dev.c

EXPORT_SYMBOL(netdev_features_change);

/**
 *	netdev_state_change - device changes state
 *	@dev: device to cause notification
 *
 *	Called to indicate a device has changed state. This function calls
 *	the notifier chains for netdev_chain and sends a NEWLINK message
 *	to the routing socket.
 */
void netdev_state_change(struct net_device *dev)
{
	if (dev->flags & IFF_UP) {
		call_netdevice_notifiers(NETDEV_CHANGE, dev);
		rtmsg_ifinfo(RTM_NEWLINK, dev, 0);
	}
}
EXPORT_SYMBOL(netdev_state_change);

void netdev_bonding_change(struct net_device *dev, unsigned long event)
{
	call_netdevice_notifiers(event, dev);
}
EXPORT_SYMBOL(netdev_bonding_change);

/**
 *	dev_load 	- load a network module
 *	@net: the applicable net namespace
 *	@name: name of interface
 *
 *	If a network interface is not present and the process has suitable
 *	privileges this function loads the module. If module loading is not
 *	available in this kernel then it becomes a nop.
 */

void dev_load(struct net *net, const char *name)
{
	struct net_device *dev;

	read_lock(&dev_base_lock);
	dev = __dev_get_by_name(net, name);
	read_unlock(&dev_base_lock);

	if (!dev && capable(CAP_NET_ADMIN))
		request_module("%s", name);
}
EXPORT_SYMBOL(dev_load);

/**
 *	dev_open	- prepare an interface for use.
 *	@dev:	device to open
 *
 *	Takes a device from down to up state. The device's private open
 *	function is invoked and then the multicast lists are loaded. Finally
 *	the device is moved into the up state and a %NETDEV_UP message is
 *	sent to the netdev notifier chain.
 *
 *	Calling this function on an active interface is a nop. On a failure
 *	a negative errno code is returned.
 */
int dev_open(struct net_device *dev)
{
	const struct net_device_ops *ops = dev->netdev_ops;
	int ret;

	ASSERT_RTNL();

	/*
	 *	Is it already up?
	 */

	if (dev->flags & IFF_UP)
		return 0;

	/*
	 *	Is it even present?
	 */
	if (!netif_device_present(dev))
		return -ENODEV;

	ret = call_netdevice_notifiers(NETDEV_PRE_UP, dev);
	ret = notifier_to_errno(ret);
	if (ret)
		return ret;

	/*
	 *	Call device private open method
	 */
	set_bit(__LINK_STATE_START, &dev->state);

	if (ops->ndo_validate_addr)
		ret = ops->ndo_validate_addr(dev);

	if (!ret && ops->ndo_open)
		ret = ops->ndo_open(dev);

	/*
	 *	If it went open OK then:
	 */

	if (ret)
		clear_bit(__LINK_STATE_START, &dev->state);
	else {
		/*
		 *	Set the flags.
		 */
		dev->flags |= IFF_UP;

		/*
		 *	Enable NET_DMA
		 */
		net_dmaengine_get();

		/*
		 *	Initialize multicasting status
		 */
		dev_set_rx_mode(dev);

		/*
		 *	Wakeup transmit queue engine
		 */
		dev_activate(dev);

		/*
		 *	... and announce new interface.
		 */
		call_netdevice_notifiers(NETDEV_UP, dev);
	}

	return ret;
}
EXPORT_SYMBOL(dev_open);

/**
 *	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)
{
	const struct net_device_ops *ops = dev->netdev_ops;
	ASSERT_RTNL();

	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);

	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(). */

	dev_deactivate(dev);

	/*
	 *	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 (ops->ndo_stop)
		ops->ndo_stop(dev);

	/*
	 *	Device is now down.
	 */

	dev->flags &= ~IFF_UP;

	/*
	 * Tell people we are down
	 */
	call_netdevice_notifiers(NETDEV_DOWN, dev);

	/*
	 *	Shutdown NET_DMA
	 */
	net_dmaengine_put();

	return 0;
}
EXPORT_SYMBOL(dev_close);


