dev.c

	struct hlist_head *head;
	struct hlist_node *p;
	int ret;

	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);

	spin_lock_init(&dev->queue_lock);
	spin_lock_init(&dev->_xmit_lock);
	dev->xmit_lock_owner = -1;
#ifdef CONFIG_NET_CLS_ACT
	spin_lock_init(&dev->ingress_lock);
#endif

	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 out;
	}

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

	/* Check for existence of name */
	head = dev_name_hash(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 out;
		}
	}

	/* 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",
					dev->name);
			dev->features &= ~NETIF_F_UFO;
		}
	}

	/*
	 *	nil rebuild_header routine,
	 *	that should be never called and used as just bug trap.
	 */

	if (!dev->rebuild_header)
		dev->rebuild_header = default_rebuild_header;

	ret = netdev_register_sysfs(dev);
	if (ret)
		goto out;
	dev->reg_state = NETREG_REGISTERED;

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

	set_bit(__LINK_STATE_PRESENT, &dev->state);

	dev->next = NULL;
	dev_init_scheduler(dev);
	write_lock_bh(&dev_base_lock);
	*dev_tail = dev;
	dev_tail = &dev->next;
	hlist_add_head(&dev->name_hlist, head);
	hlist_add_head(&dev->index_hlist, dev_index_hash(dev->ifindex));
	dev_hold(dev);
	write_unlock_bh(&dev_base_lock);

	/* Notify protocols, that a new device appeared. */
	raw_notifier_call_chain(&netdev_chain, NETDEV_REGISTER, dev);

	ret = 0;

out:
	return ret;
}

/**
 *	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_netdev 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 */
			raw_notifier_call_chain(&netdev_chain,
					    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() after it drops the semaphore.
 * 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.
 */
static DEFINE_MUTEX(net_todo_run_mutex);
void netdev_run_todo(void)
{
	struct list_head list;

	/* Need to guard against multiple cpu's getting out of order. */
	mutex_lock(&net_todo_run_mutex);

	/* Not safe to do outside the semaphore.  We must not return
	 * until all unregister events invoked by the local processor
	 * have been completed (either by this todo run, or one on
	 * another cpu).
	 */
	if (list_empty(&net_todo_list))
		goto out;

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

	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;
		}

		netdev_unregister_sysfs(dev);
		dev->reg_state = NETREG_UNREGISTERED;

		netdev_wait_allrefs(dev);

		/* paranoia */
		BUG_ON(atomic_read(&dev->refcnt));
		BUG_TRAP(!dev->ip_ptr);
		BUG_TRAP(!dev->ip6_ptr);
		BUG_TRAP(!dev->dn_ptr);

		/* It must be the very last action,
		 * after this 'dev' may point to freed up memory.
		 */
		if (dev->destructor)
			dev->destructor(dev);
	}

out:
	mutex_unlock(&net_todo_run_mutex);
}

/**
 *	alloc_netdev - allocate network device
 *	@sizeof_priv:	size of private data to allocate space for
 *	@name:		device name format string
 *	@setup:		callback to initialize device
 *
 *	Allocates a struct net_device with private data area for driver use
 *	and performs basic initialization.
 */
struct net_device *alloc_netdev(int sizeof_priv, const char *name,
		void (*setup)(struct net_device *))
{
	void *p;
	struct net_device *dev;
	int alloc_size;

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

	/* ensure 32-byte alignment of both the device and private area */
	alloc_size = (sizeof(*dev) + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST;
	alloc_size += sizeof_priv + NETDEV_ALIGN_CONST;

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

	dev = (struct net_device *)
		(((long)p + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST);
	dev->padded = (char *)dev - (char *)p;

	if (sizeof_priv)
		dev->priv = netdev_priv(dev);

	setup(dev);
	strcpy(dev->name, name);
	return dev;
}
EXPORT_SYMBOL(alloc_netdev);

/**
 *	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)
{
#ifdef CONFIG_SYSFS
	/*  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);
#else
	kfree((char *)dev - dev->padded);
#endif
}

/* Synchronize with packet receive processing. */
void synchronize_net(void)
{
	might_sleep();
	synchronize_rcu();
}

/**
 *	unregister_netdevice - remove device from the kernel
 *	@dev: device
 *
 *	This function shuts down a device interface and removes it
 *	from the kernel tables. On success 0 is returned, on a failure
 *	a negative errno code is returned.
 *
 *	Callers must hold the rtnl semaphore.  You may want
 *	unregister_netdev() instead of this.
 */

void unregister_netdevice(struct net_device *dev)
{
	struct net_device *d, **dp;

