATION_INFO_STA_FLAGS |
-			STATION_INFO_BEACON_LOSS_COUNT;
+	/* do before driver, so beacon filtering drivers have a
+	 * chance to e.g. just add the number of filtered beacons
+	 * (or just modify the value entirely, of course)
+	 */
+	if (sdata->vif.type == NL80211_IFTYPE_STATION)
+		sinfo->rx_beacon = sdata->u.mgd.count_beacon_signal;
+
+	drv_sta_statistics(local, sdata, &sta->sta, sinfo);
+
+	sinfo->filled |= BIT(NL80211_STA_INFO_INACTIVE_TIME) |
+			 BIT(NL80211_STA_INFO_STA_FLAGS) |
+			 BIT(NL80211_STA_INFO_BSS_PARAM) |
+			 BIT(NL80211_STA_INFO_CONNECTED_TIME) |
+			 BIT(NL80211_STA_INFO_RX_DROP_MISC) |
+			 BIT(NL80211_STA_INFO_BEACON_LOSS);
 
 	ktime_get_ts(&uptime);
 	sinfo->connected_time = uptime.tv_sec - sta->last_connected;
-
 	sinfo->inactive_time = jiffies_to_msecs(jiffies - sta->last_rx);
-	sinfo->tx_bytes = 0;
-	for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
-		sinfo->tx_bytes += sta->tx_bytes[ac];
-		packets += sta->tx_packets[ac];
+
+	if (!(sinfo->filled & (BIT(NL80211_STA_INFO_TX_BYTES64) |
+			       BIT(NL80211_STA_INFO_TX_BYTES)))) {
+		sinfo->tx_bytes = 0;
+		for (ac = 0; ac < IEEE80211_NUM_ACS; ac++)
+			sinfo->tx_bytes += sta->tx_bytes[ac];
+		sinfo->filled |= BIT(NL80211_STA_INFO_TX_BYTES64);
+	}
+
+	if (!(sinfo->filled & BIT(NL80211_STA_INFO_TX_PACKETS))) {
+		sinfo->tx_packets = 0;
+		for (ac = 0; ac < IEEE80211_NUM_ACS; ac++)
+			sinfo->tx_packets += sta->tx_packets[ac];
+		sinfo->filled |= BIT(NL80211_STA_INFO_TX_PACKETS);
+	}
+
+	if (!(sinfo->filled & (BIT(NL80211_STA_INFO_RX_BYTES64) |
+			       BIT(NL80211_STA_INFO_RX_BYTES)))) {
+		sinfo->rx_bytes = sta->rx_bytes;
+		sinfo->filled |= BIT(NL80211_STA_INFO_RX_BYTES64);
+	}
+
+	if (!(sinfo->filled & BIT(NL80211_STA_INFO_RX_PACKETS))) {
+		sinfo->rx_packets = sta->rx_packets;
+		sinfo->filled |= BIT(NL80211_STA_INFO_RX_PACKETS);
 	}
-	sinfo->tx_packets = packets;
-	sinfo->rx_bytes = sta->rx_bytes;
-	sinfo->rx_packets = sta->rx_packets;
-	sinfo->tx_retries = sta->tx_retry_count;
-	sinfo->tx_failed = sta->tx_retry_failed;
+
+	if (!(sinfo->filled & BIT(NL80211_STA_INFO_TX_RETRIES))) {
+		sinfo->tx_retries = sta->tx_retry_count;
+		sinfo->filled |= BIT(NL80211_STA_INFO_TX_RETRIES);
+	}
+
+	if (!(sinfo->filled & BIT(NL80211_STA_INFO_TX_FAILED))) {
+		sinfo->tx_failed = sta->tx_retry_failed;
+		sinfo->filled |= BIT(NL80211_STA_INFO_TX_FAILED);
+	}
+
 	sinfo->rx_dropped_misc = sta->rx_dropped;
 	sinfo->beacon_loss_count = sta->beacon_loss_count;
 
+	if (sdata->vif.type == NL80211_IFTYPE_STATION &&
+	    !(sdata->vif.driver_flags & IEEE80211_VIF_BEACON_FILTER)) {
+		sinfo->filled |= BIT(NL80211_STA_INFO_BEACON_RX) |
+				 BIT(NL80211_STA_INFO_BEACON_SIGNAL_AVG);
+		sinfo->rx_beacon_signal_avg = ieee80211_ave_rssi(&sdata->vif);
+	}
+
 	if ((sta->local->hw.flags & IEEE80211_HW_SIGNAL_DBM) ||
 	    (sta->local->hw.flags & IEEE80211_HW_SIGNAL_UNSPEC)) {
-		sinfo->filled |= STATION_INFO_SIGNAL | STATION_INFO_SIGNAL_AVG;
-		if (!local->ops->get_rssi ||
-		    drv_get_rssi(local, sdata, &sta->sta, &sinfo->signal))
+		if (!(sinfo->filled & BIT(NL80211_STA_INFO_SIGNAL))) {
 			sinfo->signal = (s8)sta->last_signal;
-		sinfo->signal_avg = (s8) -ewma_read(&sta->avg_signal);
+			sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
+		}
+
+		if (!(sinfo->filled & BIT(NL80211_STA_INFO_SIGNAL_AVG))) {
+			sinfo->signal_avg = (s8) -ewma_read(&sta->avg_signal);
+			sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL_AVG);
+		}
 	}
-	if (sta->chains) {
-		sinfo->filled |= STATION_INFO_CHAIN_SIGNAL |
-				 STATION_INFO_CHAIN_SIGNAL_AVG;
+
+	if (sta->chains &&
+	    !(sinfo->filled & (BIT(NL80211_STA_INFO_CHAIN_SIGNAL) |
+			       BIT(NL80211_STA_INFO_CHAIN_SIGNAL_AVG)))) {
+		sinfo->filled |= BIT(NL80211_STA_INFO_CHAIN_SIGNAL) |
+				 BIT(NL80211_STA_INFO_CHAIN_SIGNAL_AVG);
 
 		sinfo->chains = sta->chains;
 		for (i = 0; i < ARRAY_SIZE(sinfo->chain_signal); i++) {
@@ -1791,23 +1898,61 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo)
 		}
 	}
 
-	sta_set_rate_info_tx(sta, &sta->last_tx_rate, &sinfo->txrate);
-	sta_set_rate_info_rx(sta, &sinfo->rxrate);
+	if (!(sinfo->filled & BIT(NL80211_STA_INFO_TX_BITRATE))) {
+		sta_set_rate_info_tx(sta, &sta->last_tx_rate, &sinfo->txrate);
+		sinfo->filled |= BIT(NL80211_STA_INFO_TX_BITRATE);
+	}
+
+	if (!(sinfo->filled & BIT(NL80211_STA_INFO_RX_BITRATE))) {
+		sta_set_rate_info_rx(sta, &sinfo->rxrate);
+		sinfo->filled |= BIT(NL80211_STA_INFO_RX_BITRATE);
+	}
+
+	sinfo->filled |= BIT(NL80211_STA_INFO_TID_STATS);
+	for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++) {
+		struct cfg80211_tid_stats *tidstats = &sinfo->pertid[i];
+
+		if (!(tidstats->filled & BIT(NL80211_TID_STATS_RX_MSDU))) {
+			tidstats->filled |= BIT(NL80211_TID_STATS_RX_MSDU);
+			tidstats->rx_msdu = sta->rx_msdu[i];
+		}
+
+		if (!(tidstats->filled & BIT(NL80211_TID_STATS_TX_MSDU))) {
+			tidstats->filled |= BIT(NL80211_TID_STATS_TX_MSDU);
+			tidstats->tx_msdu = sta->tx_msdu[i];
+		}
+
+		if (!(tidstats->filled &
+				BIT(NL80211_TID_STATS_TX_MSDU_RETRIES)) &&
+		    local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS) {
+			tidstats->filled |=
+				BIT(NL80211_TID_STATS_TX_MSDU_RETRIES);
+			tidstats->tx_msdu_retries = sta->tx_msdu_retries[i];
+		}
+
+		if (!(tidstats->filled &
+				BIT(NL80211_TID_STATS_TX_MSDU_FAILED)) &&
+		    local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS) {
+			tidstats->filled |=
+				BIT(NL80211_TID_STATS_TX_MSDU_FAILED);
+			tidstats->tx_msdu_failed = sta->tx_msdu_failed[i];
+		}
+	}
 
 	if (ieee80211_vif_is_mesh(&sdata->vif)) {
 #ifdef CONFIG_MAC80211_MESH
-		sinfo->filled |= STATION_INFO_LLID |
-				 STATION_INFO_PLID |
-				 STATION_INFO_PLINK_STATE |
-				 STATION_INFO_LOCAL_PM |
-				 STATION_INFO_PEER_PM |
-				 STATION_INFO_NONPEER_PM;
+		sinfo->filled |= BIT(NL80211_STA_INFO_LLID) |
+				 BIT(NL80211_STA_INFO_PLID) |
+				 BIT(NL80211_STA_INFO_PLINK_STATE) |
+				 BIT(NL80211_STA_INFO_LOCAL_PM) |
+				 BIT(NL80211_STA_INFO_PEER_PM) |
+				 BIT(NL80211_STA_INFO_NONPEER_PM);
 
 		sinfo->llid = sta->llid;
 		sinfo->plid = sta->plid;
 		sinfo->plink_state = sta->plink_state;
 		if (test_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN)) {
-			sinfo->filled |= STATION_INFO_T_OFFSET;
+			sinfo->filled |= BIT(NL80211_STA_INFO_T_OFFSET);
 			sinfo->t_offset = sta->t_offset;
 		}
 		sinfo->local_pm = sta->local_pm;
@@ -1856,7 +2001,7 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo)
 		thr = drv_get_expected_throughput(local, &sta->sta);
 
 	if (thr != 0) {
-		sinfo->filled |= STATION_INFO_EXPECTED_THROUGHPUT;
+		sinfo->filled |= BIT(NL80211_STA_INFO_EXPECTED_THROUGHPUT);
 		sinfo->expected_throughput = thr;
 	}
 }
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index bcda2ac7d844..5c164fb3f6c5 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -16,6 +16,7 @@
 #include <linux/workqueue.h>
 #include <linux/average.h>
 #include <linux/etherdevice.h>
+#include <linux/rhashtable.h>
 #include "key.h"
 
 /**
@@ -49,6 +50,9 @@
  *	packets. This means the link is enabled.
  * @WLAN_STA_TDLS_INITIATOR: We are the initiator of the TDLS link with this
  *	station.
+ * @WLAN_STA_TDLS_CHAN_SWITCH: This TDLS peer supports TDLS channel-switching
+ * @WLAN_STA_TDLS_OFF_CHANNEL: The local STA is currently off-channel with this
+ *	TDLS peer
  * @WLAN_STA_UAPSD: Station requested unscheduled SP while driver was
  *	keeping station in power-save mode, reply when the driver
  *	unblocks the station.
@@ -78,6 +82,8 @@ enum ieee80211_sta_info_flags {
 	WLAN_STA_TDLS_PEER,
 	WLAN_STA_TDLS_PEER_AUTH,
 	WLAN_STA_TDLS_INITIATOR,
+	WLAN_STA_TDLS_CHAN_SWITCH,
+	WLAN_STA_TDLS_OFF_CHANNEL,
 	WLAN_STA_UAPSD,
 	WLAN_STA_SP,
 	WLAN_STA_4ADDR_EVENT,
@@ -170,6 +176,7 @@ struct tid_ampdu_tx {
  * @reorder_lock: serializes access to reorder buffer, see below.
  * @auto_seq: used for offloaded BA sessions to automatically pick head_seq_and
  *	and ssn.
+ * @removed: this session is removed (but might have been found due to RCU)
  *
  * This structure's lifetime is managed by RCU, assignments to
  * the array holding it must hold the aggregation mutex.
@@ -194,6 +201,7 @@ struct tid_ampdu_rx {
 	u16 timeout;
 	u8 dialog_token;
 	bool auto_seq;
+	bool removed;
 };
 
 /**
@@ -229,25 +237,9 @@ struct sta_ampdu_mlme {
 	u8 dialog_token_allocator;
 };
 
-/*
- * struct ieee80211_tx_latency_stat - Tx latency statistics
- *
- * Measures TX latency and jitter for a station per TID.
- *
- * @max: worst case latency
- * @sum: sum of all latencies
- * @counter: amount of Tx frames sent from interface
- * @bins: each bin counts how many frames transmitted within a certain
- * latency range. when disabled it is NULL.
- * @bin_count: amount of bins.
- */
-struct ieee80211_tx_latency_stat {
-	u32 max;
-	u32 sum;
-	u32 counter;
-	u32 *bins;
-	u32 bin_count;
-};
+
+/* Value to indicate no TID reservation */
+#define IEEE80211_TID_UNRESERVED	0xff
 
 /**
  * struct sta_info - STA information
@@ -257,7 +249,7 @@ struct ieee80211_tx_latency_stat {
  *
  * @list: global linked list entry
  * @free_list: list entry for keeping track of stations to free
- * @hnext: hash table linked list pointer
+ * @hash_node: hash node for rhashtable
  * @local: pointer to the global information
  * @sdata: virtual interface this station belongs to
  * @ptk: peer keys negotiated with this station, if any
@@ -285,6 +277,7 @@ struct ieee80211_tx_latency_stat {
  *	entered power saving state, these are also delivered to
  *	the station when it leaves powersave or polls for frames
  * @driver_buffered_tids: bitmap of TIDs the driver has data buffered on
+ * @txq_buffered_tids: bitmap of TIDs that mac80211 has txq data buffered on
  * @rx_packets: Number of MSDUs received from this STA
  * @rx_bytes: Number of bytes received from this STA
  * @last_rx: time (in jiffies) when last frame was received from this STA
@@ -306,7 +299,6 @@ struct ieee80211_tx_latency_stat {
  * @tid_seq: per-TID sequence numbers for sending to this STA
  * @ampdu_mlme: A-MPDU state machine state
  * @timer_to_tid: identity mapping to ID timers
- * @tx_lat: Tx latency statistics
  * @llid: Local link ID
  * @plid: Peer link ID
  * @reason: Cancel reason on PLINK_HOLDING state
@@ -337,12 +329,21 @@ struct ieee80211_tx_latency_stat {
  *	AP only.
  * @cipher_scheme: optional cipher scheme for this station
  * @last_tdls_pkt_time: holds the time in jiffies of last TDLS pkt ACKed
+ * @reserved_tid: reserved TID (if any, otherwise IEEE80211_TID_UNRESERVED)
+ * @tx_msdu: MSDUs transmitted to this station, using IEEE80211_NUM_TID
+ *	entry for non-QoS frames
+ * @tx_msdu_retries: MSDU retries for transmissions to to this station,
+ *	using IEEE80211_NUM_TID entry for non-QoS frames
+ * @tx_msdu_failed: MSDU failures for transmissions to to this station,
+ *	using IEEE80211_NUM_TID entry for non-QoS frames
+ * @rx_msdu: MSDUs received from this station, using IEEE80211_NUM_TID
+ *	entry for non-QoS frames
  */
 struct sta_info {
 	/* General information, mostly static */
 	struct list_head list, free_list;
 	struct rcu_head rcu_head;
-	struct sta_info __rcu *hnext;
+	struct rhash_head hash_node;
 	struct ieee80211_local *local;
 	struct ieee80211_sub_if_data *sdata;
 	struct ieee80211_key __rcu *gtk[NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS];
@@ -371,6 +372,7 @@ struct sta_info {
 	struct sk_buff_head ps_tx_buf[IEEE80211_NUM_ACS];
 	struct sk_buff_head tx_filtered[IEEE80211_NUM_ACS];
 	unsigned long driver_buffered_tids;
+	unsigned long txq_buffered_tids;
 
 	/* Updated from RX path only, no locking requirements */
 	unsigned long rx_packets;
@@ -407,6 +409,10 @@ struct sta_info {
 	u32 last_rx_rate_vht_flag;
 	u8 last_rx_rate_vht_nss;
 	u16 tid_seq[IEEE80211_QOS_CTL_TID_MASK + 1];
+	u64 tx_msdu[IEEE80211_NUM_TIDS + 1];
+	u64 tx_msdu_retries[IEEE80211_NUM_TIDS + 1];
+	u64 tx_msdu_failed[IEEE80211_NUM_TIDS + 1];
+	u64 rx_msdu[IEEE80211_NUM_TIDS + 1];
 
 	/*
 	 * Aggregation information, locked with lock.
@@ -414,8 +420,6 @@ struct sta_info {
 	struct sta_ampdu_mlme ampdu_mlme;
 	u8 timer_to_tid[IEEE80211_NUM_TIDS];
 
-	struct ieee80211_tx_latency_stat *tx_lat;
-
 #ifdef CONFIG_MAC80211_MESH
 	/*
 	 * Mesh peer link attributes
@@ -454,6 +458,8 @@ struct sta_info {
 	/* TDLS timeout data */
 	unsigned long last_tdls_pkt_time;
 
+	u8 reserved_tid;
+
 	/* keep last! */
 	struct ieee80211_sta sta;
 };
@@ -534,10 +540,6 @@ rcu_dereference_protected_tid_tx(struct sta_info *sta, int tid)
 					 lockdep_is_held(&sta->ampdu_mlme.mtx));
 }
 
-#define STA_HASH_SIZE 256
-#define STA_HASH(sta) (sta[5])
-
-
 /* Maximum number of frames to buffer per power saving station per AC */
 #define STA_MAX_TX_BUFFER	64
 
@@ -558,26 +560,15 @@ struct sta_info *sta_info_get(struct ieee80211_sub_if_data *sdata,
 struct sta_info *sta_info_get_bss(struct ieee80211_sub_if_data *sdata,
 				  const u8 *addr);
 
-static inline
-void for_each_sta_info_type_check(struct ieee80211_local *local,
-				  const u8 *addr,
-				  struct sta_info *sta,
-				  struct sta_info *nxt)
-{
-}
+u32 sta_addr_hash(const void *key, u32 length, u32 seed);
+
+#define _sta_bucket_idx(_tbl, _a)					\
+	rht_bucket_index(_tbl, sta_addr_hash(_a, ETH_ALEN, (_tbl)->hash_rnd))
 
-#define for_each_sta_info(local, _addr, _sta, nxt)			\
-	for (	/* initialise loop */					\
-		_sta = rcu_dereference(local->sta_hash[STA_HASH(_addr)]),\
-		nxt = _sta ? rcu_dereference(_sta->hnext) : NULL;	\
-		/* typecheck */						\
-		for_each_sta_info_type_check(local, (_addr), _sta, nxt),\
-		/* continue condition */				\
-		_sta;							\
-		/* advance loop */					\
-		_sta = nxt,						\
-		nxt = _sta ? rcu_dereference(_sta->hnext) : NULL	\
-	     )								\
+#define for_each_sta_info(local, tbl, _addr, _sta, _tmp)		\
+	rht_for_each_entry_rcu(_sta, _tmp, tbl, 			\
+			       _sta_bucket_idx(tbl, _addr),		\
+			       hash_node)				\
 	/* compare address and run code only if it matches */		\
 	if (ether_addr_equal(_sta->sta.addr, (_addr)))
 
@@ -614,7 +605,7 @@ int sta_info_destroy_addr_bss(struct ieee80211_sub_if_data *sdata,
 
 void sta_info_recalc_tim(struct sta_info *sta);
 
-void sta_info_init(struct ieee80211_local *local);
+int sta_info_init(struct ieee80211_local *local);
 void sta_info_stop(struct ieee80211_local *local);
 
 /**
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 89290e33dafe..005fdbe39a8b 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -12,7 +12,6 @@
 
 #include <linux/export.h>
 #include <linux/etherdevice.h>
-#include <linux/time.h>
 #include <net/mac80211.h>
 #include <asm/unaligned.h>
 #include "ieee80211_i.h"
@@ -390,6 +389,46 @@ ieee80211_add_tx_radiotap_header(struct ieee80211_local *local,
 	}
 }
 
+/*
+ * Handles the tx for TDLS teardown frames.
+ * If the frame wasn't ACKed by the peer - it will be re-sent through the AP
+ */
+static void ieee80211_tdls_td_tx_handle(struct ieee80211_local *local,
+					struct ieee80211_sub_if_data *sdata,
+					struct sk_buff *skb, u32 flags)
+{
+	struct sk_buff *teardown_skb;
+	struct sk_buff *orig_teardown_skb;
+	bool is_teardown = false;
+
+	/* Get the teardown data we need and free the lock */
+	spin_lock(&sdata->u.mgd.teardown_lock);
+	teardown_skb = sdata->u.mgd.teardown_skb;
+	orig_teardown_skb = sdata->u.mgd.orig_teardown_skb;
+	if ((skb == orig_teardown_skb) && teardown_skb) {
+		sdata->u.mgd.teardown_skb = NULL;
+		sdata->u.mgd.orig_teardown_skb = NULL;
+		is_teardown = true;
+	}
+	spin_unlock(&sdata->u.mgd.teardown_lock);
+
+	if (is_teardown) {
+		/* This mechanism relies on being able to get ACKs */
+		WARN_ON(!(local->hw.flags &
+			  IEEE80211_HW_REPORTS_TX_ACK_STATUS));
+
+		/* Check if peer has ACKed */
+		if (flags & IEEE80211_TX_STAT_ACK) {
+			dev_kfree_skb_any(teardown_skb);
+		} else {
+			tdls_dbg(sdata,
+				 "TDLS Resending teardown through AP\n");
+
+			ieee80211_subif_start_xmit(teardown_skb, skb->dev);
+		}
+	}
+}
+
 static void ieee80211_report_used_skb(struct ieee80211_local *local,
 				      struct sk_buff *skb, bool dropped)
 {
@@ -426,8 +465,19 @@ static void ieee80211_report_used_skb(struct ieee80211_local *local,
 		if (!sdata) {
 			skb->dev = NULL;
 		} else if (info->flags & IEEE80211_TX_INTFL_MLME_CONN_TX) {
-			ieee80211_mgd_conn_tx_status(sdata, hdr->frame_control,
-						     acked);
+			unsigned int hdr_size =
+				ieee80211_hdrlen(hdr->frame_control);
+
+			/* Check to see if packet is a TDLS teardown packet */
+			if (ieee80211_is_data(hdr->frame_control) &&
+			    (ieee80211_get_tdls_action(skb, hdr_size) ==
+			     WLAN_TDLS_TEARDOWN))
+				ieee80211_tdls_td_tx_handle(local, sdata, skb,
+							    info->flags);
+			else
+				ieee80211_mgd_conn_tx_status(sdata,
+							     hdr->frame_control,
+							     acked);
 		} else if (ieee80211_is_nullfunc(hdr->frame_control) ||
 			   ieee80211_is_qos_nullfunc(hdr->frame_control)) {
 			cfg80211_probe_status(sdata->dev, hdr->addr1,
@@ -464,73 +514,6 @@ static void ieee80211_report_used_skb(struct ieee80211_local *local,
 }
 
 /*
- * Measure Tx frame completion and removal time for Tx latency statistics
- * calculation. A single Tx frame latency should be measured from when it
- * is entering the Kernel until we receive Tx complete confirmation indication
- * and remove the skb.
- */
-static void ieee80211_tx_latency_end_msrmnt(struct ieee80211_local *local,
-					    struct sk_buff *skb,
-					    struct sta_info *sta,
-					    struct ieee80211_hdr *hdr)
-{
-	u32 msrmnt;
-	u16 tid;
-	u8 *qc;
-	int i, bin_range_count;
-	u32 *bin_ranges;
-	__le16 fc;
-	struct ieee80211_tx_latency_stat *tx_lat;
-	struct ieee80211_tx_latency_bin_ranges *tx_latency;
-	ktime_t skb_arv = skb->tstamp;
-
-	tx_latency = rcu_dereference(local->tx_latency);
-
-	/* assert Tx latency stats are enabled & frame arrived when enabled */
-	if (!tx_latency || !ktime_to_ns(skb_arv))
-		return;
-
-	fc = hdr->frame_control;
-
-	if (!ieee80211_is_data(fc)) /* make sure it is a data frame */
-		return;
-
-	/* get frame tid */
-	if (ieee80211_is_data_qos(hdr->frame_control)) {
-		qc = ieee80211_get_qos_ctl(hdr);
-		tid = qc[0] & IEEE80211_QOS_CTL_TID_MASK;
-	} else {
-		tid = 0;
-	}
-
-	tx_lat = &sta->tx_lat[tid];
-
-	/* Calculate the latency */
-	msrmnt = ktime_to_ms(ktime_sub(ktime_get(), skb_arv));
-
-	if (tx_lat->max < msrmnt) /* update stats */
-		tx_lat->max = msrmnt;
-	tx_lat->counter++;
-	tx_lat->sum += msrmnt;
-
-	if (!tx_lat->bins) /* bins not activated */
-		return;
-
-	/* count how many Tx frames transmitted with the appropriate latency */
-	bin_range_count = tx_latency->n_ranges;
-	bin_ranges = tx_latency->ranges;
-
-	for (i = 0; i < bin_range_count; i++) {
-		if (msrmnt <= bin_ranges[i]) {
-			tx_lat->bins[i]++;
-			break;
-		}
-	}
-	if (i == bin_range_count) /* msrmnt is bigger than the biggest range */
-		tx_lat->bins[i]++;
-}
-
-/*
  * Use a static threshold for now, best value to be determined
  * by testing ...
  * Should it depend on:
@@ -541,10 +524,9 @@ static void ieee80211_tx_latency_end_msrmnt(struct ieee80211_local *local,
 #define STA_LOST_TDLS_PKT_THRESHOLD	10
 #define STA_LOST_TDLS_PKT_TIME		(10*HZ) /* 10secs since last ACK */
 
-static void ieee80211_lost_packet(struct sta_info *sta, struct sk_buff *skb)
+static void ieee80211_lost_packet(struct sta_info *sta,
+				  struct ieee80211_tx_info *info)
 {
-	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))
@@ -571,24 +553,13 @@ static void ieee80211_lost_packet(struct sta_info *sta, struct sk_buff *skb)
 	sta->lost_packets = 0;
 }
 
-void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
+static int ieee80211_tx_get_rates(struct ieee80211_hw *hw,
+				  struct ieee80211_tx_info *info,
+				  int *retry_count)
 {
-	struct sk_buff *skb2;
-	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
-	struct ieee80211_local *local = hw_to_local(hw);
-	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
-	__le16 fc;
-	struct ieee80211_supported_band *sband;
-	struct ieee80211_sub_if_data *sdata;
-	struct net_device *prev_dev = NULL;
-	struct sta_info *sta, *tmp;
-	int retry_count = -1, i;
 	int rates_idx = -1;
-	bool send_to_cooked;
-	bool acked;
-	struct ieee80211_bar *bar;
-	int rtap_len;
-	int shift = 0;
+	int count = -1;
+	int i;
 
 	for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) {
 		if ((info->flags & IEEE80211_TX_CTL_AMPDU) &&
@@ -606,19 +577,105 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 			break;
 		}
 
-		retry_count += info->status.rates[i].count;
+		count += info->status.rates[i].count;
 	}
 	rates_idx = i - 1;
 
-	if (retry_count < 0)
-		retry_count = 0;
+	if (count < 0)
+		count = 0;
+
+	*retry_count = count;
+	return rates_idx;
+}
+
+void ieee80211_tx_status_noskb(struct ieee80211_hw *hw,
+			       struct ieee80211_sta *pubsta,
+			       struct ieee80211_tx_info *info)
+{
+	struct ieee80211_local *local = hw_to_local(hw);
+	struct ieee80211_supported_band *sband;
+	int retry_count;
+	int rates_idx;
+	bool acked, noack_success;
+
+	rates_idx = ieee80211_tx_get_rates(hw, info, &retry_count);
+
+	sband = hw->wiphy->bands[info->band];
+
+	acked = !!(info->flags & IEEE80211_TX_STAT_ACK);
+	noack_success = !!(info->flags & IEEE80211_TX_STAT_NOACK_TRANSMITTED);
+
+	if (pubsta) {
+		struct sta_info *sta;
+
+		sta = container_of(pubsta, struct sta_info, sta);
+
+		if (!acked)
+			sta->tx_retry_failed++;
+		sta->tx_retry_count += retry_count;
+
+		if (acked) {
+			sta->last_rx = jiffies;
+
+			if (sta->lost_packets)
+				sta->lost_packets = 0;
+
+			/* Track when last TDLS packet was ACKed */
+			if (test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH))
+				sta->last_tdls_pkt_time = jiffies;
+		} else {
+			ieee80211_lost_packet(sta, info);
+		}
+
+		rate_control_tx_status_noskb(local, sband, sta, info);
+	}
+
+	if (acked || noack_success) {
+		    local->dot11TransmittedFrameCount++;
+		    if (!pubsta)
+			    local->dot11MulticastTransmittedFrameCount++;
+		    if (retry_count > 0)
+			    local->dot11RetryCount++;
+		    if (retry_count > 1)
+			    local->dot11MultipleRetryCount++;
+	} else {
+		local->dot11FailedCount++;
+	}
+}
+EXPORT_SYMBOL(ieee80211_tx_status_noskb);
+
+void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
+{
+	struct sk_buff *skb2;
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
+	struct ieee80211_local *local = hw_to_local(hw);
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	__le16 fc;
+	struct ieee80211_supported_band *sband;
+	struct ieee80211_sub_if_data *sdata;
+	struct net_device *prev_dev = NULL;
+	struct sta_info *sta;
+	struct rhash_head *tmp;
+	int retry_count;
+	int rates_idx;
+	bool send_to_cooked;
+	bool acked;
+	struct ieee80211_bar *bar;
+	int rtap_len;
+	int shift = 0;
+	int tid = IEEE80211_NUM_TIDS;
+	const struct bucket_table *tbl;
+
+	rates_idx = ieee80211_tx_get_rates(hw, info, &retry_count);
 
 	rcu_read_lock();
 
 	sband = local->hw.wiphy->bands[info->band];
 	fc = hdr->frame_control;
 
-	for_each_sta_info(local, hdr->addr1, sta, tmp) {
+	tbl = rht_dereference_rcu(local->sta_hash.tbl, &local->sta_hash);
+
+	for_each_sta_info(local, tbl, hdr->addr1, sta, tmp) {
 		/* skip wrong virtual interface */
 		if (!ether_addr_equal(hdr->addr2, sta->sdata->vif.addr))
 			continue;
@@ -653,7 +710,7 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 
 		if ((info->flags & IEEE80211_TX_STAT_AMPDU_NO_BACK) &&
 		    (ieee80211_is_data_qos(fc))) {
-			u16 tid, ssn;
+			u16 ssn;
 			u8 *qc;
 
 			qc = ieee80211_get_qos_ctl(hdr);
@@ -662,10 +719,14 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 						& IEEE80211_SCTL_SEQ);
 			ieee80211_send_bar(&sta->sdata->vif, hdr->addr1,
 					   tid, ssn);
+		} else if (ieee80211_is_data_qos(fc)) {
+			u8 *qc = ieee80211_get_qos_ctl(hdr);
+
+			tid = qc[0] & 0xf;
 		}
 
 		if (!acked && ieee80211_is_back_req(fc)) {
-			u16 tid, control;
+			u16 control;
 
 			/*
 			 * BAR failed, store the last SSN and retry sending
@@ -693,6 +754,12 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 			if (!acked)
 				sta->tx_retry_failed++;
 			sta->tx_retry_count += retry_count;
+
+			if (ieee80211_is_data_present(fc)) {
+				if (!acked)
+					sta->tx_msdu_failed[tid]++;
+				sta->tx_msdu_retries[tid] += retry_count;
+			}
 		}
 
 		rate_control_tx_status(local, sband, sta, skb);
@@ -704,7 +771,8 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 
 		if ((sta->sdata->vif.type == NL80211_IFTYPE_STATION) &&
 		    (local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS))
-			ieee80211_sta_tx_notify(sta->sdata, (void *) skb->data, acked);
+			ieee80211_sta_tx_notify(sta->sdata, (void *) skb->data,
+						acked, info->status.tx_time);
 
 		if (local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS) {
 			if (info->flags & IEEE80211_TX_STAT_ACK) {
@@ -715,18 +783,12 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 				if (test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH))
 					sta->last_tdls_pkt_time = jiffies;
 			} else {
-				ieee80211_lost_packet(sta, skb);
+				ieee80211_lost_packet(sta, info);
 			}
 		}
 
 		if (acked)
 			sta->last_ack_signal = info->status.ack_signal;
-
-		/*
-		 * Measure frame removal for tx latency
-		 * statistics calculation
-		 */
-		ieee80211_tx_latency_end_msrmnt(local, skb, sta, hdr);
 	}
 
 	rcu_read_unlock();
@@ -737,10 +799,11 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 	 * Fragments are passed to low-level drivers as separate skbs, so these
 	 * are actually fragments, not frames. Update frame counters only for
 	 * the first fragment of the frame. */
-	if (info->flags & IEEE80211_TX_STAT_ACK) {
+	if ((info->flags & IEEE80211_TX_STAT_ACK) ||
+	    (info->flags & IEEE80211_TX_STAT_NOACK_TRANSMITTED)) {
 		if (ieee80211_is_first_frag(hdr->seq_ctrl)) {
 			local->dot11TransmittedFrameCount++;
-			if (is_multicast_ether_addr(hdr->addr1))
+			if (is_multicast_ether_addr(ieee80211_get_DA(hdr)))
 				local->dot11MulticastTransmittedFrameCount++;
 			if (retry_count > 0)
 				local->dot11RetryCount++;
diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c
index 4ea25dec0698..fff0d864adfa 100644
--- a/net/mac80211/tdls.c
+++ b/net/mac80211/tdls.c
@@ -35,19 +35,135 @@ void ieee80211_tdls_peer_del_work(struct work_struct *wk)
 	mutex_unlock(&local->mtx);
 }
 
-static void ieee80211_tdls_add_ext_capab(struct sk_buff *skb)
+static void ieee80211_tdls_add_ext_capab(struct ieee80211_local *local,
+					 struct sk_buff *skb)
 {
 	u8 *pos = (void *)skb_put(skb, 7);
+	bool chan_switch = local->hw.wiphy->features &
+			   NL80211_FEATURE_TDLS_CHANNEL_SWITCH;
 
 	*pos++ = WLAN_EID_EXT_CAPABILITY;
 	*pos++ = 5; /* len */
 	*pos++ = 0x0;
 	*pos++ = 0x0;
 	*pos++ = 0x0;
-	*pos++ = 0x0;
+	*pos++ = chan_switch ? WLAN_EXT_CAPA4_TDLS_CHAN_SWITCH : 0;
 	*pos++ = WLAN_EXT_CAPA5_TDLS_ENABLED;
 }
 
+static u8
+ieee80211_tdls_add_subband(struct ieee80211_sub_if_data *sdata,
+			   struct sk_buff *skb, u16 start, u16 end,
+			   u16 spacing)
+{
+	u8 subband_cnt = 0, ch_cnt = 0;
+	struct ieee80211_channel *ch;
+	struct cfg80211_chan_def chandef;
+	int i, subband_start;
+
+	for (i = start; i <= end; i += spacing) {
+		if (!ch_cnt)
+			subband_start = i;
+
+		ch = ieee80211_get_channel(sdata->local->hw.wiphy, i);
+		if (ch) {
+			/* we will be active on the channel */
+			cfg80211_chandef_create(&chandef, ch,
+						NL80211_CHAN_NO_HT);
+			if (cfg80211_reg_can_beacon(sdata->local->hw.wiphy,
+						    &chandef,
+						    sdata->wdev.iftype)) {
+				ch_cnt++;
+				/*
+				 * check if the next channel is also part of
+				 * this allowed range
+				 */
+				continue;
+			}
+		}
+
+		/*
+		 * we've reached the end of a range, with allowed channels
+		 * found
+		 */
+		if (ch_cnt) {
+			u8 *pos = skb_put(skb, 2);
+			*pos++ = ieee80211_frequency_to_channel(subband_start);
+			*pos++ = ch_cnt;
+
+			subband_cnt++;
+			ch_cnt = 0;
+		}
+	}
+
+	/* all channels in the requested range are allowed - add them here */
+	if (ch_cnt) {
+		u8 *pos = skb_put(skb, 2);
+		*pos++ = ieee80211_frequency_to_channel(subband_start);
+		*pos++ = ch_cnt;
+
+		subband_cnt++;
+	}
+
+	return subband_cnt;
+}
+
+static void
+ieee80211_tdls_add_supp_channels(struct ieee80211_sub_if_data *sdata,
+				 struct sk_buff *skb)
+{
+	/*
+	 * Add possible channels for TDLS. These are channels that are allowed
+	 * to be active.
+	 */
+	u8 subband_cnt;
+	u8 *pos = skb_put(skb, 2);
+
+	*pos++ = WLAN_EID_SUPPORTED_CHANNELS;
+
+	/*
+	 * 5GHz and 2GHz channels numbers can overlap. Ignore this for now, as
+	 * this doesn't happen in real world scenarios.
+	 */
+
+	/* 2GHz, with 5MHz spacing */
+	subband_cnt = ieee80211_tdls_add_subband(sdata, skb, 2412, 2472, 5);
+
+	/* 5GHz, with 20MHz spacing */
+	subband_cnt += ieee80211_tdls_add_subband(sdata, skb, 5000, 5825, 20);
+
+	/* length */
+	*pos = 2 * subband_cnt;
+}
+
+static void ieee80211_tdls_add_oper_classes(struct ieee80211_sub_if_data *sdata,
+					    struct sk_buff *skb)
+{
+	u8 *pos;
+	u8 op_class;
+
+	if (!ieee80211_chandef_to_operating_class(&sdata->vif.bss_conf.chandef,
+						  &op_class))
+		return;
+
+	pos = skb_put(skb, 4);
+	*pos++ = WLAN_EID_SUPPORTED_REGULATORY_CLASSES;
+	*pos++ = 2; /* len */
+
+	*pos++ = op_class;
+	*pos++ = op_class; /* give current operating class as alternate too */
+}
+
+static void ieee80211_tdls_add_bss_coex_ie(struct sk_buff *skb)
+{
+	u8 *pos = (void *)skb_put(skb, 3);
+
+	*pos++ = WLAN_EID_BSS_COEX_2040;
+	*pos++ = 1; /* len */
+
+	*pos++ = WLAN_BSS_COEX_INFORMATION_REQUEST;
+}
+
 static u16 ieee80211_get_tdls_sta_capab(struct ieee80211_sub_if_data *sdata,
 					u16 status_code)
 {
@@ -95,6 +211,17 @@ static void ieee80211_tdls_add_link_ie(struct ieee80211_sub_if_data *sdata,
 	memcpy(lnkid->resp_sta, rsp_addr, ETH_ALEN);
 }
 
+static void
+ieee80211_tdls_add_aid(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb)
+{
+	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+	u8 *pos = (void *)skb_put(skb, 4);
+
+	*pos++ = WLAN_EID_AID;
+	*pos++ = 2; /* len */
+	put_unaligned_le16(ifmgd->aid, pos);
+}
+
 /* translate numbering in the WMM parameter IE to the mac80211 notation */
 static enum ieee80211_ac_numbers ieee80211_ac_from_wmm(int ac)
 {
@@ -173,23 +300,14 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_supported_band *sband;
 	struct ieee80211_sta_ht_cap ht_cap;
+	struct ieee80211_sta_vht_cap vht_cap;
 	struct sta_info *sta = NULL;
 	size_t offset = 0, noffset;
 	u8 *pos;
 
-	rcu_read_lock();
-
-	/* we should have the peer STA if we're already responding */
-	if (action_code == WLAN_TDLS_SETUP_RESPONSE) {
-		sta = sta_info_get(sdata, peer);
-		if (WARN_ON_ONCE(!sta)) {
-			rcu_read_unlock();
-			return;
-		}
-	}
-
 	ieee80211_add_srates_ie(sdata, skb, false, band);
 	ieee80211_add_ext_srates_ie(sdata, skb, false, band);
+	ieee80211_tdls_add_supp_channels(sdata, skb);
 
 	/* add any custom IEs that go before Extended Capabilities */
 	if (extra_ies_len) {
@@ -209,7 +327,7 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata,
 		offset = noffset;
 	}
 
-	ieee80211_tdls_add_ext_capab(skb);
+	ieee80211_tdls_add_ext_capab(local, skb);
 
 	/* add the QoS element if we support it */
 	if (local->hw.queues >= IEEE80211_NUM_ACS &&
@@ -239,6 +357,19 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata,
 		offset = noffset;
 	}
 
+	rcu_read_lock();
+
+	/* we should have the peer STA if we're already responding */
+	if (action_code == WLAN_TDLS_SETUP_RESPONSE) {
+		sta = sta_info_get(sdata, peer);
+		if (WARN_ON_ONCE(!sta)) {
+			rcu_read_unlock();
+			return;
+		}
+	}
+
+	ieee80211_tdls_add_oper_classes(sdata, skb);
+
 	/*
 	 * with TDLS we can switch channels, and HT-caps are not necessarily
 	 * the same on all bands. The specification limits the setup to a
@@ -246,29 +377,86 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata,
 	 */
 	sband = local->hw.wiphy->bands[band];
 	memcpy(&ht_cap, &sband->ht_cap, sizeof(ht_cap));
+
 	if ((action_code == WLAN_TDLS_SETUP_REQUEST ||
-	     action_code == WLAN_TDLS_SETUP_RESPONSE) &&
-	    ht_cap.ht_supported && (!sta || sta->sta.ht_cap.ht_supported)) {
-		if (action_code == WLAN_TDLS_SETUP_REQUEST) {
-			ieee80211_apply_htcap_overrides(sdata, &ht_cap);
-
-			/* disable SMPS in TDLS initiator */
-			ht_cap.cap |= (WLAN_HT_CAP_SM_PS_DISABLED
-				       << IEEE80211_HT_CAP_SM_PS_SHIFT);
-		} else {
-			/* disable SMPS in TDLS responder */
-			sta->sta.ht_cap.cap |=
-				(WLAN_HT_CAP_SM_PS_DISABLED
-				 << IEEE80211_HT_CAP_SM_PS_SHIFT);
-
-			/* the peer caps are already intersected with our own */
-			memcpy(&ht_cap, &sta->sta.ht_cap, sizeof(ht_cap));
-		}
+	     action_code == WLAN_PUB_ACTION_TDLS_DISCOVER_RES) &&
+	    ht_cap.ht_supported) {
+		ieee80211_apply_htcap_overrides(sdata, &ht_cap);
+
+		/* disable SMPS in TDLS initiator */
+		ht_cap.cap |= WLAN_HT_CAP_SM_PS_DISABLED
+				<< IEEE80211_HT_CAP_SM_PS_SHIFT;
+
+		pos = skb_put(skb, sizeof(struct ieee80211_ht_cap) + 2);
+		ieee80211_ie_build_ht_cap(pos, &ht_cap, ht_cap.cap);
+	} else if (action_code == WLAN_TDLS_SETUP_RESPONSE &&
+		   ht_cap.ht_supported && sta->sta.ht_cap.ht_supported) {
+		/* disable SMPS in TDLS responder */
+		sta->sta.ht_cap.cap |= WLAN_HT_CAP_SM_PS_DISABLED
+					<< IEEE80211_HT_CAP_SM_PS_SHIFT;
+
+		/* the peer caps are already intersected with our own */
+		memcpy(&ht_cap, &sta->sta.ht_cap, sizeof(ht_cap));
 
 		pos = skb_put(skb, sizeof(struct ieee80211_ht_cap) + 2);
 		ieee80211_ie_build_ht_cap(pos, &ht_cap, ht_cap.cap);
 	}
 
+	if (ht_cap.ht_supported &&
+	    (ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40))
+		ieee80211_tdls_add_bss_coex_ie(skb);
+
+	ieee80211_tdls_add_link_ie(sdata, skb, peer, initiator);
+
+	/* add any custom IEs that go before VHT capabilities */
+	if (extra_ies_len) {
+		static const u8 before_vht_cap[] = {
+			WLAN_EID_SUPP_RATES,
+			WLAN_EID_COUNTRY,
+			WLAN_EID_EXT_SUPP_RATES,
+			WLAN_EID_SUPPORTED_CHANNELS,
+			WLAN_EID_RSN,
+			WLAN_EID_EXT_CAPABILITY,
+			WLAN_EID_QOS_CAPA,
+			WLAN_EID_FAST_BSS_TRANSITION,
+			WLAN_EID_TIMEOUT_INTERVAL,
+			WLAN_EID_SUPPORTED_REGULATORY_CLASSES,
+			WLAN_EID_MULTI_BAND,
+		};
+		noffset = ieee80211_ie_split(extra_ies, extra_ies_len,
+					     before_vht_cap,
+					     ARRAY_SIZE(before_vht_cap),
+					     offset);
+		pos = skb_put(skb, noffset - offset);
+		memcpy(pos, extra_ies + offset, noffset - offset);
+		offset = noffset;
+	}
+
+	/* build the VHT-cap similarly to the HT-cap */
+	memcpy(&vht_cap, &sband->vht_cap, sizeof(vht_cap));
+	if ((action_code == WLAN_TDLS_SETUP_REQUEST ||
+	     action_code == WLAN_PUB_ACTION_TDLS_DISCOVER_RES) &&
+	    vht_cap.vht_supported) {
+		ieee80211_apply_vhtcap_overrides(sdata, &vht_cap);
+
+		/* the AID is present only when VHT is implemented */
+		if (action_code == WLAN_TDLS_SETUP_REQUEST)
+			ieee80211_tdls_add_aid(sdata, skb);
+
+		pos = skb_put(skb, sizeof(struct ieee80211_vht_cap) + 2);
+		ieee80211_ie_build_vht_cap(pos, &vht_cap, vht_cap.cap);
+	} else if (action_code == WLAN_TDLS_SETUP_RESPONSE &&
+		   vht_cap.vht_supported && sta->sta.vht_cap.vht_supported) {
+		/* the peer caps are already intersected with our own */
+		memcpy(&vht_cap, &sta->sta.vht_cap, sizeof(vht_cap));
+
+		/* the AID is present only when VHT is implemented */
+		ieee80211_tdls_add_aid(sdata, skb);
+
+		pos = skb_put(skb, sizeof(struct ieee80211_vht_cap) + 2);
+		ieee80211_ie_build_vht_cap(pos, &vht_cap, vht_cap.cap);
+	}
+
 	rcu_read_unlock();
 
 	/* add any remaining IEs */
@@ -278,7 +466,6 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata,
 		memcpy(pos, extra_ies + offset, noffset - offset);
 	}
 
-	ieee80211_tdls_add_link_ie(sdata, skb, peer, initiator);
 }
 
 static void
@@ -291,6 +478,7 @@ ieee80211_tdls_add_setup_cfm_ies(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
 	size_t offset = 0, noffset;
 	struct sta_info *sta, *ap_sta;
+	enum ieee80211_band band = ieee80211_get_sdata_band(sdata);
 	u8 *pos;
 
 	rcu_read_lock();
@@ -350,6 +538,21 @@ ieee80211_tdls_add_setup_cfm_ies(struct ieee80211_sub_if_data *sdata,
 		}
 	}
 
+	ieee80211_tdls_add_link_ie(sdata, skb, peer, initiator);
+
+	/* only include VHT-operation if not on the 2.4GHz band */
+	if (band != IEEE80211_BAND_2GHZ && !ap_sta->sta.vht_cap.vht_supported &&
+	    sta->sta.vht_cap.vht_supported) {
+		struct ieee80211_chanctx_conf *chanctx_conf =
+				rcu_dereference(sdata->vif.chanctx_conf);
+		if (!WARN_ON(!chanctx_conf)) {
+			pos = skb_put(skb, 2 +
+				      sizeof(struct ieee80211_vht_operation));
+			ieee80211_ie_build_vht_oper(pos, &sta->sta.vht_cap,
+						    &chanctx_conf->def);
+		}
+	}
+
 	rcu_read_unlock();
 
 	/* add any remaining IEs */
@@ -358,15 +561,70 @@ ieee80211_tdls_add_setup_cfm_ies(struct ieee80211_sub_if_data *sdata,
 		pos = skb_put(skb, noffset - offset);
 		memcpy(pos, extra_ies + offset, noffset - offset);
 	}
+}
+
+static void
+ieee80211_tdls_add_chan_switch_req_ies(struct ieee80211_sub_if_data *sdata,
+				       struct sk_buff *skb, const u8 *peer,
+				       bool initiator, const u8 *extra_ies,
+				       size_t extra_ies_len, u8 oper_class,
+				       struct cfg80211_chan_def *chandef)
+{
+	struct ieee80211_tdls_data *tf;
+	size_t offset = 0, noffset;
+	u8 *pos;
+
+	if (WARN_ON_ONCE(!chandef))
+		return;
+
+	tf = (void *)skb->data;
+	tf->u.chan_switch_req.target_channel =
+		ieee80211_frequency_to_channel(chandef->chan->center_freq);
+	tf->u.chan_switch_req.oper_class = oper_class;
+
+	if (extra_ies_len) {
+		static const u8 before_lnkie[] = {
+			WLAN_EID_SECONDARY_CHANNEL_OFFSET,
+		};
+		noffset = ieee80211_ie_split(extra_ies, extra_ies_len,
+					     before_lnkie,
+					     ARRAY_SIZE(before_lnkie),
+					     offset);
+		pos = skb_put(skb, noffset - offset);
+		memcpy(pos, extra_ies + offset, noffset - offset);
+		offset = noffset;
+	}
 
 	ieee80211_tdls_add_link_ie(sdata, skb, peer, initiator);
+
+	/* add any remaining IEs */
+	if (extra_ies_len) {
+		noffset = extra_ies_len;
+		pos = skb_put(skb, noffset - offset);
+		memcpy(pos, extra_ies + offset, noffset - offset);
+	}
+}
+
+static void
+ieee80211_tdls_add_chan_switch_resp_ies(struct ieee80211_sub_if_data *sdata,
+					struct sk_buff *skb, const u8 *peer,
+					u16 status_code, bool initiator,
+					const u8 *extra_ies,
+					size_t extra_ies_len)
+{
+	if (status_code == 0)
+		ieee80211_tdls_add_link_ie(sdata, skb, peer, initiator);
+
+	if (extra_ies_len)
+		memcpy(skb_put(skb, extra_ies_len), extra_ies, extra_ies_len);
 }
 
 static void ieee80211_tdls_add_ies(struct ieee80211_sub_if_data *sdata,
 				   struct sk_buff *skb, const u8 *peer,
 				   u8 action_code, u16 status_code,
 				   bool initiator, const u8 *extra_ies,
-				   size_t extra_ies_len)
+				   size_t extra_ies_len, u8 oper_class,
+				   struct cfg80211_chan_def *chandef)
 {
 	switch (action_code) {
 	case WLAN_TDLS_SETUP_REQUEST:
@@ -393,6 +651,18 @@ static void ieee80211_tdls_add_ies(struct ieee80211_sub_if_data *sdata,
 		if (status_code == 0 || action_code == WLAN_TDLS_TEARDOWN)
 			ieee80211_tdls_add_link_ie(sdata, skb, peer, initiator);
 		break;
+	case WLAN_TDLS_CHANNEL_SWITCH_REQUEST:
+		ieee80211_tdls_add_chan_switch_req_ies(sdata, skb, peer,
+						       initiator, extra_ies,
+						       extra_ies_len,
+						       oper_class, chandef);
+		break;
+	case WLAN_TDLS_CHANNEL_SWITCH_RESPONSE:
+		ieee80211_tdls_add_chan_switch_resp_ies(sdata, skb, peer,
+							status_code,
+							initiator, extra_ies,
+							extra_ies_len);
+		break;
 	}
 
 }
@@ -459,6 +729,19 @@ ieee80211_prep_tdls_encap_data(struct wiphy *wiphy, struct net_device *dev,
 		skb_put(skb, sizeof(tf->u.discover_req));
 		tf->u.discover_req.dialog_token = dialog_token;
 		break;
+	case WLAN_TDLS_CHANNEL_SWITCH_REQUEST:
+		tf->category = WLAN_CATEGORY_TDLS;
+		tf->action_code = WLAN_TDLS_CHANNEL_SWITCH_REQUEST;
+
+		skb_put(skb, sizeof(tf->u.chan_switch_req));
+		break;
+	case WLAN_TDLS_CHANNEL_SWITCH_RESPONSE:
+		tf->category = WLAN_CATEGORY_TDLS;
+		tf->action_code = WLAN_TDLS_CHANNEL_SWITCH_RESPONSE;
+
+		skb_put(skb, sizeof(tf->u.chan_switch_resp));
+		tf->u.chan_switch_resp.status_code = cpu_to_le16(status_code);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -502,32 +785,37 @@ ieee80211_prep_tdls_direct(struct wiphy *wiphy, struct net_device *dev,
 	return 0;
 }
 
-static int
-ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev,
-				const u8 *peer, u8 action_code,
-				u8 dialog_token, u16 status_code,
-				u32 peer_capability, bool initiator,
-				const u8 *extra_ies, size_t extra_ies_len)
+static struct sk_buff *
+ieee80211_tdls_build_mgmt_packet_data(struct ieee80211_sub_if_data *sdata,
+				      const u8 *peer, u8 action_code,
+				      u8 dialog_token, u16 status_code,
+				      bool initiator, const u8 *extra_ies,
+				      size_t extra_ies_len, u8 oper_class,
+				      struct cfg80211_chan_def *chandef)
 {
-	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;
-	struct sta_info *sta;
+	struct sk_buff *skb;
 	int ret;
 
-	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 */
-			    26 + /* max(WMM-info, WMM-param) */
-			    2 + max(sizeof(struct ieee80211_ht_cap),
-				    sizeof(struct ieee80211_ht_operation)) +
-			    extra_ies_len +
-			    sizeof(struct ieee80211_tdls_lnkie));
+	skb = netdev_alloc_skb(sdata->dev,
+			       local->hw.extra_tx_headroom +
+			       max(sizeof(struct ieee80211_mgmt),
+				   sizeof(struct ieee80211_tdls_data)) +
+			       50 + /* supported rates */
+			       7 + /* ext capab */
+			       26 + /* max(WMM-info, WMM-param) */
+			       2 + max(sizeof(struct ieee80211_ht_cap),
+				       sizeof(struct ieee80211_ht_operation)) +
+			       2 + max(sizeof(struct ieee80211_vht_cap),
+				       sizeof(struct ieee80211_vht_operation)) +
+			       50 + /* supported channels */
+			       3 + /* 40/20 BSS coex */
+			       4 + /* AID */
+			       4 + /* oper classes */
+			       extra_ies_len +
+			       sizeof(struct ieee80211_tdls_lnkie));
 	if (!skb)
-		return -ENOMEM;
+		return NULL;
 
 	skb_reserve(skb, local->hw.extra_tx_headroom);
 
@@ -537,16 +825,18 @@ ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev,
 	case WLAN_TDLS_SETUP_CONFIRM:
 	case WLAN_TDLS_TEARDOWN:
 	case WLAN_TDLS_DISCOVERY_REQUEST:
-		ret = ieee80211_prep_tdls_encap_data(wiphy, dev, peer,
+	case WLAN_TDLS_CHANNEL_SWITCH_REQUEST:
+	case WLAN_TDLS_CHANNEL_SWITCH_RESPONSE:
+		ret = ieee80211_prep_tdls_encap_data(local->hw.wiphy,
+						     sdata->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,
+		ret = ieee80211_prep_tdls_direct(local->hw.wiphy, sdata->dev,
+						 peer, action_code,
 						 dialog_token, status_code,
 						 skb);
-		send_direct = true;
 		break;
 	default:
 		ret = -ENOTSUPP;
@@ -556,14 +846,40 @@ ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev,
 	if (ret < 0)
 		goto fail;
 
+	ieee80211_tdls_add_ies(sdata, skb, peer, action_code, status_code,
+			       initiator, extra_ies, extra_ies_len, oper_class,
+			       chandef);
+	return skb;
+
+fail:
+	dev_kfree_skb(skb);
+	return NULL;
+}
+
+static int
+ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev,
+				const u8 *peer, u8 action_code, u8 dialog_token,
+				u16 status_code, u32 peer_capability,
+				bool initiator, const u8 *extra_ies,
+				size_t extra_ies_len, u8 oper_class,
+				struct cfg80211_chan_def *chandef)
+{
+	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	struct sk_buff *skb = NULL;
+	struct sta_info *sta;
+	u32 flags = 0;
+	int ret = 0;
+
 	rcu_read_lock();
 	sta = sta_info_get(sdata, peer);
 
 	/* infer the initiator if we can, to support old userspace */
 	switch (action_code) {
 	case WLAN_TDLS_SETUP_REQUEST:
-		if (sta)
+		if (sta) {
 			set_sta_flag(sta, WLAN_STA_TDLS_INITIATOR);
+			sta->sta.tdls_initiator = false;
+		}
 		/* fall-through */
 	case WLAN_TDLS_SETUP_CONFIRM:
 	case WLAN_TDLS_DISCOVERY_REQUEST:
@@ -575,13 +891,17 @@ ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev,
 		 * Make the last packet sent take effect for the initiator
 		 * value.
 		 */
-		if (sta)
+		if (sta) {
 			clear_sta_flag(sta, WLAN_STA_TDLS_INITIATOR);
+			sta->sta.tdls_initiator = true;
+		}
 		/* fall-through */
 	case WLAN_PUB_ACTION_TDLS_DISCOVER_RES:
 		initiator = false;
 		break;
 	case WLAN_TDLS_TEARDOWN:
+	case WLAN_TDLS_CHANNEL_SWITCH_REQUEST:
+	case WLAN_TDLS_CHANNEL_SWITCH_RESPONSE:
 		/* any value is ok */
 		break;
 	default:
@@ -596,9 +916,17 @@ ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev,
 	if (ret < 0)
 		goto fail;
 
-	ieee80211_tdls_add_ies(sdata, skb, peer, action_code, status_code,
-			       initiator, extra_ies, extra_ies_len);
-	if (send_direct) {
+	skb = ieee80211_tdls_build_mgmt_packet_data(sdata, peer, action_code,
+						    dialog_token, status_code,
+						    initiator, extra_ies,
+						    extra_ies_len, oper_class,
+						    chandef);
+	if (!skb) {
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	if (action_code == WLAN_PUB_ACTION_TDLS_DISCOVER_RES) {
 		ieee80211_tx_skb(sdata, skb);
 		return 0;
 	}
@@ -619,9 +947,43 @@ ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev,
 		break;
 	}
 
+	/*
+	 * Set the WLAN_TDLS_TEARDOWN flag to indicate a teardown in progress.
+	 * Later, if no ACK is returned from peer, we will re-send the teardown
+	 * packet through the AP.
+	 */
+	if ((action_code == WLAN_TDLS_TEARDOWN) &&
+	    (sdata->local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS)) {
+		bool try_resend; /* Should we keep skb for possible resend */
+
+		/* If not sending directly to peer - no point in keeping skb */
+		rcu_read_lock();
+		sta = sta_info_get(sdata, peer);
+		try_resend = sta && test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH);
+		rcu_read_unlock();
+
+		spin_lock_bh(&sdata->u.mgd.teardown_lock);
+		if (try_resend && !sdata->u.mgd.teardown_skb) {
+			/* Mark it as requiring TX status callback  */
+			flags |= IEEE80211_TX_CTL_REQ_TX_STATUS |
+				 IEEE80211_TX_INTFL_MLME_CONN_TX;
+
+			/*
+			 * skb is copied since mac80211 will later set
+			 * properties that might not be the same as the AP,
+			 * such as encryption, QoS, addresses, etc.
+			 *
+			 * No problem if skb_copy() fails, so no need to check.
+			 */
+			sdata->u.mgd.teardown_skb = skb_copy(skb, GFP_ATOMIC);
+			sdata->u.mgd.orig_teardown_skb = skb;
+		}
+		spin_unlock_bh(&sdata->u.mgd.teardown_lock);
+	}
+
 	/* disable bottom halves when entering the Tx path */
 	local_bh_disable();
-	ret = ieee80211_subif_start_xmit(skb, dev);
+	__ieee80211_subif_start_xmit(skb, dev, flags);
 	local_bh_enable();
 
 	return ret;
@@ -647,7 +1009,7 @@ ieee80211_tdls_mgmt_setup(struct wiphy *wiphy, struct net_device *dev,
 	if (!is_zero_ether_addr(sdata->u.mgd.tdls_peer) &&
 	    !ether_addr_equal(sdata->u.mgd.tdls_peer, peer)) {
 		ret = -EBUSY;
-		goto exit;
+		goto out_unlock;
 	}
 
 	/*
@@ -662,26 +1024,34 @@ ieee80211_tdls_mgmt_setup(struct wiphy *wiphy, struct net_device *dev,
 		if (!sta_info_get(sdata, peer)) {
 			rcu_read_unlock();
 			ret = -ENOLINK;
-			goto exit;
+			goto out_unlock;
 		}
 		rcu_read_unlock();
 	}
 
-	ieee80211_flush_queues(local, sdata);
+	ieee80211_flush_queues(local, sdata, false);
+	memcpy(sdata->u.mgd.tdls_peer, peer, ETH_ALEN);
+	mutex_unlock(&local->mtx);
 
+	/* we cannot take the mutex while preparing the setup packet */
 	ret = ieee80211_tdls_prep_mgmt_packet(wiphy, dev, peer, action_code,
 					      dialog_token, status_code,
 					      peer_capability, initiator,
-					      extra_ies, extra_ies_len);
-	if (ret < 0)
-		goto exit;
+					      extra_ies, extra_ies_len, 0,
+					      NULL);
+	if (ret < 0) {
+		mutex_lock(&local->mtx);
+		eth_zero_addr(sdata->u.mgd.tdls_peer);
+		mutex_unlock(&local->mtx);
+		return ret;
+	}
 
-	memcpy(sdata->u.mgd.tdls_peer, peer, ETH_ALEN);
 	ieee80211_queue_delayed_work(&sdata->local->hw,
 				     &sdata->u.mgd.tdls_peer_del_work,
 				     TDLS_PEER_SETUP_TIMEOUT);
+	return 0;
 
-exit:
+out_unlock:
 	mutex_unlock(&local->mtx);
 	return ret;
 }
@@ -706,12 +1076,13 @@ ieee80211_tdls_mgmt_teardown(struct wiphy *wiphy, struct net_device *dev,
 	 */
 	ieee80211_stop_vif_queues(local, sdata,
 				  IEEE80211_QUEUE_STOP_REASON_TDLS_TEARDOWN);
-	ieee80211_flush_queues(local, sdata);
+	ieee80211_flush_queues(local, sdata, false);
 
 	ret = ieee80211_tdls_prep_mgmt_packet(wiphy, dev, peer, action_code,
 					      dialog_token, status_code,
 					      peer_capability, initiator,
-					      extra_ies, extra_ies_len);
+					      extra_ies, extra_ies_len, 0,
+					      NULL);
 	if (ret < 0)
 		sdata_err(sdata, "Failed sending TDLS teardown packet %d\n",
 			  ret);
@@ -781,7 +1152,7 @@ int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev,
 						      status_code,
 						      peer_capability,
 						      initiator, extra_ies,
-						      extra_ies_len);
+						      extra_ies_len, 0, NULL);
 		break;
 	default:
 		ret = -EOPNOTSUPP;
@@ -851,7 +1222,7 @@ int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev,
 		 */
 		tasklet_kill(&local->tx_pending_tasklet);
 		/* flush a potentially queued teardown packet */
-		ieee80211_flush_queues(local, sdata);
+		ieee80211_flush_queues(local, sdata, false);
 
 		ret = sta_info_destroy_addr(sdata, peer);
 		break;
@@ -884,3 +1255,480 @@ void ieee80211_tdls_oper_request(struct ieee80211_vif *vif, const u8 *peer,
 	cfg80211_tdls_oper_request(sdata->dev, peer, oper, reason_code, gfp);
 }
 EXPORT_SYMBOL(ieee80211_tdls_oper_request);
+
+static void
+iee80211_tdls_add_ch_switch_timing(u8 *buf, u16 switch_time, u16 switch_timeout)
+{
+	struct ieee80211_ch_switch_timing *ch_sw;
+
+	*buf++ = WLAN_EID_CHAN_SWITCH_TIMING;
+	*buf++ = sizeof(struct ieee80211_ch_switch_timing);
+
+	ch_sw = (void *)buf;
+	ch_sw->switch_time = cpu_to_le16(switch_time);
+	ch_sw->switch_timeout = cpu_to_le16(switch_timeout);
+}
+
+/* find switch timing IE in SKB ready for Tx */
+static const u8 *ieee80211_tdls_find_sw_timing_ie(struct sk_buff *skb)
+{
+	struct ieee80211_tdls_data *tf;
+	const u8 *ie_start;
+
+	/*
+	 * Get the offset for the new location of the switch timing IE.
+	 * The SKB network header will now point to the "payload_type"
+	 * element of the TDLS data frame struct.
+	 */
+	tf = container_of(skb->data + skb_network_offset(skb),
+			  struct ieee80211_tdls_data, payload_type);
+	ie_start = tf->u.chan_switch_req.variable;
+	return cfg80211_find_ie(WLAN_EID_CHAN_SWITCH_TIMING, ie_start,
+				skb->len - (ie_start - skb->data));
+}
+
+static struct sk_buff *
+ieee80211_tdls_ch_sw_tmpl_get(struct sta_info *sta, u8 oper_class,
+			      struct cfg80211_chan_def *chandef,
+			      u32 *ch_sw_tm_ie_offset)
+{
+	struct ieee80211_sub_if_data *sdata = sta->sdata;
+	u8 extra_ies[2 + sizeof(struct ieee80211_sec_chan_offs_ie) +
+		     2 + sizeof(struct ieee80211_ch_switch_timing)];
+	int extra_ies_len = 2 + sizeof(struct ieee80211_ch_switch_timing);
+	u8 *pos = extra_ies;
+	struct sk_buff *skb;
+
+	/*
+	 * if chandef points to a wide channel add a Secondary-Channel
+	 * Offset information element
+	 */
+	if (chandef->width == NL80211_CHAN_WIDTH_40) {
+		struct ieee80211_sec_chan_offs_ie *sec_chan_ie;
+		bool ht40plus;
+
+		*pos++ = WLAN_EID_SECONDARY_CHANNEL_OFFSET;
+		*pos++ = sizeof(*sec_chan_ie);
+		sec_chan_ie = (void *)pos;
+
+		ht40plus = cfg80211_get_chandef_type(chandef) ==
+							NL80211_CHAN_HT40PLUS;
+		sec_chan_ie->sec_chan_offs = ht40plus ?
+					     IEEE80211_HT_PARAM_CHA_SEC_ABOVE :
+					     IEEE80211_HT_PARAM_CHA_SEC_BELOW;
+		pos += sizeof(*sec_chan_ie);
+
+		extra_ies_len += 2 + sizeof(struct ieee80211_sec_chan_offs_ie);
+	}
+
+	/* just set the values to 0, this is a template */
+	iee80211_tdls_add_ch_switch_timing(pos, 0, 0);
+
+	skb = ieee80211_tdls_build_mgmt_packet_data(sdata, sta->sta.addr,
+					      WLAN_TDLS_CHANNEL_SWITCH_REQUEST,
+					      0, 0, !sta->sta.tdls_initiator,
+					      extra_ies, extra_ies_len,
+					      oper_class, chandef);
+	if (!skb)
+		return NULL;
+
+	skb = ieee80211_build_data_template(sdata, skb, 0);
+	if (IS_ERR(skb)) {
+		tdls_dbg(sdata, "Failed building TDLS channel switch frame\n");
+		return NULL;
+	}
+
+	if (ch_sw_tm_ie_offset) {
+		const u8 *tm_ie = ieee80211_tdls_find_sw_timing_ie(skb);
+
+		if (!tm_ie) {
+			tdls_dbg(sdata, "No switch timing IE in TDLS switch\n");
+			dev_kfree_skb_any(skb);
+			return NULL;
+		}
+
+		*ch_sw_tm_ie_offset = tm_ie - skb->data;
+	}
+
+	tdls_dbg(sdata,
+		 "TDLS channel switch request template for %pM ch %d width %d\n",
+		 sta->sta.addr, chandef->chan->center_freq, chandef->width);
+	return skb;
+}
+
+int
+ieee80211_tdls_channel_switch(struct wiphy *wiphy, struct net_device *dev,
+			      const u8 *addr, u8 oper_class,
+			      struct cfg80211_chan_def *chandef)
+{
+	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	struct ieee80211_local *local = sdata->local;
+	struct sta_info *sta;
+	struct sk_buff *skb = NULL;
+	u32 ch_sw_tm_ie;
+	int ret;
+
+	mutex_lock(&local->sta_mtx);
+	sta = sta_info_get(sdata, addr);
+	if (!sta) {
+		tdls_dbg(sdata,
+			 "Invalid TDLS peer %pM for channel switch request\n",
+			 addr);
+		ret = -ENOENT;
+		goto out;
+	}
+
+	if (!test_sta_flag(sta, WLAN_STA_TDLS_CHAN_SWITCH)) {
+		tdls_dbg(sdata, "TDLS channel switch unsupported by %pM\n",
+			 addr);
+		ret = -ENOTSUPP;
+		goto out;
+	}
+
+	skb = ieee80211_tdls_ch_sw_tmpl_get(sta, oper_class, chandef,
+					    &ch_sw_tm_ie);
+	if (!skb) {
+		ret = -ENOENT;
+		goto out;
+	}
+
+	ret = drv_tdls_channel_switch(local, sdata, &sta->sta, oper_class,
+				      chandef, skb, ch_sw_tm_ie);
+	if (!ret)
+		set_sta_flag(sta, WLAN_STA_TDLS_OFF_CHANNEL);
+
+out:
+	mutex_unlock(&local->sta_mtx);
+	dev_kfree_skb_any(skb);
+	return ret;
+}
+
+void
+ieee80211_tdls_cancel_channel_switch(struct wiphy *wiphy,
+				     struct net_device *dev,
+				     const u8 *addr)
+{
+	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	struct ieee80211_local *local = sdata->local;
+	struct sta_info *sta;
+
+	mutex_lock(&local->sta_mtx);
+	sta = sta_info_get(sdata, addr);
+	if (!sta) {
+		tdls_dbg(sdata,
+			 "Invalid TDLS peer %pM for channel switch cancel\n",
+			 addr);
+		goto out;
+	}
+
+	if (!test_sta_flag(sta, WLAN_STA_TDLS_OFF_CHANNEL)) {
+		tdls_dbg(sdata, "TDLS channel switch not initiated by %pM\n",
+			 addr);
+		goto out;
+	}
+
+	drv_tdls_cancel_channel_switch(local, sdata, &sta->sta);
+	clear_sta_flag(sta, WLAN_STA_TDLS_OFF_CHANNEL);
+
+out:
+	mutex_unlock(&local->sta_mtx);
+}
+
+static struct sk_buff *
+ieee80211_tdls_ch_sw_resp_tmpl_get(struct sta_info *sta,
+				   u32 *ch_sw_tm_ie_offset)
+{
+	struct ieee80211_sub_if_data *sdata = sta->sdata;
+	struct sk_buff *skb;
+	u8 extra_ies[2 + sizeof(struct ieee80211_ch_switch_timing)];
+
+	/* initial timing are always zero in the template */
+	iee80211_tdls_add_ch_switch_timing(extra_ies, 0, 0);
+
+	skb = ieee80211_tdls_build_mgmt_packet_data(sdata, sta->sta.addr,
+					WLAN_TDLS_CHANNEL_SWITCH_RESPONSE,
+					0, 0, !sta->sta.tdls_initiator,
+					extra_ies, sizeof(extra_ies), 0, NULL);
+	if (!skb)
+		return NULL;
+
+	skb = ieee80211_build_data_template(sdata, skb, 0);
+	if (IS_ERR(skb)) {
+		tdls_dbg(sdata,
+			 "Failed building TDLS channel switch resp frame\n");
+		return NULL;
+	}
+
+	if (ch_sw_tm_ie_offset) {
+		const u8 *tm_ie = ieee80211_tdls_find_sw_timing_ie(skb);
+
+		if (!tm_ie) {
+			tdls_dbg(sdata,
+				 "No switch timing IE in TDLS switch resp\n");
+			dev_kfree_skb_any(skb);
+			return NULL;
+		}
+
+		*ch_sw_tm_ie_offset = tm_ie - skb->data;
+	}
+
+	tdls_dbg(sdata, "TDLS get channel switch response template for %pM\n",
+		 sta->sta.addr);
+	return skb;
+}
+
+static int
+ieee80211_process_tdls_channel_switch_resp(struct ieee80211_sub_if_data *sdata,
+					   struct sk_buff *skb)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee802_11_elems elems;
+	struct sta_info *sta;
+	struct ieee80211_tdls_data *tf = (void *)skb->data;
+	bool local_initiator;
+	struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb);
+	int baselen = offsetof(typeof(*tf), u.chan_switch_resp.variable);
+	struct ieee80211_tdls_ch_sw_params params = {};
+	int ret;
+
+	params.action_code = WLAN_TDLS_CHANNEL_SWITCH_RESPONSE;
+	params.timestamp = rx_status->device_timestamp;
+
+	if (skb->len < baselen) {
+		tdls_dbg(sdata, "TDLS channel switch resp too short: %d\n",
+			 skb->len);
+		return -EINVAL;
+	}
+
+	mutex_lock(&local->sta_mtx);
+	sta = sta_info_get(sdata, tf->sa);
+	if (!sta || !test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH)) {
+		tdls_dbg(sdata, "TDLS chan switch from non-peer sta %pM\n",
+			 tf->sa);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	params.sta = &sta->sta;
+	params.status = le16_to_cpu(tf->u.chan_switch_resp.status_code);
+	if (params.status != 0) {
+		ret = 0;
+		goto call_drv;
+	}
+
+	ieee802_11_parse_elems(tf->u.chan_switch_resp.variable,
+			       skb->len - baselen, false, &elems);
+	if (elems.parse_error) {
+		tdls_dbg(sdata, "Invalid IEs in TDLS channel switch resp\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (!elems.ch_sw_timing || !elems.lnk_id) {
+		tdls_dbg(sdata, "TDLS channel switch resp - missing IEs\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/* validate the initiator is set correctly */
+	local_initiator =
+		!memcmp(elems.lnk_id->init_sta, sdata->vif.addr, ETH_ALEN);
+	if (local_initiator == sta->sta.tdls_initiator) {
+		tdls_dbg(sdata, "TDLS chan switch invalid lnk-id initiator\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	params.switch_time = le16_to_cpu(elems.ch_sw_timing->switch_time);
+	params.switch_timeout = le16_to_cpu(elems.ch_sw_timing->switch_timeout);
+
+	params.tmpl_skb =
+		ieee80211_tdls_ch_sw_resp_tmpl_get(sta, &params.ch_sw_tm_ie);
+	if (!params.tmpl_skb) {
+		ret = -ENOENT;
+		goto out;
+	}
+
+call_drv:
+	drv_tdls_recv_channel_switch(sdata->local, sdata, &params);
+
+	tdls_dbg(sdata,
+		 "TDLS channel switch response received from %pM status %d\n",
+		 tf->sa, params.status);
+
+out:
+	mutex_unlock(&local->sta_mtx);
+	dev_kfree_skb_any(params.tmpl_skb);
+	return ret;
+}
+
+static int
+ieee80211_process_tdls_channel_switch_req(struct ieee80211_sub_if_data *sdata,
+					  struct sk_buff *skb)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee802_11_elems elems;
+	struct cfg80211_chan_def chandef;
+	struct ieee80211_channel *chan;
+	enum nl80211_channel_type chan_type;
+	int freq;
+	u8 target_channel, oper_class;
+	bool local_initiator;
+	struct sta_info *sta;
+	enum ieee80211_band band;
+	struct ieee80211_tdls_data *tf = (void *)skb->data;
+	struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb);
+	int baselen = offsetof(typeof(*tf), u.chan_switch_req.variable);
+	struct ieee80211_tdls_ch_sw_params params = {};
+	int ret = 0;
+
+	params.action_code = WLAN_TDLS_CHANNEL_SWITCH_REQUEST;
+	params.timestamp = rx_status->device_timestamp;
+
+	if (skb->len < baselen) {
+		tdls_dbg(sdata, "TDLS channel switch req too short: %d\n",
+			 skb->len);
+		return -EINVAL;
+	}
+
+	target_channel = tf->u.chan_switch_req.target_channel;
+	oper_class = tf->u.chan_switch_req.oper_class;
+
+	/*
+	 * We can't easily infer the channel band. The operating class is
+	 * ambiguous - there are multiple tables (US/Europe/JP/Global). The
+	 * solution here is to treat channels with number >14 as 5GHz ones,
+	 * and specifically check for the (oper_class, channel) combinations
+	 * where this doesn't hold. These are thankfully unique according to
+	 * IEEE802.11-2012.
+	 * We consider only the 2GHz and 5GHz bands and 20MHz+ channels as
+	 * valid here.
+	 */
+	if ((oper_class == 112 || oper_class == 2 || oper_class == 3 ||
+	     oper_class == 4 || oper_class == 5 || oper_class == 6) &&
+	     target_channel < 14)
+		band = IEEE80211_BAND_5GHZ;
+	else
+		band = target_channel < 14 ? IEEE80211_BAND_2GHZ :
+					     IEEE80211_BAND_5GHZ;
+
+	freq = ieee80211_channel_to_frequency(target_channel, band);
+	if (freq == 0) {
+		tdls_dbg(sdata, "Invalid channel in TDLS chan switch: %d\n",
+			 target_channel);
+		return -EINVAL;
+	}
+
+	chan = ieee80211_get_channel(sdata->local->hw.wiphy, freq);
+	if (!chan) {
+		tdls_dbg(sdata,
+			 "Unsupported channel for TDLS chan switch: %d\n",
+			 target_channel);
+		return -EINVAL;
+	}
+
+	ieee802_11_parse_elems(tf->u.chan_switch_req.variable,
+			       skb->len - baselen, false, &elems);
+	if (elems.parse_error) {
+		tdls_dbg(sdata, "Invalid IEs in TDLS channel switch req\n");
+		return -EINVAL;
+	}
+
+	if (!elems.ch_sw_timing || !elems.lnk_id) {
+		tdls_dbg(sdata, "TDLS channel switch req - missing IEs\n");
+		return -EINVAL;
+	}
+
+	mutex_lock(&local->sta_mtx);
+	sta = sta_info_get(sdata, tf->sa);
+	if (!sta || !test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH)) {
+		tdls_dbg(sdata, "TDLS chan switch from non-peer sta %pM\n",
+			 tf->sa);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	params.sta = &sta->sta;
+
+	/* validate the initiator is set correctly */
+	local_initiator =
+		!memcmp(elems.lnk_id->init_sta, sdata->vif.addr, ETH_ALEN);
+	if (local_initiator == sta->sta.tdls_initiator) {
+		tdls_dbg(sdata, "TDLS chan switch invalid lnk-id initiator\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (!sta->sta.ht_cap.ht_supported) {
+		chan_type = NL80211_CHAN_NO_HT;
+	} else if (!elems.sec_chan_offs) {
+		chan_type = NL80211_CHAN_HT20;
+	} else {
+		switch (elems.sec_chan_offs->sec_chan_offs) {
+		case IEEE80211_HT_PARAM_CHA_SEC_ABOVE:
+			chan_type = NL80211_CHAN_HT40PLUS;
+			break;
+		case IEEE80211_HT_PARAM_CHA_SEC_BELOW:
+			chan_type = NL80211_CHAN_HT40MINUS;
+			break;
+		default:
+			chan_type = NL80211_CHAN_HT20;
+			break;
+		}
+	}
+
+	cfg80211_chandef_create(&chandef, chan, chan_type);
+	params.chandef = &chandef;
+
+	params.switch_time = le16_to_cpu(elems.ch_sw_timing->switch_time);
+	params.switch_timeout = le16_to_cpu(elems.ch_sw_timing->switch_timeout);
+
+	params.tmpl_skb =
+		ieee80211_tdls_ch_sw_resp_tmpl_get(sta,
+						   &params.ch_sw_tm_ie);
+	if (!params.tmpl_skb) {
+		ret = -ENOENT;
+		goto out;
+	}
+
+	drv_tdls_recv_channel_switch(sdata->local, sdata, &params);
+
+	tdls_dbg(sdata,
+		 "TDLS ch switch request received from %pM ch %d width %d\n",
+		 tf->sa, params.chandef->chan->center_freq,
+		 params.chandef->width);
+out:
+	mutex_unlock(&local->sta_mtx);
+	dev_kfree_skb_any(params.tmpl_skb);
+	return ret;
+}
+
+void ieee80211_process_tdls_channel_switch(struct ieee80211_sub_if_data *sdata,
+					   struct sk_buff *skb)
+{
+	struct ieee80211_tdls_data *tf = (void *)skb->data;
+	struct wiphy *wiphy = sdata->local->hw.wiphy;
+
+	/* make sure the driver supports it */
+	if (!(wiphy->features & NL80211_FEATURE_TDLS_CHANNEL_SWITCH))
+		return;
+
+	/* we want to access the entire packet */
+	if (skb_linearize(skb))
+		return;
+	/*
+	 * The packet/size was already validated by mac80211 Rx path, only look
+	 * at the action type.
+	 */
+	switch (tf->action_code) {
+	case WLAN_TDLS_CHANNEL_SWITCH_REQUEST:
+		ieee80211_process_tdls_channel_switch_req(sdata, skb);
+		break;
+	case WLAN_TDLS_CHANNEL_SWITCH_RESPONSE:
+		ieee80211_process_tdls_channel_switch_resp(sdata, skb);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return;
+	}
+}
diff --git a/net/mac80211/trace.c b/net/mac80211/trace.c
index 386e45d8a958..edfe0c170a1c 100644
--- a/net/mac80211/trace.c
+++ b/net/mac80211/trace.c
@@ -8,6 +8,7 @@
 #include "debug.h"
 #define CREATE_TRACE_POINTS
 #include "trace.h"
+#include "trace_msg.h"
 
 #ifdef CONFIG_MAC80211_MESSAGE_TRACING
 void __sdata_info(const char *fmt, ...)
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index 38fae7ebe984..4c2e7690226a 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -16,6 +16,7 @@
 
 #define STA_ENTRY	__array(char, sta_addr, ETH_ALEN)
 #define STA_ASSIGN	(sta ? memcpy(__entry->sta_addr, sta->addr, ETH_ALEN) : memset(__entry->sta_addr, 0, ETH_ALEN))
+#define STA_NAMED_ASSIGN(s)	memcpy(__entry->sta_addr, (s)->addr, ETH_ALEN)
 #define STA_PR_FMT	" sta:%pM"
 #define STA_PR_ARG	__entry->sta_addr
 
@@ -595,14 +596,33 @@ DEFINE_EVENT(local_sdata_evt, drv_sched_scan_stop,
 	TP_ARGS(local, sdata)
 );
 
-DEFINE_EVENT(local_only_evt, drv_sw_scan_start,
-	TP_PROTO(struct ieee80211_local *local),
-	TP_ARGS(local)
+TRACE_EVENT(drv_sw_scan_start,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 const u8 *mac_addr),
+
+	TP_ARGS(local, sdata, mac_addr),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		VIF_ENTRY
+		__array(char, mac_addr, ETH_ALEN)
+	),
+
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		VIF_ASSIGN;
+		memcpy(__entry->mac_addr, mac_addr, ETH_ALEN);
+	),
+
+	TP_printk(LOCAL_PR_FMT ", " VIF_PR_FMT ", addr:%pM",
+		  LOCAL_PR_ARG, VIF_PR_ARG, __entry->mac_addr)
 );
 
-DEFINE_EVENT(local_only_evt, drv_sw_scan_complete,
-	TP_PROTO(struct ieee80211_local *local),
-	TP_ARGS(local)
+DEFINE_EVENT(local_sdata_evt, drv_sw_scan_complete,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata),
+	TP_ARGS(local, sdata)
 );
 
 TRACE_EVENT(drv_get_stats,
@@ -805,6 +825,13 @@ DECLARE_EVENT_CLASS(sta_event,
 	)
 );
 
+DEFINE_EVENT(sta_event, drv_sta_statistics,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 struct ieee80211_sta *sta),
+	TP_ARGS(local, sdata, sta)
+);
+
 DEFINE_EVENT(sta_event, drv_sta_add,
 	TP_PROTO(struct ieee80211_local *local,
 		 struct ieee80211_sub_if_data *sdata,
@@ -826,6 +853,13 @@ DEFINE_EVENT(sta_event, drv_sta_pre_rcu_remove,
 	TP_ARGS(local, sdata, sta)
 );
 
+DEFINE_EVENT(sta_event, drv_sta_rate_tbl_update,
+	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,
 	TP_PROTO(struct ieee80211_local *local,
 		 struct ieee80211_sub_if_data *sdata,
@@ -987,29 +1021,34 @@ TRACE_EVENT(drv_flush,
 
 TRACE_EVENT(drv_channel_switch,
 	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
 		 struct ieee80211_channel_switch *ch_switch),
 
-	TP_ARGS(local, ch_switch),
+	TP_ARGS(local, sdata, ch_switch),
 
 	TP_STRUCT__entry(
 		LOCAL_ENTRY
+		VIF_ENTRY
 		CHANDEF_ENTRY
 		__field(u64, timestamp)
+		__field(u32, device_timestamp)
 		__field(bool, block_tx)
 		__field(u8, count)
 	),
 
 	TP_fast_assign(
 		LOCAL_ASSIGN;
+		VIF_ASSIGN;
 		CHANDEF_ASSIGN(&ch_switch->chandef)
 		__entry->timestamp = ch_switch->timestamp;
+		__entry->device_timestamp = ch_switch->device_timestamp;
 		__entry->block_tx = ch_switch->block_tx;
 		__entry->count = ch_switch->count;
 	),
 
 	TP_printk(
-		LOCAL_PR_FMT " new " CHANDEF_PR_FMT " count:%d",
-		LOCAL_PR_ARG, CHANDEF_PR_ARG, __entry->count
+		LOCAL_PR_FMT VIF_PR_FMT " new " CHANDEF_PR_FMT " count:%d",
+		LOCAL_PR_ARG, VIF_PR_ARG, CHANDEF_PR_ARG, __entry->count
 	)
 );
 
@@ -1217,28 +1256,28 @@ TRACE_EVENT(drv_set_rekey_data,
 		  LOCAL_PR_ARG, VIF_PR_ARG)
 );
 
-TRACE_EVENT(drv_rssi_callback,
+TRACE_EVENT(drv_event_callback,
 	TP_PROTO(struct ieee80211_local *local,
 		 struct ieee80211_sub_if_data *sdata,
-		 enum ieee80211_rssi_event rssi_event),
+		 const struct ieee80211_event *_event),
 
-	TP_ARGS(local, sdata, rssi_event),
+	TP_ARGS(local, sdata, _event),
 
 	TP_STRUCT__entry(
 		LOCAL_ENTRY
 		VIF_ENTRY
-		__field(u32, rssi_event)
+		__field(u32, type)
 	),
 
 	TP_fast_assign(
 		LOCAL_ASSIGN;
 		VIF_ASSIGN;
-		__entry->rssi_event = rssi_event;
+		__entry->type = _event->type;
 	),
 
 	TP_printk(
-		LOCAL_PR_FMT VIF_PR_FMT " rssi_event:%d",
-		LOCAL_PR_ARG, VIF_PR_ARG, __entry->rssi_event
+		LOCAL_PR_FMT VIF_PR_FMT " event:%d",
+		LOCAL_PR_ARG, VIF_PR_ARG, __entry->type
 	)
 );
 
@@ -1297,32 +1336,6 @@ DEFINE_EVENT(release_evt, drv_allow_buffered_frames,
 	TP_ARGS(local, sta, tids, num_frames, reason, more_data)
 );
 
-TRACE_EVENT(drv_get_rssi,
-	TP_PROTO(struct ieee80211_local *local, struct ieee80211_sta *sta,
-		 s8 rssi, int ret),
-
-	TP_ARGS(local, sta, rssi, ret),
-
-	TP_STRUCT__entry(
-		LOCAL_ENTRY
-		STA_ENTRY
-		__field(s8, rssi)
-		__field(int, ret)
-	),
-
-	TP_fast_assign(
-		LOCAL_ASSIGN;
-		STA_ASSIGN;
-		__entry->rssi = rssi;
-		__entry->ret = ret;
-	),
-
-	TP_printk(
-		LOCAL_PR_FMT STA_PR_FMT " rssi:%d ret:%d",
-		LOCAL_PR_ARG, STA_PR_ARG, __entry->rssi, __entry->ret
-	)
-);
-
 DEFINE_EVENT(local_sdata_evt, drv_mgd_prepare_tx,
 	TP_PROTO(struct ieee80211_local *local,
 		 struct ieee80211_sub_if_data *sdata),
@@ -1557,9 +1570,26 @@ DEFINE_EVENT(local_sdata_evt, drv_stop_ap,
 	TP_ARGS(local, sdata)
 );
 
-DEFINE_EVENT(local_only_evt, drv_restart_complete,
-	TP_PROTO(struct ieee80211_local *local),
-	TP_ARGS(local)
+TRACE_EVENT(drv_reconfig_complete,
+	TP_PROTO(struct ieee80211_local *local,
+		 enum ieee80211_reconfig_type reconfig_type),
+	TP_ARGS(local, reconfig_type),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		__field(u8, reconfig_type)
+	),
+
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		__entry->reconfig_type = reconfig_type;
+	),
+
+	TP_printk(
+		LOCAL_PR_FMT  " reconfig_type:%d",
+		LOCAL_PR_ARG, __entry->reconfig_type
+	)
+
 );
 
 #if IS_ENABLED(CONFIG_IPV6)
@@ -1780,6 +1810,12 @@ TRACE_EVENT(api_cqm_rssi_notify,
 	)
 );
 
+DEFINE_EVENT(local_sdata_evt, api_cqm_beacon_loss_notify,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata),
+	TP_ARGS(local, sdata)
+);
+
 TRACE_EVENT(api_scan_completed,
 	TP_PROTO(struct ieee80211_local *local, bool aborted),
 
@@ -2106,44 +2142,206 @@ TRACE_EVENT(drv_channel_switch_beacon,
 	)
 );
 
+TRACE_EVENT(drv_pre_channel_switch,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 struct ieee80211_channel_switch *ch_switch),
 
-#ifdef CONFIG_MAC80211_MESSAGE_TRACING
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM mac80211_msg
+	TP_ARGS(local, sdata, ch_switch),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		VIF_ENTRY
+		CHANDEF_ENTRY
+		__field(u64, timestamp)
+		__field(u32, device_timestamp)
+		__field(bool, block_tx)
+		__field(u8, count)
+	),
+
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		VIF_ASSIGN;
+		CHANDEF_ASSIGN(&ch_switch->chandef)
+		__entry->timestamp = ch_switch->timestamp;
+		__entry->device_timestamp = ch_switch->device_timestamp;
+		__entry->block_tx = ch_switch->block_tx;
+		__entry->count = ch_switch->count;
+	),
 
-#define MAX_MSG_LEN	100
+	TP_printk(
+		LOCAL_PR_FMT VIF_PR_FMT " prepare channel switch to "
+		CHANDEF_PR_FMT  " count:%d block_tx:%d timestamp:%llu",
+		LOCAL_PR_ARG, VIF_PR_ARG, CHANDEF_PR_ARG, __entry->count,
+		__entry->block_tx, __entry->timestamp
+	)
+);
 
-DECLARE_EVENT_CLASS(mac80211_msg_event,
-	TP_PROTO(struct va_format *vaf),
+DEFINE_EVENT(local_sdata_evt, drv_post_channel_switch,
+	     TP_PROTO(struct ieee80211_local *local,
+		      struct ieee80211_sub_if_data *sdata),
+	     TP_ARGS(local, sdata)
+);
+
+TRACE_EVENT(drv_get_txpower,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 int dbm, int ret),
 
-	TP_ARGS(vaf),
+	TP_ARGS(local, sdata, dbm, ret),
 
 	TP_STRUCT__entry(
-		__dynamic_array(char, msg, MAX_MSG_LEN)
+		LOCAL_ENTRY
+		VIF_ENTRY
+		__field(int, dbm)
+		__field(int, ret)
 	),
 
 	TP_fast_assign(
-		WARN_ON_ONCE(vsnprintf(__get_dynamic_array(msg),
-				       MAX_MSG_LEN, vaf->fmt,
-				       *vaf->va) >= MAX_MSG_LEN);
+		LOCAL_ASSIGN;
+		VIF_ASSIGN;
+		__entry->dbm = dbm;
+		__entry->ret = ret;
 	),
 
-	TP_printk("%s", __get_str(msg))
+	TP_printk(
+		LOCAL_PR_FMT VIF_PR_FMT " dbm:%d ret:%d",
+		LOCAL_PR_ARG, VIF_PR_ARG, __entry->dbm, __entry->ret
+	)
 );
 
-DEFINE_EVENT(mac80211_msg_event, mac80211_info,
-	TP_PROTO(struct va_format *vaf),
-	TP_ARGS(vaf)
+TRACE_EVENT(drv_tdls_channel_switch,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 struct ieee80211_sta *sta, u8 oper_class,
+		 struct cfg80211_chan_def *chandef),
+
+	TP_ARGS(local, sdata, sta, oper_class, chandef),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		VIF_ENTRY
+		STA_ENTRY
+		__field(u8, oper_class)
+		CHANDEF_ENTRY
+	),
+
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		VIF_ASSIGN;
+		STA_ASSIGN;
+		__entry->oper_class = oper_class;
+		CHANDEF_ASSIGN(chandef)
+	),
+
+	TP_printk(
+		LOCAL_PR_FMT VIF_PR_FMT " tdls channel switch to"
+		CHANDEF_PR_FMT  " oper_class:%d " STA_PR_FMT,
+		LOCAL_PR_ARG, VIF_PR_ARG, CHANDEF_PR_ARG, __entry->oper_class,
+		STA_PR_ARG
+	)
 );
-DEFINE_EVENT(mac80211_msg_event, mac80211_dbg,
-	TP_PROTO(struct va_format *vaf),
-	TP_ARGS(vaf)
+
+TRACE_EVENT(drv_tdls_cancel_channel_switch,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 struct ieee80211_sta *sta),
+
+	TP_ARGS(local, sdata, sta),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		VIF_ENTRY
+		STA_ENTRY
+	),
+
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		VIF_ASSIGN;
+		STA_ASSIGN;
+	),
+
+	TP_printk(
+		LOCAL_PR_FMT VIF_PR_FMT
+		" tdls cancel channel switch with " STA_PR_FMT,
+		LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG
+	)
 );
-DEFINE_EVENT(mac80211_msg_event, mac80211_err,
-	TP_PROTO(struct va_format *vaf),
-	TP_ARGS(vaf)
+
+TRACE_EVENT(drv_tdls_recv_channel_switch,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 struct ieee80211_tdls_ch_sw_params *params),
+
+	TP_ARGS(local, sdata, params),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		VIF_ENTRY
+		__field(u8, action_code)
+		STA_ENTRY
+		CHANDEF_ENTRY
+		__field(u32, status)
+		__field(bool, peer_initiator)
+		__field(u32, timestamp)
+		__field(u16, switch_time)
+		__field(u16, switch_timeout)
+	),
+
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		VIF_ASSIGN;
+		STA_NAMED_ASSIGN(params->sta);
+		CHANDEF_ASSIGN(params->chandef)
+		__entry->peer_initiator = params->sta->tdls_initiator;
+		__entry->action_code = params->action_code;
+		__entry->status = params->status;
+		__entry->timestamp = params->timestamp;
+		__entry->switch_time = params->switch_time;
+		__entry->switch_timeout = params->switch_timeout;
+	),
+
+	TP_printk(
+		LOCAL_PR_FMT VIF_PR_FMT " received tdls channel switch packet"
+		" action:%d status:%d time:%d switch time:%d switch"
+		" timeout:%d initiator: %d chan:" CHANDEF_PR_FMT STA_PR_FMT,
+		LOCAL_PR_ARG, VIF_PR_ARG, __entry->action_code, __entry->status,
+		__entry->timestamp, __entry->switch_time,
+		__entry->switch_timeout, __entry->peer_initiator,
+		CHANDEF_PR_ARG, STA_PR_ARG
+	)
+);
+
+TRACE_EVENT(drv_wake_tx_queue,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 struct txq_info *txq),
+
+	TP_ARGS(local, sdata, txq),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		VIF_ENTRY
+		STA_ENTRY
+		__field(u8, ac)
+		__field(u8, tid)
+	),
+
+	TP_fast_assign(
+		struct ieee80211_sta *sta = txq->txq.sta;
+
+		LOCAL_ASSIGN;
+		VIF_ASSIGN;
+		STA_ASSIGN;
+		__entry->ac = txq->txq.ac;
+		__entry->tid = txq->txq.tid;
+	),
+
+	TP_printk(
+		LOCAL_PR_FMT  VIF_PR_FMT  STA_PR_FMT " ac:%d tid:%d",
+		LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG, __entry->ac, __entry->tid
+	)
 );
-#endif
 
 #endif /* !__MAC80211_DRIVER_TRACE || TRACE_HEADER_MULTI_READ */
 
diff --git a/net/mac80211/trace_msg.h b/net/mac80211/trace_msg.h
new file mode 100644
index 000000000000..768f7c22a190
--- /dev/null
+++ b/net/mac80211/trace_msg.h
@@ -0,0 +1,53 @@
+#ifdef CONFIG_MAC80211_MESSAGE_TRACING
+
+#if !defined(__MAC80211_MSG_DRIVER_TRACE) || defined(TRACE_HEADER_MULTI_READ)
+#define __MAC80211_MSG_DRIVER_TRACE
+
+#include <linux/tracepoint.h>
+#include <net/mac80211.h>
+#include "ieee80211_i.h"
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mac80211_msg
+
+#define MAX_MSG_LEN	100
+
+DECLARE_EVENT_CLASS(mac80211_msg_event,
+	TP_PROTO(struct va_format *vaf),
+
+	TP_ARGS(vaf),
+
+	TP_STRUCT__entry(
+		__dynamic_array(char, msg, MAX_MSG_LEN)
+	),
+
+	TP_fast_assign(
+		WARN_ON_ONCE(vsnprintf(__get_dynamic_array(msg),
+				       MAX_MSG_LEN, vaf->fmt,
+				       *vaf->va) >= MAX_MSG_LEN);
+	),
+
+	TP_printk("%s", __get_str(msg))
+);
+
+DEFINE_EVENT(mac80211_msg_event, mac80211_info,
+	TP_PROTO(struct va_format *vaf),
+	TP_ARGS(vaf)
+);
+DEFINE_EVENT(mac80211_msg_event, mac80211_dbg,
+	TP_PROTO(struct va_format *vaf),
+	TP_ARGS(vaf)
+);
+DEFINE_EVENT(mac80211_msg_event, mac80211_err,
+	TP_PROTO(struct va_format *vaf),
+	TP_ARGS(vaf)
+);
+#endif /* !__MAC80211_MSG_DRIVER_TRACE || TRACE_HEADER_MULTI_READ */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace_msg
+#include <trace/define_trace.h>
+
+#endif
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 900632a250ec..667111ee6a20 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -20,7 +20,6 @@
 #include <linux/bitmap.h>
 #include <linux/rcupdate.h>
 #include <linux/export.h>
-#include <linux/time.h>
 #include <net/net_namespace.h>
 #include <net/ieee80211_radiotap.h>
 #include <net/cfg80211.h>
@@ -60,7 +59,7 @@ static __le16 ieee80211_duration(struct ieee80211_tx_data *tx,
 	rcu_read_unlock();
 
 	/* assume HW handles this */
-	if (tx->rate.flags & IEEE80211_TX_RC_MCS)
+	if (tx->rate.flags & (IEEE80211_TX_RC_MCS | IEEE80211_TX_RC_VHT_MCS))
 		return 0;
 
 	/* uh huh? */
@@ -296,6 +295,9 @@ ieee80211_tx_h_check_assoc(struct ieee80211_tx_data *tx)
 		 */
 		return TX_DROP;
 
+	if (tx->sdata->vif.type == NL80211_IFTYPE_OCB)
+		return TX_CONTINUE;
+
 	if (tx->sdata->vif.type == NL80211_IFTYPE_WDS)
 		return TX_CONTINUE;
 
@@ -563,6 +565,7 @@ ieee80211_tx_h_check_control_port_protocol(struct ieee80211_tx_data *tx)
 		if (tx->sdata->control_port_no_encrypt)
 			info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT;
 		info->control.flags |= IEEE80211_TX_CTRL_PORT_CTRL_PROTO;
+		info->flags |= IEEE80211_TX_CTL_USE_MINRATE;
 	}
 
 	return TX_CONTINUE;
@@ -591,23 +594,8 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx)
 	else if (!is_multicast_ether_addr(hdr->addr1) &&
 		 (key = rcu_dereference(tx->sdata->default_unicast_key)))
 		tx->key = key;
-	else if (info->flags & IEEE80211_TX_CTL_INJECTED)
-		tx->key = NULL;
-	else if (!tx->sdata->drop_unencrypted)
-		tx->key = NULL;
-	else if (tx->skb->protocol == tx->sdata->control_port_protocol)
-		tx->key = NULL;
-	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(tx->skb))
+	else
 		tx->key = NULL;
-	else {
-		I802_DEBUG_INC(tx->local->tx_handlers_drop_unencrypted);
-		return TX_DROP;
-	}
 
 	if (tx->key) {
 		bool skip_hw = false;
@@ -623,6 +611,9 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx)
 				tx->key = NULL;
 			break;
 		case WLAN_CIPHER_SUITE_CCMP:
+		case WLAN_CIPHER_SUITE_CCMP_256:
+		case WLAN_CIPHER_SUITE_GCMP:
+		case WLAN_CIPHER_SUITE_GCMP_256:
 			if (!ieee80211_is_data_present(hdr->frame_control) &&
 			    !ieee80211_use_mfp(hdr->frame_control, tx->sta,
 					       tx->skb))
@@ -633,6 +624,9 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx)
 					ieee80211_is_mgmt(hdr->frame_control);
 			break;
 		case WLAN_CIPHER_SUITE_AES_CMAC:
+		case WLAN_CIPHER_SUITE_BIP_CMAC_256:
+		case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+		case WLAN_CIPHER_SUITE_BIP_GMAC_256:
 			if (!ieee80211_is_mgmt(hdr->frame_control))
 				tx->key = NULL;
 			break;
@@ -773,12 +767,22 @@ ieee80211_tx_h_rate_ctrl(struct ieee80211_tx_data *tx)
 	return TX_CONTINUE;
 }
 
+static __le16 ieee80211_tx_next_seq(struct sta_info *sta, int tid)
+{
+	u16 *seq = &sta->tid_seq[tid];
+	__le16 ret = cpu_to_le16(*seq);
+
+	/* Increase the sequence number. */
+	*seq = (*seq + 0x10) & IEEE80211_SCTL_SEQ;
+
+	return ret;
+}
+
 static ieee80211_tx_result debug_noinline
 ieee80211_tx_h_sequence(struct ieee80211_tx_data *tx)
 {
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb);
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data;
-	u16 *seq;
 	u8 *qc;
 	int tid;
 
@@ -812,6 +816,8 @@ ieee80211_tx_h_sequence(struct ieee80211_tx_data *tx)
 		/* for pure STA mode without beacons, we can do it */
 		hdr->seq_ctrl = cpu_to_le16(tx->sdata->sequence_number);
 		tx->sdata->sequence_number += 0x10;
+		if (tx->sta)
+			tx->sta->tx_msdu[IEEE80211_NUM_TIDS]++;
 		return TX_CONTINUE;
 	}
 
@@ -827,12 +833,10 @@ ieee80211_tx_h_sequence(struct ieee80211_tx_data *tx)
 
 	qc = ieee80211_get_qos_ctl(hdr);
 	tid = *qc & IEEE80211_QOS_CTL_TID_MASK;
-	seq = &tx->sta->tid_seq[tid];
+	tx->sta->tx_msdu[tid]++;
 
-	hdr->seq_ctrl = cpu_to_le16(*seq);
-
-	/* Increase the sequence number. */
-	*seq = (*seq + 0x10) & IEEE80211_SCTL_SEQ;
+	if (!tx->sta->sta.txq[0])
+		hdr->seq_ctrl = ieee80211_tx_next_seq(tx->sta, tid);
 
 	return TX_CONTINUE;
 }
@@ -1005,9 +1009,21 @@ ieee80211_tx_h_encrypt(struct ieee80211_tx_data *tx)
 	case WLAN_CIPHER_SUITE_TKIP:
 		return ieee80211_crypto_tkip_encrypt(tx);
 	case WLAN_CIPHER_SUITE_CCMP:
-		return ieee80211_crypto_ccmp_encrypt(tx);
+		return ieee80211_crypto_ccmp_encrypt(
+			tx, IEEE80211_CCMP_MIC_LEN);
+	case WLAN_CIPHER_SUITE_CCMP_256:
+		return ieee80211_crypto_ccmp_encrypt(
+			tx, IEEE80211_CCMP_256_MIC_LEN);
 	case WLAN_CIPHER_SUITE_AES_CMAC:
 		return ieee80211_crypto_aes_cmac_encrypt(tx);
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
+		return ieee80211_crypto_aes_cmac_256_encrypt(tx);
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		return ieee80211_crypto_aes_gmac_encrypt(tx);
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		return ieee80211_crypto_gcmp_encrypt(tx);
 	default:
 		return ieee80211_crypto_hw_encrypt(tx);
 	}
@@ -1061,7 +1077,7 @@ static bool ieee80211_tx_prep_agg(struct ieee80211_tx_data *tx,
 		 * nothing -- this aggregation session is being started
 		 * but that might still fail with the driver
 		 */
-	} else {
+	} else if (!tx->sta->sta.txq[tid]) {
 		spin_lock(&tx->sta->lock);
 		/*
 		 * Need to re-check now, because we may get here
@@ -1112,11 +1128,13 @@ static bool ieee80211_tx_prep_agg(struct ieee80211_tx_data *tx,
 
 /*
  * initialises @tx
+ * pass %NULL for the station if unknown, a valid pointer if known
+ * or an ERR_PTR() if the station is known not to exist
  */
 static ieee80211_tx_result
 ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata,
 		     struct ieee80211_tx_data *tx,
-		     struct sk_buff *skb)
+		     struct sta_info *sta, struct sk_buff *skb)
 {
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_hdr *hdr;
@@ -1139,17 +1157,22 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata,
 
 	hdr = (struct ieee80211_hdr *) skb->data;
 
-	if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) {
-		tx->sta = rcu_dereference(sdata->u.vlan.sta);
-		if (!tx->sta && sdata->dev->ieee80211_ptr->use_4addr)
-			return TX_DROP;
-	} else if (info->flags & (IEEE80211_TX_CTL_INJECTED |
-				  IEEE80211_TX_INTFL_NL80211_FRAME_TX) ||
-		   tx->sdata->control_port_protocol == tx->skb->protocol) {
-		tx->sta = sta_info_get_bss(sdata, hdr->addr1);
+	if (likely(sta)) {
+		if (!IS_ERR(sta))
+			tx->sta = sta;
+	} else {
+		if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) {
+			tx->sta = rcu_dereference(sdata->u.vlan.sta);
+			if (!tx->sta && sdata->wdev.use_4addr)
+				return TX_DROP;
+		} else if (info->flags & (IEEE80211_TX_INTFL_NL80211_FRAME_TX |
+					  IEEE80211_TX_CTL_INJECTED) ||
+			   tx->sdata->control_port_protocol == tx->skb->protocol) {
+			tx->sta = sta_info_get_bss(sdata, hdr->addr1);
+		}
+		if (!tx->sta && !is_multicast_ether_addr(hdr->addr1))
+			tx->sta = sta_info_get(sdata, hdr->addr1);
 	}
-	if (!tx->sta)
-		tx->sta = sta_info_get(sdata, hdr->addr1);
 
 	if (tx->sta && ieee80211_is_data_qos(hdr->frame_control) &&
 	    !ieee80211_is_qos_nullfunc(hdr->frame_control) &&
@@ -1195,13 +1218,102 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata,
 	return TX_CONTINUE;
 }
 
+static void ieee80211_drv_tx(struct ieee80211_local *local,
+			     struct ieee80211_vif *vif,
+			     struct ieee80211_sta *pubsta,
+			     struct sk_buff *skb)
+{
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
+	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct ieee80211_tx_control control = {
+		.sta = pubsta,
+	};
+	struct ieee80211_txq *txq = NULL;
+	struct txq_info *txqi;
+	u8 ac;
+
+	if (info->control.flags & IEEE80211_TX_CTRL_PS_RESPONSE)
+		goto tx_normal;
+
+	if (!ieee80211_is_data(hdr->frame_control))
+		goto tx_normal;
+
+	if (pubsta) {
+		u8 tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK;
+
+		txq = pubsta->txq[tid];
+	} else if (vif) {
+		txq = vif->txq;
+	}
+
+	if (!txq)
+		goto tx_normal;
+
+	ac = txq->ac;
+	txqi = to_txq_info(txq);
+	atomic_inc(&sdata->txqs_len[ac]);
+	if (atomic_read(&sdata->txqs_len[ac]) >= local->hw.txq_ac_max_pending)
+		netif_stop_subqueue(sdata->dev, ac);
+
+	skb_queue_tail(&txqi->queue, skb);
+	drv_wake_tx_queue(local, txqi);
+
+	return;
+
+tx_normal:
+	drv_tx(local, &control, skb);
+}
+
+struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
+				     struct ieee80211_txq *txq)
+{
+	struct ieee80211_local *local = hw_to_local(hw);
+	struct ieee80211_sub_if_data *sdata = vif_to_sdata(txq->vif);
+	struct txq_info *txqi = container_of(txq, struct txq_info, txq);
+	struct ieee80211_hdr *hdr;
+	struct sk_buff *skb = NULL;
+	u8 ac = txq->ac;
+
+	spin_lock_bh(&txqi->queue.lock);
+
+	if (test_bit(IEEE80211_TXQ_STOP, &txqi->flags))
+		goto out;
+
+	skb = __skb_dequeue(&txqi->queue);
+	if (!skb)
+		goto out;
+
+	atomic_dec(&sdata->txqs_len[ac]);
+	if (__netif_subqueue_stopped(sdata->dev, ac))
+		ieee80211_propagate_queue_wake(local, sdata->vif.hw_queue[ac]);
+
+	hdr = (struct ieee80211_hdr *)skb->data;
+	if (txq->sta && ieee80211_is_data_qos(hdr->frame_control)) {
+		struct sta_info *sta = container_of(txq->sta, struct sta_info,
+						    sta);
+		struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+
+		hdr->seq_ctrl = ieee80211_tx_next_seq(sta, txq->tid);
+		if (test_bit(IEEE80211_TXQ_AMPDU, &txqi->flags))
+			info->flags |= IEEE80211_TX_CTL_AMPDU;
+		else
+			info->flags &= ~IEEE80211_TX_CTL_AMPDU;
+	}
+
+out:
+	spin_unlock_bh(&txqi->queue.lock);
+
+	return skb;
+}
+EXPORT_SYMBOL(ieee80211_tx_dequeue);
+
 static bool ieee80211_tx_frags(struct ieee80211_local *local,
 			       struct ieee80211_vif *vif,
 			       struct ieee80211_sta *sta,
 			       struct sk_buff_head *skbs,
 			       bool txpending)
 {
-	struct ieee80211_tx_control control;
 	struct sk_buff *skb, *tmp;
 	unsigned long flags;
 
@@ -1259,10 +1371,9 @@ static bool ieee80211_tx_frags(struct ieee80211_local *local,
 		spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
 
 		info->control.vif = vif;
-		control.sta = sta;
 
 		__skb_unlink(skb, skbs);
-		drv_tx(local, &control, skb);
+		ieee80211_drv_tx(local, vif, sta, skb);
 	}
 
 	return true;
@@ -1397,8 +1508,9 @@ bool ieee80211_tx_prepare_skb(struct ieee80211_hw *hw,
 	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	struct ieee80211_tx_data tx;
+	struct sk_buff *skb2;
 
-	if (ieee80211_tx_prepare(sdata, &tx, skb) == TX_DROP)
+	if (ieee80211_tx_prepare(sdata, &tx, NULL, skb) == TX_DROP)
 		return false;
 
 	info->band = band;
@@ -1415,6 +1527,14 @@ bool ieee80211_tx_prepare_skb(struct ieee80211_hw *hw,
 			*sta = NULL;
 	}
 
+	/* this function isn't suitable for fragmented data frames */
+	skb2 = __skb_dequeue(&tx.skbs);
+	if (WARN_ON(skb2 != skb || !skb_queue_empty(&tx.skbs))) {
+		ieee80211_free_txskb(hw, skb2);
+		ieee80211_purge_tx_queue(hw, &tx.skbs);
+		return false;
+	}
+
 	return true;
 }
 EXPORT_SYMBOL(ieee80211_tx_prepare_skb);
@@ -1423,8 +1543,8 @@ EXPORT_SYMBOL(ieee80211_tx_prepare_skb);
  * Returns false if the frame couldn't be transmitted but was queued instead.
  */
 static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata,
-			 struct sk_buff *skb, bool txpending,
-			 enum ieee80211_band band)
+			 struct sta_info *sta, struct sk_buff *skb,
+			 bool txpending)
 {
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_tx_data tx;
@@ -1440,7 +1560,7 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata,
 
 	/* initialises tx */
 	led_len = skb->len;
-	res_prepare = ieee80211_tx_prepare(sdata, &tx, skb);
+	res_prepare = ieee80211_tx_prepare(sdata, &tx, sta, skb);
 
 	if (unlikely(res_prepare == TX_DROP)) {
 		ieee80211_free_txskb(&local->hw, skb);
@@ -1449,8 +1569,6 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata,
 		return true;
 	}
 
-	info->band = band;
-
 	/* set up hw_queue value early */
 	if (!(info->flags & IEEE80211_TX_CTL_TX_OFFCHAN) ||
 	    !(local->hw.flags & IEEE80211_HW_QUEUE_CONTROL))
@@ -1498,8 +1616,8 @@ static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata,
 	return 0;
 }
 
-void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb,
-		    enum ieee80211_band band)
+void ieee80211_xmit(struct ieee80211_sub_if_data *sdata,
+		    struct sta_info *sta, struct sk_buff *skb)
 {
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
@@ -1534,7 +1652,7 @@ void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb,
 	}
 
 	ieee80211_set_qos_hdr(sdata, skb);
-	ieee80211_tx(sdata, skb, false, band);
+	ieee80211_tx(sdata, sta, skb, false);
 }
 
 static bool ieee80211_parse_tx_radiotap(struct sk_buff *skb)
@@ -1754,7 +1872,8 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb,
 				     sdata->vif.type))
 		goto fail_rcu;
 
-	ieee80211_xmit(sdata, skb, chandef->chan->band);
+	info->band = chandef->chan->band;
+	ieee80211_xmit(sdata, NULL, skb);
 	rcu_read_unlock();
 
 	return NETDEV_TX_OK;
@@ -1766,41 +1885,113 @@ fail:
 	return NETDEV_TX_OK; /* meaning, we dealt with the skb */
 }
 
-/*
- * Measure Tx frame arrival time for Tx latency statistics calculation
- * A single Tx frame latency should be measured from when it is entering the
- * Kernel until we receive Tx complete confirmation indication and the skb is
- * freed.
- */
-static void ieee80211_tx_latency_start_msrmnt(struct ieee80211_local *local,
-					      struct sk_buff *skb)
+static inline bool ieee80211_is_tdls_setup(struct sk_buff *skb)
 {
-	struct ieee80211_tx_latency_bin_ranges *tx_latency;
+	u16 ethertype = (skb->data[12] << 8) | skb->data[13];
 
-	tx_latency = rcu_dereference(local->tx_latency);
-	if (!tx_latency)
-		return;
-	skb->tstamp = ktime_get();
+	return ethertype == ETH_P_TDLS &&
+	       skb->len > 14 &&
+	       skb->data[14] == WLAN_TDLS_SNAP_RFTYPE;
+}
+
+static int ieee80211_lookup_ra_sta(struct ieee80211_sub_if_data *sdata,
+				   struct sk_buff *skb,
+				   struct sta_info **sta_out)
+{
+	struct sta_info *sta;
+
+	switch (sdata->vif.type) {
+	case NL80211_IFTYPE_AP_VLAN:
+		sta = rcu_dereference(sdata->u.vlan.sta);
+		if (sta) {
+			*sta_out = sta;
+			return 0;
+		} else if (sdata->wdev.use_4addr) {
+			return -ENOLINK;
+		}
+		/* fall through */
+	case NL80211_IFTYPE_AP:
+	case NL80211_IFTYPE_OCB:
+	case NL80211_IFTYPE_ADHOC:
+		if (is_multicast_ether_addr(skb->data)) {
+			*sta_out = ERR_PTR(-ENOENT);
+			return 0;
+		}
+		sta = sta_info_get_bss(sdata, skb->data);
+		break;
+	case NL80211_IFTYPE_WDS:
+		sta = sta_info_get(sdata, sdata->u.wds.remote_addr);
+		break;
+#ifdef CONFIG_MAC80211_MESH
+	case NL80211_IFTYPE_MESH_POINT:
+		/* determined much later */
+		*sta_out = NULL;
+		return 0;
+#endif
+	case NL80211_IFTYPE_STATION:
+		if (sdata->wdev.wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS) {
+			sta = sta_info_get(sdata, skb->data);
+			if (sta) {
+				bool tdls_peer, tdls_auth;
+
+				tdls_peer = test_sta_flag(sta,
+							  WLAN_STA_TDLS_PEER);
+				tdls_auth = test_sta_flag(sta,
+						WLAN_STA_TDLS_PEER_AUTH);
+
+				if (tdls_peer && tdls_auth) {
+					*sta_out = sta;
+					return 0;
+				}
+
+				/*
+				 * TDLS link during setup - throw out frames to
+				 * peer. Allow TDLS-setup frames to unauthorized
+				 * peers for the special case of a link teardown
+				 * after a TDLS sta is removed due to being
+				 * unreachable.
+				 */
+				if (tdls_peer && !tdls_auth &&
+				    !ieee80211_is_tdls_setup(skb))
+					return -EINVAL;
+			}
+
+		}
+
+		sta = sta_info_get(sdata, sdata->u.mgd.bssid);
+		if (!sta)
+			return -ENOLINK;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	*sta_out = sta ?: ERR_PTR(-ENOENT);
+	return 0;
 }
 
 /**
- * ieee80211_subif_start_xmit - netif start_xmit function for Ethernet-type
- * subinterfaces (wlan#, WDS, and VLAN interfaces)
- * @skb: packet to be sent
- * @dev: incoming interface
+ * ieee80211_build_hdr - build 802.11 header in the given frame
+ * @sdata: virtual interface to build the header for
+ * @skb: the skb to build the header in
+ * @info_flags: skb flags to set
+ *
+ * This function takes the skb with 802.3 header and reformats the header to
+ * the appropriate IEEE 802.11 header based on which interface the packet is
+ * being transmitted on.
  *
- * Returns: NETDEV_TX_OK both on success and on failure. On failure skb will
- *	be freed.
+ * Note that this function also takes care of the TX status request and
+ * potential unsharing of the SKB - this needs to be interleaved with the
+ * header building.
  *
- * This function takes in an Ethernet header and encapsulates it with suitable
- * IEEE 802.11 header based on which interface the packet is coming in. The
- * encapsulated packet will then be passed to master interface, wlan#.11, for
- * transmission (through low-level driver).
+ * The function requires the read-side RCU lock held
+ *
+ * Returns: the (possibly reallocated) skb or an ERR_PTR() code
  */
-netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
-				    struct net_device *dev)
+static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata,
+					   struct sk_buff *skb, u32 info_flags,
+					   struct sta_info *sta)
 {
-	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_tx_info *info;
 	int head_need;
@@ -1812,33 +2003,26 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
 	const u8 *encaps_data;
 	int encaps_len, skip_header_bytes;
 	int nh_pos, h_pos;
-	struct sta_info *sta = NULL;
-	bool wme_sta = false, authorized = false, tdls_auth = false;
-	bool tdls_peer = false, tdls_setup_frame = false;
+	bool wme_sta = false, authorized = false;
+	bool tdls_peer;
 	bool multicast;
-	u32 info_flags = 0;
 	u16 info_id = 0;
 	struct ieee80211_chanctx_conf *chanctx_conf;
 	struct ieee80211_sub_if_data *ap_sdata;
 	enum ieee80211_band band;
+	int ret;
 
-	if (unlikely(skb->len < ETH_HLEN))
-		goto fail;
+	if (IS_ERR(sta))
+		sta = NULL;
 
 	/* convert Ethernet header to proper 802.11 header (based on
 	 * operation mode) */
 	ethertype = (skb->data[12] << 8) | skb->data[13];
 	fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_DATA);
 
-	rcu_read_lock();
-
-	/* Measure frame arrival for Tx latency statistics calculation */
-	ieee80211_tx_latency_start_msrmnt(local, skb);
-
 	switch (sdata->vif.type) {
 	case NL80211_IFTYPE_AP_VLAN:
-		sta = rcu_dereference(sdata->u.vlan.sta);
-		if (sta) {
+		if (sdata->wdev.use_4addr) {
 			fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS | IEEE80211_FCTL_TODS);
 			/* RA TA DA SA */
 			memcpy(hdr.addr1, sta->sta.addr, ETH_ALEN);
@@ -1852,17 +2036,21 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
 		ap_sdata = container_of(sdata->bss, struct ieee80211_sub_if_data,
 					u.ap);
 		chanctx_conf = rcu_dereference(ap_sdata->vif.chanctx_conf);
-		if (!chanctx_conf)
-			goto fail_rcu;
+		if (!chanctx_conf) {
+			ret = -ENOTCONN;
+			goto free;
+		}
 		band = chanctx_conf->def.chan->band;
-		if (sta)
+		if (sdata->wdev.use_4addr)
 			break;
 		/* fall through */
 	case NL80211_IFTYPE_AP:
 		if (sdata->vif.type == NL80211_IFTYPE_AP)
 			chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
-		if (!chanctx_conf)
-			goto fail_rcu;
+		if (!chanctx_conf) {
+			ret = -ENOTCONN;
+			goto free;
+		}
 		fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS);
 		/* DA BSSID SA */
 		memcpy(hdr.addr1, skb->data, ETH_ALEN);
@@ -1949,42 +2137,18 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
 
 		}
 		chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
-		if (!chanctx_conf)
-			goto fail_rcu;
+		if (!chanctx_conf) {
+			ret = -ENOTCONN;
+			goto free;
+		}
 		band = chanctx_conf->def.chan->band;
 		break;
 #endif
 	case NL80211_IFTYPE_STATION:
-		if (sdata->wdev.wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS) {
-			sta = sta_info_get(sdata, skb->data);
-			if (sta) {
-				authorized = test_sta_flag(sta,
-							WLAN_STA_AUTHORIZED);
-				wme_sta = sta->sta.wme;
-				tdls_peer = test_sta_flag(sta,
-							  WLAN_STA_TDLS_PEER);
-				tdls_auth = test_sta_flag(sta,
-						WLAN_STA_TDLS_PEER_AUTH);
-			}
-
-			if (tdls_peer)
-				tdls_setup_frame =
-					ethertype == ETH_P_TDLS &&
-					skb->len > 14 &&
-					skb->data[14] == WLAN_TDLS_SNAP_RFTYPE;
-		}
+		/* we already did checks when looking up the RA STA */
+		tdls_peer = test_sta_flag(sta, WLAN_STA_TDLS_PEER);
 
-		/*
-		 * TDLS link during setup - throw out frames to peer. We allow
-		 * TDLS-setup frames to unauthorized peers for the special case
-		 * of a link teardown after a TDLS sta is removed due to being
-		 * unreachable.
-		 */
-		if (tdls_peer && !tdls_auth && !tdls_setup_frame)
-			goto fail_rcu;
-
-		/* send direct packets to authorized TDLS peers */
-		if (tdls_peer && tdls_auth) {
+		if (tdls_peer) {
 			/* DA SA BSSID */
 			memcpy(hdr.addr1, skb->data, ETH_ALEN);
 			memcpy(hdr.addr2, skb->data + ETH_ALEN, ETH_ALEN);
@@ -2009,8 +2173,23 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
 			hdrlen = 24;
 		}
 		chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
-		if (!chanctx_conf)
-			goto fail_rcu;
+		if (!chanctx_conf) {
+			ret = -ENOTCONN;
+			goto free;
+		}
+		band = chanctx_conf->def.chan->band;
+		break;
+	case NL80211_IFTYPE_OCB:
+		/* DA SA BSSID */
+		memcpy(hdr.addr1, skb->data, ETH_ALEN);
+		memcpy(hdr.addr2, skb->data + ETH_ALEN, ETH_ALEN);
+		eth_broadcast_addr(hdr.addr3);
+		hdrlen = 24;
+		chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
+		if (!chanctx_conf) {
+			ret = -ENOTCONN;
+			goto free;
+		}
 		band = chanctx_conf->def.chan->band;
 		break;
 	case NL80211_IFTYPE_ADHOC:
@@ -2020,34 +2199,30 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
 		memcpy(hdr.addr3, sdata->u.ibss.bssid, ETH_ALEN);
 		hdrlen = 24;
 		chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
-		if (!chanctx_conf)
-			goto fail_rcu;
+		if (!chanctx_conf) {
+			ret = -ENOTCONN;
+			goto free;
+		}
 		band = chanctx_conf->def.chan->band;
 		break;
 	default:
-		goto fail_rcu;
+		ret = -EINVAL;
+		goto free;
 	}
 
-	/*
-	 * There's no need to try to look up the destination
-	 * if it is a multicast address (which can only happen
-	 * in AP mode)
-	 */
 	multicast = is_multicast_ether_addr(hdr.addr1);
-	if (!multicast) {
-		sta = sta_info_get(sdata, hdr.addr1);
-		if (sta) {
-			authorized = test_sta_flag(sta, WLAN_STA_AUTHORIZED);
-			wme_sta = sta->sta.wme;
-		}
-	}
 
-	/* For mesh, the use of the QoS header is mandatory */
-	if (ieee80211_vif_is_mesh(&sdata->vif))
+	/* sta is always NULL for mesh */
+	if (sta) {
+		authorized = test_sta_flag(sta, WLAN_STA_AUTHORIZED);
+		wme_sta = sta->sta.wme;
+	} else if (ieee80211_vif_is_mesh(&sdata->vif)) {
+		/* For mesh, the use of the QoS header is mandatory */
 		wme_sta = true;
+	}
 
-	/* receiver and we are QoS enabled, use a QoS type frame */
-	if (wme_sta && local->hw.queues >= IEEE80211_NUM_ACS) {
+	/* receiver does QoS (which also means we do) use it */
+	if (wme_sta) {
 		fc |= cpu_to_le16(IEEE80211_STYPE_QOS_DATA);
 		hdrlen += 2;
 	}
@@ -2057,17 +2232,19 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
 	 * EAPOL frames from the local station.
 	 */
 	if (unlikely(!ieee80211_vif_is_mesh(&sdata->vif) &&
+		     (sdata->vif.type != NL80211_IFTYPE_OCB) &&
 		     !multicast && !authorized &&
 		     (cpu_to_be16(ethertype) != sdata->control_port_protocol ||
 		      !ether_addr_equal(sdata->vif.addr, skb->data + ETH_ALEN)))) {
 #ifdef CONFIG_MAC80211_VERBOSE_DEBUG
 		net_info_ratelimited("%s: dropped frame to %pM (unauthorized port)\n",
-				    dev->name, hdr.addr1);
+				    sdata->name, hdr.addr1);
 #endif
 
 		I802_DEBUG_INC(local->tx_handlers_drop_unauth_port);
 
-		goto fail_rcu;
+		ret = -EPERM;
+		goto free;
 	}
 
 	if (unlikely(!multicast && skb->sk &&
@@ -2104,8 +2281,10 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
 		skb = skb_clone(skb, GFP_ATOMIC);
 		kfree_skb(tmp_skb);
 
-		if (!skb)
-			goto fail_rcu;
+		if (!skb) {
+			ret = -ENOMEM;
+			goto free;
+		}
 	}
 
 	hdr.frame_control = fc;
@@ -2154,7 +2333,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
 		if (ieee80211_skb_resize(sdata, skb, head_need, true)) {
 			ieee80211_free_txskb(&local->hw, skb);
 			skb = NULL;
-			goto fail_rcu;
+			return ERR_PTR(-ENOMEM);
 		}
 	}
 
@@ -2188,9 +2367,6 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
 	nh_pos += hdrlen;
 	h_pos += hdrlen;
 
-	dev->stats.tx_packets++;
-	dev->stats.tx_bytes += skb->len;
-
 	/* Update skb pointers to various headers since this modified frame
 	 * is going to go through Linux networking code that may potentially
 	 * need things like pointer to IP header. */
@@ -2201,23 +2377,99 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
 	info = IEEE80211_SKB_CB(skb);
 	memset(info, 0, sizeof(*info));
 
-	dev->trans_start = jiffies;
-
 	info->flags = info_flags;
 	info->ack_frame_id = info_id;
+	info->band = band;
 
-	ieee80211_xmit(sdata, skb, band);
-	rcu_read_unlock();
+	return skb;
+ free:
+	kfree_skb(skb);
+	return ERR_PTR(ret);
+}
 
-	return NETDEV_TX_OK;
+void __ieee80211_subif_start_xmit(struct sk_buff *skb,
+				  struct net_device *dev,
+				  u32 info_flags)
+{
+	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	struct sta_info *sta;
+
+	if (unlikely(skb->len < ETH_HLEN)) {
+		kfree_skb(skb);
+		return;
+	}
+
+	rcu_read_lock();
+
+	if (ieee80211_lookup_ra_sta(sdata, skb, &sta)) {
+		kfree_skb(skb);
+		goto out;
+	}
+
+	skb = ieee80211_build_hdr(sdata, skb, info_flags, sta);
+	if (IS_ERR(skb))
+		goto out;
+
+	dev->stats.tx_packets++;
+	dev->stats.tx_bytes += skb->len;
+	dev->trans_start = jiffies;
 
- fail_rcu:
+	ieee80211_xmit(sdata, sta, skb);
+ out:
 	rcu_read_unlock();
- fail:
-	dev_kfree_skb(skb);
+}
+
+/**
+ * ieee80211_subif_start_xmit - netif start_xmit function for 802.3 vifs
+ * @skb: packet to be sent
+ * @dev: incoming interface
+ *
+ * On failure skb will be freed.
+ */
+netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
+				       struct net_device *dev)
+{
+	__ieee80211_subif_start_xmit(skb, dev, 0);
 	return NETDEV_TX_OK;
 }
 
+struct sk_buff *
+ieee80211_build_data_template(struct ieee80211_sub_if_data *sdata,
+			      struct sk_buff *skb, u32 info_flags)
+{
+	struct ieee80211_hdr *hdr;
+	struct ieee80211_tx_data tx = {
+		.local = sdata->local,
+		.sdata = sdata,
+	};
+	struct sta_info *sta;
+
+	rcu_read_lock();
+
+	if (ieee80211_lookup_ra_sta(sdata, skb, &sta)) {
+		kfree_skb(skb);
+		skb = ERR_PTR(-EINVAL);
+		goto out;
+	}
+
+	skb = ieee80211_build_hdr(sdata, skb, info_flags, sta);
+	if (IS_ERR(skb))
+		goto out;
+
+	hdr = (void *)skb->data;
+	tx.sta = sta_info_get(sdata, hdr->addr1);
+	tx.skb = skb;
+
+	if (ieee80211_tx_h_select_key(&tx) != TX_CONTINUE) {
+		rcu_read_unlock();
+		kfree_skb(skb);
+		return ERR_PTR(-EINVAL);
+	}
+
+out:
+	rcu_read_unlock();
+	return skb;
+}
 
 /*
  * ieee80211_clear_tx_pending may not be called in a context where
@@ -2257,8 +2509,8 @@ static bool ieee80211_tx_pending_skb(struct ieee80211_local *local,
 			dev_kfree_skb(skb);
 			return true;
 		}
-		result = ieee80211_tx(sdata, skb, true,
-				      chanctx_conf->def.chan->band);
+		info->band = chanctx_conf->def.chan->band;
+		result = ieee80211_tx(sdata, NULL, skb, true);
 	} else {
 		struct sk_buff_head skbs;
 
@@ -2872,19 +3124,16 @@ struct sk_buff *ieee80211_nullfunc_get(struct ieee80211_hw *hw,
 EXPORT_SYMBOL(ieee80211_nullfunc_get);
 
 struct sk_buff *ieee80211_probereq_get(struct ieee80211_hw *hw,
-				       struct ieee80211_vif *vif,
+				       const u8 *src_addr,
 				       const u8 *ssid, size_t ssid_len,
 				       size_t tailroom)
 {
-	struct ieee80211_sub_if_data *sdata;
-	struct ieee80211_local *local;
+	struct ieee80211_local *local = hw_to_local(hw);
 	struct ieee80211_hdr_3addr *hdr;
 	struct sk_buff *skb;
 	size_t ie_ssid_len;
 	u8 *pos;
 
-	sdata = vif_to_sdata(vif);
-	local = sdata->local;
 	ie_ssid_len = 2 + ssid_len;
 
 	skb = dev_alloc_skb(local->hw.extra_tx_headroom + sizeof(*hdr) +
@@ -2899,7 +3148,7 @@ struct sk_buff *ieee80211_probereq_get(struct ieee80211_hw *hw,
 	hdr->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
 					 IEEE80211_STYPE_PROBE_REQ);
 	eth_broadcast_addr(hdr->addr1);
-	memcpy(hdr->addr2, vif->addr, ETH_ALEN);
+	memcpy(hdr->addr2, src_addr, ETH_ALEN);
 	eth_broadcast_addr(hdr->addr3);
 
 	pos = skb_put(skb, ie_ssid_len);
@@ -2999,7 +3248,7 @@ ieee80211_get_buffered_bc(struct ieee80211_hw *hw,
 
 		if (sdata->vif.type == NL80211_IFTYPE_AP)
 			sdata = IEEE80211_DEV_TO_SUB_IF(skb->dev);
-		if (!ieee80211_tx_prepare(sdata, &tx, skb))
+		if (!ieee80211_tx_prepare(sdata, &tx, NULL, skb))
 			break;
 		dev_kfree_skb_any(skb);
 	}
@@ -3018,6 +3267,97 @@ ieee80211_get_buffered_bc(struct ieee80211_hw *hw,
 }
 EXPORT_SYMBOL(ieee80211_get_buffered_bc);
 
+int ieee80211_reserve_tid(struct ieee80211_sta *pubsta, u8 tid)
+{
+	struct sta_info *sta = container_of(pubsta, struct sta_info, sta);
+	struct ieee80211_sub_if_data *sdata = sta->sdata;
+	struct ieee80211_local *local = sdata->local;
+	int ret;
+	u32 queues;
+
+	lockdep_assert_held(&local->sta_mtx);
+
+	/* only some cases are supported right now */
+	switch (sdata->vif.type) {
+	case NL80211_IFTYPE_STATION:
+	case NL80211_IFTYPE_AP:
+	case NL80211_IFTYPE_AP_VLAN:
+		break;
+	default:
+		WARN_ON(1);
+		return -EINVAL;
+	}
+
+	if (WARN_ON(tid >= IEEE80211_NUM_UPS))
+		return -EINVAL;
+
+	if (sta->reserved_tid == tid) {
+		ret = 0;
+		goto out;
+	}
+
+	if (sta->reserved_tid != IEEE80211_TID_UNRESERVED) {
+		sdata_err(sdata, "TID reservation already active\n");
+		ret = -EALREADY;
+		goto out;
+	}
+
+	ieee80211_stop_vif_queues(sdata->local, sdata,
+				  IEEE80211_QUEUE_STOP_REASON_RESERVE_TID);
+
+	synchronize_net();
+
+	/* Tear down BA sessions so we stop aggregating on this TID */
+	if (local->hw.flags & IEEE80211_HW_AMPDU_AGGREGATION) {
+		set_sta_flag(sta, WLAN_STA_BLOCK_BA);
+		__ieee80211_stop_tx_ba_session(sta, tid,
+					       AGG_STOP_LOCAL_REQUEST);
+	}
+
+	queues = BIT(sdata->vif.hw_queue[ieee802_1d_to_ac[tid]]);
+	__ieee80211_flush_queues(local, sdata, queues, false);
+
+	sta->reserved_tid = tid;
+
+	ieee80211_wake_vif_queues(local, sdata,
+				  IEEE80211_QUEUE_STOP_REASON_RESERVE_TID);
+
+	if (local->hw.flags & IEEE80211_HW_AMPDU_AGGREGATION)
+		clear_sta_flag(sta, WLAN_STA_BLOCK_BA);
+
+	ret = 0;
+ out:
+	return ret;
+}
+EXPORT_SYMBOL(ieee80211_reserve_tid);
+
+void ieee80211_unreserve_tid(struct ieee80211_sta *pubsta, u8 tid)
+{
+	struct sta_info *sta = container_of(pubsta, struct sta_info, sta);
+	struct ieee80211_sub_if_data *sdata = sta->sdata;
+
+	lockdep_assert_held(&sdata->local->sta_mtx);
+
+	/* only some cases are supported right now */
+	switch (sdata->vif.type) {
+	case NL80211_IFTYPE_STATION:
+	case NL80211_IFTYPE_AP:
+	case NL80211_IFTYPE_AP_VLAN:
+		break;
+	default:
+		WARN_ON(1);
+		return;
+	}
+
+	if (tid != sta->reserved_tid) {
+		sdata_err(sdata, "TID to unreserve (%d) isn't reserved\n", tid);
+		return;
+	}
+
+	sta->reserved_tid = IEEE80211_TID_UNRESERVED;
+}
+EXPORT_SYMBOL(ieee80211_unreserve_tid);
+
 void __ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata,
 				 struct sk_buff *skb, int tid,
 				 enum ieee80211_band band)
@@ -3039,6 +3379,7 @@ void __ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata,
 	 * requirements are that we do not come into tx with bhs on.
 	 */
 	local_bh_disable();
-	ieee80211_xmit(sdata, skb, band);
+	IEEE80211_SKB_CB(skb)->band = band;
+	ieee80211_xmit(sdata, NULL, skb);
 	local_bh_enable();
 }
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 3c61060a4d2b..b864ebc6ab8f 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -308,6 +308,11 @@ void ieee80211_propagate_queue_wake(struct ieee80211_local *local, int queue)
 		for (ac = 0; ac < n_acs; ac++) {
 			int ac_queue = sdata->vif.hw_queue[ac];
 
+			if (local->ops->wake_tx_queue &&
+			    (atomic_read(&sdata->txqs_len[ac]) >
+			     local->hw.txq_ac_max_pending))
+				continue;
+
 			if (ac_queue == queue ||
 			    (sdata->vif.cab_queue == queue &&
 			     local->queue_stop_reasons[ac_queue] == 0 &&
@@ -576,27 +581,37 @@ ieee80211_get_vif_queues(struct ieee80211_local *local,
 	return queues;
 }
 
-void ieee80211_flush_queues(struct ieee80211_local *local,
-			    struct ieee80211_sub_if_data *sdata)
+void __ieee80211_flush_queues(struct ieee80211_local *local,
+			      struct ieee80211_sub_if_data *sdata,
+			      unsigned int queues, bool drop)
 {
-	unsigned int queues;
-
 	if (!local->ops->flush)
 		return;
 
-	queues = ieee80211_get_vif_queues(local, sdata);
+	/*
+	 * If no queue was set, or if the HW doesn't support
+	 * IEEE80211_HW_QUEUE_CONTROL - flush all queues
+	 */
+	if (!queues || !(local->hw.flags & IEEE80211_HW_QUEUE_CONTROL))
+		queues = ieee80211_get_vif_queues(local, sdata);
 
 	ieee80211_stop_queues_by_reason(&local->hw, queues,
 					IEEE80211_QUEUE_STOP_REASON_FLUSH,
 					false);
 
-	drv_flush(local, sdata, queues, false);
+	drv_flush(local, sdata, queues, drop);
 
 	ieee80211_wake_queues_by_reason(&local->hw, queues,
 					IEEE80211_QUEUE_STOP_REASON_FLUSH,
 					false);
 }
 
+void ieee80211_flush_queues(struct ieee80211_local *local,
+			    struct ieee80211_sub_if_data *sdata, bool drop)
+{
+	__ieee80211_flush_queues(local, sdata, 0, drop);
+}
+
 void ieee80211_stop_vif_queues(struct ieee80211_local *local,
 			       struct ieee80211_sub_if_data *sdata,
 			       enum queue_stop_reason reason)
@@ -615,13 +630,14 @@ void ieee80211_wake_vif_queues(struct ieee80211_local *local,
 					reason, true);
 }
 
-static void __iterate_active_interfaces(struct ieee80211_local *local,
-					u32 iter_flags,
-					void (*iterator)(void *data, u8 *mac,
-						struct ieee80211_vif *vif),
-					void *data)
+static void __iterate_interfaces(struct ieee80211_local *local,
+				 u32 iter_flags,
+				 void (*iterator)(void *data, u8 *mac,
+						  struct ieee80211_vif *vif),
+				 void *data)
 {
 	struct ieee80211_sub_if_data *sdata;
+	bool active_only = iter_flags & IEEE80211_IFACE_ITER_ACTIVE;
 
 	list_for_each_entry_rcu(sdata, &local->interfaces, list) {
 		switch (sdata->vif.type) {
@@ -635,9 +651,9 @@ static void __iterate_active_interfaces(struct ieee80211_local *local,
 			break;
 		}
 		if (!(iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL) &&
-		    !(sdata->flags & IEEE80211_SDATA_IN_DRIVER))
+		    active_only && !(sdata->flags & IEEE80211_SDATA_IN_DRIVER))
 			continue;
-		if (ieee80211_sdata_running(sdata))
+		if (ieee80211_sdata_running(sdata) || !active_only)
 			iterator(data, sdata->vif.addr,
 				 &sdata->vif);
 	}
@@ -646,12 +662,12 @@ static void __iterate_active_interfaces(struct ieee80211_local *local,
 				      lockdep_is_held(&local->iflist_mtx) ||
 				      lockdep_rtnl_is_held());
 	if (sdata &&
-	    (iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL ||
+	    (iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL || !active_only ||
 	     sdata->flags & IEEE80211_SDATA_IN_DRIVER))
 		iterator(data, sdata->vif.addr, &sdata->vif);
 }
 
-void ieee80211_iterate_active_interfaces(
+void ieee80211_iterate_interfaces(
 	struct ieee80211_hw *hw, u32 iter_flags,
 	void (*iterator)(void *data, u8 *mac,
 			 struct ieee80211_vif *vif),
@@ -660,10 +676,10 @@ void ieee80211_iterate_active_interfaces(
 	struct ieee80211_local *local = hw_to_local(hw);
 
 	mutex_lock(&local->iflist_mtx);
-	__iterate_active_interfaces(local, iter_flags, iterator, data);
+	__iterate_interfaces(local, iter_flags, iterator, data);
 	mutex_unlock(&local->iflist_mtx);
 }
-EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces);
+EXPORT_SYMBOL_GPL(ieee80211_iterate_interfaces);
 
 void ieee80211_iterate_active_interfaces_atomic(
 	struct ieee80211_hw *hw, u32 iter_flags,
@@ -674,7 +690,8 @@ void ieee80211_iterate_active_interfaces_atomic(
 	struct ieee80211_local *local = hw_to_local(hw);
 
 	rcu_read_lock();
-	__iterate_active_interfaces(local, iter_flags, iterator, data);
+	__iterate_interfaces(local, iter_flags | IEEE80211_IFACE_ITER_ACTIVE,
+			     iterator, data);
 	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces_atomic);
@@ -689,10 +706,39 @@ void ieee80211_iterate_active_interfaces_rtnl(
 
 	ASSERT_RTNL();
 
-	__iterate_active_interfaces(local, iter_flags, iterator, data);
+	__iterate_interfaces(local, iter_flags | IEEE80211_IFACE_ITER_ACTIVE,
+			     iterator, data);
 }
 EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces_rtnl);
 
+static void __iterate_stations(struct ieee80211_local *local,
+			       void (*iterator)(void *data,
+						struct ieee80211_sta *sta),
+			       void *data)
+{
+	struct sta_info *sta;
+
+	list_for_each_entry_rcu(sta, &local->sta_list, list) {
+		if (!sta->uploaded)
+			continue;
+
+		iterator(data, &sta->sta);
+	}
+}
+
+void ieee80211_iterate_stations_atomic(struct ieee80211_hw *hw,
+			void (*iterator)(void *data,
+					 struct ieee80211_sta *sta),
+			void *data)
+{
+	struct ieee80211_local *local = hw_to_local(hw);
+
+	rcu_read_lock();
+	__iterate_stations(local, iterator, data);
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(ieee80211_iterate_stations_atomic);
+
 struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
@@ -704,18 +750,33 @@ struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev)
 }
 EXPORT_SYMBOL_GPL(wdev_to_ieee80211_vif);
 
+struct wireless_dev *ieee80211_vif_to_wdev(struct ieee80211_vif *vif)
+{
+	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
+
+	if (!ieee80211_sdata_running(sdata) ||
+	    !(sdata->flags & IEEE80211_SDATA_IN_DRIVER))
+		return NULL;
+
+	return &sdata->wdev;
+}
+EXPORT_SYMBOL_GPL(ieee80211_vif_to_wdev);
+
 /*
  * Nothing should have been stuffed into the workqueue during
- * the suspend->resume cycle. If this WARN is seen then there
- * is a bug with either the driver suspend or something in
- * mac80211 stuffing into the workqueue which we haven't yet
- * cleared during mac80211's suspend cycle.
+ * the suspend->resume cycle. Since we can't check each caller
+ * of this function if we are already quiescing / suspended,
+ * check here and don't WARN since this can actually happen when
+ * the rx path (for example) is racing against __ieee80211_suspend
+ * and suspending / quiescing was set after the rx path checked
+ * them.
  */
 static bool ieee80211_can_queue_work(struct ieee80211_local *local)
 {
-	if (WARN(local->suspended && !local->resuming,
-		 "queueing ieee80211 work while going to suspend\n"))
+	if (local->quiescing || (local->suspended && !local->resuming)) {
+		pr_warn("queueing ieee80211 work while going to suspend\n");
 		return false;
+	}
 
 	return true;
 }
@@ -803,6 +864,9 @@ u32 ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action,
 		case WLAN_EID_SECONDARY_CHANNEL_OFFSET:
 		case WLAN_EID_WIDE_BW_CHANNEL_SWITCH:
 		case WLAN_EID_CHAN_SWITCH_PARAM:
+		case WLAN_EID_EXT_CAPABILITY:
+		case WLAN_EID_CHAN_SWITCH_TIMING:
+		case WLAN_EID_LINK_ID:
 		/*
 		 * not listing WLAN_EID_CHANNEL_SWITCH_WRAPPER -- it seems possible
 		 * that if the content gets bigger it might be needed more than once
@@ -822,6 +886,24 @@ u32 ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action,
 		elem_parse_failed = false;
 
 		switch (id) {
+		case WLAN_EID_LINK_ID:
+			if (elen + 2 != sizeof(struct ieee80211_tdls_lnkie)) {
+				elem_parse_failed = true;
+				break;
+			}
+			elems->lnk_id = (void *)(pos - 2);
+			break;
+		case WLAN_EID_CHAN_SWITCH_TIMING:
+			if (elen != sizeof(struct ieee80211_ch_switch_timing)) {
+				elem_parse_failed = true;
+				break;
+			}
+			elems->ch_sw_timing = (void *)pos;
+			break;
+		case WLAN_EID_EXT_CAPABILITY:
+			elems->ext_capab = pos;
+			elems->ext_capab_len = elen;
+			break;
 		case WLAN_EID_SSID:
 			elems->ssid = pos;
 			elems->ssid_len = elen;
@@ -1073,6 +1155,7 @@ void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_chanctx_conf *chanctx_conf;
 	int ac;
 	bool use_11b, enable_qos;
+	bool is_ocb; /* Use another EDCA parameters if dot11OCBActivated=true */
 	int aCWmin, aCWmax;
 
 	if (!local->ops->conf_tx)
@@ -1097,6 +1180,8 @@ void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata,
 	 */
 	enable_qos = (sdata->vif.type != NL80211_IFTYPE_STATION);
 
+	is_ocb = (sdata->vif.type == NL80211_IFTYPE_OCB);
+
 	/* Set defaults according to 802.11-2007 Table 7-37 */
 	aCWmax = 1023;
 	if (use_11b)
@@ -1118,7 +1203,10 @@ void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata,
 				qparam.cw_max = aCWmax;
 				qparam.cw_min = aCWmin;
 				qparam.txop = 0;
-				qparam.aifs = 7;
+				if (is_ocb)
+					qparam.aifs = 9;
+				else
+					qparam.aifs = 7;
 				break;
 			/* never happens but let's not leave undefined */
 			default:
@@ -1126,21 +1214,32 @@ void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata,
 				qparam.cw_max = aCWmax;
 				qparam.cw_min = aCWmin;
 				qparam.txop = 0;
-				qparam.aifs = 3;
+				if (is_ocb)
+					qparam.aifs = 6;
+				else
+					qparam.aifs = 3;
 				break;
 			case IEEE80211_AC_VI:
 				qparam.cw_max = aCWmin;
 				qparam.cw_min = (aCWmin + 1) / 2 - 1;
-				if (use_11b)
+				if (is_ocb)
+					qparam.txop = 0;
+				else if (use_11b)
 					qparam.txop = 6016/32;
 				else
 					qparam.txop = 3008/32;
-				qparam.aifs = 2;
+
+				if (is_ocb)
+					qparam.aifs = 3;
+				else
+					qparam.aifs = 2;
 				break;
 			case IEEE80211_AC_VO:
 				qparam.cw_max = (aCWmin + 1) / 2 - 1;
 				qparam.cw_min = (aCWmin + 1) / 4 - 1;
-				if (use_11b)
+				if (is_ocb)
+					qparam.txop = 0;
+				else if (use_11b)
 					qparam.txop = 3264/32;
 				else
 					qparam.txop = 1504/32;
@@ -1263,6 +1362,7 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_local *local,
 	int ext_rates_len;
 	int shift;
 	u32 rate_flags;
+	bool have_80mhz = false;
 
 	*offset = 0;
 
@@ -1391,7 +1491,17 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_local *local,
 		*offset = noffset;
 	}
 
-	if (sband->vht_cap.vht_supported) {
+	/* Check if any channel in this sband supports at least 80 MHz */
+	for (i = 0; i < sband->n_channels; i++) {
+		if (sband->channels[i].flags & (IEEE80211_CHAN_DISABLED |
+						IEEE80211_CHAN_NO_80MHZ))
+			continue;
+
+		have_80mhz = true;
+		break;
+	}
+
+	if (sband->vht_cap.vht_supported && have_80mhz) {
 		if (end - pos < 2 + sizeof(struct ieee80211_vht_cap))
 			goto out_err;
 		pos = ieee80211_ie_build_vht_cap(pos, &sband->vht_cap,
@@ -1447,7 +1557,8 @@ int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer,
 };
 
 struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata,
-					  u8 *dst, u32 ratemask,
+					  const u8 *src, const u8 *dst,
+					  u32 ratemask,
 					  struct ieee80211_channel *chan,
 					  const u8 *ssid, size_t ssid_len,
 					  const u8 *ie, size_t ie_len,
@@ -1472,8 +1583,8 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata,
 	else
 		chandef.chan = chan;
 
-	skb = ieee80211_probereq_get(&local->hw, &sdata->vif,
-				     ssid, ssid_len, 100 + ie_len);
+	skb = ieee80211_probereq_get(&local->hw, src, ssid, ssid_len,
+				     100 + ie_len);
 	if (!skb)
 		return NULL;
 
@@ -1495,7 +1606,8 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata,
 	return skb;
 }
 
-void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata, u8 *dst,
+void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata,
+			      const u8 *src, const u8 *dst,
 			      const u8 *ssid, size_t ssid_len,
 			      const u8 *ie, size_t ie_len,
 			      u32 ratemask, bool directed, u32 tx_flags,
@@ -1503,7 +1615,7 @@ void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata, u8 *dst,
 {
 	struct sk_buff *skb;
 
-	skb = ieee80211_build_probe_req(sdata, dst, ratemask, channel,
+	skb = ieee80211_build_probe_req(sdata, src, dst, ratemask, channel,
 					ssid, ssid_len,
 					ie, ie_len, directed);
 	if (skb) {
@@ -1645,8 +1757,13 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 	int res, i;
 	bool reconfig_due_to_wowlan = false;
 	struct ieee80211_sub_if_data *sched_scan_sdata;
+	struct cfg80211_sched_scan_request *sched_scan_req;
 	bool sched_scan_stopped = false;
 
+	/* nothing to do if HW shouldn't run */
+	if (!local->open_count)
+		goto wake_up;
+
 #ifdef CONFIG_PM
 	if (local->suspended)
 		local->resuming = true;
@@ -1668,9 +1785,6 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 		reconfig_due_to_wowlan = true;
 	}
 #endif
-	/* everything else happens only if HW was up & running */
-	if (!local->open_count)
-		goto wake_up;
 
 	/*
 	 * Upon resume hardware can sometimes be goofy due to
@@ -1717,8 +1831,25 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 	list_for_each_entry(sdata, &local->interfaces, list) {
 		if (sdata->vif.type != NL80211_IFTYPE_AP_VLAN &&
 		    sdata->vif.type != NL80211_IFTYPE_MONITOR &&
-		    ieee80211_sdata_running(sdata))
+		    ieee80211_sdata_running(sdata)) {
 			res = drv_add_interface(local, sdata);
+			if (WARN_ON(res))
+				break;
+		}
+	}
+
+	/* If adding any of the interfaces failed above, roll back and
+	 * report failure.
+	 */
+	if (res) {
+		list_for_each_entry_continue_reverse(sdata, &local->interfaces,
+						     list)
+			if (sdata->vif.type != NL80211_IFTYPE_AP_VLAN &&
+			    sdata->vif.type != NL80211_IFTYPE_MONITOR &&
+			    ieee80211_sdata_running(sdata))
+				drv_remove_interface(local, sdata);
+		ieee80211_handle_reconfig_failure(local);
+		return res;
 	}
 
 	/* add channel contexts */
@@ -1813,6 +1944,10 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 			ieee80211_bss_info_change_notify(sdata, changed);
 			sdata_unlock(sdata);
 			break;
+		case NL80211_IFTYPE_OCB:
+			changed |= BSS_CHANGED_OCB;
+			ieee80211_bss_info_change_notify(sdata, changed);
+			break;
 		case NL80211_IFTYPE_ADHOC:
 			changed |= BSS_CHANGED_IBSS;
 			/* fall through */
@@ -1888,6 +2023,9 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 
 	/* add back keys */
 	list_for_each_entry(sdata, &local->interfaces, list)
+		ieee80211_reset_crypto_tx_tailroom(sdata);
+
+	list_for_each_entry(sdata, &local->interfaces, list)
 		if (ieee80211_sdata_running(sdata))
 			ieee80211_enable_keys(sdata);
 
@@ -1931,13 +2069,15 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 	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_req = rcu_dereference_protected(local->sched_scan_req,
+						lockdep_is_held(&local->mtx));
+	if (sched_scan_sdata && 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_req))
 			sched_scan_stopped = true;
 	mutex_unlock(&local->mtx);
 
@@ -1948,8 +2088,8 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 	 * If this is for hw restart things are still running.
 	 * We may want to change that later, however.
 	 */
-	if (!local->suspended || reconfig_due_to_wowlan)
-		drv_restart_complete(local);
+	if (local->open_count && (!local->suspended || reconfig_due_to_wowlan))
+		drv_reconfig_complete(local, IEEE80211_RECONFIG_TYPE_RESTART);
 
 	if (!local->suspended)
 		return 0;
@@ -1960,6 +2100,21 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 	mb();
 	local->resuming = false;
 
+	/* It's possible that we don't handle the scan completion in
+	 * time during suspend, so if it's still marked as completed
+	 * here, queue the work and flush it to clean things up.
+	 * Instead of calling the worker function directly here, we
+	 * really queue it to avoid potential races with other flows
+	 * scheduling the same work.
+	 */
+	if (test_bit(SCAN_COMPLETED, &local->scanning)) {
+		ieee80211_queue_delayed_work(&local->hw, &local->scan_work, 0);
+		flush_delayed_work(&local->scan_work);
+	}
+
+	if (local->open_count && !reconfig_due_to_wowlan)
+		drv_reconfig_complete(local, IEEE80211_RECONFIG_TYPE_SUSPEND);
+
 	list_for_each_entry(sdata, &local->interfaces, list) {
 		if (!ieee80211_sdata_running(sdata))
 			continue;
@@ -2042,52 +2197,6 @@ void ieee80211_recalc_min_chandef(struct ieee80211_sub_if_data *sdata)
 	mutex_unlock(&local->chanctx_mtx);
 }
 
-static bool ieee80211_id_in_list(const u8 *ids, int n_ids, u8 id)
-{
-	int i;
-
-	for (i = 0; i < n_ids; i++)
-		if (ids[i] == id)
-			return true;
-	return false;
-}
-
-/**
- * ieee80211_ie_split - split an IE buffer according to ordering
- *
- * @ies: the IE buffer
- * @ielen: the length of the IE buffer
- * @ids: an array with element IDs that are allowed before
- *	the split
- * @n_ids: the size of the element ID array
- * @offset: offset where to start splitting in the buffer
- *
- * This function splits an IE buffer by updating the @offset
- * variable to point to the location where the buffer should be
- * split.
- *
- * It assumes that the given IE buffer is well-formed, this
- * has to be guaranteed by the caller!
- *
- * It also assumes that the IEs in the buffer are ordered
- * correctly, if not the result of using this function will not
- * be ordered correctly either, i.e. it does no reordering.
- *
- * The function returns the offset where the next part of the
- * buffer starts, which may be @ielen if the entire (remainder)
- * of the buffer should be used.
- */
-size_t ieee80211_ie_split(const u8 *ies, size_t ielen,
-			  const u8 *ids, int n_ids, size_t offset)
-{
-	size_t pos = offset;
-
-	while (pos < ielen && ieee80211_id_in_list(ids, n_ids, ies[pos]))
-		pos += 2 + ies[pos + 1];
-
-	return pos;
-}
-
 size_t ieee80211_ie_split_vendor(const u8 *ies, size_t ielen, size_t offset)
 {
 	size_t pos = offset;
@@ -2235,6 +2344,41 @@ u8 *ieee80211_ie_build_ht_oper(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap,
 	return pos + sizeof(struct ieee80211_ht_operation);
 }
 
+u8 *ieee80211_ie_build_vht_oper(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap,
+				const struct cfg80211_chan_def *chandef)
+{
+	struct ieee80211_vht_operation *vht_oper;
+
+	*pos++ = WLAN_EID_VHT_OPERATION;
+	*pos++ = sizeof(struct ieee80211_vht_operation);
+	vht_oper = (struct ieee80211_vht_operation *)pos;
+	vht_oper->center_freq_seg1_idx = ieee80211_frequency_to_channel(
+							chandef->center_freq1);
+	if (chandef->center_freq2)
+		vht_oper->center_freq_seg2_idx =
+			ieee80211_frequency_to_channel(chandef->center_freq2);
+
+	switch (chandef->width) {
+	case NL80211_CHAN_WIDTH_160:
+		vht_oper->chan_width = IEEE80211_VHT_CHANWIDTH_160MHZ;
+		break;
+	case NL80211_CHAN_WIDTH_80P80:
+		vht_oper->chan_width = IEEE80211_VHT_CHANWIDTH_80P80MHZ;
+		break;
+	case NL80211_CHAN_WIDTH_80:
+		vht_oper->chan_width = IEEE80211_VHT_CHANWIDTH_80MHZ;
+		break;
+	default:
+		vht_oper->chan_width = IEEE80211_VHT_CHANWIDTH_USE_HT;
+		break;
+	}
+
+	/* don't require special VHT peer rates */
+	vht_oper->basic_mcs_set = cpu_to_le16(0xffff);
+
+	return pos + sizeof(struct ieee80211_vht_operation);
+}
+
 void ieee80211_ht_oper_to_chandef(struct ieee80211_channel *control_chan,
 				  const struct ieee80211_ht_operation *ht_oper,
 				  struct cfg80211_chan_def *chandef)
@@ -2264,6 +2408,39 @@ void ieee80211_ht_oper_to_chandef(struct ieee80211_channel *control_chan,
 	cfg80211_chandef_create(chandef, control_chan, channel_type);
 }
 
+void ieee80211_vht_oper_to_chandef(struct ieee80211_channel *control_chan,
+				   const struct ieee80211_vht_operation *oper,
+				   struct cfg80211_chan_def *chandef)
+{
+	if (!oper)
+		return;
+
+	chandef->chan = control_chan;
+
+	switch (oper->chan_width) {
+	case IEEE80211_VHT_CHANWIDTH_USE_HT:
+		break;
+	case IEEE80211_VHT_CHANWIDTH_80MHZ:
+		chandef->width = NL80211_CHAN_WIDTH_80;
+		break;
+	case IEEE80211_VHT_CHANWIDTH_160MHZ:
+		chandef->width = NL80211_CHAN_WIDTH_160;
+		break;
+	case IEEE80211_VHT_CHANWIDTH_80P80MHZ:
+		chandef->width = NL80211_CHAN_WIDTH_80P80;
+		break;
+	default:
+		break;
+	}
+
+	chandef->center_freq1 =
+		ieee80211_channel_to_frequency(oper->center_freq_seg1_idx,
+					       control_chan->band);
+	chandef->center_freq2 =
+		ieee80211_channel_to_frequency(oper->center_freq_seg2_idx,
+					       control_chan->band);
+}
+
 int ieee80211_parse_bitrates(struct cfg80211_chan_def *chandef,
 			     const struct ieee80211_supported_band *sband,
 			     const u8 *srates, int srates_len, u32 *rates)
@@ -2447,7 +2624,9 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 		ri.mcs = status->rate_idx;
 		ri.flags |= RATE_INFO_FLAGS_MCS;
 		if (status->flag & RX_FLAG_40MHZ)
-			ri.flags |= RATE_INFO_FLAGS_40_MHZ_WIDTH;
+			ri.bw = RATE_INFO_BW_40;
+		else
+			ri.bw = RATE_INFO_BW_20;
 		if (status->flag & RX_FLAG_SHORT_GI)
 			ri.flags |= RATE_INFO_FLAGS_SHORT_GI;
 	} else if (status->flag & RX_FLAG_VHT) {
@@ -2455,13 +2634,13 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 		ri.mcs = status->rate_idx;
 		ri.nss = status->vht_nss;
 		if (status->flag & RX_FLAG_40MHZ)
-			ri.flags |= RATE_INFO_FLAGS_40_MHZ_WIDTH;
-		if (status->vht_flag & RX_VHT_FLAG_80MHZ)
-			ri.flags |= RATE_INFO_FLAGS_80_MHZ_WIDTH;
-		if (status->vht_flag & RX_VHT_FLAG_80P80MHZ)
-			ri.flags |= RATE_INFO_FLAGS_80P80_MHZ_WIDTH;
-		if (status->vht_flag & RX_VHT_FLAG_160MHZ)
-			ri.flags |= RATE_INFO_FLAGS_160_MHZ_WIDTH;
+			ri.bw = RATE_INFO_BW_40;
+		else if (status->vht_flag & RX_VHT_FLAG_80MHZ)
+			ri.bw = RATE_INFO_BW_80;
+		else if (status->vht_flag & RX_VHT_FLAG_160MHZ)
+			ri.bw = RATE_INFO_BW_160;
+		else
+			ri.bw = RATE_INFO_BW_20;
 		if (status->flag & RX_FLAG_SHORT_GI)
 			ri.flags |= RATE_INFO_FLAGS_SHORT_GI;
 	} else {
@@ -2469,10 +2648,15 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 		int shift = 0;
 		int bitrate;
 
-		if (status->flag & RX_FLAG_10MHZ)
+		if (status->flag & RX_FLAG_10MHZ) {
 			shift = 1;
-		if (status->flag & RX_FLAG_5MHZ)
+			ri.bw = RATE_INFO_BW_10;
+		} else if (status->flag & RX_FLAG_5MHZ) {
 			shift = 2;
+			ri.bw = RATE_INFO_BW_5;
+		} else {
+			ri.bw = RATE_INFO_BW_20;
+		}
 
 		sband = local->hw.wiphy->bands[status->band];
 		bitrate = sband->bitrates[status->rate_idx].bitrate;
@@ -2526,11 +2710,23 @@ void ieee80211_dfs_radar_detected_work(struct work_struct *work)
 	struct ieee80211_local *local =
 		container_of(work, struct ieee80211_local, radar_detected_work);
 	struct cfg80211_chan_def chandef = local->hw.conf.chandef;
+	struct ieee80211_chanctx *ctx;
+	int num_chanctx = 0;
+
+	mutex_lock(&local->chanctx_mtx);
+	list_for_each_entry(ctx, &local->chanctx_list, list) {
+		if (ctx->replace_state == IEEE80211_CHANCTX_REPLACES_OTHER)
+			continue;
+
+		num_chanctx++;
+		chandef = ctx->conf.def;
+	}
+	mutex_unlock(&local->chanctx_mtx);
 
 	ieee80211_dfs_cac_cancel(local);
 
-	if (local->use_chanctx)
-		/* currently not handled */
+	if (num_chanctx > 1)
+		/* XXX: multi-channel is not supported yet */
 		WARN_ON(1);
 	else
 		cfg80211_radar_event(local->hw.wiphy, &chandef, GFP_KERNEL);
@@ -3050,7 +3246,7 @@ int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata,
 		wdev_iter = &sdata_iter->wdev;
 
 		if (sdata_iter == sdata ||
-		    rcu_access_pointer(sdata_iter->vif.chanctx_conf) == NULL ||
+		    !ieee80211_sdata_running(sdata_iter) ||
 		    local->hw.wiphy->software_iftypes & BIT(wdev_iter->iftype))
 			continue;
 
@@ -3124,3 +3320,20 @@ u8 *ieee80211_add_wmm_info_ie(u8 *buf, u8 qosinfo)
 
 	return buf;
 }
+
+void ieee80211_init_tx_queue(struct ieee80211_sub_if_data *sdata,
+			     struct sta_info *sta,
+			     struct txq_info *txqi, int tid)
+{
+	skb_queue_head_init(&txqi->queue);
+	txqi->txq.vif = &sdata->vif;
+
+	if (sta) {
+		txqi->txq.sta = &sta->sta;
+		sta->sta.txq[tid] = &txqi->txq;
+		txqi->txq.ac = ieee802_1d_to_ac[tid & 7];
+	} else {
+		sdata->vif.txq = &txqi->txq;
+		txqi->txq.ac = IEEE80211_AC_BE;
+	}
+}
diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c
index 671ce0d27a80..80694d55db74 100644
--- a/net/mac80211/vht.c
+++ b/net/mac80211/vht.c
@@ -129,10 +129,6 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata,
 	if (!vht_cap_ie || !sband->vht_cap.vht_supported)
 		return;
 
-	/* don't support VHT for TDLS peers for now */
-	if (test_sta_flag(sta, WLAN_STA_TDLS_PEER))
-		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
@@ -269,49 +265,54 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata,
 	sta->sta.bandwidth = ieee80211_sta_cur_vht_bw(sta);
 }
 
-enum ieee80211_sta_rx_bandwidth ieee80211_sta_cur_vht_bw(struct sta_info *sta)
+enum ieee80211_sta_rx_bandwidth ieee80211_sta_cap_rx_bw(struct sta_info *sta)
 {
-	struct ieee80211_sub_if_data *sdata = sta->sdata;
-	u32 cap = sta->sta.vht_cap.cap;
-	enum ieee80211_sta_rx_bandwidth bw;
+	struct ieee80211_sta_vht_cap *vht_cap = &sta->sta.vht_cap;
+	u32 cap_width;
 
-	if (!sta->sta.vht_cap.vht_supported) {
-		bw = sta->sta.ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 ?
-				IEEE80211_STA_RX_BW_40 : IEEE80211_STA_RX_BW_20;
-		goto check_max;
-	}
+	if (!vht_cap->vht_supported)
+		return sta->sta.ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 ?
+				IEEE80211_STA_RX_BW_40 :
+				IEEE80211_STA_RX_BW_20;
 
-	switch (sdata->vif.bss_conf.chandef.width) {
-	default:
-		WARN_ON_ONCE(1);
-		/* fall through */
+	cap_width = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK;
+
+	if (cap_width == IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ ||
+	    cap_width == IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ)
+		return IEEE80211_STA_RX_BW_160;
+
+	return IEEE80211_STA_RX_BW_80;
+}
+
+static enum ieee80211_sta_rx_bandwidth
+ieee80211_chan_width_to_rx_bw(enum nl80211_chan_width width)
+{
+	switch (width) {
 	case NL80211_CHAN_WIDTH_20_NOHT:
 	case NL80211_CHAN_WIDTH_20:
+		return IEEE80211_STA_RX_BW_20;
 	case NL80211_CHAN_WIDTH_40:
-		bw = sta->sta.ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 ?
-				IEEE80211_STA_RX_BW_40 : IEEE80211_STA_RX_BW_20;
-		break;
+		return IEEE80211_STA_RX_BW_40;
+	case NL80211_CHAN_WIDTH_80:
+		return IEEE80211_STA_RX_BW_80;
 	case NL80211_CHAN_WIDTH_160:
-		if ((cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK) ==
-				IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ) {
-			bw = IEEE80211_STA_RX_BW_160;
-			break;
-		}
-		/* fall through */
 	case NL80211_CHAN_WIDTH_80P80:
-		if ((cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK) ==
-				IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) {
-			bw = IEEE80211_STA_RX_BW_160;
-			break;
-		}
-		/* fall through */
-	case NL80211_CHAN_WIDTH_80:
-		bw = IEEE80211_STA_RX_BW_80;
+		return IEEE80211_STA_RX_BW_160;
+	default:
+		WARN_ON_ONCE(1);
+		return IEEE80211_STA_RX_BW_20;
 	}
+}
+
+enum ieee80211_sta_rx_bandwidth ieee80211_sta_cur_vht_bw(struct sta_info *sta)
+{
+	struct ieee80211_sub_if_data *sdata = sta->sdata;
+	enum ieee80211_sta_rx_bandwidth bw;
+
+	bw = ieee80211_chan_width_to_rx_bw(sdata->vif.bss_conf.chandef.width);
+	bw = min(bw, ieee80211_sta_cap_rx_bw(sta));
+	bw = min(bw, sta->cur_max_bandwidth);
 
- check_max:
-	if (bw > sta->cur_max_bandwidth)
-		bw = sta->cur_max_bandwidth;
 	return bw;
 }
 
diff --git a/net/mac80211/wep.c b/net/mac80211/wep.c
index 9181fb6d6437..efa3f48f1ec5 100644
--- a/net/mac80211/wep.c
+++ b/net/mac80211/wep.c
@@ -98,8 +98,7 @@ static u8 *ieee80211_wep_add_iv(struct ieee80211_local *local,
 
 	hdr->frame_control |= cpu_to_le16(IEEE80211_FCTL_PROTECTED);
 
-	if (WARN_ON(skb_tailroom(skb) < IEEE80211_WEP_ICV_LEN ||
-		    skb_headroom(skb) < IEEE80211_WEP_IV_LEN))
+	if (WARN_ON(skb_headroom(skb) < IEEE80211_WEP_IV_LEN))
 		return NULL;
 
 	hdrlen = ieee80211_hdrlen(hdr->frame_control);
@@ -111,8 +110,6 @@ static u8 *ieee80211_wep_add_iv(struct ieee80211_local *local,
 	    (info->control.hw_key->flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE))
 		return newhdr + hdrlen;
 
-	skb_set_network_header(skb, skb_network_offset(skb) +
-				    IEEE80211_WEP_IV_LEN);
 	ieee80211_wep_get_iv(local, keylen, keyidx, newhdr + hdrlen);
 	return newhdr + hdrlen;
 }
@@ -169,6 +166,9 @@ int ieee80211_wep_encrypt(struct ieee80211_local *local,
 	size_t len;
 	u8 rc4key[3 + WLAN_KEY_LEN_WEP104];
 
+	if (WARN_ON(skb_tailroom(skb) < IEEE80211_WEP_ICV_LEN))
+		return -1;
+
 	iv = ieee80211_wep_add_iv(local, skb, keylen, keyidx);
 	if (!iv)
 		return -1;
diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c
index 3b873989992c..9eb0aee9105b 100644
--- a/net/mac80211/wme.c
+++ b/net/mac80211/wme.c
@@ -53,11 +53,49 @@ static int wme_downgrade_ac(struct sk_buff *skb)
 	}
 }
 
+/**
+ * ieee80211_fix_reserved_tid - return the TID to use if this one is reserved
+ * @tid: the assumed-reserved TID
+ *
+ * Returns: the alternative TID to use, or 0 on error
+ */
+static inline u8 ieee80211_fix_reserved_tid(u8 tid)
+{
+	switch (tid) {
+	case 0:
+		return 3;
+	case 1:
+		return 2;
+	case 2:
+		return 1;
+	case 3:
+		return 0;
+	case 4:
+		return 5;
+	case 5:
+		return 4;
+	case 6:
+		return 7;
+	case 7:
+		return 6;
+	}
+
+	return 0;
+}
+
 static u16 ieee80211_downgrade_queue(struct ieee80211_sub_if_data *sdata,
-				     struct sk_buff *skb)
+				     struct sta_info *sta, struct sk_buff *skb)
 {
+	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+
 	/* in case we are a client verify acm is not set for this ac */
-	while (unlikely(sdata->wmm_acm & BIT(skb->priority))) {
+	while (sdata->wmm_acm & BIT(skb->priority)) {
+		int ac = ieee802_1d_to_ac[skb->priority];
+
+		if (ifmgd->tx_tspec[ac].admitted_time &&
+		    skb->priority == ifmgd->tx_tspec[ac].up)
+			return ac;
+
 		if (wme_downgrade_ac(skb)) {
 			/*
 			 * This should not really happen. The AP has marked all
@@ -69,6 +107,10 @@ static u16 ieee80211_downgrade_queue(struct ieee80211_sub_if_data *sdata,
 		}
 	}
 
+	/* Check to see if this is a reserved TID */
+	if (sta && sta->reserved_tid == skb->priority)
+		skb->priority = ieee80211_fix_reserved_tid(skb->priority);
+
 	/* look up which queue to use for frames with this 1d tag */
 	return ieee802_1d_to_ac[skb->priority];
 }
@@ -96,7 +138,7 @@ u16 ieee80211_select_queue_80211(struct ieee80211_sub_if_data *sdata,
 	p = ieee80211_get_qos_ctl(hdr);
 	skb->priority = *p & IEEE80211_QOS_CTL_TAG1D_MASK;
 
-	return ieee80211_downgrade_queue(sdata, skb);
+	return ieee80211_downgrade_queue(sdata, NULL, skb);
 }
 
 /* Indicate which queue to use. */
@@ -108,6 +150,7 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata,
 	const u8 *ra = NULL;
 	bool qos = false;
 	struct mac80211_qos_map *qos_map;
+	u16 ret;
 
 	if (local->hw.queues < IEEE80211_NUM_ACS || skb->len < 6) {
 		skb->priority = 0; /* required for correct WPA/11i MIC */
@@ -134,11 +177,20 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata,
 		break;
 #endif
 	case NL80211_IFTYPE_STATION:
+		/* might be a TDLS station */
+		sta = sta_info_get(sdata, skb->data);
+		if (sta)
+			qos = sta->sta.wme;
+
 		ra = sdata->u.mgd.bssid;
 		break;
 	case NL80211_IFTYPE_ADHOC:
 		ra = skb->data;
 		break;
+	case NL80211_IFTYPE_OCB:
+		/* all stations are required to support WME */
+		qos = true;
+		break;
 	default:
 		break;
 	}
@@ -148,27 +200,29 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata,
 		if (sta)
 			qos = sta->sta.wme;
 	}
-	rcu_read_unlock();
 
 	if (!qos) {
 		skb->priority = 0; /* required for correct WPA/11i MIC */
-		return IEEE80211_AC_BE;
+		ret = IEEE80211_AC_BE;
+		goto out;
 	}
 
 	if (skb->protocol == sdata->control_port_protocol) {
 		skb->priority = 7;
-		return ieee80211_downgrade_queue(sdata, skb);
+		goto downgrade;
 	}
 
 	/* use the data classifier to determine what 802.1d tag the
 	 * data frame has */
-	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);
+ downgrade:
+	ret = ieee80211_downgrade_queue(sdata, sta, skb);
+ out:
+	rcu_read_unlock();
+	return ret;
 }
 
 /**
diff --git a/net/mac80211/wme.h b/net/mac80211/wme.h
index 7fea4bb8acbc..80151edc5195 100644
--- a/net/mac80211/wme.h
+++ b/net/mac80211/wme.h
@@ -13,8 +13,6 @@
 #include <linux/netdevice.h>
 #include "ieee80211_i.h"
 
-extern const int ieee802_1d_to_ac[8];
-
 u16 ieee80211_select_queue_80211(struct ieee80211_sub_if_data *sdata,
 				 struct sk_buff *skb,
 				 struct ieee80211_hdr *hdr);
diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c
index 983527a4c1ab..9d63d93c836e 100644
--- a/net/mac80211/wpa.c
+++ b/net/mac80211/wpa.c
@@ -22,6 +22,8 @@
 #include "tkip.h"
 #include "aes_ccm.h"
 #include "aes_cmac.h"
+#include "aes_gmac.h"
+#include "aes_gcm.h"
 #include "wpa.h"
 
 ieee80211_tx_result
@@ -209,8 +211,6 @@ static int tkip_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb)
 
 	pos = skb_push(skb, IEEE80211_TKIP_IV_LEN);
 	memmove(pos, pos + IEEE80211_TKIP_IV_LEN, hdrlen);
-	skb_set_network_header(skb, skb_network_offset(skb) +
-				    IEEE80211_TKIP_IV_LEN);
 	pos += hdrlen;
 
 	/* the HW only needs room for the IV, but not the actual IV */
@@ -395,7 +395,8 @@ static inline void ccmp_hdr2pn(u8 *pn, u8 *hdr)
 }
 
 
-static int ccmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb)
+static int ccmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb,
+			    unsigned int mic_len)
 {
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
 	struct ieee80211_key *key = tx->key;
@@ -426,7 +427,7 @@ static int ccmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb)
 	if (info->control.hw_key)
 		tail = 0;
 	else
-		tail = IEEE80211_CCMP_MIC_LEN;
+		tail = mic_len;
 
 	if (WARN_ON(skb_tailroom(skb) < tail ||
 		    skb_headroom(skb) < IEEE80211_CCMP_HDR_LEN))
@@ -434,8 +435,6 @@ static int ccmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb)
 
 	pos = skb_push(skb, IEEE80211_CCMP_HDR_LEN);
 	memmove(pos, pos + IEEE80211_CCMP_HDR_LEN, hdrlen);
-	skb_set_network_header(skb, skb_network_offset(skb) +
-				    IEEE80211_CCMP_HDR_LEN);
 
 	/* the HW only needs room for the IV, but not the actual IV */
 	if (info->control.hw_key &&
@@ -463,21 +462,22 @@ static int ccmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb)
 	pos += IEEE80211_CCMP_HDR_LEN;
 	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));
+				  skb_put(skb, mic_len), mic_len);
 
 	return 0;
 }
 
 
 ieee80211_tx_result
-ieee80211_crypto_ccmp_encrypt(struct ieee80211_tx_data *tx)
+ieee80211_crypto_ccmp_encrypt(struct ieee80211_tx_data *tx,
+			      unsigned int mic_len)
 {
 	struct sk_buff *skb;
 
 	ieee80211_tx_set_protected(tx);
 
 	skb_queue_walk(&tx->skbs, skb) {
-		if (ccmp_encrypt_skb(tx, skb) < 0)
+		if (ccmp_encrypt_skb(tx, skb, mic_len) < 0)
 			return TX_DROP;
 	}
 
@@ -486,7 +486,8 @@ ieee80211_crypto_ccmp_encrypt(struct ieee80211_tx_data *tx)
 
 
 ieee80211_rx_result
-ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx)
+ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx,
+			      unsigned int mic_len)
 {
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data;
 	int hdrlen;
@@ -503,8 +504,7 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx)
 	    !ieee80211_is_robust_mgmt_frame(skb))
 		return RX_CONTINUE;
 
-	data_len = skb->len - hdrlen - IEEE80211_CCMP_HDR_LEN -
-		   IEEE80211_CCMP_MIC_LEN;
+	data_len = skb->len - hdrlen - IEEE80211_CCMP_HDR_LEN - mic_len;
 	if (!rx->sta || data_len < 0)
 		return RX_DROP_UNUSABLE;
 
@@ -535,14 +535,14 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx)
 			    key->u.ccmp.tfm, b_0, aad,
 			    skb->data + hdrlen + IEEE80211_CCMP_HDR_LEN,
 			    data_len,
-			    skb->data + skb->len - IEEE80211_CCMP_MIC_LEN))
+			    skb->data + skb->len - mic_len, mic_len))
 			return RX_DROP_UNUSABLE;
 	}
 
 	memcpy(key->u.ccmp.rx_pn[queue], pn, IEEE80211_CCMP_PN_LEN);
 
 	/* Remove CCMP header and MIC */
-	if (pskb_trim(skb, skb->len - IEEE80211_CCMP_MIC_LEN))
+	if (pskb_trim(skb, skb->len - mic_len))
 		return RX_DROP_UNUSABLE;
 	memmove(skb->data + IEEE80211_CCMP_HDR_LEN, skb->data, hdrlen);
 	skb_pull(skb, IEEE80211_CCMP_HDR_LEN);
@@ -550,6 +550,229 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx)
 	return RX_CONTINUE;
 }
 
+static void gcmp_special_blocks(struct sk_buff *skb, u8 *pn, u8 *j_0, u8 *aad)
+{
+	__le16 mask_fc;
+	u8 qos_tid;
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
+
+	memcpy(j_0, hdr->addr2, ETH_ALEN);
+	memcpy(&j_0[ETH_ALEN], pn, IEEE80211_GCMP_PN_LEN);
+	j_0[13] = 0;
+	j_0[14] = 0;
+	j_0[AES_BLOCK_SIZE - 1] = 0x01;
+
+	/* AAD (extra authenticate-only data) / masked 802.11 header
+	 * FC | A1 | A2 | A3 | SC | [A4] | [QC]
+	 */
+	put_unaligned_be16(ieee80211_hdrlen(hdr->frame_control) - 2, &aad[0]);
+	/* Mask FC: zero subtype b4 b5 b6 (if not mgmt)
+	 * Retry, PwrMgt, MoreData; set Protected
+	 */
+	mask_fc = hdr->frame_control;
+	mask_fc &= ~cpu_to_le16(IEEE80211_FCTL_RETRY |
+				IEEE80211_FCTL_PM | IEEE80211_FCTL_MOREDATA);
+	if (!ieee80211_is_mgmt(hdr->frame_control))
+		mask_fc &= ~cpu_to_le16(0x0070);
+	mask_fc |= cpu_to_le16(IEEE80211_FCTL_PROTECTED);
+
+	put_unaligned(mask_fc, (__le16 *)&aad[2]);
+	memcpy(&aad[4], &hdr->addr1, 3 * ETH_ALEN);
+
+	/* Mask Seq#, leave Frag# */
+	aad[22] = *((u8 *)&hdr->seq_ctrl) & 0x0f;
+	aad[23] = 0;
+
+	if (ieee80211_is_data_qos(hdr->frame_control))
+		qos_tid = *ieee80211_get_qos_ctl(hdr) &
+			IEEE80211_QOS_CTL_TID_MASK;
+	else
+		qos_tid = 0;
+
+	if (ieee80211_has_a4(hdr->frame_control)) {
+		memcpy(&aad[24], hdr->addr4, ETH_ALEN);
+		aad[30] = qos_tid;
+		aad[31] = 0;
+	} else {
+		memset(&aad[24], 0, ETH_ALEN + IEEE80211_QOS_CTL_LEN);
+		aad[24] = qos_tid;
+	}
+}
+
+static inline void gcmp_pn2hdr(u8 *hdr, const u8 *pn, int key_id)
+{
+	hdr[0] = pn[5];
+	hdr[1] = pn[4];
+	hdr[2] = 0;
+	hdr[3] = 0x20 | (key_id << 6);
+	hdr[4] = pn[3];
+	hdr[5] = pn[2];
+	hdr[6] = pn[1];
+	hdr[7] = pn[0];
+}
+
+static inline void gcmp_hdr2pn(u8 *pn, const u8 *hdr)
+{
+	pn[0] = hdr[7];
+	pn[1] = hdr[6];
+	pn[2] = hdr[5];
+	pn[3] = hdr[4];
+	pn[4] = hdr[1];
+	pn[5] = hdr[0];
+}
+
+static int gcmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb)
+{
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
+	struct ieee80211_key *key = tx->key;
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	int hdrlen, len, tail;
+	u8 *pos;
+	u8 pn[6];
+	u64 pn64;
+	u8 aad[2 * AES_BLOCK_SIZE];
+	u8 j_0[AES_BLOCK_SIZE];
+
+	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_GENERATE_IV_MGMT) &&
+	      ieee80211_is_mgmt(hdr->frame_control))) {
+		/* hwaccel has no need for preallocated room for GCMP
+		 * header or MIC fields
+		 */
+		return 0;
+	}
+
+	hdrlen = ieee80211_hdrlen(hdr->frame_control);
+	len = skb->len - hdrlen;
+
+	if (info->control.hw_key)
+		tail = 0;
+	else
+		tail = IEEE80211_GCMP_MIC_LEN;
+
+	if (WARN_ON(skb_tailroom(skb) < tail ||
+		    skb_headroom(skb) < IEEE80211_GCMP_HDR_LEN))
+		return -1;
+
+	pos = skb_push(skb, IEEE80211_GCMP_HDR_LEN);
+	memmove(pos, pos + IEEE80211_GCMP_HDR_LEN, hdrlen);
+	skb_set_network_header(skb, skb_network_offset(skb) +
+				    IEEE80211_GCMP_HDR_LEN);
+
+	/* the HW only needs room for the IV, but not the actual IV */
+	if (info->control.hw_key &&
+	    (info->control.hw_key->flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE))
+		return 0;
+
+	hdr = (struct ieee80211_hdr *)pos;
+	pos += hdrlen;
+
+	pn64 = atomic64_inc_return(&key->u.gcmp.tx_pn);
+
+	pn[5] = pn64;
+	pn[4] = pn64 >> 8;
+	pn[3] = pn64 >> 16;
+	pn[2] = pn64 >> 24;
+	pn[1] = pn64 >> 32;
+	pn[0] = pn64 >> 40;
+
+	gcmp_pn2hdr(pos, pn, key->conf.keyidx);
+
+	/* hwaccel - with software GCMP header */
+	if (info->control.hw_key)
+		return 0;
+
+	pos += IEEE80211_GCMP_HDR_LEN;
+	gcmp_special_blocks(skb, pn, j_0, aad);
+	ieee80211_aes_gcm_encrypt(key->u.gcmp.tfm, j_0, aad, pos, len,
+				  skb_put(skb, IEEE80211_GCMP_MIC_LEN));
+
+	return 0;
+}
+
+ieee80211_tx_result
+ieee80211_crypto_gcmp_encrypt(struct ieee80211_tx_data *tx)
+{
+	struct sk_buff *skb;
+
+	ieee80211_tx_set_protected(tx);
+
+	skb_queue_walk(&tx->skbs, skb) {
+		if (gcmp_encrypt_skb(tx, skb) < 0)
+			return TX_DROP;
+	}
+
+	return TX_CONTINUE;
+}
+
+ieee80211_rx_result
+ieee80211_crypto_gcmp_decrypt(struct ieee80211_rx_data *rx)
+{
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data;
+	int hdrlen;
+	struct ieee80211_key *key = rx->key;
+	struct sk_buff *skb = rx->skb;
+	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
+	u8 pn[IEEE80211_GCMP_PN_LEN];
+	int data_len;
+	int queue;
+
+	hdrlen = ieee80211_hdrlen(hdr->frame_control);
+
+	if (!ieee80211_is_data(hdr->frame_control) &&
+	    !ieee80211_is_robust_mgmt_frame(skb))
+		return RX_CONTINUE;
+
+	data_len = skb->len - hdrlen - IEEE80211_GCMP_HDR_LEN -
+		   IEEE80211_GCMP_MIC_LEN;
+	if (!rx->sta || data_len < 0)
+		return RX_DROP_UNUSABLE;
+
+	if (status->flag & RX_FLAG_DECRYPTED) {
+		if (!pskb_may_pull(rx->skb, hdrlen + IEEE80211_GCMP_HDR_LEN))
+			return RX_DROP_UNUSABLE;
+	} else {
+		if (skb_linearize(rx->skb))
+			return RX_DROP_UNUSABLE;
+	}
+
+	gcmp_hdr2pn(pn, skb->data + hdrlen);
+
+	queue = rx->security_idx;
+
+	if (memcmp(pn, key->u.gcmp.rx_pn[queue], IEEE80211_GCMP_PN_LEN) <= 0) {
+		key->u.gcmp.replays++;
+		return RX_DROP_UNUSABLE;
+	}
+
+	if (!(status->flag & RX_FLAG_DECRYPTED)) {
+		u8 aad[2 * AES_BLOCK_SIZE];
+		u8 j_0[AES_BLOCK_SIZE];
+		/* hardware didn't decrypt/verify MIC */
+		gcmp_special_blocks(skb, pn, j_0, aad);
+
+		if (ieee80211_aes_gcm_decrypt(
+			    key->u.gcmp.tfm, j_0, aad,
+			    skb->data + hdrlen + IEEE80211_GCMP_HDR_LEN,
+			    data_len,
+			    skb->data + skb->len - IEEE80211_GCMP_MIC_LEN))
+			return RX_DROP_UNUSABLE;
+	}
+
+	memcpy(key->u.gcmp.rx_pn[queue], pn, IEEE80211_GCMP_PN_LEN);
+
+	/* Remove GCMP header and MIC */
+	if (pskb_trim(skb, skb->len - IEEE80211_GCMP_MIC_LEN))
+		return RX_DROP_UNUSABLE;
+	memmove(skb->data + IEEE80211_GCMP_HDR_LEN, skb->data, hdrlen);
+	skb_pull(skb, IEEE80211_GCMP_HDR_LEN);
+
+	return RX_CONTINUE;
+}
+
 static ieee80211_tx_result
 ieee80211_crypto_cs_encrypt(struct ieee80211_tx_data *tx,
 			    struct sk_buff *skb)
@@ -557,9 +780,8 @@ ieee80211_crypto_cs_encrypt(struct ieee80211_tx_data *tx,
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 	struct ieee80211_key *key = tx->key;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
-	const struct ieee80211_cipher_scheme *cs = key->sta->cipher_scheme;
 	int hdrlen;
-	u8 *pos;
+	u8 *pos, iv_len = key->conf.iv_len;
 
 	if (info->control.hw_key &&
 	    !(info->control.hw_key->flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE)) {
@@ -567,15 +789,14 @@ ieee80211_crypto_cs_encrypt(struct ieee80211_tx_data *tx,
 		return TX_CONTINUE;
 	}
 
-	if (unlikely(skb_headroom(skb) < cs->hdr_len &&
-		     pskb_expand_head(skb, cs->hdr_len, 0, GFP_ATOMIC)))
+	if (unlikely(skb_headroom(skb) < iv_len &&
+		     pskb_expand_head(skb, iv_len, 0, GFP_ATOMIC)))
 		return TX_DROP;
 
 	hdrlen = ieee80211_hdrlen(hdr->frame_control);
 
-	pos = skb_push(skb, cs->hdr_len);
-	memmove(pos, pos + cs->hdr_len, hdrlen);
-	skb_set_network_header(skb, skb_network_offset(skb) + cs->hdr_len);
+	pos = skb_push(skb, iv_len);
+	memmove(pos, pos + iv_len, hdrlen);
 
 	return TX_CONTINUE;
 }
@@ -734,6 +955,48 @@ ieee80211_crypto_aes_cmac_encrypt(struct ieee80211_tx_data *tx)
 	return TX_CONTINUE;
 }
 
+ieee80211_tx_result
+ieee80211_crypto_aes_cmac_256_encrypt(struct ieee80211_tx_data *tx)
+{
+	struct sk_buff *skb;
+	struct ieee80211_tx_info *info;
+	struct ieee80211_key *key = tx->key;
+	struct ieee80211_mmie_16 *mmie;
+	u8 aad[20];
+	u64 pn64;
+
+	if (WARN_ON(skb_queue_len(&tx->skbs) != 1))
+		return TX_DROP;
+
+	skb = skb_peek(&tx->skbs);
+
+	info = IEEE80211_SKB_CB(skb);
+
+	if (info->control.hw_key)
+		return TX_CONTINUE;
+
+	if (WARN_ON(skb_tailroom(skb) < sizeof(*mmie)))
+		return TX_DROP;
+
+	mmie = (struct ieee80211_mmie_16 *)skb_put(skb, sizeof(*mmie));
+	mmie->element_id = WLAN_EID_MMIE;
+	mmie->length = sizeof(*mmie) - 2;
+	mmie->key_id = cpu_to_le16(key->conf.keyidx);
+
+	/* PN = PN + 1 */
+	pn64 = atomic64_inc_return(&key->u.aes_cmac.tx_pn);
+
+	bip_ipn_set64(mmie->sequence_number, pn64);
+
+	bip_aad(skb, aad);
+
+	/* MIC = AES-256-CMAC(IGTK, AAD || Management Frame Body || MMIE, 128)
+	 */
+	ieee80211_aes_cmac_256(key->u.aes_cmac.tfm, aad,
+			       skb->data + 24, skb->len - 24, mmie->mic);
+
+	return TX_CONTINUE;
+}
 
 ieee80211_rx_result
 ieee80211_crypto_aes_cmac_decrypt(struct ieee80211_rx_data *rx)
@@ -785,6 +1048,160 @@ ieee80211_crypto_aes_cmac_decrypt(struct ieee80211_rx_data *rx)
 	return RX_CONTINUE;
 }
 
+ieee80211_rx_result
+ieee80211_crypto_aes_cmac_256_decrypt(struct ieee80211_rx_data *rx)
+{
+	struct sk_buff *skb = rx->skb;
+	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
+	struct ieee80211_key *key = rx->key;
+	struct ieee80211_mmie_16 *mmie;
+	u8 aad[20], mic[16], ipn[6];
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
+
+	if (!ieee80211_is_mgmt(hdr->frame_control))
+		return RX_CONTINUE;
+
+	/* management frames are already linear */
+
+	if (skb->len < 24 + sizeof(*mmie))
+		return RX_DROP_UNUSABLE;
+
+	mmie = (struct ieee80211_mmie_16 *)
+		(skb->data + skb->len - sizeof(*mmie));
+	if (mmie->element_id != WLAN_EID_MMIE ||
+	    mmie->length != sizeof(*mmie) - 2)
+		return RX_DROP_UNUSABLE; /* Invalid MMIE */
+
+	bip_ipn_swap(ipn, mmie->sequence_number);
+
+	if (memcmp(ipn, key->u.aes_cmac.rx_pn, 6) <= 0) {
+		key->u.aes_cmac.replays++;
+		return RX_DROP_UNUSABLE;
+	}
+
+	if (!(status->flag & RX_FLAG_DECRYPTED)) {
+		/* hardware didn't decrypt/verify MIC */
+		bip_aad(skb, aad);
+		ieee80211_aes_cmac_256(key->u.aes_cmac.tfm, aad,
+				       skb->data + 24, skb->len - 24, mic);
+		if (memcmp(mic, mmie->mic, sizeof(mmie->mic)) != 0) {
+			key->u.aes_cmac.icverrors++;
+			return RX_DROP_UNUSABLE;
+		}
+	}
+
+	memcpy(key->u.aes_cmac.rx_pn, ipn, 6);
+
+	/* Remove MMIE */
+	skb_trim(skb, skb->len - sizeof(*mmie));
+
+	return RX_CONTINUE;
+}
+
+ieee80211_tx_result
+ieee80211_crypto_aes_gmac_encrypt(struct ieee80211_tx_data *tx)
+{
+	struct sk_buff *skb;
+	struct ieee80211_tx_info *info;
+	struct ieee80211_key *key = tx->key;
+	struct ieee80211_mmie_16 *mmie;
+	struct ieee80211_hdr *hdr;
+	u8 aad[20];
+	u64 pn64;
+	u8 nonce[12];
+
+	if (WARN_ON(skb_queue_len(&tx->skbs) != 1))
+		return TX_DROP;
+
+	skb = skb_peek(&tx->skbs);
+
+	info = IEEE80211_SKB_CB(skb);
+
+	if (info->control.hw_key)
+		return TX_CONTINUE;
+
+	if (WARN_ON(skb_tailroom(skb) < sizeof(*mmie)))
+		return TX_DROP;
+
+	mmie = (struct ieee80211_mmie_16 *)skb_put(skb, sizeof(*mmie));
+	mmie->element_id = WLAN_EID_MMIE;
+	mmie->length = sizeof(*mmie) - 2;
+	mmie->key_id = cpu_to_le16(key->conf.keyidx);
+
+	/* PN = PN + 1 */
+	pn64 = atomic64_inc_return(&key->u.aes_gmac.tx_pn);
+
+	bip_ipn_set64(mmie->sequence_number, pn64);
+
+	bip_aad(skb, aad);
+
+	hdr = (struct ieee80211_hdr *)skb->data;
+	memcpy(nonce, hdr->addr2, ETH_ALEN);
+	bip_ipn_swap(nonce + ETH_ALEN, mmie->sequence_number);
+
+	/* MIC = AES-GMAC(IGTK, AAD || Management Frame Body || MMIE, 128) */
+	if (ieee80211_aes_gmac(key->u.aes_gmac.tfm, aad, nonce,
+			       skb->data + 24, skb->len - 24, mmie->mic) < 0)
+		return TX_DROP;
+
+	return TX_CONTINUE;
+}
+
+ieee80211_rx_result
+ieee80211_crypto_aes_gmac_decrypt(struct ieee80211_rx_data *rx)
+{
+	struct sk_buff *skb = rx->skb;
+	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
+	struct ieee80211_key *key = rx->key;
+	struct ieee80211_mmie_16 *mmie;
+	u8 aad[20], mic[16], ipn[6], nonce[12];
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
+
+	if (!ieee80211_is_mgmt(hdr->frame_control))
+		return RX_CONTINUE;
+
+	/* management frames are already linear */
+
+	if (skb->len < 24 + sizeof(*mmie))
+		return RX_DROP_UNUSABLE;
+
+	mmie = (struct ieee80211_mmie_16 *)
+		(skb->data + skb->len - sizeof(*mmie));
+	if (mmie->element_id != WLAN_EID_MMIE ||
+	    mmie->length != sizeof(*mmie) - 2)
+		return RX_DROP_UNUSABLE; /* Invalid MMIE */
+
+	bip_ipn_swap(ipn, mmie->sequence_number);
+
+	if (memcmp(ipn, key->u.aes_gmac.rx_pn, 6) <= 0) {
+		key->u.aes_gmac.replays++;
+		return RX_DROP_UNUSABLE;
+	}
+
+	if (!(status->flag & RX_FLAG_DECRYPTED)) {
+		/* hardware didn't decrypt/verify MIC */
+		bip_aad(skb, aad);
+
+		memcpy(nonce, hdr->addr2, ETH_ALEN);
+		memcpy(nonce + ETH_ALEN, ipn, 6);
+
+		if (ieee80211_aes_gmac(key->u.aes_gmac.tfm, aad, nonce,
+				       skb->data + 24, skb->len - 24,
+				       mic) < 0 ||
+		    memcmp(mic, mmie->mic, sizeof(mmie->mic)) != 0) {
+			key->u.aes_gmac.icverrors++;
+			return RX_DROP_UNUSABLE;
+		}
+	}
+
+	memcpy(key->u.aes_gmac.rx_pn, ipn, 6);
+
+	/* Remove MMIE */
+	skb_trim(skb, skb->len - sizeof(*mmie));
+
+	return RX_CONTINUE;
+}
+
 ieee80211_tx_result
 ieee80211_crypto_hw_encrypt(struct ieee80211_tx_data *tx)
 {
@@ -799,7 +1216,7 @@ ieee80211_crypto_hw_encrypt(struct ieee80211_tx_data *tx)
 		if (!info->control.hw_key)
 			return TX_DROP;
 
-		if (tx->key->sta->cipher_scheme) {
+		if (tx->key->flags & KEY_FLAG_CIPHER_SCHEME) {
 			res = ieee80211_crypto_cs_encrypt(tx, skb);
 			if (res != TX_CONTINUE)
 				return res;
diff --git a/net/mac80211/wpa.h b/net/mac80211/wpa.h
index 62e5a12dfe0a..d98011ee8f55 100644
--- a/net/mac80211/wpa.h
+++ b/net/mac80211/wpa.h
@@ -24,17 +24,32 @@ ieee80211_rx_result
 ieee80211_crypto_tkip_decrypt(struct ieee80211_rx_data *rx);
 
 ieee80211_tx_result
-ieee80211_crypto_ccmp_encrypt(struct ieee80211_tx_data *tx);
+ieee80211_crypto_ccmp_encrypt(struct ieee80211_tx_data *tx,
+			      unsigned int mic_len);
 ieee80211_rx_result
-ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx);
+ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx,
+			      unsigned int mic_len);
 
 ieee80211_tx_result
 ieee80211_crypto_aes_cmac_encrypt(struct ieee80211_tx_data *tx);
+ieee80211_tx_result
+ieee80211_crypto_aes_cmac_256_encrypt(struct ieee80211_tx_data *tx);
 ieee80211_rx_result
 ieee80211_crypto_aes_cmac_decrypt(struct ieee80211_rx_data *rx);
+ieee80211_rx_result
+ieee80211_crypto_aes_cmac_256_decrypt(struct ieee80211_rx_data *rx);
+ieee80211_tx_result
+ieee80211_crypto_aes_gmac_encrypt(struct ieee80211_tx_data *tx);
+ieee80211_rx_result
+ieee80211_crypto_aes_gmac_decrypt(struct ieee80211_rx_data *rx);
 ieee80211_tx_result
 ieee80211_crypto_hw_encrypt(struct ieee80211_tx_data *tx);
 ieee80211_rx_result
 ieee80211_crypto_hw_decrypt(struct ieee80211_rx_data *rx);
 
+ieee80211_tx_result
+ieee80211_crypto_gcmp_encrypt(struct ieee80211_tx_data *tx);
+ieee80211_rx_result
+ieee80211_crypto_gcmp_decrypt(struct ieee80211_rx_data *rx);
+
 #endif /* WPA_H */
diff --git a/net/mac802154/Kconfig b/net/mac802154/Kconfig
index 1818a99b3081..aa462b480a39 100644
--- a/net/mac802154/Kconfig
+++ b/net/mac802154/Kconfig
@@ -16,5 +16,5 @@ config MAC802154
 	  been tested yet!
 
 	  If you plan to use HardMAC IEEE 802.15.4 devices, you can
-	  say N here. Alternatievly you can say M to compile it as
+	  say N here. Alternatively you can say M to compile it as
 	  module.
diff --git a/net/mac802154/Makefile b/net/mac802154/Makefile
index 9723d6f3f3e5..702d8b466317 100644
--- a/net/mac802154/Makefile
+++ b/net/mac802154/Makefile
@@ -1,5 +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 llsec.o
+mac802154-objs		:= main.o rx.o tx.o mac_cmd.o mib.o \
+			   iface.o llsec.o util.o cfg.o
 
 ccflags-y += -D__CHECK_ENDIAN__
diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c
new file mode 100644
index 000000000000..70be9c799f8a
--- /dev/null
+++ b/net/mac802154/cfg.c
@@ -0,0 +1,231 @@
+/* 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.
+ *
+ * Authors:
+ * Alexander Aring <aar@pengutronix.de>
+ *
+ * Based on: net/mac80211/cfg.c
+ */
+
+#include <net/rtnetlink.h>
+#include <net/cfg802154.h>
+
+#include "ieee802154_i.h"
+#include "driver-ops.h"
+#include "cfg.h"
+
+static struct net_device *
+ieee802154_add_iface_deprecated(struct wpan_phy *wpan_phy,
+				const char *name,
+				unsigned char name_assign_type, int type)
+{
+	struct ieee802154_local *local = wpan_phy_priv(wpan_phy);
+	struct net_device *dev;
+
+	rtnl_lock();
+	dev = ieee802154_if_add(local, name, name_assign_type, type,
+				cpu_to_le64(0x0000000000000000ULL));
+	rtnl_unlock();
+
+	return dev;
+}
+
+static void ieee802154_del_iface_deprecated(struct wpan_phy *wpan_phy,
+					    struct net_device *dev)
+{
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+
+	ieee802154_if_remove(sdata);
+}
+
+static int
+ieee802154_add_iface(struct wpan_phy *phy, const char *name,
+		     unsigned char name_assign_type,
+		     enum nl802154_iftype type, __le64 extended_addr)
+{
+	struct ieee802154_local *local = wpan_phy_priv(phy);
+	struct net_device *err;
+
+	err = ieee802154_if_add(local, name, name_assign_type, type,
+				extended_addr);
+	return PTR_ERR_OR_ZERO(err);
+}
+
+static int
+ieee802154_del_iface(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev)
+{
+	ieee802154_if_remove(IEEE802154_WPAN_DEV_TO_SUB_IF(wpan_dev));
+
+	return 0;
+}
+
+static int
+ieee802154_set_channel(struct wpan_phy *wpan_phy, u8 page, u8 channel)
+{
+	struct ieee802154_local *local = wpan_phy_priv(wpan_phy);
+	int ret;
+
+	ASSERT_RTNL();
+
+	/* check if phy support this setting */
+	if (!(wpan_phy->channels_supported[page] & BIT(channel)))
+		return -EINVAL;
+
+	ret = drv_set_channel(local, page, channel);
+	if (!ret) {
+		wpan_phy->current_page = page;
+		wpan_phy->current_channel = channel;
+	}
+
+	return ret;
+}
+
+static int
+ieee802154_set_cca_mode(struct wpan_phy *wpan_phy,
+			const struct wpan_phy_cca *cca)
+{
+	struct ieee802154_local *local = wpan_phy_priv(wpan_phy);
+	int ret;
+
+	ASSERT_RTNL();
+
+	/* check if phy support this setting */
+	if (!(local->hw.flags & IEEE802154_HW_CCA_MODE))
+		return -EOPNOTSUPP;
+
+	ret = drv_set_cca_mode(local, cca);
+	if (!ret)
+		wpan_phy->cca = *cca;
+
+	return ret;
+}
+
+static int
+ieee802154_set_pan_id(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
+		      __le16 pan_id)
+{
+	ASSERT_RTNL();
+
+	/* TODO
+	 * I am not sure about to check here on broadcast pan_id.
+	 * Broadcast is a valid setting, comment from 802.15.4:
+	 * If this value is 0xffff, the device is not associated.
+	 *
+	 * This could useful to simple deassociate an device.
+	 */
+	if (pan_id == cpu_to_le16(IEEE802154_PAN_ID_BROADCAST))
+		return -EINVAL;
+
+	wpan_dev->pan_id = pan_id;
+	return 0;
+}
+
+static int
+ieee802154_set_backoff_exponent(struct wpan_phy *wpan_phy,
+				struct wpan_dev *wpan_dev,
+				u8 min_be, u8 max_be)
+{
+	struct ieee802154_local *local = wpan_phy_priv(wpan_phy);
+
+	ASSERT_RTNL();
+
+	if (!(local->hw.flags & IEEE802154_HW_CSMA_PARAMS))
+		return -EOPNOTSUPP;
+
+	wpan_dev->min_be = min_be;
+	wpan_dev->max_be = max_be;
+	return 0;
+}
+
+static int
+ieee802154_set_short_addr(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
+			  __le16 short_addr)
+{
+	ASSERT_RTNL();
+
+	/* TODO
+	 * I am not sure about to check here on broadcast short_addr.
+	 * Broadcast is a valid setting, comment from 802.15.4:
+	 * A value of 0xfffe indicates that the device has
+	 * associated but has not been allocated an address. A
+	 * value of 0xffff indicates that the device does not
+	 * have a short address.
+	 *
+	 * I think we should allow to set these settings but
+	 * don't allow to allow socket communication with it.
+	 */
+	if (short_addr == cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC) ||
+	    short_addr == cpu_to_le16(IEEE802154_ADDR_SHORT_BROADCAST))
+		return -EINVAL;
+
+	wpan_dev->short_addr = short_addr;
+	return 0;
+}
+
+static int
+ieee802154_set_max_csma_backoffs(struct wpan_phy *wpan_phy,
+				 struct wpan_dev *wpan_dev,
+				 u8 max_csma_backoffs)
+{
+	struct ieee802154_local *local = wpan_phy_priv(wpan_phy);
+
+	ASSERT_RTNL();
+
+	if (!(local->hw.flags & IEEE802154_HW_CSMA_PARAMS))
+		return -EOPNOTSUPP;
+
+	wpan_dev->csma_retries = max_csma_backoffs;
+	return 0;
+}
+
+static int
+ieee802154_set_max_frame_retries(struct wpan_phy *wpan_phy,
+				 struct wpan_dev *wpan_dev,
+				 s8 max_frame_retries)
+{
+	struct ieee802154_local *local = wpan_phy_priv(wpan_phy);
+
+	ASSERT_RTNL();
+
+	if (!(local->hw.flags & IEEE802154_HW_FRAME_RETRIES))
+		return -EOPNOTSUPP;
+
+	wpan_dev->frame_retries = max_frame_retries;
+	return 0;
+}
+
+static int
+ieee802154_set_lbt_mode(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
+			bool mode)
+{
+	struct ieee802154_local *local = wpan_phy_priv(wpan_phy);
+
+	ASSERT_RTNL();
+
+	if (!(local->hw.flags & IEEE802154_HW_LBT))
+		return -EOPNOTSUPP;
+
+	wpan_dev->lbt = mode;
+	return 0;
+}
+
+const struct cfg802154_ops mac802154_config_ops = {
+	.add_virtual_intf_deprecated = ieee802154_add_iface_deprecated,
+	.del_virtual_intf_deprecated = ieee802154_del_iface_deprecated,
+	.add_virtual_intf = ieee802154_add_iface,
+	.del_virtual_intf = ieee802154_del_iface,
+	.set_channel = ieee802154_set_channel,
+	.set_cca_mode = ieee802154_set_cca_mode,
+	.set_pan_id = ieee802154_set_pan_id,
+	.set_short_addr = ieee802154_set_short_addr,
+	.set_backoff_exponent = ieee802154_set_backoff_exponent,
+	.set_max_csma_backoffs = ieee802154_set_max_csma_backoffs,
+	.set_max_frame_retries = ieee802154_set_max_frame_retries,
+	.set_lbt_mode = ieee802154_set_lbt_mode,
+};
diff --git a/net/mac802154/cfg.h b/net/mac802154/cfg.h
new file mode 100644
index 000000000000..e2718f981e82
--- /dev/null
+++ b/net/mac802154/cfg.h
@@ -0,0 +1,9 @@
+/* mac802154 configuration hooks for cfg802154
+ */
+
+#ifndef __CFG_H
+#define __CFG_H
+
+extern const struct cfg802154_ops mac802154_config_ops;
+
+#endif /* __CFG_H */
diff --git a/net/mac802154/driver-ops.h b/net/mac802154/driver-ops.h
new file mode 100644
index 000000000000..a0533357b9ea
--- /dev/null
+++ b/net/mac802154/driver-ops.h
@@ -0,0 +1,223 @@
+#ifndef __MAC802154_DRIVER_OPS
+#define __MAC802154_DRIVER_OPS
+
+#include <linux/types.h>
+#include <linux/rtnetlink.h>
+
+#include <net/mac802154.h>
+
+#include "ieee802154_i.h"
+
+static inline int
+drv_xmit_async(struct ieee802154_local *local, struct sk_buff *skb)
+{
+	return local->ops->xmit_async(&local->hw, skb);
+}
+
+static inline int
+drv_xmit_sync(struct ieee802154_local *local, struct sk_buff *skb)
+{
+	/* don't allow other operations while sync xmit */
+	ASSERT_RTNL();
+
+	might_sleep();
+
+	return local->ops->xmit_sync(&local->hw, skb);
+}
+
+static inline int drv_start(struct ieee802154_local *local)
+{
+	might_sleep();
+
+	local->started = true;
+	smp_mb();
+
+	return local->ops->start(&local->hw);
+}
+
+static inline void drv_stop(struct ieee802154_local *local)
+{
+	might_sleep();
+
+	local->ops->stop(&local->hw);
+
+	/* sync away all work on the tasklet before clearing started */
+	tasklet_disable(&local->tasklet);
+	tasklet_enable(&local->tasklet);
+
+	barrier();
+
+	local->started = false;
+}
+
+static inline int
+drv_set_channel(struct ieee802154_local *local, u8 page, u8 channel)
+{
+	might_sleep();
+
+	return local->ops->set_channel(&local->hw, page, channel);
+}
+
+static inline int drv_set_tx_power(struct ieee802154_local *local, s8 dbm)
+{
+	might_sleep();
+
+	if (!local->ops->set_txpower) {
+		WARN_ON(1);
+		return -EOPNOTSUPP;
+	}
+
+	return local->ops->set_txpower(&local->hw, dbm);
+}
+
+static inline int drv_set_cca_mode(struct ieee802154_local *local,
+				   const struct wpan_phy_cca *cca)
+{
+	might_sleep();
+
+	if (!local->ops->set_cca_mode) {
+		WARN_ON(1);
+		return -EOPNOTSUPP;
+	}
+
+	return local->ops->set_cca_mode(&local->hw, cca);
+}
+
+static inline int drv_set_lbt_mode(struct ieee802154_local *local, bool mode)
+{
+	might_sleep();
+
+	if (!local->ops->set_lbt) {
+		WARN_ON(1);
+		return -EOPNOTSUPP;
+	}
+
+	return local->ops->set_lbt(&local->hw, mode);
+}
+
+static inline int
+drv_set_cca_ed_level(struct ieee802154_local *local, s32 ed_level)
+{
+	might_sleep();
+
+	if (!local->ops->set_cca_ed_level) {
+		WARN_ON(1);
+		return -EOPNOTSUPP;
+	}
+
+	return local->ops->set_cca_ed_level(&local->hw, ed_level);
+}
+
+static inline int drv_set_pan_id(struct ieee802154_local *local, __le16 pan_id)
+{
+	struct ieee802154_hw_addr_filt filt;
+
+	might_sleep();
+
+	if (!local->ops->set_hw_addr_filt) {
+		WARN_ON(1);
+		return -EOPNOTSUPP;
+	}
+
+	filt.pan_id = pan_id;
+
+	return local->ops->set_hw_addr_filt(&local->hw, &filt,
+					    IEEE802154_AFILT_PANID_CHANGED);
+}
+
+static inline int
+drv_set_extended_addr(struct ieee802154_local *local, __le64 extended_addr)
+{
+	struct ieee802154_hw_addr_filt filt;
+
+	might_sleep();
+
+	if (!local->ops->set_hw_addr_filt) {
+		WARN_ON(1);
+		return -EOPNOTSUPP;
+	}
+
+	filt.ieee_addr = extended_addr;
+
+	return local->ops->set_hw_addr_filt(&local->hw, &filt,
+					    IEEE802154_AFILT_IEEEADDR_CHANGED);
+}
+
+static inline int
+drv_set_short_addr(struct ieee802154_local *local, __le16 short_addr)
+{
+	struct ieee802154_hw_addr_filt filt;
+
+	might_sleep();
+
+	if (!local->ops->set_hw_addr_filt) {
+		WARN_ON(1);
+		return -EOPNOTSUPP;
+	}
+
+	filt.short_addr = short_addr;
+
+	return local->ops->set_hw_addr_filt(&local->hw, &filt,
+					    IEEE802154_AFILT_SADDR_CHANGED);
+}
+
+static inline int
+drv_set_pan_coord(struct ieee802154_local *local, bool is_coord)
+{
+	struct ieee802154_hw_addr_filt filt;
+
+	might_sleep();
+
+	if (!local->ops->set_hw_addr_filt) {
+		WARN_ON(1);
+		return -EOPNOTSUPP;
+	}
+
+	filt.pan_coord = is_coord;
+
+	return local->ops->set_hw_addr_filt(&local->hw, &filt,
+					    IEEE802154_AFILT_PANC_CHANGED);
+}
+
+static inline int
+drv_set_csma_params(struct ieee802154_local *local, u8 min_be, u8 max_be,
+		    u8 max_csma_backoffs)
+{
+	might_sleep();
+
+	if (!local->ops->set_csma_params) {
+		WARN_ON(1);
+		return -EOPNOTSUPP;
+	}
+
+	return local->ops->set_csma_params(&local->hw, min_be, max_be,
+					   max_csma_backoffs);
+}
+
+static inline int
+drv_set_max_frame_retries(struct ieee802154_local *local, s8 max_frame_retries)
+{
+	might_sleep();
+
+	if (!local->ops->set_frame_retries) {
+		WARN_ON(1);
+		return -EOPNOTSUPP;
+	}
+
+	return local->ops->set_frame_retries(&local->hw, max_frame_retries);
+}
+
+static inline int
+drv_set_promiscuous_mode(struct ieee802154_local *local, bool on)
+{
+	might_sleep();
+
+	if (!local->ops->set_promiscuous_mode) {
+		WARN_ON(1);
+		return -EOPNOTSUPP;
+	}
+
+	return local->ops->set_promiscuous_mode(&local->hw, on);
+}
+
+#endif /* __MAC802154_DRIVER_OPS */
diff --git a/net/mac802154/ieee802154_dev.c b/net/mac802154/ieee802154_dev.c
deleted file mode 100644
index b36b2b996578..000000000000
--- a/net/mac802154/ieee802154_dev.c
+++ /dev/null
@@ -1,415 +0,0 @@
-/*
- * Copyright (C) 2007-2012 Siemens AG
- *
- * Written by:
- * Alexander Smirnov <alex.bluesman.smirnov@gmail.com>
- *
- * Based on the code from 'linux-zigbee.sourceforge.net' project.
- *
- * 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.
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/netdevice.h>
-
-#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>
-
-#include "mac802154.h"
-
-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);
-		if (res)
-			goto err;
-	}
-
-	if (ipriv->ops->ieee_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;
-		mac802154_dev_set_ieee_addr(dev);
-	}
-
-	netif_start_queue(dev);
-	return 0;
-err:
-	priv->hw->open_count--;
-
-	return res;
-}
-
-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);
-
-	return 0;
-}
-
-static int
-mac802154_netdev_register(struct wpan_phy *phy, struct net_device *dev)
-{
-	struct mac802154_sub_if_data *priv;
-	struct mac802154_priv *ipriv;
-	int err;
-
-	ipriv = wpan_phy_priv(phy);
-
-	priv = netdev_priv(dev);
-	priv->dev = dev;
-	priv->hw = ipriv;
-
-	dev->needed_headroom = ipriv->hw.extra_tx_headroom;
-
-	SET_NETDEV_DEV(dev, &ipriv->phy->dev);
-
-	mutex_lock(&ipriv->slaves_mtx);
-	if (!ipriv->running) {
-		mutex_unlock(&ipriv->slaves_mtx);
-		return -ENODEV;
-	}
-	mutex_unlock(&ipriv->slaves_mtx);
-
-	err = register_netdev(dev);
-	if (err < 0)
-		return err;
-
-	rtnl_lock();
-	mutex_lock(&ipriv->slaves_mtx);
-	list_add_tail_rcu(&priv->list, &ipriv->slaves);
-	mutex_unlock(&ipriv->slaves_mtx);
-	rtnl_unlock();
-
-	return 0;
-}
-
-static void
-mac802154_del_iface(struct wpan_phy *phy, struct net_device *dev)
-{
-	struct mac802154_sub_if_data *sdata;
-
-	ASSERT_RTNL();
-
-	sdata = netdev_priv(dev);
-
-	BUG_ON(sdata->hw->phy != phy);
-
-	mutex_lock(&sdata->hw->slaves_mtx);
-	list_del_rcu(&sdata->list);
-	mutex_unlock(&sdata->hw->slaves_mtx);
-
-	synchronize_rcu();
-	unregister_netdevice(sdata->dev);
-}
-
-static struct net_device *
-mac802154_add_iface(struct wpan_phy *phy, const char *name, int type)
-{
-	struct net_device *dev;
-	int err = -ENOMEM;
-
-	switch (type) {
-	case IEEE802154_DEV_MONITOR:
-		dev = alloc_netdev(sizeof(struct mac802154_sub_if_data),
-				   name, NET_NAME_UNKNOWN,
-				   mac802154_monitor_setup);
-		break;
-	case IEEE802154_DEV_WPAN:
-		dev = alloc_netdev(sizeof(struct mac802154_sub_if_data),
-				   name, NET_NAME_UNKNOWN,
-				   mac802154_wpan_setup);
-		break;
-	default:
-		dev = NULL;
-		err = -EINVAL;
-		break;
-	}
-	if (!dev)
-		goto err;
-
-	err = mac802154_netdev_register(phy, dev);
-	if (err)
-		goto err_free;
-
-	dev_hold(dev); /* we return an incremented device refcount */
-	return dev;
-
-err_free:
-	free_netdev(dev);
-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)
-{
-	struct wpan_phy *phy;
-	struct mac802154_priv *priv;
-	size_t priv_size;
-
-	if (!ops || !ops->xmit || !ops->ed || !ops->start ||
-	    !ops->stop || !ops->set_channel) {
-		pr_err("undefined IEEE802.15.4 device operations\n");
-		return NULL;
-	}
-
-	/* Ensure 32-byte alignment of our private data and hw private data.
-	 * We use the wpan_phy priv data for both our mac802154_priv and for
-	 * the driver's private data
-	 *
-	 * in memory it'll be like this:
-	 *
-	 * +-----------------------+
-	 * | struct wpan_phy       |
-	 * +-----------------------+
-	 * | struct mac802154_priv |
-	 * +-----------------------+
-	 * | driver's private data |
-	 * +-----------------------+
-	 *
-	 * Due to ieee802154 layer isn't aware of driver and MAC structures,
-	 * so lets allign them here.
-	 */
-
-	priv_size = ALIGN(sizeof(*priv), NETDEV_ALIGN) + priv_data_len;
-
-	phy = wpan_phy_alloc(priv_size);
-	if (!phy) {
-		pr_err("failure to allocate master IEEE802.15.4 device\n");
-		return NULL;
-	}
-
-	priv = wpan_phy_priv(phy);
-	priv->phy = phy;
-	priv->hw.phy = priv->phy;
-	priv->hw.priv = (char *)priv + ALIGN(sizeof(*priv), NETDEV_ALIGN);
-	priv->ops = ops;
-
-	INIT_LIST_HEAD(&priv->slaves);
-	mutex_init(&priv->slaves_mtx);
-
-	return &priv->hw;
-}
-EXPORT_SYMBOL(ieee802154_alloc_device);
-
-void ieee802154_free_device(struct ieee802154_dev *hw)
-{
-	struct mac802154_priv *priv = mac802154_to_priv(hw);
-
-	BUG_ON(!list_empty(&priv->slaves));
-
-	mutex_destroy(&priv->slaves_mtx);
-
-	wpan_phy_free(priv->phy);
-}
-EXPORT_SYMBOL(ieee802154_free_device);
-
-int ieee802154_register_device(struct ieee802154_dev *dev)
-{
-	struct mac802154_priv *priv = mac802154_to_priv(dev);
-	int rc = -ENOSYS;
-
-	if (dev->flags & IEEE802154_HW_TXPOWER) {
-		if (!priv->ops->set_txpower)
-			goto out;
-
-		priv->phy->set_txpower = mac802154_set_txpower;
-	}
-
-	if (dev->flags & IEEE802154_HW_LBT) {
-		if (!priv->ops->set_lbt)
-			goto out;
-
-		priv->phy->set_lbt = mac802154_set_lbt;
-	}
-
-	if (dev->flags & IEEE802154_HW_CCA_MODE) {
-		if (!priv->ops->set_cca_mode)
-			goto out;
-
-		priv->phy->set_cca_mode = mac802154_set_cca_mode;
-	}
-
-	if (dev->flags & IEEE802154_HW_CCA_ED_LEVEL) {
-		if (!priv->ops->set_cca_ed_level)
-			goto out;
-
-		priv->phy->set_cca_ed_level = mac802154_set_cca_ed_level;
-	}
-
-	if (dev->flags & IEEE802154_HW_CSMA_PARAMS) {
-		if (!priv->ops->set_csma_params)
-			goto out;
-
-		priv->phy->set_csma_params = mac802154_set_csma_params;
-	}
-
-	if (dev->flags & IEEE802154_HW_FRAME_RETRIES) {
-		if (!priv->ops->set_frame_retries)
-			goto out;
-
-		priv->phy->set_frame_retries = mac802154_set_frame_retries;
-	}
-
-	priv->dev_workqueue =
-		create_singlethread_workqueue(wpan_phy_name(priv->phy));
-	if (!priv->dev_workqueue) {
-		rc = -ENOMEM;
-		goto out;
-	}
-
-	wpan_phy_set_dev(priv->phy, priv->hw.parent);
-
-	priv->phy->add_iface = mac802154_add_iface;
-	priv->phy->del_iface = mac802154_del_iface;
-
-	rc = wpan_phy_register(priv->phy);
-	if (rc < 0)
-		goto out_wq;
-
-	rtnl_lock();
-
-	mutex_lock(&priv->slaves_mtx);
-	priv->running = MAC802154_DEVICE_RUN;
-	mutex_unlock(&priv->slaves_mtx);
-
-	rtnl_unlock();
-
-	return 0;
-
-out_wq:
-	destroy_workqueue(priv->dev_workqueue);
-out:
-	return rc;
-}
-EXPORT_SYMBOL(ieee802154_register_device);
-
-void ieee802154_unregister_device(struct ieee802154_dev *dev)
-{
-	struct mac802154_priv *priv = mac802154_to_priv(dev);
-	struct mac802154_sub_if_data *sdata, *next;
-
-	flush_workqueue(priv->dev_workqueue);
-	destroy_workqueue(priv->dev_workqueue);
-
-	rtnl_lock();
-
-	mutex_lock(&priv->slaves_mtx);
-	priv->running = MAC802154_DEVICE_STOPPED;
-	mutex_unlock(&priv->slaves_mtx);
-
-	list_for_each_entry_safe(sdata, next, &priv->slaves, list) {
-		mutex_lock(&sdata->hw->slaves_mtx);
-		list_del(&sdata->list);
-		mutex_unlock(&sdata->hw->slaves_mtx);
-
-		unregister_netdevice(sdata->dev);
-	}
-
-	rtnl_unlock();
-
-	wpan_phy_unregister(priv->phy);
-}
-EXPORT_SYMBOL(ieee802154_unregister_device);
-
-MODULE_DESCRIPTION("IEEE 802.15.4 implementation");
-MODULE_LICENSE("GPL v2");
diff --git a/net/mac802154/mac802154.h b/net/mac802154/ieee802154_i.h
index 762a6f849c6b..127ba18386fc 100644
--- a/net/mac802154/mac802154.h
+++ b/net/mac802154/ieee802154_i.h
@@ -10,29 +10,28 @@
  * 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.
- *
  * Written by:
  * Pavel Smolenskiy <pavel.smolenskiy@gmail.com>
  * Maxim Gorbachyov <maxim.gorbachev@siemens.com>
  * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
  * Alexander Smirnov <alex.bluesman.smirnov@gmail.com>
  */
-#ifndef MAC802154_H
-#define MAC802154_H
+#ifndef __IEEE802154_I_H
+#define __IEEE802154_I_H
 
 #include <linux/mutex.h>
+#include <linux/hrtimer.h>
+#include <net/cfg802154.h>
 #include <net/mac802154.h>
+#include <net/nl802154.h>
 #include <net/ieee802154_netdev.h>
 
 #include "llsec.h"
 
 /* mac802154 device private data */
-struct mac802154_priv {
-	struct ieee802154_dev hw;
-	struct ieee802154_ops *ops;
+struct ieee802154_local {
+	struct ieee802154_hw hw;
+	const struct ieee802154_ops *ops;
 
 	/* ieee802154 phy */
 	struct wpan_phy *phy;
@@ -46,23 +45,29 @@ struct mac802154_priv {
 	 *
 	 * So atomic readers can use any of this protection methods.
 	 */
-	struct list_head	slaves;
-	struct mutex		slaves_mtx;
+	struct list_head	interfaces;
+	struct mutex		iflist_mtx;
 
 	/* This one is used for scanning and other jobs not to be interfered
 	 * with serial driver.
 	 */
-	struct workqueue_struct	*dev_workqueue;
+	struct workqueue_struct	*workqueue;
 
-	/* SoftMAC device is registered and running. One can add subinterfaces.
-	 * This flag should be modified under slaves_mtx and RTNL, so you can
-	 * read them using any of protection methods.
-	 */
-	bool running;
+	struct hrtimer ifs_timer;
+
+	bool started;
+
+	struct tasklet_struct tasklet;
+	struct sk_buff_head skb_queue;
 };
 
-#define	MAC802154_DEVICE_STOPPED	0x00
-#define MAC802154_DEVICE_RUN		0x01
+enum {
+	IEEE802154_RX_MSG        = 1,
+};
+
+enum ieee802154_sdata_state_bits {
+	SDATA_STATE_RUNNING,
+};
 
 /* Slave interface definition.
  *
@@ -70,72 +75,74 @@ struct mac802154_priv {
  * Each ieee802154 device/transceiver may have several slaves and able
  * to be associated with several networks at the same time.
  */
-struct mac802154_sub_if_data {
+struct ieee802154_sub_if_data {
 	struct list_head list; /* the ieee802154_priv->slaves list */
 
-	struct mac802154_priv *hw;
+	struct wpan_dev wpan_dev;
+
+	struct ieee802154_local *local;
 	struct net_device *dev;
 
-	int type;
-	bool running;
+	unsigned long state;
+	char name[IFNAMSIZ];
 
 	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;
+	/* must be last, dynamically sized area in this! */
+	struct ieee802154_vif vif;
 };
 
-#define mac802154_to_priv(_hw)	container_of(_hw, struct mac802154_priv, hw)
-
 #define MAC802154_CHAN_NONE		0xff /* No channel is assigned */
 
-extern struct ieee802154_reduced_mlme_ops mac802154_mlme_reduced;
-extern struct ieee802154_mlme_ops mac802154_mlme_wpan;
+/* utility functions/constants */
+extern const void *const mac802154_wpan_phy_privid; /*  for wpan_phy privid */
+
+static inline struct ieee802154_local *
+hw_to_local(struct ieee802154_hw *hw)
+{
+	return container_of(hw, struct ieee802154_local, hw);
+}
+
+static inline struct ieee802154_sub_if_data *
+IEEE802154_DEV_TO_SUB_IF(const struct net_device *dev)
+{
+	return netdev_priv(dev);
+}
+
+static inline struct ieee802154_sub_if_data *
+IEEE802154_WPAN_DEV_TO_SUB_IF(struct wpan_dev *wpan_dev)
+{
+	return container_of(wpan_dev, struct ieee802154_sub_if_data, wpan_dev);
+}
+
+static inline bool
+ieee802154_sdata_running(struct ieee802154_sub_if_data *sdata)
+{
+	return test_bit(SDATA_STATE_RUNNING, &sdata->state);
+}
 
-int mac802154_slave_open(struct net_device *dev);
-int mac802154_slave_close(struct net_device *dev);
-
-void mac802154_monitors_rx(struct mac802154_priv *priv, struct sk_buff *skb);
-void mac802154_monitor_setup(struct net_device *dev);
-
-void mac802154_wpans_rx(struct mac802154_priv *priv, struct sk_buff *skb);
-void mac802154_wpan_setup(struct net_device *dev);
+extern struct ieee802154_mlme_ops mac802154_mlme_wpan;
 
-netdev_tx_t mac802154_tx(struct mac802154_priv *priv, struct sk_buff *skb,
-			 u8 page, u8 chan);
+netdev_tx_t
+ieee802154_monitor_start_xmit(struct sk_buff *skb, struct net_device *dev);
+netdev_tx_t
+ieee802154_subif_start_xmit(struct sk_buff *skb, struct net_device *dev);
+enum hrtimer_restart ieee802154_xmit_ifs_timer(struct hrtimer *timer);
 
 /* MIB callbacks */
 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);
 __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,
@@ -169,4 +176,14 @@ void mac802154_get_table(struct net_device *dev,
 			 struct ieee802154_llsec_table **t);
 void mac802154_unlock_table(struct net_device *dev);
 
-#endif /* MAC802154_H */
+/* interface handling */
+int ieee802154_iface_init(void);
+void ieee802154_iface_exit(void);
+void ieee802154_if_remove(struct ieee802154_sub_if_data *sdata);
+struct net_device *
+ieee802154_if_add(struct ieee802154_local *local, const char *name,
+		  unsigned char name_assign_type, enum nl802154_iftype type,
+		  __le64 extended_addr);
+void ieee802154_remove_interfaces(struct ieee802154_local *local);
+
+#endif /* __IEEE802154_I_H */
diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c
new file mode 100644
index 000000000000..91b75abbd1a1
--- /dev/null
+++ b/net/mac802154/iface.c
@@ -0,0 +1,651 @@
+/*
+ * Copyright 2007-2012 Siemens AG
+ *
+ * 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:
+ * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
+ * Sergey Lapin <slapin@ossfans.org>
+ * Maxim Gorbachyov <maxim.gorbachev@siemens.com>
+ * Alexander Smirnov <alex.bluesman.smirnov@gmail.com>
+ */
+
+#include <linux/netdevice.h>
+#include <linux/module.h>
+#include <linux/if_arp.h>
+#include <linux/ieee802154.h>
+
+#include <net/nl802154.h>
+#include <net/mac802154.h>
+#include <net/ieee802154_netdev.h>
+#include <net/cfg802154.h>
+
+#include "ieee802154_i.h"
+#include "driver-ops.h"
+
+static int mac802154_wpan_update_llsec(struct net_device *dev)
+{
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+	struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev);
+	struct wpan_dev *wpan_dev = &sdata->wpan_dev;
+	int rc = 0;
+
+	if (ops->llsec) {
+		struct ieee802154_llsec_params params;
+		int changed = 0;
+
+		params.pan_id = wpan_dev->pan_id;
+		changed |= IEEE802154_LLSEC_PARAM_PAN_ID;
+
+		params.hwaddr = wpan_dev->extended_addr;
+		changed |= IEEE802154_LLSEC_PARAM_HWADDR;
+
+		rc = ops->llsec->set_params(dev, &params, changed);
+	}
+
+	return rc;
+}
+
+static int
+mac802154_wpan_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+{
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+	struct wpan_dev *wpan_dev = &sdata->wpan_dev;
+	struct sockaddr_ieee802154 *sa =
+		(struct sockaddr_ieee802154 *)&ifr->ifr_addr;
+	int err = -ENOIOCTLCMD;
+
+	ASSERT_RTNL();
+
+	spin_lock_bh(&sdata->mib_lock);
+
+	switch (cmd) {
+	case SIOCGIFADDR:
+	{
+		u16 pan_id, short_addr;
+
+		pan_id = le16_to_cpu(wpan_dev->pan_id);
+		short_addr = le16_to_cpu(wpan_dev->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 = pan_id;
+		sa->addr.short_addr = short_addr;
+
+		err = 0;
+		break;
+	}
+	case SIOCSIFADDR:
+		if (netif_running(dev)) {
+			spin_unlock_bh(&sdata->mib_lock);
+			return -EBUSY;
+		}
+
+		dev_warn(&dev->dev,
+			 "Using DEBUGing ioctl SIOCSIFADDR isn't recommended!\n");
+		if (sa->family != AF_IEEE802154 ||
+		    sa->addr.addr_type != IEEE802154_ADDR_SHORT ||
+		    sa->addr.pan_id == IEEE802154_PANID_BROADCAST ||
+		    sa->addr.short_addr == IEEE802154_ADDR_BROADCAST ||
+		    sa->addr.short_addr == IEEE802154_ADDR_UNDEF) {
+			err = -EINVAL;
+			break;
+		}
+
+		wpan_dev->pan_id = cpu_to_le16(sa->addr.pan_id);
+		wpan_dev->short_addr = cpu_to_le16(sa->addr.short_addr);
+
+		err = mac802154_wpan_update_llsec(dev);
+		break;
+	}
+
+	spin_unlock_bh(&sdata->mib_lock);
+	return err;
+}
+
+static int mac802154_wpan_mac_addr(struct net_device *dev, void *p)
+{
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+	struct sockaddr *addr = p;
+	__le64 extended_addr;
+
+	if (netif_running(dev))
+		return -EBUSY;
+
+	ieee802154_be64_to_le64(&extended_addr, addr->sa_data);
+	if (!ieee802154_is_valid_extended_addr(extended_addr))
+		return -EINVAL;
+
+	memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
+	sdata->wpan_dev.extended_addr = extended_addr;
+
+	return mac802154_wpan_update_llsec(dev);
+}
+
+static int mac802154_slave_open(struct net_device *dev)
+{
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+	struct ieee802154_local *local = sdata->local;
+	int res = 0;
+
+	ASSERT_RTNL();
+
+	set_bit(SDATA_STATE_RUNNING, &sdata->state);
+
+	if (!local->open_count) {
+		res = drv_start(local);
+		WARN_ON(res);
+		if (res)
+			goto err;
+	}
+
+	local->open_count++;
+	netif_start_queue(dev);
+	return 0;
+err:
+	/* might already be clear but that doesn't matter */
+	clear_bit(SDATA_STATE_RUNNING, &sdata->state);
+
+	return res;
+}
+
+static int
+ieee802154_check_mac_settings(struct ieee802154_local *local,
+			      struct wpan_dev *wpan_dev,
+			      struct wpan_dev *nwpan_dev)
+{
+	ASSERT_RTNL();
+
+	if (local->hw.flags & IEEE802154_HW_PROMISCUOUS) {
+		if (wpan_dev->promiscuous_mode != nwpan_dev->promiscuous_mode)
+			return -EBUSY;
+	}
+
+	if (local->hw.flags & IEEE802154_HW_AFILT) {
+		if (wpan_dev->pan_id != nwpan_dev->pan_id ||
+		    wpan_dev->short_addr != nwpan_dev->short_addr ||
+		    wpan_dev->extended_addr != nwpan_dev->extended_addr)
+			return -EBUSY;
+	}
+
+	if (local->hw.flags & IEEE802154_HW_CSMA_PARAMS) {
+		if (wpan_dev->min_be != nwpan_dev->min_be ||
+		    wpan_dev->max_be != nwpan_dev->max_be ||
+		    wpan_dev->csma_retries != nwpan_dev->csma_retries)
+			return -EBUSY;
+	}
+
+	if (local->hw.flags & IEEE802154_HW_FRAME_RETRIES) {
+		if (wpan_dev->frame_retries != nwpan_dev->frame_retries)
+			return -EBUSY;
+	}
+
+	if (local->hw.flags & IEEE802154_HW_LBT) {
+		if (wpan_dev->lbt != nwpan_dev->lbt)
+			return -EBUSY;
+	}
+
+	return 0;
+}
+
+static int
+ieee802154_check_concurrent_iface(struct ieee802154_sub_if_data *sdata,
+				  enum nl802154_iftype iftype)
+{
+	struct ieee802154_local *local = sdata->local;
+	struct wpan_dev *wpan_dev = &sdata->wpan_dev;
+	struct ieee802154_sub_if_data *nsdata;
+
+	/* we hold the RTNL here so can safely walk the list */
+	list_for_each_entry(nsdata, &local->interfaces, list) {
+		if (nsdata != sdata && ieee802154_sdata_running(nsdata)) {
+			int ret;
+
+			/* TODO currently we don't support multiple node types
+			 * we need to run skb_clone at rx path. Check if there
+			 * exist really an use case if we need to support
+			 * multiple node types at the same time.
+			 */
+			if (sdata->vif.type == NL802154_IFTYPE_NODE &&
+			    nsdata->vif.type == NL802154_IFTYPE_NODE)
+				return -EBUSY;
+
+			/* check all phy mac sublayer settings are the same.
+			 * We have only one phy, different values makes trouble.
+			 */
+			ret = ieee802154_check_mac_settings(local, wpan_dev,
+							    &nsdata->wpan_dev);
+			if (ret < 0)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int mac802154_wpan_open(struct net_device *dev)
+{
+	int rc;
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+	struct ieee802154_local *local = sdata->local;
+	struct wpan_dev *wpan_dev = &sdata->wpan_dev;
+	struct wpan_phy *phy = sdata->local->phy;
+
+	rc = ieee802154_check_concurrent_iface(sdata, sdata->vif.type);
+	if (rc < 0)
+		return rc;
+
+	rc = mac802154_slave_open(dev);
+	if (rc < 0)
+		return rc;
+
+	mutex_lock(&phy->pib_lock);
+
+	if (local->hw.flags & IEEE802154_HW_PROMISCUOUS) {
+		rc = drv_set_promiscuous_mode(local,
+					      wpan_dev->promiscuous_mode);
+		if (rc < 0)
+			goto out;
+	}
+
+	if (local->hw.flags & IEEE802154_HW_AFILT) {
+		rc = drv_set_pan_id(local, wpan_dev->pan_id);
+		if (rc < 0)
+			goto out;
+
+		rc = drv_set_extended_addr(local, wpan_dev->extended_addr);
+		if (rc < 0)
+			goto out;
+
+		rc = drv_set_short_addr(local, wpan_dev->short_addr);
+		if (rc < 0)
+			goto out;
+	}
+
+	if (local->hw.flags & IEEE802154_HW_LBT) {
+		rc = drv_set_lbt_mode(local, wpan_dev->lbt);
+		if (rc < 0)
+			goto out;
+	}
+
+	if (local->hw.flags & IEEE802154_HW_CSMA_PARAMS) {
+		rc = drv_set_csma_params(local, wpan_dev->min_be,
+					 wpan_dev->max_be,
+					 wpan_dev->csma_retries);
+		if (rc < 0)
+			goto out;
+	}
+
+	if (local->hw.flags & IEEE802154_HW_FRAME_RETRIES) {
+		rc = drv_set_max_frame_retries(local, wpan_dev->frame_retries);
+		if (rc < 0)
+			goto out;
+	}
+
+	mutex_unlock(&phy->pib_lock);
+	return 0;
+
+out:
+	mutex_unlock(&phy->pib_lock);
+	return rc;
+}
+
+static int mac802154_slave_close(struct net_device *dev)
+{
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+	struct ieee802154_local *local = sdata->local;
+
+	ASSERT_RTNL();
+
+	hrtimer_cancel(&local->ifs_timer);
+
+	netif_stop_queue(dev);
+	local->open_count--;
+
+	clear_bit(SDATA_STATE_RUNNING, &sdata->state);
+
+	if (!local->open_count)
+		drv_stop(local);
+
+	return 0;
+}
+
+static int mac802154_set_header_security(struct ieee802154_sub_if_data *sdata,
+					 struct ieee802154_hdr *hdr,
+					 const struct ieee802154_mac_cb *cb)
+{
+	struct ieee802154_llsec_params params;
+	u8 level;
+
+	mac802154_llsec_get_params(&sdata->sec, &params);
+
+	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;
+
+	level = cb->seclevel_override ? cb->seclevel : params.out_level;
+
+	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;
+
+	return 0;
+}
+
+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 ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+	struct wpan_dev *wpan_dev = &sdata->wpan_dev;
+	struct ieee802154_mac_cb *cb = mac_cb(skb);
+	int hlen;
+
+	if (!daddr)
+		return -EINVAL;
+
+	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);
+
+	if (mac802154_set_header_security(sdata, &hdr, cb) < 0)
+		return -EINVAL;
+
+	if (!saddr) {
+		spin_lock_bh(&sdata->mib_lock);
+
+		if (wpan_dev->short_addr == cpu_to_le16(IEEE802154_ADDR_BROADCAST) ||
+		    wpan_dev->short_addr == cpu_to_le16(IEEE802154_ADDR_UNDEF) ||
+		    wpan_dev->pan_id == cpu_to_le16(IEEE802154_PANID_BROADCAST)) {
+			hdr.source.mode = IEEE802154_ADDR_LONG;
+			hdr.source.extended_addr = wpan_dev->extended_addr;
+		} else {
+			hdr.source.mode = IEEE802154_ADDR_SHORT;
+			hdr.source.short_addr = wpan_dev->short_addr;
+		}
+
+		hdr.source.pan_id = wpan_dev->pan_id;
+
+		spin_unlock_bh(&sdata->mib_lock);
+	} else {
+		hdr.source = *(const struct ieee802154_addr *)saddr;
+	}
+
+	hdr.dest = *(const struct ieee802154_addr *)daddr;
+
+	hlen = ieee802154_hdr_push(skb, &hdr);
+	if (hlen < 0)
+		return -EINVAL;
+
+	skb_reset_mac_header(skb);
+	skb->mac_len = hlen;
+
+	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 struct header_ops mac802154_header_ops = {
+	.create		= mac802154_header_create,
+	.parse		= mac802154_header_parse,
+};
+
+static const struct net_device_ops mac802154_wpan_ops = {
+	.ndo_open		= mac802154_wpan_open,
+	.ndo_stop		= mac802154_slave_close,
+	.ndo_start_xmit		= ieee802154_subif_start_xmit,
+	.ndo_do_ioctl		= mac802154_wpan_ioctl,
+	.ndo_set_mac_address	= mac802154_wpan_mac_addr,
+};
+
+static const struct net_device_ops mac802154_monitor_ops = {
+	.ndo_open		= mac802154_wpan_open,
+	.ndo_stop		= mac802154_slave_close,
+	.ndo_start_xmit		= ieee802154_monitor_start_xmit,
+};
+
+static void mac802154_wpan_free(struct net_device *dev)
+{
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+
+	mac802154_llsec_destroy(&sdata->sec);
+
+	free_netdev(dev);
+}
+
+static void ieee802154_if_setup(struct net_device *dev)
+{
+	dev->addr_len		= IEEE802154_EXTENDED_ADDR_LEN;
+	memset(dev->broadcast, 0xff, IEEE802154_EXTENDED_ADDR_LEN);
+
+	dev->hard_header_len	= MAC802154_FRAME_HARD_HEADER_LEN;
+	dev->needed_tailroom	= 2 + 16; /* FCS + MIC */
+	dev->mtu		= IEEE802154_MTU;
+	dev->tx_queue_len	= 300;
+	dev->flags		= IFF_NOARP | IFF_BROADCAST;
+}
+
+static int
+ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata,
+		       enum nl802154_iftype type)
+{
+	struct wpan_dev *wpan_dev = &sdata->wpan_dev;
+
+	/* set some type-dependent values */
+	sdata->vif.type = type;
+	sdata->wpan_dev.iftype = type;
+
+	get_random_bytes(&wpan_dev->bsn, 1);
+	get_random_bytes(&wpan_dev->dsn, 1);
+
+	/* defaults per 802.15.4-2011 */
+	wpan_dev->min_be = 3;
+	wpan_dev->max_be = 5;
+	wpan_dev->csma_retries = 4;
+	/* for compatibility, actual default is 3 */
+	wpan_dev->frame_retries = -1;
+
+	wpan_dev->pan_id = cpu_to_le16(IEEE802154_PANID_BROADCAST);
+	wpan_dev->short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST);
+
+	switch (type) {
+	case NL802154_IFTYPE_NODE:
+		ieee802154_be64_to_le64(&wpan_dev->extended_addr,
+					sdata->dev->dev_addr);
+
+		sdata->dev->header_ops = &mac802154_header_ops;
+		sdata->dev->destructor = mac802154_wpan_free;
+		sdata->dev->netdev_ops = &mac802154_wpan_ops;
+		sdata->dev->ml_priv = &mac802154_mlme_wpan;
+		wpan_dev->promiscuous_mode = false;
+
+		spin_lock_init(&sdata->mib_lock);
+		mutex_init(&sdata->sec_mtx);
+
+		mac802154_llsec_init(&sdata->sec);
+		break;
+	case NL802154_IFTYPE_MONITOR:
+		sdata->dev->destructor = free_netdev;
+		sdata->dev->netdev_ops = &mac802154_monitor_ops;
+		wpan_dev->promiscuous_mode = true;
+		break;
+	default:
+		BUG();
+	}
+
+	return 0;
+}
+
+struct net_device *
+ieee802154_if_add(struct ieee802154_local *local, const char *name,
+		  unsigned char name_assign_type, enum nl802154_iftype type,
+		  __le64 extended_addr)
+{
+	struct net_device *ndev = NULL;
+	struct ieee802154_sub_if_data *sdata = NULL;
+	int ret = -ENOMEM;
+
+	ASSERT_RTNL();
+
+	ndev = alloc_netdev(sizeof(*sdata) + local->hw.vif_data_size, name,
+			    name_assign_type, ieee802154_if_setup);
+	if (!ndev)
+		return ERR_PTR(-ENOMEM);
+
+	ndev->needed_headroom = local->hw.extra_tx_headroom;
+
+	ret = dev_alloc_name(ndev, ndev->name);
+	if (ret < 0)
+		goto err;
+
+	ieee802154_le64_to_be64(ndev->perm_addr,
+				&local->hw.phy->perm_extended_addr);
+	switch (type) {
+	case NL802154_IFTYPE_NODE:
+		ndev->type = ARPHRD_IEEE802154;
+		if (ieee802154_is_valid_extended_addr(extended_addr))
+			ieee802154_le64_to_be64(ndev->dev_addr, &extended_addr);
+		else
+			memcpy(ndev->dev_addr, ndev->perm_addr,
+			       IEEE802154_EXTENDED_ADDR_LEN);
+		break;
+	case NL802154_IFTYPE_MONITOR:
+		ndev->type = ARPHRD_IEEE802154_MONITOR;
+		break;
+	default:
+		ret = -EINVAL;
+		goto err;
+	}
+
+	/* TODO check this */
+	SET_NETDEV_DEV(ndev, &local->phy->dev);
+	sdata = netdev_priv(ndev);
+	ndev->ieee802154_ptr = &sdata->wpan_dev;
+	memcpy(sdata->name, ndev->name, IFNAMSIZ);
+	sdata->dev = ndev;
+	sdata->wpan_dev.wpan_phy = local->hw.phy;
+	sdata->local = local;
+
+	/* setup type-dependent data */
+	ret = ieee802154_setup_sdata(sdata, type);
+	if (ret)
+		goto err;
+
+	ret = register_netdevice(ndev);
+	if (ret < 0)
+		goto err;
+
+	mutex_lock(&local->iflist_mtx);
+	list_add_tail_rcu(&sdata->list, &local->interfaces);
+	mutex_unlock(&local->iflist_mtx);
+
+	return ndev;
+
+err:
+	free_netdev(ndev);
+	return ERR_PTR(ret);
+}
+
+void ieee802154_if_remove(struct ieee802154_sub_if_data *sdata)
+{
+	ASSERT_RTNL();
+
+	mutex_lock(&sdata->local->iflist_mtx);
+	list_del_rcu(&sdata->list);
+	mutex_unlock(&sdata->local->iflist_mtx);
+
+	synchronize_rcu();
+	unregister_netdevice(sdata->dev);
+}
+
+void ieee802154_remove_interfaces(struct ieee802154_local *local)
+{
+	struct ieee802154_sub_if_data *sdata, *tmp;
+
+	mutex_lock(&local->iflist_mtx);
+	list_for_each_entry_safe(sdata, tmp, &local->interfaces, list) {
+		list_del(&sdata->list);
+
+		unregister_netdevice(sdata->dev);
+	}
+	mutex_unlock(&local->iflist_mtx);
+}
+
+static int netdev_notify(struct notifier_block *nb,
+			 unsigned long state, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct ieee802154_sub_if_data *sdata;
+
+	if (state != NETDEV_CHANGENAME)
+		return NOTIFY_DONE;
+
+	if (!dev->ieee802154_ptr || !dev->ieee802154_ptr->wpan_phy)
+		return NOTIFY_DONE;
+
+	if (dev->ieee802154_ptr->wpan_phy->privid != mac802154_wpan_phy_privid)
+		return NOTIFY_DONE;
+
+	sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+	memcpy(sdata->name, dev->name, IFNAMSIZ);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block mac802154_netdev_notifier = {
+	.notifier_call = netdev_notify,
+};
+
+int ieee802154_iface_init(void)
+{
+	return register_netdevice_notifier(&mac802154_netdev_notifier);
+}
+
+void ieee802154_iface_exit(void)
+{
+	unregister_netdevice_notifier(&mac802154_netdev_notifier);
+}
diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c
index 457058142098..985e9394e2af 100644
--- a/net/mac802154/llsec.c
+++ b/net/mac802154/llsec.c
@@ -17,10 +17,11 @@
 #include <linux/err.h>
 #include <linux/bug.h>
 #include <linux/completion.h>
-#include <net/ieee802154.h>
-#include <crypto/algapi.h>
+#include <linux/crypto.h>
+#include <linux/ieee802154.h>
+#include <crypto/aead.h>
 
-#include "mac802154.h"
+#include "ieee802154_i.h"
 #include "llsec.h"
 
 static void llsec_key_put(struct mac802154_llsec_key *key);
@@ -75,8 +76,6 @@ void mac802154_llsec_destroy(struct mac802154_llsec *sec)
 	}
 }
 
-
-
 int mac802154_llsec_get_params(struct mac802154_llsec *sec,
 			       struct ieee802154_llsec_params *params)
 {
@@ -117,8 +116,6 @@ int mac802154_llsec_set_params(struct mac802154_llsec *sec,
 	return 0;
 }
 
-
-
 static struct mac802154_llsec_key*
 llsec_key_alloc(const struct ieee802154_llsec_key *template)
 {
@@ -138,7 +135,7 @@ llsec_key_alloc(const struct ieee802154_llsec_key *template)
 	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])
+		if (IS_ERR(key->tfm[i]))
 			goto err_tfm;
 		if (crypto_aead_setkey(key->tfm[i], template->key,
 				       IEEE802154_LLSEC_KEY_SIZE))
@@ -148,7 +145,7 @@ llsec_key_alloc(const struct ieee802154_llsec_key *template)
 	}
 
 	key->tfm0 = crypto_alloc_blkcipher("ctr(aes)", 0, CRYPTO_ALG_ASYNC);
-	if (!key->tfm0)
+	if (IS_ERR(key->tfm0))
 		goto err_tfm;
 
 	if (crypto_blkcipher_setkey(key->tfm0, template->key,
@@ -294,8 +291,6 @@ int mac802154_llsec_key_del(struct mac802154_llsec *sec,
 	return -ENOENT;
 }
 
-
-
 static bool llsec_dev_use_shortaddr(__le16 short_addr)
 {
 	return short_addr != cpu_to_le16(IEEE802154_ADDR_UNDEF) &&
@@ -304,12 +299,12 @@ static bool llsec_dev_use_shortaddr(__le16 short_addr)
 
 static u32 llsec_dev_hash_short(__le16 short_addr, __le16 pan_id)
 {
-	return ((__force u16) short_addr) << 16 | (__force u16) pan_id;
+	return ((__force u16)short_addr) << 16 | (__force u16)pan_id;
 }
 
 static u64 llsec_dev_hash_long(__le64 hwaddr)
 {
-	return (__force u64) hwaddr;
+	return (__force u64)hwaddr;
 }
 
 static struct mac802154_llsec_device*
@@ -411,8 +406,6 @@ int mac802154_llsec_dev_del(struct mac802154_llsec *sec, __le64 device_addr)
 	return 0;
 }
 
-
-
 static struct mac802154_llsec_device_key*
 llsec_devkey_find(struct mac802154_llsec_device *dev,
 		  const struct ieee802154_llsec_key_id *key)
@@ -475,8 +468,6 @@ int mac802154_llsec_devkey_del(struct mac802154_llsec *sec,
 	return 0;
 }
 
-
-
 static struct mac802154_llsec_seclevel*
 llsec_find_seclevel(const struct mac802154_llsec *sec,
 		    const struct ieee802154_llsec_seclevel *sl)
@@ -532,8 +523,6 @@ int mac802154_llsec_seclevel_del(struct mac802154_llsec *sec,
 	return 0;
 }
 
-
-
 static int llsec_recover_addr(struct mac802154_llsec *sec,
 			      struct ieee802154_addr *addr)
 {
@@ -609,7 +598,6 @@ found:
 	return llsec_key_get(key);
 }
 
-
 static void llsec_geniv(u8 iv[16], __le64 addr,
 			const struct ieee802154_sechdr *sec)
 {
@@ -662,7 +650,7 @@ llsec_do_encrypt_auth(struct sk_buff *skb, const struct mac802154_llsec *sec,
 	u8 iv[16];
 	unsigned char *data;
 	int authlen, assoclen, datalen, rc;
-	struct scatterlist src, assoc[2], dst[2];
+	struct scatterlist sg;
 	struct aead_request *req;
 
 	authlen = ieee802154_sechdr_authtag_len(&hdr->sec);
@@ -672,30 +660,23 @@ llsec_do_encrypt_auth(struct sk_buff *skb, const struct mac802154_llsec *sec,
 	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);
+	skb_put(skb, authlen);
+
+	sg_init_one(&sg, skb_mac_header(skb), assoclen + datalen + authlen);
+
+	if (!(hdr->sec.level & IEEE802154_SCF_SECLEVEL_ENC)) {
 		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);
+	aead_request_set_crypt(req, &sg, &sg, datalen, iv);
+	aead_request_set_ad(req, assoclen);
 
 	rc = crypto_aead_encrypt(req);
 
@@ -786,8 +767,6 @@ fail:
 	return rc;
 }
 
-
-
 static struct mac802154_llsec_device*
 llsec_lookup_dev(struct mac802154_llsec *sec,
 		 const struct ieee802154_addr *addr)
@@ -873,7 +852,7 @@ llsec_do_decrypt_auth(struct sk_buff *skb, const struct mac802154_llsec *sec,
 	u8 iv[16];
 	unsigned char *data;
 	int authlen, datalen, assoclen, rc;
-	struct scatterlist src, assoc[2];
+	struct scatterlist sg;
 	struct aead_request *req;
 
 	authlen = ieee802154_sechdr_authtag_len(&hdr->sec);
@@ -883,27 +862,21 @@ llsec_do_decrypt_auth(struct sk_buff *skb, const struct mac802154_llsec *sec,
 	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);
+	sg_init_one(&sg, skb_mac_header(skb), assoclen + datalen);
+
+	if (!(hdr->sec.level & IEEE802154_SCF_SECLEVEL_ENC)) {
 		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);
+	aead_request_set_crypt(req, &sg, &sg, datalen, iv);
+	aead_request_set_ad(req, assoclen);
 
 	rc = crypto_aead_decrypt(req);
 
diff --git a/net/mac802154/mac_cmd.c b/net/mac802154/mac_cmd.c
index bf809131eef7..bdccb4ecd30f 100644
--- a/net/mac802154/mac_cmd.c
+++ b/net/mac802154/mac_cmd.c
@@ -12,10 +12,6 @@
  * 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.
- *
  * Written by:
  * Sergey Lapin <slapin@ossfans.org>
  * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
@@ -24,14 +20,14 @@
 
 #include <linux/skbuff.h>
 #include <linux/if_arp.h>
+#include <linux/ieee802154.h>
 
-#include <net/ieee802154.h>
 #include <net/ieee802154_netdev.h>
-#include <net/wpan-phy.h>
+#include <net/cfg802154.h>
 #include <net/mac802154.h>
-#include <net/nl802154.h>
 
-#include "mac802154.h"
+#include "ieee802154_i.h"
+#include "driver-ops.h"
 
 static int mac802154_mlme_start_req(struct net_device *dev,
 				    struct ieee802154_addr *addr,
@@ -43,11 +39,12 @@ static int mac802154_mlme_start_req(struct net_device *dev,
 	struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev);
 	int rc = 0;
 
+	ASSERT_RTNL();
+
 	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) {
@@ -69,21 +66,71 @@ static int mac802154_mlme_start_req(struct net_device *dev,
 		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 rc;
 }
 
-static struct wpan_phy *mac802154_get_phy(const struct net_device *dev)
+static int mac802154_set_mac_params(struct net_device *dev,
+				    const struct ieee802154_mac_params *params)
 {
-	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+	struct ieee802154_local *local = sdata->local;
+	struct wpan_dev *wpan_dev = &sdata->wpan_dev;
+	int ret;
+
+	ASSERT_RTNL();
+
+	/* PHY */
+	wpan_dev->wpan_phy->transmit_power = params->transmit_power;
+	wpan_dev->wpan_phy->cca = params->cca;
+	wpan_dev->wpan_phy->cca_ed_level = params->cca_ed_level;
+
+	/* MAC */
+	wpan_dev->min_be = params->min_be;
+	wpan_dev->max_be = params->max_be;
+	wpan_dev->csma_retries = params->csma_retries;
+	wpan_dev->frame_retries = params->frame_retries;
+	wpan_dev->lbt = params->lbt;
+
+	if (local->hw.flags & IEEE802154_HW_TXPOWER) {
+		ret = drv_set_tx_power(local, params->transmit_power);
+		if (ret < 0)
+			return ret;
+	}
+
+	if (local->hw.flags & IEEE802154_HW_CCA_MODE) {
+		ret = drv_set_cca_mode(local, &params->cca);
+		if (ret < 0)
+			return ret;
+	}
 
-	BUG_ON(dev->type != ARPHRD_IEEE802154);
+	if (local->hw.flags & IEEE802154_HW_CCA_ED_LEVEL) {
+		ret = drv_set_cca_ed_level(local, params->cca_ed_level);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
 
-	return to_phy(get_device(&priv->hw->phy->dev));
+static void mac802154_get_mac_params(struct net_device *dev,
+				     struct ieee802154_mac_params *params)
+{
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+	struct wpan_dev *wpan_dev = &sdata->wpan_dev;
+
+	ASSERT_RTNL();
+
+	/* PHY */
+	params->transmit_power = wpan_dev->wpan_phy->transmit_power;
+	params->cca = wpan_dev->wpan_phy->cca;
+	params->cca_ed_level = wpan_dev->wpan_phy->cca_ed_level;
+
+	/* MAC */
+	params->min_be = wpan_dev->min_be;
+	params->max_be = wpan_dev->max_be;
+	params->csma_retries = wpan_dev->csma_retries;
+	params->frame_retries = wpan_dev->frame_retries;
+	params->lbt = wpan_dev->lbt;
 }
 
 static struct ieee802154_llsec_ops mac802154_llsec_ops = {
@@ -102,12 +149,7 @@ static struct ieee802154_llsec_ops mac802154_llsec_ops = {
 	.unlock_table = mac802154_unlock_table,
 };
 
-struct ieee802154_reduced_mlme_ops mac802154_mlme_reduced = {
-	.get_phy = mac802154_get_phy,
-};
-
 struct ieee802154_mlme_ops mac802154_mlme_wpan = {
-	.get_phy = mac802154_get_phy,
 	.start_req = mac802154_mlme_start_req,
 	.get_pan_id = mac802154_dev_get_pan_id,
 	.get_short_addr = mac802154_dev_get_short_addr,
diff --git a/net/mac802154/main.c b/net/mac802154/main.c
new file mode 100644
index 000000000000..08cb32dc8fd3
--- /dev/null
+++ b/net/mac802154/main.c
@@ -0,0 +1,220 @@
+/*
+ * Copyright (C) 2007-2012 Siemens AG
+ *
+ * Written by:
+ * Alexander Smirnov <alex.bluesman.smirnov@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.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+
+#include <net/netlink.h>
+#include <net/nl802154.h>
+#include <net/mac802154.h>
+#include <net/ieee802154_netdev.h>
+#include <net/route.h>
+#include <net/cfg802154.h>
+
+#include "ieee802154_i.h"
+#include "cfg.h"
+
+static void ieee802154_tasklet_handler(unsigned long data)
+{
+	struct ieee802154_local *local = (struct ieee802154_local *)data;
+	struct sk_buff *skb;
+
+	while ((skb = skb_dequeue(&local->skb_queue))) {
+		switch (skb->pkt_type) {
+		case IEEE802154_RX_MSG:
+			/* Clear skb->pkt_type in order to not confuse kernel
+			 * netstack.
+			 */
+			skb->pkt_type = 0;
+			ieee802154_rx(&local->hw, skb);
+			break;
+		default:
+			WARN(1, "mac802154: Packet is of unknown type %d\n",
+			     skb->pkt_type);
+			kfree_skb(skb);
+			break;
+		}
+	}
+}
+
+struct ieee802154_hw *
+ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops)
+{
+	struct wpan_phy *phy;
+	struct ieee802154_local *local;
+	size_t priv_size;
+
+	if (!ops || !(ops->xmit_async || ops->xmit_sync) || !ops->ed ||
+	    !ops->start || !ops->stop || !ops->set_channel) {
+		pr_err("undefined IEEE802.15.4 device operations\n");
+		return NULL;
+	}
+
+	/* Ensure 32-byte alignment of our private data and hw private data.
+	 * We use the wpan_phy priv data for both our ieee802154_local and for
+	 * the driver's private data
+	 *
+	 * in memory it'll be like this:
+	 *
+	 * +-------------------------+
+	 * | struct wpan_phy         |
+	 * +-------------------------+
+	 * | struct ieee802154_local |
+	 * +-------------------------+
+	 * | driver's private data   |
+	 * +-------------------------+
+	 *
+	 * Due to ieee802154 layer isn't aware of driver and MAC structures,
+	 * so lets align them here.
+	 */
+
+	priv_size = ALIGN(sizeof(*local), NETDEV_ALIGN) + priv_data_len;
+
+	phy = wpan_phy_new(&mac802154_config_ops, priv_size);
+	if (!phy) {
+		pr_err("failure to allocate master IEEE802.15.4 device\n");
+		return NULL;
+	}
+
+	phy->privid = mac802154_wpan_phy_privid;
+
+	local = wpan_phy_priv(phy);
+	local->phy = phy;
+	local->hw.phy = local->phy;
+	local->hw.priv = (char *)local + ALIGN(sizeof(*local), NETDEV_ALIGN);
+	local->ops = ops;
+
+	INIT_LIST_HEAD(&local->interfaces);
+	mutex_init(&local->iflist_mtx);
+
+	tasklet_init(&local->tasklet,
+		     ieee802154_tasklet_handler,
+		     (unsigned long)local);
+
+	skb_queue_head_init(&local->skb_queue);
+
+	return &local->hw;
+}
+EXPORT_SYMBOL(ieee802154_alloc_hw);
+
+void ieee802154_free_hw(struct ieee802154_hw *hw)
+{
+	struct ieee802154_local *local = hw_to_local(hw);
+
+	BUG_ON(!list_empty(&local->interfaces));
+
+	mutex_destroy(&local->iflist_mtx);
+
+	wpan_phy_free(local->phy);
+}
+EXPORT_SYMBOL(ieee802154_free_hw);
+
+static void ieee802154_setup_wpan_phy_pib(struct wpan_phy *wpan_phy)
+{
+	/* TODO warn on empty symbol_duration
+	 * Should be done when all drivers sets this value.
+	 */
+
+	wpan_phy->lifs_period = IEEE802154_LIFS_PERIOD *
+				wpan_phy->symbol_duration;
+	wpan_phy->sifs_period = IEEE802154_SIFS_PERIOD *
+				wpan_phy->symbol_duration;
+}
+
+int ieee802154_register_hw(struct ieee802154_hw *hw)
+{
+	struct ieee802154_local *local = hw_to_local(hw);
+	struct net_device *dev;
+	int rc = -ENOSYS;
+
+	local->workqueue =
+		create_singlethread_workqueue(wpan_phy_name(local->phy));
+	if (!local->workqueue) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	hrtimer_init(&local->ifs_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	local->ifs_timer.function = ieee802154_xmit_ifs_timer;
+
+	wpan_phy_set_dev(local->phy, local->hw.parent);
+
+	ieee802154_setup_wpan_phy_pib(local->phy);
+
+	rc = wpan_phy_register(local->phy);
+	if (rc < 0)
+		goto out_wq;
+
+	rtnl_lock();
+
+	dev = ieee802154_if_add(local, "wpan%d", NET_NAME_ENUM,
+				NL802154_IFTYPE_NODE,
+				cpu_to_le64(0x0000000000000000ULL));
+	if (IS_ERR(dev)) {
+		rtnl_unlock();
+		rc = PTR_ERR(dev);
+		goto out_phy;
+	}
+
+	rtnl_unlock();
+
+	return 0;
+
+out_phy:
+	wpan_phy_unregister(local->phy);
+out_wq:
+	destroy_workqueue(local->workqueue);
+out:
+	return rc;
+}
+EXPORT_SYMBOL(ieee802154_register_hw);
+
+void ieee802154_unregister_hw(struct ieee802154_hw *hw)
+{
+	struct ieee802154_local *local = hw_to_local(hw);
+
+	tasklet_kill(&local->tasklet);
+	flush_workqueue(local->workqueue);
+	destroy_workqueue(local->workqueue);
+
+	rtnl_lock();
+
+	ieee802154_remove_interfaces(local);
+
+	rtnl_unlock();
+
+	wpan_phy_unregister(local->phy);
+}
+EXPORT_SYMBOL(ieee802154_unregister_hw);
+
+static int __init ieee802154_init(void)
+{
+	return ieee802154_iface_init();
+}
+
+static void __exit ieee802154_exit(void)
+{
+	ieee802154_iface_exit();
+
+	rcu_barrier();
+}
+
+subsys_initcall(ieee802154_init);
+module_exit(ieee802154_exit);
+
+MODULE_DESCRIPTION("IEEE 802.15.4 subsystem");
+MODULE_LICENSE("GPL v2");
diff --git a/net/mac802154/mib.c b/net/mac802154/mib.c
index 868a040fd422..5cf019a57fd7 100644
--- a/net/mac802154/mib.c
+++ b/net/mac802154/mib.c
@@ -10,10 +10,6 @@
  * 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.
- *
  * Written by:
  * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
  * Sergey Lapin <slapin@ossfans.org>
@@ -25,208 +21,100 @@
 
 #include <net/mac802154.h>
 #include <net/ieee802154_netdev.h>
-#include <net/wpan-phy.h>
-
-#include "mac802154.h"
-
-struct phy_chan_notify_work {
-	struct work_struct work;
-	struct net_device *dev;
-};
-
-struct hw_addr_filt_notify_work {
-	struct work_struct work;
-	struct net_device *dev;
-	unsigned long changed;
-};
-
-static struct mac802154_priv *mac802154_slave_get_priv(struct net_device *dev)
-{
-	struct mac802154_sub_if_data *priv = netdev_priv(dev);
-
-	BUG_ON(dev->type != ARPHRD_IEEE802154);
-
-	return priv->hw;
-}
-
-static void hw_addr_notify(struct work_struct *work)
-{
-	struct hw_addr_filt_notify_work *nw = container_of(work,
-			struct hw_addr_filt_notify_work, work);
-	struct mac802154_priv *hw = mac802154_slave_get_priv(nw->dev);
-	int res;
+#include <net/cfg802154.h>
 
-	res = hw->ops->set_hw_addr_filt(&hw->hw,
-					&hw->hw.hw_filt,
-					nw->changed);
-	if (res)
-		pr_debug("failed changed mask %lx\n", nw->changed);
-
-	kfree(nw);
-}
-
-static void set_hw_addr_filt(struct net_device *dev, unsigned long changed)
-{
-	struct mac802154_sub_if_data *priv = netdev_priv(dev);
-	struct hw_addr_filt_notify_work *work;
-
-	work = kzalloc(sizeof(*work), GFP_ATOMIC);
-	if (!work)
-		return;
-
-	INIT_WORK(&work->work, hw_addr_notify);
-	work->dev = dev;
-	work->changed = changed;
-	queue_work(priv->hw->dev_workqueue, &work->work);
-}
+#include "ieee802154_i.h"
+#include "driver-ops.h"
 
 void mac802154_dev_set_short_addr(struct net_device *dev, __le16 val)
 {
-	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
 
 	BUG_ON(dev->type != ARPHRD_IEEE802154);
 
-	spin_lock_bh(&priv->mib_lock);
-	priv->short_addr = val;
-	spin_unlock_bh(&priv->mib_lock);
-
-	if ((priv->hw->ops->set_hw_addr_filt) &&
-	    (priv->hw->hw.hw_filt.short_addr != priv->short_addr)) {
-		priv->hw->hw.hw_filt.short_addr = priv->short_addr;
-		set_hw_addr_filt(dev, IEEE802515_AFILT_SADDR_CHANGED);
-	}
+	spin_lock_bh(&sdata->mib_lock);
+	sdata->wpan_dev.short_addr = val;
+	spin_unlock_bh(&sdata->mib_lock);
 }
 
 __le16 mac802154_dev_get_short_addr(const struct net_device *dev)
 {
-	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
 	__le16 ret;
 
 	BUG_ON(dev->type != ARPHRD_IEEE802154);
 
-	spin_lock_bh(&priv->mib_lock);
-	ret = priv->short_addr;
-	spin_unlock_bh(&priv->mib_lock);
+	spin_lock_bh(&sdata->mib_lock);
+	ret = sdata->wpan_dev.short_addr;
+	spin_unlock_bh(&sdata->mib_lock);
 
 	return ret;
 }
 
-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 &&
-	    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);
-	}
-}
-
 __le16 mac802154_dev_get_pan_id(const struct net_device *dev)
 {
-	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
 	__le16 ret;
 
 	BUG_ON(dev->type != ARPHRD_IEEE802154);
 
-	spin_lock_bh(&priv->mib_lock);
-	ret = priv->pan_id;
-	spin_unlock_bh(&priv->mib_lock);
+	spin_lock_bh(&sdata->mib_lock);
+	ret = sdata->wpan_dev.pan_id;
+	spin_unlock_bh(&sdata->mib_lock);
 
 	return ret;
 }
 
 void mac802154_dev_set_pan_id(struct net_device *dev, __le16 val)
 {
-	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
 
 	BUG_ON(dev->type != ARPHRD_IEEE802154);
 
-	spin_lock_bh(&priv->mib_lock);
-	priv->pan_id = val;
-	spin_unlock_bh(&priv->mib_lock);
-
-	if ((priv->hw->ops->set_hw_addr_filt) &&
-	    (priv->hw->hw.hw_filt.pan_id != priv->pan_id)) {
-		priv->hw->hw.hw_filt.pan_id = priv->pan_id;
-		set_hw_addr_filt(dev, IEEE802515_AFILT_PANID_CHANGED);
-	}
+	spin_lock_bh(&sdata->mib_lock);
+	sdata->wpan_dev.pan_id = val;
+	spin_unlock_bh(&sdata->mib_lock);
 }
 
 u8 mac802154_dev_get_dsn(const struct net_device *dev)
 {
-	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
 
 	BUG_ON(dev->type != ARPHRD_IEEE802154);
 
-	return priv->dsn++;
-}
-
-static void phy_chan_notify(struct work_struct *work)
-{
-	struct phy_chan_notify_work *nw = container_of(work,
-					  struct phy_chan_notify_work, work);
-	struct mac802154_priv *hw = mac802154_slave_get_priv(nw->dev);
-	struct mac802154_sub_if_data *priv = netdev_priv(nw->dev);
-	int res;
-
-	mutex_lock(&priv->hw->phy->pib_lock);
-	res = hw->ops->set_channel(&hw->hw, priv->page, priv->chan);
-	if (res) {
-		pr_debug("set_channel failed\n");
-	} else {
-		priv->hw->phy->current_channel = priv->chan;
-		priv->hw->phy->current_page = priv->page;
-	}
-	mutex_unlock(&priv->hw->phy->pib_lock);
-
-	kfree(nw);
+	return sdata->wpan_dev.dsn++;
 }
 
 void mac802154_dev_set_page_channel(struct net_device *dev, u8 page, u8 chan)
 {
-	struct mac802154_sub_if_data *priv = netdev_priv(dev);
-	struct phy_chan_notify_work *work;
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+	struct ieee802154_local *local = sdata->local;
+	int res;
 
 	BUG_ON(dev->type != ARPHRD_IEEE802154);
 
-	spin_lock_bh(&priv->mib_lock);
-	priv->page = page;
-	priv->chan = chan;
-	spin_unlock_bh(&priv->mib_lock);
-
-	mutex_lock(&priv->hw->phy->pib_lock);
-	if (priv->hw->phy->current_channel != priv->chan ||
-	    priv->hw->phy->current_page != priv->page) {
-		mutex_unlock(&priv->hw->phy->pib_lock);
-
-		work = kzalloc(sizeof(*work), GFP_ATOMIC);
-		if (!work)
-			return;
-
-		INIT_WORK(&work->work, phy_chan_notify);
-		work->dev = dev;
-		queue_work(priv->hw->dev_workqueue, &work->work);
+	res = drv_set_channel(local, page, chan);
+	if (res) {
+		pr_debug("set_channel failed\n");
 	} else {
-		mutex_unlock(&priv->hw->phy->pib_lock);
+		mutex_lock(&local->phy->pib_lock);
+		local->phy->current_channel = chan;
+		local->phy->current_page = page;
+		mutex_unlock(&local->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);
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(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);
+	mutex_lock(&sdata->sec_mtx);
+	res = mac802154_llsec_get_params(&sdata->sec, params);
+	mutex_unlock(&sdata->sec_mtx);
 
 	return res;
 }
@@ -235,31 +123,30 @@ 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);
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(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);
+	mutex_lock(&sdata->sec_mtx);
+	res = mac802154_llsec_set_params(&sdata->sec, params, changed);
+	mutex_unlock(&sdata->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);
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(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);
+	mutex_lock(&sdata->sec_mtx);
+	res = mac802154_llsec_key_add(&sdata->sec, id, key);
+	mutex_unlock(&sdata->sec_mtx);
 
 	return res;
 }
@@ -267,61 +154,59 @@ int mac802154_add_key(struct net_device *dev,
 int mac802154_del_key(struct net_device *dev,
 		      const struct ieee802154_llsec_key_id *id)
 {
-	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(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);
+	mutex_lock(&sdata->sec_mtx);
+	res = mac802154_llsec_key_del(&sdata->sec, id);
+	mutex_unlock(&sdata->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);
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(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);
+	mutex_lock(&sdata->sec_mtx);
+	res = mac802154_llsec_dev_add(&sdata->sec, llsec_dev);
+	mutex_unlock(&sdata->sec_mtx);
 
 	return res;
 }
 
 int mac802154_del_dev(struct net_device *dev, __le64 dev_addr)
 {
-	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(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);
+	mutex_lock(&sdata->sec_mtx);
+	res = mac802154_llsec_dev_del(&sdata->sec, dev_addr);
+	mutex_unlock(&sdata->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);
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(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);
+	mutex_lock(&sdata->sec_mtx);
+	res = mac802154_llsec_devkey_add(&sdata->sec, device_addr, key);
+	mutex_unlock(&sdata->sec_mtx);
 
 	return res;
 }
@@ -330,30 +215,29 @@ 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);
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(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);
+	mutex_lock(&sdata->sec_mtx);
+	res = mac802154_llsec_devkey_del(&sdata->sec, device_addr, key);
+	mutex_unlock(&sdata->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);
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(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);
+	mutex_lock(&sdata->sec_mtx);
+	res = mac802154_llsec_seclevel_add(&sdata->sec, sl);
+	mutex_unlock(&sdata->sec_mtx);
 
 	return res;
 }
@@ -361,43 +245,42 @@ int mac802154_add_seclevel(struct net_device *dev,
 int mac802154_del_seclevel(struct net_device *dev,
 			   const struct ieee802154_llsec_seclevel *sl)
 {
-	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(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);
+	mutex_lock(&sdata->sec_mtx);
+	res = mac802154_llsec_seclevel_del(&sdata->sec, sl);
+	mutex_unlock(&sdata->sec_mtx);
 
 	return res;
 }
 
-
 void mac802154_lock_table(struct net_device *dev)
 {
-	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
 
 	BUG_ON(dev->type != ARPHRD_IEEE802154);
 
-	mutex_lock(&priv->sec_mtx);
+	mutex_lock(&sdata->sec_mtx);
 }
 
 void mac802154_get_table(struct net_device *dev,
 			 struct ieee802154_llsec_table **t)
 {
-	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
 
 	BUG_ON(dev->type != ARPHRD_IEEE802154);
 
-	*t = &priv->sec.table;
+	*t = &sdata->sec.table;
 }
 
 void mac802154_unlock_table(struct net_device *dev)
 {
-	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
 
 	BUG_ON(dev->type != ARPHRD_IEEE802154);
 
-	mutex_unlock(&priv->sec_mtx);
+	mutex_unlock(&sdata->sec_mtx);
 }
diff --git a/net/mac802154/monitor.c b/net/mac802154/monitor.c
deleted file mode 100644
index a68230e2b25f..000000000000
--- a/net/mac802154/monitor.c
+++ /dev/null
@@ -1,117 +0,0 @@
-/*
- * Copyright 2007, 2008, 2009 Siemens AG
- *
- * 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.
- *
- * Written by:
- * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
- * Sergey Lapin <slapin@ossfans.org>
- * Maxim Gorbachyov <maxim.gorbachev@siemens.com>
- * Alexander Smirnov <alex.bluesman.smirnov@gmail.com>
- */
-
-#include <linux/netdevice.h>
-#include <linux/skbuff.h>
-#include <linux/if_arp.h>
-#include <linux/crc-ccitt.h>
-
-#include <net/ieee802154.h>
-#include <net/mac802154.h>
-#include <net/netlink.h>
-#include <net/wpan-phy.h>
-#include <linux/nl802154.h>
-
-#include "mac802154.h"
-
-static netdev_tx_t mac802154_monitor_xmit(struct sk_buff *skb,
-					  struct net_device *dev)
-{
-	struct mac802154_sub_if_data *priv;
-	u8 chan, page;
-
-	priv = netdev_priv(dev);
-
-	/* FIXME: locking */
-	chan = priv->hw->phy->current_channel;
-	page = priv->hw->phy->current_page;
-
-	if (chan == MAC802154_CHAN_NONE) /* not initialized */
-		return NETDEV_TX_OK;
-
-	if (WARN_ON(page >= WPAN_NUM_PAGES) ||
-	    WARN_ON(chan >= WPAN_NUM_CHANNELS))
-		return NETDEV_TX_OK;
-
-	skb->skb_iif = dev->ifindex;
-	dev->stats.tx_packets++;
-	dev->stats.tx_bytes += skb->len;
-
-	return mac802154_tx(priv->hw, skb, page, chan);
-}
-
-
-void mac802154_monitors_rx(struct mac802154_priv *priv, struct sk_buff *skb)
-{
-	struct sk_buff *skb2;
-	struct mac802154_sub_if_data *sdata;
-	u16 crc = crc_ccitt(0, skb->data, skb->len);
-	u8 *data;
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(sdata, &priv->slaves, list) {
-		if (sdata->type != IEEE802154_DEV_MONITOR ||
-		    !netif_running(sdata->dev))
-			continue;
-
-		skb2 = skb_clone(skb, GFP_ATOMIC);
-		skb2->dev = sdata->dev;
-		skb2->pkt_type = PACKET_HOST;
-		data = skb_put(skb2, 2);
-		data[0] = crc & 0xff;
-		data[1] = crc >> 8;
-
-		netif_rx_ni(skb2);
-	}
-	rcu_read_unlock();
-}
-
-static const struct net_device_ops mac802154_monitor_ops = {
-	.ndo_open		= mac802154_slave_open,
-	.ndo_stop		= mac802154_slave_close,
-	.ndo_start_xmit		= mac802154_monitor_xmit,
-};
-
-void mac802154_monitor_setup(struct net_device *dev)
-{
-	struct mac802154_sub_if_data *priv;
-
-	dev->addr_len		= 0;
-	dev->hard_header_len	= 0;
-	dev->needed_tailroom	= 2; /* room for FCS */
-	dev->mtu		= IEEE802154_MTU;
-	dev->tx_queue_len	= 10;
-	dev->type		= ARPHRD_IEEE802154_MONITOR;
-	dev->flags		= IFF_NOARP | IFF_BROADCAST;
-	dev->watchdog_timeo	= 0;
-
-	dev->destructor		= free_netdev;
-	dev->netdev_ops		= &mac802154_monitor_ops;
-	dev->ml_priv		= &mac802154_mlme_reduced;
-
-	priv = netdev_priv(dev);
-	priv->type = IEEE802154_DEV_MONITOR;
-
-	priv->chan = MAC802154_CHAN_NONE; /* not initialized */
-	priv->page = 0;
-}
diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c
index a14cf9ede171..c0d67b2b4132 100644
--- a/net/mac802154/rx.c
+++ b/net/mac802154/rx.c
@@ -10,10 +10,6 @@
  * 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.
- *
  * Written by:
  * Pavel Smolenskiy <pavel.smolenskiy@gmail.com>
  * Maxim Gorbachyov <maxim.gorbachev@siemens.com>
@@ -23,92 +19,284 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/workqueue.h>
 #include <linux/netdevice.h>
 #include <linux/crc-ccitt.h>
+#include <asm/unaligned.h>
 
 #include <net/mac802154.h>
 #include <net/ieee802154_netdev.h>
+#include <net/nl802154.h>
 
-#include "mac802154.h"
+#include "ieee802154_i.h"
 
-/* The IEEE 802.15.4 standard defines 4 MAC packet types:
- * - beacon frame
- * - MAC command frame
- * - acknowledgement frame
- * - data frame
- *
- * and only the data frame should be pushed to the upper layers, other types
- * are just internal MAC layer management information. So only data packets
- * are going to be sent to the networking queue, all other will be processed
- * right here by using the device workqueue.
- */
-struct rx_work {
-	struct sk_buff *skb;
-	struct work_struct work;
-	struct ieee802154_dev *dev;
-	u8 lqi;
-};
+static int ieee802154_deliver_skb(struct sk_buff *skb)
+{
+	skb->ip_summed = CHECKSUM_UNNECESSARY;
+	skb->protocol = htons(ETH_P_IEEE802154);
 
-static void
-mac802154_subif_rx(struct ieee802154_dev *hw, struct sk_buff *skb, u8 lqi)
+	return netif_receive_skb(skb);
+}
+
+static int
+ieee802154_subif_frame(struct ieee802154_sub_if_data *sdata,
+		       struct sk_buff *skb, const struct ieee802154_hdr *hdr)
 {
-	struct mac802154_priv *priv = mac802154_to_priv(hw);
+	struct wpan_dev *wpan_dev = &sdata->wpan_dev;
+	__le16 span, sshort;
+	int rc;
 
-	mac_cb(skb)->lqi = lqi;
-	skb->protocol = htons(ETH_P_IEEE802154);
-	skb_reset_mac_header(skb);
+	pr_debug("getting packet via slave interface %s\n", sdata->dev->name);
 
-	if (!(priv->hw.flags & IEEE802154_HW_OMIT_CKSUM)) {
-		u16 crc;
+	spin_lock_bh(&sdata->mib_lock);
 
-		if (skb->len < 2) {
-			pr_debug("got invalid frame\n");
-			goto fail;
-		}
-		crc = crc_ccitt(0, skb->data, skb->len);
-		if (crc) {
-			pr_debug("CRC mismatch\n");
-			goto fail;
-		}
-		skb_trim(skb, skb->len - 2); /* CRC */
+	span = wpan_dev->pan_id;
+	sshort = wpan_dev->short_addr;
+
+	switch (mac_cb(skb)->dest.mode) {
+	case 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
+			/* ACK comes with both addresses empty */
+			skb->pkt_type = PACKET_HOST;
+		break;
+	case IEEE802154_ADDR_LONG:
+		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)->dest.extended_addr == wpan_dev->extended_addr)
+			skb->pkt_type = PACKET_HOST;
+		else
+			skb->pkt_type = PACKET_OTHERHOST;
+		break;
+	case IEEE802154_ADDR_SHORT:
+		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)->dest.short_addr == sshort)
+			skb->pkt_type = PACKET_HOST;
+		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;
+		break;
+	default:
+		spin_unlock_bh(&sdata->mib_lock);
+		pr_debug("invalid dest mode\n");
+		goto fail;
 	}
 
-	mac802154_monitors_rx(priv, skb);
-	mac802154_wpans_rx(priv, skb);
+	spin_unlock_bh(&sdata->mib_lock);
 
-	return;
+	skb->dev = sdata->dev;
+
+	rc = mac802154_llsec_decrypt(&sdata->sec, skb);
+	if (rc) {
+		pr_debug("decryption failed: %i\n", rc);
+		goto fail;
+	}
+
+	sdata->dev->stats.rx_packets++;
+	sdata->dev->stats.rx_bytes += skb->len;
+
+	switch (mac_cb(skb)->type) {
+	case IEEE802154_FC_TYPE_DATA:
+		return ieee802154_deliver_skb(skb);
+	default:
+		pr_warn("ieee802154: bad frame received (type = %d)\n",
+			mac_cb(skb)->type);
+		goto fail;
+	}
 
 fail:
 	kfree_skb(skb);
+	return NET_RX_DROP;
 }
 
-static void mac802154_rx_worker(struct work_struct *work)
+static void
+ieee802154_print_addr(const char *name, const struct ieee802154_addr *addr)
 {
-	struct rx_work *rw = container_of(work, struct rx_work, work);
+	if (addr->mode == IEEE802154_ADDR_NONE)
+		pr_debug("%s not present\n", name);
+
+	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);
 
-	mac802154_subif_rx(rw->dev, rw->skb, rw->lqi);
-	kfree(rw);
+		pr_debug("%s is hardware: %8phC\n", name, &hw);
+	}
 }
 
-void
-ieee802154_rx_irqsafe(struct ieee802154_dev *dev, struct sk_buff *skb, u8 lqi)
+static int
+ieee802154_parse_frame_start(struct sk_buff *skb, struct ieee802154_hdr *hdr)
 {
-	struct mac802154_priv *priv = mac802154_to_priv(dev);
-	struct rx_work *work;
+	int hlen;
+	struct ieee802154_mac_cb *cb = mac_cb_init(skb);
 
-	if (!skb)
-		return;
+	skb_reset_mac_header(skb);
+
+	hlen = ieee802154_hdr_pull(skb, hdr);
+	if (hlen < 0)
+		return -EINVAL;
+
+	skb->mac_len = hlen;
+
+	pr_debug("fc: %04x dsn: %02x\n", le16_to_cpup((__le16 *)&hdr->fc),
+		 hdr->seq);
+
+	cb->type = hdr->fc.type;
+	cb->ackreq = hdr->fc.ack_request;
+	cb->secen = hdr->fc.security_enabled;
+
+	ieee802154_print_addr("destination", &hdr->dest);
+	ieee802154_print_addr("source", &hdr->source);
+
+	cb->source = hdr->source;
+	cb->dest = hdr->dest;
+
+	if (hdr->fc.security_enabled) {
+		u64 key;
+
+		pr_debug("seclevel %i\n", hdr->sec.level);
+
+		switch (hdr->sec.key_id_mode) {
+		case IEEE802154_SCF_KEY_IMPLICIT:
+			pr_debug("implicit key\n");
+			break;
+
+		case IEEE802154_SCF_KEY_INDEX:
+			pr_debug("key %02x\n", hdr->sec.key_id);
+			break;
+
+		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;
+
+		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;
+}
+
+static void
+__ieee802154_rx_handle_packet(struct ieee802154_local *local,
+			      struct sk_buff *skb)
+{
+	int ret;
+	struct ieee802154_sub_if_data *sdata;
+	struct ieee802154_hdr hdr;
 
-	work = kzalloc(sizeof(*work), GFP_ATOMIC);
-	if (!work)
+	ret = ieee802154_parse_frame_start(skb, &hdr);
+	if (ret) {
+		pr_debug("got invalid frame\n");
+		kfree_skb(skb);
 		return;
+	}
+
+	list_for_each_entry_rcu(sdata, &local->interfaces, list) {
+		if (sdata->vif.type != NL802154_IFTYPE_NODE ||
+		    !netif_running(sdata->dev))
+			continue;
+
+		ieee802154_subif_frame(sdata, skb, &hdr);
+		skb = NULL;
+		break;
+	}
+
+	if (skb)
+		kfree_skb(skb);
+}
+
+static void
+ieee802154_monitors_rx(struct ieee802154_local *local, struct sk_buff *skb)
+{
+	struct sk_buff *skb2;
+	struct ieee802154_sub_if_data *sdata;
+
+	skb_reset_mac_header(skb);
+	skb->ip_summed = CHECKSUM_UNNECESSARY;
+	skb->pkt_type = PACKET_OTHERHOST;
+	skb->protocol = htons(ETH_P_IEEE802154);
+
+	list_for_each_entry_rcu(sdata, &local->interfaces, list) {
+		if (sdata->vif.type != NL802154_IFTYPE_MONITOR)
+			continue;
+
+		if (!ieee802154_sdata_running(sdata))
+			continue;
+
+		skb2 = skb_clone(skb, GFP_ATOMIC);
+		if (skb2) {
+			skb2->dev = sdata->dev;
+			ieee802154_deliver_skb(skb2);
+
+			sdata->dev->stats.rx_packets++;
+			sdata->dev->stats.rx_bytes += skb->len;
+		}
+	}
+}
+
+void ieee802154_rx(struct ieee802154_hw *hw, struct sk_buff *skb)
+{
+	struct ieee802154_local *local = hw_to_local(hw);
+	u16 crc;
 
-	INIT_WORK(&work->work, mac802154_rx_worker);
-	work->skb = skb;
-	work->dev = dev;
-	work->lqi = lqi;
+	WARN_ON_ONCE(softirq_count() == 0);
 
-	queue_work(priv->dev_workqueue, &work->work);
+	/* TODO: When a transceiver omits the checksum here, we
+	 * add an own calculated one. This is currently an ugly
+	 * solution because the monitor needs a crc here.
+	 */
+	if (local->hw.flags & IEEE802154_HW_RX_OMIT_CKSUM) {
+		crc = crc_ccitt(0, skb->data, skb->len);
+		put_unaligned_le16(crc, skb_put(skb, 2));
+	}
+
+	rcu_read_lock();
+
+	ieee802154_monitors_rx(local, skb);
+
+	/* Check if transceiver doesn't validate the checksum.
+	 * If not we validate the checksum here.
+	 */
+	if (local->hw.flags & IEEE802154_HW_RX_DROP_BAD_CKSUM) {
+		crc = crc_ccitt(0, skb->data, skb->len);
+		if (crc) {
+			rcu_read_unlock();
+			kfree_skb(skb);
+			return;
+		}
+	}
+	/* remove crc */
+	skb_trim(skb, skb->len - 2);
+
+	__ieee802154_rx_handle_packet(local, skb);
+
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL(ieee802154_rx);
+
+void
+ieee802154_rx_irqsafe(struct ieee802154_hw *hw, struct sk_buff *skb, u8 lqi)
+{
+	struct ieee802154_local *local = hw_to_local(hw);
+
+	mac_cb(skb)->lqi = lqi;
+	skb->pkt_type = IEEE802154_RX_MSG;
+	skb_queue_tail(&local->skb_queue, skb);
+	tasklet_schedule(&local->tasklet);
 }
 EXPORT_SYMBOL(ieee802154_rx_irqsafe);
diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c
index fdf4c0e67259..c62e95695c78 100644
--- a/net/mac802154/tx.c
+++ b/net/mac802154/tx.c
@@ -10,10 +10,6 @@
  * 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.
- *
  * Written by:
  * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
  * Sergey Lapin <slapin@ossfans.org>
@@ -24,106 +20,98 @@
 #include <linux/netdevice.h>
 #include <linux/if_arp.h>
 #include <linux/crc-ccitt.h>
+#include <asm/unaligned.h>
 
+#include <net/rtnetlink.h>
 #include <net/ieee802154_netdev.h>
 #include <net/mac802154.h>
-#include <net/wpan-phy.h>
+#include <net/cfg802154.h>
 
-#include "mac802154.h"
+#include "ieee802154_i.h"
+#include "driver-ops.h"
 
 /* IEEE 802.15.4 transceivers can sleep during the xmit session, so process
  * packets through the workqueue.
  */
-struct xmit_work {
+struct ieee802154_xmit_cb {
 	struct sk_buff *skb;
 	struct work_struct work;
-	struct mac802154_priv *priv;
-	u8 chan;
-	u8 page;
+	struct ieee802154_local *local;
 };
 
-static void mac802154_xmit_worker(struct work_struct *work)
+static struct ieee802154_xmit_cb ieee802154_xmit_cb;
+
+static void ieee802154_xmit_worker(struct work_struct *work)
 {
-	struct xmit_work *xw = container_of(work, struct xmit_work, work);
-	struct mac802154_sub_if_data *sdata;
+	struct ieee802154_xmit_cb *cb =
+		container_of(work, struct ieee802154_xmit_cb, work);
+	struct ieee802154_local *local = cb->local;
+	struct sk_buff *skb = cb->skb;
+	struct net_device *dev = skb->dev;
 	int res;
 
-	mutex_lock(&xw->priv->phy->pib_lock);
-	if (xw->priv->phy->current_channel != xw->chan ||
-	    xw->priv->phy->current_page != xw->page) {
-		res = xw->priv->ops->set_channel(&xw->priv->hw,
-						  xw->page,
-						  xw->chan);
-		if (res) {
-			pr_debug("set_channel failed\n");
-			goto out;
-		}
+	rtnl_lock();
 
-		xw->priv->phy->current_channel = xw->chan;
-		xw->priv->phy->current_page = xw->page;
-	}
+	/* check if ifdown occurred while schedule */
+	if (!netif_running(dev))
+		goto err_tx;
 
-	res = xw->priv->ops->xmit(&xw->priv->hw, xw->skb);
+	res = drv_xmit_sync(local, skb);
 	if (res)
-		pr_debug("transmission failed\n");
+		goto err_tx;
 
-out:
-	mutex_unlock(&xw->priv->phy->pib_lock);
+	ieee802154_xmit_complete(&local->hw, skb, false);
 
-	/* Restart the netif queue on each sub_if_data object. */
-	rcu_read_lock();
-	list_for_each_entry_rcu(sdata, &xw->priv->slaves, list)
-		netif_wake_queue(sdata->dev);
-	rcu_read_unlock();
+	dev->stats.tx_packets++;
+	dev->stats.tx_bytes += skb->len;
 
-	dev_kfree_skb(xw->skb);
+	rtnl_unlock();
 
-	kfree(xw);
+	return;
+
+err_tx:
+	/* Restart the netif queue on each sub_if_data object. */
+	ieee802154_wake_queue(&local->hw);
+	rtnl_unlock();
+	kfree_skb(skb);
+	netdev_dbg(dev, "transmission failed\n");
 }
 
-netdev_tx_t mac802154_tx(struct mac802154_priv *priv, struct sk_buff *skb,
-			 u8 page, u8 chan)
+static netdev_tx_t
+ieee802154_tx(struct ieee802154_local *local, struct sk_buff *skb)
 {
-	struct xmit_work *work;
-	struct mac802154_sub_if_data *sdata;
-
-	if (!(priv->phy->channels_supported[page] & (1 << chan))) {
-		WARN_ON(1);
-		goto err_tx;
-	}
-
-	mac802154_monitors_rx(mac802154_to_priv(&priv->hw), skb);
+	struct net_device *dev = skb->dev;
+	int ret;
 
-	if (!(priv->hw.flags & IEEE802154_HW_OMIT_CKSUM)) {
+	if (!(local->hw.flags & IEEE802154_HW_TX_OMIT_CKSUM)) {
 		u16 crc = crc_ccitt(0, skb->data, skb->len);
-		u8 *data = skb_put(skb, 2);
 
-		data[0] = crc & 0xff;
-		data[1] = crc >> 8;
+		put_unaligned_le16(crc, skb_put(skb, 2));
 	}
 
-	if (skb_cow_head(skb, priv->hw.extra_tx_headroom))
+	if (skb_cow_head(skb, local->hw.extra_tx_headroom))
 		goto err_tx;
 
-	work = kzalloc(sizeof(*work), GFP_ATOMIC);
-	if (!work) {
-		kfree_skb(skb);
-		return NETDEV_TX_BUSY;
-	}
-
 	/* Stop the netif queue on each sub_if_data object. */
-	rcu_read_lock();
-	list_for_each_entry_rcu(sdata, &priv->slaves, list)
-		netif_stop_queue(sdata->dev);
-	rcu_read_unlock();
+	ieee802154_stop_queue(&local->hw);
+
+	/* async is priority, otherwise sync is fallback */
+	if (local->ops->xmit_async) {
+		ret = drv_xmit_async(local, skb);
+		if (ret) {
+			ieee802154_wake_queue(&local->hw);
+			goto err_tx;
+		}
 
-	INIT_WORK(&work->work, mac802154_xmit_worker);
-	work->skb = skb;
-	work->priv = priv;
-	work->page = page;
-	work->chan = chan;
+		dev->stats.tx_packets++;
+		dev->stats.tx_bytes += skb->len;
+	} else {
+		INIT_WORK(&ieee802154_xmit_cb.work, ieee802154_xmit_worker);
+		ieee802154_xmit_cb.skb = skb;
+		ieee802154_xmit_cb.local = local;
 
-	queue_work(priv->dev_workqueue, &work->work);
+		queue_work(local->workqueue, &ieee802154_xmit_cb.work);
+	}
 
 	return NETDEV_TX_OK;
 
@@ -131,3 +119,31 @@ err_tx:
 	kfree_skb(skb);
 	return NETDEV_TX_OK;
 }
+
+netdev_tx_t
+ieee802154_monitor_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+
+	skb->skb_iif = dev->ifindex;
+
+	return ieee802154_tx(sdata->local, skb);
+}
+
+netdev_tx_t
+ieee802154_subif_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+	int rc;
+
+	rc = mac802154_llsec_encrypt(&sdata->sec, skb);
+	if (rc) {
+		netdev_warn(dev, "encryption failed: %i\n", rc);
+		kfree_skb(skb);
+		return NETDEV_TX_OK;
+	}
+
+	skb->skb_iif = dev->ifindex;
+
+	return ieee802154_tx(sdata->local, skb);
+}
diff --git a/net/mac802154/util.c b/net/mac802154/util.c
new file mode 100644
index 000000000000..150bf807e572
--- /dev/null
+++ b/net/mac802154/util.c
@@ -0,0 +1,95 @@
+/* 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.
+ *
+ * Authors:
+ * Alexander Aring <aar@pengutronix.de>
+ *
+ * Based on: net/mac80211/util.c
+ */
+
+#include "ieee802154_i.h"
+
+/* privid for wpan_phys to determine whether they belong to us or not */
+const void *const mac802154_wpan_phy_privid = &mac802154_wpan_phy_privid;
+
+void ieee802154_wake_queue(struct ieee802154_hw *hw)
+{
+	struct ieee802154_local *local = hw_to_local(hw);
+	struct ieee802154_sub_if_data *sdata;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(sdata, &local->interfaces, list) {
+		if (!sdata->dev)
+			continue;
+
+		netif_wake_queue(sdata->dev);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL(ieee802154_wake_queue);
+
+void ieee802154_stop_queue(struct ieee802154_hw *hw)
+{
+	struct ieee802154_local *local = hw_to_local(hw);
+	struct ieee802154_sub_if_data *sdata;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(sdata, &local->interfaces, list) {
+		if (!sdata->dev)
+			continue;
+
+		netif_stop_queue(sdata->dev);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL(ieee802154_stop_queue);
+
+enum hrtimer_restart ieee802154_xmit_ifs_timer(struct hrtimer *timer)
+{
+	struct ieee802154_local *local =
+		container_of(timer, struct ieee802154_local, ifs_timer);
+
+	ieee802154_wake_queue(&local->hw);
+
+	return HRTIMER_NORESTART;
+}
+
+void ieee802154_xmit_complete(struct ieee802154_hw *hw, struct sk_buff *skb,
+			      bool ifs_handling)
+{
+	if (ifs_handling) {
+		struct ieee802154_local *local = hw_to_local(hw);
+		u8 max_sifs_size;
+
+		/* If transceiver sets CRC on his own we need to use lifs
+		 * threshold len above 16 otherwise 18, because it's not
+		 * part of skb->len.
+		 */
+		if (hw->flags & IEEE802154_HW_TX_OMIT_CKSUM)
+			max_sifs_size = IEEE802154_MAX_SIFS_FRAME_SIZE -
+					IEEE802154_FCS_LEN;
+		else
+			max_sifs_size = IEEE802154_MAX_SIFS_FRAME_SIZE;
+
+		if (skb->len > max_sifs_size)
+			hrtimer_start(&local->ifs_timer,
+				      ktime_set(0, hw->phy->lifs_period * NSEC_PER_USEC),
+				      HRTIMER_MODE_REL);
+		else
+			hrtimer_start(&local->ifs_timer,
+				      ktime_set(0, hw->phy->sifs_period * NSEC_PER_USEC),
+				      HRTIMER_MODE_REL);
+
+		consume_skb(skb);
+	} else {
+		ieee802154_wake_queue(hw);
+		consume_skb(skb);
+	}
+}
+EXPORT_SYMBOL(ieee802154_xmit_complete);
diff --git a/net/mac802154/wpan.c b/net/mac802154/wpan.c
deleted file mode 100644
index 4ab86a57dca5..000000000000
--- a/net/mac802154/wpan.c
+++ /dev/null
@@ -1,599 +0,0 @@
-/*
- * Copyright 2007-2012 Siemens AG
- *
- * 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.
- *
- * Written by:
- * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
- * Sergey Lapin <slapin@ossfans.org>
- * Maxim Gorbachyov <maxim.gorbachev@siemens.com>
- * Alexander Smirnov <alex.bluesman.smirnov@gmail.com>
- */
-
-#include <linux/netdevice.h>
-#include <linux/module.h>
-#include <linux/if_arp.h>
-
-#include <net/rtnetlink.h>
-#include <linux/nl802154.h>
-#include <net/af_ieee802154.h>
-#include <net/mac802154.h>
-#include <net/ieee802154_netdev.h>
-#include <net/ieee802154.h>
-#include <net/wpan-phy.h>
-
-#include "mac802154.h"
-
-static int mac802154_wpan_update_llsec(struct net_device *dev)
-{
-	struct mac802154_sub_if_data *priv = netdev_priv(dev);
-	struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev);
-	int rc = 0;
-
-	if (ops->llsec) {
-		struct ieee802154_llsec_params params;
-		int changed = 0;
-
-		params.pan_id = priv->pan_id;
-		changed |= IEEE802154_LLSEC_PARAM_PAN_ID;
-
-		params.hwaddr = priv->extended_addr;
-		changed |= IEEE802154_LLSEC_PARAM_HWADDR;
-
-		rc = ops->llsec->set_params(dev, &params, changed);
-	}
-
-	return rc;
-}
-
-static int
-mac802154_wpan_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
-{
-	struct mac802154_sub_if_data *priv = netdev_priv(dev);
-	struct sockaddr_ieee802154 *sa =
-		(struct sockaddr_ieee802154 *)&ifr->ifr_addr;
-	int err = -ENOIOCTLCMD;
-
-	spin_lock_bh(&priv->mib_lock);
-
-	switch (cmd) {
-	case SIOCGIFADDR:
-	{
-		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 = pan_id;
-		sa->addr.short_addr = short_addr;
-
-		err = 0;
-		break;
-	}
-	case SIOCSIFADDR:
-		dev_warn(&dev->dev,
-			 "Using DEBUGing ioctl SIOCSIFADDR isn't recommended!\n");
-		if (sa->family != AF_IEEE802154 ||
-		    sa->addr.addr_type != IEEE802154_ADDR_SHORT ||
-		    sa->addr.pan_id == IEEE802154_PANID_BROADCAST ||
-		    sa->addr.short_addr == IEEE802154_ADDR_BROADCAST ||
-		    sa->addr.short_addr == IEEE802154_ADDR_UNDEF) {
-			err = -EINVAL;
-			break;
-		}
-
-		priv->pan_id = cpu_to_le16(sa->addr.pan_id);
-		priv->short_addr = cpu_to_le16(sa->addr.short_addr);
-
-		err = mac802154_wpan_update_llsec(dev);
-		break;
-	}
-
-	spin_unlock_bh(&priv->mib_lock);
-	return err;
-}
-
-static int mac802154_wpan_mac_addr(struct net_device *dev, void *p)
-{
-	struct sockaddr *addr = p;
-
-	if (netif_running(dev))
-		return -EBUSY;
-
-	/* FIXME: validate addr */
-	memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
-	mac802154_dev_set_ieee_addr(dev);
-	return mac802154_wpan_update_llsec(dev);
-}
-
-int mac802154_set_mac_params(struct net_device *dev,
-			     const struct ieee802154_mac_params *params)
-{
-	struct mac802154_sub_if_data *priv = netdev_priv(dev);
-
-	mutex_lock(&priv->hw->slaves_mtx);
-	priv->mac_params = *params;
-	mutex_unlock(&priv->hw->slaves_mtx);
-
-	return 0;
-}
-
-void mac802154_get_mac_params(struct net_device *dev,
-			      struct ieee802154_mac_params *params)
-{
-	struct mac802154_sub_if_data *priv = netdev_priv(dev);
-
-	mutex_lock(&priv->hw->slaves_mtx);
-	*params = priv->mac_params;
-	mutex_unlock(&priv->hw->slaves_mtx);
-}
-
-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;
-
-	rc = mac802154_slave_open(dev);
-	if (rc < 0)
-		return rc;
-
-	mutex_lock(&phy->pib_lock);
-
-	if (phy->set_txpower) {
-		rc = phy->set_txpower(phy, priv->mac_params.transmit_power);
-		if (rc < 0)
-			goto out;
-	}
-
-	if (phy->set_lbt) {
-		rc = phy->set_lbt(phy, priv->mac_params.lbt);
-		if (rc < 0)
-			goto out;
-	}
-
-	if (phy->set_cca_mode) {
-		rc = phy->set_cca_mode(phy, priv->mac_params.cca_mode);
-		if (rc < 0)
-			goto out;
-	}
-
-	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 (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;
-	}
-
-	if (phy->set_frame_retries) {
-		rc = phy->set_frame_retries(phy,
-					    priv->mac_params.frame_retries);
-		if (rc < 0)
-			goto out;
-	}
-
-	mutex_unlock(&phy->pib_lock);
-	return 0;
-
-out:
-	mutex_unlock(&phy->pib_lock);
-	return rc;
-}
-
-static int mac802154_set_header_security(struct mac802154_sub_if_data *priv,
-					 struct ieee802154_hdr *hdr,
-					 const struct ieee802154_mac_cb *cb)
-{
-	struct ieee802154_llsec_params params;
-	u8 level;
-
-	mac802154_llsec_get_params(&priv->sec, &params);
-
-	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;
-
-	level = cb->seclevel_override ? cb->seclevel : params.out_level;
-
-	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;
-
-	return 0;
-}
-
-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;
-
-	if (!daddr)
-		return -EINVAL;
-
-	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);
-
-	if (mac802154_set_header_security(priv, &hdr, cb) < 0)
-		return -EINVAL;
-
-	if (!saddr) {
-		spin_lock_bh(&priv->mib_lock);
-
-		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;
-		}
-
-		hdr.source.pan_id = priv->pan_id;
-
-		spin_unlock_bh(&priv->mib_lock);
-	} else {
-		hdr.source = *(const struct ieee802154_addr *)saddr;
-	}
-
-	hdr.dest = *(const struct ieee802154_addr *)daddr;
-
-	hlen = ieee802154_hdr_push(skb, &hdr);
-	if (hlen < 0)
-		return -EINVAL;
-
-	skb_reset_mac_header(skb);
-	skb->mac_len = hlen;
-
-	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
-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);
-
-	spin_lock_bh(&priv->mib_lock);
-	chan = priv->chan;
-	page = priv->page;
-	spin_unlock_bh(&priv->mib_lock);
-
-	if (chan == MAC802154_CHAN_NONE ||
-	    page >= WPAN_NUM_PAGES ||
-	    chan >= WPAN_NUM_CHANNELS) {
-		kfree_skb(skb);
-		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;
-
-	return mac802154_tx(priv->hw, skb, page, chan);
-}
-
-static struct header_ops mac802154_header_ops = {
-	.create		= mac802154_header_create,
-	.parse		= mac802154_header_parse,
-};
-
-static const struct net_device_ops mac802154_wpan_ops = {
-	.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;
-
-	dev->addr_len		= IEEE802154_ADDR_LEN;
-	memset(dev->broadcast, 0xff, IEEE802154_ADDR_LEN);
-
-	dev->hard_header_len	= MAC802154_FRAME_HARD_HEADER_LEN;
-	dev->header_ops		= &mac802154_header_ops;
-	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		= mac802154_wpan_free;
-	dev->netdev_ops		= &mac802154_wpan_ops;
-	dev->ml_priv		= &mac802154_mlme_wpan;
-
-	priv = netdev_priv(dev);
-	priv->type = IEEE802154_DEV_WPAN;
-
-	priv->chan = MAC802154_CHAN_NONE;
-	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);
-
-	/* 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)
-{
-	return netif_rx_ni(skb);
-}
-
-static int
-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);
-
-	span = sdata->pan_id;
-	sshort = sdata->short_addr;
-
-	switch (mac_cb(skb)->dest.mode) {
-	case 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
-			/* ACK comes with both addresses empty */
-			skb->pkt_type = PACKET_HOST;
-		break;
-	case IEEE802154_ADDR_LONG:
-		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)->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)->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)->dest.short_addr == sshort)
-			skb->pkt_type = PACKET_HOST;
-		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;
-		break;
-	default:
-		spin_unlock_bh(&sdata->mib_lock);
-		pr_debug("invalid dest mode\n");
-		kfree_skb(skb);
-		return NET_RX_DROP;
-	}
-
-	spin_unlock_bh(&sdata->mib_lock);
-
-	skb->dev = sdata->dev;
-
-	rc = mac802154_llsec_decrypt(&sdata->sec, skb);
-	if (rc) {
-		pr_debug("decryption failed: %i\n", rc);
-		goto fail;
-	}
-
-	sdata->dev->stats.rx_packets++;
-	sdata->dev->stats.rx_bytes += skb->len;
-
-	switch (mac_cb(skb)->type) {
-	case IEEE802154_FC_TYPE_DATA:
-		return mac802154_process_data(sdata->dev, skb);
-	default:
-		pr_warn("ieee802154: bad frame received (type = %d)\n",
-			mac_cb(skb)->type);
-		goto fail;
-	}
-
-fail:
-	kfree_skb(skb);
-	return NET_RX_DROP;
-}
-
-static void mac802154_print_addr(const char *name,
-				 const struct ieee802154_addr *addr)
-{
-	if (addr->mode == IEEE802154_ADDR_NONE)
-		pr_debug("%s not present\n", name);
-
-	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);
-
-		pr_debug("%s is hardware: %8phC\n", name, &hw);
-	}
-}
-
-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);
-
-	hlen = ieee802154_hdr_pull(skb, hdr);
-	if (hlen < 0)
-		return -EINVAL;
-
-	skb->mac_len = hlen;
-
-	pr_debug("fc: %04x dsn: %02x\n", le16_to_cpup((__le16 *)&hdr->fc),
-		 hdr->seq);
-
-	cb->type = hdr->fc.type;
-	cb->ackreq = hdr->fc.ack_request;
-	cb->secen = hdr->fc.security_enabled;
-
-	mac802154_print_addr("destination", &hdr->dest);
-	mac802154_print_addr("source", &hdr->source);
-
-	cb->source = hdr->source;
-	cb->dest = hdr->dest;
-
-	if (hdr->fc.security_enabled) {
-		u64 key;
-
-		pr_debug("seclevel %i\n", hdr->sec.level);
-
-		switch (hdr->sec.key_id_mode) {
-		case IEEE802154_SCF_KEY_IMPLICIT:
-			pr_debug("implicit key\n");
-			break;
-
-		case IEEE802154_SCF_KEY_INDEX:
-			pr_debug("key %02x\n", hdr->sec.key_id);
-			break;
-
-		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;
-
-		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;
-}
-
-void mac802154_wpans_rx(struct mac802154_priv *priv, struct sk_buff *skb)
-{
-	int ret;
-	struct mac802154_sub_if_data *sdata;
-	struct ieee802154_hdr hdr;
-
-	ret = mac802154_parse_frame_start(skb, &hdr);
-	if (ret) {
-		pr_debug("got invalid frame\n");
-		kfree_skb(skb);
-		return;
-	}
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(sdata, &priv->slaves, list) {
-		if (sdata->type != IEEE802154_DEV_WPAN ||
-		    !netif_running(sdata->dev))
-			continue;
-
-		mac802154_subif_frame(sdata, skb, &hdr);
-		skb = NULL;
-		break;
-	}
-	rcu_read_unlock();
-
-	if (skb)
-		kfree_skb(skb);
-}
diff --git a/net/mpls/Kconfig b/net/mpls/Kconfig
index 37421db88965..17bde799c854 100644
--- a/net/mpls/Kconfig
+++ b/net/mpls/Kconfig
@@ -1,9 +1,30 @@
 #
 # MPLS configuration
 #
+
+menuconfig MPLS
+	bool "MultiProtocol Label Switching"
+	default n
+	---help---
+	  MultiProtocol Label Switching routes packets through logical
+	  circuits.  Originally conceived as a way of routing packets at
+	  hardware speeds (before hardware was capable of routing ipv4 packets),
+	  MPLS remains a simple way of making tunnels.
+
+	  If you have not heard of MPLS you probably want to say N here.
+
+if MPLS
+
 config NET_MPLS_GSO
 	tristate "MPLS: GSO support"
 	help
 	 This is helper module to allow segmentation of non-MPLS GSO packets
 	 that have had MPLS stack entries pushed onto them and thus
 	 become MPLS GSO packets.
+
+config MPLS_ROUTING
+	tristate "MPLS: routing support"
+	help
+	 Add support for forwarding of mpls packets.
+
+endif # MPLS
diff --git a/net/mpls/Makefile b/net/mpls/Makefile
index 6dec088c2d0f..65bbe68c72e6 100644
--- a/net/mpls/Makefile
+++ b/net/mpls/Makefile
@@ -2,3 +2,6 @@
 # Makefile for MPLS.
 #
 obj-$(CONFIG_NET_MPLS_GSO) += mpls_gso.o
+obj-$(CONFIG_MPLS_ROUTING) += mpls_router.o
+
+mpls_router-y := af_mpls.o
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
new file mode 100644
index 000000000000..1f93a5978f2a
--- /dev/null
+++ b/net/mpls/af_mpls.c
@@ -0,0 +1,1153 @@
+#include <linux/types.h>
+#include <linux/skbuff.h>
+#include <linux/socket.h>
+#include <linux/sysctl.h>
+#include <linux/net.h>
+#include <linux/module.h>
+#include <linux/if_arp.h>
+#include <linux/ipv6.h>
+#include <linux/mpls.h>
+#include <linux/vmalloc.h>
+#include <net/ip.h>
+#include <net/dst.h>
+#include <net/sock.h>
+#include <net/arp.h>
+#include <net/ip_fib.h>
+#include <net/netevent.h>
+#include <net/netns/generic.h>
+#include "internal.h"
+
+#define LABEL_NOT_SPECIFIED (1<<20)
+#define MAX_NEW_LABELS 2
+
+/* This maximum ha length copied from the definition of struct neighbour */
+#define MAX_VIA_ALEN (ALIGN(MAX_ADDR_LEN, sizeof(unsigned long)))
+
+struct mpls_route { /* next hop label forwarding entry */
+	struct net_device __rcu *rt_dev;
+	struct rcu_head		rt_rcu;
+	u32			rt_label[MAX_NEW_LABELS];
+	u8			rt_protocol; /* routing protocol that set this entry */
+	u8			rt_labels;
+	u8			rt_via_alen;
+	u8			rt_via_table;
+	u8			rt_via[0];
+};
+
+static int zero = 0;
+static int label_limit = (1 << 20) - 1;
+
+static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt,
+		       struct nlmsghdr *nlh, struct net *net, u32 portid,
+		       unsigned int nlm_flags);
+
+static struct mpls_route *mpls_route_input_rcu(struct net *net, unsigned index)
+{
+	struct mpls_route *rt = NULL;
+
+	if (index < net->mpls.platform_labels) {
+		struct mpls_route __rcu **platform_label =
+			rcu_dereference(net->mpls.platform_label);
+		rt = rcu_dereference(platform_label[index]);
+	}
+	return rt;
+}
+
+static inline struct mpls_dev *mpls_dev_get(const struct net_device *dev)
+{
+	return rcu_dereference_rtnl(dev->mpls_ptr);
+}
+
+static bool mpls_output_possible(const struct net_device *dev)
+{
+	return dev && (dev->flags & IFF_UP) && netif_carrier_ok(dev);
+}
+
+static unsigned int mpls_rt_header_size(const struct mpls_route *rt)
+{
+	/* The size of the layer 2.5 labels to be added for this route */
+	return rt->rt_labels * sizeof(struct mpls_shim_hdr);
+}
+
+static unsigned int mpls_dev_mtu(const struct net_device *dev)
+{
+	/* The amount of data the layer 2 frame can hold */
+	return dev->mtu;
+}
+
+static bool mpls_pkt_too_big(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 bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb,
+			struct mpls_entry_decoded dec)
+{
+	/* RFC4385 and RFC5586 encode other packets in mpls such that
+	 * they don't conflict with the ip version number, making
+	 * decoding by examining the ip version correct in everything
+	 * except for the strangest cases.
+	 *
+	 * The strange cases if we choose to support them will require
+	 * manual configuration.
+	 */
+	struct iphdr *hdr4;
+	bool success = true;
+
+	/* The IPv4 code below accesses through the IPv4 header
+	 * checksum, which is 12 bytes into the packet.
+	 * The IPv6 code below accesses through the IPv6 hop limit
+	 * which is 8 bytes into the packet.
+	 *
+	 * For all supported cases there should always be at least 12
+	 * bytes of packet data present.  The IPv4 header is 20 bytes
+	 * without options and the IPv6 header is always 40 bytes
+	 * long.
+	 */
+	if (!pskb_may_pull(skb, 12))
+		return false;
+
+	/* Use ip_hdr to find the ip protocol version */
+	hdr4 = ip_hdr(skb);
+	if (hdr4->version == 4) {
+		skb->protocol = htons(ETH_P_IP);
+		csum_replace2(&hdr4->check,
+			      htons(hdr4->ttl << 8),
+			      htons(dec.ttl << 8));
+		hdr4->ttl = dec.ttl;
+	}
+	else if (hdr4->version == 6) {
+		struct ipv6hdr *hdr6 = ipv6_hdr(skb);
+		skb->protocol = htons(ETH_P_IPV6);
+		hdr6->hop_limit = dec.ttl;
+	}
+	else
+		/* version 0 and version 1 are used by pseudo wires */
+		success = false;
+	return success;
+}
+
+static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
+			struct packet_type *pt, struct net_device *orig_dev)
+{
+	struct net *net = dev_net(dev);
+	struct mpls_shim_hdr *hdr;
+	struct mpls_route *rt;
+	struct mpls_entry_decoded dec;
+	struct net_device *out_dev;
+	struct mpls_dev *mdev;
+	unsigned int hh_len;
+	unsigned int new_header_size;
+	unsigned int mtu;
+	int err;
+
+	/* Careful this entire function runs inside of an rcu critical section */
+
+	mdev = mpls_dev_get(dev);
+	if (!mdev || !mdev->input_enabled)
+		goto drop;
+
+	if (skb->pkt_type != PACKET_HOST)
+		goto drop;
+
+	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)
+		goto drop;
+
+	if (!pskb_may_pull(skb, sizeof(*hdr)))
+		goto drop;
+
+	/* Read and decode the label */
+	hdr = mpls_hdr(skb);
+	dec = mpls_entry_decode(hdr);
+
+	/* Pop the label */
+	skb_pull(skb, sizeof(*hdr));
+	skb_reset_network_header(skb);
+
+	skb_orphan(skb);
+
+	rt = mpls_route_input_rcu(net, dec.label);
+	if (!rt)
+		goto drop;
+
+	/* Find the output device */
+	out_dev = rcu_dereference(rt->rt_dev);
+	if (!mpls_output_possible(out_dev))
+		goto drop;
+
+	if (skb_warn_if_lro(skb))
+		goto drop;
+
+	skb_forward_csum(skb);
+
+	/* Verify ttl is valid */
+	if (dec.ttl <= 1)
+		goto drop;
+	dec.ttl -= 1;
+
+	/* Verify the destination can hold the packet */
+	new_header_size = mpls_rt_header_size(rt);
+	mtu = mpls_dev_mtu(out_dev);
+	if (mpls_pkt_too_big(skb, mtu - new_header_size))
+		goto drop;
+
+	hh_len = LL_RESERVED_SPACE(out_dev);
+	if (!out_dev->header_ops)
+		hh_len = 0;
+
+	/* Ensure there is enough space for the headers in the skb */
+	if (skb_cow(skb, hh_len + new_header_size))
+		goto drop;
+
+	skb->dev = out_dev;
+	skb->protocol = htons(ETH_P_MPLS_UC);
+
+	if (unlikely(!new_header_size && dec.bos)) {
+		/* Penultimate hop popping */
+		if (!mpls_egress(rt, skb, dec))
+			goto drop;
+	} else {
+		bool bos;
+		int i;
+		skb_push(skb, new_header_size);
+		skb_reset_network_header(skb);
+		/* Push the new labels */
+		hdr = mpls_hdr(skb);
+		bos = dec.bos;
+		for (i = rt->rt_labels - 1; i >= 0; i--) {
+			hdr[i] = mpls_entry_encode(rt->rt_label[i], dec.ttl, 0, bos);
+			bos = false;
+		}
+	}
+
+	err = neigh_xmit(rt->rt_via_table, out_dev, rt->rt_via, skb);
+	if (err)
+		net_dbg_ratelimited("%s: packet transmission failed: %d\n",
+				    __func__, err);
+	return 0;
+
+drop:
+	kfree_skb(skb);
+	return NET_RX_DROP;
+}
+
+static struct packet_type mpls_packet_type __read_mostly = {
+	.type = cpu_to_be16(ETH_P_MPLS_UC),
+	.func = mpls_forward,
+};
+
+static const struct nla_policy rtm_mpls_policy[RTA_MAX+1] = {
+	[RTA_DST]		= { .type = NLA_U32 },
+	[RTA_OIF]		= { .type = NLA_U32 },
+};
+
+struct mpls_route_config {
+	u32		rc_protocol;
+	u32		rc_ifindex;
+	u16		rc_via_table;
+	u16		rc_via_alen;
+	u8		rc_via[MAX_VIA_ALEN];
+	u32		rc_label;
+	u32		rc_output_labels;
+	u32		rc_output_label[MAX_NEW_LABELS];
+	u32		rc_nlflags;
+	struct nl_info	rc_nlinfo;
+};
+
+static struct mpls_route *mpls_rt_alloc(size_t alen)
+{
+	struct mpls_route *rt;
+
+	rt = kzalloc(sizeof(*rt) + alen, GFP_KERNEL);
+	if (rt)
+		rt->rt_via_alen = alen;
+	return rt;
+}
+
+static void mpls_rt_free(struct mpls_route *rt)
+{
+	if (rt)
+		kfree_rcu(rt, rt_rcu);
+}
+
+static void mpls_notify_route(struct net *net, unsigned index,
+			      struct mpls_route *old, struct mpls_route *new,
+			      const struct nl_info *info)
+{
+	struct nlmsghdr *nlh = info ? info->nlh : NULL;
+	unsigned portid = info ? info->portid : 0;
+	int event = new ? RTM_NEWROUTE : RTM_DELROUTE;
+	struct mpls_route *rt = new ? new : old;
+	unsigned nlm_flags = (old && new) ? NLM_F_REPLACE : 0;
+	/* Ignore reserved labels for now */
+	if (rt && (index >= 16))
+		rtmsg_lfib(event, index, rt, nlh, net, portid, nlm_flags);
+}
+
+static void mpls_route_update(struct net *net, unsigned index,
+			      struct net_device *dev, struct mpls_route *new,
+			      const struct nl_info *info)
+{
+	struct mpls_route __rcu **platform_label;
+	struct mpls_route *rt, *old = NULL;
+
+	ASSERT_RTNL();
+
+	platform_label = rtnl_dereference(net->mpls.platform_label);
+	rt = rtnl_dereference(platform_label[index]);
+	if (!dev || (rt && (rtnl_dereference(rt->rt_dev) == dev))) {
+		rcu_assign_pointer(platform_label[index], new);
+		old = rt;
+	}
+
+	mpls_notify_route(net, index, old, new, info);
+
+	/* If we removed a route free it now */
+	mpls_rt_free(old);
+}
+
+static unsigned find_free_label(struct net *net)
+{
+	struct mpls_route __rcu **platform_label;
+	size_t platform_labels;
+	unsigned index;
+
+	platform_label = rtnl_dereference(net->mpls.platform_label);
+	platform_labels = net->mpls.platform_labels;
+	for (index = 16; index < platform_labels; index++) {
+		if (!rtnl_dereference(platform_label[index]))
+			return index;
+	}
+	return LABEL_NOT_SPECIFIED;
+}
+
+static int mpls_route_add(struct mpls_route_config *cfg)
+{
+	struct mpls_route __rcu **platform_label;
+	struct net *net = cfg->rc_nlinfo.nl_net;
+	struct net_device *dev = NULL;
+	struct mpls_route *rt, *old;
+	unsigned index;
+	int i;
+	int err = -EINVAL;
+
+	index = cfg->rc_label;
+
+	/* If a label was not specified during insert pick one */
+	if ((index == LABEL_NOT_SPECIFIED) &&
+	    (cfg->rc_nlflags & NLM_F_CREATE)) {
+		index = find_free_label(net);
+	}
+
+	/* The first 16 labels are reserved, and may not be set */
+	if (index < 16)
+		goto errout;
+
+	/* The full 20 bit range may not be supported. */
+	if (index >= net->mpls.platform_labels)
+		goto errout;
+
+	/* Ensure only a supported number of labels are present */
+	if (cfg->rc_output_labels > MAX_NEW_LABELS)
+		goto errout;
+
+	err = -ENODEV;
+	dev = dev_get_by_index(net, cfg->rc_ifindex);
+	if (!dev)
+		goto errout;
+
+	/* Ensure this is a supported device */
+	err = -EINVAL;
+	if (!mpls_dev_get(dev))
+		goto errout;
+
+	err = -EINVAL;
+	if ((cfg->rc_via_table == NEIGH_LINK_TABLE) &&
+	    (dev->addr_len != cfg->rc_via_alen))
+		goto errout;
+
+	/* Append makes no sense with mpls */
+	err = -EOPNOTSUPP;
+	if (cfg->rc_nlflags & NLM_F_APPEND)
+		goto errout;
+
+	err = -EEXIST;
+	platform_label = rtnl_dereference(net->mpls.platform_label);
+	old = rtnl_dereference(platform_label[index]);
+	if ((cfg->rc_nlflags & NLM_F_EXCL) && old)
+		goto errout;
+
+	err = -EEXIST;
+	if (!(cfg->rc_nlflags & NLM_F_REPLACE) && old)
+		goto errout;
+
+	err = -ENOENT;
+	if (!(cfg->rc_nlflags & NLM_F_CREATE) && !old)
+		goto errout;
+
+	err = -ENOMEM;
+	rt = mpls_rt_alloc(cfg->rc_via_alen);
+	if (!rt)
+		goto errout;
+
+	rt->rt_labels = cfg->rc_output_labels;
+	for (i = 0; i < rt->rt_labels; i++)
+		rt->rt_label[i] = cfg->rc_output_label[i];
+	rt->rt_protocol = cfg->rc_protocol;
+	RCU_INIT_POINTER(rt->rt_dev, dev);
+	rt->rt_via_table = cfg->rc_via_table;
+	memcpy(rt->rt_via, cfg->rc_via, cfg->rc_via_alen);
+
+	mpls_route_update(net, index, NULL, rt, &cfg->rc_nlinfo);
+
+	dev_put(dev);
+	return 0;
+
+errout:
+	if (dev)
+		dev_put(dev);
+	return err;
+}
+
+static int mpls_route_del(struct mpls_route_config *cfg)
+{
+	struct net *net = cfg->rc_nlinfo.nl_net;
+	unsigned index;
+	int err = -EINVAL;
+
+	index = cfg->rc_label;
+
+	/* The first 16 labels are reserved, and may not be removed */
+	if (index < 16)
+		goto errout;
+
+	/* The full 20 bit range may not be supported */
+	if (index >= net->mpls.platform_labels)
+		goto errout;
+
+	mpls_route_update(net, index, NULL, NULL, &cfg->rc_nlinfo);
+
+	err = 0;
+errout:
+	return err;
+}
+
+#define MPLS_PERDEV_SYSCTL_OFFSET(field)	\
+	(&((struct mpls_dev *)0)->field)
+
+static const struct ctl_table mpls_dev_table[] = {
+	{
+		.procname	= "input",
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+		.data		= MPLS_PERDEV_SYSCTL_OFFSET(input_enabled),
+	},
+	{ }
+};
+
+static int mpls_dev_sysctl_register(struct net_device *dev,
+				    struct mpls_dev *mdev)
+{
+	char path[sizeof("net/mpls/conf/") + IFNAMSIZ];
+	struct ctl_table *table;
+	int i;
+
+	table = kmemdup(&mpls_dev_table, sizeof(mpls_dev_table), GFP_KERNEL);
+	if (!table)
+		goto out;
+
+	/* Table data contains only offsets relative to the base of
+	 * the mdev at this point, so make them absolute.
+	 */
+	for (i = 0; i < ARRAY_SIZE(mpls_dev_table); i++)
+		table[i].data = (char *)mdev + (uintptr_t)table[i].data;
+
+	snprintf(path, sizeof(path), "net/mpls/conf/%s", dev->name);
+
+	mdev->sysctl = register_net_sysctl(dev_net(dev), path, table);
+	if (!mdev->sysctl)
+		goto free;
+
+	return 0;
+
+free:
+	kfree(table);
+out:
+	return -ENOBUFS;
+}
+
+static void mpls_dev_sysctl_unregister(struct mpls_dev *mdev)
+{
+	struct ctl_table *table;
+
+	table = mdev->sysctl->ctl_table_arg;
+	unregister_net_sysctl_table(mdev->sysctl);
+	kfree(table);
+}
+
+static struct mpls_dev *mpls_add_dev(struct net_device *dev)
+{
+	struct mpls_dev *mdev;
+	int err = -ENOMEM;
+
+	ASSERT_RTNL();
+
+	mdev = kzalloc(sizeof(*mdev), GFP_KERNEL);
+	if (!mdev)
+		return ERR_PTR(err);
+
+	err = mpls_dev_sysctl_register(dev, mdev);
+	if (err)
+		goto free;
+
+	rcu_assign_pointer(dev->mpls_ptr, mdev);
+
+	return mdev;
+
+free:
+	kfree(mdev);
+	return ERR_PTR(err);
+}
+
+static void mpls_ifdown(struct net_device *dev)
+{
+	struct mpls_route __rcu **platform_label;
+	struct net *net = dev_net(dev);
+	struct mpls_dev *mdev;
+	unsigned index;
+
+	platform_label = rtnl_dereference(net->mpls.platform_label);
+	for (index = 0; index < net->mpls.platform_labels; index++) {
+		struct mpls_route *rt = rtnl_dereference(platform_label[index]);
+		if (!rt)
+			continue;
+		if (rtnl_dereference(rt->rt_dev) != dev)
+			continue;
+		rt->rt_dev = NULL;
+	}
+
+	mdev = mpls_dev_get(dev);
+	if (!mdev)
+		return;
+
+	mpls_dev_sysctl_unregister(mdev);
+
+	RCU_INIT_POINTER(dev->mpls_ptr, NULL);
+
+	kfree_rcu(mdev, rcu);
+}
+
+static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
+			   void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct mpls_dev *mdev;
+
+	switch(event) {
+	case NETDEV_REGISTER:
+		/* For now just support ethernet devices */
+		if ((dev->type == ARPHRD_ETHER) ||
+		    (dev->type == ARPHRD_LOOPBACK)) {
+			mdev = mpls_add_dev(dev);
+			if (IS_ERR(mdev))
+				return notifier_from_errno(PTR_ERR(mdev));
+		}
+		break;
+
+	case NETDEV_UNREGISTER:
+		mpls_ifdown(dev);
+		break;
+	case NETDEV_CHANGENAME:
+		mdev = mpls_dev_get(dev);
+		if (mdev) {
+			int err;
+
+			mpls_dev_sysctl_unregister(mdev);
+			err = mpls_dev_sysctl_register(dev, mdev);
+			if (err)
+				return notifier_from_errno(err);
+		}
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block mpls_dev_notifier = {
+	.notifier_call = mpls_dev_notify,
+};
+
+static int nla_put_via(struct sk_buff *skb,
+		       u8 table, const void *addr, int alen)
+{
+	static const int table_to_family[NEIGH_NR_TABLES + 1] = {
+		AF_INET, AF_INET6, AF_DECnet, AF_PACKET,
+	};
+	struct nlattr *nla;
+	struct rtvia *via;
+	int family = AF_UNSPEC;
+
+	nla = nla_reserve(skb, RTA_VIA, alen + 2);
+	if (!nla)
+		return -EMSGSIZE;
+
+	if (table <= NEIGH_NR_TABLES)
+		family = table_to_family[table];
+
+	via = nla_data(nla);
+	via->rtvia_family = family;
+	memcpy(via->rtvia_addr, addr, alen);
+	return 0;
+}
+
+int nla_put_labels(struct sk_buff *skb, int attrtype,
+		   u8 labels, const u32 label[])
+{
+	struct nlattr *nla;
+	struct mpls_shim_hdr *nla_label;
+	bool bos;
+	int i;
+	nla = nla_reserve(skb, attrtype, labels*4);
+	if (!nla)
+		return -EMSGSIZE;
+
+	nla_label = nla_data(nla);
+	bos = true;
+	for (i = labels - 1; i >= 0; i--) {
+		nla_label[i] = mpls_entry_encode(label[i], 0, 0, bos);
+		bos = false;
+	}
+
+	return 0;
+}
+
+int nla_get_labels(const struct nlattr *nla,
+		   u32 max_labels, u32 *labels, u32 label[])
+{
+	unsigned len = nla_len(nla);
+	unsigned nla_labels;
+	struct mpls_shim_hdr *nla_label;
+	bool bos;
+	int i;
+
+	/* len needs to be an even multiple of 4 (the label size) */
+	if (len & 3)
+		return -EINVAL;
+
+	/* Limit the number of new labels allowed */
+	nla_labels = len/4;
+	if (nla_labels > max_labels)
+		return -EINVAL;
+
+	nla_label = nla_data(nla);
+	bos = true;
+	for (i = nla_labels - 1; i >= 0; i--, bos = false) {
+		struct mpls_entry_decoded dec;
+		dec = mpls_entry_decode(nla_label + i);
+
+		/* Ensure the bottom of stack flag is properly set
+		 * and ttl and tc are both clear.
+		 */
+		if ((dec.bos != bos) || dec.ttl || dec.tc)
+			return -EINVAL;
+
+		switch (dec.label) {
+		case MPLS_LABEL_IMPLNULL:
+			/* RFC3032: This is a label that an LSR may
+			 * assign and distribute, but which never
+			 * actually appears in the encapsulation.
+			 */
+			return -EINVAL;
+		}
+
+		label[i] = dec.label;
+	}
+	*labels = nla_labels;
+	return 0;
+}
+
+static int rtm_to_route_config(struct sk_buff *skb,  struct nlmsghdr *nlh,
+			       struct mpls_route_config *cfg)
+{
+	struct rtmsg *rtm;
+	struct nlattr *tb[RTA_MAX+1];
+	int index;
+	int err;
+
+	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_mpls_policy);
+	if (err < 0)
+		goto errout;
+
+	err = -EINVAL;
+	rtm = nlmsg_data(nlh);
+	memset(cfg, 0, sizeof(*cfg));
+
+	if (rtm->rtm_family != AF_MPLS)
+		goto errout;
+	if (rtm->rtm_dst_len != 20)
+		goto errout;
+	if (rtm->rtm_src_len != 0)
+		goto errout;
+	if (rtm->rtm_tos != 0)
+		goto errout;
+	if (rtm->rtm_table != RT_TABLE_MAIN)
+		goto errout;
+	/* Any value is acceptable for rtm_protocol */
+
+	/* As mpls uses destination specific addresses
+	 * (or source specific address in the case of multicast)
+	 * all addresses have universal scope.
+	 */
+	if (rtm->rtm_scope != RT_SCOPE_UNIVERSE)
+		goto errout;
+	if (rtm->rtm_type != RTN_UNICAST)
+		goto errout;
+	if (rtm->rtm_flags != 0)
+		goto errout;
+
+	cfg->rc_label		= LABEL_NOT_SPECIFIED;
+	cfg->rc_protocol	= rtm->rtm_protocol;
+	cfg->rc_nlflags		= nlh->nlmsg_flags;
+	cfg->rc_nlinfo.portid	= NETLINK_CB(skb).portid;
+	cfg->rc_nlinfo.nlh	= nlh;
+	cfg->rc_nlinfo.nl_net	= sock_net(skb->sk);
+
+	for (index = 0; index <= RTA_MAX; index++) {
+		struct nlattr *nla = tb[index];
+		if (!nla)
+			continue;
+
+		switch(index) {
+		case RTA_OIF:
+			cfg->rc_ifindex = nla_get_u32(nla);
+			break;
+		case RTA_NEWDST:
+			if (nla_get_labels(nla, MAX_NEW_LABELS,
+					   &cfg->rc_output_labels,
+					   cfg->rc_output_label))
+				goto errout;
+			break;
+		case RTA_DST:
+		{
+			u32 label_count;
+			if (nla_get_labels(nla, 1, &label_count,
+					   &cfg->rc_label))
+				goto errout;
+
+			/* The first 16 labels are reserved, and may not be set */
+			if (cfg->rc_label < 16)
+				goto errout;
+
+			break;
+		}
+		case RTA_VIA:
+		{
+			struct rtvia *via = nla_data(nla);
+			if (nla_len(nla) < offsetof(struct rtvia, rtvia_addr))
+				goto errout;
+			cfg->rc_via_alen   = nla_len(nla) -
+				offsetof(struct rtvia, rtvia_addr);
+			if (cfg->rc_via_alen > MAX_VIA_ALEN)
+				goto errout;
+
+			/* Validate the address family */
+			switch(via->rtvia_family) {
+			case AF_PACKET:
+				cfg->rc_via_table = NEIGH_LINK_TABLE;
+				break;
+			case AF_INET:
+				cfg->rc_via_table = NEIGH_ARP_TABLE;
+				if (cfg->rc_via_alen != 4)
+					goto errout;
+				break;
+			case AF_INET6:
+				cfg->rc_via_table = NEIGH_ND_TABLE;
+				if (cfg->rc_via_alen != 16)
+					goto errout;
+				break;
+			default:
+				/* Unsupported address family */
+				goto errout;
+			}
+
+			memcpy(cfg->rc_via, via->rtvia_addr, cfg->rc_via_alen);
+			break;
+		}
+		default:
+			/* Unsupported attribute */
+			goto errout;
+		}
+	}
+
+	err = 0;
+errout:
+	return err;
+}
+
+static int mpls_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
+{
+	struct mpls_route_config cfg;
+	int err;
+
+	err = rtm_to_route_config(skb, nlh, &cfg);
+	if (err < 0)
+		return err;
+
+	return mpls_route_del(&cfg);
+}
+
+
+static int mpls_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
+{
+	struct mpls_route_config cfg;
+	int err;
+
+	err = rtm_to_route_config(skb, nlh, &cfg);
+	if (err < 0)
+		return err;
+
+	return mpls_route_add(&cfg);
+}
+
+static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event,
+			   u32 label, struct mpls_route *rt, int flags)
+{
+	struct net_device *dev;
+	struct nlmsghdr *nlh;
+	struct rtmsg *rtm;
+
+	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*rtm), flags);
+	if (nlh == NULL)
+		return -EMSGSIZE;
+
+	rtm = nlmsg_data(nlh);
+	rtm->rtm_family = AF_MPLS;
+	rtm->rtm_dst_len = 20;
+	rtm->rtm_src_len = 0;
+	rtm->rtm_tos = 0;
+	rtm->rtm_table = RT_TABLE_MAIN;
+	rtm->rtm_protocol = rt->rt_protocol;
+	rtm->rtm_scope = RT_SCOPE_UNIVERSE;
+	rtm->rtm_type = RTN_UNICAST;
+	rtm->rtm_flags = 0;
+
+	if (rt->rt_labels &&
+	    nla_put_labels(skb, RTA_NEWDST, rt->rt_labels, rt->rt_label))
+		goto nla_put_failure;
+	if (nla_put_via(skb, rt->rt_via_table, rt->rt_via, rt->rt_via_alen))
+		goto nla_put_failure;
+	dev = rtnl_dereference(rt->rt_dev);
+	if (dev && nla_put_u32(skb, RTA_OIF, dev->ifindex))
+		goto nla_put_failure;
+	if (nla_put_labels(skb, RTA_DST, 1, &label))
+		goto nla_put_failure;
+
+	nlmsg_end(skb, nlh);
+	return 0;
+
+nla_put_failure:
+	nlmsg_cancel(skb, nlh);
+	return -EMSGSIZE;
+}
+
+static int mpls_dump_routes(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct net *net = sock_net(skb->sk);
+	struct mpls_route __rcu **platform_label;
+	size_t platform_labels;
+	unsigned int index;
+
+	ASSERT_RTNL();
+
+	index = cb->args[0];
+	if (index < 16)
+		index = 16;
+
+	platform_label = rtnl_dereference(net->mpls.platform_label);
+	platform_labels = net->mpls.platform_labels;
+	for (; index < platform_labels; index++) {
+		struct mpls_route *rt;
+		rt = rtnl_dereference(platform_label[index]);
+		if (!rt)
+			continue;
+
+		if (mpls_dump_route(skb, NETLINK_CB(cb->skb).portid,
+				    cb->nlh->nlmsg_seq, RTM_NEWROUTE,
+				    index, rt, NLM_F_MULTI) < 0)
+			break;
+	}
+	cb->args[0] = index;
+
+	return skb->len;
+}
+
+static inline size_t lfib_nlmsg_size(struct mpls_route *rt)
+{
+	size_t payload =
+		NLMSG_ALIGN(sizeof(struct rtmsg))
+		+ nla_total_size(2 + rt->rt_via_alen)	/* RTA_VIA */
+		+ nla_total_size(4);			/* RTA_DST */
+	if (rt->rt_labels)				/* RTA_NEWDST */
+		payload += nla_total_size(rt->rt_labels * 4);
+	if (rt->rt_dev)					/* RTA_OIF */
+		payload += nla_total_size(4);
+	return payload;
+}
+
+static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt,
+		       struct nlmsghdr *nlh, struct net *net, u32 portid,
+		       unsigned int nlm_flags)
+{
+	struct sk_buff *skb;
+	u32 seq = nlh ? nlh->nlmsg_seq : 0;
+	int err = -ENOBUFS;
+
+	skb = nlmsg_new(lfib_nlmsg_size(rt), GFP_KERNEL);
+	if (skb == NULL)
+		goto errout;
+
+	err = mpls_dump_route(skb, portid, seq, event, label, rt, nlm_flags);
+	if (err < 0) {
+		/* -EMSGSIZE implies BUG in lfib_nlmsg_size */
+		WARN_ON(err == -EMSGSIZE);
+		kfree_skb(skb);
+		goto errout;
+	}
+	rtnl_notify(skb, net, portid, RTNLGRP_MPLS_ROUTE, nlh, GFP_KERNEL);
+
+	return;
+errout:
+	if (err < 0)
+		rtnl_set_sk_err(net, RTNLGRP_MPLS_ROUTE, err);
+}
+
+static int resize_platform_label_table(struct net *net, size_t limit)
+{
+	size_t size = sizeof(struct mpls_route *) * limit;
+	size_t old_limit;
+	size_t cp_size;
+	struct mpls_route __rcu **labels = NULL, **old;
+	struct mpls_route *rt0 = NULL, *rt2 = NULL;
+	unsigned index;
+
+	if (size) {
+		labels = kzalloc(size, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY);
+		if (!labels)
+			labels = vzalloc(size);
+
+		if (!labels)
+			goto nolabels;
+	}
+
+	/* In case the predefined labels need to be populated */
+	if (limit > MPLS_LABEL_IPV4NULL) {
+		struct net_device *lo = net->loopback_dev;
+		rt0 = mpls_rt_alloc(lo->addr_len);
+		if (!rt0)
+			goto nort0;
+		RCU_INIT_POINTER(rt0->rt_dev, lo);
+		rt0->rt_protocol = RTPROT_KERNEL;
+		rt0->rt_via_table = NEIGH_LINK_TABLE;
+		memcpy(rt0->rt_via, lo->dev_addr, lo->addr_len);
+	}
+	if (limit > MPLS_LABEL_IPV6NULL) {
+		struct net_device *lo = net->loopback_dev;
+		rt2 = mpls_rt_alloc(lo->addr_len);
+		if (!rt2)
+			goto nort2;
+		RCU_INIT_POINTER(rt2->rt_dev, lo);
+		rt2->rt_protocol = RTPROT_KERNEL;
+		rt2->rt_via_table = NEIGH_LINK_TABLE;
+		memcpy(rt2->rt_via, lo->dev_addr, lo->addr_len);
+	}
+
+	rtnl_lock();
+	/* Remember the original table */
+	old = rtnl_dereference(net->mpls.platform_label);
+	old_limit = net->mpls.platform_labels;
+
+	/* Free any labels beyond the new table */
+	for (index = limit; index < old_limit; index++)
+		mpls_route_update(net, index, NULL, NULL, NULL);
+
+	/* Copy over the old labels */
+	cp_size = size;
+	if (old_limit < limit)
+		cp_size = old_limit * sizeof(struct mpls_route *);
+
+	memcpy(labels, old, cp_size);
+
+	/* If needed set the predefined labels */
+	if ((old_limit <= MPLS_LABEL_IPV6NULL) &&
+	    (limit > MPLS_LABEL_IPV6NULL)) {
+		RCU_INIT_POINTER(labels[MPLS_LABEL_IPV6NULL], rt2);
+		rt2 = NULL;
+	}
+
+	if ((old_limit <= MPLS_LABEL_IPV4NULL) &&
+	    (limit > MPLS_LABEL_IPV4NULL)) {
+		RCU_INIT_POINTER(labels[MPLS_LABEL_IPV4NULL], rt0);
+		rt0 = NULL;
+	}
+
+	/* Update the global pointers */
+	net->mpls.platform_labels = limit;
+	rcu_assign_pointer(net->mpls.platform_label, labels);
+
+	rtnl_unlock();
+
+	mpls_rt_free(rt2);
+	mpls_rt_free(rt0);
+
+	if (old) {
+		synchronize_rcu();
+		kvfree(old);
+	}
+	return 0;
+
+nort2:
+	mpls_rt_free(rt0);
+nort0:
+	kvfree(labels);
+nolabels:
+	return -ENOMEM;
+}
+
+static int mpls_platform_labels(struct ctl_table *table, int write,
+				void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct net *net = table->data;
+	int platform_labels = net->mpls.platform_labels;
+	int ret;
+	struct ctl_table tmp = {
+		.procname	= table->procname,
+		.data		= &platform_labels,
+		.maxlen		= sizeof(int),
+		.mode		= table->mode,
+		.extra1		= &zero,
+		.extra2		= &label_limit,
+	};
+
+	ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
+
+	if (write && ret == 0)
+		ret = resize_platform_label_table(net, platform_labels);
+
+	return ret;
+}
+
+static const struct ctl_table mpls_table[] = {
+	{
+		.procname	= "platform_labels",
+		.data		= NULL,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= mpls_platform_labels,
+	},
+	{ }
+};
+
+static int mpls_net_init(struct net *net)
+{
+	struct ctl_table *table;
+
+	net->mpls.platform_labels = 0;
+	net->mpls.platform_label = NULL;
+
+	table = kmemdup(mpls_table, sizeof(mpls_table), GFP_KERNEL);
+	if (table == NULL)
+		return -ENOMEM;
+
+	table[0].data = net;
+	net->mpls.ctl = register_net_sysctl(net, "net/mpls", table);
+	if (net->mpls.ctl == NULL)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void mpls_net_exit(struct net *net)
+{
+	struct mpls_route __rcu **platform_label;
+	size_t platform_labels;
+	struct ctl_table *table;
+	unsigned int index;
+
+	table = net->mpls.ctl->ctl_table_arg;
+	unregister_net_sysctl_table(net->mpls.ctl);
+	kfree(table);
+
+	/* An rcu grace period has passed since there was a device in
+	 * the network namespace (and thus the last in flight packet)
+	 * left this network namespace.  This is because
+	 * unregister_netdevice_many and netdev_run_todo has completed
+	 * for each network device that was in this network namespace.
+	 *
+	 * As such no additional rcu synchronization is necessary when
+	 * freeing the platform_label table.
+	 */
+	rtnl_lock();
+	platform_label = rtnl_dereference(net->mpls.platform_label);
+	platform_labels = net->mpls.platform_labels;
+	for (index = 0; index < platform_labels; index++) {
+		struct mpls_route *rt = rtnl_dereference(platform_label[index]);
+		RCU_INIT_POINTER(platform_label[index], NULL);
+		mpls_rt_free(rt);
+	}
+	rtnl_unlock();
+
+	kvfree(platform_label);
+}
+
+static struct pernet_operations mpls_net_ops = {
+	.init = mpls_net_init,
+	.exit = mpls_net_exit,
+};
+
+static int __init mpls_init(void)
+{
+	int err;
+
+	BUILD_BUG_ON(sizeof(struct mpls_shim_hdr) != 4);
+
+	err = register_pernet_subsys(&mpls_net_ops);
+	if (err)
+		goto out;
+
+	err = register_netdevice_notifier(&mpls_dev_notifier);
+	if (err)
+		goto out_unregister_pernet;
+
+	dev_add_pack(&mpls_packet_type);
+
+	rtnl_register(PF_MPLS, RTM_NEWROUTE, mpls_rtm_newroute, NULL, NULL);
+	rtnl_register(PF_MPLS, RTM_DELROUTE, mpls_rtm_delroute, NULL, NULL);
+	rtnl_register(PF_MPLS, RTM_GETROUTE, NULL, mpls_dump_routes, NULL);
+	err = 0;
+out:
+	return err;
+
+out_unregister_pernet:
+	unregister_pernet_subsys(&mpls_net_ops);
+	goto out;
+}
+module_init(mpls_init);
+
+static void __exit mpls_exit(void)
+{
+	rtnl_unregister_all(PF_MPLS);
+	dev_remove_pack(&mpls_packet_type);
+	unregister_netdevice_notifier(&mpls_dev_notifier);
+	unregister_pernet_subsys(&mpls_net_ops);
+}
+module_exit(mpls_exit);
+
+MODULE_DESCRIPTION("MultiProtocol Label Switching");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_NETPROTO(PF_MPLS);
diff --git a/net/mpls/internal.h b/net/mpls/internal.h
new file mode 100644
index 000000000000..8cabeb5a1cb9
--- /dev/null
+++ b/net/mpls/internal.h
@@ -0,0 +1,56 @@
+#ifndef MPLS_INTERNAL_H
+#define MPLS_INTERNAL_H
+
+struct mpls_shim_hdr {
+	__be32 label_stack_entry;
+};
+
+struct mpls_entry_decoded {
+	u32 label;
+	u8 ttl;
+	u8 tc;
+	u8 bos;
+};
+
+struct mpls_dev {
+	int			input_enabled;
+
+	struct ctl_table_header *sysctl;
+	struct rcu_head		rcu;
+};
+
+struct sk_buff;
+
+static inline struct mpls_shim_hdr *mpls_hdr(const struct sk_buff *skb)
+{
+	return (struct mpls_shim_hdr *)skb_network_header(skb);
+}
+
+static inline struct mpls_shim_hdr mpls_entry_encode(u32 label, unsigned ttl, unsigned tc, bool bos)
+{
+	struct mpls_shim_hdr result;
+	result.label_stack_entry =
+		cpu_to_be32((label << MPLS_LS_LABEL_SHIFT) |
+			    (tc << MPLS_LS_TC_SHIFT) |
+			    (bos ? (1 << MPLS_LS_S_SHIFT) : 0) |
+			    (ttl << MPLS_LS_TTL_SHIFT));
+	return result;
+}
+
+static inline struct mpls_entry_decoded mpls_entry_decode(struct mpls_shim_hdr *hdr)
+{
+	struct mpls_entry_decoded result;
+	unsigned entry = be32_to_cpu(hdr->label_stack_entry);
+
+	result.label = (entry & MPLS_LS_LABEL_MASK) >> MPLS_LS_LABEL_SHIFT;
+	result.ttl = (entry & MPLS_LS_TTL_MASK) >> MPLS_LS_TTL_SHIFT;
+	result.tc =  (entry & MPLS_LS_TC_MASK) >> MPLS_LS_TC_SHIFT;
+	result.bos = (entry & MPLS_LS_S_MASK) >> MPLS_LS_S_SHIFT;
+
+	return result;
+}
+
+int nla_put_labels(struct sk_buff *skb, int attrtype,  u8 labels, const u32 label[]);
+int nla_get_labels(const struct nlattr *nla, u32 max_labels, u32 *labels, u32 label[]);
+
+#endif /* MPLS_INTERNAL_H */
diff --git a/net/mpls/mpls_gso.c b/net/mpls/mpls_gso.c
index e3545f21a099..809df534a720 100644
--- a/net/mpls/mpls_gso.c
+++ b/net/mpls/mpls_gso.c
@@ -31,11 +31,7 @@ static struct sk_buff *mpls_gso_segment(struct sk_buff *skb,
 				  SKB_GSO_TCPV6 |
 				  SKB_GSO_UDP |
 				  SKB_GSO_DODGY |
-				  SKB_GSO_TCP_ECN |
-				  SKB_GSO_GRE |
-				  SKB_GSO_GRE_CSUM |
-				  SKB_GSO_IPIP |
-				  SKB_GSO_MPLS)))
+				  SKB_GSO_TCP_ECN)))
 		goto out;
 
 	/* Setup inner SKB. */
@@ -64,14 +60,14 @@ out:
 	return segs;
 }
 
-static struct packet_offload mpls_mc_offload = {
+static struct packet_offload mpls_mc_offload __read_mostly = {
 	.type = cpu_to_be16(ETH_P_MPLS_MC),
 	.callbacks = {
 		.gso_segment    =	mpls_gso_segment,
 	},
 };
 
-static struct packet_offload mpls_uc_offload = {
+static struct packet_offload mpls_uc_offload __read_mostly = {
 	.type = cpu_to_be16(ETH_P_MPLS_UC),
 	.callbacks = {
 		.gso_segment    =	mpls_gso_segment,
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index ae5096ab65eb..a0f3e6a3c7d1 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -411,6 +411,13 @@ config NF_NAT_TFTP
 	depends on NF_CONNTRACK && NF_NAT
 	default NF_NAT && NF_CONNTRACK_TFTP
 
+config NF_NAT_REDIRECT
+        tristate "IPv4/IPv6 redirect support"
+	depends on NF_NAT
+        help
+          This is the kernel functionality to redirect packets to local
+          machine through NAT.
+
 config NETFILTER_SYNPROXY
 	tristate
 
@@ -431,8 +438,10 @@ config NF_TABLES
 
 	  To compile it as a module, choose M here.
 
