dev.c

/**
 *	call_netdevice_notifiers - call all network notifier blocks
 *      @val: value passed unmodified to notifier function
 *      @v:   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, void *v)
{
	return raw_notifier_call_chain(&netdev_chain, val, v);
}

/* 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);
}

void __net_timestamp(struct sk_buff *skb)
{
	struct timeval tv;

	do_gettimeofday(&tv);
	skb_set_timestamp(skb, &tv);
}
EXPORT_SYMBOL(__net_timestamp);

static inline void net_timestamp(struct sk_buff *skb)
{
	if (atomic_read(&netstamp_needed))
		__net_timestamp(skb);
	else {
		skb->tstamp.off_sec = 0;
		skb->tstamp.off_usec = 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 (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.
			 */
			skb2->mac.raw = skb2->data;

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

			skb2->h.raw = skb2->nh.raw;
			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 __netif_rx_schedule(struct net_device *dev)
{
	unsigned long flags;

	local_irq_save(flags);
	dev_hold(dev);
	list_add_tail(&dev->poll_list, &__get_cpu_var(softnet_data).poll_list);
	if (dev->quota < 0)
		dev->quota += dev->weight;
	else
		dev->quota = dev->weight;
	__raise_softirq_irqoff(NET_RX_SOFTIRQ);
	local_irq_restore(flags);
}
EXPORT_SYMBOL(__netif_rx_schedule);

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);


/* Hot-plugging. */
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);

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, int inward)
{
	unsigned int csum;
	int ret = 0, offset = skb->h.raw - skb->data;

	if (inward) {
		skb->ip_summed = CHECKSUM_NONE;
		goto out;
	}

	if (skb_cloned(skb)) {
		ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
		if (ret)
			goto out;
	}

	BUG_ON(offset > (int)skb->len);
	csum = skb_checksum(skb, offset, skb->len-offset, 0);

	offset = skb->tail - skb->h.raw;
	BUG_ON(offset <= 0);
	BUG_ON(skb->csum + 2 > offset);

	*(u16*)(skb->h.raw + skb->csum) = csum_fold(csum);
	skb->ip_summed = CHECKSUM_NONE;
out:	
	return ret;
}

/**
 *	skb_gso_segment - Perform segmentation on skb.
 *	@skb: buffer to segment
 *	@sg: whether scatter-gather is supported on the target.
 *
 *	This function segments the given skb and returns a list of segments.
 */
struct sk_buff *skb_gso_segment(struct sk_buff *skb, int sg)
{
	struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
	struct packet_type *ptype;
	int type = skb->protocol;

	BUG_ON(skb_shinfo(skb)->frag_list);
	BUG_ON(skb->ip_summed != CHECKSUM_HW);

	skb->mac.raw = skb->data;
	skb->mac_len = skb->nh.raw - skb->data;
	__skb_pull(skb, skb->mac_len);

	rcu_read_lock();
	list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type) & 15], list) {
		if (ptype->type == type && !ptype->dev && ptype->gso_segment) {
			segs = ptype->gso_segment(skb, sg);
			break;
		}
	}
	rcu_read_unlock();

	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

#ifdef CONFIG_HIGHMEM
/* 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)
{
	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;

	return 0;
}
#else
#define illegal_highdma(dev, skb)	(0)
#endif

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;

	segs = skb_gso_segment(skb, dev->features & NETIF_F_SG &&
				    !illegal_highdma(dev, skb));
	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 (netdev_nit)
			dev_queue_xmit_nit(skb, dev);

		if (!netif_needs_gso(dev, skb))
			return dev->hard_start_xmit(skb, dev);

		if (unlikely(dev_gso_segment(skb)))
			goto out_kfree_skb;
	}

	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)) {
			skb->next = nskb;
			return rc;
		}
	} while (skb->next);
	
	skb->destructor = DEV_GSO_CB(skb)->destructor;

out_kfree_skb:
	kfree_skb(skb);
	return 0;
}

#define HARD_TX_LOCK(dev, cpu) {			\
	if ((dev->features & NETIF_F_LLTX) == 0) {	\
		netif_tx_lock(dev);			\
	}						\
}

