dev.c

	 */

	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);
		rcu_read_lock();
		ret = dev_ifsioc_locked(net, &ifr, cmd);
		rcu_read_unlock();
		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_many(struct list_head *head)
{
	struct net_device *dev, *tmp;

	BUG_ON(dev_boot_phase);
	ASSERT_RTNL();

	list_for_each_entry_safe(dev, tmp, head, unreg_list) {
		/* Some devices call without registering
		 * for initialization unwind. Remove those
		 * devices and proceed with the remaining.
		 */
		if (dev->reg_state == NETREG_UNINITIALIZED) {
			pr_debug("unregister_netdevice: device %s/%p never "
				 "was registered\n", dev->name, dev);

			WARN_ON(1);
			list_del(&dev->unreg_list);
			continue;
		}

		BUG_ON(dev->reg_state != NETREG_REGISTERED);
	}

	/* If device is running, close it first. */
	dev_close_many(head);

	list_for_each_entry(dev, head, unreg_list) {
		/* And unlink it from device chain. */
		unlist_netdevice(dev);

		dev->reg_state = NETREG_UNREGISTERING;
	}

	synchronize_net();

	list_for_each_entry(dev, head, unreg_list) {
		/* 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);

		if (!dev->rtnl_link_ops ||
		    dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
			rtmsg_ifinfo(RTM_DELLINK, dev, ~0U);

		/*
		 *	Flush the unicast and multicast chains
		 */
		dev_uc_flush(dev);
		dev_mc_flush(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);
	}

	/* Process any work delayed until the end of the batch */
	dev = list_first_entry(head, struct net_device, unreg_list);
	call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev);

	rcu_barrier();

	list_for_each_entry(dev, head, unreg_list)
		dev_put(dev);
}

static void rollback_registered(struct net_device *dev)
{
	LIST_HEAD(single);

	list_add(&dev->unreg_list, &single);
	rollback_registered_many(&single);
}

u32 netdev_fix_features(struct net_device *dev, u32 features)
{
	/* Fix illegal checksum combinations */
	if ((features & NETIF_F_HW_CSUM) &&
	    (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) {
		netdev_info(dev, "mixed HW and IP checksum settings.\n");
		features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM);
	}

	if ((features & NETIF_F_NO_CSUM) &&
	    (features & (NETIF_F_HW_CSUM|NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) {
		netdev_info(dev, "mixed no checksumming and other settings.\n");
		features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM|NETIF_F_HW_CSUM);
	}

	/* Fix illegal SG+CSUM combinations. */
	if ((features & NETIF_F_SG) &&
	    !(features & NETIF_F_ALL_CSUM)) {
		netdev_info(dev,
			    "Dropping NETIF_F_SG since no checksum feature.\n");
		features &= ~NETIF_F_SG;
	}

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

	/* UFO needs SG and checksumming */
	if (features & NETIF_F_UFO) {
		/* maybe split UFO into V4 and V6? */
		if (!((features & NETIF_F_GEN_CSUM) ||
		    (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))
			    == (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) {
			netdev_info(dev,
				"Dropping NETIF_F_UFO since no checksum offload features.\n");
			features &= ~NETIF_F_UFO;
		}

		if (!(features & NETIF_F_SG)) {
			netdev_info(dev,
				"Dropping NETIF_F_UFO since no NETIF_F_SG feature.\n");
			features &= ~NETIF_F_UFO;
		}
	}

	return features;
}
EXPORT_SYMBOL(netdev_fix_features);

/**
 *	netif_stacked_transfer_operstate -	transfer operstate
 *	@rootdev: the root or lower level device to transfer state from
 *	@dev: the device to transfer operstate to
 *
 *	Transfer operational state from root to device. This is normally
 *	called when a stacking relationship exists between the root
 *	device and the device(a leaf device).
 */
void netif_stacked_transfer_operstate(const struct net_device *rootdev,
					struct net_device *dev)
{
	if (rootdev->operstate == IF_OPER_DORMANT)
		netif_dormant_on(dev);
	else
		netif_dormant_off(dev);

	if (netif_carrier_ok(rootdev)) {
		if (!netif_carrier_ok(dev))
			netif_carrier_on(dev);
	} else {
		if (netif_carrier_ok(dev))
			netif_carrier_off(dev);
	}
}
EXPORT_SYMBOL(netif_stacked_transfer_operstate);