+if NF_TABLES
+
 config NF_TABLES_INET
-	depends on NF_TABLES && IPV6
+	depends on IPV6
 	select NF_TABLES_IPV4
 	select NF_TABLES_IPV6
 	tristate "Netfilter nf_tables mixed IPv4/IPv6 tables support"
@@ -440,21 +449,18 @@ config NF_TABLES_INET
 	  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
@@ -462,42 +468,36 @@ config NFT_CT
 	  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_MASQ
-	depends on NF_TABLES
 	depends on NF_CONNTRACK
 	depends on NF_NAT
 	tristate "Netfilter nf_tables masquerade support"
@@ -505,8 +505,15 @@ config NFT_MASQ
 	  This option adds the "masquerade" expression that you can use
 	  to perform NAT in the masquerade flavour.
 
+config NFT_REDIR
+	depends on NF_CONNTRACK
+	depends on NF_NAT
+	tristate "Netfilter nf_tables redirect support"
+	help
+	  This options adds the "redirect" expression that you can use
+	  to perform NAT in the redirect flavour.
+
 config NFT_NAT
-	depends on NF_TABLES
 	depends on NF_CONNTRACK
 	select NF_NAT
 	tristate "Netfilter nf_tables nat module"
@@ -515,8 +522,6 @@ config NFT_NAT
 	  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
@@ -524,7 +529,6 @@ config NFT_QUEUE
 	  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
@@ -538,7 +542,6 @@ config NFT_REJECT_INET
 	tristate
 
 config NFT_COMPAT
-	depends on NF_TABLES
 	depends on NETFILTER_XTABLES
 	tristate "Netfilter x_tables over nf_tables module"
 	help
@@ -546,6 +549,8 @@ config NFT_COMPAT
 	  x_tables match/target extensions over the nf_tables
 	  framework.
 
+endif # NF_TABLES
+
 config NETFILTER_XTABLES
 	tristate "Netfilter Xtables support (required for ip_tables)"
 	default m if NETFILTER_ADVANCED=n
@@ -835,6 +840,7 @@ config NETFILTER_XT_TARGET_RATEEST
 config NETFILTER_XT_TARGET_REDIRECT
 	tristate "REDIRECT target support"
 	depends on NF_NAT
+	select NF_NAT_REDIRECT
 	---help---
 	REDIRECT is a special case of NAT: all incoming connections are
 	mapped onto the incoming interface's address, causing the packets to
@@ -857,6 +863,7 @@ config NETFILTER_XT_TARGET_TPROXY
 	depends on NETFILTER_XTABLES
 	depends on NETFILTER_ADVANCED
 	depends on (IPV6 || IPV6=n)
+	depends on (IP6_NF_IPTABLES || IP6_NF_IPTABLES=n)
 	depends on IP_NF_MANGLE
 	select NF_DEFRAG_IPV4
 	select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES
@@ -934,7 +941,7 @@ comment "Xtables matches"
 
 config NETFILTER_XT_MATCH_ADDRTYPE
 	tristate '"addrtype" address type match support'
-	depends on NETFILTER_ADVANCED
+	default m if NETFILTER_ADVANCED=n
 	---help---
 	  This option allows you to match what routing thinks of an address,
 	  eg. UNICAST, LOCAL, BROADCAST, ...
@@ -1350,6 +1357,7 @@ config NETFILTER_XT_MATCH_SOCKET
 	depends on NETFILTER_ADVANCED
 	depends on !NF_CONNTRACK || NF_CONNTRACK
 	depends on (IPV6 || IPV6=n)
+	depends on (IP6_NF_IPTABLES || IP6_NF_IPTABLES=n)
 	select NF_DEFRAG_IPV4
 	select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES
 	help
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index a9571be3f791..a87d8b8ec730 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -51,6 +51,7 @@ nf_nat-y	:= nf_nat_core.o nf_nat_proto_unknown.o nf_nat_proto_common.o \
 obj-$(CONFIG_NF_LOG_COMMON) += nf_log_common.o
 
 obj-$(CONFIG_NF_NAT) += nf_nat.o
+obj-$(CONFIG_NF_NAT_REDIRECT) += nf_nat_redirect.o
 
 # NAT protocols (nf_nat)
 obj-$(CONFIG_NF_NAT_PROTO_DCCP) += nf_nat_proto_dccp.o
@@ -69,7 +70,7 @@ obj-$(CONFIG_NETFILTER_SYNPROXY) += nf_synproxy_core.o
 
 # nf_tables
 nf_tables-objs += nf_tables_core.o nf_tables_api.o
-nf_tables-objs += nft_immediate.o nft_cmp.o nft_lookup.o
+nf_tables-objs += nft_immediate.o nft_cmp.o nft_lookup.o nft_dynset.o
 nf_tables-objs += nft_bitwise.o nft_byteorder.o nft_payload.o
 
 obj-$(CONFIG_NF_TABLES)		+= nf_tables.o
@@ -88,6 +89,7 @@ obj-$(CONFIG_NFT_HASH)		+= nft_hash.o
 obj-$(CONFIG_NFT_COUNTER)	+= nft_counter.o
 obj-$(CONFIG_NFT_LOG)		+= nft_log.o
 obj-$(CONFIG_NFT_MASQ)		+= nft_masq.o
+obj-$(CONFIG_NFT_REDIR)		+= nft_redir.o
 
 # generic X tables 
 obj-$(CONFIG_NETFILTER_XTABLES) += x_tables.o xt_tcpudp.o
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 024a2e25c8a4..e6163017c42d 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -17,6 +17,7 @@
 #include <linux/interrupt.h>
 #include <linux/if.h>
 #include <linux/netdevice.h>
+#include <linux/netfilter_ipv6.h>
 #include <linux/inetdevice.h>
 #include <linux/proc_fs.h>
 #include <linux/mutex.h>
@@ -119,12 +120,8 @@ EXPORT_SYMBOL(nf_unregister_hooks);
 
 unsigned int nf_iterate(struct list_head *head,
 			struct sk_buff *skb,
-			unsigned int hook,
-			const struct net_device *indev,
-			const struct net_device *outdev,
-			struct nf_hook_ops **elemp,
-			int (*okfn)(struct sk_buff *),
-			int hook_thresh)
+			struct nf_hook_state *state,
+			struct nf_hook_ops **elemp)
 {
 	unsigned int verdict;
 
@@ -133,19 +130,19 @@ unsigned int nf_iterate(struct list_head *head,
 	 * function because of risk of continuing from deleted element.
 	 */
 	list_for_each_entry_continue_rcu((*elemp), head, list) {
-		if (hook_thresh > (*elemp)->priority)
+		if (state->thresh > (*elemp)->priority)
 			continue;
 
 		/* Optimization: we don't need to hold module
 		   reference here, since function can't sleep. --RR */
 repeat:
-		verdict = (*elemp)->hook(*elemp, skb, indev, outdev, okfn);
+		verdict = (*elemp)->hook(*elemp, skb, state);
 		if (verdict != NF_ACCEPT) {
 #ifdef CONFIG_NETFILTER_DEBUG
 			if (unlikely((verdict & NF_VERDICT_MASK)
 							> NF_MAX_VERDICT)) {
 				NFDEBUG("Evil return from %p(%u).\n",
-					(*elemp)->hook, hook);
+					(*elemp)->hook, state->hook);
 				continue;
 			}
 #endif
@@ -160,11 +157,7 @@ repeat:
 
 /* Returns 1 if okfn() needs to be executed by the caller,
  * -EPERM for NF_DROP, 0 otherwise. */
-int nf_hook_slow(u_int8_t pf, unsigned int hook, struct sk_buff *skb,
-		 struct net_device *indev,
-		 struct net_device *outdev,
-		 int (*okfn)(struct sk_buff *),
-		 int hook_thresh)
+int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state)
 {
 	struct nf_hook_ops *elem;
 	unsigned int verdict;
@@ -173,10 +166,11 @@ int nf_hook_slow(u_int8_t pf, unsigned int hook, struct sk_buff *skb,
 	/* We may already have this, but read-locks nest anyway */
 	rcu_read_lock();
 
-	elem = list_entry_rcu(&nf_hooks[pf][hook], struct nf_hook_ops, list);
+	elem = list_entry_rcu(&nf_hooks[state->pf][state->hook],
+			      struct nf_hook_ops, list);
 next_hook:
-	verdict = nf_iterate(&nf_hooks[pf][hook], skb, hook, indev,
-			     outdev, &elem, okfn, hook_thresh);
+	verdict = nf_iterate(&nf_hooks[state->pf][state->hook], skb, state,
+			     &elem);
 	if (verdict == NF_ACCEPT || verdict == NF_STOP) {
 		ret = 1;
 	} else if ((verdict & NF_VERDICT_MASK) == NF_DROP) {
@@ -185,8 +179,8 @@ next_hook:
 		if (ret == 0)
 			ret = -EPERM;
 	} else if ((verdict & NF_VERDICT_MASK) == NF_QUEUE) {
-		int err = nf_queue(skb, elem, pf, hook, indev, outdev, okfn,
-						verdict >> NF_VERDICT_QBITS);
+		int err = nf_queue(skb, elem, state,
+				   verdict >> NF_VERDICT_QBITS);
 		if (err < 0) {
 			if (err == -ECANCELED)
 				goto next_hook;
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 86f9d76b1464..d259da3ce67a 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -1863,6 +1863,12 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len)
 	if (*op < IP_SET_OP_VERSION) {
 		/* Check the version at the beginning of operations */
 		struct ip_set_req_version *req_version = data;
+
+		if (*len < sizeof(struct ip_set_req_version)) {
+			ret = -EINVAL;
+			goto done;
+		}
+
 		if (req_version->version != IPSET_PROTOCOL) {
 			ret = -EPROTO;
 			goto done;
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index fee7c64e4dd1..974ff386db0f 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -147,16 +147,22 @@ hbucket_elem_add(struct hbucket *n, u8 ahash_max, size_t dsize)
 #else
 #define __CIDR(cidr, i)		(cidr)
 #endif
+
+/* cidr + 1 is stored in net_prefixes to support /0 */
+#define SCIDR(cidr, i)		(__CIDR(cidr, i) + 1)
+
 #ifdef IP_SET_HASH_WITH_NETS_PACKED
-/* When cidr is packed with nomatch, cidr - 1 is stored in the entry */
-#define CIDR(cidr, i)		(__CIDR(cidr, i) + 1)
+/* When cidr is packed with nomatch, cidr - 1 is stored in the data entry */
+#define GCIDR(cidr, i)		(__CIDR(cidr, i) + 1)
+#define NCIDR(cidr)		(cidr)
 #else
-#define CIDR(cidr, i)		(__CIDR(cidr, i))
+#define GCIDR(cidr, i)		(__CIDR(cidr, i))
+#define NCIDR(cidr)		(cidr - 1)
 #endif
 
 #define SET_HOST_MASK(family)	(family == AF_INET ? 32 : 128)
 
-#ifdef IP_SET_HASH_WITH_MULTI
+#ifdef IP_SET_HASH_WITH_NET0
 #define NLEN(family)		(SET_HOST_MASK(family) + 1)
 #else
 #define NLEN(family)		SET_HOST_MASK(family)
@@ -292,24 +298,22 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 nets_length, u8 n)
 	int i, j;
 
 	/* Add in increasing prefix order, so larger cidr first */
-	for (i = 0, j = -1; i < nets_length && h->nets[i].nets[n]; i++) {
+	for (i = 0, j = -1; i < nets_length && h->nets[i].cidr[n]; i++) {
 		if (j != -1)
 			continue;
 		else if (h->nets[i].cidr[n] < cidr)
 			j = i;
 		else if (h->nets[i].cidr[n] == cidr) {
-			h->nets[i].nets[n]++;
+			h->nets[cidr - 1].nets[n]++;
 			return;
 		}
 	}
 	if (j != -1) {
-		for (; i > j; i--) {
+		for (; i > j; i--)
 			h->nets[i].cidr[n] = h->nets[i - 1].cidr[n];
-			h->nets[i].nets[n] = h->nets[i - 1].nets[n];
-		}
 	}
 	h->nets[i].cidr[n] = cidr;
-	h->nets[i].nets[n] = 1;
+	h->nets[cidr - 1].nets[n] = 1;
 }
 
 static void
@@ -320,16 +324,12 @@ mtype_del_cidr(struct htype *h, u8 cidr, u8 nets_length, u8 n)
 	for (i = 0; i < nets_length; i++) {
 	        if (h->nets[i].cidr[n] != cidr)
 	                continue;
-                if (h->nets[i].nets[n] > 1 || i == net_end ||
-                    h->nets[i + 1].nets[n] == 0) {
-                        h->nets[i].nets[n]--;
+		h->nets[cidr -1].nets[n]--;
+		if (h->nets[cidr -1].nets[n] > 0)
                         return;
-                }
-                for (j = i; j < net_end && h->nets[j].nets[n]; j++) {
+		for (j = i; j < net_end && h->nets[j].cidr[n]; j++)
 		        h->nets[j].cidr[n] = h->nets[j + 1].cidr[n];
-		        h->nets[j].nets[n] = h->nets[j + 1].nets[n];
-                }
-                h->nets[j].nets[n] = 0;
+		h->nets[j].cidr[n] = 0;
                 return;
 	}
 }
@@ -486,7 +486,7 @@ mtype_expire(struct ip_set *set, struct htype *h, u8 nets_length, size_t dsize)
 				pr_debug("expired %u/%u\n", i, j);
 #ifdef IP_SET_HASH_WITH_NETS
 				for (k = 0; k < IPSET_NET_COUNT; k++)
-					mtype_del_cidr(h, CIDR(data->cidr, k),
+					mtype_del_cidr(h, SCIDR(data->cidr, k),
 						       nets_length, k);
 #endif
 				ip_set_ext_destroy(set, data);
@@ -633,29 +633,6 @@ 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);
-
-	if (h->elements >= h->maxelem) {
-		if (net_ratelimit())
-			pr_warn("Set %s is full, maxelem %u reached\n",
-				set->name, h->maxelem);
-		return -IPSET_ERR_HASH_FULL;
-	}
-
 	rcu_read_lock_bh();
 	t = rcu_dereference_bh(h->table);
 	key = HKEY(value, h->initval, t->htable_bits);
@@ -680,15 +657,32 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 		    j != AHASH_MAX(h) + 1)
 			j = i;
 	}
+	if (h->elements >= h->maxelem && SET_WITH_FORCEADD(set) && n->pos) {
+		/* Choosing the first entry in the array to replace */
+		j = 0;
+		goto reuse_slot;
+	}
+	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);
+
+	if (h->elements >= h->maxelem) {
+		if (net_ratelimit())
+			pr_warn("Set %s is full, maxelem %u reached\n",
+				set->name, h->maxelem);
+		ret = -IPSET_ERR_HASH_FULL;
+		goto out;
+	}
+
 reuse_slot:
 	if (j != AHASH_MAX(h) + 1) {
 		/* Fill out reused slot */
 		data = ahash_data(n, j, set->dsize);
 #ifdef IP_SET_HASH_WITH_NETS
 		for (i = 0; i < IPSET_NET_COUNT; i++) {
-			mtype_del_cidr(h, CIDR(data->cidr, i),
+			mtype_del_cidr(h, SCIDR(data->cidr, i),
 				       NLEN(set->family), i);
-			mtype_add_cidr(h, CIDR(d->cidr, i),
+			mtype_add_cidr(h, SCIDR(d->cidr, i),
 				       NLEN(set->family), i);
 		}
 #endif
@@ -705,7 +699,7 @@ reuse_slot:
 		data = ahash_data(n, n->pos++, set->dsize);
 #ifdef IP_SET_HASH_WITH_NETS
 		for (i = 0; i < IPSET_NET_COUNT; i++)
-			mtype_add_cidr(h, CIDR(d->cidr, i), NLEN(set->family),
+			mtype_add_cidr(h, SCIDR(d->cidr, i), NLEN(set->family),
 				       i);
 #endif
 		h->elements++;
@@ -766,7 +760,7 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 		h->elements--;
 #ifdef IP_SET_HASH_WITH_NETS
 		for (j = 0; j < IPSET_NET_COUNT; j++)
-			mtype_del_cidr(h, CIDR(d->cidr, j), NLEN(set->family),
+			mtype_del_cidr(h, SCIDR(d->cidr, j), NLEN(set->family),
 				       j);
 #endif
 		ip_set_ext_destroy(set, data);
@@ -827,15 +821,15 @@ mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d,
 	u8 nets_length = NLEN(set->family);
 
 	pr_debug("test by nets\n");
-	for (; j < nets_length && h->nets[j].nets[0] && !multi; j++) {
+	for (; j < nets_length && h->nets[j].cidr[0] && !multi; j++) {
 #if IPSET_NET_COUNT == 2
 		mtype_data_reset_elem(d, &orig);
-		mtype_data_netmask(d, h->nets[j].cidr[0], false);
-		for (k = 0; k < nets_length && h->nets[k].nets[1] && !multi;
+		mtype_data_netmask(d, NCIDR(h->nets[j].cidr[0]), false);
+		for (k = 0; k < nets_length && h->nets[k].cidr[1] && !multi;
 		     k++) {
-			mtype_data_netmask(d, h->nets[k].cidr[1], true);
+			mtype_data_netmask(d, NCIDR(h->nets[k].cidr[1]), true);
 #else
-		mtype_data_netmask(d, h->nets[j].cidr[0]);
+		mtype_data_netmask(d, NCIDR(h->nets[j].cidr[0]));
 #endif
 		key = HKEY(d, h->initval, t->htable_bits);
 		n = hbucket(t, key);
@@ -883,7 +877,7 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 	/* If we test an IP address and not a network address,
 	 * try all possible network sizes */
 	for (i = 0; i < IPSET_NET_COUNT; i++)
-		if (CIDR(d->cidr, i) != SET_HOST_MASK(set->family))
+		if (GCIDR(d->cidr, i) != SET_HOST_MASK(set->family))
 			break;
 	if (i == IPSET_NET_COUNT) {
 		ret = mtype_test_cidrs(set, d, ext, mext, flags);
@@ -1107,8 +1101,7 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set,
 
 	hsize = sizeof(*h);
 #ifdef IP_SET_HASH_WITH_NETS
-	hsize += sizeof(struct net_prefixes) *
-		(set->family == NFPROTO_IPV4 ? 32 : 128);
+	hsize += sizeof(struct net_prefixes) * NLEN(set->family);
 #endif
 	h = kzalloc(hsize, GFP_KERNEL);
 	if (!h)
diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c
index 35dd35873442..380ef5148ea1 100644
--- a/net/netfilter/ipset/ip_set_hash_netiface.c
+++ b/net/netfilter/ipset/ip_set_hash_netiface.c
@@ -19,6 +19,7 @@
 #include <net/netlink.h>
 
 #include <linux/netfilter.h>
+#include <linux/netfilter_bridge.h>
 #include <linux/netfilter/ipset/pfxlen.h>
 #include <linux/netfilter/ipset/ip_set.h>
 #include <linux/netfilter/ipset/ip_set_hash.h>
@@ -115,6 +116,7 @@ iface_add(struct rb_root *root, const char **iface)
 #define IP_SET_HASH_WITH_NETS
 #define IP_SET_HASH_WITH_RBTREE
 #define IP_SET_HASH_WITH_MULTI
+#define IP_SET_HASH_WITH_NET0
 
 #define STREQ(a, b)	(strcmp(a, b) == 0)
 
@@ -210,6 +212,22 @@ hash_netiface4_data_next(struct hash_netiface4_elem *next,
 #define HKEY_DATALEN	sizeof(struct hash_netiface4_elem_hashed)
 #include "ip_set_hash_gen.h"
 
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+static const char *get_physindev_name(const struct sk_buff *skb)
+{
+	struct net_device *dev = nf_bridge_get_physindev(skb);
+
+	return dev ? dev->name : NULL;
+}
+
+static const char *get_phyoutdev_name(const struct sk_buff *skb)
+{
+	struct net_device *dev = nf_bridge_get_physoutdev(skb);
+
+	return dev ? dev->name : NULL;
+}
+#endif
+
 static int
 hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb,
 		    const struct xt_action_param *par,
@@ -233,16 +251,15 @@ hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb,
 	e.ip &= ip_set_netmask(e.cidr);
 
 #define IFACE(dir)	(par->dir ? par->dir->name : NULL)
-#define PHYSDEV(dir)	(nf_bridge->dir ? nf_bridge->dir->name : NULL)
 #define SRCDIR		(opt->flags & IPSET_DIM_TWO_SRC)
 
 	if (opt->cmdflags & IPSET_FLAG_PHYSDEV) {
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-		const struct nf_bridge_info *nf_bridge = skb->nf_bridge;
+		e.iface = SRCDIR ? get_physindev_name(skb) :
+				   get_phyoutdev_name(skb);
 
-		if (!nf_bridge)
+		if (!e.iface)
 			return -EINVAL;
-		e.iface = SRCDIR ? PHYSDEV(physindev) : PHYSDEV(physoutdev);
 		e.physdev = 1;
 #else
 		e.iface = NULL;
@@ -475,11 +492,11 @@ hash_netiface6_kadt(struct ip_set *set, const struct sk_buff *skb,
 
 	if (opt->cmdflags & IPSET_FLAG_PHYSDEV) {
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-		const struct nf_bridge_info *nf_bridge = skb->nf_bridge;
-
-		if (!nf_bridge)
+		e.iface = SRCDIR ? get_physindev_name(skb) :
+				   get_phyoutdev_name(skb);
+		if (!e.iface)
 			return -EINVAL;
-		e.iface = SRCDIR ? PHYSDEV(physindev) : PHYSDEV(physoutdev);
+
 		e.physdev = 1;
 #else
 		e.iface = NULL;
diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c
index da00284b3571..ea8772afb6e7 100644
--- a/net/netfilter/ipset/ip_set_hash_netnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netnet.c
@@ -46,6 +46,7 @@ struct hash_netnet4_elem {
 		__be64 ipcmp;
 	};
 	u8 nomatch;
+	u8 padding;
 	union {
 		u8 cidr[2];
 		u16 ccmp;
@@ -271,6 +272,7 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[],
 struct hash_netnet6_elem {
 	union nf_inet_addr ip[2];
 	u8 nomatch;
+	u8 padding;
 	union {
 		u8 cidr[2];
 		u16 ccmp;
diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c
index b8053d675fc3..bfaa94c7baa7 100644
--- a/net/netfilter/ipset/ip_set_hash_netportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netportnet.c
@@ -53,6 +53,7 @@ struct hash_netportnet4_elem {
 		u8 cidr[2];
 		u16 ccmp;
 	};
+	u16 padding;
 	u8 nomatch:1;
 	u8 proto;
 };
@@ -324,6 +325,7 @@ struct hash_netportnet6_elem {
 		u8 cidr[2];
 		u16 ccmp;
 	};
+	u16 padding;
 	u8 nomatch:1;
 	u8 proto;
 };
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 990decba1fe4..5d2b806a862e 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -119,24 +119,24 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
 		struct ip_vs_service *svc;
 
 		s = this_cpu_ptr(dest->stats.cpustats);
-		s->ustats.inpkts++;
 		u64_stats_update_begin(&s->syncp);
-		s->ustats.inbytes += skb->len;
+		s->cnt.inpkts++;
+		s->cnt.inbytes += skb->len;
 		u64_stats_update_end(&s->syncp);
 
 		rcu_read_lock();
 		svc = rcu_dereference(dest->svc);
 		s = this_cpu_ptr(svc->stats.cpustats);
-		s->ustats.inpkts++;
 		u64_stats_update_begin(&s->syncp);
-		s->ustats.inbytes += skb->len;
+		s->cnt.inpkts++;
+		s->cnt.inbytes += skb->len;
 		u64_stats_update_end(&s->syncp);
 		rcu_read_unlock();
 
 		s = this_cpu_ptr(ipvs->tot_stats.cpustats);
-		s->ustats.inpkts++;
 		u64_stats_update_begin(&s->syncp);
-		s->ustats.inbytes += skb->len;
+		s->cnt.inpkts++;
+		s->cnt.inbytes += skb->len;
 		u64_stats_update_end(&s->syncp);
 	}
 }
@@ -153,24 +153,24 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
 		struct ip_vs_service *svc;
 
 		s = this_cpu_ptr(dest->stats.cpustats);
-		s->ustats.outpkts++;
 		u64_stats_update_begin(&s->syncp);
-		s->ustats.outbytes += skb->len;
+		s->cnt.outpkts++;
+		s->cnt.outbytes += skb->len;
 		u64_stats_update_end(&s->syncp);
 
 		rcu_read_lock();
 		svc = rcu_dereference(dest->svc);
 		s = this_cpu_ptr(svc->stats.cpustats);
-		s->ustats.outpkts++;
 		u64_stats_update_begin(&s->syncp);
-		s->ustats.outbytes += skb->len;
+		s->cnt.outpkts++;
+		s->cnt.outbytes += skb->len;
 		u64_stats_update_end(&s->syncp);
 		rcu_read_unlock();
 
 		s = this_cpu_ptr(ipvs->tot_stats.cpustats);
-		s->ustats.outpkts++;
 		u64_stats_update_begin(&s->syncp);
-		s->ustats.outbytes += skb->len;
+		s->cnt.outpkts++;
+		s->cnt.outbytes += skb->len;
 		u64_stats_update_end(&s->syncp);
 	}
 }
@@ -183,13 +183,19 @@ ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc)
 	struct ip_vs_cpu_stats *s;
 
 	s = this_cpu_ptr(cp->dest->stats.cpustats);
-	s->ustats.conns++;
+	u64_stats_update_begin(&s->syncp);
+	s->cnt.conns++;
+	u64_stats_update_end(&s->syncp);
 
 	s = this_cpu_ptr(svc->stats.cpustats);
-	s->ustats.conns++;
+	u64_stats_update_begin(&s->syncp);
+	s->cnt.conns++;
+	u64_stats_update_end(&s->syncp);
 
 	s = this_cpu_ptr(ipvs->tot_stats.cpustats);
-	s->ustats.conns++;
+	u64_stats_update_begin(&s->syncp);
+	s->cnt.conns++;
+	u64_stats_update_end(&s->syncp);
 }
 
 
@@ -659,16 +665,24 @@ static inline int ip_vs_gather_frags(struct sk_buff *skb, u_int32_t user)
 	return err;
 }
 
-static int ip_vs_route_me_harder(int af, struct sk_buff *skb)
+static int ip_vs_route_me_harder(int af, struct sk_buff *skb,
+				 unsigned int hooknum)
 {
+	if (!sysctl_snat_reroute(skb))
+		return 0;
+	/* Reroute replies only to remote clients (FORWARD and LOCAL_OUT) */
+	if (NF_INET_LOCAL_IN == hooknum)
+		return 0;
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6) {
-		if (sysctl_snat_reroute(skb) && ip6_route_me_harder(skb) != 0)
+		struct dst_entry *dst = skb_dst(skb);
+
+		if (dst->dev && !(dst->dev->flags & IFF_LOOPBACK) &&
+		    ip6_route_me_harder(skb) != 0)
 			return 1;
 	} else
 #endif
-		if ((sysctl_snat_reroute(skb) ||
-		     skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
+		if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
 		    ip_route_me_harder(skb, RTN_LOCAL) != 0)
 			return 1;
 
@@ -791,7 +805,8 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
 				union nf_inet_addr *snet,
 				__u8 protocol, struct ip_vs_conn *cp,
 				struct ip_vs_protocol *pp,
-				unsigned int offset, unsigned int ihl)
+				unsigned int offset, unsigned int ihl,
+				unsigned int hooknum)
 {
 	unsigned int verdict = NF_DROP;
 
@@ -821,7 +836,7 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
 #endif
 		ip_vs_nat_icmp(skb, pp, cp, 1);
 
-	if (ip_vs_route_me_harder(af, skb))
+	if (ip_vs_route_me_harder(af, skb, hooknum))
 		goto out;
 
 	/* do the statistics and put it back */
@@ -916,7 +931,7 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related,
 
 	snet.ip = iph->saddr;
 	return handle_response_icmp(AF_INET, skb, &snet, cih->protocol, cp,
-				    pp, ciph.len, ihl);
+				    pp, ciph.len, ihl, hooknum);
 }
 
 #ifdef CONFIG_IP_VS_IPV6
@@ -981,7 +996,8 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related,
 	snet.in6 = ciph.saddr.in6;
 	writable = ciph.len;
 	return handle_response_icmp(AF_INET6, skb, &snet, ciph.protocol, cp,
-				    pp, writable, sizeof(struct ipv6hdr));
+				    pp, writable, sizeof(struct ipv6hdr),
+				    hooknum);
 }
 #endif
 
@@ -1036,11 +1052,32 @@ static inline bool is_new_conn(const struct sk_buff *skb,
 	}
 }
 
+static inline bool is_new_conn_expected(const struct ip_vs_conn *cp,
+					int conn_reuse_mode)
+{
+	/* Controlled (FTP DATA or persistence)? */
+	if (cp->control)
+		return false;
+
+	switch (cp->protocol) {
+	case IPPROTO_TCP:
+		return (cp->state == IP_VS_TCP_S_TIME_WAIT) ||
+			((conn_reuse_mode & 2) &&
+			 (cp->state == IP_VS_TCP_S_FIN_WAIT) &&
+			 (cp->flags & IP_VS_CONN_F_NOOUTPUT));
+	case IPPROTO_SCTP:
+		return cp->state == IP_VS_SCTP_S_CLOSED;
+	default:
+		return false;
+	}
+}
+
 /* Handle response packets: rewrite addresses and send away...
  */
 static unsigned int
 handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
-		struct ip_vs_conn *cp, struct ip_vs_iphdr *iph)
+		struct ip_vs_conn *cp, struct ip_vs_iphdr *iph,
+		unsigned int hooknum)
 {
 	struct ip_vs_protocol *pp = pd->pp;
 
@@ -1078,7 +1115,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 	 * if it came from this machine itself.  So re-compute
 	 * the routing information.
 	 */
-	if (ip_vs_route_me_harder(af, skb))
+	if (ip_vs_route_me_harder(af, skb, hooknum))
 		goto drop;
 
 	IP_VS_DBG_PKT(10, af, pp, skb, 0, "After SNAT");
@@ -1181,7 +1218,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 	cp = pp->conn_out_get(af, skb, &iph, 0);
 
 	if (likely(cp))
-		return handle_response(af, skb, pd, cp, &iph);
+		return handle_response(af, skb, pd, cp, &iph, hooknum);
 	if (sysctl_nat_icmp_send(net) &&
 	    (pp->protocol == IPPROTO_TCP ||
 	     pp->protocol == IPPROTO_UDP ||
@@ -1235,8 +1272,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
  */
 static unsigned int
 ip_vs_reply4(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 *))
+	     const struct nf_hook_state *state)
 {
 	return ip_vs_out(ops->hooknum, skb, AF_INET);
 }
@@ -1247,8 +1283,7 @@ ip_vs_reply4(const struct nf_hook_ops *ops, struct sk_buff *skb,
  */
 static unsigned int
 ip_vs_local_reply4(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 *))
+		   const struct nf_hook_state *state)
 {
 	return ip_vs_out(ops->hooknum, skb, AF_INET);
 }
@@ -1262,8 +1297,7 @@ ip_vs_local_reply4(const struct nf_hook_ops *ops, struct sk_buff *skb,
  */
 static unsigned int
 ip_vs_reply6(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 *))
+	     const struct nf_hook_state *state)
 {
 	return ip_vs_out(ops->hooknum, skb, AF_INET6);
 }
@@ -1274,8 +1308,7 @@ ip_vs_reply6(const struct nf_hook_ops *ops, struct sk_buff *skb,
  */
 static unsigned int
 ip_vs_local_reply6(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 *))
+		   const struct nf_hook_state *state)
 {
 	return ip_vs_out(ops->hooknum, skb, AF_INET6);
 }
@@ -1574,6 +1607,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	struct ip_vs_conn *cp;
 	int ret, pkts;
 	struct netns_ipvs *ipvs;
+	int conn_reuse_mode;
 
 	/* Already marked as IPVS request or reply? */
 	if (skb->ipvs_property)
@@ -1642,10 +1676,14 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	 */
 	cp = pp->conn_in_get(af, skb, &iph, 0);
 
-	if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp && cp->dest &&
-	    unlikely(!atomic_read(&cp->dest->weight)) && !iph.fragoffs &&
-	    is_new_conn(skb, &iph)) {
-		ip_vs_conn_expire_now(cp);
+	conn_reuse_mode = sysctl_conn_reuse_mode(ipvs);
+	if (conn_reuse_mode && !iph.fragoffs &&
+	    is_new_conn(skb, &iph) && cp &&
+	    ((unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest &&
+	      unlikely(!atomic_read(&cp->dest->weight))) ||
+	     unlikely(is_new_conn_expected(cp, conn_reuse_mode)))) {
+		if (!atomic_read(&cp->n_control))
+			ip_vs_conn_expire_now(cp);
 		__ip_vs_conn_put(cp);
 		cp = NULL;
 	}
@@ -1727,9 +1765,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
  */
 static unsigned int
 ip_vs_remote_request4(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 *))
+		      const struct nf_hook_state *state)
 {
 	return ip_vs_in(ops->hooknum, skb, AF_INET);
 }
@@ -1740,8 +1776,7 @@ ip_vs_remote_request4(const struct nf_hook_ops *ops, struct sk_buff *skb,
  */
 static unsigned int
 ip_vs_local_request4(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 *))
+		     const struct nf_hook_state *state)
 {
 	return ip_vs_in(ops->hooknum, skb, AF_INET);
 }
@@ -1754,9 +1789,7 @@ ip_vs_local_request4(const struct nf_hook_ops *ops, struct sk_buff *skb,
  */
 static unsigned int
 ip_vs_remote_request6(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 *))
+		      const struct nf_hook_state *state)
 {
 	return ip_vs_in(ops->hooknum, skb, AF_INET6);
 }
@@ -1767,8 +1800,7 @@ ip_vs_remote_request6(const struct nf_hook_ops *ops, struct sk_buff *skb,
  */
 static unsigned int
 ip_vs_local_request6(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 *))
+		     const struct nf_hook_state *state)
 {
 	return ip_vs_in(ops->hooknum, skb, AF_INET6);
 }
@@ -1787,8 +1819,7 @@ ip_vs_local_request6(const struct nf_hook_ops *ops, struct sk_buff *skb,
  */
 static unsigned int
 ip_vs_forward_icmp(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 *))
+		   const struct nf_hook_state *state)
 {
 	int r;
 	struct net *net;
@@ -1809,8 +1840,7 @@ ip_vs_forward_icmp(const struct nf_hook_ops *ops, struct sk_buff *skb,
 #ifdef CONFIG_IP_VS_IPV6
 static unsigned int
 ip_vs_forward_icmp_v6(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 *))
+		      const struct nf_hook_state *state)
 {
 	int r;
 	struct net *net;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index ac7ba689efe7..285eae3a1454 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -465,8 +465,7 @@ __ip_vs_bind_svc(struct ip_vs_dest *dest, struct ip_vs_service *svc)
 
 static void ip_vs_service_free(struct ip_vs_service *svc)
 {
-	if (svc->stats.cpustats)
-		free_percpu(svc->stats.cpustats);
+	free_percpu(svc->stats.cpustats);
 	kfree(svc);
 }
 
@@ -730,9 +729,9 @@ static void ip_vs_trash_cleanup(struct net *net)
 }
 
 static void
-ip_vs_copy_stats(struct ip_vs_stats_user *dst, struct ip_vs_stats *src)
+ip_vs_copy_stats(struct ip_vs_kstats *dst, struct ip_vs_stats *src)
 {
-#define IP_VS_SHOW_STATS_COUNTER(c) dst->c = src->ustats.c - src->ustats0.c
+#define IP_VS_SHOW_STATS_COUNTER(c) dst->c = src->kstats.c - src->kstats0.c
 
 	spin_lock_bh(&src->lock);
 
@@ -748,13 +747,28 @@ ip_vs_copy_stats(struct ip_vs_stats_user *dst, struct ip_vs_stats *src)
 }
 
 static void
+ip_vs_export_stats_user(struct ip_vs_stats_user *dst, struct ip_vs_kstats *src)
+{
+	dst->conns = (u32)src->conns;
+	dst->inpkts = (u32)src->inpkts;
+	dst->outpkts = (u32)src->outpkts;
+	dst->inbytes = src->inbytes;
+	dst->outbytes = src->outbytes;
+	dst->cps = (u32)src->cps;
+	dst->inpps = (u32)src->inpps;
+	dst->outpps = (u32)src->outpps;
+	dst->inbps = (u32)src->inbps;
+	dst->outbps = (u32)src->outbps;
+}
+
+static void
 ip_vs_zero_stats(struct ip_vs_stats *stats)
 {
 	spin_lock_bh(&stats->lock);
 
 	/* get current counters as zero point, rates are zeroed */
 
-#define IP_VS_ZERO_STATS_COUNTER(c) stats->ustats0.c = stats->ustats.c
+#define IP_VS_ZERO_STATS_COUNTER(c) stats->kstats0.c = stats->kstats.c
 
 	IP_VS_ZERO_STATS_COUNTER(conns);
 	IP_VS_ZERO_STATS_COUNTER(inpkts);
@@ -1809,6 +1823,12 @@ static struct ctl_table vs_vars[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "conn_reuse_mode",
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 #ifdef CONFIG_IP_VS_DEBUG
 	{
 		.procname	= "debug_level",
@@ -2045,7 +2065,7 @@ static const struct file_operations ip_vs_info_fops = {
 static int ip_vs_stats_show(struct seq_file *seq, void *v)
 {
 	struct net *net = seq_file_single_net(seq);
-	struct ip_vs_stats_user show;
+	struct ip_vs_kstats show;
 
 /*               01234567 01234567 01234567 0123456701234567 0123456701234567 */
 	seq_puts(seq,
@@ -2054,17 +2074,22 @@ static int ip_vs_stats_show(struct seq_file *seq, void *v)
 		   "   Conns  Packets  Packets            Bytes            Bytes\n");
 
 	ip_vs_copy_stats(&show, &net_ipvs(net)->tot_stats);
-	seq_printf(seq, "%8X %8X %8X %16LX %16LX\n\n", show.conns,
-		   show.inpkts, show.outpkts,
-		   (unsigned long long) show.inbytes,
-		   (unsigned long long) show.outbytes);
-
-/*                 01234567 01234567 01234567 0123456701234567 0123456701234567 */
+	seq_printf(seq, "%8LX %8LX %8LX %16LX %16LX\n\n",
+		   (unsigned long long)show.conns,
+		   (unsigned long long)show.inpkts,
+		   (unsigned long long)show.outpkts,
+		   (unsigned long long)show.inbytes,
+		   (unsigned long long)show.outbytes);
+
+/*                01234567 01234567 01234567 0123456701234567 0123456701234567*/
 	seq_puts(seq,
-		   " Conns/s   Pkts/s   Pkts/s          Bytes/s          Bytes/s\n");
-	seq_printf(seq, "%8X %8X %8X %16X %16X\n",
-			show.cps, show.inpps, show.outpps,
-			show.inbps, show.outbps);
+		 " Conns/s   Pkts/s   Pkts/s          Bytes/s          Bytes/s\n");
+	seq_printf(seq, "%8LX %8LX %8LX %16LX %16LX\n",
+		   (unsigned long long)show.cps,
+		   (unsigned long long)show.inpps,
+		   (unsigned long long)show.outpps,
+		   (unsigned long long)show.inbps,
+		   (unsigned long long)show.outbps);
 
 	return 0;
 }
@@ -2087,7 +2112,7 @@ static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v)
 	struct net *net = seq_file_single_net(seq);
 	struct ip_vs_stats *tot_stats = &net_ipvs(net)->tot_stats;
 	struct ip_vs_cpu_stats __percpu *cpustats = tot_stats->cpustats;
-	struct ip_vs_stats_user rates;
+	struct ip_vs_kstats kstats;
 	int i;
 
 /*               01234567 01234567 01234567 0123456701234567 0123456701234567 */
@@ -2099,41 +2124,41 @@ static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v)
 	for_each_possible_cpu(i) {
 		struct ip_vs_cpu_stats *u = per_cpu_ptr(cpustats, i);
 		unsigned int start;
-		__u64 inbytes, outbytes;
+		u64 conns, inpkts, outpkts, inbytes, outbytes;
 
 		do {
 			start = u64_stats_fetch_begin_irq(&u->syncp);
-			inbytes = u->ustats.inbytes;
-			outbytes = u->ustats.outbytes;
+			conns = u->cnt.conns;
+			inpkts = u->cnt.inpkts;
+			outpkts = u->cnt.outpkts;
+			inbytes = u->cnt.inbytes;
+			outbytes = u->cnt.outbytes;
 		} 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,
-			   u->ustats.outpkts, (__u64)inbytes,
-			   (__u64)outbytes);
+		seq_printf(seq, "%3X %8LX %8LX %8LX %16LX %16LX\n",
+			   i, (u64)conns, (u64)inpkts,
+			   (u64)outpkts, (u64)inbytes,
+			   (u64)outbytes);
 	}
 
-	spin_lock_bh(&tot_stats->lock);
-
-	seq_printf(seq, "  ~ %8X %8X %8X %16LX %16LX\n\n",
-		   tot_stats->ustats.conns, tot_stats->ustats.inpkts,
-		   tot_stats->ustats.outpkts,
-		   (unsigned long long) tot_stats->ustats.inbytes,
-		   (unsigned long long) tot_stats->ustats.outbytes);
-
-	ip_vs_read_estimator(&rates, tot_stats);
+	ip_vs_copy_stats(&kstats, tot_stats);
 
-	spin_unlock_bh(&tot_stats->lock);
+	seq_printf(seq, "  ~ %8LX %8LX %8LX %16LX %16LX\n\n",
+		   (unsigned long long)kstats.conns,
+		   (unsigned long long)kstats.inpkts,
+		   (unsigned long long)kstats.outpkts,
+		   (unsigned long long)kstats.inbytes,
+		   (unsigned long long)kstats.outbytes);
 
-/*                 01234567 01234567 01234567 0123456701234567 0123456701234567 */
+/*                ... 01234567 01234567 01234567 0123456701234567 0123456701234567 */
 	seq_puts(seq,
-		   "     Conns/s   Pkts/s   Pkts/s          Bytes/s          Bytes/s\n");
-	seq_printf(seq, "    %8X %8X %8X %16X %16X\n",
-			rates.cps,
-			rates.inpps,
-			rates.outpps,
-			rates.inbps,
-			rates.outbps);
+		 "     Conns/s   Pkts/s   Pkts/s          Bytes/s          Bytes/s\n");
+	seq_printf(seq, "    %8LX %8LX %8LX %16LX %16LX\n",
+		   kstats.cps,
+		   kstats.inpps,
+		   kstats.outpps,
+		   kstats.inbps,
+		   kstats.outbps);
 
 	return 0;
 }
@@ -2401,6 +2426,7 @@ static void
 ip_vs_copy_service(struct ip_vs_service_entry *dst, struct ip_vs_service *src)
 {
 	struct ip_vs_scheduler *sched;
+	struct ip_vs_kstats kstats;
 
 	sched = rcu_dereference_protected(src->scheduler, 1);
 	dst->protocol = src->protocol;
@@ -2412,7 +2438,8 @@ ip_vs_copy_service(struct ip_vs_service_entry *dst, struct ip_vs_service *src)
 	dst->timeout = src->timeout / HZ;
 	dst->netmask = src->netmask;
 	dst->num_dests = src->num_dests;
-	ip_vs_copy_stats(&dst->stats, &src->stats);
+	ip_vs_copy_stats(&kstats, &src->stats);
+	ip_vs_export_stats_user(&dst->stats, &kstats);
 }
 
 static inline int
@@ -2486,6 +2513,7 @@ __ip_vs_get_dest_entries(struct net *net, const struct ip_vs_get_dests *get,
 		int count = 0;
 		struct ip_vs_dest *dest;
 		struct ip_vs_dest_entry entry;
+		struct ip_vs_kstats kstats;
 
 		memset(&entry, 0, sizeof(entry));
 		list_for_each_entry(dest, &svc->destinations, n_list) {
@@ -2507,7 +2535,8 @@ __ip_vs_get_dest_entries(struct net *net, const struct ip_vs_get_dests *get,
 			entry.activeconns = atomic_read(&dest->activeconns);
 			entry.inactconns = atomic_read(&dest->inactconns);
 			entry.persistconns = atomic_read(&dest->persistconns);
-			ip_vs_copy_stats(&entry.stats, &dest->stats);
+			ip_vs_copy_stats(&kstats, &dest->stats);
+			ip_vs_export_stats_user(&entry.stats, &kstats);
 			if (copy_to_user(&uptr->entrytable[count],
 					 &entry, sizeof(entry))) {
 				ret = -EFAULT;
@@ -2799,25 +2828,51 @@ static const struct nla_policy ip_vs_dest_policy[IPVS_DEST_ATTR_MAX + 1] = {
 };
 
 static int ip_vs_genl_fill_stats(struct sk_buff *skb, int container_type,
-				 struct ip_vs_stats *stats)
+				 struct ip_vs_kstats *kstats)
 {
-	struct ip_vs_stats_user ustats;
 	struct nlattr *nl_stats = nla_nest_start(skb, container_type);
+
 	if (!nl_stats)
 		return -EMSGSIZE;
 
-	ip_vs_copy_stats(&ustats, stats);
-
-	if (nla_put_u32(skb, IPVS_STATS_ATTR_CONNS, ustats.conns) ||
-	    nla_put_u32(skb, IPVS_STATS_ATTR_INPKTS, ustats.inpkts) ||
-	    nla_put_u32(skb, IPVS_STATS_ATTR_OUTPKTS, ustats.outpkts) ||
-	    nla_put_u64(skb, IPVS_STATS_ATTR_INBYTES, ustats.inbytes) ||
-	    nla_put_u64(skb, IPVS_STATS_ATTR_OUTBYTES, ustats.outbytes) ||
-	    nla_put_u32(skb, IPVS_STATS_ATTR_CPS, ustats.cps) ||
-	    nla_put_u32(skb, IPVS_STATS_ATTR_INPPS, ustats.inpps) ||
-	    nla_put_u32(skb, IPVS_STATS_ATTR_OUTPPS, ustats.outpps) ||
-	    nla_put_u32(skb, IPVS_STATS_ATTR_INBPS, ustats.inbps) ||
-	    nla_put_u32(skb, IPVS_STATS_ATTR_OUTBPS, ustats.outbps))
+	if (nla_put_u32(skb, IPVS_STATS_ATTR_CONNS, (u32)kstats->conns) ||
+	    nla_put_u32(skb, IPVS_STATS_ATTR_INPKTS, (u32)kstats->inpkts) ||
+	    nla_put_u32(skb, IPVS_STATS_ATTR_OUTPKTS, (u32)kstats->outpkts) ||
+	    nla_put_u64(skb, IPVS_STATS_ATTR_INBYTES, kstats->inbytes) ||
+	    nla_put_u64(skb, IPVS_STATS_ATTR_OUTBYTES, kstats->outbytes) ||
+	    nla_put_u32(skb, IPVS_STATS_ATTR_CPS, (u32)kstats->cps) ||
+	    nla_put_u32(skb, IPVS_STATS_ATTR_INPPS, (u32)kstats->inpps) ||
+	    nla_put_u32(skb, IPVS_STATS_ATTR_OUTPPS, (u32)kstats->outpps) ||
+	    nla_put_u32(skb, IPVS_STATS_ATTR_INBPS, (u32)kstats->inbps) ||
+	    nla_put_u32(skb, IPVS_STATS_ATTR_OUTBPS, (u32)kstats->outbps))
+		goto nla_put_failure;
+	nla_nest_end(skb, nl_stats);
+
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, nl_stats);
+	return -EMSGSIZE;
+}
+
+static int ip_vs_genl_fill_stats64(struct sk_buff *skb, int container_type,
+				   struct ip_vs_kstats *kstats)
+{
+	struct nlattr *nl_stats = nla_nest_start(skb, container_type);
+
+	if (!nl_stats)
+		return -EMSGSIZE;
+
+	if (nla_put_u64(skb, IPVS_STATS_ATTR_CONNS, kstats->conns) ||
+	    nla_put_u64(skb, IPVS_STATS_ATTR_INPKTS, kstats->inpkts) ||
+	    nla_put_u64(skb, IPVS_STATS_ATTR_OUTPKTS, kstats->outpkts) ||
+	    nla_put_u64(skb, IPVS_STATS_ATTR_INBYTES, kstats->inbytes) ||
+	    nla_put_u64(skb, IPVS_STATS_ATTR_OUTBYTES, kstats->outbytes) ||
+	    nla_put_u64(skb, IPVS_STATS_ATTR_CPS, kstats->cps) ||
+	    nla_put_u64(skb, IPVS_STATS_ATTR_INPPS, kstats->inpps) ||
+	    nla_put_u64(skb, IPVS_STATS_ATTR_OUTPPS, kstats->outpps) ||
+	    nla_put_u64(skb, IPVS_STATS_ATTR_INBPS, kstats->inbps) ||
+	    nla_put_u64(skb, IPVS_STATS_ATTR_OUTBPS, kstats->outbps))
 		goto nla_put_failure;
 	nla_nest_end(skb, nl_stats);
 
@@ -2836,6 +2891,7 @@ static int ip_vs_genl_fill_service(struct sk_buff *skb,
 	struct nlattr *nl_service;
 	struct ip_vs_flags flags = { .flags = svc->flags,
 				     .mask = ~0 };
+	struct ip_vs_kstats kstats;
 
 	nl_service = nla_nest_start(skb, IPVS_CMD_ATTR_SERVICE);
 	if (!nl_service)
@@ -2861,7 +2917,10 @@ static int ip_vs_genl_fill_service(struct sk_buff *skb,
 	    nla_put_u32(skb, IPVS_SVC_ATTR_TIMEOUT, svc->timeout / HZ) ||
 	    nla_put_be32(skb, IPVS_SVC_ATTR_NETMASK, svc->netmask))
 		goto nla_put_failure;
-	if (ip_vs_genl_fill_stats(skb, IPVS_SVC_ATTR_STATS, &svc->stats))
+	ip_vs_copy_stats(&kstats, &svc->stats);
+	if (ip_vs_genl_fill_stats(skb, IPVS_SVC_ATTR_STATS, &kstats))
+		goto nla_put_failure;
+	if (ip_vs_genl_fill_stats64(skb, IPVS_SVC_ATTR_STATS64, &kstats))
 		goto nla_put_failure;
 
 	nla_nest_end(skb, nl_service);
@@ -2888,7 +2947,8 @@ static int ip_vs_genl_dump_service(struct sk_buff *skb,
 	if (ip_vs_genl_fill_service(skb, svc) < 0)
 		goto nla_put_failure;
 
-	return genlmsg_end(skb, hdr);
+	genlmsg_end(skb, hdr);
+	return 0;
 
 nla_put_failure:
 	genlmsg_cancel(skb, hdr);
@@ -3032,6 +3092,7 @@ static struct ip_vs_service *ip_vs_genl_find_service(struct net *net,
 static int ip_vs_genl_fill_dest(struct sk_buff *skb, struct ip_vs_dest *dest)
 {
 	struct nlattr *nl_dest;
+	struct ip_vs_kstats kstats;
 
 	nl_dest = nla_nest_start(skb, IPVS_CMD_ATTR_DEST);
 	if (!nl_dest)
@@ -3054,7 +3115,10 @@ static int ip_vs_genl_fill_dest(struct sk_buff *skb, struct ip_vs_dest *dest)
 			atomic_read(&dest->persistconns)) ||
 	    nla_put_u16(skb, IPVS_DEST_ATTR_ADDR_FAMILY, dest->af))
 		goto nla_put_failure;
-	if (ip_vs_genl_fill_stats(skb, IPVS_DEST_ATTR_STATS, &dest->stats))
+	ip_vs_copy_stats(&kstats, &dest->stats);
+	if (ip_vs_genl_fill_stats(skb, IPVS_DEST_ATTR_STATS, &kstats))
+		goto nla_put_failure;
+	if (ip_vs_genl_fill_stats64(skb, IPVS_DEST_ATTR_STATS64, &kstats))
 		goto nla_put_failure;
 
 	nla_nest_end(skb, nl_dest);
@@ -3080,7 +3144,8 @@ static int ip_vs_genl_dump_dest(struct sk_buff *skb, struct ip_vs_dest *dest,
 	if (ip_vs_genl_fill_dest(skb, dest) < 0)
 		goto nla_put_failure;
 
-	return genlmsg_end(skb, hdr);
+	genlmsg_end(skb, hdr);
+	return 0;
 
 nla_put_failure:
 	genlmsg_cancel(skb, hdr);
@@ -3216,7 +3281,8 @@ static int ip_vs_genl_dump_daemon(struct sk_buff *skb, __u32 state,
 	if (ip_vs_genl_fill_daemon(skb, state, mcast_ifn, syncid))
 		goto nla_put_failure;
 
-	return genlmsg_end(skb, hdr);
+	genlmsg_end(skb, hdr);
+	return 0;
 
 nla_put_failure:
 	genlmsg_cancel(skb, hdr);
@@ -3400,7 +3466,7 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
 		if (udest.af == 0)
 			udest.af = svc->af;
 
-		if (udest.af != svc->af) {
+		if (udest.af != svc->af && cmd != IPVS_CMD_DEL_DEST) {
 			/* The synchronization protocol is incompatible
 			 * with mixed family services
 			 */
@@ -3730,6 +3796,8 @@ static int __net_init ip_vs_control_net_init_sysctl(struct net *net)
 	ipvs->sysctl_pmtu_disc = 1;
 	tbl[idx++].data = &ipvs->sysctl_pmtu_disc;
 	tbl[idx++].data = &ipvs->sysctl_backup_only;
+	ipvs->sysctl_conn_reuse_mode = 1;
+	tbl[idx++].data = &ipvs->sysctl_conn_reuse_mode;
 
 
 	ipvs->sysctl_hdr = register_net_sysctl(net, "net/ipv4/vs", tbl);
@@ -3755,6 +3823,9 @@ static void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net)
 	cancel_work_sync(&ipvs->defense_work.work);
 	unregister_net_sysctl_table(ipvs->sysctl_hdr);
 	ip_vs_stop_estimator(net, &ipvs->tot_stats);
+
+	if (!net_eq(net, &init_net))
+		kfree(ipvs->sysctl_tbl);
 }
 
 #else
diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c
index 1425e9a924c4..ef0eb0a8d552 100644
--- a/net/netfilter/ipvs/ip_vs_est.c
+++ b/net/netfilter/ipvs/ip_vs_est.c
@@ -45,17 +45,19 @@
 
   NOTES.
 
-  * The stored value for average bps is scaled by 2^5, so that maximal
-    rate is ~2.15Gbits/s, average pps and cps are scaled by 2^10.
+  * Average bps is scaled by 2^5, while average pps and cps are scaled by 2^10.
 
-  * A lot code is taken from net/sched/estimator.c
+  * Netlink users can see 64-bit values but sockopt users are restricted
+    to 32-bit values for conns, packets, bps, cps and pps.
+
+  * A lot of code is taken from net/core/gen_estimator.c
  */
 
 
 /*
  * Make a summary from each cpu
  */
-static void ip_vs_read_cpu_stats(struct ip_vs_stats_user *sum,
+static void ip_vs_read_cpu_stats(struct ip_vs_kstats *sum,
 				 struct ip_vs_cpu_stats __percpu *stats)
 {
 	int i;
@@ -64,27 +66,31 @@ static void ip_vs_read_cpu_stats(struct ip_vs_stats_user *sum,
 	for_each_possible_cpu(i) {
 		struct ip_vs_cpu_stats *s = per_cpu_ptr(stats, i);
 		unsigned int start;
-		__u64 inbytes, outbytes;
+		u64 conns, inpkts, outpkts, inbytes, outbytes;
+
 		if (add) {
-			sum->conns += s->ustats.conns;
-			sum->inpkts += s->ustats.inpkts;
-			sum->outpkts += s->ustats.outpkts;
 			do {
 				start = u64_stats_fetch_begin(&s->syncp);
-				inbytes = s->ustats.inbytes;
-				outbytes = s->ustats.outbytes;
+				conns = s->cnt.conns;
+				inpkts = s->cnt.inpkts;
+				outpkts = s->cnt.outpkts;
+				inbytes = s->cnt.inbytes;
+				outbytes = s->cnt.outbytes;
 			} while (u64_stats_fetch_retry(&s->syncp, start));
+			sum->conns += conns;
+			sum->inpkts += inpkts;
+			sum->outpkts += outpkts;
 			sum->inbytes += inbytes;
 			sum->outbytes += outbytes;
 		} else {
 			add = true;
-			sum->conns = s->ustats.conns;
-			sum->inpkts = s->ustats.inpkts;
-			sum->outpkts = s->ustats.outpkts;
 			do {
 				start = u64_stats_fetch_begin(&s->syncp);
-				sum->inbytes = s->ustats.inbytes;
-				sum->outbytes = s->ustats.outbytes;
+				sum->conns = s->cnt.conns;
+				sum->inpkts = s->cnt.inpkts;
+				sum->outpkts = s->cnt.outpkts;
+				sum->inbytes = s->cnt.inbytes;
+				sum->outbytes = s->cnt.outbytes;
 			} while (u64_stats_fetch_retry(&s->syncp, start));
 		}
 	}
@@ -95,10 +101,7 @@ static void estimation_timer(unsigned long arg)
 {
 	struct ip_vs_estimator *e;
 	struct ip_vs_stats *s;
-	u32 n_conns;
-	u32 n_inpkts, n_outpkts;
-	u64 n_inbytes, n_outbytes;
-	u32 rate;
+	u64 rate;
 	struct net *net = (struct net *)arg;
 	struct netns_ipvs *ipvs;
 
@@ -108,33 +111,29 @@ static void estimation_timer(unsigned long arg)
 		s = container_of(e, struct ip_vs_stats, est);
 
 		spin_lock(&s->lock);
-		ip_vs_read_cpu_stats(&s->ustats, s->cpustats);
-		n_conns = s->ustats.conns;
-		n_inpkts = s->ustats.inpkts;
-		n_outpkts = s->ustats.outpkts;
-		n_inbytes = s->ustats.inbytes;
-		n_outbytes = s->ustats.outbytes;
+		ip_vs_read_cpu_stats(&s->kstats, s->cpustats);
 
 		/* scaled by 2^10, but divided 2 seconds */
-		rate = (n_conns - e->last_conns) << 9;
-		e->last_conns = n_conns;
-		e->cps += ((long)rate - (long)e->cps) >> 2;
-
-		rate = (n_inpkts - e->last_inpkts) << 9;
-		e->last_inpkts = n_inpkts;
-		e->inpps += ((long)rate - (long)e->inpps) >> 2;
-
-		rate = (n_outpkts - e->last_outpkts) << 9;
-		e->last_outpkts = n_outpkts;
-		e->outpps += ((long)rate - (long)e->outpps) >> 2;
-
-		rate = (n_inbytes - e->last_inbytes) << 4;
-		e->last_inbytes = n_inbytes;
-		e->inbps += ((long)rate - (long)e->inbps) >> 2;
-
-		rate = (n_outbytes - e->last_outbytes) << 4;
-		e->last_outbytes = n_outbytes;
-		e->outbps += ((long)rate - (long)e->outbps) >> 2;
+		rate = (s->kstats.conns - e->last_conns) << 9;
+		e->last_conns = s->kstats.conns;
+		e->cps += ((s64)rate - (s64)e->cps) >> 2;
+
+		rate = (s->kstats.inpkts - e->last_inpkts) << 9;
+		e->last_inpkts = s->kstats.inpkts;
+		e->inpps += ((s64)rate - (s64)e->inpps) >> 2;
+
+		rate = (s->kstats.outpkts - e->last_outpkts) << 9;
+		e->last_outpkts = s->kstats.outpkts;
+		e->outpps += ((s64)rate - (s64)e->outpps) >> 2;
+
+		/* scaled by 2^5, but divided 2 seconds */
+		rate = (s->kstats.inbytes - e->last_inbytes) << 4;
+		e->last_inbytes = s->kstats.inbytes;
+		e->inbps += ((s64)rate - (s64)e->inbps) >> 2;
+
+		rate = (s->kstats.outbytes - e->last_outbytes) << 4;
+		e->last_outbytes = s->kstats.outbytes;
+		e->outbps += ((s64)rate - (s64)e->outbps) >> 2;
 		spin_unlock(&s->lock);
 	}
 	spin_unlock(&ipvs->est_lock);
@@ -166,14 +165,14 @@ void ip_vs_stop_estimator(struct net *net, struct ip_vs_stats *stats)
 void ip_vs_zero_estimator(struct ip_vs_stats *stats)
 {
 	struct ip_vs_estimator *est = &stats->est;
-	struct ip_vs_stats_user *u = &stats->ustats;
+	struct ip_vs_kstats *k = &stats->kstats;
 
 	/* reset counters, caller must hold the stats->lock lock */
-	est->last_inbytes = u->inbytes;
-	est->last_outbytes = u->outbytes;
-	est->last_conns = u->conns;
-	est->last_inpkts = u->inpkts;
-	est->last_outpkts = u->outpkts;
+	est->last_inbytes = k->inbytes;
+	est->last_outbytes = k->outbytes;
+	est->last_conns = k->conns;
+	est->last_inpkts = k->inpkts;
+	est->last_outpkts = k->outpkts;
 	est->cps = 0;
 	est->inpps = 0;
 	est->outpps = 0;
@@ -182,8 +181,7 @@ void ip_vs_zero_estimator(struct ip_vs_stats *stats)
 }
 
 /* Get decoded rates */
-void ip_vs_read_estimator(struct ip_vs_stats_user *dst,
-			  struct ip_vs_stats *stats)
+void ip_vs_read_estimator(struct ip_vs_kstats *dst, struct ip_vs_stats *stats)
 {
 	struct ip_vs_estimator *e = &stats->est;
 
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index 1d5341f3761d..5d3daae98bf0 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -183,6 +183,8 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 	struct nf_conn *ct;
 	struct net *net;
 
+	*diff = 0;
+
 #ifdef CONFIG_IP_VS_IPV6
 	/* This application helper doesn't work with IPv6 yet,
 	 * so turn this into a no-op for IPv6 packets
@@ -191,8 +193,6 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 		return 1;
 #endif
 
-	*diff = 0;
-
 	/* Only useful for established sessions */
 	if (cp->state != IP_VS_TCP_S_ESTABLISHED)
 		return 1;
@@ -322,6 +322,9 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 	struct ip_vs_conn *n_cp;
 	struct net *net;
 
+	/* no diff required for incoming packets */
+	*diff = 0;
+
 #ifdef CONFIG_IP_VS_IPV6
 	/* This application helper doesn't work with IPv6 yet,
 	 * so turn this into a no-op for IPv6 packets
@@ -330,9 +333,6 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 		return 1;
 #endif
 
-	/* no diff required for incoming packets */
-	*diff = 0;
-
 	/* Only useful for established sessions */
 	if (cp->state != IP_VS_TCP_S_ESTABLISHED)
 		return 1;
diff --git a/net/netfilter/ipvs/ip_vs_pe.c b/net/netfilter/ipvs/ip_vs_pe.c
index 1a82b29ce8ea..0df17caa8af6 100644
--- a/net/netfilter/ipvs/ip_vs_pe.c
+++ b/net/netfilter/ipvs/ip_vs_pe.c
@@ -37,8 +37,7 @@ struct ip_vs_pe *__ip_vs_pe_getbyname(const char *pe_name)
 			rcu_read_unlock();
 			return pe;
 		}
-		if (pe->module)
-			module_put(pe->module);
+		module_put(pe->module);
 	}
 	rcu_read_unlock();
 
diff --git a/net/netfilter/ipvs/ip_vs_sched.c b/net/netfilter/ipvs/ip_vs_sched.c
index 4dbcda6258bc..199760c71f39 100644
--- a/net/netfilter/ipvs/ip_vs_sched.c
+++ b/net/netfilter/ipvs/ip_vs_sched.c
@@ -104,8 +104,7 @@ static struct ip_vs_scheduler *ip_vs_sched_getbyname(const char *sched_name)
 			mutex_unlock(&ip_vs_sched_mutex);
 			return sched;
 		}
-		if (sched->module)
-			module_put(sched->module);
+		module_put(sched->module);
 	}
 
 	mutex_unlock(&ip_vs_sched_mutex);
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 7162c86fd50d..19b9cce6c210 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -820,8 +820,7 @@ ip_vs_conn_fill_param_sync(struct net *net, int af, union ip_vs_sync_conn *sc,
 
 		p->pe_data = kmemdup(pe_data, pe_data_len, GFP_ATOMIC);
 		if (!p->pe_data) {
-			if (p->pe->module)
-				module_put(p->pe->module);
+			module_put(p->pe->module);
 			return -ENOMEM;
 		}
 		p->pe_data_len = pe_data_len;
@@ -846,10 +845,27 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
 	struct ip_vs_conn *cp;
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
-	if (!(flags & IP_VS_CONN_F_TEMPLATE))
+	if (!(flags & IP_VS_CONN_F_TEMPLATE)) {
 		cp = ip_vs_conn_in_get(param);
-	else
+		if (cp && ((cp->dport != dport) ||
+			   !ip_vs_addr_equal(cp->daf, &cp->daddr, daddr))) {
+			if (!(flags & IP_VS_CONN_F_INACTIVE)) {
+				ip_vs_conn_expire_now(cp);
+				__ip_vs_conn_put(cp);
+				cp = NULL;
+			} else {
+				/* This is the expiration message for the
+				 * connection that was already replaced, so we
+				 * just ignore it.
+				 */
+				__ip_vs_conn_put(cp);
+				kfree(param->pe_data);
+				return;
+			}
+		}
+	} else {
 		cp = ip_vs_ct_in_get(param);
+	}
 
 	if (cp) {
 		/* Free pe_data */
@@ -897,6 +913,8 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
 			IP_VS_DBG(2, "BACKUP, add new conn. failed\n");
 			return;
 		}
+		if (!(flags & IP_VS_CONN_F_TEMPLATE))
+			kfree(param->pe_data);
 	}
 
 	if (opt)
@@ -1170,6 +1188,7 @@ static inline int ip_vs_proc_sync_conn(struct net *net, __u8 *p, __u8 *msg_end)
 				(opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL)
 				);
 #endif
+	ip_vs_pe_put(param.pe);
 	return 0;
 	/* Error exit */
 out:
@@ -1386,9 +1405,11 @@ join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname)
 
 	mreq.imr_ifindex = dev->ifindex;
 
+	rtnl_lock();
 	lock_sock(sk);
 	ret = ip_mc_join_group(sk, &mreq);
 	release_sock(sk);
+	rtnl_unlock();
 
 	return ret;
 }
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 437a3663ad03..19986ec5f21a 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -209,7 +209,7 @@ static inline void maybe_update_pmtu(int skb_af, struct sk_buff *skb, int mtu)
 	struct sock *sk = skb->sk;
 	struct rtable *ort = skb_rtable(skb);
 
-	if (!skb->dev && sk && sk->sk_state != TCP_TIME_WAIT)
+	if (!skb->dev && sk && sk_fullsock(sk))
 		ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu);
 }
 
@@ -293,7 +293,6 @@ __ip_vs_get_out_rt(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
 				  &dest->addr.ip, &dest_dst->dst_saddr.ip,
 				  atomic_read(&rt->dst.__refcnt));
 		}
-		daddr = dest->addr.ip;
 		if (ret_saddr)
 			*ret_saddr = dest_dst->dst_saddr.ip;
 	} else {
@@ -344,7 +343,7 @@ __ip_vs_get_out_rt(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
 	skb_dst_drop(skb);
 	if (noref) {
 		if (!local)
-			skb_dst_set_noref_force(skb, &rt->dst);
+			skb_dst_set_noref(skb, &rt->dst);
 		else
 			skb_dst_set(skb, dst_clone(&rt->dst));
 	} else
@@ -488,7 +487,7 @@ __ip_vs_get_out_rt_v6(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
 	skb_dst_drop(skb);
 	if (noref) {
 		if (!local)
-			skb_dst_set_noref_force(skb, &rt->dst);
+			skb_dst_set_noref(skb, &rt->dst);
 		else
 			skb_dst_set(skb, dst_clone(&rt->dst));
 	} else
@@ -537,8 +536,8 @@ static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb,
 		ip_vs_update_conntrack(skb, cp, 1);
 	if (!local) {
 		skb_forward_csum(skb);
-		NF_HOOK(pf, NF_INET_LOCAL_OUT, skb, NULL, skb_dst(skb)->dev,
-			dst_output);
+		NF_HOOK(pf, NF_INET_LOCAL_OUT, NULL, skb,
+			NULL, skb_dst(skb)->dev, dst_output_sk);
 	} else
 		ret = NF_ACCEPT;
 	return ret;
@@ -555,8 +554,8 @@ static inline int ip_vs_send_or_cont(int pf, struct sk_buff *skb,
 		ip_vs_notrack(skb);
 	if (!local) {
 		skb_forward_csum(skb);
-		NF_HOOK(pf, NF_INET_LOCAL_OUT, skb, NULL, skb_dst(skb)->dev,
-			dst_output);
+		NF_HOOK(pf, NF_INET_LOCAL_OUT, NULL, skb,
+			NULL, skb_dst(skb)->dev, dst_output_sk);
 	} else
 		ret = NF_ACCEPT;
 	return ret;
@@ -846,6 +845,8 @@ ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af,
 		new_skb = skb_realloc_headroom(skb, max_headroom);
 		if (!new_skb)
 			goto error;
+		if (skb->sk)
+			skb_set_owner_w(new_skb, skb->sk);
 		consume_skb(skb);
 		skb = new_skb;
 	}
@@ -923,7 +924,8 @@ int
 ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 		  struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
 {
-	struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
+	struct net *net = skb_net(skb);
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct rtable *rt;			/* Route to the other host */
 	__be32 saddr;				/* Source for tunnel */
 	struct net_device *tdev;		/* Device to other host */
@@ -990,7 +992,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	iph->daddr		=	cp->daddr.ip;
 	iph->saddr		=	saddr;
 	iph->ttl		=	ttl;
-	ip_select_ident(skb, NULL);
+	ip_select_ident(net, skb, NULL);
 
 	/* Another hack: avoid icmp_send in ip_fragment */
 	skb->ignore_df = 1;
diff --git a/net/netfilter/nf_conntrack_acct.c b/net/netfilter/nf_conntrack_acct.c
index a4b5e2a435ac..45da11afa785 100644
--- a/net/netfilter/nf_conntrack_acct.c
+++ b/net/netfilter/nf_conntrack_acct.c
@@ -47,9 +47,11 @@ seq_print_acct(struct seq_file *s, const struct nf_conn *ct, int dir)
 		return 0;
 
 	counter = acct->counter;
-	return seq_printf(s, "packets=%llu bytes=%llu ",
-			  (unsigned long long)atomic64_read(&counter[dir].packets),
-			  (unsigned long long)atomic64_read(&counter[dir].bytes));
+	seq_printf(s, "packets=%llu bytes=%llu ",
+		   (unsigned long long)atomic64_read(&counter[dir].packets),
+		   (unsigned long long)atomic64_read(&counter[dir].bytes));
+
+	return 0;
 };
 EXPORT_SYMBOL_GPL(seq_print_acct);
 
diff --git a/net/netfilter/nf_conntrack_amanda.c b/net/netfilter/nf_conntrack_amanda.c
index b8b95f4027ca..57a26cc90c9f 100644
--- a/net/netfilter/nf_conntrack_amanda.c
+++ b/net/netfilter/nf_conntrack_amanda.c
@@ -88,7 +88,6 @@ static int amanda_help(struct sk_buff *skb,
 		       struct nf_conn *ct,
 		       enum ip_conntrack_info ctinfo)
 {
-	struct ts_state ts;
 	struct nf_conntrack_expect *exp;
 	struct nf_conntrack_tuple *tuple;
 	unsigned int dataoff, start, stop, off, i;
@@ -113,23 +112,20 @@ static int amanda_help(struct sk_buff *skb,
 		return NF_ACCEPT;
 	}
 
-	memset(&ts, 0, sizeof(ts));
 	start = skb_find_text(skb, dataoff, skb->len,
-			      search[SEARCH_CONNECT].ts, &ts);
+			      search[SEARCH_CONNECT].ts);
 	if (start == UINT_MAX)
 		goto out;
 	start += dataoff + search[SEARCH_CONNECT].len;
 
-	memset(&ts, 0, sizeof(ts));
 	stop = skb_find_text(skb, start, skb->len,
-			     search[SEARCH_NEWLINE].ts, &ts);
+			     search[SEARCH_NEWLINE].ts);
 	if (stop == UINT_MAX)
 		goto out;
 	stop += start;
 
 	for (i = SEARCH_DATA; i <= SEARCH_INDEX; i++) {
-		memset(&ts, 0, sizeof(ts));
-		off = skb_find_text(skb, start, stop, search[i].ts, &ts);
+		off = skb_find_text(skb, start, stop, search[i].ts);
 		if (off == UINT_MAX)
 			continue;
 		off += start + search[i].len;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 5016a6929085..13fad8668f83 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -611,16 +611,15 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 	 */
 	NF_CT_ASSERT(!nf_ct_is_confirmed(ct));
 	pr_debug("Confirming conntrack %p\n", ct);
-	/* 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 */
+	/* We have to check the DYING flag after unlink 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.
+	 */
+	nf_ct_del_from_dying_or_unconfirmed_list(ct);
 
-	if (unlikely(nf_ct_is_dying(ct))) {
-		nf_conntrack_double_unlock(hash, reply_hash);
-		local_bh_enable();
-		return NF_ACCEPT;
-	}
+	if (unlikely(nf_ct_is_dying(ct)))
+		goto out;
 
 	/* See if there's one in the list already, including reverse:
 	   NAT could have grabbed it without realizing, since we're
@@ -636,8 +635,6 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 		    zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)))
 			goto out;
 
-	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
 	   weird delay cases. */
@@ -673,6 +670,7 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 	return NF_ACCEPT;
 
 out:
+	nf_ct_add_to_dying_list(ct);
 	nf_conntrack_double_unlock(hash, reply_hash);
 	NF_CT_STAT_INC(net, insert_failed);
 	local_bh_enable();
@@ -824,22 +822,19 @@ __nf_conntrack_alloc(struct net *net, u16 zone,
 		atomic_dec(&net->ct.count);
 		return ERR_PTR(-ENOMEM);
 	}
-	/*
-	 * Let ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode.next
-	 * and ct->tuplehash[IP_CT_DIR_REPLY].hnnode.next unchanged.
-	 */
-	memset(&ct->tuplehash[IP_CT_DIR_MAX], 0,
-	       offsetof(struct nf_conn, proto) -
-	       offsetof(struct nf_conn, tuplehash[IP_CT_DIR_MAX]));
 	spin_lock_init(&ct->lock);
 	ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple = *orig;
 	ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode.pprev = NULL;
 	ct->tuplehash[IP_CT_DIR_REPLY].tuple = *repl;
 	/* save hash for reusing when confirming */
 	*(unsigned long *)(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev) = hash;
+	ct->status = 0;
 	/* Don't set timer yet: wait for confirmation */
 	setup_timer(&ct->timeout, death_by_timeout, (unsigned long)ct);
 	write_pnet(&ct->ct_net, net);
+	memset(&ct->__nfct_init_offset[0], 0,
+	       offsetof(struct nf_conn, proto) -
+	       offsetof(struct nf_conn, __nfct_init_offset[0]));
 #ifdef CONFIG_NF_CONNTRACK_ZONES
 	if (zone) {
 		struct nf_conntrack_zone *nf_ct_zone;
@@ -1429,12 +1424,6 @@ void nf_ct_free_hashtable(void *hash, unsigned int size)
 }
 EXPORT_SYMBOL_GPL(nf_ct_free_hashtable);
 
-void nf_conntrack_flush_report(struct net *net, u32 portid, int report)
-{
-	nf_ct_iterate_cleanup(net, kill_all, NULL, portid, report);
-}
-EXPORT_SYMBOL_GPL(nf_conntrack_flush_report);
-
 static int untrack_refs(void)
 {
 	int cnt = 0, cpu;
@@ -1627,13 +1616,18 @@ int nf_conntrack_init_start(void)
 	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. */
 	if (!nf_conntrack_htable_size) {
+		/* Idea from tcp.c: use 1/16384 of memory.
+		 * On i386: 32MB machine has 512 buckets.
+		 * >= 1GB machines have 16384 buckets.
+		 * >= 4GB machines have 65536 buckets.
+		 */
 		nf_conntrack_htable_size
 			= (((totalram_pages << PAGE_SHIFT) / 16384)
 			   / sizeof(struct hlist_head));
-		if (totalram_pages > (1024 * 1024 * 1024 / PAGE_SIZE))
+		if (totalram_pages > (4 * (1024 * 1024 * 1024 / PAGE_SIZE)))
+			nf_conntrack_htable_size = 65536;
+		else if (totalram_pages > (1024 * 1024 * 1024 / PAGE_SIZE))
 			nf_conntrack_htable_size = 16384;
 		if (nf_conntrack_htable_size < 32)
 			nf_conntrack_htable_size = 32;
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 91a1837acd0e..7a17070c5dab 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -561,7 +561,9 @@ static int exp_seq_show(struct seq_file *s, void *v)
 				   helper->expect_policy[expect->class].name);
 	}
 
-	return seq_putc(s, '\n');
+	seq_putc(s, '\n');
+
+	return 0;
 }
 
 static const struct seq_operations exp_seq_ops = {
diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c
index 3a3a60b126e0..1d69f5b9748f 100644
--- a/net/netfilter/nf_conntrack_h323_main.c
+++ b/net/netfilter/nf_conntrack_h323_main.c
@@ -728,7 +728,8 @@ static int expect_h245(struct sk_buff *skb, struct nf_conn *ct,
 
 /* If the calling party is on the same side of the forward-to party,
  * we don't need to track the second call */
-static int callforward_do_filter(const union nf_inet_addr *src,
+static int callforward_do_filter(struct net *net,
+				 const union nf_inet_addr *src,
 				 const union nf_inet_addr *dst,
 				 u_int8_t family)
 {
@@ -750,9 +751,9 @@ static int callforward_do_filter(const union nf_inet_addr *src,
 
 		memset(&fl2, 0, sizeof(fl2));
 		fl2.daddr = dst->ip;
-		if (!afinfo->route(&init_net, (struct dst_entry **)&rt1,
+		if (!afinfo->route(net, (struct dst_entry **)&rt1,
 				   flowi4_to_flowi(&fl1), false)) {
-			if (!afinfo->route(&init_net, (struct dst_entry **)&rt2,
+			if (!afinfo->route(net, (struct dst_entry **)&rt2,
 					   flowi4_to_flowi(&fl2), false)) {
 				if (rt_nexthop(rt1, fl1.daddr) ==
 				    rt_nexthop(rt2, fl2.daddr) &&
@@ -774,9 +775,9 @@ static int callforward_do_filter(const union nf_inet_addr *src,
 
 		memset(&fl2, 0, sizeof(fl2));
 		fl2.daddr = dst->in6;
-		if (!afinfo->route(&init_net, (struct dst_entry **)&rt1,
+		if (!afinfo->route(net, (struct dst_entry **)&rt1,
 				   flowi6_to_flowi(&fl1), false)) {
-			if (!afinfo->route(&init_net, (struct dst_entry **)&rt2,
+			if (!afinfo->route(net, (struct dst_entry **)&rt2,
 					   flowi6_to_flowi(&fl2), false)) {
 				if (ipv6_addr_equal(rt6_nexthop(rt1),
 						    rt6_nexthop(rt2)) &&
@@ -807,6 +808,7 @@ static int expect_callforwarding(struct sk_buff *skb,
 	__be16 port;
 	union nf_inet_addr addr;
 	struct nf_conntrack_expect *exp;
+	struct net *net = nf_ct_net(ct);
 	typeof(nat_callforwarding_hook) nat_callforwarding;
 
 	/* Read alternativeAddress */
@@ -816,7 +818,7 @@ static int expect_callforwarding(struct sk_buff *skb,
 	/* If the calling party is on the same side of the forward-to party,
 	 * we don't need to track the second call */
 	if (callforward_filter &&
-	    callforward_do_filter(&addr, &ct->tuplehash[!dir].tuple.src.u3,
+	    callforward_do_filter(net, &addr, &ct->tuplehash[!dir].tuple.src.u3,
 				  nf_ct_l3num(ct))) {
 		pr_debug("nf_ct_q931: Call Forwarding not tracked\n");
 		return 0;
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 5b3eae7d4c9a..bd9d31537905 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -250,7 +250,7 @@ out:
 }
 EXPORT_SYMBOL_GPL(__nf_ct_try_assign_helper);
 
-/* appropiate ct lock protecting must be taken by caller */
+/* appropriate ct lock protecting must be taken by caller */
 static inline int unhelp(struct nf_conntrack_tuple_hash *i,
 			 const struct nf_conntrack_helper *me)
 {
diff --git a/net/netfilter/nf_conntrack_l3proto_generic.c b/net/netfilter/nf_conntrack_l3proto_generic.c
index e7eb807fe07d..cf9ace70bece 100644
--- a/net/netfilter/nf_conntrack_l3proto_generic.c
+++ b/net/netfilter/nf_conntrack_l3proto_generic.c
@@ -49,10 +49,9 @@ static bool generic_invert_tuple(struct nf_conntrack_tuple *tuple,
 	return true;
 }
 
-static int generic_print_tuple(struct seq_file *s,
-			    const struct nf_conntrack_tuple *tuple)
+static void generic_print_tuple(struct seq_file *s,
+				const struct nf_conntrack_tuple *tuple)
 {
-	return 0;
 }
 
 static int generic_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 1bd9ed9e62f6..d1c23940a86a 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -749,13 +749,47 @@ static int ctnetlink_done(struct netlink_callback *cb)
 	return 0;
 }
 
-struct ctnetlink_dump_filter {
+struct ctnetlink_filter {
 	struct {
 		u_int32_t val;
 		u_int32_t mask;
 	} mark;
 };
 
+static struct ctnetlink_filter *
+ctnetlink_alloc_filter(const struct nlattr * const cda[])
+{
+#ifdef CONFIG_NF_CONNTRACK_MARK
+	struct ctnetlink_filter *filter;
+
+	filter = kzalloc(sizeof(*filter), GFP_KERNEL);
+	if (filter == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	filter->mark.val = ntohl(nla_get_be32(cda[CTA_MARK]));
+	filter->mark.mask = ntohl(nla_get_be32(cda[CTA_MARK_MASK]));
+
+	return filter;
+#else
+	return ERR_PTR(-EOPNOTSUPP);
+#endif
+}
+
+static int ctnetlink_filter_match(struct nf_conn *ct, void *data)
+{
+	struct ctnetlink_filter *filter = data;
+
+	if (filter == NULL)
+		return 1;
+
+#ifdef CONFIG_NF_CONNTRACK_MARK
+	if ((ct->mark & filter->mark.mask) == filter->mark.val)
+		return 1;
+#endif
+
+	return 0;
+}
+
 static int
 ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 {
@@ -768,10 +802,6 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 	int res;
 	spinlock_t *lockp;
 
-#ifdef CONFIG_NF_CONNTRACK_MARK
-	const struct ctnetlink_dump_filter *filter = cb->data;
-#endif
-
 	last = (struct nf_conn *)cb->args[1];
 
 	local_bh_disable();
@@ -798,12 +828,9 @@ restart:
 					continue;
 				cb->args[1] = 0;
 			}
-#ifdef CONFIG_NF_CONNTRACK_MARK
-			if (filter && !((ct->mark & filter->mark.mask) ==
-					filter->mark.val)) {
+			if (!ctnetlink_filter_match(ct, cb->data))
 				continue;
-			}
-#endif
+
 			rcu_read_lock();
 			res =
 			ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid,
@@ -1001,6 +1028,25 @@ static const struct nla_policy ct_nla_policy[CTA_MAX+1] = {
 				    .len = NF_CT_LABELS_MAX_SIZE },
 };
 
+static int ctnetlink_flush_conntrack(struct net *net,
+				     const struct nlattr * const cda[],
+				     u32 portid, int report)
+{
+	struct ctnetlink_filter *filter = NULL;
+
+	if (cda[CTA_MARK] && cda[CTA_MARK_MASK]) {
+		filter = ctnetlink_alloc_filter(cda);
+		if (IS_ERR(filter))
+			return PTR_ERR(filter);
+	}
+
+	nf_ct_iterate_cleanup(net, ctnetlink_filter_match, filter,
+			      portid, report);
+	kfree(filter);
+
+	return 0;
+}
+
 static int
 ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb,
 			const struct nlmsghdr *nlh,
@@ -1024,11 +1070,9 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb,
 	else if (cda[CTA_TUPLE_REPLY])
 		err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY, u3);
 	else {
-		/* Flush the whole table */
-		nf_conntrack_flush_report(net,
-					 NETLINK_CB(skb).portid,
-					 nlmsg_report(nlh));
-		return 0;
+		return ctnetlink_flush_conntrack(net, cda,
+						 NETLINK_CB(skb).portid,
+						 nlmsg_report(nlh));
 	}
 
 	if (err < 0)
@@ -1076,21 +1120,16 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb,
 			.dump = ctnetlink_dump_table,
 			.done = ctnetlink_done,
 		};
-#ifdef CONFIG_NF_CONNTRACK_MARK
+
 		if (cda[CTA_MARK] && cda[CTA_MARK_MASK]) {
-			struct ctnetlink_dump_filter *filter;
+			struct ctnetlink_filter *filter;
 
-			filter = kzalloc(sizeof(struct ctnetlink_dump_filter),
-					 GFP_ATOMIC);
-			if (filter == NULL)
-				return -ENOMEM;
+			filter = ctnetlink_alloc_filter(cda);
+			if (IS_ERR(filter))
+				return PTR_ERR(filter);
 
-			filter->mark.val = ntohl(nla_get_be32(cda[CTA_MARK]));
-			filter->mark.mask =
-				ntohl(nla_get_be32(cda[CTA_MARK_MASK]));
 			c.data = filter;
 		}
-#endif
 		return netlink_dump_start(ctnl, skb, nlh, &c);
 	}
 
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index cb372f96f10d..6dd995c7c72b 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -618,17 +618,17 @@ out_invalid:
 	return -NF_ACCEPT;
 }
 
-static int dccp_print_tuple(struct seq_file *s,
-			    const struct nf_conntrack_tuple *tuple)
+static void dccp_print_tuple(struct seq_file *s,
+			     const struct nf_conntrack_tuple *tuple)
 {
-	return seq_printf(s, "sport=%hu dport=%hu ",
-			  ntohs(tuple->src.u.dccp.port),
-			  ntohs(tuple->dst.u.dccp.port));
+	seq_printf(s, "sport=%hu dport=%hu ",
+		   ntohs(tuple->src.u.dccp.port),
+		   ntohs(tuple->dst.u.dccp.port));
 }
 
-static int dccp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
+static void dccp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
 {
-	return seq_printf(s, "%s ", dccp_state_names[ct->proto.dccp.state]);
+	seq_printf(s, "%s ", dccp_state_names[ct->proto.dccp.state]);
 }
 
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c
index 957c1db66652..60865f110309 100644
--- a/net/netfilter/nf_conntrack_proto_generic.c
+++ b/net/netfilter/nf_conntrack_proto_generic.c
@@ -63,10 +63,9 @@ static bool generic_invert_tuple(struct nf_conntrack_tuple *tuple,
 }
 
 /* Print out the per-protocol part of the tuple. */
-static int generic_print_tuple(struct seq_file *s,
-			       const struct nf_conntrack_tuple *tuple)
+static void generic_print_tuple(struct seq_file *s,
+				const struct nf_conntrack_tuple *tuple)
 {
-	return 0;
 }
 
 static unsigned int *generic_get_timeouts(struct net *net)
diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c
index d5665739e3b1..7648674f29c3 100644
--- a/net/netfilter/nf_conntrack_proto_gre.c
+++ b/net/netfilter/nf_conntrack_proto_gre.c
@@ -226,20 +226,20 @@ static bool gre_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
 }
 
 /* print gre part of tuple */
-static int gre_print_tuple(struct seq_file *s,
-			   const struct nf_conntrack_tuple *tuple)
+static void gre_print_tuple(struct seq_file *s,
+			    const struct nf_conntrack_tuple *tuple)
 {
-	return seq_printf(s, "srckey=0x%x dstkey=0x%x ",
-			  ntohs(tuple->src.u.gre.key),
-			  ntohs(tuple->dst.u.gre.key));
+	seq_printf(s, "srckey=0x%x dstkey=0x%x ",
+		   ntohs(tuple->src.u.gre.key),
+		   ntohs(tuple->dst.u.gre.key));
 }
 
 /* print private data for conntrack */
-static int gre_print_conntrack(struct seq_file *s, struct nf_conn *ct)
+static void gre_print_conntrack(struct seq_file *s, struct nf_conn *ct)
 {
-	return seq_printf(s, "timeout=%u, stream_timeout=%u ",
-			  (ct->proto.gre.timeout / HZ),
-			  (ct->proto.gre.stream_timeout / HZ));
+	seq_printf(s, "timeout=%u, stream_timeout=%u ",
+		   (ct->proto.gre.timeout / HZ),
+		   (ct->proto.gre.stream_timeout / HZ));
 }
 
 static unsigned int *gre_get_timeouts(struct net *net)
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index 1314d33f6bcf..b45da90fad32 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -166,16 +166,16 @@ static bool sctp_invert_tuple(struct nf_conntrack_tuple *tuple,
 }
 
 /* Print out the per-protocol part of the tuple. */
-static int sctp_print_tuple(struct seq_file *s,
-			    const struct nf_conntrack_tuple *tuple)
+static void sctp_print_tuple(struct seq_file *s,
+			     const struct nf_conntrack_tuple *tuple)
 {
-	return seq_printf(s, "sport=%hu dport=%hu ",
-			  ntohs(tuple->src.u.sctp.port),
-			  ntohs(tuple->dst.u.sctp.port));
+	seq_printf(s, "sport=%hu dport=%hu ",
+		   ntohs(tuple->src.u.sctp.port),
+		   ntohs(tuple->dst.u.sctp.port));
 }
 
 /* Print out the private part of the conntrack. */
-static int sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
+static void sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
 {
 	enum sctp_conntrack state;
 
@@ -183,7 +183,7 @@ static int sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
 	state = ct->proto.sctp.state;
 	spin_unlock_bh(&ct->lock);
 
-	return seq_printf(s, "%s ", sctp_conntrack_names[state]);
+	seq_printf(s, "%s ", sctp_conntrack_names[state]);
 }
 
 #define for_each_sctp_chunk(skb, sch, _sch, offset, dataoff, count)	\
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index d87b6423ffb2..70383de72054 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -202,7 +202,7 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = {
  *	sES -> sES	:-)
  *	sFW -> sCW	Normal close request answered by ACK.
  *	sCW -> sCW
- *	sLA -> sTW	Last ACK detected.
+ *	sLA -> sTW	Last ACK detected (RFC5961 challenged)
  *	sTW -> sTW	Retransmitted last ACK. Remain in the same state.
  *	sCL -> sCL
  */
@@ -261,7 +261,7 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = {
  *	sES -> sES	:-)
  *	sFW -> sCW	Normal close request answered by ACK.
  *	sCW -> sCW
- *	sLA -> sTW	Last ACK detected.
+ *	sLA -> sTW	Last ACK detected (RFC5961 challenged)
  *	sTW -> sTW	Retransmitted last ACK.
  *	sCL -> sCL
  */
@@ -302,16 +302,16 @@ static bool tcp_invert_tuple(struct nf_conntrack_tuple *tuple,
 }
 
 /* Print out the per-protocol part of the tuple. */
-static int tcp_print_tuple(struct seq_file *s,
-			   const struct nf_conntrack_tuple *tuple)
+static void tcp_print_tuple(struct seq_file *s,
+			    const struct nf_conntrack_tuple *tuple)
 {
-	return seq_printf(s, "sport=%hu dport=%hu ",
-			  ntohs(tuple->src.u.tcp.port),
-			  ntohs(tuple->dst.u.tcp.port));
+	seq_printf(s, "sport=%hu dport=%hu ",
+		   ntohs(tuple->src.u.tcp.port),
+		   ntohs(tuple->dst.u.tcp.port));
 }
 
 /* Print out the private part of the conntrack. */
-static int tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
+static void tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
 {
 	enum tcp_conntrack state;
 
@@ -319,7 +319,7 @@ static int tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
 	state = ct->proto.tcp.state;
 	spin_unlock_bh(&ct->lock);
 
-	return seq_printf(s, "%s ", tcp_conntrack_names[state]);
+	seq_printf(s, "%s ", tcp_conntrack_names[state]);
 }
 
 static unsigned int get_conntrack_index(const struct tcphdr *tcph)
@@ -906,6 +906,7 @@ static int tcp_packet(struct nf_conn *ct,
 					1 : ct->proto.tcp.last_win;
 			ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_scale =
 				ct->proto.tcp.last_wscale;
+			ct->proto.tcp.last_flags &= ~IP_CT_EXP_CHALLENGE_ACK;
 			ct->proto.tcp.seen[ct->proto.tcp.last_dir].flags =
 				ct->proto.tcp.last_flags;
 			memset(&ct->proto.tcp.seen[dir], 0,
@@ -923,7 +924,9 @@ static int tcp_packet(struct nf_conn *ct,
 		 * may be in sync but we are not. In that case, we annotate
 		 * the TCP options and let the packet go through. If it is a
 		 * valid SYN packet, the server will reply with a SYN/ACK, and
-		 * then we'll get in sync. Otherwise, the server ignores it. */
+		 * then we'll get in sync. Otherwise, the server potentially
+		 * responds with a challenge ACK if implementing RFC5961.
+		 */
 		if (index == TCP_SYN_SET && dir == IP_CT_DIR_ORIGINAL) {
 			struct ip_ct_tcp_state seen = {};
 
@@ -939,6 +942,13 @@ static int tcp_packet(struct nf_conn *ct,
 				ct->proto.tcp.last_flags |=
 					IP_CT_TCP_FLAG_SACK_PERM;
 			}
+			/* Mark the potential for RFC5961 challenge ACK,
+			 * this pose a special problem for LAST_ACK state
+			 * as ACK is intrepretated as ACKing last FIN.
+			 */
+			if (old_state == TCP_CONNTRACK_LAST_ACK)
+				ct->proto.tcp.last_flags |=
+					IP_CT_EXP_CHALLENGE_ACK;
 		}
 		spin_unlock_bh(&ct->lock);
 		if (LOG_INVALID(net, IPPROTO_TCP))
@@ -970,6 +980,25 @@ static int tcp_packet(struct nf_conn *ct,
 			nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL,
 				  "nf_ct_tcp: invalid state ");
 		return -NF_ACCEPT;
+	case TCP_CONNTRACK_TIME_WAIT:
+		/* RFC5961 compliance cause stack to send "challenge-ACK"
+		 * e.g. in response to spurious SYNs.  Conntrack MUST
+		 * not believe this ACK is acking last FIN.
+		 */
+		if (old_state == TCP_CONNTRACK_LAST_ACK &&
+		    index == TCP_ACK_SET &&
+		    ct->proto.tcp.last_dir != dir &&
+		    ct->proto.tcp.last_index == TCP_SYN_SET &&
+		    (ct->proto.tcp.last_flags & IP_CT_EXP_CHALLENGE_ACK)) {
+			/* Detected RFC5961 challenge ACK */
+			ct->proto.tcp.last_flags &= ~IP_CT_EXP_CHALLENGE_ACK;
+			spin_unlock_bh(&ct->lock);
+			if (LOG_INVALID(net, IPPROTO_TCP))
+				nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL,
+				      "nf_ct_tcp: challenge-ACK ignored ");
+			return NF_ACCEPT; /* Don't change state */
+		}
+		break;
 	case TCP_CONNTRACK_CLOSE:
 		if (index == TCP_RST_SET
 		    && (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET)
diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c
index 9d7721cbce4b..6957281ffee5 100644
--- a/net/netfilter/nf_conntrack_proto_udp.c
+++ b/net/netfilter/nf_conntrack_proto_udp.c
@@ -63,12 +63,12 @@ static bool udp_invert_tuple(struct nf_conntrack_tuple *tuple,
 }
 
 /* Print out the per-protocol part of the tuple. */
-static int udp_print_tuple(struct seq_file *s,
-			   const struct nf_conntrack_tuple *tuple)
+static void udp_print_tuple(struct seq_file *s,
+			    const struct nf_conntrack_tuple *tuple)
 {
-	return seq_printf(s, "sport=%hu dport=%hu ",
-			  ntohs(tuple->src.u.udp.port),
-			  ntohs(tuple->dst.u.udp.port));
+	seq_printf(s, "sport=%hu dport=%hu ",
+		   ntohs(tuple->src.u.udp.port),
+		   ntohs(tuple->dst.u.udp.port));
 }
 
 static unsigned int *udp_get_timeouts(struct net *net)
diff --git a/net/netfilter/nf_conntrack_proto_udplite.c b/net/netfilter/nf_conntrack_proto_udplite.c
index 2750e6c69f82..c5903d1649f9 100644
--- a/net/netfilter/nf_conntrack_proto_udplite.c
+++ b/net/netfilter/nf_conntrack_proto_udplite.c
@@ -71,12 +71,12 @@ static bool udplite_invert_tuple(struct nf_conntrack_tuple *tuple,
 }
 
 /* Print out the per-protocol part of the tuple. */
-static int udplite_print_tuple(struct seq_file *s,
-			       const struct nf_conntrack_tuple *tuple)
+static void udplite_print_tuple(struct seq_file *s,
+				const struct nf_conntrack_tuple *tuple)
 {
-	return seq_printf(s, "sport=%hu dport=%hu ",
-			  ntohs(tuple->src.u.udp.port),
-			  ntohs(tuple->dst.u.udp.port));
+	seq_printf(s, "sport=%hu dport=%hu ",
+		   ntohs(tuple->src.u.udp.port),
+		   ntohs(tuple->dst.u.udp.port));
 }
 
 static unsigned int *udplite_get_timeouts(struct net *net)
diff --git a/net/netfilter/nf_conntrack_seqadj.c b/net/netfilter/nf_conntrack_seqadj.c
index f6e2ae91a80b..ce3e840c8704 100644
--- a/net/netfilter/nf_conntrack_seqadj.c
+++ b/net/netfilter/nf_conntrack_seqadj.c
@@ -98,9 +98,9 @@ static void nf_ct_sack_block_adjust(struct sk_buff *skb,
 			new_end_seq = htonl(ntohl(sack->end_seq) -
 				      seq->offset_before);
 
-		pr_debug("sack_adjust: start_seq: %d->%d, end_seq: %d->%d\n",
-			 ntohl(sack->start_seq), new_start_seq,
-			 ntohl(sack->end_seq), new_end_seq);
+		pr_debug("sack_adjust: start_seq: %u->%u, end_seq: %u->%u\n",
+			 ntohl(sack->start_seq), ntohl(new_start_seq),
+			 ntohl(sack->end_seq), ntohl(new_end_seq));
 
 		inet_proto_csum_replace4(&tcph->check, skb,
 					 sack->start_seq, new_start_seq, 0);
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index cf65a1e040dd..fc823fa5dcf5 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -36,12 +36,13 @@
 MODULE_LICENSE("GPL");
 
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
-int
+void
 print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple,
             const struct nf_conntrack_l3proto *l3proto,
             const struct nf_conntrack_l4proto *l4proto)
 {
-	return l3proto->print_tuple(s, tuple) || l4proto->print_tuple(s, tuple);
+	l3proto->print_tuple(s, tuple);
+	l4proto->print_tuple(s, tuple);
 }
 EXPORT_SYMBOL_GPL(print_tuple);
 
@@ -119,7 +120,7 @@ static void ct_seq_stop(struct seq_file *s, void *v)
 }
 
 #ifdef CONFIG_NF_CONNTRACK_SECMARK
-static int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct)
+static void ct_show_secctx(struct seq_file *s, const struct nf_conn *ct)
 {
 	int ret;
 	u32 len;
@@ -127,22 +128,20 @@ static int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct)
 
 	ret = security_secid_to_secctx(ct->secmark, &secctx, &len);
 	if (ret)
-		return 0;
+		return;
 
-	ret = seq_printf(s, "secctx=%s ", secctx);
+	seq_printf(s, "secctx=%s ", secctx);
 
 	security_release_secctx(secctx, len);
-	return ret;
 }
 #else
-static inline int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct)
+static inline void ct_show_secctx(struct seq_file *s, const struct nf_conn *ct)
 {
-	return 0;
 }
 #endif
 
 #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
-static int ct_show_delta_time(struct seq_file *s, const struct nf_conn *ct)
+static void ct_show_delta_time(struct seq_file *s, const struct nf_conn *ct)
 {
 	struct ct_iter_state *st = s->private;
 	struct nf_conn_tstamp *tstamp;
@@ -156,16 +155,15 @@ static int ct_show_delta_time(struct seq_file *s, const struct nf_conn *ct)
 		else
 			delta_time = 0;
 
-		return seq_printf(s, "delta-time=%llu ",
-				  (unsigned long long)delta_time);
+		seq_printf(s, "delta-time=%llu ",
+			   (unsigned long long)delta_time);
 	}
-	return 0;
+	return;
 }
 #else
-static inline int
+static inline void
 ct_show_delta_time(struct seq_file *s, const struct nf_conn *ct)
 {
-	return 0;
 }
 #endif
 
@@ -192,55 +190,54 @@ static int ct_seq_show(struct seq_file *s, void *v)
 	NF_CT_ASSERT(l4proto);
 
 	ret = -ENOSPC;
-	if (seq_printf(s, "%-8s %u %-8s %u %ld ",
-		       l3proto->name, nf_ct_l3num(ct),
-		       l4proto->name, nf_ct_protonum(ct),
-		       timer_pending(&ct->timeout)
-		       ? (long)(ct->timeout.expires - jiffies)/HZ : 0) != 0)
-		goto release;
+	seq_printf(s, "%-8s %u %-8s %u %ld ",
+		   l3proto->name, nf_ct_l3num(ct),
+		   l4proto->name, nf_ct_protonum(ct),
+		   timer_pending(&ct->timeout)
+		   ? (long)(ct->timeout.expires - jiffies)/HZ : 0);
 
-	if (l4proto->print_conntrack && l4proto->print_conntrack(s, ct))
-		goto release;
+	if (l4proto->print_conntrack)
+		l4proto->print_conntrack(s, ct);
+
+	print_tuple(s, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
+		    l3proto, l4proto);
 
-	if (print_tuple(s, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
-			l3proto, l4proto))
+	if (seq_has_overflowed(s))
 		goto release;
 
 	if (seq_print_acct(s, ct, IP_CT_DIR_ORIGINAL))
 		goto release;
 
 	if (!(test_bit(IPS_SEEN_REPLY_BIT, &ct->status)))
-		if (seq_printf(s, "[UNREPLIED] "))
-			goto release;
+		seq_printf(s, "[UNREPLIED] ");
 
-	if (print_tuple(s, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
-			l3proto, l4proto))
-		goto release;
+	print_tuple(s, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
+		    l3proto, l4proto);
 
 	if (seq_print_acct(s, ct, IP_CT_DIR_REPLY))
 		goto release;
 
 	if (test_bit(IPS_ASSURED_BIT, &ct->status))
-		if (seq_printf(s, "[ASSURED] "))
-			goto release;
+		seq_printf(s, "[ASSURED] ");
 
-#if defined(CONFIG_NF_CONNTRACK_MARK)
-	if (seq_printf(s, "mark=%u ", ct->mark))
+	if (seq_has_overflowed(s))
 		goto release;
+
+#if defined(CONFIG_NF_CONNTRACK_MARK)
+	seq_printf(s, "mark=%u ", ct->mark);
 #endif
 
-	if (ct_show_secctx(s, ct))
-		goto release;
+	ct_show_secctx(s, ct);
 
 #ifdef CONFIG_NF_CONNTRACK_ZONES
-	if (seq_printf(s, "zone=%u ", nf_ct_zone(ct)))
-		goto release;
+	seq_printf(s, "zone=%u ", nf_ct_zone(ct));
 #endif
 
-	if (ct_show_delta_time(s, ct))
-		goto release;
+	ct_show_delta_time(s, ct);
+
+	seq_printf(s, "use=%u\n", atomic_read(&ct->ct_general.use));
 
-	if (seq_printf(s, "use=%u\n", atomic_read(&ct->ct_general.use)))
+	if (seq_has_overflowed(s))
 		goto release;
 
 	ret = 0;
diff --git a/net/netfilter/nf_internals.h b/net/netfilter/nf_internals.h
index 61a3c927e63c..ea7f36784b3d 100644
--- a/net/netfilter/nf_internals.h
+++ b/net/netfilter/nf_internals.h
@@ -14,16 +14,11 @@
 
 /* core.c */
 unsigned int nf_iterate(struct list_head *head, struct sk_buff *skb,
-			unsigned int hook, const struct net_device *indev,
-			const struct net_device *outdev,
-			struct nf_hook_ops **elemp,
-			int (*okfn)(struct sk_buff *), int hook_thresh);
+			struct nf_hook_state *state, struct nf_hook_ops **elemp);
 
 /* nf_queue.c */
-int nf_queue(struct sk_buff *skb, struct nf_hook_ops *elem, u_int8_t pf,
-	     unsigned int hook, struct net_device *indev,
-	     struct net_device *outdev, int (*okfn)(struct sk_buff *),
-	     unsigned int queuenum);
+int nf_queue(struct sk_buff *skb, struct nf_hook_ops *elem,
+	     struct nf_hook_state *state, unsigned int queuenum);
 int __init netfilter_queue_init(void);
 
 /* nf_log.c */
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index d7197649dba6..675d12c69e32 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -19,6 +19,9 @@
 static struct nf_logger __rcu *loggers[NFPROTO_NUMPROTO][NF_LOG_TYPE_MAX] __read_mostly;
 static DEFINE_MUTEX(nf_log_mutex);
 
+#define nft_log_dereference(logger) \
+	rcu_dereference_protected(logger, lockdep_is_held(&nf_log_mutex))
+
 static struct nf_logger *__find_logger(int pf, const char *str_logger)
 {
 	struct nf_logger *log;
@@ -28,8 +31,7 @@ static struct nf_logger *__find_logger(int pf, const char *str_logger)
 		if (loggers[pf][i] == NULL)
 			continue;
 
-		log = rcu_dereference_protected(loggers[pf][i],
-						lockdep_is_held(&nf_log_mutex));
+		log = nft_log_dereference(loggers[pf][i]);
 		if (!strncasecmp(str_logger, log->name, strlen(log->name)))
 			return log;
 	}
@@ -45,8 +47,7 @@ void nf_log_set(struct net *net, u_int8_t pf, const struct nf_logger *logger)
 		return;
 
 	mutex_lock(&nf_log_mutex);
-	log = rcu_dereference_protected(net->nf.nf_loggers[pf],
-					lockdep_is_held(&nf_log_mutex));
+	log = nft_log_dereference(net->nf.nf_loggers[pf]);
 	if (log == NULL)
 		rcu_assign_pointer(net->nf.nf_loggers[pf], logger);
 
@@ -61,8 +62,7 @@ void nf_log_unset(struct net *net, const struct nf_logger *logger)
 
 	mutex_lock(&nf_log_mutex);
 	for (i = 0; i < NFPROTO_NUMPROTO; i++) {
-		log = rcu_dereference_protected(net->nf.nf_loggers[i],
-				lockdep_is_held(&nf_log_mutex));
+		log = nft_log_dereference(net->nf.nf_loggers[i]);
 		if (log == logger)
 			RCU_INIT_POINTER(net->nf.nf_loggers[i], NULL);
 	}
@@ -75,6 +75,7 @@ EXPORT_SYMBOL(nf_log_unset);
 int nf_log_register(u_int8_t pf, struct nf_logger *logger)
 {
 	int i;
+	int ret = 0;
 
 	if (pf >= ARRAY_SIZE(init_net.nf.nf_loggers))
 		return -EINVAL;
@@ -82,16 +83,25 @@ int nf_log_register(u_int8_t pf, struct nf_logger *logger)
 	mutex_lock(&nf_log_mutex);
 
 	if (pf == NFPROTO_UNSPEC) {
+		for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) {
+			if (rcu_access_pointer(loggers[i][logger->type])) {
+				ret = -EEXIST;
+				goto unlock;
+			}
+		}
 		for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++)
 			rcu_assign_pointer(loggers[i][logger->type], logger);
 	} else {
-		/* register at end of list to honor first register win */
+		if (rcu_access_pointer(loggers[pf][logger->type])) {
+			ret = -EEXIST;
+			goto unlock;
+		}
 		rcu_assign_pointer(loggers[pf][logger->type], logger);
 	}
 
+unlock:
 	mutex_unlock(&nf_log_mutex);
-
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL(nf_log_register);
 
@@ -144,8 +154,7 @@ int nf_logger_find_get(int pf, enum nf_log_type type)
 	struct nf_logger *logger;
 	int ret = -ENOENT;
 
-	logger = loggers[pf][type];
-	if (logger == NULL)
+	if (rcu_access_pointer(loggers[pf][type]) == NULL)
 		request_module("nf-logger-%u-%u", pf, type);
 
 	rcu_read_lock();
@@ -203,6 +212,30 @@ void nf_log_packet(struct net *net,
 }
 EXPORT_SYMBOL(nf_log_packet);
 
+void nf_log_trace(struct net *net,
+		  u_int8_t pf,
+		  unsigned int hooknum,
+		  const struct sk_buff *skb,
+		  const struct net_device *in,
+		  const struct net_device *out,
+		  const struct nf_loginfo *loginfo, const char *fmt, ...)
+{
+	va_list args;
+	char prefix[NF_LOG_PREFIXLEN];
+	const struct nf_logger *logger;
+
+	rcu_read_lock();
+	logger = rcu_dereference(net->nf.nf_loggers[pf]);
+	if (logger) {
+		va_start(args, fmt);
+		vsnprintf(prefix, sizeof(prefix), fmt, args);
+		va_end(args);
+		logger->logfn(net, pf, hooknum, skb, in, out, loginfo, prefix);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL(nf_log_trace);
+
 #define S_SIZE (1024 - (sizeof(unsigned int) + 1))
 
 struct nf_log_buf {
@@ -294,37 +327,37 @@ static int seq_show(struct seq_file *s, void *v)
 {
 	loff_t *pos = v;
 	const struct nf_logger *logger;
-	int i, ret;
+	int i;
 	struct net *net = seq_file_net(s);
 
-	logger = rcu_dereference_protected(net->nf.nf_loggers[*pos],
-					   lockdep_is_held(&nf_log_mutex));
+	logger = nft_log_dereference(net->nf.nf_loggers[*pos]);
 
 	if (!logger)
-		ret = seq_printf(s, "%2lld NONE (", *pos);
+		seq_printf(s, "%2lld NONE (", *pos);
 	else
-		ret = seq_printf(s, "%2lld %s (", *pos, logger->name);
+		seq_printf(s, "%2lld %s (", *pos, logger->name);
 
-	if (ret < 0)
-		return ret;
+	if (seq_has_overflowed(s))
+		return -ENOSPC;
 
 	for (i = 0; i < NF_LOG_TYPE_MAX; i++) {
 		if (loggers[*pos][i] == NULL)
 			continue;
 
-		logger = rcu_dereference_protected(loggers[*pos][i],
-					   lockdep_is_held(&nf_log_mutex));
-		ret = seq_printf(s, "%s", logger->name);
-		if (ret < 0)
-			return ret;
-		if (i == 0 && loggers[*pos][i + 1] != NULL) {
-			ret = seq_printf(s, ",");
-			if (ret < 0)
-				return ret;
-		}
+		logger = nft_log_dereference(loggers[*pos][i]);
+		seq_printf(s, "%s", logger->name);
+		if (i == 0 && loggers[*pos][i + 1] != NULL)
+			seq_printf(s, ",");
+
+		if (seq_has_overflowed(s))
+			return -ENOSPC;
 	}
 
-	return seq_printf(s, ")\n");
+	seq_printf(s, ")\n");
+
+	if (seq_has_overflowed(s))
+		return -ENOSPC;
+	return 0;
 }
 
 static const struct seq_operations nflog_seq_ops = {
@@ -385,8 +418,7 @@ static int nf_log_proc_dostring(struct ctl_table *table, int write,
 		mutex_unlock(&nf_log_mutex);
 	} else {
 		mutex_lock(&nf_log_mutex);
-		logger = rcu_dereference_protected(net->nf.nf_loggers[tindex],
-						   lockdep_is_held(&nf_log_mutex));
+		logger = nft_log_dereference(net->nf.nf_loggers[tindex]);
 		if (!logger)
 			table->data = "NONE";
 		else
@@ -417,8 +449,7 @@ static int netfilter_log_sysctl_init(struct net *net)
 			nf_log_sysctl_table[i].procname	=
 				nf_log_sysctl_fnames[i];
 			nf_log_sysctl_table[i].data = NULL;
-			nf_log_sysctl_table[i].maxlen =
-				NFLOGGER_NAME_LEN * sizeof(char);
+			nf_log_sysctl_table[i].maxlen = NFLOGGER_NAME_LEN;
 			nf_log_sysctl_table[i].mode = 0644;
 			nf_log_sysctl_table[i].proc_handler =
 				nf_log_proc_dostring;
diff --git a/net/netfilter/nf_log_common.c b/net/netfilter/nf_log_common.c
index a2233e77cf39..a5aa5967b8e1 100644
--- a/net/netfilter/nf_log_common.c
+++ b/net/netfilter/nf_log_common.c
@@ -17,6 +17,7 @@
 #include <net/route.h>
 
 #include <linux/netfilter.h>
+#include <linux/netfilter_bridge.h>
 #include <linux/netfilter/xt_LOG.h>
 #include <net/netfilter/nf_log.h>
 
@@ -133,7 +134,7 @@ EXPORT_SYMBOL_GPL(nf_log_dump_tcp_header);
 
 void nf_log_dump_sk_uid_gid(struct nf_log_buf *m, struct sock *sk)
 {
-	if (!sk || sk->sk_state == TCP_TIME_WAIT)
+	if (!sk || !sk_fullsock(sk))
 		return;
 
 	read_lock_bh(&sk->sk_callback_lock);
@@ -163,10 +164,10 @@ nf_log_dump_packet_common(struct nf_log_buf *m, u_int8_t pf,
 		const struct net_device *physindev;
 		const struct net_device *physoutdev;
 
-		physindev = skb->nf_bridge->physindev;
+		physindev = nf_bridge_get_physindev(skb);
 		if (physindev && in != physindev)
 			nf_log_buf_add(m, "PHYSIN=%s ", physindev->name);
-		physoutdev = skb->nf_bridge->physoutdev;
+		physoutdev = nf_bridge_get_physoutdev(skb);
 		if (physoutdev && out != physoutdev)
 			nf_log_buf_add(m, "PHYSOUT=%s ", physoutdev->name);
 	}
diff --git a/net/netfilter/nf_nat_redirect.c b/net/netfilter/nf_nat_redirect.c
new file mode 100644
index 000000000000..97b75f9bfbcd
--- /dev/null
+++ b/net/netfilter/nf_nat_redirect.c
@@ -0,0 +1,127 @@
+/*
+ * (C) 1999-2001 Paul `Rusty' Russell
+ * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
+ * Copyright (c) 2011 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.
+ *
+ * Based on Rusty Russell's IPv4 REDIRECT target. Development of IPv6
+ * NAT funded by Astaro.
+ */
+
+#include <linux/if.h>
+#include <linux/inetdevice.h>
+#include <linux/ip.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/netfilter.h>
+#include <linux/types.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/netfilter/x_tables.h>
+#include <net/addrconf.h>
+#include <net/checksum.h>
+#include <net/protocol.h>
+#include <net/netfilter/nf_nat.h>
+#include <net/netfilter/nf_nat_redirect.h>
+
+unsigned int
+nf_nat_redirect_ipv4(struct sk_buff *skb,
+		     const struct nf_nat_ipv4_multi_range_compat *mr,
+		     unsigned int hooknum)
+{
+	struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	__be32 newdst;
+	struct nf_nat_range newrange;
+
+	NF_CT_ASSERT(hooknum == NF_INET_PRE_ROUTING ||
+		     hooknum == NF_INET_LOCAL_OUT);
+
+	ct = nf_ct_get(skb, &ctinfo);
+	NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED));
+
+	/* Local packets: make them go to loopback */
+	if (hooknum == NF_INET_LOCAL_OUT) {
+		newdst = htonl(0x7F000001);
+	} else {
+		struct in_device *indev;
+		struct in_ifaddr *ifa;
+
+		newdst = 0;
+
+		rcu_read_lock();
+		indev = __in_dev_get_rcu(skb->dev);
+		if (indev != NULL) {
+			ifa = indev->ifa_list;
+			newdst = ifa->ifa_local;
+		}
+		rcu_read_unlock();
+
+		if (!newdst)
+			return NF_DROP;
+	}
+
+	/* Transfer from original range. */
+	memset(&newrange.min_addr, 0, sizeof(newrange.min_addr));
+	memset(&newrange.max_addr, 0, sizeof(newrange.max_addr));
+	newrange.flags	     = mr->range[0].flags | NF_NAT_RANGE_MAP_IPS;
+	newrange.min_addr.ip = newdst;
+	newrange.max_addr.ip = newdst;
+	newrange.min_proto   = mr->range[0].min;
+	newrange.max_proto   = mr->range[0].max;
+
+	/* Hand modified range to generic setup. */
+	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_DST);
+}
+EXPORT_SYMBOL_GPL(nf_nat_redirect_ipv4);
+
+static const struct in6_addr loopback_addr = IN6ADDR_LOOPBACK_INIT;
+
+unsigned int
+nf_nat_redirect_ipv6(struct sk_buff *skb, const struct nf_nat_range *range,
+		     unsigned int hooknum)
+{
+	struct nf_nat_range newrange;
+	struct in6_addr newdst;
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *ct;
+
+	ct = nf_ct_get(skb, &ctinfo);
+	if (hooknum == NF_INET_LOCAL_OUT) {
+		newdst = loopback_addr;
+	} else {
+		struct inet6_dev *idev;
+		struct inet6_ifaddr *ifa;
+		bool addr = false;
+
+		rcu_read_lock();
+		idev = __in6_dev_get(skb->dev);
+		if (idev != NULL) {
+			list_for_each_entry(ifa, &idev->addr_list, if_list) {
+				newdst = ifa->addr;
+				addr = true;
+				break;
+			}
+		}
+		rcu_read_unlock();
+
+		if (!addr)
+			return NF_DROP;
+	}
+
+	newrange.flags		= range->flags | NF_NAT_RANGE_MAP_IPS;
+	newrange.min_addr.in6	= newdst;
+	newrange.max_addr.in6	= newdst;
+	newrange.min_proto	= range->min_proto;
+	newrange.max_proto	= range->max_proto;
+
+	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_DST);
+}
+EXPORT_SYMBOL_GPL(nf_nat_redirect_ipv6);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 4c8b68e5fa16..2e88032cd5ad 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -10,6 +10,7 @@
 #include <linux/proc_fs.h>
 #include <linux/skbuff.h>
 #include <linux/netfilter.h>
+#include <linux/netfilter_bridge.h>
 #include <linux/seq_file.h>
 #include <linux/rcupdate.h>
 #include <net/protocol.h>
@@ -47,19 +48,25 @@ EXPORT_SYMBOL(nf_unregister_queue_handler);
 
 void nf_queue_entry_release_refs(struct nf_queue_entry *entry)
 {
+	struct nf_hook_state *state = &entry->state;
+
 	/* Release those devices we held, or Alexey will kill me. */
-	if (entry->indev)
-		dev_put(entry->indev);
-	if (entry->outdev)
-		dev_put(entry->outdev);
+	if (state->in)
+		dev_put(state->in);
+	if (state->out)
+		dev_put(state->out);
+	if (state->sk)
+		sock_put(state->sk);
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	if (entry->skb->nf_bridge) {
-		struct nf_bridge_info *nf_bridge = entry->skb->nf_bridge;
+		struct net_device *physdev;
 
-		if (nf_bridge->physindev)
-			dev_put(nf_bridge->physindev);
-		if (nf_bridge->physoutdev)
-			dev_put(nf_bridge->physoutdev);
+		physdev = nf_bridge_get_physindev(entry->skb);
+		if (physdev)
+			dev_put(physdev);
+		physdev = nf_bridge_get_physoutdev(entry->skb);
+		if (physdev)
+			dev_put(physdev);
 	}
 #endif
 	/* Drop reference to owner of hook which queued us. */
@@ -70,22 +77,25 @@ EXPORT_SYMBOL_GPL(nf_queue_entry_release_refs);
 /* Bump dev refs so they don't vanish while packet is out */
 bool nf_queue_entry_get_refs(struct nf_queue_entry *entry)
 {
+	struct nf_hook_state *state = &entry->state;
+
 	if (!try_module_get(entry->elem->owner))
 		return false;
 
-	if (entry->indev)
-		dev_hold(entry->indev);
-	if (entry->outdev)
-		dev_hold(entry->outdev);
+	if (state->in)
+		dev_hold(state->in);
+	if (state->out)
+		dev_hold(state->out);
+	if (state->sk)
+		sock_hold(state->sk);
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	if (entry->skb->nf_bridge) {
-		struct nf_bridge_info *nf_bridge = entry->skb->nf_bridge;
 		struct net_device *physdev;
 
-		physdev = nf_bridge->physindev;
+		physdev = nf_bridge_get_physindev(entry->skb);
 		if (physdev)
 			dev_hold(physdev);
-		physdev = nf_bridge->physoutdev;
+		physdev = nf_bridge_get_physoutdev(entry->skb);
 		if (physdev)
 			dev_hold(physdev);
 	}
@@ -100,12 +110,9 @@ EXPORT_SYMBOL_GPL(nf_queue_entry_get_refs);
  * through nf_reinject().
  */
 int nf_queue(struct sk_buff *skb,
-		      struct nf_hook_ops *elem,
-		      u_int8_t pf, unsigned int hook,
-		      struct net_device *indev,
-		      struct net_device *outdev,
-		      int (*okfn)(struct sk_buff *),
-		      unsigned int queuenum)
+	     struct nf_hook_ops *elem,
+	     struct nf_hook_state *state,
+	     unsigned int queuenum)
 {
 	int status = -ENOENT;
 	struct nf_queue_entry *entry = NULL;
@@ -121,7 +128,7 @@ int nf_queue(struct sk_buff *skb,
 		goto err_unlock;
 	}
 
-	afinfo = nf_get_afinfo(pf);
+	afinfo = nf_get_afinfo(state->pf);
 	if (!afinfo)
 		goto err_unlock;
 
@@ -134,11 +141,7 @@ int nf_queue(struct sk_buff *skb,
 	*entry = (struct nf_queue_entry) {
 		.skb	= skb,
 		.elem	= elem,
-		.pf	= pf,
-		.hook	= hook,
-		.indev	= indev,
-		.outdev	= outdev,
-		.okfn	= okfn,
+		.state	= *state,
 		.size	= sizeof(*entry) + afinfo->route_key_size,
 	};
 
@@ -184,30 +187,29 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict)
 	}
 
 	if (verdict == NF_ACCEPT) {
-		afinfo = nf_get_afinfo(entry->pf);
+		afinfo = nf_get_afinfo(entry->state.pf);
 		if (!afinfo || afinfo->reroute(skb, entry) < 0)
 			verdict = NF_DROP;
 	}
 
+	entry->state.thresh = INT_MIN;
+
 	if (verdict == NF_ACCEPT) {
 	next_hook:
-		verdict = nf_iterate(&nf_hooks[entry->pf][entry->hook],
-				     skb, entry->hook,
-				     entry->indev, entry->outdev, &elem,
-				     entry->okfn, INT_MIN);
+		verdict = nf_iterate(&nf_hooks[entry->state.pf][entry->state.hook],
+				     skb, &entry->state, &elem);
 	}
 
 	switch (verdict & NF_VERDICT_MASK) {
 	case NF_ACCEPT:
 	case NF_STOP:
 		local_bh_disable();
-		entry->okfn(skb);
+		entry->state.okfn(entry->state.sk, skb);
 		local_bh_enable();
 		break;
 	case NF_QUEUE:
-		err = nf_queue(skb, elem, entry->pf, entry->hook,
-				entry->indev, entry->outdev, entry->okfn,
-				verdict >> NF_VERDICT_QBITS);
+		err = nf_queue(skb, elem, &entry->state,
+			       verdict >> NF_VERDICT_QBITS);
 		if (err < 0) {
 			if (err == -ECANCELED)
 				goto next_hook;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 11ab4b078f3b..34ded09317e7 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -198,36 +198,31 @@ static int nft_delchain(struct nft_ctx *ctx)
 static inline bool
 nft_rule_is_active(struct net *net, const struct nft_rule *rule)
 {
-	return (rule->genmask & (1 << net->nft.gencursor)) == 0;
-}
-
-static inline int gencursor_next(struct net *net)
-{
-	return net->nft.gencursor+1 == 1 ? 1 : 0;
+	return (rule->genmask & nft_genmask_cur(net)) == 0;
 }
 
 static inline int
 nft_rule_is_active_next(struct net *net, const struct nft_rule *rule)
 {
-	return (rule->genmask & (1 << gencursor_next(net))) == 0;
+	return (rule->genmask & nft_genmask_next(net)) == 0;
 }
 
 static inline void
 nft_rule_activate_next(struct net *net, struct nft_rule *rule)
 {
 	/* Now inactive, will be active in the future */
-	rule->genmask = (1 << net->nft.gencursor);
+	rule->genmask = nft_genmask_cur(net);
 }
 
 static inline void
 nft_rule_deactivate_next(struct net *net, struct nft_rule *rule)
 {
-	rule->genmask = (1 << gencursor_next(net));
+	rule->genmask = nft_genmask_next(net);
 }
 
 static inline void nft_rule_clear(struct net *net, struct nft_rule *rule)
 {
-	rule->genmask = 0;
+	rule->genmask &= ~nft_genmask_next(net);
 }
 
 static int
@@ -401,7 +396,8 @@ nf_tables_chain_type_lookup(const struct nft_af_info *afi,
 }
 
 static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = {
-	[NFTA_TABLE_NAME]	= { .type = NLA_STRING },
+	[NFTA_TABLE_NAME]	= { .type = NLA_STRING,
+				    .len = NFT_TABLE_MAXNAMELEN - 1 },
 	[NFTA_TABLE_FLAGS]	= { .type = NLA_U32 },
 };
 
@@ -427,7 +423,8 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net,
 	    nla_put_be32(skb, NFTA_TABLE_USE, htonl(table->use)))
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_trim(skb, nlh);
@@ -685,26 +682,28 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb,
 	if (!try_module_get(afi->owner))
 		return -EAFNOSUPPORT;
 
-	table = kzalloc(sizeof(*table) + nla_len(name), GFP_KERNEL);
-	if (table == NULL) {
-		module_put(afi->owner);
-		return -ENOMEM;
-	}
+	err = -ENOMEM;
+	table = kzalloc(sizeof(*table), GFP_KERNEL);
+	if (table == NULL)
+		goto err1;
 
-	nla_strlcpy(table->name, name, nla_len(name));
+	nla_strlcpy(table->name, name, NFT_TABLE_MAXNAMELEN);
 	INIT_LIST_HEAD(&table->chains);
 	INIT_LIST_HEAD(&table->sets);
 	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;
-	}
+	if (err < 0)
+		goto err2;
+
 	list_add_tail_rcu(&table->list, &afi->tables);
 	return 0;
+err2:
+	kfree(table);
+err1:
+	module_put(afi->owner);
+	return err;
 }
 
 static int nft_flush_table(struct nft_ctx *ctx)
@@ -713,16 +712,12 @@ static int nft_flush_table(struct nft_ctx *ctx)
 	struct nft_chain *chain, *nc;
 	struct nft_set *set, *ns;
 
-	list_for_each_entry_safe(chain, nc, &ctx->table->chains, list) {
+	list_for_each_entry(chain, &ctx->table->chains, list) {
 		ctx->chain = chain;
 
 		err = nft_delrule_by_chain(ctx);
 		if (err < 0)
 			goto out;
-
-		err = nft_delchain(ctx);
-		if (err < 0)
-			goto out;
 	}
 
 	list_for_each_entry_safe(set, ns, &ctx->table->sets, list) {
@@ -735,6 +730,14 @@ static int nft_flush_table(struct nft_ctx *ctx)
 			goto out;
 	}
 
+	list_for_each_entry_safe(chain, nc, &ctx->table->chains, list) {
+		ctx->chain = chain;
+
+		err = nft_delchain(ctx);
+		if (err < 0)
+			goto out;
+	}
+
 	err = nft_deltable(ctx);
 out:
 	return err;
@@ -967,7 +970,8 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net,
 	if (nla_put_be32(skb, NFTA_CHAIN_USE, htonl(chain->use)))
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_trim(skb, nlh);
@@ -1130,9 +1134,11 @@ static struct nft_stats __percpu *nft_stats_alloc(const struct nlattr *attr)
 	/* Restore old counters on this cpu, no problem. Per-cpu statistics
 	 * are not exposed to userspace.
 	 */
+	preempt_disable();
 	stats = this_cpu_ptr(newstats);
 	stats->bytes = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_BYTES]));
 	stats->pkts = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS]));
+	preempt_enable();
 
 	return newstats;
 }
@@ -1217,7 +1223,10 @@ 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)) ||
+		    !(chain->flags & NFT_BASE_CHAIN)))
+			return -EOPNOTSUPP;
+
+		if (chain == NULL &&
 		    nla[NFTA_CHAIN_HOOK] == NULL)
 			return -EOPNOTSUPP;
 
@@ -1258,8 +1267,10 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 		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)
+		if (trans == NULL) {
+			free_percpu(stats);
 			return -ENOMEM;
+		}
 
 		nft_trans_chain_stats(trans) = stats;
 		nft_trans_chain_update(trans) = true;
@@ -1315,8 +1326,10 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 		hookfn = type->hooks[hooknum];
 
 		basechain = kzalloc(sizeof(*basechain), GFP_KERNEL);
-		if (basechain == NULL)
+		if (basechain == NULL) {
+			module_put(type->owner);
 			return -ENOMEM;
+		}
 
 		if (nla[NFTA_CHAIN_COUNTERS]) {
 			stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]);
@@ -1336,6 +1349,7 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 			rcu_assign_pointer(basechain->stats, stats);
 		}
 
+		write_pnet(&basechain->pnet, net);
 		basechain->type = type;
 		chain = &basechain->chain;
 
@@ -1363,7 +1377,6 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 
 	INIT_LIST_HEAD(&chain->rules);
 	chain->handle = nf_tables_alloc_handle(table);
-	chain->net = net;
 	chain->table = table;
 	nla_strlcpy(chain->name, name, NFT_CHAIN_MAXNAMELEN);
 
@@ -1532,6 +1545,23 @@ nla_put_failure:
 	return -1;
 };
 
+int nft_expr_dump(struct sk_buff *skb, unsigned int attr,
+		  const struct nft_expr *expr)
+{
+	struct nlattr *nest;
+
+	nest = nla_nest_start(skb, attr);
+	if (!nest)
+		goto nla_put_failure;
+	if (nf_tables_fill_expr_info(skb, expr) < 0)
+		goto nla_put_failure;
+	nla_nest_end(skb, nest);
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
 struct nft_expr_info {
 	const struct nft_expr_ops	*ops;
 	struct nlattr			*tb[NFT_EXPR_MAXATTR + 1];
@@ -1609,6 +1639,39 @@ static void nf_tables_expr_destroy(const struct nft_ctx *ctx,
 	module_put(expr->ops->type->owner);
 }
 
+struct nft_expr *nft_expr_init(const struct nft_ctx *ctx,
+			       const struct nlattr *nla)
+{
+	struct nft_expr_info info;
+	struct nft_expr *expr;
+	int err;
+
+	err = nf_tables_expr_parse(ctx, nla, &info);
+	if (err < 0)
+		goto err1;
+
+	err = -ENOMEM;
+	expr = kzalloc(info.ops->size, GFP_KERNEL);
+	if (expr == NULL)
+		goto err2;
+
+	err = nf_tables_newexpr(ctx, &info, expr);
+	if (err < 0)
+		goto err2;
+
+	return expr;
+err2:
+	module_put(info.ops->type->owner);
+err1:
+	return ERR_PTR(err);
+}
+
+void nft_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr)
+{
+	nf_tables_expr_destroy(ctx, expr);
+	kfree(expr);
+}
+
 /*
  * Rules
  */
@@ -1690,20 +1753,20 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net,
 	if (list == NULL)
 		goto nla_put_failure;
 	nft_rule_for_each_expr(expr, next, rule) {
-		struct nlattr *elem = nla_nest_start(skb, NFTA_LIST_ELEM);
-		if (elem == NULL)
+		if (nft_expr_dump(skb, NFTA_LIST_ELEM, expr) < 0)
 			goto nla_put_failure;
-		if (nf_tables_fill_expr_info(skb, expr) < 0)
-			goto nla_put_failure;
-		nla_nest_end(skb, elem);
 	}
 	nla_nest_end(skb, list);
 
-	if (rule->ulen &&
-	    nla_put(skb, NFTA_RULE_USERDATA, rule->ulen, nft_userdata(rule)))
-		goto nla_put_failure;
+	if (rule->udata) {
+		struct nft_userdata *udata = nft_userdata(rule);
+		if (nla_put(skb, NFTA_RULE_USERDATA, udata->len + 1,
+			    udata->data) < 0)
+			goto nla_put_failure;
+	}
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_trim(skb, nlh);
@@ -1883,11 +1946,12 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 	struct nft_table *table;
 	struct nft_chain *chain;
 	struct nft_rule *rule, *old_rule = NULL;
+	struct nft_userdata *udata;
 	struct nft_trans *trans = NULL;
 	struct nft_expr *expr;
 	struct nft_ctx ctx;
 	struct nlattr *tmp;
-	unsigned int size, i, n, ulen = 0;
+	unsigned int size, i, n, ulen = 0, usize = 0;
 	int err, rem;
 	bool create;
 	u64 handle, pos_handle;
@@ -1955,12 +2019,19 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 			n++;
 		}
 	}
+	/* Check for overflow of dlen field */
+	err = -EFBIG;
+	if (size >= 1 << 12)
+		goto err1;
 
-	if (nla[NFTA_RULE_USERDATA])
+	if (nla[NFTA_RULE_USERDATA]) {
 		ulen = nla_len(nla[NFTA_RULE_USERDATA]);
+		if (ulen > 0)
+			usize = sizeof(struct nft_userdata) + ulen;
+	}
 
 	err = -ENOMEM;
-	rule = kzalloc(sizeof(*rule) + size + ulen, GFP_KERNEL);
+	rule = kzalloc(sizeof(*rule) + size + usize, GFP_KERNEL);
 	if (rule == NULL)
 		goto err1;
 
@@ -1968,10 +2039,13 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 
 	rule->handle = handle;
 	rule->dlen   = size;
-	rule->ulen   = ulen;
+	rule->udata  = ulen ? 1 : 0;
 
-	if (ulen)
-		nla_memcpy(nft_userdata(rule), nla[NFTA_RULE_USERDATA], ulen);
+	if (ulen) {
+		udata = nft_userdata(rule);
+		udata->len = ulen - 1;
+		nla_memcpy(udata->data, nla[NFTA_RULE_USERDATA], ulen);
+	}
 
 	expr = nft_expr_first(rule);
 	for (i = 0; i < n; i++) {
@@ -2018,12 +2092,6 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 
 err3:
 	list_del_rcu(&rule->list);
-	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(&ctx, rule);
 err1:
@@ -2137,7 +2205,7 @@ nft_select_set_ops(const struct nlattr * const nla[],
 	features = 0;
 	if (nla[NFTA_SET_FLAGS] != NULL) {
 		features = ntohl(nla_get_be32(nla[NFTA_SET_FLAGS]));
-		features &= NFT_SET_INTERVAL | NFT_SET_MAP;
+		features &= NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_TIMEOUT;
 	}
 
 	bops	   = NULL;
@@ -2194,6 +2262,8 @@ static const struct nla_policy nft_set_policy[NFTA_SET_MAX + 1] = {
 	[NFTA_SET_POLICY]		= { .type = NLA_U32 },
 	[NFTA_SET_DESC]			= { .type = NLA_NESTED },
 	[NFTA_SET_ID]			= { .type = NLA_U32 },
+	[NFTA_SET_TIMEOUT]		= { .type = NLA_U64 },
+	[NFTA_SET_GC_INTERVAL]		= { .type = NLA_U32 },
 };
 
 static const struct nla_policy nft_set_desc_policy[NFTA_SET_DESC_MAX + 1] = {
@@ -2344,6 +2414,13 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
 			goto nla_put_failure;
 	}
 
+	if (set->timeout &&
+	    nla_put_be64(skb, NFTA_SET_TIMEOUT, cpu_to_be64(set->timeout)))
+		goto nla_put_failure;
+	if (set->gc_int &&
+	    nla_put_be32(skb, NFTA_SET_GC_INTERVAL, htonl(set->gc_int)))
+		goto nla_put_failure;
+
 	if (set->policy != NFT_SET_POL_PERFORMANCE) {
 		if (nla_put_be32(skb, NFTA_SET_POLICY, htonl(set->policy)))
 			goto nla_put_failure;
@@ -2357,7 +2434,8 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
 		goto nla_put_failure;
 	nla_nest_end(skb, desc);
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_trim(skb, nlh);
@@ -2477,7 +2555,7 @@ static int nf_tables_getset(struct sock *nlsk, struct sk_buff *skb,
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	int err;
 
-	/* Verify existance before starting dump */
+	/* Verify existence before starting dump */
 	err = nft_ctx_init_from_setattr(&ctx, skb, nlh, nla);
 	if (err < 0)
 		return err;
@@ -2555,7 +2633,8 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
 	char name[IFNAMSIZ];
 	unsigned int size;
 	bool create;
-	u32 ktype, dtype, flags, policy;
+	u64 timeout;
+	u32 ktype, dtype, flags, policy, gc_int;
 	struct nft_set_desc desc;
 	int err;
 
@@ -2575,15 +2654,20 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
 	}
 
 	desc.klen = ntohl(nla_get_be32(nla[NFTA_SET_KEY_LEN]));
-	if (desc.klen == 0 || desc.klen > FIELD_SIZEOF(struct nft_data, data))
+	if (desc.klen == 0 || desc.klen > NFT_DATA_VALUE_MAXLEN)
 		return -EINVAL;
 
 	flags = 0;
 	if (nla[NFTA_SET_FLAGS] != NULL) {
 		flags = ntohl(nla_get_be32(nla[NFTA_SET_FLAGS]));
 		if (flags & ~(NFT_SET_ANONYMOUS | NFT_SET_CONSTANT |
-			      NFT_SET_INTERVAL | NFT_SET_MAP))
+			      NFT_SET_INTERVAL | NFT_SET_TIMEOUT |
+			      NFT_SET_MAP | NFT_SET_EVAL))
 			return -EINVAL;
+		/* Only one of both operations is supported */
+		if ((flags & (NFT_SET_MAP | NFT_SET_EVAL)) ==
+			     (NFT_SET_MAP | NFT_SET_EVAL))
+			return -EOPNOTSUPP;
 	}
 
 	dtype = 0;
@@ -2600,14 +2684,26 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
 			if (nla[NFTA_SET_DATA_LEN] == NULL)
 				return -EINVAL;
 			desc.dlen = ntohl(nla_get_be32(nla[NFTA_SET_DATA_LEN]));
-			if (desc.dlen == 0 ||
-			    desc.dlen > FIELD_SIZEOF(struct nft_data, data))
+			if (desc.dlen == 0 || desc.dlen > NFT_DATA_VALUE_MAXLEN)
 				return -EINVAL;
 		} else
-			desc.dlen = sizeof(struct nft_data);
+			desc.dlen = sizeof(struct nft_verdict);
 	} else if (flags & NFT_SET_MAP)
 		return -EINVAL;
 
+	timeout = 0;
+	if (nla[NFTA_SET_TIMEOUT] != NULL) {
+		if (!(flags & NFT_SET_TIMEOUT))
+			return -EINVAL;
+		timeout = be64_to_cpu(nla_get_be64(nla[NFTA_SET_TIMEOUT]));
+	}
+	gc_int = 0;
+	if (nla[NFTA_SET_GC_INTERVAL] != NULL) {
+		if (!(flags & NFT_SET_TIMEOUT))
+			return -EINVAL;
+		gc_int = ntohl(nla_get_be32(nla[NFTA_SET_GC_INTERVAL]));
+	}
+
 	policy = NFT_SET_POL_PERFORMANCE;
 	if (nla[NFTA_SET_POLICY] != NULL)
 		policy = ntohl(nla_get_be32(nla[NFTA_SET_POLICY]));
@@ -2667,6 +2763,7 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
 		goto err2;
 
 	INIT_LIST_HEAD(&set->bindings);
+	write_pnet(&set->pnet, net);
 	set->ops   = ops;
 	set->ktype = ktype;
 	set->klen  = desc.klen;
@@ -2675,6 +2772,8 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
 	set->flags = flags;
 	set->size  = desc.size;
 	set->policy = policy;
+	set->timeout = timeout;
+	set->gc_int = gc_int;
 
 	err = ops->init(set, &desc, nla);
 	if (err < 0)
@@ -2743,12 +2842,14 @@ static int nf_tables_bind_check_setelem(const struct nft_ctx *ctx,
 					const struct nft_set_iter *iter,
 					const struct nft_set_elem *elem)
 {
+	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
 	enum nft_registers dreg;
 
 	dreg = nft_type_to_reg(set->dtype);
-	return nft_validate_data_load(ctx, dreg, &elem->data,
-				      set->dtype == NFT_DATA_VERDICT ?
-				      NFT_DATA_VERDICT : NFT_DATA_VALUE);
+	return nft_validate_register_store(ctx, dreg, nft_set_ext_data(ext),
+					   set->dtype == NFT_DATA_VERDICT ?
+					   NFT_DATA_VERDICT : NFT_DATA_VALUE,
+					   set->dlen);
 }
 
 int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
@@ -2760,12 +2861,13 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
 	if (!list_empty(&set->bindings) && set->flags & NFT_SET_ANONYMOUS)
 		return -EBUSY;
 
-	if (set->flags & NFT_SET_MAP) {
+	if (binding->flags & NFT_SET_MAP) {
 		/* If the set is already bound to the same chain all
 		 * jumps are already validated for that chain.
 		 */
 		list_for_each_entry(i, &set->bindings, list) {
-			if (i->chain == binding->chain)
+			if (binding->flags & NFT_SET_MAP &&
+			    i->chain == binding->chain)
 				goto bind;
 		}
 
@@ -2799,6 +2901,35 @@ void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
 		nf_tables_set_destroy(ctx, set);
 }
 
+const struct nft_set_ext_type nft_set_ext_types[] = {
+	[NFT_SET_EXT_KEY]		= {
+		.align	= __alignof__(u32),
+	},
+	[NFT_SET_EXT_DATA]		= {
+		.align	= __alignof__(u32),
+	},
+	[NFT_SET_EXT_EXPR]		= {
+		.align	= __alignof__(struct nft_expr),
+	},
+	[NFT_SET_EXT_FLAGS]		= {
+		.len	= sizeof(u8),
+		.align	= __alignof__(u8),
+	},
+	[NFT_SET_EXT_TIMEOUT]		= {
+		.len	= sizeof(u64),
+		.align	= __alignof__(u64),
+	},
+	[NFT_SET_EXT_EXPIRATION]	= {
+		.len	= sizeof(unsigned long),
+		.align	= __alignof__(unsigned long),
+	},
+	[NFT_SET_EXT_USERDATA]		= {
+		.len	= sizeof(struct nft_userdata),
+		.align	= __alignof__(struct nft_userdata),
+	},
+};
+EXPORT_SYMBOL_GPL(nft_set_ext_types);
+
 /*
  * Set elements
  */
@@ -2807,6 +2938,9 @@ static const struct nla_policy nft_set_elem_policy[NFTA_SET_ELEM_MAX + 1] = {
 	[NFTA_SET_ELEM_KEY]		= { .type = NLA_NESTED },
 	[NFTA_SET_ELEM_DATA]		= { .type = NLA_NESTED },
 	[NFTA_SET_ELEM_FLAGS]		= { .type = NLA_U32 },
+	[NFTA_SET_ELEM_TIMEOUT]		= { .type = NLA_U64 },
+	[NFTA_SET_ELEM_USERDATA]	= { .type = NLA_BINARY,
+					    .len = NFT_USERDATA_MAXLEN },
 };
 
 static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX + 1] = {
@@ -2845,6 +2979,7 @@ static int nf_tables_fill_setelem(struct sk_buff *skb,
 				  const struct nft_set *set,
 				  const struct nft_set_elem *elem)
 {
+	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
 	unsigned char *b = skb_tail_pointer(skb);
 	struct nlattr *nest;
 
@@ -2852,20 +2987,52 @@ static int nf_tables_fill_setelem(struct sk_buff *skb,
 	if (nest == NULL)
 		goto nla_put_failure;
 
-	if (nft_data_dump(skb, NFTA_SET_ELEM_KEY, &elem->key, NFT_DATA_VALUE,
-			  set->klen) < 0)
+	if (nft_data_dump(skb, NFTA_SET_ELEM_KEY, nft_set_ext_key(ext),
+			  NFT_DATA_VALUE, set->klen) < 0)
 		goto nla_put_failure;
 
-	if (set->flags & NFT_SET_MAP &&
-	    !(elem->flags & NFT_SET_ELEM_INTERVAL_END) &&
-	    nft_data_dump(skb, NFTA_SET_ELEM_DATA, &elem->data,
+	if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) &&
+	    nft_data_dump(skb, NFTA_SET_ELEM_DATA, nft_set_ext_data(ext),
 			  set->dtype == NFT_DATA_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE,
 			  set->dlen) < 0)
 		goto nla_put_failure;
 
-	if (elem->flags != 0)
-		if (nla_put_be32(skb, NFTA_SET_ELEM_FLAGS, htonl(elem->flags)))
+	if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPR) &&
+	    nft_expr_dump(skb, NFTA_SET_ELEM_EXPR, nft_set_ext_expr(ext)) < 0)
+		goto nla_put_failure;
+
+	if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) &&
+	    nla_put_be32(skb, NFTA_SET_ELEM_FLAGS,
+		         htonl(*nft_set_ext_flags(ext))))
+		goto nla_put_failure;
+
+	if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) &&
+	    nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT,
+			 cpu_to_be64(*nft_set_ext_timeout(ext))))
+		goto nla_put_failure;
+
+	if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) {
+		unsigned long expires, now = jiffies;
+
+		expires = *nft_set_ext_expiration(ext);
+		if (time_before(now, expires))
+			expires -= now;
+		else
+			expires = 0;
+
+		if (nla_put_be64(skb, NFTA_SET_ELEM_EXPIRATION,
+				 cpu_to_be64(jiffies_to_msecs(expires))))
+			goto nla_put_failure;
+	}
+
+	if (nft_set_ext_exists(ext, NFT_SET_EXT_USERDATA)) {
+		struct nft_userdata *udata;
+
+		udata = nft_set_ext_userdata(ext);
+		if (nla_put(skb, NFTA_SET_ELEM_USERDATA,
+			    udata->len + 1, udata->data))
 			goto nla_put_failure;
+	}
 
 	nla_nest_end(skb, nest);
 	return 0;
@@ -3031,7 +3198,8 @@ static int nf_tables_fill_setelem_info(struct sk_buff *skb,
 
 	nla_nest_end(skb, nest);
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_trim(skb, nlh);
@@ -3085,20 +3253,65 @@ static struct nft_trans *nft_trans_elem_alloc(struct nft_ctx *ctx,
 	return trans;
 }
 
+void *nft_set_elem_init(const struct nft_set *set,
+			const struct nft_set_ext_tmpl *tmpl,
+			const u32 *key, const u32 *data,
+			u64 timeout, gfp_t gfp)
+{
+	struct nft_set_ext *ext;
+	void *elem;
+
+	elem = kzalloc(set->ops->elemsize + tmpl->len, gfp);
+	if (elem == NULL)
+		return NULL;
+
+	ext = nft_set_elem_ext(set, elem);
+	nft_set_ext_init(ext, tmpl);
+
+	memcpy(nft_set_ext_key(ext), key, set->klen);
+	if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA))
+		memcpy(nft_set_ext_data(ext), data, set->dlen);
+	if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION))
+		*nft_set_ext_expiration(ext) =
+			jiffies + msecs_to_jiffies(timeout);
+	if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT))
+		*nft_set_ext_timeout(ext) = timeout;
+
+	return elem;
+}
+
+void nft_set_elem_destroy(const struct nft_set *set, void *elem)
+{
+	struct nft_set_ext *ext = nft_set_elem_ext(set, elem);
+
+	nft_data_uninit(nft_set_ext_key(ext), NFT_DATA_VALUE);
+	if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA))
+		nft_data_uninit(nft_set_ext_data(ext), set->dtype);
+	if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPR))
+		nf_tables_expr_destroy(NULL, nft_set_ext_expr(ext));
+
+	kfree(elem);
+}
+EXPORT_SYMBOL_GPL(nft_set_elem_destroy);
+
 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];
 	struct nft_data_desc d1, d2;
+	struct nft_set_ext_tmpl tmpl;
+	struct nft_set_ext *ext;
 	struct nft_set_elem elem;
 	struct nft_set_binding *binding;
+	struct nft_userdata *udata;
+	struct nft_data data;
 	enum nft_registers dreg;
 	struct nft_trans *trans;
+	u64 timeout;
+	u32 flags;
+	u8 ulen;
 	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)
@@ -3107,38 +3320,59 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	if (nla[NFTA_SET_ELEM_KEY] == NULL)
 		return -EINVAL;
 
-	elem.flags = 0;
+	nft_set_ext_prepare(&tmpl);
+
+	flags = 0;
 	if (nla[NFTA_SET_ELEM_FLAGS] != NULL) {
-		elem.flags = ntohl(nla_get_be32(nla[NFTA_SET_ELEM_FLAGS]));
-		if (elem.flags & ~NFT_SET_ELEM_INTERVAL_END)
+		flags = ntohl(nla_get_be32(nla[NFTA_SET_ELEM_FLAGS]));
+		if (flags & ~NFT_SET_ELEM_INTERVAL_END)
+			return -EINVAL;
+		if (!(set->flags & NFT_SET_INTERVAL) &&
+		    flags & NFT_SET_ELEM_INTERVAL_END)
 			return -EINVAL;
+		if (flags != 0)
+			nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS);
 	}
 
 	if (set->flags & NFT_SET_MAP) {
 		if (nla[NFTA_SET_ELEM_DATA] == NULL &&
-		    !(elem.flags & NFT_SET_ELEM_INTERVAL_END))
+		    !(flags & NFT_SET_ELEM_INTERVAL_END))
 			return -EINVAL;
 		if (nla[NFTA_SET_ELEM_DATA] != NULL &&
-		    elem.flags & NFT_SET_ELEM_INTERVAL_END)
+		    flags & NFT_SET_ELEM_INTERVAL_END)
 			return -EINVAL;
 	} else {
 		if (nla[NFTA_SET_ELEM_DATA] != NULL)
 			return -EINVAL;
 	}
 
-	err = nft_data_init(ctx, &elem.key, &d1, nla[NFTA_SET_ELEM_KEY]);
+	timeout = 0;
+	if (nla[NFTA_SET_ELEM_TIMEOUT] != NULL) {
+		if (!(set->flags & NFT_SET_TIMEOUT))
+			return -EINVAL;
+		timeout = be64_to_cpu(nla_get_be64(nla[NFTA_SET_ELEM_TIMEOUT]));
+	} else if (set->flags & NFT_SET_TIMEOUT) {
+		timeout = set->timeout;
+	}
+
+	err = nft_data_init(ctx, &elem.key.val, sizeof(elem.key), &d1,
+			    nla[NFTA_SET_ELEM_KEY]);
 	if (err < 0)
 		goto err1;
 	err = -EINVAL;
 	if (d1.type != NFT_DATA_VALUE || d1.len != set->klen)
 		goto err2;
 
-	err = -EEXIST;
-	if (set->ops->get(set, &elem) == 0)
-		goto err2;
+	nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, d1.len);
+	if (timeout > 0) {
+		nft_set_ext_add(&tmpl, NFT_SET_EXT_EXPIRATION);
+		if (timeout != set->timeout)
+			nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT);
+	}
 
 	if (nla[NFTA_SET_ELEM_DATA] != NULL) {
-		err = nft_data_init(ctx, &elem.data, &d2, nla[NFTA_SET_ELEM_DATA]);
+		err = nft_data_init(ctx, &data, sizeof(data), &d2,
+				    nla[NFTA_SET_ELEM_DATA]);
 		if (err < 0)
 			goto err2;
 
@@ -3154,32 +3388,68 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 				.chain	= (struct nft_chain *)binding->chain,
 			};
 
-			err = nft_validate_data_load(&bind_ctx, dreg,
-						     &elem.data, d2.type);
+			if (!(binding->flags & NFT_SET_MAP))
+				continue;
+
+			err = nft_validate_register_store(&bind_ctx, dreg,
+							  &data,
+							  d2.type, d2.len);
 			if (err < 0)
 				goto err3;
 		}
+
+		nft_set_ext_add_length(&tmpl, NFT_SET_EXT_DATA, d2.len);
+	}
+
+	/* The full maximum length of userdata can exceed the maximum
+	 * offset value (U8_MAX) for following extensions, therefor it
+	 * must be the last extension added.
+	 */
+	ulen = 0;
+	if (nla[NFTA_SET_ELEM_USERDATA] != NULL) {
+		ulen = nla_len(nla[NFTA_SET_ELEM_USERDATA]);
+		if (ulen > 0)
+			nft_set_ext_add_length(&tmpl, NFT_SET_EXT_USERDATA,
+					       ulen);
+	}
+
+	err = -ENOMEM;
+	elem.priv = nft_set_elem_init(set, &tmpl, elem.key.val.data, data.data,
+				      timeout, GFP_KERNEL);
+	if (elem.priv == NULL)
+		goto err3;
+
+	ext = nft_set_elem_ext(set, elem.priv);
+	if (flags)
+		*nft_set_ext_flags(ext) = flags;
+	if (ulen > 0) {
+		udata = nft_set_ext_userdata(ext);
+		udata->len = ulen - 1;
+		nla_memcpy(&udata->data, nla[NFTA_SET_ELEM_USERDATA], ulen);
 	}
 
 	trans = nft_trans_elem_alloc(ctx, NFT_MSG_NEWSETELEM, set);
 	if (trans == NULL)
-		goto err3;
+		goto err4;
 
+	ext->genmask = nft_genmask_cur(ctx->net) | NFT_SET_ELEM_BUSY_MASK;
 	err = set->ops->insert(set, &elem);
 	if (err < 0)
-		goto err4;
+		goto err5;
 
 	nft_trans_elem(trans) = elem;
 	list_add_tail(&trans->list, &ctx->net->nft.commit_list);
 	return 0;
 
-err4:
+err5:
 	kfree(trans);
+err4:
+	kfree(elem.priv);
 err3:
 	if (nla[NFTA_SET_ELEM_DATA] != NULL)
-		nft_data_uninit(&elem.data, d2.type);
+		nft_data_uninit(&data, d2.type);
 err2:
-	nft_data_uninit(&elem.key, d1.type);
+	nft_data_uninit(&elem.key.val, d1.type);
 err1:
 	return err;
 }
@@ -3215,11 +3485,15 @@ static int nf_tables_newsetelem(struct sock *nlsk, struct sk_buff *skb,
 		return -EBUSY;
 
 	nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) {
+		if (set->size &&
+		    !atomic_add_unless(&set->nelems, 1, set->size + set->ndeact))
+			return -ENFILE;
+
 		err = nft_add_set_elem(&ctx, set, attr);
-		if (err < 0)
+		if (err < 0) {
+			atomic_dec(&set->nelems);
 			break;
-
-		set->nelems++;
+		}
 	}
 	return err;
 }
@@ -3242,7 +3516,8 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
 	if (nla[NFTA_SET_ELEM_KEY] == NULL)
 		goto err1;
 
-	err = nft_data_init(ctx, &elem.key, &desc, nla[NFTA_SET_ELEM_KEY]);
+	err = nft_data_init(ctx, &elem.key.val, sizeof(elem.key), &desc,
+			    nla[NFTA_SET_ELEM_KEY]);
 	if (err < 0)
 		goto err1;
 
@@ -3250,21 +3525,26 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
 	if (desc.type != NFT_DATA_VALUE || desc.len != set->klen)
 		goto err2;
 
-	err = set->ops->get(set, &elem);
-	if (err < 0)
-		goto err2;
-
 	trans = nft_trans_elem_alloc(ctx, NFT_MSG_DELSETELEM, set);
 	if (trans == NULL) {
 		err = -ENOMEM;
 		goto err2;
 	}
 
+	elem.priv = set->ops->deactivate(set, &elem);
+	if (elem.priv == NULL) {
+		err = -ENOENT;
+		goto err3;
+	}
+
 	nft_trans_elem(trans) = elem;
 	list_add_tail(&trans->list, &ctx->net->nft.commit_list);
 	return 0;
+
+err3:
+	kfree(trans);
 err2:
-	nft_data_uninit(&elem.key, desc.type);
+	nft_data_uninit(&elem.key.val, desc.type);
 err1:
 	return err;
 }
@@ -3296,11 +3576,36 @@ static int nf_tables_delsetelem(struct sock *nlsk, struct sk_buff *skb,
 		if (err < 0)
 			break;
 
-		set->nelems--;
+		set->ndeact++;
 	}
 	return err;
 }
 
+void nft_set_gc_batch_release(struct rcu_head *rcu)
+{
+	struct nft_set_gc_batch *gcb;
+	unsigned int i;
+
+	gcb = container_of(rcu, struct nft_set_gc_batch, head.rcu);
+	for (i = 0; i < gcb->head.cnt; i++)
+		nft_set_elem_destroy(gcb->head.set, gcb->elems[i]);
+	kfree(gcb);
+}
+EXPORT_SYMBOL_GPL(nft_set_gc_batch_release);
+
+struct nft_set_gc_batch *nft_set_gc_batch_alloc(const struct nft_set *set,
+						gfp_t gfp)
+{
+	struct nft_set_gc_batch *gcb;
+
+	gcb = kzalloc(sizeof(*gcb), gfp);
+	if (gcb == NULL)
+		return gcb;
+	gcb->head.set = set;
+	return gcb;
+}
+EXPORT_SYMBOL_GPL(nft_set_gc_batch_alloc);
+
 static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net,
 				   u32 portid, u32 seq)
 {
@@ -3320,7 +3625,8 @@ static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net,
 	if (nla_put_be32(skb, NFTA_GEN_ID, htonl(net->nft.base_seq)))
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_trim(skb, nlh);
@@ -3484,13 +3790,8 @@ static void nft_chain_commit_update(struct nft_trans *trans)
 	}
 }
 
-/* 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)
+static void nf_tables_commit_release(struct nft_trans *trans)
 {
-	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);
@@ -3504,6 +3805,10 @@ static void nf_tables_commit_release_rcu(struct rcu_head *rt)
 	case NFT_MSG_DELSET:
 		nft_set_destroy(nft_trans_set(trans));
 		break;
+	case NFT_MSG_DELSETELEM:
+		nft_set_elem_destroy(nft_trans_elem_set(trans),
+				     nft_trans_elem(trans).priv);
+		break;
 	}
 	kfree(trans);
 }
@@ -3518,7 +3823,7 @@ static int nf_tables_commit(struct sk_buff *skb)
 	while (++net->nft.base_seq == 0);
 
 	/* A new generation has just started */
-	net->nft.gencursor = gencursor_next(net);
+	net->nft.gencursor = nft_gencursor_next(net);
 
 	/* Make sure all packets have left the previous generation before
 	 * purging old rules.
@@ -3589,33 +3894,32 @@ static int nf_tables_commit(struct sk_buff *skb)
 					     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),
+			te = (struct nft_trans_elem *)trans->data;
+
+			te->set->ops->activate(te->set, &te->elem);
+			nf_tables_setelem_notify(&trans->ctx, te->set,
+						 &te->elem,
 						 NFT_MSG_NEWSETELEM, 0);
 			nft_trans_destroy(trans);
 			break;
 		case NFT_MSG_DELSETELEM:
 			te = (struct nft_trans_elem *)trans->data;
+
 			nf_tables_setelem_notify(&trans->ctx, te->set,
 						 &te->elem,
 						 NFT_MSG_DELSETELEM, 0);
-			te->set->ops->get(te->set, &te->elem);
 			te->set->ops->remove(te->set, &te->elem);
-			nft_data_uninit(&te->elem.key, NFT_DATA_VALUE);
-			if (te->elem.flags & NFT_SET_MAP) {
-				nft_data_uninit(&te->elem.data,
-						te->set->dtype);
-			}
-			nft_trans_destroy(trans);
+			atomic_dec(&te->set->nelems);
+			te->set->ndeact--;
 			break;
 		}
 	}
 
+	synchronize_rcu();
+
 	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);
+		nf_tables_commit_release(trans);
 	}
 
 	nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN);
@@ -3623,13 +3927,8 @@ static int nf_tables_commit(struct sk_buff *skb)
 	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)
+static void nf_tables_abort_release(struct nft_trans *trans)
 {
-	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);
@@ -3643,6 +3942,10 @@ static void nf_tables_abort_release_rcu(struct rcu_head *rt)
 	case NFT_MSG_NEWSET:
 		nft_set_destroy(nft_trans_set(trans));
 		break;
+	case NFT_MSG_NEWSETELEM:
+		nft_set_elem_destroy(nft_trans_elem_set(trans),
+				     nft_trans_elem(trans).priv);
+		break;
 	}
 	kfree(trans);
 }
@@ -3651,7 +3954,7 @@ 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;
+	struct nft_trans_elem *te;
 
 	list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) {
 		switch (trans->msg_type) {
@@ -3674,8 +3977,7 @@ static int nf_tables_abort(struct sk_buff *skb)
 			break;
 		case NFT_MSG_NEWCHAIN:
 			if (nft_trans_chain_update(trans)) {
-				if (nft_trans_chain_stats(trans))
-					free_percpu(nft_trans_chain_stats(trans));
+				free_percpu(nft_trans_chain_stats(trans));
 
 				nft_trans_destroy(trans);
 			} else {
@@ -3712,24 +4014,28 @@ static int nf_tables_abort(struct sk_buff *skb)
 			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);
+			te = (struct nft_trans_elem *)trans->data;
+
+			te->set->ops->remove(te->set, &te->elem);
+			atomic_dec(&te->set->nelems);
 			break;
 		case NFT_MSG_DELSETELEM:
-			nft_trans_elem_set(trans)->nelems++;
+			te = (struct nft_trans_elem *)trans->data;
+
+			te->set->ops->activate(te->set, &te->elem);
+			te->set->ndeact--;
+
 			nft_trans_destroy(trans);
 			break;
 		}
 	}
 
+	synchronize_rcu();
+
 	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);
+		nf_tables_abort_release(trans);
 	}
 
 	return 0;
@@ -3758,6 +4064,24 @@ int nft_chain_validate_dependency(const struct nft_chain *chain,
 }
 EXPORT_SYMBOL_GPL(nft_chain_validate_dependency);
 
+int nft_chain_validate_hooks(const struct nft_chain *chain,
+			     unsigned int hook_flags)
+{
+	struct nft_base_chain *basechain;
+
+	if (chain->flags & NFT_BASE_CHAIN) {
+		basechain = nft_base_chain(chain);
+
+		if ((1 << basechain->ops[0].hooknum) & hook_flags)
+			return 0;
+
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nft_chain_validate_hooks);
+
 /*
  * Loop detection - walk through the ruleset beginning at the destination chain
  * of a new jump until either the source chain is reached (loop) or all
@@ -3775,13 +4099,18 @@ 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)
+	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
+	const struct nft_data *data;
+
+	if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) &&
+	    *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END)
 		return 0;
 
-	switch (elem->data.verdict) {
+	data = nft_set_ext_data(ext);
+	switch (data->verdict.code) {
 	case NFT_JUMP:
 	case NFT_GOTO:
-		return nf_tables_check_loops(ctx, elem->data.chain);
+		return nf_tables_check_loops(ctx, data->verdict.chain);
 	default:
 		return 0;
 	}
@@ -3814,10 +4143,11 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx,
 			if (data == NULL)
 				continue;
 
-			switch (data->verdict) {
+			switch (data->verdict.code) {
 			case NFT_JUMP:
 			case NFT_GOTO:
-				err = nf_tables_check_loops(ctx, data->chain);
+				err = nf_tables_check_loops(ctx,
+							data->verdict.chain);
 				if (err < 0)
 					return err;
 			default:
@@ -3832,7 +4162,8 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx,
 			continue;
 
 		list_for_each_entry(binding, &set->bindings, list) {
-			if (binding->chain != chain)
+			if (!(binding->flags & NFT_SET_MAP) ||
+			    binding->chain != chain)
 				continue;
 
 			iter.skip 	= 0;
@@ -3850,85 +4181,129 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx,
 }
 
 /**
- *	nft_validate_input_register - validate an expressions' input register
+ *	nft_parse_register - parse a register value from a netlink attribute
  *
- *	@reg: the register number
+ *	@attr: netlink attribute
  *
- * 	Validate that the input register is one of the general purpose
- * 	registers.
+ *	Parse and translate a register value from a netlink attribute.
+ *	Registers used to be 128 bit wide, these register numbers will be
+ *	mapped to the corresponding 32 bit register numbers.
  */
-int nft_validate_input_register(enum nft_registers reg)
+unsigned int nft_parse_register(const struct nlattr *attr)
 {
-	if (reg <= NFT_REG_VERDICT)
-		return -EINVAL;
-	if (reg > NFT_REG_MAX)
-		return -ERANGE;
-	return 0;
+	unsigned int reg;
+
+	reg = ntohl(nla_get_be32(attr));
+	switch (reg) {
+	case NFT_REG_VERDICT...NFT_REG_4:
+		return reg * NFT_REG_SIZE / NFT_REG32_SIZE;
+	default:
+		return reg + NFT_REG_SIZE / NFT_REG32_SIZE - NFT_REG32_00;
+	}
 }
-EXPORT_SYMBOL_GPL(nft_validate_input_register);
+EXPORT_SYMBOL_GPL(nft_parse_register);
 
 /**
- *	nft_validate_output_register - validate an expressions' output register
+ *	nft_dump_register - dump a register value to a netlink attribute
+ *
+ *	@skb: socket buffer
+ *	@attr: attribute number
+ *	@reg: register number
+ *
+ *	Construct a netlink attribute containing the register number. For
+ *	compatibility reasons, register numbers being a multiple of 4 are
+ *	translated to the corresponding 128 bit register numbers.
+ */
+int nft_dump_register(struct sk_buff *skb, unsigned int attr, unsigned int reg)
+{
+	if (reg % (NFT_REG_SIZE / NFT_REG32_SIZE) == 0)
+		reg = reg / (NFT_REG_SIZE / NFT_REG32_SIZE);
+	else
+		reg = reg - NFT_REG_SIZE / NFT_REG32_SIZE + NFT_REG32_00;
+
+	return nla_put_be32(skb, attr, htonl(reg));
+}
+EXPORT_SYMBOL_GPL(nft_dump_register);
+
+/**
+ *	nft_validate_register_load - validate a load from a register
  *
  *	@reg: the register number
+ *	@len: the length of the data
  *
- * 	Validate that the output register is one of the general purpose
- * 	registers or the verdict register.
+ * 	Validate that the input register is one of the general purpose
+ * 	registers and that the length of the load is within the bounds.
  */
-int nft_validate_output_register(enum nft_registers reg)
+int nft_validate_register_load(enum nft_registers reg, unsigned int len)
 {
-	if (reg < NFT_REG_VERDICT)
+	if (reg < NFT_REG_1 * NFT_REG_SIZE / NFT_REG32_SIZE)
+		return -EINVAL;
+	if (len == 0)
 		return -EINVAL;
-	if (reg > NFT_REG_MAX)
+	if (reg * NFT_REG32_SIZE + len > FIELD_SIZEOF(struct nft_regs, data))
 		return -ERANGE;
+
 	return 0;
 }
-EXPORT_SYMBOL_GPL(nft_validate_output_register);
+EXPORT_SYMBOL_GPL(nft_validate_register_load);
 
 /**
- *	nft_validate_data_load - validate an expressions' data load
+ *	nft_validate_register_store - validate an expressions' register store
  *
  *	@ctx: context of the expression performing the load
  * 	@reg: the destination register number
  * 	@data: the data to load
  * 	@type: the data type
+ * 	@len: the length of the data
  *
  * 	Validate that a data load uses the appropriate data type for
- * 	the destination register. A value of NULL for the data means
- * 	that its runtime gathered data, which is always of type
- * 	NFT_DATA_VALUE.
+ * 	the destination register and the length is within the bounds.
+ * 	A value of NULL for the data means that its runtime gathered
+ * 	data.
  */
-int nft_validate_data_load(const struct nft_ctx *ctx, enum nft_registers reg,
-			   const struct nft_data *data,
-			   enum nft_data_types type)
+int nft_validate_register_store(const struct nft_ctx *ctx,
+				enum nft_registers reg,
+				const struct nft_data *data,
+				enum nft_data_types type, unsigned int len)
 {
 	int err;
 
 	switch (reg) {
 	case NFT_REG_VERDICT:
-		if (data == NULL || type != NFT_DATA_VERDICT)
+		if (type != NFT_DATA_VERDICT)
 			return -EINVAL;
 
-		if (data->verdict == NFT_GOTO || data->verdict == NFT_JUMP) {
-			err = nf_tables_check_loops(ctx, data->chain);
+		if (data != NULL &&
+		    (data->verdict.code == NFT_GOTO ||
+		     data->verdict.code == NFT_JUMP)) {
+			err = nf_tables_check_loops(ctx, data->verdict.chain);
 			if (err < 0)
 				return err;
 
-			if (ctx->chain->level + 1 > data->chain->level) {
+			if (ctx->chain->level + 1 >
+			    data->verdict.chain->level) {
 				if (ctx->chain->level + 1 == NFT_JUMP_STACK_SIZE)
 					return -EMLINK;
-				data->chain->level = ctx->chain->level + 1;
+				data->verdict.chain->level = ctx->chain->level + 1;
 			}
 		}
 
 		return 0;
 	default:
+		if (reg < NFT_REG_1 * NFT_REG_SIZE / NFT_REG32_SIZE)
+			return -EINVAL;
+		if (len == 0)
+			return -EINVAL;
+		if (reg * NFT_REG32_SIZE + len >
+		    FIELD_SIZEOF(struct nft_regs, data))
+			return -ERANGE;
+
 		if (data != NULL && type != NFT_DATA_VALUE)
 			return -EINVAL;
 		return 0;
 	}
 }
-EXPORT_SYMBOL_GPL(nft_validate_data_load);
+EXPORT_SYMBOL_GPL(nft_validate_register_store);
 
 static const struct nla_policy nft_verdict_policy[NFTA_VERDICT_MAX + 1] = {
 	[NFTA_VERDICT_CODE]	= { .type = NLA_U32 },
@@ -3949,11 +4324,11 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
 
 	if (!tb[NFTA_VERDICT_CODE])
 		return -EINVAL;
-	data->verdict = ntohl(nla_get_be32(tb[NFTA_VERDICT_CODE]));
+	data->verdict.code = ntohl(nla_get_be32(tb[NFTA_VERDICT_CODE]));
 
-	switch (data->verdict) {
+	switch (data->verdict.code) {
 	default:
-		switch (data->verdict & NF_VERDICT_MASK) {
+		switch (data->verdict.code & NF_VERDICT_MASK) {
 		case NF_ACCEPT:
 		case NF_DROP:
 		case NF_QUEUE:
@@ -3965,7 +4340,6 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
 	case NFT_CONTINUE:
 	case NFT_BREAK:
 	case NFT_RETURN:
-		desc->len = sizeof(data->verdict);
 		break;
 	case NFT_JUMP:
 	case NFT_GOTO:
@@ -3979,21 +4353,21 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
 			return -EOPNOTSUPP;
 
 		chain->use++;
-		data->chain = chain;
-		desc->len = sizeof(data);
+		data->verdict.chain = chain;
 		break;
 	}
 
+	desc->len = sizeof(data->verdict);
 	desc->type = NFT_DATA_VERDICT;
 	return 0;
 }
 
 static void nft_verdict_uninit(const struct nft_data *data)
 {
-	switch (data->verdict) {
+	switch (data->verdict.code) {
 	case NFT_JUMP:
 	case NFT_GOTO:
-		data->chain->use--;
+		data->verdict.chain->use--;
 		break;
 	}
 }
@@ -4006,13 +4380,14 @@ static int nft_verdict_dump(struct sk_buff *skb, const struct nft_data *data)
 	if (!nest)
 		goto nla_put_failure;
 
-	if (nla_put_be32(skb, NFTA_VERDICT_CODE, htonl(data->verdict)))
+	if (nla_put_be32(skb, NFTA_VERDICT_CODE, htonl(data->verdict.code)))
 		goto nla_put_failure;
 
-	switch (data->verdict) {
+	switch (data->verdict.code) {
 	case NFT_JUMP:
 	case NFT_GOTO:
-		if (nla_put_string(skb, NFTA_VERDICT_CHAIN, data->chain->name))
+		if (nla_put_string(skb, NFTA_VERDICT_CHAIN,
+				   data->verdict.chain->name))
 			goto nla_put_failure;
 	}
 	nla_nest_end(skb, nest);
@@ -4022,7 +4397,8 @@ nla_put_failure:
 	return -1;
 }
 
-static int nft_value_init(const struct nft_ctx *ctx, struct nft_data *data,
+static int nft_value_init(const struct nft_ctx *ctx,
+			  struct nft_data *data, unsigned int size,
 			  struct nft_data_desc *desc, const struct nlattr *nla)
 {
 	unsigned int len;
@@ -4030,10 +4406,10 @@ static int nft_value_init(const struct nft_ctx *ctx, struct nft_data *data,
 	len = nla_len(nla);
 	if (len == 0)
 		return -EINVAL;
-	if (len > sizeof(data->data))
+	if (len > size)
 		return -EOVERFLOW;
 
-	nla_memcpy(data->data, nla, sizeof(data->data));
+	nla_memcpy(data->data, nla, len);
 	desc->type = NFT_DATA_VALUE;
 	desc->len  = len;
 	return 0;
@@ -4046,8 +4422,7 @@ static int nft_value_dump(struct sk_buff *skb, const struct nft_data *data,
 }
 
 static const struct nla_policy nft_data_policy[NFTA_DATA_MAX + 1] = {
-	[NFTA_DATA_VALUE]	= { .type = NLA_BINARY,
-				    .len  = FIELD_SIZEOF(struct nft_data, data) },
+	[NFTA_DATA_VALUE]	= { .type = NLA_BINARY },
 	[NFTA_DATA_VERDICT]	= { .type = NLA_NESTED },
 };
 
@@ -4056,6 +4431,7 @@ static const struct nla_policy nft_data_policy[NFTA_DATA_MAX + 1] = {
  *
  *	@ctx: context of the expression using the data
  *	@data: destination struct nft_data
+ *	@size: maximum data length
  *	@desc: data description
  *	@nla: netlink attribute containing data
  *
@@ -4065,7 +4441,8 @@ static const struct nla_policy nft_data_policy[NFTA_DATA_MAX + 1] = {
  *	The caller can indicate that it only wants to accept data of type
  *	NFT_DATA_VALUE by passing NULL for the ctx argument.
  */
-int nft_data_init(const struct nft_ctx *ctx, struct nft_data *data,
+int nft_data_init(const struct nft_ctx *ctx,
+		  struct nft_data *data, unsigned int size,
 		  struct nft_data_desc *desc, const struct nlattr *nla)
 {
 	struct nlattr *tb[NFTA_DATA_MAX + 1];
@@ -4076,7 +4453,8 @@ int nft_data_init(const struct nft_ctx *ctx, struct nft_data *data,
 		return err;
 
 	if (tb[NFTA_DATA_VALUE])
-		return nft_value_init(ctx, data, desc, tb[NFTA_DATA_VALUE]);
+		return nft_value_init(ctx, data, size, desc,
+				      tb[NFTA_DATA_VALUE]);
 	if (tb[NFTA_DATA_VERDICT] && ctx != NULL)
 		return nft_verdict_init(ctx, data, desc, tb[NFTA_DATA_VERDICT]);
 	return -EINVAL;
@@ -4094,9 +4472,9 @@ EXPORT_SYMBOL_GPL(nft_data_init);
  */
 void nft_data_uninit(const struct nft_data *data, enum nft_data_types type)
 {
-	switch (type) {
-	case NFT_DATA_VALUE:
+	if (type < NFT_DATA_VERDICT)
 		return;
+	switch (type) {
 	case NFT_DATA_VERDICT:
 		return nft_verdict_uninit(data);
 	default:
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index 3b90eb2b2c55..f153b07073af 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -8,6 +8,7 @@
  * Development of this code funded by Astaro AG (http://www.astaro.com/)
  */
 
+#include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/list.h>
@@ -21,24 +22,66 @@
 #include <net/netfilter/nf_tables.h>
 #include <net/netfilter/nf_log.h>
 
+enum nft_trace {
+	NFT_TRACE_RULE,
+	NFT_TRACE_RETURN,
+	NFT_TRACE_POLICY,
+};
+
+static const char *const comments[] = {
+	[NFT_TRACE_RULE]	= "rule",
+	[NFT_TRACE_RETURN]	= "return",
+	[NFT_TRACE_POLICY]	= "policy",
+};
+
+static struct nf_loginfo trace_loginfo = {
+	.type = NF_LOG_TYPE_LOG,
+	.u = {
+		.log = {
+			.level = LOGLEVEL_WARNING,
+			.logflags = NF_LOG_MASK,
+	        },
+	},
+};
+
+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_trace(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);
+}
+
+static inline void nft_trace_packet(const struct nft_pktinfo *pkt,
+				    const struct nft_chain *chain,
+				    int rulenum, enum nft_trace type)
+{
+	if (unlikely(pkt->skb->nf_trace))
+		__nft_trace_packet(pkt, chain, rulenum, type);
+}
+
 static void nft_cmp_fast_eval(const struct nft_expr *expr,
-			      struct nft_data data[NFT_REG_MAX + 1])
+			      struct nft_regs *regs)
 {
 	const struct nft_cmp_fast_expr *priv = nft_expr_priv(expr);
 	u32 mask = nft_cmp_fast_mask(priv->len);
 
-	if ((data[priv->sreg].data[0] & mask) == priv->data)
+	if ((regs->data[priv->sreg] & mask) == priv->data)
 		return;
-	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+	regs->verdict.code = NFT_BREAK;
 }
 
 static bool nft_payload_fast_eval(const struct nft_expr *expr,
-				  struct nft_data data[NFT_REG_MAX + 1],
+				  struct nft_regs *regs,
 				  const struct nft_pktinfo *pkt)
 {
 	const struct nft_payload *priv = nft_expr_priv(expr);
 	const struct sk_buff *skb = pkt->skb;
-	struct nft_data *dest = &data[priv->dreg];
+	u32 *dest = &regs->data[priv->dreg];
 	unsigned char *ptr;
 
 	if (priv->base == NFT_PAYLOAD_NETWORK_HEADER)
@@ -51,12 +94,13 @@ static bool nft_payload_fast_eval(const struct nft_expr *expr,
 	if (unlikely(ptr + priv->len >= skb_tail_pointer(skb)))
 		return false;
 
+	*dest = 0;
 	if (priv->len == 2)
-		*(u16 *)dest->data = *(u16 *)ptr;
+		*(u16 *)dest = *(u16 *)ptr;
 	else if (priv->len == 4)
-		*(u32 *)dest->data = *(u32 *)ptr;
+		*(u32 *)dest = *(u32 *)ptr;
 	else
-		*(u8 *)dest->data = *(u8 *)ptr;
+		*(u8 *)dest = *(u8 *)ptr;
 	return true;
 }
 
@@ -66,62 +110,25 @@ struct nft_jumpstack {
 	int			rulenum;
 };
 
-enum nft_trace {
-	NFT_TRACE_RULE,
-	NFT_TRACE_RETURN,
-	NFT_TRACE_POLICY,
-};
-
-static const char *const comments[] = {
-	[NFT_TRACE_RULE]	= "rule",
-	[NFT_TRACE_RETURN]	= "return",
-	[NFT_TRACE_POLICY]	= "policy",
-};
-
-static struct nf_loginfo trace_loginfo = {
-	.type = NF_LOG_TYPE_LOG,
-	.u = {
-		.log = {
-			.level = 4,
-			.logflags = NF_LOG_MASK,
-	        },
-	},
-};
-
-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->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(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops)
 {
 	const struct nft_chain *chain = ops->priv, *basechain = chain;
+	const struct net *net = read_pnet(&nft_base_chain(basechain)->pnet);
 	const struct nft_rule *rule;
 	const struct nft_expr *expr, *last;
-	struct nft_data data[NFT_REG_MAX + 1];
+	struct nft_regs regs;
 	unsigned int stackptr = 0;
 	struct nft_jumpstack jumpstack[NFT_JUMP_STACK_SIZE];
 	struct nft_stats *stats;
 	int rulenum;
-	/*
-	 * Cache cursor to avoid problems in case that the cursor is updated
-	 * while traversing the ruleset.
-	 */
-	unsigned int gencursor = ACCESS_ONCE(chain->net->nft.gencursor);
+	unsigned int gencursor = nft_genmask_cur(net);
 
 do_chain:
 	rulenum = 0;
 	rule = list_entry(&chain->rules, struct nft_rule, list);
 next_rule:
-	data[NFT_REG_VERDICT].verdict = NFT_CONTINUE;
+	regs.verdict.code = NFT_CONTINUE;
 	list_for_each_entry_continue_rcu(rule, &chain->rules, list) {
 
 		/* This rule is not active, skip. */
@@ -132,62 +139,52 @@ next_rule:
 
 		nft_rule_for_each_expr(expr, last, rule) {
 			if (expr->ops == &nft_cmp_fast_ops)
-				nft_cmp_fast_eval(expr, data);
+				nft_cmp_fast_eval(expr, &regs);
 			else if (expr->ops != &nft_payload_fast_ops ||
-				 !nft_payload_fast_eval(expr, data, pkt))
-				expr->ops->eval(expr, data, pkt);
+				 !nft_payload_fast_eval(expr, &regs, pkt))
+				expr->ops->eval(expr, &regs, pkt);
 
-			if (data[NFT_REG_VERDICT].verdict != NFT_CONTINUE)
+			if (regs.verdict.code != NFT_CONTINUE)
 				break;
 		}
 
-		switch (data[NFT_REG_VERDICT].verdict) {
+		switch (regs.verdict.code) {
 		case NFT_BREAK:
-			data[NFT_REG_VERDICT].verdict = NFT_CONTINUE;
+			regs.verdict.code = NFT_CONTINUE;
 			continue;
 		case NFT_CONTINUE:
-			if (unlikely(pkt->skb->nf_trace))
-				nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE);
+			nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE);
 			continue;
 		}
 		break;
 	}
 
-	switch (data[NFT_REG_VERDICT].verdict & NF_VERDICT_MASK) {
+	switch (regs.verdict.code & NF_VERDICT_MASK) {
 	case NF_ACCEPT:
 	case NF_DROP:
 	case NF_QUEUE:
-		if (unlikely(pkt->skb->nf_trace))
-			nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE);
-
-		return data[NFT_REG_VERDICT].verdict;
+		nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE);
+		return regs.verdict.code;
 	}
 
-	switch (data[NFT_REG_VERDICT].verdict) {
+	switch (regs.verdict.code) {
 	case NFT_JUMP:
-		if (unlikely(pkt->skb->nf_trace))
-			nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE);
-
 		BUG_ON(stackptr >= NFT_JUMP_STACK_SIZE);
 		jumpstack[stackptr].chain = chain;
 		jumpstack[stackptr].rule  = rule;
 		jumpstack[stackptr].rulenum = rulenum;
 		stackptr++;
-		chain = data[NFT_REG_VERDICT].chain;
-		goto do_chain;
+		/* fall through */
 	case NFT_GOTO:
-		if (unlikely(pkt->skb->nf_trace))
-			nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE);
+		nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE);
 
-		chain = data[NFT_REG_VERDICT].chain;
+		chain = regs.verdict.chain;
 		goto do_chain;
-	case NFT_RETURN:
-		if (unlikely(pkt->skb->nf_trace))
-			nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RETURN);
-		break;
 	case NFT_CONTINUE:
-		if (unlikely(pkt->skb->nf_trace && !(chain->flags & NFT_BASE_CHAIN)))
-			nft_trace_packet(pkt, chain, ++rulenum, NFT_TRACE_RETURN);
+		rulenum++;
+		/* fall through */
+	case NFT_RETURN:
+		nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RETURN);
 		break;
 	default:
 		WARN_ON(1);
@@ -201,8 +198,7 @@ next_rule:
 		goto next_rule;
 	}
 
-	if (unlikely(pkt->skb->nf_trace))
-		nft_trace_packet(pkt, basechain, -1, 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));
@@ -244,8 +240,14 @@ int __init nf_tables_core_module_init(void)
 	if (err < 0)
 		goto err6;
 
+	err = nft_dynset_module_init();
+	if (err < 0)
+		goto err7;
+
 	return 0;
 
+err7:
+	nft_payload_module_exit();
 err6:
 	nft_byteorder_module_exit();
 err5:
@@ -262,6 +264,7 @@ err1:
 
 void nf_tables_core_module_exit(void)
 {
+	nft_dynset_module_exit();
 	nft_payload_module_exit();
 	nft_byteorder_module_exit();
 	nft_bitwise_module_exit();
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 6c5a915cfa75..8b117c90ecd7 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -47,6 +47,8 @@ static const int nfnl_group2type[NFNLGRP_MAX+1] = {
 	[NFNLGRP_CONNTRACK_EXP_NEW]	= NFNL_SUBSYS_CTNETLINK_EXP,
 	[NFNLGRP_CONNTRACK_EXP_UPDATE]	= NFNL_SUBSYS_CTNETLINK_EXP,
 	[NFNLGRP_CONNTRACK_EXP_DESTROY] = NFNL_SUBSYS_CTNETLINK_EXP,
+	[NFNLGRP_NFTABLES]		= NFNL_SUBSYS_NFTABLES,
+	[NFNLGRP_ACCT_QUOTA]		= NFNL_SUBSYS_ACCT,
 };
 
 void nfnl_lock(__u8 subsys_id)
@@ -270,7 +272,7 @@ static void nfnl_err_deliver(struct list_head *err_list, struct sk_buff *skb)
 static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh,
 				u_int16_t subsys_id)
 {
-	struct sk_buff *nskb, *oskb = skb;
+	struct sk_buff *oskb = skb;
 	struct net *net = sock_net(skb->sk);
 	const struct nfnetlink_subsystem *ss;
 	const struct nfnl_callback *nc;
@@ -281,12 +283,11 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (subsys_id >= NFNL_SUBSYS_COUNT)
 		return netlink_ack(skb, nlh, -EINVAL);
 replay:
-	nskb = netlink_skb_clone(oskb, GFP_KERNEL);
-	if (!nskb)
+	skb = netlink_skb_clone(oskb, GFP_KERNEL);
+	if (!skb)
 		return netlink_ack(oskb, nlh, -ENOMEM);
 
-	nskb->sk = oskb->sk;
-	skb = nskb;
+	skb->sk = oskb->sk;
 
 	nfnl_lock(subsys_id);
 	ss = rcu_dereference_protected(table[subsys_id].subsys,
@@ -303,7 +304,7 @@ replay:
 		{
 			nfnl_unlock(subsys_id);
 			netlink_ack(skb, nlh, -EOPNOTSUPP);
-			return kfree_skb(nskb);
+			return kfree_skb(skb);
 		}
 	}
 
@@ -319,7 +320,8 @@ replay:
 		nlh = nlmsg_hdr(skb);
 		err = 0;
 
-		if (nlh->nlmsg_len < NLMSG_HDRLEN) {
+		if (nlmsg_len(nlh) < sizeof(struct nfgenmsg) ||
+		    skb->len < nlh->nlmsg_len) {
 			err = -EINVAL;
 			goto ack;
 		}
@@ -383,7 +385,7 @@ replay:
 				nfnl_err_reset(&err_list);
 				ss->abort(oskb);
 				nfnl_unlock(subsys_id);
-				kfree_skb(nskb);
+				kfree_skb(skb);
 				goto replay;
 			}
 		}
@@ -424,7 +426,7 @@ done:
 
 	nfnl_err_deliver(&err_list, oskb);
 	nfnl_unlock(subsys_id);
-	kfree_skb(nskb);
+	kfree_skb(skb);
 }
 
 static void nfnetlink_rcv(struct sk_buff *skb)
@@ -461,10 +463,15 @@ static void nfnetlink_rcv(struct sk_buff *skb)
 }
 
 #ifdef CONFIG_MODULES
-static int nfnetlink_bind(int group)
+static int nfnetlink_bind(struct net *net, int group)
 {
 	const struct nfnetlink_subsystem *ss;
-	int type = nfnl_group2type[group];
+	int type;
+
+	if (group <= NFNLGRP_NONE || group > NFNLGRP_MAX)
+		return 0;
+
+	type = nfnl_group2type[group];
 
 	rcu_read_lock();
 	ss = nfnetlink_get_subsys(type);
@@ -514,6 +521,9 @@ static int __init nfnetlink_init(void)
 {
 	int i;
 
+	for (i = NFNLGRP_NONE + 1; i <= NFNLGRP_MAX; i++)
+		BUG_ON(nfnl_group2type[i] == NFNL_SUBSYS_NONE);
+
 	for (i=0; i<NFNL_SUBSYS_COUNT; i++)
 		mutex_init(&table[i].mutex);
 
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index 9e287cb56a04..54330fb5efaf 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -77,6 +77,9 @@ nfnl_cthelper_parse_tuple(struct nf_conntrack_tuple *tuple,
 	if (!tb[NFCTH_TUPLE_L3PROTONUM] || !tb[NFCTH_TUPLE_L4PROTONUM])
 		return -EINVAL;
 
+	/* Not all fields are initialized so first zero the tuple */
+	memset(tuple, 0, sizeof(struct nf_conntrack_tuple));
+
 	tuple->src.l3num = ntohs(nla_get_be16(tb[NFCTH_TUPLE_L3PROTONUM]));
 	tuple->dst.protonum = nla_get_u8(tb[NFCTH_TUPLE_L4PROTONUM]);
 
@@ -86,7 +89,7 @@ nfnl_cthelper_parse_tuple(struct nf_conntrack_tuple *tuple,
 static int
 nfnl_cthelper_from_nlattr(struct nlattr *attr, struct nf_conn *ct)
 {
-	const struct nf_conn_help *help = nfct_help(ct);
+	struct nf_conn_help *help = nfct_help(ct);
 
 	if (attr == NULL)
 		return -EINVAL;
@@ -94,7 +97,7 @@ nfnl_cthelper_from_nlattr(struct nlattr *attr, struct nf_conn *ct)
 	if (help->helper->data_len == 0)
 		return -EINVAL;
 
-	memcpy(&help->data, nla_data(attr), help->helper->data_len);
+	memcpy(help->data, nla_data(attr), help->helper->data_len);
 	return 0;
 }
 
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index 5f1be5ba3559..4ef1fae8445e 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -12,6 +12,9 @@
  * 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_arp.h>
@@ -20,6 +23,7 @@
 #include <linux/ipv6.h>
 #include <linux/netdevice.h>
 #include <linux/netfilter.h>
+#include <linux/netfilter_bridge.h>
 #include <net/netlink.h>
 #include <linux/netfilter/nfnetlink.h>
 #include <linux/netfilter/nfnetlink_log.h>
@@ -59,7 +63,7 @@ struct nfulnl_instance {
 	struct timer_list timer;
 	struct net *net;
 	struct user_namespace *peer_user_ns;	/* User namespace of the peer process */
-	int peer_portid;			/* PORTID of the peer process */
+	u32 peer_portid;		/* PORTID of the peer process */
 
 	/* configurable parameters */
 	unsigned int flushtimeout;	/* timeout until queue flush */
@@ -148,7 +152,7 @@ static void nfulnl_timer(unsigned long data);
 
 static struct nfulnl_instance *
 instance_create(struct net *net, u_int16_t group_num,
-		int portid, struct user_namespace *user_ns)
+		u32 portid, struct user_namespace *user_ns)
 {
 	struct nfulnl_instance *inst;
 	struct nfnl_log_net *log = nfnl_log_pernet(net);
@@ -337,9 +341,6 @@ nfulnl_alloc_skb(struct net *net, u32 peer_portid, unsigned int inst_size,
 
 			skb = nfnetlink_alloc_skb(net, pkt_size,
 						  peer_portid, GFP_ATOMIC);
-			if (!skb)
-				pr_err("nfnetlink_log: can't even alloc %u bytes\n",
-				       pkt_size);
 		}
 	}
 
@@ -448,14 +449,18 @@ __build_packet_message(struct nfnl_log_net *log,
 					 htonl(br_port_get_rcu(indev)->br->dev->ifindex)))
 				goto nla_put_failure;
 		} else {
+			struct net_device *physindev;
+
 			/* Case 2: indev is bridge group, we need to look for
 			 * physical device (when called from ipv4) */
 			if (nla_put_be32(inst->skb, NFULA_IFINDEX_INDEV,
 					 htonl(indev->ifindex)))
 				goto nla_put_failure;
-			if (skb->nf_bridge && skb->nf_bridge->physindev &&
+
+			physindev = nf_bridge_get_physindev(skb);
+			if (physindev &&
 			    nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSINDEV,
-					 htonl(skb->nf_bridge->physindev->ifindex)))
+					 htonl(physindev->ifindex)))
 				goto nla_put_failure;
 		}
 #endif
@@ -479,14 +484,18 @@ __build_packet_message(struct nfnl_log_net *log,
 					 htonl(br_port_get_rcu(outdev)->br->dev->ifindex)))
 				goto nla_put_failure;
 		} else {
+			struct net_device *physoutdev;
+
 			/* Case 2: indev is a bridge group, we need to look
 			 * for physical device (when called from ipv4) */
 			if (nla_put_be32(inst->skb, NFULA_IFINDEX_OUTDEV,
 					 htonl(outdev->ifindex)))
 				goto nla_put_failure;
-			if (skb->nf_bridge && skb->nf_bridge->physoutdev &&
+
+			physoutdev = nf_bridge_get_physoutdev(skb);
+			if (physoutdev &&
 			    nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSOUTDEV,
-					 htonl(skb->nf_bridge->physoutdev->ifindex)))
+					 htonl(physoutdev->ifindex)))
 				goto nla_put_failure;
 		}
 #endif
@@ -539,7 +548,7 @@ __build_packet_message(struct nfnl_log_net *log,
 
 	/* UID */
 	sk = skb->sk;
-	if (sk && sk->sk_state != TCP_TIME_WAIT) {
+	if (sk && sk_fullsock(sk)) {
 		read_lock_bh(&sk->sk_callback_lock);
 		if (sk->sk_socket && sk->sk_socket->file) {
 			struct file *file = sk->sk_socket->file;
@@ -570,10 +579,8 @@ __build_packet_message(struct nfnl_log_net *log,
 		struct nlattr *nla;
 		int size = nla_attr_size(data_len);
 
-		if (skb_tailroom(inst->skb) < nla_total_size(data_len)) {
-			printk(KERN_WARNING "nfnetlink_log: no tailroom!\n");
-			return -1;
-		}
+		if (skb_tailroom(inst->skb) < nla_total_size(data_len))
+			goto nla_put_failure;
 
 		nla = (struct nlattr *)skb_put(inst->skb, nla_total_size(data_len));
 		nla->nla_type = NFULA_PAYLOAD;
@@ -1000,11 +1007,13 @@ static int seq_show(struct seq_file *s, void *v)
 {
 	const struct nfulnl_instance *inst = v;
 
-	return seq_printf(s, "%5d %6d %5d %1d %5d %6d %2d\n",
-			  inst->group_num,
-			  inst->peer_portid, inst->qlen,
-			  inst->copy_mode, inst->copy_range,
-			  inst->flushtimeout, atomic_read(&inst->use));
+	seq_printf(s, "%5u %6u %5u %1u %5u %6u %2u\n",
+		   inst->group_num,
+		   inst->peer_portid, inst->qlen,
+		   inst->copy_mode, inst->copy_range,
+		   inst->flushtimeout, atomic_read(&inst->use));
+
+	return 0;
 }
 
 static const struct seq_operations nful_seq_ops = {
@@ -1064,43 +1073,44 @@ static struct pernet_operations nfnl_log_net_ops = {
 
 static int __init nfnetlink_log_init(void)
 {
-	int status = -ENOMEM;
+	int status;
+
+	status = register_pernet_subsys(&nfnl_log_net_ops);
+	if (status < 0) {
+		pr_err("failed to register pernet ops\n");
+		goto out;
+	}
 
 	netlink_register_notifier(&nfulnl_rtnl_notifier);
 	status = nfnetlink_subsys_register(&nfulnl_subsys);
 	if (status < 0) {
-		pr_err("log: failed to create netlink socket\n");
+		pr_err("failed to create netlink socket\n");
 		goto cleanup_netlink_notifier;
 	}
 
 	status = nf_log_register(NFPROTO_UNSPEC, &nfulnl_logger);
 	if (status < 0) {
-		pr_err("log: failed to register logger\n");
+		pr_err("failed to register logger\n");
 		goto cleanup_subsys;
 	}
 
-	status = register_pernet_subsys(&nfnl_log_net_ops);
-	if (status < 0) {
-		pr_err("log: failed to register pernet ops\n");
-		goto cleanup_logger;
-	}
 	return status;
 
-cleanup_logger:
-	nf_log_unregister(&nfulnl_logger);
 cleanup_subsys:
 	nfnetlink_subsys_unregister(&nfulnl_subsys);
 cleanup_netlink_notifier:
 	netlink_unregister_notifier(&nfulnl_rtnl_notifier);
+	unregister_pernet_subsys(&nfnl_log_net_ops);
+out:
 	return status;
 }
 
 static void __exit nfnetlink_log_fini(void)
 {
-	unregister_pernet_subsys(&nfnl_log_net_ops);
 	nf_log_unregister(&nfulnl_logger);
 	nfnetlink_subsys_unregister(&nfulnl_subsys);
 	netlink_unregister_notifier(&nfulnl_rtnl_notifier);
+	unregister_pernet_subsys(&nfnl_log_net_ops);
 }
 
 MODULE_DESCRIPTION("netfilter userspace logging");
diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c
index 7c60ccd61a3e..11c7682fa0ea 100644
--- a/net/netfilter/nfnetlink_queue_core.c
+++ b/net/netfilter/nfnetlink_queue_core.c
@@ -25,6 +25,7 @@
 #include <linux/proc_fs.h>
 #include <linux/netfilter_ipv4.h>
 #include <linux/netfilter_ipv6.h>
+#include <linux/netfilter_bridge.h>
 #include <linux/netfilter/nfnetlink.h>
 #include <linux/netfilter/nfnetlink_queue.h>
 #include <linux/list.h>
@@ -54,7 +55,7 @@ struct nfqnl_instance {
 	struct hlist_node hlist;		/* global list of queues */
 	struct rcu_head rcu;
 
-	int peer_portid;
+	u32 peer_portid;
 	unsigned int queue_maxlen;
 	unsigned int copy_range;
 	unsigned int queue_dropped;
@@ -109,8 +110,7 @@ instance_lookup(struct nfnl_queue_net *q, u_int16_t queue_num)
 }
 
 static struct nfqnl_instance *
-instance_create(struct nfnl_queue_net *q, u_int16_t queue_num,
-		int portid)
+instance_create(struct nfnl_queue_net *q, u_int16_t queue_num, u32 portid)
 {
 	struct nfqnl_instance *inst;
 	unsigned int h;
@@ -257,7 +257,7 @@ static int nfqnl_put_sk_uidgid(struct sk_buff *skb, struct sock *sk)
 {
 	const struct cred *cred;
 
-	if (sk->sk_state == TCP_TIME_WAIT)
+	if (!sk_fullsock(sk))
 		return 0;
 
 	read_lock_bh(&sk->sk_callback_lock);
@@ -314,13 +314,13 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 	if (entskb->tstamp.tv64)
 		size += nla_total_size(sizeof(struct nfqnl_msg_packet_timestamp));
 
-	if (entry->hook <= NF_INET_FORWARD ||
-	   (entry->hook == NF_INET_POST_ROUTING && entskb->sk == NULL))
+	if (entry->state.hook <= NF_INET_FORWARD ||
+	   (entry->state.hook == NF_INET_POST_ROUTING && entskb->sk == NULL))
 		csum_verify = !skb_csum_unnecessary(entskb);
 	else
 		csum_verify = false;
 
-	outdev = entry->outdev;
+	outdev = entry->state.out;
 
 	switch ((enum nfqnl_config_mode)ACCESS_ONCE(queue->copy_mode)) {
 	case NFQNL_COPY_META:
@@ -368,23 +368,23 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 		return NULL;
 	}
 	nfmsg = nlmsg_data(nlh);
-	nfmsg->nfgen_family = entry->pf;
+	nfmsg->nfgen_family = entry->state.pf;
 	nfmsg->version = NFNETLINK_V0;
 	nfmsg->res_id = htons(queue->queue_num);
 
 	nla = __nla_reserve(skb, NFQA_PACKET_HDR, sizeof(*pmsg));
 	pmsg = nla_data(nla);
 	pmsg->hw_protocol	= entskb->protocol;
-	pmsg->hook		= entry->hook;
+	pmsg->hook		= entry->state.hook;
 	*packet_id_ptr		= &pmsg->packet_id;
 
-	indev = entry->indev;
+	indev = entry->state.in;
 	if (indev) {
 #if !IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 		if (nla_put_be32(skb, NFQA_IFINDEX_INDEV, htonl(indev->ifindex)))
 			goto nla_put_failure;
 #else
-		if (entry->pf == PF_BRIDGE) {
+		if (entry->state.pf == PF_BRIDGE) {
 			/* Case 1: indev is physical input device, we need to
 			 * look for bridge group (when called from
 			 * netfilter_bridge) */
@@ -396,14 +396,18 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 					 htonl(br_port_get_rcu(indev)->br->dev->ifindex)))
 				goto nla_put_failure;
 		} else {
+			int physinif;
+
 			/* Case 2: indev is bridge group, we need to look for
 			 * physical device (when called from ipv4) */
 			if (nla_put_be32(skb, NFQA_IFINDEX_INDEV,
 					 htonl(indev->ifindex)))
 				goto nla_put_failure;
-			if (entskb->nf_bridge && entskb->nf_bridge->physindev &&
+
+			physinif = nf_bridge_get_physinif(entskb);
+			if (physinif &&
 			    nla_put_be32(skb, NFQA_IFINDEX_PHYSINDEV,
-					 htonl(entskb->nf_bridge->physindev->ifindex)))
+					 htonl(physinif)))
 				goto nla_put_failure;
 		}
 #endif
@@ -414,7 +418,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 		if (nla_put_be32(skb, NFQA_IFINDEX_OUTDEV, htonl(outdev->ifindex)))
 			goto nla_put_failure;
 #else
-		if (entry->pf == PF_BRIDGE) {
+		if (entry->state.pf == PF_BRIDGE) {
 			/* Case 1: outdev is physical output device, we need to
 			 * look for bridge group (when called from
 			 * netfilter_bridge) */
@@ -426,14 +430,18 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 					 htonl(br_port_get_rcu(outdev)->br->dev->ifindex)))
 				goto nla_put_failure;
 		} else {
+			int physoutif;
+
 			/* Case 2: outdev is bridge group, we need to look for
 			 * physical output device (when called from ipv4) */
 			if (nla_put_be32(skb, NFQA_IFINDEX_OUTDEV,
 					 htonl(outdev->ifindex)))
 				goto nla_put_failure;
-			if (entskb->nf_bridge && entskb->nf_bridge->physoutdev &&
+
+			physoutif = nf_bridge_get_physoutif(entskb);
+			if (physoutif &&
 			    nla_put_be32(skb, NFQA_IFINDEX_PHYSOUTDEV,
-					 htonl(entskb->nf_bridge->physoutdev->ifindex)))
+					 htonl(physoutif)))
 				goto nla_put_failure;
 		}
 #endif
@@ -633,8 +641,8 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum)
 	struct nfqnl_instance *queue;
 	struct sk_buff *skb, *segs;
 	int err = -ENOBUFS;
-	struct net *net = dev_net(entry->indev ?
-				  entry->indev : entry->outdev);
+	struct net *net = dev_net(entry->state.in ?
+				  entry->state.in : entry->state.out);
 	struct nfnl_queue_net *q = nfnl_queue_pernet(net);
 
 	/* rcu_read_lock()ed by nf_hook_slow() */
@@ -647,7 +655,7 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum)
 
 	skb = entry->skb;
 
-	switch (entry->pf) {
+	switch (entry->state.pf) {
 	case NFPROTO_IPV4:
 		skb->protocol = htons(ETH_P_IP);
 		break;
@@ -757,19 +765,20 @@ nfqnl_set_mode(struct nfqnl_instance *queue,
 static int
 dev_cmp(struct nf_queue_entry *entry, unsigned long ifindex)
 {
-	if (entry->indev)
-		if (entry->indev->ifindex == ifindex)
+	if (entry->state.in)
+		if (entry->state.in->ifindex == ifindex)
 			return 1;
-	if (entry->outdev)
-		if (entry->outdev->ifindex == ifindex)
+	if (entry->state.out)
+		if (entry->state.out->ifindex == ifindex)
 			return 1;
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	if (entry->skb->nf_bridge) {
-		if (entry->skb->nf_bridge->physindev &&
-		    entry->skb->nf_bridge->physindev->ifindex == ifindex)
-			return 1;
-		if (entry->skb->nf_bridge->physoutdev &&
-		    entry->skb->nf_bridge->physoutdev->ifindex == ifindex)
+		int physinif, physoutif;
+
+		physinif = nf_bridge_get_physinif(entry->skb);
+		physoutif = nf_bridge_get_physoutif(entry->skb);
+
+		if (physinif == ifindex || physoutif == ifindex)
 			return 1;
 	}
 #endif
@@ -860,7 +869,7 @@ static const struct nla_policy nfqa_verdict_batch_policy[NFQA_MAX+1] = {
 };
 
 static struct nfqnl_instance *
-verdict_instance_lookup(struct nfnl_queue_net *q, u16 queue_num, int nlportid)
+verdict_instance_lookup(struct nfnl_queue_net *q, u16 queue_num, u32 nlportid)
 {
 	struct nfqnl_instance *queue;
 
@@ -1242,12 +1251,13 @@ static int seq_show(struct seq_file *s, void *v)
 {
 	const struct nfqnl_instance *inst = v;
 
-	return seq_printf(s, "%5d %6d %5d %1d %5d %5d %5d %8d %2d\n",
-			  inst->queue_num,
-			  inst->peer_portid, inst->queue_total,
-			  inst->copy_mode, inst->copy_range,
-			  inst->queue_dropped, inst->queue_user_dropped,
-			  inst->id_sequence, 1);
+	seq_printf(s, "%5u %6u %5u %1u %5u %5u %5u %8u %2d\n",
+		   inst->queue_num,
+		   inst->peer_portid, inst->queue_total,
+		   inst->copy_mode, inst->copy_range,
+		   inst->queue_dropped, inst->queue_user_dropped,
+		   inst->id_sequence, 1);
+	return seq_has_overflowed(s);
 }
 
 static const struct seq_operations nfqnl_seq_ops = {
@@ -1307,7 +1317,13 @@ static struct pernet_operations nfnl_queue_net_ops = {
 
 static int __init nfnetlink_queue_init(void)
 {
-	int status = -ENOMEM;
+	int status;
+
+	status = register_pernet_subsys(&nfnl_queue_net_ops);
+	if (status < 0) {
+		pr_err("nf_queue: failed to register pernet ops\n");
+		goto out;
+	}
 
 	netlink_register_notifier(&nfqnl_rtnl_notifier);
 	status = nfnetlink_subsys_register(&nfqnl_subsys);
@@ -1316,19 +1332,13 @@ static int __init nfnetlink_queue_init(void)
 		goto cleanup_netlink_notifier;
 	}
 
-	status = register_pernet_subsys(&nfnl_queue_net_ops);
-	if (status < 0) {
-		pr_err("nf_queue: failed to register pernet ops\n");
-		goto cleanup_subsys;
-	}
 	register_netdevice_notifier(&nfqnl_dev_notifier);
 	nf_register_queue_handler(&nfqh);
 	return status;
 
-cleanup_subsys:
-	nfnetlink_subsys_unregister(&nfqnl_subsys);
 cleanup_netlink_notifier:
 	netlink_unregister_notifier(&nfqnl_rtnl_notifier);
+out:
 	return status;
 }
 
@@ -1336,9 +1346,9 @@ static void __exit nfnetlink_queue_fini(void)
 {
 	nf_unregister_queue_handler();
 	unregister_netdevice_notifier(&nfqnl_dev_notifier);
-	unregister_pernet_subsys(&nfnl_queue_net_ops);
 	nfnetlink_subsys_unregister(&nfqnl_subsys);
 	netlink_unregister_notifier(&nfqnl_rtnl_notifier);
+	unregister_pernet_subsys(&nfnl_queue_net_ops);
 
 	rcu_barrier(); /* Wait for completion of call_rcu()'s */
 }
diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c
index 4fb6ee2c1106..d71cc18fa35d 100644
--- a/net/netfilter/nft_bitwise.c
+++ b/net/netfilter/nft_bitwise.c
@@ -26,18 +26,16 @@ struct nft_bitwise {
 };
 
 static void nft_bitwise_eval(const struct nft_expr *expr,
-			     struct nft_data data[NFT_REG_MAX + 1],
+			     struct nft_regs *regs,
 			     const struct nft_pktinfo *pkt)
 {
 	const struct nft_bitwise *priv = nft_expr_priv(expr);
-	const struct nft_data *src = &data[priv->sreg];
-	struct nft_data *dst = &data[priv->dreg];
+	const u32 *src = &regs->data[priv->sreg];
+	u32 *dst = &regs->data[priv->dreg];
 	unsigned int i;
 
-	for (i = 0; i < DIV_ROUND_UP(priv->len, 4); i++) {
-		dst->data[i] = (src->data[i] & priv->mask.data[i]) ^
-			       priv->xor.data[i];
-	}
+	for (i = 0; i < DIV_ROUND_UP(priv->len, 4); i++)
+		dst[i] = (src[i] & priv->mask.data[i]) ^ priv->xor.data[i];
 }
 
 static const struct nla_policy nft_bitwise_policy[NFTA_BITWISE_MAX + 1] = {
@@ -63,28 +61,27 @@ static int nft_bitwise_init(const struct nft_ctx *ctx,
 	    tb[NFTA_BITWISE_XOR] == NULL)
 		return -EINVAL;
 
-	priv->sreg = ntohl(nla_get_be32(tb[NFTA_BITWISE_SREG]));
-	err = nft_validate_input_register(priv->sreg);
+	priv->len  = ntohl(nla_get_be32(tb[NFTA_BITWISE_LEN]));
+	priv->sreg = nft_parse_register(tb[NFTA_BITWISE_SREG]);
+	err = nft_validate_register_load(priv->sreg, priv->len);
 	if (err < 0)
 		return err;
 
-	priv->dreg = ntohl(nla_get_be32(tb[NFTA_BITWISE_DREG]));
-	err = nft_validate_output_register(priv->dreg);
+	priv->dreg = nft_parse_register(tb[NFTA_BITWISE_DREG]);
+	err = nft_validate_register_store(ctx, priv->dreg, NULL,
+					  NFT_DATA_VALUE, priv->len);
 	if (err < 0)
 		return err;
-	err = nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE);
-	if (err < 0)
-		return err;
-
-	priv->len = ntohl(nla_get_be32(tb[NFTA_BITWISE_LEN]));
 
-	err = nft_data_init(NULL, &priv->mask, &d1, tb[NFTA_BITWISE_MASK]);
+	err = nft_data_init(NULL, &priv->mask, sizeof(priv->mask), &d1,
+			    tb[NFTA_BITWISE_MASK]);
 	if (err < 0)
 		return err;
 	if (d1.len != priv->len)
 		return -EINVAL;
 
-	err = nft_data_init(NULL, &priv->xor, &d2, tb[NFTA_BITWISE_XOR]);
+	err = nft_data_init(NULL, &priv->xor, sizeof(priv->xor), &d2,
+			    tb[NFTA_BITWISE_XOR]);
 	if (err < 0)
 		return err;
 	if (d2.len != priv->len)
@@ -97,9 +94,9 @@ static int nft_bitwise_dump(struct sk_buff *skb, const struct nft_expr *expr)
 {
 	const struct nft_bitwise *priv = nft_expr_priv(expr);
 
-	if (nla_put_be32(skb, NFTA_BITWISE_SREG, htonl(priv->sreg)))
+	if (nft_dump_register(skb, NFTA_BITWISE_SREG, priv->sreg))
 		goto nla_put_failure;
-	if (nla_put_be32(skb, NFTA_BITWISE_DREG, htonl(priv->dreg)))
+	if (nft_dump_register(skb, NFTA_BITWISE_DREG, priv->dreg))
 		goto nla_put_failure;
 	if (nla_put_be32(skb, NFTA_BITWISE_LEN, htonl(priv->len)))
 		goto nla_put_failure;
diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c
index c39ed8d29df1..fde5145f2e36 100644
--- a/net/netfilter/nft_byteorder.c
+++ b/net/netfilter/nft_byteorder.c
@@ -26,16 +26,17 @@ struct nft_byteorder {
 };
 
 static void nft_byteorder_eval(const struct nft_expr *expr,
-			       struct nft_data data[NFT_REG_MAX + 1],
+			       struct nft_regs *regs,
 			       const struct nft_pktinfo *pkt)
 {
 	const struct nft_byteorder *priv = nft_expr_priv(expr);
-	struct nft_data *src = &data[priv->sreg], *dst = &data[priv->dreg];
+	u32 *src = &regs->data[priv->sreg];
+	u32 *dst = &regs->data[priv->dreg];
 	union { u32 u32; u16 u16; } *s, *d;
 	unsigned int i;
 
-	s = (void *)src->data;
-	d = (void *)dst->data;
+	s = (void *)src;
+	d = (void *)dst;
 
 	switch (priv->size) {
 	case 4:
@@ -87,19 +88,6 @@ static int nft_byteorder_init(const struct nft_ctx *ctx,
 	    tb[NFTA_BYTEORDER_OP] == NULL)
 		return -EINVAL;
 
-	priv->sreg = ntohl(nla_get_be32(tb[NFTA_BYTEORDER_SREG]));
-	err = nft_validate_input_register(priv->sreg);
-	if (err < 0)
-		return err;
-
-	priv->dreg = ntohl(nla_get_be32(tb[NFTA_BYTEORDER_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;
-
 	priv->op = ntohl(nla_get_be32(tb[NFTA_BYTEORDER_OP]));
 	switch (priv->op) {
 	case NFT_BYTEORDER_NTOH:
@@ -109,10 +97,6 @@ static int nft_byteorder_init(const struct nft_ctx *ctx,
 		return -EINVAL;
 	}
 
-	priv->len = ntohl(nla_get_be32(tb[NFTA_BYTEORDER_LEN]));
-	if (priv->len == 0 || priv->len > FIELD_SIZEOF(struct nft_data, data))
-		return -EINVAL;
-
 	priv->size = ntohl(nla_get_be32(tb[NFTA_BYTEORDER_SIZE]));
 	switch (priv->size) {
 	case 2:
@@ -122,16 +106,24 @@ static int nft_byteorder_init(const struct nft_ctx *ctx,
 		return -EINVAL;
 	}
 
-	return 0;
+	priv->sreg = nft_parse_register(tb[NFTA_BYTEORDER_SREG]);
+	priv->len  = ntohl(nla_get_be32(tb[NFTA_BYTEORDER_LEN]));
+	err = nft_validate_register_load(priv->sreg, priv->len);
+	if (err < 0)
+		return err;
+
+	priv->dreg = nft_parse_register(tb[NFTA_BYTEORDER_DREG]);
+	return nft_validate_register_store(ctx, priv->dreg, NULL,
+					   NFT_DATA_VALUE, priv->len);
 }
 
 static int nft_byteorder_dump(struct sk_buff *skb, const struct nft_expr *expr)
 {
 	const struct nft_byteorder *priv = nft_expr_priv(expr);
 
-	if (nla_put_be32(skb, NFTA_BYTEORDER_SREG, htonl(priv->sreg)))
+	if (nft_dump_register(skb, NFTA_BYTEORDER_SREG, priv->sreg))
 		goto nla_put_failure;
-	if (nla_put_be32(skb, NFTA_BYTEORDER_DREG, htonl(priv->dreg)))
+	if (nft_dump_register(skb, NFTA_BYTEORDER_DREG, priv->dreg))
 		goto nla_put_failure;
 	if (nla_put_be32(skb, NFTA_BYTEORDER_OP, htonl(priv->op)))
 		goto nla_put_failure;
diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c
index e2b3f51c81f1..e25b35d70e4d 100644
--- a/net/netfilter/nft_cmp.c
+++ b/net/netfilter/nft_cmp.c
@@ -25,13 +25,13 @@ struct nft_cmp_expr {
 };
 
 static void nft_cmp_eval(const struct nft_expr *expr,
-			 struct nft_data data[NFT_REG_MAX + 1],
+			 struct nft_regs *regs,
 			 const struct nft_pktinfo *pkt)
 {
 	const struct nft_cmp_expr *priv = nft_expr_priv(expr);
 	int d;
 
-	d = nft_data_cmp(&data[priv->sreg], &priv->data, priv->len);
+	d = memcmp(&regs->data[priv->sreg], &priv->data, priv->len);
 	switch (priv->op) {
 	case NFT_CMP_EQ:
 		if (d != 0)
@@ -59,7 +59,7 @@ static void nft_cmp_eval(const struct nft_expr *expr,
 	return;
 
 mismatch:
-	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+	regs->verdict.code = NFT_BREAK;
 }
 
 static const struct nla_policy nft_cmp_policy[NFTA_CMP_MAX + 1] = {
@@ -75,12 +75,16 @@ static int nft_cmp_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 	struct nft_data_desc desc;
 	int err;
 
-	priv->sreg = ntohl(nla_get_be32(tb[NFTA_CMP_SREG]));
-	priv->op = ntohl(nla_get_be32(tb[NFTA_CMP_OP]));
-
-	err = nft_data_init(NULL, &priv->data, &desc, tb[NFTA_CMP_DATA]);
+	err = nft_data_init(NULL, &priv->data, sizeof(priv->data), &desc,
+			    tb[NFTA_CMP_DATA]);
 	BUG_ON(err < 0);
 
+	priv->sreg = nft_parse_register(tb[NFTA_CMP_SREG]);
+	err = nft_validate_register_load(priv->sreg, desc.len);
+	if (err < 0)
+		return err;
+
+	priv->op  = ntohl(nla_get_be32(tb[NFTA_CMP_OP]));
 	priv->len = desc.len;
 	return 0;
 }
@@ -89,7 +93,7 @@ static int nft_cmp_dump(struct sk_buff *skb, const struct nft_expr *expr)
 {
 	const struct nft_cmp_expr *priv = nft_expr_priv(expr);
 
-	if (nla_put_be32(skb, NFTA_CMP_SREG, htonl(priv->sreg)))
+	if (nft_dump_register(skb, NFTA_CMP_SREG, priv->sreg))
 		goto nla_put_failure;
 	if (nla_put_be32(skb, NFTA_CMP_OP, htonl(priv->op)))
 		goto nla_put_failure;
@@ -122,13 +126,18 @@ static int nft_cmp_fast_init(const struct nft_ctx *ctx,
 	u32 mask;
 	int err;
 
-	priv->sreg = ntohl(nla_get_be32(tb[NFTA_CMP_SREG]));
-
-	err = nft_data_init(NULL, &data, &desc, tb[NFTA_CMP_DATA]);
+	err = nft_data_init(NULL, &data, sizeof(data), &desc,
+			    tb[NFTA_CMP_DATA]);
 	BUG_ON(err < 0);
-	desc.len *= BITS_PER_BYTE;
 
+	priv->sreg = nft_parse_register(tb[NFTA_CMP_SREG]);
+	err = nft_validate_register_load(priv->sreg, desc.len);
+	if (err < 0)
+		return err;
+
+	desc.len *= BITS_PER_BYTE;
 	mask = nft_cmp_fast_mask(desc.len);
+
 	priv->data = data.data[0] & mask;
 	priv->len  = desc.len;
 	return 0;
@@ -139,7 +148,7 @@ static int nft_cmp_fast_dump(struct sk_buff *skb, const struct nft_expr *expr)
 	const struct nft_cmp_fast_expr *priv = nft_expr_priv(expr);
 	struct nft_data data;
 
-	if (nla_put_be32(skb, NFTA_CMP_SREG, htonl(priv->sreg)))
+	if (nft_dump_register(skb, NFTA_CMP_SREG, priv->sreg))
 		goto nla_put_failure;
 	if (nla_put_be32(skb, NFTA_CMP_OP, htonl(NFT_CMP_EQ)))
 		goto nla_put_failure;
@@ -167,7 +176,6 @@ nft_cmp_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[])
 {
 	struct nft_data_desc desc;
 	struct nft_data data;
-	enum nft_registers sreg;
 	enum nft_cmp_ops op;
 	int err;
 
@@ -176,11 +184,6 @@ nft_cmp_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[])
 	    tb[NFTA_CMP_DATA] == NULL)
 		return ERR_PTR(-EINVAL);
 
-	sreg = ntohl(nla_get_be32(tb[NFTA_CMP_SREG]));
-	err = nft_validate_input_register(sreg);
-	if (err < 0)
-		return ERR_PTR(err);
-
 	op = ntohl(nla_get_be32(tb[NFTA_CMP_OP]));
 	switch (op) {
 	case NFT_CMP_EQ:
@@ -194,7 +197,8 @@ nft_cmp_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[])
 		return ERR_PTR(-EINVAL);
 	}
 
-	err = nft_data_init(NULL, &data, &desc, tb[NFTA_CMP_DATA]);
+	err = nft_data_init(NULL, &data, sizeof(data), &desc,
+			    tb[NFTA_CMP_DATA]);
 	if (err < 0)
 		return ERR_PTR(err);
 
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 9d6d6f60a80f..7f29cfc76349 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -19,47 +19,21 @@
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter_ipv4/ip_tables.h>
 #include <linux/netfilter_ipv6/ip6_tables.h>
+#include <linux/netfilter_bridge/ebtables.h>
+#include <linux/netfilter_arp/arp_tables.h>
 #include <net/netfilter/nf_tables.h>
 
-static const struct {
-       const char	*name;
-       u8		type;
-} table_to_chaintype[] = {
-       { "filter",     NFT_CHAIN_T_DEFAULT },
-       { "raw",        NFT_CHAIN_T_DEFAULT },
-       { "security",   NFT_CHAIN_T_DEFAULT },
-       { "mangle",     NFT_CHAIN_T_ROUTE },
-       { "nat",        NFT_CHAIN_T_NAT },
-       { },
-};
-
-static int nft_compat_table_to_chaintype(const char *table)
-{
-	int i;
-
-	for (i = 0; table_to_chaintype[i].name != NULL; i++) {
-		if (strcmp(table_to_chaintype[i].name, table) == 0)
-			return table_to_chaintype[i].type;
-	}
-
-	return -1;
-}
-
 static int nft_compat_chain_validate_dependency(const char *tablename,
 						const struct nft_chain *chain)
 {
-	enum nft_chain_type type;
 	const struct nft_base_chain *basechain;
 
 	if (!tablename || !(chain->flags & NFT_BASE_CHAIN))
 		return 0;
 
-	type = nft_compat_table_to_chaintype(tablename);
-	if (type < 0)
-		return -EINVAL;
-
 	basechain = nft_base_chain(chain);
-	if (basechain->type->type != type)
+	if (strcmp(tablename, "nat") == 0 &&
+	    basechain->type->type != NFT_CHAIN_T_NAT)
 		return -EINVAL;
 
 	return 0;
@@ -68,6 +42,8 @@ static int nft_compat_chain_validate_dependency(const char *tablename,
 union nft_entry {
 	struct ipt_entry e4;
 	struct ip6t_entry e6;
+	struct ebt_entry ebt;
+	struct arpt_entry arp;
 };
 
 static inline void
@@ -78,9 +54,9 @@ nft_compat_set_par(struct xt_action_param *par, void *xt, const void *xt_info)
 	par->hotdrop	= false;
 }
 
-static void nft_target_eval(const struct nft_expr *expr,
-			    struct nft_data data[NFT_REG_MAX + 1],
-			    const struct nft_pktinfo *pkt)
+static void nft_target_eval_xt(const struct nft_expr *expr,
+			       struct nft_regs *regs,
+			       const struct nft_pktinfo *pkt)
 {
 	void *info = nft_expr_priv(expr);
 	struct xt_target *target = expr->ops->data;
@@ -94,15 +70,49 @@ static void nft_target_eval(const struct nft_expr *expr,
 	if (pkt->xt.hotdrop)
 		ret = NF_DROP;
 
-	switch(ret) {
+	switch (ret) {
 	case XT_CONTINUE:
-		data[NFT_REG_VERDICT].verdict = NFT_CONTINUE;
+		regs->verdict.code = NFT_CONTINUE;
+		break;
+	default:
+		regs->verdict.code = ret;
+		break;
+	}
+}
+
+static void nft_target_eval_bridge(const struct nft_expr *expr,
+				   struct nft_regs *regs,
+				   const struct nft_pktinfo *pkt)
+{
+	void *info = nft_expr_priv(expr);
+	struct xt_target *target = expr->ops->data;
+	struct sk_buff *skb = pkt->skb;
+	int ret;
+
+	nft_compat_set_par((struct xt_action_param *)&pkt->xt, target, info);
+
+	ret = target->target(skb, &pkt->xt);
+
+	if (pkt->xt.hotdrop)
+		ret = NF_DROP;
+
+	switch (ret) {
+	case EBT_ACCEPT:
+		regs->verdict.code = NF_ACCEPT;
+		break;
+	case EBT_DROP:
+		regs->verdict.code = NF_DROP;
+		break;
+	case EBT_CONTINUE:
+		regs->verdict.code = NFT_CONTINUE;
+		break;
+	case EBT_RETURN:
+		regs->verdict.code = NFT_RETURN;
 		break;
 	default:
-		data[NFT_REG_VERDICT].verdict = ret;
+		regs->verdict.code = ret;
 		break;
 	}
-	return;
 }
 
 static const struct nla_policy nft_target_policy[NFTA_TARGET_MAX + 1] = {
@@ -115,9 +125,9 @@ static void
 nft_target_set_tgchk_param(struct xt_tgchk_param *par,
 			   const struct nft_ctx *ctx,
 			   struct xt_target *target, void *info,
-			   union nft_entry *entry, u8 proto, bool inv)
+			   union nft_entry *entry, u16 proto, bool inv)
 {
-	par->net	= &init_net;
+	par->net	= ctx->net;
 	par->table	= ctx->table->name;
 	switch (ctx->afi->family) {
 	case AF_INET:
@@ -125,9 +135,18 @@ nft_target_set_tgchk_param(struct xt_tgchk_param *par,
 		entry->e4.ip.invflags = inv ? IPT_INV_PROTO : 0;
 		break;
 	case AF_INET6:
+		if (proto)
+			entry->e6.ipv6.flags |= IP6T_F_PROTO;
+
 		entry->e6.ipv6.proto = proto;
 		entry->e6.ipv6.invflags = inv ? IP6T_INV_PROTO : 0;
 		break;
+	case NFPROTO_BRIDGE:
+		entry->ebt.ethproto = (__force __be16)proto;
+		entry->ebt.invflags = inv ? EBT_IPROTO : 0;
+		break;
+	case NFPROTO_ARP:
+		break;
 	}
 	par->entryinfo	= entry;
 	par->target	= target;
@@ -159,7 +178,7 @@ static const struct nla_policy nft_rule_compat_policy[NFTA_RULE_COMPAT_MAX + 1]
 	[NFTA_RULE_COMPAT_FLAGS]	= { .type = NLA_U32 },
 };
 
-static int nft_parse_compat(const struct nlattr *attr, u8 *proto, bool *inv)
+static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv)
 {
 	struct nlattr *tb[NFTA_RULE_COMPAT_MAX+1];
 	u32 flags;
@@ -191,7 +210,7 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 	struct xt_target *target = expr->ops->data;
 	struct xt_tgchk_param par;
 	size_t size = XT_ALIGN(nla_len(tb[NFTA_TARGET_INFO]));
-	u8 proto = 0;
+	u16 proto = 0;
 	bool inv = false;
 	union nft_entry e = {};
 	int ret;
@@ -285,7 +304,7 @@ static int nft_target_validate(const struct nft_ctx *ctx,
 }
 
 static void nft_match_eval(const struct nft_expr *expr,
-			   struct nft_data data[NFT_REG_MAX + 1],
+			   struct nft_regs *regs,
 			   const struct nft_pktinfo *pkt)
 {
 	void *info = nft_expr_priv(expr);
@@ -298,16 +317,16 @@ static void nft_match_eval(const struct nft_expr *expr,
 	ret = match->match(skb, (struct xt_action_param *)&pkt->xt);
 
 	if (pkt->xt.hotdrop) {
-		data[NFT_REG_VERDICT].verdict = NF_DROP;
+		regs->verdict.code = NF_DROP;
 		return;
 	}
 
-	switch(ret) {
-	case true:
-		data[NFT_REG_VERDICT].verdict = NFT_CONTINUE;
+	switch (ret ? 1 : 0) {
+	case 1:
+		regs->verdict.code = NFT_CONTINUE;
 		break;
-	case false:
-		data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+	case 0:
+		regs->verdict.code = NFT_BREAK;
 		break;
 	}
 }
@@ -322,9 +341,9 @@ static const struct nla_policy nft_match_policy[NFTA_MATCH_MAX + 1] = {
 static void
 nft_match_set_mtchk_param(struct xt_mtchk_param *par, const struct nft_ctx *ctx,
 			  struct xt_match *match, void *info,
-			  union nft_entry *entry, u8 proto, bool inv)
+			  union nft_entry *entry, u16 proto, bool inv)
 {
-	par->net	= &init_net;
+	par->net	= ctx->net;
 	par->table	= ctx->table->name;
 	switch (ctx->afi->family) {
 	case AF_INET:
@@ -332,9 +351,18 @@ nft_match_set_mtchk_param(struct xt_mtchk_param *par, const struct nft_ctx *ctx,
 		entry->e4.ip.invflags = inv ? IPT_INV_PROTO : 0;
 		break;
 	case AF_INET6:
+		if (proto)
+			entry->e6.ipv6.flags |= IP6T_F_PROTO;
+
 		entry->e6.ipv6.proto = proto;
 		entry->e6.ipv6.invflags = inv ? IP6T_INV_PROTO : 0;
 		break;
+	case NFPROTO_BRIDGE:
+		entry->ebt.ethproto = (__force __be16)proto;
+		entry->ebt.invflags = inv ? EBT_IPROTO : 0;
+		break;
+	case NFPROTO_ARP:
+		break;
 	}
 	par->entryinfo	= entry;
 	par->match	= match;
@@ -369,12 +397,12 @@ nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 	struct xt_match *match = expr->ops->data;
 	struct xt_mtchk_param par;
 	size_t size = XT_ALIGN(nla_len(tb[NFTA_MATCH_INFO]));
-	u8 proto = 0;
+	u16 proto = 0;
 	bool inv = false;
 	union nft_entry e = {};
 	int ret;
 
-	ret = nft_compat_chain_validate_dependency(match->name, ctx->chain);
+	ret = nft_compat_chain_validate_dependency(match->table, ctx->chain);
 	if (ret < 0)
 		goto err;
 
@@ -448,7 +476,7 @@ static int nft_match_validate(const struct nft_ctx *ctx,
 		if (!(hook_mask & match->hooks))
 			return -EINVAL;
 
-		ret = nft_compat_chain_validate_dependency(match->name,
+		ret = nft_compat_chain_validate_dependency(match->table,
 							   ctx->chain);
 		if (ret < 0)
 			return ret;
@@ -518,6 +546,12 @@ nfnl_compat_get(struct sock *nfnl, struct sk_buff *skb,
 	case AF_INET6:
 		fmt = "ip6t_%s";
 		break;
+	case NFPROTO_BRIDGE:
+		fmt = "ebt_%s";
+		break;
+	case NFPROTO_ARP:
+		fmt = "arpt_%s";
+		break;
 	default:
 		pr_err("nft_compat: unsupported protocol %d\n",
 			nfmsg->nfgen_family);
@@ -606,8 +640,12 @@ nft_match_select_ops(const struct nft_ctx *ctx,
 		struct xt_match *match = nft_match->ops.data;
 
 		if (strcmp(match->name, mt_name) == 0 &&
-		    match->revision == rev && match->family == family)
+		    match->revision == rev && match->family == family) {
+			if (!try_module_get(match->me))
+				return ERR_PTR(-ENOENT);
+
 			return &nft_match->ops;
+		}
 	}
 
 	match = xt_request_find_match(family, mt_name, rev);
@@ -676,8 +714,12 @@ nft_target_select_ops(const struct nft_ctx *ctx,
 		struct xt_target *target = nft_target->ops.data;
 
 		if (strcmp(target->name, tg_name) == 0 &&
-		    target->revision == rev && target->family == family)
+		    target->revision == rev && target->family == family) {
+			if (!try_module_get(target->me))
+				return ERR_PTR(-ENOENT);
+
 			return &nft_target->ops;
+		}
 	}
 
 	target = xt_request_find_target(family, tg_name, rev);
@@ -691,13 +733,17 @@ nft_target_select_ops(const struct nft_ctx *ctx,
 
 	nft_target->ops.type = &nft_target_type;
 	nft_target->ops.size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize));
-	nft_target->ops.eval = nft_target_eval;
 	nft_target->ops.init = nft_target_init;
 	nft_target->ops.destroy = nft_target_destroy;
 	nft_target->ops.dump = nft_target_dump;
 	nft_target->ops.validate = nft_target_validate;
 	nft_target->ops.data = target;
 
+	if (family == NFPROTO_BRIDGE)
+		nft_target->ops.eval = nft_target_eval_bridge;
+	else
+		nft_target->ops.eval = nft_target_eval_xt;
+
 	list_add(&nft_target->head, &nft_target_list);
 
 	return &nft_target->ops;
diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c
index c89ee486ce54..17591239229f 100644
--- a/net/netfilter/nft_counter.c
+++ b/net/netfilter/nft_counter.c
@@ -24,7 +24,7 @@ struct nft_counter {
 };
 
 static void nft_counter_eval(const struct nft_expr *expr,
-			     struct nft_data data[NFT_REG_MAX + 1],
+			     struct nft_regs *regs,
 			     const struct nft_pktinfo *pkt)
 {
 	struct nft_counter *priv = nft_expr_priv(expr);
@@ -92,6 +92,7 @@ static struct nft_expr_type nft_counter_type __read_mostly = {
 	.ops		= &nft_counter_ops,
 	.policy		= nft_counter_policy,
 	.maxattr	= NFTA_COUNTER_MAX,
+	.flags		= NFT_EXPR_STATEFUL,
 	.owner		= THIS_MODULE,
 };
 
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index cc5603016242..8cbca3432f90 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -31,11 +31,11 @@ struct nft_ct {
 };
 
 static void nft_ct_get_eval(const struct nft_expr *expr,
-			    struct nft_data data[NFT_REG_MAX + 1],
+			    struct nft_regs *regs,
 			    const struct nft_pktinfo *pkt)
 {
 	const struct nft_ct *priv = nft_expr_priv(expr);
-	struct nft_data *dest = &data[priv->dreg];
+	u32 *dest = &regs->data[priv->dreg];
 	enum ip_conntrack_info ctinfo;
 	const struct nf_conn *ct;
 	const struct nf_conn_help *help;
@@ -54,8 +54,10 @@ static void nft_ct_get_eval(const struct nft_expr *expr,
 			state = NF_CT_STATE_UNTRACKED_BIT;
 		else
 			state = NF_CT_STATE_BIT(ctinfo);
-		dest->data[0] = state;
+		*dest = state;
 		return;
+	default:
+		break;
 	}
 
 	if (ct == NULL)
@@ -63,26 +65,26 @@ static void nft_ct_get_eval(const struct nft_expr *expr,
 
 	switch (priv->key) {
 	case NFT_CT_DIRECTION:
-		dest->data[0] = CTINFO2DIR(ctinfo);
+		*dest = CTINFO2DIR(ctinfo);
 		return;
 	case NFT_CT_STATUS:
-		dest->data[0] = ct->status;
+		*dest = ct->status;
 		return;
 #ifdef CONFIG_NF_CONNTRACK_MARK
 	case NFT_CT_MARK:
-		dest->data[0] = ct->mark;
+		*dest = ct->mark;
 		return;
 #endif
 #ifdef CONFIG_NF_CONNTRACK_SECMARK
 	case NFT_CT_SECMARK:
-		dest->data[0] = ct->secmark;
+		*dest = ct->secmark;
 		return;
 #endif
 	case NFT_CT_EXPIRATION:
 		diff = (long)jiffies - (long)ct->timeout.expires;
 		if (diff < 0)
 			diff = 0;
-		dest->data[0] = jiffies_to_msecs(diff);
+		*dest = jiffies_to_msecs(diff);
 		return;
 	case NFT_CT_HELPER:
 		if (ct->master == NULL)
@@ -93,9 +95,7 @@ static void nft_ct_get_eval(const struct nft_expr *expr,
 		helper = rcu_dereference(help->helper);
 		if (helper == NULL)
 			goto err;
-		if (strlen(helper->name) >= sizeof(dest->data))
-			goto err;
-		strncpy((char *)dest->data, helper->name, sizeof(dest->data));
+		strncpy((char *)dest, helper->name, NF_CT_HELPER_NAME_LEN);
 		return;
 #ifdef CONFIG_NF_CONNTRACK_LABELS
 	case NFT_CT_LABELS: {
@@ -103,58 +103,60 @@ static void nft_ct_get_eval(const struct nft_expr *expr,
 		unsigned int size;
 
 		if (!labels) {
-			memset(dest->data, 0, sizeof(dest->data));
+			memset(dest, 0, NF_CT_LABELS_MAX_SIZE);
 			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);
+		memcpy(dest, labels->bits, size);
+		if (size < NF_CT_LABELS_MAX_SIZE)
+			memset(((char *) dest) + size, 0,
+			       NF_CT_LABELS_MAX_SIZE - size);
 		return;
 	}
 #endif
+	default:
+		break;
 	}
 
 	tuple = &ct->tuplehash[priv->dir].tuple;
 	switch (priv->key) {
 	case NFT_CT_L3PROTOCOL:
-		dest->data[0] = nf_ct_l3num(ct);
+		*dest = nf_ct_l3num(ct);
 		return;
 	case NFT_CT_SRC:
-		memcpy(dest->data, tuple->src.u3.all,
+		memcpy(dest, tuple->src.u3.all,
 		       nf_ct_l3num(ct) == NFPROTO_IPV4 ? 4 : 16);
 		return;
 	case NFT_CT_DST:
-		memcpy(dest->data, tuple->dst.u3.all,
+		memcpy(dest, tuple->dst.u3.all,
 		       nf_ct_l3num(ct) == NFPROTO_IPV4 ? 4 : 16);
 		return;
 	case NFT_CT_PROTOCOL:
-		dest->data[0] = nf_ct_protonum(ct);
+		*dest = nf_ct_protonum(ct);
 		return;
 	case NFT_CT_PROTO_SRC:
-		dest->data[0] = (__force __u16)tuple->src.u.all;
+		*dest = (__force __u16)tuple->src.u.all;
 		return;
 	case NFT_CT_PROTO_DST:
-		dest->data[0] = (__force __u16)tuple->dst.u.all;
+		*dest = (__force __u16)tuple->dst.u.all;
 		return;
+	default:
+		break;
 	}
 	return;
 err:
-	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+	regs->verdict.code = NFT_BREAK;
 }
 
 static void nft_ct_set_eval(const struct nft_expr *expr,
-			    struct nft_data data[NFT_REG_MAX + 1],
+			    struct nft_regs *regs,
 			    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];
+	u32 value = regs->data[priv->sreg];
 #endif
 	enum ip_conntrack_info ctinfo;
 	struct nf_conn *ct;
@@ -172,6 +174,8 @@ static void nft_ct_set_eval(const struct nft_expr *expr,
 		}
 		break;
 #endif
+	default:
+		break;
 	}
 }
 
@@ -220,12 +224,17 @@ static int nft_ct_get_init(const struct nft_ctx *ctx,
 			   const struct nlattr * const tb[])
 {
 	struct nft_ct *priv = nft_expr_priv(expr);
+	unsigned int len;
 	int err;
 
 	priv->key = ntohl(nla_get_be32(tb[NFTA_CT_KEY]));
 	switch (priv->key) {
-	case NFT_CT_STATE:
 	case NFT_CT_DIRECTION:
+		if (tb[NFTA_CT_DIRECTION] != NULL)
+			return -EINVAL;
+		len = sizeof(u8);
+		break;
+	case NFT_CT_STATE:
 	case NFT_CT_STATUS:
 #ifdef CONFIG_NF_CONNTRACK_MARK
 	case NFT_CT_MARK:
@@ -233,22 +242,54 @@ static int nft_ct_get_init(const struct nft_ctx *ctx,
 #ifdef CONFIG_NF_CONNTRACK_SECMARK
 	case NFT_CT_SECMARK:
 #endif
+	case NFT_CT_EXPIRATION:
+		if (tb[NFTA_CT_DIRECTION] != NULL)
+			return -EINVAL;
+		len = sizeof(u32);
+		break;
 #ifdef CONFIG_NF_CONNTRACK_LABELS
 	case NFT_CT_LABELS:
+		if (tb[NFTA_CT_DIRECTION] != NULL)
+			return -EINVAL;
+		len = NF_CT_LABELS_MAX_SIZE;
+		break;
 #endif
-	case NFT_CT_EXPIRATION:
 	case NFT_CT_HELPER:
 		if (tb[NFTA_CT_DIRECTION] != NULL)
 			return -EINVAL;
+		len = NF_CT_HELPER_NAME_LEN;
 		break;
+
 	case NFT_CT_L3PROTOCOL:
 	case NFT_CT_PROTOCOL:
+		if (tb[NFTA_CT_DIRECTION] == NULL)
+			return -EINVAL;
+		len = sizeof(u8);
+		break;
 	case NFT_CT_SRC:
 	case NFT_CT_DST:
+		if (tb[NFTA_CT_DIRECTION] == NULL)
+			return -EINVAL;
+
+		switch (ctx->afi->family) {
+		case NFPROTO_IPV4:
+			len = FIELD_SIZEOF(struct nf_conntrack_tuple,
+					   src.u3.ip);
+			break;
+		case NFPROTO_IPV6:
+		case NFPROTO_INET:
+			len = FIELD_SIZEOF(struct nf_conntrack_tuple,
+					   src.u3.ip6);
+			break;
+		default:
+			return -EAFNOSUPPORT;
+		}
+		break;
 	case NFT_CT_PROTO_SRC:
 	case NFT_CT_PROTO_DST:
 		if (tb[NFTA_CT_DIRECTION] == NULL)
 			return -EINVAL;
+		len = FIELD_SIZEOF(struct nf_conntrack_tuple, src.u.all);
 		break;
 	default:
 		return -EOPNOTSUPP;
@@ -265,12 +306,9 @@ static int nft_ct_get_init(const struct nft_ctx *ctx,
 		}
 	}
 
-	priv->dreg = ntohl(nla_get_be32(tb[NFTA_CT_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);
+	priv->dreg = nft_parse_register(tb[NFTA_CT_DREG]);
+	err = nft_validate_register_store(ctx, priv->dreg, NULL,
+					  NFT_DATA_VALUE, len);
 	if (err < 0)
 		return err;
 
@@ -286,20 +324,22 @@ static int nft_ct_set_init(const struct nft_ctx *ctx,
 			   const struct nlattr * const tb[])
 {
 	struct nft_ct *priv = nft_expr_priv(expr);
+	unsigned int len;
 	int err;
 
 	priv->key = ntohl(nla_get_be32(tb[NFTA_CT_KEY]));
 	switch (priv->key) {
 #ifdef CONFIG_NF_CONNTRACK_MARK
 	case NFT_CT_MARK:
+		len = FIELD_SIZEOF(struct nf_conn, mark);
 		break;
 #endif
 	default:
 		return -EOPNOTSUPP;
 	}
 
-	priv->sreg = ntohl(nla_get_be32(tb[NFTA_CT_SREG]));
-	err = nft_validate_input_register(priv->sreg);
+	priv->sreg = nft_parse_register(tb[NFTA_CT_SREG]);
+	err = nft_validate_register_load(priv->sreg, len);
 	if (err < 0)
 		return err;
 
@@ -320,7 +360,7 @@ static int nft_ct_get_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_DREG, htonl(priv->dreg)))
+	if (nft_dump_register(skb, NFTA_CT_DREG, priv->dreg))
 		goto nla_put_failure;
 	if (nla_put_be32(skb, NFTA_CT_KEY, htonl(priv->key)))
 		goto nla_put_failure;
@@ -347,7 +387,7 @@ 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)))
+	if (nft_dump_register(skb, NFTA_CT_SREG, priv->sreg))
 		goto nla_put_failure;
 	if (nla_put_be32(skb, NFTA_CT_KEY, htonl(priv->key)))
 		goto nla_put_failure;
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
new file mode 100644
index 000000000000..513a8ef60a59
--- /dev/null
+++ b/net/netfilter/nft_dynset.c
@@ -0,0 +1,265 @@
+/*
+ * Copyright (c) 2015 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/module.h>
+#include <linux/init.h>
+#include <linux/netlink.h>
+#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_dynset {
+	struct nft_set			*set;
+	struct nft_set_ext_tmpl		tmpl;
+	enum nft_dynset_ops		op:8;
+	enum nft_registers		sreg_key:8;
+	enum nft_registers		sreg_data:8;
+	u64				timeout;
+	struct nft_expr			*expr;
+	struct nft_set_binding		binding;
+};
+
+static void *nft_dynset_new(struct nft_set *set, const struct nft_expr *expr,
+			    struct nft_regs *regs)
+{
+	const struct nft_dynset *priv = nft_expr_priv(expr);
+	struct nft_set_ext *ext;
+	u64 timeout;
+	void *elem;
+
+	if (set->size && !atomic_add_unless(&set->nelems, 1, set->size))
+		return NULL;
+
+	timeout = priv->timeout ? : set->timeout;
+	elem = nft_set_elem_init(set, &priv->tmpl,
+				 &regs->data[priv->sreg_key],
+				 &regs->data[priv->sreg_data],
+				 timeout, GFP_ATOMIC);
+	if (elem == NULL) {
+		if (set->size)
+			atomic_dec(&set->nelems);
+		return NULL;
+	}
+
+	ext = nft_set_elem_ext(set, elem);
+	if (priv->expr != NULL)
+		nft_expr_clone(nft_set_ext_expr(ext), priv->expr);
+
+	return elem;
+}
+
+static void nft_dynset_eval(const struct nft_expr *expr,
+			    struct nft_regs *regs,
+			    const struct nft_pktinfo *pkt)
+{
+	const struct nft_dynset *priv = nft_expr_priv(expr);
+	struct nft_set *set = priv->set;
+	const struct nft_set_ext *ext;
+	const struct nft_expr *sexpr;
+	u64 timeout;
+
+	if (set->ops->update(set, &regs->data[priv->sreg_key], nft_dynset_new,
+			     expr, regs, &ext)) {
+		sexpr = NULL;
+		if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPR))
+			sexpr = nft_set_ext_expr(ext);
+
+		if (priv->op == NFT_DYNSET_OP_UPDATE &&
+		    nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) {
+			timeout = priv->timeout ? : set->timeout;
+			*nft_set_ext_expiration(ext) = jiffies + timeout;
+		} else if (sexpr == NULL)
+			goto out;
+
+		if (sexpr != NULL)
+			sexpr->ops->eval(sexpr, regs, pkt);
+		return;
+	}
+out:
+	regs->verdict.code = NFT_BREAK;
+}
+
+static const struct nla_policy nft_dynset_policy[NFTA_DYNSET_MAX + 1] = {
+	[NFTA_DYNSET_SET_NAME]	= { .type = NLA_STRING },
+	[NFTA_DYNSET_SET_ID]	= { .type = NLA_U32 },
+	[NFTA_DYNSET_OP]	= { .type = NLA_U32 },
+	[NFTA_DYNSET_SREG_KEY]	= { .type = NLA_U32 },
+	[NFTA_DYNSET_SREG_DATA]	= { .type = NLA_U32 },
+	[NFTA_DYNSET_TIMEOUT]	= { .type = NLA_U64 },
+	[NFTA_DYNSET_EXPR]	= { .type = NLA_NESTED },
+};
+
+static int nft_dynset_init(const struct nft_ctx *ctx,
+			   const struct nft_expr *expr,
+			   const struct nlattr * const tb[])
+{
+	struct nft_dynset *priv = nft_expr_priv(expr);
+	struct nft_set *set;
+	u64 timeout;
+	int err;
+
+	if (tb[NFTA_DYNSET_SET_NAME] == NULL ||
+	    tb[NFTA_DYNSET_OP] == NULL ||
+	    tb[NFTA_DYNSET_SREG_KEY] == NULL)
+		return -EINVAL;
+
+	set = nf_tables_set_lookup(ctx->table, tb[NFTA_DYNSET_SET_NAME]);
+	if (IS_ERR(set)) {
+		if (tb[NFTA_DYNSET_SET_ID])
+			set = nf_tables_set_lookup_byid(ctx->net,
+							tb[NFTA_DYNSET_SET_ID]);
+		if (IS_ERR(set))
+			return PTR_ERR(set);
+	}
+
+	if (set->flags & NFT_SET_CONSTANT)
+		return -EBUSY;
+
+	priv->op = ntohl(nla_get_be32(tb[NFTA_DYNSET_OP]));
+	switch (priv->op) {
+	case NFT_DYNSET_OP_ADD:
+		break;
+	case NFT_DYNSET_OP_UPDATE:
+		if (!(set->flags & NFT_SET_TIMEOUT))
+			return -EOPNOTSUPP;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	timeout = 0;
+	if (tb[NFTA_DYNSET_TIMEOUT] != NULL) {
+		if (!(set->flags & NFT_SET_TIMEOUT))
+			return -EINVAL;
+		timeout = be64_to_cpu(nla_get_be64(tb[NFTA_DYNSET_TIMEOUT]));
+	}
+
+	priv->sreg_key = nft_parse_register(tb[NFTA_DYNSET_SREG_KEY]);
+	err = nft_validate_register_load(priv->sreg_key, set->klen);;
+	if (err < 0)
+		return err;
+
+	if (tb[NFTA_DYNSET_SREG_DATA] != NULL) {
+		if (!(set->flags & NFT_SET_MAP))
+			return -EINVAL;
+		if (set->dtype == NFT_DATA_VERDICT)
+			return -EOPNOTSUPP;
+
+		priv->sreg_data = nft_parse_register(tb[NFTA_DYNSET_SREG_DATA]);
+		err = nft_validate_register_load(priv->sreg_data, set->dlen);
+		if (err < 0)
+			return err;
+	} else if (set->flags & NFT_SET_MAP)
+		return -EINVAL;
+
+	if (tb[NFTA_DYNSET_EXPR] != NULL) {
+		if (!(set->flags & NFT_SET_EVAL))
+			return -EINVAL;
+		if (!(set->flags & NFT_SET_ANONYMOUS))
+			return -EOPNOTSUPP;
+
+		priv->expr = nft_expr_init(ctx, tb[NFTA_DYNSET_EXPR]);
+		if (IS_ERR(priv->expr))
+			return PTR_ERR(priv->expr);
+
+		err = -EOPNOTSUPP;
+		if (!(priv->expr->ops->type->flags & NFT_EXPR_STATEFUL))
+			goto err1;
+	} else if (set->flags & NFT_SET_EVAL)
+		return -EINVAL;
+
+	nft_set_ext_prepare(&priv->tmpl);
+	nft_set_ext_add_length(&priv->tmpl, NFT_SET_EXT_KEY, set->klen);
+	if (set->flags & NFT_SET_MAP)
+		nft_set_ext_add_length(&priv->tmpl, NFT_SET_EXT_DATA, set->dlen);
+	if (priv->expr != NULL)
+		nft_set_ext_add_length(&priv->tmpl, NFT_SET_EXT_EXPR,
+				       priv->expr->ops->size);
+	if (set->flags & NFT_SET_TIMEOUT) {
+		if (timeout || set->timeout)
+			nft_set_ext_add(&priv->tmpl, NFT_SET_EXT_EXPIRATION);
+	}
+
+	priv->timeout = timeout;
+
+	err = nf_tables_bind_set(ctx, set, &priv->binding);
+	if (err < 0)
+		goto err1;
+
+	priv->set = set;
+	return 0;
+
+err1:
+	if (priv->expr != NULL)
+		nft_expr_destroy(ctx, priv->expr);
+	return err;
+}
+
+static void nft_dynset_destroy(const struct nft_ctx *ctx,
+			       const struct nft_expr *expr)
+{
+	struct nft_dynset *priv = nft_expr_priv(expr);
+
+	nf_tables_unbind_set(ctx, priv->set, &priv->binding);
+	if (priv->expr != NULL)
+		nft_expr_destroy(ctx, priv->expr);
+}
+
+static int nft_dynset_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_dynset *priv = nft_expr_priv(expr);
+
+	if (nft_dump_register(skb, NFTA_DYNSET_SREG_KEY, priv->sreg_key))
+		goto nla_put_failure;
+	if (priv->set->flags & NFT_SET_MAP &&
+	    nft_dump_register(skb, NFTA_DYNSET_SREG_DATA, priv->sreg_data))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_DYNSET_OP, htonl(priv->op)))
+		goto nla_put_failure;
+	if (nla_put_string(skb, NFTA_DYNSET_SET_NAME, priv->set->name))
+		goto nla_put_failure;
+	if (nla_put_be64(skb, NFTA_DYNSET_TIMEOUT, cpu_to_be64(priv->timeout)))
+		goto nla_put_failure;
+	if (priv->expr && nft_expr_dump(skb, NFTA_DYNSET_EXPR, priv->expr))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static struct nft_expr_type nft_dynset_type;
+static const struct nft_expr_ops nft_dynset_ops = {
+	.type		= &nft_dynset_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_dynset)),
+	.eval		= nft_dynset_eval,
+	.init		= nft_dynset_init,
+	.destroy	= nft_dynset_destroy,
+	.dump		= nft_dynset_dump,
+};
+
+static struct nft_expr_type nft_dynset_type __read_mostly = {
+	.name		= "dynset",
+	.ops		= &nft_dynset_ops,
+	.policy		= nft_dynset_policy,
+	.maxattr	= NFTA_DYNSET_MAX,
+	.owner		= THIS_MODULE,
+};
+
+int __init nft_dynset_module_init(void)
+{
+	return nft_register_expr(&nft_dynset_type);
+}
+
+void nft_dynset_module_exit(void)
+{
+	nft_unregister_expr(&nft_dynset_type);
+}
diff --git a/net/netfilter/nft_expr_template.c b/net/netfilter/nft_expr_template.c
deleted file mode 100644
index b6eed4d5a096..000000000000
--- a/net/netfilter/nft_expr_template.c
+++ /dev/null
@@ -1,94 +0,0 @@
-/*
- * Copyright (c) 2008-2009 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/netlink.h>
-#include <linux/netfilter.h>
-#include <linux/netfilter/nf_tables.h>
-#include <net/netfilter/nf_tables.h>
-
-struct nft_template {
-
-};
-
-static void nft_template_eval(const struct nft_expr *expr,
-			      struct nft_data data[NFT_REG_MAX + 1],
-			      const struct nft_pktinfo *pkt)
-{
-	struct nft_template *priv = nft_expr_priv(expr);
-
-}
-
-static const struct nla_policy nft_template_policy[NFTA_TEMPLATE_MAX + 1] = {
-	[NFTA_TEMPLATE_ATTR]		= { .type = NLA_U32 },
-};
-
-static int nft_template_init(const struct nft_ctx *ctx,
-			   const struct nft_expr *expr,
-			   const struct nlattr * const tb[])
-{
-	struct nft_template *priv = nft_expr_priv(expr);
-
-	return 0;
-}
-
-static void nft_template_destroy(const struct nft_ctx *ctx,
-			       const struct nft_expr *expr)
-{
-	struct nft_template *priv = nft_expr_priv(expr);
-
-}
-
-static int nft_template_dump(struct sk_buff *skb, const struct nft_expr *expr)
-{
-	const struct nft_template *priv = nft_expr_priv(expr);
-
-	NLA_PUT_BE32(skb, NFTA_TEMPLATE_ATTR, priv->field);
-	return 0;
-
-nla_put_failure:
-	return -1;
-}
-
-static struct nft_expr_type nft_template_type;
-static const struct nft_expr_ops nft_template_ops = {
-	.type		= &nft_template_type,
-	.size		= NFT_EXPR_SIZE(sizeof(struct nft_template)),
-	.eval		= nft_template_eval,
-	.init		= nft_template_init,
-	.destroy	= nft_template_destroy,
-	.dump		= nft_template_dump,
-};
-
-static struct nft_expr_type nft_template_type __read_mostly = {
-	.name		= "template",
-	.ops		= &nft_template_ops,
-	.policy		= nft_template_policy,
-	.maxattr	= NFTA_TEMPLATE_MAX,
-	.owner		= THIS_MODULE,
-};
-
-static int __init nft_template_module_init(void)
-{
-	return nft_register_expr(&nft_template_type);
-}
-
-static void __exit nft_template_module_exit(void)
-{
-	nft_unregister_expr(&nft_template_type);
-}
-
-module_init(nft_template_module_init);
-module_exit(nft_template_module_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_EXPR("template");
diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
index 55c939f5371f..ba7aed13e174 100644
--- a/net/netfilter/nft_exthdr.c
+++ b/net/netfilter/nft_exthdr.c
@@ -26,11 +26,11 @@ struct nft_exthdr {
 };
 
 static void nft_exthdr_eval(const struct nft_expr *expr,
-			    struct nft_data data[NFT_REG_MAX + 1],
+			    struct nft_regs *regs,
 			    const struct nft_pktinfo *pkt)
 {
 	struct nft_exthdr *priv = nft_expr_priv(expr);
-	struct nft_data *dest = &data[priv->dreg];
+	u32 *dest = &regs->data[priv->dreg];
 	unsigned int offset = 0;
 	int err;
 
@@ -39,11 +39,12 @@ static void nft_exthdr_eval(const struct nft_expr *expr,
 		goto err;
 	offset += priv->offset;
 
-	if (skb_copy_bits(pkt->skb, offset, dest->data, priv->len) < 0)
+	dest[priv->len / NFT_REG32_SIZE] = 0;
+	if (skb_copy_bits(pkt->skb, offset, dest, priv->len) < 0)
 		goto err;
 	return;
 err:
-	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+	regs->verdict.code = NFT_BREAK;
 }
 
 static const struct nla_policy nft_exthdr_policy[NFTA_EXTHDR_MAX + 1] = {
@@ -58,7 +59,6 @@ static int nft_exthdr_init(const struct nft_ctx *ctx,
 			   const struct nlattr * const tb[])
 {
 	struct nft_exthdr *priv = nft_expr_priv(expr);
-	int err;
 
 	if (tb[NFTA_EXTHDR_DREG] == NULL ||
 	    tb[NFTA_EXTHDR_TYPE] == NULL ||
@@ -69,22 +69,17 @@ static int nft_exthdr_init(const struct nft_ctx *ctx,
 	priv->type   = nla_get_u8(tb[NFTA_EXTHDR_TYPE]);
 	priv->offset = ntohl(nla_get_be32(tb[NFTA_EXTHDR_OFFSET]));
 	priv->len    = ntohl(nla_get_be32(tb[NFTA_EXTHDR_LEN]));
-	if (priv->len == 0 ||
-	    priv->len > FIELD_SIZEOF(struct nft_data, data))
-		return -EINVAL;
+	priv->dreg   = nft_parse_register(tb[NFTA_EXTHDR_DREG]);
 
-	priv->dreg = ntohl(nla_get_be32(tb[NFTA_EXTHDR_DREG]));
-	err = nft_validate_output_register(priv->dreg);
-	if (err < 0)
-		return err;
-	return nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE);
+	return nft_validate_register_store(ctx, priv->dreg, NULL,
+					   NFT_DATA_VALUE, priv->len);
 }
 
 static int nft_exthdr_dump(struct sk_buff *skb, const struct nft_expr *expr)
 {
 	const struct nft_exthdr *priv = nft_expr_priv(expr);
 
-	if (nla_put_be32(skb, NFTA_EXTHDR_DREG, htonl(priv->dreg)))
+	if (nft_dump_register(skb, NFTA_EXTHDR_DREG, priv->dreg))
 		goto nla_put_failure;
 	if (nla_put_u8(skb, NFTA_EXTHDR_TYPE, priv->type))
 		goto nla_put_failure;
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index 8892b7b6184a..3f9d45d3d9b7 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -15,6 +15,7 @@
 #include <linux/log2.h>
 #include <linux/jhash.h>
 #include <linux/netlink.h>
+#include <linux/workqueue.h>
 #include <linux/rhashtable.h>
 #include <linux/netfilter.h>
 #include <linux/netfilter/nf_tables.h>
@@ -23,175 +24,314 @@
 /* We target a hash table size of 4, element hint is 75% of final size */
 #define NFT_HASH_ELEMENT_HINT 3
 
+struct nft_hash {
+	struct rhashtable		ht;
+	struct delayed_work		gc_work;
+};
+
 struct nft_hash_elem {
 	struct rhash_head		node;
-	struct nft_data			key;
-	struct nft_data			data[];
+	struct nft_set_ext		ext;
 };
 
-static bool nft_hash_lookup(const struct nft_set *set,
-			    const struct nft_data *key,
-			    struct nft_data *data)
+struct nft_hash_cmp_arg {
+	const struct nft_set		*set;
+	const u32			*key;
+	u8				genmask;
+};
+
+static const struct rhashtable_params nft_hash_params;
+
+static inline u32 nft_hash_key(const void *data, u32 len, u32 seed)
 {
-	const struct rhashtable *priv = nft_set_priv(set);
+	const struct nft_hash_cmp_arg *arg = data;
+
+	return jhash(arg->key, len, seed);
+}
+
+static inline u32 nft_hash_obj(const void *data, u32 len, u32 seed)
+{
+	const struct nft_hash_elem *he = data;
+
+	return jhash(nft_set_ext_key(&he->ext), len, seed);
+}
+
+static inline int nft_hash_cmp(struct rhashtable_compare_arg *arg,
+			       const void *ptr)
+{
+	const struct nft_hash_cmp_arg *x = arg->key;
+	const struct nft_hash_elem *he = ptr;
+
+	if (memcmp(nft_set_ext_key(&he->ext), x->key, x->set->klen))
+		return 1;
+	if (nft_set_elem_expired(&he->ext))
+		return 1;
+	if (!nft_set_elem_active(&he->ext, x->genmask))
+		return 1;
+	return 0;
+}
+
+static bool nft_hash_lookup(const struct nft_set *set, const u32 *key,
+			    const struct nft_set_ext **ext)
+{
+	struct nft_hash *priv = nft_set_priv(set);
 	const struct nft_hash_elem *he;
+	struct nft_hash_cmp_arg arg = {
+		.genmask = nft_genmask_cur(read_pnet(&set->pnet)),
+		.set	 = set,
+		.key	 = key,
+	};
 
-	he = rhashtable_lookup(priv, key);
-	if (he && set->flags & NFT_SET_MAP)
-		nft_data_copy(data, he->data);
+	he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_params);
+	if (he != NULL)
+		*ext = &he->ext;
 
 	return !!he;
 }
 
-static int nft_hash_insert(const struct nft_set *set,
-			   const struct nft_set_elem *elem)
+static bool nft_hash_update(struct nft_set *set, const u32 *key,
+			    void *(*new)(struct nft_set *,
+					 const struct nft_expr *,
+					 struct nft_regs *regs),
+			    const struct nft_expr *expr,
+			    struct nft_regs *regs,
+			    const struct nft_set_ext **ext)
 {
-	struct rhashtable *priv = nft_set_priv(set);
+	struct nft_hash *priv = nft_set_priv(set);
 	struct nft_hash_elem *he;
-	unsigned int size;
-
-	if (elem->flags != 0)
-		return -EINVAL;
+	struct nft_hash_cmp_arg arg = {
+		.genmask = NFT_GENMASK_ANY,
+		.set	 = set,
+		.key	 = key,
+	};
 
-	size = sizeof(*he);
-	if (set->flags & NFT_SET_MAP)
-		size += sizeof(he->data[0]);
+	he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_params);
+	if (he != NULL)
+		goto out;
 
-	he = kzalloc(size, GFP_KERNEL);
+	he = new(set, expr, regs);
 	if (he == NULL)
-		return -ENOMEM;
+		goto err1;
+	if (rhashtable_lookup_insert_key(&priv->ht, &arg, &he->node,
+					 nft_hash_params))
+		goto err2;
+out:
+	*ext = &he->ext;
+	return true;
 
-	nft_data_copy(&he->key, &elem->key);
-	if (set->flags & NFT_SET_MAP)
-		nft_data_copy(he->data, &elem->data);
+err2:
+	nft_set_elem_destroy(set, he);
+err1:
+	return false;
+}
 
-	rhashtable_insert(priv, &he->node, GFP_KERNEL);
+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_elem *he = elem->priv;
+	struct nft_hash_cmp_arg arg = {
+		.genmask = nft_genmask_next(read_pnet(&set->pnet)),
+		.set	 = set,
+		.key	 = elem->key.val.data,
+	};
 
-	return 0;
+	return rhashtable_lookup_insert_key(&priv->ht, &arg, &he->node,
+					    nft_hash_params);
 }
 
-static void nft_hash_elem_destroy(const struct nft_set *set,
-				  struct nft_hash_elem *he)
+static void nft_hash_activate(const struct nft_set *set,
+			      const struct nft_set_elem *elem)
 {
-	nft_data_uninit(&he->key, NFT_DATA_VALUE);
-	if (set->flags & NFT_SET_MAP)
-		nft_data_uninit(he->data, set->dtype);
-	kfree(he);
+	struct nft_hash_elem *he = elem->priv;
+
+	nft_set_elem_change_active(set, &he->ext);
+	nft_set_elem_clear_busy(&he->ext);
 }
 
-static void nft_hash_remove(const struct nft_set *set,
-			    const struct nft_set_elem *elem)
+static void *nft_hash_deactivate(const struct nft_set *set,
+				 const struct nft_set_elem *elem)
 {
-	struct rhashtable *priv = nft_set_priv(set);
-	struct rhash_head *he, __rcu **pprev;
+	struct nft_hash *priv = nft_set_priv(set);
+	struct nft_hash_elem *he;
+	struct nft_hash_cmp_arg arg = {
+		.genmask = nft_genmask_next(read_pnet(&set->pnet)),
+		.set	 = set,
+		.key	 = elem->key.val.data,
+	};
+
+	rcu_read_lock();
+	he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_params);
+	if (he != NULL) {
+		if (!nft_set_elem_mark_busy(&he->ext))
+			nft_set_elem_change_active(set, &he->ext);
+		else
+			he = NULL;
+	}
+	rcu_read_unlock();
 
-	pprev = elem->cookie;
-	he = rht_dereference((*pprev), priv);
+	return he;
+}
 
-	rhashtable_remove_pprev(priv, he, pprev, GFP_KERNEL);
+static void nft_hash_remove(const struct nft_set *set,
+			    const struct nft_set_elem *elem)
+{
+	struct nft_hash *priv = nft_set_priv(set);
+	struct nft_hash_elem *he = elem->priv;
 
-	synchronize_rcu();
-	kfree(he);
+	rhashtable_remove_fast(&priv->ht, &he->node, nft_hash_params);
 }
 
-static int nft_hash_get(const struct nft_set *set, struct nft_set_elem *elem)
+static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set,
+			  struct nft_set_iter *iter)
 {
-	const struct rhashtable *priv = nft_set_priv(set);
-	const struct bucket_table *tbl = rht_dereference_rcu(priv->tbl, priv);
-	struct rhash_head __rcu * const *pprev;
+	struct nft_hash *priv = nft_set_priv(set);
 	struct nft_hash_elem *he;
-	u32 h;
+	struct rhashtable_iter hti;
+	struct nft_set_elem elem;
+	u8 genmask = nft_genmask_cur(read_pnet(&set->pnet));
+	int err;
+
+	err = rhashtable_walk_init(&priv->ht, &hti);
+	iter->err = err;
+	if (err)
+		return;
+
+	err = rhashtable_walk_start(&hti);
+	if (err && err != -EAGAIN) {
+		iter->err = err;
+		goto out;
+	}
+
+	while ((he = rhashtable_walk_next(&hti))) {
+		if (IS_ERR(he)) {
+			err = PTR_ERR(he);
+			if (err != -EAGAIN) {
+				iter->err = err;
+				goto out;
+			}
 
-	h = rhashtable_hashfn(priv, &elem->key, set->klen);
-	pprev = &tbl->buckets[h];
-	rht_for_each_entry_rcu(he, tbl->buckets[h], node) {
-		if (nft_data_cmp(&he->key, &elem->key, set->klen)) {
-			pprev = &he->node.next;
 			continue;
 		}
 
-		elem->cookie = (void *)pprev;
-		elem->flags = 0;
-		if (set->flags & NFT_SET_MAP)
-			nft_data_copy(&elem->data, he->data);
-		return 0;
+		if (iter->count < iter->skip)
+			goto cont;
+		if (nft_set_elem_expired(&he->ext))
+			goto cont;
+		if (!nft_set_elem_active(&he->ext, genmask))
+			goto cont;
+
+		elem.priv = he;
+
+		iter->err = iter->fn(ctx, set, iter, &elem);
+		if (iter->err < 0)
+			goto out;
+
+cont:
+		iter->count++;
 	}
-	return -ENOENT;
+
+out:
+	rhashtable_walk_stop(&hti);
+	rhashtable_walk_exit(&hti);
 }
 
-static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set,
-			  struct nft_set_iter *iter)
+static void nft_hash_gc(struct work_struct *work)
 {
-	const struct rhashtable *priv = nft_set_priv(set);
-	const struct bucket_table *tbl;
-	const struct nft_hash_elem *he;
-	struct nft_set_elem elem;
-	unsigned int i;
-
-	tbl = rht_dereference_rcu(priv->tbl, priv);
-	for (i = 0; i < tbl->size; i++) {
-		rht_for_each_entry_rcu(he, tbl->buckets[i], node) {
-			if (iter->count < iter->skip)
-				goto cont;
-
-			memcpy(&elem.key, &he->key, sizeof(elem.key));
-			if (set->flags & NFT_SET_MAP)
-				memcpy(&elem.data, he->data, sizeof(elem.data));
-			elem.flags = 0;
-
-			iter->err = iter->fn(ctx, set, iter, &elem);
-			if (iter->err < 0)
-				return;
-cont:
-			iter->count++;
+	struct nft_set *set;
+	struct nft_hash_elem *he;
+	struct nft_hash *priv;
+	struct nft_set_gc_batch *gcb = NULL;
+	struct rhashtable_iter hti;
+	int err;
+
+	priv = container_of(work, struct nft_hash, gc_work.work);
+	set  = nft_set_container_of(priv);
+
+	err = rhashtable_walk_init(&priv->ht, &hti);
+	if (err)
+		goto schedule;
+
+	err = rhashtable_walk_start(&hti);
+	if (err && err != -EAGAIN)
+		goto out;
+
+	while ((he = rhashtable_walk_next(&hti))) {
+		if (IS_ERR(he)) {
+			if (PTR_ERR(he) != -EAGAIN)
+				goto out;
+			continue;
 		}
+
+		if (!nft_set_elem_expired(&he->ext))
+			continue;
+		if (nft_set_elem_mark_busy(&he->ext))
+			continue;
+
+		gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC);
+		if (gcb == NULL)
+			goto out;
+		rhashtable_remove_fast(&priv->ht, &he->node, nft_hash_params);
+		atomic_dec(&set->nelems);
+		nft_set_gc_batch_add(gcb, he);
 	}
+out:
+	rhashtable_walk_stop(&hti);
+	rhashtable_walk_exit(&hti);
+
+	nft_set_gc_batch_complete(gcb);
+schedule:
+	queue_delayed_work(system_power_efficient_wq, &priv->gc_work,
+			   nft_set_gc_interval(set));
 }
 
 static unsigned int nft_hash_privsize(const struct nlattr * const nla[])
 {
-	return sizeof(struct rhashtable);
+	return sizeof(struct nft_hash);
 }
 
-static int lockdep_nfnl_lock_is_held(void)
-{
-	return lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES);
-}
+static const struct rhashtable_params nft_hash_params = {
+	.head_offset		= offsetof(struct nft_hash_elem, node),
+	.hashfn			= nft_hash_key,
+	.obj_hashfn		= nft_hash_obj,
+	.obj_cmpfn		= nft_hash_cmp,
+	.automatic_shrinking	= true,
+};
 
 static int nft_hash_init(const struct nft_set *set,
 			 const struct nft_set_desc *desc,
 			 const struct nlattr * const tb[])
 {
-	struct rhashtable *priv = nft_set_priv(set);
-	struct rhashtable_params params = {
-		.nelem_hint = desc->size ? : NFT_HASH_ELEMENT_HINT,
-		.head_offset = offsetof(struct nft_hash_elem, node),
-		.key_offset = offsetof(struct nft_hash_elem, key),
-		.key_len = set->klen,
-		.hashfn = jhash,
-		.grow_decision = rht_grow_above_75,
-		.shrink_decision = rht_shrink_below_30,
-		.mutex_is_held = lockdep_nfnl_lock_is_held,
-	};
+	struct nft_hash *priv = nft_set_priv(set);
+	struct rhashtable_params params = nft_hash_params;
+	int err;
 
-	return rhashtable_init(priv, &params);
+	params.nelem_hint = desc->size ?: NFT_HASH_ELEMENT_HINT;
+	params.key_len	  = set->klen;
+
+	err = rhashtable_init(&priv->ht, &params);
+	if (err < 0)
+		return err;
+
+	INIT_DEFERRABLE_WORK(&priv->gc_work, nft_hash_gc);
+	if (set->flags & NFT_SET_TIMEOUT)
+		queue_delayed_work(system_power_efficient_wq, &priv->gc_work,
+				   nft_set_gc_interval(set));
+	return 0;
+}
+
+static void nft_hash_elem_destroy(void *ptr, void *arg)
+{
+	nft_set_elem_destroy((const struct nft_set *)arg, ptr);
 }
 
 static void nft_hash_destroy(const struct nft_set *set)
 {
-	const struct rhashtable *priv = nft_set_priv(set);
-	const struct bucket_table *tbl = priv->tbl;
-	struct nft_hash_elem *he, *next;
-	unsigned int i;
+	struct nft_hash *priv = nft_set_priv(set);
 
