dev.c

linux 内核源代码

	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)
{
	might_sleep();

	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.
	 */
	call_netdevice_notifiers(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().
	 *
	 * dev->stop() will invoke napi_disable() on all of it's
	 * napi_struct instances on this device.
	 */
	smp_mb__after_clear_bit(); /* Commit netif_running(). */

	/*
	 *	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
	 */
	call_netdevice_notifiers(NETDEV_DOWN, dev);

	return 0;
}


static int dev_boot_phase = 1;

/*
 *	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;
	struct net_device *last;
	struct net *net;
	int err;

	rtnl_lock();
	err = raw_notifier_chain_register(&netdev_chain, nb);
	if (err)
		goto unlock;
	if (dev_boot_phase)
		goto unlock;
	for_each_net(net) {
		for_each_netdev(net, dev) {
			err = nb->notifier_call(nb, NETDEV_REGISTER, dev);
			err = notifier_to_errno(err);
			if (err)
				goto rollback;

			if (!(dev->flags & IFF_UP))
				continue;

			nb->notifier_call(nb, NETDEV_UP, dev);
		}
	}

unlock:
	rtnl_unlock();
	return err;

rollback:
	last = dev;
	for_each_net(net) {
		for_each_netdev(net, dev) {
			if (dev == last)
				break;

			if (dev->flags & IFF_UP) {
				nb->notifier_call(nb, NETDEV_GOING_DOWN, dev);
				nb->notifier_call(nb, NETDEV_DOWN, dev);
			}
			nb->notifier_call(nb, NETDEV_UNREGISTER, dev);
		}
	}

	raw_notifier_chain_unregister(&netdev_chain, nb);
	goto unlock;
}

/**
 *	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)
{
	int err;

	rtnl_lock();
	err = raw_notifier_chain_unregister(&netdev_chain, nb);
	rtnl_unlock();
	return err;
}

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

int call_netdevice_notifiers(unsigned long val, struct net_device *dev)
{
	return raw_notifier_call_chain(&netdev_chain, val, dev);
}

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

void net_enable_timestamp(void)
{
	atomic_inc(&netstamp_needed);
}

void net_disable_timestamp(void)
{
	atomic_dec(&netstamp_needed);
}

static inline void net_timestamp(struct sk_buff *skb)
{
	if (atomic_read(&netstamp_needed))
		__net_timestamp(skb);
	else
		skb->tstamp.tv64 = 0;
}

/*
 *	Support routine. Sends outgoing frames to any network
 *	taps currently in use.
 */

static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
{
	struct packet_type *ptype;

	net_timestamp(skb);

	rcu_read_lock();
	list_for_each_entry_rcu(ptype, &ptype_all, list) {
		/* Never send packets back to the socket
		 * they originated from - MvS ([e-mail])
		 */
		if ((ptype->dev == dev || !ptype->dev) &&
		    (ptype->af_packet_priv == NULL ||
		     (struct sock *)ptype->af_packet_priv != skb->sk)) {
			struct sk_buff *skb2= skb_clone(skb, GFP_ATOMIC);
			if (!skb2)
				break;

			/* skb->nh should be correctly
			   set by sender, so that the second statement is
			   just protection against buggy protocols.
			 */
			skb_reset_mac_header(skb2);

			if (skb_network_header(skb2) < skb2->data ||
			    skb2->network_header > skb2->tail) {
				if (net_ratelimit())
					printk(KERN_CRIT "protocol %04x is "
					       "buggy, dev %s\n",
					       skb2->protocol, dev->name);
				skb_reset_network_header(skb2);
			}

			skb2->transport_header = skb2->network_header;
			skb2->pkt_type = PACKET_OUTGOING;
			ptype->func(skb2, skb->dev, ptype, skb->dev);
		}
	}
	rcu_read_unlock();
}


void __netif_schedule(struct net_device *dev)
{
	if (!test_and_set_bit(__LINK_STATE_SCHED, &dev->state)) {
		unsigned long flags;
		struct softnet_data *sd;