#ifdef CONFIG_RPS
static int netif_alloc_rx_queues(struct net_device *dev)
{
	unsigned int i, count = dev->num_rx_queues;
	struct netdev_rx_queue *rx;

	BUG_ON(count < 1);

	rx = kcalloc(count, sizeof(struct netdev_rx_queue), GFP_KERNEL);
	if (!rx) {
		pr_err("netdev: Unable to allocate %u rx queues.\n", count);
		return -ENOMEM;
	}
	dev->_rx = rx;

	for (i = 0; i < count; i++)
		rx[i].dev = dev;
	return 0;
}
#endif

static void netdev_init_one_queue(struct net_device *dev,
				  struct netdev_queue *queue, void *_unused)
{
	/* Initialize queue lock */
	spin_lock_init(&queue->_xmit_lock);
	netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type);
	queue->xmit_lock_owner = -1;
	netdev_queue_numa_node_write(queue, NUMA_NO_NODE);
	queue->dev = dev;
}

static int netif_alloc_netdev_queues(struct net_device *dev)
{
	unsigned int count = dev->num_tx_queues;
	struct netdev_queue *tx;

	BUG_ON(count < 1);

	tx = kcalloc(count, sizeof(struct netdev_queue), GFP_KERNEL);
	if (!tx) {
		pr_err("netdev: Unable to allocate %u tx queues.\n",
		       count);
		return -ENOMEM;
	}
	dev->_tx = tx;

	netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL);
	spin_lock_init(&dev->tx_global_lock);

	return 0;
}

/**
 *	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)
{
	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);

	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;
		}
	}

	ret = dev_get_valid_name(dev, dev->name, 0);
	if (ret)
		goto err_uninit;

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

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

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

	/* Enable GRO and NETIF_F_HIGHDMA for vlans by default,
	 * vlan_dev_init() will do the dev->features check, so these features
	 * are enabled only if supported by underlying device.
	 */
	dev->vlan_features |= (NETIF_F_GRO | NETIF_F_HIGHDMA);

	ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev);
	ret = notifier_to_errno(ret);
	if (ret)
		goto err_uninit;

	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;
	}
	/*
	 *	Prevent userspace races by waiting until the network
	 *	device is fully setup before sending notifications.
	 */
	if (!dev->rtnl_link_ops ||
	    dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
		rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U);

out:
	return ret;

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

/**
 *	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;

	/* 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);

	/* Note : We dont allocate pcpu_refcnt for dummy devices,
	 * because users of this 'device' dont need to change
	 * its refcount.
	 */

	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);

int netdev_refcnt_read(const struct net_device *dev)
{
	int i, refcnt = 0;

	for_each_possible_cpu(i)
		refcnt += *per_cpu_ptr(dev->pcpu_refcnt, i);
	return refcnt;
}
EXPORT_SYMBOL(netdev_refcnt_read);

/*
 * 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;
	int refcnt;

	linkwatch_forget_dev(dev);

	rebroadcast_time = warning_time = jiffies;
	refcnt = netdev_refcnt_read(dev);

	while (refcnt != 0) {
		if (time_after(jiffies, rebroadcast_time + 1 * HZ)) {
			rtnl_lock();

			/* Rebroadcast unregister notification */
			call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
			/* don't resend NETDEV_UNREGISTER_BATCH, _BATCH users
			 * should have already handle it the first time */

			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);

		refcnt = netdev_refcnt_read(dev);

		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, 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_first_entry(&list, 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(netdev_refcnt_read(dev));
		WARN_ON(rcu_dereference_raw(dev->ip_ptr));
		WARN_ON(rcu_dereference_raw(dev->ip6_ptr));
		WARN_ON(dev->dn_ptr);

		if (dev->destructor)
			dev->destructor(dev);

		/* Free network device */
		kobject_put(&dev->dev.kobj);
	}
}

/* Convert net_device_stats to rtnl_link_stats64.  They have the same
 * fields in the same order, with only the type differing.
 */
static void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64,
				    const struct net_device_stats *netdev_stats)
{
#if BITS_PER_LONG == 64
        BUILD_BUG_ON(sizeof(*stats64) != sizeof(*netdev_stats));
        memcpy(stats64, netdev_stats, sizeof(*stats64));
#else
	size_t i, n = sizeof(*stats64) / sizeof(u64);
	const unsigned long *src = (const unsigned long *)netdev_stats;
	u64 *dst = (u64 *)stats64;