-	for (i = 0; i < tbl->size; i++) {
-		for (he = rht_entry(tbl->buckets[i], struct nft_hash_elem, node);
-		     he != NULL; he = next) {
-			next = rht_entry(he->node.next, struct nft_hash_elem, node);
-			nft_hash_elem_destroy(set, he);
-		}
-	}
-	rhashtable_destroy(priv);
+	cancel_delayed_work_sync(&priv->gc_work);
+	rhashtable_free_and_destroy(&priv->ht, nft_hash_elem_destroy,
+				    (void *)set);
 }
 
 static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features,
@@ -200,11 +340,8 @@ static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features,
 	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 rhashtable) +
+		est->size = sizeof(struct nft_hash) +
 			    roundup_pow_of_two(desc->size * 4 / 3) *
 			    sizeof(struct nft_hash_elem *) +
 			    desc->size * esize;
@@ -224,15 +361,18 @@ static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features,
 
 static struct nft_set_ops nft_hash_ops __read_mostly = {
 	.privsize       = nft_hash_privsize,
+	.elemsize	= offsetof(struct nft_hash_elem, ext),
 	.estimate	= nft_hash_estimate,
 	.init		= nft_hash_init,
 	.destroy	= nft_hash_destroy,
-	.get		= nft_hash_get,
 	.insert		= nft_hash_insert,
+	.activate	= nft_hash_activate,
+	.deactivate	= nft_hash_deactivate,
 	.remove		= nft_hash_remove,
 	.lookup		= nft_hash_lookup,
+	.update		= nft_hash_update,
 	.walk		= nft_hash_walk,
-	.features	= NFT_SET_MAP,
+	.features	= NFT_SET_MAP | NFT_SET_TIMEOUT,
 	.owner		= THIS_MODULE,
 };
 
diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c
index 810385eb7249..db3b746858e3 100644
--- a/net/netfilter/nft_immediate.c
+++ b/net/netfilter/nft_immediate.c
@@ -24,12 +24,12 @@ struct nft_immediate_expr {
 };
 
 static void nft_immediate_eval(const struct nft_expr *expr,
-			       struct nft_data data[NFT_REG_MAX + 1],
+			       struct nft_regs *regs,
 			       const struct nft_pktinfo *pkt)
 {
 	const struct nft_immediate_expr *priv = nft_expr_priv(expr);
 
-	nft_data_copy(&data[priv->dreg], &priv->data);
+	nft_data_copy(&regs->data[priv->dreg], &priv->data, priv->dlen);
 }
 
 static const struct nla_policy nft_immediate_policy[NFTA_IMMEDIATE_MAX + 1] = {
@@ -49,17 +49,15 @@ static int nft_immediate_init(const struct nft_ctx *ctx,
 	    tb[NFTA_IMMEDIATE_DATA] == NULL)
 		return -EINVAL;
 
-	priv->dreg = ntohl(nla_get_be32(tb[NFTA_IMMEDIATE_DREG]));
-	err = nft_validate_output_register(priv->dreg);
-	if (err < 0)
-		return err;
-
-	err = nft_data_init(ctx, &priv->data, &desc, tb[NFTA_IMMEDIATE_DATA]);
+	err = nft_data_init(ctx, &priv->data, sizeof(priv->data), &desc,
+			    tb[NFTA_IMMEDIATE_DATA]);
 	if (err < 0)
 		return err;
 	priv->dlen = desc.len;
 
-	err = nft_validate_data_load(ctx, priv->dreg, &priv->data, desc.type);
+	priv->dreg = nft_parse_register(tb[NFTA_IMMEDIATE_DREG]);
+	err = nft_validate_register_store(ctx, priv->dreg, &priv->data,
+					  desc.type, desc.len);
 	if (err < 0)
 		goto err1;
 
@@ -81,7 +79,7 @@ static int nft_immediate_dump(struct sk_buff *skb, const struct nft_expr *expr)
 {
 	const struct nft_immediate_expr *priv = nft_expr_priv(expr);
 
-	if (nla_put_be32(skb, NFTA_IMMEDIATE_DREG, htonl(priv->dreg)))
+	if (nft_dump_register(skb, NFTA_IMMEDIATE_DREG, priv->dreg))
 		goto nla_put_failure;
 
 	return nft_data_dump(skb, NFTA_IMMEDIATE_DATA, &priv->data,
diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c
index 85da5bd02f64..435c1ccd6c0e 100644
--- a/net/netfilter/nft_limit.c
+++ b/net/netfilter/nft_limit.c
@@ -27,7 +27,7 @@ struct nft_limit {
 };
 
 static void nft_limit_eval(const struct nft_expr *expr,
-			   struct nft_data data[NFT_REG_MAX + 1],
+			   struct nft_regs *regs,
 			   const struct nft_pktinfo *pkt)
 {
 	struct nft_limit *priv = nft_expr_priv(expr);
@@ -45,7 +45,7 @@ static void nft_limit_eval(const struct nft_expr *expr,
 	}
 	spin_unlock_bh(&limit_lock);
 
-	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+	regs->verdict.code = NFT_BREAK;
 }
 
 static const struct nla_policy nft_limit_policy[NFTA_LIMIT_MAX + 1] = {
@@ -98,6 +98,7 @@ static struct nft_expr_type nft_limit_type __read_mostly = {
 	.ops		= &nft_limit_ops,
 	.policy		= nft_limit_policy,
 	.maxattr	= NFTA_LIMIT_MAX,
+	.flags		= NFT_EXPR_STATEFUL,
 	.owner		= THIS_MODULE,
 };
 
diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c
index bde05f28cf14..a13d6a386d63 100644
--- a/net/netfilter/nft_log.c
+++ b/net/netfilter/nft_log.c
@@ -27,7 +27,7 @@ struct nft_log {
 };
 
 static void nft_log_eval(const struct nft_expr *expr,
-			 struct nft_data data[NFT_REG_MAX + 1],
+			 struct nft_regs *regs,
 			 const struct nft_pktinfo *pkt)
 {
 	const struct nft_log *priv = nft_expr_priv(expr);
@@ -78,7 +78,7 @@ static int nft_log_init(const struct nft_ctx *ctx,
 			li->u.log.level =
 				ntohl(nla_get_be32(tb[NFTA_LOG_LEVEL]));
 		} else {
-			li->u.log.level = 4;
+			li->u.log.level = LOGLEVEL_WARNING;
 		}
 		if (tb[NFTA_LOG_FLAGS] != NULL) {
 			li->u.log.logflags =
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index 6404a726d17b..b3c31ef8015d 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -26,19 +26,25 @@ struct nft_lookup {
 };
 
 static void nft_lookup_eval(const struct nft_expr *expr,
-			    struct nft_data data[NFT_REG_MAX + 1],
+			    struct nft_regs *regs,
 			    const struct nft_pktinfo *pkt)
 {
 	const struct nft_lookup *priv = nft_expr_priv(expr);
 	const struct nft_set *set = priv->set;
+	const struct nft_set_ext *ext;
 
-	if (set->ops->lookup(set, &data[priv->sreg], &data[priv->dreg]))
+	if (set->ops->lookup(set, &regs->data[priv->sreg], &ext)) {
+		if (set->flags & NFT_SET_MAP)
+			nft_data_copy(&regs->data[priv->dreg],
+				      nft_set_ext_data(ext), set->dlen);
 		return;
-	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+	}
+	regs->verdict.code = NFT_BREAK;
 }
 
 static const struct nla_policy nft_lookup_policy[NFTA_LOOKUP_MAX + 1] = {
 	[NFTA_LOOKUP_SET]	= { .type = NLA_STRING },
+	[NFTA_LOOKUP_SET_ID]	= { .type = NLA_U32 },
 	[NFTA_LOOKUP_SREG]	= { .type = NLA_U32 },
 	[NFTA_LOOKUP_DREG]	= { .type = NLA_U32 },
 };
@@ -65,8 +71,11 @@ static int nft_lookup_init(const struct nft_ctx *ctx,
 			return PTR_ERR(set);
 	}
 
-	priv->sreg = ntohl(nla_get_be32(tb[NFTA_LOOKUP_SREG]));
-	err = nft_validate_input_register(priv->sreg);
+	if (set->flags & NFT_SET_EVAL)
+		return -EOPNOTSUPP;
+
+	priv->sreg = nft_parse_register(tb[NFTA_LOOKUP_SREG]);
+	err = nft_validate_register_load(priv->sreg, set->klen);
 	if (err < 0)
 		return err;
 
@@ -74,19 +83,16 @@ static int nft_lookup_init(const struct nft_ctx *ctx,
 		if (!(set->flags & NFT_SET_MAP))
 			return -EINVAL;
 
-		priv->dreg = ntohl(nla_get_be32(tb[NFTA_LOOKUP_DREG]));
-		err = nft_validate_output_register(priv->dreg);
+		priv->dreg = nft_parse_register(tb[NFTA_LOOKUP_DREG]);
+		err = nft_validate_register_store(ctx, priv->dreg, NULL,
+						  set->dtype, set->dlen);
 		if (err < 0)
 			return err;
-
-		if (priv->dreg == NFT_REG_VERDICT) {
-			if (set->dtype != NFT_DATA_VERDICT)
-				return -EINVAL;
-		} else if (set->dtype == NFT_DATA_VERDICT)
-			return -EINVAL;
 	} else if (set->flags & NFT_SET_MAP)
 		return -EINVAL;
 
+	priv->binding.flags = set->flags & NFT_SET_MAP;
+
 	err = nf_tables_bind_set(ctx, set, &priv->binding);
 	if (err < 0)
 		return err;
@@ -109,10 +115,10 @@ static int nft_lookup_dump(struct sk_buff *skb, const struct nft_expr *expr)
 
 	if (nla_put_string(skb, NFTA_LOOKUP_SET, priv->set->name))
 		goto nla_put_failure;
-	if (nla_put_be32(skb, NFTA_LOOKUP_SREG, htonl(priv->sreg)))
+	if (nft_dump_register(skb, NFTA_LOOKUP_SREG, priv->sreg))
 		goto nla_put_failure;
 	if (priv->set->flags & NFT_SET_MAP)
-		if (nla_put_be32(skb, NFTA_LOOKUP_DREG, htonl(priv->dreg)))
+		if (nft_dump_register(skb, NFTA_LOOKUP_DREG, priv->dreg))
 			goto nla_put_failure;
 	return 0;
 
diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c
index d1ffd5eb3a9b..9aea747b43ea 100644
--- a/net/netfilter/nft_masq.c
+++ b/net/netfilter/nft_masq.c
@@ -21,6 +21,21 @@ const struct nla_policy nft_masq_policy[NFTA_MASQ_MAX + 1] = {
 };
 EXPORT_SYMBOL_GPL(nft_masq_policy);
 
+int nft_masq_validate(const struct nft_ctx *ctx,
+		      const struct nft_expr *expr,
+		      const struct nft_data **data)
+{
+	int err;
+
+	err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
+	if (err < 0)
+		return err;
+
+	return nft_chain_validate_hooks(ctx->chain,
+				        (1 << NF_INET_POST_ROUTING));
+}
+EXPORT_SYMBOL_GPL(nft_masq_validate);
+
 int nft_masq_init(const struct nft_ctx *ctx,
 		  const struct nft_expr *expr,
 		  const struct nlattr * const tb[])
@@ -28,8 +43,8 @@ int nft_masq_init(const struct nft_ctx *ctx,
 	struct nft_masq *priv = nft_expr_priv(expr);
 	int err;
 
-	err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
-	if (err < 0)
+	err = nft_masq_validate(ctx, expr, NULL);
+	if (err)
 		return err;
 
 	if (tb[NFTA_MASQ_FLAGS] == NULL)
@@ -60,12 +75,5 @@ nla_put_failure:
 }
 EXPORT_SYMBOL_GPL(nft_masq_dump);
 
-int nft_masq_validate(const struct nft_ctx *ctx, const struct nft_expr *expr,
-		      const struct nft_data **data)
-{
-	return nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
-}
-EXPORT_SYMBOL_GPL(nft_masq_validate);
-
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>");
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 1e7c076ca63a..52561e1c31e2 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -25,65 +25,68 @@
 #include <net/netfilter/nft_meta.h>
 
 void nft_meta_get_eval(const struct nft_expr *expr,
-		       struct nft_data data[NFT_REG_MAX + 1],
+		       struct nft_regs *regs,
 		       const struct nft_pktinfo *pkt)
 {
 	const struct nft_meta *priv = nft_expr_priv(expr);
 	const struct sk_buff *skb = pkt->skb;
 	const struct net_device *in = pkt->in, *out = pkt->out;
-	struct nft_data *dest = &data[priv->dreg];
+	u32 *dest = &regs->data[priv->dreg];
 
 	switch (priv->key) {
 	case NFT_META_LEN:
-		dest->data[0] = skb->len;
+		*dest = skb->len;
 		break;
 	case NFT_META_PROTOCOL:
-		*(__be16 *)dest->data = skb->protocol;
+		*dest = 0;
+		*(__be16 *)dest = skb->protocol;
 		break;
 	case NFT_META_NFPROTO:
-		dest->data[0] = pkt->ops->pf;
+		*dest = pkt->ops->pf;
 		break;
 	case NFT_META_L4PROTO:
-		dest->data[0] = pkt->tprot;
+		*dest = pkt->tprot;
 		break;
 	case NFT_META_PRIORITY:
-		dest->data[0] = skb->priority;
+		*dest = skb->priority;
 		break;
 	case NFT_META_MARK:
-		dest->data[0] = skb->mark;
+		*dest = skb->mark;
 		break;
 	case NFT_META_IIF:
 		if (in == NULL)
 			goto err;
-		dest->data[0] = in->ifindex;
+		*dest = in->ifindex;
 		break;
 	case NFT_META_OIF:
 		if (out == NULL)
 			goto err;
-		dest->data[0] = out->ifindex;
+		*dest = out->ifindex;
 		break;
 	case NFT_META_IIFNAME:
 		if (in == NULL)
 			goto err;
-		strncpy((char *)dest->data, in->name, sizeof(dest->data));
+		strncpy((char *)dest, in->name, IFNAMSIZ);
 		break;
 	case NFT_META_OIFNAME:
 		if (out == NULL)
 			goto err;
-		strncpy((char *)dest->data, out->name, sizeof(dest->data));
+		strncpy((char *)dest, out->name, IFNAMSIZ);
 		break;
 	case NFT_META_IIFTYPE:
 		if (in == NULL)
 			goto err;
-		*(u16 *)dest->data = in->type;
+		*dest = 0;
+		*(u16 *)dest = in->type;
 		break;
 	case NFT_META_OIFTYPE:
 		if (out == NULL)
 			goto err;
-		*(u16 *)dest->data = out->type;
+		*dest = 0;
+		*(u16 *)dest = out->type;
 		break;
 	case NFT_META_SKUID:
-		if (skb->sk == NULL || skb->sk->sk_state == TCP_TIME_WAIT)
+		if (skb->sk == NULL || !sk_fullsock(skb->sk))
 			goto err;
 
 		read_lock_bh(&skb->sk->sk_callback_lock);
@@ -93,13 +96,12 @@ void nft_meta_get_eval(const struct nft_expr *expr,
 			goto err;
 		}
 
-		dest->data[0] =
-			from_kuid_munged(&init_user_ns,
+		*dest =	from_kuid_munged(&init_user_ns,
 				skb->sk->sk_socket->file->f_cred->fsuid);
 		read_unlock_bh(&skb->sk->sk_callback_lock);
 		break;
 	case NFT_META_SKGID:
-		if (skb->sk == NULL || skb->sk->sk_state == TCP_TIME_WAIT)
+		if (skb->sk == NULL || !sk_fullsock(skb->sk))
 			goto err;
 
 		read_lock_bh(&skb->sk->sk_callback_lock);
@@ -108,8 +110,7 @@ void nft_meta_get_eval(const struct nft_expr *expr,
 			read_unlock_bh(&skb->sk->sk_callback_lock);
 			goto err;
 		}
-		dest->data[0] =
-			from_kgid_munged(&init_user_ns,
+		*dest =	from_kgid_munged(&init_user_ns,
 				 skb->sk->sk_socket->file->f_cred->fsgid);
 		read_unlock_bh(&skb->sk->sk_callback_lock);
 		break;
@@ -119,33 +120,33 @@ void nft_meta_get_eval(const struct nft_expr *expr,
 
 		if (dst == NULL)
 			goto err;
-		dest->data[0] = dst->tclassid;
+		*dest = dst->tclassid;
 		break;
 	}
 #endif
 #ifdef CONFIG_NETWORK_SECMARK
 	case NFT_META_SECMARK:
-		dest->data[0] = skb->secmark;
+		*dest = skb->secmark;
 		break;
 #endif
 	case NFT_META_PKTTYPE:
 		if (skb->pkt_type != PACKET_LOOPBACK) {
-			dest->data[0] = skb->pkt_type;
+			*dest = skb->pkt_type;
 			break;
 		}
 
 		switch (pkt->ops->pf) {
 		case NFPROTO_IPV4:
 			if (ipv4_is_multicast(ip_hdr(skb)->daddr))
-				dest->data[0] = PACKET_MULTICAST;
+				*dest = PACKET_MULTICAST;
 			else
-				dest->data[0] = PACKET_BROADCAST;
+				*dest = PACKET_BROADCAST;
 			break;
 		case NFPROTO_IPV6:
 			if (ipv6_hdr(skb)->daddr.s6_addr[0] == 0xFF)
-				dest->data[0] = PACKET_MULTICAST;
+				*dest = PACKET_MULTICAST;
 			else
-				dest->data[0] = PACKET_BROADCAST;
+				*dest = PACKET_BROADCAST;
 			break;
 		default:
 			WARN_ON(1);
@@ -153,17 +154,22 @@ void nft_meta_get_eval(const struct nft_expr *expr,
 		}
 		break;
 	case NFT_META_CPU:
-		dest->data[0] = smp_processor_id();
+		*dest = raw_smp_processor_id();
 		break;
 	case NFT_META_IIFGROUP:
 		if (in == NULL)
 			goto err;
-		dest->data[0] = in->group;
+		*dest = in->group;
 		break;
 	case NFT_META_OIFGROUP:
 		if (out == NULL)
 			goto err;
-		dest->data[0] = out->group;
+		*dest = out->group;
+		break;
+	case NFT_META_CGROUP:
+		if (skb->sk == NULL || !sk_fullsock(skb->sk))
+			goto err;
+		*dest = skb->sk->sk_classid;
 		break;
 	default:
 		WARN_ON(1);
@@ -172,17 +178,17 @@ void nft_meta_get_eval(const struct nft_expr *expr,
 	return;
 
 err:
-	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+	regs->verdict.code = NFT_BREAK;
 }
 EXPORT_SYMBOL_GPL(nft_meta_get_eval);
 
 void nft_meta_set_eval(const struct nft_expr *expr,
-		       struct nft_data data[NFT_REG_MAX + 1],
+		       struct nft_regs *regs,
 		       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];
+	u32 value = regs->data[meta->sreg];
 
 	switch (meta->key) {
 	case NFT_META_MARK:
@@ -212,22 +218,22 @@ int nft_meta_get_init(const struct nft_ctx *ctx,
 		      const struct nlattr * const tb[])
 {
 	struct nft_meta *priv = nft_expr_priv(expr);
-	int err;
+	unsigned int len;
 
 	priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY]));
 	switch (priv->key) {
-	case NFT_META_LEN:
 	case NFT_META_PROTOCOL:
+	case NFT_META_IIFTYPE:
+	case NFT_META_OIFTYPE:
+		len = sizeof(u16);
+		break;
 	case NFT_META_NFPROTO:
 	case NFT_META_L4PROTO:
+	case NFT_META_LEN:
 	case NFT_META_PRIORITY:
 	case NFT_META_MARK:
 	case NFT_META_IIF:
 	case NFT_META_OIF:
-	case NFT_META_IIFNAME:
-	case NFT_META_OIFNAME:
-	case NFT_META_IIFTYPE:
-	case NFT_META_OIFTYPE:
 	case NFT_META_SKUID:
 	case NFT_META_SKGID:
 #ifdef CONFIG_IP_ROUTE_CLASSID
@@ -240,21 +246,20 @@ int nft_meta_get_init(const struct nft_ctx *ctx,
 	case NFT_META_CPU:
 	case NFT_META_IIFGROUP:
 	case NFT_META_OIFGROUP:
+	case NFT_META_CGROUP:
+		len = sizeof(u32);
+		break;
+	case NFT_META_IIFNAME:
+	case NFT_META_OIFNAME:
+		len = IFNAMSIZ;
 		break;
 	default:
 		return -EOPNOTSUPP;
 	}
 
-	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;
+	priv->dreg = nft_parse_register(tb[NFTA_META_DREG]);
+	return nft_validate_register_store(ctx, priv->dreg, NULL,
+					   NFT_DATA_VALUE, len);
 }
 EXPORT_SYMBOL_GPL(nft_meta_get_init);
 
@@ -263,20 +268,24 @@ int nft_meta_set_init(const struct nft_ctx *ctx,
 		      const struct nlattr * const tb[])
 {
 	struct nft_meta *priv = nft_expr_priv(expr);
+	unsigned int len;
 	int err;
 
 	priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY]));
 	switch (priv->key) {
 	case NFT_META_MARK:
 	case NFT_META_PRIORITY:
+		len = sizeof(u32);
+		break;
 	case NFT_META_NFTRACE:
+		len = sizeof(u8);
 		break;
 	default:
 		return -EOPNOTSUPP;
 	}
 
-	priv->sreg = ntohl(nla_get_be32(tb[NFTA_META_SREG]));
-	err = nft_validate_input_register(priv->sreg);
+	priv->sreg = nft_parse_register(tb[NFTA_META_SREG]);
+	err = nft_validate_register_load(priv->sreg, len);
 	if (err < 0)
 		return err;
 
@@ -291,7 +300,7 @@ int nft_meta_get_dump(struct sk_buff *skb,
 
 	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)))
+	if (nft_dump_register(skb, NFTA_META_DREG, priv->dreg))
 		goto nla_put_failure;
 	return 0;
 
@@ -307,7 +316,7 @@ int nft_meta_set_dump(struct sk_buff *skb,
 
 	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)))
+	if (nft_dump_register(skb, NFTA_META_SREG, priv->sreg))
 		goto nla_put_failure;
 
 	return 0;
diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c
index afe2b0b45ec4..ee2d71753746 100644
--- a/net/netfilter/nft_nat.c
+++ b/net/netfilter/nft_nat.c
@@ -37,7 +37,7 @@ struct nft_nat {
 };
 
 static void nft_nat_eval(const struct nft_expr *expr,
-			 struct nft_data data[NFT_REG_MAX + 1],
+			 struct nft_regs *regs,
 			 const struct nft_pktinfo *pkt)
 {
 	const struct nft_nat *priv = nft_expr_priv(expr);
@@ -49,33 +49,32 @@ static void nft_nat_eval(const struct nft_expr *expr,
 	if (priv->sreg_addr_min) {
 		if (priv->family == AF_INET) {
 			range.min_addr.ip = (__force __be32)
-					data[priv->sreg_addr_min].data[0];
+					regs->data[priv->sreg_addr_min];
 			range.max_addr.ip = (__force __be32)
-					data[priv->sreg_addr_max].data[0];
+					regs->data[priv->sreg_addr_max];
 
 		} else {
 			memcpy(range.min_addr.ip6,
-			       data[priv->sreg_addr_min].data,
-			       sizeof(struct nft_data));
+			       &regs->data[priv->sreg_addr_min],
+			       sizeof(range.min_addr.ip6));
 			memcpy(range.max_addr.ip6,
-			       data[priv->sreg_addr_max].data,
-			       sizeof(struct nft_data));
+			       &regs->data[priv->sreg_addr_max],
+			       sizeof(range.max_addr.ip6));
 		}
 		range.flags |= NF_NAT_RANGE_MAP_IPS;
 	}
 
 	if (priv->sreg_proto_min) {
-		range.min_proto.all = (__force __be16)
-					data[priv->sreg_proto_min].data[0];
-		range.max_proto.all = (__force __be16)
-					data[priv->sreg_proto_max].data[0];
+		range.min_proto.all =
+			*(__be16 *)&regs->data[priv->sreg_proto_min];
+		range.max_proto.all =
+			*(__be16 *)&regs->data[priv->sreg_proto_max];
 		range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
 	}
 
 	range.flags |= priv->flags;
 
-	data[NFT_REG_VERDICT].verdict =
-		nf_nat_setup_info(ct, &range, priv->type);
+	regs->verdict.code = nf_nat_setup_info(ct, &range, priv->type);
 }
 
 static const struct nla_policy nft_nat_policy[NFTA_NAT_MAX + 1] = {
@@ -88,17 +87,41 @@ static const struct nla_policy nft_nat_policy[NFTA_NAT_MAX + 1] = {
 	[NFTA_NAT_FLAGS]	 = { .type = NLA_U32 },
 };
 
-static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
-			const struct nlattr * const tb[])
+static int nft_nat_validate(const struct nft_ctx *ctx,
+			    const struct nft_expr *expr,
+			    const struct nft_data **data)
 {
 	struct nft_nat *priv = nft_expr_priv(expr);
-	u32 family;
 	int err;
 
 	err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
 	if (err < 0)
 		return err;
 
+	switch (priv->type) {
+	case NFT_NAT_SNAT:
+		err = nft_chain_validate_hooks(ctx->chain,
+					       (1 << NF_INET_POST_ROUTING) |
+					       (1 << NF_INET_LOCAL_IN));
+		break;
+	case NFT_NAT_DNAT:
+		err = nft_chain_validate_hooks(ctx->chain,
+					       (1 << NF_INET_PRE_ROUTING) |
+					       (1 << NF_INET_LOCAL_OUT));
+		break;
+	}
+
+	return err;
+}
+
+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);
+	unsigned int alen, plen;
+	u32 family;
+	int err;
+
 	if (tb[NFTA_NAT_TYPE] == NULL ||
 	    (tb[NFTA_NAT_REG_ADDR_MIN] == NULL &&
 	     tb[NFTA_NAT_REG_PROTO_MIN] == NULL))
@@ -115,29 +138,42 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 		return -EINVAL;
 	}
 
+	err = nft_nat_validate(ctx, expr, NULL);
+	if (err < 0)
+		return err;
+
 	if (tb[NFTA_NAT_FAMILY] == NULL)
 		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;
+
+	switch (family) {
+	case NFPROTO_IPV4:
+		alen = FIELD_SIZEOF(struct nf_nat_range, min_addr.ip);
+		break;
+	case NFPROTO_IPV6:
+		alen = FIELD_SIZEOF(struct nf_nat_range, min_addr.ip6);
+		break;
+	default:
+		return -EAFNOSUPPORT;
+	}
 	priv->family = family;
 
 	if (tb[NFTA_NAT_REG_ADDR_MIN]) {
 		priv->sreg_addr_min =
-			ntohl(nla_get_be32(tb[NFTA_NAT_REG_ADDR_MIN]));
-
-		err = nft_validate_input_register(priv->sreg_addr_min);
+			nft_parse_register(tb[NFTA_NAT_REG_ADDR_MIN]);
+		err = nft_validate_register_load(priv->sreg_addr_min, alen);
 		if (err < 0)
 			return err;
 
 		if (tb[NFTA_NAT_REG_ADDR_MAX]) {
 			priv->sreg_addr_max =
-				ntohl(nla_get_be32(tb[NFTA_NAT_REG_ADDR_MAX]));
+				nft_parse_register(tb[NFTA_NAT_REG_ADDR_MAX]);
 
-			err = nft_validate_input_register(priv->sreg_addr_max);
+			err = nft_validate_register_load(priv->sreg_addr_max,
+							 alen);
 			if (err < 0)
 				return err;
 		} else {
@@ -145,19 +181,21 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 		}
 	}
 
+	plen = FIELD_SIZEOF(struct nf_nat_range, min_addr.all);
 	if (tb[NFTA_NAT_REG_PROTO_MIN]) {
 		priv->sreg_proto_min =
-			ntohl(nla_get_be32(tb[NFTA_NAT_REG_PROTO_MIN]));
+			nft_parse_register(tb[NFTA_NAT_REG_PROTO_MIN]);
 
-		err = nft_validate_input_register(priv->sreg_proto_min);
+		err = nft_validate_register_load(priv->sreg_proto_min, plen);
 		if (err < 0)
 			return err;
 
 		if (tb[NFTA_NAT_REG_PROTO_MAX]) {
 			priv->sreg_proto_max =
-				ntohl(nla_get_be32(tb[NFTA_NAT_REG_PROTO_MAX]));
+				nft_parse_register(tb[NFTA_NAT_REG_PROTO_MAX]);
 
-			err = nft_validate_input_register(priv->sreg_proto_max);
+			err = nft_validate_register_load(priv->sreg_proto_max,
+							 plen);
 			if (err < 0)
 				return err;
 		} else {
@@ -193,18 +231,18 @@ static int nft_nat_dump(struct sk_buff *skb, const struct nft_expr *expr)
 		goto nla_put_failure;
 
 	if (priv->sreg_addr_min) {
-		if (nla_put_be32(skb, NFTA_NAT_REG_ADDR_MIN,
-				 htonl(priv->sreg_addr_min)) ||
-		    nla_put_be32(skb, NFTA_NAT_REG_ADDR_MAX,
-				 htonl(priv->sreg_addr_max)))
+		if (nft_dump_register(skb, NFTA_NAT_REG_ADDR_MIN,
+				      priv->sreg_addr_min) ||
+		    nft_dump_register(skb, NFTA_NAT_REG_ADDR_MAX,
+				      priv->sreg_addr_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)) ||
-		    nla_put_be32(skb, NFTA_NAT_REG_PROTO_MAX,
-				 htonl(priv->sreg_proto_max)))
+		if (nft_dump_register(skb, NFTA_NAT_REG_PROTO_MIN,
+				      priv->sreg_proto_min) ||
+		    nft_dump_register(skb, NFTA_NAT_REG_PROTO_MAX,
+				      priv->sreg_proto_max))
 			goto nla_put_failure;
 	}
 
@@ -219,13 +257,6 @@ nla_put_failure:
 	return -1;
 }
 
-static int nft_nat_validate(const struct nft_ctx *ctx,
-			    const struct nft_expr *expr,
-			    const struct nft_data **data)
-{
-	return nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
-}
-
 static struct nft_expr_type nft_nat_type;
 static const struct nft_expr_ops nft_nat_ops = {
 	.type           = &nft_nat_type,
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index 85daa84bfdfe..94fb3b27a2c5 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -18,12 +18,12 @@
 #include <net/netfilter/nf_tables.h>
 
 static void nft_payload_eval(const struct nft_expr *expr,
-			     struct nft_data data[NFT_REG_MAX + 1],
+			     struct nft_regs *regs,
 			     const struct nft_pktinfo *pkt)
 {
 	const struct nft_payload *priv = nft_expr_priv(expr);
 	const struct sk_buff *skb = pkt->skb;
-	struct nft_data *dest = &data[priv->dreg];
+	u32 *dest = &regs->data[priv->dreg];
 	int offset;
 
 	switch (priv->base) {
@@ -43,11 +43,12 @@ static void nft_payload_eval(const struct nft_expr *expr,
 	}
 	offset += priv->offset;
 
-	if (skb_copy_bits(skb, offset, dest->data, priv->len) < 0)
+	dest[priv->len / NFT_REG32_SIZE] = 0;
+	if (skb_copy_bits(skb, offset, dest, priv->len) < 0)
 		goto err;
 	return;
 err:
-	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+	regs->verdict.code = NFT_BREAK;
 }
 
 static const struct nla_policy nft_payload_policy[NFTA_PAYLOAD_MAX + 1] = {
@@ -62,24 +63,21 @@ static int nft_payload_init(const struct nft_ctx *ctx,
 			    const struct nlattr * const tb[])
 {
 	struct nft_payload *priv = nft_expr_priv(expr);
-	int err;
 
 	priv->base   = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE]));
 	priv->offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET]));
 	priv->len    = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN]));
+	priv->dreg   = nft_parse_register(tb[NFTA_PAYLOAD_DREG]);
 
-	priv->dreg = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_DREG]));
-	err = nft_validate_output_register(priv->dreg);
-	if (err < 0)
-		return err;
-	return nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE);
+	return nft_validate_register_store(ctx, priv->dreg, NULL,
+					   NFT_DATA_VALUE, priv->len);
 }
 
 static int nft_payload_dump(struct sk_buff *skb, const struct nft_expr *expr)
 {
 	const struct nft_payload *priv = nft_expr_priv(expr);
 
-	if (nla_put_be32(skb, NFTA_PAYLOAD_DREG, htonl(priv->dreg)) ||
+	if (nft_dump_register(skb, NFTA_PAYLOAD_DREG, priv->dreg) ||
 	    nla_put_be32(skb, NFTA_PAYLOAD_BASE, htonl(priv->base)) ||
 	    nla_put_be32(skb, NFTA_PAYLOAD_OFFSET, htonl(priv->offset)) ||
 	    nla_put_be32(skb, NFTA_PAYLOAD_LEN, htonl(priv->len)))
@@ -131,9 +129,7 @@ nft_payload_select_ops(const struct nft_ctx *ctx,
 	}
 
 	offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET]));
-	len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN]));
-	if (len == 0 || len > FIELD_SIZEOF(struct nft_data, data))
-		return ERR_PTR(-EINVAL);
+	len    = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN]));
 
 	if (len <= 4 && is_power_of_2(len) && IS_ALIGNED(offset, len) &&
 	    base != NFT_PAYLOAD_LL_HEADER)
diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c
index e8ae2f6bf232..96805d21d618 100644
--- a/net/netfilter/nft_queue.c
+++ b/net/netfilter/nft_queue.c
@@ -28,7 +28,7 @@ struct nft_queue {
 };
 
 static void nft_queue_eval(const struct nft_expr *expr,
-			   struct nft_data data[NFT_REG_MAX + 1],
+			   struct nft_regs *regs,
 			   const struct nft_pktinfo *pkt)
 {
 	struct nft_queue *priv = nft_expr_priv(expr);
@@ -51,7 +51,7 @@ static void nft_queue_eval(const struct nft_expr *expr,
 	if (priv->flags & NFT_QUEUE_FLAG_BYPASS)
 		ret |= NF_VERDICT_FLAG_QUEUE_BYPASS;
 
-	data[NFT_REG_VERDICT].verdict = ret;
+	regs->verdict.code = ret;
 }
 
 static const struct nla_policy nft_queue_policy[NFTA_QUEUE_MAX + 1] = {
diff --git a/net/netfilter/nft_rbtree.c b/net/netfilter/nft_rbtree.c
index 46214f245665..1c30f41cff5b 100644
--- a/net/netfilter/nft_rbtree.c
+++ b/net/netfilter/nft_rbtree.c
@@ -26,25 +26,25 @@ struct nft_rbtree {
 
 struct nft_rbtree_elem {
 	struct rb_node		node;
-	u16			flags;
-	struct nft_data		key;
-	struct nft_data		data[];
+	struct nft_set_ext	ext;
 };
 
-static bool nft_rbtree_lookup(const struct nft_set *set,
-			      const struct nft_data *key,
-			      struct nft_data *data)
+
+static bool nft_rbtree_lookup(const struct nft_set *set, const u32 *key,
+			      const struct nft_set_ext **ext)
 {
 	const struct nft_rbtree *priv = nft_set_priv(set);
 	const struct nft_rbtree_elem *rbe, *interval = NULL;
-	const struct rb_node *parent = priv->root.rb_node;
+	const struct rb_node *parent;
+	u8 genmask = nft_genmask_cur(read_pnet(&set->pnet));
 	int d;
 
 	spin_lock_bh(&nft_rbtree_lock);
+	parent = priv->root.rb_node;
 	while (parent != NULL) {
 		rbe = rb_entry(parent, struct nft_rbtree_elem, node);
 
-		d = nft_data_cmp(&rbe->key, key, set->klen);
+		d = memcmp(nft_set_ext_key(&rbe->ext), key, set->klen);
 		if (d < 0) {
 			parent = parent->rb_left;
 			interval = rbe;
@@ -52,12 +52,17 @@ static bool nft_rbtree_lookup(const struct nft_set *set,
 			parent = parent->rb_right;
 		else {
 found:
-			if (rbe->flags & NFT_SET_ELEM_INTERVAL_END)
+			if (!nft_set_elem_active(&rbe->ext, genmask)) {
+				parent = parent->rb_left;
+				continue;
+			}
+			if (nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) &&
+			    *nft_set_ext_flags(&rbe->ext) &
+			    NFT_SET_ELEM_INTERVAL_END)
 				goto out;
-			if (set->flags & NFT_SET_MAP)
-				nft_data_copy(data, rbe->data);
-
 			spin_unlock_bh(&nft_rbtree_lock);
+
+			*ext = &rbe->ext;
 			return true;
 		}
 	}
@@ -71,23 +76,13 @@ out:
 	return false;
 }
 
-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 &&
-	    !(rbe->flags & NFT_SET_ELEM_INTERVAL_END))
-		nft_data_uninit(rbe->data, set->dtype);
-
-	kfree(rbe);
-}
-
 static int __nft_rbtree_insert(const struct nft_set *set,
 			       struct nft_rbtree_elem *new)
 {
 	struct nft_rbtree *priv = nft_set_priv(set);
 	struct nft_rbtree_elem *rbe;
 	struct rb_node *parent, **p;
+	u8 genmask = nft_genmask_next(read_pnet(&set->pnet));
 	int d;
 
 	parent = NULL;
@@ -95,13 +90,18 @@ static int __nft_rbtree_insert(const struct nft_set *set,
 	while (*p != NULL) {
 		parent = *p;
 		rbe = rb_entry(parent, struct nft_rbtree_elem, node);
-		d = nft_data_cmp(&rbe->key, &new->key, set->klen);
+		d = memcmp(nft_set_ext_key(&rbe->ext),
+			   nft_set_ext_key(&new->ext),
+			   set->klen);
 		if (d < 0)
 			p = &parent->rb_left;
 		else if (d > 0)
 			p = &parent->rb_right;
-		else
-			return -EEXIST;
+		else {
+			if (nft_set_elem_active(&rbe->ext, genmask))
+				return -EEXIST;
+			p = &parent->rb_left;
+		}
 	}
 	rb_link_node(&new->node, parent, p);
 	rb_insert_color(&new->node, &priv->root);
@@ -111,31 +111,13 @@ static int __nft_rbtree_insert(const struct nft_set *set,
 static int nft_rbtree_insert(const struct nft_set *set,
 			     const struct nft_set_elem *elem)
 {
-	struct nft_rbtree_elem *rbe;
-	unsigned int size;
+	struct nft_rbtree_elem *rbe = elem->priv;
 	int err;
 
-	size = sizeof(*rbe);
-	if (set->flags & NFT_SET_MAP &&
-	    !(elem->flags & NFT_SET_ELEM_INTERVAL_END))
-		size += sizeof(rbe->data[0]);
-
-	rbe = kzalloc(size, GFP_KERNEL);
-	if (rbe == NULL)
-		return -ENOMEM;
-
-	rbe->flags = elem->flags;
-	nft_data_copy(&rbe->key, &elem->key);
-	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;
 }
 
@@ -143,42 +125,49 @@ static void nft_rbtree_remove(const struct nft_set *set,
 			      const struct nft_set_elem *elem)
 {
 	struct nft_rbtree *priv = nft_set_priv(set);
-	struct nft_rbtree_elem *rbe = elem->cookie;
+	struct nft_rbtree_elem *rbe = elem->priv;
 
 	spin_lock_bh(&nft_rbtree_lock);
 	rb_erase(&rbe->node, &priv->root);
 	spin_unlock_bh(&nft_rbtree_lock);
-	kfree(rbe);
 }
 
-static int nft_rbtree_get(const struct nft_set *set, struct nft_set_elem *elem)
+static void nft_rbtree_activate(const struct nft_set *set,
+				const struct nft_set_elem *elem)
+{
+	struct nft_rbtree_elem *rbe = elem->priv;
+
+	nft_set_elem_change_active(set, &rbe->ext);
+}
+
+static void *nft_rbtree_deactivate(const struct nft_set *set,
+				   const struct nft_set_elem *elem)
 {
 	const struct nft_rbtree *priv = nft_set_priv(set);
 	const struct rb_node *parent = priv->root.rb_node;
 	struct nft_rbtree_elem *rbe;
+	u8 genmask = nft_genmask_cur(read_pnet(&set->pnet));
 	int d;
 
-	spin_lock_bh(&nft_rbtree_lock);
 	while (parent != NULL) {
 		rbe = rb_entry(parent, struct nft_rbtree_elem, node);
 
-		d = nft_data_cmp(&rbe->key, &elem->key, set->klen);
+		d = memcmp(nft_set_ext_key(&rbe->ext), &elem->key.val,
+					   set->klen);
 		if (d < 0)
 			parent = parent->rb_left;
 		else if (d > 0)
 			parent = parent->rb_right;
 		else {
-			elem->cookie = rbe;
-			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;
+			if (!nft_set_elem_active(&rbe->ext, genmask)) {
+				parent = parent->rb_left;
+				continue;
+			}
+			nft_set_elem_change_active(set, &rbe->ext);
+			return rbe;
 		}
 	}
-	spin_unlock_bh(&nft_rbtree_lock);
-	return -ENOENT;
+	return NULL;
 }
 
 static void nft_rbtree_walk(const struct nft_ctx *ctx,
@@ -186,21 +175,21 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
 			    struct nft_set_iter *iter)
 {
 	const struct nft_rbtree *priv = nft_set_priv(set);
-	const struct nft_rbtree_elem *rbe;
+	struct nft_rbtree_elem *rbe;
 	struct nft_set_elem elem;
 	struct rb_node *node;
+	u8 genmask = nft_genmask_cur(read_pnet(&set->pnet));
 
 	spin_lock_bh(&nft_rbtree_lock);
 	for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) {
+		rbe = rb_entry(node, struct nft_rbtree_elem, node);
+
 		if (iter->count < iter->skip)
 			goto cont;
+		if (!nft_set_elem_active(&rbe->ext, genmask))
+			goto cont;
 
-		rbe = rb_entry(node, struct nft_rbtree_elem, node);
-		nft_data_copy(&elem.key, &rbe->key);
-		if (set->flags & NFT_SET_MAP &&
-		    !(rbe->flags & NFT_SET_ELEM_INTERVAL_END))
-			nft_data_copy(&elem.data, rbe->data);
-		elem.flags = rbe->flags;
+		elem.priv = rbe;
 
 		iter->err = iter->fn(ctx, set, iter, &elem);
 		if (iter->err < 0) {
@@ -237,7 +226,7 @@ static void nft_rbtree_destroy(const struct nft_set *set)
 	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);
+		nft_set_elem_destroy(set, rbe);
 	}
 }
 
@@ -247,9 +236,6 @@ static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features,
 	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
@@ -262,12 +248,14 @@ static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features,
 
 static struct nft_set_ops nft_rbtree_ops __read_mostly = {
 	.privsize	= nft_rbtree_privsize,
+	.elemsize	= offsetof(struct nft_rbtree_elem, ext),
 	.estimate	= nft_rbtree_estimate,
 	.init		= nft_rbtree_init,
 	.destroy	= nft_rbtree_destroy,
 	.insert		= nft_rbtree_insert,
 	.remove		= nft_rbtree_remove,
-	.get		= nft_rbtree_get,
+	.deactivate	= nft_rbtree_deactivate,
+	.activate	= nft_rbtree_activate,
 	.lookup		= nft_rbtree_lookup,
 	.walk		= nft_rbtree_walk,
 	.features	= NFT_SET_INTERVAL | NFT_SET_MAP,
diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c
new file mode 100644
index 000000000000..03f7bf40ae75
--- /dev/null
+++ b/net/netfilter/nft_redir.c
@@ -0,0 +1,111 @@
+/*
+ * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo.borrero.glez@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.
+ */
+
+#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_nat.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nft_redir.h>
+
+const struct nla_policy nft_redir_policy[NFTA_REDIR_MAX + 1] = {
+	[NFTA_REDIR_REG_PROTO_MIN]	= { .type = NLA_U32 },
+	[NFTA_REDIR_REG_PROTO_MAX]	= { .type = NLA_U32 },
+	[NFTA_REDIR_FLAGS]		= { .type = NLA_U32 },
+};
+EXPORT_SYMBOL_GPL(nft_redir_policy);
+
+int nft_redir_validate(const struct nft_ctx *ctx,
+		       const struct nft_expr *expr,
+		       const struct nft_data **data)
+{
+	int err;
+
+	err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
+	if (err < 0)
+		return err;
+
+	return nft_chain_validate_hooks(ctx->chain,
+					(1 << NF_INET_PRE_ROUTING) |
+					(1 << NF_INET_LOCAL_OUT));
+}
+EXPORT_SYMBOL_GPL(nft_redir_validate);
+
+int nft_redir_init(const struct nft_ctx *ctx,
+		   const struct nft_expr *expr,
+		   const struct nlattr * const tb[])
+{
+	struct nft_redir *priv = nft_expr_priv(expr);
+	unsigned int plen;
+	int err;
+
+	err = nft_redir_validate(ctx, expr, NULL);
+	if (err < 0)
+		return err;
+
+	plen = FIELD_SIZEOF(struct nf_nat_range, min_addr.all);
+	if (tb[NFTA_REDIR_REG_PROTO_MIN]) {
+		priv->sreg_proto_min =
+			nft_parse_register(tb[NFTA_REDIR_REG_PROTO_MIN]);
+
+		err = nft_validate_register_load(priv->sreg_proto_min, plen);
+		if (err < 0)
+			return err;
+
+		if (tb[NFTA_REDIR_REG_PROTO_MAX]) {
+			priv->sreg_proto_max =
+				nft_parse_register(tb[NFTA_REDIR_REG_PROTO_MAX]);
+
+			err = nft_validate_register_load(priv->sreg_proto_max,
+							 plen);
+			if (err < 0)
+				return err;
+		} else {
+			priv->sreg_proto_max = priv->sreg_proto_min;
+		}
+	}
+
+	if (tb[NFTA_REDIR_FLAGS]) {
+		priv->flags = ntohl(nla_get_be32(tb[NFTA_REDIR_FLAGS]));
+		if (priv->flags & ~NF_NAT_RANGE_MASK)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nft_redir_init);
+
+int nft_redir_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_redir *priv = nft_expr_priv(expr);
+
+	if (priv->sreg_proto_min) {
+		if (nft_dump_register(skb, NFTA_REDIR_REG_PROTO_MIN,
+				      priv->sreg_proto_min))
+			goto nla_put_failure;
+		if (nft_dump_register(skb, NFTA_REDIR_REG_PROTO_MAX,
+				      priv->sreg_proto_max))
+			goto nla_put_failure;
+	}
+
+	if (priv->flags != 0 &&
+	    nla_put_be32(skb, NFTA_REDIR_FLAGS, htonl(priv->flags)))
+			goto nla_put_failure;
+
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+EXPORT_SYMBOL_GPL(nft_redir_dump);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>");
diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c
index 57d3e1af5630..0522fc9bfb0a 100644
--- a/net/netfilter/nft_reject.c
+++ b/net/netfilter/nft_reject.c
@@ -63,6 +63,8 @@ int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr)
 		if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code))
 			goto nla_put_failure;
 		break;
+	default:
+		break;
 	}
 
 	return 0;
diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c
index 7b5f9d58680a..635dbba93d01 100644
--- a/net/netfilter/nft_reject_inet.c
+++ b/net/netfilter/nft_reject_inet.c
@@ -18,7 +18,7 @@
 #include <net/netfilter/ipv6/nf_reject.h>
 
 static void nft_reject_inet_eval(const struct nft_expr *expr,
-				 struct nft_data data[NFT_REG_MAX + 1],
+				 struct nft_regs *regs,
 				 const struct nft_pktinfo *pkt)
 {
 	struct nft_reject *priv = nft_expr_priv(expr);
@@ -28,14 +28,16 @@ static void nft_reject_inet_eval(const struct nft_expr *expr,
 	case NFPROTO_IPV4:
 		switch (priv->type) {
 		case NFT_REJECT_ICMP_UNREACH:
-			nf_send_unreach(pkt->skb, priv->icmp_code);
+			nf_send_unreach(pkt->skb, priv->icmp_code,
+					pkt->ops->hooknum);
 			break;
 		case NFT_REJECT_TCP_RST:
 			nf_send_reset(pkt->skb, pkt->ops->hooknum);
 			break;
 		case NFT_REJECT_ICMPX_UNREACH:
 			nf_send_unreach(pkt->skb,
-					nft_reject_icmp_code(priv->icmp_code));
+					nft_reject_icmp_code(priv->icmp_code),
+					pkt->ops->hooknum);
 			break;
 		}
 		break;
@@ -56,7 +58,8 @@ static void nft_reject_inet_eval(const struct nft_expr *expr,
 		}
 		break;
 	}
-	data[NFT_REG_VERDICT].verdict = NF_DROP;
+
+	regs->verdict.code = NF_DROP;
 }
 
 static int nft_reject_inet_init(const struct nft_ctx *ctx,
@@ -105,6 +108,8 @@ static int nft_reject_inet_dump(struct sk_buff *skb,
 		if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code))
 			goto nla_put_failure;
 		break;
+	default:
+		break;
 	}
 
 	return 0;
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 133eb4772f12..51a459c3c649 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -947,9 +947,10 @@ static int xt_table_seq_show(struct seq_file *seq, void *v)
 {
 	struct xt_table *table = list_entry(v, struct xt_table, list);
 
-	if (strlen(table->name))
-		return seq_printf(seq, "%s\n", table->name);
-	else
+	if (strlen(table->name)) {
+		seq_printf(seq, "%s\n", table->name);
+		return seq_has_overflowed(seq);
+	} else
 		return 0;
 }
 
@@ -1086,8 +1087,10 @@ static int xt_match_seq_show(struct seq_file *seq, void *v)
 		if (trav->curr == trav->head)
 			return 0;
 		match = list_entry(trav->curr, struct xt_match, list);
-		return (*match->name == '\0') ? 0 :
-		       seq_printf(seq, "%s\n", match->name);
+		if (*match->name == '\0')
+			return 0;
+		seq_printf(seq, "%s\n", match->name);
+		return seq_has_overflowed(seq);
 	}
 	return 0;
 }
@@ -1139,8 +1142,10 @@ static int xt_target_seq_show(struct seq_file *seq, void *v)
 		if (trav->curr == trav->head)
 			return 0;
 		target = list_entry(trav->curr, struct xt_target, list);
-		return (*target->name == '\0') ? 0 :
-		       seq_printf(seq, "%s\n", target->name);
+		if (*target->name == '\0')
+			return 0;
+		seq_printf(seq, "%s\n", target->name);
+		return seq_has_overflowed(seq);
 	}
 	return 0;
 }
diff --git a/net/netfilter/xt_DSCP.c b/net/netfilter/xt_DSCP.c
index ae8271652efa..3f83d38c4e5b 100644
--- a/net/netfilter/xt_DSCP.c
+++ b/net/netfilter/xt_DSCP.c
@@ -37,7 +37,8 @@ dscp_tg(struct sk_buff *skb, const struct xt_action_param *par)
 		if (!skb_make_writable(skb, sizeof(struct iphdr)))
 			return NF_DROP;
 
-		ipv4_change_dsfield(ip_hdr(skb), (__u8)(~XT_DSCP_MASK),
+		ipv4_change_dsfield(ip_hdr(skb),
+				    (__force __u8)(~XT_DSCP_MASK),
 				    dinfo->dscp << XT_DSCP_SHIFT);
 
 	}
@@ -54,7 +55,8 @@ dscp_tg6(struct sk_buff *skb, const struct xt_action_param *par)
 		if (!skb_make_writable(skb, sizeof(struct ipv6hdr)))
 			return NF_DROP;
 
-		ipv6_change_dsfield(ipv6_hdr(skb), (__u8)(~XT_DSCP_MASK),
+		ipv6_change_dsfield(ipv6_hdr(skb),
+				    (__force __u8)(~XT_DSCP_MASK),
 				    dinfo->dscp << XT_DSCP_SHIFT);
 	}
 	return XT_CONTINUE;
diff --git a/net/netfilter/xt_REDIRECT.c b/net/netfilter/xt_REDIRECT.c
index 22a10309297c..03f0b370e178 100644
--- a/net/netfilter/xt_REDIRECT.c
+++ b/net/netfilter/xt_REDIRECT.c
@@ -26,48 +26,12 @@
 #include <net/checksum.h>
 #include <net/protocol.h>
 #include <net/netfilter/nf_nat.h>
-
-static const struct in6_addr loopback_addr = IN6ADDR_LOOPBACK_INIT;
+#include <net/netfilter/nf_nat_redirect.h>
 
 static unsigned int
 redirect_tg6(struct sk_buff *skb, const struct xt_action_param *par)
 {
-	const struct nf_nat_range *range = par->targinfo;
-	struct nf_nat_range newrange;
-	struct in6_addr newdst;
-	enum ip_conntrack_info ctinfo;
-	struct nf_conn *ct;
-
-	ct = nf_ct_get(skb, &ctinfo);
-	if (par->hooknum == NF_INET_LOCAL_OUT)
-		newdst = loopback_addr;
-	else {
-		struct inet6_dev *idev;
-		struct inet6_ifaddr *ifa;
-		bool addr = false;
-
-		rcu_read_lock();
-		idev = __in6_dev_get(skb->dev);
-		if (idev != NULL) {
-			list_for_each_entry(ifa, &idev->addr_list, if_list) {
-				newdst = ifa->addr;
-				addr = true;
-				break;
-			}
-		}
-		rcu_read_unlock();
-
-		if (!addr)
-			return NF_DROP;
-	}
-
-	newrange.flags		= range->flags | NF_NAT_RANGE_MAP_IPS;
-	newrange.min_addr.in6	= newdst;
-	newrange.max_addr.in6	= newdst;
-	newrange.min_proto	= range->min_proto;
-	newrange.max_proto	= range->max_proto;
-
-	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_DST);
+	return nf_nat_redirect_ipv6(skb, par->targinfo, par->hooknum);
 }
 
 static int redirect_tg6_checkentry(const struct xt_tgchk_param *par)
@@ -98,48 +62,7 @@ static int redirect_tg4_check(const struct xt_tgchk_param *par)
 static unsigned int
 redirect_tg4(struct sk_buff *skb, const struct xt_action_param *par)
 {
-	struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-	__be32 newdst;
-	const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
-	struct nf_nat_range newrange;
-
-	NF_CT_ASSERT(par->hooknum == NF_INET_PRE_ROUTING ||
-		     par->hooknum == NF_INET_LOCAL_OUT);
-
-	ct = nf_ct_get(skb, &ctinfo);
-	NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED));
-
-	/* Local packets: make them go to loopback */
-	if (par->hooknum == NF_INET_LOCAL_OUT)
-		newdst = htonl(0x7F000001);
-	else {
-		struct in_device *indev;
-		struct in_ifaddr *ifa;
-
-		newdst = 0;
-
-		rcu_read_lock();
-		indev = __in_dev_get_rcu(skb->dev);
-		if (indev && (ifa = indev->ifa_list))
-			newdst = ifa->ifa_local;
-		rcu_read_unlock();
-
-		if (!newdst)
-			return NF_DROP;
-	}
-
-	/* Transfer from original range. */
-	memset(&newrange.min_addr, 0, sizeof(newrange.min_addr));
-	memset(&newrange.max_addr, 0, sizeof(newrange.max_addr));
-	newrange.flags	     = mr->range[0].flags | NF_NAT_RANGE_MAP_IPS;
-	newrange.min_addr.ip = newdst;
-	newrange.max_addr.ip = newdst;
-	newrange.min_proto   = mr->range[0].min;
-	newrange.max_proto   = mr->range[0].max;
-
-	/* Hand modified range to generic setup. */
-	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_DST);
+	return nf_nat_redirect_ipv4(skb, par->targinfo, par->hooknum);
 }
 
 static struct xt_target redirect_tg_reg[] __read_mostly = {
diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c
index ef8a926752a9..cca96cec1b68 100644
--- a/net/netfilter/xt_TPROXY.c
+++ b/net/netfilter/xt_TPROXY.c
@@ -42,15 +42,21 @@ enum nf_tproxy_lookup_t {
 
 static bool tproxy_sk_is_transparent(struct sock *sk)
 {
-	if (sk->sk_state != TCP_TIME_WAIT) {
-		if (inet_sk(sk)->transparent)
-			return true;
-		sock_put(sk);
-	} else {
+	switch (sk->sk_state) {
+	case TCP_TIME_WAIT:
 		if (inet_twsk(sk)->tw_transparent)
 			return true;
-		inet_twsk_put(inet_twsk(sk));
+		break;
+	case TCP_NEW_SYN_RECV:
+		if (inet_rsk(inet_reqsk(sk))->no_srccheck)
+			return true;
+		break;
+	default:
+		if (inet_sk(sk)->transparent)
+			return true;
 	}
+
+	sock_gen_put(sk);
 	return false;
 }
 
@@ -266,7 +272,7 @@ tproxy_handle_time_wait4(struct sk_buff *skb, __be32 laddr, __be16 lport,
 					    hp->source, lport ? lport : hp->dest,
 					    skb->dev, NFT_LOOKUP_LISTENER);
 		if (sk2) {
-			inet_twsk_deschedule(inet_twsk(sk), &tcp_death_row);
+			inet_twsk_deschedule(inet_twsk(sk));
 			inet_twsk_put(inet_twsk(sk));
 			sk = sk2;
 		}
@@ -431,7 +437,7 @@ tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff,
 					    tgi->lport ? tgi->lport : hp->dest,
 					    skb->dev, NFT_LOOKUP_LISTENER);
 		if (sk2) {
-			inet_twsk_deschedule(inet_twsk(sk), &tcp_death_row);
+			inet_twsk_deschedule(inet_twsk(sk));
 			inet_twsk_put(inet_twsk(sk));
 			sk = sk2;
 		}
@@ -513,8 +519,8 @@ static int tproxy_tg6_check(const struct xt_tgchk_param *par)
 {
 	const struct ip6t_ip6 *i = par->entryinfo;
 
-	if ((i->proto == IPPROTO_TCP || i->proto == IPPROTO_UDP)
-	    && !(i->flags & IP6T_INV_PROTO))
+	if ((i->proto == IPPROTO_TCP || i->proto == IPPROTO_UDP) &&
+	    !(i->invflags & IP6T_INV_PROTO))
 		return 0;
 
 	pr_info("Can be used only in combination with "
diff --git a/net/netfilter/xt_cgroup.c b/net/netfilter/xt_cgroup.c
index 7198d660b4de..a1d126f29463 100644
--- a/net/netfilter/xt_cgroup.c
+++ b/net/netfilter/xt_cgroup.c
@@ -39,7 +39,7 @@ cgroup_mt(const struct sk_buff *skb, struct xt_action_param *par)
 {
 	const struct xt_cgroup_info *info = par->matchinfo;
 
-	if (skb->sk == NULL)
+	if (skb->sk == NULL || !sk_fullsock(skb->sk))
 		return false;
 
 	return (info->id == skb->sk->sk_classid) ^ info->invert;
diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c
index fbc66bb250d5..29ba6218a820 100644
--- a/net/netfilter/xt_connlimit.c
+++ b/net/netfilter/xt_connlimit.c
@@ -134,6 +134,7 @@ static bool add_hlist(struct hlist_head *head,
 static unsigned int check_hlist(struct net *net,
 				struct hlist_head *head,
 				const struct nf_conntrack_tuple *tuple,
+				u16 zone,
 				bool *addit)
 {
 	const struct nf_conntrack_tuple_hash *found;
@@ -147,8 +148,7 @@ static unsigned int check_hlist(struct net *net,
 
 	/* check the saved connections */
 	hlist_for_each_entry_safe(conn, n, head, node) {
-		found    = nf_conntrack_find_get(net, NF_CT_DEFAULT_ZONE,
-						 &conn->tuple);
+		found = nf_conntrack_find_get(net, zone, &conn->tuple);
 		if (found == NULL) {
 			hlist_del(&conn->node);
 			kmem_cache_free(connlimit_conn_cachep, conn);
@@ -201,7 +201,7 @@ 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)
+	   u8 family, u16 zone)
 {
 	struct xt_connlimit_rb *gc_nodes[CONNLIMIT_GC_MAX_NODES];
 	struct rb_node **rbnode, *parent;
@@ -229,7 +229,7 @@ count_tree(struct net *net, struct rb_root *root,
 		} else {
 			/* same source network -> be counted! */
 			unsigned int count;
-			count = check_hlist(net, &rbconn->hhead, tuple, &addit);
+			count = check_hlist(net, &rbconn->hhead, tuple, zone, &addit);
 
 			tree_nodes_free(root, gc_nodes, gc_count);
 			if (!addit)
@@ -245,7 +245,7 @@ count_tree(struct net *net, struct rb_root *root,
 			continue;
 
 		/* only used for GC on hhead, retval and 'addit' ignored */
-		check_hlist(net, &rbconn->hhead, tuple, &addit);
+		check_hlist(net, &rbconn->hhead, tuple, zone, &addit);
 		if (hlist_empty(&rbconn->hhead))
 			gc_nodes[gc_count++] = rbconn;
 	}
@@ -290,7 +290,7 @@ static int count_them(struct net *net,
 		      const struct nf_conntrack_tuple *tuple,
 		      const union nf_inet_addr *addr,
 		      const union nf_inet_addr *mask,
-		      u_int8_t family)
+		      u_int8_t family, u16 zone)
 {
 	struct rb_root *root;
 	int count;
@@ -306,7 +306,7 @@ static int count_them(struct net *net,
 
 	spin_lock_bh(&xt_connlimit_locks[hash % CONNLIMIT_LOCK_SLOTS]);
 
-	count = count_tree(net, root, tuple, addr, mask, family);
+	count = count_tree(net, root, tuple, addr, mask, family, zone);
 
 	spin_unlock_bh(&xt_connlimit_locks[hash % CONNLIMIT_LOCK_SLOTS]);
 
@@ -324,13 +324,16 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	enum ip_conntrack_info ctinfo;
 	const struct nf_conn *ct;
 	unsigned int connections;
+	u16 zone = NF_CT_DEFAULT_ZONE;
 
 	ct = nf_ct_get(skb, &ctinfo);
-	if (ct != NULL)
+	if (ct != NULL) {
 		tuple_ptr = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
-	else if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb),
-				    par->family, &tuple))
+		zone = nf_ct_zone(ct);
+	} else if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb),
+				    par->family, &tuple)) {
 		goto hotdrop;
+	}
 
 	if (par->family == NFPROTO_IPV6) {
 		const struct ipv6hdr *iph = ipv6_hdr(skb);
@@ -343,7 +346,7 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	}
 
 	connections = count_them(net, info->data, tuple_ptr, &addr,
-	                         &info->mask, par->family);
+	                         &info->mask, par->family, zone);
 	if (connections == 0)
 		/* kmalloc failed, drop it entirely */
 		goto hotdrop;
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index 05fbc2a0be46..178696852bde 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -789,7 +789,6 @@ static void dl_seq_stop(struct seq_file *s, void *v)
 static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family,
 				   struct seq_file *s)
 {
-	int res;
 	const struct xt_hashlimit_htable *ht = s->private;
 
 	spin_lock(&ent->lock);
@@ -798,33 +797,32 @@ static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family,
 
 	switch (family) {
 	case NFPROTO_IPV4:
-		res = seq_printf(s, "%ld %pI4:%u->%pI4:%u %u %u %u\n",
-				 (long)(ent->expires - jiffies)/HZ,
-				 &ent->dst.ip.src,
-				 ntohs(ent->dst.src_port),
-				 &ent->dst.ip.dst,
-				 ntohs(ent->dst.dst_port),
-				 ent->rateinfo.credit, ent->rateinfo.credit_cap,
-				 ent->rateinfo.cost);
+		seq_printf(s, "%ld %pI4:%u->%pI4:%u %u %u %u\n",
+			   (long)(ent->expires - jiffies)/HZ,
+			   &ent->dst.ip.src,
+			   ntohs(ent->dst.src_port),
+			   &ent->dst.ip.dst,
+			   ntohs(ent->dst.dst_port),
+			   ent->rateinfo.credit, ent->rateinfo.credit_cap,
+			   ent->rateinfo.cost);
 		break;
 #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 	case NFPROTO_IPV6:
-		res = seq_printf(s, "%ld %pI6:%u->%pI6:%u %u %u %u\n",
-				 (long)(ent->expires - jiffies)/HZ,
-				 &ent->dst.ip6.src,
-				 ntohs(ent->dst.src_port),
-				 &ent->dst.ip6.dst,
-				 ntohs(ent->dst.dst_port),
-				 ent->rateinfo.credit, ent->rateinfo.credit_cap,
-				 ent->rateinfo.cost);
+		seq_printf(s, "%ld %pI6:%u->%pI6:%u %u %u %u\n",
+			   (long)(ent->expires - jiffies)/HZ,
+			   &ent->dst.ip6.src,
+			   ntohs(ent->dst.src_port),
+			   &ent->dst.ip6.dst,
+			   ntohs(ent->dst.dst_port),
+			   ent->rateinfo.credit, ent->rateinfo.credit_cap,
+			   ent->rateinfo.cost);
 		break;
 #endif
 	default:
 		BUG();
-		res = 0;
 	}
 	spin_unlock(&ent->lock);
-	return res;
+	return seq_has_overflowed(s);
 }
 
 static int dl_seq_show(struct seq_file *s, void *v)
diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c
index c529161cdbf8..0778855ea5e7 100644
--- a/net/netfilter/xt_osf.c
+++ b/net/netfilter/xt_osf.c
@@ -225,6 +225,8 @@ xt_osf_match_packet(const struct sk_buff *skb, struct xt_action_param *p)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(kf, &xt_osf_fingers[df], finger_entry) {
+		int foptsize, optnum;
+
 		f = &kf->finger;
 
 		if (!(info->flags & XT_OSF_LOG) && strcmp(info->genre, f->genre))
@@ -233,110 +235,109 @@ xt_osf_match_packet(const struct sk_buff *skb, struct xt_action_param *p)
 		optp = _optp;
 		fmatch = FMATCH_WRONG;
 
-		if (totlen == f->ss && xt_osf_ttl(skb, info, f->ttl)) {
-			int foptsize, optnum;
+		if (totlen != f->ss || !xt_osf_ttl(skb, info, f->ttl))
+			continue;
 
-			/*
-			 * Should not happen if userspace parser was written correctly.
-			 */
-			if (f->wss.wc >= OSF_WSS_MAX)
-				continue;
+		/*
+		 * Should not happen if userspace parser was written correctly.
+		 */
+		if (f->wss.wc >= OSF_WSS_MAX)
+			continue;
 
-			/* Check options */
+		/* Check options */
 
-			foptsize = 0;
-			for (optnum = 0; optnum < f->opt_num; ++optnum)
-				foptsize += f->opt[optnum].length;
+		foptsize = 0;
+		for (optnum = 0; optnum < f->opt_num; ++optnum)
+			foptsize += f->opt[optnum].length;
 
-			if (foptsize > MAX_IPOPTLEN ||
-				optsize > MAX_IPOPTLEN ||
-				optsize != foptsize)
-				continue;
+		if (foptsize > MAX_IPOPTLEN ||
+		    optsize > MAX_IPOPTLEN ||
+		    optsize != foptsize)
+			continue;
 
-			check_WSS = f->wss.wc;
+		check_WSS = f->wss.wc;
 
-			for (optnum = 0; optnum < f->opt_num; ++optnum) {
-				if (f->opt[optnum].kind == (*optp)) {
-					__u32 len = f->opt[optnum].length;
-					const __u8 *optend = optp + len;
-					int loop_cont = 0;
+		for (optnum = 0; optnum < f->opt_num; ++optnum) {
+			if (f->opt[optnum].kind == (*optp)) {
+				__u32 len = f->opt[optnum].length;
+				const __u8 *optend = optp + len;
+				int loop_cont = 0;
 
-					fmatch = FMATCH_OK;
+				fmatch = FMATCH_OK;
 
-					switch (*optp) {
-					case OSFOPT_MSS:
-						mss = optp[3];
-						mss <<= 8;
-						mss |= optp[2];
+				switch (*optp) {
+				case OSFOPT_MSS:
+					mss = optp[3];
+					mss <<= 8;
+					mss |= optp[2];
 
-						mss = ntohs((__force __be16)mss);
-						break;
-					case OSFOPT_TS:
-						loop_cont = 1;
-						break;
-					}
+					mss = ntohs((__force __be16)mss);
+					break;
+				case OSFOPT_TS:
+					loop_cont = 1;
+					break;
+				}
 
-					optp = optend;
-				} else
-					fmatch = FMATCH_OPT_WRONG;
+				optp = optend;
+			} else
+				fmatch = FMATCH_OPT_WRONG;
 
-				if (fmatch != FMATCH_OK)
-					break;
-			}
+			if (fmatch != FMATCH_OK)
+				break;
+		}
 
-			if (fmatch != FMATCH_OPT_WRONG) {
-				fmatch = FMATCH_WRONG;
+		if (fmatch != FMATCH_OPT_WRONG) {
+			fmatch = FMATCH_WRONG;
 
-				switch (check_WSS) {
-				case OSF_WSS_PLAIN:
-					if (f->wss.val == 0 || window == f->wss.val)
-						fmatch = FMATCH_OK;
-					break;
-				case OSF_WSS_MSS:
-					/*
-					 * Some smart modems decrease mangle MSS to 
-					 * SMART_MSS_2, so we check standard, decreased
-					 * and the one provided in the fingerprint MSS
-					 * values.
-					 */
+			switch (check_WSS) {
+			case OSF_WSS_PLAIN:
+				if (f->wss.val == 0 || window == f->wss.val)
+					fmatch = FMATCH_OK;
+				break;
+			case OSF_WSS_MSS:
+				/*
+				 * Some smart modems decrease mangle MSS to
+				 * SMART_MSS_2, so we check standard, decreased
+				 * and the one provided in the fingerprint MSS
+				 * values.
+				 */
 #define SMART_MSS_1	1460
 #define SMART_MSS_2	1448
-					if (window == f->wss.val * mss ||
-					    window == f->wss.val * SMART_MSS_1 ||
-					    window == f->wss.val * SMART_MSS_2)
-						fmatch = FMATCH_OK;
-					break;
-				case OSF_WSS_MTU:
-					if (window == f->wss.val * (mss + 40) ||
-					    window == f->wss.val * (SMART_MSS_1 + 40) ||
-					    window == f->wss.val * (SMART_MSS_2 + 40))
-						fmatch = FMATCH_OK;
-					break;
-				case OSF_WSS_MODULO:
-					if ((window % f->wss.val) == 0)
-						fmatch = FMATCH_OK;
-					break;
-				}
+				if (window == f->wss.val * mss ||
+				    window == f->wss.val * SMART_MSS_1 ||
+				    window == f->wss.val * SMART_MSS_2)
+					fmatch = FMATCH_OK;
+				break;
+			case OSF_WSS_MTU:
+				if (window == f->wss.val * (mss + 40) ||
+				    window == f->wss.val * (SMART_MSS_1 + 40) ||
+				    window == f->wss.val * (SMART_MSS_2 + 40))
+					fmatch = FMATCH_OK;
+				break;
+			case OSF_WSS_MODULO:
+				if ((window % f->wss.val) == 0)
+					fmatch = FMATCH_OK;
+				break;
 			}
+		}
 
-			if (fmatch != FMATCH_OK)
-				continue;
+		if (fmatch != FMATCH_OK)
+			continue;
 
-			fcount++;
+		fcount++;
 
-			if (info->flags & XT_OSF_LOG)
-				nf_log_packet(net, p->family, p->hooknum, skb,
-					p->in, p->out, NULL,
-					"%s [%s:%s] : %pI4:%d -> %pI4:%d hops=%d\n",
-					f->genre, f->version, f->subtype,
-					&ip->saddr, ntohs(tcp->source),
-					&ip->daddr, ntohs(tcp->dest),
-					f->ttl - ip->ttl);
+		if (info->flags & XT_OSF_LOG)
+			nf_log_packet(net, p->family, p->hooknum, skb,
+				      p->in, p->out, NULL,
+				      "%s [%s:%s] : %pI4:%d -> %pI4:%d hops=%d\n",
+				      f->genre, f->version, f->subtype,
+				      &ip->saddr, ntohs(tcp->source),
+				      &ip->daddr, ntohs(tcp->dest),
+				      f->ttl - ip->ttl);
 
-			if ((info->flags & XT_OSF_LOG) &&
-			    info->loglevel == XT_OSF_LOGLEVEL_FIRST)
-				break;
-		}
+		if ((info->flags & XT_OSF_LOG) &&
+		    info->loglevel == XT_OSF_LOGLEVEL_FIRST)
+			break;
 	}
 	rcu_read_unlock();
 
diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c
index f440f57a452f..1caaccbc306c 100644
--- a/net/netfilter/xt_physdev.c
+++ b/net/netfilter/xt_physdev.c
@@ -25,16 +25,15 @@ MODULE_ALIAS("ip6t_physdev");
 static bool
 physdev_mt(const struct sk_buff *skb, struct xt_action_param *par)
 {
-	static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long))));
 	const struct xt_physdev_info *info = par->matchinfo;
+	const struct net_device *physdev;
 	unsigned long ret;
 	const char *indev, *outdev;
-	const struct nf_bridge_info *nf_bridge;
 
 	/* Not a bridged IP packet or no info available yet:
 	 * LOCAL_OUT/mangle and LOCAL_OUT/nat don't know if
 	 * the destination device will be a bridge. */
-	if (!(nf_bridge = skb->nf_bridge)) {
+	if (!skb->nf_bridge) {
 		/* Return MATCH if the invert flags of the used options are on */
 		if ((info->bitmask & XT_PHYSDEV_OP_BRIDGED) &&
 		    !(info->invert & XT_PHYSDEV_OP_BRIDGED))
@@ -54,31 +53,41 @@ physdev_mt(const struct sk_buff *skb, struct xt_action_param *par)
 		return true;
 	}
 
+	physdev = nf_bridge_get_physoutdev(skb);
+	outdev = physdev ? physdev->name : NULL;
+
 	/* This only makes sense in the FORWARD and POSTROUTING chains */
 	if ((info->bitmask & XT_PHYSDEV_OP_BRIDGED) &&
-	    (!!(nf_bridge->mask & BRNF_BRIDGED) ^
-	    !(info->invert & XT_PHYSDEV_OP_BRIDGED)))
+	    (!!outdev ^ !(info->invert & XT_PHYSDEV_OP_BRIDGED)))
 		return false;
 
+	physdev = nf_bridge_get_physindev(skb);
+	indev = physdev ? physdev->name : NULL;
+
 	if ((info->bitmask & XT_PHYSDEV_OP_ISIN &&
-	    (!nf_bridge->physindev ^ !!(info->invert & XT_PHYSDEV_OP_ISIN))) ||
+	    (!indev ^ !!(info->invert & XT_PHYSDEV_OP_ISIN))) ||
 	    (info->bitmask & XT_PHYSDEV_OP_ISOUT &&
-	    (!nf_bridge->physoutdev ^ !!(info->invert & XT_PHYSDEV_OP_ISOUT))))
+	    (!outdev ^ !!(info->invert & XT_PHYSDEV_OP_ISOUT))))
 		return false;
 
 	if (!(info->bitmask & XT_PHYSDEV_OP_IN))
 		goto match_outdev;
-	indev = nf_bridge->physindev ? nf_bridge->physindev->name : nulldevname;
-	ret = ifname_compare_aligned(indev, info->physindev, info->in_mask);
 
-	if (!ret ^ !(info->invert & XT_PHYSDEV_OP_IN))
-		return false;
+	if (indev) {
+		ret = ifname_compare_aligned(indev, info->physindev,
+					     info->in_mask);
+
+		if (!ret ^ !(info->invert & XT_PHYSDEV_OP_IN))
+			return false;
+	}
 
 match_outdev:
 	if (!(info->bitmask & XT_PHYSDEV_OP_OUT))
 		return true;
-	outdev = nf_bridge->physoutdev ?
-		 nf_bridge->physoutdev->name : nulldevname;
+
+	if (!outdev)
+		return false;
+
 	ret = ifname_compare_aligned(outdev, info->physoutdev, info->out_mask);
 
 	return (!!ret ^ !(info->invert & XT_PHYSDEV_OP_OUT));
diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c
index a9faae89f955..45e1b30e4fb2 100644
--- a/net/netfilter/xt_recent.c
+++ b/net/netfilter/xt_recent.c
@@ -43,25 +43,29 @@ MODULE_LICENSE("GPL");
 MODULE_ALIAS("ipt_recent");
 MODULE_ALIAS("ip6t_recent");
 
-static unsigned int ip_list_tot = 100;
-static unsigned int ip_pkt_list_tot = 20;
-static unsigned int ip_list_hash_size = 0;
-static unsigned int ip_list_perms = 0644;
-static unsigned int ip_list_uid = 0;
-static unsigned int ip_list_gid = 0;
+static unsigned int ip_list_tot __read_mostly = 100;
+static unsigned int ip_list_hash_size __read_mostly;
+static unsigned int ip_list_perms __read_mostly = 0644;
+static unsigned int ip_list_uid __read_mostly;
+static unsigned int ip_list_gid __read_mostly;
 module_param(ip_list_tot, uint, 0400);
-module_param(ip_pkt_list_tot, uint, 0400);
 module_param(ip_list_hash_size, uint, 0400);
 module_param(ip_list_perms, uint, 0400);
 module_param(ip_list_uid, uint, S_IRUGO | S_IWUSR);
 module_param(ip_list_gid, uint, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(ip_list_tot, "number of IPs to remember per list");
-MODULE_PARM_DESC(ip_pkt_list_tot, "number of packets per IP address to remember (max. 255)");
 MODULE_PARM_DESC(ip_list_hash_size, "size of hash table used to look up IPs");
 MODULE_PARM_DESC(ip_list_perms, "permissions on /proc/net/xt_recent/* files");
 MODULE_PARM_DESC(ip_list_uid, "default owner of /proc/net/xt_recent/* files");
 MODULE_PARM_DESC(ip_list_gid, "default owning group of /proc/net/xt_recent/* files");
 
+/* retained for backwards compatibility */
+static unsigned int ip_pkt_list_tot __read_mostly;
+module_param(ip_pkt_list_tot, uint, 0400);
+MODULE_PARM_DESC(ip_pkt_list_tot, "number of packets per IP address to remember (max. 255)");
+
+#define XT_RECENT_MAX_NSTAMPS	256
+
 struct recent_entry {
 	struct list_head	list;
 	struct list_head	lru_list;
@@ -79,6 +83,7 @@ struct recent_table {
 	union nf_inet_addr	mask;
 	unsigned int		refcnt;
 	unsigned int		entries;
+	u8			nstamps_max_mask;
 	struct list_head	lru_list;
 	struct list_head	iphash[0];
 };
@@ -90,7 +95,8 @@ struct recent_net {
 #endif
 };
 
-static int recent_net_id;
+static int recent_net_id __read_mostly;
+
 static inline struct recent_net *recent_pernet(struct net *net)
 {
 	return net_generic(net, recent_net_id);
@@ -171,12 +177,15 @@ recent_entry_init(struct recent_table *t, const union nf_inet_addr *addr,
 		  u_int16_t family, u_int8_t ttl)
 {
 	struct recent_entry *e;
+	unsigned int nstamps_max = t->nstamps_max_mask;
 
 	if (t->entries >= ip_list_tot) {
 		e = list_entry(t->lru_list.next, struct recent_entry, lru_list);
 		recent_entry_remove(t, e);
 	}
-	e = kmalloc(sizeof(*e) + sizeof(e->stamps[0]) * ip_pkt_list_tot,
+
+	nstamps_max += 1;
+	e = kmalloc(sizeof(*e) + sizeof(e->stamps[0]) * nstamps_max,
 		    GFP_ATOMIC);
 	if (e == NULL)
 		return NULL;
@@ -197,7 +206,7 @@ recent_entry_init(struct recent_table *t, const union nf_inet_addr *addr,
 
 static void recent_entry_update(struct recent_table *t, struct recent_entry *e)
 {
-	e->index %= ip_pkt_list_tot;
+	e->index &= t->nstamps_max_mask;
 	e->stamps[e->index++] = jiffies;
 	if (e->index > e->nstamps)
 		e->nstamps = e->index;
@@ -326,6 +335,7 @@ static int recent_mt_check(const struct xt_mtchk_param *par,
 	kuid_t uid;
 	kgid_t gid;
 #endif
+	unsigned int nstamp_mask;
 	unsigned int i;
 	int ret = -EINVAL;
 	size_t sz;
@@ -349,19 +359,32 @@ static int recent_mt_check(const struct xt_mtchk_param *par,
 		return -EINVAL;
 	if ((info->check_set & XT_RECENT_REAP) && !info->seconds)
 		return -EINVAL;
-	if (info->hit_count > ip_pkt_list_tot) {
-		pr_info("hitcount (%u) is larger than "
-			"packets to be remembered (%u)\n",
-			info->hit_count, ip_pkt_list_tot);
+	if (info->hit_count >= XT_RECENT_MAX_NSTAMPS) {
+		pr_info("hitcount (%u) is larger than allowed maximum (%u)\n",
+			info->hit_count, XT_RECENT_MAX_NSTAMPS - 1);
 		return -EINVAL;
 	}
 	if (info->name[0] == '\0' ||
 	    strnlen(info->name, XT_RECENT_NAME_LEN) == XT_RECENT_NAME_LEN)
 		return -EINVAL;
 
+	if (ip_pkt_list_tot && info->hit_count < ip_pkt_list_tot)
+		nstamp_mask = roundup_pow_of_two(ip_pkt_list_tot) - 1;
+	else if (info->hit_count)
+		nstamp_mask = roundup_pow_of_two(info->hit_count) - 1;
+	else
+		nstamp_mask = 32 - 1;
+
 	mutex_lock(&recent_mutex);
 	t = recent_table_lookup(recent_net, info->name);
 	if (t != NULL) {
+		if (nstamp_mask > t->nstamps_max_mask) {
+			spin_lock_bh(&recent_lock);
+			recent_table_flush(t);
+			t->nstamps_max_mask = nstamp_mask;
+			spin_unlock_bh(&recent_lock);
+		}
+
 		t->refcnt++;
 		ret = 0;
 		goto out;
@@ -377,6 +400,7 @@ static int recent_mt_check(const struct xt_mtchk_param *par,
 		goto out;
 	}
 	t->refcnt = 1;
+	t->nstamps_max_mask = nstamp_mask;
 
 	memcpy(&t->mask, &info->mask, sizeof(t->mask));
 	strcpy(t->name, info->name);
@@ -497,9 +521,12 @@ static void recent_seq_stop(struct seq_file *s, void *v)
 static int recent_seq_show(struct seq_file *seq, void *v)
 {
 	const struct recent_entry *e = v;
+	struct recent_iter_state *st = seq->private;
+	const struct recent_table *t = st->table;
 	unsigned int i;
 
-	i = (e->index - 1) % ip_pkt_list_tot;
+	i = (e->index - 1) & t->nstamps_max_mask;
+
 	if (e->family == NFPROTO_IPV4)
 		seq_printf(seq, "src=%pI4 ttl: %u last_seen: %lu oldest_pkt: %u",
 			   &e->addr.ip, e->ttl, e->stamps[i], e->index);
@@ -717,7 +744,9 @@ static int __init recent_mt_init(void)
 {
 	int err;
 
-	if (!ip_list_tot || !ip_pkt_list_tot || ip_pkt_list_tot > 255)
+	BUILD_BUG_ON_NOT_POWER_OF_2(XT_RECENT_MAX_NSTAMPS);
+
+	if (!ip_list_tot || ip_pkt_list_tot >= XT_RECENT_MAX_NSTAMPS)
 		return -EINVAL;
 	ip_list_hash_size = 1 << fls(ip_list_tot);
 
diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c
index 5732cd64acc0..89045982ec94 100644
--- a/net/netfilter/xt_set.c
+++ b/net/netfilter/xt_set.c
@@ -157,7 +157,7 @@ set_match_v1_destroy(const struct xt_mtdtor_param *par)
 /* Revision 3 match */
 
 static bool
-match_counter(u64 counter, const struct ip_set_counter_match *info)
+match_counter0(u64 counter, const struct ip_set_counter_match0 *info)
 {
 	switch (info->op) {
 	case IPSET_COUNTER_NONE:
@@ -192,14 +192,60 @@ set_match_v3(const struct sk_buff *skb, struct xt_action_param *par)
 	if (!(ret && opt.cmdflags & IPSET_FLAG_MATCH_COUNTERS))
 		return ret;
 
-	if (!match_counter(opt.ext.packets, &info->packets))
-		return 0;
-	return match_counter(opt.ext.bytes, &info->bytes);
+	if (!match_counter0(opt.ext.packets, &info->packets))
+		return false;
+	return match_counter0(opt.ext.bytes, &info->bytes);
 }
 
 #define set_match_v3_checkentry	set_match_v1_checkentry
 #define set_match_v3_destroy	set_match_v1_destroy
 
+/* Revision 4 match */
+
+static bool
+match_counter(u64 counter, const struct ip_set_counter_match *info)
+{
+	switch (info->op) {
+	case IPSET_COUNTER_NONE:
+		return true;
+	case IPSET_COUNTER_EQ:
+		return counter == info->value;
+	case IPSET_COUNTER_NE:
+		return counter != info->value;
+	case IPSET_COUNTER_LT:
+		return counter < info->value;
+	case IPSET_COUNTER_GT:
+		return counter > info->value;
+	}
+	return false;
+}
+
+static bool
+set_match_v4(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	const struct xt_set_info_match_v4 *info = par->matchinfo;
+	ADT_OPT(opt, par->family, info->match_set.dim,
+		info->match_set.flags, info->flags, UINT_MAX);
+	int ret;
+
+	if (info->packets.op != IPSET_COUNTER_NONE ||
+	    info->bytes.op != IPSET_COUNTER_NONE)
+		opt.cmdflags |= IPSET_FLAG_MATCH_COUNTERS;
+
+	ret = match_set(info->match_set.index, skb, par, &opt,
+			info->match_set.flags & IPSET_INV_MATCH);
+
+	if (!(ret && opt.cmdflags & IPSET_FLAG_MATCH_COUNTERS))
+		return ret;
+
+	if (!match_counter(opt.ext.packets, &info->packets))
+		return false;
+	return match_counter(opt.ext.bytes, &info->bytes);
+}
+
+#define set_match_v4_checkentry	set_match_v1_checkentry
+#define set_match_v4_destroy	set_match_v1_destroy
+
 /* Revision 0 interface: backward compatible with netfilter/iptables */
 
 static unsigned int
@@ -573,6 +619,27 @@ static struct xt_match set_matches[] __read_mostly = {
 		.destroy	= set_match_v3_destroy,
 		.me		= THIS_MODULE
 	},
+	/* new revision for counters support: update, match */
+	{
+		.name		= "set",
+		.family		= NFPROTO_IPV4,
+		.revision	= 4,
+		.match		= set_match_v4,
+		.matchsize	= sizeof(struct xt_set_info_match_v4),
+		.checkentry	= set_match_v4_checkentry,
+		.destroy	= set_match_v4_destroy,
+		.me		= THIS_MODULE
+	},
+	{
+		.name		= "set",
+		.family		= NFPROTO_IPV6,
+		.revision	= 4,
+		.match		= set_match_v4,
+		.matchsize	= sizeof(struct xt_set_info_match_v4),
+		.checkentry	= set_match_v4_checkentry,
+		.destroy	= set_match_v4_destroy,
+		.me		= THIS_MODULE
+	},
 };
 
 static struct xt_target set_targets[] __read_mostly = {
diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c
index 1ba67931eb1b..e092cb046326 100644
--- a/net/netfilter/xt_socket.c
+++ b/net/netfilter/xt_socket.c
@@ -129,13 +129,24 @@ xt_socket_get_sock_v4(struct net *net, const u8 protocol,
 	return NULL;
 }
 
-static bool
-socket_match(const struct sk_buff *skb, struct xt_action_param *par,
-	     const struct xt_socket_mtinfo1 *info)
+static bool xt_socket_sk_is_transparent(struct sock *sk)
+{
+	switch (sk->sk_state) {
+	case TCP_TIME_WAIT:
+		return inet_twsk(sk)->tw_transparent;
+
+	case TCP_NEW_SYN_RECV:
+		return inet_rsk(inet_reqsk(sk))->no_srccheck;
+
+	default:
+		return inet_sk(sk)->transparent;
+	}
+}
+
+static struct sock *xt_socket_lookup_slow_v4(const struct sk_buff *skb,
+					     const struct net_device *indev)
 {
 	const struct iphdr *iph = ip_hdr(skb);
-	struct udphdr _hdr, *hp = NULL;
-	struct sock *sk = skb->sk;
 	__be32 uninitialized_var(daddr), uninitialized_var(saddr);
 	__be16 uninitialized_var(dport), uninitialized_var(sport);
 	u8 uninitialized_var(protocol);
@@ -145,10 +156,12 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par,
 #endif
 
 	if (iph->protocol == IPPROTO_UDP || iph->protocol == IPPROTO_TCP) {
+		struct udphdr _hdr, *hp;
+
 		hp = skb_header_pointer(skb, ip_hdrlen(skb),
 					sizeof(_hdr), &_hdr);
 		if (hp == NULL)
-			return false;
+			return NULL;
 
 		protocol = iph->protocol;
 		saddr = iph->saddr;
@@ -158,16 +171,17 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par,
 
 	} else if (iph->protocol == IPPROTO_ICMP) {
 		if (extract_icmp4_fields(skb, &protocol, &saddr, &daddr,
-					&sport, &dport))
-			return false;
+					 &sport, &dport))
+			return NULL;
 	} else {
-		return false;
+		return NULL;
 	}
 
 #ifdef XT_SOCKET_HAVE_CONNTRACK
-	/* Do the lookup with the original socket address in case this is a
-	 * reply packet of an established SNAT-ted connection. */
-
+	/* Do the lookup with the original socket address in
+	 * case this is a reply packet of an established
+	 * SNAT-ted connection.
+	 */
 	ct = nf_ct_get(skb, &ctinfo);
 	if (ct && !nf_ct_is_untracked(ct) &&
 	    ((iph->protocol != IPPROTO_ICMP &&
@@ -183,10 +197,18 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par,
 	}
 #endif
 
+	return xt_socket_get_sock_v4(dev_net(skb->dev), protocol, saddr, daddr,
+				     sport, dport, indev);
+}
+
+static bool
+socket_match(const struct sk_buff *skb, struct xt_action_param *par,
+	     const struct xt_socket_mtinfo1 *info)
+{
+	struct sock *sk = skb->sk;
+
 	if (!sk)
-		sk = xt_socket_get_sock_v4(dev_net(skb->dev), protocol,
-					   saddr, daddr, sport, dport,
-					   par->in);
+		sk = xt_socket_lookup_slow_v4(skb, par->in);
 	if (sk) {
 		bool wildcard;
 		bool transparent = true;
@@ -195,16 +217,14 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par,
 		 * unless XT_SOCKET_NOWILDCARD is set
 		 */
 		wildcard = (!(info->flags & XT_SOCKET_NOWILDCARD) &&
-			    sk->sk_state != TCP_TIME_WAIT &&
+			    sk_fullsock(sk) &&
 			    inet_sk(sk)->inet_rcv_saddr == 0);
 
 		/* Ignore non-transparent sockets,
-		   if XT_SOCKET_TRANSPARENT is used */
+		 * if XT_SOCKET_TRANSPARENT is used
+		 */
 		if (info->flags & XT_SOCKET_TRANSPARENT)
-			transparent = ((sk->sk_state != TCP_TIME_WAIT &&
-					inet_sk(sk)->transparent) ||
-				       (sk->sk_state == TCP_TIME_WAIT &&
-					inet_twsk(sk)->tw_transparent));
+			transparent = xt_socket_sk_is_transparent(sk);
 
 		if (sk != skb->sk)
 			sock_gen_put(sk);
@@ -213,12 +233,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par,
 			sk = NULL;
 	}
 
-	pr_debug("proto %hhu %pI4:%hu -> %pI4:%hu (orig %pI4:%hu) sock %p\n",
-		 protocol, &saddr, ntohs(sport),
-		 &daddr, ntohs(dport),
-		 &iph->daddr, hp ? ntohs(hp->dest) : 0, sk);
-
-	return (sk != NULL);
+	return sk != NULL;
 }
 
 static bool
@@ -243,12 +258,13 @@ static int
 extract_icmp6_fields(const struct sk_buff *skb,
 		     unsigned int outside_hdrlen,
 		     int *protocol,
-		     struct in6_addr **raddr,
-		     struct in6_addr **laddr,
+		     const struct in6_addr **raddr,
+		     const struct in6_addr **laddr,
 		     __be16 *rport,
-		     __be16 *lport)
+		     __be16 *lport,
+		     struct ipv6hdr *ipv6_var)
 {
-	struct ipv6hdr *inside_iph, _inside_iph;
+	const struct ipv6hdr *inside_iph;
 	struct icmp6hdr *icmph, _icmph;
 	__be16 *ports, _ports[2];
 	u8 inside_nexthdr;
@@ -263,12 +279,14 @@ extract_icmp6_fields(const struct sk_buff *skb,
 	if (icmph->icmp6_type & ICMPV6_INFOMSG_MASK)
 		return 1;
 
-	inside_iph = skb_header_pointer(skb, outside_hdrlen + sizeof(_icmph), sizeof(_inside_iph), &_inside_iph);
+	inside_iph = skb_header_pointer(skb, outside_hdrlen + sizeof(_icmph),
+					sizeof(*ipv6_var), ipv6_var);
 	if (inside_iph == NULL)
 		return 1;
 	inside_nexthdr = inside_iph->nexthdr;
 
-	inside_hdrlen = ipv6_skip_exthdr(skb, outside_hdrlen + sizeof(_icmph) + sizeof(_inside_iph),
+	inside_hdrlen = ipv6_skip_exthdr(skb, outside_hdrlen + sizeof(_icmph) +
+					      sizeof(*ipv6_var),
 					 &inside_nexthdr, &inside_fragoff);
 	if (inside_hdrlen < 0)
 		return 1; /* hjm: Packet has no/incomplete transport layer headers. */
@@ -312,28 +330,26 @@ xt_socket_get_sock_v6(struct net *net, const u8 protocol,
 	return NULL;
 }
 
-static bool
-socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par)
+static struct sock *xt_socket_lookup_slow_v6(const struct sk_buff *skb,
+					     const struct net_device *indev)
 {
-	struct ipv6hdr *iph = ipv6_hdr(skb);
-	struct udphdr _hdr, *hp = NULL;
-	struct sock *sk = skb->sk;
-	struct in6_addr *daddr = NULL, *saddr = NULL;
 	__be16 uninitialized_var(dport), uninitialized_var(sport);
-	int thoff = 0, uninitialized_var(tproto);
-	const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo;
+	const struct in6_addr *daddr = NULL, *saddr = NULL;
+	struct ipv6hdr *iph = ipv6_hdr(skb);
+	int thoff = 0, tproto;
 
 	tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL);
 	if (tproto < 0) {
 		pr_debug("unable to find transport header in IPv6 packet, dropping\n");
-		return NF_DROP;
+		return NULL;
 	}
 
 	if (tproto == IPPROTO_UDP || tproto == IPPROTO_TCP) {
-		hp = skb_header_pointer(skb, thoff,
-					sizeof(_hdr), &_hdr);
+		struct udphdr _hdr, *hp;
+
+		hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr);
 		if (hp == NULL)
-			return false;
+			return NULL;
 
 		saddr = &iph->saddr;
 		sport = hp->source;
@@ -341,17 +357,27 @@ socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par)
 		dport = hp->dest;
 
 	} else if (tproto == IPPROTO_ICMPV6) {
+		struct ipv6hdr ipv6_var;
+
 		if (extract_icmp6_fields(skb, thoff, &tproto, &saddr, &daddr,
-					 &sport, &dport))
-			return false;
+					 &sport, &dport, &ipv6_var))
+			return NULL;
 	} else {
-		return false;
+		return NULL;
 	}
 
+	return xt_socket_get_sock_v6(dev_net(skb->dev), tproto, saddr, daddr,
+				     sport, dport, indev);
+}
+
+static bool
+socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo;
+	struct sock *sk = skb->sk;
+
 	if (!sk)
-		sk = xt_socket_get_sock_v6(dev_net(skb->dev), tproto,
-					   saddr, daddr, sport, dport,
-					   par->in);
+		sk = xt_socket_lookup_slow_v6(skb, par->in);
 	if (sk) {
 		bool wildcard;
 		bool transparent = true;
@@ -360,16 +386,14 @@ socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par)
 		 * unless XT_SOCKET_NOWILDCARD is set
 		 */
 		wildcard = (!(info->flags & XT_SOCKET_NOWILDCARD) &&
-			    sk->sk_state != TCP_TIME_WAIT &&
+			    sk_fullsock(sk) &&
 			    ipv6_addr_any(&sk->sk_v6_rcv_saddr));
 
 		/* Ignore non-transparent sockets,
-		   if XT_SOCKET_TRANSPARENT is used */
+		 * if XT_SOCKET_TRANSPARENT is used
+		 */
 		if (info->flags & XT_SOCKET_TRANSPARENT)
-			transparent = ((sk->sk_state != TCP_TIME_WAIT &&
-					inet_sk(sk)->transparent) ||
-				       (sk->sk_state == TCP_TIME_WAIT &&
-					inet_twsk(sk)->tw_transparent));
+			transparent = xt_socket_sk_is_transparent(sk);
 
 		if (sk != skb->sk)
 			sock_gen_put(sk);
@@ -378,13 +402,7 @@ socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par)
 			sk = NULL;
 	}
 
-	pr_debug("proto %hhd %pI6:%hu -> %pI6:%hu "
-		 "(orig %pI6:%hu) sock %p\n",
-		 tproto, saddr, ntohs(sport),
-		 daddr, ntohs(dport),
-		 &iph->daddr, hp ? ntohs(hp->dest) : 0, sk);
-
-	return (sk != NULL);
+	return sk != NULL;
 }
 #endif
 
diff --git a/net/netfilter/xt_string.c b/net/netfilter/xt_string.c
index 5699adb97652..0bc3460319c8 100644
--- a/net/netfilter/xt_string.c
+++ b/net/netfilter/xt_string.c
@@ -26,13 +26,12 @@ static bool
 string_mt(const struct sk_buff *skb, struct xt_action_param *par)
 {
 	const struct xt_string_info *conf = par->matchinfo;
-	struct ts_state state;
 	bool invert;
 
 	invert = conf->u.v1.flags & XT_STRING_FLAG_INVERT;
 
 	return (skb_find_text((struct sk_buff *)skb, conf->from_offset,
-			     conf->to_offset, conf->config, &state)
+			     conf->to_offset, conf->config)
 			     != UINT_MAX) ^ invert;
 }
 
diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c
index c2f2a53a4879..7fd1104ba900 100644
--- a/net/netlabel/netlabel_cipso_v4.c
+++ b/net/netlabel/netlabel_cipso_v4.c
@@ -324,8 +324,7 @@ static int netlbl_cipsov4_add_std(struct genl_info *info,
 	return 0;
 
 add_std_failure:
-	if (doi_def)
-		cipso_v4_doi_free(doi_def);
+	cipso_v4_doi_free(doi_def);
 	return ret_val;
 }
 
@@ -641,7 +640,8 @@ static int netlbl_cipsov4_listall_cb(struct cipso_v4_doi *doi_def, void *arg)
 	if (ret_val != 0)
 		goto listall_cb_failure;
 
-	return genlmsg_end(cb_arg->skb, data);
+	genlmsg_end(cb_arg->skb, data);
+	return 0;
 
 listall_cb_failure:
 	genlmsg_cancel(cb_arg->skb, data);
diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c
index a845cd4cf21e..28cddc85b700 100644
--- a/net/netlabel/netlabel_kapi.c
+++ b/net/netlabel/netlabel_kapi.c
@@ -1065,10 +1065,12 @@ int netlbl_skbuff_getattr(const struct sk_buff *skb,
 			  u16 family,
 			  struct netlbl_lsm_secattr *secattr)
 {
+	unsigned char *ptr;
+
 	switch (family) {
 	case AF_INET:
-		if (CIPSO_V4_OPTEXIST(skb) &&
-		    cipso_v4_skbuff_getattr(skb, secattr) == 0)
+		ptr = cipso_v4_optptr(skb);
+		if (ptr && cipso_v4_getattr(ptr, secattr) == 0)
 			return 0;
 		break;
 #if IS_ENABLED(CONFIG_IPV6)
@@ -1094,7 +1096,7 @@ int netlbl_skbuff_getattr(const struct sk_buff *skb,
  */
 void netlbl_skbuff_err(struct sk_buff *skb, int error, int gateway)
 {
-	if (CIPSO_V4_OPTEXIST(skb))
+	if (cipso_v4_optptr(skb))
 		cipso_v4_error(skb, error, gateway);
 }
 
@@ -1126,11 +1128,14 @@ void netlbl_cache_invalidate(void)
 int netlbl_cache_add(const struct sk_buff *skb,
 		     const struct netlbl_lsm_secattr *secattr)
 {
+	unsigned char *ptr;
+
 	if ((secattr->flags & NETLBL_SECATTR_CACHE) == 0)
 		return -ENOMSG;
 
-	if (CIPSO_V4_OPTEXIST(skb))
-		return cipso_v4_cache_add(skb, secattr);
+	ptr = cipso_v4_optptr(skb);
+	if (ptr)
+		return cipso_v4_cache_add(ptr, secattr);
 
 	return -ENOMSG;
 }
diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c
index e66e977ef2fa..13f777f20995 100644
--- a/net/netlabel/netlabel_mgmt.c
+++ b/net/netlabel/netlabel_mgmt.c
@@ -93,23 +93,20 @@ static int netlbl_mgmt_add_common(struct genl_info *info,
 				  struct netlbl_audit *audit_info)
 {
 	int ret_val = -EINVAL;
-	struct netlbl_dom_map *entry = NULL;
 	struct netlbl_domaddr_map *addrmap = NULL;
 	struct cipso_v4_doi *cipsov4 = NULL;
 	u32 tmp_val;
+	struct netlbl_dom_map *entry = kzalloc(sizeof(*entry), GFP_KERNEL);
 
-	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
-	if (entry == NULL) {
-		ret_val = -ENOMEM;
-		goto add_failure;
-	}
+	if (!entry)
+		return -ENOMEM;
 	entry->def.type = nla_get_u32(info->attrs[NLBL_MGMT_A_PROTOCOL]);
 	if (info->attrs[NLBL_MGMT_A_DOMAIN]) {
 		size_t tmp_size = nla_len(info->attrs[NLBL_MGMT_A_DOMAIN]);
 		entry->domain = kmalloc(tmp_size, GFP_KERNEL);
 		if (entry->domain == NULL) {
 			ret_val = -ENOMEM;
-			goto add_failure;
+			goto add_free_entry;
 		}
 		nla_strlcpy(entry->domain,
 			    info->attrs[NLBL_MGMT_A_DOMAIN], tmp_size);
@@ -125,16 +122,16 @@ static int netlbl_mgmt_add_common(struct genl_info *info,
 		break;
 	case NETLBL_NLTYPE_CIPSOV4:
 		if (!info->attrs[NLBL_MGMT_A_CV4DOI])
-			goto add_failure;
+			goto add_free_domain;
 
 		tmp_val = nla_get_u32(info->attrs[NLBL_MGMT_A_CV4DOI]);
 		cipsov4 = cipso_v4_doi_getdef(tmp_val);
 		if (cipsov4 == NULL)
-			goto add_failure;
+			goto add_free_domain;
 		entry->def.cipso = cipsov4;
 		break;
 	default:
-		goto add_failure;
+		goto add_free_domain;
 	}
 
 	if (info->attrs[NLBL_MGMT_A_IPV4ADDR]) {
@@ -145,7 +142,7 @@ static int netlbl_mgmt_add_common(struct genl_info *info,
 		addrmap = kzalloc(sizeof(*addrmap), GFP_KERNEL);
 		if (addrmap == NULL) {
 			ret_val = -ENOMEM;
-			goto add_failure;
+			goto add_doi_put_def;
 		}
 		INIT_LIST_HEAD(&addrmap->list4);
 		INIT_LIST_HEAD(&addrmap->list6);
@@ -153,12 +150,12 @@ static int netlbl_mgmt_add_common(struct genl_info *info,
 		if (nla_len(info->attrs[NLBL_MGMT_A_IPV4ADDR]) !=
 		    sizeof(struct in_addr)) {
 			ret_val = -EINVAL;
-			goto add_failure;
+			goto add_free_addrmap;
 		}
 		if (nla_len(info->attrs[NLBL_MGMT_A_IPV4MASK]) !=
 		    sizeof(struct in_addr)) {
 			ret_val = -EINVAL;
-			goto add_failure;
+			goto add_free_addrmap;
 		}
 		addr = nla_data(info->attrs[NLBL_MGMT_A_IPV4ADDR]);
 		mask = nla_data(info->attrs[NLBL_MGMT_A_IPV4MASK]);
@@ -166,7 +163,7 @@ static int netlbl_mgmt_add_common(struct genl_info *info,
 		map = kzalloc(sizeof(*map), GFP_KERNEL);
 		if (map == NULL) {
 			ret_val = -ENOMEM;
-			goto add_failure;
+			goto add_free_addrmap;
 		}
 		map->list.addr = addr->s_addr & mask->s_addr;
 		map->list.mask = mask->s_addr;
@@ -178,7 +175,7 @@ static int netlbl_mgmt_add_common(struct genl_info *info,
 		ret_val = netlbl_af4list_add(&map->list, &addrmap->list4);
 		if (ret_val != 0) {
 			kfree(map);
-			goto add_failure;
+			goto add_free_addrmap;
 		}
 
 		entry->def.type = NETLBL_NLTYPE_ADDRSELECT;
@@ -192,7 +189,7 @@ static int netlbl_mgmt_add_common(struct genl_info *info,
 		addrmap = kzalloc(sizeof(*addrmap), GFP_KERNEL);
 		if (addrmap == NULL) {
 			ret_val = -ENOMEM;
-			goto add_failure;
+			goto add_doi_put_def;
 		}
 		INIT_LIST_HEAD(&addrmap->list4);
 		INIT_LIST_HEAD(&addrmap->list6);
@@ -200,12 +197,12 @@ static int netlbl_mgmt_add_common(struct genl_info *info,
 		if (nla_len(info->attrs[NLBL_MGMT_A_IPV6ADDR]) !=
 		    sizeof(struct in6_addr)) {
 			ret_val = -EINVAL;
-			goto add_failure;
+			goto add_free_addrmap;
 		}
 		if (nla_len(info->attrs[NLBL_MGMT_A_IPV6MASK]) !=
 		    sizeof(struct in6_addr)) {
 			ret_val = -EINVAL;
-			goto add_failure;
+			goto add_free_addrmap;
 		}
 		addr = nla_data(info->attrs[NLBL_MGMT_A_IPV6ADDR]);
 		mask = nla_data(info->attrs[NLBL_MGMT_A_IPV6MASK]);
@@ -213,7 +210,7 @@ static int netlbl_mgmt_add_common(struct genl_info *info,
 		map = kzalloc(sizeof(*map), GFP_KERNEL);
 		if (map == NULL) {
 			ret_val = -ENOMEM;
-			goto add_failure;
+			goto add_free_addrmap;
 		}
 		map->list.addr = *addr;
 		map->list.addr.s6_addr32[0] &= mask->s6_addr32[0];
@@ -227,7 +224,7 @@ static int netlbl_mgmt_add_common(struct genl_info *info,
 		ret_val = netlbl_af6list_add(&map->list, &addrmap->list6);
 		if (ret_val != 0) {
 			kfree(map);
-			goto add_failure;
+			goto add_free_addrmap;
 		}
 
 		entry->def.type = NETLBL_NLTYPE_ADDRSELECT;
@@ -237,16 +234,17 @@ static int netlbl_mgmt_add_common(struct genl_info *info,
 
 	ret_val = netlbl_domhsh_add(entry, audit_info);
 	if (ret_val != 0)
-		goto add_failure;
+		goto add_free_addrmap;
 
 	return 0;
 
-add_failure:
-	if (cipsov4)
-		cipso_v4_doi_putdef(cipsov4);
-	if (entry)
-		kfree(entry->domain);
+add_free_addrmap:
 	kfree(addrmap);
+add_doi_put_def:
+	cipso_v4_doi_putdef(cipsov4);
+add_free_domain:
+	kfree(entry->domain);
+add_free_entry:
 	kfree(entry);
 	return ret_val;
 }
@@ -295,15 +293,13 @@ static int netlbl_mgmt_listentry(struct sk_buff *skb,
 				return -ENOMEM;
 
 			addr_struct.s_addr = iter4->addr;
-			ret_val = nla_put(skb, NLBL_MGMT_A_IPV4ADDR,
-					  sizeof(struct in_addr),
-					  &addr_struct);
+			ret_val = nla_put_in_addr(skb, NLBL_MGMT_A_IPV4ADDR,
+						  addr_struct.s_addr);
 			if (ret_val != 0)
 				return ret_val;
 			addr_struct.s_addr = iter4->mask;
-			ret_val = nla_put(skb, NLBL_MGMT_A_IPV4MASK,
-					  sizeof(struct in_addr),
-					  &addr_struct);
+			ret_val = nla_put_in_addr(skb, NLBL_MGMT_A_IPV4MASK,
+						  addr_struct.s_addr);
 			if (ret_val != 0)
 				return ret_val;
 			map4 = netlbl_domhsh_addr4_entry(iter4);
@@ -330,14 +326,12 @@ static int netlbl_mgmt_listentry(struct sk_buff *skb,
 			if (nla_b == NULL)
 				return -ENOMEM;
 
-			ret_val = nla_put(skb, NLBL_MGMT_A_IPV6ADDR,
-					  sizeof(struct in6_addr),
-					  &iter6->addr);
+			ret_val = nla_put_in6_addr(skb, NLBL_MGMT_A_IPV6ADDR,
+						   &iter6->addr);
 			if (ret_val != 0)
 				return ret_val;
-			ret_val = nla_put(skb, NLBL_MGMT_A_IPV6MASK,
-					  sizeof(struct in6_addr),
-					  &iter6->mask);
+			ret_val = nla_put_in6_addr(skb, NLBL_MGMT_A_IPV6MASK,
+						   &iter6->mask);
 			if (ret_val != 0)
 				return ret_val;
 			map6 = netlbl_domhsh_addr6_entry(iter6);
@@ -456,7 +450,8 @@ static int netlbl_mgmt_listall_cb(struct netlbl_dom_map *entry, void *arg)
 		goto listall_cb_failure;
 
 	cb_arg->seq++;
-	return genlmsg_end(cb_arg->skb, data);
+	genlmsg_end(cb_arg->skb, data);
+	return 0;
 
 listall_cb_failure:
 	genlmsg_cancel(cb_arg->skb, data);
@@ -620,7 +615,8 @@ static int netlbl_mgmt_protocols_cb(struct sk_buff *skb,
 	if (ret_val != 0)
 		goto protocols_cb_failure;
 
-	return genlmsg_end(skb, data);
+	genlmsg_end(skb, data);
+	return 0;
 
 protocols_cb_failure:
 	genlmsg_cancel(skb, data);
diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c
index 78a63c18779e..b0380927f05f 100644
--- a/net/netlabel/netlabel_unlabeled.c
+++ b/net/netlabel/netlabel_unlabeled.c
@@ -1117,34 +1117,30 @@ static int netlbl_unlabel_staticlist_gen(u32 cmd,
 		struct in_addr addr_struct;
 
 		addr_struct.s_addr = addr4->list.addr;
-		ret_val = nla_put(cb_arg->skb,
-				  NLBL_UNLABEL_A_IPV4ADDR,
-				  sizeof(struct in_addr),
-				  &addr_struct);
+		ret_val = nla_put_in_addr(cb_arg->skb,
+					  NLBL_UNLABEL_A_IPV4ADDR,
+					  addr_struct.s_addr);
 		if (ret_val != 0)
 			goto list_cb_failure;
 
 		addr_struct.s_addr = addr4->list.mask;
-		ret_val = nla_put(cb_arg->skb,
-				  NLBL_UNLABEL_A_IPV4MASK,
-				  sizeof(struct in_addr),
-				  &addr_struct);
+		ret_val = nla_put_in_addr(cb_arg->skb,
+					  NLBL_UNLABEL_A_IPV4MASK,
+					  addr_struct.s_addr);
 		if (ret_val != 0)
 			goto list_cb_failure;
 
 		secid = addr4->secid;
 	} else {
-		ret_val = nla_put(cb_arg->skb,
-				  NLBL_UNLABEL_A_IPV6ADDR,
-				  sizeof(struct in6_addr),
-				  &addr6->list.addr);
+		ret_val = nla_put_in6_addr(cb_arg->skb,
+					   NLBL_UNLABEL_A_IPV6ADDR,
+					   &addr6->list.addr);
 		if (ret_val != 0)
 			goto list_cb_failure;
 
-		ret_val = nla_put(cb_arg->skb,
-				  NLBL_UNLABEL_A_IPV6MASK,
-				  sizeof(struct in6_addr),
-				  &addr6->list.mask);
+		ret_val = nla_put_in6_addr(cb_arg->skb,
+					   NLBL_UNLABEL_A_IPV6MASK,
+					   &addr6->list.mask);
 		if (ret_val != 0)
 			goto list_cb_failure;
 
@@ -1163,7 +1159,8 @@ static int netlbl_unlabel_staticlist_gen(u32 cmd,
 		goto list_cb_failure;
 
 	cb_arg->seq++;
-	return genlmsg_end(cb_arg->skb, data);
+	genlmsg_end(cb_arg->skb, data);
+	return 0;
 
 list_cb_failure:
 	genlmsg_cancel(cb_arg->skb, data);
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 0007b8180397..bf6e76643f78 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -61,6 +61,7 @@
 #include <linux/rhashtable.h>
 #include <asm/cacheflush.h>
 #include <linux/hash.h>
+#include <linux/genetlink.h>
 
 #include <net/net_namespace.h>
 #include <net/sock.h>
@@ -88,7 +89,7 @@ static inline int netlink_is_kernel(struct sock *sk)
 	return nlk_sk(sk)->flags & NETLINK_KERNEL_SOCKET;
 }
 
-struct netlink_table *nl_table;
+struct netlink_table *nl_table __read_mostly;
 EXPORT_SYMBOL_GPL(nl_table);
 
 static DECLARE_WAIT_QUEUE_HEAD(nl_table_wait);
@@ -97,12 +98,12 @@ static int netlink_dump(struct sock *sk);
 static void netlink_skb_destructor(struct sk_buff *skb);
 
 /* nl_table locking explained:
- * Lookup and traversal are protected with nl_sk_hash_lock or nl_table_lock
- * combined with an RCU read-side lock. Insertion and removal are protected
- * with nl_sk_hash_lock while using RCU list modification primitives and may
- * run in parallel to nl_table_lock protected lookups. Destruction of the
- * Netlink socket may only occur *after* nl_table_lock has been acquired
- * either during or after the socket has been removed from the list.
+ * Lookup and traversal are protected with an RCU read-side lock. Insertion
+ * and removal are protected with per bucket lock while using RCU list
+ * modification primitives and may run in parallel to RCU protected lookups.
+ * Destruction of the Netlink socket may only occur *after* nl_table_lock has
+ * been acquired * either during or after the socket has been removed from
+ * the list and after an RCU grace period.
  */
 DEFINE_RWLOCK(nl_table_lock);
 EXPORT_SYMBOL_GPL(nl_table_lock);
@@ -110,24 +111,13 @@ static atomic_t nl_table_users = ATOMIC_INIT(0);
 
 #define nl_deref_protected(X) rcu_dereference_protected(X, lockdep_is_held(&nl_table_lock));
 
-/* Protects netlink socket hash table mutations */
-DEFINE_MUTEX(nl_sk_hash_lock);
-EXPORT_SYMBOL_GPL(nl_sk_hash_lock);
-
-static int lockdep_nl_sk_hash_is_held(void)
-{
-#ifdef CONFIG_LOCKDEP
-	if (debug_locks)
-		return lockdep_is_held(&nl_sk_hash_lock) || lockdep_is_held(&nl_table_lock);
-#endif
-	return 1;
-}
-
 static ATOMIC_NOTIFIER_HEAD(netlink_chain);
 
 static DEFINE_SPINLOCK(netlink_tap_lock);
 static struct list_head netlink_tap_all __read_mostly;
 
+static const struct rhashtable_params netlink_rhashtable_params;
+
 static inline u32 netlink_group_mask(u32 group)
 {
 	return group ? 1 << (group - 1) : 0;
@@ -142,8 +132,7 @@ int netlink_add_tap(struct netlink_tap *nt)
 	list_add_rcu(&nt->list, &netlink_tap_all);
 	spin_unlock(&netlink_tap_lock);
 
-	if (nt->module)
-		__module_get(nt->module);
+	__module_get(nt->module);
 
 	return 0;
 }
@@ -526,14 +515,14 @@ out:
 	return err;
 }
 
-static void netlink_frame_flush_dcache(const struct nl_mmap_hdr *hdr)
+static void netlink_frame_flush_dcache(const struct nl_mmap_hdr *hdr, unsigned int nm_len)
 {
 #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1
 	struct page *p_start, *p_end;
 
 	/* First page is flushed through netlink_{get,set}_status */
 	p_start = pgvec_to_page(hdr + PAGE_SIZE);
-	p_end   = pgvec_to_page((void *)hdr + NL_MMAP_HDRLEN + hdr->nm_len - 1);
+	p_end   = pgvec_to_page((void *)hdr + NL_MMAP_HDRLEN + nm_len - 1);
 	while (p_start <= p_end) {
 		flush_dcache_page(p_start);
 		p_start++;
@@ -551,9 +540,9 @@ static enum nl_mmap_status netlink_get_status(const struct nl_mmap_hdr *hdr)
 static void netlink_set_status(struct nl_mmap_hdr *hdr,
 			       enum nl_mmap_status status)
 {
+	smp_mb();
 	hdr->nm_status = status;
 	flush_dcache_page(pgvec_to_page(hdr));
-	smp_wmb();
 }
 
 static struct nl_mmap_hdr *
@@ -708,31 +697,23 @@ static void netlink_ring_setup_skb(struct sk_buff *skb, struct sock *sk,
 
 static int netlink_mmap_sendmsg(struct sock *sk, struct msghdr *msg,
 				u32 dst_portid, u32 dst_group,
-				struct sock_iocb *siocb)
+				struct scm_cookie *scm)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
 	struct netlink_ring *ring;
 	struct nl_mmap_hdr *hdr;
 	struct sk_buff *skb;
 	unsigned int maxlen;
-	bool excl = true;
 	int err = 0, len = 0;
 
-	/* Netlink messages are validated by the receiver before processing.
-	 * In order to avoid userspace changing the contents of the message
-	 * after validation, the socket and the ring may only be used by a
-	 * single process, otherwise we fall back to copying.
-	 */
-	if (atomic_long_read(&sk->sk_socket->file->f_count) > 1 ||
-	    atomic_read(&nlk->mapped) > 1)
-		excl = false;
-
 	mutex_lock(&nlk->pg_vec_lock);
 
 	ring   = &nlk->tx_ring;
 	maxlen = ring->frame_size - NL_MMAP_HDRLEN;
 
 	do {
+		unsigned int nm_len;
+
 		hdr = netlink_current_frame(ring, NL_MMAP_STATUS_VALID);
 		if (hdr == NULL) {
 			if (!(msg->msg_flags & MSG_DONTWAIT) &&
@@ -740,41 +721,29 @@ static int netlink_mmap_sendmsg(struct sock *sk, struct msghdr *msg,
 				schedule();
 			continue;
 		}
-		if (hdr->nm_len > maxlen) {
+
+		nm_len = ACCESS_ONCE(hdr->nm_len);
+		if (nm_len > maxlen) {
 			err = -EINVAL;
 			goto out;
 		}
 
-		netlink_frame_flush_dcache(hdr);
+		netlink_frame_flush_dcache(hdr, nm_len);
 
-		if (likely(dst_portid == 0 && dst_group == 0 && excl)) {
-			skb = alloc_skb_head(GFP_KERNEL);
-			if (skb == NULL) {
-				err = -ENOBUFS;
-				goto out;
-			}
-			sock_hold(sk);
-			netlink_ring_setup_skb(skb, sk, ring, hdr);
-			NETLINK_CB(skb).flags |= NETLINK_SKB_TX;
-			__skb_put(skb, hdr->nm_len);
-			netlink_set_status(hdr, NL_MMAP_STATUS_RESERVED);
-			atomic_inc(&ring->pending);
-		} else {
-			skb = alloc_skb(hdr->nm_len, GFP_KERNEL);
-			if (skb == NULL) {
-				err = -ENOBUFS;
-				goto out;
-			}
-			__skb_put(skb, hdr->nm_len);
-			memcpy(skb->data, (void *)hdr + NL_MMAP_HDRLEN, hdr->nm_len);
-			netlink_set_status(hdr, NL_MMAP_STATUS_UNUSED);
+		skb = alloc_skb(nm_len, GFP_KERNEL);
+		if (skb == NULL) {
+			err = -ENOBUFS;
+			goto out;
 		}
+		__skb_put(skb, nm_len);
+		memcpy(skb->data, (void *)hdr + NL_MMAP_HDRLEN, nm_len);
+		netlink_set_status(hdr, NL_MMAP_STATUS_UNUSED);
 
 		netlink_increment_head(ring);
 
 		NETLINK_CB(skb).portid	  = nlk->portid;
 		NETLINK_CB(skb).dst_group = dst_group;
-		NETLINK_CB(skb).creds	  = siocb->scm->creds;
+		NETLINK_CB(skb).creds	  = scm->creds;
 
 		err = security_netlink_send(sk, skb);
 		if (err) {
@@ -814,7 +783,7 @@ static void netlink_queue_mmaped_skb(struct sock *sk, struct sk_buff *skb)
 	hdr->nm_pid	= NETLINK_CB(skb).creds.pid;
 	hdr->nm_uid	= from_kuid(sk_user_ns(sk), NETLINK_CB(skb).creds.uid);
 	hdr->nm_gid	= from_kgid(sk_user_ns(sk), NETLINK_CB(skb).creds.gid);
-	netlink_frame_flush_dcache(hdr);
+	netlink_frame_flush_dcache(hdr, hdr->nm_len);
 	netlink_set_status(hdr, NL_MMAP_STATUS_VALID);
 
 	NETLINK_CB(skb).flags |= NETLINK_SKB_DELIVERED;
@@ -853,7 +822,7 @@ static void netlink_ring_set_copied(struct sock *sk, struct sk_buff *skb)
 #define netlink_tx_is_mmaped(sk)	false
 #define netlink_mmap			sock_no_mmap
 #define netlink_poll			datagram_poll
-#define netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group, siocb)	0
+#define netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group, scm)	0
 #endif /* CONFIG_NETLINK_MMAP */
 
 static void netlink_skb_destructor(struct sk_buff *skb)
@@ -1003,32 +972,50 @@ netlink_unlock_table(void)
 
 struct netlink_compare_arg
 {
-	struct net *net;
+	possible_net_t pnet;
 	u32 portid;
 };
 
-static bool netlink_compare(void *ptr, void *arg)
+/* Doing sizeof directly may yield 4 extra bytes on 64-bit. */
+#define netlink_compare_arg_len \
+	(offsetof(struct netlink_compare_arg, portid) + sizeof(u32))
+
+static inline int netlink_compare(struct rhashtable_compare_arg *arg,
+				  const void *ptr)
 {
-	struct netlink_compare_arg *x = arg;
-	struct sock *sk = ptr;
+	const struct netlink_compare_arg *x = arg->key;
+	const struct netlink_sock *nlk = ptr;
 
-	return nlk_sk(sk)->portid == x->portid &&
-	       net_eq(sock_net(sk), x->net);
+	return nlk->portid != x->portid ||
+	       !net_eq(sock_net(&nlk->sk), read_pnet(&x->pnet));
+}
+
+static void netlink_compare_arg_init(struct netlink_compare_arg *arg,
+				     struct net *net, u32 portid)
+{
+	memset(arg, 0, sizeof(*arg));
+	write_pnet(&arg->pnet, net);
+	arg->portid = portid;
 }
 
 static struct sock *__netlink_lookup(struct netlink_table *table, u32 portid,
 				     struct net *net)
 {
-	struct netlink_compare_arg arg = {
-		.net = net,
-		.portid = portid,
-	};
-	u32 hash;
+	struct netlink_compare_arg arg;
+
+	netlink_compare_arg_init(&arg, net, portid);
+	return rhashtable_lookup_fast(&table->hash, &arg,
+				      netlink_rhashtable_params);
+}
 
-	hash = rhashtable_hashfn(&table->hash, &portid, sizeof(portid));
+static int __netlink_insert(struct netlink_table *table, struct sock *sk)
+{
+	struct netlink_compare_arg arg;
 
-	return rhashtable_lookup_compare(&table->hash, hash,
-					 &netlink_compare, &arg);
+	netlink_compare_arg_init(&arg, sock_net(sk), nlk_sk(sk)->portid);
+	return rhashtable_lookup_insert_key(&table->hash, &arg,
+					    &nlk_sk(sk)->node,
+					    netlink_rhashtable_params);
 }
 
 static struct sock *netlink_lookup(struct net *net, int protocol, u32 portid)
@@ -1036,13 +1023,11 @@ static struct sock *netlink_lookup(struct net *net, int protocol, u32 portid)
 	struct netlink_table *table = &nl_table[protocol];
 	struct sock *sk;
 
-	read_lock(&nl_table_lock);
 	rcu_read_lock();
 	sk = __netlink_lookup(table, portid, net);
 	if (sk)
 		sock_hold(sk);
 	rcu_read_unlock();
-	read_unlock(&nl_table_lock);
 
 	return sk;
 }
@@ -1073,29 +1058,35 @@ netlink_update_listeners(struct sock *sk)
 	 * makes sure updates are visible before bind or setsockopt return. */
 }
 
-static int netlink_insert(struct sock *sk, struct net *net, u32 portid)
+static int netlink_insert(struct sock *sk, u32 portid)
 {
 	struct netlink_table *table = &nl_table[sk->sk_protocol];
-	int err = -EADDRINUSE;
+	int err;
 
-	mutex_lock(&nl_sk_hash_lock);
-	if (__netlink_lookup(table, portid, net))
-		goto err;
+	lock_sock(sk);
 
 	err = -EBUSY;
 	if (nlk_sk(sk)->portid)
 		goto err;
 
 	err = -ENOMEM;
-	if (BITS_PER_LONG > 32 && unlikely(table->hash.nelems >= UINT_MAX))
+	if (BITS_PER_LONG > 32 &&
+	    unlikely(atomic_read(&table->hash.nelems) >= UINT_MAX))
 		goto err;
 
 	nlk_sk(sk)->portid = portid;
 	sock_hold(sk);
-	rhashtable_insert(&table->hash, &nlk_sk(sk)->node, GFP_KERNEL);
-	err = 0;
+
+	err = __netlink_insert(table, sk);
+	if (err) {
+		if (err == -EEXIST)
+			err = -EADDRINUSE;
+		nlk_sk(sk)->portid = 0;
+		sock_put(sk);
+	}
+
 err:
-	mutex_unlock(&nl_sk_hash_lock);
+	release_sock(sk);
 	return err;
 }
 
@@ -1103,17 +1094,20 @@ static void netlink_remove(struct sock *sk)
 {
 	struct netlink_table *table;
 
-	mutex_lock(&nl_sk_hash_lock);
 	table = &nl_table[sk->sk_protocol];
-	if (rhashtable_remove(&table->hash, &nlk_sk(sk)->node, GFP_KERNEL)) {
+	if (!rhashtable_remove_fast(&table->hash, &nlk_sk(sk)->node,
+				    netlink_rhashtable_params)) {
 		WARN_ON(atomic_read(&sk->sk_refcnt) == 1);
 		__sock_put(sk);
 	}
-	mutex_unlock(&nl_sk_hash_lock);
 
 	netlink_table_grab();
-	if (nlk_sk(sk)->subscriptions)
+	if (nlk_sk(sk)->subscriptions) {
 		__sk_del_bind_node(sk);
+		netlink_update_listeners(sk);
+	}
+	if (sk->sk_protocol == NETLINK_GENERIC)
+		atomic_inc(&genl_sk_destructing_cnt);
 	netlink_table_ungrab();
 }
 
@@ -1160,8 +1154,8 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 	struct module *module = NULL;
 	struct mutex *cb_mutex;
 	struct netlink_sock *nlk;
-	int (*bind)(int group);
-	void (*unbind)(int group);
+	int (*bind)(struct net *net, int group);
+	void (*unbind)(struct net *net, int group);
 	int err = 0;
 
 	sock->state = SS_UNCONNECTED;
@@ -1213,6 +1207,13 @@ out_module:
 	goto out;
 }
 
+static void deferred_put_nlk_sk(struct rcu_head *head)
+{
+	struct netlink_sock *nlk = container_of(head, struct netlink_sock, rcu);
+
+	sock_put(&nlk->sk);
+}
+
 static int netlink_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
@@ -1230,6 +1231,20 @@ static int netlink_release(struct socket *sock)
 	 * will be purged.
 	 */
 
+	/* must not acquire netlink_table_lock in any way again before unbind
+	 * and notifying genetlink is done as otherwise it might deadlock
+	 */
+	if (nlk->netlink_unbind) {
+		int i;
+
+		for (i = 0; i < nlk->ngroups; i++)
+			if (test_bit(i, nlk->groups))
+				nlk->netlink_unbind(sock_net(sk), i + 1);
+	}
+	if (sk->sk_protocol == NETLINK_GENERIC &&
+	    atomic_dec_return(&genl_sk_destructing_cnt) == 0)
+		wake_up(&genl_sk_destructing_waitq);
+
 	sock->sk = NULL;
 	wake_up_interruptible_all(&nlk->wait);
 
@@ -1247,8 +1262,8 @@ static int netlink_release(struct socket *sock)
 
 	module_put(nlk->module);
 
-	netlink_table_grab();
 	if (netlink_is_kernel(sk)) {
+		netlink_table_grab();
 		BUG_ON(nl_table[sk->sk_protocol].registered == 0);
 		if (--nl_table[sk->sk_protocol].registered == 0) {
 			struct listeners *old;
@@ -1262,10 +1277,8 @@ static int netlink_release(struct socket *sock)
 			nl_table[sk->sk_protocol].flags = 0;
 			nl_table[sk->sk_protocol].registered = 0;
 		}
-	} else if (nlk->subscriptions) {
-		netlink_update_listeners(sk);
+		netlink_table_ungrab();
 	}
-	netlink_table_ungrab();
 
 	kfree(nlk->groups);
 	nlk->groups = NULL;
@@ -1273,7 +1286,7 @@ static int netlink_release(struct socket *sock)
 	local_bh_disable();
 	sock_prot_inuse_add(sock_net(sk), &netlink_proto, -1);
 	local_bh_enable();
-	sock_put(sk);
+	call_rcu(&nlk->rcu, deferred_put_nlk_sk);
 	return 0;
 }
 
@@ -1288,7 +1301,6 @@ static int netlink_autobind(struct socket *sock)
 
 retry:
 	cond_resched();
-	netlink_table_grab();
 	rcu_read_lock();
 	if (__netlink_lookup(table, portid, net)) {
 		/* Bind collision, search negative portid values. */
@@ -1296,13 +1308,11 @@ retry:
 		if (rover > -4097)
 			rover = -4097;
 		rcu_read_unlock();
-		netlink_table_ungrab();
 		goto retry;
 	}
 	rcu_read_unlock();
-	netlink_table_ungrab();
 
-	err = netlink_insert(sk, net, portid);
+	err = netlink_insert(sk, portid);
 	if (err == -EADDRINUSE)
 		goto retry;
 
@@ -1431,9 +1441,10 @@ static int netlink_realloc_groups(struct sock *sk)
 	return err;
 }
 
-static void netlink_unbind(int group, long unsigned int groups,
-			   struct netlink_sock *nlk)
+static void netlink_undo_bind(int group, long unsigned int groups,
+			      struct sock *sk)
 {
+	struct netlink_sock *nlk = nlk_sk(sk);
 	int undo;
 
 	if (!nlk->netlink_unbind)
@@ -1441,7 +1452,7 @@ static void netlink_unbind(int group, long unsigned int groups,
 
 	for (undo = 0; undo < group; undo++)
 		if (test_bit(undo, &groups))
-			nlk->netlink_unbind(undo);
+			nlk->netlink_unbind(sock_net(sk), undo + 1);
 }
 
 static int netlink_bind(struct socket *sock, struct sockaddr *addr,
@@ -1479,20 +1490,20 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 		for (group = 0; group < nlk->ngroups; group++) {
 			if (!test_bit(group, &groups))
 				continue;
-			err = nlk->netlink_bind(group);
+			err = nlk->netlink_bind(net, group + 1);
 			if (!err)
 				continue;
-			netlink_unbind(group, groups, nlk);
+			netlink_undo_bind(group, groups, sk);
 			return err;
 		}
 	}
 
 	if (!nlk->portid) {
 		err = nladdr->nl_pid ?
-			netlink_insert(sk, net, nladdr->nl_pid) :
+			netlink_insert(sk, nladdr->nl_pid) :
 			netlink_autobind(sock);
 		if (err) {
-			netlink_unbind(nlk->ngroups, groups, nlk);
+			netlink_undo_bind(nlk->ngroups, groups, sk);
 			return err;
 		}
 	}
@@ -1619,13 +1630,11 @@ static struct sk_buff *netlink_alloc_large_skb(unsigned int size,
 	if (data == NULL)
 		return NULL;
 
-	skb = build_skb(data, size);
+	skb = __build_skb(data, size);
 	if (skb == NULL)
 		vfree(data);
-	else {
-		skb->head_frag = 0;
+	else
 		skb->destructor = netlink_skb_destructor;
-	}
 
 	return skb;
 }
@@ -2143,7 +2152,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 		if (!val || val - 1 >= nlk->ngroups)
 			return -EINVAL;
 		if (optname == NETLINK_ADD_MEMBERSHIP && nlk->netlink_bind) {
-			err = nlk->netlink_bind(val);
+			err = nlk->netlink_bind(sock_net(sk), val);
 			if (err)
 				return err;
 		}
@@ -2152,7 +2161,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 					 optname == NETLINK_ADD_MEMBERSHIP);
 		netlink_table_ungrab();
 		if (optname == NETLINK_DROP_MEMBERSHIP && nlk->netlink_unbind)
-			nlk->netlink_unbind(val);
+			nlk->netlink_unbind(sock_net(sk), val);
 
 		err = 0;
 		break;
@@ -2259,10 +2268,8 @@ static void netlink_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb)
 	put_cmsg(msg, SOL_NETLINK, NETLINK_PKTINFO, sizeof(info), &info);
 }
 
-static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
-			   struct msghdr *msg, size_t len)
+static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 {
-	struct sock_iocb *siocb = kiocb_to_siocb(kiocb);
 	struct sock *sk = sock->sk;
 	struct netlink_sock *nlk = nlk_sk(sk);
 	DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name);
@@ -2276,10 +2283,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	if (msg->msg_flags&MSG_OOB)
 		return -EOPNOTSUPP;
 
-	if (NULL == siocb->scm)
-		siocb->scm = &scm;
-
-	err = scm_send(sock, msg, siocb->scm, true);
+	err = scm_send(sock, msg, &scm, true);
 	if (err < 0)
 		return err;
 
@@ -2305,10 +2309,15 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 			goto out;
 	}
 
+	/* It's a really convoluted way for userland to ask for mmaped
+	 * sendmsg(), but that's what we've got...
+	 */
 	if (netlink_tx_is_mmaped(sk) &&
-	    msg->msg_iov->iov_base == NULL) {
+	    msg->msg_iter.type == ITER_IOVEC &&
+	    msg->msg_iter.nr_segs == 1 &&
+	    msg->msg_iter.iov->iov_base == NULL) {
 		err = netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group,
-					   siocb);
+					   &scm);
 		goto out;
 	}
 
@@ -2322,11 +2331,11 @@ 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).creds	= scm.creds;
 	NETLINK_CB(skb).flags	= netlink_skb_flags;
 
 	err = -EFAULT;
-	if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) {
+	if (memcpy_from_msg(skb_put(skb, len), msg, len)) {
 		kfree_skb(skb);
 		goto out;
 	}
@@ -2344,15 +2353,13 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	err = netlink_unicast(sk, skb, dst_portid, msg->msg_flags&MSG_DONTWAIT);
 
 out:
-	scm_destroy(siocb->scm);
+	scm_destroy(&scm);
 	return err;
 }
 
-static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
-			   struct msghdr *msg, size_t len,
+static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 			   int flags)
 {
-	struct sock_iocb *siocb = kiocb_to_siocb(kiocb);
 	struct scm_cookie scm;
 	struct sock *sk = sock->sk;
 	struct netlink_sock *nlk = nlk_sk(sk);
@@ -2401,7 +2408,7 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
 	}
 
 	skb_reset_transport_header(data_skb);
-	err = skb_copy_datagram_iovec(data_skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(data_skb, 0, msg, copied);
 
 	if (msg->msg_name) {
 		DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name);
@@ -2415,11 +2422,8 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
 	if (nlk->flags & NETLINK_RECV_PKTINFO)
 		netlink_cmsg_recv_pktinfo(msg, skb);
 
-	if (NULL == siocb->scm) {
-		memset(&scm, 0, sizeof(scm));
-		siocb->scm = &scm;
-	}
-	siocb->scm->creds = *NETLINK_CREDS(skb);
+	memset(&scm, 0, sizeof(scm));
+	scm.creds = *NETLINK_CREDS(skb);
 	if (flags & MSG_TRUNC)
 		copied = data_skb->len;
 
@@ -2434,7 +2438,7 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
 		}
 	}
 
-	scm_recv(sock, msg, siocb->scm, flags);
+	scm_recv(sock, msg, &scm, flags);
 out:
 	netlink_rcv_wake(sk);
 	return err ? : copied;
@@ -2495,7 +2499,7 @@ __netlink_kernel_create(struct net *net, int unit, struct module *module,
 	if (cfg && cfg->input)
 		nlk_sk(sk)->netlink_rcv = cfg->input;
 
-	if (netlink_insert(sk, net, 0))
+	if (netlink_insert(sk, 0))
 		goto out_sock_release;
 
 	nlk = nlk_sk(sk);
@@ -2897,97 +2901,97 @@ EXPORT_SYMBOL(nlmsg_notify);
 #ifdef CONFIG_PROC_FS
 struct nl_seq_iter {
 	struct seq_net_private p;
+	struct rhashtable_iter hti;
 	int link;
-	int hash_idx;
 };
 
-static struct sock *netlink_seq_socket_idx(struct seq_file *seq, loff_t pos)
+static int netlink_walk_start(struct nl_seq_iter *iter)
 {
-	struct nl_seq_iter *iter = seq->private;
-	int i, j;
-	struct netlink_sock *nlk;
-	struct sock *s;
-	loff_t off = 0;
-
-	for (i = 0; i < MAX_LINKS; i++) {
-		struct rhashtable *ht = &nl_table[i].hash;
-		const struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht);
-
-		for (j = 0; j < tbl->size; j++) {
-			rht_for_each_entry_rcu(nlk, tbl->buckets[j], node) {
-				s = (struct sock *)nlk;
+	int err;
 
-				if (sock_net(s) != seq_file_net(seq))
-					continue;
-				if (off == pos) {
-					iter->link = i;
-					iter->hash_idx = j;
-					return s;
-				}
-				++off;
-			}
-		}
+	err = rhashtable_walk_init(&nl_table[iter->link].hash, &iter->hti);
+	if (err) {
+		iter->link = MAX_LINKS;
+		return err;
 	}
-	return NULL;
+
+	err = rhashtable_walk_start(&iter->hti);
+	return err == -EAGAIN ? 0 : err;
 }
 
-static void *netlink_seq_start(struct seq_file *seq, loff_t *pos)
-	__acquires(nl_table_lock) __acquires(RCU)
+static void netlink_walk_stop(struct nl_seq_iter *iter)
 {
-	read_lock(&nl_table_lock);
-	rcu_read_lock();
-	return *pos ? netlink_seq_socket_idx(seq, *pos - 1) : SEQ_START_TOKEN;
+	rhashtable_walk_stop(&iter->hti);
+	rhashtable_walk_exit(&iter->hti);
 }
 
-static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+static void *__netlink_seq_next(struct seq_file *seq)
 {
-	struct rhashtable *ht;
+	struct nl_seq_iter *iter = seq->private;
 	struct netlink_sock *nlk;
-	struct nl_seq_iter *iter;
-	struct net *net;
-	int i, j;
 
-	++*pos;
+	do {
+		for (;;) {
+			int err;
 
-	if (v == SEQ_START_TOKEN)
-		return netlink_seq_socket_idx(seq, 0);
+			nlk = rhashtable_walk_next(&iter->hti);
 
-	net = seq_file_net(seq);
-	iter = seq->private;
-	nlk = v;
+			if (IS_ERR(nlk)) {
+				if (PTR_ERR(nlk) == -EAGAIN)
+					continue;
 
-	i = iter->link;
-	ht = &nl_table[i].hash;
-	rht_for_each_entry(nlk, nlk->node.next, ht, node)
-		if (net_eq(sock_net((struct sock *)nlk), net))
-			return nlk;
+				return nlk;
+			}
 
-	j = iter->hash_idx + 1;
+			if (nlk)
+				break;
 
-	do {
-		const struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht);
-
-		for (; j < tbl->size; j++) {
-			rht_for_each_entry(nlk, tbl->buckets[j], ht, node) {
-				if (net_eq(sock_net((struct sock *)nlk), net)) {
-					iter->link = i;
-					iter->hash_idx = j;
-					return nlk;
-				}
-			}
+			netlink_walk_stop(iter);
+			if (++iter->link >= MAX_LINKS)
+				return NULL;
+
+			err = netlink_walk_start(iter);
+			if (err)
+				return ERR_PTR(err);
 		}
+	} while (sock_net(&nlk->sk) != seq_file_net(seq));
 
-		j = 0;
-	} while (++i < MAX_LINKS);
+	return nlk;
+}
 
-	return NULL;
+static void *netlink_seq_start(struct seq_file *seq, loff_t *posp)
+{
+	struct nl_seq_iter *iter = seq->private;
+	void *obj = SEQ_START_TOKEN;
+	loff_t pos;
+	int err;
+
+	iter->link = 0;
+
+	err = netlink_walk_start(iter);
+	if (err)
+		return ERR_PTR(err);
+
+	for (pos = *posp; pos && obj && !IS_ERR(obj); pos--)
+		obj = __netlink_seq_next(seq);
+
+	return obj;
+}
+
+static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	++*pos;
+	return __netlink_seq_next(seq);
 }
 
 static void netlink_seq_stop(struct seq_file *seq, void *v)
-	__releases(RCU) __releases(nl_table_lock)
 {
-	rcu_read_unlock();
-	read_unlock(&nl_table_lock);
+	struct nl_seq_iter *iter = seq->private;
+
+	if (iter->link >= MAX_LINKS)
+		return;
+
+	netlink_walk_stop(iter);
 }
 
 
@@ -3122,20 +3126,27 @@ static struct pernet_operations __net_initdata netlink_net_ops = {
 	.exit = netlink_net_exit,
 };
 
+static inline u32 netlink_hash(const void *data, u32 len, u32 seed)
+{
+	const struct netlink_sock *nlk = data;
+	struct netlink_compare_arg arg;
+
+	netlink_compare_arg_init(&arg, sock_net(&nlk->sk), nlk->portid);
+	return jhash2((u32 *)&arg, netlink_compare_arg_len / sizeof(u32), seed);
+}
+
+static const struct rhashtable_params netlink_rhashtable_params = {
+	.head_offset = offsetof(struct netlink_sock, node),
+	.key_len = netlink_compare_arg_len,
+	.obj_hashfn = netlink_hash,
+	.obj_cmpfn = netlink_compare,
+	.automatic_shrinking = true,
+};
+
 static int __init netlink_proto_init(void)
 {
 	int i;
 	int err = proto_register(&netlink_proto, 0);
-	struct rhashtable_params ht_params = {
-		.head_offset = offsetof(struct netlink_sock, node),
-		.key_offset = offsetof(struct netlink_sock, portid),
-		.key_len = sizeof(u32), /* portid */
-		.hashfn = arch_fast_hash,
-		.max_shift = 16, /* 64K */
-		.grow_decision = rht_grow_above_75,
-		.shrink_decision = rht_shrink_below_30,
-		.mutex_is_held = lockdep_nl_sk_hash_is_held,
-	};
 
 	if (err != 0)
 		goto out;
@@ -3147,7 +3158,8 @@ static int __init netlink_proto_init(void)
 		goto panic;
 
 	for (i = 0; i < MAX_LINKS; i++) {
-		if (rhashtable_init(&nl_table[i].hash, &ht_params) < 0) {
+		if (rhashtable_init(&nl_table[i].hash,
+				    &netlink_rhashtable_params) < 0) {
 			while (--i > 0)
 				rhashtable_destroy(&nl_table[i].hash);
 			kfree(nl_table);
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index b20a1731759b..89008405d6b4 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -2,6 +2,7 @@
 #define _AF_NETLINK_H
 
 #include <linux/rhashtable.h>
+#include <linux/atomic.h>
 #include <net/sock.h>
 
 #define NLGRPSZ(x)	(ALIGN(x, sizeof(unsigned long) * 8) / 8)
@@ -39,8 +40,8 @@ struct netlink_sock {
 	struct mutex		*cb_mutex;
 	struct mutex		cb_def_mutex;
 	void			(*netlink_rcv)(struct sk_buff *skb);
-	int			(*netlink_bind)(int group);
-	void			(*netlink_unbind)(int group);
+	int			(*netlink_bind)(struct net *net, int group);
+	void			(*netlink_unbind)(struct net *net, int group);
 	struct module		*module;
 #ifdef CONFIG_NETLINK_MMAP
 	struct mutex		pg_vec_lock;
@@ -50,6 +51,7 @@ struct netlink_sock {
 #endif /* CONFIG_NETLINK_MMAP */
 
 	struct rhash_head	node;
+	struct rcu_head		rcu;
 };
 
 static inline struct netlink_sock *nlk_sk(struct sock *sk)
@@ -65,14 +67,13 @@ struct netlink_table {
 	unsigned int		groups;
 	struct mutex		*cb_mutex;
 	struct module		*module;
-	int			(*bind)(int group);
-	void			(*unbind)(int group);
+	int			(*bind)(struct net *net, int group);
+	void			(*unbind)(struct net *net, int group);
 	bool			(*compare)(struct net *net, struct sock *sock);
 	int			registered;
 };
 
 extern struct netlink_table *nl_table;
 extern rwlock_t nl_table_lock;
-extern struct mutex nl_sk_hash_lock;
 
 #endif
diff --git a/net/netlink/diag.c b/net/netlink/diag.c
index de8c74a3c061..3ee63a3cff30 100644
--- a/net/netlink/diag.c
+++ b/net/netlink/diag.c
@@ -91,7 +91,8 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
 	    sk_diag_put_rings_cfg(sk, skb))
 		goto out_nlmsg_trim;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 out_nlmsg_trim:
 	nlmsg_cancel(skb, nlh);
@@ -103,7 +104,7 @@ static int __netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
 {
 	struct netlink_table *tbl = &nl_table[protocol];
 	struct rhashtable *ht = &tbl->hash;
-	const struct bucket_table *htbl = rht_dereference(ht->tbl, ht);
+	const struct bucket_table *htbl = rht_dereference_rcu(ht->tbl, ht);
 	struct net *net = sock_net(skb->sk);
 	struct netlink_diag_req *req;
 	struct netlink_sock *nlsk;
@@ -113,7 +114,9 @@ static int __netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
 	req = nlmsg_data(cb->nlh);
 
 	for (i = 0; i < htbl->size; i++) {
-		rht_for_each_entry(nlsk, htbl->buckets[i], ht, node) {
+		struct rhash_head *pos;
+
+		rht_for_each_entry_rcu(nlsk, pos, htbl, i, node) {
 			sk = (struct sock *)nlsk;
 
 			if (!net_eq(sock_net(sk), net))
@@ -170,7 +173,7 @@ static int netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
 
 	req = nlmsg_data(cb->nlh);
 
-	mutex_lock(&nl_sk_hash_lock);
+	rcu_read_lock();
 	read_lock(&nl_table_lock);
 
 	if (req->sdiag_protocol == NDIAG_PROTO_ALL) {
@@ -184,7 +187,7 @@ static int netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	} else {
 		if (req->sdiag_protocol >= MAX_LINKS) {
 			read_unlock(&nl_table_lock);
-			mutex_unlock(&nl_sk_hash_lock);
+			rcu_read_unlock();
 			return -ENOENT;
 		}
 
@@ -192,7 +195,7 @@ static int netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	}
 
 	read_unlock(&nl_table_lock);
-	mutex_unlock(&nl_sk_hash_lock);
+	rcu_read_unlock();
 
 	return skb->len;
 }
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 76393f2f4b22..2ed5f964772e 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -23,6 +23,9 @@
 static DEFINE_MUTEX(genl_mutex); /* serialization of message processing */
 static DECLARE_RWSEM(cb_lock);
 
+atomic_t genl_sk_destructing_cnt = ATOMIC_INIT(0);
+DECLARE_WAIT_QUEUE_HEAD(genl_sk_destructing_waitq);
+
 void genl_lock(void)
 {
 	mutex_lock(&genl_mutex);
@@ -435,15 +438,18 @@ int genl_unregister_family(struct genl_family *family)
 
 	genl_lock_all();
 
-	genl_unregister_mc_groups(family);
-
 	list_for_each_entry(rc, genl_family_chain(family->id), family_list) {
 		if (family->id != rc->id || strcmp(rc->name, family->name))
 			continue;
 
+		genl_unregister_mc_groups(family);
+
 		list_del(&rc->family_list);
 		family->n_ops = 0;
-		genl_unlock_all();
+		up_write(&cb_lock);
+		wait_event(genl_sk_destructing_waitq,
+			   atomic_read(&genl_sk_destructing_cnt) == 0);
+		genl_unlock();
 
 		kfree(family->attrbuf);
 		genl_ctrl_event(CTRL_CMD_DELFAMILY, family, NULL, 0);
@@ -756,7 +762,8 @@ static int ctrl_fill_info(struct genl_family *family, u32 portid, u32 seq,
 		nla_nest_end(skb, nla_grps);
 	}
 
-	return genlmsg_end(skb, hdr);
+	genlmsg_end(skb, hdr);
+	return 0;
 
 nla_put_failure:
 	genlmsg_cancel(skb, hdr);
@@ -796,7 +803,8 @@ static int ctrl_fill_mcgrp_info(struct genl_family *family,
 	nla_nest_end(skb, nest);
 	nla_nest_end(skb, nla_grps);
 
-	return genlmsg_end(skb, hdr);
+	genlmsg_end(skb, hdr);
+	return 0;
 
 nla_put_failure:
 	genlmsg_cancel(skb, hdr);
@@ -983,11 +991,63 @@ static struct genl_multicast_group genl_ctrl_groups[] = {
 	{ .name = "notify", },
 };
 
+static int genl_bind(struct net *net, int group)
+{
+	int i, err = -ENOENT;
+
+	down_read(&cb_lock);
+	for (i = 0; i < GENL_FAM_TAB_SIZE; i++) {
+		struct genl_family *f;
+
+		list_for_each_entry(f, genl_family_chain(i), family_list) {
+			if (group >= f->mcgrp_offset &&
+			    group < f->mcgrp_offset + f->n_mcgrps) {
+				int fam_grp = group - f->mcgrp_offset;
+
+				if (!f->netnsok && net != &init_net)
+					err = -ENOENT;
+				else if (f->mcast_bind)
+					err = f->mcast_bind(net, fam_grp);
+				else
+					err = 0;
+				break;
+			}
+		}
+	}
+	up_read(&cb_lock);
+
+	return err;
+}
+
+static void genl_unbind(struct net *net, int group)
+{
+	int i;
+
+	down_read(&cb_lock);
+	for (i = 0; i < GENL_FAM_TAB_SIZE; i++) {
+		struct genl_family *f;
+
+		list_for_each_entry(f, genl_family_chain(i), family_list) {
+			if (group >= f->mcgrp_offset &&
+			    group < f->mcgrp_offset + f->n_mcgrps) {
+				int fam_grp = group - f->mcgrp_offset;
+
+				if (f->mcast_unbind)
+					f->mcast_unbind(net, fam_grp);
+				break;
+			}
+		}
+	}
+	up_read(&cb_lock);
+}
+
 static int __net_init genl_pernet_init(struct net *net)
 {
 	struct netlink_kernel_cfg cfg = {
 		.input		= genl_rcv,
 		.flags		= NL_CFG_F_NONROOT_RECV,
+		.bind		= genl_bind,
+		.unbind		= genl_unbind,
 	};
 
 	/* we'll bump the group number right afterwards */
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 1b06a1fcf3e8..b987fd56c3c5 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -1023,8 +1023,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev)
 	return 1;
 }
 
-static int nr_sendmsg(struct kiocb *iocb, struct socket *sock,
-		      struct msghdr *msg, size_t len)
+static int nr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 {
 	struct sock *sk = sock->sk;
 	struct nr_sock *nr = nr_sk(sk);
@@ -1113,7 +1112,7 @@ static int nr_sendmsg(struct kiocb *iocb, struct socket *sock,
 	skb_put(skb, len);
 
 	/* User data follows immediately after the NET/ROM transport header */
-	if (memcpy_fromiovec(skb_transport_header(skb), msg->msg_iov, len)) {
+	if (memcpy_from_msg(skb_transport_header(skb), msg, len)) {
 		kfree_skb(skb);
 		err = -EFAULT;
 		goto out;
@@ -1133,8 +1132,8 @@ out:
 	return err;
 }
 
-static int nr_recvmsg(struct kiocb *iocb, struct socket *sock,
-		      struct msghdr *msg, size_t size, int flags)
+static int nr_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+		      int flags)
 {
 	struct sock *sk = sock->sk;
 	DECLARE_SOCKADDR(struct sockaddr_ax25 *, sax, msg->msg_name);
@@ -1167,7 +1166,7 @@ static int nr_recvmsg(struct kiocb *iocb, struct socket *sock,
 		msg->msg_flags |= MSG_TRUNC;
 	}
 
-	er = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	er = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (er < 0) {
 		skb_free_datagram(sk, skb);
 		release_sock(sk);
diff --git a/net/netrom/nr_dev.c b/net/netrom/nr_dev.c
index 6ae063cebf7d..988f542481a8 100644
--- a/net/netrom/nr_dev.c
+++ b/net/netrom/nr_dev.c
@@ -65,36 +65,6 @@ int nr_rx_ip(struct sk_buff *skb, struct net_device *dev)
 	return 1;
 }
 
-#ifdef CONFIG_INET
-
-static int nr_rebuild_header(struct sk_buff *skb)
-{
-	unsigned char *bp = skb->data;
-
-	if (arp_find(bp + 7, skb))
-		return 1;
-
-	bp[6] &= ~AX25_CBIT;
-	bp[6] &= ~AX25_EBIT;
-	bp[6] |= AX25_SSSID_SPARE;
-	bp    += AX25_ADDR_LEN;
-
-	bp[6] &= ~AX25_CBIT;
-	bp[6] |= AX25_EBIT;
-	bp[6] |= AX25_SSSID_SPARE;
-
-	return 0;
-}
-
-#else
-
-static int nr_rebuild_header(struct sk_buff *skb)
-{
-	return 1;
-}
-
-#endif
-
 static int nr_header(struct sk_buff *skb, struct net_device *dev,
 		     unsigned short type,
 		     const void *daddr, const void *saddr, unsigned int len)
@@ -188,7 +158,6 @@ static netdev_tx_t nr_xmit(struct sk_buff *skb, struct net_device *dev)
 
 static const struct header_ops nr_header_ops = {
 	.create	= nr_header,
-	.rebuild= nr_rebuild_header,
 };
 
 static const struct net_device_ops nr_netdev_ops = {
diff --git a/net/nfc/core.c b/net/nfc/core.c
index 819b87702b70..cff3f1614ad4 100644
--- a/net/nfc/core.c
+++ b/net/nfc/core.c
@@ -555,7 +555,6 @@ EXPORT_SYMBOL(nfc_find_se);
 
 int nfc_enable_se(struct nfc_dev *dev, u32 se_idx)
 {
-
 	struct nfc_se *se;
 	int rc;
 
@@ -605,7 +604,6 @@ error:
 
 int nfc_disable_se(struct nfc_dev *dev, u32 se_idx)
 {
-
 	struct nfc_se *se;
 	int rc;
 
@@ -934,6 +932,27 @@ int nfc_remove_se(struct nfc_dev *dev, u32 se_idx)
 }
 EXPORT_SYMBOL(nfc_remove_se);
 
+int nfc_se_transaction(struct nfc_dev *dev, u8 se_idx,
+		       struct nfc_evt_transaction *evt_transaction)
+{
+	int rc;
+
+	pr_debug("transaction: %x\n", se_idx);
+
+	device_lock(&dev->dev);
+
+	if (!evt_transaction) {
+		rc = -EPROTO;
+		goto out;
+	}
+
+	rc = nfc_genl_se_transaction(dev, se_idx, evt_transaction);
+out:
+	device_unlock(&dev->dev);
+	return rc;
+}
+EXPORT_SYMBOL(nfc_se_transaction);
+
 static void nfc_release(struct device *d)
 {
 	struct nfc_dev *dev = to_nfc_dev(d);
diff --git a/net/nfc/digital_dep.c b/net/nfc/digital_dep.c
index b60aa35c074f..f72be7433df3 100644
--- a/net/nfc/digital_dep.c
+++ b/net/nfc/digital_dep.c
@@ -17,6 +17,9 @@
 
 #include "digital.h"
 
+#define DIGITAL_NFC_DEP_N_RETRY_NACK	2
+#define DIGITAL_NFC_DEP_N_RETRY_ATN	2
+
 #define DIGITAL_NFC_DEP_FRAME_DIR_OUT 0xD4
 #define DIGITAL_NFC_DEP_FRAME_DIR_IN  0xD5
 
@@ -32,20 +35,32 @@
 #define DIGITAL_ATR_REQ_MIN_SIZE 16
 #define DIGITAL_ATR_REQ_MAX_SIZE 64
 
-#define DIGITAL_LR_BITS_PAYLOAD_SIZE_254B 0x30
-#define DIGITAL_FSL_BITS_PAYLOAD_SIZE_254B \
-				(DIGITAL_LR_BITS_PAYLOAD_SIZE_254B >> 4)
+#define DIGITAL_DID_MAX	14
+
+#define DIGITAL_PAYLOAD_SIZE_MAX	254
+#define DIGITAL_PAYLOAD_BITS_TO_PP(s)	(((s) & 0x3) << 4)
+#define DIGITAL_PAYLOAD_PP_TO_BITS(s)	(((s) >> 4) & 0x3)
+#define DIGITAL_PAYLOAD_BITS_TO_FSL(s)	((s) & 0x3)
+#define DIGITAL_PAYLOAD_FSL_TO_BITS(s)	((s) & 0x3)
+
 #define DIGITAL_GB_BIT	0x02
 
+#define DIGITAL_NFC_DEP_REQ_RES_HEADROOM	2 /* SoD: [SB (NFC-A)] + LEN */
+#define DIGITAL_NFC_DEP_REQ_RES_TAILROOM	2 /* EoD: 2-byte CRC */
+
 #define DIGITAL_NFC_DEP_PFB_TYPE(pfb) ((pfb) & 0xE0)
 
 #define DIGITAL_NFC_DEP_PFB_TIMEOUT_BIT 0x10
+#define DIGITAL_NFC_DEP_PFB_MI_BIT	0x10
+#define DIGITAL_NFC_DEP_PFB_NACK_BIT	0x10
+#define DIGITAL_NFC_DEP_PFB_DID_BIT	0x04
 
 #define DIGITAL_NFC_DEP_PFB_IS_TIMEOUT(pfb) \
 				((pfb) & DIGITAL_NFC_DEP_PFB_TIMEOUT_BIT)
-#define DIGITAL_NFC_DEP_MI_BIT_SET(pfb)  ((pfb) & 0x10)
+#define DIGITAL_NFC_DEP_MI_BIT_SET(pfb)  ((pfb) & DIGITAL_NFC_DEP_PFB_MI_BIT)
+#define DIGITAL_NFC_DEP_NACK_BIT_SET(pfb) ((pfb) & DIGITAL_NFC_DEP_PFB_NACK_BIT)
 #define DIGITAL_NFC_DEP_NAD_BIT_SET(pfb) ((pfb) & 0x08)
-#define DIGITAL_NFC_DEP_DID_BIT_SET(pfb) ((pfb) & 0x04)
+#define DIGITAL_NFC_DEP_DID_BIT_SET(pfb) ((pfb) & DIGITAL_NFC_DEP_PFB_DID_BIT)
 #define DIGITAL_NFC_DEP_PFB_PNI(pfb)     ((pfb) & 0x03)
 
 #define DIGITAL_NFC_DEP_PFB_I_PDU          0x00
@@ -97,6 +112,34 @@ struct digital_dep_req_res {
 
 static void digital_in_recv_dep_res(struct nfc_digital_dev *ddev, void *arg,
 				    struct sk_buff *resp);
+static void digital_tg_recv_dep_req(struct nfc_digital_dev *ddev, void *arg,
+				    struct sk_buff *resp);
+
+static const u8 digital_payload_bits_map[4] = {
+	[0] = 64,
+	[1] = 128,
+	[2] = 192,
+	[3] = 254
+};
+
+static u8 digital_payload_bits_to_size(u8 payload_bits)
+{
+	if (payload_bits >= ARRAY_SIZE(digital_payload_bits_map))
+		return 0;
+
+	return digital_payload_bits_map[payload_bits];
+}
+
+static u8 digital_payload_size_to_bits(u8 payload_size)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(digital_payload_bits_map); i++)
+		if (digital_payload_bits_map[i] == payload_size)
+			return i;
+
+	return 0xff;
+}
 
 static void digital_skb_push_dep_sod(struct nfc_digital_dev *ddev,
 				     struct sk_buff *skb)
@@ -129,6 +172,106 @@ static int digital_skb_pull_dep_sod(struct nfc_digital_dev *ddev,
 	return 0;
 }
 
+static struct sk_buff *
+digital_send_dep_data_prep(struct nfc_digital_dev *ddev, struct sk_buff *skb,
+			   struct digital_dep_req_res *dep_req_res,
+			   struct digital_data_exch *data_exch)
+{
+	struct sk_buff *new_skb;
+
+	if (skb->len > ddev->remote_payload_max) {
+		dep_req_res->pfb |= DIGITAL_NFC_DEP_PFB_MI_BIT;
+
+		new_skb = digital_skb_alloc(ddev, ddev->remote_payload_max);
+		if (!new_skb) {
+			kfree_skb(ddev->chaining_skb);
+			ddev->chaining_skb = NULL;
+
+			return ERR_PTR(-ENOMEM);
+		}
+
+		skb_reserve(new_skb, ddev->tx_headroom + NFC_HEADER_SIZE +
+					DIGITAL_NFC_DEP_REQ_RES_HEADROOM);
+		memcpy(skb_put(new_skb, ddev->remote_payload_max), skb->data,
+		       ddev->remote_payload_max);
+		skb_pull(skb, ddev->remote_payload_max);
+
+		ddev->chaining_skb = skb;
+		ddev->data_exch = data_exch;
+	} else {
+		ddev->chaining_skb = NULL;
+		new_skb = skb;
+	}
+
+	return new_skb;
+}
+
+static struct sk_buff *
+digital_recv_dep_data_gather(struct nfc_digital_dev *ddev, u8 pfb,
+			     struct sk_buff *resp,
+			     int (*send_ack)(struct nfc_digital_dev *ddev,
+					     struct digital_data_exch
+							     *data_exch),
+			     struct digital_data_exch *data_exch)
+{
+	struct sk_buff *new_skb;
+	int rc;
+
+	if (DIGITAL_NFC_DEP_MI_BIT_SET(pfb) && (!ddev->chaining_skb)) {
+		ddev->chaining_skb =
+			nfc_alloc_recv_skb(8 * ddev->local_payload_max,
+					   GFP_KERNEL);
+		if (!ddev->chaining_skb) {
+			rc = -ENOMEM;
+			goto error;
+		}
+	}
+
+	if (ddev->chaining_skb) {
+		if (resp->len > skb_tailroom(ddev->chaining_skb)) {
+			new_skb = skb_copy_expand(ddev->chaining_skb,
+						  skb_headroom(
+							  ddev->chaining_skb),
+						  8 * ddev->local_payload_max,
+						  GFP_KERNEL);
+			if (!new_skb) {
+				rc = -ENOMEM;
+				goto error;
+			}
+
+			kfree_skb(ddev->chaining_skb);
+			ddev->chaining_skb = new_skb;
+		}
+
+		memcpy(skb_put(ddev->chaining_skb, resp->len), resp->data,
+		       resp->len);
+
+		kfree_skb(resp);
+		resp = NULL;
+
+		if (DIGITAL_NFC_DEP_MI_BIT_SET(pfb)) {
+			rc = send_ack(ddev, data_exch);
+			if (rc)
+				goto error;
+
+			return NULL;
+		}
+
+		resp = ddev->chaining_skb;
+		ddev->chaining_skb = NULL;
+	}
+
+	return resp;
+
+error:
+	kfree_skb(resp);
+
+	kfree_skb(ddev->chaining_skb);
+	ddev->chaining_skb = NULL;
+
+	return ERR_PTR(rc);
+}
+
 static void digital_in_recv_psl_res(struct nfc_digital_dev *ddev, void *arg,
 				    struct sk_buff *resp)
 {
@@ -198,6 +341,8 @@ static int digital_in_send_psl_req(struct nfc_digital_dev *ddev,
 {
 	struct sk_buff *skb;
 	struct digital_psl_req *psl_req;
+	int rc;
+	u8 payload_size, payload_bits;
 
 	skb = digital_skb_alloc(ddev, sizeof(*psl_req));
 	if (!skb)
@@ -211,14 +356,24 @@ static int digital_in_send_psl_req(struct nfc_digital_dev *ddev,
 	psl_req->cmd = DIGITAL_CMD_PSL_REQ;
 	psl_req->did = 0;
 	psl_req->brs = (0x2 << 3) | 0x2; /* 424F both directions */
-	psl_req->fsl = DIGITAL_FSL_BITS_PAYLOAD_SIZE_254B;
+
+	payload_size = min(ddev->local_payload_max, ddev->remote_payload_max);
+	payload_bits = digital_payload_size_to_bits(payload_size);
+	psl_req->fsl = DIGITAL_PAYLOAD_BITS_TO_FSL(payload_bits);
+
+	ddev->local_payload_max = payload_size;
+	ddev->remote_payload_max = payload_size;
 
 	digital_skb_push_dep_sod(ddev, skb);
 
 	ddev->skb_add_crc(skb);
 
-	return digital_in_send_cmd(ddev, skb, 500, digital_in_recv_psl_res,
-				   target);
+	rc = digital_in_send_cmd(ddev, skb, 500, digital_in_recv_psl_res,
+				 target);
+	if (rc)
+		kfree_skb(skb);
+
+	return rc;
 }
 
 static void digital_in_recv_atr_res(struct nfc_digital_dev *ddev, void *arg,
@@ -226,7 +381,7 @@ static void digital_in_recv_atr_res(struct nfc_digital_dev *ddev, void *arg,
 {
 	struct nfc_target *target = arg;
 	struct digital_atr_res *atr_res;
-	u8 gb_len;
+	u8 gb_len, payload_bits;
 	int rc;
 
 	if (IS_ERR(resp)) {
@@ -256,6 +411,14 @@ static void digital_in_recv_atr_res(struct nfc_digital_dev *ddev, void *arg,
 
 	atr_res = (struct digital_atr_res *)resp->data;
 
+	payload_bits = DIGITAL_PAYLOAD_PP_TO_BITS(atr_res->pp);
+	ddev->remote_payload_max = digital_payload_bits_to_size(payload_bits);
+
+	if (!ddev->remote_payload_max) {
+		rc = -EINVAL;
+		goto exit;
+	}
+
 	rc = nfc_set_remote_general_bytes(ddev->nfc_dev, atr_res->gb, gb_len);
 	if (rc)
 		goto exit;
@@ -286,6 +449,8 @@ int digital_in_send_atr_req(struct nfc_digital_dev *ddev,
 	struct sk_buff *skb;
 	struct digital_atr_req *atr_req;
 	uint size;
+	int rc;
+	u8 payload_bits;
 
 	size = DIGITAL_ATR_REQ_MIN_SIZE + gb_len;
 
@@ -314,7 +479,9 @@ int digital_in_send_atr_req(struct nfc_digital_dev *ddev,
 	atr_req->bs = 0;
 	atr_req->br = 0;
 
-	atr_req->pp = DIGITAL_LR_BITS_PAYLOAD_SIZE_254B;
+	ddev->local_payload_max = DIGITAL_PAYLOAD_SIZE_MAX;
+	payload_bits = digital_payload_size_to_bits(ddev->local_payload_max);
+	atr_req->pp = DIGITAL_PAYLOAD_BITS_TO_PP(payload_bits);
 
 	if (gb_len) {
 		atr_req->pp |= DIGITAL_GB_BIT;
@@ -325,8 +492,113 @@ int digital_in_send_atr_req(struct nfc_digital_dev *ddev,
 
 	ddev->skb_add_crc(skb);
 
-	return digital_in_send_cmd(ddev, skb, 500, digital_in_recv_atr_res,
-				   target);
+	rc = digital_in_send_cmd(ddev, skb, 500, digital_in_recv_atr_res,
+				 target);
+	if (rc)
+		kfree_skb(skb);
+
+	return rc;
+}
+
+static int digital_in_send_ack(struct nfc_digital_dev *ddev,
+			       struct digital_data_exch *data_exch)
+{
+	struct digital_dep_req_res *dep_req;
+	struct sk_buff *skb;
+	int rc;
+
+	skb = digital_skb_alloc(ddev, 1);
+	if (!skb)
+		return -ENOMEM;
+
+	skb_push(skb, sizeof(struct digital_dep_req_res));
+
+	dep_req = (struct digital_dep_req_res *)skb->data;
+
+	dep_req->dir = DIGITAL_NFC_DEP_FRAME_DIR_OUT;
+	dep_req->cmd = DIGITAL_CMD_DEP_REQ;
+	dep_req->pfb = DIGITAL_NFC_DEP_PFB_ACK_NACK_PDU |
+		       ddev->curr_nfc_dep_pni;
+
+	digital_skb_push_dep_sod(ddev, skb);
+
+	ddev->skb_add_crc(skb);
+
+	ddev->saved_skb = skb_get(skb);
+	ddev->saved_skb_len = skb->len;
+
+	rc = digital_in_send_cmd(ddev, skb, 1500, digital_in_recv_dep_res,
+				 data_exch);
+	if (rc) {
+		kfree_skb(skb);
+		kfree_skb(ddev->saved_skb);
+		ddev->saved_skb = NULL;
+	}
+
+	return rc;
+}
+
+static int digital_in_send_nack(struct nfc_digital_dev *ddev,
+				struct digital_data_exch *data_exch)
+{
+	struct digital_dep_req_res *dep_req;
+	struct sk_buff *skb;
+	int rc;
+
+	skb = digital_skb_alloc(ddev, 1);
+	if (!skb)
+		return -ENOMEM;
+
+	skb_push(skb, sizeof(struct digital_dep_req_res));
+
+	dep_req = (struct digital_dep_req_res *)skb->data;
+
+	dep_req->dir = DIGITAL_NFC_DEP_FRAME_DIR_OUT;
+	dep_req->cmd = DIGITAL_CMD_DEP_REQ;
+	dep_req->pfb = DIGITAL_NFC_DEP_PFB_ACK_NACK_PDU |
+		       DIGITAL_NFC_DEP_PFB_NACK_BIT | ddev->curr_nfc_dep_pni;
+
+	digital_skb_push_dep_sod(ddev, skb);
+
+	ddev->skb_add_crc(skb);
+
+	rc = digital_in_send_cmd(ddev, skb, 1500, digital_in_recv_dep_res,
+				 data_exch);
+	if (rc)
+		kfree_skb(skb);
+
+	return rc;
+}
+
+static int digital_in_send_atn(struct nfc_digital_dev *ddev,
+			       struct digital_data_exch *data_exch)
+{
+	struct digital_dep_req_res *dep_req;
+	struct sk_buff *skb;
+	int rc;
+
+	skb = digital_skb_alloc(ddev, 1);
+	if (!skb)
+		return -ENOMEM;
+
+	skb_push(skb, sizeof(struct digital_dep_req_res));
+
+	dep_req = (struct digital_dep_req_res *)skb->data;
+
+	dep_req->dir = DIGITAL_NFC_DEP_FRAME_DIR_OUT;
+	dep_req->cmd = DIGITAL_CMD_DEP_REQ;
+	dep_req->pfb = DIGITAL_NFC_DEP_PFB_SUPERVISOR_PDU;
+
+	digital_skb_push_dep_sod(ddev, skb);
+
+	ddev->skb_add_crc(skb);
+
+	rc = digital_in_send_cmd(ddev, skb, 1500, digital_in_recv_dep_res,
+				 data_exch);
+	if (rc)
+		kfree_skb(skb);
+
+	return rc;
 }
 
 static int digital_in_send_rtox(struct nfc_digital_dev *ddev,
@@ -355,12 +627,30 @@ static int digital_in_send_rtox(struct nfc_digital_dev *ddev,
 
 	ddev->skb_add_crc(skb);
 
+	ddev->saved_skb = skb_get(skb);
+	ddev->saved_skb_len = skb->len;
+
 	rc = digital_in_send_cmd(ddev, skb, 1500, digital_in_recv_dep_res,
 				 data_exch);
+	if (rc) {
+		kfree_skb(skb);
+		kfree_skb(ddev->saved_skb);
+		ddev->saved_skb = NULL;
+	}
 
 	return rc;
 }
 
+static int digital_in_send_saved_skb(struct nfc_digital_dev *ddev,
+				     struct digital_data_exch *data_exch)
+{
+	skb_get(ddev->saved_skb);
+	skb_push(ddev->saved_skb, ddev->saved_skb_len);
+
+	return digital_in_send_cmd(ddev, ddev->saved_skb, 1500,
+				   digital_in_recv_dep_res, data_exch);
+}
+
 static void digital_in_recv_dep_res(struct nfc_digital_dev *ddev, void *arg,
 				    struct sk_buff *resp)
 {
@@ -373,25 +663,67 @@ static void digital_in_recv_dep_res(struct nfc_digital_dev *ddev, void *arg,
 	if (IS_ERR(resp)) {
 		rc = PTR_ERR(resp);
 		resp = NULL;
+
+		if (((rc != -ETIMEDOUT) || ddev->nack_count) &&
+		    (ddev->nack_count++ < DIGITAL_NFC_DEP_N_RETRY_NACK)) {
+			ddev->atn_count = 0;
+
+			rc = digital_in_send_nack(ddev, data_exch);
+			if (rc)
+				goto error;
+
+			return;
+		} else if ((rc == -ETIMEDOUT) &&
+			   (ddev->atn_count++ < DIGITAL_NFC_DEP_N_RETRY_ATN)) {
+			ddev->nack_count = 0;
+
+			rc = digital_in_send_atn(ddev, data_exch);
+			if (rc)
+				goto error;
+
+			return;
+		}
+
+		goto exit;
+	}
+
+	rc = digital_skb_pull_dep_sod(ddev, resp);
+	if (rc) {
+		PROTOCOL_ERR("14.4.1.2");
 		goto exit;
 	}
 
 	rc = ddev->skb_check_crc(resp);
 	if (rc) {
+		if ((resp->len >= 4) &&
+		    (ddev->nack_count++ < DIGITAL_NFC_DEP_N_RETRY_NACK)) {
+			ddev->atn_count = 0;
+
+			rc = digital_in_send_nack(ddev, data_exch);
+			if (rc)
+				goto error;
+
+			kfree_skb(resp);
+
+			return;
+		}
+
 		PROTOCOL_ERR("14.4.1.6");
 		goto error;
 	}
 
-	rc = digital_skb_pull_dep_sod(ddev, resp);
-	if (rc) {
-		PROTOCOL_ERR("14.4.1.2");
+	ddev->atn_count = 0;
+	ddev->nack_count = 0;
+
+	if (resp->len > ddev->local_payload_max) {
+		rc = -EMSGSIZE;
 		goto exit;
 	}
 
+	size = sizeof(struct digital_dep_req_res);
 	dep_res = (struct digital_dep_req_res *)resp->data;
 
-	if (resp->len < sizeof(struct digital_dep_req_res) ||
-	    dep_res->dir != DIGITAL_NFC_DEP_FRAME_DIR_IN ||
+	if (resp->len < size || dep_res->dir != DIGITAL_NFC_DEP_FRAME_DIR_IN ||
 	    dep_res->cmd != DIGITAL_CMD_DEP_RES) {
 		rc = -EIO;
 		goto error;
@@ -399,6 +731,24 @@ static void digital_in_recv_dep_res(struct nfc_digital_dev *ddev, void *arg,
 
 	pfb = dep_res->pfb;
 
+	if (DIGITAL_NFC_DEP_DID_BIT_SET(pfb)) {
+		PROTOCOL_ERR("14.8.2.1");
+		rc = -EIO;
+		goto error;
+	}
+
+	if (DIGITAL_NFC_DEP_NAD_BIT_SET(pfb)) {
+		rc = -EIO;
+		goto exit;
+	}
+
+	if (size > resp->len) {
+		rc = -EIO;
+		goto error;
+	}
+
+	skb_pull(resp, size);
+
 	switch (DIGITAL_NFC_DEP_PFB_TYPE(pfb)) {
 	case DIGITAL_NFC_DEP_PFB_I_PDU:
 		if (DIGITAL_NFC_DEP_PFB_PNI(pfb) != ddev->curr_nfc_dep_pni) {
@@ -409,21 +759,71 @@ static void digital_in_recv_dep_res(struct nfc_digital_dev *ddev, void *arg,
 
 		ddev->curr_nfc_dep_pni =
 			DIGITAL_NFC_DEP_PFB_PNI(ddev->curr_nfc_dep_pni + 1);
+
+		kfree_skb(ddev->saved_skb);
+		ddev->saved_skb = NULL;
+
+		resp = digital_recv_dep_data_gather(ddev, pfb, resp,
+						    digital_in_send_ack,
+						    data_exch);
+		if (IS_ERR(resp)) {
+			rc = PTR_ERR(resp);
+			resp = NULL;
+			goto error;
+		}
+
+		/* If resp is NULL then we're still chaining so return and
+		 * wait for the next part of the PDU.  Else, the PDU is
+		 * complete so pass it up.
+		 */
+		if (!resp)
+			return;
+
 		rc = 0;
 		break;
 
 	case DIGITAL_NFC_DEP_PFB_ACK_NACK_PDU:
+		if (DIGITAL_NFC_DEP_PFB_PNI(pfb) != ddev->curr_nfc_dep_pni) {
+			PROTOCOL_ERR("14.12.3.3");
+			rc = -EIO;
+			goto exit;
+		}
+
+		ddev->curr_nfc_dep_pni =
+			DIGITAL_NFC_DEP_PFB_PNI(ddev->curr_nfc_dep_pni + 1);
+
+		if (ddev->chaining_skb && !DIGITAL_NFC_DEP_NACK_BIT_SET(pfb)) {
+			kfree_skb(ddev->saved_skb);
+			ddev->saved_skb = NULL;
+
+			rc = digital_in_send_dep_req(ddev, NULL,
+						     ddev->chaining_skb,
+						     ddev->data_exch);
+			if (rc)
+				goto error;
+
+			return;
+		}
+
 		pr_err("Received a ACK/NACK PDU\n");
-		rc = -EIO;
-		goto error;
+		rc = -EINVAL;
+		goto exit;
 
 	case DIGITAL_NFC_DEP_PFB_SUPERVISOR_PDU:
-		if (!DIGITAL_NFC_DEP_PFB_IS_TIMEOUT(pfb)) {
-			rc = -EINVAL;
-			goto error;
+		if (!DIGITAL_NFC_DEP_PFB_IS_TIMEOUT(pfb)) { /* ATN */
+			rc = digital_in_send_saved_skb(ddev, data_exch);
+			if (rc) {
+				kfree_skb(ddev->saved_skb);
+				goto error;
+			}
+
+			return;
 		}
 
-		rc = digital_in_send_rtox(ddev, data_exch, resp->data[3]);
+		kfree_skb(ddev->saved_skb);
+		ddev->saved_skb = NULL;
+
+		rc = digital_in_send_rtox(ddev, data_exch, resp->data[0]);
 		if (rc)
 			goto error;
 
@@ -431,30 +831,18 @@ static void digital_in_recv_dep_res(struct nfc_digital_dev *ddev, void *arg,
 		return;
 	}
 
-	if (DIGITAL_NFC_DEP_MI_BIT_SET(pfb)) {
-		pr_err("MI bit set. Chained PDU not supported\n");
-		rc = -EIO;
-		goto error;
-	}
-
-	size = sizeof(struct digital_dep_req_res);
-
-	if (DIGITAL_NFC_DEP_DID_BIT_SET(pfb))
-		size++;
-
-	if (size > resp->len) {
-		rc = -EIO;
-		goto error;
-	}
-
-	skb_pull(resp, size);
-
 exit:
 	data_exch->cb(data_exch->cb_context, resp, rc);
 
 error:
 	kfree(data_exch);
 
+	kfree_skb(ddev->chaining_skb);
+	ddev->chaining_skb = NULL;
+
+	kfree_skb(ddev->saved_skb);
+	ddev->saved_skb = NULL;
+
 	if (rc)
 		kfree_skb(resp);
 }
@@ -464,20 +852,47 @@ int digital_in_send_dep_req(struct nfc_digital_dev *ddev,
 			    struct digital_data_exch *data_exch)
 {
 	struct digital_dep_req_res *dep_req;
+	struct sk_buff *chaining_skb, *tmp_skb;
+	int rc;
 
 	skb_push(skb, sizeof(struct digital_dep_req_res));
 
 	dep_req = (struct digital_dep_req_res *)skb->data;
+
 	dep_req->dir = DIGITAL_NFC_DEP_FRAME_DIR_OUT;
 	dep_req->cmd = DIGITAL_CMD_DEP_REQ;
 	dep_req->pfb = ddev->curr_nfc_dep_pni;
 
-	digital_skb_push_dep_sod(ddev, skb);
+	ddev->atn_count = 0;
+	ddev->nack_count = 0;
 
-	ddev->skb_add_crc(skb);
+	chaining_skb = ddev->chaining_skb;
+
+	tmp_skb = digital_send_dep_data_prep(ddev, skb, dep_req, data_exch);
+	if (IS_ERR(tmp_skb))
+		return PTR_ERR(tmp_skb);
+
+	digital_skb_push_dep_sod(ddev, tmp_skb);
+
+	ddev->skb_add_crc(tmp_skb);
 
-	return digital_in_send_cmd(ddev, skb, 1500, digital_in_recv_dep_res,
-				   data_exch);
+	ddev->saved_skb = skb_get(tmp_skb);
+	ddev->saved_skb_len = tmp_skb->len;
+
+	rc = digital_in_send_cmd(ddev, tmp_skb, 1500, digital_in_recv_dep_res,
+				 data_exch);
+	if (rc) {
+		if (tmp_skb != skb)
+			kfree_skb(tmp_skb);
+
+		kfree_skb(chaining_skb);
+		ddev->chaining_skb = NULL;
+
+		kfree_skb(ddev->saved_skb);
+		ddev->saved_skb = NULL;
+	}
+
+	return rc;
 }
 
 static void digital_tg_set_rf_tech(struct nfc_digital_dev *ddev, u8 rf_tech)
@@ -507,11 +922,106 @@ static void digital_tg_set_rf_tech(struct nfc_digital_dev *ddev, u8 rf_tech)
 	}
 }
 
+static int digital_tg_send_ack(struct nfc_digital_dev *ddev,
+			       struct digital_data_exch *data_exch)
+{
+	struct digital_dep_req_res *dep_res;
+	struct sk_buff *skb;
+	int rc;
+
+	skb = digital_skb_alloc(ddev, 1);
+	if (!skb)
+		return -ENOMEM;
+
+	skb_push(skb, sizeof(struct digital_dep_req_res));
+
+	dep_res = (struct digital_dep_req_res *)skb->data;
+
+	dep_res->dir = DIGITAL_NFC_DEP_FRAME_DIR_IN;
+	dep_res->cmd = DIGITAL_CMD_DEP_RES;
+	dep_res->pfb = DIGITAL_NFC_DEP_PFB_ACK_NACK_PDU |
+		       ddev->curr_nfc_dep_pni;
+
+	if (ddev->did) {
+		dep_res->pfb |= DIGITAL_NFC_DEP_PFB_DID_BIT;
+
+		memcpy(skb_put(skb, sizeof(ddev->did)), &ddev->did,
+		       sizeof(ddev->did));
+	}
+
+	ddev->curr_nfc_dep_pni =
+		DIGITAL_NFC_DEP_PFB_PNI(ddev->curr_nfc_dep_pni + 1);
+
+	digital_skb_push_dep_sod(ddev, skb);
+
+	ddev->skb_add_crc(skb);
+
+	ddev->saved_skb = skb_get(skb);
+	ddev->saved_skb_len = skb->len;
+
+	rc = digital_tg_send_cmd(ddev, skb, 1500, digital_tg_recv_dep_req,
+				 data_exch);
+	if (rc) {
+		kfree_skb(skb);
+		kfree_skb(ddev->saved_skb);
+		ddev->saved_skb = NULL;
+	}
+
+	return rc;
+}
+
+static int digital_tg_send_atn(struct nfc_digital_dev *ddev)
+{
+	struct digital_dep_req_res *dep_res;
+	struct sk_buff *skb;
+	int rc;
+
+	skb = digital_skb_alloc(ddev, 1);
+	if (!skb)
+		return -ENOMEM;
+
+	skb_push(skb, sizeof(struct digital_dep_req_res));
+
+	dep_res = (struct digital_dep_req_res *)skb->data;
+
+	dep_res->dir = DIGITAL_NFC_DEP_FRAME_DIR_IN;
+	dep_res->cmd = DIGITAL_CMD_DEP_RES;
+	dep_res->pfb = DIGITAL_NFC_DEP_PFB_SUPERVISOR_PDU;
+
+	if (ddev->did) {
+		dep_res->pfb |= DIGITAL_NFC_DEP_PFB_DID_BIT;
+
+		memcpy(skb_put(skb, sizeof(ddev->did)), &ddev->did,
+		       sizeof(ddev->did));
+	}
+
+	digital_skb_push_dep_sod(ddev, skb);
+
+	ddev->skb_add_crc(skb);
+
+	rc = digital_tg_send_cmd(ddev, skb, 1500, digital_tg_recv_dep_req,
+				 NULL);
+	if (rc)
+		kfree_skb(skb);
+
+	return rc;
+}
+
+static int digital_tg_send_saved_skb(struct nfc_digital_dev *ddev)
+{
+	skb_get(ddev->saved_skb);
+	skb_push(ddev->saved_skb, ddev->saved_skb_len);
+
+	return digital_tg_send_cmd(ddev, ddev->saved_skb, 1500,
+				   digital_tg_recv_dep_req, NULL);
+}
+
 static void digital_tg_recv_dep_req(struct nfc_digital_dev *ddev, void *arg,
 				    struct sk_buff *resp)
 {
 	int rc;
 	struct digital_dep_req_res *dep_req;
+	u8 pfb;
 	size_t size;
 
 	if (IS_ERR(resp)) {
@@ -532,6 +1042,11 @@ static void digital_tg_recv_dep_req(struct nfc_digital_dev *ddev, void *arg,
 		goto exit;
 	}
 
+	if (resp->len > ddev->local_payload_max) {
+		rc = -EMSGSIZE;
+		goto exit;
+	}
+
 	size = sizeof(struct digital_dep_req_res);
 	dep_req = (struct digital_dep_req_res *)resp->data;
 
@@ -541,34 +1056,147 @@ static void digital_tg_recv_dep_req(struct nfc_digital_dev *ddev, void *arg,
 		goto exit;
 	}
 
-	if (DIGITAL_NFC_DEP_DID_BIT_SET(dep_req->pfb))
-		size++;
+	pfb = dep_req->pfb;
 
-	if (resp->len < size) {
+	if (DIGITAL_NFC_DEP_DID_BIT_SET(pfb)) {
+		if (ddev->did && (ddev->did == resp->data[3])) {
+			size++;
+		} else {
+			rc = -EIO;
+			goto exit;
+		}
+	} else if (ddev->did) {
 		rc = -EIO;
 		goto exit;
 	}
 
-	switch (DIGITAL_NFC_DEP_PFB_TYPE(dep_req->pfb)) {
+	if (DIGITAL_NFC_DEP_NAD_BIT_SET(pfb)) {
+		rc = -EIO;
+		goto exit;
+	}
+
+	if (size > resp->len) {
+		rc = -EIO;
+		goto exit;
+	}
+
+	skb_pull(resp, size);
+
+	switch (DIGITAL_NFC_DEP_PFB_TYPE(pfb)) {
 	case DIGITAL_NFC_DEP_PFB_I_PDU:
 		pr_debug("DIGITAL_NFC_DEP_PFB_I_PDU\n");
-		ddev->curr_nfc_dep_pni = DIGITAL_NFC_DEP_PFB_PNI(dep_req->pfb);
+
+		if ((ddev->atn_count && (DIGITAL_NFC_DEP_PFB_PNI(pfb - 1) !=
+						ddev->curr_nfc_dep_pni)) ||
+		    (DIGITAL_NFC_DEP_PFB_PNI(pfb) != ddev->curr_nfc_dep_pni)) {
+			PROTOCOL_ERR("14.12.3.4");
+			rc = -EIO;
+			goto exit;
+		}
+
+		if (ddev->atn_count) {
+			ddev->atn_count = 0;
+
+			rc = digital_tg_send_saved_skb(ddev);
+			if (rc)
+				goto exit;
+
+			return;
+		}
+
+		kfree_skb(ddev->saved_skb);
+		ddev->saved_skb = NULL;
+
+		resp = digital_recv_dep_data_gather(ddev, pfb, resp,
+						    digital_tg_send_ack, NULL);
+		if (IS_ERR(resp)) {
+			rc = PTR_ERR(resp);
+			resp = NULL;
+			goto exit;
+		}
+
+		/* If resp is NULL then we're still chaining so return and
+		 * wait for the next part of the PDU.  Else, the PDU is
+		 * complete so pass it up.
+		 */
+		if (!resp)
+			return;
+
+		rc = 0;
 		break;
 	case DIGITAL_NFC_DEP_PFB_ACK_NACK_PDU:
-		pr_err("Received a ACK/NACK PDU\n");
-		rc = -EINVAL;
-		goto exit;
+		if (!DIGITAL_NFC_DEP_NACK_BIT_SET(pfb)) { /* ACK */
+			if ((ddev->atn_count &&
+			     (DIGITAL_NFC_DEP_PFB_PNI(pfb - 1) !=
+						ddev->curr_nfc_dep_pni)) ||
+			    (DIGITAL_NFC_DEP_PFB_PNI(pfb) !=
+						ddev->curr_nfc_dep_pni) ||
+			    !ddev->chaining_skb || !ddev->saved_skb) {
+				rc = -EIO;
+				goto exit;
+			}
+
+			if (ddev->atn_count) {
+				ddev->atn_count = 0;
+
+				rc = digital_tg_send_saved_skb(ddev);
+				if (rc)
+					goto exit;
+
+				return;
+			}
+
+			kfree_skb(ddev->saved_skb);
+			ddev->saved_skb = NULL;
+
+			rc = digital_tg_send_dep_res(ddev, ddev->chaining_skb);
+			if (rc)
+				goto exit;
+		} else { /* NACK */
+			if ((DIGITAL_NFC_DEP_PFB_PNI(pfb + 1) !=
+						ddev->curr_nfc_dep_pni) ||
+			    !ddev->saved_skb) {
+				rc = -EIO;
+				goto exit;
+			}
+
+			ddev->atn_count = 0;
+
+			rc = digital_tg_send_saved_skb(ddev);
+			if (rc) {
+				kfree_skb(ddev->saved_skb);
+				goto exit;
+			}
+		}
+
+		return;
 	case DIGITAL_NFC_DEP_PFB_SUPERVISOR_PDU:
-		pr_err("Received a SUPERVISOR PDU\n");
-		rc = -EINVAL;
-		goto exit;
-	}
+		if (DIGITAL_NFC_DEP_PFB_IS_TIMEOUT(pfb)) {
+			rc = -EINVAL;
+			goto exit;
+		}
 
-	skb_pull(resp, size);
+		rc = digital_tg_send_atn(ddev);
+		if (rc)
+			goto exit;
+
+		ddev->atn_count++;
+
+		kfree_skb(resp);
+		return;
+	}
 
 	rc = nfc_tm_data_received(ddev->nfc_dev, resp);
 
 exit:
+	kfree_skb(ddev->chaining_skb);
+	ddev->chaining_skb = NULL;
+
+	ddev->atn_count = 0;
+
+	kfree_skb(ddev->saved_skb);
+	ddev->saved_skb = NULL;
+
 	if (rc)
 		kfree_skb(resp);
 }
@@ -576,20 +1204,54 @@ exit:
 int digital_tg_send_dep_res(struct nfc_digital_dev *ddev, struct sk_buff *skb)
 {
 	struct digital_dep_req_res *dep_res;
+	struct sk_buff *chaining_skb, *tmp_skb;
+	int rc;
 
 	skb_push(skb, sizeof(struct digital_dep_req_res));
+
 	dep_res = (struct digital_dep_req_res *)skb->data;
 
 	dep_res->dir = DIGITAL_NFC_DEP_FRAME_DIR_IN;
 	dep_res->cmd = DIGITAL_CMD_DEP_RES;
 	dep_res->pfb = ddev->curr_nfc_dep_pni;
 
-	digital_skb_push_dep_sod(ddev, skb);
+	if (ddev->did) {
+		dep_res->pfb |= DIGITAL_NFC_DEP_PFB_DID_BIT;
 
-	ddev->skb_add_crc(skb);
+		memcpy(skb_put(skb, sizeof(ddev->did)), &ddev->did,
+		       sizeof(ddev->did));
+	}
+
+	ddev->curr_nfc_dep_pni =
+		DIGITAL_NFC_DEP_PFB_PNI(ddev->curr_nfc_dep_pni + 1);
+
+	chaining_skb = ddev->chaining_skb;
+
+	tmp_skb = digital_send_dep_data_prep(ddev, skb, dep_res, NULL);
+	if (IS_ERR(tmp_skb))
+		return PTR_ERR(tmp_skb);
+
+	digital_skb_push_dep_sod(ddev, tmp_skb);
+
+	ddev->skb_add_crc(tmp_skb);
+
+	ddev->saved_skb = skb_get(tmp_skb);
+	ddev->saved_skb_len = tmp_skb->len;
+
+	rc = digital_tg_send_cmd(ddev, tmp_skb, 1500, digital_tg_recv_dep_req,
+				 NULL);
+	if (rc) {
+		if (tmp_skb != skb)
+			kfree_skb(tmp_skb);
+
+		kfree_skb(chaining_skb);
+		ddev->chaining_skb = NULL;
 
-	return digital_tg_send_cmd(ddev, skb, 1500, digital_tg_recv_dep_req,
-				   NULL);
+		kfree_skb(ddev->saved_skb);
+		ddev->saved_skb = NULL;
+	}
+
+	return rc;
 }
 
 static void digital_tg_send_psl_res_complete(struct nfc_digital_dev *ddev,
@@ -632,9 +1294,10 @@ static int digital_tg_send_psl_res(struct nfc_digital_dev *ddev, u8 did,
 
 	ddev->skb_add_crc(skb);
 
+	ddev->curr_nfc_dep_pni = 0;
+
 	rc = digital_tg_send_cmd(ddev, skb, 0, digital_tg_send_psl_res_complete,
 				 (void *)(unsigned long)rf_tech);
-
 	if (rc)
 		kfree_skb(skb);
 
@@ -647,7 +1310,7 @@ static void digital_tg_recv_psl_req(struct nfc_digital_dev *ddev, void *arg,
 	int rc;
 	struct digital_psl_req *psl_req;
 	u8 rf_tech;
-	u8 dsi;
+	u8 dsi, payload_size, payload_bits;
 
 	if (IS_ERR(resp)) {
 		rc = PTR_ERR(resp);
@@ -692,6 +1355,18 @@ static void digital_tg_recv_psl_req(struct nfc_digital_dev *ddev, void *arg,
 		goto exit;
 	}
 
+	payload_bits = DIGITAL_PAYLOAD_FSL_TO_BITS(psl_req->fsl);
+	payload_size = digital_payload_bits_to_size(payload_bits);
+
+	if (!payload_size || (payload_size > min(ddev->local_payload_max,
+						 ddev->remote_payload_max))) {
+		rc = -EINVAL;
+		goto exit;
+	}
+
+	ddev->local_payload_max = payload_size;
+	ddev->remote_payload_max = payload_size;
+
 	rc = digital_tg_send_psl_res(ddev, psl_req->did, rf_tech);
 
 exit:
@@ -712,6 +1387,8 @@ static void digital_tg_send_atr_res_complete(struct nfc_digital_dev *ddev,
 	if (resp->data[0] == DIGITAL_NFC_DEP_NFCA_SOD_SB)
 		offset++;
 
+	ddev->atn_count = 0;
+
 	if (resp->data[offset] == DIGITAL_CMD_PSL_REQ)
 		digital_tg_recv_psl_req(ddev, arg, resp);
 	else
@@ -723,7 +1400,7 @@ static int digital_tg_send_atr_res(struct nfc_digital_dev *ddev,
 {
 	struct digital_atr_res *atr_res;
 	struct sk_buff *skb;
-	u8 *gb;
+	u8 *gb, payload_bits;
 	size_t gb_len;
 	int rc;
 
@@ -744,7 +1421,11 @@ static int digital_tg_send_atr_res(struct nfc_digital_dev *ddev,
 	atr_res->cmd = DIGITAL_CMD_ATR_RES;
 	memcpy(atr_res->nfcid3, atr_req->nfcid3, sizeof(atr_req->nfcid3));
 	atr_res->to = 8;
-	atr_res->pp = DIGITAL_LR_BITS_PAYLOAD_SIZE_254B;
+
+	ddev->local_payload_max = DIGITAL_PAYLOAD_SIZE_MAX;
+	payload_bits = digital_payload_size_to_bits(ddev->local_payload_max);
+	atr_res->pp = DIGITAL_PAYLOAD_BITS_TO_PP(payload_bits);
+
 	if (gb_len) {
 		skb_put(skb, gb_len);
 
@@ -756,12 +1437,12 @@ static int digital_tg_send_atr_res(struct nfc_digital_dev *ddev,
 
 	ddev->skb_add_crc(skb);
 
+	ddev->curr_nfc_dep_pni = 0;
+
 	rc = digital_tg_send_cmd(ddev, skb, 999,
 				 digital_tg_send_atr_res_complete, NULL);
-	if (rc) {
+	if (rc)
 		kfree_skb(skb);
-		return rc;
-	}
 
 	return rc;
 }
@@ -772,7 +1453,7 @@ void digital_tg_recv_atr_req(struct nfc_digital_dev *ddev, void *arg,
 	int rc;
 	struct digital_atr_req *atr_req;
 	size_t gb_len, min_size;
-	u8 poll_tech_count;
+	u8 poll_tech_count, payload_bits;
 
 	if (IS_ERR(resp)) {
 		rc = PTR_ERR(resp);
@@ -815,11 +1496,22 @@ void digital_tg_recv_atr_req(struct nfc_digital_dev *ddev, void *arg,
 	atr_req = (struct digital_atr_req *)resp->data;
 
 	if (atr_req->dir != DIGITAL_NFC_DEP_FRAME_DIR_OUT ||
-	    atr_req->cmd != DIGITAL_CMD_ATR_REQ) {
+	    atr_req->cmd != DIGITAL_CMD_ATR_REQ ||
+	    atr_req->did > DIGITAL_DID_MAX) {
 		rc = -EINVAL;
 		goto exit;
 	}
 
+	payload_bits = DIGITAL_PAYLOAD_PP_TO_BITS(atr_req->pp);
+	ddev->remote_payload_max = digital_payload_bits_to_size(payload_bits);
+
+	if (!ddev->remote_payload_max) {
+		rc = -EINVAL;
+		goto exit;
+	}
+
+	ddev->did = atr_req->did;
+
 	rc = digital_tg_configure_hw(ddev, NFC_DIGITAL_CONFIG_FRAMING,
 				     NFC_DIGITAL_FRAMING_NFC_DEP_ACTIVATED);
 	if (rc)
diff --git a/net/nfc/hci/command.c b/net/nfc/hci/command.c
index 677d24bb70f8..844673cb7c18 100644
--- a/net/nfc/hci/command.c
+++ b/net/nfc/hci/command.c
@@ -116,23 +116,6 @@ int nfc_hci_send_event(struct nfc_hci_dev *hdev, u8 gate, u8 event,
 }
 EXPORT_SYMBOL(nfc_hci_send_event);
 
-int nfc_hci_send_response(struct nfc_hci_dev *hdev, u8 gate, u8 response,
-			  const u8 *param, size_t param_len)
-{
-	u8 pipe;
-
-	pr_debug("\n");
-
-	pipe = hdev->gate2pipe[gate];
-	if (pipe == NFC_HCI_INVALID_PIPE)
-		return -EADDRNOTAVAIL;
-
-	return nfc_hci_hcp_message_tx(hdev, pipe, NFC_HCI_HCP_RESPONSE,
-				      response, param, param_len, NULL, NULL,
-				      0);
-}
-EXPORT_SYMBOL(nfc_hci_send_response);
-
 /*
  * Execute an hci command sent to gate.
  * skb will contain response data if success. skb can be NULL if you are not
@@ -331,7 +314,7 @@ int nfc_hci_disconnect_all_gates(struct nfc_hci_dev *hdev)
 	if (r < 0)
 		return r;
 
-	memset(hdev->gate2pipe, NFC_HCI_INVALID_PIPE, sizeof(hdev->gate2pipe));
+	nfc_hci_reset_pipes(hdev);
 
 	return 0;
 }
@@ -345,6 +328,9 @@ int nfc_hci_connect_gate(struct nfc_hci_dev *hdev, u8 dest_host, u8 dest_gate,
 
 	pr_debug("\n");
 
+	if (pipe == NFC_HCI_DO_NOT_CREATE_PIPE)
+		return 0;
+
 	if (hdev->gate2pipe[dest_gate] != NFC_HCI_INVALID_PIPE)
 		return -EADDRINUSE;
 
@@ -377,6 +363,8 @@ open_pipe:
 		return r;
 	}
 
+	hdev->pipes[pipe].gate = dest_gate;
+	hdev->pipes[pipe].dest_host = dest_host;
 	hdev->gate2pipe[dest_gate] = pipe;
 
 	return 0;
diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c
index 117708263ced..6e061da2258a 100644
--- a/net/nfc/hci/core.c
+++ b/net/nfc/hci/core.c
@@ -46,6 +46,32 @@ int nfc_hci_result_to_errno(u8 result)
 }
 EXPORT_SYMBOL(nfc_hci_result_to_errno);
 
+void nfc_hci_reset_pipes(struct nfc_hci_dev *hdev)
+{
+	int i = 0;
+
+	for (i = 0; i < NFC_HCI_MAX_PIPES; i++) {
+		hdev->pipes[i].gate = NFC_HCI_INVALID_GATE;
+		hdev->pipes[i].dest_host = NFC_HCI_INVALID_HOST;
+	}
+	memset(hdev->gate2pipe, NFC_HCI_INVALID_PIPE, sizeof(hdev->gate2pipe));
+}
+EXPORT_SYMBOL(nfc_hci_reset_pipes);
+
+void nfc_hci_reset_pipes_per_host(struct nfc_hci_dev *hdev, u8 host)
+{
+	int i = 0;
+
+	for (i = 0; i < NFC_HCI_MAX_PIPES; i++) {
+		if (hdev->pipes[i].dest_host != host)
+			continue;
+
+		hdev->pipes[i].gate = NFC_HCI_INVALID_GATE;
+		hdev->pipes[i].dest_host = NFC_HCI_INVALID_HOST;
+	}
+}
+EXPORT_SYMBOL(nfc_hci_reset_pipes_per_host);
+
 static void nfc_hci_msg_tx_work(struct work_struct *work)
 {
 	struct nfc_hci_dev *hdev = container_of(work, struct nfc_hci_dev,
@@ -167,6 +193,69 @@ exit:
 void nfc_hci_cmd_received(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd,
 			  struct sk_buff *skb)
 {
+	u8 gate = hdev->pipes[pipe].gate;
+	u8 status = NFC_HCI_ANY_OK;
+	struct hci_create_pipe_resp *create_info;
+	struct hci_delete_pipe_noti *delete_info;
+	struct hci_all_pipe_cleared_noti *cleared_info;
+
+	pr_debug("from gate %x pipe %x cmd %x\n", gate, pipe, cmd);
+
+	switch (cmd) {
+	case NFC_HCI_ADM_NOTIFY_PIPE_CREATED:
+		if (skb->len != 5) {
+			status = NFC_HCI_ANY_E_NOK;
+			goto exit;
+		}
+		create_info = (struct hci_create_pipe_resp *)skb->data;
+
+		/* Save the new created pipe and bind with local gate,
+		 * the description for skb->data[3] is destination gate id
+		 * but since we received this cmd from host controller, we
+		 * are the destination and it is our local gate
+		 */
+		hdev->gate2pipe[create_info->dest_gate] = create_info->pipe;
+		hdev->pipes[create_info->pipe].gate = create_info->dest_gate;
+		hdev->pipes[create_info->pipe].dest_host =
+							create_info->src_host;
+		break;
+	case NFC_HCI_ANY_OPEN_PIPE:
+		if (gate == NFC_HCI_INVALID_GATE) {
+			status = NFC_HCI_ANY_E_NOK;
+			goto exit;
+		}
+		break;
+	case NFC_HCI_ADM_NOTIFY_PIPE_DELETED:
+		if (skb->len != 1) {
+			status = NFC_HCI_ANY_E_NOK;
+			goto exit;
+		}
+		delete_info = (struct hci_delete_pipe_noti *)skb->data;
+
+		hdev->pipes[delete_info->pipe].gate = NFC_HCI_INVALID_GATE;
+		hdev->pipes[delete_info->pipe].dest_host = NFC_HCI_INVALID_HOST;
+		break;
+	case NFC_HCI_ADM_NOTIFY_ALL_PIPE_CLEARED:
+		if (skb->len != 1) {
+			status = NFC_HCI_ANY_E_NOK;
+			goto exit;
+		}
+		cleared_info = (struct hci_all_pipe_cleared_noti *)skb->data;
+
+		nfc_hci_reset_pipes_per_host(hdev, cleared_info->host);
+		break;
+	default:
+		pr_info("Discarded unknown cmd %x to gate %x\n", cmd, gate);
+		break;
+	}
+
+	if (hdev->ops->cmd_received)
+		hdev->ops->cmd_received(hdev, pipe, cmd, skb);
+
+exit:
+	nfc_hci_hcp_message_tx(hdev, pipe, NFC_HCI_HCP_RESPONSE,
+			       status, NULL, 0, NULL, NULL, 0);
+
 	kfree_skb(skb);
 }
 
@@ -288,15 +377,15 @@ void nfc_hci_event_received(struct nfc_hci_dev *hdev, u8 pipe, u8 event,
 			    struct sk_buff *skb)
 {
 	int r = 0;
-	u8 gate = nfc_hci_pipe2gate(hdev, pipe);
+	u8 gate = hdev->pipes[pipe].gate;
 
-	if (gate == 0xff) {
+	if (gate == NFC_HCI_INVALID_GATE) {
 		pr_err("Discarded event %x to unopened pipe %x\n", event, pipe);
 		goto exit;
 	}
 
 	if (hdev->ops->event_received) {
-		r = hdev->ops->event_received(hdev, gate, event, skb);
+		r = hdev->ops->event_received(hdev, pipe, event, skb);
 		if (r <= 0)
 			goto exit_noskb;
 	}
@@ -531,7 +620,7 @@ static int hci_dev_down(struct nfc_dev *nfc_dev)
 	if (hdev->ops->close)
 		hdev->ops->close(hdev);
 
-	memset(hdev->gate2pipe, NFC_HCI_INVALID_PIPE, sizeof(hdev->gate2pipe));
+	nfc_hci_reset_pipes(hdev);
 
 	return 0;
 }
@@ -717,6 +806,19 @@ static int hci_disable_se(struct nfc_dev *nfc_dev, u32 se_idx)
 	return 0;
 }
 
+static int hci_se_io(struct nfc_dev *nfc_dev, u32 se_idx,
+		     u8 *apdu, size_t apdu_length,
+		     se_io_cb_t cb, void *cb_context)
+{
+	struct nfc_hci_dev *hdev = nfc_get_drvdata(nfc_dev);
+
+	if (hdev->ops->se_io)
+		return hdev->ops->se_io(hdev, se_idx, apdu,
+					apdu_length, cb, cb_context);
+
+	return 0;
+}
+
 static void nfc_hci_failure(struct nfc_hci_dev *hdev, int err)
 {
 	mutex_lock(&hdev->msg_tx_mutex);
@@ -830,6 +932,7 @@ static struct nfc_ops hci_nfc_ops = {
 	.discover_se = hci_discover_se,
 	.enable_se = hci_enable_se,
 	.disable_se = hci_disable_se,
+	.se_io = hci_se_io,
 };
 
 struct nfc_hci_dev *nfc_hci_allocate_device(struct nfc_hci_ops *ops,
@@ -876,7 +979,7 @@ struct nfc_hci_dev *nfc_hci_allocate_device(struct nfc_hci_ops *ops,
 
 	nfc_set_drvdata(hdev->ndev, hdev);
 
-	memset(hdev->gate2pipe, NFC_HCI_INVALID_PIPE, sizeof(hdev->gate2pipe));
+	nfc_hci_reset_pipes(hdev);
 
 	hdev->quirks = quirks;
 
diff --git a/net/nfc/hci/hci.h b/net/nfc/hci/hci.h
index c3d2e2c1394c..ab4c8e80b1ad 100644
--- a/net/nfc/hci/hci.h
+++ b/net/nfc/hci/hci.h
@@ -65,6 +65,14 @@ struct hci_create_pipe_resp {
 	u8 pipe;
 } __packed;
 
+struct hci_delete_pipe_noti {
+	u8 pipe;
+} __packed;
+
+struct hci_all_pipe_cleared_noti {
+	u8 host;
+} __packed;
+
 #define NFC_HCI_FRAGMENT	0x7f
 
 #define HCP_HEADER(type, instr) ((((type) & 0x03) << 6) | ((instr) & 0x3f))
@@ -77,8 +85,6 @@ int nfc_hci_hcp_message_tx(struct nfc_hci_dev *hdev, u8 pipe,
 			   data_exchange_cb_t cb, void *cb_context,
 			   unsigned long completion_delay);
 
-u8 nfc_hci_pipe2gate(struct nfc_hci_dev *hdev, u8 pipe);
-
 void nfc_hci_hcp_message_rx(struct nfc_hci_dev *hdev, u8 pipe, u8 type,
 			    u8 instruction, struct sk_buff *skb);
 
diff --git a/net/nfc/hci/hcp.c b/net/nfc/hci/hcp.c
index e9de1514656e..1fe725d66085 100644
--- a/net/nfc/hci/hcp.c
+++ b/net/nfc/hci/hcp.c
@@ -124,17 +124,6 @@ out_skb_err:
 	return err;
 }
 
-u8 nfc_hci_pipe2gate(struct nfc_hci_dev *hdev, u8 pipe)
-{
-	int gate;
-
-	for (gate = 0; gate < NFC_HCI_MAX_GATES; gate++)
-		if (hdev->gate2pipe[gate] == pipe)
-			return gate;
-
-	return 0xff;
-}
-
 /*
  * Receive hcp message for pipe, with type and cmd.
  * skb contains optional message data only.
diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c
index a3ad69a4c648..3621a902cb6e 100644
--- a/net/nfc/llcp_commands.c
+++ b/net/nfc/llcp_commands.c
@@ -401,7 +401,8 @@ int nfc_llcp_send_connect(struct nfc_llcp_sock *sock)
 	u8 *miux_tlv = NULL, miux_tlv_length;
 	u8 *rw_tlv = NULL, rw_tlv_length, rw;
 	int err;
-	u16 size = 0, miux;
+	u16 size = 0;
+	__be16 miux;
 
 	pr_debug("Sending CONNECT\n");
 
@@ -465,7 +466,8 @@ int nfc_llcp_send_cc(struct nfc_llcp_sock *sock)
 	u8 *miux_tlv = NULL, miux_tlv_length;
 	u8 *rw_tlv = NULL, rw_tlv_length, rw;
 	int err;
-	u16 size = 0, miux;
+	u16 size = 0;
+	__be16 miux;
 
 	pr_debug("Sending CC\n");
 
@@ -665,7 +667,7 @@ int nfc_llcp_send_i_frame(struct nfc_llcp_sock *sock,
 	if (msg_data == NULL)
 		return -ENOMEM;
 
-	if (memcpy_fromiovec(msg_data, msg->msg_iov, len)) {
+	if (memcpy_from_msg(msg_data, msg, len)) {
 		kfree(msg_data);
 		return -EFAULT;
 	}
@@ -731,7 +733,7 @@ int nfc_llcp_send_ui_frame(struct nfc_llcp_sock *sock, u8 ssap, u8 dsap,
 	if (msg_data == NULL)
 		return -ENOMEM;
 
-	if (memcpy_fromiovec(msg_data, msg->msg_iov, len)) {
+	if (memcpy_from_msg(msg_data, msg, len)) {
 		kfree(msg_data);
 		return -EFAULT;
 	}
diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c
index 51e788797317..b18f07ccb504 100644
--- a/net/nfc/llcp_core.c
+++ b/net/nfc/llcp_core.c
@@ -1,5 +1,6 @@
 /*
  * Copyright (C) 2011  Intel Corporation. All rights reserved.
+ * Copyright (C) 2014 Marvell International Ltd.
  *
  * 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
@@ -1511,8 +1512,10 @@ int nfc_llcp_data_received(struct nfc_dev *dev, struct sk_buff *skb)
 	struct nfc_llcp_local *local;
 
 	local = nfc_llcp_find_local(dev);
-	if (local == NULL)
+	if (local == NULL) {
+		kfree_skb(skb);
 		return -ENODEV;
+	}
 
 	__nfc_llcp_recv(local, skb);
 
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index 51f077a92fa9..9578bd6a4f3e 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -524,13 +524,13 @@ static int llcp_sock_getname(struct socket *sock, struct sockaddr *uaddr,
 
 static inline unsigned int llcp_accept_poll(struct sock *parent)
 {
-	struct nfc_llcp_sock *llcp_sock, *n, *parent_sock;
+	struct nfc_llcp_sock *llcp_sock, *parent_sock;
 	struct sock *sk;
 
 	parent_sock = nfc_llcp_sock(parent);
 
-	list_for_each_entry_safe(llcp_sock, n, &parent_sock->accept_queue,
-				 accept_queue) {
+	list_for_each_entry(llcp_sock, &parent_sock->accept_queue,
+			    accept_queue) {
 		sk = &llcp_sock->sk;
 
 		if (sk->sk_state == LLCP_CONNECTED)
@@ -750,8 +750,8 @@ error:
 	return ret;
 }
 
-static int llcp_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
-			     struct msghdr *msg, size_t len)
+static int llcp_sock_sendmsg(struct socket *sock, struct msghdr *msg,
+			     size_t len)
 {
 	struct sock *sk = sock->sk;
 	struct nfc_llcp_sock *llcp_sock = nfc_llcp_sock(sk);
@@ -793,8 +793,8 @@ static int llcp_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 	return nfc_llcp_send_i_frame(llcp_sock, msg, len);
 }
 
-static int llcp_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
-			     struct msghdr *msg, size_t len, int flags)
+static int llcp_sock_recvmsg(struct socket *sock, struct msghdr *msg,
+			     size_t len, int flags)
 {
 	int noblock = flags & MSG_DONTWAIT;
 	struct sock *sk = sock->sk;
@@ -832,7 +832,7 @@ static int llcp_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 	copied = min_t(unsigned int, rlen, len);
 
 	cskb = skb;
-	if (skb_copy_datagram_iovec(cskb, 0, msg->msg_iov, copied)) {
+	if (skb_copy_datagram_msg(cskb, 0, msg, copied)) {
 		if (!(flags & MSG_PEEK))
 			skb_queue_head(&sk->sk_receive_queue, skb);
 		return -EFAULT;
diff --git a/net/nfc/nci/Makefile b/net/nfc/nci/Makefile
index 7aeedc43187d..7ed8949266cc 100644
--- a/net/nfc/nci/Makefile
+++ b/net/nfc/nci/Makefile
@@ -4,6 +4,6 @@
 
 obj-$(CONFIG_NFC_NCI) += nci.o
 
-nci-objs := core.o data.o lib.o ntf.o rsp.o
+nci-objs := core.o data.o lib.o ntf.o rsp.o hci.o
 
 nci-$(CONFIG_NFC_NCI_SPI) += spi.o
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index 90b16cb40058..49ff32106080 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -3,6 +3,7 @@
  *  NFC Controller (NFCC) and a Device Host (DH).
  *
  *  Copyright (C) 2011 Texas Instruments, Inc.
+ *  Copyright (C) 2014 Marvell International Ltd.
  *
  *  Written by Ilan Elias <ilane@ti.com>
  *
@@ -40,10 +41,28 @@
 #include <net/nfc/nci_core.h>
 #include <linux/nfc.h>
 
+struct core_conn_create_data {
+	int length;
+	struct nci_core_conn_create_cmd *cmd;
+};
+
 static void nci_cmd_work(struct work_struct *work);
 static void nci_rx_work(struct work_struct *work);
 static void nci_tx_work(struct work_struct *work);
 
+struct nci_conn_info *nci_get_conn_info_by_conn_id(struct nci_dev *ndev,
+						   int conn_id)
+{
+	struct nci_conn_info *conn_info;
+
+	list_for_each_entry(conn_info, &ndev->conn_info_list, list) {
+		if (conn_info->conn_id == conn_id)
+			return conn_info;
+	}
+
+	return NULL;
+}
+
 /* ---- NCI requests ---- */
 
 void nci_req_complete(struct nci_dev *ndev, int result)
@@ -108,10 +127,10 @@ static int __nci_request(struct nci_dev *ndev,
 	return rc;
 }
 
-static inline int nci_request(struct nci_dev *ndev,
-			      void (*req)(struct nci_dev *ndev,
-					  unsigned long opt),
-			      unsigned long opt, __u32 timeout)
+inline int nci_request(struct nci_dev *ndev,
+		       void (*req)(struct nci_dev *ndev,
+				   unsigned long opt),
+		       unsigned long opt, __u32 timeout)
 {
 	int rc;
 
@@ -196,18 +215,24 @@ static void nci_set_config_req(struct nci_dev *ndev, unsigned long opt)
 	nci_send_cmd(ndev, NCI_OP_CORE_SET_CONFIG_CMD, (3 + param->len), &cmd);
 }
 
+struct nci_rf_discover_param {
+	__u32	im_protocols;
+	__u32	tm_protocols;
+};
+
 static void nci_rf_discover_req(struct nci_dev *ndev, unsigned long opt)
 {
+	struct nci_rf_discover_param *param =
+		(struct nci_rf_discover_param *)opt;
 	struct nci_rf_disc_cmd cmd;
-	__u32 protocols = opt;
 
 	cmd.num_disc_configs = 0;
 
 	if ((cmd.num_disc_configs < NCI_MAX_NUM_RF_CONFIGS) &&
-	    (protocols & NFC_PROTO_JEWEL_MASK ||
-	     protocols & NFC_PROTO_MIFARE_MASK ||
-	     protocols & NFC_PROTO_ISO14443_MASK ||
-	     protocols & NFC_PROTO_NFC_DEP_MASK)) {
+	    (param->im_protocols & NFC_PROTO_JEWEL_MASK ||
+	     param->im_protocols & NFC_PROTO_MIFARE_MASK ||
+	     param->im_protocols & NFC_PROTO_ISO14443_MASK ||
+	     param->im_protocols & NFC_PROTO_NFC_DEP_MASK)) {
 		cmd.disc_configs[cmd.num_disc_configs].rf_tech_and_mode =
 			NCI_NFC_A_PASSIVE_POLL_MODE;
 		cmd.disc_configs[cmd.num_disc_configs].frequency = 1;
@@ -215,7 +240,7 @@ static void nci_rf_discover_req(struct nci_dev *ndev, unsigned long opt)
 	}
 
 	if ((cmd.num_disc_configs < NCI_MAX_NUM_RF_CONFIGS) &&
-	    (protocols & NFC_PROTO_ISO14443_B_MASK)) {
+	    (param->im_protocols & NFC_PROTO_ISO14443_B_MASK)) {
 		cmd.disc_configs[cmd.num_disc_configs].rf_tech_and_mode =
 			NCI_NFC_B_PASSIVE_POLL_MODE;
 		cmd.disc_configs[cmd.num_disc_configs].frequency = 1;
@@ -223,8 +248,8 @@ static void nci_rf_discover_req(struct nci_dev *ndev, unsigned long opt)
 	}
 
 	if ((cmd.num_disc_configs < NCI_MAX_NUM_RF_CONFIGS) &&
-	    (protocols & NFC_PROTO_FELICA_MASK ||
-	     protocols & NFC_PROTO_NFC_DEP_MASK)) {
+	    (param->im_protocols & NFC_PROTO_FELICA_MASK ||
+	     param->im_protocols & NFC_PROTO_NFC_DEP_MASK)) {
 		cmd.disc_configs[cmd.num_disc_configs].rf_tech_and_mode =
 			NCI_NFC_F_PASSIVE_POLL_MODE;
 		cmd.disc_configs[cmd.num_disc_configs].frequency = 1;
@@ -232,13 +257,25 @@ static void nci_rf_discover_req(struct nci_dev *ndev, unsigned long opt)
 	}
 
 	if ((cmd.num_disc_configs < NCI_MAX_NUM_RF_CONFIGS) &&
-	    (protocols & NFC_PROTO_ISO15693_MASK)) {
+	    (param->im_protocols & NFC_PROTO_ISO15693_MASK)) {
 		cmd.disc_configs[cmd.num_disc_configs].rf_tech_and_mode =
 			NCI_NFC_V_PASSIVE_POLL_MODE;
 		cmd.disc_configs[cmd.num_disc_configs].frequency = 1;
 		cmd.num_disc_configs++;
 	}
 
+	if ((cmd.num_disc_configs < NCI_MAX_NUM_RF_CONFIGS - 1) &&
+	    (param->tm_protocols & NFC_PROTO_NFC_DEP_MASK)) {
+		cmd.disc_configs[cmd.num_disc_configs].rf_tech_and_mode =
+			NCI_NFC_A_PASSIVE_LISTEN_MODE;
+		cmd.disc_configs[cmd.num_disc_configs].frequency = 1;
+		cmd.num_disc_configs++;
+		cmd.disc_configs[cmd.num_disc_configs].rf_tech_and_mode =
+			NCI_NFC_F_PASSIVE_LISTEN_MODE;
+		cmd.disc_configs[cmd.num_disc_configs].frequency = 1;
+		cmd.num_disc_configs++;
+	}
+
 	nci_send_cmd(ndev, NCI_OP_RF_DISCOVER_CMD,
 		     (1 + (cmd.num_disc_configs * sizeof(struct disc_config))),
 		     &cmd);
@@ -280,7 +317,7 @@ static void nci_rf_deactivate_req(struct nci_dev *ndev, unsigned long opt)
 {
 	struct nci_rf_deactivate_cmd cmd;
 
-	cmd.type = NCI_DEACTIVATE_TYPE_IDLE_MODE;
+	cmd.type = opt;
 
 	nci_send_cmd(ndev, NCI_OP_RF_DEACTIVATE_CMD,
 		     sizeof(struct nci_rf_deactivate_cmd), &cmd);
@@ -437,10 +474,100 @@ int nci_set_config(struct nci_dev *ndev, __u8 id, size_t len, __u8 *val)
 }
 EXPORT_SYMBOL(nci_set_config);
 
+static void nci_nfcee_discover_req(struct nci_dev *ndev, unsigned long opt)
+{
+	struct nci_nfcee_discover_cmd cmd;
+	__u8 action = opt;
+
+	cmd.discovery_action = action;
+
+	nci_send_cmd(ndev, NCI_OP_NFCEE_DISCOVER_CMD, 1, &cmd);
+}
+
+int nci_nfcee_discover(struct nci_dev *ndev, u8 action)
+{
+	return nci_request(ndev, nci_nfcee_discover_req, action,
+				msecs_to_jiffies(NCI_CMD_TIMEOUT));
+}
+EXPORT_SYMBOL(nci_nfcee_discover);
+
+static void nci_nfcee_mode_set_req(struct nci_dev *ndev, unsigned long opt)
+{
+	struct nci_nfcee_mode_set_cmd *cmd =
+					(struct nci_nfcee_mode_set_cmd *)opt;
+
+	nci_send_cmd(ndev, NCI_OP_NFCEE_MODE_SET_CMD,
+		     sizeof(struct nci_nfcee_mode_set_cmd), cmd);
+}
+
+int nci_nfcee_mode_set(struct nci_dev *ndev, u8 nfcee_id, u8 nfcee_mode)
+{
+	struct nci_nfcee_mode_set_cmd cmd;
+
+	cmd.nfcee_id = nfcee_id;
+	cmd.nfcee_mode = nfcee_mode;
+
+	return nci_request(ndev, nci_nfcee_mode_set_req, (unsigned long)&cmd,
+			   msecs_to_jiffies(NCI_CMD_TIMEOUT));
+}
+EXPORT_SYMBOL(nci_nfcee_mode_set);
+
+static void nci_core_conn_create_req(struct nci_dev *ndev, unsigned long opt)
+{
+	struct core_conn_create_data *data =
+					(struct core_conn_create_data *)opt;
+
+	nci_send_cmd(ndev, NCI_OP_CORE_CONN_CREATE_CMD, data->length, data->cmd);
+}
+
+int nci_core_conn_create(struct nci_dev *ndev, u8 destination_type,
+			 u8 number_destination_params,
+			 size_t params_len,
+			 struct core_conn_create_dest_spec_params *params)
+{
+	int r;
+	struct nci_core_conn_create_cmd *cmd;
+	struct core_conn_create_data data;
+
+	data.length = params_len + sizeof(struct nci_core_conn_create_cmd);
+	cmd = kzalloc(data.length, GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->destination_type = destination_type;
+	cmd->number_destination_params = number_destination_params;
+	memcpy(cmd->params, params, params_len);
+
+	data.cmd = cmd;
+	ndev->cur_id = params->value[DEST_SPEC_PARAMS_ID_INDEX];
+
+	r = __nci_request(ndev, nci_core_conn_create_req,
+			  (unsigned long)&data,
+			  msecs_to_jiffies(NCI_CMD_TIMEOUT));
+	kfree(cmd);
+	return r;
+}
+EXPORT_SYMBOL(nci_core_conn_create);
+
+static void nci_core_conn_close_req(struct nci_dev *ndev, unsigned long opt)
+{
+	__u8 conn_id = opt;
+
+	nci_send_cmd(ndev, NCI_OP_CORE_CONN_CLOSE_CMD, 1, &conn_id);
+}
+
+int nci_core_conn_close(struct nci_dev *ndev, u8 conn_id)
+{
+	return nci_request(ndev, nci_core_conn_close_req, conn_id,
+				msecs_to_jiffies(NCI_CMD_TIMEOUT));
+}
+EXPORT_SYMBOL(nci_core_conn_close);
+
 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;
+	int rc;
 
 	param.val = nfc_get_local_general_bytes(nfc_dev, &param.len);
 	if ((param.val == NULL) || (param.len == 0))
@@ -451,14 +578,45 @@ static int nci_set_local_general_bytes(struct nfc_dev *nfc_dev)
 
 	param.id = NCI_PN_ATR_REQ_GEN_BYTES;
 
+	rc = nci_request(ndev, nci_set_config_req, (unsigned long)&param,
+			 msecs_to_jiffies(NCI_SET_CONFIG_TIMEOUT));
+	if (rc)
+		return rc;
+
+	param.id = NCI_LN_ATR_RES_GEN_BYTES;
+
 	return nci_request(ndev, nci_set_config_req, (unsigned long)&param,
 			   msecs_to_jiffies(NCI_SET_CONFIG_TIMEOUT));
 }
 
+static int nci_set_listen_parameters(struct nfc_dev *nfc_dev)
+{
+	struct nci_dev *ndev = nfc_get_drvdata(nfc_dev);
+	int rc;
+	__u8 val;
+
+	val = NCI_LA_SEL_INFO_NFC_DEP_MASK;
+
+	rc = nci_set_config(ndev, NCI_LA_SEL_INFO, 1, &val);
+	if (rc)
+		return rc;
+
+	val = NCI_LF_PROTOCOL_TYPE_NFC_DEP_MASK;
+
+	rc = nci_set_config(ndev, NCI_LF_PROTOCOL_TYPE, 1, &val);
+	if (rc)
+		return rc;
+
+	val = NCI_LF_CON_BITR_F_212 | NCI_LF_CON_BITR_F_424;
+
+	return nci_set_config(ndev, NCI_LF_CON_BITR_F, 1, &val);
+}
+
 static int nci_start_poll(struct nfc_dev *nfc_dev,
 			  __u32 im_protocols, __u32 tm_protocols)
 {
 	struct nci_dev *ndev = nfc_get_drvdata(nfc_dev);
+	struct nci_rf_discover_param param;
 	int rc;
 
 	if ((atomic_read(&ndev->state) == NCI_DISCOVERY) ||
@@ -476,13 +634,14 @@ static int nci_start_poll(struct nfc_dev *nfc_dev,
 	    (atomic_read(&ndev->state) == NCI_POLL_ACTIVE)) {
 		pr_debug("target active or w4 select, implicitly deactivate\n");
 
-		rc = nci_request(ndev, nci_rf_deactivate_req, 0,
+		rc = nci_request(ndev, nci_rf_deactivate_req,
+				 NCI_DEACTIVATE_TYPE_IDLE_MODE,
 				 msecs_to_jiffies(NCI_RF_DEACTIVATE_TIMEOUT));
 		if (rc)
 			return -EBUSY;
 	}
 
-	if (im_protocols & NFC_PROTO_NFC_DEP_MASK) {
+	if ((im_protocols | tm_protocols) & NFC_PROTO_NFC_DEP_MASK) {
 		rc = nci_set_local_general_bytes(nfc_dev);
 		if (rc) {
 			pr_err("failed to set local general bytes\n");
@@ -490,7 +649,15 @@ static int nci_start_poll(struct nfc_dev *nfc_dev,
 		}
 	}
 
-	rc = nci_request(ndev, nci_rf_discover_req, im_protocols,
+	if (tm_protocols & NFC_PROTO_NFC_DEP_MASK) {
+		rc = nci_set_listen_parameters(nfc_dev);
+		if (rc)
+			pr_err("failed to set listen parameters\n");
+	}
+
+	param.im_protocols = im_protocols;
+	param.tm_protocols = tm_protocols;
+	rc = nci_request(ndev, nci_rf_discover_req, (unsigned long)&param,
 			 msecs_to_jiffies(NCI_RF_DISC_TIMEOUT));
 
 	if (!rc)
@@ -509,7 +676,7 @@ static void nci_stop_poll(struct nfc_dev *nfc_dev)
 		return;
 	}
 
-	nci_request(ndev, nci_rf_deactivate_req, 0,
+	nci_request(ndev, nci_rf_deactivate_req, NCI_DEACTIVATE_TYPE_IDLE_MODE,
 		    msecs_to_jiffies(NCI_RF_DEACTIVATE_TIMEOUT));
 }
 
@@ -594,7 +761,8 @@ static void nci_deactivate_target(struct nfc_dev *nfc_dev,
 	ndev->target_active_prot = 0;
 
 	if (atomic_read(&ndev->state) == NCI_POLL_ACTIVE) {
-		nci_request(ndev, nci_rf_deactivate_req, 0,
+		nci_request(ndev, nci_rf_deactivate_req,
+			    NCI_DEACTIVATE_TYPE_SLEEP_MODE,
 			    msecs_to_jiffies(NCI_RF_DEACTIVATE_TIMEOUT));
 	}
 }
@@ -622,9 +790,24 @@ static int nci_dep_link_up(struct nfc_dev *nfc_dev, struct nfc_target *target,
 
 static int nci_dep_link_down(struct nfc_dev *nfc_dev)
 {
+	struct nci_dev *ndev = nfc_get_drvdata(nfc_dev);
+	int rc;
+
 	pr_debug("entry\n");
 
-	nci_deactivate_target(nfc_dev, NULL);
+	if (nfc_dev->rf_mode == NFC_RF_INITIATOR) {
+		nci_deactivate_target(nfc_dev, NULL);
+	} else {
+		if (atomic_read(&ndev->state) == NCI_LISTEN_ACTIVE ||
+		    atomic_read(&ndev->state) == NCI_DISCOVERY) {
+			nci_request(ndev, nci_rf_deactivate_req, 0,
+				msecs_to_jiffies(NCI_RF_DEACTIVATE_TIMEOUT));
+		}
+
+		rc = nfc_tm_deactivated(nfc_dev);
+		if (rc)
+			pr_err("error when signaling tm deactivation\n");
+	}
 
 	return 0;
 }
@@ -636,6 +819,11 @@ static int nci_transceive(struct nfc_dev *nfc_dev, struct nfc_target *target,
 {
 	struct nci_dev *ndev = nfc_get_drvdata(nfc_dev);
 	int rc;
+	struct nci_conn_info    *conn_info;
+
+	conn_info = ndev->rf_conn_info;
+	if (!conn_info)
+		return -EPROTO;
 
 	pr_debug("target_idx %d, len %d\n", target->idx, skb->len);
 
@@ -648,8 +836,8 @@ static int nci_transceive(struct nfc_dev *nfc_dev, struct nfc_target *target,
 		return -EBUSY;
 
 	/* store cb and context to be used on receiving data */
-	ndev->data_exchange_cb = cb;
-	ndev->data_exchange_cb_context = cb_context;
+	conn_info->data_exchange_cb = cb;
+	conn_info->data_exchange_cb_context = cb_context;
 
 	rc = nci_send_data(ndev, NCI_STATIC_RF_CONN_ID, skb);
 	if (rc)
@@ -658,21 +846,77 @@ static int nci_transceive(struct nfc_dev *nfc_dev, struct nfc_target *target,
 	return rc;
 }
 
+static int nci_tm_send(struct nfc_dev *nfc_dev, struct sk_buff *skb)
+{
+	struct nci_dev *ndev = nfc_get_drvdata(nfc_dev);
+	int rc;
+
+	rc = nci_send_data(ndev, NCI_STATIC_RF_CONN_ID, skb);
+	if (rc)
+		pr_err("unable to send data\n");
+
+	return rc;
+}
+
 static int nci_enable_se(struct nfc_dev *nfc_dev, u32 se_idx)
 {
+	struct nci_dev *ndev = nfc_get_drvdata(nfc_dev);
+
+	if (ndev->ops->enable_se)
+		return ndev->ops->enable_se(ndev, se_idx);
+
 	return 0;
 }
 
 static int nci_disable_se(struct nfc_dev *nfc_dev, u32 se_idx)
 {
+	struct nci_dev *ndev = nfc_get_drvdata(nfc_dev);
+
+	if (ndev->ops->disable_se)
+		return ndev->ops->disable_se(ndev, se_idx);
+
 	return 0;
 }
 
 static int nci_discover_se(struct nfc_dev *nfc_dev)
 {
+	int r;
+	struct nci_dev *ndev = nfc_get_drvdata(nfc_dev);
+
+	if (ndev->ops->discover_se) {
+		r = nci_nfcee_discover(ndev, NCI_NFCEE_DISCOVERY_ACTION_ENABLE);
+		if (r != NCI_STATUS_OK)
+			return -EPROTO;
+
+		return ndev->ops->discover_se(ndev);
+	}
+
+	return 0;
+}
+
+static int nci_se_io(struct nfc_dev *nfc_dev, u32 se_idx,
+		     u8 *apdu, size_t apdu_length,
+		     se_io_cb_t cb, void *cb_context)
+{
+	struct nci_dev *ndev = nfc_get_drvdata(nfc_dev);
+
+	if (ndev->ops->se_io)
+		return ndev->ops->se_io(ndev, se_idx, apdu,
+				apdu_length, cb, cb_context);
+
 	return 0;
 }
 
+static int nci_fw_download(struct nfc_dev *nfc_dev, const char *firmware_name)
+{
+	struct nci_dev *ndev = nfc_get_drvdata(nfc_dev);
+
+	if (!ndev->ops->fw_download)
+		return -ENOTSUPP;
+
+	return ndev->ops->fw_download(ndev, firmware_name);
+}
+
 static struct nfc_ops nci_nfc_ops = {
 	.dev_up = nci_dev_up,
 	.dev_down = nci_dev_down,
@@ -683,13 +927,15 @@ static struct nfc_ops nci_nfc_ops = {
 	.activate_target = nci_activate_target,
 	.deactivate_target = nci_deactivate_target,
 	.im_transceive = nci_transceive,
+	.tm_send = nci_tm_send,
 	.enable_se = nci_enable_se,
 	.disable_se = nci_disable_se,
 	.discover_se = nci_discover_se,
+	.se_io = nci_se_io,
+	.fw_download = nci_fw_download,
 };
 
 /* ---- Interface to NCI drivers ---- */
-
 /**
  * nci_allocate_device - allocate a new nci device
  *
@@ -724,13 +970,20 @@ struct nci_dev *nci_allocate_device(struct nci_ops *ops,
 					    tx_headroom + NCI_DATA_HDR_SIZE,
 					    tx_tailroom);
 	if (!ndev->nfc_dev)
-		goto free_exit;
+		goto free_nci;
+
+	ndev->hci_dev = nci_hci_allocate(ndev);
+	if (!ndev->hci_dev)
+		goto free_nfc;
 
 	nfc_set_drvdata(ndev->nfc_dev, ndev);
 
 	return ndev;
 
-free_exit:
+free_nfc:
+	kfree(ndev->nfc_dev);
+
+free_nci:
 	kfree(ndev);
 	return NULL;
 }
@@ -795,6 +1048,7 @@ int nci_register_device(struct nci_dev *ndev)
 		    (unsigned long) ndev);
 
 	mutex_init(&ndev->req_lock);
+	INIT_LIST_HEAD(&ndev->conn_info_list);
 
 	rc = nfc_register_device(ndev->nfc_dev);
 	if (rc)
@@ -820,12 +1074,19 @@ EXPORT_SYMBOL(nci_register_device);
  */
 void nci_unregister_device(struct nci_dev *ndev)
 {
+	struct nci_conn_info    *conn_info, *n;
+
 	nci_close_device(ndev);
 
 	destroy_workqueue(ndev->cmd_wq);
 	destroy_workqueue(ndev->rx_wq);
 	destroy_workqueue(ndev->tx_wq);
 
+	list_for_each_entry_safe(conn_info, n, &ndev->conn_info_list, list) {
+		list_del(&conn_info->list);
+		/* conn_info is allocated with devm_kzalloc */
+	}
+
 	nfc_unregister_device(ndev->nfc_dev);
 }
 EXPORT_SYMBOL(nci_unregister_device);
@@ -909,20 +1170,25 @@ int nci_send_cmd(struct nci_dev *ndev, __u16 opcode, __u8 plen, void *payload)
 static void nci_tx_work(struct work_struct *work)
 {
 	struct nci_dev *ndev = container_of(work, struct nci_dev, tx_work);
+	struct nci_conn_info    *conn_info;
 	struct sk_buff *skb;
 
-	pr_debug("credits_cnt %d\n", atomic_read(&ndev->credits_cnt));
+	conn_info = nci_get_conn_info_by_conn_id(ndev, ndev->cur_conn_id);
+	if (!conn_info)
+		return;
+
+	pr_debug("credits_cnt %d\n", atomic_read(&conn_info->credits_cnt));
 
 	/* Send queued tx data */
-	while (atomic_read(&ndev->credits_cnt)) {
+	while (atomic_read(&conn_info->credits_cnt)) {
 		skb = skb_dequeue(&ndev->tx_q);
 		if (!skb)
 			return;
 
 		/* Check if data flow control is used */
-		if (atomic_read(&ndev->credits_cnt) !=
+		if (atomic_read(&conn_info->credits_cnt) !=
 		    NCI_DATA_FLOW_CONTROL_NOT_USED)
-			atomic_dec(&ndev->credits_cnt);
+			atomic_dec(&conn_info->credits_cnt);
 
 		pr_debug("NCI TX: MT=data, PBF=%d, conn_id=%d, plen=%d\n",
 			 nci_pbf(skb->data),
@@ -974,7 +1240,9 @@ static void nci_rx_work(struct work_struct *work)
 	if (test_bit(NCI_DATA_EXCHANGE_TO, &ndev->flags)) {
 		/* complete the data exchange transaction, if exists */
 		if (test_bit(NCI_DATA_EXCHANGE, &ndev->flags))
-			nci_data_exchange_complete(ndev, NULL, -ETIMEDOUT);
+			nci_data_exchange_complete(ndev, NULL,
+						   ndev->cur_conn_id,
+						   -ETIMEDOUT);
 
 		clear_bit(NCI_DATA_EXCHANGE_TO, &ndev->flags);
 	}
diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c
index 427ef2c7ab68..566466d90048 100644
--- a/net/nfc/nci/data.c
+++ b/net/nfc/nci/data.c
@@ -3,6 +3,7 @@
  *  NFC Controller (NFCC) and a Device Host (DH).
  *
  *  Copyright (C) 2011 Texas Instruments, Inc.
+ *  Copyright (C) 2014 Marvell International Ltd.
  *
  *  Written by Ilan Elias <ilane@ti.com>
  *
@@ -35,10 +36,20 @@
 
 /* Complete data exchange transaction and forward skb to nfc core */
 void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb,
-				int err)
+				__u8 conn_id, int err)
 {
-	data_exchange_cb_t cb = ndev->data_exchange_cb;
-	void *cb_context = ndev->data_exchange_cb_context;
+	struct nci_conn_info    *conn_info;
+	data_exchange_cb_t cb;
+	void *cb_context;
+
+	conn_info = nci_get_conn_info_by_conn_id(ndev, conn_id);
+	if (!conn_info) {
+		kfree_skb(skb);
+		goto exit;
+	}
+
+	cb = conn_info->data_exchange_cb;
+	cb_context = conn_info->data_exchange_cb_context;
 
 	pr_debug("len %d, err %d\n", skb ? skb->len : 0, err);
 
@@ -47,9 +58,6 @@ void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb,
 	clear_bit(NCI_DATA_EXCHANGE_TO, &ndev->flags);
 
 	if (cb) {
-		ndev->data_exchange_cb = NULL;
-		ndev->data_exchange_cb_context = NULL;
-
 		/* forward skb to nfc core */
 		cb(cb_context, skb, err);
 	} else if (skb) {
@@ -59,6 +67,7 @@ void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb,
 		kfree_skb(skb);
 	}
 
+exit:
 	clear_bit(NCI_DATA_EXCHANGE, &ndev->flags);
 }
 
@@ -84,6 +93,7 @@ static inline void nci_push_data_hdr(struct nci_dev *ndev,
 static int nci_queue_tx_data_frags(struct nci_dev *ndev,
 				   __u8 conn_id,
 				   struct sk_buff *skb) {
+	struct nci_conn_info    *conn_info;
 	int total_len = skb->len;
 	unsigned char *data = skb->data;
 	unsigned long flags;
@@ -94,11 +104,17 @@ static int nci_queue_tx_data_frags(struct nci_dev *ndev,
 
 	pr_debug("conn_id 0x%x, total_len %d\n", conn_id, total_len);
 
+	conn_info = nci_get_conn_info_by_conn_id(ndev, conn_id);
+	if (!conn_info) {
+		rc = -EPROTO;
+		goto free_exit;
+	}
+
 	__skb_queue_head_init(&frags_q);
 
 	while (total_len) {
 		frag_len =
-			min_t(int, total_len, ndev->max_data_pkt_payload_size);
+			min_t(int, total_len, conn_info->max_pkt_payload_len);
 
 		skb_frag = nci_skb_alloc(ndev,
 					 (NCI_DATA_HDR_SIZE + frag_len),
@@ -150,12 +166,19 @@ exit:
 /* Send NCI data */
 int nci_send_data(struct nci_dev *ndev, __u8 conn_id, struct sk_buff *skb)
 {
+	struct nci_conn_info    *conn_info;
 	int rc = 0;
 
 	pr_debug("conn_id 0x%x, plen %d\n", conn_id, skb->len);
 
+	conn_info = nci_get_conn_info_by_conn_id(ndev, conn_id);
+	if (!conn_info) {
+		rc = -EPROTO;
+		goto free_exit;
+	}
+
 	/* check if the packet need to be fragmented */
-	if (skb->len <= ndev->max_data_pkt_payload_size) {
+	if (skb->len <= conn_info->max_pkt_payload_len) {
 		/* no need to fragment packet */
 		nci_push_data_hdr(ndev, conn_id, skb, NCI_PBF_LAST);
 
@@ -169,6 +192,7 @@ int nci_send_data(struct nci_dev *ndev, __u8 conn_id, struct sk_buff *skb)
 		}
 	}
 
+	ndev->cur_conn_id = conn_id;
 	queue_work(ndev->tx_wq, &ndev->tx_work);
 
 	goto exit;
@@ -184,11 +208,16 @@ exit:
 
 static void nci_add_rx_data_frag(struct nci_dev *ndev,
 				 struct sk_buff *skb,
-				 __u8 pbf)
+				 __u8 pbf, __u8 conn_id, __u8 status)
 {
 	int reassembly_len;
 	int err = 0;
 
+	if (status) {
+		err = status;
+		goto exit;
+	}
+
 	if (ndev->rx_data_reassembly) {
 		reassembly_len = ndev->rx_data_reassembly->len;
 
@@ -223,13 +252,23 @@ static void nci_add_rx_data_frag(struct nci_dev *ndev,
 	}
 
 exit:
-	nci_data_exchange_complete(ndev, skb, err);
+	if (ndev->nfc_dev->rf_mode == NFC_RF_TARGET) {
+		/* Data received in Target mode, forward to nfc core */
+		err = nfc_tm_data_received(ndev->nfc_dev, skb);
+		if (err)
+			pr_err("unable to handle received data\n");
+	} else {
+		nci_data_exchange_complete(ndev, skb, conn_id, err);
+	}
 }
 
 /* Rx Data packet */
 void nci_rx_data_packet(struct nci_dev *ndev, struct sk_buff *skb)
 {
 	__u8 pbf = nci_pbf(skb->data);
+	__u8 status = 0;
+	__u8 conn_id = nci_conn_id(skb->data);
+	struct nci_conn_info    *conn_info;
 
 	pr_debug("len %d\n", skb->len);
 
@@ -238,6 +277,10 @@ void nci_rx_data_packet(struct nci_dev *ndev, struct sk_buff *skb)
 		 nci_conn_id(skb->data),
 		 nci_plen(skb->data));
 
+	conn_info = nci_get_conn_info_by_conn_id(ndev, nci_conn_id(skb->data));
+	if (!conn_info)
+		return;
+
 	/* strip the nci data header */
 	skb_pull(skb, NCI_DATA_HDR_SIZE);
 
@@ -247,8 +290,9 @@ void nci_rx_data_packet(struct nci_dev *ndev, struct sk_buff *skb)
 	    ndev->target_active_prot == NFC_PROTO_ISO15693) {
 		/* frame I/F => remove the status byte */
 		pr_debug("frame I/F => remove the status byte\n");
+		status = skb->data[skb->len - 1];
 		skb_trim(skb, (skb->len - 1));
 	}
 
-	nci_add_rx_data_frag(ndev, skb, pbf);
+	nci_add_rx_data_frag(ndev, skb, pbf, conn_id, nci_to_errno(status));
 }
diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c
new file mode 100644
index 000000000000..ed54ec533836
--- /dev/null
+++ b/net/nfc/nci/hci.c
@@ -0,0 +1,694 @@
+/*
+ *  The NFC Controller Interface is the communication protocol between an
+ *  NFC Controller (NFCC) and a Device Host (DH).
+ *  This is the HCI over NCI implementation, as specified in the 10.2
+ *  section of the NCI 1.1 specification.
+ *
+ *  Copyright (C) 2014  STMicroelectronics SAS. All rights reserved.
+ *
+ *  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, see <http://www.gnu.org/licenses/>.
+ *
+ */
+
+#include <linux/skbuff.h>
+
+#include "../nfc.h"
+#include <net/nfc/nci.h>
+#include <net/nfc/nci_core.h>
+#include <linux/nfc.h>
+
+struct nci_data {
+	u8              conn_id;
+	u8              pipe;
+	u8              cmd;
+	const u8        *data;
+	u32             data_len;
+} __packed;
+
+struct nci_hci_create_pipe_params {
+	u8 src_gate;
+	u8 dest_host;
+	u8 dest_gate;
+} __packed;
+
+struct nci_hci_create_pipe_resp {
+	u8 src_host;
+	u8 src_gate;
+	u8 dest_host;
+	u8 dest_gate;
+	u8 pipe;
+} __packed;
+
+struct nci_hci_delete_pipe_noti {
+	u8 pipe;
+} __packed;
+
+struct nci_hci_all_pipe_cleared_noti {
+	u8 host;
+} __packed;
+
+struct nci_hcp_message {
+	u8 header;      /* type -cmd,evt,rsp- + instruction */
+	u8 data[];
+} __packed;
+
+struct nci_hcp_packet {
+	u8 header;      /* cbit+pipe */
+	struct nci_hcp_message message;
+} __packed;
+
+#define NCI_HCI_ANY_SET_PARAMETER  0x01
+#define NCI_HCI_ANY_GET_PARAMETER  0x02
+#define NCI_HCI_ANY_CLOSE_PIPE     0x04
+
+#define NCI_HFP_NO_CHAINING        0x80
+
+#define NCI_NFCEE_ID_HCI                0x80
+
+#define NCI_EVT_HOT_PLUG           0x03
+
+#define NCI_HCI_ADMIN_PARAM_SESSION_IDENTITY       0x01
+
+/* HCP headers */
+#define NCI_HCI_HCP_PACKET_HEADER_LEN      1
+#define NCI_HCI_HCP_MESSAGE_HEADER_LEN     1
+#define NCI_HCI_HCP_HEADER_LEN             2
+
+/* HCP types */
+#define NCI_HCI_HCP_COMMAND        0x00
+#define NCI_HCI_HCP_EVENT          0x01
+#define NCI_HCI_HCP_RESPONSE       0x02
+
+#define NCI_HCI_ADM_NOTIFY_PIPE_CREATED     0x12
+#define NCI_HCI_ADM_NOTIFY_PIPE_DELETED     0x13
+#define NCI_HCI_ADM_NOTIFY_ALL_PIPE_CLEARED 0x15
+
+#define NCI_HCI_FRAGMENT           0x7f
+#define NCI_HCP_HEADER(type, instr) ((((type) & 0x03) << 6) |\
+				      ((instr) & 0x3f))
+
+#define NCI_HCP_MSG_GET_TYPE(header) ((header & 0xc0) >> 6)
+#define NCI_HCP_MSG_GET_CMD(header)  (header & 0x3f)
+#define NCI_HCP_MSG_GET_PIPE(header) (header & 0x7f)
+
+/* HCI core */
+static void nci_hci_reset_pipes(struct nci_hci_dev *hdev)
+{
+	int i;
+
+	for (i = 0; i < NCI_HCI_MAX_PIPES; i++) {
+		hdev->pipes[i].gate = NCI_HCI_INVALID_GATE;
+		hdev->pipes[i].host = NCI_HCI_INVALID_HOST;
+	}
+	memset(hdev->gate2pipe, NCI_HCI_INVALID_PIPE, sizeof(hdev->gate2pipe));
+}
+
+static void nci_hci_reset_pipes_per_host(struct nci_dev *ndev, u8 host)
+{
+	int i;
+
+	for (i = 0; i < NCI_HCI_MAX_PIPES; i++) {
+		if (ndev->hci_dev->pipes[i].host == host) {
+			ndev->hci_dev->pipes[i].gate = NCI_HCI_INVALID_GATE;
+			ndev->hci_dev->pipes[i].host = NCI_HCI_INVALID_HOST;
+		}
+	}
+}
+
+/* Fragment HCI data over NCI packet.
+ * NFC Forum NCI 10.2.2 Data Exchange:
+ * The payload of the Data Packets sent on the Logical Connection SHALL be
+ * valid HCP packets, as defined within [ETSI_102622]. Each Data Packet SHALL
+ * contain a single HCP packet. NCI Segmentation and Reassembly SHALL NOT be
+ * applied to Data Messages in either direction. The HCI fragmentation mechanism
+ * is used if required.
+ */
+static int nci_hci_send_data(struct nci_dev *ndev, u8 pipe,
+			     const u8 data_type, const u8 *data,
+			     size_t data_len)
+{
+	struct nci_conn_info    *conn_info;
+	struct sk_buff *skb;
+	int len, i, r;
+	u8 cb = pipe;
+
+	conn_info = ndev->hci_dev->conn_info;
+	if (!conn_info)
+		return -EPROTO;
+
+	skb = nci_skb_alloc(ndev, 2 + conn_info->max_pkt_payload_len +
+			    NCI_DATA_HDR_SIZE, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	skb_reserve(skb, 2 + NCI_DATA_HDR_SIZE);
+	*skb_push(skb, 1) = data_type;
+
+	i = 0;
+	len = conn_info->max_pkt_payload_len;
+
+	do {
+		/* If last packet add NCI_HFP_NO_CHAINING */
+		if (i + conn_info->max_pkt_payload_len -
+		    (skb->len + 1) >= data_len) {
+			cb |= NCI_HFP_NO_CHAINING;
+			len = data_len - i;
+		} else {
+			len = conn_info->max_pkt_payload_len - skb->len - 1;
+		}
+
+		*skb_push(skb, 1) = cb;
+
+		if (len > 0)
+			memcpy(skb_put(skb, len), data + i, len);
+
+		r = nci_send_data(ndev, conn_info->conn_id, skb);
+		if (r < 0)
+			return r;
+
+		i += len;
+		if (i < data_len) {
+			skb_trim(skb, 0);
+			skb_pull(skb, len);
+		}
+	} while (i < data_len);
+
+	return i;
+}
+
+static void nci_hci_send_data_req(struct nci_dev *ndev, unsigned long opt)
+{
+	struct nci_data *data = (struct nci_data *)opt;
+
+	nci_hci_send_data(ndev, data->pipe, data->cmd,
+			  data->data, data->data_len);
+}
+
+int nci_hci_send_event(struct nci_dev *ndev, u8 gate, u8 event,
+		       const u8 *param, size_t param_len)
+{
+	u8 pipe = ndev->hci_dev->gate2pipe[gate];
+
+	if (pipe == NCI_HCI_INVALID_PIPE)
+		return -EADDRNOTAVAIL;
+
+	return nci_hci_send_data(ndev, pipe,
+			NCI_HCP_HEADER(NCI_HCI_HCP_EVENT, event),
+			param, param_len);
+}
+EXPORT_SYMBOL(nci_hci_send_event);
+
+int nci_hci_send_cmd(struct nci_dev *ndev, u8 gate, u8 cmd,
+		     const u8 *param, size_t param_len,
+		     struct sk_buff **skb)
+{
+	struct nci_conn_info    *conn_info;
+	struct nci_data data;
+	int r;
+	u8 pipe = ndev->hci_dev->gate2pipe[gate];
+
+	if (pipe == NCI_HCI_INVALID_PIPE)
+		return -EADDRNOTAVAIL;
+
+	conn_info = ndev->hci_dev->conn_info;
+	if (!conn_info)
+		return -EPROTO;
+
+	data.conn_id = conn_info->conn_id;
+	data.pipe = pipe;
+	data.cmd = NCI_HCP_HEADER(NCI_HCI_HCP_COMMAND, cmd);
+	data.data = param;
+	data.data_len = param_len;
+
+	r = nci_request(ndev, nci_hci_send_data_req, (unsigned long)&data,
+			msecs_to_jiffies(NCI_DATA_TIMEOUT));
+
+	if (r == NCI_STATUS_OK)
+		*skb = conn_info->rx_skb;
+
+	return r;
+}
+EXPORT_SYMBOL(nci_hci_send_cmd);
+
+static void nci_hci_event_received(struct nci_dev *ndev, u8 pipe,
+				   u8 event, struct sk_buff *skb)
+{
+	if (ndev->ops->hci_event_received)
+		ndev->ops->hci_event_received(ndev, pipe, event, skb);
+}
+
+static void nci_hci_cmd_received(struct nci_dev *ndev, u8 pipe,
+				 u8 cmd, struct sk_buff *skb)
+{
+	u8 gate = ndev->hci_dev->pipes[pipe].gate;
+	u8 status = NCI_HCI_ANY_OK | ~NCI_HCI_FRAGMENT;
+	u8 dest_gate, new_pipe;
+	struct nci_hci_create_pipe_resp *create_info;
+	struct nci_hci_delete_pipe_noti *delete_info;
+	struct nci_hci_all_pipe_cleared_noti *cleared_info;
+
+	pr_debug("from gate %x pipe %x cmd %x\n", gate, pipe, cmd);
+
+	switch (cmd) {
+	case NCI_HCI_ADM_NOTIFY_PIPE_CREATED:
+		if (skb->len != 5) {
+			status = NCI_HCI_ANY_E_NOK;
+			goto exit;
+		}
+		create_info = (struct nci_hci_create_pipe_resp *)skb->data;
+		dest_gate = create_info->dest_gate;
+		new_pipe = create_info->pipe;
+
+		/* Save the new created pipe and bind with local gate,
+		 * the description for skb->data[3] is destination gate id
+		 * but since we received this cmd from host controller, we
+		 * are the destination and it is our local gate
+		 */
+		ndev->hci_dev->gate2pipe[dest_gate] = new_pipe;
+		ndev->hci_dev->pipes[new_pipe].gate = dest_gate;
+		ndev->hci_dev->pipes[new_pipe].host =
+						create_info->src_host;
+		break;
+	case NCI_HCI_ANY_OPEN_PIPE:
+		/* If the pipe is not created report an error */
+		if (gate == NCI_HCI_INVALID_GATE) {
+			status = NCI_HCI_ANY_E_NOK;
+			goto exit;
+		}
+		break;
+	case NCI_HCI_ADM_NOTIFY_PIPE_DELETED:
+		if (skb->len != 1) {
+			status = NCI_HCI_ANY_E_NOK;
+			goto exit;
+		}
+		delete_info = (struct nci_hci_delete_pipe_noti *)skb->data;
+
+		ndev->hci_dev->pipes[delete_info->pipe].gate =
+						NCI_HCI_INVALID_GATE;
+		ndev->hci_dev->pipes[delete_info->pipe].host =
+						NCI_HCI_INVALID_HOST;
+		break;
+	case NCI_HCI_ADM_NOTIFY_ALL_PIPE_CLEARED:
+		if (skb->len != 1) {
+			status = NCI_HCI_ANY_E_NOK;
+			goto exit;
+		}
+
+		cleared_info =
+			(struct nci_hci_all_pipe_cleared_noti *)skb->data;
+		nci_hci_reset_pipes_per_host(ndev, cleared_info->host);
+		break;
+	default:
+		pr_debug("Discarded unknown cmd %x to gate %x\n", cmd, gate);
+		break;
+	}
+
+	if (ndev->ops->hci_cmd_received)
+		ndev->ops->hci_cmd_received(ndev, pipe, cmd, skb);
+
+exit:
+	nci_hci_send_data(ndev, pipe, status, NULL, 0);
+
+	kfree_skb(skb);
+}
+
+static void nci_hci_resp_received(struct nci_dev *ndev, u8 pipe,
+				  u8 result, struct sk_buff *skb)
+{
+	struct nci_conn_info    *conn_info;
+	u8 status = result;
+
+	if (result != NCI_HCI_ANY_OK)
+		goto exit;
+
+	conn_info = ndev->hci_dev->conn_info;
+	if (!conn_info) {
+		status = NCI_STATUS_REJECTED;
+		goto exit;
+	}
+
+	conn_info->rx_skb = skb;
+
+exit:
+	nci_req_complete(ndev, status);
+}
+
+/* Receive hcp message for pipe, with type and cmd.
+ * skb contains optional message data only.
+ */
+static void nci_hci_hcp_message_rx(struct nci_dev *ndev, u8 pipe,
+				   u8 type, u8 instruction, struct sk_buff *skb)
+{
+	switch (type) {
+	case NCI_HCI_HCP_RESPONSE:
+		nci_hci_resp_received(ndev, pipe, instruction, skb);
+		break;
+	case NCI_HCI_HCP_COMMAND:
+		nci_hci_cmd_received(ndev, pipe, instruction, skb);
+		break;
+	case NCI_HCI_HCP_EVENT:
+		nci_hci_event_received(ndev, pipe, instruction, skb);
+		break;
+	default:
+		pr_err("UNKNOWN MSG Type %d, instruction=%d\n",
+		       type, instruction);
+		kfree_skb(skb);
+		break;
+	}
+
+	nci_req_complete(ndev, 0);
+}
+
+static void nci_hci_msg_rx_work(struct work_struct *work)
+{
+	struct nci_hci_dev *hdev =
+		container_of(work, struct nci_hci_dev, msg_rx_work);
+	struct sk_buff *skb;
+	struct nci_hcp_message *message;
+	u8 pipe, type, instruction;
+
+	while ((skb = skb_dequeue(&hdev->msg_rx_queue)) != NULL) {
+		pipe = skb->data[0];
+		skb_pull(skb, NCI_HCI_HCP_PACKET_HEADER_LEN);
+		message = (struct nci_hcp_message *)skb->data;
+		type = NCI_HCP_MSG_GET_TYPE(message->header);
+		instruction = NCI_HCP_MSG_GET_CMD(message->header);
+		skb_pull(skb, NCI_HCI_HCP_MESSAGE_HEADER_LEN);
+
+		nci_hci_hcp_message_rx(hdev->ndev, pipe,
+				       type, instruction, skb);
+	}
+}
+
+void nci_hci_data_received_cb(void *context,
+			      struct sk_buff *skb, int err)
+{
+	struct nci_dev *ndev = (struct nci_dev *)context;
+	struct nci_hcp_packet *packet;
+	u8 pipe, type, instruction;
+	struct sk_buff *hcp_skb;
+	struct sk_buff *frag_skb;
+	int msg_len;
+
+	pr_debug("\n");
+
+	if (err) {
+		nci_req_complete(ndev, err);
+		return;
+	}
+
+	packet = (struct nci_hcp_packet *)skb->data;
+	if ((packet->header & ~NCI_HCI_FRAGMENT) == 0) {
+		skb_queue_tail(&ndev->hci_dev->rx_hcp_frags, skb);
+		return;
+	}
+
+	/* it's the last fragment. Does it need re-aggregation? */
+	if (skb_queue_len(&ndev->hci_dev->rx_hcp_frags)) {
+		pipe = packet->header & NCI_HCI_FRAGMENT;
+		skb_queue_tail(&ndev->hci_dev->rx_hcp_frags, skb);
+
+		msg_len = 0;
+		skb_queue_walk(&ndev->hci_dev->rx_hcp_frags, frag_skb) {
+			msg_len += (frag_skb->len -
+				    NCI_HCI_HCP_PACKET_HEADER_LEN);
+		}
+
+		hcp_skb = nfc_alloc_recv_skb(NCI_HCI_HCP_PACKET_HEADER_LEN +
+					     msg_len, GFP_KERNEL);
+		if (!hcp_skb) {
+			nci_req_complete(ndev, -ENOMEM);
+			return;
+		}
+
+		*skb_put(hcp_skb, NCI_HCI_HCP_PACKET_HEADER_LEN) = pipe;
+
+		skb_queue_walk(&ndev->hci_dev->rx_hcp_frags, frag_skb) {
+		       msg_len = frag_skb->len - NCI_HCI_HCP_PACKET_HEADER_LEN;
+			memcpy(skb_put(hcp_skb, msg_len), frag_skb->data +
+			       NCI_HCI_HCP_PACKET_HEADER_LEN, msg_len);
+		}
+
+		skb_queue_purge(&ndev->hci_dev->rx_hcp_frags);
+	} else {
+		packet->header &= NCI_HCI_FRAGMENT;
+		hcp_skb = skb;
+	}
+
+	/* if this is a response, dispatch immediately to
+	 * unblock waiting cmd context. Otherwise, enqueue to dispatch
+	 * in separate context where handler can also execute command.
+	 */
+	packet = (struct nci_hcp_packet *)hcp_skb->data;
+	type = NCI_HCP_MSG_GET_TYPE(packet->message.header);
+	if (type == NCI_HCI_HCP_RESPONSE) {
+		pipe = packet->header;
+		instruction = NCI_HCP_MSG_GET_CMD(packet->message.header);
+		skb_pull(hcp_skb, NCI_HCI_HCP_PACKET_HEADER_LEN +
+			 NCI_HCI_HCP_MESSAGE_HEADER_LEN);
+		nci_hci_hcp_message_rx(ndev, pipe, type, instruction, hcp_skb);
+	} else {
+		skb_queue_tail(&ndev->hci_dev->msg_rx_queue, hcp_skb);
+		schedule_work(&ndev->hci_dev->msg_rx_work);
+	}
+}
+
+int nci_hci_open_pipe(struct nci_dev *ndev, u8 pipe)
+{
+	struct nci_data data;
+	struct nci_conn_info    *conn_info;
+
+	conn_info = ndev->hci_dev->conn_info;
+	if (!conn_info)
+		return -EPROTO;
+
+	data.conn_id = conn_info->conn_id;
+	data.pipe = pipe;
+	data.cmd = NCI_HCP_HEADER(NCI_HCI_HCP_COMMAND,
+				       NCI_HCI_ANY_OPEN_PIPE);
+	data.data = NULL;
+	data.data_len = 0;
+
+	return nci_request(ndev, nci_hci_send_data_req,
+			(unsigned long)&data,
+			msecs_to_jiffies(NCI_DATA_TIMEOUT));
+}
+EXPORT_SYMBOL(nci_hci_open_pipe);
+
+int nci_hci_set_param(struct nci_dev *ndev, u8 gate, u8 idx,
+		      const u8 *param, size_t param_len)
+{
+	struct nci_conn_info *conn_info;
+	struct nci_data data;
+	int r;
+	u8 *tmp;
+	u8 pipe = ndev->hci_dev->gate2pipe[gate];
+
+	pr_debug("idx=%d to gate %d\n", idx, gate);
+
+	if (pipe == NCI_HCI_INVALID_PIPE)
+		return -EADDRNOTAVAIL;
+
+	conn_info = ndev->hci_dev->conn_info;
+	if (!conn_info)
+		return -EPROTO;
+
+	tmp = kmalloc(1 + param_len, GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
+
+	*tmp = idx;
+	memcpy(tmp + 1, param, param_len);
+
+	data.conn_id = conn_info->conn_id;
+	data.pipe = pipe;
+	data.cmd = NCI_HCP_HEADER(NCI_HCI_HCP_COMMAND,
+				       NCI_HCI_ANY_SET_PARAMETER);
+	data.data = tmp;
+	data.data_len = param_len + 1;
+
+	r = nci_request(ndev, nci_hci_send_data_req,
+			(unsigned long)&data,
+			msecs_to_jiffies(NCI_DATA_TIMEOUT));
+
+	kfree(tmp);
+	return r;
+}
+EXPORT_SYMBOL(nci_hci_set_param);
+
+int nci_hci_get_param(struct nci_dev *ndev, u8 gate, u8 idx,
+		      struct sk_buff **skb)
+{
+	struct nci_conn_info    *conn_info;
+	struct nci_data data;
+	int r;
+	u8 pipe = ndev->hci_dev->gate2pipe[gate];
+
+	pr_debug("idx=%d to gate %d\n", idx, gate);
+
+	if (pipe == NCI_HCI_INVALID_PIPE)
+		return -EADDRNOTAVAIL;
+
+	conn_info = ndev->hci_dev->conn_info;
+	if (!conn_info)
+		return -EPROTO;
+
+	data.conn_id = conn_info->conn_id;
+	data.pipe = pipe;
+	data.cmd = NCI_HCP_HEADER(NCI_HCI_HCP_COMMAND,
+				  NCI_HCI_ANY_GET_PARAMETER);
+	data.data = &idx;
+	data.data_len = 1;
+
+	r = nci_request(ndev, nci_hci_send_data_req, (unsigned long)&data,
+			msecs_to_jiffies(NCI_DATA_TIMEOUT));
+
+	if (r == NCI_STATUS_OK)
+		*skb = conn_info->rx_skb;
+
+	return r;
+}
+EXPORT_SYMBOL(nci_hci_get_param);
+
+int nci_hci_connect_gate(struct nci_dev *ndev,
+			 u8 dest_host, u8 dest_gate, u8 pipe)
+{
+	int r;
+
+	if (pipe == NCI_HCI_DO_NOT_OPEN_PIPE)
+		return 0;
+
+	if (ndev->hci_dev->gate2pipe[dest_gate] != NCI_HCI_INVALID_PIPE)
+		return -EADDRINUSE;
+
+	if (pipe != NCI_HCI_INVALID_PIPE)
+		goto open_pipe;
+
+	switch (dest_gate) {
+	case NCI_HCI_LINK_MGMT_GATE:
+		pipe = NCI_HCI_LINK_MGMT_PIPE;
+	break;
+	case NCI_HCI_ADMIN_GATE:
+		pipe = NCI_HCI_ADMIN_PIPE;
+	break;
+	}
+
+open_pipe:
+	r = nci_hci_open_pipe(ndev, pipe);
+	if (r < 0)
+		return r;
+
+	ndev->hci_dev->pipes[pipe].gate = dest_gate;
+	ndev->hci_dev->pipes[pipe].host = dest_host;
+	ndev->hci_dev->gate2pipe[dest_gate] = pipe;
+
+	return 0;
+}
+EXPORT_SYMBOL(nci_hci_connect_gate);
+
+static int nci_hci_dev_connect_gates(struct nci_dev *ndev,
+				     u8 gate_count,
+				     struct nci_hci_gate *gates)
+{
+	int r;
+
+	while (gate_count--) {
+		r = nci_hci_connect_gate(ndev, gates->dest_host,
+					 gates->gate, gates->pipe);
+		if (r < 0)
+			return r;
+		gates++;
+	}
+
+	return 0;
+}
+
+int nci_hci_dev_session_init(struct nci_dev *ndev)
+{
+	struct nci_conn_info    *conn_info;
+	struct sk_buff *skb;
+	int r;
+
+	ndev->hci_dev->count_pipes = 0;
+	ndev->hci_dev->expected_pipes = 0;
+
+	conn_info = ndev->hci_dev->conn_info;
+	if (!conn_info)
+		return -EPROTO;
+
+	conn_info->data_exchange_cb = nci_hci_data_received_cb;
+	conn_info->data_exchange_cb_context = ndev;
+
+	nci_hci_reset_pipes(ndev->hci_dev);
+
+	if (ndev->hci_dev->init_data.gates[0].gate != NCI_HCI_ADMIN_GATE)
+		return -EPROTO;
+
+	r = nci_hci_connect_gate(ndev,
+				 ndev->hci_dev->init_data.gates[0].dest_host,
+				 ndev->hci_dev->init_data.gates[0].gate,
+				 ndev->hci_dev->init_data.gates[0].pipe);
+	if (r < 0)
+		goto exit;
+
+	r = nci_hci_get_param(ndev, NCI_HCI_ADMIN_GATE,
+			      NCI_HCI_ADMIN_PARAM_SESSION_IDENTITY, &skb);
+	if (r < 0)
+		goto exit;
+
+	if (skb->len &&
+	    skb->len == strlen(ndev->hci_dev->init_data.session_id) &&
+	    memcmp(ndev->hci_dev->init_data.session_id,
+		   skb->data, skb->len) == 0 &&
+	    ndev->ops->hci_load_session) {
+		/* Restore gate<->pipe table from some proprietary location. */
+		r = ndev->ops->hci_load_session(ndev);
+		if (r < 0)
+			goto exit;
+	} else {
+		r = nci_hci_dev_connect_gates(ndev,
+					      ndev->hci_dev->init_data.gate_count,
+					      ndev->hci_dev->init_data.gates);
+		if (r < 0)
+			goto exit;
+
+		r = nci_hci_set_param(ndev, NCI_HCI_ADMIN_GATE,
+				      NCI_HCI_ADMIN_PARAM_SESSION_IDENTITY,
+				      ndev->hci_dev->init_data.session_id,
+				      strlen(ndev->hci_dev->init_data.session_id));
+	}
+	if (r == 0)
+		goto exit;
+
+exit:
+	kfree_skb(skb);
+
+	return r;
+}
+EXPORT_SYMBOL(nci_hci_dev_session_init);
+
+struct nci_hci_dev *nci_hci_allocate(struct nci_dev *ndev)
+{
+	struct nci_hci_dev *hdev;
+
+	hdev = kzalloc(sizeof(*hdev), GFP_KERNEL);
+	if (!hdev)
+		return NULL;
+
+	skb_queue_head_init(&hdev->rx_hcp_frags);
+	INIT_WORK(&hdev->msg_rx_work, nci_hci_msg_rx_work);
+	skb_queue_head_init(&hdev->msg_rx_queue);
+	hdev->ndev = ndev;
+
+	return hdev;
+}
diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c
index 205b35f666db..3218071072ac 100644
--- a/net/nfc/nci/ntf.c
+++ b/net/nfc/nci/ntf.c
@@ -43,6 +43,7 @@ static void nci_core_conn_credits_ntf_packet(struct nci_dev *ndev,
 					     struct sk_buff *skb)
 {
 	struct nci_core_conn_credit_ntf *ntf = (void *) skb->data;
+	struct nci_conn_info	*conn_info;
 	int i;
 
 	pr_debug("num_entries %d\n", ntf->num_entries);
@@ -59,11 +60,13 @@ static void nci_core_conn_credits_ntf_packet(struct nci_dev *ndev,
 			 i, ntf->conn_entries[i].conn_id,
 			 ntf->conn_entries[i].credits);
 
-		if (ntf->conn_entries[i].conn_id == NCI_STATIC_RF_CONN_ID) {
-			/* found static rf connection */
-			atomic_add(ntf->conn_entries[i].credits,
-				   &ndev->credits_cnt);
-		}
+		conn_info = nci_get_conn_info_by_conn_id(ndev,
+							 ntf->conn_entries[i].conn_id);
+		if (!conn_info)
+			return;
+
+		atomic_add(ntf->conn_entries[i].credits,
+			   &conn_info->credits_cnt);
 	}
 
 	/* trigger the next tx */
@@ -96,14 +99,14 @@ static void nci_core_conn_intf_error_ntf_packet(struct nci_dev *ndev,
 
 	/* complete the data exchange transaction, if exists */
 	if (test_bit(NCI_DATA_EXCHANGE, &ndev->flags))
-		nci_data_exchange_complete(ndev, NULL, -EIO);
+		nci_data_exchange_complete(ndev, NULL, ntf->conn_id, -EIO);
 }
 
 static __u8 *nci_extract_rf_params_nfca_passive_poll(struct nci_dev *ndev,
 			struct rf_tech_specific_params_nfca_poll *nfca_poll,
 						     __u8 *data)
 {
-	nfca_poll->sens_res = __le16_to_cpu(*((__u16 *)data));
+	nfca_poll->sens_res = __le16_to_cpu(*((__le16 *)data));
 	data += 2;
 
 	nfca_poll->nfcid1_len = min_t(__u8, *data++, NFC_NFCID1_MAXSIZE);
@@ -167,7 +170,19 @@ static __u8 *nci_extract_rf_params_nfcv_passive_poll(struct nci_dev *ndev,
 	return data;
 }
 
-__u32 nci_get_prop_rf_protocol(struct nci_dev *ndev, __u8 rf_protocol)
+static __u8 *nci_extract_rf_params_nfcf_passive_listen(struct nci_dev *ndev,
+			struct rf_tech_specific_params_nfcf_listen *nfcf_listen,
+						     __u8 *data)
+{
+	nfcf_listen->local_nfcid2_len = min_t(__u8, *data++,
+					      NFC_NFCID2_MAXSIZE);
+	memcpy(nfcf_listen->local_nfcid2, data, nfcf_listen->local_nfcid2_len);
+	data += nfcf_listen->local_nfcid2_len;
+
+	return data;
+}
+
+static __u32 nci_get_prop_rf_protocol(struct nci_dev *ndev, __u8 rf_protocol)
 {
 	if (ndev->ops->get_rfprotocol)
 		return ndev->ops->get_rfprotocol(ndev, rf_protocol);
@@ -401,17 +416,29 @@ 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;
+	struct activation_params_listen_nfc_dep *listen;
 
 	switch (ntf->activation_rf_tech_and_mode) {
 	case NCI_NFC_A_PASSIVE_POLL_MODE:
 	case NCI_NFC_F_PASSIVE_POLL_MODE:
 		poll = &ntf->activation_params.poll_nfc_dep;
-		poll->atr_res_len = min_t(__u8, *data++, 63);
+		poll->atr_res_len = min_t(__u8, *data++,
+					  NFC_ATR_RES_MAXSIZE - 2);
 		pr_debug("atr_res_len %d\n", poll->atr_res_len);
 		if (poll->atr_res_len > 0)
 			memcpy(poll->atr_res, data, poll->atr_res_len);
 		break;
 
+	case NCI_NFC_A_PASSIVE_LISTEN_MODE:
+	case NCI_NFC_F_PASSIVE_LISTEN_MODE:
+		listen = &ntf->activation_params.listen_nfc_dep;
+		listen->atr_req_len = min_t(__u8, *data++,
+					    NFC_ATR_REQ_MAXSIZE - 2);
+		pr_debug("atr_req_len %d\n", listen->atr_req_len);
+		if (listen->atr_req_len > 0)
+			memcpy(listen->atr_req, data, listen->atr_req_len);
+		break;
+
 	default:
 		pr_err("unsupported activation_rf_tech_and_mode 0x%x\n",
 		       ntf->activation_rf_tech_and_mode);
@@ -444,9 +471,52 @@ static void nci_target_auto_activated(struct nci_dev *ndev,
 	nfc_targets_found(ndev->nfc_dev, ndev->targets, ndev->n_targets);
 }
 
+static int nci_store_general_bytes_nfc_dep(struct nci_dev *ndev,
+		struct nci_rf_intf_activated_ntf *ntf)
+{
+	ndev->remote_gb_len = 0;
+
+	if (ntf->activation_params_len <= 0)
+		return NCI_STATUS_OK;
+
+	switch (ntf->activation_rf_tech_and_mode) {
+	case NCI_NFC_A_PASSIVE_POLL_MODE:
+	case NCI_NFC_F_PASSIVE_POLL_MODE:
+		ndev->remote_gb_len = min_t(__u8,
+			(ntf->activation_params.poll_nfc_dep.atr_res_len
+						- NFC_ATR_RES_GT_OFFSET),
+			NFC_ATR_RES_GB_MAXSIZE);
+		memcpy(ndev->remote_gb,
+		       (ntf->activation_params.poll_nfc_dep.atr_res
+						+ NFC_ATR_RES_GT_OFFSET),
+		       ndev->remote_gb_len);
+		break;
+
+	case NCI_NFC_A_PASSIVE_LISTEN_MODE:
+	case NCI_NFC_F_PASSIVE_LISTEN_MODE:
+		ndev->remote_gb_len = min_t(__u8,
+			(ntf->activation_params.listen_nfc_dep.atr_req_len
+						- NFC_ATR_REQ_GT_OFFSET),
+			NFC_ATR_REQ_GB_MAXSIZE);
+		memcpy(ndev->remote_gb,
+		       (ntf->activation_params.listen_nfc_dep.atr_req
+						+ NFC_ATR_REQ_GT_OFFSET),
+		       ndev->remote_gb_len);
+		break;
+
+	default:
+		pr_err("unsupported activation_rf_tech_and_mode 0x%x\n",
+		       ntf->activation_rf_tech_and_mode);
+		return NCI_STATUS_RF_PROTOCOL_ERROR;
+	}
+
+	return NCI_STATUS_OK;
+}
+
 static void nci_rf_intf_activated_ntf_packet(struct nci_dev *ndev,
 					     struct sk_buff *skb)
 {
+	struct nci_conn_info    *conn_info;
 	struct nci_rf_intf_activated_ntf ntf;
 	__u8 *data = skb->data;
 	int err = NCI_STATUS_OK;
@@ -471,6 +541,13 @@ static void nci_rf_intf_activated_ntf_packet(struct nci_dev *ndev,
 	pr_debug("rf_tech_specific_params_len %d\n",
 		 ntf.rf_tech_specific_params_len);
 
+	/* If this contains a value of 0x00 (NFCEE Direct RF
+	 * Interface) then all following parameters SHALL contain a
+	 * value of 0 and SHALL be ignored.
+	 */
+	if (ntf.rf_interface == NCI_RF_INTERFACE_NFCEE_DIRECT)
+		goto listen;
+
 	if (ntf.rf_tech_specific_params_len > 0) {
 		switch (ntf.activation_rf_tech_and_mode) {
 		case NCI_NFC_A_PASSIVE_POLL_MODE:
@@ -493,6 +570,16 @@ static void nci_rf_intf_activated_ntf_packet(struct nci_dev *ndev,
 				&(ntf.rf_tech_specific_params.nfcv_poll), data);
 			break;
 
+		case NCI_NFC_A_PASSIVE_LISTEN_MODE:
+			/* no RF technology specific parameters */
+			break;
+
+		case NCI_NFC_F_PASSIVE_LISTEN_MODE:
+			data = nci_extract_rf_params_nfcf_passive_listen(ndev,
+				&(ntf.rf_tech_specific_params.nfcf_listen),
+				data);
+			break;
+
 		default:
 			pr_err("unsupported activation_rf_tech_and_mode 0x%x\n",
 			       ntf.activation_rf_tech_and_mode);
@@ -538,50 +625,68 @@ static void nci_rf_intf_activated_ntf_packet(struct nci_dev *ndev,
 
 exit:
 	if (err == NCI_STATUS_OK) {
-		ndev->max_data_pkt_payload_size = ntf.max_data_pkt_payload_size;
-		ndev->initial_num_credits = ntf.initial_num_credits;
+		conn_info = ndev->rf_conn_info;
+		if (!conn_info)
+			return;
+
+		conn_info->max_pkt_payload_len = ntf.max_data_pkt_payload_size;
+		conn_info->initial_num_credits = ntf.initial_num_credits;
 
 		/* set the available credits to initial value */
-		atomic_set(&ndev->credits_cnt, ndev->initial_num_credits);
+		atomic_set(&conn_info->credits_cnt,
+			   conn_info->initial_num_credits);
 
 		/* store general bytes to be reported later in dep_link_up */
 		if (ntf.rf_interface == NCI_RF_INTERFACE_NFC_DEP) {
-			ndev->remote_gb_len = 0;
-
-			if (ntf.activation_params_len > 0) {
-				/* ATR_RES general bytes at offset 15 */
-				ndev->remote_gb_len = min_t(__u8,
-					(ntf.activation_params
-					.poll_nfc_dep.atr_res_len
-					- NFC_ATR_RES_GT_OFFSET),
-					NFC_MAX_GT_LEN);
-				memcpy(ndev->remote_gb,
-				       (ntf.activation_params.poll_nfc_dep
-				       .atr_res + NFC_ATR_RES_GT_OFFSET),
-				       ndev->remote_gb_len);
-			}
+			err = nci_store_general_bytes_nfc_dep(ndev, &ntf);
+			if (err != NCI_STATUS_OK)
+				pr_err("unable to store general bytes\n");
 		}
 	}
 
-	if (atomic_read(&ndev->state) == NCI_DISCOVERY) {
-		/* A single target was found and activated automatically */
-		atomic_set(&ndev->state, NCI_POLL_ACTIVE);
-		if (err == NCI_STATUS_OK)
-			nci_target_auto_activated(ndev, &ntf);
-	} else {	/* ndev->state == NCI_W4_HOST_SELECT */
-		/* A selected target was activated, so complete the request */
-		atomic_set(&ndev->state, NCI_POLL_ACTIVE);
-		nci_req_complete(ndev, err);
+	if (!(ntf.activation_rf_tech_and_mode & NCI_RF_TECH_MODE_LISTEN_MASK)) {
+		/* Poll mode */
+		if (atomic_read(&ndev->state) == NCI_DISCOVERY) {
+			/* A single target was found and activated
+			 * automatically */
+			atomic_set(&ndev->state, NCI_POLL_ACTIVE);
+			if (err == NCI_STATUS_OK)
+				nci_target_auto_activated(ndev, &ntf);
+		} else {	/* ndev->state == NCI_W4_HOST_SELECT */
+			/* A selected target was activated, so complete the
+			 * request */
+			atomic_set(&ndev->state, NCI_POLL_ACTIVE);
+			nci_req_complete(ndev, err);
+		}
+	} else {
+listen:
+		/* Listen mode */
+		atomic_set(&ndev->state, NCI_LISTEN_ACTIVE);
+		if (err == NCI_STATUS_OK &&
+		    ntf.rf_protocol == NCI_RF_PROTOCOL_NFC_DEP) {
+			err = nfc_tm_activated(ndev->nfc_dev,
+					       NFC_PROTO_NFC_DEP_MASK,
+					       NFC_COMM_PASSIVE,
+					       ndev->remote_gb,
+					       ndev->remote_gb_len);
+			if (err != NCI_STATUS_OK)
+				pr_err("error when signaling tm activation\n");
+		}
 	}
 }
 
 static void nci_rf_deactivate_ntf_packet(struct nci_dev *ndev,
 					 struct sk_buff *skb)
 {
+	struct nci_conn_info    *conn_info;
 	struct nci_rf_deactivate_ntf *ntf = (void *) skb->data;
 
 	pr_debug("entry, type 0x%x, reason 0x%x\n", ntf->type, ntf->reason);
 
+	conn_info = ndev->rf_conn_info;
+	if (!conn_info)
+		return;
+
 	/* drop tx data queue */
 	skb_queue_purge(&ndev->tx_q);
 
@@ -593,13 +698,53 @@ static void nci_rf_deactivate_ntf_packet(struct nci_dev *ndev,
 
 	/* complete the data exchange transaction, if exists */
 	if (test_bit(NCI_DATA_EXCHANGE, &ndev->flags))
-		nci_data_exchange_complete(ndev, NULL, -EIO);
+		nci_data_exchange_complete(ndev, NULL, NCI_STATIC_RF_CONN_ID,
+					   -EIO);
+
+	switch (ntf->type) {
+	case NCI_DEACTIVATE_TYPE_IDLE_MODE:
+		nci_clear_target_list(ndev);
+		atomic_set(&ndev->state, NCI_IDLE);
+		break;
+	case NCI_DEACTIVATE_TYPE_SLEEP_MODE:
+	case NCI_DEACTIVATE_TYPE_SLEEP_AF_MODE:
+		atomic_set(&ndev->state, NCI_W4_HOST_SELECT);
+		break;
+	case NCI_DEACTIVATE_TYPE_DISCOVERY:
+		nci_clear_target_list(ndev);
+		atomic_set(&ndev->state, NCI_DISCOVERY);
+		break;
+	}
 
-	nci_clear_target_list(ndev);
-	atomic_set(&ndev->state, NCI_IDLE);
 	nci_req_complete(ndev, NCI_STATUS_OK);
 }
 
+static void nci_nfcee_discover_ntf_packet(struct nci_dev *ndev,
+					  struct sk_buff *skb)
+{
+	u8 status = NCI_STATUS_OK;
+	struct nci_nfcee_discover_ntf   *nfcee_ntf =
+				(struct nci_nfcee_discover_ntf *)skb->data;
+
+	pr_debug("\n");
+
+	/* NFCForum NCI 9.2.1 HCI Network Specific Handling
+	 * If the NFCC supports the HCI Network, it SHALL return one,
+	 * and only one, NFCEE_DISCOVER_NTF with a Protocol type of
+	 * “HCI Access”, even if the HCI Network contains multiple NFCEEs.
+	 */
+	ndev->hci_dev->nfcee_id = nfcee_ntf->nfcee_id;
+	ndev->cur_id = nfcee_ntf->nfcee_id;
+
+	nci_req_complete(ndev, status);
+}
+
+static void nci_nfcee_action_ntf_packet(struct nci_dev *ndev,
+					struct sk_buff *skb)
+{
+	pr_debug("\n");
+}
+
 void nci_ntf_packet(struct nci_dev *ndev, struct sk_buff *skb)
 {
 	__u16 ntf_opcode = nci_opcode(skb->data);
@@ -638,6 +783,14 @@ void nci_ntf_packet(struct nci_dev *ndev, struct sk_buff *skb)
 		nci_rf_deactivate_ntf_packet(ndev, skb);
 		break;
 
+	case NCI_OP_NFCEE_DISCOVER_NTF:
+		nci_nfcee_discover_ntf_packet(ndev, skb);
+		break;
+
+	case NCI_OP_RF_NFCEE_ACTION_NTF:
+		nci_nfcee_action_ntf_packet(ndev, skb);
+		break;
+
 	default:
 		pr_err("unknown ntf opcode 0x%x\n", ntf_opcode);
 		break;
diff --git a/net/nfc/nci/rsp.c b/net/nfc/nci/rsp.c
index 041de51ccdbe..02486bc2ceea 100644
--- a/net/nfc/nci/rsp.c
+++ b/net/nfc/nci/rsp.c
@@ -140,13 +140,31 @@ static void nci_rf_disc_map_rsp_packet(struct nci_dev *ndev,
 
 static void nci_rf_disc_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb)
 {
+	struct nci_conn_info    *conn_info;
 	__u8 status = skb->data[0];
 
 	pr_debug("status 0x%x\n", status);
 
-	if (status == NCI_STATUS_OK)
+	if (status == NCI_STATUS_OK) {
 		atomic_set(&ndev->state, NCI_DISCOVERY);
 
+		conn_info = ndev->rf_conn_info;
+		if (!conn_info) {
+			conn_info = devm_kzalloc(&ndev->nfc_dev->dev,
+						 sizeof(struct nci_conn_info),
+						 GFP_KERNEL);
+			if (!conn_info) {
+				status = NCI_STATUS_REJECTED;
+				goto exit;
+			}
+			conn_info->conn_id = NCI_STATIC_RF_CONN_ID;
+			INIT_LIST_HEAD(&conn_info->list);
+			list_add(&conn_info->list, &ndev->conn_info_list);
+			ndev->rf_conn_info = conn_info;
+		}
+	}
+
+exit:
 	nci_req_complete(ndev, status);
 }
 
@@ -178,6 +196,90 @@ static void nci_rf_deactivate_rsp_packet(struct nci_dev *ndev,
 	}
 }
 
+static void nci_nfcee_discover_rsp_packet(struct nci_dev *ndev,
+					  struct sk_buff *skb)
+{
+	struct nci_nfcee_discover_rsp *discover_rsp;
+
+	if (skb->len != 2) {
+		nci_req_complete(ndev, NCI_STATUS_NFCEE_PROTOCOL_ERROR);
+		return;
+	}
+
+	discover_rsp = (struct nci_nfcee_discover_rsp *)skb->data;
+
+	if (discover_rsp->status != NCI_STATUS_OK ||
+	    discover_rsp->num_nfcee == 0)
+		nci_req_complete(ndev, discover_rsp->status);
+}
+
+static void nci_nfcee_mode_set_rsp_packet(struct nci_dev *ndev,
+					  struct sk_buff *skb)
+{
+	__u8 status = skb->data[0];
+
+	pr_debug("status 0x%x\n", status);
+	nci_req_complete(ndev, status);
+}
+
+static void nci_core_conn_create_rsp_packet(struct nci_dev *ndev,
+					    struct sk_buff *skb)
+{
+	__u8 status = skb->data[0];
+	struct nci_conn_info *conn_info;
+	struct nci_core_conn_create_rsp *rsp;
+
+	pr_debug("status 0x%x\n", status);
+
+	if (status == NCI_STATUS_OK) {
+		rsp = (struct nci_core_conn_create_rsp *)skb->data;
+
+		conn_info = devm_kzalloc(&ndev->nfc_dev->dev,
+					 sizeof(*conn_info), GFP_KERNEL);
+		if (!conn_info) {
+			status = NCI_STATUS_REJECTED;
+			goto exit;
+		}
+
+		conn_info->id = ndev->cur_id;
+		conn_info->conn_id = rsp->conn_id;
+
+		/* Note: data_exchange_cb and data_exchange_cb_context need to
+		 * be specify out of nci_core_conn_create_rsp_packet
+		 */
+
+		INIT_LIST_HEAD(&conn_info->list);
+		list_add(&conn_info->list, &ndev->conn_info_list);
+
+		if (ndev->cur_id == ndev->hci_dev->nfcee_id)
+			ndev->hci_dev->conn_info = conn_info;
+
+		conn_info->conn_id = rsp->conn_id;
+		conn_info->max_pkt_payload_len = rsp->max_ctrl_pkt_payload_len;
+		atomic_set(&conn_info->credits_cnt, rsp->credits_cnt);
+	}
+
+exit:
+	nci_req_complete(ndev, status);
+}
+
+static void nci_core_conn_close_rsp_packet(struct nci_dev *ndev,
+					   struct sk_buff *skb)
+{
+	struct nci_conn_info *conn_info;
+	__u8 status = skb->data[0];
+
+	pr_debug("status 0x%x\n", status);
+	if (status == NCI_STATUS_OK) {
+		conn_info = nci_get_conn_info_by_conn_id(ndev, ndev->cur_id);
+		if (conn_info) {
+			list_del(&conn_info->list);
+			devm_kfree(&ndev->nfc_dev->dev, conn_info);
+		}
+	}
+	nci_req_complete(ndev, status);
+}
+
 void nci_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb)
 {
 	__u16 rsp_opcode = nci_opcode(skb->data);
@@ -207,6 +309,14 @@ void nci_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb)
 		nci_core_set_config_rsp_packet(ndev, skb);
 		break;
 
+	case NCI_OP_CORE_CONN_CREATE_RSP:
+		nci_core_conn_create_rsp_packet(ndev, skb);
+		break;
+
+	case NCI_OP_CORE_CONN_CLOSE_RSP:
+		nci_core_conn_close_rsp_packet(ndev, skb);
+		break;
+
 	case NCI_OP_RF_DISCOVER_MAP_RSP:
 		nci_rf_disc_map_rsp_packet(ndev, skb);
 		break;
@@ -223,6 +333,14 @@ void nci_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb)
 		nci_rf_deactivate_rsp_packet(ndev, skb);
 		break;
 
+	case NCI_OP_NFCEE_DISCOVER_RSP:
+		nci_nfcee_discover_rsp_packet(ndev, skb);
+		break;
+
+	case NCI_OP_NFCEE_MODE_SET_RSP:
+		nci_nfcee_mode_set_rsp_packet(ndev, skb);
+		break;
+
 	default:
 		pr_err("unknown rsp opcode 0x%x\n", rsp_opcode);
 		break;
diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index 43cb1c17e267..3763036710ae 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -102,7 +102,8 @@ static int nfc_genl_send_target(struct sk_buff *msg, struct nfc_target *target,
 			goto nla_put_failure;
 	}
 
-	return genlmsg_end(msg, hdr);
+	genlmsg_end(msg, hdr);
+	return 0;
 
 nla_put_failure:
 	genlmsg_cancel(msg, hdr);
@@ -496,6 +497,53 @@ free_msg:
 	return -EMSGSIZE;
 }
 
+int nfc_genl_se_transaction(struct nfc_dev *dev, u8 se_idx,
+			    struct nfc_evt_transaction *evt_transaction)
+{
+	struct nfc_se *se;
+	struct sk_buff *msg;
+	void *hdr;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0,
+			  NFC_EVENT_SE_TRANSACTION);
+	if (!hdr)
+		goto free_msg;
+
+	se = nfc_find_se(dev, se_idx);
+	if (!se)
+		goto free_msg;
+
+	if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx) ||
+	    nla_put_u32(msg, NFC_ATTR_SE_INDEX, se_idx) ||
+	    nla_put_u8(msg, NFC_ATTR_SE_TYPE, se->type) ||
+	    nla_put(msg, NFC_ATTR_SE_AID, evt_transaction->aid_len,
+		    evt_transaction->aid) ||
+	    nla_put(msg, NFC_ATTR_SE_PARAMS, evt_transaction->params_len,
+		    evt_transaction->params))
+		goto nla_put_failure;
+
+	/* evt_transaction is no more used */
+	devm_kfree(&dev->dev, evt_transaction);
+
+	genlmsg_end(msg, hdr);
+
+	genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL);
+
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+free_msg:
+	/* evt_transaction is no more used */
+	devm_kfree(&dev->dev, evt_transaction);
+	nlmsg_free(msg);
+	return -EMSGSIZE;
+}
+
 static int nfc_genl_send_device(struct sk_buff *msg, struct nfc_dev *dev,
 				u32 portid, u32 seq,
 				struct netlink_callback *cb,
@@ -518,7 +566,8 @@ static int nfc_genl_send_device(struct sk_buff *msg, struct nfc_dev *dev,
 	    nla_put_u8(msg, NFC_ATTR_RF_MODE, dev->rf_mode))
 		goto nla_put_failure;
 
-	return genlmsg_end(msg, hdr);
+	genlmsg_end(msg, hdr);
+	return 0;
 
 nla_put_failure:
 	genlmsg_cancel(msg, hdr);
@@ -810,6 +859,31 @@ out:
 	return rc;
 }
 
+static int nfc_genl_activate_target(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nfc_dev *dev;
+	u32 device_idx, target_idx, protocol;
+	int rc;
+
+	if (!info->attrs[NFC_ATTR_DEVICE_INDEX])
+		return -EINVAL;
+
+	device_idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]);
+
+	dev = nfc_get_device(device_idx);
+	if (!dev)
+		return -ENODEV;
+
+	target_idx = nla_get_u32(info->attrs[NFC_ATTR_TARGET_INDEX]);
+	protocol = nla_get_u32(info->attrs[NFC_ATTR_PROTOCOLS]);
+
+	nfc_deactivate_target(dev, target_idx);
+	rc = nfc_activate_target(dev, target_idx, protocol);
+
+	nfc_put_device(dev);
+	return 0;
+}
+
 static int nfc_genl_dep_link_up(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nfc_dev *dev;
@@ -883,7 +957,8 @@ static int nfc_genl_send_params(struct sk_buff *msg,
 	    nla_put_u16(msg, NFC_ATTR_LLC_PARAM_MIUX, be16_to_cpu(local->miux)))
 		goto nla_put_failure;
 
-	return genlmsg_end(msg, hdr);
+	genlmsg_end(msg, hdr);
+	return 0;
 
 nla_put_failure:
 
@@ -1222,8 +1297,7 @@ static int nfc_genl_send_se(struct sk_buff *msg, struct nfc_dev *dev,
 		    nla_put_u8(msg, NFC_ATTR_SE_TYPE, se->type))
 			goto nla_put_failure;
 
-		if (genlmsg_end(msg, hdr) < 0)
-			goto nla_put_failure;
+		genlmsg_end(msg, hdr);
 	}
 
 	return 0;
@@ -1285,6 +1359,51 @@ static int nfc_genl_dump_ses_done(struct netlink_callback *cb)
 	return 0;
 }
 
+static int nfc_se_io(struct nfc_dev *dev, u32 se_idx,
+		     u8 *apdu, size_t apdu_length,
+		     se_io_cb_t cb, void *cb_context)
+{
+	struct nfc_se *se;
+	int rc;
+
+	pr_debug("%s se index %d\n", dev_name(&dev->dev), se_idx);
+
+	device_lock(&dev->dev);
+
+	if (!device_is_registered(&dev->dev)) {
+		rc = -ENODEV;
+		goto error;
+	}
+
+	if (!dev->dev_up) {
+		rc = -ENODEV;
+		goto error;
+	}
+
+	if (!dev->ops->se_io) {
+		rc = -EOPNOTSUPP;
+		goto error;
+	}
+
+	se = nfc_find_se(dev, se_idx);
+	if (!se) {
+		rc = -EINVAL;
+		goto error;
+	}
+
+	if (se->state != NFC_SE_ENABLED) {
+		rc = -ENODEV;
+		goto error;
+	}
+
+	rc = dev->ops->se_io(dev, se_idx, apdu,
+			apdu_length, cb, cb_context);
+
+error:
+	device_unlock(&dev->dev);
+	return rc;
+}
+
 struct se_io_ctx {
 	u32 dev_idx;
 	u32 se_idx;
@@ -1367,7 +1486,7 @@ static int nfc_genl_se_io(struct sk_buff *skb, struct genl_info *info)
 	ctx->dev_idx = dev_idx;
 	ctx->se_idx = se_idx;
 
-	return dev->ops->se_io(dev, se_idx, apdu, apdu_len, se_io_cb, ctx);
+	return nfc_se_io(dev, se_idx, apdu, apdu_len, se_io_cb, ctx);
 }
 
 static const struct genl_ops nfc_genl_ops[] = {
@@ -1455,12 +1574,17 @@ static const struct genl_ops nfc_genl_ops[] = {
 		.doit = nfc_genl_se_io,
 		.policy = nfc_genl_policy,
 	},
+	{
+		.cmd = NFC_CMD_ACTIVATE_TARGET,
+		.doit = nfc_genl_activate_target,
+		.policy = nfc_genl_policy,
+	},
 };
 
 
 struct urelease_work {
 	struct	work_struct w;
-	int	portid;
+	u32	portid;
 };
 
 static void nfc_urelease_event_work(struct work_struct *work)
diff --git a/net/nfc/nfc.h b/net/nfc/nfc.h
index 88d60064890e..a8ce80b47720 100644
--- a/net/nfc/nfc.h
+++ b/net/nfc/nfc.h
@@ -100,6 +100,8 @@ int nfc_genl_llc_send_sdres(struct nfc_dev *dev, struct hlist_head *sdres_list);
 
 int nfc_genl_se_added(struct nfc_dev *dev, u32 se_idx, u16 type);
 int nfc_genl_se_removed(struct nfc_dev *dev, u32 se_idx);
+int nfc_genl_se_transaction(struct nfc_dev *dev, u8 se_idx,
+			    struct nfc_evt_transaction *evt_transaction);
 
 struct nfc_dev *nfc_get_device(unsigned int idx);
 
diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c
index 11c3544ea546..82b4e8024778 100644
--- a/net/nfc/rawsock.c
+++ b/net/nfc/rawsock.c
@@ -211,8 +211,7 @@ static void rawsock_tx_work(struct work_struct *work)
 	}
 }
 
-static int rawsock_sendmsg(struct kiocb *iocb, struct socket *sock,
-			   struct msghdr *msg, size_t len)
+static int rawsock_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 {
 	struct sock *sk = sock->sk;
 	struct nfc_dev *dev = nfc_rawsock(sk)->dev;
@@ -231,7 +230,7 @@ static int rawsock_sendmsg(struct kiocb *iocb, struct socket *sock,
 	if (skb == NULL)
 		return rc;
 
-	rc = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
+	rc = memcpy_from_msg(skb_put(skb, len), msg, len);
 	if (rc < 0) {
 		kfree_skb(skb);
 		return rc;
@@ -248,8 +247,8 @@ static int rawsock_sendmsg(struct kiocb *iocb, struct socket *sock,
 	return len;
 }
 
-static int rawsock_recvmsg(struct kiocb *iocb, struct socket *sock,
-			   struct msghdr *msg, size_t len, int flags)
+static int rawsock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+			   int flags)
 {
 	int noblock = flags & MSG_DONTWAIT;
 	struct sock *sk = sock->sk;
@@ -269,7 +268,7 @@ static int rawsock_recvmsg(struct kiocb *iocb, struct socket *sock,
 		copied = len;
 	}
 
-	rc = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	rc = skb_copy_datagram_msg(skb, 0, msg, copied);
 
 	skb_free_datagram(sk, skb);
 
diff --git a/net/nonet.c b/net/nonet.c
deleted file mode 100644
index b1a73fda9c12..000000000000
--- a/net/nonet.c
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- * net/nonet.c
- *
- * Dummy functions to allow us to configure network support entirely
- * out of the kernel.
- *
- * Distributed under the terms of the GNU GPL version 2.
- * Copyright (c) Matthew Wilcox 2003
- */
-
-#include <linux/module.h>
-#include <linux/errno.h>
-#include <linux/fs.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-
-static int sock_no_open(struct inode *irrelevant, struct file *dontcare)
-{
-	return -ENXIO;
-}
-
-const struct file_operations bad_sock_fops = {
-	.owner = THIS_MODULE,
-	.open = sock_no_open,
-	.llseek = noop_llseek,
-};
diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig
index ba3bb8203b99..ed6b0f8dd1bb 100644
--- a/net/openvswitch/Kconfig
+++ b/net/openvswitch/Kconfig
@@ -4,7 +4,10 @@
 
 config OPENVSWITCH
 	tristate "Open vSwitch"
+	depends on INET
 	select LIBCRC32C
+	select MPLS
+	select NET_MPLS_GSO
 	---help---
 	  Open vSwitch is a multilayer Ethernet switch targeted at virtualized
 	  environments.  In addition to supporting a variety of features
@@ -29,11 +32,10 @@ config OPENVSWITCH
 	  If unsure, say N.
 
 config OPENVSWITCH_GRE
-	bool "Open vSwitch GRE tunneling support"
-	depends on INET
+	tristate "Open vSwitch GRE tunneling support"
 	depends on OPENVSWITCH
-	depends on NET_IPGRE_DEMUX && !(OPENVSWITCH=y && NET_IPGRE_DEMUX=m)
-	default y
+	depends on NET_IPGRE_DEMUX
+	default OPENVSWITCH
 	---help---
 	  If you say Y here, then the Open vSwitch will be able create GRE
 	  vport.
@@ -43,11 +45,10 @@ config OPENVSWITCH_GRE
 	  If unsure, say Y.
 
 config OPENVSWITCH_VXLAN
-	bool "Open vSwitch VXLAN tunneling support"
-	depends on INET
+	tristate "Open vSwitch VXLAN tunneling support"
 	depends on OPENVSWITCH
-	depends on VXLAN && !(OPENVSWITCH=y && VXLAN=m)
-	default y
+	depends on VXLAN
+	default OPENVSWITCH
 	---help---
 	  If you say Y here, then the Open vSwitch will be able create vxlan vport.
 
