1 files changed, 48 insertions, 3 deletions
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index f9304cb3715..48b66bbffc9 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -67,6 +67,9 @@
 #define USB_VENDOR_ID_ALPS		0x0433
 #define USB_DEVICE_ID_IBM_GAMEPAD	0x1101
 
+#define USB_VENDOR_ID_ANTON		0x1130
+#define USB_DEVICE_ID_ANTON_TOUCH_PAD	0x3101
+
 #define USB_VENDOR_ID_APPLE		0x05ac
 #define USB_DEVICE_ID_APPLE_MIGHTYMOUSE	0x0304
 #define USB_DEVICE_ID_APPLE_MAGICMOUSE	0x030d
@@ -135,6 +138,7 @@
 #define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_JIS   0x023b
 #define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ANSI  0x0255
 #define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ISO   0x0256
+#define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_JIS   0x0257
 #define USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI	0x0290
 #define USB_DEVICE_ID_APPLE_WELLSPRING8_ISO	0x0291
 #define USB_DEVICE_ID_APPLE_WELLSPRING8_JIS	0x0292
@@ -240,6 +244,10 @@
 
 #define USB_VENDOR_ID_CYGNAL		0x10c4
 #define USB_DEVICE_ID_CYGNAL_RADIO_SI470X	0x818a
+#define USB_DEVICE_ID_FOCALTECH_FTXXXX_MULTITOUCH	0x81b9
+#define USB_DEVICE_ID_CYGNAL_CP2112	0xea90
+
+#define USB_DEVICE_ID_CYGNAL_RADIO_SI4713       0x8244
 
 #define USB_VENDOR_ID_CYPRESS		0x04b4
 #define USB_DEVICE_ID_CYPRESS_MOUSE	0x0001
@@ -293,6 +301,9 @@
 
 #define USB_VENDOR_ID_DREAM_CHEEKY	0x1d34
 
+#define USB_VENDOR_ID_ELITEGROUP	0x03fc
+#define USB_DEVICE_ID_ELITEGROUP_05D8	0x05d8
+
 #define USB_VENDOR_ID_ELO		0x04E7
 #define USB_DEVICE_ID_ELO_TS2515	0x0022
 #define USB_DEVICE_ID_ELO_TS2700	0x0020
@@ -312,6 +323,7 @@
 
 #define USB_VENDOR_ID_ETURBOTOUCH	0x22b9
 #define USB_DEVICE_ID_ETURBOTOUCH	0x0006
+#define USB_DEVICE_ID_ETURBOTOUCH_2968	0x2968
 
 #define USB_VENDOR_ID_EZKEY		0x0518
 #define USB_DEVICE_ID_BTC_8193		0x0002
@@ -445,6 +457,15 @@
 #define USB_VENDOR_ID_ILITEK		0x222a
 #define USB_DEVICE_ID_ILITEK_MULTITOUCH	0x0001
 
+#define USB_VENDOR_ID_INTEL_0		0x8086
+#define USB_VENDOR_ID_INTEL_1		0x8087
+#define USB_DEVICE_ID_INTEL_HID_SENSOR_0	0x09fa
+#define USB_DEVICE_ID_INTEL_HID_SENSOR_1	0x0a04
+
+#define USB_VENDOR_ID_STM_0             0x0483
+#define USB_DEVICE_ID_STM_HID_SENSOR    0x91d1
+#define USB_DEVICE_ID_STM_HID_SENSOR_1  0x9100
+
 #define USB_VENDOR_ID_ION		0x15e4
 #define USB_DEVICE_ID_ICADE		0x0132
 
@@ -455,6 +476,7 @@
 #define USB_DEVICE_ID_HOLTEK_ALT_KEYBOARD	0xa055
 #define USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A04A	0xa04a
 #define USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A067	0xa067
+#define USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A070	0xa070
 #define USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A072	0xa072
 #define USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A081	0xa081
 
@@ -552,6 +574,7 @@
 #define USB_DEVICE_ID_LOGITECH_RUMBLEPAD_CORD	0xc20a
 #define USB_DEVICE_ID_LOGITECH_RUMBLEPAD	0xc211
 #define USB_DEVICE_ID_LOGITECH_EXTREME_3D	0xc215
+#define USB_DEVICE_ID_LOGITECH_DUAL_ACTION	0xc216
 #define USB_DEVICE_ID_LOGITECH_RUMBLEPAD2	0xc218
 #define USB_DEVICE_ID_LOGITECH_RUMBLEPAD2_2	0xc219
 #define USB_DEVICE_ID_LOGITECH_WINGMAN_F3D	0xc283
@@ -603,6 +626,7 @@
 
 #define USB_VENDOR_ID_MICROSOFT		0x045e
 #define USB_DEVICE_ID_SIDEWINDER_GV	0x003b
+#define USB_DEVICE_ID_MS_OFFICE_KB	0x0048
 #define USB_DEVICE_ID_WIRELESS_OPTICAL_DESKTOP_3_0 0x009d
 #define USB_DEVICE_ID_MS_NE4K		0x00db
 #define USB_DEVICE_ID_MS_NE4K_JP	0x00dc
@@ -611,6 +635,9 @@
 #define USB_DEVICE_ID_MS_PRESENTER_8K_USB	0x0713
 #define USB_DEVICE_ID_MS_DIGITAL_MEDIA_3K	0x0730
 #define USB_DEVICE_ID_MS_COMFORT_MOUSE_4500	0x076c
+#define USB_DEVICE_ID_MS_SURFACE_PRO_2   0x0799
+#define USB_DEVICE_ID_MS_TOUCH_COVER_2   0x07a7
+#define USB_DEVICE_ID_MS_TYPE_COVER_2    0x07a9
 
 #define USB_VENDOR_ID_MOJO		0x8282
 #define USB_DEVICE_ID_RETRO_ADAPTER	0x3201
@@ -636,6 +663,7 @@
 
 #define USB_VENDOR_ID_NEXIO		0x1870
 #define USB_DEVICE_ID_NEXIO_MULTITOUCH_420	0x010d
+#define USB_DEVICE_ID_NEXIO_MULTITOUCH_PTI0750	0x0110
 
 #define USB_VENDOR_ID_NEXTWINDOW	0x1926
 #define USB_DEVICE_ID_NEXTWINDOW_TOUCHSCREEN	0x0003
@@ -688,6 +716,8 @@
 
 #define USB_VENDOR_ID_PENMOUNT		0x14e1
 #define USB_DEVICE_ID_PENMOUNT_PCI	0x3500
+#define USB_DEVICE_ID_PENMOUNT_1610	0x1610
+#define USB_DEVICE_ID_PENMOUNT_1640	0x1640
 
 #define USB_VENDOR_ID_PETALYNX		0x18b1
 #define USB_DEVICE_ID_PETALYNX_MAXTER_REMOTE	0x0037
@@ -741,11 +771,16 @@
 #define USB_VENDOR_ID_SAITEK		0x06a3
 #define USB_DEVICE_ID_SAITEK_RUMBLEPAD	0xff17
 #define USB_DEVICE_ID_SAITEK_PS1000	0x0621
+#define USB_DEVICE_ID_SAITEK_RAT7	0x0cd7
+#define USB_DEVICE_ID_SAITEK_MMO7	0x0cd0
 
 #define USB_VENDOR_ID_SAMSUNG		0x0419
 #define USB_DEVICE_ID_SAMSUNG_IR_REMOTE	0x0001
 #define USB_DEVICE_ID_SAMSUNG_WIRELESS_KBD_MOUSE	0x0600
 
+#define USB_VENDOR_ID_SEMICO			0x1a2c
+#define USB_DEVICE_ID_SEMICO_USB_KEYKOARD	0x0023
+
 #define USB_VENDOR_ID_SENNHEISER	0x1395
 #define USB_DEVICE_ID_SENNHEISER_BTD500USB	0x002c
 
@@ -755,9 +790,11 @@
 #define USB_VENDOR_ID_SIGMATEL		0x066F
 #define USB_DEVICE_ID_SIGMATEL_STMP3780	0x3780
 
-#define USB_VENDOR_ID_SIS2_TOUCH	0x0457
+#define USB_VENDOR_ID_SIS_TOUCH		0x0457
 #define USB_DEVICE_ID_SIS9200_TOUCH	0x9200
 #define USB_DEVICE_ID_SIS817_TOUCH	0x0817
+#define USB_DEVICE_ID_SIS_TS		0x1013
+#define USB_DEVICE_ID_SIS1030_TOUCH	0x1030
 
 #define USB_VENDOR_ID_SKYCABLE			0x1223
 #define	USB_DEVICE_ID_SKYCABLE_WIRELESS_PRESENTER	0x3F07
@@ -767,6 +804,7 @@
 #define USB_DEVICE_ID_SONY_VAIO_VGP_MOUSE	0x0374
 #define USB_DEVICE_ID_SONY_PS3_BDREMOTE		0x0306
 #define USB_DEVICE_ID_SONY_PS3_CONTROLLER	0x0268
+#define USB_DEVICE_ID_SONY_PS4_CONTROLLER	0x05c4
 #define USB_DEVICE_ID_SONY_NAVIGATION_CONTROLLER	0x042f
 #define USB_DEVICE_ID_SONY_BUZZ_CONTROLLER		0x0002
 #define USB_DEVICE_ID_SONY_WIRELESS_BUZZ_CONTROLLER	0x1000
@@ -809,6 +847,12 @@
 #define USB_DEVICE_ID_SYNAPTICS_DPAD	0x0013
 #define USB_DEVICE_ID_SYNAPTICS_LTS1	0x0af8
 #define USB_DEVICE_ID_SYNAPTICS_LTS2	0x1d10
+#define USB_DEVICE_ID_SYNAPTICS_HD	0x0ac3
+#define USB_DEVICE_ID_SYNAPTICS_QUAD_HD	0x1ac3
+#define USB_DEVICE_ID_SYNAPTICS_TP_V103	0x5710
+
+#define USB_VENDOR_ID_TEXAS_INSTRUMENTS	0x2047
+#define USB_DEVICE_ID_TEXAS_INSTRUMENTS_LENOVO_YOGA	0x0855
 
 #define USB_VENDOR_ID_THINGM		0x27b8
 #define USB_DEVICE_ID_BLINK1		0x01ed
@@ -939,7 +983,8 @@
 #define USB_VENDOR_ID_PRIMAX	0x0461
 #define USB_DEVICE_ID_PRIMAX_KEYBOARD	0x4e05
 
-#define USB_VENDOR_ID_SIS	0x0457
-#define USB_DEVICE_ID_SIS_TS	0x1013
+
+#define USB_VENDOR_ID_RISO_KAGAKU	0x1294	/* Riso Kagaku Corp. */
+#define USB_DEVICE_ID_RI_KA_WEBMAIL	0x1320	/* Webmail Notifier */
 
 #endif
diff --git a/net/802/Kconfig b/net/802/Kconfig
new file mode 100644
index 00000000000..80d4bf78905
--- /dev/null
+++ b/net/802/Kconfig
@@ -0,0 +1,10 @@
+config STP
+	tristate
+	select LLC
+
+config GARP
+	tristate
+	select STP
+
+config MRP
+	tristate
diff --git a/net/802/Makefile b/net/802/Makefile
index 977704a54f6..37e654d6615 100644
--- a/net/802/Makefile
+++ b/net/802/Makefile
@@ -3,11 +3,12 @@
 #
 
 # Check the p8022 selections against net/core/Makefile.
-obj-$(CONFIG_SYSCTL)	+= sysctl_net_802.o
 obj-$(CONFIG_LLC)	+= p8022.o psnap.o
-obj-$(CONFIG_TR)	+= p8022.o psnap.o tr.o sysctl_net_802.o
 obj-$(CONFIG_NET_FC)	+=                 fc.o
 obj-$(CONFIG_FDDI)	+=                 fddi.o
 obj-$(CONFIG_HIPPI)	+=                 hippi.o
 obj-$(CONFIG_IPX)	+= p8022.o psnap.o p8023.o
 obj-$(CONFIG_ATALK)	+= p8022.o psnap.o
+obj-$(CONFIG_STP)	+= stp.o
+obj-$(CONFIG_GARP)	+= garp.o
+obj-$(CONFIG_MRP)	+= mrp.o
diff --git a/net/802/fc.c b/net/802/fc.c
index 282c4ab1abe..05eea6b98bb 100644
--- a/net/802/fc.c
+++ b/net/802/fc.c
@@ -1,6 +1,6 @@
 /*
  * NET3:	Fibre Channel device handling subroutines
- * 
+ *
  *		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
@@ -10,12 +10,9 @@
  *		v 1.0 03/22/99
  */
 
-#include <linux/config.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
 #include <linux/string.h>
 #include <linux/mm.h>
 #include <linux/socket.h>
@@ -29,21 +26,22 @@
 #include <linux/net.h>
 #include <linux/proc_fs.h>
 #include <linux/init.h>
+#include <linux/export.h>
 #include <net/arp.h>
 
 /*
- *	Put the headers on a Fibre Channel packet. 
+ *	Put the headers on a Fibre Channel packet.
  */
- 
+
 static int fc_header(struct sk_buff *skb, struct net_device *dev,
 		     unsigned short type,
-		     void *daddr, void *saddr, unsigned len) 
+		     const void *daddr, const void *saddr, unsigned int len)
 {
 	struct fch_hdr *fch;
 	int hdr_len;
 
-	/* 
-	 * Add the 802.2 SNAP header if IP as the IPv4 code calls  
+	/*
+	 * Add the 802.2 SNAP header if IP as the IPv4 code calls
 	 * dev->hard_header directly.
 	 */
 	if (type == ETH_P_IP || type == ETH_P_ARP)
@@ -61,7 +59,7 @@ static int fc_header(struct sk_buff *skb, struct net_device *dev,
 	else
 	{
 		hdr_len = sizeof(struct fch_hdr);
-		fch = (struct fch_hdr *)skb_push(skb, hdr_len);	
+		fch = (struct fch_hdr *)skb_push(skb, hdr_len);
 	}
 
 	if(saddr)
@@ -69,39 +67,42 @@ static int fc_header(struct sk_buff *skb, struct net_device *dev,
 	else
 		memcpy(fch->saddr,dev->dev_addr,dev->addr_len);
 
-	if(daddr) 
+	if(daddr)
 	{
 		memcpy(fch->daddr,daddr,dev->addr_len);
-		return(hdr_len);
+		return hdr_len;
 	}
 	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) 
+
+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;
 	}
-#ifdef CONFIG_INET
 	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)
 {
-	dev->hard_header	= fc_header;
-	dev->rebuild_header	= fc_rebuild_header;
-                
+	dev->header_ops		= &fc_header_ops;
 	dev->type		= ARPHRD_IEEE802;
 	dev->hard_header_len	= FC_HLEN;
 	dev->mtu		= 2024;
diff --git a/net/802/fddi.c b/net/802/fddi.c
index ac242a4bc34..9cda40661e0 100644
--- a/net/802/fddi.c
+++ b/net/802/fddi.c
@@ -15,7 +15,7 @@
  *			Mark Evans, <evansmp@uhura.aston.ac.uk>
  *			Florian La Roche, <rzsfl@rz.uni-sb.de>
  *			Alan Cox, <gw4pts@gw4pts.ampr.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
@@ -25,13 +25,10 @@
  *		Alan Cox		:	New arp/rebuild header
  *		Maciej W. Rozycki	:	IPv6 support
  */
- 
-#include <linux/config.h>
+
 #include <linux/module.h>
-#include <asm/system.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
 #include <linux/string.h>
 #include <linux/mm.h>
 #include <linux/socket.h>
@@ -54,11 +51,11 @@
 
 static int fddi_header(struct sk_buff *skb, struct net_device *dev,
 		       unsigned short type,
-		       void *daddr, void *saddr, unsigned len)
+		       const void *daddr, const void *saddr, unsigned int len)
 {
 	int hl = FDDI_K_SNAP_HLEN;
 	struct fddihdr *fddi;
-	
+
 	if(type != ETH_P_IP && type != ETH_P_IPV6 && type != ETH_P_ARP)
 		hl=FDDI_K_8022_HLEN-3;
 	fddi = (struct fddihdr *)skb_push(skb, hl);
@@ -75,7 +72,7 @@ static int fddi_header(struct sk_buff *skb, struct net_device *dev,
 	}
 
 	/* Set the source and destination hardware addresses */
-	 
+
 	if (saddr != NULL)
 		memcpy(fddi->saddr, saddr, dev->addr_len);
 	else
@@ -84,10 +81,10 @@ static int fddi_header(struct sk_buff *skb, struct net_device *dev,
 	if (daddr != NULL)
 	{
 		memcpy(fddi->daddr, daddr, dev->addr_len);
-		return(hl);
+		return hl;
 	}
 
-	return(-hl);
+	return -hl;
 }
 
 
@@ -96,21 +93,21 @@ static int fddi_header(struct sk_buff *skb, struct net_device *dev,
  * (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 == __constant_htons(ETH_P_IP))
+	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	
+#endif
 	{
 		printk("%s: Don't know how to resolve type %04X addresses.\n",
 		       skb->dev->name, ntohs(fddi->hdr.llc_snap.ethertype));
-		return(0);
+		return 0;
 	}
 }
 
@@ -121,32 +118,33 @@ static int fddi_rebuild_header(struct sk_buff	*skb)
  * up.  It's used to fill in specific skb fields and to set
  * the proper pointer to the start of packet data (skb->data).
  */
- 
+
 __be16 fddi_type_trans(struct sk_buff *skb, struct net_device *dev)
 {
 	struct fddihdr *fddi = (struct fddihdr *)skb->data;
 	__be16 type;
-	
+
 	/*
 	 * Set mac.raw field to point to FC byte, set data field to point
 	 * to start of packet data.  Assume 802.2 SNAP frames for now.
 	 */
 
-	skb->mac.raw = skb->data;	/* point to frame control (FC) */
-	
+	skb->dev = dev;
+	skb_reset_mac_header(skb);	/* point to frame control (FC) */
+
 	if(fddi->hdr.llc_8022_1.dsap==0xe0)
 	{
 		skb_pull(skb, FDDI_K_8022_HLEN-3);
-		type = __constant_htons(ETH_P_802_2);
+		type = htons(ETH_P_802_2);
 	}
 	else
 	{
 		skb_pull(skb, FDDI_K_SNAP_HLEN);		/* adjust for 21 byte header */
 		type=fddi->hdr.llc_snap.ethertype;
 	}
-	
+
 	/* Set packet type based on destination address and flag settings */
-			
+
 	if (*fddi->daddr & 0x01)
 	{
 		if (memcmp(fddi->daddr, dev->broadcast, FDDI_K_ALEN) == 0)
@@ -154,7 +152,7 @@ __be16 fddi_type_trans(struct sk_buff *skb, struct net_device *dev)
 		else
 			skb->pkt_type = PACKET_MULTICAST;
 	}
-	
+
 	else if (dev->flags & IFF_PROMISC)
 	{
 		if (memcmp(fddi->daddr, dev->dev_addr, FDDI_K_ALEN))
@@ -163,32 +161,36 @@ __be16 fddi_type_trans(struct sk_buff *skb, struct net_device *dev)
 
 	/* Assume 802.2 SNAP frames, for now */
 
-	return(type);
+	return type;
 }
 
 EXPORT_SYMBOL(fddi_type_trans);
 
-static int fddi_change_mtu(struct net_device *dev, int new_mtu)
+int fddi_change_mtu(struct net_device *dev, int new_mtu)
 {
 	if ((new_mtu < FDDI_K_SNAP_HLEN) || (new_mtu > FDDI_K_SNAP_DLEN))
-		return(-EINVAL);
+		return -EINVAL;
 	dev->mtu = new_mtu;
-	return(0);
+	return 0;
 }
+EXPORT_SYMBOL(fddi_change_mtu);
+
+static const struct header_ops fddi_header_ops = {
+	.create		= fddi_header,
+	.rebuild	= fddi_rebuild_header,
+};
+
 
 static void fddi_setup(struct net_device *dev)
 {
-	dev->change_mtu		= fddi_change_mtu;
-	dev->hard_header	= fddi_header;
-	dev->rebuild_header	= fddi_rebuild_header;
-
+	dev->header_ops		= &fddi_header_ops;
 	dev->type		= ARPHRD_FDDI;
 	dev->hard_header_len	= FDDI_K_SNAP_HLEN+3;	/* Assume 802.2 SNAP hdr len + 3 pad bytes */
 	dev->mtu		= FDDI_K_SNAP_DLEN;	/* Assume max payload of 802.2 SNAP frame */
 	dev->addr_len		= FDDI_K_ALEN;
 	dev->tx_queue_len	= 100;			/* Long queues on FDDI */
 	dev->flags		= IFF_BROADCAST | IFF_MULTICAST;
-	
+
 	memset(dev->broadcast, 0xFF, FDDI_K_ALEN);
 }
 
@@ -208,3 +210,5 @@ struct net_device *alloc_fddidev(int sizeof_priv)
 	return alloc_netdev(sizeof_priv, "fddi%d", fddi_setup);
 }
 EXPORT_SYMBOL(alloc_fddidev);
+
+MODULE_LICENSE("GPL");
diff --git a/net/802/garp.c b/net/802/garp.c
new file mode 100644
index 00000000000..b38ee6dcba4
--- /dev/null
+++ b/net/802/garp.c
@@ -0,0 +1,638 @@
+/*
+ *	IEEE 802.1D Generic Attribute Registration Protocol (GARP)
+ *
+ *	Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	version 2 as published by the Free Software Foundation.
+ */
+#include <linux/kernel.h>
+#include <linux/timer.h>
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/llc.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <net/llc.h>
+#include <net/llc_pdu.h>
+#include <net/garp.h>
+#include <asm/unaligned.h>
+
+static unsigned int garp_join_time __read_mostly = 200;
+module_param(garp_join_time, uint, 0644);
+MODULE_PARM_DESC(garp_join_time, "Join time in ms (default 200ms)");
+MODULE_LICENSE("GPL");
+
+static const struct garp_state_trans {
+	u8	state;
+	u8	action;
+} garp_applicant_state_table[GARP_APPLICANT_MAX + 1][GARP_EVENT_MAX + 1] = {
+	[GARP_APPLICANT_VA] = {
+		[GARP_EVENT_TRANSMIT_PDU]	= { .state = GARP_APPLICANT_AA,
+						    .action = GARP_ACTION_S_JOIN_IN },
+		[GARP_EVENT_R_JOIN_IN]		= { .state = GARP_APPLICANT_AA },
+		[GARP_EVENT_R_JOIN_EMPTY]	= { .state = GARP_APPLICANT_VA },
+		[GARP_EVENT_R_EMPTY]		= { .state = GARP_APPLICANT_VA },
+		[GARP_EVENT_R_LEAVE_IN]		= { .state = GARP_APPLICANT_VA },
+		[GARP_EVENT_R_LEAVE_EMPTY]	= { .state = GARP_APPLICANT_VP },
+		[GARP_EVENT_REQ_JOIN]		= { .state = GARP_APPLICANT_INVALID },
+		[GARP_EVENT_REQ_LEAVE]		= { .state = GARP_APPLICANT_LA },
+	},
+	[GARP_APPLICANT_AA] = {
+		[GARP_EVENT_TRANSMIT_PDU]	= { .state = GARP_APPLICANT_QA,
+						    .action = GARP_ACTION_S_JOIN_IN },
+		[GARP_EVENT_R_JOIN_IN]		= { .state = GARP_APPLICANT_QA },
+		[GARP_EVENT_R_JOIN_EMPTY]	= { .state = GARP_APPLICANT_VA },
+		[GARP_EVENT_R_EMPTY]		= { .state = GARP_APPLICANT_VA },
+		[GARP_EVENT_R_LEAVE_IN]		= { .state = GARP_APPLICANT_VA },
+		[GARP_EVENT_R_LEAVE_EMPTY]	= { .state = GARP_APPLICANT_VP },
+		[GARP_EVENT_REQ_JOIN]		= { .state = GARP_APPLICANT_INVALID },
+		[GARP_EVENT_REQ_LEAVE]		= { .state = GARP_APPLICANT_LA },
+	},
+	[GARP_APPLICANT_QA] = {
+		[GARP_EVENT_TRANSMIT_PDU]	= { .state = GARP_APPLICANT_INVALID },
+		[GARP_EVENT_R_JOIN_IN]		= { .state = GARP_APPLICANT_QA },
+		[GARP_EVENT_R_JOIN_EMPTY]	= { .state = GARP_APPLICANT_VA },
+		[GARP_EVENT_R_EMPTY]		= { .state = GARP_APPLICANT_VA },
+		[GARP_EVENT_R_LEAVE_IN]		= { .state = GARP_APPLICANT_VP },
+		[GARP_EVENT_R_LEAVE_EMPTY]	= { .state = GARP_APPLICANT_VP },
+		[GARP_EVENT_REQ_JOIN]		= { .state = GARP_APPLICANT_INVALID },
+		[GARP_EVENT_REQ_LEAVE]		= { .state = GARP_APPLICANT_LA },
+	},
+	[GARP_APPLICANT_LA] = {
+		[GARP_EVENT_TRANSMIT_PDU]	= { .state = GARP_APPLICANT_VO,
+						    .action = GARP_ACTION_S_LEAVE_EMPTY },
+		[GARP_EVENT_R_JOIN_IN]		= { .state = GARP_APPLICANT_LA },
+		[GARP_EVENT_R_JOIN_EMPTY]	= { .state = GARP_APPLICANT_VO },
+		[GARP_EVENT_R_EMPTY]		= { .state = GARP_APPLICANT_LA },
+		[GARP_EVENT_R_LEAVE_IN]		= { .state = GARP_APPLICANT_LA },
+		[GARP_EVENT_R_LEAVE_EMPTY]	= { .state = GARP_APPLICANT_VO },
+		[GARP_EVENT_REQ_JOIN]		= { .state = GARP_APPLICANT_VA },
+		[GARP_EVENT_REQ_LEAVE]		= { .state = GARP_APPLICANT_INVALID },
+	},
+	[GARP_APPLICANT_VP] = {
+		[GARP_EVENT_TRANSMIT_PDU]	= { .state = GARP_APPLICANT_AA,
+						    .action = GARP_ACTION_S_JOIN_IN },
+		[GARP_EVENT_R_JOIN_IN]		= { .state = GARP_APPLICANT_AP },
+		[GARP_EVENT_R_JOIN_EMPTY]	= { .state = GARP_APPLICANT_VP },
+		[GARP_EVENT_R_EMPTY]		= { .state = GARP_APPLICANT_VP },
+		[GARP_EVENT_R_LEAVE_IN]		= { .state = GARP_APPLICANT_VP },
+		[GARP_EVENT_R_LEAVE_EMPTY]	= { .state = GARP_APPLICANT_VP },
+		[GARP_EVENT_REQ_JOIN]		= { .state = GARP_APPLICANT_INVALID },
+		[GARP_EVENT_REQ_LEAVE]		= { .state = GARP_APPLICANT_VO },
+	},
+	[GARP_APPLICANT_AP] = {
+		[GARP_EVENT_TRANSMIT_PDU]	= { .state = GARP_APPLICANT_QA,
+						    .action = GARP_ACTION_S_JOIN_IN },
+		[GARP_EVENT_R_JOIN_IN]		= { .state = GARP_APPLICANT_QP },
+		[GARP_EVENT_R_JOIN_EMPTY]	= { .state = GARP_APPLICANT_VP },
+		[GARP_EVENT_R_EMPTY]		= { .state = GARP_APPLICANT_VP },
+		[GARP_EVENT_R_LEAVE_IN]		= { .state = GARP_APPLICANT_VP },
+		[GARP_EVENT_R_LEAVE_EMPTY]	= { .state = GARP_APPLICANT_VP },
+		[GARP_EVENT_REQ_JOIN]		= { .state = GARP_APPLICANT_INVALID },
+		[GARP_EVENT_REQ_LEAVE]		= { .state = GARP_APPLICANT_AO },
+	},
+	[GARP_APPLICANT_QP] = {
+		[GARP_EVENT_TRANSMIT_PDU]	= { .state = GARP_APPLICANT_INVALID },
+		[GARP_EVENT_R_JOIN_IN]		= { .state = GARP_APPLICANT_QP },
+		[GARP_EVENT_R_JOIN_EMPTY]	= { .state = GARP_APPLICANT_VP },
+		[GARP_EVENT_R_EMPTY]		= { .state = GARP_APPLICANT_VP },
+		[GARP_EVENT_R_LEAVE_IN]		= { .state = GARP_APPLICANT_VP },
+		[GARP_EVENT_R_LEAVE_EMPTY]	= { .state = GARP_APPLICANT_VP },
+		[GARP_EVENT_REQ_JOIN]		= { .state = GARP_APPLICANT_INVALID },
+		[GARP_EVENT_REQ_LEAVE]		= { .state = GARP_APPLICANT_QO },
+	},
+	[GARP_APPLICANT_VO] = {
+		[GARP_EVENT_TRANSMIT_PDU]	= { .state = GARP_APPLICANT_INVALID },
+		[GARP_EVENT_R_JOIN_IN]		= { .state = GARP_APPLICANT_AO },
+		[GARP_EVENT_R_JOIN_EMPTY]	= { .state = GARP_APPLICANT_VO },
+		[GARP_EVENT_R_EMPTY]		= { .state = GARP_APPLICANT_VO },
+		[GARP_EVENT_R_LEAVE_IN]		= { .state = GARP_APPLICANT_VO },
+		[GARP_EVENT_R_LEAVE_EMPTY]	= { .state = GARP_APPLICANT_VO },
+		[GARP_EVENT_REQ_JOIN]		= { .state = GARP_APPLICANT_VP },
+		[GARP_EVENT_REQ_LEAVE]		= { .state = GARP_APPLICANT_INVALID },
+	},
+	[GARP_APPLICANT_AO] = {
+		[GARP_EVENT_TRANSMIT_PDU]	= { .state = GARP_APPLICANT_INVALID },
+		[GARP_EVENT_R_JOIN_IN]		= { .state = GARP_APPLICANT_QO },
+		[GARP_EVENT_R_JOIN_EMPTY]	= { .state = GARP_APPLICANT_VO },
+		[GARP_EVENT_R_EMPTY]		= { .state = GARP_APPLICANT_VO },
+		[GARP_EVENT_R_LEAVE_IN]		= { .state = GARP_APPLICANT_VO },
+		[GARP_EVENT_R_LEAVE_EMPTY]	= { .state = GARP_APPLICANT_VO },
+		[GARP_EVENT_REQ_JOIN]		= { .state = GARP_APPLICANT_AP },
+		[GARP_EVENT_REQ_LEAVE]		= { .state = GARP_APPLICANT_INVALID },
+	},
+	[GARP_APPLICANT_QO] = {
+		[GARP_EVENT_TRANSMIT_PDU]	= { .state = GARP_APPLICANT_INVALID },
+		[GARP_EVENT_R_JOIN_IN]		= { .state = GARP_APPLICANT_QO },
+		[GARP_EVENT_R_JOIN_EMPTY]	= { .state = GARP_APPLICANT_VO },
+		[GARP_EVENT_R_EMPTY]		= { .state = GARP_APPLICANT_VO },
+		[GARP_EVENT_R_LEAVE_IN]		= { .state = GARP_APPLICANT_VO },
+		[GARP_EVENT_R_LEAVE_EMPTY]	= { .state = GARP_APPLICANT_VO },
+		[GARP_EVENT_REQ_JOIN]		= { .state = GARP_APPLICANT_QP },
+		[GARP_EVENT_REQ_LEAVE]		= { .state = GARP_APPLICANT_INVALID },
+	},
+};
+
+static int garp_attr_cmp(const struct garp_attr *attr,
+			 const void *data, u8 len, u8 type)
+{
+	if (attr->type != type)
+		return attr->type - type;
+	if (attr->dlen != len)
+		return attr->dlen - len;
+	return memcmp(attr->data, data, len);
+}
+
+static struct garp_attr *garp_attr_lookup(const struct garp_applicant *app,
+					  const void *data, u8 len, u8 type)
+{
+	struct rb_node *parent = app->gid.rb_node;
+	struct garp_attr *attr;
+	int d;
+
+	while (parent) {
+		attr = rb_entry(parent, struct garp_attr, node);
+		d = garp_attr_cmp(attr, data, len, type);
+		if (d > 0)
+			parent = parent->rb_left;
+		else if (d < 0)
+			parent = parent->rb_right;
+		else
+			return attr;
+	}
+	return NULL;
+}
+
+static struct garp_attr *garp_attr_create(struct garp_applicant *app,
+					  const void *data, u8 len, u8 type)
+{
+	struct rb_node *parent = NULL, **p = &app->gid.rb_node;
+	struct garp_attr *attr;
+	int d;
+
+	while (*p) {
+		parent = *p;
+		attr = rb_entry(parent, struct garp_attr, node);
+		d = garp_attr_cmp(attr, data, len, type);
+		if (d > 0)
+			p = &parent->rb_left;
+		else if (d < 0)
+			p = &parent->rb_right;
+		else {
+			/* The attribute already exists; re-use it. */
+			return attr;
+		}
+	}
+	attr = kmalloc(sizeof(*attr) + len, GFP_ATOMIC);
+	if (!attr)
+		return attr;
+	attr->state = GARP_APPLICANT_VO;
+	attr->type  = type;
+	attr->dlen  = len;
+	memcpy(attr->data, data, len);
+
+	rb_link_node(&attr->node, parent, p);
+	rb_insert_color(&attr->node, &app->gid);
+	return attr;
+}
+
+static void garp_attr_destroy(struct garp_applicant *app, struct garp_attr *attr)
+{
+	rb_erase(&attr->node, &app->gid);
+	kfree(attr);
+}
+
+static int garp_pdu_init(struct garp_applicant *app)
+{
+	struct sk_buff *skb;
+	struct garp_pdu_hdr *gp;
+
+#define LLC_RESERVE	sizeof(struct llc_pdu_un)
+	skb = alloc_skb(app->dev->mtu + LL_RESERVED_SPACE(app->dev),
+			GFP_ATOMIC);
+	if (!skb)
+		return -ENOMEM;
+
+	skb->dev = app->dev;
+	skb->protocol = htons(ETH_P_802_2);
+	skb_reserve(skb, LL_RESERVED_SPACE(app->dev) + LLC_RESERVE);
+
+	gp = (struct garp_pdu_hdr *)__skb_put(skb, sizeof(*gp));
+	put_unaligned(htons(GARP_PROTOCOL_ID), &gp->protocol);
+
+	app->pdu = skb;
+	return 0;
+}
+
+static int garp_pdu_append_end_mark(struct garp_applicant *app)
+{
+	if (skb_tailroom(app->pdu) < sizeof(u8))
+		return -1;
+	*(u8 *)__skb_put(app->pdu, sizeof(u8)) = GARP_END_MARK;
+	return 0;
+}
+
+static void garp_pdu_queue(struct garp_applicant *app)
+{
+	if (!app->pdu)
+		return;
+
+	garp_pdu_append_end_mark(app);
+	garp_pdu_append_end_mark(app);
+
+	llc_pdu_header_init(app->pdu, LLC_PDU_TYPE_U, LLC_SAP_BSPAN,
+			    LLC_SAP_BSPAN, LLC_PDU_CMD);
+	llc_pdu_init_as_ui_cmd(app->pdu);
+	llc_mac_hdr_init(app->pdu, app->dev->dev_addr,
+			 app->app->proto.group_address);
+
+	skb_queue_tail(&app->queue, app->pdu);
+	app->pdu = NULL;
+}
+
+static void garp_queue_xmit(struct garp_applicant *app)
+{
+	struct sk_buff *skb;
+
+	while ((skb = skb_dequeue(&app->queue)))
+		dev_queue_xmit(skb);
+}
+
+static int garp_pdu_append_msg(struct garp_applicant *app, u8 attrtype)
+{
+	struct garp_msg_hdr *gm;
+
+	if (skb_tailroom(app->pdu) < sizeof(*gm))
+		return -1;
+	gm = (struct garp_msg_hdr *)__skb_put(app->pdu, sizeof(*gm));
+	gm->attrtype = attrtype;
+	garp_cb(app->pdu)->cur_type = attrtype;
+	return 0;
+}
+
+static int garp_pdu_append_attr(struct garp_applicant *app,
+				const struct garp_attr *attr,
+				enum garp_attr_event event)
+{
+	struct garp_attr_hdr *ga;
+	unsigned int len;
+	int err;
+again:
+	if (!app->pdu) {
+		err = garp_pdu_init(app);
+		if (err < 0)
+			return err;
+	}
+
+	if (garp_cb(app->pdu)->cur_type != attr->type) {
+		if (garp_cb(app->pdu)->cur_type &&
+		    garp_pdu_append_end_mark(app) < 0)
+			goto queue;
+		if (garp_pdu_append_msg(app, attr->type) < 0)
+			goto queue;
+	}
+
+	len = sizeof(*ga) + attr->dlen;
+	if (skb_tailroom(app->pdu) < len)
+		goto queue;
+	ga = (struct garp_attr_hdr *)__skb_put(app->pdu, len);
+	ga->len   = len;
+	ga->event = event;
+	memcpy(ga->data, attr->data, attr->dlen);
+	return 0;
+
+queue:
+	garp_pdu_queue(app);
+	goto again;
+}
+
+static void garp_attr_event(struct garp_applicant *app,
+			    struct garp_attr *attr, enum garp_event event)
+{
+	enum garp_applicant_state state;
+
+	state = garp_applicant_state_table[attr->state][event].state;
+	if (state == GARP_APPLICANT_INVALID)
+		return;
+
+	switch (garp_applicant_state_table[attr->state][event].action) {
+	case GARP_ACTION_NONE:
+		break;
+	case GARP_ACTION_S_JOIN_IN:
+		/* When appending the attribute fails, don't update state in
+		 * order to retry on next TRANSMIT_PDU event. */
+		if (garp_pdu_append_attr(app, attr, GARP_JOIN_IN) < 0)
+			return;
+		break;
+	case GARP_ACTION_S_LEAVE_EMPTY:
+		garp_pdu_append_attr(app, attr, GARP_LEAVE_EMPTY);
+		/* As a pure applicant, sending a leave message implies that
+		 * the attribute was unregistered and can be destroyed. */
+		garp_attr_destroy(app, attr);
+		return;
+	default:
+		WARN_ON(1);
+	}
+
+	attr->state = state;
+}
+
+int garp_request_join(const struct net_device *dev,
+		      const struct garp_application *appl,
+		      const void *data, u8 len, u8 type)
+{
+	struct garp_port *port = rtnl_dereference(dev->garp_port);
+	struct garp_applicant *app = rtnl_dereference(port->applicants[appl->type]);
+	struct garp_attr *attr;
+
+	spin_lock_bh(&app->lock);
+	attr = garp_attr_create(app, data, len, type);
+	if (!attr) {
+		spin_unlock_bh(&app->lock);
+		return -ENOMEM;
+	}
+	garp_attr_event(app, attr, GARP_EVENT_REQ_JOIN);
+	spin_unlock_bh(&app->lock);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(garp_request_join);
+
+void garp_request_leave(const struct net_device *dev,
+			const struct garp_application *appl,
+			const void *data, u8 len, u8 type)
+{
+	struct garp_port *port = rtnl_dereference(dev->garp_port);
+	struct garp_applicant *app = rtnl_dereference(port->applicants[appl->type]);
+	struct garp_attr *attr;
+
+	spin_lock_bh(&app->lock);
+	attr = garp_attr_lookup(app, data, len, type);
+	if (!attr) {
+		spin_unlock_bh(&app->lock);
+		return;
+	}
+	garp_attr_event(app, attr, GARP_EVENT_REQ_LEAVE);
+	spin_unlock_bh(&app->lock);
+}
+EXPORT_SYMBOL_GPL(garp_request_leave);
+
+static void garp_gid_event(struct garp_applicant *app, enum garp_event event)
+{
+	struct rb_node *node, *next;
+	struct garp_attr *attr;
+
+	for (node = rb_first(&app->gid);
+	     next = node ? rb_next(node) : NULL, node != NULL;
+	     node = next) {
+		attr = rb_entry(node, struct garp_attr, node);
+		garp_attr_event(app, attr, event);
+	}
+}
+
+static void garp_join_timer_arm(struct garp_applicant *app)
+{
+	unsigned long delay;
+
+	delay = (u64)msecs_to_jiffies(garp_join_time) * prandom_u32() >> 32;
+	mod_timer(&app->join_timer, jiffies + delay);
+}
+
+static void garp_join_timer(unsigned long data)
+{
+	struct garp_applicant *app = (struct garp_applicant *)data;
+
+	spin_lock(&app->lock);
+	garp_gid_event(app, GARP_EVENT_TRANSMIT_PDU);
+	garp_pdu_queue(app);
+	spin_unlock(&app->lock);
+
+	garp_queue_xmit(app);
+	garp_join_timer_arm(app);
+}
+
+static int garp_pdu_parse_end_mark(struct sk_buff *skb)
+{
+	if (!pskb_may_pull(skb, sizeof(u8)))
+		return -1;
+	if (*skb->data == GARP_END_MARK) {
+		skb_pull(skb, sizeof(u8));
+		return -1;
+	}
+	return 0;
+}
+
+static int garp_pdu_parse_attr(struct garp_applicant *app, struct sk_buff *skb,
+			       u8 attrtype)
+{
+	const struct garp_attr_hdr *ga;
+	struct garp_attr *attr;
+	enum garp_event event;
+	unsigned int dlen;
+
+	if (!pskb_may_pull(skb, sizeof(*ga)))
+		return -1;
+	ga = (struct garp_attr_hdr *)skb->data;
+	if (ga->len < sizeof(*ga))
+		return -1;
+
+	if (!pskb_may_pull(skb, ga->len))
+		return -1;
+	skb_pull(skb, ga->len);
+	dlen = sizeof(*ga) - ga->len;
+
+	if (attrtype > app->app->maxattr)
+		return 0;
+
+	switch (ga->event) {
+	case GARP_LEAVE_ALL:
+		if (dlen != 0)
+			return -1;
+		garp_gid_event(app, GARP_EVENT_R_LEAVE_EMPTY);
+		return 0;
+	case GARP_JOIN_EMPTY:
+		event = GARP_EVENT_R_JOIN_EMPTY;
+		break;
+	case GARP_JOIN_IN:
+		event = GARP_EVENT_R_JOIN_IN;
+		break;
+	case GARP_LEAVE_EMPTY:
+		event = GARP_EVENT_R_LEAVE_EMPTY;
+		break;
+	case GARP_EMPTY:
+		event = GARP_EVENT_R_EMPTY;
+		break;
+	default:
+		return 0;
+	}
+
+	if (dlen == 0)
+		return -1;
+	attr = garp_attr_lookup(app, ga->data, dlen, attrtype);
+	if (attr == NULL)
+		return 0;
+	garp_attr_event(app, attr, event);
+	return 0;
+}
+
+static int garp_pdu_parse_msg(struct garp_applicant *app, struct sk_buff *skb)
+{
+	const struct garp_msg_hdr *gm;
+
+	if (!pskb_may_pull(skb, sizeof(*gm)))
+		return -1;
+	gm = (struct garp_msg_hdr *)skb->data;
+	if (gm->attrtype == 0)
+		return -1;
+	skb_pull(skb, sizeof(*gm));
+
+	while (skb->len > 0) {
+		if (garp_pdu_parse_attr(app, skb, gm->attrtype) < 0)
+			return -1;
+		if (garp_pdu_parse_end_mark(skb) < 0)
+			break;
+	}
+	return 0;
+}
+
+static void garp_pdu_rcv(const struct stp_proto *proto, struct sk_buff *skb,
+			 struct net_device *dev)
+{
+	struct garp_application *appl = proto->data;
+	struct garp_port *port;
+	struct garp_applicant *app;
+	const struct garp_pdu_hdr *gp;
+
+	port = rcu_dereference(dev->garp_port);
+	if (!port)
+		goto err;
+	app = rcu_dereference(port->applicants[appl->type]);
+	if (!app)
+		goto err;
+
+	if (!pskb_may_pull(skb, sizeof(*gp)))
+		goto err;
+	gp = (struct garp_pdu_hdr *)skb->data;
+	if (get_unaligned(&gp->protocol) != htons(GARP_PROTOCOL_ID))
+		goto err;
+	skb_pull(skb, sizeof(*gp));
+
+	spin_lock(&app->lock);
+	while (skb->len > 0) {
+		if (garp_pdu_parse_msg(app, skb) < 0)
+			break;
+		if (garp_pdu_parse_end_mark(skb) < 0)
+			break;
+	}
+	spin_unlock(&app->lock);
+err:
+	kfree_skb(skb);
+}
+
+static int garp_init_port(struct net_device *dev)
+{
+	struct garp_port *port;
+
+	port = kzalloc(sizeof(*port), GFP_KERNEL);
+	if (!port)
+		return -ENOMEM;
+	rcu_assign_pointer(dev->garp_port, port);
+	return 0;
+}
+
+static void garp_release_port(struct net_device *dev)
+{
+	struct garp_port *port = rtnl_dereference(dev->garp_port);
+	unsigned int i;
+
+	for (i = 0; i <= GARP_APPLICATION_MAX; i++) {
+		if (rtnl_dereference(port->applicants[i]))
+			return;
+	}
+	RCU_INIT_POINTER(dev->garp_port, NULL);
+	kfree_rcu(port, rcu);
+}
+
+int garp_init_applicant(struct net_device *dev, struct garp_application *appl)
+{
+	struct garp_applicant *app;
+	int err;
+
+	ASSERT_RTNL();
+
+	if (!rtnl_dereference(dev->garp_port)) {
+		err = garp_init_port(dev);
+		if (err < 0)
+			goto err1;
+	}
+
+	err = -ENOMEM;
+	app = kzalloc(sizeof(*app), GFP_KERNEL);
+	if (!app)
+		goto err2;
+
+	err = dev_mc_add(dev, appl->proto.group_address);
+	if (err < 0)
+		goto err3;
+
+	app->dev = dev;
+	app->app = appl;
+	app->gid = RB_ROOT;
+	spin_lock_init(&app->lock);
+	skb_queue_head_init(&app->queue);
+	rcu_assign_pointer(dev->garp_port->applicants[appl->type], app);
+	setup_timer(&app->join_timer, garp_join_timer, (unsigned long)app);
+	garp_join_timer_arm(app);
+	return 0;
+
+err3:
+	kfree(app);
+err2:
+	garp_release_port(dev);
+err1:
+	return err;
+}
+EXPORT_SYMBOL_GPL(garp_init_applicant);
+
+void garp_uninit_applicant(struct net_device *dev, struct garp_application *appl)
+{
+	struct garp_port *port = rtnl_dereference(dev->garp_port);
+	struct garp_applicant *app = rtnl_dereference(port->applicants[appl->type]);
+
+	ASSERT_RTNL();
+
+	RCU_INIT_POINTER(port->applicants[appl->type], NULL);
+
+	/* Delete timer and generate a final TRANSMIT_PDU event to flush out
+	 * all pending messages before the applicant is gone. */
+	del_timer_sync(&app->join_timer);
+
+	spin_lock_bh(&app->lock);
+	garp_gid_event(app, GARP_EVENT_TRANSMIT_PDU);
+	garp_pdu_queue(app);
+	spin_unlock_bh(&app->lock);
+
+	garp_queue_xmit(app);
+
+	dev_mc_del(dev, appl->proto.group_address);
+	kfree_rcu(app, rcu);
+	garp_release_port(dev);
+}
+EXPORT_SYMBOL_GPL(garp_uninit_applicant);
+
+int garp_register_application(struct garp_application *appl)
+{
+	appl->proto.rcv = garp_pdu_rcv;
+	appl->proto.data = appl;
+	return stp_proto_register(&appl->proto);
+}
+EXPORT_SYMBOL_GPL(garp_register_application);
+
+void garp_unregister_application(struct garp_application *appl)
+{
+	stp_proto_unregister(&appl->proto);
+}
+EXPORT_SYMBOL_GPL(garp_unregister_application);
diff --git a/net/802/hippi.c b/net/802/hippi.c
index 6d7fed3dd99..5ff2a718ddc 100644
--- a/net/802/hippi.c
+++ b/net/802/hippi.c
@@ -23,7 +23,6 @@
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
 #include <linux/string.h>
 #include <linux/mm.h>
 #include <linux/socket.h>
@@ -36,19 +35,17 @@
 #include <net/arp.h>
 #include <net/sock.h>
 #include <asm/uaccess.h>
-#include <asm/checksum.h>
-#include <asm/system.h>
 
 /*
- * Create the HIPPI MAC header for an arbitrary protocol layer 
+ * Create the HIPPI MAC header for an arbitrary protocol layer
  *
  * saddr=NULL	means use device source address
  * daddr=NULL	means leave destination address (eg unresolved arp)
  */
 
 static int hippi_header(struct sk_buff *skb, struct net_device *dev,
-			unsigned short type, void *daddr, void *saddr,
-			unsigned len)
+			unsigned short type,
+			const void *daddr, const void *saddr, unsigned int len)
 {
 	struct hippi_hdr *hip = (struct hippi_hdr *)skb_push(skb, HIPPI_HLEN);
 	struct hippi_cb *hcb = (struct hippi_cb *) skb->cb;
@@ -62,7 +59,7 @@ static int hippi_header(struct sk_buff *skb, struct net_device *dev,
 	 * Due to the stupidity of the little endian byte-order we
 	 * have to set the fp field this way.
 	 */
-	hip->fp.fixed		= __constant_htonl(0x04800018);
+	hip->fp.fixed		= htonl(0x04800018);
 	hip->fp.d2_size		= htonl(len + 8);
 	hip->le.fc		= 0;
 	hip->le.double_wide	= 0;	/* only HIPPI 800 for the time being */
@@ -105,8 +102,8 @@ static int hippi_rebuild_header(struct sk_buff *skb)
 	/*
 	 * Only IP is currently supported
 	 */
-	 
-	if(hip->snap.ethertype != __constant_htons(ETH_P_IP)) 
+
+	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;
@@ -123,19 +120,19 @@ static int hippi_rebuild_header(struct sk_buff *skb)
 /*
  *	Determine the packet's protocol ID.
  */
- 
+
 __be16 hippi_type_trans(struct sk_buff *skb, struct net_device *dev)
 {
 	struct hippi_hdr *hip;
-	
-	hip = (struct hippi_hdr *) skb->data;
 
 	/*
 	 * This is actually wrong ... question is if we really should
 	 * set the raw address here.
 	 */
-	 skb->mac.raw = skb->data;
-	 skb_pull(skb, HIPPI_HLEN);
+	skb->dev = dev;
+	skb_reset_mac_header(skb);
+	hip = (struct hippi_hdr *)skb_mac_header(skb);
+	skb_pull(skb, HIPPI_HLEN);
 
 	/*
 	 * No fancy promisc stuff here now.
@@ -146,7 +143,7 @@ __be16 hippi_type_trans(struct sk_buff *skb, struct net_device *dev)
 
 EXPORT_SYMBOL(hippi_type_trans);
 
-static int hippi_change_mtu(struct net_device *dev, int new_mtu)
+int hippi_change_mtu(struct net_device *dev, int new_mtu)
 {
 	/*
 	 * HIPPI's got these nice large MTUs.
@@ -154,14 +151,15 @@ static int hippi_change_mtu(struct net_device *dev, int new_mtu)
 	if ((new_mtu < 68) || (new_mtu > 65280))
 		return -EINVAL;
 	dev->mtu = new_mtu;
-	return(0);
+	return 0;
 }
+EXPORT_SYMBOL(hippi_change_mtu);
 
 /*
  * For HIPPI we will actually use the lower 4 bytes of the hardware
  * address as the I-FIELD rather than the actual hardware address.
  */
-static int hippi_mac_addr(struct net_device *dev, void *p)
+int hippi_mac_addr(struct net_device *dev, void *p)
 {
 	struct sockaddr *addr = p;
 	if (netif_running(dev))
@@ -169,32 +167,32 @@ static int hippi_mac_addr(struct net_device *dev, void *p)
 	memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
 	return 0;
 }
+EXPORT_SYMBOL(hippi_mac_addr);
 
-static int hippi_neigh_setup_dev(struct net_device *dev, struct neigh_parms *p)
+int hippi_neigh_setup_dev(struct net_device *dev, struct neigh_parms *p)
 {
 	/* Never send broadcast/multicast ARP messages */
-	p->mcast_probes = 0;
- 
+	NEIGH_VAR_INIT(p, MCAST_PROBES, 0);
+
 	/* In IPv6 unicast probes are valid even on NBMA,
 	* because they are encapsulated in normal IPv6 protocol.
-	* Should be a generic flag. 
+	* Should be a generic flag.
 	*/
 	if (p->tbl->family != AF_INET6)
-		p->ucast_probes = 0;
+		NEIGH_VAR_INIT(p, UCAST_PROBES, 0);
 	return 0;
 }
+EXPORT_SYMBOL(hippi_neigh_setup_dev);
+
+static const struct header_ops hippi_header_ops = {
+	.create		= hippi_header,
+	.rebuild	= hippi_rebuild_header,
+};
+
 
 static void hippi_setup(struct net_device *dev)
 {
-	dev->set_multicast_list		= NULL;
-	dev->change_mtu			= hippi_change_mtu;
-	dev->hard_header		= hippi_header;
-	dev->rebuild_header 		= hippi_rebuild_header;
-	dev->set_mac_address 		= hippi_mac_addr;
-	dev->hard_header_parse		= NULL;
-	dev->hard_header_cache		= NULL;
-	dev->header_cache_update	= NULL;
-	dev->neigh_setup 		= hippi_neigh_setup_dev; 
+	dev->header_ops			= &hippi_header_ops;
 
 	/*
 	 * We don't support HIPPI `ARP' for the time being, and probably
@@ -211,9 +209,9 @@ static void hippi_setup(struct net_device *dev)
 
 	/*
 	 * HIPPI doesn't support broadcast+multicast and we only use
-	 * static ARP tables. ARP is disabled by hippi_neigh_setup_dev. 
+	 * static ARP tables. ARP is disabled by hippi_neigh_setup_dev.
 	 */
-	dev->flags = 0; 
+	dev->flags = 0;
 }
 