	BUILD_BUG_ON(sizeof(*netdev_stats) / sizeof(unsigned long) !=
		     sizeof(*stats64) / sizeof(u64));
	for (i = 0; i < n; i++)
		dst[i] = src[i];
#endif
}

/**
 *	dev_get_stats	- get network device statistics
 *	@dev: device to get statistics from
 *	@storage: place to store stats
 *
 *	Get network statistics from device. Return @storage.
 *	The device driver may provide its own method by setting
 *	dev->netdev_ops->get_stats64 or dev->netdev_ops->get_stats;
 *	otherwise the internal statistics structure is used.
 */
struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
					struct rtnl_link_stats64 *storage)
{
	const struct net_device_ops *ops = dev->netdev_ops;

	if (ops->ndo_get_stats64) {
		memset(storage, 0, sizeof(*storage));
		ops->ndo_get_stats64(dev, storage);
	} else if (ops->ndo_get_stats) {
		netdev_stats_to_stats64(storage, ops->ndo_get_stats(dev));
	} else {
		netdev_stats_to_stats64(storage, &dev->stats);
	}
	storage->rx_dropped += atomic_long_read(&dev->rx_dropped);
	return storage;
}
EXPORT_SYMBOL(dev_get_stats);

struct netdev_queue *dev_ingress_queue_create(struct net_device *dev)
{
	struct netdev_queue *queue = dev_ingress_queue(dev);

#ifdef CONFIG_NET_CLS_ACT
	if (queue)
		return queue;
	queue = kzalloc(sizeof(*queue), GFP_KERNEL);
	if (!queue)
		return NULL;
	netdev_init_one_queue(dev, queue, NULL);
	queue->qdisc = &noop_qdisc;
	queue->qdisc_sleeping = &noop_qdisc;
	rcu_assign_pointer(dev->ingress_queue, queue);
#endif
	return queue;
}

/**
 *	alloc_netdev_mqs - allocate network device
 *	@sizeof_priv:	size of private data to allocate space for
 *	@name:		device name format string
 *	@setup:		callback to initialize device
 *	@txqs:		the number of TX subqueues to allocate
 *	@rxqs:		the number of RX subqueues to allocate
 *
 *	Allocates a struct net_device with private data area for driver use
 *	and performs basic initialization.  Also allocates subquue structs
 *	for each queue on the device.
 */
struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
		void (*setup)(struct net_device *),
		unsigned int txqs, unsigned int rxqs)
{
	struct net_device *dev;
	size_t alloc_size;
	struct net_device *p;

	BUG_ON(strlen(name) >= sizeof(dev->name));

	if (txqs < 1) {
		pr_err("alloc_netdev: Unable to allocate device "
		       "with zero queues.\n");
		return NULL;
	}

#ifdef CONFIG_RPS
	if (rxqs < 1) {
		pr_err("alloc_netdev: Unable to allocate device "
		       "with zero RX queues.\n");
		return NULL;
	}
#endif

	alloc_size = sizeof(struct net_device);
	if (sizeof_priv) {
		/* ensure 32-byte alignment of private area */
		alloc_size = ALIGN(alloc_size, NETDEV_ALIGN);
		alloc_size += sizeof_priv;
	}
	/* ensure 32-byte alignment of whole construct */
	alloc_size += NETDEV_ALIGN - 1;

	p = kzalloc(alloc_size, GFP_KERNEL);
	if (!p) {
		printk(KERN_ERR "alloc_netdev: Unable to allocate device.\n");
		return NULL;
	}

	dev = PTR_ALIGN(p, NETDEV_ALIGN);
	dev->padded = (char *)dev - (char *)p;

	dev->pcpu_refcnt = alloc_percpu(int);
	if (!dev->pcpu_refcnt)
		goto free_p;

	if (dev_addr_init(dev))
		goto free_pcpu;

	dev_mc_init(dev);
	dev_uc_init(dev);

	dev_net_set(dev, &init_net);

	dev->gso_max_size = GSO_MAX_SIZE;