#define HARD_TX_UNLOCK(dev) {				\
	if ((dev->features & NETIF_F_LLTX) == 0) {	\
		netif_tx_unlock(dev);			\
	}						\
}

/**
 *	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 Qdisc *q;
	int rc = -ENOMEM;

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

	if (skb_shinfo(skb)->frag_list &&
	    !(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_HW &&
	    (!(dev->features & NETIF_F_GEN_CSUM) &&
	     (!(dev->features & NETIF_F_IP_CSUM) ||
	      skb->protocol != htons(ETH_P_IP))))
	      	if (skb_checksum_help(skb, 0))
	      		goto out_kfree_skb;

gso:
	spin_lock_prefetch(&dev->queue_lock);

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

	/* Updates of qdisc are serialized by queue_lock. 
	 * The struct Qdisc which is pointed to by qdisc is now a 
	 * rcu structure - it may be accessed without acquiring 
	 * a lock (but the structure may be stale.) The freeing of the
	 * qdisc will be deferred until it's known that there are no 
	 * more references to it.
	 * 
	 * If the qdisc has an enqueue function, we still need to 
	 * hold the queue_lock before calling it, since queue_lock
	 * also serializes access to the device queue.
	 */

	q = rcu_dereference(dev->qdisc);
#ifdef CONFIG_NET_CLS_ACT
	skb->tc_verd = SET_TC_AT(skb->tc_verd,AT_EGRESS);
#endif
	if (q->enqueue) {
		/* Grab device queue */
		spin_lock(&dev->queue_lock);

		rc = q->enqueue(skb, q);

		qdisc_run(dev);

		spin_unlock(&dev->queue_lock);
		rc = rc == NET_XMIT_BYPASS ? NET_XMIT_SUCCESS : rc;
		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 (dev->xmit_lock_owner != cpu) {

			HARD_TX_LOCK(dev, cpu);

			if (!netif_queue_stopped(dev)) {
				rc = 0;
				if (!dev_hard_start_xmit(skb, dev)) {
					HARD_TX_UNLOCK(dev);
					goto out;
				}
			}
			HARD_TX_UNLOCK(dev);
			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;
}


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

int netdev_max_backlog = 1000;
int netdev_budget = 300;
int weight_p = 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_CN_LOW   (low congestion)
 *	NET_RX_CN_MOD   (moderate congestion)
 *	NET_RX_CN_HIGH  (high 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 */
	if (netpoll_rx(skb))
		return NET_RX_DROP;

	if (!skb->tstamp.off_sec)
		net_timestamp(skb);

	/*
	 * The code is rearranged so that the path is the most
	 * short when CPU is congested, but is still operating.
	 */
	local_irq_save(flags);
	queue = &__get_cpu_var(softnet_data);

	__get_cpu_var(netdev_rx_stat).total++;
	if (queue->input_pkt_queue.qlen <= netdev_max_backlog) {
		if (queue->input_pkt_queue.qlen) {
enqueue:
			dev_hold(skb->dev);
			__skb_queue_tail(&queue->input_pkt_queue, skb);
			local_irq_restore(flags);
			return NET_RX_SUCCESS;
		}

		netif_rx_schedule(&queue->backlog_dev);
		goto enqueue;
	}

	__get_cpu_var(netdev_rx_stat).dropped++;
	local_irq_restore(flags);

	kfree_skb(skb);
	return NET_RX_DROP;
}

int netif_rx_ni(struct sk_buff *skb)
{
	int err;

	preempt_disable();
	err = netif_rx(skb);
	if (local_softirq_pending())
		do_softirq();
	preempt_enable();

	return err;
}

EXPORT_SYMBOL(netif_rx_ni);