 /**
diff --git a/net/802/mrp.c b/net/802/mrp.c
new file mode 100644
index 00000000000..72db2785ef2
--- /dev/null
+++ b/net/802/mrp.c
@@ -0,0 +1,926 @@
+/*
+ *	IEEE 802.1Q Multiple Registration Protocol (MRP)
+ *
+ *	Copyright (c) 2012 Massachusetts Institute of Technology
+ *
+ *	Adapted from code in net/802/garp.c
+ *	Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	version 2 as published by the Free Software Foundation.
+ */
+#include <linux/kernel.h>
+#include <linux/timer.h>
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <net/mrp.h>
+#include <asm/unaligned.h>
+
+static unsigned int mrp_join_time __read_mostly = 200;
+module_param(mrp_join_time, uint, 0644);
+MODULE_PARM_DESC(mrp_join_time, "Join time in ms (default 200ms)");
+
+static unsigned int mrp_periodic_time __read_mostly = 1000;
+module_param(mrp_periodic_time, uint, 0644);
+MODULE_PARM_DESC(mrp_periodic_time, "Periodic time in ms (default 1s)");
+
+MODULE_LICENSE("GPL");
+
+static const u8
+mrp_applicant_state_table[MRP_APPLICANT_MAX + 1][MRP_EVENT_MAX + 1] = {
+	[MRP_APPLICANT_VO] = {
+		[MRP_EVENT_NEW]		= MRP_APPLICANT_VN,
+		[MRP_EVENT_JOIN]	= MRP_APPLICANT_VP,
+		[MRP_EVENT_LV]		= MRP_APPLICANT_VO,
+		[MRP_EVENT_TX]		= MRP_APPLICANT_VO,
+		[MRP_EVENT_R_NEW]	= MRP_APPLICANT_VO,
+		[MRP_EVENT_R_JOIN_IN]	= MRP_APPLICANT_AO,
+		[MRP_EVENT_R_IN]	= MRP_APPLICANT_VO,
+		[MRP_EVENT_R_JOIN_MT]	= MRP_APPLICANT_VO,
+		[MRP_EVENT_R_MT]	= MRP_APPLICANT_VO,
+		[MRP_EVENT_R_LV]	= MRP_APPLICANT_VO,
+		[MRP_EVENT_R_LA]	= MRP_APPLICANT_VO,
+		[MRP_EVENT_REDECLARE]	= MRP_APPLICANT_VO,
+		[MRP_EVENT_PERIODIC]	= MRP_APPLICANT_VO,
+	},
+	[MRP_APPLICANT_VP] = {
+		[MRP_EVENT_NEW]		= MRP_APPLICANT_VN,
+		[MRP_EVENT_JOIN]	= MRP_APPLICANT_VP,
+		[MRP_EVENT_LV]		= MRP_APPLICANT_VO,
+		[MRP_EVENT_TX]		= MRP_APPLICANT_AA,
+		[MRP_EVENT_R_NEW]	= MRP_APPLICANT_VP,
+		[MRP_EVENT_R_JOIN_IN]	= MRP_APPLICANT_AP,
+		[MRP_EVENT_R_IN]	= MRP_APPLICANT_VP,
+		[MRP_EVENT_R_JOIN_MT]	= MRP_APPLICANT_VP,
+		[MRP_EVENT_R_MT]	= MRP_APPLICANT_VP,
+		[MRP_EVENT_R_LV]	= MRP_APPLICANT_VP,
+		[MRP_EVENT_R_LA]	= MRP_APPLICANT_VP,
+		[MRP_EVENT_REDECLARE]	= MRP_APPLICANT_VP,
+		[MRP_EVENT_PERIODIC]	= MRP_APPLICANT_VP,
+	},
+	[MRP_APPLICANT_VN] = {
+		[MRP_EVENT_NEW]		= MRP_APPLICANT_VN,
+		[MRP_EVENT_JOIN]	= MRP_APPLICANT_VN,
+		[MRP_EVENT_LV]		= MRP_APPLICANT_LA,
+		[MRP_EVENT_TX]		= MRP_APPLICANT_AN,
+		[MRP_EVENT_R_NEW]	= MRP_APPLICANT_VN,
+		[MRP_EVENT_R_JOIN_IN]	= MRP_APPLICANT_VN,
+		[MRP_EVENT_R_IN]	= MRP_APPLICANT_VN,
+		[MRP_EVENT_R_JOIN_MT]	= MRP_APPLICANT_VN,
+		[MRP_EVENT_R_MT]	= MRP_APPLICANT_VN,
+		[MRP_EVENT_R_LV]	= MRP_APPLICANT_VN,
+		[MRP_EVENT_R_LA]	= MRP_APPLICANT_VN,
+		[MRP_EVENT_REDECLARE]	= MRP_APPLICANT_VN,
+		[MRP_EVENT_PERIODIC]	= MRP_APPLICANT_VN,
+	},
+	[MRP_APPLICANT_AN] = {
+		[MRP_EVENT_NEW]		= MRP_APPLICANT_AN,
+		[MRP_EVENT_JOIN]	= MRP_APPLICANT_AN,
+		[MRP_EVENT_LV]		= MRP_APPLICANT_LA,
+		[MRP_EVENT_TX]		= MRP_APPLICANT_QA,
+		[MRP_EVENT_R_NEW]	= MRP_APPLICANT_AN,
+		[MRP_EVENT_R_JOIN_IN]	= MRP_APPLICANT_AN,
+		[MRP_EVENT_R_IN]	= MRP_APPLICANT_AN,
+		[MRP_EVENT_R_JOIN_MT]	= MRP_APPLICANT_AN,
+		[MRP_EVENT_R_MT]	= MRP_APPLICANT_AN,
+		[MRP_EVENT_R_LV]	= MRP_APPLICANT_VN,
+		[MRP_EVENT_R_LA]	= MRP_APPLICANT_VN,
+		[MRP_EVENT_REDECLARE]	= MRP_APPLICANT_VN,
+		[MRP_EVENT_PERIODIC]	= MRP_APPLICANT_AN,
+	},
+	[MRP_APPLICANT_AA] = {
+		[MRP_EVENT_NEW]		= MRP_APPLICANT_VN,
+		[MRP_EVENT_JOIN]	= MRP_APPLICANT_AA,
+		[MRP_EVENT_LV]		= MRP_APPLICANT_LA,
+		[MRP_EVENT_TX]		= MRP_APPLICANT_QA,
+		[MRP_EVENT_R_NEW]	= MRP_APPLICANT_AA,
+		[MRP_EVENT_R_JOIN_IN]	= MRP_APPLICANT_QA,
+		[MRP_EVENT_R_IN]	= MRP_APPLICANT_AA,
+		[MRP_EVENT_R_JOIN_MT]	= MRP_APPLICANT_AA,
+		[MRP_EVENT_R_MT]	= MRP_APPLICANT_AA,
+		[MRP_EVENT_R_LV]	= MRP_APPLICANT_VP,
+		[MRP_EVENT_R_LA]	= MRP_APPLICANT_VP,
+		[MRP_EVENT_REDECLARE]	= MRP_APPLICANT_VP,
+		[MRP_EVENT_PERIODIC]	= MRP_APPLICANT_AA,
+	},
+	[MRP_APPLICANT_QA] = {
+		[MRP_EVENT_NEW]		= MRP_APPLICANT_VN,
+		[MRP_EVENT_JOIN]	= MRP_APPLICANT_QA,
+		[MRP_EVENT_LV]		= MRP_APPLICANT_LA,
+		[MRP_EVENT_TX]		= MRP_APPLICANT_QA,
+		[MRP_EVENT_R_NEW]	= MRP_APPLICANT_QA,
+		[MRP_EVENT_R_JOIN_IN]	= MRP_APPLICANT_QA,
+		[MRP_EVENT_R_IN]	= MRP_APPLICANT_QA,
+		[MRP_EVENT_R_JOIN_MT]	= MRP_APPLICANT_AA,
+		[MRP_EVENT_R_MT]	= MRP_APPLICANT_AA,
+		[MRP_EVENT_R_LV]	= MRP_APPLICANT_VP,
+		[MRP_EVENT_R_LA]	= MRP_APPLICANT_VP,
+		[MRP_EVENT_REDECLARE]	= MRP_APPLICANT_VP,
+		[MRP_EVENT_PERIODIC]	= MRP_APPLICANT_AA,
+	},
+	[MRP_APPLICANT_LA] = {
+		[MRP_EVENT_NEW]		= MRP_APPLICANT_VN,
+		[MRP_EVENT_JOIN]	= MRP_APPLICANT_AA,
+		[MRP_EVENT_LV]		= MRP_APPLICANT_LA,
+		[MRP_EVENT_TX]		= MRP_APPLICANT_VO,
+		[MRP_EVENT_R_NEW]	= MRP_APPLICANT_LA,
+		[MRP_EVENT_R_JOIN_IN]	= MRP_APPLICANT_LA,
+		[MRP_EVENT_R_IN]	= MRP_APPLICANT_LA,
+		[MRP_EVENT_R_JOIN_MT]	= MRP_APPLICANT_LA,
+		[MRP_EVENT_R_MT]	= MRP_APPLICANT_LA,
+		[MRP_EVENT_R_LV]	= MRP_APPLICANT_LA,
+		[MRP_EVENT_R_LA]	= MRP_APPLICANT_LA,
+		[MRP_EVENT_REDECLARE]	= MRP_APPLICANT_LA,
+		[MRP_EVENT_PERIODIC]	= MRP_APPLICANT_LA,
+	},
+	[MRP_APPLICANT_AO] = {
+		[MRP_EVENT_NEW]		= MRP_APPLICANT_VN,
+		[MRP_EVENT_JOIN]	= MRP_APPLICANT_AP,
+		[MRP_EVENT_LV]		= MRP_APPLICANT_AO,
+		[MRP_EVENT_TX]		= MRP_APPLICANT_AO,
+		[MRP_EVENT_R_NEW]	= MRP_APPLICANT_AO,
+		[MRP_EVENT_R_JOIN_IN]	= MRP_APPLICANT_QO,
+		[MRP_EVENT_R_IN]	= MRP_APPLICANT_AO,
+		[MRP_EVENT_R_JOIN_MT]	= MRP_APPLICANT_AO,
+		[MRP_EVENT_R_MT]	= MRP_APPLICANT_AO,
+		[MRP_EVENT_R_LV]	= MRP_APPLICANT_VO,
+		[MRP_EVENT_R_LA]	= MRP_APPLICANT_VO,
+		[MRP_EVENT_REDECLARE]	= MRP_APPLICANT_VO,
+		[MRP_EVENT_PERIODIC]	= MRP_APPLICANT_AO,
+	},
+	[MRP_APPLICANT_QO] = {
+		[MRP_EVENT_NEW]		= MRP_APPLICANT_VN,
+		[MRP_EVENT_JOIN]	= MRP_APPLICANT_QP,
+		[MRP_EVENT_LV]		= MRP_APPLICANT_QO,
+		[MRP_EVENT_TX]		= MRP_APPLICANT_QO,
+		[MRP_EVENT_R_NEW]	= MRP_APPLICANT_QO,
+		[MRP_EVENT_R_JOIN_IN]	= MRP_APPLICANT_QO,
+		[MRP_EVENT_R_IN]	= MRP_APPLICANT_QO,
+		[MRP_EVENT_R_JOIN_MT]	= MRP_APPLICANT_AO,
+		[MRP_EVENT_R_MT]	= MRP_APPLICANT_AO,
+		[MRP_EVENT_R_LV]	= MRP_APPLICANT_VO,
+		[MRP_EVENT_R_LA]	= MRP_APPLICANT_VO,
+		[MRP_EVENT_REDECLARE]	= MRP_APPLICANT_VO,
+		[MRP_EVENT_PERIODIC]	= MRP_APPLICANT_QO,
+	},
+	[MRP_APPLICANT_AP] = {
+		[MRP_EVENT_NEW]		= MRP_APPLICANT_VN,
+		[MRP_EVENT_JOIN]	= MRP_APPLICANT_AP,
+		[MRP_EVENT_LV]		= MRP_APPLICANT_AO,
+		[MRP_EVENT_TX]		= MRP_APPLICANT_QA,
+		[MRP_EVENT_R_NEW]	= MRP_APPLICANT_AP,
+		[MRP_EVENT_R_JOIN_IN]	= MRP_APPLICANT_QP,
+		[MRP_EVENT_R_IN]	= MRP_APPLICANT_AP,
+		[MRP_EVENT_R_JOIN_MT]	= MRP_APPLICANT_AP,
+		[MRP_EVENT_R_MT]	= MRP_APPLICANT_AP,
+		[MRP_EVENT_R_LV]	= MRP_APPLICANT_VP,
+		[MRP_EVENT_R_LA]	= MRP_APPLICANT_VP,
+		[MRP_EVENT_REDECLARE]	= MRP_APPLICANT_VP,
+		[MRP_EVENT_PERIODIC]	= MRP_APPLICANT_AP,
+	},
+	[MRP_APPLICANT_QP] = {
+		[MRP_EVENT_NEW]		= MRP_APPLICANT_VN,
+		[MRP_EVENT_JOIN]	= MRP_APPLICANT_QP,
+		[MRP_EVENT_LV]		= MRP_APPLICANT_QO,
+		[MRP_EVENT_TX]		= MRP_APPLICANT_QP,
+		[MRP_EVENT_R_NEW]	= MRP_APPLICANT_QP,
+		[MRP_EVENT_R_JOIN_IN]	= MRP_APPLICANT_QP,
+		[MRP_EVENT_R_IN]	= MRP_APPLICANT_QP,
+		[MRP_EVENT_R_JOIN_MT]	= MRP_APPLICANT_AP,
+		[MRP_EVENT_R_MT]	= MRP_APPLICANT_AP,
+		[MRP_EVENT_R_LV]	= MRP_APPLICANT_VP,
+		[MRP_EVENT_R_LA]	= MRP_APPLICANT_VP,
+		[MRP_EVENT_REDECLARE]	= MRP_APPLICANT_VP,
+		[MRP_EVENT_PERIODIC]	= MRP_APPLICANT_AP,
+	},
+};
+
+static const u8
+mrp_tx_action_table[MRP_APPLICANT_MAX + 1] = {
+	[MRP_APPLICANT_VO] = MRP_TX_ACTION_S_IN_OPTIONAL,
+	[MRP_APPLICANT_VP] = MRP_TX_ACTION_S_JOIN_IN,
+	[MRP_APPLICANT_VN] = MRP_TX_ACTION_S_NEW,
+	[MRP_APPLICANT_AN] = MRP_TX_ACTION_S_NEW,
+	[MRP_APPLICANT_AA] = MRP_TX_ACTION_S_JOIN_IN,
+	[MRP_APPLICANT_QA] = MRP_TX_ACTION_S_JOIN_IN_OPTIONAL,
+	[MRP_APPLICANT_LA] = MRP_TX_ACTION_S_LV,
+	[MRP_APPLICANT_AO] = MRP_TX_ACTION_S_IN_OPTIONAL,
+	[MRP_APPLICANT_QO] = MRP_TX_ACTION_S_IN_OPTIONAL,
+	[MRP_APPLICANT_AP] = MRP_TX_ACTION_S_JOIN_IN,
+	[MRP_APPLICANT_QP] = MRP_TX_ACTION_S_IN_OPTIONAL,
+};
+
+static void mrp_attrvalue_inc(void *value, u8 len)
+{
+	u8 *v = (u8 *)value;
+
+	/* Add 1 to the last byte. If it becomes zero,
+	 * go to the previous byte and repeat.
+	 */
+	while (len > 0 && !++v[--len])
+		;
+}
+
+static int mrp_attr_cmp(const struct mrp_attr *attr,
+			 const void *value, u8 len, u8 type)
+{
+	if (attr->type != type)
+		return attr->type - type;
+	if (attr->len != len)
+		return attr->len - len;
+	return memcmp(attr->value, value, len);
+}
+
+static struct mrp_attr *mrp_attr_lookup(const struct mrp_applicant *app,
+					const void *value, u8 len, u8 type)
+{
+	struct rb_node *parent = app->mad.rb_node;
+	struct mrp_attr *attr;
+	int d;
+
+	while (parent) {
+		attr = rb_entry(parent, struct mrp_attr, node);
+		d = mrp_attr_cmp(attr, value, len, type);
+		if (d > 0)
+			parent = parent->rb_left;
+		else if (d < 0)
+			parent = parent->rb_right;
+		else
+			return attr;
+	}
+	return NULL;
+}
+
+static struct mrp_attr *mrp_attr_create(struct mrp_applicant *app,
+					const void *value, u8 len, u8 type)
+{
+	struct rb_node *parent = NULL, **p = &app->mad.rb_node;
+	struct mrp_attr *attr;
+	int d;
+
+	while (*p) {
+		parent = *p;
+		attr = rb_entry(parent, struct mrp_attr, node);
+		d = mrp_attr_cmp(attr, value, len, type);
+		if (d > 0)
+			p = &parent->rb_left;
+		else if (d < 0)
+			p = &parent->rb_right;
+		else {
+			/* The attribute already exists; re-use it. */
+			return attr;
+		}
+	}
+	attr = kmalloc(sizeof(*attr) + len, GFP_ATOMIC);
+	if (!attr)
+		return attr;
+	attr->state = MRP_APPLICANT_VO;
+	attr->type  = type;
+	attr->len   = len;
+	memcpy(attr->value, value, len);
+
+	rb_link_node(&attr->node, parent, p);
+	rb_insert_color(&attr->node, &app->mad);
+	return attr;
+}
+
+static void mrp_attr_destroy(struct mrp_applicant *app, struct mrp_attr *attr)
+{
+	rb_erase(&attr->node, &app->mad);
+	kfree(attr);
+}
+
+static int mrp_pdu_init(struct mrp_applicant *app)
+{
+	struct sk_buff *skb;
+	struct mrp_pdu_hdr *ph;
+
+	skb = alloc_skb(app->dev->mtu + LL_RESERVED_SPACE(app->dev),
+			GFP_ATOMIC);
+	if (!skb)
+		return -ENOMEM;
+
+	skb->dev = app->dev;
+	skb->protocol = app->app->pkttype.type;
+	skb_reserve(skb, LL_RESERVED_SPACE(app->dev));
+	skb_reset_network_header(skb);
+	skb_reset_transport_header(skb);
+
+	ph = (struct mrp_pdu_hdr *)__skb_put(skb, sizeof(*ph));
+	ph->version = app->app->version;
+
+	app->pdu = skb;
+	return 0;
+}
+
+static int mrp_pdu_append_end_mark(struct mrp_applicant *app)
+{
+	__be16 *endmark;
+
+	if (skb_tailroom(app->pdu) < sizeof(*endmark))
+		return -1;
+	endmark = (__be16 *)__skb_put(app->pdu, sizeof(*endmark));
+	put_unaligned(MRP_END_MARK, endmark);
+	return 0;
+}
+
+static void mrp_pdu_queue(struct mrp_applicant *app)
+{
+	if (!app->pdu)
+		return;
+
+	if (mrp_cb(app->pdu)->mh)
+		mrp_pdu_append_end_mark(app);
+	mrp_pdu_append_end_mark(app);
+
+	dev_hard_header(app->pdu, app->dev, ntohs(app->app->pkttype.type),
+			app->app->group_address, app->dev->dev_addr,
+			app->pdu->len);
+
+	skb_queue_tail(&app->queue, app->pdu);
+	app->pdu = NULL;
+}
+
+static void mrp_queue_xmit(struct mrp_applicant *app)
+{
+	struct sk_buff *skb;
+
+	while ((skb = skb_dequeue(&app->queue)))
+		dev_queue_xmit(skb);
+}
+
+static int mrp_pdu_append_msg_hdr(struct mrp_applicant *app,
+				  u8 attrtype, u8 attrlen)
+{
+	struct mrp_msg_hdr *mh;
+
+	if (mrp_cb(app->pdu)->mh) {
+		if (mrp_pdu_append_end_mark(app) < 0)
+			return -1;
+		mrp_cb(app->pdu)->mh = NULL;
+		mrp_cb(app->pdu)->vah = NULL;
+	}
+
+	if (skb_tailroom(app->pdu) < sizeof(*mh))
+		return -1;
+	mh = (struct mrp_msg_hdr *)__skb_put(app->pdu, sizeof(*mh));
+	mh->attrtype = attrtype;
+	mh->attrlen = attrlen;
+	mrp_cb(app->pdu)->mh = mh;
+	return 0;
+}
+
+static int mrp_pdu_append_vecattr_hdr(struct mrp_applicant *app,
+				      const void *firstattrvalue, u8 attrlen)
+{
+	struct mrp_vecattr_hdr *vah;
+
+	if (skb_tailroom(app->pdu) < sizeof(*vah) + attrlen)
+		return -1;
+	vah = (struct mrp_vecattr_hdr *)__skb_put(app->pdu,
+						  sizeof(*vah) + attrlen);
+	put_unaligned(0, &vah->lenflags);
+	memcpy(vah->firstattrvalue, firstattrvalue, attrlen);
+	mrp_cb(app->pdu)->vah = vah;
+	memcpy(mrp_cb(app->pdu)->attrvalue, firstattrvalue, attrlen);
+	return 0;
+}
+
+static int mrp_pdu_append_vecattr_event(struct mrp_applicant *app,
+					const struct mrp_attr *attr,
+					enum mrp_vecattr_event vaevent)
+{
+	u16 len, pos;
+	u8 *vaevents;
+	int err;
+again:
+	if (!app->pdu) {
+		err = mrp_pdu_init(app);
+		if (err < 0)
+			return err;
+	}
+
+	/* If there is no Message header in the PDU, or the Message header is
+	 * for a different attribute type, add an EndMark (if necessary) and a
+	 * new Message header to the PDU.
+	 */
+	if (!mrp_cb(app->pdu)->mh ||
+	    mrp_cb(app->pdu)->mh->attrtype != attr->type ||
+	    mrp_cb(app->pdu)->mh->attrlen != attr->len) {
+		if (mrp_pdu_append_msg_hdr(app, attr->type, attr->len) < 0)
+			goto queue;
+	}
+
+	/* If there is no VectorAttribute header for this Message in the PDU,
+	 * or this attribute's value does not sequentially follow the previous
+	 * attribute's value, add a new VectorAttribute header to the PDU.
+	 */
+	if (!mrp_cb(app->pdu)->vah ||
+	    memcmp(mrp_cb(app->pdu)->attrvalue, attr->value, attr->len)) {
+		if (mrp_pdu_append_vecattr_hdr(app, attr->value, attr->len) < 0)
+			goto queue;
+	}
+
+	len = be16_to_cpu(get_unaligned(&mrp_cb(app->pdu)->vah->lenflags));
+	pos = len % 3;
+
+	/* Events are packed into Vectors in the PDU, three to a byte. Add a
+	 * byte to the end of the Vector if necessary.
+	 */
+	if (!pos) {
+		if (skb_tailroom(app->pdu) < sizeof(u8))
+			goto queue;
+		vaevents = (u8 *)__skb_put(app->pdu, sizeof(u8));
+	} else {
+		vaevents = (u8 *)(skb_tail_pointer(app->pdu) - sizeof(u8));
+	}
+
+	switch (pos) {
+	case 0:
+		*vaevents = vaevent * (__MRP_VECATTR_EVENT_MAX *
+				       __MRP_VECATTR_EVENT_MAX);
+		break;
+	case 1:
+		*vaevents += vaevent * __MRP_VECATTR_EVENT_MAX;
+		break;
+	case 2:
+		*vaevents += vaevent;
+		break;
+	default:
+		WARN_ON(1);
+	}
+
+	/* Increment the length of the VectorAttribute in the PDU, as well as
+	 * the value of the next attribute that would continue its Vector.
+	 */
+	put_unaligned(cpu_to_be16(++len), &mrp_cb(app->pdu)->vah->lenflags);
+	mrp_attrvalue_inc(mrp_cb(app->pdu)->attrvalue, attr->len);
+
+	return 0;
+
+queue:
+	mrp_pdu_queue(app);
+	goto again;
+}
+
+static void mrp_attr_event(struct mrp_applicant *app,
+			   struct mrp_attr *attr, enum mrp_event event)
+{
+	enum mrp_applicant_state state;
+
+	state = mrp_applicant_state_table[attr->state][event];
+	if (state == MRP_APPLICANT_INVALID) {
+		WARN_ON(1);
+		return;
+	}
+
+	if (event == MRP_EVENT_TX) {
+		/* When appending the attribute fails, don't update its state
+		 * in order to retry at the next TX event.
+		 */
+
+		switch (mrp_tx_action_table[attr->state]) {
+		case MRP_TX_ACTION_NONE:
+		case MRP_TX_ACTION_S_JOIN_IN_OPTIONAL:
+		case MRP_TX_ACTION_S_IN_OPTIONAL:
+			break;
+		case MRP_TX_ACTION_S_NEW:
+			if (mrp_pdu_append_vecattr_event(
+				    app, attr, MRP_VECATTR_EVENT_NEW) < 0)
+				return;
+			break;
+		case MRP_TX_ACTION_S_JOIN_IN:
+			if (mrp_pdu_append_vecattr_event(
+				    app, attr, MRP_VECATTR_EVENT_JOIN_IN) < 0)
+				return;
+			break;
+		case MRP_TX_ACTION_S_LV:
+			if (mrp_pdu_append_vecattr_event(
+				    app, attr, MRP_VECATTR_EVENT_LV) < 0)
+				return;
+			/* As a pure applicant, sending a leave message
+			 * implies that the attribute was unregistered and
+			 * can be destroyed.
+			 */
+			mrp_attr_destroy(app, attr);
+			return;
+		default:
+			WARN_ON(1);
+		}
+	}
+
+	attr->state = state;
+}
+
+int mrp_request_join(const struct net_device *dev,
+		     const struct mrp_application *appl,
+		     const void *value, u8 len, u8 type)
+{
+	struct mrp_port *port = rtnl_dereference(dev->mrp_port);
+	struct mrp_applicant *app = rtnl_dereference(
+		port->applicants[appl->type]);
+	struct mrp_attr *attr;
+
+	if (sizeof(struct mrp_skb_cb) + len >
+	    FIELD_SIZEOF(struct sk_buff, cb))
+		return -ENOMEM;
+
+	spin_lock_bh(&app->lock);
+	attr = mrp_attr_create(app, value, len, type);
+	if (!attr) {
+		spin_unlock_bh(&app->lock);
+		return -ENOMEM;
+	}
+	mrp_attr_event(app, attr, MRP_EVENT_JOIN);
+	spin_unlock_bh(&app->lock);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mrp_request_join);
+
+void mrp_request_leave(const struct net_device *dev,
+		       const struct mrp_application *appl,
+		       const void *value, u8 len, u8 type)
+{
+	struct mrp_port *port = rtnl_dereference(dev->mrp_port);
+	struct mrp_applicant *app = rtnl_dereference(
+		port->applicants[appl->type]);
+	struct mrp_attr *attr;
+
+	if (sizeof(struct mrp_skb_cb) + len >
+	    FIELD_SIZEOF(struct sk_buff, cb))
+		return;
+
+	spin_lock_bh(&app->lock);
+	attr = mrp_attr_lookup(app, value, len, type);
+	if (!attr) {
+		spin_unlock_bh(&app->lock);
+		return;
+	}
+	mrp_attr_event(app, attr, MRP_EVENT_LV);
+	spin_unlock_bh(&app->lock);
+}
+EXPORT_SYMBOL_GPL(mrp_request_leave);
+
+static void mrp_mad_event(struct mrp_applicant *app, enum mrp_event event)
+{
+	struct rb_node *node, *next;
+	struct mrp_attr *attr;
+
+	for (node = rb_first(&app->mad);
+	     next = node ? rb_next(node) : NULL, node != NULL;
+	     node = next) {
+		attr = rb_entry(node, struct mrp_attr, node);
+		mrp_attr_event(app, attr, event);
+	}
+}
+
+static void mrp_join_timer_arm(struct mrp_applicant *app)
+{
+	unsigned long delay;
+
+	delay = (u64)msecs_to_jiffies(mrp_join_time) * prandom_u32() >> 32;
+	mod_timer(&app->join_timer, jiffies + delay);
+}
+
+static void mrp_join_timer(unsigned long data)
+{
+	struct mrp_applicant *app = (struct mrp_applicant *)data;
+
+	spin_lock(&app->lock);
+	mrp_mad_event(app, MRP_EVENT_TX);
+	mrp_pdu_queue(app);
+	spin_unlock(&app->lock);
+
+	mrp_queue_xmit(app);
+	mrp_join_timer_arm(app);
+}
+
+static void mrp_periodic_timer_arm(struct mrp_applicant *app)
+{
+	mod_timer(&app->periodic_timer,
+		  jiffies + msecs_to_jiffies(mrp_periodic_time));
+}
+
+static void mrp_periodic_timer(unsigned long data)
+{
+	struct mrp_applicant *app = (struct mrp_applicant *)data;
+
+	spin_lock(&app->lock);
+	mrp_mad_event(app, MRP_EVENT_PERIODIC);
+	mrp_pdu_queue(app);
+	spin_unlock(&app->lock);
+
+	mrp_periodic_timer_arm(app);
+}
+
+static int mrp_pdu_parse_end_mark(struct sk_buff *skb, int *offset)
+{
+	__be16 endmark;
+
+	if (skb_copy_bits(skb, *offset, &endmark, sizeof(endmark)) < 0)
+		return -1;
+	if (endmark == MRP_END_MARK) {
+		*offset += sizeof(endmark);
+		return -1;
+	}
+	return 0;
+}
+
+static void mrp_pdu_parse_vecattr_event(struct mrp_applicant *app,
+					struct sk_buff *skb,
+					enum mrp_vecattr_event vaevent)
+{
+	struct mrp_attr *attr;
+	enum mrp_event event;
+
+	attr = mrp_attr_lookup(app, mrp_cb(skb)->attrvalue,
+			       mrp_cb(skb)->mh->attrlen,
+			       mrp_cb(skb)->mh->attrtype);
+	if (attr == NULL)
+		return;
+
+	switch (vaevent) {
+	case MRP_VECATTR_EVENT_NEW:
+		event = MRP_EVENT_R_NEW;
+		break;
+	case MRP_VECATTR_EVENT_JOIN_IN:
+		event = MRP_EVENT_R_JOIN_IN;
+		break;
+	case MRP_VECATTR_EVENT_IN:
+		event = MRP_EVENT_R_IN;
+		break;
+	case MRP_VECATTR_EVENT_JOIN_MT:
+		event = MRP_EVENT_R_JOIN_MT;
+		break;
+	case MRP_VECATTR_EVENT_MT:
+		event = MRP_EVENT_R_MT;
+		break;
+	case MRP_VECATTR_EVENT_LV:
+		event = MRP_EVENT_R_LV;
+		break;
+	default:
+		return;
+	}
+
+	mrp_attr_event(app, attr, event);
+}
+
+static int mrp_pdu_parse_vecattr(struct mrp_applicant *app,
+				 struct sk_buff *skb, int *offset)
+{
+	struct mrp_vecattr_hdr _vah;
+	u16 valen;
+	u8 vaevents, vaevent;
+
+	mrp_cb(skb)->vah = skb_header_pointer(skb, *offset, sizeof(_vah),
+					      &_vah);
+	if (!mrp_cb(skb)->vah)
+		return -1;
+	*offset += sizeof(_vah);
+
+	if (get_unaligned(&mrp_cb(skb)->vah->lenflags) &
+	    MRP_VECATTR_HDR_FLAG_LA)
+		mrp_mad_event(app, MRP_EVENT_R_LA);
+	valen = be16_to_cpu(get_unaligned(&mrp_cb(skb)->vah->lenflags) &
+			    MRP_VECATTR_HDR_LEN_MASK);
+
+	/* The VectorAttribute structure in a PDU carries event information
+	 * about one or more attributes having consecutive values. Only the
+	 * value for the first attribute is contained in the structure. So
+	 * we make a copy of that value, and then increment it each time we
+	 * advance to the next event in its Vector.
+	 */
+	if (sizeof(struct mrp_skb_cb) + mrp_cb(skb)->mh->attrlen >
+	    FIELD_SIZEOF(struct sk_buff, cb))
+		return -1;
+	if (skb_copy_bits(skb, *offset, mrp_cb(skb)->attrvalue,
+			  mrp_cb(skb)->mh->attrlen) < 0)
+		return -1;
+	*offset += mrp_cb(skb)->mh->attrlen;
+
+	/* In a VectorAttribute, the Vector contains events which are packed
+	 * three to a byte. We process one byte of the Vector at a time.
+	 */
+	while (valen > 0) {
+		if (skb_copy_bits(skb, *offset, &vaevents,
+				  sizeof(vaevents)) < 0)
+			return -1;
+		*offset += sizeof(vaevents);
+
+		/* Extract and process the first event. */
+		vaevent = vaevents / (__MRP_VECATTR_EVENT_MAX *
+				      __MRP_VECATTR_EVENT_MAX);
+		if (vaevent >= __MRP_VECATTR_EVENT_MAX) {
+			/* The byte is malformed; stop processing. */
+			return -1;
+		}
+		mrp_pdu_parse_vecattr_event(app, skb, vaevent);
+
+		/* If present, extract and process the second event. */
+		if (!--valen)
+			break;
+		mrp_attrvalue_inc(mrp_cb(skb)->attrvalue,
+				  mrp_cb(skb)->mh->attrlen);
+		vaevents %= (__MRP_VECATTR_EVENT_MAX *
+			     __MRP_VECATTR_EVENT_MAX);
+		vaevent = vaevents / __MRP_VECATTR_EVENT_MAX;
+		mrp_pdu_parse_vecattr_event(app, skb, vaevent);
+
+		/* If present, extract and process the third event. */
+		if (!--valen)
+			break;
+		mrp_attrvalue_inc(mrp_cb(skb)->attrvalue,
+				  mrp_cb(skb)->mh->attrlen);
+		vaevents %= __MRP_VECATTR_EVENT_MAX;
+		vaevent = vaevents;
+		mrp_pdu_parse_vecattr_event(app, skb, vaevent);
+	}
+	return 0;
+}
+
+static int mrp_pdu_parse_msg(struct mrp_applicant *app, struct sk_buff *skb,
+			     int *offset)
+{
+	struct mrp_msg_hdr _mh;
+
+	mrp_cb(skb)->mh = skb_header_pointer(skb, *offset, sizeof(_mh), &_mh);
+	if (!mrp_cb(skb)->mh)
+		return -1;
+	*offset += sizeof(_mh);
+
+	if (mrp_cb(skb)->mh->attrtype == 0 ||
+	    mrp_cb(skb)->mh->attrtype > app->app->maxattr ||
+	    mrp_cb(skb)->mh->attrlen == 0)
+		return -1;
+
+	while (skb->len > *offset) {
+		if (mrp_pdu_parse_end_mark(skb, offset) < 0)
+			break;
+		if (mrp_pdu_parse_vecattr(app, skb, offset) < 0)
+			return -1;
+	}
+	return 0;
+}
+
+static int mrp_rcv(struct sk_buff *skb, struct net_device *dev,
+		   struct packet_type *pt, struct net_device *orig_dev)
+{
+	struct mrp_application *appl = container_of(pt, struct mrp_application,
+						    pkttype);
+	struct mrp_port *port;
+	struct mrp_applicant *app;
+	struct mrp_pdu_hdr _ph;
+	const struct mrp_pdu_hdr *ph;
+	int offset = skb_network_offset(skb);
+
+	/* If the interface is in promiscuous mode, drop the packet if
+	 * it was unicast to another host.
+	 */
+	if (unlikely(skb->pkt_type == PACKET_OTHERHOST))
+		goto out;
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (unlikely(!skb))
+		goto out;
+	port = rcu_dereference(dev->mrp_port);
+	if (unlikely(!port))
+		goto out;
+	app = rcu_dereference(port->applicants[appl->type]);
+	if (unlikely(!app))
+		goto out;
+
+	ph = skb_header_pointer(skb, offset, sizeof(_ph), &_ph);
+	if (!ph)
+		goto out;
+	offset += sizeof(_ph);
+
+	if (ph->version != app->app->version)
+		goto out;
+
+	spin_lock(&app->lock);
+	while (skb->len > offset) {
+		if (mrp_pdu_parse_end_mark(skb, &offset) < 0)
+			break;
+		if (mrp_pdu_parse_msg(app, skb, &offset) < 0)
+			break;
+	}
+	spin_unlock(&app->lock);
+out:
+	kfree_skb(skb);
+	return 0;
+}
+
+static int mrp_init_port(struct net_device *dev)
+{
+	struct mrp_port *port;
+
+	port = kzalloc(sizeof(*port), GFP_KERNEL);
+	if (!port)
+		return -ENOMEM;
+	rcu_assign_pointer(dev->mrp_port, port);
+	return 0;
+}
+
+static void mrp_release_port(struct net_device *dev)
+{
+	struct mrp_port *port = rtnl_dereference(dev->mrp_port);
+	unsigned int i;
+
+	for (i = 0; i <= MRP_APPLICATION_MAX; i++) {
+		if (rtnl_dereference(port->applicants[i]))
+			return;
+	}
+	RCU_INIT_POINTER(dev->mrp_port, NULL);
+	kfree_rcu(port, rcu);
+}
+
+int mrp_init_applicant(struct net_device *dev, struct mrp_application *appl)
+{
+	struct mrp_applicant *app;
+	int err;
+
+	ASSERT_RTNL();
+
+	if (!rtnl_dereference(dev->mrp_port)) {
+		err = mrp_init_port(dev);
+		if (err < 0)
+			goto err1;
+	}
+
+	err = -ENOMEM;
+	app = kzalloc(sizeof(*app), GFP_KERNEL);
+	if (!app)
+		goto err2;
+
+	err = dev_mc_add(dev, appl->group_address);
+	if (err < 0)
+		goto err3;
+
+	app->dev = dev;
+	app->app = appl;
+	app->mad = RB_ROOT;
+	spin_lock_init(&app->lock);
+	skb_queue_head_init(&app->queue);
+	rcu_assign_pointer(dev->mrp_port->applicants[appl->type], app);
+	setup_timer(&app->join_timer, mrp_join_timer, (unsigned long)app);
+	mrp_join_timer_arm(app);
+	setup_timer(&app->periodic_timer, mrp_periodic_timer,
+		    (unsigned long)app);
+	mrp_periodic_timer_arm(app);
+	return 0;
+
+err3:
+	kfree(app);
+err2:
+	mrp_release_port(dev);
+err1:
+	return err;
+}
+EXPORT_SYMBOL_GPL(mrp_init_applicant);
+
+void mrp_uninit_applicant(struct net_device *dev, struct mrp_application *appl)
+{
+	struct mrp_port *port = rtnl_dereference(dev->mrp_port);
+	struct mrp_applicant *app = rtnl_dereference(
+		port->applicants[appl->type]);
+
+	ASSERT_RTNL();
+
+	RCU_INIT_POINTER(port->applicants[appl->type], NULL);
+
+	/* Delete timer and generate a final TX event to flush out
+	 * all pending messages before the applicant is gone.
+	 */
+	del_timer_sync(&app->join_timer);
+	del_timer_sync(&app->periodic_timer);
+
+	spin_lock_bh(&app->lock);
+	mrp_mad_event(app, MRP_EVENT_TX);
+	mrp_pdu_queue(app);
+	spin_unlock_bh(&app->lock);
+
+	mrp_queue_xmit(app);
+
+	dev_mc_del(dev, appl->group_address);
+	kfree_rcu(app, rcu);
+	mrp_release_port(dev);
+}
+EXPORT_SYMBOL_GPL(mrp_uninit_applicant);
+
+int mrp_register_application(struct mrp_application *appl)
+{
+	appl->pkttype.func = mrp_rcv;
+	dev_add_pack(&appl->pkttype);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mrp_register_application);
+
+void mrp_unregister_application(struct mrp_application *appl)
+{
+	dev_remove_pack(&appl->pkttype);
+}
+EXPORT_SYMBOL_GPL(mrp_unregister_application);
diff --git a/net/802/p8022.c b/net/802/p8022.c
index 2530f35241c..0bda8de7df5 100644
--- a/net/802/p8022.c
+++ b/net/802/p8022.c
@@ -1,6 +1,5 @@
 /*
- *	NET3:	Support for 802.2 demultiplexing off Ethernet (Token ring
- *		is kept separate see p8022tr.c)
+ *	NET3:	Support for 802.2 demultiplexing off Ethernet
  *		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
@@ -18,6 +17,7 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
+#include <linux/slab.h>
 #include <net/datalink.h>
 #include <linux/mm.h>
 #include <linux/in.h>
diff --git a/net/802/p8023.c b/net/802/p8023.c
index d23e906456e..1256a40da43 100644
--- a/net/802/p8023.c
+++ b/net/802/p8023.c
@@ -18,6 +18,7 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
+#include <linux/slab.h>
 
 #include <net/datalink.h>
 #include <net/p8022.h>
@@ -31,7 +32,7 @@ static int p8023_request(struct datalink_proto *dl,
 {
 	struct net_device *dev = skb->dev;
 
-	dev->hard_header(skb, dev, ETH_P_802_3, dest_node, NULL, skb->len);
+	dev_hard_header(skb, dev, ETH_P_802_3, dest_node, NULL, skb->len);
 	return dev_queue_xmit(skb);
 }
 
@@ -59,3 +60,5 @@ void destroy_8023_client(struct datalink_proto *dl)
 
 EXPORT_SYMBOL(destroy_8023_client);
 EXPORT_SYMBOL(make_8023_client);
+
+MODULE_LICENSE("GPL");
diff --git a/net/802/psnap.c b/net/802/psnap.c
index 34e42968b47..db6baf7cf6e 100644
--- a/net/802/psnap.c
+++ b/net/802/psnap.c
@@ -1,7 +1,7 @@
 /*
  *	SNAP data link layer. Derived from 802.2
  *
- *		Alan Cox <Alan.Cox@linux.org>,
+ *		Alan Cox <alan@lxorguk.ukuu.org.uk>,
  *		from the 802.2 layer by Greg Page.
  *		Merged in additions from Greg Page's psnap.c.
  *
@@ -14,12 +14,14 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
+#include <linux/slab.h>
 #include <net/datalink.h>
 #include <net/llc.h>
 #include <net/psnap.h>
 #include <linux/mm.h>
 #include <linux/in.h>
 #include <linux/init.h>
+#include <linux/rculist.h>
 
 static LIST_HEAD(snap_list);
 static DEFINE_SPINLOCK(snap_lock);
@@ -28,13 +30,11 @@ static struct llc_sap *snap_sap;
 /*
  *	Find a snap client by matching the 5 bytes.
  */
-static struct datalink_proto *find_snap_client(unsigned char *desc)
+static struct datalink_proto *find_snap_client(const unsigned char *desc)
 {
-	struct list_head *entry;
 	struct datalink_proto *proto = NULL, *p;
 
-	list_for_each_rcu(entry, &snap_list) {
-		p = list_entry(entry, struct datalink_proto, node);
+	list_for_each_entry_rcu(p, &snap_list, node) {
 		if (!memcmp(p->type, desc, 5)) {
 			proto = p;
 			break;
@@ -52,26 +52,31 @@ static int snap_rcv(struct sk_buff *skb, struct net_device *dev,
 	int rc = 1;
 	struct datalink_proto *proto;
 	static struct packet_type snap_packet_type = {
-		.type = __constant_htons(ETH_P_SNAP),
+		.type = cpu_to_be16(ETH_P_SNAP),
 	};
 
+	if (unlikely(!pskb_may_pull(skb, 5)))
+		goto drop;
+
 	rcu_read_lock();
-	proto = find_snap_client(skb->h.raw);
+	proto = find_snap_client(skb_transport_header(skb));
 	if (proto) {
 		/* Pass the frame on. */
-		u8 *hdr = skb->data;
-		skb->h.raw  += 5;
-		skb_pull(skb, 5);
-		skb_postpull_rcsum(skb, hdr, 5);
+		skb->transport_header += 5;
+		skb_pull_rcsum(skb, 5);
 		rc = proto->rcvfunc(skb, dev, &snap_packet_type, orig_dev);
-	} else {
-		skb->sk = NULL;
-		kfree_skb(skb);
-		rc = 1;
 	}
-
 	rcu_read_unlock();
+
+	if (unlikely(!proto))
+		goto drop;
+
+out:
 	return rc;
+
+drop:
+	kfree_skb(skb);
+	goto out;
 }
 
 /*
@@ -91,15 +96,16 @@ static int snap_request(struct datalink_proto *dl,
 EXPORT_SYMBOL(register_snap_client);
 EXPORT_SYMBOL(unregister_snap_client);
 
-static char snap_err_msg[] __initdata =
+static const char snap_err_msg[] __initconst =
 	KERN_CRIT "SNAP - unable to register with 802.2\n";
 
 static int __init snap_init(void)
 {
 	snap_sap = llc_sap_open(0xAA, snap_rcv);
-
-	if (!snap_sap)
+	if (!snap_sap) {
 		printk(snap_err_msg);
+		return -EBUSY;
+	}
 
 	return 0;
 }
@@ -117,9 +123,9 @@ module_exit(snap_exit);
 /*
  *	Register SNAP clients. We don't yet use this for IP.
  */
-struct datalink_proto *register_snap_client(unsigned char *desc,
+struct datalink_proto *register_snap_client(const unsigned char *desc,
 					    int (*rcvfunc)(struct sk_buff *,
-						    	   struct net_device *,
+							   struct net_device *,
 							   struct packet_type *,
 							   struct net_device *))
 {
@@ -132,7 +138,7 @@ struct datalink_proto *register_snap_client(unsigned char *desc,
 
 	proto = kmalloc(sizeof(*proto), GFP_ATOMIC);
 	if (proto) {
-		memcpy(proto->type, desc,5);
+		memcpy(proto->type, desc, 5);
 		proto->rcvfunc		= rcvfunc;
 		proto->header_length	= 5 + 3; /* snap + 802.2 */
 		proto->request		= snap_request;
@@ -141,7 +147,6 @@ struct datalink_proto *register_snap_client(unsigned char *desc,
 out:
 	spin_unlock_bh(&snap_lock);
 
-	synchronize_net();
 	return proto;
 }
 
diff --git a/net/802/stp.c b/net/802/stp.c
new file mode 100644
index 00000000000..2c40ba0ec11
--- /dev/null
+++ b/net/802/stp.c
@@ -0,0 +1,104 @@
+/*
+ *	STP SAP demux
+ *
+ *	Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	version 2 as published by the Free Software Foundation.
+ */
+#include <linux/mutex.h>
+#include <linux/skbuff.h>
+#include <linux/etherdevice.h>
+#include <linux/llc.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <net/llc.h>
+#include <net/llc_pdu.h>
+#include <net/stp.h>
+
+/* 01:80:c2:00:00:20 - 01:80:c2:00:00:2F */
+#define GARP_ADDR_MIN	0x20
+#define GARP_ADDR_MAX	0x2F
+#define GARP_ADDR_RANGE	(GARP_ADDR_MAX - GARP_ADDR_MIN)
+
+static const struct stp_proto __rcu *garp_protos[GARP_ADDR_RANGE + 1] __read_mostly;
+static const struct stp_proto __rcu *stp_proto __read_mostly;
+
+static struct llc_sap *sap __read_mostly;
+static unsigned int sap_registered;
+static DEFINE_MUTEX(stp_proto_mutex);
+
+/* Called under rcu_read_lock from LLC */
+static int stp_pdu_rcv(struct sk_buff *skb, struct net_device *dev,
+		       struct packet_type *pt, struct net_device *orig_dev)
+{
+	const struct ethhdr *eh = eth_hdr(skb);
+	const struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb);
+	const struct stp_proto *proto;
+
+	if (pdu->ssap != LLC_SAP_BSPAN ||
+	    pdu->dsap != LLC_SAP_BSPAN ||
+	    pdu->ctrl_1 != LLC_PDU_TYPE_U)
+		goto err;
+
+	if (eh->h_dest[5] >= GARP_ADDR_MIN && eh->h_dest[5] <= GARP_ADDR_MAX) {
+		proto = rcu_dereference(garp_protos[eh->h_dest[5] -
+						    GARP_ADDR_MIN]);
+		if (proto &&
+		    !ether_addr_equal(eh->h_dest, proto->group_address))
+			goto err;
+	} else
+		proto = rcu_dereference(stp_proto);
+
+	if (!proto)
+		goto err;
+
+	proto->rcv(proto, skb, dev);
+	return 0;
+
+err:
+	kfree_skb(skb);
+	return 0;
+}
+
+int stp_proto_register(const struct stp_proto *proto)
+{
+	int err = 0;
+
+	mutex_lock(&stp_proto_mutex);
+	if (sap_registered++ == 0) {
+		sap = llc_sap_open(LLC_SAP_BSPAN, stp_pdu_rcv);
+		if (!sap) {
+			err = -ENOMEM;
+			goto out;
+		}
+	}
+	if (is_zero_ether_addr(proto->group_address))
+		rcu_assign_pointer(stp_proto, proto);
+	else
+		rcu_assign_pointer(garp_protos[proto->group_address[5] -
+					       GARP_ADDR_MIN], proto);
+out:
+	mutex_unlock(&stp_proto_mutex);
+	return err;
+}
+EXPORT_SYMBOL_GPL(stp_proto_register);
+
+void stp_proto_unregister(const struct stp_proto *proto)
+{
+	mutex_lock(&stp_proto_mutex);
+	if (is_zero_ether_addr(proto->group_address))
+		RCU_INIT_POINTER(stp_proto, NULL);
+	else
+		RCU_INIT_POINTER(garp_protos[proto->group_address[5] -
+					       GARP_ADDR_MIN], NULL);
+	synchronize_rcu();
+
+	if (--sap_registered == 0)
+		llc_sap_put(sap);
+	mutex_unlock(&stp_proto_mutex);
+}
+EXPORT_SYMBOL_GPL(stp_proto_unregister);
+
+MODULE_LICENSE("GPL");
diff --git a/net/802/sysctl_net_802.c b/net/802/sysctl_net_802.c
deleted file mode 100644
index 700129556c1..00000000000
--- a/net/802/sysctl_net_802.c
+++ /dev/null
@@ -1,34 +0,0 @@
-/* -*- linux-c -*-
- *		sysctl_net_802.c: sysctl interface to net 802 subsystem.
- *
- *		Begun April 1, 1996, Mike Shaver.
- *		Added /proc/sys/net/802 directory entry (empty =) ). [MS]
- *
- *		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/config.h>
-#include <linux/mm.h>
-#include <linux/if_tr.h>
-#include <linux/sysctl.h>
-
-#ifdef CONFIG_TR
-extern int sysctl_tr_rif_timeout;
-#endif
-
-struct ctl_table tr_table[] = {
-#ifdef CONFIG_TR
-	{
-		.ctl_name	= NET_TR_RIF_TIMEOUT,
-		.procname	= "rif_timeout",
-		.data		= &sysctl_tr_rif_timeout,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= &proc_dointvec
-	},
-#endif /* CONFIG_TR */
-	{ 0 },
-};
diff --git a/net/802/tr.c b/net/802/tr.c
deleted file mode 100644
index afd8385c0c9..00000000000
--- a/net/802/tr.c
+++ /dev/null
@@ -1,648 +0,0 @@
-/*
- * NET3:	Token ring device handling subroutines
- * 
- *		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:       3 Feb 97 Paul Norton <pnorton@cts.com> Minor routing fixes.
- *              Added rif table to /proc/net/tr_rif and rif timeout to
- *              /proc/sys/net/token-ring/rif_timeout.
- *              22 Jun 98 Paul Norton <p.norton@computer.org> Rearranged
- *              tr_header and tr_type_trans to handle passing IPX SNAP and
- *              802.2 through the correct layers. Eliminated tr_reformat.
- *        
- */
-
-#include <asm/uaccess.h>
-#include <asm/system.h>
-#include <linux/config.h>
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/jiffies.h>
-#include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/socket.h>
-#include <linux/in.h>
-#include <linux/inet.h>
-#include <linux/netdevice.h>
-#include <linux/trdevice.h>
-#include <linux/skbuff.h>
-#include <linux/errno.h>
-#include <linux/timer.h>
-#include <linux/net.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <linux/init.h>
-#include <net/arp.h>
-
-static void tr_add_rif_info(struct trh_hdr *trh, struct net_device *dev);
-static void rif_check_expire(unsigned long dummy);
-
-#define TR_SR_DEBUG 0
-
-/*
- *	Each RIF entry we learn is kept this way
- */
- 
-struct rif_cache {
-	unsigned char addr[TR_ALEN];
-	int iface;
-	__be16 rcf;
-	__be16 rseg[8];
-	struct rif_cache *next;
-	unsigned long last_used;
-	unsigned char local_ring;
-};
-
-#define RIF_TABLE_SIZE 32
-
-/*
- *	We hash the RIF cache 32 ways. We do after all have to look it
- *	up a lot.
- */
- 
-static struct rif_cache *rif_table[RIF_TABLE_SIZE];
-
-static DEFINE_SPINLOCK(rif_lock);
-
-
-/*
- *	Garbage disposal timer.
- */
- 
-static struct timer_list rif_timer;
-
-int sysctl_tr_rif_timeout = 60*10*HZ;
-
-static inline unsigned long rif_hash(const unsigned char *addr)
-{
-	unsigned long x;
-
-	x = addr[0];
-	x = (x << 2) ^ addr[1];
-	x = (x << 2) ^ addr[2];
-	x = (x << 2) ^ addr[3];
-	x = (x << 2) ^ addr[4];
-	x = (x << 2) ^ addr[5];
-
-	x ^= x >> 8;
-
-	return x & (RIF_TABLE_SIZE - 1);
-}
-
-/*
- *	Put the headers on a token ring packet. Token ring source routing
- *	makes this a little more exciting than on ethernet.
- */
- 
-static int tr_header(struct sk_buff *skb, struct net_device *dev,
-		     unsigned short type,
-		     void *daddr, void *saddr, unsigned len) 
-{
-	struct trh_hdr *trh;
-	int hdr_len;
-
-	/* 
-	 * Add the 802.2 SNAP header if IP as the IPv4/IPv6 code calls  
-	 * dev->hard_header directly.
-	 */
-	if (type == ETH_P_IP || type == ETH_P_IPV6 || type == ETH_P_ARP)
-	{
-		struct trllc *trllc;
-
-		hdr_len = sizeof(struct trh_hdr) + sizeof(struct trllc);
-		trh = (struct trh_hdr *)skb_push(skb, hdr_len);
-		trllc = (struct trllc *)(trh+1);
-		trllc->dsap = trllc->ssap = EXTENDED_SAP;
-		trllc->llc = UI_CMD;
-		trllc->protid[0] = trllc->protid[1] = trllc->protid[2] = 0x00;
-		trllc->ethertype = htons(type);
-	}
-	else
-	{
-		hdr_len = sizeof(struct trh_hdr);
-		trh = (struct trh_hdr *)skb_push(skb, hdr_len);	
-	}
-
-	trh->ac=AC;
-	trh->fc=LLC_FRAME;
-
-	if(saddr)
-		memcpy(trh->saddr,saddr,dev->addr_len);
-	else
-		memcpy(trh->saddr,dev->dev_addr,dev->addr_len);
-
-	/*
-	 *	Build the destination and then source route the frame
-	 */
-	 
-	if(daddr) 
-	{
-		memcpy(trh->daddr,daddr,dev->addr_len);
-		tr_source_route(skb,trh,dev);
-		return(hdr_len);
-	}
-
-	return -hdr_len;
-}
-	
-/*
- *	A neighbour discovery of some species (eg arp) has completed. We
- *	can now send the packet.
- */
- 
-static int tr_rebuild_header(struct sk_buff *skb) 
-{
-	struct trh_hdr *trh=(struct trh_hdr *)skb->data;
-	struct trllc *trllc=(struct trllc *)(skb->data+sizeof(struct trh_hdr));
-	struct net_device *dev = skb->dev;
-
-	/*
-	 *	FIXME: We don't yet support IPv6 over token rings
-	 */
-	 
-	if(trllc->ethertype != htons(ETH_P_IP)) {
-		printk("tr_rebuild_header: Don't know how to resolve type %04X addresses ?\n",(unsigned int)htons(trllc->ethertype));
-		return 0;
-	}
-
-#ifdef CONFIG_INET
-	if(arp_find(trh->daddr, skb)) {
-			return 1;
-	}
-	else 
-#endif	
-	{	
-		tr_source_route(skb,trh,dev); 
-		return 0;
-	}
-}
-	
-/*
- *	Some of this is a bit hackish. We intercept RIF information
- *	used for source routing. We also grab IP directly and don't feed
- *	it via SNAP.
- */
- 
-unsigned short tr_type_trans(struct sk_buff *skb, struct net_device *dev) 
-{
-
-	struct trh_hdr *trh=(struct trh_hdr *)skb->data;
-	struct trllc *trllc;
-	unsigned riflen=0;
-	
-	skb->mac.raw = skb->data;
-	
-       	if(trh->saddr[0] & TR_RII)
-		riflen = (ntohs(trh->rcf) & TR_RCF_LEN_MASK) >> 8;
-
-	trllc = (struct trllc *)(skb->data+sizeof(struct trh_hdr)-TR_MAXRIFLEN+riflen);
-
-	skb_pull(skb,sizeof(struct trh_hdr)-TR_MAXRIFLEN+riflen);
-
-	if(*trh->daddr & 0x80) 
-	{
-		if(!memcmp(trh->daddr,dev->broadcast,TR_ALEN)) 	
-			skb->pkt_type=PACKET_BROADCAST;
-		else
-			skb->pkt_type=PACKET_MULTICAST;
-	}
-	else if ( (trh->daddr[0] & 0x01) && (trh->daddr[1] & 0x00) && (trh->daddr[2] & 0x5E))
-	{
-		skb->pkt_type=PACKET_MULTICAST;
-	}
-	else if(dev->flags & IFF_PROMISC) 
-	{
-		if(memcmp(trh->daddr, dev->dev_addr, TR_ALEN))
-			skb->pkt_type=PACKET_OTHERHOST;
-	}
-
-	if ((skb->pkt_type != PACKET_BROADCAST) &&
-	    (skb->pkt_type != PACKET_MULTICAST))
-		tr_add_rif_info(trh,dev) ; 
-
-	/*
-	 * Strip the SNAP header from ARP packets since we don't 
-	 * pass them through to the 802.2/SNAP layers.
-	 */
-
-	if (trllc->dsap == EXTENDED_SAP &&
-	    (trllc->ethertype == ntohs(ETH_P_IP) ||
-	     trllc->ethertype == ntohs(ETH_P_IPV6) ||
-	     trllc->ethertype == ntohs(ETH_P_ARP)))
-	{
-		skb_pull(skb, sizeof(struct trllc));
-		return trllc->ethertype;
-	}
-
-	return ntohs(ETH_P_TR_802_2);
-}
-
-/*
- *	We try to do source routing... 
- */
-
-void tr_source_route(struct sk_buff *skb,struct trh_hdr *trh,struct net_device *dev) 
-{
-	int slack;
-	unsigned int hash;
-	struct rif_cache *entry;
-	unsigned char *olddata;
-	unsigned long flags;
-	static const unsigned char mcast_func_addr[] 
-		= {0xC0,0x00,0x00,0x04,0x00,0x00};
-	
-	spin_lock_irqsave(&rif_lock, flags);
-
-	/*
-	 *	Broadcasts are single route as stated in RFC 1042 
-	 */
-	if( (!memcmp(&(trh->daddr[0]),&(dev->broadcast[0]),TR_ALEN)) ||
-	    (!memcmp(&(trh->daddr[0]),&(mcast_func_addr[0]), TR_ALEN))  )
-	{
-		trh->rcf=htons((((sizeof(trh->rcf)) << 8) & TR_RCF_LEN_MASK)  
-			       | TR_RCF_FRAME2K | TR_RCF_LIMITED_BROADCAST);
-		trh->saddr[0]|=TR_RII;
-	}
-	else 
-	{
-		hash = rif_hash(trh->daddr);
-		/*
-		 *	Walk the hash table and look for an entry
-		 */
-		for(entry=rif_table[hash];entry && memcmp(&(entry->addr[0]),&(trh->daddr[0]),TR_ALEN);entry=entry->next);
-
-		/*
-		 *	If we found an entry we can route the frame.
-		 */
-		if(entry) 
-		{
-#if TR_SR_DEBUG
-printk("source routing for %02X:%02X:%02X:%02X:%02X:%02X\n",trh->daddr[0],
-		  trh->daddr[1],trh->daddr[2],trh->daddr[3],trh->daddr[4],trh->daddr[5]);
-#endif
-			if(!entry->local_ring && (ntohs(entry->rcf) & TR_RCF_LEN_MASK) >> 8)
-			{
-				trh->rcf=entry->rcf;
-				memcpy(&trh->rseg[0],&entry->rseg[0],8*sizeof(unsigned short));
-				trh->rcf^=htons(TR_RCF_DIR_BIT);	
-				trh->rcf&=htons(0x1fff);	/* Issam Chehab <ichehab@madge1.demon.co.uk> */
-
-				trh->saddr[0]|=TR_RII;
-#if TR_SR_DEBUG
-				printk("entry found with rcf %04x\n", entry->rcf);
-			}
-			else
-			{
-				printk("entry found but without rcf length, local=%02x\n", entry->local_ring);
-#endif
-			}
-			entry->last_used=jiffies;
-		}
-		else 
-		{
-			/*
-			 *	Without the information we simply have to shout
-			 *	on the wire. The replies should rapidly clean this
-			 *	situation up.
-			 */
-			trh->rcf=htons((((sizeof(trh->rcf)) << 8) & TR_RCF_LEN_MASK)  
-				       | TR_RCF_FRAME2K | TR_RCF_LIMITED_BROADCAST);
-			trh->saddr[0]|=TR_RII;
-#if TR_SR_DEBUG
-			printk("no entry in rif table found - broadcasting frame\n");
-#endif
-		}
-	}
-
-	/* Compress the RIF here so we don't have to do it in the driver(s) */
-	if (!(trh->saddr[0] & 0x80))
-		slack = 18;
-	else 
-		slack = 18 - ((ntohs(trh->rcf) & TR_RCF_LEN_MASK)>>8);
-	olddata = skb->data;
-	spin_unlock_irqrestore(&rif_lock, flags);
-
-	skb_pull(skb, slack);
-	memmove(skb->data, olddata, sizeof(struct trh_hdr) - slack);
-}
-
-/*
- *	We have learned some new RIF information for our source
- *	routing.
- */
- 
-static void tr_add_rif_info(struct trh_hdr *trh, struct net_device *dev)
-{
-	unsigned int hash, rii_p = 0;
-	unsigned long flags;
-	struct rif_cache *entry;
-	unsigned char saddr0;
-
-	spin_lock_irqsave(&rif_lock, flags);
-	saddr0 = trh->saddr[0];
-	
-	/*
-	 *	Firstly see if the entry exists
-	 */
-
-       	if(trh->saddr[0] & TR_RII)
-	{
-		trh->saddr[0]&=0x7f;
-		if (((ntohs(trh->rcf) & TR_RCF_LEN_MASK) >> 8) > 2)
-		{
-			rii_p = 1;
-	        }
-	}
-
-	hash = rif_hash(trh->saddr);
-	for(entry=rif_table[hash];entry && memcmp(&(entry->addr[0]),&(trh->saddr[0]),TR_ALEN);entry=entry->next);
-
-	if(entry==NULL) 
-	{
-#if TR_SR_DEBUG
-printk("adding rif_entry: addr:%02X:%02X:%02X:%02X:%02X:%02X rcf:%04X\n",
-		trh->saddr[0],trh->saddr[1],trh->saddr[2],
-       		trh->saddr[3],trh->saddr[4],trh->saddr[5],
-		ntohs(trh->rcf));
-#endif
-		/*
-		 *	Allocate our new entry. A failure to allocate loses
-		 *	use the information. This is harmless.
-		 *
-		 *	FIXME: We ought to keep some kind of cache size
-		 *	limiting and adjust the timers to suit.
-		 */
-		entry=kmalloc(sizeof(struct rif_cache),GFP_ATOMIC);
-
-		if(!entry) 
-		{
-			printk(KERN_DEBUG "tr.c: Couldn't malloc rif cache entry !\n");
-			spin_unlock_irqrestore(&rif_lock, flags);
-			return;
-		}
-
-		memcpy(&(entry->addr[0]),&(trh->saddr[0]),TR_ALEN);
-		entry->iface = dev->ifindex;
-		entry->next=rif_table[hash];
-		entry->last_used=jiffies;
-		rif_table[hash]=entry;
-
-		if (rii_p)
-		{
-			entry->rcf = trh->rcf & htons((unsigned short)~TR_RCF_BROADCAST_MASK);
-			memcpy(&(entry->rseg[0]),&(trh->rseg[0]),8*sizeof(unsigned short));
-			entry->local_ring = 0;
-		}
-		else
-		{
-			entry->local_ring = 1;
-		}
-	} 	
-	else	/* Y. Tahara added */
-	{ 
-		/*
-		 *	Update existing entries
-		 */
-		if (!entry->local_ring) 
-		    if (entry->rcf != (trh->rcf & htons((unsigned short)~TR_RCF_BROADCAST_MASK)) &&
-			 !(trh->rcf & htons(TR_RCF_BROADCAST_MASK)))
-		    {
-#if TR_SR_DEBUG
-printk("updating rif_entry: addr:%02X:%02X:%02X:%02X:%02X:%02X rcf:%04X\n",
-		trh->saddr[0],trh->saddr[1],trh->saddr[2],
-		trh->saddr[3],trh->saddr[4],trh->saddr[5],
-		ntohs(trh->rcf));
-#endif
-			    entry->rcf = trh->rcf & htons((unsigned short)~TR_RCF_BROADCAST_MASK);
-        		    memcpy(&(entry->rseg[0]),&(trh->rseg[0]),8*sizeof(unsigned short));
-		    }                                         
-           	entry->last_used=jiffies;               
-	}
-	trh->saddr[0]=saddr0; /* put the routing indicator back for tcpdump */
-	spin_unlock_irqrestore(&rif_lock, flags);
-}
-
-/*
- *	Scan the cache with a timer and see what we need to throw out.
- */
-
-static void rif_check_expire(unsigned long dummy) 
-{
-	int i;
-	unsigned long flags, next_interval = jiffies + sysctl_tr_rif_timeout/2;
-
-	spin_lock_irqsave(&rif_lock, flags);
-	
-	for(i =0; i < RIF_TABLE_SIZE; i++) {
-		struct rif_cache *entry, **pentry;
-		
-		pentry = rif_table+i;
-		while((entry=*pentry) != NULL) {
-			unsigned long expires
-				= entry->last_used + sysctl_tr_rif_timeout;
-
-			if (time_before_eq(expires, jiffies)) {
-				*pentry = entry->next;
-				kfree(entry);
-			} else {
-				pentry = &entry->next;
-
-				if (time_before(expires, next_interval))
-					next_interval = expires;
-			}
-		}
-	}
-	
-	spin_unlock_irqrestore(&rif_lock, flags);
-
-	mod_timer(&rif_timer, next_interval);
-
-}
-
-/*
- *	Generate the /proc/net information for the token ring RIF
- *	routing.
- */
- 
-#ifdef CONFIG_PROC_FS
-
-static struct rif_cache *rif_get_idx(loff_t pos)
-{
-	int i;
-	struct rif_cache *entry;
-	loff_t off = 0;
-
-	for(i = 0; i < RIF_TABLE_SIZE; i++) 
-		for(entry = rif_table[i]; entry; entry = entry->next) {
-			if (off == pos)
-				return entry;
-			++off;
-		}
-
-	return NULL;
-}
-
-static void *rif_seq_start(struct seq_file *seq, loff_t *pos)
-{
-	spin_lock_irq(&rif_lock);
-
-	return *pos ? rif_get_idx(*pos - 1) : SEQ_START_TOKEN;
-}
-
-static void *rif_seq_next(struct seq_file *seq, void *v, loff_t *pos)
-{
-	int i;
-	struct rif_cache *ent = v;
-
-	++*pos;
-
-	if (v == SEQ_START_TOKEN) {
-		i = -1;
-		goto scan;
-	}
-
-	if (ent->next) 
-		return ent->next;
-
-	i = rif_hash(ent->addr);
- scan:
-	while (++i < RIF_TABLE_SIZE) {
-		if ((ent = rif_table[i]) != NULL)
-			return ent;
-	}
-	return NULL;
-}
-
-static void rif_seq_stop(struct seq_file *seq, void *v)
-{
-	spin_unlock_irq(&rif_lock);
-}
-
-static int rif_seq_show(struct seq_file *seq, void *v)
-{
-	int j, rcf_len, segment, brdgnmb;
-	struct rif_cache *entry = v;
-
-	if (v == SEQ_START_TOKEN)
-		seq_puts(seq,
-		     "if     TR address       TTL   rcf   routing segments\n");
-	else {
-		struct net_device *dev = dev_get_by_index(entry->iface);
-		long ttl = (long) (entry->last_used + sysctl_tr_rif_timeout)
-				- (long) jiffies;
-
-		seq_printf(seq, "%s %02X:%02X:%02X:%02X:%02X:%02X %7li ",
-			   dev?dev->name:"?",
-			   entry->addr[0],entry->addr[1],entry->addr[2],
-			   entry->addr[3],entry->addr[4],entry->addr[5],
-			   ttl/HZ);
-
-			if (entry->local_ring)
-			        seq_puts(seq, "local\n");
-			else {
-
-				seq_printf(seq, "%04X", ntohs(entry->rcf));
-				rcf_len = ((ntohs(entry->rcf) & TR_RCF_LEN_MASK)>>8)-2; 
-				if (rcf_len)
-				        rcf_len >>= 1;
-				for(j = 1; j < rcf_len; j++) {
-					if(j==1) {
-						segment=ntohs(entry->rseg[j-1])>>4;
-						seq_printf(seq,"  %03X",segment);
-					};
-					segment=ntohs(entry->rseg[j])>>4;
-					brdgnmb=ntohs(entry->rseg[j-1])&0x00f;
-					seq_printf(seq,"-%01X-%03X",brdgnmb,segment);
-				}
-				seq_putc(seq, '\n');
-			}
-	   	}
-	return 0;
-}
-
-
-static struct seq_operations rif_seq_ops = {
-	.start = rif_seq_start,
-	.next  = rif_seq_next,
-	.stop  = rif_seq_stop,
-	.show  = rif_seq_show,
-};
-
-static int rif_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &rif_seq_ops);
-}
-
-static struct file_operations rif_seq_fops = {
-	.owner	 = THIS_MODULE,
-	.open    = rif_seq_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release,
-};
-
-#endif
-
-static void tr_setup(struct net_device *dev)
-{
-	/*
-	 *	Configure and register
-	 */
-	
-	dev->hard_header	= tr_header;
-	dev->rebuild_header	= tr_rebuild_header;
-
-	dev->type		= ARPHRD_IEEE802_TR;
-	dev->hard_header_len	= TR_HLEN;
-	dev->mtu		= 2000;
-	dev->addr_len		= TR_ALEN;
-	dev->tx_queue_len	= 100;	/* Long queues on tr */
-	
-	memset(dev->broadcast,0xFF, TR_ALEN);
-
-	/* New-style flags. */
-	dev->flags		= IFF_BROADCAST | IFF_MULTICAST ;
-}
-
-/**
- * alloc_trdev - Register token ring device
- * @sizeof_priv: Size of additional driver-private structure to be allocated
- *	for this token ring device
- *
- * Fill in the fields of the device structure with token ring-generic values.
- *
- * Constructs a new net device, complete with a private data area of
- * size @sizeof_priv.  A 32-byte (not bit) alignment is enforced for
- * this private data area.
- */
-struct net_device *alloc_trdev(int sizeof_priv)
-{
-	return alloc_netdev(sizeof_priv, "tr%d", tr_setup);
-}
-
-/*
- *	Called during bootup.  We don't actually have to initialise
- *	too much for this.
- */
-
-static int __init rif_init(void)
-{
-	init_timer(&rif_timer);
-	rif_timer.expires  = sysctl_tr_rif_timeout;
-	rif_timer.data     = 0L;
-	rif_timer.function = rif_check_expire;
-	add_timer(&rif_timer);
-
-	proc_net_fops_create("tr_rif", S_IRUGO, &rif_seq_fops);
-	return 0;
-}
-
-module_init(rif_init);
-
-EXPORT_SYMBOL(tr_source_route);
-EXPORT_SYMBOL(tr_type_trans);
-EXPORT_SYMBOL(alloc_trdev);
diff --git a/net/8021q/Kconfig b/net/8021q/Kconfig
index c4a382e450e..42320180967 100644
--- a/net/8021q/Kconfig
+++ b/net/8021q/Kconfig
@@ -3,17 +3,38 @@
 #
 
 config VLAN_8021Q
-	tristate "802.1Q VLAN Support"
+	tristate "802.1Q/802.1ad VLAN Support"
 	---help---
 	  Select this and you will be able to create 802.1Q VLAN interfaces
-	  on your ethernet interfaces.  802.1Q VLAN supports almost
-	  everything a regular ethernet interface does, including
-	  firewalling, bridging, and of course IP traffic.  You will need
-	  the 'vconfig' tool from the VLAN project in order to effectively
-	  use VLANs.  See the VLAN web page for more information:
+	  on your Ethernet interfaces. 802.1Q VLAN supports almost
+	  everything a regular Ethernet interface does, including
+	  firewalling, bridging, and of course IP traffic. You will need
+	  the 'ip' utility in order to effectively use VLANs.
+	  See the VLAN web page for more information:
 	  <http://www.candelatech.com/~greear/vlan.html>
 
 	  To compile this code as a module, choose M here: the module
 	  will be called 8021q.
 
 	  If unsure, say N.
+
+config VLAN_8021Q_GVRP
+	bool "GVRP (GARP VLAN Registration Protocol) support"
+	depends on VLAN_8021Q
+	select GARP
+	help
+	  Select this to enable GVRP end-system support. GVRP is used for
+	  automatic propagation of registered VLANs to switches.
+
+	  If unsure, say N.
+
+config VLAN_8021Q_MVRP
+	bool "MVRP (Multiple VLAN Registration Protocol) support"
+	depends on VLAN_8021Q
+	select MRP
+	help
+	  Select this to enable MVRP end-system support. MVRP is used for
+	  automatic propagation of registered VLANs to switches; it
+	  supersedes GVRP and is not backwards-compatible.
+
+	  If unsure, say N.
diff --git a/net/8021q/Makefile b/net/8021q/Makefile
index 97feb44dbdc..7bc8db08d7e 100644
--- a/net/8021q/Makefile
+++ b/net/8021q/Makefile
@@ -1,12 +1,11 @@
 #
 # Makefile for the Linux VLAN layer.
 #
+obj-$(subst m,y,$(CONFIG_VLAN_8021Q))	+= vlan_core.o
+obj-$(CONFIG_VLAN_8021Q)		+= 8021q.o
 
-obj-$(CONFIG_VLAN_8021Q) += 8021q.o
-
-8021q-objs := vlan.o vlan_dev.o
-
-ifeq ($(CONFIG_PROC_FS),y)
-8021q-objs += vlanproc.o
-endif
+8021q-y					:= vlan.o vlan_dev.o vlan_netlink.o
+8021q-$(CONFIG_VLAN_8021Q_GVRP)		+= vlan_gvrp.o
+8021q-$(CONFIG_VLAN_8021Q_MVRP)		+= vlan_mvrp.o
+8021q-$(CONFIG_PROC_FS)			+= vlanproc.o
 
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index fa76220708c..44ebd5c2cd4 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -3,9 +3,9 @@
  *		Ethernet-type device handling.
  *
  * Authors:	Ben Greear <greearb@candelatech.com>
- *              Please send support related email to: vlan@scry.wanfear.com
+ *              Please send support related email to: netdev@vger.kernel.org
  *              VLAN Home Page: http://www.candelatech.com/~greear/vlan.html
- * 
+ *
  * Fixes:
  *              Fix for packet capture - Nick Eggleston <nick@dccinc.com>;
  *		Add HW acceleration hooks - David S. Miller <davem@redhat.com>;
@@ -18,19 +18,23 @@
  *		2 of the License, or (at your option) any later version.
  */
 
-#include <asm/uaccess.h> /* for copy_from_user */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/capability.h>
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
-#include <net/datalink.h>
-#include <linux/mm.h>
-#include <linux/in.h>
+#include <linux/slab.h>
 #include <linux/init.h>
+#include <linux/rculist.h>
 #include <net/p8022.h>
 #include <net/arp.h>
 #include <linux/rtnetlink.h>
 #include <linux/notifier.h>
+#include <net/rtnetlink.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <asm/uaccess.h>
 
 #include <linux/if_vlan.h>
 #include "vlan.h"
@@ -40,531 +44,331 @@
 
 /* Global VLAN variables */
 
-/* Our listing of VLAN group(s) */
-static struct hlist_head vlan_group_hash[VLAN_GRP_HASH_SIZE];
-#define vlan_grp_hashfn(IDX)	((((IDX) >> VLAN_GRP_HASH_SHIFT) ^ (IDX)) & VLAN_GRP_HASH_MASK)
-
-static char vlan_fullname[] = "802.1Q VLAN Support";
-static char vlan_version[] = DRV_VERSION;
-static char vlan_copyright[] = "Ben Greear <greearb@candelatech.com>";
-static char vlan_buggyright[] = "David S. Miller <davem@redhat.com>";
+int vlan_net_id __read_mostly;
 
-static int vlan_device_event(struct notifier_block *, unsigned long, void *);
-static int vlan_ioctl_handler(void __user *);
-static int unregister_vlan_dev(struct net_device *, unsigned short );
-
-static struct notifier_block vlan_notifier_block = {
-	.notifier_call = vlan_device_event,
-};
-
-/* These may be changed at run-time through IOCTLs */
-
-/* Determines interface naming scheme. */
-unsigned short vlan_name_type = VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD;
-
-static struct packet_type vlan_packet_type = {
-	.type = __constant_htons(ETH_P_8021Q),
-	.func = vlan_skb_recv, /* VLAN receive method */
-};
-
-/* Bits of netdev state that are propagated from real device to virtual */
-#define VLAN_LINK_STATE_MASK \
-	((1<<__LINK_STATE_PRESENT)|(1<<__LINK_STATE_NOCARRIER))
+const char vlan_fullname[] = "802.1Q VLAN Support";
+const char vlan_version[] = DRV_VERSION;
 
 /* End of global variables definitions. */
 
-/*
- * Function vlan_proto_init (pro)
- *
- *    Initialize VLAN protocol layer, 
- *
- */
-static int __init vlan_proto_init(void)
+static int vlan_group_prealloc_vid(struct vlan_group *vg,
+				   __be16 vlan_proto, u16 vlan_id)
 {
-	int err;
+	struct net_device **array;
+	unsigned int pidx, vidx;
+	unsigned int size;
 
-	printk(VLAN_INF "%s v%s %s\n",
-	       vlan_fullname, vlan_version, vlan_copyright);
-	printk(VLAN_INF "All bugs added by %s\n",
-	       vlan_buggyright);
-
-	/* proc file system initialization */
-	err = vlan_proc_init();
-	if (err < 0) {
-		printk(KERN_ERR 
-		       "%s %s: can't create entry in proc filesystem!\n",
-		       __FUNCTION__, VLAN_NAME);
-		return err;
-	}
-
-	dev_add_pack(&vlan_packet_type);
+	ASSERT_RTNL();
 
-	/* Register us to receive netdevice events */
-	err = register_netdevice_notifier(&vlan_notifier_block);
-	if (err < 0) {
-		dev_remove_pack(&vlan_packet_type);
-		vlan_proc_cleanup();
-		return err;
-	}
+	pidx  = vlan_proto_idx(vlan_proto);
+	vidx  = vlan_id / VLAN_GROUP_ARRAY_PART_LEN;
+	array = vg->vlan_devices_arrays[pidx][vidx];
+	if (array != NULL)
+		return 0;
 
-	vlan_ioctl_set(vlan_ioctl_handler);
+	size = sizeof(struct net_device *) * VLAN_GROUP_ARRAY_PART_LEN;
+	array = kzalloc(size, GFP_KERNEL);
+	if (array == NULL)
+		return -ENOBUFS;
 
+	vg->vlan_devices_arrays[pidx][vidx] = array;
 	return 0;
 }
 
-/* Cleanup all vlan devices 
- * Note: devices that have been registered that but not
- * brought up will exist but have no module ref count.
- */
-static void __exit vlan_cleanup_devices(void)
+void unregister_vlan_dev(struct net_device *dev, struct list_head *head)
 {
-	struct net_device *dev, *nxt;
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+	struct net_device *real_dev = vlan->real_dev;
+	struct vlan_info *vlan_info;
+	struct vlan_group *grp;
+	u16 vlan_id = vlan->vlan_id;
 
-	rtnl_lock();
-	for (dev = dev_base; dev; dev = nxt) {
-		nxt = dev->next;
-		if (dev->priv_flags & IFF_802_1Q_VLAN) {
-			unregister_vlan_dev(VLAN_DEV_INFO(dev)->real_dev,
-					    VLAN_DEV_INFO(dev)->vlan_id);
+	ASSERT_RTNL();
 
-			unregister_netdevice(dev);
-		}
-	}
-	rtnl_unlock();
-}
+	vlan_info = rtnl_dereference(real_dev->vlan_info);
+	BUG_ON(!vlan_info);
 
-/*
- *     Module 'remove' entry point.
- *     o delete /proc/net/router directory and static entries.
- */ 
-static void __exit vlan_cleanup_module(void)
-{
-	int i;
+	grp = &vlan_info->grp;
 
-	vlan_ioctl_set(NULL);
+	grp->nr_vlan_devs--;
 
-	/* Un-register us from receiving netdevice events */
-	unregister_netdevice_notifier(&vlan_notifier_block);
+	if (vlan->flags & VLAN_FLAG_MVRP)
+		vlan_mvrp_request_leave(dev);
+	if (vlan->flags & VLAN_FLAG_GVRP)
+		vlan_gvrp_request_leave(dev);
 
-	dev_remove_pack(&vlan_packet_type);
-	vlan_cleanup_devices();
+	vlan_group_set_device(grp, vlan->vlan_proto, vlan_id, NULL);
 
-	/* This table must be empty if there are no module
-	 * references left.
+	netdev_upper_dev_unlink(real_dev, dev);
+	/* Because unregister_netdevice_queue() makes sure at least one rcu
+	 * grace period is respected before device freeing,
+	 * we dont need to call synchronize_net() here.
 	 */
-	for (i = 0; i < VLAN_GRP_HASH_SIZE; i++) {
-		BUG_ON(!hlist_empty(&vlan_group_hash[i]));
-	}
-	vlan_proc_cleanup();
-
-	synchronize_net();
-}
+	unregister_netdevice_queue(dev, head);
 
-module_init(vlan_proto_init);
-module_exit(vlan_cleanup_module);
-
-/* Must be invoked with RCU read lock (no preempt) */
-static struct vlan_group *__vlan_find_group(int real_dev_ifindex)
-{
-	struct vlan_group *grp;
-	struct hlist_node *n;
-	int hash = vlan_grp_hashfn(real_dev_ifindex);
-
-	hlist_for_each_entry_rcu(grp, n, &vlan_group_hash[hash], hlist) {
-		if (grp->real_dev_ifindex == real_dev_ifindex)
-			return grp;
+	if (grp->nr_vlan_devs == 0) {
+		vlan_mvrp_uninit_applicant(real_dev);
+		vlan_gvrp_uninit_applicant(real_dev);
 	}
 
-	return NULL;
+	/* Take it out of our own structures, but be sure to interlock with
+	 * HW accelerating devices or SW vlan input packet processing if
+	 * VLAN is not 0 (leave it there for 802.1p).
+	 */
+	if (vlan_id)
+		vlan_vid_del(real_dev, vlan->vlan_proto, vlan_id);
+
+	/* Get rid of the vlan's reference to real_dev */
+	dev_put(real_dev);
 }
 
-/*  Find the protocol handler.  Assumes VID < VLAN_VID_MASK.
- *
- * Must be invoked with RCU read lock (no preempt)
- */
-struct net_device *__find_vlan_dev(struct net_device *real_dev,
-				   unsigned short VID)
+int vlan_check_real_dev(struct net_device *real_dev,
+			__be16 protocol, u16 vlan_id)
 {
-	struct vlan_group *grp = __vlan_find_group(real_dev->ifindex);
+	const char *name = real_dev->name;
 
-	if (grp)
-                return grp->vlan_devices[VID];
+	if (real_dev->features & NETIF_F_VLAN_CHALLENGED) {
+		pr_info("VLANs not supported on %s\n", name);
+		return -EOPNOTSUPP;
+	}
 
-	return NULL;
-}
+	if (vlan_find_dev(real_dev, protocol, vlan_id) != NULL)
+		return -EEXIST;
 
-static void vlan_rcu_free(struct rcu_head *rcu)
-{
-	kfree(container_of(rcu, struct vlan_group, rcu));
+	return 0;
 }
 
-
-/* This returns 0 if everything went fine.
- * It will return 1 if the group was killed as a result.
- * A negative return indicates failure.
- *
- * The RTNL lock must be held.
- */
-static int unregister_vlan_dev(struct net_device *real_dev,
-			       unsigned short vlan_id)
+int register_vlan_dev(struct net_device *dev)
 {
-	struct net_device *dev = NULL;
-	int real_dev_ifindex = real_dev->ifindex;
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+	struct net_device *real_dev = vlan->real_dev;
+	u16 vlan_id = vlan->vlan_id;
+	struct vlan_info *vlan_info;
 	struct vlan_group *grp;
-	int i, ret;
-
-#ifdef VLAN_DEBUG
-	printk(VLAN_DBG "%s: VID: %i\n", __FUNCTION__, vlan_id);
-#endif
+	int err;
 
-	/* sanity check */
-	if (vlan_id >= VLAN_VID_MASK)
-		return -EINVAL;
+	err = vlan_vid_add(real_dev, vlan->vlan_proto, vlan_id);
+	if (err)
+		return err;
 
-	ASSERT_RTNL();
-	grp = __vlan_find_group(real_dev_ifindex);
-
-	ret = 0;
-
-	if (grp) {
-		dev = grp->vlan_devices[vlan_id];
-		if (dev) {
-			/* Remove proc entry */
-			vlan_proc_rem_dev(dev);
-
-			/* Take it out of our own structures, but be sure to
-			 * interlock with HW accelerating devices or SW vlan
-			 * input packet processing.
-			 */
-			if (real_dev->features &
-			    (NETIF_F_HW_VLAN_RX | NETIF_F_HW_VLAN_FILTER)) {
-				real_dev->vlan_rx_kill_vid(real_dev, vlan_id);
-			}
-
-			grp->vlan_devices[vlan_id] = NULL;
-			synchronize_net();
-
-
-			/* Caller unregisters (and if necessary, puts)
-			 * VLAN device, but we get rid of the reference to
-			 * real_dev here.
-			 */
-			dev_put(real_dev);
-
-			/* If the group is now empty, kill off the
-			 * group.
-			 */
-			for (i = 0; i < VLAN_VID_MASK; i++)
-				if (grp->vlan_devices[i])
-					break;
-
-			if (i == VLAN_VID_MASK) {
-				if (real_dev->features & NETIF_F_HW_VLAN_RX)
-					real_dev->vlan_rx_register(real_dev, NULL);
-
-				hlist_del_rcu(&grp->hlist);
-
-				/* Free the group, after all cpu's are done. */
-				call_rcu(&grp->rcu, vlan_rcu_free);
-
-				grp = NULL;
-				ret = 1;
-			}
-		}
+	vlan_info = rtnl_dereference(real_dev->vlan_info);
+	/* vlan_info should be there now. vlan_vid_add took care of it */
+	BUG_ON(!vlan_info);
+
+	grp = &vlan_info->grp;
+	if (grp->nr_vlan_devs == 0) {
+		err = vlan_gvrp_init_applicant(real_dev);
+		if (err < 0)
+			goto out_vid_del;
+		err = vlan_mvrp_init_applicant(real_dev);
+		if (err < 0)
+			goto out_uninit_gvrp;
 	}
 
-        return ret;
-}
-
-static int unregister_vlan_device(const char *vlan_IF_name)
-{
-	struct net_device *dev = NULL;
-	int ret;
-
+	err = vlan_group_prealloc_vid(grp, vlan->vlan_proto, vlan_id);
+	if (err < 0)
+		goto out_uninit_mvrp;
 
-	dev = dev_get_by_name(vlan_IF_name);
-	ret = -EINVAL;
-	if (dev) {
-		if (dev->priv_flags & IFF_802_1Q_VLAN) {
-			rtnl_lock();
+	vlan->nest_level = dev_get_nest_level(real_dev, is_vlan_dev) + 1;
+	err = register_netdevice(dev);
+	if (err < 0)
+		goto out_uninit_mvrp;
 
-			ret = unregister_vlan_dev(VLAN_DEV_INFO(dev)->real_dev,
-						  VLAN_DEV_INFO(dev)->vlan_id);
+	err = netdev_upper_dev_link(real_dev, dev);
+	if (err)
+		goto out_unregister_netdev;
 
-			dev_put(dev);
-			unregister_netdevice(dev);
+	/* Account for reference in struct vlan_dev_priv */
+	dev_hold(real_dev);
 
-			rtnl_unlock();
+	netif_stacked_transfer_operstate(real_dev, dev);
+	linkwatch_fire_event(dev); /* _MUST_ call rfc2863_policy() */
 
-			if (ret == 1)
-				ret = 0;
-		} else {
-			printk(VLAN_ERR 
-			       "%s: ERROR:	Tried to remove a non-vlan device "
-			       "with VLAN code, name: %s  priv_flags: %hX\n",
-			       __FUNCTION__, dev->name, dev->priv_flags);
-			dev_put(dev);
-			ret = -EPERM;
-		}
-	} else {
-#ifdef VLAN_DEBUG
-		printk(VLAN_DBG "%s: WARNING: Could not find dev.\n", __FUNCTION__);
-#endif
-		ret = -EINVAL;
-	}
-
-	return ret;
-}
-
-static void vlan_setup(struct net_device *new_dev)
-{
-	SET_MODULE_OWNER(new_dev);
-	    
-	/* new_dev->ifindex = 0;  it will be set when added to
-	 * the global list.
-	 * iflink is set as well.
+	/* So, got the sucker initialized, now lets place
+	 * it into our local structure.
 	 */
-	new_dev->get_stats = vlan_dev_get_stats;
+	vlan_group_set_device(grp, vlan->vlan_proto, vlan_id, dev);
+	grp->nr_vlan_devs++;
 
-	/* Make this thing known as a VLAN device */
-	new_dev->priv_flags |= IFF_802_1Q_VLAN;
-				
-	/* Set us up to have no queue, as the underlying Hardware device
-	 * can do all the queueing we could want.
-	 */
-	new_dev->tx_queue_len = 0;
-
-	/* set up method calls */
-	new_dev->change_mtu = vlan_dev_change_mtu;
-	new_dev->open = vlan_dev_open;
-	new_dev->stop = vlan_dev_stop;
-	new_dev->set_mac_address = vlan_dev_set_mac_address;
-	new_dev->set_multicast_list = vlan_dev_set_multicast_list;
-	new_dev->destructor = free_netdev;
-	new_dev->do_ioctl = vlan_dev_ioctl;
+	return 0;
+
+out_unregister_netdev:
+	unregister_netdevice(dev);
+out_uninit_mvrp:
+	if (grp->nr_vlan_devs == 0)
+		vlan_mvrp_uninit_applicant(real_dev);
+out_uninit_gvrp:
+	if (grp->nr_vlan_devs == 0)
+		vlan_gvrp_uninit_applicant(real_dev);
+out_vid_del:
+	vlan_vid_del(real_dev, vlan->vlan_proto, vlan_id);
+	return err;
 }
 
 /*  Attach a VLAN device to a mac address (ie Ethernet Card).
- *  Returns the device that was created, or NULL if there was
- *  an error of some kind.
+ *  Returns 0 if the device was created or a negative error code otherwise.
  */
-static struct net_device *register_vlan_device(const char *eth_IF_name,
-					       unsigned short VLAN_ID)
+static int register_vlan_device(struct net_device *real_dev, u16 vlan_id)
 {
-	struct vlan_group *grp;
 	struct net_device *new_dev;
-	struct net_device *real_dev; /* the ethernet device */
+	struct vlan_dev_priv *vlan;
+	struct net *net = dev_net(real_dev);
+	struct vlan_net *vn = net_generic(net, vlan_net_id);
 	char name[IFNAMSIZ];
+	int err;
 