		local_irq_save(flags);
		sd = &__get_cpu_var(softnet_data);
		dev->next_sched = sd->output_queue;
		sd->output_queue = dev;
		raise_softirq_irqoff(NET_TX_SOFTIRQ);
		local_irq_restore(flags);
	}
}
EXPORT_SYMBOL(__netif_schedule);

void dev_kfree_skb_irq(struct sk_buff *skb)
{
	if (atomic_dec_and_test(&skb->users)) {
		struct softnet_data *sd;
		unsigned long flags;

		local_irq_save(flags);
		sd = &__get_cpu_var(softnet_data);
		skb->next = sd->completion_queue;
		sd->completion_queue = skb;
		raise_softirq_irqoff(NET_TX_SOFTIRQ);
		local_irq_restore(flags);
	}
}
EXPORT_SYMBOL(dev_kfree_skb_irq);

void dev_kfree_skb_any(struct sk_buff *skb)
{
	if (in_irq() || irqs_disabled())
		dev_kfree_skb_irq(skb);
	else
		dev_kfree_skb(skb);
}
EXPORT_SYMBOL(dev_kfree_skb_any);


/**
 * netif_device_detach - mark device as removed
 * @dev: network device
 *
 * Mark device as removed from system and therefore no longer available.
 */
void netif_device_detach(struct net_device *dev)
{
	if (test_and_clear_bit(__LINK_STATE_PRESENT, &dev->state) &&
	    netif_running(dev)) {
		netif_stop_queue(dev);
	}
}
EXPORT_SYMBOL(netif_device_detach);

/**
 * netif_device_attach - mark device as attached
 * @dev: network device
 *
 * Mark device as attached from system and restart if needed.
 */
void netif_device_attach(struct net_device *dev)
{
	if (!test_and_set_bit(__LINK_STATE_PRESENT, &dev->state) &&
	    netif_running(dev)) {
		netif_wake_queue(dev);
		__netdev_watchdog_up(dev);
	}
}
EXPORT_SYMBOL(netif_device_attach);


/*
 * Invalidate hardware checksum when packet is to be mangled, and
 * complete checksum manually on outgoing path.
 */
int skb_checksum_help(struct sk_buff *skb)
{
	__wsum csum;
	int ret = 0, offset;

	if (skb->ip_summed == CHECKSUM_COMPLETE)
		goto out_set_summed;

	if (unlikely(skb_shinfo(skb)->gso_size)) {
		/* Let GSO fix up the checksum. */
		goto out_set_summed;
	}

	offset = skb->csum_start - skb_headroom(skb);
	BUG_ON(offset >= skb_headlen(skb));
	csum = skb_checksum(skb, offset, skb->len - offset, 0);

	offset += skb->csum_offset;
	BUG_ON(offset + sizeof(__sum16) > skb_headlen(skb));

	if (skb_cloned(skb) &&
	    !skb_clone_writable(skb, offset + sizeof(__sum16))) {
		ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
		if (ret)
			goto out;
	}

	*(__sum16 *)(skb->data + offset) = csum_fold(csum);
out_set_summed:
	skb->ip_summed = CHECKSUM_NONE;
out:
	return ret;
}

/**
 *	skb_gso_segment - Perform segmentation on skb.
 *	@skb: buffer to segment
 *	@features: features for the output path (see dev->features)
 *
 *	This function segments the given skb and returns a list of segments.
 *
 *	It may return NULL if the skb requires no segmentation.  This is
 *	only possible when GSO is used for verifying header integrity.
 */
struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features)
{
	struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
	struct packet_type *ptype;
	__be16 type = skb->protocol;
	int err;