@@ -56,11 +57,10 @@ config OPENVSWITCH_VXLAN
 	  If unsure, say Y.
 
 config OPENVSWITCH_GENEVE
-	bool "Open vSwitch Geneve tunneling support"
-	depends on INET
+	tristate "Open vSwitch Geneve tunneling support"
 	depends on OPENVSWITCH
-	depends on GENEVE && !(OPENVSWITCH=y && GENEVE=m)
-	default y
+	depends on GENEVE
+	default OPENVSWITCH
 	---help---
 	  If you say Y here, then the Open vSwitch will be able create geneve vport.
 
diff --git a/net/openvswitch/Makefile b/net/openvswitch/Makefile
index 9a33a273c375..91b9478413ef 100644
--- a/net/openvswitch/Makefile
+++ b/net/openvswitch/Makefile
@@ -15,14 +15,6 @@ openvswitch-y := \
 	vport-internal_dev.o \
 	vport-netdev.o
 
-ifneq ($(CONFIG_OPENVSWITCH_GENEVE),)
-openvswitch-y += vport-geneve.o
-endif
-
-ifneq ($(CONFIG_OPENVSWITCH_VXLAN),)
-openvswitch-y += vport-vxlan.o
-endif
-
-ifneq ($(CONFIG_OPENVSWITCH_GRE),)
-openvswitch-y += vport-gre.o
-endif
+obj-$(CONFIG_OPENVSWITCH_GENEVE)+= vport-geneve.o
+obj-$(CONFIG_OPENVSWITCH_VXLAN)	+= vport-vxlan.o
+obj-$(CONFIG_OPENVSWITCH_GRE)	+= vport-gre.o
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 006886dbee36..b491c1c296fe 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -28,10 +28,12 @@
 #include <linux/in6.h>
 #include <linux/if_arp.h>
 #include <linux/if_vlan.h>
+
 #include <net/ip.h>
 #include <net/ipv6.h>
 #include <net/checksum.h>
 #include <net/dsfield.h>
+#include <net/mpls.h>
 #include <net/sctp/checksum.h>
 
 #include "datapath.h"
@@ -67,7 +69,7 @@ static void action_fifo_init(struct action_fifo *fifo)
 	fifo->tail = 0;
 }
 
-static bool action_fifo_is_empty(struct action_fifo *fifo)
+static bool action_fifo_is_empty(const struct action_fifo *fifo)
 {
 	return (fifo->head == fifo->tail);
 }
@@ -90,7 +92,7 @@ static struct deferred_action *action_fifo_put(struct action_fifo *fifo)
 
 /* Return true if fifo is not full */
 static struct deferred_action *add_deferred_actions(struct sk_buff *skb,
-						    struct sw_flow_key *key,
+						    const struct sw_flow_key *key,
 						    const struct nlattr *attr)
 {
 	struct action_fifo *fifo;
@@ -107,115 +109,172 @@ static struct deferred_action *add_deferred_actions(struct sk_buff *skb,
 	return da;
 }
 
-static int make_writable(struct sk_buff *skb, int write_len)
+static void invalidate_flow_key(struct sw_flow_key *key)
 {
-	if (!pskb_may_pull(skb, write_len))
+	key->eth.type = htons(0);
+}
+
+static bool is_flow_key_valid(const struct sw_flow_key *key)
+{
+	return !!key->eth.type;
+}
+
+static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key,
+		     const struct ovs_action_push_mpls *mpls)
+{
+	__be32 *new_mpls_lse;
+	struct ethhdr *hdr;
+
+	/* Networking stack do not allow simultaneous Tunnel and MPLS GSO. */
+	if (skb->encapsulation)
+		return -ENOTSUPP;
+
+	if (skb_cow_head(skb, MPLS_HLEN) < 0)
 		return -ENOMEM;
 
-	if (!skb_cloned(skb) || skb_clone_writable(skb, write_len))
-		return 0;
+	skb_push(skb, MPLS_HLEN);
+	memmove(skb_mac_header(skb) - MPLS_HLEN, skb_mac_header(skb),
+		skb->mac_len);
+	skb_reset_mac_header(skb);
+
+	new_mpls_lse = (__be32 *)skb_mpls_header(skb);
+	*new_mpls_lse = mpls->mpls_lse;
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		skb->csum = csum_add(skb->csum, csum_partial(new_mpls_lse,
+							     MPLS_HLEN, 0));
+
+	hdr = eth_hdr(skb);
+	hdr->h_proto = mpls->mpls_ethertype;
 
-	return pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
+	if (!skb->inner_protocol)
+		skb_set_inner_protocol(skb, skb->protocol);
+	skb->protocol = mpls->mpls_ethertype;
+
+	invalidate_flow_key(key);
+	return 0;
 }
 
-/* remove VLAN header from packet and update csum accordingly. */
-static int __pop_vlan_tci(struct sk_buff *skb, __be16 *current_tci)
+static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key,
+		    const __be16 ethertype)
 {
-	struct vlan_hdr *vhdr;
+	struct ethhdr *hdr;
 	int err;
 
-	err = make_writable(skb, VLAN_ETH_HLEN);
+	err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
 	if (unlikely(err))
 		return err;
 
-	if (skb->ip_summed == CHECKSUM_COMPLETE)
-		skb->csum = csum_sub(skb->csum, csum_partial(skb->data
-					+ (2 * ETH_ALEN), VLAN_HLEN, 0));
+	skb_postpull_rcsum(skb, skb_mpls_header(skb), MPLS_HLEN);
 
-	vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN);
-	*current_tci = vhdr->h_vlan_TCI;
+	memmove(skb_mac_header(skb) + MPLS_HLEN, skb_mac_header(skb),
+		skb->mac_len);
 
-	memmove(skb->data + VLAN_HLEN, skb->data, 2 * ETH_ALEN);
-	__skb_pull(skb, VLAN_HLEN);
+	__skb_pull(skb, MPLS_HLEN);
+	skb_reset_mac_header(skb);
 
-	vlan_set_encap_proto(skb, vhdr);
-	skb->mac_header += VLAN_HLEN;
-	if (skb_network_offset(skb) < ETH_HLEN)
-		skb_set_network_header(skb, ETH_HLEN);
-	skb_reset_mac_len(skb);
+	/* skb_mpls_header() is used to locate the ethertype
+	 * field correctly in the presence of VLAN tags.
+	 */
+	hdr = (struct ethhdr *)(skb_mpls_header(skb) - ETH_HLEN);
+	hdr->h_proto = ethertype;
+	if (eth_p_mpls(skb->protocol))
+		skb->protocol = ethertype;
 
+	invalidate_flow_key(key);
 	return 0;
 }
 
-static int pop_vlan(struct sk_buff *skb)
+/* 'KEY' must not have any bits set outside of the 'MASK' */
+#define MASKED(OLD, KEY, MASK) ((KEY) | ((OLD) & ~(MASK)))
+#define SET_MASKED(OLD, KEY, MASK) ((OLD) = MASKED(OLD, KEY, MASK))
+
+static int set_mpls(struct sk_buff *skb, struct sw_flow_key *flow_key,
+		    const __be32 *mpls_lse, const __be32 *mask)
 {
-	__be16 tci;
+	__be32 *stack;
+	__be32 lse;
 	int err;
 
-	if (likely(vlan_tx_tag_present(skb))) {
-		skb->vlan_tci = 0;
-	} else {
-		if (unlikely(skb->protocol != htons(ETH_P_8021Q) ||
-			     skb->len < VLAN_ETH_HLEN))
-			return 0;
-
-		err = __pop_vlan_tci(skb, &tci);
-		if (err)
-			return err;
-	}
-	/* move next vlan tag to hw accel tag */
-	if (likely(skb->protocol != htons(ETH_P_8021Q) ||
-		   skb->len < VLAN_ETH_HLEN))
-		return 0;
-
-	err = __pop_vlan_tci(skb, &tci);
+	err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
 	if (unlikely(err))
 		return err;
 
-	__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), ntohs(tci));
+	stack = (__be32 *)skb_mpls_header(skb);
+	lse = MASKED(*stack, *mpls_lse, *mask);
+	if (skb->ip_summed == CHECKSUM_COMPLETE) {
+		__be32 diff[] = { ~(*stack), lse };
+
+		skb->csum = ~csum_partial((char *)diff, sizeof(diff),
+					  ~skb->csum);
+	}
+
+	*stack = lse;
+	flow_key->mpls.top_lse = lse;
 	return 0;
 }
 
-static int push_vlan(struct sk_buff *skb, const struct ovs_action_push_vlan *vlan)
+static int pop_vlan(struct sk_buff *skb, struct sw_flow_key *key)
 {
-	if (unlikely(vlan_tx_tag_present(skb))) {
-		u16 current_tag;
+	int err;
 
-		/* push down current VLAN tag */
-		current_tag = vlan_tx_tag_get(skb);
+	err = skb_vlan_pop(skb);
+	if (skb_vlan_tag_present(skb))
+		invalidate_flow_key(key);
+	else
+		key->eth.tci = 0;
+	return err;
+}
 
-		if (!__vlan_put_tag(skb, skb->vlan_proto, current_tag))
-			return -ENOMEM;
+static int push_vlan(struct sk_buff *skb, struct sw_flow_key *key,
+		     const struct ovs_action_push_vlan *vlan)
+{
+	if (skb_vlan_tag_present(skb))
+		invalidate_flow_key(key);
+	else
+		key->eth.tci = vlan->vlan_tci;
+	return skb_vlan_push(skb, vlan->vlan_tpid,
+			     ntohs(vlan->vlan_tci) & ~VLAN_TAG_PRESENT);
+}
 
-		if (skb->ip_summed == CHECKSUM_COMPLETE)
-			skb->csum = csum_add(skb->csum, csum_partial(skb->data
-					+ (2 * ETH_ALEN), VLAN_HLEN, 0));
+/* 'src' is already properly masked. */
+static void ether_addr_copy_masked(u8 *dst_, const u8 *src_, const u8 *mask_)
+{
+	u16 *dst = (u16 *)dst_;
+	const u16 *src = (const u16 *)src_;
+	const u16 *mask = (const u16 *)mask_;
 
-	}
-	__vlan_hwaccel_put_tag(skb, vlan->vlan_tpid, ntohs(vlan->vlan_tci) & ~VLAN_TAG_PRESENT);
-	return 0;
+	SET_MASKED(dst[0], src[0], mask[0]);
+	SET_MASKED(dst[1], src[1], mask[1]);
+	SET_MASKED(dst[2], src[2], mask[2]);
 }
 
-static int set_eth_addr(struct sk_buff *skb,
-			const struct ovs_key_ethernet *eth_key)
+static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *flow_key,
+			const struct ovs_key_ethernet *key,
+			const struct ovs_key_ethernet *mask)
 {
 	int err;
-	err = make_writable(skb, ETH_HLEN);
+
+	err = skb_ensure_writable(skb, ETH_HLEN);
 	if (unlikely(err))
 		return err;
 
 	skb_postpull_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
 
-	ether_addr_copy(eth_hdr(skb)->h_source, eth_key->eth_src);
-	ether_addr_copy(eth_hdr(skb)->h_dest, eth_key->eth_dst);
+	ether_addr_copy_masked(eth_hdr(skb)->h_source, key->eth_src,
+			       mask->eth_src);
+	ether_addr_copy_masked(eth_hdr(skb)->h_dest, key->eth_dst,
+			       mask->eth_dst);
 
 	ovs_skb_postpush_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
 
+	ether_addr_copy(flow_key->eth.src, eth_hdr(skb)->h_source);
+	ether_addr_copy(flow_key->eth.dst, eth_hdr(skb)->h_dest);
 	return 0;
 }
 
 static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh,
-				__be32 *addr, __be32 new_addr)
+			__be32 *addr, __be32 new_addr)
 {
 	int transport_len = skb->len - skb_transport_offset(skb);
 
@@ -246,11 +305,11 @@ static void update_ipv6_checksum(struct sk_buff *skb, u8 l4_proto,
 {
 	int transport_len = skb->len - skb_transport_offset(skb);
 
-	if (l4_proto == IPPROTO_TCP) {
+	if (l4_proto == NEXTHDR_TCP) {
 		if (likely(transport_len >= sizeof(struct tcphdr)))
 			inet_proto_csum_replace16(&tcp_hdr(skb)->check, skb,
 						  addr, new_addr, 1);
-	} else if (l4_proto == IPPROTO_UDP) {
+	} else if (l4_proto == NEXTHDR_UDP) {
 		if (likely(transport_len >= sizeof(struct udphdr))) {
 			struct udphdr *uh = udp_hdr(skb);
 
@@ -261,9 +320,22 @@ static void update_ipv6_checksum(struct sk_buff *skb, u8 l4_proto,
 					uh->check = CSUM_MANGLED_0;
 			}
 		}
+	} else if (l4_proto == NEXTHDR_ICMP) {
+		if (likely(transport_len >= sizeof(struct icmp6hdr)))
+			inet_proto_csum_replace16(&icmp6_hdr(skb)->icmp6_cksum,
+						  skb, addr, new_addr, 1);
 	}
 }
 
+static void mask_ipv6_addr(const __be32 old[4], const __be32 addr[4],
+			   const __be32 mask[4], __be32 masked[4])
+{
+	masked[0] = MASKED(old[0], addr[0], mask[0]);
+	masked[1] = MASKED(old[1], addr[1], mask[1]);
+	masked[2] = MASKED(old[2], addr[2], mask[2]);
+	masked[3] = MASKED(old[3], addr[3], mask[3]);
+}
+
 static void set_ipv6_addr(struct sk_buff *skb, u8 l4_proto,
 			  __be32 addr[4], const __be32 new_addr[4],
 			  bool recalculate_csum)
@@ -275,218 +347,278 @@ static void set_ipv6_addr(struct sk_buff *skb, u8 l4_proto,
 	memcpy(addr, new_addr, sizeof(__be32[4]));
 }
 
-static void set_ipv6_tc(struct ipv6hdr *nh, u8 tc)
+static void set_ipv6_fl(struct ipv6hdr *nh, u32 fl, u32 mask)
 {
-	nh->priority = tc >> 4;
-	nh->flow_lbl[0] = (nh->flow_lbl[0] & 0x0F) | ((tc & 0x0F) << 4);
+	/* Bits 21-24 are always unmasked, so this retains their values. */
+	SET_MASKED(nh->flow_lbl[0], (u8)(fl >> 16), (u8)(mask >> 16));
+	SET_MASKED(nh->flow_lbl[1], (u8)(fl >> 8), (u8)(mask >> 8));
+	SET_MASKED(nh->flow_lbl[2], (u8)fl, (u8)mask);
 }
 
-static void set_ipv6_fl(struct ipv6hdr *nh, u32 fl)
+static void set_ip_ttl(struct sk_buff *skb, struct iphdr *nh, u8 new_ttl,
+		       u8 mask)
 {
-	nh->flow_lbl[0] = (nh->flow_lbl[0] & 0xF0) | (fl & 0x000F0000) >> 16;
-	nh->flow_lbl[1] = (fl & 0x0000FF00) >> 8;
-	nh->flow_lbl[2] = fl & 0x000000FF;
-}
+	new_ttl = MASKED(nh->ttl, new_ttl, mask);
 
-static void set_ip_ttl(struct sk_buff *skb, struct iphdr *nh, u8 new_ttl)
-{
 	csum_replace2(&nh->check, htons(nh->ttl << 8), htons(new_ttl << 8));
 	nh->ttl = new_ttl;
 }
 
-static int set_ipv4(struct sk_buff *skb, const struct ovs_key_ipv4 *ipv4_key)
+static int set_ipv4(struct sk_buff *skb, struct sw_flow_key *flow_key,
+		    const struct ovs_key_ipv4 *key,
+		    const struct ovs_key_ipv4 *mask)
 {
 	struct iphdr *nh;
+	__be32 new_addr;
 	int err;
 
-	err = make_writable(skb, skb_network_offset(skb) +
-				 sizeof(struct iphdr));
+	err = skb_ensure_writable(skb, skb_network_offset(skb) +
+				  sizeof(struct iphdr));
 	if (unlikely(err))
 		return err;
 
 	nh = ip_hdr(skb);
 
-	if (ipv4_key->ipv4_src != nh->saddr)
-		set_ip_addr(skb, nh, &nh->saddr, ipv4_key->ipv4_src);
-
-	if (ipv4_key->ipv4_dst != nh->daddr)
-		set_ip_addr(skb, nh, &nh->daddr, ipv4_key->ipv4_dst);
+	/* Setting an IP addresses is typically only a side effect of
+	 * matching on them in the current userspace implementation, so it
+	 * makes sense to check if the value actually changed.
+	 */
+	if (mask->ipv4_src) {
+		new_addr = MASKED(nh->saddr, key->ipv4_src, mask->ipv4_src);
 
-	if (ipv4_key->ipv4_tos != nh->tos)
-		ipv4_change_dsfield(nh, 0, ipv4_key->ipv4_tos);
+		if (unlikely(new_addr != nh->saddr)) {
+			set_ip_addr(skb, nh, &nh->saddr, new_addr);
+			flow_key->ipv4.addr.src = new_addr;
+		}
+	}
+	if (mask->ipv4_dst) {
+		new_addr = MASKED(nh->daddr, key->ipv4_dst, mask->ipv4_dst);
 
-	if (ipv4_key->ipv4_ttl != nh->ttl)
-		set_ip_ttl(skb, nh, ipv4_key->ipv4_ttl);
+		if (unlikely(new_addr != nh->daddr)) {
+			set_ip_addr(skb, nh, &nh->daddr, new_addr);
+			flow_key->ipv4.addr.dst = new_addr;
+		}
+	}
+	if (mask->ipv4_tos) {
+		ipv4_change_dsfield(nh, ~mask->ipv4_tos, key->ipv4_tos);
+		flow_key->ip.tos = nh->tos;
+	}
+	if (mask->ipv4_ttl) {
+		set_ip_ttl(skb, nh, key->ipv4_ttl, mask->ipv4_ttl);
+		flow_key->ip.ttl = nh->ttl;
+	}
 
 	return 0;
 }
 
-static int set_ipv6(struct sk_buff *skb, const struct ovs_key_ipv6 *ipv6_key)
+static bool is_ipv6_mask_nonzero(const __be32 addr[4])
+{
+	return !!(addr[0] | addr[1] | addr[2] | addr[3]);
+}
+
+static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key,
+		    const struct ovs_key_ipv6 *key,
+		    const struct ovs_key_ipv6 *mask)
 {
 	struct ipv6hdr *nh;
 	int err;
-	__be32 *saddr;
-	__be32 *daddr;
 
-	err = make_writable(skb, skb_network_offset(skb) +
-			    sizeof(struct ipv6hdr));
+	err = skb_ensure_writable(skb, skb_network_offset(skb) +
+				  sizeof(struct ipv6hdr));
 	if (unlikely(err))
 		return err;
 
 	nh = ipv6_hdr(skb);
-	saddr = (__be32 *)&nh->saddr;
-	daddr = (__be32 *)&nh->daddr;
 
-	if (memcmp(ipv6_key->ipv6_src, saddr, sizeof(ipv6_key->ipv6_src)))
-		set_ipv6_addr(skb, ipv6_key->ipv6_proto, saddr,
-			      ipv6_key->ipv6_src, true);
+	/* Setting an IP addresses is typically only a side effect of
+	 * matching on them in the current userspace implementation, so it
+	 * makes sense to check if the value actually changed.
+	 */
+	if (is_ipv6_mask_nonzero(mask->ipv6_src)) {
+		__be32 *saddr = (__be32 *)&nh->saddr;
+		__be32 masked[4];
 
-	if (memcmp(ipv6_key->ipv6_dst, daddr, sizeof(ipv6_key->ipv6_dst))) {
+		mask_ipv6_addr(saddr, key->ipv6_src, mask->ipv6_src, masked);
+
+		if (unlikely(memcmp(saddr, masked, sizeof(masked)))) {
+			set_ipv6_addr(skb, key->ipv6_proto, saddr, masked,
+				      true);
+			memcpy(&flow_key->ipv6.addr.src, masked,
+			       sizeof(flow_key->ipv6.addr.src));
+		}
+	}
+	if (is_ipv6_mask_nonzero(mask->ipv6_dst)) {
 		unsigned int offset = 0;
 		int flags = IP6_FH_F_SKIP_RH;
 		bool recalc_csum = true;
-
-		if (ipv6_ext_hdr(nh->nexthdr))
-			recalc_csum = ipv6_find_hdr(skb, &offset,
-						    NEXTHDR_ROUTING, NULL,
-						    &flags) != NEXTHDR_ROUTING;
-
-		set_ipv6_addr(skb, ipv6_key->ipv6_proto, daddr,
-			      ipv6_key->ipv6_dst, recalc_csum);
+		__be32 *daddr = (__be32 *)&nh->daddr;
+		__be32 masked[4];
+
+		mask_ipv6_addr(daddr, key->ipv6_dst, mask->ipv6_dst, masked);
+
+		if (unlikely(memcmp(daddr, masked, sizeof(masked)))) {
+			if (ipv6_ext_hdr(nh->nexthdr))
+				recalc_csum = (ipv6_find_hdr(skb, &offset,
+							     NEXTHDR_ROUTING,
+							     NULL, &flags)
+					       != NEXTHDR_ROUTING);
+
+			set_ipv6_addr(skb, key->ipv6_proto, daddr, masked,
+				      recalc_csum);
+			memcpy(&flow_key->ipv6.addr.dst, masked,
+			       sizeof(flow_key->ipv6.addr.dst));
+		}
+	}
+	if (mask->ipv6_tclass) {
+		ipv6_change_dsfield(nh, ~mask->ipv6_tclass, key->ipv6_tclass);
+		flow_key->ip.tos = ipv6_get_dsfield(nh);
+	}
+	if (mask->ipv6_label) {
+		set_ipv6_fl(nh, ntohl(key->ipv6_label),
+			    ntohl(mask->ipv6_label));
+		flow_key->ipv6.label =
+		    *(__be32 *)nh & htonl(IPV6_FLOWINFO_FLOWLABEL);
+	}
+	if (mask->ipv6_hlimit) {
+		SET_MASKED(nh->hop_limit, key->ipv6_hlimit, mask->ipv6_hlimit);
+		flow_key->ip.ttl = nh->hop_limit;
 	}
-
-	set_ipv6_tc(nh, ipv6_key->ipv6_tclass);
-	set_ipv6_fl(nh, ntohl(ipv6_key->ipv6_label));
-	nh->hop_limit = ipv6_key->ipv6_hlimit;
-
 	return 0;
 }
 
-/* Must follow make_writable() since that can move the skb data. */
+/* Must follow skb_ensure_writable() since that can move the skb data. */
 static void set_tp_port(struct sk_buff *skb, __be16 *port,
-			 __be16 new_port, __sum16 *check)
+			__be16 new_port, __sum16 *check)
 {
 	inet_proto_csum_replace2(check, skb, *port, new_port, 0);
 	*port = new_port;
-	skb_clear_hash(skb);
 }
 
-static void set_udp_port(struct sk_buff *skb, __be16 *port, __be16 new_port)
-{
-	struct udphdr *uh = udp_hdr(skb);
-
-	if (uh->check && skb->ip_summed != CHECKSUM_PARTIAL) {
-		set_tp_port(skb, port, new_port, &uh->check);
-
-		if (!uh->check)
-			uh->check = CSUM_MANGLED_0;
-	} else {
-		*port = new_port;
-		skb_clear_hash(skb);
-	}
-}
-
-static int set_udp(struct sk_buff *skb, const struct ovs_key_udp *udp_port_key)
+static int set_udp(struct sk_buff *skb, struct sw_flow_key *flow_key,
+		   const struct ovs_key_udp *key,
+		   const struct ovs_key_udp *mask)
 {
 	struct udphdr *uh;
+	__be16 src, dst;
 	int err;
 
-	err = make_writable(skb, skb_transport_offset(skb) +
-				 sizeof(struct udphdr));
+	err = skb_ensure_writable(skb, skb_transport_offset(skb) +
+				  sizeof(struct udphdr));
 	if (unlikely(err))
 		return err;
 
 	uh = udp_hdr(skb);
-	if (udp_port_key->udp_src != uh->source)
-		set_udp_port(skb, &uh->source, udp_port_key->udp_src);
+	/* Either of the masks is non-zero, so do not bother checking them. */
+	src = MASKED(uh->source, key->udp_src, mask->udp_src);
+	dst = MASKED(uh->dest, key->udp_dst, mask->udp_dst);
 
-	if (udp_port_key->udp_dst != uh->dest)
-		set_udp_port(skb, &uh->dest, udp_port_key->udp_dst);
+	if (uh->check && skb->ip_summed != CHECKSUM_PARTIAL) {
+		if (likely(src != uh->source)) {
+			set_tp_port(skb, &uh->source, src, &uh->check);
+			flow_key->tp.src = src;
+		}
+		if (likely(dst != uh->dest)) {
+			set_tp_port(skb, &uh->dest, dst, &uh->check);
+			flow_key->tp.dst = dst;
+		}
+
+		if (unlikely(!uh->check))
+			uh->check = CSUM_MANGLED_0;
+	} else {
+		uh->source = src;
+		uh->dest = dst;
+		flow_key->tp.src = src;
+		flow_key->tp.dst = dst;
+	}
+
+	skb_clear_hash(skb);
 
 	return 0;
 }
 
-static int set_tcp(struct sk_buff *skb, const struct ovs_key_tcp *tcp_port_key)
+static int set_tcp(struct sk_buff *skb, struct sw_flow_key *flow_key,
+		   const struct ovs_key_tcp *key,
+		   const struct ovs_key_tcp *mask)
 {
 	struct tcphdr *th;
+	__be16 src, dst;
 	int err;
 
-	err = make_writable(skb, skb_transport_offset(skb) +
-				 sizeof(struct tcphdr));
+	err = skb_ensure_writable(skb, skb_transport_offset(skb) +
+				  sizeof(struct tcphdr));
 	if (unlikely(err))
 		return err;
 
 	th = tcp_hdr(skb);
-	if (tcp_port_key->tcp_src != th->source)
-		set_tp_port(skb, &th->source, tcp_port_key->tcp_src, &th->check);
-
-	if (tcp_port_key->tcp_dst != th->dest)
-		set_tp_port(skb, &th->dest, tcp_port_key->tcp_dst, &th->check);
+	src = MASKED(th->source, key->tcp_src, mask->tcp_src);
+	if (likely(src != th->source)) {
+		set_tp_port(skb, &th->source, src, &th->check);
+		flow_key->tp.src = src;
+	}
+	dst = MASKED(th->dest, key->tcp_dst, mask->tcp_dst);
+	if (likely(dst != th->dest)) {
+		set_tp_port(skb, &th->dest, dst, &th->check);
+		flow_key->tp.dst = dst;
+	}
+	skb_clear_hash(skb);
 
 	return 0;
 }
 
-static int set_sctp(struct sk_buff *skb,
-		     const struct ovs_key_sctp *sctp_port_key)
+static int set_sctp(struct sk_buff *skb, struct sw_flow_key *flow_key,
+		    const struct ovs_key_sctp *key,
+		    const struct ovs_key_sctp *mask)
 {
+	unsigned int sctphoff = skb_transport_offset(skb);
 	struct sctphdr *sh;
+	__le32 old_correct_csum, new_csum, old_csum;
 	int err;
-	unsigned int sctphoff = skb_transport_offset(skb);
 
-	err = make_writable(skb, sctphoff + sizeof(struct sctphdr));
+	err = skb_ensure_writable(skb, sctphoff + sizeof(struct sctphdr));
 	if (unlikely(err))
 		return err;
 
 	sh = sctp_hdr(skb);
-	if (sctp_port_key->sctp_src != sh->source ||
-	    sctp_port_key->sctp_dst != sh->dest) {
-		__le32 old_correct_csum, new_csum, old_csum;
-
-		old_csum = sh->checksum;
-		old_correct_csum = sctp_compute_cksum(skb, sctphoff);
+	old_csum = sh->checksum;
+	old_correct_csum = sctp_compute_cksum(skb, sctphoff);
 
-		sh->source = sctp_port_key->sctp_src;
-		sh->dest = sctp_port_key->sctp_dst;
+	sh->source = MASKED(sh->source, key->sctp_src, mask->sctp_src);
+	sh->dest = MASKED(sh->dest, key->sctp_dst, mask->sctp_dst);
 
-		new_csum = sctp_compute_cksum(skb, sctphoff);
+	new_csum = sctp_compute_cksum(skb, sctphoff);
 
-		/* Carry any checksum errors through. */
-		sh->checksum = old_csum ^ old_correct_csum ^ new_csum;
+	/* Carry any checksum errors through. */
+	sh->checksum = old_csum ^ old_correct_csum ^ new_csum;
 
-		skb_clear_hash(skb);
-	}
+	skb_clear_hash(skb);
+	flow_key->tp.src = sh->source;
+	flow_key->tp.dst = sh->dest;
 
 	return 0;
 }
 
-static int do_output(struct datapath *dp, struct sk_buff *skb, int out_port)
+static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port)
 {
-	struct vport *vport;
+	struct vport *vport = ovs_vport_rcu(dp, out_port);
 
-	if (unlikely(!skb))
-		return -ENOMEM;
-
-	vport = ovs_vport_rcu(dp, out_port);
-	if (unlikely(!vport)) {
+	if (likely(vport))
+		ovs_vport_send(vport, skb);
+	else
 		kfree_skb(skb);
-		return -ENODEV;
-	}
-
-	ovs_vport_send(vport, skb);
-	return 0;
 }
 
 static int output_userspace(struct datapath *dp, struct sk_buff *skb,
 			    struct sw_flow_key *key, const struct nlattr *attr)
 {
+	struct ovs_tunnel_info info;
 	struct dp_upcall_info upcall;
 	const struct nlattr *a;
 	int rem;
 
 	upcall.cmd = OVS_PACKET_CMD_ACTION;
-	upcall.key = key;
 	upcall.userdata = NULL;
 	upcall.portid = 0;
+	upcall.egress_tun_info = NULL;
 
 	for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
 		 a = nla_next(a, &rem)) {
@@ -498,15 +630,27 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb,
 		case OVS_USERSPACE_ATTR_PID:
 			upcall.portid = nla_get_u32(a);
 			break;
+
+		case OVS_USERSPACE_ATTR_EGRESS_TUN_PORT: {
+			/* Get out tunnel info. */
+			struct vport *vport;
+
+			vport = ovs_vport_rcu(dp, nla_get_u32(a));
+			if (vport) {
+				int err;
+
+				err = ovs_vport_get_egress_tun_info(vport, skb,
+								    &info);
+				if (!err)
+					upcall.egress_tun_info = &info;
+			}
+			break;
 		}
-	}
 
-	return ovs_dp_upcall(dp, skb, &upcall);
-}
+		} /* End of switch. */
+	}
 
-static bool last_action(const struct nlattr *a, int rem)
-{
-	return a->nla_len == rem;
+	return ovs_dp_upcall(dp, skb, key, &upcall);
 }
 
 static int sample(struct datapath *dp, struct sk_buff *skb,
@@ -543,7 +687,7 @@ static int sample(struct datapath *dp, struct sk_buff *skb,
 	 * user space. This skb will be consumed by its caller.
 	 */
 	if (likely(nla_type(a) == OVS_ACTION_ATTR_USERSPACE &&
-		   last_action(a, rem)))
+		   nla_is_last(a, rem)))
 		return output_userspace(dp, skb, key, a);
 
 	skb = skb_clone(skb, GFP_ATOMIC);
@@ -577,45 +721,76 @@ static void execute_hash(struct sk_buff *skb, struct sw_flow_key *key,
 }
 
 static int execute_set_action(struct sk_buff *skb,
-				 const struct nlattr *nested_attr)
+			      struct sw_flow_key *flow_key,
+			      const struct nlattr *a)
+{
+	/* Only tunnel set execution is supported without a mask. */
+	if (nla_type(a) == OVS_KEY_ATTR_TUNNEL_INFO) {
+		OVS_CB(skb)->egress_tun_info = nla_data(a);
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+/* Mask is at the midpoint of the data. */
+#define get_mask(a, type) ((const type)nla_data(a) + 1)
+
+static int execute_masked_set_action(struct sk_buff *skb,
+				     struct sw_flow_key *flow_key,
+				     const struct nlattr *a)
 {
 	int err = 0;
 
-	switch (nla_type(nested_attr)) {
+	switch (nla_type(a)) {
 	case OVS_KEY_ATTR_PRIORITY:
-		skb->priority = nla_get_u32(nested_attr);
+		SET_MASKED(skb->priority, nla_get_u32(a), *get_mask(a, u32 *));
+		flow_key->phy.priority = skb->priority;
 		break;
 
 	case OVS_KEY_ATTR_SKB_MARK:
-		skb->mark = nla_get_u32(nested_attr);
+		SET_MASKED(skb->mark, nla_get_u32(a), *get_mask(a, u32 *));
+		flow_key->phy.skb_mark = skb->mark;
 		break;
 
 	case OVS_KEY_ATTR_TUNNEL_INFO:
-		OVS_CB(skb)->egress_tun_info = nla_data(nested_attr);
+		/* Masked data not supported for tunnel. */
+		err = -EINVAL;
 		break;
 
 	case OVS_KEY_ATTR_ETHERNET:
-		err = set_eth_addr(skb, nla_data(nested_attr));
+		err = set_eth_addr(skb, flow_key, nla_data(a),
+				   get_mask(a, struct ovs_key_ethernet *));
 		break;
 
 	case OVS_KEY_ATTR_IPV4:
-		err = set_ipv4(skb, nla_data(nested_attr));
+		err = set_ipv4(skb, flow_key, nla_data(a),
+			       get_mask(a, struct ovs_key_ipv4 *));
 		break;
 
 	case OVS_KEY_ATTR_IPV6:
-		err = set_ipv6(skb, nla_data(nested_attr));
+		err = set_ipv6(skb, flow_key, nla_data(a),
+			       get_mask(a, struct ovs_key_ipv6 *));
 		break;
 
 	case OVS_KEY_ATTR_TCP:
-		err = set_tcp(skb, nla_data(nested_attr));
+		err = set_tcp(skb, flow_key, nla_data(a),
+			      get_mask(a, struct ovs_key_tcp *));
 		break;
 
 	case OVS_KEY_ATTR_UDP:
-		err = set_udp(skb, nla_data(nested_attr));
+		err = set_udp(skb, flow_key, nla_data(a),
+			      get_mask(a, struct ovs_key_udp *));
 		break;
 
 	case OVS_KEY_ATTR_SCTP:
-		err = set_sctp(skb, nla_data(nested_attr));
+		err = set_sctp(skb, flow_key, nla_data(a),
+			       get_mask(a, struct ovs_key_sctp *));
+		break;
+
+	case OVS_KEY_ATTR_MPLS:
+		err = set_mpls(skb, flow_key, nla_data(a), get_mask(a,
+								    __be32 *));
 		break;
 	}
 
@@ -627,13 +802,17 @@ static int execute_recirc(struct datapath *dp, struct sk_buff *skb,
 			  const struct nlattr *a, int rem)
 {
 	struct deferred_action *da;
-	int err;
 
-	err = ovs_flow_key_update(skb, key);
-	if (err)
-		return err;
+	if (!is_flow_key_valid(key)) {
+		int err;
+
+		err = ovs_flow_key_update(skb, key);
+		if (err)
+			return err;
+	}
+	BUG_ON(!is_flow_key_valid(key));
 
-	if (!last_action(a, rem)) {
+	if (!nla_is_last(a, rem)) {
 		/* Recirc action is the not the last action
 		 * of the action list, need to clone the skb.
 		 */
@@ -668,7 +847,8 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 	/* Every output action needs a separate clone of 'skb', but the common
 	 * case is just a single output action, so that doing a clone and
 	 * then freeing the original skbuff is wasteful.  So the following code
-	 * is slightly obscure just to avoid that. */
+	 * is slightly obscure just to avoid that.
+	 */
 	int prev_port = -1;
 	const struct nlattr *a;
 	int rem;
@@ -677,8 +857,12 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 	     a = nla_next(a, &rem)) {
 		int err = 0;
 
-		if (prev_port != -1) {
-			do_output(dp, skb_clone(skb, GFP_ATOMIC), prev_port);
+		if (unlikely(prev_port != -1)) {
+			struct sk_buff *out_skb = skb_clone(skb, GFP_ATOMIC);
+
+			if (out_skb)
+				do_output(dp, out_skb, prev_port);
+
 			prev_port = -1;
 		}
 
@@ -695,19 +879,25 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			execute_hash(skb, key, a);
 			break;
 
+		case OVS_ACTION_ATTR_PUSH_MPLS:
+			err = push_mpls(skb, key, nla_data(a));
+			break;
+
+		case OVS_ACTION_ATTR_POP_MPLS:
+			err = pop_mpls(skb, key, nla_get_be16(a));
+			break;
+
 		case OVS_ACTION_ATTR_PUSH_VLAN:
-			err = push_vlan(skb, nla_data(a));
-			if (unlikely(err)) /* skb already freed. */
-				return err;
+			err = push_vlan(skb, key, nla_data(a));
 			break;
 
 		case OVS_ACTION_ATTR_POP_VLAN:
-			err = pop_vlan(skb);
+			err = pop_vlan(skb, key);
 			break;
 
 		case OVS_ACTION_ATTR_RECIRC:
 			err = execute_recirc(dp, skb, key, a, rem);
-			if (last_action(a, rem)) {
+			if (nla_is_last(a, rem)) {
 				/* If this is the last action, the skb has
 				 * been consumed or freed.
 				 * Return immediately.
@@ -717,13 +907,16 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			break;
 
 		case OVS_ACTION_ATTR_SET:
-			err = execute_set_action(skb, nla_data(a));
+			err = execute_set_action(skb, key, nla_data(a));
+			break;
+
+		case OVS_ACTION_ATTR_SET_MASKED:
+		case OVS_ACTION_ATTR_SET_TO_MASKED:
+			err = execute_masked_set_action(skb, key, nla_data(a));
 			break;
 
 		case OVS_ACTION_ATTR_SAMPLE:
 			err = sample(dp, skb, key, a);
-			if (unlikely(err)) /* skb already freed. */
-				return err;
 			break;
 		}
 
@@ -769,14 +962,12 @@ static void process_deferred_actions(struct datapath *dp)
 
 /* Execute a list of actions against 'skb'. */
 int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
+			const struct sw_flow_actions *acts,
 			struct sw_flow_key *key)
 {
 	int level = this_cpu_read(exec_actions_level);
-	struct sw_flow_actions *acts;
 	int err;
 
-	acts = rcu_dereference(OVS_CB(skb)->flow->sf_acts);
-
 	this_cpu_inc(exec_actions_level);
 	OVS_CB(skb)->egress_tun_info = NULL;
 	err = do_execute_actions(dp, skb, key,
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index e6d7255183eb..096c6276e6b9 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -59,11 +59,14 @@
 #include "vport-netdev.h"
 
 int ovs_net_id __read_mostly;
+EXPORT_SYMBOL_GPL(ovs_net_id);
 
 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 const struct nla_policy flow_policy[];
+
 static const struct genl_multicast_group ovs_dp_flow_multicast_group = {
 	.name = OVS_FLOW_MCGROUP,
 };
@@ -82,8 +85,7 @@ static bool ovs_must_notify(struct genl_family *family, struct genl_info *info,
 			    unsigned int group)
 {
 	return info->nlhdr->nlmsg_flags & NLM_F_ECHO ||
-	       genl_has_listeners(family, genl_info_net(info)->genl_sock,
-				  group);
+	       genl_has_listeners(family, genl_info_net(info), group);
 }
 
 static void ovs_notify(struct genl_family *family,
@@ -130,27 +132,41 @@ int lockdep_ovsl_is_held(void)
 	else
 		return 1;
 }
+EXPORT_SYMBOL_GPL(lockdep_ovsl_is_held);
 #endif
 
 static struct vport *new_vport(const struct vport_parms *);
 static int queue_gso_packets(struct datapath *dp, struct sk_buff *,
+			     const struct sw_flow_key *,
 			     const struct dp_upcall_info *);
 static int queue_userspace_packet(struct datapath *dp, struct sk_buff *,
+				  const struct sw_flow_key *,
 				  const struct dp_upcall_info *);
 
-/* Must be called with rcu_read_lock or ovs_mutex. */
-static struct datapath *get_dp(struct net *net, int dp_ifindex)
+/* Must be called with rcu_read_lock. */
+static struct datapath *get_dp_rcu(struct net *net, int dp_ifindex)
 {
-	struct datapath *dp = NULL;
-	struct net_device *dev;
+	struct net_device *dev = dev_get_by_index_rcu(net, dp_ifindex);
 
-	rcu_read_lock();
-	dev = dev_get_by_index_rcu(net, dp_ifindex);
 	if (dev) {
 		struct vport *vport = ovs_internal_dev_get_vport(dev);
 		if (vport)
-			dp = vport->dp;
+			return vport->dp;
 	}
+
+	return NULL;
+}
+
+/* The caller must hold either ovs_mutex or rcu_read_lock to keep the
+ * returned dp pointer valid.
+ */
+static inline struct datapath *get_dp(struct net *net, int dp_ifindex)
+{
+	struct datapath *dp;
+
+	WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_ovsl_is_held());
+	rcu_read_lock();
+	dp = get_dp_rcu(net, dp_ifindex);
 	rcu_read_unlock();
 
 	return dp;
@@ -163,7 +179,7 @@ const char *ovs_dp_name(const struct datapath *dp)
 	return vport->ops->get_name(vport);
 }
 
-static int get_dpifindex(struct datapath *dp)
+static int get_dpifindex(const struct datapath *dp)
 {
 	struct vport *local;
 	int ifindex;
@@ -185,8 +201,8 @@ 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);
 	kfree(dp);
 }
@@ -243,6 +259,7 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key)
 	const struct vport *p = OVS_CB(skb)->input_vport;
 	struct datapath *dp = p->dp;
 	struct sw_flow *flow;
+	struct sw_flow_actions *sf_acts;
 	struct dp_stats_percpu *stats;
 	u64 *stats_counter;
 	u32 n_mask_hit;
@@ -256,10 +273,10 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key)
 		int error;
 
 		upcall.cmd = OVS_PACKET_CMD_MISS;
-		upcall.key = key;
 		upcall.userdata = NULL;
 		upcall.portid = ovs_vport_find_upcall_portid(p, skb);
-		error = ovs_dp_upcall(dp, skb, &upcall);
+		upcall.egress_tun_info = NULL;
+		error = ovs_dp_upcall(dp, skb, key, &upcall);
 		if (unlikely(error))
 			kfree_skb(skb);
 		else
@@ -268,10 +285,10 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key)
 		goto out;
 	}
 
-	OVS_CB(skb)->flow = flow;
+	ovs_flow_stats_update(flow, key->tp.flags, skb);
+	sf_acts = rcu_dereference(flow->sf_acts);
+	ovs_execute_actions(dp, skb, sf_acts, key);
 
-	ovs_flow_stats_update(OVS_CB(skb)->flow, key->tp.flags, skb);
-	ovs_execute_actions(dp, skb, key);
 	stats_counter = &stats->n_hit;
 
 out:
@@ -283,6 +300,7 @@ out:
 }
 
 int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb,
+		  const struct sw_flow_key *key,
 		  const struct dp_upcall_info *upcall_info)
 {
 	struct dp_stats_percpu *stats;
@@ -294,9 +312,9 @@ int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb,
 	}
 
 	if (!skb_is_gso(skb))
-		err = queue_userspace_packet(dp, skb, upcall_info);
+		err = queue_userspace_packet(dp, skb, key, upcall_info);
 	else
-		err = queue_gso_packets(dp, skb, upcall_info);
+		err = queue_gso_packets(dp, skb, key, upcall_info);
 	if (err)
 		goto err;
 
@@ -313,39 +331,43 @@ err:
 }
 
 static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
+			     const struct sw_flow_key *key,
 			     const struct dp_upcall_info *upcall_info)
 {
 	unsigned short gso_type = skb_shinfo(skb)->gso_type;
-	struct dp_upcall_info later_info;
 	struct sw_flow_key later_key;
 	struct sk_buff *segs, *nskb;
+	struct ovs_skb_cb ovs_cb;
 	int err;
 
+	ovs_cb = *OVS_CB(skb);
 	segs = __skb_gso_segment(skb, NETIF_F_SG, false);
+	*OVS_CB(skb) = ovs_cb;
 	if (IS_ERR(segs))
 		return PTR_ERR(segs);
 	if (segs == NULL)
 		return -EINVAL;
 
+	if (gso_type & SKB_GSO_UDP) {
+		/* The initial flow key extracted by ovs_flow_key_extract()
+		 * in this case is for a first fragment, so we need to
+		 * properly mark later fragments.
+		 */
+		later_key = *key;
+		later_key.ip.frag = OVS_FRAG_TYPE_LATER;
+	}
+
 	/* Queue all of the segments. */
 	skb = segs;
 	do {
-		err = queue_userspace_packet(dp, skb, upcall_info);
+		*OVS_CB(skb) = ovs_cb;
+		if (gso_type & SKB_GSO_UDP && skb != segs)
+			key = &later_key;
+
+		err = queue_userspace_packet(dp, skb, key, upcall_info);
 		if (err)
 			break;
 
-		if (skb == segs && gso_type & SKB_GSO_UDP) {
-			/* The initial flow key extracted by ovs_flow_extract()
-			 * in this case is for a first fragment, so we need to
-			 * properly mark later fragments.
-			 */
-			later_key = *upcall_info->key;
-			later_key.ip.frag = OVS_FRAG_TYPE_LATER;
-
-			later_info = *upcall_info;
-			later_info.key = &later_key;
-			upcall_info = &later_info;
-		}
 	} while ((skb = skb->next));
 
 	/* Free all of the segments. */
@@ -360,46 +382,26 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 	return err;
 }
 
-static size_t key_attr_size(void)
-{
-	return    nla_total_size(4)   /* OVS_KEY_ATTR_PRIORITY */
-		+ nla_total_size(0)   /* OVS_KEY_ATTR_TUNNEL */
-		  + nla_total_size(8)   /* OVS_TUNNEL_KEY_ATTR_ID */
-		  + nla_total_size(4)   /* OVS_TUNNEL_KEY_ATTR_IPV4_SRC */
-		  + nla_total_size(4)   /* OVS_TUNNEL_KEY_ATTR_IPV4_DST */
-		  + nla_total_size(1)   /* OVS_TUNNEL_KEY_ATTR_TOS */
-		  + nla_total_size(1)   /* OVS_TUNNEL_KEY_ATTR_TTL */
-		  + nla_total_size(0)   /* OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT */
-		  + nla_total_size(0)   /* OVS_TUNNEL_KEY_ATTR_CSUM */
-		  + nla_total_size(0)   /* OVS_TUNNEL_KEY_ATTR_OAM */
-		  + nla_total_size(256)   /* OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS */
-		+ nla_total_size(4)   /* OVS_KEY_ATTR_IN_PORT */
-		+ nla_total_size(4)   /* OVS_KEY_ATTR_SKB_MARK */
-		+ nla_total_size(12)  /* OVS_KEY_ATTR_ETHERNET */
-		+ nla_total_size(2)   /* OVS_KEY_ATTR_ETHERTYPE */
-		+ nla_total_size(4)   /* OVS_KEY_ATTR_8021Q */
-		+ nla_total_size(0)   /* OVS_KEY_ATTR_ENCAP */
-		+ nla_total_size(2)   /* OVS_KEY_ATTR_ETHERTYPE */
-		+ nla_total_size(40)  /* OVS_KEY_ATTR_IPV6 */
-		+ nla_total_size(2)   /* OVS_KEY_ATTR_ICMPV6 */
-		+ nla_total_size(28); /* OVS_KEY_ATTR_ND */
-}
-
-static size_t upcall_msg_size(const struct nlattr *userdata,
+static size_t upcall_msg_size(const struct dp_upcall_info *upcall_info,
 			      unsigned int hdrlen)
 {
 	size_t size = NLMSG_ALIGN(sizeof(struct ovs_header))
 		+ nla_total_size(hdrlen) /* OVS_PACKET_ATTR_PACKET */
-		+ nla_total_size(key_attr_size()); /* OVS_PACKET_ATTR_KEY */
+		+ nla_total_size(ovs_key_attr_size()); /* OVS_PACKET_ATTR_KEY */
 
 	/* OVS_PACKET_ATTR_USERDATA */
-	if (userdata)
-		size += NLA_ALIGN(userdata->nla_len);
+	if (upcall_info->userdata)
+		size += NLA_ALIGN(upcall_info->userdata->nla_len);
+
+	/* OVS_PACKET_ATTR_EGRESS_TUN_KEY */
+	if (upcall_info->egress_tun_info)
+		size += nla_total_size(ovs_tun_key_attr_size());
 
 	return size;
 }
 
 static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
+				  const struct sw_flow_key *key,
 				  const struct dp_upcall_info *upcall_info)
 {
 	struct ovs_header *upcall;
@@ -418,16 +420,15 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 	if (!dp_ifindex)
 		return -ENODEV;
 
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		nskb = skb_clone(skb, GFP_ATOMIC);
 		if (!nskb)
 			return -ENOMEM;
 
-		nskb = __vlan_put_tag(nskb, nskb->vlan_proto, vlan_tx_tag_get(nskb));
+		nskb = __vlan_hwaccel_push_inside(nskb);
 		if (!nskb)
 			return -ENOMEM;
 
-		nskb->vlan_tci = 0;
 		skb = nskb;
 	}
 
@@ -450,7 +451,7 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 	else
 		hlen = skb->len;
 
-	len = upcall_msg_size(upcall_info->userdata, hlen);
+	len = upcall_msg_size(upcall_info, hlen);
 	user_skb = genlmsg_new_unicast(len, &info, GFP_ATOMIC);
 	if (!user_skb) {
 		err = -ENOMEM;
@@ -461,16 +462,22 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 			     0, upcall_info->cmd);
 	upcall->dp_ifindex = dp_ifindex;
 
-	nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_KEY);
-	err = ovs_nla_put_flow(upcall_info->key, upcall_info->key, user_skb);
+	err = ovs_nla_put_key(key, key, OVS_PACKET_ATTR_KEY, false, user_skb);
 	BUG_ON(err);
-	nla_nest_end(user_skb, nla);
 
 	if (upcall_info->userdata)
 		__nla_put(user_skb, OVS_PACKET_ATTR_USERDATA,
 			  nla_len(upcall_info->userdata),
 			  nla_data(upcall_info->userdata));
 
+	if (upcall_info->egress_tun_info) {
+		nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_EGRESS_TUN_KEY);
+		err = ovs_nla_put_egress_tunnel_key(user_skb,
+						    upcall_info->egress_tun_info);
+		BUG_ON(err);
+		nla_nest_end(user_skb, nla);
+	}
+
 	/* Only reserve room for attribute header, packet data is added
 	 * in skb_zerocopy() */
 	if (!(nla = nla_reserve(user_skb, OVS_PACKET_ATTR_PACKET, 0))) {
@@ -510,11 +517,13 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
 	struct sw_flow_actions *acts;
 	struct sk_buff *packet;
 	struct sw_flow *flow;
+	struct sw_flow_actions *sf_acts;
 	struct datapath *dp;
 	struct ethhdr *eth;
 	struct vport *input_vport;
 	int len;
 	int err;
+	bool log = !a[OVS_PACKET_ATTR_PROBE];
 
 	err = -EINVAL;
 	if (!a[OVS_PACKET_ATTR_PACKET] || !a[OVS_PACKET_ATTR_KEY] ||
@@ -548,29 +557,22 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
 		goto err_kfree_skb;
 
 	err = ovs_flow_key_extract_userspace(a[OVS_PACKET_ATTR_KEY], packet,
-					     &flow->key);
+					     &flow->key, log);
 	if (err)
 		goto err_flow_free;
 
-	acts = ovs_nla_alloc_flow_actions(nla_len(a[OVS_PACKET_ATTR_ACTIONS]));
-	err = PTR_ERR(acts);
-	if (IS_ERR(acts))
-		goto err_flow_free;
-
 	err = ovs_nla_copy_actions(a[OVS_PACKET_ATTR_ACTIONS],
-				   &flow->key, 0, &acts);
+				   &flow->key, &acts, log);
 	if (err)
 		goto err_flow_free;
 
 	rcu_assign_pointer(flow->sf_acts, acts);
-
 	OVS_CB(packet)->egress_tun_info = NULL;
-	OVS_CB(packet)->flow = flow;
 	packet->priority = flow->key.phy.priority;
 	packet->mark = flow->key.phy.skb_mark;
 
 	rcu_read_lock();
-	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
+	dp = get_dp_rcu(sock_net(skb->sk), ovs_header->dp_ifindex);
 	err = -ENODEV;
 	if (!dp)
 		goto err_unlock;
@@ -583,9 +585,10 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
 		goto err_unlock;
 
 	OVS_CB(packet)->input_vport = input_vport;
+	sf_acts = rcu_dereference(flow->sf_acts);
 
 	local_bh_disable();
-	err = ovs_execute_actions(dp, packet, &flow->key);
+	err = ovs_execute_actions(dp, packet, sf_acts, &flow->key);
 	local_bh_enable();
 	rcu_read_unlock();
 
@@ -606,6 +609,7 @@ static const struct nla_policy packet_policy[OVS_PACKET_ATTR_MAX + 1] = {
 	[OVS_PACKET_ATTR_PACKET] = { .len = ETH_HLEN },
 	[OVS_PACKET_ATTR_KEY] = { .type = NLA_NESTED },
 	[OVS_PACKET_ATTR_ACTIONS] = { .type = NLA_NESTED },
+	[OVS_PACKET_ATTR_PROBE] = { .type = NLA_FLAG },
 };
 
 static const struct genl_ops dp_packet_genl_ops[] = {
@@ -628,7 +632,7 @@ static struct genl_family dp_packet_genl_family = {
 	.n_ops = ARRAY_SIZE(dp_packet_genl_ops),
 };
 
-static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats,
+static void get_dp_stats(const struct datapath *dp, struct ovs_dp_stats *stats,
 			 struct ovs_dp_megaflow_stats *mega_stats)
 {
 	int i;
@@ -659,70 +663,81 @@ static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats,
 	}
 }
 
-static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts)
+static bool should_fill_key(const struct sw_flow_id *sfid, uint32_t ufid_flags)
 {
-	return NLMSG_ALIGN(sizeof(struct ovs_header))
-		+ nla_total_size(key_attr_size()) /* OVS_FLOW_ATTR_KEY */
-		+ nla_total_size(key_attr_size()) /* OVS_FLOW_ATTR_MASK */
-		+ nla_total_size(sizeof(struct ovs_flow_stats)) /* OVS_FLOW_ATTR_STATS */
-		+ nla_total_size(1) /* OVS_FLOW_ATTR_TCP_FLAGS */
-		+ nla_total_size(8) /* OVS_FLOW_ATTR_USED */
-		+ nla_total_size(acts->actions_len); /* OVS_FLOW_ATTR_ACTIONS */
+	return ovs_identifier_is_ufid(sfid) &&
+	       !(ufid_flags & OVS_UFID_F_OMIT_KEY);
 }
 
-/* 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)
+static bool should_fill_mask(uint32_t ufid_flags)
 {
-	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;
-	int err;
+	return !(ufid_flags & OVS_UFID_F_OMIT_MASK);
+}
 
-	ovs_header = genlmsg_put(skb, portid, seq, &dp_flow_genl_family, flags, cmd);
-	if (!ovs_header)
-		return -EMSGSIZE;
+static bool should_fill_actions(uint32_t ufid_flags)
+{
+	return !(ufid_flags & OVS_UFID_F_OMIT_ACTIONS);
+}
 
-	ovs_header->dp_ifindex = dp_ifindex;
+static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts,
+				    const struct sw_flow_id *sfid,
+				    uint32_t ufid_flags)
+{
+	size_t len = NLMSG_ALIGN(sizeof(struct ovs_header));
 
-	/* Fill flow key. */
-	nla = nla_nest_start(skb, OVS_FLOW_ATTR_KEY);
-	if (!nla)
-		goto nla_put_failure;
+	/* OVS_FLOW_ATTR_UFID */
+	if (sfid && ovs_identifier_is_ufid(sfid))
+		len += nla_total_size(sfid->ufid_len);
 
-	err = ovs_nla_put_flow(&flow->unmasked_key, &flow->unmasked_key, skb);
-	if (err)
-		goto error;
-	nla_nest_end(skb, nla);
+	/* OVS_FLOW_ATTR_KEY */
+	if (!sfid || should_fill_key(sfid, ufid_flags))
+		len += nla_total_size(ovs_key_attr_size());
 
-	nla = nla_nest_start(skb, OVS_FLOW_ATTR_MASK);
-	if (!nla)
-		goto nla_put_failure;
+	/* OVS_FLOW_ATTR_MASK */
+	if (should_fill_mask(ufid_flags))
+		len += nla_total_size(ovs_key_attr_size());
 
-	err = ovs_nla_put_flow(&flow->key, &flow->mask->key, skb);
-	if (err)
-		goto error;
+	/* OVS_FLOW_ATTR_ACTIONS */
+	if (should_fill_actions(ufid_flags))
+		len += nla_total_size(acts->actions_len);
+
+	return len
+		+ nla_total_size(sizeof(struct ovs_flow_stats)) /* OVS_FLOW_ATTR_STATS */
+		+ nla_total_size(1) /* OVS_FLOW_ATTR_TCP_FLAGS */
+		+ nla_total_size(8); /* OVS_FLOW_ATTR_USED */
+}
 
-	nla_nest_end(skb, nla);
+/* Called with ovs_mutex or RCU read lock. */
+static int ovs_flow_cmd_fill_stats(const struct sw_flow *flow,
+				   struct sk_buff *skb)
+{
+	struct ovs_flow_stats stats;
+	__be16 tcp_flags;
+	unsigned long used;
 
 	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;
+		return -EMSGSIZE;
 
 	if (stats.n_packets &&
 	    nla_put(skb, OVS_FLOW_ATTR_STATS, sizeof(struct ovs_flow_stats), &stats))
-		goto nla_put_failure;
+		return -EMSGSIZE;
 
 	if ((u8)ntohs(tcp_flags) &&
 	     nla_put_u8(skb, OVS_FLOW_ATTR_TCP_FLAGS, (u8)ntohs(tcp_flags)))
-		goto nla_put_failure;
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+/* Called with ovs_mutex or RCU read lock. */
+static int ovs_flow_cmd_fill_actions(const struct sw_flow *flow,
+				     struct sk_buff *skb, int skb_orig_len)
+{
+	struct nlattr *start;
+	int err;
 
 	/* If OVS_FLOW_ATTR_ACTIONS doesn't fit, skip dumping the actions if
 	 * this is the first flow to be dumped into 'skb'.  This is unusual for
@@ -746,17 +761,62 @@ static int ovs_flow_cmd_fill_info(const struct sw_flow *flow, int dp_ifindex,
 			nla_nest_end(skb, start);
 		else {
 			if (skb_orig_len)
-				goto error;
+				return err;
 
 			nla_nest_cancel(skb, start);
 		}
-	} else if (skb_orig_len)
-		goto nla_put_failure;
+	} else if (skb_orig_len) {
+		return -EMSGSIZE;
+	}
 
-	return genlmsg_end(skb, ovs_header);
+	return 0;
+}
+
+/* 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, u32 ufid_flags)
+{
+	const int skb_orig_len = skb->len;
+	struct ovs_header *ovs_header;
+	int err;
+
+	ovs_header = genlmsg_put(skb, portid, seq, &dp_flow_genl_family,
+				 flags, cmd);
+	if (!ovs_header)
+		return -EMSGSIZE;
+
+	ovs_header->dp_ifindex = dp_ifindex;
+
+	err = ovs_nla_put_identifier(flow, skb);
+	if (err)
+		goto error;
+
+	if (should_fill_key(&flow->id, ufid_flags)) {
+		err = ovs_nla_put_masked_key(flow, skb);
+		if (err)
+			goto error;
+	}
+
+	if (should_fill_mask(ufid_flags)) {
+		err = ovs_nla_put_mask(flow, skb);
+		if (err)
+			goto error;
+	}
+
+	err = ovs_flow_cmd_fill_stats(flow, skb);
+	if (err)
+		goto error;
+
+	if (should_fill_actions(ufid_flags)) {
+		err = ovs_flow_cmd_fill_actions(flow, skb, skb_orig_len);
+		if (err)
+			goto error;
+	}
+
+	genlmsg_end(skb, ovs_header);
+	return 0;
 
-nla_put_failure:
-	err = -EMSGSIZE;
 error:
 	genlmsg_cancel(skb, ovs_header);
 	return err;
@@ -764,15 +824,19 @@ error:
 
 /* May not be called with RCU read lock. */
 static struct sk_buff *ovs_flow_cmd_alloc_info(const struct sw_flow_actions *acts,
+					       const struct sw_flow_id *sfid,
 					       struct genl_info *info,
-					       bool always)
+					       bool always,
+					       uint32_t ufid_flags)
 {
 	struct sk_buff *skb;
+	size_t len;
 
 	if (!always && !ovs_must_notify(&dp_flow_genl_family, info, 0))
 		return NULL;
 
-	skb = genlmsg_new_unicast(ovs_flow_cmd_msg_size(acts), info, GFP_KERNEL);
+	len = ovs_flow_cmd_msg_size(acts, sfid, ufid_flags);
+	skb = genlmsg_new_unicast(len, info, GFP_KERNEL);
 	if (!skb)
 		return ERR_PTR(-ENOMEM);
 
@@ -783,19 +847,19 @@ static struct sk_buff *ovs_flow_cmd_alloc_info(const struct sw_flow_actions *act
 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)
+					       bool always, u32 ufid_flags)
 {
 	struct sk_buff *skb;
 	int retval;
 
-	skb = ovs_flow_cmd_alloc_info(ovsl_dereference(flow->sf_acts), info,
-				      always);
+	skb = ovs_flow_cmd_alloc_info(ovsl_dereference(flow->sf_acts),
+				      &flow->id, info, always, ufid_flags);
 	if (IS_ERR_OR_NULL(skb))
 		return skb;
 
 	retval = ovs_flow_cmd_fill_info(flow, dp_ifindex, skb,
 					info->snd_portid, info->snd_seq, 0,
-					cmd);
+					cmd, ufid_flags);
 	BUG_ON(retval < 0);
 	return skb;
 }
@@ -804,20 +868,27 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nlattr **a = info->attrs;
 	struct ovs_header *ovs_header = info->userhdr;
-	struct sw_flow *flow, *new_flow;
+	struct sw_flow *flow = NULL, *new_flow;
 	struct sw_flow_mask mask;
 	struct sk_buff *reply;
 	struct datapath *dp;
+	struct sw_flow_key key;
 	struct sw_flow_actions *acts;
 	struct sw_flow_match match;
+	u32 ufid_flags = ovs_nla_get_ufid_flags(a[OVS_FLOW_ATTR_UFID_FLAGS]);
 	int error;
+	bool log = !a[OVS_FLOW_ATTR_PROBE];
 
 	/* Must have key and actions. */
 	error = -EINVAL;
-	if (!a[OVS_FLOW_ATTR_KEY])
+	if (!a[OVS_FLOW_ATTR_KEY]) {
+		OVS_NLERR(log, "Flow key attr not present in new flow.");
 		goto error;
-	if (!a[OVS_FLOW_ATTR_ACTIONS])
+	}
+	if (!a[OVS_FLOW_ATTR_ACTIONS]) {
+		OVS_NLERR(log, "Flow actions attr not present in new flow.");
 		goto error;
+	}
 
 	/* Most of the time we need to allocate a new flow, do it before
 	 * locking.
@@ -829,28 +900,30 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	/* 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]);
+	ovs_match_init(&match, &key, &mask);
+	error = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY],
+				  a[OVS_FLOW_ATTR_MASK], log);
 	if (error)
 		goto err_kfree_flow;
 
-	ovs_flow_mask_key(&new_flow->key, &new_flow->unmasked_key, &mask);
+	ovs_flow_mask_key(&new_flow->key, &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))
+	/* Extract flow identifier. */
+	error = ovs_nla_get_identifier(&new_flow->id, a[OVS_FLOW_ATTR_UFID],
+				       &key, log);
+	if (error)
 		goto err_kfree_flow;
 
+	/* Validate actions. */
 	error = ovs_nla_copy_actions(a[OVS_FLOW_ATTR_ACTIONS], &new_flow->key,
-				     0, &acts);
+				     &acts, log);
 	if (error) {
-		OVS_NLERR("Flow actions may not be safe on all matching packets.\n");
-		goto err_kfree_acts;
+		OVS_NLERR(log, "Flow actions may not be safe on all matching packets.");
+		goto err_kfree_flow;
 	}
 
-	reply = ovs_flow_cmd_alloc_info(acts, info, false);
+	reply = ovs_flow_cmd_alloc_info(acts, &new_flow->id, info, false,
+					ufid_flags);
 	if (IS_ERR(reply)) {
 		error = PTR_ERR(reply);
 		goto err_kfree_acts;
@@ -862,8 +935,12 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 		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 (ovs_identifier_is_ufid(&new_flow->id))
+		flow = ovs_flow_tbl_lookup_ufid(&dp->table, &new_flow->id);
+	if (!flow)
+		flow = ovs_flow_tbl_lookup(&dp->table, &key);
 	if (likely(!flow)) {
 		rcu_assign_pointer(new_flow->sf_acts, acts);
 
@@ -879,7 +956,8 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 						       ovs_header->dp_ifindex,
 						       reply, info->snd_portid,
 						       info->snd_seq, 0,
-						       OVS_FLOW_CMD_NEW);
+						       OVS_FLOW_CMD_NEW,
+						       ufid_flags);
 			BUG_ON(error < 0);
 		}
 		ovs_unlock();
@@ -897,9 +975,15 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 			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);
+		/* The flow identifier has to be the same for flow updates.
+		 * Look for any overlapping flow.
+		 */
+		if (unlikely(!ovs_flow_cmp(flow, &match))) {
+			if (ovs_identifier_is_key(&flow->id))
+				flow = ovs_flow_tbl_lookup_exact(&dp->table,
+								 &match);
+			else /* UFID matches but key is different */
+				flow = NULL;
 			if (!flow) {
 				error = -ENOENT;
 				goto err_unlock_ovs;
@@ -914,7 +998,8 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 						       ovs_header->dp_ifindex,
 						       reply, info->snd_portid,
 						       info->snd_seq, 0,
-						       OVS_FLOW_CMD_NEW);
+						       OVS_FLOW_CMD_NEW,
+						       ufid_flags);
 			BUG_ON(error < 0);
 		}
 		ovs_unlock();
@@ -938,23 +1023,21 @@ error:
 	return error;
 }
 
+/* Factor out action copy to avoid "Wframe-larger-than=1024" warning. */
 static struct sw_flow_actions *get_flow_actions(const struct nlattr *a,
 						const struct sw_flow_key *key,
-						const struct sw_flow_mask *mask)
+						const struct sw_flow_mask *mask,
+						bool log)
 {
 	struct sw_flow_actions *acts;
 	struct sw_flow_key masked_key;
 	int error;
 
-	acts = ovs_nla_alloc_flow_actions(nla_len(a));
-	if (IS_ERR(acts))
-		return acts;
-
 	ovs_flow_mask_key(&masked_key, key, mask);
-	error = ovs_nla_copy_actions(a, &masked_key, 0, &acts);
+	error = ovs_nla_copy_actions(a, &masked_key, &acts, log);
 	if (error) {
-		OVS_NLERR("Flow actions may not be safe on all matching packets.\n");
-		kfree(acts);
+		OVS_NLERR(log,
+			  "Actions may not be safe on all matching packets");
 		return ERR_PTR(error);
 	}
 
@@ -972,31 +1055,38 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info)
 	struct datapath *dp;
 	struct sw_flow_actions *old_acts = NULL, *acts = NULL;
 	struct sw_flow_match match;
+	struct sw_flow_id sfid;
+	u32 ufid_flags = ovs_nla_get_ufid_flags(a[OVS_FLOW_ATTR_UFID_FLAGS]);
 	int error;
+	bool log = !a[OVS_FLOW_ATTR_PROBE];
+	bool ufid_present;
 
 	/* Extract key. */
 	error = -EINVAL;
-	if (!a[OVS_FLOW_ATTR_KEY])
+	if (!a[OVS_FLOW_ATTR_KEY]) {
+		OVS_NLERR(log, "Flow key attribute not present in set flow.");
 		goto error;
+	}
 
+	ufid_present = ovs_nla_get_ufid(&sfid, a[OVS_FLOW_ATTR_UFID], log);
 	ovs_match_init(&match, &key, &mask);
-	error = ovs_nla_get_match(&match,
-				  a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK]);
+	error = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY],
+				  a[OVS_FLOW_ATTR_MASK], log);
 	if (error)
 		goto error;
 
 	/* Validate actions. */
 	if (a[OVS_FLOW_ATTR_ACTIONS]) {
-		acts = get_flow_actions(a[OVS_FLOW_ATTR_ACTIONS], &key, &mask);
+		acts = get_flow_actions(a[OVS_FLOW_ATTR_ACTIONS], &key, &mask,
+					log);
 		if (IS_ERR(acts)) {
 			error = PTR_ERR(acts);
 			goto error;
 		}
-	}
 
-	/* Can allocate before locking if have acts. */
-	if (acts) {
-		reply = ovs_flow_cmd_alloc_info(acts, info, false);
+		/* Can allocate before locking if have acts. */
+		reply = ovs_flow_cmd_alloc_info(acts, &sfid, info, false,
+						ufid_flags);
 		if (IS_ERR(reply)) {
 			error = PTR_ERR(reply);
 			goto err_kfree_acts;
@@ -1010,7 +1100,10 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info)
 		goto err_unlock_ovs;
 	}
 	/* Check that the flow exists. */
-	flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
+	if (ufid_present)
+		flow = ovs_flow_tbl_lookup_ufid(&dp->table, &sfid);
+	else
+		flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
 	if (unlikely(!flow)) {
 		error = -ENOENT;
 		goto err_unlock_ovs;
@@ -1026,13 +1119,16 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info)
 						       ovs_header->dp_ifindex,
 						       reply, info->snd_portid,
 						       info->snd_seq, 0,
-						       OVS_FLOW_CMD_NEW);
+						       OVS_FLOW_CMD_NEW,
+						       ufid_flags);
 			BUG_ON(error < 0);
 		}
 	} else {
 		/* Could not alloc without acts before locking. */
 		reply = ovs_flow_cmd_build_info(flow, ovs_header->dp_ifindex,
-						info, OVS_FLOW_CMD_NEW, false);
+						info, OVS_FLOW_CMD_NEW, false,
+						ufid_flags);
+
 		if (unlikely(IS_ERR(reply))) {
 			error = PTR_ERR(reply);
 			goto err_unlock_ovs;
@@ -1069,15 +1165,22 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info)
 	struct sw_flow *flow;
 	struct datapath *dp;
 	struct sw_flow_match match;
-	int err;
-
-	if (!a[OVS_FLOW_ATTR_KEY]) {
-		OVS_NLERR("Flow get message rejected, Key attribute missing.\n");
-		return -EINVAL;
+	struct sw_flow_id ufid;
+	u32 ufid_flags = ovs_nla_get_ufid_flags(a[OVS_FLOW_ATTR_UFID_FLAGS]);
+	int err = 0;
+	bool log = !a[OVS_FLOW_ATTR_PROBE];
+	bool ufid_present;
+
+	ufid_present = ovs_nla_get_ufid(&ufid, a[OVS_FLOW_ATTR_UFID], log);
+	if (a[OVS_FLOW_ATTR_KEY]) {
+		ovs_match_init(&match, &key, NULL);
+		err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL,
+					log);
+	} else if (!ufid_present) {
+		OVS_NLERR(log,
+			  "Flow get message rejected, Key attribute missing.");
+		err = -EINVAL;
 	}
-
-	ovs_match_init(&match, &key, NULL);
-	err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL);
 	if (err)
 		return err;
 
@@ -1088,14 +1191,17 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info)
 		goto unlock;
 	}
 
-	flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
+	if (ufid_present)
+		flow = ovs_flow_tbl_lookup_ufid(&dp->table, &ufid);
+	else
+		flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
 	if (!flow) {
 		err = -ENOENT;
 		goto unlock;
 	}
 
 	reply = ovs_flow_cmd_build_info(flow, ovs_header->dp_ifindex, info,
-					OVS_FLOW_CMD_NEW, true);
+					OVS_FLOW_CMD_NEW, true, ufid_flags);
 	if (IS_ERR(reply)) {
 		err = PTR_ERR(reply);
 		goto unlock;
@@ -1114,14 +1220,20 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
 	struct ovs_header *ovs_header = info->userhdr;
 	struct sw_flow_key key;
 	struct sk_buff *reply;
-	struct sw_flow *flow;
+	struct sw_flow *flow = NULL;
 	struct datapath *dp;
 	struct sw_flow_match match;
+	struct sw_flow_id ufid;
+	u32 ufid_flags = ovs_nla_get_ufid_flags(a[OVS_FLOW_ATTR_UFID_FLAGS]);
 	int err;
+	bool log = !a[OVS_FLOW_ATTR_PROBE];
+	bool ufid_present;
 
-	if (likely(a[OVS_FLOW_ATTR_KEY])) {
+	ufid_present = ovs_nla_get_ufid(&ufid, a[OVS_FLOW_ATTR_UFID], log);
+	if (a[OVS_FLOW_ATTR_KEY]) {
 		ovs_match_init(&match, &key, NULL);
-		err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL);
+		err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL,
+					log);
 		if (unlikely(err))
 			return err;
 	}
@@ -1133,12 +1245,15 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
 		goto unlock;
 	}
 
-	if (unlikely(!a[OVS_FLOW_ATTR_KEY])) {
+	if (unlikely(!a[OVS_FLOW_ATTR_KEY] && !ufid_present)) {
 		err = ovs_flow_tbl_flush(&dp->table);
 		goto unlock;
 	}
 
-	flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
+	if (ufid_present)
+		flow = ovs_flow_tbl_lookup_ufid(&dp->table, &ufid);
+	else
+		flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
 	if (unlikely(!flow)) {
 		err = -ENOENT;
 		goto unlock;
@@ -1148,14 +1263,15 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
 	ovs_unlock();
 
 	reply = ovs_flow_cmd_alloc_info((const struct sw_flow_actions __force *) flow->sf_acts,
-					info, false);
+					&flow->id, info, false, ufid_flags);
 	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);
+						     OVS_FLOW_CMD_DEL,
+						     ufid_flags);
 			rcu_read_unlock();
 			BUG_ON(err < 0);
 
@@ -1174,12 +1290,21 @@ unlock:
 
 static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
 {
+	struct nlattr *a[__OVS_FLOW_ATTR_MAX];
 	struct ovs_header *ovs_header = genlmsg_data(nlmsg_data(cb->nlh));
 	struct table_instance *ti;
 	struct datapath *dp;
+	u32 ufid_flags;
+	int err;
+
+	err = genlmsg_parse(cb->nlh, &dp_flow_genl_family, a,
+			    OVS_FLOW_ATTR_MAX, flow_policy);
+	if (err)
+		return err;
+	ufid_flags = ovs_nla_get_ufid_flags(a[OVS_FLOW_ATTR_UFID_FLAGS]);
 
 	rcu_read_lock();
-	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
+	dp = get_dp_rcu(sock_net(skb->sk), ovs_header->dp_ifindex);
 	if (!dp) {
 		rcu_read_unlock();
 		return -ENODEV;
@@ -1199,7 +1324,7 @@ static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
 		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)
+					   OVS_FLOW_CMD_NEW, ufid_flags) < 0)
 			break;
 
 		cb->args[0] = bucket;
@@ -1211,8 +1336,12 @@ static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
 
 static const struct nla_policy flow_policy[OVS_FLOW_ATTR_MAX + 1] = {
 	[OVS_FLOW_ATTR_KEY] = { .type = NLA_NESTED },
+	[OVS_FLOW_ATTR_MASK] = { .type = NLA_NESTED },
 	[OVS_FLOW_ATTR_ACTIONS] = { .type = NLA_NESTED },
 	[OVS_FLOW_ATTR_CLEAR] = { .type = NLA_FLAG },
+	[OVS_FLOW_ATTR_PROBE] = { .type = NLA_FLAG },
+	[OVS_FLOW_ATTR_UFID] = { .type = NLA_UNSPEC, .len = 1 },
+	[OVS_FLOW_ATTR_UFID_FLAGS] = { .type = NLA_U32 },
 };
 
 static const struct genl_ops dp_flow_genl_ops[] = {
@@ -1265,7 +1394,7 @@ static size_t ovs_dp_cmd_msg_size(void)
 	return msgsize;
 }
 
-/* Called with ovs_mutex or RCU read lock. */
+/* Called with ovs_mutex. */
 static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb,
 				u32 portid, u32 seq, u32 flags, u8 cmd)
 {
@@ -1298,7 +1427,8 @@ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb,
 	if (nla_put_u32(skb, OVS_DP_ATTR_USER_FEATURES, dp->user_features))
 		goto nla_put_failure;
 
-	return genlmsg_end(skb, ovs_header);
+	genlmsg_end(skb, ovs_header);
+	return 0;
 
 nla_put_failure:
 	genlmsg_cancel(skb, ovs_header);
@@ -1313,7 +1443,7 @@ static struct sk_buff *ovs_dp_cmd_alloc_info(struct genl_info *info)
 
 /* Called with rcu_read_lock or ovs_mutex. */
 static struct datapath *lookup_datapath(struct net *net,
-					struct ovs_header *ovs_header,
+					const struct ovs_header *ovs_header,
 					struct nlattr *a[OVS_DP_ATTR_MAX + 1])
 {
 	struct datapath *dp;
@@ -1341,7 +1471,7 @@ static void ovs_dp_reset_user_features(struct sk_buff *skb, struct genl_info *in
 	dp->user_features = 0;
 }
 
-static void ovs_dp_change(struct datapath *dp, struct nlattr **a)
+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]);
@@ -1370,7 +1500,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	if (dp == NULL)
 		goto err_free_reply;
 
-	ovs_dp_set_net(dp, hold_net(sock_net(skb->sk)));
+	ovs_dp_set_net(dp, sock_net(skb->sk));
 
 	/* Allocate table. */
 	err = ovs_flow_tbl_init(&dp->table);
@@ -1442,9 +1572,8 @@ err_destroy_ports_array:
 err_destroy_percpu:
 	free_percpu(dp->stats_percpu);
 err_destroy_table:
-	ovs_flow_tbl_destroy(&dp->table, false);
+	ovs_flow_tbl_destroy(&dp->table);
 err_free_dp:
-	release_net(ovs_dp_get_net(dp));
 	kfree(dp);
 err_free_reply:
 	kfree_skb(reply);
@@ -1474,8 +1603,6 @@ static void __dp_destroy(struct datapath *dp)
 	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);
 }
 
@@ -1555,7 +1682,7 @@ static int ovs_dp_cmd_get(struct sk_buff *skb, struct genl_info *info)
 	if (!reply)
 		return -ENOMEM;
 
-	rcu_read_lock();
+	ovs_lock();
 	dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs);
 	if (IS_ERR(dp)) {
 		err = PTR_ERR(dp);
@@ -1564,12 +1691,12 @@ static int ovs_dp_cmd_get(struct sk_buff *skb, struct genl_info *info)
 	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);
 
 err_unlock_free:
-	rcu_read_unlock();
+	ovs_unlock();
 	kfree_skb(reply);
 	return err;
 }
@@ -1581,8 +1708,8 @@ static int ovs_dp_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	int skip = cb->args[0];
 	int i = 0;
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(dp, &ovs_net->dps, list_node) {
+	ovs_lock();
+	list_for_each_entry(dp, &ovs_net->dps, list_node) {
 		if (i >= skip &&
 		    ovs_dp_cmd_fill_info(dp, skb, NETLINK_CB(cb->skb).portid,
 					 cb->nlh->nlmsg_seq, NLM_F_MULTI,
@@ -1590,7 +1717,7 @@ static int ovs_dp_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
 			break;
 		i++;
 	}
-	rcu_read_unlock();
+	ovs_unlock();
 
 	cb->args[0] = i;
 
@@ -1674,7 +1801,8 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb,
 	if (err == -EMSGSIZE)
 		goto error;
 
-	return genlmsg_end(skb, ovs_header);
+	genlmsg_end(skb, ovs_header);
+	return 0;
 
 nla_put_failure:
 	err = -EMSGSIZE;
@@ -1707,7 +1835,7 @@ struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 portid,
 
 /* Called with ovs_mutex or RCU read lock. */
 static struct vport *lookup_vport(struct net *net,
-				  struct ovs_header *ovs_header,
+				  const struct ovs_header *ovs_header,
 				  struct nlattr *a[OVS_VPORT_ATTR_MAX + 1])
 {
 	struct datapath *dp;
@@ -1764,6 +1892,7 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info)
 		return -ENOMEM;
 
 	ovs_lock();
+restart:
 	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
 	err = -ENODEV;
 	if (!dp)
@@ -1795,8 +1924,11 @@ 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))
+	if (IS_ERR(vport)) {
+		if (err == -EAGAIN)
+			goto restart;
 		goto exit_unlock_free;
+	}
 
 	err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
 				      info->snd_seq, 0, OVS_VPORT_CMD_NEW);
@@ -1939,7 +2071,7 @@ static int ovs_vport_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	int i, j = 0;
 
 	rcu_read_lock();
-	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
+	dp = get_dp_rcu(sock_net(skb->sk), ovs_header->dp_ifindex);
 	if (!dp) {
 		rcu_read_unlock();
 		return -ENODEV;
@@ -2060,14 +2192,55 @@ static int __net_init ovs_init_net(struct net *net)
 	return 0;
 }
 
-static void __net_exit ovs_exit_net(struct net *net)
+static void __net_exit list_vports_from_net(struct net *net, struct net *dnet,
+					    struct list_head *head)
 {
-	struct datapath *dp, *dp_next;
 	struct ovs_net *ovs_net = net_generic(net, ovs_net_id);
+	struct datapath *dp;
+
+	list_for_each_entry(dp, &ovs_net->dps, list_node) {
+		int i;
+
+		for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) {
+			struct vport *vport;
+
+			hlist_for_each_entry(vport, &dp->ports[i], dp_hash_node) {
+				struct netdev_vport *netdev_vport;
+
+				if (vport->ops->type != OVS_VPORT_TYPE_INTERNAL)
+					continue;
+
+				netdev_vport = netdev_vport_priv(vport);
+				if (dev_net(netdev_vport->dev) == dnet)
+					list_add(&vport->detach_list, head);
+			}
+		}
+	}
+}
+
+static void __net_exit ovs_exit_net(struct net *dnet)
+{
+	struct datapath *dp, *dp_next;
+	struct ovs_net *ovs_net = net_generic(dnet, ovs_net_id);
+	struct vport *vport, *vport_next;
+	struct net *net;
+	LIST_HEAD(head);
 
 	ovs_lock();
 	list_for_each_entry_safe(dp, dp_next, &ovs_net->dps, list_node)
 		__dp_destroy(dp);
+
+	rtnl_lock();
+	for_each_net(net)
+		list_vports_from_net(net, dnet, &head);
+	rtnl_unlock();
+
+	/* Detach all vports from given namespace. */
+	list_for_each_entry_safe(vport, vport_next, &head, detach_list) {
+		list_del(&vport->detach_list);
+		ovs_dp_detach_port(vport);
+	}
+
 	ovs_unlock();
 
 	cancel_work_sync(&ovs_net->dp_notify_work);
@@ -2112,12 +2285,18 @@ static int __init dp_init(void)
 	if (err)
 		goto error_netns_exit;
 
+	err = ovs_netdev_init();
+	if (err)
+		goto error_unreg_notifier;
+
 	err = dp_register_genl();
 	if (err < 0)
-		goto error_unreg_notifier;
+		goto error_unreg_netdev;
 
 	return 0;
 
+error_unreg_netdev:
+	ovs_netdev_exit();
 error_unreg_notifier:
 	unregister_netdevice_notifier(&ovs_dp_device_notifier);
 error_netns_exit:
@@ -2137,6 +2316,7 @@ error:
 static void dp_cleanup(void)
 {
 	dp_unregister_genl(ARRAY_SIZE(dp_genl_families));
+	ovs_netdev_exit();
 	unregister_netdevice_notifier(&ovs_dp_device_notifier);
 	unregister_pernet_device(&ovs_net_ops);
 	rcu_barrier();
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 974135439c5c..4ec4a480b147 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -84,24 +84,20 @@ struct datapath {
 	/* Stats. */
 	struct dp_stats_percpu __percpu *stats_percpu;
 
-#ifdef CONFIG_NET_NS
 	/* Network namespace ref. */
-	struct net *net;
-#endif
+	possible_net_t net;
 
 	u32 user_features;
 };
 
 /**
  * struct ovs_skb_cb - OVS data in skb CB
- * @flow: The flow associated with this packet.  May be %NULL if no flow.
  * @egress_tun_key: Tunnel information about this packet on egress path.
  * NULL if the packet is not being tunneled.
  * @input_vport: The original vport packet came in on. This value is cached
  * when a packet is received by OVS.
  */
 struct ovs_skb_cb {
-	struct sw_flow		*flow;
 	struct ovs_tunnel_info  *egress_tun_info;
 	struct vport		*input_vport;
 };
@@ -110,18 +106,18 @@ struct ovs_skb_cb {
 /**
  * struct dp_upcall - metadata to include with a packet to send to userspace
  * @cmd: One of %OVS_PACKET_CMD_*.
- * @key: Becomes %OVS_PACKET_ATTR_KEY.  Must be nonnull.
  * @userdata: If nonnull, its variable-length value is passed to userspace as
  * %OVS_PACKET_ATTR_USERDATA.
- * @pid: Netlink PID to which packet should be sent.  If @pid is 0 then no
- * packet is sent and the packet is accounted in the datapath's @n_lost
+ * @portid: Netlink portid to which packet should be sent.  If @portid is 0
+ * then no packet is sent and the packet is accounted in the datapath's @n_lost
  * counter.
+ * @egress_tun_info: If nonnull, becomes %OVS_PACKET_ATTR_EGRESS_TUN_KEY.
  */
 struct dp_upcall_info {
-	u8 cmd;
-	const struct sw_flow_key *key;
+	const struct ovs_tunnel_info *egress_tun_info;
 	const struct nlattr *userdata;
 	u32 portid;
+	u8 cmd;
 };
 
 /**
@@ -151,7 +147,7 @@ int lockdep_ovsl_is_held(void);
 #define rcu_dereference_ovsl(p)					\
 	rcu_dereference_check(p, lockdep_ovsl_is_held())
 
-static inline struct net *ovs_dp_get_net(struct datapath *dp)
+static inline struct net *ovs_dp_get_net(const struct datapath *dp)
 {
 	return read_pnet(&dp->net);
 }
@@ -187,23 +183,23 @@ extern struct genl_family dp_vport_genl_family;
 void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key);
 void ovs_dp_detach_port(struct vport *);
 int ovs_dp_upcall(struct datapath *, struct sk_buff *,
-		  const struct dp_upcall_info *);
+		  const struct sw_flow_key *, 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,
-			struct sw_flow_key *);
+			const struct sw_flow_actions *, struct sw_flow_key *);
 
 void ovs_dp_notify_wq(struct work_struct *work);
 
 int action_fifos_init(void);
 void action_fifos_exit(void);
 
-#define OVS_NLERR(fmt, ...)					\
+#define OVS_NLERR(logging_allowed, fmt, ...)			\
 do {								\
-	if (net_ratelimit())					\
-		pr_info("netlink: " fmt, ##__VA_ARGS__);	\
+	if (logging_allowed && net_ratelimit())			\
+		pr_info("netlink: " fmt "\n", ##__VA_ARGS__);	\
 } while (0)
 #endif /* datapath.h */
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 2b78789ea7c5..2dacc7b5af23 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -32,6 +32,7 @@
 #include <linux/if_arp.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
+#include <linux/mpls.h>
 #include <linux/sctp.h>
 #include <linux/smp.h>
 #include <linux/tcp.h>
@@ -42,6 +43,7 @@
 #include <net/ip.h>
 #include <net/ip_tunnels.h>
 #include <net/ipv6.h>
+#include <net/mpls.h>
 #include <net/ndisc.h>
 
 #include "datapath.h"
@@ -64,10 +66,11 @@ u64 ovs_flow_used_time(unsigned long flow_jiffies)
 #define TCP_FLAGS_BE16(tp) (*(__be16 *)&tcp_flag_word(tp) & htons(0x0FFF))
 
 void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags,
-			   struct sk_buff *skb)
+			   const struct sk_buff *skb)
 {
 	struct flow_stats *stats;
 	int node = numa_node_id();
+	int len = skb->len + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0);
 
 	stats = rcu_dereference(flow->stats[node]);
 
@@ -97,13 +100,15 @@ void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags,
 
 				new_stats =
 					kmem_cache_alloc_node(flow_stats_cache,
-							      GFP_THISNODE |
+							      GFP_NOWAIT |
+							      __GFP_THISNODE |
+							      __GFP_NOWARN |
 							      __GFP_NOMEMALLOC,
 							      node);
 				if (likely(new_stats)) {
 					new_stats->used = jiffies;
 					new_stats->packet_count = 1;
-					new_stats->byte_count = skb->len;
+					new_stats->byte_count = len;
 					new_stats->tcp_flags = tcp_flags;
 					spin_lock_init(&new_stats->lock);
 
@@ -118,7 +123,7 @@ void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags,
 
 	stats->used = jiffies;
 	stats->packet_count++;
-	stats->byte_count += skb->len;
+	stats->byte_count += len;
 	stats->tcp_flags |= tcp_flags;
 unlock:
 	spin_unlock(&stats->lock);
@@ -469,7 +474,7 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 	 */
 
 	key->eth.tci = 0;
-	if (vlan_tx_tag_present(skb))
+	if (skb_vlan_tag_present(skb))
 		key->eth.tci = htons(skb->vlan_tci);
 	else if (eth->h_proto == htons(ETH_P_8021Q))
 		if (unlikely(parse_vlan(skb, key)))
@@ -480,6 +485,7 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 		return -ENOMEM;
 
 	skb_reset_network_header(skb);
+	skb_reset_mac_len(skb);
 	__skb_push(skb, skb->data - skb_mac_header(skb));
 
 	/* Network layer. */
@@ -584,6 +590,33 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 			memset(&key->ip, 0, sizeof(key->ip));
 			memset(&key->ipv4, 0, sizeof(key->ipv4));
 		}
+	} else if (eth_p_mpls(key->eth.type)) {
+		size_t stack_len = MPLS_HLEN;
+
+		/* In the presence of an MPLS label stack the end of the L2
+		 * header and the beginning of the L3 header differ.
+		 *
+		 * Advance network_header to the beginning of the L3
+		 * header. mac_len corresponds to the end of the L2 header.
+		 */
+		while (1) {
+			__be32 lse;
+
+			error = check_header(skb, skb->mac_len + stack_len);
+			if (unlikely(error))
+				return 0;
+
+			memcpy(&lse, skb_network_header(skb), MPLS_HLEN);
+
+			if (stack_len == MPLS_HLEN)
+				memcpy(&key->mpls.top_lse, &lse, MPLS_HLEN);
+
+			skb_set_network_header(skb, skb->mac_len + stack_len);
+			if (lse & htonl(MPLS_LS_S_MASK))
+				break;
+
+			stack_len += MPLS_HLEN;
+		}
 	} else if (key->eth.type == htons(ETH_P_IPV6)) {
 		int nh_len;             /* IPv6 Header + Extensions */
 
@@ -649,7 +682,7 @@ int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key)
 	return key_extract(skb, key);
 }
 
-int ovs_flow_key_extract(struct ovs_tunnel_info *tun_info,
+int ovs_flow_key_extract(const struct ovs_tunnel_info *tun_info,
 			 struct sk_buff *skb, struct sw_flow_key *key)
 {
 	/* Extract metadata from packet. */
@@ -660,7 +693,7 @@ int ovs_flow_key_extract(struct ovs_tunnel_info *tun_info,
 			BUILD_BUG_ON((1 << (sizeof(tun_info->options_len) *
 						   8)) - 1
 					> sizeof(key->tun_opts));
-			memcpy(GENEVE_OPTS(key, tun_info->options_len),
+			memcpy(TUN_METADATA_OPTS(key, tun_info->options_len),
 			       tun_info->options, tun_info->options_len);
 			key->tun_opts_len = tun_info->options_len;
 		} else {
@@ -682,12 +715,14 @@ int ovs_flow_key_extract(struct ovs_tunnel_info *tun_info,
 
 int ovs_flow_key_extract_userspace(const struct nlattr *attr,
 				   struct sk_buff *skb,
-				   struct sw_flow_key *key)
+				   struct sw_flow_key *key, bool log)
 {
 	int err;
 
+	memset(key, 0, OVS_SW_FLOW_KEY_METADATA_SIZE);
+
 	/* Extract metadata from netlink attributes. */
-	err = ovs_nla_get_flow_metadata(attr, key);
+	err = ovs_nla_get_flow_metadata(attr, key, log);
 	if (err)
 		return err;
 
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index 71813318c8c7..a076e445ccc2 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -37,8 +37,8 @@ struct sk_buff;
 
 /* Used to memset ovs_key_ipv4_tunnel padding. */
 #define OVS_TUNNEL_KEY_SIZE					\
-	(offsetof(struct ovs_key_ipv4_tunnel, ipv4_ttl) +	\
-	FIELD_SIZEOF(struct ovs_key_ipv4_tunnel, ipv4_ttl))
+	(offsetof(struct ovs_key_ipv4_tunnel, tp_dst) +		\
+	 FIELD_SIZEOF(struct ovs_key_ipv4_tunnel, tp_dst))
 
 struct ovs_key_ipv4_tunnel {
 	__be64 tun_id;
@@ -47,11 +47,13 @@ struct ovs_key_ipv4_tunnel {
 	__be16 tun_flags;
 	u8   ipv4_tos;
 	u8   ipv4_ttl;
+	__be16 tp_src;
+	__be16 tp_dst;
 } __packed __aligned(4); /* Minimize padding. */
 
 struct ovs_tunnel_info {
 	struct ovs_key_ipv4_tunnel tunnel;
-	struct geneve_opt *options;
+	const void *options;
 	u8 options_len;
 };
 
@@ -59,32 +61,64 @@ struct ovs_tunnel_info {
  * maximum size. This allows us to get the benefits of variable length
  * matching for small options.
  */
-#define GENEVE_OPTS(flow_key, opt_len)	\
-	((struct geneve_opt *)((flow_key)->tun_opts + \
-			       FIELD_SIZEOF(struct sw_flow_key, tun_opts) - \
-			       opt_len))
+#define TUN_METADATA_OFFSET(opt_len) \
+	(FIELD_SIZEOF(struct sw_flow_key, tun_opts) - opt_len)
+#define TUN_METADATA_OPTS(flow_key, opt_len) \
+	((void *)((flow_key)->tun_opts + TUN_METADATA_OFFSET(opt_len)))
 
-static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info,
-					  const struct iphdr *iph,
-					  __be64 tun_id, __be16 tun_flags,
-					  struct geneve_opt *opts,
-					  u8 opts_len)
+static inline void __ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info,
+					    __be32 saddr, __be32 daddr,
+					    u8 tos, u8 ttl,
+					    __be16 tp_src,
+					    __be16 tp_dst,
+					    __be64 tun_id,
+					    __be16 tun_flags,
+					    const void *opts,
+					    u8 opts_len)
 {
 	tun_info->tunnel.tun_id = tun_id;
-	tun_info->tunnel.ipv4_src = iph->saddr;
-	tun_info->tunnel.ipv4_dst = iph->daddr;
-	tun_info->tunnel.ipv4_tos = iph->tos;
-	tun_info->tunnel.ipv4_ttl = iph->ttl;
+	tun_info->tunnel.ipv4_src = saddr;
+	tun_info->tunnel.ipv4_dst = daddr;
+	tun_info->tunnel.ipv4_tos = tos;
+	tun_info->tunnel.ipv4_ttl = ttl;
 	tun_info->tunnel.tun_flags = tun_flags;
 
-	/* clear struct padding. */
-	memset((unsigned char *)&tun_info->tunnel + OVS_TUNNEL_KEY_SIZE, 0,
-	       sizeof(tun_info->tunnel) - OVS_TUNNEL_KEY_SIZE);
+	/* For the tunnel types on the top of IPsec, the tp_src and tp_dst of
+	 * the upper tunnel are used.
+	 * E.g: GRE over IPSEC, the tp_src and tp_port are zero.
+	 */
+	tun_info->tunnel.tp_src = tp_src;
+	tun_info->tunnel.tp_dst = tp_dst;
+
+	/* Clear struct padding. */
+	if (sizeof(tun_info->tunnel) != OVS_TUNNEL_KEY_SIZE)
+		memset((unsigned char *)&tun_info->tunnel + OVS_TUNNEL_KEY_SIZE,
+		       0, sizeof(tun_info->tunnel) - OVS_TUNNEL_KEY_SIZE);
 
 	tun_info->options = opts;
 	tun_info->options_len = opts_len;
 }
 
+static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info,
+					  const struct iphdr *iph,
+					  __be16 tp_src,
+					  __be16 tp_dst,
+					  __be64 tun_id,
+					  __be16 tun_flags,
+					  const void *opts,
+					  u8 opts_len)
+{
+	__ovs_flow_tun_info_init(tun_info, iph->saddr, iph->daddr,
+				 iph->tos, iph->ttl,
+				 tp_src, tp_dst,
+				 tun_id, tun_flags,
+				 opts, opts_len);
+}
+
+#define OVS_SW_FLOW_KEY_METADATA_SIZE			\
+	(offsetof(struct sw_flow_key, recirc_id) +	\
+	FIELD_SIZEOF(struct sw_flow_key, recirc_id))
+
 struct sw_flow_key {
 	u8 tun_opts[255];
 	u8 tun_opts_len;
@@ -102,12 +136,17 @@ struct sw_flow_key {
 		__be16 tci;		/* 0 if no VLAN, VLAN_TAG_PRESENT set otherwise. */
 		__be16 type;		/* Ethernet frame type. */
 	} eth;
-	struct {
-		u8     proto;		/* IP protocol or lower 8 bits of ARP opcode. */
-		u8     tos;		/* IP ToS. */
-		u8     ttl;		/* IP TTL/hop limit. */
-		u8     frag;		/* One of OVS_FRAG_TYPE_*. */
-	} ip;
+	union {
+		struct {
+			__be32 top_lse;	/* top label stack entry */
+		} mpls;
+		struct {
+			u8     proto;	/* IP protocol or lower 8 bits of ARP opcode. */
+			u8     tos;	    /* IP ToS. */
+			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. */
@@ -158,6 +197,16 @@ struct sw_flow_match {
 	struct sw_flow_mask *mask;
 };
 
+#define MAX_UFID_LENGTH 16 /* 128 bits */
+
+struct sw_flow_id {
+	u32 ufid_len;
+	union {
+		u32 ufid[MAX_UFID_LENGTH / 4];
+		struct sw_flow_key *unmasked_key;
+	};
+};
+
 struct sw_flow_actions {
 	struct rcu_head rcu;
 	u32 actions_len;
@@ -174,13 +223,15 @@ struct flow_stats {
 
 struct sw_flow {
 	struct rcu_head rcu;
-	struct hlist_node hash_node[2];
-	u32 hash;
+	struct {
+		struct hlist_node node[2];
+		u32 hash;
+	} flow_table, ufid_table;
 	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_id id;
 	struct sw_flow_mask *mask;
 	struct sw_flow_actions __rcu *sf_acts;
 	struct flow_stats __rcu *stats[]; /* One for each NUMA node.  First one
@@ -204,19 +255,30 @@ struct arp_eth_header {
 	unsigned char       ar_tip[4];		/* target IP address        */
 } __packed;
 
+static inline bool ovs_identifier_is_ufid(const struct sw_flow_id *sfid)
+{
+	return sfid->ufid_len;
+}
+
+static inline bool ovs_identifier_is_key(const struct sw_flow_id *sfid)
+{
+	return !ovs_identifier_is_ufid(sfid);
+}
+
 void ovs_flow_stats_update(struct sw_flow *, __be16 tcp_flags,
-			   struct sk_buff *);
+			   const 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_key_update(struct sk_buff *skb, struct sw_flow_key *key);
-int ovs_flow_key_extract(struct ovs_tunnel_info *tun_info, struct sk_buff *skb,
+int ovs_flow_key_extract(const struct ovs_tunnel_info *tun_info,
+			 struct sk_buff *skb,
 			 struct sw_flow_key *key);
 /* Extract key from packet coming from userspace. */
 int ovs_flow_key_extract_userspace(const struct nlattr *attr,
 				   struct sk_buff *skb,
-				   struct sw_flow_key *key);
+				   struct sw_flow_key *key, bool log);
 
 #endif /* flow.h */
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 939bcb32100f..c691b1a1eee0 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -46,24 +46,30 @@
 #include <net/ip.h>
 #include <net/ipv6.h>
 #include <net/ndisc.h>
+#include <net/mpls.h>
 
 #include "flow_netlink.h"
+#include "vport-vxlan.h"
 
-static void update_range__(struct sw_flow_match *match,
-			   size_t offset, size_t size, bool is_mask)
+struct ovs_len_tbl {
+	int len;
+	const struct ovs_len_tbl *next;
+};
+
+#define OVS_ATTR_NESTED -1
+
+static void update_range(struct sw_flow_match *match,
+			 size_t offset, size_t size, bool is_mask)
 {
-	struct sw_flow_key_range *range = NULL;
+	struct sw_flow_key_range *range;
 	size_t start = rounddown(offset, sizeof(long));
 	size_t end = roundup(offset + size, sizeof(long));
 
 	if (!is_mask)
 		range = &match->range;
-	else if (match->mask)
+	else
 		range = &match->mask->range;
 
-	if (!range)
-		return;
-
 	if (range->start == range->end) {
 		range->start = start;
 		range->end = end;
@@ -79,22 +85,20 @@ static void update_range__(struct sw_flow_match *match,
 
 #define SW_FLOW_KEY_PUT(match, field, value, is_mask) \
 	do { \
-		update_range__(match, offsetof(struct sw_flow_key, field),  \
-				     sizeof((match)->key->field), is_mask); \
-		if (is_mask) {						    \
-			if ((match)->mask)				    \
-				(match)->mask->key.field = value;	    \
-		} else {                                                    \
+		update_range(match, offsetof(struct sw_flow_key, field),    \
+			     sizeof((match)->key->field), is_mask);	    \
+		if (is_mask)						    \
+			(match)->mask->key.field = value;		    \
+		else							    \
 			(match)->key->field = value;		            \
-		}                                                           \
 	} while (0)
 
 #define SW_FLOW_KEY_MEMCPY_OFFSET(match, offset, value_p, len, is_mask)	    \
 	do {								    \
-		update_range__(match, offset, len, is_mask);		    \
+		update_range(match, offset, len, is_mask);		    \
 		if (is_mask)						    \
 			memcpy((u8 *)&(match)->mask->key + offset, value_p, \
-			       len);					    \
+			       len);					   \
 		else							    \
 			memcpy((u8 *)(match)->key + offset, value_p, len);  \
 	} while (0)
@@ -103,22 +107,20 @@ static void update_range__(struct sw_flow_match *match,
 	SW_FLOW_KEY_MEMCPY_OFFSET(match, offsetof(struct sw_flow_key, field), \
 				  value_p, len, is_mask)
 
-#define SW_FLOW_KEY_MEMSET_FIELD(match, field, value, is_mask) \
-	do { \
-		update_range__(match, offsetof(struct sw_flow_key, field),  \
-				     sizeof((match)->key->field), is_mask); \
-		if (is_mask) {						    \
-			if ((match)->mask)				    \
-				memset((u8 *)&(match)->mask->key.field, value,\
-				       sizeof((match)->mask->key.field));   \
-		} else {                                                    \
+#define SW_FLOW_KEY_MEMSET_FIELD(match, field, value, is_mask)		    \
+	do {								    \
+		update_range(match, offsetof(struct sw_flow_key, field),    \
+			     sizeof((match)->key->field), is_mask);	    \
+		if (is_mask)						    \
+			memset((u8 *)&(match)->mask->key.field, value,      \
+			       sizeof((match)->mask->key.field));	    \
+		else							    \
 			memset((u8 *)&(match)->key->field, value,           \
 			       sizeof((match)->key->field));                \
-		}                                                           \
 	} while (0)
 
 static bool match_validate(const struct sw_flow_match *match,
-			   u64 key_attrs, u64 mask_attrs)
+			   u64 key_attrs, u64 mask_attrs, bool log)
 {
 	u64 key_expected = 1 << OVS_KEY_ATTR_ETHERNET;
 	u64 mask_allowed = key_attrs;  /* At most allow all key attributes */
@@ -134,7 +136,8 @@ static bool match_validate(const struct sw_flow_match *match,
 			| (1 << OVS_KEY_ATTR_ICMP)
 			| (1 << OVS_KEY_ATTR_ICMPV6)
 			| (1 << OVS_KEY_ATTR_ARP)
-			| (1 << OVS_KEY_ATTR_ND));
+			| (1 << OVS_KEY_ATTR_ND)
+			| (1 << OVS_KEY_ATTR_MPLS));
 
 	/* Always allowed mask fields. */
 	mask_allowed |= ((1 << OVS_KEY_ATTR_TUNNEL)
@@ -149,6 +152,12 @@ static bool match_validate(const struct sw_flow_match *match,
 			mask_allowed |= 1 << OVS_KEY_ATTR_ARP;
 	}
 
+	if (eth_p_mpls(match->key->eth.type)) {
+		key_expected |= 1 << OVS_KEY_ATTR_MPLS;
+		if (match->mask && (match->mask->key.eth.type == htons(0xffff)))
+			mask_allowed |= 1 << OVS_KEY_ATTR_MPLS;
+	}
+
 	if (match->key->eth.type == htons(ETH_P_IP)) {
 		key_expected |= 1 << OVS_KEY_ATTR_IPV4;
 		if (match->mask && (match->mask->key.eth.type == htons(0xffff)))
@@ -220,7 +229,7 @@ static bool match_validate(const struct sw_flow_match *match,
 						htons(NDISC_NEIGHBOUR_SOLICITATION) ||
 				    match->key->tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)) {
 					key_expected |= 1 << OVS_KEY_ATTR_ND;
-					if (match->mask && (match->mask->key.tp.src == htons(0xffff)))
+					if (match->mask && (match->mask->key.tp.src == htons(0xff)))
 						mask_allowed |= 1 << OVS_KEY_ATTR_ND;
 				}
 			}
@@ -229,43 +238,107 @@ 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",
-				(unsigned long long)key_attrs, (unsigned long long)key_expected);
+		OVS_NLERR(log, "Missing key (keys=%llx, expected=%llx)",
+			  (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",
-				(unsigned long long)mask_attrs, (unsigned long long)mask_allowed);
+		OVS_NLERR(log, "Unexpected mask (mask=%llx, allowed=%llx)",
+			  (unsigned long long)mask_attrs,
+			  (unsigned long long)mask_allowed);
 		return false;
 	}
 
 	return true;
 }
 
+size_t ovs_tun_key_attr_size(void)
+{
+	/* Whenever adding new OVS_TUNNEL_KEY_ FIELDS, we should consider
+	 * updating this function.
+	 */
+	return    nla_total_size(8)    /* OVS_TUNNEL_KEY_ATTR_ID */
+		+ nla_total_size(4)    /* OVS_TUNNEL_KEY_ATTR_IPV4_SRC */
+		+ nla_total_size(4)    /* OVS_TUNNEL_KEY_ATTR_IPV4_DST */
+		+ nla_total_size(1)    /* OVS_TUNNEL_KEY_ATTR_TOS */
+		+ nla_total_size(1)    /* OVS_TUNNEL_KEY_ATTR_TTL */
+		+ nla_total_size(0)    /* OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT */
+		+ nla_total_size(0)    /* OVS_TUNNEL_KEY_ATTR_CSUM */
+		+ nla_total_size(0)    /* OVS_TUNNEL_KEY_ATTR_OAM */
+		+ nla_total_size(256)  /* OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS */
+		/* OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS is mutually exclusive with
+		 * OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS and covered by it.
+		 */
+		+ nla_total_size(2)    /* OVS_TUNNEL_KEY_ATTR_TP_SRC */
+		+ nla_total_size(2);   /* OVS_TUNNEL_KEY_ATTR_TP_DST */
+}
+
+size_t ovs_key_attr_size(void)
+{
+	/* Whenever adding new OVS_KEY_ FIELDS, we should consider
+	 * updating this function.
+	 */
+	BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 22);
+
+	return    nla_total_size(4)   /* OVS_KEY_ATTR_PRIORITY */
+		+ nla_total_size(0)   /* OVS_KEY_ATTR_TUNNEL */
+		  + ovs_tun_key_attr_size()
+		+ nla_total_size(4)   /* OVS_KEY_ATTR_IN_PORT */
+		+ nla_total_size(4)   /* OVS_KEY_ATTR_SKB_MARK */
+		+ nla_total_size(4)   /* OVS_KEY_ATTR_DP_HASH */
+		+ nla_total_size(4)   /* OVS_KEY_ATTR_RECIRC_ID */
+		+ nla_total_size(12)  /* OVS_KEY_ATTR_ETHERNET */
+		+ nla_total_size(2)   /* OVS_KEY_ATTR_ETHERTYPE */
+		+ nla_total_size(4)   /* OVS_KEY_ATTR_VLAN */
+		+ nla_total_size(0)   /* OVS_KEY_ATTR_ENCAP */
+		+ nla_total_size(2)   /* OVS_KEY_ATTR_ETHERTYPE */
+		+ nla_total_size(40)  /* OVS_KEY_ATTR_IPV6 */
+		+ nla_total_size(2)   /* OVS_KEY_ATTR_ICMPV6 */
+		+ nla_total_size(28); /* OVS_KEY_ATTR_ND */
+}
+
+static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] = {
+	[OVS_TUNNEL_KEY_ATTR_ID]	    = { .len = sizeof(u64) },
+	[OVS_TUNNEL_KEY_ATTR_IPV4_SRC]	    = { .len = sizeof(u32) },
+	[OVS_TUNNEL_KEY_ATTR_IPV4_DST]	    = { .len = sizeof(u32) },
+	[OVS_TUNNEL_KEY_ATTR_TOS]	    = { .len = 1 },
+	[OVS_TUNNEL_KEY_ATTR_TTL]	    = { .len = 1 },
+	[OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT] = { .len = 0 },
+	[OVS_TUNNEL_KEY_ATTR_CSUM]	    = { .len = 0 },
+	[OVS_TUNNEL_KEY_ATTR_TP_SRC]	    = { .len = sizeof(u16) },
+	[OVS_TUNNEL_KEY_ATTR_TP_DST]	    = { .len = sizeof(u16) },
+	[OVS_TUNNEL_KEY_ATTR_OAM]	    = { .len = 0 },
+	[OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS]   = { .len = OVS_ATTR_NESTED },
+	[OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS]    = { .len = OVS_ATTR_NESTED },
+};
+
 /* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute.  */
-static const int ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = {
-	[OVS_KEY_ATTR_ENCAP] = -1,
-	[OVS_KEY_ATTR_PRIORITY] = sizeof(u32),
-	[OVS_KEY_ATTR_IN_PORT] = sizeof(u32),
-	[OVS_KEY_ATTR_SKB_MARK] = sizeof(u32),
-	[OVS_KEY_ATTR_ETHERNET] = sizeof(struct ovs_key_ethernet),
-	[OVS_KEY_ATTR_VLAN] = sizeof(__be16),
-	[OVS_KEY_ATTR_ETHERTYPE] = sizeof(__be16),
-	[OVS_KEY_ATTR_IPV4] = sizeof(struct ovs_key_ipv4),
-	[OVS_KEY_ATTR_IPV6] = sizeof(struct ovs_key_ipv6),
-	[OVS_KEY_ATTR_TCP] = sizeof(struct ovs_key_tcp),
-	[OVS_KEY_ATTR_TCP_FLAGS] = sizeof(__be16),
-	[OVS_KEY_ATTR_UDP] = sizeof(struct ovs_key_udp),
-	[OVS_KEY_ATTR_SCTP] = sizeof(struct ovs_key_sctp),
-	[OVS_KEY_ATTR_ICMP] = sizeof(struct ovs_key_icmp),
-	[OVS_KEY_ATTR_ICMPV6] = sizeof(struct ovs_key_icmpv6),
-	[OVS_KEY_ATTR_ARP] = sizeof(struct ovs_key_arp),
-	[OVS_KEY_ATTR_ND] = sizeof(struct ovs_key_nd),
-	[OVS_KEY_ATTR_RECIRC_ID] = sizeof(u32),
-	[OVS_KEY_ATTR_DP_HASH] = sizeof(u32),
-	[OVS_KEY_ATTR_TUNNEL] = -1,
+static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = {
+	[OVS_KEY_ATTR_ENCAP]	 = { .len = OVS_ATTR_NESTED },
+	[OVS_KEY_ATTR_PRIORITY]	 = { .len = sizeof(u32) },
+	[OVS_KEY_ATTR_IN_PORT]	 = { .len = sizeof(u32) },
+	[OVS_KEY_ATTR_SKB_MARK]	 = { .len = sizeof(u32) },
+	[OVS_KEY_ATTR_ETHERNET]	 = { .len = sizeof(struct ovs_key_ethernet) },
+	[OVS_KEY_ATTR_VLAN]	 = { .len = sizeof(__be16) },
+	[OVS_KEY_ATTR_ETHERTYPE] = { .len = sizeof(__be16) },
+	[OVS_KEY_ATTR_IPV4]	 = { .len = sizeof(struct ovs_key_ipv4) },
+	[OVS_KEY_ATTR_IPV6]	 = { .len = sizeof(struct ovs_key_ipv6) },
+	[OVS_KEY_ATTR_TCP]	 = { .len = sizeof(struct ovs_key_tcp) },
+	[OVS_KEY_ATTR_TCP_FLAGS] = { .len = sizeof(__be16) },
+	[OVS_KEY_ATTR_UDP]	 = { .len = sizeof(struct ovs_key_udp) },
+	[OVS_KEY_ATTR_SCTP]	 = { .len = sizeof(struct ovs_key_sctp) },
+	[OVS_KEY_ATTR_ICMP]	 = { .len = sizeof(struct ovs_key_icmp) },
+	[OVS_KEY_ATTR_ICMPV6]	 = { .len = sizeof(struct ovs_key_icmpv6) },
+	[OVS_KEY_ATTR_ARP]	 = { .len = sizeof(struct ovs_key_arp) },
+	[OVS_KEY_ATTR_ND]	 = { .len = sizeof(struct ovs_key_nd) },
+	[OVS_KEY_ATTR_RECIRC_ID] = { .len = sizeof(u32) },
+	[OVS_KEY_ATTR_DP_HASH]	 = { .len = sizeof(u32) },
+	[OVS_KEY_ATTR_TUNNEL]	 = { .len = OVS_ATTR_NESTED,
+				     .next = ovs_tunnel_key_lens, },
+	[OVS_KEY_ATTR_MPLS]	 = { .len = sizeof(struct ovs_key_mpls) },
 };
 
 static bool is_all_zero(const u8 *fp, size_t size)
@@ -284,7 +357,7 @@ static bool is_all_zero(const u8 *fp, size_t size)
 
 static int __parse_flow_nlattrs(const struct nlattr *attr,
 				const struct nlattr *a[],
-				u64 *attrsp, bool nz)
+				u64 *attrsp, bool log, bool nz)
 {
 	const struct nlattr *nla;
 	u64 attrs;
@@ -296,21 +369,20 @@ static int __parse_flow_nlattrs(const struct nlattr *attr,
 		int expected_len;
 
 		if (type > OVS_KEY_ATTR_MAX) {
-			OVS_NLERR("Unknown key attribute (type=%d, max=%d).\n",
+			OVS_NLERR(log, "Key type %d is out of range max %d",
 				  type, OVS_KEY_ATTR_MAX);
 			return -EINVAL;
 		}
 
 		if (attrs & (1 << type)) {
-			OVS_NLERR("Duplicate key attribute (type %d).\n", type);
+			OVS_NLERR(log, "Duplicate key (type %d).", type);
 			return -EINVAL;
 		}
 
-		expected_len = ovs_key_lens[type];
-		if (nla_len(nla) != expected_len && expected_len != -1) {
-			OVS_NLERR("Key attribute has unexpected length (type=%d"
-				  ", length=%d, expected=%d).\n", type,
-				  nla_len(nla), expected_len);
+		expected_len = ovs_key_lens[type].len;
+		if (nla_len(nla) != expected_len && expected_len != OVS_ATTR_NESTED) {
+			OVS_NLERR(log, "Key %d has unexpected len %d expected %d",
+				  type, nla_len(nla), expected_len);
 			return -EINVAL;
 		}
 
@@ -320,7 +392,7 @@ static int __parse_flow_nlattrs(const struct nlattr *attr,
 		}
 	}
 	if (rem) {
-		OVS_NLERR("Message has %d unknown bytes.\n", rem);
+		OVS_NLERR(log, "Message has %d unknown bytes.", rem);
 		return -EINVAL;
 	}
 
@@ -329,51 +401,129 @@ static int __parse_flow_nlattrs(const struct nlattr *attr,
 }
 
 static int parse_flow_mask_nlattrs(const struct nlattr *attr,
-				   const struct nlattr *a[], u64 *attrsp)
+				   const struct nlattr *a[], u64 *attrsp,
+				   bool log)
 {
-	return __parse_flow_nlattrs(attr, a, attrsp, true);
+	return __parse_flow_nlattrs(attr, a, attrsp, log, true);
 }
 
 static int parse_flow_nlattrs(const struct nlattr *attr,
-			      const struct nlattr *a[], u64 *attrsp)
+			      const struct nlattr *a[], u64 *attrsp,
+			      bool log)
 {
-	return __parse_flow_nlattrs(attr, a, attrsp, false);
+	return __parse_flow_nlattrs(attr, a, attrsp, log, false);
+}
+
+static int genev_tun_opt_from_nlattr(const struct nlattr *a,
+				     struct sw_flow_match *match, bool is_mask,
+				     bool log)
+{
+	unsigned long opt_key_offset;
+
+	if (nla_len(a) > sizeof(match->key->tun_opts)) {
+		OVS_NLERR(log, "Geneve option length err (len %d, max %zu).",
+			  nla_len(a), sizeof(match->key->tun_opts));
+		return -EINVAL;
+	}
+
+	if (nla_len(a) % 4 != 0) {
+		OVS_NLERR(log, "Geneve opt len %d is not a multiple of 4.",
+			  nla_len(a));
+		return -EINVAL;
+	}
+
+	/* We need to record the length of the options passed
+	 * down, otherwise packets with the same format but
+	 * additional options will be silently matched.
+	 */
+	if (!is_mask) {
+		SW_FLOW_KEY_PUT(match, tun_opts_len, nla_len(a),
+				false);
+	} else {
+		/* This is somewhat unusual because it looks at
+		 * both the key and mask while parsing the
+		 * attributes (and by extension assumes the key
+		 * is parsed first). Normally, we would verify
+		 * that each is the correct length and that the
+		 * attributes line up in the validate function.
+		 * However, that is difficult because this is
+		 * variable length and we won't have the
+		 * information later.
+		 */
+		if (match->key->tun_opts_len != nla_len(a)) {
+			OVS_NLERR(log, "Geneve option len %d != mask len %d",
+				  match->key->tun_opts_len, nla_len(a));
+			return -EINVAL;
+		}
+
+		SW_FLOW_KEY_PUT(match, tun_opts_len, 0xff, true);
+	}
+
+	opt_key_offset = TUN_METADATA_OFFSET(nla_len(a));
+	SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset, nla_data(a),
+				  nla_len(a), is_mask);
+	return 0;
+}
+
+static const struct nla_policy vxlan_opt_policy[OVS_VXLAN_EXT_MAX + 1] = {
+	[OVS_VXLAN_EXT_GBP]	= { .type = NLA_U32 },
+};
+
+static int vxlan_tun_opt_from_nlattr(const struct nlattr *a,
+				     struct sw_flow_match *match, bool is_mask,
+				     bool log)
+{
+	struct nlattr *tb[OVS_VXLAN_EXT_MAX+1];
+	unsigned long opt_key_offset;
+	struct ovs_vxlan_opts opts;
+	int err;
+
+	BUILD_BUG_ON(sizeof(opts) > sizeof(match->key->tun_opts));
+
+	err = nla_parse_nested(tb, OVS_VXLAN_EXT_MAX, a, vxlan_opt_policy);
+	if (err < 0)
+		return err;
+
+	memset(&opts, 0, sizeof(opts));
+
+	if (tb[OVS_VXLAN_EXT_GBP])
+		opts.gbp = nla_get_u32(tb[OVS_VXLAN_EXT_GBP]);
+
+	if (!is_mask)
+		SW_FLOW_KEY_PUT(match, tun_opts_len, sizeof(opts), false);
+	else
+		SW_FLOW_KEY_PUT(match, tun_opts_len, 0xff, true);
+
+	opt_key_offset = TUN_METADATA_OFFSET(sizeof(opts));
+	SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset, &opts, sizeof(opts),
+				  is_mask);
+	return 0;
 }
 
 static int ipv4_tun_from_nlattr(const struct nlattr *attr,
-				struct sw_flow_match *match, bool is_mask)
+				struct sw_flow_match *match, bool is_mask,
+				bool log)
 {
 	struct nlattr *a;
 	int rem;
 	bool ttl = false;
 	__be16 tun_flags = 0;
-	unsigned long opt_key_offset;
+	int opts_type = 0;
 
 	nla_for_each_nested(a, attr, rem) {
 		int type = nla_type(a);
-		static const u32 ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] = {
-			[OVS_TUNNEL_KEY_ATTR_ID] = sizeof(u64),
-			[OVS_TUNNEL_KEY_ATTR_IPV4_SRC] = sizeof(u32),
-			[OVS_TUNNEL_KEY_ATTR_IPV4_DST] = sizeof(u32),
-			[OVS_TUNNEL_KEY_ATTR_TOS] = 1,
-			[OVS_TUNNEL_KEY_ATTR_TTL] = 1,
-			[OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT] = 0,
-			[OVS_TUNNEL_KEY_ATTR_CSUM] = 0,
-			[OVS_TUNNEL_KEY_ATTR_OAM] = 0,
-			[OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS] = -1,
-		};
+		int err;
 
 		if (type > OVS_TUNNEL_KEY_ATTR_MAX) {
-			OVS_NLERR("Unknown IPv4 tunnel attribute (type=%d, max=%d).\n",
-			type, OVS_TUNNEL_KEY_ATTR_MAX);
+			OVS_NLERR(log, "Tunnel attr %d out of range max %d",
+				  type, OVS_TUNNEL_KEY_ATTR_MAX);
 			return -EINVAL;
 		}
 
-		if (ovs_tunnel_key_lens[type] != nla_len(a) &&
-		    ovs_tunnel_key_lens[type] != -1) {
-			OVS_NLERR("IPv4 tunnel attribute type has unexpected "
-				  " length (type=%d, length=%d, expected=%d).\n",
-				  type, nla_len(a), ovs_tunnel_key_lens[type]);
+		if (ovs_tunnel_key_lens[type].len != nla_len(a) &&
+		    ovs_tunnel_key_lens[type].len != OVS_ATTR_NESTED) {
+			OVS_NLERR(log, "Tunnel attr %d has unexpected len %d expected %d",
+				  type, nla_len(a), ovs_tunnel_key_lens[type].len);
 			return -EINVAL;
 		}
 
@@ -385,11 +535,11 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
 			break;
 		case OVS_TUNNEL_KEY_ATTR_IPV4_SRC:
 			SW_FLOW_KEY_PUT(match, tun_key.ipv4_src,
-					nla_get_be32(a), is_mask);
+					nla_get_in_addr(a), is_mask);
 			break;
 		case OVS_TUNNEL_KEY_ATTR_IPV4_DST:
 			SW_FLOW_KEY_PUT(match, tun_key.ipv4_dst,
-					nla_get_be32(a), is_mask);
+					nla_get_in_addr(a), is_mask);
 			break;
 		case OVS_TUNNEL_KEY_ATTR_TOS:
 			SW_FLOW_KEY_PUT(match, tun_key.ipv4_tos,
@@ -406,62 +556,45 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
 		case OVS_TUNNEL_KEY_ATTR_CSUM:
 			tun_flags |= TUNNEL_CSUM;
 			break;
+		case OVS_TUNNEL_KEY_ATTR_TP_SRC:
+			SW_FLOW_KEY_PUT(match, tun_key.tp_src,
+					nla_get_be16(a), is_mask);
+			break;
+		case OVS_TUNNEL_KEY_ATTR_TP_DST:
+			SW_FLOW_KEY_PUT(match, tun_key.tp_dst,
+					nla_get_be16(a), is_mask);
+			break;
 		case OVS_TUNNEL_KEY_ATTR_OAM:
 			tun_flags |= TUNNEL_OAM;
 			break;
 		case OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS:
-			tun_flags |= TUNNEL_OPTIONS_PRESENT;
-			if (nla_len(a) > sizeof(match->key->tun_opts)) {
-				OVS_NLERR("Geneve option length exceeds maximum size (len %d, max %zu).\n",
-					  nla_len(a),
-					  sizeof(match->key->tun_opts));
+			if (opts_type) {
+				OVS_NLERR(log, "Multiple metadata blocks provided");
 				return -EINVAL;
 			}
 
-			if (nla_len(a) % 4 != 0) {
-				OVS_NLERR("Geneve option length is not a multiple of 4 (len %d).\n",
-					  nla_len(a));
+			err = genev_tun_opt_from_nlattr(a, match, is_mask, log);
+			if (err)
+				return err;
+
+			tun_flags |= TUNNEL_GENEVE_OPT;
+			opts_type = type;
+			break;
+		case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS:
+			if (opts_type) {
+				OVS_NLERR(log, "Multiple metadata blocks provided");
 				return -EINVAL;
 			}
 
-			/* We need to record the length of the options passed
-			 * down, otherwise packets with the same format but
-			 * additional options will be silently matched.
-			 */
-			if (!is_mask) {
-				SW_FLOW_KEY_PUT(match, tun_opts_len, nla_len(a),
-						false);
-			} else {
-				/* This is somewhat unusual because it looks at
-				 * both the key and mask while parsing the
-				 * attributes (and by extension assumes the key
-				 * is parsed first). Normally, we would verify
-				 * that each is the correct length and that the
-				 * attributes line up in the validate function.
-				 * However, that is difficult because this is
-				 * variable length and we won't have the
-				 * information later.
-				 */
-				if (match->key->tun_opts_len != nla_len(a)) {
-					OVS_NLERR("Geneve option key length (%d) is different from mask length (%d).",
-						  match->key->tun_opts_len,
-						  nla_len(a));
-					return -EINVAL;
-				}
-
-				SW_FLOW_KEY_PUT(match, tun_opts_len, 0xff,
-						true);
-			}
+			err = vxlan_tun_opt_from_nlattr(a, match, is_mask, log);
+			if (err)
+				return err;
 
-			opt_key_offset = (unsigned long)GENEVE_OPTS(
-					  (struct sw_flow_key *)0,
-					  nla_len(a));
-			SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset,
-						  nla_data(a), nla_len(a),
-						  is_mask);
+			tun_flags |= TUNNEL_VXLAN_OPT;
+			opts_type = type;
 			break;
 		default:
-			OVS_NLERR("Unknown IPv4 tunnel attribute (%d).\n",
+			OVS_NLERR(log, "Unknown IPv4 tunnel attribute %d",
 				  type);
 			return -EINVAL;
 		}
@@ -470,38 +603,57 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
 	SW_FLOW_KEY_PUT(match, tun_key.tun_flags, tun_flags, is_mask);
 
 	if (rem > 0) {
-		OVS_NLERR("IPv4 tunnel attribute has %d unknown bytes.\n", rem);
+		OVS_NLERR(log, "IPv4 tunnel attribute has %d unknown bytes.",
+			  rem);
 		return -EINVAL;
 	}
 
 	if (!is_mask) {
 		if (!match->key->tun_key.ipv4_dst) {
-			OVS_NLERR("IPv4 tunnel destination address is zero.\n");
+			OVS_NLERR(log, "IPv4 tunnel dst address is zero");
 			return -EINVAL;
 		}
 
 		if (!ttl) {
-			OVS_NLERR("IPv4 tunnel TTL not specified.\n");
+			OVS_NLERR(log, "IPv4 tunnel TTL not specified.");
 			return -EINVAL;
 		}
 	}
 
+	return opts_type;
+}
+
+static int vxlan_opt_to_nlattr(struct sk_buff *skb,
+			       const void *tun_opts, int swkey_tun_opts_len)
+{
+	const struct ovs_vxlan_opts *opts = tun_opts;
+	struct nlattr *nla;
+
+	nla = nla_nest_start(skb, OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS);
+	if (!nla)
+		return -EMSGSIZE;
+
+	if (nla_put_u32(skb, OVS_VXLAN_EXT_GBP, opts->gbp) < 0)
+		return -EMSGSIZE;
+
+	nla_nest_end(skb, nla);
 	return 0;
 }
 
 static int __ipv4_tun_to_nlattr(struct sk_buff *skb,
 				const struct ovs_key_ipv4_tunnel *output,
-				const struct geneve_opt *tun_opts,
-				int swkey_tun_opts_len)
+				const void *tun_opts, int swkey_tun_opts_len)
 {
 	if (output->tun_flags & TUNNEL_KEY &&
 	    nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id))
 		return -EMSGSIZE;
 	if (output->ipv4_src &&
-	    nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC, output->ipv4_src))
+	    nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC,
+			    output->ipv4_src))
 		return -EMSGSIZE;
 	if (output->ipv4_dst &&
-	    nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST, output->ipv4_dst))
+	    nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST,
+			    output->ipv4_dst))
 		return -EMSGSIZE;
 	if (output->ipv4_tos &&
 	    nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TOS, output->ipv4_tos))
@@ -514,22 +666,31 @@ static int __ipv4_tun_to_nlattr(struct sk_buff *skb,
 	if ((output->tun_flags & TUNNEL_CSUM) &&
 	    nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_CSUM))
 		return -EMSGSIZE;
+	if (output->tp_src &&
+	    nla_put_be16(skb, OVS_TUNNEL_KEY_ATTR_TP_SRC, output->tp_src))
+		return -EMSGSIZE;
+	if (output->tp_dst &&
+	    nla_put_be16(skb, OVS_TUNNEL_KEY_ATTR_TP_DST, output->tp_dst))
+		return -EMSGSIZE;
 	if ((output->tun_flags & TUNNEL_OAM) &&
 	    nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_OAM))
 		return -EMSGSIZE;
-	if (tun_opts &&
-	    nla_put(skb, OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS,
-		    swkey_tun_opts_len, tun_opts))
-		return -EMSGSIZE;
+	if (tun_opts) {
+		if (output->tun_flags & TUNNEL_GENEVE_OPT &&
+		    nla_put(skb, OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS,
+			    swkey_tun_opts_len, tun_opts))
+			return -EMSGSIZE;
+		else if (output->tun_flags & TUNNEL_VXLAN_OPT &&
+			 vxlan_opt_to_nlattr(skb, tun_opts, swkey_tun_opts_len))
+			return -EMSGSIZE;
+	}
 
 	return 0;
 }
 
-
 static int ipv4_tun_to_nlattr(struct sk_buff *skb,
 			      const struct ovs_key_ipv4_tunnel *output,
-			      const struct geneve_opt *tun_opts,
-			      int swkey_tun_opts_len)
+			      const void *tun_opts, int swkey_tun_opts_len)
 {
 	struct nlattr *nla;
 	int err;
@@ -546,8 +707,17 @@ static int ipv4_tun_to_nlattr(struct sk_buff *skb,
 	return 0;
 }
 
+int ovs_nla_put_egress_tunnel_key(struct sk_buff *skb,
+				  const struct ovs_tunnel_info *egress_tun_info)
+{
+	return __ipv4_tun_to_nlattr(skb, &egress_tun_info->tunnel,
+				    egress_tun_info->options,
+				    egress_tun_info->options_len);
+}
+
 static int metadata_from_nlattrs(struct sw_flow_match *match,  u64 *attrs,
-				 const struct nlattr **a, bool is_mask)
+				 const struct nlattr **a, bool is_mask,
+				 bool log)
 {
 	if (*attrs & (1 << OVS_KEY_ATTR_DP_HASH)) {
 		u32 hash_val = nla_get_u32(a[OVS_KEY_ATTR_DP_HASH]);
@@ -572,10 +742,13 @@ static int metadata_from_nlattrs(struct sw_flow_match *match,  u64 *attrs,
 	if (*attrs & (1 << OVS_KEY_ATTR_IN_PORT)) {
 		u32 in_port = nla_get_u32(a[OVS_KEY_ATTR_IN_PORT]);
 
-		if (is_mask)
+		if (is_mask) {
 			in_port = 0xffffffff; /* Always exact match in_port. */
-		else if (in_port >= DP_MAX_PORTS)
+		} else if (in_port >= DP_MAX_PORTS) {
+			OVS_NLERR(log, "Port %d exceeds max allowable %d",
+				  in_port, DP_MAX_PORTS);
 			return -EINVAL;
+		}
 
 		SW_FLOW_KEY_PUT(match, phy.in_port, in_port, is_mask);
 		*attrs &= ~(1 << OVS_KEY_ATTR_IN_PORT);
@@ -591,7 +764,7 @@ static int metadata_from_nlattrs(struct sw_flow_match *match,  u64 *attrs,
 	}
 	if (*attrs & (1 << OVS_KEY_ATTR_TUNNEL)) {
 		if (ipv4_tun_from_nlattr(a[OVS_KEY_ATTR_TUNNEL], match,
-					 is_mask))
+					 is_mask, log) < 0)
 			return -EINVAL;
 		*attrs &= ~(1 << OVS_KEY_ATTR_TUNNEL);
 	}
@@ -599,12 +772,12 @@ static int metadata_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)
+				const struct nlattr **a, bool is_mask,
+				bool log)
 {
 	int err;
-	u64 orig_attrs = attrs;
 
-	err = metadata_from_nlattrs(match, &attrs, a, is_mask);
+	err = metadata_from_nlattrs(match, &attrs, a, is_mask, log);
 	if (err)
 		return err;
 
@@ -625,17 +798,16 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
 		tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]);
 		if (!(tci & htons(VLAN_TAG_PRESENT))) {
 			if (is_mask)
-				OVS_NLERR("VLAN TCI mask does not have exact match for VLAN_TAG_PRESENT bit.\n");
+				OVS_NLERR(log, "VLAN TCI mask does not have exact match for VLAN_TAG_PRESENT bit.");
 			else
-				OVS_NLERR("VLAN TCI does not have VLAN_TAG_PRESENT bit set.\n");
+				OVS_NLERR(log, "VLAN TCI does not have VLAN_TAG_PRESENT bit set.");
 
 			return -EINVAL;
 		}
 
 		SW_FLOW_KEY_PUT(match, eth.tci, tci, is_mask);
 		attrs &= ~(1 << OVS_KEY_ATTR_VLAN);
-	} else if (!is_mask)
-		SW_FLOW_KEY_PUT(match, eth.tci, htons(0xffff), true);
+	}
 
 	if (attrs & (1 << OVS_KEY_ATTR_ETHERTYPE)) {
 		__be16 eth_type;
@@ -645,8 +817,8 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
 			/* Always exact match EtherType. */
 			eth_type = htons(0xffff);
 		} else if (ntohs(eth_type) < ETH_P_802_3_MIN) {
-			OVS_NLERR("EtherType is less than minimum (type=%x, min=%x).\n",
-					ntohs(eth_type), ETH_P_802_3_MIN);
+			OVS_NLERR(log, "EtherType %x is less than min %x",
+				  ntohs(eth_type), ETH_P_802_3_MIN);
 			return -EINVAL;
 		}
 
@@ -661,8 +833,8 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
 
 		ipv4_key = nla_data(a[OVS_KEY_ATTR_IPV4]);
 		if (!is_mask && ipv4_key->ipv4_frag > OVS_FRAG_TYPE_MAX) {
-			OVS_NLERR("Unknown IPv4 fragment type (value=%d, max=%d).\n",
-				ipv4_key->ipv4_frag, OVS_FRAG_TYPE_MAX);
+			OVS_NLERR(log, "IPv4 frag type %d is out of range max %d",
+				  ipv4_key->ipv4_frag, OVS_FRAG_TYPE_MAX);
 			return -EINVAL;
 		}
 		SW_FLOW_KEY_PUT(match, ip.proto,
@@ -685,10 +857,17 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
 
 		ipv6_key = nla_data(a[OVS_KEY_ATTR_IPV6]);
 		if (!is_mask && ipv6_key->ipv6_frag > OVS_FRAG_TYPE_MAX) {
-			OVS_NLERR("Unknown IPv6 fragment type (value=%d, max=%d).\n",
-				ipv6_key->ipv6_frag, OVS_FRAG_TYPE_MAX);
+			OVS_NLERR(log, "IPv6 frag type %d is out of range max %d",
+				  ipv6_key->ipv6_frag, OVS_FRAG_TYPE_MAX);
+			return -EINVAL;
+		}
+
+		if (!is_mask && ipv6_key->ipv6_label & htonl(0xFFF00000)) {
+			OVS_NLERR(log, "IPv6 flow label %x is out of range (max=%x).\n",
+				  ntohl(ipv6_key->ipv6_label), (1 << 20) - 1);
 			return -EINVAL;
 		}
+
 		SW_FLOW_KEY_PUT(match, ipv6.label,
 				ipv6_key->ipv6_label, is_mask);
 		SW_FLOW_KEY_PUT(match, ip.proto,
@@ -716,7 +895,7 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
 
 		arp_key = nla_data(a[OVS_KEY_ATTR_ARP]);
 		if (!is_mask && (arp_key->arp_op & htons(0xff00))) {
-			OVS_NLERR("Unknown ARP opcode (opcode=%d).\n",
+			OVS_NLERR(log, "Unknown ARP opcode (opcode=%d).",
 				  arp_key->arp_op);
 			return -EINVAL;
 		}
@@ -735,6 +914,16 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
 		attrs &= ~(1 << OVS_KEY_ATTR_ARP);
 	}
 
+	if (attrs & (1 << OVS_KEY_ATTR_MPLS)) {
+		const struct ovs_key_mpls *mpls_key;
+
+		mpls_key = nla_data(a[OVS_KEY_ATTR_MPLS]);
+		SW_FLOW_KEY_PUT(match, mpls.top_lse,
+				mpls_key->mpls_lse, is_mask);
+
+		attrs &= ~(1 << OVS_KEY_ATTR_MPLS);
+	 }
+
 	if (attrs & (1 << OVS_KEY_ATTR_TCP)) {
 		const struct ovs_key_tcp *tcp_key;
 
@@ -745,15 +934,9 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
 	}
 
 	if (attrs & (1 << OVS_KEY_ATTR_TCP_FLAGS)) {
-		if (orig_attrs & (1 << OVS_KEY_ATTR_IPV4)) {
-			SW_FLOW_KEY_PUT(match, tp.flags,
-					nla_get_be16(a[OVS_KEY_ATTR_TCP_FLAGS]),
-					is_mask);
-		} else {
-			SW_FLOW_KEY_PUT(match, tp.flags,
-					nla_get_be16(a[OVS_KEY_ATTR_TCP_FLAGS]),
-					is_mask);
-		}
+		SW_FLOW_KEY_PUT(match, tp.flags,
+				nla_get_be16(a[OVS_KEY_ATTR_TCP_FLAGS]),
+				is_mask);
 		attrs &= ~(1 << OVS_KEY_ATTR_TCP_FLAGS);
 	}
 
@@ -812,24 +995,25 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
 		attrs &= ~(1 << OVS_KEY_ATTR_ND);
 	}
 
-	if (attrs != 0)
+	if (attrs != 0) {
+		OVS_NLERR(log, "Unknown key attributes %llx",
+			  (unsigned long long)attrs);
 		return -EINVAL;
+	}
 
 	return 0;
 }
 
-static void nlattr_set(struct nlattr *attr, u8 val, bool is_attr_mask_key)
+static void nlattr_set(struct nlattr *attr, u8 val,
+		       const struct ovs_len_tbl *tbl)
 {
 	struct nlattr *nla;
 	int rem;
 
 	/* The nlattr stream should already have been validated */
 	nla_for_each_nested(nla, attr, rem) {
-		/* We assume that ovs_key_lens[type] == -1 means that type is a
-		 * nested attribute
-		 */
-		if (is_attr_mask_key && ovs_key_lens[nla_type(nla)] == -1)
-			nlattr_set(nla, val, false);
+		if (tbl && tbl[nla_type(nla)].len == OVS_ATTR_NESTED)
+			nlattr_set(nla, val, tbl[nla_type(nla)].next);
 		else
 			memset(nla_data(nla), val, nla_len(nla));
 	}
@@ -837,7 +1021,7 @@ static void nlattr_set(struct nlattr *attr, u8 val, bool is_attr_mask_key)
 
 static void mask_set_nlattr(struct nlattr *attr, u8 val)
 {
-	nlattr_set(attr, val, true);
+	nlattr_set(attr, val, ovs_key_lens);
 }
 
 /**
@@ -851,10 +1035,14 @@ static void mask_set_nlattr(struct nlattr *attr, u8 val)
  * of this flow.
  * @mask: Optional. Netlink attribute holding nested %OVS_KEY_ATTR_* Netlink
  * attribute specifies the mask field of the wildcarded flow.
+ * @log: Boolean to allow kernel error logging.  Normally true, but when
+ * probing for feature compatibility this should be passed in as false to
+ * suppress unnecessary error logging.
  */
 int ovs_nla_get_match(struct sw_flow_match *match,
-		      const struct nlattr *key,
-		      const struct nlattr *mask)
+		      const struct nlattr *nla_key,
+		      const struct nlattr *nla_mask,
+		      bool log)
 {
 	const struct nlattr *a[OVS_KEY_ATTR_MAX + 1];
 	const struct nlattr *encap;
@@ -864,7 +1052,7 @@ int ovs_nla_get_match(struct sw_flow_match *match,
 	bool encap_valid = false;
 	int err;
 
-	err = parse_flow_nlattrs(key, a, &key_attrs);
+	err = parse_flow_nlattrs(nla_key, a, &key_attrs, log);
 	if (err)
 		return err;
 
@@ -875,7 +1063,7 @@ int ovs_nla_get_match(struct sw_flow_match *match,
 
 		if (!((key_attrs & (1 << OVS_KEY_ATTR_VLAN)) &&
 		      (key_attrs & (1 << OVS_KEY_ATTR_ENCAP)))) {
-			OVS_NLERR("Invalid Vlan frame.\n");
+			OVS_NLERR(log, "Invalid Vlan frame.");
 			return -EINVAL;
 		}
 
@@ -886,61 +1074,68 @@ int ovs_nla_get_match(struct sw_flow_match *match,
 		encap_valid = true;
 
 		if (tci & htons(VLAN_TAG_PRESENT)) {
-			err = parse_flow_nlattrs(encap, a, &key_attrs);
+			err = parse_flow_nlattrs(encap, a, &key_attrs, log);
 			if (err)
 				return err;
 		} else if (!tci) {
 			/* Corner case for truncated 802.1Q header. */
 			if (nla_len(encap)) {
-				OVS_NLERR("Truncated 802.1Q header has non-zero encap attribute.\n");
+				OVS_NLERR(log, "Truncated 802.1Q header has non-zero encap attribute.");
 				return -EINVAL;
 			}
 		} else {
-			OVS_NLERR("Encap attribute is set for a non-VLAN frame.\n");
+			OVS_NLERR(log, "Encap attr is set for non-VLAN frame");
 			return  -EINVAL;
 		}
 	}
 
-	err = ovs_key_from_nlattrs(match, key_attrs, a, false);
+	err = ovs_key_from_nlattrs(match, key_attrs, a, false, log);
 	if (err)
 		return err;
 
-	if (match->mask && !mask) {
-		/* Create an exact match mask. We need to set to 0xff all the
-		 * 'match->mask' fields that have been touched in 'match->key'.
-		 * We cannot simply memset 'match->mask', because padding bytes
-		 * and fields not specified in 'match->key' should be left to 0.
-		 * Instead, we use a stream of netlink attributes, copied from
-		 * 'key' and set to 0xff: ovs_key_from_nlattrs() will take care
-		 * of filling 'match->mask' appropriately.
-		 */
-		newmask = kmemdup(key, nla_total_size(nla_len(key)),
-				  GFP_KERNEL);
-		if (!newmask)
-			return -ENOMEM;
+	if (match->mask) {
+		if (!nla_mask) {
+			/* Create an exact match mask. We need to set to 0xff
+			 * all the 'match->mask' fields that have been touched
+			 * in 'match->key'. We cannot simply memset
+			 * 'match->mask', because padding bytes and fields not
+			 * specified in 'match->key' should be left to 0.
+			 * Instead, we use a stream of netlink attributes,
+			 * copied from 'key' and set to 0xff.
+			 * ovs_key_from_nlattrs() will take care of filling
+			 * 'match->mask' appropriately.
+			 */
+			newmask = kmemdup(nla_key,
+					  nla_total_size(nla_len(nla_key)),
+					  GFP_KERNEL);
+			if (!newmask)
+				return -ENOMEM;
 
-		mask_set_nlattr(newmask, 0xff);
+			mask_set_nlattr(newmask, 0xff);
 
-		/* The userspace does not send tunnel attributes that are 0,
-		 * but we should not wildcard them nonetheless.
-		 */
-		if (match->key->tun_key.ipv4_dst)
-			SW_FLOW_KEY_MEMSET_FIELD(match, tun_key, 0xff, true);
+			/* The userspace does not send tunnel attributes that
+			 * are 0, but we should not wildcard them nonetheless.
+			 */
+			if (match->key->tun_key.ipv4_dst)
+				SW_FLOW_KEY_MEMSET_FIELD(match, tun_key,
+							 0xff, true);
 
-		mask = newmask;
-	}
+			nla_mask = newmask;
+		}
 
-	if (mask) {
-		err = parse_flow_mask_nlattrs(mask, a, &mask_attrs);
+		err = parse_flow_mask_nlattrs(nla_mask, a, &mask_attrs, log);
 		if (err)
 			goto free_newmask;
 
+		/* Always match on tci. */
+		SW_FLOW_KEY_PUT(match, eth.tci, htons(0xffff), true);
+
 		if (mask_attrs & 1 << OVS_KEY_ATTR_ENCAP) {
 			__be16 eth_type = 0;
 			__be16 tci = 0;
 
 			if (!encap_valid) {
-				OVS_NLERR("Encap mask attribute is set for non-VLAN frame.\n");
+				OVS_NLERR(log, "Encap mask attribute is set for non-VLAN frame.");
 				err = -EINVAL;
 				goto free_newmask;
 			}
@@ -952,12 +1147,13 @@ int ovs_nla_get_match(struct sw_flow_match *match,
 			if (eth_type == htons(0xffff)) {
 				mask_attrs &= ~(1 << OVS_KEY_ATTR_ETHERTYPE);
 				encap = a[OVS_KEY_ATTR_ENCAP];
-				err = parse_flow_mask_nlattrs(encap, a, &mask_attrs);
+				err = parse_flow_mask_nlattrs(encap, a,
+							      &mask_attrs, log);
 				if (err)
 					goto free_newmask;
 			} else {
-				OVS_NLERR("VLAN frames must have an exact match on the TPID (mask=%x).\n",
-						ntohs(eth_type));
+				OVS_NLERR(log, "VLAN frames must have an exact match on the TPID (mask=%x).",
+					  ntohs(eth_type));
 				err = -EINVAL;
 				goto free_newmask;
 			}
@@ -966,18 +1162,19 @@ int ovs_nla_get_match(struct sw_flow_match *match,
 				tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]);
 
 			if (!(tci & htons(VLAN_TAG_PRESENT))) {
-				OVS_NLERR("VLAN tag present bit must have an exact match (tci_mask=%x).\n", ntohs(tci));
+				OVS_NLERR(log, "VLAN tag present bit must have an exact match (tci_mask=%x).",
+					  ntohs(tci));
 				err = -EINVAL;
 				goto free_newmask;
 			}
 		}
 
-		err = ovs_key_from_nlattrs(match, mask_attrs, a, true);
+		err = ovs_key_from_nlattrs(match, mask_attrs, a, true, log);
 		if (err)
 			goto free_newmask;
 	}
 
-	if (!match_validate(match, key_attrs, mask_attrs))
+	if (!match_validate(match, key_attrs, mask_attrs, log))
 		err = -EINVAL;
 
 free_newmask:
@@ -985,11 +1182,67 @@ free_newmask:
 	return err;
 }
 
+static size_t get_ufid_len(const struct nlattr *attr, bool log)
+{
+	size_t len;
+
+	if (!attr)
+		return 0;
+
+	len = nla_len(attr);
+	if (len < 1 || len > MAX_UFID_LENGTH) {
+		OVS_NLERR(log, "ufid size %u bytes exceeds the range (1, %d)",
+			  nla_len(attr), MAX_UFID_LENGTH);
+		return 0;
+	}
+
+	return len;
+}
+
+/* Initializes 'flow->ufid', returning true if 'attr' contains a valid UFID,
+ * or false otherwise.
+ */
+bool ovs_nla_get_ufid(struct sw_flow_id *sfid, const struct nlattr *attr,
+		      bool log)
+{
+	sfid->ufid_len = get_ufid_len(attr, log);
+	if (sfid->ufid_len)
+		memcpy(sfid->ufid, nla_data(attr), sfid->ufid_len);
+
+	return sfid->ufid_len;
+}
+
+int ovs_nla_get_identifier(struct sw_flow_id *sfid, const struct nlattr *ufid,
+			   const struct sw_flow_key *key, bool log)
+{
+	struct sw_flow_key *new_key;
+
+	if (ovs_nla_get_ufid(sfid, ufid, log))
+		return 0;
+
+	/* If UFID was not provided, use unmasked key. */
+	new_key = kmalloc(sizeof(*new_key), GFP_KERNEL);
+	if (!new_key)
+		return -ENOMEM;
+	memcpy(new_key, key, sizeof(*key));
+	sfid->unmasked_key = new_key;
+
+	return 0;
+}
+
+u32 ovs_nla_get_ufid_flags(const struct nlattr *attr)
+{
+	return attr ? nla_get_u32(attr) : 0;
+}
+
 /**
  * ovs_nla_get_flow_metadata - parses Netlink attributes into a flow key.
  * @key: Receives extracted in_port, priority, tun_key and skb_mark.
  * @attr: Netlink attribute holding nested %OVS_KEY_ATTR_* Netlink attribute
  * sequence.
+ * @log: Boolean to allow kernel error logging.  Normally true, but when
+ * probing for feature compatibility this should be passed in as false to
+ * suppress unnecessary error logging.
  *
  * This parses a series of Netlink attributes that form a flow key, which must
  * take the same form accepted by flow_from_nlattrs(), but only enough of it to
@@ -998,14 +1251,15 @@ free_newmask:
  */
 
 int ovs_nla_get_flow_metadata(const struct nlattr *attr,
-			      struct sw_flow_key *key)
+			      struct sw_flow_key *key,
+			      bool log)
 {
 	const struct nlattr *a[OVS_KEY_ATTR_MAX + 1];
 	struct sw_flow_match match;
 	u64 attrs = 0;
 	int err;
 
-	err = parse_flow_nlattrs(attr, a, &attrs);
+	err = parse_flow_nlattrs(attr, a, &attrs, log);
 	if (err)
 		return -EINVAL;
 
@@ -1014,15 +1268,15 @@ int ovs_nla_get_flow_metadata(const struct nlattr *attr,
 
 	key->phy.in_port = DP_MAX_PORTS;
 
-	return metadata_from_nlattrs(&match, &attrs, a, false);
+	return metadata_from_nlattrs(&match, &attrs, a, false, log);
 }
 
-int ovs_nla_put_flow(const struct sw_flow_key *swkey,
-		     const struct sw_flow_key *output, struct sk_buff *skb)
+static int __ovs_nla_put_key(const struct sw_flow_key *swkey,
+			     const struct sw_flow_key *output, bool is_mask,
+			     struct sk_buff *skb)
 {
 	struct ovs_key_ethernet *eth_key;
 	struct nlattr *nla, *encap;
-	bool is_mask = (swkey != output);
 
 	if (nla_put_u32(skb, OVS_KEY_ATTR_RECIRC_ID, output->recirc_id))
 		goto nla_put_failure;
@@ -1034,10 +1288,10 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
 		goto nla_put_failure;
 
 	if ((swkey->tun_key.ipv4_dst || is_mask)) {
-		const struct geneve_opt *opts = NULL;
+		const void *opts = NULL;
 
 		if (output->tun_key.tun_flags & TUNNEL_OPTIONS_PRESENT)
-			opts = GENEVE_OPTS(output, swkey->tun_opts_len);
+			opts = TUN_METADATA_OPTS(output, swkey->tun_opts_len);
 
 		if (ipv4_tun_to_nlattr(skb, &output->tun_key, opts,
 				       swkey->tun_opts_len))
@@ -1140,6 +1394,14 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
 		arp_key->arp_op = htons(output->ip.proto);
 		ether_addr_copy(arp_key->arp_sha, output->ipv4.arp.sha);
 		ether_addr_copy(arp_key->arp_tha, output->ipv4.arp.tha);
+	} else if (eth_p_mpls(swkey->eth.type)) {
+		struct ovs_key_mpls *mpls_key;
+
+		nla = nla_reserve(skb, OVS_KEY_ATTR_MPLS, sizeof(*mpls_key));
+		if (!nla)
+			goto nla_put_failure;
+		mpls_key = nla_data(nla);
+		mpls_key->mpls_lse = output->mpls.top_lse;
 	}
 
 	if ((swkey->eth.type == htons(ETH_P_IP) ||
@@ -1224,14 +1486,59 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
+int ovs_nla_put_key(const struct sw_flow_key *swkey,
+		    const struct sw_flow_key *output, int attr, bool is_mask,
+		    struct sk_buff *skb)
+{
+	int err;
+	struct nlattr *nla;
+
+	nla = nla_nest_start(skb, attr);
+	if (!nla)
+		return -EMSGSIZE;
+	err = __ovs_nla_put_key(swkey, output, is_mask, skb);
+	if (err)
+		return err;
+	nla_nest_end(skb, nla);
+
+	return 0;
+}
+
+/* Called with ovs_mutex or RCU read lock. */
+int ovs_nla_put_identifier(const struct sw_flow *flow, struct sk_buff *skb)
+{
+	if (ovs_identifier_is_ufid(&flow->id))
+		return nla_put(skb, OVS_FLOW_ATTR_UFID, flow->id.ufid_len,
+			       flow->id.ufid);
+
+	return ovs_nla_put_key(flow->id.unmasked_key, flow->id.unmasked_key,
+			       OVS_FLOW_ATTR_KEY, false, skb);
+}
+
+/* Called with ovs_mutex or RCU read lock. */
+int ovs_nla_put_masked_key(const struct sw_flow *flow, struct sk_buff *skb)
+{
+	return ovs_nla_put_key(&flow->key, &flow->key,
+				OVS_FLOW_ATTR_KEY, false, skb);
+}
+
+/* Called with ovs_mutex or RCU read lock. */
+int ovs_nla_put_mask(const struct sw_flow *flow, struct sk_buff *skb)
+{
+	return ovs_nla_put_key(&flow->key, &flow->mask->key,
+				OVS_FLOW_ATTR_MASK, true, skb);
+}
+
 #define MAX_ACTIONS_BUFSIZE	(32 * 1024)
 
-struct sw_flow_actions *ovs_nla_alloc_flow_actions(int size)
+static struct sw_flow_actions *nla_alloc_flow_actions(int size, bool log)
 {
 	struct sw_flow_actions *sfa;
 
-	if (size > MAX_ACTIONS_BUFSIZE)
+	if (size > MAX_ACTIONS_BUFSIZE) {
+		OVS_NLERR(log, "Flow action size %u bytes exceeds max", size);
 		return ERR_PTR(-EINVAL);
+	}
 
 	sfa = kmalloc(sizeof(*sfa) + size, GFP_KERNEL);
 	if (!sfa)
@@ -1249,7 +1556,7 @@ void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts)
 }
 
 static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa,
-				       int attr_len)
+				       int attr_len, bool log)
 {
 
 	struct sw_flow_actions *acts;
@@ -1269,7 +1576,7 @@ static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa,
 		new_acts_size = MAX_ACTIONS_BUFSIZE;
 	}
 
-	acts = ovs_nla_alloc_flow_actions(new_acts_size);
+	acts = nla_alloc_flow_actions(new_acts_size, log);
 	if (IS_ERR(acts))
 		return (void *)acts;
 
@@ -1284,11 +1591,11 @@ out:
 }
 
 static struct nlattr *__add_action(struct sw_flow_actions **sfa,
-				   int attrtype, void *data, int len)
+				   int attrtype, void *data, int len, bool log)
 {
 	struct nlattr *a;
 
-	a = reserve_sfa_size(sfa, nla_attr_size(len));
+	a = reserve_sfa_size(sfa, nla_attr_size(len), log);
 	if (IS_ERR(a))
 		return a;
 
@@ -1303,24 +1610,22 @@ static struct nlattr *__add_action(struct sw_flow_actions **sfa,
 }
 
 static int add_action(struct sw_flow_actions **sfa, int attrtype,
-		      void *data, int len)
+		      void *data, int len, bool log)
 {
 	struct nlattr *a;
 
-	a = __add_action(sfa, attrtype, data, len);
-	if (IS_ERR(a))
-		return PTR_ERR(a);
+	a = __add_action(sfa, attrtype, data, len, log);
 
-	return 0;
+	return PTR_ERR_OR_ZERO(a);
 }
 
 static inline int add_nested_action_start(struct sw_flow_actions **sfa,
-					  int attrtype)
+					  int attrtype, bool log)
 {
 	int used = (*sfa)->actions_len;
 	int err;
 
-	err = add_action(sfa, attrtype, NULL, 0);
+	err = add_action(sfa, attrtype, NULL, 0, log);
 	if (err)
 		return err;
 
@@ -1336,9 +1641,15 @@ static inline void add_nested_action_end(struct sw_flow_actions *sfa,
 	a->nla_len = sfa->actions_len - st_offset;
 }
 
+static int __ovs_nla_copy_actions(const struct nlattr *attr,
+				  const struct sw_flow_key *key,
+				  int depth, struct sw_flow_actions **sfa,
+				  __be16 eth_type, __be16 vlan_tci, bool log);
+
 static int validate_and_copy_sample(const struct nlattr *attr,
 				    const struct sw_flow_key *key, int depth,
-				    struct sw_flow_actions **sfa)
+				    struct sw_flow_actions **sfa,
+				    __be16 eth_type, __be16 vlan_tci, bool log)
 {
 	const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1];
 	const struct nlattr *probability, *actions;
@@ -1364,18 +1675,19 @@ static int validate_and_copy_sample(const struct nlattr *attr,
 		return -EINVAL;
 
 	/* validation done, copy sample action. */
-	start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SAMPLE);
+	start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SAMPLE, log);
 	if (start < 0)
 		return start;
 	err = add_action(sfa, OVS_SAMPLE_ATTR_PROBABILITY,
-			 nla_data(probability), sizeof(u32));
+			 nla_data(probability), sizeof(u32), log);
 	if (err)
 		return err;
-	st_acts = add_nested_action_start(sfa, OVS_SAMPLE_ATTR_ACTIONS);
+	st_acts = add_nested_action_start(sfa, OVS_SAMPLE_ATTR_ACTIONS, log);
 	if (st_acts < 0)
 		return st_acts;
 
-	err = ovs_nla_copy_actions(actions, key, depth + 1, sfa);
+	err = __ovs_nla_copy_actions(actions, key, depth + 1, sfa,
+				     eth_type, vlan_tci, log);
 	if (err)
 		return err;
 
@@ -1385,16 +1697,6 @@ static int validate_and_copy_sample(const struct nlattr *attr,
 	return 0;
 }
 
-static int validate_tp_port(const struct sw_flow_key *flow_key)
-{
-	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;
-}
-
 void ovs_match_init(struct sw_flow_match *match,
 		    struct sw_flow_key *key,
 		    struct sw_flow_mask *mask)
@@ -1411,51 +1713,66 @@ void ovs_match_init(struct sw_flow_match *match,
 	}
 }
 
+static int validate_geneve_opts(struct sw_flow_key *key)
+{
+	struct geneve_opt *option;
+	int opts_len = key->tun_opts_len;
+	bool crit_opt = false;
+
+	option = (struct geneve_opt *)TUN_METADATA_OPTS(key, key->tun_opts_len);
+	while (opts_len > 0) {
+		int len;
+
+		if (opts_len < sizeof(*option))
+			return -EINVAL;
+
+		len = sizeof(*option) + option->length * 4;
+		if (len > opts_len)
+			return -EINVAL;
+
+		crit_opt |= !!(option->type & GENEVE_CRIT_OPT_TYPE);
+
+		option = (struct geneve_opt *)((u8 *)option + len);
+		opts_len -= len;
+	};
+
+	key->tun_key.tun_flags |= crit_opt ? TUNNEL_CRIT_OPT : 0;
+
+	return 0;
+}
+
 static int validate_and_copy_set_tun(const struct nlattr *attr,
-				     struct sw_flow_actions **sfa)
+				     struct sw_flow_actions **sfa, bool log)
 {
 	struct sw_flow_match match;
 	struct sw_flow_key key;
 	struct ovs_tunnel_info *tun_info;
 	struct nlattr *a;
-	int err, start;
+	int err = 0, start, opts_type;
 
 	ovs_match_init(&match, &key, NULL);
-	err = ipv4_tun_from_nlattr(nla_data(attr), &match, false);
-	if (err)
-		return err;
+	opts_type = ipv4_tun_from_nlattr(nla_data(attr), &match, false, log);
+	if (opts_type < 0)
+		return opts_type;
 
 	if (key.tun_opts_len) {
-		struct geneve_opt *option = GENEVE_OPTS(&key,
-							key.tun_opts_len);
-		int opts_len = key.tun_opts_len;
-		bool crit_opt = false;
-
-		while (opts_len > 0) {
-			int len;
-
-			if (opts_len < sizeof(*option))
-				return -EINVAL;
-
-			len = sizeof(*option) + option->length * 4;
-			if (len > opts_len)
-				return -EINVAL;
-
-			crit_opt |= !!(option->type & GENEVE_CRIT_OPT_TYPE);
-
-			option = (struct geneve_opt *)((u8 *)option + len);
-			opts_len -= len;
-		};
-
-		key.tun_key.tun_flags |= crit_opt ? TUNNEL_CRIT_OPT : 0;
+		switch (opts_type) {
+		case OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS:
+			err = validate_geneve_opts(&key);
+			if (err < 0)
+				return err;
+			break;
+		case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS:
+			break;
+		}
 	};
 
-	start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SET);
+	start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SET, log);
 	if (start < 0)
 		return start;
 
 	a = __add_action(sfa, OVS_KEY_ATTR_TUNNEL_INFO, NULL,
-			 sizeof(*tun_info) + key.tun_opts_len);
+			 sizeof(*tun_info) + key.tun_opts_len, log);
 	if (IS_ERR(a))
 		return PTR_ERR(a);
 
@@ -1468,9 +1785,9 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
 		 * everything else will go away after flow setup. We can append
 		 * it to tun_info and then point there.
 		 */
-		memcpy((tun_info + 1), GENEVE_OPTS(&key, key.tun_opts_len),
-		       key.tun_opts_len);
-		tun_info->options = (struct geneve_opt *)(tun_info + 1);
+		memcpy((tun_info + 1),
+		       TUN_METADATA_OPTS(&key, key.tun_opts_len), key.tun_opts_len);
+		tun_info->options = (tun_info + 1);
 	} else {
 		tun_info->options = NULL;
 	}
@@ -1480,21 +1797,43 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
 	return err;
 }
 
+/* Return false if there are any non-masked bits set.
+ * Mask follows data immediately, before any netlink padding.
+ */
+static bool validate_masked(u8 *data, int len)
+{
+	u8 *mask = data + len;
+
+	while (len--)
+		if (*data++ & ~*mask++)
+			return false;
+
+	return true;
+}
+
 static int validate_set(const struct nlattr *a,
 			const struct sw_flow_key *flow_key,
 			struct sw_flow_actions **sfa,
-			bool *set_tun)
+			bool *skip_copy, __be16 eth_type, bool masked, bool log)
 {
 	const struct nlattr *ovs_key = nla_data(a);
 	int key_type = nla_type(ovs_key);
+	size_t key_len;
 
 	/* There can be only one key in a action */
 	if (nla_total_size(nla_len(ovs_key)) != nla_len(a))
 		return -EINVAL;
 
+	key_len = nla_len(ovs_key);
+	if (masked)
+		key_len /= 2;
+
 	if (key_type > OVS_KEY_ATTR_MAX ||
-	    (ovs_key_lens[key_type] != nla_len(ovs_key) &&
-	     ovs_key_lens[key_type] != -1))
+	    (ovs_key_lens[key_type].len != key_len &&
+	     ovs_key_lens[key_type].len != OVS_ATTR_NESTED))
+		return -EINVAL;
+
+	if (masked && !validate_masked(nla_data(ovs_key), key_len))
 		return -EINVAL;
 
 	switch (key_type) {
@@ -1508,69 +1847,128 @@ static int validate_set(const struct nlattr *a,
 		break;
 
 	case OVS_KEY_ATTR_TUNNEL:
-		*set_tun = true;
-		err = validate_and_copy_set_tun(a, sfa);
+		if (eth_p_mpls(eth_type))
+			return -EINVAL;
+
+		if (masked)
+			return -EINVAL; /* Masked tunnel set not supported. */
+
+		*skip_copy = true;
+		err = validate_and_copy_set_tun(a, sfa, log);
 		if (err)
 			return err;
 		break;
 
 	case OVS_KEY_ATTR_IPV4:
-		if (flow_key->eth.type != htons(ETH_P_IP))
-			return -EINVAL;
-
-		if (!flow_key->ip.proto)
+		if (eth_type != htons(ETH_P_IP))
 			return -EINVAL;
 
 		ipv4_key = nla_data(ovs_key);
-		if (ipv4_key->ipv4_proto != flow_key->ip.proto)
-			return -EINVAL;
 
-		if (ipv4_key->ipv4_frag != flow_key->ip.frag)
-			return -EINVAL;
+		if (masked) {
+			const struct ovs_key_ipv4 *mask = ipv4_key + 1;
 
+			/* Non-writeable fields. */
+			if (mask->ipv4_proto || mask->ipv4_frag)
+				return -EINVAL;
+		} else {
+			if (ipv4_key->ipv4_proto != flow_key->ip.proto)
+				return -EINVAL;
+
+			if (ipv4_key->ipv4_frag != flow_key->ip.frag)
+				return -EINVAL;
+		}
 		break;
 
 	case OVS_KEY_ATTR_IPV6:
-		if (flow_key->eth.type != htons(ETH_P_IPV6))
-			return -EINVAL;
-
-		if (!flow_key->ip.proto)
+		if (eth_type != htons(ETH_P_IPV6))
 			return -EINVAL;
 
 		ipv6_key = nla_data(ovs_key);
-		if (ipv6_key->ipv6_proto != flow_key->ip.proto)
-			return -EINVAL;
 
-		if (ipv6_key->ipv6_frag != flow_key->ip.frag)
-			return -EINVAL;
+		if (masked) {
+			const struct ovs_key_ipv6 *mask = ipv6_key + 1;
+
+			/* Non-writeable fields. */
+			if (mask->ipv6_proto || mask->ipv6_frag)
+				return -EINVAL;
 
+			/* Invalid bits in the flow label mask? */
+			if (ntohl(mask->ipv6_label) & 0xFFF00000)
+				return -EINVAL;
+		} else {
+			if (ipv6_key->ipv6_proto != flow_key->ip.proto)
+				return -EINVAL;
+
+			if (ipv6_key->ipv6_frag != flow_key->ip.frag)
+				return -EINVAL;
+		}
 		if (ntohl(ipv6_key->ipv6_label) & 0xFFF00000)
 			return -EINVAL;
 
 		break;
 
 	case OVS_KEY_ATTR_TCP:
-		if (flow_key->ip.proto != IPPROTO_TCP)
+		if ((eth_type != htons(ETH_P_IP) &&
+		     eth_type != htons(ETH_P_IPV6)) ||
+		    flow_key->ip.proto != IPPROTO_TCP)
 			return -EINVAL;
 
-		return validate_tp_port(flow_key);
+		break;
 
 	case OVS_KEY_ATTR_UDP:
-		if (flow_key->ip.proto != IPPROTO_UDP)
+		if ((eth_type != htons(ETH_P_IP) &&
+		     eth_type != htons(ETH_P_IPV6)) ||
+		    flow_key->ip.proto != IPPROTO_UDP)
 			return -EINVAL;
 
-		return validate_tp_port(flow_key);
+		break;
+
+	case OVS_KEY_ATTR_MPLS:
+		if (!eth_p_mpls(eth_type))
+			return -EINVAL;
+		break;
 
 	case OVS_KEY_ATTR_SCTP:
-		if (flow_key->ip.proto != IPPROTO_SCTP)
+		if ((eth_type != htons(ETH_P_IP) &&
+		     eth_type != htons(ETH_P_IPV6)) ||
+		    flow_key->ip.proto != IPPROTO_SCTP)
 			return -EINVAL;
 
-		return validate_tp_port(flow_key);
+		break;
 
 	default:
 		return -EINVAL;
 	}
 
+	/* Convert non-masked non-tunnel set actions to masked set actions. */
+	if (!masked && key_type != OVS_KEY_ATTR_TUNNEL) {
+		int start, len = key_len * 2;
+		struct nlattr *at;
+
+		*skip_copy = true;
+
+		start = add_nested_action_start(sfa,
+						OVS_ACTION_ATTR_SET_TO_MASKED,
+						log);
+		if (start < 0)
+			return start;
+
+		at = __add_action(sfa, key_type, NULL, len, log);
+		if (IS_ERR(at))
+			return PTR_ERR(at);
+
+		memcpy(nla_data(at), nla_data(ovs_key), key_len); /* Key. */
+		memset(nla_data(at) + key_len, 0xff, key_len);    /* Mask. */
+		/* Clear non-writeable bits from otherwise writeable fields. */
+		if (key_type == OVS_KEY_ATTR_IPV6) {
+			struct ovs_key_ipv6 *mask = nla_data(at) + key_len;
+
+			mask->ipv6_label &= htonl(0x000FFFFF);
+		}
+		add_nested_action_end(*sfa, start);
+	}
+
 	return 0;
 }
 
@@ -1579,6 +1977,7 @@ static int validate_userspace(const struct nlattr *attr)
 	static const struct nla_policy userspace_policy[OVS_USERSPACE_ATTR_MAX + 1] = {
 		[OVS_USERSPACE_ATTR_PID] = {.type = NLA_U32 },
 		[OVS_USERSPACE_ATTR_USERDATA] = {.type = NLA_UNSPEC },
+		[OVS_USERSPACE_ATTR_EGRESS_TUN_PORT] = {.type = NLA_U32 },
 	};
 	struct nlattr *a[OVS_USERSPACE_ATTR_MAX + 1];
 	int error;
@@ -1596,12 +1995,12 @@ static int validate_userspace(const struct nlattr *attr)
 }
 
 static int copy_action(const struct nlattr *from,
-		       struct sw_flow_actions **sfa)
+		       struct sw_flow_actions **sfa, bool log)
 {
 	int totlen = NLA_ALIGN(from->nla_len);
 	struct nlattr *to;
 
-	to = reserve_sfa_size(sfa, from->nla_len);
+	to = reserve_sfa_size(sfa, from->nla_len, log);
 	if (IS_ERR(to))
 		return PTR_ERR(to);
 
@@ -1609,10 +2008,10 @@ static int copy_action(const struct nlattr *from,
 	return 0;
 }
 
-int ovs_nla_copy_actions(const struct nlattr *attr,
-			 const struct sw_flow_key *key,
-			 int depth,
-			 struct sw_flow_actions **sfa)
+static int __ovs_nla_copy_actions(const struct nlattr *attr,
+				  const struct sw_flow_key *key,
+				  int depth, struct sw_flow_actions **sfa,
+				  __be16 eth_type, __be16 vlan_tci, bool log)
 {
 	const struct nlattr *a;
 	int rem, err;
@@ -1626,9 +2025,12 @@ int ovs_nla_copy_actions(const struct nlattr *attr,
 			[OVS_ACTION_ATTR_OUTPUT] = sizeof(u32),
 			[OVS_ACTION_ATTR_RECIRC] = sizeof(u32),
 			[OVS_ACTION_ATTR_USERSPACE] = (u32)-1,
+			[OVS_ACTION_ATTR_PUSH_MPLS] = sizeof(struct ovs_action_push_mpls),
+			[OVS_ACTION_ATTR_POP_MPLS] = sizeof(__be16),
 			[OVS_ACTION_ATTR_PUSH_VLAN] = sizeof(struct ovs_action_push_vlan),
 			[OVS_ACTION_ATTR_POP_VLAN] = 0,
 			[OVS_ACTION_ATTR_SET] = (u32)-1,
+			[OVS_ACTION_ATTR_SET_MASKED] = (u32)-1,
 			[OVS_ACTION_ATTR_SAMPLE] = (u32)-1,
 			[OVS_ACTION_ATTR_HASH] = sizeof(struct ovs_action_hash)
 		};
@@ -1671,6 +2073,7 @@ int ovs_nla_copy_actions(const struct nlattr *attr,
 		}
 
 		case OVS_ACTION_ATTR_POP_VLAN:
+			vlan_tci = htons(0);
 			break;
 
 		case OVS_ACTION_ATTR_PUSH_VLAN:
@@ -1679,29 +2082,76 @@ int ovs_nla_copy_actions(const struct nlattr *attr,
 				return -EINVAL;
 			if (!(vlan->vlan_tci & htons(VLAN_TAG_PRESENT)))
 				return -EINVAL;
+			vlan_tci = vlan->vlan_tci;
 			break;
 
 		case OVS_ACTION_ATTR_RECIRC:
 			break;
 
+		case OVS_ACTION_ATTR_PUSH_MPLS: {
+			const struct ovs_action_push_mpls *mpls = nla_data(a);
+
+			if (!eth_p_mpls(mpls->mpls_ethertype))
+				return -EINVAL;
+			/* Prohibit push MPLS other than to a white list
+			 * for packets that have a known tag order.
+			 */
+			if (vlan_tci & htons(VLAN_TAG_PRESENT) ||
+			    (eth_type != htons(ETH_P_IP) &&
+			     eth_type != htons(ETH_P_IPV6) &&
+			     eth_type != htons(ETH_P_ARP) &&
+			     eth_type != htons(ETH_P_RARP) &&
+			     !eth_p_mpls(eth_type)))
+				return -EINVAL;
+			eth_type = mpls->mpls_ethertype;
+			break;
+		}
+
+		case OVS_ACTION_ATTR_POP_MPLS:
+			if (vlan_tci & htons(VLAN_TAG_PRESENT) ||
+			    !eth_p_mpls(eth_type))
+				return -EINVAL;
+
+			/* Disallow subsequent L2.5+ set and mpls_pop actions
+			 * as there is no check here to ensure that the new
+			 * eth_type is valid and thus set actions could
+			 * write off the end of the packet or otherwise
+			 * corrupt it.
+			 *
+			 * Support for these actions is planned using packet
+			 * recirculation.
+			 */
+			eth_type = htons(0);
+			break;
+
 		case OVS_ACTION_ATTR_SET:
-			err = validate_set(a, key, sfa, &skip_copy);
+			err = validate_set(a, key, sfa,
+					   &skip_copy, eth_type, false, log);
+			if (err)
+				return err;
+			break;
+
+		case OVS_ACTION_ATTR_SET_MASKED:
+			err = validate_set(a, key, sfa,
+					   &skip_copy, eth_type, true, log);
 			if (err)
 				return err;
 			break;
 
 		case OVS_ACTION_ATTR_SAMPLE:
-			err = validate_and_copy_sample(a, key, depth, sfa);
+			err = validate_and_copy_sample(a, key, depth, sfa,
+						       eth_type, vlan_tci, log);
 			if (err)
 				return err;
 			skip_copy = true;
 			break;
 
 		default:
+			OVS_NLERR(log, "Unknown Action type %d", type);
 			return -EINVAL;
 		}
 		if (!skip_copy) {
-			err = copy_action(a, sfa);
+			err = copy_action(a, sfa, log);
 			if (err)
 				return err;
 		}
@@ -1713,6 +2163,25 @@ int ovs_nla_copy_actions(const struct nlattr *attr,
 	return 0;
 }
 
+/* 'key' must be the masked key. */
+int ovs_nla_copy_actions(const struct nlattr *attr,
+			 const struct sw_flow_key *key,
+			 struct sw_flow_actions **sfa, bool log)
+{
+	int err;
+
+	*sfa = nla_alloc_flow_actions(nla_len(attr), log);
+	if (IS_ERR(*sfa))
+		return PTR_ERR(*sfa);
+
+	err = __ovs_nla_copy_actions(attr, key, 0, sfa, key->eth.type,
+				     key->eth.tci, log);
+	if (err)
+		kfree(*sfa);
+
+	return err;
+}
+
 static int sample_action_to_attr(const struct nlattr *attr, struct sk_buff *skb)
 {
 	const struct nlattr *a;
@@ -1782,6 +2251,27 @@ static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb)
 	return 0;
 }
 
+static int masked_set_action_to_set_action_attr(const struct nlattr *a,
+						struct sk_buff *skb)
+{
+	const struct nlattr *ovs_key = nla_data(a);
+	struct nlattr *nla;
+	size_t key_len = nla_len(ovs_key) / 2;
+
+	/* Revert the conversion we did from a non-masked set action to
+	 * masked set action.
+	 */
+	nla = nla_nest_start(skb, OVS_ACTION_ATTR_SET);
+	if (!nla)
+		return -EMSGSIZE;
+
+	if (nla_put(skb, nla_type(ovs_key), key_len, nla_data(ovs_key)))
+		return -EMSGSIZE;
+
+	nla_nest_end(skb, nla);
+	return 0;
+}
+
 int ovs_nla_put_actions(const struct nlattr *attr, int len, struct sk_buff *skb)
 {
 	const struct nlattr *a;
@@ -1797,6 +2287,12 @@ int ovs_nla_put_actions(const struct nlattr *attr, int len, struct sk_buff *skb)
 				return err;
 			break;
 
+		case OVS_ACTION_ATTR_SET_TO_MASKED:
+			err = masked_set_action_to_set_action_attr(a, skb);
+			if (err)
+				return err;
+			break;
+
 		case OVS_ACTION_ATTR_SAMPLE:
 			err = sample_action_to_attr(a, skb);
 			if (err)
diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h
index 206e45add888..5c3d75bff310 100644
--- a/net/openvswitch/flow_netlink.h
+++ b/net/openvswitch/flow_netlink.h
@@ -37,24 +37,37 @@
 
 #include "flow.h"
 
+size_t ovs_tun_key_attr_size(void);
+size_t ovs_key_attr_size(void);
+
 void ovs_match_init(struct sw_flow_match *match,
 		    struct sw_flow_key *key, struct sw_flow_mask *mask);
 
-int ovs_nla_put_flow(const struct sw_flow_key *,
-		     const struct sw_flow_key *, struct sk_buff *);
-int ovs_nla_get_flow_metadata(const struct nlattr *, struct sw_flow_key *);
+int ovs_nla_put_key(const struct sw_flow_key *, const struct sw_flow_key *,
+		    int attr, bool is_mask, struct sk_buff *);
+int ovs_nla_get_flow_metadata(const struct nlattr *, struct sw_flow_key *,
+			      bool log);
+
+int ovs_nla_put_identifier(const struct sw_flow *flow, struct sk_buff *skb);
+int ovs_nla_put_masked_key(const struct sw_flow *flow, struct sk_buff *skb);
+int ovs_nla_put_mask(const struct sw_flow *flow, struct sk_buff *skb);
+
+int ovs_nla_get_match(struct sw_flow_match *, const struct nlattr *key,
+		      const struct nlattr *mask, bool log);
+int ovs_nla_put_egress_tunnel_key(struct sk_buff *,
+				  const struct ovs_tunnel_info *);
 
-int ovs_nla_get_match(struct sw_flow_match *match,
-		      const struct nlattr *,
-		      const struct nlattr *);
+bool ovs_nla_get_ufid(struct sw_flow_id *, const struct nlattr *, bool log);
+int ovs_nla_get_identifier(struct sw_flow_id *sfid, const struct nlattr *ufid,
+			   const struct sw_flow_key *key, bool log);
+u32 ovs_nla_get_ufid_flags(const struct nlattr *attr);
 
 int ovs_nla_copy_actions(const struct nlattr *attr,
-			 const struct sw_flow_key *key, int depth,
-			 struct sw_flow_actions **sfa);
+			 const struct sw_flow_key *key,
+			 struct sw_flow_actions **sfa, bool log);
 int ovs_nla_put_actions(const struct nlattr *attr,
 			int len, struct sk_buff *skb);
 
-struct sw_flow_actions *ovs_nla_alloc_flow_actions(int actions_len);
 void ovs_nla_free_flow_actions(struct sw_flow_actions *);
 
 #endif /* flow_netlink.h */
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index cf2d853646f0..4613df8c8290 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.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
@@ -25,7 +25,7 @@
 #include <linux/if_vlan.h>
 #include <net/llc_pdu.h>
 #include <linux/kernel.h>
-#include <linux/hash.h>
+#include <linux/jhash.h>
 #include <linux/jiffies.h>
 #include <linux/llc.h>
 #include <linux/module.h>
@@ -85,6 +85,8 @@ struct sw_flow *ovs_flow_alloc(void)
 
 	flow->sf_acts = NULL;
 	flow->mask = NULL;
+	flow->id.unmasked_key = NULL;
+	flow->id.ufid_len = 0;
 	flow->stats_last_writer = NUMA_NO_NODE;
 
 	/* Initialize the default stat node. */
@@ -107,7 +109,7 @@ err:
 	return ERR_PTR(-ENOMEM);
 }
 
-int ovs_flow_tbl_count(struct flow_table *table)
+int ovs_flow_tbl_count(const struct flow_table *table)
 {
 	return table->count;
 }
@@ -139,6 +141,8 @@ static void flow_free(struct sw_flow *flow)
 {
 	int node;
 
+	if (ovs_identifier_is_key(&flow->id))
+		kfree(flow->id.unmasked_key);
 	kfree((struct sw_flow_actions __force *)flow->sf_acts);
 	for_each_node(node)
 		if (flow->stats[node])
@@ -200,18 +204,28 @@ static struct table_instance *table_instance_alloc(int new_size)
 
 int ovs_flow_tbl_init(struct flow_table *table)
 {
-	struct table_instance *ti;
+	struct table_instance *ti, *ufid_ti;
 
 	ti = table_instance_alloc(TBL_MIN_BUCKETS);
 
 	if (!ti)
 		return -ENOMEM;
 
+	ufid_ti = table_instance_alloc(TBL_MIN_BUCKETS);
+	if (!ufid_ti)
+		goto free_ti;
+
 	rcu_assign_pointer(table->ti, ti);
+	rcu_assign_pointer(table->ufid_ti, ufid_ti);
 	INIT_LIST_HEAD(&table->mask_list);
 	table->last_rehash = jiffies;
 	table->count = 0;
+	table->ufid_count = 0;
 	return 0;
+
+free_ti:
+	__table_instance_destroy(ti);
+	return -ENOMEM;
 }
 
 static void flow_tbl_destroy_rcu_cb(struct rcu_head *rcu)
@@ -221,13 +235,16 @@ static void flow_tbl_destroy_rcu_cb(struct rcu_head *rcu)
 	__table_instance_destroy(ti);
 }
 
-static void table_instance_destroy(struct table_instance *ti, bool deferred)
+static void table_instance_destroy(struct table_instance *ti,
+				   struct table_instance *ufid_ti,
+				   bool deferred)
 {
 	int i;
 
 	if (!ti)
 		return;
 
+	BUG_ON(!ufid_ti);
 	if (ti->keep_flows)
 		goto skip_flows;
 
@@ -236,25 +253,35 @@ static void table_instance_destroy(struct table_instance *ti, bool deferred)
 		struct hlist_head *head = flex_array_get(ti->buckets, i);
 		struct hlist_node *n;
 		int ver = ti->node_ver;
+		int ufid_ver = ufid_ti->node_ver;
 
-		hlist_for_each_entry_safe(flow, n, head, hash_node[ver]) {
-			hlist_del_rcu(&flow->hash_node[ver]);
+		hlist_for_each_entry_safe(flow, n, head, flow_table.node[ver]) {
+			hlist_del_rcu(&flow->flow_table.node[ver]);
+			if (ovs_identifier_is_ufid(&flow->id))
+				hlist_del_rcu(&flow->ufid_table.node[ufid_ver]);
 			ovs_flow_free(flow, deferred);
 		}
 	}
 
 skip_flows:
-	if (deferred)
+	if (deferred) {
 		call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb);
-	else
+		call_rcu(&ufid_ti->rcu, flow_tbl_destroy_rcu_cb);
+	} else {
 		__table_instance_destroy(ti);
+		__table_instance_destroy(ufid_ti);
+	}
 }
 
-void ovs_flow_tbl_destroy(struct flow_table *table, bool deferred)
+/* No need for locking this function is called from RCU callback or
+ * error path.
+ */
+void ovs_flow_tbl_destroy(struct flow_table *table)
 {
-	struct table_instance *ti = ovsl_dereference(table->ti);
+	struct table_instance *ti = rcu_dereference_raw(table->ti);
+	struct table_instance *ufid_ti = rcu_dereference_raw(table->ufid_ti);
 
-	table_instance_destroy(ti, deferred);
+	table_instance_destroy(ti, ufid_ti, false);
 }
 
 struct sw_flow *ovs_flow_tbl_dump_next(struct table_instance *ti,
@@ -269,7 +296,7 @@ struct sw_flow *ovs_flow_tbl_dump_next(struct table_instance *ti,
 	while (*bucket < ti->n_buckets) {
 		i = 0;
 		head = flex_array_get(ti->buckets, *bucket);
-		hlist_for_each_entry_rcu(flow, head, hash_node[ver]) {
+		hlist_for_each_entry_rcu(flow, head, flow_table.node[ver]) {
 			if (i < *last) {
 				i++;
 				continue;
@@ -291,16 +318,26 @@ static struct hlist_head *find_bucket(struct table_instance *ti, u32 hash)
 				(hash & (ti->n_buckets - 1)));
 }
 
-static void table_instance_insert(struct table_instance *ti, struct sw_flow *flow)
+static void table_instance_insert(struct table_instance *ti,
+				  struct sw_flow *flow)
 {
 	struct hlist_head *head;
 
-	head = find_bucket(ti, flow->hash);
-	hlist_add_head_rcu(&flow->hash_node[ti->node_ver], head);
+	head = find_bucket(ti, flow->flow_table.hash);
+	hlist_add_head_rcu(&flow->flow_table.node[ti->node_ver], head);
+}
+
+static void ufid_table_instance_insert(struct table_instance *ti,
+				       struct sw_flow *flow)
+{
+	struct hlist_head *head;
+
+	head = find_bucket(ti, flow->ufid_table.hash);
+	hlist_add_head_rcu(&flow->ufid_table.node[ti->node_ver], head);
 }
 
 static void flow_table_copy_flows(struct table_instance *old,
-				  struct table_instance *new)
+				  struct table_instance *new, bool ufid)
 {
 	int old_ver;
 	int i;
@@ -315,15 +352,21 @@ static void flow_table_copy_flows(struct table_instance *old,
 
 		head = flex_array_get(old->buckets, i);
 
-		hlist_for_each_entry(flow, head, hash_node[old_ver])
-			table_instance_insert(new, flow);
+		if (ufid)
+			hlist_for_each_entry(flow, head,
+					     ufid_table.node[old_ver])
+				ufid_table_instance_insert(new, flow);
+		else
+			hlist_for_each_entry(flow, head,
+					     flow_table.node[old_ver])
+				table_instance_insert(new, flow);
 	}
 
 	old->keep_flows = true;
 }
 
 static struct table_instance *table_instance_rehash(struct table_instance *ti,
-					    int n_buckets)
+						    int n_buckets, bool ufid)
 {
 	struct table_instance *new_ti;
 
@@ -331,39 +374,52 @@ static struct table_instance *table_instance_rehash(struct table_instance *ti,
 	if (!new_ti)
 		return NULL;
 
-	flow_table_copy_flows(ti, new_ti);
+	flow_table_copy_flows(ti, new_ti, ufid);
 
 	return new_ti;
 }
 
 int ovs_flow_tbl_flush(struct flow_table *flow_table)
 {
-	struct table_instance *old_ti;
-	struct table_instance *new_ti;
+	struct table_instance *old_ti, *new_ti;
+	struct table_instance *old_ufid_ti, *new_ufid_ti;
 
-	old_ti = ovsl_dereference(flow_table->ti);
 	new_ti = table_instance_alloc(TBL_MIN_BUCKETS);
 	if (!new_ti)
 		return -ENOMEM;
+	new_ufid_ti = table_instance_alloc(TBL_MIN_BUCKETS);
+	if (!new_ufid_ti)
+		goto err_free_ti;
+
+	old_ti = ovsl_dereference(flow_table->ti);
+	old_ufid_ti = ovsl_dereference(flow_table->ufid_ti);
 
 	rcu_assign_pointer(flow_table->ti, new_ti);
+	rcu_assign_pointer(flow_table->ufid_ti, new_ufid_ti);
 	flow_table->last_rehash = jiffies;
 	flow_table->count = 0;
+	flow_table->ufid_count = 0;
 
-	table_instance_destroy(old_ti, true);
+	table_instance_destroy(old_ti, old_ufid_ti, true);
 	return 0;
+
+err_free_ti:
+	__table_instance_destroy(new_ti);
+	return -ENOMEM;
 }
 
-static u32 flow_hash(const struct sw_flow_key *key, int key_start,
-		     int key_end)
+static u32 flow_hash(const struct sw_flow_key *key,
+		     const struct sw_flow_key_range *range)
 {
+	int key_start = range->start;
+	int key_end = range->end;
 	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 arch_fast_hash2(hash_key, hash_u32s, 0);
+	return jhash2(hash_key, hash_u32s, 0);
 }
 
 static int flow_key_start(const struct sw_flow_key *key)
@@ -392,39 +448,37 @@ static bool cmp_key(const struct sw_flow_key *key1,
 
 static bool flow_cmp_masked_key(const struct sw_flow *flow,
 				const struct sw_flow_key *key,
-				int key_start, int key_end)
+				const struct sw_flow_key_range *range)
 {
-	return cmp_key(&flow->key, key, key_start, key_end);
+	return cmp_key(&flow->key, key, range->start, range->end);
 }
 
-bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow,
-			       struct sw_flow_match *match)
+static bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow,
+				      const struct sw_flow_match *match)
 {
 	struct sw_flow_key *key = match->key;
 	int key_start = flow_key_start(key);
 	int key_end = match->range.end;
 
-	return cmp_key(&flow->unmasked_key, key, key_start, key_end);
+	BUG_ON(ovs_identifier_is_ufid(&flow->id));
+	return cmp_key(flow->id.unmasked_key, key, key_start, key_end);
 }
 
 static struct sw_flow *masked_flow_lookup(struct table_instance *ti,
 					  const struct sw_flow_key *unmasked,
-					  struct sw_flow_mask *mask)
+					  const struct sw_flow_mask *mask)
 {
 	struct sw_flow *flow;
 	struct hlist_head *head;
-	int key_start = mask->range.start;
-	int key_end = mask->range.end;
 	u32 hash;
 	struct sw_flow_key masked_key;
 
 	ovs_flow_mask_key(&masked_key, unmasked, mask);
-	hash = flow_hash(&masked_key, key_start, key_end);
+	hash = flow_hash(&masked_key, &mask->range);
 	head = find_bucket(ti, hash);
-	hlist_for_each_entry_rcu(flow, head, hash_node[ti->node_ver]) {
-		if (flow->mask == mask && flow->hash == hash &&
-		    flow_cmp_masked_key(flow, &masked_key,
-					  key_start, key_end))
+	hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver]) {
+		if (flow->mask == mask && flow->flow_table.hash == hash &&
+		    flow_cmp_masked_key(flow, &masked_key, &mask->range))
 			return flow;
 	}
 	return NULL;
@@ -457,7 +511,7 @@ struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *tbl,
 }
 
 struct sw_flow *ovs_flow_tbl_lookup_exact(struct flow_table *tbl,
-					  struct sw_flow_match *match)
+					  const struct sw_flow_match *match)
 {
 	struct table_instance *ti = rcu_dereference_ovsl(tbl->ti);
 	struct sw_flow_mask *mask;
@@ -466,7 +520,48 @@ struct sw_flow *ovs_flow_tbl_lookup_exact(struct flow_table *tbl,
 	/* 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 */
+		if (flow && ovs_identifier_is_key(&flow->id) &&
+		    ovs_flow_cmp_unmasked_key(flow, match))
+			return flow;
+	}
+	return NULL;
+}
+
+static u32 ufid_hash(const struct sw_flow_id *sfid)
+{
+	return jhash(sfid->ufid, sfid->ufid_len, 0);
+}
+
+static bool ovs_flow_cmp_ufid(const struct sw_flow *flow,
+			      const struct sw_flow_id *sfid)
+{
+	if (flow->id.ufid_len != sfid->ufid_len)
+		return false;
+
+	return !memcmp(flow->id.ufid, sfid->ufid, sfid->ufid_len);
+}
+
+bool ovs_flow_cmp(const struct sw_flow *flow, const struct sw_flow_match *match)
+{
+	if (ovs_identifier_is_ufid(&flow->id))
+		return flow_cmp_masked_key(flow, match->key, &match->range);
+
+	return ovs_flow_cmp_unmasked_key(flow, match);
+}
+
+struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *tbl,
+					 const struct sw_flow_id *ufid)
+{
+	struct table_instance *ti = rcu_dereference_ovsl(tbl->ufid_ti);
+	struct sw_flow *flow;
+	struct hlist_head *head;
+	u32 hash;
+
+	hash = ufid_hash(ufid);
+	head = find_bucket(ti, hash);
+	hlist_for_each_entry_rcu(flow, head, ufid_table.node[ti->node_ver]) {
+		if (flow->ufid_table.hash == hash &&
+		    ovs_flow_cmp_ufid(flow, ufid))
 			return flow;
 	}
 	return NULL;
@@ -483,9 +578,10 @@ int ovs_flow_tbl_num_masks(const struct flow_table *table)
 	return num;
 }
 
-static struct table_instance *table_instance_expand(struct table_instance *ti)
+static struct table_instance *table_instance_expand(struct table_instance *ti,
+						    bool ufid)
 {
-	return table_instance_rehash(ti, ti->n_buckets * 2);
+	return table_instance_rehash(ti, ti->n_buckets * 2, ufid);
 }
 
 /* Remove 'mask' from the mask list, if it is not needed any more. */
@@ -510,10 +606,15 @@ static void flow_mask_remove(struct flow_table *tbl, struct sw_flow_mask *mask)
 void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow)
 {
 	struct table_instance *ti = ovsl_dereference(table->ti);
+	struct table_instance *ufid_ti = ovsl_dereference(table->ufid_ti);
 
 	BUG_ON(table->count == 0);
-	hlist_del_rcu(&flow->hash_node[ti->node_ver]);
+	hlist_del_rcu(&flow->flow_table.node[ti->node_ver]);
 	table->count--;
+	if (ovs_identifier_is_ufid(&flow->id)) {
+		hlist_del_rcu(&flow->ufid_table.node[ufid_ti->node_ver]);
+		table->ufid_count--;
+	}
 
 	/* RCU delete the mask. 'flow->mask' is not NULLed, as it should be
 	 * accessible as long as the RCU read lock is held.
@@ -560,7 +661,7 @@ static struct sw_flow_mask *flow_mask_find(const struct flow_table *tbl,
 
 /* 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)
+			    const struct sw_flow_mask *new)
 {
 	struct sw_flow_mask *mask;
 	mask = flow_mask_find(tbl, new);
@@ -582,34 +683,64 @@ static int flow_mask_insert(struct flow_table *tbl, struct sw_flow *flow,
 }
 
 /* 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)
+static void flow_key_insert(struct flow_table *table, struct sw_flow *flow)
 {
 	struct table_instance *new_ti = NULL;
 	struct table_instance *ti;
-	int err;
 
-	err = flow_mask_insert(table, flow, mask);
-	if (err)
-		return err;
-
-	flow->hash = flow_hash(&flow->key, flow->mask->range.start,
-			flow->mask->range.end);
+	flow->flow_table.hash = flow_hash(&flow->key, &flow->mask->range);
 	ti = ovsl_dereference(table->ti);
 	table_instance_insert(ti, flow);
 	table->count++;
 
 	/* Expand table, if necessary, to make room. */
 	if (table->count > ti->n_buckets)
-		new_ti = table_instance_expand(ti);
+		new_ti = table_instance_expand(ti, false);
 	else if (time_after(jiffies, table->last_rehash + REHASH_INTERVAL))
-		new_ti = table_instance_rehash(ti, ti->n_buckets);
+		new_ti = table_instance_rehash(ti, ti->n_buckets, false);
 
 	if (new_ti) {
 		rcu_assign_pointer(table->ti, new_ti);
-		table_instance_destroy(ti, true);
+		call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb);
 		table->last_rehash = jiffies;
 	}
+}
+
+/* Must be called with OVS mutex held. */
+static void flow_ufid_insert(struct flow_table *table, struct sw_flow *flow)
+{
+	struct table_instance *ti;
+
+	flow->ufid_table.hash = ufid_hash(&flow->id);
+	ti = ovsl_dereference(table->ufid_ti);
+	ufid_table_instance_insert(ti, flow);
+	table->ufid_count++;
+
+	/* Expand table, if necessary, to make room. */
+	if (table->ufid_count > ti->n_buckets) {
+		struct table_instance *new_ti;
+
+		new_ti = table_instance_expand(ti, true);
+		if (new_ti) {
+			rcu_assign_pointer(table->ufid_ti, new_ti);
+			call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb);
+		}
+	}
+}
+
+/* Must be called with OVS mutex held. */
+int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow,
+			const struct sw_flow_mask *mask)
+{
+	int err;
+
+	err = flow_mask_insert(table, flow, mask);
+	if (err)
+		return err;
+	flow_key_insert(table, flow);
+	if (ovs_identifier_is_ufid(&flow->id))
+		flow_ufid_insert(table, flow);
+
 	return 0;
 }
 
diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h
index 5918bff7f3f6..616eda10d955 100644
--- a/net/openvswitch/flow_table.h
+++ b/net/openvswitch/flow_table.h
@@ -47,9 +47,11 @@ struct table_instance {
 
 struct flow_table {
 	struct table_instance __rcu *ti;
+	struct table_instance __rcu *ufid_ti;
 	struct list_head mask_list;
 	unsigned long last_rehash;
 	unsigned int count;
+	unsigned int ufid_count;
 };
 
 extern struct kmem_cache *flow_stats_cache;
@@ -61,12 +63,12 @@ struct sw_flow *ovs_flow_alloc(void);
 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, bool deferred);
+int ovs_flow_tbl_count(const struct flow_table *table);
+void ovs_flow_tbl_destroy(struct flow_table *table);
 int ovs_flow_tbl_flush(struct flow_table *flow_table);
 
 int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow,
-			struct sw_flow_mask *mask);
+			const struct sw_flow_mask *mask);
 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,
@@ -77,9 +79,11 @@ struct sw_flow *ovs_flow_tbl_lookup_stats(struct flow_table *,
 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);
+					  const struct sw_flow_match *match);
+struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *,
+					 const struct sw_flow_id *);
+
+bool ovs_flow_cmp(const struct sw_flow *, const struct sw_flow_match *);
 
 void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
 		       const struct sw_flow_mask *mask);
diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c
index 106a9d80b663..bf02fd5808c9 100644
--- a/net/openvswitch/vport-geneve.c
+++ b/net/openvswitch/vport-geneve.c
@@ -9,14 +9,13 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <linux/version.h>
-
 #include <linux/in.h>
 #include <linux/ip.h>
 #include <linux/net.h>
 #include <linux/rculist.h>
 #include <linux/udp.h>
 #include <linux/if_vlan.h>
+#include <linux/module.h>
 
 #include <net/geneve.h>
 #include <net/icmp.h>
@@ -28,6 +27,8 @@
 #include "datapath.h"
 #include "vport.h"
 
+static struct vport_ops ovs_geneve_vport_ops;
+
 /**
  * struct geneve_port - Keeps track of open UDP ports
  * @gs: The socket created for this port number.
@@ -65,7 +66,7 @@ static void tunnel_id_to_vni(__be64 tun_id, __u8 *vni)
 }
 
 /* Convert 24 bit VNI to 64 bit tunnel ID. */
-static __be64 vni_to_tunnel_id(__u8 *vni)
+static __be64 vni_to_tunnel_id(const __u8 *vni)
 {
 #ifdef __BIG_ENDIAN
 	return (vni[0] << 16) | (vni[1] << 8) | vni[2];
@@ -87,14 +88,16 @@ static void geneve_rcv(struct geneve_sock *gs, struct sk_buff *skb)
 
 	opts_len = geneveh->opt_len * 4;
 
-	flags = TUNNEL_KEY | TUNNEL_OPTIONS_PRESENT |
+	flags = TUNNEL_KEY | TUNNEL_GENEVE_OPT |
 		(udp_hdr(skb)->check != 0 ? TUNNEL_CSUM : 0) |
 		(geneveh->oam ? TUNNEL_OAM : 0) |
 		(geneveh->critical ? TUNNEL_CRIT_OPT : 0);
 
 	key = vni_to_tunnel_id(geneveh->vni);
 
-	ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), key, flags,
+	ovs_flow_tun_info_init(&tun_info, ip_hdr(skb),
+			       udp_hdr(skb)->source, udp_hdr(skb)->dest,
+			       key, flags,
 			       geneveh->options, opts_len);
 
 	ovs_vport_receive(vport, skb, &tun_info);
@@ -167,7 +170,7 @@ error:
 
 static int geneve_tnl_send(struct vport *vport, struct sk_buff *skb)
 {
-	struct ovs_key_ipv4_tunnel *tun_key;
+	const struct ovs_key_ipv4_tunnel *tun_key;
 	struct ovs_tunnel_info *tun_info;
 	struct net *net = ovs_dp_get_net(vport->dp);
 	struct geneve_port *geneve_port = geneve_vport(vport);
@@ -175,7 +178,7 @@ static int geneve_tnl_send(struct vport *vport, struct sk_buff *skb)
 	__be16 sport;
 	struct rtable *rt;
 	struct flowi4 fl;
-	u8 vni[3];
+	u8 vni[3], opts_len, *opts;
 	__be16 df;
 	int err;
 
@@ -186,16 +189,7 @@ static int geneve_tnl_send(struct vport *vport, struct sk_buff *skb)
 	}
 
 	tun_key = &tun_info->tunnel;
-
-	/* Route lookup */
-	memset(&fl, 0, sizeof(fl));
-	fl.daddr = tun_key->ipv4_dst;
-	fl.saddr = tun_key->ipv4_src;
-	fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos);
-	fl.flowi4_mark = skb->mark;
-	fl.flowi4_proto = IPPROTO_UDP;
-
-	rt = ip_route_output_key(net, &fl);
+	rt = ovs_tunnel_route_lookup(net, tun_key, skb->mark, &fl, IPPROTO_UDP);
 	if (IS_ERR(rt)) {
 		err = PTR_ERR(rt);
 		goto error;
@@ -206,15 +200,25 @@ static int geneve_tnl_send(struct vport *vport, struct sk_buff *skb)
 	tunnel_id_to_vni(tun_key->tun_id, vni);
 	skb->ignore_df = 1;
 
+	if (tun_key->tun_flags & TUNNEL_GENEVE_OPT) {
+		opts = (u8 *)tun_info->options;
+		opts_len = tun_info->options_len;
+	} else {
+		opts = NULL;
+		opts_len = 0;
+	}
+
 	err = geneve_xmit_skb(geneve_port->gs, rt, skb, fl.saddr,
 			      tun_key->ipv4_dst, tun_key->ipv4_tos,
 			      tun_key->ipv4_ttl, df, sport, dport,
-			      tun_key->tun_flags, vni,
-			      tun_info->options_len, (u8 *)tun_info->options,
-			      false);
+			      tun_key->tun_flags, vni, opts_len, opts,
+			      !!(tun_key->tun_flags & TUNNEL_CSUM), false);
 	if (err < 0)
 		ip_rt_put(rt);
+	return err;
+
 error:
+	kfree_skb(skb);
 	return err;
 }
 
@@ -225,11 +229,46 @@ static const char *geneve_get_name(const struct vport *vport)
 	return geneve_port->name;
 }
 
-const struct vport_ops ovs_geneve_vport_ops = {
+static int geneve_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
+				      struct ovs_tunnel_info *egress_tun_info)
+{
+	struct geneve_port *geneve_port = geneve_vport(vport);
+	struct net *net = ovs_dp_get_net(vport->dp);
+	__be16 dport = inet_sk(geneve_port->gs->sock->sk)->inet_sport;
+	__be16 sport = udp_flow_src_port(net, skb, 1, USHRT_MAX, true);
+
+	/* Get tp_src and tp_dst, refert to geneve_build_header().
+	 */
+	return ovs_tunnel_get_egress_info(egress_tun_info,
+					  ovs_dp_get_net(vport->dp),
+					  OVS_CB(skb)->egress_tun_info,
+					  IPPROTO_UDP, skb->mark, sport, dport);
+}
+
+static struct vport_ops ovs_geneve_vport_ops = {
 	.type		= OVS_VPORT_TYPE_GENEVE,
 	.create		= geneve_tnl_create,
 	.destroy	= geneve_tnl_destroy,
 	.get_name	= geneve_get_name,
 	.get_options	= geneve_get_options,
 	.send		= geneve_tnl_send,
+	.owner          = THIS_MODULE,
+	.get_egress_tun_info	= geneve_get_egress_tun_info,
 };
+
+static int __init ovs_geneve_tnl_init(void)
+{
+	return ovs_vport_ops_register(&ovs_geneve_vport_ops);
+}
+
+static void __exit ovs_geneve_tnl_exit(void)
+{
+	ovs_vport_ops_unregister(&ovs_geneve_vport_ops);
+}
+
+module_init(ovs_geneve_tnl_init);
+module_exit(ovs_geneve_tnl_exit);
+
+MODULE_DESCRIPTION("OVS: Geneve swiching port");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("vport-type-5");
diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c
index 108b82da2fd9..f17ac9642f4e 100644
--- a/net/openvswitch/vport-gre.c
+++ b/net/openvswitch/vport-gre.c
@@ -29,6 +29,7 @@
 #include <linux/jhash.h>
 #include <linux/list.h>
 #include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/workqueue.h>
 #include <linux/rculist.h>
 #include <net/route.h>
@@ -45,6 +46,8 @@
 #include "datapath.h"
 #include "vport.h"
 
+static struct vport_ops ovs_gre_vport_ops;
+
 /* Returns the least-significant 32 bits of a __be64. */
 static __be32 be64_get_low32(__be64 x)
 {
@@ -70,7 +73,7 @@ static struct sk_buff *__build_header(struct sk_buff *skb,
 
 	skb = gre_handle_offloads(skb, !!(tun_key->tun_flags & TUNNEL_CSUM));
 	if (IS_ERR(skb))
-		return NULL;
+		return skb;
 
 	tpi.flags = filter_tnl_flags(tun_key->tun_flags);
 	tpi.proto = htons(ETH_P_TEB);
@@ -105,7 +108,7 @@ static int gre_rcv(struct sk_buff *skb,
 		return PACKET_REJECT;
 
 	key = key_to_tunnel_id(tpi->key, tpi->seq);
-	ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), key,
+	ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), 0, 0, key,
 			       filter_tnl_flags(tpi->flags), NULL, 0);
 
 	ovs_vport_receive(vport, skb, &tun_info);
@@ -131,7 +134,7 @@ static int gre_err(struct sk_buff *skb, u32 info,
 static int gre_tnl_send(struct vport *vport, struct sk_buff *skb)
 {
 	struct net *net = ovs_dp_get_net(vport->dp);
-	struct ovs_key_ipv4_tunnel *tun_key;
+	const struct ovs_key_ipv4_tunnel *tun_key;
 	struct flowi4 fl;
 	struct rtable *rt;
 	int min_headroom;
@@ -141,27 +144,21 @@ static int gre_tnl_send(struct vport *vport, struct sk_buff *skb)
 
 	if (unlikely(!OVS_CB(skb)->egress_tun_info)) {
 		err = -EINVAL;
-		goto error;
+		goto err_free_skb;
 	}
 
 	tun_key = &OVS_CB(skb)->egress_tun_info->tunnel;
-	/* Route lookup */
-	memset(&fl, 0, sizeof(fl));
-	fl.daddr = tun_key->ipv4_dst;
-	fl.saddr = tun_key->ipv4_src;
-	fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos);
-	fl.flowi4_mark = skb->mark;
-	fl.flowi4_proto = IPPROTO_GRE;
-
-	rt = ip_route_output_key(net, &fl);
-	if (IS_ERR(rt))
-		return PTR_ERR(rt);
+	rt = ovs_tunnel_route_lookup(net, tun_key, skb->mark, &fl, IPPROTO_GRE);
+	if (IS_ERR(rt)) {
+		err = PTR_ERR(rt);
+		goto err_free_skb;
+	}
 
 	tunnel_hlen = ip_gre_calc_hlen(tun_key->tun_flags);
 
 	min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
 			+ tunnel_hlen + sizeof(struct iphdr)
-			+ (vlan_tx_tag_present(skb) ? VLAN_HLEN : 0);
+			+ (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0);
 	if (skb_headroom(skb) < min_headroom || skb_header_cloned(skb)) {
 		int head_delta = SKB_DATA_ALIGN(min_headroom -
 						skb_headroom(skb) +
@@ -172,20 +169,17 @@ static int gre_tnl_send(struct vport *vport, struct sk_buff *skb)
 			goto err_free_rt;
 	}
 
-	if (vlan_tx_tag_present(skb)) {
-		if (unlikely(!__vlan_put_tag(skb,
-					     skb->vlan_proto,
-					     vlan_tx_tag_get(skb)))) {
-			err = -ENOMEM;
-			goto err_free_rt;
-		}
-		skb->vlan_tci = 0;
+	skb = vlan_hwaccel_push_inside(skb);
+	if (unlikely(!skb)) {
+		err = -ENOMEM;
+		goto err_free_rt;
 	}
 
 	/* Push Tunnel header. */
 	skb = __build_header(skb, tunnel_hlen);
-	if (unlikely(!skb)) {
-		err = 0;
+	if (IS_ERR(skb)) {
+		err = PTR_ERR(skb);
+		skb = NULL;
 		goto err_free_rt;
 	}
 
@@ -199,7 +193,8 @@ static int gre_tnl_send(struct vport *vport, struct sk_buff *skb)
 			     tun_key->ipv4_tos, tun_key->ipv4_ttl, df, false);
 err_free_rt:
 	ip_rt_put(rt);
-error:
+err_free_skb:
+	kfree_skb(skb);
 	return err;
 }
 
@@ -281,10 +276,38 @@ static void gre_tnl_destroy(struct vport *vport)
 	gre_exit();
 }
 
-const struct vport_ops ovs_gre_vport_ops = {
+static int gre_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
+				   struct ovs_tunnel_info *egress_tun_info)
+{
+	return ovs_tunnel_get_egress_info(egress_tun_info,
+					  ovs_dp_get_net(vport->dp),
+					  OVS_CB(skb)->egress_tun_info,
+					  IPPROTO_GRE, skb->mark, 0, 0);
+}
+
+static struct vport_ops ovs_gre_vport_ops = {
 	.type		= OVS_VPORT_TYPE_GRE,
 	.create		= gre_create,
 	.destroy	= gre_tnl_destroy,
 	.get_name	= gre_get_name,
 	.send		= gre_tnl_send,
+	.get_egress_tun_info	= gre_get_egress_tun_info,
+	.owner		= THIS_MODULE,
 };
+
+static int __init ovs_gre_tnl_init(void)
+{
+	return ovs_vport_ops_register(&ovs_gre_vport_ops);
+}
+
+static void __exit ovs_gre_tnl_exit(void)
+{
+	ovs_vport_ops_unregister(&ovs_gre_vport_ops);
+}
+
+module_init(ovs_gre_tnl_init);
+module_exit(ovs_gre_tnl_exit);
+
+MODULE_DESCRIPTION("OVS: GRE switching port");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("vport-type-3");
diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c
index 84516126e5f3..6a55f7105505 100644
--- a/net/openvswitch/vport-internal_dev.c
+++ b/net/openvswitch/vport-internal_dev.c
@@ -36,6 +36,8 @@ struct internal_dev {
 	struct vport *vport;
 };
 
+static struct vport_ops ovs_internal_vport_ops;
+
 static struct internal_dev *internal_dev_priv(struct net_device *netdev)
 {
 	return netdev_priv(netdev);
@@ -222,6 +224,11 @@ static int internal_dev_recv(struct vport *vport, struct sk_buff *skb)
 	struct net_device *netdev = netdev_vport_priv(vport)->dev;
 	int len;
 
+	if (unlikely(!(netdev->flags & IFF_UP))) {
+		kfree_skb(skb);
+		return 0;
+	}
+
 	len = skb->len;
 
 	skb_dst_drop(skb);
@@ -238,7 +245,7 @@ static int internal_dev_recv(struct vport *vport, struct sk_buff *skb)
 	return len;
 }
 
-const struct vport_ops ovs_internal_vport_ops = {
+static struct vport_ops ovs_internal_vport_ops = {
 	.type		= OVS_VPORT_TYPE_INTERNAL,
 	.create		= internal_dev_create,
 	.destroy	= internal_dev_destroy,
@@ -261,10 +268,21 @@ struct vport *ovs_internal_dev_get_vport(struct net_device *netdev)
 
 int ovs_internal_dev_rtnl_link_register(void)
 {
-	return rtnl_link_register(&internal_dev_link_ops);
+	int err;
+
+	err = rtnl_link_register(&internal_dev_link_ops);
+	if (err < 0)
+		return err;
+
+	err = ovs_vport_ops_register(&ovs_internal_vport_ops);
+	if (err < 0)
+		rtnl_link_unregister(&internal_dev_link_ops);
+
+	return err;
 }
 
 void ovs_internal_dev_rtnl_link_unregister(void)
 {
+	ovs_vport_ops_unregister(&ovs_internal_vport_ops);
 	rtnl_link_unregister(&internal_dev_link_ops);
 }
diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c
index d21f77d875ba..33e6d6e2908f 100644
--- a/net/openvswitch/vport-netdev.c
+++ b/net/openvswitch/vport-netdev.c
@@ -33,6 +33,8 @@
 #include "vport-internal_dev.h"
 #include "vport-netdev.h"
 
+static struct vport_ops ovs_netdev_vport_ops;
+
 /* Must be called with rcu_read_lock. */
 static void netdev_port_receive(struct vport *vport, struct sk_buff *skb)
 {
@@ -75,7 +77,7 @@ static rx_handler_result_t netdev_frame_hook(struct sk_buff **pskb)
 	return RX_HANDLER_CONSUMED;
 }
 
-static struct net_device *get_dpdev(struct datapath *dp)
+static struct net_device *get_dpdev(const struct datapath *dp)
 {
 	struct vport *local;
 
@@ -123,6 +125,7 @@ static struct vport *netdev_create(const struct vport_parms *parms)
 	if (err)
 		goto error_master_upper_dev_unlink;
 
+	dev_disable_lro(netdev_vport->dev);
 	dev_set_promiscuity(netdev_vport->dev, 1);
 	netdev_vport->dev->priv_flags |= IFF_OVS_DATAPATH;
 	rtnl_unlock();
@@ -224,10 +227,20 @@ struct vport *ovs_netdev_get_vport(struct net_device *dev)
 		return NULL;
 }
 
-const struct vport_ops ovs_netdev_vport_ops = {
+static struct vport_ops ovs_netdev_vport_ops = {
 	.type		= OVS_VPORT_TYPE_NETDEV,
 	.create		= netdev_create,
 	.destroy	= netdev_destroy,
 	.get_name	= ovs_netdev_get_name,
 	.send		= netdev_send,
 };
+
+int __init ovs_netdev_init(void)
+{
+	return ovs_vport_ops_register(&ovs_netdev_vport_ops);
+}
+
+void ovs_netdev_exit(void)
+{
+	ovs_vport_ops_unregister(&ovs_netdev_vport_ops);
+}
diff --git a/net/openvswitch/vport-netdev.h b/net/openvswitch/vport-netdev.h
index 8df01c1127e5..6f7038e79c52 100644
--- a/net/openvswitch/vport-netdev.h
+++ b/net/openvswitch/vport-netdev.h
@@ -41,4 +41,7 @@ netdev_vport_priv(const struct vport *vport)
 const char *ovs_netdev_get_name(const struct vport *);
 void ovs_netdev_detach_dev(struct vport *);
 
+int __init ovs_netdev_init(void);
+void ovs_netdev_exit(void);
+
 #endif /* vport_netdev.h */
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index 2735e01dca73..6d39766e7828 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -24,6 +24,7 @@
 #include <linux/net.h>
 #include <linux/rculist.h>
 #include <linux/udp.h>
+#include <linux/module.h>
 
 #include <net/icmp.h>
 #include <net/ip.h>
@@ -39,6 +40,7 @@
 
 #include "datapath.h"
 #include "vport.h"
+#include "vport-vxlan.h"
 
 /**
  * struct vxlan_port - Keeps track of open UDP ports
@@ -48,25 +50,41 @@
 struct vxlan_port {
 	struct vxlan_sock *vs;
 	char name[IFNAMSIZ];
+	u32 exts; /* VXLAN_F_* in <net/vxlan.h> */
 };
 
+static struct vport_ops ovs_vxlan_vport_ops;
+
 static inline struct vxlan_port *vxlan_vport(const struct vport *vport)
 {
 	return vport_priv(vport);
 }
 
 /* Called with rcu_read_lock and BH disabled. */
-static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, __be32 vx_vni)
+static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb,
+		      struct vxlan_metadata *md)
 {
 	struct ovs_tunnel_info tun_info;
+	struct vxlan_port *vxlan_port;
 	struct vport *vport = vs->data;
 	struct iphdr *iph;
+	struct ovs_vxlan_opts opts = {
+		.gbp = md->gbp,
+	};
 	__be64 key;
+	__be16 flags;
+
+	flags = TUNNEL_KEY | (udp_hdr(skb)->check != 0 ? TUNNEL_CSUM : 0);
+	vxlan_port = vxlan_vport(vport);
+	if (vxlan_port->exts & VXLAN_F_GBP && md->gbp)
+		flags |= TUNNEL_VXLAN_OPT;
 
 	/* Save outer tunnel values */
 	iph = ip_hdr(skb);
-	key = cpu_to_be64(ntohl(vx_vni) >> 8);
-	ovs_flow_tun_info_init(&tun_info, iph, key, TUNNEL_KEY, NULL, 0);
+	key = cpu_to_be64(ntohl(md->vni) >> 8);
+	ovs_flow_tun_info_init(&tun_info, iph,
+			       udp_hdr(skb)->source, udp_hdr(skb)->dest,
+			       key, flags, &opts, sizeof(opts));
 
 	ovs_vport_receive(vport, skb, &tun_info);
 }
@@ -78,6 +96,21 @@ static int vxlan_get_options(const struct vport *vport, struct sk_buff *skb)
 
 	if (nla_put_u16(skb, OVS_TUNNEL_ATTR_DST_PORT, ntohs(dst_port)))
 		return -EMSGSIZE;
+
+	if (vxlan_port->exts) {
+		struct nlattr *exts;
+
+		exts = nla_nest_start(skb, OVS_TUNNEL_ATTR_EXTENSION);
+		if (!exts)
+			return -EMSGSIZE;
+
+		if (vxlan_port->exts & VXLAN_F_GBP &&
+		    nla_put_flag(skb, OVS_VXLAN_EXT_GBP))
+			return -EMSGSIZE;
+
+		nla_nest_end(skb, exts);
+	}
+
 	return 0;
 }
 
@@ -90,6 +123,31 @@ static void vxlan_tnl_destroy(struct vport *vport)
 	ovs_vport_deferred_free(vport);
 }
 
+static const struct nla_policy exts_policy[OVS_VXLAN_EXT_MAX+1] = {
+	[OVS_VXLAN_EXT_GBP]	= { .type = NLA_FLAG, },
+};
+
+static int vxlan_configure_exts(struct vport *vport, struct nlattr *attr)
+{
+	struct nlattr *exts[OVS_VXLAN_EXT_MAX+1];
+	struct vxlan_port *vxlan_port;
+	int err;
+
+	if (nla_len(attr) < sizeof(struct nlattr))
+		return -EINVAL;
+
+	err = nla_parse_nested(exts, OVS_VXLAN_EXT_MAX, attr, exts_policy);
+	if (err < 0)
+		return err;
+
+	vxlan_port = vxlan_vport(vport);
+
+	if (exts[OVS_VXLAN_EXT_GBP])
+		vxlan_port->exts |= VXLAN_F_GBP;
+
+	return 0;
+}
+
 static struct vport *vxlan_tnl_create(const struct vport_parms *parms)
 {
 	struct net *net = ovs_dp_get_net(parms->dp);
@@ -122,7 +180,17 @@ 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, 0);
+	a = nla_find_nested(options, OVS_TUNNEL_ATTR_EXTENSION);
+	if (a) {
+		err = vxlan_configure_exts(vport, a);
+		if (err) {
+			ovs_vport_free(vport);
+			goto error;
+		}
+	}
+
+	vs = vxlan_sock_add(net, htons(dst_port), vxlan_rcv, vport, true,
+			    vxlan_port->exts);
 	if (IS_ERR(vs)) {
 		ovs_vport_free(vport);
 		return (void *)vs;
@@ -135,17 +203,35 @@ error:
 	return ERR_PTR(err);
 }
 
+static int vxlan_ext_gbp(struct sk_buff *skb)
+{
+	const struct ovs_tunnel_info *tun_info;
+	const struct ovs_vxlan_opts *opts;
+
+	tun_info = OVS_CB(skb)->egress_tun_info;
+	opts = tun_info->options;
+
+	if (tun_info->tunnel.tun_flags & TUNNEL_VXLAN_OPT &&
+	    tun_info->options_len >= sizeof(*opts))
+		return opts->gbp;
+	else
+		return 0;
+}
+
 static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
 {
 	struct net *net = ovs_dp_get_net(vport->dp);
 	struct vxlan_port *vxlan_port = vxlan_vport(vport);
-	__be16 dst_port = inet_sk(vxlan_port->vs->sock->sk)->inet_sport;
-	struct ovs_key_ipv4_tunnel *tun_key;
+	struct sock *sk = vxlan_port->vs->sock->sk;
+	__be16 dst_port = inet_sk(sk)->inet_sport;
+	const struct ovs_key_ipv4_tunnel *tun_key;
+	struct vxlan_metadata md = {0};
 	struct rtable *rt;
 	struct flowi4 fl;
 	__be16 src_port;
 	__be16 df;
 	int err;
+	u32 vxflags;
 
 	if (unlikely(!OVS_CB(skb)->egress_tun_info)) {
 		err = -EINVAL;
@@ -153,15 +239,7 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
 	}
 
 	tun_key = &OVS_CB(skb)->egress_tun_info->tunnel;
-	/* Route lookup */
-	memset(&fl, 0, sizeof(fl));
-	fl.daddr = tun_key->ipv4_dst;
-	fl.saddr = tun_key->ipv4_src;
-	fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos);
-	fl.flowi4_mark = skb->mark;
-	fl.flowi4_proto = IPPROTO_UDP;
-
-	rt = ip_route_output_key(net, &fl);
+	rt = ovs_tunnel_route_lookup(net, tun_key, skb->mark, &fl, IPPROTO_UDP);
 	if (IS_ERR(rt)) {
 		err = PTR_ERR(rt);
 		goto error;
@@ -173,30 +251,72 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
 	skb->ignore_df = 1;
 
 	src_port = udp_flow_src_port(net, skb, 0, 0, true);
+	md.vni = htonl(be64_to_cpu(tun_key->tun_id) << 8);
+	md.gbp = vxlan_ext_gbp(skb);
+	vxflags = vxlan_port->exts |
+		      (tun_key->tun_flags & TUNNEL_CSUM ? VXLAN_F_UDP_CSUM : 0);
 
-	err = vxlan_xmit_skb(vxlan_port->vs, rt, skb,
-			     fl.saddr, tun_key->ipv4_dst,
+	err = vxlan_xmit_skb(rt, sk, skb, fl.saddr, tun_key->ipv4_dst,
 			     tun_key->ipv4_tos, tun_key->ipv4_ttl, df,
 			     src_port, dst_port,
-			     htonl(be64_to_cpu(tun_key->tun_id) << 8),
-			     false);
+			     &md, false, vxflags);
 	if (err < 0)
 		ip_rt_put(rt);
+	return err;
 error:
+	kfree_skb(skb);
 	return err;
 }
 
+static int vxlan_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
+				     struct ovs_tunnel_info *egress_tun_info)
+{
+	struct net *net = ovs_dp_get_net(vport->dp);
+	struct vxlan_port *vxlan_port = vxlan_vport(vport);
+	__be16 dst_port = inet_sk(vxlan_port->vs->sock->sk)->inet_sport;
+	__be16 src_port;
+	int port_min;
+	int port_max;
+
+	inet_get_local_port_range(net, &port_min, &port_max);
+	src_port = udp_flow_src_port(net, skb, 0, 0, true);
+
+	return ovs_tunnel_get_egress_info(egress_tun_info, net,
+					  OVS_CB(skb)->egress_tun_info,
+					  IPPROTO_UDP, skb->mark,
+					  src_port, dst_port);
+}
+
 static const char *vxlan_get_name(const struct vport *vport)
 {
 	struct vxlan_port *vxlan_port = vxlan_vport(vport);
 	return vxlan_port->name;
 }
 
-const struct vport_ops ovs_vxlan_vport_ops = {
+static struct vport_ops ovs_vxlan_vport_ops = {
 	.type		= OVS_VPORT_TYPE_VXLAN,
 	.create		= vxlan_tnl_create,
 	.destroy	= vxlan_tnl_destroy,
 	.get_name	= vxlan_get_name,
 	.get_options	= vxlan_get_options,
 	.send		= vxlan_tnl_send,
+	.get_egress_tun_info	= vxlan_get_egress_tun_info,
+	.owner		= THIS_MODULE,
 };
+
+static int __init ovs_vxlan_tnl_init(void)
+{
+	return ovs_vport_ops_register(&ovs_vxlan_vport_ops);
+}
+
+static void __exit ovs_vxlan_tnl_exit(void)
+{
+	ovs_vport_ops_unregister(&ovs_vxlan_vport_ops);
+}
+
+module_init(ovs_vxlan_tnl_init);
+module_exit(ovs_vxlan_tnl_exit);
+
+MODULE_DESCRIPTION("OVS: VXLAN switching port");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("vport-type-4");
diff --git a/net/openvswitch/vport-vxlan.h b/net/openvswitch/vport-vxlan.h
new file mode 100644
index 000000000000..4b08233e73d5
--- /dev/null
+++ b/net/openvswitch/vport-vxlan.h
@@ -0,0 +1,11 @@
+#ifndef VPORT_VXLAN_H
+#define VPORT_VXLAN_H 1
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+
+struct ovs_vxlan_opts {
+	__u32 gbp;
+};
+
+#endif
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 6015802ebe6f..067a3fff1d2c 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -28,6 +28,7 @@
 #include <linux/rtnetlink.h>
 #include <linux/compat.h>
 #include <net/net_namespace.h>
+#include <linux/module.h>
 
 #include "datapath.h"
 #include "vport.h"
@@ -36,22 +37,7 @@
 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[] = {
-	&ovs_netdev_vport_ops,
-	&ovs_internal_vport_ops,
-
-#ifdef CONFIG_OPENVSWITCH_GRE
-	&ovs_gre_vport_ops,
-#endif
-#ifdef CONFIG_OPENVSWITCH_VXLAN
-	&ovs_vxlan_vport_ops,
-#endif
-#ifdef CONFIG_OPENVSWITCH_GENEVE
-	&ovs_geneve_vport_ops,
-#endif
-};
+static LIST_HEAD(vport_ops_list);
 
 /* Protected by RCU read lock for reading, ovs_mutex for writing. */
 static struct hlist_head *dev_table;
@@ -82,12 +68,38 @@ void ovs_vport_exit(void)
 	kfree(dev_table);
 }
 
-static struct hlist_head *hash_bucket(struct net *net, const char *name)
+static struct hlist_head *hash_bucket(const struct net *net, const char *name)
 {
 	unsigned int hash = jhash(name, strlen(name), (unsigned long) net);
 	return &dev_table[hash & (VPORT_HASH_BUCKETS - 1)];
 }
 
+int ovs_vport_ops_register(struct vport_ops *ops)
+{
+	int err = -EEXIST;
+	struct vport_ops *o;
+
+	ovs_lock();
+	list_for_each_entry(o, &vport_ops_list, list)
+		if (ops->type == o->type)
+			goto errout;
+
+	list_add_tail(&ops->list, &vport_ops_list);
+	err = 0;
+errout:
+	ovs_unlock();
+	return err;
+}
+EXPORT_SYMBOL_GPL(ovs_vport_ops_register);
+
+void ovs_vport_ops_unregister(struct vport_ops *ops)
+{
+	ovs_lock();
+	list_del(&ops->list);
+	ovs_unlock();
+}
+EXPORT_SYMBOL_GPL(ovs_vport_ops_unregister);
+
 /**
  *	ovs_vport_locate - find a port that has already been created
  *
@@ -95,7 +107,7 @@ static struct hlist_head *hash_bucket(struct net *net, const char *name)
  *
  * Must be called with ovs or RCU read lock.
  */
-struct vport *ovs_vport_locate(struct net *net, const char *name)
+struct vport *ovs_vport_locate(const struct net *net, const char *name)
 {
 	struct hlist_head *bucket = hash_bucket(net, name);
 	struct vport *vport;
@@ -153,6 +165,7 @@ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops,
 
 	return vport;
 }
+EXPORT_SYMBOL_GPL(ovs_vport_alloc);
 
 /**
  *	ovs_vport_free - uninitialize and free vport
@@ -173,6 +186,18 @@ void ovs_vport_free(struct vport *vport)
 	free_percpu(vport->percpu_stats);
 	kfree(vport);
 }
+EXPORT_SYMBOL_GPL(ovs_vport_free);
+
+static struct vport_ops *ovs_vport_lookup(const struct vport_parms *parms)
+{
+	struct vport_ops *ops;
+
+	list_for_each_entry(ops, &vport_ops_list, list)
+		if (ops->type == parms->type)
+			return ops;
+
+	return NULL;
+}
 
 /**
  *	ovs_vport_add - add vport device (for kernel callers)
@@ -184,31 +209,40 @@ void ovs_vport_free(struct vport *vport)
  */
 struct vport *ovs_vport_add(const struct vport_parms *parms)
 {
+	struct vport_ops *ops;
 	struct vport *vport;
-	int err = 0;
-	int i;
 
-	for (i = 0; i < ARRAY_SIZE(vport_ops_list); i++) {
-		if (vport_ops_list[i]->type == parms->type) {
-			struct hlist_head *bucket;
+	ops = ovs_vport_lookup(parms);
+	if (ops) {
+		struct hlist_head *bucket;
 
-			vport = vport_ops_list[i]->create(parms);
-			if (IS_ERR(vport)) {
-				err = PTR_ERR(vport);
-				goto out;
-			}
+		if (!try_module_get(ops->owner))
+			return ERR_PTR(-EAFNOSUPPORT);
 
-			bucket = hash_bucket(ovs_dp_get_net(vport->dp),
-					     vport->ops->get_name(vport));
-			hlist_add_head_rcu(&vport->hash_node, bucket);
+		vport = ops->create(parms);
+		if (IS_ERR(vport)) {
+			module_put(ops->owner);
 			return vport;
 		}
+
+		bucket = hash_bucket(ovs_dp_get_net(vport->dp),
+				     vport->ops->get_name(vport));
+		hlist_add_head_rcu(&vport->hash_node, bucket);
+		return vport;
 	}
 
-	err = -EAFNOSUPPORT;
+	/* Unlock to attempt module load and return -EAGAIN if load
+	 * was successful as we need to restart the port addition
+	 * workflow.
+	 */
+	ovs_unlock();
+	request_module("vport-type-%d", parms->type);
+	ovs_lock();
 
-out:
-	return ERR_PTR(err);
+	if (!ovs_vport_lookup(parms))
+		return ERR_PTR(-EAFNOSUPPORT);
+	else
+		return ERR_PTR(-EAGAIN);
 }
 
 /**
@@ -240,7 +274,7 @@ void ovs_vport_del(struct vport *vport)
 	ASSERT_OVSL();
 
 	hlist_del_rcu(&vport->hash_node);
-
+	module_put(vport->ops->owner);
 	vport->ops->destroy(vport);
 }
 
@@ -344,7 +378,7 @@ int ovs_vport_get_options(const struct vport *vport, struct sk_buff *skb)
  *
  * Must be called with ovs_mutex.
  */
-int ovs_vport_set_upcall_portids(struct vport *vport,  struct nlattr *ids)
+int ovs_vport_set_upcall_portids(struct vport *vport, const struct nlattr *ids)
 {
 	struct vport_portids *old, *vport_portids;
 
@@ -435,7 +469,7 @@ u32 ovs_vport_find_upcall_portid(const struct vport *vport, struct sk_buff *skb)
  * skb->data should point to the Ethernet header.
  */
 void ovs_vport_receive(struct vport *vport, struct sk_buff *skb,
-		       struct ovs_tunnel_info *tun_info)
+		       const struct ovs_tunnel_info *tun_info)
 {
 	struct pcpu_sw_netstats *stats;
 	struct sw_flow_key key;
@@ -444,7 +478,8 @@ void ovs_vport_receive(struct vport *vport, struct sk_buff *skb,
 	stats = this_cpu_ptr(vport->percpu_stats);
 	u64_stats_update_begin(&stats->syncp);
 	stats->rx_packets++;
-	stats->rx_bytes += skb->len;
+	stats->rx_bytes += skb->len +
+			   (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0);
 	u64_stats_update_end(&stats->syncp);
 
 	OVS_CB(skb)->input_vport = vport;
@@ -457,6 +492,7 @@ void ovs_vport_receive(struct vport *vport, struct sk_buff *skb,
 	}
 	ovs_dp_process_packet(skb, &key);
 }
+EXPORT_SYMBOL_GPL(ovs_vport_receive);
 
 /**
  *	ovs_vport_send - send a packet on a device
@@ -482,10 +518,9 @@ int ovs_vport_send(struct vport *vport, struct sk_buff *skb)
 		u64_stats_update_end(&stats->syncp);
 	} else if (sent < 0) {
 		ovs_vport_record_error(vport, VPORT_E_TX_ERROR);
-		kfree_skb(skb);
-	} else
+	} else {
 		ovs_vport_record_error(vport, VPORT_E_TX_DROPPED);
-
+	}
 	return sent;
 }
 
@@ -535,3 +570,58 @@ void ovs_vport_deferred_free(struct vport *vport)
 
 	call_rcu(&vport->rcu, free_vport_rcu);
 }
+EXPORT_SYMBOL_GPL(ovs_vport_deferred_free);
+
+int ovs_tunnel_get_egress_info(struct ovs_tunnel_info *egress_tun_info,
+			       struct net *net,
+			       const struct ovs_tunnel_info *tun_info,
+			       u8 ipproto,
+			       u32 skb_mark,
+			       __be16 tp_src,
+			       __be16 tp_dst)
+{
+	const struct ovs_key_ipv4_tunnel *tun_key;
+	struct rtable *rt;
+	struct flowi4 fl;
+
+	if (unlikely(!tun_info))
+		return -EINVAL;
+
+	tun_key = &tun_info->tunnel;
+
+	/* Route lookup to get srouce IP address.
+	 * The process may need to be changed if the corresponding process
+	 * in vports ops changed.
+	 */
+	rt = ovs_tunnel_route_lookup(net, tun_key, skb_mark, &fl, ipproto);
+	if (IS_ERR(rt))
+		return PTR_ERR(rt);
+
+	ip_rt_put(rt);
+
+	/* Generate egress_tun_info based on tun_info,
+	 * saddr, tp_src and tp_dst
+	 */
+	__ovs_flow_tun_info_init(egress_tun_info,
+				 fl.saddr, tun_key->ipv4_dst,
+				 tun_key->ipv4_tos,
+				 tun_key->ipv4_ttl,
+				 tp_src, tp_dst,
+				 tun_key->tun_id,
+				 tun_key->tun_flags,
+				 tun_info->options,
+				 tun_info->options_len);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ovs_tunnel_get_egress_info);
+
+int ovs_vport_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
+				  struct ovs_tunnel_info *info)
+{
+	/* get_egress_tun_info() is only implemented on tunnel ports. */
+	if (unlikely(!vport->ops->get_egress_tun_info))
+		return -EINVAL;
+
+	return vport->ops->get_egress_tun_info(vport, skb, info);
+}
diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h
index 8942125de3a6..bc85331a6c60 100644
--- a/net/openvswitch/vport.h
+++ b/net/openvswitch/vport.h
@@ -45,19 +45,29 @@ void ovs_vport_exit(void);
 struct vport *ovs_vport_add(const struct vport_parms *);
 void ovs_vport_del(struct vport *);
 
-struct vport *ovs_vport_locate(struct net *net, const char *name);
+struct vport *ovs_vport_locate(const struct net *net, const char *name);
 
 void ovs_vport_get_stats(struct vport *, struct ovs_vport_stats *);
 
 int ovs_vport_set_options(struct vport *, struct nlattr *options);
 int ovs_vport_get_options(const struct vport *, struct sk_buff *);
 
-int ovs_vport_set_upcall_portids(struct vport *, struct nlattr *pids);
+int ovs_vport_set_upcall_portids(struct vport *, const struct nlattr *pids);
 int ovs_vport_get_upcall_portids(const struct vport *, struct sk_buff *);
 u32 ovs_vport_find_upcall_portid(const struct vport *, struct sk_buff *);
 
 int ovs_vport_send(struct vport *, struct sk_buff *);
 
+int ovs_tunnel_get_egress_info(struct ovs_tunnel_info *egress_tun_info,
+			       struct net *net,
+			       const struct ovs_tunnel_info *tun_info,
+			       u8 ipproto,
+			       u32 skb_mark,
+			       __be16 tp_src,
+			       __be16 tp_dst);
+int ovs_vport_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
+				  struct ovs_tunnel_info *info);
+
 /* The following definitions are for implementers of vport devices: */
 
 struct vport_err_stats {
@@ -93,6 +103,7 @@ struct vport_portids {
  * @ops: Class structure.
  * @percpu_stats: Points to per-CPU statistics used and maintained by vport
  * @err_stats: Points to error statistics used and maintained by vport
+ * @detach_list: list used for detaching vport in net-exit call.
  */
 struct vport {
 	struct rcu_head rcu;
@@ -107,6 +118,7 @@ struct vport {
 	struct pcpu_sw_netstats __percpu *percpu_stats;
 
 	struct vport_err_stats err_stats;
+	struct list_head detach_list;
 };
 
 /**
@@ -146,6 +158,8 @@ struct vport_parms {
  * @get_name: Get the device's name.
  * @send: Send a packet on the device.  Returns the length of the packet sent,
  * zero for dropped packets or negative for error.
+ * @get_egress_tun_info: Get the egress tunnel 5-tuple and other info for
+ * a packet.
  */
 struct vport_ops {
 	enum ovs_vport_type type;
@@ -161,6 +175,11 @@ struct vport_ops {
 	const char *(*get_name)(const struct vport *);
 
 	int (*send)(struct vport *, struct sk_buff *);
+	int (*get_egress_tun_info)(struct vport *, struct sk_buff *,
+				   struct ovs_tunnel_info *);
+
+	struct module *owner;
+	struct list_head list;
 };
 
 enum vport_err_type {
@@ -207,15 +226,7 @@ static inline struct vport *vport_from_priv(void *priv)
 }
 
 void ovs_vport_receive(struct vport *, struct sk_buff *,
-		       struct ovs_tunnel_info *);
-
-/* List of statically compiled vport implementations.  Don't forget to also
- * add yours to the list at the top of vport.c. */
-extern const struct vport_ops ovs_netdev_vport_ops;
-extern const struct vport_ops ovs_internal_vport_ops;
-extern const struct vport_ops ovs_gre_vport_ops;
-extern const struct vport_ops ovs_vxlan_vport_ops;
-extern const struct vport_ops ovs_geneve_vport_ops;
+		       const struct ovs_tunnel_info *);
 
 static inline void ovs_skb_postpush_rcsum(struct sk_buff *skb,
 				      const void *start, unsigned int len)
@@ -224,4 +235,25 @@ static inline void ovs_skb_postpush_rcsum(struct sk_buff *skb,
 		skb->csum = csum_add(skb->csum, csum_partial(start, len, 0));
 }
 
+int ovs_vport_ops_register(struct vport_ops *ops);
+void ovs_vport_ops_unregister(struct vport_ops *ops);
+
+static inline struct rtable *ovs_tunnel_route_lookup(struct net *net,
+						     const struct ovs_key_ipv4_tunnel *key,
+						     u32 mark,
+						     struct flowi4 *fl,
+						     u8 protocol)
+{
+	struct rtable *rt;
+
+	memset(fl, 0, sizeof(*fl));
+	fl->daddr = key->ipv4_dst;
+	fl->saddr = key->ipv4_src;
+	fl->flowi4_tos = RT_TOS(key->ipv4_tos);
+	fl->flowi4_mark = mark;
+	fl->flowi4_proto = protocol;
+
+	rt = ip_route_output_key(net, fl);
+	return rt;
+}
 #endif /* vport.h */
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 87d20f48ff06..b5989c6ee551 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -216,10 +216,16 @@ static void prb_fill_vlan_info(struct tpacket_kbdq_core *,
 static void packet_flush_mclist(struct sock *sk);
 
 struct packet_skb_cb {
-	unsigned int origlen;
 	union {
 		struct sockaddr_pkt pkt;
-		struct sockaddr_ll ll;
+		union {
+			/* Trick: alias skb original length with
+			 * ll.sll_family and ll.protocol in order
+			 * to save room.
+			 */
+			unsigned int origlen;
+			struct sockaddr_ll ll;
+		};
 	} sa;
 };
 
@@ -378,7 +384,7 @@ static void unregister_prot_hook(struct sock *sk, bool sync)
 		__unregister_prot_hook(sk, sync);
 }
 
-static inline __pure struct page *pgv_to_page(void *addr)
+static inline struct page * __pure pgv_to_page(void *addr)
 {
 	if (is_vmalloc_addr(addr))
 		return vmalloc_to_page(addr);
@@ -698,6 +704,10 @@ static void prb_retire_rx_blk_timer_expired(unsigned long data)
 
 	if (pkc->last_kactive_blk_num == pkc->kactive_blk_num) {
 		if (!frozen) {
+			if (!BLOCK_NUM_PKTS(pbd)) {
+				/* An empty block. Just refresh the timer. */
+				goto refresh_timer;
+			}
 			prb_retire_current_block(pkc, po, TP_STATUS_BLK_TMO);
 			if (!prb_dispatch_next_block(pkc, po))
 				goto refresh_timer;
@@ -785,6 +795,7 @@ static void prb_close_block(struct tpacket_kbdq_core *pkc1,
 
 	struct tpacket3_hdr *last_pkt;
 	struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1;
+	struct sock *sk = &po->sk;
 
 	if (po->stats.stats3.tp_drops)
 		status |= TP_STATUS_LOSING;
@@ -797,7 +808,11 @@ static void prb_close_block(struct tpacket_kbdq_core *pkc1,
 		h1->ts_last_pkt.ts_sec = last_pkt->tp_sec;
 		h1->ts_last_pkt.ts_nsec	= last_pkt->tp_nsec;
 	} else {
-		/* Ok, we tmo'd - so get the current time */
+		/* Ok, we tmo'd - so get the current time.
+		 *
+		 * It shouldn't really happen as we don't close empty
+		 * blocks. See prb_retire_rx_blk_timer_expired().
+		 */
 		struct timespec ts;
 		getnstimeofday(&ts);
 		h1->ts_last_pkt.ts_sec = ts.tv_sec;
@@ -809,6 +824,8 @@ static void prb_close_block(struct tpacket_kbdq_core *pkc1,
 	/* Flush the block */
 	prb_flush_block(pkc1, pbd1, status);
 
+	sk->sk_data_ready(sk);
+
 	pkc1->kactive_blk_num = GET_NEXT_PRB_BLK_NUM(pkc1);
 }
 
@@ -983,8 +1000,8 @@ static void prb_clear_rxhash(struct tpacket_kbdq_core *pkc,
 static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc,
 			struct tpacket3_hdr *ppd)
 {
-	if (vlan_tx_tag_present(pkc->skb)) {
-		ppd->hv1.tp_vlan_tci = vlan_tx_tag_get(pkc->skb);
+	if (skb_vlan_tag_present(pkc->skb)) {
+		ppd->hv1.tp_vlan_tci = skb_vlan_tag_get(pkc->skb);
 		ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->vlan_proto);
 		ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
 	} else {
@@ -1346,14 +1363,14 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
 		return 0;
 	}
 
+	if (fanout_has_flag(f, PACKET_FANOUT_FLAG_DEFRAG)) {
+		skb = ip_check_defrag(skb, IP_DEFRAG_AF_PACKET);
+		if (!skb)
+			return 0;
+	}
 	switch (f->type) {
 	case PACKET_FANOUT_HASH:
 	default:
-		if (fanout_has_flag(f, PACKET_FANOUT_FLAG_DEFRAG)) {
-			skb = ip_check_defrag(skb, IP_DEFRAG_AF_PACKET);
-			if (!skb)
-				return 0;
-		}
 		idx = fanout_demux_hash(f, skb, num);
 		break;
 	case PACKET_FANOUT_LB:
@@ -1597,8 +1614,8 @@ oom:
  *	protocol layers and you must therefore supply it with a complete frame
  */
 
-static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock,
-			       struct msghdr *msg, size_t len)
+static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg,
+			       size_t len)
 {
 	struct sock *sk = sock->sk;
 	DECLARE_SOCKADDR(struct sockaddr_pkt *, saddr, msg->msg_name);
@@ -1676,7 +1693,7 @@ retry:
 			if (len < hhlen)
 				skb_reset_network_header(skb);
 		}
-		err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
+		err = memcpy_from_msg(skb_put(skb, len), msg, len);
 		if (err)
 			goto out_free;
 		goto retry;
@@ -1807,13 +1824,10 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev,
 		skb = nskb;
 	}
 
-	BUILD_BUG_ON(sizeof(*PACKET_SKB_CB(skb)) + MAX_ADDR_LEN - 8 >
-		     sizeof(skb->cb));
+	sock_skb_cb_check_size(sizeof(*PACKET_SKB_CB(skb)) + MAX_ADDR_LEN - 8);
 
 	sll = &PACKET_SKB_CB(skb)->sa.ll;
-	sll->sll_family = AF_PACKET;
 	sll->sll_hatype = dev->type;
-	sll->sll_protocol = skb->protocol;
 	sll->sll_pkttype = skb->pkt_type;
 	if (unlikely(po->origdev))
 		sll->sll_ifindex = orig_dev->ifindex;
@@ -1822,7 +1836,10 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev,
 
 	sll->sll_halen = dev_parse_header(skb, sll->sll_addr);
 
-	PACKET_SKB_CB(skb)->origlen = skb->len;
+	/* sll->sll_family and sll->sll_protocol are set in packet_recvmsg().
+	 * Use their space for storing the original skb length.
+	 */
+	PACKET_SKB_CB(skb)->sa.origlen = skb->len;
 
 	if (pskb_trim(skb, snaplen))
 		goto drop_n_acct;
@@ -1836,7 +1853,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev,
 
 	spin_lock(&sk->sk_receive_queue.lock);
 	po->stats.stats1.tp_packets++;
-	skb->dropcount = atomic_read(&sk->sk_drops);
+	sock_skb_set_dropcount(sk, skb);
 	__skb_queue_tail(&sk->sk_receive_queue, skb);
 	spin_unlock(&sk->sk_receive_queue.lock);
 	sk->sk_data_ready(sk);
@@ -1899,14 +1916,19 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		}
 	}
 
-	if (skb->ip_summed == CHECKSUM_PARTIAL)
-		status |= TP_STATUS_CSUMNOTREADY;
-
 	snaplen = skb->len;
 
 	res = run_filter(skb, sk, snaplen);
 	if (!res)
 		goto drop_n_restore;
+
+	if (skb->ip_summed == CHECKSUM_PARTIAL)
+		status |= TP_STATUS_CSUMNOTREADY;
+	else if (skb->pkt_type != PACKET_OUTGOING &&
+		 (skb->ip_summed == CHECKSUM_COMPLETE ||
+		  skb_csum_unnecessary(skb)))
+		status |= TP_STATUS_CSUM_VALID;
+
 	if (snaplen > res)
 		snaplen = res;
 
@@ -1997,8 +2019,8 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		h.h2->tp_net = netoff;
 		h.h2->tp_sec = ts.tv_sec;
 		h.h2->tp_nsec = ts.tv_nsec;
-		if (vlan_tx_tag_present(skb)) {
-			h.h2->tp_vlan_tci = vlan_tx_tag_get(skb);
+		if (skb_vlan_tag_present(skb)) {
+			h.h2->tp_vlan_tci = skb_vlan_tag_get(skb);
 			h.h2->tp_vlan_tpid = ntohs(skb->vlan_proto);
 			status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
 		} else {
@@ -2052,12 +2074,12 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	smp_wmb();
 #endif
 
-	if (po->tp_version <= TPACKET_V2)
+	if (po->tp_version <= TPACKET_V2) {
 		__packet_set_status(po, h.raw, status);
-	else
+		sk->sk_data_ready(sk);
+	} else {
 		prb_clear_blk_fill_status(&po->rx_ring);
-
-	sk->sk_data_ready(sk);
+	}
 
 drop_n_restore:
 	if (skb_head != skb->data && skb_shared(skb)) {
@@ -2095,6 +2117,18 @@ static void tpacket_destruct_skb(struct sk_buff *skb)
 	sock_wfree(skb);
 }
 
+static bool ll_header_truncated(const struct net_device *dev, int len)
+{
+	/* net device doesn't like empty head */
+	if (unlikely(len <= dev->hard_header_len)) {
+		net_warn_ratelimited("%s: packet size is too short (%d <= %d)\n",
+				     current->comm, len, dev->hard_header_len);
+		return true;
+	}
+
+	return false;
+}
+
 static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 		void *frame, struct net_device *dev, int size_max,
 		__be16 proto, unsigned char *addr, int hlen)
@@ -2170,12 +2204,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 		if (unlikely(err < 0))
 			return -EINVAL;
 	} else if (dev->hard_header_len) {
-		/* net device doesn't like empty head */
-		if (unlikely(tp_len <= dev->hard_header_len)) {
-			pr_err("packet size is too short (%d < %d)\n",
-			       tp_len, dev->hard_header_len);
+		if (ll_header_truncated(dev, tp_len))
 			return -EINVAL;
-		}
 
 		skb_push(skb, dev->hard_header_len);
 		err = skb_store_bits(skb, 0, data,
@@ -2281,11 +2311,14 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 		tlen = dev->needed_tailroom;
 		skb = sock_alloc_send_skb(&po->sk,
 				hlen + tlen + sizeof(struct sockaddr_ll),
-				0, &err);
+				!need_wait, &err);
 
-		if (unlikely(skb == NULL))
+		if (unlikely(skb == NULL)) {
+			/* we assume the socket was initially writeable ... */
+			if (likely(len_sum > 0))
+				err = len_sum;
 			goto out_status;
-
+		}
 		tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto,
 					  addr, hlen);
 		if (tp_len > dev->mtu + dev->hard_header_len) {
@@ -2400,6 +2433,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	unsigned short gso_type = 0;
 	int hlen, tlen;
 	int extra_len = 0;
+	ssize_t n;
 
 	/*
 	 *	Get and verify the address.
@@ -2438,19 +2472,21 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 
 		len -= vnet_hdr_len;
 
-		err = memcpy_fromiovec((void *)&vnet_hdr, msg->msg_iov,
-				       vnet_hdr_len);
-		if (err < 0)
+		err = -EFAULT;
+		n = copy_from_iter(&vnet_hdr, vnet_hdr_len, &msg->msg_iter);
+		if (n != vnet_hdr_len)
 			goto out_unlock;
 
 		if ((vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) &&
-		    (vnet_hdr.csum_start + vnet_hdr.csum_offset + 2 >
-		      vnet_hdr.hdr_len))
-			vnet_hdr.hdr_len = vnet_hdr.csum_start +
-						 vnet_hdr.csum_offset + 2;
+		    (__virtio16_to_cpu(false, vnet_hdr.csum_start) +
+		     __virtio16_to_cpu(false, vnet_hdr.csum_offset) + 2 >
+		      __virtio16_to_cpu(false, vnet_hdr.hdr_len)))
+			vnet_hdr.hdr_len = __cpu_to_virtio16(false,
+				 __virtio16_to_cpu(false, vnet_hdr.csum_start) +
+				__virtio16_to_cpu(false, vnet_hdr.csum_offset) + 2);
 
 		err = -EINVAL;
-		if (vnet_hdr.hdr_len > len)
+		if (__virtio16_to_cpu(false, vnet_hdr.hdr_len) > len)
 			goto out_unlock;
 
 		if (vnet_hdr.gso_type != VIRTIO_NET_HDR_GSO_NONE) {
@@ -2492,7 +2528,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	err = -ENOBUFS;
 	hlen = LL_RESERVED_SPACE(dev);
 	tlen = dev->needed_tailroom;
-	skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, vnet_hdr.hdr_len,
+	skb = packet_alloc_skb(sk, hlen + tlen, hlen, len,
+			       __virtio16_to_cpu(false, vnet_hdr.hdr_len),
 			       msg->msg_flags & MSG_DONTWAIT, &err);
 	if (skb == NULL)
 		goto out_unlock;
@@ -2500,12 +2537,17 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	skb_set_network_header(skb, reserve);
 
 	err = -EINVAL;
-	if (sock->type == SOCK_DGRAM &&
-	    (offset = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, len)) < 0)
-		goto out_free;
+	if (sock->type == SOCK_DGRAM) {
+		offset = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, len);
+		if (unlikely(offset < 0))
+			goto out_free;
+	} else {
+		if (ll_header_truncated(dev, len))
+			goto out_free;
+	}
 
 	/* Returns -EFAULT on error */
-	err = skb_copy_datagram_from_iovec(skb, offset, msg->msg_iov, 0, len);
+	err = skb_copy_datagram_from_iter(skb, offset, &msg->msg_iter, len);
 	if (err)
 		goto out_free;
 
@@ -2534,14 +2576,16 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 
 	if (po->has_vnet_hdr) {
 		if (vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
-			if (!skb_partial_csum_set(skb, vnet_hdr.csum_start,
-						  vnet_hdr.csum_offset)) {
+			u16 s = __virtio16_to_cpu(false, vnet_hdr.csum_start);
+			u16 o = __virtio16_to_cpu(false, vnet_hdr.csum_offset);
+			if (!skb_partial_csum_set(skb, s, o)) {
 				err = -EINVAL;
 				goto out_free;
 			}
 		}
 
-		skb_shinfo(skb)->gso_size = vnet_hdr.gso_size;
+		skb_shinfo(skb)->gso_size =
+			__virtio16_to_cpu(false, vnet_hdr.gso_size);
 		skb_shinfo(skb)->gso_type = gso_type;
 
 		/* Header must be checked, and gso_segs computed. */
@@ -2573,8 +2617,7 @@ out:
 	return err;
 }
 
-static int packet_sendmsg(struct kiocb *iocb, struct socket *sock,
-		struct msghdr *msg, size_t len)
+static int packet_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 {
 	struct sock *sk = sock->sk;
 	struct packet_sock *po = pkt_sk(sk);
@@ -2854,13 +2897,14 @@ out:
  *	If necessary we block.
  */
 
-static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
-			  struct msghdr *msg, size_t len, int flags)
+static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+			  int flags)
 {
 	struct sock *sk = sock->sk;
 	struct sk_buff *skb;
 	int copied, err;
 	int vnet_hdr_len = 0;
+	unsigned int origlen = 0;
 
 	err = -EINVAL;
 	if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT|MSG_ERRQUEUE))
@@ -2912,8 +2956,10 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
 			struct skb_shared_info *sinfo = skb_shinfo(skb);
 
 			/* This is a hint as to how much should be linear. */
-			vnet_hdr.hdr_len = skb_headlen(skb);
-			vnet_hdr.gso_size = sinfo->gso_size;
+			vnet_hdr.hdr_len =
+				__cpu_to_virtio16(false, skb_headlen(skb));
+			vnet_hdr.gso_size =
+				__cpu_to_virtio16(false, sinfo->gso_size);
 			if (sinfo->gso_type & SKB_GSO_TCPV4)
 				vnet_hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
 			else if (sinfo->gso_type & SKB_GSO_TCPV6)
@@ -2931,14 +2977,15 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 		if (skb->ip_summed == CHECKSUM_PARTIAL) {
 			vnet_hdr.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
-			vnet_hdr.csum_start = skb_checksum_start_offset(skb);
-			vnet_hdr.csum_offset = skb->csum_offset;
+			vnet_hdr.csum_start = __cpu_to_virtio16(false,
+					  skb_checksum_start_offset(skb));
+			vnet_hdr.csum_offset = __cpu_to_virtio16(false,
+							 skb->csum_offset);
 		} else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
 			vnet_hdr.flags = VIRTIO_NET_HDR_F_DATA_VALID;
 		} /* else everything is zero */
 
-		err = memcpy_toiovec(msg->msg_iov, (void *)&vnet_hdr,
-				     vnet_hdr_len);
+		err = memcpy_to_msg(msg, (void *)&vnet_hdr, vnet_hdr_len);
 		if (err < 0)
 			goto out_free;
 	}
@@ -2953,10 +3000,19 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
 		msg->msg_flags |= MSG_TRUNC;
 	}
 
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (err)
 		goto out_free;
 
+	if (sock->type != SOCK_PACKET) {
+		struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll;
+
+		/* Original length was stored in sockaddr_ll fields */
+		origlen = PACKET_SKB_CB(skb)->sa.origlen;
+		sll->sll_family = AF_PACKET;
+		sll->sll_protocol = skb->protocol;
+	}
+
 	sock_recv_ts_and_drops(msg, sk, skb);
 
 	if (msg->msg_name) {
@@ -2968,6 +3024,7 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
 			msg->msg_namelen = sizeof(struct sockaddr_pkt);
 		} else {
 			struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll;
+
 			msg->msg_namelen = sll->sll_halen +
 				offsetof(struct sockaddr_ll, sll_addr);
 		}
@@ -2981,12 +3038,17 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
 		aux.tp_status = TP_STATUS_USER;
 		if (skb->ip_summed == CHECKSUM_PARTIAL)
 			aux.tp_status |= TP_STATUS_CSUMNOTREADY;
-		aux.tp_len = PACKET_SKB_CB(skb)->origlen;
+		else if (skb->pkt_type != PACKET_OUTGOING &&
+			 (skb->ip_summed == CHECKSUM_COMPLETE ||
+			  skb_csum_unnecessary(skb)))
+			aux.tp_status |= TP_STATUS_CSUM_VALID;
+
+		aux.tp_len = origlen;
 		aux.tp_snaplen = skb->len;
 		aux.tp_mac = 0;
 		aux.tp_net = skb_network_offset(skb);
-		if (vlan_tx_tag_present(skb)) {
-			aux.tp_vlan_tci = vlan_tx_tag_get(skb);
+		if (skb_vlan_tag_present(skb)) {
+			aux.tp_vlan_tci = skb_vlan_tag_get(skb);
 			aux.tp_vlan_tpid = ntohs(skb->vlan_proto);
 			aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
 		} else {
@@ -3090,11 +3152,18 @@ static int packet_dev_mc(struct net_device *dev, struct packet_mclist *i,
 	return 0;
 }
 
-static void packet_dev_mclist(struct net_device *dev, struct packet_mclist *i, int what)
+static void packet_dev_mclist_delete(struct net_device *dev,
+				     struct packet_mclist **mlp)
 {
-	for ( ; i; i = i->next) {
-		if (i->ifindex == dev->ifindex)
-			packet_dev_mc(dev, i, what);
+	struct packet_mclist *ml;
+
+	while ((ml = *mlp) != NULL) {
+		if (ml->ifindex == dev->ifindex) {
+			packet_dev_mc(dev, ml, -1);
+			*mlp = ml->next;
+			kfree(ml);
+		} else
+			mlp = &ml->next;
 	}
 }
 
@@ -3171,12 +3240,11 @@ static int packet_mc_drop(struct sock *sk, struct packet_mreq_max *mreq)
 					packet_dev_mc(dev, ml, -1);
 				kfree(ml);
 			}
-			rtnl_unlock();
-			return 0;
+			break;
 		}
 	}
 	rtnl_unlock();
-	return -EADDRNOTAVAIL;
+	return 0;
 }
 
 static void packet_flush_mclist(struct sock *sk)
@@ -3526,7 +3594,7 @@ static int packet_notifier(struct notifier_block *this,
 		switch (msg) {
 		case NETDEV_UNREGISTER:
 			if (po->mclist)
-				packet_dev_mclist(dev, po->mclist, -1);
+				packet_dev_mclist_delete(dev, &po->mclist);
 			/* fallthrough */
 
 		case NETDEV_DOWN:
diff --git a/net/packet/diag.c b/net/packet/diag.c
index 92f2c7107eec..0ed68f0238bf 100644
--- a/net/packet/diag.c
+++ b/net/packet/diag.c
@@ -177,7 +177,8 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
 				     PACKET_DIAG_FILTER))
 		goto out_nlmsg_trim;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 out_nlmsg_trim:
 	nlmsg_cancel(skb, nlh);
diff --git a/net/packet/internal.h b/net/packet/internal.h
index cdddf6a30399..fe6e20caea1d 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -74,9 +74,7 @@ extern struct mutex fanout_mutex;
 #define PACKET_FANOUT_MAX	256
 
 struct packet_fanout {
-#ifdef CONFIG_NET_NS
-	struct net		*net;
-#endif
+	possible_net_t		net;
 	unsigned int		num_members;
 	u16			id;
 	u8			type;
diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c
index 5a940dbd74a3..32ab87d34828 100644
--- a/net/phonet/af_phonet.c
+++ b/net/phonet/af_phonet.c
@@ -426,16 +426,17 @@ static int phonet_rcv(struct sk_buff *skb, struct net_device *dev,
 
 		out_dev = phonet_route_output(net, pn_sockaddr_get_addr(&sa));
 		if (!out_dev) {
-			LIMIT_NETDEBUG(KERN_WARNING"No Phonet route to %02X\n",
-					pn_sockaddr_get_addr(&sa));
+			net_dbg_ratelimited("No Phonet route to %02X\n",
+					    pn_sockaddr_get_addr(&sa));
 			goto out;
 		}
 
 		__skb_push(skb, sizeof(struct phonethdr));
 		skb->dev = out_dev;
 		if (out_dev == dev) {
-			LIMIT_NETDEBUG(KERN_ERR"Phonet loop to %02X on %s\n",
-					pn_sockaddr_get_addr(&sa), dev->name);
+			net_dbg_ratelimited("Phonet loop to %02X on %s\n",
+					    pn_sockaddr_get_addr(&sa),
+					    dev->name);
 			goto out_dev;
 		}
 		/* Some drivers (e.g. TUN) do not allocate HW header space */
diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c
index 290352c0e6b4..5e710435ffa9 100644
--- a/net/phonet/datagram.c
+++ b/net/phonet/datagram.c
@@ -83,8 +83,7 @@ static int pn_init(struct sock *sk)
 	return 0;
 }
 
-static int pn_sendmsg(struct kiocb *iocb, struct sock *sk,
-			struct msghdr *msg, size_t len)
+static int pn_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 {
 	DECLARE_SOCKADDR(struct sockaddr_pn *, target, msg->msg_name);
 	struct sk_buff *skb;
@@ -109,7 +108,7 @@ static int pn_sendmsg(struct kiocb *iocb, struct sock *sk,
 		return err;
 	skb_reserve(skb, MAX_PHONET_HEADER);
 
-	err = memcpy_fromiovec((void *)skb_put(skb, len), msg->msg_iov, len);
+	err = memcpy_from_msg((void *)skb_put(skb, len), msg, len);
 	if (err < 0) {
 		kfree_skb(skb);
 		return err;
@@ -125,9 +124,8 @@ static int pn_sendmsg(struct kiocb *iocb, struct sock *sk,
 	return (err >= 0) ? len : err;
 }
 
-static int pn_recvmsg(struct kiocb *iocb, struct sock *sk,
-			struct msghdr *msg, size_t len, int noblock,
-			int flags, int *addr_len)
+static int pn_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+		      int noblock, int flags, int *addr_len)
 {
 	struct sk_buff *skb = NULL;
 	struct sockaddr_pn sa;
@@ -150,7 +148,7 @@ static int pn_recvmsg(struct kiocb *iocb, struct sock *sk,
 		copylen = len;
 	}
 
-	rval = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copylen);
+	rval = skb_copy_datagram_msg(skb, 0, msg, copylen);
 	if (rval) {
 		rval = -EFAULT;
 		goto out;
diff --git a/net/phonet/pep-gprs.c b/net/phonet/pep-gprs.c
index e9a83a637185..fa8237fdc57b 100644
--- a/net/phonet/pep-gprs.c
+++ b/net/phonet/pep-gprs.c
@@ -203,8 +203,7 @@ static netdev_tx_t gprs_xmit(struct sk_buff *skb, struct net_device *dev)
 	len = skb->len;
 	err = pep_write(sk, skb);
 	if (err) {
-		LIMIT_NETDEBUG(KERN_WARNING"%s: TX error (%d)\n",
-				dev->name, err);
+		net_dbg_ratelimited("%s: TX error (%d)\n", dev->name, err);
 		dev->stats.tx_aborted_errors++;
 		dev->stats.tx_errors++;
 	} else {
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index 70a547ea5177..6de2aeb98a1f 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -272,8 +272,8 @@ static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb)
 
 	hdr = pnp_hdr(skb);
 	if (hdr->data[0] != PN_PEP_TYPE_COMMON) {
-		LIMIT_NETDEBUG(KERN_DEBUG"Phonet unknown PEP type: %u\n",
-				(unsigned int)hdr->data[0]);
+		net_dbg_ratelimited("Phonet unknown PEP type: %u\n",
+				    (unsigned int)hdr->data[0]);
 		return -EOPNOTSUPP;
 	}
 
@@ -304,8 +304,8 @@ static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb)
 		break;
 
 	default:
-		LIMIT_NETDEBUG(KERN_DEBUG"Phonet unknown PEP indication: %u\n",
-				(unsigned int)hdr->data[1]);
+		net_dbg_ratelimited("Phonet unknown PEP indication: %u\n",
+				    (unsigned int)hdr->data[1]);
 		return -EOPNOTSUPP;
 	}
 	if (wake)
@@ -451,8 +451,8 @@ static int pipe_do_rcv(struct sock *sk, struct sk_buff *skb)
 		break;
 
 	default:
-		LIMIT_NETDEBUG(KERN_DEBUG"Phonet unknown PEP message: %u\n",
-				hdr->message_id);
+		net_dbg_ratelimited("Phonet unknown PEP message: %u\n",
+				    hdr->message_id);
 		err = -EINVAL;
 	}
 out:
@@ -1118,8 +1118,7 @@ static int pipe_skb_send(struct sock *sk, struct sk_buff *skb)
 
 }
 
-static int pep_sendmsg(struct kiocb *iocb, struct sock *sk,
-			struct msghdr *msg, size_t len)
+static int pep_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 {
 	struct pep_sock *pn = pep_sk(sk);
 	struct sk_buff *skb;
@@ -1141,7 +1140,7 @@ static int pep_sendmsg(struct kiocb *iocb, struct sock *sk,
 		return err;
 
 	skb_reserve(skb, MAX_PHONET_HEADER + 3 + pn->aligned);
-	err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
+	err = memcpy_from_msg(skb_put(skb, len), msg, len);
 	if (err < 0)
 		goto outfree;
 
@@ -1246,9 +1245,8 @@ struct sk_buff *pep_read(struct sock *sk)
 	return skb;
 }
 
-static int pep_recvmsg(struct kiocb *iocb, struct sock *sk,
-			struct msghdr *msg, size_t len, int noblock,
-			int flags, int *addr_len)
+static int pep_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+		       int noblock, int flags, int *addr_len)
 {
 	struct sk_buff *skb;
 	int err;
@@ -1296,7 +1294,7 @@ copy:
 	else
 		len = skb->len;
 
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, len);
+	err = skb_copy_datagram_msg(skb, 0, msg, len);
 	if (!err)
 		err = (flags & MSG_TRUNC) ? skb->len : len;
 
diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c
index b64151ade6b3..bc5ee5fbe6ae 100644
--- a/net/phonet/pn_netlink.c
+++ b/net/phonet/pn_netlink.c
@@ -121,7 +121,8 @@ static int fill_addr(struct sk_buff *skb, struct net_device *dev, u8 addr,
 	ifm->ifa_index = dev->ifindex;
 	if (nla_put_u8(skb, IFA_LOCAL, addr))
 		goto nla_put_failure;
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
@@ -190,7 +191,8 @@ static int fill_route(struct sk_buff *skb, struct net_device *dev, u8 dst,
 	if (nla_put_u8(skb, RTA_DST, dst) ||
 	    nla_put_u32(skb, RTA_OIF, dev->ifindex))
 		goto nla_put_failure;
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
@@ -270,27 +272,23 @@ static int route_doit(struct sk_buff *skb, struct nlmsghdr *nlh)
 static int route_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct net *net = sock_net(skb->sk);
-	u8 addr, addr_idx = 0, addr_start_idx = cb->args[0];
+	u8 addr;
 
 	rcu_read_lock();
-	for (addr = 0; addr < 64; addr++) {
-		struct net_device *dev;
+	for (addr = cb->args[0]; addr < 64; addr++) {
+		struct net_device *dev = phonet_route_get_rcu(net, addr << 2);
 
-		dev = phonet_route_get_rcu(net, addr << 2);
 		if (!dev)
 			continue;
 
-		if (addr_idx++ < addr_start_idx)
-			continue;
 		if (fill_route(skb, dev, addr << 2, NETLINK_CB(cb->skb).portid,
-				cb->nlh->nlmsg_seq, RTM_NEWROUTE))
+			       cb->nlh->nlmsg_seq, RTM_NEWROUTE) < 0)
 			goto out;
 	}
 
 out:
 	rcu_read_unlock();
-	cb->args[0] = addr_idx;
-	cb->args[1] = 0;
+	cb->args[0] = addr;
 
 	return skb->len;
 }
diff --git a/net/phonet/socket.c b/net/phonet/socket.c
index 008214a3d5eb..d575ef4e9aa6 100644
--- a/net/phonet/socket.c
+++ b/net/phonet/socket.c
@@ -425,15 +425,15 @@ out:
 	return err;
 }
 
-static int pn_socket_sendmsg(struct kiocb *iocb, struct socket *sock,
-				struct msghdr *m, size_t total_len)
+static int pn_socket_sendmsg(struct socket *sock, struct msghdr *m,
+			     size_t total_len)
 {
 	struct sock *sk = sock->sk;
 
 	if (pn_socket_autobind(sock))
 		return -EAGAIN;
 
-	return sk->sk_prot->sendmsg(iocb, sk, m, total_len);
+	return sk->sk_prot->sendmsg(sk, m, total_len);
 }
 
 const struct proto_ops phonet_dgram_ops = {
diff --git a/net/rds/cong.c b/net/rds/cong.c
index e5b65acd650b..e6144b8246fd 100644
--- a/net/rds/cong.c
+++ b/net/rds/cong.c
@@ -221,7 +221,21 @@ void rds_cong_queue_updates(struct rds_cong_map *map)
 	list_for_each_entry(conn, &map->m_conn_list, c_map_item) {
 		if (!test_and_set_bit(0, &conn->c_map_queued)) {
 			rds_stats_inc(s_cong_update_queued);
-			rds_send_xmit(conn);
+			/* We cannot inline the call to rds_send_xmit() here
+			 * for two reasons (both pertaining to a TCP transport):
+			 * 1. When we get here from the receive path, we
+			 *    are already holding the sock_lock (held by
+			 *    tcp_v4_rcv()). So inlining calls to
+			 *    tcp_setsockopt and/or tcp_sendmsg will deadlock
+			 *    when it tries to get the sock_lock())
+			 * 2. Interrupts are masked so that we can mark the
+			 *    the port congested from both send and recv paths.
+			 *    (See comment around declaration of rdc_cong_lock).
+			 *    An attempt to get the sock_lock() here will
+			 *    therefore trigger warnings.
+			 * Defer the xmit to rds_send_worker() instead.
+			 */
+			queue_delayed_work(rds_wq, &conn->c_send_w, 0);
 		}
 	}
 
diff --git a/net/rds/connection.c b/net/rds/connection.c
index 378c3a6acf84..da6da57e5f36 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -126,11 +126,14 @@ static struct rds_connection *__rds_conn_create(__be32 laddr, __be32 faddr,
 	struct rds_transport *loop_trans;
 	unsigned long flags;
 	int ret;
+	struct rds_transport *otrans = trans;
 
+	if (!is_outgoing && otrans->t_type == RDS_TRANS_TCP)
+		goto new_conn;
 	rcu_read_lock();
 	conn = rds_conn_lookup(head, laddr, faddr, trans);
 	if (conn && conn->c_loopback && conn->c_trans != &rds_loop_transport &&
-	    !is_outgoing) {
+	    laddr == faddr && !is_outgoing) {
 		/* This is a looped back IB connection, and we're
 		 * called by the code handling the incoming connect.
 		 * We need a second connection object into which we
@@ -142,6 +145,7 @@ static struct rds_connection *__rds_conn_create(__be32 laddr, __be32 faddr,
 	if (conn)
 		goto out;
 
+new_conn:
 	conn = kmem_cache_zalloc(rds_conn_slab, gfp);
 	if (!conn) {
 		conn = ERR_PTR(-ENOMEM);
@@ -193,6 +197,7 @@ static struct rds_connection *__rds_conn_create(__be32 laddr, __be32 faddr,
 	}
 
 	atomic_set(&conn->c_state, RDS_CONN_DOWN);
+	conn->c_send_gen = 0;
 	conn->c_reconnect_jiffies = 0;
 	INIT_DELAYED_WORK(&conn->c_send_w, rds_send_worker);
 	INIT_DELAYED_WORK(&conn->c_recv_w, rds_recv_worker);
@@ -229,13 +234,22 @@ static struct rds_connection *__rds_conn_create(__be32 laddr, __be32 faddr,
 		/* Creating normal conn */
 		struct rds_connection *found;
 
-		found = rds_conn_lookup(head, laddr, faddr, trans);
+		if (!is_outgoing && otrans->t_type == RDS_TRANS_TCP)
+			found = NULL;
+		else
+			found = rds_conn_lookup(head, laddr, faddr, trans);
 		if (found) {
 			trans->conn_free(conn->c_transport_data);
 			kmem_cache_free(rds_conn_slab, conn);
 			conn = found;
 		} else {
-			hlist_add_head_rcu(&conn->c_hash_node, head);
+			if ((is_outgoing && otrans->t_type == RDS_TRANS_TCP) ||
+			    (otrans->t_type != RDS_TRANS_TCP)) {
+				/* Only the active side should be added to
+				 * reconnect list for TCP.
+				 */
+				hlist_add_head_rcu(&conn->c_hash_node, head);
+			}
 			rds_cong_add_conn(conn);
 			rds_conn_count++;
 		}
diff --git a/net/rds/ib.h b/net/rds/ib.h
index 7280ab8810c2..c36d713229e0 100644
--- a/net/rds/ib.h
+++ b/net/rds/ib.h
@@ -316,8 +316,7 @@ int rds_ib_recv_alloc_caches(struct rds_ib_connection *ic);
 void rds_ib_recv_free_caches(struct rds_ib_connection *ic);
 void rds_ib_recv_refill(struct rds_connection *conn, int prefill);
 void rds_ib_inc_free(struct rds_incoming *inc);
-int rds_ib_inc_copy_to_user(struct rds_incoming *inc, struct iovec *iov,
-			     size_t size);
+int rds_ib_inc_copy_to_user(struct rds_incoming *inc, struct iov_iter *to);
 void rds_ib_recv_cq_comp_handler(struct ib_cq *cq, void *context);
 void rds_ib_recv_tasklet_fn(unsigned long data);
 void rds_ib_recv_init_ring(struct rds_ib_connection *ic);
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index 31b74f5e61ad..8a09ee7db3c1 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -183,8 +183,17 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even
 
 	/* If the peer gave us the last packet it saw, process this as if
 	 * we had received a regular ACK. */
-	if (dp && dp->dp_ack_seq)
-		rds_send_drop_acked(conn, be64_to_cpu(dp->dp_ack_seq), NULL);
+	if (dp) {
+		/* dp structure start is not guaranteed to be 8 bytes aligned.
+		 * Since dp_ack_seq is 64-bit extended load operations can be
+		 * used so go through get_unaligned to avoid unaligned errors.
+		 */
+		__be64 dp_ack_seq = get_unaligned(&dp->dp_ack_seq);
+
+		if (dp_ack_seq)
+			rds_send_drop_acked(conn, be64_to_cpu(dp_ack_seq),
+					    NULL);
+	}
 
 	rds_connect_complete(conn);
 }
diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c
index d67de453c35a..1b981a4e42c2 100644
--- a/net/rds/ib_recv.c
+++ b/net/rds/ib_recv.c
@@ -472,15 +472,12 @@ static struct list_head *rds_ib_recv_cache_get(struct rds_ib_refill_cache *cache
 	return head;
 }
 
-int rds_ib_inc_copy_to_user(struct rds_incoming *inc, struct iovec *first_iov,
-			    size_t size)
+int rds_ib_inc_copy_to_user(struct rds_incoming *inc, struct iov_iter *to)
 {
 	struct rds_ib_incoming *ibinc;
 	struct rds_page_frag *frag;
-	struct iovec *iov = first_iov;
 	unsigned long to_copy;
 	unsigned long frag_off = 0;
-	unsigned long iov_off = 0;
 	int copied = 0;
 	int ret;
 	u32 len;
@@ -489,37 +486,25 @@ int rds_ib_inc_copy_to_user(struct rds_incoming *inc, struct iovec *first_iov,
 	frag = list_entry(ibinc->ii_frags.next, struct rds_page_frag, f_item);
 	len = be32_to_cpu(inc->i_hdr.h_len);
 
-	while (copied < size && copied < len) {
+	while (iov_iter_count(to) && copied < len) {
 		if (frag_off == RDS_FRAG_SIZE) {
 			frag = list_entry(frag->f_item.next,
 					  struct rds_page_frag, f_item);
 			frag_off = 0;
 		}
-		while (iov_off == iov->iov_len) {
-			iov_off = 0;
-			iov++;
-		}
-
-		to_copy = min(iov->iov_len - iov_off, RDS_FRAG_SIZE - frag_off);
-		to_copy = min_t(size_t, to_copy, size - copied);
+		to_copy = min_t(unsigned long, iov_iter_count(to),
+				RDS_FRAG_SIZE - frag_off);
 		to_copy = min_t(unsigned long, to_copy, len - copied);
 
-		rdsdebug("%lu bytes to user [%p, %zu] + %lu from frag "
-			 "[%p, %u] + %lu\n",
-			 to_copy, iov->iov_base, iov->iov_len, iov_off,
-			 sg_page(&frag->f_sg), frag->f_sg.offset, frag_off);
-
 		/* XXX needs + offset for multiple recvs per page */
-		ret = rds_page_copy_to_user(sg_page(&frag->f_sg),
-					    frag->f_sg.offset + frag_off,
-					    iov->iov_base + iov_off,
-					    to_copy);
-		if (ret) {
-			copied = ret;
-			break;
-		}
+		rds_stats_add(s_copy_to_user, to_copy);
+		ret = copy_page_to_iter(sg_page(&frag->f_sg),
+					frag->f_sg.offset + frag_off,
+					to_copy,
+					to);
+		if (ret != to_copy)
+			return -EFAULT;
 
-		iov_off += to_copy;
 		frag_off += to_copy;
 		copied += to_copy;
 	}
diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c
index 1dde91e3dc70..bd3825d38abc 100644
--- a/net/rds/ib_send.c
+++ b/net/rds/ib_send.c
@@ -409,7 +409,7 @@ try_again:
 	posted = IB_GET_POST_CREDITS(oldval);
 	avail = IB_GET_SEND_CREDITS(oldval);
 
-	rdsdebug("rds_ib_send_grab_credits(%u): credits=%u posted=%u\n",
+	rdsdebug("wanted=%u credits=%u posted=%u\n",
 			wanted, avail, posted);
 
 	/* The last credit must be used to send a credit update. */
@@ -453,7 +453,7 @@ void rds_ib_send_add_credits(struct rds_connection *conn, unsigned int credits)
 	if (credits == 0)
 		return;
 
-	rdsdebug("rds_ib_send_add_credits(%u): current=%u%s\n",
+	rdsdebug("credits=%u current=%u%s\n",
 			credits,
 			IB_GET_SEND_CREDITS(atomic_read(&ic->i_credits)),
 			test_bit(RDS_LL_SEND_FULL, &conn->c_flags) ? ", ll_send_full" : "");
diff --git a/net/rds/iw.h b/net/rds/iw.h
index 04ce3b193f79..cbe6674e31ee 100644
--- a/net/rds/iw.h
+++ b/net/rds/iw.h
@@ -325,8 +325,7 @@ int rds_iw_recv(struct rds_connection *conn);
 int rds_iw_recv_refill(struct rds_connection *conn, gfp_t kptr_gfp,
 		       gfp_t page_gfp, int prefill);
 void rds_iw_inc_free(struct rds_incoming *inc);
-int rds_iw_inc_copy_to_user(struct rds_incoming *inc, struct iovec *iov,
-			     size_t size);
+int rds_iw_inc_copy_to_user(struct rds_incoming *inc, struct iov_iter *to);
 void rds_iw_recv_cq_comp_handler(struct ib_cq *cq, void *context);
 void rds_iw_recv_tasklet_fn(unsigned long data);
 void rds_iw_recv_init_ring(struct rds_iw_connection *ic);
diff --git a/net/rds/iw_cm.c b/net/rds/iw_cm.c
index a91e1db62ee6..a6c2bea9f8f9 100644
--- a/net/rds/iw_cm.c
+++ b/net/rds/iw_cm.c
@@ -590,8 +590,8 @@ void rds_iw_conn_shutdown(struct rds_connection *conn)
 			/* Actually this may happen quite frequently, when
 			 * an outgoing connect raced with an incoming connect.
 			 */
-			rdsdebug("rds_iw_conn_shutdown: failed to disconnect,"
-				   " cm: %p err %d\n", ic->i_cm_id, err);
+			rdsdebug("failed to disconnect, cm: %p err %d\n",
+				 ic->i_cm_id, err);
 		}
 
 		if (ic->i_cm_id->qp) {
diff --git a/net/rds/iw_rdma.c b/net/rds/iw_rdma.c
index a817705ce2d0..dba8d0864f18 100644
--- a/net/rds/iw_rdma.c
+++ b/net/rds/iw_rdma.c
@@ -88,7 +88,9 @@ static unsigned int rds_iw_unmap_fastreg_list(struct rds_iw_mr_pool *pool,
 			int *unpinned);
 static void rds_iw_destroy_fastreg(struct rds_iw_mr_pool *pool, struct rds_iw_mr *ibmr);
 
-static int rds_iw_get_device(struct rds_sock *rs, struct rds_iw_device **rds_iwdev, struct rdma_cm_id **cm_id)
+static int rds_iw_get_device(struct sockaddr_in *src, struct sockaddr_in *dst,
+			     struct rds_iw_device **rds_iwdev,
+			     struct rdma_cm_id **cm_id)
 {
 	struct rds_iw_device *iwdev;
 	struct rds_iw_cm_id *i_cm_id;
@@ -112,15 +114,15 @@ static int rds_iw_get_device(struct rds_sock *rs, struct rds_iw_device **rds_iwd
 				src_addr->sin_port,
 				dst_addr->sin_addr.s_addr,
 				dst_addr->sin_port,
-				rs->rs_bound_addr,
-				rs->rs_bound_port,
-				rs->rs_conn_addr,
-				rs->rs_conn_port);
+				src->sin_addr.s_addr,
+				src->sin_port,
+				dst->sin_addr.s_addr,
+				dst->sin_port);
 #ifdef WORKING_TUPLE_DETECTION
-			if (src_addr->sin_addr.s_addr == rs->rs_bound_addr &&
-			    src_addr->sin_port == rs->rs_bound_port &&
-			    dst_addr->sin_addr.s_addr == rs->rs_conn_addr &&
-			    dst_addr->sin_port == rs->rs_conn_port) {
+			if (src_addr->sin_addr.s_addr == src->sin_addr.s_addr &&
+			    src_addr->sin_port == src->sin_port &&
+			    dst_addr->sin_addr.s_addr == dst->sin_addr.s_addr &&
+			    dst_addr->sin_port == dst->sin_port) {
 #else
 			/* FIXME - needs to compare the local and remote
 			 * ipaddr/port tuple, but the ipaddr is the only
@@ -128,7 +130,7 @@ static int rds_iw_get_device(struct rds_sock *rs, struct rds_iw_device **rds_iwd
 			 * zero'ed.  It doesn't appear to be properly populated
 			 * during connection setup...
 			 */
-			if (src_addr->sin_addr.s_addr == rs->rs_bound_addr) {
+			if (src_addr->sin_addr.s_addr == src->sin_addr.s_addr) {
 #endif
 				spin_unlock_irq(&iwdev->spinlock);
 				*rds_iwdev = iwdev;
@@ -180,19 +182,13 @@ int rds_iw_update_cm_id(struct rds_iw_device *rds_iwdev, struct rdma_cm_id *cm_i
 {
 	struct sockaddr_in *src_addr, *dst_addr;
 	struct rds_iw_device *rds_iwdev_old;
-	struct rds_sock rs;
 	struct rdma_cm_id *pcm_id;
 	int rc;
 
 	src_addr = (struct sockaddr_in *)&cm_id->route.addr.src_addr;
 	dst_addr = (struct sockaddr_in *)&cm_id->route.addr.dst_addr;
 
-	rs.rs_bound_addr = src_addr->sin_addr.s_addr;
-	rs.rs_bound_port = src_addr->sin_port;
-	rs.rs_conn_addr = dst_addr->sin_addr.s_addr;
-	rs.rs_conn_port = dst_addr->sin_port;
-
-	rc = rds_iw_get_device(&rs, &rds_iwdev_old, &pcm_id);
+	rc = rds_iw_get_device(src_addr, dst_addr, &rds_iwdev_old, &pcm_id);
 	if (rc)
 		rds_iw_remove_cm_id(rds_iwdev, cm_id);
 
@@ -598,9 +594,17 @@ void *rds_iw_get_mr(struct scatterlist *sg, unsigned long nents,
 	struct rds_iw_device *rds_iwdev;
 	struct rds_iw_mr *ibmr = NULL;
 	struct rdma_cm_id *cm_id;
+	struct sockaddr_in src = {
+		.sin_addr.s_addr = rs->rs_bound_addr,
+		.sin_port = rs->rs_bound_port,
+	};
+	struct sockaddr_in dst = {
+		.sin_addr.s_addr = rs->rs_conn_addr,
+		.sin_port = rs->rs_conn_port,
+	};
 	int ret;
 
-	ret = rds_iw_get_device(rs, &rds_iwdev, &cm_id);
+	ret = rds_iw_get_device(&src, &dst, &rds_iwdev, &cm_id);
 	if (ret || !cm_id) {
 		ret = -ENODEV;
 		goto out;
diff --git a/net/rds/iw_recv.c b/net/rds/iw_recv.c
index aa8bf6786008..a66d1794b2d0 100644
--- a/net/rds/iw_recv.c
+++ b/net/rds/iw_recv.c
@@ -303,15 +303,12 @@ void rds_iw_inc_free(struct rds_incoming *inc)
 	BUG_ON(atomic_read(&rds_iw_allocation) < 0);
 }
 
-int rds_iw_inc_copy_to_user(struct rds_incoming *inc, struct iovec *first_iov,
-			    size_t size)
+int rds_iw_inc_copy_to_user(struct rds_incoming *inc, struct iov_iter *to)
 {
 	struct rds_iw_incoming *iwinc;
 	struct rds_page_frag *frag;
-	struct iovec *iov = first_iov;
 	unsigned long to_copy;
 	unsigned long frag_off = 0;
-	unsigned long iov_off = 0;
 	int copied = 0;
 	int ret;
 	u32 len;
@@ -320,37 +317,25 @@ int rds_iw_inc_copy_to_user(struct rds_incoming *inc, struct iovec *first_iov,
 	frag = list_entry(iwinc->ii_frags.next, struct rds_page_frag, f_item);
 	len = be32_to_cpu(inc->i_hdr.h_len);
 
-	while (copied < size && copied < len) {
+	while (iov_iter_count(to) && copied < len) {
 		if (frag_off == RDS_FRAG_SIZE) {
 			frag = list_entry(frag->f_item.next,
 					  struct rds_page_frag, f_item);
 			frag_off = 0;
 		}
-		while (iov_off == iov->iov_len) {
-			iov_off = 0;
-			iov++;
-		}
-
-		to_copy = min(iov->iov_len - iov_off, RDS_FRAG_SIZE - frag_off);
-		to_copy = min_t(size_t, to_copy, size - copied);
+		to_copy = min_t(unsigned long, iov_iter_count(to),
+				RDS_FRAG_SIZE - frag_off);
 		to_copy = min_t(unsigned long, to_copy, len - copied);
 
-		rdsdebug("%lu bytes to user [%p, %zu] + %lu from frag "
-			 "[%p, %lu] + %lu\n",
-			 to_copy, iov->iov_base, iov->iov_len, iov_off,
-			 frag->f_page, frag->f_offset, frag_off);
-
 		/* XXX needs + offset for multiple recvs per page */
-		ret = rds_page_copy_to_user(frag->f_page,
-					    frag->f_offset + frag_off,
-					    iov->iov_base + iov_off,
-					    to_copy);
-		if (ret) {
-			copied = ret;
-			break;
-		}
+		rds_stats_add(s_copy_to_user, to_copy);
+		ret = copy_page_to_iter(frag->f_page,
+					frag->f_offset + frag_off,
+					to_copy,
+					to);
+		if (ret != to_copy)
+			return -EFAULT;
 
-		iov_off += to_copy;
 		frag_off += to_copy;
 		copied += to_copy;
 	}
diff --git a/net/rds/iw_send.c b/net/rds/iw_send.c
index 9105ea03aec5..13834780a308 100644
--- a/net/rds/iw_send.c
+++ b/net/rds/iw_send.c
@@ -361,7 +361,7 @@ try_again:
 	posted = IB_GET_POST_CREDITS(oldval);
 	avail = IB_GET_SEND_CREDITS(oldval);
 
-	rdsdebug("rds_iw_send_grab_credits(%u): credits=%u posted=%u\n",
+	rdsdebug("wanted=%u credits=%u posted=%u\n",
 			wanted, avail, posted);
 
 	/* The last credit must be used to send a credit update. */
@@ -405,7 +405,7 @@ void rds_iw_send_add_credits(struct rds_connection *conn, unsigned int credits)
 	if (credits == 0)
 		return;
 
-	rdsdebug("rds_iw_send_add_credits(%u): current=%u%s\n",
+	rdsdebug("credits=%u current=%u%s\n",
 			credits,
 			IB_GET_SEND_CREDITS(atomic_read(&ic->i_credits)),
 			test_bit(RDS_LL_SEND_FULL, &conn->c_flags) ? ", ll_send_full" : "");
diff --git a/net/rds/message.c b/net/rds/message.c
index aba232f9f308..756c73729126 100644
--- a/net/rds/message.c
+++ b/net/rds/message.c
@@ -264,75 +264,54 @@ struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned in
 	return rm;
 }
 
-int rds_message_copy_from_user(struct rds_message *rm, struct iovec *first_iov,
-					       size_t total_len)
+int rds_message_copy_from_user(struct rds_message *rm, struct iov_iter *from)
 {
-	unsigned long to_copy;
-	unsigned long iov_off;
+	unsigned long to_copy, nbytes;
 	unsigned long sg_off;
-	struct iovec *iov;
 	struct scatterlist *sg;
 	int ret = 0;
 
-	rm->m_inc.i_hdr.h_len = cpu_to_be32(total_len);
+	rm->m_inc.i_hdr.h_len = cpu_to_be32(iov_iter_count(from));
 
 	/*
 	 * now allocate and copy in the data payload.
 	 */
 	sg = rm->data.op_sg;
-	iov = first_iov;
-	iov_off = 0;
 	sg_off = 0; /* Dear gcc, sg->page will be null from kzalloc. */
 
-	while (total_len) {
+	while (iov_iter_count(from)) {
 		if (!sg_page(sg)) {
-			ret = rds_page_remainder_alloc(sg, total_len,
+			ret = rds_page_remainder_alloc(sg, iov_iter_count(from),
 						       GFP_HIGHUSER);
 			if (ret)
-				goto out;
+				return ret;
 			rm->data.op_nents++;
 			sg_off = 0;
 		}
 
-		while (iov_off == iov->iov_len) {
-			iov_off = 0;
-			iov++;
-		}
-
-		to_copy = min(iov->iov_len - iov_off, sg->length - sg_off);
-		to_copy = min_t(size_t, to_copy, total_len);
-
-		rdsdebug("copying %lu bytes from user iov [%p, %zu] + %lu to "
-			 "sg [%p, %u, %u] + %lu\n",
-			 to_copy, iov->iov_base, iov->iov_len, iov_off,
-			 (void *)sg_page(sg), sg->offset, sg->length, sg_off);
+		to_copy = min_t(unsigned long, iov_iter_count(from),
+				sg->length - sg_off);
 
-		ret = rds_page_copy_from_user(sg_page(sg), sg->offset + sg_off,
-					      iov->iov_base + iov_off,
-					      to_copy);
-		if (ret)
-			goto out;
+		rds_stats_add(s_copy_from_user, to_copy);
+		nbytes = copy_page_from_iter(sg_page(sg), sg->offset + sg_off,
+					     to_copy, from);
+		if (nbytes != to_copy)
+			return -EFAULT;
 
-		iov_off += to_copy;
-		total_len -= to_copy;
 		sg_off += to_copy;
 
 		if (sg_off == sg->length)
 			sg++;
 	}
 
-out:
 	return ret;
 }
 
-int rds_message_inc_copy_to_user(struct rds_incoming *inc,
-				 struct iovec *first_iov, size_t size)
+int rds_message_inc_copy_to_user(struct rds_incoming *inc, struct iov_iter *to)
 {
 	struct rds_message *rm;
-	struct iovec *iov;
 	struct scatterlist *sg;
 	unsigned long to_copy;
-	unsigned long iov_off;
 	unsigned long vec_off;
 	int copied;
 	int ret;
@@ -341,36 +320,21 @@ int rds_message_inc_copy_to_user(struct rds_incoming *inc,
 	rm = container_of(inc, struct rds_message, m_inc);
 	len = be32_to_cpu(rm->m_inc.i_hdr.h_len);
 
-	iov = first_iov;
-	iov_off = 0;
 	sg = rm->data.op_sg;
 	vec_off = 0;
 	copied = 0;
 
-	while (copied < size && copied < len) {
-		while (iov_off == iov->iov_len) {
-			iov_off = 0;
-			iov++;
-		}
-
-		to_copy = min(iov->iov_len - iov_off, sg->length - vec_off);
-		to_copy = min_t(size_t, to_copy, size - copied);
+	while (iov_iter_count(to) && copied < len) {
+		to_copy = min_t(unsigned long, iov_iter_count(to),
+				sg->length - vec_off);
 		to_copy = min_t(unsigned long, to_copy, len - copied);
 
-		rdsdebug("copying %lu bytes to user iov [%p, %zu] + %lu to "
-			 "sg [%p, %u, %u] + %lu\n",
-			 to_copy, iov->iov_base, iov->iov_len, iov_off,
-			 sg_page(sg), sg->offset, sg->length, vec_off);
-
-		ret = rds_page_copy_to_user(sg_page(sg), sg->offset + vec_off,
-					    iov->iov_base + iov_off,
-					    to_copy);
-		if (ret) {
-			copied = ret;
-			break;
-		}
+		rds_stats_add(s_copy_to_user, to_copy);
+		ret = copy_page_to_iter(sg_page(sg), sg->offset + vec_off,
+					to_copy, to);
+		if (ret != to_copy)
+			return -EFAULT;
 
-		iov_off += to_copy;
 		vec_off += to_copy;
 		copied += to_copy;
 
diff --git a/net/rds/rds.h b/net/rds/rds.h
index 48f8ffc60f8f..0d41155a2258 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -110,6 +110,7 @@ struct rds_connection {
 	void			*c_transport_data;
 
 	atomic_t		c_state;
+	unsigned long		c_send_gen;
 	unsigned long		c_flags;
 	unsigned long		c_reconnect_jiffies;
 	struct delayed_work	c_send_w;
@@ -431,8 +432,7 @@ struct rds_transport {
 	int (*xmit_rdma)(struct rds_connection *conn, struct rm_rdma_op *op);
 	int (*xmit_atomic)(struct rds_connection *conn, struct rm_atomic_op *op);
 	int (*recv)(struct rds_connection *conn);
-	int (*inc_copy_to_user)(struct rds_incoming *inc, struct iovec *iov,
-				size_t size);
+	int (*inc_copy_to_user)(struct rds_incoming *inc, struct iov_iter *to);
 	void (*inc_free)(struct rds_incoming *inc);
 
 	int (*cm_handle_connect)(struct rdma_cm_id *cm_id,
@@ -657,8 +657,7 @@ rds_conn_connecting(struct rds_connection *conn)
 /* message.c */
 struct rds_message *rds_message_alloc(unsigned int nents, gfp_t gfp);
 struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents);
-int rds_message_copy_from_user(struct rds_message *rm, struct iovec *first_iov,
-					       size_t total_len);
+int rds_message_copy_from_user(struct rds_message *rm, struct iov_iter *from);
 struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned int total_len);
 void rds_message_populate_header(struct rds_header *hdr, __be16 sport,
 				 __be16 dport, u64 seq);
@@ -667,8 +666,7 @@ int rds_message_add_extension(struct rds_header *hdr,
 int rds_message_next_extension(struct rds_header *hdr,
 			       unsigned int *pos, void *buf, unsigned int *buflen);
 int rds_message_add_rdma_dest_extension(struct rds_header *hdr, u32 r_key, u32 offset);
-int rds_message_inc_copy_to_user(struct rds_incoming *inc,
-				 struct iovec *first_iov, size_t size);
+int rds_message_inc_copy_to_user(struct rds_incoming *inc, struct iov_iter *to);
 void rds_message_inc_free(struct rds_incoming *inc);
 void rds_message_addref(struct rds_message *rm);
 void rds_message_put(struct rds_message *rm);
@@ -705,8 +703,8 @@ void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn,
 void rds_inc_put(struct rds_incoming *inc);
 void rds_recv_incoming(struct rds_connection *conn, __be32 saddr, __be32 daddr,
 		       struct rds_incoming *inc, gfp_t gfp);
-int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
-		size_t size, int msg_flags);
+int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+		int msg_flags);
 void rds_clear_recv_queue(struct rds_sock *rs);
 int rds_notify_queue_get(struct rds_sock *rs, struct msghdr *msg);
 void rds_inc_info_copy(struct rds_incoming *inc,
@@ -714,8 +712,7 @@ void rds_inc_info_copy(struct rds_incoming *inc,
 		       __be32 saddr, __be32 daddr, int flip);
 
 /* send.c */
-int rds_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
-		size_t payload_len);
+int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len);
 void rds_send_reset(struct rds_connection *conn);
 int rds_send_xmit(struct rds_connection *conn);
 struct sockaddr_in;
diff --git a/net/rds/recv.c b/net/rds/recv.c
index bd82522534fc..a00462b0d01d 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -395,8 +395,8 @@ static int rds_cmsg_recv(struct rds_incoming *inc, struct msghdr *msg)
 	return 0;
 }
 
-int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
-		size_t size, int msg_flags)
+int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+		int msg_flags)
 {
 	struct sock *sk = sock->sk;
 	struct rds_sock *rs = rds_sk_to_rs(sk);
@@ -414,6 +414,7 @@ int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
 		goto out;
 
 	while (1) {
+		struct iov_iter save;
 		/* If there are pending notifications, do those - and nothing else */
 		if (!list_empty(&rs->rs_notify_queue)) {
 			ret = rds_notify_queue_get(rs, msg);
@@ -449,8 +450,8 @@ int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
 		rdsdebug("copying inc %p from %pI4:%u to user\n", inc,
 			 &inc->i_conn->c_faddr,
 			 ntohs(inc->i_hdr.h_sport));
-		ret = inc->i_conn->c_trans->inc_copy_to_user(inc, msg->msg_iov,
-							     size);
+		save = msg->msg_iter;
+		ret = inc->i_conn->c_trans->inc_copy_to_user(inc, &msg->msg_iter);
 		if (ret < 0)
 			break;
 
@@ -463,6 +464,7 @@ int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
 			rds_inc_put(inc);
 			inc = NULL;
 			rds_stats_inc(s_recv_deliver_raced);
+			msg->msg_iter = save;
 			continue;
 		}
 
diff --git a/net/rds/send.c b/net/rds/send.c
index 0a64541020b0..e9430f537f9c 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -140,8 +140,11 @@ int rds_send_xmit(struct rds_connection *conn)
 	struct scatterlist *sg;
 	int ret = 0;
 	LIST_HEAD(to_be_dropped);
+	int batch_count;
+	unsigned long send_gen = 0;
 
 restart:
+	batch_count = 0;
 
 	/*
 	 * sendmsg calls here after having queued its message on the send
@@ -157,6 +160,17 @@ restart:
 	}
 
 	/*
+	 * we record the send generation after doing the xmit acquire.
+	 * if someone else manages to jump in and do some work, we'll use
+	 * this to avoid a goto restart farther down.
+	 *
+	 * The acquire_in_xmit() check above ensures that only one
+	 * caller can increment c_send_gen at any time.
+	 */
+	conn->c_send_gen++;
+	send_gen = conn->c_send_gen;
+
+	/*
 	 * rds_conn_shutdown() sets the conn state and then tests RDS_IN_XMIT,
 	 * we do the opposite to avoid races.
 	 */
@@ -202,6 +216,16 @@ restart:
 		if (!rm) {
 			unsigned int len;
 
+			batch_count++;
+
+			/* we want to process as big a batch as we can, but
+			 * we also want to avoid softlockups.  If we've been
+			 * through a lot of messages, lets back off and see
+			 * if anyone else jumps in
+			 */
+			if (batch_count >= 1024)
+				goto over_batch;
+
 			spin_lock_irqsave(&conn->c_lock, flags);
 
 			if (!list_empty(&conn->c_send_queue)) {
@@ -357,9 +381,9 @@ restart:
 		}
 	}
 
+over_batch:
 	if (conn->c_trans->xmit_complete)
 		conn->c_trans->xmit_complete(conn);
-
 	release_in_xmit(conn);
 
 	/* Nuke any messages we decided not to retransmit. */
@@ -380,10 +404,15 @@ restart:
 	 * If the transport cannot continue (i.e ret != 0), then it must
 	 * call us when more room is available, such as from the tx
 	 * completion handler.
+	 *
+	 * We have an extra generation check here so that if someone manages
+	 * to jump in after our release_in_xmit, we'll see that they have done
+	 * some work and we will skip our goto
 	 */
 	if (ret == 0) {
 		smp_mb();
-		if (!list_empty(&conn->c_send_queue)) {
+		if (!list_empty(&conn->c_send_queue) &&
+		    send_gen == conn->c_send_gen) {
 			rds_stats_inc(s_send_lock_queue_raced);
 			goto restart;
 		}
@@ -826,7 +855,7 @@ static int rds_rm_size(struct msghdr *msg, int data_len)
 	int cmsg_groups = 0;
 	int retval;
 
-	for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) {
+	for_each_cmsghdr(cmsg, msg) {
 		if (!CMSG_OK(msg, cmsg))
 			return -EINVAL;
 
@@ -878,7 +907,7 @@ static int rds_cmsg_send(struct rds_sock *rs, struct rds_message *rm,
 	struct cmsghdr *cmsg;
 	int ret = 0;
 
-	for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) {
+	for_each_cmsghdr(cmsg, msg) {
 		if (!CMSG_OK(msg, cmsg))
 			return -EINVAL;
 
@@ -920,8 +949,7 @@ static int rds_cmsg_send(struct rds_sock *rs, struct rds_message *rm,
 	return ret;
 }
 
-int rds_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
-		size_t payload_len)
+int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 {
 	struct sock *sk = sock->sk;
 	struct rds_sock *rs = rds_sk_to_rs(sk);
@@ -982,7 +1010,7 @@ int rds_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
 			ret = -ENOMEM;
 			goto out;
 		}
-		ret = rds_message_copy_from_user(rm, msg->msg_iov, payload_len);
+		ret = rds_message_copy_from_user(rm, &msg->msg_iter);
 		if (ret)
 			goto out;
 	}
diff --git a/net/rds/sysctl.c b/net/rds/sysctl.c
index c3b0cd43eb56..c173f69e1479 100644
--- a/net/rds/sysctl.c
+++ b/net/rds/sysctl.c
@@ -71,14 +71,14 @@ static struct ctl_table rds_sysctl_rds_table[] = {
 	{
 		.procname	= "max_unacked_packets",
 		.data		= &rds_sysctl_max_unacked_packets,
-		.maxlen         = sizeof(unsigned long),
+		.maxlen         = sizeof(int),
 		.mode           = 0644,
 		.proc_handler   = proc_dointvec,
 	},
 	{
 		.procname	= "max_unacked_bytes",
 		.data		= &rds_sysctl_max_unacked_bytes,
-		.maxlen         = sizeof(unsigned long),
+		.maxlen         = sizeof(int),
 		.mode           = 0644,
 		.proc_handler   = proc_dointvec,
 	},
diff --git a/net/rds/tcp.h b/net/rds/tcp.h
index 65637491f728..0dbdd37162da 100644
--- a/net/rds/tcp.h
+++ b/net/rds/tcp.h
@@ -69,8 +69,7 @@ void rds_tcp_recv_exit(void);
 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,
-			     size_t size);
+int rds_tcp_inc_copy_to_user(struct rds_incoming *inc, struct iov_iter *to);
 
 /* tcp_send.c */
 void rds_tcp_xmit_prepare(struct rds_connection *conn);
diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c
index f9f564a6c960..973109c7b8e8 100644
--- a/net/rds/tcp_connect.c
+++ b/net/rds/tcp_connect.c
@@ -62,6 +62,7 @@ void rds_tcp_state_change(struct sock *sk)
 		case TCP_ESTABLISHED:
 			rds_connect_complete(conn);
 			break;
+		case TCP_CLOSE_WAIT:
 		case TCP_CLOSE:
 			rds_conn_drop(conn);
 		default:
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 23ab4dcd1d9f..0da49e34495f 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -45,12 +45,45 @@ static void rds_tcp_accept_worker(struct work_struct *work);
 static DECLARE_WORK(rds_tcp_listen_work, rds_tcp_accept_worker);
 static struct socket *rds_tcp_listen_sock;
 
+static int rds_tcp_keepalive(struct socket *sock)
+{
+	/* values below based on xs_udp_default_timeout */
+	int keepidle = 5; /* send a probe 'keepidle' secs after last data */
+	int keepcnt = 5; /* number of unack'ed probes before declaring dead */
+	int keepalive = 1;
+	int ret = 0;
+
+	ret = kernel_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE,
+				(char *)&keepalive, sizeof(keepalive));
+	if (ret < 0)
+		goto bail;
+
+	ret = kernel_setsockopt(sock, IPPROTO_TCP, TCP_KEEPCNT,
+				(char *)&keepcnt, sizeof(keepcnt));
+	if (ret < 0)
+		goto bail;
+
+	ret = kernel_setsockopt(sock, IPPROTO_TCP, TCP_KEEPIDLE,
+				(char *)&keepidle, sizeof(keepidle));
+	if (ret < 0)
+		goto bail;
+
+	/* KEEPINTVL is the interval between successive probes. We follow
+	 * the model in xs_tcp_finish_connecting() and re-use keepidle.
+	 */
+	ret = kernel_setsockopt(sock, IPPROTO_TCP, TCP_KEEPINTVL,
+				(char *)&keepidle, sizeof(keepidle));
+bail:
+	return ret;
+}
+
 static int rds_tcp_accept_one(struct socket *sock)
 {
 	struct socket *new_sock = NULL;
 	struct rds_connection *conn;
 	int ret;
 	struct inet_sock *inet;
+	struct rds_tcp_connection *rs_tcp;
 
 	ret = sock_create_lite(sock->sk->sk_family, sock->sk->sk_type,
 			       sock->sk->sk_protocol, &new_sock);
@@ -63,6 +96,10 @@ static int rds_tcp_accept_one(struct socket *sock)
 	if (ret < 0)
 		goto out;
 
+	ret = rds_tcp_keepalive(new_sock);
+	if (ret < 0)
+		goto out;
+
 	rds_tcp_tune(new_sock);
 
 	inet = inet_sk(new_sock->sk);
@@ -77,6 +114,15 @@ static int rds_tcp_accept_one(struct socket *sock)
 		ret = PTR_ERR(conn);
 		goto out;
 	}
+	/* An incoming SYN request came in, and TCP just accepted it.
+	 * We always create a new conn for listen side of TCP, and do not
+	 * add it to the c_hash_list.
+	 *
+	 * If the client reboots, this conn will need to be cleaned up.
+	 * rds_tcp_state_change() will do that cleanup
+	 */
+	rs_tcp = (struct rds_tcp_connection *)conn->c_transport_data;
+	WARN_ON(!rs_tcp || rs_tcp->t_sock);
 
 	/*
 	 * see the comment above rds_queue_delayed_reconnect()
diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c
index 9ae6e0a264ec..fbc5ef88bc0e 100644
--- a/net/rds/tcp_recv.c
+++ b/net/rds/tcp_recv.c
@@ -59,50 +59,30 @@ void rds_tcp_inc_free(struct rds_incoming *inc)
 /*
  * this is pretty lame, but, whatever.
  */
-int rds_tcp_inc_copy_to_user(struct rds_incoming *inc, struct iovec *first_iov,
-			     size_t size)
+int rds_tcp_inc_copy_to_user(struct rds_incoming *inc, struct iov_iter *to)
 {
 	struct rds_tcp_incoming *tinc;
-	struct iovec *iov, tmp;
 	struct sk_buff *skb;
-	unsigned long to_copy, skb_off;
 	int ret = 0;
 
-	if (size == 0)
+	if (!iov_iter_count(to))
 		goto out;
 
 	tinc = container_of(inc, struct rds_tcp_incoming, ti_inc);
-	iov = first_iov;
-	tmp = *iov;
 
 	skb_queue_walk(&tinc->ti_skb_list, skb) {
-		skb_off = 0;
-		while (skb_off < skb->len) {
-			while (tmp.iov_len == 0) {
-				iov++;
-				tmp = *iov;
-			}
-
-			to_copy = min(tmp.iov_len, size);
+		unsigned long to_copy, skb_off;
+		for (skb_off = 0; skb_off < skb->len; skb_off += to_copy) {
+			to_copy = iov_iter_count(to);
 			to_copy = min(to_copy, skb->len - skb_off);
 
-			rdsdebug("ret %d size %zu skb %p skb_off %lu "
-				 "skblen %d iov_base %p iov_len %zu cpy %lu\n",
-				 ret, size, skb, skb_off, skb->len,
-				 tmp.iov_base, tmp.iov_len, to_copy);
-
-			/* modifies tmp as it copies */
-			if (skb_copy_datagram_iovec(skb, skb_off, &tmp,
-						    to_copy)) {
-				ret = -EFAULT;
-				goto out;
-			}
+			if (skb_copy_datagram_iter(skb, skb_off, to, to_copy))
+				return -EFAULT;
 
 			rds_stats_add(s_copy_to_user, to_copy);
-			size -= to_copy;
 			ret += to_copy;
-			skb_off += to_copy;
-			if (size == 0)
+
+			if (!iov_iter_count(to))
 				goto out;
 		}
 	}
diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c
index 0f62326c0f5e..d978f2f46ff3 100644
--- a/net/rfkill/rfkill-gpio.c
+++ b/net/rfkill/rfkill-gpio.c
@@ -63,6 +63,15 @@ static const struct rfkill_ops rfkill_gpio_ops = {
 	.set_block = rfkill_gpio_set_power,
 };
 
+static const struct acpi_gpio_params reset_gpios = { 0, 0, false };
+static const struct acpi_gpio_params shutdown_gpios = { 1, 0, false };
+
+static const struct acpi_gpio_mapping acpi_rfkill_default_gpios[] = {
+	{ "reset-gpios", &reset_gpios, 1 },
+	{ "shutdown-gpios", &shutdown_gpios, 1 },
+	{ },
+};
+
 static int rfkill_gpio_acpi_probe(struct device *dev,
 				  struct rfkill_gpio_data *rfkill)
 {
@@ -75,7 +84,8 @@ static int rfkill_gpio_acpi_probe(struct device *dev,
 	rfkill->name = dev_name(dev);
 	rfkill->type = (unsigned)id->driver_data;
 
-	return 0;
+	return acpi_dev_add_driver_gpios(ACPI_COMPANION(dev),
+					 acpi_rfkill_default_gpios);
 }
 
 static int rfkill_gpio_probe(struct platform_device *pdev)
@@ -102,7 +112,7 @@ static int rfkill_gpio_probe(struct platform_device *pdev)
 
 	rfkill->clk = devm_clk_get(&pdev->dev, NULL);
 
-	gpio = devm_gpiod_get_index(&pdev->dev, "reset", 0);
+	gpio = devm_gpiod_get(&pdev->dev, "reset");
 	if (!IS_ERR(gpio)) {
 		ret = gpiod_direction_output(gpio, 0);
 		if (ret)
@@ -110,7 +120,7 @@ static int rfkill_gpio_probe(struct platform_device *pdev)
 		rfkill->reset_gpio = gpio;
 	}
 
-	gpio = devm_gpiod_get_index(&pdev->dev, "shutdown", 1);
+	gpio = devm_gpiod_get(&pdev->dev, "shutdown");
 	if (!IS_ERR(gpio)) {
 		ret = gpiod_direction_output(gpio, 0);
 		if (ret)
@@ -150,6 +160,8 @@ static int rfkill_gpio_remove(struct platform_device *pdev)
 	rfkill_unregister(rfkill->rfkill_dev);
 	rfkill_destroy(rfkill->rfkill_dev);
 
+	acpi_dev_remove_driver_gpios(ACPI_COMPANION(&pdev->dev));
+
 	return 0;
 }
 
@@ -158,6 +170,7 @@ static const struct acpi_device_id rfkill_acpi_match[] = {
 	{ "BCM2E1A", RFKILL_TYPE_BLUETOOTH },
 	{ "BCM2E39", RFKILL_TYPE_BLUETOOTH },
 	{ "BCM2E3D", RFKILL_TYPE_BLUETOOTH },
+	{ "BCM2E40", RFKILL_TYPE_BLUETOOTH },
 	{ "BCM2E64", RFKILL_TYPE_BLUETOOTH },
 	{ "BCM4752", RFKILL_TYPE_GPS },
 	{ "LNV4752", RFKILL_TYPE_GPS },
@@ -171,7 +184,6 @@ static struct platform_driver rfkill_gpio_driver = {
 	.remove = rfkill_gpio_remove,
 	.driver = {
 		.name = "rfkill_gpio",
-		.owner = THIS_MODULE,
 		.acpi_match_table = ACPI_PTR(rfkill_acpi_match),
 	},
 };
diff --git a/net/rfkill/rfkill-regulator.c b/net/rfkill/rfkill-regulator.c
index cf5b145902e5..50cd26a48e87 100644
--- a/net/rfkill/rfkill-regulator.c
+++ b/net/rfkill/rfkill-regulator.c
@@ -142,7 +142,6 @@ static struct platform_driver rfkill_regulator_driver = {
 	.remove = rfkill_regulator_remove,
 	.driver = {
 		.name = "rfkill-regulator",
-		.owner = THIS_MODULE,
 	},
 };
 
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index a85c1a086ae4..8ae603069a1a 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -1046,8 +1046,7 @@ int rose_rx_call_request(struct sk_buff *skb, struct net_device *dev, struct ros
 	return 1;
 }
 
-static int rose_sendmsg(struct kiocb *iocb, struct socket *sock,
-			struct msghdr *msg, size_t len)
+static int rose_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 {
 	struct sock *sk = sock->sk;
 	struct rose_sock *rose = rose_sk(sk);
@@ -1121,7 +1120,7 @@ static int rose_sendmsg(struct kiocb *iocb, struct socket *sock,
 	skb_reset_transport_header(skb);
 	skb_put(skb, len);
 
-	err = memcpy_fromiovec(skb_transport_header(skb), msg->msg_iov, len);
+	err = memcpy_from_msg(skb_transport_header(skb), msg, len);
 	if (err) {
 		kfree_skb(skb);
 		return err;
@@ -1211,8 +1210,8 @@ static int rose_sendmsg(struct kiocb *iocb, struct socket *sock,
 }
 
 
-static int rose_recvmsg(struct kiocb *iocb, struct socket *sock,
-			struct msghdr *msg, size_t size, int flags)
+static int rose_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+			int flags)
 {
 	struct sock *sk = sock->sk;
 	struct rose_sock *rose = rose_sk(sk);
@@ -1249,7 +1248,7 @@ static int rose_recvmsg(struct kiocb *iocb, struct socket *sock,
 		msg->msg_flags |= MSG_TRUNC;
 	}
 
-	skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	skb_copy_datagram_msg(skb, 0, msg, copied);
 
 	if (msg->msg_name) {
 		struct sockaddr_rose *srose;
diff --git a/net/rose/rose_dev.c b/net/rose/rose_dev.c
index 50005888be57..369ca81a8c5d 100644
--- a/net/rose/rose_dev.c
+++ b/net/rose/rose_dev.c
@@ -41,6 +41,9 @@ static int rose_header(struct sk_buff *skb, struct net_device *dev,
 {
 	unsigned char *buff = skb_push(skb, ROSE_MIN_LEN + 2);
 
+	if (daddr)
+		memcpy(buff + 7, daddr, dev->addr_len);
+
 	*buff++ = ROSE_GFI | ROSE_Q_BIT;
 	*buff++ = 0x00;
 	*buff++ = ROSE_DATA;
@@ -53,43 +56,6 @@ static int rose_header(struct sk_buff *skb, struct net_device *dev,
 	return -37;
 }
 
-static int rose_rebuild_header(struct sk_buff *skb)
-{
-#ifdef CONFIG_INET
-	struct net_device *dev = skb->dev;
-	struct net_device_stats *stats = &dev->stats;
-	unsigned char *bp = (unsigned char *)skb->data;
-	struct sk_buff *skbn;
-	unsigned int len;
-
-	if (arp_find(bp + 7, skb)) {
-		return 1;
-	}
-
-	if ((skbn = skb_clone(skb, GFP_ATOMIC)) == NULL) {
-		kfree_skb(skb);
-		return 1;
-	}
-
-	if (skb->sk != NULL)
-		skb_set_owner_w(skbn, skb->sk);
-
-	kfree_skb(skb);
-
-	len = skbn->len;
-
-	if (!rose_route_frame(skbn, NULL)) {
-		kfree_skb(skbn);
-		stats->tx_errors++;
-		return 1;
-	}
-
-	stats->tx_packets++;
-	stats->tx_bytes += len;
-#endif
-	return 1;
-}
-
 static int rose_set_mac_address(struct net_device *dev, void *addr)
 {
 	struct sockaddr *sa = addr;
@@ -134,19 +100,26 @@ static int rose_close(struct net_device *dev)
 static netdev_tx_t rose_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct net_device_stats *stats = &dev->stats;
+	unsigned int len = skb->len;
 
 	if (!netif_running(dev)) {
 		printk(KERN_ERR "ROSE: rose_xmit - called when iface is down\n");
 		return NETDEV_TX_BUSY;
 	}
-	dev_kfree_skb(skb);
-	stats->tx_errors++;
+
+	if (!rose_route_frame(skb, NULL)) {
+		dev_kfree_skb(skb);
+		stats->tx_errors++;
+		return NETDEV_TX_OK;
+	}
+
+	stats->tx_packets++;
+	stats->tx_bytes += len;
 	return NETDEV_TX_OK;
 }
 
 static const struct header_ops rose_header_ops = {
 	.create	= rose_header,
-	.rebuild = rose_rebuild_header,
 };
 
 static const struct net_device_ops rose_netdev_ops = {
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 7b1670489638..0095b9a0b779 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -441,8 +441,7 @@ static int rxrpc_connect(struct socket *sock, struct sockaddr *addr,
  *   - sends a call data packet
  *   - may send an abort (abort code in control data)
  */
-static int rxrpc_sendmsg(struct kiocb *iocb, struct socket *sock,
-			 struct msghdr *m, size_t len)
+static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len)
 {
 	struct rxrpc_transport *trans;
 	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
@@ -482,7 +481,7 @@ static int rxrpc_sendmsg(struct kiocb *iocb, struct socket *sock,
 	switch (rx->sk.sk_state) {
 	case RXRPC_SERVER_LISTENING:
 		if (!m->msg_name) {
-			ret = rxrpc_server_sendmsg(iocb, rx, m, len);
+			ret = rxrpc_server_sendmsg(rx, m, len);
 			break;
 		}
 	case RXRPC_SERVER_BOUND:
@@ -492,7 +491,7 @@ static int rxrpc_sendmsg(struct kiocb *iocb, struct socket *sock,
 			break;
 		}
 	case RXRPC_CLIENT_CONNECTED:
-		ret = rxrpc_client_sendmsg(iocb, rx, trans, m, len);
+		ret = rxrpc_client_sendmsg(rx, trans, m, len);
 		break;
 	default:
 		ret = -ENOTCONN;
diff --git a/net/rxrpc/ar-ack.c b/net/rxrpc/ar-ack.c
index c6be17a959a6..e0547f521f20 100644
--- a/net/rxrpc/ar-ack.c
+++ b/net/rxrpc/ar-ack.c
@@ -218,7 +218,8 @@ static void rxrpc_resend(struct rxrpc_call *call)
 	struct rxrpc_header *hdr;
 	struct sk_buff *txb;
 	unsigned long *p_txb, resend_at;
-	int loop, stop;
+	bool stop;
+	int loop;
 	u8 resend;
 
 	_enter("{%d,%d,%d,%d},",
@@ -226,7 +227,7 @@ static void rxrpc_resend(struct rxrpc_call *call)
 	       atomic_read(&call->sequence),
 	       CIRC_CNT(call->acks_head, call->acks_tail, call->acks_winsz));
 
-	stop = 0;
+	stop = false;
 	resend = 0;
 	resend_at = 0;
 
@@ -255,11 +256,11 @@ static void rxrpc_resend(struct rxrpc_call *call)
 			_proto("Tx DATA %%%u { #%d }",
 			       ntohl(sp->hdr.serial), ntohl(sp->hdr.seq));
 			if (rxrpc_send_packet(call->conn->trans, txb) < 0) {
-				stop = 0;
+				stop = true;
 				sp->resend_at = jiffies + 3;
 			} else {
 				sp->resend_at =
-					jiffies + rxrpc_resend_timeout * HZ;
+					jiffies + rxrpc_resend_timeout;
 			}
 		}
 
diff --git a/net/rxrpc/ar-error.c b/net/rxrpc/ar-error.c
index 74c0fcd36838..0610efa83d72 100644
--- a/net/rxrpc/ar-error.c
+++ b/net/rxrpc/ar-error.c
@@ -42,10 +42,15 @@ void rxrpc_UDP_error_report(struct sock *sk)
 		_leave("UDP socket errqueue empty");
 		return;
 	}
+	serr = SKB_EXT_ERR(skb);
+	if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) {
+		_leave("UDP empty message");
+		kfree_skb(skb);
+		return;
+	}
 
 	rxrpc_new_skb(skb);
 
-	serr = SKB_EXT_ERR(skb);
 	addr = *(__be32 *)(skb_network_header(skb) + serr->addr_offset);
 	port = serr->port;
 
diff --git a/net/rxrpc/ar-input.c b/net/rxrpc/ar-input.c
index 481f89f93789..4505a691d88c 100644
--- a/net/rxrpc/ar-input.c
+++ b/net/rxrpc/ar-input.c
@@ -28,7 +28,7 @@
 const char *rxrpc_pkts[] = {
 	"?00",
 	"DATA", "ACK", "BUSY", "ABORT", "ACKALL", "CHALL", "RESP", "DEBUG",
-	"?09", "?10", "?11", "?12", "?13", "?14", "?15"
+	"?09", "?10", "?11", "?12", "VERSION", "?14", "?15"
 };
 
 /*
@@ -593,6 +593,20 @@ static void rxrpc_post_packet_to_conn(struct rxrpc_connection *conn,
 	rxrpc_queue_conn(conn);
 }
 
+/*
+ * post endpoint-level events to the local endpoint
+ * - this includes debug and version messages
+ */
+static void rxrpc_post_packet_to_local(struct rxrpc_local *local,
+				       struct sk_buff *skb)
+{
+	_enter("%p,%p", local, skb);
+
+	atomic_inc(&local->usage);
+	skb_queue_tail(&local->event_queue, skb);
+	rxrpc_queue_work(&local->event_processor);
+}
+
 static struct rxrpc_connection *rxrpc_conn_from_local(struct rxrpc_local *local,
 					       struct sk_buff *skb,
 					       struct rxrpc_skb_priv *sp)
@@ -699,6 +713,11 @@ void rxrpc_data_ready(struct sock *sk)
 		goto bad_message;
 	}
 
+	if (sp->hdr.type == RXRPC_PACKET_TYPE_VERSION) {
+		rxrpc_post_packet_to_local(local, skb);
+		goto out;
+	}
+	
 	if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA &&
 	    (sp->hdr.callNumber == 0 || sp->hdr.seq == 0))
 		goto bad_message;
@@ -731,6 +750,8 @@ void rxrpc_data_ready(struct sock *sk)
 		else
 			goto cant_route_call;
 	}
+
+out:
 	rxrpc_put_local(local);
 	return;
 
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index ba9fd36d3f15..aef1bd294e17 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -152,11 +152,13 @@ struct rxrpc_local {
 	struct work_struct	destroyer;	/* endpoint destroyer */
 	struct work_struct	acceptor;	/* incoming call processor */
 	struct work_struct	rejecter;	/* packet reject writer */
+	struct work_struct	event_processor; /* endpoint event processor */
 	struct list_head	services;	/* services listening on this endpoint */
 	struct list_head	link;		/* link in endpoint list */
 	struct rw_semaphore	defrag_sem;	/* control re-enablement of IP DF bit */
 	struct sk_buff_head	accept_queue;	/* incoming calls awaiting acceptance */
 	struct sk_buff_head	reject_queue;	/* packets awaiting rejection */
+	struct sk_buff_head	event_queue;	/* endpoint event packets awaiting processing */
 	spinlock_t		lock;		/* access lock */
 	rwlock_t		services_lock;	/* lock for services list */
 	atomic_t		usage;
@@ -548,10 +550,9 @@ int rxrpc_get_server_data_key(struct rxrpc_connection *, const void *, time_t,
 extern unsigned rxrpc_resend_timeout;
 
 int rxrpc_send_packet(struct rxrpc_transport *, struct sk_buff *);
-int rxrpc_client_sendmsg(struct kiocb *, struct rxrpc_sock *,
-			 struct rxrpc_transport *, struct msghdr *, size_t);
-int rxrpc_server_sendmsg(struct kiocb *, struct rxrpc_sock *, struct msghdr *,
-			 size_t);
+int rxrpc_client_sendmsg(struct rxrpc_sock *, struct rxrpc_transport *,
+			 struct msghdr *, size_t);
+int rxrpc_server_sendmsg(struct rxrpc_sock *, struct msghdr *, size_t);
 
 /*
  * ar-peer.c
@@ -572,8 +573,7 @@ extern const struct file_operations rxrpc_connection_seq_fops;
  * ar-recvmsg.c
  */
 void rxrpc_remove_user_ID(struct rxrpc_sock *, struct rxrpc_call *);
-int rxrpc_recvmsg(struct kiocb *, struct socket *, struct msghdr *, size_t,
-		  int);
+int rxrpc_recvmsg(struct socket *, struct msghdr *, size_t, int);
 
 /*
  * ar-security.c
diff --git a/net/rxrpc/ar-local.c b/net/rxrpc/ar-local.c
index 87f7135d238b..ca904ed5400a 100644
--- a/net/rxrpc/ar-local.c
+++ b/net/rxrpc/ar-local.c
@@ -13,16 +13,22 @@
 #include <linux/net.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>
+#include <linux/udp.h>
+#include <linux/ip.h>
 #include <net/sock.h>
 #include <net/af_rxrpc.h>
+#include <generated/utsrelease.h>
 #include "ar-internal.h"
 
+static const char rxrpc_version_string[65] = "linux-" UTS_RELEASE " AF_RXRPC";
+
 static LIST_HEAD(rxrpc_locals);
 DEFINE_RWLOCK(rxrpc_local_lock);
 static DECLARE_RWSEM(rxrpc_local_sem);
 static DECLARE_WAIT_QUEUE_HEAD(rxrpc_local_wq);
 
 static void rxrpc_destroy_local(struct work_struct *work);
+static void rxrpc_process_local_events(struct work_struct *work);
 
 /*
  * allocate a new local
@@ -37,11 +43,13 @@ struct rxrpc_local *rxrpc_alloc_local(struct sockaddr_rxrpc *srx)
 		INIT_WORK(&local->destroyer, &rxrpc_destroy_local);
 		INIT_WORK(&local->acceptor, &rxrpc_accept_incoming_calls);
 		INIT_WORK(&local->rejecter, &rxrpc_reject_packets);
+		INIT_WORK(&local->event_processor, &rxrpc_process_local_events);
 		INIT_LIST_HEAD(&local->services);
 		INIT_LIST_HEAD(&local->link);
 		init_rwsem(&local->defrag_sem);
 		skb_queue_head_init(&local->accept_queue);
 		skb_queue_head_init(&local->reject_queue);
+		skb_queue_head_init(&local->event_queue);
 		spin_lock_init(&local->lock);
 		rwlock_init(&local->services_lock);
 		atomic_set(&local->usage, 1);
@@ -264,10 +272,12 @@ static void rxrpc_destroy_local(struct work_struct *work)
 	ASSERT(list_empty(&local->services));
 	ASSERT(!work_pending(&local->acceptor));
 	ASSERT(!work_pending(&local->rejecter));
+	ASSERT(!work_pending(&local->event_processor));
 
 	/* finish cleaning up the local descriptor */
 	rxrpc_purge_queue(&local->accept_queue);
 	rxrpc_purge_queue(&local->reject_queue);
+	rxrpc_purge_queue(&local->event_queue);
 	kernel_sock_shutdown(local->socket, SHUT_RDWR);
 	sock_release(local->socket);
 
@@ -308,3 +318,91 @@ void __exit rxrpc_destroy_all_locals(void)
 
 	_leave("");
 }
+
+/*
+ * Reply to a version request
+ */
+static void rxrpc_send_version_request(struct rxrpc_local *local,
+				       struct rxrpc_header *hdr,
+				       struct sk_buff *skb)
+{
+	struct sockaddr_in sin;
+	struct msghdr msg;
+	struct kvec iov[2];
+	size_t len;
+	int ret;
+
+	_enter("");
+
+	sin.sin_family = AF_INET;
+	sin.sin_port = udp_hdr(skb)->source;
+	sin.sin_addr.s_addr = ip_hdr(skb)->saddr;
+
+	msg.msg_name	= &sin;
+	msg.msg_namelen	= sizeof(sin);
+	msg.msg_control	= NULL;
+	msg.msg_controllen = 0;
+	msg.msg_flags	= 0;
+
+	hdr->seq	= 0;
+	hdr->serial	= 0;
+	hdr->type	= RXRPC_PACKET_TYPE_VERSION;
+	hdr->flags	= RXRPC_LAST_PACKET | (~hdr->flags & RXRPC_CLIENT_INITIATED);
+	hdr->userStatus	= 0;
+	hdr->_rsvd	= 0;
+
+	iov[0].iov_base	= hdr;
+	iov[0].iov_len	= sizeof(*hdr);
+	iov[1].iov_base	= (char *)rxrpc_version_string;
+	iov[1].iov_len	= sizeof(rxrpc_version_string);
+
+	len = iov[0].iov_len + iov[1].iov_len;
+
+	_proto("Tx VERSION (reply)");
+
+	ret = kernel_sendmsg(local->socket, &msg, iov, 2, len);
+	if (ret < 0)
+		_debug("sendmsg failed: %d", ret);
+
+	_leave("");
+}
+
+/*
+ * Process event packets targetted at a local endpoint.
+ */
+static void rxrpc_process_local_events(struct work_struct *work)
+{
+	struct rxrpc_local *local = container_of(work, struct rxrpc_local, event_processor);
+	struct sk_buff *skb;
+	char v;
+
+	_enter("");
+
+	atomic_inc(&local->usage);
+	
+	while ((skb = skb_dequeue(&local->event_queue))) {
+		struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+
+		kdebug("{%d},{%u}", local->debug_id, sp->hdr.type);
+
+		switch (sp->hdr.type) {
+		case RXRPC_PACKET_TYPE_VERSION:
+			if (skb_copy_bits(skb, 0, &v, 1) < 0)
+				return;
+			_proto("Rx VERSION { %02x }", v);
+			if (v == 0)
+				rxrpc_send_version_request(local, &sp->hdr, skb);
+			break;
+
+		default:
+			/* Just ignore anything we don't understand */
+			break;
+		}
+
+		rxrpc_put_local(local);
+		rxrpc_free_skb(skb);
+	}
+
+	rxrpc_put_local(local);
+	_leave("");
+}
diff --git a/net/rxrpc/ar-output.c b/net/rxrpc/ar-output.c
index 0b4b9a79f5ab..c0042807bfc6 100644
--- a/net/rxrpc/ar-output.c
+++ b/net/rxrpc/ar-output.c
@@ -23,8 +23,7 @@
  */
 unsigned rxrpc_resend_timeout = 4 * HZ;
 
-static int rxrpc_send_data(struct kiocb *iocb,
-			   struct rxrpc_sock *rx,
+static int rxrpc_send_data(struct rxrpc_sock *rx,
 			   struct rxrpc_call *call,
 			   struct msghdr *msg, size_t len);
 
@@ -45,7 +44,7 @@ static int rxrpc_sendmsg_cmsg(struct rxrpc_sock *rx, struct msghdr *msg,
 	if (msg->msg_controllen == 0)
 		return -EINVAL;
 
-	for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) {
+	for_each_cmsghdr(cmsg, msg) {
 		if (!CMSG_OK(msg, cmsg))
 			return -EINVAL;
 
@@ -129,9 +128,8 @@ static void rxrpc_send_abort(struct rxrpc_call *call, u32 abort_code)
  * - caller holds the socket locked
  * - the socket may be either a client socket or a server socket
  */
-int rxrpc_client_sendmsg(struct kiocb *iocb, struct rxrpc_sock *rx,
-			 struct rxrpc_transport *trans, struct msghdr *msg,
-			 size_t len)
+int rxrpc_client_sendmsg(struct rxrpc_sock *rx, struct rxrpc_transport *trans,
+			 struct msghdr *msg, size_t len)
 {
 	struct rxrpc_conn_bundle *bundle;
 	enum rxrpc_command cmd;
@@ -191,7 +189,7 @@ int rxrpc_client_sendmsg(struct kiocb *iocb, struct rxrpc_sock *rx,
 		/* request phase complete for this client call */
 		ret = -EPROTO;
 	} else {
-		ret = rxrpc_send_data(iocb, rx, call, msg, len);
+		ret = rxrpc_send_data(rx, call, msg, len);
 	}
 
 	rxrpc_put_call(call);
@@ -232,10 +230,7 @@ int rxrpc_kernel_send_data(struct rxrpc_call *call, struct msghdr *msg,
 		   call->state != RXRPC_CALL_SERVER_SEND_REPLY) {
 		ret = -EPROTO; /* request phase complete for this client call */
 	} else {
-		mm_segment_t oldfs = get_fs();
-		set_fs(KERNEL_DS);
-		ret = rxrpc_send_data(NULL, call->socket, call, msg, len);
-		set_fs(oldfs);
+		ret = rxrpc_send_data(call->socket, call, msg, len);
 	}
 
 	release_sock(&call->socket->sk);
@@ -274,8 +269,7 @@ EXPORT_SYMBOL(rxrpc_kernel_abort_call);
  * send a message through a server socket
  * - caller holds the socket locked
  */
-int rxrpc_server_sendmsg(struct kiocb *iocb, struct rxrpc_sock *rx,
-			 struct msghdr *msg, size_t len)
+int rxrpc_server_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 {
 	enum rxrpc_command cmd;
 	struct rxrpc_call *call;
@@ -316,7 +310,7 @@ int rxrpc_server_sendmsg(struct kiocb *iocb, struct rxrpc_sock *rx,
 			break;
 		}
 
-		ret = rxrpc_send_data(iocb, rx, call, msg, len);
+		ret = rxrpc_send_data(rx, call, msg, len);
 		break;
 
 	case RXRPC_CMD_SEND_ABORT:
@@ -523,21 +517,16 @@ static void rxrpc_queue_packet(struct rxrpc_call *call, struct sk_buff *skb,
  * - must be called in process context
  * - caller holds the socket locked
  */
-static int rxrpc_send_data(struct kiocb *iocb,
-			   struct rxrpc_sock *rx,
+static int rxrpc_send_data(struct rxrpc_sock *rx,
 			   struct rxrpc_call *call,
 			   struct msghdr *msg, size_t len)
 {
 	struct rxrpc_skb_priv *sp;
-	unsigned char __user *from;
 	struct sk_buff *skb;
-	struct iovec *iov;
 	struct sock *sk = &rx->sk;
 	long timeo;
 	bool more;
-	int ret, ioc, segment, copied;
-
-	_enter(",,,{%zu},%zu", msg->msg_iovlen, len);
+	int ret, copied;
 
 	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
 
@@ -547,11 +536,6 @@ static int rxrpc_send_data(struct kiocb *iocb,
 	if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
 		return -EPIPE;
 
-	iov = msg->msg_iov;
-	ioc = msg->msg_iovlen - 1;
-	from = iov->iov_base;
-	segment = iov->iov_len;
-	iov++;
 	more = msg->msg_flags & MSG_MORE;
 
 	skb = call->tx_pending;
@@ -559,13 +543,6 @@ static int rxrpc_send_data(struct kiocb *iocb,
 
 	copied = 0;
 	do {
-		int copy;
-
-		if (segment > len)
-			segment = len;
-
-		_debug("SEGMENT %d @%p", segment, from);
-
 		if (!skb) {
 			size_t size, chunk, max, space;
 
@@ -587,8 +564,8 @@ static int rxrpc_send_data(struct kiocb *iocb,
 			max &= ~(call->conn->size_align - 1UL);
 
 			chunk = max;
-			if (chunk > len && !more)
-				chunk = len;
+			if (chunk > msg_data_left(msg) && !more)
+				chunk = msg_data_left(msg);
 
 			space = chunk + call->conn->size_align;
 			space &= ~(call->conn->size_align - 1UL);
@@ -631,34 +608,22 @@ static int rxrpc_send_data(struct kiocb *iocb,
 		sp = rxrpc_skb(skb);
 
 		/* append next segment of data to the current buffer */
-		copy = skb_tailroom(skb);
-		ASSERTCMP(copy, >, 0);
-		if (copy > segment)
-			copy = segment;
-		if (copy > sp->remain)
-			copy = sp->remain;
-
-		_debug("add");
-		ret = skb_add_data(skb, from, copy);
-		_debug("added");
-		if (ret < 0)
-			goto efault;
-		sp->remain -= copy;
-		skb->mark += copy;
-		copied += copy;
-
-		len -= copy;
-		segment -= copy;
-		from += copy;
-		while (segment == 0 && ioc > 0) {
-			from = iov->iov_base;
-			segment = iov->iov_len;
-			iov++;
-			ioc--;
-		}
-		if (len == 0) {
-			segment = 0;
-			ioc = 0;
+		if (msg_data_left(msg) > 0) {
+			int copy = skb_tailroom(skb);
+			ASSERTCMP(copy, >, 0);
+			if (copy > msg_data_left(msg))
+				copy = msg_data_left(msg);
+			if (copy > sp->remain)
+				copy = sp->remain;
+
+			_debug("add");
+			ret = skb_add_data(skb, &msg->msg_iter, copy);
+			_debug("added");
+			if (ret < 0)
+				goto efault;
+			sp->remain -= copy;
+			skb->mark += copy;
+			copied += copy;
 		}
 
 		/* check for the far side aborting the call or a network error
@@ -667,7 +632,8 @@ static int rxrpc_send_data(struct kiocb *iocb,
 			goto call_aborted;
 
 		/* add the packet to the send queue if it's now full */
-		if (sp->remain <= 0 || (segment == 0 && !more)) {
+		if (sp->remain <= 0 ||
+		    (msg_data_left(msg) == 0 && !more)) {
 			struct rxrpc_connection *conn = call->conn;
 			uint32_t seq;
 			size_t pad;
@@ -697,7 +663,7 @@ static int rxrpc_send_data(struct kiocb *iocb,
 			sp->hdr.serviceId = conn->service_id;
 
 			sp->hdr.flags = conn->out_clientflag;
-			if (len == 0 && !more)
+			if (msg_data_left(msg) == 0 && !more)
 				sp->hdr.flags |= RXRPC_LAST_PACKET;
 			else if (CIRC_SPACE(call->acks_head, call->acks_tail,
 					    call->acks_winsz) > 1)
@@ -713,11 +679,10 @@ static int rxrpc_send_data(struct kiocb *iocb,
 
 			memcpy(skb->head, &sp->hdr,
 			       sizeof(struct rxrpc_header));
-			rxrpc_queue_packet(call, skb, segment == 0 && !more);
+			rxrpc_queue_packet(call, skb, !msg_data_left(msg) && !more);
 			skb = NULL;
 		}
-
-	} while (segment > 0);
+	} while (msg_data_left(msg) > 0);
 
 success:
 	ret = copied;
diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c
index e9aaa65c0778..b92beded7459 100644
--- a/net/rxrpc/ar-recvmsg.c
+++ b/net/rxrpc/ar-recvmsg.c
@@ -43,8 +43,8 @@ void rxrpc_remove_user_ID(struct rxrpc_sock *rx, struct rxrpc_call *call)
  * - we need to be careful about two or more threads calling recvmsg
  *   simultaneously
  */
-int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock,
-		  struct msghdr *msg, size_t len, int flags)
+int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+		  int flags)
 {
 	struct rxrpc_skb_priv *sp;
 	struct rxrpc_call *call = NULL, *continue_call = NULL;
@@ -87,7 +87,7 @@ int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock,
 		if (!skb) {
 			/* nothing remains on the queue */
 			if (copied &&
-			    (msg->msg_flags & MSG_PEEK || timeo == 0))
+			    (flags & MSG_PEEK || timeo == 0))
 				goto out;
 
 			/* wait for a message to turn up */
@@ -150,7 +150,7 @@ int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock,
 				       &call->conn->trans->peer->srx, len);
 				msg->msg_namelen = len;
 			}
-			sock_recv_ts_and_drops(msg, &rx->sk, skb);
+			sock_recv_timestamp(msg, &rx->sk, skb);
 		}
 
 		/* receive the message */
@@ -180,7 +180,7 @@ int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock,
 		if (copy > len - copied)
 			copy = len - copied;
 
-		ret = skb_copy_datagram_iovec(skb, offset, msg->msg_iov, copy);
+		ret = skb_copy_datagram_msg(skb, offset, msg, copy);
 
 		if (ret < 0)
 			goto copy_error;
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index a1a8e29e5fc9..2274e723a3df 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -22,8 +22,9 @@ menuconfig NET_SCHED
 	  This code is considered to be experimental.
 
