dev.c

	/* rtnl_mutex must be held here */

	__hw_addr_flush(&dev->uc_list);
	dev->uc_count = 0;
}

static void dev_unicast_init(struct net_device *dev)
{
	/* rtnl_mutex must be held here */

	INIT_LIST_HEAD(&dev->uc_list);
}


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->mc_list);
	dev->mc_count = 0;

	netif_addr_unlock_bh(dev);
}

/**
 *	dev_get_flags - get flags reported to userspace
 *	@dev: device
 *
 *	Get the combination of flag bits exported through APIs to userspace.
 */
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;
}

/**
 *	dev_change_flags - change device settings
 *	@dev: device
 *	@flags: device state flags
 *
 *	Change settings on device based state flags. The flags are
 *	in the userspace exported format.
 */
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 ((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;
}

/**
 *	dev_set_mtu - Change maximum transfer unit
 *	@dev: device
 *	@new_mtu: new transfer unit
 *
 *	Change the maximum transfer size of the network device.
 */
int dev_set_mtu(struct net_device *dev, int new_mtu)
{
	const struct net_device_ops *ops = dev->netdev_ops;
	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 (ops->ndo_change_mtu)
		err = ops->ndo_change_mtu(dev, new_mtu);
	else
		dev->mtu = new_mtu;

	if (!err && dev->flags & IFF_UP)
		call_netdevice_notifiers(NETDEV_CHANGEMTU, dev);
	return err;
}

/**
 *	dev_set_mac_address - Change Media Access Control Address
 *	@dev: device
 *	@sa: new address
 *
 *	Change the hardware (MAC) address of the device
 */
int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa)
{
	const struct net_device_ops *ops = dev->netdev_ops;
	int err;

	if (!ops->ndo_set_mac_address)
		return -EOPNOTSUPP;
	if (sa->sa_family != dev->type)
		return -EINVAL;
	if (!netif_device_present(dev))
		return -ENODEV;
	err = ops->ndo_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 = (short) 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);
	const struct net_device_ops *ops;

	if (!dev)
		return -ENODEV;

	ops = dev->netdev_ops;

	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 (ops->ndo_set_config) {
				if (!netif_device_present(dev))
					return -ENODEV;
				return ops->ndo_set_config(dev, &ifr->ifr_map);
			}
			return -EOPNOTSUPP;

		case SIOCADDMULTI:
			if ((!ops->ndo_set_multicast_list && !ops->ndo_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 ((!ops->ndo_set_multicast_list && !ops->ndo_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 == SIOCSHWTSTAMP ||
			    cmd == SIOCWANDEV) {
				err = -EOPNOTSUPP;
				if (ops->ndo_do_ioctl) {
					if (netif_device_present(dev))
						err = ops->ndo_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:
		case SIOCSHWTSTAMP:
			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 LIST_HEAD(net_todo_list);

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

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_unicast_flush(dev);
	dev_addr_discard(dev);

	if (dev->netdev_ops->ndo_uninit)
		dev->netdev_ops->ndo_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);
}

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

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

	if (features & NETIF_F_UFO) {
		if (!(features & NETIF_F_GEN_CSUM)) {
			if (name)
				printk(KERN_ERR "%s: Dropping NETIF_F_UFO "
				       "since no NETIF_F_HW_CSUM feature.\n",
				       name);
			features &= ~NETIF_F_UFO;
		}

		if (!(features & NETIF_F_SG)) {
			if (name)
				printk(KERN_ERR "%s: Dropping NETIF_F_UFO "
				       "since no NETIF_F_SG feature.\n", name);
			features &= ~NETIF_F_UFO;
		}
	}

	return features;
}
EXPORT_SYMBOL(netdev_fix_features);

/**
 *	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 = dev_net(dev);

	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(!net);

	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->netdev_ops->ndo_init) {
		ret = dev->netdev_ops->ndo_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);
	}

	dev->features = netdev_fix_features(dev->features, dev->name);

	/* Enable software GSO if SG is supported. */
	if (dev->features & NETIF_F_SG)
		dev->features |= NETIF_F_GSO;

	netdev_initialize_kobject(dev);
	ret = netdev_register_kobject(dev);
	if (ret)
		goto err_uninit;
	dev->reg_state = NETREG_REGISTERED;

	/*
	 *	Default initial state at registry is that the
	 *	device is present.
	 */

	set_bit(__LINK_STATE_PRESENT, &dev->state);

	dev_init_scheduler(dev);
	dev_hold(dev);
	list_netdevice(dev);

	/* Notify protocols, that a new device appeared. */
	ret = call_netdevice_notifiers(NETDEV_REGISTER, dev);
	ret = notifier_to_errno(ret);
	if (ret) {
		rollback_registered(dev);
		dev->reg_state = NETREG_UNREGISTERED;
	}

out:
	return ret;

err_uninit:
	if (dev->netdev_ops->ndo_uninit)
		dev->netdev_ops->ndo_uninit(dev);
	goto out;
}