	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. */
	if (dev->flags & IFF_UP)
		dev_close(dev);

	/* And unlink it from device chain. */
	for (dp = &dev_base; (d = *dp) != NULL; dp = &d->next) {
		if (d == dev) {
			write_lock_bh(&dev_base_lock);
			hlist_del(&dev->name_hlist);
			hlist_del(&dev->index_hlist);
			if (dev_tail == &dev->next)
				dev_tail = dp;
			*dp = d->next;
			write_unlock_bh(&dev_base_lock);
			break;
		}
	}
	BUG_ON(!d);

	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.
	*/
	raw_notifier_call_chain(&netdev_chain, NETDEV_UNREGISTER, dev);

	/*
	 *	Flush the multicast chain
	 */
	dev_mc_discard(dev);

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

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

	/* Finish processing unregister after unlock */
	net_set_todo(dev);

	synchronize_net();

	dev_put(dev);
}

/**
 *	unregister_netdev - remove device from the kernel
 *	@dev: device
 *
 *	This function shuts down a device interface and removes it
 *	from the kernel tables. On success 0 is returned, on a failure
 *	a negative errno code is returned.
 *
 *	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);

static int dev_cpu_callback(struct notifier_block *nfb,
			    unsigned long action,
			    void *ocpu)
{
	struct sk_buff **list_skb;
	struct net_device **list_net;
	struct sk_buff *skb;
	unsigned int cpu, oldcpu = (unsigned long)ocpu;
	struct softnet_data *sd, *oldsd;

	if (action != CPU_DEAD)
		return NOTIFY_OK;

	local_irq_disable();
	cpu = smp_processor_id();
	sd = &per_cpu(softnet_data, cpu);
	oldsd = &per_cpu(softnet_data, oldcpu);

	/* Find end of our completion_queue. */
	list_skb = &sd->completion_queue;
	while (*list_skb)
		list_skb = &(*list_skb)->next;
	/* Append completion queue from offline CPU. */
	*list_skb = oldsd->completion_queue;
	oldsd->completion_queue = NULL;

	/* Find end of our output_queue. */
	list_net = &sd->output_queue;
	while (*list_net)
		list_net = &(*list_net)->next_sched;
	/* Append output queue from offline CPU. */
	*list_net = oldsd->output_queue;
	oldsd->output_queue = NULL;

	raise_softirq_irqoff(NET_TX_SOFTIRQ);
	local_irq_enable();

	/* Process offline CPU's input_pkt_queue */
	while ((skb = __skb_dequeue(&oldsd->input_pkt_queue)))
		netif_rx(skb);

	return NOTIFY_OK;
}

#ifdef CONFIG_NET_DMA
/**
 * net_dma_rebalance -
 * This is called when the number of channels allocated to the net_dma_client
 * changes.  The net_dma_client tries to have one DMA channel per CPU.
 */
static void net_dma_rebalance(void)
{
	unsigned int cpu, i, n;
	struct dma_chan *chan;

	if (net_dma_count == 0) {
		for_each_online_cpu(cpu)
			rcu_assign_pointer(per_cpu(softnet_data, cpu).net_dma, NULL);
		return;
	}

	i = 0;
	cpu = first_cpu(cpu_online_map);

	rcu_read_lock();
	list_for_each_entry(chan, &net_dma_client->channels, client_node) {
		n = ((num_online_cpus() / net_dma_count)
		   + (i < (num_online_cpus() % net_dma_count) ? 1 : 0));

		while(n) {
			per_cpu(softnet_data, cpu).net_dma = chan;
			cpu = next_cpu(cpu, cpu_online_map);
			n--;
		}
		i++;
	}
	rcu_read_unlock();
}

/**
 * netdev_dma_event - event callback for the net_dma_client
 * @client: should always be net_dma_client
 * @chan: DMA channel for the event
 * @event: event type
 */
static void netdev_dma_event(struct dma_client *client, struct dma_chan *chan,
	enum dma_event event)
{
	spin_lock(&net_dma_event_lock);
	switch (event) {
	case DMA_RESOURCE_ADDED:
		net_dma_count++;
		net_dma_rebalance();
		break;
	case DMA_RESOURCE_REMOVED:
		net_dma_count--;
		net_dma_rebalance();
		break;
	default:
		break;
	}
	spin_unlock(&net_dma_event_lock);
}

/**
 * netdev_dma_regiser - register the networking subsystem as a DMA client
 */
static int __init netdev_dma_register(void)
{
	spin_lock_init(&net_dma_event_lock);
	net_dma_client = dma_async_client_register(netdev_dma_event);
	if (net_dma_client == NULL)
		return -ENOMEM;

	dma_async_client_chan_request(net_dma_client, num_online_cpus());
	return 0;
}

#else
static int __init netdev_dma_register(void) { return -ENODEV; }
#endif /* CONFIG_NET_DMA */