 	  To administer these schedulers, you'll need the user-level utilities
-	  from the package iproute2+tc at <ftp://ftp.tux.org/pub/net/ip-routing/>.
-	  That package also contains some documentation; for more, check out
+	  from the package iproute2+tc at
+	  <https://www.kernel.org/pub/linux/utils/net/iproute2/>.  That package
+	  also contains some documentation; for more, check out
 	  <http://www.linuxfoundation.org/collaborate/workgroups/networking/iproute2>.
 
 	  This Quality of Service (QoS) support will enable you to use
@@ -336,7 +337,7 @@ config NET_SCH_PLUG
 	  of virtual machines by allowing the generated network output to be rolled
 	  back if needed.
 
-	  For more information, please refer to http://wiki.xensource.com/xenwiki/Remus
+	  For more information, please refer to <http://wiki.xenproject.org/wiki/Remus>
 
 	  Say Y here if you are using this kernel for Xen dom0 and
 	  want to protect Xen guests with Remus.
@@ -347,7 +348,7 @@ config NET_SCH_PLUG
 comment "Classification"
 
 config NET_CLS
-	boolean
+	bool
 
 config NET_CLS_BASIC
 	tristate "Elementary classification (BASIC)"
@@ -686,6 +687,41 @@ config NET_ACT_CSUM
 	  To compile this code as a module, choose M here: the
 	  module will be called act_csum.
 
+config NET_ACT_VLAN
+        tristate "Vlan manipulation"
+        depends on NET_CLS_ACT
+        ---help---
+	  Say Y here to push or pop vlan headers.
+
+	  If unsure, say N.
+
+	  To compile this code as a module, choose M here: the
+	  module will be called act_vlan.
+
+config NET_ACT_BPF
+        tristate "BPF based action"
+        depends on NET_CLS_ACT
+        ---help---
+	  Say Y here to execute BPF code on packets. The BPF code will decide
+	  if the packet should be dropped or not.
+
+	  If unsure, say N.
+
+	  To compile this code as a module, choose M here: the
+	  module will be called act_bpf.
+
+config NET_ACT_CONNMARK
+        tristate "Netfilter Connection Mark Retriever"
+        depends on NET_CLS_ACT && NETFILTER && IP_NF_IPTABLES
+        depends on NF_CONNTRACK && NF_CONNTRACK_MARK
+        ---help---
+	  Say Y here to allow retrieving of conn mark
+
+	  If unsure, say N.
+
+	  To compile this code as a module, choose M here: the
+	  module will be called act_connmark.
+
 config NET_CLS_IND
 	bool "Incoming device classification"
 	depends on NET_CLS_U32 || NET_CLS_FW
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 0a869a11f3e6..7ca7f4c1b8c2 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -16,6 +16,9 @@ obj-$(CONFIG_NET_ACT_PEDIT)	+= act_pedit.o
 obj-$(CONFIG_NET_ACT_SIMP)	+= act_simple.o
 obj-$(CONFIG_NET_ACT_SKBEDIT)	+= act_skbedit.o
 obj-$(CONFIG_NET_ACT_CSUM)	+= act_csum.o
+obj-$(CONFIG_NET_ACT_VLAN)	+= act_vlan.o
+obj-$(CONFIG_NET_ACT_BPF)	+= act_bpf.o
+obj-$(CONFIG_NET_ACT_CONNMARK)	+= act_connmark.o
 obj-$(CONFIG_NET_SCH_FIFO)	+= sch_fifo.o
 obj-$(CONFIG_NET_SCH_CBQ)	+= sch_cbq.o
 obj-$(CONFIG_NET_SCH_HTB)	+= sch_htb.o
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
new file mode 100644
index 000000000000..dc6a2d324bd8
--- /dev/null
+++ b/net/sched/act_bpf.c
@@ -0,0 +1,362 @@
+/*
+ * Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us>
+ *
+ * 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/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+#include <linux/rtnetlink.h>
+#include <linux/filter.h>
+#include <linux/bpf.h>
+
+#include <net/netlink.h>
+#include <net/pkt_sched.h>
+
+#include <linux/tc_act/tc_bpf.h>
+#include <net/tc_act/tc_bpf.h>
+
+#define BPF_TAB_MASK		15
+#define ACT_BPF_NAME_LEN	256
+
+struct tcf_bpf_cfg {
+	struct bpf_prog *filter;
+	struct sock_filter *bpf_ops;
+	char *bpf_name;
+	u32 bpf_fd;
+	u16 bpf_num_ops;
+};
+
+static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act,
+		   struct tcf_result *res)
+{
+	struct tcf_bpf *prog = act->priv;
+	int action, filter_res;
+
+	if (unlikely(!skb_mac_header_was_set(skb)))
+		return TC_ACT_UNSPEC;
+
+	spin_lock(&prog->tcf_lock);
+
+	prog->tcf_tm.lastuse = jiffies;
+	bstats_update(&prog->tcf_bstats, skb);
+
+	/* Needed here for accessing maps. */
+	rcu_read_lock();
+	filter_res = BPF_PROG_RUN(prog->filter, skb);
+	rcu_read_unlock();
+
+	/* A BPF program may overwrite the default action opcode.
+	 * Similarly as in cls_bpf, if filter_res == -1 we use the
+	 * default action specified from tc.
+	 *
+	 * In case a different well-known TC_ACT opcode has been
+	 * returned, it will overwrite the default one.
+	 *
+	 * For everything else that is unkown, TC_ACT_UNSPEC is
+	 * returned.
+	 */
+	switch (filter_res) {
+	case TC_ACT_PIPE:
+	case TC_ACT_RECLASSIFY:
+	case TC_ACT_OK:
+		action = filter_res;
+		break;
+	case TC_ACT_SHOT:
+		action = filter_res;
+		prog->tcf_qstats.drops++;
+		break;
+	case TC_ACT_UNSPEC:
+		action = prog->tcf_action;
+		break;
+	default:
+		action = TC_ACT_UNSPEC;
+		break;
+	}
+
+	spin_unlock(&prog->tcf_lock);
+	return action;
+}
+
+static bool tcf_bpf_is_ebpf(const struct tcf_bpf *prog)
+{
+	return !prog->bpf_ops;
+}
+
+static int tcf_bpf_dump_bpf_info(const struct tcf_bpf *prog,
+				 struct sk_buff *skb)
+{
+	struct nlattr *nla;
+
+	if (nla_put_u16(skb, TCA_ACT_BPF_OPS_LEN, prog->bpf_num_ops))
+		return -EMSGSIZE;
+
+	nla = nla_reserve(skb, TCA_ACT_BPF_OPS, prog->bpf_num_ops *
+			  sizeof(struct sock_filter));
+	if (nla == NULL)
+		return -EMSGSIZE;
+
+	memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla));
+
+	return 0;
+}
+
+static int tcf_bpf_dump_ebpf_info(const struct tcf_bpf *prog,
+				  struct sk_buff *skb)
+{
+	if (nla_put_u32(skb, TCA_ACT_BPF_FD, prog->bpf_fd))
+		return -EMSGSIZE;
+
+	if (prog->bpf_name &&
+	    nla_put_string(skb, TCA_ACT_BPF_NAME, prog->bpf_name))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+static int tcf_bpf_dump(struct sk_buff *skb, struct tc_action *act,
+			int bind, int ref)
+{
+	unsigned char *tp = skb_tail_pointer(skb);
+	struct tcf_bpf *prog = act->priv;
+	struct tc_act_bpf opt = {
+		.index   = prog->tcf_index,
+		.refcnt  = prog->tcf_refcnt - ref,
+		.bindcnt = prog->tcf_bindcnt - bind,
+		.action  = prog->tcf_action,
+	};
+	struct tcf_t tm;
+	int ret;
+
+	if (nla_put(skb, TCA_ACT_BPF_PARMS, sizeof(opt), &opt))
+		goto nla_put_failure;
+
+	if (tcf_bpf_is_ebpf(prog))
+		ret = tcf_bpf_dump_ebpf_info(prog, skb);
+	else
+		ret = tcf_bpf_dump_bpf_info(prog, skb);
+	if (ret)
+		goto nla_put_failure;
+
+	tm.install = jiffies_to_clock_t(jiffies - prog->tcf_tm.install);
+	tm.lastuse = jiffies_to_clock_t(jiffies - prog->tcf_tm.lastuse);
+	tm.expires = jiffies_to_clock_t(prog->tcf_tm.expires);
+
+	if (nla_put(skb, TCA_ACT_BPF_TM, sizeof(tm), &tm))
+		goto nla_put_failure;
+
+	return skb->len;
+
+nla_put_failure:
+	nlmsg_trim(skb, tp);
+	return -1;
+}
+
+static const struct nla_policy act_bpf_policy[TCA_ACT_BPF_MAX + 1] = {
+	[TCA_ACT_BPF_PARMS]	= { .len = sizeof(struct tc_act_bpf) },
+	[TCA_ACT_BPF_FD]	= { .type = NLA_U32 },
+	[TCA_ACT_BPF_NAME]	= { .type = NLA_NUL_STRING, .len = ACT_BPF_NAME_LEN },
+	[TCA_ACT_BPF_OPS_LEN]	= { .type = NLA_U16 },
+	[TCA_ACT_BPF_OPS]	= { .type = NLA_BINARY,
+				    .len = sizeof(struct sock_filter) * BPF_MAXINSNS },
+};
+
+static int tcf_bpf_init_from_ops(struct nlattr **tb, struct tcf_bpf_cfg *cfg)
+{
+	struct sock_filter *bpf_ops;
+	struct sock_fprog_kern fprog_tmp;
+	struct bpf_prog *fp;
+	u16 bpf_size, bpf_num_ops;
+	int ret;
+
+	bpf_num_ops = nla_get_u16(tb[TCA_ACT_BPF_OPS_LEN]);
+	if (bpf_num_ops	> BPF_MAXINSNS || bpf_num_ops == 0)
+		return -EINVAL;
+
+	bpf_size = bpf_num_ops * sizeof(*bpf_ops);
+	if (bpf_size != nla_len(tb[TCA_ACT_BPF_OPS]))
+		return -EINVAL;
+
+	bpf_ops = kzalloc(bpf_size, GFP_KERNEL);
+	if (bpf_ops == NULL)
+		return -ENOMEM;
+
+	memcpy(bpf_ops, nla_data(tb[TCA_ACT_BPF_OPS]), bpf_size);
+
+	fprog_tmp.len = bpf_num_ops;
+	fprog_tmp.filter = bpf_ops;
+
+	ret = bpf_prog_create(&fp, &fprog_tmp);
+	if (ret < 0) {
+		kfree(bpf_ops);
+		return ret;
+	}
+
+	cfg->bpf_ops = bpf_ops;
+	cfg->bpf_num_ops = bpf_num_ops;
+	cfg->filter = fp;
+
+	return 0;
+}
+
+static int tcf_bpf_init_from_efd(struct nlattr **tb, struct tcf_bpf_cfg *cfg)
+{
+	struct bpf_prog *fp;
+	char *name = NULL;
+	u32 bpf_fd;
+
+	bpf_fd = nla_get_u32(tb[TCA_ACT_BPF_FD]);
+
+	fp = bpf_prog_get(bpf_fd);
+	if (IS_ERR(fp))
+		return PTR_ERR(fp);
+
+	if (fp->type != BPF_PROG_TYPE_SCHED_ACT) {
+		bpf_prog_put(fp);
+		return -EINVAL;
+	}
+
+	if (tb[TCA_ACT_BPF_NAME]) {
+		name = kmemdup(nla_data(tb[TCA_ACT_BPF_NAME]),
+			       nla_len(tb[TCA_ACT_BPF_NAME]),
+			       GFP_KERNEL);
+		if (!name) {
+			bpf_prog_put(fp);
+			return -ENOMEM;
+		}
+	}
+
+	cfg->bpf_fd = bpf_fd;
+	cfg->bpf_name = name;
+	cfg->filter = fp;
+
+	return 0;
+}
+
+static int tcf_bpf_init(struct net *net, struct nlattr *nla,
+			struct nlattr *est, struct tc_action *act,
+			int replace, int bind)
+{
+	struct nlattr *tb[TCA_ACT_BPF_MAX + 1];
+	struct tc_act_bpf *parm;
+	struct tcf_bpf *prog;
+	struct tcf_bpf_cfg cfg;
+	bool is_bpf, is_ebpf;
+	int ret;
+
+	if (!nla)
+		return -EINVAL;
+
+	ret = nla_parse_nested(tb, TCA_ACT_BPF_MAX, nla, act_bpf_policy);
+	if (ret < 0)
+		return ret;
+
+	is_bpf = tb[TCA_ACT_BPF_OPS_LEN] && tb[TCA_ACT_BPF_OPS];
+	is_ebpf = tb[TCA_ACT_BPF_FD];
+
+	if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf) ||
+	    !tb[TCA_ACT_BPF_PARMS])
+		return -EINVAL;
+
+	parm = nla_data(tb[TCA_ACT_BPF_PARMS]);
+
+	memset(&cfg, 0, sizeof(cfg));
+
+	ret = is_bpf ? tcf_bpf_init_from_ops(tb, &cfg) :
+		       tcf_bpf_init_from_efd(tb, &cfg);
+	if (ret < 0)
+		return ret;
+
+	if (!tcf_hash_check(parm->index, act, bind)) {
+		ret = tcf_hash_create(parm->index, est, act,
+				      sizeof(*prog), bind);
+		if (ret < 0)
+			goto destroy_fp;
+
+		ret = ACT_P_CREATED;
+	} else {
+		/* Don't override defaults. */
+		if (bind)
+			goto destroy_fp;
+
+		tcf_hash_release(act, bind);
+		if (!replace) {
+			ret = -EEXIST;
+			goto destroy_fp;
+		}
+	}
+
+	prog = to_bpf(act);
+	spin_lock_bh(&prog->tcf_lock);
+
+	prog->bpf_ops = cfg.bpf_ops;
+	prog->bpf_name = cfg.bpf_name;
+
+	if (cfg.bpf_num_ops)
+		prog->bpf_num_ops = cfg.bpf_num_ops;
+	if (cfg.bpf_fd)
+		prog->bpf_fd = cfg.bpf_fd;
+
+	prog->tcf_action = parm->action;
+	prog->filter = cfg.filter;
+
+	spin_unlock_bh(&prog->tcf_lock);
+
+	if (ret == ACT_P_CREATED)
+		tcf_hash_insert(act);
+
+	return ret;
+
+destroy_fp:
+	if (is_ebpf)
+		bpf_prog_put(cfg.filter);
+	else
+		bpf_prog_destroy(cfg.filter);
+
+	kfree(cfg.bpf_ops);
+	kfree(cfg.bpf_name);
+
+	return ret;
+}
+
+static void tcf_bpf_cleanup(struct tc_action *act, int bind)
+{
+	const struct tcf_bpf *prog = act->priv;
+
+	if (tcf_bpf_is_ebpf(prog))
+		bpf_prog_put(prog->filter);
+	else
+		bpf_prog_destroy(prog->filter);
+}
+
+static struct tc_action_ops act_bpf_ops __read_mostly = {
+	.kind		=	"bpf",
+	.type		=	TCA_ACT_BPF,
+	.owner		=	THIS_MODULE,
+	.act		=	tcf_bpf,
+	.dump		=	tcf_bpf_dump,
+	.cleanup	=	tcf_bpf_cleanup,
+	.init		=	tcf_bpf_init,
+};
+
+static int __init bpf_init_module(void)
+{
+	return tcf_register_action(&act_bpf_ops, BPF_TAB_MASK);
+}
+
+static void __exit bpf_cleanup_module(void)
+{
+	tcf_unregister_action(&act_bpf_ops);
+}
+
+module_init(bpf_init_module);
+module_exit(bpf_cleanup_module);
+
+MODULE_AUTHOR("Jiri Pirko <jiri@resnulli.us>");
+MODULE_DESCRIPTION("TC BPF based action");
+MODULE_LICENSE("GPL v2");
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
new file mode 100644
index 000000000000..295d14bd6c67
--- /dev/null
+++ b/net/sched/act_connmark.c
@@ -0,0 +1,190 @@
+/*
+ * net/sched/act_connmark.c  netfilter connmark retriever action
+ * skb mark is over-written
+ *
+ * Copyright (c) 2011 Felix Fietkau <nbd@openwrt.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/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+#include <linux/rtnetlink.h>
+#include <linux/pkt_cls.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <net/netlink.h>
+#include <net/pkt_sched.h>
+#include <net/act_api.h>
+#include <uapi/linux/tc_act/tc_connmark.h>
+#include <net/tc_act/tc_connmark.h>
+
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_zones.h>
+
+#define CONNMARK_TAB_MASK     3
+
+static int tcf_connmark(struct sk_buff *skb, const struct tc_action *a,
+			struct tcf_result *res)
+{
+	const struct nf_conntrack_tuple_hash *thash;
+	struct nf_conntrack_tuple tuple;
+	enum ip_conntrack_info ctinfo;
+	struct tcf_connmark_info *ca = a->priv;
+	struct nf_conn *c;
+	int proto;
+
+	spin_lock(&ca->tcf_lock);
+	ca->tcf_tm.lastuse = jiffies;
+	bstats_update(&ca->tcf_bstats, skb);
+
+	if (skb->protocol == htons(ETH_P_IP)) {
+		if (skb->len < sizeof(struct iphdr))
+			goto out;
+
+		proto = NFPROTO_IPV4;
+	} else if (skb->protocol == htons(ETH_P_IPV6)) {
+		if (skb->len < sizeof(struct ipv6hdr))
+			goto out;
+
+		proto = NFPROTO_IPV6;
+	} else {
+		goto out;
+	}
+
+	c = nf_ct_get(skb, &ctinfo);
+	if (c) {
+		skb->mark = c->mark;
+		/* using overlimits stats to count how many packets marked */
+		ca->tcf_qstats.overlimits++;
+		goto out;
+	}
+
+	if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb),
+			       proto, &tuple))
+		goto out;
+
+	thash = nf_conntrack_find_get(dev_net(skb->dev), ca->zone, &tuple);
+	if (!thash)
+		goto out;
+
+	c = nf_ct_tuplehash_to_ctrack(thash);
+	/* using overlimits stats to count how many packets marked */
+	ca->tcf_qstats.overlimits++;
+	skb->mark = c->mark;
+	nf_ct_put(c);
+
+out:
+	spin_unlock(&ca->tcf_lock);
+	return ca->tcf_action;
+}
+
+static const struct nla_policy connmark_policy[TCA_CONNMARK_MAX + 1] = {
+	[TCA_CONNMARK_PARMS] = { .len = sizeof(struct tc_connmark) },
+};
+
+static int tcf_connmark_init(struct net *net, struct nlattr *nla,
+			     struct nlattr *est, struct tc_action *a,
+			     int ovr, int bind)
+{
+	struct nlattr *tb[TCA_CONNMARK_MAX + 1];
+	struct tcf_connmark_info *ci;
+	struct tc_connmark *parm;
+	int ret = 0;
+
+	if (!nla)
+		return -EINVAL;
+
+	ret = nla_parse_nested(tb, TCA_CONNMARK_MAX, nla, connmark_policy);
+	if (ret < 0)
+		return ret;
+
+	parm = nla_data(tb[TCA_CONNMARK_PARMS]);
+
+	if (!tcf_hash_check(parm->index, a, bind)) {
+		ret = tcf_hash_create(parm->index, est, a, sizeof(*ci), bind);
+		if (ret)
+			return ret;
+
+		ci = to_connmark(a);
+		ci->tcf_action = parm->action;
+		ci->zone = parm->zone;
+
+		tcf_hash_insert(a);
+		ret = ACT_P_CREATED;
+	} else {
+		ci = to_connmark(a);
+		if (bind)
+			return 0;
+		tcf_hash_release(a, bind);
+		if (!ovr)
+			return -EEXIST;
+		/* replacing action and zone */
+		ci->tcf_action = parm->action;
+		ci->zone = parm->zone;
+	}
+
+	return ret;
+}
+
+static inline int tcf_connmark_dump(struct sk_buff *skb, struct tc_action *a,
+				    int bind, int ref)
+{
+	unsigned char *b = skb_tail_pointer(skb);
+	struct tcf_connmark_info *ci = a->priv;
+
+	struct tc_connmark opt = {
+		.index   = ci->tcf_index,
+		.refcnt  = ci->tcf_refcnt - ref,
+		.bindcnt = ci->tcf_bindcnt - bind,
+		.action  = ci->tcf_action,
+		.zone   = ci->zone,
+	};
+	struct tcf_t t;
+
+	if (nla_put(skb, TCA_CONNMARK_PARMS, sizeof(opt), &opt))
+		goto nla_put_failure;
+
+	t.install = jiffies_to_clock_t(jiffies - ci->tcf_tm.install);
+	t.lastuse = jiffies_to_clock_t(jiffies - ci->tcf_tm.lastuse);
+	t.expires = jiffies_to_clock_t(ci->tcf_tm.expires);
+	if (nla_put(skb, TCA_CONNMARK_TM, sizeof(t), &t))
+		goto nla_put_failure;
+
+	return skb->len;
+nla_put_failure:
+	nlmsg_trim(skb, b);
+	return -1;
+}
+
+static struct tc_action_ops act_connmark_ops = {
+	.kind		=	"connmark",
+	.type		=	TCA_ACT_CONNMARK,
+	.owner		=	THIS_MODULE,
+	.act		=	tcf_connmark,
+	.dump		=	tcf_connmark_dump,
+	.init		=	tcf_connmark_init,
+};
+
+static int __init connmark_init_module(void)
+{
+	return tcf_register_action(&act_connmark_ops, CONNMARK_TAB_MASK);
+}
+
+static void __exit connmark_cleanup_module(void)
+{
+	tcf_unregister_action(&act_connmark_ops);
+}
+
+module_init(connmark_init_module);
+module_exit(connmark_cleanup_module);
+MODULE_AUTHOR("Felix Fietkau <nbd@openwrt.org>");
+MODULE_DESCRIPTION("Connection tracking mark restoring");
+MODULE_LICENSE("GPL");
+
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index edbf40dac709..4cd5cf1aedf8 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -509,7 +509,7 @@ static int tcf_csum(struct sk_buff *skb,
 	if (unlikely(action == TC_ACT_SHOT))
 		goto drop;
 
-	switch (skb->protocol) {
+	switch (tc_skb_protocol(skb)) {
 	case cpu_to_be16(ETH_P_IP):
 		if (!tcf_csum_ipv4(skb, update_flags))
 			goto drop;
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index d6bcbd9f7791..7fffc2272701 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -1,5 +1,5 @@
 /*
- * net/sched/gact.c	Generic actions
+ * net/sched/act_gact.c		Generic actions
  *
  *		This program is free software; you can redistribute it and/or
  *		modify it under the terms of the GNU General Public License
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 8a64a0734aee..cbc8dd7dd48a 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -1,5 +1,5 @@
 /*
- * net/sched/ipt.c     iptables target interface
+ * net/sched/act_ipt.c		iptables target interface
  *
  *TODO: Add other tables. For now we only support the ipv4 table targets
  *
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index eb48306033d9..3f63ceac8e01 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -1,5 +1,5 @@
 /*
- * net/sched/mirred.c	packet mirroring and redirect actions
+ * net/sched/act_mirred.c	packet mirroring and redirect actions
  *
  *		This program is free software; you can redistribute it and/or
  *		modify it under the terms of the GNU General Public License
@@ -157,7 +157,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
 
 	if (!(at & AT_EGRESS)) {
 		if (m->tcfm_ok_push)
-			skb_push(skb2, skb2->dev->hard_header_len);
+			skb_push(skb2, skb->mac_len);
 	}
 
 	/* mirror is always swallowed */
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 5f9bcb2e080b..59649d588d79 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -1,5 +1,5 @@
 /*
- * net/sched/pedit.c	Generic packet editor
+ * net/sched/act_pedit.c	Generic packet editor
  *
  *		This program is free software; you can redistribute it and/or
  *		modify it under the terms of the GNU General Public License
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 69791ca77a05..9a1c42a43f92 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -1,5 +1,5 @@
 /*
- * net/sched/police.c	Input police filter.
+ * net/sched/act_police.c	Input police filter
  *
  *		This program is free software; you can redistribute it and/or
  *		modify it under the terms of the GNU General Public License
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 992c2317ce88..6a8d9488613a 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -1,5 +1,5 @@
 /*
- * net/sched/simp.c	Simple example of an action
+ * net/sched/act_simple.c	Simple example of an action
  *
  *		This program is free software; you can redistribute it and/or
  *		modify it under the terms of the GNU General Public License
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
new file mode 100644
index 000000000000..d735ecf0b1a7
--- /dev/null
+++ b/net/sched/act_vlan.c
@@ -0,0 +1,207 @@
+/*
+ * Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us>
+ *
+ * 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/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+#include <linux/rtnetlink.h>
+#include <linux/if_vlan.h>
+#include <net/netlink.h>
+#include <net/pkt_sched.h>
+
+#include <linux/tc_act/tc_vlan.h>
+#include <net/tc_act/tc_vlan.h>
+
+#define VLAN_TAB_MASK     15
+
+static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a,
+		    struct tcf_result *res)
+{
+	struct tcf_vlan *v = a->priv;
+	int action;
+	int err;
+
+	spin_lock(&v->tcf_lock);
+	v->tcf_tm.lastuse = jiffies;
+	bstats_update(&v->tcf_bstats, skb);
+	action = v->tcf_action;
+
+	switch (v->tcfv_action) {
+	case TCA_VLAN_ACT_POP:
+		err = skb_vlan_pop(skb);
+		if (err)
+			goto drop;
+		break;
+	case TCA_VLAN_ACT_PUSH:
+		err = skb_vlan_push(skb, v->tcfv_push_proto, v->tcfv_push_vid);
+		if (err)
+			goto drop;
+		break;
+	default:
+		BUG();
+	}
+
+	goto unlock;
+
+drop:
+	action = TC_ACT_SHOT;
+	v->tcf_qstats.drops++;
+unlock:
+	spin_unlock(&v->tcf_lock);
+	return action;
+}
+
+static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = {
+	[TCA_VLAN_PARMS]		= { .len = sizeof(struct tc_vlan) },
+	[TCA_VLAN_PUSH_VLAN_ID]		= { .type = NLA_U16 },
+	[TCA_VLAN_PUSH_VLAN_PROTOCOL]	= { .type = NLA_U16 },
+};
+
+static int tcf_vlan_init(struct net *net, struct nlattr *nla,
+			 struct nlattr *est, struct tc_action *a,
+			 int ovr, int bind)
+{
+	struct nlattr *tb[TCA_VLAN_MAX + 1];
+	struct tc_vlan *parm;
+	struct tcf_vlan *v;
+	int action;
+	__be16 push_vid = 0;
+	__be16 push_proto = 0;
+	int ret = 0;
+	int err;
+
+	if (!nla)
+		return -EINVAL;
+
+	err = nla_parse_nested(tb, TCA_VLAN_MAX, nla, vlan_policy);
+	if (err < 0)
+		return err;
+
+	if (!tb[TCA_VLAN_PARMS])
+		return -EINVAL;
+	parm = nla_data(tb[TCA_VLAN_PARMS]);
+	switch (parm->v_action) {
+	case TCA_VLAN_ACT_POP:
+		break;
+	case TCA_VLAN_ACT_PUSH:
+		if (!tb[TCA_VLAN_PUSH_VLAN_ID])
+			return -EINVAL;
+		push_vid = nla_get_u16(tb[TCA_VLAN_PUSH_VLAN_ID]);
+		if (push_vid >= VLAN_VID_MASK)
+			return -ERANGE;
+
+		if (tb[TCA_VLAN_PUSH_VLAN_PROTOCOL]) {
+			push_proto = nla_get_be16(tb[TCA_VLAN_PUSH_VLAN_PROTOCOL]);
+			switch (push_proto) {
+			case htons(ETH_P_8021Q):
+			case htons(ETH_P_8021AD):
+				break;
+			default:
+				return -EPROTONOSUPPORT;
+			}
+		} else {
+			push_proto = htons(ETH_P_8021Q);
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+	action = parm->v_action;
+
+	if (!tcf_hash_check(parm->index, a, bind)) {
+		ret = tcf_hash_create(parm->index, est, a, sizeof(*v), bind);
+		if (ret)
+			return ret;
+
+		ret = ACT_P_CREATED;
+	} else {
+		if (bind)
+			return 0;
+		tcf_hash_release(a, bind);
+		if (!ovr)
+			return -EEXIST;
+	}
+
+	v = to_vlan(a);
+
+	spin_lock_bh(&v->tcf_lock);
+
+	v->tcfv_action = action;
+	v->tcfv_push_vid = push_vid;
+	v->tcfv_push_proto = push_proto;
+
+	v->tcf_action = parm->action;
+
+	spin_unlock_bh(&v->tcf_lock);
+
+	if (ret == ACT_P_CREATED)
+		tcf_hash_insert(a);
+	return ret;
+}
+
+static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a,
+			 int bind, int ref)
+{
+	unsigned char *b = skb_tail_pointer(skb);
+	struct tcf_vlan *v = a->priv;
+	struct tc_vlan opt = {
+		.index    = v->tcf_index,
+		.refcnt   = v->tcf_refcnt - ref,
+		.bindcnt  = v->tcf_bindcnt - bind,
+		.action   = v->tcf_action,
+		.v_action = v->tcfv_action,
+	};
+	struct tcf_t t;
+
+	if (nla_put(skb, TCA_VLAN_PARMS, sizeof(opt), &opt))
+		goto nla_put_failure;
+
+	if (v->tcfv_action == TCA_VLAN_ACT_PUSH &&
+	    (nla_put_u16(skb, TCA_VLAN_PUSH_VLAN_ID, v->tcfv_push_vid) ||
+	     nla_put_be16(skb, TCA_VLAN_PUSH_VLAN_PROTOCOL, v->tcfv_push_proto)))
+		goto nla_put_failure;
+
+	t.install = jiffies_to_clock_t(jiffies - v->tcf_tm.install);
+	t.lastuse = jiffies_to_clock_t(jiffies - v->tcf_tm.lastuse);
+	t.expires = jiffies_to_clock_t(v->tcf_tm.expires);
+	if (nla_put(skb, TCA_VLAN_TM, sizeof(t), &t))
+		goto nla_put_failure;
+	return skb->len;
+
+nla_put_failure:
+	nlmsg_trim(skb, b);
+	return -1;
+}
+
+static struct tc_action_ops act_vlan_ops = {
+	.kind		=	"vlan",
+	.type		=	TCA_ACT_VLAN,
+	.owner		=	THIS_MODULE,
+	.act		=	tcf_vlan,
+	.dump		=	tcf_vlan_dump,
+	.init		=	tcf_vlan_init,
+};
+
+static int __init vlan_init_module(void)
+{
+	return tcf_register_action(&act_vlan_ops, VLAN_TAB_MASK);
+}
+
+static void __exit vlan_cleanup_module(void)
+{
+	tcf_unregister_action(&act_vlan_ops);
+}
+
+module_init(vlan_init_module);
+module_exit(vlan_cleanup_module);
+
+MODULE_AUTHOR("Jiri Pirko <jiri@resnulli.us>");
+MODULE_DESCRIPTION("vlan manipulation actions");
+MODULE_LICENSE("GPL v2");
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index aad6a679fb13..a75864d93142 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -81,6 +81,11 @@ int unregister_tcf_proto_ops(struct tcf_proto_ops *ops)
 	struct tcf_proto_ops *t;
 	int rc = -ENOENT;
 
+	/* Wait for outstanding call_rcu()s, if any, from a
+	 * tcf_proto_ops's destroy() handler.
+	 */
+	rcu_barrier();
+
 	write_lock(&cls_mod_lock);
 	list_for_each_entry(t, &tcf_proto_base, head) {
 		if (t == ops) {
@@ -286,7 +291,7 @@ replay:
 			RCU_INIT_POINTER(*back, next);
 
 			tfilter_notify(net, skb, n, tp, fh, RTM_DELTFILTER);
-			tcf_destroy(tp);
+			tcf_destroy(tp, true);
 			err = 0;
 			goto errout;
 		}
@@ -301,14 +306,19 @@ replay:
 			err = -EEXIST;
 			if (n->nlmsg_flags & NLM_F_EXCL) {
 				if (tp_created)
-					tcf_destroy(tp);
+					tcf_destroy(tp, true);
 				goto errout;
 			}
 			break;
 		case RTM_DELTFILTER:
 			err = tp->ops->delete(tp, fh);
-			if (err == 0)
+			if (err == 0) {
+				struct tcf_proto *next = rtnl_dereference(tp->next);
+
 				tfilter_notify(net, skb, n, tp, fh, RTM_DELTFILTER);
+				if (tcf_destroy(tp, false))
+					RCU_INIT_POINTER(*back, next);
+			}
 			goto errout;
 		case RTM_GETTFILTER:
 			err = tfilter_notify(net, skb, n, tp, fh, RTM_NEWTFILTER);
@@ -329,7 +339,7 @@ replay:
 		tfilter_notify(net, skb, n, tp, fh, RTM_NEWTFILTER);
 	} else {
 		if (tp_created)
-			tcf_destroy(tp);
+			tcf_destroy(tp, true);
 	}
 
 errout:
@@ -556,8 +566,9 @@ void tcf_exts_change(struct tcf_proto *tp, struct tcf_exts *dst,
 }
 EXPORT_SYMBOL(tcf_exts_change);
 
-#define tcf_exts_first_act(ext) \
-		list_first_entry(&(exts)->actions, struct tc_action, list)
+#define tcf_exts_first_act(ext)					\
+	list_first_entry_or_null(&(exts)->actions,		\
+				 struct tc_action, list)
 
 int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts)
 {
@@ -603,7 +614,7 @@ int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts)
 {
 #ifdef CONFIG_NET_CLS_ACT
 	struct tc_action *a = tcf_exts_first_act(exts);
-	if (tcf_action_copy_stats(skb, a, 1) < 0)
+	if (a != NULL && tcf_action_copy_stats(skb, a, 1) < 0)
 		return -1;
 #endif
 	return 0;
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index cd61280941e5..0b8c3ace671f 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -65,17 +65,16 @@ static unsigned long basic_get(struct tcf_proto *tp, u32 handle)
 	if (head == NULL)
 		return 0UL;
 
-	list_for_each_entry(f, &head->flist, link)
-		if (f->handle == handle)
+	list_for_each_entry(f, &head->flist, link) {
+		if (f->handle == handle) {
 			l = (unsigned long) f;
+			break;
+		}
+	}
 
 	return l;
 }
 
-static void basic_put(struct tcf_proto *tp, unsigned long f)
-{
-}
-
 static int basic_init(struct tcf_proto *tp)
 {
 	struct basic_head *head;
@@ -97,11 +96,14 @@ static void basic_delete_filter(struct rcu_head *head)
 	kfree(f);
 }
 
-static void basic_destroy(struct tcf_proto *tp)
+static bool basic_destroy(struct tcf_proto *tp, bool force)
 {
 	struct basic_head *head = rtnl_dereference(tp->root);
 	struct basic_filter *f, *n;
 
+	if (!force && !list_empty(&head->flist))
+		return false;
+
 	list_for_each_entry_safe(f, n, &head->flist, link) {
 		list_del_rcu(&f->link);
 		tcf_unbind_filter(tp, &f->res);
@@ -109,22 +111,17 @@ static void basic_destroy(struct tcf_proto *tp)
 	}
 	RCU_INIT_POINTER(tp->root, NULL);
 	kfree_rcu(head, rcu);
+	return true;
 }
 
 static int basic_delete(struct tcf_proto *tp, unsigned long arg)
 {
-	struct basic_head *head = rtnl_dereference(tp->root);
-	struct basic_filter *t, *f = (struct basic_filter *) arg;
-
-	list_for_each_entry(t, &head->flist, link)
-		if (t == f) {
-			list_del_rcu(&t->link);
-			tcf_unbind_filter(tp, &t->res);
-			call_rcu(&t->rcu, basic_delete_filter);
-			return 0;
-		}
+	struct basic_filter *f = (struct basic_filter *) arg;
 
-	return -ENOENT;
+	list_del_rcu(&f->link);
+	tcf_unbind_filter(tp, &f->res);
+	call_rcu(&f->rcu, basic_delete_filter);
+	return 0;
 }
 
 static const struct nla_policy basic_policy[TCA_BASIC_MAX + 1] = {
@@ -188,10 +185,9 @@ static int basic_change(struct net *net, struct sk_buff *in_skb,
 			return -EINVAL;
 	}
 
-	err = -ENOBUFS;
 	fnew = kzalloc(sizeof(*fnew), GFP_KERNEL);
-	if (fnew == NULL)
-		goto errout;
+	if (!fnew)
+		return -ENOBUFS;
 
 	tcf_exts_init(&fnew->exts, TCA_BASIC_ACT, TCA_BASIC_POLICE);
 	err = -EINVAL;
@@ -293,7 +289,6 @@ static struct tcf_proto_ops cls_basic_ops __read_mostly = {
 	.init		=	basic_init,
 	.destroy	=	basic_destroy,
 	.get		=	basic_get,
-	.put		=	basic_put,
 	.change		=	basic_change,
 	.delete		=	basic_delete,
 	.walk		=	basic_walk,
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index eed49d1d0878..91bd9c19471d 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -16,6 +16,8 @@
 #include <linux/types.h>
 #include <linux/skbuff.h>
 #include <linux/filter.h>
+#include <linux/bpf.h>
+
 #include <net/rtnetlink.h>
 #include <net/pkt_cls.h>
 #include <net/sock.h>
@@ -24,6 +26,8 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Daniel Borkmann <dborkman@redhat.com>");
 MODULE_DESCRIPTION("TC BPF based classifier");
 
+#define CLS_BPF_NAME_LEN	256
+
 struct cls_bpf_head {
 	struct list_head plist;
 	u32 hgen;
@@ -32,18 +36,24 @@ struct cls_bpf_head {
 
 struct cls_bpf_prog {
 	struct bpf_prog *filter;
-	struct sock_filter *bpf_ops;
-	struct tcf_exts exts;
-	struct tcf_result res;
 	struct list_head link;
+	struct tcf_result res;
+	struct tcf_exts exts;
 	u32 handle;
-	u16 bpf_len;
+	union {
+		u32 bpf_fd;
+		u16 bpf_num_ops;
+	};
+	struct sock_filter *bpf_ops;
+	const char *bpf_name;
 	struct tcf_proto *tp;
 	struct rcu_head rcu;
 };
 
 static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = {
 	[TCA_BPF_CLASSID]	= { .type = NLA_U32 },
+	[TCA_BPF_FD]		= { .type = NLA_U32 },
+	[TCA_BPF_NAME]		= { .type = NLA_NUL_STRING, .len = CLS_BPF_NAME_LEN },
 	[TCA_BPF_OPS_LEN]	= { .type = NLA_U16 },
 	[TCA_BPF_OPS]		= { .type = NLA_BINARY,
 				    .len = sizeof(struct sock_filter) * BPF_MAXINSNS },
@@ -54,8 +64,13 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 {
 	struct cls_bpf_head *head = rcu_dereference_bh(tp->root);
 	struct cls_bpf_prog *prog;
-	int ret;
+	int ret = -1;
+
+	if (unlikely(!skb_mac_header_was_set(skb)))
+		return -1;
 
+	/* Needed here for accessing maps. */
+	rcu_read_lock();
 	list_for_each_entry_rcu(prog, &head->plist, link) {
 		int filter_res = BPF_PROG_RUN(prog->filter, skb);
 
@@ -70,10 +85,16 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 		if (ret < 0)
 			continue;
 
-		return ret;
+		break;
 	}
+	rcu_read_unlock();
 
-	return -1;
+	return ret;
+}
+
+static bool cls_bpf_is_ebpf(const struct cls_bpf_prog *prog)
+{
+	return !prog->bpf_ops;
 }
 
 static int cls_bpf_init(struct tcf_proto *tp)
@@ -94,8 +115,12 @@ static void cls_bpf_delete_prog(struct tcf_proto *tp, struct cls_bpf_prog *prog)
 {
 	tcf_exts_destroy(&prog->exts);
 
-	bpf_prog_destroy(prog->filter);
+	if (cls_bpf_is_ebpf(prog))
+		bpf_prog_put(prog->filter);
+	else
+		bpf_prog_destroy(prog->filter);
 
+	kfree(prog->bpf_name);
 	kfree(prog->bpf_ops);
 	kfree(prog);
 }
@@ -109,26 +134,23 @@ static void __cls_bpf_delete_prog(struct rcu_head *rcu)
 
 static int cls_bpf_delete(struct tcf_proto *tp, unsigned long arg)
 {
-	struct cls_bpf_head *head = rtnl_dereference(tp->root);
-	struct cls_bpf_prog *prog, *todel = (struct cls_bpf_prog *) arg;
+	struct cls_bpf_prog *prog = (struct cls_bpf_prog *) arg;
 
-	list_for_each_entry(prog, &head->plist, link) {
-		if (prog == todel) {
-			list_del_rcu(&prog->link);
-			tcf_unbind_filter(tp, &prog->res);
-			call_rcu(&prog->rcu, __cls_bpf_delete_prog);
-			return 0;
-		}
-	}
+	list_del_rcu(&prog->link);
+	tcf_unbind_filter(tp, &prog->res);
+	call_rcu(&prog->rcu, __cls_bpf_delete_prog);
 
-	return -ENOENT;
+	return 0;
 }
 
-static void cls_bpf_destroy(struct tcf_proto *tp)
+static bool cls_bpf_destroy(struct tcf_proto *tp, bool force)
 {
 	struct cls_bpf_head *head = rtnl_dereference(tp->root);
 	struct cls_bpf_prog *prog, *tmp;
 
+	if (!force && !list_empty(&head->plist))
+		return false;
+
 	list_for_each_entry_safe(prog, tmp, &head->plist, link) {
 		list_del_rcu(&prog->link);
 		tcf_unbind_filter(tp, &prog->res);
@@ -137,6 +159,7 @@ static void cls_bpf_destroy(struct tcf_proto *tp)
 
 	RCU_INIT_POINTER(tp->root, NULL);
 	kfree_rcu(head, rcu);
+	return true;
 }
 
 static unsigned long cls_bpf_get(struct tcf_proto *tp, u32 handle)
@@ -148,7 +171,7 @@ static unsigned long cls_bpf_get(struct tcf_proto *tp, u32 handle)
 	if (head == NULL)
 		return 0UL;
 
-	list_for_each_entry_rcu(prog, &head->plist, link) {
+	list_for_each_entry(prog, &head->plist, link) {
 		if (prog->handle == handle) {
 			ret = (unsigned long) prog;
 			break;
@@ -158,8 +181,84 @@ static unsigned long cls_bpf_get(struct tcf_proto *tp, u32 handle)
 	return ret;
 }
 
-static void cls_bpf_put(struct tcf_proto *tp, unsigned long f)
+static int cls_bpf_prog_from_ops(struct nlattr **tb,
+				 struct cls_bpf_prog *prog, u32 classid)
+{
+	struct sock_filter *bpf_ops;
+	struct sock_fprog_kern fprog_tmp;
+	struct bpf_prog *fp;
+	u16 bpf_size, bpf_num_ops;
+	int ret;
+
+	bpf_num_ops = nla_get_u16(tb[TCA_BPF_OPS_LEN]);
+	if (bpf_num_ops > BPF_MAXINSNS || bpf_num_ops == 0)
+		return -EINVAL;
+
+	bpf_size = bpf_num_ops * sizeof(*bpf_ops);
+	if (bpf_size != nla_len(tb[TCA_BPF_OPS]))
+		return -EINVAL;
+
+	bpf_ops = kzalloc(bpf_size, GFP_KERNEL);
+	if (bpf_ops == NULL)
+		return -ENOMEM;
+
+	memcpy(bpf_ops, nla_data(tb[TCA_BPF_OPS]), bpf_size);
+
+	fprog_tmp.len = bpf_num_ops;
+	fprog_tmp.filter = bpf_ops;
+
+	ret = bpf_prog_create(&fp, &fprog_tmp);
+	if (ret < 0) {
+		kfree(bpf_ops);
+		return ret;
+	}
+
+	prog->bpf_ops = bpf_ops;
+	prog->bpf_num_ops = bpf_num_ops;
+	prog->bpf_name = NULL;
+
+	prog->filter = fp;
+	prog->res.classid = classid;
+
+	return 0;
+}
+
+static int cls_bpf_prog_from_efd(struct nlattr **tb,
+				 struct cls_bpf_prog *prog, u32 classid)
 {
+	struct bpf_prog *fp;
+	char *name = NULL;
+	u32 bpf_fd;
+
+	bpf_fd = nla_get_u32(tb[TCA_BPF_FD]);
+
+	fp = bpf_prog_get(bpf_fd);
+	if (IS_ERR(fp))
+		return PTR_ERR(fp);
+
+	if (fp->type != BPF_PROG_TYPE_SCHED_CLS) {
+		bpf_prog_put(fp);
+		return -EINVAL;
+	}
+
+	if (tb[TCA_BPF_NAME]) {
+		name = kmemdup(nla_data(tb[TCA_BPF_NAME]),
+			       nla_len(tb[TCA_BPF_NAME]),
+			       GFP_KERNEL);
+		if (!name) {
+			bpf_prog_put(fp);
+			return -ENOMEM;
+		}
+	}
+
+	prog->bpf_ops = NULL;
+	prog->bpf_fd = bpf_fd;
+	prog->bpf_name = name;
+
+	prog->filter = fp;
+	prog->res.classid = classid;
+
+	return 0;
 }
 
 static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp,
@@ -167,15 +266,16 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp,
 				   unsigned long base, struct nlattr **tb,
 				   struct nlattr *est, bool ovr)
 {
-	struct sock_filter *bpf_ops;
 	struct tcf_exts exts;
-	struct sock_fprog_kern tmp;
-	struct bpf_prog *fp;
-	u16 bpf_size, bpf_len;
+	bool is_bpf, is_ebpf;
 	u32 classid;
 	int ret;
 
-	if (!tb[TCA_BPF_OPS_LEN] || !tb[TCA_BPF_OPS] || !tb[TCA_BPF_CLASSID])
+	is_bpf = tb[TCA_BPF_OPS_LEN] && tb[TCA_BPF_OPS];
+	is_ebpf = tb[TCA_BPF_FD];
+
+	if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf) ||
+	    !tb[TCA_BPF_CLASSID])
 		return -EINVAL;
 
 	tcf_exts_init(&exts, TCA_BPF_ACT, TCA_BPF_POLICE);
@@ -184,57 +284,39 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp,
 		return ret;
 
 	classid = nla_get_u32(tb[TCA_BPF_CLASSID]);
-	bpf_len = nla_get_u16(tb[TCA_BPF_OPS_LEN]);
-	if (bpf_len > BPF_MAXINSNS || bpf_len == 0) {
-		ret = -EINVAL;
-		goto errout;
-	}
 
-	bpf_size = bpf_len * sizeof(*bpf_ops);
-	bpf_ops = kzalloc(bpf_size, GFP_KERNEL);
-	if (bpf_ops == NULL) {
-		ret = -ENOMEM;
-		goto errout;
+	ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog, classid) :
+		       cls_bpf_prog_from_efd(tb, prog, classid);
+	if (ret < 0) {
+		tcf_exts_destroy(&exts);
+		return ret;
 	}
 
-	memcpy(bpf_ops, nla_data(tb[TCA_BPF_OPS]), bpf_size);
-
-	tmp.len = bpf_len;
-	tmp.filter = bpf_ops;
-
-	ret = bpf_prog_create(&fp, &tmp);
-	if (ret)
-		goto errout_free;
-
-	prog->bpf_len = bpf_len;
-	prog->bpf_ops = bpf_ops;
-	prog->filter = fp;
-	prog->res.classid = classid;
-
 	tcf_bind_filter(tp, &prog->res, base);
 	tcf_exts_change(tp, &prog->exts, &exts);
 
 	return 0;
-errout_free:
-	kfree(bpf_ops);
-errout:
-	tcf_exts_destroy(&exts);
-	return ret;
 }
 
 static u32 cls_bpf_grab_new_handle(struct tcf_proto *tp,
 				   struct cls_bpf_head *head)
 {
 	unsigned int i = 0x80000000;
+	u32 handle;
 
 	do {
 		if (++head->hgen == 0x7FFFFFFF)
 			head->hgen = 1;
 	} while (--i > 0 && cls_bpf_get(tp, head->hgen));
-	if (i == 0)
+
+	if (unlikely(i == 0)) {
 		pr_err("Insufficient number of handles\n");
+		handle = 0;
+	} else {
+		handle = head->hgen;
+	}
 
-	return i;
+	return handle;
 }
 
 static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
@@ -297,11 +379,43 @@ errout:
 	return ret;
 }
 
+static int cls_bpf_dump_bpf_info(const struct cls_bpf_prog *prog,
+				 struct sk_buff *skb)
+{
+	struct nlattr *nla;
+
+	if (nla_put_u16(skb, TCA_BPF_OPS_LEN, prog->bpf_num_ops))
+		return -EMSGSIZE;
+
+	nla = nla_reserve(skb, TCA_BPF_OPS, prog->bpf_num_ops *
+			  sizeof(struct sock_filter));
+	if (nla == NULL)
+		return -EMSGSIZE;
+
+	memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla));
+
+	return 0;
+}
+
+static int cls_bpf_dump_ebpf_info(const struct cls_bpf_prog *prog,
+				  struct sk_buff *skb)
+{
+	if (nla_put_u32(skb, TCA_BPF_FD, prog->bpf_fd))
+		return -EMSGSIZE;
+
+	if (prog->bpf_name &&
+	    nla_put_string(skb, TCA_BPF_NAME, prog->bpf_name))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
 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;
-	struct nlattr *nest, *nla;
+	struct nlattr *nest;
+	int ret;
 
 	if (prog == NULL)
 		return skb->len;
@@ -314,16 +428,14 @@ static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 
 	if (nla_put_u32(skb, TCA_BPF_CLASSID, prog->res.classid))
 		goto nla_put_failure;
-	if (nla_put_u16(skb, TCA_BPF_OPS_LEN, prog->bpf_len))
-		goto nla_put_failure;
 
-	nla = nla_reserve(skb, TCA_BPF_OPS, prog->bpf_len *
-			  sizeof(struct sock_filter));
-	if (nla == NULL)
+	if (cls_bpf_is_ebpf(prog))
+		ret = cls_bpf_dump_ebpf_info(prog, skb);
+	else
+		ret = cls_bpf_dump_bpf_info(prog, skb);
+	if (ret)
 		goto nla_put_failure;
 
-	memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla));
-
 	if (tcf_exts_dump(skb, &prog->exts) < 0)
 		goto nla_put_failure;
 
@@ -344,7 +456,7 @@ static void cls_bpf_walk(struct tcf_proto *tp, struct tcf_walker *arg)
 	struct cls_bpf_head *head = rtnl_dereference(tp->root);
 	struct cls_bpf_prog *prog;
 
-	list_for_each_entry_rcu(prog, &head->plist, link) {
+	list_for_each_entry(prog, &head->plist, link) {
 		if (arg->count < arg->skip)
 			goto skip;
 		if (arg->fn(tp, (unsigned long) prog, arg) < 0) {
@@ -363,7 +475,6 @@ static struct tcf_proto_ops cls_bpf_ops __read_mostly = {
 	.init		=	cls_bpf_init,
 	.destroy	=	cls_bpf_destroy,
 	.get		=	cls_bpf_get,
-	.put		=	cls_bpf_put,
 	.change		=	cls_bpf_change,
 	.delete		=	cls_bpf_delete,
 	.walk		=	cls_bpf_walk,
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index d61a801222c1..ea611b216412 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -67,10 +67,6 @@ static unsigned long cls_cgroup_get(struct tcf_proto *tp, u32 handle)
 	return 0UL;
 }
 
-static void cls_cgroup_put(struct tcf_proto *tp, unsigned long f)
-{
-}
-
 static int cls_cgroup_init(struct tcf_proto *tp)
 {
 	return 0;
@@ -117,11 +113,7 @@ static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb,
 		return -ENOBUFS;
 
 	tcf_exts_init(&new->exts, TCA_CGROUP_ACT, TCA_CGROUP_POLICE);
-	if (head)
-		new->handle = head->handle;
-	else
-		new->handle = handle;
-
+	new->handle = handle;
 	new->tp = tp;
 	err = nla_parse_nested(tb, TCA_CGROUP_MAX, tca[TCA_OPTIONS],
 			       cgroup_policy);
@@ -151,14 +143,18 @@ errout:
 	return err;
 }
 
-static void cls_cgroup_destroy(struct tcf_proto *tp)
+static bool cls_cgroup_destroy(struct tcf_proto *tp, bool force)
 {
 	struct cls_cgroup_head *head = rtnl_dereference(tp->root);
 
+	if (!force)
+		return false;
+
 	if (head) {
 		RCU_INIT_POINTER(tp->root, NULL);
 		call_rcu(&head->rcu, cls_cgroup_destroy_rcu);
 	}
+	return true;
 }
 
 static int cls_cgroup_delete(struct tcf_proto *tp, unsigned long arg)
@@ -185,7 +181,6 @@ static int cls_cgroup_dump(struct net *net, struct tcf_proto *tp, unsigned long
 			   struct sk_buff *skb, struct tcmsg *t)
 {
 	struct cls_cgroup_head *head = rtnl_dereference(tp->root);
-	unsigned char *b = skb_tail_pointer(skb);
 	struct nlattr *nest;
 
 	t->tcm_handle = head->handle;
@@ -206,7 +201,7 @@ static int cls_cgroup_dump(struct net *net, struct tcf_proto *tp, unsigned long
 	return skb->len;
 
 nla_put_failure:
-	nlmsg_trim(skb, b);
+	nla_nest_cancel(skb, nest);
 	return -1;
 }
 
@@ -217,7 +212,6 @@ static struct tcf_proto_ops cls_cgroup_ops __read_mostly = {
 	.classify	=	cls_cgroup_classify,
 	.destroy	=	cls_cgroup_destroy,
 	.get		=	cls_cgroup_get,
-	.put		=	cls_cgroup_put,
 	.delete		=	cls_cgroup_delete,
 	.walk		=	cls_cgroup_walk,
 	.dump		=	cls_cgroup_dump,
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 4ac515f2a6ce..a620c4e288a5 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -77,7 +77,7 @@ static u32 flow_get_dst(const struct sk_buff *skb, const struct flow_keys *flow)
 {
 	if (flow->dst)
 		return ntohl(flow->dst);
-	return addr_fold(skb_dst(skb)) ^ (__force u16)skb->protocol;
+	return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb);
 }
 
 static u32 flow_get_proto(const struct sk_buff *skb, const struct flow_keys *flow)
@@ -98,7 +98,7 @@ static u32 flow_get_proto_dst(const struct sk_buff *skb, const struct flow_keys
 	if (flow->ports)
 		return ntohs(flow->port16[1]);
 
-	return addr_fold(skb_dst(skb)) ^ (__force u16)skb->protocol;
+	return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb);
 }
 
 static u32 flow_get_iif(const struct sk_buff *skb)
@@ -144,7 +144,7 @@ static u32 flow_get_nfct(const struct sk_buff *skb)
 
 static u32 flow_get_nfct_src(const struct sk_buff *skb, const struct flow_keys *flow)
 {
-	switch (skb->protocol) {
+	switch (tc_skb_protocol(skb)) {
 	case htons(ETH_P_IP):
 		return ntohl(CTTUPLE(skb, src.u3.ip));
 	case htons(ETH_P_IPV6):
@@ -156,7 +156,7 @@ fallback:
 
 static u32 flow_get_nfct_dst(const struct sk_buff *skb, const struct flow_keys *flow)
 {
-	switch (skb->protocol) {
+	switch (tc_skb_protocol(skb)) {
 	case htons(ETH_P_IP):
 		return ntohl(CTTUPLE(skb, dst.u3.ip));
 	case htons(ETH_P_IPV6):
@@ -426,10 +426,7 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
 			goto err2;
 
 		/* Copy fold into fnew */
-		fnew->handle = fold->handle;
-		fnew->keymask = fold->keymask;
 		fnew->tp = fold->tp;
-
 		fnew->handle = fold->handle;
 		fnew->nkeys = fold->nkeys;
 		fnew->keymask = fold->keymask;
@@ -560,17 +557,21 @@ static int flow_init(struct tcf_proto *tp)
 	return 0;
 }
 
-static void flow_destroy(struct tcf_proto *tp)
+static bool flow_destroy(struct tcf_proto *tp, bool force)
 {
 	struct flow_head *head = rtnl_dereference(tp->root);
 	struct flow_filter *f, *next;
 
+	if (!force && !list_empty(&head->filters))
+		return false;
+
 	list_for_each_entry_safe(f, next, &head->filters, list) {
 		list_del_rcu(&f->list);
 		call_rcu(&f->rcu, flow_destroy_filter);
 	}
 	RCU_INIT_POINTER(tp->root, NULL);
 	kfree_rcu(head, rcu);
+	return true;
 }
 
 static unsigned long flow_get(struct tcf_proto *tp, u32 handle)
@@ -578,16 +579,12 @@ static unsigned long flow_get(struct tcf_proto *tp, u32 handle)
 	struct flow_head *head = rtnl_dereference(tp->root);
 	struct flow_filter *f;
 
-	list_for_each_entry_rcu(f, &head->filters, list)
+	list_for_each_entry(f, &head->filters, list)
 		if (f->handle == handle)
 			return (unsigned long)f;
 	return 0;
 }
 
-static void flow_put(struct tcf_proto *tp, unsigned long f)
-{
-}
-
 static int flow_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 		     struct sk_buff *skb, struct tcmsg *t)
 {
@@ -645,7 +642,7 @@ static int flow_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 	return skb->len;
 
 nla_put_failure:
-	nlmsg_trim(skb, nest);
+	nla_nest_cancel(skb, nest);
 	return -1;
 }
 
@@ -654,7 +651,7 @@ static void flow_walk(struct tcf_proto *tp, struct tcf_walker *arg)
 	struct flow_head *head = rtnl_dereference(tp->root);
 	struct flow_filter *f;
 
-	list_for_each_entry_rcu(f, &head->filters, list) {
+	list_for_each_entry(f, &head->filters, list) {
 		if (arg->count < arg->skip)
 			goto skip;
 		if (arg->fn(tp, (unsigned long)f, arg) < 0) {
@@ -674,7 +671,6 @@ static struct tcf_proto_ops cls_flow_ops __read_mostly = {
 	.change		= flow_change,
 	.delete		= flow_delete,
 	.get		= flow_get,
-	.put		= flow_put,
 	.dump		= flow_dump,
 	.walk		= flow_walk,
 	.owner		= THIS_MODULE,
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index dbfdfd1f1a9f..715e01e5910a 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -33,6 +33,7 @@
 
 struct fw_head {
 	u32			mask;
+	bool			mask_set;
 	struct fw_filter __rcu	*ht[HTSIZE];
 	struct rcu_head		rcu;
 };
@@ -111,12 +112,16 @@ static unsigned long fw_get(struct tcf_proto *tp, u32 handle)
 	return 0;
 }
 
-static void fw_put(struct tcf_proto *tp, unsigned long f)
-{
-}
-
 static int fw_init(struct tcf_proto *tp)
 {
+	struct fw_head *head;
+
+	head = kzalloc(sizeof(struct fw_head), GFP_KERNEL);
+	if (head == NULL)
+		return -ENOBUFS;
+
+	head->mask_set = false;
+	rcu_assign_pointer(tp->root, head);
 	return 0;
 }
 
@@ -128,14 +133,20 @@ static void fw_delete_filter(struct rcu_head *head)
 	kfree(f);
 }
 
-static void fw_destroy(struct tcf_proto *tp)
+static bool fw_destroy(struct tcf_proto *tp, bool force)
 {
 	struct fw_head *head = rtnl_dereference(tp->root);
 	struct fw_filter *f;
 	int h;
 
 	if (head == NULL)
-		return;
+		return true;
+
+	if (!force) {
+		for (h = 0; h < HTSIZE; h++)
+			if (rcu_access_pointer(head->ht[h]))
+				return false;
+	}
 
 	for (h = 0; h < HTSIZE; h++) {
 		while ((f = rtnl_dereference(head->ht[h])) != NULL) {
@@ -147,6 +158,7 @@ static void fw_destroy(struct tcf_proto *tp)
 	}
 	RCU_INIT_POINTER(tp->root, NULL);
 	kfree_rcu(head, rcu);
+	return true;
 }
 
 static int fw_delete(struct tcf_proto *tp, unsigned long arg)
@@ -290,17 +302,11 @@ static int fw_change(struct net *net, struct sk_buff *in_skb,
 	if (!handle)
 		return -EINVAL;
 
-	if (head == NULL) {
-		u32 mask = 0xFFFFFFFF;
+	if (!head->mask_set) {
+		head->mask = 0xFFFFFFFF;
 		if (tb[TCA_FW_MASK])
-			mask = nla_get_u32(tb[TCA_FW_MASK]);
-
-		head = kzalloc(sizeof(struct fw_head), GFP_KERNEL);
-		if (head == NULL)
-			return -ENOBUFS;
-		head->mask = mask;
-
-		rcu_assign_pointer(tp->root, head);
+			head->mask = nla_get_u32(tb[TCA_FW_MASK]);
+		head->mask_set = true;
 	}
 
 	f = kzalloc(sizeof(struct fw_filter), GFP_KERNEL);
@@ -360,7 +366,6 @@ static int fw_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 {
 	struct fw_head *head = rtnl_dereference(tp->root);
 	struct fw_filter *f = (struct fw_filter *)fh;
-	unsigned char *b = skb_tail_pointer(skb);
 	struct nlattr *nest;
 
 	if (f == NULL)
@@ -401,7 +406,7 @@ static int fw_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 	return skb->len;
 
 nla_put_failure:
-	nlmsg_trim(skb, b);
+	nla_nest_cancel(skb, nest);
 	return -1;
 }
 
@@ -411,7 +416,6 @@ static struct tcf_proto_ops cls_fw_ops __read_mostly = {
 	.init		=	fw_init,
 	.destroy	=	fw_destroy,
 	.get		=	fw_get,
-	.put		=	fw_put,
 	.change		=	fw_change,
 	.delete		=	fw_delete,
 	.walk		=	fw_walk,
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index 109a329b7198..08a3b0a6f5ab 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -256,12 +256,15 @@ static unsigned long route4_get(struct tcf_proto *tp, u32 handle)
 	return 0;
 }
 
-static void route4_put(struct tcf_proto *tp, unsigned long f)
-{
-}
-
 static int route4_init(struct tcf_proto *tp)
 {
+	struct route4_head *head;
+
+	head = kzalloc(sizeof(struct route4_head), GFP_KERNEL);
+	if (head == NULL)
+		return -ENOBUFS;
+
+	rcu_assign_pointer(tp->root, head);
 	return 0;
 }
 
@@ -274,13 +277,20 @@ route4_delete_filter(struct rcu_head *head)
 	kfree(f);
 }
 
-static void route4_destroy(struct tcf_proto *tp)
+static bool route4_destroy(struct tcf_proto *tp, bool force)
 {
 	struct route4_head *head = rtnl_dereference(tp->root);
 	int h1, h2;
 
 	if (head == NULL)
-		return;
+		return true;
+
+	if (!force) {
+		for (h1 = 0; h1 <= 256; h1++) {
+			if (rcu_access_pointer(head->table[h1]))
+				return false;
+		}
+	}
 
 	for (h1 = 0; h1 <= 256; h1++) {
 		struct route4_bucket *b;
@@ -305,6 +315,7 @@ static void route4_destroy(struct tcf_proto *tp)
 	}
 	RCU_INIT_POINTER(tp->root, NULL);
 	kfree_rcu(head, rcu);
+	return true;
 }
 
 static int route4_delete(struct tcf_proto *tp, unsigned long arg)
@@ -488,13 +499,6 @@ static int route4_change(struct net *net, struct sk_buff *in_skb,
 			return -EINVAL;
 
 	err = -ENOBUFS;
-	if (head == NULL) {
-		head = kzalloc(sizeof(struct route4_head), GFP_KERNEL);
-		if (head == NULL)
-			goto errout;
-		rcu_assign_pointer(tp->root, head);
-	}
-
 	f = kzalloc(sizeof(struct route4_filter), GFP_KERNEL);
 	if (!f)
 		goto errout;
@@ -597,7 +601,6 @@ 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;
-	unsigned char *b = skb_tail_pointer(skb);
 	struct nlattr *nest;
 	u32 id;
 
@@ -639,7 +642,7 @@ static int route4_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 	return skb->len;
 
 nla_put_failure:
-	nlmsg_trim(skb, b);
+	nla_nest_cancel(skb, nest);
 	return -1;
 }
 
@@ -649,7 +652,6 @@ static struct tcf_proto_ops cls_route4_ops __read_mostly = {
 	.init		=	route4_init,
 	.destroy	=	route4_destroy,
 	.get		=	route4_get,
-	.put		=	route4_put,
 	.change		=	route4_change,
 	.delete		=	route4_delete,
 	.walk		=	route4_walk,
diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
index 6bb55f277a5a..02fa82792dab 100644
--- a/net/sched/cls_rsvp.h
+++ b/net/sched/cls_rsvp.h
@@ -271,10 +271,6 @@ static unsigned long rsvp_get(struct tcf_proto *tp, u32 handle)
 	return 0;
 }
 
-static void rsvp_put(struct tcf_proto *tp, unsigned long f)
-{
-}
-
 static int rsvp_init(struct tcf_proto *tp)
 {
 	struct rsvp_head *data;
@@ -295,13 +291,20 @@ rsvp_delete_filter(struct tcf_proto *tp, struct rsvp_filter *f)
 	kfree_rcu(f, rcu);
 }
 
-static void rsvp_destroy(struct tcf_proto *tp)
+static bool rsvp_destroy(struct tcf_proto *tp, bool force)
 {
 	struct rsvp_head *data = rtnl_dereference(tp->root);
 	int h1, h2;
 
 	if (data == NULL)
-		return;
+		return true;
+
+	if (!force) {
+		for (h1 = 0; h1 < 256; h1++) {
+			if (rcu_access_pointer(data->ht[h1]))
+				return false;
+		}
+	}
 
 	RCU_INIT_POINTER(tp->root, NULL);
 
@@ -323,6 +326,7 @@ static void rsvp_destroy(struct tcf_proto *tp)
 		}
 	}
 	kfree_rcu(data, rcu);
+	return true;
 }
 
 static int rsvp_delete(struct tcf_proto *tp, unsigned long arg)
@@ -657,7 +661,6 @@ static int rsvp_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 {
 	struct rsvp_filter *f = (struct rsvp_filter *)fh;
 	struct rsvp_session *s;
-	unsigned char *b = skb_tail_pointer(skb);
 	struct nlattr *nest;
 	struct tc_rsvp_pinfo pinfo;
 
@@ -698,7 +701,7 @@ static int rsvp_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 	return skb->len;
 
 nla_put_failure:
-	nlmsg_trim(skb, b);
+	nla_nest_cancel(skb, nest);
 	return -1;
 }
 
@@ -708,7 +711,6 @@ static struct tcf_proto_ops RSVP_OPS __read_mostly = {
 	.init		=	rsvp_init,
 	.destroy	=	rsvp_destroy,
 	.get		=	rsvp_get,
-	.put		=	rsvp_put,
 	.change		=	rsvp_change,
 	.delete		=	rsvp_delete,
 	.walk		=	rsvp_walk,
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 30f10fb07f4a..a557dbaf5afe 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -116,13 +116,6 @@ static unsigned long tcindex_get(struct tcf_proto *tp, u32 handle)
 	return r && tcindex_filter_is_set(r) ? (unsigned long) r : 0UL;
 }
 
-
-static void tcindex_put(struct tcf_proto *tp, unsigned long f)
-{
-	pr_debug("tcindex_put(tp %p,f 0x%lx)\n", tp, f);
-}
-
-
 static int tcindex_init(struct tcf_proto *tp)
 {
 	struct tcindex_data *p;
@@ -475,11 +468,14 @@ static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker)
 	}
 }
 
-static void tcindex_destroy(struct tcf_proto *tp)
+static bool tcindex_destroy(struct tcf_proto *tp, bool force)
 {
 	struct tcindex_data *p = rtnl_dereference(tp->root);
 	struct tcf_walker walker;
 
+	if (!force)
+		return false;
+
 	pr_debug("tcindex_destroy(tp %p),p %p\n", tp, p);
 	walker.count = 0;
 	walker.skip = 0;
@@ -488,6 +484,7 @@ static void tcindex_destroy(struct tcf_proto *tp)
 
 	RCU_INIT_POINTER(tp->root, NULL);
 	call_rcu(&p->rcu, __tcindex_destroy);
+	return true;
 }
 
 
@@ -496,11 +493,10 @@ static int tcindex_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 {
 	struct tcindex_data *p = rtnl_dereference(tp->root);
 	struct tcindex_filter_result *r = (struct tcindex_filter_result *) fh;
-	unsigned char *b = skb_tail_pointer(skb);
 	struct nlattr *nest;
 
-	pr_debug("tcindex_dump(tp %p,fh 0x%lx,skb %p,t %p),p %p,r %p,b %p\n",
-		 tp, fh, skb, t, p, r, b);
+	pr_debug("tcindex_dump(tp %p,fh 0x%lx,skb %p,t %p),p %p,r %p\n",
+		 tp, fh, skb, t, p, r);
 	pr_debug("p->perfect %p p->h %p\n", p->perfect, p->h);
 
 	nest = nla_nest_start(skb, TCA_OPTIONS);
@@ -550,7 +546,7 @@ static int tcindex_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 	return skb->len;
 
 nla_put_failure:
-	nlmsg_trim(skb, b);
+	nla_nest_cancel(skb, nest);
 	return -1;
 }
 
@@ -560,7 +556,6 @@ static struct tcf_proto_ops cls_tcindex_ops __read_mostly = {
 	.init		=	tcindex_init,
 	.destroy	=	tcindex_destroy,
 	.get		=	tcindex_get,
-	.put		=	tcindex_put,
 	.change		=	tcindex_change,
 	.delete		=	tcindex_delete,
 	.walk		=	tcindex_walk,
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 0472909bb014..cab9e9b43967 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -78,8 +78,11 @@ struct tc_u_hnode {
 	struct tc_u_common	*tp_c;
 	int			refcnt;
 	unsigned int		divisor;
-	struct tc_u_knode __rcu	*ht[1];
 	struct rcu_head		rcu;
+	/* The 'ht' field MUST be the last field in structure to allow for
+	 * more entries allocated at end of structure.
+	 */
+	struct tc_u_knode __rcu	*ht[1];
 };
 
 struct tc_u_common {
@@ -299,10 +302,6 @@ static unsigned long u32_get(struct tcf_proto *tp, u32 handle)
 	return (unsigned long)u32_lookup_key(ht, handle);
 }
 
-static void u32_put(struct tcf_proto *tp, unsigned long f)
-{
-}
-
 static u32 gen_new_htid(struct tc_u_common *tp_c)
 {
 	int i = 0x800;
@@ -464,13 +463,35 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht)
 	return -ENOENT;
 }
 
-static void u32_destroy(struct tcf_proto *tp)
+static bool ht_empty(struct tc_u_hnode *ht)
+{
+	unsigned int h;
+
+	for (h = 0; h <= ht->divisor; h++)
+		if (rcu_access_pointer(ht->ht[h]))
+			return false;
+
+	return true;
+}
+
+static bool u32_destroy(struct tcf_proto *tp, bool force)
 {
 	struct tc_u_common *tp_c = tp->data;
 	struct tc_u_hnode *root_ht = rtnl_dereference(tp->root);
 
 	WARN_ON(root_ht == NULL);
 
+	if (!force) {
+		if (root_ht) {
+			if (root_ht->refcnt > 1)
+				return false;
+			if (root_ht->refcnt == 1) {
+				if (!ht_empty(root_ht))
+					return false;
+			}
+		}
+	}
+
 	if (root_ht && --root_ht->refcnt == 0)
 		u32_destroy_hnode(tp, root_ht);
 
@@ -495,6 +516,7 @@ static void u32_destroy(struct tcf_proto *tp)
 	}
 
 	tp->data = NULL;
+	return true;
 }
 
 static int u32_delete(struct tcf_proto *tp, unsigned long arg)
@@ -1021,7 +1043,6 @@ static struct tcf_proto_ops cls_u32_ops __read_mostly = {
 	.init		=	u32_init,
 	.destroy	=	u32_destroy,
 	.get		=	u32_get,
-	.put		=	u32_put,
 	.change		=	u32_change,
 	.delete		=	u32_delete,
 	.walk		=	u32_walk,
diff --git a/net/sched/em_ipset.c b/net/sched/em_ipset.c
index 5b4a4efe468c..a3d79c8bf3b8 100644
--- a/net/sched/em_ipset.c
+++ b/net/sched/em_ipset.c
@@ -59,7 +59,7 @@ static int em_ipset_match(struct sk_buff *skb, struct tcf_ematch *em,
 	struct net_device *dev, *indev = NULL;
 	int ret, network_offset;
 
-	switch (skb->protocol) {
+	switch (tc_skb_protocol(skb)) {
 	case htons(ETH_P_IP):
 		acpar.family = NFPROTO_IPV4;
 		if (!pskb_network_may_pull(skb, sizeof(struct iphdr)))
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index c8f8c399b99a..b5294ce20cd4 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -176,7 +176,7 @@ META_COLLECTOR(int_vlan_tag)
 {
 	unsigned short tag;
 
-	tag = vlan_tx_tag_get(skb);
+	tag = skb_vlan_tag_get(skb);
 	if (!tag && __vlan_get_tag(skb, &tag))
 		*err = -1;
 	else
@@ -197,7 +197,7 @@ META_COLLECTOR(int_priority)
 META_COLLECTOR(int_protocol)
 {
 	/* Let userspace take care of the byte ordering */
-	dst->value = skb->protocol;
+	dst->value = tc_skb_protocol(skb);
 }
 
 META_COLLECTOR(int_pkttype)
diff --git a/net/sched/em_text.c b/net/sched/em_text.c
index f03c3de16c27..73e2ed576ceb 100644
--- a/net/sched/em_text.c
+++ b/net/sched/em_text.c
@@ -34,7 +34,6 @@ static int em_text_match(struct sk_buff *skb, struct tcf_ematch *m,
 {
 	struct text_match *tm = EM_TEXT_PRIV(m);
 	int from, to;
-	struct ts_state state;
 
 	from = tcf_get_base_ptr(skb, tm->from_layer) - skb->data;
 	from += tm->from_offset;
@@ -42,7 +41,7 @@ static int em_text_match(struct sk_buff *skb, struct tcf_ematch *m,
 	to = tcf_get_base_ptr(skb, tm->to_layer) - skb->data;
 	to += tm->to_offset;
 
-	return skb_find_text(skb, from, to, tm->config, &state) != UINT_MAX;
+	return skb_find_text(skb, from, to, tm->config) != UINT_MAX;
 }
 
 static int em_text_change(struct net *net, void *data, int len,
diff --git a/net/sched/ematch.c b/net/sched/ematch.c
index 6742200b1307..fbb7ebfc58c6 100644
--- a/net/sched/ematch.c
+++ b/net/sched/ematch.c
@@ -228,6 +228,7 @@ static int tcf_em_validate(struct tcf_proto *tp,
 				 * to replay the request.
 				 */
 				module_put(em->ops->owner);
+				em->ops = NULL;
 				err = -EAGAIN;
 			}
 #endif
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 76f402e05bd6..73a123daa2cc 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -815,10 +815,8 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
 		if (dev->flags & IFF_UP)
 			dev_deactivate(dev);
 
-		if (new && new->ops->attach) {
-			new->ops->attach(new);
-			num_q = 0;
-		}
+		if (new && new->ops->attach)
+			goto skip;
 
 		for (i = 0; i < num_q; i++) {
 			struct netdev_queue *dev_queue = dev_ingress_queue(dev);
@@ -834,12 +832,16 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
 				qdisc_destroy(old);
 		}
 
+skip:
 		if (!ingress) {
 			notify_and_destroy(net, skb, n, classid,
 					   dev->qdisc, new);
 			if (new && !new->ops->attach)
 				atomic_inc(&new->refcnt);
 			dev->qdisc = new ? : &noop_qdisc;
+
+			if (new && new->ops->attach)
+				new->ops->attach(new);
 		} else {
 			notify_and_destroy(net, skb, n, classid, old, new);
 		}
@@ -1807,7 +1809,7 @@ done:
 int tc_classify_compat(struct sk_buff *skb, const struct tcf_proto *tp,
 		       struct tcf_result *res)
 {
-	__be16 protocol = skb->protocol;
+	__be16 protocol = tc_skb_protocol(skb);
 	int err;
 
 	for (; tp; tp = rcu_dereference_bh(tp->next)) {
@@ -1858,11 +1860,15 @@ reclassify:
 }
 EXPORT_SYMBOL(tc_classify);
 
-void tcf_destroy(struct tcf_proto *tp)
+bool tcf_destroy(struct tcf_proto *tp, bool force)
 {
-	tp->ops->destroy(tp);
-	module_put(tp->ops->owner);
-	kfree_rcu(tp, rcu);
+	if (tp->ops->destroy(tp, force)) {
+		module_put(tp->ops->owner);
+		kfree_rcu(tp, rcu);
+		return true;
+	}
+
+	return false;
 }
 
 void tcf_destroy_chain(struct tcf_proto __rcu **fl)
@@ -1871,7 +1877,7 @@ void tcf_destroy_chain(struct tcf_proto __rcu **fl)
 
 	while ((tp = rtnl_dereference(*fl)) != NULL) {
 		RCU_INIT_POINTER(*fl, tp->next);
-		tcf_destroy(tp);
+		tcf_destroy(tp, true);
 	}
 }
 EXPORT_SYMBOL(tcf_destroy_chain);
@@ -1879,13 +1885,10 @@ EXPORT_SYMBOL(tcf_destroy_chain);
 #ifdef CONFIG_PROC_FS
 static int psched_show(struct seq_file *seq, void *v)
 {
-	struct timespec ts;
-
-	hrtimer_get_res(CLOCK_MONOTONIC, &ts);
 	seq_printf(seq, "%08x %08x %08x %08x\n",
 		   (u32)NSEC_PER_USEC, (u32)PSCHED_TICKS2NS(1),
 		   1000000,
-		   (u32)NSEC_PER_SEC/(u32)ktime_to_ns(timespec_to_ktime(ts)));
+		   (u32)NSEC_PER_SEC / hrtimer_resolution);
 
 	return 0;
 }
diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c
index de28f8e968e8..7a0bdb16ac92 100644
--- a/net/sched/sch_codel.c
+++ b/net/sched/sch_codel.c
@@ -164,7 +164,7 @@ static int codel_init(struct Qdisc *sch, struct nlattr *opt)
 
 	sch->limit = DEFAULT_CODEL_LIMIT;
 
-	codel_params_init(&q->params);
+	codel_params_init(&q->params, sch);
 	codel_vars_init(&q->vars);
 	codel_stats_init(&q->stats);
 
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 227114f27f94..66700a6116aa 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -203,7 +203,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	pr_debug("%s(skb %p,sch %p,[qdisc %p])\n", __func__, skb, sch, p);
 
 	if (p->set_tc_index) {
-		switch (skb->protocol) {
+		switch (tc_skb_protocol(skb)) {
 		case htons(ETH_P_IP):
 			if (skb_cow_head(skb, sizeof(struct iphdr)))
 				goto drop;
@@ -289,7 +289,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch)
 	index = skb->tc_index & (p->indices - 1);
 	pr_debug("index %d->%d\n", skb->tc_index, index);
 
-	switch (skb->protocol) {
+	switch (tc_skb_protocol(skb)) {
 	case htons(ETH_P_IP):
 		ipv4_change_dsfield(ip_hdr(skb), p->mask[index],
 				    p->value[index]);
@@ -306,7 +306,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch)
 		 */
 		if (p->mask[index] != 0xff || p->value[index])
 			pr_warn("%s: unsupported protocol %d\n",
-				__func__, ntohs(skb->protocol));
+				__func__, ntohs(tc_skb_protocol(skb)));
 		break;
 	}
 
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index cbd7e1fd23b4..f377702d4b91 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -1,14 +1,14 @@
 /*
  * net/sched/sch_fq.c Fair Queue Packet Scheduler (per flow pacing)
  *
- *  Copyright (C) 2013 Eric Dumazet <edumazet@google.com>
+ *  Copyright (C) 2013-2015 Eric Dumazet <edumazet@google.com>
  *
  *	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.
  *
- *  Meant to be mostly used for localy generated traffic :
+ *  Meant to be mostly used for locally generated traffic :
  *  Fast classification depends on skb->sk being set before reaching us.
  *  If not, (router workload), we use rxhash as fallback, with 32 bits wide hash.
  *  All packets belonging to a socket are considered as a 'flow'.
@@ -52,6 +52,7 @@
 #include <net/pkt_sched.h>
 #include <net/sock.h>
 #include <net/tcp_states.h>
+#include <net/tcp.h>
 
 /*
  * Per flow structure, dynamically allocated
@@ -62,7 +63,7 @@ struct fq_flow {
 		struct sk_buff *tail;	/* last skb in the list */
 		unsigned long  age;	/* jiffies when flow was emptied, for gc */
 	};
-	struct rb_node	fq_node; 	/* anchor in fq_root[] trees */
+	struct rb_node	fq_node;	/* anchor in fq_root[] trees */
 	struct sock	*sk;
 	int		qlen;		/* number of packets in flow queue */
 	int		credit;
@@ -92,6 +93,7 @@ struct fq_sched_data {
 	u32		flow_refill_delay;
 	u32		flow_max_rate;	/* optional max rate per flow */
 	u32		flow_plimit;	/* max packets per flow */
+	u32		orphan_mask;	/* mask for orphaned skb */
 	struct rb_root	*fq_root;
 	u8		rate_enable;
 	u8		fq_trees_log;
@@ -222,11 +224,20 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q)
 	if (unlikely((skb->priority & TC_PRIO_MAX) == TC_PRIO_CONTROL))
 		return &q->internal;
 
-	if (unlikely(!sk)) {
+	/* SYNACK messages are attached to a listener socket.
+	 * 1) They are not part of a 'flow' yet
+	 * 2) We do not want to rate limit them (eg SYNFLOOD attack),
+	 *    especially if the listener set SO_MAX_PACING_RATE
+	 * 3) We pretend they are orphaned
+	 */
+	if (!sk || sk->sk_state == TCP_LISTEN) {
+		unsigned long hash = skb_get_hash(skb) & q->orphan_mask;
+
 		/* 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_hash(skb) | 1L);
+		sk = (struct sock *)((hash << 1) | 1UL);
+		skb_orphan(skb);
 	}
 
 	root = &q->fq_root[hash_32((u32)(long)sk, q->fq_trees_log)];
@@ -445,7 +456,9 @@ begin:
 		goto begin;
 	}
 
-	if (unlikely(f->head && now < f->time_next_packet)) {
+	skb = f->head;
+	if (unlikely(skb && now < f->time_next_packet &&
+		     !skb_is_tcp_pure_ack(skb))) {
 		head->first = f->next;
 		fq_flow_set_throttled(q, f);
 		goto begin;
@@ -464,14 +477,17 @@ begin:
 		goto begin;
 	}
 	prefetch(&skb->end);
-	f->time_next_packet = now;
 	f->credit -= qdisc_pkt_len(skb);
 
 	if (f->credit > 0 || !q->rate_enable)
 		goto out;
 
+	/* Do not pace locally generated ack packets */
+	if (skb_is_tcp_pure_ack(skb))
+		goto out;
+
 	rate = q->flow_max_rate;
-	if (skb->sk && skb->sk->sk_state != TCP_TIME_WAIT)
+	if (skb->sk)
 		rate = min(skb->sk->sk_pacing_rate, rate);
 
 	if (rate != ~0U) {
@@ -481,12 +497,11 @@ begin:
 		if (likely(rate))
 			do_div(len, rate);
 		/* Since socket rate can change later,
-		 * clamp the delay to 125 ms.
-		 * TODO: maybe segment the too big skb, as in commit
-		 * e43ac79a4bc ("sch_tbf: segment too big GSO packets")
+		 * clamp the delay to 1 second.
+		 * Really, providers of too big packets should be fixed !
 		 */
-		if (unlikely(len > 125 * NSEC_PER_MSEC)) {
-			len = 125 * NSEC_PER_MSEC;
+		if (unlikely(len > NSEC_PER_SEC)) {
+			len = NSEC_PER_SEC;
 			q->stat_pkts_too_long++;
 		}
 
@@ -671,8 +686,14 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt)
 	if (tb[TCA_FQ_FLOW_PLIMIT])
 		q->flow_plimit = nla_get_u32(tb[TCA_FQ_FLOW_PLIMIT]);
 
-	if (tb[TCA_FQ_QUANTUM])
-		q->quantum = nla_get_u32(tb[TCA_FQ_QUANTUM]);
+	if (tb[TCA_FQ_QUANTUM]) {
+		u32 quantum = nla_get_u32(tb[TCA_FQ_QUANTUM]);
+
+		if (quantum > 0)
+			q->quantum = quantum;
+		else
+			err = -EINVAL;
+	}
 
 	if (tb[TCA_FQ_INITIAL_QUANTUM])
 		q->initial_quantum = nla_get_u32(tb[TCA_FQ_INITIAL_QUANTUM]);
@@ -699,6 +720,9 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt)
 		q->flow_refill_delay = usecs_to_jiffies(usecs_delay);
 	}
 
+	if (tb[TCA_FQ_ORPHAN_MASK])
+		q->orphan_mask = nla_get_u32(tb[TCA_FQ_ORPHAN_MASK]);
+
 	if (!err) {
 		sch_tree_unlock(sch);
 		err = fq_resize(sch, fq_log);
@@ -744,6 +768,7 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt)
 	q->delayed		= RB_ROOT;
 	q->fq_root		= NULL;
 	q->fq_trees_log		= ilog2(1024);
+	q->orphan_mask		= 1024 - 1;
 	qdisc_watchdog_init(&q->watchdog, sch);
 
 	if (opt)
@@ -773,6 +798,7 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb)
 	    nla_put_u32(skb, TCA_FQ_FLOW_MAX_RATE, q->flow_max_rate) ||
 	    nla_put_u32(skb, TCA_FQ_FLOW_REFILL_DELAY,
 			jiffies_to_usecs(q->flow_refill_delay)) ||
+	    nla_put_u32(skb, TCA_FQ_ORPHAN_MASK, q->orphan_mask) ||
 	    nla_put_u32(skb, TCA_FQ_BUCKETS_LOG, q->fq_trees_log))
 		goto nla_put_failure;
 
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index b9ca32ebc1de..c244c45b78d7 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -94,7 +94,7 @@ static unsigned int fq_codel_classify(struct sk_buff *skb, struct Qdisc *sch,
 	    TC_H_MIN(skb->priority) <= q->flows_cnt)
 		return TC_H_MIN(skb->priority);
 
-	filter = rcu_dereference(q->filter_list);
+	filter = rcu_dereference_bh(q->filter_list);
 	if (!filter)
 		return fq_codel_hash(q, skb) + 1;
 
@@ -391,7 +391,7 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt)
 	q->perturbation = prandom_u32();
 	INIT_LIST_HEAD(&q->new_flows);
 	INIT_LIST_HEAD(&q->old_flows);
-	codel_params_init(&q->cparams);
+	codel_params_init(&q->cparams, sch);
 	codel_stats_init(&q->cstats);
 	q->cparams.ecn = true;
 
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index a4ca4517cdc8..634529e0ce6b 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -229,7 +229,7 @@ static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		break;
 	}
 
-	if (q->backlog + qdisc_pkt_len(skb) <= q->limit) {
+	if (gred_backlog(t, q, sch) + qdisc_pkt_len(skb) <= q->limit) {
 		q->backlog += qdisc_pkt_len(skb);
 		return qdisc_enqueue_tail(skb, sch);
 	}
@@ -553,7 +553,7 @@ static int gred_dump(struct Qdisc *sch, struct sk_buff *skb)
 
 		opt.limit	= q->limit;
 		opt.DP		= q->DP;
-		opt.backlog	= q->backlog;
+		opt.backlog	= gred_backlog(table, q, sch);
 		opt.prio	= q->prio;
 		opt.qth_min	= q->parms.qth_min >> q->parms.Wlog;
 		opt.qth_max	= q->parms.qth_max >> q->parms.Wlog;
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index eb5b8445fef9..4cdbfb85686a 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -88,11 +88,19 @@ static int ingress_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 
 /* ------------------------------------------------------------- */
 
+static int ingress_init(struct Qdisc *sch, struct nlattr *opt)
+{
+	net_inc_ingress_queue();
+
+	return 0;
+}
+
 static void ingress_destroy(struct Qdisc *sch)
 {
 	struct ingress_qdisc_data *p = qdisc_priv(sch);
 
 	tcf_destroy_chain(&p->filter_list);
+	net_dec_ingress_queue();
 }
 
 static int ingress_dump(struct Qdisc *sch, struct sk_buff *skb)
@@ -124,6 +132,7 @@ static struct Qdisc_ops ingress_qdisc_ops __read_mostly = {
 	.id		=	"ingress",
 	.priv_size	=	sizeof(struct ingress_qdisc_data),
 	.enqueue	=	ingress_enqueue,
+	.init		=	ingress_init,
 	.destroy	=	ingress_destroy,
 	.dump		=	ingress_dump,
 	.owner		=	THIS_MODULE,
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index b34331967e02..956ead2cab9a 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -139,33 +139,20 @@ struct netem_sched_data {
 
 /* Time stamp put into socket buffer control block
  * Only valid when skbs are in our internal t(ime)fifo queue.
+ *
+ * As skb->rbnode uses same storage than skb->next, skb->prev and skb->tstamp,
+ * and skb->next & skb->prev are scratch space for a qdisc,
+ * we save skb->tstamp value in skb->cb[] before destroying it.
  */
 struct netem_skb_cb {
 	psched_time_t	time_to_send;
 	ktime_t		tstamp_save;
 };
 
-/* Because space in skb->cb[] is tight, netem overloads skb->next/prev/tstamp
- * to hold a rb_node structure.
- *
- * If struct sk_buff layout is changed, the following checks will complain.
- */
-static struct rb_node *netem_rb_node(struct sk_buff *skb)
-{
-	BUILD_BUG_ON(offsetof(struct sk_buff, next) != 0);
-	BUILD_BUG_ON(offsetof(struct sk_buff, prev) !=
-		     offsetof(struct sk_buff, next) + sizeof(skb->next));
-	BUILD_BUG_ON(offsetof(struct sk_buff, tstamp) !=
-		     offsetof(struct sk_buff, prev) + sizeof(skb->prev));
-	BUILD_BUG_ON(sizeof(struct rb_node) > sizeof(skb->next) +
-					      sizeof(skb->prev) +
-					      sizeof(skb->tstamp));
-	return (struct rb_node *)&skb->next;
-}
 
 static struct sk_buff *netem_rb_to_skb(struct rb_node *rb)
 {
-	return (struct sk_buff *)rb;
+	return container_of(rb, struct sk_buff, rbnode);
 }
 
 static inline struct netem_skb_cb *netem_skb_cb(struct sk_buff *skb)
@@ -403,8 +390,8 @@ static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch)
 		else
 			p = &parent->rb_left;
 	}
-	rb_link_node(netem_rb_node(nskb), parent, p);
-	rb_insert_color(netem_rb_node(nskb), &q->t_root);
+	rb_link_node(&nskb->rbnode, parent, p);
+	rb_insert_color(&nskb->rbnode, &q->t_root);
 	sch->q.qlen++;
 }
 
@@ -573,8 +560,8 @@ static struct sk_buff *netem_dequeue(struct Qdisc *sch)
 tfifo_dequeue:
 	skb = __skb_dequeue(&sch->q);
 	if (skb) {
-deliver:
 		qdisc_qstats_backlog_dec(sch, skb);
+deliver:
 		qdisc_unthrottled(sch);
 		qdisc_bstats_update(sch, skb);
 		return skb;
@@ -591,6 +578,7 @@ deliver:
 			rb_erase(p, &q->t_root);
 
 			sch->q.qlen--;
+			qdisc_qstats_backlog_dec(sch, skb);
 			skb->next = NULL;
 			skb->prev = NULL;
 			skb->tstamp = netem_skb_cb(skb)->tstamp_save;
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index 6ada42396a24..e02687185a59 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -122,13 +122,6 @@ teql_peek(struct Qdisc *sch)
 	return NULL;
 }
 
-static inline void
-teql_neigh_release(struct neighbour *n)
-{
-	if (n)
-		neigh_release(n);
-}
-
 static void
 teql_reset(struct Qdisc *sch)
 {
@@ -249,8 +242,8 @@ __teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res,
 		char haddr[MAX_ADDR_LEN];
 
 		neigh_ha_snapshot(haddr, n, dev);
-		err = dev_hard_header(skb, dev, ntohs(skb->protocol), haddr,
-				      NULL, skb->len);
+		err = dev_hard_header(skb, dev, ntohs(tc_skb_protocol(skb)),
+				      haddr, NULL, skb->len);
 
 		if (err < 0)
 			err = -EINVAL;
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index f791edd64d6c..197c3f59ecbf 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -391,8 +391,7 @@ void sctp_association_free(struct sctp_association *asoc)
 	sctp_asconf_queue_teardown(asoc);
 
 	/* Free pending address space being deleted */
-	if (asoc->asconf_addr_del_pending != NULL)
-		kfree(asoc->asconf_addr_del_pending);
+	kfree(asoc->asconf_addr_del_pending);
 
 	/* AUTH - Free the endpoint shared keys */
 	sctp_auth_destroy_keys(&asoc->endpoint_shared_keys);
@@ -1182,7 +1181,6 @@ void sctp_assoc_update(struct sctp_association *asoc,
 	asoc->peer.peer_hmacs = new->peer.peer_hmacs;
 	new->peer.peer_hmacs = NULL;
 
-	sctp_auth_key_put(asoc->asoc_shared_key);
 	sctp_auth_asoc_init_active_key(asoc, GFP_ATOMIC);
 }
 
diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index fb7976aee61c..4f15b7d730e1 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -381,13 +381,14 @@ nomem:
 }
 
 
-/* Public interface to creat the association shared key.
+/* Public interface to create the association shared key.
  * See code above for the algorithm.
  */
 int sctp_auth_asoc_init_active_key(struct sctp_association *asoc, gfp_t gfp)
 {
 	struct sctp_auth_bytes	*secret;
 	struct sctp_shared_key *ep_key;
+	struct sctp_chunk *chunk;
 
 	/* If we don't support AUTH, or peer is not capable
 	 * we don't need to do anything.
@@ -410,6 +411,14 @@ int sctp_auth_asoc_init_active_key(struct sctp_association *asoc, gfp_t gfp)
 	sctp_auth_key_put(asoc->asoc_shared_key);
 	asoc->asoc_shared_key = secret;
 
+	/* Update send queue in case any chunk already in there now
+	 * needs authenticating
+	 */
+	list_for_each_entry(chunk, &asoc->outqueue.out_chunk_list, list) {
+		if (sctp_auth_send_cid(chunk->chunk_hdr->type, asoc))
+			chunk->auth = 1;
+	}
+
 	return 0;
 }
 
diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c
index 158701da2d31..a3380917f197 100644
--- a/net/sctp/chunk.c
+++ b/net/sctp/chunk.c
@@ -164,7 +164,7 @@ static void sctp_datamsg_assign(struct sctp_datamsg *msg, struct sctp_chunk *chu
  */
 struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc,
 					    struct sctp_sndrcvinfo *sinfo,
-					    struct msghdr *msgh, int msg_len)
+					    struct iov_iter *from)
 {
 	int max, whole, i, offset, over, err;
 	int len, first_len;
@@ -172,6 +172,7 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc,
 	struct sctp_chunk *chunk;
 	struct sctp_datamsg *msg;
 	struct list_head *pos, *temp;
+	size_t msg_len = iov_iter_count(from);
 	__u8 frag;
 
 	msg = sctp_datamsg_new(GFP_KERNEL);
@@ -279,12 +280,10 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc,
 			goto errout;
 		}
 
-		err = sctp_user_addto_chunk(chunk, offset, len, msgh->msg_iov);
+		err = sctp_user_addto_chunk(chunk, len, from);
 		if (err < 0)
 			goto errout_chunk_free;
 
-		offset += len;
-
 		/* Put the chunk->skb back into the form expected by send.  */
 		__skb_pull(chunk->skb, (__u8 *)chunk->chunk_hdr
 			   - (__u8 *)chunk->skb->data);
@@ -317,7 +316,7 @@ 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, over, from);
 
 		/* Put the chunk->skb back into the form expected by send.  */
 		__skb_pull(chunk->skb, (__u8 *)chunk->chunk_hdr
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 42dffd428389..fc5e45b8a832 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -401,12 +401,12 @@ int sctp_packet_transmit(struct sctp_packet *packet)
 	sk = chunk->skb->sk;
 
 	/* Allocate the new skb.  */
-	nskb = alloc_skb(packet->size + LL_MAX_HEADER, GFP_ATOMIC);
+	nskb = alloc_skb(packet->size + MAX_HEADER, GFP_ATOMIC);
 	if (!nskb)
 		goto nomem;
 
 	/* Make sure the outbound skb has enough header room reserved. */
-	skb_reserve(nskb, packet->overhead + LL_MAX_HEADER);
+	skb_reserve(nskb, packet->overhead + MAX_HEADER);
 
 	/* Set the owning socket so that we know where to get the
 	 * destination IP address.
diff --git a/net/sctp/proc.c b/net/sctp/proc.c
index 34229ee7f379..0697eda5aed8 100644
--- a/net/sctp/proc.c
+++ b/net/sctp/proc.c
@@ -417,7 +417,7 @@ static void *sctp_remaddr_seq_start(struct seq_file *seq, loff_t *pos)
 
 	if (*pos == 0)
 		seq_printf(seq, "ADDR ASSOC_ID HB_ACT RTO MAX_PATH_RTX "
-				"REM_ADDR_RTX  START\n");
+				"REM_ADDR_RTX START STATE\n");
 
 	return (void *)pos;
 }
@@ -490,14 +490,20 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v)
 			 * Note: We don't have a way to tally this at the moment
 			 * so lets just leave it as zero for the moment
 			 */
-			seq_printf(seq, "0 ");
+			seq_puts(seq, "0 ");
 
 			/*
 			 * remote address start time (START).  This is also not
 			 * currently implemented, but we can record it with a
 			 * jiffies marker in a subsequent patch
 			 */
-			seq_printf(seq, "0");
+			seq_puts(seq, "0 ");
+
+			/*
+			 * The current state of this destination. I.e.
+			 * SCTP_ACTIVE, SCTP_INACTIVE, ...
+			 */
+			seq_printf(seq, "%d", tsp->state);
 
 			seq_printf(seq, "\n");
 		}
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 8f34b27d5775..53b7acde9aa3 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1322,8 +1322,7 @@ static __init int sctp_init(void)
 	int max_share;
 	int order;
 
-	BUILD_BUG_ON(sizeof(struct sctp_ulpevent) >
-		     sizeof(((struct sk_buff *) 0)->cb));
+	sock_skb_cb_check_size(sizeof(struct sctp_ulpevent));
 
 	/* Allocate bind_bucket and chunk caches. */
 	status = -ENOBUFS;
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 9f32741abb1c..06320c8c1c86 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1001,7 +1001,7 @@ no_mem:
 
 /* Helper to create ABORT with a SCTP_ERROR_USER_ABORT error.  */
 struct sctp_chunk *sctp_make_abort_user(const struct sctp_association *asoc,
-					const struct msghdr *msg,
+					struct msghdr *msg,
 					size_t paylen)
 {
 	struct sctp_chunk *retval;
@@ -1018,7 +1018,7 @@ struct sctp_chunk *sctp_make_abort_user(const struct sctp_association *asoc,
 		if (!payload)
 			goto err_payload;
 
-		err = memcpy_fromiovec(payload, msg->msg_iov, paylen);
+		err = memcpy_from_msg(payload, msg, paylen);
 		if (err < 0)
 			goto err_copy;
 	}
@@ -1491,26 +1491,26 @@ static void *sctp_addto_chunk_fixed(struct sctp_chunk *chunk,
  * chunk is not big enough.
  * Returns a kernel err value.
  */
-int sctp_user_addto_chunk(struct sctp_chunk *chunk, int off, int len,
-			  struct iovec *data)
+int sctp_user_addto_chunk(struct sctp_chunk *chunk, int len,
+			  struct iov_iter *from)
 {
-	__u8 *target;
-	int err = 0;
+	void *target;
+	ssize_t copied;
 
 	/* Make room in chunk for data.  */
 	target = skb_put(chunk->skb, len);
 
 	/* Copy data (whole iovec) into chunk */
-	if ((err = memcpy_fromiovecend(target, data, off, len)))
-		goto out;
+	copied = copy_from_iter(target, len, from);
+	if (copied != len)
+		return -EFAULT;
 
 	/* Adjust the chunk length field.  */
 	chunk->chunk_hdr->length =
 		htons(ntohs(chunk->chunk_hdr->length) + len);
 	chunk->chunk_end = skb_tail_pointer(chunk->skb);
 
-out:
-	return err;
+	return 0;
 }
 
 /* Helper function to assign a TSN if needed.  This assumes that both
@@ -2608,7 +2608,7 @@ do_addr_param:
 
 		addr_param = param.v + sizeof(sctp_addip_param_t);
 
-		af = sctp_get_af_specific(param_type2af(param.p->type));
+		af = sctp_get_af_specific(param_type2af(addr_param->p.type));
 		if (af == NULL)
 			break;
 
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 634a2abb5f3a..f09de7fac2e6 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -102,11 +102,6 @@ static int sctp_autobind(struct sock *sk);
 static void sctp_sock_migrate(struct sock *, struct sock *,
 			      struct sctp_association *, sctp_socket_type_t);
 
-extern struct kmem_cache *sctp_bucket_cachep;
-extern long sysctl_sctp_mem[3];
-extern int sysctl_sctp_rmem[3];
-extern int sysctl_sctp_wmem[3];
-
 static int sctp_memory_pressure;
 static atomic_long_t sctp_memory_allocated;
 struct percpu_counter sctp_sockets_allocated;
@@ -162,7 +157,7 @@ static inline void sctp_set_owner_w(struct sctp_chunk *chunk)
 
 	chunk->skb->destructor = sctp_wfree;
 	/* Save the chunk pointer in skb for sctp_wfree to use later.  */
-	*((struct sctp_chunk **)(chunk->skb->cb)) = chunk;
+	skb_shinfo(chunk->skb)->destructor_arg = chunk;
 
 	asoc->sndbuf_used += SCTP_DATA_SNDSIZE(chunk) +
 				sizeof(struct sk_buff) +
@@ -1586,8 +1581,7 @@ static int sctp_error(struct sock *sk, int flags, int err)
 
 static int sctp_msghdr_parse(const struct msghdr *, sctp_cmsgs_t *);
 
-static int sctp_sendmsg(struct kiocb *iocb, struct sock *sk,
-			struct msghdr *msg, size_t msg_len)
+static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len)
 {
 	struct net *net = sock_net(sk);
 	struct sctp_sock *sp;
@@ -1603,7 +1597,7 @@ static int sctp_sendmsg(struct kiocb *iocb, struct sock *sk,
 	sctp_assoc_t associd = 0;
 	sctp_cmsgs_t cmsgs = { NULL };
 	sctp_scope_t scope;
-	bool fill_sinfo_ttl = false;
+	bool fill_sinfo_ttl = false, wait_connect = false;
 	struct sctp_datamsg *datamsg;
 	int msg_flags = msg->msg_flags;
 	__u16 sinfo_flags = 0;
@@ -1943,11 +1937,12 @@ static int sctp_sendmsg(struct kiocb *iocb, struct sock *sk,
 		if (err < 0)
 			goto out_free;
 
+		wait_connect = true;
 		pr_debug("%s: we associated primitively\n", __func__);
 	}
 
 	/* Break the message into multiple chunks of maximum size. */
-	datamsg = sctp_datamsg_from_user(asoc, sinfo, msg, msg_len);
+	datamsg = sctp_datamsg_from_user(asoc, sinfo, &msg->msg_iter);
 	if (IS_ERR(datamsg)) {
 		err = PTR_ERR(datamsg);
 		goto out_free;
@@ -1980,6 +1975,11 @@ static int sctp_sendmsg(struct kiocb *iocb, struct sock *sk,
 	sctp_datamsg_put(datamsg);
 	err = msg_len;
 
+	if (unlikely(wait_connect)) {
+		timeo = sock_sndtimeo(sk, msg_flags & MSG_DONTWAIT);
+		sctp_wait_for_connect(asoc, &timeo);
+	}
+
 	/* If we are already past ASSOCIATE, the lower
 	 * layers are responsible for association cleanup.
 	 */
@@ -2060,9 +2060,8 @@ static int sctp_skb_pull(struct sk_buff *skb, int len)
  *  flags   - flags sent or received with the user message, see Section
  *            5 for complete description of the flags.
  */
-static int sctp_recvmsg(struct kiocb *iocb, struct sock *sk,
-			struct msghdr *msg, size_t len, int noblock,
-			int flags, int *addr_len)
+static int sctp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+			int noblock, int flags, int *addr_len)
 {
 	struct sctp_ulpevent *event = NULL;
 	struct sctp_sock *sp = sctp_sk(sk);
@@ -2095,7 +2094,7 @@ static int sctp_recvmsg(struct kiocb *iocb, struct sock *sk,
 	if (copied > len)
 		copied = len;
 
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 
 	event = sctp_skb2event(skb);
 
@@ -6592,8 +6591,7 @@ static int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs)
 	struct cmsghdr *cmsg;
 	struct msghdr *my_msg = (struct msghdr *)msg;
 
-	for (cmsg = CMSG_FIRSTHDR(msg); cmsg != NULL;
-	     cmsg = CMSG_NXTHDR(my_msg, cmsg)) {
+	for_each_cmsghdr(cmsg, my_msg) {
 		if (!CMSG_OK(my_msg, cmsg))
 			return -EINVAL;
 
@@ -6870,14 +6868,10 @@ static void sctp_wake_up_waiters(struct sock *sk,
  */
 static void sctp_wfree(struct sk_buff *skb)
 {
-	struct sctp_association *asoc;
-	struct sctp_chunk *chunk;
-	struct sock *sk;
+	struct sctp_chunk *chunk = skb_shinfo(skb)->destructor_arg;
+	struct sctp_association *asoc = chunk->asoc;
+	struct sock *sk = asoc->base.sk;
 
-	/* Get the saved chunk pointer.  */
-	chunk = *((struct sctp_chunk **)(skb->cb));
-	asoc = chunk->asoc;
-	sk = asoc->base.sk;
 	asoc->sndbuf_used -= SCTP_DATA_SNDSIZE(chunk) +
 				sizeof(struct sk_buff) +
 				sizeof(struct sctp_chunk);
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index 2e9ada10fd84..26d50c565f54 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -58,10 +58,6 @@ static unsigned long max_autoclose_max =
 	(MAX_SCHEDULE_TIMEOUT / HZ > UINT_MAX)
 	? UINT_MAX : MAX_SCHEDULE_TIMEOUT / HZ;
 
-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,
 				void __user *buffer, size_t *lenp,
 				loff_t *ppos);
diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c
index d49dc2ed30ad..ce469d648ffb 100644
--- a/net/sctp/ulpqueue.c
+++ b/net/sctp/ulpqueue.c
@@ -205,9 +205,10 @@ 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))
+	if (!sctp_ulpevent_is_notification(event)) {
 		sk_mark_napi_id(sk, skb);
-
+		sk_incoming_cpu_update(sk);
+	}
 	/* Check if the user wishes to receive this event.  */
 	if (!sctp_ulpevent_is_enabled(event, &sctp_sk(sk)->subscribe))
 		goto out_free;
diff --git a/net/socket.c b/net/socket.c
index fe20c319a0bb..884e32997698 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -113,11 +113,8 @@ unsigned int sysctl_net_busy_read __read_mostly;
 unsigned int sysctl_net_busy_poll __read_mostly;
 #endif
 
-static int sock_no_open(struct inode *irrelevant, struct file *dontcare);
-static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov,
-			 unsigned long nr_segs, loff_t pos);
-static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov,
-			  unsigned long nr_segs, loff_t pos);
+static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to);
+static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from);
 static int sock_mmap(struct file *file, struct vm_area_struct *vma);
 
 static int sock_close(struct inode *inode, struct file *file);
@@ -143,15 +140,14 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos,
 static const struct file_operations socket_file_ops = {
 	.owner =	THIS_MODULE,
 	.llseek =	no_llseek,
-	.aio_read =	sock_aio_read,
-	.aio_write =	sock_aio_write,
+	.read_iter =	sock_read_iter,
+	.write_iter =	sock_write_iter,
 	.poll =		sock_poll,
 	.unlocked_ioctl = sock_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = compat_sock_ioctl,
 #endif
 	.mmap =		sock_mmap,
-	.open =		sock_no_open,	/* special open code to disallow open via /proc */
 	.release =	sock_close,
 	.fasync =	sock_fasync,
 	.sendpage =	sock_sendpage,
@@ -316,7 +312,7 @@ static const struct super_operations sockfs_ops = {
 static char *sockfs_dname(struct dentry *dentry, char *buffer, int buflen)
 {
 	return dynamic_dname(dentry, buffer, buflen, "socket:[%lu]",
-				dentry->d_inode->i_ino);
+				d_inode(dentry)->i_ino);
 }
 
 static const struct dentry_operations sockfs_dentry_operations = {
@@ -374,13 +370,12 @@ struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname)
 	path.mnt = mntget(sock_mnt);
 
 	d_instantiate(path.dentry, SOCK_INODE(sock));
-	SOCK_INODE(sock)->i_fop = &socket_file_ops;
 
 	file = alloc_file(&path, FMODE_READ | FMODE_WRITE,
 		  &socket_file_ops);
 	if (unlikely(IS_ERR(file))) {
 		/* drop dentry, keep inode */
-		ihold(path.dentry->d_inode);
+		ihold(d_inode(path.dentry));
 		path_put(&path);
 		return file;
 	}
@@ -502,7 +497,7 @@ static ssize_t sockfs_listxattr(struct dentry *dentry, char *buffer,
 	ssize_t len;
 	ssize_t used = 0;
 
-	len = security_inode_listsecurity(dentry->d_inode, buffer, size);
+	len = security_inode_listsecurity(d_inode(dentry), buffer, size);
 	if (len < 0)
 		return len;
 	used += len;
@@ -559,23 +554,6 @@ static struct socket *sock_alloc(void)
 	return sock;
 }
 
-/*
- *	In theory you can't get an open on this inode, but /proc provides
- *	a back door. Remember to keep it shut otherwise you'll let the
- *	creepy crawlies in.
- */
-
-static int sock_no_open(struct inode *irrelevant, struct file *dontcare)
-{
-	return -ENXIO;
-}
-
-const struct file_operations bad_sock_fops = {
-	.owner = THIS_MODULE,
-	.open = sock_no_open,
-	.llseek = noop_llseek,
-};
-
 /**
  *	sock_release	-	close a socket
  *	@sock: socket to close
@@ -630,72 +608,27 @@ void __sock_tx_timestamp(const struct sock *sk, __u8 *tx_flags)
 }
 EXPORT_SYMBOL(__sock_tx_timestamp);
 
-static inline int __sock_sendmsg_nosec(struct kiocb *iocb, struct socket *sock,
-				       struct msghdr *msg, size_t size)
+static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg)
 {
-	struct sock_iocb *si = kiocb_to_siocb(iocb);
-
-	si->sock = sock;
-	si->scm = NULL;
-	si->msg = msg;
-	si->size = size;
-
-	return sock->ops->sendmsg(iocb, sock, msg, size);
-}
-
-static inline int __sock_sendmsg(struct kiocb *iocb, struct socket *sock,
-				 struct msghdr *msg, size_t size)
-{
-	int err = security_socket_sendmsg(sock, msg, size);
-
-	return err ?: __sock_sendmsg_nosec(iocb, sock, msg, size);
-}
-
-int sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
-{
-	struct kiocb iocb;
-	struct sock_iocb siocb;
-	int ret;
-
-	init_sync_kiocb(&iocb, NULL);
-	iocb.private = &siocb;
-	ret = __sock_sendmsg(&iocb, sock, msg, size);
-	if (-EIOCBQUEUED == ret)
-		ret = wait_on_sync_kiocb(&iocb);
+	int ret = sock->ops->sendmsg(sock, msg, msg_data_left(msg));
+	BUG_ON(ret == -EIOCBQUEUED);
 	return ret;
 }
-EXPORT_SYMBOL(sock_sendmsg);
 
-static int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg, size_t size)
+int sock_sendmsg(struct socket *sock, struct msghdr *msg)
 {
-	struct kiocb iocb;
-	struct sock_iocb siocb;
-	int ret;
+	int err = security_socket_sendmsg(sock, msg,
+					  msg_data_left(msg));
 
-	init_sync_kiocb(&iocb, NULL);
-	iocb.private = &siocb;
-	ret = __sock_sendmsg_nosec(&iocb, sock, msg, size);
-	if (-EIOCBQUEUED == ret)
-		ret = wait_on_sync_kiocb(&iocb);
-	return ret;
+	return err ?: sock_sendmsg_nosec(sock, msg);
 }
+EXPORT_SYMBOL(sock_sendmsg);
 
 int kernel_sendmsg(struct socket *sock, struct msghdr *msg,
 		   struct kvec *vec, size_t num, size_t size)
 {
-	mm_segment_t oldfs = get_fs();
-	int result;
-
-	set_fs(KERNEL_DS);
-	/*
-	 * the following is safe, since for compiler definitions of kvec and
-	 * iovec are identical, yielding the same in-core layout and alignment
-	 */
-	msg->msg_iov = (struct iovec *)vec;
-	msg->msg_iovlen = num;
-	result = sock_sendmsg(sock, msg, size);
-	set_fs(oldfs);
-	return result;
+	iov_iter_kvec(&msg->msg_iter, WRITE | ITER_KVEC, vec, num, size);
+	return sock_sendmsg(sock, msg);
 }
 EXPORT_SYMBOL(kernel_sendmsg);
 
@@ -763,9 +696,9 @@ EXPORT_SYMBOL_GPL(__sock_recv_wifi_status);
 static inline void sock_recv_drops(struct msghdr *msg, struct sock *sk,
 				   struct sk_buff *skb)
 {
-	if (sock_flag(sk, SOCK_RXQ_OVFL) && skb && skb->dropcount)
+	if (sock_flag(sk, SOCK_RXQ_OVFL) && skb && SOCK_SKB_CB(skb)->dropcount)
 		put_cmsg(msg, SOL_SOCKET, SO_RXQ_OVFL,
-			sizeof(__u32), &skb->dropcount);
+			sizeof(__u32), &SOCK_SKB_CB(skb)->dropcount);
 }
 
 void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
@@ -776,59 +709,21 @@ void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
 }
 EXPORT_SYMBOL_GPL(__sock_recv_ts_and_drops);
 
-static inline int __sock_recvmsg_nosec(struct kiocb *iocb, struct socket *sock,
-				       struct msghdr *msg, size_t size, int flags)
+static inline int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg,
+				     size_t size, int flags)
 {
-	struct sock_iocb *si = kiocb_to_siocb(iocb);
-
-	si->sock = sock;
-	si->scm = NULL;
-	si->msg = msg;
-	si->size = size;
-	si->flags = flags;
-
-	return sock->ops->recvmsg(iocb, sock, msg, size, flags);
+	return sock->ops->recvmsg(sock, msg, size, flags);
 }
 
-static inline int __sock_recvmsg(struct kiocb *iocb, struct socket *sock,
-				 struct msghdr *msg, size_t size, int flags)
+int sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+		 int flags)
 {
 	int err = security_socket_recvmsg(sock, msg, size, flags);
 
-	return err ?: __sock_recvmsg_nosec(iocb, sock, msg, size, flags);
-}
-
-int sock_recvmsg(struct socket *sock, struct msghdr *msg,
-		 size_t size, int flags)
-{
-	struct kiocb iocb;
-	struct sock_iocb siocb;
-	int ret;
-
-	init_sync_kiocb(&iocb, NULL);
-	iocb.private = &siocb;
-	ret = __sock_recvmsg(&iocb, sock, msg, size, flags);
-	if (-EIOCBQUEUED == ret)
-		ret = wait_on_sync_kiocb(&iocb);
-	return ret;
+	return err ?: sock_recvmsg_nosec(sock, msg, size, flags);
 }
 EXPORT_SYMBOL(sock_recvmsg);
 
-static int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg,
-			      size_t size, int flags)
-{
-	struct kiocb iocb;
-	struct sock_iocb siocb;
-	int ret;
-
-	init_sync_kiocb(&iocb, NULL);
-	iocb.private = &siocb;
-	ret = __sock_recvmsg_nosec(&iocb, sock, msg, size, flags);
-	if (-EIOCBQUEUED == ret)
-		ret = wait_on_sync_kiocb(&iocb);
-	return ret;
-}
-
 /**
  * kernel_recvmsg - Receive a message from a socket (kernel space)
  * @sock:       The socket to receive the message from
@@ -850,12 +745,8 @@ int kernel_recvmsg(struct socket *sock, struct msghdr *msg,
 	mm_segment_t oldfs = get_fs();
 	int result;
 
+	iov_iter_kvec(&msg->msg_iter, READ | ITER_KVEC, vec, num, size);
 	set_fs(KERNEL_DS);
-	/*
-	 * the following is safe, since for compiler definitions of kvec and
-	 * iovec are identical, yielding the same in-core layout and alignment
-	 */
-	msg->msg_iov = (struct iovec *)vec, msg->msg_iovlen = num;
 	result = sock_recvmsg(sock, msg, size, flags);
 	set_fs(oldfs);
 	return result;
@@ -889,94 +780,48 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos,
 	return sock->ops->splice_read(sock, ppos, pipe, len, flags);
 }
 
-static struct sock_iocb *alloc_sock_iocb(struct kiocb *iocb,
-					 struct sock_iocb *siocb)
-{
-	if (!is_sync_kiocb(iocb))
-		BUG();
-
-	siocb->kiocb = iocb;
-	iocb->private = siocb;
-	return siocb;
-}
-
-static ssize_t do_sock_read(struct msghdr *msg, struct kiocb *iocb,
-		struct file *file, const struct iovec *iov,
-		unsigned long nr_segs)
+static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
+	struct file *file = iocb->ki_filp;
 	struct socket *sock = file->private_data;
-	size_t size = 0;
-	int i;
-
-	for (i = 0; i < nr_segs; i++)
-		size += iov[i].iov_len;
-
-	msg->msg_name = NULL;
-	msg->msg_namelen = 0;
-	msg->msg_control = NULL;
-	msg->msg_controllen = 0;
-	msg->msg_iov = (struct iovec *)iov;
-	msg->msg_iovlen = nr_segs;
-	msg->msg_flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0;
+	struct msghdr msg = {.msg_iter = *to,
+			     .msg_iocb = iocb};
+	ssize_t res;
 
-	return __sock_recvmsg(iocb, sock, msg, size, msg->msg_flags);
-}
-
-static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov,
-				unsigned long nr_segs, loff_t pos)
-{
-	struct sock_iocb siocb, *x;
+	if (file->f_flags & O_NONBLOCK)
+		msg.msg_flags = MSG_DONTWAIT;
 
-	if (pos != 0)
+	if (iocb->ki_pos != 0)
 		return -ESPIPE;
 
-	if (iocb->ki_nbytes == 0)	/* Match SYS5 behaviour */
+	if (!iov_iter_count(to))	/* Match SYS5 behaviour */
 		return 0;
 
-
-	x = alloc_sock_iocb(iocb, &siocb);
-	if (!x)
-		return -ENOMEM;
-	return do_sock_read(&x->async_msg, iocb, iocb->ki_filp, iov, nr_segs);
+	res = sock_recvmsg(sock, &msg, iov_iter_count(to), msg.msg_flags);
+	*to = msg.msg_iter;
+	return res;
 }
 
-static ssize_t do_sock_write(struct msghdr *msg, struct kiocb *iocb,
-			struct file *file, const struct iovec *iov,
-			unsigned long nr_segs)
+static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
+	struct file *file = iocb->ki_filp;
 	struct socket *sock = file->private_data;
-	size_t size = 0;
-	int i;
-
-	for (i = 0; i < nr_segs; i++)
-		size += iov[i].iov_len;
-
-	msg->msg_name = NULL;
-	msg->msg_namelen = 0;
-	msg->msg_control = NULL;
-	msg->msg_controllen = 0;
-	msg->msg_iov = (struct iovec *)iov;
-	msg->msg_iovlen = nr_segs;
-	msg->msg_flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0;
-	if (sock->type == SOCK_SEQPACKET)
-		msg->msg_flags |= MSG_EOR;
-
-	return __sock_sendmsg(iocb, sock, msg, size);
-}
-
-static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov,
-			  unsigned long nr_segs, loff_t pos)
-{
-	struct sock_iocb siocb, *x;
+	struct msghdr msg = {.msg_iter = *from,
+			     .msg_iocb = iocb};
+	ssize_t res;
 
-	if (pos != 0)
+	if (iocb->ki_pos != 0)
 		return -ESPIPE;
 
-	x = alloc_sock_iocb(iocb, &siocb);
-	if (!x)
-		return -ENOMEM;
+	if (file->f_flags & O_NONBLOCK)
+		msg.msg_flags = MSG_DONTWAIT;
 
-	return do_sock_write(&x->async_msg, iocb, iocb->ki_filp, iov, nr_segs);
+	if (sock->type == SOCK_SEQPACKET)
+		msg.msg_flags |= MSG_EOR;
+
+	res = sock_sendmsg(sock, &msg);
+	*from = msg.msg_iter;
+	return res;
 }
 
 /*
@@ -1791,17 +1636,14 @@ SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len,
 	struct iovec iov;
 	int fput_needed;
 
-	if (len > INT_MAX)
-		len = INT_MAX;
+	err = import_single_range(WRITE, buff, len, &iov, &msg.msg_iter);
+	if (unlikely(err))
+		return err;
 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
 	if (!sock)
 		goto out;
 
-	iov.iov_base = buff;
-	iov.iov_len = len;
 	msg.msg_name = NULL;
-	msg.msg_iov = &iov;
-	msg.msg_iovlen = 1;
 	msg.msg_control = NULL;
 	msg.msg_controllen = 0;
 	msg.msg_namelen = 0;
@@ -1815,7 +1657,7 @@ SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len,
 	if (sock->file->f_flags & O_NONBLOCK)
 		flags |= MSG_DONTWAIT;
 	msg.msg_flags = flags;
-	err = sock_sendmsg(sock, &msg, len);
+	err = sock_sendmsg(sock, &msg);
 
 out_put:
 	fput_light(sock->file, fput_needed);
@@ -1850,25 +1692,22 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size,
 	int err, err2;
 	int fput_needed;
 
-	if (size > INT_MAX)
-		size = INT_MAX;
+	err = import_single_range(READ, ubuf, size, &iov, &msg.msg_iter);
+	if (unlikely(err))
+		return err;
 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
 	if (!sock)
 		goto out;
 
 	msg.msg_control = NULL;
 	msg.msg_controllen = 0;
-	msg.msg_iovlen = 1;
-	msg.msg_iov = &iov;
-	iov.iov_len = size;
-	iov.iov_base = ubuf;
 	/* Save some cycles and don't copy the address if not needed */
 	msg.msg_name = addr ? (struct sockaddr *)&address : NULL;
 	/* We assume all kernel code knows the size of sockaddr_storage */
 	msg.msg_namelen = 0;
 	if (sock->file->f_flags & O_NONBLOCK)
 		flags |= MSG_DONTWAIT;
-	err = sock_recvmsg(sock, &msg, size, flags);
+	err = sock_recvmsg(sock, &msg, iov_iter_count(&msg.msg_iter), flags);
 
 	if (err >= 0 && addr != NULL) {
 		err2 = move_addr_to_user(&address,
@@ -1989,12 +1828,26 @@ struct used_address {
 };
 
 static int copy_msghdr_from_user(struct msghdr *kmsg,
-				 struct msghdr __user *umsg)
+				 struct user_msghdr __user *umsg,
+				 struct sockaddr __user **save_addr,
+				 struct iovec **iov)
 {
-	if (copy_from_user(kmsg, umsg, sizeof(struct msghdr)))
+	struct sockaddr __user *uaddr;
+	struct iovec __user *uiov;
+	size_t nr_segs;
+	ssize_t err;
+
+	if (!access_ok(VERIFY_READ, umsg, sizeof(*umsg)) ||
+	    __get_user(uaddr, &umsg->msg_name) ||
+	    __get_user(kmsg->msg_namelen, &umsg->msg_namelen) ||
+	    __get_user(uiov, &umsg->msg_iov) ||
+	    __get_user(nr_segs, &umsg->msg_iovlen) ||
+	    __get_user(kmsg->msg_control, &umsg->msg_control) ||
+	    __get_user(kmsg->msg_controllen, &umsg->msg_controllen) ||
+	    __get_user(kmsg->msg_flags, &umsg->msg_flags))
 		return -EFAULT;
 
-	if (kmsg->msg_name == NULL)
+	if (!uaddr)
 		kmsg->msg_namelen = 0;
 
 	if (kmsg->msg_namelen < 0)
@@ -2002,10 +1855,32 @@ static int copy_msghdr_from_user(struct msghdr *kmsg,
 
 	if (kmsg->msg_namelen > sizeof(struct sockaddr_storage))
 		kmsg->msg_namelen = sizeof(struct sockaddr_storage);
-	return 0;
+
+	if (save_addr)
+		*save_addr = uaddr;
+
+	if (uaddr && kmsg->msg_namelen) {
+		if (!save_addr) {
+			err = move_addr_to_kernel(uaddr, kmsg->msg_namelen,
+						  kmsg->msg_name);
+			if (err < 0)
+				return err;
+		}
+	} else {
+		kmsg->msg_name = NULL;
+		kmsg->msg_namelen = 0;
+	}
+
+	if (nr_segs > UIO_MAXIOV)
+		return -EMSGSIZE;
+
+	kmsg->msg_iocb = NULL;
+
+	return import_iovec(save_addr ? READ : WRITE, uiov, nr_segs,
+			    UIO_FASTIOV, iov, &kmsg->msg_iter);
 }
 
-static int ___sys_sendmsg(struct socket *sock, struct msghdr __user *msg,
+static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg,
 			 struct msghdr *msg_sys, unsigned int flags,
 			 struct used_address *used_address)
 {
@@ -2017,37 +1892,17 @@ static int ___sys_sendmsg(struct socket *sock, struct msghdr __user *msg,
 	    __attribute__ ((aligned(sizeof(__kernel_size_t))));
 	/* 20 is size of ipv6_pktinfo */
 	unsigned char *ctl_buf = ctl;
-	int err, ctl_len, total_len;
+	int ctl_len;
+	ssize_t err;
 
-	err = -EFAULT;
-	if (MSG_CMSG_COMPAT & flags) {
-		if (get_compat_msghdr(msg_sys, msg_compat))
-			return -EFAULT;
-	} else {
-		err = copy_msghdr_from_user(msg_sys, msg);
-		if (err)
-			return err;
-	}
+	msg_sys->msg_name = &address;
 
-	if (msg_sys->msg_iovlen > UIO_FASTIOV) {
-		err = -EMSGSIZE;
-		if (msg_sys->msg_iovlen > UIO_MAXIOV)
-			goto out;
-		err = -ENOMEM;
-		iov = kmalloc(msg_sys->msg_iovlen * sizeof(struct iovec),
-			      GFP_KERNEL);
-		if (!iov)
-			goto out;
-	}
-
-	/* This will also move the address data into kernel space */
-	if (MSG_CMSG_COMPAT & flags) {
-		err = verify_compat_iovec(msg_sys, iov, &address, VERIFY_READ);
-	} else
-		err = verify_iovec(msg_sys, iov, &address, VERIFY_READ);
+	if (MSG_CMSG_COMPAT & flags)
+		err = get_compat_msghdr(msg_sys, msg_compat, NULL, &iov);
+	else
+		err = copy_msghdr_from_user(msg_sys, msg, NULL, &iov);
 	if (err < 0)
-		goto out_freeiov;
-	total_len = err;
+		return err;
 
 	err = -ENOBUFS;
 
@@ -2094,10 +1949,10 @@ static int ___sys_sendmsg(struct socket *sock, struct msghdr __user *msg,
 	    used_address->name_len == msg_sys->msg_namelen &&
 	    !memcmp(&used_address->name, msg_sys->msg_name,
 		    used_address->name_len)) {
-		err = sock_sendmsg_nosec(sock, msg_sys, total_len);
+		err = sock_sendmsg_nosec(sock, msg_sys);
 		goto out_freectl;
 	}
-	err = sock_sendmsg(sock, msg_sys, total_len);
+	err = sock_sendmsg(sock, msg_sys);
 	/*
 	 * If this is sendmmsg() and sending to current destination address was
 	 * successful, remember it.
@@ -2113,9 +1968,7 @@ out_freectl:
 	if (ctl_buf != ctl)
 		sock_kfree_s(sock->sk, ctl_buf, ctl_len);
 out_freeiov:
-	if (iov != iovstack)
-		kfree(iov);
-out:
+	kfree(iov);
 	return err;
 }
 
@@ -2123,7 +1976,7 @@ out:
  *	BSD sendmsg interface
  */
 
-long __sys_sendmsg(int fd, struct msghdr __user *msg, unsigned flags)
+long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned flags)
 {
 	int fput_needed, err;
 	struct msghdr msg_sys;
@@ -2140,7 +1993,7 @@ out:
 	return err;
 }
 
-SYSCALL_DEFINE3(sendmsg, int, fd, struct msghdr __user *, msg, unsigned int, flags)
+SYSCALL_DEFINE3(sendmsg, int, fd, struct user_msghdr __user *, msg, unsigned int, flags)
 {
 	if (flags & MSG_CMSG_COMPAT)
 		return -EINVAL;
@@ -2177,7 +2030,7 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
 
 	while (datagrams < vlen) {
 		if (MSG_CMSG_COMPAT & flags) {
-			err = ___sys_sendmsg(sock, (struct msghdr __user *)compat_entry,
+			err = ___sys_sendmsg(sock, (struct user_msghdr __user *)compat_entry,
 					     &msg_sys, flags, &used_address);
 			if (err < 0)
 				break;
@@ -2185,7 +2038,7 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
 			++compat_entry;
 		} else {
 			err = ___sys_sendmsg(sock,
-					     (struct msghdr __user *)entry,
+					     (struct user_msghdr __user *)entry,
 					     &msg_sys, flags, &used_address);
 			if (err < 0)
 				break;
@@ -2215,7 +2068,7 @@ SYSCALL_DEFINE4(sendmmsg, int, fd, struct mmsghdr __user *, mmsg,
 	return __sys_sendmmsg(fd, mmsg, vlen, flags);
 }
 
-static int ___sys_recvmsg(struct socket *sock, struct msghdr __user *msg,
+static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg,
 			 struct msghdr *msg_sys, unsigned int flags, int nosec)
 {
 	struct compat_msghdr __user *msg_compat =
@@ -2223,47 +2076,25 @@ static int ___sys_recvmsg(struct socket *sock, struct msghdr __user *msg,
 	struct iovec iovstack[UIO_FASTIOV];
 	struct iovec *iov = iovstack;
 	unsigned long cmsg_ptr;
-	int err, total_len, len;
+	int total_len, len;
+	ssize_t err;
 
 	/* kernel mode address */
 	struct sockaddr_storage addr;
 
 	/* user mode address pointers */
 	struct sockaddr __user *uaddr;
-	int __user *uaddr_len;
+	int __user *uaddr_len = COMPAT_NAMELEN(msg);
 
-	if (MSG_CMSG_COMPAT & flags) {
-		if (get_compat_msghdr(msg_sys, msg_compat))
-			return -EFAULT;
-	} else {
-		err = copy_msghdr_from_user(msg_sys, msg);
-		if (err)
-			return err;
-	}
+	msg_sys->msg_name = &addr;
 
-	if (msg_sys->msg_iovlen > UIO_FASTIOV) {
-		err = -EMSGSIZE;
-		if (msg_sys->msg_iovlen > UIO_MAXIOV)
-			goto out;
-		err = -ENOMEM;
-		iov = kmalloc(msg_sys->msg_iovlen * sizeof(struct iovec),
-			      GFP_KERNEL);
-		if (!iov)
-			goto out;
-	}
-
-	/* Save the user-mode address (verify_iovec will change the
-	 * kernel msghdr to use the kernel address space)
-	 */
-	uaddr = (__force void __user *)msg_sys->msg_name;
-	uaddr_len = COMPAT_NAMELEN(msg);
 	if (MSG_CMSG_COMPAT & flags)
-		err = verify_compat_iovec(msg_sys, iov, &addr, VERIFY_WRITE);
+		err = get_compat_msghdr(msg_sys, msg_compat, &uaddr, &iov);
 	else
-		err = verify_iovec(msg_sys, iov, &addr, VERIFY_WRITE);
+		err = copy_msghdr_from_user(msg_sys, msg, &uaddr, &iov);
 	if (err < 0)
-		goto out_freeiov;
-	total_len = err;
+		return err;
+	total_len = iov_iter_count(&msg_sys->msg_iter);
 
 	cmsg_ptr = (unsigned long)msg_sys->msg_control;
 	msg_sys->msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT);
@@ -2301,9 +2132,7 @@ static int ___sys_recvmsg(struct socket *sock, struct msghdr __user *msg,
 	err = len;
 
 out_freeiov:
-	if (iov != iovstack)
-		kfree(iov);
-out:
+	kfree(iov);
 	return err;
 }
 
@@ -2311,7 +2140,7 @@ out:
  *	BSD recvmsg interface
  */
 
-long __sys_recvmsg(int fd, struct msghdr __user *msg, unsigned flags)
+long __sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned flags)
 {
 	int fput_needed, err;
 	struct msghdr msg_sys;
@@ -2328,7 +2157,7 @@ out:
 	return err;
 }
 
-SYSCALL_DEFINE3(recvmsg, int, fd, struct msghdr __user *, msg,
+SYSCALL_DEFINE3(recvmsg, int, fd, struct user_msghdr __user *, msg,
 		unsigned int, flags)
 {
 	if (flags & MSG_CMSG_COMPAT)
@@ -2373,7 +2202,7 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
 		 * No need to ask LSM for more than the first datagram.
 		 */
 		if (MSG_CMSG_COMPAT & flags) {
-			err = ___sys_recvmsg(sock, (struct msghdr __user *)compat_entry,
+			err = ___sys_recvmsg(sock, (struct user_msghdr __user *)compat_entry,
 					     &msg_sys, flags & ~MSG_WAITFORONE,
 					     datagrams);
 			if (err < 0)
@@ -2382,7 +2211,7 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
 			++compat_entry;
 		} else {
 			err = ___sys_recvmsg(sock,
-					     (struct msghdr __user *)entry,
+					     (struct user_msghdr __user *)entry,
 					     &msg_sys, flags & ~MSG_WAITFORONE,
 					     datagrams);
 			if (err < 0)
@@ -2571,13 +2400,13 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
 				   (int __user *)a[4]);
 		break;
 	case SYS_SENDMSG:
-		err = sys_sendmsg(a0, (struct msghdr __user *)a1, a[2]);
+		err = sys_sendmsg(a0, (struct user_msghdr __user *)a1, a[2]);
 		break;
 	case SYS_SENDMMSG:
 		err = sys_sendmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3]);
 		break;
 	case SYS_RECVMSG:
-		err = sys_recvmsg(a0, (struct msghdr __user *)a1, a[2]);
+		err = sys_recvmsg(a0, (struct user_msghdr __user *)a1, a[2]);
 		break;
 	case SYS_RECVMMSG:
 		err = sys_recvmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3],
diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig
index 0754d0f466d2..9068e72aa73c 100644
--- a/net/sunrpc/Kconfig
+++ b/net/sunrpc/Kconfig
@@ -1,9 +1,11 @@
 config SUNRPC
 	tristate
+	depends on MULTIUSER
 
 config SUNRPC_GSS
 	tristate
 	select OID_REGISTRY
+	depends on MULTIUSER
 
 config SUNRPC_BACKCHANNEL
 	bool
@@ -35,6 +37,7 @@ config RPCSEC_GSS_KRB5
 config SUNRPC_DEBUG
 	bool "RPC: Enable dprintk debugging"
 	depends on SUNRPC && SYSCTL
+	select DEBUG_FS
 	help
 	  This option enables a sysctl-based debugging interface
 	  that is be used by the 'rpcdebug' utility to turn on or off
diff --git a/net/sunrpc/Makefile b/net/sunrpc/Makefile
index e5a7a1cac8f3..15e6f6c23c5d 100644
--- a/net/sunrpc/Makefile
+++ b/net/sunrpc/Makefile
@@ -14,6 +14,7 @@ sunrpc-y := clnt.o xprt.o socklib.o xprtsock.o sched.o \
 	    addr.o rpcb_clnt.o timer.o xdr.o \
 	    sunrpc_syms.o cache.o rpc_pipe.o \
 	    svc_xprt.o
+sunrpc-$(CONFIG_SUNRPC_DEBUG) += debugfs.o
 sunrpc-$(CONFIG_SUNRPC_BACKCHANNEL) += backchannel_rqst.o bc_svc.o
 sunrpc-$(CONFIG_PROC_FS) += stats.o
 sunrpc-$(CONFIG_SYSCTL) += sysctl.o
diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index 383eb919ac0b..47f38be4155f 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -16,7 +16,7 @@
 #include <linux/sunrpc/gss_api.h>
 #include <linux/spinlock.h>
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_AUTH
 #endif
 
@@ -646,7 +646,7 @@ rpcauth_init_cred(struct rpc_cred *cred, const struct auth_cred *acred,
 	cred->cr_auth = auth;
 	cred->cr_ops = ops;
 	cred->cr_expire = jiffies;
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	cred->cr_magic = RPCAUTH_CRED_MAGIC;
 #endif
 	cred->cr_uid = acred->uid;
diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c
index 6f6b829c9e8e..41248b1820c7 100644
--- a/net/sunrpc/auth_generic.c
+++ b/net/sunrpc/auth_generic.c
@@ -14,7 +14,7 @@
 #include <linux/sunrpc/debug.h>
 #include <linux/sunrpc/sched.h>
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_AUTH
 #endif
 
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 53ed8d3f8897..dace13d7638e 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -66,7 +66,7 @@ static unsigned int gss_expired_cred_retry_delay = GSS_RETRY_EXPIRED;
 #define GSS_KEY_EXPIRE_TIMEO 240
 static unsigned int gss_key_expire_timeo = GSS_KEY_EXPIRE_TIMEO;
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_AUTH
 #endif
 
diff --git a/net/sunrpc/auth_gss/gss_generic_token.c b/net/sunrpc/auth_gss/gss_generic_token.c
index c586e92bcf76..254defe446a7 100644
--- a/net/sunrpc/auth_gss/gss_generic_token.c
+++ b/net/sunrpc/auth_gss/gss_generic_token.c
@@ -38,7 +38,7 @@
 #include <linux/sunrpc/gss_asn1.h>
 
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY        RPCDBG_AUTH
 #endif
 
diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c
index f5ed9f6ece06..b5408e8a37f2 100644
--- a/net/sunrpc/auth_gss/gss_krb5_crypto.c
+++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c
@@ -45,7 +45,7 @@
 #include <linux/sunrpc/gss_krb5.h>
 #include <linux/sunrpc/xdr.h>
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY        RPCDBG_AUTH
 #endif
 
diff --git a/net/sunrpc/auth_gss/gss_krb5_keys.c b/net/sunrpc/auth_gss/gss_krb5_keys.c
index 24589bd2a4b6..234fa8d0fd9b 100644
--- a/net/sunrpc/auth_gss/gss_krb5_keys.c
+++ b/net/sunrpc/auth_gss/gss_krb5_keys.c
@@ -61,7 +61,7 @@
 #include <linux/sunrpc/xdr.h>
 #include <linux/lcm.h>
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY        RPCDBG_AUTH
 #endif
 
diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c
index 0d3c158ef8fa..28db442a0034 100644
--- a/net/sunrpc/auth_gss/gss_krb5_mech.c
+++ b/net/sunrpc/auth_gss/gss_krb5_mech.c
@@ -45,7 +45,7 @@
 #include <linux/crypto.h>
 #include <linux/sunrpc/gss_krb5_enctypes.h>
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_AUTH
 #endif
 
diff --git a/net/sunrpc/auth_gss/gss_krb5_seal.c b/net/sunrpc/auth_gss/gss_krb5_seal.c
index 42768e5c3994..1d74d653e6c0 100644
--- a/net/sunrpc/auth_gss/gss_krb5_seal.c
+++ b/net/sunrpc/auth_gss/gss_krb5_seal.c
@@ -64,7 +64,7 @@
 #include <linux/random.h>
 #include <linux/crypto.h>
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY        RPCDBG_AUTH
 #endif
 
diff --git a/net/sunrpc/auth_gss/gss_krb5_seqnum.c b/net/sunrpc/auth_gss/gss_krb5_seqnum.c
index 62ac90c62cb1..20d55c793eb6 100644
--- a/net/sunrpc/auth_gss/gss_krb5_seqnum.c
+++ b/net/sunrpc/auth_gss/gss_krb5_seqnum.c
@@ -35,7 +35,7 @@
 #include <linux/sunrpc/gss_krb5.h>
 #include <linux/crypto.h>
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY        RPCDBG_AUTH
 #endif
 
diff --git a/net/sunrpc/auth_gss/gss_krb5_unseal.c b/net/sunrpc/auth_gss/gss_krb5_unseal.c
index 6c981ddc19f8..dcf9515d9aef 100644
--- a/net/sunrpc/auth_gss/gss_krb5_unseal.c
+++ b/net/sunrpc/auth_gss/gss_krb5_unseal.c
@@ -62,7 +62,7 @@
 #include <linux/sunrpc/gss_krb5.h>
 #include <linux/crypto.h>
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY        RPCDBG_AUTH
 #endif
 
diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c
index 4b614c604fe0..ca7e92a32f84 100644
--- a/net/sunrpc/auth_gss/gss_krb5_wrap.c
+++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c
@@ -35,7 +35,7 @@
 #include <linux/pagemap.h>
 #include <linux/crypto.h>
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_AUTH
 #endif
 
diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c
index 92d5ab99fbf3..7063d856a598 100644
--- a/net/sunrpc/auth_gss/gss_mech_switch.c
+++ b/net/sunrpc/auth_gss/gss_mech_switch.c
@@ -46,7 +46,7 @@
 #include <linux/sunrpc/gss_api.h>
 #include <linux/sunrpc/clnt.h>
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY        RPCDBG_AUTH
 #endif
 
diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c
index abbb7dcd1689..59eeed43eda2 100644
--- a/net/sunrpc/auth_gss/gss_rpc_upcall.c
+++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c
@@ -217,6 +217,8 @@ static void gssp_free_receive_pages(struct gssx_arg_accept_sec_context *arg)
 
 	for (i = 0; i < arg->npages && arg->pages[i]; i++)
 		__free_page(arg->pages[i]);
+
+	kfree(arg->pages);
 }
 
 static int gssp_alloc_receive_pages(struct gssx_arg_accept_sec_context *arg)
diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c
index 1ec19f6f0c2b..eeeba5adee6d 100644
--- a/net/sunrpc/auth_gss/gss_rpc_xdr.c
+++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c
@@ -793,20 +793,26 @@ int gssx_dec_accept_sec_context(struct rpc_rqst *rqstp,
 {
 	u32 value_follows;
 	int err;
+	struct page *scratch;
+
+	scratch = alloc_page(GFP_KERNEL);
+	if (!scratch)
+		return -ENOMEM;
+	xdr_set_scratch_buffer(xdr, page_address(scratch), PAGE_SIZE);
 
 	/* res->status */
 	err = gssx_dec_status(xdr, &res->status);
 	if (err)
-		return err;
+		goto out_free;
 
 	/* res->context_handle */
 	err = gssx_dec_bool(xdr, &value_follows);
 	if (err)
-		return err;
+		goto out_free;
 	if (value_follows) {
 		err = gssx_dec_ctx(xdr, res->context_handle);
 		if (err)
-			return err;
+			goto out_free;
 	} else {
 		res->context_handle = NULL;
 	}
@@ -814,11 +820,11 @@ int gssx_dec_accept_sec_context(struct rpc_rqst *rqstp,
 	/* res->output_token */
 	err = gssx_dec_bool(xdr, &value_follows);
 	if (err)
-		return err;
+		goto out_free;
 	if (value_follows) {
 		err = gssx_dec_buffer(xdr, res->output_token);
 		if (err)
-			return err;
+			goto out_free;
 	} else {
 		res->output_token = NULL;
 	}
@@ -826,14 +832,17 @@ int gssx_dec_accept_sec_context(struct rpc_rqst *rqstp,
 	/* res->delegated_cred_handle */
 	err = gssx_dec_bool(xdr, &value_follows);
 	if (err)
-		return err;
+		goto out_free;
 	if (value_follows) {
 		/* we do not support upcall servers sending this data. */
-		return -EINVAL;
+		err = -EINVAL;
+		goto out_free;
 	}
 
 	/* res->options */
 	err = gssx_dec_option_array(xdr, &res->options);
 
+out_free:
+	__free_page(scratch);
 	return err;
 }
diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.h b/net/sunrpc/auth_gss/gss_rpc_xdr.h
index 685a688f3d8a..9d88c6239f01 100644
--- a/net/sunrpc/auth_gss/gss_rpc_xdr.h
+++ b/net/sunrpc/auth_gss/gss_rpc_xdr.h
@@ -25,7 +25,7 @@
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/xprtsock.h>
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_AUTH
 #endif
 
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index c548ab213f76..1095be9c80ab 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -51,7 +51,7 @@
 #include "gss_rpc_upcall.h"
 
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_AUTH
 #endif
 
@@ -463,6 +463,8 @@ static int rsc_parse(struct cache_detail *cd,
 		/* number of additional gid's */
 		if (get_int(&mesg, &N))
 			goto out;
+		if (N < 0 || N > NGROUPS_MAX)
+			goto out;
 		status = -ENOMEM;
 		rsci.cred.cr_group_info = groups_alloc(N);
 		if (rsci.cred.cr_group_info == NULL)
@@ -886,7 +888,7 @@ unwrap_priv_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct gs
 	u32 priv_len, maj_stat;
 	int pad, saved_len, remaining_len, offset;
 
-	rqstp->rq_splice_ok = false;
+	clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
 
 	priv_len = svc_getnl(&buf->head[0]);
 	if (rqstp->rq_deferred) {
diff --git a/net/sunrpc/auth_null.c b/net/sunrpc/auth_null.c
index 712c123e04e9..c2a2b584a056 100644
--- a/net/sunrpc/auth_null.c
+++ b/net/sunrpc/auth_null.c
@@ -10,7 +10,7 @@
 #include <linux/module.h>
 #include <linux/sunrpc/clnt.h>
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_AUTH
 #endif
 
@@ -138,7 +138,7 @@ struct rpc_cred null_cred = {
 	.cr_ops		= &null_credops,
 	.cr_count	= ATOMIC_INIT(1),
 	.cr_flags	= 1UL << RPCAUTH_CRED_UPTODATE,
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	.cr_magic	= RPCAUTH_CRED_MAGIC,
 #endif
 };
diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c
index d5d692366294..4feda2d0a833 100644
--- a/net/sunrpc/auth_unix.c
+++ b/net/sunrpc/auth_unix.c
@@ -25,7 +25,7 @@ struct unx_cred {
 
 #define UNX_WRITESLACK		(21 + (UNX_MAXNODENAME >> 2))
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_AUTH
 #endif
 
diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c
index 9761a0da964d..9dd0ea8db463 100644
--- a/net/sunrpc/backchannel_rqst.c
+++ b/net/sunrpc/backchannel_rqst.c
@@ -27,7 +27,7 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #include <linux/export.h>
 #include <linux/sunrpc/bc_xprt.h>
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 #define RPCDBG_FACILITY	RPCDBG_TRANS
 #endif
 
@@ -309,12 +309,15 @@ 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;
 
+	spin_lock(&xprt->bc_pa_lock);
+	list_del(&req->rq_bc_pa_list);
+	spin_unlock(&xprt->bc_pa_lock);
+
 	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 066362141133..2928afffbb81 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -20,6 +20,7 @@
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/ctype.h>
+#include <linux/string_helpers.h>
 #include <asm/uaccess.h>
 #include <linux/poll.h>
 #include <linux/seq_file.h>
@@ -920,7 +921,7 @@ static unsigned int cache_poll(struct file *filp, poll_table *wait,
 	poll_wait(filp, &queue_wait, wait);
 
 	/* alway allow write */
-	mask = POLL_OUT | POLLWRNORM;
+	mask = POLLOUT | POLLWRNORM;
 
 	if (!rp)
 		return mask;
@@ -1067,30 +1068,17 @@ void qword_add(char **bpp, int *lp, char *str)
 {
 	char *bp = *bpp;
 	int len = *lp;
-	char c;
+	int ret;
 
 	if (len < 0) return;
 
-	while ((c=*str++) && len)
-		switch(c) {
-		case ' ':
-		case '\t':
-		case '\n':
-		case '\\':
-			if (len >= 4) {
-				*bp++ = '\\';
-				*bp++ = '0' + ((c & 0300)>>6);
-				*bp++ = '0' + ((c & 0070)>>3);
-				*bp++ = '0' + ((c & 0007)>>0);
-			}
-			len -= 4;
-			break;
-		default:
-			*bp++ = c;
-			len--;
-		}
-	if (c || len <1) len = -1;
-	else {
+	ret = string_escape_str(str, bp, len, ESCAPE_OCTAL, "\\ \n\t");
+	if (ret >= len) {
+		bp += len;
+		len = -1;
+	} else {
+		bp += ret;
+		len -= ret;
 		*bp++ = ' ';
 		len--;
 	}
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 9acd6ce88db7..e6ce1517367f 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -42,7 +42,7 @@
 #include "sunrpc.h"
 #include "netns.h"
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_CALL
 #endif
 
@@ -286,10 +286,8 @@ static struct rpc_xprt *rpc_clnt_set_transport(struct rpc_clnt *clnt,
 
 static void rpc_clnt_set_nodename(struct rpc_clnt *clnt, const char *nodename)
 {
-	clnt->cl_nodelen = strlen(nodename);
-	if (clnt->cl_nodelen > UNX_MAXNODENAME)
-		clnt->cl_nodelen = UNX_MAXNODENAME;
-	memcpy(clnt->cl_nodename, nodename, clnt->cl_nodelen);
+	clnt->cl_nodelen = strlcpy(clnt->cl_nodename,
+			nodename, sizeof(clnt->cl_nodename));
 }
 
 static int rpc_client_register(struct rpc_clnt *clnt,
@@ -305,6 +303,8 @@ static int rpc_client_register(struct rpc_clnt *clnt,
 	struct super_block *pipefs_sb;
 	int err;
 
+	rpc_clnt_debugfs_register(clnt);
+
 	pipefs_sb = rpc_get_sb_net(net);
 	if (pipefs_sb) {
 		err = rpc_setup_pipedir(pipefs_sb, clnt);
@@ -331,6 +331,7 @@ err_auth:
 out:
 	if (pipefs_sb)
 		rpc_put_sb_net(net);
+	rpc_clnt_debugfs_unregister(clnt);
 	return err;
 }
 
@@ -360,6 +361,7 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args,
 	const struct rpc_version *version;
 	struct rpc_clnt *clnt = NULL;
 	const struct rpc_timeout *timeout;
+	const char *nodename = args->nodename;
 	int err;
 
 	/* sanity check the name before trying to print it */
@@ -415,8 +417,10 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args,
 
 	atomic_set(&clnt->cl_count, 1);
 
+	if (nodename == NULL)
+		nodename = utsname()->nodename;
 	/* save the nodename */
-	rpc_clnt_set_nodename(clnt, utsname()->nodename);
+	rpc_clnt_set_nodename(clnt, nodename);
 
 	err = rpc_client_register(clnt, args->authflavor, args->client_name);
 	if (err)
@@ -571,6 +575,7 @@ static struct rpc_clnt *__rpc_clone_client(struct rpc_create_args *args,
 	if (xprt == NULL)
 		goto out_err;
 	args->servername = xprt->servername;
+	args->nodename = clnt->cl_nodename;
 
 	new = rpc_new_client(args, xprt, clnt);
 	if (IS_ERR(new)) {
@@ -670,6 +675,7 @@ int rpc_switch_client_transport(struct rpc_clnt *clnt,
 
 	rpc_unregister_client(clnt);
 	__rpc_clnt_remove_pipedir(clnt);
+	rpc_clnt_debugfs_unregister(clnt);
 
 	/*
 	 * A new transport was created.  "clnt" therefore
@@ -771,6 +777,7 @@ rpc_free_client(struct rpc_clnt *clnt)
 			rcu_dereference(clnt->cl_xprt)->servername);
 	if (clnt->cl_parent != clnt)
 		parent = clnt->cl_parent;
+	rpc_clnt_debugfs_unregister(clnt);
 	rpc_clnt_remove_pipedir(clnt);
 	rpc_unregister_client(clnt);
 	rpc_free_iostats(clnt->cl_metrics);
@@ -1396,8 +1403,9 @@ rpc_restart_call(struct rpc_task *task)
 }
 EXPORT_SYMBOL_GPL(rpc_restart_call);
 
-#ifdef RPC_DEBUG
-static const char *rpc_proc_name(const struct rpc_task *task)
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
+const char
+*rpc_proc_name(const struct rpc_task *task)
 {
 	const struct rpc_procinfo *proc = task->tk_msg.rpc_proc;
 
@@ -1816,6 +1824,7 @@ call_connect_status(struct rpc_task *task)
 	case -ECONNABORTED:
 	case -ENETUNREACH:
 	case -EHOSTUNREACH:
+	case -EADDRINUSE:
 	case -ENOBUFS:
 	case -EPIPE:
 		if (RPC_IS_SOFTCONN(task))
@@ -1924,6 +1933,7 @@ call_transmit_status(struct rpc_task *task)
 		}
 	case -ECONNRESET:
 	case -ECONNABORTED:
+	case -EADDRINUSE:
 	case -ENOTCONN:
 	case -ENOBUFS:
 	case -EPIPE:
@@ -2043,6 +2053,7 @@ call_status(struct rpc_task *task)
 	case -ECONNRESET:
 	case -ECONNABORTED:
 		rpc_force_rebind(clnt);
+	case -EADDRINUSE:
 	case -ENOBUFS:
 		rpc_delay(task, 3*HZ);
 	case -EPIPE:
@@ -2421,7 +2432,7 @@ struct rpc_task *rpc_call_null(struct rpc_clnt *clnt, struct rpc_cred *cred, int
 }
 EXPORT_SYMBOL_GPL(rpc_call_null);
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 static void rpc_show_header(void)
 {
 	printk(KERN_INFO "-pid- flgs status -client- --rqstp- "
diff --git a/net/sunrpc/debugfs.c b/net/sunrpc/debugfs.c
new file mode 100644
index 000000000000..82962f7e6e88
--- /dev/null
+++ b/net/sunrpc/debugfs.c
@@ -0,0 +1,298 @@
+/**
+ * debugfs interface for sunrpc
+ *
+ * (c) 2014 Jeff Layton <jlayton@primarydata.com>
+ */
+
+#include <linux/debugfs.h>
+#include <linux/sunrpc/sched.h>
+#include <linux/sunrpc/clnt.h>
+#include "netns.h"
+
+static struct dentry *topdir;
+static struct dentry *rpc_clnt_dir;
+static struct dentry *rpc_xprt_dir;
+
+struct rpc_clnt_iter {
+	struct rpc_clnt	*clnt;
+	loff_t		pos;
+};
+
+static int
+tasks_show(struct seq_file *f, void *v)
+{
+	u32 xid = 0;
+	struct rpc_task *task = v;
+	struct rpc_clnt *clnt = task->tk_client;
+	const char *rpc_waitq = "none";
+
+	if (RPC_IS_QUEUED(task))
+		rpc_waitq = rpc_qname(task->tk_waitqueue);
+
+	if (task->tk_rqstp)
+		xid = be32_to_cpu(task->tk_rqstp->rq_xid);
+
+	seq_printf(f, "%5u %04x %6d 0x%x 0x%x %8ld %ps %sv%u %s a:%ps q:%s\n",
+		task->tk_pid, task->tk_flags, task->tk_status,
+		clnt->cl_clid, xid, task->tk_timeout, task->tk_ops,
+		clnt->cl_program->name, clnt->cl_vers, rpc_proc_name(task),
+		task->tk_action, rpc_waitq);
+	return 0;
+}
+
+static void *
+tasks_start(struct seq_file *f, loff_t *ppos)
+	__acquires(&clnt->cl_lock)
+{
+	struct rpc_clnt_iter *iter = f->private;
+	loff_t pos = *ppos;
+	struct rpc_clnt *clnt = iter->clnt;
+	struct rpc_task *task;
+
+	iter->pos = pos + 1;
+	spin_lock(&clnt->cl_lock);
+	list_for_each_entry(task, &clnt->cl_tasks, tk_task)
+		if (pos-- == 0)
+			return task;
+	return NULL;
+}
+
+static void *
+tasks_next(struct seq_file *f, void *v, loff_t *pos)
+{
+	struct rpc_clnt_iter *iter = f->private;
+	struct rpc_clnt *clnt = iter->clnt;
+	struct rpc_task *task = v;
+	struct list_head *next = task->tk_task.next;
+
+	++iter->pos;
+	++*pos;
+
+	/* If there's another task on list, return it */
+	if (next == &clnt->cl_tasks)
+		return NULL;
+	return list_entry(next, struct rpc_task, tk_task);
+}
+
+static void
+tasks_stop(struct seq_file *f, void *v)
+	__releases(&clnt->cl_lock)
+{
+	struct rpc_clnt_iter *iter = f->private;
+	struct rpc_clnt *clnt = iter->clnt;
+
+	spin_unlock(&clnt->cl_lock);
+}
+
+static const struct seq_operations tasks_seq_operations = {
+	.start	= tasks_start,
+	.next	= tasks_next,
+	.stop	= tasks_stop,
+	.show	= tasks_show,
+};
+
+static int tasks_open(struct inode *inode, struct file *filp)
+{
+	int ret = seq_open_private(filp, &tasks_seq_operations,
+					sizeof(struct rpc_clnt_iter));
+
+	if (!ret) {
+		struct seq_file *seq = filp->private_data;
+		struct rpc_clnt_iter *iter = seq->private;
+
+		iter->clnt = inode->i_private;
+
+		if (!atomic_inc_not_zero(&iter->clnt->cl_count)) {
+			seq_release_private(inode, filp);
+			ret = -EINVAL;
+		}
+	}
+
+	return ret;
+}
+
+static int
+tasks_release(struct inode *inode, struct file *filp)
+{
+	struct seq_file *seq = filp->private_data;
+	struct rpc_clnt_iter *iter = seq->private;
+
+	rpc_release_client(iter->clnt);
+	return seq_release_private(inode, filp);
+}
+
+static const struct file_operations tasks_fops = {
+	.owner		= THIS_MODULE,
+	.open		= tasks_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= tasks_release,
+};
+
+void
+rpc_clnt_debugfs_register(struct rpc_clnt *clnt)
+{
+	int len;
+	char name[24]; /* enough for "../../rpc_xprt/ + 8 hex digits + NULL */
+	struct rpc_xprt *xprt;
+
+	/* Already registered? */
+	if (clnt->cl_debugfs || !rpc_clnt_dir)
+		return;
+
+	len = snprintf(name, sizeof(name), "%x", clnt->cl_clid);
+	if (len >= sizeof(name))
+		return;
+
+	/* make the per-client dir */
+	clnt->cl_debugfs = debugfs_create_dir(name, rpc_clnt_dir);
+	if (!clnt->cl_debugfs)
+		return;
+
+	/* make tasks file */
+	if (!debugfs_create_file("tasks", S_IFREG | S_IRUSR, clnt->cl_debugfs,
+				 clnt, &tasks_fops))
+		goto out_err;
+
+	rcu_read_lock();
+	xprt = rcu_dereference(clnt->cl_xprt);
+	/* no "debugfs" dentry? Don't bother with the symlink. */
+	if (!xprt->debugfs) {
+		rcu_read_unlock();
+		return;
+	}
+	len = snprintf(name, sizeof(name), "../../rpc_xprt/%s",
+			xprt->debugfs->d_name.name);
+	rcu_read_unlock();
+
+	if (len >= sizeof(name))
+		goto out_err;
+
+	if (!debugfs_create_symlink("xprt", clnt->cl_debugfs, name))
+		goto out_err;
+
+	return;
+out_err:
+	debugfs_remove_recursive(clnt->cl_debugfs);
+	clnt->cl_debugfs = NULL;
+}
+
+void
+rpc_clnt_debugfs_unregister(struct rpc_clnt *clnt)
+{
+	debugfs_remove_recursive(clnt->cl_debugfs);
+	clnt->cl_debugfs = NULL;
+}
+
+static int
+xprt_info_show(struct seq_file *f, void *v)
+{
+	struct rpc_xprt *xprt = f->private;
+
+	seq_printf(f, "netid: %s\n", xprt->address_strings[RPC_DISPLAY_NETID]);
+	seq_printf(f, "addr:  %s\n", xprt->address_strings[RPC_DISPLAY_ADDR]);
+	seq_printf(f, "port:  %s\n", xprt->address_strings[RPC_DISPLAY_PORT]);
+	seq_printf(f, "state: 0x%lx\n", xprt->state);
+	return 0;
+}
+
+static int
+xprt_info_open(struct inode *inode, struct file *filp)
+{
+	int ret;
+	struct rpc_xprt *xprt = inode->i_private;
+
+	ret = single_open(filp, xprt_info_show, xprt);
+
+	if (!ret) {
+		if (!xprt_get(xprt)) {
+			single_release(inode, filp);
+			ret = -EINVAL;
+		}
+	}
+	return ret;
+}
+
+static int
+xprt_info_release(struct inode *inode, struct file *filp)
+{
+	struct rpc_xprt *xprt = inode->i_private;
+
+	xprt_put(xprt);
+	return single_release(inode, filp);
+}
+
+static const struct file_operations xprt_info_fops = {
+	.owner		= THIS_MODULE,
+	.open		= xprt_info_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= xprt_info_release,
+};
+
+void
+rpc_xprt_debugfs_register(struct rpc_xprt *xprt)
+{
+	int len, id;
+	static atomic_t	cur_id;
+	char		name[9]; /* 8 hex digits + NULL term */
+
+	if (!rpc_xprt_dir)
+		return;
+
+	id = (unsigned int)atomic_inc_return(&cur_id);
+
+	len = snprintf(name, sizeof(name), "%x", id);
+	if (len >= sizeof(name))
+		return;
+
+	/* make the per-client dir */
+	xprt->debugfs = debugfs_create_dir(name, rpc_xprt_dir);
+	if (!xprt->debugfs)
+		return;
+
+	/* make tasks file */
+	if (!debugfs_create_file("info", S_IFREG | S_IRUSR, xprt->debugfs,
+				 xprt, &xprt_info_fops)) {
+		debugfs_remove_recursive(xprt->debugfs);
+		xprt->debugfs = NULL;
+	}
+}
+
+void
+rpc_xprt_debugfs_unregister(struct rpc_xprt *xprt)
+{
+	debugfs_remove_recursive(xprt->debugfs);
+	xprt->debugfs = NULL;
+}
+
+void __exit
+sunrpc_debugfs_exit(void)
+{
+	debugfs_remove_recursive(topdir);
+	topdir = NULL;
+	rpc_clnt_dir = NULL;
+	rpc_xprt_dir = NULL;
+}
+
+void __init
+sunrpc_debugfs_init(void)
+{
+	topdir = debugfs_create_dir("sunrpc", NULL);
+	if (!topdir)
+		return;
+
+	rpc_clnt_dir = debugfs_create_dir("rpc_clnt", topdir);
+	if (!rpc_clnt_dir)
+		goto out_remove;
+
+	rpc_xprt_dir = debugfs_create_dir("rpc_xprt", topdir);
+	if (!rpc_xprt_dir)
+		goto out_remove;
+
+	return;
+out_remove:
+	debugfs_remove_recursive(topdir);
+	topdir = NULL;
+	rpc_clnt_dir = NULL;
+}
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index 2d12b76b5a64..d81186d34558 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -94,7 +94,7 @@ rpc_timeout_upcall_queue(struct work_struct *work)
 	}
 	dentry = dget(pipe->dentry);
 	spin_unlock(&pipe->lock);
-	rpc_purge_list(dentry ? &RPC_I(dentry->d_inode)->waitq : NULL,
+	rpc_purge_list(dentry ? &RPC_I(d_inode(dentry))->waitq : NULL,
 			&free_list, destroy_msg, -ETIMEDOUT);
 	dput(dentry);
 }
@@ -152,7 +152,7 @@ rpc_queue_upcall(struct rpc_pipe *pipe, struct rpc_pipe_msg *msg)
 	dentry = dget(pipe->dentry);
 	spin_unlock(&pipe->lock);
 	if (dentry) {
-		wake_up(&RPC_I(dentry->d_inode)->waitq);
+		wake_up(&RPC_I(d_inode(dentry))->waitq);
 		dput(dentry);
 	}
 	return res;
@@ -591,7 +591,7 @@ static int __rpc_mkpipe_dentry(struct inode *dir, struct dentry *dentry,
 	err = __rpc_create_common(dir, dentry, S_IFIFO | mode, i_fop, private);
 	if (err)
 		return err;
-	rpci = RPC_I(dentry->d_inode);
+	rpci = RPC_I(d_inode(dentry));
 	rpci->private = private;
 	rpci->pipe = pipe;
 	fsnotify_create(dir, dentry);
@@ -616,7 +616,7 @@ int rpc_rmdir(struct dentry *dentry)
 	int error;
 
 	parent = dget_parent(dentry);
-	dir = parent->d_inode;
+	dir = d_inode(parent);
 	mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT);
 	error = __rpc_rmdir(dir, dentry);
 	mutex_unlock(&dir->i_mutex);
@@ -638,7 +638,7 @@ static int __rpc_unlink(struct inode *dir, struct dentry *dentry)
 
 static int __rpc_rmpipe(struct inode *dir, struct dentry *dentry)
 {
-	struct inode *inode = dentry->d_inode;
+	struct inode *inode = d_inode(dentry);
 
 	rpc_close_pipes(inode);
 	return __rpc_unlink(dir, dentry);
@@ -654,7 +654,7 @@ static struct dentry *__rpc_lookup_create_exclusive(struct dentry *parent,
 		if (!dentry)
 			return ERR_PTR(-ENOMEM);
 	}
-	if (dentry->d_inode == NULL)
+	if (d_really_is_negative(dentry))
 		return dentry;
 	dput(dentry);
 	return ERR_PTR(-EEXIST);
@@ -667,7 +667,7 @@ static void __rpc_depopulate(struct dentry *parent,
 			     const struct rpc_filelist *files,
 			     int start, int eof)
 {
-	struct inode *dir = parent->d_inode;
+	struct inode *dir = d_inode(parent);
 	struct dentry *dentry;
 	struct qstr name;
 	int i;
@@ -679,9 +679,9 @@ static void __rpc_depopulate(struct dentry *parent,
 
 		if (dentry == NULL)
 			continue;
-		if (dentry->d_inode == NULL)
+		if (d_really_is_negative(dentry))
 			goto next;
-		switch (dentry->d_inode->i_mode & S_IFMT) {
+		switch (d_inode(dentry)->i_mode & S_IFMT) {
 			default:
 				BUG();
 			case S_IFREG:
@@ -699,7 +699,7 @@ static void rpc_depopulate(struct dentry *parent,
 			   const struct rpc_filelist *files,
 			   int start, int eof)
 {
-	struct inode *dir = parent->d_inode;
+	struct inode *dir = d_inode(parent);
 
 	mutex_lock_nested(&dir->i_mutex, I_MUTEX_CHILD);
 	__rpc_depopulate(parent, files, start, eof);
@@ -711,7 +711,7 @@ static int rpc_populate(struct dentry *parent,
 			int start, int eof,
 			void *private)
 {
-	struct inode *dir = parent->d_inode;
+	struct inode *dir = d_inode(parent);
 	struct dentry *dentry;
 	int i, err;
 
@@ -754,7 +754,7 @@ static struct dentry *rpc_mkdir_populate(struct dentry *parent,
 		int (*populate)(struct dentry *, void *), void *args_populate)
 {
 	struct dentry *dentry;
-	struct inode *dir = parent->d_inode;
+	struct inode *dir = d_inode(parent);
 	int error;
 
 	mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT);
@@ -787,7 +787,7 @@ static int rpc_rmdir_depopulate(struct dentry *dentry,
 	int error;
 
 	parent = dget_parent(dentry);
-	dir = parent->d_inode;
+	dir = d_inode(parent);
 	mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT);
 	if (depopulate != NULL)
 		depopulate(dentry);
@@ -819,7 +819,7 @@ struct dentry *rpc_mkpipe_dentry(struct dentry *parent, const char *name,
 				 void *private, struct rpc_pipe *pipe)
 {
 	struct dentry *dentry;
-	struct inode *dir = parent->d_inode;
+	struct inode *dir = d_inode(parent);
 	umode_t umode = S_IFIFO | S_IRUSR | S_IWUSR;
 	int err;
 
@@ -864,7 +864,7 @@ rpc_unlink(struct dentry *dentry)
 	int error = 0;
 
 	parent = dget_parent(dentry);
-	dir = parent->d_inode;
+	dir = d_inode(parent);
 	mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT);
 	error = __rpc_rmpipe(dir, dentry);
 	mutex_unlock(&dir->i_mutex);
@@ -1375,7 +1375,7 @@ 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_rmpipe(d_inode(clnt_dir), 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);
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index 1891a1022c17..cf5770d8f49a 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -32,7 +32,7 @@
 
 #include "netns.h"
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_BIND
 #endif
 
@@ -355,7 +355,8 @@ out:
 	return result;
 }
 
-static struct rpc_clnt *rpcb_create(struct net *net, const char *hostname,
+static struct rpc_clnt *rpcb_create(struct net *net, const char *nodename,
+				    const char *hostname,
 				    struct sockaddr *srvaddr, size_t salen,
 				    int proto, u32 version)
 {
@@ -365,6 +366,7 @@ static struct rpc_clnt *rpcb_create(struct net *net, const char *hostname,
 		.address	= srvaddr,
 		.addrsize	= salen,
 		.servername	= hostname,
+		.nodename	= nodename,
 		.program	= &rpcb_program,
 		.version	= version,
 		.authflavor	= RPC_AUTH_UNIX,
@@ -740,7 +742,9 @@ void rpcb_getport_async(struct rpc_task *task)
 	dprintk("RPC: %5u %s: trying rpcbind version %u\n",
 		task->tk_pid, __func__, bind_version);
 
-	rpcb_clnt = rpcb_create(xprt->xprt_net, xprt->servername, sap, salen,
+	rpcb_clnt = rpcb_create(xprt->xprt_net,
+				clnt->cl_nodename,
+				xprt->servername, sap, salen,
 				xprt->prot, bind_version);
 	if (IS_ERR(rpcb_clnt)) {
 		status = PTR_ERR(rpcb_clnt);
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index fe3441abdbe5..337ca851a350 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -24,7 +24,7 @@
 
 #include "sunrpc.h"
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 #define RPCDBG_FACILITY		RPCDBG_SCHED
 #endif
 
@@ -89,8 +89,8 @@ __rpc_add_timer(struct rpc_wait_queue *queue, struct rpc_task *task)
 	if (!task->tk_timeout)
 		return;
 
-	dprintk("RPC: %5u setting alarm for %lu ms\n",
-			task->tk_pid, task->tk_timeout * 1000 / HZ);
+	dprintk("RPC: %5u setting alarm for %u ms\n",
+		task->tk_pid, jiffies_to_msecs(task->tk_timeout));
 
 	task->u.tk_wait.expires = jiffies + task->tk_timeout;
 	if (list_empty(&queue->timer_list.list) || time_before(task->u.tk_wait.expires, queue->timer_list.expires))
@@ -258,7 +258,7 @@ static int rpc_wait_bit_killable(struct wait_bit_key *key)
 	return 0;
 }
 
-#if defined(RPC_DEBUG) || defined(RPC_TRACEPOINTS)
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || IS_ENABLED(CONFIG_TRACEPOINTS)
 static void rpc_task_set_debuginfo(struct rpc_task *task)
 {
 	static atomic_t rpc_pid;
@@ -844,10 +844,10 @@ 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_NOWARN;
+	gfp_t gfp = GFP_NOIO | __GFP_NOWARN;
 
 	if (RPC_IS_SWAPPER(task))
-		gfp |= __GFP_MEMALLOC;
+		gfp = __GFP_MEMALLOC | GFP_NOWAIT | __GFP_NOWARN;
 
 	size += sizeof(struct rpc_buffer);
 	if (size <= RPC_BUFFER_MAXSIZE)
@@ -1069,7 +1069,8 @@ static int rpciod_start(void)
 	 * Create the rpciod thread and wait for it to start.
 	 */
 	dprintk("RPC:       creating workqueue rpciod\n");
-	wq = alloc_workqueue("rpciod", WQ_MEM_RECLAIM, 1);
+	/* Note: highpri because network receive is latency sensitive */
+	wq = alloc_workqueue("rpciod", WQ_MEM_RECLAIM | WQ_HIGHPRI, 0);
 	rpciod_workqueue = wq;
 	return rpciod_workqueue != NULL;
 }
diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c
index 54530490944e..2ecb994314c1 100644
--- a/net/sunrpc/stats.c
+++ b/net/sunrpc/stats.c
@@ -116,7 +116,15 @@ EXPORT_SYMBOL_GPL(svc_seq_show);
  */
 struct rpc_iostats *rpc_alloc_iostats(struct rpc_clnt *clnt)
 {
-	return kcalloc(clnt->cl_maxproc, sizeof(struct rpc_iostats), GFP_KERNEL);
+	struct rpc_iostats *stats;
+	int i;
+
+	stats = kcalloc(clnt->cl_maxproc, sizeof(*stats), GFP_KERNEL);
+	if (stats) {
+		for (i = 0; i < clnt->cl_maxproc; i++)
+			spin_lock_init(&stats[i].om_lock);
+	}
+	return stats;
 }
 EXPORT_SYMBOL_GPL(rpc_alloc_iostats);
 
@@ -132,22 +140,21 @@ void rpc_free_iostats(struct rpc_iostats *stats)
 EXPORT_SYMBOL_GPL(rpc_free_iostats);
 
 /**
- * rpc_count_iostats - tally up per-task stats
+ * rpc_count_iostats_metrics - tally up per-task stats
  * @task: completed rpc_task
- * @stats: array of stat structures
- *
- * Relies on the caller for serialization.
+ * @op_metrics: stat structure for OP that will accumulate stats from @task
  */
-void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats)
+void rpc_count_iostats_metrics(const struct rpc_task *task,
+			       struct rpc_iostats *op_metrics)
 {
 	struct rpc_rqst *req = task->tk_rqstp;
-	struct rpc_iostats *op_metrics;
-	ktime_t delta;
+	ktime_t delta, now;
 
-	if (!stats || !req)
+	if (!op_metrics || !req)
 		return;
 
-	op_metrics = &stats[task->tk_msg.rpc_proc->p_statidx];
+	now = ktime_get();
+	spin_lock(&op_metrics->om_lock);
 
 	op_metrics->om_ops++;
 	op_metrics->om_ntrans += req->rq_ntrans;
@@ -161,8 +168,24 @@ void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats)
 
 	op_metrics->om_rtt = ktime_add(op_metrics->om_rtt, req->rq_rtt);
 
-	delta = ktime_sub(ktime_get(), task->tk_start);
+	delta = ktime_sub(now, task->tk_start);
 	op_metrics->om_execute = ktime_add(op_metrics->om_execute, delta);
+
+	spin_unlock(&op_metrics->om_lock);
+}
+EXPORT_SYMBOL_GPL(rpc_count_iostats_metrics);
+
+/**
+ * rpc_count_iostats - tally up per-task stats
+ * @task: completed rpc_task
+ * @stats: array of stat structures
+ *
+ * Uses the statidx from @task
+ */
+void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats)
+{
+	rpc_count_iostats_metrics(task,
+				  &stats[task->tk_msg.rpc_proc->p_statidx]);
 }
 EXPORT_SYMBOL_GPL(rpc_count_iostats);
 
diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c
index cd30120de9e4..ee5d3d253102 100644
--- a/net/sunrpc/sunrpc_syms.c
+++ b/net/sunrpc/sunrpc_syms.c
@@ -97,7 +97,9 @@ init_sunrpc(void)
 	err = register_rpc_pipefs();
 	if (err)
 		goto out4;
-#ifdef RPC_DEBUG
+
+	sunrpc_debugfs_init();
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	rpc_register_sysctl();
 #endif
 	svc_init_xprt_sock();	/* svc sock transport */
@@ -120,10 +122,11 @@ cleanup_sunrpc(void)
 	rpcauth_remove_module();
 	cleanup_socket_xprt();
 	svc_cleanup_xprt_sock();
+	sunrpc_debugfs_exit();
 	unregister_rpc_pipefs();
 	rpc_destroy_mempool();
 	unregister_pernet_subsys(&sunrpc_net_ops);
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	rpc_unregister_sysctl();
 #endif
 	rcu_barrier(); /* Wait for completion of call_rcu()'s */
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index ca8a7958f4e6..78974e4d9ad2 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -28,6 +28,8 @@
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/bc_xprt.h>
 
+#include <trace/events/sunrpc.h>
+
 #define RPCDBG_FACILITY	RPCDBG_SVCDSP
 
 static void svc_unregister(const struct svc_serv *serv, struct net *net);
@@ -189,7 +191,7 @@ svc_pool_map_init_percpu(struct svc_pool_map *m)
 		return err;
 
 	for_each_online_cpu(cpu) {
-		BUG_ON(pidx > maxpools);
+		BUG_ON(pidx >= maxpools);
 		m->to_pool[cpu] = pidx;
 		m->pool_to[pidx] = cpu;
 		pidx++;
@@ -474,15 +476,11 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
 				i, serv->sv_name);
 
 		pool->sp_id = i;
-		INIT_LIST_HEAD(&pool->sp_threads);
 		INIT_LIST_HEAD(&pool->sp_sockets);
 		INIT_LIST_HEAD(&pool->sp_all_threads);
 		spin_lock_init(&pool->sp_lock);
 	}
 
-	if (svc_uses_rpcbind(serv) && (!serv->sv_shutdown))
-		serv->sv_shutdown = svc_rpcb_cleanup;
-
 	return serv;
 }
 
@@ -503,13 +501,15 @@ svc_create_pooled(struct svc_program *prog, unsigned int bufsize,
 	unsigned int npools = svc_pool_map_get();
 
 	serv = __svc_create(prog, bufsize, npools, shutdown);
+	if (!serv)
+		goto out_err;
 
-	if (serv != NULL) {
-		serv->sv_function = func;
-		serv->sv_module = mod;
-	}
-
+	serv->sv_function = func;
+	serv->sv_module = mod;
 	return serv;
+out_err:
+	svc_pool_map_put();
+	return NULL;
 }
 EXPORT_SYMBOL_GPL(svc_create_pooled);
 
@@ -613,12 +613,14 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node)
 		goto out_enomem;
 
 	serv->sv_nrthreads++;
+	__set_bit(RQ_BUSY, &rqstp->rq_flags);
+	spin_lock_init(&rqstp->rq_lock);
+	rqstp->rq_server = serv;
+	rqstp->rq_pool = pool;
 	spin_lock_bh(&pool->sp_lock);
 	pool->sp_nrthreads++;
-	list_add(&rqstp->rq_all, &pool->sp_all_threads);
+	list_add_rcu(&rqstp->rq_all, &pool->sp_all_threads);
 	spin_unlock_bh(&pool->sp_lock);
-	rqstp->rq_server = serv;
-	rqstp->rq_pool = pool;
 
 	rqstp->rq_argp = kmalloc_node(serv->sv_xdrsize, GFP_KERNEL, node);
 	if (!rqstp->rq_argp)
@@ -683,7 +685,8 @@ found_pool:
 		 * so we don't try to kill it again.
 		 */
 		rqstp = list_entry(pool->sp_all_threads.next, struct svc_rqst, rq_all);
-		list_del_init(&rqstp->rq_all);
+		set_bit(RQ_VICTIM, &rqstp->rq_flags);
+		list_del_rcu(&rqstp->rq_all);
 		task = rqstp->rq_task;
 	}
 	spin_unlock_bh(&pool->sp_lock);
@@ -765,8 +768,8 @@ svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
 EXPORT_SYMBOL_GPL(svc_set_num_threads);
 
 /*
- * Called from a server thread as it's exiting. Caller must hold the BKL or
- * the "service mutex", whichever is appropriate for the service.
+ * Called from a server thread as it's exiting. Caller must hold the "service
+ * mutex" for the service.
  */
 void
 svc_exit_thread(struct svc_rqst *rqstp)
@@ -781,10 +784,11 @@ svc_exit_thread(struct svc_rqst *rqstp)
 
 	spin_lock_bh(&pool->sp_lock);
 	pool->sp_nrthreads--;
-	list_del(&rqstp->rq_all);
+	if (!test_and_set_bit(RQ_VICTIM, &rqstp->rq_flags))
+		list_del_rcu(&rqstp->rq_all);
 	spin_unlock_bh(&pool->sp_lock);
 
-	kfree(rqstp);
+	kfree_rcu(rqstp, rq_rcu_head);
 
 	/* Release the server */
 	if (serv)
@@ -1040,7 +1044,7 @@ static void svc_unregister(const struct svc_serv *serv, struct net *net)
 /*
  * dprintk the given error with the address of the client that caused it.
  */
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 static __printf(2, 3)
 void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...)
 {
@@ -1084,10 +1088,10 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 		goto err_short_len;
 
 	/* Will be turned off only in gss privacy case: */
-	rqstp->rq_splice_ok = true;
+	set_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
 	/* Will be turned off only when NFSv4 Sessions are used */
-	rqstp->rq_usedeferral = true;
-	rqstp->rq_dropme = false;
+	set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
+	clear_bit(RQ_DROPME, &rqstp->rq_flags);
 
 	/* Setup reply header */
 	rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp);
@@ -1187,7 +1191,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 		*statp = procp->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp);
 
 		/* Encode reply */
-		if (rqstp->rq_dropme) {
+		if (test_bit(RQ_DROPME, &rqstp->rq_flags)) {
 			if (procp->pc_release)
 				procp->pc_release(rqstp, NULL, rqstp->rq_resp);
 			goto dropit;
@@ -1314,24 +1318,25 @@ svc_process(struct svc_rqst *rqstp)
 	rqstp->rq_res.tail[0].iov_base = NULL;
 	rqstp->rq_res.tail[0].iov_len = 0;
 
-	rqstp->rq_xid = svc_getu32(argv);
-
 	dir  = svc_getnl(argv);
 	if (dir != 0) {
 		/* direction != CALL */
 		svc_printk(rqstp, "bad direction %d, dropping request\n", dir);
 		serv->sv_stats->rpcbadfmt++;
-		svc_drop(rqstp);
-		return 0;
+		goto out_drop;
 	}
 
 	/* Returns 1 for send, 0 for drop */
-	if (svc_process_common(rqstp, argv, resv))
-		return svc_send(rqstp);
-	else {
-		svc_drop(rqstp);
-		return 0;
+	if (likely(svc_process_common(rqstp, argv, resv))) {
+		int ret = svc_send(rqstp);
+
+		trace_svc_process(rqstp, ret);
+		return ret;
 	}
+out_drop:
+	trace_svc_process(rqstp, 0);
+	svc_drop(rqstp);
+	return 0;
 }
 
 #if defined(CONFIG_SUNRPC_BACKCHANNEL)
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index c179ca2a5aa4..163ac45c3639 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -15,6 +15,7 @@
 #include <linux/sunrpc/svcsock.h>
 #include <linux/sunrpc/xprt.h>
 #include <linux/module.h>
+#include <trace/events/sunrpc.h>
 
 #define RPCDBG_FACILITY	RPCDBG_SVCXPRT
 
@@ -41,7 +42,7 @@ static LIST_HEAD(svc_xprt_class_list);
  *	svc_pool->sp_lock protects most of the fields of that pool.
  *	svc_serv->sv_lock protects sv_tempsocks, sv_permsocks, sv_tmpcnt.
  *	when both need to be taken (rare), svc_serv->sv_lock is first.
- *	BKL protects svc_serv->sv_nrthread.
+ *	The "service mutex" protects svc_serv->sv_nrthread.
  *	svc_sock->sk_lock protects the svc_sock->sk_deferred list
  *             and the ->sk_info_authunix cache.
  *
@@ -66,7 +67,6 @@ static LIST_HEAD(svc_xprt_class_list);
  *		  that no other thread will be using the transport or will
  *		  try to set XPT_DEAD.
  */
-
 int svc_reg_xprt_class(struct svc_xprt_class *xcl)
 {
 	struct svc_xprt_class *cl;
@@ -219,9 +219,11 @@ static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl,
  */
 static void svc_xprt_received(struct svc_xprt *xprt)
 {
-	WARN_ON_ONCE(!test_bit(XPT_BUSY, &xprt->xpt_flags));
-	if (!test_bit(XPT_BUSY, &xprt->xpt_flags))
+	if (!test_bit(XPT_BUSY, &xprt->xpt_flags)) {
+		WARN_ONCE(1, "xprt=0x%p already busy!", xprt);
 		return;
+	}
+
 	/* As soon as we clear busy, the xprt could be closed and
 	 * 'put', so we need a reference to call svc_xprt_do_enqueue with:
 	 */
@@ -309,25 +311,6 @@ char *svc_print_addr(struct svc_rqst *rqstp, char *buf, size_t len)
 }
 EXPORT_SYMBOL_GPL(svc_print_addr);
 
-/*
- * Queue up an idle server thread.  Must have pool->sp_lock held.
- * Note: this is really a stack rather than a queue, so that we only
- * use as many different threads as we need, and the rest don't pollute
- * the cache.
- */
-static void svc_thread_enqueue(struct svc_pool *pool, struct svc_rqst *rqstp)
-{
-	list_add(&rqstp->rq_list, &pool->sp_threads);
-}
-
-/*
- * Dequeue an nfsd thread.  Must have pool->sp_lock held.
- */
-static void svc_thread_dequeue(struct svc_pool *pool, struct svc_rqst *rqstp)
-{
-	list_del(&rqstp->rq_list);
-}
-
 static bool svc_xprt_has_something_to_do(struct svc_xprt *xprt)
 {
 	if (xprt->xpt_flags & ((1<<XPT_CONN)|(1<<XPT_CLOSE)))
@@ -340,11 +323,12 @@ static bool svc_xprt_has_something_to_do(struct svc_xprt *xprt)
 static void svc_xprt_do_enqueue(struct svc_xprt *xprt)
 {
 	struct svc_pool *pool;
-	struct svc_rqst	*rqstp;
+	struct svc_rqst	*rqstp = NULL;
 	int cpu;
+	bool queued = false;
 
 	if (!svc_xprt_has_something_to_do(xprt))
-		return;
+		goto out;
 
 	/* Mark transport as busy. It will remain in this state until
 	 * the provider calls svc_xprt_received. We update XPT_BUSY
@@ -354,43 +338,69 @@ static void svc_xprt_do_enqueue(struct svc_xprt *xprt)
 	if (test_and_set_bit(XPT_BUSY, &xprt->xpt_flags)) {
 		/* Don't enqueue transport while already enqueued */
 		dprintk("svc: transport %p busy, not enqueued\n", xprt);
-		return;
+		goto out;
 	}
 
 	cpu = get_cpu();
 	pool = svc_pool_for_cpu(xprt->xpt_server, cpu);
-	spin_lock_bh(&pool->sp_lock);
 
-	pool->sp_stats.packets++;
-
-	if (!list_empty(&pool->sp_threads)) {
-		rqstp = list_entry(pool->sp_threads.next,
-				   struct svc_rqst,
-				   rq_list);
-		dprintk("svc: transport %p served by daemon %p\n",
-			xprt, rqstp);
-		svc_thread_dequeue(pool, rqstp);
-		if (rqstp->rq_xprt)
-			printk(KERN_ERR
-				"svc_xprt_enqueue: server %p, rq_xprt=%p!\n",
-				rqstp, rqstp->rq_xprt);
-		/* Note the order of the following 3 lines:
-		 * We want to assign xprt to rqstp->rq_xprt only _after_
-		 * we've woken up the process, so that we don't race with
-		 * the lockless check in svc_get_next_xprt().
+	atomic_long_inc(&pool->sp_stats.packets);
+
+redo_search:
+	/* find a thread for this xprt */
+	rcu_read_lock();
+	list_for_each_entry_rcu(rqstp, &pool->sp_all_threads, rq_all) {
+		/* Do a lockless check first */
+		if (test_bit(RQ_BUSY, &rqstp->rq_flags))
+			continue;
+
+		/*
+		 * Once the xprt has been queued, it can only be dequeued by
+		 * the task that intends to service it. All we can do at that
+		 * point is to try to wake this thread back up so that it can
+		 * do so.
 		 */
-		svc_xprt_get(xprt);
+		if (!queued) {
+			spin_lock_bh(&rqstp->rq_lock);
+			if (test_and_set_bit(RQ_BUSY, &rqstp->rq_flags)) {
+				/* already busy, move on... */
+				spin_unlock_bh(&rqstp->rq_lock);
+				continue;
+			}
+
+			/* this one will do */
+			rqstp->rq_xprt = xprt;
+			svc_xprt_get(xprt);
+			spin_unlock_bh(&rqstp->rq_lock);
+		}
+		rcu_read_unlock();
+
+		atomic_long_inc(&pool->sp_stats.threads_woken);
 		wake_up_process(rqstp->rq_task);
-		rqstp->rq_xprt = xprt;
-		pool->sp_stats.threads_woken++;
-	} else {
+		put_cpu();
+		goto out;
+	}
+	rcu_read_unlock();
+
+	/*
+	 * We didn't find an idle thread to use, so we need to queue the xprt.
+	 * Do so and then search again. If we find one, we can't hook this one
+	 * up to it directly but we can wake the thread up in the hopes that it
+	 * will pick it up once it searches for a xprt to service.
+	 */
+	if (!queued) {
+		queued = true;
 		dprintk("svc: transport %p put into queue\n", xprt);
+		spin_lock_bh(&pool->sp_lock);
 		list_add_tail(&xprt->xpt_ready, &pool->sp_sockets);
 		pool->sp_stats.sockets_queued++;
+		spin_unlock_bh(&pool->sp_lock);
+		goto redo_search;
 	}
-
-	spin_unlock_bh(&pool->sp_lock);
+	rqstp = NULL;
 	put_cpu();
+out:
+	trace_svc_xprt_do_enqueue(xprt, rqstp);
 }
 
 /*
@@ -407,22 +417,28 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
 EXPORT_SYMBOL_GPL(svc_xprt_enqueue);
 
 /*
- * Dequeue the first transport.  Must be called with the pool->sp_lock held.
+ * Dequeue the first transport, if there is one.
  */
 static struct svc_xprt *svc_xprt_dequeue(struct svc_pool *pool)
 {
-	struct svc_xprt	*xprt;
+	struct svc_xprt	*xprt = NULL;
 
 	if (list_empty(&pool->sp_sockets))
-		return NULL;
-
-	xprt = list_entry(pool->sp_sockets.next,
-			  struct svc_xprt, xpt_ready);
-	list_del_init(&xprt->xpt_ready);
+		goto out;
 
-	dprintk("svc: transport %p dequeued, inuse=%d\n",
-		xprt, atomic_read(&xprt->xpt_ref.refcount));
+	spin_lock_bh(&pool->sp_lock);
+	if (likely(!list_empty(&pool->sp_sockets))) {
+		xprt = list_first_entry(&pool->sp_sockets,
+					struct svc_xprt, xpt_ready);
+		list_del_init(&xprt->xpt_ready);
+		svc_xprt_get(xprt);
 
+		dprintk("svc: transport %p dequeued, inuse=%d\n",
+			xprt, atomic_read(&xprt->xpt_ref.refcount));
+	}
+	spin_unlock_bh(&pool->sp_lock);
+out:
+	trace_svc_xprt_dequeue(xprt);
 	return xprt;
 }
 
@@ -483,34 +499,36 @@ static void svc_xprt_release(struct svc_rqst *rqstp)
 }
 
 /*
- * External function to wake up a server waiting for data
- * This really only makes sense for services like lockd
- * which have exactly one thread anyway.
+ * Some svc_serv's will have occasional work to do, even when a xprt is not
+ * waiting to be serviced. This function is there to "kick" a task in one of
+ * those services so that it can wake up and do that work. Note that we only
+ * bother with pool 0 as we don't need to wake up more than one thread for
+ * this purpose.
  */
 void svc_wake_up(struct svc_serv *serv)
 {
 	struct svc_rqst	*rqstp;
-	unsigned int i;
 	struct svc_pool *pool;
 
-	for (i = 0; i < serv->sv_nrpools; i++) {
-		pool = &serv->sv_pools[i];
+	pool = &serv->sv_pools[0];
 
-		spin_lock_bh(&pool->sp_lock);
-		if (!list_empty(&pool->sp_threads)) {
-			rqstp = list_entry(pool->sp_threads.next,
-					   struct svc_rqst,
-					   rq_list);
-			dprintk("svc: daemon %p woken up.\n", rqstp);
-			/*
-			svc_thread_dequeue(pool, rqstp);
-			rqstp->rq_xprt = NULL;
-			 */
-			wake_up_process(rqstp->rq_task);
-		} else
-			pool->sp_task_pending = 1;
-		spin_unlock_bh(&pool->sp_lock);
+	rcu_read_lock();
+	list_for_each_entry_rcu(rqstp, &pool->sp_all_threads, rq_all) {
+		/* skip any that aren't queued */
+		if (test_bit(RQ_BUSY, &rqstp->rq_flags))
+			continue;
+		rcu_read_unlock();
+		dprintk("svc: daemon %p woken up.\n", rqstp);
+		wake_up_process(rqstp->rq_task);
+		trace_svc_wake_up(rqstp->rq_task->pid);
+		return;
 	}
+	rcu_read_unlock();
+
+	/* No free entries available */
+	set_bit(SP_TASK_PENDING, &pool->sp_flags);
+	smp_wmb();
+	trace_svc_wake_up(0);
 }
 EXPORT_SYMBOL_GPL(svc_wake_up);
 
@@ -621,75 +639,86 @@ static int svc_alloc_arg(struct svc_rqst *rqstp)
 	return 0;
 }
 
+static bool
+rqst_should_sleep(struct svc_rqst *rqstp)
+{
+	struct svc_pool		*pool = rqstp->rq_pool;
+
+	/* did someone call svc_wake_up? */
+	if (test_and_clear_bit(SP_TASK_PENDING, &pool->sp_flags))
+		return false;
+
+	/* was a socket queued? */
+	if (!list_empty(&pool->sp_sockets))
+		return false;
+
+	/* are we shutting down? */
+	if (signalled() || kthread_should_stop())
+		return false;
+
+	/* are we freezing? */
+	if (freezing(current))
+		return false;
+
+	return true;
+}
+
 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;
 	long			time_left = 0;
 
+	/* rq_xprt should be clear on entry */
+	WARN_ON_ONCE(rqstp->rq_xprt);
+
 	/* Normally we will wait up to 5 seconds for any required
 	 * cache information to be provided.
 	 */
 	rqstp->rq_chandle.thread_wait = 5*HZ;
 
-	spin_lock_bh(&pool->sp_lock);
 	xprt = svc_xprt_dequeue(pool);
 	if (xprt) {
 		rqstp->rq_xprt = xprt;
-		svc_xprt_get(xprt);
 
 		/* As there is a shortage of threads and this request
 		 * had to be queued, don't allow the thread to wait so
 		 * long for cache updates.
 		 */
 		rqstp->rq_chandle.thread_wait = 1*HZ;
-		pool->sp_task_pending = 0;
-	} else {
-		if (pool->sp_task_pending) {
-			pool->sp_task_pending = 0;
-			xprt = ERR_PTR(-EAGAIN);
-			goto out;
-		}
-		/*
-		 * We have to be able to interrupt this wait
-		 * to bring down the daemons ...
-		 */
-		set_current_state(TASK_INTERRUPTIBLE);
+		clear_bit(SP_TASK_PENDING, &pool->sp_flags);
+		return xprt;
+	}
 
-		/* No data pending. Go to sleep */
-		svc_thread_enqueue(pool, rqstp);
-		spin_unlock_bh(&pool->sp_lock);
+	/*
+	 * We have to be able to interrupt this wait
+	 * to bring down the daemons ...
+	 */
+	set_current_state(TASK_INTERRUPTIBLE);
+	clear_bit(RQ_BUSY, &rqstp->rq_flags);
+	smp_mb();
 
-		if (!(signalled() || kthread_should_stop())) {
-			time_left = schedule_timeout(timeout);
-			__set_current_state(TASK_RUNNING);
+	if (likely(rqst_should_sleep(rqstp)))
+		time_left = schedule_timeout(timeout);
+	else
+		__set_current_state(TASK_RUNNING);
 
-			try_to_freeze();
+	try_to_freeze();
 
-			xprt = rqstp->rq_xprt;
-			if (xprt != NULL)
-				return xprt;
-		} else
-			__set_current_state(TASK_RUNNING);
+	spin_lock_bh(&rqstp->rq_lock);
+	set_bit(RQ_BUSY, &rqstp->rq_flags);
+	spin_unlock_bh(&rqstp->rq_lock);
 
-		spin_lock_bh(&pool->sp_lock);
-		if (!time_left)
-			pool->sp_stats.threads_timedout++;
+	xprt = rqstp->rq_xprt;
+	if (xprt != NULL)
+		return xprt;
 
-		xprt = rqstp->rq_xprt;
-		if (!xprt) {
-			svc_thread_dequeue(pool, rqstp);
-			spin_unlock_bh(&pool->sp_lock);
-			dprintk("svc: server %p, no data yet\n", rqstp);
-			if (signalled() || kthread_should_stop())
-				return ERR_PTR(-EINTR);
-			else
-				return ERR_PTR(-EAGAIN);
-		}
-	}
-out:
-	spin_unlock_bh(&pool->sp_lock);
-	return xprt;
+	if (!time_left)
+		atomic_long_inc(&pool->sp_stats.threads_timedout);
+
+	if (signalled() || kthread_should_stop())
+		return ERR_PTR(-EINTR);
+	return ERR_PTR(-EAGAIN);
 }
 
 static void svc_add_new_temp_xprt(struct svc_serv *serv, struct svc_xprt *newxpt)
@@ -718,7 +747,7 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt)
 		dprintk("svc_recv: found XPT_CLOSE\n");
 		svc_delete_xprt(xprt);
 		/* Leave XPT_BUSY set on the dead xprt: */
-		return 0;
+		goto out;
 	}
 	if (test_bit(XPT_LISTENER, &xprt->xpt_flags)) {
 		struct svc_xprt *newxpt;
@@ -749,6 +778,8 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt)
 	}
 	/* clear XPT_BUSY: */
 	svc_xprt_received(xprt);
+out:
+	trace_svc_handle_xprt(xprt, len);
 	return len;
 }
 
@@ -773,35 +804,46 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 
 	err = svc_alloc_arg(rqstp);
 	if (err)
-		return err;
+		goto out;
 
 	try_to_freeze();
 	cond_resched();
+	err = -EINTR;
 	if (signalled() || kthread_should_stop())
-		return -EINTR;
+		goto out;
 
 	xprt = svc_get_next_xprt(rqstp, timeout);
-	if (IS_ERR(xprt))
-		return PTR_ERR(xprt);
+	if (IS_ERR(xprt)) {
+		err = PTR_ERR(xprt);
+		goto out;
+	}
 
 	len = svc_handle_xprt(rqstp, xprt);
 
 	/* No data, incomplete (TCP) read, or accept() */
+	err = -EAGAIN;
 	if (len <= 0)
-		goto out;
+		goto out_release;
 
 	clear_bit(XPT_OLD, &xprt->xpt_flags);
 
-	rqstp->rq_secure = xprt->xpt_ops->xpo_secure_port(rqstp);
+	if (xprt->xpt_ops->xpo_secure_port(rqstp))
+		set_bit(RQ_SECURE, &rqstp->rq_flags);
+	else
+		clear_bit(RQ_SECURE, &rqstp->rq_flags);
 	rqstp->rq_chandle.defer = svc_defer;
+	rqstp->rq_xid = svc_getu32(&rqstp->rq_arg.head[0]);
 
 	if (serv->sv_stats)
 		serv->sv_stats->netcnt++;
+	trace_svc_recv(rqstp, len);
 	return len;
-out:
+out_release:
 	rqstp->rq_res.len = 0;
 	svc_xprt_release(rqstp);
-	return -EAGAIN;
+out:
+	trace_svc_recv(rqstp, err);
+	return err;
 }
 EXPORT_SYMBOL_GPL(svc_recv);
 
@@ -821,12 +863,12 @@ EXPORT_SYMBOL_GPL(svc_drop);
 int svc_send(struct svc_rqst *rqstp)
 {
 	struct svc_xprt	*xprt;
-	int		len;
+	int		len = -EFAULT;
 	struct xdr_buf	*xb;
 
 	xprt = rqstp->rq_xprt;
 	if (!xprt)
-		return -EFAULT;
+		goto out;
 
 	/* release the receive skb before sending the reply */
 	rqstp->rq_xprt->xpt_ops->xpo_release_rqst(rqstp);
@@ -849,7 +891,9 @@ int svc_send(struct svc_rqst *rqstp)
 	svc_xprt_release(rqstp);
 
 	if (len == -ECONNREFUSED || len == -ENOTCONN || len == -EAGAIN)
-		return 0;
+		len = 0;
+out:
+	trace_svc_send(rqstp, len);
 	return len;
 }
 
@@ -884,7 +928,6 @@ static void svc_age_temp_xprts(unsigned long closure)
 			continue;
 		list_del_init(le);
 		set_bit(XPT_CLOSE, &xprt->xpt_flags);
-		set_bit(XPT_DETACHED, &xprt->xpt_flags);
 		dprintk("queuing xprt %p for closing\n", xprt);
 
 		/* a thread will dequeue and close it soon */
@@ -924,8 +967,7 @@ static void svc_delete_xprt(struct svc_xprt *xprt)
 	xprt->xpt_ops->xpo_detach(xprt);
 
 	spin_lock_bh(&serv->sv_lock);
-	if (!test_and_set_bit(XPT_DETACHED, &xprt->xpt_flags))
-		list_del_init(&xprt->xpt_list);
+	list_del_init(&xprt->xpt_list);
 	WARN_ON_ONCE(!list_empty(&xprt->xpt_ready));
 	if (test_bit(XPT_TEMP, &xprt->xpt_flags))
 		serv->sv_tmpcnt--;
@@ -1069,7 +1111,7 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req)
 	struct svc_rqst *rqstp = container_of(req, struct svc_rqst, rq_chandle);
 	struct svc_deferred_req *dr;
 
-	if (rqstp->rq_arg.page_len || !rqstp->rq_usedeferral)
+	if (rqstp->rq_arg.page_len || !test_bit(RQ_USEDEFERRAL, &rqstp->rq_flags))
 		return NULL; /* if more than a page, give up FIXME */
 	if (rqstp->rq_deferred) {
 		dr = rqstp->rq_deferred;
@@ -1098,7 +1140,7 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req)
 	}
 	svc_xprt_get(rqstp->rq_xprt);
 	dr->xprt = rqstp->rq_xprt;
-	rqstp->rq_dropme = true;
+	set_bit(RQ_DROPME, &rqstp->rq_flags);
 
 	dr->handle.revisit = svc_revisit;
 	return &dr->handle;
@@ -1300,10 +1342,10 @@ static int svc_pool_stats_show(struct seq_file *m, void *p)
 
 	seq_printf(m, "%u %lu %lu %lu %lu\n",
 		pool->sp_id,
-		pool->sp_stats.packets,
+		(unsigned long)atomic_long_read(&pool->sp_stats.packets),
 		pool->sp_stats.sockets_queued,
-		pool->sp_stats.threads_woken,
-		pool->sp_stats.threads_timedout);
+		(unsigned long)atomic_long_read(&pool->sp_stats.threads_woken),
+		(unsigned long)atomic_long_read(&pool->sp_stats.threads_timedout));
 
 	return 0;
 }
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 3f959c681885..0c8120229a03 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -257,7 +257,7 @@ static int svc_sendto(struct svc_rqst *rqstp, struct xdr_buf *xdr)
 
 		svc_set_cmsg_data(rqstp, cmh);
 
-		if (sock_sendmsg(sock, &msg, 0) < 0)
+		if (sock_sendmsg(sock, &msg) < 0)
 			goto out;
 	}
 
@@ -1019,17 +1019,12 @@ static int receive_cb_reply(struct svc_sock *svsk, struct svc_rqst *rqstp)
 	xid = *p++;
 	calldir = *p;
 
-	if (bc_xprt)
-		req = xprt_lookup_rqst(bc_xprt, xid);
-
-	if (!req) {
-		printk(KERN_NOTICE
-			"%s: Got unrecognized reply: "
-			"calldir 0x%x xpt_bc_xprt %p xid %08x\n",
-			__func__, ntohl(calldir),
-			bc_xprt, ntohl(xid));
+	if (!bc_xprt)
 		return -EAGAIN;
-	}
+	spin_lock_bh(&bc_xprt->transport_lock);
+	req = xprt_lookup_rqst(bc_xprt, xid);
+	if (!req)
+		goto unlock_notfound;
 
 	memcpy(&req->rq_private_buf, &req->rq_rcv_buf, sizeof(struct xdr_buf));
 	/*
@@ -1040,11 +1035,21 @@ static int receive_cb_reply(struct svc_sock *svsk, struct svc_rqst *rqstp)
 	dst = &req->rq_private_buf.head[0];
 	src = &rqstp->rq_arg.head[0];
 	if (dst->iov_len < src->iov_len)
-		return -EAGAIN; /* whatever; just giving up. */
+		goto unlock_eagain; /* whatever; just giving up. */
 	memcpy(dst->iov_base, src->iov_base, src->iov_len);
 	xprt_complete_rqst(req->rq_task, rqstp->rq_arg.len);
 	rqstp->rq_arg.len = 0;
+	spin_unlock_bh(&bc_xprt->transport_lock);
 	return 0;
+unlock_notfound:
+	printk(KERN_NOTICE
+		"%s: Got unrecognized reply: "
+		"calldir 0x%x xpt_bc_xprt %p xid %08x\n",
+		__func__, ntohl(calldir),
+		bc_xprt, ntohl(xid));
+unlock_eagain:
+	spin_unlock_bh(&bc_xprt->transport_lock);
+	return -EAGAIN;
 }
 
 static int copy_pages_to_kvecs(struct kvec *vec, struct page **pages, int len)
@@ -1140,7 +1145,10 @@ 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);
+	if (test_bit(XPT_LOCAL, &svsk->sk_xprt.xpt_flags))
+		set_bit(RQ_LOCAL, &rqstp->rq_flags);
+	else
+		clear_bit(RQ_LOCAL, &rqstp->rq_flags);
 
 	p = (__be32 *)rqstp->rq_arg.head[0].iov_base;
 	calldir = p[1];
diff --git a/net/sunrpc/sysctl.c b/net/sunrpc/sysctl.c
index c99c58e2ee66..887f0183b4c6 100644
--- a/net/sunrpc/sysctl.c
+++ b/net/sunrpc/sysctl.c
@@ -37,7 +37,7 @@ EXPORT_SYMBOL_GPL(nfsd_debug);
 unsigned int	nlm_debug;
 EXPORT_SYMBOL_GPL(nlm_debug);
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 
 static struct ctl_table_header *sunrpc_table_header;
 static struct ctl_table sunrpc_table[];
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 290af97bf6f9..4439ac4c1b53 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -606,7 +606,7 @@ void xdr_truncate_encode(struct xdr_stream *xdr, size_t len)
 	struct kvec *head = buf->head;
 	struct kvec *tail = buf->tail;
 	int fraglen;
-	int new, old;
+	int new;
 
 	if (len > buf->len) {
 		WARN_ON_ONCE(1);
@@ -617,9 +617,10 @@ void xdr_truncate_encode(struct xdr_stream *xdr, size_t len)
 	fraglen = min_t(int, buf->len - len, tail->iov_len);
 	tail->iov_len -= fraglen;
 	buf->len -= fraglen;
-	if (tail->iov_len && buf->len == len) {
+	if (tail->iov_len) {
 		xdr->p = tail->iov_base + tail->iov_len;
-		/* xdr->end, xdr->iov should be set already */
+		WARN_ON_ONCE(!xdr->end);
+		WARN_ON_ONCE(!xdr->iov);
 		return;
 	}
 	WARN_ON_ONCE(fraglen);
@@ -628,14 +629,14 @@ void xdr_truncate_encode(struct xdr_stream *xdr, size_t len)
 	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->page_ptr = buf->pages + (new >> PAGE_SHIFT);
+
+	if (buf->page_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 */
+		WARN_ON_ONCE(xdr->iov);
 		return;
 	}
 	if (fraglen) {
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 56e4e150e80e..1d4fe24af06a 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -49,13 +49,15 @@
 #include <linux/sunrpc/metrics.h>
 #include <linux/sunrpc/bc_xprt.h>
 
+#include <trace/events/sunrpc.h>
+
 #include "sunrpc.h"
 
 /*
  * Local variables
  */
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_XPRT
 #endif
 
@@ -324,6 +326,15 @@ out_unlock:
 	xprt_clear_locked(xprt);
 }
 
+static void xprt_task_clear_bytes_sent(struct rpc_task *task)
+{
+	if (task != NULL) {
+		struct rpc_rqst *req = task->tk_rqstp;
+		if (req != NULL)
+			req->rq_bytes_sent = 0;
+	}
+}
+
 /**
  * xprt_release_xprt - allow other requests to use a transport
  * @xprt: transport with other tasks potentially waiting
@@ -334,11 +345,7 @@ out_unlock:
 void xprt_release_xprt(struct rpc_xprt *xprt, struct rpc_task *task)
 {
 	if (xprt->snd_task == task) {
-		if (task != NULL) {
-			struct rpc_rqst *req = task->tk_rqstp;
-			if (req != NULL)
-				req->rq_bytes_sent = 0;
-		}
+		xprt_task_clear_bytes_sent(task);
 		xprt_clear_locked(xprt);
 		__xprt_lock_write_next(xprt);
 	}
@@ -356,11 +363,7 @@ EXPORT_SYMBOL_GPL(xprt_release_xprt);
 void xprt_release_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task)
 {
 	if (xprt->snd_task == task) {
-		if (task != NULL) {
-			struct rpc_rqst *req = task->tk_rqstp;
-			if (req != NULL)
-				req->rq_bytes_sent = 0;
-		}
+		xprt_task_clear_bytes_sent(task);
 		xprt_clear_locked(xprt);
 		__xprt_lock_write_next_cong(xprt);
 	}
@@ -681,13 +684,44 @@ xprt_init_autodisconnect(unsigned long data)
 	if (test_and_set_bit(XPRT_LOCKED, &xprt->state))
 		goto out_abort;
 	spin_unlock(&xprt->transport_lock);
-	set_bit(XPRT_CONNECTION_CLOSE, &xprt->state);
 	queue_work(rpciod_workqueue, &xprt->task_cleanup);
 	return;
 out_abort:
 	spin_unlock(&xprt->transport_lock);
 }
 
+bool xprt_lock_connect(struct rpc_xprt *xprt,
+		struct rpc_task *task,
+		void *cookie)
+{
+	bool ret = false;
+
+	spin_lock_bh(&xprt->transport_lock);
+	if (!test_bit(XPRT_LOCKED, &xprt->state))
+		goto out;
+	if (xprt->snd_task != task)
+		goto out;
+	xprt_task_clear_bytes_sent(task);
+	xprt->snd_task = cookie;
+	ret = true;
+out:
+	spin_unlock_bh(&xprt->transport_lock);
+	return ret;
+}
+
+void xprt_unlock_connect(struct rpc_xprt *xprt, void *cookie)
+{
+	spin_lock_bh(&xprt->transport_lock);
+	if (xprt->snd_task != cookie)
+		goto out;
+	if (!test_bit(XPRT_LOCKED, &xprt->state))
+		goto out;
+	xprt->snd_task =NULL;
+	xprt->ops->release_xprt(xprt, NULL);
+out:
+	spin_unlock_bh(&xprt->transport_lock);
+}
+
 /**
  * xprt_connect - schedule a transport connect operation
  * @task: RPC task that is requesting the connect
@@ -710,9 +744,7 @@ void xprt_connect(struct rpc_task *task)
 	if (test_and_clear_bit(XPRT_CLOSE_WAIT, &xprt->state))
 		xprt->ops->close(xprt);
 
-	if (xprt_connected(xprt))
-		xprt_release_write(xprt, task);
-	else {
+	if (!xprt_connected(xprt)) {
 		task->tk_rqstp->rq_bytes_sent = 0;
 		task->tk_timeout = task->tk_rqstp->rq_timeout;
 		rpc_sleep_on(&xprt->pending, task, xprt_connect_status);
@@ -724,6 +756,7 @@ void xprt_connect(struct rpc_task *task)
 		xprt->stat.connect_start = jiffies;
 		xprt->ops->connect(xprt, task);
 	}
+	xprt_release_write(xprt, task);
 }
 
 static void xprt_connect_status(struct rpc_task *task)
@@ -756,7 +789,6 @@ static void xprt_connect_status(struct rpc_task *task)
 		dprintk("RPC: %5u xprt_connect_status: error %d connecting to "
 				"server %s\n", task->tk_pid, -task->tk_status,
 				xprt->servername);
-		xprt_release_write(xprt, task);
 		task->tk_status = -EIO;
 	}
 }
@@ -772,11 +804,14 @@ struct rpc_rqst *xprt_lookup_rqst(struct rpc_xprt *xprt, __be32 xid)
 	struct rpc_rqst *entry;
 
 	list_for_each_entry(entry, &xprt->recv, rq_list)
-		if (entry->rq_xid == xid)
+		if (entry->rq_xid == xid) {
+			trace_xprt_lookup_rqst(xprt, xid, 0);
 			return entry;
+		}
 
 	dprintk("RPC:       xprt_lookup_rqst did not find xid %08x\n",
 			ntohl(xid));
+	trace_xprt_lookup_rqst(xprt, xid, -ENOENT);
 	xprt->stat.bad_xids++;
 	return NULL;
 }
@@ -810,6 +845,7 @@ void xprt_complete_rqst(struct rpc_task *task, int copied)
 
 	dprintk("RPC: %5u xid %08x complete (%d bytes received)\n",
 			task->tk_pid, ntohl(req->rq_xid), copied);
+	trace_xprt_complete_rqst(xprt, req->rq_xid, copied);
 
 	xprt->stat.recvs++;
 	req->rq_rtt = ktime_sub(ktime_get(), req->rq_xtime);
@@ -926,6 +962,7 @@ void xprt_transmit(struct rpc_task *task)
 
 	req->rq_xtime = ktime_get();
 	status = xprt->ops->send_request(task);
+	trace_xprt_transmit(xprt, req->rq_xid, status);
 	if (status != 0) {
 		task->tk_status = status;
 		return;
@@ -1336,6 +1373,8 @@ found:
 		return ERR_PTR(-ENOMEM);
 	}
 
+	rpc_xprt_debugfs_register(xprt);
+
 	dprintk("RPC:       created transport %p with %u slots\n", xprt,
 			xprt->max_reqs);
 out:
@@ -1352,6 +1391,7 @@ static void xprt_destroy(struct rpc_xprt *xprt)
 	dprintk("RPC:       destroying transport %p\n", xprt);
 	del_timer_sync(&xprt->timer);
 
+	rpc_xprt_debugfs_unregister(xprt);
 	rpc_destroy_wait_queue(&xprt->binding);
 	rpc_destroy_wait_queue(&xprt->pending);
 	rpc_destroy_wait_queue(&xprt->sending);
diff --git a/net/sunrpc/xprtrdma/Makefile b/net/sunrpc/xprtrdma/Makefile
index da5136fd5694..579f72bbcf4b 100644
--- a/net/sunrpc/xprtrdma/Makefile
+++ b/net/sunrpc/xprtrdma/Makefile
@@ -1,6 +1,7 @@
 obj-$(CONFIG_SUNRPC_XPRT_RDMA_CLIENT) += xprtrdma.o
 
-xprtrdma-y := transport.o rpc_rdma.o verbs.o
+xprtrdma-y := transport.o rpc_rdma.o verbs.o \
+	fmr_ops.o frwr_ops.o physical_ops.o
 
 obj-$(CONFIG_SUNRPC_XPRT_RDMA_SERVER) += svcrdma.o
 
diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c
new file mode 100644
index 000000000000..302d4ebf6fbf
--- /dev/null
+++ b/net/sunrpc/xprtrdma/fmr_ops.c
@@ -0,0 +1,208 @@
+/*
+ * Copyright (c) 2015 Oracle.  All rights reserved.
+ * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved.
+ */
+
+/* Lightweight memory registration using Fast Memory Regions (FMR).
+ * Referred to sometimes as MTHCAFMR mode.
+ *
+ * FMR uses synchronous memory registration and deregistration.
+ * FMR registration is known to be fast, but FMR deregistration
+ * can take tens of usecs to complete.
+ */
+
+#include "xprt_rdma.h"
+
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
+# define RPCDBG_FACILITY	RPCDBG_TRANS
+#endif
+
+/* Maximum scatter/gather per FMR */
+#define RPCRDMA_MAX_FMR_SGES	(64)
+
+static int
+fmr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep,
+	    struct rpcrdma_create_data_internal *cdata)
+{
+	return 0;
+}
+
+/* FMR mode conveys up to 64 pages of payload per chunk segment.
+ */
+static size_t
+fmr_op_maxpages(struct rpcrdma_xprt *r_xprt)
+{
+	return min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS,
+		     rpcrdma_max_segments(r_xprt) * RPCRDMA_MAX_FMR_SGES);
+}
+
+static int
+fmr_op_init(struct rpcrdma_xprt *r_xprt)
+{
+	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
+	int mr_access_flags = IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_READ;
+	struct ib_fmr_attr fmr_attr = {
+		.max_pages	= RPCRDMA_MAX_FMR_SGES,
+		.max_maps	= 1,
+		.page_shift	= PAGE_SHIFT
+	};
+	struct ib_pd *pd = r_xprt->rx_ia.ri_pd;
+	struct rpcrdma_mw *r;
+	int i, rc;
+
+	INIT_LIST_HEAD(&buf->rb_mws);
+	INIT_LIST_HEAD(&buf->rb_all);
+
+	i = (buf->rb_max_requests + 1) * RPCRDMA_MAX_SEGS;
+	dprintk("RPC:       %s: initializing %d FMRs\n", __func__, i);
+
+	while (i--) {
+		r = kzalloc(sizeof(*r), GFP_KERNEL);
+		if (!r)
+			return -ENOMEM;
+
+		r->r.fmr = ib_alloc_fmr(pd, mr_access_flags, &fmr_attr);
+		if (IS_ERR(r->r.fmr))
+			goto out_fmr_err;
+
+		list_add(&r->mw_list, &buf->rb_mws);
+		list_add(&r->mw_all, &buf->rb_all);
+	}
+	return 0;
+
+out_fmr_err:
+	rc = PTR_ERR(r->r.fmr);
+	dprintk("RPC:       %s: ib_alloc_fmr status %i\n", __func__, rc);
+	kfree(r);
+	return rc;
+}
+
+/* Use the ib_map_phys_fmr() verb to register a memory region
+ * for remote access via RDMA READ or RDMA WRITE.
+ */
+static int
+fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
+	   int nsegs, bool writing)
+{
+	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+	struct ib_device *device = ia->ri_id->device;
+	enum dma_data_direction direction = rpcrdma_data_dir(writing);
+	struct rpcrdma_mr_seg *seg1 = seg;
+	struct rpcrdma_mw *mw = seg1->rl_mw;
+	u64 physaddrs[RPCRDMA_MAX_DATA_SEGS];
+	int len, pageoff, i, rc;
+
+	pageoff = offset_in_page(seg1->mr_offset);
+	seg1->mr_offset -= pageoff;	/* start of page */
+	seg1->mr_len += pageoff;
+	len = -pageoff;
+	if (nsegs > RPCRDMA_MAX_FMR_SGES)
+		nsegs = RPCRDMA_MAX_FMR_SGES;
+	for (i = 0; i < nsegs;) {
+		rpcrdma_map_one(device, seg, direction);
+		physaddrs[i] = seg->mr_dma;
+		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;
+	}
+
+	rc = ib_map_phys_fmr(mw->r.fmr, physaddrs, i, seg1->mr_dma);
+	if (rc)
+		goto out_maperr;
+
+	seg1->mr_rkey = mw->r.fmr->rkey;
+	seg1->mr_base = seg1->mr_dma + pageoff;
+	seg1->mr_nsegs = i;
+	seg1->mr_len = len;
+	return i;
+
+out_maperr:
+	dprintk("RPC:       %s: ib_map_phys_fmr %u@0x%llx+%i (%d) status %i\n",
+		__func__, len, (unsigned long long)seg1->mr_dma,
+		pageoff, i, rc);
+	while (i--)
+		rpcrdma_unmap_one(device, --seg);
+	return rc;
+}
+
+/* Use the ib_unmap_fmr() verb to prevent further remote
+ * access via RDMA READ or RDMA WRITE.
+ */
+static int
+fmr_op_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg)
+{
+	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+	struct rpcrdma_mr_seg *seg1 = seg;
+	struct ib_device *device;
+	int rc, nsegs = seg->mr_nsegs;
+	LIST_HEAD(l);
+
+	list_add(&seg1->rl_mw->r.fmr->list, &l);
+	rc = ib_unmap_fmr(&l);
+	read_lock(&ia->ri_qplock);
+	device = ia->ri_id->device;
+	while (seg1->mr_nsegs--)
+		rpcrdma_unmap_one(device, seg++);
+	read_unlock(&ia->ri_qplock);
+	if (rc)
+		goto out_err;
+	return nsegs;
+
+out_err:
+	dprintk("RPC:       %s: ib_unmap_fmr status %i\n", __func__, rc);
+	return nsegs;
+}
+
+/* After a disconnect, unmap all FMRs.
+ *
+ * This is invoked only in the transport connect worker in order
+ * to serialize with rpcrdma_register_fmr_external().
+ */
+static void
+fmr_op_reset(struct rpcrdma_xprt *r_xprt)
+{
+	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
+	struct rpcrdma_mw *r;
+	LIST_HEAD(list);
+	int rc;
+
+	list_for_each_entry(r, &buf->rb_all, mw_all)
+		list_add(&r->r.fmr->list, &list);
+
+	rc = ib_unmap_fmr(&list);
+	if (rc)
+		dprintk("RPC:       %s: ib_unmap_fmr failed %i\n",
+			__func__, rc);
+}
+
+static void
+fmr_op_destroy(struct rpcrdma_buffer *buf)
+{
+	struct rpcrdma_mw *r;
+	int rc;
+
+	while (!list_empty(&buf->rb_all)) {
+		r = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all);
+		list_del(&r->mw_all);
+		rc = ib_dealloc_fmr(r->r.fmr);
+		if (rc)
+			dprintk("RPC:       %s: ib_dealloc_fmr failed %i\n",
+				__func__, rc);
+		kfree(r);
+	}
+}
+
+const struct rpcrdma_memreg_ops rpcrdma_fmr_memreg_ops = {
+	.ro_map				= fmr_op_map,
+	.ro_unmap			= fmr_op_unmap,
+	.ro_open			= fmr_op_open,
+	.ro_maxpages			= fmr_op_maxpages,
+	.ro_init			= fmr_op_init,
+	.ro_reset			= fmr_op_reset,
+	.ro_destroy			= fmr_op_destroy,
+	.ro_displayname			= "fmr",
+};
diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
new file mode 100644
index 000000000000..dff0481dbcf8
--- /dev/null
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -0,0 +1,353 @@
+/*
+ * Copyright (c) 2015 Oracle.  All rights reserved.
+ * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved.
+ */
+
+/* Lightweight memory registration using Fast Registration Work
+ * Requests (FRWR). Also referred to sometimes as FRMR mode.
+ *
+ * FRWR features ordered asynchronous registration and deregistration
+ * of arbitrarily sized memory regions. This is the fastest and safest
+ * but most complex memory registration mode.
+ */
+
+#include "xprt_rdma.h"
+
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
+# define RPCDBG_FACILITY	RPCDBG_TRANS
+#endif
+
+static int
+__frwr_init(struct rpcrdma_mw *r, struct ib_pd *pd, struct ib_device *device,
+	    unsigned int depth)
+{
+	struct rpcrdma_frmr *f = &r->r.frmr;
+	int rc;
+
+	f->fr_mr = ib_alloc_fast_reg_mr(pd, depth);
+	if (IS_ERR(f->fr_mr))
+		goto out_mr_err;
+	f->fr_pgl = ib_alloc_fast_reg_page_list(device, depth);
+	if (IS_ERR(f->fr_pgl))
+		goto out_list_err;
+	return 0;
+
+out_mr_err:
+	rc = PTR_ERR(f->fr_mr);
+	dprintk("RPC:       %s: ib_alloc_fast_reg_mr status %i\n",
+		__func__, rc);
+	return rc;
+
+out_list_err:
+	rc = PTR_ERR(f->fr_pgl);
+	dprintk("RPC:       %s: ib_alloc_fast_reg_page_list status %i\n",
+		__func__, rc);
+	ib_dereg_mr(f->fr_mr);
+	return rc;
+}
+
+static void
+__frwr_release(struct rpcrdma_mw *r)
+{
+	int rc;
+
+	rc = ib_dereg_mr(r->r.frmr.fr_mr);
+	if (rc)
+		dprintk("RPC:       %s: ib_dereg_mr status %i\n",
+			__func__, rc);
+	ib_free_fast_reg_page_list(r->r.frmr.fr_pgl);
+}
+
+static int
+frwr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep,
+	     struct rpcrdma_create_data_internal *cdata)
+{
+	struct ib_device_attr *devattr = &ia->ri_devattr;
+	int depth, delta;
+
+	ia->ri_max_frmr_depth =
+			min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS,
+			      devattr->max_fast_reg_page_list_len);
+	dprintk("RPC:       %s: device's max FR page list len = %u\n",
+		__func__, ia->ri_max_frmr_depth);
+
+	/* Add room for frmr register and invalidate WRs.
+	 * 1. FRMR reg WR for head
+	 * 2. FRMR invalidate WR for head
+	 * 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
+	 */
+	depth = 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) {
+		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 / depth;
+		if (!cdata->max_requests)
+			return -EINVAL;
+		ep->rep_attr.cap.max_send_wr = cdata->max_requests *
+					       depth;
+	}
+
+	return 0;
+}
+
+/* FRWR mode conveys a list of pages per chunk segment. The
+ * maximum length of that list is the FRWR page list depth.
+ */
+static size_t
+frwr_op_maxpages(struct rpcrdma_xprt *r_xprt)
+{
+	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+
+	return min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS,
+		     rpcrdma_max_segments(r_xprt) * ia->ri_max_frmr_depth);
+}
+
+/* If FAST_REG or LOCAL_INV failed, indicate the frmr needs to be reset. */
+static void
+frwr_sendcompletion(struct ib_wc *wc)
+{
+	struct rpcrdma_mw *r;
+
+	if (likely(wc->status == IB_WC_SUCCESS))
+		return;
+
+	/* WARNING: Only wr_id and status are reliable at this point */
+	r = (struct rpcrdma_mw *)(unsigned long)wc->wr_id;
+	dprintk("RPC:       %s: frmr %p (stale), status %d\n",
+		__func__, r, wc->status);
+	r->r.frmr.fr_state = FRMR_IS_STALE;
+}
+
+static int
+frwr_op_init(struct rpcrdma_xprt *r_xprt)
+{
+	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
+	struct ib_device *device = r_xprt->rx_ia.ri_id->device;
+	unsigned int depth = r_xprt->rx_ia.ri_max_frmr_depth;
+	struct ib_pd *pd = r_xprt->rx_ia.ri_pd;
+	int i;
+
+	INIT_LIST_HEAD(&buf->rb_mws);
+	INIT_LIST_HEAD(&buf->rb_all);
+
+	i = (buf->rb_max_requests + 1) * RPCRDMA_MAX_SEGS;
+	dprintk("RPC:       %s: initializing %d FRMRs\n", __func__, i);
+
+	while (i--) {
+		struct rpcrdma_mw *r;
+		int rc;
+
+		r = kzalloc(sizeof(*r), GFP_KERNEL);
+		if (!r)
+			return -ENOMEM;
+
+		rc = __frwr_init(r, pd, device, depth);
+		if (rc) {
+			kfree(r);
+			return rc;
+		}
+
+		list_add(&r->mw_list, &buf->rb_mws);
+		list_add(&r->mw_all, &buf->rb_all);
+		r->mw_sendcompletion = frwr_sendcompletion;
+	}
+
+	return 0;
+}
+
+/* Post a FAST_REG Work Request to register a memory region
+ * for remote access via RDMA READ or RDMA WRITE.
+ */
+static int
+frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
+	    int nsegs, bool writing)
+{
+	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+	struct ib_device *device = ia->ri_id->device;
+	enum dma_data_direction direction = rpcrdma_data_dir(writing);
+	struct rpcrdma_mr_seg *seg1 = seg;
+	struct rpcrdma_mw *mw = seg1->rl_mw;
+	struct rpcrdma_frmr *frmr = &mw->r.frmr;
+	struct ib_mr *mr = frmr->fr_mr;
+	struct ib_send_wr fastreg_wr, *bad_wr;
+	u8 key;
+	int len, pageoff;
+	int i, rc;
+	int seg_len;
+	u64 pa;
+	int page_no;
+
+	pageoff = offset_in_page(seg1->mr_offset);
+	seg1->mr_offset -= pageoff;	/* start of page */
+	seg1->mr_len += pageoff;
+	len = -pageoff;
+	if (nsegs > ia->ri_max_frmr_depth)
+		nsegs = ia->ri_max_frmr_depth;
+	for (page_no = i = 0; i < nsegs;) {
+		rpcrdma_map_one(device, seg, direction);
+		pa = seg->mr_dma;
+		for (seg_len = seg->mr_len; seg_len > 0; seg_len -= PAGE_SIZE) {
+			frmr->fr_pgl->page_list[page_no++] = pa;
+			pa += PAGE_SIZE;
+		}
+		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;
+	}
+	dprintk("RPC:       %s: Using frmr %p to map %d segments (%d bytes)\n",
+		__func__, mw, i, len);
+
+	frmr->fr_state = FRMR_IS_VALID;
+
+	memset(&fastreg_wr, 0, sizeof(fastreg_wr));
+	fastreg_wr.wr_id = (unsigned long)(void *)mw;
+	fastreg_wr.opcode = IB_WR_FAST_REG_MR;
+	fastreg_wr.wr.fast_reg.iova_start = seg1->mr_dma + pageoff;
+	fastreg_wr.wr.fast_reg.page_list = frmr->fr_pgl;
+	fastreg_wr.wr.fast_reg.page_shift = PAGE_SHIFT;
+	fastreg_wr.wr.fast_reg.page_list_len = page_no;
+	fastreg_wr.wr.fast_reg.length = len;
+	fastreg_wr.wr.fast_reg.access_flags = writing ?
+				IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE :
+				IB_ACCESS_REMOTE_READ;
+	key = (u8)(mr->rkey & 0x000000FF);
+	ib_update_fast_reg_key(mr, ++key);
+	fastreg_wr.wr.fast_reg.rkey = mr->rkey;
+
+	DECR_CQCOUNT(&r_xprt->rx_ep);
+	rc = ib_post_send(ia->ri_id->qp, &fastreg_wr, &bad_wr);
+	if (rc)
+		goto out_senderr;
+
+	seg1->mr_rkey = mr->rkey;
+	seg1->mr_base = seg1->mr_dma + pageoff;
+	seg1->mr_nsegs = i;
+	seg1->mr_len = len;
+	return i;
+
+out_senderr:
+	dprintk("RPC:       %s: ib_post_send status %i\n", __func__, rc);
+	ib_update_fast_reg_key(mr, --key);
+	frmr->fr_state = FRMR_IS_INVALID;
+	while (i--)
+		rpcrdma_unmap_one(device, --seg);
+	return rc;
+}
+
+/* Post a LOCAL_INV Work Request to prevent further remote access
+ * via RDMA READ or RDMA WRITE.
+ */
+static int
+frwr_op_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg)
+{
+	struct rpcrdma_mr_seg *seg1 = seg;
+	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+	struct ib_send_wr invalidate_wr, *bad_wr;
+	int rc, nsegs = seg->mr_nsegs;
+	struct ib_device *device;
+
+	seg1->rl_mw->r.frmr.fr_state = FRMR_IS_INVALID;
+
+	memset(&invalidate_wr, 0, sizeof(invalidate_wr));
+	invalidate_wr.wr_id = (unsigned long)(void *)seg1->rl_mw;
+	invalidate_wr.opcode = IB_WR_LOCAL_INV;
+	invalidate_wr.ex.invalidate_rkey = seg1->rl_mw->r.frmr.fr_mr->rkey;
+	DECR_CQCOUNT(&r_xprt->rx_ep);
+
+	read_lock(&ia->ri_qplock);
+	device = ia->ri_id->device;
+	while (seg1->mr_nsegs--)
+		rpcrdma_unmap_one(device, seg++);
+	rc = ib_post_send(ia->ri_id->qp, &invalidate_wr, &bad_wr);
+	read_unlock(&ia->ri_qplock);
+	if (rc)
+		goto out_err;
+	return nsegs;
+
+out_err:
+	/* Force rpcrdma_buffer_get() to retry */
+	seg1->rl_mw->r.frmr.fr_state = FRMR_IS_STALE;
+	dprintk("RPC:       %s: ib_post_send status %i\n", __func__, rc);
+	return nsegs;
+}
+
+/* After a disconnect, a flushed FAST_REG_MR can leave an FRMR in
+ * an unusable state. Find FRMRs in this state and dereg / reg
+ * each.  FRMRs that are VALID and attached to an rpcrdma_req are
+ * also torn down.
+ *
+ * This gives all in-use FRMRs a fresh rkey and leaves them INVALID.
+ *
+ * This is invoked only in the transport connect worker in order
+ * to serialize with rpcrdma_register_frmr_external().
+ */
+static void
+frwr_op_reset(struct rpcrdma_xprt *r_xprt)
+{
+	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
+	struct ib_device *device = r_xprt->rx_ia.ri_id->device;
+	unsigned int depth = r_xprt->rx_ia.ri_max_frmr_depth;
+	struct ib_pd *pd = r_xprt->rx_ia.ri_pd;
+	struct rpcrdma_mw *r;
+	int rc;
+
+	list_for_each_entry(r, &buf->rb_all, mw_all) {
+		if (r->r.frmr.fr_state == FRMR_IS_INVALID)
+			continue;
+
+		__frwr_release(r);
+		rc = __frwr_init(r, pd, device, depth);
+		if (rc) {
+			dprintk("RPC:       %s: mw %p left %s\n",
+				__func__, r,
+				(r->r.frmr.fr_state == FRMR_IS_STALE ?
+					"stale" : "valid"));
+			continue;
+		}
+
+		r->r.frmr.fr_state = FRMR_IS_INVALID;
+	}
+}
+
+static void
+frwr_op_destroy(struct rpcrdma_buffer *buf)
+{
+	struct rpcrdma_mw *r;
+
+	while (!list_empty(&buf->rb_all)) {
+		r = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all);
+		list_del(&r->mw_all);
+		__frwr_release(r);
+		kfree(r);
+	}
+}
+
+const struct rpcrdma_memreg_ops rpcrdma_frwr_memreg_ops = {
+	.ro_map				= frwr_op_map,
+	.ro_unmap			= frwr_op_unmap,
+	.ro_open			= frwr_op_open,
+	.ro_maxpages			= frwr_op_maxpages,
+	.ro_init			= frwr_op_init,
+	.ro_reset			= frwr_op_reset,
+	.ro_destroy			= frwr_op_destroy,
+	.ro_displayname			= "frwr",
+};
diff --git a/net/sunrpc/xprtrdma/physical_ops.c b/net/sunrpc/xprtrdma/physical_ops.c
new file mode 100644
index 000000000000..ba518af16787
--- /dev/null
+++ b/net/sunrpc/xprtrdma/physical_ops.c
@@ -0,0 +1,94 @@
+/*
+ * Copyright (c) 2015 Oracle.  All rights reserved.
+ * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved.
+ */
+
+/* No-op chunk preparation. All client memory is pre-registered.
+ * Sometimes referred to as ALLPHYSICAL mode.
+ *
+ * Physical registration is simple because all client memory is
+ * pre-registered and never deregistered. This mode is good for
+ * adapter bring up, but is considered not safe: the server is
+ * trusted not to abuse its access to client memory not involved
+ * in RDMA I/O.
+ */
+
+#include "xprt_rdma.h"
+
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
+# define RPCDBG_FACILITY	RPCDBG_TRANS
+#endif
+
+static int
+physical_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep,
+		 struct rpcrdma_create_data_internal *cdata)
+{
+	return 0;
+}
+
+/* PHYSICAL memory registration conveys one page per chunk segment.
+ */
+static size_t
+physical_op_maxpages(struct rpcrdma_xprt *r_xprt)
+{
+	return min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS,
+		     rpcrdma_max_segments(r_xprt));
+}
+
+static int
+physical_op_init(struct rpcrdma_xprt *r_xprt)
+{
+	return 0;
+}
+
+/* The client's physical memory is already exposed for
+ * remote access via RDMA READ or RDMA WRITE.
+ */
+static int
+physical_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
+		int nsegs, bool writing)
+{
+	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+
+	rpcrdma_map_one(ia->ri_id->device, seg,
+			rpcrdma_data_dir(writing));
+	seg->mr_rkey = ia->ri_bind_mem->rkey;
+	seg->mr_base = seg->mr_dma;
+	seg->mr_nsegs = 1;
+	return 1;
+}
+
+/* Unmap a memory region, but leave it registered.
+ */
+static int
+physical_op_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg)
+{
+	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+
+	read_lock(&ia->ri_qplock);
+	rpcrdma_unmap_one(ia->ri_id->device, seg);
+	read_unlock(&ia->ri_qplock);
+
+	return 1;
+}
+
+static void
+physical_op_reset(struct rpcrdma_xprt *r_xprt)
+{
+}
+
+static void
+physical_op_destroy(struct rpcrdma_buffer *buf)
+{
+}
+
+const struct rpcrdma_memreg_ops rpcrdma_physical_memreg_ops = {
+	.ro_map				= physical_op_map,
+	.ro_unmap			= physical_op_unmap,
+	.ro_open			= physical_op_open,
+	.ro_maxpages			= physical_op_maxpages,
+	.ro_init			= physical_op_init,
+	.ro_reset			= physical_op_reset,
+	.ro_destroy			= physical_op_destroy,
+	.ro_displayname			= "physical",
+};
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 6166c985fe24..2c53ea9e1b83 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -49,11 +49,19 @@
 
 #include <linux/highmem.h>
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_TRANS
 #endif
 
-#ifdef RPC_DEBUG
+enum rpcrdma_chunktype {
+	rpcrdma_noch = 0,
+	rpcrdma_readch,
+	rpcrdma_areadch,
+	rpcrdma_writech,
+	rpcrdma_replych
+};
+
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 static const char transfertypes[][12] = {
 	"pure inline",	/* no chunks */
 	" read chunk",	/* some argument via rdma read */
@@ -179,6 +187,7 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target,
 	struct rpcrdma_write_array *warray = NULL;
 	struct rpcrdma_write_chunk *cur_wchunk = NULL;
 	__be32 *iptr = headerp->rm_body.rm_chunks;
+	int (*map)(struct rpcrdma_xprt *, struct rpcrdma_mr_seg *, int, bool);
 
 	if (type == rpcrdma_readch || type == rpcrdma_areadch) {
 		/* a read chunk - server will RDMA Read our memory */
@@ -201,17 +210,19 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target,
 	if (nsegs < 0)
 		return nsegs;
 
+	map = r_xprt->rx_ia.ri_ops->ro_map;
 	do {
-		n = rpcrdma_register_external(seg, nsegs,
-						cur_wchunk != NULL, r_xprt);
+		n = map(r_xprt, seg, nsegs, cur_wchunk != NULL);
 		if (n <= 0)
 			goto out;
 		if (cur_rchunk) {	/* read */
 			cur_rchunk->rc_discrim = xdr_one;
 			/* all read chunks have the same "position" */
-			cur_rchunk->rc_position = htonl(pos);
-			cur_rchunk->rc_target.rs_handle = htonl(seg->mr_rkey);
-			cur_rchunk->rc_target.rs_length = htonl(seg->mr_len);
+			cur_rchunk->rc_position = cpu_to_be32(pos);
+			cur_rchunk->rc_target.rs_handle =
+						cpu_to_be32(seg->mr_rkey);
+			cur_rchunk->rc_target.rs_length =
+						cpu_to_be32(seg->mr_len);
 			xdr_encode_hyper(
 					(__be32 *)&cur_rchunk->rc_target.rs_offset,
 					seg->mr_base);
@@ -222,8 +233,10 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target,
 			cur_rchunk++;
 			r_xprt->rx_stats.read_chunk_count++;
 		} else {		/* write/reply */
-			cur_wchunk->wc_target.rs_handle = htonl(seg->mr_rkey);
-			cur_wchunk->wc_target.rs_length = htonl(seg->mr_len);
+			cur_wchunk->wc_target.rs_handle =
+						cpu_to_be32(seg->mr_rkey);
+			cur_wchunk->wc_target.rs_length =
+						cpu_to_be32(seg->mr_len);
 			xdr_encode_hyper(
 					(__be32 *)&cur_wchunk->wc_target.rs_offset,
 					seg->mr_base);
@@ -257,7 +270,7 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target,
 		*iptr++ = xdr_zero;	/* encode a NULL reply chunk */
 	} else {
 		warray->wc_discrim = xdr_one;
-		warray->wc_nchunks = htonl(nchunks);
+		warray->wc_nchunks = cpu_to_be32(nchunks);
 		iptr = (__be32 *) cur_wchunk;
 		if (type == rpcrdma_writech) {
 			*iptr++ = xdr_zero; /* finish the write chunk list */
@@ -271,34 +284,13 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target,
 	return (unsigned char *)iptr - (unsigned char *)headerp;
 
 out:
-	if (r_xprt->rx_ia.ri_memreg_strategy != RPCRDMA_FRMR) {
-		for (pos = 0; nchunks--;)
-			pos += rpcrdma_deregister_external(
-					&req->rl_segments[pos], r_xprt);
-	}
-	return n;
-}
-
-/*
- * Marshal chunks. This routine returns the header length
- * consumed by marshaling.
- *
- * Returns positive RPC/RDMA header size, or negative errno.
- */
+	if (r_xprt->rx_ia.ri_memreg_strategy == RPCRDMA_FRMR)
+		return n;
 
-ssize_t
-rpcrdma_marshal_chunks(struct rpc_rqst *rqst, ssize_t result)
-{
-	struct rpcrdma_req *req = rpcr_to_rdmar(rqst);
-	struct rpcrdma_msg *headerp = (struct rpcrdma_msg *)req->rl_base;
-
-	if (req->rl_rtype != rpcrdma_noch)
-		result = rpcrdma_create_chunks(rqst, &rqst->rq_snd_buf,
-					       headerp, req->rl_rtype);
-	else if (req->rl_wtype != rpcrdma_noch)
-		result = rpcrdma_create_chunks(rqst, &rqst->rq_rcv_buf,
-					       headerp, req->rl_wtype);
-	return result;
+	for (pos = 0; nchunks--;)
+		pos += r_xprt->rx_ia.ri_ops->ro_unmap(r_xprt,
+						      &req->rl_segments[pos]);
+	return n;
 }
 
 /*
@@ -393,6 +385,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	char *base;
 	size_t rpclen, padlen;
 	ssize_t hdrlen;
+	enum rpcrdma_chunktype rtype, wtype;
 	struct rpcrdma_msg *headerp;
 
 	/*
@@ -402,13 +395,12 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	base = rqst->rq_svec[0].iov_base;
 	rpclen = rqst->rq_svec[0].iov_len;
 
-	/* build RDMA header in private area at front */
-	headerp = (struct rpcrdma_msg *) req->rl_base;
-	/* don't htonl XID, it's already done in request */
+	headerp = rdmab_to_msg(req->rl_rdmabuf);
+	/* don't byte-swap XID, it's already done in request */
 	headerp->rm_xid = rqst->rq_xid;
-	headerp->rm_vers = xdr_one;
-	headerp->rm_credit = htonl(r_xprt->rx_buf.rb_max_requests);
-	headerp->rm_type = htonl(RDMA_MSG);
+	headerp->rm_vers = rpcrdma_version;
+	headerp->rm_credit = cpu_to_be32(r_xprt->rx_buf.rb_max_requests);
+	headerp->rm_type = rdma_msg;
 
 	/*
 	 * Chunks needed for results?
@@ -430,13 +422,13 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	 * into pages; otherwise use reply chunks.
 	 */
 	if (rqst->rq_rcv_buf.buflen <= RPCRDMA_INLINE_READ_THRESHOLD(rqst))
-		req->rl_wtype = rpcrdma_noch;
+		wtype = rpcrdma_noch;
 	else if (rqst->rq_rcv_buf.page_len == 0)
-		req->rl_wtype = rpcrdma_replych;
+		wtype = rpcrdma_replych;
 	else if (rqst->rq_rcv_buf.flags & XDRBUF_READ)
-		req->rl_wtype = rpcrdma_writech;
+		wtype = rpcrdma_writech;
 	else
-		req->rl_wtype = rpcrdma_replych;
+		wtype = rpcrdma_replych;
 
 	/*
 	 * Chunks needed for arguments?
@@ -453,22 +445,22 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	 * TBD check NFSv4 setacl
 	 */
 	if (rqst->rq_snd_buf.len <= RPCRDMA_INLINE_WRITE_THRESHOLD(rqst))
-		req->rl_rtype = rpcrdma_noch;
+		rtype = rpcrdma_noch;
 	else if (rqst->rq_snd_buf.page_len == 0)
-		req->rl_rtype = rpcrdma_areadch;
+		rtype = rpcrdma_areadch;
 	else
-		req->rl_rtype = rpcrdma_readch;
+		rtype = rpcrdma_readch;
 
 	/* The following simplification is not true forever */
-	if (req->rl_rtype != rpcrdma_noch && req->rl_wtype == rpcrdma_replych)
-		req->rl_wtype = rpcrdma_noch;
-	if (req->rl_rtype != rpcrdma_noch && req->rl_wtype != rpcrdma_noch) {
+	if (rtype != rpcrdma_noch && wtype == rpcrdma_replych)
+		wtype = rpcrdma_noch;
+	if (rtype != rpcrdma_noch && wtype != rpcrdma_noch) {
 		dprintk("RPC:       %s: cannot marshal multiple chunk lists\n",
 			__func__);
 		return -EIO;
 	}
 
-	hdrlen = 28; /*sizeof *headerp;*/
+	hdrlen = RPCRDMA_HDRLEN_MIN;
 	padlen = 0;
 
 	/*
@@ -476,22 +468,22 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	 * When padding is in use and applies to the transfer, insert
 	 * it and change the message type.
 	 */
-	if (req->rl_rtype == rpcrdma_noch) {
+	if (rtype == rpcrdma_noch) {
 
 		padlen = rpcrdma_inline_pullup(rqst,
 						RPCRDMA_INLINE_PAD_VALUE(rqst));
 
 		if (padlen) {
-			headerp->rm_type = htonl(RDMA_MSGP);
+			headerp->rm_type = rdma_msgp;
 			headerp->rm_body.rm_padded.rm_align =
-				htonl(RPCRDMA_INLINE_PAD_VALUE(rqst));
+				cpu_to_be32(RPCRDMA_INLINE_PAD_VALUE(rqst));
 			headerp->rm_body.rm_padded.rm_thresh =
-				htonl(RPCRDMA_INLINE_PAD_THRESH);
+				cpu_to_be32(RPCRDMA_INLINE_PAD_THRESH);
 			headerp->rm_body.rm_padded.rm_pempty[0] = xdr_zero;
 			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 */
-			if (req->rl_wtype != rpcrdma_noch) {
+			if (wtype != rpcrdma_noch) {
 				dprintk("RPC:       %s: invalid chunk list\n",
 					__func__);
 				return -EIO;
@@ -512,19 +504,27 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 			 * on receive. Therefore, we request a reply chunk
 			 * for non-writes wherever feasible and efficient.
 			 */
-			if (req->rl_wtype == rpcrdma_noch)
-				req->rl_wtype = rpcrdma_replych;
+			if (wtype == rpcrdma_noch)
+				wtype = rpcrdma_replych;
 		}
 	}
 
-	hdrlen = rpcrdma_marshal_chunks(rqst, hdrlen);
+	if (rtype != rpcrdma_noch) {
+		hdrlen = rpcrdma_create_chunks(rqst, &rqst->rq_snd_buf,
+					       headerp, rtype);
+		wtype = rtype;	/* simplify dprintk */
+
+	} else if (wtype != rpcrdma_noch) {
+		hdrlen = rpcrdma_create_chunks(rqst, &rqst->rq_rcv_buf,
+					       headerp, wtype);
+	}
 	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",
-		__func__, transfertypes[req->rl_wtype], hdrlen, rpclen, padlen,
-		headerp, base, req->rl_iov.lkey);
+		__func__, transfertypes[wtype], hdrlen, rpclen, padlen,
+		headerp, base, rdmab_lkey(req->rl_rdmabuf));
 
 	/*
 	 * initialize send_iov's - normally only two: rdma chunk header and
@@ -533,26 +533,26 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	 * header and any write data. In all non-rdma cases, any following
 	 * data has been copied into the RPC header buffer.
 	 */
-	req->rl_send_iov[0].addr = req->rl_iov.addr;
+	req->rl_send_iov[0].addr = rdmab_addr(req->rl_rdmabuf);
 	req->rl_send_iov[0].length = hdrlen;
-	req->rl_send_iov[0].lkey = req->rl_iov.lkey;
+	req->rl_send_iov[0].lkey = rdmab_lkey(req->rl_rdmabuf);
 
-	req->rl_send_iov[1].addr = req->rl_iov.addr + (base - req->rl_base);
+	req->rl_send_iov[1].addr = rdmab_addr(req->rl_sendbuf);
 	req->rl_send_iov[1].length = rpclen;
-	req->rl_send_iov[1].lkey = req->rl_iov.lkey;
+	req->rl_send_iov[1].lkey = rdmab_lkey(req->rl_sendbuf);
 
 	req->rl_niovs = 2;
 
 	if (padlen) {
 		struct rpcrdma_ep *ep = &r_xprt->rx_ep;
 
-		req->rl_send_iov[2].addr = ep->rep_pad.addr;
+		req->rl_send_iov[2].addr = rdmab_addr(ep->rep_padbuf);
 		req->rl_send_iov[2].length = padlen;
-		req->rl_send_iov[2].lkey = ep->rep_pad.lkey;
+		req->rl_send_iov[2].lkey = rdmab_lkey(ep->rep_padbuf);
 
 		req->rl_send_iov[3].addr = req->rl_send_iov[1].addr + rpclen;
 		req->rl_send_iov[3].length = rqst->rq_slen - rpclen;
-		req->rl_send_iov[3].lkey = req->rl_iov.lkey;
+		req->rl_send_iov[3].lkey = rdmab_lkey(req->rl_sendbuf);
 
 		req->rl_niovs = 4;
 	}
@@ -569,8 +569,9 @@ rpcrdma_count_chunks(struct rpcrdma_rep *rep, unsigned int max, int wrchunk, __b
 {
 	unsigned int i, total_len;
 	struct rpcrdma_write_chunk *cur_wchunk;
+	char *base = (char *)rdmab_to_msg(rep->rr_rdmabuf);
 
-	i = ntohl(**iptrp);	/* get array count */
+	i = be32_to_cpu(**iptrp);
 	if (i > max)
 		return -1;
 	cur_wchunk = (struct rpcrdma_write_chunk *) (*iptrp + 1);
@@ -582,11 +583,11 @@ rpcrdma_count_chunks(struct rpcrdma_rep *rep, unsigned int max, int wrchunk, __b
 			xdr_decode_hyper((__be32 *)&seg->rs_offset, &off);
 			dprintk("RPC:       %s: chunk %d@0x%llx:0x%x\n",
 				__func__,
-				ntohl(seg->rs_length),
+				be32_to_cpu(seg->rs_length),
 				(unsigned long long)off,
-				ntohl(seg->rs_handle));
+				be32_to_cpu(seg->rs_handle));
 		}
-		total_len += ntohl(seg->rs_length);
+		total_len += be32_to_cpu(seg->rs_length);
 		++cur_wchunk;
 	}
 	/* check and adjust for properly terminated write chunk */
@@ -596,7 +597,7 @@ rpcrdma_count_chunks(struct rpcrdma_rep *rep, unsigned int max, int wrchunk, __b
 			return -1;
 		cur_wchunk = (struct rpcrdma_write_chunk *) w;
 	}
-	if ((char *) cur_wchunk > rep->rr_base + rep->rr_len)
+	if ((char *)cur_wchunk > base + rep->rr_len)
 		return -1;
 
 	*iptrp = (__be32 *) cur_wchunk;
@@ -691,7 +692,9 @@ 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;
+	struct rpcrdma_xprt *r_xprt =
+		container_of(ep, struct rpcrdma_xprt, rx_ep);
+	struct rpc_xprt *xprt = &r_xprt->rx_xprt;
 
 	spin_lock_bh(&xprt->transport_lock);
 	if (++xprt->connect_cookie == 0)	/* maintain a reserved value */
@@ -734,6 +737,7 @@ rpcrdma_reply_handler(struct rpcrdma_rep *rep)
 	__be32 *iptr;
 	int rdmalen, status;
 	unsigned long cwnd;
+	u32 credits;
 
 	/* Check status. If bad, signal disconnect and return rep to pool */
 	if (rep->rr_len == ~0U) {
@@ -744,14 +748,14 @@ rpcrdma_reply_handler(struct rpcrdma_rep *rep)
 		}
 		return;
 	}
-	if (rep->rr_len < 28) {
+	if (rep->rr_len < RPCRDMA_HDRLEN_MIN) {
 		dprintk("RPC:       %s: short/invalid reply\n", __func__);
 		goto repost;
 	}
-	headerp = (struct rpcrdma_msg *) rep->rr_base;
-	if (headerp->rm_vers != xdr_one) {
+	headerp = rdmab_to_msg(rep->rr_rdmabuf);
+	if (headerp->rm_vers != rpcrdma_version) {
 		dprintk("RPC:       %s: invalid version %d\n",
-			__func__, ntohl(headerp->rm_vers));
+			__func__, be32_to_cpu(headerp->rm_vers));
 		goto repost;
 	}
 
@@ -762,7 +766,8 @@ rpcrdma_reply_handler(struct rpcrdma_rep *rep)
 		spin_unlock(&xprt->transport_lock);
 		dprintk("RPC:       %s: reply 0x%p failed "
 			"to match any request xid 0x%08x len %d\n",
-			__func__, rep, headerp->rm_xid, rep->rr_len);
+			__func__, rep, be32_to_cpu(headerp->rm_xid),
+			rep->rr_len);
 repost:
 		r_xprt->rx_stats.bad_reply_count++;
 		rep->rr_func = rpcrdma_reply_handler;
@@ -778,13 +783,14 @@ repost:
 		spin_unlock(&xprt->transport_lock);
 		dprintk("RPC:       %s: duplicate reply 0x%p to RPC "
 			"request 0x%p: xid 0x%08x\n", __func__, rep, req,
-			headerp->rm_xid);
+			be32_to_cpu(headerp->rm_xid));
 		goto repost;
 	}
 
 	dprintk("RPC:       %s: reply 0x%p completes request 0x%p\n"
 		"                   RPC request 0x%p xid 0x%08x\n",
-			__func__, rep, req, rqst, headerp->rm_xid);
+			__func__, rep, req, rqst,
+			be32_to_cpu(headerp->rm_xid));
 
 	/* from here on, the reply is no longer an orphan */
 	req->rl_reply = rep;
@@ -793,7 +799,7 @@ repost:
 	/* check for expected message types */
 	/* The order of some of these tests is important. */
 	switch (headerp->rm_type) {
-	case htonl(RDMA_MSG):
+	case rdma_msg:
 		/* never expect read chunks */
 		/* never expect reply chunks (two ways to check) */
 		/* never expect write chunks without having offered RDMA */
@@ -824,22 +830,24 @@ repost:
 		} else {
 			/* else ordinary inline */
 			rdmalen = 0;
-			iptr = (__be32 *)((unsigned char *)headerp + 28);
-			rep->rr_len -= 28; /*sizeof *headerp;*/
+			iptr = (__be32 *)((unsigned char *)headerp +
+							RPCRDMA_HDRLEN_MIN);
+			rep->rr_len -= RPCRDMA_HDRLEN_MIN;
 			status = rep->rr_len;
 		}
 		/* Fix up the rpc results for upper layer */
 		rpcrdma_inline_fixup(rqst, (char *)iptr, rep->rr_len, rdmalen);
 		break;
 
-	case htonl(RDMA_NOMSG):
+	case rdma_nomsg:
 		/* never expect read or write chunks, always reply chunks */
 		if (headerp->rm_body.rm_chunks[0] != xdr_zero ||
 		    headerp->rm_body.rm_chunks[1] != xdr_zero ||
 		    headerp->rm_body.rm_chunks[2] != xdr_one ||
 		    req->rl_nchunks == 0)
 			goto badheader;
-		iptr = (__be32 *)((unsigned char *)headerp + 28);
+		iptr = (__be32 *)((unsigned char *)headerp +
+							RPCRDMA_HDRLEN_MIN);
 		rdmalen = rpcrdma_count_chunks(rep, req->rl_nchunks, 0, &iptr);
 		if (rdmalen < 0)
 			goto badheader;
@@ -853,7 +861,7 @@ badheader:
 		dprintk("%s: invalid rpcrdma reply header (type %d):"
 				" chunks[012] == %d %d %d"
 				" expected chunks <= %d\n",
-				__func__, ntohl(headerp->rm_type),
+				__func__, be32_to_cpu(headerp->rm_type),
 				headerp->rm_body.rm_chunks[0],
 				headerp->rm_body.rm_chunks[1],
 				headerp->rm_body.rm_chunks[2],
@@ -863,8 +871,14 @@ badheader:
 		break;
 	}
 
+	credits = be32_to_cpu(headerp->rm_credit);
+	if (credits == 0)
+		credits = 1;	/* don't deadlock */
+	else if (credits > r_xprt->rx_buf.rb_max_requests)
+		credits = r_xprt->rx_buf.rb_max_requests;
+
 	cwnd = xprt->cwnd;
-	xprt->cwnd = atomic_read(&r_xprt->rx_buf.rb_credits) << RPC_CWNDSHIFT;
+	xprt->cwnd = credits << RPC_CWNDSHIFT;
 	if (xprt->cwnd > cwnd)
 		xprt_release_rqst_cong(rqst->rq_task);
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_marshal.c b/net/sunrpc/xprtrdma/svc_rdma_marshal.c
index 65b146297f5a..b681855cf970 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_marshal.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_marshal.c
@@ -71,22 +71,6 @@ static u32 *decode_read_list(u32 *va, u32 *vaend)
 }
 
 /*
- * Determine number of chunks and total bytes in chunk list. The chunk
- * list has already been verified to fit within the RPCRDMA header.
- */
-void svc_rdma_rcl_chunk_counts(struct rpcrdma_read_chunk *ch,
-			       int *ch_count, int *byte_count)
-{
-	/* compute the number of bytes represented by read chunks */
-	*byte_count = 0;
-	*ch_count = 0;
-	for (; ch->rc_discrim != 0; ch++) {
-		*byte_count = *byte_count + ntohl(ch->rc_target.rs_length);
-		*ch_count = *ch_count + 1;
-	}
-}
-
-/*
  * Decodes a write chunk list. The expected format is as follows:
  *    descrim  : xdr_one
  *    nchunks  : <count>
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index e0110270d650..f9f13a32ddb8 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -43,7 +43,6 @@
 #include <linux/sunrpc/debug.h>
 #include <linux/sunrpc/rpc_rdma.h>
 #include <linux/spinlock.h>
-#include <linux/highmem.h>
 #include <asm/unaligned.h>
 #include <rdma/ib_verbs.h>
 #include <rdma/rdma_cm.h>
@@ -60,6 +59,7 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp,
 			       struct svc_rdma_op_ctxt *ctxt,
 			       u32 byte_count)
 {
+	struct rpcrdma_msg *rmsgp;
 	struct page *page;
 	u32 bc;
 	int sge_no;
@@ -82,7 +82,14 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp,
 	/* If data remains, store it in the pagelist */
 	rqstp->rq_arg.page_len = bc;
 	rqstp->rq_arg.page_base = 0;
-	rqstp->rq_arg.pages = &rqstp->rq_pages[1];
+
+	/* RDMA_NOMSG: RDMA READ data should land just after RDMA RECV data */
+	rmsgp = (struct rpcrdma_msg *)rqstp->rq_arg.head[0].iov_base;
+	if (be32_to_cpu(rmsgp->rm_type) == RDMA_NOMSG)
+		rqstp->rq_arg.pages = &rqstp->rq_pages[0];
+	else
+		rqstp->rq_arg.pages = &rqstp->rq_pages[1];
+
 	sge_no = 1;
 	while (bc && sge_no < ctxt->count) {
 		page = ctxt->pages[sge_no];
@@ -95,14 +102,6 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp,
 	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
-	 */
-	BUG_ON(bc && (sge_no == ctxt->count));
-	BUG_ON((rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len)
-	       != byte_count);
-	BUG_ON(rqstp->rq_arg.len != byte_count);
-
 	/* If not all pages were used from the SGL, free the remaining ones */
 	bc = sge_no;
 	while (sge_no < ctxt->count) {
@@ -125,26 +124,16 @@ static int rdma_read_max_sge(struct svcxprt_rdma *xprt, int sge_count)
 		return min_t(int, sge_count, xprt->sc_max_sge);
 }
 
-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)
+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,
+			bool last)
 {
 	struct ib_send_wr read_wr;
 	int pages_needed = PAGE_ALIGN(*page_offset + rs_length) >> PAGE_SHIFT;
@@ -229,15 +218,15 @@ static int rdma_read_chunk_lcl(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,
-				int *page_no,
-				u32 *page_offset,
-				u32 rs_handle,
-				u32 rs_length,
-				u64 rs_offset,
-				int last)
+int rdma_read_chunk_frmr(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,
+			 bool last)
 {
 	struct ib_send_wr read_wr;
 	struct ib_send_wr inv_wr;
@@ -365,24 +354,84 @@ static int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt,
 	return ret;
 }
 
+static unsigned int
+rdma_rcl_chunk_count(struct rpcrdma_read_chunk *ch)
+{
+	unsigned int count;
+
+	for (count = 0; ch->rc_discrim != xdr_zero; ch++)
+		count++;
+	return count;
+}
+
+/* If there was additional inline content, append it to the end of arg.pages.
+ * Tail copy has to be done after the reader function has determined how many
+ * pages are needed for RDMA READ.
+ */
+static int
+rdma_copy_tail(struct svc_rqst *rqstp, struct svc_rdma_op_ctxt *head,
+	       u32 position, u32 byte_count, u32 page_offset, int page_no)
+{
+	char *srcp, *destp;
+	int ret;
+
+	ret = 0;
+	srcp = head->arg.head[0].iov_base + position;
+	byte_count = head->arg.head[0].iov_len - position;
+	if (byte_count > PAGE_SIZE) {
+		dprintk("svcrdma: large tail unsupported\n");
+		return 0;
+	}
+
+	/* Fit as much of the tail on the current page as possible */
+	if (page_offset != PAGE_SIZE) {
+		destp = page_address(rqstp->rq_arg.pages[page_no]);
+		destp += page_offset;
+		while (byte_count--) {
+			*destp++ = *srcp++;
+			page_offset++;
+			if (page_offset == PAGE_SIZE && byte_count)
+				goto more;
+		}
+		goto done;
+	}
+
+more:
+	/* Fit the rest on the next page */
+	page_no++;
+	destp = page_address(rqstp->rq_arg.pages[page_no]);
+	while (byte_count--)
+		*destp++ = *srcp++;
+
+	rqstp->rq_respages = &rqstp->rq_arg.pages[page_no+1];
+	rqstp->rq_next_page = rqstp->rq_respages + 1;
+
+done:
+	byte_count = head->arg.head[0].iov_len - position;
+	head->arg.page_len += byte_count;
+	head->arg.len += byte_count;
+	head->arg.buflen += byte_count;
+	return 1;
+}
+
 static int rdma_read_chunks(struct svcxprt_rdma *xprt,
 			    struct rpcrdma_msg *rmsgp,
 			    struct svc_rqst *rqstp,
 			    struct svc_rdma_op_ctxt *head)
 {
-	int page_no, ch_count, ret;
+	int page_no, ret;
 	struct rpcrdma_read_chunk *ch;
-	u32 page_offset, byte_count;
+	u32 handle, page_offset, byte_count;
+	u32 position;
 	u64 rs_offset;
-	rdma_reader_fn reader;
+	bool last;
 
 	/* If no read list is present, return 0 */
 	ch = svc_rdma_get_read_chunk(rmsgp);
 	if (!ch)
 		return 0;
 
-	svc_rdma_rcl_chunk_counts(ch, &ch_count, &byte_count);
-	if (ch_count > RPCSVC_MAXPAGES)
+	if (rdma_rcl_chunk_count(ch) > RPCSVC_MAXPAGES)
 		return -EINVAL;
 
 	/* The request is completed when the RDMA_READs complete. The
@@ -391,34 +440,41 @@ static int rdma_read_chunks(struct svcxprt_rdma *xprt,
 	 */
 	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;
 
-	/* Use FRMR if supported */
-	if (xprt->sc_dev_caps & SVCRDMA_DEVCAP_FAST_REG)
-		reader = rdma_read_chunk_frmr;
-	else
-		reader = rdma_read_chunk_lcl;
+	ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
+	position = be32_to_cpu(ch->rc_position);
+
+	/* RDMA_NOMSG: RDMA READ data should land just after RDMA RECV data */
+	if (position == 0) {
+		head->arg.pages = &head->pages[0];
+		page_offset = head->byte_len;
+	} else {
+		head->arg.pages = &head->pages[head->count];
+		page_offset = 0;
+	}
 
-	page_no = 0; page_offset = 0;
-	for (ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
-	     ch->rc_discrim != 0; ch++) {
+	ret = 0;
+	page_no = 0;
+	for (; ch->rc_discrim != xdr_zero; ch++) {
+		if (be32_to_cpu(ch->rc_position) != position)
+			goto err;
 
+		handle = be32_to_cpu(ch->rc_target.rs_handle),
+		byte_count = be32_to_cpu(ch->rc_target.rs_length);
 		xdr_decode_hyper((__be32 *)&ch->rc_target.rs_offset,
 				 &rs_offset);
-		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 */
-				     );
+			last = (ch + 1)->rc_discrim == xdr_zero;
+			ret = xprt->sc_reader(xprt, rqstp, head,
+					      &page_no, &page_offset,
+					      handle, byte_count,
+					      rs_offset, last);
 			if (ret < 0)
 				goto err;
 			byte_count -= ret;
@@ -426,7 +482,24 @@ static int rdma_read_chunks(struct svcxprt_rdma *xprt,
 			head->arg.buflen += ret;
 		}
 	}
+
+	/* Read list may need XDR round-up (see RFC 5666, s. 3.7) */
+	if (page_offset & 3) {
+		u32 pad = 4 - (page_offset & 3);
+
+		head->arg.page_len += pad;
+		head->arg.len += pad;
+		head->arg.buflen += pad;
+		page_offset += pad;
+	}
+
 	ret = 1;
+	if (position && position < head->arg.head[0].iov_len)
+		ret = rdma_copy_tail(rqstp, head, position,
+				     byte_count, page_offset, page_no);
+	head->arg.head[0].iov_len = position;
+	head->position = position;
+
  err:
 	/* Detach arg pages. svc_recv will replenish them */
 	for (page_no = 0;
@@ -436,47 +509,33 @@ static int rdma_read_chunks(struct svcxprt_rdma *xprt,
 	return ret;
 }
 
-/*
- * To avoid a separate RDMA READ just for a handful of zero bytes,
- * RFC 5666 section 3.7 allows the client to omit the XDR zero pad
- * in chunk lists.
- */
-static void
-rdma_fix_xdr_pad(struct xdr_buf *buf)
-{
-	unsigned int page_len = buf->page_len;
-	unsigned int size = (XDR_QUADLEN(page_len) << 2) - page_len;
-	unsigned int offset, pg_no;
-	char *p;
-
-	if (size == 0)
-		return;
-
-	pg_no = page_len >> PAGE_SHIFT;
-	offset = page_len & ~PAGE_MASK;
-	p = page_address(buf->pages[pg_no]);
-	memset(p + offset, 0, size);
-
-	buf->page_len += size;
-	buf->buflen += size;
-	buf->len += size;
-}
-
 static int rdma_read_complete(struct svc_rqst *rqstp,
 			      struct svc_rdma_op_ctxt *head)
 {
 	int page_no;
 	int ret;
 
-	BUG_ON(!head);
-
 	/* Copy RPC pages */
 	for (page_no = 0; page_no < head->count; page_no++) {
 		put_page(rqstp->rq_pages[page_no]);
 		rqstp->rq_pages[page_no] = head->pages[page_no];
 	}
+
+	/* Adjustments made for RDMA_NOMSG type requests */
+	if (head->position == 0) {
+		if (head->arg.len <= head->sge[0].length) {
+			head->arg.head[0].iov_len = head->arg.len -
+							head->byte_len;
+			head->arg.page_len = 0;
+		} else {
+			head->arg.head[0].iov_len = head->sge[0].length -
+								head->byte_len;
+			head->arg.page_len = head->arg.len -
+						head->sge[0].length;
+		}
+	}
+
 	/* Point rq_arg.pages past header */
-	rdma_fix_xdr_pad(&head->arg);
 	rqstp->rq_arg.pages = &rqstp->rq_pages[head->hdr_count];
 	rqstp->rq_arg.page_len = head->arg.page_len;
 	rqstp->rq_arg.page_base = head->arg.page_base;
@@ -501,8 +560,8 @@ static int rdma_read_complete(struct svc_rqst *rqstp,
 	ret = rqstp->rq_arg.head[0].iov_len
 		+ rqstp->rq_arg.page_len
 		+ rqstp->rq_arg.tail[0].iov_len;
-	dprintk("svcrdma: deferred read ret=%d, rq_arg.len =%d, "
-		"rq_arg.head[0].iov_base=%p, rq_arg.head[0].iov_len = %zd\n",
+	dprintk("svcrdma: deferred read ret=%d, rq_arg.len=%u, "
+		"rq_arg.head[0].iov_base=%p, rq_arg.head[0].iov_len=%zu\n",
 		ret, rqstp->rq_arg.len,	rqstp->rq_arg.head[0].iov_base,
 		rqstp->rq_arg.head[0].iov_len);
 
@@ -558,7 +617,6 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 	}
 	dprintk("svcrdma: processing ctxt=%p on xprt=%p, rqstp=%p, status=%d\n",
 		ctxt, rdma_xprt, rqstp, ctxt->wc_status);
-	BUG_ON(ctxt->wc_status != IB_WC_SUCCESS);
 	atomic_inc(&rdma_stat_recv);
 
 	/* Build up the XDR from the receive buffers. */
@@ -591,8 +649,8 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 		+ rqstp->rq_arg.tail[0].iov_len;
 	svc_rdma_put_context(ctxt, 0);
  out:
-	dprintk("svcrdma: ret = %d, rq_arg.len =%d, "
-		"rq_arg.head[0].iov_base=%p, rq_arg.head[0].iov_len = %zd\n",
+	dprintk("svcrdma: ret=%d, rq_arg.len=%u, "
+		"rq_arg.head[0].iov_base=%p, rq_arg.head[0].iov_len=%zd\n",
 		ret, rqstp->rq_arg.len,
 		rqstp->rq_arg.head[0].iov_base,
 		rqstp->rq_arg.head[0].iov_len);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 9f1b50689c0f..7de33d1af9b6 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -60,8 +60,11 @@ static int map_xdr(struct svcxprt_rdma *xprt,
 	u32 page_off;
 	int page_no;
 
-	BUG_ON(xdr->len !=
-	       (xdr->head[0].iov_len + xdr->page_len + xdr->tail[0].iov_len));
+	if (xdr->len !=
+	    (xdr->head[0].iov_len + xdr->page_len + xdr->tail[0].iov_len)) {
+		pr_err("svcrdma: map_xdr: XDR buffer length error\n");
+		return -EIO;
+	}
 
 	/* Skip the first sge, this is for the RPCRDMA header */
 	sge_no = 1;
@@ -150,7 +153,11 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp,
 	int bc;
 	struct svc_rdma_op_ctxt *ctxt;
 
-	BUG_ON(vec->count > RPCSVC_MAXPAGES);
+	if (vec->count > RPCSVC_MAXPAGES) {
+		pr_err("svcrdma: Too many pages (%lu)\n", vec->count);
+		return -EIO;
+	}
+
 	dprintk("svcrdma: RDMA_WRITE rmr=%x, to=%llx, xdr_off=%d, "
 		"write_len=%d, vec->sge=%p, vec->count=%lu\n",
 		rmr, (unsigned long long)to, xdr_off,
@@ -190,7 +197,10 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp,
 		sge_off = 0;
 		sge_no++;
 		xdr_sge_no++;
-		BUG_ON(xdr_sge_no > vec->count);
+		if (xdr_sge_no > vec->count) {
+			pr_err("svcrdma: Too many sges (%d)\n", xdr_sge_no);
+			goto err;
+		}
 		bc -= sge_bytes;
 		if (sge_no == xprt->sc_max_sge)
 			break;
@@ -421,7 +431,10 @@ static int send_reply(struct svcxprt_rdma *rdma,
 		ctxt->sge[sge_no].lkey = rdma->sc_dma_lkey;
 		ctxt->sge[sge_no].length = sge_bytes;
 	}
-	BUG_ON(byte_count != 0);
+	if (byte_count != 0) {
+		pr_err("svcrdma: Could not map %d bytes\n", byte_count);
+		goto err;
+	}
 
 	/* Save all respages in the ctxt and remove them from the
 	 * respages array. They are our pages until the I/O
@@ -442,7 +455,10 @@ static int send_reply(struct svcxprt_rdma *rdma,
 	}
 	rqstp->rq_next_page = rqstp->rq_respages + 1;
 
-	BUG_ON(sge_no > rdma->sc_max_sge);
+	if (sge_no > rdma->sc_max_sge) {
+		pr_err("svcrdma: Too many sges (%d)\n", sge_no);
+		goto err;
+	}
 	memset(&send_wr, 0, sizeof send_wr);
 	ctxt->wr_op = IB_WR_SEND;
 	send_wr.wr_id = (unsigned long)ctxt;
@@ -467,18 +483,6 @@ void svc_rdma_prep_reply_hdr(struct svc_rqst *rqstp)
 {
 }
 
-/*
- * Return the start of an xdr buffer.
- */
-static void *xdr_start(struct xdr_buf *xdr)
-{
-	return xdr->head[0].iov_base -
-		(xdr->len -
-		 xdr->page_len -
-		 xdr->tail[0].iov_len -
-		 xdr->head[0].iov_len);
-}
-
 int svc_rdma_sendto(struct svc_rqst *rqstp)
 {
 	struct svc_xprt *xprt = rqstp->rq_xprt;
@@ -496,8 +500,10 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
 
 	dprintk("svcrdma: sending response for rqstp=%p\n", rqstp);
 
-	/* Get the RDMA request header. */
-	rdma_argp = xdr_start(&rqstp->rq_arg);
+	/* Get the RDMA request header. The receive logic always
+	 * places this at the start of page 0.
+	 */
+	rdma_argp = page_address(rqstp->rq_pages[0]);
 
 	/* Build an req vec for the XDR */
 	ctxt = svc_rdma_get_context(rdma);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 4e618808bc98..f609c1c2d38d 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -139,7 +139,6 @@ void svc_rdma_put_context(struct svc_rdma_op_ctxt *ctxt, int free_pages)
 	struct svcxprt_rdma *xprt;
 	int i;
 
-	BUG_ON(!ctxt);
 	xprt = ctxt->xprt;
 	if (free_pages)
 		for (i = 0; i < ctxt->count; i++)
@@ -339,12 +338,14 @@ static void process_context(struct svcxprt_rdma *xprt,
 
 	switch (ctxt->wr_op) {
 	case IB_WR_SEND:
-		BUG_ON(ctxt->frmr);
+		if (ctxt->frmr)
+			pr_err("svcrdma: SEND: ctxt->frmr != NULL\n");
 		svc_rdma_put_context(ctxt, 1);
 		break;
 
 	case IB_WR_RDMA_WRITE:
-		BUG_ON(ctxt->frmr);
+		if (ctxt->frmr)
+			pr_err("svcrdma: WRITE: ctxt->frmr != NULL\n");
 		svc_rdma_put_context(ctxt, 0);
 		break;
 
@@ -353,19 +354,21 @@ static void process_context(struct svcxprt_rdma *xprt,
 		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);
-			spin_lock_bh(&xprt->sc_rq_dto_lock);
-			set_bit(XPT_DATA, &xprt->sc_xprt.xpt_flags);
-			list_add_tail(&read_hdr->dto_q,
-				      &xprt->sc_read_complete_q);
-			spin_unlock_bh(&xprt->sc_rq_dto_lock);
+			if (read_hdr) {
+				spin_lock_bh(&xprt->sc_rq_dto_lock);
+				set_bit(XPT_DATA, &xprt->sc_xprt.xpt_flags);
+				list_add_tail(&read_hdr->dto_q,
+					      &xprt->sc_read_complete_q);
+				spin_unlock_bh(&xprt->sc_rq_dto_lock);
+			} else {
+				pr_err("svcrdma: ctxt->read_hdr == NULL\n");
+			}
 			svc_xprt_enqueue(&xprt->sc_xprt);
 		}
 		svc_rdma_put_context(ctxt, 0);
 		break;
 
 	default:
-		BUG_ON(1);
 		printk(KERN_ERR "svcrdma: unexpected completion type, "
 		       "opcode=%d\n",
 		       ctxt->wr_op);
@@ -513,7 +516,10 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt)
 	buflen = 0;
 	ctxt->direction = DMA_FROM_DEVICE;
 	for (sge_no = 0; buflen < xprt->sc_max_req_size; sge_no++) {
-		BUG_ON(sge_no >= xprt->sc_max_sge);
+		if (sge_no >= xprt->sc_max_sge) {
+			pr_err("svcrdma: Too many sges (%d)\n", sge_no);
+			goto err_put_ctxt;
+		}
 		page = svc_rdma_get_page();
 		ctxt->pages[sge_no] = page;
 		pa = ib_dma_map_page(xprt->sc_cm_id->device,
@@ -687,7 +693,6 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv,
 {
 	struct rdma_cm_id *listen_id;
 	struct svcxprt_rdma *cma_xprt;
-	struct svc_xprt *xprt;
 	int ret;
 
 	dprintk("svcrdma: Creating RDMA socket\n");
@@ -698,7 +703,6 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv,
 	cma_xprt = rdma_create_xprt(serv, 1);
 	if (!cma_xprt)
 		return ERR_PTR(-ENOMEM);
-	xprt = &cma_xprt->sc_xprt;
 
 	listen_id = rdma_create_id(rdma_listen_handler, cma_xprt, RDMA_PS_TCP,
 				   IB_QPT_RC);
@@ -822,7 +826,7 @@ void svc_rdma_put_frmr(struct svcxprt_rdma *rdma,
 	if (frmr) {
 		frmr_unmap_dma(rdma, frmr);
 		spin_lock_bh(&rdma->sc_frmr_q_lock);
-		BUG_ON(!list_empty(&frmr->frmr_list));
+		WARN_ON_ONCE(!list_empty(&frmr->frmr_list));
 		list_add(&frmr->frmr_list, &rdma->sc_frmr_q);
 		spin_unlock_bh(&rdma->sc_frmr_q_lock);
 	}
@@ -970,10 +974,12 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 	 * NB:	iWARP requires remote write access for the data sink
 	 *	of an RDMA_READ. IB does not.
 	 */
+	newxprt->sc_reader = rdma_read_chunk_lcl;
 	if (devattr.device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS) {
 		newxprt->sc_frmr_pg_list_len =
 			devattr.max_fast_reg_page_list_len;
 		newxprt->sc_dev_caps |= SVCRDMA_DEVCAP_FAST_REG;
+		newxprt->sc_reader = rdma_read_chunk_frmr;
 	}
 
 	/*
@@ -1125,7 +1131,9 @@ static void __svc_rdma_free(struct work_struct *work)
 	dprintk("svcrdma: svc_rdma_free(%p)\n", rdma);
 
 	/* We should only be called from kref_put */
-	BUG_ON(atomic_read(&rdma->sc_xprt.xpt_ref.refcount) != 0);
+	if (atomic_read(&rdma->sc_xprt.xpt_ref.refcount) != 0)
+		pr_err("svcrdma: sc_xprt still in use? (%d)\n",
+		       atomic_read(&rdma->sc_xprt.xpt_ref.refcount));
 
 	/*
 	 * Destroy queued, but not processed read completions. Note
@@ -1153,8 +1161,12 @@ static void __svc_rdma_free(struct work_struct *work)
 	}
 
 	/* Warn if we leaked a resource or under-referenced */
-	WARN_ON(atomic_read(&rdma->sc_ctxt_used) != 0);
-	WARN_ON(atomic_read(&rdma->sc_dma_used) != 0);
+	if (atomic_read(&rdma->sc_ctxt_used) != 0)
+		pr_err("svcrdma: ctxt still in use? (%d)\n",
+		       atomic_read(&rdma->sc_ctxt_used));
+	if (atomic_read(&rdma->sc_dma_used) != 0)
+		pr_err("svcrdma: dma still in use? (%d)\n",
+		       atomic_read(&rdma->sc_dma_used));
 
 	/* De-allocate fastreg mr */
 	rdma_dealloc_frmr_q(rdma);
@@ -1254,7 +1266,6 @@ int svc_rdma_send(struct svcxprt_rdma *xprt, struct ib_send_wr *wr)
 	if (test_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags))
 		return -ENOTCONN;
 
-	BUG_ON(wr->send_flags != IB_SEND_SIGNALED);
 	wr_count = 1;
 	for (n_wr = wr->next; n_wr; n_wr = n_wr->next)
 		wr_count++;
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 6a4615dd0261..54f23b1be986 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -55,7 +55,7 @@
 
 #include "xprt_rdma.h"
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_TRANS
 #endif
 
@@ -73,9 +73,9 @@ static unsigned int xprt_rdma_max_inline_read = RPCRDMA_DEF_INLINE;
 static unsigned int xprt_rdma_max_inline_write = RPCRDMA_DEF_INLINE;
 static unsigned int xprt_rdma_inline_write_padding;
 static unsigned int xprt_rdma_memreg_strategy = RPCRDMA_FRMR;
-                int xprt_rdma_pad_optimize = 0;
+		int xprt_rdma_pad_optimize = 1;
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 
 static unsigned int min_slot_table_size = RPCRDMA_MIN_SLOT_TABLE;
 static unsigned int max_slot_table_size = RPCRDMA_MAX_SLOT_TABLE;
@@ -157,12 +157,47 @@ static struct ctl_table sunrpc_table[] = {
 static struct rpc_xprt_ops xprt_rdma_procs;	/* forward reference */
 
 static void
+xprt_rdma_format_addresses4(struct rpc_xprt *xprt, struct sockaddr *sap)
+{
+	struct sockaddr_in *sin = (struct sockaddr_in *)sap;
+	char buf[20];
+
+	snprintf(buf, sizeof(buf), "%08x", ntohl(sin->sin_addr.s_addr));
+	xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL);
+
+	xprt->address_strings[RPC_DISPLAY_NETID] = RPCBIND_NETID_RDMA;
+}
+
+static void
+xprt_rdma_format_addresses6(struct rpc_xprt *xprt, struct sockaddr *sap)
+{
+	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;
+	char buf[40];
+
+	snprintf(buf, sizeof(buf), "%pi6", &sin6->sin6_addr);
+	xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL);
+
+	xprt->address_strings[RPC_DISPLAY_NETID] = RPCBIND_NETID_RDMA6;
+}
+
+static void
 xprt_rdma_format_addresses(struct rpc_xprt *xprt)
 {
 	struct sockaddr *sap = (struct sockaddr *)
 					&rpcx_to_rdmad(xprt).addr;
-	struct sockaddr_in *sin = (struct sockaddr_in *)sap;
-	char buf[64];
+	char buf[128];
+
+	switch (sap->sa_family) {
+	case AF_INET:
+		xprt_rdma_format_addresses4(xprt, sap);
+		break;
+	case AF_INET6:
+		xprt_rdma_format_addresses6(xprt, sap);
+		break;
+	default:
+		pr_err("rpcrdma: Unrecognized address family\n");
+		return;
+	}
 
 	(void)rpc_ntop(sap, buf, sizeof(buf));
 	xprt->address_strings[RPC_DISPLAY_ADDR] = kstrdup(buf, GFP_KERNEL);
@@ -170,16 +205,10 @@ xprt_rdma_format_addresses(struct rpc_xprt *xprt)
 	snprintf(buf, sizeof(buf), "%u", rpc_get_port(sap));
 	xprt->address_strings[RPC_DISPLAY_PORT] = kstrdup(buf, GFP_KERNEL);
 
-	xprt->address_strings[RPC_DISPLAY_PROTO] = "rdma";
-
-	snprintf(buf, sizeof(buf), "%08x", ntohl(sin->sin_addr.s_addr));
-	xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL);
-
 	snprintf(buf, sizeof(buf), "%4hx", rpc_get_port(sap));
 	xprt->address_strings[RPC_DISPLAY_HEX_PORT] = kstrdup(buf, GFP_KERNEL);
 
-	/* netid */
-	xprt->address_strings[RPC_DISPLAY_NETID] = "rdma";
+	xprt->address_strings[RPC_DISPLAY_PROTO] = "rdma";
 }
 
 static void
@@ -200,9 +229,9 @@ xprt_rdma_free_addresses(struct rpc_xprt *xprt)
 static void
 xprt_rdma_connect_worker(struct work_struct *work)
 {
-	struct rpcrdma_xprt *r_xprt =
-		container_of(work, struct rpcrdma_xprt, rdma_connect.work);
-	struct rpc_xprt *xprt = &r_xprt->xprt;
+	struct rpcrdma_xprt *r_xprt = container_of(work, struct rpcrdma_xprt,
+						   rx_connect_worker.work);
+	struct rpc_xprt *xprt = &r_xprt->rx_xprt;
 	int rc = 0;
 
 	xprt_clear_connected(xprt);
@@ -235,7 +264,7 @@ xprt_rdma_destroy(struct rpc_xprt *xprt)
 
 	dprintk("RPC:       %s: called\n", __func__);
 
-	cancel_delayed_work_sync(&r_xprt->rdma_connect);
+	cancel_delayed_work_sync(&r_xprt->rx_connect_worker);
 
 	xprt_clear_connected(xprt);
 
@@ -364,8 +393,7 @@ xprt_setup_rdma(struct xprt_create *args)
 	 * any inline data. Also specify any padding which will be provided
 	 * from a preregistered zero buffer.
 	 */
-	rc = rpcrdma_buffer_create(&new_xprt->rx_buf, new_ep, &new_xprt->rx_ia,
-				&new_xprt->rx_data);
+	rc = rpcrdma_buffer_create(new_xprt);
 	if (rc)
 		goto out3;
 
@@ -374,12 +402,14 @@ xprt_setup_rdma(struct xprt_create *args)
 	 * connection loss notification is async. We also catch connection loss
 	 * when reaping receives.
 	 */
-	INIT_DELAYED_WORK(&new_xprt->rdma_connect, xprt_rdma_connect_worker);
-	new_ep->rep_func = rpcrdma_conn_func;
-	new_ep->rep_xprt = xprt;
+	INIT_DELAYED_WORK(&new_xprt->rx_connect_worker,
+			  xprt_rdma_connect_worker);
 
 	xprt_rdma_format_addresses(xprt);
-	xprt->max_payload = rpcrdma_max_payload(new_xprt);
+	xprt->max_payload = new_xprt->rx_ia.ri_ops->ro_maxpages(new_xprt);
+	if (xprt->max_payload == 0)
+		goto out4;
+	xprt->max_payload <<= PAGE_SHIFT;
 	dprintk("RPC:       %s: transport data payload maximum: %zu bytes\n",
 		__func__, xprt->max_payload);
 
@@ -434,94 +464,101 @@ xprt_rdma_connect(struct rpc_xprt *xprt, struct rpc_task *task)
 
 	if (r_xprt->rx_ep.rep_connected != 0) {
 		/* Reconnect */
-		schedule_delayed_work(&r_xprt->rdma_connect,
-			xprt->reestablish_timeout);
+		schedule_delayed_work(&r_xprt->rx_connect_worker,
+				      xprt->reestablish_timeout);
 		xprt->reestablish_timeout <<= 1;
 		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);
+		schedule_delayed_work(&r_xprt->rx_connect_worker, 0);
 		if (!RPC_IS_ASYNC(task))
-			flush_delayed_work(&r_xprt->rdma_connect);
+			flush_delayed_work(&r_xprt->rx_connect_worker);
 	}
 }
 
 /*
  * 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
- * sequence. For this reason, the recv buffers are attached to send
- * buffers for portions of the RPC. Note that the RPC layer allocates
- * both send and receive buffers in the same call. We may register
- * the receive buffer portion when using reply chunks.
+ * sequence.
+ *
+ * The RPC layer allocates both send and receive buffers in the same call
+ * (rq_send_buf and rq_rcv_buf are both part of a single contiguous buffer).
+ * We may register rq_rcv_buf when using reply chunks.
  */
 static void *
 xprt_rdma_allocate(struct rpc_task *task, size_t size)
 {
 	struct rpc_xprt *xprt = task->tk_rqstp->rq_xprt;
-	struct rpcrdma_req *req, *nreq;
+	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
+	struct rpcrdma_regbuf *rb;
+	struct rpcrdma_req *req;
+	size_t min_size;
+	gfp_t flags;
 
-	req = rpcrdma_buffer_get(&rpcx_to_rdmax(xprt)->rx_buf);
+	req = rpcrdma_buffer_get(&r_xprt->rx_buf);
 	if (req == NULL)
 		return NULL;
 
-	if (size > req->rl_size) {
-		dprintk("RPC:       %s: size %zd too large for buffer[%zd]: "
-			"prog %d vers %d proc %d\n",
-			__func__, size, req->rl_size,
-			task->tk_client->cl_prog, task->tk_client->cl_vers,
-			task->tk_msg.rpc_proc->p_proc);
-		/*
-		 * Outgoing length shortage. Our inline write max must have
-		 * been configured to perform direct i/o.
-		 *
-		 * This is therefore a large metadata operation, and the
-		 * allocate call was made on the maximum possible message,
-		 * e.g. containing long filename(s) or symlink data. In
-		 * fact, while these metadata operations *might* carry
-		 * large outgoing payloads, they rarely *do*. However, we
-		 * have to commit to the request here, so reallocate and
-		 * register it now. The data path will never require this
-		 * reallocation.
-		 *
-		 * If the allocation or registration fails, the RPC framework
-		 * will (doggedly) retry.
-		 */
-		if (task->tk_flags & RPC_TASK_SWAPPER)
-			nreq = kmalloc(sizeof *req + size, GFP_ATOMIC);
-		else
-			nreq = kmalloc(sizeof *req + size, GFP_NOFS);
-		if (nreq == NULL)
-			goto outfail;
-
-		if (rpcrdma_register_internal(&rpcx_to_rdmax(xprt)->rx_ia,
-				nreq->rl_base, size + sizeof(struct rpcrdma_req)
-				- offsetof(struct rpcrdma_req, rl_base),
-				&nreq->rl_handle, &nreq->rl_iov)) {
-			kfree(nreq);
-			goto outfail;
-		}
-		rpcx_to_rdmax(xprt)->rx_stats.hardway_register_count += size;
-		nreq->rl_size = size;
-		nreq->rl_niovs = 0;
-		nreq->rl_nchunks = 0;
-		nreq->rl_buffer = (struct rpcrdma_buffer *)req;
-		nreq->rl_reply = req->rl_reply;
-		memcpy(nreq->rl_segments,
-			req->rl_segments, sizeof nreq->rl_segments);
-		/* flag the swap with an unused field */
-		nreq->rl_iov.length = 0;
-		req->rl_reply = NULL;
-		req = nreq;
-	}
+	flags = GFP_NOIO | __GFP_NOWARN;
+	if (RPC_IS_SWAPPER(task))
+		flags = __GFP_MEMALLOC | GFP_NOWAIT | __GFP_NOWARN;
+
+	if (req->rl_rdmabuf == NULL)
+		goto out_rdmabuf;
+	if (req->rl_sendbuf == NULL)
+		goto out_sendbuf;
+	if (size > req->rl_sendbuf->rg_size)
+		goto out_sendbuf;
+
+out:
 	dprintk("RPC:       %s: size %zd, request 0x%p\n", __func__, size, req);
 	req->rl_connect_cookie = 0;	/* our reserved value */
-	return req->rl_xdr_buf;
-
-outfail:
+	return req->rl_sendbuf->rg_base;
+
+out_rdmabuf:
+	min_size = RPCRDMA_INLINE_WRITE_THRESHOLD(task->tk_rqstp);
+	rb = rpcrdma_alloc_regbuf(&r_xprt->rx_ia, min_size, flags);
+	if (IS_ERR(rb))
+		goto out_fail;
+	req->rl_rdmabuf = rb;
+
+out_sendbuf:
+	/* XDR encoding and RPC/RDMA marshaling of this request has not
+	 * yet occurred. Thus a lower bound is needed to prevent buffer
+	 * overrun during marshaling.
+	 *
+	 * RPC/RDMA marshaling may choose to send payload bearing ops
+	 * inline, if the result is smaller than the inline threshold.
+	 * The value of the "size" argument accounts for header
+	 * requirements but not for the payload in these cases.
+	 *
+	 * Likewise, allocate enough space to receive a reply up to the
+	 * size of the inline threshold.
+	 *
+	 * It's unlikely that both the send header and the received
+	 * reply will be large, but slush is provided here to allow
+	 * flexibility when marshaling.
+	 */
+	min_size = RPCRDMA_INLINE_READ_THRESHOLD(task->tk_rqstp);
+	min_size += RPCRDMA_INLINE_WRITE_THRESHOLD(task->tk_rqstp);
+	if (size < min_size)
+		size = min_size;
+
+	rb = rpcrdma_alloc_regbuf(&r_xprt->rx_ia, size, flags);
+	if (IS_ERR(rb))
+		goto out_fail;
+	rb->rg_owner = req;
+
+	r_xprt->rx_stats.hardway_register_count += size;
+	rpcrdma_free_regbuf(&r_xprt->rx_ia, req->rl_sendbuf);
+	req->rl_sendbuf = rb;
+	goto out;
+
+out_fail:
 	rpcrdma_buffer_put(req);
-	rpcx_to_rdmax(xprt)->rx_stats.failed_marshal_count++;
+	r_xprt->rx_stats.failed_marshal_count++;
 	return NULL;
 }
 
@@ -533,47 +570,24 @@ xprt_rdma_free(void *buffer)
 {
 	struct rpcrdma_req *req;
 	struct rpcrdma_xprt *r_xprt;
-	struct rpcrdma_rep *rep;
+	struct rpcrdma_regbuf *rb;
 	int i;
 
 	if (buffer == NULL)
 		return;
 
-	req = container_of(buffer, struct rpcrdma_req, rl_xdr_buf[0]);
-	if (req->rl_iov.length == 0) {	/* see allocate above */
-		r_xprt = container_of(((struct rpcrdma_req *) req->rl_buffer)->rl_buffer,
-				      struct rpcrdma_xprt, rx_buf);
-	} else
-		r_xprt = container_of(req->rl_buffer, struct rpcrdma_xprt, rx_buf);
-	rep = req->rl_reply;
+	rb = container_of(buffer, struct rpcrdma_regbuf, rg_base[0]);
+	req = rb->rg_owner;
+	r_xprt = container_of(req->rl_buffer, struct rpcrdma_xprt, rx_buf);
 
-	dprintk("RPC:       %s: called on 0x%p%s\n",
-		__func__, rep, (rep && rep->rr_func) ? " (with waiter)" : "");
+	dprintk("RPC:       %s: called on 0x%p\n", __func__, req->rl_reply);
 
-	/*
-	 * 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
-	 * interrupted, our framework will clean up.
-	 */
 	for (i = 0; req->rl_nchunks;) {
 		--req->rl_nchunks;
-		i += rpcrdma_deregister_external(
-			&req->rl_segments[i], r_xprt);
-	}
-
-	if (req->rl_iov.length == 0) {	/* see allocate above */
-		struct rpcrdma_req *oreq = (struct rpcrdma_req *)req->rl_buffer;
-		oreq->rl_reply = req->rl_reply;
-		(void) rpcrdma_deregister_internal(&r_xprt->rx_ia,
-						   req->rl_handle,
-						   &req->rl_iov);
-		kfree(req);
-		req = oreq;
+		i += r_xprt->rx_ia.ri_ops->ro_unmap(r_xprt,
+						    &req->rl_segments[i]);
 	}
 
-	/* Put back request+reply buffers */
 	rpcrdma_buffer_put(req);
 }
 
@@ -597,10 +611,7 @@ xprt_rdma_send_request(struct rpc_task *task)
 	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
 	int rc = 0;
 
-	if (req->rl_niovs == 0)
-		rc = rpcrdma_marshal_req(rqst);
-	else if (r_xprt->rx_ia.ri_memreg_strategy == RPCRDMA_FRMR)
-		rc = rpcrdma_marshal_chunks(rqst, 0);
+	rc = rpcrdma_marshal_req(rqst);
 	if (rc < 0)
 		goto failed_marshal;
 
@@ -705,7 +716,7 @@ static void __exit xprt_rdma_cleanup(void)
 	int rc;
 
 	dprintk("RPCRDMA Module Removed, deregister RPC RDMA transport\n");
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	if (sunrpc_table_header) {
 		unregister_sysctl_table(sunrpc_table_header);
 		sunrpc_table_header = NULL;
@@ -736,7 +747,7 @@ static int __init xprt_rdma_init(void)
 	dprintk("\tPadding %d\n\tMemreg %d\n",
 		xprt_rdma_inline_write_padding, xprt_rdma_memreg_strategy);
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	if (!sunrpc_table_header)
 		sunrpc_table_header = register_sysctl_table(sunrpc_table);
 #endif
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 3b91aedf439e..4870d272e006 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -49,6 +49,8 @@
 
 #include <linux/interrupt.h>
 #include <linux/slab.h>
+#include <linux/prefetch.h>
+#include <linux/sunrpc/addr.h>
 #include <asm/bitops.h>
 