-#ifdef VLAN_DEBUG
-	printk(VLAN_DBG "%s: if_name -:%s:-	vid: %i\n",
-		__FUNCTION__, eth_IF_name, VLAN_ID);
-#endif
-
-	if (VLAN_ID >= VLAN_VID_MASK)
-		goto out_ret_null;
-
-	/* find the device relating to eth_IF_name. */
-	real_dev = dev_get_by_name(eth_IF_name);
-	if (!real_dev)
-		goto out_ret_null;
-
-	if (real_dev->features & NETIF_F_VLAN_CHALLENGED) {
-		printk(VLAN_DBG "%s: VLANs not supported on %s.\n",
-			__FUNCTION__, real_dev->name);
-		goto out_put_dev;
-	}
-
-	if ((real_dev->features & NETIF_F_HW_VLAN_RX) &&
-	    (real_dev->vlan_rx_register == NULL ||
-	     real_dev->vlan_rx_kill_vid == NULL)) {
-		printk(VLAN_DBG "%s: Device %s has buggy VLAN hw accel.\n",
-			__FUNCTION__, real_dev->name);
-		goto out_put_dev;
-	}
-
-	if ((real_dev->features & NETIF_F_HW_VLAN_FILTER) &&
-	    (real_dev->vlan_rx_add_vid == NULL ||
-	     real_dev->vlan_rx_kill_vid == NULL)) {
-		printk(VLAN_DBG "%s: Device %s has buggy VLAN hw accel.\n",
-			__FUNCTION__, real_dev->name);
-		goto out_put_dev;
-	}
-
-	/* From this point on, all the data structures must remain
-	 * consistent.
-	 */
-	rtnl_lock();
-
-	/* The real device must be up and operating in order to
-	 * assosciate a VLAN device with it.
-	 */
-	if (!(real_dev->flags & IFF_UP))
-		goto out_unlock;
+	if (vlan_id >= VLAN_VID_MASK)
+		return -ERANGE;
 
-	if (__find_vlan_dev(real_dev, VLAN_ID) != NULL) {
-		/* was already registered. */
-		printk(VLAN_DBG "%s: ALREADY had VLAN registered\n", __FUNCTION__);
-		goto out_unlock;
-	}
+	err = vlan_check_real_dev(real_dev, htons(ETH_P_8021Q), vlan_id);
+	if (err < 0)
+		return err;
 
 	/* Gotta set up the fields for the device. */
-#ifdef VLAN_DEBUG
-	printk(VLAN_DBG "About to allocate name, vlan_name_type: %i\n",
-	       vlan_name_type);
-#endif
-	switch (vlan_name_type) {
+	switch (vn->name_type) {
 	case VLAN_NAME_TYPE_RAW_PLUS_VID:
 		/* name will look like:	 eth1.0005 */
-		snprintf(name, IFNAMSIZ, "%s.%.4i", real_dev->name, VLAN_ID);
+		snprintf(name, IFNAMSIZ, "%s.%.4i", real_dev->name, vlan_id);
 		break;
 	case VLAN_NAME_TYPE_PLUS_VID_NO_PAD:
 		/* Put our vlan.VID in the name.
 		 * Name will look like:	 vlan5
 		 */
-		snprintf(name, IFNAMSIZ, "vlan%i", VLAN_ID);
+		snprintf(name, IFNAMSIZ, "vlan%i", vlan_id);
 		break;
 	case VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD:
 		/* Put our vlan.VID in the name.
 		 * Name will look like:	 eth0.5
 		 */
-		snprintf(name, IFNAMSIZ, "%s.%i", real_dev->name, VLAN_ID);
+		snprintf(name, IFNAMSIZ, "%s.%i", real_dev->name, vlan_id);
 		break;
 	case VLAN_NAME_TYPE_PLUS_VID:
 		/* Put our vlan.VID in the name.
 		 * Name will look like:	 vlan0005
 		 */
 	default:
-		snprintf(name, IFNAMSIZ, "vlan%.4i", VLAN_ID);
-	};
-		    
-	new_dev = alloc_netdev(sizeof(struct vlan_dev_info), name,
-			       vlan_setup);
-	if (new_dev == NULL)
-		goto out_unlock;
+		snprintf(name, IFNAMSIZ, "vlan%.4i", vlan_id);
+	}
 
-#ifdef VLAN_DEBUG
-	printk(VLAN_DBG "Allocated new name -:%s:-\n", new_dev->name);
-#endif
-	/* IFF_BROADCAST|IFF_MULTICAST; ??? */
-	new_dev->flags = real_dev->flags;
-	new_dev->flags &= ~IFF_UP;
+	new_dev = alloc_netdev(sizeof(struct vlan_dev_priv), name, vlan_setup);
 
-	new_dev->state = real_dev->state & VLAN_LINK_STATE_MASK;
+	if (new_dev == NULL)
+		return -ENOBUFS;
 
+	dev_net_set(new_dev, net);
 	/* need 4 bytes for extra VLAN header info,
 	 * hope the underlying device can handle it.
 	 */
 	new_dev->mtu = real_dev->mtu;
+	new_dev->priv_flags |= (real_dev->priv_flags & IFF_UNICAST_FLT);
+
+	vlan = vlan_dev_priv(new_dev);
+	vlan->vlan_proto = htons(ETH_P_8021Q);
+	vlan->vlan_id = vlan_id;
+	vlan->real_dev = real_dev;
+	vlan->dent = NULL;
+	vlan->flags = VLAN_FLAG_REORDER_HDR;
+
+	new_dev->rtnl_link_ops = &vlan_link_ops;
+	err = register_vlan_dev(new_dev);
+	if (err < 0)
+		goto out_free_newdev;
 
-	/* TODO: maybe just assign it to be ETHERNET? */
-	new_dev->type = real_dev->type;
-
-	new_dev->hard_header_len = real_dev->hard_header_len;
-	if (!(real_dev->features & NETIF_F_HW_VLAN_TX)) {
-		/* Regular ethernet + 4 bytes (18 total). */
-		new_dev->hard_header_len += VLAN_HLEN;
-	}
+	return 0;
 
-	VLAN_MEM_DBG("new_dev->priv malloc, addr: %p  size: %i\n",
-		     new_dev->priv,
-		     sizeof(struct vlan_dev_info));
-	    
-	memcpy(new_dev->broadcast, real_dev->broadcast, real_dev->addr_len);
-	memcpy(new_dev->dev_addr, real_dev->dev_addr, real_dev->addr_len);
-	new_dev->addr_len = real_dev->addr_len;
-
-	if (real_dev->features & NETIF_F_HW_VLAN_TX) {
-		new_dev->hard_header = real_dev->hard_header;
-		new_dev->hard_start_xmit = vlan_dev_hwaccel_hard_start_xmit;
-		new_dev->rebuild_header = real_dev->rebuild_header;
-	} else {
-		new_dev->hard_header = vlan_dev_hard_header;
-		new_dev->hard_start_xmit = vlan_dev_hard_start_xmit;
-		new_dev->rebuild_header = vlan_dev_rebuild_header;
-	}
-	new_dev->hard_header_parse = real_dev->hard_header_parse;
+out_free_newdev:
+	free_netdev(new_dev);
+	return err;
+}
 
-	VLAN_DEV_INFO(new_dev)->vlan_id = VLAN_ID; /* 1 through VLAN_VID_MASK */
-	VLAN_DEV_INFO(new_dev)->real_dev = real_dev;
-	VLAN_DEV_INFO(new_dev)->dent = NULL;
-	VLAN_DEV_INFO(new_dev)->flags = 1;
+static void vlan_sync_address(struct net_device *dev,
+			      struct net_device *vlandev)
+{
+	struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev);
 
-#ifdef VLAN_DEBUG
-	printk(VLAN_DBG "About to go find the group for idx: %i\n",
-	       real_dev->ifindex);
-#endif
-	    
-	if (register_netdevice(new_dev))
-		goto out_free_newdev;
+	/* May be called without an actual change */
+	if (ether_addr_equal(vlan->real_dev_addr, dev->dev_addr))
+		return;
 
-	/* So, got the sucker initialized, now lets place
-	 * it into our local structure.
-	 */
-	grp = __vlan_find_group(real_dev->ifindex);
+	/* vlan address was different from the old address and is equal to
+	 * the new address */
+	if (!ether_addr_equal(vlandev->dev_addr, vlan->real_dev_addr) &&
+	    ether_addr_equal(vlandev->dev_addr, dev->dev_addr))
+		dev_uc_del(dev, vlandev->dev_addr);
 
-	/* Note, we are running under the RTNL semaphore
-	 * so it cannot "appear" on us.
-	 */
-	if (!grp) { /* need to add a new group */
-		grp = kmalloc(sizeof(struct vlan_group), GFP_KERNEL);
-		if (!grp)
-			goto out_free_unregister;
-					
-		/* printk(KERN_ALERT "VLAN REGISTER:  Allocated new group.\n"); */
-		memset(grp, 0, sizeof(struct vlan_group));
-		grp->real_dev_ifindex = real_dev->ifindex;
-
-		hlist_add_head_rcu(&grp->hlist, 
-				   &vlan_group_hash[vlan_grp_hashfn(real_dev->ifindex)]);
-
-		if (real_dev->features & NETIF_F_HW_VLAN_RX)
-			real_dev->vlan_rx_register(real_dev, grp);
-	}
-	    
-	grp->vlan_devices[VLAN_ID] = new_dev;
+	/* vlan address was equal to the old address and is different from
+	 * the new address */
+	if (ether_addr_equal(vlandev->dev_addr, vlan->real_dev_addr) &&
+	    !ether_addr_equal(vlandev->dev_addr, dev->dev_addr))
+		dev_uc_add(dev, vlandev->dev_addr);
 
-	if (vlan_proc_add_dev(new_dev)<0)/* create it's proc entry */
-            	printk(KERN_WARNING "VLAN: failed to add proc entry for %s\n",
-					                 new_dev->name);
+	ether_addr_copy(vlan->real_dev_addr, dev->dev_addr);
+}
 
-	if (real_dev->features & NETIF_F_HW_VLAN_FILTER)
-		real_dev->vlan_rx_add_vid(real_dev, VLAN_ID);
+static void vlan_transfer_features(struct net_device *dev,
+				   struct net_device *vlandev)
+{
+	struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev);
 
-	rtnl_unlock();
+	vlandev->gso_max_size = dev->gso_max_size;
 
+	if (vlan_hw_offload_capable(dev->features, vlan->vlan_proto))
+		vlandev->hard_header_len = dev->hard_header_len;
+	else
+		vlandev->hard_header_len = dev->hard_header_len + VLAN_HLEN;
 
-#ifdef VLAN_DEBUG
-	printk(VLAN_DBG "Allocated new device successfully, returning.\n");
+#if IS_ENABLED(CONFIG_FCOE)
+	vlandev->fcoe_ddp_xid = dev->fcoe_ddp_xid;
 #endif
-	return new_dev;
-
-out_free_unregister:
-	unregister_netdev(new_dev);
-	goto out_unlock;
-
-out_free_newdev:
-	free_netdev(new_dev);
-
-out_unlock:
-	rtnl_unlock();
 
-out_put_dev:
-	dev_put(real_dev);
+	netdev_update_features(vlandev);
+}
 
-out_ret_null:
-	return NULL;
+static void __vlan_device_event(struct net_device *dev, unsigned long event)
+{
+	switch (event) {
+	case NETDEV_CHANGENAME:
+		vlan_proc_rem_dev(dev);
+		if (vlan_proc_add_dev(dev) < 0)
+			pr_warn("failed to change proc name for %s\n",
+				dev->name);
+		break;
+	case NETDEV_REGISTER:
+		if (vlan_proc_add_dev(dev) < 0)
+			pr_warn("failed to add proc entry for %s\n", dev->name);
+		break;
+	case NETDEV_UNREGISTER:
+		vlan_proc_rem_dev(dev);
+		break;
+	}
 }
 
-static int vlan_device_event(struct notifier_block *unused, unsigned long event, void *ptr)
+static int vlan_device_event(struct notifier_block *unused, unsigned long event,
+			     void *ptr)
 {
-	struct net_device *dev = ptr;
-	struct vlan_group *grp = __vlan_find_group(dev->ifindex);
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct vlan_group *grp;
+	struct vlan_info *vlan_info;
 	int i, flgs;
 	struct net_device *vlandev;
+	struct vlan_dev_priv *vlan;
+	bool last = false;
+	LIST_HEAD(list);
+
+	if (is_vlan_dev(dev))
+		__vlan_device_event(dev, event);
+
+	if ((event == NETDEV_UP) &&
+	    (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) {
+		pr_info("adding VLAN 0 to HW filter on device %s\n",
+			dev->name);
+		vlan_vid_add(dev, htons(ETH_P_8021Q), 0);
+	}
 
-	if (!grp)
+	vlan_info = rtnl_dereference(dev->vlan_info);
+	if (!vlan_info)
 		goto out;
+	grp = &vlan_info->grp;
 
 	/* It is OK that we do not hold the group lock right now,
 	 * as we run under the RTNL lock.
@@ -573,93 +377,118 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
 	switch (event) {
 	case NETDEV_CHANGE:
 		/* Propagate real device state to vlan devices */
-		flgs = dev->state & VLAN_LINK_STATE_MASK;
-		for (i = 0; i < VLAN_GROUP_ARRAY_LEN; i++) {
-			vlandev = grp->vlan_devices[i];
-			if (!vlandev)
+		vlan_group_for_each_dev(grp, i, vlandev)
+			netif_stacked_transfer_operstate(dev, vlandev);
+		break;
+
+	case NETDEV_CHANGEADDR:
+		/* Adjust unicast filters on underlying device */
+		vlan_group_for_each_dev(grp, i, vlandev) {
+			flgs = vlandev->flags;
+			if (!(flgs & IFF_UP))
 				continue;
 
-			if (netif_carrier_ok(dev)) {
-				if (!netif_carrier_ok(vlandev))
-					netif_carrier_on(vlandev);
-			} else {
-				if (netif_carrier_ok(vlandev))
-					netif_carrier_off(vlandev);
-			}
-
-			if ((vlandev->state & VLAN_LINK_STATE_MASK) != flgs) {
-				vlandev->state = (vlandev->state &~ VLAN_LINK_STATE_MASK) 
-					| flgs;
-				netdev_state_change(vlandev);
-			}
+			vlan_sync_address(dev, vlandev);
 		}
 		break;
 
-	case NETDEV_DOWN:
-		/* Put all VLANs for this dev in the down state too.  */
-		for (i = 0; i < VLAN_GROUP_ARRAY_LEN; i++) {
-			vlandev = grp->vlan_devices[i];
-			if (!vlandev)
+	case NETDEV_CHANGEMTU:
+		vlan_group_for_each_dev(grp, i, vlandev) {
+			if (vlandev->mtu <= dev->mtu)
 				continue;
 
+			dev_set_mtu(vlandev, dev->mtu);
+		}
+		break;
+
+	case NETDEV_FEAT_CHANGE:
+		/* Propagate device features to underlying device */
+		vlan_group_for_each_dev(grp, i, vlandev)
+			vlan_transfer_features(dev, vlandev);
+		break;
+
+	case NETDEV_DOWN:
+		if (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)
+			vlan_vid_del(dev, htons(ETH_P_8021Q), 0);
+
+		/* Put all VLANs for this dev in the down state too.  */
+		vlan_group_for_each_dev(grp, i, vlandev) {
 			flgs = vlandev->flags;
 			if (!(flgs & IFF_UP))
 				continue;
 
-			dev_change_flags(vlandev, flgs & ~IFF_UP);
+			vlan = vlan_dev_priv(vlandev);
+			if (!(vlan->flags & VLAN_FLAG_LOOSE_BINDING))
+				dev_change_flags(vlandev, flgs & ~IFF_UP);
+			netif_stacked_transfer_operstate(dev, vlandev);
 		}
 		break;
 
 	case NETDEV_UP:
 		/* Put all VLANs for this dev in the up state too.  */
-		for (i = 0; i < VLAN_GROUP_ARRAY_LEN; i++) {
-			vlandev = grp->vlan_devices[i];
-			if (!vlandev)
-				continue;
-				
+		vlan_group_for_each_dev(grp, i, vlandev) {
 			flgs = vlandev->flags;
 			if (flgs & IFF_UP)
 				continue;
 
-			dev_change_flags(vlandev, flgs | IFF_UP);
+			vlan = vlan_dev_priv(vlandev);
+			if (!(vlan->flags & VLAN_FLAG_LOOSE_BINDING))
+				dev_change_flags(vlandev, flgs | IFF_UP);
+			netif_stacked_transfer_operstate(dev, vlandev);
 		}
 		break;
-		
-	case NETDEV_UNREGISTER:
-		/* Delete all VLANs for this dev. */
-		for (i = 0; i < VLAN_GROUP_ARRAY_LEN; i++) {
-			int ret;
-
-			vlandev = grp->vlan_devices[i];
-			if (!vlandev)
-				continue;
-
-			ret = unregister_vlan_dev(dev,
-						  VLAN_DEV_INFO(vlandev)->vlan_id);
-
-			unregister_netdevice(vlandev);
 
-			/* Group was destroyed? */
-			if (ret == 1)
+	case NETDEV_UNREGISTER:
+		/* twiddle thumbs on netns device moves */
+		if (dev->reg_state != NETREG_UNREGISTERING)
+			break;
+
+		vlan_group_for_each_dev(grp, i, vlandev) {
+			/* removal of last vid destroys vlan_info, abort
+			 * afterwards */
+			if (vlan_info->nr_vids == 1)
+				last = true;
+
+			unregister_vlan_dev(vlandev, &list);
+			if (last)
 				break;
 		}
+		unregister_netdevice_many(&list);
+		break;
+
+	case NETDEV_PRE_TYPE_CHANGE:
+		/* Forbid underlaying device to change its type. */
+		if (vlan_uses_dev(dev))
+			return NOTIFY_BAD;
+		break;
+
+	case NETDEV_NOTIFY_PEERS:
+	case NETDEV_BONDING_FAILOVER:
+	case NETDEV_RESEND_IGMP:
+		/* Propagate to vlan devices */
+		vlan_group_for_each_dev(grp, i, vlandev)
+			call_netdevice_notifiers(event, vlandev);
 		break;
-	};
+	}
 
 out:
 	return NOTIFY_DONE;
 }
 
+static struct notifier_block vlan_notifier_block __read_mostly = {
+	.notifier_call = vlan_device_event,
+};
+
 /*
  *	VLAN IOCTL handler.
  *	o execute requested action or pass command to the device driver
  *   arg is really a struct vlan_ioctl_args __user *.
  */
-static int vlan_ioctl_handler(void __user *arg)
+static int vlan_ioctl_handler(struct net *net, void __user *arg)
 {
-	int err = 0;
-	unsigned short vid = 0;
+	int err;
 	struct vlan_ioctl_args args;
+	struct net_device *dev = NULL;
 
 	if (copy_from_user(&args, arg, sizeof(struct vlan_ioctl_args)))
 		return -EFAULT;
@@ -668,41 +497,65 @@ static int vlan_ioctl_handler(void __user *arg)
 	args.device1[23] = 0;
 	args.u.device2[23] = 0;
 
-#ifdef VLAN_DEBUG
-	printk(VLAN_DBG "%s: args.cmd: %x\n", __FUNCTION__, args.cmd);
-#endif
+	rtnl_lock();
+
+	switch (args.cmd) {
+	case SET_VLAN_INGRESS_PRIORITY_CMD:
+	case SET_VLAN_EGRESS_PRIORITY_CMD:
+	case SET_VLAN_FLAG_CMD:
+	case ADD_VLAN_CMD:
+	case DEL_VLAN_CMD:
+	case GET_VLAN_REALDEV_NAME_CMD:
+	case GET_VLAN_VID_CMD:
+		err = -ENODEV;
+		dev = __dev_get_by_name(net, args.device1);
+		if (!dev)
+			goto out;
+
+		err = -EINVAL;
+		if (args.cmd != ADD_VLAN_CMD && !is_vlan_dev(dev))
+			goto out;
+	}
 
 	switch (args.cmd) {
 	case SET_VLAN_INGRESS_PRIORITY_CMD:
-		if (!capable(CAP_NET_ADMIN))
-			return -EPERM;
-		err = vlan_dev_set_ingress_priority(args.device1,
-						    args.u.skb_priority,
-						    args.vlan_qos);
+		err = -EPERM;
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+			break;
+		vlan_dev_set_ingress_priority(dev,
+					      args.u.skb_priority,
+					      args.vlan_qos);
+		err = 0;
 		break;
 
 	case SET_VLAN_EGRESS_PRIORITY_CMD:
-		if (!capable(CAP_NET_ADMIN))
-			return -EPERM;
-		err = vlan_dev_set_egress_priority(args.device1,
+		err = -EPERM;
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+			break;
+		err = vlan_dev_set_egress_priority(dev,
 						   args.u.skb_priority,
 						   args.vlan_qos);
 		break;
 
 	case SET_VLAN_FLAG_CMD:
-		if (!capable(CAP_NET_ADMIN))
-			return -EPERM;
-		err = vlan_dev_set_vlan_flag(args.device1,
-					     args.u.flag,
-					     args.vlan_qos);
+		err = -EPERM;
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+			break;
+		err = vlan_dev_change_flags(dev,
+					    args.vlan_qos ? args.u.flag : 0,
+					    args.u.flag);
 		break;
 
 	case SET_VLAN_NAME_TYPE_CMD:
-		if (!capable(CAP_NET_ADMIN))
-			return -EPERM;
+		err = -EPERM;
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+			break;
 		if ((args.u.name_type >= 0) &&
 		    (args.u.name_type < VLAN_NAME_TYPE_HIGHEST)) {
-			vlan_name_type = args.u.name_type;
+			struct vlan_net *vn;
+
+			vn = net_generic(net, vlan_net_id);
+			vn->name_type = args.u.name_type;
 			err = 0;
 		} else {
 			err = -EINVAL;
@@ -710,78 +563,126 @@ static int vlan_ioctl_handler(void __user *arg)
 		break;
 
 	case ADD_VLAN_CMD:
-		if (!capable(CAP_NET_ADMIN))
-			return -EPERM;
-		/* we have been given the name of the Ethernet Device we want to
-		 * talk to:  args.dev1	 We also have the
-		 * VLAN ID:  args.u.VID
-		 */
-		if (register_vlan_device(args.device1, args.u.VID)) {
-			err = 0;
-		} else {
-			err = -EINVAL;
-		}
+		err = -EPERM;
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+			break;
+		err = register_vlan_device(dev, args.u.VID);
 		break;
 
 	case DEL_VLAN_CMD:
-		if (!capable(CAP_NET_ADMIN))
-			return -EPERM;
-		/* Here, the args.dev1 is the actual VLAN we want
-		 * to get rid of.
-		 */
-		err = unregister_vlan_device(args.device1);
+		err = -EPERM;
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+			break;
+		unregister_vlan_dev(dev, NULL);
+		err = 0;
 		break;
 
-	case GET_VLAN_INGRESS_PRIORITY_CMD:
-		/* TODO:  Implement
-		   err = vlan_dev_get_ingress_priority(args);
-		   if (copy_to_user((void*)arg, &args,
-		        sizeof(struct vlan_ioctl_args))) {
-		        err = -EFAULT;
-		   }
-		*/
-		err = -EINVAL;
-		break;
-	case GET_VLAN_EGRESS_PRIORITY_CMD:
-		/* TODO:  Implement
-		   err = vlan_dev_get_egress_priority(args.device1, &(args.args);
-		   if (copy_to_user((void*)arg, &args,
-		        sizeof(struct vlan_ioctl_args))) {
-		        err = -EFAULT;
-		   }
-		*/
-		err = -EINVAL;
-		break;
 	case GET_VLAN_REALDEV_NAME_CMD:
-		err = vlan_dev_get_realdev_name(args.device1, args.u.device2);
-		if (err)
-			goto out;
+		err = 0;
+		vlan_dev_get_realdev_name(dev, args.u.device2);
 		if (copy_to_user(arg, &args,
-				 sizeof(struct vlan_ioctl_args))) {
+				 sizeof(struct vlan_ioctl_args)))
 			err = -EFAULT;
-		}
 		break;
 
 	case GET_VLAN_VID_CMD:
-		err = vlan_dev_get_vid(args.device1, &vid);
-		if (err)
-			goto out;
-		args.u.VID = vid;
+		err = 0;
+		args.u.VID = vlan_dev_vlan_id(dev);
 		if (copy_to_user(arg, &args,
-				 sizeof(struct vlan_ioctl_args))) {
-                      err = -EFAULT;
-		}
+				 sizeof(struct vlan_ioctl_args)))
+		      err = -EFAULT;
 		break;
 
 	default:
-		/* pass on to underlying device instead?? */
-		printk(VLAN_DBG "%s: Unknown VLAN CMD: %x \n",
-			__FUNCTION__, args.cmd);
-		return -EINVAL;
-	};
+		err = -EOPNOTSUPP;
+		break;
+	}
 out:
+	rtnl_unlock();
+	return err;
+}
+
+static int __net_init vlan_init_net(struct net *net)
+{
+	struct vlan_net *vn = net_generic(net, vlan_net_id);
+	int err;
+
+	vn->name_type = VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD;
+
+	err = vlan_proc_init(net);
+
+	return err;
+}
+
+static void __net_exit vlan_exit_net(struct net *net)
+{
+	vlan_proc_cleanup(net);
+}
+
+static struct pernet_operations vlan_net_ops = {
+	.init = vlan_init_net,
+	.exit = vlan_exit_net,
+	.id   = &vlan_net_id,
+	.size = sizeof(struct vlan_net),
+};
+
+static int __init vlan_proto_init(void)
+{
+	int err;
+
+	pr_info("%s v%s\n", vlan_fullname, vlan_version);
+
+	err = register_pernet_subsys(&vlan_net_ops);
+	if (err < 0)
+		goto err0;
+
+	err = register_netdevice_notifier(&vlan_notifier_block);
+	if (err < 0)
+		goto err2;
+
+	err = vlan_gvrp_init();
+	if (err < 0)
+		goto err3;
+
+	err = vlan_mvrp_init();
+	if (err < 0)
+		goto err4;
+
+	err = vlan_netlink_init();
+	if (err < 0)
+		goto err5;
+
+	vlan_ioctl_set(vlan_ioctl_handler);
+	return 0;
+
+err5:
+	vlan_mvrp_uninit();
+err4:
+	vlan_gvrp_uninit();
+err3:
+	unregister_netdevice_notifier(&vlan_notifier_block);
+err2:
+	unregister_pernet_subsys(&vlan_net_ops);
+err0:
 	return err;
 }
 
+static void __exit vlan_cleanup_module(void)
+{
+	vlan_ioctl_set(NULL);
+	vlan_netlink_fini();
+
+	unregister_netdevice_notifier(&vlan_notifier_block);
+
+	unregister_pernet_subsys(&vlan_net_ops);
+	rcu_barrier(); /* Wait for completion of call_rcu()'s */
+
+	vlan_mvrp_uninit();
+	vlan_gvrp_uninit();
+}
+
+module_init(vlan_proto_init);
+module_exit(vlan_cleanup_module);
+
 MODULE_LICENSE("GPL");
 MODULE_VERSION(DRV_VERSION);
diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h
index 9ae3a14dd01..9d010a09ab9 100644
--- a/net/8021q/vlan.h
+++ b/net/8021q/vlan.h
@@ -2,71 +2,172 @@
 #define __BEN_VLAN_802_1Q_INC__
 
 #include <linux/if_vlan.h>
+#include <linux/u64_stats_sync.h>
+#include <linux/list.h>
 
-/*  Uncomment this if you want debug traces to be shown. */
-/* #define VLAN_DEBUG */
+/* if this changes, algorithm will have to be reworked because this
+ * depends on completely exhausting the VLAN identifier space.  Thus
+ * it gives constant time look-up, but in many cases it wastes memory.
+ */
+#define VLAN_GROUP_ARRAY_SPLIT_PARTS  8
+#define VLAN_GROUP_ARRAY_PART_LEN     (VLAN_N_VID/VLAN_GROUP_ARRAY_SPLIT_PARTS)
 
-#define VLAN_ERR KERN_ERR
-#define VLAN_INF KERN_INFO
-#define VLAN_DBG KERN_ALERT /* change these... to debug, having a hard time
-                             * changing the log level at run-time..for some reason.
-                             */
+enum vlan_protos {
+	VLAN_PROTO_8021Q	= 0,
+	VLAN_PROTO_8021AD,
+	VLAN_PROTO_NUM,
+};
 
-/*
+struct vlan_group {
+	unsigned int		nr_vlan_devs;
+	struct hlist_node	hlist;	/* linked list */
+	struct net_device **vlan_devices_arrays[VLAN_PROTO_NUM]
+					       [VLAN_GROUP_ARRAY_SPLIT_PARTS];
+};
 
-These I use for memory debugging.  I feared a leak at one time, but
-I never found it..and the problem seems to have dissappeared.  Still,
-I'll bet they might prove useful again... --Ben
+struct vlan_info {
+	struct net_device	*real_dev; /* The ethernet(like) device
+					    * the vlan is attached to.
+					    */
+	struct vlan_group	grp;
+	struct list_head	vid_list;
+	unsigned int		nr_vids;
+	struct rcu_head		rcu;
+};
 
+static inline unsigned int vlan_proto_idx(__be16 proto)
+{
+	switch (proto) {
+	case htons(ETH_P_8021Q):
+		return VLAN_PROTO_8021Q;
+	case htons(ETH_P_8021AD):
+		return VLAN_PROTO_8021AD;
+	default:
+		BUG();
+		return 0;
+	}
+}
 
-#define VLAN_MEM_DBG(x, y, z) printk(VLAN_DBG "%s:  "  x, __FUNCTION__, y, z);
-#define VLAN_FMEM_DBG(x, y) printk(VLAN_DBG "%s:  " x, __FUNCTION__, y);
-*/
+static inline struct net_device *__vlan_group_get_device(struct vlan_group *vg,
+							 unsigned int pidx,
+							 u16 vlan_id)
+{
+	struct net_device **array;
 
-/* This way they don't do anything! */
-#define VLAN_MEM_DBG(x, y, z) 
-#define VLAN_FMEM_DBG(x, y)
+	array = vg->vlan_devices_arrays[pidx]
+				       [vlan_id / VLAN_GROUP_ARRAY_PART_LEN];
+	return array ? array[vlan_id % VLAN_GROUP_ARRAY_PART_LEN] : NULL;
+}
 
+static inline struct net_device *vlan_group_get_device(struct vlan_group *vg,
+						       __be16 vlan_proto,
+						       u16 vlan_id)
+{
+	return __vlan_group_get_device(vg, vlan_proto_idx(vlan_proto), vlan_id);
+}
 
-extern unsigned short vlan_name_type;
+static inline void vlan_group_set_device(struct vlan_group *vg,
+					 __be16 vlan_proto, u16 vlan_id,
+					 struct net_device *dev)
+{
+	struct net_device **array;
+	if (!vg)
+		return;
+	array = vg->vlan_devices_arrays[vlan_proto_idx(vlan_proto)]
+				       [vlan_id / VLAN_GROUP_ARRAY_PART_LEN];
+	array[vlan_id % VLAN_GROUP_ARRAY_PART_LEN] = dev;
+}
 
-#define VLAN_GRP_HASH_SHIFT	5
-#define VLAN_GRP_HASH_SIZE	(1 << VLAN_GRP_HASH_SHIFT)
-#define VLAN_GRP_HASH_MASK	(VLAN_GRP_HASH_SIZE - 1)
+/* Must be invoked with rcu_read_lock or with RTNL. */
+static inline struct net_device *vlan_find_dev(struct net_device *real_dev,
+					       __be16 vlan_proto, u16 vlan_id)
+{
+	struct vlan_info *vlan_info = rcu_dereference_rtnl(real_dev->vlan_info);
 
-/*  Find a VLAN device by the MAC address of its Ethernet device, and
- *  it's VLAN ID.  The default configuration is to have VLAN's scope
- *  to be box-wide, so the MAC will be ignored.  The mac will only be
- *  looked at if we are configured to have a separate set of VLANs per
- *  each MAC addressable interface.  Note that this latter option does
- *  NOT follow the spec for VLANs, but may be useful for doing very
- *  large quantities of VLAN MUX/DEMUX onto FrameRelay or ATM PVCs.
- *
- *  Must be invoked with rcu_read_lock (ie preempt disabled)
- *  or with RTNL.
- */
-struct net_device *__find_vlan_dev(struct net_device* real_dev,
-				   unsigned short VID); /* vlan.c */
+	if (vlan_info)
+		return vlan_group_get_device(&vlan_info->grp,
+					     vlan_proto, vlan_id);
+
+	return NULL;
+}
+
+#define vlan_group_for_each_dev(grp, i, dev) \
+	for ((i) = 0; i < VLAN_PROTO_NUM * VLAN_N_VID; i++) \
+		if (((dev) = __vlan_group_get_device((grp), (i) / VLAN_N_VID, \
+							    (i) % VLAN_N_VID)))
 
 /* found in vlan_dev.c */
-int vlan_dev_rebuild_header(struct sk_buff *skb);
-int vlan_skb_recv(struct sk_buff *skb, struct net_device *dev,
-                  struct packet_type *ptype, struct net_device *orig_dev);
-int vlan_dev_hard_header(struct sk_buff *skb, struct net_device *dev,
-                         unsigned short type, void *daddr, void *saddr,
-                         unsigned len);
-int vlan_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev);
-int vlan_dev_hwaccel_hard_start_xmit(struct sk_buff *skb, struct net_device *dev);
-int vlan_dev_change_mtu(struct net_device *dev, int new_mtu);
-int vlan_dev_set_mac_address(struct net_device *dev, void* addr);
-int vlan_dev_open(struct net_device* dev);
-int vlan_dev_stop(struct net_device* dev);
-int vlan_dev_ioctl(struct net_device* dev, struct ifreq *ifr, int cmd);
-int vlan_dev_set_ingress_priority(char* dev_name, __u32 skb_prio, short vlan_prio);
-int vlan_dev_set_egress_priority(char* dev_name, __u32 skb_prio, short vlan_prio);
-int vlan_dev_set_vlan_flag(char* dev_name, __u32 flag, short flag_val);
-int vlan_dev_get_realdev_name(const char* dev_name, char* result);
-int vlan_dev_get_vid(const char* dev_name, unsigned short* result);
-void vlan_dev_set_multicast_list(struct net_device *vlan_dev);
+void vlan_dev_set_ingress_priority(const struct net_device *dev,
+				   u32 skb_prio, u16 vlan_prio);
+int vlan_dev_set_egress_priority(const struct net_device *dev,
+				 u32 skb_prio, u16 vlan_prio);
+int vlan_dev_change_flags(const struct net_device *dev, u32 flag, u32 mask);
+void vlan_dev_get_realdev_name(const struct net_device *dev, char *result);
+
+int vlan_check_real_dev(struct net_device *real_dev,
+			__be16 protocol, u16 vlan_id);
+void vlan_setup(struct net_device *dev);
+int register_vlan_dev(struct net_device *dev);
+void unregister_vlan_dev(struct net_device *dev, struct list_head *head);
+
+static inline u32 vlan_get_ingress_priority(struct net_device *dev,
+					    u16 vlan_tci)
+{
+	struct vlan_dev_priv *vip = vlan_dev_priv(dev);
+
+	return vip->ingress_priority_map[(vlan_tci >> VLAN_PRIO_SHIFT) & 0x7];
+}
+
+#ifdef CONFIG_VLAN_8021Q_GVRP
+int vlan_gvrp_request_join(const struct net_device *dev);
+void vlan_gvrp_request_leave(const struct net_device *dev);
+int vlan_gvrp_init_applicant(struct net_device *dev);
+void vlan_gvrp_uninit_applicant(struct net_device *dev);
+int vlan_gvrp_init(void);
+void vlan_gvrp_uninit(void);
+#else
+static inline int vlan_gvrp_request_join(const struct net_device *dev) { return 0; }
+static inline void vlan_gvrp_request_leave(const struct net_device *dev) {}
+static inline int vlan_gvrp_init_applicant(struct net_device *dev) { return 0; }
+static inline void vlan_gvrp_uninit_applicant(struct net_device *dev) {}
+static inline int vlan_gvrp_init(void) { return 0; }
+static inline void vlan_gvrp_uninit(void) {}
+#endif
+
+#ifdef CONFIG_VLAN_8021Q_MVRP
+int vlan_mvrp_request_join(const struct net_device *dev);
+void vlan_mvrp_request_leave(const struct net_device *dev);
+int vlan_mvrp_init_applicant(struct net_device *dev);
+void vlan_mvrp_uninit_applicant(struct net_device *dev);
+int vlan_mvrp_init(void);
+void vlan_mvrp_uninit(void);
+#else
+static inline int vlan_mvrp_request_join(const struct net_device *dev) { return 0; }
+static inline void vlan_mvrp_request_leave(const struct net_device *dev) {}
+static inline int vlan_mvrp_init_applicant(struct net_device *dev) { return 0; }
+static inline void vlan_mvrp_uninit_applicant(struct net_device *dev) {}
+static inline int vlan_mvrp_init(void) { return 0; }
+static inline void vlan_mvrp_uninit(void) {}
+#endif
+
+extern const char vlan_fullname[];
+extern const char vlan_version[];
+int vlan_netlink_init(void);
+void vlan_netlink_fini(void);
+
+extern struct rtnl_link_ops vlan_link_ops;
+
+extern int vlan_net_id;
+
+struct proc_dir_entry;
+
+struct vlan_net {
+	/* /proc/net/vlan */
+	struct proc_dir_entry *proc_vlan_dir;
+	/* /proc/net/vlan/config */
+	struct proc_dir_entry *proc_vlan_conf;
+	/* Determines interface naming scheme. */
+	unsigned short name_type;
+};
 
 #endif /* !(__BEN_VLAN_802_1Q_INC__) */
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
new file mode 100644
index 00000000000..75d42776399
--- /dev/null
+++ b/net/8021q/vlan_core.c
@@ -0,0 +1,415 @@
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/if_vlan.h>
+#include <linux/netpoll.h>
+#include <linux/export.h>
+#include "vlan.h"
+
+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);
+	struct net_device *vlan_dev;
+	struct vlan_pcpu_stats *rx_stats;
+
+	vlan_dev = vlan_find_dev(skb->dev, vlan_proto, vlan_id);
+	if (!vlan_dev)
+		return false;
+
+	skb = *skbp = skb_share_check(skb, GFP_ATOMIC);
+	if (unlikely(!skb))
+		return false;
+
+	skb->dev = vlan_dev;
+	if (unlikely(skb->pkt_type == PACKET_OTHERHOST)) {
+		/* Our lower layer thinks this is not local, let's make sure.
+		 * This allows the VLAN to have a different MAC than the
+		 * underlying device, and still route correctly. */
+		if (ether_addr_equal_64bits(eth_hdr(skb)->h_dest, vlan_dev->dev_addr))
+			skb->pkt_type = PACKET_HOST;
+	}
+
+	if (!(vlan_dev_priv(vlan_dev)->flags & VLAN_FLAG_REORDER_HDR)) {
+		unsigned int offset = skb->data - skb_mac_header(skb);
+
+		/*
+		 * 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);
+		skb = *skbp = vlan_insert_tag(skb, skb->vlan_proto,
+					      skb->vlan_tci);
+		if (!skb)
+			return false;
+		skb_pull(skb, offset + VLAN_HLEN);
+		skb_reset_mac_len(skb);
+	}
+
+	skb->priority = vlan_get_ingress_priority(vlan_dev, skb->vlan_tci);
+	skb->vlan_tci = 0;
+
+	rx_stats = this_cpu_ptr(vlan_dev_priv(vlan_dev)->vlan_pcpu_stats);
+
+	u64_stats_update_begin(&rx_stats->syncp);
+	rx_stats->rx_packets++;
+	rx_stats->rx_bytes += skb->len;
+	if (skb->pkt_type == PACKET_MULTICAST)
+		rx_stats->rx_multicast++;
+	u64_stats_update_end(&rx_stats->syncp);
+
+	return true;
+}
+
+/* Must be invoked with rcu_read_lock. */
+struct net_device *__vlan_find_dev_deep_rcu(struct net_device *dev,
+					__be16 vlan_proto, u16 vlan_id)
+{
+	struct vlan_info *vlan_info = rcu_dereference(dev->vlan_info);
+
+	if (vlan_info) {
+		return vlan_group_get_device(&vlan_info->grp,
+					     vlan_proto, vlan_id);
+	} else {
+		/*
+		 * Lower devices of master uppers (bonding, team) do not have
+		 * grp assigned to themselves. Grp is assigned to upper device
+		 * instead.
+		 */
+		struct net_device *upper_dev;
+
+		upper_dev = netdev_master_upper_dev_get_rcu(dev);
+		if (upper_dev)
+			return __vlan_find_dev_deep_rcu(upper_dev,
+						    vlan_proto, vlan_id);
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL(__vlan_find_dev_deep_rcu);
+
+struct net_device *vlan_dev_real_dev(const struct net_device *dev)
+{
+	struct net_device *ret = vlan_dev_priv(dev)->real_dev;
+
+	while (is_vlan_dev(ret))
+		ret = vlan_dev_priv(ret)->real_dev;
+
+	return ret;
+}
+EXPORT_SYMBOL(vlan_dev_real_dev);
+
+u16 vlan_dev_vlan_id(const struct net_device *dev)
+{
+	return vlan_dev_priv(dev)->vlan_id;
+}
+EXPORT_SYMBOL(vlan_dev_vlan_id);
+
+__be16 vlan_dev_vlan_proto(const struct net_device *dev)
+{
+	return vlan_dev_priv(dev)->vlan_proto;
+}
+EXPORT_SYMBOL(vlan_dev_vlan_proto);
+
+static struct sk_buff *vlan_reorder_header(struct sk_buff *skb)
+{
+	if (skb_cow(skb, skb_headroom(skb)) < 0) {
+		kfree_skb(skb);
+		return NULL;
+	}
+
+	memmove(skb->data - ETH_HLEN, skb->data - VLAN_ETH_HLEN, 2 * ETH_ALEN);
+	skb->mac_header += VLAN_HLEN;
+	return skb;
+}
+
+struct sk_buff *vlan_untag(struct sk_buff *skb)
+{
+	struct vlan_hdr *vhdr;
+	u16 vlan_tci;
+
+	if (unlikely(vlan_tx_tag_present(skb))) {
+		/* vlan_tci is already set-up so leave this for another time */
+		return skb;
+	}
+
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (unlikely(!skb))
+		goto err_free;
+
+	if (unlikely(!pskb_may_pull(skb, VLAN_HLEN)))
+		goto err_free;
+
+	vhdr = (struct vlan_hdr *) skb->data;
+	vlan_tci = ntohs(vhdr->h_vlan_TCI);
+	__vlan_hwaccel_put_tag(skb, skb->protocol, vlan_tci);
+
+	skb_pull_rcsum(skb, VLAN_HLEN);
+	vlan_set_encap_proto(skb, vhdr);
+
+	skb = vlan_reorder_header(skb);
+	if (unlikely(!skb))
+		goto err_free;
+
+	skb_reset_network_header(skb);
+	skb_reset_transport_header(skb);
+	skb_reset_mac_len(skb);
+
+	return skb;
+
+err_free:
+	kfree_skb(skb);
+	return NULL;
+}
+EXPORT_SYMBOL(vlan_untag);
+
+
+/*
+ * vlan info and vid list
+ */
+
+static void vlan_group_free(struct vlan_group *grp)
+{
+	int i, j;
+
+	for (i = 0; i < VLAN_PROTO_NUM; i++)
+		for (j = 0; j < VLAN_GROUP_ARRAY_SPLIT_PARTS; j++)
+			kfree(grp->vlan_devices_arrays[i][j]);
+}
+
+static void vlan_info_free(struct vlan_info *vlan_info)
+{
+	vlan_group_free(&vlan_info->grp);
+	kfree(vlan_info);
+}
+
+static void vlan_info_rcu_free(struct rcu_head *rcu)
+{
+	vlan_info_free(container_of(rcu, struct vlan_info, rcu));
+}
+
+static struct vlan_info *vlan_info_alloc(struct net_device *dev)
+{
+	struct vlan_info *vlan_info;
+
+	vlan_info = kzalloc(sizeof(struct vlan_info), GFP_KERNEL);
+	if (!vlan_info)
+		return NULL;
+
+	vlan_info->real_dev = dev;
+	INIT_LIST_HEAD(&vlan_info->vid_list);
+	return vlan_info;
+}
+
+struct vlan_vid_info {
+	struct list_head list;
+	__be16 proto;
+	u16 vid;
+	int refcount;
+};
+
+static bool vlan_hw_filter_capable(const struct net_device *dev,
+				     const struct vlan_vid_info *vid_info)
+{
+	if (vid_info->proto == htons(ETH_P_8021Q) &&
+	    dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)
+		return true;
+	if (vid_info->proto == htons(ETH_P_8021AD) &&
+	    dev->features & NETIF_F_HW_VLAN_STAG_FILTER)
+		return true;
+	return false;
+}
+
+static struct vlan_vid_info *vlan_vid_info_get(struct vlan_info *vlan_info,
+					       __be16 proto, u16 vid)
+{
+	struct vlan_vid_info *vid_info;
+
+	list_for_each_entry(vid_info, &vlan_info->vid_list, list) {
+		if (vid_info->proto == proto && vid_info->vid == vid)
+			return vid_info;
+	}
+	return NULL;
+}
+
+static struct vlan_vid_info *vlan_vid_info_alloc(__be16 proto, u16 vid)
+{
+	struct vlan_vid_info *vid_info;
+
+	vid_info = kzalloc(sizeof(struct vlan_vid_info), GFP_KERNEL);
+	if (!vid_info)
+		return NULL;
+	vid_info->proto = proto;
+	vid_info->vid = vid;
+
+	return vid_info;
+}
+
+static int __vlan_vid_add(struct vlan_info *vlan_info, __be16 proto, u16 vid,
+			  struct vlan_vid_info **pvid_info)
+{
+	struct net_device *dev = vlan_info->real_dev;
+	const struct net_device_ops *ops = dev->netdev_ops;
+	struct vlan_vid_info *vid_info;
+	int err;
+
+	vid_info = vlan_vid_info_alloc(proto, vid);
+	if (!vid_info)
+		return -ENOMEM;
+
+	if (vlan_hw_filter_capable(dev, vid_info)) {
+		err =  ops->ndo_vlan_rx_add_vid(dev, proto, vid);
+		if (err) {
+			kfree(vid_info);
+			return err;
+		}
+	}
+	list_add(&vid_info->list, &vlan_info->vid_list);
+	vlan_info->nr_vids++;
+	*pvid_info = vid_info;
+	return 0;
+}
+
+int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid)
+{
+	struct vlan_info *vlan_info;
+	struct vlan_vid_info *vid_info;
+	bool vlan_info_created = false;
+	int err;
+
+	ASSERT_RTNL();
+
+	vlan_info = rtnl_dereference(dev->vlan_info);
+	if (!vlan_info) {
+		vlan_info = vlan_info_alloc(dev);
+		if (!vlan_info)
+			return -ENOMEM;
+		vlan_info_created = true;
+	}
+	vid_info = vlan_vid_info_get(vlan_info, proto, vid);
+	if (!vid_info) {
+		err = __vlan_vid_add(vlan_info, proto, vid, &vid_info);
+		if (err)
+			goto out_free_vlan_info;
+	}
+	vid_info->refcount++;
+
+	if (vlan_info_created)
+		rcu_assign_pointer(dev->vlan_info, vlan_info);
+
+	return 0;
+
+out_free_vlan_info:
+	if (vlan_info_created)
+		kfree(vlan_info);
+	return err;
+}
+EXPORT_SYMBOL(vlan_vid_add);
+
+static void __vlan_vid_del(struct vlan_info *vlan_info,
+			   struct vlan_vid_info *vid_info)
+{
+	struct net_device *dev = vlan_info->real_dev;
+	const struct net_device_ops *ops = dev->netdev_ops;
+	__be16 proto = vid_info->proto;
+	u16 vid = vid_info->vid;
+	int err;
+
+	if (vlan_hw_filter_capable(dev, vid_info)) {
+		err = ops->ndo_vlan_rx_kill_vid(dev, proto, vid);
+		if (err) {
+			pr_warn("failed to kill vid %04x/%d for device %s\n",
+				proto, vid, dev->name);
+		}
+	}
+	list_del(&vid_info->list);
+	kfree(vid_info);
+	vlan_info->nr_vids--;
+}
+
+void vlan_vid_del(struct net_device *dev, __be16 proto, u16 vid)
+{
+	struct vlan_info *vlan_info;
+	struct vlan_vid_info *vid_info;
+
+	ASSERT_RTNL();
+
+	vlan_info = rtnl_dereference(dev->vlan_info);
+	if (!vlan_info)
+		return;
+
+	vid_info = vlan_vid_info_get(vlan_info, proto, vid);
+	if (!vid_info)
+		return;
+	vid_info->refcount--;
+	if (vid_info->refcount == 0) {
+		__vlan_vid_del(vlan_info, vid_info);
+		if (vlan_info->nr_vids == 0) {
+			RCU_INIT_POINTER(dev->vlan_info, NULL);
+			call_rcu(&vlan_info->rcu, vlan_info_rcu_free);
+		}
+	}
+}
+EXPORT_SYMBOL(vlan_vid_del);
+
+int vlan_vids_add_by_dev(struct net_device *dev,
+			 const struct net_device *by_dev)
+{
+	struct vlan_vid_info *vid_info;
+	struct vlan_info *vlan_info;
+	int err;
+
+	ASSERT_RTNL();
+
+	vlan_info = rtnl_dereference(by_dev->vlan_info);
+	if (!vlan_info)
+		return 0;
+
+	list_for_each_entry(vid_info, &vlan_info->vid_list, list) {
+		err = vlan_vid_add(dev, vid_info->proto, vid_info->vid);
+		if (err)
+			goto unwind;
+	}
+	return 0;
+
+unwind:
+	list_for_each_entry_continue_reverse(vid_info,
+					     &vlan_info->vid_list,
+					     list) {
+		vlan_vid_del(dev, vid_info->proto, vid_info->vid);
+	}
+
+	return err;
+}
+EXPORT_SYMBOL(vlan_vids_add_by_dev);
+
+void vlan_vids_del_by_dev(struct net_device *dev,
+			  const struct net_device *by_dev)
+{
+	struct vlan_vid_info *vid_info;
+	struct vlan_info *vlan_info;
+
+	ASSERT_RTNL();
+
+	vlan_info = rtnl_dereference(by_dev->vlan_info);
+	if (!vlan_info)
+		return;
+
+	list_for_each_entry(vid_info, &vlan_info->vid_list, list)
+		vlan_vid_del(dev, vid_info->proto, vid_info->vid);
+}
+EXPORT_SYMBOL(vlan_vids_del_by_dev);
+
+bool vlan_uses_dev(const struct net_device *dev)
+{
+	struct vlan_info *vlan_info;
+
+	ASSERT_RTNL();
+
+	vlan_info = rtnl_dereference(dev->vlan_info);
+	if (!vlan_info)
+		return false;
+	return vlan_info->grp.nr_vlan_devs ? true : false;
+}
+EXPORT_SYMBOL(vlan_uses_dev);
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 0f604d227da..dd11f612e03 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -3,16 +3,16 @@
  *		Ethernet-type device handling.
  *
  * Authors:	Ben Greear <greearb@candelatech.com>
- *              Please send support related email to: vlan@scry.wanfear.com
+ *              Please send support related email to: netdev@vger.kernel.org
  *              VLAN Home Page: http://www.candelatech.com/~greear/vlan.html
- * 
+ *
  * Fixes:       Mar 22 2001: Martin Bokaemper <mbokaemper@unispherenetworks.com>
  *                - reset skb->pkt_type on incoming packets when MAC was changed
  *                - see that changed MAC is saddr for outgoing packets
  *              Oct 20, 2001:  Ard van Breeman:
  *                - Fix MC-list, finally.
  *                - Flush MC-list on VLAN destroy.
- *                
+ *
  *
  *		This program is free software; you can redistribute it and/or
  *		modify it under the terms of the GNU General Public License
@@ -20,22 +20,20 @@
  *		2 of the License, or (at your option) any later version.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/in.h>
-#include <linux/init.h>
-#include <asm/uaccess.h> /* for copy_from_user */
+#include <linux/slab.h>
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
-#include <net/datalink.h>
-#include <net/p8022.h>
+#include <linux/ethtool.h>
 #include <net/arp.h>
 
 #include "vlan.h"
 #include "vlanproc.h"
 #include <linux/if_vlan.h>
-#include <net/ip.h>
+#include <linux/netpoll.h>
 
 /*
  *	Rebuild the Ethernet MAC header. This is called after an ARP
@@ -47,847 +45,764 @@
  *
  * TODO:  This needs a checkup, I'm ignorant here. --BLG
  */
-int vlan_dev_rebuild_header(struct sk_buff *skb)
+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 __constant_htons(ETH_P_IP):
+	case htons(ETH_P_IP):
 
 		/* TODO:  Confirm this will work with VLAN headers... */
 		return arp_find(veth->h_dest, skb);
-#endif	
+#endif
 	default:
-		printk(VLAN_DBG
-		       "%s: unable to resolve type %X addresses.\n", 
-		       dev->name, (int)veth->h_vlan_encapsulated_proto);
-	 
-		memcpy(veth->h_source, dev->dev_addr, ETH_ALEN);
-		break;
-	};
+		pr_debug("%s: unable to resolve type %X addresses\n",
+			 dev->name, ntohs(veth->h_vlan_encapsulated_proto));
 
-	return 0;
-}
-
-static inline struct sk_buff *vlan_check_reorder_header(struct sk_buff *skb)
-{
-	if (VLAN_DEV_INFO(skb->dev)->flags & 1) {
-		if (skb_shared(skb) || skb_cloned(skb)) {
-			struct sk_buff *nskb = skb_copy(skb, GFP_ATOMIC);
-			kfree_skb(skb);
-			skb = nskb;
-		}
-		if (skb) {
-			/* Lifted from Gleb's VLAN code... */
-			memmove(skb->data - ETH_HLEN,
-				skb->data - VLAN_ETH_HLEN, 12);
-			skb->mac.raw += VLAN_HLEN;
-		}
+		ether_addr_copy(veth->h_source, dev->dev_addr);
+		break;
 	}
 
-	return skb;
+	return 0;
 }
 
 /*
- *	Determine the packet's protocol ID. The rule here is that we 
- *	assume 802.3 if the type field is short enough to be a length.
- *	This is normal practice and works for any 'now in use' protocol.
- *
- *  Also, at this point we assume that we ARE dealing exclusively with
- *  VLAN packets, or packets that should be made into VLAN packets based
- *  on a default VLAN ID.
+ *	Create the VLAN header for an arbitrary protocol layer
  *
- *  NOTE:  Should be similar to ethernet/eth.c.
- *
- *  SANITY NOTE:  This method is called when a packet is moving up the stack
- *                towards userland.  To get here, it would have already passed
- *                through the ethernet/eth.c eth_type_trans() method.
- *  SANITY NOTE 2: We are referencing to the VLAN_HDR frields, which MAY be
- *                 stored UNALIGNED in the memory.  RISC systems don't like
- *                 such cases very much...
- *  SANITY NOTE 2a:  According to Dave Miller & Alexey, it will always be aligned,
- *                 so there doesn't need to be any of the unaligned stuff.  It has
- *                 been commented out now...  --Ben
+ *	saddr=NULL	means use device source address
+ *	daddr=NULL	means leave destination address (eg unresolved arp)
  *
+ *  This is called when the SKB is moving down the stack towards the
+ *  physical devices.
  */
-int vlan_skb_recv(struct sk_buff *skb, struct net_device *dev,
-                  struct packet_type* ptype, struct net_device *orig_dev)
+static int vlan_dev_hard_header(struct sk_buff *skb, struct net_device *dev,
+				unsigned short type,
+				const void *daddr, const void *saddr,
+				unsigned int len)
 {
-	unsigned char *rawp = NULL;
-	struct vlan_hdr *vhdr = (struct vlan_hdr *)(skb->data);
-	unsigned short vid;
-	struct net_device_stats *stats;
-	unsigned short vlan_TCI;
-	__be16 proto;
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+	struct vlan_hdr *vhdr;
+	unsigned int vhdrlen = 0;
+	u16 vlan_tci = 0;
+	int rc;
 
-	/* vlan_TCI = ntohs(get_unaligned(&vhdr->h_vlan_TCI)); */
-	vlan_TCI = ntohs(vhdr->h_vlan_TCI);
+	if (!(vlan->flags & VLAN_FLAG_REORDER_HDR)) {
+		vhdr = (struct vlan_hdr *) skb_push(skb, VLAN_HLEN);
 
-	vid = (vlan_TCI & VLAN_VID_MASK);
+		vlan_tci = vlan->vlan_id;
+		vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb->priority);
+		vhdr->h_vlan_TCI = htons(vlan_tci);
 
-#ifdef VLAN_DEBUG
-	printk(VLAN_DBG "%s: skb: %p vlan_id: %hx\n",
-		__FUNCTION__, skb, vid);
-#endif
+		/*
+		 *  Set the protocol type. For a packet of type ETH_P_802_3/2 we
+		 *  put the length in here instead.
+		 */
+		if (type != ETH_P_802_3 && type != ETH_P_802_2)
+			vhdr->h_vlan_encapsulated_proto = htons(type);
+		else
+			vhdr->h_vlan_encapsulated_proto = htons(len);
 
-	/* Ok, we will find the correct VLAN device, strip the header,
-	 * and then go on as usual.
-	 */
+		skb->protocol = vlan->vlan_proto;
+		type = ntohs(vlan->vlan_proto);
+		vhdrlen = VLAN_HLEN;
+	}
 
-	/* We have 12 bits of vlan ID.
-	 *
-	 * We must not drop allow preempt until we hold a
-	 * reference to the device (netif_rx does that) or we
-	 * fail.
-	 */
+	/* Before delegating work to the lower layer, enter our MAC-address */
+	if (saddr == NULL)
+		saddr = dev->dev_addr;
 
-	rcu_read_lock();
-	skb->dev = __find_vlan_dev(dev, vid);
-	if (!skb->dev) {
-		rcu_read_unlock();
+	/* Now make the underlying real hard header */
+	dev = vlan->real_dev;
+	rc = dev_hard_header(skb, dev, type, daddr, saddr, len + vhdrlen);
+	if (rc > 0)
+		rc += vhdrlen;
+	return rc;
+}
 
-#ifdef VLAN_DEBUG
-		printk(VLAN_DBG "%s: ERROR: No net_device for VID: %i on dev: %s [%i]\n",
-			__FUNCTION__, (unsigned int)(vid), dev->name, dev->ifindex);
+static inline netdev_tx_t vlan_netpoll_send_skb(struct vlan_dev_priv *vlan, struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	if (vlan->netpoll)
+		netpoll_send_skb(vlan->netpoll, skb);
+#else
+	BUG();
 #endif
-		kfree_skb(skb);
-		return -1;
-	}
-
-	skb->dev->last_rx = jiffies;
+	return NETDEV_TX_OK;
+}
 
-	/* Bump the rx counters for the VLAN device. */
-	stats = vlan_dev_get_stats(skb->dev);
-	stats->rx_packets++;
-	stats->rx_bytes += skb->len;
+static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb,
+					    struct net_device *dev)
+{
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+	struct vlan_ethhdr *veth = (struct vlan_ethhdr *)(skb->data);
+	unsigned int len;
+	int ret;
 
-	skb_pull(skb, VLAN_HLEN); /* take off the VLAN header (4 bytes currently) */
+	/* Handle non-VLAN frames if they are sent to us, for example by DHCP.
+	 *
+	 * NOTE: THIS ASSUMES DIX ETHERNET, SPECIFICALLY NOT SUPPORTING
+	 * OTHER THINGS LIKE FDDI/TokenRing/802.3 SNAPs...
+	 */
+	if (veth->h_vlan_proto != vlan->vlan_proto ||
+	    vlan->flags & VLAN_FLAG_REORDER_HDR) {
+		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);
+	}
 
-	/* Need to correct hardware checksum */
-	skb_postpull_rcsum(skb, vhdr, VLAN_HLEN);
+	skb->dev = vlan->real_dev;
+	len = skb->len;
+	if (unlikely(netpoll_tx_running(dev)))
+		return vlan_netpoll_send_skb(vlan, skb);
 
-	/* Ok, lets check to make sure the device (dev) we
-	 * came in on is what this VLAN is attached to.
-	 */
+	ret = dev_queue_xmit(skb);
 
-	if (dev != VLAN_DEV_INFO(skb->dev)->real_dev) {
-		rcu_read_unlock();
+	if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
+		struct vlan_pcpu_stats *stats;
 
-#ifdef VLAN_DEBUG
-		printk(VLAN_DBG "%s: dropping skb: %p because came in on wrong device, dev: %s  real_dev: %s, skb_dev: %s\n",
-			__FUNCTION__, skb, dev->name, 
-			VLAN_DEV_INFO(skb->dev)->real_dev->name, 
-			skb->dev->name);
-#endif
-		kfree_skb(skb);
-		stats->rx_errors++;
-		return -1;
+		stats = this_cpu_ptr(vlan->vlan_pcpu_stats);
+		u64_stats_update_begin(&stats->syncp);
+		stats->tx_packets++;
+		stats->tx_bytes += len;
+		u64_stats_update_end(&stats->syncp);
+	} else {
+		this_cpu_inc(vlan->vlan_pcpu_stats->tx_dropped);
 	}
 
-	/*
-	 * Deal with ingress priority mapping.
+	return ret;
+}
+
+static int vlan_dev_change_mtu(struct net_device *dev, int new_mtu)
+{
+	/* TODO: gotta make sure the underlying layer can handle it,
+	 * maybe an IFF_VLAN_CAPABLE flag for devices?
 	 */
-	skb->priority = vlan_get_ingress_priority(skb->dev, ntohs(vhdr->h_vlan_TCI));
+	if (vlan_dev_priv(dev)->real_dev->mtu < new_mtu)
+		return -ERANGE;
 
-#ifdef VLAN_DEBUG
-	printk(VLAN_DBG "%s: priority: %lu  for TCI: %hu (hbo)\n",
-		__FUNCTION__, (unsigned long)(skb->priority), 
-		ntohs(vhdr->h_vlan_TCI));
-#endif
+	dev->mtu = new_mtu;
 
-	/* The ethernet driver already did the pkt_type calculations
-	 * for us...
-	 */
-	switch (skb->pkt_type) {
-	case PACKET_BROADCAST: /* Yeah, stats collect these together.. */
-		// stats->broadcast ++; // no such counter :-(
-		break;
+	return 0;
+}
 
-	case PACKET_MULTICAST:
-		stats->multicast++;
-		break;
+void vlan_dev_set_ingress_priority(const struct net_device *dev,
+				   u32 skb_prio, u16 vlan_prio)
+{
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 
-	case PACKET_OTHERHOST: 
-		/* Our lower layer thinks this is not local, let's make sure.
-		 * This allows the VLAN to have a different MAC than the underlying
-		 * device, and still route correctly.
-		 */
-		if (!compare_ether_addr(eth_hdr(skb)->h_dest, skb->dev->dev_addr)) {
-			/* It is for our (changed) MAC-address! */
-			skb->pkt_type = PACKET_HOST;
-		}
-		break;
-	default:
-		break;
-	};
+	if (vlan->ingress_priority_map[vlan_prio & 0x7] && !skb_prio)
+		vlan->nr_ingress_mappings--;
+	else if (!vlan->ingress_priority_map[vlan_prio & 0x7] && skb_prio)
+		vlan->nr_ingress_mappings++;
 
-	/*  Was a VLAN packet, grab the encapsulated protocol, which the layer
-	 * three protocols care about.
-	 */
-	/* proto = get_unaligned(&vhdr->h_vlan_encapsulated_proto); */
-	proto = vhdr->h_vlan_encapsulated_proto;
+	vlan->ingress_priority_map[vlan_prio & 0x7] = skb_prio;
+}
 
-	skb->protocol = proto;
-	if (ntohs(proto) >= 1536) {
-		/* place it back on the queue to be handled by
-		 * true layer 3 protocols.
-		 */
+int vlan_dev_set_egress_priority(const struct net_device *dev,
+				 u32 skb_prio, u16 vlan_prio)
+{
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+	struct vlan_priority_tci_mapping *mp = NULL;
+	struct vlan_priority_tci_mapping *np;
+	u32 vlan_qos = (vlan_prio << VLAN_PRIO_SHIFT) & VLAN_PRIO_MASK;
 
-		/* See if we are configured to re-write the VLAN header
-		 * to make it look like ethernet...
-		 */
-		skb = vlan_check_reorder_header(skb);
-
-		/* Can be null if skb-clone fails when re-ordering */
-		if (skb) {
-			netif_rx(skb);
-		} else {
-			/* TODO:  Add a more specific counter here. */
-			stats->rx_errors++;
+	/* See if a priority mapping exists.. */
+	mp = vlan->egress_priority_map[skb_prio & 0xF];
+	while (mp) {
+		if (mp->priority == skb_prio) {
+			if (mp->vlan_qos && !vlan_qos)
+				vlan->nr_egress_mappings--;
+			else if (!mp->vlan_qos && vlan_qos)
+				vlan->nr_egress_mappings++;
+			mp->vlan_qos = vlan_qos;
+			return 0;
 		}
-		rcu_read_unlock();
-		return 0;
+		mp = mp->next;
 	}
 
-	rawp = skb->data;
-
-	/*
-	 * This is a magic hack to spot IPX packets. Older Novell breaks
-	 * the protocol design and runs IPX over 802.3 without an 802.2 LLC
-	 * layer. We look for FFFF which isn't a used 802.2 SSAP/DSAP. This
-	 * won't work for fault tolerant netware but does for the rest.
+	/* Create a new mapping then. */
+	mp = vlan->egress_priority_map[skb_prio & 0xF];
+	np = kmalloc(sizeof(struct vlan_priority_tci_mapping), GFP_KERNEL);
+	if (!np)
+		return -ENOBUFS;
+
+	np->next = mp;
+	np->priority = skb_prio;
+	np->vlan_qos = vlan_qos;
+	/* Before inserting this element in hash table, make sure all its fields
+	 * are committed to memory.
+	 * coupled with smp_rmb() in vlan_dev_get_egress_qos_mask()
 	 */
-	if (*(unsigned short *)rawp == 0xFFFF) {
-		skb->protocol = __constant_htons(ETH_P_802_3);
-		/* place it back on the queue to be handled by true layer 3 protocols.
-		 */
+	smp_wmb();
+	vlan->egress_priority_map[skb_prio & 0xF] = np;
+	if (vlan_qos)
+		vlan->nr_egress_mappings++;
+	return 0;
+}
 
-		/* See if we are configured to re-write the VLAN header
-		 * to make it look like ethernet...
-		 */
-		skb = vlan_check_reorder_header(skb);
-
-		/* Can be null if skb-clone fails when re-ordering */
-		if (skb) {
-			netif_rx(skb);
-		} else {
-			/* TODO:  Add a more specific counter here. */
-			stats->rx_errors++;
-		}
-		rcu_read_unlock();
-		return 0;
-	}
+/* Flags are defined in the vlan_flags enum in include/linux/if_vlan.h file. */
+int vlan_dev_change_flags(const struct net_device *dev, u32 flags, u32 mask)
+{
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+	u32 old_flags = vlan->flags;
 
-	/*
-	 *	Real 802.2 LLC
-	 */
-	skb->protocol = __constant_htons(ETH_P_802_2);
-	/* place it back on the queue to be handled by upper layer protocols.
-	 */
+	if (mask & ~(VLAN_FLAG_REORDER_HDR | VLAN_FLAG_GVRP |
+		     VLAN_FLAG_LOOSE_BINDING | VLAN_FLAG_MVRP))
+		return -EINVAL;
 
-	/* See if we are configured to re-write the VLAN header
-	 * to make it look like ethernet...
-	 */
-	skb = vlan_check_reorder_header(skb);
+	vlan->flags = (old_flags & ~mask) | (flags & mask);
 
-	/* Can be null if skb-clone fails when re-ordering */
-	if (skb) {
-		netif_rx(skb);
-	} else {
-		/* TODO:  Add a more specific counter here. */
-		stats->rx_errors++;
+	if (netif_running(dev) && (vlan->flags ^ old_flags) & VLAN_FLAG_GVRP) {
+		if (vlan->flags & VLAN_FLAG_GVRP)
+			vlan_gvrp_request_join(dev);
+		else
+			vlan_gvrp_request_leave(dev);
+	}
+
+	if (netif_running(dev) && (vlan->flags ^ old_flags) & VLAN_FLAG_MVRP) {
+		if (vlan->flags & VLAN_FLAG_MVRP)
+			vlan_mvrp_request_join(dev);
+		else
+			vlan_mvrp_request_leave(dev);
 	}
-	rcu_read_unlock();
 	return 0;
 }
 
-static inline unsigned short vlan_dev_get_egress_qos_mask(struct net_device* dev,
-							  struct sk_buff* skb)
+void vlan_dev_get_realdev_name(const struct net_device *dev, char *result)
 {
-	struct vlan_priority_tci_mapping *mp =
-		VLAN_DEV_INFO(dev)->egress_priority_map[(skb->priority & 0xF)];
-
-	while (mp) {
-		if (mp->priority == skb->priority) {
-			return mp->vlan_qos; /* This should already be shifted to mask
-					      * correctly with the VLAN's TCI
-					      */
-		}
-		mp = mp->next;
-	}
-	return 0;
+	strncpy(result, vlan_dev_priv(dev)->real_dev->name, 23);
 }
 
-/*
- *	Create the VLAN header for an arbitrary protocol layer 
- *
- *	saddr=NULL	means use device source address
- *	daddr=NULL	means leave destination address (eg unresolved arp)
- *
- *  This is called when the SKB is moving down the stack towards the
- *  physical devices.
- */
-int vlan_dev_hard_header(struct sk_buff *skb, struct net_device *dev,
-                         unsigned short type, void *daddr, void *saddr,
-                         unsigned len)
+static int vlan_dev_open(struct net_device *dev)
 {
-	struct vlan_hdr *vhdr;
-	unsigned short veth_TCI = 0;
-	int rc = 0;
-	int build_vlan_header = 0;
-	struct net_device *vdev = dev; /* save this for the bottom of the method */
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+	struct net_device *real_dev = vlan->real_dev;
+	int err;
 
-#ifdef VLAN_DEBUG
-	printk(VLAN_DBG "%s: skb: %p type: %hx len: %x vlan_id: %hx, daddr: %p\n",
-		__FUNCTION__, skb, type, len, VLAN_DEV_INFO(dev)->vlan_id, daddr);
-#endif
+	if (!(real_dev->flags & IFF_UP) &&
+	    !(vlan->flags & VLAN_FLAG_LOOSE_BINDING))
+		return -ENETDOWN;
 
-	/* build vlan header only if re_order_header flag is NOT set.  This
-	 * fixes some programs that get confused when they see a VLAN device
-	 * sending a frame that is VLAN encoded (the consensus is that the VLAN
-	 * device should look completely like an Ethernet device when the
-	 * REORDER_HEADER flag is set)	The drawback to this is some extra 
-	 * header shuffling in the hard_start_xmit.  Users can turn off this
-	 * REORDER behaviour with the vconfig tool.
-	 */
-	build_vlan_header = ((VLAN_DEV_INFO(dev)->flags & 1) == 0);
+	if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr)) {
+		err = dev_uc_add(real_dev, dev->dev_addr);
+		if (err < 0)
+			goto out;
+	}
 
-	if (build_vlan_header) {
-		vhdr = (struct vlan_hdr *) skb_push(skb, VLAN_HLEN);
+	if (dev->flags & IFF_ALLMULTI) {
+		err = dev_set_allmulti(real_dev, 1);
+		if (err < 0)
+			goto del_unicast;
+	}
+	if (dev->flags & IFF_PROMISC) {
+		err = dev_set_promiscuity(real_dev, 1);
+		if (err < 0)
+			goto clear_allmulti;
+	}
 
-		/* build the four bytes that make this a VLAN header. */
+	ether_addr_copy(vlan->real_dev_addr, real_dev->dev_addr);
 
-		/* Now, construct the second two bytes. This field looks something
-		 * like:
-		 * usr_priority: 3 bits	 (high bits)
-		 * CFI		 1 bit
-		 * VLAN ID	 12 bits (low bits)
-		 *
-		 */
-		veth_TCI = VLAN_DEV_INFO(dev)->vlan_id;
-		veth_TCI |= vlan_dev_get_egress_qos_mask(dev, skb);
+	if (vlan->flags & VLAN_FLAG_GVRP)
+		vlan_gvrp_request_join(dev);
 
-		vhdr->h_vlan_TCI = htons(veth_TCI);
+	if (vlan->flags & VLAN_FLAG_MVRP)
+		vlan_mvrp_request_join(dev);
 
-		/*
-		 *  Set the protocol type.
-		 *  For a packet of type ETH_P_802_3 we put the length in here instead.
-		 *  It is up to the 802.2 layer to carry protocol information.
-		 */
+	if (netif_carrier_ok(real_dev))
+		netif_carrier_on(dev);
+	return 0;
 
-		if (type != ETH_P_802_3) {
-			vhdr->h_vlan_encapsulated_proto = htons(type);
-		} else {
-			vhdr->h_vlan_encapsulated_proto = htons(len);
-		}
-	}
+clear_allmulti:
+	if (dev->flags & IFF_ALLMULTI)
+		dev_set_allmulti(real_dev, -1);
+del_unicast:
+	if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr))
+		dev_uc_del(real_dev, dev->dev_addr);
+out:
+	netif_carrier_off(dev);
+	return err;
+}
 
-	/* Before delegating work to the lower layer, enter our MAC-address */
-	if (saddr == NULL)
-		saddr = dev->dev_addr;
+static int vlan_dev_stop(struct net_device *dev)
+{
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+	struct net_device *real_dev = vlan->real_dev;
 
-	dev = VLAN_DEV_INFO(dev)->real_dev;
+	dev_mc_unsync(real_dev, dev);
+	dev_uc_unsync(real_dev, dev);
+	if (dev->flags & IFF_ALLMULTI)
+		dev_set_allmulti(real_dev, -1);
+	if (dev->flags & IFF_PROMISC)
+		dev_set_promiscuity(real_dev, -1);
 