/**
 *	init_dummy_netdev	- init a dummy network device for NAPI
 *	@dev: device to init
 *
 *	This takes a network device structure and initialize the minimum
 *	amount of fields so it can be used to schedule NAPI polls without
 *	registering a full blown interface. This is to be used by drivers
 *	that need to tie several hardware interfaces to a single NAPI
 *	poll scheduler due to HW limitations.
 */
int init_dummy_netdev(struct net_device *dev)
{
	/* Clear everything. Note we don't initialize spinlocks
	 * are they aren't supposed to be taken by any of the
	 * NAPI code and this dummy netdev is supposed to be
	 * only ever used for NAPI polls
	 */
	memset(dev, 0, sizeof(struct net_device));

	/* make sure we BUG if trying to hit standard
	 * register/unregister code path
	 */
	dev->reg_state = NETREG_DUMMY;

	/* initialize the ref count */
	atomic_set(&dev->refcnt, 1);

	/* NAPI wants this */
	INIT_LIST_HEAD(&dev->napi_list);

	/* a dummy interface is started by default */
	set_bit(__LINK_STATE_PRESENT, &dev->state);
	set_bit(__LINK_STATE_START, &dev->state);

	return 0;
}
EXPORT_SYMBOL_GPL(init_dummy_netdev);


/**
 *	register_netdev	- 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.
 *
 *	This is a wrapper around register_netdevice that takes the rtnl semaphore
 *	and expands the device name if you passed a format string to
 *	alloc_netdev.
 */
int register_netdev(struct net_device *dev)
{
	int err;

	rtnl_lock();

	/*
	 * If the name is a format string the caller wants us to do a
	 * name allocation.
	 */
	if (strchr(dev->name, '%')) {
		err = dev_alloc_name(dev, dev->name);
		if (err < 0)
			goto out;
	}

	err = register_netdevice(dev);
out:
	rtnl_unlock();
	return err;
}
EXPORT_SYMBOL(register_netdev);

/*
 * netdev_wait_allrefs - wait until all references are gone.
 *
 * This is called when unregistering network devices.
 *
 * Any protocol or device that holds a reference should register
 * for netdevice notification, and cleanup and put back the
 * reference if they receive an UNREGISTER event.
 * We can get stuck here if buggy protocols don't correctly
 * call dev_put.
 */
static void netdev_wait_allrefs(struct net_device *dev)
{
	unsigned long rebroadcast_time, warning_time;

	rebroadcast_time = warning_time = jiffies;
	while (atomic_read(&dev->refcnt) != 0) {
		if (time_after(jiffies, rebroadcast_time + 1 * HZ)) {
			rtnl_lock();

			/* Rebroadcast unregister notification */
			call_netdevice_notifiers(NETDEV_UNREGISTER, dev);

			if (test_bit(__LINK_STATE_LINKWATCH_PENDING,
				     &dev->state)) {
				/* We must not have linkwatch events
				 * pending on unregister. If this
				 * happens, we simply run the queue
				 * unscheduled, resulting in a noop
				 * for this device.
				 */
				linkwatch_run_queue();
			}

			__rtnl_unlock();

			rebroadcast_time = jiffies;
		}

		msleep(250);

		if (time_after(jiffies, warning_time + 10 * HZ)) {
			printk(KERN_EMERG "unregister_netdevice: "
			       "waiting for %s to become free. Usage "
			       "count = %d\n",
			       dev->name, atomic_read(&dev->refcnt));
			warning_time = jiffies;
		}
	}
}

/* The sequence is:
 *
 *	rtnl_lock();
 *	...
 *	register_netdevice(x1);
 *	register_netdevice(x2);
 *	...
 *	unregister_netdevice(y1);
 *	unregister_netdevice(y2);
 *      ...
 *	rtnl_unlock();
 *	free_netdev(y1);
 *	free_netdev(y2);
 *
 * We are invoked by rtnl_unlock().
 * This allows us to deal with problems:
 * 1) We can delete sysfs objects which invoke hotplug
 *    without deadlocking with linkwatch via keventd.
 * 2) Since we run with the RTNL semaphore not held, we can sleep
 *    safely in order to wait for the netdev refcnt to drop to zero.
 *
 * We must not return until all unregister events added during
 * the interval the lock was held have been completed.
 */
void netdev_run_todo(void)
{
	struct list_head list;

	/* Snapshot list, allow later requests */
	list_replace_init(&net_todo_list, &list);

	__rtnl_unlock();

	while (!list_empty(&list)) {
		struct net_device *dev
			= list_entry(list.next, struct net_device, todo_list);
		list_del(&dev->todo_list);

		if (unlikely(dev->reg_state != NETREG_UNREGISTERING)) {
			printk(KERN_ERR "network todo '%s' but state %d\n",
			       dev->name, dev->reg_state);
			dump_stack();
			continue;
		}

		dev->reg_state = NETREG_UNREGISTERED;

		on_each_cpu(flush_backlog, dev, 1);

		netdev_wait_allrefs(dev);

		/* paranoia */
		BUG_ON(atomic_read(&dev->refcnt));
		WARN_ON(dev->ip_ptr);