static inline struct net_device *skb_bond(struct sk_buff *skb)
{
	struct net_device *dev = skb->dev;

	if (dev->master) {
		/*
		 * On bonding slaves other than the currently active
		 * slave, suppress duplicates except for 802.3ad
		 * ETH_P_SLOW and alb non-mcast/bcast.
		 */
		if (dev->priv_flags & IFF_SLAVE_INACTIVE) {
			if (dev->master->priv_flags & IFF_MASTER_ALB) {
				if (skb->pkt_type != PACKET_BROADCAST &&
				    skb->pkt_type != PACKET_MULTICAST)
					goto keep;
			}

			if (dev->master->priv_flags & IFF_MASTER_8023AD &&
			    skb->protocol == __constant_htons(ETH_P_SLOW))
				goto keep;
		
			kfree_skb(skb);
			return NULL;
		}
keep:
		skb->dev = dev->master;
	}

	return dev;
}

static void net_tx_action(struct softirq_action *h)
{
	struct softnet_data *sd = &__get_cpu_var(softnet_data);

	if (sd->completion_queue) {
		struct sk_buff *clist;

		local_irq_disable();
		clist = sd->completion_queue;
		sd->completion_queue = NULL;
		local_irq_enable();

		while (clist) {
			struct sk_buff *skb = clist;
			clist = clist->next;

			BUG_TRAP(!atomic_read(&skb->users));
			__kfree_skb(skb);
		}
	}

	if (sd->output_queue) {
		struct net_device *head;

		local_irq_disable();
		head = sd->output_queue;
		sd->output_queue = NULL;
		local_irq_enable();

		while (head) {
			struct net_device *dev = head;
			head = head->next_sched;

			smp_mb__before_clear_bit();
			clear_bit(__LINK_STATE_SCHED, &dev->state);

			if (spin_trylock(&dev->queue_lock)) {
				qdisc_run(dev);
				spin_unlock(&dev->queue_lock);
			} else {
				netif_schedule(dev);
			}
		}
	}
}

static __inline__ int deliver_skb(struct sk_buff *skb,
				  struct packet_type *pt_prev,
				  struct net_device *orig_dev)
{
	atomic_inc(&skb->users);
	return pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
}

#if defined(CONFIG_BRIDGE) || defined (CONFIG_BRIDGE_MODULE)
int (*br_handle_frame_hook)(struct net_bridge_port *p, struct sk_buff **pskb);
struct net_bridge;
struct net_bridge_fdb_entry *(*br_fdb_get_hook)(struct net_bridge *br,
						unsigned char *addr);
void (*br_fdb_put_hook)(struct net_bridge_fdb_entry *ent);

static __inline__ int handle_bridge(struct sk_buff **pskb,
				    struct packet_type **pt_prev, int *ret,
				    struct net_device *orig_dev)
{
	struct net_bridge_port *port;

	if ((*pskb)->pkt_type == PACKET_LOOPBACK ||
	    (port = rcu_dereference((*pskb)->dev->br_port)) == NULL)
		return 0;

	if (*pt_prev) {
		*ret = deliver_skb(*pskb, *pt_prev, orig_dev);
		*pt_prev = NULL;
	} 
	
	return br_handle_frame_hook(port, pskb);
}
#else
#define handle_bridge(skb, pt_prev, ret, orig_dev)	(0)
#endif

#ifdef CONFIG_NET_CLS_ACT
/* TODO: Maybe we should just force sch_ingress to be compiled in
 * when CONFIG_NET_CLS_ACT is? otherwise some useless instructions
 * a compare and 2 stores extra right now if we dont have it on
 * but have CONFIG_NET_CLS_ACT
 * NOTE: This doesnt stop any functionality; if you dont have 
 * the ingress scheduler, you just cant add policies on ingress.
 *
 */
static int ing_filter(struct sk_buff *skb) 
{
	struct Qdisc *q;
	struct net_device *dev = skb->dev;
	int result = TC_ACT_OK;
	