-	/* MPLS can send us skbuffs w/out enough space.	 This check will grow the
-	 * skb if it doesn't have enough headroom.  Not a beautiful solution, so
-	 * I'll tick a counter so that users can know it's happening...	 If they
-	 * care...
-	 */
+	if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr))
+		dev_uc_del(real_dev, dev->dev_addr);
 
-	/* NOTE:  This may still break if the underlying device is not the final
-	 * device (and thus there are more headers to add...)  It should work for
-	 * good-ole-ethernet though.
-	 */
-	if (skb_headroom(skb) < dev->hard_header_len) {
-		struct sk_buff *sk_tmp = skb;
-		skb = skb_realloc_headroom(sk_tmp, dev->hard_header_len);
-		kfree_skb(sk_tmp);
-		if (skb == NULL) {
-			struct net_device_stats *stats = vlan_dev_get_stats(vdev);
-			stats->tx_dropped++;
-			return -ENOMEM;
-		}
-		VLAN_DEV_INFO(vdev)->cnt_inc_headroom_on_tx++;
-#ifdef VLAN_DEBUG
-		printk(VLAN_DBG "%s: %s: had to grow skb.\n", __FUNCTION__, vdev->name);
-#endif
-	}
+	netif_carrier_off(dev);
+	return 0;
+}
+
+static int vlan_dev_set_mac_address(struct net_device *dev, void *p)
+{
+	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
+	struct sockaddr *addr = p;
+	int err;
 
-	if (build_vlan_header) {
-		/* Now make the underlying real hard header */
-		rc = dev->hard_header(skb, dev, ETH_P_8021Q, daddr, saddr, len + VLAN_HLEN);
+	if (!is_valid_ether_addr(addr->sa_data))
+		return -EADDRNOTAVAIL;
 
-		if (rc > 0) {
-			rc += VLAN_HLEN;
-		} else if (rc < 0) {
-			rc -= VLAN_HLEN;
-		}
-	} else {
-		/* If here, then we'll just make a normal looking ethernet frame,
-		 * but, the hard_start_xmit method will insert the tag (it has to
-		 * be able to do this for bridged and other skbs that don't come
-		 * down the protocol stack in an orderly manner.
-		 */
-		rc = dev->hard_header(skb, dev, type, daddr, saddr, len);
+	if (!(dev->flags & IFF_UP))
+		goto out;
+
+	if (!ether_addr_equal(addr->sa_data, real_dev->dev_addr)) {
+		err = dev_uc_add(real_dev, addr->sa_data);
+		if (err < 0)
+			return err;
 	}
 
-	return rc;
+	if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr))
+		dev_uc_del(real_dev, dev->dev_addr);
+
+out:
+	ether_addr_copy(dev->dev_addr, addr->sa_data);
+	return 0;
 }
 
-int vlan_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static int vlan_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
-	struct net_device_stats *stats = vlan_dev_get_stats(dev);
-	struct vlan_ethhdr *veth = (struct vlan_ethhdr *)(skb->data);
+	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
+	const struct net_device_ops *ops = real_dev->netdev_ops;
+	struct ifreq ifrr;
+	int err = -EOPNOTSUPP;
 
-	/* Handle non-VLAN frames if they are sent to us, for example by DHCP.
-	 *
-	 * NOTE: THIS ASSUMES DIX ETHERNET, SPECIFICALLY NOT SUPPORTING
-	 * OTHER THINGS LIKE FDDI/TokenRing/802.3 SNAPs...
-	 */
+	strncpy(ifrr.ifr_name, real_dev->name, IFNAMSIZ);
+	ifrr.ifr_ifru = ifr->ifr_ifru;
 
-	if (veth->h_vlan_proto != __constant_htons(ETH_P_8021Q)) {
-		int orig_headroom = skb_headroom(skb);
-		unsigned short veth_TCI;
+	switch (cmd) {
+	case SIOCGMIIPHY:
+	case SIOCGMIIREG:
+	case SIOCSMIIREG:
+		if (netif_device_present(real_dev) && ops->ndo_do_ioctl)
+			err = ops->ndo_do_ioctl(real_dev, &ifrr, cmd);
+		break;
+	}
 
-		/* This is not a VLAN frame...but we can fix that! */
-		VLAN_DEV_INFO(dev)->cnt_encap_on_xmit++;
+	if (!err)
+		ifr->ifr_ifru = ifrr.ifr_ifru;
 
-#ifdef VLAN_DEBUG
-		printk(VLAN_DBG "%s: proto to encap: 0x%hx (hbo)\n",
-			__FUNCTION__, htons(veth->h_vlan_proto));
-#endif
-		/* Construct the second two bytes. This field looks something
-		 * like:
-		 * usr_priority: 3 bits	 (high bits)
-		 * CFI		 1 bit
-		 * VLAN ID	 12 bits (low bits)
-		 */
-		veth_TCI = VLAN_DEV_INFO(dev)->vlan_id;
-		veth_TCI |= vlan_dev_get_egress_qos_mask(dev, skb);
+	return err;
+}
 
-		skb = __vlan_put_tag(skb, veth_TCI);
-		if (!skb) {
-			stats->tx_dropped++;
-			return 0;
-		}
+static int vlan_dev_neigh_setup(struct net_device *dev, struct neigh_parms *pa)
+{
+	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
+	const struct net_device_ops *ops = real_dev->netdev_ops;
+	int err = 0;
 
-		if (orig_headroom < VLAN_HLEN) {
-			VLAN_DEV_INFO(dev)->cnt_inc_headroom_on_tx++;
-		}
-	}
+	if (netif_device_present(real_dev) && ops->ndo_neigh_setup)
+		err = ops->ndo_neigh_setup(real_dev, pa);
 
-#ifdef VLAN_DEBUG
-	printk(VLAN_DBG "%s: about to send skb: %p to dev: %s\n",
-		__FUNCTION__, skb, skb->dev->name);
-	printk(VLAN_DBG "  %2hx.%2hx.%2hx.%2xh.%2hx.%2hx %2hx.%2hx.%2hx.%2hx.%2hx.%2hx %4hx %4hx %4hx\n",
-	       veth->h_dest[0], veth->h_dest[1], veth->h_dest[2], veth->h_dest[3], veth->h_dest[4], veth->h_dest[5],
-	       veth->h_source[0], veth->h_source[1], veth->h_source[2], veth->h_source[3], veth->h_source[4], veth->h_source[5],
-	       veth->h_vlan_proto, veth->h_vlan_TCI, veth->h_vlan_encapsulated_proto);
-#endif
+	return err;
+}
 
-	stats->tx_packets++; /* for statics only */
-	stats->tx_bytes += skb->len;
+#if IS_ENABLED(CONFIG_FCOE)
+static int vlan_dev_fcoe_ddp_setup(struct net_device *dev, u16 xid,
+				   struct scatterlist *sgl, unsigned int sgc)
+{
+	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
+	const struct net_device_ops *ops = real_dev->netdev_ops;
+	int rc = 0;
 
-	skb->dev = VLAN_DEV_INFO(dev)->real_dev;
-	dev_queue_xmit(skb);
+	if (ops->ndo_fcoe_ddp_setup)
+		rc = ops->ndo_fcoe_ddp_setup(real_dev, xid, sgl, sgc);
 
-	return 0;
+	return rc;
 }
 
-int vlan_dev_hwaccel_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static int vlan_dev_fcoe_ddp_done(struct net_device *dev, u16 xid)
 {
-	struct net_device_stats *stats = vlan_dev_get_stats(dev);
-	unsigned short veth_TCI;
+	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
+	const struct net_device_ops *ops = real_dev->netdev_ops;
+	int len = 0;
 
-	/* Construct the second two bytes. This field looks something
-	 * like:
-	 * usr_priority: 3 bits	 (high bits)
-	 * CFI		 1 bit
-	 * VLAN ID	 12 bits (low bits)
-	 */
-	veth_TCI = VLAN_DEV_INFO(dev)->vlan_id;
-	veth_TCI |= vlan_dev_get_egress_qos_mask(dev, skb);
-	skb = __vlan_hwaccel_put_tag(skb, veth_TCI);
+	if (ops->ndo_fcoe_ddp_done)
+		len = ops->ndo_fcoe_ddp_done(real_dev, xid);
 
-	stats->tx_packets++;
-	stats->tx_bytes += skb->len;
+	return len;
+}
 
-	skb->dev = VLAN_DEV_INFO(dev)->real_dev;
-	dev_queue_xmit(skb);
+static int vlan_dev_fcoe_enable(struct net_device *dev)
+{
+	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
+	const struct net_device_ops *ops = real_dev->netdev_ops;
+	int rc = -EINVAL;
 
-	return 0;
+	if (ops->ndo_fcoe_enable)
+		rc = ops->ndo_fcoe_enable(real_dev);
+	return rc;
 }
 
-int vlan_dev_change_mtu(struct net_device *dev, int new_mtu)
+static int vlan_dev_fcoe_disable(struct net_device *dev)
 {
-	/* TODO: gotta make sure the underlying layer can handle it,
-	 * maybe an IFF_VLAN_CAPABLE flag for devices?
-	 */
-	if (VLAN_DEV_INFO(dev)->real_dev->mtu < new_mtu)
-		return -ERANGE;
+	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
+	const struct net_device_ops *ops = real_dev->netdev_ops;
+	int rc = -EINVAL;
 
-	dev->mtu = new_mtu;
+	if (ops->ndo_fcoe_disable)
+		rc = ops->ndo_fcoe_disable(real_dev);
+	return rc;
+}
 
-	return 0;
+static int vlan_dev_fcoe_get_wwn(struct net_device *dev, u64 *wwn, int type)
+{
+	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
+	const struct net_device_ops *ops = real_dev->netdev_ops;
+	int rc = -EINVAL;
+
+	if (ops->ndo_fcoe_get_wwn)
+		rc = ops->ndo_fcoe_get_wwn(real_dev, wwn, type);
+	return rc;
 }
 
-int vlan_dev_set_ingress_priority(char *dev_name, __u32 skb_prio, short vlan_prio)
+static int vlan_dev_fcoe_ddp_target(struct net_device *dev, u16 xid,
+				    struct scatterlist *sgl, unsigned int sgc)
 {
-	struct net_device *dev = dev_get_by_name(dev_name);
+	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
+	const struct net_device_ops *ops = real_dev->netdev_ops;
+	int rc = 0;
 
-	if (dev) {
-		if (dev->priv_flags & IFF_802_1Q_VLAN) {
-			/* see if a priority mapping exists.. */
-			VLAN_DEV_INFO(dev)->ingress_priority_map[vlan_prio & 0x7] = skb_prio;
-			dev_put(dev);
-			return 0;
-		}
+	if (ops->ndo_fcoe_ddp_target)
+		rc = ops->ndo_fcoe_ddp_target(real_dev, xid, sgl, sgc);
 
-		dev_put(dev);
-	}
-	return -EINVAL;
+	return rc;
 }
+#endif
 
-int vlan_dev_set_egress_priority(char *dev_name, __u32 skb_prio, short vlan_prio)
+static void vlan_dev_change_rx_flags(struct net_device *dev, int change)
 {
-	struct net_device *dev = dev_get_by_name(dev_name);
-	struct vlan_priority_tci_mapping *mp = NULL;
-	struct vlan_priority_tci_mapping *np;
-   
-	if (dev) {
-		if (dev->priv_flags & IFF_802_1Q_VLAN) {
-			/* See if a priority mapping exists.. */
-			mp = VLAN_DEV_INFO(dev)->egress_priority_map[skb_prio & 0xF];
-			while (mp) {
-				if (mp->priority == skb_prio) {
-					mp->vlan_qos = ((vlan_prio << 13) & 0xE000);
-					dev_put(dev);
-					return 0;
-				}
-				mp = mp->next;
-			}
-
-			/* Create a new mapping then. */
-			mp = VLAN_DEV_INFO(dev)->egress_priority_map[skb_prio & 0xF];
-			np = kmalloc(sizeof(struct vlan_priority_tci_mapping), GFP_KERNEL);
-			if (np) {
-				np->next = mp;
-				np->priority = skb_prio;
-				np->vlan_qos = ((vlan_prio << 13) & 0xE000);
-				VLAN_DEV_INFO(dev)->egress_priority_map[skb_prio & 0xF] = np;
-				dev_put(dev);
-				return 0;
-			} else {
-				dev_put(dev);
-				return -ENOBUFS;
-			}
-		}
-		dev_put(dev);
-	}
-	return -EINVAL;
-}
-
-/* Flags are defined in the vlan_dev_info class in include/linux/if_vlan.h file. */
-int vlan_dev_set_vlan_flag(char *dev_name, __u32 flag, short flag_val)
-{
-	struct net_device *dev = dev_get_by_name(dev_name);
-
-	if (dev) {
-		if (dev->priv_flags & IFF_802_1Q_VLAN) {
-			/* verify flag is supported */
-			if (flag == 1) {
-				if (flag_val) {
-					VLAN_DEV_INFO(dev)->flags |= 1;
-				} else {
-					VLAN_DEV_INFO(dev)->flags &= ~1;
-				}
-				dev_put(dev);
-				return 0;
-			} else {
-				printk(KERN_ERR  "%s: flag %i is not valid.\n",
-					__FUNCTION__, (int)(flag));
-				dev_put(dev);
-				return -EINVAL;
-			}
-		} else {
-			printk(KERN_ERR 
-			       "%s: %s is not a vlan device, priv_flags: %hX.\n",
-			       __FUNCTION__, dev->name, dev->priv_flags);
-			dev_put(dev);
-		}
-	} else {
-		printk(KERN_ERR  "%s: Could not find device: %s\n", 
-			__FUNCTION__, dev_name);
+	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
+
+	if (dev->flags & IFF_UP) {
+		if (change & IFF_ALLMULTI)
+			dev_set_allmulti(real_dev, dev->flags & IFF_ALLMULTI ? 1 : -1);
+		if (change & IFF_PROMISC)
+			dev_set_promiscuity(real_dev, dev->flags & IFF_PROMISC ? 1 : -1);
 	}
+}
 
-	return -EINVAL;
+static void vlan_dev_set_rx_mode(struct net_device *vlan_dev)
+{
+	dev_mc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
+	dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
 }
 
+/*
+ * vlan network devices have devices nesting below it, and are a special
+ * "super class" of normal network devices; split their locks off into a
+ * separate class since they always nest.
+ */
+static struct lock_class_key vlan_netdev_xmit_lock_key;
+static struct lock_class_key vlan_netdev_addr_lock_key;
 
-int vlan_dev_get_realdev_name(const char *dev_name, char* result)
+static void vlan_dev_set_lockdep_one(struct net_device *dev,
+				     struct netdev_queue *txq,
+				     void *_subclass)
 {
-	struct net_device *dev = dev_get_by_name(dev_name);
-	int rv = 0;
-	if (dev) {
-		if (dev->priv_flags & IFF_802_1Q_VLAN) {
-			strncpy(result, VLAN_DEV_INFO(dev)->real_dev->name, 23);
-			rv = 0;
-		} else {
-			rv = -EINVAL;
-		}
-		dev_put(dev);
-	} else {
-		rv = -ENODEV;
-	}
-	return rv;
+	lockdep_set_class_and_subclass(&txq->_xmit_lock,
+				       &vlan_netdev_xmit_lock_key,
+				       *(int *)_subclass);
 }
 
-int vlan_dev_get_vid(const char *dev_name, unsigned short* result)
+static void vlan_dev_set_lockdep_class(struct net_device *dev, int subclass)
 {
-	struct net_device *dev = dev_get_by_name(dev_name);
-	int rv = 0;
-	if (dev) {
-		if (dev->priv_flags & IFF_802_1Q_VLAN) {
-			*result = VLAN_DEV_INFO(dev)->vlan_id;
-			rv = 0;
-		} else {
-			rv = -EINVAL;
-		}
-		dev_put(dev);
-	} else {
-		rv = -ENODEV;
-	}
-	return rv;
+	lockdep_set_class_and_subclass(&dev->addr_list_lock,
+				       &vlan_netdev_addr_lock_key,
+				       subclass);
+	netdev_for_each_tx_queue(dev, vlan_dev_set_lockdep_one, &subclass);
 }
 
+static int vlan_dev_get_lock_subclass(struct net_device *dev)
+{
+	return vlan_dev_priv(dev)->nest_level;
+}
+
+static const struct header_ops vlan_header_ops = {
+	.create	 = vlan_dev_hard_header,
+	.rebuild = vlan_dev_rebuild_header,
+	.parse	 = eth_header_parse,
+};
 
-int vlan_dev_set_mac_address(struct net_device *dev, void *addr_struct_p)
+static int vlan_passthru_hard_header(struct sk_buff *skb, struct net_device *dev,
+				     unsigned short type,
+				     const void *daddr, const void *saddr,
+				     unsigned int len)
 {
-	struct sockaddr *addr = (struct sockaddr *)(addr_struct_p);
-	int i;
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+	struct net_device *real_dev = vlan->real_dev;
+
+	if (saddr == NULL)
+		saddr = dev->dev_addr;
 
-	if (netif_running(dev))
-		return -EBUSY;
+	return dev_hard_header(skb, real_dev, type, daddr, saddr, len);
+}
 
-	memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
+static const struct header_ops vlan_passthru_header_ops = {
+	.create	 = vlan_passthru_hard_header,
+	.rebuild = dev_rebuild_header,
+	.parse	 = eth_header_parse,
+};
 
-	printk("%s: Setting MAC address to ", dev->name);
-	for (i = 0; i < 6; i++)
-		printk(" %2.2x", dev->dev_addr[i]);
-	printk(".\n");
+static struct device_type vlan_type = {
+	.name	= "vlan",
+};
 
-	if (memcmp(VLAN_DEV_INFO(dev)->real_dev->dev_addr,
-		   dev->dev_addr,
-		   dev->addr_len) != 0) {
-		if (!(VLAN_DEV_INFO(dev)->real_dev->flags & IFF_PROMISC)) {
-			int flgs = VLAN_DEV_INFO(dev)->real_dev->flags;
+static const struct net_device_ops vlan_netdev_ops;
 
-			/* Increment our in-use promiscuity counter */
-			dev_set_promiscuity(VLAN_DEV_INFO(dev)->real_dev, 1);
+static int vlan_dev_init(struct net_device *dev)
+{
+	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
 
-			/* Make PROMISC visible to the user. */
-			flgs |= IFF_PROMISC;
-			printk("VLAN (%s):  Setting underlying device (%s) to promiscious mode.\n",
-			       dev->name, VLAN_DEV_INFO(dev)->real_dev->name);
-			dev_change_flags(VLAN_DEV_INFO(dev)->real_dev, flgs);
-		}
+	netif_carrier_off(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_HIGHDMA | NETIF_F_SCTP_CSUM |
+			   NETIF_F_ALL_FCOE;
+
+	dev->features |= real_dev->vlan_features | NETIF_F_LLTX;
+	dev->gso_max_size = real_dev->gso_max_size;
+	if (dev->features & NETIF_F_VLAN_FEATURES)
+		netdev_warn(real_dev, "VLAN features are set incorrectly.  Q-in-Q configurations may not work correctly.\n");
+
+
+	/* ipv6 shared card related stuff */
+	dev->dev_id = real_dev->dev_id;
+
+	if (is_zero_ether_addr(dev->dev_addr))
+		eth_hw_addr_inherit(dev, real_dev);
+	if (is_zero_ether_addr(dev->broadcast))
+		memcpy(dev->broadcast, real_dev->broadcast, dev->addr_len);
+
+#if IS_ENABLED(CONFIG_FCOE)
+	dev->fcoe_ddp_xid = real_dev->fcoe_ddp_xid;
+#endif
+
+	dev->needed_headroom = real_dev->needed_headroom;
+	if (vlan_hw_offload_capable(real_dev->features,
+				    vlan_dev_priv(dev)->vlan_proto)) {
+		dev->header_ops      = &vlan_passthru_header_ops;
+		dev->hard_header_len = real_dev->hard_header_len;
 	} else {
-		printk("VLAN (%s):  Underlying device (%s) has same MAC, not checking promiscious mode.\n",
-		       dev->name, VLAN_DEV_INFO(dev)->real_dev->name);
+		dev->header_ops      = &vlan_header_ops;
+		dev->hard_header_len = real_dev->hard_header_len + VLAN_HLEN;
 	}
 
-	return 0;
-}
+	dev->netdev_ops = &vlan_netdev_ops;
 
-static inline int vlan_dmi_equals(struct dev_mc_list *dmi1,
-                                  struct dev_mc_list *dmi2)
-{
-	return ((dmi1->dmi_addrlen == dmi2->dmi_addrlen) &&
-		(memcmp(dmi1->dmi_addr, dmi2->dmi_addr, dmi1->dmi_addrlen) == 0));
-}
+	SET_NETDEV_DEVTYPE(dev, &vlan_type);
 
-/** dmi is a single entry into a dev_mc_list, a single node.  mc_list is
- *  an entire list, and we'll iterate through it.
- */
-static int vlan_should_add_mc(struct dev_mc_list *dmi, struct dev_mc_list *mc_list)
-{
-	struct dev_mc_list *idmi;
-
-	for (idmi = mc_list; idmi != NULL; ) {
-		if (vlan_dmi_equals(dmi, idmi)) {
-			if (dmi->dmi_users > idmi->dmi_users)
-				return 1;
-			else
-				return 0;
-		} else {
-			idmi = idmi->next;
-		}
-	}
+	vlan_dev_set_lockdep_class(dev, vlan_dev_get_lock_subclass(dev));
 
-	return 1;
+	vlan_dev_priv(dev)->vlan_pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats);
+	if (!vlan_dev_priv(dev)->vlan_pcpu_stats)
+		return -ENOMEM;
+
+	return 0;
 }
 
-static inline void vlan_destroy_mc_list(struct dev_mc_list *mc_list)
+static void vlan_dev_uninit(struct net_device *dev)
 {
-	struct dev_mc_list *dmi = mc_list;
-	struct dev_mc_list *next;
+	struct vlan_priority_tci_mapping *pm;
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+	int i;
 
-	while(dmi) {
-		next = dmi->next;
-		kfree(dmi);
-		dmi = next;
+	for (i = 0; i < ARRAY_SIZE(vlan->egress_priority_map); i++) {
+		while ((pm = vlan->egress_priority_map[i]) != NULL) {
+			vlan->egress_priority_map[i] = pm->next;
+			kfree(pm);
+		}
 	}
 }
 
-static void vlan_copy_mc_list(struct dev_mc_list *mc_list, struct vlan_dev_info *vlan_info)
+static netdev_features_t vlan_dev_fix_features(struct net_device *dev,
+	netdev_features_t features)
 {
-	struct dev_mc_list *dmi, *new_dmi;
+	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
+	netdev_features_t old_features = features;
 
-	vlan_destroy_mc_list(vlan_info->old_mc_list);
-	vlan_info->old_mc_list = NULL;
+	features = netdev_intersect_features(features, real_dev->vlan_features);
+	features |= NETIF_F_RXCSUM;
+	features = netdev_intersect_features(features, real_dev->features);
 
-	for (dmi = mc_list; dmi != NULL; dmi = dmi->next) {
-		new_dmi = kmalloc(sizeof(*new_dmi), GFP_ATOMIC);
-		if (new_dmi == NULL) {
-			printk(KERN_ERR "vlan: cannot allocate memory. "
-			       "Multicast may not work properly from now.\n");
-			return;
-		}
+	features |= old_features & NETIF_F_SOFT_FEATURES;
+	features |= NETIF_F_LLTX;
 
-		/* Copy whole structure, then make new 'next' pointer */
-		*new_dmi = *dmi;
-		new_dmi->next = vlan_info->old_mc_list;
-		vlan_info->old_mc_list = new_dmi;
-	}
+	return features;
 }
 
-static void vlan_flush_mc_list(struct net_device *dev)
+static int vlan_ethtool_get_settings(struct net_device *dev,
+				     struct ethtool_cmd *cmd)
 {
-	struct dev_mc_list *dmi = dev->mc_list;
+	const struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 
-	while (dmi) {
-		printk(KERN_DEBUG "%s: del %.2x:%.2x:%.2x:%.2x:%.2x:%.2x mcast address from vlan interface\n",
-		       dev->name,
-		       dmi->dmi_addr[0],
-		       dmi->dmi_addr[1],
-		       dmi->dmi_addr[2],
-		       dmi->dmi_addr[3],
-		       dmi->dmi_addr[4],
-		       dmi->dmi_addr[5]);
-		dev_mc_delete(dev, dmi->dmi_addr, dmi->dmi_addrlen, 0);
-		dmi = dev->mc_list;
-	}
+	return __ethtool_get_settings(vlan->real_dev, cmd);
+}
 
-	/* dev->mc_list is NULL by the time we get here. */
-	vlan_destroy_mc_list(VLAN_DEV_INFO(dev)->old_mc_list);
-	VLAN_DEV_INFO(dev)->old_mc_list = NULL;
+static void vlan_ethtool_get_drvinfo(struct net_device *dev,
+				     struct ethtool_drvinfo *info)
+{
+	strlcpy(info->driver, vlan_fullname, sizeof(info->driver));
+	strlcpy(info->version, vlan_version, sizeof(info->version));
+	strlcpy(info->fw_version, "N/A", sizeof(info->fw_version));
 }
 
-int vlan_dev_open(struct net_device *dev)
+static struct rtnl_link_stats64 *vlan_dev_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 {
-	if (!(VLAN_DEV_INFO(dev)->real_dev->flags & IFF_UP))
-		return -ENETDOWN;
+	struct vlan_pcpu_stats *p;
+	u32 rx_errors = 0, tx_dropped = 0;
+	int i;
 
-	return 0;
+	for_each_possible_cpu(i) {
+		u64 rxpackets, rxbytes, rxmulticast, txpackets, txbytes;
+		unsigned int start;
+
+		p = per_cpu_ptr(vlan_dev_priv(dev)->vlan_pcpu_stats, i);
+		do {
+			start = u64_stats_fetch_begin_irq(&p->syncp);
+			rxpackets	= p->rx_packets;
+			rxbytes		= p->rx_bytes;
+			rxmulticast	= p->rx_multicast;
+			txpackets	= p->tx_packets;
+			txbytes		= p->tx_bytes;
+		} while (u64_stats_fetch_retry_irq(&p->syncp, start));
+
+		stats->rx_packets	+= rxpackets;
+		stats->rx_bytes		+= rxbytes;
+		stats->multicast	+= rxmulticast;
+		stats->tx_packets	+= txpackets;
+		stats->tx_bytes		+= txbytes;
+		/* rx_errors & tx_dropped are u32 */
+		rx_errors	+= p->rx_errors;
+		tx_dropped	+= p->tx_dropped;
+	}
+	stats->rx_errors  = rx_errors;
+	stats->tx_dropped = tx_dropped;
+
+	return stats;
 }
 
-int vlan_dev_stop(struct net_device *dev)
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void vlan_dev_poll_controller(struct net_device *dev)
 {
-	vlan_flush_mc_list(dev);
-	return 0;
+	return;
 }
 
-int vlan_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+static int vlan_dev_netpoll_setup(struct net_device *dev, struct netpoll_info *npinfo)
 {
-	struct net_device *real_dev = VLAN_DEV_INFO(dev)->real_dev;
-	struct ifreq ifrr;
-	int err = -EOPNOTSUPP;
-
-	strncpy(ifrr.ifr_name, real_dev->name, IFNAMSIZ);
-	ifrr.ifr_ifru = ifr->ifr_ifru;
-
-	switch(cmd) {
-	case SIOCGMIIPHY:
-	case SIOCGMIIREG:
-	case SIOCSMIIREG:
-		if (real_dev->do_ioctl && netif_device_present(real_dev)) 
-			err = real_dev->do_ioctl(real_dev, &ifrr, cmd);
-		break;
-
-	case SIOCETHTOOL:
-		err = dev_ethtool(&ifrr);
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+	struct net_device *real_dev = vlan->real_dev;
+	struct netpoll *netpoll;
+	int err = 0;
+
+	netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL);
+	err = -ENOMEM;
+	if (!netpoll)
+		goto out;
+
+	err = __netpoll_setup(netpoll, real_dev);
+	if (err) {
+		kfree(netpoll);
+		goto out;
 	}
 
-	if (!err) 
-		ifr->ifr_ifru = ifrr.ifr_ifru;
+	vlan->netpoll = netpoll;
 
+out:
 	return err;
 }
 
-/** Taken from Gleb + Lennert's VLAN code, and modified... */
-void vlan_dev_set_multicast_list(struct net_device *vlan_dev)
+static void vlan_dev_netpoll_cleanup(struct net_device *dev)
 {
-	struct dev_mc_list *dmi;
-	struct net_device *real_dev;
-	int inc;
+	struct vlan_dev_priv *vlan= vlan_dev_priv(dev);
+	struct netpoll *netpoll = vlan->netpoll;
 
-	if (vlan_dev && (vlan_dev->priv_flags & IFF_802_1Q_VLAN)) {
-		/* Then it's a real vlan device, as far as we can tell.. */
-		real_dev = VLAN_DEV_INFO(vlan_dev)->real_dev;
+	if (!netpoll)
+		return;
 
-		/* compare the current promiscuity to the last promisc we had.. */
-		inc = vlan_dev->promiscuity - VLAN_DEV_INFO(vlan_dev)->old_promiscuity;
-		if (inc) {
-			printk(KERN_INFO "%s: dev_set_promiscuity(master, %d)\n",
-			       vlan_dev->name, inc);
-			dev_set_promiscuity(real_dev, inc); /* found in dev.c */
-			VLAN_DEV_INFO(vlan_dev)->old_promiscuity = vlan_dev->promiscuity;
-		}
+	vlan->netpoll = NULL;
 
-		inc = vlan_dev->allmulti - VLAN_DEV_INFO(vlan_dev)->old_allmulti;
-		if (inc) {
-			printk(KERN_INFO "%s: dev_set_allmulti(master, %d)\n",
-			       vlan_dev->name, inc);
-			dev_set_allmulti(real_dev, inc); /* dev.c */
-			VLAN_DEV_INFO(vlan_dev)->old_allmulti = vlan_dev->allmulti;
-		}
+	__netpoll_free_async(netpoll);
+}
+#endif /* CONFIG_NET_POLL_CONTROLLER */
+
+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,
+};
+
+static const struct net_device_ops vlan_netdev_ops = {
+	.ndo_change_mtu		= vlan_dev_change_mtu,
+	.ndo_init		= vlan_dev_init,
+	.ndo_uninit		= vlan_dev_uninit,
+	.ndo_open		= vlan_dev_open,
+	.ndo_stop		= vlan_dev_stop,
+	.ndo_start_xmit =  vlan_dev_hard_start_xmit,
+	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_set_mac_address	= vlan_dev_set_mac_address,
+	.ndo_set_rx_mode	= vlan_dev_set_rx_mode,
+	.ndo_change_rx_flags	= vlan_dev_change_rx_flags,
+	.ndo_do_ioctl		= vlan_dev_ioctl,
+	.ndo_neigh_setup	= vlan_dev_neigh_setup,
+	.ndo_get_stats64	= vlan_dev_get_stats64,
+#if IS_ENABLED(CONFIG_FCOE)
+	.ndo_fcoe_ddp_setup	= vlan_dev_fcoe_ddp_setup,
+	.ndo_fcoe_ddp_done	= vlan_dev_fcoe_ddp_done,
+	.ndo_fcoe_enable	= vlan_dev_fcoe_enable,
+	.ndo_fcoe_disable	= vlan_dev_fcoe_disable,
+	.ndo_fcoe_get_wwn	= vlan_dev_fcoe_get_wwn,
+	.ndo_fcoe_ddp_target	= vlan_dev_fcoe_ddp_target,
+#endif
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller	= vlan_dev_poll_controller,
+	.ndo_netpoll_setup	= vlan_dev_netpoll_setup,
+	.ndo_netpoll_cleanup	= vlan_dev_netpoll_cleanup,
+#endif
+	.ndo_fix_features	= vlan_dev_fix_features,
+	.ndo_get_lock_subclass  = vlan_dev_get_lock_subclass,
+};
 
-		/* looking for addresses to add to master's list */
-		for (dmi = vlan_dev->mc_list; dmi != NULL; dmi = dmi->next) {
-			if (vlan_should_add_mc(dmi, VLAN_DEV_INFO(vlan_dev)->old_mc_list)) {
-				dev_mc_add(real_dev, dmi->dmi_addr, dmi->dmi_addrlen, 0);
-				printk(KERN_DEBUG "%s: add %.2x:%.2x:%.2x:%.2x:%.2x:%.2x mcast address to master interface\n",
-				       vlan_dev->name,
-				       dmi->dmi_addr[0],
-				       dmi->dmi_addr[1],
-				       dmi->dmi_addr[2],
-				       dmi->dmi_addr[3],
-				       dmi->dmi_addr[4],
-				       dmi->dmi_addr[5]);
-			}
-		}
+static void vlan_dev_free(struct net_device *dev)
+{
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 
-		/* looking for addresses to delete from master's list */
-		for (dmi = VLAN_DEV_INFO(vlan_dev)->old_mc_list; dmi != NULL; dmi = dmi->next) {
-			if (vlan_should_add_mc(dmi, vlan_dev->mc_list)) {
-				/* if we think we should add it to the new list, then we should really
-				 * delete it from the real list on the underlying device.
-				 */
-				dev_mc_delete(real_dev, dmi->dmi_addr, dmi->dmi_addrlen, 0);
-				printk(KERN_DEBUG "%s: del %.2x:%.2x:%.2x:%.2x:%.2x:%.2x mcast address from master interface\n",
-				       vlan_dev->name,
-				       dmi->dmi_addr[0],
-				       dmi->dmi_addr[1],
-				       dmi->dmi_addr[2],
-				       dmi->dmi_addr[3],
-				       dmi->dmi_addr[4],
-				       dmi->dmi_addr[5]);
-			}
-		}
+	free_percpu(vlan->vlan_pcpu_stats);
+	vlan->vlan_pcpu_stats = NULL;
+	free_netdev(dev);
+}
 
-		/* save multicast list */
-		vlan_copy_mc_list(vlan_dev->mc_list, VLAN_DEV_INFO(vlan_dev));
-	}
+void vlan_setup(struct net_device *dev)
+{
+	ether_setup(dev);
+
+	dev->priv_flags		|= IFF_802_1Q_VLAN;
+	dev->priv_flags		&= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING);
+	dev->tx_queue_len	= 0;
+
+	dev->netdev_ops		= &vlan_netdev_ops;
+	dev->destructor		= vlan_dev_free;
+	dev->ethtool_ops	= &vlan_ethtool_ops;
+
+	memset(dev->broadcast, 0, ETH_ALEN);
 }
diff --git a/net/8021q/vlan_gvrp.c b/net/8021q/vlan_gvrp.c
new file mode 100644
index 00000000000..66a80320b03
--- /dev/null
+++ b/net/8021q/vlan_gvrp.c
@@ -0,0 +1,70 @@
+/*
+ * 	IEEE 802.1Q GARP VLAN Registration Protocol (GVRP)
+ *
+ * 	Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	version 2 as published by the Free Software Foundation.
+ */
+#include <linux/types.h>
+#include <linux/if_vlan.h>
+#include <net/garp.h>
+#include "vlan.h"
+
+#define GARP_GVRP_ADDRESS	{ 0x01, 0x80, 0xc2, 0x00, 0x00, 0x21 }
+
+enum gvrp_attributes {
+	GVRP_ATTR_INVALID,
+	GVRP_ATTR_VID,
+	__GVRP_ATTR_MAX
+};
+#define GVRP_ATTR_MAX	(__GVRP_ATTR_MAX - 1)
+
+static struct garp_application vlan_gvrp_app __read_mostly = {
+	.proto.group_address	= GARP_GVRP_ADDRESS,
+	.maxattr		= GVRP_ATTR_MAX,
+	.type			= GARP_APPLICATION_GVRP,
+};
+
+int vlan_gvrp_request_join(const struct net_device *dev)
+{
+	const struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+	__be16 vlan_id = htons(vlan->vlan_id);
+
+	if (vlan->vlan_proto != htons(ETH_P_8021Q))
+		return 0;
+	return garp_request_join(vlan->real_dev, &vlan_gvrp_app,
+				 &vlan_id, sizeof(vlan_id), GVRP_ATTR_VID);
+}
+
+void vlan_gvrp_request_leave(const struct net_device *dev)
+{
+	const struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+	__be16 vlan_id = htons(vlan->vlan_id);
+
+	if (vlan->vlan_proto != htons(ETH_P_8021Q))
+		return;
+	garp_request_leave(vlan->real_dev, &vlan_gvrp_app,
+			   &vlan_id, sizeof(vlan_id), GVRP_ATTR_VID);
+}
+
+int vlan_gvrp_init_applicant(struct net_device *dev)
+{
+	return garp_init_applicant(dev, &vlan_gvrp_app);
+}
+
+void vlan_gvrp_uninit_applicant(struct net_device *dev)
+{
+	garp_uninit_applicant(dev, &vlan_gvrp_app);
+}
+
+int __init vlan_gvrp_init(void)
+{
+	return garp_register_application(&vlan_gvrp_app);
+}
+
+void vlan_gvrp_uninit(void)
+{
+	garp_unregister_application(&vlan_gvrp_app);
+}
diff --git a/net/8021q/vlan_mvrp.c b/net/8021q/vlan_mvrp.c
new file mode 100644
index 00000000000..e0fe091801b
--- /dev/null
+++ b/net/8021q/vlan_mvrp.c
@@ -0,0 +1,76 @@
+/*
+ *	IEEE 802.1Q Multiple VLAN Registration Protocol (MVRP)
+ *
+ *	Copyright (c) 2012 Massachusetts Institute of Technology
+ *
+ *	Adapted from code in net/8021q/vlan_gvrp.c
+ *	Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	version 2 as published by the Free Software Foundation.
+ */
+#include <linux/types.h>
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <net/mrp.h>
+#include "vlan.h"
+
+#define MRP_MVRP_ADDRESS	{ 0x01, 0x80, 0xc2, 0x00, 0x00, 0x21 }
+
+enum mvrp_attributes {
+	MVRP_ATTR_INVALID,
+	MVRP_ATTR_VID,
+	__MVRP_ATTR_MAX
+};
+#define MVRP_ATTR_MAX	(__MVRP_ATTR_MAX - 1)
+
+static struct mrp_application vlan_mrp_app __read_mostly = {
+	.type		= MRP_APPLICATION_MVRP,
+	.maxattr	= MVRP_ATTR_MAX,
+	.pkttype.type	= htons(ETH_P_MVRP),
+	.group_address	= MRP_MVRP_ADDRESS,
+	.version	= 0,
+};
+
+int vlan_mvrp_request_join(const struct net_device *dev)
+{
+	const struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+	__be16 vlan_id = htons(vlan->vlan_id);
+
+	if (vlan->vlan_proto != htons(ETH_P_8021Q))
+		return 0;
+	return mrp_request_join(vlan->real_dev, &vlan_mrp_app,
+				&vlan_id, sizeof(vlan_id), MVRP_ATTR_VID);
+}
+
+void vlan_mvrp_request_leave(const struct net_device *dev)
+{
+	const struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+	__be16 vlan_id = htons(vlan->vlan_id);
+
+	if (vlan->vlan_proto != htons(ETH_P_8021Q))
+		return;
+	mrp_request_leave(vlan->real_dev, &vlan_mrp_app,
+			  &vlan_id, sizeof(vlan_id), MVRP_ATTR_VID);
+}
+
+int vlan_mvrp_init_applicant(struct net_device *dev)
+{
+	return mrp_init_applicant(dev, &vlan_mrp_app);
+}
+
+void vlan_mvrp_uninit_applicant(struct net_device *dev)
+{
+	mrp_uninit_applicant(dev, &vlan_mrp_app);
+}
+
+int __init vlan_mvrp_init(void)
+{
+	return mrp_register_application(&vlan_mrp_app);
+}
+
+void vlan_mvrp_uninit(void)
+{
+	mrp_unregister_application(&vlan_mrp_app);
+}
diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
new file mode 100644
index 00000000000..8ac8a5cc214
--- /dev/null
+++ b/net/8021q/vlan_netlink.c
@@ -0,0 +1,265 @@
+/*
+ *	VLAN netlink control interface
+ *
+ * 	Copyright (c) 2007 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/netdevice.h>
+#include <linux/if_vlan.h>
+#include <linux/module.h>
+#include <net/net_namespace.h>
+#include <net/netlink.h>
+#include <net/rtnetlink.h>
+#include "vlan.h"
+
+
+static const struct nla_policy vlan_policy[IFLA_VLAN_MAX + 1] = {
+	[IFLA_VLAN_ID]		= { .type = NLA_U16 },
+	[IFLA_VLAN_FLAGS]	= { .len = sizeof(struct ifla_vlan_flags) },
+	[IFLA_VLAN_EGRESS_QOS]	= { .type = NLA_NESTED },
+	[IFLA_VLAN_INGRESS_QOS] = { .type = NLA_NESTED },
+	[IFLA_VLAN_PROTOCOL]	= { .type = NLA_U16 },
+};
+
+static const struct nla_policy vlan_map_policy[IFLA_VLAN_QOS_MAX + 1] = {
+	[IFLA_VLAN_QOS_MAPPING] = { .len = sizeof(struct ifla_vlan_qos_mapping) },
+};
+
+
+static inline int vlan_validate_qos_map(struct nlattr *attr)
+{
+	if (!attr)
+		return 0;
+	return nla_validate_nested(attr, IFLA_VLAN_QOS_MAX, vlan_map_policy);
+}
+
+static int vlan_validate(struct nlattr *tb[], struct nlattr *data[])
+{
+	struct ifla_vlan_flags *flags;
+	u16 id;
+	int err;
+
+	if (tb[IFLA_ADDRESS]) {
+		if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN)
+			return -EINVAL;
+		if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS])))
+			return -EADDRNOTAVAIL;
+	}
+
+	if (!data)
+		return -EINVAL;
+
+	if (data[IFLA_VLAN_PROTOCOL]) {
+		switch (nla_get_be16(data[IFLA_VLAN_PROTOCOL])) {
+		case htons(ETH_P_8021Q):
+		case htons(ETH_P_8021AD):
+			break;
+		default:
+			return -EPROTONOSUPPORT;
+		}
+	}
+
+	if (data[IFLA_VLAN_ID]) {
+		id = nla_get_u16(data[IFLA_VLAN_ID]);
+		if (id >= VLAN_VID_MASK)
+			return -ERANGE;
+	}
+	if (data[IFLA_VLAN_FLAGS]) {
+		flags = nla_data(data[IFLA_VLAN_FLAGS]);
+		if ((flags->flags & flags->mask) &
+		    ~(VLAN_FLAG_REORDER_HDR | VLAN_FLAG_GVRP |
+		      VLAN_FLAG_LOOSE_BINDING | VLAN_FLAG_MVRP))
+			return -EINVAL;
+	}
+
+	err = vlan_validate_qos_map(data[IFLA_VLAN_INGRESS_QOS]);
+	if (err < 0)
+		return err;
+	err = vlan_validate_qos_map(data[IFLA_VLAN_EGRESS_QOS]);
+	if (err < 0)
+		return err;
+	return 0;
+}
+
+static int vlan_changelink(struct net_device *dev,
+			   struct nlattr *tb[], struct nlattr *data[])
+{
+	struct ifla_vlan_flags *flags;
+	struct ifla_vlan_qos_mapping *m;
+	struct nlattr *attr;
+	int rem;
+
+	if (data[IFLA_VLAN_FLAGS]) {
+		flags = nla_data(data[IFLA_VLAN_FLAGS]);
+		vlan_dev_change_flags(dev, flags->flags, flags->mask);
+	}
+	if (data[IFLA_VLAN_INGRESS_QOS]) {
+		nla_for_each_nested(attr, data[IFLA_VLAN_INGRESS_QOS], rem) {
+			m = nla_data(attr);
+			vlan_dev_set_ingress_priority(dev, m->to, m->from);
+		}
+	}
+	if (data[IFLA_VLAN_EGRESS_QOS]) {
+		nla_for_each_nested(attr, data[IFLA_VLAN_EGRESS_QOS], rem) {
+			m = nla_data(attr);
+			vlan_dev_set_egress_priority(dev, m->from, m->to);
+		}
+	}
+	return 0;
+}
+
+static int vlan_newlink(struct net *src_net, struct net_device *dev,
+			struct nlattr *tb[], struct nlattr *data[])
+{
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+	struct net_device *real_dev;
+	__be16 proto;
+	int err;
+
+	if (!data[IFLA_VLAN_ID])
+		return -EINVAL;
+
+	if (!tb[IFLA_LINK])
+		return -EINVAL;
+	real_dev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK]));
+	if (!real_dev)
+		return -ENODEV;
+
+	if (data[IFLA_VLAN_PROTOCOL])
+		proto = nla_get_be16(data[IFLA_VLAN_PROTOCOL]);
+	else
+		proto = htons(ETH_P_8021Q);
+
+	vlan->vlan_proto = proto;
+	vlan->vlan_id	 = nla_get_u16(data[IFLA_VLAN_ID]);
+	vlan->real_dev	 = real_dev;
+	vlan->flags	 = VLAN_FLAG_REORDER_HDR;
+
+	err = vlan_check_real_dev(real_dev, vlan->vlan_proto, vlan->vlan_id);
+	if (err < 0)
+		return err;
+
+	if (!tb[IFLA_MTU])
+		dev->mtu = real_dev->mtu;
+	else if (dev->mtu > real_dev->mtu)
+		return -EINVAL;
+
+	err = vlan_changelink(dev, tb, data);
+	if (err < 0)
+		return err;
+
+	return register_vlan_dev(dev);
+}
+
+static inline size_t vlan_qos_map_size(unsigned int n)
+{
+	if (n == 0)
+		return 0;
+	/* IFLA_VLAN_{EGRESS,INGRESS}_QOS + n * IFLA_VLAN_QOS_MAPPING */
+	return nla_total_size(sizeof(struct nlattr)) +
+	       nla_total_size(sizeof(struct ifla_vlan_qos_mapping)) * n;
+}
+
+static size_t vlan_get_size(const struct net_device *dev)
+{
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+
+	return nla_total_size(2) +	/* IFLA_VLAN_PROTOCOL */
+	       nla_total_size(2) +	/* IFLA_VLAN_ID */
+	       nla_total_size(sizeof(struct ifla_vlan_flags)) + /* IFLA_VLAN_FLAGS */
+	       vlan_qos_map_size(vlan->nr_ingress_mappings) +
+	       vlan_qos_map_size(vlan->nr_egress_mappings);
+}
+
+static int vlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
+{
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+	struct vlan_priority_tci_mapping *pm;
+	struct ifla_vlan_flags f;
+	struct ifla_vlan_qos_mapping m;
+	struct nlattr *nest;
+	unsigned int i;
+
+	if (nla_put_be16(skb, IFLA_VLAN_PROTOCOL, vlan->vlan_proto) ||
+	    nla_put_u16(skb, IFLA_VLAN_ID, vlan->vlan_id))
+		goto nla_put_failure;
+	if (vlan->flags) {
+		f.flags = vlan->flags;
+		f.mask  = ~0;
+		if (nla_put(skb, IFLA_VLAN_FLAGS, sizeof(f), &f))
+			goto nla_put_failure;
+	}
+	if (vlan->nr_ingress_mappings) {
+		nest = nla_nest_start(skb, IFLA_VLAN_INGRESS_QOS);
+		if (nest == NULL)
+			goto nla_put_failure;
+
+		for (i = 0; i < ARRAY_SIZE(vlan->ingress_priority_map); i++) {
+			if (!vlan->ingress_priority_map[i])
+				continue;
+
+			m.from = i;
+			m.to   = vlan->ingress_priority_map[i];
+			if (nla_put(skb, IFLA_VLAN_QOS_MAPPING,
+				    sizeof(m), &m))
+				goto nla_put_failure;
+		}
+		nla_nest_end(skb, nest);
+	}
+
+	if (vlan->nr_egress_mappings) {
+		nest = nla_nest_start(skb, IFLA_VLAN_EGRESS_QOS);
+		if (nest == NULL)
+			goto nla_put_failure;
+
+		for (i = 0; i < ARRAY_SIZE(vlan->egress_priority_map); i++) {
+			for (pm = vlan->egress_priority_map[i]; pm;
+			     pm = pm->next) {
+				if (!pm->vlan_qos)
+					continue;
+
+				m.from = pm->priority;
+				m.to   = (pm->vlan_qos >> 13) & 0x7;
+				if (nla_put(skb, IFLA_VLAN_QOS_MAPPING,
+					    sizeof(m), &m))
+					goto nla_put_failure;
+			}
+		}
+		nla_nest_end(skb, nest);
+	}
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
+struct rtnl_link_ops vlan_link_ops __read_mostly = {
+	.kind		= "vlan",
+	.maxtype	= IFLA_VLAN_MAX,
+	.policy		= vlan_policy,
+	.priv_size	= sizeof(struct vlan_dev_priv),
+	.setup		= vlan_setup,
+	.validate	= vlan_validate,
+	.newlink	= vlan_newlink,
+	.changelink	= vlan_changelink,
+	.dellink	= unregister_vlan_dev,
+	.get_size	= vlan_get_size,
+	.fill_info	= vlan_fill_info,
+};
+
+int __init vlan_netlink_init(void)
+{
+	return rtnl_link_register(&vlan_link_ops);
+}
+
+void __exit vlan_netlink_fini(void)
+{
+	rtnl_link_unregister(&vlan_link_ops);
+}
+
+MODULE_ALIAS_RTNL_LINK("vlan");
diff --git a/net/8021q/vlanproc.c b/net/8021q/vlanproc.c
index 7b214cffc95..1d0e89213a2 100644
--- a/net/8021q/vlanproc.c
+++ b/net/8021q/vlanproc.c
@@ -17,23 +17,19 @@
  * Jan 20, 1998        Ben Greear     Initial Version
  *****************************************************************************/
 
-#include <linux/config.h>
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
-#include <linux/stddef.h>	/* offsetof(), etc. */
-#include <linux/errno.h>	/* return codes */
+#include <linux/errno.h>
 #include <linux/kernel.h>
-#include <linux/slab.h>		/* kmalloc(), kfree() */
-#include <linux/mm.h>
-#include <linux/string.h>	/* inline mem*, str* functions */
-#include <linux/init.h>		/* __initfunc et al. */
-#include <asm/byteorder.h>	/* htons(), etc. */
-#include <asm/uaccess.h>	/* copy_to_user */
-#include <asm/io.h>
+#include <linux/string.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/fs.h>
 #include <linux/netdevice.h>
 #include <linux/if_vlan.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
 #include "vlanproc.h"
 #include "vlan.h"
 
@@ -52,7 +48,7 @@ static int vlandev_seq_show(struct seq_file *seq, void *v);
 
 
 /*
- *	Names of the proc directory entries 
+ *	Names of the proc directory entries
  */
 
 static const char name_root[]	 = "vlan";
@@ -60,17 +56,17 @@ static const char name_conf[]	 = "config";
 
 /*
  *	Structures for interfacing with the /proc filesystem.
- *	VLAN creates its own directory /proc/net/vlan with the folowing
+ *	VLAN creates its own directory /proc/net/vlan with the following
  *	entries:
  *	config		device status/configuration
  *	<device>	entry for each  device
  */
 
 /*
- *	Generic /proc/net/vlan/<file> file and inode operations 
+ *	Generic /proc/net/vlan/<file> file and inode operations
  */
 
-static struct seq_operations vlan_seq_ops = {
+static const struct seq_operations vlan_seq_ops = {
 	.start = vlan_seq_start,
 	.next = vlan_seq_next,
 	.stop = vlan_seq_stop,
@@ -79,15 +75,16 @@ static struct seq_operations vlan_seq_ops = {
 
 static int vlan_seq_open(struct inode *inode, struct file *file)
 {
-	return seq_open(file, &vlan_seq_ops);
+	return seq_open_net(inode, file, &vlan_seq_ops,
+			sizeof(struct seq_net_private));
 }
 
-static struct file_operations vlan_fops = {
+static const struct file_operations vlan_fops = {
 	.owner	 = THIS_MODULE,
 	.open    = vlan_seq_open,
 	.read    = seq_read,
 	.llseek  = seq_lseek,
-	.release = seq_release,
+	.release = seq_release_net,
 };
 
 /*
@@ -96,10 +93,10 @@ static struct file_operations vlan_fops = {
 
 static int vlandev_seq_open(struct inode *inode, struct file *file)
 {
-	return single_open(file, vlandev_seq_show, PDE(inode)->data);
+	return single_open(file, vlandev_seq_show, PDE_DATA(inode));
 }
 
-static struct file_operations vlandev_fops = {
+static const struct file_operations vlandev_fops = {
 	.owner = THIS_MODULE,
 	.open    = vlandev_seq_open,
 	.read    = seq_read,
@@ -108,27 +105,15 @@ static struct file_operations vlandev_fops = {
 };
 
 /*
- * Proc filesystem derectory entries.
- */
-
-/*
- *	/proc/net/vlan 
- */
-
-static struct proc_dir_entry *proc_vlan_dir;
-
-/*
- *	/proc/net/vlan/config 
+ * Proc filesystem directory entries.
  */
 
-static struct proc_dir_entry *proc_vlan_conf;
-
 /* Strings */
-static const char *vlan_name_type_str[VLAN_NAME_TYPE_HIGHEST] = {
-    [VLAN_NAME_TYPE_RAW_PLUS_VID]       = "VLAN_NAME_TYPE_RAW_PLUS_VID",
-    [VLAN_NAME_TYPE_PLUS_VID_NO_PAD]	= "VLAN_NAME_TYPE_PLUS_VID_NO_PAD",
-    [VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD]= "VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD",
-    [VLAN_NAME_TYPE_PLUS_VID]		= "VLAN_NAME_TYPE_PLUS_VID",
+static const char *const vlan_name_type_str[VLAN_NAME_TYPE_HIGHEST] = {
+    [VLAN_NAME_TYPE_RAW_PLUS_VID]        = "VLAN_NAME_TYPE_RAW_PLUS_VID",
+    [VLAN_NAME_TYPE_PLUS_VID_NO_PAD]	 = "VLAN_NAME_TYPE_PLUS_VID_NO_PAD",
+    [VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD] = "VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD",
+    [VLAN_NAME_TYPE_PLUS_VID]		 = "VLAN_NAME_TYPE_PLUS_VID",
 };
 /*
  *	Interface functions
@@ -138,13 +123,15 @@ static const char *vlan_name_type_str[VLAN_NAME_TYPE_HIGHEST] = {
  *	Clean up /proc/net/vlan entries
  */
 
-void vlan_proc_cleanup(void)
+void vlan_proc_cleanup(struct net *net)
 {
-	if (proc_vlan_conf)
-		remove_proc_entry(name_conf, proc_vlan_dir);
+	struct vlan_net *vn = net_generic(net, vlan_net_id);
 
-	if (proc_vlan_dir)
-		proc_net_remove(name_root);
+	if (vn->proc_vlan_conf)
+		remove_proc_entry(name_conf, vn->proc_vlan_dir);
+
+	if (vn->proc_vlan_dir)
+		remove_proc_entry(name_root, net->proc_net);
 
 	/* Dynamically added entries should be cleaned up as their vlan_device
 	 * is removed, so we should not have to take care of it here...
@@ -155,19 +142,23 @@ void vlan_proc_cleanup(void)
  *	Create /proc/net/vlan entries
  */
 
-int __init vlan_proc_init(void)
+int __net_init vlan_proc_init(struct net *net)
 {
-	proc_vlan_dir = proc_mkdir(name_root, proc_net);
-	if (proc_vlan_dir) {
-		proc_vlan_conf = create_proc_entry(name_conf,
-						   S_IFREG|S_IRUSR|S_IWUSR,
-						   proc_vlan_dir);
-		if (proc_vlan_conf) {
-			proc_vlan_conf->proc_fops = &vlan_fops;
-			return 0;
-		}
-	}
-	vlan_proc_cleanup();
+	struct vlan_net *vn = net_generic(net, vlan_net_id);
+
+	vn->proc_vlan_dir = proc_net_mkdir(net, name_root, net->proc_net);
+	if (!vn->proc_vlan_dir)
+		goto err;
+
+	vn->proc_vlan_conf = proc_create(name_conf, S_IFREG|S_IRUSR|S_IWUSR,
+				     vn->proc_vlan_dir, &vlan_fops);
+	if (!vn->proc_vlan_conf)
+		goto err;
+	return 0;
+
+err:
+	pr_err("can't create entry in proc filesystem!\n");
+	vlan_proc_cleanup(net);
 	return -ENOBUFS;
 }
 
@@ -175,30 +166,16 @@ int __init vlan_proc_init(void)
  *	Add directory entry for VLAN device.
  */
 
-int vlan_proc_add_dev (struct net_device *vlandev)
+int vlan_proc_add_dev(struct net_device *vlandev)
 {
-	struct vlan_dev_info *dev_info = VLAN_DEV_INFO(vlandev);
-
-	if (!(vlandev->priv_flags & IFF_802_1Q_VLAN)) {
-		printk(KERN_ERR
-		       "ERROR:	vlan_proc_add, device -:%s:- is NOT a VLAN\n",
-		       vlandev->name);
-		return -EINVAL;
-	}
+	struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev);
+	struct vlan_net *vn = net_generic(dev_net(vlandev), vlan_net_id);
 
-	dev_info->dent = create_proc_entry(vlandev->name,
-					   S_IFREG|S_IRUSR|S_IWUSR,
-					   proc_vlan_dir);
-	if (!dev_info->dent)
+	vlan->dent =
+		proc_create_data(vlandev->name, S_IFREG|S_IRUSR|S_IWUSR,
+				 vn->proc_vlan_dir, &vlandev_fops, vlandev);
+	if (!vlan->dent)
 		return -ENOBUFS;
-
-	dev_info->dent->proc_fops = &vlandev_fops;
-	dev_info->dent->data = vlandev;
-
-#ifdef VLAN_DEBUG
-	printk(KERN_ERR "vlan_proc_add, device -:%s:- being added.\n",
-	       vlandev->name);
-#endif
 	return 0;
 }
 
@@ -207,28 +184,9 @@ int vlan_proc_add_dev (struct net_device *vlandev)
  */
 int vlan_proc_rem_dev(struct net_device *vlandev)
 {
-	if (!vlandev) {
-		printk(VLAN_ERR "%s: invalid argument: %p\n",
-			__FUNCTION__, vlandev);
-		return -EINVAL;
-	}
-
-	if (!(vlandev->priv_flags & IFF_802_1Q_VLAN)) {
-		printk(VLAN_DBG "%s: invalid argument, device: %s is not a VLAN device, priv_flags: 0x%4hX.\n",
-			__FUNCTION__, vlandev->name, vlandev->priv_flags);
-		return -EINVAL;
-	}
-
-#ifdef VLAN_DEBUG
-	printk(VLAN_DBG "%s: dev: %p\n", __FUNCTION__, vlandev);
-#endif
-
 	/** NOTE:  This will consume the memory pointed to by dent, it seems. */
-	if (VLAN_DEV_INFO(vlandev)->dent) {
-		remove_proc_entry(VLAN_DEV_INFO(vlandev)->dent->name, proc_vlan_dir);
-		VLAN_DEV_INFO(vlandev)->dent = NULL;
-	}
-
+	proc_remove(vlan_dev_priv(vlandev)->dent);
+	vlan_dev_priv(vlandev)->dent = NULL;
 	return 0;
 }
 
@@ -238,64 +196,77 @@ int vlan_proc_rem_dev(struct net_device *vlandev)
  * The following few functions build the content of /proc/net/vlan/config
  */
 
-/* starting at dev, find a VLAN device */
-static struct net_device *vlan_skip(struct net_device *dev) 
-{
-	while (dev && !(dev->priv_flags & IFF_802_1Q_VLAN)) 
-		dev = dev->next;
-
-	return dev;
-}
-
-/* start read of /proc/net/vlan/config */ 
+/* start read of /proc/net/vlan/config */
 static void *vlan_seq_start(struct seq_file *seq, loff_t *pos)
+	__acquires(rcu)
 {
 	struct net_device *dev;
+	struct net *net = seq_file_net(seq);
 	loff_t i = 1;
 
-	read_lock(&dev_base_lock);
-
+	rcu_read_lock();
 	if (*pos == 0)
 		return SEQ_START_TOKEN;
-	
-	for (dev = vlan_skip(dev_base); dev && i < *pos; 
-	     dev = vlan_skip(dev->next), ++i);
-		
-	return  (i == *pos) ? dev : NULL;
-} 
+
+	for_each_netdev_rcu(net, dev) {
+		if (!is_vlan_dev(dev))
+			continue;
+
+		if (i++ == *pos)
+			return dev;
+	}
+
+	return  NULL;
+}
 
 static void *vlan_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
+	struct net_device *dev;
+	struct net *net = seq_file_net(seq);
+
 	++*pos;
 
-	return vlan_skip((v == SEQ_START_TOKEN)  
-			    ? dev_base 
-			    : ((struct net_device *)v)->next);
+	dev = v;
+	if (v == SEQ_START_TOKEN)
+		dev = net_device_entry(&net->dev_base_head);
+
+	for_each_netdev_continue_rcu(net, dev) {
+		if (!is_vlan_dev(dev))
+			continue;
+
+		return dev;
+	}
+
+	return NULL;
 }
 
 static void vlan_seq_stop(struct seq_file *seq, void *v)
+	__releases(rcu)
 {
-	read_unlock(&dev_base_lock);
+	rcu_read_unlock();
 }
 
 static int vlan_seq_show(struct seq_file *seq, void *v)
 {
+	struct net *net = seq_file_net(seq);
+	struct vlan_net *vn = net_generic(net, vlan_net_id);
+
 	if (v == SEQ_START_TOKEN) {
 		const char *nmtype = NULL;
 
 		seq_puts(seq, "VLAN Dev name	 | VLAN ID\n");
 
-		if (vlan_name_type < ARRAY_SIZE(vlan_name_type_str))
-		    nmtype =  vlan_name_type_str[vlan_name_type];
+		if (vn->name_type < ARRAY_SIZE(vlan_name_type_str))
+		    nmtype =  vlan_name_type_str[vn->name_type];
 
-		seq_printf(seq, "Name-Type: %s\n", 
-			   nmtype ? nmtype :  "UNKNOWN" );
+		seq_printf(seq, "Name-Type: %s\n",
+			   nmtype ? nmtype :  "UNKNOWN");
 	} else {
 		const struct net_device *vlandev = v;
-		const struct vlan_dev_info *dev_info = VLAN_DEV_INFO(vlandev);
+		const struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev);
 
-		seq_printf(seq, "%-15s| %d  | %s\n",  vlandev->name,  
-			   dev_info->vlan_id,    dev_info->real_dev->name);
+		seq_printf(seq, "%-15s| %d  | %s\n",  vlandev->name,
+			   vlan->vlan_id,    vlan->real_dev->name);
 	}
 	return 0;
 }
@@ -303,50 +274,46 @@ static int vlan_seq_show(struct seq_file *seq, void *v)
 static int vlandev_seq_show(struct seq_file *seq, void *offset)
 {
 	struct net_device *vlandev = (struct net_device *) seq->private;
-	const struct vlan_dev_info *dev_info = VLAN_DEV_INFO(vlandev);
-	struct net_device_stats *stats;
-	static const char fmt[] = "%30s %12lu\n";
+	const struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev);
+	struct rtnl_link_stats64 temp;
+	const struct rtnl_link_stats64 *stats;
+	static const char fmt64[] = "%30s %12llu\n";
 	int i;
 
-	if ((vlandev == NULL) || (!(vlandev->priv_flags & IFF_802_1Q_VLAN)))
+	if (!is_vlan_dev(vlandev))
 		return 0;
 
-	seq_printf(seq, "%s  VID: %d	 REORDER_HDR: %i  dev->priv_flags: %hx\n",
-		       vlandev->name, dev_info->vlan_id,
-		       (int)(dev_info->flags & 1), vlandev->priv_flags);
-
-
-	stats = vlan_dev_get_stats(vlandev);
+	stats = dev_get_stats(vlandev, &temp);
+	seq_printf(seq,
+		   "%s  VID: %d	 REORDER_HDR: %i  dev->priv_flags: %hx\n",
+		   vlandev->name, vlan->vlan_id,
+		   (int)(vlan->flags & 1), vlandev->priv_flags);
 
-	seq_printf(seq, fmt, "total frames received", stats->rx_packets);
-	seq_printf(seq, fmt, "total bytes received", stats->rx_bytes);
-	seq_printf(seq, fmt, "Broadcast/Multicast Rcvd", stats->multicast);
+	seq_printf(seq, fmt64, "total frames received", stats->rx_packets);
+	seq_printf(seq, fmt64, "total bytes received", stats->rx_bytes);
+	seq_printf(seq, fmt64, "Broadcast/Multicast Rcvd", stats->multicast);
 	seq_puts(seq, "\n");
-	seq_printf(seq, fmt, "total frames transmitted", stats->tx_packets);
-	seq_printf(seq, fmt, "total bytes transmitted", stats->tx_bytes);
-	seq_printf(seq, fmt, "total headroom inc", 
-		   dev_info->cnt_inc_headroom_on_tx);
-	seq_printf(seq, fmt, "total encap on xmit", 
-		   dev_info->cnt_encap_on_xmit);
-	seq_printf(seq, "Device: %s", dev_info->real_dev->name);
+	seq_printf(seq, fmt64, "total frames transmitted", stats->tx_packets);
+	seq_printf(seq, fmt64, "total bytes transmitted", stats->tx_bytes);
+	seq_printf(seq, "Device: %s", vlan->real_dev->name);
 	/* now show all PRIORITY mappings relating to this VLAN */
-	seq_printf(seq, 
-		       "\nINGRESS priority mappings: 0:%lu  1:%lu  2:%lu  3:%lu  4:%lu  5:%lu  6:%lu 7:%lu\n",
-		       dev_info->ingress_priority_map[0],
-		       dev_info->ingress_priority_map[1],
-		       dev_info->ingress_priority_map[2],
-		       dev_info->ingress_priority_map[3],
-		       dev_info->ingress_priority_map[4],
-		       dev_info->ingress_priority_map[5],
-		       dev_info->ingress_priority_map[6],
-		       dev_info->ingress_priority_map[7]);
-
-	seq_printf(seq, "EGRESSS priority Mappings: ");
+	seq_printf(seq, "\nINGRESS priority mappings: "
+			"0:%u  1:%u  2:%u  3:%u  4:%u  5:%u  6:%u 7:%u\n",
+		   vlan->ingress_priority_map[0],
+		   vlan->ingress_priority_map[1],
+		   vlan->ingress_priority_map[2],
+		   vlan->ingress_priority_map[3],
+		   vlan->ingress_priority_map[4],
+		   vlan->ingress_priority_map[5],
+		   vlan->ingress_priority_map[6],
+		   vlan->ingress_priority_map[7]);
+
+	seq_printf(seq, " EGRESS priority mappings: ");
 	for (i = 0; i < 16; i++) {
 		const struct vlan_priority_tci_mapping *mp
-			= dev_info->egress_priority_map[i];
+			= vlan->egress_priority_map[i];
 		while (mp) {
-			seq_printf(seq, "%lu:%hu ",
+			seq_printf(seq, "%u:%hu ",
 				   mp->priority, ((mp->vlan_qos >> 13) & 0x7));
 			mp = mp->next;
 		}
diff --git a/net/8021q/vlanproc.h b/net/8021q/vlanproc.h
index f908ee332fd..063f60a3d5c 100644
--- a/net/8021q/vlanproc.h
+++ b/net/8021q/vlanproc.h
@@ -2,18 +2,19 @@
 #define __BEN_VLAN_PROC_INC__
 
 #ifdef CONFIG_PROC_FS
-int vlan_proc_init(void);
+struct net;
+
+int vlan_proc_init(struct net *net);
 int vlan_proc_rem_dev(struct net_device *vlandev);
-int vlan_proc_add_dev (struct net_device *vlandev);
-void vlan_proc_cleanup (void);
+int vlan_proc_add_dev(struct net_device *vlandev);
+void vlan_proc_cleanup(struct net *net);
 
 #else /* No CONFIG_PROC_FS */
 
-#define vlan_proc_init()	(0)
-#define vlan_proc_cleanup()	do {} while(0)
-#define vlan_proc_add_dev(dev)	({(void)(dev), 0;})
-#define vlan_proc_rem_dev(dev)	({(void)(dev), 0;})
-
+#define vlan_proc_init(net)	(0)
+#define vlan_proc_cleanup(net)	do {} while (0)
+#define vlan_proc_add_dev(dev)	({(void)(dev), 0; })
+#define vlan_proc_rem_dev(dev)	({(void)(dev), 0; })
 #endif
 