/*
 *	Initialize the DEV module. At boot time this walks the device list and
 *	unhooks any devices that fail to initialise (normally hardware not
 *	present) and leaves us with a valid list of present and active devices.
 *
 */

/*
 *       This is called single threaded during boot, so no need
 *       to take the rtnl semaphore.
 */
static int __init net_dev_init(void)
{
	int i, rc = -ENOMEM;

	BUG_ON(!dev_boot_phase);

	if (dev_proc_init())
		goto out;

	if (netdev_sysfs_init())
		goto out;

	INIT_LIST_HEAD(&ptype_all);
	for (i = 0; i < 16; i++)
		INIT_LIST_HEAD(&ptype_base[i]);

	for (i = 0; i < ARRAY_SIZE(dev_name_head); i++)
		INIT_HLIST_HEAD(&dev_name_head[i]);

	for (i = 0; i < ARRAY_SIZE(dev_index_head); i++)
		INIT_HLIST_HEAD(&dev_index_head[i]);

	/*
	 *	Initialise the packet receive queues.
	 */

	for_each_possible_cpu(i) {
		struct softnet_data *queue;

		queue = &per_cpu(softnet_data, i);
		skb_queue_head_init(&queue->input_pkt_queue);
		queue->completion_queue = NULL;
		INIT_LIST_HEAD(&queue->poll_list);
		set_bit(__LINK_STATE_START, &queue->backlog_dev.state);
		queue->backlog_dev.weight = weight_p;
		queue->backlog_dev.poll = process_backlog;
		atomic_set(&queue->backlog_dev.refcnt, 1);
	}

	netdev_dma_register();

	dev_boot_phase = 0;

	open_softirq(NET_TX_SOFTIRQ, net_tx_action, NULL);
	open_softirq(NET_RX_SOFTIRQ, net_rx_action, NULL);

	hotcpu_notifier(dev_cpu_callback, 0);
	dst_init();
	dev_mcast_init();
	rc = 0;
out:
	return rc;
}

subsys_initcall(net_dev_init);

EXPORT_SYMBOL(__dev_get_by_index);
EXPORT_SYMBOL(__dev_get_by_name);
EXPORT_SYMBOL(__dev_remove_pack);
EXPORT_SYMBOL(dev_valid_name);
EXPORT_SYMBOL(dev_add_pack);
EXPORT_SYMBOL(dev_alloc_name);
EXPORT_SYMBOL(dev_close);
EXPORT_SYMBOL(dev_get_by_flags);
EXPORT_SYMBOL(dev_get_by_index);
EXPORT_SYMBOL(dev_get_by_name);
EXPORT_SYMBOL(dev_open);
EXPORT_SYMBOL(dev_queue_xmit);
EXPORT_SYMBOL(dev_remove_pack);
EXPORT_SYMBOL(dev_set_allmulti);
EXPORT_SYMBOL(dev_set_promiscuity);
EXPORT_SYMBOL(dev_change_flags);
EXPORT_SYMBOL(dev_set_mtu);
EXPORT_SYMBOL(dev_set_mac_address);
EXPORT_SYMBOL(free_netdev);
EXPORT_SYMBOL(netdev_boot_setup_check);
EXPORT_SYMBOL(netdev_set_master);
EXPORT_SYMBOL(netdev_state_change);
EXPORT_SYMBOL(netif_receive_skb);
EXPORT_SYMBOL(netif_rx);
EXPORT_SYMBOL(register_gifconf);
EXPORT_SYMBOL(register_netdevice);
EXPORT_SYMBOL(register_netdevice_notifier);
EXPORT_SYMBOL(skb_checksum_help);
EXPORT_SYMBOL(synchronize_net);
EXPORT_SYMBOL(unregister_netdevice);
EXPORT_SYMBOL(unregister_netdevice_notifier);
EXPORT_SYMBOL(net_enable_timestamp);
EXPORT_SYMBOL(net_disable_timestamp);
EXPORT_SYMBOL(dev_get_flags);

#if defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE)
EXPORT_SYMBOL(br_handle_frame_hook);
EXPORT_SYMBOL(br_fdb_get_hook);
EXPORT_SYMBOL(br_fdb_put_hook);
#endif

#ifdef CONFIG_KMOD
EXPORT_SYMBOL(dev_load);
#endif

EXPORT_PER_CPU_SYMBOL(softnet_data);