	INIT_LIST_HEAD(&dev->ethtool_ntuple_list.list);
	dev->ethtool_ntuple_list.count = 0;
	INIT_LIST_HEAD(&dev->napi_list);
	INIT_LIST_HEAD(&dev->unreg_list);
	INIT_LIST_HEAD(&dev->link_watch_list);
	dev->priv_flags = IFF_XMIT_DST_RELEASE;
	setup(dev);

	dev->num_tx_queues = txqs;
	dev->real_num_tx_queues = txqs;
	if (netif_alloc_netdev_queues(dev))
		goto free_all;

#ifdef CONFIG_RPS
	dev->num_rx_queues = rxqs;
	dev->real_num_rx_queues = rxqs;
	if (netif_alloc_rx_queues(dev))
		goto free_all;
#endif

	strcpy(dev->name, name);
	dev->group = INIT_NETDEV_GROUP;
	return dev;

free_all:
	free_netdev(dev);
	return NULL;

free_pcpu:
	free_percpu(dev->pcpu_refcnt);
	kfree(dev->_tx);
#ifdef CONFIG_RPS
	kfree(dev->_rx);
#endif

free_p:
	kfree(p);
	return NULL;
}
EXPORT_SYMBOL(alloc_netdev_mqs);

/**
 *	free_netdev - free network device
 *	@dev: device
 *
 *	This function does the last stage of destroying an allocated device
 * 	interface. The reference to the device object is released.
 *	If this is the last reference then it will be freed.
 */
void free_netdev(struct net_device *dev)
{
	struct napi_struct *p, *n;

	release_net(dev_net(dev));

	kfree(dev->_tx);
#ifdef CONFIG_RPS
	kfree(dev->_rx);
#endif

	kfree(rcu_dereference_raw(dev->ingress_queue));

	/* Flush device addresses */
	dev_addr_flush(dev);

	/* Clear ethtool n-tuple list */
	ethtool_ntuple_flush(dev);

	list_for_each_entry_safe(p, n, &dev->napi_list, dev_list)
		netif_napi_del(p);

	free_percpu(dev->pcpu_refcnt);
	dev->pcpu_refcnt = NULL;

	/*  Compatibility with error handling in drivers */
	if (dev->reg_state == NETREG_UNINITIALIZED) {
		kfree((char *)dev - dev->padded);
		return;
	}

	BUG_ON(dev->reg_state != NETREG_UNREGISTERED);
	dev->reg_state = NETREG_RELEASED;

	/* will free via device release */
	put_device(&dev->dev);
}
EXPORT_SYMBOL(free_netdev);

/**
 *	synchronize_net -  Synchronize with packet receive processing
 *
 *	Wait for packets currently being received to be done.
 *	Does not block later packets from starting.
 */
void synchronize_net(void)
{
	might_sleep();
	synchronize_rcu();
}
EXPORT_SYMBOL(synchronize_net);

/**
 *	unregister_netdevice_queue - remove device from the kernel
 *	@dev: device
 *	@head: list
 *
 *	This function shuts down a device interface and removes it
 *	from the kernel tables.
 *	If head not NULL, device is queued to be unregistered later.
 *
 *	Callers must hold the rtnl semaphore.  You may want
 *	unregister_netdev() instead of this.
 */

void unregister_netdevice_queue(struct net_device *dev, struct list_head *head)
{
	ASSERT_RTNL();

	if (head) {
		list_move_tail(&dev->unreg_list, head);
	} else {
		rollback_registered(dev);
		/* Finish processing unregister after unlock */
		net_set_todo(dev);
	}
}
EXPORT_SYMBOL(unregister_netdevice_queue);

/**
 *	unregister_netdevice_many - unregister many devices
 *	@head: list of devices
 */
void unregister_netdevice_many(struct list_head *head)
{
	struct net_device *dev;

	if (!list_empty(head)) {
		rollback_registered_many(head);
		list_for_each_entry(dev, head, unreg_list)
			net_set_todo(dev);
	}
}
EXPORT_SYMBOL(unregister_netdevice_many);

/**
 *	unregister_netdev - remove device from the kernel
 *	@dev: device
 *
 *	This function shuts down a device interface and removes it
 *	from the kernel tables.
 *
 *	This is just a wrapper for unregister_netdevice that takes
 *	the rtnl semaphore.  In general you want to use this and not
 *	unregister_netdevice.
 */
void unregister_netdev(struct net_device *dev)
{
	rtnl_lock();
	unregister_netdevice(dev);
	rtnl_unlock();
}
EXPORT_SYMBOL(unregister_netdev);