 #endif /* !(__BEN_VLAN_PROC_INC__) */
diff --git a/net/9p/Kconfig b/net/9p/Kconfig
new file mode 100644
index 00000000000..a75174a3372
--- /dev/null
+++ b/net/9p/Kconfig
@@ -0,0 +1,36 @@
+#
+# 9P protocol configuration
+#
+
+menuconfig NET_9P
+	depends on NET
+	tristate "Plan 9 Resource Sharing Support (9P2000)"
+	help
+	  If you say Y here, you will get experimental support for
+	  Plan 9 resource sharing via the 9P2000 protocol.
+
+	  See <http://v9fs.sf.net> for more information.
+
+	  If unsure, say N.
+
+if NET_9P
+
+config NET_9P_VIRTIO
+	depends on VIRTIO
+	tristate "9P Virtio Transport"
+	help
+	  This builds support for a transports between
+	  guest partitions and a host partition.
+
+config NET_9P_RDMA
+	depends on INET && INFINIBAND && INFINIBAND_ADDR_TRANS
+	tristate "9P RDMA Transport (Experimental)"
+	help
+	  This builds support for an RDMA transport.
+
+config NET_9P_DEBUG
+	bool "Debug information"
+	help
+	  Say Y if you want the 9P subsystem to log debug information.
+
+endif
diff --git a/net/9p/Makefile b/net/9p/Makefile
new file mode 100644
index 00000000000..a0874cc1f71
--- /dev/null
+++ b/net/9p/Makefile
@@ -0,0 +1,18 @@
+obj-$(CONFIG_NET_9P) := 9pnet.o
+obj-$(CONFIG_NET_9P_VIRTIO) += 9pnet_virtio.o
+obj-$(CONFIG_NET_9P_RDMA) += 9pnet_rdma.o
+
+9pnet-objs := \
+	mod.o \
+	client.o \
+	error.o \
+	util.o \
+	protocol.o \
+	trans_fd.o \
+	trans_common.o \
+
+9pnet_virtio-objs := \
+	trans_virtio.o \
+
+9pnet_rdma-objs := \
+	trans_rdma.o \
diff --git a/net/9p/client.c b/net/9p/client.c
new file mode 100644
index 00000000000..0004cbaac4a
--- /dev/null
+++ b/net/9p/client.c
@@ -0,0 +1,2278 @@
+/*
+ * net/9p/clnt.c
+ *
+ * 9P Client
+ *
+ *  Copyright (C) 2008 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2007 by Latchesar Ionkov <lucho@ionkov.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.
+ *
+ *  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:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/poll.h>
+#include <linux/idr.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/uaccess.h>
+#include <net/9p/9p.h>
+#include <linux/parser.h>
+#include <net/9p/client.h>
+#include <net/9p/transport.h>
+#include "protocol.h"
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/9p.h>
+
+/*
+  * Client Option Parsing (code inspired by NFS code)
+  *  - a little lazy - parse all client options
+  */
+
+enum {
+	Opt_msize,
+	Opt_trans,
+	Opt_legacy,
+	Opt_version,
+	Opt_err,
+};
+
+static const match_table_t tokens = {
+	{Opt_msize, "msize=%u"},
+	{Opt_legacy, "noextend"},
+	{Opt_trans, "trans=%s"},
+	{Opt_version, "version=%s"},
+	{Opt_err, NULL},
+};
+
+inline int p9_is_proto_dotl(struct p9_client *clnt)
+{
+	return clnt->proto_version == p9_proto_2000L;
+}
+EXPORT_SYMBOL(p9_is_proto_dotl);
+
+inline int p9_is_proto_dotu(struct p9_client *clnt)
+{
+	return clnt->proto_version == p9_proto_2000u;
+}
+EXPORT_SYMBOL(p9_is_proto_dotu);
+
+/*
+ * Some error codes are taken directly from the server replies,
+ * make sure they are valid.
+ */
+static int safe_errno(int err)
+{
+	if ((err > 0) || (err < -MAX_ERRNO)) {
+		p9_debug(P9_DEBUG_ERROR, "Invalid error code %d\n", err);
+		return -EPROTO;
+	}
+	return err;
+}
+
+
+/* Interpret mount option for protocol version */
+static int get_protocol_version(char *s)
+{
+	int version = -EINVAL;
+
+	if (!strcmp(s, "9p2000")) {
+		version = p9_proto_legacy;
+		p9_debug(P9_DEBUG_9P, "Protocol version: Legacy\n");
+	} else if (!strcmp(s, "9p2000.u")) {
+		version = p9_proto_2000u;
+		p9_debug(P9_DEBUG_9P, "Protocol version: 9P2000.u\n");
+	} else if (!strcmp(s, "9p2000.L")) {
+		version = p9_proto_2000L;
+		p9_debug(P9_DEBUG_9P, "Protocol version: 9P2000.L\n");
+	} else
+		pr_info("Unknown protocol version %s\n", s);
+
+	return version;
+}
+
+/**
+ * parse_options - parse mount options into client structure
+ * @opts: options string passed from mount
+ * @clnt: existing v9fs client information
+ *
+ * Return 0 upon success, -ERRNO upon failure
+ */
+
+static int parse_opts(char *opts, struct p9_client *clnt)
+{
+	char *options, *tmp_options;
+	char *p;
+	substring_t args[MAX_OPT_ARGS];
+	int option;
+	char *s;
+	int ret = 0;
+
+	clnt->proto_version = p9_proto_2000L;
+	clnt->msize = 8192;
+
+	if (!opts)
+		return 0;
+
+	tmp_options = kstrdup(opts, GFP_KERNEL);
+	if (!tmp_options) {
+		p9_debug(P9_DEBUG_ERROR,
+			 "failed to allocate copy of option string\n");
+		return -ENOMEM;
+	}
+	options = tmp_options;
+
+	while ((p = strsep(&options, ",")) != NULL) {
+		int token, r;
+		if (!*p)
+			continue;
+		token = match_token(p, tokens, args);
+		switch (token) {
+		case Opt_msize:
+			r = match_int(&args[0], &option);
+			if (r < 0) {
+				p9_debug(P9_DEBUG_ERROR,
+					 "integer field, but no integer?\n");
+				ret = r;
+				continue;
+			}
+			clnt->msize = option;
+			break;
+		case Opt_trans:
+			s = match_strdup(&args[0]);
+			if (!s) {
+				ret = -ENOMEM;
+				p9_debug(P9_DEBUG_ERROR,
+					 "problem allocating copy of trans arg\n");
+				goto free_and_return;
+			 }
+			clnt->trans_mod = v9fs_get_trans_by_name(s);
+			if (clnt->trans_mod == NULL) {
+				pr_info("Could not find request transport: %s\n",
+					s);
+				ret = -EINVAL;
+				kfree(s);
+				goto free_and_return;
+			}
+			kfree(s);
+			break;
+		case Opt_legacy:
+			clnt->proto_version = p9_proto_legacy;
+			break;
+		case Opt_version:
+			s = match_strdup(&args[0]);
+			if (!s) {
+				ret = -ENOMEM;
+				p9_debug(P9_DEBUG_ERROR,
+					 "problem allocating copy of version arg\n");
+				goto free_and_return;
+			}
+			ret = get_protocol_version(s);
+			if (ret == -EINVAL) {
+				kfree(s);
+				goto free_and_return;
+			}
+			kfree(s);
+			clnt->proto_version = ret;
+			break;
+		default:
+			continue;
+		}
+	}
+
+free_and_return:
+	kfree(tmp_options);
+	return ret;
+}
+
+static struct p9_fcall *p9_fcall_alloc(int alloc_msize)
+{
+	struct p9_fcall *fc;
+	fc = kmalloc(sizeof(struct p9_fcall) + alloc_msize, GFP_NOFS);
+	if (!fc)
+		return NULL;
+	fc->capacity = alloc_msize;
+	fc->sdata = (char *) fc + sizeof(struct p9_fcall);
+	return fc;
+}
+
+/**
+ * p9_tag_alloc - lookup/allocate a request by tag
+ * @c: client session to lookup tag within
+ * @tag: numeric id for transaction
+ *
+ * this is a simple array lookup, but will grow the
+ * request_slots as necessary to accommodate transaction
+ * ids which did not previously have a slot.
+ *
+ * this code relies on the client spinlock to manage locks, its
+ * possible we should switch to something else, but I'd rather
+ * stick with something low-overhead for the common case.
+ *
+ */
+
+static struct p9_req_t *
+p9_tag_alloc(struct p9_client *c, u16 tag, unsigned int max_size)
+{
+	unsigned long flags;
+	int row, col;
+	struct p9_req_t *req;
+	int alloc_msize = min(c->msize, max_size);
+
+	/* This looks up the original request by tag so we know which
+	 * buffer to read the data into */
+	tag++;
+
+	if (tag >= c->max_tag) {
+		spin_lock_irqsave(&c->lock, flags);
+		/* check again since original check was outside of lock */
+		while (tag >= c->max_tag) {
+			row = (tag / P9_ROW_MAXTAG);
+			c->reqs[row] = kcalloc(P9_ROW_MAXTAG,
+					sizeof(struct p9_req_t), GFP_ATOMIC);
+
+			if (!c->reqs[row]) {
+				pr_err("Couldn't grow tag array\n");
+				spin_unlock_irqrestore(&c->lock, flags);
+				return ERR_PTR(-ENOMEM);
+			}
+			for (col = 0; col < P9_ROW_MAXTAG; col++) {
+				c->reqs[row][col].status = REQ_STATUS_IDLE;
+				c->reqs[row][col].tc = NULL;
+			}
+			c->max_tag += P9_ROW_MAXTAG;
+		}
+		spin_unlock_irqrestore(&c->lock, flags);
+	}
+	row = tag / P9_ROW_MAXTAG;
+	col = tag % P9_ROW_MAXTAG;
+
+	req = &c->reqs[row][col];
+	if (!req->wq) {
+		req->wq = kmalloc(sizeof(wait_queue_head_t), GFP_NOFS);
+		if (!req->wq)
+			goto grow_failed;
+		init_waitqueue_head(req->wq);
+	}
+
+	if (!req->tc)
+		req->tc = p9_fcall_alloc(alloc_msize);
+	if (!req->rc)
+		req->rc = p9_fcall_alloc(alloc_msize);
+	if (!req->tc || !req->rc)
+		goto grow_failed;
+
+	p9pdu_reset(req->tc);
+	p9pdu_reset(req->rc);
+
+	req->tc->tag = tag-1;
+	req->status = REQ_STATUS_ALLOC;
+
+	return req;
+
+grow_failed:
+	pr_err("Couldn't grow tag array\n");
+	kfree(req->tc);
+	kfree(req->rc);
+	kfree(req->wq);
+	req->tc = req->rc = NULL;
+	req->wq = NULL;
+	return ERR_PTR(-ENOMEM);
+}
+
+/**
+ * p9_tag_lookup - lookup a request by tag
+ * @c: client session to lookup tag within
+ * @tag: numeric id for transaction
+ *
+ */
+
+struct p9_req_t *p9_tag_lookup(struct p9_client *c, u16 tag)
+{
+	int row, col;
+
+	/* This looks up the original request by tag so we know which
+	 * buffer to read the data into */
+	tag++;
+
+	if(tag >= c->max_tag) 
+		return NULL;
+
+	row = tag / P9_ROW_MAXTAG;
+	col = tag % P9_ROW_MAXTAG;
+
+	return &c->reqs[row][col];
+}
+EXPORT_SYMBOL(p9_tag_lookup);
+
+/**
+ * p9_tag_init - setup tags structure and contents
+ * @c:  v9fs client struct
+ *
+ * This initializes the tags structure for each client instance.
+ *
+ */
+
+static int p9_tag_init(struct p9_client *c)
+{
+	int err = 0;
+
+	c->tagpool = p9_idpool_create();
+	if (IS_ERR(c->tagpool)) {
+		err = PTR_ERR(c->tagpool);
+		goto error;
+	}
+	err = p9_idpool_get(c->tagpool); /* reserve tag 0 */
+	if (err < 0) {
+		p9_idpool_destroy(c->tagpool);
+		goto error;
+	}
+	c->max_tag = 0;
+error:
+	return err;
+}
+
+/**
+ * p9_tag_cleanup - cleans up tags structure and reclaims resources
+ * @c:  v9fs client struct
+ *
+ * This frees resources associated with the tags structure
+ *
+ */
+static void p9_tag_cleanup(struct p9_client *c)
+{
+	int row, col;
+
+	/* check to insure all requests are idle */
+	for (row = 0; row < (c->max_tag/P9_ROW_MAXTAG); row++) {
+		for (col = 0; col < P9_ROW_MAXTAG; col++) {
+			if (c->reqs[row][col].status != REQ_STATUS_IDLE) {
+				p9_debug(P9_DEBUG_MUX,
+					 "Attempting to cleanup non-free tag %d,%d\n",
+					 row, col);
+				/* TODO: delay execution of cleanup */
+				return;
+			}
+		}
+	}
+
+	if (c->tagpool) {
+		p9_idpool_put(0, c->tagpool); /* free reserved tag 0 */
+		p9_idpool_destroy(c->tagpool);
+	}
+
+	/* free requests associated with tags */
+	for (row = 0; row < (c->max_tag/P9_ROW_MAXTAG); row++) {
+		for (col = 0; col < P9_ROW_MAXTAG; col++) {
+			kfree(c->reqs[row][col].wq);
+			kfree(c->reqs[row][col].tc);
+			kfree(c->reqs[row][col].rc);
+		}
+		kfree(c->reqs[row]);
+	}
+	c->max_tag = 0;
+}
+
+/**
+ * p9_free_req - free a request and clean-up as necessary
+ * c: client state
+ * r: request to release
+ *
+ */
+
+static void p9_free_req(struct p9_client *c, struct p9_req_t *r)
+{
+	int tag = r->tc->tag;
+	p9_debug(P9_DEBUG_MUX, "clnt %p req %p tag: %d\n", c, r, tag);
+
+	r->status = REQ_STATUS_IDLE;
+	if (tag != P9_NOTAG && p9_idpool_check(tag, c->tagpool))
+		p9_idpool_put(tag, c->tagpool);
+}
+
+/**
+ * p9_client_cb - call back from transport to client
+ * c: client state
+ * req: request received
+ *
+ */
+void p9_client_cb(struct p9_client *c, struct p9_req_t *req, int status)
+{
+	p9_debug(P9_DEBUG_MUX, " tag %d\n", req->tc->tag);
+
+	/*
+	 * This barrier is needed to make sure any change made to req before
+	 * the other thread wakes up will indeed be seen by the waiting side.
+	 */
+	smp_wmb();
+	req->status = status;
+
+	wake_up(req->wq);
+	p9_debug(P9_DEBUG_MUX, "wakeup: %d\n", req->tc->tag);
+}
+EXPORT_SYMBOL(p9_client_cb);
+
+/**
+ * p9_parse_header - parse header arguments out of a packet
+ * @pdu: packet to parse
+ * @size: size of packet
+ * @type: type of request
+ * @tag: tag of packet
+ * @rewind: set if we need to rewind offset afterwards
+ */
+
+int
+p9_parse_header(struct p9_fcall *pdu, int32_t *size, int8_t *type, int16_t *tag,
+								int rewind)
+{
+	int8_t r_type;
+	int16_t r_tag;
+	int32_t r_size;
+	int offset = pdu->offset;
+	int err;
+
+	pdu->offset = 0;
+	if (pdu->size == 0)
+		pdu->size = 7;
+
+	err = p9pdu_readf(pdu, 0, "dbw", &r_size, &r_type, &r_tag);
+	if (err)
+		goto rewind_and_exit;
+
+	pdu->size = r_size;
+	pdu->id = r_type;
+	pdu->tag = r_tag;
+
+	p9_debug(P9_DEBUG_9P, "<<< size=%d type: %d tag: %d\n",
+		 pdu->size, pdu->id, pdu->tag);
+
+	if (type)
+		*type = r_type;
+	if (tag)
+		*tag = r_tag;
+	if (size)
+		*size = r_size;
+
+
+rewind_and_exit:
+	if (rewind)
+		pdu->offset = offset;
+	return err;
+}
+EXPORT_SYMBOL(p9_parse_header);
+
+/**
+ * p9_check_errors - check 9p packet for error return and process it
+ * @c: current client instance
+ * @req: request to parse and check for error conditions
+ *
+ * returns error code if one is discovered, otherwise returns 0
+ *
+ * this will have to be more complicated if we have multiple
+ * error packet types
+ */
+
+static int p9_check_errors(struct p9_client *c, struct p9_req_t *req)
+{
+	int8_t type;
+	int err;
+	int ecode;
+
+	err = p9_parse_header(req->rc, NULL, &type, NULL, 0);
+	/*
+	 * dump the response from server
+	 * This should be after check errors which poplulate pdu_fcall.
+	 */
+	trace_9p_protocol_dump(c, req->rc);
+	if (err) {
+		p9_debug(P9_DEBUG_ERROR, "couldn't parse header %d\n", err);
+		return err;
+	}
+	if (type != P9_RERROR && type != P9_RLERROR)
+		return 0;
+
+	if (!p9_is_proto_dotl(c)) {
+		char *ename;
+		err = p9pdu_readf(req->rc, c->proto_version, "s?d",
+				  &ename, &ecode);
+		if (err)
+			goto out_err;
+
+		if (p9_is_proto_dotu(c))
+			err = -ecode;
+
+		if (!err || !IS_ERR_VALUE(err)) {
+			err = p9_errstr2errno(ename, strlen(ename));
+
+			p9_debug(P9_DEBUG_9P, "<<< RERROR (%d) %s\n",
+				 -ecode, ename);
+		}
+		kfree(ename);
+	} else {
+		err = p9pdu_readf(req->rc, c->proto_version, "d", &ecode);
+		err = -ecode;
+
+		p9_debug(P9_DEBUG_9P, "<<< RLERROR (%d)\n", -ecode);
+	}
+
+	return err;
+
+out_err:
+	p9_debug(P9_DEBUG_ERROR, "couldn't parse error%d\n", err);
+
+	return err;
+}
+
+/**
+ * p9_check_zc_errors - check 9p packet for error return and process it
+ * @c: current client instance
+ * @req: request to parse and check for error conditions
+ * @in_hdrlen: Size of response protocol buffer.
+ *
+ * returns error code if one is discovered, otherwise returns 0
+ *
+ * this will have to be more complicated if we have multiple
+ * error packet types
+ */
+
+static int p9_check_zc_errors(struct p9_client *c, struct p9_req_t *req,
+			      char *uidata, int in_hdrlen, int kern_buf)
+{
+	int err;
+	int ecode;
+	int8_t type;
+	char *ename = NULL;
+
+	err = p9_parse_header(req->rc, NULL, &type, NULL, 0);
+	/*
+	 * dump the response from server
+	 * This should be after parse_header which poplulate pdu_fcall.
+	 */
+	trace_9p_protocol_dump(c, req->rc);
+	if (err) {
+		p9_debug(P9_DEBUG_ERROR, "couldn't parse header %d\n", err);
+		return err;
+	}
+
+	if (type != P9_RERROR && type != P9_RLERROR)
+		return 0;
+
+	if (!p9_is_proto_dotl(c)) {
+		/* Error is reported in string format */
+		int len;
+		/* 7 = header size for RERROR; */
+		int inline_len = in_hdrlen - 7;
+
+		len =  req->rc->size - req->rc->offset;
+		if (len > (P9_ZC_HDR_SZ - 7)) {
+			err = -EFAULT;
+			goto out_err;
+		}
+
+		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;
+				}
+			}
+		}
+		ename = NULL;
+		err = p9pdu_readf(req->rc, c->proto_version, "s?d",
+				  &ename, &ecode);
+		if (err)
+			goto out_err;
+
+		if (p9_is_proto_dotu(c))
+			err = -ecode;
+
+		if (!err || !IS_ERR_VALUE(err)) {
+			err = p9_errstr2errno(ename, strlen(ename));
+
+			p9_debug(P9_DEBUG_9P, "<<< RERROR (%d) %s\n",
+				 -ecode, ename);
+		}
+		kfree(ename);
+	} else {
+		err = p9pdu_readf(req->rc, c->proto_version, "d", &ecode);
+		err = -ecode;
+
+		p9_debug(P9_DEBUG_9P, "<<< RLERROR (%d)\n", -ecode);
+	}
+	return err;
+
+out_err:
+	p9_debug(P9_DEBUG_ERROR, "couldn't parse error%d\n", err);
+	return err;
+}
+
+static struct p9_req_t *
+p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...);
+
+/**
+ * p9_client_flush - flush (cancel) a request
+ * @c: client state
+ * @oldreq: request to cancel
+ *
+ * This sents a flush for a particular request and links
+ * the flush request to the original request.  The current
+ * code only supports a single flush request although the protocol
+ * allows for multiple flush requests to be sent for a single request.
+ *
+ */
+
+static int p9_client_flush(struct p9_client *c, struct p9_req_t *oldreq)
+{
+	struct p9_req_t *req;
+	int16_t oldtag;
+	int err;
+
+	err = p9_parse_header(oldreq->tc, NULL, NULL, &oldtag, 1);
+	if (err)
+		return err;
+
+	p9_debug(P9_DEBUG_9P, ">>> TFLUSH tag %d\n", oldtag);
+
+	req = p9_client_rpc(c, P9_TFLUSH, "w", oldtag);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	/*
+	 * if we haven't received a response for oldreq,
+	 * remove it from the list
+	 */
+	if (oldreq->status == REQ_STATUS_SENT)
+		if (c->trans_mod->cancelled)
+			c->trans_mod->cancelled(c, oldreq);
+
+	p9_free_req(c, req);
+	return 0;
+}
+
+static struct p9_req_t *p9_client_prepare_req(struct p9_client *c,
+					      int8_t type, int req_size,
+					      const char *fmt, va_list ap)
+{
+	int tag, err;
+	struct p9_req_t *req;
+
+	p9_debug(P9_DEBUG_MUX, "client %p op %d\n", c, type);
+
+	/* we allow for any status other than disconnected */
+	if (c->status == Disconnected)
+		return ERR_PTR(-EIO);
+
+	/* if status is begin_disconnected we allow only clunk request */
+	if ((c->status == BeginDisconnect) && (type != P9_TCLUNK))
+		return ERR_PTR(-EIO);
+
+	tag = P9_NOTAG;
+	if (type != P9_TVERSION) {
+		tag = p9_idpool_get(c->tagpool);
+		if (tag < 0)
+			return ERR_PTR(-ENOMEM);
+	}
+
+	req = p9_tag_alloc(c, tag, req_size);
+	if (IS_ERR(req))
+		return req;
+
+	/* marshall the data */
+	p9pdu_prepare(req->tc, tag, type);
+	err = p9pdu_vwritef(req->tc, c->proto_version, fmt, ap);
+	if (err)
+		goto reterr;
+	p9pdu_finalize(c, req->tc);
+	trace_9p_client_req(c, type, tag);
+	return req;
+reterr:
+	p9_free_req(c, req);
+	return ERR_PTR(err);
+}
+
+/**
+ * p9_client_rpc - issue a request and wait for a response
+ * @c: client session
+ * @type: type of request
+ * @fmt: protocol format string (see protocol.c)
+ *
+ * Returns request structure (which client must free using p9_free_req)
+ */
+
+static struct p9_req_t *
+p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...)
+{
+	va_list ap;
+	int sigpending, err;
+	unsigned long flags;
+	struct p9_req_t *req;
+
+	va_start(ap, fmt);
+	req = p9_client_prepare_req(c, type, c->msize, fmt, ap);
+	va_end(ap);
+	if (IS_ERR(req))
+		return req;
+
+	if (signal_pending(current)) {
+		sigpending = 1;
+		clear_thread_flag(TIF_SIGPENDING);
+	} else
+		sigpending = 0;
+
+	err = c->trans_mod->request(c, req);
+	if (err < 0) {
+		if (err != -ERESTARTSYS && err != -EFAULT)
+			c->status = Disconnected;
+		goto reterr;
+	}
+again:
+	/* Wait for the response */
+	err = wait_event_interruptible(*req->wq,
+				       req->status >= REQ_STATUS_RCVD);
+
+	/*
+	 * Make sure our req is coherent with regard to updates in other
+	 * threads - echoes to wmb() in the callback
+	 */
+	smp_rmb();
+
+	if ((err == -ERESTARTSYS) && (c->status == Connected)
+				  && (type == P9_TFLUSH)) {
+		sigpending = 1;
+		clear_thread_flag(TIF_SIGPENDING);
+		goto again;
+	}
+
+	if (req->status == REQ_STATUS_ERROR) {
+		p9_debug(P9_DEBUG_ERROR, "req_status error %d\n", req->t_err);
+		err = req->t_err;
+	}
+	if ((err == -ERESTARTSYS) && (c->status == Connected)) {
+		p9_debug(P9_DEBUG_MUX, "flushing\n");
+		sigpending = 1;
+		clear_thread_flag(TIF_SIGPENDING);
+
+		if (c->trans_mod->cancel(c, req))
+			p9_client_flush(c, req);
+
+		/* if we received the response anyway, don't signal error */
+		if (req->status == REQ_STATUS_RCVD)
+			err = 0;
+	}
+	if (sigpending) {
+		spin_lock_irqsave(&current->sighand->siglock, flags);
+		recalc_sigpending();
+		spin_unlock_irqrestore(&current->sighand->siglock, flags);
+	}
+	if (err < 0)
+		goto reterr;
+
+	err = p9_check_errors(c, req);
+	trace_9p_client_res(c, type, req->rc->tag, err);
+	if (!err)
+		return req;
+reterr:
+	p9_free_req(c, req);
+	return ERR_PTR(safe_errno(err));
+}
+
+/**
+ * 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
+ * @inlen: read buffer size
+ * @olen: write buffer size
+ * @hdrlen: reader header size, This is the size of response protocol data
+ * @fmt: protocol format string (see protocol.c)
+ *
+ * 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,
+					 int inlen, int olen, int in_hdrlen,
+					 int kern_buf, const char *fmt, ...)
+{
+	va_list ap;
+	int sigpending, err;
+	unsigned long flags;
+	struct p9_req_t *req;
+
+	va_start(ap, fmt);
+	/*
+	 * We allocate a inline protocol data of only 4k bytes.
+	 * The actual content is passed in zero-copy fashion.
+	 */
+	req = p9_client_prepare_req(c, type, P9_ZC_HDR_SZ, fmt, ap);
+	va_end(ap);
+	if (IS_ERR(req))
+		return req;
+
+	if (signal_pending(current)) {
+		sigpending = 1;
+		clear_thread_flag(TIF_SIGPENDING);
+	} 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);
+	if (err < 0) {
+		if (err == -EIO)
+			c->status = Disconnected;
+		goto reterr;
+	}
+	if (req->status == REQ_STATUS_ERROR) {
+		p9_debug(P9_DEBUG_ERROR, "req_status error %d\n", req->t_err);
+		err = req->t_err;
+	}
+	if ((err == -ERESTARTSYS) && (c->status == Connected)) {
+		p9_debug(P9_DEBUG_MUX, "flushing\n");
+		sigpending = 1;
+		clear_thread_flag(TIF_SIGPENDING);
+
+		if (c->trans_mod->cancel(c, req))
+			p9_client_flush(c, req);
+
+		/* if we received the response anyway, don't signal error */
+		if (req->status == REQ_STATUS_RCVD)
+			err = 0;
+	}
+	if (sigpending) {
+		spin_lock_irqsave(&current->sighand->siglock, flags);
+		recalc_sigpending();
+		spin_unlock_irqrestore(&current->sighand->siglock, flags);
+	}
+	if (err < 0)
+		goto reterr;
+
+	err = p9_check_zc_errors(c, req, uidata, in_hdrlen, kern_buf);
+	trace_9p_client_res(c, type, req->rc->tag, err);
+	if (!err)
+		return req;
+reterr:
+	p9_free_req(c, req);
+	return ERR_PTR(safe_errno(err));
+}
+
+static struct p9_fid *p9_fid_create(struct p9_client *clnt)
+{
+	int ret;
+	struct p9_fid *fid;
+	unsigned long flags;
+
+	p9_debug(P9_DEBUG_FID, "clnt %p\n", clnt);
+	fid = kmalloc(sizeof(struct p9_fid), GFP_KERNEL);
+	if (!fid)
+		return ERR_PTR(-ENOMEM);
+
+	ret = p9_idpool_get(clnt->fidpool);
+	if (ret < 0) {
+		ret = -ENOSPC;
+		goto error;
+	}
+	fid->fid = ret;
+
+	memset(&fid->qid, 0, sizeof(struct p9_qid));
+	fid->mode = -1;
+	fid->uid = current_fsuid();
+	fid->clnt = clnt;
+	fid->rdir = NULL;
+	spin_lock_irqsave(&clnt->lock, flags);
+	list_add(&fid->flist, &clnt->fidlist);
+	spin_unlock_irqrestore(&clnt->lock, flags);
+
+	return fid;
+
+error:
+	kfree(fid);
+	return ERR_PTR(ret);
+}
+
+static void p9_fid_destroy(struct p9_fid *fid)
+{
+	struct p9_client *clnt;
+	unsigned long flags;
+
+	p9_debug(P9_DEBUG_FID, "fid %d\n", fid->fid);
+	clnt = fid->clnt;
+	p9_idpool_put(fid->fid, clnt->fidpool);
+	spin_lock_irqsave(&clnt->lock, flags);
+	list_del(&fid->flist);
+	spin_unlock_irqrestore(&clnt->lock, flags);
+	kfree(fid->rdir);
+	kfree(fid);
+}
+
+static int p9_client_version(struct p9_client *c)
+{
+	int err = 0;
+	struct p9_req_t *req;
+	char *version;
+	int msize;
+
+	p9_debug(P9_DEBUG_9P, ">>> TVERSION msize %d protocol %d\n",
+		 c->msize, c->proto_version);
+
+	switch (c->proto_version) {
+	case p9_proto_2000L:
+		req = p9_client_rpc(c, P9_TVERSION, "ds",
+					c->msize, "9P2000.L");
+		break;
+	case p9_proto_2000u:
+		req = p9_client_rpc(c, P9_TVERSION, "ds",
+					c->msize, "9P2000.u");
+		break;
+	case p9_proto_legacy:
+		req = p9_client_rpc(c, P9_TVERSION, "ds",
+					c->msize, "9P2000");
+		break;
+	default:
+		return -EINVAL;
+		break;
+	}
+
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	err = p9pdu_readf(req->rc, c->proto_version, "ds", &msize, &version);
+	if (err) {
+		p9_debug(P9_DEBUG_9P, "version error %d\n", err);
+		trace_9p_protocol_dump(c, req->rc);
+		goto error;
+	}
+
+	p9_debug(P9_DEBUG_9P, "<<< RVERSION msize %d %s\n", msize, version);
+	if (!strncmp(version, "9P2000.L", 8))
+		c->proto_version = p9_proto_2000L;
+	else if (!strncmp(version, "9P2000.u", 8))
+		c->proto_version = p9_proto_2000u;
+	else if (!strncmp(version, "9P2000", 6))
+		c->proto_version = p9_proto_legacy;
+	else {
+		err = -EREMOTEIO;
+		goto error;
+	}
+
+	if (msize < c->msize)
+		c->msize = msize;
+
+error:
+	kfree(version);
+	p9_free_req(c, req);
+
+	return err;
+}
+
+struct p9_client *p9_client_create(const char *dev_name, char *options)
+{
+	int err;
+	struct p9_client *clnt;
+	char *client_id;
+
+	err = 0;
+	clnt = kmalloc(sizeof(struct p9_client), GFP_KERNEL);
+	if (!clnt)
+		return ERR_PTR(-ENOMEM);
+
+	clnt->trans_mod = NULL;
+	clnt->trans = NULL;
+
+	client_id = utsname()->nodename;
+	memcpy(clnt->name, client_id, strlen(client_id) + 1);
+
+	spin_lock_init(&clnt->lock);
+	INIT_LIST_HEAD(&clnt->fidlist);
+
+	err = p9_tag_init(clnt);
+	if (err < 0)
+		goto free_client;
+
+	err = parse_opts(options, clnt);
+	if (err < 0)
+		goto destroy_tagpool;
+
+	if (!clnt->trans_mod)
+		clnt->trans_mod = v9fs_get_default_trans();
+
+	if (clnt->trans_mod == NULL) {
+		err = -EPROTONOSUPPORT;
+		p9_debug(P9_DEBUG_ERROR,
+			 "No transport defined or default transport\n");
+		goto destroy_tagpool;
+	}
+
+	clnt->fidpool = p9_idpool_create();
+	if (IS_ERR(clnt->fidpool)) {
+		err = PTR_ERR(clnt->fidpool);
+		goto put_trans;
+	}
+
+	p9_debug(P9_DEBUG_MUX, "clnt %p trans %p msize %d protocol %d\n",
+		 clnt, clnt->trans_mod, clnt->msize, clnt->proto_version);
+
+	err = clnt->trans_mod->create(clnt, dev_name, options);
+	if (err)
+		goto destroy_fidpool;
+
+	if (clnt->msize > clnt->trans_mod->maxsize)
+		clnt->msize = clnt->trans_mod->maxsize;
+
+	err = p9_client_version(clnt);
+	if (err)
+		goto close_trans;
+
+	return clnt;
+
+close_trans:
+	clnt->trans_mod->close(clnt);
+destroy_fidpool:
+	p9_idpool_destroy(clnt->fidpool);
+put_trans:
+	v9fs_put_trans(clnt->trans_mod);
+destroy_tagpool:
+	p9_idpool_destroy(clnt->tagpool);
+free_client:
+	kfree(clnt);
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL(p9_client_create);
+
+void p9_client_destroy(struct p9_client *clnt)
+{
+	struct p9_fid *fid, *fidptr;
+
+	p9_debug(P9_DEBUG_MUX, "clnt %p\n", clnt);
+
+	if (clnt->trans_mod)
+		clnt->trans_mod->close(clnt);
+
+	v9fs_put_trans(clnt->trans_mod);
+
+	list_for_each_entry_safe(fid, fidptr, &clnt->fidlist, flist) {
+		pr_info("Found fid %d not clunked\n", fid->fid);
+		p9_fid_destroy(fid);
+	}
+
+	if (clnt->fidpool)
+		p9_idpool_destroy(clnt->fidpool);
+
+	p9_tag_cleanup(clnt);
+
+	kfree(clnt);
+}
+EXPORT_SYMBOL(p9_client_destroy);
+
+void p9_client_disconnect(struct p9_client *clnt)
+{
+	p9_debug(P9_DEBUG_9P, "clnt %p\n", clnt);
+	clnt->status = Disconnected;
+}
+EXPORT_SYMBOL(p9_client_disconnect);
+
+void p9_client_begin_disconnect(struct p9_client *clnt)
+{
+	p9_debug(P9_DEBUG_9P, "clnt %p\n", clnt);
+	clnt->status = BeginDisconnect;
+}
+EXPORT_SYMBOL(p9_client_begin_disconnect);
+
+struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid,
+	char *uname, kuid_t n_uname, char *aname)
+{
+	int err = 0;
+	struct p9_req_t *req;
+	struct p9_fid *fid;
+	struct p9_qid qid;
+
+
+	p9_debug(P9_DEBUG_9P, ">>> TATTACH afid %d uname %s aname %s\n",
+		 afid ? afid->fid : -1, uname, aname);
+	fid = p9_fid_create(clnt);
+	if (IS_ERR(fid)) {
+		err = PTR_ERR(fid);
+		fid = NULL;
+		goto error;
+	}
+
+	req = p9_client_rpc(clnt, P9_TATTACH, "ddss?u", fid->fid,
+			afid ? afid->fid : P9_NOFID, uname, aname, n_uname);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto error;
+	}
+
+	err = p9pdu_readf(req->rc, clnt->proto_version, "Q", &qid);
+	if (err) {
+		trace_9p_protocol_dump(clnt, req->rc);
+		p9_free_req(clnt, req);
+		goto error;
+	}
+
+	p9_debug(P9_DEBUG_9P, "<<< RATTACH qid %x.%llx.%x\n",
+		 qid.type, (unsigned long long)qid.path, qid.version);
+
+	memmove(&fid->qid, &qid, sizeof(struct p9_qid));
+
+	p9_free_req(clnt, req);
+	return fid;
+
+error:
+	if (fid)
+		p9_fid_destroy(fid);
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL(p9_client_attach);
+
+struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname,
+		char **wnames, int clone)
+{
+	int err;
+	struct p9_client *clnt;
+	struct p9_fid *fid;
+	struct p9_qid *wqids;
+	struct p9_req_t *req;
+	uint16_t nwqids, count;
+
+	err = 0;
+	wqids = NULL;
+	clnt = oldfid->clnt;
+	if (clone) {
+		fid = p9_fid_create(clnt);
+		if (IS_ERR(fid)) {
+			err = PTR_ERR(fid);
+			fid = NULL;
+			goto error;
+		}
+
+		fid->uid = oldfid->uid;
+	} else
+		fid = oldfid;
+
+
+	p9_debug(P9_DEBUG_9P, ">>> TWALK fids %d,%d nwname %ud wname[0] %s\n",
+		 oldfid->fid, fid->fid, nwname, wnames ? wnames[0] : NULL);
+
+	req = p9_client_rpc(clnt, P9_TWALK, "ddT", oldfid->fid, fid->fid,
+								nwname, wnames);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto error;
+	}
+
+	err = p9pdu_readf(req->rc, clnt->proto_version, "R", &nwqids, &wqids);
+	if (err) {
+		trace_9p_protocol_dump(clnt, req->rc);
+		p9_free_req(clnt, req);
+		goto clunk_fid;
+	}
+	p9_free_req(clnt, req);
+
+	p9_debug(P9_DEBUG_9P, "<<< RWALK nwqid %d:\n", nwqids);
+
+	if (nwqids != nwname) {
+		err = -ENOENT;
+		goto clunk_fid;
+	}
+
+	for (count = 0; count < nwqids; count++)
+		p9_debug(P9_DEBUG_9P, "<<<     [%d] %x.%llx.%x\n",
+			count, wqids[count].type,
+			(unsigned long long)wqids[count].path,
+			wqids[count].version);
+
+	if (nwname)
+		memmove(&fid->qid, &wqids[nwqids - 1], sizeof(struct p9_qid));
+	else
+		fid->qid = oldfid->qid;
+
+	kfree(wqids);
+	return fid;
+
+clunk_fid:
+	kfree(wqids);
+	p9_client_clunk(fid);
+	fid = NULL;
+
+error:
+	if (fid && (fid != oldfid))
+		p9_fid_destroy(fid);
+
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL(p9_client_walk);
+
+int p9_client_open(struct p9_fid *fid, int mode)
+{
+	int err;
+	struct p9_client *clnt;
+	struct p9_req_t *req;
+	struct p9_qid qid;
+	int iounit;
+
+	clnt = fid->clnt;
+	p9_debug(P9_DEBUG_9P, ">>> %s fid %d mode %d\n",
+		p9_is_proto_dotl(clnt) ? "TLOPEN" : "TOPEN", fid->fid, mode);
+	err = 0;
+
+	if (fid->mode != -1)
+		return -EINVAL;
+
+	if (p9_is_proto_dotl(clnt))
+		req = p9_client_rpc(clnt, P9_TLOPEN, "dd", fid->fid, mode);
+	else
+		req = p9_client_rpc(clnt, P9_TOPEN, "db", fid->fid, mode);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto error;
+	}
+
+	err = p9pdu_readf(req->rc, clnt->proto_version, "Qd", &qid, &iounit);
+	if (err) {
+		trace_9p_protocol_dump(clnt, req->rc);
+		goto free_and_error;
+	}
+
+	p9_debug(P9_DEBUG_9P, "<<< %s qid %x.%llx.%x iounit %x\n",
+		p9_is_proto_dotl(clnt) ? "RLOPEN" : "ROPEN",  qid.type,
+		(unsigned long long)qid.path, qid.version, iounit);
+
+	fid->mode = mode;
+	fid->iounit = iounit;
+
+free_and_error:
+	p9_free_req(clnt, req);
+error:
+	return err;
+}
+EXPORT_SYMBOL(p9_client_open);
+
+int p9_client_create_dotl(struct p9_fid *ofid, char *name, u32 flags, u32 mode,
+		kgid_t gid, struct p9_qid *qid)
+{
+	int err = 0;
+	struct p9_client *clnt;
+	struct p9_req_t *req;
+	int iounit;
+
+	p9_debug(P9_DEBUG_9P,
+			">>> TLCREATE fid %d name %s flags %d mode %d gid %d\n",
+			ofid->fid, name, flags, mode,
+		 	from_kgid(&init_user_ns, gid));
+	clnt = ofid->clnt;
+
+	if (ofid->mode != -1)
+		return -EINVAL;
+
+	req = p9_client_rpc(clnt, P9_TLCREATE, "dsddg", ofid->fid, name, flags,
+			mode, gid);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto error;
+	}
+
+	err = p9pdu_readf(req->rc, clnt->proto_version, "Qd", qid, &iounit);
+	if (err) {
+		trace_9p_protocol_dump(clnt, req->rc);
+		goto free_and_error;
+	}
+
+	p9_debug(P9_DEBUG_9P, "<<< RLCREATE qid %x.%llx.%x iounit %x\n",
+			qid->type,
+			(unsigned long long)qid->path,
+			qid->version, iounit);
+
+	ofid->mode = mode;
+	ofid->iounit = iounit;
+
+free_and_error:
+	p9_free_req(clnt, req);
+error:
+	return err;
+}
+EXPORT_SYMBOL(p9_client_create_dotl);
+
+int p9_client_fcreate(struct p9_fid *fid, char *name, u32 perm, int mode,
+		     char *extension)
+{
+	int err;
+	struct p9_client *clnt;
+	struct p9_req_t *req;
+	struct p9_qid qid;
+	int iounit;
+
+	p9_debug(P9_DEBUG_9P, ">>> TCREATE fid %d name %s perm %d mode %d\n",
+						fid->fid, name, perm, mode);
+	err = 0;
+	clnt = fid->clnt;
+
+	if (fid->mode != -1)
+		return -EINVAL;
+
+	req = p9_client_rpc(clnt, P9_TCREATE, "dsdb?s", fid->fid, name, perm,
+				mode, extension);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto error;
+	}
+
+	err = p9pdu_readf(req->rc, clnt->proto_version, "Qd", &qid, &iounit);
+	if (err) {
+		trace_9p_protocol_dump(clnt, req->rc);
+		goto free_and_error;
+	}
+
+	p9_debug(P9_DEBUG_9P, "<<< RCREATE qid %x.%llx.%x iounit %x\n",
+				qid.type,
+				(unsigned long long)qid.path,
+				qid.version, iounit);
+
+	fid->mode = mode;
+	fid->iounit = iounit;
+
+free_and_error:
+	p9_free_req(clnt, req);
+error:
+	return err;
+}
+EXPORT_SYMBOL(p9_client_fcreate);
+
+int p9_client_symlink(struct p9_fid *dfid, char *name, char *symtgt, kgid_t gid,
+		struct p9_qid *qid)
+{
+	int err = 0;
+	struct p9_client *clnt;
+	struct p9_req_t *req;
+
+	p9_debug(P9_DEBUG_9P, ">>> TSYMLINK dfid %d name %s  symtgt %s\n",
+			dfid->fid, name, symtgt);
+	clnt = dfid->clnt;
+
+	req = p9_client_rpc(clnt, P9_TSYMLINK, "dssg", dfid->fid, name, symtgt,
+			gid);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto error;
+	}
+
+	err = p9pdu_readf(req->rc, clnt->proto_version, "Q", qid);
+	if (err) {
+		trace_9p_protocol_dump(clnt, req->rc);
+		goto free_and_error;
+	}
+
+	p9_debug(P9_DEBUG_9P, "<<< RSYMLINK qid %x.%llx.%x\n",
+			qid->type, (unsigned long long)qid->path, qid->version);
+
+free_and_error:
+	p9_free_req(clnt, req);
+error:
+	return err;
+}
+EXPORT_SYMBOL(p9_client_symlink);
+
+int p9_client_link(struct p9_fid *dfid, struct p9_fid *oldfid, char *newname)
+{
+	struct p9_client *clnt;
+	struct p9_req_t *req;
+
+	p9_debug(P9_DEBUG_9P, ">>> TLINK dfid %d oldfid %d newname %s\n",
+			dfid->fid, oldfid->fid, newname);
+	clnt = dfid->clnt;
+	req = p9_client_rpc(clnt, P9_TLINK, "dds", dfid->fid, oldfid->fid,
+			newname);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	p9_debug(P9_DEBUG_9P, "<<< RLINK\n");
+	p9_free_req(clnt, req);
+	return 0;
+}
+EXPORT_SYMBOL(p9_client_link);
+
+int p9_client_fsync(struct p9_fid *fid, int datasync)
+{
+	int err;
+	struct p9_client *clnt;
+	struct p9_req_t *req;
+
+	p9_debug(P9_DEBUG_9P, ">>> TFSYNC fid %d datasync:%d\n",
+			fid->fid, datasync);
+	err = 0;
+	clnt = fid->clnt;
+
+	req = p9_client_rpc(clnt, P9_TFSYNC, "dd", fid->fid, datasync);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto error;
+	}
+
+	p9_debug(P9_DEBUG_9P, "<<< RFSYNC fid %d\n", fid->fid);
+
+	p9_free_req(clnt, req);
+
+error:
+	return err;
+}
+EXPORT_SYMBOL(p9_client_fsync);
+
+int p9_client_clunk(struct p9_fid *fid)
+{
+	int err;
+	struct p9_client *clnt;
+	struct p9_req_t *req;
+	int retries = 0;
+
+	if (!fid) {
+		pr_warn("%s (%d): Trying to clunk with NULL fid\n",
+			__func__, task_pid_nr(current));
+		dump_stack();
+		return 0;
+	}
+
+again:
+	p9_debug(P9_DEBUG_9P, ">>> TCLUNK fid %d (try %d)\n", fid->fid,
+								retries);
+	err = 0;
+	clnt = fid->clnt;
+
+	req = p9_client_rpc(clnt, P9_TCLUNK, "d", fid->fid);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto error;
+	}
+
+	p9_debug(P9_DEBUG_9P, "<<< RCLUNK fid %d\n", fid->fid);
+
+	p9_free_req(clnt, req);
+error:
+	/*
+	 * Fid is not valid even after a failed clunk
+	 * If interrupted, retry once then give up and
+	 * leak fid until umount.
+	 */
+	if (err == -ERESTARTSYS) {
+		if (retries++ == 0)
+			goto again;
+	} else
+		p9_fid_destroy(fid);
+	return err;
+}
+EXPORT_SYMBOL(p9_client_clunk);
+
+int p9_client_remove(struct p9_fid *fid)
+{
+	int err;
+	struct p9_client *clnt;
+	struct p9_req_t *req;
+
+	p9_debug(P9_DEBUG_9P, ">>> TREMOVE fid %d\n", fid->fid);
+	err = 0;
+	clnt = fid->clnt;
+
+	req = p9_client_rpc(clnt, P9_TREMOVE, "d", fid->fid);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto error;
+	}
+
+	p9_debug(P9_DEBUG_9P, "<<< RREMOVE fid %d\n", fid->fid);
+
+	p9_free_req(clnt, req);
+error:
+	if (err == -ERESTARTSYS)
+		p9_client_clunk(fid);
+	else
+		p9_fid_destroy(fid);
+	return err;
+}
+EXPORT_SYMBOL(p9_client_remove);
+
+int p9_client_unlinkat(struct p9_fid *dfid, const char *name, int flags)
+{
+	int err = 0;
+	struct p9_req_t *req;
+	struct p9_client *clnt;
+
+	p9_debug(P9_DEBUG_9P, ">>> TUNLINKAT fid %d %s %d\n",
+		   dfid->fid, name, flags);
+
+	clnt = dfid->clnt;
+	req = p9_client_rpc(clnt, P9_TUNLINKAT, "dsd", dfid->fid, name, flags);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto error;
+	}
+	p9_debug(P9_DEBUG_9P, "<<< RUNLINKAT fid %d %s\n", dfid->fid, name);
+
+	p9_free_req(clnt, req);
+error:
+	return err;
+}
+EXPORT_SYMBOL(p9_client_unlinkat);
+
+int
+p9_client_read(struct p9_fid *fid, char *data, char __user *udata, u64 offset,
+								u32 count)
+{
+	char *dataptr;
+	int kernel_buf = 0;
+	struct p9_req_t *req;
+	struct p9_client *clnt;
+	int err, rsize, non_zc = 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;
+	}
+
+	err = p9pdu_readf(req->rc, clnt->proto_version, "D", &count, &dataptr);
+	if (err) {
+		trace_9p_protocol_dump(clnt, req->rc);
+		goto free_and_error;
+	}
+
+	p9_debug(P9_DEBUG_9P, "<<< RREAD count %d\n", count);
+
+	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;
+			}
+		}
+	}
+	p9_free_req(clnt, req);
+	return count;
+
+free_and_error:
+	p9_free_req(clnt, req);
+error:
+	return err;
+}
+EXPORT_SYMBOL(p9_client_read);
+
+int
+p9_client_write(struct p9_fid *fid, char *data, const char __user *udata,
+							u64 offset, u32 count)
+{
+	int err, rsize;
+	int kernel_buf = 0;
+	struct p9_client *clnt;
+	struct p9_req_t *req;
+
+	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;
+
+	if (count < rsize)
+		rsize = 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_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;
+}
+EXPORT_SYMBOL(p9_client_write);
+
+struct p9_wstat *p9_client_stat(struct p9_fid *fid)
+{
+	int err;
+	struct p9_client *clnt;
+	struct p9_wstat *ret = kmalloc(sizeof(struct p9_wstat), GFP_KERNEL);
+	struct p9_req_t *req;
+	u16 ignored;
+
+	p9_debug(P9_DEBUG_9P, ">>> TSTAT fid %d\n", fid->fid);
+
+	if (!ret)
+		return ERR_PTR(-ENOMEM);
+
+	err = 0;
+	clnt = fid->clnt;
+
+	req = p9_client_rpc(clnt, P9_TSTAT, "d", fid->fid);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto error;
+	}
+
+	err = p9pdu_readf(req->rc, clnt->proto_version, "wS", &ignored, ret);
+	if (err) {
+		trace_9p_protocol_dump(clnt, req->rc);
+		p9_free_req(clnt, req);
+		goto error;
+	}
+
+	p9_debug(P9_DEBUG_9P,
+		"<<< RSTAT sz=%x type=%x dev=%x qid=%x.%llx.%x\n"
+		"<<<    mode=%8.8x atime=%8.8x mtime=%8.8x length=%llx\n"
+		"<<<    name=%s uid=%s gid=%s muid=%s extension=(%s)\n"
+		"<<<    uid=%d gid=%d n_muid=%d\n",
+		ret->size, ret->type, ret->dev, ret->qid.type,
+		(unsigned long long)ret->qid.path, ret->qid.version, ret->mode,
+		ret->atime, ret->mtime, (unsigned long long)ret->length,
+		ret->name, ret->uid, ret->gid, ret->muid, ret->extension,
+		from_kuid(&init_user_ns, ret->n_uid),
+		from_kgid(&init_user_ns, ret->n_gid),
+		from_kuid(&init_user_ns, ret->n_muid));
+
+	p9_free_req(clnt, req);
+	return ret;
+
+error:
+	kfree(ret);
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL(p9_client_stat);
+
+struct p9_stat_dotl *p9_client_getattr_dotl(struct p9_fid *fid,
+							u64 request_mask)
+{
+	int err;
+	struct p9_client *clnt;
+	struct p9_stat_dotl *ret = kmalloc(sizeof(struct p9_stat_dotl),
+								GFP_KERNEL);
+	struct p9_req_t *req;
+
+	p9_debug(P9_DEBUG_9P, ">>> TGETATTR fid %d, request_mask %lld\n",
+							fid->fid, request_mask);
+
+	if (!ret)
+		return ERR_PTR(-ENOMEM);
+
+	err = 0;
+	clnt = fid->clnt;
+
+	req = p9_client_rpc(clnt, P9_TGETATTR, "dq", fid->fid, request_mask);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto error;
+	}
+
+	err = p9pdu_readf(req->rc, clnt->proto_version, "A", ret);
+	if (err) {
+		trace_9p_protocol_dump(clnt, req->rc);
+		p9_free_req(clnt, req);
+		goto error;
+	}
+
+	p9_debug(P9_DEBUG_9P,
+		"<<< RGETATTR st_result_mask=%lld\n"
+		"<<< qid=%x.%llx.%x\n"
+		"<<< st_mode=%8.8x st_nlink=%llu\n"
+		"<<< st_uid=%d st_gid=%d\n"
+		"<<< st_rdev=%llx st_size=%llx st_blksize=%llu st_blocks=%llu\n"
+		"<<< st_atime_sec=%lld st_atime_nsec=%lld\n"
+		"<<< st_mtime_sec=%lld st_mtime_nsec=%lld\n"
+		"<<< st_ctime_sec=%lld st_ctime_nsec=%lld\n"
+		"<<< st_btime_sec=%lld st_btime_nsec=%lld\n"
+		"<<< st_gen=%lld st_data_version=%lld",
+		ret->st_result_mask, ret->qid.type, ret->qid.path,
+		ret->qid.version, ret->st_mode, ret->st_nlink,
+		from_kuid(&init_user_ns, ret->st_uid),
+		from_kgid(&init_user_ns, ret->st_gid),
+		ret->st_rdev, ret->st_size, ret->st_blksize,
+		ret->st_blocks, ret->st_atime_sec, ret->st_atime_nsec,
+		ret->st_mtime_sec, ret->st_mtime_nsec, ret->st_ctime_sec,
+		ret->st_ctime_nsec, ret->st_btime_sec, ret->st_btime_nsec,
+		ret->st_gen, ret->st_data_version);
+
+	p9_free_req(clnt, req);
+	return ret;
+
+error:
+	kfree(ret);
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL(p9_client_getattr_dotl);
+
+static int p9_client_statsize(struct p9_wstat *wst, int proto_version)
+{
+	int ret;
+
+	/* NOTE: size shouldn't include its own length */
+	/* size[2] type[2] dev[4] qid[13] */
+	/* mode[4] atime[4] mtime[4] length[8]*/
+	/* name[s] uid[s] gid[s] muid[s] */
+	ret = 2+4+13+4+4+4+8+2+2+2+2;
+
+	if (wst->name)
+		ret += strlen(wst->name);
+	if (wst->uid)
+		ret += strlen(wst->uid);
+	if (wst->gid)
+		ret += strlen(wst->gid);
+	if (wst->muid)
+		ret += strlen(wst->muid);
+
+	if ((proto_version == p9_proto_2000u) ||
+		(proto_version == p9_proto_2000L)) {
+		ret += 2+4+4+4;	/* extension[s] n_uid[4] n_gid[4] n_muid[4] */
+		if (wst->extension)
+			ret += strlen(wst->extension);
+	}
+
+	return ret;
+}
+
+int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst)
+{
+	int err;
+	struct p9_req_t *req;
+	struct p9_client *clnt;
+
+	err = 0;
+	clnt = fid->clnt;
+	wst->size = p9_client_statsize(wst, clnt->proto_version);
+	p9_debug(P9_DEBUG_9P, ">>> TWSTAT fid %d\n", fid->fid);
+	p9_debug(P9_DEBUG_9P,
+		"     sz=%x type=%x dev=%x qid=%x.%llx.%x\n"
+		"     mode=%8.8x atime=%8.8x mtime=%8.8x length=%llx\n"
+		"     name=%s uid=%s gid=%s muid=%s extension=(%s)\n"
+		"     uid=%d gid=%d n_muid=%d\n",
+		wst->size, wst->type, wst->dev, wst->qid.type,
+		(unsigned long long)wst->qid.path, wst->qid.version, wst->mode,
+		wst->atime, wst->mtime, (unsigned long long)wst->length,
+		wst->name, wst->uid, wst->gid, wst->muid, wst->extension,
+		from_kuid(&init_user_ns, wst->n_uid),
+		from_kgid(&init_user_ns, wst->n_gid),
+		from_kuid(&init_user_ns, wst->n_muid));
+
+	req = p9_client_rpc(clnt, P9_TWSTAT, "dwS", fid->fid, wst->size+2, wst);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto error;
+	}
+
+	p9_debug(P9_DEBUG_9P, "<<< RWSTAT fid %d\n", fid->fid);
+
+	p9_free_req(clnt, req);
+error:
+	return err;
+}
+EXPORT_SYMBOL(p9_client_wstat);
+
+int p9_client_setattr(struct p9_fid *fid, struct p9_iattr_dotl *p9attr)
+{
+	int err;
+	struct p9_req_t *req;
+	struct p9_client *clnt;
+
+	err = 0;
+	clnt = fid->clnt;
+	p9_debug(P9_DEBUG_9P, ">>> TSETATTR fid %d\n", fid->fid);
+	p9_debug(P9_DEBUG_9P,
+		"    valid=%x mode=%x uid=%d gid=%d size=%lld\n"
+		"    atime_sec=%lld atime_nsec=%lld\n"
+		"    mtime_sec=%lld mtime_nsec=%lld\n",
+		p9attr->valid, p9attr->mode,
+		from_kuid(&init_user_ns, p9attr->uid),
+		from_kgid(&init_user_ns, p9attr->gid),
+		p9attr->size, p9attr->atime_sec, p9attr->atime_nsec,
+		p9attr->mtime_sec, p9attr->mtime_nsec);
+
+	req = p9_client_rpc(clnt, P9_TSETATTR, "dI", fid->fid, p9attr);
+
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto error;
+	}
+	p9_debug(P9_DEBUG_9P, "<<< RSETATTR fid %d\n", fid->fid);
+	p9_free_req(clnt, req);
+error:
+	return err;
+}
+EXPORT_SYMBOL(p9_client_setattr);
+
+int p9_client_statfs(struct p9_fid *fid, struct p9_rstatfs *sb)
+{
+	int err;
+	struct p9_req_t *req;
+	struct p9_client *clnt;
+
+	err = 0;
+	clnt = fid->clnt;
+
+	p9_debug(P9_DEBUG_9P, ">>> TSTATFS fid %d\n", fid->fid);
+
+	req = p9_client_rpc(clnt, P9_TSTATFS, "d", fid->fid);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto error;
+	}
+
+	err = p9pdu_readf(req->rc, clnt->proto_version, "ddqqqqqqd", &sb->type,
+		&sb->bsize, &sb->blocks, &sb->bfree, &sb->bavail,
+		&sb->files, &sb->ffree, &sb->fsid, &sb->namelen);
+	if (err) {
+		trace_9p_protocol_dump(clnt, req->rc);
+		p9_free_req(clnt, req);
+		goto error;
+	}
+
+	p9_debug(P9_DEBUG_9P, "<<< RSTATFS fid %d type 0x%lx bsize %ld "
+		"blocks %llu bfree %llu bavail %llu files %llu ffree %llu "
+		"fsid %llu namelen %ld\n",
+		fid->fid, (long unsigned int)sb->type, (long int)sb->bsize,
+		sb->blocks, sb->bfree, sb->bavail, sb->files,  sb->ffree,
+		sb->fsid, (long int)sb->namelen);
+
+	p9_free_req(clnt, req);
+error:
+	return err;
+}
+EXPORT_SYMBOL(p9_client_statfs);
+
+int p9_client_rename(struct p9_fid *fid,
+		     struct p9_fid *newdirfid, const char *name)
+{
+	int err;
+	struct p9_req_t *req;
+	struct p9_client *clnt;
+
+	err = 0;
+	clnt = fid->clnt;
+
+	p9_debug(P9_DEBUG_9P, ">>> TRENAME fid %d newdirfid %d name %s\n",
+			fid->fid, newdirfid->fid, name);
+
+	req = p9_client_rpc(clnt, P9_TRENAME, "dds", fid->fid,
+			newdirfid->fid, name);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto error;
+	}
+
+	p9_debug(P9_DEBUG_9P, "<<< RRENAME fid %d\n", fid->fid);
+
+	p9_free_req(clnt, req);
+error:
+	return err;
+}
+EXPORT_SYMBOL(p9_client_rename);
+
+int p9_client_renameat(struct p9_fid *olddirfid, const char *old_name,
+		       struct p9_fid *newdirfid, const char *new_name)
+{
+	int err;
+	struct p9_req_t *req;
+	struct p9_client *clnt;
+
+	err = 0;
+	clnt = olddirfid->clnt;
+
+	p9_debug(P9_DEBUG_9P, ">>> TRENAMEAT olddirfid %d old name %s"
+		   " newdirfid %d new name %s\n", olddirfid->fid, old_name,
+		   newdirfid->fid, new_name);
+
+	req = p9_client_rpc(clnt, P9_TRENAMEAT, "dsds", olddirfid->fid,
+			    old_name, newdirfid->fid, new_name);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto error;
+	}
+
+	p9_debug(P9_DEBUG_9P, "<<< RRENAMEAT newdirfid %d new name %s\n",
+		   newdirfid->fid, new_name);
+
+	p9_free_req(clnt, req);
+error:
+	return err;
+}
+EXPORT_SYMBOL(p9_client_renameat);
+
+/*
+ * An xattrwalk without @attr_name gives the fid for the lisxattr namespace
+ */
+struct p9_fid *p9_client_xattrwalk(struct p9_fid *file_fid,
+				const char *attr_name, u64 *attr_size)
+{
+	int err;
+	struct p9_req_t *req;
+	struct p9_client *clnt;
+	struct p9_fid *attr_fid;
+
+	err = 0;
+	clnt = file_fid->clnt;
+	attr_fid = p9_fid_create(clnt);
+	if (IS_ERR(attr_fid)) {
+		err = PTR_ERR(attr_fid);
+		attr_fid = NULL;
+		goto error;
+	}
+	p9_debug(P9_DEBUG_9P,
+		">>> TXATTRWALK file_fid %d, attr_fid %d name %s\n",
+		file_fid->fid, attr_fid->fid, attr_name);
+
+	req = p9_client_rpc(clnt, P9_TXATTRWALK, "dds",
+			file_fid->fid, attr_fid->fid, attr_name);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto error;
+	}
+	err = p9pdu_readf(req->rc, clnt->proto_version, "q", attr_size);
+	if (err) {
+		trace_9p_protocol_dump(clnt, req->rc);
+		p9_free_req(clnt, req);
+		goto clunk_fid;
+	}
+	p9_free_req(clnt, req);
+	p9_debug(P9_DEBUG_9P, "<<<  RXATTRWALK fid %d size %llu\n",
+		attr_fid->fid, *attr_size);
+	return attr_fid;
+clunk_fid:
+	p9_client_clunk(attr_fid);
+	attr_fid = NULL;
+error:
+	if (attr_fid && (attr_fid != file_fid))
+		p9_fid_destroy(attr_fid);
+
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL_GPL(p9_client_xattrwalk);
+
+int p9_client_xattrcreate(struct p9_fid *fid, const char *name,
+			u64 attr_size, int flags)
+{
+	int err;
+	struct p9_req_t *req;
+	struct p9_client *clnt;
+
+	p9_debug(P9_DEBUG_9P,
+		">>> TXATTRCREATE fid %d name  %s size %lld flag %d\n",
+		fid->fid, name, (long long)attr_size, flags);
+	err = 0;
+	clnt = fid->clnt;
+	req = p9_client_rpc(clnt, P9_TXATTRCREATE, "dsqd",
+			fid->fid, name, attr_size, flags);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto error;
+	}
+	p9_debug(P9_DEBUG_9P, "<<< RXATTRCREATE fid %d\n", fid->fid);
+	p9_free_req(clnt, req);
+error:
+	return err;
+}
+EXPORT_SYMBOL_GPL(p9_client_xattrcreate);
+
+int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset)
+{
+	int err, rsize, non_zc = 0;
+	struct p9_client *clnt;
+	struct p9_req_t *req;
+	char *dataptr;
+
+	p9_debug(P9_DEBUG_9P, ">>> TREADDIR 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_READDIRHDRSZ)
+		rsize = clnt->msize - P9_READDIRHDRSZ;
+
+	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_TREADDIR, data, NULL, rsize, 0,
+				       11, 1, "dqd", fid->fid, offset, rsize);
+	} else {
+		non_zc = 1;
+		req = p9_client_rpc(clnt, P9_TREADDIR, "dqd", fid->fid,
+				    offset, rsize);
+	}
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto error;
+	}
+
+	err = p9pdu_readf(req->rc, clnt->proto_version, "D", &count, &dataptr);
+	if (err) {
+		trace_9p_protocol_dump(clnt, req->rc);
+		goto free_and_error;
+	}
+
+	p9_debug(P9_DEBUG_9P, "<<< RREADDIR count %d\n", count);
+
+	if (non_zc)
+		memmove(data, dataptr, count);
+
+	p9_free_req(clnt, req);
+	return count;
+
+free_and_error:
+	p9_free_req(clnt, req);
+error:
+	return err;
+}
+EXPORT_SYMBOL(p9_client_readdir);
+
+int p9_client_mknod_dotl(struct p9_fid *fid, char *name, int mode,
+			dev_t rdev, kgid_t gid, struct p9_qid *qid)
+{
+	int err;
+	struct p9_client *clnt;
+	struct p9_req_t *req;
+
+	err = 0;
+	clnt = fid->clnt;
+	p9_debug(P9_DEBUG_9P, ">>> TMKNOD fid %d name %s mode %d major %d "
+		"minor %d\n", fid->fid, name, mode, MAJOR(rdev), MINOR(rdev));
+	req = p9_client_rpc(clnt, P9_TMKNOD, "dsdddg", fid->fid, name, mode,
+		MAJOR(rdev), MINOR(rdev), gid);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	err = p9pdu_readf(req->rc, clnt->proto_version, "Q", qid);
+	if (err) {
+		trace_9p_protocol_dump(clnt, req->rc);
+		goto error;
+	}
+	p9_debug(P9_DEBUG_9P, "<<< RMKNOD qid %x.%llx.%x\n", qid->type,
+				(unsigned long long)qid->path, qid->version);
+
+error:
+	p9_free_req(clnt, req);
+	return err;
+
+}
+EXPORT_SYMBOL(p9_client_mknod_dotl);
+
+int p9_client_mkdir_dotl(struct p9_fid *fid, char *name, int mode,
+				kgid_t gid, struct p9_qid *qid)
+{
+	int err;
+	struct p9_client *clnt;
+	struct p9_req_t *req;
+
+	err = 0;
+	clnt = fid->clnt;
+	p9_debug(P9_DEBUG_9P, ">>> TMKDIR fid %d name %s mode %d gid %d\n",
+		 fid->fid, name, mode, from_kgid(&init_user_ns, gid));
+	req = p9_client_rpc(clnt, P9_TMKDIR, "dsdg", fid->fid, name, mode,
+		gid);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	err = p9pdu_readf(req->rc, clnt->proto_version, "Q", qid);
+	if (err) {
+		trace_9p_protocol_dump(clnt, req->rc);
+		goto error;
+	}
+	p9_debug(P9_DEBUG_9P, "<<< RMKDIR qid %x.%llx.%x\n", qid->type,
+				(unsigned long long)qid->path, qid->version);
+
+error:
+	p9_free_req(clnt, req);
+	return err;
+
+}
+EXPORT_SYMBOL(p9_client_mkdir_dotl);
+
+int p9_client_lock_dotl(struct p9_fid *fid, struct p9_flock *flock, u8 *status)
+{
+	int err;
+	struct p9_client *clnt;
+	struct p9_req_t *req;
+
+	err = 0;
+	clnt = fid->clnt;
+	p9_debug(P9_DEBUG_9P, ">>> TLOCK fid %d type %i flags %d "
+			"start %lld length %lld proc_id %d client_id %s\n",
+			fid->fid, flock->type, flock->flags, flock->start,
+			flock->length, flock->proc_id, flock->client_id);
+
+	req = p9_client_rpc(clnt, P9_TLOCK, "dbdqqds", fid->fid, flock->type,
+				flock->flags, flock->start, flock->length,
+					flock->proc_id, flock->client_id);
+
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	err = p9pdu_readf(req->rc, clnt->proto_version, "b", status);
+	if (err) {
+		trace_9p_protocol_dump(clnt, req->rc);
+		goto error;
+	}
+	p9_debug(P9_DEBUG_9P, "<<< RLOCK status %i\n", *status);
+error:
+	p9_free_req(clnt, req);
+	return err;
+
+}
+EXPORT_SYMBOL(p9_client_lock_dotl);
+
+int p9_client_getlock_dotl(struct p9_fid *fid, struct p9_getlock *glock)
+{
+	int err;
+	struct p9_client *clnt;
+	struct p9_req_t *req;
+
+	err = 0;
+	clnt = fid->clnt;
+	p9_debug(P9_DEBUG_9P, ">>> TGETLOCK fid %d, type %i start %lld "
+		"length %lld proc_id %d client_id %s\n", fid->fid, glock->type,
+		glock->start, glock->length, glock->proc_id, glock->client_id);
+
+	req = p9_client_rpc(clnt, P9_TGETLOCK, "dbqqds", fid->fid,  glock->type,
+		glock->start, glock->length, glock->proc_id, glock->client_id);
+
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	err = p9pdu_readf(req->rc, clnt->proto_version, "bqqds", &glock->type,
+			&glock->start, &glock->length, &glock->proc_id,
+			&glock->client_id);
+	if (err) {
+		trace_9p_protocol_dump(clnt, req->rc);
+		goto error;
+	}
+	p9_debug(P9_DEBUG_9P, "<<< RGETLOCK type %i start %lld length %lld "
+		"proc_id %d client_id %s\n", glock->type, glock->start,
+		glock->length, glock->proc_id, glock->client_id);
+error:
+	p9_free_req(clnt, req);
+	return err;
+}
+EXPORT_SYMBOL(p9_client_getlock_dotl);
+
+int p9_client_readlink(struct p9_fid *fid, char **target)
+{
+	int err;
+	struct p9_client *clnt;
+	struct p9_req_t *req;
+
+	err = 0;
+	clnt = fid->clnt;
+	p9_debug(P9_DEBUG_9P, ">>> TREADLINK fid %d\n", fid->fid);
+
+	req = p9_client_rpc(clnt, P9_TREADLINK, "d", fid->fid);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	err = p9pdu_readf(req->rc, clnt->proto_version, "s", target);
+	if (err) {
+		trace_9p_protocol_dump(clnt, req->rc);
+		goto error;
+	}
+	p9_debug(P9_DEBUG_9P, "<<< RREADLINK target %s\n", *target);
+error:
+	p9_free_req(clnt, req);
+	return err;
+}
+EXPORT_SYMBOL(p9_client_readlink);
diff --git a/net/9p/error.c b/net/9p/error.c
new file mode 100644
index 00000000000..126fd0dceea
--- /dev/null
+++ b/net/9p/error.c
@@ -0,0 +1,247 @@
+/*
+ * linux/fs/9p/error.c
+ *
+ * Error string handling
+ *
+ * Plan 9 uses error strings, Unix uses error numbers.  These functions
+ * try to help manage that and provide for dynamically adding error
+ * mappings.
+ *
+ *  Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ *  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:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/jhash.h>
+#include <linux/errno.h>
+#include <net/9p/9p.h>
+
+/**
+ * struct errormap - map string errors from Plan 9 to Linux numeric ids
+ * @name: string sent over 9P
+ * @val: numeric id most closely representing @name
+ * @namelen: length of string
+ * @list: hash-table list for string lookup
+ */
+struct errormap {
+	char *name;
+	int val;
+
+	int namelen;
+	struct hlist_node list;
+};
+
+#define ERRHASHSZ		32
+static struct hlist_head hash_errmap[ERRHASHSZ];
+
+/* FixMe - reduce to a reasonable size */
+static struct errormap errmap[] = {
+	{"Operation not permitted", EPERM},
+	{"wstat prohibited", EPERM},
+	{"No such file or directory", ENOENT},
+	{"directory entry not found", ENOENT},
+	{"file not found", ENOENT},
+	{"Interrupted system call", EINTR},
+	{"Input/output error", EIO},
+	{"No such device or address", ENXIO},
+	{"Argument list too long", E2BIG},
+	{"Bad file descriptor", EBADF},
+	{"Resource temporarily unavailable", EAGAIN},
+	{"Cannot allocate memory", ENOMEM},
+	{"Permission denied", EACCES},
+	{"Bad address", EFAULT},
+	{"Block device required", ENOTBLK},
+	{"Device or resource busy", EBUSY},
+	{"File exists", EEXIST},
+	{"Invalid cross-device link", EXDEV},
+	{"No such device", ENODEV},
+	{"Not a directory", ENOTDIR},
+	{"Is a directory", EISDIR},
+	{"Invalid argument", EINVAL},
+	{"Too many open files in system", ENFILE},
+	{"Too many open files", EMFILE},
+	{"Text file busy", ETXTBSY},
+	{"File too large", EFBIG},
+	{"No space left on device", ENOSPC},
+	{"Illegal seek", ESPIPE},
+	{"Read-only file system", EROFS},
+	{"Too many links", EMLINK},
+	{"Broken pipe", EPIPE},
+	{"Numerical argument out of domain", EDOM},
+	{"Numerical result out of range", ERANGE},
+	{"Resource deadlock avoided", EDEADLK},
+	{"File name too long", ENAMETOOLONG},
+	{"No locks available", ENOLCK},
+	{"Function not implemented", ENOSYS},
+	{"Directory not empty", ENOTEMPTY},
+	{"Too many levels of symbolic links", ELOOP},
+	{"No message of desired type", ENOMSG},
+	{"Identifier removed", EIDRM},
+	{"No data available", ENODATA},
+	{"Machine is not on the network", ENONET},
+	{"Package not installed", ENOPKG},
+	{"Object is remote", EREMOTE},
+	{"Link has been severed", ENOLINK},
+	{"Communication error on send", ECOMM},
+	{"Protocol error", EPROTO},
+	{"Bad message", EBADMSG},
+	{"File descriptor in bad state", EBADFD},
+	{"Streams pipe error", ESTRPIPE},
+	{"Too many users", EUSERS},
+	{"Socket operation on non-socket", ENOTSOCK},
+	{"Message too long", EMSGSIZE},
+	{"Protocol not available", ENOPROTOOPT},
+	{"Protocol not supported", EPROTONOSUPPORT},
+	{"Socket type not supported", ESOCKTNOSUPPORT},
+	{"Operation not supported", EOPNOTSUPP},
+	{"Protocol family not supported", EPFNOSUPPORT},
+	{"Network is down", ENETDOWN},
+	{"Network is unreachable", ENETUNREACH},
+	{"Network dropped connection on reset", ENETRESET},
+	{"Software caused connection abort", ECONNABORTED},
+	{"Connection reset by peer", ECONNRESET},
+	{"No buffer space available", ENOBUFS},
+	{"Transport endpoint is already connected", EISCONN},
+	{"Transport endpoint is not connected", ENOTCONN},
+	{"Cannot send after transport endpoint shutdown", ESHUTDOWN},
+	{"Connection timed out", ETIMEDOUT},
+	{"Connection refused", ECONNREFUSED},
+	{"Host is down", EHOSTDOWN},
+	{"No route to host", EHOSTUNREACH},
+	{"Operation already in progress", EALREADY},
+	{"Operation now in progress", EINPROGRESS},
+	{"Is a named type file", EISNAM},
+	{"Remote I/O error", EREMOTEIO},
+	{"Disk quota exceeded", EDQUOT},
+/* errors from fossil, vacfs, and u9fs */
+	{"fid unknown or out of range", EBADF},
+	{"permission denied", EACCES},
+	{"file does not exist", ENOENT},
+	{"authentication failed", ECONNREFUSED},
+	{"bad offset in directory read", ESPIPE},
+	{"bad use of fid", EBADF},
+	{"wstat can't convert between files and directories", EPERM},
+	{"directory is not empty", ENOTEMPTY},
+	{"file exists", EEXIST},
+	{"file already exists", EEXIST},
+	{"file or directory already exists", EEXIST},
+	{"fid already in use", EBADF},
+	{"file in use", ETXTBSY},
+	{"i/o error", EIO},
+	{"file already open for I/O", ETXTBSY},
+	{"illegal mode", EINVAL},
+	{"illegal name", ENAMETOOLONG},
+	{"not a directory", ENOTDIR},
+	{"not a member of proposed group", EPERM},
+	{"not owner", EACCES},
+	{"only owner can change group in wstat", EACCES},
+	{"read only file system", EROFS},
+	{"no access to special file", EPERM},
+	{"i/o count too large", EIO},
+	{"unknown group", EINVAL},
+	{"unknown user", EINVAL},
+	{"bogus wstat buffer", EPROTO},
+	{"exclusive use file already open", EAGAIN},
+	{"corrupted directory entry", EIO},
+	{"corrupted file entry", EIO},
+	{"corrupted block label", EIO},
+	{"corrupted meta data", EIO},
+	{"illegal offset", EINVAL},
+	{"illegal path element", ENOENT},
+	{"root of file system is corrupted", EIO},
+	{"corrupted super block", EIO},
+	{"protocol botch", EPROTO},
+	{"file system is full", ENOSPC},
+	{"file is in use", EAGAIN},
+	{"directory entry is not allocated", ENOENT},
+	{"file is read only", EROFS},
+	{"file has been removed", EIDRM},
+	{"only support truncation to zero length", EPERM},
+	{"cannot remove root", EPERM},
+	{"file too big", EFBIG},
+	{"venti i/o error", EIO},
+	/* these are not errors */
+	{"u9fs rhostsauth: no authentication required", 0},
+	{"u9fs authnone: no authentication required", 0},
+	{NULL, -1}
+};
+
+/**
+ * p9_error_init - preload mappings into hash list
+ *
+ */
+
+int p9_error_init(void)
+{
+	struct errormap *c;
+	int bucket;
+
+	/* initialize hash table */
+	for (bucket = 0; bucket < ERRHASHSZ; bucket++)
+		INIT_HLIST_HEAD(&hash_errmap[bucket]);
+
+	/* load initial error map into hash table */
+	for (c = errmap; c->name != NULL; c++) {
+		c->namelen = strlen(c->name);
+		bucket = jhash(c->name, c->namelen, 0) % ERRHASHSZ;
+		INIT_HLIST_NODE(&c->list);
+		hlist_add_head(&c->list, &hash_errmap[bucket]);
+	}
+
+	return 1;
+}
+EXPORT_SYMBOL(p9_error_init);
+
+/**
+ * errstr2errno - convert error string to error number
+ * @errstr: error string
+ * @len: length of error string
+ *
+ */
+
+int p9_errstr2errno(char *errstr, int len)
+{
+	int errno;
+	struct errormap *c;
+	int bucket;
+
+	errno = 0;
+	c = NULL;
+	bucket = jhash(errstr, len, 0) % ERRHASHSZ;
+	hlist_for_each_entry(c, &hash_errmap[bucket], list) {
+		if (c->namelen == len && !memcmp(c->name, errstr, len)) {
+			errno = c->val;
+			break;
+		}
+	}
+
+	if (errno == 0) {
+		/* TODO: if error isn't found, add it dynamically */
+		errstr[len] = 0;
+		pr_err("%s: server reported unknown error %s\n",
+		       __func__, errstr);
+		errno = ESERVERFAULT;
+	}
+
+	return -errno;
+}
+EXPORT_SYMBOL(p9_errstr2errno);
diff --git a/net/9p/mod.c b/net/9p/mod.c
new file mode 100644
index 00000000000..6ab36aea772
--- /dev/null
+++ b/net/9p/mod.c
@@ -0,0 +1,201 @@
+/*
+ *  net/9p/9p.c
+ *
+ *  9P entry point
+ *
+ *  Copyright (C) 2007 by Latchesar Ionkov <lucho@ionkov.net>
+ *  Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ *  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:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/moduleparam.h>
+#include <net/9p/9p.h>
+#include <linux/fs.h>
+#include <linux/parser.h>
+#include <net/9p/client.h>
+#include <net/9p/transport.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+
+#ifdef CONFIG_NET_9P_DEBUG
+unsigned int p9_debug_level = 0;	/* feature-rific global debug level  */
+EXPORT_SYMBOL(p9_debug_level);
+module_param_named(debug, p9_debug_level, uint, 0);
+MODULE_PARM_DESC(debug, "9P debugging level");
+
+void _p9_debug(enum p9_debug_flags level, const char *func,
+		const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+
+	if ((p9_debug_level & level) != level)
+		return;
+
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	if (level == P9_DEBUG_9P)
+		pr_notice("(%8.8d) %pV", task_pid_nr(current), &vaf);
+	else
+		pr_notice("-- %s (%d): %pV", func, task_pid_nr(current), &vaf);
+
+	va_end(args);
+}
+EXPORT_SYMBOL(_p9_debug);
+#endif
+
+/*
+ * Dynamic Transport Registration Routines
+ *
+ */
+
+static DEFINE_SPINLOCK(v9fs_trans_lock);
+static LIST_HEAD(v9fs_trans_list);
+
+/**
+ * v9fs_register_trans - register a new transport with 9p
+ * @m: structure describing the transport module and entry points
+ *
+ */
+void v9fs_register_trans(struct p9_trans_module *m)
+{
+	spin_lock(&v9fs_trans_lock);
+	list_add_tail(&m->list, &v9fs_trans_list);
+	spin_unlock(&v9fs_trans_lock);
+}
+EXPORT_SYMBOL(v9fs_register_trans);
+
+/**
+ * v9fs_unregister_trans - unregister a 9p transport
+ * @m: the transport to remove
+ *
+ */
+void v9fs_unregister_trans(struct p9_trans_module *m)
+{
+	spin_lock(&v9fs_trans_lock);
+	list_del_init(&m->list);
+	spin_unlock(&v9fs_trans_lock);
+}
+EXPORT_SYMBOL(v9fs_unregister_trans);
+
+/**
+ * v9fs_get_trans_by_name - get transport with the matching name
+ * @name: string identifying transport
+ *
+ */
+struct p9_trans_module *v9fs_get_trans_by_name(char *s)
+{
+	struct p9_trans_module *t, *found = NULL;
+
+	spin_lock(&v9fs_trans_lock);
+
+	list_for_each_entry(t, &v9fs_trans_list, list)
+		if (strcmp(t->name, s) == 0 &&
+		    try_module_get(t->owner)) {
+			found = t;
+			break;
+		}
+
+	spin_unlock(&v9fs_trans_lock);
+	return found;
+}
+EXPORT_SYMBOL(v9fs_get_trans_by_name);
+
+/**
+ * v9fs_get_default_trans - get the default transport
+ *
+ */
+
+struct p9_trans_module *v9fs_get_default_trans(void)
+{
+	struct p9_trans_module *t, *found = NULL;
+
+	spin_lock(&v9fs_trans_lock);
+
+	list_for_each_entry(t, &v9fs_trans_list, list)
+		if (t->def && try_module_get(t->owner)) {
+			found = t;
+			break;
+		}
+
+	if (!found)
+		list_for_each_entry(t, &v9fs_trans_list, list)
+			if (try_module_get(t->owner)) {
+				found = t;
+				break;
+			}
+
+	spin_unlock(&v9fs_trans_lock);
+	return found;
+}
+EXPORT_SYMBOL(v9fs_get_default_trans);
+
+/**
+ * v9fs_put_trans - put trans
+ * @m: transport to put
+ *
+ */
+void v9fs_put_trans(struct p9_trans_module *m)
+{
+	if (m)
+		module_put(m->owner);
+}
+
+/**
+ * init_p9 - Initialize module
+ *
+ */
+static int __init init_p9(void)
+{
+	int ret = 0;
+
+	p9_error_init();
+	pr_info("Installing 9P2000 support\n");
+	p9_trans_fd_init();
+
+	return ret;
+}
+
+/**
+ * exit_p9 - shutdown module
+ *
+ */
+
+static void __exit exit_p9(void)
+{
+	pr_info("Unloading 9P2000 support\n");
+
+	p9_trans_fd_exit();
+}
+
+module_init(init_p9)
+module_exit(exit_p9)
+
+MODULE_AUTHOR("Latchesar Ionkov <lucho@ionkov.net>");
+MODULE_AUTHOR("Eric Van Hensbergen <ericvh@gmail.com>");
+MODULE_AUTHOR("Ron Minnich <rminnich@lanl.gov>");
+MODULE_LICENSE("GPL");
diff --git a/net/9p/protocol.c b/net/9p/protocol.c
new file mode 100644
index 00000000000..ab9127ec5b7
--- /dev/null
+++ b/net/9p/protocol.c
@@ -0,0 +1,636 @@
+/*
+ * net/9p/protocol.c
+ *
+ * 9P Protocol Support Code
+ *
+ *  Copyright (C) 2008 by Eric Van Hensbergen <ericvh@gmail.com>
+ *
+ *  Base on code from Anthony Liguori <aliguori@us.ibm.com>
+ *  Copyright (C) 2008 by IBM, Corp.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  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:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/uaccess.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/stddef.h>
+#include <linux/types.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+#include "protocol.h"
+
+#include <trace/events/9p.h>
+
+static int
+p9pdu_writef(struct p9_fcall *pdu, int proto_version, const char *fmt, ...);
+
+void p9stat_free(struct p9_wstat *stbuf)
+{
+	kfree(stbuf->name);
+	kfree(stbuf->uid);
+	kfree(stbuf->gid);
+	kfree(stbuf->muid);
+	kfree(stbuf->extension);
+}
+EXPORT_SYMBOL(p9stat_free);
+
+size_t pdu_read(struct p9_fcall *pdu, void *data, size_t size)
+{
+	size_t len = min(pdu->size - pdu->offset, size);
+	memcpy(data, &pdu->sdata[pdu->offset], len);
+	pdu->offset += len;
+	return size - len;
+}
+
+static size_t pdu_write(struct p9_fcall *pdu, const void *data, size_t size)
+{
+	size_t len = min(pdu->capacity - pdu->size, size);
+	memcpy(&pdu->sdata[pdu->size], data, len);
+	pdu->size += len;
+	return size - len;
+}
+
+static size_t
+pdu_write_u(struct p9_fcall *pdu, const char __user *udata, size_t size)
+{
+	size_t len = min(pdu->capacity - pdu->size, size);
+	if (copy_from_user(&pdu->sdata[pdu->size], udata, len))
+		len = 0;
+
+	pdu->size += len;
+	return size - len;
+}
+
+/*
+	b - int8_t
+	w - int16_t
+	d - int32_t
+	q - int64_t
+	s - string
+	u - numeric uid
+	g - numeric gid
+	S - stat
+	Q - qid
+	D - data blob (int32_t size followed by void *, results are not freed)
+	T - array of strings (int16_t count, followed by strings)
+	R - array of qids (int16_t count, followed by qids)
+	A - stat for 9p2000.L (p9_stat_dotl)
+	? - if optional = 1, continue parsing
+*/
+
+static int
+p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt,
+	va_list ap)
+{
+	const char *ptr;
+	int errcode = 0;
+
+	for (ptr = fmt; *ptr; ptr++) {
+		switch (*ptr) {
+		case 'b':{
+				int8_t *val = va_arg(ap, int8_t *);
+				if (pdu_read(pdu, val, sizeof(*val))) {
+					errcode = -EFAULT;
+					break;
+				}
+			}
+			break;
+		case 'w':{
+				int16_t *val = va_arg(ap, int16_t *);
+				__le16 le_val;
+				if (pdu_read(pdu, &le_val, sizeof(le_val))) {
+					errcode = -EFAULT;
+					break;
+				}
+				*val = le16_to_cpu(le_val);
+			}
+			break;
+		case 'd':{
+				int32_t *val = va_arg(ap, int32_t *);
+				__le32 le_val;
+				if (pdu_read(pdu, &le_val, sizeof(le_val))) {
+					errcode = -EFAULT;
+					break;
+				}
+				*val = le32_to_cpu(le_val);
+			}
+			break;
+		case 'q':{
+				int64_t *val = va_arg(ap, int64_t *);
+				__le64 le_val;
+				if (pdu_read(pdu, &le_val, sizeof(le_val))) {
+					errcode = -EFAULT;
+					break;
+				}
+				*val = le64_to_cpu(le_val);
+			}
+			break;
+		case 's':{
+				char **sptr = va_arg(ap, char **);
+				uint16_t len;
+
+				errcode = p9pdu_readf(pdu, proto_version,
+								"w", &len);
+				if (errcode)
+					break;
+
+				*sptr = kmalloc(len + 1, GFP_NOFS);
+				if (*sptr == NULL) {
+					errcode = -EFAULT;
+					break;
+				}
+				if (pdu_read(pdu, *sptr, len)) {
+					errcode = -EFAULT;
+					kfree(*sptr);
+					*sptr = NULL;
+				} else
+					(*sptr)[len] = 0;
+			}
+			break;
+		case 'u': {
+				kuid_t *uid = va_arg(ap, kuid_t *);
+				__le32 le_val;
+				if (pdu_read(pdu, &le_val, sizeof(le_val))) {
+					errcode = -EFAULT;
+					break;
+				}
+				*uid = make_kuid(&init_user_ns,
+						 le32_to_cpu(le_val));
+			} break;
+		case 'g': {
+				kgid_t *gid = va_arg(ap, kgid_t *);
+				__le32 le_val;
+				if (pdu_read(pdu, &le_val, sizeof(le_val))) {
+					errcode = -EFAULT;
+					break;
+				}
+				*gid = make_kgid(&init_user_ns,
+						 le32_to_cpu(le_val));
+			} break;
+		case 'Q':{
+				struct p9_qid *qid =
+				    va_arg(ap, struct p9_qid *);
+
+				errcode = p9pdu_readf(pdu, proto_version, "bdq",
+						      &qid->type, &qid->version,
+						      &qid->path);
+			}
+			break;
+		case 'S':{
+				struct p9_wstat *stbuf =
+				    va_arg(ap, struct p9_wstat *);
+
+				memset(stbuf, 0, sizeof(struct p9_wstat));
+				stbuf->n_uid = stbuf->n_muid = INVALID_UID;
+				stbuf->n_gid = INVALID_GID;
+
+				errcode =
+				    p9pdu_readf(pdu, proto_version,
+						"wwdQdddqssss?sugu",
+						&stbuf->size, &stbuf->type,
+						&stbuf->dev, &stbuf->qid,
+						&stbuf->mode, &stbuf->atime,
+						&stbuf->mtime, &stbuf->length,
+						&stbuf->name, &stbuf->uid,
+						&stbuf->gid, &stbuf->muid,
+						&stbuf->extension,
+						&stbuf->n_uid, &stbuf->n_gid,
+						&stbuf->n_muid);
+				if (errcode)
+					p9stat_free(stbuf);
+			}
+			break;
+		case 'D':{
+				uint32_t *count = va_arg(ap, uint32_t *);
+				void **data = va_arg(ap, void **);
+
+				errcode =
+				    p9pdu_readf(pdu, proto_version, "d", count);
+				if (!errcode) {
+					*count =
+					    min_t(uint32_t, *count,
+						  pdu->size - pdu->offset);
+					*data = &pdu->sdata[pdu->offset];
+				}
+			}
+			break;
+		case 'T':{
+				uint16_t *nwname = va_arg(ap, uint16_t *);
+				char ***wnames = va_arg(ap, char ***);
+
+				errcode = p9pdu_readf(pdu, proto_version,
+								"w", nwname);
+				if (!errcode) {
+					*wnames =
+					    kmalloc(sizeof(char *) * *nwname,
+						    GFP_NOFS);
+					if (!*wnames)
+						errcode = -ENOMEM;
+				}
+
+				if (!errcode) {
+					int i;
+
+					for (i = 0; i < *nwname; i++) {
+						errcode =
+						    p9pdu_readf(pdu,
+								proto_version,
+								"s",
+								&(*wnames)[i]);
+						if (errcode)
+							break;
+					}
+				}
+
+				if (errcode) {
+					if (*wnames) {
+						int i;
+
+						for (i = 0; i < *nwname; i++)
+							kfree((*wnames)[i]);
+					}
+					kfree(*wnames);
+					*wnames = NULL;
+				}
+			}
+			break;
+		case 'R':{
+				int16_t *nwqid = va_arg(ap, int16_t *);
+				struct p9_qid **wqids =
+				    va_arg(ap, struct p9_qid **);
+
+				*wqids = NULL;
+
+				errcode =
+				    p9pdu_readf(pdu, proto_version, "w", nwqid);
+				if (!errcode) {
+					*wqids =
+					    kmalloc(*nwqid *
+						    sizeof(struct p9_qid),
+						    GFP_NOFS);
+					if (*wqids == NULL)
+						errcode = -ENOMEM;
+				}
+
+				if (!errcode) {
+					int i;
+
+					for (i = 0; i < *nwqid; i++) {
+						errcode =
+						    p9pdu_readf(pdu,
+								proto_version,
+								"Q",
+								&(*wqids)[i]);
+						if (errcode)
+							break;
+					}
+				}
+
+				if (errcode) {
+					kfree(*wqids);
+					*wqids = NULL;
+				}
+			}
+			break;
+		case 'A': {
+				struct p9_stat_dotl *stbuf =
+				    va_arg(ap, struct p9_stat_dotl *);
+
+				memset(stbuf, 0, sizeof(struct p9_stat_dotl));
+				errcode =
+				    p9pdu_readf(pdu, proto_version,
+					"qQdugqqqqqqqqqqqqqqq",
+					&stbuf->st_result_mask,
+					&stbuf->qid,
+					&stbuf->st_mode,
+					&stbuf->st_uid, &stbuf->st_gid,
+					&stbuf->st_nlink,
+					&stbuf->st_rdev, &stbuf->st_size,
+					&stbuf->st_blksize, &stbuf->st_blocks,
+					&stbuf->st_atime_sec,
+					&stbuf->st_atime_nsec,
+					&stbuf->st_mtime_sec,
+					&stbuf->st_mtime_nsec,
+					&stbuf->st_ctime_sec,
+					&stbuf->st_ctime_nsec,
+					&stbuf->st_btime_sec,
+					&stbuf->st_btime_nsec,
+					&stbuf->st_gen,
+					&stbuf->st_data_version);
+			}
+			break;
+		case '?':
+			if ((proto_version != p9_proto_2000u) &&
+				(proto_version != p9_proto_2000L))
+				return 0;
+			break;
+		default:
+			BUG();
+			break;
+		}
+
+		if (errcode)
+			break;
+	}
+
+	return errcode;
+}
+
+int
+p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt,
+	va_list ap)
+{
+	const char *ptr;
+	int errcode = 0;
+
+	for (ptr = fmt; *ptr; ptr++) {
