dev.c

/*
 * 	NET3	Protocol independent device support routines.
 *
 *		This program is free software; you can redistribute it and/or
 *		modify it under the terms of the GNU General Public License
 *		as published by the Free Software Foundation; either version
 *		2 of the License, or (at your option) any later version.
 *
 *	Derived from the non IP parts of dev.c 1.0.19
 * 		Authors:	Ross Biro
 *				Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *				Mark Evans, <evansmp@uhura.aston.ac.uk>
 *
 *	Additional Authors:
 *		Florian la Roche <rzsfl@rz.uni-sb.de>
 *		Alan Cox <gw4pts@gw4pts.ampr.org>
 *		David Hinds <dahinds@users.sourceforge.net>
 *		Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
 *		Adam Sulmicki <adam@cfar.umd.edu>
 *              Pekka Riikonen <priikone@poesidon.pspt.fi>
 *
 *	Changes:
 *              D.J. Barrow     :       Fixed bug where dev->refcnt gets set
 *              			to 2 if register_netdev gets called
 *              			before net_dev_init & also removed a
 *              			few lines of code in the process.
 *		Alan Cox	:	device private ioctl copies fields back.
 *		Alan Cox	:	Transmit queue code does relevant
 *					stunts to keep the queue safe.
 *		Alan Cox	:	Fixed double lock.
 *		Alan Cox	:	Fixed promisc NULL pointer trap
 *		????????	:	Support the full private ioctl range
 *		Alan Cox	:	Moved ioctl permission check into
 *					drivers
 *		Tim Kordas	:	SIOCADDMULTI/SIOCDELMULTI
 *		Alan Cox	:	100 backlog just doesn't cut it when
 *					you start doing multicast video 8)
 *		Alan Cox	:	Rewrote net_bh and list manager.
 *		Alan Cox	: 	Fix ETH_P_ALL echoback lengths.
 *		Alan Cox	:	Took out transmit every packet pass
 *					Saved a few bytes in the ioctl handler
 *		Alan Cox	:	Network driver sets packet type before
 *					calling netif_rx. Saves a function
 *					call a packet.
 *		Alan Cox	:	Hashed net_bh()
 *		Richard Kooijman:	Timestamp fixes.
 *		Alan Cox	:	Wrong field in SIOCGIFDSTADDR
 *		Alan Cox	:	Device lock protection.
 *		Alan Cox	: 	Fixed nasty side effect of device close
 *					changes.
 *		Rudi Cilibrasi	:	Pass the right thing to
 *					set_mac_address()
 *		Dave Miller	:	32bit quantity for the device lock to
 *					make it work out on a Sparc.
 *		Bjorn Ekwall	:	Added KERNELD hack.
 *		Alan Cox	:	Cleaned up the backlog initialise.
 *		Craig Metz	:	SIOCGIFCONF fix if space for under
 *					1 device.
 *	    Thomas Bogendoerfer :	Return ENODEV for dev_open, if there
 *					is no device open function.
 *		Andi Kleen	:	Fix error reporting for SIOCGIFCONF
 *	    Michael Chastain	:	Fix signed/unsigned for SIOCGIFCONF
 *		Cyrus Durgin	:	Cleaned for KMOD
 *		Adam Sulmicki   :	Bug Fix : Network Device Unload
 *					A network device unload needs to purge
 *					the backlog queue.
 *	Paul Rusty Russell	:	SIOCSIFNAME
 *              Pekka Riikonen  :	Netdev boot-time settings code
 *              Andrew Morton   :       Make unregister_netdevice wait
 *              			indefinitely on dev->refcnt
 * 		J Hadi Salim	:	- Backlog queue sampling
 *				        - netif_rx() feedback
 */

#include <asm/uaccess.h>
#include <asm/system.h>
#include <linux/bitops.h>
#include <linux/capability.h>
#include <linux/config.h>
#include <linux/cpu.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>
#include <linux/sockios.h>
#include <linux/errno.h>
#include <linux/interrupt.h>
#include <linux/if_ether.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/notifier.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <linux/rtnetlink.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/stat.h>
#include <linux/if_bridge.h>
#include <linux/divert.h>
#include <net/dst.h>
#include <net/pkt_sched.h>
#include <net/checksum.h>
#include <linux/highmem.h>
#include <linux/init.h>
#include <linux/kmod.h>
#include <linux/module.h>
#include <linux/kallsyms.h>
#include <linux/netpoll.h>
#include <linux/rcupdate.h>
#include <linux/delay.h>
#ifdef CONFIG_NET_RADIO
#include <linux/wireless.h>		/* Note : will define WIRELESS_EXT */
#include <net/iw_handler.h>
#endif	/* CONFIG_NET_RADIO */
#include <asm/current.h>

/*
 *	The list of packet types we will receive (as opposed to discard)
 *	and the routines to invoke.
 *
 *	Why 16. Because with 16 the only overlap we get on a hash of the
 *	low nibble of the protocol value is RARP/SNAP/X.25.
 *
 *      NOTE:  That is no longer true with the addition of VLAN tags.  Not
 *             sure which should go first, but I bet it won't make much
 *             difference if we are running VLANs.  The good news is that
 *             this protocol won't be in the list unless compiled in, so
 *             the average user (w/out VLANs) will not be adversly affected.
 *             --BLG
 *
 *		0800	IP
 *		8100    802.1Q VLAN
 *		0001	802.3
 *		0002	AX.25
 *		0004	802.2
 *		8035	RARP
 *		0005	SNAP
 *		0805	X.25
 *		0806	ARP
 *		8137	IPX
 *		0009	Localtalk
 *		86DD	IPv6
 */

static DEFINE_SPINLOCK(ptype_lock);
static struct list_head ptype_base[16];	/* 16 way hashed list */
static struct list_head ptype_all;		/* Taps */

/*
 * The @dev_base list is protected by @dev_base_lock and the rtln
 * semaphore.
 *
 * Pure readers hold dev_base_lock for reading.
 *
 * Writers must hold the rtnl semaphore while they loop through the
 * dev_base list, and hold dev_base_lock for writing when they do the
 * actual updates.  This allows pure readers to access the list even
 * while a writer is preparing to update it.
 *
 * To put it another way, dev_base_lock is held for writing only to
 * protect against pure readers; the rtnl semaphore provides the
 * protection against other writers.
 *
 * See, for example usages, register_netdevice() and
 * unregister_netdevice(), which must be called with the rtnl
 * semaphore held.
 */
struct net_device *dev_base;
static struct net_device **dev_tail = &dev_base;
DEFINE_RWLOCK(dev_base_lock);

EXPORT_SYMBOL(dev_base);
EXPORT_SYMBOL(dev_base_lock);

#define NETDEV_HASHBITS	8
static struct hlist_head dev_name_head[1<<NETDEV_HASHBITS];
static struct hlist_head dev_index_head[1<<NETDEV_HASHBITS];

static inline struct hlist_head *dev_name_hash(const char *name)
{
	unsigned hash = full_name_hash(name, strnlen(name, IFNAMSIZ));
	return &dev_name_head[hash & ((1<<NETDEV_HASHBITS)-1)];
}

static inline struct hlist_head *dev_index_hash(int ifindex)
{
	return &dev_index_head[ifindex & ((1<<NETDEV_HASHBITS)-1)];
}

/*
 *	Our notifier list
 */

static struct notifier_block *netdev_chain;

/*
 *	Device drivers call our routines to queue packets here. We empty the
 *	queue in the local softnet handler.
 */
DEFINE_PER_CPU(struct softnet_data, softnet_data) = { NULL };

#ifdef CONFIG_SYSFS
extern int netdev_sysfs_init(void);
extern int netdev_register_sysfs(struct net_device *);
extern void netdev_unregister_sysfs(struct net_device *);
#else
#define netdev_sysfs_init()	 	(0)
#define netdev_register_sysfs(dev)	(0)
#define	netdev_unregister_sysfs(dev)	do { } while(0)
#endif


/*******************************************************************************

		Protocol management and registration routines

*******************************************************************************/

/*
 *	For efficiency
 */

int netdev_nit;

/*
 *	Add a protocol ID to the list. Now that the input handler is
 *	smarter we can dispense with all the messy stuff that used to be
 *	here.
 *
 *	BEWARE!!! Protocol handlers, mangling input packets,
 *	MUST BE last in hash buckets and checking protocol handlers
 *	MUST start from promiscuous ptype_all chain in net_bh.
 *	It is true now, do not change it.
 *	Explanation follows: if protocol handler, mangling packet, will
 *	be the first on list, it is not able to sense, that packet
 *	is cloned and should be copied-on-write, so that it will
 *	change it and subsequent readers will get broken packet.
 *							--ANK (980803)
 */

/**
 *	dev_add_pack - add packet handler
 *	@pt: packet type declaration
 *
 *	Add a protocol handler to the networking stack. The passed &packet_type
 *	is linked into kernel lists and may not be freed until it has been
 *	removed from the kernel lists.
 *
 *	This call does not sleep therefore it can not 
 *	guarantee all CPU's that are in middle of receiving packets
 *	will see the new packet type (until the next received packet).
 */

void dev_add_pack(struct packet_type *pt)
{
	int hash;

	spin_lock_bh(&ptype_lock);
	if (pt->type == htons(ETH_P_ALL)) {
		netdev_nit++;
		list_add_rcu(&pt->list, &ptype_all);
	} else {
		hash = ntohs(pt->type) & 15;
		list_add_rcu(&pt->list, &ptype_base[hash]);
	}
	spin_unlock_bh(&ptype_lock);
}

/**
 *	__dev_remove_pack	 - remove packet handler
 *	@pt: packet type declaration
 *
 *	Remove a protocol handler that was previously added to the kernel
 *	protocol handlers by dev_add_pack(). The passed &packet_type is removed
 *	from the kernel lists and can be freed or reused once this function
 *	returns. 
 *
 *      The packet type might still be in use by receivers
 *	and must not be freed until after all the CPU's have gone
 *	through a quiescent state.
 */
void __dev_remove_pack(struct packet_type *pt)
{
	struct list_head *head;
	struct packet_type *pt1;

	spin_lock_bh(&ptype_lock);

	if (pt->type == htons(ETH_P_ALL)) {
		netdev_nit--;
		head = &ptype_all;
	} else
		head = &ptype_base[ntohs(pt->type) & 15];

	list_for_each_entry(pt1, head, list) {
		if (pt == pt1) {
			list_del_rcu(&pt->list);
			goto out;
		}
	}

	printk(KERN_WARNING "dev_remove_pack: %p not found.\n", pt);
out:
	spin_unlock_bh(&ptype_lock);
}
/**
 *	dev_remove_pack	 - remove packet handler
 *	@pt: packet type declaration
 *
 *	Remove a protocol handler that was previously added to the kernel
 *	protocol handlers by dev_add_pack(). The passed &packet_type is removed
 *	from the kernel lists and can be freed or reused once this function
 *	returns.
 *
 *	This call sleeps to guarantee that no CPU is looking at the packet
 *	type after return.
 */
void dev_remove_pack(struct packet_type *pt)
{
	__dev_remove_pack(pt);
	
	synchronize_net();
}

/******************************************************************************

		      Device Boot-time Settings Routines

*******************************************************************************/

/* Boot time configuration table */
static struct netdev_boot_setup dev_boot_setup[NETDEV_BOOT_SETUP_MAX];

/**
 *	netdev_boot_setup_add	- add new setup entry
 *	@name: name of the device
 *	@map: configured settings for the device
 *
 *	Adds new setup entry to the dev_boot_setup list.  The function
 *	returns 0 on error and 1 on success.  This is a generic routine to
 *	all netdevices.
 */
static int netdev_boot_setup_add(char *name, struct ifmap *map)
{
	struct netdev_boot_setup *s;
	int i;

	s = dev_boot_setup;
	for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) {
		if (s[i].name[0] == '\0' || s[i].name[0] == ' ') {
			memset(s[i].name, 0, sizeof(s[i].name));
			strcpy(s[i].name, name);
			memcpy(&s[i].map, map, sizeof(s[i].map));
			break;
		}
	}

	return i >= NETDEV_BOOT_SETUP_MAX ? 0 : 1;
}

/**
 *	netdev_boot_setup_check	- check boot time settings
 *	@dev: the netdevice
 *
 * 	Check boot time settings for the device.
 *	The found settings are set for the device to be used
 *	later in the device probing.
 *	Returns 0 if no settings found, 1 if they are.
 */
int netdev_boot_setup_check(struct net_device *dev)
{
	struct netdev_boot_setup *s = dev_boot_setup;
	int i;

	for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) {
		if (s[i].name[0] != '\0' && s[i].name[0] != ' ' &&
		    !strncmp(dev->name, s[i].name, strlen(s[i].name))) {
			dev->irq 	= s[i].map.irq;
			dev->base_addr 	= s[i].map.base_addr;
			dev->mem_start 	= s[i].map.mem_start;
			dev->mem_end 	= s[i].map.mem_end;
			return 1;
		}
	}
	return 0;
}


/**
 *	netdev_boot_base	- get address from boot time settings
 *	@prefix: prefix for network device
 *	@unit: id for network device
 *
 * 	Check boot time settings for the base address of device.
 *	The found settings are set for the device to be used
 *	later in the device probing.
 *	Returns 0 if no settings found.
 */
unsigned long netdev_boot_base(const char *prefix, int unit)
{
	const struct netdev_boot_setup *s = dev_boot_setup;
	char name[IFNAMSIZ];
	int i;

	sprintf(name, "%s%d", prefix, unit);

	/*
	 * If device already registered then return base of 1
	 * to indicate not to probe for this interface
	 */
	if (__dev_get_by_name(name))
		return 1;

	for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++)
		if (!strcmp(name, s[i].name))
			return s[i].map.base_addr;
	return 0;
}

/*
 * Saves at boot time configured settings for any netdevice.
 */
int __init netdev_boot_setup(char *str)
{
	int ints[5];
	struct ifmap map;

	str = get_options(str, ARRAY_SIZE(ints), ints);
	if (!str || !*str)
		return 0;

	/* Save settings */
	memset(&map, 0, sizeof(map));
	if (ints[0] > 0)
		map.irq = ints[1];
	if (ints[0] > 1)
		map.base_addr = ints[2];
	if (ints[0] > 2)
		map.mem_start = ints[3];
	if (ints[0] > 3)
		map.mem_end = ints[4];

	/* Add new entry to the list */
	return netdev_boot_setup_add(str, &map);
}

__setup("netdev=", netdev_boot_setup);

/*******************************************************************************

			    Device Interface Subroutines

*******************************************************************************/

/**
 *	__dev_get_by_name	- find a device by its name
 *	@name: name to find
 *
 *	Find an interface by name. Must be called under RTNL semaphore
 *	or @dev_base_lock. If the name is found a pointer to the device
 *	is returned. If the name is not found then %NULL is returned. The
 *	reference counters are not incremented so the caller must be
 *	careful with locks.
 */

struct net_device *__dev_get_by_name(const char *name)
{
	struct hlist_node *p;

	hlist_for_each(p, dev_name_hash(name)) {
		struct net_device *dev
			= hlist_entry(p, struct net_device, name_hlist);
		if (!strncmp(dev->name, name, IFNAMSIZ))
			return dev;
	}
	return NULL;
}

/**
 *	dev_get_by_name		- find a device by its name
 *	@name: name to find
 *
 *	Find an interface by name. This can be called from any
 *	context and does its own locking. The returned handle has
 *	the usage count incremented and the caller must use dev_put() to
 *	release it when it is no longer needed. %NULL is returned if no
 *	matching device is found.
 */

struct net_device *dev_get_by_name(const char *name)
{
	struct net_device *dev;

	read_lock(&dev_base_lock);
	dev = __dev_get_by_name(name);
	if (dev)
		dev_hold(dev);
	read_unlock(&dev_base_lock);
	return dev;
}

/**
 *	__dev_get_by_index - find a device by its ifindex
 *	@ifindex: index of device
 *
 *	Search for an interface by index. Returns %NULL if the device
 *	is not found or a pointer to the device. The device has not
 *	had its reference counter increased so the caller must be careful
 *	about locking. The caller must hold either the RTNL semaphore
 *	or @dev_base_lock.
 */

struct net_device *__dev_get_by_index(int ifindex)
{
	struct hlist_node *p;

	hlist_for_each(p, dev_index_hash(ifindex)) {
		struct net_device *dev
			= hlist_entry(p, struct net_device, index_hlist);
		if (dev->ifindex == ifindex)
			return dev;
	}
	return NULL;
}


/**
 *	dev_get_by_index - find a device by its ifindex
 *	@ifindex: index of device
 *
 *	Search for an interface by index. Returns NULL if the device
 *	is not found or a pointer to the device. The device returned has
 *	had a reference added and the pointer is safe until the user calls
 *	dev_put to indicate they have finished with it.
 */

struct net_device *dev_get_by_index(int ifindex)
{
	struct net_device *dev;

	read_lock(&dev_base_lock);
	dev = __dev_get_by_index(ifindex);
	if (dev)
		dev_hold(dev);
	read_unlock(&dev_base_lock);
	return dev;
}

/**
 *	dev_getbyhwaddr - find a device by its hardware address
 *	@type: media type of device
 *	@ha: hardware address
 *
 *	Search for an interface by MAC address. Returns NULL if the device
 *	is not found or a pointer to the device. The caller must hold the
 *	rtnl semaphore. The returned device has not had its ref count increased
 *	and the caller must therefore be careful about locking
 *
 *	BUGS:
 *	If the API was consistent this would be __dev_get_by_hwaddr
 */

struct net_device *dev_getbyhwaddr(unsigned short type, char *ha)
{
	struct net_device *dev;

	ASSERT_RTNL();

	for (dev = dev_base; dev; dev = dev->next)
		if (dev->type == type &&
		    !memcmp(dev->dev_addr, ha, dev->addr_len))
			break;
	return dev;
}

EXPORT_SYMBOL(dev_getbyhwaddr);

struct net_device *dev_getfirstbyhwtype(unsigned short type)
{
	struct net_device *dev;

	rtnl_lock();
	for (dev = dev_base; dev; dev = dev->next) {
		if (dev->type == type) {
			dev_hold(dev);
			break;
		}
	}
	rtnl_unlock();
	return dev;
}

EXPORT_SYMBOL(dev_getfirstbyhwtype);

/**
 *	dev_get_by_flags - find any device with given flags
 *	@if_flags: IFF_* values
 *	@mask: bitmask of bits in if_flags to check
 *
 *	Search for any interface with the given flags. Returns NULL if a device
 *	is not found or a pointer to the device. The device returned has 
 *	had a reference added and the pointer is safe until the user calls
 *	dev_put to indicate they have finished with it.
 */

struct net_device * dev_get_by_flags(unsigned short if_flags, unsigned short mask)
{
	struct net_device *dev;

	read_lock(&dev_base_lock);
	for (dev = dev_base; dev != NULL; dev = dev->next) {
		if (((dev->flags ^ if_flags) & mask) == 0) {
			dev_hold(dev);
			break;
		}
	}
	read_unlock(&dev_base_lock);
	return dev;
}

/**
 *	dev_valid_name - check if name is okay for network device
 *	@name: name string
 *
 *	Network device names need to be valid file names to
 *	to allow sysfs to work
 */
int dev_valid_name(const char *name)
{
	return !(*name == '\0' 
		 || !strcmp(name, ".")
		 || !strcmp(name, "..")
		 || strchr(name, '/'));
}

/**
 *	dev_alloc_name - allocate a name for a device
 *	@dev: device
 *	@name: name format string
 *
 *	Passed a format string - eg "lt%d" it will try and find a suitable
 *	id. Not efficient for many devices, not called a lot. The caller
 *	must hold the dev_base or rtnl lock while allocating the name and
 *	adding the device in order to avoid duplicates. Returns the number
 *	of the unit assigned or a negative errno code.
 */

int dev_alloc_name(struct net_device *dev, const char *name)
{
	int i = 0;
	char buf[IFNAMSIZ];
	const char *p;
	const int max_netdevices = 8*PAGE_SIZE;
	long *inuse;
	struct net_device *d;

	p = strnchr(name, IFNAMSIZ-1, '%');
	if (p) {
		/*
		 * Verify the string as this thing may have come from
		 * the user.  There must be either one "%d" and no other "%"
		 * characters.
		 */
		if (p[1] != 'd' || strchr(p + 2, '%'))
			return -EINVAL;

		/* Use one page as a bit array of possible slots */
		inuse = (long *) get_zeroed_page(GFP_ATOMIC);
		if (!inuse)
			return -ENOMEM;

		for (d = dev_base; d; d = d->next) {
			if (!sscanf(d->name, name, &i))
				continue;
			if (i < 0 || i >= max_netdevices)
				continue;

			/*  avoid cases where sscanf is not exact inverse of printf */
			snprintf(buf, sizeof(buf), name, i);
			if (!strncmp(buf, d->name, IFNAMSIZ))
				set_bit(i, inuse);
		}

		i = find_first_zero_bit(inuse, max_netdevices);
		free_page((unsigned long) inuse);
	}

	snprintf(buf, sizeof(buf), name, i);
	if (!__dev_get_by_name(buf)) {
		strlcpy(dev->name, buf, IFNAMSIZ);
		return i;
	}

	/* It is possible to run out of possible slots
	 * when the name is long and there isn't enough space left
	 * for the digits, or if all bits are used.
	 */
	return -ENFILE;
}


/**
 *	dev_change_name - change name of a device
 *	@dev: device
 *	@newname: name (or format string) must be at least IFNAMSIZ
 *
 *	Change name of a device, can pass format strings "eth%d".
 *	for wildcarding.
 */
int dev_change_name(struct net_device *dev, char *newname)
{
	int err = 0;

	ASSERT_RTNL();

	if (dev->flags & IFF_UP)
		return -EBUSY;

	if (!dev_valid_name(newname))
		return -EINVAL;

	if (strchr(newname, '%')) {
		err = dev_alloc_name(dev, newname);
		if (err < 0)
			return err;
		strcpy(newname, dev->name);
	}
	else if (__dev_get_by_name(newname))
		return -EEXIST;
	else
		strlcpy(dev->name, newname, IFNAMSIZ);

	err = class_device_rename(&dev->class_dev, dev->name);
	if (!err) {
		hlist_del(&dev->name_hlist);
		hlist_add_head(&dev->name_hlist, dev_name_hash(dev->name));
		notifier_call_chain(&netdev_chain, NETDEV_CHANGENAME, dev);
	}

	return err;
}

/**
 *	netdev_features_change - device changes fatures
 *	@dev: device to cause notification
 *
 *	Called to indicate a device has changed features.
 */
void netdev_features_change(struct net_device *dev)
{
	notifier_call_chain(&netdev_chain, NETDEV_FEAT_CHANGE, dev);
}
EXPORT_SYMBOL(netdev_features_change);

/**
 *	netdev_state_change - device changes state
 *	@dev: device to cause notification
 *
 *	Called to indicate a device has changed state. This function calls
 *	the notifier chains for netdev_chain and sends a NEWLINK message
 *	to the routing socket.
 */
void netdev_state_change(struct net_device *dev)
{
	if (dev->flags & IFF_UP) {
		notifier_call_chain(&netdev_chain, NETDEV_CHANGE, dev);
		rtmsg_ifinfo(RTM_NEWLINK, dev, 0);
	}
}

/**
 *	dev_load 	- load a network module
 *	@name: name of interface
 *
 *	If a network interface is not present and the process has suitable
 *	privileges this function loads the module. If module loading is not
 *	available in this kernel then it becomes a nop.
 */

void dev_load(const char *name)
{
	struct net_device *dev;  

	read_lock(&dev_base_lock);
	dev = __dev_get_by_name(name);
	read_unlock(&dev_base_lock);

	if (!dev && capable(CAP_SYS_MODULE))
		request_module("%s", name);
}

static int default_rebuild_header(struct sk_buff *skb)
{
	printk(KERN_DEBUG "%s: default_rebuild_header called -- BUG!\n",
	       skb->dev ? skb->dev->name : "NULL!!!");
	kfree_skb(skb);
	return 1;
}


/**
 *	dev_open	- prepare an interface for use.
 *	@dev:	device to open
 *
 *	Takes a device from down to up state. The device's private open
 *	function is invoked and then the multicast lists are loaded. Finally
 *	the device is moved into the up state and a %NETDEV_UP message is
 *	sent to the netdev notifier chain.
 *
 *	Calling this function on an active interface is a nop. On a failure
 *	a negative errno code is returned.
 */
int dev_open(struct net_device *dev)
{
	int ret = 0;

	/*
	 *	Is it already up?
	 */

	if (dev->flags & IFF_UP)
		return 0;

	/*
	 *	Is it even present?
	 */
	if (!netif_device_present(dev))
		return -ENODEV;

	/*
	 *	Call device private open method
	 */
	set_bit(__LINK_STATE_START, &dev->state);
	if (dev->open) {
		ret = dev->open(dev);
		if (ret)
			clear_bit(__LINK_STATE_START, &dev->state);
	}

 	/*
	 *	If it went open OK then:
	 */

	if (!ret) {
		/*
		 *	Set the flags.
		 */
		dev->flags |= IFF_UP;

		/*
		 *	Initialize multicasting status
		 */
		dev_mc_upload(dev);

		/*
		 *	Wakeup transmit queue engine
		 */
		dev_activate(dev);

		/*
		 *	... and announce new interface.
		 */
		notifier_call_chain(&netdev_chain, NETDEV_UP, dev);
	}
	return ret;
}

/**
 *	dev_close - shutdown an interface.
 *	@dev: device to shutdown
 *
 *	This function moves an active device into down state. A
 *	%NETDEV_GOING_DOWN is sent to the netdev notifier chain. The device
 *	is then deactivated and finally a %NETDEV_DOWN is sent to the notifier
 *	chain.
 */
int dev_close(struct net_device *dev)
{
	if (!(dev->flags & IFF_UP))
		return 0;

	/*
	 *	Tell people we are going down, so that they can
	 *	prepare to death, when device is still operating.
	 */
	notifier_call_chain(&netdev_chain, NETDEV_GOING_DOWN, dev);

	dev_deactivate(dev);

	clear_bit(__LINK_STATE_START, &dev->state);

	/* Synchronize to scheduled poll. We cannot touch poll list,
	 * it can be even on different cpu. So just clear netif_running(),
	 * and wait when poll really will happen. Actually, the best place
	 * for this is inside dev->stop() after device stopped its irq
	 * engine, but this requires more changes in devices. */

	smp_mb__after_clear_bit(); /* Commit netif_running(). */
	while (test_bit(__LINK_STATE_RX_SCHED, &dev->state)) {
		/* No hurry. */
		msleep(1);
	}

	/*
	 *	Call the device specific close. This cannot fail.
	 *	Only if device is UP
	 *
	 *	We allow it to be called even after a DETACH hot-plug
	 *	event.
	 */
	if (dev->stop)
		dev->stop(dev);

	/*
	 *	Device is now down.
	 */

	dev->flags &= ~IFF_UP;

	/*
	 * Tell people we are down
	 */
	notifier_call_chain(&netdev_chain, NETDEV_DOWN, dev);

	return 0;
}


/*
 *	Device change register/unregister. These are not inline or static
 *	as we export them to the world.
 */

/**
 *	register_netdevice_notifier - register a network notifier block
 *	@nb: notifier
 *
 *	Register a notifier to be called when network device events occur.
 *	The notifier passed is linked into the kernel structures and must
 *	not be reused until it has been unregistered. A negative errno code
 *	is returned on a failure.
 *
 * 	When registered all registration and up events are replayed
 *	to the new notifier to allow device to have a race free 
 *	view of the network device list.
 */

int register_netdevice_notifier(struct notifier_block *nb)
{
	struct net_device *dev;
	int err;

	rtnl_lock();
	err = notifier_chain_register(&netdev_chain, nb);
	if (!err) {
		for (dev = dev_base; dev; dev = dev->next) {
			nb->notifier_call(nb, NETDEV_REGISTER, dev);

			if (dev->flags & IFF_UP) 
				nb->notifier_call(nb, NETDEV_UP, dev);
		}
	}
	rtnl_unlock();
	return err;
}

/**
 *	unregister_netdevice_notifier - unregister a network notifier block
 *	@nb: notifier
 *
 *	Unregister a notifier previously registered by
 *	register_netdevice_notifier(). The notifier is unlinked into the
 *	kernel structures and may then be reused. A negative errno code
 *	is returned on a failure.
 */

int unregister_netdevice_notifier(struct notifier_block *nb)
{
	return notifier_chain_unregister(&netdev_chain, nb);
}

/**
 *	call_netdevice_notifiers - call all network notifier blocks
 *      @val: value passed unmodified to notifier function
 *      @v:   pointer passed unmodified to notifier function
 *
 *	Call all network notifier blocks.  Parameters and return value
 *	are as for notifier_call_chain().
 */

int call_netdevice_notifiers(unsigned long val, void *v)
{
	return notifier_call_chain(&netdev_chain, val, v);
}

/* When > 0 there are consumers of rx skb time stamps */
static atomic_t netstamp_needed = ATOMIC_INIT(0);