 #include "xprt_rdma.h"
@@ -57,12 +59,10 @@
  * Globals/Macros
  */
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_TRANS
 #endif
 
-static void rpcrdma_reset_frmrs(struct rpcrdma_ia *);
-
 /*
  * internal functions
  */
@@ -105,16 +105,54 @@ rpcrdma_run_tasklet(unsigned long data)
 
 static DECLARE_TASKLET(rpcrdma_tasklet_g, rpcrdma_run_tasklet, 0UL);
 
+static const char * const async_event[] = {
+	"CQ error",
+	"QP fatal error",
+	"QP request error",
+	"QP access error",
+	"communication established",
+	"send queue drained",
+	"path migration successful",
+	"path mig error",
+	"device fatal error",
+	"port active",
+	"port error",
+	"LID change",
+	"P_key change",
+	"SM change",
+	"SRQ error",
+	"SRQ limit reached",
+	"last WQE reached",
+	"client reregister",
+	"GID change",
+};
+
+#define ASYNC_MSG(status)					\
+	((status) < ARRAY_SIZE(async_event) ?			\
+		async_event[(status)] : "unknown async error")
+
+static void
+rpcrdma_schedule_tasklet(struct list_head *sched_list)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&rpcrdma_tk_lock_g, flags);
+	list_splice_tail(sched_list, &rpcrdma_tasklets_g);
+	spin_unlock_irqrestore(&rpcrdma_tk_lock_g, flags);
+	tasklet_schedule(&rpcrdma_tasklet_g);
+}
+
 static void
 rpcrdma_qp_async_error_upcall(struct ib_event *event, void *context)
 {
 	struct rpcrdma_ep *ep = context;
 
-	dprintk("RPC:       %s: QP error %X on device %s ep %p\n",
-		__func__, event->event, event->device->name, context);
+	pr_err("RPC:       %s: %s on device %s ep %p\n",
+	       __func__, ASYNC_MSG(event->event),
+		event->device->name, context);
 	if (ep->rep_connected == 1) {
 		ep->rep_connected = -EIO;
-		ep->rep_func(ep);
+		rpcrdma_conn_func(ep);
 		wake_up_all(&ep->rep_connect_wait);
 	}
 }
@@ -124,27 +162,60 @@ rpcrdma_cq_async_error_upcall(struct ib_event *event, void *context)
 {
 	struct rpcrdma_ep *ep = context;
 
-	dprintk("RPC:       %s: CQ error %X on device %s ep %p\n",
-		__func__, event->event, event->device->name, context);
+	pr_err("RPC:       %s: %s on device %s ep %p\n",
+	       __func__, ASYNC_MSG(event->event),
+		event->device->name, context);
 	if (ep->rep_connected == 1) {
 		ep->rep_connected = -EIO;
-		ep->rep_func(ep);
+		rpcrdma_conn_func(ep);
 		wake_up_all(&ep->rep_connect_wait);
 	}
 }
 
+static const char * const wc_status[] = {
+	"success",
+	"local length error",
+	"local QP operation error",
+	"local EE context operation error",
+	"local protection error",
+	"WR flushed",
+	"memory management operation error",
+	"bad response error",
+	"local access error",
+	"remote invalid request error",
+	"remote access error",
+	"remote operation error",
+	"transport retry counter exceeded",
+	"RNR retry counter exceeded",
+	"local RDD violation error",
+	"remove invalid RD request",
+	"operation aborted",
+	"invalid EE context number",
+	"invalid EE context state",
+	"fatal error",
+	"response timeout error",
+	"general error",
+};
+
+#define COMPLETION_MSG(status)					\
+	((status) < ARRAY_SIZE(wc_status) ?			\
+		wc_status[(status)] : "unexpected completion error")
+
 static void
 rpcrdma_sendcq_process_wc(struct ib_wc *wc)
 {
-	struct rpcrdma_mw *frmr = (struct rpcrdma_mw *)(unsigned long)wc->wr_id;
-
-	dprintk("RPC:       %s: frmr %p status %X opcode %d\n",
-		__func__, frmr, wc->status, wc->opcode);
+	/* WARNING: Only wr_id and status are reliable at this point */
+	if (wc->wr_id == RPCRDMA_IGNORE_COMPLETION) {
+		if (wc->status != IB_WC_SUCCESS &&
+		    wc->status != IB_WC_WR_FLUSH_ERR)
+			pr_err("RPC:       %s: SEND: %s\n",
+			       __func__, COMPLETION_MSG(wc->status));
+	} else {
+		struct rpcrdma_mw *r;
 
-	if (wc->wr_id == 0ULL)
-		return;
-	if (wc->status != IB_WC_SUCCESS)
-		frmr->r.frmr.fr_state = FRMR_IS_STALE;
+		r = (struct rpcrdma_mw *)(unsigned long)wc->wr_id;
+		r->mw_sendcompletion(wc);
+	}
 }
 
 static int
@@ -208,33 +279,32 @@ rpcrdma_recvcq_process_wc(struct ib_wc *wc, struct list_head *sched_list)
 	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);
+	/* WARNING: Only wr_id and status are reliable at this point */
+	if (wc->status != IB_WC_SUCCESS)
+		goto out_fail;
 
-	if (wc->status != IB_WC_SUCCESS) {
-		rep->rr_len = ~0U;
-		goto out_schedule;
-	}
+	/* status == SUCCESS means all fields in wc are trustworthy */
 	if (wc->opcode != IB_WC_RECV)
 		return;
 
+	dprintk("RPC:       %s: rep %p opcode 'recv', length %u: success\n",
+		__func__, rep, wc->byte_len);
+
 	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);
-	}
+				   rdmab_addr(rep->rr_rdmabuf),
+				   rep->rr_len, DMA_FROM_DEVICE);
+	prefetch(rdmab_to_msg(rep->rr_rdmabuf));
 
 out_schedule:
 	list_add_tail(&rep->rr_list, sched_list);
+	return;
+out_fail:
+	if (wc->status != IB_WC_WR_FLUSH_ERR)
+		pr_err("RPC:       %s: rep %p: %s\n",
+		       __func__, rep, COMPLETION_MSG(wc->status));
+	rep->rr_len = ~0U;
+	goto out_schedule;
 }
 
 static int
@@ -243,7 +313,6 @@ rpcrdma_recvcq_poll(struct ib_cq *cq, struct rpcrdma_ep *ep)
 	struct list_head sched_list;
 	struct ib_wc *wcs;
 	int budget, count, rc;
-	unsigned long flags;
 
 	INIT_LIST_HEAD(&sched_list);
 	budget = RPCRDMA_WC_BUDGET / RPCRDMA_POLLSIZE;
@@ -261,10 +330,7 @@ rpcrdma_recvcq_poll(struct ib_cq *cq, struct rpcrdma_ep *ep)
 	rc = 0;
 
 out_schedule:
-	spin_lock_irqsave(&rpcrdma_tk_lock_g, flags);
-	list_splice_tail(&sched_list, &rpcrdma_tasklets_g);
-	spin_unlock_irqrestore(&rpcrdma_tk_lock_g, flags);
-	tasklet_schedule(&rpcrdma_tasklet_g);
+	rpcrdma_schedule_tasklet(&sched_list);
 	return rc;
 }
 
@@ -309,11 +375,18 @@ rpcrdma_recvcq_upcall(struct ib_cq *cq, void *cq_context)
 static void
 rpcrdma_flush_cqs(struct rpcrdma_ep *ep)
 {
-	rpcrdma_recvcq_upcall(ep->rep_attr.recv_cq, ep);
-	rpcrdma_sendcq_upcall(ep->rep_attr.send_cq, ep);
+	struct ib_wc wc;
+	LIST_HEAD(sched_list);
+
+	while (ib_poll_cq(ep->rep_attr.recv_cq, 1, &wc) > 0)
+		rpcrdma_recvcq_process_wc(&wc, &sched_list);
+	if (!list_empty(&sched_list))
+		rpcrdma_schedule_tasklet(&sched_list);
+	while (ib_poll_cq(ep->rep_attr.send_cq, 1, &wc) > 0)
+		rpcrdma_sendcq_process_wc(&wc);
 }
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 static const char * const conn[] = {
 	"address resolved",
 	"address error",
@@ -344,11 +417,11 @@ rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event)
 	struct rpcrdma_xprt *xprt = id->context;
 	struct rpcrdma_ia *ia = &xprt->rx_ia;
 	struct rpcrdma_ep *ep = &xprt->rx_ep;
-#ifdef RPC_DEBUG
-	struct sockaddr_in *addr = (struct sockaddr_in *) &ep->rep_remote_addr;
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
+	struct sockaddr *sap = (struct sockaddr *)&ep->rep_remote_addr;
 #endif
-	struct ib_qp_attr attr;
-	struct ib_qp_init_attr iattr;
+	struct ib_qp_attr *attr = &ia->ri_qp_attr;
+	struct ib_qp_init_attr *iattr = &ia->ri_qp_init_attr;
 	int connstate = 0;
 
 	switch (event->event) {
@@ -371,12 +444,13 @@ rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event)
 		break;
 	case RDMA_CM_EVENT_ESTABLISHED:
 		connstate = 1;
-		ib_query_qp(ia->ri_id->qp, &attr,
-			IB_QP_MAX_QP_RD_ATOMIC | IB_QP_MAX_DEST_RD_ATOMIC,
-			&iattr);
+		ib_query_qp(ia->ri_id->qp, attr,
+			    IB_QP_MAX_QP_RD_ATOMIC | IB_QP_MAX_DEST_RD_ATOMIC,
+			    iattr);
 		dprintk("RPC:       %s: %d responder resources"
 			" (%d initiator)\n",
-			__func__, attr.max_dest_rd_atomic, attr.max_rd_atomic);
+			__func__, attr->max_dest_rd_atomic,
+			attr->max_rd_atomic);
 		goto connected;
 	case RDMA_CM_EVENT_CONNECT_ERROR:
 		connstate = -ENOTCONN;
@@ -393,38 +467,33 @@ rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event)
 	case RDMA_CM_EVENT_DEVICE_REMOVAL:
 		connstate = -ENODEV;
 connected:
-		atomic_set(&rpcx_to_rdmax(ep->rep_xprt)->rx_buf.rb_credits, 1);
 		dprintk("RPC:       %s: %sconnected\n",
 					__func__, connstate > 0 ? "" : "dis");
 		ep->rep_connected = connstate;
-		ep->rep_func(ep);
+		rpcrdma_conn_func(ep);
 		wake_up_all(&ep->rep_connect_wait);
 		/*FALLTHROUGH*/
 	default:
-		dprintk("RPC:       %s: %pI4:%u (ep 0x%p): %s\n",
-			__func__, &addr->sin_addr.s_addr,
-			ntohs(addr->sin_port), ep,
+		dprintk("RPC:       %s: %pIS:%u (ep 0x%p): %s\n",
+			__func__, sap, rpc_get_port(sap), ep,
 			CONNECTION_MSG(event->event));
 		break;
 	}
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	if (connstate == 1) {
-		int ird = attr.max_dest_rd_atomic;
+		int ird = attr->max_dest_rd_atomic;
 		int tird = ep->rep_remote_cma.responder_resources;
-		printk(KERN_INFO "rpcrdma: connection to %pI4:%u "
-			"on %s, memreg %d slots %d ird %d%s\n",
-			&addr->sin_addr.s_addr,
-			ntohs(addr->sin_port),
+
+		pr_info("rpcrdma: connection to %pIS:%u on %s, memreg '%s', %d credits, %d responders%s\n",
+			sap, rpc_get_port(sap),
 			ia->ri_id->device->name,
-			ia->ri_memreg_strategy,
+			ia->ri_ops->ro_displayname,
 			xprt->rx_buf.rb_max_requests,
 			ird, ird < 4 && ird < tird / 2 ? " (low!)" : "");
 	} else if (connstate < 0) {
-		printk(KERN_INFO "rpcrdma: connection to %pI4:%u closed (%d)\n",
-			&addr->sin_addr.s_addr,
-			ntohs(addr->sin_port),
-			connstate);
+		pr_info("rpcrdma: connection to %pIS:%u closed (%d)\n",
+			sap, rpc_get_port(sap), connstate);
 	}
 #endif
 
@@ -511,8 +580,8 @@ int
 rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg)
 {
 	int rc, mem_priv;
-	struct ib_device_attr devattr;
 	struct rpcrdma_ia *ia = &xprt->rx_ia;
+	struct ib_device_attr *devattr = &ia->ri_devattr;
 
 	ia->ri_id = rpcrdma_create_id(xprt, ia, addr);
 	if (IS_ERR(ia->ri_id)) {
@@ -528,36 +597,27 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg)
 		goto out2;
 	}
 
-	/*
-	 * Query the device to determine if the requested memory
-	 * registration strategy is supported. If it isn't, set the
-	 * strategy to a globally supported model.
-	 */
-	rc = ib_query_device(ia->ri_id->device, &devattr);
+	rc = ib_query_device(ia->ri_id->device, devattr);
 	if (rc) {
 		dprintk("RPC:       %s: ib_query_device failed %d\n",
 			__func__, rc);
-		goto out2;
+		goto out3;
 	}
 
-	if (devattr.device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY) {
+	if (devattr->device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY) {
 		ia->ri_have_dma_lkey = 1;
 		ia->ri_dma_lkey = ia->ri_id->device->local_dma_lkey;
 	}
 
 	if (memreg == RPCRDMA_FRMR) {
 		/* Requires both frmr reg and local dma lkey */
-		if ((devattr.device_cap_flags &
+		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)) {
+		    (IB_DEVICE_MEM_MGT_EXTENSIONS|IB_DEVICE_LOCAL_DMA_LKEY)) ||
+		      (devattr->max_fast_reg_page_list_len == 0)) {
 			dprintk("RPC:       %s: FRMR registration "
 				"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) {
@@ -578,13 +638,16 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg)
 	 */
 	switch (memreg) {
 	case RPCRDMA_FRMR:
+		ia->ri_ops = &rpcrdma_frwr_memreg_ops;
 		break;
 	case RPCRDMA_ALLPHYSICAL:
+		ia->ri_ops = &rpcrdma_physical_memreg_ops;
 		mem_priv = IB_ACCESS_LOCAL_WRITE |
 				IB_ACCESS_REMOTE_WRITE |
 				IB_ACCESS_REMOTE_READ;
 		goto register_setup;
 	case RPCRDMA_MTHCAFMR:
+		ia->ri_ops = &rpcrdma_fmr_memreg_ops;
 		if (ia->ri_have_dma_lkey)
 			break;
 		mem_priv = IB_ACCESS_LOCAL_WRITE;
@@ -595,23 +658,27 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg)
 				"phys register failed with %lX\n",
 				__func__, PTR_ERR(ia->ri_bind_mem));
 			rc = -ENOMEM;
-			goto out2;
+			goto out3;
 		}
 		break;
 	default:
 		printk(KERN_ERR "RPC: Unsupported memory "
 				"registration mode: %d\n", memreg);
 		rc = -ENOMEM;
-		goto out2;
+		goto out3;
 	}
-	dprintk("RPC:       %s: memory registration strategy is %d\n",
-		__func__, memreg);
+	dprintk("RPC:       %s: memory registration strategy is '%s'\n",
+		__func__, ia->ri_ops->ro_displayname);
 
 	/* Else will do memory reg/dereg for each chunk */
 	ia->ri_memreg_strategy = memreg;
 
 	rwlock_init(&ia->ri_qplock);
 	return 0;
+
+out3:
+	ib_dealloc_pd(ia->ri_pd);
+	ia->ri_pd = NULL;
 out2:
 	rdma_destroy_id(ia->ri_id);
 	ia->ri_id = NULL;
@@ -655,66 +722,21 @@ int
 rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
 				struct rpcrdma_create_data_internal *cdata)
 {
-	struct ib_device_attr devattr;
+	struct ib_device_attr *devattr = &ia->ri_devattr;
 	struct ib_cq *sendcq, *recvcq;
 	int rc, err;
 
-	rc = ib_query_device(ia->ri_id->device, &devattr);
-	if (rc) {
-		dprintk("RPC:       %s: ib_query_device failed %d\n",
-			__func__, rc);
-		return rc;
-	}
-
 	/* check provider's send/recv wr limits */
-	if (cdata->max_requests > devattr.max_qp_wr)
-		cdata->max_requests = devattr.max_qp_wr;
+	if (cdata->max_requests > devattr->max_qp_wr)
+		cdata->max_requests = devattr->max_qp_wr;
 
 	ep->rep_attr.event_handler = rpcrdma_qp_async_error_upcall;
 	ep->rep_attr.qp_context = ep;
-	/* send_cq and recv_cq initialized below */
 	ep->rep_attr.srq = NULL;
 	ep->rep_attr.cap.max_send_wr = cdata->max_requests;
-	switch (ia->ri_memreg_strategy) {
-	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. 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
-		 */
-
-		/* 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 / depth;
-			if (!cdata->max_requests)
-				return -EINVAL;
-			ep->rep_attr.cap.max_send_wr = cdata->max_requests *
-						       depth;
-		}
-		break;
-	}
-	default:
-		break;
-	}
+	rc = ia->ri_ops->ro_open(ia, ep, cdata);
+	if (rc)
+		return rc;
 	ep->rep_attr.cap.max_recv_wr = cdata->max_requests;
 	ep->rep_attr.cap.max_send_sge = (cdata->padding ? 4 : 2);
 	ep->rep_attr.cap.max_recv_sge = 1;
@@ -723,6 +745,14 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
 	ep->rep_attr.qp_type = IB_QPT_RC;
 	ep->rep_attr.port_num = ~0;
 
+	if (cdata->padding) {
+		ep->rep_padbuf = rpcrdma_alloc_regbuf(ia, cdata->padding,
+						      GFP_KERNEL);
+		if (IS_ERR(ep->rep_padbuf))
+			return PTR_ERR(ep->rep_padbuf);
+	} else
+		ep->rep_padbuf = NULL;
+
 	dprintk("RPC:       %s: requested max: dtos: send %d recv %d; "
 		"iovs: send %d recv %d\n",
 		__func__,
@@ -733,10 +763,11 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
 
 	/* set trigger for requesting send completion */
 	ep->rep_cqinit = ep->rep_attr.cap.max_send_wr/2 - 1;
-	if (ep->rep_cqinit <= 2)
+	if (ep->rep_cqinit > RPCRDMA_MAX_UNSIGNALED_SENDS)
+		ep->rep_cqinit = RPCRDMA_MAX_UNSIGNALED_SENDS;
+	else 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);
 
@@ -786,10 +817,11 @@ 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 (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;
+		ep->rep_remote_cma.responder_resources =
+						devattr->max_qp_rd_atom;
 
 	ep->rep_remote_cma.retry_count = 7;
 	ep->rep_remote_cma.flow_control = 0;
@@ -803,6 +835,7 @@ out2:
 		dprintk("RPC:       %s: ib_destroy_cq returned %i\n",
 			__func__, err);
 out1:
+	rpcrdma_free_regbuf(ia, ep->rep_padbuf);
 	return rc;
 }
 
@@ -829,11 +862,7 @@ rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
 		ia->ri_id->qp = NULL;
 	}
 
-	/* padding - could be done in rpcrdma_buffer_destroy... */
-	if (ep->rep_pad_mr) {
-		rpcrdma_deregister_internal(ia, ep->rep_pad_mr, &ep->rep_pad);
-		ep->rep_pad_mr = NULL;
-	}
+	rpcrdma_free_regbuf(ia, ep->rep_padbuf);
 
 	rpcrdma_clean_cq(ep->rep_attr.recv_cq);
 	rc = ib_destroy_cq(ep->rep_attr.recv_cq);
@@ -866,10 +895,9 @@ retry:
 		rpcrdma_ep_disconnect(ep, ia);
 		rpcrdma_flush_cqs(ep);
 
-		if (ia->ri_memreg_strategy == RPCRDMA_FRMR)
-			rpcrdma_reset_frmrs(ia);
-
 		xprt = container_of(ia, struct rpcrdma_xprt, rx_ia);
+		ia->ri_ops->ro_reset(xprt);
+
 		id = rpcrdma_create_id(xprt, ia,
 				(struct sockaddr *)&xprt->rx_data.addr);
 		if (IS_ERR(id)) {
@@ -992,113 +1020,69 @@ rpcrdma_ep_disconnect(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
 	}
 }
 
-static int
-rpcrdma_init_fmrs(struct rpcrdma_ia *ia, struct rpcrdma_buffer *buf)
+static struct rpcrdma_req *
+rpcrdma_create_req(struct rpcrdma_xprt *r_xprt)
 {
-	int mr_access_flags = IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_READ;
-	struct ib_fmr_attr fmr_attr = {
-		.max_pages	= RPCRDMA_MAX_DATA_SEGS,
-		.max_maps	= 1,
-		.page_shift	= PAGE_SHIFT
-	};
-	struct rpcrdma_mw *r;
-	int i, rc;
-
-	i = (buf->rb_max_requests + 1) * RPCRDMA_MAX_SEGS;
-	dprintk("RPC:       %s: initializing %d FMRs\n", __func__, i);
-
-	while (i--) {
-		r = kzalloc(sizeof(*r), GFP_KERNEL);
-		if (r == NULL)
-			return -ENOMEM;
-
-		r->r.fmr = ib_alloc_fmr(ia->ri_pd, mr_access_flags, &fmr_attr);
-		if (IS_ERR(r->r.fmr)) {
-			rc = PTR_ERR(r->r.fmr);
-			dprintk("RPC:       %s: ib_alloc_fmr failed %i\n",
-				__func__, rc);
-			goto out_free;
-		}
+	struct rpcrdma_req *req;
 
-		list_add(&r->mw_list, &buf->rb_mws);
-		list_add(&r->mw_all, &buf->rb_all);
-	}
-	return 0;
+	req = kzalloc(sizeof(*req), GFP_KERNEL);
+	if (req == NULL)
+		return ERR_PTR(-ENOMEM);
 
-out_free:
-	kfree(r);
-	return rc;
+	req->rl_buffer = &r_xprt->rx_buf;
+	return req;
 }
 
-static int
-rpcrdma_init_frmrs(struct rpcrdma_ia *ia, struct rpcrdma_buffer *buf)
+static struct rpcrdma_rep *
+rpcrdma_create_rep(struct rpcrdma_xprt *r_xprt)
 {
-	struct rpcrdma_frmr *f;
-	struct rpcrdma_mw *r;
-	int i, rc;
-
-	i = (buf->rb_max_requests + 1) * RPCRDMA_MAX_SEGS;
-	dprintk("RPC:       %s: initializing %d FRMRs\n", __func__, i);
-
-	while (i--) {
-		r = kzalloc(sizeof(*r), GFP_KERNEL);
-		if (r == NULL)
-			return -ENOMEM;
-		f = &r->r.frmr;
-
-		f->fr_mr = ib_alloc_fast_reg_mr(ia->ri_pd,
-						ia->ri_max_frmr_depth);
-		if (IS_ERR(f->fr_mr)) {
-			rc = PTR_ERR(f->fr_mr);
-			dprintk("RPC:       %s: ib_alloc_fast_reg_mr "
-				"failed %i\n", __func__, rc);
-			goto out_free;
-		}
-
-		f->fr_pgl = ib_alloc_fast_reg_page_list(ia->ri_id->device,
-							ia->ri_max_frmr_depth);
-		if (IS_ERR(f->fr_pgl)) {
-			rc = PTR_ERR(f->fr_pgl);
-			dprintk("RPC:       %s: ib_alloc_fast_reg_page_list "
-				"failed %i\n", __func__, rc);
+	struct rpcrdma_create_data_internal *cdata = &r_xprt->rx_data;
+	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+	struct rpcrdma_rep *rep;
+	int rc;
 
-			ib_dereg_mr(f->fr_mr);
-			goto out_free;
-		}
+	rc = -ENOMEM;
+	rep = kzalloc(sizeof(*rep), GFP_KERNEL);
+	if (rep == NULL)
+		goto out;
 
-		list_add(&r->mw_list, &buf->rb_mws);
-		list_add(&r->mw_all, &buf->rb_all);
+	rep->rr_rdmabuf = rpcrdma_alloc_regbuf(ia, cdata->inline_rsize,
+					       GFP_KERNEL);
+	if (IS_ERR(rep->rr_rdmabuf)) {
+		rc = PTR_ERR(rep->rr_rdmabuf);
+		goto out_free;
 	}
 
-	return 0;
+	rep->rr_buffer = &r_xprt->rx_buf;
+	return rep;
 
 out_free:
-	kfree(r);
-	return rc;
+	kfree(rep);
+out:
+	return ERR_PTR(rc);
 }
 
 int
-rpcrdma_buffer_create(struct rpcrdma_buffer *buf, struct rpcrdma_ep *ep,
-	struct rpcrdma_ia *ia, struct rpcrdma_create_data_internal *cdata)
+rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt)
 {
+	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
+	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+	struct rpcrdma_create_data_internal *cdata = &r_xprt->rx_data;
 	char *p;
-	size_t len, rlen, wlen;
+	size_t len;
 	int i, rc;
 
 	buf->rb_max_requests = cdata->max_requests;
 	spin_lock_init(&buf->rb_lock);
-	atomic_set(&buf->rb_credits, 1);
 
 	/* Need to allocate:
 	 *   1.  arrays for send and recv pointers
 	 *   2.  arrays of struct rpcrdma_req to fill in pointers
 	 *   3.  array of struct rpcrdma_rep for replies
-	 *   4.  padding, if any
 	 * Send/recv buffers in req/rep need to be registered
 	 */
 	len = buf->rb_max_requests *
 		(sizeof(struct rpcrdma_req *) + sizeof(struct rpcrdma_rep *));
-	len += cdata->padding;
 
 	p = kzalloc(len, GFP_KERNEL);
 	if (p == NULL) {
@@ -1114,90 +1098,33 @@ rpcrdma_buffer_create(struct rpcrdma_buffer *buf, struct rpcrdma_ep *ep,
 	buf->rb_recv_bufs = (struct rpcrdma_rep **) p;
 	p = (char *) &buf->rb_recv_bufs[buf->rb_max_requests];
 
-	/*
-	 * Register the zeroed pad buffer, if any.
-	 */
-	if (cdata->padding) {
-		rc = rpcrdma_register_internal(ia, p, cdata->padding,
-					    &ep->rep_pad_mr, &ep->rep_pad);
-		if (rc)
-			goto out;
-	}
-	p += cdata->padding;
-
-	INIT_LIST_HEAD(&buf->rb_mws);
-	INIT_LIST_HEAD(&buf->rb_all);
-	switch (ia->ri_memreg_strategy) {
-	case RPCRDMA_FRMR:
-		rc = rpcrdma_init_frmrs(ia, buf);
-		if (rc)
-			goto out;
-		break;
-	case RPCRDMA_MTHCAFMR:
-		rc = rpcrdma_init_fmrs(ia, buf);
-		if (rc)
-			goto out;
-		break;
-	default:
-		break;
-	}
-
-	/*
-	 * 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);
+	rc = ia->ri_ops->ro_init(r_xprt);
+	if (rc)
+		goto out;
 
 	for (i = 0; i < buf->rb_max_requests; i++) {
 		struct rpcrdma_req *req;
 		struct rpcrdma_rep *rep;
 
-		req = kmalloc(wlen, GFP_KERNEL);
-		if (req == NULL) {
+		req = rpcrdma_create_req(r_xprt);
+		if (IS_ERR(req)) {
 			dprintk("RPC:       %s: request buffer %d alloc"
 				" failed\n", __func__, i);
-			rc = -ENOMEM;
+			rc = PTR_ERR(req);
 			goto out;
 		}
-		memset(req, 0, sizeof(struct rpcrdma_req));
 		buf->rb_send_bufs[i] = req;
-		buf->rb_send_bufs[i]->rl_buffer = buf;
-
-		rc = rpcrdma_register_internal(ia, 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 = wlen -
-						sizeof(struct rpcrdma_req);
 
-		rep = kmalloc(rlen, GFP_KERNEL);
-		if (rep == NULL) {
+		rep = rpcrdma_create_rep(r_xprt);
+		if (IS_ERR(rep)) {
 			dprintk("RPC:       %s: reply buffer %d alloc failed\n",
 				__func__, i);
-			rc = -ENOMEM;
+			rc = PTR_ERR(rep);
 			goto out;
 		}
-		memset(rep, 0, sizeof(struct rpcrdma_rep));
 		buf->rb_recv_bufs[i] = rep;
-		buf->rb_recv_bufs[i]->rr_buffer = buf;
-
-		rc = rpcrdma_register_internal(ia, 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)
-			goto out;
-
 	}
-	dprintk("RPC:       %s: max_requests %d\n",
-		__func__, buf->rb_max_requests);
-	/* done */
+
 	return 0;
 out:
 	rpcrdma_buffer_destroy(buf);
@@ -1205,44 +1132,24 @@ out:
 }
 
 static void
-rpcrdma_destroy_fmrs(struct rpcrdma_buffer *buf)
+rpcrdma_destroy_rep(struct rpcrdma_ia *ia, struct rpcrdma_rep *rep)
 {
-	struct rpcrdma_mw *r;
-	int rc;
-
-	while (!list_empty(&buf->rb_all)) {
-		r = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all);
-		list_del(&r->mw_all);
-		list_del(&r->mw_list);
-
-		rc = ib_dealloc_fmr(r->r.fmr);
-		if (rc)
-			dprintk("RPC:       %s: ib_dealloc_fmr failed %i\n",
-				__func__, rc);
+	if (!rep)
+		return;
 
-		kfree(r);
-	}
+	rpcrdma_free_regbuf(ia, rep->rr_rdmabuf);
+	kfree(rep);
 }
 
 static void
-rpcrdma_destroy_frmrs(struct rpcrdma_buffer *buf)
+rpcrdma_destroy_req(struct rpcrdma_ia *ia, struct rpcrdma_req *req)
 {
-	struct rpcrdma_mw *r;
-	int rc;
-
-	while (!list_empty(&buf->rb_all)) {
-		r = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all);
-		list_del(&r->mw_all);
-		list_del(&r->mw_list);
-
-		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);
+	if (!req)
+		return;
 
-		kfree(r);
-	}
+	rpcrdma_free_regbuf(ia, req->rl_sendbuf);
+	rpcrdma_free_regbuf(ia, req->rl_rdmabuf);
+	kfree(req);
 }
 
 void
@@ -1259,90 +1166,17 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf)
 	dprintk("RPC:       %s: entering\n", __func__);
 
 	for (i = 0; i < buf->rb_max_requests; i++) {
-		if (buf->rb_recv_bufs && buf->rb_recv_bufs[i]) {
-			rpcrdma_deregister_internal(ia,
-					buf->rb_recv_bufs[i]->rr_handle,
-					&buf->rb_recv_bufs[i]->rr_iov);
-			kfree(buf->rb_recv_bufs[i]);
-		}
-		if (buf->rb_send_bufs && buf->rb_send_bufs[i]) {
-			rpcrdma_deregister_internal(ia,
-					buf->rb_send_bufs[i]->rl_handle,
-					&buf->rb_send_bufs[i]->rl_iov);
-			kfree(buf->rb_send_bufs[i]);
-		}
+		if (buf->rb_recv_bufs)
+			rpcrdma_destroy_rep(ia, buf->rb_recv_bufs[i]);
+		if (buf->rb_send_bufs)
+			rpcrdma_destroy_req(ia, buf->rb_send_bufs[i]);
 	}
 
-	switch (ia->ri_memreg_strategy) {
-	case RPCRDMA_FRMR:
-		rpcrdma_destroy_frmrs(buf);
-		break;
-	case RPCRDMA_MTHCAFMR:
-		rpcrdma_destroy_fmrs(buf);
-		break;
-	default:
-		break;
-	}
+	ia->ri_ops->ro_destroy(buf);
 
 	kfree(buf->rb_pool);
 }
 
-/* After a disconnect, a flushed FAST_REG_MR can leave an FRMR in
- * an unusable state. Find FRMRs in this state and dereg / reg
- * each.  FRMRs that are VALID and attached to an rpcrdma_req are
- * also torn down.
- *
- * This gives all in-use FRMRs a fresh rkey and leaves them INVALID.
- *
- * This is invoked only in the transport connect worker in order
- * to serialize with rpcrdma_register_frmr_external().
- */
-static void
-rpcrdma_reset_frmrs(struct rpcrdma_ia *ia)
-{
-	struct rpcrdma_xprt *r_xprt =
-				container_of(ia, struct rpcrdma_xprt, rx_ia);
-	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
-	struct list_head *pos;
-	struct rpcrdma_mw *r;
-	int rc;
-
-	list_for_each(pos, &buf->rb_all) {
-		r = list_entry(pos, struct rpcrdma_mw, mw_all);
-
-		if (r->r.frmr.fr_state == FRMR_IS_INVALID)
-			continue;
-
-		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);
-
-		r->r.frmr.fr_mr = ib_alloc_fast_reg_mr(ia->ri_pd,
-					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);
-			continue;
-		}
-		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);
-			continue;
-		}
-		r->r.frmr.fr_state = FRMR_IS_INVALID;
-	}
-}
-
 /* "*mw" can be NULL when rpcrdma_buffer_get_mrs() fails, leaving
  * some req segments uninitialized.
  */
@@ -1366,8 +1200,8 @@ rpcrdma_buffer_put_mrs(struct rpcrdma_req *req, struct rpcrdma_buffer *buf)
 	int i;
 
 	for (i = 1, seg++; i < RPCRDMA_MAX_SEGS; seg++, i++)
-		rpcrdma_buffer_put_mr(&seg->mr_chunk.rl_mw, buf);
-	rpcrdma_buffer_put_mr(&seg1->mr_chunk.rl_mw, buf);
+		rpcrdma_buffer_put_mr(&seg->rl_mw, buf);
+	rpcrdma_buffer_put_mr(&seg1->rl_mw, buf);
 }
 
 static void
@@ -1382,7 +1216,7 @@ rpcrdma_buffer_put_sendbuf(struct rpcrdma_req *req, struct rpcrdma_buffer *buf)
 	}
 }
 
-/* rpcrdma_unmap_one() was already done by rpcrdma_deregister_frmr_external().
+/* rpcrdma_unmap_one() was already done during deregistration.
  * Redo only the ib_post_send().
  */
 static void
@@ -1453,7 +1287,7 @@ rpcrdma_buffer_get_frmrs(struct rpcrdma_req *req, struct rpcrdma_buffer *buf,
 			list_add(&r->mw_list, stale);
 			continue;
 		}
-		req->rl_segments[i].mr_chunk.rl_mw = r;
+		req->rl_segments[i].rl_mw = r;
 		if (unlikely(i-- == 0))
 			return req;	/* Success */
 	}
@@ -1475,7 +1309,7 @@ rpcrdma_buffer_get_fmrs(struct rpcrdma_req *req, struct rpcrdma_buffer *buf)
 		r = list_entry(buf->rb_mws.next,
 			       struct rpcrdma_mw, mw_list);
 		list_del(&r->mw_list);
-		req->rl_segments[i].mr_chunk.rl_mw = r;
+		req->rl_segments[i].rl_mw = r;
 		if (unlikely(i-- == 0))
 			return req;	/* Success */
 	}
@@ -1574,8 +1408,6 @@ rpcrdma_recv_buffer_get(struct rpcrdma_req *req)
 	struct rpcrdma_buffer *buffers = req->rl_buffer;
 	unsigned long flags;
 
-	if (req->rl_iov.length == 0)	/* special case xprt_rdma_allocate() */
-		buffers = ((struct rpcrdma_req *) buffers)->rl_buffer;
 	spin_lock_irqsave(&buffers->rb_lock, flags);
 	if (buffers->rb_recv_index < buffers->rb_max_requests) {
 		req->rl_reply = buffers->rb_recv_bufs[buffers->rb_recv_index];
@@ -1604,7 +1436,15 @@ rpcrdma_recv_buffer_put(struct rpcrdma_rep *rep)
  * Wrappers for internal-use kmalloc memory registration, used by buffer code.
  */
 
-int
+void
+rpcrdma_mapping_error(struct rpcrdma_mr_seg *seg)
+{
+	dprintk("RPC:       map_one: offset %p iova %llx len %zu\n",
+		seg->mr_offset,
+		(unsigned long long)seg->mr_dma, seg->mr_dmalen);
+}
+
+static int
 rpcrdma_register_internal(struct rpcrdma_ia *ia, void *va, int len,
 				struct ib_mr **mrp, struct ib_sge *iov)
 {
@@ -1655,7 +1495,7 @@ rpcrdma_register_internal(struct rpcrdma_ia *ia, void *va, int len,
 	return rc;
 }
 
-int
+static int
 rpcrdma_deregister_internal(struct rpcrdma_ia *ia,
 				struct ib_mr *mr, struct ib_sge *iov)
 {
@@ -1673,286 +1513,59 @@ rpcrdma_deregister_internal(struct rpcrdma_ia *ia,
 	return rc;
 }
 
-/*
- * Wrappers for chunk registration, shared by read/write chunk code.
+/**
+ * rpcrdma_alloc_regbuf - kmalloc and register memory for SEND/RECV buffers
+ * @ia: controlling rpcrdma_ia
+ * @size: size of buffer to be allocated, in bytes
+ * @flags: GFP flags
+ *
+ * Returns pointer to private header of an area of internally
+ * registered memory, or an ERR_PTR. The registered buffer follows
+ * the end of the private header.
+ *
+ * xprtrdma uses a regbuf for posting an outgoing RDMA SEND, or for
+ * receiving the payload of RDMA RECV operations. regbufs are not
+ * used for RDMA READ/WRITE operations, thus are registered only for
+ * LOCAL access.
  */
-
-static void
-rpcrdma_map_one(struct rpcrdma_ia *ia, struct rpcrdma_mr_seg *seg, int writing)
+struct rpcrdma_regbuf *
+rpcrdma_alloc_regbuf(struct rpcrdma_ia *ia, size_t size, gfp_t flags)
 {
-	seg->mr_dir = writing ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
-	seg->mr_dmalen = seg->mr_len;
-	if (seg->mr_page)
-		seg->mr_dma = ib_dma_map_page(ia->ri_id->device,
-				seg->mr_page, offset_in_page(seg->mr_offset),
-				seg->mr_dmalen, seg->mr_dir);
-	else
-		seg->mr_dma = ib_dma_map_single(ia->ri_id->device,
-				seg->mr_offset,
-				seg->mr_dmalen, seg->mr_dir);
-	if (ib_dma_mapping_error(ia->ri_id->device, seg->mr_dma)) {
-		dprintk("RPC:       %s: mr_dma %llx mr_offset %p mr_dma_len %zu\n",
-			__func__,
-			(unsigned long long)seg->mr_dma,
-			seg->mr_offset, seg->mr_dmalen);
-	}
-}
-
-static void
-rpcrdma_unmap_one(struct rpcrdma_ia *ia, struct rpcrdma_mr_seg *seg)
-{
-	if (seg->mr_page)
-		ib_dma_unmap_page(ia->ri_id->device,
-				seg->mr_dma, seg->mr_dmalen, seg->mr_dir);
-	else
-		ib_dma_unmap_single(ia->ri_id->device,
-				seg->mr_dma, seg->mr_dmalen, seg->mr_dir);
-}
-
-static int
-rpcrdma_register_frmr_external(struct rpcrdma_mr_seg *seg,
-			int *nsegs, int writing, struct rpcrdma_ia *ia,
-			struct rpcrdma_xprt *r_xprt)
-{
-	struct rpcrdma_mr_seg *seg1 = seg;
-	struct rpcrdma_mw *mw = seg1->mr_chunk.rl_mw;
-	struct rpcrdma_frmr *frmr = &mw->r.frmr;
-	struct ib_mr *mr = frmr->fr_mr;
-	struct ib_send_wr fastreg_wr, *bad_wr;
-	u8 key;
-	int len, pageoff;
-	int i, rc;
-	int seg_len;
-	u64 pa;
-	int page_no;
-
-	pageoff = offset_in_page(seg1->mr_offset);
-	seg1->mr_offset -= pageoff;	/* start of page */
-	seg1->mr_len += pageoff;
-	len = -pageoff;
-	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;
-		for (seg_len = seg->mr_len; seg_len > 0; seg_len -= PAGE_SIZE) {
-			frmr->fr_pgl->page_list[page_no++] = pa;
-			pa += PAGE_SIZE;
-		}
-		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;
-	}
-	dprintk("RPC:       %s: Using frmr %p to map %d segments\n",
-		__func__, mw, i);
-
-	frmr->fr_state = FRMR_IS_VALID;
-
-	memset(&fastreg_wr, 0, sizeof(fastreg_wr));
-	fastreg_wr.wr_id = (unsigned long)(void *)mw;
-	fastreg_wr.opcode = IB_WR_FAST_REG_MR;
-	fastreg_wr.wr.fast_reg.iova_start = seg1->mr_dma;
-	fastreg_wr.wr.fast_reg.page_list = frmr->fr_pgl;
-	fastreg_wr.wr.fast_reg.page_list_len = page_no;
-	fastreg_wr.wr.fast_reg.page_shift = PAGE_SHIFT;
-	fastreg_wr.wr.fast_reg.length = page_no << PAGE_SHIFT;
-	if (fastreg_wr.wr.fast_reg.length < len) {
-		rc = -EIO;
-		goto out_err;
-	}
-
-	/* Bump the key */
-	key = (u8)(mr->rkey & 0x000000FF);
-	ib_update_fast_reg_key(mr, ++key);
-
-	fastreg_wr.wr.fast_reg.access_flags = (writing ?
-				IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE :
-				IB_ACCESS_REMOTE_READ);
-	fastreg_wr.wr.fast_reg.rkey = mr->rkey;
-	DECR_CQCOUNT(&r_xprt->rx_ep);
-
-	rc = ib_post_send(ia->ri_id->qp, &fastreg_wr, &bad_wr);
-	if (rc) {
-		dprintk("RPC:       %s: failed ib_post_send for register,"
-			" status %i\n", __func__, rc);
-		ib_update_fast_reg_key(mr, --key);
-		goto out_err;
-	} else {
-		seg1->mr_rkey = mr->rkey;
-		seg1->mr_base = seg1->mr_dma + pageoff;
-		seg1->mr_nsegs = i;
-		seg1->mr_len = len;
-	}
-	*nsegs = i;
-	return 0;
-out_err:
-	frmr->fr_state = FRMR_IS_INVALID;
-	while (i--)
-		rpcrdma_unmap_one(ia, --seg);
-	return rc;
-}
-
-static int
-rpcrdma_deregister_frmr_external(struct rpcrdma_mr_seg *seg,
-			struct rpcrdma_ia *ia, struct rpcrdma_xprt *r_xprt)
-{
-	struct rpcrdma_mr_seg *seg1 = seg;
-	struct ib_send_wr invalidate_wr, *bad_wr;
+	struct rpcrdma_regbuf *rb;
 	int rc;
 
-	seg1->mr_chunk.rl_mw->r.frmr.fr_state = FRMR_IS_INVALID;
-
-	memset(&invalidate_wr, 0, sizeof invalidate_wr);
-	invalidate_wr.wr_id = (unsigned long)(void *)seg1->mr_chunk.rl_mw;
-	invalidate_wr.opcode = IB_WR_LOCAL_INV;
-	invalidate_wr.ex.invalidate_rkey = seg1->mr_chunk.rl_mw->r.frmr.fr_mr->rkey;
-	DECR_CQCOUNT(&r_xprt->rx_ep);
-
-	read_lock(&ia->ri_qplock);
-	while (seg1->mr_nsegs--)
-		rpcrdma_unmap_one(ia, seg++);
-	rc = ib_post_send(ia->ri_id->qp, &invalidate_wr, &bad_wr);
-	read_unlock(&ia->ri_qplock);
-	if (rc) {
-		/* Force rpcrdma_buffer_get() to retry */
-		seg1->mr_chunk.rl_mw->r.frmr.fr_state = FRMR_IS_STALE;
-		dprintk("RPC:       %s: failed ib_post_send for invalidate,"
-			" status %i\n", __func__, rc);
-	}
-	return rc;
-}
-
-static int
-rpcrdma_register_fmr_external(struct rpcrdma_mr_seg *seg,
-			int *nsegs, int writing, struct rpcrdma_ia *ia)
-{
-	struct rpcrdma_mr_seg *seg1 = seg;
-	u64 physaddrs[RPCRDMA_MAX_DATA_SEGS];
-	int len, pageoff, i, rc;
-
-	pageoff = offset_in_page(seg1->mr_offset);
-	seg1->mr_offset -= pageoff;	/* start of page */
-	seg1->mr_len += pageoff;
-	len = -pageoff;
-	if (*nsegs > RPCRDMA_MAX_DATA_SEGS)
-		*nsegs = RPCRDMA_MAX_DATA_SEGS;
-	for (i = 0; i < *nsegs;) {
-		rpcrdma_map_one(ia, seg, writing);
-		physaddrs[i] = seg->mr_dma;
-		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;
-	}
-	rc = ib_map_phys_fmr(seg1->mr_chunk.rl_mw->r.fmr,
-				physaddrs, i, seg1->mr_dma);
-	if (rc) {
-		dprintk("RPC:       %s: failed ib_map_phys_fmr "
-			"%u@0x%llx+%i (%d)... status %i\n", __func__,
-			len, (unsigned long long)seg1->mr_dma,
-			pageoff, i, rc);
-		while (i--)
-			rpcrdma_unmap_one(ia, --seg);
-	} else {
-		seg1->mr_rkey = seg1->mr_chunk.rl_mw->r.fmr->rkey;
-		seg1->mr_base = seg1->mr_dma + pageoff;
-		seg1->mr_nsegs = i;
-		seg1->mr_len = len;
-	}
-	*nsegs = i;
-	return rc;
-}
-
-static int
-rpcrdma_deregister_fmr_external(struct rpcrdma_mr_seg *seg,
-			struct rpcrdma_ia *ia)
-{
-	struct rpcrdma_mr_seg *seg1 = seg;
-	LIST_HEAD(l);
-	int rc;
+	rc = -ENOMEM;
+	rb = kmalloc(sizeof(*rb) + size, flags);
+	if (rb == NULL)
+		goto out;
 
-	list_add(&seg1->mr_chunk.rl_mw->r.fmr->list, &l);
-	rc = ib_unmap_fmr(&l);
-	read_lock(&ia->ri_qplock);
-	while (seg1->mr_nsegs--)
-		rpcrdma_unmap_one(ia, seg++);
-	read_unlock(&ia->ri_qplock);
+	rb->rg_size = size;
+	rb->rg_owner = NULL;
+	rc = rpcrdma_register_internal(ia, rb->rg_base, size,
+				       &rb->rg_mr, &rb->rg_iov);
 	if (rc)
-		dprintk("RPC:       %s: failed ib_unmap_fmr,"
-			" 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)
-{
-	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
-	int rc = 0;
-
-	switch (ia->ri_memreg_strategy) {
-
-	case RPCRDMA_ALLPHYSICAL:
-		rpcrdma_map_one(ia, seg, writing);
-		seg->mr_rkey = ia->ri_bind_mem->rkey;
-		seg->mr_base = seg->mr_dma;
-		seg->mr_nsegs = 1;
-		nsegs = 1;
-		break;
+		goto out_free;
 
-	/* Registration using frmr registration */
-	case RPCRDMA_FRMR:
-		rc = rpcrdma_register_frmr_external(seg, &nsegs, writing, ia, r_xprt);
-		break;
+	return rb;
 
-	/* Registration using fmr memory registration */
-	case RPCRDMA_MTHCAFMR:
-		rc = rpcrdma_register_fmr_external(seg, &nsegs, writing, ia);
-		break;
-
-	default:
-		return -1;
-	}
-	if (rc)
-		return -1;
-
-	return nsegs;
+out_free:
+	kfree(rb);
+out:
+	return ERR_PTR(rc);
 }
 
-int
-rpcrdma_deregister_external(struct rpcrdma_mr_seg *seg,
-		struct rpcrdma_xprt *r_xprt)
+/**
+ * rpcrdma_free_regbuf - deregister and free registered buffer
+ * @ia: controlling rpcrdma_ia
+ * @rb: regbuf to be deregistered and freed
+ */
+void
+rpcrdma_free_regbuf(struct rpcrdma_ia *ia, struct rpcrdma_regbuf *rb)
 {
-	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
-	int nsegs = seg->mr_nsegs, rc;
-
-	switch (ia->ri_memreg_strategy) {
-
-	case RPCRDMA_ALLPHYSICAL:
-		read_lock(&ia->ri_qplock);
-		rpcrdma_unmap_one(ia, seg);
-		read_unlock(&ia->ri_qplock);
-		break;
-
-	case RPCRDMA_FRMR:
-		rc = rpcrdma_deregister_frmr_external(seg, ia, r_xprt);
-		break;
-
-	case RPCRDMA_MTHCAFMR:
-		rc = rpcrdma_deregister_fmr_external(seg, ia);
-		break;
-
-	default:
-		break;
+	if (rb) {
+		rpcrdma_deregister_internal(ia, rb->rg_mr, &rb->rg_iov);
+		kfree(rb);
 	}
-	return nsegs;
 }
 
 /*
@@ -1977,7 +1590,7 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia,
 	}
 
 	send_wr.next = NULL;
-	send_wr.wr_id = 0ULL;	/* no send cookie */
+	send_wr.wr_id = RPCRDMA_IGNORE_COMPLETION;
 	send_wr.sg_list = req->rl_send_iov;
 	send_wr.num_sge = req->rl_niovs;
 	send_wr.opcode = IB_WR_SEND;
@@ -2020,11 +1633,13 @@ rpcrdma_ep_post_recv(struct rpcrdma_ia *ia,
 
 	recv_wr.next = NULL;
 	recv_wr.wr_id = (u64) (unsigned long) rep;
-	recv_wr.sg_list = &rep->rr_iov;
+	recv_wr.sg_list = &rep->rr_rdmabuf->rg_iov;
 	recv_wr.num_sge = 1;
 
 	ib_dma_sync_single_for_cpu(ia->ri_id->device,
-		rep->rr_iov.addr, rep->rr_iov.length, DMA_BIDIRECTIONAL);
+				   rdmab_addr(rep->rr_rdmabuf),
+				   rdmab_length(rep->rr_rdmabuf),
+				   DMA_BIDIRECTIONAL);
 
 	rc = ib_post_recv(ia->ri_id->qp, &recv_wr, &recv_wr_fail);
 
@@ -2034,43 +1649,24 @@ rpcrdma_ep_post_recv(struct rpcrdma_ia *ia,
 	return rc;
 }
 
-/* Physical mapping means one Read/Write list entry per-page.
- * All list entries must fit within an inline buffer
- *
- * NB: The server must return a Write list for NFS READ,
- *     which has the same constraint. Factor in the inline
- *     rsize as well.
+/* How many chunk list items fit within our inline buffers?
  */
-static size_t
-rpcrdma_physical_max_payload(struct rpcrdma_xprt *r_xprt)
+unsigned int
+rpcrdma_max_segments(struct rpcrdma_xprt *r_xprt)
 {
 	struct rpcrdma_create_data_internal *cdata = &r_xprt->rx_data;
-	unsigned int inline_size, pages;
+	int bytes, segments;
 
-	inline_size = min_t(unsigned int,
-			    cdata->inline_wsize, cdata->inline_rsize);
-	inline_size -= RPCRDMA_HDRLEN_MIN;
-	pages = inline_size / sizeof(struct rpcrdma_segment);
-	return pages << PAGE_SHIFT;
-}
-
-static size_t
-rpcrdma_mr_max_payload(struct rpcrdma_xprt *r_xprt)
-{
-	return RPCRDMA_MAX_DATA_SEGS << PAGE_SHIFT;
-}
-
-size_t
-rpcrdma_max_payload(struct rpcrdma_xprt *r_xprt)
-{
-	size_t result;
-
-	switch (r_xprt->rx_ia.ri_memreg_strategy) {
-	case RPCRDMA_ALLPHYSICAL:
-		result = rpcrdma_physical_max_payload(r_xprt);
-		break;
-	default:
-		result = rpcrdma_mr_max_payload(r_xprt);
+	bytes = min_t(unsigned int, cdata->inline_wsize, cdata->inline_rsize);
+	bytes -= RPCRDMA_HDRLEN_MIN;
+	if (bytes < sizeof(struct rpcrdma_segment) * 2) {
+		pr_warn("RPC:       %s: inline threshold too small\n",
+			__func__);
+		return 0;
 	}
-	return result;
+
+	segments = 1 << (fls(bytes / sizeof(struct rpcrdma_segment)) - 1);
+	dprintk("RPC:       %s: max chunk list size = %d segments\n",
+		__func__, segments);
+	return segments;
 }
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index ac7fc9a31342..78e0b8beaa36 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -60,6 +60,7 @@
  * Interface Adapter -- one per transport instance
  */
 struct rpcrdma_ia {
+	const struct rpcrdma_memreg_ops	*ri_ops;
 	rwlock_t		ri_qplock;
 	struct rdma_cm_id 	*ri_id;
 	struct ib_pd		*ri_pd;
@@ -70,6 +71,9 @@ struct rpcrdma_ia {
 	int			ri_async_rc;
 	enum rpcrdma_memreg	ri_memreg_strategy;
 	unsigned int		ri_max_frmr_depth;
+	struct ib_device_attr	ri_devattr;
+	struct ib_qp_attr	ri_qp_attr;
+	struct ib_qp_init_attr	ri_qp_init_attr;
 };
 
 /*
@@ -83,13 +87,9 @@ struct rpcrdma_ep {
 	atomic_t		rep_cqcount;
 	int			rep_cqinit;
 	int			rep_connected;
-	struct rpcrdma_ia	*rep_ia;
 	struct ib_qp_init_attr	rep_attr;
 	wait_queue_head_t 	rep_connect_wait;
-	struct ib_sge		rep_pad;	/* holds zeroed pad */
-	struct ib_mr		*rep_pad_mr;	/* holds zeroed pad */
-	void			(*rep_func)(struct rpcrdma_ep *);
-	struct rpc_xprt		*rep_xprt;	/* for rep_func */
+	struct rpcrdma_regbuf	*rep_padbuf;
 	struct rdma_conn_param	rep_remote_cma;
 	struct sockaddr_storage	rep_remote_addr;
 	struct delayed_work	rep_connect_worker;
@@ -97,17 +97,57 @@ struct rpcrdma_ep {
 	struct ib_wc		rep_recv_wcs[RPCRDMA_POLLSIZE];
 };
 
+/*
+ * Force a signaled SEND Work Request every so often,
+ * in case the provider needs to do some housekeeping.
+ */
+#define RPCRDMA_MAX_UNSIGNALED_SENDS	(32)
+
 #define INIT_CQCOUNT(ep) atomic_set(&(ep)->rep_cqcount, (ep)->rep_cqinit)
 #define DECR_CQCOUNT(ep) atomic_sub_return(1, &(ep)->rep_cqcount)
 
-enum rpcrdma_chunktype {
-	rpcrdma_noch = 0,
-	rpcrdma_readch,
-	rpcrdma_areadch,
-	rpcrdma_writech,
-	rpcrdma_replych
+/* Force completion handler to ignore the signal
+ */
+#define RPCRDMA_IGNORE_COMPLETION	(0ULL)
+
+/* Registered buffer -- registered kmalloc'd memory for RDMA SEND/RECV
+ *
+ * The below structure appears at the front of a large region of kmalloc'd
+ * memory, which always starts on a good alignment boundary.
+ */
+
+struct rpcrdma_regbuf {
+	size_t			rg_size;
+	struct rpcrdma_req	*rg_owner;
+	struct ib_mr		*rg_mr;
+	struct ib_sge		rg_iov;
+	__be32			rg_base[0] __attribute__ ((aligned(256)));
 };
 
+static inline u64
+rdmab_addr(struct rpcrdma_regbuf *rb)
+{
+	return rb->rg_iov.addr;
+}
+
+static inline u32
+rdmab_length(struct rpcrdma_regbuf *rb)
+{
+	return rb->rg_iov.length;
+}
+
+static inline u32
+rdmab_lkey(struct rpcrdma_regbuf *rb)
+{
+	return rb->rg_iov.lkey;
+}
+
+static inline struct rpcrdma_msg *
+rdmab_to_msg(struct rpcrdma_regbuf *rb)
+{
+	return (struct rpcrdma_msg *)rb->rg_base;
+}
+
 /*
  * struct rpcrdma_rep -- this structure encapsulates state required to recv
  * and complete a reply, asychronously. It needs several pieces of
@@ -128,22 +168,16 @@ enum rpcrdma_chunktype {
 /* temporary static scatter/gather max */
 #define RPCRDMA_MAX_DATA_SEGS	(64)	/* max scatter/gather */
 #define RPCRDMA_MAX_SEGS 	(RPCRDMA_MAX_DATA_SEGS + 2) /* head+tail = 2 */
-#define MAX_RPCRDMAHDR	(\
-	/* max supported RPC/RDMA header */ \
-	sizeof(struct rpcrdma_msg) + (2 * sizeof(u32)) + \
-	(sizeof(struct rpcrdma_read_chunk) * RPCRDMA_MAX_SEGS) + sizeof(u32))
 
 struct rpcrdma_buffer;
 
 struct rpcrdma_rep {
-	unsigned int	rr_len;		/* actual received reply length */
-	struct rpcrdma_buffer *rr_buffer; /* home base for this structure */
-	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 */
-	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 */
+	unsigned int		rr_len;
+	struct rpcrdma_buffer	*rr_buffer;
+	struct rpc_xprt		*rr_xprt;
+	void			(*rr_func)(struct rpcrdma_rep *);
+	struct list_head	rr_list;
+	struct rpcrdma_regbuf	*rr_rdmabuf;
 };
 
 /*
@@ -176,6 +210,7 @@ struct rpcrdma_mw {
 		struct ib_fmr		*fmr;
 		struct rpcrdma_frmr	frmr;
 	} r;
+	void			(*mw_sendcompletion)(struct ib_wc *);
 	struct list_head	mw_list;
 	struct list_head	mw_all;
 };
@@ -205,10 +240,7 @@ struct rpcrdma_mw {
  */
 
 struct rpcrdma_mr_seg {		/* chunk descriptors */
-	union {				/* chunk memory handles */
-		struct ib_mr	*rl_mr;		/* if registered directly */
-		struct rpcrdma_mw *rl_mw;	/* if registered from region */
-	} mr_chunk;
+	struct rpcrdma_mw *rl_mw;	/* registered MR */
 	u64		mr_base;	/* registration result */
 	u32		mr_rkey;	/* registration result */
 	u32		mr_len;		/* length of chunk or segment */
@@ -221,22 +253,26 @@ struct rpcrdma_mr_seg {		/* chunk descriptors */
 };
 
 struct rpcrdma_req {
-	size_t 		rl_size;	/* actual length of buffer */
 	unsigned int	rl_niovs;	/* 0, 2 or 4 */
 	unsigned int	rl_nchunks;	/* non-zero if chunks */
 	unsigned int	rl_connect_cookie;	/* retry detection */
-	enum rpcrdma_chunktype	rl_rtype, rl_wtype;
 	struct rpcrdma_buffer *rl_buffer; /* home base for this structure */
 	struct rpcrdma_rep	*rl_reply;/* holder for reply buffer */
-	struct rpcrdma_mr_seg rl_segments[RPCRDMA_MAX_SEGS];/* chunk segments */
 	struct ib_sge	rl_send_iov[4];	/* for active requests */
-	struct ib_sge	rl_iov;		/* for posting */
-	struct ib_mr	*rl_handle;	/* handle for mem in rl_iov */
-	char		rl_base[MAX_RPCRDMAHDR]; /* start of actual buffer */
-	__u32 		rl_xdr_buf[0];	/* start of returned rpc rq_buffer */
+	struct rpcrdma_regbuf *rl_rdmabuf;
+	struct rpcrdma_regbuf *rl_sendbuf;
+	struct rpcrdma_mr_seg rl_segments[RPCRDMA_MAX_SEGS];
 };
-#define rpcr_to_rdmar(r) \
-	container_of((r)->rq_buffer, struct rpcrdma_req, rl_xdr_buf[0])
+
+static inline struct rpcrdma_req *
+rpcr_to_rdmar(struct rpc_rqst *rqst)
+{
+	void *buffer = rqst->rq_buffer;
+	struct rpcrdma_regbuf *rb;
+
+	rb = container_of(buffer, struct rpcrdma_regbuf, rg_base);
+	return rb->rg_owner;
+}
 
 /*
  * struct rpcrdma_buffer -- holds list/queue of pre-registered memory for
@@ -246,8 +282,7 @@ struct rpcrdma_req {
  */
 struct rpcrdma_buffer {
 	spinlock_t	rb_lock;	/* protects indexes */
-	atomic_t	rb_credits;	/* most recent server credits */
-	int		rb_max_requests;/* client max requests */
+	u32		rb_max_requests;/* client max requests */
 	struct list_head rb_mws;	/* optional memory windows/fmrs/frmrs */
 	struct list_head rb_all;
 	int		rb_send_index;
@@ -302,6 +337,29 @@ struct rpcrdma_stats {
 };
 
 /*
+ * Per-registration mode operations
+ */
+struct rpcrdma_xprt;
+struct rpcrdma_memreg_ops {
+	int		(*ro_map)(struct rpcrdma_xprt *,
+				  struct rpcrdma_mr_seg *, int, bool);
+	int		(*ro_unmap)(struct rpcrdma_xprt *,
+				    struct rpcrdma_mr_seg *);
+	int		(*ro_open)(struct rpcrdma_ia *,
+				   struct rpcrdma_ep *,
+				   struct rpcrdma_create_data_internal *);
+	size_t		(*ro_maxpages)(struct rpcrdma_xprt *);
+	int		(*ro_init)(struct rpcrdma_xprt *);
+	void		(*ro_reset)(struct rpcrdma_xprt *);
+	void		(*ro_destroy)(struct rpcrdma_buffer *);
+	const char	*ro_displayname;
+};
+
+extern const struct rpcrdma_memreg_ops rpcrdma_fmr_memreg_ops;
+extern const struct rpcrdma_memreg_ops rpcrdma_frwr_memreg_ops;
+extern const struct rpcrdma_memreg_ops rpcrdma_physical_memreg_ops;
+
+/*
  * RPCRDMA transport -- encapsulates the structures above for
  * integration with RPC.
  *
@@ -312,16 +370,16 @@ struct rpcrdma_stats {
  * during unmount.
  */
 struct rpcrdma_xprt {
-	struct rpc_xprt		xprt;
+	struct rpc_xprt		rx_xprt;
 	struct rpcrdma_ia	rx_ia;
 	struct rpcrdma_ep	rx_ep;
 	struct rpcrdma_buffer	rx_buf;
 	struct rpcrdma_create_data_internal rx_data;
-	struct delayed_work	rdma_connect;
+	struct delayed_work	rx_connect_worker;
 	struct rpcrdma_stats	rx_stats;
 };
 
-#define rpcx_to_rdmax(x) container_of(x, struct rpcrdma_xprt, xprt)
+#define rpcx_to_rdmax(x) container_of(x, struct rpcrdma_xprt, rx_xprt)
 #define rpcx_to_rdmad(x) (rpcx_to_rdmax(x)->rx_data)
 
 /* Setting this to 0 ensures interoperability with early servers.
@@ -352,9 +410,7 @@ int rpcrdma_ep_post_recv(struct rpcrdma_ia *, struct rpcrdma_ep *,
 /*
  * Buffer calls - xprtrdma/verbs.c
  */
-int rpcrdma_buffer_create(struct rpcrdma_buffer *, struct rpcrdma_ep *,
-				struct rpcrdma_ia *,
-				struct rpcrdma_create_data_internal *);
+int rpcrdma_buffer_create(struct rpcrdma_xprt *);
 void rpcrdma_buffer_destroy(struct rpcrdma_buffer *);
 
 struct rpcrdma_req *rpcrdma_buffer_get(struct rpcrdma_buffer *);
@@ -362,15 +418,55 @@ void rpcrdma_buffer_put(struct rpcrdma_req *);
 void rpcrdma_recv_buffer_get(struct rpcrdma_req *);
 void rpcrdma_recv_buffer_put(struct rpcrdma_rep *);
 
-int rpcrdma_register_internal(struct rpcrdma_ia *, void *, int,
-				struct ib_mr **, struct ib_sge *);
-int rpcrdma_deregister_internal(struct rpcrdma_ia *,
-				struct ib_mr *, struct ib_sge *);
+struct rpcrdma_regbuf *rpcrdma_alloc_regbuf(struct rpcrdma_ia *,
+					    size_t, gfp_t);
+void rpcrdma_free_regbuf(struct rpcrdma_ia *,
+			 struct rpcrdma_regbuf *);
+
+unsigned int rpcrdma_max_segments(struct rpcrdma_xprt *);
+
+/*
+ * Wrappers for chunk registration, shared by read/write chunk code.
+ */
 
-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 rpcrdma_mapping_error(struct rpcrdma_mr_seg *);
+
+static inline enum dma_data_direction
+rpcrdma_data_dir(bool writing)
+{
+	return writing ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
+}
+
+static inline void
+rpcrdma_map_one(struct ib_device *device, struct rpcrdma_mr_seg *seg,
+		enum dma_data_direction direction)
+{
+	seg->mr_dir = direction;
+	seg->mr_dmalen = seg->mr_len;
+
+	if (seg->mr_page)
+		seg->mr_dma = ib_dma_map_page(device,
+				seg->mr_page, offset_in_page(seg->mr_offset),
+				seg->mr_dmalen, seg->mr_dir);
+	else
+		seg->mr_dma = ib_dma_map_single(device,
+				seg->mr_offset,
+				seg->mr_dmalen, seg->mr_dir);
+
+	if (ib_dma_mapping_error(device, seg->mr_dma))
+		rpcrdma_mapping_error(seg);
+}
+
+static inline void
+rpcrdma_unmap_one(struct ib_device *device, struct rpcrdma_mr_seg *seg)
+{
+	if (seg->mr_page)
+		ib_dma_unmap_page(device,
+				  seg->mr_dma, seg->mr_dmalen, seg->mr_dir);
+	else
+		ib_dma_unmap_single(device,
+				    seg->mr_dma, seg->mr_dmalen, seg->mr_dir);
+}
 
 /*
  * RPC/RDMA connection management calls - xprtrdma/rpc_rdma.c
@@ -382,9 +478,7 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *);
 /*
  * RPC/RDMA protocol calls - xprtrdma/rpc_rdma.c
  */
-ssize_t rpcrdma_marshal_chunks(struct rpc_rqst *, ssize_t);
 int rpcrdma_marshal_req(struct rpc_rqst *);
-size_t rpcrdma_max_payload(struct rpcrdma_xprt *);
 
 /* Temporary NFS request map cache. Created in svc_rdma.c  */
 extern struct kmem_cache *svc_rdma_map_cachep;
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 3b305ab17afe..66891e32c5e3 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -63,6 +63,8 @@ static unsigned int xprt_max_tcp_slot_table_entries = RPC_MAX_SLOT_TABLE;
 static unsigned int xprt_min_resvport = RPC_DEF_MIN_RESVPORT;
 static unsigned int xprt_max_resvport = RPC_DEF_MAX_RESVPORT;
 
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
+
 #define XS_TCP_LINGER_TO	(15U * HZ)
 static unsigned int xs_tcp_fin_timeout __read_mostly = XS_TCP_LINGER_TO;
 
@@ -75,8 +77,6 @@ static unsigned int xs_tcp_fin_timeout __read_mostly = XS_TCP_LINGER_TO;
  * someone else's file names!
  */
 
-#ifdef RPC_DEBUG
-
 static unsigned int min_slot_table_size = RPC_MIN_SLOT_TABLE;
 static unsigned int max_slot_table_size = RPC_MAX_SLOT_TABLE;
 static unsigned int max_tcp_slot_table_limit = RPC_MAX_SLOT_TABLE_LIMIT;
@@ -186,7 +186,7 @@ static struct ctl_table sunrpc_table[] = {
  */
 #define XS_IDLE_DISC_TO		(5U * 60 * HZ)
 
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # undef  RPC_DEBUG_DATA
 # define RPCDBG_FACILITY	RPCDBG_TRANS
 #endif
@@ -216,65 +216,6 @@ static inline void xs_pktdump(char *msg, u32 *packet, unsigned int count)
 }
 #endif
 
-struct sock_xprt {
-	struct rpc_xprt		xprt;
-
-	/*
-	 * Network layer
-	 */
-	struct socket *		sock;
-	struct sock *		inet;
-
-	/*
-	 * State of TCP reply receive
-	 */
-	__be32			tcp_fraghdr,
-				tcp_xid,
-				tcp_calldir;
-
-	u32			tcp_offset,
-				tcp_reclen;
-
-	unsigned long		tcp_copied,
-				tcp_flags;
-
-	/*
-	 * Connection of transports
-	 */
-	struct delayed_work	connect_worker;
-	struct sockaddr_storage	srcaddr;
-	unsigned short		srcport;
-
-	/*
-	 * UDP socket buffer size parameters
-	 */
-	size_t			rcvsize,
-				sndsize;
-
-	/*
-	 * Saved socket callback addresses
-	 */
-	void			(*old_data_ready)(struct sock *);
-	void			(*old_state_change)(struct sock *);
-	void			(*old_write_space)(struct sock *);
-	void			(*old_error_report)(struct sock *);
-};
-
-/*
- * TCP receive state flags
- */
-#define TCP_RCV_LAST_FRAG	(1UL << 0)
-#define TCP_RCV_COPY_FRAGHDR	(1UL << 1)
-#define TCP_RCV_COPY_XID	(1UL << 2)
-#define TCP_RCV_COPY_DATA	(1UL << 3)
-#define TCP_RCV_READ_CALLDIR	(1UL << 4)
-#define TCP_RCV_COPY_CALLDIR	(1UL << 5)
-
-/*
- * TCP RPC flags
- */
-#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;
@@ -686,7 +627,7 @@ process_status:
  * @xprt: transport
  *
  * Initiates a graceful shutdown of the TCP socket by calling the
- * equivalent of shutdown(SHUT_WR);
+ * equivalent of shutdown(SHUT_RDWR);
  */
 static void xs_tcp_shutdown(struct rpc_xprt *xprt)
 {
@@ -694,7 +635,7 @@ static void xs_tcp_shutdown(struct rpc_xprt *xprt)
 	struct socket *sock = transport->sock;
 
 	if (sock != NULL) {
-		kernel_sock_shutdown(sock, SHUT_WR);
+		kernel_sock_shutdown(sock, SHUT_RDWR);
 		trace_rpc_socket_shutdown(xprt, sock);
 	}
 }
@@ -777,9 +718,9 @@ static int xs_tcp_send_request(struct rpc_task *task)
 		dprintk("RPC:       sendmsg returned unrecognized error %d\n",
 			-status);
 	case -ECONNRESET:
-		xs_tcp_shutdown(xprt);
 	case -ECONNREFUSED:
 	case -ENOTCONN:
+	case -EADDRINUSE:
 	case -EPIPE:
 		clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
 	}
@@ -832,6 +773,21 @@ static void xs_restore_old_callbacks(struct sock_xprt *transport, struct sock *s
 	sk->sk_error_report = transport->old_error_report;
 }
 
+static void xs_sock_reset_connection_flags(struct rpc_xprt *xprt)
+{
+	smp_mb__before_atomic();
+	clear_bit(XPRT_CLOSE_WAIT, &xprt->state);
+	clear_bit(XPRT_CLOSING, &xprt->state);
+	smp_mb__after_atomic();
+}
+
+static void xs_sock_mark_closed(struct rpc_xprt *xprt)
+{
+	xs_sock_reset_connection_flags(xprt);
+	/* Mark transport as closed and wake up all pending tasks */
+	xprt_disconnect_done(xprt);
+}
+
 /**
  * xs_error_report - callback to handle TCP socket state errors
  * @sk: socket
@@ -851,11 +807,12 @@ static void xs_error_report(struct sock *sk)
 	err = -sk->sk_err;
 	if (err == 0)
 		goto out;
+	/* Is this a reset event? */
+	if (sk->sk_state == TCP_CLOSE)
+		xs_sock_mark_closed(xprt);
 	dprintk("RPC:       xs_error_report client %p, error=%d...\n",
 			xprt, -err);
 	trace_rpc_socket_error(xprt, sk->sk_socket, err);
-	if (test_bit(XPRT_CONNECTION_REUSE, &xprt->state))
-		goto out;
 	xprt_wake_pending_tasks(xprt, err);
  out:
 	read_unlock_bh(&sk->sk_callback_lock);
@@ -865,12 +822,11 @@ static void xs_reset_transport(struct sock_xprt *transport)
 {
 	struct socket *sock = transport->sock;
 	struct sock *sk = transport->inet;
+	struct rpc_xprt *xprt = &transport->xprt;
 
 	if (sk == NULL)
 		return;
 
-	transport->srcport = 0;
-
 	write_lock_bh(&sk->sk_callback_lock);
 	transport->inet = NULL;
 	transport->sock = NULL;
@@ -879,8 +835,9 @@ static void xs_reset_transport(struct sock_xprt *transport)
 
 	xs_restore_old_callbacks(transport, sk);
 	write_unlock_bh(&sk->sk_callback_lock);
+	xs_sock_reset_connection_flags(xprt);
 
-	trace_rpc_socket_close(&transport->xprt, sock);
+	trace_rpc_socket_close(xprt, sock);
 	sock_release(sock);
 }
 
@@ -900,27 +857,12 @@ static void xs_close(struct rpc_xprt *xprt)
 
 	dprintk("RPC:       xs_close xprt %p\n", xprt);
 
-	cancel_delayed_work_sync(&transport->connect_worker);
-
 	xs_reset_transport(transport);
 	xprt->reestablish_timeout = 0;
 
-	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_atomic();
 	xprt_disconnect_done(xprt);
 }
 
-static void xs_tcp_close(struct rpc_xprt *xprt)
-{
-	if (test_and_clear_bit(XPRT_CONNECTION_CLOSE, &xprt->state))
-		xs_close(xprt);
-	else
-		xs_tcp_shutdown(xprt);
-}
-
 static void xs_xprt_free(struct rpc_xprt *xprt)
 {
 	xs_free_peer_addresses(xprt);
@@ -1091,7 +1033,6 @@ static void xs_udp_data_ready(struct sock *sk)
  */
 static void xs_tcp_force_close(struct rpc_xprt *xprt)
 {
-	set_bit(XPRT_CONNECTION_CLOSE, &xprt->state);
 	xprt_force_disconnect(xprt);
 }
 
@@ -1415,6 +1356,7 @@ static int xs_tcp_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, uns
 
 	dprintk("RPC:       xs_tcp_data_recv started\n");
 	do {
+		trace_xs_tcp_data_recv(transport);
 		/* Read in a new fragment marker if necessary */
 		/* Can we ever really expect to get completely empty fragments? */
 		if (transport->tcp_flags & TCP_RCV_COPY_FRAGHDR) {
@@ -1439,6 +1381,7 @@ static int xs_tcp_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, uns
 		/* Skip over any trailing bytes on short reads */
 		xs_tcp_read_discard(transport, &desc);
 	} while (desc.count);
+	trace_xs_tcp_data_recv(transport);
 	dprintk("RPC:       xs_tcp_data_recv done\n");
 	return len - desc.count;
 }
@@ -1454,12 +1397,15 @@ static void xs_tcp_data_ready(struct sock *sk)
 	struct rpc_xprt *xprt;
 	read_descriptor_t rd_desc;
 	int read;
+	unsigned long total = 0;
 
 	dprintk("RPC:       xs_tcp_data_ready...\n");
 
 	read_lock_bh(&sk->sk_callback_lock);
-	if (!(xprt = xprt_from_sock(sk)))
+	if (!(xprt = xprt_from_sock(sk))) {
+		read = 0;
 		goto out;
+	}
 	/* Any data means we had a useful conversation, so
 	 * the we don't need to delay the next reconnect
 	 */
@@ -1471,59 +1417,14 @@ static void xs_tcp_data_ready(struct sock *sk)
 	do {
 		rd_desc.count = 65536;
 		read = tcp_read_sock(sk, &rd_desc, xs_tcp_data_recv);
+		if (read > 0)
+			total += read;
 	} while (read > 0);
 out:
+	trace_xs_tcp_data_ready(xprt, read, total);
 	read_unlock_bh(&sk->sk_callback_lock);
 }
 
-/*
- * Do the equivalent of linger/linger2 handling for dealing with
- * broken servers that don't close the socket in a timely
- * fashion
- */
-static void xs_tcp_schedule_linger_timeout(struct rpc_xprt *xprt,
-		unsigned long timeout)
-{
-	struct sock_xprt *transport;
-
-	if (xprt_test_and_set_connecting(xprt))
-		return;
-	set_bit(XPRT_CONNECTION_ABORT, &xprt->state);
-	transport = container_of(xprt, struct sock_xprt, xprt);
-	queue_delayed_work(rpciod_workqueue, &transport->connect_worker,
-			   timeout);
-}
-
-static void xs_tcp_cancel_linger_timeout(struct rpc_xprt *xprt)
-{
-	struct sock_xprt *transport;
-
-	transport = container_of(xprt, struct sock_xprt, xprt);
-
-	if (!test_bit(XPRT_CONNECTION_ABORT, &xprt->state) ||
-	    !cancel_delayed_work(&transport->connect_worker))
-		return;
-	clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
-	xprt_clear_connecting(xprt);
-}
-
-static void xs_sock_reset_connection_flags(struct rpc_xprt *xprt)
-{
-	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_atomic();
-}
-
-static void xs_sock_mark_closed(struct rpc_xprt *xprt)
-{
-	xs_sock_reset_connection_flags(xprt);
-	/* Mark transport as closed and wake up all pending tasks */
-	xprt_disconnect_done(xprt);
-}
-
 /**
  * xs_tcp_state_change - callback to handle TCP socket state changes
  * @sk: socket whose state has changed
@@ -1572,7 +1473,6 @@ static void xs_tcp_state_change(struct sock *sk)
 		clear_bit(XPRT_CONNECTED, &xprt->state);
 		clear_bit(XPRT_CLOSE_WAIT, &xprt->state);
 		smp_mb__after_atomic();
-		xs_tcp_schedule_linger_timeout(xprt, xs_tcp_fin_timeout);
 		break;
 	case TCP_CLOSE_WAIT:
 		/* The server initiated a shutdown of the socket */
@@ -1589,13 +1489,11 @@ static void xs_tcp_state_change(struct sock *sk)
 		break;
 	case TCP_LAST_ACK:
 		set_bit(XPRT_CLOSING, &xprt->state);
-		xs_tcp_schedule_linger_timeout(xprt, xs_tcp_fin_timeout);
 		smp_mb__before_atomic();
 		clear_bit(XPRT_CONNECTED, &xprt->state);
 		smp_mb__after_atomic();
 		break;
 	case TCP_CLOSE:
-		xs_tcp_cancel_linger_timeout(xprt);
 		xs_sock_mark_closed(xprt);
 	}
  out:
@@ -1718,6 +1616,40 @@ static unsigned short xs_get_random_port(void)
 }
 
 /**
+ * xs_set_reuseaddr_port - set the socket's port and address reuse options
+ * @sock: socket
+ *
+ * Note that this function has to be called on all sockets that share the
+ * same port, and it must be called before binding.
+ */
+static void xs_sock_set_reuseport(struct socket *sock)
+{
+	int opt = 1;
+
+	kernel_setsockopt(sock, SOL_SOCKET, SO_REUSEPORT,
+			(char *)&opt, sizeof(opt));
+}
+
+static unsigned short xs_sock_getport(struct socket *sock)
+{
+	struct sockaddr_storage buf;
+	int buflen;
+	unsigned short port = 0;
+
+	if (kernel_getsockname(sock, (struct sockaddr *)&buf, &buflen) < 0)
+		goto out;
+	switch (buf.ss_family) {
+	case AF_INET6:
+		port = ntohs(((struct sockaddr_in6 *)&buf)->sin6_port);
+		break;
+	case AF_INET:
+		port = ntohs(((struct sockaddr_in *)&buf)->sin_port);
+	}
+out:
+	return port;
+}
+
+/**
  * xs_set_port - reset the port number in the remote endpoint address
  * @xprt: generic transport
  * @port: new port number
@@ -1731,6 +1663,12 @@ static void xs_set_port(struct rpc_xprt *xprt, unsigned short port)
 	xs_update_peer_port(xprt);
 }
 
+static void xs_set_srcport(struct sock_xprt *transport, struct socket *sock)
+{
+	if (transport->srcport == 0)
+		transport->srcport = xs_sock_getport(sock);
+}
+
 static unsigned short xs_get_srcport(struct sock_xprt *transport)
 {
 	unsigned short port = transport->srcport;
@@ -1884,7 +1822,8 @@ static void xs_dummy_setup_socket(struct work_struct *work)
 }
 
 static struct socket *xs_create_sock(struct rpc_xprt *xprt,
-		struct sock_xprt *transport, int family, int type, int protocol)
+		struct sock_xprt *transport, int family, int type,
+		int protocol, bool reuseport)
 {
 	struct socket *sock;
 	int err;
@@ -1897,6 +1836,9 @@ static struct socket *xs_create_sock(struct rpc_xprt *xprt,
 	}
 	xs_reclassify_socket(family, sock);
 
+	if (reuseport)
+		xs_sock_set_reuseport(sock);
+
 	err = xs_bind(transport, sock);
 	if (err) {
 		sock_release(sock);
@@ -1954,7 +1896,6 @@ static int xs_local_setup_socket(struct sock_xprt *transport)
 	struct socket *sock;
 	int status = -EIO;
 
-	clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
 	status = __sock_create(xprt->xprt_net, AF_LOCAL,
 					SOCK_STREAM, 0, &sock, 1);
 	if (status < 0) {
@@ -2095,10 +2036,9 @@ static void xs_udp_setup_socket(struct work_struct *work)
 	struct socket *sock = transport->sock;
 	int status = -EIO;
 
-	/* Start by resetting any existing state */
-	xs_reset_transport(transport);
 	sock = xs_create_sock(xprt, transport,
-			xs_addr(xprt)->sa_family, SOCK_DGRAM, IPPROTO_UDP);
+			xs_addr(xprt)->sa_family, SOCK_DGRAM,
+			IPPROTO_UDP, false);
 	if (IS_ERR(sock))
 		goto out;
 
@@ -2112,61 +2052,11 @@ static void xs_udp_setup_socket(struct work_struct *work)
 	trace_rpc_socket_connect(xprt, sock, 0);
 	status = 0;
 out:
+	xprt_unlock_connect(xprt, transport);
 	xprt_clear_connecting(xprt);
 	xprt_wake_pending_tasks(xprt, status);
 }
 
-/*
- * We need to preserve the port number so the reply cache on the server can
- * find our cached RPC replies when we get around to reconnecting.
- */
-static void xs_abort_connection(struct sock_xprt *transport)
-{
-	int result;
-	struct sockaddr any;
-
-	dprintk("RPC:       disconnecting xprt %p to reuse port\n", transport);
-
-	/*
-	 * Disconnect the transport socket by doing a connect operation
-	 * with AF_UNSPEC.  This should return immediately...
-	 */
-	memset(&any, 0, sizeof(any));
-	any.sa_family = AF_UNSPEC;
-	result = kernel_connect(transport->sock, &any, sizeof(any), 0);
-	trace_rpc_socket_reset_connection(&transport->xprt,
-			transport->sock, result);
-	if (!result)
-		xs_sock_reset_connection_flags(&transport->xprt);
-	dprintk("RPC:       AF_UNSPEC connect return code %d\n", result);
-}
-
-static void xs_tcp_reuse_connection(struct sock_xprt *transport)
-{
-	unsigned int state = transport->inet->sk_state;
-
-	if (state == TCP_CLOSE && transport->sock->state == SS_UNCONNECTED) {
-		/* we don't need to abort the connection if the socket
-		 * hasn't undergone a shutdown
-		 */
-		if (transport->inet->sk_shutdown == 0)
-			return;
-		dprintk("RPC:       %s: TCP_CLOSEd and sk_shutdown set to %d\n",
-				__func__, transport->inet->sk_shutdown);
-	}
-	if ((1 << state) & (TCPF_ESTABLISHED|TCPF_SYN_SENT)) {
-		/* we don't need to abort the connection if the socket
-		 * hasn't undergone a shutdown
-		 */
-		if (transport->inet->sk_shutdown == 0)
-			return;
-		dprintk("RPC:       %s: ESTABLISHED/SYN_SENT "
-				"sk_shutdown set to %d\n",
-				__func__, transport->inet->sk_shutdown);
-	}
-	xs_abort_connection(transport);
-}
-
 static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 {
 	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
@@ -2200,9 +2090,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 		sk->sk_allocation = GFP_ATOMIC;
 
 		/* socket options */
-		sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
 		sock_reset_flag(sk, SOCK_LINGER);
-		tcp_sk(sk)->linger2 = 0;
 		tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF;
 
 		xprt_clear_connected(xprt);
@@ -2225,6 +2113,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 	ret = kernel_connect(sock, xs_addr(xprt), xprt->addrlen, O_NONBLOCK);
 	switch (ret) {
 	case 0:
+		xs_set_srcport(transport, sock);
 	case -EINPROGRESS:
 		/* SYN_SENT! */
 		if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO)
@@ -2251,25 +2140,13 @@ static void xs_tcp_setup_socket(struct work_struct *work)
 	int status = -EIO;
 
 	if (!sock) {
-		clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
 		sock = xs_create_sock(xprt, transport,
-				xs_addr(xprt)->sa_family, SOCK_STREAM, IPPROTO_TCP);
+				xs_addr(xprt)->sa_family, SOCK_STREAM,
+				IPPROTO_TCP, true);
 		if (IS_ERR(sock)) {
 			status = PTR_ERR(sock);
 			goto out;
 		}
-	} else {
-		int abort_and_exit;
-
-		abort_and_exit = test_and_clear_bit(XPRT_CONNECTION_ABORT,
-				&xprt->state);
-		/* "close" the socket, preserving the local port */
-		set_bit(XPRT_CONNECTION_REUSE, &xprt->state);
-		xs_tcp_reuse_connection(transport);
-		clear_bit(XPRT_CONNECTION_REUSE, &xprt->state);
-
-		if (abort_and_exit)
-			goto out_eagain;
 	}
 
 	dprintk("RPC:       worker connecting xprt %p via %s to "
@@ -2296,6 +2173,7 @@ static void xs_tcp_setup_socket(struct work_struct *work)
 	case 0:
 	case -EINPROGRESS:
 	case -EALREADY:
+		xprt_unlock_connect(xprt, transport);
 		xprt_clear_connecting(xprt);
 		return;
 	case -EINVAL:
@@ -2305,13 +2183,15 @@ static void xs_tcp_setup_socket(struct work_struct *work)
 	case -ECONNREFUSED:
 	case -ECONNRESET:
 	case -ENETUNREACH:
+	case -EADDRINUSE:
 	case -ENOBUFS:
 		/* retry with existing socket, after a delay */
+		xs_tcp_force_close(xprt);
 		goto out;
 	}
-out_eagain:
 	status = -EAGAIN;
 out:
+	xprt_unlock_connect(xprt, transport);
 	xprt_clear_connecting(xprt);
 	xprt_wake_pending_tasks(xprt, status);
 }
@@ -2334,6 +2214,11 @@ static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task)
 {
 	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
 
+	WARN_ON_ONCE(!xprt_lock_connect(xprt, task, transport));
+
+	/* Start by resetting any existing state */
+	xs_reset_transport(transport);
+
 	if (transport->sock != NULL && !RPC_IS_SOFTCONN(task)) {
 		dprintk("RPC:       xs_connect delayed xprt %p for %lu "
 				"seconds\n",
@@ -2610,7 +2495,7 @@ static struct rpc_xprt_ops xs_tcp_ops = {
 	.buf_free		= rpc_free,
 	.send_request		= xs_tcp_send_request,
 	.set_retrans_timeout	= xprt_set_retrans_timeout_def,
-	.close			= xs_tcp_close,
+	.close			= xs_tcp_shutdown,
 	.destroy		= xs_destroy,
 	.print_stats		= xs_tcp_print_stats,
 };
@@ -3042,7 +2927,7 @@ static struct xprt_class	xs_bc_tcp_transport = {
  */
 int init_socket_xprt(void)
 {
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	if (!sunrpc_table_header)
 		sunrpc_table_header = register_sysctl_table(sunrpc_table);
 #endif
@@ -3061,7 +2946,7 @@ int init_socket_xprt(void)
  */
 void cleanup_socket_xprt(void)
 {
-#ifdef RPC_DEBUG
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	if (sunrpc_table_header) {
 		unregister_sysctl_table(sunrpc_table_header);
 		sunrpc_table_header = NULL;
diff --git a/net/switchdev/Kconfig b/net/switchdev/Kconfig
new file mode 100644
index 000000000000..86a47e17cfaf
--- /dev/null
+++ b/net/switchdev/Kconfig
@@ -0,0 +1,13 @@
+#
+# Configuration for Switch device support
+#
+
+config NET_SWITCHDEV
+	bool "Switch (and switch-ish) device support (EXPERIMENTAL)"
+	depends on INET
+	---help---
+	  This module provides glue between core networking code and device
+	  drivers in order to support hardware switch chips in very generic
+	  meaning of the word "switch". This include devices supporting L2/L3 but
+	  also various flow offloading chips, including switches embedded into
+	  SR-IOV NICs.
diff --git a/net/switchdev/Makefile b/net/switchdev/Makefile
new file mode 100644
index 000000000000..5ed63ed324d0
--- /dev/null
+++ b/net/switchdev/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the Switch device API
+#
+
+obj-$(CONFIG_NET_SWITCHDEV) += switchdev.o
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
new file mode 100644
index 000000000000..055453d48668
--- /dev/null
+++ b/net/switchdev/switchdev.c
@@ -0,0 +1,404 @@
+/*
+ * net/switchdev/switchdev.c - Switch device API
+ * Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us>
+ * Copyright (c) 2014-2015 Scott Feldman <sfeldma@gmail.com>
+ *
+ * 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/types.h>
+#include <linux/init.h>
+#include <linux/mutex.h>
+#include <linux/notifier.h>
+#include <linux/netdevice.h>
+#include <net/ip_fib.h>
+#include <net/switchdev.h>
+
+/**
+ *	netdev_switch_parent_id_get - Get ID of a switch
+ *	@dev: port device
+ *	@psid: switch ID
+ *
+ *	Get ID of a switch this port is part of.
+ */
+int netdev_switch_parent_id_get(struct net_device *dev,
+				struct netdev_phys_item_id *psid)
+{
+	const struct swdev_ops *ops = dev->swdev_ops;
+
+	if (!ops || !ops->swdev_parent_id_get)
+		return -EOPNOTSUPP;
+	return ops->swdev_parent_id_get(dev, psid);
+}
+EXPORT_SYMBOL_GPL(netdev_switch_parent_id_get);
+
+/**
+ *	netdev_switch_port_stp_update - Notify switch device port of STP
+ *					state change
+ *	@dev: port device
+ *	@state: port STP state
+ *
+ *	Notify switch device port of bridge port STP state change.
+ */
+int netdev_switch_port_stp_update(struct net_device *dev, u8 state)
+{
+	const struct swdev_ops *ops = dev->swdev_ops;
+	struct net_device *lower_dev;
+	struct list_head *iter;
+	int err = -EOPNOTSUPP;
+
+	if (ops && ops->swdev_port_stp_update)
+		return ops->swdev_port_stp_update(dev, state);
+
+	netdev_for_each_lower_dev(dev, lower_dev, iter) {
+		err = netdev_switch_port_stp_update(lower_dev, state);
+		if (err && err != -EOPNOTSUPP)
+			return err;
+	}
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(netdev_switch_port_stp_update);
+
+static DEFINE_MUTEX(netdev_switch_mutex);
+static RAW_NOTIFIER_HEAD(netdev_switch_notif_chain);
+
+/**
+ *	register_netdev_switch_notifier - Register notifier
+ *	@nb: notifier_block
+ *
+ *	Register switch device notifier. This should be used by code
+ *	which needs to monitor events happening in particular device.
+ *	Return values are same as for atomic_notifier_chain_register().
+ */
+int register_netdev_switch_notifier(struct notifier_block *nb)
+{
+	int err;
+
+	mutex_lock(&netdev_switch_mutex);
+	err = raw_notifier_chain_register(&netdev_switch_notif_chain, nb);
+	mutex_unlock(&netdev_switch_mutex);
+	return err;
+}
+EXPORT_SYMBOL_GPL(register_netdev_switch_notifier);
+
+/**
+ *	unregister_netdev_switch_notifier - Unregister notifier
+ *	@nb: notifier_block
+ *
+ *	Unregister switch device notifier.
+ *	Return values are same as for atomic_notifier_chain_unregister().
+ */
+int unregister_netdev_switch_notifier(struct notifier_block *nb)
+{
+	int err;
+
+	mutex_lock(&netdev_switch_mutex);
+	err = raw_notifier_chain_unregister(&netdev_switch_notif_chain, nb);
+	mutex_unlock(&netdev_switch_mutex);
+	return err;
+}
+EXPORT_SYMBOL_GPL(unregister_netdev_switch_notifier);
+
+/**
+ *	call_netdev_switch_notifiers - Call notifiers
+ *	@val: value passed unmodified to notifier function
+ *	@dev: port device
+ *	@info: notifier information data
+ *
+ *	Call all network notifier blocks. This should be called by driver
+ *	when it needs to propagate hardware event.
+ *	Return values are same as for atomic_notifier_call_chain().
+ */
+int call_netdev_switch_notifiers(unsigned long val, struct net_device *dev,
+				 struct netdev_switch_notifier_info *info)
+{
+	int err;
+
+	info->dev = dev;
+	mutex_lock(&netdev_switch_mutex);
+	err = raw_notifier_call_chain(&netdev_switch_notif_chain, val, info);
+	mutex_unlock(&netdev_switch_mutex);
+	return err;
+}
+EXPORT_SYMBOL_GPL(call_netdev_switch_notifiers);
+
+/**
+ *	netdev_switch_port_bridge_setlink - Notify switch device port of bridge
+ *	port attributes
+ *
+ *	@dev: port device
+ *	@nlh: netlink msg with bridge port attributes
+ *	@flags: bridge setlink flags
+ *
+ *	Notify switch device port of bridge port attributes
+ */
+int netdev_switch_port_bridge_setlink(struct net_device *dev,
+				      struct nlmsghdr *nlh, u16 flags)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+
+	if (!(dev->features & NETIF_F_HW_SWITCH_OFFLOAD))
+		return 0;
+
+	if (!ops->ndo_bridge_setlink)
+		return -EOPNOTSUPP;
+
+	return ops->ndo_bridge_setlink(dev, nlh, flags);
+}
+EXPORT_SYMBOL_GPL(netdev_switch_port_bridge_setlink);
+
+/**
+ *	netdev_switch_port_bridge_dellink - Notify switch device port of bridge
+ *	port attribute delete
+ *
+ *	@dev: port device
+ *	@nlh: netlink msg with bridge port attributes
+ *	@flags: bridge setlink flags
+ *
+ *	Notify switch device port of bridge port attribute delete
+ */
+int netdev_switch_port_bridge_dellink(struct net_device *dev,
+				      struct nlmsghdr *nlh, u16 flags)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+
+	if (!(dev->features & NETIF_F_HW_SWITCH_OFFLOAD))
+		return 0;
+
+	if (!ops->ndo_bridge_dellink)
+		return -EOPNOTSUPP;
+
+	return ops->ndo_bridge_dellink(dev, nlh, flags);
+}
+EXPORT_SYMBOL_GPL(netdev_switch_port_bridge_dellink);
+
+/**
+ *	ndo_dflt_netdev_switch_port_bridge_setlink - default ndo bridge setlink
+ *						     op for master devices
+ *
+ *	@dev: port device
+ *	@nlh: netlink msg with bridge port attributes
+ *	@flags: bridge setlink flags
+ *
+ *	Notify master device slaves of bridge port attributes
+ */
+int ndo_dflt_netdev_switch_port_bridge_setlink(struct net_device *dev,
+					       struct nlmsghdr *nlh, u16 flags)
+{
+	struct net_device *lower_dev;
+	struct list_head *iter;
+	int ret = 0, err = 0;
+
+	if (!(dev->features & NETIF_F_HW_SWITCH_OFFLOAD))
+		return ret;
+
+	netdev_for_each_lower_dev(dev, lower_dev, iter) {
+		err = netdev_switch_port_bridge_setlink(lower_dev, nlh, flags);
+		if (err && err != -EOPNOTSUPP)
+			ret = err;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ndo_dflt_netdev_switch_port_bridge_setlink);
+
+/**
+ *	ndo_dflt_netdev_switch_port_bridge_dellink - default ndo bridge dellink
+ *						     op for master devices
+ *
+ *	@dev: port device
+ *	@nlh: netlink msg with bridge port attributes
+ *	@flags: bridge dellink flags
+ *
+ *	Notify master device slaves of bridge port attribute deletes
+ */
+int ndo_dflt_netdev_switch_port_bridge_dellink(struct net_device *dev,
+					       struct nlmsghdr *nlh, u16 flags)
+{
+	struct net_device *lower_dev;
+	struct list_head *iter;
+	int ret = 0, err = 0;
+
+	if (!(dev->features & NETIF_F_HW_SWITCH_OFFLOAD))
+		return ret;
+
+	netdev_for_each_lower_dev(dev, lower_dev, iter) {
+		err = netdev_switch_port_bridge_dellink(lower_dev, nlh, flags);
+		if (err && err != -EOPNOTSUPP)
+			ret = err;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ndo_dflt_netdev_switch_port_bridge_dellink);
+
+static struct net_device *netdev_switch_get_lowest_dev(struct net_device *dev)
+{
+	const struct swdev_ops *ops = dev->swdev_ops;
+	struct net_device *lower_dev;
+	struct net_device *port_dev;
+	struct list_head *iter;
+
+	/* Recusively search down until we find a sw port dev.
+	 * (A sw port dev supports swdev_parent_id_get).
+	 */
+
+	if (dev->features & NETIF_F_HW_SWITCH_OFFLOAD &&
+	    ops && ops->swdev_parent_id_get)
+		return dev;
+
+	netdev_for_each_lower_dev(dev, lower_dev, iter) {
+		port_dev = netdev_switch_get_lowest_dev(lower_dev);
+		if (port_dev)
+			return port_dev;
+	}
+
+	return NULL;
+}
+
+static struct net_device *netdev_switch_get_dev_by_nhs(struct fib_info *fi)
+{
+	struct netdev_phys_item_id psid;
+	struct netdev_phys_item_id prev_psid;
+	struct net_device *dev = NULL;
+	int nhsel;
+
+	/* For this route, all nexthop devs must be on the same switch. */
+
+	for (nhsel = 0; nhsel < fi->fib_nhs; nhsel++) {
+		const struct fib_nh *nh = &fi->fib_nh[nhsel];
+
+		if (!nh->nh_dev)
+			return NULL;
+
+		dev = netdev_switch_get_lowest_dev(nh->nh_dev);
+		if (!dev)
+			return NULL;
+
+		if (netdev_switch_parent_id_get(dev, &psid))
+			return NULL;
+
+		if (nhsel > 0) {
+			if (prev_psid.id_len != psid.id_len)
+				return NULL;
+			if (memcmp(prev_psid.id, psid.id, psid.id_len))
+				return NULL;
+		}
+
+		prev_psid = psid;
+	}
+
+	return dev;
+}
+
+/**
+ *	netdev_switch_fib_ipv4_add - Add IPv4 route entry to switch
+ *
+ *	@dst: route's IPv4 destination address
+ *	@dst_len: destination address length (prefix length)
+ *	@fi: route FIB info structure
+ *	@tos: route TOS
+ *	@type: route type
+ *	@nlflags: netlink flags passed in (NLM_F_*)
+ *	@tb_id: route table ID
+ *
+ *	Add IPv4 route entry to switch device.
+ */
+int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi,
+			       u8 tos, u8 type, u32 nlflags, u32 tb_id)
+{
+	struct net_device *dev;
+	const struct swdev_ops *ops;
+	int err = 0;
+
+	/* Don't offload route if using custom ip rules or if
+	 * IPv4 FIB offloading has been disabled completely.
+	 */
+
+#ifdef CONFIG_IP_MULTIPLE_TABLES
+	if (fi->fib_net->ipv4.fib_has_custom_rules)
+		return 0;
+#endif
+
+	if (fi->fib_net->ipv4.fib_offload_disabled)
+		return 0;
+
+	dev = netdev_switch_get_dev_by_nhs(fi);
+	if (!dev)
+		return 0;
+	ops = dev->swdev_ops;
+
+	if (ops->swdev_fib_ipv4_add) {
+		err = ops->swdev_fib_ipv4_add(dev, htonl(dst), dst_len,
+					      fi, tos, type, nlflags,
+					      tb_id);
+		if (!err)
+			fi->fib_flags |= RTNH_F_OFFLOAD;
+	}
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(netdev_switch_fib_ipv4_add);
+
+/**
+ *	netdev_switch_fib_ipv4_del - Delete IPv4 route entry from switch
+ *
+ *	@dst: route's IPv4 destination address
+ *	@dst_len: destination address length (prefix length)
+ *	@fi: route FIB info structure
+ *	@tos: route TOS
+ *	@type: route type
+ *	@tb_id: route table ID
+ *
+ *	Delete IPv4 route entry from switch device.
+ */
+int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi,
+			       u8 tos, u8 type, u32 tb_id)
+{
+	struct net_device *dev;
+	const struct swdev_ops *ops;
+	int err = 0;
+
+	if (!(fi->fib_flags & RTNH_F_OFFLOAD))
+		return 0;
+
+	dev = netdev_switch_get_dev_by_nhs(fi);
+	if (!dev)
+		return 0;
+	ops = dev->swdev_ops;
+
+	if (ops->swdev_fib_ipv4_del) {
+		err = ops->swdev_fib_ipv4_del(dev, htonl(dst), dst_len,
+					      fi, tos, type, tb_id);
+		if (!err)
+			fi->fib_flags &= ~RTNH_F_OFFLOAD;
+	}
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(netdev_switch_fib_ipv4_del);
+
+/**
+ *	netdev_switch_fib_ipv4_abort - Abort an IPv4 FIB operation
+ *
+ *	@fi: route FIB info structure
+ */
+void netdev_switch_fib_ipv4_abort(struct fib_info *fi)
+{
+	/* There was a problem installing this route to the offload
+	 * device.  For now, until we come up with more refined
+	 * policy handling, abruptly end IPv4 fib offloading for
+	 * for entire net by flushing offload device(s) of all
+	 * IPv4 routes, and mark IPv4 fib offloading broken from
+	 * this point forward.
+	 */
+
+	fib_flush_external(fi->fib_net);
+	fi->fib_net->ipv4.fib_offload_disabled = true;
+}
+EXPORT_SYMBOL_GPL(netdev_switch_fib_ipv4_abort);
diff --git a/net/tipc/Kconfig b/net/tipc/Kconfig
index c890848f9d56..c25a3a149dc4 100644
--- a/net/tipc/Kconfig
+++ b/net/tipc/Kconfig
@@ -20,21 +20,17 @@ menuconfig TIPC
 
 	  If in doubt, say N.
 
-config TIPC_PORTS
-	int "Maximum number of ports in a node"
-	depends on TIPC
-	range 127 65535
-	default "8191"
-	help
-	  Specifies how many ports can be supported by a node.
-	  Can range from 127 to 65535 ports; default is 8191.
-
-	  Setting this to a smaller value saves some memory,
-	  setting it to higher allows for more ports.
-
 config TIPC_MEDIA_IB
 	bool "InfiniBand media type support"
 	depends on TIPC && INFINIBAND_IPOIB
 	help
 	  Saying Y here will enable support for running TIPC on
 	  IP-over-InfiniBand devices.
+config TIPC_MEDIA_UDP
+	bool "IP/UDP media type support"
+	depends on TIPC
+	select NET_UDP_TUNNEL
+	help
+	  Saying Y here will enable support for running TIPC over IP/UDP
+	bool
+	default y
diff --git a/net/tipc/Makefile b/net/tipc/Makefile
index b8a13caad59a..57e460be4692 100644
--- a/net/tipc/Makefile
+++ b/net/tipc/Makefile
@@ -4,11 +4,12 @@
 
 obj-$(CONFIG_TIPC) := tipc.o
 
-tipc-y	+= addr.o bcast.o bearer.o config.o \
+tipc-y	+= addr.o bcast.o bearer.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 \
-	   socket.o log.o eth_media.o server.o
+	   netlink.o netlink_compat.o node.o socket.o eth_media.o \
+	   server.o socket.o
 
+tipc-$(CONFIG_TIPC_MEDIA_UDP)	+= udp_media.o
 tipc-$(CONFIG_TIPC_MEDIA_IB)	+= ib_media.o
 tipc-$(CONFIG_SYSCTL)		+= sysctl.o
diff --git a/net/tipc/addr.c b/net/tipc/addr.c
index 357b74b26f9e..ba7daa864d44 100644
--- a/net/tipc/addr.c
+++ b/net/tipc/addr.c
@@ -34,8 +34,58 @@
  * POSSIBILITY OF SUCH DAMAGE.
  */
 
-#include "core.h"
+#include <linux/kernel.h>
 #include "addr.h"
+#include "core.h"
+
+u32 tipc_own_addr(struct net *net)
+{
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+
+	return tn->own_addr;
+}
+
+/**
+ * in_own_cluster - test for cluster inclusion; <0.0.0> always matches
+ */
+int in_own_cluster(struct net *net, u32 addr)
+{
+	return in_own_cluster_exact(net, addr) || !addr;
+}
+
+int in_own_cluster_exact(struct net *net, u32 addr)
+{
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+
+	return !((addr ^ tn->own_addr) >> 12);
+}
+
+/**
+ * in_own_node - test for node inclusion; <0.0.0> always matches
+ */
+int in_own_node(struct net *net, u32 addr)
+{
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+
+	return (addr == tn->own_addr) || !addr;
+}
+
+/**
+ * addr_domain - convert 2-bit scope value to equivalent message lookup domain
+ *
+ * Needed when address of a named message must be looked up a second time
+ * after a network hop.
+ */
+u32 addr_domain(struct net *net, u32 sc)
+{
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+
+	if (likely(sc == TIPC_NODE_SCOPE))
+		return tn->own_addr;
+	if (sc == TIPC_CLUSTER_SCOPE)
+		return tipc_cluster_mask(tn->own_addr);
+	return tipc_zone_mask(tn->own_addr);
+}
 
 /**
  * tipc_addr_domain_valid - validates a network domain address
diff --git a/net/tipc/addr.h b/net/tipc/addr.h
index a74acf9ee804..7ba6d5c8ae40 100644
--- a/net/tipc/addr.h
+++ b/net/tipc/addr.h
@@ -37,7 +37,10 @@
 #ifndef _TIPC_ADDR_H
 #define _TIPC_ADDR_H
 
-#include "core.h"
+#include <linux/types.h>
+#include <linux/tipc.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
 
 #define TIPC_ZONE_MASK		0xff000000u
 #define TIPC_CLUSTER_MASK	0xfffff000u
@@ -52,42 +55,11 @@ static inline u32 tipc_cluster_mask(u32 addr)
 	return addr & TIPC_CLUSTER_MASK;
 }
 
-static inline int in_own_cluster_exact(u32 addr)
-{
-	return !((addr ^ tipc_own_addr) >> 12);
-}
-
-/**
- * in_own_node - test for node inclusion; <0.0.0> always matches
- */
-static inline int in_own_node(u32 addr)
-{
-	return (addr == tipc_own_addr) || !addr;
-}
-
-/**
- * in_own_cluster - test for cluster inclusion; <0.0.0> always matches
- */
-static inline int in_own_cluster(u32 addr)
-{
-	return in_own_cluster_exact(addr) || !addr;
-}
-
-/**
- * addr_domain - convert 2-bit scope value to equivalent message lookup domain
- *
- * Needed when address of a named message must be looked up a second time
- * after a network hop.
- */
-static inline u32 addr_domain(u32 sc)
-{
-	if (likely(sc == TIPC_NODE_SCOPE))
-		return tipc_own_addr;
-	if (sc == TIPC_CLUSTER_SCOPE)
-		return tipc_cluster_mask(tipc_own_addr);
-	return tipc_zone_mask(tipc_own_addr);
-}
-
+u32 tipc_own_addr(struct net *net);
+int in_own_cluster(struct net *net, u32 addr);
+int in_own_cluster_exact(struct net *net, u32 addr);
+int in_own_node(struct net *net, u32 addr);
+u32 addr_domain(struct net *net, u32 sc);
 int tipc_addr_domain_valid(u32);
 int tipc_addr_node_valid(u32 addr);
 int tipc_in_scope(u32 domain, u32 addr);
diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
index b8670bf262e2..c5cbdcb1f0b5 100644
--- a/net/tipc/bcast.c
+++ b/net/tipc/bcast.c
@@ -1,7 +1,7 @@
 /*
  * net/tipc/bcast.c: TIPC broadcast code
  *
- * Copyright (c) 2004-2006, 2014, Ericsson AB
+ * Copyright (c) 2004-2006, 2014-2015, Ericsson AB
  * Copyright (c) 2004, Intel Corporation.
  * Copyright (c) 2005, 2010-2011, Wind River Systems
  * All rights reserved.
@@ -35,77 +35,14 @@
  * POSSIBILITY OF SUCH DAMAGE.
  */
 
-#include "core.h"
-#include "link.h"
 #include "socket.h"
 #include "msg.h"
 #include "bcast.h"
 #include "name_distr.h"
+#include "core.h"
 
 #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
- * @primary: pointer to primary bearer
- * @secondary: pointer to secondary bearer
- *
- * Bearers must have same priority and same set of reachable destinations
- * to be paired.
- */
-
-struct tipc_bcbearer_pair {
-	struct tipc_bearer *primary;
-	struct tipc_bearer *secondary;
-};
-
-/**
- * struct tipc_bcbearer - bearer used by broadcast link
- * @bearer: (non-standard) broadcast bearer structure
- * @media: (non-standard) broadcast media structure
- * @bpairs: array of bearer pairs
- * @bpairs_temp: temporary array of bearer pairs used by tipc_bcbearer_sort()
- * @remains: temporary node map used by tipc_bcbearer_send()
- * @remains_new: temporary node map used tipc_bcbearer_send()
- *
- * 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 "bclink_lock".
- */
-struct tipc_bcbearer {
-	struct tipc_bearer bearer;
-	struct tipc_media media;
-	struct tipc_bcbearer_pair bpairs[MAX_BEARERS];
-	struct tipc_bcbearer_pair bpairs_temp[TIPC_MAX_LINK_PRI + 1];
-	struct tipc_node_map remains;
-	struct tipc_node_map remains_new;
-};
-
-/**
- * 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 *bcbearer;
-static struct tipc_bclink *bclink;
-static struct tipc_link *bcl;
 
 const char tipc_bclink_name[] = "broadcast-link";
 
@@ -115,28 +52,25 @@ static void tipc_nmap_diff(struct tipc_node_map *nm_a,
 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)
+static void tipc_bclink_lock(struct net *net)
 {
-	spin_lock_bh(&bclink->lock);
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+
+	spin_lock_bh(&tn->bclink->lock);
 }
 
-static void tipc_bclink_unlock(void)
+static void tipc_bclink_unlock(struct net *net)
 {
-	struct tipc_node *node = NULL;
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 
-	if (likely(!bclink->flags)) {
-		spin_unlock_bh(&bclink->lock);
-		return;
-	}
+	spin_unlock_bh(&tn->bclink->lock);
+}
 
-	if (bclink->flags & TIPC_BCLINK_RESET) {
-		bclink->flags &= ~TIPC_BCLINK_RESET;
-		node = tipc_bclink_retransmit_to();
-	}
-	spin_unlock_bh(&bclink->lock);
+void tipc_bclink_input(struct net *net)
+{
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 
-	if (node)
-		tipc_link_reset_all(node);
+	tipc_sk_mcast_rcv(net, &tn->bclink->arrvq, &tn->bclink->inputq);
 }
 
 uint  tipc_bclink_get_mtu(void)
@@ -144,11 +78,6 @@ uint  tipc_bclink_get_mtu(void)
 	return MAX_PKT_DEFAULT_MCAST;
 }
 
-void tipc_bclink_set_flags(unsigned int flags)
-{
-	bclink->flags |= flags;
-}
-
 static u32 bcbuf_acks(struct sk_buff *buf)
 {
 	return (u32)(unsigned long)TIPC_SKB_CB(buf)->handle;
@@ -164,31 +93,41 @@ static void bcbuf_decr_acks(struct sk_buff *buf)
 	bcbuf_set_acks(buf, bcbuf_acks(buf) - 1);
 }
 
-void tipc_bclink_add_node(u32 addr)
+void tipc_bclink_add_node(struct net *net, u32 addr)
 {
-	tipc_bclink_lock();
-	tipc_nmap_add(&bclink->bcast_nodes, addr);
-	tipc_bclink_unlock();
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+
+	tipc_bclink_lock(net);
+	tipc_nmap_add(&tn->bclink->bcast_nodes, addr);
+	tipc_bclink_unlock(net);
 }
 
-void tipc_bclink_remove_node(u32 addr)
+void tipc_bclink_remove_node(struct net *net, u32 addr)
 {
-	tipc_bclink_lock();
-	tipc_nmap_remove(&bclink->bcast_nodes, addr);
-	tipc_bclink_unlock();
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+
+	tipc_bclink_lock(net);
+	tipc_nmap_remove(&tn->bclink->bcast_nodes, addr);
+	tipc_bclink_unlock(net);
 }
 
-static void bclink_set_last_sent(void)
+static void bclink_set_last_sent(struct net *net)
 {
-	if (bcl->next_out)
-		bcl->fsm_msg_cnt = mod(buf_seqno(bcl->next_out) - 1);
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	struct tipc_link *bcl = tn->bcl;
+	struct sk_buff *skb = skb_peek(&bcl->backlogq);
+
+	if (skb)
+		bcl->fsm_msg_cnt = mod(buf_seqno(skb) - 1);
 	else
 		bcl->fsm_msg_cnt = mod(bcl->next_out_no - 1);
 }
 
-u32 tipc_bclink_get_last_sent(void)
+u32 tipc_bclink_get_last_sent(struct net *net)
 {
-	return bcl->fsm_msg_cnt;
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+
+	return tn->bcl->fsm_msg_cnt;
 }
 
 static void bclink_update_last_sent(struct tipc_node *node, u32 seqno)
@@ -197,15 +136,16 @@ static void bclink_update_last_sent(struct tipc_node *node, u32 seqno)
 						seqno : node->bclink.last_sent;
 }
 
-
 /**
  * tipc_bclink_retransmit_to - get most recent node to request retransmission
  *
  * Called with bclink_lock locked
  */
-struct tipc_node *tipc_bclink_retransmit_to(void)
+struct tipc_node *tipc_bclink_retransmit_to(struct net *net)
 {
-	return bclink->retransmit_to;
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+
+	return tn->bclink->retransmit_to;
 }
 
 /**
@@ -215,14 +155,17 @@ struct tipc_node *tipc_bclink_retransmit_to(void)
  *
  * Called with bclink_lock locked
  */
-static void bclink_retransmit_pkt(u32 after, u32 to)
+static void bclink_retransmit_pkt(struct tipc_net *tn, u32 after, u32 to)
 {
-	struct sk_buff *buf;
+	struct sk_buff *skb;
+	struct tipc_link *bcl = tn->bcl;
 
-	buf = bcl->first_out;
-	while (buf && less_eq(buf_seqno(buf), after))
-		buf = buf->next;
-	tipc_link_retransmit(bcl, buf, mod(to - after));
+	skb_queue_walk(&bcl->transmq, skb) {
+		if (more(buf_seqno(skb), after)) {
+			tipc_link_retransmit(bcl, skb, mod(to - after));
+			break;
+		}
+	}
 }
 
 /**
@@ -230,10 +173,11 @@ static void bclink_retransmit_pkt(u32 after, u32 to)
  *
  * Called with no locks taken
  */
-void tipc_bclink_wakeup_users(void)
+void tipc_bclink_wakeup_users(struct net *net)
 {
-	while (skb_queue_len(&bclink->link.waiting_sks))
-		tipc_sk_rcv(skb_dequeue(&bclink->link.waiting_sks));
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+
+	tipc_sk_rcv(net, &tn->bclink->link.wakeupq);
 }
 
 /**
@@ -245,14 +189,19 @@ void tipc_bclink_wakeup_users(void)
  */
 void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked)
 {
-	struct sk_buff *crs;
-	struct sk_buff *next;
+	struct sk_buff *skb, *tmp;
 	unsigned int released = 0;
+	struct net *net = n_ptr->net;
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+
+	if (unlikely(!n_ptr->bclink.recv_permitted))
+		return;
+
+	tipc_bclink_lock(net);
 
-	tipc_bclink_lock();
 	/* Bail out if tx queue is empty (no clean up is required) */
-	crs = bcl->first_out;
-	if (!crs)
+	skb = skb_peek(&tn->bcl->transmq);
+	if (!skb)
 		goto exit;
 
 	/* Determine which messages need to be acknowledged */
@@ -262,59 +211,50 @@ void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked)
 		 * acknowledge sent messages only (if other nodes still exist)
 		 * or both sent and unsent messages (otherwise)
 		 */
-		if (bclink->bcast_nodes.count)
-			acked = bcl->fsm_msg_cnt;
+		if (tn->bclink->bcast_nodes.count)
+			acked = tn->bcl->fsm_msg_cnt;
 		else
-			acked = bcl->next_out_no;
+			acked = tn->bcl->next_out_no;
 	} else {
 		/*
 		 * Bail out if specified sequence number does not correspond
 		 * to a message that has been sent and not yet acknowledged
 		 */
-		if (less(acked, buf_seqno(crs)) ||
-		    less(bcl->fsm_msg_cnt, acked) ||
+		if (less(acked, buf_seqno(skb)) ||
+		    less(tn->bcl->fsm_msg_cnt, acked) ||
 		    less_eq(acked, n_ptr->bclink.acked))
 			goto exit;
 	}
 
 	/* Skip over packets that node has previously acknowledged */
-	while (crs && less_eq(buf_seqno(crs), n_ptr->bclink.acked))
-		crs = crs->next;
+	skb_queue_walk(&tn->bcl->transmq, skb) {
+		if (more(buf_seqno(skb), n_ptr->bclink.acked))
+			break;
+	}
 
 	/* Update packets that node is now acknowledging */
-
-	while (crs && less_eq(buf_seqno(crs), acked)) {
-		next = crs->next;
-
-		if (crs != bcl->next_out)
-			bcbuf_decr_acks(crs);
-		else {
-			bcbuf_set_acks(crs, 0);
-			bcl->next_out = next;
-			bclink_set_last_sent();
-		}
-
-		if (bcbuf_acks(crs) == 0) {
-			bcl->first_out = next;
-			bcl->out_queue_size--;
-			kfree_skb(crs);
+	skb_queue_walk_from_safe(&tn->bcl->transmq, skb, tmp) {
+		if (more(buf_seqno(skb), acked))
+			break;
+		bcbuf_decr_acks(skb);
+		bclink_set_last_sent(net);
+		if (bcbuf_acks(skb) == 0) {
+			__skb_unlink(skb, &tn->bcl->transmq);
+			kfree_skb(skb);
 			released = 1;
 		}
-		crs = next;
 	}
 	n_ptr->bclink.acked = acked;
 
 	/* Try resolving broadcast link congestion, if necessary */
-
-	if (unlikely(bcl->next_out)) {
-		tipc_link_push_queue(bcl);
-		bclink_set_last_sent();
+	if (unlikely(skb_peek(&tn->bcl->backlogq))) {
+		tipc_link_push_packets(tn->bcl);
+		bclink_set_last_sent(net);
 	}
-	if (unlikely(released && !skb_queue_empty(&bcl->waiting_sks)))
+	if (unlikely(released && !skb_queue_empty(&tn->bcl->wakeupq)))
 		n_ptr->action_flags |= TIPC_WAKEUP_BCAST_USERS;
-
 exit:
-	tipc_bclink_unlock();
+	tipc_bclink_unlock(net);
 }
 
 /**
@@ -322,24 +262,24 @@ exit:
  *
  * RCU and node lock set
  */
-void tipc_bclink_update_link_state(struct tipc_node *n_ptr, u32 last_sent)
+void tipc_bclink_update_link_state(struct tipc_node *n_ptr,
+				   u32 last_sent)
 {
 	struct sk_buff *buf;
+	struct net *net = n_ptr->net;
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 
 	/* Ignore "stale" link state info */
-
 	if (less_eq(last_sent, n_ptr->bclink.last_in))
 		return;
 
 	/* Update link synchronization state; quit if in sync */
-
 	bclink_update_last_sent(n_ptr, last_sent);
 
 	if (n_ptr->bclink.last_sent == n_ptr->bclink.last_in)
 		return;
 
 	/* Update out-of-sync state; quit if loss is still unconfirmed */
-
 	if ((++n_ptr->bclink.oos_state) == 1) {
 		if (n_ptr->bclink.deferred_size < (TIPC_MIN_LINK_WIN / 2))
 			return;
@@ -347,30 +287,28 @@ void tipc_bclink_update_link_state(struct tipc_node *n_ptr, u32 last_sent)
 	}
 
 	/* Don't NACK if one has been recently sent (or seen) */
-
 	if (n_ptr->bclink.oos_state & 0x1)
 		return;
 
 	/* Send NACK */
-
 	buf = tipc_buf_acquire(INT_H_SIZE);
 	if (buf) {
 		struct tipc_msg *msg = buf_msg(buf);
+		struct sk_buff *skb = skb_peek(&n_ptr->bclink.deferdq);
+		u32 to = skb ? buf_seqno(skb) - 1 : n_ptr->bclink.last_sent;
 
-		tipc_msg_init(msg, BCAST_PROTOCOL, STATE_MSG,
+		tipc_msg_init(tn->own_addr, msg, BCAST_PROTOCOL, STATE_MSG,
 			      INT_H_SIZE, n_ptr->addr);
 		msg_set_non_seq(msg, 1);
-		msg_set_mc_netid(msg, tipc_net_id);
+		msg_set_mc_netid(msg, tn->net_id);
 		msg_set_bcast_ack(msg, n_ptr->bclink.last_in);
 		msg_set_bcgap_after(msg, n_ptr->bclink.last_in);
-		msg_set_bcgap_to(msg, n_ptr->bclink.deferred_head
-				 ? buf_seqno(n_ptr->bclink.deferred_head) - 1
-				 : n_ptr->bclink.last_sent);
-
-		tipc_bclink_lock();
-		tipc_bearer_send(MAX_BEARERS, buf, NULL);
-		bcl->stats.sent_nacks++;
-		tipc_bclink_unlock();
+		msg_set_bcgap_to(msg, to);
+
+		tipc_bclink_lock(net);
+		tipc_bearer_send(net, MAX_BEARERS, buf, NULL);
+		tn->bcl->stats.sent_nacks++;
+		tipc_bclink_unlock(net);
 		kfree_skb(buf);
 
 		n_ptr->bclink.oos_state++;
@@ -383,66 +321,75 @@ 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.
  */
-static void bclink_peek_nack(struct tipc_msg *msg)
+static void bclink_peek_nack(struct net *net, struct tipc_msg *msg)
 {
-	struct tipc_node *n_ptr = tipc_node_find(msg_destnode(msg));
+	struct tipc_node *n_ptr = tipc_node_find(net, msg_destnode(msg));
 
 	if (unlikely(!n_ptr))
 		return;
 
 	tipc_node_lock(n_ptr);
-
 	if (n_ptr->bclink.recv_permitted &&
 	    (n_ptr->bclink.last_in != n_ptr->bclink.last_sent) &&
 	    (n_ptr->bclink.last_in == msg_bcgap_after(msg)))
 		n_ptr->bclink.oos_state = 2;
-
 	tipc_node_unlock(n_ptr);
+	tipc_node_put(n_ptr);
 }
 
-/* tipc_bclink_xmit - broadcast buffer chain to all nodes in cluster
+/* tipc_bclink_xmit - deliver buffer chain to all nodes in cluster
  *                    and to identified node local sockets
- * @buf: chain of buffers containing message
+ * @net: the applicable net namespace
+ * @list: chain of buffers containing message
  * Consumes the buffer chain, except when returning -ELINKCONG
  * Returns 0 if success, otherwise errno: -ELINKCONG,-EHOSTUNREACH,-EMSGSIZE
  */
-int tipc_bclink_xmit(struct sk_buff *buf)
+int tipc_bclink_xmit(struct net *net, struct sk_buff_head *list)
 {
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	struct tipc_link *bcl = tn->bcl;
+	struct tipc_bclink *bclink = tn->bclink;
 	int rc = 0;
 	int bc = 0;
-	struct sk_buff *clbuf;
+	struct sk_buff *skb;
+	struct sk_buff_head arrvq;
+	struct sk_buff_head inputq;
 
 	/* Prepare clone of message for local node */
-	clbuf = tipc_msg_reassemble(buf);
-	if (unlikely(!clbuf)) {
-		kfree_skb_list(buf);
+	skb = tipc_msg_reassemble(list);
+	if (unlikely(!skb)) {
+		__skb_queue_purge(list);
 		return -EHOSTUNREACH;
 	}
-
-	/* Broadcast to all other nodes */
+	/* Broadcast to all nodes */
 	if (likely(bclink)) {
-		tipc_bclink_lock();
+		tipc_bclink_lock(net);
 		if (likely(bclink->bcast_nodes.count)) {
-			rc = __tipc_link_xmit(bcl, buf);
+			rc = __tipc_link_xmit(net, bcl, list);
 			if (likely(!rc)) {
-				bclink_set_last_sent();
+				u32 len = skb_queue_len(&bcl->transmq);
+
+				bclink_set_last_sent(net);
 				bcl->stats.queue_sz_counts++;
-				bcl->stats.accu_queue_sz += bcl->out_queue_size;
+				bcl->stats.accu_queue_sz += len;
 			}
 			bc = 1;
 		}
-		tipc_bclink_unlock();
+		tipc_bclink_unlock(net);
 	}
 
 	if (unlikely(!bc))
-		kfree_skb_list(buf);
+		__skb_queue_purge(list);
 
+	if (unlikely(rc)) {
+		kfree_skb(skb);
+		return rc;
+	}
 	/* Deliver message clone */
-	if (likely(!rc))
-		tipc_sk_mcast_rcv(clbuf);
-	else
-		kfree_skb(clbuf);
-
+	__skb_queue_head_init(&arrvq);
+	skb_queue_head_init(&inputq);
+	__skb_queue_tail(&arrvq, skb);
+	tipc_sk_mcast_rcv(net, &arrvq, &inputq);
 	return rc;
 }
 
@@ -453,20 +400,21 @@ int tipc_bclink_xmit(struct sk_buff *buf)
  */
 static void bclink_accept_pkt(struct tipc_node *node, u32 seqno)
 {
+	struct tipc_net *tn = net_generic(node->net, tipc_net_id);
+
 	bclink_update_last_sent(node, seqno);
 	node->bclink.last_in = seqno;
 	node->bclink.oos_state = 0;
-	bcl->stats.recv_info++;
+	tn->bcl->stats.recv_info++;
 
 	/*
 	 * Unicast an ACK periodically, ensuring that
 	 * all nodes in the cluster don't ACK at the same time
 	 */
-
-	if (((seqno - tipc_own_addr) % TIPC_MIN_LINK_WIN) == 0) {
+	if (((seqno - tn->own_addr) % TIPC_MIN_LINK_WIN) == 0) {
 		tipc_link_proto_xmit(node->active_links[node->addr & 1],
-				     STATE_MSG, 0, 0, 0, 0, 0);
-		bcl->stats.sent_acks++;
+				     STATE_MSG, 0, 0, 0, 0);
+		tn->bcl->stats.sent_acks++;
 	}
 }
 
@@ -475,20 +423,24 @@ static void bclink_accept_pkt(struct tipc_node *node, u32 seqno)
  *
  * RCU is locked, no other locks set
  */
-void tipc_bclink_rcv(struct sk_buff *buf)
+void tipc_bclink_rcv(struct net *net, struct sk_buff *buf)
 {
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	struct tipc_link *bcl = tn->bcl;
 	struct tipc_msg *msg = buf_msg(buf);
 	struct tipc_node *node;
 	u32 next_in;
 	u32 seqno;
 	int deferred = 0;
+	int pos = 0;
+	struct sk_buff *iskb;
+	struct sk_buff_head *arrvq, *inputq;
 
 	/* Screen out unwanted broadcast messages */
-
-	if (msg_mc_netid(msg) != tipc_net_id)
+	if (msg_mc_netid(msg) != tn->net_id)
 		goto exit;
 
-	node = tipc_node_find(msg_prevnode(msg));
+	node = tipc_node_find(net, msg_prevnode(msg));
 	if (unlikely(!node))
 		goto exit;
 
@@ -497,84 +449,85 @@ void tipc_bclink_rcv(struct sk_buff *buf)
 		goto unlock;
 
 	/* Handle broadcast protocol message */
-
 	if (unlikely(msg_user(msg) == BCAST_PROTOCOL)) {
 		if (msg_type(msg) != STATE_MSG)
 			goto unlock;
-		if (msg_destnode(msg) == tipc_own_addr) {
+		if (msg_destnode(msg) == tn->own_addr) {
 			tipc_bclink_acknowledge(node, msg_bcast_ack(msg));
-			tipc_node_unlock(node);
-			tipc_bclink_lock();
+			tipc_bclink_lock(net);
 			bcl->stats.recv_nacks++;
-			bclink->retransmit_to = node;
-			bclink_retransmit_pkt(msg_bcgap_after(msg),
+			tn->bclink->retransmit_to = node;
+			bclink_retransmit_pkt(tn, msg_bcgap_after(msg),
 					      msg_bcgap_to(msg));
-			tipc_bclink_unlock();
+			tipc_bclink_unlock(net);
+			tipc_node_unlock(node);
 		} else {
 			tipc_node_unlock(node);
-			bclink_peek_nack(msg);
+			bclink_peek_nack(net, msg);
 		}
+		tipc_node_put(node);
 		goto exit;
 	}
 
 	/* Handle in-sequence broadcast message */
-
 	seqno = msg_seqno(msg);
 	next_in = mod(node->bclink.last_in + 1);
+	arrvq = &tn->bclink->arrvq;
+	inputq = &tn->bclink->inputq;
 
 	if (likely(seqno == next_in)) {
 receive:
 		/* Deliver message to destination */
-
 		if (likely(msg_isdata(msg))) {
-			tipc_bclink_lock();
+			tipc_bclink_lock(net);
 			bclink_accept_pkt(node, seqno);
-			tipc_bclink_unlock();
+			spin_lock_bh(&inputq->lock);
+			__skb_queue_tail(arrvq, buf);
+			spin_unlock_bh(&inputq->lock);
+			node->action_flags |= TIPC_BCAST_MSG_EVT;
+			tipc_bclink_unlock(net);
 			tipc_node_unlock(node);
-			if (likely(msg_mcast(msg)))
-				tipc_sk_mcast_rcv(buf);
-			else
-				kfree_skb(buf);
 		} else if (msg_user(msg) == MSG_BUNDLER) {
-			tipc_bclink_lock();
+			tipc_bclink_lock(net);
 			bclink_accept_pkt(node, seqno);
 			bcl->stats.recv_bundles++;
 			bcl->stats.recv_bundled += msg_msgcnt(msg);
-			tipc_bclink_unlock();
+			pos = 0;
+			while (tipc_msg_extract(buf, &iskb, &pos)) {
+				spin_lock_bh(&inputq->lock);
+				__skb_queue_tail(arrvq, iskb);
+				spin_unlock_bh(&inputq->lock);
+			}
+			node->action_flags |= TIPC_BCAST_MSG_EVT;
+			tipc_bclink_unlock(net);
 			tipc_node_unlock(node);
-			tipc_link_bundle_rcv(buf);
 		} else if (msg_user(msg) == MSG_FRAGMENTER) {
+			tipc_bclink_lock(net);
+			bclink_accept_pkt(node, seqno);
 			tipc_buf_append(&node->bclink.reasm_buf, &buf);
-			if (unlikely(!buf && !node->bclink.reasm_buf))
+			if (unlikely(!buf && !node->bclink.reasm_buf)) {
+				tipc_bclink_unlock(net);
 				goto unlock;
-			tipc_bclink_lock();
-			bclink_accept_pkt(node, seqno);
+			}
 			bcl->stats.recv_fragments++;
 			if (buf) {
 				bcl->stats.recv_fragmented++;
 				msg = buf_msg(buf);
-				tipc_bclink_unlock();
+				tipc_bclink_unlock(net);
 				goto receive;
 			}
-			tipc_bclink_unlock();
+			tipc_bclink_unlock(net);
 			tipc_node_unlock(node);
-		} else if (msg_user(msg) == NAME_DISTRIBUTOR) {
-			tipc_bclink_lock();
-			bclink_accept_pkt(node, seqno);
-			tipc_bclink_unlock();
-			tipc_node_unlock(node);
-			tipc_named_rcv(buf);
 		} else {
-			tipc_bclink_lock();
+			tipc_bclink_lock(net);
 			bclink_accept_pkt(node, seqno);
-			tipc_bclink_unlock();
+			tipc_bclink_unlock(net);
 			tipc_node_unlock(node);
 			kfree_skb(buf);
 		}
 		buf = NULL;
 
 		/* Determine new synchronization state */
-
 		tipc_node_lock(node);
 		if (unlikely(!tipc_node_is_up(node)))
 			goto unlock;
@@ -582,48 +535,42 @@ receive:
 		if (node->bclink.last_in == node->bclink.last_sent)
 			goto unlock;
 
-		if (!node->bclink.deferred_head) {
+		if (skb_queue_empty(&node->bclink.deferdq)) {
 			node->bclink.oos_state = 1;
 			goto unlock;
 		}
 
-		msg = buf_msg(node->bclink.deferred_head);
+		msg = buf_msg(skb_peek(&node->bclink.deferdq));
 		seqno = msg_seqno(msg);
 		next_in = mod(next_in + 1);
 		if (seqno != next_in)
 			goto unlock;
 
 		/* Take in-sequence message from deferred queue & deliver it */
-
-		buf = node->bclink.deferred_head;
-		node->bclink.deferred_head = buf->next;
-		buf->next = NULL;
-		node->bclink.deferred_size--;
+		buf = __skb_dequeue(&node->bclink.deferdq);
 		goto receive;
 	}
 
 	/* Handle out-of-sequence broadcast message */
-
 	if (less(next_in, seqno)) {
-		deferred = tipc_link_defer_pkt(&node->bclink.deferred_head,
-					       &node->bclink.deferred_tail,
+		deferred = tipc_link_defer_pkt(&node->bclink.deferdq,
 					       buf);
-		node->bclink.deferred_size += deferred;
 		bclink_update_last_sent(node, seqno);
 		buf = NULL;
 	}
 
-	tipc_bclink_lock();
+	tipc_bclink_lock(net);
 
 	if (deferred)
 		bcl->stats.deferred_recv++;
 	else
 		bcl->stats.duplicates++;
 
-	tipc_bclink_unlock();
+	tipc_bclink_unlock(net);
 
 unlock:
 	tipc_node_unlock(node);
+	tipc_node_put(node);
 exit:
 	kfree_skb(buf);
 }
@@ -631,7 +578,7 @@ exit:
 u32 tipc_bclink_acks_missing(struct tipc_node *n_ptr)
 {
 	return (n_ptr->bclink.recv_permitted &&
-		(tipc_bclink_get_last_sent() != n_ptr->bclink.acked));
+		(tipc_bclink_get_last_sent(n_ptr->net) != n_ptr->bclink.acked));
 }
 
 
@@ -644,11 +591,15 @@ u32 tipc_bclink_acks_missing(struct tipc_node *n_ptr)
  * Returns 0 (packet sent successfully) under all circumstances,
  * since the broadcast link's pseudo-bearer never blocks
  */
-static int tipc_bcbearer_send(struct sk_buff *buf, struct tipc_bearer *unused1,
+static int tipc_bcbearer_send(struct net *net, struct sk_buff *buf,
+			      struct tipc_bearer *unused1,
 			      struct tipc_media_addr *unused2)
 {
 	int bp_index;
 	struct tipc_msg *msg = buf_msg(buf);
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	struct tipc_bcbearer *bcbearer = tn->bcbearer;
+	struct tipc_bclink *bclink = tn->bclink;
 
 	/* Prepare broadcast link message for reliable transmission,
 	 * if first time trying to send it;
@@ -658,9 +609,8 @@ static int tipc_bcbearer_send(struct sk_buff *buf, struct tipc_bearer *unused1,
 	if (likely(!msg_non_seq(buf_msg(buf)))) {
 		bcbuf_set_acks(buf, bclink->bcast_nodes.count);
 		msg_set_non_seq(msg, 1);
-		msg_set_mc_netid(msg, tipc_net_id);
-		bcl->stats.sent_info++;
-
+		msg_set_mc_netid(msg, tn->net_id);
+		tn->bcl->stats.sent_info++;
 		if (WARN_ON(!bclink->bcast_nodes.count)) {
 			dump_stack();
 			return 0;
@@ -688,13 +638,14 @@ 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->identity, buf, &b->bcast_addr);
+			tipc_bearer_send(net, b->identity, buf, &b->bcast_addr);
 		} else {
 			/* Avoid concurrent buffer access */
 			tbuf = pskb_copy_for_clone(buf, GFP_ATOMIC);
 			if (!tbuf)
 				break;
-			tipc_bearer_send(b->identity, tbuf, &b->bcast_addr);
+			tipc_bearer_send(net, b->identity, tbuf,
+					 &b->bcast_addr);
 			kfree_skb(tbuf); /* Bearer keeps a clone */
 		}
 		if (bcbearer->remains_new.count == 0)
@@ -709,15 +660,18 @@ 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(struct tipc_node_map *nm_ptr, u32 node, bool action)
+void tipc_bcbearer_sort(struct net *net, struct tipc_node_map *nm_ptr,
+			u32 node, bool action)
 {
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	struct tipc_bcbearer *bcbearer = tn->bcbearer;
 	struct tipc_bcbearer_pair *bp_temp = bcbearer->bpairs_temp;
 	struct tipc_bcbearer_pair *bp_curr;
 	struct tipc_bearer *b;
 	int b_index;
 	int pri;
 
-	tipc_bclink_lock();
+	tipc_bclink_lock(net);
 
 	if (action)
 		tipc_nmap_add(nm_ptr, node);
@@ -729,7 +683,7 @@ void tipc_bcbearer_sort(struct tipc_node_map *nm_ptr, u32 node, bool action)
 
 	rcu_read_lock();
 	for (b_index = 0; b_index < MAX_BEARERS; b_index++) {
-		b = rcu_dereference_rtnl(bearer_list[b_index]);
+		b = rcu_dereference_rtnl(tn->bearer_list[b_index]);
 		if (!b || !b->nodes.count)
 			continue;
 
@@ -764,77 +718,161 @@ void tipc_bcbearer_sort(struct tipc_node_map *nm_ptr, u32 node, bool action)
 		bp_curr++;
 	}
 
-	tipc_bclink_unlock();
+	tipc_bclink_unlock(net);
 }
 
+static int __tipc_nl_add_bc_link_stat(struct sk_buff *skb,
+				      struct tipc_stats *stats)
+{
+	int i;
+	struct nlattr *nest;
+
+	struct nla_map {
+		__u32 key;
+		__u32 val;
+	};
+
+	struct nla_map map[] = {
+		{TIPC_NLA_STATS_RX_INFO, stats->recv_info},
+		{TIPC_NLA_STATS_RX_FRAGMENTS, stats->recv_fragments},
+		{TIPC_NLA_STATS_RX_FRAGMENTED, stats->recv_fragmented},
+		{TIPC_NLA_STATS_RX_BUNDLES, stats->recv_bundles},
+		{TIPC_NLA_STATS_RX_BUNDLED, stats->recv_bundled},
+		{TIPC_NLA_STATS_TX_INFO, stats->sent_info},
+		{TIPC_NLA_STATS_TX_FRAGMENTS, stats->sent_fragments},
+		{TIPC_NLA_STATS_TX_FRAGMENTED, stats->sent_fragmented},
+		{TIPC_NLA_STATS_TX_BUNDLES, stats->sent_bundles},
+		{TIPC_NLA_STATS_TX_BUNDLED, stats->sent_bundled},
+		{TIPC_NLA_STATS_RX_NACKS, stats->recv_nacks},
+		{TIPC_NLA_STATS_RX_DEFERRED, stats->deferred_recv},
+		{TIPC_NLA_STATS_TX_NACKS, stats->sent_nacks},
+		{TIPC_NLA_STATS_TX_ACKS, stats->sent_acks},
+		{TIPC_NLA_STATS_RETRANSMITTED, stats->retransmitted},
+		{TIPC_NLA_STATS_DUPLICATES, stats->duplicates},
+		{TIPC_NLA_STATS_LINK_CONGS, stats->link_congs},
+		{TIPC_NLA_STATS_MAX_QUEUE, stats->max_queue_sz},
+		{TIPC_NLA_STATS_AVG_QUEUE, stats->queue_sz_counts ?
+			(stats->accu_queue_sz / stats->queue_sz_counts) : 0}
+	};
+
+	nest = nla_nest_start(skb, TIPC_NLA_LINK_STATS);
+	if (!nest)
+		return -EMSGSIZE;
+
+	for (i = 0; i <  ARRAY_SIZE(map); i++)
+		if (nla_put_u32(skb, map[i].key, map[i].val))
+			goto msg_full;
+
+	nla_nest_end(skb, nest);
+
+	return 0;
+msg_full:
+	nla_nest_cancel(skb, nest);
 
-int tipc_bclink_stats(char *buf, const u32 buf_size)
+	return -EMSGSIZE;
+}
+
+int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg)
 {
-	int ret;
-	struct tipc_stats *s;
+	int err;
+	void *hdr;
+	struct nlattr *attrs;
+	struct nlattr *prop;
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	struct tipc_link *bcl = tn->bcl;
 
 	if (!bcl)
 		return 0;
 
-	tipc_bclink_lock();
-
-	s = &bcl->stats;
-
-	ret = tipc_snprintf(buf, buf_size, "Link <%s>\n"
-			    "  Window:%u packets\n",
-			    bcl->name, bcl->queue_limit[0]);
-	ret += tipc_snprintf(buf + ret, buf_size - ret,
-			     "  RX packets:%u fragments:%u/%u bundles:%u/%u\n",
-			     s->recv_info, s->recv_fragments,
-			     s->recv_fragmented, s->recv_bundles,
-			     s->recv_bundled);
-	ret += tipc_snprintf(buf + ret, buf_size - ret,
-			     "  TX packets:%u fragments:%u/%u bundles:%u/%u\n",
-			     s->sent_info, s->sent_fragments,
-			     s->sent_fragmented, s->sent_bundles,
-			     s->sent_bundled);
-	ret += tipc_snprintf(buf + ret, buf_size - ret,
-			     "  RX naks:%u defs:%u dups:%u\n",
-			     s->recv_nacks, s->deferred_recv, s->duplicates);
-	ret += tipc_snprintf(buf + ret, buf_size - ret,
-			     "  TX naks:%u acks:%u dups:%u\n",
-			     s->sent_nacks, s->sent_acks, s->retransmitted);
-	ret += tipc_snprintf(buf + ret, buf_size - ret,
-			     "  Congestion link:%u  Send queue max:%u avg:%u\n",
-			     s->link_congs, s->max_queue_sz,
-			     s->queue_sz_counts ?
-			     (s->accu_queue_sz / s->queue_sz_counts) : 0);
-
-	tipc_bclink_unlock();
-	return ret;
-}
-
-int tipc_bclink_reset_stats(void)
+	tipc_bclink_lock(net);
+
+	hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family,
+			  NLM_F_MULTI, TIPC_NL_LINK_GET);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	attrs = nla_nest_start(msg->skb, TIPC_NLA_LINK);
+	if (!attrs)
+		goto msg_full;
+
+	/* The broadcast link is always up */
+	if (nla_put_flag(msg->skb, TIPC_NLA_LINK_UP))
+		goto attr_msg_full;
+
+	if (nla_put_flag(msg->skb, TIPC_NLA_LINK_BROADCAST))
+		goto attr_msg_full;
+	if (nla_put_string(msg->skb, TIPC_NLA_LINK_NAME, bcl->name))
+		goto attr_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_LINK_RX, bcl->next_in_no))
+		goto attr_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, bcl->next_out_no))
+		goto attr_msg_full;
+
+	prop = nla_nest_start(msg->skb, TIPC_NLA_LINK_PROP);
+	if (!prop)
+		goto attr_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bcl->window))
+		goto prop_msg_full;
+	nla_nest_end(msg->skb, prop);
+
+	err = __tipc_nl_add_bc_link_stat(msg->skb, &bcl->stats);
+	if (err)
+		goto attr_msg_full;
+
+	tipc_bclink_unlock(net);
+	nla_nest_end(msg->skb, attrs);
+	genlmsg_end(msg->skb, hdr);
+
+	return 0;
+
+prop_msg_full:
+	nla_nest_cancel(msg->skb, prop);
+attr_msg_full:
+	nla_nest_cancel(msg->skb, attrs);
+msg_full:
+	tipc_bclink_unlock(net);
+	genlmsg_cancel(msg->skb, hdr);
+
+	return -EMSGSIZE;
+}
+
+int tipc_bclink_reset_stats(struct net *net)
 {
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	struct tipc_link *bcl = tn->bcl;
+
 	if (!bcl)
 		return -ENOPROTOOPT;
 
-	tipc_bclink_lock();
+	tipc_bclink_lock(net);
 	memset(&bcl->stats, 0, sizeof(bcl->stats));
-	tipc_bclink_unlock();
+	tipc_bclink_unlock(net);
 	return 0;
 }
 
-int tipc_bclink_set_queue_limits(u32 limit)
+int tipc_bclink_set_queue_limits(struct net *net, u32 limit)
 {
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	struct tipc_link *bcl = tn->bcl;
+
 	if (!bcl)
 		return -ENOPROTOOPT;
 	if ((limit < TIPC_MIN_LINK_WIN) || (limit > TIPC_MAX_LINK_WIN))
 		return -EINVAL;
 
-	tipc_bclink_lock();
+	tipc_bclink_lock(net);
 	tipc_link_set_queue_limits(bcl, limit);
-	tipc_bclink_unlock();
+	tipc_bclink_unlock(net);
 	return 0;
 }
 
-int tipc_bclink_init(void)
+int tipc_bclink_init(struct net *net)
 {
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	struct tipc_bcbearer *bcbearer;
+	struct tipc_bclink *bclink;
+	struct tipc_link *bcl;
+
 	bcbearer = kzalloc(sizeof(*bcbearer), GFP_ATOMIC);
 	if (!bcbearer)
 		return -ENOMEM;
@@ -851,30 +889,42 @@ int tipc_bclink_init(void)
 	sprintf(bcbearer->media.name, "tipc-broadcast");
 
 	spin_lock_init(&bclink->lock);
-	__skb_queue_head_init(&bcl->waiting_sks);
+	__skb_queue_head_init(&bcl->transmq);
+	__skb_queue_head_init(&bcl->backlogq);
+	__skb_queue_head_init(&bcl->deferdq);
+	skb_queue_head_init(&bcl->wakeupq);
 	bcl->next_out_no = 1;
 	spin_lock_init(&bclink->node.lock);
-	__skb_queue_head_init(&bclink->node.waiting_sks);
+	__skb_queue_head_init(&bclink->arrvq);
+	skb_queue_head_init(&bclink->inputq);
 	bcl->owner = &bclink->node;
-	bcl->max_pkt = MAX_PKT_DEFAULT_MCAST;
+	bcl->owner->net = net;
+	bcl->mtu = MAX_PKT_DEFAULT_MCAST;
 	tipc_link_set_queue_limits(bcl, BCLINK_WIN_DEFAULT);
 	bcl->bearer_id = MAX_BEARERS;
-	rcu_assign_pointer(bearer_list[MAX_BEARERS], &bcbearer->bearer);
+	rcu_assign_pointer(tn->bearer_list[MAX_BEARERS], &bcbearer->bearer);
 	bcl->state = WORKING_WORKING;
+	bcl->pmsg = (struct tipc_msg *)&bcl->proto_msg;
+	msg_set_prevnode(bcl->pmsg, tn->own_addr);
 	strlcpy(bcl->name, tipc_bclink_name, TIPC_MAX_LINK_NAME);
+	tn->bcbearer = bcbearer;
+	tn->bclink = bclink;
+	tn->bcl = bcl;
 	return 0;
 }
 
-void tipc_bclink_stop(void)
+void tipc_bclink_stop(struct net *net)
 {
-	tipc_bclink_lock();
-	tipc_link_purge_queues(bcl);
-	tipc_bclink_unlock();
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 
-	RCU_INIT_POINTER(bearer_list[BCBEARER], NULL);
+	tipc_bclink_lock(net);
+	tipc_link_purge_queues(tn->bcl);
+	tipc_bclink_unlock(net);
+
+	RCU_INIT_POINTER(tn->bearer_list[BCBEARER], NULL);
 	synchronize_net();
-	kfree(bcbearer);
-	kfree(bclink);
+	kfree(tn->bcbearer);
+	kfree(tn->bclink);
 }
 
 /**
@@ -934,50 +984,3 @@ static void tipc_nmap_diff(struct tipc_node_map *nm_a,
 		}
 	}
 }
-
-/**
- * tipc_port_list_add - add a port to a port list, ensuring no duplicates
- */
-void tipc_port_list_add(struct tipc_port_list *pl_ptr, u32 port)
-{
-	struct tipc_port_list *item = pl_ptr;
-	int i;
-	int item_sz = PLSIZE;
-	int cnt = pl_ptr->count;
-
-	for (; ; cnt -= item_sz, item = item->next) {
-		if (cnt < PLSIZE)
-			item_sz = cnt;
-		for (i = 0; i < item_sz; i++)
-			if (item->ports[i] == port)
-				return;
-		if (i < PLSIZE) {
-			item->ports[i] = port;
-			pl_ptr->count++;
-			return;
-		}
-		if (!item->next) {
-			item->next = kmalloc(sizeof(*item), GFP_ATOMIC);
-			if (!item->next) {
-				pr_warn("Incomplete multicast delivery, no memory\n");
-				return;
-			}
-			item->next->next = NULL;
-		}
-	}
-}
-
-/**
- * tipc_port_list_free - free dynamically created entries in port_list chain
- *
- */
-void tipc_port_list_free(struct tipc_port_list *pl_ptr)
-{
-	struct tipc_port_list *item;
-	struct tipc_port_list *next;
-
-	for (item = pl_ptr->next; item; item = next) {
-		next = item->next;
-		kfree(item);
-	}
-}
diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h
index e7b0f85a82bc..4bdc12277d33 100644
--- a/net/tipc/bcast.h
+++ b/net/tipc/bcast.h
@@ -1,7 +1,7 @@
 /*
  * net/tipc/bcast.h: Include file for TIPC broadcast code
  *
- * Copyright (c) 2003-2006, 2014, Ericsson AB
+ * Copyright (c) 2003-2006, 2014-2015, Ericsson AB
  * Copyright (c) 2005, 2010-2011, Wind River Systems
  * All rights reserved.
  *
@@ -37,37 +37,70 @@
 #ifndef _TIPC_BCAST_H
 #define _TIPC_BCAST_H
 
-#define MAX_NODES 4096
-#define WSIZE 32
-#define TIPC_BCLINK_RESET 1
+#include <linux/tipc_config.h>
+#include "link.h"
+#include "node.h"
 
 /**
- * struct tipc_node_map - set of node identifiers
- * @count: # of nodes in set
- * @map: bitmap of node identifiers that are in the set
+ * struct tipc_bcbearer_pair - a pair of bearers used by broadcast link
+ * @primary: pointer to primary bearer
+ * @secondary: pointer to secondary bearer
+ *
+ * Bearers must have same priority and same set of reachable destinations
+ * to be paired.
  */
-struct tipc_node_map {
-	u32 count;
-	u32 map[MAX_NODES / WSIZE];
+
+struct tipc_bcbearer_pair {
+	struct tipc_bearer *primary;
+	struct tipc_bearer *secondary;
 };
 
-#define PLSIZE 32
+#define	BCBEARER		MAX_BEARERS
 
 /**
- * struct tipc_port_list - set of node local destination ports
- * @count: # of ports in set (only valid for first entry in list)
- * @next: pointer to next entry in list
- * @ports: array of port references
+ * struct tipc_bcbearer - bearer used by broadcast link
+ * @bearer: (non-standard) broadcast bearer structure
+ * @media: (non-standard) broadcast media structure
+ * @bpairs: array of bearer pairs
+ * @bpairs_temp: temporary array of bearer pairs used by tipc_bcbearer_sort()
+ * @remains: temporary node map used by tipc_bcbearer_send()
+ * @remains_new: temporary node map used tipc_bcbearer_send()
+ *
+ * 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 "bclink_lock".
  */
-struct tipc_port_list {
-	int count;
-	struct tipc_port_list *next;
-	u32 ports[PLSIZE];
+struct tipc_bcbearer {
+	struct tipc_bearer bearer;
+	struct tipc_media media;
+	struct tipc_bcbearer_pair bpairs[MAX_BEARERS];
+	struct tipc_bcbearer_pair bpairs_temp[TIPC_MAX_LINK_PRI + 1];
+	struct tipc_node_map remains;
+	struct tipc_node_map remains_new;
 };
 
+/**
+ * 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
+ * @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;
+	struct sk_buff_head arrvq;
+	struct sk_buff_head inputq;
+	struct tipc_node_map bcast_nodes;
+	struct tipc_node *retransmit_to;
+};
 
 struct tipc_node;
-
 extern const char tipc_bclink_name[];
 
 /**
@@ -79,25 +112,25 @@ static inline int tipc_nmap_equal(struct tipc_node_map *nm_a,
 	return !memcmp(nm_a, nm_b, sizeof(*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);
-
-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);
+int tipc_bclink_init(struct net *net);
+void tipc_bclink_stop(struct net *net);
+void tipc_bclink_add_node(struct net *net, u32 addr);
+void tipc_bclink_remove_node(struct net *net, u32 addr);
+struct tipc_node *tipc_bclink_retransmit_to(struct net *tn);
 void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked);
-void tipc_bclink_rcv(struct sk_buff *buf);
-u32  tipc_bclink_get_last_sent(void);
+void tipc_bclink_rcv(struct net *net, struct sk_buff *buf);
+u32  tipc_bclink_get_last_sent(struct net *net);
 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(struct tipc_node_map *nm_ptr, u32 node, bool action);
+void tipc_bclink_update_link_state(struct tipc_node *node,
+				   u32 last_sent);
+int  tipc_bclink_reset_stats(struct net *net);
+int  tipc_bclink_set_queue_limits(struct net *net, u32 limit);
+void tipc_bcbearer_sort(struct net *net, struct tipc_node_map *nm_ptr,
+			u32 node, bool action);
 uint  tipc_bclink_get_mtu(void);
-int tipc_bclink_xmit(struct sk_buff *buf);
-void tipc_bclink_wakeup_users(void);
+int tipc_bclink_xmit(struct net *net, struct sk_buff_head *list);
+void tipc_bclink_wakeup_users(struct net *net);
+int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg);
+void tipc_bclink_input(struct net *net);
+
 #endif
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 264474394f9f..70e3dacbf84a 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -1,7 +1,7 @@
 /*
  * net/tipc/bearer.c: TIPC bearer code
  *
- * Copyright (c) 1996-2006, 2013, Ericsson AB
+ * Copyright (c) 1996-2006, 2013-2014, Ericsson AB
  * Copyright (c) 2004-2006, 2010-2013, Wind River Systems
  * All rights reserved.
  *
@@ -34,10 +34,12 @@
  * POSSIBILITY OF SUCH DAMAGE.
  */
 
+#include <net/sock.h>
 #include "core.h"
-#include "config.h"
 #include "bearer.h"
+#include "link.h"
 #include "discover.h"
+#include "bcast.h"
 
 #define MAX_ADDR_STR 60
 
@@ -46,12 +48,31 @@ static struct tipc_media * const media_info_array[] = {
 #ifdef CONFIG_TIPC_MEDIA_IB
 	&ib_media_info,
 #endif
+#ifdef CONFIG_TIPC_MEDIA_UDP
+	&udp_media_info,
+#endif
 	NULL
 };
 
-struct tipc_bearer __rcu *bearer_list[MAX_BEARERS + 1];
+static const struct nla_policy
+tipc_nl_bearer_policy[TIPC_NLA_BEARER_MAX + 1]	= {
+	[TIPC_NLA_BEARER_UNSPEC]		= { .type = NLA_UNSPEC },
+	[TIPC_NLA_BEARER_NAME] = {
+		.type = NLA_STRING,
+		.len = TIPC_MAX_BEARER_NAME
+	},
+	[TIPC_NLA_BEARER_PROP]			= { .type = NLA_NESTED },
+	[TIPC_NLA_BEARER_DOMAIN]		= { .type = NLA_U32 }
+};
+
+static const struct nla_policy tipc_nl_media_policy[TIPC_NLA_MEDIA_MAX + 1] = {
+	[TIPC_NLA_MEDIA_UNSPEC]		= { .type = NLA_UNSPEC },
+	[TIPC_NLA_MEDIA_NAME]		= { .type = NLA_STRING },
+	[TIPC_NLA_MEDIA_PROP]		= { .type = NLA_NESTED }
+};
 
-static void bearer_disable(struct tipc_bearer *b_ptr, bool shutting_down);
+static void bearer_disable(struct net *net, struct tipc_bearer *b_ptr,
+			   bool shutting_down);
 
 /**
  * tipc_media_find - locates specified media object by name
@@ -93,38 +114,18 @@ void tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a)
 	m_ptr = media_find_id(a->media_id);
 
 	if (m_ptr && !m_ptr->addr2str(a, addr_str, sizeof(addr_str)))
-		ret = tipc_snprintf(buf, len, "%s(%s)", m_ptr->name, addr_str);
+		ret = scnprintf(buf, len, "%s(%s)", m_ptr->name, addr_str);
 	else {
 		u32 i;
 
-		ret = tipc_snprintf(buf, len, "UNKNOWN(%u)", a->media_id);
+		ret = scnprintf(buf, len, "UNKNOWN(%u)", a->media_id);
 		for (i = 0; i < sizeof(a->value); i++)
-			ret += tipc_snprintf(buf - ret, len + ret,
+			ret += scnprintf(buf - ret, len + ret,
 					    "-%02x", a->value[i]);
 	}
 }
 
 /**
- * tipc_media_get_names - record names of registered media in buffer
- */
-struct sk_buff *tipc_media_get_names(void)
-{
-	struct sk_buff *buf;
-	int i;
-
-	buf = tipc_cfg_reply_alloc(MAX_MEDIA * TLV_SPACE(TIPC_MAX_MEDIA_NAME));
-	if (!buf)
-		return NULL;
-
-	for (i = 0; media_info_array[i] != NULL; i++) {
-		tipc_cfg_append_tlv(buf, TIPC_TLV_MEDIA_NAME,
-				    media_info_array[i]->name,
-				    strlen(media_info_array[i]->name) + 1);
-	}
-	return buf;
-}
-
-/**
  * bearer_name_validate - validate & (optionally) deconstruct bearer name
  * @name: ptr to bearer name string
  * @name_parts: ptr to area for bearer name components (or NULL if not needed)
@@ -172,68 +173,43 @@ static int bearer_name_validate(const char *name,
 /**
  * tipc_bearer_find - locates bearer object with matching bearer name
  */
-struct tipc_bearer *tipc_bearer_find(const char *name)
+struct tipc_bearer *tipc_bearer_find(struct net *net, const char *name)
 {
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	struct tipc_bearer *b_ptr;
 	u32 i;
 
 	for (i = 0; i < MAX_BEARERS; i++) {
-		b_ptr = rtnl_dereference(bearer_list[i]);
+		b_ptr = rtnl_dereference(tn->bearer_list[i]);
 		if (b_ptr && (!strcmp(b_ptr->name, name)))
 			return b_ptr;
 	}
 	return NULL;
 }
 
-/**
- * tipc_bearer_get_names - record names of bearers in buffer
- */
-struct sk_buff *tipc_bearer_get_names(void)
-{
-	struct sk_buff *buf;
-	struct tipc_bearer *b;
-	int i, j;
-
-	buf = tipc_cfg_reply_alloc(MAX_BEARERS * TLV_SPACE(TIPC_MAX_BEARER_NAME));
-	if (!buf)
-		return NULL;
-
-	for (i = 0; media_info_array[i] != NULL; i++) {
-		for (j = 0; j < MAX_BEARERS; j++) {
-			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->name,
-						    strlen(b->name) + 1);
-			}
-		}
-	}
-	return buf;
-}
-
-void tipc_bearer_add_dest(u32 bearer_id, u32 dest)
+void tipc_bearer_add_dest(struct net *net, u32 bearer_id, u32 dest)
 {
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	struct tipc_bearer *b_ptr;
 
 	rcu_read_lock();
-	b_ptr = rcu_dereference_rtnl(bearer_list[bearer_id]);
+	b_ptr = rcu_dereference_rtnl(tn->bearer_list[bearer_id]);
 	if (b_ptr) {
-		tipc_bcbearer_sort(&b_ptr->nodes, dest, true);
+		tipc_bcbearer_sort(net, &b_ptr->nodes, dest, true);
 		tipc_disc_add_dest(b_ptr->link_req);
 	}
 	rcu_read_unlock();
 }
 
-void tipc_bearer_remove_dest(u32 bearer_id, u32 dest)
+void tipc_bearer_remove_dest(struct net *net, u32 bearer_id, u32 dest)
 {
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	struct tipc_bearer *b_ptr;
 
 	rcu_read_lock();
-	b_ptr = rcu_dereference_rtnl(bearer_list[bearer_id]);
+	b_ptr = rcu_dereference_rtnl(tn->bearer_list[bearer_id]);
 	if (b_ptr) {
-		tipc_bcbearer_sort(&b_ptr->nodes, dest, false);
+		tipc_bcbearer_sort(net, &b_ptr->nodes, dest, false);
 		tipc_disc_remove_dest(b_ptr->link_req);
 	}
 	rcu_read_unlock();
@@ -242,8 +218,11 @@ void tipc_bearer_remove_dest(u32 bearer_id, u32 dest)
 /**
  * tipc_enable_bearer - enable bearer with the given name
  */
-int tipc_enable_bearer(const char *name, u32 disc_domain, u32 priority)
+static int tipc_enable_bearer(struct net *net, const char *name,
+			      u32 disc_domain, u32 priority,
+			      struct nlattr *attr[])
 {
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	struct tipc_bearer *b_ptr;
 	struct tipc_media *m_ptr;
 	struct tipc_bearer_names b_names;
@@ -253,7 +232,7 @@ int tipc_enable_bearer(const char *name, u32 disc_domain, u32 priority)
 	u32 i;
 	int res = -EINVAL;
 
-	if (!tipc_own_addr) {
+	if (!tn->own_addr) {
 		pr_warn("Bearer <%s> rejected, not supported in standalone mode\n",
 			name);
 		return -ENOPROTOOPT;
@@ -263,11 +242,11 @@ int tipc_enable_bearer(const char *name, u32 disc_domain, u32 priority)
 		return -EINVAL;
 	}
 	if (tipc_addr_domain_valid(disc_domain) &&
-	    (disc_domain != tipc_own_addr)) {
-		if (tipc_in_scope(disc_domain, tipc_own_addr)) {
-			disc_domain = tipc_own_addr & TIPC_CLUSTER_MASK;
+	    (disc_domain != tn->own_addr)) {
+		if (tipc_in_scope(disc_domain, tn->own_addr)) {
+			disc_domain = tn->own_addr & TIPC_CLUSTER_MASK;
 			res = 0;   /* accept any node in own cluster */
-		} else if (in_own_cluster_exact(disc_domain))
+		} else if (in_own_cluster_exact(net, disc_domain))
 			res = 0;   /* accept specified node in own cluster */
 	}
 	if (res) {
@@ -295,7 +274,7 @@ restart:
 	bearer_id = MAX_BEARERS;
 	with_this_prio = 1;
 	for (i = MAX_BEARERS; i-- != 0; ) {
-		b_ptr = rtnl_dereference(bearer_list[i]);
+		b_ptr = rtnl_dereference(tn->bearer_list[i]);
 		if (!b_ptr) {
 			bearer_id = i;
 			continue;
@@ -329,7 +308,7 @@ restart:
 
 	strcpy(b_ptr->name, name);
 	b_ptr->media = m_ptr;
-	res = m_ptr->enable_media(b_ptr);
+	res = m_ptr->enable_media(net, b_ptr, attr);
 	if (res) {
 		pr_warn("Bearer <%s> rejected, enable failure (%d)\n",
 			name, -res);
@@ -343,15 +322,15 @@ restart:
 	b_ptr->net_plane = bearer_id + 'A';
 	b_ptr->priority = priority;
 
-	res = tipc_disc_create(b_ptr, &b_ptr->bcast_addr);
+	res = tipc_disc_create(net, b_ptr, &b_ptr->bcast_addr);
 	if (res) {
-		bearer_disable(b_ptr, false);
+		bearer_disable(net, b_ptr, false);
 		pr_warn("Bearer <%s> rejected, discovery object creation failed\n",
 			name);
 		return -EINVAL;
 	}
 
-	rcu_assign_pointer(bearer_list[bearer_id], b_ptr);
+	rcu_assign_pointer(tn->bearer_list[bearer_id], b_ptr);
 
 	pr_info("Enabled bearer <%s>, discovery domain %s, priority %u\n",
 		name,
@@ -362,11 +341,11 @@ restart:
 /**
  * tipc_reset_bearer - Reset all links established over this bearer
  */
-static int tipc_reset_bearer(struct tipc_bearer *b_ptr)
+static int tipc_reset_bearer(struct net *net, struct tipc_bearer *b_ptr)
 {
 	pr_info("Resetting bearer <%s>\n", b_ptr->name);
-	tipc_link_reset_list(b_ptr->identity);
-	tipc_disc_reset(b_ptr);
+	tipc_link_reset_list(net, b_ptr->identity);
+	tipc_disc_reset(net, b_ptr);
 	return 0;
 }
 
@@ -375,49 +354,36 @@ static int tipc_reset_bearer(struct tipc_bearer *b_ptr)
  *
  * Note: This routine assumes caller holds RTNL lock.
  */
-static void bearer_disable(struct tipc_bearer *b_ptr, bool shutting_down)
+static void bearer_disable(struct net *net, struct tipc_bearer *b_ptr,
+			   bool shutting_down)
 {
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	u32 i;
 
 	pr_info("Disabling bearer <%s>\n", b_ptr->name);
 	b_ptr->media->disable_media(b_ptr);
 
-	tipc_link_delete_list(b_ptr->identity, shutting_down);
+	tipc_link_delete_list(net, b_ptr->identity, shutting_down);
 	if (b_ptr->link_req)
 		tipc_disc_delete(b_ptr->link_req);
 
 	for (i = 0; i < MAX_BEARERS; i++) {
-		if (b_ptr == rtnl_dereference(bearer_list[i])) {
-			RCU_INIT_POINTER(bearer_list[i], NULL);
+		if (b_ptr == rtnl_dereference(tn->bearer_list[i])) {
+			RCU_INIT_POINTER(tn->bearer_list[i], NULL);
 			break;
 		}
 	}
 	kfree_rcu(b_ptr, rcu);
 }
 
-int tipc_disable_bearer(const char *name)
-{
-	struct tipc_bearer *b_ptr;
-	int res;
-
-	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, false);
-		res = 0;
-	}
-	return res;
-}
-
-int tipc_enable_l2_media(struct tipc_bearer *b)
+int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b,
+			 struct nlattr *attr[])
 {
 	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);
+	dev = dev_get_by_name(net, driver_name);
 	if (!dev)
 		return -ENODEV;
 
@@ -456,8 +422,8 @@ void tipc_disable_l2_media(struct tipc_bearer *b)
  * @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)
+int tipc_l2_send_msg(struct net *net, struct sk_buff *buf,
+		     struct tipc_bearer *b, struct tipc_media_addr *dest)
 {
 	struct sk_buff *clone;
 	struct net_device *dev;
@@ -493,15 +459,16 @@ int tipc_l2_send_msg(struct sk_buff *buf, struct tipc_bearer *b,
  * 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,
+void tipc_bearer_send(struct net *net, u32 bearer_id, struct sk_buff *buf,
 		      struct tipc_media_addr *dest)
 {
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	struct tipc_bearer *b_ptr;
 
 	rcu_read_lock();
-	b_ptr = rcu_dereference_rtnl(bearer_list[bearer_id]);
+	b_ptr = rcu_dereference_rtnl(tn->bearer_list[bearer_id]);
 	if (likely(b_ptr))
-		b_ptr->media->send_msg(buf, b_ptr, dest);
+		b_ptr->media->send_msg(net, buf, b_ptr, dest);
 	rcu_read_unlock();
 }
 
@@ -521,17 +488,12 @@ static int tipc_l2_rcv_msg(struct sk_buff *buf, struct net_device *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);
+			tipc_rcv(dev_net(dev), buf, b_ptr);
 			rcu_read_unlock();
 			return NET_RX_SUCCESS;
 		}
@@ -554,11 +516,9 @@ static int tipc_l2_rcv_msg(struct sk_buff *buf, struct net_device *dev,
 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;
+	struct net *net = dev_net(dev);
+	struct tipc_bearer *b_ptr;
 
 	b_ptr = rtnl_dereference(dev->tipc_ptr);
 	if (!b_ptr)
@@ -572,16 +532,16 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt,
 			break;
 	case NETDEV_DOWN:
 	case NETDEV_CHANGEMTU:
-		tipc_reset_bearer(b_ptr);
+		tipc_reset_bearer(net, b_ptr);
 		break;
 	case NETDEV_CHANGEADDR:
 		b_ptr->media->raw2addr(b_ptr, &b_ptr->addr,
 				       (char *)dev->dev_addr);
-		tipc_reset_bearer(b_ptr);
+		tipc_reset_bearer(net, b_ptr);
 		break;
 	case NETDEV_UNREGISTER:
 	case NETDEV_CHANGENAME:
-		bearer_disable(b_ptr, false);
+		bearer_disable(dev_net(dev), b_ptr, false);
 		break;
 	}
 	return NOTIFY_OK;
@@ -614,16 +574,452 @@ void tipc_bearer_cleanup(void)
 	dev_remove_pack(&tipc_packet_type);
 }
 
-void tipc_bearer_stop(void)
+void tipc_bearer_stop(struct net *net)
 {
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	struct tipc_bearer *b_ptr;
 	u32 i;
 
 	for (i = 0; i < MAX_BEARERS; i++) {
-		b_ptr = rtnl_dereference(bearer_list[i]);
+		b_ptr = rtnl_dereference(tn->bearer_list[i]);
 		if (b_ptr) {
-			bearer_disable(b_ptr, true);
-			bearer_list[i] = NULL;
+			bearer_disable(net, b_ptr, true);
+			tn->bearer_list[i] = NULL;
+		}
+	}
+}
+
+/* Caller should hold rtnl_lock to protect the bearer */
+static int __tipc_nl_add_bearer(struct tipc_nl_msg *msg,
+				struct tipc_bearer *bearer, int nlflags)
+{
+	void *hdr;
+	struct nlattr *attrs;
+	struct nlattr *prop;
+
+	hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family,
+			  nlflags, TIPC_NL_BEARER_GET);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	attrs = nla_nest_start(msg->skb, TIPC_NLA_BEARER);
+	if (!attrs)
+		goto msg_full;
+
+	if (nla_put_string(msg->skb, TIPC_NLA_BEARER_NAME, bearer->name))
+		goto attr_msg_full;
+
+	prop = nla_nest_start(msg->skb, TIPC_NLA_BEARER_PROP);
+	if (!prop)
+		goto prop_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, bearer->priority))
+		goto prop_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_TOL, bearer->tolerance))
+		goto prop_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bearer->window))
+		goto prop_msg_full;
+
+	nla_nest_end(msg->skb, prop);
+	nla_nest_end(msg->skb, attrs);
+	genlmsg_end(msg->skb, hdr);
+
+	return 0;
+
+prop_msg_full:
+	nla_nest_cancel(msg->skb, prop);
+attr_msg_full:
+	nla_nest_cancel(msg->skb, attrs);
+msg_full:
+	genlmsg_cancel(msg->skb, hdr);
+
+	return -EMSGSIZE;
+}
+
+int tipc_nl_bearer_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	int err;
+	int i = cb->args[0];
+	struct tipc_bearer *bearer;
+	struct tipc_nl_msg msg;
+	struct net *net = sock_net(skb->sk);
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+
+	if (i == MAX_BEARERS)
+		return 0;
+
+	msg.skb = skb;
+	msg.portid = NETLINK_CB(cb->skb).portid;
+	msg.seq = cb->nlh->nlmsg_seq;
+
+	rtnl_lock();
+	for (i = 0; i < MAX_BEARERS; i++) {
+		bearer = rtnl_dereference(tn->bearer_list[i]);
+		if (!bearer)
+			continue;
+
+		err = __tipc_nl_add_bearer(&msg, bearer, NLM_F_MULTI);
+		if (err)
+			break;
+	}
+	rtnl_unlock();
+
+	cb->args[0] = i;
+	return skb->len;
+}
+
+int tipc_nl_bearer_get(struct sk_buff *skb, struct genl_info *info)
+{
+	int err;
+	char *name;
+	struct sk_buff *rep;
+	struct tipc_bearer *bearer;
+	struct tipc_nl_msg msg;
+	struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1];
+	struct net *net = genl_info_net(info);
+
+	if (!info->attrs[TIPC_NLA_BEARER])
+		return -EINVAL;
+
+	err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX,
+			       info->attrs[TIPC_NLA_BEARER],
+			       tipc_nl_bearer_policy);
+	if (err)
+		return err;
+
+	if (!attrs[TIPC_NLA_BEARER_NAME])
+		return -EINVAL;
+	name = nla_data(attrs[TIPC_NLA_BEARER_NAME]);
+
+	rep = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!rep)
+		return -ENOMEM;
+
+	msg.skb = rep;
+	msg.portid = info->snd_portid;
+	msg.seq = info->snd_seq;
+
+	rtnl_lock();
+	bearer = tipc_bearer_find(net, name);
+	if (!bearer) {
+		err = -EINVAL;
+		goto err_out;
+	}
+
+	err = __tipc_nl_add_bearer(&msg, bearer, 0);
+	if (err)
+		goto err_out;
+	rtnl_unlock();
+
+	return genlmsg_reply(rep, info);
+err_out:
+	rtnl_unlock();
+	nlmsg_free(rep);
+
+	return err;
+}
+
+int tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info)
+{
+	int err;
+	char *name;
+	struct tipc_bearer *bearer;
+	struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1];
+	struct net *net = sock_net(skb->sk);
+
+	if (!info->attrs[TIPC_NLA_BEARER])
+		return -EINVAL;
+
+	err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX,
+			       info->attrs[TIPC_NLA_BEARER],
+			       tipc_nl_bearer_policy);
+	if (err)
+		return err;
+
+	if (!attrs[TIPC_NLA_BEARER_NAME])
+		return -EINVAL;
+
+	name = nla_data(attrs[TIPC_NLA_BEARER_NAME]);
+
+	rtnl_lock();
+	bearer = tipc_bearer_find(net, name);
+	if (!bearer) {
+		rtnl_unlock();
+		return -EINVAL;
+	}
+
+	bearer_disable(net, bearer, false);
+	rtnl_unlock();
+
+	return 0;
+}
+
+int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info)
+{
+	int err;
+	char *bearer;
+	struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1];
+	struct net *net = sock_net(skb->sk);
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	u32 domain;
+	u32 prio;
+
+	prio = TIPC_MEDIA_LINK_PRI;
+	domain = tn->own_addr & TIPC_CLUSTER_MASK;
+
+	if (!info->attrs[TIPC_NLA_BEARER])
+		return -EINVAL;
+
+	err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX,
+			       info->attrs[TIPC_NLA_BEARER],
+			       tipc_nl_bearer_policy);
+	if (err)
+		return err;
+
+	if (!attrs[TIPC_NLA_BEARER_NAME])
+		return -EINVAL;
+
+	bearer = nla_data(attrs[TIPC_NLA_BEARER_NAME]);
+
+	if (attrs[TIPC_NLA_BEARER_DOMAIN])
+		domain = nla_get_u32(attrs[TIPC_NLA_BEARER_DOMAIN]);
+
+	if (attrs[TIPC_NLA_BEARER_PROP]) {
+		struct nlattr *props[TIPC_NLA_PROP_MAX + 1];
+
+		err = tipc_nl_parse_link_prop(attrs[TIPC_NLA_BEARER_PROP],
+					      props);
+		if (err)
+			return err;
+
+		if (props[TIPC_NLA_PROP_PRIO])
+			prio = nla_get_u32(props[TIPC_NLA_PROP_PRIO]);
+	}
+
+	rtnl_lock();
+	err = tipc_enable_bearer(net, bearer, domain, prio, attrs);
+	if (err) {
+		rtnl_unlock();
+		return err;
+	}
+	rtnl_unlock();
+
+	return 0;
+}
+
+int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info)
+{
+	int err;
+	char *name;
+	struct tipc_bearer *b;
+	struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1];
+	struct net *net = genl_info_net(info);
+
+	if (!info->attrs[TIPC_NLA_BEARER])
+		return -EINVAL;
+
+	err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX,
+			       info->attrs[TIPC_NLA_BEARER],
+			       tipc_nl_bearer_policy);
+	if (err)
+		return err;
+
+	if (!attrs[TIPC_NLA_BEARER_NAME])
+		return -EINVAL;
+	name = nla_data(attrs[TIPC_NLA_BEARER_NAME]);
+
+	rtnl_lock();
+	b = tipc_bearer_find(net, name);
+	if (!b) {
+		rtnl_unlock();
+		return -EINVAL;
+	}
+
+	if (attrs[TIPC_NLA_BEARER_PROP]) {
+		struct nlattr *props[TIPC_NLA_PROP_MAX + 1];
+
+		err = tipc_nl_parse_link_prop(attrs[TIPC_NLA_BEARER_PROP],
+					      props);
+		if (err) {
+			rtnl_unlock();
+			return err;
 		}
+
+		if (props[TIPC_NLA_PROP_TOL])
+			b->tolerance = nla_get_u32(props[TIPC_NLA_PROP_TOL]);
+		if (props[TIPC_NLA_PROP_PRIO])
+			b->priority = nla_get_u32(props[TIPC_NLA_PROP_PRIO]);
+		if (props[TIPC_NLA_PROP_WIN])
+			b->window = nla_get_u32(props[TIPC_NLA_PROP_WIN]);
 	}
+	rtnl_unlock();
+
+	return 0;
+}
+
+static int __tipc_nl_add_media(struct tipc_nl_msg *msg,
+			       struct tipc_media *media, int nlflags)
+{
+	void *hdr;
+	struct nlattr *attrs;
+	struct nlattr *prop;
+
+	hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family,
+			  nlflags, TIPC_NL_MEDIA_GET);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	attrs = nla_nest_start(msg->skb, TIPC_NLA_MEDIA);
+	if (!attrs)
+		goto msg_full;
+
+	if (nla_put_string(msg->skb, TIPC_NLA_MEDIA_NAME, media->name))
+		goto attr_msg_full;
+
+	prop = nla_nest_start(msg->skb, TIPC_NLA_MEDIA_PROP);
+	if (!prop)
+		goto prop_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, media->priority))
+		goto prop_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_TOL, media->tolerance))
+		goto prop_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, media->window))
+		goto prop_msg_full;
+
+	nla_nest_end(msg->skb, prop);
+	nla_nest_end(msg->skb, attrs);
+	genlmsg_end(msg->skb, hdr);
+
+	return 0;
+
+prop_msg_full:
+	nla_nest_cancel(msg->skb, prop);
+attr_msg_full:
+	nla_nest_cancel(msg->skb, attrs);
+msg_full:
+	genlmsg_cancel(msg->skb, hdr);
+
+	return -EMSGSIZE;
+}
+
+int tipc_nl_media_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	int err;
+	int i = cb->args[0];
+	struct tipc_nl_msg msg;
+
+	if (i == MAX_MEDIA)
+		return 0;
+
+	msg.skb = skb;
+	msg.portid = NETLINK_CB(cb->skb).portid;
+	msg.seq = cb->nlh->nlmsg_seq;
+
+	rtnl_lock();
+	for (; media_info_array[i] != NULL; i++) {
+		err = __tipc_nl_add_media(&msg, media_info_array[i],
+					  NLM_F_MULTI);
+		if (err)
+			break;
+	}
+	rtnl_unlock();
+
+	cb->args[0] = i;
+	return skb->len;
+}
+
+int tipc_nl_media_get(struct sk_buff *skb, struct genl_info *info)
+{
+	int err;
+	char *name;
+	struct tipc_nl_msg msg;
+	struct tipc_media *media;
+	struct sk_buff *rep;
+	struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1];
+
+	if (!info->attrs[TIPC_NLA_MEDIA])
+		return -EINVAL;
+
+	err = nla_parse_nested(attrs, TIPC_NLA_MEDIA_MAX,
+			       info->attrs[TIPC_NLA_MEDIA],
+			       tipc_nl_media_policy);
+	if (err)
+		return err;
+
+	if (!attrs[TIPC_NLA_MEDIA_NAME])
+		return -EINVAL;
+	name = nla_data(attrs[TIPC_NLA_MEDIA_NAME]);
+
+	rep = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!rep)
+		return -ENOMEM;
+
+	msg.skb = rep;
+	msg.portid = info->snd_portid;
+	msg.seq = info->snd_seq;
+
+	rtnl_lock();
+	media = tipc_media_find(name);
+	if (!media) {
+		err = -EINVAL;
+		goto err_out;
+	}
+
+	err = __tipc_nl_add_media(&msg, media, 0);
+	if (err)
+		goto err_out;
+	rtnl_unlock();
+
+	return genlmsg_reply(rep, info);
+err_out:
+	rtnl_unlock();
+	nlmsg_free(rep);
+
+	return err;
+}
+
+int tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info)
+{
+	int err;
+	char *name;
+	struct tipc_media *m;
+	struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1];
+
+	if (!info->attrs[TIPC_NLA_MEDIA])
+		return -EINVAL;
+
+	err = nla_parse_nested(attrs, TIPC_NLA_MEDIA_MAX,
+			       info->attrs[TIPC_NLA_MEDIA],
+			       tipc_nl_media_policy);
+
+	if (!attrs[TIPC_NLA_MEDIA_NAME])
+		return -EINVAL;
+	name = nla_data(attrs[TIPC_NLA_MEDIA_NAME]);
+
+	rtnl_lock();
+	m = tipc_media_find(name);
+	if (!m) {
+		rtnl_unlock();
+		return -EINVAL;
+	}
+
+	if (attrs[TIPC_NLA_MEDIA_PROP]) {
+		struct nlattr *props[TIPC_NLA_PROP_MAX + 1];
+
+		err = tipc_nl_parse_link_prop(attrs[TIPC_NLA_MEDIA_PROP],
+					      props);
+		if (err) {
+			rtnl_unlock();
+			return err;
+		}
+
+		if (props[TIPC_NLA_PROP_TOL])
+			m->tolerance = nla_get_u32(props[TIPC_NLA_PROP_TOL]);
+		if (props[TIPC_NLA_PROP_PRIO])
+			m->priority = nla_get_u32(props[TIPC_NLA_PROP_PRIO]);
+		if (props[TIPC_NLA_PROP_WIN])
+			m->window = nla_get_u32(props[TIPC_NLA_PROP_WIN]);
+	}
+	rtnl_unlock();
+
+	return 0;
 }
diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h
index 78fccc49de23..5cad243ee8fc 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, 2013, Ericsson AB
+ * Copyright (c) 1996-2006, 2013-2014, Ericsson AB
  * Copyright (c) 2005, 2010-2011, Wind River Systems
  * All rights reserved.
  *
@@ -37,24 +37,39 @@
 #ifndef _TIPC_BEARER_H
 #define _TIPC_BEARER_H
 
-#include "bcast.h"
+#include "netlink.h"
+#include <net/genetlink.h>
 
 #define MAX_BEARERS	2
-#define MAX_MEDIA	2
+#define MAX_MEDIA	3
+#define MAX_NODES	4096
+#define WSIZE		32
 
 /* 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	32
+#define TIPC_MEDIA_INFO_SIZE	32
 #define TIPC_MEDIA_TYPE_OFFSET	3
+#define TIPC_MEDIA_ADDR_OFFSET	4
 
 /*
  * Identifiers of supported TIPC media types
  */
 #define TIPC_MEDIA_TYPE_ETH	1
 #define TIPC_MEDIA_TYPE_IB	2
+#define TIPC_MEDIA_TYPE_UDP	3
+
+/**
+ * struct tipc_node_map - set of node identifiers
+ * @count: # of nodes in set
+ * @map: bitmap of node identifiers that are in the set
+ */
+struct tipc_node_map {
+	u32 count;
+	u32 map[MAX_NODES / WSIZE];
+};
 
 /**
  * struct tipc_media_addr - destination address used by TIPC bearers
@@ -63,7 +78,7 @@
  * @broadcast: non-zero if address is a broadcast address
  */
 struct tipc_media_addr {
-	u8 value[TIPC_MEDIA_ADDR_SIZE];
+	u8 value[TIPC_MEDIA_INFO_SIZE];
 	u8 media_id;
 	u8 broadcast;
 };
@@ -87,10 +102,11 @@ struct tipc_bearer;
  * @name: media name
  */
 struct tipc_media {
-	int (*send_msg)(struct sk_buff *buf,
+	int (*send_msg)(struct net *net, struct sk_buff *buf,
 			struct tipc_bearer *b_ptr,
 			struct tipc_media_addr *dest);
-	int (*enable_media)(struct tipc_bearer *b_ptr);
+	int (*enable_media)(struct net *net, struct tipc_bearer *b_ptr,
+			    struct nlattr *attr[]);
 	void (*disable_media)(struct tipc_bearer *b_ptr);
 	int (*addr2str)(struct tipc_media_addr *addr,
 			char *strbuf,
@@ -155,17 +171,11 @@ struct tipc_bearer_names {
 	char if_name[TIPC_MAX_IF_NAME];
 };
 
-struct tipc_link;
-
-extern struct tipc_bearer __rcu *bearer_list[];
-
 /*
  * TIPC routines available to supported media types
  */
 
-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);
+void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b_ptr);
 
 /*
  * Routines made available to TIPC by supported media types
@@ -175,25 +185,37 @@ extern struct tipc_media eth_media_info;
 #ifdef CONFIG_TIPC_MEDIA_IB
 extern struct tipc_media ib_media_info;
 #endif
+#ifdef CONFIG_TIPC_MEDIA_UDP
+extern struct tipc_media udp_media_info;
+#endif
+
+int tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info);
+int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info);
+int tipc_nl_bearer_dump(struct sk_buff *skb, struct netlink_callback *cb);
+int tipc_nl_bearer_get(struct sk_buff *skb, struct genl_info *info);
+int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info);
+
+int tipc_nl_media_dump(struct sk_buff *skb, struct netlink_callback *cb);
+int tipc_nl_media_get(struct sk_buff *skb, struct genl_info *info);
+int tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info);
 
 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);
+int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b,
+			 struct nlattr *attrs[]);
 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);
+int tipc_l2_send_msg(struct net *net, 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(u32 bearer_id, u32 dest);
-void tipc_bearer_remove_dest(u32 bearer_id, u32 dest);
-struct tipc_bearer *tipc_bearer_find(const char *name);
+void tipc_bearer_add_dest(struct net *net, u32 bearer_id, u32 dest);
+void tipc_bearer_remove_dest(struct net *net, u32 bearer_id, u32 dest);
+struct tipc_bearer *tipc_bearer_find(struct net *net, const char *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);
-void tipc_bearer_send(u32 bearer_id, struct sk_buff *buf,
+void tipc_bearer_stop(struct net *net);
+void tipc_bearer_send(struct net *net, 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
deleted file mode 100644
index 876f4c6a2631..000000000000
--- a/net/tipc/config.c
+++ /dev/null
@@ -1,342 +0,0 @@
-/*
- * net/tipc/config.c: TIPC configuration management code
- *
- * Copyright (c) 2002-2006, Ericsson AB
- * Copyright (c) 2004-2007, 2010-2013, 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"
-#include "socket.h"
-#include "name_table.h"
-#include "config.h"
-#include "server.h"
-
-#define REPLY_TRUNCATED "<truncated>\n"
-
-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;
-
-	buf = alloc_skb(rep_headroom + payload_size, GFP_ATOMIC);
-	if (buf)
-		skb_reserve(buf, rep_headroom);
-	return buf;
-}
-
-int tipc_cfg_append_tlv(struct sk_buff *buf, int tlv_type,
-			void *tlv_data, int tlv_data_size)
-{
-	struct tlv_desc *tlv = (struct tlv_desc *)skb_tail_pointer(buf);
-	int new_tlv_space = TLV_SPACE(tlv_data_size);
-
-	if (skb_tailroom(buf) < new_tlv_space)
-		return 0;
-	skb_put(buf, new_tlv_space);
-	tlv->tlv_type = htons(tlv_type);
-	tlv->tlv_len  = htons(TLV_LENGTH(tlv_data_size));
-	if (tlv_data_size && tlv_data)
-		memcpy(TLV_DATA(tlv), tlv_data, tlv_data_size);
-	return 1;
-}
-
-static struct sk_buff *tipc_cfg_reply_unsigned_type(u16 tlv_type, u32 value)
-{
-	struct sk_buff *buf;
-	__be32 value_net;
-
-	buf = tipc_cfg_reply_alloc(TLV_SPACE(sizeof(value)));
-	if (buf) {
-		value_net = htonl(value);
-		tipc_cfg_append_tlv(buf, tlv_type, &value_net,
-				    sizeof(value_net));
-	}
-	return buf;
-}
-
-static struct sk_buff *tipc_cfg_reply_unsigned(u32 value)
-{
-	return tipc_cfg_reply_unsigned_type(TIPC_TLV_UNSIGNED, value);
-}
-
-struct sk_buff *tipc_cfg_reply_string_type(u16 tlv_type, char *string)
-{
-	struct sk_buff *buf;
-	int string_len = strlen(string) + 1;
-
-	buf = tipc_cfg_reply_alloc(TLV_SPACE(string_len));
-	if (buf)
-		tipc_cfg_append_tlv(buf, tlv_type, string, string_len);
-	return buf;
-}
-
-static struct sk_buff *tipc_show_stats(void)
-{
-	struct sk_buff *buf;
-	struct tlv_desc *rep_tlv;
-	char *pb;
-	int pb_len;
-	int str_len;
-	u32 value;
-
-	if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_UNSIGNED))
-		return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR);
-
-	value = ntohl(*(u32 *)TLV_DATA(req_tlv_area));
-	if (value != 0)
-		return tipc_cfg_reply_error_string("unsupported argument");
-
-	buf = tipc_cfg_reply_alloc(TLV_SPACE(ULTRA_STRING_MAX_LEN));
-	if (buf == NULL)
-		return NULL;
-
-	rep_tlv = (struct tlv_desc *)buf->data;
-	pb = TLV_DATA(rep_tlv);
-	pb_len = ULTRA_STRING_MAX_LEN;
-
-	str_len = tipc_snprintf(pb, pb_len, "TIPC version " TIPC_MOD_VER "\n");
-	str_len += 1;	/* for "\0" */
-	skb_put(buf, TLV_SPACE(str_len));
-	TLV_SET(rep_tlv, TIPC_TLV_ULTRA_STRING, NULL, str_len);
-
-	return buf;
-}
-
-static struct sk_buff *cfg_enable_bearer(void)
-{
-	struct tipc_bearer_config *args;
-
-	if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_BEARER_CONFIG))
-		return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR);
-
-	args = (struct tipc_bearer_config *)TLV_DATA(req_tlv_area);
-	if (tipc_enable_bearer(args->name,
-			       ntohl(args->disc_domain),
-			       ntohl(args->priority)))
-		return tipc_cfg_reply_error_string("unable to enable bearer");
-
-	return tipc_cfg_reply_none();
-}
-
-static struct sk_buff *cfg_disable_bearer(void)
-{
-	if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_BEARER_NAME))
-		return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR);
-
-	if (tipc_disable_bearer((char *)TLV_DATA(req_tlv_area)))
-		return tipc_cfg_reply_error_string("unable to disable bearer");
-
-	return tipc_cfg_reply_none();
-}
-
-static struct sk_buff *cfg_set_own_addr(void)
-{
-	u32 addr;
-
-	if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_NET_ADDR))
-		return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR);
-
-	addr = ntohl(*(__be32 *)TLV_DATA(req_tlv_area));
-	if (addr == tipc_own_addr)
-		return tipc_cfg_reply_none();
-	if (!tipc_addr_node_valid(addr))
-		return tipc_cfg_reply_error_string(TIPC_CFG_INVALID_VALUE
-						   " (node address)");
-	if (tipc_own_addr)
-		return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED
-						   " (cannot change node address once assigned)");
-	if (!tipc_net_start(addr))
-		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)
-{
-	u32 value;
-
-	if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_UNSIGNED))
-		return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR);
-	value = ntohl(*(__be32 *)TLV_DATA(req_tlv_area));
-	if (value == tipc_max_ports)
-		return tipc_cfg_reply_none();
-	if (value < 127 || value > 65535)
-		return tipc_cfg_reply_error_string(TIPC_CFG_INVALID_VALUE
-						   " (max ports must be 127-65535)");
-	return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED
-		" (cannot change max ports while TIPC is active)");
-}
-
-static struct sk_buff *cfg_set_netid(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);
-	value = ntohl(*(__be32 *)TLV_DATA(req_tlv_area));
-	if (value == tipc_net_id)
-		return tipc_cfg_reply_none();
-	if (value < 1 || value > 9999)
-		return tipc_cfg_reply_error_string(TIPC_CFG_INVALID_VALUE
-						   " (network id must be 1-9999)");
-	if (tipc_own_addr)
-		return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED
-			" (cannot change network id once TIPC has joined a network)");
-	tipc_net_id = value;
-	return tipc_cfg_reply_none();
-}
-
-struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area,
-				int request_space, int reply_headroom)
-{
-	struct sk_buff *rep_tlv_buf;
-
-	rtnl_lock();
-
-	/* Save request and reply details in a well-known location */
-	req_tlv_area = request_area;
-	req_tlv_space = request_space;
-	rep_headroom = reply_headroom;
-
-	/* Check command authorization */
-	if (likely(in_own_node(orig_node))) {
-		/* command is permitted */
-	} else {
-		rep_tlv_buf = tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED
-							  " (cannot be done remotely)");
-		goto exit;
-	}
-
-	/* Call appropriate processing routine */
-	switch (cmd) {
-	case TIPC_CMD_NOOP:
-		rep_tlv_buf = tipc_cfg_reply_none();
-		break;
-	case TIPC_CMD_GET_NODES:
-		rep_tlv_buf = tipc_node_get_nodes(req_tlv_area, req_tlv_space);
-		break;
-	case TIPC_CMD_GET_LINKS:
-		rep_tlv_buf = tipc_node_get_links(req_tlv_area, req_tlv_space);
-		break;
-	case TIPC_CMD_SHOW_LINK_STATS:
-		rep_tlv_buf = tipc_link_cmd_show_stats(req_tlv_area, req_tlv_space);
-		break;
-	case TIPC_CMD_RESET_LINK_STATS:
-		rep_tlv_buf = tipc_link_cmd_reset_stats(req_tlv_area, req_tlv_space);
-		break;
-	case TIPC_CMD_SHOW_NAME_TABLE:
-		rep_tlv_buf = tipc_nametbl_get(req_tlv_area, req_tlv_space);
-		break;
-	case TIPC_CMD_GET_BEARER_NAMES:
-		rep_tlv_buf = tipc_bearer_get_names();
-		break;
-	case TIPC_CMD_GET_MEDIA_NAMES:
-		rep_tlv_buf = tipc_media_get_names();
-		break;
-	case TIPC_CMD_SHOW_PORTS:
-		rep_tlv_buf = tipc_sk_socks_show();
-		break;
-	case TIPC_CMD_SHOW_STATS:
-		rep_tlv_buf = tipc_show_stats();
-		break;
-	case TIPC_CMD_SET_LINK_TOL:
-	case TIPC_CMD_SET_LINK_PRI:
-	case TIPC_CMD_SET_LINK_WINDOW:
-		rep_tlv_buf = tipc_link_cmd_config(req_tlv_area, req_tlv_space, cmd);
-		break;
-	case TIPC_CMD_ENABLE_BEARER:
-		rep_tlv_buf = cfg_enable_bearer();
-		break;
-	case TIPC_CMD_DISABLE_BEARER:
-		rep_tlv_buf = cfg_disable_bearer();
-		break;
-	case TIPC_CMD_SET_NODE_ADDR:
-		rep_tlv_buf = cfg_set_own_addr();
-		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_MAX_PORTS:
-		rep_tlv_buf = tipc_cfg_reply_unsigned(tipc_max_ports);
-		break;
-	case TIPC_CMD_GET_NETID:
-		rep_tlv_buf = tipc_cfg_reply_unsigned(tipc_net_id);
-		break;
-	case TIPC_CMD_NOT_NET_ADMIN:
-		rep_tlv_buf =
-			tipc_cfg_reply_error_string(TIPC_CFG_NOT_NET_ADMIN);
-		break;
-	case TIPC_CMD_SET_MAX_ZONES:
-	case TIPC_CMD_GET_MAX_ZONES:
-	case TIPC_CMD_SET_MAX_SLAVES:
-	case TIPC_CMD_GET_MAX_SLAVES:
-	case TIPC_CMD_SET_MAX_CLUSTERS:
-	case TIPC_CMD_GET_MAX_CLUSTERS:
-	case TIPC_CMD_SET_MAX_NODES:
-	case TIPC_CMD_GET_MAX_NODES:
-	case TIPC_CMD_SET_MAX_SUBSCR:
-	case TIPC_CMD_GET_MAX_SUBSCR:
-	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)");
-		break;
-	default:
-		rep_tlv_buf = tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED
-							  " (unknown command)");
-		break;
-	}
-
-	WARN_ON(rep_tlv_buf->len > TLV_SPACE(ULTRA_STRING_MAX_LEN));
-
-	/* Append an error message if we cannot return all requested data */
-	if (rep_tlv_buf->len == TLV_SPACE(ULTRA_STRING_MAX_LEN)) {
-		if (*(rep_tlv_buf->data + ULTRA_STRING_MAX_LEN) != '\0')
-			sprintf(rep_tlv_buf->data + rep_tlv_buf->len -
-				sizeof(REPLY_TRUNCATED) - 1, REPLY_TRUNCATED);
-	}
-
-	/* Return reply buffer */
-exit:
-	rtnl_unlock();
-	return rep_tlv_buf;
-}
diff --git a/net/tipc/config.h b/net/tipc/config.h
deleted file mode 100644
index 47b1bf181612..000000000000
--- a/net/tipc/config.h
+++ /dev/null
@@ -1,67 +0,0 @@
-/*
- * net/tipc/config.h: Include file for TIPC configuration service code
- *
- * Copyright (c) 2003-2006, 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.
- */
-
-#ifndef _TIPC_CONFIG_H
-#define _TIPC_CONFIG_H
-
-/* ---------------------------------------------------------------------- */
-
-#include "link.h"
-
-struct sk_buff *tipc_cfg_reply_alloc(int payload_size);
-int tipc_cfg_append_tlv(struct sk_buff *buf, int tlv_type,
-			void *tlv_data, int tlv_data_size);
-struct sk_buff *tipc_cfg_reply_string_type(u16 tlv_type, char *string);
-
-static inline struct sk_buff *tipc_cfg_reply_none(void)
-{
-	return tipc_cfg_reply_alloc(0);
-}
-
-static inline struct sk_buff *tipc_cfg_reply_error_string(char *string)
-{
-	return tipc_cfg_reply_string_type(TIPC_TLV_ERROR_STRING, string);
-}
-
-static inline struct sk_buff *tipc_cfg_reply_ultra_string(char *string)
-{
-	return tipc_cfg_reply_string_type(TIPC_TLV_ULTRA_STRING, string);
-}
-
-struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd,
-				const void *req_tlv_area, int req_tlv_space,
-				int headroom);
-#endif
diff --git a/net/tipc/core.c b/net/tipc/core.c
index a5737b8407dd..be1c9fa60b09 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -34,82 +34,88 @@
  * POSSIBILITY OF SUCH DAMAGE.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include "core.h"
 #include "name_table.h"
 #include "subscr.h"
-#include "config.h"
+#include "bearer.h"
+#include "net.h"
 #include "socket.h"
 
 #include <linux/module.h>
 
-/* global variables used by multiple sub-systems within TIPC */
-int tipc_random __read_mostly;
-
 /* configurable TIPC parameters */
-u32 tipc_own_addr __read_mostly;
-int tipc_max_ports __read_mostly;
 int tipc_net_id __read_mostly;
 int sysctl_tipc_rmem[3] __read_mostly;	/* min/default/max */
 
-/**
- * tipc_buf_acquire - creates a TIPC message buffer
- * @size: message size (including TIPC header)
- *
- * Returns a new buffer with data pointers set to the specified size.
- *
- * NOTE: Headroom is reserved to allow prepending of a data link header.
- *       There may also be unrequested tailroom present at the buffer's end.
- */
-struct sk_buff *tipc_buf_acquire(u32 size)
+static int __net_init tipc_init_net(struct net *net)
 {
-	struct sk_buff *skb;
-	unsigned int buf_size = (BUF_HEADROOM + size + 3) & ~3u;
-
-	skb = alloc_skb_fclone(buf_size, GFP_ATOMIC);
-	if (skb) {
-		skb_reserve(skb, BUF_HEADROOM);
-		skb_put(skb, size);
-		skb->next = NULL;
-	}
-	return skb;
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	int err;
+
+	tn->net_id = 4711;
+	tn->own_addr = 0;
+	get_random_bytes(&tn->random, sizeof(int));
+	INIT_LIST_HEAD(&tn->node_list);
+	spin_lock_init(&tn->node_list_lock);
+
+	err = tipc_sk_rht_init(net);
+	if (err)
+		goto out_sk_rht;
+
+	err = tipc_nametbl_init(net);
+	if (err)
+		goto out_nametbl;
+
+	err = tipc_subscr_start(net);
+	if (err)
+		goto out_subscr;
+	return 0;
+
+out_subscr:
+	tipc_nametbl_stop(net);
+out_nametbl:
+	tipc_sk_rht_destroy(net);
+out_sk_rht:
+	return err;
 }
 
-/**
- * tipc_core_stop - switch TIPC from SINGLE NODE to NOT RUNNING mode
- */
-static void tipc_core_stop(void)
+static void __net_exit tipc_exit_net(struct net *net)
 {
-	tipc_net_stop();
-	tipc_bearer_cleanup();
-	tipc_netlink_stop();
-	tipc_subscr_stop();
-	tipc_nametbl_stop();
-	tipc_sk_ref_table_stop();
-	tipc_socket_stop();
-	tipc_unregister_sysctl();
+	tipc_subscr_stop(net);
+	tipc_net_stop(net);
+	tipc_nametbl_stop(net);
+	tipc_sk_rht_destroy(net);
 }
 
-/**
- * tipc_core_start - switch TIPC from NOT RUNNING to SINGLE NODE mode
- */
-static int tipc_core_start(void)
+static struct pernet_operations tipc_net_ops = {
+	.init = tipc_init_net,
+	.exit = tipc_exit_net,
+	.id   = &tipc_net_id,
+	.size = sizeof(struct tipc_net),
+};
+
+static int __init tipc_init(void)
 {
 	int err;
 
-	get_random_bytes(&tipc_random, sizeof(tipc_random));
-
-	err = tipc_sk_ref_table_init(tipc_max_ports, tipc_random);
-	if (err)
-		goto out_reftbl;
+	pr_info("Activated (version " TIPC_MOD_VER ")\n");
 
-	err = tipc_nametbl_init();
-	if (err)
-		goto out_nametbl;
+	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] = TIPC_CONN_OVERLOAD_LIMIT;
 
 	err = tipc_netlink_start();
 	if (err)
 		goto out_netlink;
 
+	err = tipc_netlink_compat_start();
+	if (err)
+		goto out_netlink_compat;
+
 	err = tipc_socket_init();
 	if (err)
 		goto out_socket;
@@ -118,58 +124,40 @@ static int tipc_core_start(void)
 	if (err)
 		goto out_sysctl;
 
-	err = tipc_subscr_start();
+	err = register_pernet_subsys(&tipc_net_ops);
 	if (err)
-		goto out_subscr;
+		goto out_pernet;
 
 	err = tipc_bearer_setup();
 	if (err)
 		goto out_bearer;
 
+	pr_info("Started in single node mode\n");
 	return 0;
 out_bearer:
-	tipc_subscr_stop();
-out_subscr:
+	unregister_pernet_subsys(&tipc_net_ops);
+out_pernet:
 	tipc_unregister_sysctl();
 out_sysctl:
 	tipc_socket_stop();
 out_socket:
+	tipc_netlink_compat_stop();
+out_netlink_compat:
 	tipc_netlink_stop();
 out_netlink:
-	tipc_nametbl_stop();
-out_nametbl:
-	tipc_sk_ref_table_stop();
-out_reftbl:
+	pr_err("Unable to start in single node mode\n");
 	return err;
 }
 
-static int __init tipc_init(void)
-{
-	int res;
-
-	pr_info("Activated (version " TIPC_MOD_VER ")\n");
-
-	tipc_own_addr = 0;
-	tipc_max_ports = CONFIG_TIPC_PORTS;
-	tipc_net_id = 4711;
-
-	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] = TIPC_CONN_OVERLOAD_LIMIT;
-
-	res = tipc_core_start();
-	if (res)
-		pr_err("Unable to start in single node mode\n");
-	else
-		pr_info("Started in single node mode\n");
-	return res;
-}
-
 static void __exit tipc_exit(void)
 {
-	tipc_core_stop();
+	tipc_bearer_cleanup();
+	unregister_pernet_subsys(&tipc_net_ops);
+	tipc_netlink_stop();
+	tipc_netlink_compat_stop();
+	tipc_socket_stop();
+	tipc_unregister_sysctl();
+
 	pr_info("Deactivated\n");
 }
 
diff --git a/net/tipc/core.h b/net/tipc/core.h
index f773b148722f..3dc68c7a966d 100644
--- a/net/tipc/core.h
+++ b/net/tipc/core.h
@@ -37,10 +37,9 @@
 #ifndef _TIPC_CORE_H
 #define _TIPC_CORE_H
 
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
 #include <linux/tipc.h>
 #include <linux/tipc_config.h>
+#include <linux/tipc_netlink.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
@@ -58,47 +57,54 @@
 #include <linux/vmalloc.h>
 #include <linux/rtnetlink.h>
 #include <linux/etherdevice.h>
+#include <net/netns/generic.h>
+#include <linux/rhashtable.h>
+
+#include "node.h"
+#include "bearer.h"
+#include "bcast.h"
+#include "netlink.h"
+#include "link.h"
+#include "node.h"
+#include "msg.h"
 
 #define TIPC_MOD_VER "2.0.0"
 
-#define ULTRA_STRING_MAX_LEN	32768
-#define TIPC_MAX_SUBSCRIPTIONS	65535
-#define TIPC_MAX_PUBLICATIONS	65535
+extern int tipc_net_id __read_mostly;
+extern int sysctl_tipc_rmem[3] __read_mostly;
+extern int sysctl_tipc_named_timeout __read_mostly;
 
-struct tipc_msg;	/* msg.h */
+struct tipc_net {
+	u32 own_addr;
+	int net_id;
+	int random;
 
-int tipc_snprintf(char *buf, int len, const char *fmt, ...);
+	/* Node table and node list */
+	spinlock_t node_list_lock;
+	struct hlist_head node_htable[NODE_HTABLE_SIZE];
+	struct list_head node_list;
+	u32 num_nodes;
+	u32 num_links;
 
-/*
- * TIPC-specific error codes
- */
-#define ELINKCONG EAGAIN	/* link congestion <=> resource unavailable */
+	/* Bearer list */
+	struct tipc_bearer __rcu *bearer_list[MAX_BEARERS + 1];
 
-/*
- * Global configuration variables
- */
-extern u32 tipc_own_addr __read_mostly;
-extern int tipc_max_ports __read_mostly;
-extern int tipc_net_id __read_mostly;
-extern int sysctl_tipc_rmem[3] __read_mostly;
-extern int sysctl_tipc_named_timeout __read_mostly;
+	/* Broadcast link */
+	struct tipc_bcbearer *bcbearer;
+	struct tipc_bclink *bclink;
+	struct tipc_link *bcl;
 
-/*
- * Other global variables
- */
-extern int tipc_random __read_mostly;
+	/* Socket hash table */
+	struct rhashtable sk_rht;
 
-/*
- * Routines available to privileged subsystems
- */
-int tipc_netlink_start(void);
-void tipc_netlink_stop(void);
-int tipc_socket_init(void);
-void tipc_socket_stop(void);
-int tipc_sock_create_local(int type, struct socket **res);
-void tipc_sock_release_local(struct socket *sock);
-int tipc_sock_accept_local(struct socket *sock, struct socket **newsock,
-			   int flags);
+	/* Name table */
+	spinlock_t nametbl_lock;
+	struct name_table *nametbl;
+
+	/* Topology subscription server */
+	struct tipc_server *topsrv;
+	atomic_t subscription_count;
+};
 
 #ifdef CONFIG_SYSCTL
 int tipc_register_sysctl(void);
@@ -107,101 +113,4 @@ void tipc_unregister_sysctl(void);
 #define tipc_register_sysctl() 0
 #define tipc_unregister_sysctl()
 #endif
-
-/*
- * TIPC timer code
- */
-typedef void (*Handler) (unsigned long);
-
-/**
- * k_init_timer - initialize a timer
- * @timer: pointer to timer structure
- * @routine: pointer to routine to invoke when timer expires
- * @argument: value to pass to routine when timer expires
- *
- * Timer must be initialized before use (and terminated when no longer needed).
- */
-static inline void k_init_timer(struct timer_list *timer, Handler routine,
-				unsigned long argument)
-{
-	setup_timer(timer, routine, argument);
-}
-
-/**
- * k_start_timer - start a timer
- * @timer: pointer to timer structure
- * @msec: time to delay (in ms)
- *
- * Schedules a previously initialized timer for later execution.
- * If timer is already running, the new timeout overrides the previous request.
- *
- * To ensure the timer doesn't expire before the specified delay elapses,
- * the amount of delay is rounded up when converting to the jiffies
- * then an additional jiffy is added to account for the fact that
- * the starting time may be in the middle of the current jiffy.
- */
-static inline void k_start_timer(struct timer_list *timer, unsigned long msec)
-{
-	mod_timer(timer, jiffies + msecs_to_jiffies(msec) + 1);
-}
-
-/**
- * k_cancel_timer - cancel a timer
- * @timer: pointer to timer structure
- *
- * Cancels a previously initialized timer.
- * Can be called safely even if the timer is already inactive.
- *
- * WARNING: Must not be called when holding locks required by the timer's
- *          timeout routine, otherwise deadlock can occur on SMP systems!
- */
-static inline void k_cancel_timer(struct timer_list *timer)
-{
-	del_timer_sync(timer);
-}
-
-/**
- * k_term_timer - terminate a timer
- * @timer: pointer to timer structure
- *
- * Prevents further use of a previously initialized timer.
- *
- * WARNING: Caller must ensure timer isn't currently running.
- *
- * (Do not "enhance" this routine to automatically cancel an active timer,
- * otherwise deadlock can arise when a timeout routine calls k_term_timer.)
- */
-static inline void k_term_timer(struct timer_list *timer)
-{
-}
-
-/*
- * TIPC message buffer code
- *
- * TIPC message buffer headroom reserves space for the worst-case
- * link-level device header (in case the message is sent off-node).
- *
- * Note: Headroom should be a multiple of 4 to ensure the TIPC header fields
- *       are word aligned for quicker access
- */
-#define BUF_HEADROOM LL_MAX_HEADER
-
-struct tipc_skb_cb {
-	void *handle;
-	struct sk_buff *tail;
-	bool deferred;
-	bool wakeup_pending;
-	u16 chain_sz;
-	u16 chain_imp;
-};
-
-#define TIPC_SKB_CB(__skb) ((struct tipc_skb_cb *)&((__skb)->cb[0]))
-
-static inline struct tipc_msg *buf_msg(struct sk_buff *skb)
-{
-	return (struct tipc_msg *)skb->data;
-}
-
-struct sk_buff *tipc_buf_acquire(u32 size);
-
 #endif
diff --git a/net/tipc/discover.c b/net/tipc/discover.c
index aa722a42ef8b..967e292f53c8 100644
--- a/net/tipc/discover.c
+++ b/net/tipc/discover.c
@@ -1,7 +1,7 @@
 /*
  * net/tipc/discover.c
  *
- * Copyright (c) 2003-2006, 2014, Ericsson AB
+ * Copyright (c) 2003-2006, 2014-2015, Ericsson AB
  * Copyright (c) 2005-2006, 2010-2011, Wind River Systems
  * All rights reserved.
  *
@@ -38,15 +38,19 @@
 #include "link.h"
 #include "discover.h"
 
-#define TIPC_LINK_REQ_INIT	125	/* min delay during bearer start up */
-#define TIPC_LINK_REQ_FAST	1000	/* max delay if bearer has no links */
-#define TIPC_LINK_REQ_SLOW	60000	/* max delay if bearer has links */
-#define TIPC_LINK_REQ_INACTIVE	0xffffffff /* indicates no timer in use */
-
+/* min delay during bearer start up */
+#define TIPC_LINK_REQ_INIT	msecs_to_jiffies(125)
+/* max delay if bearer has no links */
+#define TIPC_LINK_REQ_FAST	msecs_to_jiffies(1000)
+/* max delay if bearer has links */
+#define TIPC_LINK_REQ_SLOW	msecs_to_jiffies(60000)
+/* indicates no timer in use */
+#define TIPC_LINK_REQ_INACTIVE	0xffffffff
 
 /**
  * struct tipc_link_req - information about an ongoing link setup request
  * @bearer_id: identity of bearer issuing requests
+ * @net: network namespace instance
  * @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)
@@ -58,31 +62,36 @@
 struct tipc_link_req {
 	u32 bearer_id;
 	struct tipc_media_addr dest;
+	struct net *net;
 	u32 domain;
 	int num_nodes;
 	spinlock_t lock;
 	struct sk_buff *buf;
 	struct timer_list timer;
-	unsigned int timer_intv;
+	unsigned long timer_intv;
 };
 
 /**
  * tipc_disc_init_msg - initialize a link setup message
+ * @net: the applicable net namespace
  * @type: message type (request or response)
  * @b_ptr: ptr to bearer issuing message
  */
-static void tipc_disc_init_msg(struct sk_buff *buf, u32 type,
+static void tipc_disc_init_msg(struct net *net, struct sk_buff *buf, u32 type,
 			       struct tipc_bearer *b_ptr)
 {
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	struct tipc_msg *msg;
 	u32 dest_domain = b_ptr->domain;
 
 	msg = buf_msg(buf);
-	tipc_msg_init(msg, LINK_CONFIG, type, INT_H_SIZE, dest_domain);
+	tipc_msg_init(tn->own_addr, msg, LINK_CONFIG, type,
+		      MAX_H_SIZE, dest_domain);
 	msg_set_non_seq(msg, 1);
-	msg_set_node_sig(msg, tipc_random);
+	msg_set_node_sig(msg, tn->random);
+	msg_set_node_capabilities(msg, 0);
 	msg_set_dest_domain(msg, dest_domain);
-	msg_set_bc_netid(msg, tipc_net_id);
+	msg_set_bc_netid(msg, tn->net_id);
 	b_ptr->media->addr2msg(msg_media_addr(msg), &b_ptr->addr);
 }
 
@@ -107,11 +116,14 @@ static void disc_dupl_alert(struct tipc_bearer *b_ptr, u32 node_addr,
 
 /**
  * tipc_disc_rcv - handle incoming discovery message (request or response)
+ * @net: the applicable net namespace
  * @buf: buffer containing message
  * @bearer: bearer that message arrived on
  */
-void tipc_disc_rcv(struct sk_buff *buf, struct tipc_bearer *bearer)
+void tipc_disc_rcv(struct net *net, struct sk_buff *buf,
+		   struct tipc_bearer *bearer)
 {
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	struct tipc_node *node;
 	struct tipc_link *link;
 	struct tipc_media_addr maddr;
@@ -122,6 +134,7 @@ void tipc_disc_rcv(struct sk_buff *buf, struct tipc_bearer *bearer)
 	u32 net_id = msg_bc_netid(msg);
 	u32 mtyp = msg_type(msg);
 	u32 signature = msg_node_sig(msg);
+	u16 caps = msg_node_capabilities(msg);
 	bool addr_match = false;
 	bool sign_match = false;
 	bool link_up = false;
@@ -133,7 +146,7 @@ void tipc_disc_rcv(struct sk_buff *buf, struct tipc_bearer *bearer)
 	kfree_skb(buf);
 
 	/* Ensure message from node is valid and communication is permitted */
-	if (net_id != tipc_net_id)
+	if (net_id != tn->net_id)
 		return;
 	if (maddr.broadcast)
 		return;
@@ -142,24 +155,21 @@ void tipc_disc_rcv(struct sk_buff *buf, struct tipc_bearer *bearer)
 	if (!tipc_addr_node_valid(onode))
 		return;
 
-	if (in_own_node(onode)) {
+	if (in_own_node(net, onode)) {
 		if (memcmp(&maddr, &bearer->addr, sizeof(maddr)))
-			disc_dupl_alert(bearer, tipc_own_addr, &maddr);
+			disc_dupl_alert(bearer, tn->own_addr, &maddr);
 		return;
 	}
-	if (!tipc_in_scope(ddom, tipc_own_addr))
+	if (!tipc_in_scope(ddom, tn->own_addr))
 		return;
 	if (!tipc_in_scope(bearer->domain, onode))
 		return;
 
-	/* Locate, or if necessary, create, node: */
-	node = tipc_node_find(onode);
-	if (!node)
-		node = tipc_node_create(onode);
+	node = tipc_node_create(net, onode);
 	if (!node)
 		return;
-
 	tipc_node_lock(node);
+	node->capabilities = caps;
 	link = node->links[bearer->identity];
 
 	/* Prepare to validate requesting node's signature and media address */
@@ -242,14 +252,15 @@ void tipc_disc_rcv(struct sk_buff *buf, struct tipc_bearer *bearer)
 
 	/* Send response, if necessary */
 	if (respond && (mtyp == DSC_REQ_MSG)) {
-		rbuf = tipc_buf_acquire(INT_H_SIZE);
+		rbuf = tipc_buf_acquire(MAX_H_SIZE);
 		if (rbuf) {
-			tipc_disc_init_msg(rbuf, DSC_RESP_MSG, bearer);
-			tipc_bearer_send(bearer->identity, rbuf, &maddr);
+			tipc_disc_init_msg(net, rbuf, DSC_RESP_MSG, bearer);
+			tipc_bearer_send(net, bearer->identity, rbuf, &maddr);
 			kfree_skb(rbuf);
 		}
 	}
 	tipc_node_unlock(node);
+	tipc_node_put(node);
 }
 
 /**
@@ -265,7 +276,7 @@ static void disc_update(struct tipc_link_req *req)
 		if ((req->timer_intv == TIPC_LINK_REQ_INACTIVE) ||
 		    (req->timer_intv > TIPC_LINK_REQ_FAST)) {
 			req->timer_intv = TIPC_LINK_REQ_INIT;
-			k_start_timer(&req->timer, req->timer_intv);
+			mod_timer(&req->timer, jiffies + req->timer_intv);
 		}
 	}
 }
@@ -295,12 +306,13 @@ void tipc_disc_remove_dest(struct tipc_link_req *req)
 
 /**
  * disc_timeout - send a periodic link setup request
- * @req: ptr to link request structure
+ * @data: ptr to link request structure
  *
  * Called whenever a link setup request timer associated with a bearer expires.
  */
-static void disc_timeout(struct tipc_link_req *req)
+static void disc_timeout(unsigned long data)
 {
+	struct tipc_link_req *req = (struct tipc_link_req *)data;
 	int max_delay;
 
 	spin_lock_bh(&req->lock);
@@ -318,7 +330,7 @@ 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_id, req->buf, &req->dest);
+	tipc_bearer_send(req->net, req->bearer_id, req->buf, &req->dest);
 
 
 	req->timer_intv *= 2;
@@ -329,44 +341,46 @@ static void disc_timeout(struct tipc_link_req *req)
 	if (req->timer_intv > max_delay)
 		req->timer_intv = max_delay;
 
-	k_start_timer(&req->timer, req->timer_intv);
+	mod_timer(&req->timer, jiffies + req->timer_intv);
 exit:
 	spin_unlock_bh(&req->lock);
 }
 
 /**
  * tipc_disc_create - create object to send periodic link setup requests
+ * @net: the applicable net namespace
  * @b_ptr: ptr to bearer issuing requests
  * @dest: destination address for request messages
  * @dest_domain: network domain to which links can be established
  *
  * Returns 0 if successful, otherwise -errno.
  */
-int tipc_disc_create(struct tipc_bearer *b_ptr, struct tipc_media_addr *dest)
+int tipc_disc_create(struct net *net, struct tipc_bearer *b_ptr,
+		     struct tipc_media_addr *dest)
 {
 	struct tipc_link_req *req;
 
 	req = kmalloc(sizeof(*req), GFP_ATOMIC);
 	if (!req)
 		return -ENOMEM;
-
-	req->buf = tipc_buf_acquire(INT_H_SIZE);
+	req->buf = tipc_buf_acquire(MAX_H_SIZE);
 	if (!req->buf) {
 		kfree(req);
 		return -ENOMEM;
 	}
 
-	tipc_disc_init_msg(req->buf, DSC_REQ_MSG, b_ptr);
+	tipc_disc_init_msg(net, req->buf, DSC_REQ_MSG, b_ptr);
 	memcpy(&req->dest, dest, sizeof(*dest));
+	req->net = net;
 	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);
+	setup_timer(&req->timer, disc_timeout, (unsigned long)req);
+	mod_timer(&req->timer, jiffies + req->timer_intv);
 	b_ptr->link_req = req;
-	tipc_bearer_send(req->bearer_id, req->buf, &req->dest);
+	tipc_bearer_send(net, req->bearer_id, req->buf, &req->dest);
 	return 0;
 }
 
@@ -376,28 +390,29 @@ int tipc_disc_create(struct tipc_bearer *b_ptr, struct tipc_media_addr *dest)
  */
 void tipc_disc_delete(struct tipc_link_req *req)
 {
-	k_cancel_timer(&req->timer);
-	k_term_timer(&req->timer);
+	del_timer_sync(&req->timer);
 	kfree_skb(req->buf);
 	kfree(req);
 }
 
 /**
  * tipc_disc_reset - reset object to send periodic link setup requests
+ * @net: the applicable net namespace
  * @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)
+void tipc_disc_reset(struct net *net, 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);
+	tipc_disc_init_msg(net, req->buf, DSC_REQ_MSG, b_ptr);
+	req->net = net;
 	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);
+	mod_timer(&req->timer, jiffies + req->timer_intv);
+	tipc_bearer_send(net, 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 515b57392f4d..c9b12770c5ed 100644
--- a/net/tipc/discover.h
+++ b/net/tipc/discover.h
@@ -39,11 +39,13 @@
 
 struct tipc_link_req;
 
-int tipc_disc_create(struct tipc_bearer *b_ptr, struct tipc_media_addr *dest);
+int tipc_disc_create(struct net *net, 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_reset(struct net *net, 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_rcv(struct sk_buff *buf, struct tipc_bearer *b_ptr);
+void tipc_disc_rcv(struct net *net, 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 5e1426f1751f..f69a2fde9f4a 100644
--- a/net/tipc/eth_media.c
+++ b/net/tipc/eth_media.c
@@ -37,8 +37,6 @@
 #include "core.h"
 #include "bearer.h"
 
-#define ETH_ADDR_OFFSET  4  /* MAC addr position inside address field */
-
 /* Convert Ethernet address (media address format) to string */
 static int tipc_eth_addr2str(struct tipc_media_addr *addr,
 			     char *strbuf, int bufsz)
@@ -53,9 +51,9 @@ static int tipc_eth_addr2str(struct tipc_media_addr *addr,
 /* Convert from media address format to discovery message addr format */
 static int tipc_eth_addr2msg(char *msg, struct tipc_media_addr *addr)
 {
-	memset(msg, 0, TIPC_MEDIA_ADDR_SIZE);
+	memset(msg, 0, TIPC_MEDIA_INFO_SIZE);
 	msg[TIPC_MEDIA_TYPE_OFFSET] = TIPC_MEDIA_TYPE_ETH;
-	memcpy(msg + ETH_ADDR_OFFSET, addr->value, ETH_ALEN);
+	memcpy(msg + TIPC_MEDIA_ADDR_OFFSET, addr->value, ETH_ALEN);
 	return 0;
 }
 
@@ -79,7 +77,7 @@ static int tipc_eth_msg2addr(struct tipc_bearer *b,
 			     char *msg)
 {
 	/* Skip past preamble: */
-	msg += ETH_ADDR_OFFSET;
+	msg += TIPC_MEDIA_ADDR_OFFSET;
 	return tipc_eth_raw2addr(b, addr, msg);
 }
 
diff --git a/net/tipc/ib_media.c b/net/tipc/ib_media.c
index 8522eef9c136..e8c16718e3fa 100644
--- a/net/tipc/ib_media.c
+++ b/net/tipc/ib_media.c
@@ -57,7 +57,7 @@ static int tipc_ib_addr2str(struct tipc_media_addr *a, char *str_buf,
 /* Convert from media address format to discovery message addr format */
 static int tipc_ib_addr2msg(char *msg, struct tipc_media_addr *addr)
 {
-	memset(msg, 0, TIPC_MEDIA_ADDR_SIZE);
+	memset(msg, 0, TIPC_MEDIA_INFO_SIZE);
 	memcpy(msg, addr->value, INFINIBAND_ALEN);
 	return 0;
 }
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 1db162aa64a5..43a515dc97b0 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, 2012-2014, Ericsson AB
+ * Copyright (c) 1996-2007, 2012-2015, Ericsson AB
  * Copyright (c) 2004-2007, 2010-2013, Wind River Systems
  * All rights reserved.
  *
@@ -35,11 +35,13 @@
  */
 
 #include "core.h"
+#include "subscr.h"
 #include "link.h"
+#include "bcast.h"
 #include "socket.h"
 #include "name_distr.h"
 #include "discover.h"
-#include "config.h"
+#include "netlink.h"
 
 #include <linux/pkt_sched.h>
 
@@ -50,6 +52,30 @@ static const char *link_co_err = "Link changeover error, ";
 static const char *link_rst_msg = "Resetting link ";
 static const char *link_unk_evt = "Unknown link event ";
 
+static const struct nla_policy tipc_nl_link_policy[TIPC_NLA_LINK_MAX + 1] = {
+	[TIPC_NLA_LINK_UNSPEC]		= { .type = NLA_UNSPEC },
+	[TIPC_NLA_LINK_NAME] = {
+		.type = NLA_STRING,
+		.len = TIPC_MAX_LINK_NAME
+	},
+	[TIPC_NLA_LINK_MTU]		= { .type = NLA_U32 },
+	[TIPC_NLA_LINK_BROADCAST]	= { .type = NLA_FLAG },
+	[TIPC_NLA_LINK_UP]		= { .type = NLA_FLAG },
+	[TIPC_NLA_LINK_ACTIVE]		= { .type = NLA_FLAG },
+	[TIPC_NLA_LINK_PROP]		= { .type = NLA_NESTED },
+	[TIPC_NLA_LINK_STATS]		= { .type = NLA_NESTED },
+	[TIPC_NLA_LINK_RX]		= { .type = NLA_U32 },
+	[TIPC_NLA_LINK_TX]		= { .type = NLA_U32 }
+};
+
+/* Properties valid for media, bearar and link */
+static const struct nla_policy tipc_nl_prop_policy[TIPC_NLA_PROP_MAX + 1] = {
+	[TIPC_NLA_PROP_UNSPEC]		= { .type = NLA_UNSPEC },
+	[TIPC_NLA_PROP_PRIO]		= { .type = NLA_U32 },
+	[TIPC_NLA_PROP_TOL]		= { .type = NLA_U32 },
+	[TIPC_NLA_PROP_WIN]		= { .type = NLA_U32 }
+};
+
 /*
  * Out-of-range value for link session numbers
  */
@@ -63,32 +89,23 @@ static const char *link_unk_evt = "Unknown link event ";
 #define  TIMEOUT_EVT     560817u	/* link timer expired */
 
 /*
- * The following two 'message types' is really just implementation
- * data conveniently stored in the message header.
- * They must not be considered part of the protocol
+ * State value stored in 'failover_pkts'
  */
-#define OPEN_MSG   0
-#define CLOSED_MSG 1
+#define FIRST_FAILOVER 0xffffu
 
-/*
- * State value stored in 'exp_msg_count'
- */
-#define START_CHANGEOVER 100000u
-
-static void link_handle_out_of_seq_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 void link_handle_out_of_seq_msg(struct tipc_link *link,
+				       struct sk_buff *skb);
+static void tipc_link_proto_rcv(struct tipc_link *link,
+				struct sk_buff *skb);
+static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tol);
 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 tipc_link_sync_xmit(struct tipc_link *l);
 static void tipc_link_sync_rcv(struct tipc_node *n, struct sk_buff *buf);
-static int tipc_link_input(struct tipc_link *l, struct sk_buff *buf);
-static int tipc_link_prepare_input(struct tipc_link *l, struct sk_buff **buf);
-
+static void tipc_link_input(struct tipc_link *l, struct sk_buff *skb);
+static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb);
+static bool tipc_link_failover_rcv(struct tipc_link *l, struct sk_buff **skb);
 /*
  *  Simple link routines
  */
@@ -97,42 +114,26 @@ static unsigned int align(unsigned int i)
 	return (i + 3) & ~3u;
 }
 
-static void link_init_max_pkt(struct tipc_link *l_ptr)
+static void tipc_link_release(struct kref *kref)
 {
-	struct tipc_bearer *b_ptr;
-	u32 max_pkt;
-
-	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;
-
-	l_ptr->max_pkt_target = max_pkt;
-	if (l_ptr->max_pkt_target < MAX_PKT_DEFAULT)
-		l_ptr->max_pkt = l_ptr->max_pkt_target;
-	else
-		l_ptr->max_pkt = MAX_PKT_DEFAULT;
+	kfree(container_of(kref, struct tipc_link, ref));
+}
 
-	l_ptr->max_pkt_probes = 0;
+static void tipc_link_get(struct tipc_link *l_ptr)
+{
+	kref_get(&l_ptr->ref);
 }
 
-static u32 link_next_sent(struct tipc_link *l_ptr)
+static void tipc_link_put(struct tipc_link *l_ptr)
 {
-	if (l_ptr->next_out)
-		return buf_seqno(l_ptr->next_out);
-	return mod(l_ptr->next_out_no);
+	kref_put(&l_ptr->ref, tipc_link_release);
 }
 
-static u32 link_last_sent(struct tipc_link *l_ptr)
+static struct tipc_link *tipc_parallel_link(struct tipc_link *l)
 {
-	return mod(link_next_sent(l_ptr) - 1);
+	if (l->owner->active_links[0] != l)
+		return l->owner->active_links[0];
+	return l->owner->active_links[1];
 }
 
 /*
@@ -155,16 +156,20 @@ int tipc_link_is_active(struct tipc_link *l_ptr)
  * link_timeout - handle expiration of link timer
  * @l_ptr: pointer to link
  */
-static void link_timeout(struct tipc_link *l_ptr)
+static void link_timeout(unsigned long data)
 {
+	struct tipc_link *l_ptr = (struct tipc_link *)data;
+	struct sk_buff *skb;
+
 	tipc_node_lock(l_ptr->owner);
 
 	/* update counters used in statistical profiling of send traffic */
-	l_ptr->stats.accu_queue_sz += l_ptr->out_queue_size;
+	l_ptr->stats.accu_queue_sz += skb_queue_len(&l_ptr->transmq);
 	l_ptr->stats.queue_sz_counts++;
 
-	if (l_ptr->first_out) {
-		struct tipc_msg *msg = buf_msg(l_ptr->first_out);
+	skb = skb_peek(&l_ptr->transmq);
+	if (skb) {
+		struct tipc_msg *msg = buf_msg(skb);
 		u32 length = msg_size(msg);
 
 		if ((msg_user(msg) == MSG_FRAGMENTER) &&
@@ -192,18 +197,19 @@ static void link_timeout(struct tipc_link *l_ptr)
 	}
 
 	/* do all other link processing performed on a periodic basis */
-
 	link_state_event(l_ptr, TIMEOUT_EVT);
 
-	if (l_ptr->next_out)
-		tipc_link_push_queue(l_ptr);
+	if (skb_queue_len(&l_ptr->backlogq))
+		tipc_link_push_packets(l_ptr);
 
 	tipc_node_unlock(l_ptr->owner);
+	tipc_link_put(l_ptr);
 }
 
-static void link_set_timer(struct tipc_link *l_ptr, u32 time)
+static void link_set_timer(struct tipc_link *link, unsigned long time)
 {
-	k_start_timer(&l_ptr->timer, time);
+	if (!mod_timer(&link->timer, jiffies + time))
+		tipc_link_get(link);
 }
 
 /**
@@ -218,15 +224,17 @@ 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_net *tn = net_generic(n_ptr->net, tipc_net_id);
 	struct tipc_link *l_ptr;
 	struct tipc_msg *msg;
 	char *if_name;
 	char addr_string[16];
 	u32 peer = n_ptr->addr;
 
-	if (n_ptr->link_cnt >= 2) {
+	if (n_ptr->link_cnt >= MAX_BEARERS) {
 		tipc_addr_string_fill(addr_string, n_ptr->addr);
-		pr_err("Attempt to establish third link to %s\n", addr_string);
+		pr_err("Attempt to establish %uth link to %s. Max %u allowed.\n",
+			n_ptr->link_cnt, addr_string, MAX_BEARERS);
 		return NULL;
 	}
 
@@ -242,12 +250,12 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr,
 		pr_warn("Link creation failed, no memory\n");
 		return NULL;
 	}
-
+	kref_init(&l_ptr->ref);
 	l_ptr->addr = peer;
 	if_name = strchr(b_ptr->name, ':') + 1;
 	sprintf(l_ptr->name, "%u.%u.%u:%s-%u.%u.%u:unknown",
-		tipc_zone(tipc_own_addr), tipc_cluster(tipc_own_addr),
-		tipc_node(tipc_own_addr),
+		tipc_zone(tn->own_addr), tipc_cluster(tn->own_addr),
+		tipc_node(tn->own_addr),
 		if_name,
 		tipc_zone(peer), tipc_cluster(peer), tipc_node(peer));
 		/* note: peer i/f name is updated by reset/activate message */
@@ -261,87 +269,104 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr,
 
 	l_ptr->pmsg = (struct tipc_msg *)&l_ptr->proto_msg;
 	msg = l_ptr->pmsg;
-	tipc_msg_init(msg, LINK_PROTOCOL, RESET_MSG, INT_H_SIZE, l_ptr->addr);
+	tipc_msg_init(tn->own_addr, msg, LINK_PROTOCOL, RESET_MSG, INT_H_SIZE,
+		      l_ptr->addr);
 	msg_set_size(msg, sizeof(l_ptr->proto_msg));
-	msg_set_session(msg, (tipc_random & 0xffff));
+	msg_set_session(msg, (tn->random & 0xffff));
 	msg_set_bearer_id(msg, b_ptr->identity);
 	strcpy((char *)msg_data(msg), if_name);
-
+	l_ptr->net_plane = b_ptr->net_plane;
+	l_ptr->advertised_mtu = b_ptr->mtu;
+	l_ptr->mtu = l_ptr->advertised_mtu;
 	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;
-	__skb_queue_head_init(&l_ptr->waiting_sks);
-
+	__skb_queue_head_init(&l_ptr->transmq);
+	__skb_queue_head_init(&l_ptr->backlogq);
+	__skb_queue_head_init(&l_ptr->deferdq);
+	skb_queue_head_init(&l_ptr->wakeupq);
+	skb_queue_head_init(&l_ptr->inputq);
+	skb_queue_head_init(&l_ptr->namedq);
 	link_reset_statistics(l_ptr);
-
 	tipc_node_attach_link(n_ptr, l_ptr);
-
-	k_init_timer(&l_ptr->timer, (Handler)link_timeout,
-		     (unsigned long)l_ptr);
-
+	setup_timer(&l_ptr->timer, link_timeout, (unsigned long)l_ptr);
 	link_state_event(l_ptr, STARTING_EVT);
 
 	return l_ptr;
 }
 
-void tipc_link_delete_list(unsigned int bearer_id, bool shutting_down)
+/**
+ * tipc_link_delete - Delete a link
+ * @l: link to be deleted
+ */
+void tipc_link_delete(struct tipc_link *l)
 {
-	struct tipc_link *l_ptr;
-	struct tipc_node *n_ptr;
+	tipc_link_reset(l);
+	if (del_timer(&l->timer))
+		tipc_link_put(l);
+	l->flags |= LINK_STOPPED;
+	/* Delete link now, or when timer is finished: */
+	tipc_link_reset_fragments(l);
+	tipc_node_detach_link(l->owner, l);
+	tipc_link_put(l);
+}
+
+void tipc_link_delete_list(struct net *net, unsigned int bearer_id,
+			   bool shutting_down)
+{
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	struct tipc_link *link;
+	struct tipc_node *node;
 
 	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);
-
-				/* 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);
+	list_for_each_entry_rcu(node, &tn->node_list, list) {
+		tipc_node_lock(node);
+		link = node->links[bearer_id];
+		if (link)
+			tipc_link_delete(link);
+		tipc_node_unlock(node);
 	}
 	rcu_read_unlock();
 }
 
 /**
- * link_schedule_user - schedule user for wakeup after congestion
+ * link_schedule_user - schedule a message sender for wakeup after congestion
  * @link: congested link
- * @oport: sending port
- * @chain_sz: size of buffer chain that was attempted sent
- * @imp: importance of message attempted sent
+ * @list: message that was attempted sent
  * Create pseudo msg to send back to user when congestion abates
+ * Only consumes message if there is an error
  */
-static bool link_schedule_user(struct tipc_link *link, u32 oport,
-			       uint chain_sz, uint imp)
+static int link_schedule_user(struct tipc_link *link, struct sk_buff_head *list)
 {
-	struct sk_buff *buf;
+	struct tipc_msg *msg = buf_msg(skb_peek(list));
+	int imp = msg_importance(msg);
+	u32 oport = msg_origport(msg);
+	u32 addr = link_own_addr(link);
+	struct sk_buff *skb;
 
-	buf = tipc_msg_create(SOCK_WAKEUP, 0, INT_H_SIZE, 0, tipc_own_addr,
-			      tipc_own_addr, oport, 0, 0);
-	if (!buf)
-		return false;
-	TIPC_SKB_CB(buf)->chain_sz = chain_sz;
-	TIPC_SKB_CB(buf)->chain_imp = imp;
-	__skb_queue_tail(&link->waiting_sks, buf);
+	/* This really cannot happen...  */
+	if (unlikely(imp > TIPC_CRITICAL_IMPORTANCE)) {
+		pr_warn("%s<%s>, send queue full", link_rst_msg, link->name);
+		tipc_link_reset(link);
+		goto err;
+	}
+	/* Non-blocking sender: */
+	if (TIPC_SKB_CB(skb_peek(list))->wakeup_pending)
+		return -ELINKCONG;
+
+	/* Create and schedule wakeup pseudo message */
+	skb = tipc_msg_create(SOCK_WAKEUP, 0, INT_H_SIZE, 0,
+			      addr, addr, oport, 0, 0);
+	if (!skb)
+		goto err;
+	TIPC_SKB_CB(skb)->chain_sz = skb_queue_len(list);
+	TIPC_SKB_CB(skb)->chain_imp = imp;
+	skb_queue_tail(&link->wakeupq, skb);
 	link->stats.link_congs++;
-	return true;
+	return -ELINKCONG;
+err:
+	__skb_queue_purge(list);
+	return -ENOBUFS;
 }
 
 /**
@@ -350,32 +375,26 @@ static bool link_schedule_user(struct tipc_link *link, u32 oport,
  * Move a number of waiting users, as permitted by available space in
  * the send queue, from link wait queue to node wait queue for wakeup
  */
-static void link_prepare_wakeup(struct tipc_link *link)
+void link_prepare_wakeup(struct tipc_link *l)
 {
-	struct sk_buff_head *wq = &link->waiting_sks;
-	struct sk_buff *buf;
-	uint pend_qsz = link->out_queue_size;
-
-	for (buf = skb_peek(wq); buf; buf = skb_peek(wq)) {
-		if (pend_qsz >= link->queue_limit[TIPC_SKB_CB(buf)->chain_imp])
+	int pnd[TIPC_SYSTEM_IMPORTANCE + 1] = {0,};
+	int imp, lim;
+	struct sk_buff *skb, *tmp;
+
+	skb_queue_walk_safe(&l->wakeupq, skb, tmp) {
+		imp = TIPC_SKB_CB(skb)->chain_imp;
+		lim = l->window + l->backlog[imp].limit;
+		pnd[imp] += TIPC_SKB_CB(skb)->chain_sz;
+		if ((pnd[imp] + l->backlog[imp].len) >= lim)
 			break;
-		pend_qsz += TIPC_SKB_CB(buf)->chain_sz;
-		__skb_queue_tail(&link->owner->waiting_sks, __skb_dequeue(wq));
+		skb_unlink(skb, &l->wakeupq);
+		skb_queue_tail(&l->inputq, skb);
+		l->owner->inputq = &l->inputq;
+		l->owner->action_flags |= TIPC_MSG_EVT;
 	}
 }
 
 /**
- * link_release_outqueue - purge link's outbound message queue
- * @l_ptr: pointer to link
- */
-static void link_release_outqueue(struct tipc_link *l_ptr)
-{
-	kfree_skb_list(l_ptr->first_out);
-	l_ptr->first_out = NULL;
-	l_ptr->out_queue_size = 0;
-}
-
-/**
  * tipc_link_reset_fragments - purge link's inbound message fragments queue
  * @l_ptr: pointer to link
  */
@@ -385,33 +404,42 @@ void tipc_link_reset_fragments(struct tipc_link *l_ptr)
 	l_ptr->reasm_buf = NULL;
 }
 
+static void tipc_link_purge_backlog(struct tipc_link *l)
+{
+	__skb_queue_purge(&l->backlogq);
+	l->backlog[TIPC_LOW_IMPORTANCE].len = 0;
+	l->backlog[TIPC_MEDIUM_IMPORTANCE].len = 0;
+	l->backlog[TIPC_HIGH_IMPORTANCE].len = 0;
+	l->backlog[TIPC_CRITICAL_IMPORTANCE].len = 0;
+	l->backlog[TIPC_SYSTEM_IMPORTANCE].len = 0;
+}
+
 /**
  * tipc_link_purge_queues - purge all pkt queues associated with link
  * @l_ptr: pointer to link
  */
 void tipc_link_purge_queues(struct tipc_link *l_ptr)
 {
-	kfree_skb_list(l_ptr->oldest_deferred_in);
-	kfree_skb_list(l_ptr->first_out);
+	__skb_queue_purge(&l_ptr->deferdq);
+	__skb_queue_purge(&l_ptr->transmq);
+	tipc_link_purge_backlog(l_ptr);
 	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)
 {
 	u32 prev_state = l_ptr->state;
-	u32 checkpoint = l_ptr->next_in_no;
 	int was_active_link = tipc_link_is_active(l_ptr);
 	struct tipc_node *owner = l_ptr->owner;
+	struct tipc_link *pl = tipc_parallel_link(l_ptr);
 
 	msg_set_session(l_ptr->pmsg, ((msg_session(l_ptr->pmsg) + 1) & 0xffff));
 
 	/* Link is down, accept any session */
 	l_ptr->peer_session = INVALID_SESSION;
 
-	/* Prepare for max packet size negotiation */
-	link_init_max_pkt(l_ptr);
+	/* Prepare for renewed mtu size negotiation */
+	l_ptr->mtu = l_ptr->advertised_mtu;
 
 	l_ptr->state = RESET_UNKNOWN;
 
@@ -419,45 +447,43 @@ 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->bearer_id, l_ptr->addr);
-
-	if (was_active_link && tipc_node_active_links(l_ptr->owner)) {
-		l_ptr->reset_checkpoint = checkpoint;
-		l_ptr->exp_msg_count = START_CHANGEOVER;
-	}
-
-	/* Clean up all queues: */
-	link_release_outqueue(l_ptr);
-	kfree_skb(l_ptr->proto_msg_queue);
-	l_ptr->proto_msg_queue = NULL;
-	kfree_skb_list(l_ptr->oldest_deferred_in);
-	if (!skb_queue_empty(&l_ptr->waiting_sks)) {
-		skb_queue_splice_init(&l_ptr->waiting_sks, &owner->waiting_sks);
-		owner->action_flags |= TIPC_WAKEUP_USERS;
+	tipc_bearer_remove_dest(owner->net, l_ptr->bearer_id, l_ptr->addr);
+
+	if (was_active_link && tipc_node_is_up(l_ptr->owner) && (pl != l_ptr)) {
+		l_ptr->flags |= LINK_FAILINGOVER;
+		l_ptr->failover_checkpt = l_ptr->next_in_no;
+		pl->failover_pkts = FIRST_FAILOVER;
+		pl->failover_checkpt = l_ptr->next_in_no;
+		pl->failover_skb = l_ptr->reasm_buf;
+	} else {
+		kfree_skb(l_ptr->reasm_buf);
 	}
-	l_ptr->retransm_queue_head = 0;
-	l_ptr->retransm_queue_size = 0;
-	l_ptr->last_out = NULL;
-	l_ptr->first_out = NULL;
-	l_ptr->next_out = NULL;
-	l_ptr->unacked_window = 0;
+	/* Clean up all queues, except inputq: */
+	__skb_queue_purge(&l_ptr->transmq);
+	__skb_queue_purge(&l_ptr->deferdq);
+	if (!owner->inputq)
+		owner->inputq = &l_ptr->inputq;
+	skb_queue_splice_init(&l_ptr->wakeupq, owner->inputq);
+	if (!skb_queue_empty(owner->inputq))
+		owner->action_flags |= TIPC_MSG_EVT;
+	tipc_link_purge_backlog(l_ptr);
+	l_ptr->reasm_buf = NULL;
+	l_ptr->rcv_unacked = 0;
 	l_ptr->checkpoint = 1;
 	l_ptr->next_out_no = 1;
-	l_ptr->deferred_inqueue_sz = 0;
-	l_ptr->oldest_deferred_in = NULL;
-	l_ptr->newest_deferred_in = NULL;
 	l_ptr->fsm_msg_cnt = 0;
 	l_ptr->stale_count = 0;
 	link_reset_statistics(l_ptr);
 }
 
-void tipc_link_reset_list(unsigned int bearer_id)
+void tipc_link_reset_list(struct net *net, unsigned int bearer_id)
 {
+	struct tipc_net *tn = net_generic(net, tipc_net_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) {
+	list_for_each_entry_rcu(n_ptr, &tn->node_list, list) {
 		tipc_node_lock(n_ptr);
 		l_ptr = n_ptr->links[bearer_id];
 		if (l_ptr)
@@ -467,11 +493,14 @@ void tipc_link_reset_list(unsigned int bearer_id)
 	rcu_read_unlock();
 }
 
-static void link_activate(struct tipc_link *l_ptr)
+static void link_activate(struct tipc_link *link)
 {
-	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->bearer_id, l_ptr->addr);
+	struct tipc_node *node = link->owner;
+
+	link->next_in_no = 1;
+	link->stats.recv_info = 1;
+	tipc_node_link_up(node, link);
+	tipc_bearer_add_dest(node->net, link->bearer_id, link->addr);
 }
 
 /**
@@ -482,7 +511,7 @@ static void link_activate(struct tipc_link *l_ptr)
 static void link_state_event(struct tipc_link *l_ptr, unsigned int event)
 {
 	struct tipc_link *other;
-	u32 cont_intv = l_ptr->continuity_interval;
+	unsigned long cont_intv = l_ptr->cont_intv;
 
 	if (l_ptr->flags & LINK_STOPPED)
 		return;
@@ -490,8 +519,7 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event)
 	if (!(l_ptr->flags & LINK_STARTED) && (event != STARTING_EVT))
 		return;		/* Not yet. */
 
-	/* Check whether changeover is going on */
-	if (l_ptr->exp_msg_count) {
+	if (l_ptr->flags & LINK_FAILINGOVER) {
 		if (event == TIMEOUT_EVT)
 			link_set_timer(l_ptr, cont_intv);
 		return;
@@ -508,11 +536,7 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event)
 				l_ptr->checkpoint = l_ptr->next_in_no;
 				if (tipc_bclink_acks_missing(l_ptr->owner)) {
 					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_proto_xmit(l_ptr, STATE_MSG,
-							     1, 0, 0, 0, 0);
+							     0, 0, 0, 0);
 					l_ptr->fsm_msg_cnt++;
 				}
 				link_set_timer(l_ptr, cont_intv);
@@ -520,23 +544,23 @@ 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_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0, 0);
+			tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0);
 			l_ptr->fsm_msg_cnt++;
 			link_set_timer(l_ptr, cont_intv / 4);
 			break;
 		case RESET_MSG:
-			pr_info("%s<%s>, requested by peer\n", link_rst_msg,
-				l_ptr->name);
+			pr_debug("%s<%s>, requested by peer\n",
+				 link_rst_msg, l_ptr->name);
 			tipc_link_reset(l_ptr);
 			l_ptr->state = RESET_RESET;
 			l_ptr->fsm_msg_cnt = 0;
 			tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG,
-					     0, 0, 0, 0, 0);
+					     0, 0, 0, 0);
 			l_ptr->fsm_msg_cnt++;
 			link_set_timer(l_ptr, cont_intv);
 			break;
 		default:
-			pr_err("%s%u in WW state\n", link_unk_evt, event);
+			pr_debug("%s%u in WW state\n", link_unk_evt, event);
 		}
 		break;
 	case WORKING_UNKNOWN:
@@ -548,13 +572,13 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event)
 			link_set_timer(l_ptr, cont_intv);
 			break;
 		case RESET_MSG:
-			pr_info("%s<%s>, requested by peer while probing\n",
-				link_rst_msg, l_ptr->name);
+			pr_debug("%s<%s>, requested by peer while probing\n",
+				 link_rst_msg, l_ptr->name);
 			tipc_link_reset(l_ptr);
 			l_ptr->state = RESET_RESET;
 			l_ptr->fsm_msg_cnt = 0;
 			tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG,
-					     0, 0, 0, 0, 0);
+					     0, 0, 0, 0);
 			l_ptr->fsm_msg_cnt++;
 			link_set_timer(l_ptr, cont_intv);
 			break;
@@ -565,23 +589,23 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event)
 				l_ptr->checkpoint = l_ptr->next_in_no;
 				if (tipc_bclink_acks_missing(l_ptr->owner)) {
 					tipc_link_proto_xmit(l_ptr, STATE_MSG,
-							     0, 0, 0, 0, 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_proto_xmit(l_ptr, STATE_MSG,
-						     1, 0, 0, 0, 0);
+						     1, 0, 0, 0);
 				l_ptr->fsm_msg_cnt++;
 				link_set_timer(l_ptr, cont_intv / 4);
 			} else {	/* Link has failed */
-				pr_warn("%s<%s>, peer not responding\n",
-					link_rst_msg, l_ptr->name);
+				pr_debug("%s<%s>, peer not responding\n",
+					 link_rst_msg, l_ptr->name);
 				tipc_link_reset(l_ptr);
 				l_ptr->state = RESET_UNKNOWN;
 				l_ptr->fsm_msg_cnt = 0;
 				tipc_link_proto_xmit(l_ptr, RESET_MSG,
-						     0, 0, 0, 0, 0);
+						     0, 0, 0, 0);
 				l_ptr->fsm_msg_cnt++;
 				link_set_timer(l_ptr, cont_intv);
 			}
@@ -601,7 +625,7 @@ 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_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0, 0);
+			tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0);
 			l_ptr->fsm_msg_cnt++;
 			if (l_ptr->owner->working_links == 1)
 				tipc_link_sync_xmit(l_ptr);
@@ -611,15 +635,17 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event)
 			l_ptr->state = RESET_RESET;
 			l_ptr->fsm_msg_cnt = 0;
 			tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG,
-					     1, 0, 0, 0, 0);
+					     1, 0, 0, 0);
 			l_ptr->fsm_msg_cnt++;
 			link_set_timer(l_ptr, cont_intv);
 			break;
 		case STARTING_EVT:
 			l_ptr->flags |= LINK_STARTED;
-			/* fall through */
+			l_ptr->fsm_msg_cnt++;
+			link_set_timer(l_ptr, cont_intv);
+			break;
 		case TIMEOUT_EVT:
-			tipc_link_proto_xmit(l_ptr, RESET_MSG, 0, 0, 0, 0, 0);
+			tipc_link_proto_xmit(l_ptr, RESET_MSG, 0, 0, 0, 0);
 			l_ptr->fsm_msg_cnt++;
 			link_set_timer(l_ptr, cont_intv);
 			break;
@@ -637,7 +663,7 @@ 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_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0, 0);
+			tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0);
 			l_ptr->fsm_msg_cnt++;
 			if (l_ptr->owner->working_links == 1)
 				tipc_link_sync_xmit(l_ptr);
@@ -647,7 +673,7 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event)
 			break;
 		case TIMEOUT_EVT:
 			tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG,
-					     0, 0, 0, 0, 0);
+					     0, 0, 0, 0);
 			l_ptr->fsm_msg_cnt++;
 			link_set_timer(l_ptr, cont_intv);
 			break;
@@ -660,145 +686,141 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event)
 	}
 }
 
-/* tipc_link_cong: determine return value and how to treat the
- * sent buffer during link congestion.
- * - For plain, errorless user data messages we keep the buffer and
- *   return -ELINKONG.
- * - For all other messages we discard the buffer and return -EHOSTUNREACH
- * - For TIPC internal messages we also reset the link
- */
-static int tipc_link_cong(struct tipc_link *link, struct sk_buff *buf)
-{
-	struct tipc_msg *msg = buf_msg(buf);
-	uint imp = tipc_msg_tot_importance(msg);
-	u32 oport = msg_tot_origport(msg);
-
-	if (unlikely(imp > TIPC_CRITICAL_IMPORTANCE)) {
-		pr_warn("%s<%s>, send queue full", link_rst_msg, link->name);
-		tipc_link_reset(link);
-		goto drop;
-	}
-	if (unlikely(msg_errcode(msg)))
-		goto drop;
-	if (unlikely(msg_reroute_cnt(msg)))
-		goto drop;
-	if (TIPC_SKB_CB(buf)->wakeup_pending)
-		return -ELINKCONG;
-	if (link_schedule_user(link, oport, TIPC_SKB_CB(buf)->chain_sz, imp))
-		return -ELINKCONG;
-drop:
-	kfree_skb_list(buf);
-	return -EHOSTUNREACH;
-}
-
 /**
  * __tipc_link_xmit(): same as tipc_link_xmit, but destlink is known & locked
  * @link: link to use
- * @buf: chain of buffers containing message
- * Consumes the buffer chain, except when returning -ELINKCONG
- * Returns 0 if success, otherwise errno: -ELINKCONG, -EMSGSIZE (plain socket
- * user data messages) or -EHOSTUNREACH (all other messages/senders)
- * Only the socket functions tipc_send_stream() and tipc_send_packet() need
- * to act on the return value, since they may need to do more send attempts.
+ * @list: chain of buffers containing message
+ *
+ * Consumes the buffer chain, except when returning -ELINKCONG,
+ * since the caller then may want to make more send attempts.
+ * Returns 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS
+ * Messages at TIPC_SYSTEM_IMPORTANCE are always accepted
  */
-int __tipc_link_xmit(struct tipc_link *link, struct sk_buff *buf)
+int __tipc_link_xmit(struct net *net, struct tipc_link *link,
+		     struct sk_buff_head *list)
 {
-	struct tipc_msg *msg = buf_msg(buf);
-	uint psz = msg_size(msg);
-	uint qsz = link->out_queue_size;
-	uint sndlim = link->queue_limit[0];
-	uint imp = tipc_msg_tot_importance(msg);
-	uint mtu = link->max_pkt;
+	struct tipc_msg *msg = buf_msg(skb_peek(list));
+	unsigned int maxwin = link->window;
+	unsigned int imp = msg_importance(msg);
+	uint mtu = link->mtu;
 	uint ack = mod(link->next_in_no - 1);
 	uint seqno = link->next_out_no;
 	uint bc_last_in = link->owner->bclink.last_in;
 	struct tipc_media_addr *addr = &link->media_addr;
-	struct sk_buff *next = buf->next;
+	struct sk_buff_head *transmq = &link->transmq;
+	struct sk_buff_head *backlogq = &link->backlogq;
+	struct sk_buff *skb, *tmp;
 
-	/* Match queue limits against msg importance: */
-	if (unlikely(qsz >= link->queue_limit[imp]))
-		return tipc_link_cong(link, buf);
+	/* Match backlog limit against msg importance: */
+	if (unlikely(link->backlog[imp].len >= link->backlog[imp].limit))
+		return link_schedule_user(link, list);
 
-	/* Has valid packet limit been used ? */
-	if (unlikely(psz > mtu)) {
-		kfree_skb_list(buf);
+	if (unlikely(msg_size(msg) > mtu)) {
+		__skb_queue_purge(list);
 		return -EMSGSIZE;
 	}
-
-	/* Prepare each packet for sending, and add to outqueue: */
-	while (buf) {
-		next = buf->next;
-		msg = buf_msg(buf);
-		msg_set_word(msg, 2, ((ack << 16) | mod(seqno)));
+	/* Prepare each packet for sending, and add to relevant queue: */
+	skb_queue_walk_safe(list, skb, tmp) {
+		__skb_unlink(skb, list);
+		msg = buf_msg(skb);
+		msg_set_seqno(msg, seqno);
+		msg_set_ack(msg, ack);
 		msg_set_bcast_ack(msg, bc_last_in);
 
-		if (!link->first_out) {
-			link->first_out = buf;
-		} else if (qsz < sndlim) {
-			link->last_out->next = buf;
-		} else if (tipc_msg_bundle(link->last_out, buf, mtu)) {
+		if (likely(skb_queue_len(transmq) < maxwin)) {
+			__skb_queue_tail(transmq, skb);
+			tipc_bearer_send(net, link->bearer_id, skb, addr);
+			link->rcv_unacked = 0;
+			seqno++;
+			continue;
+		}
+		if (tipc_msg_bundle(skb_peek_tail(backlogq), skb, mtu)) {
 			link->stats.sent_bundled++;
-			buf = next;
-			next = buf->next;
 			continue;
-		} else if (tipc_msg_make_bundle(&buf, mtu, link->addr)) {
+		}
+		if (tipc_msg_make_bundle(&skb, mtu, link->addr)) {
 			link->stats.sent_bundled++;
 			link->stats.sent_bundles++;
-			link->last_out->next = buf;
-			if (!link->next_out)
-				link->next_out = buf;
-		} else {
-			link->last_out->next = buf;
-			if (!link->next_out)
-				link->next_out = buf;
-		}
-
-		/* Send packet if possible: */
-		if (likely(++qsz <= sndlim)) {
-			tipc_bearer_send(link->bearer_id, buf, addr);
-			link->next_out = next;
-			link->unacked_window = 0;
+			imp = msg_importance(buf_msg(skb));
 		}
+		__skb_queue_tail(backlogq, skb);
+		link->backlog[imp].len++;
 		seqno++;
-		link->last_out = buf;
-		buf = next;
 	}
 	link->next_out_no = seqno;
-	link->out_queue_size = qsz;
+	return 0;
+}
+
+static void skb2list(struct sk_buff *skb, struct sk_buff_head *list)
+{
+	skb_queue_head_init(list);
+	__skb_queue_tail(list, skb);
+}
+
+static int __tipc_link_xmit_skb(struct tipc_link *link, struct sk_buff *skb)
+{
+	struct sk_buff_head head;
+
+	skb2list(skb, &head);
+	return __tipc_link_xmit(link->owner->net, link, &head);
+}
+
+/* tipc_link_xmit_skb(): send single buffer to destination
+ * Buffers sent via this functon are generally TIPC_SYSTEM_IMPORTANCE
+ * messages, which will not be rejected
+ * The only exception is datagram messages rerouted after secondary
+ * lookup, which are rare and safe to dispose of anyway.
+ * TODO: Return real return value, and let callers use
+ * tipc_wait_for_sendpkt() where applicable
+ */
+int tipc_link_xmit_skb(struct net *net, struct sk_buff *skb, u32 dnode,
+		       u32 selector)
+{
+	struct sk_buff_head head;
+	int rc;
+
+	skb2list(skb, &head);
+	rc = tipc_link_xmit(net, &head, dnode, selector);
+	if (rc == -ELINKCONG)
+		kfree_skb(skb);
 	return 0;
 }
 
 /**
  * tipc_link_xmit() is the general link level function for message sending
- * @buf: chain of buffers containing message
+ * @net: the applicable net namespace
+ * @list: chain of buffers containing message
  * @dsz: amount of user data to be sent
  * @dnode: address of destination node
  * @selector: a number used for deterministic link selection
  * Consumes the buffer chain, except when returning -ELINKCONG
  * Returns 0 if success, otherwise errno: -ELINKCONG,-EHOSTUNREACH,-EMSGSIZE
  */
-int tipc_link_xmit(struct sk_buff *buf, u32 dnode, u32 selector)
+int tipc_link_xmit(struct net *net, struct sk_buff_head *list, u32 dnode,
+		   u32 selector)
 {
 	struct tipc_link *link = NULL;
 	struct tipc_node *node;
 	int rc = -EHOSTUNREACH;
 
-	node = tipc_node_find(dnode);
+	node = tipc_node_find(net, dnode);
 	if (node) {
 		tipc_node_lock(node);
 		link = node->active_links[selector & 1];
 		if (link)
-			rc = __tipc_link_xmit(link, buf);
+			rc = __tipc_link_xmit(net, link, list);
 		tipc_node_unlock(node);
+		tipc_node_put(node);
 	}
-
 	if (link)
 		return rc;
 
-	if (likely(in_own_node(dnode)))
-		return tipc_sk_rcv(buf);
+	if (likely(in_own_node(net, dnode))) {
+		tipc_sk_rcv(net, list);
+		return 0;
+	}
 
-	kfree_skb_list(buf);
+	__skb_queue_purge(list);
 	return rc;
 }
 
@@ -812,17 +834,18 @@ int tipc_link_xmit(struct sk_buff *buf, u32 dnode, u32 selector)
  */
 static void tipc_link_sync_xmit(struct tipc_link *link)
 {
-	struct sk_buff *buf;
+	struct sk_buff *skb;
 	struct tipc_msg *msg;
 
-	buf = tipc_buf_acquire(INT_H_SIZE);
-	if (!buf)
+	skb = tipc_buf_acquire(INT_H_SIZE);
+	if (!skb)
 		return;
 
-	msg = buf_msg(buf);
-	tipc_msg_init(msg, BCAST_PROTOCOL, STATE_MSG, INT_H_SIZE, link->addr);
+	msg = buf_msg(skb);
+	tipc_msg_init(link_own_addr(link), msg, BCAST_PROTOCOL, STATE_MSG,
+		      INT_H_SIZE, link->addr);
 	msg_set_last_bcast(msg, link->owner->bclink.acked);
-	__tipc_link_xmit(link, buf);
+	__tipc_link_xmit_skb(link, skb);
 }
 
 /*
@@ -843,84 +866,32 @@ static void tipc_link_sync_rcv(struct tipc_node *n, struct sk_buff *buf)
 }
 
 /*
- * tipc_link_push_packet: Push one unsent packet to the media
+ * tipc_link_push_packets - push unsent packets to bearer
+ *
+ * Push out the unsent messages of a link where congestion
+ * has abated. Node is locked.
+ *
+ * Called with node locked
  */
-static u32 tipc_link_push_packet(struct tipc_link *l_ptr)
+void tipc_link_push_packets(struct tipc_link *link)
 {
-	struct sk_buff *buf = l_ptr->first_out;
-	u32 r_q_size = l_ptr->retransm_queue_size;
-	u32 r_q_head = l_ptr->retransm_queue_head;
-
-	/* Step to position where retransmission failed, if any,    */
-	/* consider that buffers may have been released in meantime */
-	if (r_q_size && buf) {
-		u32 last = lesser(mod(r_q_head + r_q_size),
-				  link_last_sent(l_ptr));
-		u32 first = buf_seqno(buf);
-
-		while (buf && less(first, r_q_head)) {
-			first = mod(first + 1);
-			buf = buf->next;
-		}
-		l_ptr->retransm_queue_head = r_q_head = first;
-		l_ptr->retransm_queue_size = r_q_size = mod(last - first);
-	}
-
-	/* Continue retransmission now, if there is anything: */
-	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->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++;
-		return 0;
-	}
-
-	/* Send deferred protocol message, if any: */
-	buf = l_ptr->proto_msg_queue;
-	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->bearer_id, buf, &l_ptr->media_addr);
-		l_ptr->unacked_window = 0;
-		kfree_skb(buf);
-		l_ptr->proto_msg_queue = NULL;
-		return 0;
-	}
+	struct sk_buff *skb;
+	struct tipc_msg *msg;
+	unsigned int ack = mod(link->next_in_no - 1);
 
-	/* Send one deferred data message, if send window not full: */
-	buf = l_ptr->next_out;
-	if (buf) {
-		struct tipc_msg *msg = buf_msg(buf);
-		u32 next = msg_seqno(msg);
-		u32 first = buf_seqno(l_ptr->first_out);
-
-		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->bearer_id, buf,
-					 &l_ptr->media_addr);
-			if (msg_user(msg) == MSG_BUNDLER)
-				msg_set_type(msg, BUNDLE_CLOSED);
-			l_ptr->next_out = buf->next;
-			return 0;
-		}
+	while (skb_queue_len(&link->transmq) < link->window) {
+		skb = __skb_dequeue(&link->backlogq);
+		if (!skb)
+			break;
+		msg = buf_msg(skb);
+		link->backlog[msg_importance(msg)].len--;
+		msg_set_ack(msg, ack);
+		msg_set_bcast_ack(msg, link->owner->bclink.last_in);
+		link->rcv_unacked = 0;
+		__skb_queue_tail(&link->transmq, skb);
+		tipc_bearer_send(link->owner->net, link->bearer_id,
+				 skb, &link->media_addr);
 	}
-	return 1;
-}
-
-/*
- * push_queue(): push out the unsent messages of a link where
- *               congestion has abated. Node is locked
- */
-void tipc_link_push_queue(struct tipc_link *l_ptr)
-{
-	u32 res;
-
-	do {
-		res = tipc_link_push_packet(l_ptr);
-	} while (!res);
 }
 
 void tipc_link_reset_all(struct tipc_node *node)
@@ -947,6 +918,7 @@ static void link_retransmit_failure(struct tipc_link *l_ptr,
 				    struct sk_buff *buf)
 {
 	struct tipc_msg *msg = buf_msg(buf);
+	struct net *net = l_ptr->owner->net;
 
 	pr_warn("Retransmission failure on link <%s>\n", l_ptr->name);
 
@@ -964,8 +936,7 @@ static void link_retransmit_failure(struct tipc_link *l_ptr,
 		pr_cont("Outstanding acks: %lu\n",
 			(unsigned long) TIPC_SKB_CB(buf)->handle);
 
-		n_ptr = tipc_bclink_retransmit_to();
-		tipc_node_lock(n_ptr);
+		n_ptr = tipc_bclink_retransmit_to(net);
 
 		tipc_addr_string_fill(addr_string, n_ptr->addr);
 		pr_info("Broadcast link info for %s\n", addr_string);
@@ -977,27 +948,25 @@ static void link_retransmit_failure(struct tipc_link *l_ptr,
 			n_ptr->bclink.oos_state,
 			n_ptr->bclink.last_sent);
 
-		tipc_node_unlock(n_ptr);
-
-		tipc_bclink_set_flags(TIPC_BCLINK_RESET);
+		n_ptr->action_flags |= TIPC_BCAST_RESET;
 		l_ptr->stale_count = 0;
 	}
 }
 
-void tipc_link_retransmit(struct tipc_link *l_ptr, struct sk_buff *buf,
+void tipc_link_retransmit(struct tipc_link *l_ptr, struct sk_buff *skb,
 			  u32 retransmits)
 {
 	struct tipc_msg *msg;
 
-	if (!buf)
+	if (!skb)
 		return;
 
-	msg = buf_msg(buf);
+	msg = buf_msg(skb);
 
 	/* Detect repeated retransmit failures */
 	if (l_ptr->last_retransmitted == msg_seqno(msg)) {
 		if (++l_ptr->stale_count > 100) {
-			link_retransmit_failure(l_ptr, buf);
+			link_retransmit_failure(l_ptr, skb);
 			return;
 		}
 	} else {
@@ -1005,152 +974,111 @@ void tipc_link_retransmit(struct tipc_link *l_ptr, struct sk_buff *buf,
 		l_ptr->stale_count = 1;
 	}
 
-	while (retransmits && (buf != l_ptr->next_out) && buf) {
-		msg = buf_msg(buf);
+	skb_queue_walk_from(&l_ptr->transmq, skb) {
+		if (!retransmits)
+			break;
+		msg = buf_msg(skb);
 		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->bearer_id, buf, &l_ptr->media_addr);
-		buf = buf->next;
+		tipc_bearer_send(l_ptr->owner->net, l_ptr->bearer_id, skb,
+				 &l_ptr->media_addr);
 		retransmits--;
 		l_ptr->stats.retransmitted++;
 	}
-
-	l_ptr->retransm_queue_head = l_ptr->retransm_queue_size = 0;
 }
 
-/**
- * link_insert_deferred_queue - insert deferred messages back into receive chain
+/* link_synch(): check if all packets arrived before the synch
+ *               point have been consumed
+ * Returns true if the parallel links are synched, otherwise false
  */
-static struct sk_buff *link_insert_deferred_queue(struct tipc_link *l_ptr,
-						  struct sk_buff *buf)
+static bool link_synch(struct tipc_link *l)
 {
-	u32 seq_no;
+	unsigned int post_synch;
+	struct tipc_link *pl;
 
-	if (l_ptr->oldest_deferred_in == NULL)
-		return buf;
+	pl  = tipc_parallel_link(l);
+	if (pl == l)
+		goto synched;
 
-	seq_no = buf_seqno(l_ptr->oldest_deferred_in);
-	if (seq_no == mod(l_ptr->next_in_no)) {
-		l_ptr->newest_deferred_in->next = buf;
-		buf = l_ptr->oldest_deferred_in;
-		l_ptr->oldest_deferred_in = NULL;
-		l_ptr->deferred_inqueue_sz = 0;
-	}
-	return buf;
+	/* Was last pre-synch packet added to input queue ? */
+	if (less_eq(pl->next_in_no, l->synch_point))
+		return false;
+
+	/* Is it still in the input queue ? */
+	post_synch = mod(pl->next_in_no - l->synch_point) - 1;
+	if (skb_queue_len(&pl->inputq) > post_synch)
+		return false;
+synched:
+	l->flags &= ~LINK_SYNCHING;
+	return true;
 }
 
-/**
- * link_recv_buf_validate - validate basic format of received message
- *
- * This routine ensures a TIPC message has an acceptable header, and at least
- * as much data as the header indicates it should.  The routine also ensures
- * that the entire message header is stored in the main fragment of the message
- * buffer, to simplify future access to message header fields.
- *
- * Note: Having extra info present in the message header or data areas is OK.
- * TIPC will ignore the excess, under the assumption that it is optional info
- * introduced by a later release of the protocol.
- */
-static int link_recv_buf_validate(struct sk_buff *buf)
+static void link_retrieve_defq(struct tipc_link *link,
+			       struct sk_buff_head *list)
 {
-	static u32 min_data_hdr_size[8] = {
-		SHORT_H_SIZE, MCAST_H_SIZE, NAMED_H_SIZE, BASIC_H_SIZE,
-		MAX_H_SIZE, MAX_H_SIZE, MAX_H_SIZE, MAX_H_SIZE
-		};
-
-	struct tipc_msg *msg;
-	u32 tipc_hdr[2];
-	u32 size;
-	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;
-
-	msg = skb_header_pointer(buf, 0, sizeof(tipc_hdr), tipc_hdr);
-	if (msg == NULL)
-		return 0;
-
-	if (unlikely(msg_version(msg) != TIPC_VERSION))
-		return 0;
-
-	size = msg_size(msg);
-	hdr_size = msg_hdr_sz(msg);
-	min_hdr_size = msg_isdata(msg) ?
-		min_data_hdr_size[msg_type(msg)] : INT_H_SIZE;
+	u32 seq_no;
 
-	if (unlikely((hdr_size < min_hdr_size) ||
-		     (size < hdr_size) ||
-		     (buf->len < size) ||
-		     (size - hdr_size > TIPC_MAX_USER_MSG_SIZE)))
-		return 0;
+	if (skb_queue_empty(&link->deferdq))
+		return;
 
-	return pskb_may_pull(buf, hdr_size);
+	seq_no = buf_seqno(skb_peek(&link->deferdq));
+	if (seq_no == mod(link->next_in_no))
+		skb_queue_splice_tail_init(&link->deferdq, list);
 }
 
 /**
  * tipc_rcv - process TIPC packets/messages arriving from off-node
- * @head: pointer to message buffer chain
+ * @net: the applicable net namespace
+ * @skb: TIPC packet
  * @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_rcv(struct sk_buff *head, struct tipc_bearer *b_ptr)
+void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b_ptr)
 {
-	while (head) {
-		struct tipc_node *n_ptr;
-		struct tipc_link *l_ptr;
-		struct sk_buff *crs;
-		struct sk_buff *buf = head;
-		struct tipc_msg *msg;
-		u32 seq_no;
-		u32 ackd;
-		u32 released = 0;
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	struct sk_buff_head head;
+	struct tipc_node *n_ptr;
+	struct tipc_link *l_ptr;
+	struct sk_buff *skb1, *tmp;
+	struct tipc_msg *msg;
+	u32 seq_no;
+	u32 ackd;
+	u32 released;
 
-		head = head->next;
-		buf->next = NULL;
+	skb2list(skb, &head);
 
+	while ((skb = __skb_dequeue(&head))) {
 		/* Ensure message is well-formed */
-		if (unlikely(!link_recv_buf_validate(buf)))
-			goto discard;
-
-		/* Ensure message data is a single contiguous unit */
-		if (unlikely(skb_linearize(buf)))
+		if (unlikely(!tipc_msg_validate(skb)))
 			goto discard;
 
 		/* Handle arrival of a non-unicast link message */
-		msg = buf_msg(buf);
-
+		msg = buf_msg(skb);
 		if (unlikely(msg_non_seq(msg))) {
 			if (msg_user(msg) ==  LINK_CONFIG)
-				tipc_disc_rcv(buf, b_ptr);
+				tipc_disc_rcv(net, skb, b_ptr);
 			else
-				tipc_bclink_rcv(buf);
+				tipc_bclink_rcv(net, skb);
 			continue;
 		}
 
 		/* Discard unicast link messages destined for another node */
 		if (unlikely(!msg_short(msg) &&
-			     (msg_destnode(msg) != tipc_own_addr)))
+			     (msg_destnode(msg) != tn->own_addr)))
 			goto discard;
 
 		/* Locate neighboring node that sent message */
-		n_ptr = tipc_node_find(msg_prevnode(msg));
+		n_ptr = tipc_node_find(net, msg_prevnode(msg));
 		if (unlikely(!n_ptr))
 			goto discard;
-		tipc_node_lock(n_ptr);
 
+		tipc_node_lock(n_ptr);
 		/* Locate unicast link endpoint that should handle message */
 		l_ptr = n_ptr->links[b_ptr->identity];
 		if (unlikely(!l_ptr))
-			goto unlock_discard;
+			goto unlock;
 
 		/* Verify that communication with node is currently allowed */
 		if ((n_ptr->action_flags & TIPC_WAIT_PEER_LINKS_DOWN) &&
@@ -1161,45 +1089,39 @@ void tipc_rcv(struct sk_buff *head, struct tipc_bearer *b_ptr)
 			n_ptr->action_flags &= ~TIPC_WAIT_PEER_LINKS_DOWN;
 
 		if (tipc_node_blocked(n_ptr))
-			goto unlock_discard;
+			goto unlock;
 
 		/* Validate message sequence number info */
 		seq_no = msg_seqno(msg);
 		ackd = msg_ack(msg);
 
 		/* Release acked messages */
-		if (n_ptr->bclink.recv_permitted)
+		if (unlikely(n_ptr->bclink.acked != msg_bcast_ack(msg)))
 			tipc_bclink_acknowledge(n_ptr, msg_bcast_ack(msg));
 
-		crs = l_ptr->first_out;
-		while ((crs != l_ptr->next_out) &&
-		       less_eq(buf_seqno(crs), ackd)) {
-			struct sk_buff *next = crs->next;
-			kfree_skb(crs);
-			crs = next;
-			released++;
-		}
-		if (released) {
-			l_ptr->first_out = crs;
-			l_ptr->out_queue_size -= released;
+		released = 0;
+		skb_queue_walk_safe(&l_ptr->transmq, skb1, tmp) {
+			if (more(buf_seqno(skb1), ackd))
+				break;
+			 __skb_unlink(skb1, &l_ptr->transmq);
+			 kfree_skb(skb1);
+			 released = 1;
 		}
 
 		/* Try sending any messages link endpoint has pending */
-		if (unlikely(l_ptr->next_out))
-			tipc_link_push_queue(l_ptr);
+		if (unlikely(skb_queue_len(&l_ptr->backlogq)))
+			tipc_link_push_packets(l_ptr);
 
-		if (released && !skb_queue_empty(&l_ptr->waiting_sks)) {
+		if (released && !skb_queue_empty(&l_ptr->wakeupq))
 			link_prepare_wakeup(l_ptr);
-			l_ptr->owner->action_flags |= TIPC_WAKEUP_USERS;
-		}
 
 		/* Process the incoming packet */
 		if (unlikely(!link_working_working(l_ptr))) {
 			if (msg_user(msg) == LINK_PROTOCOL) {
-				tipc_link_proto_rcv(l_ptr, buf);
-				head = link_insert_deferred_queue(l_ptr, head);
-				tipc_node_unlock(n_ptr);
-				continue;
+				tipc_link_proto_rcv(l_ptr, skb);
+				link_retrieve_defq(l_ptr, &head);
+				skb = NULL;
+				goto unlock;
 			}
 
 			/* Traffic message. Conditionally activate link */
@@ -1207,118 +1129,135 @@ void tipc_rcv(struct sk_buff *head, struct tipc_bearer *b_ptr)
 
 			if (link_working_working(l_ptr)) {
 				/* Re-insert buffer in front of queue */
-				buf->next = head;
-				head = buf;
-				tipc_node_unlock(n_ptr);
-				continue;
+				__skb_queue_head(&head, skb);
+				skb = NULL;
+				goto unlock;
 			}
-			goto unlock_discard;
+			goto unlock;
 		}
 
 		/* Link is now in state WORKING_WORKING */
 		if (unlikely(seq_no != mod(l_ptr->next_in_no))) {
-			link_handle_out_of_seq_msg(l_ptr, buf);
-			head = link_insert_deferred_queue(l_ptr, head);
-			tipc_node_unlock(n_ptr);
-			continue;
+			link_handle_out_of_seq_msg(l_ptr, skb);
+			link_retrieve_defq(l_ptr, &head);
+			skb = NULL;
+			goto unlock;
+		}
+		/* Synchronize with parallel link if applicable */
+		if (unlikely((l_ptr->flags & LINK_SYNCHING) && !msg_dup(msg))) {
+			if (!link_synch(l_ptr))
+				goto unlock;
 		}
 		l_ptr->next_in_no++;
-		if (unlikely(l_ptr->oldest_deferred_in))
-			head = link_insert_deferred_queue(l_ptr, head);
-
-		if (unlikely(++l_ptr->unacked_window >= TIPC_MIN_LINK_WIN)) {
+		if (unlikely(!skb_queue_empty(&l_ptr->deferdq)))
+			link_retrieve_defq(l_ptr, &head);
+		if (unlikely(++l_ptr->rcv_unacked >= TIPC_MIN_LINK_WIN)) {
 			l_ptr->stats.sent_acks++;
-			tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, 0, 0, 0);
+			tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, 0, 0);
 		}
-
-		if (tipc_link_prepare_input(l_ptr, &buf)) {
-			tipc_node_unlock(n_ptr);
-			continue;
-		}
-		tipc_node_unlock(n_ptr);
-		msg = buf_msg(buf);
-		if (tipc_link_input(l_ptr, buf) != 0)
-			goto discard;
-		continue;
-unlock_discard:
+		tipc_link_input(l_ptr, skb);
+		skb = NULL;
+unlock:
 		tipc_node_unlock(n_ptr);
+		tipc_node_put(n_ptr);
 discard:
-		kfree_skb(buf);
+		if (unlikely(skb))
+			kfree_skb(skb);
 	}
 }
 
-/**
- * tipc_link_prepare_input - process TIPC link messages
- *
- * returns nonzero if the message was consumed
+/* tipc_data_input - deliver data and name distr msgs to upper layer
  *
+ * Consumes buffer if message is of right type
  * Node lock must be held
  */
-static int tipc_link_prepare_input(struct tipc_link *l, struct sk_buff **buf)
+static bool tipc_data_input(struct tipc_link *link, struct sk_buff *skb)
 {
-	struct tipc_node *n;
-	struct tipc_msg *msg;
-	int res = -EINVAL;
+	struct tipc_node *node = link->owner;
+	struct tipc_msg *msg = buf_msg(skb);
+	u32 dport = msg_destport(msg);
 
-	n = l->owner;
-	msg = buf_msg(*buf);
 	switch (msg_user(msg)) {
-	case CHANGEOVER_PROTOCOL:
-		if (tipc_link_tunnel_rcv(n, buf))
-			res = 0;
-		break;
-	case MSG_FRAGMENTER:
-		l->stats.recv_fragments++;
-		if (tipc_buf_append(&l->reasm_buf, buf)) {
-			l->stats.recv_fragmented++;
-			res = 0;
-		} else if (!l->reasm_buf) {
-			tipc_link_reset(l);
+	case TIPC_LOW_IMPORTANCE:
+	case TIPC_MEDIUM_IMPORTANCE:
+	case TIPC_HIGH_IMPORTANCE:
+	case TIPC_CRITICAL_IMPORTANCE:
+	case CONN_MANAGER:
+		if (tipc_skb_queue_tail(&link->inputq, skb, dport)) {
+			node->inputq = &link->inputq;
+			node->action_flags |= TIPC_MSG_EVT;
 		}
-		break;
-	case MSG_BUNDLER:
-		l->stats.recv_bundles++;
-		l->stats.recv_bundled += msg_msgcnt(msg);
-		res = 0;
-		break;
+		return true;
 	case NAME_DISTRIBUTOR:
-		n->bclink.recv_permitted = true;
-		res = 0;
-		break;
+		node->bclink.recv_permitted = true;
+		node->namedq = &link->namedq;
+		skb_queue_tail(&link->namedq, skb);
+		if (skb_queue_len(&link->namedq) == 1)
+			node->action_flags |= TIPC_NAMED_MSG_EVT;
+		return true;
+	case MSG_BUNDLER:
+	case TUNNEL_PROTOCOL:
+	case MSG_FRAGMENTER:
 	case BCAST_PROTOCOL:
-		tipc_link_sync_rcv(n, *buf);
-		break;
+		return false;
 	default:
-		res = 0;
-	}
-	return res;
+		pr_warn("Dropping received illegal msg type\n");
+		kfree_skb(skb);
+		return false;
+	};
 }
-/**
- * tipc_link_input - Deliver message too higher layers
+
+/* tipc_link_input - process packet that has passed link protocol check
+ *
+ * Consumes buffer
+ * Node lock must be held
  */
-static int tipc_link_input(struct tipc_link *l, struct sk_buff *buf)
+static void tipc_link_input(struct tipc_link *link, struct sk_buff *skb)
 {
-	struct tipc_msg *msg = buf_msg(buf);
-	int res = 0;
+	struct tipc_node *node = link->owner;
+	struct tipc_msg *msg = buf_msg(skb);
+	struct sk_buff *iskb;
+	int pos = 0;
+
+	if (likely(tipc_data_input(link, skb)))
+		return;
 
 	switch (msg_user(msg)) {
-	case TIPC_LOW_IMPORTANCE:
-	case TIPC_MEDIUM_IMPORTANCE:
-	case TIPC_HIGH_IMPORTANCE:
-	case TIPC_CRITICAL_IMPORTANCE:
-	case CONN_MANAGER:
-		tipc_sk_rcv(buf);
+	case TUNNEL_PROTOCOL:
+		if (msg_dup(msg)) {
+			link->flags |= LINK_SYNCHING;
+			link->synch_point = msg_seqno(msg_get_wrapped(msg));
+			kfree_skb(skb);
+			break;
+		}
+		if (!tipc_link_failover_rcv(link, &skb))
+			break;
+		if (msg_user(buf_msg(skb)) != MSG_BUNDLER) {
+			tipc_data_input(link, skb);
+			break;
+		}
+	case MSG_BUNDLER:
+		link->stats.recv_bundles++;
+		link->stats.recv_bundled += msg_msgcnt(msg);
+
+		while (tipc_msg_extract(skb, &iskb, &pos))
+			tipc_data_input(link, iskb);
 		break;
-	case NAME_DISTRIBUTOR:
-		tipc_named_rcv(buf);
+	case MSG_FRAGMENTER:
+		link->stats.recv_fragments++;
+		if (tipc_buf_append(&link->reasm_buf, &skb)) {
+			link->stats.recv_fragmented++;
+			tipc_data_input(link, skb);
+		} else if (!link->reasm_buf) {
+			tipc_link_reset(link);
+		}
 		break;
-	case MSG_BUNDLER:
-		tipc_link_bundle_rcv(buf);
+	case BCAST_PROTOCOL:
+		tipc_link_sync_rcv(node, skb);
 		break;
 	default:
-		res = -EINVAL;
-	}
-	return res;
+		break;
+	};
 }
 
 /**
@@ -1326,48 +1265,37 @@ static int tipc_link_input(struct tipc_link *l, struct sk_buff *buf)
  *
  * Returns increase in queue length (i.e. 0 or 1)
  */
-u32 tipc_link_defer_pkt(struct sk_buff **head, struct sk_buff **tail,
-			struct sk_buff *buf)
+u32 tipc_link_defer_pkt(struct sk_buff_head *list, struct sk_buff *skb)
 {
-	struct sk_buff *queue_buf;
-	struct sk_buff **prev;
-	u32 seq_no = buf_seqno(buf);
-
-	buf->next = NULL;
+	struct sk_buff *skb1;
+	u32 seq_no = buf_seqno(skb);
 
 	/* Empty queue ? */
-	if (*head == NULL) {
-		*head = *tail = buf;
+	if (skb_queue_empty(list)) {
+		__skb_queue_tail(list, skb);
 		return 1;
 	}
 
 	/* Last ? */
-	if (less(buf_seqno(*tail), seq_no)) {
-		(*tail)->next = buf;
-		*tail = buf;
+	if (less(buf_seqno(skb_peek_tail(list)), seq_no)) {
+		__skb_queue_tail(list, skb);
 		return 1;
 	}
 
 	/* Locate insertion point in queue, then insert; discard if duplicate */
-	prev = head;
-	queue_buf = *head;
-	for (;;) {
-		u32 curr_seqno = buf_seqno(queue_buf);
+	skb_queue_walk(list, skb1) {
+		u32 curr_seqno = buf_seqno(skb1);
 
 		if (seq_no == curr_seqno) {
-			kfree_skb(buf);
+			kfree_skb(skb);
 			return 0;
 		}
 
 		if (less(seq_no, curr_seqno))
 			break;
-
-		prev = &queue_buf->next;
-		queue_buf = queue_buf->next;
 	}
 
-	buf->next = queue_buf;
-	*prev = buf;
+	__skb_queue_before(list, skb1, skb);
 	return 1;
 }
 
@@ -1397,36 +1325,28 @@ static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr,
 		return;
 	}
 
-	if (tipc_link_defer_pkt(&l_ptr->oldest_deferred_in,
-				&l_ptr->newest_deferred_in, buf)) {
-		l_ptr->deferred_inqueue_sz++;
+	if (tipc_link_defer_pkt(&l_ptr->deferdq, buf)) {
 		l_ptr->stats.deferred_recv++;
-		TIPC_SKB_CB(buf)->deferred = true;
-		if ((l_ptr->deferred_inqueue_sz % 16) == 1)
-			tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, 0, 0, 0);
-	} else
+		if ((skb_queue_len(&l_ptr->deferdq) % TIPC_MIN_LINK_WIN) == 1)
+			tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, 0, 0);
+	} else {
 		l_ptr->stats.duplicates++;
+	}
 }
 
 /*
  * Send protocol message to the other endpoint.
  */
 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)
+			  u32 gap, u32 tolerance, u32 priority)
 {
 	struct sk_buff *buf = NULL;
 	struct tipc_msg *msg = l_ptr->pmsg;
 	u32 msg_size = sizeof(l_ptr->proto_msg);
 	int r_flag;
 
-	/* Discard any previous message that was deferred due to congestion */
-	if (l_ptr->proto_msg_queue) {
-		kfree_skb(l_ptr->proto_msg_queue);
-		l_ptr->proto_msg_queue = NULL;
-	}
-
-	/* Don't send protocol message during link changeover */
-	if (l_ptr->exp_msg_count)
+	/* Don't send protocol message during link failover */
+	if (l_ptr->flags & LINK_FAILINGOVER)
 		return;
 
 	/* Abort non-RESET send if communication with node is prohibited */
@@ -1437,18 +1357,18 @@ void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int probe_msg,
 	msg_set_type(msg, msg_typ);
 	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());
+	msg_set_last_bcast(msg, tipc_bclink_get_last_sent(l_ptr->owner->net));
 
 	if (msg_typ == STATE_MSG) {
 		u32 next_sent = mod(l_ptr->next_out_no);
 
 		if (!tipc_link_is_up(l_ptr))
 			return;
-		if (l_ptr->next_out)
-			next_sent = buf_seqno(l_ptr->next_out);
+		if (skb_queue_len(&l_ptr->backlogq))
+			next_sent = buf_seqno(skb_peek(&l_ptr->backlogq));
 		msg_set_next_sent(msg, next_sent);
-		if (l_ptr->oldest_deferred_in) {
-			u32 rec = buf_seqno(l_ptr->oldest_deferred_in);
+		if (!skb_queue_empty(&l_ptr->deferdq)) {
+			u32 rec = buf_seqno(skb_peek(&l_ptr->deferdq));
 			gap = mod(rec - mod(l_ptr->next_in_no));
 		}
 		msg_set_seq_gap(msg, gap);
@@ -1456,35 +1376,20 @@ void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int probe_msg,
 			l_ptr->stats.sent_nacks++;
 		msg_set_link_tolerance(msg, tolerance);
 		msg_set_linkprio(msg, priority);
-		msg_set_max_pkt(msg, ack_mtu);
+		msg_set_max_pkt(msg, l_ptr->mtu);
 		msg_set_ack(msg, mod(l_ptr->next_in_no - 1));
 		msg_set_probe(msg, probe_msg != 0);
-		if (probe_msg) {
-			u32 mtu = l_ptr->max_pkt;
-
-			if ((mtu < l_ptr->max_pkt_target) &&
-			    link_working_working(l_ptr) &&
-			    l_ptr->fsm_msg_cnt) {
-				msg_size = (mtu + (l_ptr->max_pkt_target - mtu)/2 + 2) & ~3;
-				if (l_ptr->max_pkt_probes == 10) {
-					l_ptr->max_pkt_target = (msg_size - 4);
-					l_ptr->max_pkt_probes = 0;
-					msg_size = (mtu + (l_ptr->max_pkt_target - mtu)/2 + 2) & ~3;
-				}
-				l_ptr->max_pkt_probes++;
-			}
-
+		if (probe_msg)
 			l_ptr->stats.sent_probes++;
-		}
 		l_ptr->stats.sent_states++;
 	} else {		/* RESET_MSG or ACTIVATE_MSG */
-		msg_set_ack(msg, mod(l_ptr->reset_checkpoint - 1));
+		msg_set_ack(msg, mod(l_ptr->failover_checkpt - 1));
 		msg_set_seq_gap(msg, 0);
 		msg_set_next_sent(msg, 1);
 		msg_set_probe(msg, 0);
 		msg_set_link_tolerance(msg, l_ptr->tolerance);
 		msg_set_linkprio(msg, l_ptr->priority);
-		msg_set_max_pkt(msg, l_ptr->max_pkt_target);
+		msg_set_max_pkt(msg, l_ptr->advertised_mtu);
 	}
 
 	r_flag = (l_ptr->owner->working_links > tipc_link_is_up(l_ptr));
@@ -1500,9 +1405,9 @@ void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int probe_msg,
 
 	skb_copy_to_linear_data(buf, msg, sizeof(l_ptr->proto_msg));
 	buf->priority = TC_PRIO_CONTROL;
-
-	tipc_bearer_send(l_ptr->bearer_id, buf, &l_ptr->media_addr);
-	l_ptr->unacked_window = 0;
+	tipc_bearer_send(l_ptr->owner->net, l_ptr->bearer_id, buf,
+			 &l_ptr->media_addr);
+	l_ptr->rcv_unacked = 0;
 	kfree_skb(buf);
 }
 
@@ -1511,20 +1416,18 @@ void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int probe_msg,
  * Note that network plane id propagates through the network, and may
  * change at any time. The node with lowest address rules
  */
-static void tipc_link_proto_rcv(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;
-	u32 max_pkt_ack;
 	u32 msg_tol;
 	struct tipc_msg *msg = buf_msg(buf);
 
-	/* Discard protocol message during link changeover */
-	if (l_ptr->exp_msg_count)
+	if (l_ptr->flags & LINK_FAILINGOVER)
 		goto exit;
 
 	if (l_ptr->net_plane != msg_net_plane(msg))
-		if (tipc_own_addr > msg_prevnode(msg))
+		if (link_own_addr(l_ptr) > msg_prevnode(msg))
 			l_ptr->net_plane = msg_net_plane(msg);
 
 	switch (msg_type(msg)) {
@@ -1559,15 +1462,8 @@ static void tipc_link_proto_rcv(struct tipc_link *l_ptr, struct sk_buff *buf)
 		if (msg_linkprio(msg) > l_ptr->priority)
 			l_ptr->priority = msg_linkprio(msg);
 
-		max_pkt_info = msg_max_pkt(msg);
-		if (max_pkt_info) {
-			if (max_pkt_info < l_ptr->max_pkt_target)
-				l_ptr->max_pkt_target = max_pkt_info;
-			if (l_ptr->max_pkt > l_ptr->max_pkt_target)
-				l_ptr->max_pkt = l_ptr->max_pkt_target;
-		} else {
-			l_ptr->max_pkt = l_ptr->max_pkt_target;
-		}
+		if (l_ptr->mtu > msg_max_pkt(msg))
+			l_ptr->mtu = msg_max_pkt(msg);
 
 		/* Synchronize broadcast link info, if not done previously */
 		if (!tipc_node_is_up(l_ptr->owner)) {
@@ -1591,9 +1487,9 @@ static void tipc_link_proto_rcv(struct tipc_link *l_ptr, struct sk_buff *buf)
 
 		if (msg_linkprio(msg) &&
 		    (msg_linkprio(msg) != l_ptr->priority)) {
-			pr_warn("%s<%s>, priority change %u->%u\n",
-				link_rst_msg, l_ptr->name, l_ptr->priority,
-				msg_linkprio(msg));
+			pr_debug("%s<%s>, priority change %u->%u\n",
+				 link_rst_msg, l_ptr->name,
+				 l_ptr->priority, msg_linkprio(msg));
 			l_ptr->priority = msg_linkprio(msg);
 			tipc_link_reset(l_ptr); /* Enforce change to take effect */
 			break;
@@ -1612,18 +1508,8 @@ static void tipc_link_proto_rcv(struct tipc_link *l_ptr, struct sk_buff *buf)
 				      mod(l_ptr->next_in_no));
 		}
 
-		max_pkt_ack = msg_max_pkt(msg);
-		if (max_pkt_ack > l_ptr->max_pkt) {
-			l_ptr->max_pkt = max_pkt_ack;
-			l_ptr->max_pkt_probes = 0;
-		}
-
-		max_pkt_ack = 0;
-		if (msg_probe(msg)) {
+		if (msg_probe(msg))
 			l_ptr->stats.recv_probes++;
-			if (msg_size(msg) > sizeof(l_ptr->proto_msg))
-				max_pkt_ack = msg_size(msg);
-		}
 
 		/* Protocol message before retransmits, reduce loss risk */
 		if (l_ptr->owner->bclink.recv_permitted)
@@ -1631,12 +1517,12 @@ static void tipc_link_proto_rcv(struct tipc_link *l_ptr, struct sk_buff *buf)
 						      msg_last_bcast(msg));
 
 		if (rec_gap || (msg_probe(msg))) {
-			tipc_link_proto_xmit(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);
 		}
 		if (msg_seq_gap(msg)) {
 			l_ptr->stats.recv_nacks++;
-			tipc_link_retransmit(l_ptr, l_ptr->first_out,
+			tipc_link_retransmit(l_ptr, skb_peek(&l_ptr->transmq),
 					     msg_seq_gap(msg));
 		}
 		break;
@@ -1655,7 +1541,7 @@ static void tipc_link_tunnel_xmit(struct tipc_link *l_ptr,
 				  u32 selector)
 {
 	struct tipc_link *tunnel;
-	struct sk_buff *buf;
+	struct sk_buff *skb;
 	u32 length = msg_size(msg);
 
 	tunnel = l_ptr->owner->active_links[selector & 1];
@@ -1664,14 +1550,14 @@ static void tipc_link_tunnel_xmit(struct tipc_link *l_ptr,
 		return;
 	}
 	msg_set_size(tunnel_hdr, length + INT_H_SIZE);
-	buf = tipc_buf_acquire(length + INT_H_SIZE);
-	if (!buf) {
+	skb = tipc_buf_acquire(length + INT_H_SIZE);
+	if (!skb) {
 		pr_warn("%sunable to send tunnel msg\n", link_co_err);
 		return;
 	}
-	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_xmit(tunnel, buf);
+	skb_copy_to_linear_data(skb, tunnel_hdr, INT_H_SIZE);
+	skb_copy_to_linear_data_offset(skb, INT_H_SIZE, msg, length);
+	__tipc_link_xmit_skb(tunnel, skb);
 }
 
 
@@ -1683,28 +1569,29 @@ static void tipc_link_tunnel_xmit(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;
+	int msgcount;
 	struct tipc_link *tunnel = l_ptr->owner->active_links[0];
 	struct tipc_msg tunnel_hdr;
+	struct sk_buff *skb;
 	int split_bundles;
 
 	if (!tunnel)
 		return;
 
-	tipc_msg_init(&tunnel_hdr, CHANGEOVER_PROTOCOL,
-		 ORIGINAL_MSG, INT_H_SIZE, l_ptr->addr);
+	tipc_msg_init(link_own_addr(l_ptr), &tunnel_hdr, TUNNEL_PROTOCOL,
+		      FAILOVER_MSG, INT_H_SIZE, l_ptr->addr);
+	skb_queue_splice_tail_init(&l_ptr->backlogq, &l_ptr->transmq);
+	tipc_link_purge_backlog(l_ptr);
+	msgcount = skb_queue_len(&l_ptr->transmq);
 	msg_set_bearer_id(&tunnel_hdr, l_ptr->peer_bearer_id);
 	msg_set_msgcnt(&tunnel_hdr, msgcount);
 
-	if (!l_ptr->first_out) {
-		struct sk_buff *buf;
-
-		buf = tipc_buf_acquire(INT_H_SIZE);
-		if (buf) {
-			skb_copy_to_linear_data(buf, &tunnel_hdr, INT_H_SIZE);
+	if (skb_queue_empty(&l_ptr->transmq)) {
+		skb = tipc_buf_acquire(INT_H_SIZE);
+		if (skb) {
+			skb_copy_to_linear_data(skb, &tunnel_hdr, INT_H_SIZE);
 			msg_set_size(&tunnel_hdr, INT_H_SIZE);
-			__tipc_link_xmit(tunnel, buf);
+			__tipc_link_xmit_skb(tunnel, skb);
 		} else {
 			pr_warn("%sunable to send changeover msg\n",
 				link_co_err);
@@ -1715,8 +1602,8 @@ void tipc_link_failover_send_queue(struct tipc_link *l_ptr)
 	split_bundles = (l_ptr->owner->active_links[0] !=
 			 l_ptr->owner->active_links[1]);
 
-	while (crs) {
-		struct tipc_msg *msg = buf_msg(crs);
+	skb_queue_walk(&l_ptr->transmq, skb) {
+		struct tipc_msg *msg = buf_msg(skb);
 
 		if ((msg_user(msg) == MSG_BUNDLER) && split_bundles) {
 			struct tipc_msg *m = msg_get_wrapped(msg);
@@ -1734,7 +1621,6 @@ void tipc_link_failover_send_queue(struct tipc_link *l_ptr)
 			tipc_link_tunnel_xmit(l_ptr, &tunnel_hdr, msg,
 					      msg_link_selector(msg));
 		}
-		crs = crs->next;
 	}
 }
 
@@ -1747,247 +1633,151 @@ void tipc_link_failover_send_queue(struct tipc_link *l_ptr)
  * 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)
+void tipc_link_dup_queue_xmit(struct tipc_link *link,
+			      struct tipc_link *tnl)
 {
-	struct sk_buff *iter;
-	struct tipc_msg tunnel_hdr;
-
-	tipc_msg_init(&tunnel_hdr, CHANGEOVER_PROTOCOL,
-		 DUPLICATE_MSG, INT_H_SIZE, l_ptr->addr);
-	msg_set_msgcnt(&tunnel_hdr, l_ptr->out_queue_size);
-	msg_set_bearer_id(&tunnel_hdr, l_ptr->peer_bearer_id);
-	iter = l_ptr->first_out;
-	while (iter) {
-		struct sk_buff *outbuf;
-		struct tipc_msg *msg = buf_msg(iter);
-		u32 length = msg_size(msg);
-
-		if (msg_user(msg) == MSG_BUNDLER)
-			msg_set_type(msg, CLOSED_MSG);
-		msg_set_ack(msg, mod(l_ptr->next_in_no - 1));	/* Update */
-		msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in);
-		msg_set_size(&tunnel_hdr, length + INT_H_SIZE);
-		outbuf = tipc_buf_acquire(length + INT_H_SIZE);
-		if (outbuf == NULL) {
+	struct sk_buff *skb;
+	struct tipc_msg tnl_hdr;
+	struct sk_buff_head *queue = &link->transmq;
+	int mcnt;
+
+	tipc_msg_init(link_own_addr(link), &tnl_hdr, TUNNEL_PROTOCOL,
+		      SYNCH_MSG, INT_H_SIZE, link->addr);
+	mcnt = skb_queue_len(&link->transmq) + skb_queue_len(&link->backlogq);
+	msg_set_msgcnt(&tnl_hdr, mcnt);
+	msg_set_bearer_id(&tnl_hdr, link->peer_bearer_id);
+
+tunnel_queue:
+	skb_queue_walk(queue, skb) {
+		struct sk_buff *outskb;
+		struct tipc_msg *msg = buf_msg(skb);
+		u32 len = msg_size(msg);
+
+		msg_set_ack(msg, mod(link->next_in_no - 1));
+		msg_set_bcast_ack(msg, link->owner->bclink.last_in);
+		msg_set_size(&tnl_hdr, len + INT_H_SIZE);
+		outskb = tipc_buf_acquire(len + INT_H_SIZE);
+		if (outskb == NULL) {
 			pr_warn("%sunable to send duplicate msg\n",
 				link_co_err);
 			return;
 		}
-		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_xmit(tunnel, outbuf);
-		if (!tipc_link_is_up(l_ptr))
+		skb_copy_to_linear_data(outskb, &tnl_hdr, INT_H_SIZE);
+		skb_copy_to_linear_data_offset(outskb, INT_H_SIZE,
+					       skb->data, len);
+		__tipc_link_xmit_skb(tnl, outskb);
+		if (!tipc_link_is_up(link))
 			return;
-		iter = iter->next;
 	}
-}
-
-/**
- * buf_extract - extracts embedded TIPC message from another message
- * @skb: encapsulating message buffer
- * @from_pos: offset to extract from
- *
- * Returns a new message buffer containing an embedded message.  The
- * encapsulating message itself is left unchanged.
- */
-static struct sk_buff *buf_extract(struct sk_buff *skb, u32 from_pos)
-{
-	struct tipc_msg *msg = (struct tipc_msg *)(skb->data + from_pos);
-	u32 size = msg_size(msg);
-	struct sk_buff *eb;
-
-	eb = tipc_buf_acquire(size);
-	if (eb)
-		skb_copy_to_linear_data(eb, msg, size);
-	return eb;
-}
-
-
-
-/* tipc_link_dup_rcv(): Receive a tunnelled DUPLICATE_MSG packet.
- * Owner node is locked.
- */
-static void tipc_link_dup_rcv(struct tipc_link *l_ptr,
-			      struct sk_buff *t_buf)
-{
-	struct sk_buff *buf;
-
-	if (!tipc_link_is_up(l_ptr))
+	if (queue == &link->backlogq)
 		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;
-	}
-
-	/* Add buffer to deferred queue, if applicable: */
-	link_handle_out_of_seq_msg(l_ptr, buf);
+	queue = &link->backlogq;
+	goto tunnel_queue;
 }
 
-/*  tipc_link_failover_rcv(): Receive a tunnelled ORIGINAL_MSG packet
+/*  tipc_link_failover_rcv(): Receive a tunnelled FAILOVER_MSG packet
  *  Owner node is locked.
  */
-static struct sk_buff *tipc_link_failover_rcv(struct tipc_link *l_ptr,
-					      struct sk_buff *t_buf)
+static bool tipc_link_failover_rcv(struct tipc_link *link,
+				   struct sk_buff **skb)
 {
-	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);
+	struct tipc_msg *msg = buf_msg(*skb);
+	struct sk_buff *iskb = NULL;
+	struct tipc_link *pl = NULL;
+	int bearer_id = msg_bearer_id(msg);
+	int pos = 0;
 
-	/* 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;
-		}
-		msg = buf_msg(buf);
-
-		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);
+	if (msg_type(msg) != FAILOVER_MSG) {
+		pr_warn("%sunknown tunnel pkt received\n", link_co_err);
+		goto exit;
 	}
-	return buf;
-}
+	if (bearer_id >= MAX_BEARERS)
+		goto exit;
 
-/*  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);
+	if (bearer_id == link->bearer_id)
+		goto exit;
 
-	*buf = NULL;
+	pl = link->owner->links[bearer_id];
+	if (pl && tipc_link_is_up(pl))
+		tipc_link_reset(pl);
 
-	if (bearer_id >= MAX_BEARERS)
+	if (link->failover_pkts == FIRST_FAILOVER)
+		link->failover_pkts = msg_msgcnt(msg);
+
+	/* Should we expect an inner packet? */
+	if (!link->failover_pkts)
 		goto exit;
 
-	l_ptr = n_ptr->links[bearer_id];
-	if (!l_ptr)
+	if (!tipc_msg_extract(*skb, &iskb, &pos)) {
+		pr_warn("%sno inner failover pkt\n", link_co_err);
+		*skb = NULL;
 		goto exit;
+	}
+	link->failover_pkts--;
+	*skb = NULL;
 
-	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);
+	/* Was this packet already delivered? */
+	if (less(buf_seqno(iskb), link->failover_checkpt)) {
+		kfree_skb(iskb);
+		iskb = NULL;
+		goto exit;
+	}
+	if (msg_user(buf_msg(iskb)) == MSG_FRAGMENTER) {
+		link->stats.recv_fragments++;
+		tipc_buf_append(&link->failover_skb, &iskb);
+	}
 exit:
-	kfree_skb(t_buf);
-	return *buf != NULL;
+	if (!link->failover_pkts && pl)
+		pl->flags &= ~LINK_FAILINGOVER;
+	kfree_skb(*skb);
+	*skb = iskb;
+	return *skb;
 }
 
-/*
- *  Bundler functionality:
- */
-void tipc_link_bundle_rcv(struct sk_buff *buf)
+static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tol)
 {
-	u32 msgcount = msg_msgcnt(buf_msg(buf));
-	u32 pos = INT_H_SIZE;
-	struct sk_buff *obuf;
-	struct tipc_msg *omsg;
-
-	while (msgcount--) {
-		obuf = buf_extract(buf, pos);
-		if (obuf == NULL) {
-			pr_warn("Link unable to unbundle message(s)\n");
-			break;
-		}
-		omsg = buf_msg(obuf);
-		pos += align(msg_size(omsg));
-		if (msg_isdata(omsg)) {
-			if (unlikely(msg_type(omsg) == TIPC_MCAST_MSG))
-				tipc_sk_mcast_rcv(obuf);
-			else
-				tipc_sk_rcv(obuf);
-		} else if (msg_user(omsg) == CONN_MANAGER) {
-			tipc_sk_rcv(obuf);
-		} else if (msg_user(omsg) == NAME_DISTRIBUTOR) {
-			tipc_named_rcv(obuf);
-		} else {
-			pr_warn("Illegal bundled msg: %u\n", msg_user(omsg));
-			kfree_skb(obuf);
-		}
-	}
-	kfree_skb(buf);
-}
+	unsigned long intv = ((tol / 4) > 500) ? 500 : tol / 4;
 
-static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tolerance)
-{
-	if ((tolerance < TIPC_MIN_LINK_TOL) || (tolerance > TIPC_MAX_LINK_TOL))
+	if ((tol < TIPC_MIN_LINK_TOL) || (tol > TIPC_MAX_LINK_TOL))
 		return;
 
-	l_ptr->tolerance = tolerance;
-	l_ptr->continuity_interval =
-		((tolerance / 4) > 500) ? 500 : tolerance / 4;
-	l_ptr->abort_limit = tolerance / (l_ptr->continuity_interval / 4);
+	l_ptr->tolerance = tol;
+	l_ptr->cont_intv = msecs_to_jiffies(intv);
+	l_ptr->abort_limit = tol / (jiffies_to_msecs(l_ptr->cont_intv) / 4);
 }
 
-void tipc_link_set_queue_limits(struct tipc_link *l_ptr, u32 window)
+void tipc_link_set_queue_limits(struct tipc_link *l, u32 win)
 {
-	/* Data messages from this node, inclusive FIRST_FRAGM */
-	l_ptr->queue_limit[TIPC_LOW_IMPORTANCE] = window;
-	l_ptr->queue_limit[TIPC_MEDIUM_IMPORTANCE] = (window / 3) * 4;
-	l_ptr->queue_limit[TIPC_HIGH_IMPORTANCE] = (window / 3) * 5;
-	l_ptr->queue_limit[TIPC_CRITICAL_IMPORTANCE] = (window / 3) * 6;
-	/* Transiting data messages,inclusive FIRST_FRAGM */
-	l_ptr->queue_limit[TIPC_LOW_IMPORTANCE + 4] = 300;
-	l_ptr->queue_limit[TIPC_MEDIUM_IMPORTANCE + 4] = 600;
-	l_ptr->queue_limit[TIPC_HIGH_IMPORTANCE + 4] = 900;
-	l_ptr->queue_limit[TIPC_CRITICAL_IMPORTANCE + 4] = 1200;
-	l_ptr->queue_limit[CONN_MANAGER] = 1200;
-	l_ptr->queue_limit[CHANGEOVER_PROTOCOL] = 2500;
-	l_ptr->queue_limit[NAME_DISTRIBUTOR] = 3000;
-	/* FRAGMENT and LAST_FRAGMENT packets */
-	l_ptr->queue_limit[MSG_FRAGMENTER] = 4000;
+	int max_bulk = TIPC_MAX_PUBLICATIONS / (l->mtu / ITEM_SIZE);
+
+	l->window = win;
+	l->backlog[TIPC_LOW_IMPORTANCE].limit      = win / 2;
+	l->backlog[TIPC_MEDIUM_IMPORTANCE].limit   = win;
+	l->backlog[TIPC_HIGH_IMPORTANCE].limit     = win / 2 * 3;
+	l->backlog[TIPC_CRITICAL_IMPORTANCE].limit = win * 2;
+	l->backlog[TIPC_SYSTEM_IMPORTANCE].limit   = max_bulk;
 }
 
 /* tipc_link_find_owner - locate owner node of link by link's name
+ * @net: the applicable net namespace
  * @name: pointer to link name string
  * @bearer_id: pointer to index in 'node->links' array where the link was found.
  *
  * Returns pointer to node owning the link, or 0 if no matching link is found.
  */
-static struct tipc_node *tipc_link_find_owner(const char *link_name,
+static struct tipc_node *tipc_link_find_owner(struct net *net,
+					      const char *link_name,
 					      unsigned int *bearer_id)
 {
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	struct tipc_link *l_ptr;
 	struct tipc_node *n_ptr;
-	struct tipc_node *found_node = 0;
+	struct tipc_node *found_node = NULL;
 	int i;
 
 	*bearer_id = 0;
 	rcu_read_lock();
-	list_for_each_entry_rcu(n_ptr, &tipc_node_list, list) {
+	list_for_each_entry_rcu(n_ptr, &tn->node_list, list) {
 		tipc_node_lock(n_ptr);
 		for (i = 0; i < MAX_BEARERS; i++) {
 			l_ptr = n_ptr->links[i];
@@ -2007,371 +1797,476 @@ static struct tipc_node *tipc_link_find_owner(const char *link_name,
 }
 
 /**
- * link_value_is_valid -- validate proposed link tolerance/priority/window
- *
- * @cmd: value type (TIPC_CMD_SET_LINK_*)
- * @new_value: the new value
- *
- * Returns 1 if value is within range, 0 if not.
+ * link_reset_statistics - reset link statistics
+ * @l_ptr: pointer to link
  */
-static int link_value_is_valid(u16 cmd, u32 new_value)
+static void link_reset_statistics(struct tipc_link *l_ptr)
 {
-	switch (cmd) {
-	case TIPC_CMD_SET_LINK_TOL:
-		return (new_value >= TIPC_MIN_LINK_TOL) &&
-			(new_value <= TIPC_MAX_LINK_TOL);
-	case TIPC_CMD_SET_LINK_PRI:
-		return (new_value <= TIPC_MAX_LINK_PRI);
-	case TIPC_CMD_SET_LINK_WINDOW:
-		return (new_value >= TIPC_MIN_LINK_WIN) &&
-			(new_value <= TIPC_MAX_LINK_WIN);
+	memset(&l_ptr->stats, 0, sizeof(l_ptr->stats));
+	l_ptr->stats.sent_info = l_ptr->next_out_no;
+	l_ptr->stats.recv_info = l_ptr->next_in_no;
+}
+
+static void link_print(struct tipc_link *l_ptr, const char *str)
+{
+	struct tipc_net *tn = net_generic(l_ptr->owner->net, tipc_net_id);
+	struct tipc_bearer *b_ptr;
+
+	rcu_read_lock();
+	b_ptr = rcu_dereference_rtnl(tn->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");
+	else if (link_reset_reset(l_ptr))
+		pr_cont(":RR\n");
+	else if (link_reset_unknown(l_ptr))
+		pr_cont(":RU\n");
+	else if (link_working_working(l_ptr))
+		pr_cont(":WW\n");
+	else
+		pr_cont("\n");
+}
+
+/* Parse and validate nested (link) properties valid for media, bearer and link
+ */
+int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[])
+{
+	int err;
+
+	err = nla_parse_nested(props, TIPC_NLA_PROP_MAX, prop,
+			       tipc_nl_prop_policy);
+	if (err)
+		return err;
+
+	if (props[TIPC_NLA_PROP_PRIO]) {
+		u32 prio;
+
+		prio = nla_get_u32(props[TIPC_NLA_PROP_PRIO]);
+		if (prio > TIPC_MAX_LINK_PRI)
+			return -EINVAL;
+	}
+
+	if (props[TIPC_NLA_PROP_TOL]) {
+		u32 tol;
+
+		tol = nla_get_u32(props[TIPC_NLA_PROP_TOL]);
+		if ((tol < TIPC_MIN_LINK_TOL) || (tol > TIPC_MAX_LINK_TOL))
+			return -EINVAL;
 	}
+
+	if (props[TIPC_NLA_PROP_WIN]) {
+		u32 win;
+
+		win = nla_get_u32(props[TIPC_NLA_PROP_WIN]);
+		if ((win < TIPC_MIN_LINK_WIN) || (win > TIPC_MAX_LINK_WIN))
+			return -EINVAL;
+	}
+
 	return 0;
 }
 