/**
 *	dev_disable_lro - disable Large Receive Offload on a device
 *	@dev: device
 *
 *	Disable Large Receive Offload (LRO) on a net device.  Must be
 *	called under RTNL.  This is needed if received packets may be
 *	forwarded to another interface.
 */
void dev_disable_lro(struct net_device *dev)
{
	if (dev->ethtool_ops && dev->ethtool_ops->get_flags &&
	    dev->ethtool_ops->set_flags) {
		u32 flags = dev->ethtool_ops->get_flags(dev);
		if (flags & ETH_FLAG_LRO) {
			flags &= ~ETH_FLAG_LRO;
			dev->ethtool_ops->set_flags(dev, flags);
		}
	}
	WARN_ON(dev->features & NETIF_F_LRO);
}
EXPORT_SYMBOL(dev_disable_lro);


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;
}
EXPORT_SYMBOL(register_netdevice_notifier);

/**
 *	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;
}
EXPORT_SYMBOL(unregister_netdevice_notifier);

/**
 *	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);
}
EXPORT_SYMBOL(net_enable_timestamp);

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

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;

#ifdef CONFIG_NET_CLS_ACT
	if (!(skb->tstamp.tv64 && (G_TC_FROM(skb->tc_verd) & AT_INGRESS)))
		net_timestamp(skb);
#else
	net_timestamp(skb);
#endif

	rcu_read_lock();
	list_for_each_entry_rcu(ptype, &ptype_all, list) {
		/* Never send packets back to the socket
		 * they originated from - MvS (miquels@drinkel.ow.org)
		 */
		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();
}


static inline void __netif_reschedule(struct Qdisc *q)
{
	struct softnet_data *sd;
	unsigned long flags;

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

void __netif_schedule(struct Qdisc *q)
{
	if (!test_and_set_bit(__QDISC_STATE_SCHED, &q->state))
		__netif_reschedule(q);
}
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_tx_stop_all_queues(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_tx_wake_all_queues(dev);
		__netdev_watchdog_up(dev);
	}
}
EXPORT_SYMBOL(netif_device_attach);

static bool can_checksum_protocol(unsigned long features, __be16 protocol)
{
	return ((features & NETIF_F_GEN_CSUM) ||
		((features & NETIF_F_IP_CSUM) &&
		 protocol == htons(ETH_P_IP)) ||
		((features & NETIF_F_IPV6_CSUM) &&
		 protocol == htons(ETH_P_IPV6)) ||
		((features & NETIF_F_FCOE_CRC) &&
		 protocol == htons(ETH_P_FCOE)));
}

static bool dev_can_checksum(struct net_device *dev, struct sk_buff *skb)
{
	if (can_checksum_protocol(dev->features, skb->protocol))
		return true;

	if (skb->protocol == htons(ETH_P_8021Q)) {
		struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
		if (can_checksum_protocol(dev->features & dev->vlan_features,
					  veh->h_vlan_encapsulated_proto))
			return true;
	}

	return false;
}

/*
 * 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;
}
EXPORT_SYMBOL(skb_checksum_help);

/**
 *	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;

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

	if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) {
		struct net_device *dev = skb->dev;
		struct ethtool_drvinfo info = {};

		if (dev && dev->ethtool_ops && dev->ethtool_ops->get_drvinfo)
			dev->ethtool_ops->get_drvinfo(dev, &info);

		WARN(1, "%s: caps=(0x%lx, 0x%lx) len=%d data_len=%d "
			"ip_summed=%d",
		     info.driver, dev ? dev->features : 0L,
		     skb->sk ? skb->sk->sk_route_caps : 0L,
		     skb->len, skb->data_len, skb->ip_summed);

		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) & PTYPE_HASH_MASK], 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 (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,
			struct netdev_queue *txq)
{
	const struct net_device_ops *ops = dev->netdev_ops;
	int rc;

	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;
		}

		/*
		 * If device doesnt need skb->dst, release it right now while
		 * its hot in this cpu cache
		 */
		if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
			skb_dst_drop(skb);

		rc = ops->ndo_start_xmit(skb, dev);
		if (rc == NETDEV_TX_OK)
			txq_trans_update(txq);
		/*
		 * TODO: if skb_orphan() was called by
		 * dev->hard_start_xmit() (for example, the unmodified
		 * igb driver does that; bnx2 doesn't), then
		 * skb_tx_software_timestamp() will be unable to send
		 * back the time stamp.
		 *
		 * How can this be prevented? Always create another
		 * reference to the socket before calling
		 * dev->hard_start_xmit()? Prevent that skb_orphan()
		 * does anything in dev->hard_start_xmit() by clearing
		 * the skb destructor before the call and restoring it
		 * afterwards, then doing the skb_orphan() ourselves?
		 */
		return rc;
	}