+		switch (*ptr) {
+		case 'b':{
+				int8_t val = va_arg(ap, int);
+				if (pdu_write(pdu, &val, sizeof(val)))
+					errcode = -EFAULT;
+			}
+			break;
+		case 'w':{
+				__le16 val = cpu_to_le16(va_arg(ap, int));
+				if (pdu_write(pdu, &val, sizeof(val)))
+					errcode = -EFAULT;
+			}
+			break;
+		case 'd':{
+				__le32 val = cpu_to_le32(va_arg(ap, int32_t));
+				if (pdu_write(pdu, &val, sizeof(val)))
+					errcode = -EFAULT;
+			}
+			break;
+		case 'q':{
+				__le64 val = cpu_to_le64(va_arg(ap, int64_t));
+				if (pdu_write(pdu, &val, sizeof(val)))
+					errcode = -EFAULT;
+			}
+			break;
+		case 's':{
+				const char *sptr = va_arg(ap, const char *);
+				uint16_t len = 0;
+				if (sptr)
+					len = min_t(size_t, strlen(sptr),
+								USHRT_MAX);
+
+				errcode = p9pdu_writef(pdu, proto_version,
+								"w", len);
+				if (!errcode && pdu_write(pdu, sptr, len))
+					errcode = -EFAULT;
+			}
+			break;
+		case 'u': {
+				kuid_t uid = va_arg(ap, kuid_t);
+				__le32 val = cpu_to_le32(
+						from_kuid(&init_user_ns, uid));
+				if (pdu_write(pdu, &val, sizeof(val)))
+					errcode = -EFAULT;
+			} break;
+		case 'g': {
+				kgid_t gid = va_arg(ap, kgid_t);
+				__le32 val = cpu_to_le32(
+						from_kgid(&init_user_ns, gid));
+				if (pdu_write(pdu, &val, sizeof(val)))
+					errcode = -EFAULT;
+			} break;
+		case 'Q':{
+				const struct p9_qid *qid =
+				    va_arg(ap, const struct p9_qid *);
+				errcode =
+				    p9pdu_writef(pdu, proto_version, "bdq",
+						 qid->type, qid->version,
+						 qid->path);
+			} break;
+		case 'S':{
+				const struct p9_wstat *stbuf =
+				    va_arg(ap, const struct p9_wstat *);
+				errcode =
+				    p9pdu_writef(pdu, proto_version,
+						 "wwdQdddqssss?sugu",
+						 stbuf->size, stbuf->type,
+						 stbuf->dev, &stbuf->qid,
+						 stbuf->mode, stbuf->atime,
+						 stbuf->mtime, stbuf->length,
+						 stbuf->name, stbuf->uid,
+						 stbuf->gid, stbuf->muid,
+						 stbuf->extension, stbuf->n_uid,
+						 stbuf->n_gid, stbuf->n_muid);
+			} break;
+		case 'D':{
+				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 *);
+				errcode = p9pdu_writef(pdu, proto_version, "d",
+									count);
+				if (!errcode && pdu_write_u(pdu, udata, count))
+					errcode = -EFAULT;
+			}
+			break;
+		case 'T':{
+				uint16_t nwname = va_arg(ap, int);
+				const char **wnames = va_arg(ap, const char **);
+
+				errcode = p9pdu_writef(pdu, proto_version, "w",
+									nwname);
+				if (!errcode) {
+					int i;
+
+					for (i = 0; i < nwname; i++) {
+						errcode =
+						    p9pdu_writef(pdu,
+								proto_version,
+								 "s",
+								 wnames[i]);
+						if (errcode)
+							break;
+					}
+				}
+			}
+			break;
+		case 'R':{
+				int16_t nwqid = va_arg(ap, int);
+				struct p9_qid *wqids =
+				    va_arg(ap, struct p9_qid *);
+
+				errcode = p9pdu_writef(pdu, proto_version, "w",
+									nwqid);
+				if (!errcode) {
+					int i;
+
+					for (i = 0; i < nwqid; i++) {
+						errcode =
+						    p9pdu_writef(pdu,
+								proto_version,
+								 "Q",
+								 &wqids[i]);
+						if (errcode)
+							break;
+					}
+				}
+			}
+			break;
+		case 'I':{
+				struct p9_iattr_dotl *p9attr = va_arg(ap,
+							struct p9_iattr_dotl *);
+
+				errcode = p9pdu_writef(pdu, proto_version,
+							"ddugqqqqq",
+							p9attr->valid,
+							p9attr->mode,
+							p9attr->uid,
+							p9attr->gid,
+							p9attr->size,
+							p9attr->atime_sec,
+							p9attr->atime_nsec,
+							p9attr->mtime_sec,
+							p9attr->mtime_nsec);
+			}
+			break;
+		case '?':
+			if ((proto_version != p9_proto_2000u) &&
+				(proto_version != p9_proto_2000L))
+				return 0;
+			break;
+		default:
+			BUG();
+			break;
+		}
+
+		if (errcode)
+			break;
+	}
+
+	return errcode;
+}
+
+int p9pdu_readf(struct p9_fcall *pdu, int proto_version, const char *fmt, ...)
+{
+	va_list ap;
+	int ret;
+
+	va_start(ap, fmt);
+	ret = p9pdu_vreadf(pdu, proto_version, fmt, ap);
+	va_end(ap);
+
+	return ret;
+}
+
+static int
+p9pdu_writef(struct p9_fcall *pdu, int proto_version, const char *fmt, ...)
+{
+	va_list ap;
+	int ret;
+
+	va_start(ap, fmt);
+	ret = p9pdu_vwritef(pdu, proto_version, fmt, ap);
+	va_end(ap);
+
+	return ret;
+}
+
+int p9stat_read(struct p9_client *clnt, char *buf, int len, struct p9_wstat *st)
+{
+	struct p9_fcall fake_pdu;
+	int ret;
+
+	fake_pdu.size = len;
+	fake_pdu.capacity = len;
+	fake_pdu.sdata = buf;
+	fake_pdu.offset = 0;
+
+	ret = p9pdu_readf(&fake_pdu, clnt->proto_version, "S", st);
+	if (ret) {
+		p9_debug(P9_DEBUG_9P, "<<< p9stat_read failed: %d\n", ret);
+		trace_9p_protocol_dump(clnt, &fake_pdu);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(p9stat_read);
+
+int p9pdu_prepare(struct p9_fcall *pdu, int16_t tag, int8_t type)
+{
+	pdu->id = type;
+	return p9pdu_writef(pdu, 0, "dbw", 0, type, tag);
+}
+
+int p9pdu_finalize(struct p9_client *clnt, struct p9_fcall *pdu)
+{
+	int size = pdu->size;
+	int err;
+
+	pdu->size = 0;
+	err = p9pdu_writef(pdu, 0, "d", size);
+	pdu->size = size;
+
+	trace_9p_protocol_dump(clnt, pdu);
+	p9_debug(P9_DEBUG_9P, ">>> size=%d type: %d tag: %d\n",
+		 pdu->size, pdu->id, pdu->tag);
+
+	return err;
+}
+
+void p9pdu_reset(struct p9_fcall *pdu)
+{
+	pdu->offset = 0;
+	pdu->size = 0;
+}
+
+int p9dirent_read(struct p9_client *clnt, char *buf, int len,
+		  struct p9_dirent *dirent)
+{
+	struct p9_fcall fake_pdu;
+	int ret;
+	char *nameptr;
+
+	fake_pdu.size = len;
+	fake_pdu.capacity = len;
+	fake_pdu.sdata = buf;
+	fake_pdu.offset = 0;
+
+	ret = p9pdu_readf(&fake_pdu, clnt->proto_version, "Qqbs", &dirent->qid,
+			  &dirent->d_off, &dirent->d_type, &nameptr);
+	if (ret) {
+		p9_debug(P9_DEBUG_9P, "<<< p9dirent_read failed: %d\n", ret);
+		trace_9p_protocol_dump(clnt, &fake_pdu);
+		goto out;
+	}
+
+	strcpy(dirent->d_name, nameptr);
+	kfree(nameptr);
+
+out:
+	return fake_pdu.offset;
+}
+EXPORT_SYMBOL(p9dirent_read);
diff --git a/net/9p/protocol.h b/net/9p/protocol.h
new file mode 100644
index 00000000000..2cc525fa49f
--- /dev/null
+++ b/net/9p/protocol.h
@@ -0,0 +1,34 @@
+/*
+ * net/9p/protocol.h
+ *
+ * 9P Protocol Support Code
+ *
+ *  Copyright (C) 2008 by Eric Van Hensbergen <ericvh@gmail.com>
+ *
+ *  Base on code from Anthony Liguori <aliguori@us.ibm.com>
+ *  Copyright (C) 2008 by IBM, Corp.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  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:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+int p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt,
+								va_list ap);
+int p9pdu_readf(struct p9_fcall *pdu, int proto_version, const char *fmt, ...);
+int p9pdu_prepare(struct p9_fcall *pdu, int16_t tag, int8_t type);
+int p9pdu_finalize(struct p9_client *clnt, struct p9_fcall *pdu);
+void p9pdu_reset(struct p9_fcall *pdu);
+size_t pdu_read(struct p9_fcall *pdu, void *data, size_t size);
diff --git a/net/9p/trans_common.c b/net/9p/trans_common.c
new file mode 100644
index 00000000000..2ee3879161b
--- /dev/null
+++ b/net/9p/trans_common.c
@@ -0,0 +1,69 @@
+/*
+ * Copyright IBM Corporation, 2010
+ * Author Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+
+#include <linux/slab.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.
+ */
+void p9_release_pages(struct page **pages, int nr_pages)
+{
+	int i;
+
+	for (i = 0; i < nr_pages; i++)
+		if (pages[i])
+			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
new file mode 100644
index 00000000000..173bb550a9e
--- /dev/null
+++ b/net/9p/trans_common.h
@@ -0,0 +1,17 @@
+/*
+ * Copyright IBM Corporation, 2010
+ * Author Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+
+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
new file mode 100644
index 00000000000..80d08f6664c
--- /dev/null
+++ b/net/9p/trans_fd.c
@@ -0,0 +1,1118 @@
+/*
+ * linux/fs/9p/trans_fd.c
+ *
+ * Fd transport layer.  Includes deprecated socket layer.
+ *
+ *  Copyright (C) 2006 by Russ Cox <rsc@swtch.com>
+ *  Copyright (C) 2004-2005 by Latchesar Ionkov <lucho@ionkov.net>
+ *  Copyright (C) 2004-2008 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 1997-2002 by Ron Minnich <rminnich@sarnoff.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/in.h>
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/ipv6.h>
+#include <linux/kthread.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/un.h>
+#include <linux/uaccess.h>
+#include <linux/inet.h>
+#include <linux/idr.h>
+#include <linux/file.h>
+#include <linux/parser.h>
+#include <linux/slab.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+#include <net/9p/transport.h>
+
+#include <linux/syscalls.h> /* killme */
+
+#define P9_PORT 564
+#define MAX_SOCK_BUF (64*1024)
+#define MAXPOLLWADDR	2
+
+/**
+ * struct p9_fd_opts - per-transport options
+ * @rfd: file descriptor for reading (trans=fd)
+ * @wfd: file descriptor for writing (trans=fd)
+ * @port: port to connect to (trans=tcp)
+ *
+ */
+
+struct p9_fd_opts {
+	int rfd;
+	int wfd;
+	u16 port;
+	int privport;
+};
+
+/*
+  * Option Parsing (code inspired by NFS code)
+  *  - a little lazy - parse all fd-transport options
+  */
+
+enum {
+	/* Options that take integer arguments */
+	Opt_port, Opt_rfdno, Opt_wfdno, Opt_err,
+	/* Options that take no arguments */
+	Opt_privport,
+};
+
+static const match_table_t tokens = {
+	{Opt_port, "port=%u"},
+	{Opt_rfdno, "rfdno=%u"},
+	{Opt_wfdno, "wfdno=%u"},
+	{Opt_privport, "privport"},
+	{Opt_err, NULL},
+};
+
+enum {
+	Rworksched = 1,		/* read work scheduled or running */
+	Rpending = 2,		/* can read */
+	Wworksched = 4,		/* write work scheduled or running */
+	Wpending = 8,		/* can write */
+};
+
+struct p9_poll_wait {
+	struct p9_conn *conn;
+	wait_queue_t wait;
+	wait_queue_head_t *wait_addr;
+};
+
+/**
+ * struct p9_conn - fd mux connection state information
+ * @mux_list: list link for mux to manage multiple connections (?)
+ * @client: reference to client instance for this connection
+ * @err: error state
+ * @req_list: accounting for requests which have been sent
+ * @unsent_req_list: accounting for requests that haven't been sent
+ * @req: current request being processed (if any)
+ * @tmp_buf: temporary buffer to read in header
+ * @rsize: amount to read for current frame
+ * @rpos: read position in current frame
+ * @rbuf: current read buffer
+ * @wpos: write position for current frame
+ * @wsize: amount of data to write for current frame
+ * @wbuf: current write buffer
+ * @poll_pending_link: pending links to be polled per conn
+ * @poll_wait: array of wait_q's for various worker threads
+ * @pt: poll state
+ * @rq: current read work
+ * @wq: current write work
+ * @wsched: ????
+ *
+ */
+
+struct p9_conn {
+	struct list_head mux_list;
+	struct p9_client *client;
+	int err;
+	struct list_head req_list;
+	struct list_head unsent_req_list;
+	struct p9_req_t *req;
+	char tmp_buf[7];
+	int rsize;
+	int rpos;
+	char *rbuf;
+	int wpos;
+	int wsize;
+	char *wbuf;
+	struct list_head poll_pending_link;
+	struct p9_poll_wait poll_wait[MAXPOLLWADDR];
+	poll_table pt;
+	struct work_struct rq;
+	struct work_struct wq;
+	unsigned long wsched;
+};
+
+/**
+ * struct p9_trans_fd - transport state
+ * @rd: reference to file to read from
+ * @wr: reference of file to write to
+ * @conn: connection state reference
+ *
+ */
+
+struct p9_trans_fd {
+	struct file *rd;
+	struct file *wr;
+	struct p9_conn conn;
+};
+
+static void p9_poll_workfn(struct work_struct *work);
+
+static DEFINE_SPINLOCK(p9_poll_lock);
+static LIST_HEAD(p9_poll_pending_list);
+static DECLARE_WORK(p9_poll_work, p9_poll_workfn);
+
+static unsigned int p9_ipport_resv_min = P9_DEF_MIN_RESVPORT;
+static unsigned int p9_ipport_resv_max = P9_DEF_MAX_RESVPORT;
+
+static void p9_mux_poll_stop(struct p9_conn *m)
+{
+	unsigned long flags;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(m->poll_wait); i++) {
+		struct p9_poll_wait *pwait = &m->poll_wait[i];
+
+		if (pwait->wait_addr) {
+			remove_wait_queue(pwait->wait_addr, &pwait->wait);
+			pwait->wait_addr = NULL;
+		}
+	}
+
+	spin_lock_irqsave(&p9_poll_lock, flags);
+	list_del_init(&m->poll_pending_link);
+	spin_unlock_irqrestore(&p9_poll_lock, flags);
+}
+
+/**
+ * p9_conn_cancel - cancel all pending requests with error
+ * @m: mux data
+ * @err: error code
+ *
+ */
+
+static void p9_conn_cancel(struct p9_conn *m, int err)
+{
+	struct p9_req_t *req, *rtmp;
+	unsigned long flags;
+	LIST_HEAD(cancel_list);
+
+	p9_debug(P9_DEBUG_ERROR, "mux %p err %d\n", m, err);
+
+	spin_lock_irqsave(&m->client->lock, flags);
+
+	if (m->err) {
+		spin_unlock_irqrestore(&m->client->lock, flags);
+		return;
+	}
+
+	m->err = err;
+
+	list_for_each_entry_safe(req, rtmp, &m->req_list, req_list) {
+		list_move(&req->req_list, &cancel_list);
+	}
+	list_for_each_entry_safe(req, rtmp, &m->unsent_req_list, req_list) {
+		list_move(&req->req_list, &cancel_list);
+	}
+	spin_unlock_irqrestore(&m->client->lock, flags);
+
+	list_for_each_entry_safe(req, rtmp, &cancel_list, req_list) {
+		p9_debug(P9_DEBUG_ERROR, "call back req %p\n", req);
+		list_del(&req->req_list);
+		if (!req->t_err)
+			req->t_err = err;
+		p9_client_cb(m->client, req, REQ_STATUS_ERROR);
+	}
+}
+
+static int
+p9_fd_poll(struct p9_client *client, struct poll_table_struct *pt)
+{
+	int ret, n;
+	struct p9_trans_fd *ts = NULL;
+
+	if (client && client->status == Connected)
+		ts = client->trans;
+
+	if (!ts)
+		return -EREMOTEIO;
+
+	if (!ts->rd->f_op->poll)
+		return -EIO;
+
+	if (!ts->wr->f_op->poll)
+		return -EIO;
+
+	ret = ts->rd->f_op->poll(ts->rd, pt);
+	if (ret < 0)
+		return ret;
+
+	if (ts->rd != ts->wr) {
+		n = ts->wr->f_op->poll(ts->wr, pt);
+		if (n < 0)
+			return n;
+		ret = (ret & ~POLLOUT) | (n & ~POLLIN);
+	}
+
+	return ret;
+}
+
+/**
+ * p9_fd_read- read from a fd
+ * @client: client instance
+ * @v: buffer to receive data into
+ * @len: size of receive buffer
+ *
+ */
+
+static int p9_fd_read(struct p9_client *client, void *v, int len)
+{
+	int ret;
+	struct p9_trans_fd *ts = NULL;
+
+	if (client && client->status != Disconnected)
+		ts = client->trans;
+
+	if (!ts)
+		return -EREMOTEIO;
+
+	if (!(ts->rd->f_flags & O_NONBLOCK))
+		p9_debug(P9_DEBUG_ERROR, "blocking read ...\n");
+
+	ret = kernel_read(ts->rd, ts->rd->f_pos, v, len);
+	if (ret <= 0 && ret != -ERESTARTSYS && ret != -EAGAIN)
+		client->status = Disconnected;
+	return ret;
+}
+
+/**
+ * p9_read_work - called when there is some data to be read from a transport
+ * @work: container of work to be done
+ *
+ */
+
+static void p9_read_work(struct work_struct *work)
+{
+	int n, err;
+	struct p9_conn *m;
+	int status = REQ_STATUS_ERROR;
+
+	m = container_of(work, struct p9_conn, rq);
+
+	if (m->err < 0)
+		return;
+
+	p9_debug(P9_DEBUG_TRANS, "start mux %p pos %d\n", m, m->rpos);
+
+	if (!m->rbuf) {
+		m->rbuf = m->tmp_buf;
+		m->rpos = 0;
+		m->rsize = 7; /* start by reading header */
+	}
+
+	clear_bit(Rpending, &m->wsched);
+	p9_debug(P9_DEBUG_TRANS, "read mux %p pos %d size: %d = %d\n",
+		 m, m->rpos, m->rsize, m->rsize-m->rpos);
+	err = p9_fd_read(m->client, m->rbuf + m->rpos,
+						m->rsize - m->rpos);
+	p9_debug(P9_DEBUG_TRANS, "mux %p got %d bytes\n", m, err);
+	if (err == -EAGAIN) {
+		goto end_clear;
+	}
+
+	if (err <= 0)
+		goto error;
+
+	m->rpos += err;
+
+	if ((!m->req) && (m->rpos == m->rsize)) { /* header read in */
+		u16 tag;
+		p9_debug(P9_DEBUG_TRANS, "got new header\n");
+
+		n = le32_to_cpu(*(__le32 *) m->rbuf); /* read packet size */
+		if (n >= m->client->msize) {
+			p9_debug(P9_DEBUG_ERROR,
+				 "requested packet size too big: %d\n", n);
+			err = -EIO;
+			goto error;
+		}
+
+		tag = le16_to_cpu(*(__le16 *) (m->rbuf+5)); /* read tag */
+		p9_debug(P9_DEBUG_TRANS,
+			 "mux %p pkt: size: %d bytes tag: %d\n", m, n, tag);
+
+		m->req = p9_tag_lookup(m->client, tag);
+		if (!m->req || (m->req->status != REQ_STATUS_SENT)) {
+			p9_debug(P9_DEBUG_ERROR, "Unexpected packet tag %d\n",
+				 tag);
+			err = -EIO;
+			goto error;
+		}
+
+		if (m->req->rc == NULL) {
+			m->req->rc = kmalloc(sizeof(struct p9_fcall) +
+						m->client->msize, GFP_NOFS);
+			if (!m->req->rc) {
+				m->req = NULL;
+				err = -ENOMEM;
+				goto error;
+			}
+		}
+		m->rbuf = (char *)m->req->rc + sizeof(struct p9_fcall);
+		memcpy(m->rbuf, m->tmp_buf, m->rsize);
+		m->rsize = n;
+	}
+
+	/* not an else because some packets (like clunk) have no payload */
+	if ((m->req) && (m->rpos == m->rsize)) { /* packet is read in */
+		p9_debug(P9_DEBUG_TRANS, "got new packet\n");
+		spin_lock(&m->client->lock);
+		if (m->req->status != REQ_STATUS_ERROR)
+			status = REQ_STATUS_RCVD;
+		list_del(&m->req->req_list);
+		spin_unlock(&m->client->lock);
+		p9_client_cb(m->client, m->req, status);
+		m->rbuf = NULL;
+		m->rpos = 0;
+		m->rsize = 0;
+		m->req = NULL;
+	}
+
+end_clear:
+	clear_bit(Rworksched, &m->wsched);
+
+	if (!list_empty(&m->req_list)) {
+		if (test_and_clear_bit(Rpending, &m->wsched))
+			n = POLLIN;
+		else
+			n = p9_fd_poll(m->client, NULL);
+
+		if ((n & POLLIN) && !test_and_set_bit(Rworksched, &m->wsched)) {
+			p9_debug(P9_DEBUG_TRANS, "sched read work %p\n", m);
+			schedule_work(&m->rq);
+		}
+	}
+
+	return;
+error:
+	p9_conn_cancel(m, err);
+	clear_bit(Rworksched, &m->wsched);
+}
+
+/**
+ * p9_fd_write - write to a socket
+ * @client: client instance
+ * @v: buffer to send data from
+ * @len: size of send buffer
+ *
+ */
+
+static int p9_fd_write(struct p9_client *client, void *v, int len)
+{
+	int ret;
+	mm_segment_t oldfs;
+	struct p9_trans_fd *ts = NULL;
+
+	if (client && client->status != Disconnected)
+		ts = client->trans;
+
+	if (!ts)
+		return -EREMOTEIO;
+
+	if (!(ts->wr->f_flags & O_NONBLOCK))
+		p9_debug(P9_DEBUG_ERROR, "blocking write ...\n");
+
+	oldfs = get_fs();
+	set_fs(get_ds());
+	/* The cast to a user pointer is valid due to the set_fs() */
+	ret = vfs_write(ts->wr, (__force void __user *)v, len, &ts->wr->f_pos);
+	set_fs(oldfs);
+
+	if (ret <= 0 && ret != -ERESTARTSYS && ret != -EAGAIN)
+		client->status = Disconnected;
+	return ret;
+}
+
+/**
+ * p9_write_work - called when a transport can send some data
+ * @work: container for work to be done
+ *
+ */
+
+static void p9_write_work(struct work_struct *work)
+{
+	int n, err;
+	struct p9_conn *m;
+	struct p9_req_t *req;
+
+	m = container_of(work, struct p9_conn, wq);
+
+	if (m->err < 0) {
+		clear_bit(Wworksched, &m->wsched);
+		return;
+	}
+
+	if (!m->wsize) {
+		spin_lock(&m->client->lock);
+		if (list_empty(&m->unsent_req_list)) {
+			clear_bit(Wworksched, &m->wsched);
+			spin_unlock(&m->client->lock);
+			return;
+		}
+
+		req = list_entry(m->unsent_req_list.next, struct p9_req_t,
+			       req_list);
+		req->status = REQ_STATUS_SENT;
+		p9_debug(P9_DEBUG_TRANS, "move req %p\n", req);
+		list_move_tail(&req->req_list, &m->req_list);
+
+		m->wbuf = req->tc->sdata;
+		m->wsize = req->tc->size;
+		m->wpos = 0;
+		spin_unlock(&m->client->lock);
+	}
+
+	p9_debug(P9_DEBUG_TRANS, "mux %p pos %d size %d\n",
+		 m, m->wpos, m->wsize);
+	clear_bit(Wpending, &m->wsched);
+	err = p9_fd_write(m->client, m->wbuf + m->wpos, m->wsize - m->wpos);
+	p9_debug(P9_DEBUG_TRANS, "mux %p sent %d bytes\n", m, err);
+	if (err == -EAGAIN)
+		goto end_clear;
+
+
+	if (err < 0)
+		goto error;
+	else if (err == 0) {
+		err = -EREMOTEIO;
+		goto error;
+	}
+
+	m->wpos += err;
+	if (m->wpos == m->wsize)
+		m->wpos = m->wsize = 0;
+
+end_clear:
+	clear_bit(Wworksched, &m->wsched);
+
+	if (m->wsize || !list_empty(&m->unsent_req_list)) {
+		if (test_and_clear_bit(Wpending, &m->wsched))
+			n = POLLOUT;
+		else
+			n = p9_fd_poll(m->client, NULL);
+
+		if ((n & POLLOUT) &&
+		   !test_and_set_bit(Wworksched, &m->wsched)) {
+			p9_debug(P9_DEBUG_TRANS, "sched write work %p\n", m);
+			schedule_work(&m->wq);
+		}
+	}
+
+	return;
+
+error:
+	p9_conn_cancel(m, err);
+	clear_bit(Wworksched, &m->wsched);
+}
+
+static int p9_pollwake(wait_queue_t *wait, unsigned int mode, int sync, void *key)
+{
+	struct p9_poll_wait *pwait =
+		container_of(wait, struct p9_poll_wait, wait);
+	struct p9_conn *m = pwait->conn;
+	unsigned long flags;
+
+	spin_lock_irqsave(&p9_poll_lock, flags);
+	if (list_empty(&m->poll_pending_link))
+		list_add_tail(&m->poll_pending_link, &p9_poll_pending_list);
+	spin_unlock_irqrestore(&p9_poll_lock, flags);
+
+	schedule_work(&p9_poll_work);
+	return 1;
+}
+
+/**
+ * p9_pollwait - add poll task to the wait queue
+ * @filp: file pointer being polled
+ * @wait_address: wait_q to block on
+ * @p: poll state
+ *
+ * called by files poll operation to add v9fs-poll task to files wait queue
+ */
+
+static void
+p9_pollwait(struct file *filp, wait_queue_head_t *wait_address, poll_table *p)
+{
+	struct p9_conn *m = container_of(p, struct p9_conn, pt);
+	struct p9_poll_wait *pwait = NULL;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(m->poll_wait); i++) {
+		if (m->poll_wait[i].wait_addr == NULL) {
+			pwait = &m->poll_wait[i];
+			break;
+		}
+	}
+
+	if (!pwait) {
+		p9_debug(P9_DEBUG_ERROR, "not enough wait_address slots\n");
+		return;
+	}
+
+	pwait->conn = m;
+	pwait->wait_addr = wait_address;
+	init_waitqueue_func_entry(&pwait->wait, p9_pollwake);
+	add_wait_queue(wait_address, &pwait->wait);
+}
+
+/**
+ * p9_conn_create - initialize the per-session mux data
+ * @client: client instance
+ *
+ * Note: Creates the polling task if this is the first session.
+ */
+
+static void p9_conn_create(struct p9_client *client)
+{
+	int n;
+	struct p9_trans_fd *ts = client->trans;
+	struct p9_conn *m = &ts->conn;
+
+	p9_debug(P9_DEBUG_TRANS, "client %p msize %d\n", client, client->msize);
+
+	INIT_LIST_HEAD(&m->mux_list);
+	m->client = client;
+
+	INIT_LIST_HEAD(&m->req_list);
+	INIT_LIST_HEAD(&m->unsent_req_list);
+	INIT_WORK(&m->rq, p9_read_work);
+	INIT_WORK(&m->wq, p9_write_work);
+	INIT_LIST_HEAD(&m->poll_pending_link);
+	init_poll_funcptr(&m->pt, p9_pollwait);
+
+	n = p9_fd_poll(client, &m->pt);
+	if (n & POLLIN) {
+		p9_debug(P9_DEBUG_TRANS, "mux %p can read\n", m);
+		set_bit(Rpending, &m->wsched);
+	}
+
+	if (n & POLLOUT) {
+		p9_debug(P9_DEBUG_TRANS, "mux %p can write\n", m);
+		set_bit(Wpending, &m->wsched);
+	}
+}
+
+/**
+ * p9_poll_mux - polls a mux and schedules read or write works if necessary
+ * @m: connection to poll
+ *
+ */
+
+static void p9_poll_mux(struct p9_conn *m)
+{
+	int n;
+
+	if (m->err < 0)
+		return;
+
+	n = p9_fd_poll(m->client, NULL);
+	if (n < 0 || n & (POLLERR | POLLHUP | POLLNVAL)) {
+		p9_debug(P9_DEBUG_TRANS, "error mux %p err %d\n", m, n);
+		if (n >= 0)
+			n = -ECONNRESET;
+		p9_conn_cancel(m, n);
+	}
+
+	if (n & POLLIN) {
+		set_bit(Rpending, &m->wsched);
+		p9_debug(P9_DEBUG_TRANS, "mux %p can read\n", m);
+		if (!test_and_set_bit(Rworksched, &m->wsched)) {
+			p9_debug(P9_DEBUG_TRANS, "sched read work %p\n", m);
+			schedule_work(&m->rq);
+		}
+	}
+
+	if (n & POLLOUT) {
+		set_bit(Wpending, &m->wsched);
+		p9_debug(P9_DEBUG_TRANS, "mux %p can write\n", m);
+		if ((m->wsize || !list_empty(&m->unsent_req_list)) &&
+		    !test_and_set_bit(Wworksched, &m->wsched)) {
+			p9_debug(P9_DEBUG_TRANS, "sched write work %p\n", m);
+			schedule_work(&m->wq);
+		}
+	}
+}
+
+/**
+ * p9_fd_request - send 9P request
+ * The function can sleep until the request is scheduled for sending.
+ * The function can be interrupted. Return from the function is not
+ * a guarantee that the request is sent successfully.
+ *
+ * @client: client instance
+ * @req: request to be sent
+ *
+ */
+
+static int p9_fd_request(struct p9_client *client, struct p9_req_t *req)
+{
+	int n;
+	struct p9_trans_fd *ts = client->trans;
+	struct p9_conn *m = &ts->conn;
+
+	p9_debug(P9_DEBUG_TRANS, "mux %p task %p tcall %p id %d\n",
+		 m, current, req->tc, req->tc->id);
+	if (m->err < 0)
+		return m->err;
+
+	spin_lock(&client->lock);
+	req->status = REQ_STATUS_UNSENT;
+	list_add_tail(&req->req_list, &m->unsent_req_list);
+	spin_unlock(&client->lock);
+
+	if (test_and_clear_bit(Wpending, &m->wsched))
+		n = POLLOUT;
+	else
+		n = p9_fd_poll(m->client, NULL);
+
+	if (n & POLLOUT && !test_and_set_bit(Wworksched, &m->wsched))
+		schedule_work(&m->wq);
+
+	return 0;
+}
+
+static int p9_fd_cancel(struct p9_client *client, struct p9_req_t *req)
+{
+	int ret = 1;
+
+	p9_debug(P9_DEBUG_TRANS, "client %p req %p\n", client, req);
+
+	spin_lock(&client->lock);
+
+	if (req->status == REQ_STATUS_UNSENT) {
+		list_del(&req->req_list);
+		req->status = REQ_STATUS_FLSHD;
+		ret = 0;
+	}
+	spin_unlock(&client->lock);
+
+	return ret;
+}
+
+static int p9_fd_cancelled(struct p9_client *client, struct p9_req_t *req)
+{
+	p9_debug(P9_DEBUG_TRANS, "client %p req %p\n", client, req);
+
+	/* we haven't received a response for oldreq,
+	 * remove it from the list.
+	 */
+	spin_lock(&client->lock);
+	list_del(&req->req_list);
+	spin_unlock(&client->lock);
+
+	return 0;
+}
+
+/**
+ * parse_opts - parse mount options into p9_fd_opts structure
+ * @params: options string passed from mount
+ * @opts: fd transport-specific structure to parse options into
+ *
+ * Returns 0 upon success, -ERRNO upon failure
+ */
+
+static int parse_opts(char *params, struct p9_fd_opts *opts)
+{
+	char *p;
+	substring_t args[MAX_OPT_ARGS];
+	int option;
+	char *options, *tmp_options;
+
+	opts->port = P9_PORT;
+	opts->rfd = ~0;
+	opts->wfd = ~0;
+
+	if (!params)
+		return 0;
+
+	tmp_options = kstrdup(params, GFP_KERNEL);
+	if (!tmp_options) {
+		p9_debug(P9_DEBUG_ERROR,
+			 "failed to allocate copy of option string\n");
+		return -ENOMEM;
+	}
+	options = tmp_options;
+
+	while ((p = strsep(&options, ",")) != NULL) {
+		int token;
+		int r;
+		if (!*p)
+			continue;
+		token = match_token(p, tokens, args);
+		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:
+			opts->port = option;
+			break;
+		case Opt_rfdno:
+			opts->rfd = option;
+			break;
+		case Opt_wfdno:
+			opts->wfd = option;
+			break;
+		case Opt_privport:
+			opts->privport = 1;
+			break;
+		default:
+			continue;
+		}
+	}
+
+	kfree(tmp_options);
+	return 0;
+}
+
+static int p9_fd_open(struct p9_client *client, int rfd, int wfd)
+{
+	struct p9_trans_fd *ts = kzalloc(sizeof(struct p9_trans_fd),
+					   GFP_KERNEL);
+	if (!ts)
+		return -ENOMEM;
+
+	ts->rd = fget(rfd);
+	ts->wr = fget(wfd);
+	if (!ts->rd || !ts->wr) {
+		if (ts->rd)
+			fput(ts->rd);
+		if (ts->wr)
+			fput(ts->wr);
+		kfree(ts);
+		return -EIO;
+	}
+
+	client->trans = ts;
+	client->status = Connected;
+
+	return 0;
+}
+
+static int p9_socket_open(struct p9_client *client, struct socket *csocket)
+{
+	struct p9_trans_fd *p;
+	struct file *file;
+
+	p = kzalloc(sizeof(struct p9_trans_fd), GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	csocket->sk->sk_allocation = GFP_NOIO;
+	file = sock_alloc_file(csocket, 0, NULL);
+	if (IS_ERR(file)) {
+		pr_err("%s (%d): failed to map fd\n",
+		       __func__, task_pid_nr(current));
+		sock_release(csocket);
+		kfree(p);
+		return PTR_ERR(file);
+	}
+
+	get_file(file);
+	p->wr = p->rd = file;
+	client->trans = p;
+	client->status = Connected;
+
+	p->rd->f_flags |= O_NONBLOCK;
+
+	p9_conn_create(client);
+	return 0;
+}
+
+/**
+ * p9_mux_destroy - cancels all pending requests of mux
+ * @m: mux to destroy
+ *
+ */
+
+static void p9_conn_destroy(struct p9_conn *m)
+{
+	p9_debug(P9_DEBUG_TRANS, "mux %p prev %p next %p\n",
+		 m, m->mux_list.prev, m->mux_list.next);
+
+	p9_mux_poll_stop(m);
+	cancel_work_sync(&m->rq);
+	cancel_work_sync(&m->wq);
+
+	p9_conn_cancel(m, -ECONNRESET);
+
+	m->client = NULL;
+}
+
+/**
+ * p9_fd_close - shutdown file descriptor transport
+ * @client: client instance
+ *
+ */
+
+static void p9_fd_close(struct p9_client *client)
+{
+	struct p9_trans_fd *ts;
+
+	if (!client)
+		return;
+
+	ts = client->trans;
+	if (!ts)
+		return;
+
+	client->status = Disconnected;
+
+	p9_conn_destroy(&ts->conn);
+
+	if (ts->rd)
+		fput(ts->rd);
+	if (ts->wr)
+		fput(ts->wr);
+
+	kfree(ts);
+}
+
+/*
+ * stolen from NFS - maybe should be made a generic function?
+ */
+static inline int valid_ipaddr4(const char *buf)
+{
+	int rc, count, in[4];
+
+	rc = sscanf(buf, "%d.%d.%d.%d", &in[0], &in[1], &in[2], &in[3]);
+	if (rc != 4)
+		return -EINVAL;
+	for (count = 0; count < 4; count++) {
+		if (in[count] > 255)
+			return -EINVAL;
+	}
+	return 0;
+}
+
+static int p9_bind_privport(struct socket *sock)
+{
+	struct sockaddr_in cl;
+	int port, err = -EINVAL;
+
+	memset(&cl, 0, sizeof(cl));
+	cl.sin_family = AF_INET;
+	cl.sin_addr.s_addr = INADDR_ANY;
+	for (port = p9_ipport_resv_max; port >= p9_ipport_resv_min; port--) {
+		cl.sin_port = htons((ushort)port);
+		err = kernel_bind(sock, (struct sockaddr *)&cl, sizeof(cl));
+		if (err != -EADDRINUSE)
+			break;
+	}
+	return err;
+}
+
+
+static int
+p9_fd_create_tcp(struct p9_client *client, const char *addr, char *args)
+{
+	int err;
+	struct socket *csocket;
+	struct sockaddr_in sin_server;
+	struct p9_fd_opts opts;
+
+	err = parse_opts(args, &opts);
+	if (err < 0)
+		return err;
+
+	if (valid_ipaddr4(addr) < 0)
+		return -EINVAL;
+
+	csocket = NULL;
+
+	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,
+			    SOCK_STREAM, IPPROTO_TCP, &csocket, 1);
+	if (err) {
+		pr_err("%s (%d): problem creating socket\n",
+		       __func__, task_pid_nr(current));
+		return err;
+	}
+
+	if (opts.privport) {
+		err = p9_bind_privport(csocket);
+		if (err < 0) {
+			pr_err("%s (%d): problem binding to privport\n",
+			       __func__, task_pid_nr(current));
+			sock_release(csocket);
+			return err;
+		}
+	}
+
+	err = csocket->ops->connect(csocket,
+				    (struct sockaddr *)&sin_server,
+				    sizeof(struct sockaddr_in), 0);
+	if (err < 0) {
+		pr_err("%s (%d): problem connecting socket to %s\n",
+		       __func__, task_pid_nr(current), addr);
+		sock_release(csocket);
+		return err;
+	}
+
+	return p9_socket_open(client, csocket);
+}
+
+static int
+p9_fd_create_unix(struct p9_client *client, const char *addr, char *args)
+{
+	int err;
+	struct socket *csocket;
+	struct sockaddr_un sun_server;
+
+	csocket = NULL;
+
+	if (strlen(addr) >= UNIX_PATH_MAX) {
+		pr_err("%s (%d): address too long: %s\n",
+		       __func__, task_pid_nr(current), addr);
+		return -ENAMETOOLONG;
+	}
+
+	sun_server.sun_family = PF_UNIX;
+	strcpy(sun_server.sun_path, addr);
+	err = __sock_create(read_pnet(&current->nsproxy->net_ns), PF_UNIX,
+			    SOCK_STREAM, 0, &csocket, 1);
+	if (err < 0) {
+		pr_err("%s (%d): problem creating socket\n",
+		       __func__, task_pid_nr(current));
+
+		return err;
+	}
+	err = csocket->ops->connect(csocket, (struct sockaddr *)&sun_server,
+			sizeof(struct sockaddr_un) - 1, 0);
+	if (err < 0) {
+		pr_err("%s (%d): problem connecting socket: %s: %d\n",
+		       __func__, task_pid_nr(current), addr, err);
+		sock_release(csocket);
+		return err;
+	}
+
+	return p9_socket_open(client, csocket);
+}
+
+static int
+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);
+
+	if (opts.rfd == ~0 || opts.wfd == ~0) {
+		pr_err("Insufficient options for proto=fd\n");
+		return -ENOPROTOOPT;
+	}
+
+	err = p9_fd_open(client, opts.rfd, opts.wfd);
+	if (err < 0)
+		return err;
+
+	p = (struct p9_trans_fd *) client->trans;
+	p9_conn_create(client);
+
+	return 0;
+}
+
+static struct p9_trans_module p9_tcp_trans = {
+	.name = "tcp",
+	.maxsize = MAX_SOCK_BUF,
+	.def = 0,
+	.create = p9_fd_create_tcp,
+	.close = p9_fd_close,
+	.request = p9_fd_request,
+	.cancel = p9_fd_cancel,
+	.cancelled = p9_fd_cancelled,
+	.owner = THIS_MODULE,
+};
+
+static struct p9_trans_module p9_unix_trans = {
+	.name = "unix",
+	.maxsize = MAX_SOCK_BUF,
+	.def = 0,
+	.create = p9_fd_create_unix,
+	.close = p9_fd_close,
+	.request = p9_fd_request,
+	.cancel = p9_fd_cancel,
+	.cancelled = p9_fd_cancelled,
+	.owner = THIS_MODULE,
+};
+
+static struct p9_trans_module p9_fd_trans = {
+	.name = "fd",
+	.maxsize = MAX_SOCK_BUF,
+	.def = 0,
+	.create = p9_fd_create,
+	.close = p9_fd_close,
+	.request = p9_fd_request,
+	.cancel = p9_fd_cancel,
+	.cancelled = p9_fd_cancelled,
+	.owner = THIS_MODULE,
+};
+
+/**
+ * p9_poll_proc - poll worker thread
+ * @a: thread state and arguments
+ *
+ * polls all v9fs transports for new events and queues the appropriate
+ * work to the work queue
+ *
+ */
+
+static void p9_poll_workfn(struct work_struct *work)
+{
+	unsigned long flags;
+
+	p9_debug(P9_DEBUG_TRANS, "start %p\n", current);
+
+	spin_lock_irqsave(&p9_poll_lock, flags);
+	while (!list_empty(&p9_poll_pending_list)) {
+		struct p9_conn *conn = list_first_entry(&p9_poll_pending_list,
+							struct p9_conn,
+							poll_pending_link);
+		list_del_init(&conn->poll_pending_link);
+		spin_unlock_irqrestore(&p9_poll_lock, flags);
+
+		p9_poll_mux(conn);
+
+		spin_lock_irqsave(&p9_poll_lock, flags);
+	}
+	spin_unlock_irqrestore(&p9_poll_lock, flags);
+
+	p9_debug(P9_DEBUG_TRANS, "finish\n");
+}
+
+int p9_trans_fd_init(void)
+{
+	v9fs_register_trans(&p9_tcp_trans);
+	v9fs_register_trans(&p9_unix_trans);
+	v9fs_register_trans(&p9_fd_trans);
+
+	return 0;
+}
+
+void p9_trans_fd_exit(void)
+{
+	flush_work(&p9_poll_work);
+	v9fs_unregister_trans(&p9_tcp_trans);
+	v9fs_unregister_trans(&p9_unix_trans);
+	v9fs_unregister_trans(&p9_fd_trans);
+}
diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c
new file mode 100644
index 00000000000..14ad43b5cf8
--- /dev/null
+++ b/net/9p/trans_rdma.c
@@ -0,0 +1,765 @@
+/*
+ * linux/fs/9p/trans_rdma.c
+ *
+ * RDMA transport layer based on the trans_fd.c implementation.
+ *
+ *  Copyright (C) 2008 by Tom Tucker <tom@opengridcomputing.com>
+ *  Copyright (C) 2006 by Russ Cox <rsc@swtch.com>
+ *  Copyright (C) 2004-2005 by Latchesar Ionkov <lucho@ionkov.net>
+ *  Copyright (C) 2004-2008 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 1997-2002 by Ron Minnich <rminnich@sarnoff.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/in.h>
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/ipv6.h>
+#include <linux/kthread.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/un.h>
+#include <linux/uaccess.h>
+#include <linux/inet.h>
+#include <linux/idr.h>
+#include <linux/file.h>
+#include <linux/parser.h>
+#include <linux/semaphore.h>
+#include <linux/slab.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+#include <net/9p/transport.h>
+#include <rdma/ib_verbs.h>
+#include <rdma/rdma_cm.h>
+
+#define P9_PORT			5640
+#define P9_RDMA_SQ_DEPTH	32
+#define P9_RDMA_RQ_DEPTH	32
+#define P9_RDMA_SEND_SGE	4
+#define P9_RDMA_RECV_SGE	4
+#define P9_RDMA_IRD		0
+#define P9_RDMA_ORD		0
+#define P9_RDMA_TIMEOUT		30000		/* 30 seconds */
+#define P9_RDMA_MAXSIZE		(1024*1024)	/* 1MB */
+
+/**
+ * struct p9_trans_rdma - RDMA transport instance
+ *
+ * @state: tracks the transport state machine for connection setup and tear down
+ * @cm_id: The RDMA CM ID
+ * @pd: Protection Domain pointer
+ * @qp: Queue Pair pointer
+ * @cq: Completion Queue pointer
+ * @dm_mr: DMA Memory Region pointer
+ * @lkey: The local access only memory region key
+ * @timeout: Number of uSecs to wait for connection management events
+ * @sq_depth: The depth of the Send Queue
+ * @sq_sem: Semaphore for the SQ
+ * @rq_depth: The depth of the Receive Queue.
+ * @rq_sem: Semaphore for the RQ
+ * @excess_rc : Amount of posted Receive Contexts without a pending request.
+ *		See rdma_request()
+ * @addr: The remote peer's address
+ * @req_lock: Protects the active request list
+ * @cm_done: Completion event for connection management tracking
+ */
+struct p9_trans_rdma {
+	enum {
+		P9_RDMA_INIT,
+		P9_RDMA_ADDR_RESOLVED,
+		P9_RDMA_ROUTE_RESOLVED,
+		P9_RDMA_CONNECTED,
+		P9_RDMA_FLUSHING,
+		P9_RDMA_CLOSING,
+		P9_RDMA_CLOSED,
+	} state;
+	struct rdma_cm_id *cm_id;
+	struct ib_pd *pd;
+	struct ib_qp *qp;
+	struct ib_cq *cq;
+	struct ib_mr *dma_mr;
+	u32 lkey;
+	long timeout;
+	int sq_depth;
+	struct semaphore sq_sem;
+	int rq_depth;
+	struct semaphore rq_sem;
+	atomic_t excess_rc;
+	struct sockaddr_in addr;
+	spinlock_t req_lock;
+
+	struct completion cm_done;
+};
+
+/**
+ * p9_rdma_context - Keeps track of in-process WR
+ *
+ * @wc_op: The original WR op for when the CQE completes in error.
+ * @busa: Bus address to unmap when the WR completes
+ * @req: Keeps track of requests (send)
+ * @rc: Keepts track of replies (receive)
+ */
+struct p9_rdma_req;
+struct p9_rdma_context {
+	enum ib_wc_opcode wc_op;
+	dma_addr_t busa;
+	union {
+		struct p9_req_t *req;
+		struct p9_fcall *rc;
+	};
+};
+
+/**
+ * p9_rdma_opts - Collection of mount options
+ * @port: port of connection
+ * @sq_depth: The requested depth of the SQ. This really doesn't need
+ * to be any deeper than the number of threads used in the client
+ * @rq_depth: The depth of the RQ. Should be greater than or equal to SQ depth
+ * @timeout: Time to wait in msecs for CM events
+ */
+struct p9_rdma_opts {
+	short port;
+	int sq_depth;
+	int rq_depth;
+	long timeout;
+};
+
+/*
+ * Option Parsing (code inspired by NFS code)
+ */
+enum {
+	/* Options that take integer arguments */
+	Opt_port, Opt_rq_depth, Opt_sq_depth, Opt_timeout, Opt_err,
+};
+
+static match_table_t tokens = {
+	{Opt_port, "port=%u"},
+	{Opt_sq_depth, "sq=%u"},
+	{Opt_rq_depth, "rq=%u"},
+	{Opt_timeout, "timeout=%u"},
+	{Opt_err, NULL},
+};
+
+/**
+ * parse_opts - parse mount options into rdma options structure
+ * @params: options string passed from mount
+ * @opts: rdma transport-specific structure to parse options into
+ *
+ * Returns 0 upon success, -ERRNO upon failure
+ */
+static int parse_opts(char *params, struct p9_rdma_opts *opts)
+{
+	char *p;
+	substring_t args[MAX_OPT_ARGS];
+	int option;
+	char *options, *tmp_options;
+
+	opts->port = P9_PORT;
+	opts->sq_depth = P9_RDMA_SQ_DEPTH;
+	opts->rq_depth = P9_RDMA_RQ_DEPTH;
+	opts->timeout = P9_RDMA_TIMEOUT;
+
+	if (!params)
+		return 0;
+
+	tmp_options = kstrdup(params, GFP_KERNEL);
+	if (!tmp_options) {
+		p9_debug(P9_DEBUG_ERROR,
+			 "failed to allocate copy of option string\n");
+		return -ENOMEM;
+	}
+	options = tmp_options;
+
+	while ((p = strsep(&options, ",")) != NULL) {
+		int token;
+		int r;
+		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;
+		}
+		switch (token) {
+		case Opt_port:
+			opts->port = option;
+			break;
+		case Opt_sq_depth:
+			opts->sq_depth = option;
+			break;
+		case Opt_rq_depth:
+			opts->rq_depth = option;
+			break;
+		case Opt_timeout:
+			opts->timeout = option;
+			break;
+		default:
+			continue;
+		}
+	}
+	/* RQ must be at least as large as the SQ */
+	opts->rq_depth = max(opts->rq_depth, opts->sq_depth);
+	kfree(tmp_options);
+	return 0;
+}
+
+static int
+p9_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event)
+{
+	struct p9_client *c = id->context;
+	struct p9_trans_rdma *rdma = c->trans;
+	switch (event->event) {
+	case RDMA_CM_EVENT_ADDR_RESOLVED:
+		BUG_ON(rdma->state != P9_RDMA_INIT);
+		rdma->state = P9_RDMA_ADDR_RESOLVED;
+		break;
+
+	case RDMA_CM_EVENT_ROUTE_RESOLVED:
+		BUG_ON(rdma->state != P9_RDMA_ADDR_RESOLVED);
+		rdma->state = P9_RDMA_ROUTE_RESOLVED;
+		break;
+
+	case RDMA_CM_EVENT_ESTABLISHED:
+		BUG_ON(rdma->state != P9_RDMA_ROUTE_RESOLVED);
+		rdma->state = P9_RDMA_CONNECTED;
+		break;
+
+	case RDMA_CM_EVENT_DISCONNECTED:
+		if (rdma)
+			rdma->state = P9_RDMA_CLOSED;
+		if (c)
+			c->status = Disconnected;
+		break;
+
+	case RDMA_CM_EVENT_TIMEWAIT_EXIT:
+		break;
+
+	case RDMA_CM_EVENT_ADDR_CHANGE:
+	case RDMA_CM_EVENT_ROUTE_ERROR:
+	case RDMA_CM_EVENT_DEVICE_REMOVAL:
+	case RDMA_CM_EVENT_MULTICAST_JOIN:
+	case RDMA_CM_EVENT_MULTICAST_ERROR:
+	case RDMA_CM_EVENT_REJECTED:
+	case RDMA_CM_EVENT_CONNECT_REQUEST:
+	case RDMA_CM_EVENT_CONNECT_RESPONSE:
+	case RDMA_CM_EVENT_CONNECT_ERROR:
+	case RDMA_CM_EVENT_ADDR_ERROR:
+	case RDMA_CM_EVENT_UNREACHABLE:
+		c->status = Disconnected;
+		rdma_disconnect(rdma->cm_id);
+		break;
+	default:
+		BUG();
+	}
+	complete(&rdma->cm_done);
+	return 0;
+}
+
+static void
+handle_recv(struct p9_client *client, struct p9_trans_rdma *rdma,
+	    struct p9_rdma_context *c, enum ib_wc_status status, u32 byte_len)
+{
+	struct p9_req_t *req;
+	int err = 0;
+	int16_t tag;
+
+	req = NULL;
+	ib_dma_unmap_single(rdma->cm_id->device, c->busa, client->msize,
+							 DMA_FROM_DEVICE);
+
+	if (status != IB_WC_SUCCESS)
+		goto err_out;
+
+	err = p9_parse_header(c->rc, NULL, NULL, &tag, 1);
+	if (err)
+		goto err_out;
+
+	req = p9_tag_lookup(client, tag);
+	if (!req)
+		goto err_out;
+
+	/* Check that we have not yet received a reply for this request.
+	 */
+	if (unlikely(req->rc)) {
+		pr_err("Duplicate reply for request %d", tag);
+		goto err_out;
+	}
+
+	req->rc = c->rc;
+	p9_client_cb(client, req, REQ_STATUS_RCVD);
+
+	return;
+
+ err_out:
+	p9_debug(P9_DEBUG_ERROR, "req %p err %d status %d\n", req, err, status);
+	rdma->state = P9_RDMA_FLUSHING;
+	client->status = Disconnected;
+}
+
+static void
+handle_send(struct p9_client *client, struct p9_trans_rdma *rdma,
+	    struct p9_rdma_context *c, enum ib_wc_status status, u32 byte_len)
+{
+	ib_dma_unmap_single(rdma->cm_id->device,
+			    c->busa, c->req->tc->size,
+			    DMA_TO_DEVICE);
+}
+
+static void qp_event_handler(struct ib_event *event, void *context)
+{
+	p9_debug(P9_DEBUG_ERROR, "QP event %d context %p\n",
+		 event->event, context);
+}
+
+static void cq_comp_handler(struct ib_cq *cq, void *cq_context)
+{
+	struct p9_client *client = cq_context;
+	struct p9_trans_rdma *rdma = client->trans;
+	int ret;
+	struct ib_wc wc;
+
+	ib_req_notify_cq(rdma->cq, IB_CQ_NEXT_COMP);
+	while ((ret = ib_poll_cq(cq, 1, &wc)) > 0) {
+		struct p9_rdma_context *c = (void *) (unsigned long) wc.wr_id;
+
+		switch (c->wc_op) {
+		case IB_WC_RECV:
+			handle_recv(client, rdma, c, wc.status, wc.byte_len);
+			up(&rdma->rq_sem);
+			break;
+
+		case IB_WC_SEND:
+			handle_send(client, rdma, c, wc.status, wc.byte_len);
+			up(&rdma->sq_sem);
+			break;
+
+		default:
+			pr_err("unexpected completion type, c->wc_op=%d, wc.opcode=%d, status=%d\n",
+			       c->wc_op, wc.opcode, wc.status);
+			break;
+		}
+		kfree(c);
+	}
+}
+
+static void cq_event_handler(struct ib_event *e, void *v)
+{
+	p9_debug(P9_DEBUG_ERROR, "CQ event %d context %p\n", e->event, v);
+}
+
+static void rdma_destroy_trans(struct p9_trans_rdma *rdma)
+{
+	if (!rdma)
+		return;
+
+	if (rdma->dma_mr && !IS_ERR(rdma->dma_mr))
+		ib_dereg_mr(rdma->dma_mr);
+
+	if (rdma->qp && !IS_ERR(rdma->qp))
+		ib_destroy_qp(rdma->qp);
+
+	if (rdma->pd && !IS_ERR(rdma->pd))
+		ib_dealloc_pd(rdma->pd);
+
+	if (rdma->cq && !IS_ERR(rdma->cq))
+		ib_destroy_cq(rdma->cq);
+
+	if (rdma->cm_id && !IS_ERR(rdma->cm_id))
+		rdma_destroy_id(rdma->cm_id);
+
+	kfree(rdma);
+}
+
+static int
+post_recv(struct p9_client *client, struct p9_rdma_context *c)
+{
+	struct p9_trans_rdma *rdma = client->trans;
+	struct ib_recv_wr wr, *bad_wr;
+	struct ib_sge sge;
+
+	c->busa = ib_dma_map_single(rdma->cm_id->device,
+				    c->rc->sdata, client->msize,
+				    DMA_FROM_DEVICE);
+	if (ib_dma_mapping_error(rdma->cm_id->device, c->busa))
+		goto error;
+
+	sge.addr = c->busa;
+	sge.length = client->msize;
+	sge.lkey = rdma->lkey;
+
+	wr.next = NULL;
+	c->wc_op = IB_WC_RECV;
+	wr.wr_id = (unsigned long) c;
+	wr.sg_list = &sge;
+	wr.num_sge = 1;
+	return ib_post_recv(rdma->qp, &wr, &bad_wr);
+
+ error:
+	p9_debug(P9_DEBUG_ERROR, "EIO\n");
+	return -EIO;
+}
+
+static int rdma_request(struct p9_client *client, struct p9_req_t *req)
+{
+	struct p9_trans_rdma *rdma = client->trans;
+	struct ib_send_wr wr, *bad_wr;
+	struct ib_sge sge;
+	int err = 0;
+	unsigned long flags;
+	struct p9_rdma_context *c = NULL;
+	struct p9_rdma_context *rpl_context = NULL;
+
+	/* When an error occurs between posting the recv and the send,
+	 * there will be a receive context posted without a pending request.
+	 * Since there is no way to "un-post" it, we remember it and skip
+	 * post_recv() for the next request.
+	 * So here,
+	 * see if we are this `next request' and need to absorb an excess rc.
+	 * If yes, then drop and free our own, and do not recv_post().
+	 **/
+	if (unlikely(atomic_read(&rdma->excess_rc) > 0)) {
+		if ((atomic_sub_return(1, &rdma->excess_rc) >= 0)) {
+			/* Got one ! */
+			kfree(req->rc);
+			req->rc = NULL;
+			goto dont_need_post_recv;
+		} else {
+			/* We raced and lost. */
+			atomic_inc(&rdma->excess_rc);
+		}
+	}
+
+	/* Allocate an fcall for the reply */
+	rpl_context = kmalloc(sizeof *rpl_context, GFP_NOFS);
+	if (!rpl_context) {
+		err = -ENOMEM;
+		goto recv_error;
+	}
+	rpl_context->rc = req->rc;
+
+	/*
+	 * Post a receive buffer for this request. We need to ensure
+	 * there is a reply buffer available for every outstanding
+	 * request. A flushed request can result in no reply for an
+	 * outstanding request, so we must keep a count to avoid
+	 * overflowing the RQ.
+	 */
+	if (down_interruptible(&rdma->rq_sem)) {
+		err = -EINTR;
+		goto recv_error;
+	}
+
+	err = post_recv(client, rpl_context);
+	if (err) {
+		p9_debug(P9_DEBUG_FCALL, "POST RECV failed\n");
+		goto recv_error;
+	}
+	/* remove posted receive buffer from request structure */
+	req->rc = NULL;
+
+dont_need_post_recv:
+	/* Post the request */
+	c = kmalloc(sizeof *c, GFP_NOFS);
+	if (!c) {
+		err = -ENOMEM;
+		goto send_error;
+	}
+	c->req = req;
+
+	c->busa = ib_dma_map_single(rdma->cm_id->device,
+				    c->req->tc->sdata, c->req->tc->size,
+				    DMA_TO_DEVICE);
+	if (ib_dma_mapping_error(rdma->cm_id->device, c->busa)) {
+		err = -EIO;
+		goto send_error;
+	}
+
+	sge.addr = c->busa;
+	sge.length = c->req->tc->size;
+	sge.lkey = rdma->lkey;
+
+	wr.next = NULL;
+	c->wc_op = IB_WC_SEND;
+	wr.wr_id = (unsigned long) c;
+	wr.opcode = IB_WR_SEND;
+	wr.send_flags = IB_SEND_SIGNALED;
+	wr.sg_list = &sge;
+	wr.num_sge = 1;
+
+	if (down_interruptible(&rdma->sq_sem)) {
+		err = -EINTR;
+		goto send_error;
+	}
+
+	/* Mark request as `sent' *before* we actually send it,
+	 * because doing if after could erase the REQ_STATUS_RCVD
+	 * status in case of a very fast reply.
+	 */
+	req->status = REQ_STATUS_SENT;
+	err = ib_post_send(rdma->qp, &wr, &bad_wr);
+	if (err)
+		goto send_error;
+
+	/* Success */
+	return 0;
+
+ /* Handle errors that happened during or while preparing the send: */
+ send_error:
+	req->status = REQ_STATUS_ERROR;
+	kfree(c);
+	p9_debug(P9_DEBUG_ERROR, "Error %d in rdma_request()\n", err);
+
+	/* Ach.
+	 *  We did recv_post(), but not send. We have one recv_post in excess.
+	 */
+	atomic_inc(&rdma->excess_rc);
+	return err;
+
+ /* Handle errors that happened during or while preparing post_recv(): */
+ recv_error:
+	kfree(rpl_context);
+	spin_lock_irqsave(&rdma->req_lock, flags);
+	if (rdma->state < P9_RDMA_CLOSING) {
+		rdma->state = P9_RDMA_CLOSING;
+		spin_unlock_irqrestore(&rdma->req_lock, flags);
+		rdma_disconnect(rdma->cm_id);
+	} else
+		spin_unlock_irqrestore(&rdma->req_lock, flags);
+	return err;
+}
+
+static void rdma_close(struct p9_client *client)
+{
+	struct p9_trans_rdma *rdma;
+
+	if (!client)
+		return;
+
+	rdma = client->trans;
+	if (!rdma)
+		return;
+
+	client->status = Disconnected;
+	rdma_disconnect(rdma->cm_id);
+	rdma_destroy_trans(rdma);
+}
+
+/**
+ * alloc_rdma - Allocate and initialize the rdma transport structure
+ * @opts: Mount options structure
+ */
+static struct p9_trans_rdma *alloc_rdma(struct p9_rdma_opts *opts)
+{
+	struct p9_trans_rdma *rdma;
+
+	rdma = kzalloc(sizeof(struct p9_trans_rdma), GFP_KERNEL);
+	if (!rdma)
+		return NULL;
+
+	rdma->sq_depth = opts->sq_depth;
+	rdma->rq_depth = opts->rq_depth;
+	rdma->timeout = opts->timeout;
+	spin_lock_init(&rdma->req_lock);
+	init_completion(&rdma->cm_done);
+	sema_init(&rdma->sq_sem, rdma->sq_depth);
+	sema_init(&rdma->rq_sem, rdma->rq_depth);
+	atomic_set(&rdma->excess_rc, 0);
+
+	return rdma;
+}
+
+static int rdma_cancel(struct p9_client *client, struct p9_req_t *req)
+{
+	/* Nothing to do here.
+	 * We will take care of it (if we have to) in rdma_cancelled()
+	 */
+	return 1;
+}
+
+/* A request has been fully flushed without a reply.
+ * That means we have posted one buffer in excess.
+ */
+static int rdma_cancelled(struct p9_client *client, struct p9_req_t *req)
+{
+	struct p9_trans_rdma *rdma = client->trans;
+	atomic_inc(&rdma->excess_rc);
+	return 0;
+}
+
+/**
+ * trans_create_rdma - Transport method for creating atransport instance
+ * @client: client instance
+ * @addr: IP address string
+ * @args: Mount options string
+ */
+static int
+rdma_create_trans(struct p9_client *client, const char *addr, char *args)
+{
+	int err;
+	struct p9_rdma_opts opts;
+	struct p9_trans_rdma *rdma;
+	struct rdma_conn_param conn_param;
+	struct ib_qp_init_attr qp_attr;
+	struct ib_device_attr devattr;
+
+	/* Parse the transport specific mount options */
+	err = parse_opts(args, &opts);
+	if (err < 0)
+		return err;
+
+	/* Create and initialize the RDMA transport structure */
+	rdma = alloc_rdma(&opts);
+	if (!rdma)
+		return -ENOMEM;
+
+	/* Create the RDMA CM ID */
+	rdma->cm_id = rdma_create_id(p9_cm_event_handler, client, RDMA_PS_TCP,
+				     IB_QPT_RC);
+	if (IS_ERR(rdma->cm_id))
+		goto error;
+
+	/* Associate the client with the transport */
+	client->trans = rdma;
+
+	/* Resolve the server's address */
+	rdma->addr.sin_family = AF_INET;
+	rdma->addr.sin_addr.s_addr = in_aton(addr);
+	rdma->addr.sin_port = htons(opts.port);
+	err = rdma_resolve_addr(rdma->cm_id, NULL,
+				(struct sockaddr *)&rdma->addr,
+				rdma->timeout);
+	if (err)
+		goto error;
+	err = wait_for_completion_interruptible(&rdma->cm_done);
+	if (err || (rdma->state != P9_RDMA_ADDR_RESOLVED))
+		goto error;
+
+	/* Resolve the route to the server */
+	err = rdma_resolve_route(rdma->cm_id, rdma->timeout);
+	if (err)
+		goto error;
+	err = wait_for_completion_interruptible(&rdma->cm_done);
+	if (err || (rdma->state != P9_RDMA_ROUTE_RESOLVED))
+		goto error;
+
+	/* Query the device attributes */
+	err = ib_query_device(rdma->cm_id->device, &devattr);
+	if (err)
+		goto error;
+
+	/* Create the Completion Queue */
+	rdma->cq = ib_create_cq(rdma->cm_id->device, cq_comp_handler,
+				cq_event_handler, client,
+				opts.sq_depth + opts.rq_depth + 1, 0);
+	if (IS_ERR(rdma->cq))
+		goto error;
+	ib_req_notify_cq(rdma->cq, IB_CQ_NEXT_COMP);
+
+	/* Create the Protection Domain */
+	rdma->pd = ib_alloc_pd(rdma->cm_id->device);
+	if (IS_ERR(rdma->pd))
+		goto error;
+
+	/* Cache the DMA lkey in the transport */
+	rdma->dma_mr = NULL;
+	if (devattr.device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY)
+		rdma->lkey = rdma->cm_id->device->local_dma_lkey;
+	else {
+		rdma->dma_mr = ib_get_dma_mr(rdma->pd, IB_ACCESS_LOCAL_WRITE);
+		if (IS_ERR(rdma->dma_mr))
+			goto error;
+		rdma->lkey = rdma->dma_mr->lkey;
+	}
+
+	/* Create the Queue Pair */
+	memset(&qp_attr, 0, sizeof qp_attr);
+	qp_attr.event_handler = qp_event_handler;
+	qp_attr.qp_context = client;
+	qp_attr.cap.max_send_wr = opts.sq_depth;
+	qp_attr.cap.max_recv_wr = opts.rq_depth;
+	qp_attr.cap.max_send_sge = P9_RDMA_SEND_SGE;
+	qp_attr.cap.max_recv_sge = P9_RDMA_RECV_SGE;
+	qp_attr.sq_sig_type = IB_SIGNAL_REQ_WR;
+	qp_attr.qp_type = IB_QPT_RC;
+	qp_attr.send_cq = rdma->cq;
+	qp_attr.recv_cq = rdma->cq;
+	err = rdma_create_qp(rdma->cm_id, rdma->pd, &qp_attr);
+	if (err)
+		goto error;
+	rdma->qp = rdma->cm_id->qp;
+
+	/* Request a connection */
+	memset(&conn_param, 0, sizeof(conn_param));
+	conn_param.private_data = NULL;
+	conn_param.private_data_len = 0;
+	conn_param.responder_resources = P9_RDMA_IRD;
+	conn_param.initiator_depth = P9_RDMA_ORD;
+	err = rdma_connect(rdma->cm_id, &conn_param);
+	if (err)
+		goto error;
+	err = wait_for_completion_interruptible(&rdma->cm_done);
+	if (err || (rdma->state != P9_RDMA_CONNECTED))
+		goto error;
+
+	client->status = Connected;
+
+	return 0;
+
+error:
+	rdma_destroy_trans(rdma);
+	return -ENOTCONN;
+}
+
+static struct p9_trans_module p9_rdma_trans = {
+	.name = "rdma",
+	.maxsize = P9_RDMA_MAXSIZE,
+	.def = 0,
+	.owner = THIS_MODULE,
+	.create = rdma_create_trans,
+	.close = rdma_close,
+	.request = rdma_request,
+	.cancel = rdma_cancel,
+	.cancelled = rdma_cancelled,
+};
+
+/**
+ * p9_trans_rdma_init - Register the 9P RDMA transport driver
+ */
+static int __init p9_trans_rdma_init(void)
+{
+	v9fs_register_trans(&p9_rdma_trans);
+	return 0;
+}
+
+static void __exit p9_trans_rdma_exit(void)
+{
+	v9fs_unregister_trans(&p9_rdma_trans);
+}
+
+module_init(p9_trans_rdma_init);
+module_exit(p9_trans_rdma_exit);
+
+MODULE_AUTHOR("Tom Tucker <tom@opengridcomputing.com>");
+MODULE_DESCRIPTION("RDMA Transport for 9P");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
new file mode 100644
index 00000000000..6940d8fe897
--- /dev/null
+++ b/net/9p/trans_virtio.c
@@ -0,0 +1,728 @@
+/*
+ * The Virtio 9p transport driver
+ *
+ * This is a block based transport driver based on the lguest block driver
+ * code.
+ *
+ *  Copyright (C) 2007, 2008 Eric Van Hensbergen, IBM Corporation
+ *
+ *  Based on virtio console driver
+ *  Copyright (C) 2006, 2007 Rusty Russell, IBM 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.
+ *
+ *  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:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/in.h>
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/ipv6.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/un.h>
+#include <linux/uaccess.h>
+#include <linux/inet.h>
+#include <linux/idr.h>
+#include <linux/file.h>
+#include <linux/highmem.h>
+#include <linux/slab.h>
+#include <net/9p/9p.h>
+#include <linux/parser.h>
+#include <net/9p/client.h>
+#include <net/9p/transport.h>
+#include <linux/scatterlist.h>
+#include <linux/swap.h>
+#include <linux/virtio.h>
+#include <linux/virtio_9p.h>
+#include "trans_common.h"
+
+#define VIRTQUEUE_NUM	128
+
+/* a single mutex to manage channel initialization and attachment */
+static DEFINE_MUTEX(virtio_9p_lock);
+static DECLARE_WAIT_QUEUE_HEAD(vp_wq);
+static atomic_t vp_pinned = ATOMIC_INIT(0);
+
+/**
+ * struct virtio_chan - per-instance transport information
+ * @initialized: whether the channel is initialized
+ * @inuse: whether the channel is in use
+ * @lock: protects multiple elements within this structure
+ * @client: client instance
+ * @vdev: virtio dev associated with this channel
+ * @vq: virtio queue associated with this channel
+ * @sg: scatter gather list which is used to pack a request (protected?)
+ *
+ * We keep all per-channel information in a structure.
+ * This structure is allocated within the devices dev->mem space.
+ * A pointer to the structure will get put in the transport private.
+ *
+ */
+
+struct virtio_chan {
+	bool inuse;
+
+	spinlock_t lock;
+
+	struct p9_client *client;
+	struct virtio_device *vdev;
+	struct virtqueue *vq;
+	int ring_bufs_avail;
+	wait_queue_head_t *vc_wq;
+	/* This is global limit. Since we don't have a global structure,
+	 * will be placing it in each channel.
+	 */
+	unsigned long p9_max_pages;
+	/* Scatterlist: can be too big for stack. */
+	struct scatterlist sg[VIRTQUEUE_NUM];
+
+	int tag_len;
+	/*
+	 * tag name to identify a mount Non-null terminated
+	 */
+	char *tag;
+
+	struct list_head chan_list;
+};
+
+static struct list_head virtio_chan_list;
+
+/* How many bytes left in this page. */
+static unsigned int rest_of_page(void *data)
+{
+	return PAGE_SIZE - ((unsigned long)data % PAGE_SIZE);
+}
+
+/**
+ * p9_virtio_close - reclaim resources of a channel
+ * @client: client instance
+ *
+ * This reclaims a channel by freeing its resources and
+ * reseting its inuse flag.
+ *
+ */
+
+static void p9_virtio_close(struct p9_client *client)
+{
+	struct virtio_chan *chan = client->trans;
+
+	mutex_lock(&virtio_9p_lock);
+	if (chan)
+		chan->inuse = false;
+	mutex_unlock(&virtio_9p_lock);
+}
+
+/**
+ * req_done - callback which signals activity from the server
+ * @vq: virtio queue activity was received on
+ *
+ * This notifies us that the server has triggered some activity
+ * on the virtio channel - most likely a response to request we
+ * sent.  Figure out which requests now have responses and wake up
+ * those threads.
+ *
+ * Bugs: could do with some additional sanity checking, but appears to work.
+ *
+ */
+
+static void req_done(struct virtqueue *vq)
+{
+	struct virtio_chan *chan = vq->vdev->priv;
+	struct p9_fcall *rc;
+	unsigned int len;
+	struct p9_req_t *req;
+	unsigned long flags;
+
+	p9_debug(P9_DEBUG_TRANS, ": request done\n");
+
+	while (1) {
+		spin_lock_irqsave(&chan->lock, flags);
+		rc = virtqueue_get_buf(chan->vq, &len);
+		if (rc == NULL) {
+			spin_unlock_irqrestore(&chan->lock, flags);
+			break;
+		}
+		chan->ring_bufs_avail = 1;
+		spin_unlock_irqrestore(&chan->lock, flags);
+		/* Wakeup if anyone waiting for VirtIO ring space. */
+		wake_up(chan->vc_wq);
+		p9_debug(P9_DEBUG_TRANS, ": rc %p\n", rc);
+		p9_debug(P9_DEBUG_TRANS, ": lookup tag %d\n", rc->tag);
+		req = p9_tag_lookup(chan->client, rc->tag);
+		p9_client_cb(chan->client, req, REQ_STATUS_RCVD);
+	}
+}
+
+/**
+ * pack_sg_list - pack a scatter gather list from a linear buffer
+ * @sg: scatter/gather list to pack into
+ * @start: which segment of the sg_list to start at
+ * @limit: maximum segment to pack data to
+ * @data: data to pack into scatter/gather list
+ * @count: amount of data to pack into the scatter/gather list
+ *
+ * sg_lists have multiple segments of various sizes.  This will pack
+ * arbitrary data into an existing scatter gather list, segmenting the
+ * data as necessary within constraints.
+ *
+ */
+
+static int pack_sg_list(struct scatterlist *sg, int start,
+			int limit, char *data, int count)
+{
+	int s;
+	int index = start;
+
+	while (count) {
+		s = rest_of_page(data);
+		if (s > count)
+			s = count;
+		BUG_ON(index > limit);
+		/* Make sure we don't terminate early. */
+		sg_unmark_end(&sg[index]);
+		sg_set_buf(&sg[index++], data, s);
+		count -= s;
+		data += s;
+	}
+	if (index-start)
+		sg_mark_end(&sg[index - 1]);
+	return index-start;
+}
+
+/* We don't currently allow canceling of virtio requests */
+static int p9_virtio_cancel(struct p9_client *client, struct p9_req_t *req)
+{
+	return 1;
+}
+
+/**
+ * pack_sg_list_p - Just like pack_sg_list. Instead of taking a buffer,
+ * this takes a list of pages.
+ * @sg: scatter/gather list to pack into
+ * @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
+ * @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)
+{
+	int i = 0, s;
+	int data_off;
+	int index = start;
+
+	BUG_ON(nr_pages > (limit - start));
+	/*
+	 * 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);
+		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--;
+	}
+
+	if (index-start)
+		sg_mark_end(&sg[index - 1]);
+	return index - start;
+}
+
+/**
+ * p9_virtio_request - issue a request
+ * @client: client instance issuing the request
+ * @req: request to be issued
+ *
+ */
+
+static int
+p9_virtio_request(struct p9_client *client, struct p9_req_t *req)
+{
+	int err;
+	int in, out, out_sgs, in_sgs;
+	unsigned long flags;
+	struct virtio_chan *chan = client->trans;
+	struct scatterlist *sgs[2];
+
+	p9_debug(P9_DEBUG_TRANS, "9p debug: virtio request\n");
+
+	req->status = REQ_STATUS_SENT;
+req_retry:
+	spin_lock_irqsave(&chan->lock, flags);
+
+	out_sgs = in_sgs = 0;
+	/* Handle out VirtIO ring buffers */
+	out = pack_sg_list(chan->sg, 0,
+			   VIRTQUEUE_NUM, req->tc->sdata, req->tc->size);
+	if (out)
+		sgs[out_sgs++] = chan->sg;
+
+	in = pack_sg_list(chan->sg, out,
+			  VIRTQUEUE_NUM, req->rc->sdata, req->rc->capacity);
+	if (in)
+		sgs[out_sgs + in_sgs++] = chan->sg + out;
+
+	err = virtqueue_add_sgs(chan->vq, sgs, out_sgs, in_sgs, req->tc,
+				GFP_ATOMIC);
+	if (err < 0) {
+		if (err == -ENOSPC) {
+			chan->ring_bufs_avail = 0;
+			spin_unlock_irqrestore(&chan->lock, flags);
+			err = wait_event_interruptible(*chan->vc_wq,
+							chan->ring_bufs_avail);
+			if (err  == -ERESTARTSYS)
+				return err;
+
+			p9_debug(P9_DEBUG_TRANS, "Retry virtio request\n");
+			goto req_retry;
+		} else {
+			spin_unlock_irqrestore(&chan->lock, flags);
+			p9_debug(P9_DEBUG_TRANS,
+				 "virtio rpc add_sgs returned failure\n");
+			return -EIO;
+		}
+	}
+	virtqueue_kick(chan->vq);
+	spin_unlock_irqrestore(&chan->lock, flags);
+
+	p9_debug(P9_DEBUG_TRANS, "virtio request kicked\n");
+	return 0;
+}
+
+static int p9_get_mapped_pages(struct virtio_chan *chan,
+			       struct page **pages, char *data,
+			       int nr_pages, int write, int kern_buf)
+{
+	int err;
+	if (!kern_buf) {
+		/*
+		 * We allow only p9_max_pages pinned. We wait for the
+		 * Other zc request to finish here
+		 */
+		if (atomic_read(&vp_pinned) >= chan->p9_max_pages) {
+			err = wait_event_interruptible(vp_wq,
+			      (atomic_read(&vp_pinned) < chan->p9_max_pages));
+			if (err == -ERESTARTSYS)
+				return err;
+		}
+		err = p9_payload_gup(data, &nr_pages, pages, write);
+		if (err < 0)
+			return err;
+		atomic_add(nr_pages, &vp_pinned);
+	} 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);
+			else
+				pages[index++] = kmap_to_page(data);
+			data += s;
+			nr_pages--;
+		}
+		nr_pages = count;
+	}
+	return nr_pages;
+}
+
+/**
+ * p9_virtio_zc_request - issue a zero copy request
+ * @client: client instance issuing the request
+ * @req: request to be issued
+ * @uidata: user bffer that should be ued for zero copy read
+ * @uodata: user buffer that shoud be user for zero copy write
+ * @inlen: read buffer size
+ * @olen: write buffer size
+ * @hdrlen: reader header size, This is the size of response protocol data
+ *
+ */
+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)
+{
+	int in, out, err, out_sgs, in_sgs;
+	unsigned long flags;
+	int in_nr_pages = 0, out_nr_pages = 0;
+	struct page **in_pages = NULL, **out_pages = NULL;
+	struct virtio_chan *chan = client->trans;
+	struct scatterlist *sgs[4];
+
+	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;
+		}
+		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;
+		}
+	}
+	req->status = REQ_STATUS_SENT;
+req_retry_pinned:
+	spin_lock_irqsave(&chan->lock, flags);
+
+	out_sgs = in_sgs = 0;
+
+	/* out data */
+	out = pack_sg_list(chan->sg, 0,
+			   VIRTQUEUE_NUM, req->tc->sdata, req->tc->size);
+
+	if (out)
+		sgs[out_sgs++] = chan->sg;
+
+	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);
+	}
+		
+	/*
+	 * Take care of in data
+	 * For example TREAD have 11.
+	 * 11 is the read/write header = PDU Header(7) + IO Size (4).
+	 * Arrange in such a way that server places header in the
+	 * alloced memory and payload onto the user buffer.
+	 */
+	in = pack_sg_list(chan->sg, out,
+			  VIRTQUEUE_NUM, req->rc->sdata, in_hdr_len);
+	if (in)
+		sgs[out_sgs + in_sgs++] = chan->sg + out;
+
+	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);
+	}
+
+	BUG_ON(out_sgs + in_sgs > ARRAY_SIZE(sgs));
+	err = virtqueue_add_sgs(chan->vq, sgs, out_sgs, in_sgs, req->tc,
+				GFP_ATOMIC);
+	if (err < 0) {
+		if (err == -ENOSPC) {
+			chan->ring_bufs_avail = 0;
+			spin_unlock_irqrestore(&chan->lock, flags);
+			err = wait_event_interruptible(*chan->vc_wq,
+						       chan->ring_bufs_avail);
+			if (err  == -ERESTARTSYS)
+				goto err_out;
+
+			p9_debug(P9_DEBUG_TRANS, "Retry virtio request\n");
+			goto req_retry_pinned;
+		} else {
+			spin_unlock_irqrestore(&chan->lock, flags);
+			p9_debug(P9_DEBUG_TRANS,
+				 "virtio rpc add_sgs returned failure\n");
+			err = -EIO;
+			goto err_out;
+		}
+	}
+	virtqueue_kick(chan->vq);
+	spin_unlock_irqrestore(&chan->lock, flags);
+	p9_debug(P9_DEBUG_TRANS, "virtio request kicked\n");
+	err = wait_event_interruptible(*req->wq,
+				       req->status >= REQ_STATUS_RCVD);
+	/*
+	 * Non kernel buffers are pinned, unpin them
+	 */
+err_out:
+	if (!kern_buf) {
+		if (in_pages) {
+			p9_release_pages(in_pages, in_nr_pages);
+			atomic_sub(in_nr_pages, &vp_pinned);
+		}
+		if (out_pages) {
+			p9_release_pages(out_pages, out_nr_pages);
+			atomic_sub(out_nr_pages, &vp_pinned);
+		}
+		/* wakeup anybody waiting for slots to pin pages */
+		wake_up(&vp_wq);
+	}
+	kfree(in_pages);
+	kfree(out_pages);
+	return err;
+}
+
+static ssize_t p9_mount_tag_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct virtio_chan *chan;
+	struct virtio_device *vdev;
+
+	vdev = dev_to_virtio(dev);
+	chan = vdev->priv;
+
+	return snprintf(buf, chan->tag_len + 1, "%s", chan->tag);
+}
+
+static DEVICE_ATTR(mount_tag, 0444, p9_mount_tag_show, NULL);
+
+/**
+ * p9_virtio_probe - probe for existence of 9P virtio channels
+ * @vdev: virtio device to probe
+ *
+ * This probes for existing virtio channels.
+ *
+ */
+
+static int p9_virtio_probe(struct virtio_device *vdev)
+{
+	__u16 tag_len;
+	char *tag;
+	int err;
+	struct virtio_chan *chan;
+
+	chan = kmalloc(sizeof(struct virtio_chan), GFP_KERNEL);
+	if (!chan) {
+		pr_err("Failed to allocate virtio 9P channel\n");
+		err = -ENOMEM;
+		goto fail;
+	}
+
+	chan->vdev = vdev;
+
+	/* We expect one virtqueue, for requests. */
+	chan->vq = virtio_find_single_vq(vdev, req_done, "requests");
+	if (IS_ERR(chan->vq)) {
+		err = PTR_ERR(chan->vq);
+		goto out_free_vq;
+	}
+	chan->vq->vdev->priv = chan;
+	spin_lock_init(&chan->lock);
+
+	sg_init_table(chan->sg, VIRTQUEUE_NUM);
+
+	chan->inuse = false;
+	if (virtio_has_feature(vdev, VIRTIO_9P_MOUNT_TAG)) {
+		virtio_cread(vdev, struct virtio_9p_config, tag_len, &tag_len);
+	} else {
+		err = -EINVAL;
+		goto out_free_vq;
+	}
+	tag = kmalloc(tag_len, GFP_KERNEL);
+	if (!tag) {
+		err = -ENOMEM;
+		goto out_free_vq;
+	}
+
+	virtio_cread_bytes(vdev, offsetof(struct virtio_9p_config, tag),
+			   tag, tag_len);
+	chan->tag = tag;
+	chan->tag_len = tag_len;
+	err = sysfs_create_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr);
+	if (err) {
+		goto out_free_tag;
+	}
+	chan->vc_wq = kmalloc(sizeof(wait_queue_head_t), GFP_KERNEL);
+	if (!chan->vc_wq) {
+		err = -ENOMEM;
+		goto out_free_tag;
+	}
+	init_waitqueue_head(chan->vc_wq);
+	chan->ring_bufs_avail = 1;
+	/* Ceiling limit to avoid denial of service attacks */
+	chan->p9_max_pages = nr_free_buffer_pages()/4;
+
+	mutex_lock(&virtio_9p_lock);
+	list_add_tail(&chan->chan_list, &virtio_chan_list);
+	mutex_unlock(&virtio_9p_lock);
+
+	/* Let udev rules use the new mount_tag attribute. */
+	kobject_uevent(&(vdev->dev.kobj), KOBJ_CHANGE);
+
+	return 0;
+
+out_free_tag:
+	kfree(tag);
+out_free_vq:
+	vdev->config->del_vqs(vdev);
+	kfree(chan);
+fail:
+	return err;
+}
+
+
+/**
+ * p9_virtio_create - allocate a new virtio channel
+ * @client: client instance invoking this transport
+ * @devname: string identifying the channel to connect to (unused)
+ * @args: args passed from sys_mount() for per-transport options (unused)
+ *
+ * This sets up a transport channel for 9p communication.  Right now
+ * we only match the first available channel, but eventually we couldlook up
+ * alternate channels by matching devname versus a virtio_config entry.
+ * We use a simple reference count mechanism to ensure that only a single
+ * mount has a channel open at a time.
+ *
+ */
+
+static int
+p9_virtio_create(struct p9_client *client, const char *devname, char *args)
+{
+	struct virtio_chan *chan;
+	int ret = -ENOENT;
+	int found = 0;
+
+	mutex_lock(&virtio_9p_lock);
+	list_for_each_entry(chan, &virtio_chan_list, chan_list) {
+		if (!strncmp(devname, chan->tag, chan->tag_len) &&
+		    strlen(devname) == chan->tag_len) {
+			if (!chan->inuse) {
+				chan->inuse = true;
+				found = 1;
+				break;
+			}
+			ret = -EBUSY;
+		}
+	}
+	mutex_unlock(&virtio_9p_lock);
+
+	if (!found) {
+		pr_err("no channels available\n");
+		return ret;
+	}
+
+	client->trans = (void *)chan;
+	client->status = Connected;
+	chan->client = client;
+
+	return 0;
+}
+
+/**
+ * p9_virtio_remove - clean up resources associated with a virtio device
+ * @vdev: virtio device to remove
+ *
+ */
+
+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);
+
+	mutex_lock(&virtio_9p_lock);
+	list_del(&chan->chan_list);
+	mutex_unlock(&virtio_9p_lock);
+	sysfs_remove_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr);
+	kobject_uevent(&(vdev->dev.kobj), KOBJ_CHANGE);
+	kfree(chan->tag);
+	kfree(chan->vc_wq);
+	kfree(chan);
+
+}
+
+static struct virtio_device_id id_table[] = {
+	{ VIRTIO_ID_9P, VIRTIO_DEV_ANY_ID },
+	{ 0 },
+};
+
+static unsigned int features[] = {
+	VIRTIO_9P_MOUNT_TAG,
+};
+
+/* The standard "struct lguest_driver": */
+static struct virtio_driver p9_virtio_drv = {
+	.feature_table  = features,
+	.feature_table_size = ARRAY_SIZE(features),
+	.driver.name    = KBUILD_MODNAME,
+	.driver.owner	= THIS_MODULE,
+	.id_table	= id_table,
+	.probe		= p9_virtio_probe,
+	.remove		= p9_virtio_remove,
+};
+
+static struct p9_trans_module p9_virtio_trans = {
+	.name = "virtio",
+	.create = p9_virtio_create,
+	.close = p9_virtio_close,
+	.request = p9_virtio_request,
+	.zc_request = p9_virtio_zc_request,
+	.cancel = p9_virtio_cancel,
+	/*
+	 * We leave one entry for input and one entry for response
+	 * headers. We also skip one more entry to accomodate, address
+	 * that are not at page boundary, that can result in an extra
+	 * page in zero copy.
+	 */
+	.maxsize = PAGE_SIZE * (VIRTQUEUE_NUM - 3),
+	.def = 1,
+	.owner = THIS_MODULE,
+};
+
+/* The standard init function */
+static int __init p9_virtio_init(void)
+{
+	INIT_LIST_HEAD(&virtio_chan_list);
+
+	v9fs_register_trans(&p9_virtio_trans);
+	return register_virtio_driver(&p9_virtio_drv);
+}
+
+static void __exit p9_virtio_cleanup(void)
+{
+	unregister_virtio_driver(&p9_virtio_drv);
+	v9fs_unregister_trans(&p9_virtio_trans);
+}
+
+module_init(p9_virtio_init);
+module_exit(p9_virtio_cleanup);
+
+MODULE_DEVICE_TABLE(virtio, id_table);
+MODULE_AUTHOR("Eric Van Hensbergen <ericvh@gmail.com>");
+MODULE_DESCRIPTION("Virtio 9p Transport");
+MODULE_LICENSE("GPL");
diff --git a/net/9p/util.c b/net/9p/util.c
new file mode 100644
index 00000000000..59f278e64f5
--- /dev/null
+++ b/net/9p/util.c
@@ -0,0 +1,141 @@
+/*
+ *  net/9p/util.c
+ *
+ *  This file contains some helper functions
+ *
+ *  Copyright (C) 2007 by Latchesar Ionkov <lucho@ionkov.net>
+ *  Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ *  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:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/parser.h>
+#include <linux/idr.h>
+#include <linux/slab.h>
+#include <net/9p/9p.h>
+
+/**
+ * struct p9_idpool - per-connection accounting for tag idpool
+ * @lock: protects the pool
+ * @pool: idr to allocate tag id from
+ *
+ */
+
+struct p9_idpool {
+	spinlock_t lock;
+	struct idr pool;
+};
+
+/**
+ * p9_idpool_create - create a new per-connection id pool
+ *
+ */
+
+struct p9_idpool *p9_idpool_create(void)
+{
+	struct p9_idpool *p;
+
+	p = kmalloc(sizeof(struct p9_idpool), GFP_KERNEL);
+	if (!p)
+		return ERR_PTR(-ENOMEM);
+
+	spin_lock_init(&p->lock);
+	idr_init(&p->pool);
+
+	return p;
+}
+EXPORT_SYMBOL(p9_idpool_create);
+
+/**
+ * p9_idpool_destroy - create a new per-connection id pool
+ * @p: idpool to destroy
+ */
+
+void p9_idpool_destroy(struct p9_idpool *p)
+{
+	idr_destroy(&p->pool);
+	kfree(p);
+}
+EXPORT_SYMBOL(p9_idpool_destroy);
+
+/**
+ * p9_idpool_get - allocate numeric id from pool
+ * @p: pool to allocate from
+ *
+ * Bugs: This seems to be an awful generic function, should it be in idr.c with
+ *            the lock included in struct idr?
+ */
+
+int p9_idpool_get(struct p9_idpool *p)
+{
+	int i;
+	unsigned long flags;
+
+	idr_preload(GFP_NOFS);
+	spin_lock_irqsave(&p->lock, flags);
+
+	/* no need to store exactly p, we just need something non-null */
+	i = idr_alloc(&p->pool, p, 0, 0, GFP_NOWAIT);
+
+	spin_unlock_irqrestore(&p->lock, flags);
+	idr_preload_end();
+	if (i < 0)
+		return -1;
+
+	p9_debug(P9_DEBUG_MUX, " id %d pool %p\n", i, p);
+	return i;
+}
+EXPORT_SYMBOL(p9_idpool_get);
+
+/**
+ * p9_idpool_put - release numeric id from pool
+ * @id: numeric id which is being released
+ * @p: pool to release id into
+ *
+ * Bugs: This seems to be an awful generic function, should it be in idr.c with
+ *            the lock included in struct idr?
+ */
+
+void p9_idpool_put(int id, struct p9_idpool *p)
+{
+	unsigned long flags;
+
+	p9_debug(P9_DEBUG_MUX, " id %d pool %p\n", id, p);
+
+	spin_lock_irqsave(&p->lock, flags);
+	idr_remove(&p->pool, id);
+	spin_unlock_irqrestore(&p->lock, flags);
+}
+EXPORT_SYMBOL(p9_idpool_put);
+
+/**
+ * p9_idpool_check - check if the specified id is available
+ * @id: id to check
+ * @p: pool to check
+ */
+
+int p9_idpool_check(int id, struct p9_idpool *p)
+{
+	return idr_find(&p->pool, id) != NULL;
+}
+EXPORT_SYMBOL(p9_idpool_check);
+
diff --git a/net/Kconfig b/net/Kconfig
index 5126f58d9c4..d92afe4204d 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -2,10 +2,10 @@
 # Network configuration
 #
 