-/**
- * link_cmd_set_value - change priority/tolerance/window for link/bearer/media
- * @name: ptr to link, bearer, or media name
- * @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 RTNL lock to ensure link/bearer/media is not deleted.
- *
- * Returns 0 if value updated and negative value on error.
- */
-static int link_cmd_set_value(const char *name, u32 new_value, u16 cmd)
+int tipc_nl_link_set(struct sk_buff *skb, struct genl_info *info)
 {
-	struct tipc_node *node;
-	struct tipc_link *l_ptr;
-	struct tipc_bearer *b_ptr;
-	struct tipc_media *m_ptr;
-	int bearer_id;
+	int err;
 	int res = 0;
+	int bearer_id;
+	char *name;
+	struct tipc_link *link;
+	struct tipc_node *node;
+	struct nlattr *attrs[TIPC_NLA_LINK_MAX + 1];
+	struct net *net = sock_net(skb->sk);
 
-	node = tipc_link_find_owner(name, &bearer_id);
-	if (node) {
-		tipc_node_lock(node);
-		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;
+	if (!info->attrs[TIPC_NLA_LINK])
+		return -EINVAL;
+
+	err = nla_parse_nested(attrs, TIPC_NLA_LINK_MAX,
+			       info->attrs[TIPC_NLA_LINK],
+			       tipc_nl_link_policy);
+	if (err)
+		return err;
+
+	if (!attrs[TIPC_NLA_LINK_NAME])
+		return -EINVAL;
+
+	name = nla_data(attrs[TIPC_NLA_LINK_NAME]);
+
+	node = tipc_link_find_owner(net, name, &bearer_id);
+	if (!node)
+		return -EINVAL;
+
+	tipc_node_lock(node);
+
+	link = node->links[bearer_id];
+	if (!link) {
+		res = -EINVAL;
+		goto out;
 	}
 
-	b_ptr = tipc_bearer_find(name);
-	if (b_ptr) {
-		switch (cmd) {
-		case TIPC_CMD_SET_LINK_TOL:
-			b_ptr->tolerance = new_value;
-			break;
-		case TIPC_CMD_SET_LINK_PRI:
-			b_ptr->priority = new_value;
-			break;
-		case TIPC_CMD_SET_LINK_WINDOW:
-			b_ptr->window = new_value;
-			break;
-		default:
-			res = -EINVAL;
-			break;
+	if (attrs[TIPC_NLA_LINK_PROP]) {
+		struct nlattr *props[TIPC_NLA_PROP_MAX + 1];
+
+		err = tipc_nl_parse_link_prop(attrs[TIPC_NLA_LINK_PROP],
+					      props);
+		if (err) {
+			res = err;
+			goto out;
 		}
-		return res;
-	}
 
-	m_ptr = tipc_media_find(name);
-	if (!m_ptr)
-		return -ENODEV;
-	switch (cmd) {
-	case TIPC_CMD_SET_LINK_TOL:
-		m_ptr->tolerance = new_value;
-		break;
-	case TIPC_CMD_SET_LINK_PRI:
-		m_ptr->priority = new_value;
-		break;
-	case TIPC_CMD_SET_LINK_WINDOW:
-		m_ptr->window = new_value;
-		break;
-	default:
-		res = -EINVAL;
-		break;
+		if (props[TIPC_NLA_PROP_TOL]) {
+			u32 tol;
+
+			tol = nla_get_u32(props[TIPC_NLA_PROP_TOL]);
+			link_set_supervision_props(link, tol);
+			tipc_link_proto_xmit(link, STATE_MSG, 0, 0, tol, 0);
+		}
+		if (props[TIPC_NLA_PROP_PRIO]) {
+			u32 prio;
+
+			prio = nla_get_u32(props[TIPC_NLA_PROP_PRIO]);
+			link->priority = prio;
+			tipc_link_proto_xmit(link, STATE_MSG, 0, 0, 0, prio);
+		}
+		if (props[TIPC_NLA_PROP_WIN]) {
+			u32 win;
+
+			win = nla_get_u32(props[TIPC_NLA_PROP_WIN]);
+			tipc_link_set_queue_limits(link, win);
+		}
 	}
+
+out:
+	tipc_node_unlock(node);
+
 	return res;
 }
 
-struct sk_buff *tipc_link_cmd_config(const void *req_tlv_area, int req_tlv_space,
-				     u16 cmd)
+static int __tipc_nl_add_stats(struct sk_buff *skb, struct tipc_stats *s)
 {
-	struct tipc_link_config *args;
-	u32 new_value;
-	int res;
-
-	if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_LINK_CONFIG))
-		return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR);
-
-	args = (struct tipc_link_config *)TLV_DATA(req_tlv_area);
-	new_value = ntohl(args->value);
-
-	if (!link_value_is_valid(cmd, new_value))
-		return tipc_cfg_reply_error_string(
-			"cannot change, value invalid");
-
-	if (!strcmp(args->name, tipc_bclink_name)) {
-		if ((cmd == TIPC_CMD_SET_LINK_WINDOW) &&
-		    (tipc_bclink_set_queue_limits(new_value) == 0))
-			return tipc_cfg_reply_none();
-		return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED
-						   " (cannot change setting on broadcast link)");
-	}
+	int i;
+	struct nlattr *stats;
+
+	struct nla_map {
+		u32 key;
+		u32 val;
+	};
+
+	struct nla_map map[] = {
+		{TIPC_NLA_STATS_RX_INFO, s->recv_info},
+		{TIPC_NLA_STATS_RX_FRAGMENTS, s->recv_fragments},
+		{TIPC_NLA_STATS_RX_FRAGMENTED, s->recv_fragmented},
+		{TIPC_NLA_STATS_RX_BUNDLES, s->recv_bundles},
+		{TIPC_NLA_STATS_RX_BUNDLED, s->recv_bundled},
+		{TIPC_NLA_STATS_TX_INFO, s->sent_info},
+		{TIPC_NLA_STATS_TX_FRAGMENTS, s->sent_fragments},
+		{TIPC_NLA_STATS_TX_FRAGMENTED, s->sent_fragmented},
+		{TIPC_NLA_STATS_TX_BUNDLES, s->sent_bundles},
+		{TIPC_NLA_STATS_TX_BUNDLED, s->sent_bundled},
+		{TIPC_NLA_STATS_MSG_PROF_TOT, (s->msg_length_counts) ?
+			s->msg_length_counts : 1},
+		{TIPC_NLA_STATS_MSG_LEN_CNT, s->msg_length_counts},
+		{TIPC_NLA_STATS_MSG_LEN_TOT, s->msg_lengths_total},
+		{TIPC_NLA_STATS_MSG_LEN_P0, s->msg_length_profile[0]},
+		{TIPC_NLA_STATS_MSG_LEN_P1, s->msg_length_profile[1]},
+		{TIPC_NLA_STATS_MSG_LEN_P2, s->msg_length_profile[2]},
+		{TIPC_NLA_STATS_MSG_LEN_P3, s->msg_length_profile[3]},
+		{TIPC_NLA_STATS_MSG_LEN_P4, s->msg_length_profile[4]},
+		{TIPC_NLA_STATS_MSG_LEN_P5, s->msg_length_profile[5]},
+		{TIPC_NLA_STATS_MSG_LEN_P6, s->msg_length_profile[6]},
+		{TIPC_NLA_STATS_RX_STATES, s->recv_states},
+		{TIPC_NLA_STATS_RX_PROBES, s->recv_probes},
+		{TIPC_NLA_STATS_RX_NACKS, s->recv_nacks},
+		{TIPC_NLA_STATS_RX_DEFERRED, s->deferred_recv},
+		{TIPC_NLA_STATS_TX_STATES, s->sent_states},
+		{TIPC_NLA_STATS_TX_PROBES, s->sent_probes},
+		{TIPC_NLA_STATS_TX_NACKS, s->sent_nacks},
+		{TIPC_NLA_STATS_TX_ACKS, s->sent_acks},
+		{TIPC_NLA_STATS_RETRANSMITTED, s->retransmitted},
+		{TIPC_NLA_STATS_DUPLICATES, s->duplicates},
+		{TIPC_NLA_STATS_LINK_CONGS, s->link_congs},
+		{TIPC_NLA_STATS_MAX_QUEUE, s->max_queue_sz},
+		{TIPC_NLA_STATS_AVG_QUEUE, s->queue_sz_counts ?
+			(s->accu_queue_sz / s->queue_sz_counts) : 0}
+	};
+
+	stats = nla_nest_start(skb, TIPC_NLA_LINK_STATS);
+	if (!stats)
+		return -EMSGSIZE;
+
+	for (i = 0; i <  ARRAY_SIZE(map); i++)
+		if (nla_put_u32(skb, map[i].key, map[i].val))
+			goto msg_full;
 
-	res = link_cmd_set_value(args->name, new_value, cmd);
-	if (res)
-		return tipc_cfg_reply_error_string("cannot change link setting");
+	nla_nest_end(skb, stats);
 
-	return tipc_cfg_reply_none();
+	return 0;
+msg_full:
+	nla_nest_cancel(skb, stats);
+
+	return -EMSGSIZE;
 }
 
-/**
- * link_reset_statistics - reset link statistics
- * @l_ptr: pointer to link
- */
-static void link_reset_statistics(struct tipc_link *l_ptr)
+/* Caller should hold appropriate locks to protect the link */
+static int __tipc_nl_add_link(struct net *net, struct tipc_nl_msg *msg,
+			      struct tipc_link *link, int nlflags)
 {
-	memset(&l_ptr->stats, 0, sizeof(l_ptr->stats));
-	l_ptr->stats.sent_info = l_ptr->next_out_no;
-	l_ptr->stats.recv_info = l_ptr->next_in_no;
+	int err;
+	void *hdr;
+	struct nlattr *attrs;
+	struct nlattr *prop;
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+
+	hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family,
+			  nlflags, TIPC_NL_LINK_GET);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	attrs = nla_nest_start(msg->skb, TIPC_NLA_LINK);
+	if (!attrs)
+		goto msg_full;
+
+	if (nla_put_string(msg->skb, TIPC_NLA_LINK_NAME, link->name))
+		goto attr_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_LINK_DEST,
+			tipc_cluster_mask(tn->own_addr)))
+		goto attr_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_LINK_MTU, link->mtu))
+		goto attr_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_LINK_RX, link->next_in_no))
+		goto attr_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, link->next_out_no))
+		goto attr_msg_full;
+
+	if (tipc_link_is_up(link))
+		if (nla_put_flag(msg->skb, TIPC_NLA_LINK_UP))
+			goto attr_msg_full;
+	if (tipc_link_is_active(link))
+		if (nla_put_flag(msg->skb, TIPC_NLA_LINK_ACTIVE))
+			goto attr_msg_full;
+
+	prop = nla_nest_start(msg->skb, TIPC_NLA_LINK_PROP);
+	if (!prop)
+		goto attr_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, link->priority))
+		goto prop_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_TOL, link->tolerance))
+		goto prop_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN,
+			link->window))
+		goto prop_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, link->priority))
+		goto prop_msg_full;
+	nla_nest_end(msg->skb, prop);
+
+	err = __tipc_nl_add_stats(msg->skb, &link->stats);
+	if (err)
+		goto attr_msg_full;
+
+	nla_nest_end(msg->skb, attrs);
+	genlmsg_end(msg->skb, hdr);
+
+	return 0;
+
+prop_msg_full:
+	nla_nest_cancel(msg->skb, prop);
+attr_msg_full:
+	nla_nest_cancel(msg->skb, attrs);
+msg_full:
+	genlmsg_cancel(msg->skb, hdr);
+
+	return -EMSGSIZE;
 }
 
-struct sk_buff *tipc_link_cmd_reset_stats(const void *req_tlv_area, int req_tlv_space)
+/* Caller should hold node lock  */
+static int __tipc_nl_add_node_links(struct net *net, struct tipc_nl_msg *msg,
+				    struct tipc_node *node, u32 *prev_link)
 {
-	char *link_name;
-	struct tipc_link *l_ptr;
-	struct tipc_node *node;
-	unsigned int bearer_id;
+	u32 i;
+	int err;
 
-	if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_LINK_NAME))
-		return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR);
+	for (i = *prev_link; i < MAX_BEARERS; i++) {
+		*prev_link = i;
 
-	link_name = (char *)TLV_DATA(req_tlv_area);
-	if (!strcmp(link_name, tipc_bclink_name)) {
-		if (tipc_bclink_reset_stats())
-			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");
+		if (!node->links[i])
+			continue;
 
-	tipc_node_lock(node);
-	l_ptr = node->links[bearer_id];
-	if (!l_ptr) {
-		tipc_node_unlock(node);
-		return tipc_cfg_reply_error_string("link not found");
+		err = __tipc_nl_add_link(net, msg, node->links[i], NLM_F_MULTI);
+		if (err)
+			return err;
 	}
-	link_reset_statistics(l_ptr);
-	tipc_node_unlock(node);
-	return tipc_cfg_reply_none();
+	*prev_link = 0;
+
+	return 0;
 }
 
-/**
- * percent - convert count to a percentage of total (rounding up or down)
- */
-static u32 percent(u32 count, u32 total)
+int tipc_nl_link_dump(struct sk_buff *skb, struct netlink_callback *cb)
 {
-	return (count * 100 + (total / 2)) / total;
+	struct net *net = sock_net(skb->sk);
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	struct tipc_node *node;
+	struct tipc_nl_msg msg;
+	u32 prev_node = cb->args[0];
+	u32 prev_link = cb->args[1];
+	int done = cb->args[2];
+	int err;
+
+	if (done)
+		return 0;
+
+	msg.skb = skb;
+	msg.portid = NETLINK_CB(cb->skb).portid;
+	msg.seq = cb->nlh->nlmsg_seq;
+
+	rcu_read_lock();
+	if (prev_node) {
+		node = tipc_node_find(net, prev_node);
+		if (!node) {
+			/* We never set seq or call nl_dump_check_consistent()
+			 * this means that setting prev_seq here will cause the
+			 * consistence check to fail in the netlink callback
+			 * handler. Resulting in the last NLMSG_DONE message
+			 * having the NLM_F_DUMP_INTR flag set.
+			 */
+			cb->prev_seq = 1;
+			goto out;
+		}
+		tipc_node_put(node);
+
+		list_for_each_entry_continue_rcu(node, &tn->node_list,
+						 list) {
+			tipc_node_lock(node);
+			err = __tipc_nl_add_node_links(net, &msg, node,
+						       &prev_link);
+			tipc_node_unlock(node);
+			if (err)
+				goto out;
+
+			prev_node = node->addr;
+		}
+	} else {
+		err = tipc_nl_add_bc_link(net, &msg);
+		if (err)
+			goto out;
+
+		list_for_each_entry_rcu(node, &tn->node_list, list) {
+			tipc_node_lock(node);
+			err = __tipc_nl_add_node_links(net, &msg, node,
+						       &prev_link);
+			tipc_node_unlock(node);
+			if (err)
+				goto out;
+
+			prev_node = node->addr;
+		}
+	}
+	done = 1;
+out:
+	rcu_read_unlock();
+
+	cb->args[0] = prev_node;
+	cb->args[1] = prev_link;
+	cb->args[2] = done;
+
+	return skb->len;
 }
 
-/**
- * tipc_link_stats - print link statistics
- * @name: link name
- * @buf: print buffer area
- * @buf_size: size of print buffer area
- *
- * Returns length of print buffer data string (or 0 if error)
- */
-static int tipc_link_stats(const char *name, char *buf, const u32 buf_size)
+int tipc_nl_link_get(struct sk_buff *skb, struct genl_info *info)
 {
-	struct tipc_link *l;
-	struct tipc_stats *s;
+	struct net *net = genl_info_net(info);
+	struct sk_buff *ans_skb;
+	struct tipc_nl_msg msg;
+	struct tipc_link *link;
 	struct tipc_node *node;
-	char *status;
-	u32 profile_total = 0;
-	unsigned int bearer_id;
-	int ret;
+	char *name;
+	int bearer_id;
+	int err;
 
-	if (!strcmp(name, tipc_bclink_name))
-		return tipc_bclink_stats(buf, buf_size);
+	if (!info->attrs[TIPC_NLA_LINK_NAME])
+		return -EINVAL;
 
-	node = tipc_link_find_owner(name, &bearer_id);
+	name = nla_data(info->attrs[TIPC_NLA_LINK_NAME]);
+	node = tipc_link_find_owner(net, name, &bearer_id);
 	if (!node)
-		return 0;
+		return -EINVAL;
 
-	tipc_node_lock(node);
+	ans_skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!ans_skb)
+		return -ENOMEM;
 
-	l = node->links[bearer_id];
-	if (!l) {
-		tipc_node_unlock(node);
-		return 0;
+	msg.skb = ans_skb;
+	msg.portid = info->snd_portid;
+	msg.seq = info->snd_seq;
+
+	tipc_node_lock(node);
+	link = node->links[bearer_id];
+	if (!link) {
+		err = -EINVAL;
+		goto err_out;
 	}
 
-	s = &l->stats;
+	err = __tipc_nl_add_link(net, &msg, link, 0);
+	if (err)
+		goto err_out;
 
-	if (tipc_link_is_active(l))
-		status = "ACTIVE";
-	else if (tipc_link_is_up(l))
-		status = "STANDBY";
-	else
-		status = "DEFUNCT";
-
-	ret = tipc_snprintf(buf, buf_size, "Link <%s>\n"
-			    "  %s  MTU:%u  Priority:%u  Tolerance:%u ms"
-			    "  Window:%u packets\n",
-			    l->name, status, l->max_pkt, l->priority,
-			    l->tolerance, l->queue_limit[0]);
-
-	ret += tipc_snprintf(buf + ret, buf_size - ret,
-			     "  RX packets:%u fragments:%u/%u bundles:%u/%u\n",
-			     l->next_in_no - s->recv_info, s->recv_fragments,
-			     s->recv_fragmented, s->recv_bundles,
-			     s->recv_bundled);
-
-	ret += tipc_snprintf(buf + ret, buf_size - ret,
-			     "  TX packets:%u fragments:%u/%u bundles:%u/%u\n",
-			     l->next_out_no - s->sent_info, s->sent_fragments,
-			     s->sent_fragmented, s->sent_bundles,
-			     s->sent_bundled);
-
-	profile_total = s->msg_length_counts;
-	if (!profile_total)
-		profile_total = 1;
-
-	ret += tipc_snprintf(buf + ret, buf_size - ret,
-			     "  TX profile sample:%u packets  average:%u octets\n"
-			     "  0-64:%u%% -256:%u%% -1024:%u%% -4096:%u%% "
-			     "-16384:%u%% -32768:%u%% -66000:%u%%\n",
-			     s->msg_length_counts,
-			     s->msg_lengths_total / profile_total,
-			     percent(s->msg_length_profile[0], profile_total),
-			     percent(s->msg_length_profile[1], profile_total),
-			     percent(s->msg_length_profile[2], profile_total),
-			     percent(s->msg_length_profile[3], profile_total),
-			     percent(s->msg_length_profile[4], profile_total),
-			     percent(s->msg_length_profile[5], profile_total),
-			     percent(s->msg_length_profile[6], profile_total));
-
-	ret += tipc_snprintf(buf + ret, buf_size - ret,
-			     "  RX states:%u probes:%u naks:%u defs:%u"
-			     " dups:%u\n", s->recv_states, s->recv_probes,
-			     s->recv_nacks, s->deferred_recv, s->duplicates);
-
-	ret += tipc_snprintf(buf + ret, buf_size - ret,
-			     "  TX states:%u probes:%u naks:%u acks:%u"
-			     " dups:%u\n", s->sent_states, s->sent_probes,
-			     s->sent_nacks, s->sent_acks, s->retransmitted);
-
-	ret += tipc_snprintf(buf + ret, buf_size - ret,
-			     "  Congestion link:%u  Send queue"
-			     " max:%u avg:%u\n", s->link_congs,
-			     s->max_queue_sz, s->queue_sz_counts ?
-			     (s->accu_queue_sz / s->queue_sz_counts) : 0);
+	tipc_node_unlock(node);
+
+	return genlmsg_reply(ans_skb, info);
 
+err_out:
 	tipc_node_unlock(node);
-	return ret;
+	nlmsg_free(ans_skb);
+
+	return err;
 }
 
-struct sk_buff *tipc_link_cmd_show_stats(const void *req_tlv_area, int req_tlv_space)
+int tipc_nl_link_reset_stats(struct sk_buff *skb, struct genl_info *info)
 {
-	struct sk_buff *buf;
-	struct tlv_desc *rep_tlv;
-	int str_len;
-	int pb_len;
-	char *pb;
+	int err;
+	char *link_name;
+	unsigned int bearer_id;
+	struct tipc_link *link;
+	struct tipc_node *node;
+	struct nlattr *attrs[TIPC_NLA_LINK_MAX + 1];
+	struct net *net = sock_net(skb->sk);
 
-	if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_LINK_NAME))
-		return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR);
+	if (!info->attrs[TIPC_NLA_LINK])
+		return -EINVAL;
 
-	buf = tipc_cfg_reply_alloc(TLV_SPACE(ULTRA_STRING_MAX_LEN));
-	if (!buf)
-		return NULL;
+	err = nla_parse_nested(attrs, TIPC_NLA_LINK_MAX,
+			       info->attrs[TIPC_NLA_LINK],
+			       tipc_nl_link_policy);
+	if (err)
+		return err;
 
-	rep_tlv = (struct tlv_desc *)buf->data;
-	pb = TLV_DATA(rep_tlv);
-	pb_len = ULTRA_STRING_MAX_LEN;
-	str_len = tipc_link_stats((char *)TLV_DATA(req_tlv_area),
-				  pb, pb_len);
-	if (!str_len) {
-		kfree_skb(buf);
-		return tipc_cfg_reply_error_string("link not found");
-	}
-	str_len += 1;	/* for "\0" */
-	skb_put(buf, TLV_SPACE(str_len));
-	TLV_SET(rep_tlv, TIPC_TLV_ULTRA_STRING, NULL, str_len);
+	if (!attrs[TIPC_NLA_LINK_NAME])
+		return -EINVAL;
 
-	return buf;
-}
+	link_name = nla_data(attrs[TIPC_NLA_LINK_NAME]);
 
-/**
- * tipc_link_get_max_pkt - get maximum packet size to use when sending to destination
- * @dest: network address of destination node
- * @selector: used to select from set of active links
- *
- * If no active link can be found, uses default maximum packet size.
- */
-u32 tipc_link_get_max_pkt(u32 dest, u32 selector)
-{
-	struct tipc_node *n_ptr;
-	struct tipc_link *l_ptr;
-	u32 res = MAX_PKT_DEFAULT;
+	if (strcmp(link_name, tipc_bclink_name) == 0) {
+		err = tipc_bclink_reset_stats(net);
+		if (err)
+			return err;
+		return 0;
+	}
 
-	if (dest == tipc_own_addr)
-		return MAX_MSG_SIZE;
+	node = tipc_link_find_owner(net, link_name, &bearer_id);
+	if (!node)
+		return -EINVAL;
 
-	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 = l_ptr->max_pkt;
-		tipc_node_unlock(n_ptr);
+	tipc_node_lock(node);
+
+	link = node->links[bearer_id];
+	if (!link) {
+		tipc_node_unlock(node);
+		return -EINVAL;
 	}
-	return res;
-}
 
-static void link_print(struct tipc_link *l_ptr, const char *str)
-{
-	struct tipc_bearer *b_ptr;
+	link_reset_statistics(link);
 
-	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();
+	tipc_node_unlock(node);
 
-	if (link_working_unknown(l_ptr))
-		pr_cont(":WU\n");
-	else if (link_reset_reset(l_ptr))
-		pr_cont(":RR\n");
-	else if (link_reset_unknown(l_ptr))
-		pr_cont(":RU\n");
-	else if (link_working_working(l_ptr))
-		pr_cont(":WW\n");
-	else
-		pr_cont("\n");
+	return 0;
 }
diff --git a/net/tipc/link.h b/net/tipc/link.h
index b567a3427fda..b5b4e3554d4e 100644
--- a/net/tipc/link.h
+++ b/net/tipc/link.h
@@ -37,9 +37,14 @@
 #ifndef _TIPC_LINK_H
 #define _TIPC_LINK_H
 
+#include <net/genetlink.h>
 #include "msg.h"
 #include "node.h"
 
+/* TIPC-specific error codes
+*/
+#define ELINKCONG EAGAIN	/* link congestion <=> resource unavailable */
+
 /* Out-of-range value for link sequence numbers
  */
 #define INVALID_LINK_SEQ 0x10000
@@ -53,8 +58,10 @@
 
 /* Link endpoint execution states
  */
-#define LINK_STARTED    0x0001
-#define LINK_STOPPED    0x0002
+#define LINK_STARTED     0x0001
+#define LINK_STOPPED     0x0002
+#define LINK_SYNCHING    0x0004
+#define LINK_FAILINGOVER 0x0008
 
 /* Starting value for maximum packet size negotiation on unicast links
  * (unless bearer MTU is less)
@@ -98,13 +105,14 @@ struct tipc_stats {
  * @media_addr: media address to use when sending messages over link
  * @timer: link timer
  * @owner: pointer to peer node
+ * @refcnt: reference counter for permanent references (owner node & timer)
  * @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
  * @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]
+ * @cont_intv: link continuity testing interval
  * @abort_limit: # of unacknowledged continuity probes needed to reset link
  * @state: current state of link FSM
  * @fsm_msg_cnt: # of protocol messages link FSM has sent in current state
@@ -112,28 +120,23 @@ struct tipc_stats {
  * @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)
+ * @backlog_limit: backlog queue congestion thresholds (indexed by importance)
  * @exp_msg_count: # of tunnelled messages expected during link changeover
  * @reset_checkpoint: seq # of last acknowledged message at time of link reset
- * @max_pkt: current maximum packet size for this link
- * @max_pkt_target: desired maximum packet size for this link
- * @max_pkt_probes: # of probes based on current (max_pkt, max_pkt_target)
- * @out_queue_size: # of messages in outbound message queue
- * @first_out: ptr to first outbound message in queue
- * @last_out: ptr to last outbound message in queue
+ * @mtu: current maximum packet size for this link
+ * @advertised_mtu: advertised own mtu when link is being established
+ * @transmitq: queue for sent, non-acked messages
+ * @backlogq: queue for messages waiting to be sent
  * @next_out_no: next sequence number to use for outbound messages
  * @last_retransmitted: sequence number of most recently retransmitted message
  * @stale_count: # of identical retransmit requests made by peer
  * @next_in_no: next sequence number to expect for inbound messages
- * @deferred_inqueue_sz: # of messages in inbound message queue
- * @oldest_deferred_in: ptr to first inbound message in queue
- * @newest_deferred_in: ptr to last inbound message in queue
+ * @deferred_queue: deferred queue saved OOS b'cast message received from node
  * @unacked_window: # of inbound messages rx'd without ack'ing back to peer
- * @proto_msg_queue: ptr to (single) outbound control message
- * @retransm_queue_size: number of messages to retransmit
- * @retransm_queue_head: sequence number of first message to retransmit
+ * @inputq: buffer queue for messages to be delivered upwards
+ * @namedq: buffer queue for name table messages to be delivered upwards
  * @next_out: ptr to first unsent outbound message in queue
- * @waiting_sks: linked list of sockets waiting for link congestion to abate
+ * @wakeupq: linked list of wakeup msgs waiting for link congestion to abate
  * @long_msg_seq_no: next identifier to use for outbound fragmented messages
  * @reasm_buf: head of partially reassembled inbound message fragments
  * @stats: collects statistics regarding link activity
@@ -144,6 +147,7 @@ struct tipc_link {
 	struct tipc_media_addr media_addr;
 	struct timer_list timer;
 	struct tipc_node *owner;
+	struct kref ref;
 
 	/* Management and link supervision data */
 	unsigned int flags;
@@ -152,7 +156,7 @@ struct tipc_link {
 	u32 peer_bearer_id;
 	u32 bearer_id;
 	u32 tolerance;
-	u32 continuity_interval;
+	unsigned long cont_intv;
 	u32 abort_limit;
 	int state;
 	u32 fsm_msg_cnt;
@@ -163,41 +167,40 @@ struct tipc_link {
 	struct tipc_msg *pmsg;
 	u32 priority;
 	char net_plane;
-	u32 queue_limit[15];	/* queue_limit[0]==window limit */
+	u16 synch_point;
 
-	/* Changeover */
-	u32 exp_msg_count;
-	u32 reset_checkpoint;
+	/* Failover */
+	u16 failover_pkts;
+	u16 failover_checkpt;
+	struct sk_buff *failover_skb;
 
 	/* Max packet negotiation */
-	u32 max_pkt;
-	u32 max_pkt_target;
-	u32 max_pkt_probes;
+	u16 mtu;
+	u16 advertised_mtu;
 
 	/* Sending */
-	u32 out_queue_size;
-	struct sk_buff *first_out;
-	struct sk_buff *last_out;
+	struct sk_buff_head transmq;
+	struct sk_buff_head backlogq;
+	struct {
+		u16 len;
+		u16 limit;
+	} backlog[5];
 	u32 next_out_no;
+	u32 window;
 	u32 last_retransmitted;
 	u32 stale_count;
 
 	/* Reception */
 	u32 next_in_no;
-	u32 deferred_inqueue_sz;
-	struct sk_buff *oldest_deferred_in;
-	struct sk_buff *newest_deferred_in;
-	u32 unacked_window;
+	u32 rcv_unacked;
+	struct sk_buff_head deferdq;
+	struct sk_buff_head inputq;
+	struct sk_buff_head namedq;
 
 	/* Congestion handling */
-	struct sk_buff *proto_msg_queue;
-	u32 retransm_queue_size;
-	u32 retransm_queue_head;
-	struct sk_buff *next_out;
-	struct sk_buff_head waiting_sks;
+	struct sk_buff_head wakeupq;
 
 	/* Fragmentation/reassembly */
-	u32 long_msg_seq_no;
 	struct sk_buff *reasm_buf;
 
 	/* Statistics */
@@ -209,35 +212,40 @@ 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_list(unsigned int bearer_id, bool shutting_down);
+void tipc_link_delete(struct tipc_link *link);
+void tipc_link_delete_list(struct net *net, 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);
 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);
-void tipc_link_reset_list(unsigned int bearer_id);
-int tipc_link_xmit(struct sk_buff *buf, u32 dest, u32 selector);
-int __tipc_link_xmit(struct tipc_link *link, struct sk_buff *buf);
-u32 tipc_link_get_max_pkt(u32 dest, u32 selector);
-void tipc_link_bundle_rcv(struct sk_buff *buf);
+void tipc_link_reset_list(struct net *net, unsigned int bearer_id);
+int tipc_link_xmit_skb(struct net *net, struct sk_buff *skb, u32 dest,
+		       u32 selector);
+int tipc_link_xmit(struct net *net, struct sk_buff_head *list, u32 dest,
+		   u32 selector);
+int __tipc_link_xmit(struct net *net, struct tipc_link *link,
+		     struct sk_buff_head *list);
 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);
+			  u32 gap, u32 tolerance, u32 priority);
+void tipc_link_push_packets(struct tipc_link *l_ptr);
+u32 tipc_link_defer_pkt(struct sk_buff_head *list, struct sk_buff *buf);
 void tipc_link_set_queue_limits(struct tipc_link *l_ptr, u32 window);
 void tipc_link_retransmit(struct tipc_link *l_ptr,
 			  struct sk_buff *start, u32 retransmits);
+struct sk_buff *tipc_skb_queue_next(const struct sk_buff_head *list,
+				    const struct sk_buff *skb);
+
+int tipc_nl_link_dump(struct sk_buff *skb, struct netlink_callback *cb);
+int tipc_nl_link_get(struct sk_buff *skb, struct genl_info *info);
+int tipc_nl_link_set(struct sk_buff *skb, struct genl_info *info);
+int tipc_nl_link_reset_stats(struct sk_buff *skb, struct genl_info *info);
+int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[]);
+void link_prepare_wakeup(struct tipc_link *l);
 
 /*
  * Link sequence number manipulation routines (uses modulo 2**16 arithmetic)
@@ -252,18 +260,14 @@ static inline u32 mod(u32 x)
 	return x & 0xffffu;
 }
 
-static inline int between(u32 lower, u32 upper, u32 n)
+static inline int less_eq(u32 left, u32 right)
 {
-	if ((lower < n) && (n < upper))
-		return 1;
-	if ((upper < lower) && ((n > lower) || (n < upper)))
-		return 1;
-	return 0;
+	return mod(right - left) < 32768u;
 }
 
-static inline int less_eq(u32 left, u32 right)
+static inline int more(u32 left, u32 right)
 {
-	return mod(right - left) < 32768u;
+	return !less_eq(left, right);
 }
 
 static inline int less(u32 left, u32 right)
@@ -276,6 +280,10 @@ static inline u32 lesser(u32 left, u32 right)
 	return less_eq(left, right) ? left : right;
 }
 
+static inline u32 link_own_addr(struct tipc_link *l)
+{
+	return msg_prevnode(l->pmsg);
+}
 
 /*
  * Link status checking routines
@@ -300,9 +308,4 @@ static inline int link_reset_reset(struct tipc_link *l_ptr)
 	return l_ptr->state == RESET_RESET;
 }
 
-static inline int link_congested(struct tipc_link *l_ptr)
-{
-	return l_ptr->out_queue_size >= l_ptr->queue_limit[0];
-}
-
 #endif
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 74745a47d72a..c3e96e815418 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, 2014, Ericsson AB
+ * Copyright (c) 2000-2006, 2014-2015, Ericsson AB
  * Copyright (c) 2005, 2010-2011, Wind River Systems
  * All rights reserved.
  *
@@ -34,6 +34,7 @@
  * POSSIBILITY OF SUCH DAMAGE.
  */
 
+#include <net/sock.h>
 #include "core.h"
 #include "msg.h"
 #include "addr.h"
@@ -46,25 +47,48 @@ static unsigned int align(unsigned int i)
 	return (i + 3) & ~3u;
 }
 
-void tipc_msg_init(struct tipc_msg *m, u32 user, u32 type, u32 hsize,
-		   u32 destnode)
+/**
+ * tipc_buf_acquire - creates a TIPC message buffer
+ * @size: message size (including TIPC header)
+ *
+ * Returns a new buffer with data pointers set to the specified size.
+ *
+ * NOTE: Headroom is reserved to allow prepending of a data link header.
+ *       There may also be unrequested tailroom present at the buffer's end.
+ */
+struct sk_buff *tipc_buf_acquire(u32 size)
+{
+	struct sk_buff *skb;
+	unsigned int buf_size = (BUF_HEADROOM + size + 3) & ~3u;
+
+	skb = alloc_skb_fclone(buf_size, GFP_ATOMIC);
+	if (skb) {
+		skb_reserve(skb, BUF_HEADROOM);
+		skb_put(skb, size);
+		skb->next = NULL;
+	}
+	return skb;
+}
+
+void tipc_msg_init(u32 own_node, struct tipc_msg *m, u32 user, u32 type,
+		   u32 hsize, u32 dnode)
 {
 	memset(m, 0, hsize);
 	msg_set_version(m);
 	msg_set_user(m, user);
 	msg_set_hdr_sz(m, hsize);
 	msg_set_size(m, hsize);
-	msg_set_prevnode(m, tipc_own_addr);
+	msg_set_prevnode(m, own_node);
 	msg_set_type(m, type);
 	if (hsize > SHORT_H_SIZE) {
-		msg_set_orignode(m, tipc_own_addr);
-		msg_set_destnode(m, destnode);
+		msg_set_orignode(m, own_node);
+		msg_set_destnode(m, dnode);
 	}
 }
 
-struct sk_buff *tipc_msg_create(uint user, uint type, uint hdr_sz,
-				uint data_sz, u32 dnode, u32 onode,
-				u32 dport, u32 oport, int errcode)
+struct sk_buff *tipc_msg_create(uint user, uint type,
+				uint hdr_sz, uint data_sz, u32 dnode,
+				u32 onode, u32 dport, u32 oport, int errcode)
 {
 	struct tipc_msg *msg;
 	struct sk_buff *buf;
@@ -74,9 +98,8 @@ struct sk_buff *tipc_msg_create(uint user, uint type, uint hdr_sz,
 		return NULL;
 
 	msg = buf_msg(buf);
-	tipc_msg_init(msg, user, type, hdr_sz, dnode);
+	tipc_msg_init(onode, msg, user, type, hdr_sz, dnode);
 	msg_set_size(msg, hdr_sz + data_sz);
-	msg_set_prevnode(msg, onode);
 	msg_set_origport(msg, oport);
 	msg_set_destport(msg, dport);
 	msg_set_errcode(msg, errcode);
@@ -91,7 +114,7 @@ struct sk_buff *tipc_msg_create(uint user, uint type, uint hdr_sz,
  * @*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
+ *            out: head buf after successful complete reassembly, otherwise NULL
  * Returns 1 when reassembly complete, otherwise 0
  */
 int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf)
@@ -142,6 +165,9 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf)
 	}
 
 	if (fragid == LAST_FRAGMENT) {
+		TIPC_SKB_CB(head)->validated = false;
+		if (unlikely(!tipc_msg_validate(head)))
+			goto err;
 		*buf = head;
 		TIPC_SKB_CB(head)->tail = NULL;
 		*headbuf = NULL;
@@ -149,7 +175,6 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf)
 	}
 	*buf = NULL;
 	return 0;
-
 err:
 	pr_warn_ratelimited("Unable to build fragment list\n");
 	kfree_skb(*buf);
@@ -158,19 +183,61 @@ err:
 	return 0;
 }
 
+/* tipc_msg_validate - validate basic format of received message
+ *
+ * This routine ensures a TIPC message has an acceptable header, and at least
+ * as much data as the header indicates it should.  The routine also ensures
+ * that the entire message header is stored in the main fragment of the message
+ * buffer, to simplify future access to message header fields.
+ *
+ * Note: Having extra info present in the message header or data areas is OK.
+ * TIPC will ignore the excess, under the assumption that it is optional info
+ * introduced by a later release of the protocol.
+ */
+bool tipc_msg_validate(struct sk_buff *skb)
+{
+	struct tipc_msg *msg;
+	int msz, hsz;
+
+	if (unlikely(TIPC_SKB_CB(skb)->validated))
+		return true;
+	if (unlikely(!pskb_may_pull(skb, MIN_H_SIZE)))
+		return false;
+
+	hsz = msg_hdr_sz(buf_msg(skb));
+	if (unlikely(hsz < MIN_H_SIZE) || (hsz > MAX_H_SIZE))
+		return false;
+	if (unlikely(!pskb_may_pull(skb, hsz)))
+		return false;
+
+	msg = buf_msg(skb);
+	if (unlikely(msg_version(msg) != TIPC_VERSION))
+		return false;
+
+	msz = msg_size(msg);
+	if (unlikely(msz < hsz))
+		return false;
+	if (unlikely((msz - hsz) > TIPC_MAX_USER_MSG_SIZE))
+		return false;
+	if (unlikely(skb->len < msz))
+		return false;
+
+	TIPC_SKB_CB(skb)->validated = true;
+	return true;
+}
 
 /**
  * tipc_msg_build - create buffer chain containing specified header and data
  * @mhdr: Message header, to be prepended to data
- * @iov: User data
- * @offset: Posision in iov to start copying from
+ * @m: User message
  * @dsz: Total length of user data
  * @pktmax: Max packet size that can be used
- * @chain: Buffer or chain of buffers to be returned to caller
+ * @list: Buffer or chain of buffers to be returned to caller
+ *
  * Returns message data size or errno: -ENOMEM, -EFAULT
  */
-int tipc_msg_build(struct tipc_msg *mhdr, struct iovec const *iov,
-		   int offset, int dsz, int pktmax , struct sk_buff **chain)
+int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m,
+		   int offset, int dsz, int pktmax, struct sk_buff_head *list)
 {
 	int mhsz = msg_hdr_sz(mhdr);
 	int msz = mhsz + dsz;
@@ -179,43 +246,45 @@ int tipc_msg_build(struct tipc_msg *mhdr, struct iovec const *iov,
 	int pktrem = pktmax;
 	int drem = dsz;
 	struct tipc_msg pkthdr;
-	struct sk_buff *buf, *prev;
+	struct sk_buff *skb;
 	char *pktpos;
 	int rc;
-	uint chain_sz = 0;
+
 	msg_set_size(mhdr, msz);
 
 	/* No fragmentation needed? */
 	if (likely(msz <= pktmax)) {
-		buf = tipc_buf_acquire(msz);
-		*chain = buf;
-		if (unlikely(!buf))
+		skb = tipc_buf_acquire(msz);
+		if (unlikely(!skb))
 			return -ENOMEM;
-		skb_copy_to_linear_data(buf, mhdr, mhsz);
-		pktpos = buf->data + mhsz;
-		TIPC_SKB_CB(buf)->chain_sz = 1;
-		if (!dsz || !memcpy_fromiovecend(pktpos, iov, offset, dsz))
+		skb_orphan(skb);
+		__skb_queue_tail(list, skb);
+		skb_copy_to_linear_data(skb, mhdr, mhsz);
+		pktpos = skb->data + mhsz;
+		if (copy_from_iter(pktpos, dsz, &m->msg_iter) == dsz)
 			return dsz;
 		rc = -EFAULT;
 		goto error;
 	}
 
 	/* Prepare reusable fragment header */
-	tipc_msg_init(&pkthdr, MSG_FRAGMENTER, FIRST_FRAGMENT,
-		      INT_H_SIZE, msg_destnode(mhdr));
+	tipc_msg_init(msg_prevnode(mhdr), &pkthdr, MSG_FRAGMENTER,
+		      FIRST_FRAGMENT, INT_H_SIZE, msg_destnode(mhdr));
 	msg_set_size(&pkthdr, pktmax);
 	msg_set_fragm_no(&pkthdr, pktno);
+	msg_set_importance(&pkthdr, msg_importance(mhdr));
 
 	/* Prepare first fragment */
-	*chain = buf = tipc_buf_acquire(pktmax);
-	if (!buf)
+	skb = tipc_buf_acquire(pktmax);
+	if (!skb)
 		return -ENOMEM;
-	chain_sz = 1;
-	pktpos = buf->data;
-	skb_copy_to_linear_data(buf, &pkthdr, INT_H_SIZE);
+	skb_orphan(skb);
+	__skb_queue_tail(list, skb);
+	pktpos = skb->data;
+	skb_copy_to_linear_data(skb, &pkthdr, INT_H_SIZE);
 	pktpos += INT_H_SIZE;
 	pktrem -= INT_H_SIZE;
-	skb_copy_to_linear_data_offset(buf, INT_H_SIZE, mhdr, mhsz);
+	skb_copy_to_linear_data_offset(skb, INT_H_SIZE, mhdr, mhsz);
 	pktpos += mhsz;
 	pktrem -= mhsz;
 
@@ -223,12 +292,11 @@ int tipc_msg_build(struct tipc_msg *mhdr, struct iovec const *iov,
 		if (drem < pktrem)
 			pktrem = drem;
 
-		if (memcpy_fromiovecend(pktpos, iov, offset, pktrem)) {
+		if (copy_from_iter(pktpos, pktrem, &m->msg_iter) != pktrem) {
 			rc = -EFAULT;
 			goto error;
 		}
 		drem -= pktrem;
-		offset += pktrem;
 
 		if (!drem)
 			break;
@@ -238,111 +306,153 @@ int tipc_msg_build(struct tipc_msg *mhdr, struct iovec const *iov,
 			pktsz = drem + INT_H_SIZE;
 		else
 			pktsz = pktmax;
-		prev = buf;
-		buf = tipc_buf_acquire(pktsz);
-		if (!buf) {
+		skb = tipc_buf_acquire(pktsz);
+		if (!skb) {
 			rc = -ENOMEM;
 			goto error;
 		}
-		chain_sz++;
-		prev->next = buf;
+		skb_orphan(skb);
+		__skb_queue_tail(list, skb);
 		msg_set_type(&pkthdr, FRAGMENT);
 		msg_set_size(&pkthdr, pktsz);
 		msg_set_fragm_no(&pkthdr, ++pktno);
-		skb_copy_to_linear_data(buf, &pkthdr, INT_H_SIZE);
-		pktpos = buf->data + INT_H_SIZE;
+		skb_copy_to_linear_data(skb, &pkthdr, INT_H_SIZE);
+		pktpos = skb->data + INT_H_SIZE;
 		pktrem = pktsz - INT_H_SIZE;
 
 	} while (1);
-	TIPC_SKB_CB(*chain)->chain_sz = chain_sz;
-	msg_set_type(buf_msg(buf), LAST_FRAGMENT);
+	msg_set_type(buf_msg(skb), LAST_FRAGMENT);
 	return dsz;
 error:
-	kfree_skb_list(*chain);
-	*chain = NULL;
+	__skb_queue_purge(list);
+	__skb_queue_head_init(list);
 	return rc;
 }
 
 /**
  * tipc_msg_bundle(): Append contents of a buffer to tail of an existing one
- * @bbuf: the existing buffer ("bundle")
- * @buf:  buffer to be appended
+ * @bskb: the buffer to append to ("bundle")
+ * @skb:  buffer to be appended
  * @mtu:  max allowable size for the bundle buffer
  * Consumes buffer if successful
  * Returns true if bundling could be performed, otherwise false
  */
-bool tipc_msg_bundle(struct sk_buff *bbuf, struct sk_buff *buf, u32 mtu)
+bool tipc_msg_bundle(struct sk_buff *bskb, struct sk_buff *skb, u32 mtu)
 {
-	struct tipc_msg *bmsg = buf_msg(bbuf);
-	struct tipc_msg *msg = buf_msg(buf);
-	unsigned int bsz = msg_size(bmsg);
+	struct tipc_msg *bmsg;
+	struct tipc_msg *msg = buf_msg(skb);
+	unsigned int bsz;
 	unsigned int msz = msg_size(msg);
-	u32 start = align(bsz);
+	u32 start, pad;
 	u32 max = mtu - INT_H_SIZE;
-	u32 pad = start - bsz;
 
 	if (likely(msg_user(msg) == MSG_FRAGMENTER))
 		return false;
-	if (unlikely(msg_user(msg) == CHANGEOVER_PROTOCOL))
+	if (!bskb)
+		return false;
+	bmsg = buf_msg(bskb);
+	bsz = msg_size(bmsg);
+	start = align(bsz);
+	pad = start - bsz;
+
+	if (unlikely(msg_user(msg) == TUNNEL_PROTOCOL))
 		return false;
 	if (unlikely(msg_user(msg) == BCAST_PROTOCOL))
 		return false;
 	if (likely(msg_user(bmsg) != MSG_BUNDLER))
 		return false;
-	if (likely(msg_type(bmsg) != BUNDLE_OPEN))
-		return false;
-	if (unlikely(skb_tailroom(bbuf) < (pad + msz)))
+	if (unlikely(skb_tailroom(bskb) < (pad + msz)))
 		return false;
 	if (unlikely(max < (start + msz)))
 		return false;
 
-	skb_put(bbuf, pad + msz);
-	skb_copy_to_linear_data_offset(bbuf, start, buf->data, msz);
+	skb_put(bskb, pad + msz);
+	skb_copy_to_linear_data_offset(bskb, start, skb->data, msz);
 	msg_set_size(bmsg, start + msz);
 	msg_set_msgcnt(bmsg, msg_msgcnt(bmsg) + 1);
-	bbuf->next = buf->next;
-	kfree_skb(buf);
+	kfree_skb(skb);
 	return true;
 }
 
 /**
+ *  tipc_msg_extract(): extract bundled inner packet from buffer
+ *  @skb: buffer to be extracted from.
+ *  @iskb: extracted inner buffer, to be returned
+ *  @pos: position in outer message of msg to be extracted.
+ *        Returns position of next msg
+ *  Consumes outer buffer when last packet extracted
+ *  Returns true when when there is an extracted buffer, otherwise false
+ */
+bool tipc_msg_extract(struct sk_buff *skb, struct sk_buff **iskb, int *pos)
+{
+	struct tipc_msg *msg;
+	int imsz, offset;
+
+	*iskb = NULL;
+	if (unlikely(skb_linearize(skb)))
+		goto none;
+
+	msg = buf_msg(skb);
+	offset = msg_hdr_sz(msg) + *pos;
+	if (unlikely(offset > (msg_size(msg) - MIN_H_SIZE)))
+		goto none;
+
+	*iskb = skb_clone(skb, GFP_ATOMIC);
+	if (unlikely(!*iskb))
+		goto none;
+	skb_pull(*iskb, offset);
+	imsz = msg_size(buf_msg(*iskb));
+	skb_trim(*iskb, imsz);
+	if (unlikely(!tipc_msg_validate(*iskb)))
+		goto none;
+	*pos += align(imsz);
+	return true;
+none:
+	kfree_skb(skb);
+	kfree_skb(*iskb);
+	*iskb = NULL;
+	return false;
+}
+
+/**
  * tipc_msg_make_bundle(): Create bundle buf and append message to its tail
- * @buf:  buffer to be appended and replaced
- * @mtu:  max allowable size for the bundle buffer, inclusive header
+ * @list: the buffer chain
+ * @skb: buffer to be appended and replaced
+ * @mtu: max allowable size for the bundle buffer, inclusive header
  * @dnode: destination node for message. (Not always present in header)
  * Replaces buffer if successful
- * Returns true if sucess, otherwise false
+ * Returns true if success, otherwise false
  */
-bool tipc_msg_make_bundle(struct sk_buff **buf, u32 mtu, u32 dnode)
+bool tipc_msg_make_bundle(struct sk_buff **skb, u32 mtu, u32 dnode)
 {
-	struct sk_buff *bbuf;
+	struct sk_buff *bskb;
 	struct tipc_msg *bmsg;
-	struct tipc_msg *msg = buf_msg(*buf);
+	struct tipc_msg *msg = buf_msg(*skb);
 	u32 msz = msg_size(msg);
 	u32 max = mtu - INT_H_SIZE;
 
 	if (msg_user(msg) == MSG_FRAGMENTER)
 		return false;
-	if (msg_user(msg) == CHANGEOVER_PROTOCOL)
+	if (msg_user(msg) == TUNNEL_PROTOCOL)
 		return false;
 	if (msg_user(msg) == BCAST_PROTOCOL)
 		return false;
 	if (msz > (max / 2))
 		return false;
 
-	bbuf = tipc_buf_acquire(max);
-	if (!bbuf)
+	bskb = tipc_buf_acquire(max);
+	if (!bskb)
 		return false;
 
-	skb_trim(bbuf, INT_H_SIZE);
-	bmsg = buf_msg(bbuf);
-	tipc_msg_init(bmsg, MSG_BUNDLER, BUNDLE_OPEN, INT_H_SIZE, dnode);
+	skb_trim(bskb, INT_H_SIZE);
+	bmsg = buf_msg(bskb);
+	tipc_msg_init(msg_prevnode(msg), bmsg, MSG_BUNDLER, 0,
+		      INT_H_SIZE, dnode);
 	msg_set_seqno(bmsg, msg_seqno(msg));
 	msg_set_ack(bmsg, msg_ack(msg));
 	msg_set_bcast_ack(bmsg, msg_bcast_ack(msg));
-	bbuf->next = (*buf)->next;
-	tipc_msg_bundle(bbuf, *buf, mtu);
-	*buf = bbuf;
+	tipc_msg_bundle(bskb, *skb, mtu);
+	*skb = bskb;
 	return true;
 }
 
@@ -354,28 +464,25 @@ bool tipc_msg_make_bundle(struct sk_buff **buf, u32 mtu, u32 dnode)
  * Consumes buffer if failure
  * Returns true if success, otherwise false
  */
-bool tipc_msg_reverse(struct sk_buff *buf, u32 *dnode, int err)
+bool tipc_msg_reverse(u32 own_addr,  struct sk_buff *buf, u32 *dnode,
+		      int err)
 {
 	struct tipc_msg *msg = buf_msg(buf);
-	uint imp = msg_importance(msg);
 	struct tipc_msg ohdr;
 	uint rdsz = min_t(uint, msg_data_sz(msg), MAX_FORWARD_SIZE);
 
 	if (skb_linearize(buf))
 		goto exit;
+	msg = buf_msg(buf);
 	if (msg_dest_droppable(msg))
 		goto exit;
 	if (msg_errcode(msg))
 		goto exit;
-
 	memcpy(&ohdr, msg, msg_hdr_sz(msg));
-	imp = min_t(uint, imp + 1, TIPC_CRITICAL_IMPORTANCE);
-	if (msg_isdata(msg))
-		msg_set_importance(msg, imp);
 	msg_set_errcode(msg, err);
 	msg_set_origport(msg, msg_destport(&ohdr));
 	msg_set_destport(msg, msg_origport(&ohdr));
-	msg_set_prevnode(msg, tipc_own_addr);
+	msg_set_prevnode(msg, own_addr);
 	if (!msg_short(msg)) {
 		msg_set_orignode(msg, msg_destnode(&ohdr));
 		msg_set_destnode(msg, msg_orignode(&ohdr));
@@ -387,64 +494,70 @@ bool tipc_msg_reverse(struct sk_buff *buf, u32 *dnode, int err)
 	return true;
 exit:
 	kfree_skb(buf);
+	*dnode = 0;
 	return false;
 }
 
 /**
- * tipc_msg_eval: determine fate of message that found no destination
- * @buf: the buffer containing the message.
- * @dnode: return value: next-hop node, if message to be forwarded
- * @err: error code to use, if message to be rejected
- *
+ * tipc_msg_lookup_dest(): try to find new destination for named message
+ * @skb: the buffer containing the message.
+ * @dnode: return value: next-hop node, if destination found
+ * @err: return value: error code to use, if message to be rejected
  * Does not consume buffer
- * Returns 0 (TIPC_OK) if message ok and we can try again, -TIPC error
- * code if message to be rejected
+ * Returns true if a destination is found, false otherwise
  */
-int tipc_msg_eval(struct sk_buff *buf, u32 *dnode)
+bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb,
+			  u32 *dnode, int *err)
 {
-	struct tipc_msg *msg = buf_msg(buf);
+	struct tipc_msg *msg = buf_msg(skb);
 	u32 dport;
+	u32 own_addr = tipc_own_addr(net);
 
-	if (msg_type(msg) != TIPC_NAMED_MSG)
-		return -TIPC_ERR_NO_PORT;
-	if (skb_linearize(buf))
-		return -TIPC_ERR_NO_NAME;
-	if (msg_data_sz(msg) > MAX_FORWARD_SIZE)
-		return -TIPC_ERR_NO_NAME;
-	if (msg_reroute_cnt(msg) > 0)
-		return -TIPC_ERR_NO_NAME;
-
-	*dnode = addr_domain(msg_lookup_scope(msg));
-	dport = tipc_nametbl_translate(msg_nametype(msg),
-				       msg_nameinst(msg),
-				       dnode);
+	if (!msg_isdata(msg))
+		return false;
+	if (!msg_named(msg))
+		return false;
+	if (msg_errcode(msg))
+		return false;
+	*err = -TIPC_ERR_NO_NAME;
+	if (skb_linearize(skb))
+		return false;
+	if (msg_reroute_cnt(msg))
+		return false;
+	*dnode = addr_domain(net, msg_lookup_scope(msg));
+	dport = tipc_nametbl_translate(net, msg_nametype(msg),
+				       msg_nameinst(msg), dnode);
 	if (!dport)
-		return -TIPC_ERR_NO_NAME;
+		return false;
 	msg_incr_reroute_cnt(msg);
+	if (*dnode != own_addr)
+		msg_set_prevnode(msg, own_addr);
 	msg_set_destnode(msg, *dnode);
 	msg_set_destport(msg, dport);
-	return TIPC_OK;
+	*err = TIPC_OK;
+	return true;
 }
 
 /* tipc_msg_reassemble() - clone a buffer chain of fragments and
  *                         reassemble the clones into one message
  */
-struct sk_buff *tipc_msg_reassemble(struct sk_buff *chain)
+struct sk_buff *tipc_msg_reassemble(struct sk_buff_head *list)
 {
-	struct sk_buff *buf = chain;
-	struct sk_buff *frag = buf;
+	struct sk_buff *skb;
+	struct sk_buff *frag = NULL;
 	struct sk_buff *head = NULL;
 	int hdr_sz;
 
 	/* Copy header if single buffer */
-	if (!buf->next) {
-		hdr_sz = skb_headroom(buf) + msg_hdr_sz(buf_msg(buf));
-		return __pskb_copy(buf, hdr_sz, GFP_ATOMIC);
+	if (skb_queue_len(list) == 1) {
+		skb = skb_peek(list);
+		hdr_sz = skb_headroom(skb) + msg_hdr_sz(buf_msg(skb));
+		return __pskb_copy(skb, hdr_sz, GFP_ATOMIC);
 	}
 
 	/* Clone all fragments and reassemble */
-	while (buf) {
-		frag = skb_clone(buf, GFP_ATOMIC);
+	skb_queue_walk(list, skb) {
+		frag = skb_clone(skb, GFP_ATOMIC);
 		if (!frag)
 			goto error;
 		frag->next = NULL;
@@ -452,7 +565,6 @@ struct sk_buff *tipc_msg_reassemble(struct sk_buff *chain)
 			break;
 		if (!head)
 			goto error;
-		buf = buf->next;
 	}
 	return frag;
 error:
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index 0ea7b695ac4d..e1d3595e2ee9 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, 2014, Ericsson AB
+ * Copyright (c) 2000-2007, 2014-2015 Ericsson AB
  * Copyright (c) 2005-2008, 2010-2011, Wind River Systems
  * All rights reserved.
  *
@@ -37,7 +37,7 @@
 #ifndef _TIPC_MSG_H
 #define _TIPC_MSG_H
 
-#include "bearer.h"
+#include <linux/tipc.h>
 
 /*
  * Constants and routines used to read and write TIPC payload message headers
@@ -45,6 +45,7 @@
  * Note: Some items are also used with TIPC internal message headers
  */
 #define TIPC_VERSION              2
+struct plist;
 
 /*
  * Payload message users are defined in TIPC's public API:
@@ -53,6 +54,8 @@
  * - TIPC_HIGH_IMPORTANCE
  * - TIPC_CRITICAL_IMPORTANCE
  */
+#define TIPC_SYSTEM_IMPORTANCE	4
+
 
 /*
  * Payload message types
@@ -63,6 +66,19 @@
 #define TIPC_DIRECT_MSG		3
 
 /*
+ * Internal message users
+ */
+#define  BCAST_PROTOCOL       5
+#define  MSG_BUNDLER          6
+#define  LINK_PROTOCOL        7
+#define  CONN_MANAGER         8
+#define  TUNNEL_PROTOCOL      10
+#define  NAME_DISTRIBUTOR     11
+#define  MSG_FRAGMENTER       12
+#define  LINK_CONFIG          13
+#define  SOCK_WAKEUP          14       /* pseudo user */
+
+/*
  * Message header sizes
  */
 #define SHORT_H_SIZE              24	/* In-cluster basic payload message */
@@ -75,13 +91,39 @@
 
 #define MAX_MSG_SIZE (MAX_H_SIZE + TIPC_MAX_USER_MSG_SIZE)
 
-#define TIPC_MEDIA_ADDR_OFFSET	5
+#define TIPC_MEDIA_INFO_OFFSET	5
 
+/**
+ * TIPC message buffer code
+ *
+ * TIPC message buffer headroom reserves space for the worst-case
+ * link-level device header (in case the message is sent off-node).
+ *
+ * Note: Headroom should be a multiple of 4 to ensure the TIPC header fields
+ *       are word aligned for quicker access
+ */
+#define BUF_HEADROOM (LL_MAX_HEADER + 48)
+
+struct tipc_skb_cb {
+	void *handle;
+	struct sk_buff *tail;
+	bool validated;
+	bool wakeup_pending;
+	bool bundling;
+	u16 chain_sz;
+	u16 chain_imp;
+};
+
+#define TIPC_SKB_CB(__skb) ((struct tipc_skb_cb *)&((__skb)->cb[0]))
 
 struct tipc_msg {
 	__be32 hdr[15];
 };
 
+static inline struct tipc_msg *buf_msg(struct sk_buff *skb)
+{
+	return (struct tipc_msg *)skb->data;
+}
 
 static inline u32 msg_word(struct tipc_msg *m, u32 pos)
 {
@@ -143,16 +185,6 @@ static inline void msg_set_user(struct tipc_msg *m, u32 n)
 	msg_set_bits(m, 0, 25, 0xf, n);
 }
 
-static inline u32 msg_importance(struct tipc_msg *m)
-{
-	return msg_bits(m, 0, 25, 0xf);
-}
-
-static inline void msg_set_importance(struct tipc_msg *m, u32 i)
-{
-	msg_set_user(m, i);
-}
-
 static inline u32 msg_hdr_sz(struct tipc_msg *m)
 {
 	return msg_bits(m, 0, 21, 0xf) << 2;
@@ -208,6 +240,15 @@ static inline void msg_set_size(struct tipc_msg *m, u32 sz)
 	m->hdr[0] = htonl((msg_word(m, 0) & ~0x1ffff) | sz);
 }
 
+static inline unchar *msg_data(struct tipc_msg *m)
+{
+	return ((unchar *)m) + msg_hdr_sz(m);
+}
+
+static inline struct tipc_msg *msg_get_wrapped(struct tipc_msg *m)
+{
+	return (struct tipc_msg *)msg_data(m);
+}
 
 /*
  * Word 1
@@ -309,6 +350,25 @@ static inline void msg_set_seqno(struct tipc_msg *m, u32 n)
 /*
  * Words 3-10
  */
+static inline u32 msg_importance(struct tipc_msg *m)
+{
+	if (unlikely(msg_user(m) == MSG_FRAGMENTER))
+		return msg_bits(m, 5, 13, 0x7);
+	if (likely(msg_isdata(m) && !msg_errcode(m)))
+		return msg_user(m);
+	return TIPC_SYSTEM_IMPORTANCE;
+}
+
+static inline void msg_set_importance(struct tipc_msg *m, u32 i)
+{
+	if (unlikely(msg_user(m) == MSG_FRAGMENTER))
+		msg_set_bits(m, 5, 13, 0x7, i);
+	else if (likely(i < TIPC_SYSTEM_IMPORTANCE))
+		msg_set_user(m, i);
+	else
+		pr_warn("Trying to set illegal importance in message\n");
+}
+
 static inline u32 msg_prevnode(struct tipc_msg *m)
 {
 	return msg_word(m, 3);
@@ -321,6 +381,8 @@ static inline void msg_set_prevnode(struct tipc_msg *m, u32 a)
 
 static inline u32 msg_origport(struct tipc_msg *m)
 {
+	if (msg_user(m) == MSG_FRAGMENTER)
+		m = msg_get_wrapped(m);
 	return msg_word(m, 4);
 }
 
@@ -416,35 +478,11 @@ static inline void msg_set_nameupper(struct tipc_msg *m, u32 n)
 	msg_set_word(m, 10, n);
 }
 
-static inline unchar *msg_data(struct tipc_msg *m)
-{
-	return ((unchar *)m) + msg_hdr_sz(m);
-}
-
-static inline struct tipc_msg *msg_get_wrapped(struct tipc_msg *m)
-{
-	return (struct tipc_msg *)msg_data(m);
-}
-
 /*
  * Constants and routines used to read and write TIPC internal message headers
  */
 
 /*
- * Internal message users
- */
-#define  BCAST_PROTOCOL       5
-#define  MSG_BUNDLER          6
-#define  LINK_PROTOCOL        7
-#define  CONN_MANAGER         8
-#define  ROUTE_DISTRIBUTOR    9		/* obsoleted */
-#define  CHANGEOVER_PROTOCOL  10
-#define  NAME_DISTRIBUTOR     11
-#define  MSG_FRAGMENTER       12
-#define  LINK_CONFIG          13
-#define  SOCK_WAKEUP          14       /* pseudo user */
-
-/*
  *  Connection management protocol message types
  */
 #define CONN_PROBE        0
@@ -464,11 +502,6 @@ static inline struct tipc_msg *msg_get_wrapped(struct tipc_msg *m)
 #define FRAGMENT		1
 #define LAST_FRAGMENT		2
 
-/* Bundling protocol message types
- */
-#define BUNDLE_OPEN             0
-#define BUNDLE_CLOSED           1
-
 /*
  * Link management protocol message types
  */
@@ -479,8 +512,8 @@ static inline struct tipc_msg *msg_get_wrapped(struct tipc_msg *m)
 /*
  * Changeover tunnel message types
  */
-#define DUPLICATE_MSG		0
-#define ORIGINAL_MSG		1
+#define SYNCH_MSG		0
+#define FAILOVER_MSG		1
 
 /*
  * Config protocol message types
@@ -488,7 +521,6 @@ static inline struct tipc_msg *msg_get_wrapped(struct tipc_msg *m)
 #define DSC_REQ_MSG		0
 #define DSC_RESP_MSG		1
 
-
 /*
  * Word 1
  */
@@ -512,6 +544,24 @@ static inline void msg_set_node_sig(struct tipc_msg *m, u32 n)
 	msg_set_bits(m, 1, 0, 0xffff, n);
 }
 
+static inline u32 msg_node_capabilities(struct tipc_msg *m)
+{
+	return msg_bits(m, 1, 15, 0x1fff);
+}
+
+static inline void msg_set_node_capabilities(struct tipc_msg *m, u32 n)
+{
+	msg_set_bits(m, 1, 15, 0x1fff, n);
+}
+
+static inline bool msg_dup(struct tipc_msg *m)
+{
+	if (likely(msg_user(m) != TUNNEL_PROTOCOL))
+		return false;
+	if (msg_type(m) != SYNCH_MSG)
+		return false;
+	return true;
+}
 
 /*
  * Word 2
@@ -666,7 +716,7 @@ static inline void msg_set_redundant_link(struct tipc_msg *m, u32 r)
 
 static inline char *msg_media_addr(struct tipc_msg *m)
 {
-	return (char *)&m->hdr[TIPC_MEDIA_ADDR_OFFSET];
+	return (char *)&m->hdr[TIPC_MEDIA_INFO_OFFSET];
 }
 
 /*
@@ -712,40 +762,112 @@ static inline void msg_set_link_tolerance(struct tipc_msg *m, u32 n)
 	msg_set_bits(m, 9, 0, 0xffff, n);
 }
 
-static inline u32 tipc_msg_tot_importance(struct tipc_msg *m)
-{
-	if ((msg_user(m) == MSG_FRAGMENTER) && (msg_type(m) == FIRST_FRAGMENT))
-		return msg_importance(msg_get_wrapped(m));
-	return msg_importance(m);
-}
-
-static inline u32 msg_tot_origport(struct tipc_msg *m)
-{
-	if ((msg_user(m) == MSG_FRAGMENTER) && (msg_type(m) == FIRST_FRAGMENT))
-		return msg_origport(msg_get_wrapped(m));
-	return msg_origport(m);
-}
-
-bool tipc_msg_reverse(struct sk_buff *buf, u32 *dnode, int err);
-
-int tipc_msg_eval(struct sk_buff *buf, u32 *dnode);
-
-void tipc_msg_init(struct tipc_msg *m, u32 user, u32 type, u32 hsize,
-		   u32 destnode);
-
+struct sk_buff *tipc_buf_acquire(u32 size);
+bool tipc_msg_validate(struct sk_buff *skb);
+bool tipc_msg_reverse(u32 own_addr, struct sk_buff *buf, u32 *dnode,
+		      int err);
+void tipc_msg_init(u32 own_addr, struct tipc_msg *m, u32 user, u32 type,
+		   u32 hsize, u32 destnode);
 struct sk_buff *tipc_msg_create(uint user, uint type, uint hdr_sz,
 				uint data_sz, u32 dnode, u32 onode,
 				u32 dport, u32 oport, int errcode);
-
 int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf);
+bool tipc_msg_bundle(struct sk_buff *bskb, struct sk_buff *skb, u32 mtu);
+
+bool tipc_msg_make_bundle(struct sk_buff **skb, u32 mtu, u32 dnode);
+bool tipc_msg_extract(struct sk_buff *skb, struct sk_buff **iskb, int *pos);
+int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m,
+		   int offset, int dsz, int mtu, struct sk_buff_head *list);
+bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, u32 *dnode,
+			  int *err);
+struct sk_buff *tipc_msg_reassemble(struct sk_buff_head *list);
+
+/* tipc_skb_peek(): peek and reserve first buffer in list
+ * @list: list to be peeked in
+ * Returns pointer to first buffer in list, if any
+ */
+static inline struct sk_buff *tipc_skb_peek(struct sk_buff_head *list,
+					    spinlock_t *lock)
+{
+	struct sk_buff *skb;
+
+	spin_lock_bh(lock);
+	skb = skb_peek(list);
+	if (skb)
+		skb_get(skb);
+	spin_unlock_bh(lock);
+	return skb;
+}
+
+/* tipc_skb_peek_port(): find a destination port, ignoring all destinations
+ *                       up to and including 'filter'.
+ * Note: ignoring previously tried destinations minimizes the risk of
+ *       contention on the socket lock
+ * @list: list to be peeked in
+ * @filter: last destination to be ignored from search
+ * Returns a destination port number, of applicable.
+ */
+static inline u32 tipc_skb_peek_port(struct sk_buff_head *list, u32 filter)
+{
+	struct sk_buff *skb;
+	u32 dport = 0;
+	bool ignore = true;
+
+	spin_lock_bh(&list->lock);
+	skb_queue_walk(list, skb) {
+		dport = msg_destport(buf_msg(skb));
+		if (!filter || skb_queue_is_last(list, skb))
+			break;
+		if (dport == filter)
+			ignore = false;
+		else if (!ignore)
+			break;
+	}
+	spin_unlock_bh(&list->lock);
+	return dport;
+}
+
+/* tipc_skb_dequeue(): unlink first buffer with dest 'dport' from list
+ * @list: list to be unlinked from
+ * @dport: selection criteria for buffer to unlink
+ */
+static inline struct sk_buff *tipc_skb_dequeue(struct sk_buff_head *list,
+					       u32 dport)
+{
+	struct sk_buff *_skb, *tmp, *skb = NULL;
+
+	spin_lock_bh(&list->lock);
+	skb_queue_walk_safe(list, _skb, tmp) {
+		if (msg_destport(buf_msg(_skb)) == dport) {
+			__skb_unlink(_skb, list);
+			skb = _skb;
+			break;
+		}
+	}
+	spin_unlock_bh(&list->lock);
+	return skb;
+}
+
+/* tipc_skb_queue_tail(): add buffer to tail of list;
+ * @list: list to be appended to
+ * @skb: buffer to append. Always appended
+ * @dport: the destination port of the buffer
+ * returns true if dport differs from previous destination
+ */
+static inline bool tipc_skb_queue_tail(struct sk_buff_head *list,
+				       struct sk_buff *skb, u32 dport)
+{
+	struct sk_buff *_skb = NULL;
+	bool rv = false;
 
-bool tipc_msg_bundle(struct sk_buff *bbuf, struct sk_buff *buf, u32 mtu);
-
-bool tipc_msg_make_bundle(struct sk_buff **buf, u32 mtu, u32 dnode);
-
-int tipc_msg_build(struct tipc_msg *mhdr, struct iovec const *iov,
-		   int offset, int dsz, int mtu , struct sk_buff **chain);
-
-struct sk_buff *tipc_msg_reassemble(struct sk_buff *chain);
+	spin_lock_bh(&list->lock);
+	_skb = skb_peek_tail(list);
+	if (!_skb || (msg_destport(buf_msg(_skb)) != dport) ||
+	    (skb_queue_len(list) > 32))
+		rv = true;
+	__skb_queue_tail(list, skb);
+	spin_unlock_bh(&list->lock);
+	return rv;
+}
 
 #endif
diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c
index 376d2bb51d8d..41e7b7e4dda0 100644
--- a/net/tipc/name_distr.c
+++ b/net/tipc/name_distr.c
@@ -38,39 +38,6 @@
 #include "link.h"
 #include "name_distr.h"
 
-/**
- * struct publ_list - list of publications made by this node
- * @list: circular list of publications
- * @list_size: number of entries in list
- */
-struct publ_list {
-	struct list_head list;
-	u32 size;
-};
-
-static struct publ_list publ_zone = {
-	.list = LIST_HEAD_INIT(publ_zone.list),
-	.size = 0,
-};
-
-static struct publ_list publ_cluster = {
-	.list = LIST_HEAD_INIT(publ_cluster.list),
-	.size = 0,
-};
-
-static struct publ_list publ_node = {
-	.list = LIST_HEAD_INIT(publ_node.list),
-	.size = 0,
-};
-
-static struct publ_list *publ_lists[] = {
-	NULL,
-	&publ_zone,	/* publ_lists[TIPC_ZONE_SCOPE]		*/
-	&publ_cluster,	/* publ_lists[TIPC_CLUSTER_SCOPE]	*/
-	&publ_node	/* publ_lists[TIPC_NODE_SCOPE]		*/
-};
-
-
 int sysctl_tipc_named_timeout __read_mostly = 2000;
 
 /**
@@ -101,58 +68,63 @@ static void publ_to_item(struct distr_item *i, struct publication *p)
 /**
  * named_prepare_buf - allocate & initialize a publication message
  */
-static struct sk_buff *named_prepare_buf(u32 type, u32 size, u32 dest)
+static struct sk_buff *named_prepare_buf(struct net *net, u32 type, u32 size,
+					 u32 dest)
 {
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	struct sk_buff *buf = tipc_buf_acquire(INT_H_SIZE + size);
 	struct tipc_msg *msg;
 
 	if (buf != NULL) {
 		msg = buf_msg(buf);
-		tipc_msg_init(msg, NAME_DISTRIBUTOR, type, INT_H_SIZE, dest);
+		tipc_msg_init(tn->own_addr, msg, NAME_DISTRIBUTOR, type,
+			      INT_H_SIZE, dest);
 		msg_set_size(msg, INT_H_SIZE + size);
 	}
 	return buf;
 }
 
-void named_cluster_distribute(struct sk_buff *buf)
+void named_cluster_distribute(struct net *net, struct sk_buff *skb)
 {
-	struct sk_buff *obuf;
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	struct sk_buff *oskb;
 	struct tipc_node *node;
 	u32 dnode;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(node, &tipc_node_list, list) {
+	list_for_each_entry_rcu(node, &tn->node_list, list) {
 		dnode = node->addr;
-		if (in_own_node(dnode))
+		if (in_own_node(net, dnode))
 			continue;
 		if (!tipc_node_active_links(node))
 			continue;
-		obuf = skb_copy(buf, GFP_ATOMIC);
-		if (!obuf)
+		oskb = pskb_copy(skb, GFP_ATOMIC);
+		if (!oskb)
 			break;
-		msg_set_destnode(buf_msg(obuf), dnode);
-		tipc_link_xmit(obuf, dnode, dnode);
+		msg_set_destnode(buf_msg(oskb), dnode);
+		tipc_link_xmit_skb(net, oskb, dnode, dnode);
 	}
 	rcu_read_unlock();
 
-	kfree_skb(buf);
+	kfree_skb(skb);
 }
 
 /**
  * tipc_named_publish - tell other nodes about a new publication by this node
  */
-struct sk_buff *tipc_named_publish(struct publication *publ)
+struct sk_buff *tipc_named_publish(struct net *net, struct publication *publ)
 {
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	struct sk_buff *buf;
 	struct distr_item *item;
 
-	list_add_tail(&publ->local_list, &publ_lists[publ->scope]->list);
-	publ_lists[publ->scope]->size++;
+	list_add_tail_rcu(&publ->local_list,
+			  &tn->nametbl->publ_list[publ->scope]);
 
 	if (publ->scope == TIPC_NODE_SCOPE)
 		return NULL;
 
-	buf = named_prepare_buf(PUBLICATION, ITEM_SIZE, 0);
+	buf = named_prepare_buf(net, PUBLICATION, ITEM_SIZE, 0);
 	if (!buf) {
 		pr_warn("Publication distribution failure\n");
 		return NULL;
@@ -166,18 +138,17 @@ struct sk_buff *tipc_named_publish(struct publication *publ)
 /**
  * tipc_named_withdraw - tell other nodes about a withdrawn publication by this node
  */
-struct sk_buff *tipc_named_withdraw(struct publication *publ)
+struct sk_buff *tipc_named_withdraw(struct net *net, struct publication *publ)
 {
 	struct sk_buff *buf;
 	struct distr_item *item;
 
 	list_del(&publ->local_list);
-	publ_lists[publ->scope]->size--;
 
 	if (publ->scope == TIPC_NODE_SCOPE)
 		return NULL;
 
-	buf = named_prepare_buf(WITHDRAWAL, ITEM_SIZE, 0);
+	buf = named_prepare_buf(net, WITHDRAWAL, ITEM_SIZE, 0);
 	if (!buf) {
 		pr_warn("Withdrawal distribution failure\n");
 		return NULL;
@@ -190,32 +161,30 @@ struct sk_buff *tipc_named_withdraw(struct publication *publ)
 
 /**
  * named_distribute - prepare name info for bulk distribution to another node
- * @msg_list: list of messages (buffers) to be returned from this function
+ * @list: list of messages (buffers) to be returned from this function
  * @dnode: node to be updated
  * @pls: linked list of publication items to be packed into buffer chain
  */
-static void named_distribute(struct list_head *msg_list, u32 dnode,
-			     struct publ_list *pls)
+static void named_distribute(struct net *net, struct sk_buff_head *list,
+			     u32 dnode, struct list_head *pls)
 {
 	struct publication *publ;
-	struct sk_buff *buf = NULL;
+	struct sk_buff *skb = NULL;
 	struct distr_item *item = NULL;
-	uint dsz = pls->size * ITEM_SIZE;
-	uint msg_dsz = (tipc_node_get_mtu(dnode, 0) / ITEM_SIZE) * ITEM_SIZE;
-	uint rem = dsz;
-	uint msg_rem = 0;
+	uint msg_dsz = (tipc_node_get_mtu(net, dnode, 0) / ITEM_SIZE) *
+			ITEM_SIZE;
+	uint msg_rem = msg_dsz;
 
-	list_for_each_entry(publ, &pls->list, local_list) {
+	list_for_each_entry(publ, pls, local_list) {
 		/* Prepare next buffer: */
-		if (!buf) {
-			msg_rem = min_t(uint, rem, msg_dsz);
-			rem -= msg_rem;
-			buf = named_prepare_buf(PUBLICATION, msg_rem, dnode);
-			if (!buf) {
+		if (!skb) {
+			skb = named_prepare_buf(net, PUBLICATION, msg_rem,
+						dnode);
+			if (!skb) {
 				pr_warn("Bulk publication failure\n");
 				return;
 			}
-			item = (struct distr_item *)msg_data(buf_msg(buf));
+			item = (struct distr_item *)msg_data(buf_msg(skb));
 		}
 
 		/* Pack publication into message: */
@@ -225,47 +194,91 @@ static void named_distribute(struct list_head *msg_list, u32 dnode,
 
 		/* Append full buffer to list: */
 		if (!msg_rem) {
-			list_add_tail((struct list_head *)buf, msg_list);
-			buf = NULL;
+			__skb_queue_tail(list, skb);
+			skb = NULL;
+			msg_rem = msg_dsz;
 		}
 	}
+	if (skb) {
+		msg_set_size(buf_msg(skb), INT_H_SIZE + (msg_dsz - msg_rem));
+		skb_trim(skb, INT_H_SIZE + (msg_dsz - msg_rem));
+		__skb_queue_tail(list, skb);
+	}
 }
 
 /**
  * tipc_named_node_up - tell specified node about all publications by this node
  */
-void tipc_named_node_up(u32 dnode)
+void tipc_named_node_up(struct net *net, u32 dnode)
 {
-	LIST_HEAD(msg_list);
-	struct sk_buff *buf_chain;
-
-	read_lock_bh(&tipc_nametbl_lock);
-	named_distribute(&msg_list, dnode, &publ_cluster);
-	named_distribute(&msg_list, dnode, &publ_zone);
-	read_unlock_bh(&tipc_nametbl_lock);
-
-	/* Convert circular list to linear list and send: */
-	buf_chain = (struct sk_buff *)msg_list.next;
-	((struct sk_buff *)msg_list.prev)->next = NULL;
-	tipc_link_xmit(buf_chain, dnode, dnode);
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	struct sk_buff_head head;
+
+	__skb_queue_head_init(&head);
+
+	rcu_read_lock();
+	named_distribute(net, &head, dnode,
+			 &tn->nametbl->publ_list[TIPC_CLUSTER_SCOPE]);
+	named_distribute(net, &head, dnode,
+			 &tn->nametbl->publ_list[TIPC_ZONE_SCOPE]);
+	rcu_read_unlock();
+
+	tipc_link_xmit(net, &head, dnode, dnode);
+}
+
+static void tipc_publ_subscribe(struct net *net, struct publication *publ,
+				u32 addr)
+{
+	struct tipc_node *node;
+
+	if (in_own_node(net, addr))
+		return;
+
+	node = tipc_node_find(net, addr);
+	if (!node) {
+		pr_warn("Node subscription rejected, unknown node 0x%x\n",
+			addr);
+		return;
+	}
+
+	tipc_node_lock(node);
+	list_add_tail(&publ->nodesub_list, &node->publ_list);
+	tipc_node_unlock(node);
+	tipc_node_put(node);
+}
+
+static void tipc_publ_unsubscribe(struct net *net, struct publication *publ,
+				  u32 addr)
+{
+	struct tipc_node *node;
+
+	node = tipc_node_find(net, addr);
+	if (!node)
+		return;
+
+	tipc_node_lock(node);
+	list_del_init(&publ->nodesub_list);
+	tipc_node_unlock(node);
+	tipc_node_put(node);
 }
 
 /**
- * named_purge_publ - remove publication associated with a failed node
+ * tipc_publ_purge - remove publication associated with a failed node
  *
  * Invoked for each publication issued by a newly failed node.
  * Removes publication structure from name table & deletes it.
  */
-static void named_purge_publ(struct publication *publ)
+static void tipc_publ_purge(struct net *net, struct publication *publ, u32 addr)
 {
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	struct publication *p;
 
-	write_lock_bh(&tipc_nametbl_lock);
-	p = tipc_nametbl_remove_publ(publ->type, publ->lower,
+	spin_lock_bh(&tn->nametbl_lock);
+	p = tipc_nametbl_remove_publ(net, publ->type, publ->lower,
 				     publ->node, publ->ref, publ->key);
 	if (p)
-		tipc_nodesub_unsubscribe(&p->subscr);
-	write_unlock_bh(&tipc_nametbl_lock);
+		tipc_publ_unsubscribe(net, p, addr);
+	spin_unlock_bh(&tn->nametbl_lock);
 
 	if (p != publ) {
 		pr_err("Unable to remove publication from failed node\n"
@@ -274,7 +287,15 @@ static void named_purge_publ(struct publication *publ)
 		       publ->key);
 	}
 
-	kfree(p);
+	kfree_rcu(p, rcu);
+}
+
+void tipc_publ_notify(struct net *net, struct list_head *nsub_list, u32 addr)
+{
+	struct publication *publ, *tmp;
+
+	list_for_each_entry_safe(publ, tmp, nsub_list, nodesub_list)
+		tipc_publ_purge(net, publ, addr);
 }
 
 /**
@@ -284,28 +305,29 @@ static void named_purge_publ(struct publication *publ)
  * tipc_nametbl_lock must be held.
  * Returns the publication item if successful, otherwise NULL.
  */
-static bool tipc_update_nametbl(struct distr_item *i, u32 node, u32 dtype)
+static bool tipc_update_nametbl(struct net *net, struct distr_item *i,
+				u32 node, u32 dtype)
 {
 	struct publication *publ = NULL;
 
 	if (dtype == PUBLICATION) {
-		publ = tipc_nametbl_insert_publ(ntohl(i->type), ntohl(i->lower),
+		publ = tipc_nametbl_insert_publ(net, ntohl(i->type),
+						ntohl(i->lower),
 						ntohl(i->upper),
 						TIPC_CLUSTER_SCOPE, node,
 						ntohl(i->ref), ntohl(i->key));
 		if (publ) {
-			tipc_nodesub_subscribe(&publ->subscr, node, publ,
-					       (net_ev_handler)
-					       named_purge_publ);
+			tipc_publ_subscribe(net, publ, node);
 			return true;
 		}
 	} else if (dtype == WITHDRAWAL) {
-		publ = tipc_nametbl_remove_publ(ntohl(i->type), ntohl(i->lower),
+		publ = tipc_nametbl_remove_publ(net, ntohl(i->type),
+						ntohl(i->lower),
 						node, ntohl(i->ref),
 						ntohl(i->key));
 		if (publ) {
-			tipc_nodesub_unsubscribe(&publ->subscr);
-			kfree(publ);
+			tipc_publ_unsubscribe(net, publ, node);
+			kfree_rcu(publ, rcu);
 			return true;
 		}
 	} else {
@@ -337,7 +359,7 @@ static void tipc_named_add_backlog(struct distr_item *i, u32 type, u32 node)
  * tipc_named_process_backlog - try to process any pending name table updates
  * from the network.
  */
-void tipc_named_process_backlog(void)
+void tipc_named_process_backlog(struct net *net)
 {
 	struct distr_queue_item *e, *tmp;
 	char addr[16];
@@ -345,7 +367,7 @@ void tipc_named_process_backlog(void)
 
 	list_for_each_entry_safe(e, tmp, &tipc_dist_queue, next) {
 		if (time_after(e->expires, now)) {
-			if (!tipc_update_nametbl(&e->i, e->node, e->dtype))
+			if (!tipc_update_nametbl(net, &e->i, e->node, e->dtype))
 				continue;
 		} else {
 			tipc_addr_string_fill(addr, e->node);
@@ -361,24 +383,34 @@ void tipc_named_process_backlog(void)
 }
 
 /**
- * tipc_named_rcv - process name table update message sent by another node
+ * tipc_named_rcv - process name table update messages sent by another node
  */
-void tipc_named_rcv(struct sk_buff *buf)
+void tipc_named_rcv(struct net *net, struct sk_buff_head *inputq)
 {
-	struct tipc_msg *msg = buf_msg(buf);
-	struct distr_item *item = (struct distr_item *)msg_data(msg);
-	u32 count = msg_data_sz(msg) / ITEM_SIZE;
-	u32 node = msg_orignode(msg);
-
-	write_lock_bh(&tipc_nametbl_lock);
-	while (count--) {
-		if (!tipc_update_nametbl(item, node, msg_type(msg)))
-			tipc_named_add_backlog(item, msg_type(msg), node);
-		item++;
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	struct tipc_msg *msg;
+	struct distr_item *item;
+	uint count;
+	u32 node;
+	struct sk_buff *skb;
+	int mtype;
+
+	spin_lock_bh(&tn->nametbl_lock);
+	for (skb = skb_dequeue(inputq); skb; skb = skb_dequeue(inputq)) {
+		msg = buf_msg(skb);
+		mtype = msg_type(msg);
+		item = (struct distr_item *)msg_data(msg);
+		count = msg_data_sz(msg) / ITEM_SIZE;
+		node = msg_orignode(msg);
+		while (count--) {
+			if (!tipc_update_nametbl(net, item, node, mtype))
+				tipc_named_add_backlog(item, mtype, node);
+			item++;
+		}
+		kfree_skb(skb);
+		tipc_named_process_backlog(net);
 	}
-	tipc_named_process_backlog();
-	write_unlock_bh(&tipc_nametbl_lock);
-	kfree_skb(buf);
+	spin_unlock_bh(&tn->nametbl_lock);
 }
 
 /**
@@ -388,16 +420,18 @@ void tipc_named_rcv(struct sk_buff *buf)
  * All name table entries published by this node are updated to reflect
  * the node's new network address.
  */
-void tipc_named_reinit(void)
+void tipc_named_reinit(struct net *net)
 {
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	struct publication *publ;
 	int scope;
 
-	write_lock_bh(&tipc_nametbl_lock);
+	spin_lock_bh(&tn->nametbl_lock);
 
 	for (scope = TIPC_ZONE_SCOPE; scope <= TIPC_NODE_SCOPE; scope++)
-		list_for_each_entry(publ, &publ_lists[scope]->list, local_list)
-			publ->node = tipc_own_addr;
+		list_for_each_entry_rcu(publ, &tn->nametbl->publ_list[scope],
+					local_list)
+			publ->node = tn->own_addr;
 
-	write_unlock_bh(&tipc_nametbl_lock);
+	spin_unlock_bh(&tn->nametbl_lock);
 }
diff --git a/net/tipc/name_distr.h b/net/tipc/name_distr.h
index b9e75feb3434..dd2d9fd80da2 100644
--- a/net/tipc/name_distr.h
+++ b/net/tipc/name_distr.h
@@ -67,12 +67,13 @@ struct distr_item {
 	__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 dnode);
-void tipc_named_rcv(struct sk_buff *buf);
-void tipc_named_reinit(void);
-void tipc_named_process_backlog(void);
+struct sk_buff *tipc_named_publish(struct net *net, struct publication *publ);
+struct sk_buff *tipc_named_withdraw(struct net *net, struct publication *publ);
+void named_cluster_distribute(struct net *net, struct sk_buff *buf);
+void tipc_named_node_up(struct net *net, u32 dnode);
+void tipc_named_rcv(struct net *net, struct sk_buff_head *msg_queue);
+void tipc_named_reinit(struct net *net);
+void tipc_named_process_backlog(struct net *net);
+void tipc_publ_notify(struct net *net, struct list_head *nsub_list, u32 addr);
 
 #endif
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index 3a6a0a7c0759..ab0ac62a1287 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -1,8 +1,8 @@
 /*
  * net/tipc/name_table.c: TIPC name table code
  *
- * Copyright (c) 2000-2006, Ericsson AB
- * Copyright (c) 2004-2008, 2010-2011, Wind River Systems
+ * Copyright (c) 2000-2006, 2014-2015, Ericsson AB
+ * Copyright (c) 2004-2008, 2010-2014, Wind River Systems
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -34,14 +34,24 @@
  * POSSIBILITY OF SUCH DAMAGE.
  */
 
+#include <net/sock.h>
 #include "core.h"
-#include "config.h"
+#include "netlink.h"
 #include "name_table.h"
 #include "name_distr.h"
 #include "subscr.h"
+#include "bcast.h"
+#include "addr.h"
+#include <net/genetlink.h>
 
 #define TIPC_NAMETBL_SIZE 1024		/* must be a power of 2 */
 
+static const struct nla_policy
+tipc_nl_name_table_policy[TIPC_NLA_NAME_TABLE_MAX + 1] = {
+	[TIPC_NLA_NAME_TABLE_UNSPEC]	= { .type = NLA_UNSPEC },
+	[TIPC_NLA_NAME_TABLE_PUBL]	= { .type = NLA_NESTED }
+};
+
 /**
  * struct name_info - name sequence publication info
  * @node_list: circular list of publications made by own node
@@ -86,6 +96,7 @@ struct sub_seq {
  * @ns_list: links to adjacent name sequences in hash chain
  * @subscriptions: list of subscriptions for this 'type'
  * @lock: spinlock controlling access to publication lists of all sub-sequences
+ * @rcu: RCU callback head used for deferred freeing
  */
 struct name_seq {
 	u32 type;
@@ -95,22 +106,9 @@ struct name_seq {
 	struct hlist_node ns_list;
 	struct list_head subscriptions;
 	spinlock_t lock;
+	struct rcu_head rcu;
 };
 
-/**
- * struct name_table - table containing all existing port name publications
- * @types: pointer to fixed-sized array of name sequence lists,
- *         accessed via hashing on 'type'; name sequence lists are *not* sorted
- * @local_publ_count: number of publications issued by this node
- */
-struct name_table {
-	struct hlist_head *types;
-	u32 local_publ_count;
-};
-
-static struct name_table table;
-DEFINE_RWLOCK(tipc_nametbl_lock);
-
 static int hash(int x)
 {
 	return x & (TIPC_NAMETBL_SIZE - 1);
@@ -136,9 +134,7 @@ static struct publication *publ_create(u32 type, u32 lower, u32 upper,
 	publ->node = node;
 	publ->ref = port_ref;
 	publ->key = key;
-	INIT_LIST_HEAD(&publ->local_list);
 	INIT_LIST_HEAD(&publ->pport_list);
-	INIT_LIST_HEAD(&publ->subscr.nodesub_list);
 	return publ;
 }
 
@@ -173,22 +169,10 @@ static struct name_seq *tipc_nameseq_create(u32 type, struct hlist_head *seq_hea
 	nseq->alloc = 1;
 	INIT_HLIST_NODE(&nseq->ns_list);
 	INIT_LIST_HEAD(&nseq->subscriptions);
-	hlist_add_head(&nseq->ns_list, seq_head);
+	hlist_add_head_rcu(&nseq->ns_list, seq_head);
 	return nseq;
 }
 
-/*
- * nameseq_delete_empty - deletes a name sequence structure if now unused
- */
-static void nameseq_delete_empty(struct name_seq *seq)
-{
-	if (!seq->first_free && list_empty(&seq->subscriptions)) {
-		hlist_del_init(&seq->ns_list);
-		kfree(seq->sseqs);
-		kfree(seq);
-	}
-}
-
 /**
  * nameseq_find_subseq - find sub-sequence (if any) matching a name instance
  *
@@ -245,9 +229,11 @@ static u32 nameseq_locate_subseq(struct name_seq *nseq, u32 instance)
 /**
  * tipc_nameseq_insert_publ
  */
-static struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq,
-						    u32 type, u32 lower, u32 upper,
-						    u32 scope, u32 node, u32 port, u32 key)
+static struct publication *tipc_nameseq_insert_publ(struct net *net,
+						    struct name_seq *nseq,
+						    u32 type, u32 lower,
+						    u32 upper, u32 scope,
+						    u32 node, u32 port, u32 key)
 {
 	struct tipc_subscription *s;
 	struct tipc_subscription *st;
@@ -332,12 +318,12 @@ static struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq,
 	list_add(&publ->zone_list, &info->zone_list);
 	info->zone_list_size++;
 
-	if (in_own_cluster(node)) {
+	if (in_own_cluster(net, node)) {
 		list_add(&publ->cluster_list, &info->cluster_list);
 		info->cluster_list_size++;
 	}
 
-	if (in_own_node(node)) {
+	if (in_own_node(net, node)) {
 		list_add(&publ->node_list, &info->node_list);
 		info->node_list_size++;
 	}
@@ -366,8 +352,10 @@ static struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq,
  * A failed withdraw request simply returns a failure indication and lets the
  * caller issue any error or warning messages associated with such a problem.
  */
-static struct publication *tipc_nameseq_remove_publ(struct name_seq *nseq, u32 inst,
-						    u32 node, u32 ref, u32 key)
+static struct publication *tipc_nameseq_remove_publ(struct net *net,
+						    struct name_seq *nseq,
+						    u32 inst, u32 node,
+						    u32 ref, u32 key)
 {
 	struct publication *publ;
 	struct sub_seq *sseq = nameseq_find_subseq(nseq, inst);
@@ -395,13 +383,13 @@ found:
 	info->zone_list_size--;
 
 	/* Remove publication from cluster scope list, if present */
-	if (in_own_cluster(node)) {
+	if (in_own_cluster(net, node)) {
 		list_del(&publ->cluster_list);
 		info->cluster_list_size--;
 	}
 
 	/* Remove publication from node scope list, if present */
-	if (in_own_node(node)) {
+	if (in_own_node(net, node)) {
 		list_del(&publ->node_list);
 		info->node_list_size--;
 	}
@@ -464,13 +452,14 @@ static void tipc_nameseq_subscribe(struct name_seq *nseq,
 	}
 }
 
-static struct name_seq *nametbl_find_seq(u32 type)
+static struct name_seq *nametbl_find_seq(struct net *net, u32 type)
 {
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	struct hlist_head *seq_head;
 	struct name_seq *ns;
 
-	seq_head = &table.types[hash(type)];
-	hlist_for_each_entry(ns, seq_head, ns_list) {
+	seq_head = &tn->nametbl->seq_hlist[hash(type)];
+	hlist_for_each_entry_rcu(ns, seq_head, ns_list) {
 		if (ns->type == type)
 			return ns;
 	}
@@ -478,10 +467,14 @@ static struct name_seq *nametbl_find_seq(u32 type)
 	return NULL;
 };
 
-struct publication *tipc_nametbl_insert_publ(u32 type, u32 lower, u32 upper,
-					     u32 scope, u32 node, u32 port, u32 key)
+struct publication *tipc_nametbl_insert_publ(struct net *net, u32 type,
+					     u32 lower, u32 upper, u32 scope,
+					     u32 node, u32 port, u32 key)
 {
-	struct name_seq *seq = nametbl_find_seq(type);
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	struct publication *publ;
+	struct name_seq *seq = nametbl_find_seq(net, type);
+	int index = hash(type);
 
 	if ((scope < TIPC_ZONE_SCOPE) || (scope > TIPC_NODE_SCOPE) ||
 	    (lower > upper)) {
@@ -491,25 +484,37 @@ struct publication *tipc_nametbl_insert_publ(u32 type, u32 lower, u32 upper,
 	}
 
 	if (!seq)
-		seq = tipc_nameseq_create(type, &table.types[hash(type)]);
+		seq = tipc_nameseq_create(type, &tn->nametbl->seq_hlist[index]);
 	if (!seq)
 		return NULL;
 
-	return tipc_nameseq_insert_publ(seq, type, lower, upper,
+	spin_lock_bh(&seq->lock);
+	publ = tipc_nameseq_insert_publ(net, seq, type, lower, upper,
 					scope, node, port, key);
+	spin_unlock_bh(&seq->lock);
+	return publ;
 }
 
-struct publication *tipc_nametbl_remove_publ(u32 type, u32 lower,
-					     u32 node, u32 ref, u32 key)
+struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type,
+					     u32 lower, u32 node, u32 ref,
+					     u32 key)
 {
 	struct publication *publ;
-	struct name_seq *seq = nametbl_find_seq(type);
+	struct name_seq *seq = nametbl_find_seq(net, type);
 
 	if (!seq)
 		return NULL;
 
-	publ = tipc_nameseq_remove_publ(seq, lower, node, ref, key);
-	nameseq_delete_empty(seq);
+	spin_lock_bh(&seq->lock);
+	publ = tipc_nameseq_remove_publ(net, seq, lower, node, ref, key);
+	if (!seq->first_free && list_empty(&seq->subscriptions)) {
+		hlist_del_init_rcu(&seq->ns_list);
+		kfree(seq->sseqs);
+		spin_unlock_bh(&seq->lock);
+		kfree_rcu(seq, rcu);
+		return publ;
+	}
+	spin_unlock_bh(&seq->lock);
 	return publ;
 }
 
@@ -526,8 +531,10 @@ struct publication *tipc_nametbl_remove_publ(u32 type, u32 lower,
  * - if name translation is attempted and fails, sets 'destnode' to 0
  *   and returns 0
  */
-u32 tipc_nametbl_translate(u32 type, u32 instance, u32 *destnode)
+u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance,
+			   u32 *destnode)
 {
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	struct sub_seq *sseq;
 	struct name_info *info;
 	struct publication *publ;
@@ -535,17 +542,17 @@ u32 tipc_nametbl_translate(u32 type, u32 instance, u32 *destnode)
 	u32 ref = 0;
 	u32 node = 0;
 
-	if (!tipc_in_scope(*destnode, tipc_own_addr))
+	if (!tipc_in_scope(*destnode, tn->own_addr))
 		return 0;
 
-	read_lock_bh(&tipc_nametbl_lock);
-	seq = nametbl_find_seq(type);
+	rcu_read_lock();
+	seq = nametbl_find_seq(net, type);
 	if (unlikely(!seq))
 		goto not_found;
+	spin_lock_bh(&seq->lock);
 	sseq = nameseq_find_subseq(seq, instance);
 	if (unlikely(!sseq))
-		goto not_found;
-	spin_lock_bh(&seq->lock);
+		goto no_match;
 	info = sseq->info;
 
 	/* Closest-First Algorithm */
@@ -572,13 +579,13 @@ u32 tipc_nametbl_translate(u32 type, u32 instance, u32 *destnode)
 	}
 
 	/* Round-Robin Algorithm */
-	else if (*destnode == tipc_own_addr) {
+	else if (*destnode == tn->own_addr) {
 		if (list_empty(&info->node_list))
 			goto no_match;
 		publ = list_first_entry(&info->node_list, struct publication,
 					node_list);
 		list_move_tail(&publ->node_list, &info->node_list);
-	} else if (in_own_cluster_exact(*destnode)) {
+	} else if (in_own_cluster_exact(net, *destnode)) {
 		if (list_empty(&info->cluster_list))
 			goto no_match;
 		publ = list_first_entry(&info->cluster_list, struct publication,
@@ -595,7 +602,7 @@ u32 tipc_nametbl_translate(u32 type, u32 instance, u32 *destnode)
 no_match:
 	spin_unlock_bh(&seq->lock);
 not_found:
-	read_unlock_bh(&tipc_nametbl_lock);
+	rcu_read_unlock();
 	*destnode = node;
 	return ref;
 }
@@ -612,8 +619,8 @@ not_found:
  *
  * Returns non-zero if any off-node ports overlap
  */
-int tipc_nametbl_mc_translate(u32 type, u32 lower, u32 upper, u32 limit,
-			      struct tipc_port_list *dports)
+int tipc_nametbl_mc_translate(struct net *net, u32 type, u32 lower, u32 upper,
+			      u32 limit, struct tipc_plist *dports)
 {
 	struct name_seq *seq;
 	struct sub_seq *sseq;
@@ -621,13 +628,12 @@ int tipc_nametbl_mc_translate(u32 type, u32 lower, u32 upper, u32 limit,
 	struct name_info *info;
 	int res = 0;
 
-	read_lock_bh(&tipc_nametbl_lock);
-	seq = nametbl_find_seq(type);
+	rcu_read_lock();
+	seq = nametbl_find_seq(net, type);
 	if (!seq)
 		goto exit;
 
 	spin_lock_bh(&seq->lock);
-
 	sseq = seq->sseqs + nameseq_locate_subseq(seq, lower);
 	sseq_stop = seq->sseqs + seq->first_free;
 	for (; sseq != sseq_stop; sseq++) {
@@ -639,77 +645,83 @@ int tipc_nametbl_mc_translate(u32 type, u32 lower, u32 upper, u32 limit,
 		info = sseq->info;
 		list_for_each_entry(publ, &info->node_list, node_list) {
 			if (publ->scope <= limit)
-				tipc_port_list_add(dports, publ->ref);
+				tipc_plist_push(dports, publ->ref);
 		}
 
 		if (info->cluster_list_size != info->node_list_size)
 			res = 1;
 	}
-
 	spin_unlock_bh(&seq->lock);
 exit:
-	read_unlock_bh(&tipc_nametbl_lock);
+	rcu_read_unlock();
 	return res;
 }
 
 /*
  * tipc_nametbl_publish - add name publication to network name tables
  */
-struct publication *tipc_nametbl_publish(u32 type, u32 lower, u32 upper,
-					 u32 scope, u32 port_ref, u32 key)
+struct publication *tipc_nametbl_publish(struct net *net, u32 type, u32 lower,
+					 u32 upper, u32 scope, u32 port_ref,
+					 u32 key)
 {
 	struct publication *publ;
 	struct sk_buff *buf = NULL;
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 
-	if (table.local_publ_count >= TIPC_MAX_PUBLICATIONS) {
+	spin_lock_bh(&tn->nametbl_lock);
+	if (tn->nametbl->local_publ_count >= TIPC_MAX_PUBLICATIONS) {
 		pr_warn("Publication failed, local publication limit reached (%u)\n",
 			TIPC_MAX_PUBLICATIONS);
+		spin_unlock_bh(&tn->nametbl_lock);
 		return NULL;
 	}
 
-	write_lock_bh(&tipc_nametbl_lock);
-	publ = tipc_nametbl_insert_publ(type, lower, upper, scope,
-				   tipc_own_addr, port_ref, key);
+	publ = tipc_nametbl_insert_publ(net, type, lower, upper, scope,
+					tn->own_addr, port_ref, key);
 	if (likely(publ)) {
-		table.local_publ_count++;
-		buf = tipc_named_publish(publ);
+		tn->nametbl->local_publ_count++;
+		buf = tipc_named_publish(net, publ);
 		/* Any pending external events? */
-		tipc_named_process_backlog();
+		tipc_named_process_backlog(net);
 	}
-	write_unlock_bh(&tipc_nametbl_lock);
+	spin_unlock_bh(&tn->nametbl_lock);
 
 	if (buf)
-		named_cluster_distribute(buf);
+		named_cluster_distribute(net, buf);
 	return publ;
 }
 
 /**
  * tipc_nametbl_withdraw - withdraw name publication from network name tables
  */
-int tipc_nametbl_withdraw(u32 type, u32 lower, u32 ref, u32 key)
+int tipc_nametbl_withdraw(struct net *net, u32 type, u32 lower, u32 ref,
+			  u32 key)
 {
 	struct publication *publ;
-	struct sk_buff *buf;
+	struct sk_buff *skb = NULL;
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 
-	write_lock_bh(&tipc_nametbl_lock);
-	publ = tipc_nametbl_remove_publ(type, lower, tipc_own_addr, ref, key);
+	spin_lock_bh(&tn->nametbl_lock);
+	publ = tipc_nametbl_remove_publ(net, type, lower, tn->own_addr,
+					ref, key);
 	if (likely(publ)) {
-		table.local_publ_count--;
-		buf = tipc_named_withdraw(publ);
+		tn->nametbl->local_publ_count--;
+		skb = tipc_named_withdraw(net, publ);
 		/* Any pending external events? */
-		tipc_named_process_backlog();
-		write_unlock_bh(&tipc_nametbl_lock);
+		tipc_named_process_backlog(net);
 		list_del_init(&publ->pport_list);
-		kfree(publ);
+		kfree_rcu(publ, rcu);
+	} else {
+		pr_err("Unable to remove local publication\n"
+		       "(type=%u, lower=%u, ref=%u, key=%u)\n",
+		       type, lower, ref, key);
+	}
+	spin_unlock_bh(&tn->nametbl_lock);
 
-		if (buf)
-			named_cluster_distribute(buf);
+	if (skb) {
+		named_cluster_distribute(net, skb);
 		return 1;
 	}
-	write_unlock_bh(&tipc_nametbl_lock);
-	pr_err("Unable to remove local publication\n"
-	       "(type=%u, lower=%u, ref=%u, key=%u)\n",
-	       type, lower, ref, key);
 	return 0;
 }
 
@@ -718,13 +730,15 @@ int tipc_nametbl_withdraw(u32 type, u32 lower, u32 ref, u32 key)
  */
 void tipc_nametbl_subscribe(struct tipc_subscription *s)
 {
+	struct tipc_net *tn = net_generic(s->net, tipc_net_id);
 	u32 type = s->seq.type;
+	int index = hash(type);
 	struct name_seq *seq;
 
-	write_lock_bh(&tipc_nametbl_lock);
-	seq = nametbl_find_seq(type);
+	spin_lock_bh(&tn->nametbl_lock);
+	seq = nametbl_find_seq(s->net, type);
 	if (!seq)
-		seq = tipc_nameseq_create(type, &table.types[hash(type)]);
+		seq = tipc_nameseq_create(type, &tn->nametbl->seq_hlist[index]);
 	if (seq) {
 		spin_lock_bh(&seq->lock);
 		tipc_nameseq_subscribe(seq, s);
@@ -733,7 +747,7 @@ void tipc_nametbl_subscribe(struct tipc_subscription *s)
 		pr_warn("Failed to create subscription for {%u,%u,%u}\n",
 			s->seq.type, s->seq.lower, s->seq.upper);
 	}
-	write_unlock_bh(&tipc_nametbl_lock);
+	spin_unlock_bh(&tn->nametbl_lock);
 }
 
 /**
@@ -741,257 +755,316 @@ void tipc_nametbl_subscribe(struct tipc_subscription *s)
  */
 void tipc_nametbl_unsubscribe(struct tipc_subscription *s)
 {
+	struct tipc_net *tn = net_generic(s->net, tipc_net_id);
 	struct name_seq *seq;
 
-	write_lock_bh(&tipc_nametbl_lock);
-	seq = nametbl_find_seq(s->seq.type);
+	spin_lock_bh(&tn->nametbl_lock);
+	seq = nametbl_find_seq(s->net, s->seq.type);
 	if (seq != NULL) {
 		spin_lock_bh(&seq->lock);
 		list_del_init(&s->nameseq_list);
-		spin_unlock_bh(&seq->lock);
-		nameseq_delete_empty(seq);
+		if (!seq->first_free && list_empty(&seq->subscriptions)) {
+			hlist_del_init_rcu(&seq->ns_list);
+			kfree(seq->sseqs);
+			spin_unlock_bh(&seq->lock);
+			kfree_rcu(seq, rcu);
+		} else {
+			spin_unlock_bh(&seq->lock);
+		}
 	}
-	write_unlock_bh(&tipc_nametbl_lock);
+	spin_unlock_bh(&tn->nametbl_lock);
 }
 
+int tipc_nametbl_init(struct net *net)
+{
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	struct name_table *tipc_nametbl;
+	int i;
+
+	tipc_nametbl = kzalloc(sizeof(*tipc_nametbl), GFP_ATOMIC);
+	if (!tipc_nametbl)
+		return -ENOMEM;
+
+	for (i = 0; i < TIPC_NAMETBL_SIZE; i++)
+		INIT_HLIST_HEAD(&tipc_nametbl->seq_hlist[i]);
+
+	INIT_LIST_HEAD(&tipc_nametbl->publ_list[TIPC_ZONE_SCOPE]);
+	INIT_LIST_HEAD(&tipc_nametbl->publ_list[TIPC_CLUSTER_SCOPE]);
+	INIT_LIST_HEAD(&tipc_nametbl->publ_list[TIPC_NODE_SCOPE]);
+	tn->nametbl = tipc_nametbl;
+	spin_lock_init(&tn->nametbl_lock);
+	return 0;
+}
 
 /**
- * subseq_list - print specified sub-sequence contents into the given buffer
+ * tipc_purge_publications - remove all publications for a given type
+ *
+ * tipc_nametbl_lock must be held when calling this function
  */
-static int subseq_list(struct sub_seq *sseq, char *buf, int len, u32 depth,
-		       u32 index)
+static void tipc_purge_publications(struct net *net, struct name_seq *seq)
 {
-	char portIdStr[27];
-	const char *scope_str[] = {"", " zone", " cluster", " node"};
-	struct publication *publ;
+	struct publication *publ, *safe;
+	struct sub_seq *sseq;
 	struct name_info *info;
-	int ret;
-
-	ret = tipc_snprintf(buf, len, "%-10u %-10u ", sseq->lower, sseq->upper);
 
-	if (depth == 2) {
-		ret += tipc_snprintf(buf - ret, len + ret, "\n");
-		return ret;
+	spin_lock_bh(&seq->lock);
+	sseq = seq->sseqs;
+	info = sseq->info;
+	list_for_each_entry_safe(publ, safe, &info->zone_list, zone_list) {
+		tipc_nameseq_remove_publ(net, seq, publ->lower, publ->node,
+					 publ->ref, publ->key);
+		kfree_rcu(publ, rcu);
 	}
+	hlist_del_init_rcu(&seq->ns_list);
+	kfree(seq->sseqs);
+	spin_unlock_bh(&seq->lock);
 
-	info = sseq->info;
+	kfree_rcu(seq, rcu);
+}
 
-	list_for_each_entry(publ, &info->zone_list, zone_list) {
-		sprintf(portIdStr, "<%u.%u.%u:%u>",
-			 tipc_zone(publ->node), tipc_cluster(publ->node),
-			 tipc_node(publ->node), publ->ref);
-		ret += tipc_snprintf(buf + ret, len - ret, "%-26s ", portIdStr);
-		if (depth > 3) {
-			ret += tipc_snprintf(buf + ret, len - ret, "%-10u %s",
-					     publ->key, scope_str[publ->scope]);
+void tipc_nametbl_stop(struct net *net)
+{
+	u32 i;
+	struct name_seq *seq;
+	struct hlist_head *seq_head;
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	struct name_table *tipc_nametbl = tn->nametbl;
+
+	/* Verify name table is empty and purge any lingering
+	 * publications, then release the name table
+	 */
+	spin_lock_bh(&tn->nametbl_lock);
+	for (i = 0; i < TIPC_NAMETBL_SIZE; i++) {
+		if (hlist_empty(&tipc_nametbl->seq_hlist[i]))
+			continue;
+		seq_head = &tipc_nametbl->seq_hlist[i];
+		hlist_for_each_entry_rcu(seq, seq_head, ns_list) {
+			tipc_purge_publications(net, seq);
 		}
-		if (!list_is_last(&publ->zone_list, &info->zone_list))
-			ret += tipc_snprintf(buf + ret, len - ret,
-					     "\n%33s", " ");
 	}
+	spin_unlock_bh(&tn->nametbl_lock);
+
+	synchronize_net();
+	kfree(tipc_nametbl);
 
-	ret += tipc_snprintf(buf + ret, len - ret, "\n");
-	return ret;
 }
 
-/**
- * nameseq_list - print specified name sequence contents into the given buffer
- */
-static int nameseq_list(struct name_seq *seq, char *buf, int len, u32 depth,
-			u32 type, u32 lowbound, u32 upbound, u32 index)
+static int __tipc_nl_add_nametable_publ(struct tipc_nl_msg *msg,
+					struct name_seq *seq,
+					struct sub_seq *sseq, u32 *last_publ)
 {
-	struct sub_seq *sseq;
-	char typearea[11];
-	int ret = 0;
+	void *hdr;
+	struct nlattr *attrs;
+	struct nlattr *publ;
+	struct publication *p;
+
+	if (*last_publ) {
+		list_for_each_entry(p, &sseq->info->zone_list, zone_list)
+			if (p->key == *last_publ)
+				break;
+		if (p->key != *last_publ)
+			return -EPIPE;
+	} else {
+		p = list_first_entry(&sseq->info->zone_list, struct publication,
+				     zone_list);
+	}
 
-	if (seq->first_free == 0)
-		return 0;
+	list_for_each_entry_from(p, &sseq->info->zone_list, zone_list) {
+		*last_publ = p->key;
+
+		hdr = genlmsg_put(msg->skb, msg->portid, msg->seq,
+				  &tipc_genl_family, NLM_F_MULTI,
+				  TIPC_NL_NAME_TABLE_GET);
+		if (!hdr)
+			return -EMSGSIZE;
+
+		attrs = nla_nest_start(msg->skb, TIPC_NLA_NAME_TABLE);
+		if (!attrs)
+			goto msg_full;
+
+		publ = nla_nest_start(msg->skb, TIPC_NLA_NAME_TABLE_PUBL);
+		if (!publ)
+			goto attr_msg_full;
+
+		if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_TYPE, seq->type))
+			goto publ_msg_full;
+		if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_LOWER, sseq->lower))
+			goto publ_msg_full;
+		if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_UPPER, sseq->upper))
+			goto publ_msg_full;
+		if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_SCOPE, p->scope))
+			goto publ_msg_full;
+		if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_NODE, p->node))
+			goto publ_msg_full;
+		if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_REF, p->ref))
+			goto publ_msg_full;
+		if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_KEY, p->key))
+			goto publ_msg_full;
+
+		nla_nest_end(msg->skb, publ);
+		nla_nest_end(msg->skb, attrs);
+		genlmsg_end(msg->skb, hdr);
+	}
+	*last_publ = 0;
 
-	sprintf(typearea, "%-10u", seq->type);
+	return 0;
 
-	if (depth == 1) {
-		ret += tipc_snprintf(buf, len, "%s\n", typearea);
-		return ret;
-	}
+publ_msg_full:
+	nla_nest_cancel(msg->skb, publ);
+attr_msg_full:
+	nla_nest_cancel(msg->skb, attrs);
+msg_full:
+	genlmsg_cancel(msg->skb, hdr);
 
-	for (sseq = seq->sseqs; sseq != &seq->sseqs[seq->first_free]; sseq++) {
-		if ((lowbound <= sseq->upper) && (upbound >= sseq->lower)) {
-			ret += tipc_snprintf(buf + ret, len - ret, "%s ",
-					    typearea);
-			spin_lock_bh(&seq->lock);
-			ret += subseq_list(sseq, buf + ret, len - ret,
-					  depth, index);
-			spin_unlock_bh(&seq->lock);
-			sprintf(typearea, "%10s", " ");
-		}
-	}
-	return ret;
+	return -EMSGSIZE;
 }
 
-/**
- * nametbl_header - print name table header into the given buffer
- */
-static int nametbl_header(char *buf, int len, u32 depth)
+static int __tipc_nl_subseq_list(struct tipc_nl_msg *msg, struct name_seq *seq,
+				 u32 *last_lower, u32 *last_publ)
 {
-	const char *header[] = {
-		"Type       ",
-		"Lower      Upper      ",
-		"Port Identity              ",
-		"Publication Scope"
-	};
+	struct sub_seq *sseq;
+	struct sub_seq *sseq_start;
+	int err;
 
-	int i;
-	int ret = 0;
-
-	if (depth > 4)
-		depth = 4;
-	for (i = 0; i < depth; i++)
-		ret += tipc_snprintf(buf + ret, len - ret, header[i]);
-	ret += tipc_snprintf(buf + ret, len - ret, "\n");
-	return ret;
+	if (*last_lower) {
+		sseq_start = nameseq_find_subseq(seq, *last_lower);
+		if (!sseq_start)
+			return -EPIPE;
+	} else {
+		sseq_start = seq->sseqs;
+	}
+
+	for (sseq = sseq_start; sseq != &seq->sseqs[seq->first_free]; sseq++) {
+		err = __tipc_nl_add_nametable_publ(msg, seq, sseq, last_publ);
+		if (err) {
+			*last_lower = sseq->lower;
+			return err;
+		}
+	}
+	*last_lower = 0;
+
+	return 0;
 }
 
-/**
- * nametbl_list - print specified name table contents into the given buffer
- */
-static int nametbl_list(char *buf, int len, u32 depth_info,
-			u32 type, u32 lowbound, u32 upbound)
+static int tipc_nl_seq_list(struct net *net, struct tipc_nl_msg *msg,
+			    u32 *last_type, u32 *last_lower, u32 *last_publ)
 {
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	struct hlist_head *seq_head;
-	struct name_seq *seq;
-	int all_types;
-	int ret = 0;
-	u32 depth;
-	u32 i;
+	struct name_seq *seq = NULL;
+	int err;
+	int i;
 
-	all_types = (depth_info & TIPC_NTQ_ALLTYPES);
-	depth = (depth_info & ~TIPC_NTQ_ALLTYPES);
+	if (*last_type)
+		i = hash(*last_type);
+	else
+		i = 0;
 
-	if (depth == 0)
-		return 0;
+	for (; i < TIPC_NAMETBL_SIZE; i++) {
+		seq_head = &tn->nametbl->seq_hlist[i];
 
-	if (all_types) {
-		/* display all entries in name table to specified depth */
-		ret += nametbl_header(buf, len, depth);
-		lowbound = 0;
-		upbound = ~0;
-		for (i = 0; i < TIPC_NAMETBL_SIZE; i++) {
-			seq_head = &table.types[i];
-			hlist_for_each_entry(seq, seq_head, ns_list) {
-				ret += nameseq_list(seq, buf + ret, len - ret,
-						   depth, seq->type,
-						   lowbound, upbound, i);
-			}
-		}
-	} else {
-		/* display only the sequence that matches the specified type */
-		if (upbound < lowbound) {
-			ret += tipc_snprintf(buf + ret, len - ret,
-					"invalid name sequence specified\n");
-			return ret;
-		}
-		ret += nametbl_header(buf + ret, len - ret, depth);
-		i = hash(type);
-		seq_head = &table.types[i];
-		hlist_for_each_entry(seq, seq_head, ns_list) {
-			if (seq->type == type) {
-				ret += nameseq_list(seq, buf + ret, len - ret,
-						   depth, type,
-						   lowbound, upbound, i);
+		if (*last_type) {
+			seq = nametbl_find_seq(net, *last_type);
+			if (!seq)
+				return -EPIPE;
+		} else {
+			hlist_for_each_entry_rcu(seq, seq_head, ns_list)
 				break;
+			if (!seq)
+				continue;
+		}
+
+		hlist_for_each_entry_from_rcu(seq, ns_list) {
+			spin_lock_bh(&seq->lock);
+			err = __tipc_nl_subseq_list(msg, seq, last_lower,
+						    last_publ);
+
+			if (err) {
+				*last_type = seq->type;
+				spin_unlock_bh(&seq->lock);
+				return err;
 			}
+			spin_unlock_bh(&seq->lock);
 		}
+		*last_type = 0;
 	}
-	return ret;
+	return 0;
 }
 
-struct sk_buff *tipc_nametbl_get(const void *req_tlv_area, int req_tlv_space)
+int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb)
 {
-	struct sk_buff *buf;
-	struct tipc_name_table_query *argv;
-	struct tlv_desc *rep_tlv;
-	char *pb;
-	int pb_len;
-	int str_len;
-
-	if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_NAME_TBL_QUERY))
-		return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR);
-
-	buf = tipc_cfg_reply_alloc(TLV_SPACE(ULTRA_STRING_MAX_LEN));
-	if (!buf)
-		return NULL;
+	int err;
+	int done = cb->args[3];
+	u32 last_type = cb->args[0];
+	u32 last_lower = cb->args[1];
+	u32 last_publ = cb->args[2];
+	struct net *net = sock_net(skb->sk);
+	struct tipc_nl_msg msg;
+
+	if (done)
+		return 0;
 
-	rep_tlv = (struct tlv_desc *)buf->data;
-	pb = TLV_DATA(rep_tlv);
-	pb_len = ULTRA_STRING_MAX_LEN;
-	argv = (struct tipc_name_table_query *)TLV_DATA(req_tlv_area);
-	read_lock_bh(&tipc_nametbl_lock);
-	str_len = nametbl_list(pb, pb_len, ntohl(argv->depth),
-			       ntohl(argv->type),
-			       ntohl(argv->lowbound), ntohl(argv->upbound));
-	read_unlock_bh(&tipc_nametbl_lock);
-	str_len += 1;	/* for "\0" */
-	skb_put(buf, TLV_SPACE(str_len));
-	TLV_SET(rep_tlv, TIPC_TLV_ULTRA_STRING, NULL, str_len);
-
-	return buf;
-}
+	msg.skb = skb;
+	msg.portid = NETLINK_CB(cb->skb).portid;
+	msg.seq = cb->nlh->nlmsg_seq;
+
+	rcu_read_lock();
+	err = tipc_nl_seq_list(net, &msg, &last_type, &last_lower, &last_publ);
+	if (!err) {
+		done = 1;
+	} else if (err != -EMSGSIZE) {
+		/* We never set seq or call nl_dump_check_consistent() this
+		 * means that setting prev_seq here will cause the consistence
+		 * check to fail in the netlink callback handler. Resulting in
+		 * the NLMSG_DONE message having the NLM_F_DUMP_INTR flag set if
+		 * we got an error.
+		 */
+		cb->prev_seq = 1;
+	}
+	rcu_read_unlock();
 
-int tipc_nametbl_init(void)
-{
-	table.types = kcalloc(TIPC_NAMETBL_SIZE, sizeof(struct hlist_head),
-			      GFP_ATOMIC);
-	if (!table.types)
-		return -ENOMEM;
+	cb->args[0] = last_type;
+	cb->args[1] = last_lower;
+	cb->args[2] = last_publ;
+	cb->args[3] = done;
 
-	table.local_publ_count = 0;
-	return 0;
+	return skb->len;
 }
 
-/**
- * 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)
+void tipc_plist_push(struct tipc_plist *pl, u32 port)
 {
-	struct publication *publ, *safe;
-	struct sub_seq *sseq;
-	struct name_info *info;
+	struct tipc_plist *nl;
 
-	if (!seq->sseqs) {
-		nameseq_delete_empty(seq);
+	if (likely(!pl->port)) {
+		pl->port = port;
 		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);
+	if (pl->port == port)
+		return;
+	list_for_each_entry(nl, &pl->list, list) {
+		if (nl->port == port)
+			return;
+	}
+	nl = kmalloc(sizeof(*nl), GFP_ATOMIC);
+	if (nl) {
+		nl->port = port;
+		list_add(&nl->list, &pl->list);
 	}
 }
 
-void tipc_nametbl_stop(void)
+u32 tipc_plist_pop(struct tipc_plist *pl)
 {
-	u32 i;
-	struct name_seq *seq;
-	struct hlist_head *seq_head;
-	struct hlist_node *safe;
+	struct tipc_plist *nl;
+	u32 port = 0;
 
-	/* 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;
-		seq_head = &table.types[i];
-		hlist_for_each_entry_safe(seq, safe, seq_head, ns_list) {
-			tipc_purge_publications(seq);
-		}
+	if (likely(list_empty(&pl->list))) {
+		port = pl->port;
+		pl->port = 0;
+		return port;
 	}
-	kfree(table.types);
-	table.types = NULL;
-	write_unlock_bh(&tipc_nametbl_lock);
+	nl = list_first_entry(&pl->list, typeof(*nl), list);
+	port = nl->port;
+	list_del(&nl->list);
+	kfree(nl);
+	return port;
 }
diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h
index f02f48b9a216..1524a73830f7 100644
--- a/net/tipc/name_table.h
+++ b/net/tipc/name_table.h
@@ -1,7 +1,7 @@
 /*
  * net/tipc/name_table.h: Include file for TIPC name table code
  *
- * Copyright (c) 2000-2006, Ericsson AB
+ * Copyright (c) 2000-2006, 2014-2015, Ericsson AB
  * Copyright (c) 2004-2005, 2010-2011, Wind River Systems
  * All rights reserved.
  *
@@ -37,15 +37,15 @@
 #ifndef _TIPC_NAME_TABLE_H
 #define _TIPC_NAME_TABLE_H
 
-#include "node_subscr.h"
-
 struct tipc_subscription;
-struct tipc_port_list;
+struct tipc_plist;
 
 /*
  * TIPC name types reserved for internal TIPC use (both current and planned)
  */
-#define TIPC_ZM_SRV 3		/* zone master service name type */
+#define TIPC_ZM_SRV		3	/* zone master service name type */
+#define TIPC_PUBL_SCOPE_NUM	(TIPC_NODE_SCOPE + 1)
+#define TIPC_NAMETBL_SIZE	1024	/* must be a power of 2 */
 
 /**
  * struct publication - info about a published (name or) name sequence
@@ -56,12 +56,13 @@ struct tipc_port_list;
  * @node: network address of publishing port's node
  * @ref: publishing port
  * @key: publication key
- * @subscr: subscription to "node down" event (for off-node publications only)
+ * @nodesub_list: subscription to "node down" event (off-node publication only)
  * @local_list: adjacent entries in list of publications made by this node
  * @pport_list: adjacent entries in list of publications made by this port
  * @node_list: adjacent matching name seq publications with >= node scope
  * @cluster_list: adjacent matching name seq publications with >= cluster scope
  * @zone_list: adjacent matching name seq publications with >= zone scope
+ * @rcu: RCU callback head used for deferred freeing
  *
  * Note that the node list, cluster list, and zone list are circular lists.
  */
@@ -73,32 +74,60 @@ struct publication {
 	u32 node;
 	u32 ref;
 	u32 key;
-	struct tipc_node_subscr subscr;
+	struct list_head nodesub_list;
 	struct list_head local_list;
 	struct list_head pport_list;
 	struct list_head node_list;
 	struct list_head cluster_list;
 	struct list_head zone_list;
+	struct rcu_head rcu;
 };
 
+/**
+ * struct name_table - table containing all existing port name publications
+ * @seq_hlist: name sequence hash lists
+ * @publ_list: pulication lists
+ * @local_publ_count: number of publications issued by this node
+ */
+struct name_table {
+	struct hlist_head seq_hlist[TIPC_NAMETBL_SIZE];
+	struct list_head publ_list[TIPC_PUBL_SCOPE_NUM];
+	u32 local_publ_count;
+};
 
-extern rwlock_t tipc_nametbl_lock;
+int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb);
 
-struct sk_buff *tipc_nametbl_get(const void *req_tlv_area, int req_tlv_space);
-u32 tipc_nametbl_translate(u32 type, u32 instance, u32 *node);
-int tipc_nametbl_mc_translate(u32 type, u32 lower, u32 upper, u32 limit,
-			      struct tipc_port_list *dports);
-struct publication *tipc_nametbl_publish(u32 type, u32 lower, u32 upper,
-					 u32 scope, u32 port_ref, u32 key);
-int tipc_nametbl_withdraw(u32 type, u32 lower, u32 ref, u32 key);
-struct publication *tipc_nametbl_insert_publ(u32 type, u32 lower, u32 upper,
-					     u32 scope, u32 node, u32 ref,
+u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance, u32 *node);
+int tipc_nametbl_mc_translate(struct net *net, u32 type, u32 lower, u32 upper,
+			      u32 limit, struct tipc_plist *dports);
+struct publication *tipc_nametbl_publish(struct net *net, u32 type, u32 lower,
+					 u32 upper, u32 scope, u32 port_ref,
+					 u32 key);
+int tipc_nametbl_withdraw(struct net *net, u32 type, u32 lower, u32 ref,
+			  u32 key);
+struct publication *tipc_nametbl_insert_publ(struct net *net, u32 type,
+					     u32 lower, u32 upper, u32 scope,
+					     u32 node, u32 ref, u32 key);
+struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type,
+					     u32 lower, u32 node, u32 ref,
 					     u32 key);
-struct publication *tipc_nametbl_remove_publ(u32 type, u32 lower, u32 node,
-					     u32 ref, u32 key);
 void tipc_nametbl_subscribe(struct tipc_subscription *s);
 void tipc_nametbl_unsubscribe(struct tipc_subscription *s);
-int tipc_nametbl_init(void);
-void tipc_nametbl_stop(void);
+int tipc_nametbl_init(struct net *net);
+void tipc_nametbl_stop(struct net *net);
+
+struct tipc_plist {
+	struct list_head list;
+	u32 port;
+};
+
+static inline void tipc_plist_init(struct tipc_plist *pl)
+{
+	INIT_LIST_HEAD(&pl->list);
+	pl->port = 0;
+}
+
+void tipc_plist_push(struct tipc_plist *pl, u32 port);
+u32 tipc_plist_pop(struct tipc_plist *pl);
 
 #endif
diff --git a/net/tipc/net.c b/net/tipc/net.c
index 93b9944a6a8b..a54f3cbe2246 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -40,7 +40,11 @@
 #include "subscr.h"
 #include "socket.h"
 #include "node.h"
-#include "config.h"
+
+static const struct nla_policy tipc_nl_net_policy[TIPC_NLA_NET_MAX + 1] = {
+	[TIPC_NLA_NET_UNSPEC]	= { .type = NLA_UNSPEC },
+	[TIPC_NLA_NET_ID]	= { .type = NLA_U32 }
+};
 
 /*
  * The TIPC locking policy is designed to ensure a very fine locking
@@ -103,38 +107,148 @@
  *     - A local spin_lock protecting the queue of subscriber events.
 */
 
-int tipc_net_start(u32 addr)
+int tipc_net_start(struct net *net, u32 addr)
 {
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	char addr_string[16];
 	int res;
 
-	tipc_own_addr = addr;
-	tipc_named_reinit();
-	tipc_sk_reinit();
-	res = tipc_bclink_init();
+	tn->own_addr = addr;
+	tipc_named_reinit(net);
+	tipc_sk_reinit(net);
+	res = tipc_bclink_init(net);
 	if (res)
 		return res;
 
-	tipc_nametbl_publish(TIPC_CFG_SRV, tipc_own_addr, tipc_own_addr,
-			     TIPC_ZONE_SCOPE, 0, tipc_own_addr);
+	tipc_nametbl_publish(net, TIPC_CFG_SRV, tn->own_addr, tn->own_addr,
+			     TIPC_ZONE_SCOPE, 0, tn->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);
+		tipc_addr_string_fill(addr_string, tn->own_addr),
+		tn->net_id);
 	return 0;
 }
 
-void tipc_net_stop(void)
+void tipc_net_stop(struct net *net)
 {
-	if (!tipc_own_addr)
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+
+	if (!tn->own_addr)
 		return;
 
-	tipc_nametbl_withdraw(TIPC_CFG_SRV, tipc_own_addr, 0, tipc_own_addr);
+	tipc_nametbl_withdraw(net, TIPC_CFG_SRV, tn->own_addr, 0,
+			      tn->own_addr);
 	rtnl_lock();
-	tipc_bearer_stop();
-	tipc_bclink_stop();
-	tipc_node_stop();
+	tipc_bearer_stop(net);
+	tipc_bclink_stop(net);
+	tipc_node_stop(net);
 	rtnl_unlock();
 
 	pr_info("Left network mode\n");
 }
+
+static int __tipc_nl_add_net(struct net *net, struct tipc_nl_msg *msg)
+{
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	void *hdr;
+	struct nlattr *attrs;
+
+	hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family,
+			  NLM_F_MULTI, TIPC_NL_NET_GET);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	attrs = nla_nest_start(msg->skb, TIPC_NLA_NET);
+	if (!attrs)
+		goto msg_full;
+
+	if (nla_put_u32(msg->skb, TIPC_NLA_NET_ID, tn->net_id))
+		goto attr_msg_full;
+
+	nla_nest_end(msg->skb, attrs);
+	genlmsg_end(msg->skb, hdr);
+
+	return 0;
+
+attr_msg_full:
+	nla_nest_cancel(msg->skb, attrs);
+msg_full:
+	genlmsg_cancel(msg->skb, hdr);
+
+	return -EMSGSIZE;
+}
+
+int tipc_nl_net_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct net *net = sock_net(skb->sk);
+	int err;
+	int done = cb->args[0];
+	struct tipc_nl_msg msg;
+
+	if (done)
+		return 0;
+
+	msg.skb = skb;
+	msg.portid = NETLINK_CB(cb->skb).portid;
+	msg.seq = cb->nlh->nlmsg_seq;
+
+	err = __tipc_nl_add_net(net, &msg);
+	if (err)
+		goto out;
+
+	done = 1;
+out:
+	cb->args[0] = done;
+
+	return skb->len;
+}
+
+int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info)
+{
+	struct net *net = sock_net(skb->sk);
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	struct nlattr *attrs[TIPC_NLA_NET_MAX + 1];
+	int err;
+
+	if (!info->attrs[TIPC_NLA_NET])
+		return -EINVAL;
+
+	err = nla_parse_nested(attrs, TIPC_NLA_NET_MAX,
+			       info->attrs[TIPC_NLA_NET],
+			       tipc_nl_net_policy);
+	if (err)
+		return err;
+
+	if (attrs[TIPC_NLA_NET_ID]) {
+		u32 val;
+
+		/* Can't change net id once TIPC has joined a network */
+		if (tn->own_addr)
+			return -EPERM;
+
+		val = nla_get_u32(attrs[TIPC_NLA_NET_ID]);
+		if (val < 1 || val > 9999)
+			return -EINVAL;
+
+		tn->net_id = val;
+	}
+
+	if (attrs[TIPC_NLA_NET_ADDR]) {
+		u32 addr;
+
+		/* Can't change net addr once TIPC has joined a network */
+		if (tn->own_addr)
+			return -EPERM;
+
+		addr = nla_get_u32(attrs[TIPC_NLA_NET_ADDR]);
+		if (!tipc_addr_node_valid(addr))
+			return -EINVAL;
+
+		rtnl_lock();
+		tipc_net_start(net, addr);
+		rtnl_unlock();
+	}
+
+	return 0;
+}
diff --git a/net/tipc/net.h b/net/tipc/net.h
index 59ef3388be2c..77a7a118911d 100644
--- a/net/tipc/net.h
+++ b/net/tipc/net.h
@@ -1,7 +1,7 @@
 /*
  * net/tipc/net.h: Include file for TIPC network routing code
  *
- * Copyright (c) 1995-2006, Ericsson AB
+ * Copyright (c) 1995-2006, 2014, Ericsson AB
  * Copyright (c) 2005, 2010-2011, Wind River Systems
  * All rights reserved.
  *
@@ -37,7 +37,13 @@
 #ifndef _TIPC_NET_H
 #define _TIPC_NET_H
 
-int tipc_net_start(u32 addr);
-void tipc_net_stop(void);
+#include <net/genetlink.h>
+
+int tipc_net_start(struct net *net, u32 addr);
+
+void tipc_net_stop(struct net *net);
+
+int tipc_nl_net_dump(struct sk_buff *skb, struct netlink_callback *cb);
+int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info);
 
 #endif
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index ad844d365340..7f6475efc984 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -1,7 +1,7 @@
 /*
  * net/tipc/netlink.c: TIPC configuration handling
  *
- * Copyright (c) 2005-2006, Ericsson AB
+ * Copyright (c) 2005-2006, 2014, Ericsson AB
  * Copyright (c) 2005-2007, Wind River Systems
  * All rights reserved.
  *
@@ -35,59 +35,136 @@
  */
 
 #include "core.h"
-#include "config.h"
+#include "socket.h"
+#include "name_table.h"
+#include "bearer.h"
+#include "link.h"
+#include "node.h"
+#include "net.h"
 #include <net/genetlink.h>
 
-static int handle_cmd(struct sk_buff *skb, struct genl_info *info)
-{
-	struct sk_buff *rep_buf;
-	struct nlmsghdr *rep_nlh;
-	struct nlmsghdr *req_nlh = info->nlhdr;
-	struct tipc_genlmsghdr *req_userhdr = info->userhdr;
-	int hdr_space = nlmsg_total_size(GENL_HDRLEN + TIPC_GENL_HDRLEN);
-	u16 cmd;
-
-	if ((req_userhdr->cmd & 0xC000) && (!netlink_capable(skb, CAP_NET_ADMIN)))
-		cmd = TIPC_CMD_NOT_NET_ADMIN;
-	else
-		cmd = req_userhdr->cmd;
-
-	rep_buf = tipc_cfg_do_cmd(req_userhdr->dest, cmd,
-			nlmsg_data(req_nlh) + GENL_HDRLEN + TIPC_GENL_HDRLEN,
-			nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN),
-			hdr_space);
-
-	if (rep_buf) {
-		skb_push(rep_buf, hdr_space);
-		rep_nlh = nlmsg_hdr(rep_buf);
-		memcpy(rep_nlh, req_nlh, hdr_space);
-		rep_nlh->nlmsg_len = rep_buf->len;
-		genlmsg_unicast(&init_net, rep_buf, NETLINK_CB(skb).portid);
-	}
-
-	return 0;
-}
+static const struct nla_policy tipc_nl_policy[TIPC_NLA_MAX + 1] = {
+	[TIPC_NLA_UNSPEC]	= { .type = NLA_UNSPEC, },
+	[TIPC_NLA_BEARER]	= { .type = NLA_NESTED, },
+	[TIPC_NLA_SOCK]		= { .type = NLA_NESTED, },
+	[TIPC_NLA_PUBL]		= { .type = NLA_NESTED, },
+	[TIPC_NLA_LINK]		= { .type = NLA_NESTED, },
+	[TIPC_NLA_MEDIA]	= { .type = NLA_NESTED, },
+	[TIPC_NLA_NODE]		= { .type = NLA_NESTED, },
+	[TIPC_NLA_NET]		= { .type = NLA_NESTED, },
+	[TIPC_NLA_NAME_TABLE]	= { .type = NLA_NESTED, }
+};
 
-static struct genl_family tipc_genl_family = {
+/* Users of the legacy API (tipc-config) can't handle that we add operations,
+ * so we have a separate genl handling for the new API.
+ */
+struct genl_family tipc_genl_family = {
 	.id		= GENL_ID_GENERATE,
-	.name		= TIPC_GENL_NAME,
-	.version	= TIPC_GENL_VERSION,
-	.hdrsize	= TIPC_GENL_HDRLEN,
-	.maxattr	= 0,
+	.name		= TIPC_GENL_V2_NAME,
+	.version	= TIPC_GENL_V2_VERSION,
+	.hdrsize	= 0,
+	.maxattr	= TIPC_NLA_MAX,
+	.netnsok	= true,
 };
 
-static struct genl_ops tipc_genl_ops[] = {
+static const struct genl_ops tipc_genl_v2_ops[] = {
+	{
+		.cmd	= TIPC_NL_BEARER_DISABLE,
+		.doit	= tipc_nl_bearer_disable,
+		.policy = tipc_nl_policy,
+	},
+	{
+		.cmd	= TIPC_NL_BEARER_ENABLE,
+		.doit	= tipc_nl_bearer_enable,
+		.policy = tipc_nl_policy,
+	},
+	{
+		.cmd	= TIPC_NL_BEARER_GET,
+		.doit	= tipc_nl_bearer_get,
+		.dumpit	= tipc_nl_bearer_dump,
+		.policy = tipc_nl_policy,
+	},
+	{
+		.cmd	= TIPC_NL_BEARER_SET,
+		.doit	= tipc_nl_bearer_set,
+		.policy = tipc_nl_policy,
+	},
+	{
+		.cmd	= TIPC_NL_SOCK_GET,
+		.dumpit	= tipc_nl_sk_dump,
+		.policy = tipc_nl_policy,
+	},
+	{
+		.cmd	= TIPC_NL_PUBL_GET,
+		.dumpit	= tipc_nl_publ_dump,
+		.policy = tipc_nl_policy,
+	},
 	{
-		.cmd		= TIPC_GENL_CMD,
-		.doit		= handle_cmd,
+		.cmd	= TIPC_NL_LINK_GET,
+		.doit   = tipc_nl_link_get,
+		.dumpit	= tipc_nl_link_dump,
+		.policy = tipc_nl_policy,
 	},
+	{
+		.cmd	= TIPC_NL_LINK_SET,
+		.doit	= tipc_nl_link_set,
+		.policy = tipc_nl_policy,
+	},
+	{
+		.cmd	= TIPC_NL_LINK_RESET_STATS,
+		.doit   = tipc_nl_link_reset_stats,
+		.policy = tipc_nl_policy,
+	},
+	{
+		.cmd	= TIPC_NL_MEDIA_GET,
+		.doit	= tipc_nl_media_get,
+		.dumpit	= tipc_nl_media_dump,
+		.policy = tipc_nl_policy,
+	},
+	{
+		.cmd	= TIPC_NL_MEDIA_SET,
+		.doit	= tipc_nl_media_set,
+		.policy = tipc_nl_policy,
+	},
+	{
+		.cmd	= TIPC_NL_NODE_GET,
+		.dumpit	= tipc_nl_node_dump,
+		.policy = tipc_nl_policy,
+	},
+	{
+		.cmd	= TIPC_NL_NET_GET,
+		.dumpit	= tipc_nl_net_dump,
+		.policy = tipc_nl_policy,
+	},
+	{
+		.cmd	= TIPC_NL_NET_SET,
+		.doit	= tipc_nl_net_set,
+		.policy = tipc_nl_policy,
+	},
+	{
+		.cmd	= TIPC_NL_NAME_TABLE_GET,
+		.dumpit	= tipc_nl_name_table_dump,
+		.policy = tipc_nl_policy,
+	}
 };
 
+int tipc_nlmsg_parse(const struct nlmsghdr *nlh, struct nlattr ***attr)
+{
+	u32 maxattr = tipc_genl_family.maxattr;
+
+	*attr = tipc_genl_family.attrbuf;
+	if (!*attr)
+		return -EOPNOTSUPP;
+
+	return nlmsg_parse(nlh, GENL_HDRLEN, *attr, maxattr, tipc_nl_policy);
+}
+
 int tipc_netlink_start(void)
 {
 	int res;
 
-	res = genl_register_family_with_ops(&tipc_genl_family, tipc_genl_ops);
+	res = genl_register_family_with_ops(&tipc_genl_family,
+					    tipc_genl_v2_ops);
 	if (res) {
 		pr_err("Failed to register netlink interface\n");
 		return res;
diff --git a/net/tipc/log.c b/net/tipc/netlink.h
index abef644f27d8..08a1db67b927 100644
--- a/net/tipc/log.c
+++ b/net/tipc/netlink.h
@@ -1,8 +1,7 @@
 /*
- * net/tipc/log.c: TIPC print buffer routines for debugging
+ * net/tipc/netlink.h: Include file for TIPC netlink code
  *
- * Copyright (c) 1996-2006, Ericsson AB
- * Copyright (c) 2005-2007, Wind River Systems
+ * Copyright (c) 2014, Ericsson AB
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -34,22 +33,21 @@
  * POSSIBILITY OF SUCH DAMAGE.
  */
 
-#include "core.h"
-#include "config.h"
+#ifndef _TIPC_NETLINK_H
+#define _TIPC_NETLINK_H
 
-/**
- * tipc_snprintf - append formatted output to print buffer
- * @buf: pointer to print buffer
- * @len: buffer length
- * @fmt: formatted info to be printed
- */
-int tipc_snprintf(char *buf, int len, const char *fmt, ...)
-{
-	int i;
-	va_list args;
+extern struct genl_family tipc_genl_family;
+int tipc_nlmsg_parse(const struct nlmsghdr *nlh, struct nlattr ***buf);
+
+struct tipc_nl_msg {
+	struct sk_buff *skb;
+	u32 portid;
+	u32 seq;
+};
+
+int tipc_netlink_start(void);
+int tipc_netlink_compat_start(void);
+void tipc_netlink_stop(void);
+void tipc_netlink_compat_stop(void);
 
-	va_start(args, fmt);
-	i = vscnprintf(buf, len, fmt, args);
-	va_end(args);
-	return i;
-}
+#endif
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
new file mode 100644
index 000000000000..ce9121e8e990
--- /dev/null
+++ b/net/tipc/netlink_compat.c
@@ -0,0 +1,1084 @@
+/*
+ * 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.
+ */
+
+#include "core.h"
+#include "bearer.h"
+#include "link.h"
+#include "name_table.h"
+#include "socket.h"
+#include "node.h"
+#include "net.h"
+#include <net/genetlink.h>
+#include <linux/tipc_config.h>
+
+/* The legacy API had an artificial message length limit called
+ * ULTRA_STRING_MAX_LEN.
+ */
+#define ULTRA_STRING_MAX_LEN 32768
+
+#define TIPC_SKB_MAX TLV_SPACE(ULTRA_STRING_MAX_LEN)
+
+#define REPLY_TRUNCATED "<truncated>\n"
+
+struct tipc_nl_compat_msg {
+	u16 cmd;
+	int rep_type;
+	int rep_size;
+	int req_type;
+	struct sk_buff *rep;
+	struct tlv_desc *req;
+	struct sock *dst_sk;
+};
+
+struct tipc_nl_compat_cmd_dump {
+	int (*header)(struct tipc_nl_compat_msg *);
+	int (*dumpit)(struct sk_buff *, struct netlink_callback *);
+	int (*format)(struct tipc_nl_compat_msg *msg, struct nlattr **attrs);
+};
+
+struct tipc_nl_compat_cmd_doit {
+	int (*doit)(struct sk_buff *skb, struct genl_info *info);
+	int (*transcode)(struct sk_buff *skb, struct tipc_nl_compat_msg *msg);
+};
+
+static int tipc_skb_tailroom(struct sk_buff *skb)
+{
+	int tailroom;
+	int limit;
+
+	tailroom = skb_tailroom(skb);
+	limit = TIPC_SKB_MAX - skb->len;
+
+	if (tailroom < limit)
+		return tailroom;
+
+	return limit;
+}
+
+static int tipc_add_tlv(struct sk_buff *skb, u16 type, void *data, u16 len)
+{
+	struct tlv_desc *tlv = (struct tlv_desc *)skb_tail_pointer(skb);
+
+	if (tipc_skb_tailroom(skb) < TLV_SPACE(len))
+		return -EMSGSIZE;
+
+	skb_put(skb, TLV_SPACE(len));
+	tlv->tlv_type = htons(type);
+	tlv->tlv_len = htons(TLV_LENGTH(len));
+	if (len && data)
+		memcpy(TLV_DATA(tlv), data, len);
+
+	return 0;
+}
+
+static void tipc_tlv_init(struct sk_buff *skb, u16 type)
+{
+	struct tlv_desc *tlv = (struct tlv_desc *)skb->data;
+
+	TLV_SET_LEN(tlv, 0);
+	TLV_SET_TYPE(tlv, type);
+	skb_put(skb, sizeof(struct tlv_desc));
+}
+
+static int tipc_tlv_sprintf(struct sk_buff *skb, const char *fmt, ...)
+{
+	int n;
+	u16 len;
+	u32 rem;
+	char *buf;
+	struct tlv_desc *tlv;
+	va_list args;
+
+	rem = tipc_skb_tailroom(skb);
+
+	tlv = (struct tlv_desc *)skb->data;
+	len = TLV_GET_LEN(tlv);
+	buf = TLV_DATA(tlv) + len;
+
+	va_start(args, fmt);
+	n = vscnprintf(buf, rem, fmt, args);
+	va_end(args);
+
+	TLV_SET_LEN(tlv, n + len);
+	skb_put(skb, n);
+
+	return n;
+}
+
+static struct sk_buff *tipc_tlv_alloc(int size)
+{
+	int hdr_len;
+	struct sk_buff *buf;
+
+	size = TLV_SPACE(size);
+	hdr_len = nlmsg_total_size(GENL_HDRLEN + TIPC_GENL_HDRLEN);
+
+	buf = alloc_skb(hdr_len + size, GFP_KERNEL);
+	if (!buf)
+		return NULL;
+
+	skb_reserve(buf, hdr_len);
+
+	return buf;
+}
+
+static struct sk_buff *tipc_get_err_tlv(char *str)
+{
+	int str_len = strlen(str) + 1;
+	struct sk_buff *buf;
+
+	buf = tipc_tlv_alloc(TLV_SPACE(str_len));
+	if (buf)
+		tipc_add_tlv(buf, TIPC_TLV_ERROR_STRING, str, str_len);
+
+	return buf;
+}
+
+static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
+				   struct tipc_nl_compat_msg *msg,
+				   struct sk_buff *arg)
+{
+	int len = 0;
+	int err;
+	struct sk_buff *buf;
+	struct nlmsghdr *nlmsg;
+	struct netlink_callback cb;
+
+	memset(&cb, 0, sizeof(cb));
+	cb.nlh = (struct nlmsghdr *)arg->data;
+	cb.skb = arg;
+
+	buf = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	buf->sk = msg->dst_sk;
+
+	do {
+		int rem;
+
+		len = (*cmd->dumpit)(buf, &cb);
+
+		nlmsg_for_each_msg(nlmsg, nlmsg_hdr(buf), len, rem) {
+			struct nlattr **attrs;
+
+			err = tipc_nlmsg_parse(nlmsg, &attrs);
+			if (err)
+				goto err_out;
+
+			err = (*cmd->format)(msg, attrs);
+			if (err)
+				goto err_out;
+
+			if (tipc_skb_tailroom(msg->rep) <= 1) {
+				err = -EMSGSIZE;
+				goto err_out;
+			}
+		}
+
+		skb_reset_tail_pointer(buf);
+		buf->len = 0;
+
+	} while (len);
+
+	err = 0;
+
+err_out:
+	kfree_skb(buf);
+
+	if (err == -EMSGSIZE) {
+		/* The legacy API only considered messages filling
+		 * "ULTRA_STRING_MAX_LEN" to be truncated.
+		 */
+		if ((TIPC_SKB_MAX - msg->rep->len) <= 1) {
+			char *tail = skb_tail_pointer(msg->rep);
+
+			if (*tail != '\0')
+				sprintf(tail - sizeof(REPLY_TRUNCATED) - 1,
+					REPLY_TRUNCATED);
+		}
+
+		return 0;
+	}
+
+	return err;
+}
+
+static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
+				 struct tipc_nl_compat_msg *msg)
+{
+	int err;
+	struct sk_buff *arg;
+
+	if (msg->req_type && !TLV_CHECK_TYPE(msg->req, msg->req_type))
+		return -EINVAL;
+
+	msg->rep = tipc_tlv_alloc(msg->rep_size);
+	if (!msg->rep)
+		return -ENOMEM;
+
+	if (msg->rep_type)
+		tipc_tlv_init(msg->rep, msg->rep_type);
+
+	if (cmd->header)
+		(*cmd->header)(msg);
+
+	arg = nlmsg_new(0, GFP_KERNEL);
+	if (!arg) {
+		kfree_skb(msg->rep);
+		return -ENOMEM;
+	}
+
+	err = __tipc_nl_compat_dumpit(cmd, msg, arg);
+	if (err)
+		kfree_skb(msg->rep);
+
+	kfree_skb(arg);
+
+	return err;
+}
+
+static int __tipc_nl_compat_doit(struct tipc_nl_compat_cmd_doit *cmd,
+				 struct tipc_nl_compat_msg *msg)
+{
+	int err;
+	struct sk_buff *doit_buf;
+	struct sk_buff *trans_buf;
+	struct nlattr **attrbuf;
+	struct genl_info info;
+
+	trans_buf = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!trans_buf)
+		return -ENOMEM;
+
+	err = (*cmd->transcode)(trans_buf, msg);
+	if (err)
+		goto trans_out;
+
+	attrbuf = kmalloc((tipc_genl_family.maxattr + 1) *
+			sizeof(struct nlattr *), GFP_KERNEL);
+	if (!attrbuf) {
+		err = -ENOMEM;
+		goto trans_out;
+	}
+
+	err = nla_parse(attrbuf, tipc_genl_family.maxattr,
+			(const struct nlattr *)trans_buf->data,
+			trans_buf->len, NULL);
+	if (err)
+		goto parse_out;
+
+	doit_buf = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!doit_buf) {
+		err = -ENOMEM;
+		goto parse_out;
+	}
+
+	doit_buf->sk = msg->dst_sk;
+
+	memset(&info, 0, sizeof(info));
+	info.attrs = attrbuf;
+
+	err = (*cmd->doit)(doit_buf, &info);
+
+	kfree_skb(doit_buf);
+parse_out:
+	kfree(attrbuf);
+trans_out:
+	kfree_skb(trans_buf);
+
+	return err;
+}
+
+static int tipc_nl_compat_doit(struct tipc_nl_compat_cmd_doit *cmd,
+			       struct tipc_nl_compat_msg *msg)
+{
+	int err;
+
+	if (msg->req_type && !TLV_CHECK_TYPE(msg->req, msg->req_type))
+		return -EINVAL;
+
+	err = __tipc_nl_compat_doit(cmd, msg);
+	if (err)
+		return err;
+
+	/* The legacy API considered an empty message a success message */
+	msg->rep = tipc_tlv_alloc(0);
+	if (!msg->rep)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static int tipc_nl_compat_bearer_dump(struct tipc_nl_compat_msg *msg,
+				      struct nlattr **attrs)
+{
+	struct nlattr *bearer[TIPC_NLA_BEARER_MAX + 1];
+
+	nla_parse_nested(bearer, TIPC_NLA_BEARER_MAX, attrs[TIPC_NLA_BEARER],
+			 NULL);
+
+	return tipc_add_tlv(msg->rep, TIPC_TLV_BEARER_NAME,
+			    nla_data(bearer[TIPC_NLA_BEARER_NAME]),
+			    nla_len(bearer[TIPC_NLA_BEARER_NAME]));
+}
+
+static int tipc_nl_compat_bearer_enable(struct sk_buff *skb,
+					struct tipc_nl_compat_msg *msg)
+{
+	struct nlattr *prop;
+	struct nlattr *bearer;
+	struct tipc_bearer_config *b;
+
+	b = (struct tipc_bearer_config *)TLV_DATA(msg->req);
+
+	bearer = nla_nest_start(skb, TIPC_NLA_BEARER);
+	if (!bearer)
+		return -EMSGSIZE;
+
+	if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, b->name))
+		return -EMSGSIZE;
+
+	if (nla_put_u32(skb, TIPC_NLA_BEARER_DOMAIN, ntohl(b->disc_domain)))
+		return -EMSGSIZE;
+
+	if (ntohl(b->priority) <= TIPC_MAX_LINK_PRI) {
+		prop = nla_nest_start(skb, TIPC_NLA_BEARER_PROP);
+		if (!prop)
+			return -EMSGSIZE;
+		if (nla_put_u32(skb, TIPC_NLA_PROP_PRIO, ntohl(b->priority)))
+			return -EMSGSIZE;
+		nla_nest_end(skb, prop);
+	}
+	nla_nest_end(skb, bearer);
+
+	return 0;
+}
+
+static int tipc_nl_compat_bearer_disable(struct sk_buff *skb,
+					 struct tipc_nl_compat_msg *msg)
+{
+	char *name;
+	struct nlattr *bearer;
+
+	name = (char *)TLV_DATA(msg->req);
+
+	bearer = nla_nest_start(skb, TIPC_NLA_BEARER);
+	if (!bearer)
+		return -EMSGSIZE;
+
+	if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, name))
+		return -EMSGSIZE;
+
+	nla_nest_end(skb, bearer);
+
+	return 0;
+}
+
+static inline u32 perc(u32 count, u32 total)
+{
+	return (count * 100 + (total / 2)) / total;
+}
+
+static void __fill_bc_link_stat(struct tipc_nl_compat_msg *msg,
+				struct nlattr *prop[], struct nlattr *stats[])
+{
+	tipc_tlv_sprintf(msg->rep, "  Window:%u packets\n",
+			 nla_get_u32(prop[TIPC_NLA_PROP_WIN]));
+
+	tipc_tlv_sprintf(msg->rep,
+			 "  RX packets:%u fragments:%u/%u bundles:%u/%u\n",
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_INFO]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_FRAGMENTS]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_FRAGMENTED]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_BUNDLES]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_BUNDLED]));
+
+	tipc_tlv_sprintf(msg->rep,
+			 "  TX packets:%u fragments:%u/%u bundles:%u/%u\n",
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_INFO]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_FRAGMENTS]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_FRAGMENTED]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_BUNDLES]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_BUNDLED]));
+
+	tipc_tlv_sprintf(msg->rep, "  RX naks:%u defs:%u dups:%u\n",
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_NACKS]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_DEFERRED]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_DUPLICATES]));
+
+	tipc_tlv_sprintf(msg->rep, "  TX naks:%u acks:%u dups:%u\n",
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_NACKS]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_ACKS]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_RETRANSMITTED]));
+
+	tipc_tlv_sprintf(msg->rep,
+			 "  Congestion link:%u  Send queue max:%u avg:%u",
+			 nla_get_u32(stats[TIPC_NLA_STATS_LINK_CONGS]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_MAX_QUEUE]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_AVG_QUEUE]));
+}
+
+static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg,
+					 struct nlattr **attrs)
+{
+	char *name;
+	struct nlattr *link[TIPC_NLA_LINK_MAX + 1];
+	struct nlattr *prop[TIPC_NLA_PROP_MAX + 1];
+	struct nlattr *stats[TIPC_NLA_STATS_MAX + 1];
+
+	nla_parse_nested(link, TIPC_NLA_LINK_MAX, attrs[TIPC_NLA_LINK], NULL);
+
+	nla_parse_nested(prop, TIPC_NLA_PROP_MAX, link[TIPC_NLA_LINK_PROP],
+			 NULL);
+
+	nla_parse_nested(stats, TIPC_NLA_STATS_MAX, link[TIPC_NLA_LINK_STATS],
+			 NULL);
+
+	name = (char *)TLV_DATA(msg->req);
+	if (strcmp(name, nla_data(link[TIPC_NLA_LINK_NAME])) != 0)
+		return 0;
+
+	tipc_tlv_sprintf(msg->rep, "\nLink <%s>\n",
+			 nla_data(link[TIPC_NLA_LINK_NAME]));
+
+	if (link[TIPC_NLA_LINK_BROADCAST]) {
+		__fill_bc_link_stat(msg, prop, stats);
+		return 0;
+	}
+
+	if (link[TIPC_NLA_LINK_ACTIVE])
+		tipc_tlv_sprintf(msg->rep, "  ACTIVE");
+	else if (link[TIPC_NLA_LINK_UP])
+		tipc_tlv_sprintf(msg->rep, "  STANDBY");
+	else
+		tipc_tlv_sprintf(msg->rep, "  DEFUNCT");
+
+	tipc_tlv_sprintf(msg->rep, "  MTU:%u  Priority:%u",
+			 nla_get_u32(link[TIPC_NLA_LINK_MTU]),
+			 nla_get_u32(prop[TIPC_NLA_PROP_PRIO]));
+
+	tipc_tlv_sprintf(msg->rep, "  Tolerance:%u ms  Window:%u packets\n",
+			 nla_get_u32(prop[TIPC_NLA_PROP_TOL]),
+			 nla_get_u32(prop[TIPC_NLA_PROP_WIN]));
+
+	tipc_tlv_sprintf(msg->rep,
+			 "  RX packets:%u fragments:%u/%u bundles:%u/%u\n",
+			 nla_get_u32(link[TIPC_NLA_LINK_RX]) -
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_INFO]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_FRAGMENTS]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_FRAGMENTED]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_BUNDLES]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_BUNDLED]));
+
+	tipc_tlv_sprintf(msg->rep,
+			 "  TX packets:%u fragments:%u/%u bundles:%u/%u\n",
+			 nla_get_u32(link[TIPC_NLA_LINK_TX]) -
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_INFO]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_FRAGMENTS]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_FRAGMENTED]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_BUNDLES]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_BUNDLED]));
+
+	tipc_tlv_sprintf(msg->rep,
+			 "  TX profile sample:%u packets  average:%u octets\n",
+			 nla_get_u32(stats[TIPC_NLA_STATS_MSG_LEN_CNT]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_MSG_LEN_TOT]) /
+			 nla_get_u32(stats[TIPC_NLA_STATS_MSG_PROF_TOT]));
+
+	tipc_tlv_sprintf(msg->rep,
+			 "  0-64:%u%% -256:%u%% -1024:%u%% -4096:%u%% ",
+			 perc(nla_get_u32(stats[TIPC_NLA_STATS_MSG_LEN_P0]),
+			      nla_get_u32(stats[TIPC_NLA_STATS_MSG_PROF_TOT])),
+			 perc(nla_get_u32(stats[TIPC_NLA_STATS_MSG_LEN_P1]),
+			      nla_get_u32(stats[TIPC_NLA_STATS_MSG_PROF_TOT])),
+			 perc(nla_get_u32(stats[TIPC_NLA_STATS_MSG_LEN_P2]),
+			      nla_get_u32(stats[TIPC_NLA_STATS_MSG_PROF_TOT])),
+			 perc(nla_get_u32(stats[TIPC_NLA_STATS_MSG_LEN_P3]),
+			      nla_get_u32(stats[TIPC_NLA_STATS_MSG_PROF_TOT])));
+
+	tipc_tlv_sprintf(msg->rep, "-16384:%u%% -32768:%u%% -66000:%u%%\n",
+			 perc(nla_get_u32(stats[TIPC_NLA_STATS_MSG_LEN_P4]),
+			      nla_get_u32(stats[TIPC_NLA_STATS_MSG_PROF_TOT])),
+			 perc(nla_get_u32(stats[TIPC_NLA_STATS_MSG_LEN_P5]),
+			      nla_get_u32(stats[TIPC_NLA_STATS_MSG_PROF_TOT])),
+			 perc(nla_get_u32(stats[TIPC_NLA_STATS_MSG_LEN_P6]),
+			      nla_get_u32(stats[TIPC_NLA_STATS_MSG_PROF_TOT])));
+
+	tipc_tlv_sprintf(msg->rep,
+			 "  RX states:%u probes:%u naks:%u defs:%u dups:%u\n",
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_STATES]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_PROBES]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_NACKS]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_DEFERRED]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_DUPLICATES]));
+
+	tipc_tlv_sprintf(msg->rep,
+			 "  TX states:%u probes:%u naks:%u acks:%u dups:%u\n",
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_STATES]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_PROBES]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_NACKS]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_ACKS]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_RETRANSMITTED]));
+
+	tipc_tlv_sprintf(msg->rep,
+			 "  Congestion link:%u  Send queue max:%u avg:%u",
+			 nla_get_u32(stats[TIPC_NLA_STATS_LINK_CONGS]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_MAX_QUEUE]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_AVG_QUEUE]));
+
+	return 0;
+}
+
+static int tipc_nl_compat_link_dump(struct tipc_nl_compat_msg *msg,
+				    struct nlattr **attrs)
+{
+	struct nlattr *link[TIPC_NLA_LINK_MAX + 1];
+	struct tipc_link_info link_info;
+
+	nla_parse_nested(link, TIPC_NLA_LINK_MAX, attrs[TIPC_NLA_LINK], NULL);
+
+	link_info.dest = nla_get_flag(link[TIPC_NLA_LINK_DEST]);
+	link_info.up = htonl(nla_get_flag(link[TIPC_NLA_LINK_UP]));
+	strcpy(link_info.str, nla_data(link[TIPC_NLA_LINK_NAME]));
+
+	return tipc_add_tlv(msg->rep, TIPC_TLV_LINK_INFO,
+			    &link_info, sizeof(link_info));
+}
+
+static int tipc_nl_compat_link_set(struct sk_buff *skb,
+				   struct tipc_nl_compat_msg *msg)
+{
+	struct nlattr *link;
+	struct nlattr *prop;
+	struct tipc_link_config *lc;
+
+	lc = (struct tipc_link_config *)TLV_DATA(msg->req);
+
+	link = nla_nest_start(skb, TIPC_NLA_LINK);
+	if (!link)
+		return -EMSGSIZE;
+
+	if (nla_put_string(skb, TIPC_NLA_LINK_NAME, lc->name))
+		return -EMSGSIZE;
+
+	prop = nla_nest_start(skb, TIPC_NLA_LINK_PROP);
+	if (!prop)
+		return -EMSGSIZE;
+
+	if (msg->cmd == TIPC_CMD_SET_LINK_PRI) {
+		if (nla_put_u32(skb, TIPC_NLA_PROP_PRIO, ntohl(lc->value)))
+			return -EMSGSIZE;
+	} else if (msg->cmd == TIPC_CMD_SET_LINK_TOL) {
+		if (nla_put_u32(skb, TIPC_NLA_PROP_TOL, ntohl(lc->value)))
+			return -EMSGSIZE;
+	} else if (msg->cmd == TIPC_CMD_SET_LINK_WINDOW) {
+		if (nla_put_u32(skb, TIPC_NLA_PROP_WIN, ntohl(lc->value)))
+			return -EMSGSIZE;
+	}
+
+	nla_nest_end(skb, prop);
+	nla_nest_end(skb, link);
+
+	return 0;
+}
+
+static int tipc_nl_compat_link_reset_stats(struct sk_buff *skb,
+					   struct tipc_nl_compat_msg *msg)
+{
+	char *name;
+	struct nlattr *link;
+
+	name = (char *)TLV_DATA(msg->req);
+
+	link = nla_nest_start(skb, TIPC_NLA_LINK);
+	if (!link)
+		return -EMSGSIZE;
+
+	if (nla_put_string(skb, TIPC_NLA_LINK_NAME, name))
+		return -EMSGSIZE;
+
+	nla_nest_end(skb, link);
+
+	return 0;
+}
+
+static int tipc_nl_compat_name_table_dump_header(struct tipc_nl_compat_msg *msg)
+{
+	int i;
+	u32 depth;
+	struct tipc_name_table_query *ntq;
+	static const char * const header[] = {
+		"Type       ",
+		"Lower      Upper      ",
+		"Port Identity              ",
+		"Publication Scope"
+	};
+
+	ntq = (struct tipc_name_table_query *)TLV_DATA(msg->req);
+
+	depth = ntohl(ntq->depth);
+
+	if (depth > 4)
+		depth = 4;
+	for (i = 0; i < depth; i++)
+		tipc_tlv_sprintf(msg->rep, header[i]);
+	tipc_tlv_sprintf(msg->rep, "\n");
+
+	return 0;
+}
+
+static int tipc_nl_compat_name_table_dump(struct tipc_nl_compat_msg *msg,
+					  struct nlattr **attrs)
+{
+	char port_str[27];
+	struct tipc_name_table_query *ntq;
+	struct nlattr *nt[TIPC_NLA_NAME_TABLE_MAX + 1];
+	struct nlattr *publ[TIPC_NLA_PUBL_MAX + 1];
+	u32 node, depth, type, lowbound, upbound;
+	static const char * const scope_str[] = {"", " zone", " cluster",
+						 " node"};
+
+	nla_parse_nested(nt, TIPC_NLA_NAME_TABLE_MAX,
+			 attrs[TIPC_NLA_NAME_TABLE], NULL);
+
+	nla_parse_nested(publ, TIPC_NLA_PUBL_MAX, nt[TIPC_NLA_NAME_TABLE_PUBL],
+			 NULL);
+
+	ntq = (struct tipc_name_table_query *)TLV_DATA(msg->req);
+
+	depth = ntohl(ntq->depth);
+	type = ntohl(ntq->type);
+	lowbound = ntohl(ntq->lowbound);
+	upbound = ntohl(ntq->upbound);
+
+	if (!(depth & TIPC_NTQ_ALLTYPES) &&
+	    (type != nla_get_u32(publ[TIPC_NLA_PUBL_TYPE])))
+		return 0;
+	if (lowbound && (lowbound > nla_get_u32(publ[TIPC_NLA_PUBL_UPPER])))
+		return 0;
+	if (upbound && (upbound < nla_get_u32(publ[TIPC_NLA_PUBL_LOWER])))
+		return 0;
+
+	tipc_tlv_sprintf(msg->rep, "%-10u ",
+			 nla_get_u32(publ[TIPC_NLA_PUBL_TYPE]));
+
+	if (depth == 1)
+		goto out;
+
+	tipc_tlv_sprintf(msg->rep, "%-10u %-10u ",
+			 nla_get_u32(publ[TIPC_NLA_PUBL_LOWER]),
+			 nla_get_u32(publ[TIPC_NLA_PUBL_UPPER]));
+
+	if (depth == 2)
+		goto out;
+
+	node = nla_get_u32(publ[TIPC_NLA_PUBL_NODE]);
+	sprintf(port_str, "<%u.%u.%u:%u>", tipc_zone(node), tipc_cluster(node),
+		tipc_node(node), nla_get_u32(publ[TIPC_NLA_PUBL_REF]));
+	tipc_tlv_sprintf(msg->rep, "%-26s ", port_str);
+
+	if (depth == 3)
+		goto out;
+
+	tipc_tlv_sprintf(msg->rep, "%-10u %s",
+			 nla_get_u32(publ[TIPC_NLA_PUBL_REF]),
+			 scope_str[nla_get_u32(publ[TIPC_NLA_PUBL_SCOPE])]);
+out:
+	tipc_tlv_sprintf(msg->rep, "\n");
+
+	return 0;
+}
+
+static int __tipc_nl_compat_publ_dump(struct tipc_nl_compat_msg *msg,
+				      struct nlattr **attrs)
+{
+	u32 type, lower, upper;
+	struct nlattr *publ[TIPC_NLA_PUBL_MAX + 1];
+
+	nla_parse_nested(publ, TIPC_NLA_PUBL_MAX, attrs[TIPC_NLA_PUBL], NULL);
+
+	type = nla_get_u32(publ[TIPC_NLA_PUBL_TYPE]);
+	lower = nla_get_u32(publ[TIPC_NLA_PUBL_LOWER]);
+	upper = nla_get_u32(publ[TIPC_NLA_PUBL_UPPER]);
+
+	if (lower == upper)
+		tipc_tlv_sprintf(msg->rep, " {%u,%u}", type, lower);
+	else
+		tipc_tlv_sprintf(msg->rep, " {%u,%u,%u}", type, lower, upper);
+
+	return 0;
+}
+
+static int tipc_nl_compat_publ_dump(struct tipc_nl_compat_msg *msg, u32 sock)
+{
+	int err;
+	void *hdr;
+	struct nlattr *nest;
+	struct sk_buff *args;
+	struct tipc_nl_compat_cmd_dump dump;
+
+	args = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!args)
+		return -ENOMEM;
+
+	hdr = genlmsg_put(args, 0, 0, &tipc_genl_family, NLM_F_MULTI,
+			  TIPC_NL_PUBL_GET);
+
+	nest = nla_nest_start(args, TIPC_NLA_SOCK);
+	if (!nest) {
+		kfree_skb(args);
+		return -EMSGSIZE;
+	}
+
+	if (nla_put_u32(args, TIPC_NLA_SOCK_REF, sock)) {
+		kfree_skb(args);
+		return -EMSGSIZE;
+	}
+
+	nla_nest_end(args, nest);
+	genlmsg_end(args, hdr);
+
+	dump.dumpit = tipc_nl_publ_dump;
+	dump.format = __tipc_nl_compat_publ_dump;
+
+	err = __tipc_nl_compat_dumpit(&dump, msg, args);
+
+	kfree_skb(args);
+
+	return err;
+}
+
+static int tipc_nl_compat_sk_dump(struct tipc_nl_compat_msg *msg,
+				  struct nlattr **attrs)
+{
+	int err;
+	u32 sock_ref;
+	struct nlattr *sock[TIPC_NLA_SOCK_MAX + 1];
+
+	nla_parse_nested(sock, TIPC_NLA_SOCK_MAX, attrs[TIPC_NLA_SOCK], NULL);
+
+	sock_ref = nla_get_u32(sock[TIPC_NLA_SOCK_REF]);
+	tipc_tlv_sprintf(msg->rep, "%u:", sock_ref);
+
+	if (sock[TIPC_NLA_SOCK_CON]) {
+		u32 node;
+		struct nlattr *con[TIPC_NLA_CON_MAX + 1];
+
+		nla_parse_nested(con, TIPC_NLA_CON_MAX, sock[TIPC_NLA_SOCK_CON],
+				 NULL);
+
+		node = nla_get_u32(con[TIPC_NLA_CON_NODE]);
+		tipc_tlv_sprintf(msg->rep, "  connected to <%u.%u.%u:%u>",
+				 tipc_zone(node),
+				 tipc_cluster(node),
+				 tipc_node(node),
+				 nla_get_u32(con[TIPC_NLA_CON_SOCK]));
+
+		if (con[TIPC_NLA_CON_FLAG])
+			tipc_tlv_sprintf(msg->rep, " via {%u,%u}\n",
+					 nla_get_u32(con[TIPC_NLA_CON_TYPE]),
+					 nla_get_u32(con[TIPC_NLA_CON_INST]));
+		else
+			tipc_tlv_sprintf(msg->rep, "\n");
+	} else if (sock[TIPC_NLA_SOCK_HAS_PUBL]) {
+		tipc_tlv_sprintf(msg->rep, " bound to");
+
+		err = tipc_nl_compat_publ_dump(msg, sock_ref);
+		if (err)
+			return err;
+	}
+	tipc_tlv_sprintf(msg->rep, "\n");
+
+	return 0;
+}
+
+static int tipc_nl_compat_media_dump(struct tipc_nl_compat_msg *msg,
+				     struct nlattr **attrs)
+{
+	struct nlattr *media[TIPC_NLA_MEDIA_MAX + 1];
+
+	nla_parse_nested(media, TIPC_NLA_MEDIA_MAX, attrs[TIPC_NLA_MEDIA],
+			 NULL);
+
+	return tipc_add_tlv(msg->rep, TIPC_TLV_MEDIA_NAME,
+			    nla_data(media[TIPC_NLA_MEDIA_NAME]),
+			    nla_len(media[TIPC_NLA_MEDIA_NAME]));
+}
+
+static int tipc_nl_compat_node_dump(struct tipc_nl_compat_msg *msg,
+				    struct nlattr **attrs)
+{
+	struct tipc_node_info node_info;
+	struct nlattr *node[TIPC_NLA_NODE_MAX + 1];
+
+	nla_parse_nested(node, TIPC_NLA_NODE_MAX, attrs[TIPC_NLA_NODE], NULL);
+
+	node_info.addr = htonl(nla_get_u32(node[TIPC_NLA_NODE_ADDR]));
+	node_info.up = htonl(nla_get_flag(node[TIPC_NLA_NODE_UP]));
+
+	return tipc_add_tlv(msg->rep, TIPC_TLV_NODE_INFO, &node_info,
+			    sizeof(node_info));
+}
+
+static int tipc_nl_compat_net_set(struct sk_buff *skb,
+				  struct tipc_nl_compat_msg *msg)
+{
+	u32 val;
+	struct nlattr *net;
+
+	val = ntohl(*(__be32 *)TLV_DATA(msg->req));
+
+	net = nla_nest_start(skb, TIPC_NLA_NET);
+	if (!net)
+		return -EMSGSIZE;
+
+	if (msg->cmd == TIPC_CMD_SET_NODE_ADDR) {
+		if (nla_put_u32(skb, TIPC_NLA_NET_ADDR, val))
+			return -EMSGSIZE;
+	} else if (msg->cmd == TIPC_CMD_SET_NETID) {
+		if (nla_put_u32(skb, TIPC_NLA_NET_ID, val))
+			return -EMSGSIZE;
+	}
+	nla_nest_end(skb, net);
+
+	return 0;
+}
+
+static int tipc_nl_compat_net_dump(struct tipc_nl_compat_msg *msg,
+				   struct nlattr **attrs)
+{
+	__be32 id;
+	struct nlattr *net[TIPC_NLA_NET_MAX + 1];
+
+	nla_parse_nested(net, TIPC_NLA_NET_MAX, attrs[TIPC_NLA_NET], NULL);
+	id = htonl(nla_get_u32(net[TIPC_NLA_NET_ID]));
+
+	return tipc_add_tlv(msg->rep, TIPC_TLV_UNSIGNED, &id, sizeof(id));
+}
+
+static int tipc_cmd_show_stats_compat(struct tipc_nl_compat_msg *msg)
+{
+	msg->rep = tipc_tlv_alloc(ULTRA_STRING_MAX_LEN);
+	if (!msg->rep)
+		return -ENOMEM;
+
+	tipc_tlv_init(msg->rep, TIPC_TLV_ULTRA_STRING);
+	tipc_tlv_sprintf(msg->rep, "TIPC version " TIPC_MOD_VER "\n");
+
+	return 0;
+}
+
+static int tipc_nl_compat_handle(struct tipc_nl_compat_msg *msg)
+{
+	struct tipc_nl_compat_cmd_dump dump;
+	struct tipc_nl_compat_cmd_doit doit;
+
+	memset(&dump, 0, sizeof(dump));
+	memset(&doit, 0, sizeof(doit));
+
+	switch (msg->cmd) {
+	case TIPC_CMD_NOOP:
+		msg->rep = tipc_tlv_alloc(0);
+		if (!msg->rep)
+			return -ENOMEM;
+		return 0;
+	case TIPC_CMD_GET_BEARER_NAMES:
+		msg->rep_size = MAX_BEARERS * TLV_SPACE(TIPC_MAX_BEARER_NAME);
+		dump.dumpit = tipc_nl_bearer_dump;
+		dump.format = tipc_nl_compat_bearer_dump;
+		return tipc_nl_compat_dumpit(&dump, msg);
+	case TIPC_CMD_ENABLE_BEARER:
+		msg->req_type = TIPC_TLV_BEARER_CONFIG;
+		doit.doit = tipc_nl_bearer_enable;
+		doit.transcode = tipc_nl_compat_bearer_enable;
+		return tipc_nl_compat_doit(&doit, msg);
+	case TIPC_CMD_DISABLE_BEARER:
+		msg->req_type = TIPC_TLV_BEARER_NAME;
+		doit.doit = tipc_nl_bearer_disable;
+		doit.transcode = tipc_nl_compat_bearer_disable;
+		return tipc_nl_compat_doit(&doit, msg);
+	case TIPC_CMD_SHOW_LINK_STATS:
+		msg->req_type = TIPC_TLV_LINK_NAME;
+		msg->rep_size = ULTRA_STRING_MAX_LEN;
+		msg->rep_type = TIPC_TLV_ULTRA_STRING;
+		dump.dumpit = tipc_nl_link_dump;
+		dump.format = tipc_nl_compat_link_stat_dump;
+		return tipc_nl_compat_dumpit(&dump, msg);
+	case TIPC_CMD_GET_LINKS:
+		msg->req_type = TIPC_TLV_NET_ADDR;
+		msg->rep_size = ULTRA_STRING_MAX_LEN;
+		dump.dumpit = tipc_nl_link_dump;
+		dump.format = tipc_nl_compat_link_dump;
+		return tipc_nl_compat_dumpit(&dump, msg);
+	case TIPC_CMD_SET_LINK_TOL:
+	case TIPC_CMD_SET_LINK_PRI:
+	case TIPC_CMD_SET_LINK_WINDOW:
+		msg->req_type =  TIPC_TLV_LINK_CONFIG;
+		doit.doit = tipc_nl_link_set;
+		doit.transcode = tipc_nl_compat_link_set;
+		return tipc_nl_compat_doit(&doit, msg);
+	case TIPC_CMD_RESET_LINK_STATS:
+		msg->req_type = TIPC_TLV_LINK_NAME;
+		doit.doit = tipc_nl_link_reset_stats;
+		doit.transcode = tipc_nl_compat_link_reset_stats;
+		return tipc_nl_compat_doit(&doit, msg);
+	case TIPC_CMD_SHOW_NAME_TABLE:
+		msg->req_type = TIPC_TLV_NAME_TBL_QUERY;
+		msg->rep_size = ULTRA_STRING_MAX_LEN;
+		msg->rep_type = TIPC_TLV_ULTRA_STRING;
+		dump.header = tipc_nl_compat_name_table_dump_header;
+		dump.dumpit = tipc_nl_name_table_dump;
+		dump.format = tipc_nl_compat_name_table_dump;
+		return tipc_nl_compat_dumpit(&dump, msg);
+	case TIPC_CMD_SHOW_PORTS:
+		msg->rep_size = ULTRA_STRING_MAX_LEN;
+		msg->rep_type = TIPC_TLV_ULTRA_STRING;
+		dump.dumpit = tipc_nl_sk_dump;
+		dump.format = tipc_nl_compat_sk_dump;
+		return tipc_nl_compat_dumpit(&dump, msg);
+	case TIPC_CMD_GET_MEDIA_NAMES:
+		msg->rep_size = MAX_MEDIA * TLV_SPACE(TIPC_MAX_MEDIA_NAME);
+		dump.dumpit = tipc_nl_media_dump;
+		dump.format = tipc_nl_compat_media_dump;
+		return tipc_nl_compat_dumpit(&dump, msg);
+	case TIPC_CMD_GET_NODES:
+		msg->rep_size = ULTRA_STRING_MAX_LEN;
+		dump.dumpit = tipc_nl_node_dump;
+		dump.format = tipc_nl_compat_node_dump;
+		return tipc_nl_compat_dumpit(&dump, msg);
+	case TIPC_CMD_SET_NODE_ADDR:
+		msg->req_type = TIPC_TLV_NET_ADDR;
+		doit.doit = tipc_nl_net_set;
+		doit.transcode = tipc_nl_compat_net_set;
+		return tipc_nl_compat_doit(&doit, msg);
+	case TIPC_CMD_SET_NETID:
+		msg->req_type = TIPC_TLV_UNSIGNED;
+		doit.doit = tipc_nl_net_set;
+		doit.transcode = tipc_nl_compat_net_set;
+		return tipc_nl_compat_doit(&doit, msg);
+	case TIPC_CMD_GET_NETID:
+		msg->rep_size = sizeof(u32);
+		dump.dumpit = tipc_nl_net_dump;
+		dump.format = tipc_nl_compat_net_dump;
+		return tipc_nl_compat_dumpit(&dump, msg);
+	case TIPC_CMD_SHOW_STATS:
+		return tipc_cmd_show_stats_compat(msg);
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static int tipc_nl_compat_recv(struct sk_buff *skb, struct genl_info *info)
+{
+	int err;
+	int len;
+	struct tipc_nl_compat_msg msg;
+	struct nlmsghdr *req_nlh;
+	struct nlmsghdr *rep_nlh;
+	struct tipc_genlmsghdr *req_userhdr = info->userhdr;
+	struct net *net = genl_info_net(info);
+
+	memset(&msg, 0, sizeof(msg));
+
+	req_nlh = (struct nlmsghdr *)skb->data;
+	msg.req = nlmsg_data(req_nlh) + GENL_HDRLEN + TIPC_GENL_HDRLEN;
+	msg.cmd = req_userhdr->cmd;
+	msg.dst_sk = info->dst_sk;
+
+	if ((msg.cmd & 0xC000) && (!netlink_net_capable(skb, CAP_NET_ADMIN))) {
+		msg.rep = tipc_get_err_tlv(TIPC_CFG_NOT_NET_ADMIN);
+		err = -EACCES;
+		goto send;
+	}
+
+	len = nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN);
+	if (TLV_GET_LEN(msg.req) && !TLV_OK(msg.req, len)) {
+		msg.rep = tipc_get_err_tlv(TIPC_CFG_NOT_SUPPORTED);
+		err = -EOPNOTSUPP;
+		goto send;
+	}
+
+	err = tipc_nl_compat_handle(&msg);
+	if (err == -EOPNOTSUPP)
+		msg.rep = tipc_get_err_tlv(TIPC_CFG_NOT_SUPPORTED);
+	else if (err == -EINVAL)
+		msg.rep = tipc_get_err_tlv(TIPC_CFG_TLV_ERROR);
+send:
+	if (!msg.rep)
+		return err;
+
+	len = nlmsg_total_size(GENL_HDRLEN + TIPC_GENL_HDRLEN);
+	skb_push(msg.rep, len);
+	rep_nlh = nlmsg_hdr(msg.rep);
+	memcpy(rep_nlh, info->nlhdr, len);
+	rep_nlh->nlmsg_len = msg.rep->len;
+	genlmsg_unicast(net, msg.rep, NETLINK_CB(skb).portid);
+
+	return err;
+}
+
+static struct genl_family tipc_genl_compat_family = {
+	.id		= GENL_ID_GENERATE,
+	.name		= TIPC_GENL_NAME,
+	.version	= TIPC_GENL_VERSION,
+	.hdrsize	= TIPC_GENL_HDRLEN,
+	.maxattr	= 0,
+	.netnsok	= true,
+};
+
+static struct genl_ops tipc_genl_compat_ops[] = {
+	{
+		.cmd		= TIPC_GENL_CMD,
+		.doit		= tipc_nl_compat_recv,
+	},
+};
+
+int tipc_netlink_compat_start(void)
+{
+	int res;
+
+	res = genl_register_family_with_ops(&tipc_genl_compat_family,
+					    tipc_genl_compat_ops);
+	if (res) {
+		pr_err("Failed to register legacy compat interface\n");
+		return res;
+	}
+
+	return 0;
+}
+
+void tipc_netlink_compat_stop(void)
+{
+	genl_unregister_family(&tipc_genl_compat_family);
+}
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 5781634e957d..22c059ad2999 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -35,21 +35,14 @@
  */
 
 #include "core.h"
-#include "config.h"
+#include "link.h"
 #include "node.h"
 #include "name_distr.h"
 #include "socket.h"
 
-#define NODE_HTABLE_SIZE 512
-
 static void node_lost_contact(struct tipc_node *n_ptr);
 static void node_established_contact(struct tipc_node *n_ptr);
-
-static struct hlist_head node_htable[NODE_HTABLE_SIZE];
-LIST_HEAD(tipc_node_list);
-static u32 tipc_num_nodes;
-static u32 tipc_num_links;
-static DEFINE_SPINLOCK(node_list_lock);
+static void tipc_node_delete(struct tipc_node *node);
 
 struct tipc_sock_conn {
 	u32 port;
@@ -58,6 +51,12 @@ struct tipc_sock_conn {
 	struct list_head list;
 };
 
+static const struct nla_policy tipc_nl_node_policy[TIPC_NLA_NODE_MAX + 1] = {
+	[TIPC_NLA_NODE_UNSPEC]		= { .type = NLA_UNSPEC },
+	[TIPC_NLA_NODE_ADDR]		= { .type = NLA_U32 },
+	[TIPC_NLA_NODE_UP]		= { .type = NLA_FLAG }
+};
+
 /*
  * A trivial power-of-two bitmask technique is used for speed, since this
  * operation is done for every incoming TIPC packet. The number of hash table
@@ -69,19 +68,39 @@ static unsigned int tipc_hashfn(u32 addr)
 	return addr & (NODE_HTABLE_SIZE - 1);
 }
 
+static void tipc_node_kref_release(struct kref *kref)
+{
+	struct tipc_node *node = container_of(kref, struct tipc_node, kref);
+
+	tipc_node_delete(node);
+}
+
+void tipc_node_put(struct tipc_node *node)
+{
+	kref_put(&node->kref, tipc_node_kref_release);
+}
+
+static void tipc_node_get(struct tipc_node *node)
+{
+	kref_get(&node->kref);
+}
+
 /*
  * tipc_node_find - locate specified node object, if it exists
  */
-struct tipc_node *tipc_node_find(u32 addr)
+struct tipc_node *tipc_node_find(struct net *net, u32 addr)
 {
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	struct tipc_node *node;
 
-	if (unlikely(!in_own_cluster_exact(addr)))
+	if (unlikely(!in_own_cluster_exact(net, addr)))
 		return NULL;
 
 	rcu_read_lock();
-	hlist_for_each_entry_rcu(node, &node_htable[tipc_hashfn(addr)], hash) {
+	hlist_for_each_entry_rcu(node, &tn->node_htable[tipc_hashfn(addr)],
+				 hash) {
 		if (node->addr == addr) {
+			tipc_node_get(node);
 			rcu_read_unlock();
 			return node;
 		}
@@ -90,78 +109,80 @@ struct tipc_node *tipc_node_find(u32 addr)
 	return NULL;
 }
 
-struct tipc_node *tipc_node_create(u32 addr)
+struct tipc_node *tipc_node_create(struct net *net, u32 addr)
 {
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	struct tipc_node *n_ptr, *temp_node;
 
-	spin_lock_bh(&node_list_lock);
-
+	spin_lock_bh(&tn->node_list_lock);
+	n_ptr = tipc_node_find(net, addr);
+	if (n_ptr)
+		goto exit;
 	n_ptr = kzalloc(sizeof(*n_ptr), GFP_ATOMIC);
 	if (!n_ptr) {
-		spin_unlock_bh(&node_list_lock);
 		pr_warn("Node creation failed, no memory\n");
-		return NULL;
+		goto exit;
 	}
-
 	n_ptr->addr = addr;
+	n_ptr->net = net;
+	kref_init(&n_ptr->kref);
 	spin_lock_init(&n_ptr->lock);
 	INIT_HLIST_NODE(&n_ptr->hash);
 	INIT_LIST_HEAD(&n_ptr->list);
-	INIT_LIST_HEAD(&n_ptr->nsub);
+	INIT_LIST_HEAD(&n_ptr->publ_list);
 	INIT_LIST_HEAD(&n_ptr->conn_sks);
-	__skb_queue_head_init(&n_ptr->waiting_sks);
-
-	hlist_add_head_rcu(&n_ptr->hash, &node_htable[tipc_hashfn(addr)]);
-
-	list_for_each_entry_rcu(temp_node, &tipc_node_list, list) {
+	__skb_queue_head_init(&n_ptr->bclink.deferdq);
+	hlist_add_head_rcu(&n_ptr->hash, &tn->node_htable[tipc_hashfn(addr)]);
+	list_for_each_entry_rcu(temp_node, &tn->node_list, list) {
 		if (n_ptr->addr < temp_node->addr)
 			break;
 	}
 	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_list_lock);
+	tipc_node_get(n_ptr);
+exit:
+	spin_unlock_bh(&tn->node_list_lock);
 	return n_ptr;
 }
 
-static void tipc_node_delete(struct tipc_node *n_ptr)
+static void tipc_node_delete(struct tipc_node *node)
 {
-	list_del_rcu(&n_ptr->list);
-	hlist_del_rcu(&n_ptr->hash);
-	kfree_rcu(n_ptr, rcu);
-
-	tipc_num_nodes--;
+	list_del_rcu(&node->list);
+	hlist_del_rcu(&node->hash);
+	kfree_rcu(node, rcu);
 }
 
-void tipc_node_stop(void)
+void tipc_node_stop(struct net *net)
 {
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	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);
+	spin_lock_bh(&tn->node_list_lock);
+	list_for_each_entry_safe(node, t_node, &tn->node_list, list)
+		tipc_node_put(node);
+	spin_unlock_bh(&tn->node_list_lock);
 }
 
-int tipc_node_add_conn(u32 dnode, u32 port, u32 peer_port)
+int tipc_node_add_conn(struct net *net, u32 dnode, u32 port, u32 peer_port)
 {
 	struct tipc_node *node;
 	struct tipc_sock_conn *conn;
+	int err = 0;
 
-	if (in_own_node(dnode))
+	if (in_own_node(net, dnode))
 		return 0;
 
-	node = tipc_node_find(dnode);
+	node = tipc_node_find(net, dnode);
 	if (!node) {
 		pr_warn("Connecting sock to node 0x%x failed\n", dnode);
 		return -EHOSTUNREACH;
 	}
 	conn = kmalloc(sizeof(*conn), GFP_ATOMIC);
-	if (!conn)
-		return -EHOSTUNREACH;
+	if (!conn) {
+		err = -EHOSTUNREACH;
+		goto exit;
+	}
 	conn->peer_node = dnode;
 	conn->port = port;
 	conn->peer_port = peer_port;
@@ -169,18 +190,20 @@ int tipc_node_add_conn(u32 dnode, u32 port, u32 peer_port)
 	tipc_node_lock(node);
 	list_add_tail(&conn->list, &node->conn_sks);
 	tipc_node_unlock(node);
-	return 0;
+exit:
+	tipc_node_put(node);
+	return err;
 }
 
-void tipc_node_remove_conn(u32 dnode, u32 port)
+void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port)
 {
 	struct tipc_node *node;
 	struct tipc_sock_conn *conn, *safe;
 
-	if (in_own_node(dnode))
+	if (in_own_node(net, dnode))
 		return;
 
-	node = tipc_node_find(dnode);
+	node = tipc_node_find(net, dnode);
 	if (!node)
 		return;
 
@@ -192,23 +215,7 @@ void tipc_node_remove_conn(u32 dnode, u32 port)
 		kfree(conn);
 	}
 	tipc_node_unlock(node);
-}
-
-void tipc_node_abort_sock_conns(struct list_head *conns)
-{
-	struct tipc_sock_conn *conn, *safe;
-	struct sk_buff *buf;
-
-	list_for_each_entry_safe(conn, safe, conns, list) {
-		buf = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, TIPC_CONN_MSG,
-				      SHORT_H_SIZE, 0, tipc_own_addr,
-				      conn->peer_node, conn->port,
-				      conn->peer_port, TIPC_ERR_NO_NODE);
-		if (likely(buf))
-			tipc_sk_rcv(buf);
-		list_del(&conn->list);
-		kfree(conn);
-	}
+	tipc_node_put(node);
 }
 
 /**
@@ -224,8 +231,8 @@ void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr)
 	n_ptr->action_flags |= TIPC_NOTIFY_LINK_UP;
 	n_ptr->link_id = l_ptr->peer_bearer_id << 16 | l_ptr->bearer_id;
 
-	pr_info("Established link <%s> on network plane %c\n",
-		l_ptr->name, l_ptr->net_plane);
+	pr_debug("Established link <%s> on network plane %c\n",
+		 l_ptr->name, l_ptr->net_plane);
 
 	if (!active[0]) {
 		active[0] = active[1] = l_ptr;
@@ -233,7 +240,7 @@ void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr)
 		goto exit;
 	}
 	if (l_ptr->priority < active[0]->priority) {
-		pr_info("New link <%s> becomes standby\n", l_ptr->name);
+		pr_debug("New link <%s> becomes standby\n", l_ptr->name);
 		goto exit;
 	}
 	tipc_link_dup_queue_xmit(active[0], l_ptr);
@@ -241,14 +248,14 @@ void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr)
 		active[0] = l_ptr;
 		goto exit;
 	}
-	pr_info("Old link <%s> becomes standby\n", active[0]->name);
+	pr_debug("Old link <%s> becomes standby\n", active[0]->name);
 	if (active[1] != active[0])
-		pr_info("Old link <%s> becomes standby\n", active[1]->name);
+		pr_debug("Old link <%s> becomes standby\n", active[1]->name);
 	active[0] = active[1] = l_ptr;
 exit:
 	/* Leave room for changeover header when returning 'mtu' to users: */
-	n_ptr->act_mtus[0] = active[0]->max_pkt - INT_H_SIZE;
-	n_ptr->act_mtus[1] = active[1]->max_pkt - INT_H_SIZE;
+	n_ptr->act_mtus[0] = active[0]->mtu - INT_H_SIZE;
+	n_ptr->act_mtus[1] = active[1]->mtu - INT_H_SIZE;
 }
 
 /**
@@ -283,6 +290,7 @@ 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_net *tn = net_generic(n_ptr->net, tipc_net_id);
 	struct tipc_link **active;
 
 	n_ptr->working_links--;
@@ -290,12 +298,12 @@ void tipc_node_link_down(struct tipc_node *n_ptr, struct tipc_link *l_ptr)
 	n_ptr->link_id = l_ptr->peer_bearer_id << 16 | l_ptr->bearer_id;
 
 	if (!tipc_link_is_active(l_ptr)) {
-		pr_info("Lost standby link <%s> on network plane %c\n",
-			l_ptr->name, l_ptr->net_plane);
+		pr_debug("Lost standby link <%s> on network plane %c\n",
+			 l_ptr->name, l_ptr->net_plane);
 		return;
 	}
-	pr_info("Lost link <%s> on network plane %c\n",
-		l_ptr->name, l_ptr->net_plane);
+	pr_debug("Lost link <%s> on network plane %c\n",
+		 l_ptr->name, l_ptr->net_plane);
 
 	active = &n_ptr->active_links[0];
 	if (active[0] == l_ptr)
@@ -311,13 +319,12 @@ void tipc_node_link_down(struct tipc_node *n_ptr, struct tipc_link *l_ptr)
 
 	/* Leave room for changeover header when returning 'mtu' to users: */
 	if (active[0]) {
-		n_ptr->act_mtus[0] = active[0]->max_pkt - INT_H_SIZE;
-		n_ptr->act_mtus[1] = active[1]->max_pkt - INT_H_SIZE;
+		n_ptr->act_mtus[0] = active[0]->mtu - INT_H_SIZE;
+		n_ptr->act_mtus[1] = active[1]->mtu - INT_H_SIZE;
 		return;
 	}
-
 	/* Loopback link went down? No fragmentation needed from now on. */
-	if (n_ptr->addr == tipc_own_addr) {
+	if (n_ptr->addr == tn->own_addr) {
 		n_ptr->act_mtus[0] = MAX_MSG_SIZE;
 		n_ptr->act_mtus[1] = MAX_MSG_SIZE;
 	}
@@ -336,9 +343,6 @@ 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->bearer_id] = l_ptr;
-	spin_lock_bh(&node_list_lock);
-	tipc_num_links++;
-	spin_unlock_bh(&node_list_lock);
 	n_ptr->link_cnt++;
 }
 
@@ -350,9 +354,6 @@ void tipc_node_detach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr)
 		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--;
 	}
 }
@@ -361,162 +362,71 @@ static void node_established_contact(struct tipc_node *n_ptr)
 {
 	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);
+	n_ptr->bclink.acked = tipc_bclink_get_last_sent(n_ptr->net);
+	tipc_bclink_add_node(n_ptr->net, n_ptr->addr);
 }
 
 static void node_lost_contact(struct tipc_node *n_ptr)
 {
 	char addr_string[16];
-	u32 i;
+	struct tipc_sock_conn *conn, *safe;
+	struct list_head *conns = &n_ptr->conn_sks;
+	struct sk_buff *skb;
+	struct tipc_net *tn = net_generic(n_ptr->net, tipc_net_id);
+	uint i;
 
-	pr_info("Lost contact with %s\n",
-		tipc_addr_string_fill(addr_string, n_ptr->addr));
+	pr_debug("Lost contact with %s\n",
+		 tipc_addr_string_fill(addr_string, n_ptr->addr));
 
 	/* Flush broadcast link info associated with lost node */
 	if (n_ptr->bclink.recv_permitted) {
-		kfree_skb_list(n_ptr->bclink.deferred_head);
-		n_ptr->bclink.deferred_size = 0;
+		__skb_queue_purge(&n_ptr->bclink.deferdq);
 
 		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);
+		tipc_bclink_remove_node(n_ptr->net, n_ptr->addr);
 		tipc_bclink_acknowledge(n_ptr, INVALID_LINK_SEQ);
 
 		n_ptr->bclink.recv_permitted = false;
 	}
 
-	/* Abort link changeover */
+	/* Abort any ongoing link failover */
 	for (i = 0; i < MAX_BEARERS; i++) {
 		struct tipc_link *l_ptr = n_ptr->links[i];
 		if (!l_ptr)
 			continue;
-		l_ptr->reset_checkpoint = l_ptr->next_in_no;
-		l_ptr->exp_msg_count = 0;
+		l_ptr->flags &= ~LINK_FAILINGOVER;
+		l_ptr->failover_checkpt = 0;
+		l_ptr->failover_pkts = 0;
+		kfree_skb(l_ptr->failover_skb);
+		l_ptr->failover_skb = NULL;
 		tipc_link_reset_fragments(l_ptr);
 	}
 
 	n_ptr->action_flags &= ~TIPC_WAIT_OWN_LINKS_DOWN;
 
-	/* 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)
-{
-	u32 domain;
-	struct sk_buff *buf;
-	struct tipc_node *n_ptr;
-	struct tipc_node_info node_info;
-	u32 payload_size;
-
-	if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_NET_ADDR))
-		return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR);
-
-	domain = ntohl(*(__be32 *)TLV_DATA(req_tlv_area));
-	if (!tipc_addr_domain_valid(domain))
-		return tipc_cfg_reply_error_string(TIPC_CFG_INVALID_VALUE
-						   " (network address)");
-
-	spin_lock_bh(&node_list_lock);
-	if (!tipc_num_nodes) {
-		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) {
-		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);
+	/* Prevent re-contact with node until cleanup is done */
+	n_ptr->action_flags |= TIPC_WAIT_PEER_LINKS_DOWN;
 
-	buf = tipc_cfg_reply_alloc(payload_size);
-	if (!buf)
-		return NULL;
+	/* Notify publications from this node */
+	n_ptr->action_flags |= TIPC_NOTIFY_NODE_DOWN;
 
-	/* Add TLVs for all nodes in scope */
-	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);
-		node_info.up = htonl(tipc_node_is_up(n_ptr));
-		tipc_cfg_append_tlv(buf, TIPC_TLV_NODE_INFO,
-				    &node_info, sizeof(node_info));
-	}
-	rcu_read_unlock();
-	return buf;
-}
-
-struct sk_buff *tipc_node_get_links(const void *req_tlv_area, int req_tlv_space)
-{
-	u32 domain;
-	struct sk_buff *buf;
-	struct tipc_node *n_ptr;
-	struct tipc_link_info link_info;
-	u32 payload_size;
-
-	if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_NET_ADDR))
-		return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR);
-
-	domain = ntohl(*(__be32 *)TLV_DATA(req_tlv_area));
-	if (!tipc_addr_domain_valid(domain))
-		return tipc_cfg_reply_error_string(TIPC_CFG_INVALID_VALUE
-						   " (network address)");
-
-	if (!tipc_own_addr)
-		return tipc_cfg_reply_none();
-
-	spin_lock_bh(&node_list_lock);
-	/* Get space for all unicast links + broadcast link */
-	payload_size = TLV_SPACE((sizeof(link_info)) * (tipc_num_links + 1));
-	if (payload_size > 32768u) {
-		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)
-		return NULL;
-
-	/* Add TLV for broadcast link */
-	link_info.dest = htonl(tipc_cluster_mask(tipc_own_addr));
-	link_info.up = htonl(1);
-	strlcpy(link_info.str, tipc_bclink_name, TIPC_MAX_LINK_NAME);
-	tipc_cfg_append_tlv(buf, TIPC_TLV_LINK_INFO, &link_info, sizeof(link_info));
-
-	/* Add TLVs for any other links in scope */
-	rcu_read_lock();
-	list_for_each_entry_rcu(n_ptr, &tipc_node_list, list) {
-		u32 i;
-
-		if (!tipc_in_scope(domain, n_ptr->addr))
-			continue;
-		tipc_node_lock(n_ptr);
-		for (i = 0; i < MAX_BEARERS; i++) {
-			if (!n_ptr->links[i])
-				continue;
-			link_info.dest = htonl(n_ptr->addr);
-			link_info.up = htonl(tipc_link_is_up(n_ptr->links[i]));
-			strcpy(link_info.str, n_ptr->links[i]->name);
-			tipc_cfg_append_tlv(buf, TIPC_TLV_LINK_INFO,
-					    &link_info, sizeof(link_info));
+	/* Notify sockets connected to node */
+	list_for_each_entry_safe(conn, safe, conns, list) {
+		skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, TIPC_CONN_MSG,
+				      SHORT_H_SIZE, 0, tn->own_addr,
+				      conn->peer_node, conn->port,
+				      conn->peer_port, TIPC_ERR_NO_NODE);
+		if (likely(skb)) {
+			skb_queue_tail(n_ptr->inputq, skb);
+			n_ptr->action_flags |= TIPC_MSG_EVT;
 		}
-		tipc_node_unlock(n_ptr);
+		list_del(&conn->list);
+		kfree(conn);
 	}
-	rcu_read_unlock();
-	return buf;
 }
 
 /**
@@ -528,76 +438,184 @@ struct sk_buff *tipc_node_get_links(const void *req_tlv_area, int req_tlv_space)
  *
  * Returns 0 on success
  */
-int tipc_node_get_linkname(u32 bearer_id, u32 addr, char *linkname, size_t len)
+int tipc_node_get_linkname(struct net *net, u32 bearer_id, u32 addr,
+			   char *linkname, size_t len)
 {
 	struct tipc_link *link;
-	struct tipc_node *node = tipc_node_find(addr);
+	int err = -EINVAL;
+	struct tipc_node *node = tipc_node_find(net, addr);
+
+	if (!node)
+		return err;
+
+	if (bearer_id >= MAX_BEARERS)
+		goto exit;
 
-	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;
+		err = 0;
 	}
+exit:
 	tipc_node_unlock(node);
-	return -EINVAL;
+	tipc_node_put(node);
+	return err;
 }
 
 void tipc_node_unlock(struct tipc_node *node)
 {
-	LIST_HEAD(nsub_list);
-	LIST_HEAD(conn_sks);
-	struct sk_buff_head waiting_sks;
+	struct net *net = node->net;
 	u32 addr = 0;
-	int flags = node->action_flags;
+	u32 flags = node->action_flags;
 	u32 link_id = 0;
+	struct list_head *publ_list;
+	struct sk_buff_head *inputq = node->inputq;
+	struct sk_buff_head *namedq;
 
-	if (likely(!flags)) {
+	if (likely(!flags || (flags == TIPC_MSG_EVT))) {
+		node->action_flags = 0;
 		spin_unlock_bh(&node->lock);
+		if (flags == TIPC_MSG_EVT)
+			tipc_sk_rcv(net, inputq);
 		return;
 	}
 
 	addr = node->addr;
 	link_id = node->link_id;
-	__skb_queue_head_init(&waiting_sks);
+	namedq = node->namedq;
+	publ_list = &node->publ_list;
 
-	if (flags & TIPC_WAKEUP_USERS)
-		skb_queue_splice_init(&node->waiting_sks, &waiting_sks);
-
-	if (flags & TIPC_NOTIFY_NODE_DOWN) {
-		list_replace_init(&node->nsub, &nsub_list);
-		list_replace_init(&node->conn_sks, &conn_sks);
-	}
-	node->action_flags &= ~(TIPC_WAKEUP_USERS | TIPC_NOTIFY_NODE_DOWN |
-				TIPC_NOTIFY_NODE_UP | TIPC_NOTIFY_LINK_UP |
-				TIPC_NOTIFY_LINK_DOWN |
-				TIPC_WAKEUP_BCAST_USERS);
+	node->action_flags &= ~(TIPC_MSG_EVT |
+				TIPC_NOTIFY_NODE_DOWN | TIPC_NOTIFY_NODE_UP |
+				TIPC_NOTIFY_LINK_DOWN | TIPC_NOTIFY_LINK_UP |
+				TIPC_WAKEUP_BCAST_USERS | TIPC_BCAST_MSG_EVT |
+				TIPC_NAMED_MSG_EVT | TIPC_BCAST_RESET);
 
 	spin_unlock_bh(&node->lock);
 
-	while (!skb_queue_empty(&waiting_sks))
-		tipc_sk_rcv(__skb_dequeue(&waiting_sks));
-
-	if (!list_empty(&conn_sks))
-		tipc_node_abort_sock_conns(&conn_sks);
-
-	if (!list_empty(&nsub_list))
-		tipc_nodesub_notify(&nsub_list);
+	if (flags & TIPC_NOTIFY_NODE_DOWN)
+		tipc_publ_notify(net, publ_list, addr);
 
 	if (flags & TIPC_WAKEUP_BCAST_USERS)
-		tipc_bclink_wakeup_users();
+		tipc_bclink_wakeup_users(net);
 
 	if (flags & TIPC_NOTIFY_NODE_UP)
-		tipc_named_node_up(addr);
+		tipc_named_node_up(net, addr);
 
 	if (flags & TIPC_NOTIFY_LINK_UP)
-		tipc_nametbl_publish(TIPC_LINK_STATE, addr, addr,
+		tipc_nametbl_publish(net, TIPC_LINK_STATE, addr, addr,
 				     TIPC_NODE_SCOPE, link_id, addr);
 
 	if (flags & TIPC_NOTIFY_LINK_DOWN)
-		tipc_nametbl_withdraw(TIPC_LINK_STATE, addr,
+		tipc_nametbl_withdraw(net, TIPC_LINK_STATE, addr,
 				      link_id, addr);
+
+	if (flags & TIPC_MSG_EVT)
+		tipc_sk_rcv(net, inputq);
+
+	if (flags & TIPC_NAMED_MSG_EVT)
+		tipc_named_rcv(net, namedq);
+
+	if (flags & TIPC_BCAST_MSG_EVT)
+		tipc_bclink_input(net);
+
+	if (flags & TIPC_BCAST_RESET)
+		tipc_link_reset_all(node);
+}
+
+/* Caller should hold node lock for the passed node */
+static int __tipc_nl_add_node(struct tipc_nl_msg *msg, struct tipc_node *node)
+{
+	void *hdr;
+	struct nlattr *attrs;
+
+	hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family,
+			  NLM_F_MULTI, TIPC_NL_NODE_GET);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	attrs = nla_nest_start(msg->skb, TIPC_NLA_NODE);
+	if (!attrs)
+		goto msg_full;
+
+	if (nla_put_u32(msg->skb, TIPC_NLA_NODE_ADDR, node->addr))
+		goto attr_msg_full;
+	if (tipc_node_is_up(node))
+		if (nla_put_flag(msg->skb, TIPC_NLA_NODE_UP))
+			goto attr_msg_full;
+
+	nla_nest_end(msg->skb, attrs);
+	genlmsg_end(msg->skb, hdr);
+
+	return 0;
+
+attr_msg_full:
+	nla_nest_cancel(msg->skb, attrs);
+msg_full:
+	genlmsg_cancel(msg->skb, hdr);
+
+	return -EMSGSIZE;
+}
+
+int tipc_nl_node_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	int err;
+	struct net *net = sock_net(skb->sk);
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	int done = cb->args[0];
+	int last_addr = cb->args[1];
+	struct tipc_node *node;
+	struct tipc_nl_msg msg;
+
+	if (done)
+		return 0;
+
+	msg.skb = skb;
+	msg.portid = NETLINK_CB(cb->skb).portid;
+	msg.seq = cb->nlh->nlmsg_seq;
+
+	rcu_read_lock();
+	if (last_addr) {
+		node = tipc_node_find(net, last_addr);
+		if (!node) {
+			rcu_read_unlock();
+			/* We never set seq or call nl_dump_check_consistent()
+			 * this means that setting prev_seq here will cause the
+			 * consistence check to fail in the netlink callback
+			 * handler. Resulting in the NLMSG_DONE message having
+			 * the NLM_F_DUMP_INTR flag set if the node state
+			 * changed while we released the lock.
+			 */
+			cb->prev_seq = 1;
+			return -EPIPE;
+		}
+		tipc_node_put(node);
+	}
+
+	list_for_each_entry_rcu(node, &tn->node_list, list) {
+		if (last_addr) {
+			if (node->addr == last_addr)
+				last_addr = 0;
+			else
+				continue;
+		}
+
+		tipc_node_lock(node);
+		err = __tipc_nl_add_node(&msg, node);
+		if (err) {
+			last_addr = node->addr;
+			tipc_node_unlock(node);
+			goto out;
+		}
+
+		tipc_node_unlock(node);
+	}
+	done = 1;
+out:
+	cb->args[0] = done;
+	cb->args[1] = last_addr;
+	rcu_read_unlock();
+
+	return skb->len;
 }
diff --git a/net/tipc/node.h b/net/tipc/node.h
index 04e91458bb29..02d5c20dc551 100644
--- a/net/tipc/node.h
+++ b/net/tipc/node.h
@@ -1,7 +1,7 @@
 /*
  * net/tipc/node.h: Include file for TIPC node management routines
  *
- * Copyright (c) 2000-2006, Ericsson AB
+ * Copyright (c) 2000-2006, 2014-2015, Ericsson AB
  * Copyright (c) 2005, 2010-2014, Wind River Systems
  * All rights reserved.
  *
@@ -37,16 +37,15 @@
 #ifndef _TIPC_NODE_H
 #define _TIPC_NODE_H
 
-#include "node_subscr.h"
 #include "addr.h"
 #include "net.h"
 #include "bearer.h"
 #include "msg.h"
 
-/*
- * Out-of-range value for node signature
- */
-#define INVALID_NODE_SIG 0x10000
+/* Out-of-range value for node signature */
+#define INVALID_NODE_SIG	0x10000
+
+#define NODE_HTABLE_SIZE	512
 
 /* Flags used to take different actions according to flag type
  * TIPC_WAIT_PEER_LINKS_DOWN: wait to see that peer's links are down
@@ -56,14 +55,17 @@
  * TIPC_DISTRIBUTE_NAME: publish or withdraw link state name type
  */
 enum {
+	TIPC_MSG_EVT                    = 1,
 	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),
-	TIPC_WAKEUP_USERS		= (1 << 5),
-	TIPC_WAKEUP_BCAST_USERS		= (1 << 6),
-	TIPC_NOTIFY_LINK_UP		= (1 << 7),
-	TIPC_NOTIFY_LINK_DOWN		= (1 << 8)
+	TIPC_WAKEUP_BCAST_USERS		= (1 << 5),
+	TIPC_NOTIFY_LINK_UP		= (1 << 6),
+	TIPC_NOTIFY_LINK_DOWN		= (1 << 7),
+	TIPC_NAMED_MSG_EVT		= (1 << 8),
+	TIPC_BCAST_MSG_EVT		= (1 << 9),
+	TIPC_BCAST_RESET		= (1 << 10)
 };
 
 /**
@@ -72,10 +74,9 @@ enum {
  * @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
+ * @deferred_queue: deferred queue saved OOS b'cast message received from node
  * @reasm_buf: broadcast reassembly queue head from node
+ * @inputq_map: bitmap indicating which inqueues should be kicked
  * @recv_permitted: true if node is allowed to receive b'cast messages
  */
 struct tipc_node_bclink {
@@ -84,17 +85,22 @@ struct tipc_node_bclink {
 	u32 last_sent;
 	u32 oos_state;
 	u32 deferred_size;
-	struct sk_buff *deferred_head;
-	struct sk_buff *deferred_tail;
+	struct sk_buff_head deferdq;
 	struct sk_buff *reasm_buf;
+	int inputq_map;
 	bool recv_permitted;
 };
 
 /**
  * struct tipc_node - TIPC node structure
  * @addr: network address of node
+ * @ref: reference counter to node object
  * @lock: spinlock governing access to structure
+ * @net: the applicable net namespace
  * @hash: links to adjacent nodes in unsorted hash chain
+ * @inputq: pointer to input queue containing messages for msg event
+ * @namedq: pointer to name table input queue with name table messages
+ * @curr_link: the link holding the node lock, if any
  * @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
@@ -102,48 +108,53 @@ struct tipc_node_bclink {
  * @list: links to adjacent nodes in sorted list of cluster's nodes
  * @working_links: number of working links to node (both active and standby)
  * @link_cnt: number of links to node
+ * @capabilities: bitmap, indicating peer node's functional capabilities
  * @signature: node instance identifier
  * @link_id: local and remote bearer ids of changing link, if any
- * @nsub: list of "node down" subscriptions monitoring node
+ * @publ_list: list of publications
  * @rcu: rcu struct for tipc_node
  */
 struct tipc_node {
 	u32 addr;
+	struct kref kref;
 	spinlock_t lock;
+	struct net *net;
 	struct hlist_node hash;
+	struct sk_buff_head *inputq;
+	struct sk_buff_head *namedq;
 	struct tipc_link *active_links[2];
 	u32 act_mtus[2];
 	struct tipc_link *links[MAX_BEARERS];
-	unsigned int action_flags;
+	int action_flags;
 	struct tipc_node_bclink bclink;
 	struct list_head list;
 	int link_cnt;
-	int working_links;
+	u16 working_links;
+	u16 capabilities;
 	u32 signature;
 	u32 link_id;
-	struct list_head nsub;
-	struct sk_buff_head waiting_sks;
+	struct list_head publ_list;
 	struct list_head conn_sks;
 	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_stop(void);
+struct tipc_node *tipc_node_find(struct net *net, u32 addr);
+void tipc_node_put(struct tipc_node *node);
+struct tipc_node *tipc_node_create(struct net *net, u32 addr);
+void tipc_node_stop(struct net *net);
 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_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);
+int tipc_node_get_linkname(struct net *net, u32 bearer_id, u32 node,
+			   char *linkname, size_t len);
 void tipc_node_unlock(struct tipc_node *node);
-int tipc_node_add_conn(u32 dnode, u32 port, u32 peer_port);
-void tipc_node_remove_conn(u32 dnode, u32 port);
+int tipc_node_add_conn(struct net *net, u32 dnode, u32 port, u32 peer_port);
+void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port);
+
+int tipc_nl_node_dump(struct sk_buff *skb, struct netlink_callback *cb);
 
 static inline void tipc_node_lock(struct tipc_node *node)
 {
@@ -156,17 +167,19 @@ static inline bool tipc_node_blocked(struct tipc_node *node)
 		TIPC_NOTIFY_NODE_DOWN | TIPC_WAIT_OWN_LINKS_DOWN));
 }
 
-static inline uint tipc_node_get_mtu(u32 addr, u32 selector)
+static inline uint tipc_node_get_mtu(struct net *net, u32 addr, u32 selector)
 {
 	struct tipc_node *node;
 	u32 mtu;
 
-	node = tipc_node_find(addr);
+	node = tipc_node_find(net, addr);
 
-	if (likely(node))
+	if (likely(node)) {
 		mtu = node->act_mtus[selector & 1];
-	else
+		tipc_node_put(node);
+	} else {
 		mtu = MAX_MSG_SIZE;
+	}
 
 	return mtu;
 }
diff --git a/net/tipc/node_subscr.c b/net/tipc/node_subscr.c
deleted file mode 100644
index 2d13eea8574a..000000000000
--- a/net/tipc/node_subscr.c
+++ /dev/null
@@ -1,96 +0,0 @@
-/*
- * net/tipc/node_subscr.c: TIPC "node down" subscription handling
- *
- * Copyright (c) 1995-2006, Ericsson AB
- * Copyright (c) 2005, 2010-2011, 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"
-#include "node_subscr.h"
-#include "node.h"
-
-/**
- * tipc_nodesub_subscribe - create "node down" subscription for specified node
- */
-void tipc_nodesub_subscribe(struct tipc_node_subscr *node_sub, u32 addr,
-			    void *usr_handle, net_ev_handler handle_down)
-{
-	if (in_own_node(addr)) {
-		node_sub->node = NULL;
-		return;
-	}
-
-	node_sub->node = tipc_node_find(addr);
-	if (!node_sub->node) {
-		pr_warn("Node subscription rejected, unknown node 0x%x\n",
-			addr);
-		return;
-	}
-	node_sub->handle_node_down = handle_down;
-	node_sub->usr_handle = usr_handle;
-
-	tipc_node_lock(node_sub->node);
-	list_add_tail(&node_sub->nodesub_list, &node_sub->node->nsub);
-	tipc_node_unlock(node_sub->node);
-}
-
-/**
- * tipc_nodesub_unsubscribe - cancel "node down" subscription (if any)
- */
-void tipc_nodesub_unsubscribe(struct tipc_node_subscr *node_sub)
-{
-	if (!node_sub->node)
-		return;
-
-	tipc_node_lock(node_sub->node);
-	list_del_init(&node_sub->nodesub_list);
-	tipc_node_unlock(node_sub->node);
-}
-
-/**
- * tipc_nodesub_notify - notify subscribers that a node is unreachable
- *
- * Note: node is locked by caller
- */
-void tipc_nodesub_notify(struct list_head *nsub_list)
-{
-	struct tipc_node_subscr *ns, *safe;
-	net_ev_handler handle_node_down;
-
-	list_for_each_entry_safe(ns, safe, nsub_list, nodesub_list) {
-		handle_node_down = ns->handle_node_down;
-		if (handle_node_down) {
-			ns->handle_node_down = NULL;
-			handle_node_down(ns->usr_handle);
-		}
-	}
-}
diff --git a/net/tipc/node_subscr.h b/net/tipc/node_subscr.h
deleted file mode 100644
index d91b8cc81e3d..000000000000
--- a/net/tipc/node_subscr.h
+++ /dev/null
@@ -1,63 +0,0 @@
-/*
- * net/tipc/node_subscr.h: Include file for TIPC "node down" subscription handling
- *
- * Copyright (c) 1995-2006, Ericsson AB
- * Copyright (c) 2005, 2010-2011, 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.
- */
-
-#ifndef _TIPC_NODE_SUBSCR_H
-#define _TIPC_NODE_SUBSCR_H
-
-#include "addr.h"
-
-typedef void (*net_ev_handler) (void *usr_handle);
-
-/**
- * struct tipc_node_subscr - "node down" subscription entry
- * @node: ptr to node structure of interest (or NULL, if none)
- * @handle_node_down: routine to invoke when node fails
- * @usr_handle: argument to pass to routine when node fails
- * @nodesub_list: adjacent entries in list of subscriptions for the node
- */
-struct tipc_node_subscr {
-	struct tipc_node *node;
-	net_ev_handler handle_node_down;
-	void *usr_handle;
-	struct list_head nodesub_list;
-};
-
-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 list_head *nsub_list);
-
-#endif
diff --git a/net/tipc/server.c b/net/tipc/server.c
index a538a02f869b..77ff03ed1e18 100644
--- a/net/tipc/server.c
+++ b/net/tipc/server.c
@@ -35,12 +35,15 @@
 
 #include "server.h"
 #include "core.h"
+#include "socket.h"
 #include <net/sock.h>
+#include <linux/module.h>
 
 /* Number of messages to send before rescheduling */
 #define MAX_SEND_MSG_COUNT	25
 #define MAX_RECV_MSG_COUNT	25
 #define CF_CONNECTED		1
+#define CF_SERVER		2
 
 #define sock2con(x) ((struct tipc_conn *)(x)->sk_user_data)
 
@@ -87,9 +90,19 @@ 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 sockaddr_tipc *saddr = con->server->saddr;
+	struct socket *sock = con->sock;
+	struct sock *sk;
 
-	if (con->sock) {
-		tipc_sock_release_local(con->sock);
+	if (sock) {
+		sk = sock->sk;
+		if (test_bit(CF_SERVER, &con->flags)) {
+			__module_get(sock->ops->owner);
+			__module_get(sk->sk_prot_creator->owner);
+		}
+		saddr->scope = -TIPC_NODE_SCOPE;
+		kernel_bind(sock, (struct sockaddr *)saddr, sizeof(*saddr));
+		sock_release(sock);
 		con->sock = NULL;
 	}
 
@@ -255,7 +268,8 @@ static int tipc_receive_from_sock(struct tipc_conn *con)
 		goto out_close;
 	}
 
-	s->tipc_conn_recvmsg(con->conid, &addr, con->usr_data, buf, ret);
+	s->tipc_conn_recvmsg(sock_net(con->sock->sk), con->conid, &addr,
+			     con->usr_data, buf, ret);
 
 	kmem_cache_free(s->rcvbuf_cache, buf);
 
@@ -279,7 +293,7 @@ static int tipc_accept_from_sock(struct tipc_conn *con)
 	struct tipc_conn *newcon;
 	int ret;
 
-	ret = tipc_sock_accept_local(sock, &newsock, O_NONBLOCK);
+	ret = kernel_accept(sock, &newsock, O_NONBLOCK);
 	if (ret < 0)
 		return ret;
 
@@ -307,7 +321,7 @@ static struct socket *tipc_create_listen_sock(struct tipc_conn *con)
 	struct socket *sock = NULL;
 	int ret;
 
-	ret = tipc_sock_create_local(s->type, &sock);
+	ret = __sock_create(s->net, AF_TIPC, SOCK_SEQPACKET, 0, &sock, 1);
 	if (ret < 0)
 		return NULL;
 	ret = kernel_setsockopt(sock, SOL_TIPC, TIPC_IMPORTANCE,
@@ -335,11 +349,31 @@ static struct socket *tipc_create_listen_sock(struct tipc_conn *con)
 		pr_err("Unknown socket type %d\n", s->type);
 		goto create_err;
 	}
+
+	/* As server's listening socket owner and creator is the same module,
+	 * we have to decrease TIPC module reference count to guarantee that
+	 * it remains zero after the server socket is created, otherwise,
+	 * executing "rmmod" command is unable to make TIPC module deleted
+	 * after TIPC module is inserted successfully.
+	 *
+	 * However, the reference count is ever increased twice in
+	 * sock_create_kern(): one is to increase the reference count of owner
+	 * of TIPC socket's proto_ops struct; another is to increment the
+	 * reference count of owner of TIPC proto struct. Therefore, we must
+	 * decrement the module reference count twice to ensure that it keeps
+	 * zero after server's listening socket is created. Of course, we
+	 * must bump the module reference count twice as well before the socket
+	 * is closed.
+	 */
+	module_put(sock->ops->owner);
+	module_put(sock->sk->sk_prot_creator->owner);
+	set_bit(CF_SERVER, &con->flags);
+
 	return sock;
 
 create_err:
+	kernel_sock_shutdown(sock, SHUT_RDWR);
 	sock_release(sock);
-	con->sock = NULL;
 	return NULL;
 }
 
diff --git a/net/tipc/server.h b/net/tipc/server.h
index be817b0b547e..9015faedb1b0 100644
--- a/net/tipc/server.h
+++ b/net/tipc/server.h
@@ -36,7 +36,9 @@
 #ifndef _TIPC_SERVER_H
 #define _TIPC_SERVER_H
 
-#include "core.h"
+#include <linux/idr.h>
+#include <linux/tipc.h>
+#include <net/net_namespace.h>
 
 #define TIPC_SERVER_NAME_LEN	32
 
@@ -45,6 +47,7 @@
  * @conn_idr: identifier set of connection
  * @idr_lock: protect the connection identifier set
  * @idr_in_use: amount of allocated identifier entry
+ * @net: network namspace instance
  * @rcvbuf_cache: memory cache of server receive buffer
  * @rcv_wq: receive workqueue
  * @send_wq: send workqueue
@@ -61,16 +64,18 @@ struct tipc_server {
 	struct idr conn_idr;
 	spinlock_t idr_lock;
 	int idr_in_use;
+	struct net *net;
 	struct kmem_cache *rcvbuf_cache;
 	struct workqueue_struct *rcv_wq;
 	struct workqueue_struct *send_wq;
 	int max_rcvbuf_size;
-	void *(*tipc_conn_new) (int conid);
-	void (*tipc_conn_shutdown) (int conid, void *usr_data);
-	void (*tipc_conn_recvmsg) (int conid, struct sockaddr_tipc *addr,
-				   void *usr_data, void *buf, size_t len);
+	void *(*tipc_conn_new)(int conid);
+	void (*tipc_conn_shutdown)(int conid, void *usr_data);
+	void (*tipc_conn_recvmsg)(struct net *net, int conid,
+				  struct sockaddr_tipc *addr, void *usr_data,
+				  void *buf, size_t len);
 	struct sockaddr_tipc *saddr;
-	const char name[TIPC_SERVER_NAME_LEN];
+	char name[TIPC_SERVER_NAME_LEN];
 	int imp;
 	int type;
 };
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 51bddc236a15..f485600c4507 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, 2012-2014, Ericsson AB
+ * Copyright (c) 2001-2007, 2012-2015, Ericsson AB
  * Copyright (c) 2004-2008, 2010-2013, Wind River Systems
  * All rights reserved.
  *
@@ -34,22 +34,24 @@
  * POSSIBILITY OF SUCH DAMAGE.
  */
 
+#include <linux/rhashtable.h>
 #include "core.h"
 #include "name_table.h"
 #include "node.h"
 #include "link.h"
-#include <linux/export.h>
-#include "config.h"
+#include "name_distr.h"
 #include "socket.h"
 
-#define SS_LISTENING	-1	/* socket is listening */
-#define SS_READY	-2	/* socket is connectionless */
+#define SS_LISTENING		-1	/* socket is listening */
+#define SS_READY		-2	/* socket is connectionless */
 
-#define CONN_TIMEOUT_DEFAULT  8000	/* default connect timeout = 8s */
-#define CONN_PROBING_INTERVAL 3600000	/* [ms] => 1 h */
-#define TIPC_FWD_MSG	      1
-#define TIPC_CONN_OK          0
-#define TIPC_CONN_PROBING     1
+#define CONN_TIMEOUT_DEFAULT	8000	/* default connect timeout = 8s */
+#define CONN_PROBING_INTERVAL	msecs_to_jiffies(3600000)  /* [ms] => 1 h */
+#define TIPC_FWD_MSG		1
+#define TIPC_CONN_OK		0
+#define TIPC_CONN_PROBING	1
+#define TIPC_MAX_PORT		0xffffffff
+#define TIPC_MIN_PORT		1
 
 /**
  * struct tipc_sock - TIPC socket structure
@@ -59,21 +61,21 @@
  * @conn_instance: TIPC instance used when connection was established
  * @published: non-zero if port has one or more associated names
  * @max_pkt: maximum packet size "hint" used when building messages sent by port
- * @ref: unique reference to port in TIPC object registry
+ * @portid: unique port identity in TIPC socket hash table
  * @phdr: preformatted message header used when sending messages
  * @port_list: adjacent ports in TIPC's global list of ports
  * @publications: list of publications for port
  * @pub_count: total # of publications port has made during its lifetime
  * @probing_state:
- * @probing_interval:
- * @timer:
- * @port: port - interacts with 'sk' and with the rest of the TIPC stack
- * @peer_name: the peer of the connection, if any
+ * @probing_intv:
  * @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
  * @link_cong: non-zero if owner must sleep because of link congestion
  * @sent_unacked: # messages sent by socket, and not yet acked by peer
  * @rcv_unacked: # messages read by user, but not yet acked back to peer
+ * @remote: 'connected' peer for dgram/rdm
+ * @node: hash table node
+ * @rcu: rcu struct for tipc_sock
  */
 struct tipc_sock {
 	struct sock sk;
@@ -82,19 +84,21 @@ struct tipc_sock {
 	u32 conn_instance;
 	int published;
 	u32 max_pkt;
-	u32 ref;
+	u32 portid;
 	struct tipc_msg phdr;
 	struct list_head sock_list;
 	struct list_head publications;
 	u32 pub_count;
 	u32 probing_state;
-	u32 probing_interval;
-	struct timer_list timer;
+	unsigned long probing_intv;
 	uint conn_timeout;
 	atomic_t dupl_rcvcnt;
 	bool link_cong;
 	uint sent_unacked;
 	uint rcv_unacked;
+	struct sockaddr_tipc remote;
+	struct rhash_head node;
+	struct rcu_head rcu;
 };
 
 static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb);
@@ -103,23 +107,32 @@ static void tipc_write_space(struct sock *sk);
 static int tipc_release(struct socket *sock);
 static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags);
 static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p);
-static void tipc_sk_timeout(unsigned long ref);
+static void tipc_sk_timeout(unsigned long data);
 static int tipc_sk_publish(struct tipc_sock *tsk, uint scope,
 			   struct tipc_name_seq const *seq);
 static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope,
 			    struct tipc_name_seq const *seq);
-static u32 tipc_sk_ref_acquire(struct tipc_sock *tsk);
-static void tipc_sk_ref_discard(u32 ref);
-static struct tipc_sock *tipc_sk_get(u32 ref);
-static struct tipc_sock *tipc_sk_get_next(u32 *ref);
-static void tipc_sk_put(struct tipc_sock *tsk);
+static struct tipc_sock *tipc_sk_lookup(struct net *net, u32 portid);
+static int tipc_sk_insert(struct tipc_sock *tsk);
+static void tipc_sk_remove(struct tipc_sock *tsk);
+static int __tipc_send_stream(struct socket *sock, struct msghdr *m,
+			      size_t dsz);
+static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz);
 
 static const struct proto_ops packet_ops;
 static const struct proto_ops stream_ops;
 static const struct proto_ops msg_ops;
-
 static struct proto tipc_proto;
-static struct proto tipc_proto_kern;
+
+static const struct nla_policy tipc_nl_sock_policy[TIPC_NLA_SOCK_MAX + 1] = {
+	[TIPC_NLA_SOCK_UNSPEC]		= { .type = NLA_UNSPEC },
+	[TIPC_NLA_SOCK_ADDR]		= { .type = NLA_U32 },
+	[TIPC_NLA_SOCK_REF]		= { .type = NLA_U32 },
+	[TIPC_NLA_SOCK_CON]		= { .type = NLA_NESTED },
+	[TIPC_NLA_SOCK_HAS_PUBL]	= { .type = NLA_FLAG }
+};
+
+static const struct rhashtable_params tsk_rht_params;
 
 /*
  * Revised TIPC socket locking policy:
@@ -166,6 +179,11 @@ static struct proto tipc_proto_kern;
  *   - port reference
  */
 
+static u32 tsk_own_node(struct tipc_sock *tsk)
+{
+	return msg_prevnode(&tsk->phdr);
+}
+
 static u32 tsk_peer_node(struct tipc_sock *tsk)
 {
 	return msg_destnode(&tsk->phdr);
@@ -236,12 +254,13 @@ static void tsk_advance_rx_queue(struct sock *sk)
  */
 static void tsk_rej_rx_queue(struct sock *sk)
 {
-	struct sk_buff *buf;
+	struct sk_buff *skb;
 	u32 dnode;
+	u32 own_node = tsk_own_node(tipc_sk(sk));
 
-	while ((buf = __skb_dequeue(&sk->sk_receive_queue))) {
-		if (tipc_msg_reverse(buf, &dnode, TIPC_ERR_NO_PORT))
-			tipc_link_xmit(buf, dnode, 0);
+	while ((skb = __skb_dequeue(&sk->sk_receive_queue))) {
+		if (tipc_msg_reverse(own_node, skb, &dnode, TIPC_ERR_NO_PORT))
+			tipc_link_xmit_skb(sock_net(sk), skb, dnode, 0);
 	}
 }
 
@@ -252,6 +271,7 @@ static void tsk_rej_rx_queue(struct sock *sk)
  */
 static bool tsk_peer_msg(struct tipc_sock *tsk, struct tipc_msg *msg)
 {
+	struct tipc_net *tn = net_generic(sock_net(&tsk->sk), tipc_net_id);
 	u32 peer_port = tsk_peer_port(tsk);
 	u32 orig_node;
 	u32 peer_node;
@@ -268,10 +288,10 @@ static bool tsk_peer_msg(struct tipc_sock *tsk, struct tipc_msg *msg)
 	if (likely(orig_node == peer_node))
 		return true;
 
-	if (!orig_node && (peer_node == tipc_own_addr))
+	if (!orig_node && (peer_node == tn->own_addr))
 		return true;
 
-	if (!peer_node && (orig_node == tipc_own_addr))
+	if (!peer_node && (orig_node == tn->own_addr))
 		return true;
 
 	return false;
@@ -292,12 +312,12 @@ static bool tsk_peer_msg(struct tipc_sock *tsk, struct tipc_msg *msg)
 static int tipc_sk_create(struct net *net, struct socket *sock,
 			  int protocol, int kern)
 {
+	struct tipc_net *tn;
 	const struct proto_ops *ops;
 	socket_state state;
 	struct sock *sk;
 	struct tipc_sock *tsk;
 	struct tipc_msg *msg;
-	u32 ref;
 
 	/* Validate arguments */
 	if (unlikely(protocol != 0))
@@ -322,33 +342,28 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
 	}
 
 	/* Allocate socket's protocol area */
-	if (!kern)
-		sk = sk_alloc(net, AF_TIPC, GFP_KERNEL, &tipc_proto);
-	else
-		sk = sk_alloc(net, AF_TIPC, GFP_KERNEL, &tipc_proto_kern);
-
+	sk = sk_alloc(net, AF_TIPC, GFP_KERNEL, &tipc_proto);
 	if (sk == NULL)
 		return -ENOMEM;
 
 	tsk = tipc_sk(sk);
-	ref = tipc_sk_ref_acquire(tsk);
-	if (!ref) {
-		pr_warn("Socket create failed; reference table exhausted\n");
-		return -ENOMEM;
-	}
 	tsk->max_pkt = MAX_PKT_DEFAULT;
-	tsk->ref = ref;
 	INIT_LIST_HEAD(&tsk->publications);
 	msg = &tsk->phdr;
-	tipc_msg_init(msg, TIPC_LOW_IMPORTANCE, TIPC_NAMED_MSG,
+	tn = net_generic(sock_net(sk), tipc_net_id);
+	tipc_msg_init(tn->own_addr, msg, TIPC_LOW_IMPORTANCE, TIPC_NAMED_MSG,
 		      NAMED_H_SIZE, 0);
-	msg_set_origport(msg, ref);
 
 	/* Finish initializing socket data structures */
 	sock->ops = ops;
 	sock->state = state;
 	sock_init_data(sock, sk);
-	k_init_timer(&tsk->timer, (Handler)tipc_sk_timeout, ref);
+	if (tipc_sk_insert(tsk)) {
+		pr_warn("Socket create failed; port numbrer exhausted\n");
+		return -EINVAL;
+	}
+	msg_set_origport(msg, tsk->portid);
+	setup_timer(&sk->sk_timer, tipc_sk_timeout, (unsigned long)tsk);
 	sk->sk_backlog_rcv = tipc_backlog_rcv;
 	sk->sk_rcvbuf = sysctl_tipc_rmem[1];
 	sk->sk_data_ready = tipc_data_ready;
@@ -365,73 +380,11 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
 	return 0;
 }
 
-/**
- * tipc_sock_create_local - create TIPC socket from inside TIPC module
- * @type: socket type - SOCK_RDM or SOCK_SEQPACKET
- *
- * We cannot use sock_creat_kern here because it bumps module user count.
- * Since socket owner and creator is the same module we must make sure
- * that module count remains zero for module local sockets, otherwise
- * we cannot do rmmod.
- *
- * Returns 0 on success, errno otherwise
- */
-int tipc_sock_create_local(int type, struct socket **res)
-{
-	int rc;
-
-	rc = sock_create_lite(AF_TIPC, type, 0, res);
-	if (rc < 0) {
-		pr_err("Failed to create kernel socket\n");
-		return rc;
-	}
-	tipc_sk_create(&init_net, *res, 0, 1);
-
-	return 0;
-}
-
-/**
- * tipc_sock_release_local - release socket created by tipc_sock_create_local
- * @sock: the socket to be released.
- *
- * Module reference count is not incremented when such sockets are created,
- * so we must keep it from being decremented when they are released.
- */
-void tipc_sock_release_local(struct socket *sock)
+static void tipc_sk_callback(struct rcu_head *head)
 {
-	tipc_release(sock);
-	sock->ops = NULL;
-	sock_release(sock);
-}
-
-/**
- * tipc_sock_accept_local - accept a connection on a socket created
- * with tipc_sock_create_local. Use this function to avoid that
- * module reference count is inadvertently incremented.
- *
- * @sock:    the accepting socket
- * @newsock: reference to the new socket to be created
- * @flags:   socket flags
- */
-
-int tipc_sock_accept_local(struct socket *sock, struct socket **newsock,
-			   int flags)
-{
-	struct sock *sk = sock->sk;
-	int ret;
+	struct tipc_sock *tsk = container_of(head, struct tipc_sock, rcu);
 
-	ret = sock_create_lite(sk->sk_family, sk->sk_type,
-			       sk->sk_protocol, newsock);
-	if (ret < 0)
-		return ret;
-
-	ret = tipc_accept(sock, *newsock, flags);
-	if (ret < 0) {
-		sock_release(*newsock);
-		return ret;
-	}
-	(*newsock)->ops = sock->ops;
-	return ret;
+	sock_put(&tsk->sk);
 }
 
 /**
@@ -453,9 +406,10 @@ int tipc_sock_accept_local(struct socket *sock, struct socket **newsock,
 static int tipc_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
+	struct net *net;
 	struct tipc_sock *tsk;
-	struct sk_buff *buf;
-	u32 dnode;
+	struct sk_buff *skb;
+	u32 dnode, probing_state;
 
 	/*
 	 * Exit if socket isn't fully initialized (occurs when a failed accept()
@@ -464,6 +418,7 @@ static int tipc_release(struct socket *sock)
 	if (sk == NULL)
 		return 0;
 
+	net = sock_net(sk);
 	tsk = tipc_sk(sk);
 	lock_sock(sk);
 
@@ -473,36 +428,39 @@ static int tipc_release(struct socket *sock)
 	 */
 	dnode = tsk_peer_node(tsk);
 	while (sock->state != SS_DISCONNECTING) {
-		buf = __skb_dequeue(&sk->sk_receive_queue);
-		if (buf == NULL)
+		skb = __skb_dequeue(&sk->sk_receive_queue);
+		if (skb == NULL)
 			break;
-		if (TIPC_SKB_CB(buf)->handle != NULL)
-			kfree_skb(buf);
+		if (TIPC_SKB_CB(skb)->handle != NULL)
+			kfree_skb(skb);
 		else {
 			if ((sock->state == SS_CONNECTING) ||
 			    (sock->state == SS_CONNECTED)) {
 				sock->state = SS_DISCONNECTING;
 				tsk->connected = 0;
-				tipc_node_remove_conn(dnode, tsk->ref);
+				tipc_node_remove_conn(net, dnode, tsk->portid);
 			}
-			if (tipc_msg_reverse(buf, &dnode, TIPC_ERR_NO_PORT))
-				tipc_link_xmit(buf, dnode, 0);
+			if (tipc_msg_reverse(tsk_own_node(tsk), skb, &dnode,
+					     TIPC_ERR_NO_PORT))
+				tipc_link_xmit_skb(net, skb, dnode, 0);
 		}
 	}
 
 	tipc_sk_withdraw(tsk, 0, NULL);
-	tipc_sk_ref_discard(tsk->ref);
-	k_cancel_timer(&tsk->timer);
+	probing_state = tsk->probing_state;
+	if (del_timer_sync(&sk->sk_timer) &&
+	    probing_state != TIPC_CONN_PROBING)
+		sock_put(sk);
+	tipc_sk_remove(tsk);
 	if (tsk->connected) {
-		buf = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, TIPC_CONN_MSG,
-				      SHORT_H_SIZE, 0, dnode, tipc_own_addr,
-				      tsk_peer_port(tsk),
-				      tsk->ref, TIPC_ERR_NO_PORT);
-		if (buf)
-			tipc_link_xmit(buf, dnode, tsk->ref);
-		tipc_node_remove_conn(dnode, tsk->ref);
+		skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE,
+				      TIPC_CONN_MSG, SHORT_H_SIZE, 0, dnode,
+				      tsk_own_node(tsk), tsk_peer_port(tsk),
+				      tsk->portid, TIPC_ERR_NO_PORT);
+		if (skb)
+			tipc_link_xmit_skb(net, skb, dnode, tsk->portid);
+		tipc_node_remove_conn(net, dnode, tsk->portid);
 	}
-	k_term_timer(&tsk->timer);
 
 	/* Discard any remaining (connection-based) messages in receive queue */
 	__skb_queue_purge(&sk->sk_receive_queue);
@@ -510,7 +468,8 @@ static int tipc_release(struct socket *sock)
 	/* Reject any messages that accumulated in backlog queue */
 	sock->state = SS_DISCONNECTING;
 	release_sock(sk);
-	sock_put(sk);
+
+	call_rcu(&tsk->rcu, tipc_sk_callback);
 	sock->sk = NULL;
 
 	return 0;
@@ -594,6 +553,7 @@ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
 {
 	struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr;
 	struct tipc_sock *tsk = tipc_sk(sock->sk);
+	struct tipc_net *tn = net_generic(sock_net(sock->sk), tipc_net_id);
 
 	memset(addr, 0, sizeof(*addr));
 	if (peer) {
@@ -603,8 +563,8 @@ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
 		addr->addr.id.ref = tsk_peer_port(tsk);
 		addr->addr.id.node = tsk_peer_node(tsk);
 	} else {
-		addr->addr.id.ref = tsk->ref;
-		addr->addr.id.node = tipc_own_addr;
+		addr->addr.id.ref = tsk->portid;
+		addr->addr.id.node = tn->own_addr;
 	}
 
 	*uaddr_len = sizeof(*addr);
@@ -692,7 +652,7 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock,
  * tipc_sendmcast - send multicast message
  * @sock: socket structure
  * @seq: destination address
- * @iov: message data to send
+ * @msg: message to send
  * @dsz: total length of message data
  * @timeo: timeout to wait for wakeup
  *
@@ -700,11 +660,14 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock,
  * Returns the number of bytes sent on success, or errno
  */
 static int tipc_sendmcast(struct  socket *sock, struct tipc_name_seq *seq,
-			  struct iovec *iov, size_t dsz, long timeo)
+			  struct msghdr *msg, size_t dsz, long timeo)
 {
 	struct sock *sk = sock->sk;
-	struct tipc_msg *mhdr = &tipc_sk(sk)->phdr;
-	struct sk_buff *buf;
+	struct tipc_sock *tsk = tipc_sk(sk);
+	struct net *net = sock_net(sk);
+	struct tipc_msg *mhdr = &tsk->phdr;
+	struct sk_buff_head *pktchain = &sk->sk_write_queue;
+	struct iov_iter save = msg->msg_iter;
 	uint mtu;
 	int rc;
 
@@ -719,82 +682,97 @@ static int tipc_sendmcast(struct  socket *sock, struct tipc_name_seq *seq,
 
 new_mtu:
 	mtu = tipc_bclink_get_mtu();
-	rc = tipc_msg_build(mhdr, iov, 0, dsz, mtu, &buf);
+	rc = tipc_msg_build(mhdr, msg, 0, dsz, mtu, pktchain);
 	if (unlikely(rc < 0))
 		return rc;
 
 	do {
-		rc = tipc_bclink_xmit(buf);
+		rc = tipc_bclink_xmit(net, pktchain);
 		if (likely(rc >= 0)) {
 			rc = dsz;
 			break;
 		}
-		if (rc == -EMSGSIZE)
+		if (rc == -EMSGSIZE) {
+			msg->msg_iter = save;
 			goto new_mtu;
+		}
 		if (rc != -ELINKCONG)
 			break;
 		tipc_sk(sk)->link_cong = 1;
 		rc = tipc_wait_for_sndmsg(sock, &timeo);
 		if (rc)
-			kfree_skb_list(buf);
+			__skb_queue_purge(pktchain);
 	} while (!rc);
 	return rc;
 }
 
-/* tipc_sk_mcast_rcv - Deliver multicast message to all destination sockets
+/**
+ * tipc_sk_mcast_rcv - Deliver multicast messages to all destination sockets
+ * @arrvq: queue with arriving messages, to be cloned after destination lookup
+ * @inputq: queue with cloned messages, delivered to socket after dest lookup
+ *
+ * Multi-threaded: parallel calls with reference to same queues may occur
  */
-void tipc_sk_mcast_rcv(struct sk_buff *buf)
+void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
+		       struct sk_buff_head *inputq)
 {
-	struct tipc_msg *msg = buf_msg(buf);
-	struct tipc_port_list dports = {0, NULL, };
-	struct tipc_port_list *item;
-	struct sk_buff *b;
-	uint i, last, dst = 0;
+	struct tipc_msg *msg;
+	struct tipc_plist dports;
+	u32 portid;
 	u32 scope = TIPC_CLUSTER_SCOPE;
-
-	if (in_own_node(msg_orignode(msg)))
-		scope = TIPC_NODE_SCOPE;
-
-	/* Create destination port list: */
-	tipc_nametbl_mc_translate(msg_nametype(msg),
-				  msg_namelower(msg),
-				  msg_nameupper(msg),
-				  scope,
-				  &dports);
-	last = dports.count;
-	if (!last) {
-		kfree_skb(buf);
-		return;
-	}
-
-	for (item = &dports; item; item = item->next) {
-		for (i = 0; i < PLSIZE && ++dst <= last; i++) {
-			b = (dst != last) ? skb_clone(buf, GFP_ATOMIC) : buf;
-			if (!b) {
-				pr_warn("Failed do clone mcast rcv buffer\n");
+	struct sk_buff_head tmpq;
+	uint hsz;
+	struct sk_buff *skb, *_skb;
+
+	__skb_queue_head_init(&tmpq);
+	tipc_plist_init(&dports);
+
+	skb = tipc_skb_peek(arrvq, &inputq->lock);
+	for (; skb; skb = tipc_skb_peek(arrvq, &inputq->lock)) {
+		msg = buf_msg(skb);
+		hsz = skb_headroom(skb) + msg_hdr_sz(msg);
+
+		if (in_own_node(net, msg_orignode(msg)))
+			scope = TIPC_NODE_SCOPE;
+
+		/* Create destination port list and message clones: */
+		tipc_nametbl_mc_translate(net,
+					  msg_nametype(msg), msg_namelower(msg),
+					  msg_nameupper(msg), scope, &dports);
+		portid = tipc_plist_pop(&dports);
+		for (; portid; portid = tipc_plist_pop(&dports)) {
+			_skb = __pskb_copy(skb, hsz, GFP_ATOMIC);
+			if (_skb) {
+				msg_set_destport(buf_msg(_skb), portid);
+				__skb_queue_tail(&tmpq, _skb);
 				continue;
 			}
-			msg_set_destport(msg, item->ports[i]);
-			tipc_sk_rcv(b);
+			pr_warn("Failed to clone mcast rcv buffer\n");
 		}
+		/* Append to inputq if not already done by other thread */
+		spin_lock_bh(&inputq->lock);
+		if (skb_peek(arrvq) == skb) {
+			skb_queue_splice_tail_init(&tmpq, inputq);
+			kfree_skb(__skb_dequeue(arrvq));
+		}
+		spin_unlock_bh(&inputq->lock);
+		__skb_queue_purge(&tmpq);
+		kfree_skb(skb);
 	}
-	tipc_port_list_free(&dports);
+	tipc_sk_rcv(net, inputq);
 }
 
 /**
  * tipc_sk_proto_rcv - receive a connection mng protocol message
  * @tsk: receiving socket
- * @dnode: node to send response message to, if any
- * @buf: buffer containing protocol message
- * Returns 0 (TIPC_OK) if message was consumed, 1 (TIPC_FWD_MSG) if
- * (CONN_PROBE_REPLY) message should be forwarded.
+ * @skb: pointer to message buffer. Set to NULL if buffer is consumed.
  */
-static int tipc_sk_proto_rcv(struct tipc_sock *tsk, u32 *dnode,
-			     struct sk_buff *buf)
+static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff **skb)
 {
-	struct tipc_msg *msg = buf_msg(buf);
+	struct tipc_msg *msg = buf_msg(*skb);
 	int conn_cong;
-
+	u32 dnode;
+	u32 own_node = tsk_own_node(tsk);
 	/* Ignore if connection cannot be validated: */
 	if (!tsk_peer_msg(tsk, msg))
 		goto exit;
@@ -807,48 +785,15 @@ static int tipc_sk_proto_rcv(struct tipc_sock *tsk, u32 *dnode,
 		if (conn_cong)
 			tsk->sk.sk_write_space(&tsk->sk);
 	} else if (msg_type(msg) == CONN_PROBE) {
-		if (!tipc_msg_reverse(buf, dnode, TIPC_OK))
-			return TIPC_OK;
-		msg_set_type(msg, CONN_PROBE_REPLY);
-		return TIPC_FWD_MSG;
+		if (tipc_msg_reverse(own_node, *skb, &dnode, TIPC_OK)) {
+			msg_set_type(msg, CONN_PROBE_REPLY);
+			return;
+		}
 	}
 	/* Do nothing if msg_type() == CONN_PROBE_REPLY */
 exit:
-	kfree_skb(buf);
-	return TIPC_OK;
-}
-
-/**
- * dest_name_check - verify user is permitted to send to specified port name
- * @dest: destination address
- * @m: descriptor for message to be sent
- *
- * Prevents restricted configuration commands from being issued by
- * unauthorized users.
- *
- * Returns 0 if permission is granted, otherwise errno
- */
-static int dest_name_check(struct sockaddr_tipc *dest, struct msghdr *m)
-{
-	struct tipc_cfg_msg_hdr hdr;
-
-	if (unlikely(dest->addrtype == TIPC_ADDR_ID))
-		return 0;
-	if (likely(dest->addr.name.name.type >= TIPC_RESERVED_TYPES))
-		return 0;
-	if (likely(dest->addr.name.name.type == TIPC_TOP_SRV))
-		return 0;
-	if (likely(dest->addr.name.name.type != TIPC_CFG_SRV))
-		return -EACCES;
-
-	if (!m->msg_iovlen || (m->msg_iov[0].iov_len < sizeof(hdr)))
-		return -EMSGSIZE;
-	if (copy_from_user(&hdr, m->msg_iov[0].iov_base, sizeof(hdr)))
-		return -EFAULT;
-	if ((ntohs(hdr.tcm_type) & 0xC000) && (!capable(CAP_NET_ADMIN)))
-		return -EACCES;
-
-	return 0;
+	kfree_skb(*skb);
+	*skb = NULL;
 }
 
 static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p)
@@ -878,7 +823,6 @@ static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p)
 
 /**
  * tipc_sendmsg - send message in connectionless manner
- * @iocb: if NULL, indicates that socket lock is already held
  * @sock: socket structure
  * @m: message to send
  * @dsz: amount of user data to be sent
@@ -890,61 +834,63 @@ static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p)
  *
  * Returns the number of bytes sent on success, or errno otherwise
  */
-static int tipc_sendmsg(struct kiocb *iocb, struct socket *sock,
+static int tipc_sendmsg(struct socket *sock,
 			struct msghdr *m, size_t dsz)
 {
+	struct sock *sk = sock->sk;
+	int ret;
+
+	lock_sock(sk);
+	ret = __tipc_sendmsg(sock, m, dsz);
+	release_sock(sk);
+
+	return ret;
+}
+
+static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz)
+{
 	DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
 	struct sock *sk = sock->sk;
 	struct tipc_sock *tsk = tipc_sk(sk);
+	struct net *net = sock_net(sk);
 	struct tipc_msg *mhdr = &tsk->phdr;
-	struct iovec *iov = m->msg_iov;
 	u32 dnode, dport;
-	struct sk_buff *buf;
-	struct tipc_name_seq *seq = &dest->addr.nameseq;
+	struct sk_buff_head *pktchain = &sk->sk_write_queue;
+	struct sk_buff *skb;
+	struct tipc_name_seq *seq;
+	struct iov_iter save;
 	u32 mtu;
 	long timeo;
-	int rc = -EINVAL;
-
-	if (unlikely(!dest))
-		return -EDESTADDRREQ;
-
-	if (unlikely((m->msg_namelen < sizeof(*dest)) ||
-		     (dest->family != AF_TIPC)))
-		return -EINVAL;
+	int rc;
 
 	if (dsz > TIPC_MAX_USER_MSG_SIZE)
 		return -EMSGSIZE;
-
-	if (iocb)
-		lock_sock(sk);
-
+	if (unlikely(!dest)) {
+		if (tsk->connected && sock->state == SS_READY)
+			dest = &tsk->remote;
+		else
+			return -EDESTADDRREQ;
+	} else if (unlikely(m->msg_namelen < sizeof(*dest)) ||
+		   dest->family != AF_TIPC) {
+		return -EINVAL;
+	}
 	if (unlikely(sock->state != SS_READY)) {
-		if (sock->state == SS_LISTENING) {
-			rc = -EPIPE;
-			goto exit;
-		}
-		if (sock->state != SS_UNCONNECTED) {
-			rc = -EISCONN;
-			goto exit;
-		}
-		if (tsk->published) {
-			rc = -EOPNOTSUPP;
-			goto exit;
-		}
+		if (sock->state == SS_LISTENING)
+			return -EPIPE;
+		if (sock->state != SS_UNCONNECTED)
+			return -EISCONN;
+		if (tsk->published)
+			return -EOPNOTSUPP;
 		if (dest->addrtype == TIPC_ADDR_NAME) {
 			tsk->conn_type = dest->addr.name.name.type;
 			tsk->conn_instance = dest->addr.name.name.instance;
 		}
 	}
-	rc = dest_name_check(dest, m);
-	if (rc)
-		goto exit;
-
+	seq = &dest->addr.nameseq;
 	timeo = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT);
 
 	if (dest->addrtype == TIPC_ADDR_MCAST) {
-		rc = tipc_sendmcast(sock, seq, iov, dsz, timeo);
-		goto exit;
+		return tipc_sendmcast(sock, seq, m, dsz, timeo);
 	} else if (dest->addrtype == TIPC_ADDR_NAME) {
 		u32 type = dest->addr.name.name.type;
 		u32 inst = dest->addr.name.name.instance;
@@ -956,13 +902,11 @@ static int tipc_sendmsg(struct kiocb *iocb, struct socket *sock,
 		msg_set_nametype(mhdr, type);
 		msg_set_nameinst(mhdr, inst);
 		msg_set_lookup_scope(mhdr, tipc_addr_scope(domain));
-		dport = tipc_nametbl_translate(type, inst, &dnode);
+		dport = tipc_nametbl_translate(net, type, inst, &dnode);
 		msg_set_destnode(mhdr, dnode);
 		msg_set_destport(mhdr, dport);
-		if (unlikely(!dport && !dnode)) {
-			rc = -EHOSTUNREACH;
-			goto exit;
-		}
+		if (unlikely(!dport && !dnode))
+			return -EHOSTUNREACH;
 	} else if (dest->addrtype == TIPC_ADDR_ID) {
 		dnode = dest->addr.id.node;
 		msg_set_type(mhdr, TIPC_DIRECT_MSG);
@@ -972,33 +916,34 @@ static int tipc_sendmsg(struct kiocb *iocb, struct socket *sock,
 		msg_set_hdr_sz(mhdr, BASIC_H_SIZE);
 	}
 
+	save = m->msg_iter;
 new_mtu:
-	mtu = tipc_node_get_mtu(dnode, tsk->ref);
-	rc = tipc_msg_build(mhdr, iov, 0, dsz, mtu, &buf);
+	mtu = tipc_node_get_mtu(net, dnode, tsk->portid);
+	rc = tipc_msg_build(mhdr, m, 0, dsz, mtu, pktchain);
 	if (rc < 0)
-		goto exit;
+		return rc;
 
 	do {
-		TIPC_SKB_CB(buf)->wakeup_pending = tsk->link_cong;
-		rc = tipc_link_xmit(buf, dnode, tsk->ref);
+		skb = skb_peek(pktchain);
+		TIPC_SKB_CB(skb)->wakeup_pending = tsk->link_cong;
+		rc = tipc_link_xmit(net, pktchain, dnode, tsk->portid);
 		if (likely(rc >= 0)) {
 			if (sock->state != SS_READY)
 				sock->state = SS_CONNECTING;
 			rc = dsz;
 			break;
 		}
-		if (rc == -EMSGSIZE)
+		if (rc == -EMSGSIZE) {
+			m->msg_iter = save;
 			goto new_mtu;
+		}
 		if (rc != -ELINKCONG)
 			break;
 		tsk->link_cong = 1;
 		rc = tipc_wait_for_sndmsg(sock, &timeo);
 		if (rc)
-			kfree_skb_list(buf);
+			__skb_queue_purge(pktchain);
 	} while (!rc);
-exit:
-	if (iocb)
-		release_sock(sk);
 
 	return rc;
 }
@@ -1035,7 +980,6 @@ static int tipc_wait_for_sndpkt(struct socket *sock, long *timeo_p)
 
 /**
  * tipc_send_stream - send stream-oriented data
- * @iocb: (unused)
  * @sock: socket structure
  * @m: data to send
  * @dsz: total length of data to be transmitted
@@ -1045,23 +989,36 @@ static int tipc_wait_for_sndpkt(struct socket *sock, long *timeo_p)
  * Returns the number of bytes sent on success (or partial success),
  * or errno if no data sent
  */
-static int tipc_send_stream(struct kiocb *iocb, struct socket *sock,
-			    struct msghdr *m, size_t dsz)
+static int tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz)
 {
 	struct sock *sk = sock->sk;
+	int ret;
+
+	lock_sock(sk);
+	ret = __tipc_send_stream(sock, m, dsz);
+	release_sock(sk);
+
+	return ret;
+}
+
+static int __tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz)
+{
+	struct sock *sk = sock->sk;
+	struct net *net = sock_net(sk);
 	struct tipc_sock *tsk = tipc_sk(sk);
 	struct tipc_msg *mhdr = &tsk->phdr;
-	struct sk_buff *buf;
+	struct sk_buff_head *pktchain = &sk->sk_write_queue;
 	DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
-	u32 ref = tsk->ref;
+	u32 portid = tsk->portid;
 	int rc = -EINVAL;
 	long timeo;
 	u32 dnode;
 	uint mtu, send, sent = 0;
+	struct iov_iter save;
 
 	/* Handle implied connection establishment */
 	if (unlikely(dest)) {
-		rc = tipc_sendmsg(iocb, sock, m, dsz);
+		rc = __tipc_sendmsg(sock, m, dsz);
 		if (dsz && (dsz == rc))
 			tsk->sent_unacked = 1;
 		return rc;
@@ -1069,29 +1026,26 @@ static int tipc_send_stream(struct kiocb *iocb, struct socket *sock,
 	if (dsz > (uint)INT_MAX)
 		return -EMSGSIZE;
 
-	if (iocb)
-		lock_sock(sk);
-
 	if (unlikely(sock->state != SS_CONNECTED)) {
 		if (sock->state == SS_DISCONNECTING)
-			rc = -EPIPE;
+			return -EPIPE;
 		else
-			rc = -ENOTCONN;
-		goto exit;
+			return -ENOTCONN;
 	}
 
 	timeo = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT);
 	dnode = tsk_peer_node(tsk);
 
 next:
+	save = m->msg_iter;
 	mtu = tsk->max_pkt;
 	send = min_t(uint, dsz - sent, TIPC_MAX_USER_MSG_SIZE);
-	rc = tipc_msg_build(mhdr, m->msg_iov, sent, send, mtu, &buf);
+	rc = tipc_msg_build(mhdr, m, sent, send, mtu, pktchain);
 	if (unlikely(rc < 0))
-		goto exit;
+		return rc;
 	do {
 		if (likely(!tsk_conn_cong(tsk))) {
-			rc = tipc_link_xmit(buf, dnode, ref);
+			rc = tipc_link_xmit(net, pktchain, dnode, portid);
 			if (likely(!rc)) {
 				tsk->sent_unacked++;
 				sent += send;
@@ -1100,7 +1054,9 @@ next:
 				goto next;
 			}
 			if (rc == -EMSGSIZE) {
-				tsk->max_pkt = tipc_node_get_mtu(dnode, ref);
+				tsk->max_pkt = tipc_node_get_mtu(net, dnode,
+								 portid);
+				m->msg_iter = save;
 				goto next;
 			}
 			if (rc != -ELINKCONG)
@@ -1109,17 +1065,14 @@ next:
 		}
 		rc = tipc_wait_for_sndpkt(sock, &timeo);
 		if (rc)
-			kfree_skb_list(buf);
+			__skb_queue_purge(pktchain);
 	} while (!rc);
-exit:
-	if (iocb)
-		release_sock(sk);
+
 	return sent ? sent : rc;
 }
 
 /**
  * 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
  * @dsz: length of data to be transmitted
@@ -1128,13 +1081,12 @@ exit:
  *
  * Returns the number of bytes sent on success, or errno otherwise
  */
-static int tipc_send_packet(struct kiocb *iocb, struct socket *sock,
-			    struct msghdr *m, size_t dsz)
+static int tipc_send_packet(struct socket *sock, struct msghdr *m, size_t dsz)
 {
 	if (dsz > TIPC_MAX_USER_MSG_SIZE)
 		return -EMSGSIZE;
 
-	return tipc_send_stream(iocb, sock, m, dsz);
+	return tipc_send_stream(sock, m, dsz);
 }
 
 /* tipc_sk_finish_conn - complete the setup of a connection
@@ -1142,6 +1094,8 @@ static int tipc_send_packet(struct kiocb *iocb, struct socket *sock,
 static void tipc_sk_finish_conn(struct tipc_sock *tsk, u32 peer_port,
 				u32 peer_node)
 {
+	struct sock *sk = &tsk->sk;
+	struct net *net = sock_net(sk);
 	struct tipc_msg *msg = &tsk->phdr;
 
 	msg_set_destnode(msg, peer_node);
@@ -1150,12 +1104,12 @@ static void tipc_sk_finish_conn(struct tipc_sock *tsk, u32 peer_port,
 	msg_set_lookup_scope(msg, 0);
 	msg_set_hdr_sz(msg, SHORT_H_SIZE);
 
-	tsk->probing_interval = CONN_PROBING_INTERVAL;
+	tsk->probing_intv = CONN_PROBING_INTERVAL;
 	tsk->probing_state = TIPC_CONN_OK;
 	tsk->connected = 1;
-	k_start_timer(&tsk->timer, tsk->probing_interval);
-	tipc_node_add_conn(peer_node, tsk->ref, peer_port);
-	tsk->max_pkt = tipc_node_get_mtu(peer_node, tsk->ref);
+	sk_reset_timer(sk, &sk->sk_timer, jiffies + tsk->probing_intv);
+	tipc_node_add_conn(net, peer_node, tsk->portid, peer_port);
+	tsk->max_pkt = tipc_node_get_mtu(net, peer_node, tsk->portid);
 }
 
 /**
@@ -1254,20 +1208,22 @@ static int tipc_sk_anc_data_recv(struct msghdr *m, struct tipc_msg *msg,
 
 static void tipc_sk_send_ack(struct tipc_sock *tsk, uint ack)
 {
-	struct sk_buff *buf = NULL;
+	struct net *net = sock_net(&tsk->sk);
+	struct sk_buff *skb = NULL;
 	struct tipc_msg *msg;
 	u32 peer_port = tsk_peer_port(tsk);
 	u32 dnode = tsk_peer_node(tsk);
 
 	if (!tsk->connected)
 		return;
-	buf = tipc_msg_create(CONN_MANAGER, CONN_ACK, INT_H_SIZE, 0, dnode,
-			      tipc_own_addr, peer_port, tsk->ref, TIPC_OK);
-	if (!buf)
+	skb = tipc_msg_create(CONN_MANAGER, CONN_ACK, INT_H_SIZE, 0,
+			      dnode, tsk_own_node(tsk), peer_port,
+			      tsk->portid, TIPC_OK);
+	if (!skb)
 		return;
-	msg = buf_msg(buf);
+	msg = buf_msg(skb);
 	msg_set_msgcnt(msg, ack);
-	tipc_link_xmit(buf, dnode, msg_link_selector(msg));
+	tipc_link_xmit_skb(net, skb, dnode, msg_link_selector(msg));
 }
 
 static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop)
@@ -1291,12 +1247,12 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop)
 		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;
+		err = sock_intr_errno(timeo);
+		if (signal_pending(current))
+			break;
 	}
 	finish_wait(sk_sleep(sk), &wait);
 	*timeop = timeo;
@@ -1305,7 +1261,6 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop)
 
 /**
  * tipc_recvmsg - receive packet-oriented message
- * @iocb: (unused)
  * @m: descriptor for message info
  * @buf_len: total size of user buffer area
  * @flags: receive flags
@@ -1315,8 +1270,8 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop)
  *
  * Returns size of returned message data, errno otherwise
  */
-static int tipc_recvmsg(struct kiocb *iocb, struct socket *sock,
-			struct msghdr *m, size_t buf_len, int flags)
+static int tipc_recvmsg(struct socket *sock, struct msghdr *m, size_t buf_len,
+			int flags)
 {
 	struct sock *sk = sock->sk;
 	struct tipc_sock *tsk = tipc_sk(sk);
@@ -1372,8 +1327,7 @@ restart:
 			sz = buf_len;
 			m->msg_flags |= MSG_TRUNC;
 		}
-		res = skb_copy_datagram_iovec(buf, msg_hdr_sz(msg),
-					      m->msg_iov, sz);
+		res = skb_copy_datagram_msg(buf, msg_hdr_sz(msg), m, sz);
 		if (res)
 			goto exit;
 		res = sz;
@@ -1401,7 +1355,6 @@ exit:
 
 /**
  * tipc_recv_stream - receive stream-oriented data
- * @iocb: (unused)
  * @m: descriptor for message info
  * @buf_len: total size of user buffer area
  * @flags: receive flags
@@ -1411,8 +1364,8 @@ exit:
  *
  * Returns size of returned message data, errno otherwise
  */
-static int tipc_recv_stream(struct kiocb *iocb, struct socket *sock,
-			    struct msghdr *m, size_t buf_len, int flags)
+static int tipc_recv_stream(struct socket *sock, struct msghdr *m,
+			    size_t buf_len, int flags)
 {
 	struct sock *sk = sock->sk;
 	struct tipc_sock *tsk = tipc_sk(sk);
@@ -1473,8 +1426,8 @@ restart:
 		needed = (buf_len - sz_copied);
 		sz_to_copy = (sz <= needed) ? sz : needed;
 
-		res = skb_copy_datagram_iovec(buf, msg_hdr_sz(msg) + offset,
-					      m->msg_iov, sz_to_copy);
+		res = skb_copy_datagram_msg(buf, msg_hdr_sz(msg) + offset,
+					    m, sz_to_copy);
 		if (res)
 			goto exit;
 
@@ -1554,15 +1507,16 @@ static void tipc_data_ready(struct sock *sk)
 /**
  * filter_connect - Handle all incoming messages for a connection-based socket
  * @tsk: TIPC socket
- * @msg: message
+ * @skb: pointer to message buffer. Set to NULL if buffer is consumed
  *
- * Returns 0 (TIPC_OK) if everyting ok, -TIPC_ERR_NO_PORT otherwise
+ * Returns 0 (TIPC_OK) if everything ok, -TIPC_ERR_NO_PORT otherwise
  */
-static int filter_connect(struct tipc_sock *tsk, struct sk_buff **buf)
+static int filter_connect(struct tipc_sock *tsk, struct sk_buff **skb)
 {
 	struct sock *sk = &tsk->sk;
+	struct net *net = sock_net(sk);
 	struct socket *sock = sk->sk_socket;
-	struct tipc_msg *msg = buf_msg(*buf);
+	struct tipc_msg *msg = buf_msg(*skb);
 	int retval = -TIPC_ERR_NO_PORT;
 
 	if (msg_mcast(msg))
@@ -1576,8 +1530,8 @@ static int filter_connect(struct tipc_sock *tsk, struct sk_buff **buf)
 				sock->state = SS_DISCONNECTING;
 				tsk->connected = 0;
 				/* let timer expire on it's own */
-				tipc_node_remove_conn(tsk_peer_node(tsk),
-						      tsk->ref);
+				tipc_node_remove_conn(net, tsk_peer_node(tsk),
+						      tsk->portid);
 			}
 			retval = TIPC_OK;
 		}
@@ -1612,8 +1566,8 @@ static int filter_connect(struct tipc_sock *tsk, struct sk_buff **buf)
 		 * connect() routine if sleeping.
 		 */
 		if (msg_data_sz(msg) == 0) {
-			kfree_skb(*buf);
-			*buf = NULL;
+			kfree_skb(*skb);
+			*skb = NULL;
 			if (waitqueue_active(sk_sleep(sk)))
 				wake_up_interruptible(sk_sleep(sk));
 		}
@@ -1665,32 +1619,33 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *buf)
 /**
  * filter_rcv - validate incoming message
  * @sk: socket
- * @buf: message
+ * @skb: pointer to message. Set to NULL if buffer is consumed.
  *
  * Enqueues message on receive queue if acceptable; optionally handles
  * disconnect indication for a connected socket.
  *
- * Called with socket lock already taken; port lock may also be taken.
+ * Called with socket lock already taken
  *
- * Returns 0 (TIPC_OK) if message was consumed, -TIPC error code if message
- * to be rejected, 1 (TIPC_FWD_MSG) if (CONN_MANAGER) message to be forwarded
+ * Returns 0 (TIPC_OK) if message was ok, -TIPC error code if rejected
  */
-static int filter_rcv(struct sock *sk, struct sk_buff *buf)
+static int filter_rcv(struct sock *sk, struct sk_buff **skb)
 {
 	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 onode;
+	struct tipc_msg *msg = buf_msg(*skb);
+	unsigned int limit = rcvbuf_limit(sk, *skb);
 	int rc = TIPC_OK;
 
-	if (unlikely(msg_user(msg) == CONN_MANAGER))
-		return tipc_sk_proto_rcv(tsk, &onode, buf);
+	if (unlikely(msg_user(msg) == CONN_MANAGER)) {
+		tipc_sk_proto_rcv(tsk, skb);
+		return TIPC_OK;
+	}
 
 	if (unlikely(msg_user(msg) == SOCK_WAKEUP)) {
-		kfree_skb(buf);
+		kfree_skb(*skb);
 		tsk->link_cong = 0;
 		sk->sk_write_space(sk);
+		*skb = NULL;
 		return TIPC_OK;
 	}
 
@@ -1702,101 +1657,150 @@ static int filter_rcv(struct sock *sk, struct sk_buff *buf)
 		if (msg_connected(msg))
 			return -TIPC_ERR_NO_PORT;
 	} else {
-		rc = filter_connect(tsk, &buf);
-		if (rc != TIPC_OK || buf == NULL)
+		rc = filter_connect(tsk, skb);
+		if (rc != TIPC_OK || !*skb)
 			return rc;
 	}
 
 	/* Reject message if there isn't room to queue it */
-	if (sk_rmem_alloc_get(sk) + buf->truesize >= limit)
+	if (sk_rmem_alloc_get(sk) + (*skb)->truesize >= limit)
 		return -TIPC_ERR_OVERLOAD;
 
 	/* Enqueue message */
-	TIPC_SKB_CB(buf)->handle = NULL;
-	__skb_queue_tail(&sk->sk_receive_queue, buf);
-	skb_set_owner_r(buf, sk);
+	TIPC_SKB_CB(*skb)->handle = NULL;
+	__skb_queue_tail(&sk->sk_receive_queue, *skb);
+	skb_set_owner_r(*skb, sk);
 
 	sk->sk_data_ready(sk);
+	*skb = NULL;
 	return TIPC_OK;
 }
 
 /**
  * tipc_backlog_rcv - handle incoming message from backlog queue
  * @sk: socket
- * @buf: message
+ * @skb: message
  *
- * Caller must hold socket lock, but not port lock.
+ * Caller must hold socket lock
  *
  * Returns 0
  */
-static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *buf)
+static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb)
 {
-	int rc;
-	u32 onode;
+	int err;
+	atomic_t *dcnt;
+	u32 dnode;
 	struct tipc_sock *tsk = tipc_sk(sk);
-	uint truesize = buf->truesize;
-
-	rc = filter_rcv(sk, buf);
-
-	if (likely(!rc)) {
-		if (atomic_read(&tsk->dupl_rcvcnt) < TIPC_CONN_OVERLOAD_LIMIT)
-			atomic_add(truesize, &tsk->dupl_rcvcnt);
+	struct net *net = sock_net(sk);
+	uint truesize = skb->truesize;
+
+	err = filter_rcv(sk, &skb);
+	if (likely(!skb)) {
+		dcnt = &tsk->dupl_rcvcnt;
+		if (atomic_read(dcnt) < TIPC_CONN_OVERLOAD_LIMIT)
+			atomic_add(truesize, dcnt);
 		return 0;
 	}
+	if (!err || tipc_msg_reverse(tsk_own_node(tsk), skb, &dnode, -err))
+		tipc_link_xmit_skb(net, skb, dnode, tsk->portid);
+	return 0;
+}
 
-	if ((rc < 0) && !tipc_msg_reverse(buf, &onode, -rc))
-		return 0;
-
-	tipc_link_xmit(buf, onode, 0);
+/**
+ * tipc_sk_enqueue - extract all buffers with destination 'dport' from
+ *                   inputq and try adding them to socket or backlog queue
+ * @inputq: list of incoming buffers with potentially different destinations
+ * @sk: socket where the buffers should be enqueued
+ * @dport: port number for the socket
+ * @_skb: returned buffer to be forwarded or rejected, if applicable
+ *
+ * Caller must hold socket lock
+ *
+ * Returns TIPC_OK if all buffers enqueued, otherwise -TIPC_ERR_OVERLOAD
+ * or -TIPC_ERR_NO_PORT
+ */
+static int tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk,
+			   u32 dport, struct sk_buff **_skb)
+{
+	unsigned int lim;
+	atomic_t *dcnt;
+	int err;
+	struct sk_buff *skb;
+	unsigned long time_limit = jiffies + 2;
 
-	return 0;
+	while (skb_queue_len(inputq)) {
+		if (unlikely(time_after_eq(jiffies, time_limit)))
+			return TIPC_OK;
+		skb = tipc_skb_dequeue(inputq, dport);
+		if (unlikely(!skb))
+			return TIPC_OK;
+		if (!sock_owned_by_user(sk)) {
+			err = filter_rcv(sk, &skb);
+			if (likely(!skb))
+				continue;
+			*_skb = skb;
+			return err;
+		}
+		dcnt = &tipc_sk(sk)->dupl_rcvcnt;
+		if (sk->sk_backlog.len)
+			atomic_set(dcnt, 0);
+		lim = rcvbuf_limit(sk, skb) + atomic_read(dcnt);
+		if (likely(!sk_add_backlog(sk, skb, lim)))
+			continue;
+		*_skb = skb;
+		return -TIPC_ERR_OVERLOAD;
+	}
+	return TIPC_OK;
 }
 
 /**
- * tipc_sk_rcv - handle incoming message
- * @buf: buffer containing arriving message
- * Consumes buffer
- * Returns 0 if success, or errno: -EHOSTUNREACH
+ * tipc_sk_rcv - handle a chain of incoming buffers
+ * @inputq: buffer list containing the buffers
+ * Consumes all buffers in list until inputq is empty
+ * Note: may be called in multiple threads referring to the same queue
+ * Returns 0 if last buffer was accepted, otherwise -EHOSTUNREACH
+ * Only node local calls check the return value, sending single-buffer queues
  */
-int tipc_sk_rcv(struct sk_buff *buf)
+int tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq)
 {
+	u32 dnode, dport = 0;
+	int err;
+	struct sk_buff *skb;
 	struct tipc_sock *tsk;
+	struct tipc_net *tn;
 	struct sock *sk;
-	u32 dport = msg_destport(buf_msg(buf));
-	int rc = TIPC_OK;
-	uint limit;
-	u32 dnode;
 
-	/* Validate destination and message */
-	tsk = tipc_sk_get(dport);
-	if (unlikely(!tsk)) {
-		rc = tipc_msg_eval(buf, &dnode);
-		goto exit;
+	while (skb_queue_len(inputq)) {
+		err = -TIPC_ERR_NO_PORT;
+		skb = NULL;
+		dport = tipc_skb_peek_port(inputq, dport);
+		tsk = tipc_sk_lookup(net, dport);
+		if (likely(tsk)) {
+			sk = &tsk->sk;
+			if (likely(spin_trylock_bh(&sk->sk_lock.slock))) {
+				err = tipc_sk_enqueue(inputq, sk, dport, &skb);
+				spin_unlock_bh(&sk->sk_lock.slock);
+				dport = 0;
+			}
+			sock_put(sk);
+		} else {
+			skb = tipc_skb_dequeue(inputq, dport);
+		}
+		if (likely(!skb))
+			continue;
+		if (tipc_msg_lookup_dest(net, skb, &dnode, &err))
+			goto xmit;
+		if (!err) {
+			dnode = msg_destnode(buf_msg(skb));
+			goto xmit;
+		}
+		tn = net_generic(net, tipc_net_id);
+		if (!tipc_msg_reverse(tn->own_addr, skb, &dnode, -err))
+			continue;
+xmit:
+		tipc_link_xmit_skb(net, skb, dnode, dport);
 	}
-	sk = &tsk->sk;
-
-	/* Queue message */
-	spin_lock_bh(&sk->sk_lock.slock);
-
-	if (!sock_owned_by_user(sk)) {
-		rc = filter_rcv(sk, buf);
-	} else {
-		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))
-			rc = -TIPC_ERR_OVERLOAD;
-	}
-	spin_unlock_bh(&sk->sk_lock.slock);
-	tipc_sk_put(tsk);
-	if (likely(!rc))
-		return 0;
-exit:
-	if ((rc < 0) && !tipc_msg_reverse(buf, &dnode, -rc))
-		return -EHOSTUNREACH;
-
-	tipc_link_xmit(buf, dnode, 0);
-	return (rc < 0) ? -EHOSTUNREACH : 0;
+	return err ? -EHOSTUNREACH : 0;
 }
 
 static int tipc_wait_for_connect(struct socket *sock, long *timeo_p)
@@ -1834,17 +1838,26 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest,
 			int destlen, int flags)
 {
 	struct sock *sk = sock->sk;
+	struct tipc_sock *tsk = tipc_sk(sk);
 	struct sockaddr_tipc *dst = (struct sockaddr_tipc *)dest;
 	struct msghdr m = {NULL,};
-	long timeout = (flags & O_NONBLOCK) ? 0 : tipc_sk(sk)->conn_timeout;
+	long timeout = (flags & O_NONBLOCK) ? 0 : tsk->conn_timeout;
 	socket_state previous;
-	int res;
+	int res = 0;
 
 	lock_sock(sk);
 
-	/* For now, TIPC does not allow use of connect() with DGRAM/RDM types */
+	/* DGRAM/RDM connect(), just save the destaddr */
 	if (sock->state == SS_READY) {
-		res = -EOPNOTSUPP;
+		if (dst->family == AF_UNSPEC) {
+			memset(&tsk->remote, 0, sizeof(struct sockaddr_tipc));
+			tsk->connected = 0;
+		} else if (destlen != sizeof(struct sockaddr_tipc)) {
+			res = -EINVAL;
+		} else {
+			memcpy(&tsk->remote, dest, destlen);
+			tsk->connected = 1;
+		}
 		goto exit;
 	}
 
@@ -1872,7 +1885,7 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest,
 		if (!timeout)
 			m.msg_flags = MSG_DONTWAIT;
 
-		res = tipc_sendmsg(NULL, sock, &m, 0);
+		res = __tipc_sendmsg(sock, &m, 0);
 		if ((res < 0) && (res != -EWOULDBLOCK))
 			goto exit;
 
@@ -1952,12 +1965,12 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo)
 		err = -EINVAL;
 		if (sock->state != SS_LISTENING)
 			break;
-		err = sock_intr_errno(timeo);
-		if (signal_pending(current))
-			break;
 		err = -EAGAIN;
 		if (!timeo)
 			break;
+		err = sock_intr_errno(timeo);
+		if (signal_pending(current))
+			break;
 	}
 	finish_wait(sk_sleep(sk), &wait);
 	return err;
@@ -2028,7 +2041,7 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags)
 		struct msghdr m = {NULL,};
 
 		tsk_advance_rx_queue(sk);
-		tipc_send_packet(NULL, new_sock, &m, 0);
+		__tipc_send_stream(new_sock, &m, 0);
 	} else {
 		__skb_dequeue(&sk->sk_receive_queue);
 		__skb_queue_head(&new_sk->sk_receive_queue, buf);
@@ -2052,8 +2065,9 @@ exit:
 static int tipc_shutdown(struct socket *sock, int how)
 {
 	struct sock *sk = sock->sk;
+	struct net *net = sock_net(sk);
 	struct tipc_sock *tsk = tipc_sk(sk);
-	struct sk_buff *buf;
+	struct sk_buff *skb;
 	u32 dnode;
 	int res;
 
@@ -2068,27 +2082,29 @@ static int tipc_shutdown(struct socket *sock, int how)
 
 restart:
 		/* Disconnect and send a 'FIN+' or 'FIN-' message to peer */
-		buf = __skb_dequeue(&sk->sk_receive_queue);
-		if (buf) {
-			if (TIPC_SKB_CB(buf)->handle != NULL) {
-				kfree_skb(buf);
+		skb = __skb_dequeue(&sk->sk_receive_queue);
+		if (skb) {
+			if (TIPC_SKB_CB(skb)->handle != NULL) {
+				kfree_skb(skb);
 				goto restart;
 			}
-			if (tipc_msg_reverse(buf, &dnode, TIPC_CONN_SHUTDOWN))
-				tipc_link_xmit(buf, dnode, tsk->ref);
-			tipc_node_remove_conn(dnode, tsk->ref);
+			if (tipc_msg_reverse(tsk_own_node(tsk), skb, &dnode,
+					     TIPC_CONN_SHUTDOWN))
+				tipc_link_xmit_skb(net, skb, dnode,
+						   tsk->portid);
 		} else {
 			dnode = tsk_peer_node(tsk);
-			buf = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE,
+
+			skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE,
 					      TIPC_CONN_MSG, SHORT_H_SIZE,
-					      0, dnode, tipc_own_addr,
+					      0, dnode, tsk_own_node(tsk),
 					      tsk_peer_port(tsk),
-					      tsk->ref, TIPC_CONN_SHUTDOWN);
-			tipc_link_xmit(buf, dnode, tsk->ref);
+					      tsk->portid, TIPC_CONN_SHUTDOWN);
+			tipc_link_xmit_skb(net, skb, dnode, tsk->portid);
 		}
 		tsk->connected = 0;
 		sock->state = SS_DISCONNECTING;
-		tipc_node_remove_conn(dnode, tsk->ref);
+		tipc_node_remove_conn(net, dnode, tsk->portid);
 		/* fall through */
 
 	case SS_DISCONNECTING:
@@ -2109,18 +2125,14 @@ restart:
 	return res;
 }
 
-static void tipc_sk_timeout(unsigned long ref)
+static void tipc_sk_timeout(unsigned long data)
 {
-	struct tipc_sock *tsk;
-	struct sock *sk;
-	struct sk_buff *buf = NULL;
+	struct tipc_sock *tsk = (struct tipc_sock *)data;
+	struct sock *sk = &tsk->sk;
+	struct sk_buff *skb = NULL;
 	u32 peer_port, peer_node;
+	u32 own_node = tsk_own_node(tsk);
 
-	tsk = tipc_sk_get(ref);
-	if (!tsk)
-		return;
-
-	sk = &tsk->sk;
 	bh_lock_sock(sk);
 	if (!tsk->connected) {
 		bh_unlock_sock(sk);
@@ -2130,39 +2142,46 @@ static void tipc_sk_timeout(unsigned long ref)
 	peer_node = tsk_peer_node(tsk);
 
 	if (tsk->probing_state == TIPC_CONN_PROBING) {
-		/* Previous probe not answered -> self abort */
-		buf = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, TIPC_CONN_MSG,
-				      SHORT_H_SIZE, 0, tipc_own_addr,
-				      peer_node, ref, peer_port,
-				      TIPC_ERR_NO_PORT);
+		if (!sock_owned_by_user(sk)) {
+			sk->sk_socket->state = SS_DISCONNECTING;
+			tsk->connected = 0;
+			tipc_node_remove_conn(sock_net(sk), tsk_peer_node(tsk),
+					      tsk_peer_port(tsk));
+			sk->sk_state_change(sk);
+		} else {
+			/* Try again later */
+			sk_reset_timer(sk, &sk->sk_timer, (HZ / 20));
+		}
+
 	} else {
-		buf = tipc_msg_create(CONN_MANAGER, CONN_PROBE, INT_H_SIZE,
-				      0, peer_node, tipc_own_addr,
-				      peer_port, ref, TIPC_OK);
+		skb = tipc_msg_create(CONN_MANAGER, CONN_PROBE,
+				      INT_H_SIZE, 0, peer_node, own_node,
+				      peer_port, tsk->portid, TIPC_OK);
 		tsk->probing_state = TIPC_CONN_PROBING;
-		k_start_timer(&tsk->timer, tsk->probing_interval);
+		sk_reset_timer(sk, &sk->sk_timer, jiffies + tsk->probing_intv);
 	}
 	bh_unlock_sock(sk);
-	if (buf)
-		tipc_link_xmit(buf, peer_node, ref);
+	if (skb)
+		tipc_link_xmit_skb(sock_net(sk), skb, peer_node, tsk->portid);
 exit:
-	tipc_sk_put(tsk);
+	sock_put(sk);
 }
 
 static int tipc_sk_publish(struct tipc_sock *tsk, uint scope,
 			   struct tipc_name_seq const *seq)
 {
+	struct net *net = sock_net(&tsk->sk);
 	struct publication *publ;
 	u32 key;
 
 	if (tsk->connected)
 		return -EINVAL;
-	key = tsk->ref + tsk->pub_count + 1;
-	if (key == tsk->ref)
+	key = tsk->portid + tsk->pub_count + 1;
+	if (key == tsk->portid)
 		return -EADDRINUSE;
 
-	publ = tipc_nametbl_publish(seq->type, seq->lower, seq->upper,
-				    scope, tsk->ref, key);
+	publ = tipc_nametbl_publish(net, seq->type, seq->lower, seq->upper,
+				    scope, tsk->portid, key);
 	if (unlikely(!publ))
 		return -EINVAL;
 
@@ -2175,6 +2194,7 @@ static int tipc_sk_publish(struct tipc_sock *tsk, uint scope,
 static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope,
 			    struct tipc_name_seq const *seq)
 {
+	struct net *net = sock_net(&tsk->sk);
 	struct publication *publ;
 	struct publication *safe;
 	int rc = -EINVAL;
@@ -2189,12 +2209,12 @@ static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope,
 				continue;
 			if (publ->upper != seq->upper)
 				break;
-			tipc_nametbl_withdraw(publ->type, publ->lower,
+			tipc_nametbl_withdraw(net, publ->type, publ->lower,
 					      publ->ref, publ->key);
 			rc = 0;
 			break;
 		}
-		tipc_nametbl_withdraw(publ->type, publ->lower,
+		tipc_nametbl_withdraw(net, publ->type, publ->lower,
 				      publ->ref, publ->key);
 		rc = 0;
 	}
@@ -2203,336 +2223,105 @@ static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope,
 	return rc;
 }
 
-static int tipc_sk_show(struct tipc_sock *tsk, char *buf,
-			int len, int full_id)
-{
-	struct publication *publ;
-	int ret;
-
-	if (full_id)
-		ret = tipc_snprintf(buf, len, "<%u.%u.%u:%u>:",
-				    tipc_zone(tipc_own_addr),
-				    tipc_cluster(tipc_own_addr),
-				    tipc_node(tipc_own_addr), tsk->ref);
-	else
-		ret = tipc_snprintf(buf, len, "%-10u:", tsk->ref);
-
-	if (tsk->connected) {
-		u32 dport = tsk_peer_port(tsk);
-		u32 destnode = tsk_peer_node(tsk);
-
-		ret += tipc_snprintf(buf + ret, len - ret,
-				     " connected to <%u.%u.%u:%u>",
-				     tipc_zone(destnode),
-				     tipc_cluster(destnode),
-				     tipc_node(destnode), dport);
-		if (tsk->conn_type != 0)
-			ret += tipc_snprintf(buf + ret, len - ret,
-					     " via {%u,%u}", tsk->conn_type,
-					     tsk->conn_instance);
-	} else if (tsk->published) {
-		ret += tipc_snprintf(buf + ret, len - ret, " bound to");
-		list_for_each_entry(publ, &tsk->publications, pport_list) {
-			if (publ->lower == publ->upper)
-				ret += tipc_snprintf(buf + ret, len - ret,
-						     " {%u,%u}", publ->type,
-						     publ->lower);
-			else
-				ret += tipc_snprintf(buf + ret, len - ret,
-						     " {%u,%u,%u}", publ->type,
-						     publ->lower, publ->upper);
-		}
-	}
-	ret += tipc_snprintf(buf + ret, len - ret, "\n");
-	return ret;
-}
-
-struct sk_buff *tipc_sk_socks_show(void)
-{
-	struct sk_buff *buf;
-	struct tlv_desc *rep_tlv;
-	char *pb;
-	int pb_len;
-	struct tipc_sock *tsk;
-	int str_len = 0;
-	u32 ref = 0;
-
-	buf = tipc_cfg_reply_alloc(TLV_SPACE(ULTRA_STRING_MAX_LEN));
-	if (!buf)
-		return NULL;
-	rep_tlv = (struct tlv_desc *)buf->data;
-	pb = TLV_DATA(rep_tlv);
-	pb_len = ULTRA_STRING_MAX_LEN;
-
-	tsk = tipc_sk_get_next(&ref);
-	for (; tsk; tsk = tipc_sk_get_next(&ref)) {
-		lock_sock(&tsk->sk);
-		str_len += tipc_sk_show(tsk, pb + str_len,
-					pb_len - str_len, 0);
-		release_sock(&tsk->sk);
-		tipc_sk_put(tsk);
-	}
-	str_len += 1;	/* for "\0" */
-	skb_put(buf, TLV_SPACE(str_len));
-	TLV_SET(rep_tlv, TIPC_TLV_ULTRA_STRING, NULL, str_len);
-
-	return buf;
-}
-
 /* tipc_sk_reinit: set non-zero address in all existing sockets
  *                 when we go from standalone to network mode.
  */
-void tipc_sk_reinit(void)
+void tipc_sk_reinit(struct net *net)
 {
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	const struct bucket_table *tbl;
+	struct rhash_head *pos;
+	struct tipc_sock *tsk;
 	struct tipc_msg *msg;
-	u32 ref = 0;
-	struct tipc_sock *tsk = tipc_sk_get_next(&ref);
+	int i;
 
-	for (; tsk; tsk = tipc_sk_get_next(&ref)) {
-		lock_sock(&tsk->sk);
-		msg = &tsk->phdr;
-		msg_set_prevnode(msg, tipc_own_addr);
-		msg_set_orignode(msg, tipc_own_addr);
-		release_sock(&tsk->sk);
-		tipc_sk_put(tsk);
+	rcu_read_lock();
+	tbl = rht_dereference_rcu((&tn->sk_rht)->tbl, &tn->sk_rht);
+	for (i = 0; i < tbl->size; i++) {
+		rht_for_each_entry_rcu(tsk, pos, tbl, i, node) {
+			spin_lock_bh(&tsk->sk.sk_lock.slock);
+			msg = &tsk->phdr;
+			msg_set_prevnode(msg, tn->own_addr);
+			msg_set_orignode(msg, tn->own_addr);
+			spin_unlock_bh(&tsk->sk.sk_lock.slock);
+		}
 	}
+	rcu_read_unlock();
 }
 
-/**
- * struct reference - TIPC socket reference entry
- * @tsk: pointer to socket associated with reference entry
- * @ref: reference value for socket (combines instance & array index info)
- */
-struct reference {
-	struct tipc_sock *tsk;
-	u32 ref;
-};
-
-/**
- * struct tipc_ref_table - table of TIPC socket reference entries
- * @entries: pointer to array of reference entries
- * @capacity: array index of first unusable entry
- * @init_point: array index of first uninitialized entry
- * @first_free: array index of first unused socket reference entry
- * @last_free: array index of last unused socket reference entry
- * @index_mask: bitmask for array index portion of reference values
- * @start_mask: initial value for instance value portion of reference values
- */
-struct ref_table {
-	struct reference *entries;
-	u32 capacity;
-	u32 init_point;
-	u32 first_free;
-	u32 last_free;
-	u32 index_mask;
-	u32 start_mask;
-};
-
-/* Socket reference table consists of 2**N entries.
- *
- * State	Socket ptr	Reference
- * -----        ----------      ---------
- * In use        non-NULL       XXXX|own index
- *				(XXXX changes each time entry is acquired)
- * Free            NULL         YYYY|next free index
- *				(YYYY is one more than last used XXXX)
- * Uninitialized   NULL         0
- *
- * Entry 0 is not used; this allows index 0 to denote the end of the free list.
- *
- * Note that a reference value of 0 does not necessarily indicate that an
- * entry is uninitialized, since the last entry in the free list could also
- * have a reference value of 0 (although this is unlikely).
- */
-
-static struct ref_table tipc_ref_table;
-
-static DEFINE_RWLOCK(ref_table_lock);
-
-/**
- * tipc_ref_table_init - create reference table for sockets
- */
-int tipc_sk_ref_table_init(u32 req_sz, u32 start)
+static struct tipc_sock *tipc_sk_lookup(struct net *net, u32 portid)
 {
-	struct reference *table;
-	u32 actual_sz;
-
-	/* account for unused entry, then round up size to a power of 2 */
-
-	req_sz++;
-	for (actual_sz = 16; actual_sz < req_sz; actual_sz <<= 1) {
-		/* do nothing */
-	};
-
-	/* allocate table & mark all entries as uninitialized */
-	table = vzalloc(actual_sz * sizeof(struct reference));
-	if (table == NULL)
-		return -ENOMEM;
-
-	tipc_ref_table.entries = table;
-	tipc_ref_table.capacity = req_sz;
-	tipc_ref_table.init_point = 1;
-	tipc_ref_table.first_free = 0;
-	tipc_ref_table.last_free = 0;
-	tipc_ref_table.index_mask = actual_sz - 1;
-	tipc_ref_table.start_mask = start & ~tipc_ref_table.index_mask;
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	struct tipc_sock *tsk;
 
-	return 0;
-}
+	rcu_read_lock();
+	tsk = rhashtable_lookup_fast(&tn->sk_rht, &portid, tsk_rht_params);
+	if (tsk)
+		sock_hold(&tsk->sk);
+	rcu_read_unlock();
 
-/**
- * tipc_ref_table_stop - destroy reference table for sockets
- */
-void tipc_sk_ref_table_stop(void)
-{
-	if (!tipc_ref_table.entries)
-		return;
-	vfree(tipc_ref_table.entries);
-	tipc_ref_table.entries = NULL;
+	return tsk;
 }
 
-/* tipc_ref_acquire - create reference to a socket
- *
- * Register an socket pointer in the reference table.
- * Returns a unique reference value that is used from then on to retrieve the
- * socket pointer, or to determine if the socket has been deregistered.
- */
-u32 tipc_sk_ref_acquire(struct tipc_sock *tsk)
+static int tipc_sk_insert(struct tipc_sock *tsk)
 {
-	u32 index;
-	u32 index_mask;
-	u32 next_plus_upper;
-	u32 ref = 0;
-	struct reference *entry;
-
-	if (unlikely(!tsk)) {
-		pr_err("Attempt to acquire ref. to non-existent obj\n");
-		return 0;
-	}
-	if (unlikely(!tipc_ref_table.entries)) {
-		pr_err("Ref. table not found in acquisition attempt\n");
-		return 0;
-	}
-
-	/* Take a free entry, if available; otherwise initialize a new one */
-	write_lock_bh(&ref_table_lock);
-	index = tipc_ref_table.first_free;
-	entry = &tipc_ref_table.entries[index];
-
-	if (likely(index)) {
-		index = tipc_ref_table.first_free;
-		entry = &tipc_ref_table.entries[index];
-		index_mask = tipc_ref_table.index_mask;
-		next_plus_upper = entry->ref;
-		tipc_ref_table.first_free = next_plus_upper & index_mask;
-		ref = (next_plus_upper & ~index_mask) + index;
-		entry->tsk = tsk;
-	} else if (tipc_ref_table.init_point < tipc_ref_table.capacity) {
-		index = tipc_ref_table.init_point++;
-		entry = &tipc_ref_table.entries[index];
-		ref = tipc_ref_table.start_mask + index;
+	struct sock *sk = &tsk->sk;
+	struct net *net = sock_net(sk);
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	u32 remaining = (TIPC_MAX_PORT - TIPC_MIN_PORT) + 1;
+	u32 portid = prandom_u32() % remaining + TIPC_MIN_PORT;
+
+	while (remaining--) {
+		portid++;
+		if ((portid < TIPC_MIN_PORT) || (portid > TIPC_MAX_PORT))
+			portid = TIPC_MIN_PORT;
+		tsk->portid = portid;
+		sock_hold(&tsk->sk);
+		if (!rhashtable_lookup_insert_fast(&tn->sk_rht, &tsk->node,
+						   tsk_rht_params))
+			return 0;
+		sock_put(&tsk->sk);
 	}
 
-	if (ref) {
-		entry->ref = ref;
-		entry->tsk = tsk;
-	}
-	write_unlock_bh(&ref_table_lock);
-	return ref;
+	return -1;
 }
 
-/* tipc_sk_ref_discard - invalidate reference to an socket
- *
- * Disallow future references to an socket and free up the entry for re-use.
- */
-void tipc_sk_ref_discard(u32 ref)
+static void tipc_sk_remove(struct tipc_sock *tsk)
 {
-	struct reference *entry;
-	u32 index;
-	u32 index_mask;
-
-	if (unlikely(!tipc_ref_table.entries)) {
-		pr_err("Ref. table not found during discard attempt\n");
-		return;
-	}
-
-	index_mask = tipc_ref_table.index_mask;
-	index = ref & index_mask;
-	entry = &tipc_ref_table.entries[index];
-
-	write_lock_bh(&ref_table_lock);
+	struct sock *sk = &tsk->sk;
+	struct tipc_net *tn = net_generic(sock_net(sk), tipc_net_id);
 
-	if (unlikely(!entry->tsk)) {
-		pr_err("Attempt to discard ref. to non-existent socket\n");
-		goto exit;
-	}
-	if (unlikely(entry->ref != ref)) {
-		pr_err("Attempt to discard non-existent reference\n");
-		goto exit;
+	if (!rhashtable_remove_fast(&tn->sk_rht, &tsk->node, tsk_rht_params)) {
+		WARN_ON(atomic_read(&sk->sk_refcnt) == 1);
+		__sock_put(sk);
 	}
-
-	/* Mark entry as unused; increment instance part of entry's
-	 *   reference to invalidate any subsequent references
-	 */
-
-	entry->tsk = NULL;
-	entry->ref = (ref & ~index_mask) + (index_mask + 1);
-
-	/* Append entry to free entry list */
-	if (unlikely(tipc_ref_table.first_free == 0))
-		tipc_ref_table.first_free = index;
-	else
-		tipc_ref_table.entries[tipc_ref_table.last_free].ref |= index;
-	tipc_ref_table.last_free = index;
-exit:
-	write_unlock_bh(&ref_table_lock);
 }
 
-/* tipc_sk_get - find referenced socket and return pointer to it
- */
-struct tipc_sock *tipc_sk_get(u32 ref)
+static const struct rhashtable_params tsk_rht_params = {
+	.nelem_hint = 192,
+	.head_offset = offsetof(struct tipc_sock, node),
+	.key_offset = offsetof(struct tipc_sock, portid),
+	.key_len = sizeof(u32), /* portid */
+	.max_size = 1048576,
+	.min_size = 256,
+	.automatic_shrinking = true,
+};
+
+int tipc_sk_rht_init(struct net *net)
 {
-	struct reference *entry;
-	struct tipc_sock *tsk;
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 
-	if (unlikely(!tipc_ref_table.entries))
-		return NULL;
-	read_lock_bh(&ref_table_lock);
-	entry = &tipc_ref_table.entries[ref & tipc_ref_table.index_mask];
-	tsk = entry->tsk;
-	if (likely(tsk && (entry->ref == ref)))
-		sock_hold(&tsk->sk);
-	else
-		tsk = NULL;
-	read_unlock_bh(&ref_table_lock);
-	return tsk;
+	return rhashtable_init(&tn->sk_rht, &tsk_rht_params);
 }
 
-/* tipc_sk_get_next - lock & return next socket after referenced one
-*/
-struct tipc_sock *tipc_sk_get_next(u32 *ref)
+void tipc_sk_rht_destroy(struct net *net)
 {
-	struct reference *entry;
-	struct tipc_sock *tsk = NULL;
-	uint index = *ref & tipc_ref_table.index_mask;
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 
-	read_lock_bh(&ref_table_lock);
-	while (++index < tipc_ref_table.capacity) {
-		entry = &tipc_ref_table.entries[index];
-		if (!entry->tsk)
-			continue;
-		tsk = entry->tsk;
-		sock_hold(&tsk->sk);
-		*ref = entry->ref;
-		break;
-	}
-	read_unlock_bh(&ref_table_lock);
-	return tsk;
-}
+	/* Wait for socket readers to complete */
+	synchronize_net();
 
-static void tipc_sk_put(struct tipc_sock *tsk)
-{
-	sock_put(&tsk->sk);
+	rhashtable_destroy(&tn->sk_rht);
 }
 
 /**
@@ -2664,8 +2453,9 @@ static int tipc_getsockopt(struct socket *sock, int lvl, int opt,
 	return put_user(sizeof(value), ol);
 }
 
-static int tipc_ioctl(struct socket *sk, unsigned int cmd, unsigned long arg)
+static int tipc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 {
+	struct sock *sk = sock->sk;
 	struct tipc_sioc_ln_req lnr;
 	void __user *argp = (void __user *)arg;
 
@@ -2673,7 +2463,8 @@ static int tipc_ioctl(struct socket *sk, unsigned int cmd, unsigned long arg)
 	case SIOCGETLINKNAME:
 		if (copy_from_user(&lnr, argp, sizeof(lnr)))
 			return -EFAULT;
-		if (!tipc_node_get_linkname(lnr.bearer_id & 0xffff, lnr.peer,
+		if (!tipc_node_get_linkname(sock_net(sk),
+					    lnr.bearer_id & 0xffff, lnr.peer,
 					    lnr.linkname, TIPC_MAX_LINK_NAME)) {
 			if (copy_to_user(argp, &lnr, sizeof(lnr)))
 				return -EFAULT;
@@ -2763,12 +2554,6 @@ static struct proto tipc_proto = {
 	.sysctl_rmem	= sysctl_tipc_rmem
 };
 
-static struct proto tipc_proto_kern = {
-	.name		= "TIPC",
-	.obj_size	= sizeof(struct tipc_sock),
-	.sysctl_rmem	= sysctl_tipc_rmem
-};
-
 /**
  * tipc_socket_init - initialize TIPC socket interface
  *
@@ -2802,3 +2587,251 @@ void tipc_socket_stop(void)
 	sock_unregister(tipc_family_ops.family);
 	proto_unregister(&tipc_proto);
 }
+
+/* Caller should hold socket lock for the passed tipc socket. */
+static int __tipc_nl_add_sk_con(struct sk_buff *skb, struct tipc_sock *tsk)
+{
+	u32 peer_node;
+	u32 peer_port;
+	struct nlattr *nest;
+
+	peer_node = tsk_peer_node(tsk);
+	peer_port = tsk_peer_port(tsk);
+
+	nest = nla_nest_start(skb, TIPC_NLA_SOCK_CON);
+
+	if (nla_put_u32(skb, TIPC_NLA_CON_NODE, peer_node))
+		goto msg_full;
+	if (nla_put_u32(skb, TIPC_NLA_CON_SOCK, peer_port))
+		goto msg_full;
+
+	if (tsk->conn_type != 0) {
+		if (nla_put_flag(skb, TIPC_NLA_CON_FLAG))
+			goto msg_full;
+		if (nla_put_u32(skb, TIPC_NLA_CON_TYPE, tsk->conn_type))
+			goto msg_full;
+		if (nla_put_u32(skb, TIPC_NLA_CON_INST, tsk->conn_instance))
+			goto msg_full;
+	}
+	nla_nest_end(skb, nest);
+
+	return 0;
+
+msg_full:
+	nla_nest_cancel(skb, nest);
+
+	return -EMSGSIZE;
+}
+
+/* Caller should hold socket lock for the passed tipc socket. */
+static int __tipc_nl_add_sk(struct sk_buff *skb, struct netlink_callback *cb,
+			    struct tipc_sock *tsk)
+{
+	int err;
+	void *hdr;
+	struct nlattr *attrs;
+	struct net *net = sock_net(skb->sk);
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+
+	hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+			  &tipc_genl_family, NLM_F_MULTI, TIPC_NL_SOCK_GET);
+	if (!hdr)
+		goto msg_cancel;
+
+	attrs = nla_nest_start(skb, TIPC_NLA_SOCK);
+	if (!attrs)
+		goto genlmsg_cancel;
+	if (nla_put_u32(skb, TIPC_NLA_SOCK_REF, tsk->portid))
+		goto attr_msg_cancel;
+	if (nla_put_u32(skb, TIPC_NLA_SOCK_ADDR, tn->own_addr))
+		goto attr_msg_cancel;
+
+	if (tsk->connected) {
+		err = __tipc_nl_add_sk_con(skb, tsk);
+		if (err)
+			goto attr_msg_cancel;
+	} else if (!list_empty(&tsk->publications)) {
+		if (nla_put_flag(skb, TIPC_NLA_SOCK_HAS_PUBL))
+			goto attr_msg_cancel;
+	}
+	nla_nest_end(skb, attrs);
+	genlmsg_end(skb, hdr);
+
+	return 0;
+
+attr_msg_cancel:
+	nla_nest_cancel(skb, attrs);
+genlmsg_cancel:
+	genlmsg_cancel(skb, hdr);
+msg_cancel:
+	return -EMSGSIZE;
+}
+
+int tipc_nl_sk_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	int err;
+	struct tipc_sock *tsk;
+	const struct bucket_table *tbl;
+	struct rhash_head *pos;
+	struct net *net = sock_net(skb->sk);
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	u32 tbl_id = cb->args[0];
+	u32 prev_portid = cb->args[1];
+
+	rcu_read_lock();
+	tbl = rht_dereference_rcu((&tn->sk_rht)->tbl, &tn->sk_rht);
+	for (; tbl_id < tbl->size; tbl_id++) {
+		rht_for_each_entry_rcu(tsk, pos, tbl, tbl_id, node) {
+			spin_lock_bh(&tsk->sk.sk_lock.slock);
+			if (prev_portid && prev_portid != tsk->portid) {
+				spin_unlock_bh(&tsk->sk.sk_lock.slock);
+				continue;
+			}
+
+			err = __tipc_nl_add_sk(skb, cb, tsk);
+			if (err) {
+				prev_portid = tsk->portid;
+				spin_unlock_bh(&tsk->sk.sk_lock.slock);
+				goto out;
+			}
+			prev_portid = 0;
+			spin_unlock_bh(&tsk->sk.sk_lock.slock);
+		}
+	}
+out:
+	rcu_read_unlock();
+	cb->args[0] = tbl_id;
+	cb->args[1] = prev_portid;
+
+	return skb->len;
+}
+
+/* Caller should hold socket lock for the passed tipc socket. */
+static int __tipc_nl_add_sk_publ(struct sk_buff *skb,
+				 struct netlink_callback *cb,
+				 struct publication *publ)
+{
+	void *hdr;
+	struct nlattr *attrs;
+
+	hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+			  &tipc_genl_family, NLM_F_MULTI, TIPC_NL_PUBL_GET);
+	if (!hdr)
+		goto msg_cancel;
+
+	attrs = nla_nest_start(skb, TIPC_NLA_PUBL);
+	if (!attrs)
+		goto genlmsg_cancel;
+
+	if (nla_put_u32(skb, TIPC_NLA_PUBL_KEY, publ->key))
+		goto attr_msg_cancel;
+	if (nla_put_u32(skb, TIPC_NLA_PUBL_TYPE, publ->type))
+		goto attr_msg_cancel;
+	if (nla_put_u32(skb, TIPC_NLA_PUBL_LOWER, publ->lower))
+		goto attr_msg_cancel;
+	if (nla_put_u32(skb, TIPC_NLA_PUBL_UPPER, publ->upper))
+		goto attr_msg_cancel;
+
+	nla_nest_end(skb, attrs);
+	genlmsg_end(skb, hdr);
+
+	return 0;
+
+attr_msg_cancel:
+	nla_nest_cancel(skb, attrs);
+genlmsg_cancel:
+	genlmsg_cancel(skb, hdr);
+msg_cancel:
+	return -EMSGSIZE;
+}
+
+/* Caller should hold socket lock for the passed tipc socket. */
+static int __tipc_nl_list_sk_publ(struct sk_buff *skb,
+				  struct netlink_callback *cb,
+				  struct tipc_sock *tsk, u32 *last_publ)
+{
+	int err;
+	struct publication *p;
+
+	if (*last_publ) {
+		list_for_each_entry(p, &tsk->publications, pport_list) {
+			if (p->key == *last_publ)
+				break;
+		}
+		if (p->key != *last_publ) {
+			/* We never set seq or call nl_dump_check_consistent()
+			 * this means that setting prev_seq here will cause the
+			 * consistence check to fail in the netlink callback
+			 * handler. Resulting in the last NLMSG_DONE message
+			 * having the NLM_F_DUMP_INTR flag set.
+			 */
+			cb->prev_seq = 1;
+			*last_publ = 0;
+			return -EPIPE;
+		}
+	} else {
+		p = list_first_entry(&tsk->publications, struct publication,
+				     pport_list);
+	}
+
+	list_for_each_entry_from(p, &tsk->publications, pport_list) {
+		err = __tipc_nl_add_sk_publ(skb, cb, p);
+		if (err) {
+			*last_publ = p->key;
+			return err;
+		}
+	}
+	*last_publ = 0;
+
+	return 0;
+}
+
+int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	int err;
+	u32 tsk_portid = cb->args[0];
+	u32 last_publ = cb->args[1];
+	u32 done = cb->args[2];
+	struct net *net = sock_net(skb->sk);
+	struct tipc_sock *tsk;
+
+	if (!tsk_portid) {
+		struct nlattr **attrs;
+		struct nlattr *sock[TIPC_NLA_SOCK_MAX + 1];
+
+		err = tipc_nlmsg_parse(cb->nlh, &attrs);
+		if (err)
+			return err;
+
+		err = nla_parse_nested(sock, TIPC_NLA_SOCK_MAX,
+				       attrs[TIPC_NLA_SOCK],
+				       tipc_nl_sock_policy);
+		if (err)
+			return err;
+
+		if (!sock[TIPC_NLA_SOCK_REF])
+			return -EINVAL;
+
+		tsk_portid = nla_get_u32(sock[TIPC_NLA_SOCK_REF]);
+	}
+
+	if (done)
+		return 0;
+
+	tsk = tipc_sk_lookup(net, tsk_portid);
+	if (!tsk)
+		return -EINVAL;
+
+	lock_sock(&tsk->sk);
+	err = __tipc_nl_list_sk_publ(skb, cb, tsk, &last_publ);
+	if (!err)
+		done = 1;
+	release_sock(&tsk->sk);
+	sock_put(&tsk->sk);
+
+	cb->args[0] = tsk_portid;
+	cb->args[1] = last_publ;
+	cb->args[2] = done;
+
+	return skb->len;
+}
diff --git a/net/tipc/socket.h b/net/tipc/socket.h
index baa43d03901e..bf6551389522 100644
--- a/net/tipc/socket.h
+++ b/net/tipc/socket.h
@@ -1,6 +1,6 @@
 /* net/tipc/socket.h: Include file for TIPC socket code
  *
- * Copyright (c) 2014, Ericsson AB
+ * Copyright (c) 2014-2015, Ericsson AB
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -36,16 +36,21 @@
 #define _TIPC_SOCK_H
 
 #include <net/sock.h>
+#include <net/genetlink.h>
 
 #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))
-int tipc_sk_rcv(struct sk_buff *buf);
-struct sk_buff *tipc_sk_socks_show(void);
-void tipc_sk_mcast_rcv(struct sk_buff *buf);
-void tipc_sk_reinit(void);
-int tipc_sk_ref_table_init(u32 requested_size, u32 start);
-void tipc_sk_ref_table_stop(void);
+int tipc_socket_init(void);
+void tipc_socket_stop(void);
+int tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq);
+void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
+		       struct sk_buff_head *inputq);
+void tipc_sk_reinit(struct net *net);
+int tipc_sk_rht_init(struct net *net);
+void tipc_sk_rht_destroy(struct net *net);
+int tipc_nl_sk_dump(struct sk_buff *skb, struct netlink_callback *cb);
+int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb);
 
 #endif
diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c
index 31b5cb232a43..1c147c869c2e 100644
--- a/net/tipc/subscr.c
+++ b/net/tipc/subscr.c
@@ -50,33 +50,6 @@ struct tipc_subscriber {
 	struct list_head subscription_list;
 };
 