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

		skb->next = nskb->next;
		nskb->next = NULL;
		rc = ops->ndo_start_xmit(nskb, dev);
		if (unlikely(rc != NETDEV_TX_OK)) {
			nskb->next = skb->next;
			skb->next = nskb;
			return rc;
		}
		txq_trans_update(txq);
		if (unlikely(netif_tx_queue_stopped(txq) && skb->next))
			return NETDEV_TX_BUSY;
	} while (skb->next);

	skb->destructor = DEV_GSO_CB(skb)->destructor;

out_kfree_skb:
	kfree_skb(skb);
	return NETDEV_TX_OK;
}

static u32 skb_tx_hashrnd;

u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb)
{
	u32 hash;

	if (skb_rx_queue_recorded(skb)) {
		hash = skb_get_rx_queue(skb);
		while (unlikely(hash >= dev->real_num_tx_queues))
			hash -= dev->real_num_tx_queues;
		return hash;
	}

	if (skb->sk && skb->sk->sk_hash)
		hash = skb->sk->sk_hash;
	else
		hash = skb->protocol;

	hash = jhash_1word(hash, skb_tx_hashrnd);

	return (u16) (((u64) hash * dev->real_num_tx_queues) >> 32);
}
EXPORT_SYMBOL(skb_tx_hash);

static struct netdev_queue *dev_pick_tx(struct net_device *dev,
					struct sk_buff *skb)
{
	const struct net_device_ops *ops = dev->netdev_ops;
	u16 queue_index = 0;

	if (ops->ndo_select_queue)
		queue_index = ops->ndo_select_queue(dev, skb);
	else if (dev->real_num_tx_queues > 1)
		queue_index = skb_tx_hash(dev, skb);

	skb_set_queue_mapping(skb, queue_index);
	return netdev_get_tx_queue(dev, queue_index);
}

static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
				 struct net_device *dev,
				 struct netdev_queue *txq)
{
	spinlock_t *root_lock = qdisc_lock(q);
	int rc;

	spin_lock(root_lock);
	if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) {
		kfree_skb(skb);
		rc = NET_XMIT_DROP;
	} else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) &&
		   !test_and_set_bit(__QDISC_STATE_RUNNING, &q->state)) {
		/*
		 * This is a work-conserving queue; there are no old skbs
		 * waiting to be sent out; and the qdisc is not running -
		 * xmit the skb directly.
		 */
		__qdisc_update_bstats(q, skb->len);
		if (sch_direct_xmit(skb, q, dev, txq, root_lock))
			__qdisc_run(q);
		else
			clear_bit(__QDISC_STATE_RUNNING, &q->state);

		rc = NET_XMIT_SUCCESS;
	} else {
		rc = qdisc_enqueue_root(skb, q);
		qdisc_run(q);
	}
	spin_unlock(root_lock);

	return rc;
}

/**
 *	dev_queue_xmit - transmit a buffer
 *	@skb: buffer to transmit
 *
 *	Queue a buffer for transmission to a network device. The caller must
 *	have set the device and priority and built the buffer before calling
 *	this function. The function can be called from an interrupt.
 *
 *	A negative errno code is returned on a failure. A success does not
 *	guarantee the frame will be transmitted as it may be dropped due
 *	to congestion or traffic shaping.
 *
 * -----------------------------------------------------------------------------------
 *      I notice this method can also return errors from the queue disciplines,
 *      including NET_XMIT_DROP, which is a positive value.  So, errors can also
 *      be positive.
 *
 *      Regardless of the return value, the skb is consumed, so it is currently
 *      difficult to retry a send to this method.  (You can bump the ref count
 *      before sending to hold a reference for retry if you are careful.)
 *
 *      When calling this method, interrupts MUST be enabled.  This is because
 *      the BH enable code must have IRQs enabled so that it will not deadlock.
 *          --BLG
 */
int dev_queue_xmit(struct sk_buff *skb)
{
	struct net_device *dev = skb->dev;
	struct netdev_queue *txq;
	struct Qdisc *q;
	int rc = -ENOMEM;