	BUG_ON(skb_shinfo(skb)->frag_list);

	skb_reset_mac_header(skb);
	skb->mac_len = skb->network_header - skb->mac_header;
	__skb_pull(skb, skb->mac_len);

	if (WARN_ON(skb->ip_summed != CHECKSUM_PARTIAL)) {
		if (skb_header_cloned(skb) &&
		    (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))
			return ERR_PTR(err);
	}

	rcu_read_lock();
	list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type) & 15], list) {
		if (ptype->type == type && !ptype->dev && ptype->gso_segment) {
			if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) {
				err = ptype->gso_send_check(skb);
				segs = ERR_PTR(err);
				if (err || skb_gso_ok(skb, features))
					break;
				__skb_push(skb, (skb->data -
						 skb_network_header(skb)));
			}
			segs = ptype->gso_segment(skb, features);
			break;
		}
	}
	rcu_read_unlock();

	__skb_push(skb, skb->data - skb_mac_header(skb));

	return segs;
}

EXPORT_SYMBOL(skb_gso_segment);

/* Take action when hardware reception checksum errors are detected. */
#ifdef CONFIG_BUG
void netdev_rx_csum_fault(struct net_device *dev)
{
	if (net_ratelimit()) {
		printk(KERN_ERR "%s: hw csum failure.\n",
			dev ? dev->name : "<unknown>");
		dump_stack();
	}
}
EXPORT_SYMBOL(netdev_rx_csum_fault);
#endif

/* Actually, we should eliminate this check as soon as we know, that:
 * 1. IOMMU is present and allows to map all the memory.
 * 2. No high memory really exists on this machine.
 */

static inline int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
{
#ifdef CONFIG_HIGHMEM
	int i;

	if (dev->features & NETIF_F_HIGHDMA)
		return 0;

	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
		if (PageHighMem(skb_shinfo(skb)->frags[i].page))
			return 1;

#endif
	return 0;
}

struct dev_gso_cb {
	void (*destructor)(struct sk_buff *skb);
};

#define DEV_GSO_CB(skb) ((struct dev_gso_cb *)(skb)->cb)

static void dev_gso_skb_destructor(struct sk_buff *skb)
{
	struct dev_gso_cb *cb;

	do {
		struct sk_buff *nskb = skb->next;

		skb->next = nskb->next;
		nskb->next = NULL;
		kfree_skb(nskb);
	} while (skb->next);

	cb = DEV_GSO_CB(skb);
	if (cb->destructor)
		cb->destructor(skb);
}

/**
 *	dev_gso_segment - Perform emulated hardware segmentation on skb.
 *	@skb: buffer to segment
 *
 *	This function segments the given skb and stores the list of segments
 *	in skb->next.
 */
static int dev_gso_segment(struct sk_buff *skb)
{
	struct net_device *dev = skb->dev;
	struct sk_buff *segs;
	int features = dev->features & ~(illegal_highdma(dev, skb) ?
					 NETIF_F_SG : 0);

	segs = skb_gso_segment(skb, features);

	/* Verifying header integrity only. */
	if (!segs)
		return 0;

	if (unlikely(IS_ERR(segs)))
		return PTR_ERR(segs);

	skb->next = segs;
	DEV_GSO_CB(skb)->destructor = skb->destructor;
	skb->destructor = dev_gso_skb_destructor;

	return 0;
}

int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
	if (likely(!skb->next)) {
		if (!list_empty(&ptype_all))
			dev_queue_xmit_nit(skb, dev);

		if (netif_needs_gso(dev, skb)) {
			if (unlikely(dev_gso_segment(skb)))
				goto out_kfree_skb;
			if (skb->next)
				goto gso;
		}

		return dev->hard_start_xmit(skb, dev);
	}

gso:
	do {
		struct sk_buff *nskb = skb->next;
		int rc;

		skb->next = nskb->next;
		nskb->next = NULL;
		rc = dev->hard_start_xmit(nskb, dev);
		if (unlikely(rc)) {
			nskb->next = skb->next;
			skb->next = nskb;
			return rc;
		}
		if (unlikely((netif_queue_stopped(dev) ||
			     netif_subqueue_stopped(dev, skb)) &&
			     skb->next))
			return NETDEV_TX_BUSY;
	} while (skb->next);