-static void subscr_conn_msg_event(int conid, struct sockaddr_tipc *addr,
-				  void *usr_data, void *buf, size_t len);
-static void *subscr_named_msg_event(int conid);
-static void subscr_conn_shutdown_event(int conid, void *usr_data);
-
-static atomic_t subscription_count = ATOMIC_INIT(0);
-
-static struct sockaddr_tipc topsrv_addr __read_mostly = {
-	.family			= AF_TIPC,
-	.addrtype		= TIPC_ADDR_NAMESEQ,
-	.addr.nameseq.type	= TIPC_TOP_SRV,
-	.addr.nameseq.lower	= TIPC_TOP_SRV,
-	.addr.nameseq.upper	= TIPC_TOP_SRV,
-	.scope			= TIPC_NODE_SCOPE
-};
-
-static struct tipc_server topsrv __read_mostly = {
-	.saddr			= &topsrv_addr,
-	.imp			= TIPC_CRITICAL_IMPORTANCE,
-	.type			= SOCK_SEQPACKET,
-	.max_rcvbuf_size	= sizeof(struct tipc_subscr),
-	.name			= "topology_server",
-	.tipc_conn_recvmsg	= subscr_conn_msg_event,
-	.tipc_conn_new		= subscr_named_msg_event,
-	.tipc_conn_shutdown	= subscr_conn_shutdown_event,
-};
-
 /**
  * htohl - convert value to endianness used by destination
  * @in: value to convert
@@ -93,6 +66,7 @@ static void subscr_send_event(struct tipc_subscription *sub, u32 found_lower,
 			      u32 found_upper, u32 event, u32 port_ref,
 			      u32 node)
 {
+	struct tipc_net *tn = net_generic(sub->net, tipc_net_id);
 	struct tipc_subscriber *subscriber = sub->subscriber;
 	struct kvec msg_sect;
 
@@ -103,8 +77,8 @@ static void subscr_send_event(struct tipc_subscription *sub, u32 found_lower,
 	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);
-	tipc_conn_sendmsg(&topsrv, subscriber->conid, NULL, msg_sect.iov_base,
-			  msg_sect.iov_len);
+	tipc_conn_sendmsg(tn->topsrv, subscriber->conid, NULL,
+			  msg_sect.iov_base, msg_sect.iov_len);
 }
 
 /**
@@ -141,9 +115,11 @@ void tipc_subscr_report_overlap(struct tipc_subscription *sub, u32 found_lower,
 	subscr_send_event(sub, found_lower, found_upper, event, port_ref, node);
 }
 
-static void subscr_timeout(struct tipc_subscription *sub)
+static void subscr_timeout(unsigned long data)
 {
+	struct tipc_subscription *sub = (struct tipc_subscription *)data;
 	struct tipc_subscriber *subscriber = sub->subscriber;
+	struct tipc_net *tn = net_generic(sub->net, tipc_net_id);
 
 	/* The spin lock per subscriber is used to protect its members */
 	spin_lock_bh(&subscriber->lock);
@@ -167,9 +143,8 @@ static void subscr_timeout(struct tipc_subscription *sub)
 			  TIPC_SUBSCR_TIMEOUT, 0, 0);
 
 	/* Now destroy subscription */
-	k_term_timer(&sub->timer);
 	kfree(sub);
-	atomic_dec(&subscription_count);
+	atomic_dec(&tn->subscription_count);
 }
 
 /**
@@ -179,20 +154,12 @@ static void subscr_timeout(struct tipc_subscription *sub)
  */
 static void subscr_del(struct tipc_subscription *sub)
 {
+	struct tipc_net *tn = net_generic(sub->net, tipc_net_id);
+
 	tipc_nametbl_unsubscribe(sub);
 	list_del(&sub->subscription_list);
 	kfree(sub);
-	atomic_dec(&subscription_count);
-}
-
-/**
- * subscr_terminate - terminate communication with a subscriber
- *
- * Note: Must call it in process context since it might sleep.
- */
-static void subscr_terminate(struct tipc_subscriber *subscriber)
-{
-	tipc_conn_terminate(&topsrv, subscriber->conid);
+	atomic_dec(&tn->subscription_count);
 }
 
 static void subscr_release(struct tipc_subscriber *subscriber)
@@ -207,8 +174,7 @@ static void subscr_release(struct tipc_subscriber *subscriber)
 				 subscription_list) {
 		if (sub->timeout != TIPC_WAIT_FOREVER) {
 			spin_unlock_bh(&subscriber->lock);
-			k_cancel_timer(&sub->timer);
-			k_term_timer(&sub->timer);
+			del_timer_sync(&sub->timer);
 			spin_lock_bh(&subscriber->lock);
 		}
 		subscr_del(sub);
@@ -250,8 +216,7 @@ static void subscr_cancel(struct tipc_subscr *s,
 	if (sub->timeout != TIPC_WAIT_FOREVER) {
 		sub->timeout = TIPC_WAIT_FOREVER;
 		spin_unlock_bh(&subscriber->lock);
-		k_cancel_timer(&sub->timer);
-		k_term_timer(&sub->timer);
+		del_timer_sync(&sub->timer);
 		spin_lock_bh(&subscriber->lock);
 	}
 	subscr_del(sub);
@@ -262,9 +227,11 @@ static void subscr_cancel(struct tipc_subscr *s,
  *
  * Called with subscriber lock held.
  */
-static int subscr_subscribe(struct tipc_subscr *s,
+static int subscr_subscribe(struct net *net, struct tipc_subscr *s,
 			    struct tipc_subscriber *subscriber,
-			    struct tipc_subscription **sub_p) {
+			    struct tipc_subscription **sub_p)
+{
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	struct tipc_subscription *sub;
 	int swap;
 
@@ -279,7 +246,7 @@ static int subscr_subscribe(struct tipc_subscr *s,
 	}
 
 	/* Refuse subscription if global limit exceeded */
-	if (atomic_read(&subscription_count) >= TIPC_MAX_SUBSCRIPTIONS) {
+	if (atomic_read(&tn->subscription_count) >= TIPC_MAX_SUBSCRIPTIONS) {
 		pr_warn("Subscription rejected, limit reached (%u)\n",
 			TIPC_MAX_SUBSCRIPTIONS);
 		return -EINVAL;
@@ -293,10 +260,11 @@ static int subscr_subscribe(struct tipc_subscr *s,
 	}
 
 	/* Initialize subscription object */
+	sub->net = net;
 	sub->seq.type = htohl(s->seq.type, swap);
 	sub->seq.lower = htohl(s->seq.lower, swap);
 	sub->seq.upper = htohl(s->seq.upper, swap);
-	sub->timeout = htohl(s->timeout, swap);
+	sub->timeout = msecs_to_jiffies(htohl(s->timeout, swap));
 	sub->filter = htohl(s->filter, swap);
 	if ((!(sub->filter & TIPC_SUB_PORTS) ==
 	     !(sub->filter & TIPC_SUB_SERVICE)) ||
@@ -305,16 +273,14 @@ static int subscr_subscribe(struct tipc_subscr *s,
 		kfree(sub);
 		return -EINVAL;
 	}
-	INIT_LIST_HEAD(&sub->nameseq_list);
 	list_add(&sub->subscription_list, &subscriber->subscription_list);
 	sub->subscriber = subscriber;
 	sub->swap = swap;
 	memcpy(&sub->evt.s, s, sizeof(struct tipc_subscr));
-	atomic_inc(&subscription_count);
+	atomic_inc(&tn->subscription_count);
 	if (sub->timeout != TIPC_WAIT_FOREVER) {
-		k_init_timer(&sub->timer,
-			     (Handler)subscr_timeout, (unsigned long)sub);
-		k_start_timer(&sub->timer, sub->timeout);
+		setup_timer(&sub->timer, subscr_timeout, (unsigned long)sub);
+		mod_timer(&sub->timer, jiffies + sub->timeout);
 	}
 	*sub_p = sub;
 	return 0;
@@ -327,24 +293,23 @@ static void subscr_conn_shutdown_event(int conid, void *usr_data)
 }
 
 /* Handle one request to create a new subscription for the subscriber */
-static void subscr_conn_msg_event(int conid, struct sockaddr_tipc *addr,
-				  void *usr_data, void *buf, size_t len)
+static void subscr_conn_msg_event(struct net *net, int conid,
+				  struct sockaddr_tipc *addr, void *usr_data,
+				  void *buf, size_t len)
 {
 	struct tipc_subscriber *subscriber = usr_data;
 	struct tipc_subscription *sub = NULL;
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 
 	spin_lock_bh(&subscriber->lock);
-	if (subscr_subscribe((struct tipc_subscr *)buf, subscriber, &sub) < 0) {
-		spin_unlock_bh(&subscriber->lock);
-		subscr_terminate(subscriber);
-		return;
-	}
+	subscr_subscribe(net, (struct tipc_subscr *)buf, subscriber, &sub);
 	if (sub)
 		tipc_nametbl_subscribe(sub);
+	else
+		tipc_conn_terminate(tn->topsrv, subscriber->conid);
 	spin_unlock_bh(&subscriber->lock);
 }
 
-
 /* Handle one request to establish a new subscriber */
 static void *subscr_named_msg_event(int conid)
 {
@@ -363,12 +328,50 @@ static void *subscr_named_msg_event(int conid)
 	return (void *)subscriber;
 }
 
-int tipc_subscr_start(void)
+int tipc_subscr_start(struct net *net)
 {
-	return tipc_server_start(&topsrv);
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	const char name[] = "topology_server";
+	struct tipc_server *topsrv;
+	struct sockaddr_tipc *saddr;
+
+	saddr = kzalloc(sizeof(*saddr), GFP_ATOMIC);
+	if (!saddr)
+		return -ENOMEM;
+	saddr->family			= AF_TIPC;
+	saddr->addrtype			= TIPC_ADDR_NAMESEQ;
+	saddr->addr.nameseq.type	= TIPC_TOP_SRV;
+	saddr->addr.nameseq.lower	= TIPC_TOP_SRV;
+	saddr->addr.nameseq.upper	= TIPC_TOP_SRV;
+	saddr->scope			= TIPC_NODE_SCOPE;
+
+	topsrv = kzalloc(sizeof(*topsrv), GFP_ATOMIC);
+	if (!topsrv) {
+		kfree(saddr);
+		return -ENOMEM;
+	}
+	topsrv->net			= net;
+	topsrv->saddr			= saddr;
+	topsrv->imp			= TIPC_CRITICAL_IMPORTANCE;
+	topsrv->type			= SOCK_SEQPACKET;
+	topsrv->max_rcvbuf_size		= sizeof(struct tipc_subscr);
+	topsrv->tipc_conn_recvmsg	= subscr_conn_msg_event;
+	topsrv->tipc_conn_new		= subscr_named_msg_event;
+	topsrv->tipc_conn_shutdown	= subscr_conn_shutdown_event;
+
+	strncpy(topsrv->name, name, strlen(name) + 1);
+	tn->topsrv = topsrv;
+	atomic_set(&tn->subscription_count, 0);
+
+	return tipc_server_start(topsrv);
 }
 
-void tipc_subscr_stop(void)
+void tipc_subscr_stop(struct net *net)
 {
-	tipc_server_stop(&topsrv);
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	struct tipc_server *topsrv = tn->topsrv;
+
+	tipc_server_stop(topsrv);
+	kfree(topsrv->saddr);
+	kfree(topsrv);
 }
diff --git a/net/tipc/subscr.h b/net/tipc/subscr.h
index 393e417bee3f..33488bd9fe3c 100644
--- a/net/tipc/subscr.h
+++ b/net/tipc/subscr.h
@@ -39,6 +39,9 @@
 
 #include "server.h"
 
+#define TIPC_MAX_SUBSCRIPTIONS	65535
+#define TIPC_MAX_PUBLICATIONS	65535
+
 struct tipc_subscription;
 struct tipc_subscriber;
 
@@ -46,6 +49,7 @@ struct tipc_subscriber;
  * struct tipc_subscription - TIPC network topology subscription object
  * @subscriber: pointer to its subscriber
  * @seq: name sequence associated with subscription
+ * @net: point to network namespace
  * @timeout: duration of subscription (in ms)
  * @filter: event filtering to be done for subscription
  * @timer: timer governing subscription duration (optional)
@@ -58,7 +62,8 @@ struct tipc_subscriber;
 struct tipc_subscription {
 	struct tipc_subscriber *subscriber;
 	struct tipc_name_seq seq;
-	u32 timeout;
+	struct net *net;
+	unsigned long timeout;
 	u32 filter;
 	struct timer_list timer;
 	struct list_head nameseq_list;
@@ -69,13 +74,10 @@ struct tipc_subscription {
 
 int tipc_subscr_overlap(struct tipc_subscription *sub, u32 found_lower,
 			u32 found_upper);
-
 void tipc_subscr_report_overlap(struct tipc_subscription *sub, u32 found_lower,
 				u32 found_upper, u32 event, u32 port_ref,
 				u32 node, int must);
-
-int tipc_subscr_start(void);
-
-void tipc_subscr_stop(void);
+int tipc_subscr_start(struct net *net);
+void tipc_subscr_stop(struct net *net);
 
 #endif
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
new file mode 100644
index 000000000000..66deebc66aa1
--- /dev/null
+++ b/net/tipc/udp_media.c
@@ -0,0 +1,448 @@
+/* net/tipc/udp_media.c: IP bearer support for TIPC
+ *
+ * Copyright (c) 2015, 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.
+ */
+
+#include <linux/socket.h>
+#include <linux/ip.h>
+#include <linux/udp.h>
+#include <linux/inet.h>
+#include <linux/inetdevice.h>
+#include <linux/igmp.h>
+#include <linux/kernel.h>
+#include <linux/workqueue.h>
+#include <linux/list.h>
+#include <net/sock.h>
+#include <net/ip.h>
+#include <net/udp_tunnel.h>
+#include <net/addrconf.h>
+#include <linux/tipc_netlink.h>
+#include "core.h"
+#include "bearer.h"
+
+/* IANA assigned UDP port */
+#define UDP_PORT_DEFAULT	6118
+
+static const struct nla_policy tipc_nl_udp_policy[TIPC_NLA_UDP_MAX + 1] = {
+	[TIPC_NLA_UDP_UNSPEC]	= {.type = NLA_UNSPEC},
+	[TIPC_NLA_UDP_LOCAL]	= {.type = NLA_BINARY,
+				   .len = sizeof(struct sockaddr_storage)},
+	[TIPC_NLA_UDP_REMOTE]	= {.type = NLA_BINARY,
+				   .len = sizeof(struct sockaddr_storage)},
+};
+
+/**
+ * struct udp_media_addr - IP/UDP addressing information
+ *
+ * This is the bearer level originating address used in neighbor discovery
+ * messages, and all fields should be in network byte order
+ */
+struct udp_media_addr {
+	__be16	proto;
+	__be16	udp_port;
+	union {
+		struct in_addr ipv4;
+		struct in6_addr ipv6;
+	};
+};
+
+/**
+ * struct udp_bearer - ip/udp bearer data structure
+ * @bearer:	associated generic tipc bearer
+ * @ubsock:	bearer associated socket
+ * @ifindex:	local address scope
+ * @work:	used to schedule deferred work on a bearer
+ */
+struct udp_bearer {
+	struct tipc_bearer __rcu *bearer;
+	struct socket *ubsock;
+	u32 ifindex;
+	struct work_struct work;
+};
+
+/* udp_media_addr_set - convert a ip/udp address to a TIPC media address */
+static void tipc_udp_media_addr_set(struct tipc_media_addr *addr,
+				    struct udp_media_addr *ua)
+{
+	memset(addr, 0, sizeof(struct tipc_media_addr));
+	addr->media_id = TIPC_MEDIA_TYPE_UDP;
+	memcpy(addr->value, ua, sizeof(struct udp_media_addr));
+	if (ntohs(ua->proto) == ETH_P_IP) {
+		if (ipv4_is_multicast(ua->ipv4.s_addr))
+			addr->broadcast = 1;
+	} else if (ntohs(ua->proto) == ETH_P_IPV6) {
+		if (ipv6_addr_type(&ua->ipv6) & IPV6_ADDR_MULTICAST)
+			addr->broadcast = 1;
+	} else {
+		pr_err("Invalid UDP media address\n");
+	}
+}
+
+/* tipc_udp_addr2str - convert ip/udp address to string */
+static int tipc_udp_addr2str(struct tipc_media_addr *a, char *buf, int size)
+{
+	struct udp_media_addr *ua = (struct udp_media_addr *)&a->value;
+
+	if (ntohs(ua->proto) == ETH_P_IP)
+		snprintf(buf, size, "%pI4:%u", &ua->ipv4, ntohs(ua->udp_port));
+	else if (ntohs(ua->proto) == ETH_P_IPV6)
+		snprintf(buf, size, "%pI6:%u", &ua->ipv6, ntohs(ua->udp_port));
+	else
+		pr_err("Invalid UDP media address\n");
+	return 0;
+}
+
+/* tipc_udp_msg2addr - extract an ip/udp address from a TIPC ndisc message */
+static int tipc_udp_msg2addr(struct tipc_bearer *b, struct tipc_media_addr *a,
+			     char *msg)
+{
+	struct udp_media_addr *ua;
+
+	ua = (struct udp_media_addr *) (msg + TIPC_MEDIA_ADDR_OFFSET);
+	if (msg[TIPC_MEDIA_TYPE_OFFSET] != TIPC_MEDIA_TYPE_UDP)
+		return -EINVAL;
+	tipc_udp_media_addr_set(a, ua);
+	return 0;
+}
+
+/* tipc_udp_addr2msg - write an ip/udp address to a TIPC ndisc message */
+static int tipc_udp_addr2msg(char *msg, struct tipc_media_addr *a)
+{
+	memset(msg, 0, TIPC_MEDIA_INFO_SIZE);
+	msg[TIPC_MEDIA_TYPE_OFFSET] = TIPC_MEDIA_TYPE_UDP;
+	memcpy(msg + TIPC_MEDIA_ADDR_OFFSET, a->value,
+	       sizeof(struct udp_media_addr));
+	return 0;
+}
+
+/* tipc_send_msg - enqueue a send request */
+static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb,
+			     struct tipc_bearer *b,
+			     struct tipc_media_addr *dest)
+{
+	int ttl, err = 0;
+	struct udp_bearer *ub;
+	struct udp_media_addr *dst = (struct udp_media_addr *)&dest->value;
+	struct udp_media_addr *src = (struct udp_media_addr *)&b->addr.value;
+	struct sk_buff *clone;
+	struct rtable *rt;
+
+	clone = skb_clone(skb, GFP_ATOMIC);
+	skb_set_inner_protocol(clone, htons(ETH_P_TIPC));
+	ub = rcu_dereference_rtnl(b->media_ptr);
+	if (!ub) {
+		err = -ENODEV;
+		goto tx_error;
+	}
+	if (dst->proto == htons(ETH_P_IP)) {
+		struct flowi4 fl = {
+			.daddr = dst->ipv4.s_addr,
+			.saddr = src->ipv4.s_addr,
+			.flowi4_mark = clone->mark,
+			.flowi4_proto = IPPROTO_UDP
+		};
+		rt = ip_route_output_key(net, &fl);
+		if (IS_ERR(rt)) {
+			err = PTR_ERR(rt);
+			goto tx_error;
+		}
+		ttl = ip4_dst_hoplimit(&rt->dst);
+		err = udp_tunnel_xmit_skb(rt, ub->ubsock->sk, clone,
+					  src->ipv4.s_addr,
+					  dst->ipv4.s_addr, 0, ttl, 0,
+					  src->udp_port, dst->udp_port,
+					  false, true);
+		if (err < 0) {
+			ip_rt_put(rt);
+			goto tx_error;
+		}
+#if IS_ENABLED(CONFIG_IPV6)
+	} else {
+		struct dst_entry *ndst;
+		struct flowi6 fl6 = {
+			.flowi6_oif = ub->ifindex,
+			.daddr = dst->ipv6,
+			.saddr = src->ipv6,
+			.flowi6_proto = IPPROTO_UDP
+		};
+		err = ipv6_stub->ipv6_dst_lookup(ub->ubsock->sk, &ndst, &fl6);
+		if (err)
+			goto tx_error;
+		ttl = ip6_dst_hoplimit(ndst);
+		err = udp_tunnel6_xmit_skb(ndst, ub->ubsock->sk, clone,
+					   ndst->dev, &src->ipv6,
+					   &dst->ipv6, 0, ttl, src->udp_port,
+					   dst->udp_port, false);
+#endif
+	}
+	return err;
+
+tx_error:
+	kfree_skb(clone);
+	return err;
+}
+
+/* tipc_udp_recv - read data from bearer socket */
+static int tipc_udp_recv(struct sock *sk, struct sk_buff *skb)
+{
+	struct udp_bearer *ub;
+	struct tipc_bearer *b;
+
+	ub = rcu_dereference_sk_user_data(sk);
+	if (!ub) {
+		pr_err_ratelimited("Failed to get UDP bearer reference");
+		kfree_skb(skb);
+		return 0;
+	}
+
+	skb_pull(skb, sizeof(struct udphdr));
+	rcu_read_lock();
+	b = rcu_dereference_rtnl(ub->bearer);
+
+	if (b) {
+		tipc_rcv(sock_net(sk), skb, b);
+		rcu_read_unlock();
+		return 0;
+	}
+	rcu_read_unlock();
+	kfree_skb(skb);
+	return 0;
+}
+
+static int enable_mcast(struct udp_bearer *ub, struct udp_media_addr *remote)
+{
+	int err = 0;
+	struct ip_mreqn mreqn;
+	struct sock *sk = ub->ubsock->sk;
+
+	if (ntohs(remote->proto) == ETH_P_IP) {
+		if (!ipv4_is_multicast(remote->ipv4.s_addr))
+			return 0;
+		mreqn.imr_multiaddr = remote->ipv4;
+		mreqn.imr_ifindex = ub->ifindex;
+		err = ip_mc_join_group(sk, &mreqn);
+#if IS_ENABLED(CONFIG_IPV6)
+	} else {
+		if (!ipv6_addr_is_multicast(&remote->ipv6))
+			return 0;
+		err = ipv6_stub->ipv6_sock_mc_join(sk, ub->ifindex,
+						   &remote->ipv6);
+#endif
+	}
+	return err;
+}
+
+/**
+ * parse_options - build local/remote addresses from configuration
+ * @attrs:	netlink config data
+ * @ub:		UDP bearer instance
+ * @local:	local bearer IP address/port
+ * @remote:	peer or multicast IP/port
+ */
+static int parse_options(struct nlattr *attrs[], struct udp_bearer *ub,
+			 struct udp_media_addr *local,
+			 struct udp_media_addr *remote)
+{
+	struct nlattr *opts[TIPC_NLA_UDP_MAX + 1];
+	struct sockaddr_storage *sa_local, *sa_remote;
+
+	if (!attrs[TIPC_NLA_BEARER_UDP_OPTS])
+		goto err;
+	if (nla_parse_nested(opts, TIPC_NLA_UDP_MAX,
+			     attrs[TIPC_NLA_BEARER_UDP_OPTS],
+			     tipc_nl_udp_policy))
+		goto err;
+	if (opts[TIPC_NLA_UDP_LOCAL] && opts[TIPC_NLA_UDP_REMOTE]) {
+		sa_local = nla_data(opts[TIPC_NLA_UDP_LOCAL]);
+		sa_remote = nla_data(opts[TIPC_NLA_UDP_REMOTE]);
+	} else {
+err:
+		pr_err("Invalid UDP bearer configuration");
+		return -EINVAL;
+	}
+	if ((sa_local->ss_family & sa_remote->ss_family) == AF_INET) {
+		struct sockaddr_in *ip4;
+
+		ip4 = (struct sockaddr_in *)sa_local;
+		local->proto = htons(ETH_P_IP);
+		local->udp_port = ip4->sin_port;
+		local->ipv4.s_addr = ip4->sin_addr.s_addr;
+
+		ip4 = (struct sockaddr_in *)sa_remote;
+		remote->proto = htons(ETH_P_IP);
+		remote->udp_port = ip4->sin_port;
+		remote->ipv4.s_addr = ip4->sin_addr.s_addr;
+		return 0;
+
+#if IS_ENABLED(CONFIG_IPV6)
+	} else if ((sa_local->ss_family & sa_remote->ss_family) == AF_INET6) {
+		struct sockaddr_in6 *ip6;
+
+		ip6 = (struct sockaddr_in6 *)sa_local;
+		local->proto = htons(ETH_P_IPV6);
+		local->udp_port = ip6->sin6_port;
+		local->ipv6 = ip6->sin6_addr;
+		ub->ifindex = ip6->sin6_scope_id;
+
+		ip6 = (struct sockaddr_in6 *)sa_remote;
+		remote->proto = htons(ETH_P_IPV6);
+		remote->udp_port = ip6->sin6_port;
+		remote->ipv6 = ip6->sin6_addr;
+		return 0;
+#endif
+	}
+	return -EADDRNOTAVAIL;
+}
+
+/**
+ * tipc_udp_enable - callback to create a new udp bearer instance
+ * @net:	network namespace
+ * @b:		pointer to generic tipc_bearer
+ * @attrs:	netlink bearer configuration
+ *
+ * validate the bearer parameters and initialize the udp bearer
+ * rtnl_lock should be held
+ */
+static int tipc_udp_enable(struct net *net, struct tipc_bearer *b,
+			   struct nlattr *attrs[])
+{
+	int err = -EINVAL;
+	struct udp_bearer *ub;
+	struct udp_media_addr *remote;
+	struct udp_media_addr local = {0};
+	struct udp_port_cfg udp_conf = {0};
+	struct udp_tunnel_sock_cfg tuncfg = {NULL};
+
+	ub = kzalloc(sizeof(*ub), GFP_ATOMIC);
+	if (!ub)
+		return -ENOMEM;
+
+	remote = (struct udp_media_addr *)&b->bcast_addr.value;
+	memset(remote, 0, sizeof(struct udp_media_addr));
+	err = parse_options(attrs, ub, &local, remote);
+	if (err)
+		goto err;
+
+	b->bcast_addr.media_id = TIPC_MEDIA_TYPE_UDP;
+	b->bcast_addr.broadcast = 1;
+	rcu_assign_pointer(b->media_ptr, ub);
+	rcu_assign_pointer(ub->bearer, b);
+	tipc_udp_media_addr_set(&b->addr, &local);
+	if (local.proto == htons(ETH_P_IP)) {
+		struct net_device *dev;
+
+		dev = __ip_dev_find(net, local.ipv4.s_addr, false);
+		if (!dev) {
+			err = -ENODEV;
+			goto err;
+		}
+		udp_conf.family = AF_INET;
+		udp_conf.local_ip.s_addr = htonl(INADDR_ANY);
+		udp_conf.use_udp_checksums = false;
+		ub->ifindex = dev->ifindex;
+		b->mtu = dev->mtu - sizeof(struct iphdr)
+			- sizeof(struct udphdr);
+#if IS_ENABLED(CONFIG_IPV6)
+	} else if (local.proto == htons(ETH_P_IPV6)) {
+		udp_conf.family = AF_INET6;
+		udp_conf.use_udp6_tx_checksums = true;
+		udp_conf.use_udp6_rx_checksums = true;
+		udp_conf.local_ip6 = in6addr_any;
+		b->mtu = 1280;
+#endif
+	} else {
+		err = -EAFNOSUPPORT;
+		goto err;
+	}
+	udp_conf.local_udp_port = local.udp_port;
+	err = udp_sock_create(net, &udp_conf, &ub->ubsock);
+	if (err)
+		goto err;
+	tuncfg.sk_user_data = ub;
+	tuncfg.encap_type = 1;
+	tuncfg.encap_rcv = tipc_udp_recv;
+	tuncfg.encap_destroy = NULL;
+	setup_udp_tunnel_sock(net, ub->ubsock, &tuncfg);
+
+	if (enable_mcast(ub, remote))
+		goto err;
+	return 0;
+err:
+	kfree(ub);
+	return err;
+}
+
+/* cleanup_bearer - break the socket/bearer association */
+static void cleanup_bearer(struct work_struct *work)
+{
+	struct udp_bearer *ub = container_of(work, struct udp_bearer, work);
+
+	if (ub->ubsock)
+		udp_tunnel_sock_release(ub->ubsock);
+	synchronize_net();
+	kfree(ub);
+}
+
+/* tipc_udp_disable - detach bearer from socket */
+static void tipc_udp_disable(struct tipc_bearer *b)
+{
+	struct udp_bearer *ub;
+
+	ub = rcu_dereference_rtnl(b->media_ptr);
+	if (!ub) {
+		pr_err("UDP bearer instance not found\n");
+		return;
+	}
+	if (ub->ubsock)
+		sock_set_flag(ub->ubsock->sk, SOCK_DEAD);
+	RCU_INIT_POINTER(b->media_ptr, NULL);
+	RCU_INIT_POINTER(ub->bearer, NULL);
+
+	/* sock_release need to be done outside of rtnl lock */
+	INIT_WORK(&ub->work, cleanup_bearer);
+	schedule_work(&ub->work);
+}
+
+struct tipc_media udp_media_info = {
+	.send_msg	= tipc_udp_send_msg,
+	.enable_media	= tipc_udp_enable,
+	.disable_media	= tipc_udp_disable,
+	.addr2str	= tipc_udp_addr2str,
+	.addr2msg	= tipc_udp_addr2msg,
+	.msg2addr	= tipc_udp_msg2addr,
+	.priority	= TIPC_DEF_LINK_PRI,
+	.tolerance	= TIPC_DEF_LINK_TOL,
+	.window		= TIPC_DEF_LINK_WIN,
+	.type_id	= TIPC_MEDIA_TYPE_UDP,
+	.hwaddr_len	= 0,
+	.name		= "udp"
+};
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index e96884380732..06430598cf51 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -305,7 +305,7 @@ static struct sock *unix_find_socket_byinode(struct inode *i)
 		    &unix_socket_table[i->i_ino & (UNIX_HASH_SIZE - 1)]) {
 		struct dentry *dentry = unix_sk(s)->path.dentry;
 
-		if (dentry && dentry->d_inode == i) {
+		if (dentry && d_backing_inode(dentry) == i) {
 			sock_hold(s);
 			goto found;
 		}
@@ -516,20 +516,15 @@ static unsigned int unix_dgram_poll(struct file *, struct socket *,
 				    poll_table *);
 static int unix_ioctl(struct socket *, unsigned int, unsigned long);
 static int unix_shutdown(struct socket *, int);
-static int unix_stream_sendmsg(struct kiocb *, struct socket *,
-			       struct msghdr *, size_t);
-static int unix_stream_recvmsg(struct kiocb *, struct socket *,
-			       struct msghdr *, size_t, int);
-static int unix_dgram_sendmsg(struct kiocb *, struct socket *,
-			      struct msghdr *, size_t);
-static int unix_dgram_recvmsg(struct kiocb *, struct socket *,
-			      struct msghdr *, size_t, int);
+static int unix_stream_sendmsg(struct socket *, struct msghdr *, size_t);
+static int unix_stream_recvmsg(struct socket *, struct msghdr *, size_t, int);
+static int unix_dgram_sendmsg(struct socket *, struct msghdr *, size_t);
+static int unix_dgram_recvmsg(struct socket *, struct msghdr *, size_t, int);
 static int unix_dgram_connect(struct socket *, struct sockaddr *,
 			      int, int);
-static int unix_seqpacket_sendmsg(struct kiocb *, struct socket *,
-				  struct msghdr *, size_t);
-static int unix_seqpacket_recvmsg(struct kiocb *, struct socket *,
-				  struct msghdr *, size_t, int);
+static int unix_seqpacket_sendmsg(struct socket *, struct msghdr *, size_t);
+static int unix_seqpacket_recvmsg(struct socket *, struct msghdr *, size_t,
+				  int);
 
 static int unix_set_peek_off(struct sock *sk, int val)
 {
@@ -783,7 +778,7 @@ static struct sock *unix_find_other(struct net *net,
 		err = kern_path(sunname->sun_path, LOOKUP_FOLLOW, &path);
 		if (err)
 			goto fail;
-		inode = path.dentry->d_inode;
+		inode = d_backing_inode(path.dentry);
 		err = inode_permission(inode, MAY_WRITE);
 		if (err)
 			goto put_fail;
@@ -844,7 +839,7 @@ static int unix_mknod(const char *sun_path, umode_t mode, struct path *res)
 	 */
 	err = security_path_mknod(&path, dentry, mode, 0);
 	if (!err) {
-		err = vfs_mknod(path.dentry->d_inode, dentry, mode, 0);
+		err = vfs_mknod(d_inode(path.dentry), dentry, mode, 0);
 		if (!err) {
 			res->mnt = mntget(path.mnt);
 			res->dentry = dget(dentry);
@@ -910,7 +905,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 			goto out_up;
 		}
 		addr->hash = UNIX_HASH_SIZE;
-		hash = path.dentry->d_inode->i_ino & (UNIX_HASH_SIZE-1);
+		hash = d_backing_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE-1);
 		spin_lock(&unix_table_lock);
 		u->path = path;
 		list = &unix_socket_table[hash];
@@ -1442,10 +1437,9 @@ static void maybe_add_creds(struct sk_buff *skb, const struct socket *sock,
  *	Send AF_UNIX data.
  */
 
-static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
-			      struct msghdr *msg, size_t len)
+static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
+			      size_t len)
 {
-	struct sock_iocb *siocb = kiocb_to_siocb(kiocb);
 	struct sock *sk = sock->sk;
 	struct net *net = sock_net(sk);
 	struct unix_sock *u = unix_sk(sk);
@@ -1456,14 +1450,12 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	unsigned int hash;
 	struct sk_buff *skb;
 	long timeo;
-	struct scm_cookie tmp_scm;
+	struct scm_cookie scm;
 	int max_level;
 	int data_len = 0;
 
-	if (NULL == siocb->scm)
-		siocb->scm = &tmp_scm;
 	wait_for_unix_gc();
-	err = scm_send(sock, msg, siocb->scm, false);
+	err = scm_send(sock, msg, &scm, false);
 	if (err < 0)
 		return err;
 
@@ -1507,16 +1499,16 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	if (skb == NULL)
 		goto out;
 
-	err = unix_scm_to_skb(siocb->scm, skb, true);
+	err = unix_scm_to_skb(&scm, skb, true);
 	if (err < 0)
 		goto out_free;
 	max_level = err + 1;
-	unix_get_secdata(siocb->scm, skb);
+	unix_get_secdata(&scm, skb);
 
 	skb_put(skb, len - data_len);
 	skb->data_len = data_len;
 	skb->len = len;
-	err = skb_copy_datagram_from_iovec(skb, 0, msg->msg_iov, 0, len);
+	err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, len);
 	if (err)
 		goto out_free;
 
@@ -1606,7 +1598,7 @@ restart:
 	unix_state_unlock(other);
 	other->sk_data_ready(other);
 	sock_put(other);
-	scm_destroy(siocb->scm);
+	scm_destroy(&scm);
 	return len;
 
 out_unlock:
@@ -1616,7 +1608,7 @@ out_free:
 out:
 	if (other)
 		sock_put(other);
-	scm_destroy(siocb->scm);
+	scm_destroy(&scm);
 	return err;
 }
 
@@ -1625,24 +1617,21 @@ out:
  */
 #define UNIX_SKB_FRAGS_SZ (PAGE_SIZE << get_order(32768))
 
-static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
-			       struct msghdr *msg, size_t len)
+static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
+			       size_t len)
 {
-	struct sock_iocb *siocb = kiocb_to_siocb(kiocb);
 	struct sock *sk = sock->sk;
 	struct sock *other = NULL;
 	int err, size;
 	struct sk_buff *skb;
 	int sent = 0;
-	struct scm_cookie tmp_scm;
+	struct scm_cookie scm;
 	bool fds_sent = false;
 	int max_level;
 	int data_len;
 
-	if (NULL == siocb->scm)
-		siocb->scm = &tmp_scm;
 	wait_for_unix_gc();
-	err = scm_send(sock, msg, siocb->scm, false);
+	err = scm_send(sock, msg, &scm, false);
 	if (err < 0)
 		return err;
 
@@ -1683,7 +1672,7 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 			goto out_err;
 
 		/* Only send the fds in the first buffer */
-		err = unix_scm_to_skb(siocb->scm, skb, !fds_sent);
+		err = unix_scm_to_skb(&scm, skb, !fds_sent);
 		if (err < 0) {
 			kfree_skb(skb);
 			goto out_err;
@@ -1694,8 +1683,7 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 		skb_put(skb, size - data_len);
 		skb->data_len = data_len;
 		skb->len = size;
-		err = skb_copy_datagram_from_iovec(skb, 0, msg->msg_iov,
-						   sent, size);
+		err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size);
 		if (err) {
 			kfree_skb(skb);
 			goto out_err;
@@ -1716,8 +1704,7 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 		sent += size;
 	}
 
-	scm_destroy(siocb->scm);
-	siocb->scm = NULL;
+	scm_destroy(&scm);
 
 	return sent;
 
@@ -1729,13 +1716,12 @@ pipe_err:
 		send_sig(SIGPIPE, current, 0);
 	err = -EPIPE;
 out_err:
-	scm_destroy(siocb->scm);
-	siocb->scm = NULL;
+	scm_destroy(&scm);
 	return sent ? : err;
 }
 
-static int unix_seqpacket_sendmsg(struct kiocb *kiocb, struct socket *sock,
-				  struct msghdr *msg, size_t len)
+static int unix_seqpacket_sendmsg(struct socket *sock, struct msghdr *msg,
+				  size_t len)
 {
 	int err;
 	struct sock *sk = sock->sk;
@@ -1750,19 +1736,18 @@ static int unix_seqpacket_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	if (msg->msg_namelen)
 		msg->msg_namelen = 0;
 
-	return unix_dgram_sendmsg(kiocb, sock, msg, len);
+	return unix_dgram_sendmsg(sock, msg, len);
 }
 
-static int unix_seqpacket_recvmsg(struct kiocb *iocb, struct socket *sock,
-			      struct msghdr *msg, size_t size,
-			      int flags)
+static int unix_seqpacket_recvmsg(struct socket *sock, struct msghdr *msg,
+				  size_t size, int flags)
 {
 	struct sock *sk = sock->sk;
 
 	if (sk->sk_state != TCP_ESTABLISHED)
 		return -ENOTCONN;
 
-	return unix_dgram_recvmsg(iocb, sock, msg, size, flags);
+	return unix_dgram_recvmsg(sock, msg, size, flags);
 }
 
 static void unix_copy_addr(struct msghdr *msg, struct sock *sk)
@@ -1775,12 +1760,10 @@ static void unix_copy_addr(struct msghdr *msg, struct sock *sk)
 	}
 }
 
-static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
-			      struct msghdr *msg, size_t size,
-			      int flags)
+static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
+			      size_t size, int flags)
 {
-	struct sock_iocb *siocb = kiocb_to_siocb(iocb);
-	struct scm_cookie tmp_scm;
+	struct scm_cookie scm;
 	struct sock *sk = sock->sk;
 	struct unix_sock *u = unix_sk(sk);
 	int noblock = flags & MSG_DONTWAIT;
@@ -1825,23 +1808,21 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
 	else if (size < skb->len - skip)
 		msg->msg_flags |= MSG_TRUNC;
 
-	err = skb_copy_datagram_iovec(skb, skip, msg->msg_iov, size);
+	err = skb_copy_datagram_msg(skb, skip, msg, size);
 	if (err)
 		goto out_free;
 
 	if (sock_flag(sk, SOCK_RCVTSTAMP))
 		__sock_recv_timestamp(msg, sk, skb);
 
-	if (!siocb->scm) {
-		siocb->scm = &tmp_scm;
-		memset(&tmp_scm, 0, sizeof(tmp_scm));
-	}
-	scm_set_cred(siocb->scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid);
-	unix_set_secdata(siocb->scm, skb);
+	memset(&scm, 0, sizeof(scm));
+
+	scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid);
+	unix_set_secdata(&scm, skb);
 
 	if (!(flags & MSG_PEEK)) {
 		if (UNIXCB(skb).fp)
-			unix_detach_fds(siocb->scm, skb);
+			unix_detach_fds(&scm, skb);
 
 		sk_peek_offset_bwd(sk, skb->len);
 	} else {
@@ -1861,11 +1842,11 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
 		sk_peek_offset_fwd(sk, size);
 
 		if (UNIXCB(skb).fp)
-			siocb->scm->fp = scm_fp_dup(UNIXCB(skb).fp);
+			scm.fp = scm_fp_dup(UNIXCB(skb).fp);
 	}
 	err = (flags & MSG_TRUNC) ? skb->len - skip : size;
 
-	scm_recv(sock, msg, siocb->scm, flags);
+	scm_recv(sock, msg, &scm, flags);
 
 out_free:
 	skb_free_datagram(sk, skb);
@@ -1899,6 +1880,10 @@ static long unix_stream_data_wait(struct sock *sk, long timeo,
 		unix_state_unlock(sk);
 		timeo = freezable_schedule_timeout(timeo);
 		unix_state_lock(sk);
+
+		if (sock_flag(sk, SOCK_DEAD))
+			break;
+
 		clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
 	}
 
@@ -1912,12 +1897,10 @@ static unsigned int unix_skb_len(const struct sk_buff *skb)
 	return skb->len - UNIXCB(skb).consumed;
 }
 
-static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
-			       struct msghdr *msg, size_t size,
-			       int flags)
+static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg,
+			       size_t size, int flags)
 {
-	struct sock_iocb *siocb = kiocb_to_siocb(iocb);
-	struct scm_cookie tmp_scm;
+	struct scm_cookie scm;
 	struct sock *sk = sock->sk;
 	struct unix_sock *u = unix_sk(sk);
 	DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, msg->msg_name);
@@ -1944,10 +1927,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 	 * while sleeps in memcpy_tomsg
 	 */
 
-	if (!siocb->scm) {
-		siocb->scm = &tmp_scm;
-		memset(&tmp_scm, 0, sizeof(tmp_scm));
-	}
+	memset(&scm, 0, sizeof(scm));
 
 	err = mutex_lock_interruptible(&u->readlock);
 	if (unlikely(err)) {
@@ -1963,6 +1943,10 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 		struct sk_buff *skb, *last;
 
 		unix_state_lock(sk);
+		if (sock_flag(sk, SOCK_DEAD)) {
+			err = -ECONNRESET;
+			goto unlock;
+		}
 		last = skb = skb_peek(&sk->sk_receive_queue);
 again:
 		if (skb == NULL) {
@@ -2013,13 +1997,13 @@ again:
 
 		if (check_creds) {
 			/* Never glue messages from different writers */
-			if ((UNIXCB(skb).pid  != siocb->scm->pid) ||
-			    !uid_eq(UNIXCB(skb).uid, siocb->scm->creds.uid) ||
-			    !gid_eq(UNIXCB(skb).gid, siocb->scm->creds.gid))
+			if ((UNIXCB(skb).pid  != scm.pid) ||
+			    !uid_eq(UNIXCB(skb).uid, scm.creds.uid) ||
+			    !gid_eq(UNIXCB(skb).gid, scm.creds.gid))
 				break;
 		} else if (test_bit(SOCK_PASSCRED, &sock->flags)) {
 			/* Copy credentials */
-			scm_set_cred(siocb->scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid);
+			scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid);
 			check_creds = 1;
 		}
 
@@ -2030,8 +2014,8 @@ again:
 		}
 
 		chunk = min_t(unsigned int, unix_skb_len(skb) - skip, size);
-		if (skb_copy_datagram_iovec(skb, UNIXCB(skb).consumed + skip,
-					    msg->msg_iov, chunk)) {
+		if (skb_copy_datagram_msg(skb, UNIXCB(skb).consumed + skip,
+					  msg, chunk)) {
 			if (copied == 0)
 				copied = -EFAULT;
 			break;
@@ -2046,7 +2030,7 @@ again:
 			sk_peek_offset_bwd(sk, chunk);
 
 			if (UNIXCB(skb).fp)
-				unix_detach_fds(siocb->scm, skb);
+				unix_detach_fds(&scm, skb);
 
 			if (unix_skb_len(skb))
 				break;
@@ -2054,13 +2038,13 @@ again:
 			skb_unlink(skb, &sk->sk_receive_queue);
 			consume_skb(skb);
 
-			if (siocb->scm->fp)
+			if (scm.fp)
 				break;
 		} else {
 			/* It is questionable, see note in unix_dgram_recvmsg.
 			 */
 			if (UNIXCB(skb).fp)
-				siocb->scm->fp = scm_fp_dup(UNIXCB(skb).fp);
+				scm.fp = scm_fp_dup(UNIXCB(skb).fp);
 
 			sk_peek_offset_fwd(sk, chunk);
 
@@ -2069,7 +2053,7 @@ again:
 	} while (size);
 
 	mutex_unlock(&u->readlock);
-	scm_recv(sock, msg, siocb->scm, flags);
+	scm_recv(sock, msg, &scm, flags);
 out:
 	return copied ? : err;
 }
diff --git a/net/unix/diag.c b/net/unix/diag.c
index 86fa0f3b2caf..c512f64d5287 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -25,7 +25,7 @@ static int sk_diag_dump_vfs(struct sock *sk, struct sk_buff *nlskb)
 
 	if (dentry) {
 		struct unix_diag_vfs uv = {
-			.udiag_vfs_ino = dentry->d_inode->i_ino,
+			.udiag_vfs_ino = d_backing_inode(dentry)->i_ino,
 			.udiag_vfs_dev = dentry->d_sb->s_dev,
 		};
 
@@ -155,7 +155,8 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r
 	if (nla_put_u8(skb, UNIX_DIAG_SHUTDOWN, sk->sk_shutdown))
 		goto out_nlmsg_trim;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 out_nlmsg_trim:
 	nlmsg_cancel(skb, nlh);
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 99f7012b23b9..a73a226f2d33 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -95,39 +95,36 @@ static DECLARE_WAIT_QUEUE_HEAD(unix_gc_wait);
 
 unsigned int unix_tot_inflight;
 
-
 struct sock *unix_get_socket(struct file *filp)
 {
 	struct sock *u_sock = NULL;
 	struct inode *inode = file_inode(filp);
 
-	/*
-	 *	Socket ?
-	 */
+	/* Socket ? */
 	if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) {
 		struct socket *sock = SOCKET_I(inode);
 		struct sock *s = sock->sk;
 
-		/*
-		 *	PF_UNIX ?
-		 */
+		/* PF_UNIX ? */
 		if (s && sock->ops && sock->ops->family == PF_UNIX)
 			u_sock = s;
 	}
 	return u_sock;
 }
 
-/*
- *	Keep the number of times in flight count for the file
- *	descriptor if it is for an AF_UNIX socket.
+/* Keep the number of times in flight count for the file
+ * descriptor if it is for an AF_UNIX socket.
  */
 
 void unix_inflight(struct file *fp)
 {
 	struct sock *s = unix_get_socket(fp);
+
 	if (s) {
 		struct unix_sock *u = unix_sk(s);
+
 		spin_lock(&unix_gc_lock);
+
 		if (atomic_long_inc_return(&u->inflight) == 1) {
 			BUG_ON(!list_empty(&u->link));
 			list_add_tail(&u->link, &gc_inflight_list);
@@ -142,10 +139,13 @@ void unix_inflight(struct file *fp)
 void unix_notinflight(struct file *fp)
 {
 	struct sock *s = unix_get_socket(fp);
+
 	if (s) {
 		struct unix_sock *u = unix_sk(s);
+
 		spin_lock(&unix_gc_lock);
 		BUG_ON(list_empty(&u->link));
+
 		if (atomic_long_dec_and_test(&u->inflight))
 			list_del_init(&u->link);
 		unix_tot_inflight--;
@@ -161,32 +161,27 @@ static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *),
 
 	spin_lock(&x->sk_receive_queue.lock);
 	skb_queue_walk_safe(&x->sk_receive_queue, skb, next) {
-		/*
-		 *	Do we have file descriptors ?
-		 */
+		/* Do we have file descriptors ? */
 		if (UNIXCB(skb).fp) {
 			bool hit = false;
-			/*
-			 *	Process the descriptors of this socket
-			 */
+			/* Process the descriptors of this socket */
 			int nfd = UNIXCB(skb).fp->count;
 			struct file **fp = UNIXCB(skb).fp->fp;
+
 			while (nfd--) {
-				/*
-				 *	Get the socket the fd matches
-				 *	if it indeed does so
-				 */
+				/* Get the socket the fd matches if it indeed does so */
 				struct sock *sk = unix_get_socket(*fp++);
+
 				if (sk) {
 					struct unix_sock *u = unix_sk(sk);
 
-					/*
-					 * Ignore non-candidates, they could
+					/* Ignore non-candidates, they could
 					 * have been added to the queues after
 					 * starting the garbage collection
 					 */
 					if (test_bit(UNIX_GC_CANDIDATE, &u->gc_flags)) {
 						hit = true;
+
 						func(u);
 					}
 				}
@@ -203,24 +198,22 @@ static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *),
 static void scan_children(struct sock *x, void (*func)(struct unix_sock *),
 			  struct sk_buff_head *hitlist)
 {
-	if (x->sk_state != TCP_LISTEN)
+	if (x->sk_state != TCP_LISTEN) {
 		scan_inflight(x, func, hitlist);
-	else {
+	} else {
 		struct sk_buff *skb;
 		struct sk_buff *next;
 		struct unix_sock *u;
 		LIST_HEAD(embryos);
 
-		/*
-		 * For a listening socket collect the queued embryos
+		/* For a listening socket collect the queued embryos
 		 * and perform a scan on them as well.
 		 */
 		spin_lock(&x->sk_receive_queue.lock);
 		skb_queue_walk_safe(&x->sk_receive_queue, skb, next) {
 			u = unix_sk(skb->sk);
 
-			/*
-			 * An embryo cannot be in-flight, so it's safe
+			/* An embryo cannot be in-flight, so it's safe
 			 * to use the list link.
 			 */
 			BUG_ON(!list_empty(&u->link));
@@ -249,8 +242,7 @@ static void inc_inflight(struct unix_sock *usk)
 static void inc_inflight_move_tail(struct unix_sock *u)
 {
 	atomic_long_inc(&u->inflight);
-	/*
-	 * If this still might be part of a cycle, move it to the end
+	/* If this still might be part of a cycle, move it to the end
 	 * of the list, so that it's checked even if it was already
 	 * passed over
 	 */
@@ -263,8 +255,7 @@ static bool gc_in_progress;
 
 void wait_for_unix_gc(void)
 {
-	/*
-	 * If number of inflight sockets is insane,
+	/* If number of inflight sockets is insane,
 	 * force a garbage collect right now.
 	 */
 	if (unix_tot_inflight > UNIX_INFLIGHT_TRIGGER_GC && !gc_in_progress)
@@ -288,8 +279,7 @@ void unix_gc(void)
 		goto out;
 
 	gc_in_progress = true;
-	/*
-	 * First, select candidates for garbage collection.  Only
+	/* First, select candidates for garbage collection.  Only
 	 * in-flight sockets are considered, and from those only ones
 	 * which don't have any external reference.
 	 *
@@ -320,15 +310,13 @@ void unix_gc(void)
 		}
 	}
 
-	/*
-	 * Now remove all internal in-flight reference to children of
+	/* Now remove all internal in-flight reference to children of
 	 * the candidates.
 	 */
 	list_for_each_entry(u, &gc_candidates, link)
 		scan_children(&u->sk, dec_inflight, NULL);
 
-	/*
-	 * Restore the references for children of all candidates,
+	/* Restore the references for children of all candidates,
 	 * which have remaining references.  Do this recursively, so
 	 * only those remain, which form cyclic references.
 	 *
@@ -350,8 +338,7 @@ void unix_gc(void)
 	}
 	list_del(&cursor);
 
-	/*
-	 * not_cycle_list contains those sockets which do not make up a
+	/* not_cycle_list contains those sockets which do not make up a
 	 * cycle.  Restore these to the inflight list.
 	 */
 	while (!list_empty(&not_cycle_list)) {
@@ -360,8 +347,7 @@ void unix_gc(void)
 		list_move_tail(&u->link, &gc_inflight_list);
 	}
 
-	/*
-	 * Now gc_candidates contains only garbage.  Restore original
+	/* Now gc_candidates contains only garbage.  Restore original
 	 * inflight counters for these as well, and remove the skbuffs
 	 * which are creating the cycle(s).
 	 */
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 85d232bed87d..2ec86e652a19 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -949,8 +949,8 @@ static unsigned int vsock_poll(struct file *file, struct socket *sock,
 	return mask;
 }
 
-static int vsock_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
-			       struct msghdr *msg, size_t len)
+static int vsock_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
+			       size_t len)
 {
 	int err;
 	struct sock *sk;
@@ -1013,7 +1013,7 @@ static int vsock_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
 		goto out;
 	}
 
-	err = transport->dgram_enqueue(vsk, remote_addr, msg->msg_iov, len);
+	err = transport->dgram_enqueue(vsk, remote_addr, msg, len);
 
 out:
 	release_sock(sk);
@@ -1062,11 +1062,10 @@ out:
 	return err;
 }
 
-static int vsock_dgram_recvmsg(struct kiocb *kiocb, struct socket *sock,
-			       struct msghdr *msg, size_t len, int flags)
+static int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
+			       size_t len, int flags)
 {
-	return transport->dgram_dequeue(kiocb, vsock_sk(sock->sk), msg, len,
-					flags);
+	return transport->dgram_dequeue(vsock_sk(sock->sk), msg, len, flags);
 }
 
 static const struct proto_ops vsock_dgram_ops = {
@@ -1505,8 +1504,8 @@ static int vsock_stream_getsockopt(struct socket *sock,
 	return 0;
 }
 
-static int vsock_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
-				struct msghdr *msg, size_t len)
+static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg,
+				size_t len)
 {
 	struct sock *sk;
 	struct vsock_sock *vsk;
@@ -1617,7 +1616,7 @@ static int vsock_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 		 */
 
 		written = transport->stream_enqueue(
-				vsk, msg->msg_iov,
+				vsk, msg,
 				len - total_written);
 		if (written < 0) {
 			err = -ENOMEM;
@@ -1644,9 +1643,8 @@ out:
 
 
 static int
-vsock_stream_recvmsg(struct kiocb *kiocb,
-		     struct socket *sock,
-		     struct msghdr *msg, size_t len, int flags)
+vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+		     int flags)
 {
 	struct sock *sk;
 	struct vsock_sock *vsk;
@@ -1739,7 +1737,7 @@ vsock_stream_recvmsg(struct kiocb *kiocb,
 				break;
 
 			read = transport->stream_dequeue(
-					vsk, msg->msg_iov,
+					vsk, msg,
 					len - copied, flags);
 			if (read < 0) {
 				err = -ENOMEM;
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index 9bb63ffec4f2..c294da095461 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -1697,7 +1697,7 @@ static int vmci_transport_dgram_bind(struct vsock_sock *vsk,
 static int vmci_transport_dgram_enqueue(
 	struct vsock_sock *vsk,
 	struct sockaddr_vm *remote_addr,
-	struct iovec *iov,
+	struct msghdr *msg,
 	size_t len)
 {
 	int err;
@@ -1714,7 +1714,7 @@ static int vmci_transport_dgram_enqueue(
 	if (!dg)
 		return -ENOMEM;
 
-	memcpy_fromiovec(VMCI_DG_PAYLOAD(dg), iov, len);
+	memcpy_from_msg(VMCI_DG_PAYLOAD(dg), msg, len);
 
 	dg->dst = vmci_make_handle(remote_addr->svm_cid,
 				   remote_addr->svm_port);
@@ -1730,8 +1730,7 @@ static int vmci_transport_dgram_enqueue(
 	return err - sizeof(*dg);
 }
 
-static int vmci_transport_dgram_dequeue(struct kiocb *kiocb,
-					struct vsock_sock *vsk,
+static int vmci_transport_dgram_dequeue(struct vsock_sock *vsk,
 					struct msghdr *msg, size_t len,
 					int flags)
 {
@@ -1773,8 +1772,7 @@ static int vmci_transport_dgram_dequeue(struct kiocb *kiocb,
 	}
 
 	/* Place the datagram payload in the user's iovec. */
-	err = skb_copy_datagram_iovec(skb, sizeof(*dg), msg->msg_iov,
-		payload_len);
+	err = skb_copy_datagram_msg(skb, sizeof(*dg), msg, payload_len);
 	if (err)
 		goto out;
 
@@ -1836,22 +1834,22 @@ static int vmci_transport_connect(struct vsock_sock *vsk)
 
 static ssize_t vmci_transport_stream_dequeue(
 	struct vsock_sock *vsk,
-	struct iovec *iov,
+	struct msghdr *msg,
 	size_t len,
 	int flags)
 {
 	if (flags & MSG_PEEK)
-		return vmci_qpair_peekv(vmci_trans(vsk)->qpair, iov, len, 0);
+		return vmci_qpair_peekv(vmci_trans(vsk)->qpair, msg, len, 0);
 	else
-		return vmci_qpair_dequev(vmci_trans(vsk)->qpair, iov, len, 0);
+		return vmci_qpair_dequev(vmci_trans(vsk)->qpair, msg, len, 0);
 }
 
 static ssize_t vmci_transport_stream_enqueue(
 	struct vsock_sock *vsk,
-	struct iovec *iov,
+	struct msghdr *msg,
 	size_t len)
 {
-	return vmci_qpair_enquev(vmci_trans(vsk)->qpair, iov, len, 0);
+	return vmci_qpair_enquev(vmci_trans(vsk)->qpair, msg, len, 0);
 }
 
 static s64 vmci_transport_stream_has_data(struct vsock_sock *vsk)
diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig
index 29c8675f9a11..4f5543dd2524 100644
--- a/net/wireless/Kconfig
+++ b/net/wireless/Kconfig
@@ -175,13 +175,21 @@ config CFG80211_INTERNAL_REGDB
 	  Most distributions have a CRDA package.  So if unsure, say N.
 
 config CFG80211_WEXT
-	bool "cfg80211 wireless extensions compatibility"
+	bool "cfg80211 wireless extensions compatibility" if !CFG80211_WEXT_EXPORT
 	depends on CFG80211
 	select WEXT_CORE
+	default y if CFG80211_WEXT_EXPORT
 	help
 	  Enable this option if you need old userspace for wireless
 	  extensions with cfg80211-based drivers.
 
+config CFG80211_WEXT_EXPORT
+	bool
+	depends on CFG80211
+	help
+	  Drivers should select this option if they require cfg80211's
+	  wext compatibility symbols to be exported.
+
 config LIB80211
 	tristate
 	default n
diff --git a/net/wireless/Makefile b/net/wireless/Makefile
index a761670af31d..4c9e39f04ef8 100644
--- a/net/wireless/Makefile
+++ b/net/wireless/Makefile
@@ -10,7 +10,7 @@ obj-$(CONFIG_WEXT_SPY) += wext-spy.o
 obj-$(CONFIG_WEXT_PRIV) += wext-priv.o
 
 cfg80211-y += core.o sysfs.o radiotap.o util.o reg.o scan.o nl80211.o
-cfg80211-y += mlme.o ibss.o sme.o chan.o ethtool.o mesh.o ap.o trace.o
+cfg80211-y += mlme.o ibss.o sme.o chan.o ethtool.o mesh.o ap.o trace.o ocb.o
 cfg80211-$(CONFIG_CFG80211_DEBUGFS) += debugfs.o
 cfg80211-$(CONFIG_CFG80211_WEXT) += wext-compat.o wext-sme.o
 cfg80211-$(CONFIG_CFG80211_INTERNAL_REGDB) += regdb.o
diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index 72d81e2154d5..7aaf7415dc4c 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -115,7 +115,7 @@ bool cfg80211_chandef_valid(const struct cfg80211_chan_def *chandef)
 EXPORT_SYMBOL(cfg80211_chandef_valid);
 
 static void chandef_primary_freqs(const struct cfg80211_chan_def *c,
-				  int *pri40, int *pri80)
+				  u32 *pri40, u32 *pri80)
 {
 	int tmp;
 
@@ -366,6 +366,7 @@ int cfg80211_chandef_dfs_required(struct wiphy *wiphy,
 
 		break;
 	case NL80211_IFTYPE_STATION:
+	case NL80211_IFTYPE_OCB:
 	case NL80211_IFTYPE_P2P_CLIENT:
 	case NL80211_IFTYPE_MONITOR:
 	case NL80211_IFTYPE_AP_VLAN:
@@ -602,7 +603,7 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy,
 {
 	struct ieee80211_sta_ht_cap *ht_cap;
 	struct ieee80211_sta_vht_cap *vht_cap;
-	u32 width, control_freq;
+	u32 width, control_freq, cap;
 
 	if (WARN_ON(!cfg80211_chandef_valid(chandef)))
 		return false;
@@ -642,7 +643,8 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy,
 			return false;
 		break;
 	case NL80211_CHAN_WIDTH_80P80:
-		if (!(vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ))
+		cap = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK;
+		if (cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ)
 			return false;
 	case NL80211_CHAN_WIDTH_80:
 		if (!vht_cap->vht_supported)
@@ -653,7 +655,9 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy,
 	case NL80211_CHAN_WIDTH_160:
 		if (!vht_cap->vht_supported)
 			return false;
-		if (!(vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ))
+		cap = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK;
+		if (cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ &&
+		    cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ)
 			return false;
 		prohibited_flags |= IEEE80211_CHAN_NO_160MHZ;
 		width = 160;
@@ -892,6 +896,13 @@ cfg80211_get_chan_state(struct wireless_dev *wdev,
 				*radar_detect |= BIT(wdev->chandef.width);
 		}
 		return;
+	case NL80211_IFTYPE_OCB:
+		if (wdev->chandef.chan) {
+			*chan = wdev->chandef.chan;
+			*chanmode = CHAN_MODE_SHARED;
+			return;
+		}
+		break;
 	case NL80211_IFTYPE_MONITOR:
 	case NL80211_IFTYPE_AP_VLAN:
 	case NL80211_IFTYPE_WDS:
diff --git a/net/wireless/core.c b/net/wireless/core.c
index f52a4cd7017c..2a0bbd22854b 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -86,11 +86,11 @@ struct wiphy *wiphy_idx_to_wiphy(int wiphy_idx)
 	return &rdev->wiphy;
 }
 
-int cfg80211_dev_rename(struct cfg80211_registered_device *rdev,
-			char *newname)
+static int cfg80211_dev_check_name(struct cfg80211_registered_device *rdev,
+				   const char *newname)
 {
 	struct cfg80211_registered_device *rdev2;
-	int wiphy_idx, taken = -1, result, digits;
+	int wiphy_idx, taken = -1, digits;
 
 	ASSERT_RTNL();
 
@@ -109,15 +109,28 @@ int cfg80211_dev_rename(struct cfg80211_registered_device *rdev,
 			return -EINVAL;
 	}
 
+	/* Ensure another device does not already have this name. */
+	list_for_each_entry(rdev2, &cfg80211_rdev_list, list)
+		if (strcmp(newname, wiphy_name(&rdev2->wiphy)) == 0)
+			return -EINVAL;
+
+	return 0;
+}
+
+int cfg80211_dev_rename(struct cfg80211_registered_device *rdev,
+			char *newname)
+{
+	int result;
+
+	ASSERT_RTNL();
 
 	/* Ignore nop renames */
-	if (strcmp(newname, dev_name(&rdev->wiphy.dev)) == 0)
+	if (strcmp(newname, wiphy_name(&rdev->wiphy)) == 0)
 		return 0;
 
-	/* Ensure another device does not already have this name. */
-	list_for_each_entry(rdev2, &cfg80211_rdev_list, list)
-		if (strcmp(newname, dev_name(&rdev2->wiphy.dev)) == 0)
-			return -EINVAL;
+	result = cfg80211_dev_check_name(rdev, newname);
+	if (result < 0)
+		return result;
 
 	result = device_rename(&rdev->wiphy.dev, newname);
 	if (result)
@@ -307,9 +320,24 @@ static void cfg80211_destroy_iface_wk(struct work_struct *work)
 	rtnl_unlock();
 }
 
+static void cfg80211_sched_scan_stop_wk(struct work_struct *work)
+{
+	struct cfg80211_registered_device *rdev;
+
+	rdev = container_of(work, struct cfg80211_registered_device,
+			   sched_scan_stop_wk);
+
+	rtnl_lock();
+
+	__cfg80211_stop_sched_scan(rdev, false);
+
+	rtnl_unlock();
+}
+
 /* exported functions */
 
-struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv)
+struct wiphy *wiphy_new_nm(const struct cfg80211_ops *ops, int sizeof_priv,
+			   const char *requested_name)
 {
 	static atomic_t wiphy_counter = ATOMIC_INIT(0);
 
@@ -346,7 +374,31 @@ struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv)
 	rdev->wiphy_idx--;
 
 	/* give it a proper name */
-	dev_set_name(&rdev->wiphy.dev, PHY_NAME "%d", rdev->wiphy_idx);
+	if (requested_name && requested_name[0]) {
+		int rv;
+
+		rtnl_lock();
+		rv = cfg80211_dev_check_name(rdev, requested_name);
+
+		if (rv < 0) {
+			rtnl_unlock();
+			goto use_default_name;
+		}
+
+		rv = dev_set_name(&rdev->wiphy.dev, "%s", requested_name);
+		rtnl_unlock();
+		if (rv)
+			goto use_default_name;
+	} else {
+use_default_name:
+		/* NOTE:  This is *probably* safe w/out holding rtnl because of
+		 * the restrictions on phy names.  Probably this call could
+		 * fail if some other part of the kernel (re)named a device
+		 * phyX.  But, might should add some locking and check return
+		 * value, and use a different name if this one exists?
+		 */
+		dev_set_name(&rdev->wiphy.dev, PHY_NAME "%d", rdev->wiphy_idx);
+	}
 
 	INIT_LIST_HEAD(&rdev->wdev_list);
 	INIT_LIST_HEAD(&rdev->beacon_registrations);
@@ -368,6 +420,7 @@ struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv)
 	INIT_LIST_HEAD(&rdev->destroy_list);
 	spin_lock_init(&rdev->destroy_list_lock);
 	INIT_WORK(&rdev->destroy_work, cfg80211_destroy_iface_wk);
+	INIT_WORK(&rdev->sched_scan_stop_wk, cfg80211_sched_scan_stop_wk);
 
 #ifdef CONFIG_CFG80211_DEFAULT_PS
 	rdev->wiphy.flags |= WIPHY_FLAG_PS_ON_BY_DEFAULT;
@@ -406,7 +459,7 @@ struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv)
 
 	return &rdev->wiphy;
 }
-EXPORT_SYMBOL(wiphy_new);
+EXPORT_SYMBOL(wiphy_new_nm);
 
 static int wiphy_verify_combinations(struct wiphy *wiphy)
 {
@@ -503,6 +556,32 @@ int wiphy_register(struct wiphy *wiphy)
 		    !wiphy->wowlan->tcp))
 		return -EINVAL;
 #endif
+	if (WARN_ON((wiphy->features & NL80211_FEATURE_TDLS_CHANNEL_SWITCH) &&
+		    (!rdev->ops->tdls_channel_switch ||
+		     !rdev->ops->tdls_cancel_channel_switch)))
+		return -EINVAL;
+
+	/*
+	 * if a wiphy has unsupported modes for regulatory channel enforcement,
+	 * opt-out of enforcement checking
+	 */
+	if (wiphy->interface_modes & ~(BIT(NL80211_IFTYPE_STATION) |
+				       BIT(NL80211_IFTYPE_P2P_CLIENT) |
+				       BIT(NL80211_IFTYPE_AP) |
+				       BIT(NL80211_IFTYPE_P2P_GO) |
+				       BIT(NL80211_IFTYPE_ADHOC) |
+				       BIT(NL80211_IFTYPE_P2P_DEVICE) |
+				       BIT(NL80211_IFTYPE_AP_VLAN) |
+				       BIT(NL80211_IFTYPE_MONITOR)))
+		wiphy->regulatory_flags |= REGULATORY_IGNORE_STALE_KICKOFF;
+
+	if (WARN_ON((wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) &&
+		    (wiphy->regulatory_flags &
+					(REGULATORY_CUSTOM_REG |
+					 REGULATORY_STRICT_REG |
+					 REGULATORY_COUNTRY_IE_FOLLOW_POWER |
+					 REGULATORY_COUNTRY_IE_IGNORE))))
+		return -EINVAL;
 
 	if (WARN_ON(wiphy->coalesce &&
 		    (!wiphy->coalesce->n_rules ||
@@ -722,6 +801,7 @@ void wiphy_unregister(struct wiphy *wiphy)
 	flush_work(&rdev->event_work);
 	cancel_delayed_work_sync(&rdev->dfs_update_channels_wk);
 	flush_work(&rdev->destroy_work);
+	flush_work(&rdev->sched_scan_stop_wk);
 
 #ifdef CONFIG_PM
 	if (rdev->wiphy.wowlan_config && rdev->ops->set_wakeup)
@@ -802,6 +882,7 @@ void __cfg80211_leave(struct cfg80211_registered_device *rdev,
 		      struct wireless_dev *wdev)
 {
 	struct net_device *dev = wdev->netdev;
+	struct cfg80211_sched_scan_request *sched_scan_req;
 
 	ASSERT_RTNL();
 	ASSERT_WDEV_LOCK(wdev);
@@ -812,7 +893,8 @@ void __cfg80211_leave(struct cfg80211_registered_device *rdev,
 		break;
 	case NL80211_IFTYPE_P2P_CLIENT:
 	case NL80211_IFTYPE_STATION:
-		if (rdev->sched_scan_req && dev == rdev->sched_scan_req->dev)
+		sched_scan_req = rtnl_dereference(rdev->sched_scan_req);
+		if (sched_scan_req && dev == sched_scan_req->dev)
 			__cfg80211_stop_sched_scan(rdev, false);
 
 #ifdef CONFIG_CFG80211_WEXT
@@ -831,7 +913,22 @@ void __cfg80211_leave(struct cfg80211_registered_device *rdev,
 	case NL80211_IFTYPE_P2P_GO:
 		__cfg80211_stop_ap(rdev, dev, true);
 		break;
-	default:
+	case NL80211_IFTYPE_OCB:
+		__cfg80211_leave_ocb(rdev, dev);
+		break;
+	case NL80211_IFTYPE_WDS:
+		/* must be handled by mac80211/driver, has no APIs */
+		break;
+	case NL80211_IFTYPE_P2P_DEVICE:
+		/* cannot happen, has no netdev */
+		break;
+	case NL80211_IFTYPE_AP_VLAN:
+	case NL80211_IFTYPE_MONITOR:
+		/* nothing to do */
+		break;
+	case NL80211_IFTYPE_UNSPECIFIED:
+	case NUM_NL80211_IFTYPES:
+		/* invalid */
 		break;
 	}
 }
@@ -872,6 +969,7 @@ 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;
+	struct cfg80211_sched_scan_request *sched_scan_req;
 
 	if (!wdev)
 		return NOTIFY_DONE;
@@ -936,8 +1034,9 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
 			___cfg80211_scan_done(rdev, false);
 		}
 
-		if (WARN_ON(rdev->sched_scan_req &&
-			    rdev->sched_scan_req->dev == wdev->netdev)) {
+		sched_scan_req = rtnl_dereference(rdev->sched_scan_req);
+		if (WARN_ON(sched_scan_req &&
+			    sched_scan_req->dev == wdev->netdev)) {
 			__cfg80211_stop_sched_scan(rdev, false);
 		}
 
@@ -1100,6 +1199,7 @@ out_fail_wq:
 	regulatory_exit();
 out_fail_reg:
 	debugfs_remove(ieee80211_debugfs_dir);
+	nl80211_exit();
 out_fail_nl80211:
 	unregister_netdevice_notifier(&cfg80211_netdev_notifier);
 out_fail_notifier:
diff --git a/net/wireless/core.h b/net/wireless/core.h
index 7e3a3cef7df9..801cd49c5a0c 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -36,6 +36,13 @@ struct cfg80211_registered_device {
 	 * the country on the country IE changed. */
 	char country_ie_alpha2[2];
 
+	/*
+	 * the driver requests the regulatory core to set this regulatory
+	 * domain as the wiphy's. Only used for %REGULATORY_WIPHY_SELF_MANAGED
+	 * devices using the regulatory_set_wiphy_regd() API
+	 */
+	const struct ieee80211_regdomain *requested_regd;
+
 	/* If a Country IE has been received this tells us the environment
 	 * which its telling us its in. This defaults to ENVIRON_ANY */
 	enum environment_cap env;
@@ -63,7 +70,7 @@ struct cfg80211_registered_device {
 	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;
+	struct cfg80211_sched_scan_request __rcu *sched_scan_req;
 	unsigned long suspend_at;
 	struct work_struct scan_done_wk;
 	struct work_struct sched_scan_results_wk;
@@ -84,6 +91,8 @@ struct cfg80211_registered_device {
 	struct list_head destroy_list;
 	struct work_struct destroy_work;
 
+	struct work_struct sched_scan_stop_wk;
+
 	/* 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);
@@ -111,6 +120,7 @@ cfg80211_rdev_free_wowlan(struct cfg80211_registered_device *rdev)
 	    rdev->wiphy.wowlan_config->tcp->sock)
 		sock_release(rdev->wiphy.wowlan_config->tcp->sock);
 	kfree(rdev->wiphy.wowlan_config->tcp);
+	kfree(rdev->wiphy.wowlan_config->nd_config);
 	kfree(rdev->wiphy.wowlan_config);
 #endif
 }
@@ -290,6 +300,18 @@ int cfg80211_set_mesh_channel(struct cfg80211_registered_device *rdev,
 			      struct wireless_dev *wdev,
 			      struct cfg80211_chan_def *chandef);
 
+/* OCB */
+int __cfg80211_join_ocb(struct cfg80211_registered_device *rdev,
+			struct net_device *dev,
+			struct ocb_setup *setup);
+int cfg80211_join_ocb(struct cfg80211_registered_device *rdev,
+		      struct net_device *dev,
+		      struct ocb_setup *setup);
+int __cfg80211_leave_ocb(struct cfg80211_registered_device *rdev,
+			 struct net_device *dev);
+int cfg80211_leave_ocb(struct cfg80211_registered_device *rdev,
+		       struct net_device *dev);
+
 /* AP */
 int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev,
 		       struct net_device *dev, bool notify);
diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c
index e24fc585c883..4c55fab9b4e4 100644
--- a/net/wireless/ibss.c
+++ b/net/wireless/ibss.c
@@ -30,7 +30,7 @@ void __cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid,
 		return;
 
 	bss = cfg80211_get_bss(wdev->wiphy, channel, bssid, NULL, 0,
-			       WLAN_CAPABILITY_IBSS, WLAN_CAPABILITY_IBSS);
+			       IEEE80211_BSS_TYPE_IBSS, IEEE80211_PRIVACY_ANY);
 
 	if (WARN_ON(!bss))
 		return;
@@ -533,7 +533,7 @@ int cfg80211_ibss_wext_giwap(struct net_device *dev,
 	else if (wdev->wext.ibss.bssid)
 		memcpy(ap_addr->sa_data, wdev->wext.ibss.bssid, ETH_ALEN);
 	else
-		memset(ap_addr->sa_data, 0, ETH_ALEN);
+		eth_zero_addr(ap_addr->sa_data);
 
 	wdev_unlock(wdev);
 
diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c
index 2c52b59e43f3..7aae329e2b4e 100644
--- a/net/wireless/mlme.c
+++ b/net/wireless/mlme.c
@@ -229,7 +229,8 @@ int cfg80211_mlme_auth(struct cfg80211_registered_device *rdev,
 		return -EALREADY;
 
 	req.bss = cfg80211_get_bss(&rdev->wiphy, chan, bssid, ssid, ssid_len,
-				   WLAN_CAPABILITY_ESS, WLAN_CAPABILITY_ESS);
+				   IEEE80211_BSS_TYPE_ESS,
+				   IEEE80211_PRIVACY_ANY);
 	if (!req.bss)
 		return -ENOENT;
 
@@ -296,7 +297,8 @@ int cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev,
 				   rdev->wiphy.vht_capa_mod_mask);
 
 	req->bss = cfg80211_get_bss(&rdev->wiphy, chan, bssid, ssid, ssid_len,
-				    WLAN_CAPABILITY_ESS, WLAN_CAPABILITY_ESS);
+				    IEEE80211_BSS_TYPE_ESS,
+				    IEEE80211_PRIVACY_ANY);
 	if (!req->bss)
 		return -ENOENT;
 
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 5839c85075f1..dd78445c7d50 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -59,13 +59,13 @@ enum nl80211_multicast_groups {
 };
 
 static const struct genl_multicast_group nl80211_mcgrps[] = {
-	[NL80211_MCGRP_CONFIG] = { .name = "config", },
-	[NL80211_MCGRP_SCAN] = { .name = "scan", },
-	[NL80211_MCGRP_REGULATORY] = { .name = "regulatory", },
-	[NL80211_MCGRP_MLME] = { .name = "mlme", },
-	[NL80211_MCGRP_VENDOR] = { .name = "vendor", },
+	[NL80211_MCGRP_CONFIG] = { .name = NL80211_MULTICAST_GROUP_CONFIG },
+	[NL80211_MCGRP_SCAN] = { .name = NL80211_MULTICAST_GROUP_SCAN },
+	[NL80211_MCGRP_REGULATORY] = { .name = NL80211_MULTICAST_GROUP_REG },
+	[NL80211_MCGRP_MLME] = { .name = NL80211_MULTICAST_GROUP_MLME },
+	[NL80211_MCGRP_VENDOR] = { .name = NL80211_MULTICAST_GROUP_VENDOR },
 #ifdef CONFIG_NL80211_TESTMODE
-	[NL80211_MCGRP_TESTMODE] = { .name = "testmode", }
+	[NL80211_MCGRP_TESTMODE] = { .name = NL80211_MULTICAST_GROUP_TESTMODE }
 #endif
 };
 
@@ -209,7 +209,7 @@ cfg80211_get_dev_from_info(struct net *netns, struct genl_info *info)
 }
 
 /* policy for the attributes */
-static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = {
+static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_WIPHY] = { .type = NLA_U32 },
 	[NL80211_ATTR_WIPHY_NAME] = { .type = NLA_NUL_STRING,
 				      .len = 20-1 },
@@ -388,13 +388,18 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = {
 	[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_SOCKET_OWNER] = { .type = NLA_FLAG },
 	[NL80211_ATTR_CSA_C_OFFSETS_TX] = { .type = NLA_BINARY },
 	[NL80211_ATTR_USE_RRM] = { .type = NLA_FLAG },
 	[NL80211_ATTR_TSID] = { .type = NLA_U8 },
 	[NL80211_ATTR_USER_PRIO] = { .type = NLA_U8 },
 	[NL80211_ATTR_ADMITTED_TIME] = { .type = NLA_U16 },
 	[NL80211_ATTR_SMPS_MODE] = { .type = NLA_U8 },
+	[NL80211_ATTR_MAC_MASK] = { .len = ETH_ALEN },
+	[NL80211_ATTR_WIPHY_SELF_MANAGED_REG] = { .type = NLA_FLAG },
+	[NL80211_ATTR_NETNS_FD] = { .type = NLA_U32 },
+	[NL80211_ATTR_SCHED_SCAN_DELAY] = { .type = NLA_U32 },
+	[NL80211_ATTR_REG_INDOOR] = { .type = NLA_FLAG },
 };
 
 /* policy for the key attributes */
@@ -428,6 +433,7 @@ nl80211_wowlan_policy[NUM_NL80211_WOWLAN_TRIG] = {
 	[NL80211_WOWLAN_TRIG_4WAY_HANDSHAKE] = { .type = NLA_FLAG },
 	[NL80211_WOWLAN_TRIG_RFKILL_RELEASE] = { .type = NLA_FLAG },
 	[NL80211_WOWLAN_TRIG_TCP_CONNECTION] = { .type = NLA_NESTED },
+	[NL80211_WOWLAN_TRIG_NET_DETECT] = { .type = NLA_NESTED },
 };
 
 static const struct nla_policy
@@ -884,7 +890,12 @@ static int nl80211_key_allowed(struct wireless_dev *wdev)
 		if (!wdev->current_bss)
 			return -ENOLINK;
 		break;
-	default:
+	case NL80211_IFTYPE_UNSPECIFIED:
+	case NL80211_IFTYPE_OCB:
+	case NL80211_IFTYPE_MONITOR:
+	case NL80211_IFTYPE_P2P_DEVICE:
+	case NL80211_IFTYPE_WDS:
+	case NUM_NL80211_IFTYPES:
 		return -EINVAL;
 	}
 
@@ -1080,6 +1091,11 @@ static int nl80211_send_wowlan(struct sk_buff *msg,
 			return -ENOBUFS;
 	}
 
+	if ((rdev->wiphy.wowlan->flags & WIPHY_WOWLAN_NET_DETECT) &&
+	    nla_put_u32(msg, NL80211_WOWLAN_TRIG_NET_DETECT,
+			rdev->wiphy.wowlan->max_nd_match_sets))
+		return -ENOBUFS;
+
 	if (large && nl80211_send_wowlan_tcp_caps(rdev, msg))
 		return -ENOBUFS;
 
@@ -1514,8 +1530,8 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 			if (rdev->wiphy.flags & WIPHY_FLAG_HAS_CHANNEL_SWITCH)
 				CMD(channel_switch, CHANNEL_SWITCH);
 			CMD(set_qos_map, SET_QOS_MAP);
-			if (rdev->wiphy.flags &
-					WIPHY_FLAG_SUPPORTS_WMM_ADMISSION)
+			if (rdev->wiphy.features &
+					NL80211_FEATURE_SUPPORTS_WMM_ADMISSION)
 				CMD(add_tx_ts, ADD_TX_TS);
 		}
 		/* add into the if now */
@@ -1692,12 +1708,22 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 			       rdev->wiphy.max_num_csa_counters))
 			goto nla_put_failure;
 
+		if (rdev->wiphy.regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED &&
+		    nla_put_flag(msg, NL80211_ATTR_WIPHY_SELF_MANAGED_REG))
+			goto nla_put_failure;
+
+		if (nla_put(msg, NL80211_ATTR_EXT_FEATURES,
+			    sizeof(rdev->wiphy.ext_features),
+			    rdev->wiphy.ext_features))
+			goto nla_put_failure;
+
 		/* done */
 		state->split_start = 0;
 		break;
 	}
  finish:
-	return genlmsg_end(msg, hdr);
+	genlmsg_end(msg, hdr);
+	return 0;
 
  nla_put_failure:
 	genlmsg_cancel(msg, hdr);
@@ -2308,7 +2334,8 @@ static inline u64 wdev_id(struct wireless_dev *wdev)
 static int nl80211_send_chandef(struct sk_buff *msg,
 				const struct cfg80211_chan_def *chandef)
 {
-	WARN_ON(!cfg80211_chandef_valid(chandef));
+	if (WARN_ON(!cfg80211_chandef_valid(chandef)))
+		return -EINVAL;
 
 	if (nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ,
 			chandef->chan->center_freq))
@@ -2336,12 +2363,16 @@ static int nl80211_send_chandef(struct sk_buff *msg,
 
 static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flags,
 			      struct cfg80211_registered_device *rdev,
-			      struct wireless_dev *wdev)
+			      struct wireless_dev *wdev, bool removal)
 {
 	struct net_device *dev = wdev->netdev;
+	u8 cmd = NL80211_CMD_NEW_INTERFACE;
 	void *hdr;
 
-	hdr = nl80211hdr_put(msg, portid, seq, flags, NL80211_CMD_NEW_INTERFACE);
+	if (removal)
+		cmd = NL80211_CMD_DEL_INTERFACE;
+
+	hdr = nl80211hdr_put(msg, portid, seq, flags, cmd);
 	if (!hdr)
 		return -1;
 
@@ -2375,7 +2406,8 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag
 			goto nla_put_failure;
 	}
 
-	return genlmsg_end(msg, hdr);
+	genlmsg_end(msg, hdr);
+	return 0;
 
  nla_put_failure:
 	genlmsg_cancel(msg, hdr);
@@ -2408,7 +2440,7 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback *
 			}
 			if (nl80211_send_iface(skb, NETLINK_CB(cb->skb).portid,
 					       cb->nlh->nlmsg_seq, NLM_F_MULTI,
-					       rdev, wdev) < 0) {
+					       rdev, wdev, false) < 0) {
 				goto out;
 			}
 			if_idx++;
@@ -2436,7 +2468,7 @@ 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,
-			       rdev, wdev) < 0) {
+			       rdev, wdev, false) < 0) {
 		nlmsg_free(msg);
 		return -ENOBUFS;
 	}
@@ -2582,7 +2614,7 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info)
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
 	struct vif_params params;
 	struct wireless_dev *wdev;
-	struct sk_buff *msg;
+	struct sk_buff *msg, *event;
 	int err;
 	enum nl80211_iftype type = NL80211_IFTYPE_UNSPECIFIED;
 	u32 flags;
@@ -2605,7 +2637,9 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info)
 	    !(rdev->wiphy.interface_modes & (1 << type)))
 		return -EOPNOTSUPP;
 
-	if (type == NL80211_IFTYPE_P2P_DEVICE && info->attrs[NL80211_ATTR_MAC]) {
+	if ((type == NL80211_IFTYPE_P2P_DEVICE ||
+	     rdev->wiphy.features & NL80211_FEATURE_MAC_ON_CREATE) &&
+	    info->attrs[NL80211_ATTR_MAC]) {
 		nla_memcpy(params.macaddr, info->attrs[NL80211_ATTR_MAC],
 			   ETH_ALEN);
 		if (!is_valid_ether_addr(params.macaddr))
@@ -2619,10 +2653,6 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info)
 			return err;
 	}
 
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return -ENOMEM;
-
 	err = parse_monitor_flags(type == NL80211_IFTYPE_MONITOR ?
 				  info->attrs[NL80211_ATTR_MNTR_FLAGS] : NULL,
 				  &flags);
@@ -2631,15 +2661,23 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info)
 	    !(rdev->wiphy.features & NL80211_FEATURE_ACTIVE_MONITOR))
 		return -EOPNOTSUPP;
 
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
 	wdev = rdev_add_virtual_intf(rdev,
 				nla_data(info->attrs[NL80211_ATTR_IFNAME]),
-				type, err ? NULL : &flags, &params);
-	if (IS_ERR(wdev)) {
+				NET_NAME_USER, type, err ? NULL : &flags,
+				&params);
+	if (WARN_ON(!wdev)) {
+		nlmsg_free(msg);
+		return -EPROTO;
+	} else if (IS_ERR(wdev)) {
 		nlmsg_free(msg);
 		return PTR_ERR(wdev);
 	}
 
-	if (info->attrs[NL80211_ATTR_IFACE_SOCKET_OWNER])
+	if (info->attrs[NL80211_ATTR_SOCKET_OWNER])
 		wdev->owner_nlportid = info->snd_portid;
 
 	switch (type) {
@@ -2675,11 +2713,25 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	if (nl80211_send_iface(msg, info->snd_portid, info->snd_seq, 0,
-			       rdev, wdev) < 0) {
+			       rdev, wdev, false) < 0) {
 		nlmsg_free(msg);
 		return -ENOBUFS;
 	}
 
+	event = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (event) {
+		if (nl80211_send_iface(event, 0, 0, 0,
+				       rdev, wdev, false) < 0) {
+			nlmsg_free(event);
+			goto out;
+		}
+
+		genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy),
+					event, 0, NL80211_MCGRP_CONFIG,
+					GFP_KERNEL);
+	}
+
+out:
 	return genlmsg_reply(msg, info);
 }
 
@@ -2687,10 +2739,18 @@ static int nl80211_del_interface(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
 	struct wireless_dev *wdev = info->user_ptr[1];
+	struct sk_buff *msg;
+	int status;
 
 	if (!rdev->ops->del_virtual_intf)
 		return -EOPNOTSUPP;
 
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (msg && nl80211_send_iface(msg, 0, 0, 0, rdev, wdev, true) < 0) {
+		nlmsg_free(msg);
+		msg = NULL;
+	}
+
 	/*
 	 * If we remove a wireless device without a netdev then clear
 	 * user_ptr[1] so that nl80211_post_doit won't dereference it
@@ -2701,7 +2761,15 @@ static int nl80211_del_interface(struct sk_buff *skb, struct genl_info *info)
 	if (!wdev->netdev)
 		info->user_ptr[1] = NULL;
 
-	return rdev_del_virtual_intf(rdev, wdev);
+	status = rdev_del_virtual_intf(rdev, wdev);
+	if (status >= 0 && msg)
+		genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy),
+					msg, 0, NL80211_MCGRP_CONFIG,
+					GFP_KERNEL);
+	else
+		nlmsg_free(msg);
+
+	return status;
 }
 
 static int nl80211_set_noack_map(struct sk_buff *skb, struct genl_info *info)
@@ -2805,6 +2873,9 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info)
 	if (!rdev->ops->get_key)
 		return -EOPNOTSUPP;
 
+	if (!pairwise && mac_addr && !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN))
+		return -ENOENT;
+
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!msg)
 		return -ENOMEM;
@@ -2824,10 +2895,6 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info)
 	    nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, mac_addr))
 		goto nla_put_failure;
 
-	if (pairwise && mac_addr &&
-	    !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN))
-		return -ENOENT;
-
 	err = rdev_get_key(rdev, dev, key_idx, pairwise, mac_addr, &cookie,
 			   get_key_callback);
 
@@ -2998,7 +3065,7 @@ static int nl80211_del_key(struct sk_buff *skb, struct genl_info *info)
 	wdev_lock(dev->ieee80211_ptr);
 	err = nl80211_key_allowed(dev->ieee80211_ptr);
 
-	if (key.type == NL80211_KEYTYPE_PAIRWISE && mac_addr &&
+	if (key.type == NL80211_KEYTYPE_GROUP && mac_addr &&
 	    !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN))
 		err = -ENOENT;
 
@@ -3514,6 +3581,7 @@ static bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info,
 	struct nlattr *rate;
 	u32 bitrate;
 	u16 bitrate_compat;
+	enum nl80211_attrs rate_flg;
 
 	rate = nla_nest_start(msg, attr);
 	if (!rate)
@@ -3530,12 +3598,36 @@ static bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info,
 	    nla_put_u16(msg, NL80211_RATE_INFO_BITRATE, bitrate_compat))
 		return false;
 
+	switch (info->bw) {
+	case RATE_INFO_BW_5:
+		rate_flg = NL80211_RATE_INFO_5_MHZ_WIDTH;
+		break;
+	case RATE_INFO_BW_10:
+		rate_flg = NL80211_RATE_INFO_10_MHZ_WIDTH;
+		break;
+	default:
+		WARN_ON(1);
+		/* fall through */
+	case RATE_INFO_BW_20:
+		rate_flg = 0;
+		break;
+	case RATE_INFO_BW_40:
+		rate_flg = NL80211_RATE_INFO_40_MHZ_WIDTH;
+		break;
+	case RATE_INFO_BW_80:
+		rate_flg = NL80211_RATE_INFO_80_MHZ_WIDTH;
+		break;
+	case RATE_INFO_BW_160:
+		rate_flg = NL80211_RATE_INFO_160_MHZ_WIDTH;
+		break;
+	}
+
+	if (rate_flg && nla_put_flag(msg, rate_flg))
+		return false;
+
 	if (info->flags & RATE_INFO_FLAGS_MCS) {
 		if (nla_put_u8(msg, NL80211_RATE_INFO_MCS, info->mcs))
 			return false;
-		if (info->flags & RATE_INFO_FLAGS_40_MHZ_WIDTH &&
-		    nla_put_flag(msg, NL80211_RATE_INFO_40_MHZ_WIDTH))
-			return false;
 		if (info->flags & RATE_INFO_FLAGS_SHORT_GI &&
 		    nla_put_flag(msg, NL80211_RATE_INFO_SHORT_GI))
 			return false;
@@ -3544,18 +3636,6 @@ static bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info,
 			return false;
 		if (nla_put_u8(msg, NL80211_RATE_INFO_VHT_NSS, info->nss))
 			return false;
-		if (info->flags & RATE_INFO_FLAGS_40_MHZ_WIDTH &&
-		    nla_put_flag(msg, NL80211_RATE_INFO_40_MHZ_WIDTH))
-			return false;
-		if (info->flags & RATE_INFO_FLAGS_80_MHZ_WIDTH &&
-		    nla_put_flag(msg, NL80211_RATE_INFO_80_MHZ_WIDTH))
-			return false;
-		if (info->flags & RATE_INFO_FLAGS_80P80_MHZ_WIDTH &&
-		    nla_put_flag(msg, NL80211_RATE_INFO_80P80_MHZ_WIDTH))
-			return false;
-		if (info->flags & RATE_INFO_FLAGS_160_MHZ_WIDTH &&
-		    nla_put_flag(msg, NL80211_RATE_INFO_160_MHZ_WIDTH))
-			return false;
 		if (info->flags & RATE_INFO_FLAGS_SHORT_GI &&
 		    nla_put_flag(msg, NL80211_RATE_INFO_SHORT_GI))
 			return false;
@@ -3591,8 +3671,8 @@ static bool nl80211_put_signal(struct sk_buff *msg, u8 mask, s8 *signal,
 	return true;
 }
 
-static int nl80211_send_station(struct sk_buff *msg, u32 portid, u32 seq,
-				int flags,
+static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid,
+				u32 seq, int flags,
 				struct cfg80211_registered_device *rdev,
 				struct net_device *dev,
 				const u8 *mac_addr, struct station_info *sinfo)
@@ -3600,7 +3680,7 @@ static int nl80211_send_station(struct sk_buff *msg, u32 portid, u32 seq,
 	void *hdr;
 	struct nlattr *sinfoattr, *bss_param;
 
-	hdr = nl80211hdr_put(msg, portid, seq, flags, NL80211_CMD_NEW_STATION);
+	hdr = nl80211hdr_put(msg, portid, seq, flags, cmd);
 	if (!hdr)
 		return -1;
 
@@ -3612,115 +3692,77 @@ static int nl80211_send_station(struct sk_buff *msg, u32 portid, u32 seq,
 	sinfoattr = nla_nest_start(msg, NL80211_ATTR_STA_INFO);
 	if (!sinfoattr)
 		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_CONNECTED_TIME) &&
-	    nla_put_u32(msg, NL80211_STA_INFO_CONNECTED_TIME,
-			sinfo->connected_time))
-		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_INACTIVE_TIME) &&
-	    nla_put_u32(msg, NL80211_STA_INFO_INACTIVE_TIME,
-			sinfo->inactive_time))
-		goto nla_put_failure;
-	if ((sinfo->filled & (STATION_INFO_RX_BYTES |
-			      STATION_INFO_RX_BYTES64)) &&
+
+#define PUT_SINFO(attr, memb, type) do {				\
+	if (sinfo->filled & BIT(NL80211_STA_INFO_ ## attr) &&		\
+	    nla_put_ ## type(msg, NL80211_STA_INFO_ ## attr,		\
+			     sinfo->memb))				\
+		goto nla_put_failure;					\
+	} while (0)
+
+	PUT_SINFO(CONNECTED_TIME, connected_time, u32);
+	PUT_SINFO(INACTIVE_TIME, inactive_time, u32);
+
+	if (sinfo->filled & (BIT(NL80211_STA_INFO_RX_BYTES) |
+			     BIT(NL80211_STA_INFO_RX_BYTES64)) &&
 	    nla_put_u32(msg, NL80211_STA_INFO_RX_BYTES,
 			(u32)sinfo->rx_bytes))
 		goto nla_put_failure;
-	if ((sinfo->filled & (STATION_INFO_TX_BYTES |
-			      STATION_INFO_TX_BYTES64)) &&
+
+	if (sinfo->filled & (BIT(NL80211_STA_INFO_TX_BYTES) |
+			     BIT(NL80211_STA_INFO_TX_BYTES64)) &&
 	    nla_put_u32(msg, NL80211_STA_INFO_TX_BYTES,
 			(u32)sinfo->tx_bytes))
 		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_RX_BYTES64) &&
-	    nla_put_u64(msg, NL80211_STA_INFO_RX_BYTES64,
-			sinfo->rx_bytes))
-		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_TX_BYTES64) &&
-	    nla_put_u64(msg, NL80211_STA_INFO_TX_BYTES64,
-			sinfo->tx_bytes))
-		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_LLID) &&
-	    nla_put_u16(msg, NL80211_STA_INFO_LLID, sinfo->llid))
-		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_PLID) &&
-	    nla_put_u16(msg, NL80211_STA_INFO_PLID, sinfo->plid))
-		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_PLINK_STATE) &&
-	    nla_put_u8(msg, NL80211_STA_INFO_PLINK_STATE,
-		       sinfo->plink_state))
-		goto nla_put_failure;
+
+	PUT_SINFO(RX_BYTES64, rx_bytes, u64);
+	PUT_SINFO(TX_BYTES64, tx_bytes, u64);
+	PUT_SINFO(LLID, llid, u16);
+	PUT_SINFO(PLID, plid, u16);
+	PUT_SINFO(PLINK_STATE, plink_state, u8);
+
 	switch (rdev->wiphy.signal_type) {
 	case CFG80211_SIGNAL_TYPE_MBM:
-		if ((sinfo->filled & STATION_INFO_SIGNAL) &&
-		    nla_put_u8(msg, NL80211_STA_INFO_SIGNAL,
-			       sinfo->signal))
-			goto nla_put_failure;
-		if ((sinfo->filled & STATION_INFO_SIGNAL_AVG) &&
-		    nla_put_u8(msg, NL80211_STA_INFO_SIGNAL_AVG,
-			       sinfo->signal_avg))
-			goto nla_put_failure;
+		PUT_SINFO(SIGNAL, signal, u8);
+		PUT_SINFO(SIGNAL_AVG, signal_avg, u8);
 		break;
 	default:
 		break;
 	}
-	if (sinfo->filled & STATION_INFO_CHAIN_SIGNAL) {
+	if (sinfo->filled & BIT(NL80211_STA_INFO_CHAIN_SIGNAL)) {
 		if (!nl80211_put_signal(msg, sinfo->chains,
 					sinfo->chain_signal,
 					NL80211_STA_INFO_CHAIN_SIGNAL))
 			goto nla_put_failure;
 	}
-	if (sinfo->filled & STATION_INFO_CHAIN_SIGNAL_AVG) {
+	if (sinfo->filled & BIT(NL80211_STA_INFO_CHAIN_SIGNAL_AVG)) {
 		if (!nl80211_put_signal(msg, sinfo->chains,
 					sinfo->chain_signal_avg,
 					NL80211_STA_INFO_CHAIN_SIGNAL_AVG))
 			goto nla_put_failure;
 	}
-	if (sinfo->filled & STATION_INFO_TX_BITRATE) {
+	if (sinfo->filled & BIT(NL80211_STA_INFO_TX_BITRATE)) {
 		if (!nl80211_put_sta_rate(msg, &sinfo->txrate,
 					  NL80211_STA_INFO_TX_BITRATE))
 			goto nla_put_failure;
 	}
-	if (sinfo->filled & STATION_INFO_RX_BITRATE) {
+	if (sinfo->filled & BIT(NL80211_STA_INFO_RX_BITRATE)) {
 		if (!nl80211_put_sta_rate(msg, &sinfo->rxrate,
 					  NL80211_STA_INFO_RX_BITRATE))
 			goto nla_put_failure;
 	}
-	if ((sinfo->filled & STATION_INFO_RX_PACKETS) &&
-	    nla_put_u32(msg, NL80211_STA_INFO_RX_PACKETS,
-			sinfo->rx_packets))
-		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_TX_PACKETS) &&
-	    nla_put_u32(msg, NL80211_STA_INFO_TX_PACKETS,
-			sinfo->tx_packets))
-		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_TX_RETRIES) &&
-	    nla_put_u32(msg, NL80211_STA_INFO_TX_RETRIES,
-			sinfo->tx_retries))
-		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_TX_FAILED) &&
-	    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))
-		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_LOCAL_PM) &&
-	    nla_put_u32(msg, NL80211_STA_INFO_LOCAL_PM,
-			sinfo->local_pm))
-		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_PEER_PM) &&
-	    nla_put_u32(msg, NL80211_STA_INFO_PEER_PM,
-			sinfo->peer_pm))
-		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_NONPEER_PM) &&
-	    nla_put_u32(msg, NL80211_STA_INFO_NONPEER_PM,
-			sinfo->nonpeer_pm))
-		goto nla_put_failure;
-	if (sinfo->filled & STATION_INFO_BSS_PARAM) {
+
+	PUT_SINFO(RX_PACKETS, rx_packets, u32);
+	PUT_SINFO(TX_PACKETS, tx_packets, u32);
+	PUT_SINFO(TX_RETRIES, tx_retries, u32);
+	PUT_SINFO(TX_FAILED, tx_failed, u32);
+	PUT_SINFO(EXPECTED_THROUGHPUT, expected_throughput, u32);
+	PUT_SINFO(BEACON_LOSS, beacon_loss_count, u32);
+	PUT_SINFO(LOCAL_PM, local_pm, u32);
+	PUT_SINFO(PEER_PM, peer_pm, u32);
+	PUT_SINFO(NONPEER_PM, nonpeer_pm, u32);
+
+	if (sinfo->filled & BIT(NL80211_STA_INFO_BSS_PARAM)) {
 		bss_param = nla_nest_start(msg, NL80211_STA_INFO_BSS_PARAM);
 		if (!bss_param)
 			goto nla_put_failure;
@@ -3739,23 +3781,68 @@ static int nl80211_send_station(struct sk_buff *msg, u32 portid, u32 seq,
 
 		nla_nest_end(msg, bss_param);
 	}
-	if ((sinfo->filled & STATION_INFO_STA_FLAGS) &&
+	if ((sinfo->filled & BIT(NL80211_STA_INFO_STA_FLAGS)) &&
 	    nla_put(msg, NL80211_STA_INFO_STA_FLAGS,
 		    sizeof(struct nl80211_sta_flag_update),
 		    &sinfo->sta_flags))
 		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_T_OFFSET) &&
-		nla_put_u64(msg, NL80211_STA_INFO_T_OFFSET,
-			    sinfo->t_offset))
-		goto nla_put_failure;
+
+	PUT_SINFO(T_OFFSET, t_offset, u64);
+	PUT_SINFO(RX_DROP_MISC, rx_dropped_misc, u64);
+	PUT_SINFO(BEACON_RX, rx_beacon, u64);
+	PUT_SINFO(BEACON_SIGNAL_AVG, rx_beacon_signal_avg, u8);
+
+#undef PUT_SINFO
+
+	if (sinfo->filled & BIT(NL80211_STA_INFO_TID_STATS)) {
+		struct nlattr *tidsattr;
+		int tid;
+
+		tidsattr = nla_nest_start(msg, NL80211_STA_INFO_TID_STATS);
+		if (!tidsattr)
+			goto nla_put_failure;
+
+		for (tid = 0; tid < IEEE80211_NUM_TIDS + 1; tid++) {
+			struct cfg80211_tid_stats *tidstats;
+			struct nlattr *tidattr;
+
+			tidstats = &sinfo->pertid[tid];
+
+			if (!tidstats->filled)
+				continue;
+
+			tidattr = nla_nest_start(msg, tid + 1);
+			if (!tidattr)
+				goto nla_put_failure;
+
+#define PUT_TIDVAL(attr, memb, type) do {				\
+	if (tidstats->filled & BIT(NL80211_TID_STATS_ ## attr) &&	\
+	    nla_put_ ## type(msg, NL80211_TID_STATS_ ## attr,		\
+			     tidstats->memb))				\
+		goto nla_put_failure;					\
+	} while (0)
+
+			PUT_TIDVAL(RX_MSDU, rx_msdu, u64);
+			PUT_TIDVAL(TX_MSDU, tx_msdu, u64);
+			PUT_TIDVAL(TX_MSDU_RETRIES, tx_msdu_retries, u64);
+			PUT_TIDVAL(TX_MSDU_FAILED, tx_msdu_failed, u64);
+
+#undef PUT_TIDVAL
+			nla_nest_end(msg, tidattr);
+		}
+
+		nla_nest_end(msg, tidsattr);
+	}
+
 	nla_nest_end(msg, sinfoattr);
 
-	if ((sinfo->filled & STATION_INFO_ASSOC_REQ_IES) &&
+	if (sinfo->assoc_req_ies_len &&
 	    nla_put(msg, NL80211_ATTR_IE, sinfo->assoc_req_ies_len,
 		    sinfo->assoc_req_ies))
 		goto nla_put_failure;
 
-	return genlmsg_end(msg, hdr);
+	genlmsg_end(msg, hdr);
+	return 0;
 
  nla_put_failure:
 	genlmsg_cancel(msg, hdr);
@@ -3795,7 +3882,7 @@ static int nl80211_dump_station(struct sk_buff *skb,
 		if (err)
 			goto out_err;
 
-		if (nl80211_send_station(skb,
+		if (nl80211_send_station(skb, NL80211_CMD_NEW_STATION,
 				NETLINK_CB(cb->skb).portid,
 				cb->nlh->nlmsg_seq, NLM_F_MULTI,
 				rdev, wdev->netdev, mac_addr,
@@ -3842,7 +3929,8 @@ static int nl80211_get_station(struct sk_buff *skb, struct genl_info *info)
 	if (!msg)
 		return -ENOMEM;
 
-	if (nl80211_send_station(msg, info->snd_portid, info->snd_seq, 0,
+	if (nl80211_send_station(msg, NL80211_CMD_NEW_STATION,
+				 info->snd_portid, info->snd_seq, 0,
 				 rdev, dev, mac_addr, &sinfo) < 0) {
 		nlmsg_free(msg);
 		return -ENOBUFS;
@@ -4312,6 +4400,16 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info)
 	if (parse_station_flags(info, dev->ieee80211_ptr->iftype, &params))
 		return -EINVAL;
 
+	/* HT/VHT requires QoS, but if we don't have that just ignore HT/VHT
+	 * as userspace might just pass through the capabilities from the IEs
+	 * directly, rather than enforcing this restriction and returning an
+	 * error in this case.
+	 */
+	if (!(params.sta_flags_set & BIT(NL80211_STA_FLAG_WME))) {
+		params.ht_capa = NULL;
+		params.vht_capa = NULL;
+	}
+
 	/* When you run into this, adjust the code below for the new flag */
 	BUILD_BUG_ON(NL80211_STA_FLAG_MAX != 7);
 
@@ -4398,10 +4496,12 @@ static int nl80211_del_station(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 *mac_addr = NULL;
+	struct station_del_parameters params;
+
+	memset(&params, 0, sizeof(params));
 
 	if (info->attrs[NL80211_ATTR_MAC])
-		mac_addr = nla_data(info->attrs[NL80211_ATTR_MAC]);
+		params.mac = nla_data(info->attrs[NL80211_ATTR_MAC]);
 
 	if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP &&
 	    dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP_VLAN &&
@@ -4412,7 +4512,28 @@ static int nl80211_del_station(struct sk_buff *skb, struct genl_info *info)
 	if (!rdev->ops->del_station)
 		return -EOPNOTSUPP;
 
-	return rdev_del_station(rdev, dev, mac_addr);
+	if (info->attrs[NL80211_ATTR_MGMT_SUBTYPE]) {
+		params.subtype =
+			nla_get_u8(info->attrs[NL80211_ATTR_MGMT_SUBTYPE]);
+		if (params.subtype != IEEE80211_STYPE_DISASSOC >> 4 &&
+		    params.subtype != IEEE80211_STYPE_DEAUTH >> 4)
+			return -EINVAL;
+	} else {
+		/* Default to Deauthentication frame */
+		params.subtype = IEEE80211_STYPE_DEAUTH >> 4;
+	}
+
+	if (info->attrs[NL80211_ATTR_REASON_CODE]) {
+		params.reason_code =
+			nla_get_u16(info->attrs[NL80211_ATTR_REASON_CODE]);
+		if (params.reason_code == 0)
+			return -EINVAL; /* 0 is reserved */
+	} else {
+		/* Default to reason code 2 */
+		params.reason_code = WLAN_REASON_PREV_AUTH_NOT_VALID;
+	}
+
+	return rdev_del_station(rdev, dev, &params);
 }
 
 static int nl80211_send_mpath(struct sk_buff *msg, u32 portid, u32 seq,
@@ -4423,7 +4544,7 @@ static int nl80211_send_mpath(struct sk_buff *msg, u32 portid, u32 seq,
 	void *hdr;
 	struct nlattr *pinfoattr;
 
-	hdr = nl80211hdr_put(msg, portid, seq, flags, NL80211_CMD_NEW_STATION);
+	hdr = nl80211hdr_put(msg, portid, seq, flags, NL80211_CMD_NEW_MPATH);
 	if (!hdr)
 		return -1;
 
@@ -4461,7 +4582,8 @@ static int nl80211_send_mpath(struct sk_buff *msg, u32 portid, u32 seq,
 
 	nla_nest_end(msg, pinfoattr);
 
-	return genlmsg_end(msg, hdr);
+	genlmsg_end(msg, hdr);
+	return 0;
 
  nla_put_failure:
 	genlmsg_cancel(msg, hdr);
@@ -4624,6 +4746,96 @@ static int nl80211_del_mpath(struct sk_buff *skb, struct genl_info *info)
 	return rdev_del_mpath(rdev, dev, dst);
 }
 
+static int nl80211_get_mpp(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg80211_registered_device *rdev = info->user_ptr[0];
+	int err;
+	struct net_device *dev = info->user_ptr[1];
+	struct mpath_info pinfo;
+	struct sk_buff *msg;
+	u8 *dst = NULL;
+	u8 mpp[ETH_ALEN];
+
+	memset(&pinfo, 0, sizeof(pinfo));
+
+	if (!info->attrs[NL80211_ATTR_MAC])
+		return -EINVAL;
+
+	dst = nla_data(info->attrs[NL80211_ATTR_MAC]);
+
+	if (!rdev->ops->get_mpp)
+		return -EOPNOTSUPP;
+
+	if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_MESH_POINT)
+		return -EOPNOTSUPP;
+
+	err = rdev_get_mpp(rdev, dev, dst, mpp, &pinfo);
+	if (err)
+		return err;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	if (nl80211_send_mpath(msg, info->snd_portid, info->snd_seq, 0,
+			       dev, dst, mpp, &pinfo) < 0) {
+		nlmsg_free(msg);
+		return -ENOBUFS;
+	}
+
+	return genlmsg_reply(msg, info);
+}
+
+static int nl80211_dump_mpp(struct sk_buff *skb,
+			    struct netlink_callback *cb)
+{
+	struct mpath_info pinfo;
+	struct cfg80211_registered_device *rdev;
+	struct wireless_dev *wdev;
+	u8 dst[ETH_ALEN];
+	u8 mpp[ETH_ALEN];
+	int path_idx = cb->args[2];
+	int err;
+
+	err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
+	if (err)
+		return err;
+
+	if (!rdev->ops->dump_mpp) {
+		err = -EOPNOTSUPP;
+		goto out_err;
+	}
+
+	if (wdev->iftype != NL80211_IFTYPE_MESH_POINT) {
+		err = -EOPNOTSUPP;
+		goto out_err;
+	}
+
+	while (1) {
+		err = rdev_dump_mpp(rdev, wdev->netdev, path_idx, dst,
+				    mpp, &pinfo);
+		if (err == -ENOENT)
+			break;
+		if (err)
+			goto out_err;
+
+		if (nl80211_send_mpath(skb, NETLINK_CB(cb->skb).portid,
+				       cb->nlh->nlmsg_seq, NLM_F_MULTI,
+				       wdev->netdev, dst, mpp,
+				       &pinfo) < 0)
+			goto out;
+
+		path_idx++;
+	}
+
+ out:
+	cb->args[2] = path_idx;
+	err = skb->len;
+ out_err:
+	nl80211_finish_wdev_dump(rdev);
+	return err;
+}
+
 static int nl80211_set_bss(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
@@ -4756,7 +4968,10 @@ static int parse_reg_rule(struct nlattr *tb[],
 static int nl80211_req_set_reg(struct sk_buff *skb, struct genl_info *info)
 {
 	char *data = NULL;
+	bool is_indoor;
 	enum nl80211_user_reg_hint_type user_reg_hint_type;
+	u32 owner_nlportid;
+
 
 	/*
 	 * You should only get this when cfg80211 hasn't yet initialized
@@ -4782,7 +4997,15 @@ static int nl80211_req_set_reg(struct sk_buff *skb, struct genl_info *info)
 		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();
+		if (info->attrs[NL80211_ATTR_SOCKET_OWNER]) {
+			owner_nlportid = info->snd_portid;
+			is_indoor = !!info->attrs[NL80211_ATTR_REG_INDOOR];
+		} else {
+			owner_nlportid = 0;
+			is_indoor = true;
+		}
+
+		return regulatory_hint_indoor(is_indoor, owner_nlportid);
 	default:
 		return -EINVAL;
 	}
@@ -5063,7 +5286,7 @@ do {									    \
 	FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshAwakeWindowDuration,
 				  0, 65535, mask,
 				  NL80211_MESHCONF_AWAKE_WINDOW, nla_get_u16);
-	FILL_IN_MESH_PARAM_IF_SET(tb, cfg, plink_timeout, 1, 0xffffffff,
+	FILL_IN_MESH_PARAM_IF_SET(tb, cfg, plink_timeout, 0, 0xffffffff,
 				  mask, NL80211_MESHCONF_PLINK_TIMEOUT,
 				  nla_get_u32);
 	if (mask_out)
@@ -5165,42 +5388,20 @@ static int nl80211_update_mesh_config(struct sk_buff *skb,
 	return err;
 }
 
-static int nl80211_get_reg(struct sk_buff *skb, struct genl_info *info)
+static int nl80211_put_regdom(const struct ieee80211_regdomain *regdom,
+			      struct sk_buff *msg)
 {
-	const struct ieee80211_regdomain *regdom;
-	struct sk_buff *msg;
-	void *hdr = NULL;
 	struct nlattr *nl_reg_rules;
 	unsigned int i;
 
-	if (!cfg80211_regdomain)
-		return -EINVAL;
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return -ENOBUFS;
-
-	hdr = nl80211hdr_put(msg, info->snd_portid, info->snd_seq, 0,
-			     NL80211_CMD_GET_REG);
-	if (!hdr)
-		goto put_failure;
-
-	if (reg_last_request_cell_base() &&
-	    nla_put_u32(msg, NL80211_ATTR_USER_REG_HINT_TYPE,
-			NL80211_USER_REG_HINT_CELL_BASE))
-		goto nla_put_failure;
-
-	rcu_read_lock();
-	regdom = rcu_dereference(cfg80211_regdomain);
-
 	if (nla_put_string(msg, NL80211_ATTR_REG_ALPHA2, regdom->alpha2) ||
 	    (regdom->dfs_region &&
 	     nla_put_u8(msg, NL80211_ATTR_DFS_REGION, regdom->dfs_region)))
-		goto nla_put_failure_rcu;
+		goto nla_put_failure;
 
 	nl_reg_rules = nla_nest_start(msg, NL80211_ATTR_REG_RULES);
 	if (!nl_reg_rules)
-		goto nla_put_failure_rcu;
+		goto nla_put_failure;
 
 	for (i = 0; i < regdom->n_reg_rules; i++) {
 		struct nlattr *nl_reg_rule;
@@ -5215,7 +5416,7 @@ static int nl80211_get_reg(struct sk_buff *skb, struct genl_info *info)
 
 		nl_reg_rule = nla_nest_start(msg, i);
 		if (!nl_reg_rule)
-			goto nla_put_failure_rcu;
+			goto nla_put_failure;
 
 		max_bandwidth_khz = freq_range->max_bandwidth_khz;
 		if (!max_bandwidth_khz)
@@ -5236,13 +5437,74 @@ static int nl80211_get_reg(struct sk_buff *skb, struct genl_info *info)
 				power_rule->max_eirp) ||
 		    nla_put_u32(msg, NL80211_ATTR_DFS_CAC_TIME,
 				reg_rule->dfs_cac_ms))
-			goto nla_put_failure_rcu;
+			goto nla_put_failure;
 
 		nla_nest_end(msg, nl_reg_rule);
 	}
-	rcu_read_unlock();
 
 	nla_nest_end(msg, nl_reg_rules);
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
+static int nl80211_get_reg_do(struct sk_buff *skb, struct genl_info *info)
+{
+	const struct ieee80211_regdomain *regdom = NULL;
+	struct cfg80211_registered_device *rdev;
+	struct wiphy *wiphy = NULL;
+	struct sk_buff *msg;
+	void *hdr;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOBUFS;
+
+	hdr = nl80211hdr_put(msg, info->snd_portid, info->snd_seq, 0,
+			     NL80211_CMD_GET_REG);
+	if (!hdr)
+		goto put_failure;
+
+	if (info->attrs[NL80211_ATTR_WIPHY]) {
+		bool self_managed;
+
+		rdev = cfg80211_get_dev_from_info(genl_info_net(info), info);
+		if (IS_ERR(rdev)) {
+			nlmsg_free(msg);
+			return PTR_ERR(rdev);
+		}
+
+		wiphy = &rdev->wiphy;
+		self_managed = wiphy->regulatory_flags &
+			       REGULATORY_WIPHY_SELF_MANAGED;
+		regdom = get_wiphy_regdom(wiphy);
+
+		/* a self-managed-reg device must have a private regdom */
+		if (WARN_ON(!regdom && self_managed)) {
+			nlmsg_free(msg);
+			return -EINVAL;
+		}
+
+		if (regdom &&
+		    nla_put_u32(msg, NL80211_ATTR_WIPHY, get_wiphy_idx(wiphy)))
+			goto nla_put_failure;
+	}
+
+	if (!wiphy && reg_last_request_cell_base() &&
+	    nla_put_u32(msg, NL80211_ATTR_USER_REG_HINT_TYPE,
+			NL80211_USER_REG_HINT_CELL_BASE))
+		goto nla_put_failure;
+
+	rcu_read_lock();
+
+	if (!regdom)
+		regdom = rcu_dereference(cfg80211_regdomain);
+
+	if (nl80211_put_regdom(regdom, msg))
+		goto nla_put_failure_rcu;
+
+	rcu_read_unlock();
 
 	genlmsg_end(msg, hdr);
 	return genlmsg_reply(msg, info);
@@ -5256,15 +5518,93 @@ put_failure:
 	return -EMSGSIZE;
 }
 
+static int nl80211_send_regdom(struct sk_buff *msg, struct netlink_callback *cb,
+			       u32 seq, int flags, struct wiphy *wiphy,
+			       const struct ieee80211_regdomain *regdom)
+{
+	void *hdr = nl80211hdr_put(msg, NETLINK_CB(cb->skb).portid, seq, flags,
+				   NL80211_CMD_GET_REG);
+
+	if (!hdr)
+		return -1;
+
+	genl_dump_check_consistent(cb, hdr, &nl80211_fam);
+
+	if (nl80211_put_regdom(regdom, msg))
+		goto nla_put_failure;
+
+	if (!wiphy && reg_last_request_cell_base() &&
+	    nla_put_u32(msg, NL80211_ATTR_USER_REG_HINT_TYPE,
+			NL80211_USER_REG_HINT_CELL_BASE))
+		goto nla_put_failure;
+
+	if (wiphy &&
+	    nla_put_u32(msg, NL80211_ATTR_WIPHY, get_wiphy_idx(wiphy)))
+		goto nla_put_failure;
+
+	if (wiphy && wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED &&
+	    nla_put_flag(msg, NL80211_ATTR_WIPHY_SELF_MANAGED_REG))
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	return -EMSGSIZE;
+}
+
+static int nl80211_get_reg_dump(struct sk_buff *skb,
+				struct netlink_callback *cb)
+{
+	const struct ieee80211_regdomain *regdom = NULL;
+	struct cfg80211_registered_device *rdev;
+	int err, reg_idx, start = cb->args[2];
+
+	rtnl_lock();
+
+	if (cfg80211_regdomain && start == 0) {
+		err = nl80211_send_regdom(skb, cb, cb->nlh->nlmsg_seq,
+					  NLM_F_MULTI, NULL,
+					  rtnl_dereference(cfg80211_regdomain));
+		if (err < 0)
+			goto out_err;
+	}
+
+	/* the global regdom is idx 0 */
+	reg_idx = 1;
+	list_for_each_entry(rdev, &cfg80211_rdev_list, list) {
+		regdom = get_wiphy_regdom(&rdev->wiphy);
+		if (!regdom)
+			continue;
+
+		if (++reg_idx <= start)
+			continue;
+
+		err = nl80211_send_regdom(skb, cb, cb->nlh->nlmsg_seq,
+					  NLM_F_MULTI, &rdev->wiphy, regdom);
+		if (err < 0) {
+			reg_idx--;
+			break;
+		}
+	}
+
+	cb->args[2] = reg_idx;
+	err = skb->len;
+out_err:
+	rtnl_unlock();
+	return err;
+}
+
 static int nl80211_set_reg(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nlattr *tb[NL80211_REG_RULE_ATTR_MAX + 1];
 	struct nlattr *nl_reg_rule;
-	char *alpha2 = NULL;
-	int rem_reg_rules = 0, r = 0;
+	char *alpha2;
+	int rem_reg_rules, r;
 	u32 num_rules = 0, rule_idx = 0, size_of_regd;
 	enum nl80211_dfs_regions dfs_region = NL80211_DFS_UNSET;
-	struct ieee80211_regdomain *rd = NULL;
+	struct ieee80211_regdomain *rd;
 
 	if (!info->attrs[NL80211_ATTR_REG_ALPHA2])
 		return -EINVAL;
@@ -5324,7 +5664,7 @@ static int nl80211_set_reg(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
-	r = set_regdom(rd);
+	r = set_regdom(rd, REGD_SOURCE_CRDA);
 	/* set_regdom took ownership */
 	rd = NULL;
 
@@ -5358,6 +5698,43 @@ static int validate_scan_freqs(struct nlattr *freqs)
 	return n_channels;
 }
 
+static int nl80211_parse_random_mac(struct nlattr **attrs,
+				    u8 *mac_addr, u8 *mac_addr_mask)
+{
+	int i;
+
+	if (!attrs[NL80211_ATTR_MAC] && !attrs[NL80211_ATTR_MAC_MASK]) {
+		eth_zero_addr(mac_addr);
+		eth_zero_addr(mac_addr_mask);
+		mac_addr[0] = 0x2;
+		mac_addr_mask[0] = 0x3;
+
+		return 0;
+	}
+
+	/* need both or none */
+	if (!attrs[NL80211_ATTR_MAC] || !attrs[NL80211_ATTR_MAC_MASK])
+		return -EINVAL;
+
+	memcpy(mac_addr, nla_data(attrs[NL80211_ATTR_MAC]), ETH_ALEN);
+	memcpy(mac_addr_mask, nla_data(attrs[NL80211_ATTR_MAC_MASK]), ETH_ALEN);
+
+	/* don't allow or configure an mcast address */
+	if (!is_multicast_ether_addr(mac_addr_mask) ||
+	    is_multicast_ether_addr(mac_addr))
+		return -EINVAL;
+
+	/*
+	 * allow users to pass a MAC address that has bits set outside
+	 * of the mask, but don't bother drivers with having to deal
+	 * with such bits
+	 */
+	for (i = 0; i < ETH_ALEN; i++)
+		mac_addr[i] &= mac_addr_mask[i];
+
+	return 0;
+}
+
 static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
@@ -5424,7 +5801,7 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info)
 		request->ssids = (void *)&request->channels[n_channels];
 	request->n_ssids = n_ssids;
 	if (ie_len) {
-		if (request->ssids)
+		if (n_ssids)
 			request->ie = (void *)(request->ssids + n_ssids);
 		else
 			request->ie = (void *)(request->channels + n_channels);
@@ -5480,7 +5857,7 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info)
 	request->n_channels = i;
 
 	i = 0;
-	if (info->attrs[NL80211_ATTR_SCAN_SSIDS]) {
+	if (n_ssids) {
 		nla_for_each_nested(attr, info->attrs[NL80211_ATTR_SCAN_SSIDS], tmp) {
 			if (nla_len(attr) > IEEE80211_MAX_SSID_LEN) {
 				err = -EINVAL;
@@ -5535,6 +5912,25 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info)
 			err = -EOPNOTSUPP;
 			goto out_free;
 		}
+
+		if (request->flags & NL80211_SCAN_FLAG_RANDOM_ADDR) {
+			if (!(wiphy->features &
+					NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR)) {
+				err = -EOPNOTSUPP;
+				goto out_free;
+			}
+
+			if (wdev->current_bss) {
+				err = -EOPNOTSUPP;
+				goto out_free;
+			}
+
+			err = nl80211_parse_random_mac(info->attrs,
+						       request->mac_addr,
+						       request->mac_addr_mask);
+			if (err)
+				goto out_free;
+		}
 	}
 
 	request->no_cck =
@@ -5561,14 +5957,12 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info)
 	return err;
 }
 
-static int nl80211_start_sched_scan(struct sk_buff *skb,
-				    struct genl_info *info)
+static struct cfg80211_sched_scan_request *
+nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev,
+			 struct nlattr **attrs)
 {
 	struct cfg80211_sched_scan_request *request;
-	struct cfg80211_registered_device *rdev = info->user_ptr[0];
-	struct net_device *dev = info->user_ptr[1];
 	struct nlattr *attr;
-	struct wiphy *wiphy;
 	int err, tmp, n_ssids = 0, n_match_sets = 0, n_channels, i;
 	u32 interval;
 	enum ieee80211_band band;
@@ -5576,38 +5970,32 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
 	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)
-		return -EOPNOTSUPP;
-
-	if (!is_valid_ie_attr(info->attrs[NL80211_ATTR_IE]))
-		return -EINVAL;
+	if (!is_valid_ie_attr(attrs[NL80211_ATTR_IE]))
+		return ERR_PTR(-EINVAL);
 
-	if (!info->attrs[NL80211_ATTR_SCHED_SCAN_INTERVAL])
-		return -EINVAL;
+	if (!attrs[NL80211_ATTR_SCHED_SCAN_INTERVAL])
+		return ERR_PTR(-EINVAL);
 
-	interval = nla_get_u32(info->attrs[NL80211_ATTR_SCHED_SCAN_INTERVAL]);
+	interval = nla_get_u32(attrs[NL80211_ATTR_SCHED_SCAN_INTERVAL]);
 	if (interval == 0)
-		return -EINVAL;
-
-	wiphy = &rdev->wiphy;
+		return ERR_PTR(-EINVAL);
 
-	if (info->attrs[NL80211_ATTR_SCAN_FREQUENCIES]) {
+	if (attrs[NL80211_ATTR_SCAN_FREQUENCIES]) {
 		n_channels = validate_scan_freqs(
-				info->attrs[NL80211_ATTR_SCAN_FREQUENCIES]);
+				attrs[NL80211_ATTR_SCAN_FREQUENCIES]);
 		if (!n_channels)
-			return -EINVAL;
+			return ERR_PTR(-EINVAL);
 	} else {
 		n_channels = ieee80211_get_num_supported_channels(wiphy);
 	}
 
-	if (info->attrs[NL80211_ATTR_SCAN_SSIDS])
-		nla_for_each_nested(attr, info->attrs[NL80211_ATTR_SCAN_SSIDS],
+	if (attrs[NL80211_ATTR_SCAN_SSIDS])
+		nla_for_each_nested(attr, attrs[NL80211_ATTR_SCAN_SSIDS],
 				    tmp)
 			n_ssids++;
 
 	if (n_ssids > wiphy->max_sched_scan_ssids)
-		return -EINVAL;
+		return ERR_PTR(-EINVAL);
 
 	/*
 	 * First, count the number of 'real' matchsets. Due to an issue with
@@ -5618,9 +6006,9 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
 	 * 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]) {
+	if (attrs[NL80211_ATTR_SCHED_SCAN_MATCH]) {
 		nla_for_each_nested(attr,
-				    info->attrs[NL80211_ATTR_SCHED_SCAN_MATCH],
+				    attrs[NL80211_ATTR_SCHED_SCAN_MATCH],
 				    tmp) {
 			struct nlattr *rssi;
 
@@ -5628,7 +6016,7 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
 					nla_data(attr), nla_len(attr),
 					nl80211_match_policy);
 			if (err)
-				return err;
+				return ERR_PTR(err);
 			/* add other standalone attributes here */
 			if (tb[NL80211_SCHED_SCAN_MATCH_ATTR_SSID]) {
 				n_match_sets++;
@@ -5645,36 +6033,29 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
 		n_match_sets = 1;
 
 	if (n_match_sets > wiphy->max_match_sets)
-		return -EINVAL;
+		return ERR_PTR(-EINVAL);
 
-	if (info->attrs[NL80211_ATTR_IE])
-		ie_len = nla_len(info->attrs[NL80211_ATTR_IE]);
+	if (attrs[NL80211_ATTR_IE])
+		ie_len = nla_len(attrs[NL80211_ATTR_IE]);
 	else
 		ie_len = 0;
 
 	if (ie_len > wiphy->max_sched_scan_ie_len)
-		return -EINVAL;
-
-	if (rdev->sched_scan_req) {
-		err = -EINPROGRESS;
-		goto out;
-	}
+		return ERR_PTR(-EINVAL);
 
 	request = kzalloc(sizeof(*request)
 			+ sizeof(*request->ssids) * n_ssids
 			+ sizeof(*request->match_sets) * n_match_sets
 			+ sizeof(*request->channels) * n_channels
 			+ ie_len, GFP_KERNEL);
-	if (!request) {
-		err = -ENOMEM;
-		goto out;
-	}
+	if (!request)
+		return ERR_PTR(-ENOMEM);
 
 	if (n_ssids)
 		request->ssids = (void *)&request->channels[n_channels];
 	request->n_ssids = n_ssids;
 	if (ie_len) {
-		if (request->ssids)
+		if (n_ssids)
 			request->ie = (void *)(request->ssids + n_ssids);
 		else
 			request->ie = (void *)(request->channels + n_channels);
@@ -5683,7 +6064,7 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
 	if (n_match_sets) {
 		if (request->ie)
 			request->match_sets = (void *)(request->ie + ie_len);
-		else if (request->ssids)
+		else if (n_ssids)
 			request->match_sets =
 				(void *)(request->ssids + n_ssids);
 		else
@@ -5693,10 +6074,10 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
 	request->n_match_sets = n_match_sets;
 
 	i = 0;
-	if (info->attrs[NL80211_ATTR_SCAN_FREQUENCIES]) {
+	if (attrs[NL80211_ATTR_SCAN_FREQUENCIES]) {
 		/* user specified, bail out if channel not found */
 		nla_for_each_nested(attr,
-				    info->attrs[NL80211_ATTR_SCAN_FREQUENCIES],
+				    attrs[NL80211_ATTR_SCAN_FREQUENCIES],
 				    tmp) {
 			struct ieee80211_channel *chan;
 
@@ -5742,8 +6123,8 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
 	request->n_channels = i;
 
 	i = 0;
-	if (info->attrs[NL80211_ATTR_SCAN_SSIDS]) {
-		nla_for_each_nested(attr, info->attrs[NL80211_ATTR_SCAN_SSIDS],
+	if (n_ssids) {
+		nla_for_each_nested(attr, attrs[NL80211_ATTR_SCAN_SSIDS],
 				    tmp) {
 			if (nla_len(attr) > IEEE80211_MAX_SSID_LEN) {
 				err = -EINVAL;
@@ -5757,9 +6138,9 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
 	}
 
 	i = 0;
-	if (info->attrs[NL80211_ATTR_SCHED_SCAN_MATCH]) {
+	if (attrs[NL80211_ATTR_SCHED_SCAN_MATCH]) {
 		nla_for_each_nested(attr,
-				    info->attrs[NL80211_ATTR_SCHED_SCAN_MATCH],
+				    attrs[NL80211_ATTR_SCHED_SCAN_MATCH],
 				    tmp) {
 			struct nlattr *ssid, *rssi;
 
@@ -5799,7 +6180,7 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
 		}
 
 		/* there was no other matchset, so the RSSI one is alone */
-		if (i == 0)
+		if (i == 0 && n_match_sets)
 			request->match_sets[0].rssi_thold = default_match_rssi;
 
 		request->min_rssi_thold = INT_MAX;
@@ -5814,36 +6195,98 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
 	if (ie_len) {
 		request->ie_len = ie_len;
 		memcpy((void *)request->ie,
-		       nla_data(info->attrs[NL80211_ATTR_IE]),
+		       nla_data(attrs[NL80211_ATTR_IE]),
 		       request->ie_len);
 	}
 
-	if (info->attrs[NL80211_ATTR_SCAN_FLAGS]) {
+	if (attrs[NL80211_ATTR_SCAN_FLAGS]) {
 		request->flags = nla_get_u32(
-			info->attrs[NL80211_ATTR_SCAN_FLAGS]);
+			attrs[NL80211_ATTR_SCAN_FLAGS]);
 		if ((request->flags & NL80211_SCAN_FLAG_LOW_PRIORITY) &&
 		    !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) {
 			err = -EOPNOTSUPP;
 			goto out_free;
 		}
+
+		if (request->flags & NL80211_SCAN_FLAG_RANDOM_ADDR) {
+			u32 flg = NL80211_FEATURE_SCHED_SCAN_RANDOM_MAC_ADDR;
+
+			if (!wdev) /* must be net-detect */
+				flg = NL80211_FEATURE_ND_RANDOM_MAC_ADDR;
+
+			if (!(wiphy->features & flg)) {
+				err = -EOPNOTSUPP;
+				goto out_free;
+			}
+
+			if (wdev && wdev->current_bss) {
+				err = -EOPNOTSUPP;
+				goto out_free;
+			}
+
+			err = nl80211_parse_random_mac(attrs, request->mac_addr,
+						       request->mac_addr_mask);
+			if (err)
+				goto out_free;
+		}
 	}
 
-	request->dev = dev;
-	request->wiphy = &rdev->wiphy;
+	if (attrs[NL80211_ATTR_SCHED_SCAN_DELAY])
+		request->delay =
+			nla_get_u32(attrs[NL80211_ATTR_SCHED_SCAN_DELAY]);
+
 	request->interval = interval;
 	request->scan_start = jiffies;
 
-	err = rdev_sched_scan_start(rdev, dev, request);
-	if (!err) {
-		rdev->sched_scan_req = request;
-		nl80211_send_sched_scan(rdev, dev,
-					NL80211_CMD_START_SCHED_SCAN);
-		goto out;
-	}
+	return request;
 
 out_free:
 	kfree(request);
-out:
+	return ERR_PTR(err);
+}
+
+static int nl80211_start_sched_scan(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];
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	struct cfg80211_sched_scan_request *sched_scan_req;
+	int err;
+
+	if (!(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_SCHED_SCAN) ||
+	    !rdev->ops->sched_scan_start)
+		return -EOPNOTSUPP;
+
+	if (rdev->sched_scan_req)
+		return -EINPROGRESS;
+
+	sched_scan_req = nl80211_parse_sched_scan(&rdev->wiphy, wdev,
+						  info->attrs);
+
+	err = PTR_ERR_OR_ZERO(sched_scan_req);
+	if (err)
+		goto out_err;
+
+	err = rdev_sched_scan_start(rdev, dev, sched_scan_req);
+	if (err)
+		goto out_free;
+
+	sched_scan_req->dev = dev;
+	sched_scan_req->wiphy = &rdev->wiphy;
+
+	if (info->attrs[NL80211_ATTR_SOCKET_OWNER])
+		sched_scan_req->owner_nlportid = info->snd_portid;
+
+	rcu_assign_pointer(rdev->sched_scan_req, sched_scan_req);
+
+	nl80211_send_sched_scan(rdev, dev,
+				NL80211_CMD_START_SCHED_SCAN);
+	return 0;
+
+out_free:
+	kfree(sched_scan_req);
+out_err:
 	return err;
 }
 
@@ -5923,7 +6366,6 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info)
 	 * function is called under RTNL lock, so this should not be a problem.
 	 */
 	static struct nlattr *csa_attrs[NL80211_ATTR_MAX+1];
-	u8 radar_detect_width = 0;
 	int err;
 	bool need_new_beacon = false;
 	int len, i;
@@ -6059,10 +6501,8 @@ skip_beacons:
 	if (err < 0)
 		return err;
 
-	if (err > 0) {
-		radar_detect_width = BIT(params.chandef.width);
+	if (err > 0)
 		params.radar_required = true;
-	}
 
 	if (info->attrs[NL80211_ATTR_CH_SWITCH_BLOCK_TX])
 		params.block_tx = true;
@@ -6181,7 +6621,8 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb,
 
 	nla_nest_end(msg, bss);
 
-	return genlmsg_end(msg, hdr);
+	genlmsg_end(msg, hdr);
+	return 0;
 
  fail_unlock_rcu:
 	rcu_read_unlock();
@@ -6229,12 +6670,17 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb)
 }
 
 static int nl80211_send_survey(struct sk_buff *msg, u32 portid, u32 seq,
-				int flags, struct net_device *dev,
-				struct survey_info *survey)
+			       int flags, struct net_device *dev,
+			       bool allow_radio_stats,
+			       struct survey_info *survey)
 {
 	void *hdr;
 	struct nlattr *infoattr;
 
+	/* skip radio stats if userspace didn't request them */
+	if (!survey->channel && !allow_radio_stats)
+		return 0;
+
 	hdr = nl80211hdr_put(msg, portid, seq, flags,
 			     NL80211_CMD_NEW_SURVEY_RESULTS);
 	if (!hdr)
@@ -6247,7 +6693,8 @@ static int nl80211_send_survey(struct sk_buff *msg, u32 portid, u32 seq,
 	if (!infoattr)
 		goto nla_put_failure;
 
-	if (nla_put_u32(msg, NL80211_SURVEY_INFO_FREQUENCY,
+	if (survey->channel &&
+	    nla_put_u32(msg, NL80211_SURVEY_INFO_FREQUENCY,
 			survey->channel->center_freq))
 		goto nla_put_failure;
 
@@ -6257,49 +6704,57 @@ static int nl80211_send_survey(struct sk_buff *msg, u32 portid, u32 seq,
 	if ((survey->filled & SURVEY_INFO_IN_USE) &&
 	    nla_put_flag(msg, NL80211_SURVEY_INFO_IN_USE))
 		goto nla_put_failure;
-	if ((survey->filled & SURVEY_INFO_CHANNEL_TIME) &&
-	    nla_put_u64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME,
-			survey->channel_time))
+	if ((survey->filled & SURVEY_INFO_TIME) &&
+	    nla_put_u64(msg, NL80211_SURVEY_INFO_TIME,
+			survey->time))
 		goto nla_put_failure;
-	if ((survey->filled & SURVEY_INFO_CHANNEL_TIME_BUSY) &&
-	    nla_put_u64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME_BUSY,
-			survey->channel_time_busy))
+	if ((survey->filled & SURVEY_INFO_TIME_BUSY) &&
+	    nla_put_u64(msg, NL80211_SURVEY_INFO_TIME_BUSY,
+			survey->time_busy))
 		goto nla_put_failure;
-	if ((survey->filled & SURVEY_INFO_CHANNEL_TIME_EXT_BUSY) &&
-	    nla_put_u64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME_EXT_BUSY,
-			survey->channel_time_ext_busy))
+	if ((survey->filled & SURVEY_INFO_TIME_EXT_BUSY) &&
+	    nla_put_u64(msg, NL80211_SURVEY_INFO_TIME_EXT_BUSY,
+			survey->time_ext_busy))
 		goto nla_put_failure;
-	if ((survey->filled & SURVEY_INFO_CHANNEL_TIME_RX) &&
-	    nla_put_u64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME_RX,
-			survey->channel_time_rx))
+	if ((survey->filled & SURVEY_INFO_TIME_RX) &&
+	    nla_put_u64(msg, NL80211_SURVEY_INFO_TIME_RX,
+			survey->time_rx))
 		goto nla_put_failure;
-	if ((survey->filled & SURVEY_INFO_CHANNEL_TIME_TX) &&
-	    nla_put_u64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME_TX,
-			survey->channel_time_tx))
+	if ((survey->filled & SURVEY_INFO_TIME_TX) &&
+	    nla_put_u64(msg, NL80211_SURVEY_INFO_TIME_TX,
+			survey->time_tx))
+		goto nla_put_failure;
+	if ((survey->filled & SURVEY_INFO_TIME_SCAN) &&
+	    nla_put_u64(msg, NL80211_SURVEY_INFO_TIME_SCAN,
+			survey->time_scan))
 		goto nla_put_failure;
 
 	nla_nest_end(msg, infoattr);
 
-	return genlmsg_end(msg, hdr);
+	genlmsg_end(msg, hdr);
+	return 0;
 
  nla_put_failure:
 	genlmsg_cancel(msg, hdr);
 	return -EMSGSIZE;
 }
 
-static int nl80211_dump_survey(struct sk_buff *skb,
-			struct netlink_callback *cb)
+static int nl80211_dump_survey(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct survey_info survey;
 	struct cfg80211_registered_device *rdev;
 	struct wireless_dev *wdev;
 	int survey_idx = cb->args[2];
 	int res;
+	bool radio_stats;
 
 	res = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
 	if (res)
 		return res;
 
+	/* prepare_wdev_dump parsed the attributes */
+	radio_stats = nl80211_fam.attrbuf[NL80211_ATTR_SURVEY_RADIO_STATS];
+
 	if (!wdev->netdev) {
 		res = -EINVAL;
 		goto out_err;
@@ -6311,23 +6766,15 @@ static int nl80211_dump_survey(struct sk_buff *skb,
 	}
 
 	while (1) {
-		struct ieee80211_channel *chan;
-
 		res = rdev_dump_survey(rdev, wdev->netdev, survey_idx, &survey);
 		if (res == -ENOENT)
 			break;
 		if (res)
 			goto out_err;
 
-		/* Survey without a channel doesn't make sense */
-		if (!survey.channel) {
-			res = -EINVAL;
-			goto out;
-		}
-
-		chan = ieee80211_get_channel(&rdev->wiphy,
-					     survey.channel->center_freq);
-		if (!chan || chan->flags & IEEE80211_CHAN_DISABLED) {
+		/* don't send disabled channels, but do send non-channel data */
+		if (survey.channel &&
+		    survey.channel->flags & IEEE80211_CHAN_DISABLED) {
 			survey_idx++;
 			continue;
 		}
@@ -6335,7 +6782,7 @@ static int nl80211_dump_survey(struct sk_buff *skb,
 		if (nl80211_send_survey(skb,
 				NETLINK_CB(cb->skb).portid,
 				cb->nlh->nlmsg_seq, NLM_F_MULTI,
-				wdev->netdev, &survey) < 0)
+				wdev->netdev, radio_stats, &survey) < 0)
 			goto out;
 		survey_idx++;
 	}
@@ -6839,8 +7286,18 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info)
 		break;
 	case NL80211_CHAN_WIDTH_20:
 	case NL80211_CHAN_WIDTH_40:
-		if (rdev->wiphy.features & NL80211_FEATURE_HT_IBSS)
-			break;
+		if (!(rdev->wiphy.features & NL80211_FEATURE_HT_IBSS))
+			return -EINVAL;
+		break;
+	case NL80211_CHAN_WIDTH_80:
+	case NL80211_CHAN_WIDTH_80P80:
+	case NL80211_CHAN_WIDTH_160:
+		if (!(rdev->wiphy.features & NL80211_FEATURE_HT_IBSS))
+			return -EINVAL;
+		if (!wiphy_ext_feature_isset(&rdev->wiphy,
+					     NL80211_EXT_FEATURE_VHT_IBSS))
+			return -EINVAL;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -6953,8 +7410,8 @@ static int nl80211_set_mcast_rate(struct sk_buff *skb, struct genl_info *info)
 
 static struct sk_buff *
 __cfg80211_alloc_vendor_skb(struct cfg80211_registered_device *rdev,
-			    int approxlen, u32 portid, u32 seq,
-			    enum nl80211_commands cmd,
+			    struct wireless_dev *wdev, int approxlen,
+			    u32 portid, u32 seq, enum nl80211_commands cmd,
 			    enum nl80211_attrs attr,
 			    const struct nl80211_vendor_cmd_info *info,
 			    gfp_t gfp)
@@ -6985,6 +7442,16 @@ __cfg80211_alloc_vendor_skb(struct cfg80211_registered_device *rdev,
 			goto nla_put_failure;
 	}
 
+	if (wdev) {
+		if (nla_put_u64(skb, NL80211_ATTR_WDEV,
+				wdev_id(wdev)))
+			goto nla_put_failure;
+		if (wdev->netdev &&
+		    nla_put_u32(skb, NL80211_ATTR_IFINDEX,
+				wdev->netdev->ifindex))
+			goto nla_put_failure;
+	}
+
 	data = nla_nest_start(skb, attr);
 
 	((void **)skb->cb)[0] = rdev;
@@ -6999,6 +7466,7 @@ __cfg80211_alloc_vendor_skb(struct cfg80211_registered_device *rdev,
 }
 
 struct sk_buff *__cfg80211_alloc_event_skb(struct wiphy *wiphy,
+					   struct wireless_dev *wdev,
 					   enum nl80211_commands cmd,
 					   enum nl80211_attrs attr,
 					   int vendor_event_idx,
@@ -7024,7 +7492,7 @@ struct sk_buff *__cfg80211_alloc_event_skb(struct wiphy *wiphy,
 		return NULL;
 	}
 
-	return __cfg80211_alloc_vendor_skb(rdev, approxlen, 0, 0,
+	return __cfg80211_alloc_vendor_skb(rdev, wdev, approxlen, 0, 0,
 					   cmd, attr, info, gfp);
 }
 EXPORT_SYMBOL(__cfg80211_alloc_event_skb);
@@ -7348,14 +7816,19 @@ static int nl80211_wiphy_netns(struct sk_buff *skb, struct genl_info *info)
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
 	struct net *net;
 	int err;
-	u32 pid;
 
-	if (!info->attrs[NL80211_ATTR_PID])
-		return -EINVAL;
+	if (info->attrs[NL80211_ATTR_PID]) {
+		u32 pid = nla_get_u32(info->attrs[NL80211_ATTR_PID]);
 
-	pid = nla_get_u32(info->attrs[NL80211_ATTR_PID]);
+		net = get_net_ns_by_pid(pid);
+	} else if (info->attrs[NL80211_ATTR_NETNS_FD]) {
+		u32 fd = nla_get_u32(info->attrs[NL80211_ATTR_NETNS_FD]);
+
+		net = get_net_ns_by_fd(fd);
+	} else {
+		return -EINVAL;
+	}
 
-	net = get_net_ns_by_pid(pid);
 	if (IS_ERR(net))
 		return PTR_ERR(net);
 
@@ -8159,6 +8632,28 @@ static int nl80211_set_cqm(struct sk_buff *skb, struct genl_info *info)
 	return -EINVAL;
 }
 
+static int nl80211_join_ocb(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];
+	struct ocb_setup setup = {};
+	int err;
+
+	err = nl80211_parse_chandef(rdev, info, &setup.chandef);
+	if (err)
+		return err;
+
+	return cfg80211_join_ocb(rdev, dev, &setup);
+}
+
+static int nl80211_leave_ocb(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_leave_ocb(rdev, dev);
+}
+
 static int nl80211_join_mesh(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
@@ -8298,8 +8793,8 @@ static int nl80211_send_wowlan_tcp(struct sk_buff *msg,
 	if (!nl_tcp)
 		return -ENOBUFS;
 
-	if (nla_put_be32(msg, NL80211_WOWLAN_TCP_SRC_IPV4, tcp->src) ||
-	    nla_put_be32(msg, NL80211_WOWLAN_TCP_DST_IPV4, tcp->dst) ||
+	if (nla_put_in_addr(msg, NL80211_WOWLAN_TCP_SRC_IPV4, tcp->src) ||
+	    nla_put_in_addr(msg, NL80211_WOWLAN_TCP_DST_IPV4, tcp->dst) ||
 	    nla_put(msg, NL80211_WOWLAN_TCP_DST_MAC, ETH_ALEN, tcp->dst_mac) ||
 	    nla_put_u16(msg, NL80211_WOWLAN_TCP_SRC_PORT, tcp->src_port) ||
 	    nla_put_u16(msg, NL80211_WOWLAN_TCP_DST_PORT, tcp->dst_port) ||
@@ -8329,6 +8824,51 @@ static int nl80211_send_wowlan_tcp(struct sk_buff *msg,
 	return 0;
 }
 
+static int nl80211_send_wowlan_nd(struct sk_buff *msg,
+				  struct cfg80211_sched_scan_request *req)
+{
+	struct nlattr *nd, *freqs, *matches, *match;
+	int i;
+
+	if (!req)
+		return 0;
+
+	nd = nla_nest_start(msg, NL80211_WOWLAN_TRIG_NET_DETECT);
+	if (!nd)
+		return -ENOBUFS;
+
+	if (nla_put_u32(msg, NL80211_ATTR_SCHED_SCAN_INTERVAL, req->interval))
+		return -ENOBUFS;
+
+	if (nla_put_u32(msg, NL80211_ATTR_SCHED_SCAN_DELAY, req->delay))
+		return -ENOBUFS;
+
+	freqs = nla_nest_start(msg, NL80211_ATTR_SCAN_FREQUENCIES);
+	if (!freqs)
+		return -ENOBUFS;
+
+	for (i = 0; i < req->n_channels; i++)
+		nla_put_u32(msg, i, req->channels[i]->center_freq);
+
+	nla_nest_end(msg, freqs);
+
+	if (req->n_match_sets) {
+		matches = nla_nest_start(msg, NL80211_ATTR_SCHED_SCAN_MATCH);
+		for (i = 0; i < req->n_match_sets; i++) {
+			match = nla_nest_start(msg, i);
+			nla_put(msg, NL80211_SCHED_SCAN_MATCH_ATTR_SSID,
+				req->match_sets[i].ssid.ssid_len,
+				req->match_sets[i].ssid.ssid);
+			nla_nest_end(msg, match);
+		}
+		nla_nest_end(msg, matches);
+	}
+
+	nla_nest_end(msg, nd);
+
+	return 0;
+}
+
 static int nl80211_get_wowlan(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
@@ -8386,6 +8926,11 @@ static int nl80211_get_wowlan(struct sk_buff *skb, struct genl_info *info)
 					    rdev->wiphy.wowlan_config->tcp))
 			goto nla_put_failure;
 
+		if (nl80211_send_wowlan_nd(
+			    msg,
+			    rdev->wiphy.wowlan_config->nd_config))
+			goto nla_put_failure;
+
 		nla_nest_end(msg, nl_wowlan);
 	}
 
@@ -8483,8 +9028,8 @@ static int nl80211_parse_wowlan_tcp(struct cfg80211_registered_device *rdev,
 	cfg = kzalloc(size, GFP_KERNEL);
 	if (!cfg)
 		return -ENOMEM;
-	cfg->src = nla_get_be32(tb[NL80211_WOWLAN_TCP_SRC_IPV4]);
-	cfg->dst = nla_get_be32(tb[NL80211_WOWLAN_TCP_DST_IPV4]);
+	cfg->src = nla_get_in_addr(tb[NL80211_WOWLAN_TCP_SRC_IPV4]);
+	cfg->dst = nla_get_in_addr(tb[NL80211_WOWLAN_TCP_DST_IPV4]);
 	memcpy(cfg->dst_mac, nla_data(tb[NL80211_WOWLAN_TCP_DST_MAC]),
 	       ETH_ALEN);
 	if (tb[NL80211_WOWLAN_TCP_SRC_PORT])
@@ -8542,6 +9087,39 @@ static int nl80211_parse_wowlan_tcp(struct cfg80211_registered_device *rdev,
 	return 0;
 }
 
+static int nl80211_parse_wowlan_nd(struct cfg80211_registered_device *rdev,
+				   const struct wiphy_wowlan_support *wowlan,
+				   struct nlattr *attr,
+				   struct cfg80211_wowlan *trig)
+{
+	struct nlattr **tb;
+	int err;
+
+	tb = kzalloc(NUM_NL80211_ATTR * sizeof(*tb), GFP_KERNEL);
+	if (!tb)
+		return -ENOMEM;
+
+	if (!(wowlan->flags & WIPHY_WOWLAN_NET_DETECT)) {
+		err = -EOPNOTSUPP;
+		goto out;
+	}
+
+	err = nla_parse(tb, NL80211_ATTR_MAX,
+			nla_data(attr), nla_len(attr),
+			nl80211_policy);
+	if (err)
+		goto out;
+
+	trig->nd_config = nl80211_parse_sched_scan(&rdev->wiphy, NULL, tb);
+	err = PTR_ERR_OR_ZERO(trig->nd_config);
+	if (err)
+		trig->nd_config = NULL;
+
+out:
+	kfree(tb);
+	return err;
+}
+
 static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
@@ -8551,6 +9129,7 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info)
 	const struct wiphy_wowlan_support *wowlan = rdev->wiphy.wowlan;
 	int err, i;
 	bool prev_enabled = rdev->wiphy.wowlan_config;
+	bool regular = false;
 
 	if (!wowlan)
 		return -EOPNOTSUPP;
@@ -8578,12 +9157,14 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info)
 		if (!(wowlan->flags & WIPHY_WOWLAN_DISCONNECT))
 			return -EINVAL;
 		new_triggers.disconnect = true;
+		regular = true;
 	}
 
 	if (tb[NL80211_WOWLAN_TRIG_MAGIC_PKT]) {
 		if (!(wowlan->flags & WIPHY_WOWLAN_MAGIC_PKT))
 			return -EINVAL;
 		new_triggers.magic_pkt = true;
+		regular = true;
 	}
 
 	if (tb[NL80211_WOWLAN_TRIG_GTK_REKEY_SUPPORTED])
@@ -8593,24 +9174,28 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info)
 		if (!(wowlan->flags & WIPHY_WOWLAN_GTK_REKEY_FAILURE))
 			return -EINVAL;
 		new_triggers.gtk_rekey_failure = true;
+		regular = true;
 	}
 
 	if (tb[NL80211_WOWLAN_TRIG_EAP_IDENT_REQUEST]) {
 		if (!(wowlan->flags & WIPHY_WOWLAN_EAP_IDENTITY_REQ))
 			return -EINVAL;
 		new_triggers.eap_identity_req = true;
+		regular = true;
 	}
 
 	if (tb[NL80211_WOWLAN_TRIG_4WAY_HANDSHAKE]) {
 		if (!(wowlan->flags & WIPHY_WOWLAN_4WAY_HANDSHAKE))
 			return -EINVAL;
 		new_triggers.four_way_handshake = true;
+		regular = true;
 	}
 
 	if (tb[NL80211_WOWLAN_TRIG_RFKILL_RELEASE]) {
 		if (!(wowlan->flags & WIPHY_WOWLAN_RFKILL_RELEASE))
 			return -EINVAL;
 		new_triggers.rfkill_release = true;
+		regular = true;
 	}
 
 	if (tb[NL80211_WOWLAN_TRIG_PKT_PATTERN]) {
@@ -8619,6 +9204,8 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info)
 		int rem, pat_len, mask_len, pkt_offset;
 		struct nlattr *pat_tb[NUM_NL80211_PKTPAT];
 
+		regular = true;
+
 		nla_for_each_nested(pat, tb[NL80211_WOWLAN_TRIG_PKT_PATTERN],
 				    rem)
 			n_patterns++;
@@ -8680,6 +9267,7 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	if (tb[NL80211_WOWLAN_TRIG_TCP_CONNECTION]) {
+		regular = true;
 		err = nl80211_parse_wowlan_tcp(
 			rdev, tb[NL80211_WOWLAN_TRIG_TCP_CONNECTION],
 			&new_triggers);
@@ -8687,6 +9275,26 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info)
 			goto error;
 	}
 
+	if (tb[NL80211_WOWLAN_TRIG_NET_DETECT]) {
+		regular = true;
+		err = nl80211_parse_wowlan_nd(
+			rdev, wowlan, tb[NL80211_WOWLAN_TRIG_NET_DETECT],
+			&new_triggers);
+		if (err)
+			goto error;
+	}
+
+	/* The 'any' trigger means the device continues operating more or less
+	 * as in its normal operation mode and wakes up the host on most of the
+	 * normal interrupts (like packet RX, ...)
+	 * It therefore makes little sense to combine with the more constrained
+	 * wakeup trigger modes.
+	 */
+	if (new_triggers.any && regular) {
+		err = -EINVAL;
+		goto error;
+	}
+
 	ntrig = kmemdup(&new_triggers, sizeof(new_triggers), GFP_KERNEL);
 	if (!ntrig) {
 		err = -ENOMEM;
@@ -9355,7 +9963,7 @@ struct sk_buff *__cfg80211_alloc_reply_skb(struct wiphy *wiphy,
 	if (WARN_ON(!rdev->cur_cmd_info))
 		return NULL;
 
-	return __cfg80211_alloc_vendor_skb(rdev, approxlen,
+	return __cfg80211_alloc_vendor_skb(rdev, NULL, approxlen,
 					   rdev->cur_cmd_info->snd_portid,
 					   rdev->cur_cmd_info->snd_seq,
 					   cmd, attr, NULL, GFP_KERNEL);
@@ -9444,7 +10052,7 @@ static int nl80211_add_tx_ts(struct sk_buff *skb, struct genl_info *info)
 	u16 admitted_time = 0;
 	int err;
 
-	if (!(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_WMM_ADMISSION))
+	if (!(rdev->wiphy.features & NL80211_FEATURE_SUPPORTS_WMM_ADMISSION))
 		return -EOPNOTSUPP;
 
 	if (!info->attrs[NL80211_ATTR_TSID] || !info->attrs[NL80211_ATTR_MAC] ||
@@ -9460,12 +10068,10 @@ static int nl80211_add_tx_ts(struct sk_buff *skb, struct genl_info *info)
 		return -EINVAL;
 
 	/* WMM uses TIDs 0-7 even for TSPEC */
-	if (tsid < IEEE80211_FIRST_TSPEC_TSID) {
-		if (!(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_WMM_ADMISSION))
-			return -EINVAL;
-	} else {
+	if (tsid >= IEEE80211_FIRST_TSPEC_TSID) {
 		/* TODO: handle 802.11 TSPEC/admission control
-		 * need more attributes for that (e.g. BA session requirement)
+		 * need more attributes for that (e.g. BA session requirement);
+		 * change the WMM adminssion test above to allow both then
 		 */
 		return -EINVAL;
 	}
@@ -9521,6 +10127,98 @@ static int nl80211_del_tx_ts(struct sk_buff *skb, struct genl_info *info)
 	return err;
 }
 
+static int nl80211_tdls_channel_switch(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];
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	struct cfg80211_chan_def chandef = {};
+	const u8 *addr;
+	u8 oper_class;
+	int err;
+
+	if (!rdev->ops->tdls_channel_switch ||
+	    !(rdev->wiphy.features & NL80211_FEATURE_TDLS_CHANNEL_SWITCH))
+		return -EOPNOTSUPP;
+
+	switch (dev->ieee80211_ptr->iftype) {
+	case NL80211_IFTYPE_STATION:
+	case NL80211_IFTYPE_P2P_CLIENT:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	if (!info->attrs[NL80211_ATTR_MAC] ||
+	    !info->attrs[NL80211_ATTR_OPER_CLASS])
+		return -EINVAL;
+
+	err = nl80211_parse_chandef(rdev, info, &chandef);
+	if (err)
+		return err;
+
+	/*
+	 * Don't allow wide channels on the 2.4Ghz band, as per IEEE802.11-2012
+	 * section 10.22.6.2.1. Disallow 5/10Mhz channels as well for now, the
+	 * specification is not defined for them.
+	 */
+	if (chandef.chan->band == IEEE80211_BAND_2GHZ &&
+	    chandef.width != NL80211_CHAN_WIDTH_20_NOHT &&
+	    chandef.width != NL80211_CHAN_WIDTH_20)
+		return -EINVAL;
+
+	/* we will be active on the TDLS link */
+	if (!cfg80211_reg_can_beacon(&rdev->wiphy, &chandef, wdev->iftype))
+		return -EINVAL;
+
+	/* don't allow switching to DFS channels */
+	if (cfg80211_chandef_dfs_required(wdev->wiphy, &chandef, wdev->iftype))
+		return -EINVAL;
+
+	addr = nla_data(info->attrs[NL80211_ATTR_MAC]);
+	oper_class = nla_get_u8(info->attrs[NL80211_ATTR_OPER_CLASS]);
+
+	wdev_lock(wdev);
+	err = rdev_tdls_channel_switch(rdev, dev, addr, oper_class, &chandef);
+	wdev_unlock(wdev);
+
+	return err;
+}
+
+static int nl80211_tdls_cancel_channel_switch(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];
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	const u8 *addr;
+
+	if (!rdev->ops->tdls_channel_switch ||
+	    !rdev->ops->tdls_cancel_channel_switch ||
+	    !(rdev->wiphy.features & NL80211_FEATURE_TDLS_CHANNEL_SWITCH))
+		return -EOPNOTSUPP;
+
+	switch (dev->ieee80211_ptr->iftype) {
+	case NL80211_IFTYPE_STATION:
+	case NL80211_IFTYPE_P2P_CLIENT:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	if (!info->attrs[NL80211_ATTR_MAC])
+		return -EINVAL;
+
+	addr = nla_data(info->attrs[NL80211_ATTR_MAC]);
+
+	wdev_lock(wdev);
+	rdev_tdls_cancel_channel_switch(rdev, dev, addr);
+	wdev_unlock(wdev);
+
+	return 0;
+}
+
 #define NL80211_FLAG_NEED_WIPHY		0x01
 #define NL80211_FLAG_NEED_NETDEV	0x02
 #define NL80211_FLAG_NEED_RTNL		0x04
@@ -9782,6 +10480,15 @@ static const struct genl_ops nl80211_ops[] = {
 				  NL80211_FLAG_NEED_RTNL,
 	},
 	{
+		.cmd = NL80211_CMD_GET_MPP,
+		.doit = nl80211_get_mpp,
+		.dumpit = nl80211_dump_mpp,
+		.policy = nl80211_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
+				  NL80211_FLAG_NEED_RTNL,
+	},
+	{
 		.cmd = NL80211_CMD_SET_MPATH,
 		.doit = nl80211_set_mpath,
 		.policy = nl80211_policy,
@@ -9815,7 +10522,8 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_GET_REG,
-		.doit = nl80211_get_reg,
+		.doit = nl80211_get_reg_do,
+		.dumpit = nl80211_get_reg_dump,
 		.policy = nl80211_policy,
 		.internal_flags = NL80211_FLAG_NEED_RTNL,
 		/* can be retrieved by unprivileged users */
@@ -10095,6 +10803,22 @@ static const struct genl_ops nl80211_ops[] = {
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL80211_CMD_JOIN_OCB,
+		.doit = nl80211_join_ocb,
+		.policy = nl80211_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
+				  NL80211_FLAG_NEED_RTNL,
+	},
+	{
+		.cmd = NL80211_CMD_LEAVE_OCB,
+		.doit = nl80211_leave_ocb,
+		.policy = nl80211_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
+				  NL80211_FLAG_NEED_RTNL,
+	},
 #ifdef CONFIG_PM
 	{
 		.cmd = NL80211_CMD_GET_WOWLAN,
@@ -10294,6 +11018,22 @@ static const struct genl_ops nl80211_ops[] = {
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL80211_CMD_TDLS_CHANNEL_SWITCH,
+		.doit = nl80211_tdls_channel_switch,
+		.policy = nl80211_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
+				  NL80211_FLAG_NEED_RTNL,
+	},
+	{
+		.cmd = NL80211_CMD_TDLS_CANCEL_CHANNEL_SWITCH,
+		.doit = nl80211_tdls_cancel_channel_switch,
+		.policy = nl80211_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
+				  NL80211_FLAG_NEED_RTNL,
+	},
 };
 
 /* notification functions */
@@ -10382,7 +11122,8 @@ static int nl80211_send_scan_msg(struct sk_buff *msg,
 	/* ignore errors and send incomplete event anyway */
 	nl80211_add_scan_req(msg, rdev);
 
-	return genlmsg_end(msg, hdr);
+	genlmsg_end(msg, hdr);
+	return 0;
 
  nla_put_failure:
 	genlmsg_cancel(msg, hdr);
@@ -10405,7 +11146,8 @@ nl80211_send_sched_scan_msg(struct sk_buff *msg,
 	    nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex))
 		goto nla_put_failure;
 
-	return genlmsg_end(msg, hdr);
+	genlmsg_end(msg, hdr);
+	return 0;
 
  nla_put_failure:
 	genlmsg_cancel(msg, hdr);
@@ -10497,25 +11239,9 @@ void nl80211_send_sched_scan(struct cfg80211_registered_device *rdev,
 				NL80211_MCGRP_SCAN, GFP_KERNEL);
 }
 
-/*
- * This can happen on global regulatory changes or device specific settings
- * based on custom world regulatory domains.
- */
-void nl80211_send_reg_change_event(struct regulatory_request *request)
+static bool nl80211_reg_change_event_fill(struct sk_buff *msg,
+					  struct regulatory_request *request)
 {
-	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_REG_CHANGE);
-	if (!hdr) {
-		nlmsg_free(msg);
-		return;
-	}
-
 	/* Userspace can always count this one always being set */
 	if (nla_put_u8(msg, NL80211_ATTR_REG_INITIATOR, request->initiator))
 		goto nla_put_failure;
@@ -10541,8 +11267,46 @@ void nl80211_send_reg_change_event(struct regulatory_request *request)
 			goto nla_put_failure;
 	}
 
-	if (request->wiphy_idx != WIPHY_IDX_INVALID &&
-	    nla_put_u32(msg, NL80211_ATTR_WIPHY, request->wiphy_idx))
+	if (request->wiphy_idx != WIPHY_IDX_INVALID) {
+		struct wiphy *wiphy = wiphy_idx_to_wiphy(request->wiphy_idx);
+
+		if (wiphy &&
+		    nla_put_u32(msg, NL80211_ATTR_WIPHY, request->wiphy_idx))
+			goto nla_put_failure;
+
+		if (wiphy &&
+		    wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED &&
+		    nla_put_flag(msg, NL80211_ATTR_WIPHY_SELF_MANAGED_REG))
+			goto nla_put_failure;
+	}
+
+	return true;
+
+nla_put_failure:
+	return false;
+}
+
+/*
+ * This can happen on global regulatory changes or device specific settings
+ * based on custom regulatory domains.
+ */
+void nl80211_common_reg_change_event(enum nl80211_commands cmd_id,
+				     struct regulatory_request *request)
+{
+	struct sk_buff *msg;
+	void *hdr;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return;
+
+	hdr = nl80211hdr_put(msg, 0, 0, 0, cmd_id);
+	if (!hdr) {
+		nlmsg_free(msg);
+		return;
+	}
+
+	if (nl80211_reg_change_event_fill(msg, request) == false)
 		goto nla_put_failure;
 
 	genlmsg_end(msg, hdr);
@@ -11081,7 +11845,7 @@ void cfg80211_new_sta(struct net_device *dev, const u8 *mac_addr,
 	if (!msg)
 		return;
 
-	if (nl80211_send_station(msg, 0, 0, 0,
+	if (nl80211_send_station(msg, NL80211_CMD_NEW_STATION, 0, 0, 0,
 				 rdev, dev, mac_addr, sinfo) < 0) {
 		nlmsg_free(msg);
 		return;
@@ -11092,12 +11856,16 @@ void cfg80211_new_sta(struct net_device *dev, const u8 *mac_addr,
 }
 EXPORT_SYMBOL(cfg80211_new_sta);
 
-void cfg80211_del_sta(struct net_device *dev, const u8 *mac_addr, gfp_t gfp)
+void cfg80211_del_sta_sinfo(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_rdev(wiphy);
 	struct sk_buff *msg;
-	void *hdr;
+	struct station_info empty_sinfo = {};
+
+	if (!sinfo)
+		sinfo = &empty_sinfo;
 
 	trace_cfg80211_del_sta(dev, mac_addr);
 
@@ -11105,27 +11873,16 @@ void cfg80211_del_sta(struct net_device *dev, const u8 *mac_addr, gfp_t gfp)
 	if (!msg)
 		return;
 
-	hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_DEL_STATION);
-	if (!hdr) {
+	if (nl80211_send_station(msg, NL80211_CMD_DEL_STATION, 0, 0, 0,
+				 rdev, dev, mac_addr, sinfo) < 0) {
 		nlmsg_free(msg);
 		return;
 	}
 
-	if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) ||
-	    nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, mac_addr))
-		goto nla_put_failure;
-
-	genlmsg_end(msg, hdr);
-
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				NL80211_MCGRP_MLME, gfp);
-	return;
-
- nla_put_failure:
-	genlmsg_cancel(msg, hdr);
-	nlmsg_free(msg);
 }
-EXPORT_SYMBOL(cfg80211_del_sta);
+EXPORT_SYMBOL(cfg80211_del_sta_sinfo);
 
 void cfg80211_conn_failed(struct net_device *dev, const u8 *mac_addr,
 			  enum nl80211_connect_failed_reason reason,
@@ -11325,55 +12082,155 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie,
 }
 EXPORT_SYMBOL(cfg80211_mgmt_tx_status);
 
-void cfg80211_cqm_rssi_notify(struct net_device *dev,
-			      enum nl80211_cqm_rssi_threshold_event rssi_event,
-			      gfp_t gfp)
+static struct sk_buff *cfg80211_prepare_cqm(struct net_device *dev,
+					    const char *mac, gfp_t gfp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
-	struct sk_buff *msg;
-	struct nlattr *pinfoattr;
-	void *hdr;
-
-	trace_cfg80211_cqm_rssi_notify(dev, rssi_event);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
+	struct sk_buff *msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp);
+	void **cb;
 
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp);
 	if (!msg)
-		return;
+		return NULL;
 
-	hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_NOTIFY_CQM);
-	if (!hdr) {
+	cb = (void **)msg->cb;
+
+	cb[0] = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_NOTIFY_CQM);
+	if (!cb[0]) {
 		nlmsg_free(msg);
-		return;
+		return NULL;
 	}
 
 	if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) ||
 	    nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex))
 		goto nla_put_failure;
 
-	pinfoattr = nla_nest_start(msg, NL80211_ATTR_CQM);
-	if (!pinfoattr)
+	if (mac && nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, mac))
 		goto nla_put_failure;
 
-	if (nla_put_u32(msg, NL80211_ATTR_CQM_RSSI_THRESHOLD_EVENT,
-			rssi_event))
+	cb[1] = nla_nest_start(msg, NL80211_ATTR_CQM);
+	if (!cb[1])
 		goto nla_put_failure;
 
-	nla_nest_end(msg, pinfoattr);
+	cb[2] = rdev;
 
-	genlmsg_end(msg, hdr);
+	return msg;
+ nla_put_failure:
+	nlmsg_free(msg);
+	return NULL;
+}
+
+static void cfg80211_send_cqm(struct sk_buff *msg, gfp_t gfp)
+{
+	void **cb = (void **)msg->cb;
+	struct cfg80211_registered_device *rdev = cb[2];
+
+	nla_nest_end(msg, cb[1]);
+	genlmsg_end(msg, cb[0]);
+
+	memset(msg->cb, 0, sizeof(msg->cb));
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				NL80211_MCGRP_MLME, gfp);
+}
+
+void cfg80211_cqm_rssi_notify(struct net_device *dev,
+			      enum nl80211_cqm_rssi_threshold_event rssi_event,
+			      gfp_t gfp)
+{
+	struct sk_buff *msg;
+
+	trace_cfg80211_cqm_rssi_notify(dev, rssi_event);
+
+	if (WARN_ON(rssi_event != NL80211_CQM_RSSI_THRESHOLD_EVENT_LOW &&
+		    rssi_event != NL80211_CQM_RSSI_THRESHOLD_EVENT_HIGH))
+		return;
+
+	msg = cfg80211_prepare_cqm(dev, NULL, gfp);
+	if (!msg)
+		return;
+
+	if (nla_put_u32(msg, NL80211_ATTR_CQM_RSSI_THRESHOLD_EVENT,
+			rssi_event))
+		goto nla_put_failure;
+
+	cfg80211_send_cqm(msg, gfp);
+
 	return;
 
  nla_put_failure:
-	genlmsg_cancel(msg, hdr);
 	nlmsg_free(msg);
 }
 EXPORT_SYMBOL(cfg80211_cqm_rssi_notify);
 
+void cfg80211_cqm_txe_notify(struct net_device *dev,
+			     const u8 *peer, u32 num_packets,
+			     u32 rate, u32 intvl, gfp_t gfp)
+{
+	struct sk_buff *msg;
+
+	msg = cfg80211_prepare_cqm(dev, peer, gfp);
+	if (!msg)
+		return;
+
+	if (nla_put_u32(msg, NL80211_ATTR_CQM_TXE_PKTS, num_packets))
+		goto nla_put_failure;
+
+	if (nla_put_u32(msg, NL80211_ATTR_CQM_TXE_RATE, rate))
+		goto nla_put_failure;
+
+	if (nla_put_u32(msg, NL80211_ATTR_CQM_TXE_INTVL, intvl))
+		goto nla_put_failure;
+
+	cfg80211_send_cqm(msg, gfp);
+	return;
+
+ nla_put_failure:
+	nlmsg_free(msg);
+}
+EXPORT_SYMBOL(cfg80211_cqm_txe_notify);
+
+void cfg80211_cqm_pktloss_notify(struct net_device *dev,
+				 const u8 *peer, u32 num_packets, gfp_t gfp)
+{
+	struct sk_buff *msg;
+
+	trace_cfg80211_cqm_pktloss_notify(dev, peer, num_packets);
+
+	msg = cfg80211_prepare_cqm(dev, peer, gfp);
+	if (!msg)
+		return;
+
+	if (nla_put_u32(msg, NL80211_ATTR_CQM_PKT_LOSS_EVENT, num_packets))
+		goto nla_put_failure;
+
+	cfg80211_send_cqm(msg, gfp);
+	return;
+
+ nla_put_failure:
+	nlmsg_free(msg);
+}
+EXPORT_SYMBOL(cfg80211_cqm_pktloss_notify);
+
+void cfg80211_cqm_beacon_loss_notify(struct net_device *dev, gfp_t gfp)
+{
+	struct sk_buff *msg;
+
+	msg = cfg80211_prepare_cqm(dev, NULL, gfp);
+	if (!msg)
+		return;
+
+	if (nla_put_flag(msg, NL80211_ATTR_CQM_BEACON_LOSS_EVENT))
+		goto nla_put_failure;
+
+	cfg80211_send_cqm(msg, gfp);
+	return;
+
+ nla_put_failure:
+	nlmsg_free(msg);
+}
+EXPORT_SYMBOL(cfg80211_cqm_beacon_loss_notify);
+
 static void nl80211_gtk_rekey_notify(struct cfg80211_registered_device *rdev,
 				     struct net_device *netdev, const u8 *bssid,
 				     const u8 *replay_ctr, gfp_t gfp)
@@ -11491,7 +12348,9 @@ EXPORT_SYMBOL(cfg80211_pmksa_candidate_notify);
 static void nl80211_ch_switch_notify(struct cfg80211_registered_device *rdev,
 				     struct net_device *netdev,
 				     struct cfg80211_chan_def *chandef,
-				     gfp_t gfp)
+				     gfp_t gfp,
+				     enum nl80211_commands notif,
+				     u8 count)
 {
 	struct sk_buff *msg;
 	void *hdr;
@@ -11500,7 +12359,7 @@ static void nl80211_ch_switch_notify(struct cfg80211_registered_device *rdev,
 	if (!msg)
 		return;
 
-	hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_CH_SWITCH_NOTIFY);
+	hdr = nl80211hdr_put(msg, 0, 0, 0, notif);
 	if (!hdr) {
 		nlmsg_free(msg);
 		return;
@@ -11512,6 +12371,10 @@ static void nl80211_ch_switch_notify(struct cfg80211_registered_device *rdev,
 	if (nl80211_send_chandef(msg, chandef))
 		goto nla_put_failure;
 
+	if ((notif == NL80211_CMD_CH_SWITCH_STARTED_NOTIFY) &&
+	    (nla_put_u32(msg, NL80211_ATTR_CH_SWITCH_COUNT, count)))
+			goto nla_put_failure;
+
 	genlmsg_end(msg, hdr);
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
@@ -11534,70 +12397,27 @@ void cfg80211_ch_switch_notify(struct net_device *dev,
 
 	trace_cfg80211_ch_switch_notify(dev, chandef);
 
-	if (WARN_ON(wdev->iftype != NL80211_IFTYPE_AP &&
-		    wdev->iftype != NL80211_IFTYPE_P2P_GO &&
-		    wdev->iftype != NL80211_IFTYPE_ADHOC &&
-		    wdev->iftype != NL80211_IFTYPE_MESH_POINT))
-		return;
-
 	wdev->chandef = *chandef;
 	wdev->preset_chandef = *chandef;
-	nl80211_ch_switch_notify(rdev, dev, chandef, GFP_KERNEL);
+	nl80211_ch_switch_notify(rdev, dev, chandef, GFP_KERNEL,
+				 NL80211_CMD_CH_SWITCH_NOTIFY, 0);
 }
 EXPORT_SYMBOL(cfg80211_ch_switch_notify);
 
-void cfg80211_cqm_txe_notify(struct net_device *dev,
-			     const u8 *peer, u32 num_packets,
-			     u32 rate, u32 intvl, gfp_t gfp)
+void cfg80211_ch_switch_started_notify(struct net_device *dev,
+				       struct cfg80211_chan_def *chandef,
+				       u8 count)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct wiphy *wiphy = wdev->wiphy;
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
-	struct sk_buff *msg;
-	struct nlattr *pinfoattr;
-	void *hdr;
-
-	msg = nlmsg_new(NLMSG_GOODSIZE, gfp);
-	if (!msg)
-		return;
-
-	hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_NOTIFY_CQM);
-	if (!hdr) {
-		nlmsg_free(msg);
-		return;
-	}
-
-	if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) ||
-	    nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) ||
-	    nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, peer))
-		goto nla_put_failure;
-
-	pinfoattr = nla_nest_start(msg, NL80211_ATTR_CQM);
-	if (!pinfoattr)
-		goto nla_put_failure;
 
-	if (nla_put_u32(msg, NL80211_ATTR_CQM_TXE_PKTS, num_packets))
-		goto nla_put_failure;
+	trace_cfg80211_ch_switch_started_notify(dev, chandef);
 
-	if (nla_put_u32(msg, NL80211_ATTR_CQM_TXE_RATE, rate))
-		goto nla_put_failure;
-
-	if (nla_put_u32(msg, NL80211_ATTR_CQM_TXE_INTVL, intvl))
-		goto nla_put_failure;
-
-	nla_nest_end(msg, pinfoattr);
-
-	genlmsg_end(msg, hdr);
-
-	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				NL80211_MCGRP_MLME, gfp);
-	return;
-
- nla_put_failure:
-	genlmsg_cancel(msg, hdr);
-	nlmsg_free(msg);
+	nl80211_ch_switch_notify(rdev, dev, chandef, GFP_KERNEL,
+				 NL80211_CMD_CH_SWITCH_STARTED_NOTIFY, count);
 }
-EXPORT_SYMBOL(cfg80211_cqm_txe_notify);
+EXPORT_SYMBOL(cfg80211_ch_switch_started_notify);
 
 void
 nl80211_radar_notify(struct cfg80211_registered_device *rdev,
@@ -11647,54 +12467,6 @@ nl80211_radar_notify(struct cfg80211_registered_device *rdev,
 	nlmsg_free(msg);
 }
 
-void cfg80211_cqm_pktloss_notify(struct net_device *dev,
-				 const u8 *peer, u32 num_packets, gfp_t gfp)
-{
-	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
-	struct sk_buff *msg;
-	struct nlattr *pinfoattr;
-	void *hdr;
-
-	trace_cfg80211_cqm_pktloss_notify(dev, peer, num_packets);
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp);
-	if (!msg)
-		return;
-
-	hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_NOTIFY_CQM);
-	if (!hdr) {
-		nlmsg_free(msg);
-		return;
-	}
-
-	if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) ||
-	    nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) ||
-	    nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, peer))
-		goto nla_put_failure;
-
-	pinfoattr = nla_nest_start(msg, NL80211_ATTR_CQM);
-	if (!pinfoattr)
-		goto nla_put_failure;
-
-	if (nla_put_u32(msg, NL80211_ATTR_CQM_PKT_LOSS_EVENT, num_packets))
-		goto nla_put_failure;
-
-	nla_nest_end(msg, pinfoattr);
-
-	genlmsg_end(msg, hdr);
-
-	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				NL80211_MCGRP_MLME, gfp);
-	return;
-
- nla_put_failure:
-	genlmsg_cancel(msg, hdr);
-	nlmsg_free(msg);
-}
-EXPORT_SYMBOL(cfg80211_cqm_pktloss_notify);
-
 void cfg80211_probe_status(struct net_device *dev, const u8 *addr,
 			   u64 cookie, bool acked, gfp_t gfp)
 {
@@ -11782,6 +12554,65 @@ void cfg80211_report_obss_beacon(struct wiphy *wiphy,
 EXPORT_SYMBOL(cfg80211_report_obss_beacon);
 
 #ifdef CONFIG_PM
+static int cfg80211_net_detect_results(struct sk_buff *msg,
+				       struct cfg80211_wowlan_wakeup *wakeup)
+{
+	struct cfg80211_wowlan_nd_info *nd = wakeup->net_detect;
+	struct nlattr *nl_results, *nl_match, *nl_freqs;
+	int i, j;
+
+	nl_results = nla_nest_start(
+		msg, NL80211_WOWLAN_TRIG_NET_DETECT_RESULTS);
+	if (!nl_results)
+		return -EMSGSIZE;
+
+	for (i = 0; i < nd->n_matches; i++) {
+		struct cfg80211_wowlan_nd_match *match = nd->matches[i];
+
+		nl_match = nla_nest_start(msg, i);
+		if (!nl_match)
+			break;
+
+		/* The SSID attribute is optional in nl80211, but for
+		 * simplicity reasons it's always present in the
+		 * cfg80211 structure.  If a driver can't pass the
+		 * SSID, that needs to be changed.  A zero length SSID
+		 * is still a valid SSID (wildcard), so it cannot be
+		 * used for this purpose.
+		 */
+		if (nla_put(msg, NL80211_ATTR_SSID, match->ssid.ssid_len,
+			    match->ssid.ssid)) {
+			nla_nest_cancel(msg, nl_match);
+			goto out;
+		}
+
+		if (match->n_channels) {
+			nl_freqs = nla_nest_start(
+				msg, NL80211_ATTR_SCAN_FREQUENCIES);
+			if (!nl_freqs) {
+				nla_nest_cancel(msg, nl_match);
+				goto out;
+			}
+
+			for (j = 0; j < match->n_channels; j++) {
+				if (nla_put_u32(msg, j, match->channels[j])) {
+					nla_nest_cancel(msg, nl_freqs);
+					nla_nest_cancel(msg, nl_match);
+					goto out;
+				}
+			}
+
+			nla_nest_end(msg, nl_freqs);
+		}
+
+		nla_nest_end(msg, nl_match);
+	}
+
+out:
+	nla_nest_end(msg, nl_results);
+	return 0;
+}
+
 void cfg80211_report_wowlan_wakeup(struct wireless_dev *wdev,
 				   struct cfg80211_wowlan_wakeup *wakeup,
 				   gfp_t gfp)
@@ -11876,6 +12707,10 @@ void cfg80211_report_wowlan_wakeup(struct wireless_dev *wdev,
 				goto free_msg;
 		}
 
+		if (wakeup->net_detect &&
+		    cfg80211_net_detect_results(msg, wakeup))
+				goto free_msg;
+
 		nla_nest_end(msg, reasons);
 	}
 
@@ -11949,6 +12784,13 @@ static int nl80211_netlink_notify(struct notifier_block * nb,
 
 	list_for_each_entry_rcu(rdev, &cfg80211_rdev_list, list) {
 		bool schedule_destroy_work = false;
+		bool schedule_scan_stop = false;
+		struct cfg80211_sched_scan_request *sched_scan_req =
+			rcu_dereference(rdev->sched_scan_req);
+
+		if (sched_scan_req && notify->portid &&
+		    sched_scan_req->owner_nlportid == notify->portid)
+			schedule_scan_stop = true;
 
 		list_for_each_entry_rcu(wdev, &rdev->wdev_list, list) {
 			cfg80211_mlme_unregister_socket(wdev, notify->portid);
@@ -11979,11 +12821,22 @@ static int nl80211_netlink_notify(struct notifier_block * nb,
 				spin_unlock(&rdev->destroy_list_lock);
 				schedule_work(&rdev->destroy_work);
 			}
+		} else if (schedule_scan_stop) {
+			sched_scan_req->owner_nlportid = 0;
+
+			if (rdev->ops->sched_scan_stop &&
+			    rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_SCHED_SCAN)
+				schedule_work(&rdev->sched_scan_stop_wk);
 		}
 	}
 
 	rcu_read_unlock();
 
+	/*
+	 * It is possible that the user space process that is controlling the
+	 * indoor setting disappeared, so notify the regulatory core.
+	 */
+	regulatory_netlink_notify(notify->portid);
 	return NOTIFY_OK;
 }
 
diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h
index 7ad70d6f0cc6..84d4edf1d545 100644
--- a/net/wireless/nl80211.h
+++ b/net/wireless/nl80211.h
@@ -17,7 +17,21 @@ 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,
 				     struct net_device *netdev);
-void nl80211_send_reg_change_event(struct regulatory_request *request);
+void nl80211_common_reg_change_event(enum nl80211_commands cmd_id,
+				     struct regulatory_request *request);
+
+static inline void
+nl80211_send_reg_change_event(struct regulatory_request *request)
+{
+	nl80211_common_reg_change_event(NL80211_CMD_REG_CHANGE, request);
+}
+
+static inline void
+nl80211_send_wiphy_reg_change_event(struct regulatory_request *request)
+{
+	nl80211_common_reg_change_event(NL80211_CMD_WIPHY_REG_CHANGE, request);
+}
+
 void nl80211_send_rx_auth(struct cfg80211_registered_device *rdev,
 			  struct net_device *netdev,
 			  const u8 *buf, size_t len, gfp_t gfp);
diff --git a/net/wireless/ocb.c b/net/wireless/ocb.c
new file mode 100644
index 000000000000..c00d4a792319
--- /dev/null
+++ b/net/wireless/ocb.c
@@ -0,0 +1,88 @@
+/*
+ * OCB mode implementation
+ *
+ * Copyright: (c) 2014 Czech Technical University in Prague
+ *            (c) 2014 Volkswagen Group Research
+ * Author:    Rostislav Lisovy <rostislav.lisovy@fel.cvut.cz>
+ * Funded by: Volkswagen Group Research
+ *
+ * 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/ieee80211.h>
+#include <net/cfg80211.h>
+#include "nl80211.h"
+#include "core.h"
+#include "rdev-ops.h"
+
+int __cfg80211_join_ocb(struct cfg80211_registered_device *rdev,
+			struct net_device *dev,
+			struct ocb_setup *setup)
+{
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	int err;
+
+	ASSERT_WDEV_LOCK(wdev);
+
+	if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_OCB)
+		return -EOPNOTSUPP;
+
+	if (WARN_ON(!setup->chandef.chan))
+		return -EINVAL;
+
+	err = rdev_join_ocb(rdev, dev, setup);
+	if (!err)
+		wdev->chandef = setup->chandef;
+
+	return err;
+}
+
+int cfg80211_join_ocb(struct cfg80211_registered_device *rdev,
+		      struct net_device *dev,
+		      struct ocb_setup *setup)
+{
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	int err;
+
+	wdev_lock(wdev);
+	err = __cfg80211_join_ocb(rdev, dev, setup);
+	wdev_unlock(wdev);
+
+	return err;
+}
+
+int __cfg80211_leave_ocb(struct cfg80211_registered_device *rdev,
+			 struct net_device *dev)
+{
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	int err;
+
+	ASSERT_WDEV_LOCK(wdev);
+
+	if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_OCB)
+		return -EOPNOTSUPP;
+
+	if (!rdev->ops->leave_ocb)
+		return -EOPNOTSUPP;
+
+	err = rdev_leave_ocb(rdev, dev);
+	if (!err)
+		memset(&wdev->chandef, 0, sizeof(wdev->chandef));
+
+	return err;
+}
+
+int cfg80211_leave_ocb(struct cfg80211_registered_device *rdev,
+		       struct net_device *dev)
+{
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	int err;
+
+	wdev_lock(wdev);
+	err = __cfg80211_leave_ocb(rdev, dev);
+	wdev_unlock(wdev);
+
+	return err;
+}
diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h
index f6d457d6a558..c6e83a7468c0 100644
--- a/net/wireless/rdev-ops.h
+++ b/net/wireless/rdev-ops.h
@@ -35,13 +35,14 @@ static inline void rdev_set_wakeup(struct cfg80211_registered_device *rdev,
 
 static inline struct wireless_dev
 *rdev_add_virtual_intf(struct cfg80211_registered_device *rdev, char *name,
+		       unsigned char name_assign_type,
 		       enum nl80211_iftype type, u32 *flags,
 		       struct vif_params *params)
 {
 	struct wireless_dev *ret;
 	trace_rdev_add_virtual_intf(&rdev->wiphy, name, type);
-	ret = rdev->ops->add_virtual_intf(&rdev->wiphy, name, type, flags,
-					  params);
+	ret = rdev->ops->add_virtual_intf(&rdev->wiphy, name, name_assign_type,
+					  type, flags, params);
 	trace_rdev_return_wdev(&rdev->wiphy, ret);
 	return ret;
 }
@@ -178,11 +179,12 @@ static inline int rdev_add_station(struct cfg80211_registered_device *rdev,
 }
 
 static inline int rdev_del_station(struct cfg80211_registered_device *rdev,
-				   struct net_device *dev, u8 *mac)
+				   struct net_device *dev,
+				   struct station_del_parameters *params)
 {
 	int ret;
-	trace_rdev_del_station(&rdev->wiphy, dev, mac);
-	ret = rdev->ops->del_station(&rdev->wiphy, dev, mac);
+	trace_rdev_del_station(&rdev->wiphy, dev, params);
+	ret = rdev->ops->del_station(&rdev->wiphy, dev, params);
 	trace_rdev_return_int(&rdev->wiphy, ret);
 	return ret;
 }
@@ -263,6 +265,18 @@ static inline int rdev_get_mpath(struct cfg80211_registered_device *rdev,
 
 }
 
+static inline int rdev_get_mpp(struct cfg80211_registered_device *rdev,
+			       struct net_device *dev, u8 *dst, u8 *mpp,
+			       struct mpath_info *pinfo)
+{
+	int ret;
+
+	trace_rdev_get_mpp(&rdev->wiphy, dev, dst, mpp);
+	ret = rdev->ops->get_mpp(&rdev->wiphy, dev, dst, mpp, pinfo);
+	trace_rdev_return_int_mpath_info(&rdev->wiphy, ret, pinfo);
+	return ret;
+}
+
 static inline int rdev_dump_mpath(struct cfg80211_registered_device *rdev,
 				  struct net_device *dev, int idx, u8 *dst,
 				  u8 *next_hop, struct mpath_info *pinfo)
@@ -271,7 +285,20 @@ static inline int rdev_dump_mpath(struct cfg80211_registered_device *rdev,
 	int ret;
 	trace_rdev_dump_mpath(&rdev->wiphy, dev, idx, dst, next_hop);
 	ret = rdev->ops->dump_mpath(&rdev->wiphy, dev, idx, dst, next_hop,
-				     pinfo);
+				    pinfo);
+	trace_rdev_return_int_mpath_info(&rdev->wiphy, ret, pinfo);
+	return ret;
+}
+
+static inline int rdev_dump_mpp(struct cfg80211_registered_device *rdev,
+				struct net_device *dev, int idx, u8 *dst,
+				u8 *mpp, struct mpath_info *pinfo)
+
+{
+	int ret;
+
+	trace_rdev_dump_mpp(&rdev->wiphy, dev, idx, dst, mpp);
+	ret = rdev->ops->dump_mpp(&rdev->wiphy, dev, idx, dst, mpp, pinfo);
 	trace_rdev_return_int_mpath_info(&rdev->wiphy, ret, pinfo);
 	return ret;
 }
@@ -322,6 +349,27 @@ static inline int rdev_leave_mesh(struct cfg80211_registered_device *rdev,
 	return ret;
 }
 
+static inline int rdev_join_ocb(struct cfg80211_registered_device *rdev,
+				struct net_device *dev,
+				struct ocb_setup *setup)
+{
+	int ret;
+	trace_rdev_join_ocb(&rdev->wiphy, dev, setup);
+	ret = rdev->ops->join_ocb(&rdev->wiphy, dev, setup);
+	trace_rdev_return_int(&rdev->wiphy, ret);
+	return ret;
+}
+
+static inline int rdev_leave_ocb(struct cfg80211_registered_device *rdev,
+				 struct net_device *dev)
+{
+	int ret;
+	trace_rdev_leave_ocb(&rdev->wiphy, dev);
+	ret = rdev->ops->leave_ocb(&rdev->wiphy, dev);
+	trace_rdev_return_int(&rdev->wiphy, ret);
+	return ret;
+}
+
 static inline int rdev_change_bss(struct cfg80211_registered_device *rdev,
 				  struct net_device *dev,
 				  struct bss_parameters *params)
@@ -946,4 +994,28 @@ rdev_del_tx_ts(struct cfg80211_registered_device *rdev,
 	return ret;
 }
 
+static inline int
+rdev_tdls_channel_switch(struct cfg80211_registered_device *rdev,
+			 struct net_device *dev, const u8 *addr,
+			 u8 oper_class, struct cfg80211_chan_def *chandef)
+{
+	int ret;
+
+	trace_rdev_tdls_channel_switch(&rdev->wiphy, dev, addr, oper_class,
+				       chandef);
+	ret = rdev->ops->tdls_channel_switch(&rdev->wiphy, dev, addr,
+					     oper_class, chandef);
+	trace_rdev_return_int(&rdev->wiphy, ret);
+	return ret;
+}
+
+static inline void
+rdev_tdls_cancel_channel_switch(struct cfg80211_registered_device *rdev,
+				struct net_device *dev, const u8 *addr)
+{
+	trace_rdev_tdls_cancel_channel_switch(&rdev->wiphy, dev, addr);
+	rdev->ops->tdls_cancel_channel_switch(&rdev->wiphy, dev, addr);
+	trace_rdev_return_void(&rdev->wiphy);
+}
+
 #endif /* __CFG80211_RDEV_OPS */
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index b725a31a4751..0e347f888fe9 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -56,6 +56,7 @@
 #include <net/cfg80211.h>
 #include "core.h"
 #include "reg.h"
+#include "rdev-ops.h"
 #include "regdb.h"
 #include "nl80211.h"
 
@@ -66,6 +67,12 @@
 #define REG_DBG_PRINT(args...)
 #endif
 
+/*
+ * Grace period we give before making sure all current interfaces reside on
+ * channels allowed by the current regulatory domain.
+ */
+#define REG_ENFORCE_GRACE_MS 60000
+
 /**
  * enum reg_request_treatment - regulatory request treatment
  *
@@ -75,17 +82,12 @@
  *	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 = {
@@ -102,7 +104,7 @@ static struct regulatory_request core_request_world = {
  * protected by RTNL (and can be accessed with RCU protection)
  */
 static struct regulatory_request __rcu *last_request =
-	(void __rcu *)&core_request_world;
+	(void __force __rcu *)&core_request_world;
 
 /* To trigger userspace events */
 static struct platform_device *reg_pdev;
@@ -126,16 +128,24 @@ 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 spinlock_t reg_indoor_lock;
+
+/* Used to track the userspace process controlling the indoor setting */
+static u32 reg_is_indoor_portid;
+
+/* Max number of consecutive attempts to communicate with CRDA  */
+#define REG_MAX_CRDA_TIMEOUTS 10
+
+static u32 reg_crda_timeouts;
 
 static const struct ieee80211_regdomain *get_cfg80211_regdom(void)
 {
 	return rtnl_dereference(cfg80211_regdomain);
 }
 
-static const struct ieee80211_regdomain *get_wiphy_regdom(struct wiphy *wiphy)
+const struct ieee80211_regdomain *get_wiphy_regdom(struct wiphy *wiphy)
 {
 	return rtnl_dereference(wiphy->regd);
 }
@@ -210,6 +220,9 @@ struct reg_beacon {
 	struct ieee80211_channel chan;
 };
 
+static void reg_check_chans_work(struct work_struct *work);
+static DECLARE_DELAYED_WORK(reg_check_chans, reg_check_chans_work);
+
 static void reg_todo(struct work_struct *work);
 static DECLARE_WORK(reg_work, reg_todo);
 
@@ -218,7 +231,7 @@ static DECLARE_DELAYED_WORK(reg_timeout, reg_timeout_work);
 
 /* We keep a static world regulatory domain in case of the absence of CRDA */
 static const struct ieee80211_regdomain world_regdom = {
-	.n_reg_rules = 6,
+	.n_reg_rules = 8,
 	.alpha2 =  "00",
 	.reg_rules = {
 		/* IEEE 802.11b/g, channels 1..11 */
@@ -477,7 +490,7 @@ static void reg_regdb_search(struct work_struct *work)
 	mutex_unlock(&reg_regdb_search_mutex);
 
 	if (!IS_ERR_OR_NULL(regdom))
-		set_regdom(regdom);
+		set_regdom(regdom, REGD_SOURCE_INTERNAL_DB);
 
 	rtnl_unlock();
 }
@@ -527,15 +540,20 @@ static int call_crda(const char *alpha2)
 	snprintf(country, sizeof(country), "COUNTRY=%c%c",
 		 alpha2[0], alpha2[1]);
 
+	/* query internal regulatory database (if it exists) */
+	reg_regdb_query(alpha2);
+
+	if (reg_crda_timeouts > REG_MAX_CRDA_TIMEOUTS) {
+		pr_info("Exceeded CRDA call max attempts. Not calling CRDA\n");
+		return -EINVAL;
+	}
+
 	if (!is_world_regdom((char *) alpha2))
 		pr_info("Calling CRDA for country: %c%c\n",
 			alpha2[0], alpha2[1]);
 	else
 		pr_info("Calling CRDA to update world regulatory domain\n");
 
-	/* query internal regulatory database (if it exists) */
-	reg_regdb_query(alpha2);
-
 	return kobject_uevent_env(&reg_pdev->dev.kobj, KOBJ_CHANGE, env);
 }
 
@@ -544,6 +562,9 @@ reg_call_crda(struct regulatory_request *request)
 {
 	if (call_crda(request->alpha2))
 		return REG_REQ_IGNORE;
+
+	queue_delayed_work(system_power_efficient_wq,
+			   &reg_timeout, msecs_to_jiffies(3142));
 	return REG_REQ_OK;
 }
 
@@ -573,8 +594,9 @@ static const struct ieee80211_regdomain *reg_get_regdomain(struct wiphy *wiphy)
 	return get_cfg80211_regdom();
 }
 
-unsigned int reg_get_max_bandwidth(const struct ieee80211_regdomain *rd,
-				   const struct ieee80211_reg_rule *rule)
+static unsigned int
+reg_get_max_bandwidth_from_range(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;
@@ -622,6 +644,27 @@ unsigned int reg_get_max_bandwidth(const struct ieee80211_regdomain *rd,
 	return end_freq - start_freq;
 }
 
+unsigned int reg_get_max_bandwidth(const struct ieee80211_regdomain *rd,
+				   const struct ieee80211_reg_rule *rule)
+{
+	unsigned int bw = reg_get_max_bandwidth_from_range(rd, rule);
+
+	if (rule->flags & NL80211_RRF_NO_160MHZ)
+		bw = min_t(unsigned int, bw, MHZ_TO_KHZ(80));
+	if (rule->flags & NL80211_RRF_NO_80MHZ)
+		bw = min_t(unsigned int, bw, MHZ_TO_KHZ(40));
+
+	/*
+	 * HT40+/HT40- limits are handled per-channel. Only limit BW if both
+	 * are not allowed.
+	 */
+	if (rule->flags & NL80211_RRF_NO_HT40MINUS &&
+	    rule->flags & NL80211_RRF_NO_HT40PLUS)
+		bw = min_t(unsigned int, bw, MHZ_TO_KHZ(20));
+
+	return bw;
+}
+
 /* Sanity check on a regulatory rule */
 static bool is_valid_reg_rule(const struct ieee80211_reg_rule *rule)
 {
@@ -946,6 +989,16 @@ static u32 map_regdom_flags(u32 rd_flags)
 		channel_flags |= IEEE80211_CHAN_NO_OFDM;
 	if (rd_flags & NL80211_RRF_NO_OUTDOOR)
 		channel_flags |= IEEE80211_CHAN_INDOOR_ONLY;
+	if (rd_flags & NL80211_RRF_GO_CONCURRENT)
+		channel_flags |= IEEE80211_CHAN_GO_CONCURRENT;
+	if (rd_flags & NL80211_RRF_NO_HT40MINUS)
+		channel_flags |= IEEE80211_CHAN_NO_HT40MINUS;
+	if (rd_flags & NL80211_RRF_NO_HT40PLUS)
+		channel_flags |= IEEE80211_CHAN_NO_HT40PLUS;
+	if (rd_flags & NL80211_RRF_NO_80MHZ)
+		channel_flags |= IEEE80211_CHAN_NO_80MHZ;
+	if (rd_flags & NL80211_RRF_NO_160MHZ)
+		channel_flags |= IEEE80211_CHAN_NO_160MHZ;
 	return channel_flags;
 }
 
@@ -1206,13 +1259,6 @@ 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());
@@ -1265,6 +1311,9 @@ static bool ignore_reg_update(struct wiphy *wiphy,
 {
 	struct regulatory_request *lr = get_last_request();
 
+	if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED)
+		return true;
+
 	if (!lr) {
 		REG_DBG_PRINT("Ignoring regulatory request set by %s "
 			      "since last_request is not set\n",
@@ -1486,6 +1535,114 @@ static void reg_call_notifier(struct wiphy *wiphy,
 		wiphy->reg_notifier(wiphy, request);
 }
 
+static bool reg_wdev_chan_valid(struct wiphy *wiphy, struct wireless_dev *wdev)
+{
+	struct cfg80211_chan_def chandef;
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
+	enum nl80211_iftype iftype;
+
+	wdev_lock(wdev);
+	iftype = wdev->iftype;
+
+	/* make sure the interface is active */
+	if (!wdev->netdev || !netif_running(wdev->netdev))
+		goto wdev_inactive_unlock;
+
+	switch (iftype) {
+	case NL80211_IFTYPE_AP:
+	case NL80211_IFTYPE_P2P_GO:
+		if (!wdev->beacon_interval)
+			goto wdev_inactive_unlock;
+		chandef = wdev->chandef;
+		break;
+	case NL80211_IFTYPE_ADHOC:
+		if (!wdev->ssid_len)
+			goto wdev_inactive_unlock;
+		chandef = wdev->chandef;
+		break;
+	case NL80211_IFTYPE_STATION:
+	case NL80211_IFTYPE_P2P_CLIENT:
+		if (!wdev->current_bss ||
+		    !wdev->current_bss->pub.channel)
+			goto wdev_inactive_unlock;
+
+		if (!rdev->ops->get_channel ||
+		    rdev_get_channel(rdev, wdev, &chandef))
+			cfg80211_chandef_create(&chandef,
+						wdev->current_bss->pub.channel,
+						NL80211_CHAN_NO_HT);
+		break;
+	case NL80211_IFTYPE_MONITOR:
+	case NL80211_IFTYPE_AP_VLAN:
+	case NL80211_IFTYPE_P2P_DEVICE:
+		/* no enforcement required */
+		break;
+	default:
+		/* others not implemented for now */
+		WARN_ON(1);
+		break;
+	}
+
+	wdev_unlock(wdev);
+
+	switch (iftype) {
+	case NL80211_IFTYPE_AP:
+	case NL80211_IFTYPE_P2P_GO:
+	case NL80211_IFTYPE_ADHOC:
+		return cfg80211_reg_can_beacon(wiphy, &chandef, iftype);
+	case NL80211_IFTYPE_STATION:
+	case NL80211_IFTYPE_P2P_CLIENT:
+		return cfg80211_chandef_usable(wiphy, &chandef,
+					       IEEE80211_CHAN_DISABLED);
+	default:
+		break;
+	}
+
+	return true;
+
+wdev_inactive_unlock:
+	wdev_unlock(wdev);
+	return true;
+}
+
+static void reg_leave_invalid_chans(struct wiphy *wiphy)
+{
+	struct wireless_dev *wdev;
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
+
+	ASSERT_RTNL();
+
+	list_for_each_entry(wdev, &rdev->wdev_list, list)
+		if (!reg_wdev_chan_valid(wiphy, wdev))
+			cfg80211_leave(rdev, wdev);
+}
+
+static void reg_check_chans_work(struct work_struct *work)
+{
+	struct cfg80211_registered_device *rdev;
+
+	REG_DBG_PRINT("Verifying active interfaces after reg change\n");
+	rtnl_lock();
+
+	list_for_each_entry(rdev, &cfg80211_rdev_list, list)
+		if (!(rdev->wiphy.regulatory_flags &
+		      REGULATORY_IGNORE_STALE_KICKOFF))
+			reg_leave_invalid_chans(&rdev->wiphy);
+
+	rtnl_unlock();
+}
+
+static void reg_check_channels(void)
+{
+	/*
+	 * Give usermode a chance to do something nicer (move to another
+	 * channel, orderly disconnection), before forcing a disconnection.
+	 */
+	mod_delayed_work(system_power_efficient_wq,
+			 &reg_check_chans,
+			 msecs_to_jiffies(REG_ENFORCE_GRACE_MS));
+}
+
 static void wiphy_update_regulatory(struct wiphy *wiphy,
 				    enum nl80211_reg_initiator initiator)
 {
@@ -1525,6 +1682,8 @@ static void update_all_wiphy_regulatory(enum nl80211_reg_initiator initiator)
 		wiphy = &rdev->wiphy;
 		wiphy_update_regulatory(wiphy, initiator);
 	}
+
+	reg_check_channels();
 }
 
 static void handle_channel_custom(struct wiphy *wiphy,
@@ -1543,8 +1702,12 @@ static void handle_channel_custom(struct wiphy *wiphy,
 	if (IS_ERR(reg_rule)) {
 		REG_DBG_PRINT("Disabling freq %d MHz as custom regd has no rule that fits it\n",
 			      chan->center_freq);
-		chan->orig_flags |= IEEE80211_CHAN_DISABLED;
-		chan->flags = chan->orig_flags;
+		if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) {
+			chan->flags |= IEEE80211_CHAN_DISABLED;
+		} else {
+			chan->orig_flags |= IEEE80211_CHAN_DISABLED;
+			chan->flags = chan->orig_flags;
+		}
 		return;
 	}
 
@@ -1565,10 +1728,29 @@ static void handle_channel_custom(struct wiphy *wiphy,
 	if (max_bandwidth_khz < MHZ_TO_KHZ(160))
 		bw_flags |= IEEE80211_CHAN_NO_160MHZ;
 
-	chan->flags |= map_regdom_flags(reg_rule->flags) | bw_flags;
+	chan->dfs_state_entered = jiffies;
+	chan->dfs_state = NL80211_DFS_USABLE;
+
+	chan->beacon_found = false;
+
+	if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED)
+		chan->flags = chan->orig_flags | bw_flags |
+			      map_regdom_flags(reg_rule->flags);
+	else
+		chan->flags |= map_regdom_flags(reg_rule->flags) | bw_flags;
+
 	chan->max_antenna_gain = (int) MBI_TO_DBI(power_rule->max_antenna_gain);
 	chan->max_reg_power = chan->max_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;
+	}
+
+	chan->max_power = chan->max_reg_power;
 }
 
 static void handle_band_custom(struct wiphy *wiphy,
@@ -1622,8 +1804,7 @@ static void reg_set_request_processed(void)
 		need_more_processing = true;
 	spin_unlock(&reg_requests_lock);
 
-	if (lr->initiator == NL80211_REGDOM_SET_BY_USER)
-		cancel_delayed_work(&reg_timeout);
+	cancel_delayed_work(&reg_timeout);
 
 	if (need_more_processing)
 		schedule_work(&reg_work);
@@ -1655,11 +1836,6 @@ __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);
 
@@ -1707,8 +1883,7 @@ 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 ||
-	    treatment == REG_REQ_USER_HINT_HANDLED) {
+	    treatment == REG_REQ_ALREADY_SET) {
 		reg_free_request(user_request);
 		return treatment;
 	}
@@ -1760,7 +1935,7 @@ static enum reg_request_treatment
 reg_process_hint_driver(struct wiphy *wiphy,
 			struct regulatory_request *driver_request)
 {
-	const struct ieee80211_regdomain *regd;
+	const struct ieee80211_regdomain *regd, *tmp;
 	enum reg_request_treatment treatment;
 
 	treatment = __reg_process_hint_driver(driver_request);
@@ -1769,7 +1944,6 @@ reg_process_hint_driver(struct wiphy *wiphy,
 	case REG_REQ_OK:
 		break;
 	case REG_REQ_IGNORE:
-	case REG_REQ_USER_HINT_HANDLED:
 		reg_free_request(driver_request);
 		return treatment;
 	case REG_REQ_INTERSECT:
@@ -1780,7 +1954,10 @@ reg_process_hint_driver(struct wiphy *wiphy,
 			reg_free_request(driver_request);
 			return REG_REQ_IGNORE;
 		}
+
+		tmp = get_wiphy_regdom(wiphy);
 		rcu_assign_pointer(wiphy->regd, regd);
+		rcu_free_regdom(tmp);
 	}
 
 
@@ -1839,11 +2016,8 @@ __reg_process_hint_country_ie(struct wiphy *wiphy,
 			return REG_REQ_IGNORE;
 		return REG_REQ_ALREADY_SET;
 	}
-	/*
-	 * Two consecutive Country IE hints on the same wiphy.
-	 * This should be picked up early by the driver/stack
-	 */
-	if (WARN_ON(regdom_changes(country_ie_request->alpha2)))
+
+	if (regdom_changes(country_ie_request->alpha2))
 		return REG_REQ_OK;
 	return REG_REQ_ALREADY_SET;
 }
@@ -1869,7 +2043,6 @@ 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:
 		reg_free_request(country_ie_request);
@@ -1908,11 +2081,8 @@ static void reg_process_hint(struct regulatory_request *reg_request)
 	case NL80211_REGDOM_SET_BY_USER:
 		treatment = reg_process_hint_user(reg_request);
 		if (treatment == REG_REQ_IGNORE ||
-		    treatment == REG_REQ_ALREADY_SET ||
-		    treatment == REG_REQ_USER_HINT_HANDLED)
+		    treatment == REG_REQ_ALREADY_SET)
 			return;
-		queue_delayed_work(system_power_efficient_wq,
-				   &reg_timeout, msecs_to_jiffies(3142));
 		return;
 	case NL80211_REGDOM_SET_BY_DRIVER:
 		if (!wiphy)
@@ -1931,8 +2101,10 @@ static void reg_process_hint(struct regulatory_request *reg_request)
 
 	/* This is required so that the orig_* parameters are saved */
 	if (treatment == REG_REQ_ALREADY_SET && wiphy &&
-	    wiphy->regulatory_flags & REGULATORY_STRICT_REG)
+	    wiphy->regulatory_flags & REGULATORY_STRICT_REG) {
 		wiphy_update_regulatory(wiphy, reg_request->initiator);
+		reg_check_channels();
+	}
 
 	return;
 
@@ -1940,6 +2112,26 @@ out_free:
 	reg_free_request(reg_request);
 }
 
+static bool reg_only_self_managed_wiphys(void)
+{
+	struct cfg80211_registered_device *rdev;
+	struct wiphy *wiphy;
+	bool self_managed_found = false;
+
+	ASSERT_RTNL();
+
+	list_for_each_entry(rdev, &cfg80211_rdev_list, list) {
+		wiphy = &rdev->wiphy;
+		if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED)
+			self_managed_found = true;
+		else
+			return false;
+	}
+
+	/* make sure at least one self-managed wiphy exists */
+	return self_managed_found;
+}
+
 /*
  * Processes regulatory hints, this is all the NL80211_REGDOM_SET_BY_*
  * Regulatory hints come on a first come first serve basis and we
@@ -1971,7 +2163,19 @@ static void reg_process_pending_hints(void)
 
 	spin_unlock(&reg_requests_lock);
 
+	if (reg_only_self_managed_wiphys()) {
+		reg_free_request(reg_request);
+		return;
+	}
+
 	reg_process_hint(reg_request);
+
+	lr = get_last_request();
+
+	spin_lock(&reg_requests_lock);
+	if (!list_empty(&reg_requests_list) && lr && lr->processed)
+		schedule_work(&reg_work);
+	spin_unlock(&reg_requests_lock);
 }
 
 /* Processes beacon hints -- this has nothing to do with country IEs */
@@ -1998,11 +2202,52 @@ static void reg_process_pending_beacon_hints(void)
 	spin_unlock_bh(&reg_pending_beacons_lock);
 }
 
+static void reg_process_self_managed_hints(void)
+{
+	struct cfg80211_registered_device *rdev;
+	struct wiphy *wiphy;
+	const struct ieee80211_regdomain *tmp;
+	const struct ieee80211_regdomain *regd;
+	enum ieee80211_band band;
+	struct regulatory_request request = {};
+
+	list_for_each_entry(rdev, &cfg80211_rdev_list, list) {
+		wiphy = &rdev->wiphy;
+
+		spin_lock(&reg_requests_lock);
+		regd = rdev->requested_regd;
+		rdev->requested_regd = NULL;
+		spin_unlock(&reg_requests_lock);
+
+		if (regd == NULL)
+			continue;
+
+		tmp = get_wiphy_regdom(wiphy);
+		rcu_assign_pointer(wiphy->regd, regd);
+		rcu_free_regdom(tmp);
+
+		for (band = 0; band < IEEE80211_NUM_BANDS; band++)
+			handle_band_custom(wiphy, wiphy->bands[band], regd);
+
+		reg_process_ht_flags(wiphy);
+
+		request.wiphy_idx = get_wiphy_idx(wiphy);
+		request.alpha2[0] = regd->alpha2[0];
+		request.alpha2[1] = regd->alpha2[1];
+		request.initiator = NL80211_REGDOM_SET_BY_DRIVER;
+
+		nl80211_send_wiphy_reg_change_event(&request);
+	}
+
+	reg_check_channels();
+}
+
 static void reg_todo(struct work_struct *work)
 {
 	rtnl_lock();
 	reg_process_pending_hints();
 	reg_process_pending_beacon_hints();
+	reg_process_self_managed_hints();
 	rtnl_unlock();
 }
 
@@ -2058,27 +2303,58 @@ int regulatory_hint_user(const char *alpha2,
 	request->initiator = NL80211_REGDOM_SET_BY_USER;
 	request->user_reg_hint_type = user_reg_hint_type;
 
+	/* Allow calling CRDA again */
+	reg_crda_timeouts = 0;
+
 	queue_regulatory_request(request);
 
 	return 0;
 }
 
-int regulatory_hint_indoor_user(void)
+int regulatory_hint_indoor(bool is_indoor, u32 portid)
 {
-	struct regulatory_request *request;
+	spin_lock(&reg_indoor_lock);
 
-	request = kzalloc(sizeof(struct regulatory_request), GFP_KERNEL);
-	if (!request)
-		return -ENOMEM;
+	/* It is possible that more than one user space process is trying to
+	 * configure the indoor setting. To handle such cases, clear the indoor
+	 * setting in case that some process does not think that the device
+	 * is operating in an indoor environment. In addition, if a user space
+	 * process indicates that it is controlling the indoor setting, save its
+	 * portid, i.e., make it the owner.
+	 */
+	reg_is_indoor = is_indoor;
+	if (reg_is_indoor) {
+		if (!reg_is_indoor_portid)
+			reg_is_indoor_portid = portid;
+	} else {
+		reg_is_indoor_portid = 0;
+	}
 
-	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);
+	spin_unlock(&reg_indoor_lock);
+
+	if (!is_indoor)
+		reg_check_channels();
 
 	return 0;
 }
 
+void regulatory_netlink_notify(u32 portid)
+{
+	spin_lock(&reg_indoor_lock);
+
+	if (reg_is_indoor_portid != portid) {
+		spin_unlock(&reg_indoor_lock);
+		return;
+	}
+
+	reg_is_indoor = false;
+	reg_is_indoor_portid = 0;
+
+	spin_unlock(&reg_indoor_lock);
+
+	reg_check_channels();
+}
+
 /* Driver hints */
 int regulatory_hint(struct wiphy *wiphy, const char *alpha2)
 {
@@ -2099,6 +2375,9 @@ int regulatory_hint(struct wiphy *wiphy, const char *alpha2)
 	request->alpha2[1] = alpha2[1];
 	request->initiator = NL80211_REGDOM_SET_BY_DRIVER;
 
+	/* Allow calling CRDA again */
+	reg_crda_timeouts = 0;
+
 	queue_regulatory_request(request);
 
 	return 0;
@@ -2152,6 +2431,9 @@ void regulatory_hint_country_ie(struct wiphy *wiphy, enum ieee80211_band band,
 	request->initiator = NL80211_REGDOM_SET_BY_COUNTRY_IE;
 	request->country_ie_env = env;
 
+	/* Allow calling CRDA again */
+	reg_crda_timeouts = 0;
+
 	queue_regulatory_request(request);
 	request = NULL;
 out:
@@ -2240,13 +2522,22 @@ static void restore_regulatory_settings(bool reset_user)
 	char alpha2[2];
 	char world_alpha2[2];
 	struct reg_beacon *reg_beacon, *btmp;
-	struct regulatory_request *reg_request, *tmp;
 	LIST_HEAD(tmp_reg_req_list);
 	struct cfg80211_registered_device *rdev;
 
 	ASSERT_RTNL();
 
-	reg_is_indoor = false;
+	/*
+	 * Clear the indoor setting in case that it is not controlled by user
+	 * space, as otherwise there is no guarantee that the device is still
+	 * operating in an indoor environment.
+	 */
+	spin_lock(&reg_indoor_lock);
+	if (reg_is_indoor && !reg_is_indoor_portid) {
+		reg_is_indoor = false;
+		reg_check_channels();
+	}
+	spin_unlock(&reg_indoor_lock);
 
 	reset_regdomains(true, &world_regdom);
 	restore_alpha2(alpha2, reset_user);
@@ -2258,11 +2549,7 @@ static void restore_regulatory_settings(bool reset_user)
 	 * settings.
 	 */
 	spin_lock(&reg_requests_lock);
-	list_for_each_entry_safe(reg_request, tmp, &reg_requests_list, list) {
-		if (reg_request->initiator != NL80211_REGDOM_SET_BY_USER)
-			continue;
-		list_move_tail(&reg_request->list, &tmp_reg_req_list);
-	}
+	list_splice_tail_init(&reg_requests_list, &tmp_reg_req_list);
 	spin_unlock(&reg_requests_lock);
 
 	/* Clear beacon hints */
@@ -2283,6 +2570,8 @@ static void restore_regulatory_settings(bool reset_user)
 	world_alpha2[1] = cfg80211_world_regdom->alpha2[1];
 
 	list_for_each_entry(rdev, &cfg80211_rdev_list, list) {
+		if (rdev->wiphy.regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED)
+			continue;
 		if (rdev->wiphy.regulatory_flags & REGULATORY_CUSTOM_REG)
 			restore_custom_reg_settings(&rdev->wiphy);
 	}
@@ -2623,7 +2912,8 @@ static int reg_set_rd_country_ie(const struct ieee80211_regdomain *rd,
  * multiple drivers can be ironed out later. Caller must've already
  * kmalloc'd the rd structure.
  */
-int set_regdom(const struct ieee80211_regdomain *rd)
+int set_regdom(const struct ieee80211_regdomain *rd,
+	       enum ieee80211_regd_source regd_src)
 {
 	struct regulatory_request *lr;
 	bool user_reset = false;
@@ -2634,6 +2924,9 @@ int set_regdom(const struct ieee80211_regdomain *rd)
 		return -EINVAL;
 	}
 
+	if (regd_src == REGD_SOURCE_CRDA)
+		reg_crda_timeouts = 0;
+
 	lr = get_last_request();
 
 	/* Note that this doesn't update the wiphys, this is done below */
@@ -2686,10 +2979,79 @@ int set_regdom(const struct ieee80211_regdomain *rd)
 	return 0;
 }
 
+static int __regulatory_set_wiphy_regd(struct wiphy *wiphy,
+				       struct ieee80211_regdomain *rd)
+{
+	const struct ieee80211_regdomain *regd;
+	const struct ieee80211_regdomain *prev_regd;
+	struct cfg80211_registered_device *rdev;
+
+	if (WARN_ON(!wiphy || !rd))
+		return -EINVAL;
+
+	if (WARN(!(wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED),
+		 "wiphy should have REGULATORY_WIPHY_SELF_MANAGED\n"))
+		return -EPERM;
+
+	if (WARN(!is_valid_rd(rd), "Invalid regulatory domain detected\n")) {
+		print_regdomain_info(rd);
+		return -EINVAL;
+	}
+
+	regd = reg_copy_regd(rd);
+	if (IS_ERR(regd))
+		return PTR_ERR(regd);
+
+	rdev = wiphy_to_rdev(wiphy);
+
+	spin_lock(&reg_requests_lock);
+	prev_regd = rdev->requested_regd;
+	rdev->requested_regd = regd;
+	spin_unlock(&reg_requests_lock);
+
+	kfree(prev_regd);
+	return 0;
+}
+
+int regulatory_set_wiphy_regd(struct wiphy *wiphy,
+			      struct ieee80211_regdomain *rd)
+{
+	int ret = __regulatory_set_wiphy_regd(wiphy, rd);
+
+	if (ret)
+		return ret;
+
+	schedule_work(&reg_work);
+	return 0;
+}
+EXPORT_SYMBOL(regulatory_set_wiphy_regd);
+
+int regulatory_set_wiphy_regd_sync_rtnl(struct wiphy *wiphy,
+					struct ieee80211_regdomain *rd)
+{
+	int ret;
+
+	ASSERT_RTNL();
+
+	ret = __regulatory_set_wiphy_regd(wiphy, rd);
+	if (ret)
+		return ret;
+
+	/* process the request immediately */
+	reg_process_self_managed_hints();
+	return 0;
+}
+EXPORT_SYMBOL(regulatory_set_wiphy_regd_sync_rtnl);
+
 void wiphy_regulatory_register(struct wiphy *wiphy)
 {
 	struct regulatory_request *lr;
 
+	/* self-managed devices ignore external hints */
+	if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED)
+		wiphy->regulatory_flags |= REGULATORY_DISABLE_BEACON_HINTS |
+					   REGULATORY_COUNTRY_IE_IGNORE;
+
 	if (!reg_dev_ignore_cell_hint(wiphy))
 		reg_num_devs_support_basehint++;
 
@@ -2724,6 +3086,7 @@ static void reg_timeout_work(struct work_struct *work)
 {
 	REG_DBG_PRINT("Timeout while waiting for CRDA to reply, restoring regulatory settings\n");
 	rtnl_lock();
+	reg_crda_timeouts++;
 	restore_regulatory_settings(true);
 	rtnl_unlock();
 }
@@ -2772,6 +3135,7 @@ int __init regulatory_init(void)
 
 	spin_lock_init(&reg_requests_lock);
 	spin_lock_init(&reg_pending_beacons_lock);
+	spin_lock_init(&reg_indoor_lock);
 
 	reg_regdb_size_check();
 
@@ -2813,6 +3177,7 @@ void regulatory_exit(void)
 
 	cancel_work_sync(&reg_work);
 	cancel_delayed_work_sync(&reg_timeout);
+	cancel_delayed_work_sync(&reg_check_chans);
 
 	/* Lock to suppress warnings */
 	rtnl_lock();
diff --git a/net/wireless/reg.h b/net/wireless/reg.h
index 5e48031ccb9a..9f495d76eca0 100644
--- a/net/wireless/reg.h
+++ b/net/wireless/reg.h
@@ -16,6 +16,11 @@
  * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
  */
 
+enum ieee80211_regd_source {
+	REGD_SOURCE_INTERNAL_DB,
+	REGD_SOURCE_CRDA,
+};
+
 extern const struct ieee80211_regdomain __rcu *cfg80211_regdomain;
 
 bool reg_is_valid_request(const char *alpha2);
@@ -25,7 +30,20 @@ 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);
+
+/**
+ * regulatory_hint_indoor - hint operation in indoor env. or not
+ * @is_indoor: if true indicates that user space thinks that the
+ * device is operating in an indoor environment.
+ * @portid: the netlink port ID on which the hint was given.
+ */
+int regulatory_hint_indoor(bool is_indoor, u32 portid);
+
+/**
+ * regulatory_netlink_notify - notify on released netlink socket
+ * @portid: the netlink socket port ID
+ */
+void regulatory_netlink_notify(u32 portid);
 
 void wiphy_regulatory_register(struct wiphy *wiphy);
 void wiphy_regulatory_deregister(struct wiphy *wiphy);
@@ -33,11 +51,14 @@ void wiphy_regulatory_deregister(struct wiphy *wiphy);
 int __init regulatory_init(void);
 void regulatory_exit(void);
 
-int set_regdom(const struct ieee80211_regdomain *rd);
+int set_regdom(const struct ieee80211_regdomain *rd,
+	       enum ieee80211_regd_source regd_src);
+
 unsigned int reg_get_max_bandwidth(const struct ieee80211_regdomain *rd,
 				   const struct ieee80211_reg_rule *rule);
 
 bool reg_last_request_cell_base(void);
+const struct ieee80211_regdomain *get_wiphy_regdom(struct wiphy *wiphy);
 
 /**
  * regulatory_hint_found_beacon - hints a beacon was found on a channel
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index bda39f149810..3a50aa2553bf 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -257,7 +257,7 @@ void __cfg80211_sched_scan_results(struct work_struct *wk)
 
 	rtnl_lock();
 
-	request = rdev->sched_scan_req;
+	request = rtnl_dereference(rdev->sched_scan_req);
 
 	/* we don't have sched_scan_req anymore if the scan is stopping */
 	if (request) {
@@ -279,7 +279,8 @@ void cfg80211_sched_scan_results(struct wiphy *wiphy)
 {
 	trace_cfg80211_sched_scan_results(wiphy);
 	/* ignore if we're not scanning */
-	if (wiphy_to_rdev(wiphy)->sched_scan_req)
+
+	if (rcu_access_pointer(wiphy_to_rdev(wiphy)->sched_scan_req))
 		queue_work(cfg80211_wq,
 			   &wiphy_to_rdev(wiphy)->sched_scan_results_wk);
 }
@@ -308,6 +309,7 @@ EXPORT_SYMBOL(cfg80211_sched_scan_stopped);
 int __cfg80211_stop_sched_scan(struct cfg80211_registered_device *rdev,
 			       bool driver_initiated)
 {
+	struct cfg80211_sched_scan_request *sched_scan_req;
 	struct net_device *dev;
 
 	ASSERT_RTNL();
@@ -315,7 +317,8 @@ int __cfg80211_stop_sched_scan(struct cfg80211_registered_device *rdev,
 	if (!rdev->sched_scan_req)
 		return -ENOENT;
 
-	dev = rdev->sched_scan_req->dev;
+	sched_scan_req = rtnl_dereference(rdev->sched_scan_req);
+	dev = sched_scan_req->dev;
 
 	if (!driver_initiated) {
 		int err = rdev_sched_scan_stop(rdev, dev);
@@ -325,8 +328,8 @@ int __cfg80211_stop_sched_scan(struct cfg80211_registered_device *rdev,
 
 	nl80211_send_sched_scan(rdev, dev, NL80211_CMD_SCHED_SCAN_STOPPED);
 
-	kfree(rdev->sched_scan_req);
-	rdev->sched_scan_req = NULL;
+	RCU_INIT_POINTER(rdev->sched_scan_req, NULL);
+	kfree_rcu(sched_scan_req, rcu_head);
 
 	return 0;
 }
@@ -528,24 +531,78 @@ static int cmp_bss(struct cfg80211_bss *a,
 	}
 }
 
+static bool cfg80211_bss_type_match(u16 capability,
+				    enum ieee80211_band band,
+				    enum ieee80211_bss_type bss_type)
+{
+	bool ret = true;
+	u16 mask, val;
+
+	if (bss_type == IEEE80211_BSS_TYPE_ANY)
+		return ret;
+
+	if (band == IEEE80211_BAND_60GHZ) {
+		mask = WLAN_CAPABILITY_DMG_TYPE_MASK;
+		switch (bss_type) {
+		case IEEE80211_BSS_TYPE_ESS:
+			val = WLAN_CAPABILITY_DMG_TYPE_AP;
+			break;
+		case IEEE80211_BSS_TYPE_PBSS:
+			val = WLAN_CAPABILITY_DMG_TYPE_PBSS;
+			break;
+		case IEEE80211_BSS_TYPE_IBSS:
+			val = WLAN_CAPABILITY_DMG_TYPE_IBSS;
+			break;
+		default:
+			return false;
+		}
+	} else {
+		mask = WLAN_CAPABILITY_ESS | WLAN_CAPABILITY_IBSS;
+		switch (bss_type) {
+		case IEEE80211_BSS_TYPE_ESS:
+			val = WLAN_CAPABILITY_ESS;
+			break;
+		case IEEE80211_BSS_TYPE_IBSS:
+			val = WLAN_CAPABILITY_IBSS;
+			break;
+		case IEEE80211_BSS_TYPE_MBSS:
+			val = 0;
+			break;
+		default:
+			return false;
+		}
+	}
+
+	ret = ((capability & mask) == val);
+	return ret;
+}
+
 /* Returned bss is reference counted and must be cleaned up appropriately. */
 struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy,
 				      struct ieee80211_channel *channel,
 				      const u8 *bssid,
 				      const u8 *ssid, size_t ssid_len,
-				      u16 capa_mask, u16 capa_val)
+				      enum ieee80211_bss_type bss_type,
+				      enum ieee80211_privacy privacy)
 {
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct cfg80211_internal_bss *bss, *res = NULL;
 	unsigned long now = jiffies;
+	int bss_privacy;
 
-	trace_cfg80211_get_bss(wiphy, channel, bssid, ssid, ssid_len, capa_mask,
-			       capa_val);
+	trace_cfg80211_get_bss(wiphy, channel, bssid, ssid, ssid_len, bss_type,
+			       privacy);
 
 	spin_lock_bh(&rdev->bss_lock);
 
 	list_for_each_entry(bss, &rdev->bss_list, list) {
-		if ((bss->pub.capability & capa_mask) != capa_val)
+		if (!cfg80211_bss_type_match(bss->pub.capability,
+					     bss->pub.channel->band, bss_type))
+			continue;
+
+		bss_privacy = (bss->pub.capability & WLAN_CAPABILITY_PRIVACY);
+		if ((privacy == IEEE80211_PRIVACY_ON && !bss_privacy) ||
+		    (privacy == IEEE80211_PRIVACY_OFF && bss_privacy))
 			continue;
 		if (channel && bss->pub.channel != channel)
 			continue;
@@ -893,6 +950,7 @@ cfg80211_inform_bss_width(struct wiphy *wiphy,
 	struct cfg80211_bss_ies *ies;
 	struct ieee80211_channel *channel;
 	struct cfg80211_internal_bss tmp = {}, *res;
+	int bss_type;
 	bool signal_valid;
 
 	if (WARN_ON(!wiphy))
@@ -947,8 +1005,15 @@ cfg80211_inform_bss_width(struct wiphy *wiphy,
 	if (!res)
 		return NULL;
 
-	if (res->pub.capability & WLAN_CAPABILITY_ESS)
-		regulatory_hint_found_beacon(wiphy, channel, gfp);
+	if (channel->band == IEEE80211_BAND_60GHZ) {
+		bss_type = res->pub.capability & WLAN_CAPABILITY_DMG_TYPE_MASK;
+		if (bss_type == WLAN_CAPABILITY_DMG_TYPE_AP ||
+		    bss_type == WLAN_CAPABILITY_DMG_TYPE_PBSS)
+			regulatory_hint_found_beacon(wiphy, channel, gfp);
+	} else {
+		if (res->pub.capability & WLAN_CAPABILITY_ESS)
+			regulatory_hint_found_beacon(wiphy, channel, gfp);
+	}
 
 	trace_cfg80211_return_bss(&res->pub);
 	/* cfg80211_bss_update gives us a referenced result */
@@ -970,6 +1035,7 @@ cfg80211_inform_bss_width_frame(struct wiphy *wiphy,
 	bool signal_valid;
 	size_t ielen = len - offsetof(struct ieee80211_mgmt,
 				      u.probe_resp.variable);
+	int bss_type;
 
 	BUILD_BUG_ON(offsetof(struct ieee80211_mgmt, u.probe_resp.variable) !=
 			offsetof(struct ieee80211_mgmt, u.beacon.variable));
@@ -1022,8 +1088,15 @@ cfg80211_inform_bss_width_frame(struct wiphy *wiphy,
 	if (!res)
 		return NULL;
 
-	if (res->pub.capability & WLAN_CAPABILITY_ESS)
-		regulatory_hint_found_beacon(wiphy, channel, gfp);
+	if (channel->band == IEEE80211_BAND_60GHZ) {
+		bss_type = res->pub.capability & WLAN_CAPABILITY_DMG_TYPE_MASK;
+		if (bss_type == WLAN_CAPABILITY_DMG_TYPE_AP ||
+		    bss_type == WLAN_CAPABILITY_DMG_TYPE_PBSS)
+			regulatory_hint_found_beacon(wiphy, channel, gfp);
+	} else {
+		if (res->pub.capability & WLAN_CAPABILITY_ESS)
+			regulatory_hint_found_beacon(wiphy, channel, gfp);
+	}
 
 	trace_cfg80211_return_bss(&res->pub);
 	/* cfg80211_bss_update gives us a referenced result */
@@ -1234,17 +1307,17 @@ int cfg80211_wext_siwscan(struct net_device *dev,
 	kfree(creq);
 	return err;
 }
-EXPORT_SYMBOL_GPL(cfg80211_wext_siwscan);
+EXPORT_WEXT_HANDLER(cfg80211_wext_siwscan);
 
-static void ieee80211_scan_add_ies(struct iw_request_info *info,
-				   const struct cfg80211_bss_ies *ies,
-				   char **current_ev, char *end_buf)
+static char *ieee80211_scan_add_ies(struct iw_request_info *info,
+				    const struct cfg80211_bss_ies *ies,
+				    char *current_ev, char *end_buf)
 {
 	const u8 *pos, *end, *next;
 	struct iw_event iwe;
 
 	if (!ies)
-		return;
+		return current_ev;
 
 	/*
 	 * If needed, fragment the IEs buffer (at IE boundaries) into short
@@ -1261,10 +1334,11 @@ static void ieee80211_scan_add_ies(struct iw_request_info *info,
 		memset(&iwe, 0, sizeof(iwe));
 		iwe.cmd = IWEVGENIE;
 		iwe.u.data.length = next - pos;
-		*current_ev = iwe_stream_add_point(info, *current_ev,
-						   end_buf, &iwe,
-						   (void *)pos);
-
+		current_ev = iwe_stream_add_point_check(info, current_ev,
+							end_buf, &iwe,
+							(void *)pos);
+		if (IS_ERR(current_ev))
+			return current_ev;
 		pos = next;
 	}
 
@@ -1272,10 +1346,14 @@ static void ieee80211_scan_add_ies(struct iw_request_info *info,
 		memset(&iwe, 0, sizeof(iwe));
 		iwe.cmd = IWEVGENIE;
 		iwe.u.data.length = end - pos;
-		*current_ev = iwe_stream_add_point(info, *current_ev,
-						   end_buf, &iwe,
-						   (void *)pos);
+		current_ev = iwe_stream_add_point_check(info, current_ev,
+							end_buf, &iwe,
+							(void *)pos);
+		if (IS_ERR(current_ev))
+			return current_ev;
 	}
+
+	return current_ev;
 }
 
 static char *
@@ -1286,7 +1364,8 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info,
 	const struct cfg80211_bss_ies *ies;
 	struct iw_event iwe;
 	const u8 *ie;
-	u8 *buf, *cfg, *p;
+	u8 buf[50];
+	u8 *cfg, *p, *tmp;
 	int rem, i, sig;
 	bool ismesh = false;
 
@@ -1294,22 +1373,28 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info,
 	iwe.cmd = SIOCGIWAP;
 	iwe.u.ap_addr.sa_family = ARPHRD_ETHER;
 	memcpy(iwe.u.ap_addr.sa_data, bss->pub.bssid, ETH_ALEN);
-	current_ev = iwe_stream_add_event(info, current_ev, end_buf, &iwe,
-					  IW_EV_ADDR_LEN);
+	current_ev = iwe_stream_add_event_check(info, current_ev, end_buf, &iwe,
+						IW_EV_ADDR_LEN);
+	if (IS_ERR(current_ev))
+		return current_ev;
 
 	memset(&iwe, 0, sizeof(iwe));
 	iwe.cmd = SIOCGIWFREQ;
 	iwe.u.freq.m = ieee80211_frequency_to_channel(bss->pub.channel->center_freq);
 	iwe.u.freq.e = 0;
-	current_ev = iwe_stream_add_event(info, current_ev, end_buf, &iwe,
-					  IW_EV_FREQ_LEN);
+	current_ev = iwe_stream_add_event_check(info, current_ev, end_buf, &iwe,
+						IW_EV_FREQ_LEN);
+	if (IS_ERR(current_ev))
+		return current_ev;
 
 	memset(&iwe, 0, sizeof(iwe));
 	iwe.cmd = SIOCGIWFREQ;
 	iwe.u.freq.m = bss->pub.channel->center_freq;
 	iwe.u.freq.e = 6;
-	current_ev = iwe_stream_add_event(info, current_ev, end_buf, &iwe,
-					  IW_EV_FREQ_LEN);
+	current_ev = iwe_stream_add_event_check(info, current_ev, end_buf, &iwe,
+						IW_EV_FREQ_LEN);
+	if (IS_ERR(current_ev))
+		return current_ev;
 
 	if (wiphy->signal_type != CFG80211_SIGNAL_TYPE_NONE) {
 		memset(&iwe, 0, sizeof(iwe));
@@ -1338,8 +1423,11 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info,
 			/* not reached */
 			break;
 		}
-		current_ev = iwe_stream_add_event(info, current_ev, end_buf,
-						  &iwe, IW_EV_QUAL_LEN);
+		current_ev = iwe_stream_add_event_check(info, current_ev,
+							end_buf, &iwe,
+							IW_EV_QUAL_LEN);
+		if (IS_ERR(current_ev))
+			return current_ev;
 	}
 
 	memset(&iwe, 0, sizeof(iwe));
@@ -1349,8 +1437,10 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info,
 	else
 		iwe.u.data.flags = IW_ENCODE_DISABLED;
 	iwe.u.data.length = 0;
-	current_ev = iwe_stream_add_point(info, current_ev, end_buf,
-					  &iwe, "");
+	current_ev = iwe_stream_add_point_check(info, current_ev, end_buf,
+						&iwe, "");
+	if (IS_ERR(current_ev))
+		return current_ev;
 
 	rcu_read_lock();
 	ies = rcu_dereference(bss->pub.ies);
@@ -1368,66 +1458,91 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info,
 			iwe.cmd = SIOCGIWESSID;
 			iwe.u.data.length = ie[1];
 			iwe.u.data.flags = 1;
-			current_ev = iwe_stream_add_point(info, current_ev, end_buf,
-							  &iwe, (u8 *)ie + 2);
+			current_ev = iwe_stream_add_point_check(info,
+								current_ev,
+								end_buf, &iwe,
+								(u8 *)ie + 2);
+			if (IS_ERR(current_ev))
+				goto unlock;
 			break;
 		case WLAN_EID_MESH_ID:
 			memset(&iwe, 0, sizeof(iwe));
 			iwe.cmd = SIOCGIWESSID;
 			iwe.u.data.length = ie[1];
 			iwe.u.data.flags = 1;
-			current_ev = iwe_stream_add_point(info, current_ev, end_buf,
-							  &iwe, (u8 *)ie + 2);
+			current_ev = iwe_stream_add_point_check(info,
+								current_ev,
+								end_buf, &iwe,
+								(u8 *)ie + 2);
+			if (IS_ERR(current_ev))
+				goto unlock;
 			break;
 		case WLAN_EID_MESH_CONFIG:
 			ismesh = true;
 			if (ie[1] != sizeof(struct ieee80211_meshconf_ie))
 				break;
-			buf = kmalloc(50, GFP_ATOMIC);
-			if (!buf)
-				break;
 			cfg = (u8 *)ie + 2;
 			memset(&iwe, 0, sizeof(iwe));
 			iwe.cmd = IWEVCUSTOM;
 			sprintf(buf, "Mesh Network Path Selection Protocol ID: "
 				"0x%02X", cfg[0]);
 			iwe.u.data.length = strlen(buf);
-			current_ev = iwe_stream_add_point(info, current_ev,
-							  end_buf,
-							  &iwe, buf);
+			current_ev = iwe_stream_add_point_check(info,
+								current_ev,
+								end_buf,
+								&iwe, buf);
+			if (IS_ERR(current_ev))
+				goto unlock;
 			sprintf(buf, "Path Selection Metric ID: 0x%02X",
 				cfg[1]);
 			iwe.u.data.length = strlen(buf);
-			current_ev = iwe_stream_add_point(info, current_ev,
-							  end_buf,
-							  &iwe, buf);
+			current_ev = iwe_stream_add_point_check(info,
+								current_ev,
+								end_buf,
+								&iwe, buf);
+			if (IS_ERR(current_ev))
+				goto unlock;
 			sprintf(buf, "Congestion Control Mode ID: 0x%02X",
 				cfg[2]);
 			iwe.u.data.length = strlen(buf);
-			current_ev = iwe_stream_add_point(info, current_ev,
-							  end_buf,
-							  &iwe, buf);
+			current_ev = iwe_stream_add_point_check(info,
+								current_ev,
+								end_buf,
+								&iwe, buf);
+			if (IS_ERR(current_ev))
+				goto unlock;
 			sprintf(buf, "Synchronization ID: 0x%02X", cfg[3]);
 			iwe.u.data.length = strlen(buf);
-			current_ev = iwe_stream_add_point(info, current_ev,
-							  end_buf,
-							  &iwe, buf);
+			current_ev = iwe_stream_add_point_check(info,
+								current_ev,
+								end_buf,
+								&iwe, buf);
+			if (IS_ERR(current_ev))
+				goto unlock;
 			sprintf(buf, "Authentication ID: 0x%02X", cfg[4]);
 			iwe.u.data.length = strlen(buf);
-			current_ev = iwe_stream_add_point(info, current_ev,
-							  end_buf,
-							  &iwe, buf);
+			current_ev = iwe_stream_add_point_check(info,
+								current_ev,
+								end_buf,
+								&iwe, buf);
+			if (IS_ERR(current_ev))
+				goto unlock;
 			sprintf(buf, "Formation Info: 0x%02X", cfg[5]);
 			iwe.u.data.length = strlen(buf);
-			current_ev = iwe_stream_add_point(info, current_ev,
-							  end_buf,
-							  &iwe, buf);
+			current_ev = iwe_stream_add_point_check(info,
+								current_ev,
+								end_buf,
+								&iwe, buf);
+			if (IS_ERR(current_ev))
+				goto unlock;
 			sprintf(buf, "Capabilities: 0x%02X", cfg[6]);
 			iwe.u.data.length = strlen(buf);
-			current_ev = iwe_stream_add_point(info, current_ev,
-							  end_buf,
-							  &iwe, buf);
-			kfree(buf);
+			current_ev = iwe_stream_add_point_check(info,
+								current_ev,
+								end_buf,
+								&iwe, buf);
+			if (IS_ERR(current_ev))
+				goto unlock;
 			break;
 		case WLAN_EID_SUPP_RATES:
 		case WLAN_EID_EXT_SUPP_RATES:
@@ -1442,8 +1557,14 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info,
 			for (i = 0; i < ie[1]; i++) {
 				iwe.u.bitrate.value =
 					((ie[i + 2] & 0x7f) * 500000);
+				tmp = p;
 				p = iwe_stream_add_value(info, current_ev, p,
-						end_buf, &iwe, IW_EV_PARAM_LEN);
+							 end_buf, &iwe,
+							 IW_EV_PARAM_LEN);
+				if (p == tmp) {
+					current_ev = ERR_PTR(-E2BIG);
+					goto unlock;
+				}
 			}
 			current_ev = p;
 			break;
@@ -1462,31 +1583,35 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info,
 			iwe.u.mode = IW_MODE_MASTER;
 		else
 			iwe.u.mode = IW_MODE_ADHOC;
-		current_ev = iwe_stream_add_event(info, current_ev, end_buf,
-						  &iwe, IW_EV_UINT_LEN);
-	}
-
-	buf = kmalloc(31, GFP_ATOMIC);
-	if (buf) {
-		memset(&iwe, 0, sizeof(iwe));
-		iwe.cmd = IWEVCUSTOM;
-		sprintf(buf, "tsf=%016llx", (unsigned long long)(ies->tsf));
-		iwe.u.data.length = strlen(buf);
-		current_ev = iwe_stream_add_point(info, current_ev, end_buf,
-						  &iwe, buf);
-		memset(&iwe, 0, sizeof(iwe));
-		iwe.cmd = IWEVCUSTOM;
-		sprintf(buf, " Last beacon: %ums ago",
-			elapsed_jiffies_msecs(bss->ts));
-		iwe.u.data.length = strlen(buf);
-		current_ev = iwe_stream_add_point(info, current_ev,
-						  end_buf, &iwe, buf);
-		kfree(buf);
+		current_ev = iwe_stream_add_event_check(info, current_ev,
+							end_buf, &iwe,
+							IW_EV_UINT_LEN);
+		if (IS_ERR(current_ev))
+			goto unlock;
 	}
 
-	ieee80211_scan_add_ies(info, ies, &current_ev, end_buf);
+	memset(&iwe, 0, sizeof(iwe));
+	iwe.cmd = IWEVCUSTOM;
+	sprintf(buf, "tsf=%016llx", (unsigned long long)(ies->tsf));
+	iwe.u.data.length = strlen(buf);
+	current_ev = iwe_stream_add_point_check(info, current_ev, end_buf,
+						&iwe, buf);
+	if (IS_ERR(current_ev))
+		goto unlock;
+	memset(&iwe, 0, sizeof(iwe));
+	iwe.cmd = IWEVCUSTOM;
+	sprintf(buf, " Last beacon: %ums ago",
+		elapsed_jiffies_msecs(bss->ts));
+	iwe.u.data.length = strlen(buf);
+	current_ev = iwe_stream_add_point_check(info, current_ev,
+						end_buf, &iwe, buf);
+	if (IS_ERR(current_ev))
+		goto unlock;
+
+	current_ev = ieee80211_scan_add_ies(info, ies, current_ev, end_buf);
+
+ unlock:
 	rcu_read_unlock();
-
 	return current_ev;
 }
 
@@ -1498,19 +1623,27 @@ static int ieee80211_scan_results(struct cfg80211_registered_device *rdev,
 	char *current_ev = buf;
 	char *end_buf = buf + len;
 	struct cfg80211_internal_bss *bss;
+	int err = 0;
 
 	spin_lock_bh(&rdev->bss_lock);
 	cfg80211_bss_expire(rdev);
 
 	list_for_each_entry(bss, &rdev->bss_list, list) {
 		if (buf + len - current_ev <= IW_EV_ADDR_LEN) {
-			spin_unlock_bh(&rdev->bss_lock);
-			return -E2BIG;
+			err = -E2BIG;
+			break;
 		}
 		current_ev = ieee80211_bss(&rdev->wiphy, info, bss,
 					   current_ev, end_buf);
+		if (IS_ERR(current_ev)) {
+			err = PTR_ERR(current_ev);
+			break;
+		}
 	}
 	spin_unlock_bh(&rdev->bss_lock);
+
+	if (err)
+		return err;
 	return current_ev - buf;
 }
 
@@ -1542,5 +1675,5 @@ int cfg80211_wext_giwscan(struct net_device *dev,
 
 	return res;
 }
-EXPORT_SYMBOL_GPL(cfg80211_wext_giwscan);
+EXPORT_WEXT_HANDLER(cfg80211_wext_giwscan);
 #endif
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index dc1668ff543b..d11454f87bac 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -42,7 +42,7 @@ struct cfg80211_conn {
 		CFG80211_CONN_CONNECTED,
 	} state;
 	u8 bssid[ETH_ALEN], prev_bssid[ETH_ALEN];
-	u8 *ie;
+	const u8 *ie;
 	size_t ie_len;
 	bool auto_auth, prev_bssid_valid;
 };
@@ -80,9 +80,18 @@ static int cfg80211_conn_scan(struct wireless_dev *wdev)
 	if (!request)
 		return -ENOMEM;
 
-	if (wdev->conn->params.channel)
+	if (wdev->conn->params.channel) {
+		enum ieee80211_band band = wdev->conn->params.channel->band;
+		struct ieee80211_supported_band *sband =
+			wdev->wiphy->bands[band];
+
+		if (!sband) {
+			kfree(request);
+			return -EINVAL;
+		}
 		request->channels[0] = wdev->conn->params.channel;
-	else {
+		request->rates[band] = (1 << sband->n_bitrates) - 1;
+	} else {
 		int i = 0, j;
 		enum ieee80211_band band;
 		struct ieee80211_supported_band *bands;
@@ -248,19 +257,15 @@ static struct cfg80211_bss *cfg80211_get_conn_bss(struct wireless_dev *wdev)
 {
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct cfg80211_bss *bss;
-	u16 capa = WLAN_CAPABILITY_ESS;
 
 	ASSERT_WDEV_LOCK(wdev);
 
-	if (wdev->conn->params.privacy)
-		capa |= WLAN_CAPABILITY_PRIVACY;
-
 	bss = cfg80211_get_bss(wdev->wiphy, wdev->conn->params.channel,
 			       wdev->conn->params.bssid,
 			       wdev->conn->params.ssid,
 			       wdev->conn->params.ssid_len,
-			       WLAN_CAPABILITY_ESS | WLAN_CAPABILITY_PRIVACY,
-			       capa);
+			       IEEE80211_BSS_TYPE_ESS,
+			       IEEE80211_PRIVACY(wdev->conn->params.privacy));
 	if (!bss)
 		return NULL;
 
@@ -418,6 +423,62 @@ void cfg80211_sme_assoc_timeout(struct wireless_dev *wdev)
 	schedule_work(&rdev->conn_work);
 }
 
+static int cfg80211_sme_get_conn_ies(struct wireless_dev *wdev,
+				     const u8 *ies, size_t ies_len,
+				     const u8 **out_ies, size_t *out_ies_len)
+{
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
+	u8 *buf;
+	size_t offs;
+
+	if (!rdev->wiphy.extended_capabilities_len ||
+	    (ies && cfg80211_find_ie(WLAN_EID_EXT_CAPABILITY, ies, ies_len))) {
+		*out_ies = kmemdup(ies, ies_len, GFP_KERNEL);
+		if (!*out_ies)
+			return -ENOMEM;
+		*out_ies_len = ies_len;
+		return 0;
+	}
+
+	buf = kmalloc(ies_len + rdev->wiphy.extended_capabilities_len + 2,
+		      GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	if (ies_len) {
+		static const u8 before_extcapa[] = {
+			/* not listing IEs expected to be created by driver */
+			WLAN_EID_RSN,
+			WLAN_EID_QOS_CAPA,
+			WLAN_EID_RRM_ENABLED_CAPABILITIES,
+			WLAN_EID_MOBILITY_DOMAIN,
+			WLAN_EID_SUPPORTED_REGULATORY_CLASSES,
+			WLAN_EID_BSS_COEX_2040,
+		};
+
+		offs = ieee80211_ie_split(ies, ies_len, before_extcapa,
+					  ARRAY_SIZE(before_extcapa), 0);
+		memcpy(buf, ies, offs);
+		/* leave a whole for extended capabilities IE */
+		memcpy(buf + offs + rdev->wiphy.extended_capabilities_len + 2,
+		       ies + offs, ies_len - offs);
+	} else {
+		offs = 0;
+	}
+
+	/* place extended capabilities IE (with only driver capabilities) */
+	buf[offs] = WLAN_EID_EXT_CAPABILITY;
+	buf[offs + 1] = rdev->wiphy.extended_capabilities_len;
+	memcpy(buf + offs + 2,
+	       rdev->wiphy.extended_capabilities,
+	       rdev->wiphy.extended_capabilities_len);
+
+	*out_ies = buf;
+	*out_ies_len = ies_len + rdev->wiphy.extended_capabilities_len + 2;
+
+	return 0;
+}
+
 static int cfg80211_sme_connect(struct wireless_dev *wdev,
 				struct cfg80211_connect_params *connect,
 				const u8 *prev_bssid)
@@ -448,16 +509,14 @@ static int cfg80211_sme_connect(struct wireless_dev *wdev,
 		memcpy(wdev->conn->bssid, connect->bssid, ETH_ALEN);
 	}
 
-	if (connect->ie) {
-		wdev->conn->ie = kmemdup(connect->ie, connect->ie_len,
-					GFP_KERNEL);
-		wdev->conn->params.ie = wdev->conn->ie;
-		if (!wdev->conn->ie) {
-			kfree(wdev->conn);
-			wdev->conn = NULL;
-			return -ENOMEM;
-		}
+	if (cfg80211_sme_get_conn_ies(wdev, connect->ie, connect->ie_len,
+				      &wdev->conn->ie,
+				      &wdev->conn->params.ie_len)) {
+		kfree(wdev->conn);
+		wdev->conn = NULL;
+		return -ENOMEM;
 	}
+	wdev->conn->params.ie = wdev->conn->ie;
 
 	if (connect->auth_type == NL80211_AUTHTYPE_AUTOMATIC) {
 		wdev->conn->auto_auth = true;
@@ -628,8 +687,8 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
 		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);
+				       IEEE80211_BSS_TYPE_ESS,
+				       IEEE80211_PRIVACY_ANY);
 		if (bss)
 			cfg80211_hold_bss(bss_from_pub(bss));
 	}
@@ -786,8 +845,8 @@ void cfg80211_roamed(struct net_device *dev,
 	struct cfg80211_bss *bss;
 
 	bss = cfg80211_get_bss(wdev->wiphy, channel, bssid, wdev->ssid,
-			       wdev->ssid_len, WLAN_CAPABILITY_ESS,
-			       WLAN_CAPABILITY_ESS);
+			       wdev->ssid_len,
+			       IEEE80211_BSS_TYPE_ESS, IEEE80211_PRIVACY_ANY);
 	if (WARN_ON(!bss))
 		return;
 
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 625a6e6d1168..af3617c9879e 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -7,6 +7,7 @@
 #include <linux/tracepoint.h>
 
 #include <linux/rtnetlink.h>
+#include <linux/etherdevice.h>
 #include <net/cfg80211.h>
 #include "core.h"
 
@@ -15,7 +16,7 @@
 	if (given_mac)						     \
 		memcpy(__entry->entry_mac, given_mac, ETH_ALEN);     \
 	else							     \
-		memset(__entry->entry_mac, 0, ETH_ALEN);	     \
+		eth_zero_addr(__entry->entry_mac);		     \
 	} while (0)
 #define MAC_PR_FMT "%pM"
 #define MAC_PR_ARG(entry_mac) (__entry->entry_mac)
@@ -600,6 +601,11 @@ DEFINE_EVENT(wiphy_netdev_evt, rdev_leave_ibss,
 	TP_ARGS(wiphy, netdev)
 );
 
+DEFINE_EVENT(wiphy_netdev_evt, rdev_leave_ocb,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev),
+	TP_ARGS(wiphy, netdev)
+);
+
 DEFINE_EVENT(wiphy_netdev_evt, rdev_flush_pmksa,
 	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev),
 	TP_ARGS(wiphy, netdev)
@@ -622,6 +628,7 @@ DECLARE_EVENT_CLASS(station_add_change,
 		__field(u8, plink_state)
 		__field(u8, uapsd_queues)
 		__array(u8, ht_capa, (int)sizeof(struct ieee80211_ht_cap))
+		__array(char, vlan, IFNAMSIZ)
 	),
 	TP_fast_assign(
 		WIPHY_ASSIGN;
@@ -639,16 +646,19 @@ DECLARE_EVENT_CLASS(station_add_change,
 		if (params->ht_capa)
 			memcpy(__entry->ht_capa, params->ht_capa,
 			       sizeof(struct ieee80211_ht_cap));
+		memset(__entry->vlan, 0, sizeof(__entry->vlan));
+		if (params->vlan)
+			memcpy(__entry->vlan, params->vlan->name, IFNAMSIZ);
 	),
 	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", station mac: " MAC_PR_FMT
 		  ", station flags mask: %u, station flags set: %u, "
 		  "station modify mask: %u, listen interval: %d, aid: %u, "
-		  "plink action: %u, plink state: %u, uapsd queues: %u",
+		  "plink action: %u, plink state: %u, uapsd queues: %u, vlan:%s",
 		  WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(sta_mac),
 		  __entry->sta_flags_mask, __entry->sta_flags_set,
 		  __entry->sta_modify_mask, __entry->listen_interval,
 		  __entry->aid, __entry->plink_action, __entry->plink_state,
-		  __entry->uapsd_queues)
+		  __entry->uapsd_queues, __entry->vlan)
 );
 
 DEFINE_EVENT(station_add_change, rdev_add_station,
@@ -680,9 +690,34 @@ DECLARE_EVENT_CLASS(wiphy_netdev_mac_evt,
 		  WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(sta_mac))
 );
 
-DEFINE_EVENT(wiphy_netdev_mac_evt, rdev_del_station,
-	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, const u8 *mac),
-	TP_ARGS(wiphy, netdev, mac)
+DECLARE_EVENT_CLASS(station_del,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+		 struct station_del_parameters *params),
+	TP_ARGS(wiphy, netdev, params),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		NETDEV_ENTRY
+		MAC_ENTRY(sta_mac)
+		__field(u8, subtype)
+		__field(u16, reason_code)
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		NETDEV_ASSIGN;
+		MAC_ASSIGN(sta_mac, params->mac);
+		__entry->subtype = params->subtype;
+		__entry->reason_code = params->reason_code;
+	),
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", station mac: " MAC_PR_FMT
+		  ", subtype: %u, reason_code: %u",
+		  WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(sta_mac),
+		  __entry->subtype, __entry->reason_code)
+);
+
+DEFINE_EVENT(station_del, rdev_del_station,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+		 struct station_del_parameters *params),
+	TP_ARGS(wiphy, netdev, params)
 );
 
 DEFINE_EVENT(wiphy_netdev_mac_evt, rdev_get_station,
@@ -801,6 +836,51 @@ TRACE_EVENT(rdev_dump_mpath,
 		  MAC_PR_ARG(next_hop))
 );
 
+TRACE_EVENT(rdev_get_mpp,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+		 u8 *dst, u8 *mpp),
+	TP_ARGS(wiphy, netdev, dst, mpp),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		NETDEV_ENTRY
+		MAC_ENTRY(dst)
+		MAC_ENTRY(mpp)
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		NETDEV_ASSIGN;
+		MAC_ASSIGN(dst, dst);
+		MAC_ASSIGN(mpp, mpp);
+	),
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", destination: " MAC_PR_FMT
+		  ", mpp: " MAC_PR_FMT, WIPHY_PR_ARG, NETDEV_PR_ARG,
+		  MAC_PR_ARG(dst), MAC_PR_ARG(mpp))
+);
+
+TRACE_EVENT(rdev_dump_mpp,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, int idx,
+		 u8 *dst, u8 *mpp),
+	TP_ARGS(wiphy, netdev, idx, mpp, dst),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		NETDEV_ENTRY
+		MAC_ENTRY(dst)
+		MAC_ENTRY(mpp)
+		__field(int, idx)
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		NETDEV_ASSIGN;
+		MAC_ASSIGN(dst, dst);
+		MAC_ASSIGN(mpp, mpp);
+		__entry->idx = idx;
+	),
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", index: %d, destination: "
+		  MAC_PR_FMT ", mpp: " MAC_PR_FMT,
+		  WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->idx, MAC_PR_ARG(dst),
+		  MAC_PR_ARG(mpp))
+);
+
 TRACE_EVENT(rdev_return_int_mpath_info,
 	TP_PROTO(struct wiphy *wiphy, int ret, struct mpath_info *pinfo),
 	TP_ARGS(wiphy, ret, pinfo),
@@ -1002,7 +1082,7 @@ TRACE_EVENT(rdev_auth,
 		if (req->bss)
 			MAC_ASSIGN(bssid, req->bss->bssid);
 		else
-			memset(__entry->bssid, 0, ETH_ALEN);
+			eth_zero_addr(__entry->bssid);
 		__entry->auth_type = req->auth_type;
 	),
 	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", auth type: %d, bssid: " MAC_PR_FMT,
@@ -1028,7 +1108,7 @@ TRACE_EVENT(rdev_assoc,
 		if (req->bss)
 			MAC_ASSIGN(bssid, req->bss->bssid);
 		else
-			memset(__entry->bssid, 0, ETH_ALEN);
+			eth_zero_addr(__entry->bssid);
 		MAC_ASSIGN(prev_bssid, req->prev_bssid);
 		__entry->use_mfp = req->use_mfp;
 		__entry->flags = req->flags;
@@ -1078,7 +1158,7 @@ TRACE_EVENT(rdev_disassoc,
 		if (req->bss)
 			MAC_ASSIGN(bssid, req->bss->bssid);
 		else
-			memset(__entry->bssid, 0, ETH_ALEN);
+			eth_zero_addr(__entry->bssid);
 		__entry->reason_code = req->reason_code;
 		__entry->local_state_change = req->local_state_change;
 	),
@@ -1246,6 +1326,22 @@ TRACE_EVENT(rdev_join_ibss,
 		  WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(bssid), __entry->ssid)
 );
 
+TRACE_EVENT(rdev_join_ocb,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+		 const struct ocb_setup *setup),
+	TP_ARGS(wiphy, netdev, setup),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		NETDEV_ENTRY
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		NETDEV_ASSIGN;
+	),
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT,
+		  WIPHY_PR_ARG, NETDEV_PR_ARG)
+);
+
 TRACE_EVENT(rdev_set_wiphy_params,
 	TP_PROTO(struct wiphy *wiphy, u32 changed),
 	TP_ARGS(wiphy, changed),
@@ -1513,11 +1609,12 @@ TRACE_EVENT(rdev_return_int_survey_info,
 		WIPHY_ENTRY
 		CHAN_ENTRY
 		__field(int, ret)
-		__field(u64, channel_time)
-		__field(u64, channel_time_busy)
-		__field(u64, channel_time_ext_busy)
-		__field(u64, channel_time_rx)
-		__field(u64, channel_time_tx)
+		__field(u64, time)
+		__field(u64, time_busy)
+		__field(u64, time_ext_busy)
+		__field(u64, time_rx)
+		__field(u64, time_tx)
+		__field(u64, time_scan)
 		__field(u32, filled)
 		__field(s8, noise)
 	),
@@ -1525,22 +1622,24 @@ TRACE_EVENT(rdev_return_int_survey_info,
 		WIPHY_ASSIGN;
 		CHAN_ASSIGN(info->channel);
 		__entry->ret = ret;
-		__entry->channel_time = info->channel_time;
-		__entry->channel_time_busy = info->channel_time_busy;
-		__entry->channel_time_ext_busy = info->channel_time_ext_busy;
-		__entry->channel_time_rx = info->channel_time_rx;
-		__entry->channel_time_tx = info->channel_time_tx;
+		__entry->time = info->time;
+		__entry->time_busy = info->time_busy;
+		__entry->time_ext_busy = info->time_ext_busy;
+		__entry->time_rx = info->time_rx;
+		__entry->time_tx = info->time_tx;
+		__entry->time_scan = info->time_scan;
 		__entry->filled = info->filled;
 		__entry->noise = info->noise;
 	),
 	TP_printk(WIPHY_PR_FMT ", returned: %d, " CHAN_PR_FMT
 		  ", channel time: %llu, channel time busy: %llu, "
 		  "channel time extension busy: %llu, channel time rx: %llu, "
-		  "channel time tx: %llu, filled: %u, noise: %d",
+		  "channel time tx: %llu, scan time: %llu, filled: %u, noise: %d",
 		  WIPHY_PR_ARG, __entry->ret, CHAN_PR_ARG,
-		  __entry->channel_time, __entry->channel_time_busy,
-		  __entry->channel_time_ext_busy, __entry->channel_time_rx,
-		  __entry->channel_time_tx, __entry->filled, __entry->noise)
+		  __entry->time, __entry->time_busy,
+		  __entry->time_ext_busy, __entry->time_rx,
+		  __entry->time_tx, __entry->time_scan,
+		  __entry->filled, __entry->noise)
 );
 
 TRACE_EVENT(rdev_tdls_oper,
@@ -1941,6 +2040,48 @@ TRACE_EVENT(rdev_del_tx_ts,
 		  WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(peer), __entry->tsid)
 );
 
+TRACE_EVENT(rdev_tdls_channel_switch,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+		 const u8 *addr, u8 oper_class,
+		 struct cfg80211_chan_def *chandef),
+	TP_ARGS(wiphy, netdev, addr, oper_class, chandef),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		NETDEV_ENTRY
+		MAC_ENTRY(addr)
+		__field(u8, oper_class)
+		CHAN_DEF_ENTRY
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		NETDEV_ASSIGN;
+		MAC_ASSIGN(addr, addr);
+		CHAN_DEF_ASSIGN(chandef);
+	),
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " MAC_PR_FMT
+		  " oper class %d, " CHAN_DEF_PR_FMT,
+		  WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(addr),
+		  __entry->oper_class, CHAN_DEF_PR_ARG)
+);
+
+TRACE_EVENT(rdev_tdls_cancel_channel_switch,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+		 const u8 *addr),
+	TP_ARGS(wiphy, netdev, addr),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		NETDEV_ENTRY
+		MAC_ENTRY(addr)
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		NETDEV_ASSIGN;
+		MAC_ASSIGN(addr, addr);
+	),
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " MAC_PR_FMT,
+		  WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(addr))
+);
+
 /*************************************************************
  *	     cfg80211 exported functions traces		     *
  *************************************************************/
@@ -2264,6 +2405,22 @@ TRACE_EVENT(cfg80211_ch_switch_notify,
 		  NETDEV_PR_ARG, CHAN_DEF_PR_ARG)
 );
 
+TRACE_EVENT(cfg80211_ch_switch_started_notify,
+	TP_PROTO(struct net_device *netdev,
+		 struct cfg80211_chan_def *chandef),
+	TP_ARGS(netdev, chandef),
+	TP_STRUCT__entry(
+		NETDEV_ENTRY
+		CHAN_DEF_ENTRY
+	),
+	TP_fast_assign(
+		NETDEV_ASSIGN;
+		CHAN_DEF_ASSIGN(chandef);
+	),
+	TP_printk(NETDEV_PR_FMT ", " CHAN_DEF_PR_FMT,
+		  NETDEV_PR_ARG, CHAN_DEF_PR_ARG)
+);
+
 TRACE_EVENT(cfg80211_radar_event,
 	TP_PROTO(struct wiphy *wiphy, struct cfg80211_chan_def *chandef),
 	TP_ARGS(wiphy, chandef),
@@ -2484,28 +2641,30 @@ DEFINE_EVENT(wiphy_only_evt, cfg80211_sched_scan_stopped,
 TRACE_EVENT(cfg80211_get_bss,
 	TP_PROTO(struct wiphy *wiphy, struct ieee80211_channel *channel,
 		 const u8 *bssid, const u8 *ssid, size_t ssid_len,
-		 u16 capa_mask, u16 capa_val),
-	TP_ARGS(wiphy, channel, bssid, ssid, ssid_len, capa_mask, capa_val),
+		 enum ieee80211_bss_type bss_type,
+		 enum ieee80211_privacy privacy),
+	TP_ARGS(wiphy, channel, bssid, ssid, ssid_len, bss_type, privacy),
 	TP_STRUCT__entry(
 		WIPHY_ENTRY
 		CHAN_ENTRY
 		MAC_ENTRY(bssid)
 		__dynamic_array(u8, ssid, ssid_len)
-		__field(u16, capa_mask)
-		__field(u16, capa_val)
+		__field(enum ieee80211_bss_type, bss_type)
+		__field(enum ieee80211_privacy, privacy)
 	),
 	TP_fast_assign(
 		WIPHY_ASSIGN;
 		CHAN_ASSIGN(channel);
 		MAC_ASSIGN(bssid, bssid);
 		memcpy(__get_dynamic_array(ssid), ssid, ssid_len);
-		__entry->capa_mask = capa_mask;
-		__entry->capa_val = capa_val;
-	),
-	TP_printk(WIPHY_PR_FMT ", " CHAN_PR_FMT ", " MAC_PR_FMT ", buf: %#.2x, "
-		  "capa_mask: %d, capa_val: %u", WIPHY_PR_ARG, CHAN_PR_ARG,
-		  MAC_PR_ARG(bssid), ((u8 *)__get_dynamic_array(ssid))[0],
-		  __entry->capa_mask, __entry->capa_val)
+		__entry->bss_type = bss_type;
+		__entry->privacy = privacy;
+	),
+	TP_printk(WIPHY_PR_FMT ", " CHAN_PR_FMT ", " MAC_PR_FMT
+		  ", buf: %#.2x, bss_type: %d, privacy: %d",
+		  WIPHY_PR_ARG, CHAN_PR_ARG, MAC_PR_ARG(bssid),
+		  ((u8 *)__get_dynamic_array(ssid))[0], __entry->bss_type,
+		  __entry->privacy)
 );
 
 TRACE_EVENT(cfg80211_inform_bss_width_frame,
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 5e233a577d0f..70051ab52f4f 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -227,18 +227,32 @@ int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev,
 	if (pairwise && !mac_addr)
 		return -EINVAL;
 
-	/*
-	 * Disallow pairwise keys with non-zero index unless it's WEP
-	 * or a vendor specific cipher (because current deployments use
-	 * pairwise WEP keys with non-zero indices and for vendor specific
-	 * ciphers this should be validated in the driver or hardware level
-	 * - but 802.11i clearly specifies to use zero)
-	 */
-	if (pairwise && key_idx &&
-	    ((params->cipher == WLAN_CIPHER_SUITE_TKIP) ||
-	     (params->cipher == WLAN_CIPHER_SUITE_CCMP) ||
-	     (params->cipher == WLAN_CIPHER_SUITE_AES_CMAC)))
-		return -EINVAL;
+	switch (params->cipher) {
+	case WLAN_CIPHER_SUITE_TKIP:
+	case WLAN_CIPHER_SUITE_CCMP:
+	case WLAN_CIPHER_SUITE_CCMP_256:
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		/* Disallow pairwise keys with non-zero index unless it's WEP
+		 * or a vendor specific cipher (because current deployments use
+		 * pairwise WEP keys with non-zero indices and for vendor
+		 * specific ciphers this should be validated in the driver or
+		 * hardware level - but 802.11i clearly specifies to use zero)
+		 */
+		if (pairwise && key_idx)
+			return -EINVAL;
+		break;
+	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		/* Disallow BIP (group-only) cipher as pairwise cipher */
+		if (pairwise)
+			return -EINVAL;
+		break;
+	default:
+		break;
+	}
 
 	switch (params->cipher) {
 	case WLAN_CIPHER_SUITE_WEP40:
@@ -253,6 +267,18 @@ int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev,
 		if (params->key_len != WLAN_KEY_LEN_CCMP)
 			return -EINVAL;
 		break;
+	case WLAN_CIPHER_SUITE_CCMP_256:
+		if (params->key_len != WLAN_KEY_LEN_CCMP_256)
+			return -EINVAL;
+		break;
+	case WLAN_CIPHER_SUITE_GCMP:
+		if (params->key_len != WLAN_KEY_LEN_GCMP)
+			return -EINVAL;
+		break;
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		if (params->key_len != WLAN_KEY_LEN_GCMP_256)
+			return -EINVAL;
+		break;
 	case WLAN_CIPHER_SUITE_WEP104:
 		if (params->key_len != WLAN_KEY_LEN_WEP104)
 			return -EINVAL;
@@ -261,6 +287,18 @@ int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev,
 		if (params->key_len != WLAN_KEY_LEN_AES_CMAC)
 			return -EINVAL;
 		break;
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
+		if (params->key_len != WLAN_KEY_LEN_BIP_CMAC_256)
+			return -EINVAL;
+		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+		if (params->key_len != WLAN_KEY_LEN_BIP_GMAC_128)
+			return -EINVAL;
+		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		if (params->key_len != WLAN_KEY_LEN_BIP_GMAC_256)
+			return -EINVAL;
+		break;
 	default:
 		/*
 		 * We don't know anything about this algorithm,
@@ -280,7 +318,13 @@ int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev,
 			return -EINVAL;
 		case WLAN_CIPHER_SUITE_TKIP:
 		case WLAN_CIPHER_SUITE_CCMP:
+		case WLAN_CIPHER_SUITE_CCMP_256:
+		case WLAN_CIPHER_SUITE_GCMP:
+		case WLAN_CIPHER_SUITE_GCMP_256:
 		case WLAN_CIPHER_SUITE_AES_CMAC:
+		case WLAN_CIPHER_SUITE_BIP_CMAC_256:
+		case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+		case WLAN_CIPHER_SUITE_BIP_GMAC_256:
 			if (params->seq_len != 6)
 				return -EINVAL;
 			break;
@@ -308,6 +352,12 @@ unsigned int __attribute_const__ ieee80211_hdrlen(__le16 fc)
 		goto out;
 	}
 
+	if (ieee80211_is_mgmt(fc)) {
+		if (ieee80211_has_order(fc))
+			hdrlen += IEEE80211_HT_CTL_LEN;
+		goto out;
+	}
+
 	if (ieee80211_is_ctl(fc)) {
 		/*
 		 * ACK and CTS are 10 bytes, all others 16. To see how
@@ -442,7 +492,8 @@ int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr,
 		break;
 	case cpu_to_le16(0):
 		if (iftype != NL80211_IFTYPE_ADHOC &&
-		    iftype != NL80211_IFTYPE_STATION)
+		    iftype != NL80211_IFTYPE_STATION &&
+		    iftype != NL80211_IFTYPE_OCB)
 				return -1;
 		break;
 	}
@@ -519,6 +570,7 @@ int ieee80211_data_from_8023(struct sk_buff *skb, const u8 *addr,
 		memcpy(hdr.addr3, skb->data, ETH_ALEN);
 		hdrlen = 24;
 		break;
+	case NL80211_IFTYPE_OCB:
 	case NL80211_IFTYPE_ADHOC:
 		/* DA SA BSSID */
 		memcpy(hdr.addr1, skb->data, ETH_ALEN);
@@ -706,8 +758,8 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb,
 	if (skb->priority >= 256 && skb->priority <= 263)
 		return skb->priority - 256;
 
-	if (vlan_tx_tag_present(skb)) {
-		vlan_priority = (vlan_tx_tag_get(skb) & VLAN_PRIO_MASK)
+	if (skb_vlan_tag_present(skb)) {
+		vlan_priority = (skb_vlan_tag_get(skb) & VLAN_PRIO_MASK)
 			>> VLAN_PRIO_SHIFT;
 		if (vlan_priority > 0)
 			return vlan_priority;
@@ -937,6 +989,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev,
 			if (dev->ieee80211_ptr->use_4addr)
 				break;
 			/* fall through */
+		case NL80211_IFTYPE_OCB:
 		case NL80211_IFTYPE_P2P_CLIENT:
 		case NL80211_IFTYPE_ADHOC:
 			dev->priv_flags |= IFF_DONT_BRIDGE;
@@ -1070,10 +1123,24 @@ static u32 cfg80211_calculate_bitrate_vht(struct rate_info *rate)
 	if (WARN_ON_ONCE(rate->mcs > 9))
 		return 0;
 
-	idx = rate->flags & (RATE_INFO_FLAGS_160_MHZ_WIDTH |
-			     RATE_INFO_FLAGS_80P80_MHZ_WIDTH) ? 3 :
-		  rate->flags & RATE_INFO_FLAGS_80_MHZ_WIDTH ? 2 :
-		  rate->flags & RATE_INFO_FLAGS_40_MHZ_WIDTH ? 1 : 0;
+	switch (rate->bw) {
+	case RATE_INFO_BW_160:
+		idx = 3;
+		break;
+	case RATE_INFO_BW_80:
+		idx = 2;
+		break;
+	case RATE_INFO_BW_40:
+		idx = 1;
+		break;
+	case RATE_INFO_BW_5:
+	case RATE_INFO_BW_10:
+	default:
+		WARN_ON(1);
+		/* fall through */
+	case RATE_INFO_BW_20:
+		idx = 0;
+	}
 
 	bitrate = base[idx][rate->mcs];
 	bitrate *= rate->nss;
@@ -1104,8 +1171,7 @@ u32 cfg80211_calculate_bitrate(struct rate_info *rate)
 	modulation = rate->mcs & 7;
 	streams = (rate->mcs >> 3) + 1;
 
-	bitrate = (rate->flags & RATE_INFO_FLAGS_40_MHZ_WIDTH) ?
-			13500000 : 6500000;
+	bitrate = (rate->bw == RATE_INFO_BW_40) ? 13500000 : 6500000;
 
 	if (modulation < 4)
 		bitrate *= (modulation + 1);
@@ -1224,12 +1290,54 @@ int cfg80211_get_p2p_attr(const u8 *ies, unsigned int len,
 }
 EXPORT_SYMBOL(cfg80211_get_p2p_attr);
 
+static bool ieee80211_id_in_list(const u8 *ids, int n_ids, u8 id)
+{
+	int i;
+
+	for (i = 0; i < n_ids; i++)
+		if (ids[i] == id)
+			return true;
+	return false;
+}
+
+size_t ieee80211_ie_split_ric(const u8 *ies, size_t ielen,
+			      const u8 *ids, int n_ids,
+			      const u8 *after_ric, int n_after_ric,
+			      size_t offset)
+{
+	size_t pos = offset;
+
+	while (pos < ielen && ieee80211_id_in_list(ids, n_ids, ies[pos])) {
+		if (ies[pos] == WLAN_EID_RIC_DATA && n_after_ric) {
+			pos += 2 + ies[pos + 1];
+
+			while (pos < ielen &&
+			       !ieee80211_id_in_list(after_ric, n_after_ric,
+						     ies[pos]))
+				pos += 2 + ies[pos + 1];
+		} else {
+			pos += 2 + ies[pos + 1];
+		}
+	}
+
+	return pos;
+}
+EXPORT_SYMBOL(ieee80211_ie_split_ric);
+
+size_t ieee80211_ie_split(const u8 *ies, size_t ielen,
+			  const u8 *ids, int n_ids, size_t offset)
+{
+	return ieee80211_ie_split_ric(ies, ielen, ids, n_ids, NULL, 0, offset);
+}
+EXPORT_SYMBOL(ieee80211_ie_split);
+
 bool ieee80211_operating_class_to_band(u8 operating_class,
 				       enum ieee80211_band *band)
 {
 	switch (operating_class) {
 	case 112:
 	case 115 ... 127:
+	case 128 ... 130:
 		*band = IEEE80211_BAND_5GHZ;
 		return true;
 	case 81:
@@ -1247,6 +1355,135 @@ bool ieee80211_operating_class_to_band(u8 operating_class,
 }
 EXPORT_SYMBOL(ieee80211_operating_class_to_band);
 
+bool ieee80211_chandef_to_operating_class(struct cfg80211_chan_def *chandef,
+					  u8 *op_class)
+{
+	u8 vht_opclass;
+	u16 freq = chandef->center_freq1;
+
+	if (freq >= 2412 && freq <= 2472) {
+		if (chandef->width > NL80211_CHAN_WIDTH_40)
+			return false;
+
+		/* 2.407 GHz, channels 1..13 */
+		if (chandef->width == NL80211_CHAN_WIDTH_40) {
+			if (freq > chandef->chan->center_freq)
+				*op_class = 83; /* HT40+ */
+			else
+				*op_class = 84; /* HT40- */
+		} else {
+			*op_class = 81;
+		}
+
+		return true;
+	}
+
+	if (freq == 2484) {
+		if (chandef->width > NL80211_CHAN_WIDTH_40)
+			return false;
+
+		*op_class = 82; /* channel 14 */
+		return true;
+	}
+
+	switch (chandef->width) {
+	case NL80211_CHAN_WIDTH_80:
+		vht_opclass = 128;
+		break;
+	case NL80211_CHAN_WIDTH_160:
+		vht_opclass = 129;
+		break;
+	case NL80211_CHAN_WIDTH_80P80:
+		vht_opclass = 130;
+		break;
+	case NL80211_CHAN_WIDTH_10:
+	case NL80211_CHAN_WIDTH_5:
+		return false; /* unsupported for now */
+	default:
+		vht_opclass = 0;
+		break;
+	}
+
+	/* 5 GHz, channels 36..48 */
+	if (freq >= 5180 && freq <= 5240) {
+		if (vht_opclass) {
+			*op_class = vht_opclass;
+		} else if (chandef->width == NL80211_CHAN_WIDTH_40) {
+			if (freq > chandef->chan->center_freq)
+				*op_class = 116;
+			else
+				*op_class = 117;
+		} else {
+			*op_class = 115;
+		}
+
+		return true;
+	}
+
+	/* 5 GHz, channels 52..64 */
+	if (freq >= 5260 && freq <= 5320) {
+		if (vht_opclass) {
+			*op_class = vht_opclass;
+		} else if (chandef->width == NL80211_CHAN_WIDTH_40) {
+			if (freq > chandef->chan->center_freq)
+				*op_class = 119;
+			else
+				*op_class = 120;
+		} else {
+			*op_class = 118;
+		}
+
+		return true;
+	}
+
+	/* 5 GHz, channels 100..144 */
+	if (freq >= 5500 && freq <= 5720) {
+		if (vht_opclass) {
+			*op_class = vht_opclass;
+		} else if (chandef->width == NL80211_CHAN_WIDTH_40) {
+			if (freq > chandef->chan->center_freq)
+				*op_class = 122;
+			else
+				*op_class = 123;
+		} else {
+			*op_class = 121;
+		}
+
+		return true;
+	}
+
+	/* 5 GHz, channels 149..169 */
+	if (freq >= 5745 && freq <= 5845) {
+		if (vht_opclass) {
+			*op_class = vht_opclass;
+		} else if (chandef->width == NL80211_CHAN_WIDTH_40) {
+			if (freq > chandef->chan->center_freq)
+				*op_class = 126;
+			else
+				*op_class = 127;
+		} else if (freq <= 5805) {
+			*op_class = 124;
+		} else {
+			*op_class = 125;
+		}
+
+		return true;
+	}
+
+	/* 56.16 GHz, channel 1..4 */
+	if (freq >= 56160 + 2160 * 1 && freq <= 56160 + 2160 * 4) {
+		if (chandef->width >= NL80211_CHAN_WIDTH_40)
+			return false;
+
+		*op_class = 180;
+		return true;
+	}
+
+	/* not supported yet */
+	return false;
+}
+EXPORT_SYMBOL(ieee80211_chandef_to_operating_class);
+
 int cfg80211_validate_beacon_int(struct cfg80211_registered_device *rdev,
 				 u32 beacon_int)
 {
diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c
index 0f47948c572f..fd682832a0e3 100644
--- a/net/wireless/wext-compat.c
+++ b/net/wireless/wext-compat.c
@@ -63,7 +63,7 @@ int cfg80211_wext_giwname(struct net_device *dev,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(cfg80211_wext_giwname);
+EXPORT_WEXT_HANDLER(cfg80211_wext_giwname);
 
 int cfg80211_wext_siwmode(struct net_device *dev, struct iw_request_info *info,
 			  u32 *mode, char *extra)
@@ -99,7 +99,7 @@ int cfg80211_wext_siwmode(struct net_device *dev, struct iw_request_info *info,
 
 	return cfg80211_change_iface(rdev, dev, type, NULL, &vifparams);
 }
-EXPORT_SYMBOL_GPL(cfg80211_wext_siwmode);
+EXPORT_WEXT_HANDLER(cfg80211_wext_siwmode);
 
 int cfg80211_wext_giwmode(struct net_device *dev, struct iw_request_info *info,
 			  u32 *mode, char *extra)
@@ -134,7 +134,7 @@ int cfg80211_wext_giwmode(struct net_device *dev, struct iw_request_info *info,
 	}
 	return 0;
 }
-EXPORT_SYMBOL_GPL(cfg80211_wext_giwmode);
+EXPORT_WEXT_HANDLER(cfg80211_wext_giwmode);
 
 
 int cfg80211_wext_giwrange(struct net_device *dev,
@@ -248,7 +248,7 @@ int cfg80211_wext_giwrange(struct net_device *dev,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(cfg80211_wext_giwrange);
+EXPORT_WEXT_HANDLER(cfg80211_wext_giwrange);
 
 
 /**
@@ -303,7 +303,7 @@ int cfg80211_wext_siwrts(struct net_device *dev,
 
 	return err;
 }
-EXPORT_SYMBOL_GPL(cfg80211_wext_siwrts);
+EXPORT_WEXT_HANDLER(cfg80211_wext_siwrts);
 
 int cfg80211_wext_giwrts(struct net_device *dev,
 			 struct iw_request_info *info,
@@ -317,7 +317,7 @@ int cfg80211_wext_giwrts(struct net_device *dev,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(cfg80211_wext_giwrts);
+EXPORT_WEXT_HANDLER(cfg80211_wext_giwrts);
 
 int cfg80211_wext_siwfrag(struct net_device *dev,
 			  struct iw_request_info *info,
@@ -343,7 +343,7 @@ int cfg80211_wext_siwfrag(struct net_device *dev,
 
 	return err;
 }
-EXPORT_SYMBOL_GPL(cfg80211_wext_siwfrag);
+EXPORT_WEXT_HANDLER(cfg80211_wext_siwfrag);
 
 int cfg80211_wext_giwfrag(struct net_device *dev,
 			  struct iw_request_info *info,
@@ -357,7 +357,7 @@ int cfg80211_wext_giwfrag(struct net_device *dev,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(cfg80211_wext_giwfrag);
+EXPORT_WEXT_HANDLER(cfg80211_wext_giwfrag);
 
 static int cfg80211_wext_siwretry(struct net_device *dev,
 				  struct iw_request_info *info,
@@ -427,7 +427,7 @@ int cfg80211_wext_giwretry(struct net_device *dev,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(cfg80211_wext_giwretry);
+EXPORT_WEXT_HANDLER(cfg80211_wext_giwretry);
 
 static int __cfg80211_set_encryption(struct cfg80211_registered_device *rdev,
 				     struct net_device *dev, bool pairwise,
@@ -1300,7 +1300,7 @@ static int cfg80211_wext_giwrate(struct net_device *dev,
 	if (err)
 		return err;
 
-	if (!(sinfo.filled & STATION_INFO_TX_BITRATE))
+	if (!(sinfo.filled & BIT(NL80211_STA_INFO_TX_BITRATE)))
 		return -EOPNOTSUPP;
 
 	rate->value = 100000 * cfg80211_calculate_bitrate(&sinfo.txrate);
@@ -1333,6 +1333,8 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev)
 	memcpy(bssid, wdev->current_bss->pub.bssid, ETH_ALEN);
 	wdev_unlock(wdev);
 
+	memset(&sinfo, 0, sizeof(sinfo));
+
 	if (rdev_get_station(rdev, dev, bssid, &sinfo))
 		return NULL;
 
@@ -1340,7 +1342,7 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev)
 
 	switch (rdev->wiphy.signal_type) {
 	case CFG80211_SIGNAL_TYPE_MBM:
-		if (sinfo.filled & STATION_INFO_SIGNAL) {
+		if (sinfo.filled & BIT(NL80211_STA_INFO_SIGNAL)) {
 			int sig = sinfo.signal;
 			wstats.qual.updated |= IW_QUAL_LEVEL_UPDATED;
 			wstats.qual.updated |= IW_QUAL_QUAL_UPDATED;
@@ -1354,7 +1356,7 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev)
 			break;
 		}
 	case CFG80211_SIGNAL_TYPE_UNSPEC:
-		if (sinfo.filled & STATION_INFO_SIGNAL) {
+		if (sinfo.filled & BIT(NL80211_STA_INFO_SIGNAL)) {
 			wstats.qual.updated |= IW_QUAL_LEVEL_UPDATED;
 			wstats.qual.updated |= IW_QUAL_QUAL_UPDATED;
 			wstats.qual.level = sinfo.signal;
@@ -1367,9 +1369,9 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev)
 	}
 
 	wstats.qual.updated |= IW_QUAL_NOISE_INVALID;
-	if (sinfo.filled & STATION_INFO_RX_DROP_MISC)
+	if (sinfo.filled & BIT(NL80211_STA_INFO_RX_DROP_MISC))
 		wstats.discard.misc = sinfo.rx_dropped_misc;
-	if (sinfo.filled & STATION_INFO_TX_FAILED)
+	if (sinfo.filled & BIT(NL80211_STA_INFO_TX_FAILED))
 		wstats.discard.retries = sinfo.tx_failed;
 
 	return &wstats;
diff --git a/net/wireless/wext-compat.h b/net/wireless/wext-compat.h
index ebcacca2f731..94c7405a5413 100644
--- a/net/wireless/wext-compat.h
+++ b/net/wireless/wext-compat.h
@@ -4,6 +4,12 @@
 #include <net/iw_handler.h>
 #include <linux/wireless.h>
 
+#ifdef CONFIG_CFG80211_WEXT_EXPORT
+#define EXPORT_WEXT_HANDLER(h) EXPORT_SYMBOL_GPL(h)
+#else
+#define EXPORT_WEXT_HANDLER(h)
+#endif /* CONFIG_CFG80211_WEXT_EXPORT */
+
 int cfg80211_ibss_wext_siwfreq(struct net_device *dev,
 			       struct iw_request_info *info,
 			       struct iw_freq *freq, char *extra);
diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c
index 368611c05739..a4e8af3321d2 100644
--- a/net/wireless/wext-sme.c
+++ b/net/wireless/wext-sme.c
@@ -322,7 +322,7 @@ int cfg80211_mgd_wext_giwap(struct net_device *dev,
 	if (wdev->current_bss)
 		memcpy(ap_addr->sa_data, wdev->current_bss->pub.bssid, ETH_ALEN);
 	else
-		memset(ap_addr->sa_data, 0, ETH_ALEN);
+		eth_zero_addr(ap_addr->sa_data);
 	wdev_unlock(wdev);
 
 	return 0;
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 5ad4418ef093..c3ab230e4493 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -1077,8 +1077,7 @@ out_clear_request:
 	goto out;
 }
 
-static int x25_sendmsg(struct kiocb *iocb, struct socket *sock,
-		       struct msghdr *msg, size_t len)
+static int x25_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 {
 	struct sock *sk = sock->sk;
 	struct x25_sock *x25 = x25_sk(sk);
@@ -1170,7 +1169,7 @@ static int x25_sendmsg(struct kiocb *iocb, struct socket *sock,
 	skb_reset_transport_header(skb);
 	skb_put(skb, len);
 
-	rc = memcpy_fromiovec(skb_transport_header(skb), msg->msg_iov, len);
+	rc = memcpy_from_msg(skb_transport_header(skb), msg, len);
 	if (rc)
 		goto out_kfree_skb;
 
@@ -1252,8 +1251,7 @@ out_kfree_skb:
 }
 
 
-static int x25_recvmsg(struct kiocb *iocb, struct socket *sock,
-		       struct msghdr *msg, size_t size,
+static int x25_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 		       int flags)
 {
 	struct sock *sk = sock->sk;
@@ -1335,7 +1333,7 @@ static int x25_recvmsg(struct kiocb *iocb, struct socket *sock,
 	/* Currently, each datagram always contains a complete record */
 	msg->msg_flags |= MSG_EOR;
 
-	rc = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	rc = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (rc)
 		goto out_free_dgram;
 
diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c
index debe733386f8..42f7c76cf853 100644
--- a/net/xfrm/xfrm_algo.c
+++ b/net/xfrm/xfrm_algo.c
@@ -31,6 +31,7 @@ static struct xfrm_algo_desc aead_list[] = {
 
 	.uinfo = {
 		.aead = {
+			.geniv = "seqniv",
 			.icv_truncbits = 64,
 		}
 	},
@@ -49,6 +50,7 @@ static struct xfrm_algo_desc aead_list[] = {
 
 	.uinfo = {
 		.aead = {
+			.geniv = "seqniv",
 			.icv_truncbits = 96,
 		}
 	},
@@ -67,6 +69,7 @@ static struct xfrm_algo_desc aead_list[] = {
 
 	.uinfo = {
 		.aead = {
+			.geniv = "seqniv",
 			.icv_truncbits = 128,
 		}
 	},
@@ -85,6 +88,7 @@ static struct xfrm_algo_desc aead_list[] = {
 
 	.uinfo = {
 		.aead = {
+			.geniv = "seqniv",
 			.icv_truncbits = 64,
 		}
 	},
@@ -103,6 +107,7 @@ static struct xfrm_algo_desc aead_list[] = {
 
 	.uinfo = {
 		.aead = {
+			.geniv = "seqniv",
 			.icv_truncbits = 96,
 		}
 	},
@@ -121,6 +126,7 @@ static struct xfrm_algo_desc aead_list[] = {
 
 	.uinfo = {
 		.aead = {
+			.geniv = "seqniv",
 			.icv_truncbits = 128,
 		}
 	},
@@ -139,6 +145,7 @@ static struct xfrm_algo_desc aead_list[] = {
 
 	.uinfo = {
 		.aead = {
+			.geniv = "seqiv",
 			.icv_truncbits = 128,
 		}
 	},
@@ -152,6 +159,18 @@ static struct xfrm_algo_desc aead_list[] = {
 		.sadb_alg_maxbits = 256
 	}
 },
+{
+	.name = "rfc7539esp(chacha20,poly1305)",
+
+	.uinfo = {
+		.aead = {
+			.geniv = "seqniv",
+			.icv_truncbits = 128,
+		}
+	},
+
+	.pfkey_supported = 0,
+},
 };
 
 static struct xfrm_algo_desc aalg_list[] = {
@@ -353,6 +372,7 @@ static struct xfrm_algo_desc ealg_list[] = {
 
 	.uinfo = {
 		.encr = {
+			.geniv = "echainiv",
 			.blockbits = 64,
 			.defkeybits = 64,
 		}
@@ -373,6 +393,7 @@ static struct xfrm_algo_desc ealg_list[] = {
 
 	.uinfo = {
 		.encr = {
+			.geniv = "echainiv",
 			.blockbits = 64,
 			.defkeybits = 192,
 		}
@@ -393,6 +414,7 @@ static struct xfrm_algo_desc ealg_list[] = {
 
 	.uinfo = {
 		.encr = {
+			.geniv = "echainiv",
 			.blockbits = 64,
 			.defkeybits = 128,
 		}
@@ -413,6 +435,7 @@ static struct xfrm_algo_desc ealg_list[] = {
 
 	.uinfo = {
 		.encr = {
+			.geniv = "echainiv",
 			.blockbits = 64,
 			.defkeybits = 128,
 		}
@@ -433,6 +456,7 @@ static struct xfrm_algo_desc ealg_list[] = {
 
 	.uinfo = {
 		.encr = {
+			.geniv = "echainiv",
 			.blockbits = 128,
 			.defkeybits = 128,
 		}
@@ -453,6 +477,7 @@ static struct xfrm_algo_desc ealg_list[] = {
 
 	.uinfo = {
 		.encr = {
+			.geniv = "echainiv",
 			.blockbits = 128,
 			.defkeybits = 128,
 		}
@@ -473,6 +498,7 @@ static struct xfrm_algo_desc ealg_list[] = {
 
 	.uinfo = {
 		.encr = {
+			.geniv = "echainiv",
 			.blockbits = 128,
 			.defkeybits = 128,
 		}
@@ -493,6 +519,7 @@ static struct xfrm_algo_desc ealg_list[] = {
 
 	.uinfo = {
 		.encr = {
+			.geniv = "echainiv",
 			.blockbits = 128,
 			.defkeybits = 128,
 		}
@@ -512,6 +539,7 @@ static struct xfrm_algo_desc ealg_list[] = {
 
 	.uinfo = {
 		.encr = {
+			.geniv = "seqiv",
 			.blockbits = 128,
 			.defkeybits = 160, /* 128-bit key + 32-bit nonce */
 		}
@@ -561,11 +589,6 @@ static struct xfrm_algo_desc calg_list[] = {
 },
 };
 
-static inline int aead_entries(void)
-{
-	return ARRAY_SIZE(aead_list);
-}
-
 static inline int aalg_entries(void)
 {
 	return ARRAY_SIZE(aalg_list);
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 85d1d4764612..b58286ecd156 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -13,6 +13,8 @@
 #include <net/dst.h>
 #include <net/ip.h>
 #include <net/xfrm.h>
+#include <net/ip_tunnels.h>
+#include <net/ip6_tunnel.h>
 
 static struct kmem_cache *secpath_cachep __read_mostly;
 
@@ -186,6 +188,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 	struct xfrm_state *x = NULL;
 	xfrm_address_t *daddr;
 	struct xfrm_mode *inner_mode;
+	u32 mark = skb->mark;
 	unsigned int family;
 	int decaps = 0;
 	int async = 0;
@@ -203,6 +206,18 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 				   XFRM_SPI_SKB_CB(skb)->daddroff);
 	family = XFRM_SPI_SKB_CB(skb)->family;
 
+	/* if tunnel is present override skb->mark value with tunnel i_key */
+	if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4) {
+		switch (family) {
+		case AF_INET:
+			mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4->parms.i_key);
+			break;
+		case AF_INET6:
+			mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6->parms.i_key);
+			break;
+		}
+	}
+
 	/* Allocate new secpath or COW existing one. */
 	if (!skb->sp || atomic_read(&skb->sp->refcnt) != 1) {
 		struct sec_path *sp;
@@ -229,7 +244,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 			goto drop;
 		}
 
-		x = xfrm_state_lookup(net, skb->mark, daddr, spi, nexthdr, family);
+		x = xfrm_state_lookup(net, mark, daddr, spi, nexthdr, family);
 		if (x == NULL) {
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES);
 			xfrm_audit_state_notfound(skb, family, spi, seq);
@@ -238,11 +253,6 @@ 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);
@@ -271,6 +281,11 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 
 		spin_unlock(&x->lock);
 
+		if (xfrm_tunnel_check(skb, x, family)) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR);
+			goto drop;
+		}
+
 		seq_hi = htonl(xfrm_replay_seqhi(x, seq));
 
 		XFRM_SKB_CB(skb)->seq.input.low = seq;
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 7c532856b398..fbcedbe33190 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -19,7 +19,7 @@
 #include <net/dst.h>
 #include <net/xfrm.h>
 
-static int xfrm_output2(struct sk_buff *skb);
+static int xfrm_output2(struct sock *sk, struct sk_buff *skb);
 
 static int xfrm_skb_check_space(struct sk_buff *skb)
 {
@@ -130,7 +130,7 @@ int xfrm_output_resume(struct sk_buff *skb, int err)
 			return dst_output(skb);
 
 		err = nf_hook(skb_dst(skb)->ops->family,
-			      NF_INET_POST_ROUTING, skb,
+			      NF_INET_POST_ROUTING, skb->sk, skb,
 			      NULL, skb_dst(skb)->dev, xfrm_output2);
 		if (unlikely(err != 1))
 			goto out;
@@ -144,12 +144,12 @@ out:
 }
 EXPORT_SYMBOL_GPL(xfrm_output_resume);
 
-static int xfrm_output2(struct sk_buff *skb)
+static int xfrm_output2(struct sock *sk, struct sk_buff *skb)
 {
 	return xfrm_output_resume(skb, 1);
 }
 
-static int xfrm_output_gso(struct sk_buff *skb)
+static int xfrm_output_gso(struct sock *sk, struct sk_buff *skb)
 {
 	struct sk_buff *segs;
 
@@ -165,7 +165,7 @@ static int xfrm_output_gso(struct sk_buff *skb)
 		int err;
 
 		segs->next = NULL;
-		err = xfrm_output2(segs);
+		err = xfrm_output2(sk, segs);
 
 		if (unlikely(err)) {
 			kfree_skb_list(nskb);
@@ -178,13 +178,13 @@ static int xfrm_output_gso(struct sk_buff *skb)
 	return 0;
 }
 
-int xfrm_output(struct sk_buff *skb)
+int xfrm_output(struct sock *sk, struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb_dst(skb)->dev);
 	int err;
 
 	if (skb_is_gso(skb))
-		return xfrm_output_gso(skb);
+		return xfrm_output_gso(sk, skb);
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		err = skb_checksum_help(skb);
@@ -195,7 +195,7 @@ int xfrm_output(struct sk_buff *skb)
 		}
 	}
 
-	return xfrm_output2(skb);
+	return xfrm_output2(sk, skb);
 }
 EXPORT_SYMBOL_GPL(xfrm_output);
 
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 88bf289abdc9..638af0655aaf 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -55,6 +55,7 @@ static int stale_bundle(struct dst_entry *dst);
 static int xfrm_bundle_ok(struct xfrm_dst *xdst);
 static void xfrm_policy_queue_process(unsigned long arg);
 
+static void __xfrm_policy_link(struct xfrm_policy *pol, int dir);
 static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
 						int dir);
 
@@ -561,7 +562,7 @@ static void xfrm_hash_resize(struct work_struct *work)
 	mutex_lock(&hash_resize_mutex);
 
 	total = 0;
-	for (dir = 0; dir < XFRM_POLICY_MAX * 2; dir++) {
+	for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
 		if (xfrm_bydst_should_resize(net, dir, &total))
 			xfrm_bydst_resize(net, dir);
 	}
@@ -601,7 +602,7 @@ static void xfrm_hash_rebuild(struct work_struct *work)
 	write_lock_bh(&net->xfrm.xfrm_policy_lock);
 
 	/* reset the bydst and inexact table in all directions */
-	for (dir = 0; dir < XFRM_POLICY_MAX * 2; dir++) {
+	for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
 		INIT_HLIST_HEAD(&net->xfrm.policy_inexact[dir]);
 		hmask = net->xfrm.policy_bydst[dir].hmask;
 		odst = net->xfrm.policy_bydst[dir].table;
@@ -779,8 +780,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 		hlist_add_behind(&policy->bydst, newpos);
 	else
 		hlist_add_head(&policy->bydst, chain);
-	xfrm_pol_hold(policy);
-	net->xfrm.policy_count[dir]++;
+	__xfrm_policy_link(policy, dir);
 	atomic_inc(&net->xfrm.flow_cache_genid);
 
 	/* After previous checking, family can either be AF_INET or AF_INET6 */
@@ -799,7 +799,6 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 	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(&net->xfrm.xfrm_policy_lock);
 
 	if (delpol)
@@ -1247,17 +1246,10 @@ out:
 static void __xfrm_policy_link(struct xfrm_policy *pol, int dir)
 {
 	struct net *net = xp_net(pol);
-	struct hlist_head *chain = policy_hash_bysel(net, &pol->selector,
-						     pol->family, dir);
 
 	list_add(&pol->walk.all, &net->xfrm.policy_all);
-	hlist_add_head(&pol->bydst, chain);
-	hlist_add_head(&pol->byidx, net->xfrm.policy_byidx+idx_hash(net, pol->index));
 	net->xfrm.policy_count[dir]++;
 	xfrm_pol_hold(pol);
-
-	if (xfrm_bydst_should_resize(net, dir, NULL))
-		schedule_work(&net->xfrm.policy_hash_work);
 }
 
 static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
@@ -1265,17 +1257,31 @@ static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
 {
 	struct net *net = xp_net(pol);
 
-	if (hlist_unhashed(&pol->bydst))
+	if (list_empty(&pol->walk.all))
 		return NULL;
 
-	hlist_del_init(&pol->bydst);
-	hlist_del(&pol->byidx);
-	list_del(&pol->walk.all);
+	/* Socket policies are not hashed. */
+	if (!hlist_unhashed(&pol->bydst)) {
+		hlist_del(&pol->bydst);
+		hlist_del(&pol->byidx);
+	}
+
+	list_del_init(&pol->walk.all);
 	net->xfrm.policy_count[dir]--;
 
 	return pol;
 }
 
+static void xfrm_sk_policy_link(struct xfrm_policy *pol, int dir)
+{
+	__xfrm_policy_link(pol, XFRM_POLICY_MAX + dir);
+}
+
+static void xfrm_sk_policy_unlink(struct xfrm_policy *pol, int dir)
+{
+	__xfrm_policy_unlink(pol, XFRM_POLICY_MAX + dir);
+}
+
 int xfrm_policy_delete(struct xfrm_policy *pol, int dir)
 {
 	struct net *net = xp_net(pol);
@@ -1307,7 +1313,7 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol)
 	if (pol) {
 		pol->curlft.add_time = get_seconds();
 		pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir, 0);
-		__xfrm_policy_link(pol, XFRM_POLICY_MAX+dir);
+		xfrm_sk_policy_link(pol, dir);
 	}
 	if (old_pol) {
 		if (pol)
@@ -1316,7 +1322,7 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol)
 		/* Unlinking succeeds always. This is the only function
 		 * allowed to delete or replace socket policy.
 		 */
-		__xfrm_policy_unlink(old_pol, XFRM_POLICY_MAX+dir);
+		xfrm_sk_policy_unlink(old_pol, dir);
 	}
 	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
@@ -1349,7 +1355,7 @@ static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir)
 		memcpy(newp->xfrm_vec, old->xfrm_vec,
 		       newp->xfrm_nr*sizeof(struct xfrm_tmpl));
 		write_lock_bh(&net->xfrm.xfrm_policy_lock);
-		__xfrm_policy_link(newp, XFRM_POLICY_MAX+dir);
+		xfrm_sk_policy_link(newp, dir);
 		write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 		xfrm_pol_put(newp);
 	}
@@ -1878,7 +1884,6 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols,
 
 static void xfrm_policy_queue_process(unsigned long arg)
 {
-	int err = 0;
 	struct sk_buff *skb;
 	struct sock *sk;
 	struct dst_entry *dst;
@@ -1941,7 +1946,7 @@ static void xfrm_policy_queue_process(unsigned long arg)
 		skb_dst_drop(skb);
 		skb_dst_set(skb, dst);
 
-		err = dst_output(skb);
+		dst_output(skb);
 	}
 
 out:
@@ -2264,11 +2269,9 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
 		 * have the xfrm_state's. We need to wait for KM to
 		 * negotiate new SA's or bail out with error.*/
 		if (net->xfrm.sysctl_larval_drop) {
-			dst_release(dst);
-			xfrm_pols_put(pols, drop_pols);
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES);
-
-			return ERR_PTR(-EREMOTE);
+			err = -EREMOTE;
+			goto error;
 		}
 
 		err = -EAGAIN;
@@ -2319,7 +2322,8 @@ nopol:
 error:
 	dst_release(dst);
 dropdst:
-	dst_release(dst_orig);
+	if (!(flags & XFRM_LOOKUP_KEEP_DST_REF))
+		dst_release(dst_orig);
 	xfrm_pols_put(pols, drop_pols);
 	return ERR_PTR(err);
 }
@@ -2333,7 +2337,8 @@ struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig,
 				    struct sock *sk, int flags)
 {
 	struct dst_entry *dst = xfrm_lookup(net, dst_orig, fl, sk,
-					    flags | XFRM_LOOKUP_QUEUE);
+					    flags | XFRM_LOOKUP_QUEUE |
+					    XFRM_LOOKUP_KEEP_DST_REF);
 
 	if (IS_ERR(dst) && PTR_ERR(dst) == -EREMOTE)
 		return make_blackhole(net, dst_orig->ops->family, dst_orig);
@@ -2966,10 +2971,11 @@ static int __net_init xfrm_policy_init(struct net *net)
 		goto out_byidx;
 	net->xfrm.policy_idx_hmask = hmask;
 
-	for (dir = 0; dir < XFRM_POLICY_MAX * 2; dir++) {
+	for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
 		struct xfrm_policy_hash *htab;
 
 		net->xfrm.policy_count[dir] = 0;
+		net->xfrm.policy_count[XFRM_POLICY_MAX + dir] = 0;
 		INIT_HLIST_HEAD(&net->xfrm.policy_inexact[dir]);
 
 		htab = &net->xfrm.policy_bydst[dir];
@@ -3021,7 +3027,7 @@ static void xfrm_policy_fini(struct net *net)
 
 	WARN_ON(!list_empty(&net->xfrm.policy_all));
 
-	for (dir = 0; dir < XFRM_POLICY_MAX * 2; dir++) {
+	for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
 		struct xfrm_policy_hash *htab;
 
 		WARN_ON(!hlist_empty(&net->xfrm.policy_inexact[dir]));
diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c
index dab57daae408..4fd725a0c500 100644
--- a/net/xfrm/xfrm_replay.c
+++ b/net/xfrm/xfrm_replay.c
@@ -99,6 +99,7 @@ static int xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb)
 
 	if (x->type->flags & XFRM_TYPE_REPLAY_PROT) {
 		XFRM_SKB_CB(skb)->seq.output.low = ++x->replay.oseq;
+		XFRM_SKB_CB(skb)->seq.output.hi = 0;
 		if (unlikely(x->replay.oseq == 0)) {
 			x->replay.oseq--;
 			xfrm_audit_state_replay_overflow(x, skb);
@@ -177,6 +178,7 @@ static int xfrm_replay_overflow_bmp(struct xfrm_state *x, struct sk_buff *skb)
 
 	if (x->type->flags & XFRM_TYPE_REPLAY_PROT) {
 		XFRM_SKB_CB(skb)->seq.output.low = ++replay_esn->oseq;
+		XFRM_SKB_CB(skb)->seq.output.hi = 0;
 		if (unlikely(replay_esn->oseq == 0)) {
 			replay_esn->oseq--;
 			xfrm_audit_state_replay_overflow(x, skb);
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index de971b6d38c5..96688cd0f6f1 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -927,8 +927,8 @@ struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi,
 			x->id.spi != spi)
 			continue;
 
-		spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 		xfrm_state_hold(x);
+		spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 		return x;
 	}
 	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
@@ -1043,12 +1043,12 @@ static struct xfrm_state *__find_acq_core(struct net *net,
 			break;
 
 		case AF_INET6:
-			*(struct in6_addr *)x->sel.daddr.a6 = *(struct in6_addr *)daddr;
-			*(struct in6_addr *)x->sel.saddr.a6 = *(struct in6_addr *)saddr;
+			x->sel.daddr.in6 = daddr->in6;
+			x->sel.saddr.in6 = saddr->in6;
 			x->sel.prefixlen_d = 128;
 			x->sel.prefixlen_s = 128;
-			*(struct in6_addr *)x->props.saddr.a6 = *(struct in6_addr *)saddr;
-			*(struct in6_addr *)x->id.daddr.a6 = *(struct in6_addr *)daddr;
+			x->props.saddr.in6 = saddr->in6;
+			x->id.daddr.in6 = daddr->in6;
 			break;
 		}
 
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index e812e988c111..bd16c6c7e1e7 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -289,6 +289,31 @@ static int attach_one_algo(struct xfrm_algo **algpp, u8 *props,
 	return 0;
 }
 
+static int attach_crypt(struct xfrm_state *x, struct nlattr *rta)
+{
+	struct xfrm_algo *p, *ualg;
+	struct xfrm_algo_desc *algo;
+
+	if (!rta)
+		return 0;
+
+	ualg = nla_data(rta);
+
+	algo = xfrm_ealg_get_byname(ualg->alg_name, 1);
+	if (!algo)
+		return -ENOSYS;
+	x->props.ealgo = algo->desc.sadb_alg_id;
+
+	p = kmemdup(ualg, xfrm_alg_len(ualg), GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	strcpy(p->alg_name, algo->name);
+	x->ealg = p;
+	x->geniv = algo->uinfo.encr.geniv;
+	return 0;
+}
+
 static int attach_auth(struct xfrm_algo_auth **algpp, u8 *props,
 		       struct nlattr *rta)
 {
@@ -349,8 +374,7 @@ static int attach_auth_trunc(struct xfrm_algo_auth **algpp, u8 *props,
 	return 0;
 }
 
-static int attach_aead(struct xfrm_algo_aead **algpp, u8 *props,
-		       struct nlattr *rta)
+static int attach_aead(struct xfrm_state *x, struct nlattr *rta)
 {
 	struct xfrm_algo_aead *p, *ualg;
 	struct xfrm_algo_desc *algo;
@@ -363,14 +387,15 @@ static int attach_aead(struct xfrm_algo_aead **algpp, u8 *props,
 	algo = xfrm_aead_get_byname(ualg->alg_name, ualg->alg_icv_len, 1);
 	if (!algo)
 		return -ENOSYS;
-	*props = algo->desc.sadb_alg_id;
+	x->props.ealgo = algo->desc.sadb_alg_id;
 
 	p = kmemdup(ualg, aead_len(ualg), GFP_KERNEL);
 	if (!p)
 		return -ENOMEM;
 
 	strcpy(p->alg_name, algo->name);
-	*algpp = p;
+	x->aead = p;
+	x->geniv = algo->uinfo.aead.geniv;
 	return 0;
 }
 
@@ -515,8 +540,7 @@ static struct xfrm_state *xfrm_state_construct(struct net *net,
 	if (attrs[XFRMA_SA_EXTRA_FLAGS])
 		x->props.extra_flags = nla_get_u32(attrs[XFRMA_SA_EXTRA_FLAGS]);
 
-	if ((err = attach_aead(&x->aead, &x->props.ealgo,
-			       attrs[XFRMA_ALG_AEAD])))
+	if ((err = attach_aead(x, attrs[XFRMA_ALG_AEAD])))
 		goto error;
 	if ((err = attach_auth_trunc(&x->aalg, &x->props.aalgo,
 				     attrs[XFRMA_ALG_AUTH_TRUNC])))
@@ -526,9 +550,7 @@ static struct xfrm_state *xfrm_state_construct(struct net *net,
 				       attrs[XFRMA_ALG_AUTH])))
 			goto error;
 	}
-	if ((err = attach_one_algo(&x->ealg, &x->props.ealgo,
-				   xfrm_ealg_get_byname,
-				   attrs[XFRMA_ALG_CRYPT])))
+	if ((err = attach_crypt(x, attrs[XFRMA_ALG_CRYPT])))
 		goto error;
 	if ((err = attach_one_algo(&x->calg, &x->props.calgo,
 				   xfrm_calg_get_byname,
@@ -824,13 +846,15 @@ static int copy_to_user_state_extra(struct xfrm_state *x,
 	ret = xfrm_mark_put(skb, &x->mark);
 	if (ret)
 		goto out;
-	if (x->replay_esn) {
+	if (x->replay_esn)
 		ret = nla_put(skb, XFRMA_REPLAY_ESN_VAL,
 			      xfrm_replay_state_esn_len(x->replay_esn),
 			      x->replay_esn);
-		if (ret)
-			goto out;
-	}
+	else
+		ret = nla_put(skb, XFRMA_REPLAY_VAL, sizeof(x->replay),
+			      &x->replay);
+	if (ret)
+		goto out;
 	if (x->security)
 		ret = copy_sec_ctx(x->security, skb);
 out:
@@ -1017,7 +1041,8 @@ static int build_spdinfo(struct sk_buff *skb, struct net *net,
 		return err;
 	}
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 }
 
 static int xfrm_set_spdinfo(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -1119,7 +1144,8 @@ static int build_sadinfo(struct sk_buff *skb, struct net *net,
 		return err;
 	}
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 }
 
 static int xfrm_get_sadinfo(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -1840,7 +1866,8 @@ static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct
 	if (err)
 		goto out_cancel;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 out_cancel:
 	nlmsg_cancel(skb, nlh);
@@ -2280,7 +2307,8 @@ static int build_migrate(struct sk_buff *skb, const struct xfrm_migrate *m,
 			goto out_cancel;
 	}
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 out_cancel:
 	nlmsg_cancel(skb, nlh);
@@ -2417,6 +2445,11 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	const struct xfrm_link *link;
 	int type, err;
 
+#ifdef CONFIG_COMPAT
+	if (is_compat_task())
+		return -ENOTSUPP;
+#endif
+
 	type = nlh->nlmsg_type;
 	if (type > XFRM_MSG_MAX)
 		return -EINVAL;
@@ -2488,7 +2521,8 @@ static int build_expire(struct sk_buff *skb, struct xfrm_state *x, const struct
 	if (err)
 		return err;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 }
 
 static int xfrm_exp_state_notify(struct xfrm_state *x, const struct km_event *c)
@@ -2569,6 +2603,8 @@ static inline size_t xfrm_sa_len(struct xfrm_state *x)
 		l += nla_total_size(sizeof(x->tfcpad));
 	if (x->replay_esn)
 		l += nla_total_size(xfrm_replay_state_esn_len(x->replay_esn));
+	else
+		l += nla_total_size(sizeof(struct xfrm_replay_state));
 	if (x->security)
 		l += nla_total_size(sizeof(struct xfrm_user_sec_ctx) +
 				    x->security->ctx_len);
@@ -2708,7 +2744,8 @@ static int build_acquire(struct sk_buff *skb, struct xfrm_state *x,
 		return err;
 	}
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 }
 
 static int xfrm_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *xt,
@@ -2823,7 +2860,8 @@ static int build_polexpire(struct sk_buff *skb, struct xfrm_policy *xp,
 	}
 	upe->hard = !!hard;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 }
 
 static int xfrm_exp_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c)
@@ -2982,7 +3020,8 @@ static int build_report(struct sk_buff *skb, u8 proto,
 			return err;
 		}
 	}
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 }
 
 static int xfrm_send_report(struct net *net, u8 proto,
@@ -3027,7 +3066,8 @@ static int build_mapping(struct sk_buff *skb, struct xfrm_state *x,
 	um->old_sport = x->encap->encap_sport;
 	um->reqid = x->props.reqid;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 }
 
 static int xfrm_send_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr,