dev.c

int dev_set_allmulti(struct net_device *dev, int inc)
{
	unsigned short old_flags = dev->flags;

	ASSERT_RTNL();

	dev->flags |= IFF_ALLMULTI;
	dev->allmulti += inc;
	if (dev->allmulti == 0) {
		/*
		 * Avoid overflow.
		 * If inc causes overflow, untouch allmulti and return error.
		 */
		if (inc < 0)
			dev->flags &= ~IFF_ALLMULTI;
		else {
			dev->allmulti -= inc;
			printk(KERN_WARNING "%s: allmulti touches roof, "
				"set allmulti failed, allmulti feature of "
				"device might be broken.\n", dev->name);
			return -EOVERFLOW;
		}
	}
	if (dev->flags ^ old_flags) {
		if (dev->change_rx_flags)
			dev->change_rx_flags(dev, IFF_ALLMULTI);
		dev_set_rx_mode(dev);
	}
	return 0;
}

/*
 *	Upload unicast and multicast address lists to device and
 *	configure RX filtering. When the device doesn't support unicast
 *	filtering it is put in promiscuous mode while unicast addresses
 *	are present.
 */
void __dev_set_rx_mode(struct net_device *dev)
{
	/* dev_open will call this function so the list will stay sane. */
	if (!(dev->flags&IFF_UP))
		return;

	if (!netif_device_present(dev))
		return;

	if (dev->set_rx_mode)
		dev->set_rx_mode(dev);
	else {
		/* Unicast addresses changes may only happen under the rtnl,
		 * therefore calling __dev_set_promiscuity here is safe.
		 */
		if (dev->uc_count > 0 && !dev->uc_promisc) {
			__dev_set_promiscuity(dev, 1);
			dev->uc_promisc = 1;
		} else if (dev->uc_count == 0 && dev->uc_promisc) {
			__dev_set_promiscuity(dev, -1);
			dev->uc_promisc = 0;
		}

		if (dev->set_multicast_list)
			dev->set_multicast_list(dev);
	}
}

void dev_set_rx_mode(struct net_device *dev)
{
	netif_addr_lock_bh(dev);
	__dev_set_rx_mode(dev);
	netif_addr_unlock_bh(dev);
}

int __dev_addr_delete(struct dev_addr_list **list, int *count,
		      void *addr, int alen, int glbl)
{
	struct dev_addr_list *da;

	for (; (da = *list) != NULL; list = &da->next) {
		if (memcmp(da->da_addr, addr, da->da_addrlen) == 0 &&
		    alen == da->da_addrlen) {
			if (glbl) {
				int old_glbl = da->da_gusers;
				da->da_gusers = 0;
				if (old_glbl == 0)
					break;
			}
			if (--da->da_users)
				return 0;

			*list = da->next;
			kfree(da);
			(*count)--;
			return 0;
		}
	}
	return -ENOENT;
}

int __dev_addr_add(struct dev_addr_list **list, int *count,
		   void *addr, int alen, int glbl)
{
	struct dev_addr_list *da;

	for (da = *list; da != NULL; da = da->next) {
		if (memcmp(da->da_addr, addr, da->da_addrlen) == 0 &&
		    da->da_addrlen == alen) {
			if (glbl) {
				int old_glbl = da->da_gusers;
				da->da_gusers = 1;
				if (old_glbl)
					return 0;
			}
			da->da_users++;
			return 0;
		}
	}

	da = kzalloc(sizeof(*da), GFP_ATOMIC);
	if (da == NULL)
		return -ENOMEM;
	memcpy(da->da_addr, addr, alen);
	da->da_addrlen = alen;
	da->da_users = 1;
	da->da_gusers = glbl ? 1 : 0;
	da->next = *list;
	*list = da;
	(*count)++;
	return 0;
}

/**
 *	dev_unicast_delete	- Release secondary unicast address.
 *	@dev: device
 *	@addr: address to delete
 *	@alen: length of @addr
 *
 *	Release reference to a secondary unicast address and remove it
 *	from the device if the reference count drops to zero.
 *
 * 	The caller must hold the rtnl_mutex.
 */
int dev_unicast_delete(struct net_device *dev, void *addr, int alen)
{
	int err;

	ASSERT_RTNL();

	netif_addr_lock_bh(dev);
	err = __dev_addr_delete(&dev->uc_list, &dev->uc_count, addr, alen, 0);
	if (!err)
		__dev_set_rx_mode(dev);
	netif_addr_unlock_bh(dev);
	return err;
}
EXPORT_SYMBOL(dev_unicast_delete);

/**
 *	dev_unicast_add		- add a secondary unicast address
 *	@dev: device
 *	@addr: address to add
 *	@alen: length of @addr
 *
 *	Add a secondary unicast address to the device or increase
 *	the reference count if it already exists.
 *
 *	The caller must hold the rtnl_mutex.
 */
int dev_unicast_add(struct net_device *dev, void *addr, int alen)
{
	int err;

	ASSERT_RTNL();

	netif_addr_lock_bh(dev);
	err = __dev_addr_add(&dev->uc_list, &dev->uc_count, addr, alen, 0);
	if (!err)
		__dev_set_rx_mode(dev);
	netif_addr_unlock_bh(dev);
	return err;
}
EXPORT_SYMBOL(dev_unicast_add);

int __dev_addr_sync(struct dev_addr_list **to, int *to_count,
		    struct dev_addr_list **from, int *from_count)
{
	struct dev_addr_list *da, *next;
	int err = 0;

	da = *from;
	while (da != NULL) {
		next = da->next;
		if (!da->da_synced) {
			err = __dev_addr_add(to, to_count,
					     da->da_addr, da->da_addrlen, 0);
			if (err < 0)
				break;
			da->da_synced = 1;
			da->da_users++;
		} else if (da->da_users == 1) {
			__dev_addr_delete(to, to_count,
					  da->da_addr, da->da_addrlen, 0);
			__dev_addr_delete(from, from_count,
					  da->da_addr, da->da_addrlen, 0);
		}
		da = next;
	}
	return err;
}

void __dev_addr_unsync(struct dev_addr_list **to, int *to_count,
		       struct dev_addr_list **from, int *from_count)
{
	struct dev_addr_list *da, *next;

	da = *from;
	while (da != NULL) {
		next = da->next;
		if (da->da_synced) {
			__dev_addr_delete(to, to_count,
					  da->da_addr, da->da_addrlen, 0);
			da->da_synced = 0;
			__dev_addr_delete(from, from_count,
					  da->da_addr, da->da_addrlen, 0);
		}
		da = next;
	}
}

/**
 *	dev_unicast_sync - Synchronize device's unicast list to another device
 *	@to: destination device
 *	@from: source device
 *
 *	Add newly added addresses to the destination device and release
 *	addresses that have no users left. The source device must be
 *	locked by netif_tx_lock_bh.
 *
 *	This function is intended to be called from the dev->set_rx_mode
 *	function of layered software devices.
 */
int dev_unicast_sync(struct net_device *to, struct net_device *from)
{
	int err = 0;

	netif_addr_lock_bh(to);
	err = __dev_addr_sync(&to->uc_list, &to->uc_count,
			      &from->uc_list, &from->uc_count);
	if (!err)
		__dev_set_rx_mode(to);
	netif_addr_unlock_bh(to);
	return err;
}
EXPORT_SYMBOL(dev_unicast_sync);

/**
 *	dev_unicast_unsync - Remove synchronized addresses from the destination device
 *	@to: destination device
 *	@from: source device
 *
 *	Remove all addresses that were added to the destination device by
 *	dev_unicast_sync(). This function is intended to be called from the
 *	dev->stop function of layered software devices.
 */
void dev_unicast_unsync(struct net_device *to, struct net_device *from)
{
	netif_addr_lock_bh(from);
	netif_addr_lock(to);

	__dev_addr_unsync(&to->uc_list, &to->uc_count,
			  &from->uc_list, &from->uc_count);
	__dev_set_rx_mode(to);

	netif_addr_unlock(to);
	netif_addr_unlock_bh(from);
}
EXPORT_SYMBOL(dev_unicast_unsync);

static void __dev_addr_discard(struct dev_addr_list **list)
{
	struct dev_addr_list *tmp;

	while (*list != NULL) {
		tmp = *list;
		*list = tmp->next;
		if (tmp->da_users > tmp->da_gusers)
			printk("__dev_addr_discard: address leakage! "
			       "da_users=%d\n", tmp->da_users);
		kfree(tmp);
	}
}

static void dev_addr_discard(struct net_device *dev)
{
	netif_addr_lock_bh(dev);

	__dev_addr_discard(&dev->uc_list);
	dev->uc_count = 0;

	__dev_addr_discard(&dev->mc_list);
	dev->mc_count = 0;

	netif_addr_unlock_bh(dev);
}

unsigned dev_get_flags(const struct net_device *dev)
{
	unsigned flags;

	flags = (dev->flags & ~(IFF_PROMISC |
				IFF_ALLMULTI |
				IFF_RUNNING |
				IFF_LOWER_UP |
				IFF_DORMANT)) |
		(dev->gflags & (IFF_PROMISC |
				IFF_ALLMULTI));

	if (netif_running(dev)) {
		if (netif_oper_up(dev))
			flags |= IFF_RUNNING;
		if (netif_carrier_ok(dev))
			flags |= IFF_LOWER_UP;
		if (netif_dormant(dev))
			flags |= IFF_DORMANT;
	}

	return flags;
}

int dev_change_flags(struct net_device *dev, unsigned flags)
{
	int ret, changes;
	int old_flags = dev->flags;

	ASSERT_RTNL();

	/*
	 *	Set the flags on our device.
	 */

	dev->flags = (flags & (IFF_DEBUG | IFF_NOTRAILERS | IFF_NOARP |
			       IFF_DYNAMIC | IFF_MULTICAST | IFF_PORTSEL |
			       IFF_AUTOMEDIA)) |
		     (dev->flags & (IFF_UP | IFF_VOLATILE | IFF_PROMISC |
				    IFF_ALLMULTI));

	/*
	 *	Load in the correct multicast list now the flags have changed.
	 */

	if (dev->change_rx_flags && (old_flags ^ flags) & IFF_MULTICAST)
		dev->change_rx_flags(dev, IFF_MULTICAST);

	dev_set_rx_mode(dev);

	/*
	 *	Have we downed the interface. We handle IFF_UP ourselves
	 *	according to user attempts to set it, rather than blindly
	 *	setting it.
	 */

	ret = 0;
	if ((old_flags ^ flags) & IFF_UP) {	/* Bit is different  ? */
		ret = ((old_flags & IFF_UP) ? dev_close : dev_open)(dev);

		if (!ret)
			dev_set_rx_mode(dev);
	}

	if (dev->flags & IFF_UP &&
	    ((old_flags ^ dev->flags) &~ (IFF_UP | IFF_PROMISC | IFF_ALLMULTI |
					  IFF_VOLATILE)))
		call_netdevice_notifiers(NETDEV_CHANGE, dev);

	if ((flags ^ dev->gflags) & IFF_PROMISC) {
		int inc = (flags & IFF_PROMISC) ? +1 : -1;
		dev->gflags ^= IFF_PROMISC;
		dev_set_promiscuity(dev, inc);
	}

	/* NOTE: order of synchronization of IFF_PROMISC and IFF_ALLMULTI
	   is important. Some (broken) drivers set IFF_PROMISC, when
	   IFF_ALLMULTI is requested not asking us and not reporting.
	 */
	if ((flags ^ dev->gflags) & IFF_ALLMULTI) {
		int inc = (flags & IFF_ALLMULTI) ? +1 : -1;
		dev->gflags ^= IFF_ALLMULTI;
		dev_set_allmulti(dev, inc);
	}

	/* Exclude state transition flags, already notified */
	changes = (old_flags ^ dev->flags) & ~(IFF_UP | IFF_RUNNING);
	if (changes)
		rtmsg_ifinfo(RTM_NEWLINK, dev, changes);

	return ret;
}

int dev_set_mtu(struct net_device *dev, int new_mtu)
{
	int err;

	if (new_mtu == dev->mtu)
		return 0;

	/*	MTU must be positive.	 */
	if (new_mtu < 0)
		return -EINVAL;

	if (!netif_device_present(dev))
		return -ENODEV;

	err = 0;
	if (dev->change_mtu)
		err = dev->change_mtu(dev, new_mtu);
	else
		dev->mtu = new_mtu;
	if (!err && dev->flags & IFF_UP)
		call_netdevice_notifiers(NETDEV_CHANGEMTU, dev);
	return err;
}

int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa)
{
	int err;

	if (!dev->set_mac_address)
		return -EOPNOTSUPP;
	if (sa->sa_family != dev->type)
		return -EINVAL;
	if (!netif_device_present(dev))
		return -ENODEV;
	err = dev->set_mac_address(dev, sa);
	if (!err)
		call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
	return err;
}

/*
 *	Perform the SIOCxIFxxx calls, inside read_lock(dev_base_lock)
 */
static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cmd)
{
	int err;
	struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name);

	if (!dev)
		return -ENODEV;

	switch (cmd) {
		case SIOCGIFFLAGS:	/* Get interface flags */
			ifr->ifr_flags = dev_get_flags(dev);
			return 0;

		case SIOCGIFMETRIC:	/* Get the metric on the interface
					   (currently unused) */
			ifr->ifr_metric = 0;
			return 0;

		case SIOCGIFMTU:	/* Get the MTU of a device */
			ifr->ifr_mtu = dev->mtu;
			return 0;

		case SIOCGIFHWADDR:
			if (!dev->addr_len)
				memset(ifr->ifr_hwaddr.sa_data, 0, sizeof ifr->ifr_hwaddr.sa_data);
			else
				memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr,
				       min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len));
			ifr->ifr_hwaddr.sa_family = dev->type;
			return 0;

		case SIOCGIFSLAVE:
			err = -EINVAL;
			break;

		case SIOCGIFMAP:
			ifr->ifr_map.mem_start = dev->mem_start;
			ifr->ifr_map.mem_end   = dev->mem_end;
			ifr->ifr_map.base_addr = dev->base_addr;
			ifr->ifr_map.irq       = dev->irq;
			ifr->ifr_map.dma       = dev->dma;
			ifr->ifr_map.port      = dev->if_port;
			return 0;

		case SIOCGIFINDEX:
			ifr->ifr_ifindex = dev->ifindex;
			return 0;

		case SIOCGIFTXQLEN:
			ifr->ifr_qlen = dev->tx_queue_len;
			return 0;

		default:
			/* dev_ioctl() should ensure this case
			 * is never reached
			 */
			WARN_ON(1);
			err = -EINVAL;
			break;

	}
	return err;
}

/*
 *	Perform the SIOCxIFxxx calls, inside rtnl_lock()
 */
static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
{
	int err;
	struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name);

	if (!dev)
		return -ENODEV;

	switch (cmd) {
		case SIOCSIFFLAGS:	/* Set interface flags */
			return dev_change_flags(dev, ifr->ifr_flags);

		case SIOCSIFMETRIC:	/* Set the metric on the interface
					   (currently unused) */
			return -EOPNOTSUPP;

		case SIOCSIFMTU:	/* Set the MTU of a device */
			return dev_set_mtu(dev, ifr->ifr_mtu);

		case SIOCSIFHWADDR:
			return dev_set_mac_address(dev, &ifr->ifr_hwaddr);

		case SIOCSIFHWBROADCAST:
			if (ifr->ifr_hwaddr.sa_family != dev->type)
				return -EINVAL;
			memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data,
			       min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len));
			call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
			return 0;

		case SIOCSIFMAP:
			if (dev->set_config) {
				if (!netif_device_present(dev))
					return -ENODEV;
				return dev->set_config(dev, &ifr->ifr_map);
			}
			return -EOPNOTSUPP;

		case SIOCADDMULTI:
			if ((!dev->set_multicast_list && !dev->set_rx_mode) ||
			    ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
				return -EINVAL;
			if (!netif_device_present(dev))
				return -ENODEV;
			return dev_mc_add(dev, ifr->ifr_hwaddr.sa_data,
					  dev->addr_len, 1);

		case SIOCDELMULTI:
			if ((!dev->set_multicast_list && !dev->set_rx_mode) ||
			    ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
				return -EINVAL;
			if (!netif_device_present(dev))
				return -ENODEV;
			return dev_mc_delete(dev, ifr->ifr_hwaddr.sa_data,
					     dev->addr_len, 1);

		case SIOCSIFTXQLEN:
			if (ifr->ifr_qlen < 0)
				return -EINVAL;
			dev->tx_queue_len = ifr->ifr_qlen;
			return 0;

		case SIOCSIFNAME:
			ifr->ifr_newname[IFNAMSIZ-1] = '\0';
			return dev_change_name(dev, ifr->ifr_newname);

		/*
		 *	Unknown or private ioctl
		 */

		default:
			if ((cmd >= SIOCDEVPRIVATE &&
			    cmd <= SIOCDEVPRIVATE + 15) ||
			    cmd == SIOCBONDENSLAVE ||
			    cmd == SIOCBONDRELEASE ||
			    cmd == SIOCBONDSETHWADDR ||
			    cmd == SIOCBONDSLAVEINFOQUERY ||
			    cmd == SIOCBONDINFOQUERY ||
			    cmd == SIOCBONDCHANGEACTIVE ||
			    cmd == SIOCGMIIPHY ||
			    cmd == SIOCGMIIREG ||
			    cmd == SIOCSMIIREG ||
			    cmd == SIOCBRADDIF ||
			    cmd == SIOCBRDELIF ||
			    cmd == SIOCWANDEV) {
				err = -EOPNOTSUPP;
				if (dev->do_ioctl) {
					if (netif_device_present(dev))
						err = dev->do_ioctl(dev, ifr,
								    cmd);
					else
						err = -ENODEV;
				}
			} else
				err = -EINVAL;

	}
	return err;
}

/*
 *	This function handles all "interface"-type I/O control requests. The actual
 *	'doing' part of this is dev_ifsioc above.
 */

/**
 *	dev_ioctl	-	network device ioctl
 *	@net: the applicable net namespace
 *	@cmd: command to issue
 *	@arg: pointer to a struct ifreq in user space
 *
 *	Issue ioctl functions to devices. This is normally called by the
 *	user space syscall interfaces but can sometimes be useful for
 *	other purposes. The return value is the return from the syscall if
 *	positive or a negative errno code on error.
 */

int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg)
{
	struct ifreq ifr;
	int ret;
	char *colon;

	/* One special case: SIOCGIFCONF takes ifconf argument
	   and requires shared lock, because it sleeps writing
	   to user space.
	 */

	if (cmd == SIOCGIFCONF) {
		rtnl_lock();
		ret = dev_ifconf(net, (char __user *) arg);
		rtnl_unlock();
		return ret;
	}
	if (cmd == SIOCGIFNAME)
		return dev_ifname(net, (struct ifreq __user *)arg);

	if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
		return -EFAULT;

	ifr.ifr_name[IFNAMSIZ-1] = 0;

	colon = strchr(ifr.ifr_name, ':');
	if (colon)
		*colon = 0;

	/*
	 *	See which interface the caller is talking about.
	 */

	switch (cmd) {
		/*
		 *	These ioctl calls:
		 *	- can be done by all.
		 *	- atomic and do not require locking.
		 *	- return a value
		 */
		case SIOCGIFFLAGS:
		case SIOCGIFMETRIC:
		case SIOCGIFMTU:
		case SIOCGIFHWADDR:
		case SIOCGIFSLAVE:
		case SIOCGIFMAP:
		case SIOCGIFINDEX:
		case SIOCGIFTXQLEN:
			dev_load(net, ifr.ifr_name);
			read_lock(&dev_base_lock);
			ret = dev_ifsioc_locked(net, &ifr, cmd);
			read_unlock(&dev_base_lock);
			if (!ret) {
				if (colon)
					*colon = ':';
				if (copy_to_user(arg, &ifr,
						 sizeof(struct ifreq)))
					ret = -EFAULT;
			}
			return ret;

		case SIOCETHTOOL:
			dev_load(net, ifr.ifr_name);
			rtnl_lock();
			ret = dev_ethtool(net, &ifr);
			rtnl_unlock();
			if (!ret) {
				if (colon)
					*colon = ':';
				if (copy_to_user(arg, &ifr,
						 sizeof(struct ifreq)))
					ret = -EFAULT;
			}
			return ret;

		/*
		 *	These ioctl calls:
		 *	- require superuser power.
		 *	- require strict serialization.
		 *	- return a value
		 */
		case SIOCGMIIPHY:
		case SIOCGMIIREG:
		case SIOCSIFNAME:
			if (!capable(CAP_NET_ADMIN))
				return -EPERM;
			dev_load(net, ifr.ifr_name);
			rtnl_lock();
			ret = dev_ifsioc(net, &ifr, cmd);
			rtnl_unlock();
			if (!ret) {
				if (colon)
					*colon = ':';
				if (copy_to_user(arg, &ifr,
						 sizeof(struct ifreq)))
					ret = -EFAULT;
			}
			return ret;

		/*
		 *	These ioctl calls:
		 *	- require superuser power.
		 *	- require strict serialization.
		 *	- do not return a value
		 */
		case SIOCSIFFLAGS:
		case SIOCSIFMETRIC:
		case SIOCSIFMTU:
		case SIOCSIFMAP:
		case SIOCSIFHWADDR:
		case SIOCSIFSLAVE:
		case SIOCADDMULTI:
		case SIOCDELMULTI:
		case SIOCSIFHWBROADCAST:
		case SIOCSIFTXQLEN:
		case SIOCSMIIREG:
		case SIOCBONDENSLAVE:
		case SIOCBONDRELEASE:
		case SIOCBONDSETHWADDR:
		case SIOCBONDCHANGEACTIVE:
		case SIOCBRADDIF:
		case SIOCBRDELIF:
			if (!capable(CAP_NET_ADMIN))
				return -EPERM;
			/* fall through */
		case SIOCBONDSLAVEINFOQUERY:
		case SIOCBONDINFOQUERY:
			dev_load(net, ifr.ifr_name);
			rtnl_lock();
			ret = dev_ifsioc(net, &ifr, cmd);
			rtnl_unlock();
			return ret;

		case SIOCGIFMEM:
			/* Get the per device memory space. We can add this but
			 * currently do not support it */
		case SIOCSIFMEM:
			/* Set the per device memory buffer space.
			 * Not applicable in our case */
		case SIOCSIFLINK:
			return -EINVAL;

		/*
		 *	Unknown or private ioctl.
		 */
		default:
			if (cmd == SIOCWANDEV ||
			    (cmd >= SIOCDEVPRIVATE &&
			     cmd <= SIOCDEVPRIVATE + 15)) {
				dev_load(net, ifr.ifr_name);
				rtnl_lock();
				ret = dev_ifsioc(net, &ifr, cmd);
				rtnl_unlock();
				if (!ret && copy_to_user(arg, &ifr,
							 sizeof(struct ifreq)))
					ret = -EFAULT;
				return ret;
			}
			/* Take care of Wireless Extensions */
			if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST)
				return wext_handle_ioctl(net, &ifr, cmd, arg);
			return -EINVAL;
	}
}


/**
 *	dev_new_index	-	allocate an ifindex
 *	@net: the applicable net namespace
 *
 *	Returns a suitable unique value for a new device interface
 *	number.  The caller must hold the rtnl semaphore or the
 *	dev_base_lock to be sure it remains unique.
 */
static int dev_new_index(struct net *net)
{
	static int ifindex;
	for (;;) {
		if (++ifindex <= 0)
			ifindex = 1;
		if (!__dev_get_by_index(net, ifindex))
			return ifindex;
	}
}

/* Delayed registration/unregisteration */
static DEFINE_SPINLOCK(net_todo_list_lock);
static LIST_HEAD(net_todo_list);

static void net_set_todo(struct net_device *dev)
{
	spin_lock(&net_todo_list_lock);
	list_add_tail(&dev->todo_list, &net_todo_list);
	spin_unlock(&net_todo_list_lock);
}

static void rollback_registered(struct net_device *dev)
{
	BUG_ON(dev_boot_phase);
	ASSERT_RTNL();

	/* Some devices call without registering for initialization unwind. */
	if (dev->reg_state == NETREG_UNINITIALIZED) {
		printk(KERN_DEBUG "unregister_netdevice: device %s/%p never "
				  "was registered\n", dev->name, dev);

		WARN_ON(1);
		return;
	}

	BUG_ON(dev->reg_state != NETREG_REGISTERED);

	/* If device is running, close it first. */
	dev_close(dev);

	/* And unlink it from device chain. */
	unlist_netdevice(dev);

	dev->reg_state = NETREG_UNREGISTERING;

	synchronize_net();

	/* Shutdown queueing discipline. */
	dev_shutdown(dev);


	/* Notify protocols, that we are about to destroy
	   this device. They should clean all the things.
	*/
	call_netdevice_notifiers(NETDEV_UNREGISTER, dev);

	/*
	 *	Flush the unicast and multicast chains
	 */
	dev_addr_discard(dev);

	if (dev->uninit)
		dev->uninit(dev);

	/* Notifier chain MUST detach us from master device. */
	WARN_ON(dev->master);

	/* Remove entries from kobject tree */
	netdev_unregister_kobject(dev);

	synchronize_net();

	dev_put(dev);
}

static void __netdev_init_queue_locks_one(struct net_device *dev,
					  struct netdev_queue *dev_queue,
					  void *_unused)
{
	spin_lock_init(&dev_queue->_xmit_lock);
	netdev_set_xmit_lockdep_class(&dev_queue->_xmit_lock, dev->type);
	dev_queue->xmit_lock_owner = -1;
}

static void netdev_init_queue_locks(struct net_device *dev)
{
	netdev_for_each_tx_queue(dev, __netdev_init_queue_locks_one, NULL);
	__netdev_init_queue_locks_one(dev, &dev->rx_queue, NULL);
}

/**
 *	register_netdevice	- register a network device
 *	@dev: device to register
 *
 *	Take a completed network device structure and add it to the kernel
 *	interfaces. A %NETDEV_REGISTER message is sent to the netdev notifier
 *	chain. 0 is returned on success. A negative errno code is returned
 *	on a failure to set up the device, or if the name is a duplicate.
 *
 *	Callers must hold the rtnl semaphore. You may want
 *	register_netdev() instead of this.
 *
 *	BUGS:
 *	The locking appears insufficient to guarantee two parallel registers
 *	will not get the same name.
 */

int register_netdevice(struct net_device *dev)
{
	struct hlist_head *head;
	struct hlist_node *p;
	int ret;
	struct net *net;

	BUG_ON(dev_boot_phase);
	ASSERT_RTNL();

	might_sleep();

	/* When net_device's are persistent, this will be fatal. */
	BUG_ON(dev->reg_state != NETREG_UNINITIALIZED);
	BUG_ON(!dev_net(dev));
	net = dev_net(dev);

	spin_lock_init(&dev->addr_list_lock);
	netdev_set_addr_lockdep_class(dev);
	netdev_init_queue_locks(dev);

	dev->iflink = -1;

	/* Init, if this function is available */
	if (dev->init) {
		ret = dev->init(dev);
		if (ret) {
			if (ret > 0)
				ret = -EIO;
			goto out;
		}
	}

	if (!dev_valid_name(dev->name)) {
		ret = -EINVAL;
		goto err_uninit;
	}

	dev->ifindex = dev_new_index(net);
	if (dev->iflink == -1)
		dev->iflink = dev->ifindex;

	/* Check for existence of name */
	head = dev_name_hash(net, dev->name);
	hlist_for_each(p, head) {
		struct net_device *d
			= hlist_entry(p, struct net_device, name_hlist);
		if (!strncmp(d->name, dev->name, IFNAMSIZ)) {
			ret = -EEXIST;
			goto err_uninit;
		}
	}

	/* Fix illegal checksum combinations */
	if ((dev->features & NETIF_F_HW_CSUM) &&
	    (dev->features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) {
		printk(KERN_NOTICE "%s: mixed HW and IP checksum settings.\n",
		       dev->name);
		dev->features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM);
	}

	if ((dev->features & NETIF_F_NO_CSUM) &&
	    (dev->features & (NETIF_F_HW_CSUM|NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) {
		printk(KERN_NOTICE "%s: mixed no checksumming and other settings.\n",
		       dev->name);
		dev->features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM|NETIF_F_HW_CSUM);
	}


	/* Fix illegal SG+CSUM combinations. */
	if ((dev->features & NETIF_F_SG) &&
	    !(dev->features & NETIF_F_ALL_CSUM)) {
		printk(KERN_NOTICE "%s: Dropping NETIF_F_SG since no checksum feature.\n",
		       dev->name);
		dev->features &= ~NETIF_F_SG;
	}

	/* TSO requires that SG is present as well. */
	if ((dev->features & NETIF_F_TSO) &&
	    !(dev->features & NETIF_F_SG)) {
		printk(KERN_NOTICE "%s: Dropping NETIF_F_TSO since no SG feature.\n",
		       dev->name);
		dev->features &= ~NETIF_F_TSO;
	}
	if (dev->features & NETIF_F_UFO) {
		if (!(dev->features & NETIF_F_HW_CSUM)) {
			printk(KERN_ERR "%s: Dropping NETIF_F_UFO since no "
					"NETIF_F_HW_CSUM feature.\n",
							dev->name);
			dev->features &= ~NETIF_F_UFO;
		}
		if (!(dev->features & NETIF_F_SG)) {
			printk(KERN_ERR "%s: Dropping NETIF_F_UFO since no "
					"NETIF_F_SG feature.\n",