	if (dev->qdisc_ingress) {
		__u32 ttl = (__u32) G_TC_RTTL(skb->tc_verd);
		if (MAX_RED_LOOP < ttl++) {
			printk("Redir loop detected Dropping packet (%s->%s)\n",
				skb->input_dev->name, skb->dev->name);
			return TC_ACT_SHOT;
		}

		skb->tc_verd = SET_TC_RTTL(skb->tc_verd,ttl);

		skb->tc_verd = SET_TC_AT(skb->tc_verd,AT_INGRESS);

		spin_lock(&dev->ingress_lock);
		if ((q = dev->qdisc_ingress) != NULL)
			result = q->enqueue(skb, q);
		spin_unlock(&dev->ingress_lock);

	}

	return result;
}
#endif

int netif_receive_skb(struct sk_buff *skb)
{
	struct packet_type *ptype, *pt_prev;
	struct net_device *orig_dev;
	int ret = NET_RX_DROP;
	unsigned short type;

	/* if we've gotten here through NAPI, check netpoll */
	if (skb->dev->poll && netpoll_rx(skb))
		return NET_RX_DROP;

	if (!skb->tstamp.off_sec)
		net_timestamp(skb);

	if (!skb->input_dev)
		skb->input_dev = skb->dev;

	orig_dev = skb_bond(skb);

	if (!orig_dev)
		return NET_RX_DROP;

	__get_cpu_var(netdev_rx_stat).total++;

	skb->h.raw = skb->nh.raw = skb->data;
	skb->mac_len = skb->nh.raw - skb->mac.raw;

	pt_prev = NULL;

	rcu_read_lock();

#ifdef CONFIG_NET_CLS_ACT
	if (skb->tc_verd & TC_NCLS) {
		skb->tc_verd = CLR_TC_NCLS(skb->tc_verd);
		goto ncls;
	}
#endif

	list_for_each_entry_rcu(ptype, &ptype_all, list) {
		if (!ptype->dev || ptype->dev == skb->dev) {
			if (pt_prev) 
				ret = deliver_skb(skb, pt_prev, orig_dev);
			pt_prev = ptype;
		}
	}

#ifdef CONFIG_NET_CLS_ACT
	if (pt_prev) {
		ret = deliver_skb(skb, pt_prev, orig_dev);
		pt_prev = NULL; /* noone else should process this after*/
	} else {
		skb->tc_verd = SET_TC_OK2MUNGE(skb->tc_verd);
	}

	ret = ing_filter(skb);

	if (ret == TC_ACT_SHOT || (ret == TC_ACT_STOLEN)) {
		kfree_skb(skb);
		goto out;
	}

	skb->tc_verd = 0;
ncls:
#endif

	handle_diverter(skb);

	if (handle_bridge(&skb, &pt_prev, &ret, orig_dev))
		goto out;

	type = skb->protocol;
	list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type)&15], list) {
		if (ptype->type == type &&
		    (!ptype->dev || ptype->dev == skb->dev)) {
			if (pt_prev) 
				ret = deliver_skb(skb, pt_prev, orig_dev);
			pt_prev = ptype;
		}
	}

	if (pt_prev) {
		ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
	} else {
		kfree_skb(skb);
		/* Jamal, now you will not able to escape explaining
		 * me how you were going to use this. :-)
		 */
		ret = NET_RX_DROP;
	}

out:
	rcu_read_unlock();
	return ret;
}

static int process_backlog(struct net_device *backlog_dev, int *budget)
{
	int work = 0;
	int quota = min(backlog_dev->quota, *budget);
	struct softnet_data *queue = &__get_cpu_var(softnet_data);
	unsigned long start_time = jiffies;

	backlog_dev->weight = weight_p;
	for (;;) {
		struct sk_buff *skb;
		struct net_device *dev;

		local_irq_disable();
		skb = __skb_dequeue(&queue->input_pkt_queue);
		if (!skb)
			goto job_done;
		local_irq_enable();

		dev = skb->dev;

		netif_receive_skb(skb);

		dev_put(dev);

		work++;

		if (work >= quota || jiffies - start_time > 1)
			break;

	}

	backlog_dev->quota -= work;
	*budget -= work;
	return -1;

job_done:
	backlog_dev->quota -= work;
	*budget -= work;

	list_del(&backlog_dev->poll_list);
	smp_mb__before_clear_bit();
	netif_poll_enable(backlog_dev);

	local_irq_enable();
	return 0;
}

static void net_rx_action(struct softirq_action *h)
{
	struct softnet_data *queue = &__get_cpu_var(softnet_data);
	unsigned long start_time = jiffies;
	int budget = netdev_budget;
	void *have;

	local_irq_disable();

	while (!list_empty(&queue->poll_list)) {
		struct net_device *dev;

		if (budget <= 0 || jiffies - start_time > 1)
			goto softnet_break;

		local_irq_enable();

		dev = list_entry(queue->poll_list.next,
				 struct net_device, poll_list);
		have = netpoll_poll_lock(dev);

		if (dev->quota <= 0 || dev->poll(dev, &budget)) {
			netpoll_poll_unlock(have);
			local_irq_disable();
			list_move_tail(&dev->poll_list, &queue->poll_list);
			if (dev->quota < 0)
				dev->quota += dev->weight;
			else
				dev->quota = dev->weight;
		} else {
			netpoll_poll_unlock(have);
			dev_put(dev);
			local_irq_disable();
		}
	}
out:
#ifdef CONFIG_NET_DMA
	/*
	 * There may not be any more sk_buffs coming right now, so push
	 * any pending DMA copies to hardware
	 */
	if (net_dma_client) {
		struct dma_chan *chan;
		rcu_read_lock();
		list_for_each_entry_rcu(chan, &net_dma_client->channels, client_node)
			dma_async_memcpy_issue_pending(chan);
		rcu_read_unlock();
	}
#endif
	local_irq_enable();
	return;

softnet_break:
	__get_cpu_var(netdev_rx_stat).time_squeeze++;
	__raise_softirq_irqoff(NET_RX_SOFTIRQ);
	goto out;
}

static gifconf_func_t * gifconf_list [NPROTO];

/**
 *	register_gifconf	-	register a SIOCGIF handler
 *	@family: Address family
 *	@gifconf: Function handler
 *
 *	Register protocol dependent address dumping routines. The handler
 *	that is passed must not be freed or reused until it has been replaced
 *	by another handler.
 */
int register_gifconf(unsigned int family, gifconf_func_t * gifconf)
{
	if (family >= NPROTO)
		return -EINVAL;
	gifconf_list[family] = gifconf;
	return 0;
}


/*
 *	Map an interface index to its name (SIOCGIFNAME)
 */

/*
 *	We need this ioctl for efficient implementation of the
 *	if_indextoname() function required by the IPv6 API.  Without
 *	it, we would have to search all the interfaces to find a
 *	match.  --pb
 */

static int dev_ifname(struct ifreq __user *arg)
{
	struct net_device *dev;
	struct ifreq ifr;

	/*
	 *	Fetch the caller's info block.
	 */

	if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
		return -EFAULT;

	read_lock(&dev_base_lock);
	dev = __dev_get_by_index(ifr.ifr_ifindex);
	if (!dev) {
		read_unlock(&dev_base_lock);
		return -ENODEV;
	}

	strcpy(ifr.ifr_name, dev->name);
	read_unlock(&dev_base_lock);

	if (copy_to_user(arg, &ifr, sizeof(struct ifreq)))
		return -EFAULT;
	return 0;
}

/*
 *	Perform a SIOCGIFCONF call. This structure will change
 *	size eventually, and there is nothing I can do about it.
 *	Thus we will need a 'compatibility mode'.
 */

static int dev_ifconf(char __user *arg)
{