-menu "Networking"
-
-config NET
+menuconfig NET
 	bool "Networking support"
+	select NLATTR
+	select GENERIC_NET_UTILS
 	---help---
 	  Unless you really know what you are doing, you should say Y here.
 	  The reason is that some programs need kernel networking support even
@@ -22,28 +22,43 @@ config NET
 	  recommended to read the NET-HOWTO, available from
 	  <http://www.tldp.org/docs.html#howto>.
 
-# Make sure that all config symbols are dependent on NET
 if NET
 
-menu "Networking options"
+config WANT_COMPAT_NETLINK_MESSAGES
+	bool
+	help
+	  This option can be selected by other options that need compat
+	  netlink messages.
 
-config NETDEBUG
-	bool "Network packet debugging"
+config COMPAT_NETLINK_MESSAGES
+	def_bool y
+	depends on COMPAT
+	depends on WEXT_CORE || WANT_COMPAT_NETLINK_MESSAGES
 	help
-	  You can say Y here if you want to get additional messages useful in
-	  debugging bad packets, but can overwhelm logs under denial of service
-	  attacks.
+	  This option makes it possible to send different netlink messages
+	  to tasks depending on whether the task is a compat task or not. To
+	  achieve this, you need to set skb_shinfo(skb)->frag_list to the
+	  compat skb before sending the skb, the netlink code will sort out
+	  which message to actually pass to the task.
+
+	  Newly written code should NEVER need this option but do
+	  compat-independent messages instead!
+
+menu "Networking options"
 
 source "net/packet/Kconfig"
 source "net/unix/Kconfig"
 source "net/xfrm/Kconfig"
+source "net/iucv/Kconfig"
 
 config INET
 	bool "TCP/IP networking"
+	select CRYPTO
+	select CRYPTO_AES
 	---help---
 	  These are the protocols used on the Internet and on most local
 	  Ethernets. It is highly recommended to say Y here (this will enlarge
-	  your kernel by about 144 KB), since some programs (e.g. the X window
+	  your kernel by about 400 KB), since some programs (e.g. the X window
 	  system) use TCP/IP even if your machine is not connected to any
 	  other computer. You will get the so-called loopback device which
 	  allows you to ping yourself (great fun, that!).
@@ -63,11 +78,32 @@ config INET
 if INET
 source "net/ipv4/Kconfig"
 source "net/ipv6/Kconfig"
+source "net/netlabel/Kconfig"
 
 endif # if INET
 
+config NETWORK_SECMARK
+	bool "Security Marking"
+	help
+	  This enables security marking of network packets, similar
+	  to nfmark, but designated for security purposes.
+	  If you are unsure how to answer this question, answer N.
+
+config NET_PTP_CLASSIFY
+	def_bool n
+
+config NETWORK_PHY_TIMESTAMPING
+	bool "Timestamping in PHY devices"
+	select NET_PTP_CLASSIFY
+	help
+	  This allows timestamping of network packets by PHYs with
+	  hardware timestamping capabilities. This option adds some
+	  overhead in the transmit and receive paths.
+
+	  If you are unsure how to answer this question, answer N.
+
 menuconfig NETFILTER
-	bool "Network packet filtering (replaces ipchains)"
+	bool "Network packet filtering framework (Netfilter)"
 	---help---
 	  Netfilter is a framework for filtering and mangling network packets
 	  that pass through your Linux box.
@@ -119,12 +155,6 @@ menuconfig NETFILTER
 	  <file:Documentation/Changes> under "iptables" for the location of
 	  these packages.
 
-	  Make sure to say N to "Fast switching" below if you intend to say Y
-	  here, as Fast switching currently bypasses netfilter.
-
-	  Chances are that you should say Y here if you compile a kernel which
-	  will run as a router and N for regular hosts. If unsure, say N.
-
 if NETFILTER
 
 config NETFILTER_DEBUG
@@ -134,9 +164,21 @@ config NETFILTER_DEBUG
 	  You can say Y here if you want to get additional messages useful in
 	  debugging the netfilter code.
 
+config NETFILTER_ADVANCED
+	bool "Advanced netfilter configuration"
+	depends on NETFILTER
+	default y
+	help
+	  If you say Y here you can select between all the netfilter modules.
+	  If you say N the more unusual ones will not be shown and the
+	  basic ones needed by most people will default to 'M'.
+
+	  If unsure, say Y.
+
 config BRIDGE_NETFILTER
 	bool "Bridged IP/ARP packets filtering"
 	depends on BRIDGE && NETFILTER && INET
+	depends on NETFILTER_ADVANCED
 	default y
 	---help---
 	  Enabling this option will let arptables resp. iptables see bridged
@@ -157,9 +199,13 @@ endif
 
 source "net/dccp/Kconfig"
 source "net/sctp/Kconfig"
+source "net/rds/Kconfig"
 source "net/tipc/Kconfig"
 source "net/atm/Kconfig"
+source "net/l2tp/Kconfig"
+source "net/802/Kconfig"
 source "net/bridge/Kconfig"
+source "net/dsa/Kconfig"
 source "net/8021q/Kconfig"
 source "net/decnet/Kconfig"
 source "net/llc/Kconfig"
@@ -167,42 +213,87 @@ source "net/ipx/Kconfig"
 source "drivers/net/appletalk/Kconfig"
 source "net/x25/Kconfig"
 source "net/lapb/Kconfig"
+source "net/phonet/Kconfig"
+source "net/ieee802154/Kconfig"
+source "net/mac802154/Kconfig"
+source "net/sched/Kconfig"
+source "net/dcb/Kconfig"
+source "net/dns_resolver/Kconfig"
+source "net/batman-adv/Kconfig"
+source "net/openvswitch/Kconfig"
+source "net/vmw_vsock/Kconfig"
+source "net/netlink/Kconfig"
+source "net/mpls/Kconfig"
+source "net/hsr/Kconfig"
+
+config RPS
+	boolean
+	depends on SMP && SYSFS
+	default y
+
+config RFS_ACCEL
+	boolean
+	depends on RPS
+	select CPU_RMAP
+	default y
 
-config NET_DIVERT
-	bool "Frame Diverter (EXPERIMENTAL)"
-	depends on EXPERIMENTAL
+config XPS
+	boolean
+	depends on SMP
+	default y
+
+config CGROUP_NET_PRIO
+	bool "Network priority cgroup"
+	depends on CGROUPS
 	---help---
-	  The Frame Diverter allows you to divert packets from the
-	  network, that are not aimed at the interface receiving it (in
-	  promisc. mode). Typically, a Linux box setup as an Ethernet bridge
-	  with the Frames Diverter on, can do some *really* transparent www
-	  caching using a Squid proxy for example.
-
-	  This is very useful when you don't want to change your router's
-	  config (or if you simply don't have access to it).
-
-	  The other possible usages of diverting Ethernet Frames are
-	  numberous:
-	  - reroute smtp traffic to another interface
-	  - traffic-shape certain network streams
-	  - transparently proxy smtp connections
-	  - etc...
-
-	  For more informations, please refer to:
-	  <http://diverter.sourceforge.net/>
-	  <http://perso.wanadoo.fr/magpie/EtherDivert.html>
+	  Cgroup subsystem for use in assigning processes to network priorities on
+	  a per-interface basis.
 
-	  If unsure, say N.
+config CGROUP_NET_CLASSID
+	boolean "Network classid cgroup"
+	depends on CGROUPS
+	---help---
+	  Cgroup subsystem for use as general purpose socket classid marker that is
+	  being used in cls_cgroup and for netfilter matching.
 
-source "net/econet/Kconfig"
-source "net/wanrouter/Kconfig"
-source "net/sched/Kconfig"
+config NET_RX_BUSY_POLL
+	boolean
+	default y
+
+config BQL
+	boolean
+	depends on SYSFS
+	select DQL
+	default y
+
+config BPF_JIT
+	bool "enable BPF Just In Time compiler"
+	depends on HAVE_BPF_JIT
+	depends on MODULES
+	---help---
+	  Berkeley Packet Filter filtering capabilities are normally handled
+	  by an interpreter. This option allows kernel to generate a native
+	  code when filter is loaded in memory. This should speedup
+	  packet sniffing (libpcap/tcpdump). Note : Admin should enable
+	  this feature changing /proc/sys/net/core/bpf_jit_enable
+
+config NET_FLOW_LIMIT
+	boolean
+	depends on RPS
+	default y
+	---help---
+	  The network stack has to drop packets when a receive processing CPU's
+	  backlog reaches netdev_max_backlog. If a few out of many active flows
+	  generate the vast majority of load, drop their traffic earlier to
+	  maintain capacity for the other flows. This feature provides servers
+	  with many clients some protection against DoS by a single (spoofed)
+	  flow that greatly exceeds average workload.
 
 menu "Network testing"
 
 config NET_PKTGEN
 	tristate "Packet Generator (USE WITH CAUTION)"
-	depends on PROC_FS
+	depends on INET && PROC_FS
 	---help---
 	  This module will inject preconfigured packets, at a configurable
 	  rate, out of a given interface.  It is used for network interface
@@ -215,15 +306,70 @@ config NET_PKTGEN
 	  To compile this code as a module, choose M here: the
 	  module will be called pktgen.
 
+config NET_TCPPROBE
+	tristate "TCP connection probing"
+	depends on INET && PROC_FS && KPROBES
+	---help---
+	This module allows for capturing the changes to TCP connection
+	state in response to incoming packets. It is used for debugging
+	TCP congestion avoidance modules. If you don't understand
+	what was just said, you don't need it: say N.
+
+	Documentation on how to use TCP connection probing can be found
+	at:
+	
+	  http://www.linuxfoundation.org/collaborate/workgroups/networking/tcpprobe
+
+	To compile this code as a module, choose M here: the
+	module will be called tcp_probe.
+
+config NET_DROP_MONITOR
+	tristate "Network packet drop alerting service"
+	depends on INET && TRACEPOINTS
+	---help---
+	This feature provides an alerting service to userspace in the
+	event that packets are discarded in the network stack.  Alerts
+	are broadcast via netlink socket to any listening user space
+	process.  If you don't need network drop alerts, or if you are ok
+	just checking the various proc files and other utilities for
+	drop statistics, say N here.
+
 endmenu
 
 endmenu
 
 source "net/ax25/Kconfig"
+source "net/can/Kconfig"
 source "net/irda/Kconfig"
 source "net/bluetooth/Kconfig"
-source "net/ieee80211/Kconfig"
+source "net/rxrpc/Kconfig"
+
+config FIB_RULES
+	bool
+
+menuconfig WIRELESS
+	bool "Wireless"
+	depends on !S390
+	default y
+
+if WIRELESS
+
+source "net/wireless/Kconfig"
+source "net/mac80211/Kconfig"
+
+endif # WIRELESS
+
+source "net/wimax/Kconfig"
+
+source "net/rfkill/Kconfig"
+source "net/9p/Kconfig"
+source "net/caif/Kconfig"
+source "net/ceph/Kconfig"
+source "net/nfc/Kconfig"
+
 
 endif   # if NET
-endmenu # Networking
 
+# Used by archs to tell that they support BPF_JIT
+config HAVE_BPF_JIT
+	bool
diff --git a/net/Makefile b/net/Makefile
index 065796f5fb1..cbbbe6d657c 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -19,34 +19,56 @@ obj-$(CONFIG_NETFILTER)		+= netfilter/
 obj-$(CONFIG_INET)		+= ipv4/
 obj-$(CONFIG_XFRM)		+= xfrm/
 obj-$(CONFIG_UNIX)		+= unix/
-ifneq ($(CONFIG_IPV6),)
-obj-y				+= ipv6/
-endif
+obj-$(CONFIG_NET)		+= ipv6/
 obj-$(CONFIG_PACKET)		+= packet/
 obj-$(CONFIG_NET_KEY)		+= key/
-obj-$(CONFIG_NET_SCHED)		+= sched/
 obj-$(CONFIG_BRIDGE)		+= bridge/
+obj-$(CONFIG_NET_DSA)		+= dsa/
 obj-$(CONFIG_IPX)		+= ipx/
 obj-$(CONFIG_ATALK)		+= appletalk/
-obj-$(CONFIG_WAN_ROUTER)	+= wanrouter/
 obj-$(CONFIG_X25)		+= x25/
 obj-$(CONFIG_LAPB)		+= lapb/
 obj-$(CONFIG_NETROM)		+= netrom/
 obj-$(CONFIG_ROSE)		+= rose/
 obj-$(CONFIG_AX25)		+= ax25/
+obj-$(CONFIG_CAN)		+= can/
 obj-$(CONFIG_IRDA)		+= irda/
 obj-$(CONFIG_BT)		+= bluetooth/
 obj-$(CONFIG_SUNRPC)		+= sunrpc/
-obj-$(CONFIG_RXRPC)		+= rxrpc/
+obj-$(CONFIG_AF_RXRPC)		+= rxrpc/
 obj-$(CONFIG_ATM)		+= atm/
+obj-$(CONFIG_L2TP)		+= l2tp/
 obj-$(CONFIG_DECNET)		+= decnet/
-obj-$(CONFIG_ECONET)		+= econet/
-obj-$(CONFIG_VLAN_8021Q)	+= 8021q/
+obj-$(CONFIG_PHONET)		+= phonet/
+ifneq ($(CONFIG_VLAN_8021Q),)
+obj-y				+= 8021q/
+endif
 obj-$(CONFIG_IP_DCCP)		+= dccp/
 obj-$(CONFIG_IP_SCTP)		+= sctp/
-obj-$(CONFIG_IEEE80211)		+= ieee80211/
+obj-$(CONFIG_RDS)		+= rds/
+obj-$(CONFIG_WIRELESS)		+= wireless/
+obj-$(CONFIG_MAC80211)		+= mac80211/
 obj-$(CONFIG_TIPC)		+= tipc/
+obj-$(CONFIG_NETLABEL)		+= netlabel/
+obj-$(CONFIG_IUCV)		+= iucv/
+obj-$(CONFIG_RFKILL)		+= rfkill/
+obj-$(CONFIG_NET_9P)		+= 9p/
+obj-$(CONFIG_CAIF)		+= caif/
+ifneq ($(CONFIG_DCB),)
+obj-y				+= dcb/
+endif
+obj-y				+= ieee802154/
+obj-$(CONFIG_MAC802154)		+= mac802154/
 
 ifeq ($(CONFIG_NET),y)
 obj-$(CONFIG_SYSCTL)		+= sysctl_net.o
 endif
+obj-$(CONFIG_WIMAX)		+= wimax/
+obj-$(CONFIG_DNS_RESOLVER)	+= dns_resolver/
+obj-$(CONFIG_CEPH_LIB)		+= ceph/
+obj-$(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_HSR)		+= hsr/
diff --git a/net/TUNABLE b/net/TUNABLE
deleted file mode 100644
index 9913211f07a..00000000000
--- a/net/TUNABLE
+++ /dev/null
@@ -1,50 +0,0 @@
-The following parameters should be tunable at compile time. Some of them
-exist as sysctls too.
-
-This is far from complete
-
-Item			Description
-----------------------------------------------------------------------------
-MAX_LINKS		Maximum number of netlink minor devices. (1-32)
-RIF_TABLE_SIZE		Token ring RIF cache size (tunable)
-AARP_HASH_SIZE		Size of Appletalk hash table (tunable)
-AX25_DEF_T1		AX.25 parameters. These are all tunable via
-AX25_DEF_T2		SIOCAX25SETPARMS
-AX25_DEF_T3		T1-T3,N2 have the meanings in the specification
-AX25_DEF_N2
-AX25_DEF_AXDEFMODE	8 = normal 128 is PE1CHL extended
-AX25_DEF_IPDEFMODE	'D' - datagram  'V' - virtual connection
-AX25_DEF_BACKOFF	'E'xponential 'L'inear
-AX25_DEF_NETROM		Allow netrom 1=Y
-AX25_DF_TEXT		Allow PID=Text 1=Y
-AX25_DEF_WINDOW		Window for normal mode
-AX25_DEF_EWINDOW	Window for PE1CHL mode
-AX25_DEF_DIGI		1 for inband 2 for cross band 3 for both
-AX25_DEF_CONMODE	Allow connected modes 1=Yes
-AX25_ROUTE_MAX		AX.25 route cache size - no currently tunable
-Unnamed (16)		Number of protocol hash slots (tunable)
-DEV_NUMBUFFS		Number of priority levels (not easily tunable)
-Unnamed (300)		Maximum packet backlog queue (tunable)
-MAX_IOVEC		Maximum number of iovecs in a message (tunable)
-MIN_WINDOW		Offered minimum window (tunable)
-MAX_WINDOW		Offered maximum window (tunable)
-MAX_HEADER		Largest physical header (tunable)
-MAX_ADDR_LEN		Largest physical address (tunable)
-SOCK_ARRAY_SIZE		IP socket array hash size (tunable)
-IP_MAX_MEMBERSHIPS	Largest number of groups per socket (BSD style) (tunable)
-16			Hard coded constant for amount of room allowed for
-			cache align and faster forwarding (tunable)
-IP_FRAG_TIME		Time we hold a fragment for. (tunable)
-PORT_MASQ_BEGIN		First port reserved for masquerade (tunable)
-PORT_MASQ_END		Last port used for masquerade	(tunable)
-MASQUERADE_EXPIRE_TCP_FIN	Time we keep a masquerade for after a FIN
-MASQUERADE_EXPIRE_UDP	Time we keep a UDP masquerade for (tunable)
-MAXVIFS			Maximum mrouted vifs (1-32)
-MFC_LINES		Lines in the multicast router cache (tunable)
-
-NetROM parameters are tunable via an ioctl passing a struct
-
-4000			Size a Unix domain socket malloc falls back to 
-			(tunable) should be 8K - a bit for 8K machines like
-			the ALPHA
-
diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c
index 7076097debc..d1c55d8dd0a 100644
--- a/net/appletalk/aarp.c
+++ b/net/appletalk/aarp.c
@@ -29,8 +29,8 @@
  *
  */
 
-#include <linux/config.h>
 #include <linux/if_arp.h>
+#include <linux/slab.h>
 #include <net/sock.h>
 #include <net/datalink.h>
 #include <net/psnap.h>
@@ -39,6 +39,8 @@
 #include <linux/init.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
+#include <linux/export.h>
+#include <linux/etherdevice.h>
 
 int sysctl_aarp_expiry_time = AARP_EXPIRY_TIME;
 int sysctl_aarp_tick_time = AARP_TICK_TIME;
@@ -66,7 +68,7 @@ struct aarp_entry {
 	unsigned long		expires_at;
 	struct atalk_addr	target_addr;
 	struct net_device	*dev;
-	char			hwaddr[6];
+	char			hwaddr[ETH_ALEN];
 	unsigned short		xmit_count;
 	struct aarp_entry	*next;
 };
@@ -119,7 +121,9 @@ static void __aarp_send_query(struct aarp_entry *a)
 
 	/* Set up the buffer */
 	skb_reserve(skb, dev->hard_header_len + aarp_dl->header_length);
-	skb->nh.raw      = skb->h.raw = skb_put(skb, sizeof(*eah));
+	skb_reset_network_header(skb);
+	skb_reset_transport_header(skb);
+	skb_put(skb, sizeof(*eah));
 	skb->protocol    = htons(ETH_P_ATALK);
 	skb->dev	 = dev;
 	eah		 = aarp_hdr(skb);
@@ -131,7 +135,7 @@ static void __aarp_send_query(struct aarp_entry *a)
 	eah->pa_len	 = AARP_PA_ALEN;
 	eah->function	 = htons(AARP_REQUEST);
 
-	memcpy(eah->hw_src, dev->dev_addr, ETH_ALEN);
+	ether_addr_copy(eah->hw_src, dev->dev_addr);
 
 	eah->pa_src_zero = 0;
 	eah->pa_src_net	 = sat->s_net;
@@ -164,7 +168,9 @@ static void aarp_send_reply(struct net_device *dev, struct atalk_addr *us,
 
 	/* Set up the buffer */
 	skb_reserve(skb, dev->hard_header_len + aarp_dl->header_length);
-	skb->nh.raw      = skb->h.raw = skb_put(skb, sizeof(*eah));
+	skb_reset_network_header(skb);
+	skb_reset_transport_header(skb);
+	skb_put(skb, sizeof(*eah));
 	skb->protocol    = htons(ETH_P_ATALK);
 	skb->dev	 = dev;
 	eah		 = aarp_hdr(skb);
@@ -176,7 +182,7 @@ static void aarp_send_reply(struct net_device *dev, struct atalk_addr *us,
 	eah->pa_len	 = AARP_PA_ALEN;
 	eah->function	 = htons(AARP_REPLY);
 
-	memcpy(eah->hw_src, dev->dev_addr, ETH_ALEN);
+	ether_addr_copy(eah->hw_src, dev->dev_addr);
 
 	eah->pa_src_zero = 0;
 	eah->pa_src_net	 = us->s_net;
@@ -185,7 +191,7 @@ static void aarp_send_reply(struct net_device *dev, struct atalk_addr *us,
 	if (!sha)
 		memset(eah->hw_dst, '\0', ETH_ALEN);
 	else
-		memcpy(eah->hw_dst, sha, ETH_ALEN);
+		ether_addr_copy(eah->hw_dst, sha);
 
 	eah->pa_dst_zero = 0;
 	eah->pa_dst_net	 = them->s_net;
@@ -213,7 +219,9 @@ static void aarp_send_probe(struct net_device *dev, struct atalk_addr *us)
 
 	/* Set up the buffer */
 	skb_reserve(skb, dev->hard_header_len + aarp_dl->header_length);
-	skb->nh.raw      = skb->h.raw = skb_put(skb, sizeof(*eah));
+	skb_reset_network_header(skb);
+	skb_reset_transport_header(skb);
+	skb_put(skb, sizeof(*eah));
 	skb->protocol    = htons(ETH_P_ATALK);
 	skb->dev	 = dev;
 	eah		 = aarp_hdr(skb);
@@ -225,7 +233,7 @@ static void aarp_send_probe(struct net_device *dev, struct atalk_addr *us)
 	eah->pa_len	 = AARP_PA_ALEN;
 	eah->function	 = htons(AARP_PROBE);
 
-	memcpy(eah->hw_src, dev->dev_addr, ETH_ALEN);
+	ether_addr_copy(eah->hw_src, dev->dev_addr);
 
 	eah->pa_src_zero = 0;
 	eah->pa_src_net	 = us->s_net;
@@ -325,15 +333,19 @@ static void aarp_expire_timeout(unsigned long unused)
 static int aarp_device_event(struct notifier_block *this, unsigned long event,
 			     void *ptr)
 {
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	int ct;
 
+	if (!net_eq(dev_net(dev), &init_net))
+		return NOTIFY_DONE;
+
 	if (event == NETDEV_DOWN) {
 		write_lock_bh(&aarp_lock);
 
 		for (ct = 0; ct < AARP_HASH_SIZE; ct++) {
-			__aarp_expire_device(&resolved[ct], ptr);
-			__aarp_expire_device(&unresolved[ct], ptr);
-			__aarp_expire_device(&proxies[ct], ptr);
+			__aarp_expire_device(&resolved[ct], dev);
+			__aarp_expire_device(&unresolved[ct], dev);
+			__aarp_expire_device(&proxies[ct], dev);
 		}
 
 		write_unlock_bh(&aarp_lock);
@@ -434,13 +446,14 @@ static void aarp_send_probe_phase1(struct atalk_iface *iface)
 {
 	struct ifreq atreq;
 	struct sockaddr_at *sa = (struct sockaddr_at *)&atreq.ifr_addr;
+	const struct net_device_ops *ops = iface->dev->netdev_ops;
 
 	sa->sat_addr.s_node = iface->address.s_node;
 	sa->sat_addr.s_net = ntohs(iface->address.s_net);
 
 	/* We pass the Net:Node to the drivers/cards by a Device ioctl. */
-	if (!(iface->dev->do_ioctl(iface->dev, &atreq, SIOCSIFADDR))) {
-		(void)iface->dev->do_ioctl(iface->dev, &atreq, SIOCGIFADDR);
+	if (!(ops->ndo_do_ioctl(iface->dev, &atreq, SIOCSIFADDR))) {
+		ops->ndo_do_ioctl(iface->dev, &atreq, SIOCGIFADDR);
 		if (iface->address.s_net != htons(sa->sat_addr.s_net) ||
 		    iface->address.s_node != sa->sat_addr.s_node)
 			iface->status |= ATIF_PROBE_FAIL;
@@ -540,7 +553,7 @@ int aarp_send_ddp(struct net_device *dev, struct sk_buff *skb,
 	int hash;
 	struct aarp_entry *a;
 
-	skb->nh.raw = skb->data;
+	skb_reset_network_header(skb);
 
 	/* Check for LocalTalk first */
 	if (dev->type == ARPHRD_LOCALTLK) {
@@ -589,7 +602,7 @@ int aarp_send_ddp(struct net_device *dev, struct sk_buff *skb,
 
 	/* Non ELAP we cannot do. */
 	if (dev->type != ARPHRD_ETHER)
-		return -1;
+		goto free_it;
 
 	skb->dev = dev;
 	skb->protocol = htons(ETH_P_ATALK);
@@ -624,7 +637,7 @@ int aarp_send_ddp(struct net_device *dev, struct sk_buff *skb,
 	if (!a) {
 		/* Whoops slipped... good job it's an unreliable protocol 8) */
 		write_unlock_bh(&aarp_lock);
-		return -1;
+		goto free_it;
 	}
 
 	/* Set up the queue */
@@ -653,15 +666,21 @@ out_unlock:
 	write_unlock_bh(&aarp_lock);
 
 	/* Tell the ddp layer we have taken over for this frame. */
-	return 0;
+	goto sent;
 
 sendit:
 	if (skb->sk)
 		skb->priority = skb->sk->sk_priority;
-	dev_queue_xmit(skb);
+	if (dev_queue_xmit(skb))
+		goto drop;
 sent:
-	return 1;
+	return NET_XMIT_SUCCESS;
+free_it:
+	kfree_skb(skb);
+drop:
+	return NET_XMIT_DROP;
 }
+EXPORT_SYMBOL(aarp_send_ddp);
 
 /*
  *	An entry in the aarp unresolved queue has become resolved. Send
@@ -707,6 +726,9 @@ static int aarp_rcv(struct sk_buff *skb, struct net_device *dev,
 	struct atalk_addr sa, *ma, da;
 	struct atalk_iface *ifa;
 
+	if (!net_eq(dev_net(dev), &init_net))
+		goto out0;
+
 	/* We only do Ethernet SNAP AARP. */
 	if (dev->type != ARPHRD_ETHER)
 		goto out0;
@@ -759,89 +781,87 @@ static int aarp_rcv(struct sk_buff *skb, struct net_device *dev,
 	}
 
 	switch (function) {
-		case AARP_REPLY:
-			if (!unresolved_count)	/* Speed up */
-				break;
-
-			/* Find the entry.  */
-			a = __aarp_find_entry(unresolved[hash], dev, &sa);
-			if (!a || dev != a->dev)
-				break;
+	case AARP_REPLY:
+		if (!unresolved_count)	/* Speed up */
+			break;
 
-			/* We can fill one in - this is good. */
-			memcpy(a->hwaddr, ea->hw_src, ETH_ALEN);
-			__aarp_resolved(&unresolved[hash], a, hash);
-			if (!unresolved_count)
-				mod_timer(&aarp_timer,
-					  jiffies + sysctl_aarp_expiry_time);
+		/* Find the entry.  */
+		a = __aarp_find_entry(unresolved[hash], dev, &sa);
+		if (!a || dev != a->dev)
 			break;
 
-		case AARP_REQUEST:
-		case AARP_PROBE:
+		/* We can fill one in - this is good. */
+		ether_addr_copy(a->hwaddr, ea->hw_src);
+		__aarp_resolved(&unresolved[hash], a, hash);
+		if (!unresolved_count)
+			mod_timer(&aarp_timer,
+				  jiffies + sysctl_aarp_expiry_time);
+		break;
 
+	case AARP_REQUEST:
+	case AARP_PROBE:
+
+		/*
+		 * If it is my address set ma to my address and reply.
+		 * We can treat probe and request the same.  Probe
+		 * simply means we shouldn't cache the querying host,
+		 * as in a probe they are proposing an address not
+		 * using one.
+		 *
+		 * Support for proxy-AARP added. We check if the
+		 * address is one of our proxies before we toss the
+		 * packet out.
+		 */
+
+		sa.s_node = ea->pa_dst_node;
+		sa.s_net  = ea->pa_dst_net;
+
+		/* See if we have a matching proxy. */
+		ma = __aarp_proxy_find(dev, &sa);
+		if (!ma)
+			ma = &ifa->address;
+		else { /* We need to make a copy of the entry. */
+			da.s_node = sa.s_node;
+			da.s_net = sa.s_net;
+			ma = &da;
+		}
+
+		if (function == AARP_PROBE) {
 			/*
-			 * If it is my address set ma to my address and reply.
-			 * We can treat probe and request the same.  Probe
-			 * simply means we shouldn't cache the querying host,
-			 * as in a probe they are proposing an address not
-			 * using one.
-			 *
-			 * Support for proxy-AARP added. We check if the
-			 * address is one of our proxies before we toss the
-			 * packet out.
+			 * A probe implies someone trying to get an
+			 * address. So as a precaution flush any
+			 * entries we have for this address.
 			 */
+			a = __aarp_find_entry(resolved[sa.s_node %
+						       (AARP_HASH_SIZE - 1)],
+					      skb->dev, &sa);
 
-			sa.s_node = ea->pa_dst_node;
-			sa.s_net  = ea->pa_dst_net;
-
-			/* See if we have a matching proxy. */
-			ma = __aarp_proxy_find(dev, &sa);
-			if (!ma)
-				ma = &ifa->address;
-			else { /* We need to make a copy of the entry. */
-				da.s_node = sa.s_node;
-				da.s_net = da.s_net;
-				ma = &da;
-			}
-
-			if (function == AARP_PROBE) {
-				/*
-				 * A probe implies someone trying to get an
-				 * address. So as a precaution flush any
-				 * entries we have for this address.
-				 */
-				struct aarp_entry *a;
-
-				a = __aarp_find_entry(resolved[sa.s_node %
-							  (AARP_HASH_SIZE - 1)],
-						      skb->dev, &sa);
-
-				/*
-				 * Make it expire next tick - that avoids us
-				 * getting into a probe/flush/learn/probe/
-				 * flush/learn cycle during probing of a slow
-				 * to respond host addr.
-				 */
-				if (a) {
-					a->expires_at = jiffies - 1;
-					mod_timer(&aarp_timer, jiffies +
-							sysctl_aarp_tick_time);
-				}
+			/*
+			 * Make it expire next tick - that avoids us
+			 * getting into a probe/flush/learn/probe/
+			 * flush/learn cycle during probing of a slow
+			 * to respond host addr.
+			 */
+			if (a) {
+				a->expires_at = jiffies - 1;
+				mod_timer(&aarp_timer, jiffies +
+					  sysctl_aarp_tick_time);
 			}
+		}
 
-			if (sa.s_node != ma->s_node)
-				break;
+		if (sa.s_node != ma->s_node)
+			break;
 
-			if (sa.s_net && ma->s_net && sa.s_net != ma->s_net)
-				break;
+		if (sa.s_net && ma->s_net && sa.s_net != ma->s_net)
+			break;
 
-			sa.s_node = ea->pa_src_node;
-			sa.s_net = ea->pa_src_net;
+		sa.s_node = ea->pa_src_node;
+		sa.s_net = ea->pa_src_net;
 
-			/* aarp_my_address has found the address to use for us.
-			*/
-			aarp_send_reply(dev, ma, &sa, ea->hw_src);
-			break;
+		/* aarp_my_address has found the address to use for us.
+		 */
+		aarp_send_reply(dev, ma, &sa, ea->hw_src);
+		break;
 	}
 
 unlock:
@@ -864,9 +884,7 @@ void __init aarp_proto_init(void)
 	aarp_dl = register_snap_client(aarp_snap_id, aarp_rcv);
 	if (!aarp_dl)
 		printk(KERN_CRIT "Unable to register AARP with SNAP.\n");
-	init_timer(&aarp_timer);
-	aarp_timer.function = aarp_expire_timeout;
-	aarp_timer.data	    = 0;
+	setup_timer(&aarp_timer, aarp_expire_timeout, 0);
 	aarp_timer.expires  = jiffies + sysctl_aarp_expiry_time;
 	add_timer(&aarp_timer);
 	register_netdevice_notifier(&aarp_notifier);
@@ -896,7 +914,7 @@ struct aarp_iter_state {
 
 /*
  * Get the aarp entry that is in the chain described
- * by the iterator. 
+ * by the iterator.
  * If pos is set then skip till that index.
  * pos = 1 is the first entry
  */
@@ -906,9 +924,9 @@ static struct aarp_entry *iter_next(struct aarp_iter_state *iter, loff_t *pos)
 	struct aarp_entry **table = iter->table;
 	loff_t off = 0;
 	struct aarp_entry *entry;
-	
+
  rescan:
-	while(ct < AARP_HASH_SIZE) {
+	while (ct < AARP_HASH_SIZE) {
 		for (entry = table[ct]; entry; entry = entry->next) {
 			if (!pos || ++off == *pos) {
 				iter->table = table;
@@ -933,6 +951,7 @@ static struct aarp_entry *iter_next(struct aarp_iter_state *iter, loff_t *pos)
 }
 
 static void *aarp_seq_start(struct seq_file *seq, loff_t *pos)
+	__acquires(aarp_lock)
 {
 	struct aarp_iter_state *iter = seq->private;
 
@@ -951,9 +970,9 @@ static void *aarp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	++*pos;
 
 	/* first line after header */
-	if (v == SEQ_START_TOKEN) 
+	if (v == SEQ_START_TOKEN)
 		entry = iter_next(iter, NULL);
-		
+
 	/* next entry in current bucket */
 	else if (entry->next)
 		entry = entry->next;
@@ -967,6 +986,7 @@ static void *aarp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 }
 
 static void aarp_seq_stop(struct seq_file *seq, void *v)
+	__releases(aarp_lock)
 {
 	read_unlock_bh(&aarp_lock);
 }
@@ -975,7 +995,7 @@ static const char *dt2str(unsigned long ticks)
 {
 	static char buf[32];
 
-	sprintf(buf, "%ld.%02ld", ticks / HZ, ((ticks % HZ) * 100 ) / HZ);
+	sprintf(buf, "%ld.%02ld", ticks / HZ, ((ticks % HZ) * 100) / HZ);
 
 	return buf;
 }
@@ -987,7 +1007,7 @@ static int aarp_seq_show(struct seq_file *seq, void *v)
 	unsigned long now = jiffies;
 
 	if (v == SEQ_START_TOKEN)
-		seq_puts(seq, 
+		seq_puts(seq,
 			 "Address  Interface   Hardware Address"
 			 "   Expires LastSend  Retry Status\n");
 	else {
@@ -995,13 +1015,7 @@ static int aarp_seq_show(struct seq_file *seq, void *v)
 			   ntohs(entry->target_addr.s_net),
 			   (unsigned int) entry->target_addr.s_node,
 			   entry->dev ? entry->dev->name : "????");
-		seq_printf(seq, "%02X:%02X:%02X:%02X:%02X:%02X",
-			   entry->hwaddr[0] & 0xFF,
-			   entry->hwaddr[1] & 0xFF,
-			   entry->hwaddr[2] & 0xFF,
-			   entry->hwaddr[3] & 0xFF,
-			   entry->hwaddr[4] & 0xFF,
-			   entry->hwaddr[5] & 0xFF);
+		seq_printf(seq, "%pM", entry->hwaddr);
 		seq_printf(seq, " %8s",
 			   dt2str((long)entry->expires_at - (long)now));
 		if (iter->table == unresolved)
@@ -1015,11 +1029,11 @@ static int aarp_seq_show(struct seq_file *seq, void *v)
 			   : (iter->table == unresolved) ? "unresolved"
 			   : (iter->table == proxies) ? "proxies"
 			   : "unknown");
-	}				 
+	}
 	return 0;
 }
 
-static struct seq_operations aarp_seq_ops = {
+static const struct seq_operations aarp_seq_ops = {
 	.start  = aarp_seq_start,
 	.next   = aarp_seq_next,
 	.stop   = aarp_seq_stop,
@@ -1028,28 +1042,11 @@ static struct seq_operations aarp_seq_ops = {
 
 static int aarp_seq_open(struct inode *inode, struct file *file)
 {
-	struct seq_file *seq;
-	int rc = -ENOMEM;
-	struct aarp_iter_state *s = kmalloc(sizeof(*s), GFP_KERNEL);
-       
-	if (!s)
-		goto out;
-
-	rc = seq_open(file, &aarp_seq_ops);
-	if (rc)
-		goto out_kfree;
-
-	seq	     = file->private_data;
-	seq->private = s;
-	memset(s, 0, sizeof(*s));
-out:
-	return rc;
-out_kfree:
-	kfree(s);
-	goto out;
+	return seq_open_private(file, &aarp_seq_ops,
+			sizeof(struct aarp_iter_state));
 }
 
-struct file_operations atalk_seq_arp_fops = {
+const struct file_operations atalk_seq_arp_fops = {
 	.owner		= THIS_MODULE,
 	.open           = aarp_seq_open,
 	.read           = seq_read,
diff --git a/net/appletalk/atalk_proc.c b/net/appletalk/atalk_proc.c
index dc4048dd98c..af46bc49e1e 100644
--- a/net/appletalk/atalk_proc.c
+++ b/net/appletalk/atalk_proc.c
@@ -8,12 +8,13 @@
  *	Free Software Foundation, version 2.
  */
 
-#include <linux/config.h>
 #include <linux/init.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
+#include <net/net_namespace.h>
 #include <net/sock.h>
 #include <linux/atalk.h>
+#include <linux/export.h>
 
 
 static __inline__ struct atalk_iface *atalk_get_interface_idx(loff_t pos)
@@ -27,6 +28,7 @@ static __inline__ struct atalk_iface *atalk_get_interface_idx(loff_t pos)
 }
 
 static void *atalk_seq_interface_start(struct seq_file *seq, loff_t *pos)
+	__acquires(atalk_interfaces_lock)
 {
 	loff_t l = *pos;
 