	/* GSO will handle the following emulations directly. */
	if (netif_needs_gso(dev, skb))
		goto gso;

	if (skb_has_frags(skb) &&
	    !(dev->features & NETIF_F_FRAGLIST) &&
	    __skb_linearize(skb))
		goto out_kfree_skb;

	/* Fragmented skb is linearized if device does not support SG,
	 * or if at least one of fragments is in highmem and device
	 * does not support DMA from it.
	 */
	if (skb_shinfo(skb)->nr_frags &&
	    (!(dev->features & NETIF_F_SG) || illegal_highdma(dev, skb)) &&
	    __skb_linearize(skb))
		goto out_kfree_skb;

	/* If packet is not checksummed and device does not support
	 * checksumming for this protocol, complete checksumming here.
	 */
	if (skb->ip_summed == CHECKSUM_PARTIAL) {
		skb_set_transport_header(skb, skb->csum_start -
					      skb_headroom(skb));
		if (!dev_can_checksum(dev, skb) && skb_checksum_help(skb))
			goto out_kfree_skb;
	}

gso:
	/* Disable soft irqs for various locks below. Also
	 * stops preemption for RCU.
	 */
	rcu_read_lock_bh();

	txq = dev_pick_tx(dev, skb);
	q = rcu_dereference(txq->qdisc);

#ifdef CONFIG_NET_CLS_ACT
	skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_EGRESS);
#endif
	if (q->enqueue) {
		rc = __dev_xmit_skb(skb, q, dev, txq);
		goto out;
	}

	/* The device has no queue. Common case for software devices:
	   loopback, all the sorts of tunnels...

	   Really, it is unlikely that netif_tx_lock protection is necessary
	   here.  (f.e. loopback and IP tunnels are clean ignoring statistics
	   counters.)
	   However, it is possible, that they rely on protection
	   made by us here.

	   Check this and shot the lock. It is not prone from deadlocks.
	   Either shot noqueue qdisc, it is even simpler 8)
	 */
	if (dev->flags & IFF_UP) {
		int cpu = smp_processor_id(); /* ok because BHs are off */

		if (txq->xmit_lock_owner != cpu) {

			HARD_TX_LOCK(dev, txq, cpu);

			if (!netif_tx_queue_stopped(txq)) {
				rc = NET_XMIT_SUCCESS;
				if (!dev_hard_start_xmit(skb, dev, txq)) {
					HARD_TX_UNLOCK(dev, txq);
					goto out;
				}
			}
			HARD_TX_UNLOCK(dev, txq);
			if (net_ratelimit())
				printk(KERN_CRIT "Virtual device %s asks to "
				       "queue packet!\n", dev->name);
		} else {
			/* Recursion is detected! It is possible,
			 * unfortunately */
			if (net_ratelimit())
				printk(KERN_CRIT "Dead loop on virtual device "
				       "%s, fix it urgently!\n", dev->name);
		}
	}

	rc = -ENETDOWN;
	rcu_read_unlock_bh();

out_kfree_skb:
	kfree_skb(skb);
	return rc;
out:
	rcu_read_unlock_bh();
	return rc;
}
EXPORT_SYMBOL(dev_queue_xmit);


/*=======================================================================
			Receiver routines
  =======================================================================*/

int netdev_max_backlog __read_mostly = 1000;
int netdev_budget __read_mostly = 300;
int weight_p __read_mostly = 64;            /* old backlog weight */

DEFINE_PER_CPU(struct netif_rx_stats, netdev_rx_stat) = { 0, };


/**
 *	netif_rx	-	post buffer to the network code
 *	@skb: buffer to post
 *
 *	This function receives a packet from a device driver and queues it for
 *	the upper (protocol) levels to process.  It always succeeds. The buffer
 *	may be dropped during processing for congestion control or by the
 *	protocol layers.
 *
 *	return values:
 *	NET_RX_SUCCESS	(no congestion)
 *	NET_RX_DROP     (packet was dropped)
 *
 */

int netif_rx(struct sk_buff *skb)
{
	struct softnet_data *queue;
	unsigned long flags;

	/* if netpoll wants it, pretend we never saw it */