@@ -52,6 +54,7 @@ out:
 }
 
 static void atalk_seq_interface_stop(struct seq_file *seq, void *v)
+	__releases(atalk_interfaces_lock)
 {
 	read_unlock_bh(&atalk_interfaces_lock);
 }
@@ -86,6 +89,7 @@ static __inline__ struct atalk_route *atalk_get_route_idx(loff_t pos)
 }
 
 static void *atalk_seq_route_start(struct seq_file *seq, loff_t *pos)
+	__acquires(atalk_routes_lock)
 {
 	loff_t l = *pos;
 
@@ -111,6 +115,7 @@ out:
 }
 
 static void atalk_seq_route_stop(struct seq_file *seq, void *v)
+	__releases(atalk_routes_lock)
 {
 	read_unlock_bh(&atalk_routes_lock);
 }
@@ -140,42 +145,20 @@ out:
 	return 0;
 }
 
-static __inline__ struct sock *atalk_get_socket_idx(loff_t pos)
-{
-	struct sock *s;
-	struct hlist_node *node;
-
-	sk_for_each(s, node, &atalk_sockets)
-		if (!pos--)
-			goto found;
-	s = NULL;
-found:
-	return s;
-}
-
 static void *atalk_seq_socket_start(struct seq_file *seq, loff_t *pos)
+	__acquires(atalk_sockets_lock)
 {
-	loff_t l = *pos;
-
 	read_lock_bh(&atalk_sockets_lock);
-	return l ? atalk_get_socket_idx(--l) : SEQ_START_TOKEN;
+	return seq_hlist_start_head(&atalk_sockets, *pos);
 }
 
 static void *atalk_seq_socket_next(struct seq_file *seq, void *v, loff_t *pos)
 {
-	struct sock *i;
-
-	++*pos;
-	if (v == SEQ_START_TOKEN) {
-		i = sk_head(&atalk_sockets);
-		goto out;
-	}
-	i = sk_next(v);
-out:
-	return i;
+	return seq_hlist_next(v, &atalk_sockets, pos);
 }
 
 static void atalk_seq_socket_stop(struct seq_file *seq, void *v)
+	__releases(atalk_sockets_lock)
 {
 	read_unlock_bh(&atalk_sockets_lock);
 }
@@ -191,35 +174,36 @@ static int atalk_seq_socket_show(struct seq_file *seq, void *v)
 		goto out;
 	}
 
-	s = v;
+	s = sk_entry(v);
 	at = at_sk(s);
 
 	seq_printf(seq, "%02X   %04X:%02X:%02X  %04X:%02X:%02X  %08X:%08X "
-			"%02X %d\n",
+			"%02X %u\n",
 		   s->sk_type, ntohs(at->src_net), at->src_node, at->src_port,
 		   ntohs(at->dest_net), at->dest_node, at->dest_port,
-		   atomic_read(&s->sk_wmem_alloc),
-		   atomic_read(&s->sk_rmem_alloc),
-		   s->sk_state, SOCK_INODE(s->sk_socket)->i_uid);
+		   sk_wmem_alloc_get(s),
+		   sk_rmem_alloc_get(s),
+		   s->sk_state,
+		   from_kuid_munged(seq_user_ns(seq), sock_i_uid(s)));
 out:
 	return 0;
 }
 
-static struct seq_operations atalk_seq_interface_ops = {
+static const struct seq_operations atalk_seq_interface_ops = {
 	.start  = atalk_seq_interface_start,
 	.next   = atalk_seq_interface_next,
 	.stop   = atalk_seq_interface_stop,
 	.show   = atalk_seq_interface_show,
 };
 
-static struct seq_operations atalk_seq_route_ops = {
+static const struct seq_operations atalk_seq_route_ops = {
 	.start  = atalk_seq_route_start,
 	.next   = atalk_seq_route_next,
 	.stop   = atalk_seq_route_stop,
 	.show   = atalk_seq_route_show,
 };
 
-static struct seq_operations atalk_seq_socket_ops = {
+static const struct seq_operations atalk_seq_socket_ops = {
 	.start  = atalk_seq_socket_start,
 	.next   = atalk_seq_socket_next,
 	.stop   = atalk_seq_socket_stop,
@@ -241,7 +225,7 @@ static int atalk_seq_socket_open(struct inode *inode, struct file *file)
 	return seq_open(file, &atalk_seq_socket_ops);
 }
 
-static struct file_operations atalk_seq_interface_fops = {
+static const struct file_operations atalk_seq_interface_fops = {
 	.owner		= THIS_MODULE,
 	.open		= atalk_seq_interface_open,
 	.read		= seq_read,
@@ -249,7 +233,7 @@ static struct file_operations atalk_seq_interface_fops = {
 	.release	= seq_release,
 };
 
-static struct file_operations atalk_seq_route_fops = {
+static const struct file_operations atalk_seq_route_fops = {
 	.owner		= THIS_MODULE,
 	.open		= atalk_seq_route_open,
 	.read		= seq_read,
@@ -257,7 +241,7 @@ static struct file_operations atalk_seq_route_fops = {
 	.release	= seq_release,
 };
 
-static struct file_operations atalk_seq_socket_fops = {
+static const struct file_operations atalk_seq_socket_fops = {
 	.owner		= THIS_MODULE,
 	.open		= atalk_seq_socket_open,
 	.read		= seq_read,
@@ -272,30 +256,28 @@ int __init atalk_proc_init(void)
 	struct proc_dir_entry *p;
 	int rc = -ENOMEM;
 
-	atalk_proc_dir = proc_mkdir("atalk", proc_net);
+	atalk_proc_dir = proc_mkdir("atalk", init_net.proc_net);
 	if (!atalk_proc_dir)
 		goto out;
-	atalk_proc_dir->owner = THIS_MODULE;
 
-	p = create_proc_entry("interface", S_IRUGO, atalk_proc_dir);
+	p = proc_create("interface", S_IRUGO, atalk_proc_dir,
+			&atalk_seq_interface_fops);
 	if (!p)
 		goto out_interface;
-	p->proc_fops = &atalk_seq_interface_fops;
 
-	p = create_proc_entry("route", S_IRUGO, atalk_proc_dir);
+	p = proc_create("route", S_IRUGO, atalk_proc_dir,
+			&atalk_seq_route_fops);
 	if (!p)
 		goto out_route;
-	p->proc_fops = &atalk_seq_route_fops;
 
-	p = create_proc_entry("socket", S_IRUGO, atalk_proc_dir);
+	p = proc_create("socket", S_IRUGO, atalk_proc_dir,
+			&atalk_seq_socket_fops);
 	if (!p)
 		goto out_socket;
-	p->proc_fops = &atalk_seq_socket_fops;
 
-	p = create_proc_entry("arp", S_IRUGO, atalk_proc_dir);
-	if (!p) 
+	p = proc_create("arp", S_IRUGO, atalk_proc_dir, &atalk_seq_arp_fops);
+	if (!p)
 		goto out_arp;
-	p->proc_fops = &atalk_seq_arp_fops;
 
 	rc = 0;
 out:
@@ -307,7 +289,7 @@ out_socket:
 out_route:
 	remove_proc_entry("interface", atalk_proc_dir);
 out_interface:
-	remove_proc_entry("atalk", proc_net);
+	remove_proc_entry("atalk", init_net.proc_net);
 	goto out;
 }
 
@@ -317,5 +299,5 @@ void __exit atalk_proc_exit(void)
 	remove_proc_entry("route", atalk_proc_dir);
 	remove_proc_entry("socket", atalk_proc_dir);
 	remove_proc_entry("arp", atalk_proc_dir);
-	remove_proc_entry("atalk", proc_net);
+	remove_proc_entry("atalk", init_net.proc_net);
 }
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 697ac55e29d..bfcf6be1d66 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -2,7 +2,7 @@
  *	DDP:	An implementation of the AppleTalk DDP protocol for
  *		Ethernet 'ELAP'.
  *
- *		Alan Cox  <Alan.Cox@linux.org>
+ *		Alan Cox  <alan@lxorguk.ukuu.org.uk>
  *
  *		With more than a little assistance from
  *
@@ -28,16 +28,16 @@
  *		Bradford Johnson	:	IP-over-DDP (experimental)
  *		Jay Schulist		:	Moved IP-over-DDP to its own
  *						driver file. (ipddp.c & ipddp.h)
- *		Jay Schulist		:	Made work as module with 
+ *		Jay Schulist		:	Made work as module with
  *						AppleTalk drivers, cleaned it.
  *		Rob Newberry		:	Added proxy AARP and AARP
  *						procfs, moved probing to AARP
  *						module.
- *              Adrian Sun/ 
- *              Michael Zuelsdorff      :       fix for net.0 packets. don't 
+ *              Adrian Sun/
+ *              Michael Zuelsdorff      :       fix for net.0 packets. don't
  *                                              allow illegal ether/tokentalk
- *                                              port assignment. we lose a 
- *                                              valid localtalk port as a 
+ *                                              port assignment. we lose a
+ *                                              valid localtalk port as a
  *                                              result.
  *		Arnaldo C. de Melo	:	Cleanup, in preparation for
  *						shared skb support 8)
@@ -48,20 +48,22 @@
  *		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/config.h>
 #include <linux/capability.h>
 #include <linux/module.h>
 #include <linux/if_arp.h>
 #include <linux/termios.h>	/* For TIOCOUTQ/INQ */
+#include <linux/compat.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 <linux/atalk.h>
+#include <linux/highmem.h>
 
 struct datalink_proto *ddp_dl, *aarp_dl;
 static const struct proto_ops atalk_dgram_ops;
@@ -91,26 +93,25 @@ static struct sock *atalk_search_socket(struct sockaddr_at *to,
 					struct atalk_iface *atif)
 {
 	struct sock *s;
-	struct hlist_node *node;
 
 	read_lock_bh(&atalk_sockets_lock);
-	sk_for_each(s, node, &atalk_sockets) {
+	sk_for_each(s, &atalk_sockets) {
 		struct atalk_sock *at = at_sk(s);
 
 		if (to->sat_port != at->src_port)
 			continue;
 
-	    	if (to->sat_addr.s_net == ATADDR_ANYNET &&
+		if (to->sat_addr.s_net == ATADDR_ANYNET &&
 		    to->sat_addr.s_node == ATADDR_BCAST)
 			goto found;
 
-	    	if (to->sat_addr.s_net == at->src_net &&
+		if (to->sat_addr.s_net == at->src_net &&
 		    (to->sat_addr.s_node == at->src_node ||
 		     to->sat_addr.s_node == ATADDR_BCAST ||
 		     to->sat_addr.s_node == ATADDR_ANYNODE))
 			goto found;
 
-	    	/* XXXX.0 -- we got a request for this router. make sure
+		/* XXXX.0 -- we got a request for this router. make sure
 		 * that the node is appropriately set. */
 		if (to->sat_addr.s_node == ATADDR_ANYNODE &&
 		    to->sat_addr.s_net != ATADDR_ANYNET &&
@@ -127,8 +128,8 @@ found:
 
 /**
  * atalk_find_or_insert_socket - Try to find a socket matching ADDR
- * @sk - socket to insert in the list if it is not there already
- * @sat - address to search for
+ * @sk: socket to insert in the list if it is not there already
+ * @sat: address to search for
  *
  * Try to find a socket matching ADDR in the socket list, if found then return
  * it. If not, insert SK into the socket list.
@@ -139,11 +140,10 @@ static struct sock *atalk_find_or_insert_socket(struct sock *sk,
 						struct sockaddr_at *sat)
 {
 	struct sock *s;
-	struct hlist_node *node;
 	struct atalk_sock *at;
 
 	write_lock_bh(&atalk_sockets_lock);
-	sk_for_each(s, node, &atalk_sockets) {
+	sk_for_each(s, &atalk_sockets) {
 		at = at_sk(s);
 
 		if (at->src_net == sat->sat_addr.s_net &&
@@ -162,8 +162,7 @@ static void atalk_destroy_timer(unsigned long data)
 {
 	struct sock *sk = (struct sock *)data;
 
-	if (atomic_read(&sk->sk_wmem_alloc) ||
-	    atomic_read(&sk->sk_rmem_alloc)) {
+	if (sk_has_allocations(sk)) {
 		sk->sk_timer.expires = jiffies + SOCK_DESTROY_TIME;
 		add_timer(&sk->sk_timer);
 	} else
@@ -175,12 +174,10 @@ static inline void atalk_destroy_socket(struct sock *sk)
 	atalk_remove_socket(sk);
 	skb_queue_purge(&sk->sk_receive_queue);
 
-	if (atomic_read(&sk->sk_wmem_alloc) ||
-	    atomic_read(&sk->sk_rmem_alloc)) {
-		init_timer(&sk->sk_timer);
+	if (sk_has_allocations(sk)) {
+		setup_timer(&sk->sk_timer, atalk_destroy_timer,
+				(unsigned long)sk);
 		sk->sk_timer.expires	= jiffies + SOCK_DESTROY_TIME;
-		sk->sk_timer.function	= atalk_destroy_timer;
-		sk->sk_timer.data	= (unsigned long)sk;
 		add_timer(&sk->sk_timer);
 	} else
 		sock_put(sk);
@@ -228,12 +225,11 @@ static void atif_drop_device(struct net_device *dev)
 static struct atalk_iface *atif_add_device(struct net_device *dev,
 					   struct atalk_addr *sa)
 {
-	struct atalk_iface *iface = kmalloc(sizeof(*iface), GFP_KERNEL);
+	struct atalk_iface *iface = kzalloc(sizeof(*iface), GFP_KERNEL);
 
 	if (!iface)
 		goto out;
 
-	memset(iface, 0, sizeof(*iface));
 	dev_hold(dev);
 	iface->dev = dev;
 	dev->atalk_ptr = iface;
@@ -297,7 +293,7 @@ static int atif_probe_device(struct atalk_iface *atif)
 
 /* Perform AARP probing for a proxy address */
 static int atif_proxy_probe_device(struct atalk_iface *atif,
-				   struct atalk_addr* proxy_addr)
+				   struct atalk_addr *proxy_addr)
 {
 	int netrange = ntohs(atif->nets.nr_lastnet) -
 			ntohs(atif->nets.nr_firstnet) + 1;
@@ -315,7 +311,7 @@ static int atif_proxy_probe_device(struct atalk_iface *atif,
 
 	if (probe_node == ATADDR_ANYNODE)
 		probe_node = jiffies & 0xFF;
-		
+
 	/* Scan the networks */
 	for (netct = 0; netct <= netrange; netct++) {
 		/* Sweep the available nodes from a given start */
@@ -418,7 +414,7 @@ static struct atalk_iface *atalk_find_interface(__be16 net, int node)
 		if (node == ATADDR_ANYNODE && net != ATADDR_ANYNET &&
 		    ntohs(iface->nets.nr_firstnet) <= ntohs(net) &&
 		    ntohs(net) <= ntohs(iface->nets.nr_lastnet))
-		        break;
+			break;
 	}
 	read_unlock_bh(&atalk_interfaces_lock);
 	return iface;
@@ -433,13 +429,13 @@ static struct atalk_iface *atalk_find_interface(__be16 net, int node)
 static struct atalk_route *atrtr_find(struct atalk_addr *target)
 {
 	/*
-	 * we must search through all routes unless we find a 
+	 * we must search through all routes unless we find a
 	 * host route, because some host routes might overlap
 	 * network routes
 	 */
 	struct atalk_route *net_route = NULL;
 	struct atalk_route *r;
-	
+
 	read_lock_bh(&atalk_routes_lock);
 	for (r = atalk_routes; r; r = r->next) {
 		if (!(r->flags & RTF_UP))
@@ -461,8 +457,8 @@ static struct atalk_route *atrtr_find(struct atalk_addr *target)
 				net_route = r;
 		}
 	}
-	
-	/* 
+
+	/*
 	 * if we found a network route but not a direct host
 	 * route, then return it
 	 */
@@ -541,15 +537,15 @@ static int atrtr_create(struct rtentry *r, struct net_device *devhint)
 		for (iface = atalk_interfaces; iface; iface = iface->next) {
 			if (!riface &&
 			    ntohs(ga->sat_addr.s_net) >=
-			    		ntohs(iface->nets.nr_firstnet) &&
+					ntohs(iface->nets.nr_firstnet) &&
 			    ntohs(ga->sat_addr.s_net) <=
-			    		ntohs(iface->nets.nr_lastnet))
+					ntohs(iface->nets.nr_lastnet))
 				riface = iface;
 
 			if (ga->sat_addr.s_net == iface->address.s_net &&
 			    ga->sat_addr.s_node == iface->address.s_node)
 				riface = iface;
-		}		
+		}
 		read_unlock_bh(&atalk_interfaces_lock);
 
 		retval = -ENETUNREACH;
@@ -560,12 +556,11 @@ static int atrtr_create(struct rtentry *r, struct net_device *devhint)
 	}
 
 	if (!rt) {
-		rt = kmalloc(sizeof(*rt), GFP_ATOMIC);
+		rt = kzalloc(sizeof(*rt), GFP_ATOMIC);
 
 		retval = -ENOBUFS;
 		if (!rt)
 			goto out_unlock;
-		memset(rt, 0, sizeof(*rt));
 
 		rt->next = atalk_routes;
 		atalk_routes = rt;
@@ -586,7 +581,7 @@ out:
 }
 
 /* Delete a route. Find it and discard it */
-static int atrtr_delete(struct atalk_addr * addr)
+static int atrtr_delete(struct atalk_addr *addr)
 {
 	struct atalk_route **r = &atalk_routes;
 	int retval = 0;
@@ -649,9 +644,14 @@ static inline void atalk_dev_down(struct net_device *dev)
 static int ddp_device_event(struct notifier_block *this, unsigned long event,
 			    void *ptr)
 {
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+
+	if (!net_eq(dev_net(dev), &init_net))
+		return NOTIFY_DONE;
+
 	if (event == NETDEV_DOWN)
 		/* Discard any use of this */
-	        atalk_dev_down(ptr);
+		atalk_dev_down(dev);
 
 	return NOTIFY_DONE;
 }
@@ -674,7 +674,7 @@ static int atif_ioctl(int cmd, void __user *arg)
 	if (copy_from_user(&atreq, arg, sizeof(atreq)))
 		return -EFAULT;
 
-	dev = __dev_get_by_name(atreq.ifr_name);
+	dev = __dev_get_by_name(&init_net, atreq.ifr_name);
 	if (!dev)
 		return -ENODEV;
 
@@ -682,195 +682,192 @@ static int atif_ioctl(int cmd, void __user *arg)
 	atif = atalk_find_dev(dev);
 
 	switch (cmd) {
-		case SIOCSIFADDR:
-			if (!capable(CAP_NET_ADMIN))
-				return -EPERM;
-			if (sa->sat_family != AF_APPLETALK)
-				return -EINVAL;
-			if (dev->type != ARPHRD_ETHER &&
-			    dev->type != ARPHRD_LOOPBACK &&
-			    dev->type != ARPHRD_LOCALTLK &&
-			    dev->type != ARPHRD_PPP)
-				return -EPROTONOSUPPORT;
+	case SIOCSIFADDR:
+		if (!capable(CAP_NET_ADMIN))
+			return -EPERM;
+		if (sa->sat_family != AF_APPLETALK)
+			return -EINVAL;
+		if (dev->type != ARPHRD_ETHER &&
+		    dev->type != ARPHRD_LOOPBACK &&
+		    dev->type != ARPHRD_LOCALTLK &&
+		    dev->type != ARPHRD_PPP)
+			return -EPROTONOSUPPORT;
 
-			nr = (struct atalk_netrange *)&sa->sat_zero[0];
-			add_route = 1;
+		nr = (struct atalk_netrange *)&sa->sat_zero[0];
+		add_route = 1;
 
-			/*
-			 * if this is a point-to-point iface, and we already
-			 * have an iface for this AppleTalk address, then we
-			 * should not add a route
-			 */
-			if ((dev->flags & IFF_POINTOPOINT) &&
-			    atalk_find_interface(sa->sat_addr.s_net,
-				    		 sa->sat_addr.s_node)) {
-				printk(KERN_DEBUG "AppleTalk: point-to-point "
-						  "interface added with "
-						  "existing address\n");
-				add_route = 0;
-			}
-			
-			/*
-			 * Phase 1 is fine on LocalTalk but we don't do
-			 * EtherTalk phase 1. Anyone wanting to add it go ahead.
-			 */
-			if (dev->type == ARPHRD_ETHER && nr->nr_phase != 2)
-				return -EPROTONOSUPPORT;
-			if (sa->sat_addr.s_node == ATADDR_BCAST ||
-			    sa->sat_addr.s_node == 254)
+		/*
+		 * if this is a point-to-point iface, and we already
+		 * have an iface for this AppleTalk address, then we
+		 * should not add a route
+		 */
+		if ((dev->flags & IFF_POINTOPOINT) &&
+		    atalk_find_interface(sa->sat_addr.s_net,
+					 sa->sat_addr.s_node)) {
+			printk(KERN_DEBUG "AppleTalk: point-to-point "
+			       "interface added with "
+			       "existing address\n");
+			add_route = 0;
+		}
+
+		/*
+		 * Phase 1 is fine on LocalTalk but we don't do
+		 * EtherTalk phase 1. Anyone wanting to add it go ahead.
+		 */
+		if (dev->type == ARPHRD_ETHER && nr->nr_phase != 2)
+			return -EPROTONOSUPPORT;
+		if (sa->sat_addr.s_node == ATADDR_BCAST ||
+		    sa->sat_addr.s_node == 254)
+			return -EINVAL;
+		if (atif) {
+			/* Already setting address */
+			if (atif->status & ATIF_PROBE)
+				return -EBUSY;
+
+			atif->address.s_net  = sa->sat_addr.s_net;
+			atif->address.s_node = sa->sat_addr.s_node;
+			atrtr_device_down(dev);	/* Flush old routes */
+		} else {
+			atif = atif_add_device(dev, &sa->sat_addr);
+			if (!atif)
+				return -ENOMEM;
+		}
+		atif->nets = *nr;
+
+		/*
+		 * Check if the chosen address is used. If so we
+		 * error and atalkd will try another.
+		 */
+
+		if (!(dev->flags & IFF_LOOPBACK) &&
+		    !(dev->flags & IFF_POINTOPOINT) &&
+		    atif_probe_device(atif) < 0) {
+			atif_drop_device(dev);
+			return -EADDRINUSE;
+		}
+
+		/* Hey it worked - add the direct routes */
+		sa = (struct sockaddr_at *)&rtdef.rt_gateway;
+		sa->sat_family = AF_APPLETALK;
+		sa->sat_addr.s_net  = atif->address.s_net;
+		sa->sat_addr.s_node = atif->address.s_node;
+		sa = (struct sockaddr_at *)&rtdef.rt_dst;
+		rtdef.rt_flags = RTF_UP;
+		sa->sat_family = AF_APPLETALK;
+		sa->sat_addr.s_node = ATADDR_ANYNODE;
+		if (dev->flags & IFF_LOOPBACK ||
+		    dev->flags & IFF_POINTOPOINT)
+			rtdef.rt_flags |= RTF_HOST;
+
+		/* Routerless initial state */
+		if (nr->nr_firstnet == htons(0) &&
+		    nr->nr_lastnet == htons(0xFFFE)) {
+			sa->sat_addr.s_net = atif->address.s_net;
+			atrtr_create(&rtdef, dev);
+			atrtr_set_default(dev);
+		} else {
+			limit = ntohs(nr->nr_lastnet);
+			if (limit - ntohs(nr->nr_firstnet) > 4096) {
+				printk(KERN_WARNING "Too many routes/"
+				       "iface.\n");
 				return -EINVAL;
-			if (atif) {
-				/* Already setting address */
-				if (atif->status & ATIF_PROBE)
-					return -EBUSY;
-
-				atif->address.s_net  = sa->sat_addr.s_net;
-				atif->address.s_node = sa->sat_addr.s_node;
-				atrtr_device_down(dev);	/* Flush old routes */
-			} else {
-				atif = atif_add_device(dev, &sa->sat_addr);
-				if (!atif)
-					return -ENOMEM;
 			}
-			atif->nets = *nr;
+			if (add_route)
+				for (ct = ntohs(nr->nr_firstnet);
+				     ct <= limit; ct++) {
+					sa->sat_addr.s_net = htons(ct);
+					atrtr_create(&rtdef, dev);
+				}
+		}
+		dev_mc_add_global(dev, aarp_mcast);
+		return 0;
 
-			/*
-			 * Check if the chosen address is used. If so we
-			 * error and atalkd will try another.
-			 */
+	case SIOCGIFADDR:
+		if (!atif)
+			return -EADDRNOTAVAIL;
 
-			if (!(dev->flags & IFF_LOOPBACK) &&
-			    !(dev->flags & IFF_POINTOPOINT) &&
-			    atif_probe_device(atif) < 0) {
-				atif_drop_device(dev);
-				return -EADDRINUSE;
-			}
+		sa->sat_family = AF_APPLETALK;
+		sa->sat_addr = atif->address;
+		break;
 
-			/* Hey it worked - add the direct routes */
-			sa = (struct sockaddr_at *)&rtdef.rt_gateway;
-			sa->sat_family = AF_APPLETALK;
-			sa->sat_addr.s_net  = atif->address.s_net;
-			sa->sat_addr.s_node = atif->address.s_node;
-			sa = (struct sockaddr_at *)&rtdef.rt_dst;
-			rtdef.rt_flags = RTF_UP;
-			sa->sat_family = AF_APPLETALK;
-			sa->sat_addr.s_node = ATADDR_ANYNODE;
-			if (dev->flags & IFF_LOOPBACK ||
-			    dev->flags & IFF_POINTOPOINT)
-				rtdef.rt_flags |= RTF_HOST;
-
-			/* Routerless initial state */
-			if (nr->nr_firstnet == htons(0) &&
-			    nr->nr_lastnet == htons(0xFFFE)) {
-				sa->sat_addr.s_net = atif->address.s_net;
-				atrtr_create(&rtdef, dev);
-				atrtr_set_default(dev);
-			} else {
-				limit = ntohs(nr->nr_lastnet);
-				if (limit - ntohs(nr->nr_firstnet) > 4096) {
-					printk(KERN_WARNING "Too many routes/"
-							    "iface.\n");
-					return -EINVAL;
-				}
-				if (add_route)
-					for (ct = ntohs(nr->nr_firstnet);
-					     ct <= limit; ct++) {
-						sa->sat_addr.s_net = htons(ct);
-						atrtr_create(&rtdef, dev);
-					}
-			}
-			dev_mc_add(dev, aarp_mcast, 6, 1);
-			return 0;
+	case SIOCGIFBRDADDR:
+		if (!atif)
+			return -EADDRNOTAVAIL;
 
-		case SIOCGIFADDR:
-			if (!atif)
-				return -EADDRNOTAVAIL;
+		sa->sat_family = AF_APPLETALK;
+		sa->sat_addr.s_net = atif->address.s_net;
+		sa->sat_addr.s_node = ATADDR_BCAST;
+		break;
 
-			sa->sat_family = AF_APPLETALK;
-			sa->sat_addr = atif->address;
-			break;
+	case SIOCATALKDIFADDR:
+	case SIOCDIFADDR:
+		if (!capable(CAP_NET_ADMIN))
+			return -EPERM;
+		if (sa->sat_family != AF_APPLETALK)
+			return -EINVAL;
+		atalk_dev_down(dev);
+		break;
 
-		case SIOCGIFBRDADDR:
-			if (!atif)
-				return -EADDRNOTAVAIL;
+	case SIOCSARP:
+		if (!capable(CAP_NET_ADMIN))
+			return -EPERM;
+		if (sa->sat_family != AF_APPLETALK)
+			return -EINVAL;
+		/*
+		 * for now, we only support proxy AARP on ELAP;
+		 * we should be able to do it for LocalTalk, too.
+		 */
+		if (dev->type != ARPHRD_ETHER)
+			return -EPROTONOSUPPORT;
 
-			sa->sat_family = AF_APPLETALK;
-			sa->sat_addr.s_net = atif->address.s_net;
-			sa->sat_addr.s_node = ATADDR_BCAST;
-			break;
+		/*
+		 * atif points to the current interface on this network;
+		 * we aren't concerned about its current status (at
+		 * least for now), but it has all the settings about
+		 * the network we're going to probe. Consequently, it
+		 * must exist.
+		 */
+		if (!atif)
+			return -EADDRNOTAVAIL;
 
-	        case SIOCATALKDIFADDR:
-	        case SIOCDIFADDR:
-			if (!capable(CAP_NET_ADMIN))
-				return -EPERM;
-			if (sa->sat_family != AF_APPLETALK)
-				return -EINVAL;
-			atalk_dev_down(dev);
-			break;			
-
-		case SIOCSARP:
-			if (!capable(CAP_NET_ADMIN))
-                                return -EPERM;
-                        if (sa->sat_family != AF_APPLETALK)
-                                return -EINVAL;
-                        if (!atif)
-                                return -EADDRNOTAVAIL;
-
-                        /*
-                         * for now, we only support proxy AARP on ELAP;
-                         * we should be able to do it for LocalTalk, too.
-                         */
-                        if (dev->type != ARPHRD_ETHER)
-                                return -EPROTONOSUPPORT;
-
-                        /*
-                         * atif points to the current interface on this network;
-                         * we aren't concerned about its current status (at
-			 * least for now), but it has all the settings about
-			 * the network we're going to probe. Consequently, it
-			 * must exist.
-                         */
-                        if (!atif)
-                                return -EADDRNOTAVAIL;
-
-                        nr = (struct atalk_netrange *)&(atif->nets);
-                        /*
-                         * Phase 1 is fine on Localtalk but we don't do
-                         * Ethertalk phase 1. Anyone wanting to add it go ahead.
-                         */
-                        if (dev->type == ARPHRD_ETHER && nr->nr_phase != 2)
-                                return -EPROTONOSUPPORT;
-
-                        if (sa->sat_addr.s_node == ATADDR_BCAST ||
-			    sa->sat_addr.s_node == 254)
-                                return -EINVAL;
-
-                        /*
-                         * Check if the chosen address is used. If so we
-                         * error and ATCP will try another.
-                         */
-                      	if (atif_proxy_probe_device(atif, &(sa->sat_addr)) < 0)
-                      		return -EADDRINUSE;
-                      	
-			/*
-                         * We now have an address on the local network, and
-			 * the AARP code will defend it for us until we take it
-			 * down. We don't set up any routes right now, because
-			 * ATCP will install them manually via SIOCADDRT.
-                         */
-                        break;
-
-                case SIOCDARP:
-                        if (!capable(CAP_NET_ADMIN))
-                                return -EPERM;
-                        if (sa->sat_family != AF_APPLETALK)
-                                return -EINVAL;
-                        if (!atif)
-                                return -EADDRNOTAVAIL;
-
-                        /* give to aarp module to remove proxy entry */
-                        aarp_proxy_remove(atif->dev, &(sa->sat_addr));
-                        return 0;
+		nr = (struct atalk_netrange *)&(atif->nets);
+		/*
+		 * Phase 1 is fine on Localtalk but we don't do
+		 * Ethertalk phase 1. Anyone wanting to add it go ahead.
+		 */
+		if (dev->type == ARPHRD_ETHER && nr->nr_phase != 2)
+			return -EPROTONOSUPPORT;
+
+		if (sa->sat_addr.s_node == ATADDR_BCAST ||
+		    sa->sat_addr.s_node == 254)
+			return -EINVAL;
+
+		/*
+		 * Check if the chosen address is used. If so we
+		 * error and ATCP will try another.
+		 */
+		if (atif_proxy_probe_device(atif, &(sa->sat_addr)) < 0)
+			return -EADDRINUSE;
+
+		/*
+		 * We now have an address on the local network, and
+		 * the AARP code will defend it for us until we take it
+		 * down. We don't set up any routes right now, because
+		 * ATCP will install them manually via SIOCADDRT.
+		 */
+		break;
+
+	case SIOCDARP:
+		if (!capable(CAP_NET_ADMIN))
+			return -EPERM;
+		if (sa->sat_family != AF_APPLETALK)
+			return -EINVAL;
+		if (!atif)
+			return -EADDRNOTAVAIL;
+
+		/* give to aarp module to remove proxy entry */
+		aarp_proxy_remove(atif->dev, &(sa->sat_addr));
+		return 0;
 	}
 
 	return copy_to_user(arg, &atreq, sizeof(atreq)) ? -EFAULT : 0;
@@ -885,25 +882,25 @@ static int atrtr_ioctl(unsigned int cmd, void __user *arg)
 		return -EFAULT;
 
 	switch (cmd) {
-		case SIOCDELRT:
-			if (rt.rt_dst.sa_family != AF_APPLETALK)
-				return -EINVAL;
-			return atrtr_delete(&((struct sockaddr_at *)
-						&rt.rt_dst)->sat_addr);
-
-		case SIOCADDRT: {
-			struct net_device *dev = NULL;
-			if (rt.rt_dev) {
-				char name[IFNAMSIZ];
-				if (copy_from_user(name, rt.rt_dev, IFNAMSIZ-1))
-					return -EFAULT;
-				name[IFNAMSIZ-1] = '\0';
-				dev = __dev_get_by_name(name);
-				if (!dev)
-					return -ENODEV;
-			}			
-			return atrtr_create(&rt, dev);
+	case SIOCDELRT:
+		if (rt.rt_dst.sa_family != AF_APPLETALK)
+			return -EINVAL;
+		return atrtr_delete(&((struct sockaddr_at *)
+				      &rt.rt_dst)->sat_addr);
+
+	case SIOCADDRT: {
+		struct net_device *dev = NULL;
+		if (rt.rt_dev) {
+			char name[IFNAMSIZ];
+			if (copy_from_user(name, rt.rt_dev, IFNAMSIZ-1))
+				return -EFAULT;
+			name[IFNAMSIZ-1] = '\0';
+			dev = __dev_get_by_name(&init_net, name);
+			if (!dev)
+				return -ENODEV;
 		}
+		return atrtr_create(&rt, dev);
+	}
 	}
 	return -EINVAL;
 }
@@ -919,18 +916,13 @@ static int atrtr_ioctl(unsigned int cmd, void __user *arg)
  * Checksum: This is 'optional'. It's quite likely also a good
  * candidate for assembler hackery 8)
  */
-static unsigned long atalk_sum_partial(const unsigned char *data, 
+static unsigned long atalk_sum_partial(const unsigned char *data,
 				       int len, unsigned long sum)
 {
 	/* This ought to be unwrapped neatly. I'll trust gcc for now */
 	while (len--) {
-		sum += *data;
-		sum <<= 1;
-		if (sum & 0x10000) {
-			sum++;
-			sum &= 0xffff;
-		}
-		data++;
+		sum += *data++;
+		sum = rol16(sum, 1);
 	}
 	return sum;
 }
@@ -940,14 +932,15 @@ static unsigned long atalk_sum_skb(const struct sk_buff *skb, int offset,
 				   int len, unsigned long sum)
 {
 	int start = skb_headlen(skb);
+	struct sk_buff *frag_iter;
 	int i, copy;
 
 	/* checksum stuff in header space */
-	if ( (copy = start - offset) > 0) {
+	if ((copy = start - offset) > 0) {
 		if (copy > len)
 			copy = len;
 		sum = atalk_sum_partial(skb->data + offset, copy, sum);
-		if ( (len -= copy) == 0) 
+		if ((len -= copy) == 0)
 			return sum;
 
 		offset += copy;
@@ -956,20 +949,19 @@ static unsigned long atalk_sum_skb(const struct sk_buff *skb, int offset,
 	/* checksum stuff in frags */
 	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);
 
-		BUG_TRAP(start <= offset + len);
-
-		end = start + skb_shinfo(skb)->frags[i].size;
+		end = start + skb_frag_size(frag);
 		if ((copy = end - offset) > 0) {
 			u8 *vaddr;
-			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 
 			if (copy > len)
 				copy = len;
-			vaddr = kmap_skb_frag(frag);
+			vaddr = kmap_atomic(skb_frag_page(frag));
 			sum = atalk_sum_partial(vaddr + frag->page_offset +
 						  offset - start, copy, sum);
-			kunmap_skb_frag(vaddr);
+			kunmap_atomic(vaddr);
 
 			if (!(len -= copy))
 				return sum;
@@ -978,26 +970,22 @@ static unsigned long atalk_sum_skb(const struct sk_buff *skb, int offset,
 		start = end;
 	}
 
-	if (skb_shinfo(skb)->frag_list) {
-		struct sk_buff *list = skb_shinfo(skb)->frag_list;
-
-		for (; list; list = list->next) {
-			int end;
+	skb_walk_frags(skb, frag_iter) {
+		int end;
 
-			BUG_TRAP(start <= offset + len);
+		WARN_ON(start > offset + len);
 
-			end = start + list->len;
-			if ((copy = end - offset) > 0) {
-				if (copy > len)
-					copy = len;
-				sum = atalk_sum_skb(list, offset - start,
-						    copy, sum);
-				if ((len -= copy) == 0)
-					return sum;
-				offset += copy;
-			}
-			start = end;
+		end = start + frag_iter->len;
+		if ((copy = end - offset) > 0) {
+			if (copy > len)
+				copy = len;
+			sum = atalk_sum_skb(frag_iter, offset - start,
+					    copy, sum);
+			if ((len -= copy) == 0)
+				return sum;
+			offset += copy;
 		}
+		start = end;
 	}
 
 	BUG_ON(len > 0);
@@ -1005,7 +993,7 @@ static unsigned long atalk_sum_skb(const struct sk_buff *skb, int offset,
 	return sum;
 }
 
-static unsigned short atalk_checksum(const struct sk_buff *skb, int len)
+static __be16 atalk_checksum(const struct sk_buff *skb, int len)
 {
 	unsigned long sum;
 
@@ -1013,7 +1001,7 @@ static unsigned short atalk_checksum(const struct sk_buff *skb, int len)
 	sum = atalk_sum_skb(skb, 4, len-4, 0);
 
 	/* Use 0xFFFF for 0. 0 itself means none */
-	return sum ? htons((unsigned short)sum) : 0xFFFF;
+	return sum ? htons((unsigned short)sum) : htons(0xFFFF);
 }
 
 static struct proto ddp_proto = {
@@ -1026,19 +1014,23 @@ static struct proto ddp_proto = {
  * Create a socket. Initialise the socket, blank the addresses
  * set the state.
  */
-static int atalk_create(struct socket *sock, int protocol)
+static int atalk_create(struct net *net, struct socket *sock, int protocol,
+			int kern)
 {
 	struct sock *sk;
 	int rc = -ESOCKTNOSUPPORT;
 
+	if (!net_eq(net, &init_net))
+		return -EAFNOSUPPORT;
+
 	/*
 	 * We permit SOCK_DGRAM and RAW is an extension. It is trivial to do
-	 * and gives you the full ELAP frame. Should be handy for CAP 8) 
+	 * and gives you the full ELAP frame. Should be handy for CAP 8)
 	 */
 	if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM)
 		goto out;
 	rc = -ENOMEM;
-	sk = sk_alloc(PF_APPLETALK, GFP_KERNEL, &ddp_proto, 1);
+	sk = sk_alloc(net, PF_APPLETALK, GFP_KERNEL, &ddp_proto);
 	if (!sk)
 		goto out;
 	rc = 0;
@@ -1057,17 +1049,23 @@ static int atalk_release(struct socket *sock)
 	struct sock *sk = sock->sk;
 
 	if (sk) {
+		sock_hold(sk);
+		lock_sock(sk);
+
 		sock_orphan(sk);
 		sock->sk = NULL;
 		atalk_destroy_socket(sk);
+
+		release_sock(sk);
+		sock_put(sk);
 	}
 	return 0;
 }
 
 /**
  * atalk_pick_and_bind_port - Pick a source port when one is not given
- * @sk - socket to insert into the tables
- * @sat - address to search for
+ * @sk: socket to insert into the tables
+ * @sat: address to search for
  *
  * Pick a source port when one is not given. If we can find a suitable free
  * one, we insert the socket into the tables using it.
@@ -1084,9 +1082,8 @@ static int atalk_pick_and_bind_port(struct sock *sk, struct sockaddr_at *sat)
 	     sat->sat_port < ATPORT_LAST;
 	     sat->sat_port++) {
 		struct sock *s;
-		struct hlist_node *node;
 
-		sk_for_each(s, node, &atalk_sockets) {
+		sk_for_each(s, &atalk_sockets) {
 			struct atalk_sock *at = at_sk(s);
 
 			if (at->src_net == sat->sat_addr.s_net &&
@@ -1136,6 +1133,7 @@ static int atalk_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	struct sockaddr_at *addr = (struct sockaddr_at *)uaddr;
 	struct sock *sk = sock->sk;
 	struct atalk_sock *at = at_sk(sk);
+	int err;
 
 	if (!sock_flag(sk, SOCK_ZAPPED) ||
 	    addr_len != sizeof(struct sockaddr_at))
@@ -1144,37 +1142,44 @@ static int atalk_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	if (addr->sat_family != AF_APPLETALK)
 		return -EAFNOSUPPORT;
 
+	lock_sock(sk);
 	if (addr->sat_addr.s_net == htons(ATADDR_ANYNET)) {
 		struct atalk_addr *ap = atalk_find_primary();
 
+		err = -EADDRNOTAVAIL;
 		if (!ap)
-			return -EADDRNOTAVAIL;
+			goto out;
 
 		at->src_net  = addr->sat_addr.s_net = ap->s_net;
-		at->src_node = addr->sat_addr.s_node= ap->s_node;
+		at->src_node = addr->sat_addr.s_node = ap->s_node;
 	} else {
+		err = -EADDRNOTAVAIL;
 		if (!atalk_find_interface(addr->sat_addr.s_net,
 					  addr->sat_addr.s_node))
-			return -EADDRNOTAVAIL;
+			goto out;
 
 		at->src_net  = addr->sat_addr.s_net;
 		at->src_node = addr->sat_addr.s_node;
 	}
 
 	if (addr->sat_port == ATADDR_ANYPORT) {
-		int n = atalk_pick_and_bind_port(sk, addr);
+		err = atalk_pick_and_bind_port(sk, addr);
 
-		if (n < 0)
-			return n;
+		if (err < 0)
+			goto out;
 	} else {
 		at->src_port = addr->sat_port;
 
+		err = -EADDRINUSE;
 		if (atalk_find_or_insert_socket(sk, addr))
-			return -EADDRINUSE;
+			goto out;
 	}
 
 	sock_reset_flag(sk, SOCK_ZAPPED);
-	return 0;
+	err = 0;
+out:
+	release_sock(sk);
+	return err;
 }
 
 /* Set the address we talk to */
@@ -1184,6 +1189,7 @@ static int atalk_connect(struct socket *sock, struct sockaddr *uaddr,
 	struct sock *sk = sock->sk;
 	struct atalk_sock *at = at_sk(sk);
 	struct sockaddr_at *addr;
+	int err;
 
 	sk->sk_state   = TCP_CLOSE;
 	sock->state = SS_UNCONNECTED;
@@ -1198,22 +1204,23 @@ static int atalk_connect(struct socket *sock, struct sockaddr *uaddr,
 
 	if (addr->sat_addr.s_node == ATADDR_BCAST &&
 	    !sock_flag(sk, SOCK_BROADCAST)) {
-#if 1	
-		printk(KERN_WARNING "%s is broken and did not set "
-				    "SO_BROADCAST. It will break when 2.2 is "
-				    "released.\n",
+#if 1
+		pr_warn("atalk_connect: %s is broken and did not set SO_BROADCAST.\n",
 			current->comm);
 #else
 		return -EACCES;
-#endif			
+#endif
 	}
 
+	lock_sock(sk);
+	err = -EBUSY;
 	if (sock_flag(sk, SOCK_ZAPPED))
 		if (atalk_autobind(sk) < 0)
-			return -EBUSY;
+			goto out;
 
+	err = -ENETUNREACH;
 	if (!atrtr_get_dev(&addr->sat_addr))
-		return -ENETUNREACH;
+		goto out;
 
 	at->dest_port = addr->sat_port;
 	at->dest_net  = addr->sat_addr.s_net;
@@ -1221,7 +1228,10 @@ static int atalk_connect(struct socket *sock, struct sockaddr *uaddr,
 
 	sock->state  = SS_CONNECTED;
 	sk->sk_state = TCP_ESTABLISHED;
-	return 0;
+	err = 0;
+out:
+	release_sock(sk);
+	return err;
 }
 
 /*
@@ -1234,16 +1244,21 @@ static int atalk_getname(struct socket *sock, struct sockaddr *uaddr,
 	struct sockaddr_at sat;
 	struct sock *sk = sock->sk;
 	struct atalk_sock *at = at_sk(sk);
+	int err;
 
+	lock_sock(sk);
+	err = -ENOBUFS;
 	if (sock_flag(sk, SOCK_ZAPPED))
 		if (atalk_autobind(sk) < 0)
-			return -ENOBUFS;
+			goto out;
 
 	*uaddr_len = sizeof(struct sockaddr_at);
+	memset(&sat, 0, sizeof(sat));
 
 	if (peer) {
+		err = -ENOTCONN;
 		if (sk->sk_state != TCP_ESTABLISHED)
-			return -ENOTCONN;
+			goto out;
 
 		sat.sat_addr.s_net  = at->dest_net;
 		sat.sat_addr.s_node = at->dest_node;
@@ -1254,36 +1269,41 @@ static int atalk_getname(struct socket *sock, struct sockaddr *uaddr,
 		sat.sat_port	    = at->src_port;
 	}
 
+	err = 0;
 	sat.sat_family = AF_APPLETALK;
 	memcpy(uaddr, &sat, sizeof(sat));
-	return 0;
+
+out:
+	release_sock(sk);
+	return err;
 }
 
 #if defined(CONFIG_IPDDP) || defined(CONFIG_IPDDP_MODULE)
 static __inline__ int is_ip_over_ddp(struct sk_buff *skb)
 {
-        return skb->data[12] == 22;
+	return skb->data[12] == 22;
 }
 
 static int handle_ip_over_ddp(struct sk_buff *skb)
 {
-        struct net_device *dev = __dev_get_by_name("ipddp0");
+	struct net_device *dev = __dev_get_by_name(&init_net, "ipddp0");
 	struct net_device_stats *stats;
 
 	/* This needs to be able to handle ipddp"N" devices */
-        if (!dev)
-                return -ENODEV;
-
-        skb->protocol = htons(ETH_P_IP);
-        skb_pull(skb, 13);
-        skb->dev   = dev;
-        skb->h.raw = skb->data;
-
-	stats = dev->priv;
-        stats->rx_packets++;
-        stats->rx_bytes += skb->len + 13;
-        netif_rx(skb);  /* Send the SKB up to a higher place. */
-	return 0;
+	if (!dev) {
+		kfree_skb(skb);
+		return NET_RX_DROP;
+	}
+
+	skb->protocol = htons(ETH_P_IP);
+	skb_pull(skb, 13);
+	skb->dev   = dev;
+	skb_reset_transport_header(skb);
+
+	stats = netdev_priv(dev);
+	stats->rx_packets++;
+	stats->rx_bytes += skb->len + 13;
+	return netif_rx(skb);  /* Send the SKB up to a higher place. */
 }
 #else
 /* make it easy for gcc to optimize this test out, i.e. kill the code */
@@ -1291,16 +1311,15 @@ static int handle_ip_over_ddp(struct sk_buff *skb)
 #define handle_ip_over_ddp(skb) 0
 #endif
 
-static void atalk_route_packet(struct sk_buff *skb, struct net_device *dev,
-			       struct ddpehdr *ddp, struct ddpebits *ddphv,
-			       int origlen)
+static int atalk_route_packet(struct sk_buff *skb, struct net_device *dev,
+			      struct ddpehdr *ddp, __u16 len_hops, int origlen)
 {
 	struct atalk_route *rt;
 	struct atalk_addr ta;
 
 	/*
 	 * Don't route multicast, etc., packets, or packets sent to "this
-	 * network" 
+	 * network"
 	 */
 	if (skb->pkt_type != PACKET_HOST || !ddp->deh_dnet) {
 		/*
@@ -1320,10 +1339,12 @@ static void atalk_route_packet(struct sk_buff *skb, struct net_device *dev,
 
 	/* Route the packet */
 	rt = atrtr_find(&ta);
-	if (!rt || ddphv->deh_hops == DDP_MAXHOPS)
+	/* increment hops count */
+	len_hops += 1 << 10;
+	if (!rt || !(len_hops & (15 << 10)))
 		goto free_it;
+
 	/* FIXME: use skb->cb to be able to use shared skbs */
-	ddphv->deh_hops++;
 
 	/*
 	 * Route goes through another gateway, so set the target to the
@@ -1335,14 +1356,13 @@ static void atalk_route_packet(struct sk_buff *skb, struct net_device *dev,
 		ta.s_node = rt->gateway.s_node;
 	}
 
-        /* Fix up skb->len field */
-        skb_trim(skb, min_t(unsigned int, origlen,
+	/* Fix up skb->len field */
+	skb_trim(skb, min_t(unsigned int, origlen,
 			    (rt->dev->hard_header_len +
-			     ddp_dl->header_length + ddphv->deh_len)));
+			     ddp_dl->header_length + (len_hops & 1023))));
 
-	/* Mend the byte order */
 	/* FIXME: use skb->cb to be able to use shared skbs */
-	*((__u16 *)ddp) = ntohs(*((__u16 *)ddphv));
+	ddp->deh_len_hops = htons(len_hops);
 
 	/*
 	 * Send the buffer onwards
@@ -1359,22 +1379,24 @@ static void atalk_route_packet(struct sk_buff *skb, struct net_device *dev,
 		/* 22 bytes - 12 ether, 2 len, 3 802.2 5 snap */
 		struct sk_buff *nskb = skb_realloc_headroom(skb, 32);
 		kfree_skb(skb);
-		if (!nskb) 
-			goto out;
 		skb = nskb;
 	} else
 		skb = skb_unshare(skb, GFP_ATOMIC);
-	
+
 	/*
 	 * If the buffer didn't vanish into the lack of space bitbucket we can
 	 * send it.
 	 */
-	if (skb && aarp_send_ddp(rt->dev, skb, &ta, NULL) == -1)
-		goto free_it;
-out:
-	return;
+	if (skb == NULL)
+		goto drop;
+
+	if (aarp_send_ddp(rt->dev, skb, &ta, NULL) == NET_XMIT_DROP)
+		return NET_RX_DROP;
+	return NET_RX_SUCCESS;
 free_it:
 	kfree_skb(skb);
+drop:
+	return NET_RX_DROP;
 }
 
 /**
@@ -1384,10 +1406,10 @@ free_it:
  *	@pt - packet type
  *
  *	Receive a packet (in skb) from device dev. This has come from the SNAP
- *	decoder, and on entry skb->h.raw is the DDP header, skb->len is the DDP
- *	header, skb->len is the DDP length. The physical headers have been
- *	extracted. PPP should probably pass frames marked as for this layer.
- *	[ie ARPHRD_ETHERTALK]
+ *	decoder, and on entry skb->transport_header is the DDP header, skb->len
+ *	is the DDP header, skb->len is the DDP length. The physical headers
+ *	have been extracted. PPP should probably pass frames marked as for this
+ *	layer.  [ie ARPHRD_ETHERTALK]
  */
 static int atalk_rcv(struct sk_buff *skb, struct net_device *dev,
 		     struct packet_type *pt, struct net_device *orig_dev)
@@ -1396,46 +1418,47 @@ static int atalk_rcv(struct sk_buff *skb, struct net_device *dev,
 	struct sock *sock;
 	struct atalk_iface *atif;
 	struct sockaddr_at tosat;
-        int origlen;
-        struct ddpebits ddphv;
+	int origlen;
+	__u16 len_hops;
+
+	if (!net_eq(dev_net(dev), &init_net))
+		goto drop;
 
 	/* Don't mangle buffer if shared */
-	if (!(skb = skb_share_check(skb, GFP_ATOMIC))) 
+	if (!(skb = skb_share_check(skb, GFP_ATOMIC)))
 		goto out;
-		
+
 	/* Size check and make sure header is contiguous */
 	if (!pskb_may_pull(skb, sizeof(*ddp)))
-		goto freeit;
+		goto drop;
 
 	ddp = ddp_hdr(skb);
 
-	/*
-	 *	Fix up the length field	[Ok this is horrible but otherwise
-	 *	I end up with unions of bit fields and messy bit field order
-	 *	compiler/endian dependencies..]
-	 */
-	*((__u16 *)&ddphv) = ntohs(*((__u16 *)ddp));
+	len_hops = ntohs(ddp->deh_len_hops);
 
 	/* Trim buffer in case of stray trailing data */
 	origlen = skb->len;
-	skb_trim(skb, min_t(unsigned int, skb->len, ddphv.deh_len));
+	skb_trim(skb, min_t(unsigned int, skb->len, len_hops & 1023));
 
 	/*
 	 * Size check to see if ddp->deh_len was crap
 	 * (Otherwise we'll detonate most spectacularly
-	 * in the middle of recvmsg()).
+	 * in the middle of atalk_checksum() or recvmsg()).
 	 */
-	if (skb->len < sizeof(*ddp))
-		goto freeit;
+	if (skb->len < sizeof(*ddp) || skb->len < (len_hops & 1023)) {
+		pr_debug("AppleTalk: dropping corrupted frame (deh_len=%u, "
+			 "skb->len=%u)\n", len_hops & 1023, skb->len);
+		goto drop;
+	}
 
 	/*
 	 * Any checksums. Note we don't do htons() on this == is assumed to be
 	 * valid for net byte orders all over the networking code...
 	 */
 	if (ddp->deh_sum &&
-	    atalk_checksum(skb, ddphv.deh_len) != ddp->deh_sum)
+	    atalk_checksum(skb, len_hops & 1023) != ddp->deh_sum)
 		/* Not a valid AppleTalk frame - dustbin time */
-		goto freeit;
+		goto drop;
 
 	/* Check the packet is aimed at us */
 	if (!ddp->deh_dnet)	/* Net 0 is 'this network' */
@@ -1447,8 +1470,7 @@ static int atalk_rcv(struct sk_buff *skb, struct net_device *dev,
 		/* Not ours, so we route the packet via the correct
 		 * AppleTalk iface
 		 */
-		atalk_route_packet(skb, dev, ddp, &ddphv, origlen);
-		goto out;
+		return atalk_route_packet(skb, dev, ddp, len_hops, origlen);
 	}
 
 	/* if IP over DDP is not selected this code will be optimized out */
@@ -1464,18 +1486,19 @@ static int atalk_rcv(struct sk_buff *skb, struct net_device *dev,
 
 	sock = atalk_search_socket(&tosat, atif);
 	if (!sock) /* But not one of our sockets */
-		goto freeit;
+		goto drop;
 
 	/* Queue packet (standard) */
-	skb->sk = sock;
-
 	if (sock_queue_rcv_skb(sock, skb) < 0)
-		goto freeit;
-out:
-	return 0;
-freeit:
+		goto drop;
+
+	return NET_RX_SUCCESS;
+
+drop:
 	kfree_skb(skb);
-	goto out;
+out:
+	return NET_RX_DROP;
+
 }
 
 /*
@@ -1486,17 +1509,20 @@ freeit:
 static int ltalk_rcv(struct sk_buff *skb, struct net_device *dev,
 		     struct packet_type *pt, struct net_device *orig_dev)
 {
+	if (!net_eq(dev_net(dev), &init_net))
+		goto freeit;
+
 	/* Expand any short form frames */
-	if (skb->mac.raw[2] == 1) {
+	if (skb_mac_header(skb)[2] == 1) {
 		struct ddpehdr *ddp;
 		/* Find our address */
 		struct atalk_addr *ap = atalk_find_dev_addr(dev);
 
-		if (!ap || skb->len < sizeof(struct ddpshdr))
+		if (!ap || skb->len < sizeof(__be16) || skb->len > 1023)
 			goto freeit;
 
 		/* Don't mangle buffer if shared */
-		if (!(skb = skb_share_check(skb, GFP_ATOMIC))) 
+		if (!(skb = skb_share_check(skb, GFP_ATOMIC)))
 			return 0;
 
 		/*
@@ -1507,14 +1533,14 @@ static int ltalk_rcv(struct sk_buff *skb, struct net_device *dev,
 
 		/* Now fill in the long header */
 
-	 	/*
-	 	 * These two first. The mac overlays the new source/dest
-	 	 * network information so we MUST copy these before
-	 	 * we write the network numbers !
-	 	 */
+		/*
+		 * These two first. The mac overlays the new source/dest
+		 * network information so we MUST copy these before
+		 * we write the network numbers !
+		 */
 
-		ddp->deh_dnode = skb->mac.raw[0];     /* From physical header */
-		ddp->deh_snode = skb->mac.raw[1];     /* From physical header */
+		ddp->deh_dnode = skb_mac_header(skb)[0];     /* From physical header */
+		ddp->deh_snode = skb_mac_header(skb)[1];     /* From physical header */
 
 		ddp->deh_dnet  = ap->s_net;	/* Network number */
 		ddp->deh_snet  = ap->s_net;
@@ -1522,13 +1548,10 @@ static int ltalk_rcv(struct sk_buff *skb, struct net_device *dev,
 		/*
 		 * Not sure about this bit...
 		 */
-		ddp->deh_len   = skb->len;
-		ddp->deh_hops  = DDP_MAXHOPS;	/* Non routable, so force a drop
-						   if we slip up later */
-		/* Mend the byte order */
-		*((__u16 *)ddp) = htons(*((__u16 *)ddp));
+		/* Non routable, so force a drop if we slip up later */
+		ddp->deh_len_hops = htons(skb->len + (DDP_MAXHOPS << 10));
 	}
-	skb->h.raw = skb->data;
+	skb_reset_transport_header(skb);
 
 	return atalk_rcv(skb, dev, pt, orig_dev);
 freeit:
@@ -1541,7 +1564,7 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
 {
 	struct sock *sk = sock->sk;
 	struct atalk_sock *at = at_sk(sk);
-	struct sockaddr_at *usat = (struct sockaddr_at *)msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_at *, usat, msg->msg_name);
 	int flags = msg->msg_flags;
 	int loopback = 0;
 	struct sockaddr_at local_satalk, gsat;
@@ -1558,27 +1581,28 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
 	if (len > DDP_MAXSZ)
 		return -EMSGSIZE;
 
+	lock_sock(sk);
 	if (usat) {
+		err = -EBUSY;
 		if (sock_flag(sk, SOCK_ZAPPED))
 			if (atalk_autobind(sk) < 0)
-				return -EBUSY;
+				goto out;
 
+		err = -EINVAL;
 		if (msg->msg_namelen < sizeof(*usat) ||
 		    usat->sat_family != AF_APPLETALK)
-			return -EINVAL;
+			goto out;
 
-		/* netatalk doesn't implement this check */
+		err = -EPERM;
+		/* netatalk didn't implement this check */
 		if (usat->sat_addr.s_node == ATADDR_BCAST &&
 		    !sock_flag(sk, SOCK_BROADCAST)) {
-			printk(KERN_INFO "SO_BROADCAST: Fix your netatalk as "
-					 "it will break before 2.2\n");
-#if 0
-			return -EPERM;
-#endif
+			goto out;
 		}
 	} else {
+		err = -ENOTCONN;
 		if (sk->sk_state != TCP_ESTABLISHED)
-			return -ENOTCONN;
+			goto out;
 		usat = &local_satalk;
 		usat->sat_family      = AF_APPLETALK;
 		usat->sat_port	      = at->dest_port;
@@ -1594,7 +1618,6 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
 
 	if (usat->sat_addr.s_net || usat->sat_addr.s_node == ATADDR_ANYNODE) {
 		rt = atrtr_find(&usat->sat_addr);
-		dev = rt->dev;
 	} else {
 		struct atalk_addr at_hint;
 
@@ -1602,10 +1625,10 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
 		at_hint.s_net  = at->src_net;
 
 		rt = atrtr_find(&at_hint);
-		dev = rt->dev;
 	}
+	err = ENETUNREACH;
 	if (!rt)
-		return -ENETUNREACH;
+		goto out;
 
 	dev = rt->dev;
 
@@ -1613,11 +1636,12 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
 			sk, size, dev->name);
 
 	size += dev->hard_header_len;
+	release_sock(sk);
 	skb = sock_alloc_send_skb(sk, size, (flags & MSG_DONTWAIT), &err);
+	lock_sock(sk);
 	if (!skb)
-		return err;
-	
-	skb->sk = sk;
+		goto out;
+
 	skb_reserve(skb, ddp_dl->header_length);
 	skb_reserve(skb, dev->hard_header_len);
 	skb->dev = dev;
@@ -1625,16 +1649,7 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
 	SOCK_DEBUG(sk, "SK %p: Begin build.\n", sk);
 
 	ddp = (struct ddpehdr *)skb_put(skb, sizeof(struct ddpehdr));
-	ddp->deh_pad  = 0;
-	ddp->deh_hops = 0;
-	ddp->deh_len  = len + sizeof(*ddp);
-	/*
-	 * Fix up the length field [Ok this is horrible but otherwise
-	 * I end up with unions of bit fields and messy bit field order
-	 * compiler/endian dependencies..
-	 */
-	*((__u16 *)ddp) = ntohs(*((__u16 *)ddp));
-
+	ddp->deh_len_hops  = htons(len + sizeof(*ddp));
 	ddp->deh_dnet  = usat->sat_addr.s_net;
 	ddp->deh_snet  = at->src_net;
 	ddp->deh_dnode = usat->sat_addr.s_node;
@@ -1647,10 +1662,11 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
 	err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
 	if (err) {
 		kfree_skb(skb);
-		return -EFAULT;
+		err = -EFAULT;
+		goto out;
 	}
 
-	if (sk->sk_no_check == 1)
+	if (sk->sk_no_check_tx)
 		ddp->deh_sum = 0;
 	else
 		ddp->deh_sum = atalk_checksum(skb, len + sizeof(*ddp));
@@ -1666,10 +1682,10 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
 		if (skb2) {
 			loopback = 1;
 			SOCK_DEBUG(sk, "SK %p: send out(copy).\n", sk);
-			if (aarp_send_ddp(dev, skb2,
-					  &usat->sat_addr, NULL) == -1)
-				kfree_skb(skb2);
-				/* else queued/sent above in the aarp queue */
+			/*
+			 * If it fails it is queued/sent above in the aarp queue
+			 */
+			aarp_send_ddp(dev, skb2, &usat->sat_addr, NULL);
 		}
 	}
 
@@ -1686,7 +1702,8 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
 			rt = atrtr_find(&at_lo);
 			if (!rt) {
 				kfree_skb(skb);
-				return -ENETUNREACH;
+				err = -ENETUNREACH;
+				goto out;
 			}
 			dev = rt->dev;
 			skb->dev = dev;
@@ -1699,62 +1716,63 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
 		    usat = &gsat;
 		}
 
-		if (aarp_send_ddp(dev, skb, &usat->sat_addr, NULL) == -1)
-			kfree_skb(skb);
-		/* else queued/sent above in the aarp queue */
+		/*
+		 * If it fails it is queued/sent above in the aarp queue
+		 */
+		aarp_send_ddp(dev, skb, &usat->sat_addr, NULL);
 	}
 	SOCK_DEBUG(sk, "SK %p: Done write (%Zd).\n", sk, len);
 
-	return len;
+out:
+	release_sock(sk);
+	return err ? : len;
 }
 
 static int atalk_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
 			 size_t size, int flags)
 {
 	struct sock *sk = sock->sk;
-	struct sockaddr_at *sat = (struct sockaddr_at *)msg->msg_name;
 	struct ddpehdr *ddp;
 	int copied = 0;
+	int offset = 0;
 	int err = 0;
-        struct ddpebits ddphv;
-	struct sk_buff *skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
+	struct sk_buff *skb;
+
+	skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
 						flags & MSG_DONTWAIT, &err);
+	lock_sock(sk);
+
 	if (!skb)
-		return err;
+		goto out;
 
 	/* FIXME: use skb->cb to be able to use shared skbs */
 	ddp = ddp_hdr(skb);
-	*((__u16 *)&ddphv) = ntohs(*((__u16 *)ddp));
+	copied = ntohs(ddp->deh_len_hops) & 1023;
 
-	if (sk->sk_type == SOCK_RAW) {
-		copied = ddphv.deh_len;
-		if (copied > size) {
-			copied = size;
-			msg->msg_flags |= MSG_TRUNC;
-		}
-
-		err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
-	} else {
-		copied = ddphv.deh_len - sizeof(*ddp);
-		if (copied > size) {
-			copied = size;
-			msg->msg_flags |= MSG_TRUNC;
-		}
-		err = skb_copy_datagram_iovec(skb, sizeof(*ddp),
-					      msg->msg_iov, copied);
+	if (sk->sk_type != SOCK_RAW) {
+		offset = sizeof(*ddp);
+		copied -= offset;
 	}
 
-	if (!err) {
-		if (sat) {
-			sat->sat_family      = AF_APPLETALK;
-			sat->sat_port        = ddp->deh_sport;
-			sat->sat_addr.s_node = ddp->deh_snode;
-			sat->sat_addr.s_net  = ddp->deh_snet;
-		}
-		msg->msg_namelen = sizeof(*sat);
+	if (copied > size) {
+		copied = size;
+		msg->msg_flags |= MSG_TRUNC;
+	}
+	err = skb_copy_datagram_iovec(skb, offset, msg->msg_iov, copied);
+
+	if (!err && msg->msg_name) {
+		DECLARE_SOCKADDR(struct sockaddr_at *, sat, msg->msg_name);
+		sat->sat_family      = AF_APPLETALK;
+		sat->sat_port        = ddp->deh_sport;
+		sat->sat_addr.s_node = ddp->deh_snode;
+		sat->sat_addr.s_net  = ddp->deh_snet;
+		msg->msg_namelen     = sizeof(*sat);
 	}
 
 	skb_free_datagram(sk, skb);	/* Free the datagram. */
+
+out:
+	release_sock(sk);
 	return err ? : copied;
 }
 
@@ -1769,63 +1787,83 @@ static int atalk_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 	void __user *argp = (void __user *)arg;
 
 	switch (cmd) {
-		/* Protocol layer */
-		case TIOCOUTQ: {
-			long amount = sk->sk_sndbuf -
-				      atomic_read(&sk->sk_wmem_alloc);
-
-			if (amount < 0)
-				amount = 0;
-			rc = put_user(amount, (int __user *)argp);
-			break;
-		}
-		case TIOCINQ: {
-			/*
-			 * These two are safe on a single CPU system as only
-			 * user tasks fiddle here
-			 */
-			struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
-			long amount = 0;
+	/* Protocol layer */
+	case TIOCOUTQ: {
+		long amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk);
+
+		if (amount < 0)
+			amount = 0;
+		rc = put_user(amount, (int __user *)argp);
+		break;
+	}
+	case TIOCINQ: {
+		/*
+		 * These two are safe on a single CPU system as only
+		 * user tasks fiddle here
+		 */
+		struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
+		long amount = 0;
 
-			if (skb)
-				amount = skb->len - sizeof(struct ddpehdr);
-			rc = put_user(amount, (int __user *)argp);
-			break;
-		}
-		case SIOCGSTAMP:
-			rc = sock_get_timestamp(sk, argp);
-			break;
-		/* Routing */
-		case SIOCADDRT:
-		case SIOCDELRT:
-			rc = -EPERM;
-			if (capable(CAP_NET_ADMIN))
-				rc = atrtr_ioctl(cmd, argp);
-			break;
-		/* Interface */
-		case SIOCGIFADDR:
-		case SIOCSIFADDR:
-		case SIOCGIFBRDADDR:
-		case SIOCATALKDIFADDR:
-		case SIOCDIFADDR:
-		case SIOCSARP:		/* proxy AARP */
-		case SIOCDARP:		/* proxy AARP */
-			rtnl_lock();
-			rc = atif_ioctl(cmd, argp);
-			rtnl_unlock();
-			break;
+		if (skb)
+		amount = skb->len - sizeof(struct ddpehdr);
+		rc = put_user(amount, (int __user *)argp);
+		break;
+	}
+	case SIOCGSTAMP:
+		rc = sock_get_timestamp(sk, argp);
+		break;
+	case SIOCGSTAMPNS:
+		rc = sock_get_timestampns(sk, argp);
+		break;
+	/* Routing */
+	case SIOCADDRT:
+	case SIOCDELRT:
+		rc = -EPERM;
+		if (capable(CAP_NET_ADMIN))
+			rc = atrtr_ioctl(cmd, argp);
+		break;
+	/* Interface */
+	case SIOCGIFADDR:
+	case SIOCSIFADDR:
+	case SIOCGIFBRDADDR:
+	case SIOCATALKDIFADDR:
+	case SIOCDIFADDR:
+	case SIOCSARP:		/* proxy AARP */
+	case SIOCDARP:		/* proxy AARP */
+		rtnl_lock();
+		rc = atif_ioctl(cmd, argp);
+		rtnl_unlock();
+		break;
 	}
 
 	return rc;
 }
 
-static struct net_proto_family atalk_family_ops = {
+
+#ifdef CONFIG_COMPAT
+static int atalk_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
+{
+	/*
+	 * SIOCATALKDIFADDR is a SIOCPROTOPRIVATE ioctl number, so we
+	 * cannot handle it in common code. The data we access if ifreq
+	 * here is compatible, so we can simply call the native
+	 * handler.
+	 */
+	if (cmd == SIOCATALKDIFADDR)
+		return atalk_ioctl(sock, cmd, (unsigned long)compat_ptr(arg));
+
+	return -ENOIOCTLCMD;
+}
+#endif
+
+
+static const struct net_proto_family atalk_family_ops = {
 	.family		= PF_APPLETALK,
 	.create		= atalk_create,
 	.owner		= THIS_MODULE,
 };
 
-static const struct proto_ops SOCKOPS_WRAPPED(atalk_dgram_ops) = {
+static const struct proto_ops atalk_dgram_ops = {
 	.family		= PF_APPLETALK,
 	.owner		= THIS_MODULE,
 	.release	= atalk_release,
@@ -1836,6 +1874,9 @@ static const struct proto_ops SOCKOPS_WRAPPED(atalk_dgram_ops) = {
 	.getname	= atalk_getname,
 	.poll		= datagram_poll,
 	.ioctl		= atalk_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= atalk_compat_ioctl,
+#endif
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= sock_no_setsockopt,
@@ -1846,31 +1887,27 @@ static const struct proto_ops SOCKOPS_WRAPPED(atalk_dgram_ops) = {
 	.sendpage	= sock_no_sendpage,
 };
 
-#include <linux/smp_lock.h>
-SOCKOPS_WRAP(atalk_dgram, PF_APPLETALK);
-
 static struct notifier_block ddp_notifier = {
 	.notifier_call	= ddp_device_event,
 };
 
-static struct packet_type ltalk_packet_type = {
-	.type		= __constant_htons(ETH_P_LOCALTALK),
+static struct packet_type ltalk_packet_type __read_mostly = {
+	.type		= cpu_to_be16(ETH_P_LOCALTALK),
 	.func		= ltalk_rcv,
 };
 
-static struct packet_type ppptalk_packet_type = {
-	.type		= __constant_htons(ETH_P_PPPTALK),
+static struct packet_type ppptalk_packet_type __read_mostly = {
+	.type		= cpu_to_be16(ETH_P_PPPTALK),
 	.func		= atalk_rcv,
 };
 
 static unsigned char ddp_snap_id[] = { 0x08, 0x00, 0x07, 0x80, 0x9B };
 
 /* Export symbols for use by drivers when AppleTalk is a module */
-EXPORT_SYMBOL(aarp_send_ddp);
 EXPORT_SYMBOL(atrtr_get_dev);
 EXPORT_SYMBOL(atalk_find_dev_addr);
 
-static char atalk_err_snap[] __initdata =
+static const char atalk_err_snap[] __initconst =
 	KERN_CRIT "Unable to register DDP with SNAP.\n";
 
 /* Called by proto.c on kernel start up */
@@ -1924,6 +1961,6 @@ static void __exit atalk_exit(void)
 module_exit(atalk_exit);
 
 MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Alan Cox <Alan.Cox@linux.org>");
+MODULE_AUTHOR("Alan Cox <alan@lxorguk.ukuu.org.uk>");
 MODULE_DESCRIPTION("AppleTalk 0.20\n");
 MODULE_ALIAS_NETPROTO(PF_APPLETALK);
diff --git a/net/appletalk/dev.c b/net/appletalk/dev.c
index 1237e208e24..6c8016f6186 100644
--- a/net/appletalk/dev.c
+++ b/net/appletalk/dev.c
@@ -9,33 +9,16 @@
 #include <linux/if_arp.h>
 #include <linux/if_ltalk.h>
 
-static int ltalk_change_mtu(struct net_device *dev, int mtu)
-{
-	return -EINVAL;
-}
-
-static int ltalk_mac_addr(struct net_device *dev, void *addr)
-{	
-	return -EINVAL;
-}
-
 static void ltalk_setup(struct net_device *dev)
 {
 	/* Fill in the fields of the device structure with localtalk-generic values. */
-	
-	dev->change_mtu		= ltalk_change_mtu;
-	dev->hard_header	= NULL;
-	dev->rebuild_header 	= NULL;
-	dev->set_mac_address 	= ltalk_mac_addr;
-	dev->hard_header_cache	= NULL;
-	dev->header_cache_update= NULL;
 
 	dev->type		= ARPHRD_LOCALTLK;
 	dev->hard_header_len 	= LTALK_HLEN;
 	dev->mtu		= LTALK_MTU;
 	dev->addr_len		= LTALK_ALEN;
-	dev->tx_queue_len	= 10;	
-	
+	dev->tx_queue_len	= 10;
+
 	dev->broadcast[0]	= 0xFF;
 
 	dev->flags		= IFF_BROADCAST|IFF_MULTICAST|IFF_NOARP;
diff --git a/net/appletalk/sysctl_net_atalk.c b/net/appletalk/sysctl_net_atalk.c