dev.c

 *
 *      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 = dev_hard_start_xmit(skb, dev, txq);
				if (dev_xmit_complete(rc)) {
					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 */
	if (netpoll_rx(skb))
		return NET_RX_DROP;

	if (!skb->tstamp.tv64)
		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:
			__skb_queue_tail(&queue->input_pkt_queue, skb);
			local_irq_restore(flags);
			return NET_RX_SUCCESS;
		}

		napi_schedule(&queue->backlog);
		goto enqueue;
	}

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

	kfree_skb(skb);
	return NET_RX_DROP;
}
EXPORT_SYMBOL(netif_rx);

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 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;

			WARN_ON(atomic_read(&skb->users));
			__kfree_skb(skb);
		}
	}

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

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

		while (head) {
			struct Qdisc *q = head;
			spinlock_t *root_lock;

			head = head->next_sched;

			root_lock = qdisc_lock(q);
			if (spin_trylock(root_lock)) {
				smp_mb__before_clear_bit();
				clear_bit(__QDISC_STATE_SCHED,
					  &q->state);
				qdisc_run(q);
				spin_unlock(root_lock);
			} else {
				if (!test_bit(__QDISC_STATE_DEACTIVATED,
					      &q->state)) {
					__netif_reschedule(q);
				} else {
					smp_mb__before_clear_bit();
					clear_bit(__QDISC_STATE_SCHED,
						  &q->state);
				}
			}
		}
	}
}

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)

#if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE)
/* This hook is defined here for ATM LANE */
int (*br_fdb_test_addr_hook)(struct net_device *dev,
			     unsigned char *addr) __read_mostly;
EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook);
#endif

/*
 * If bridge module is loaded call bridging hook.
 *  returns NULL if packet was consumed.
 */
struct sk_buff *(*br_handle_frame_hook)(struct net_bridge_port *p,
					struct sk_buff *skb) __read_mostly;
EXPORT_SYMBOL_GPL(br_handle_frame_hook);

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

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

	if (*pt_prev) {
		*ret = deliver_skb(skb, *pt_prev, orig_dev);
		*pt_prev = NULL;
	}

	return br_handle_frame_hook(port, skb);
}
#else
#define handle_bridge(skb, pt_prev, ret, orig_dev)	(skb)
#endif

#if defined(CONFIG_MACVLAN) || defined(CONFIG_MACVLAN_MODULE)
struct sk_buff *(*macvlan_handle_frame_hook)(struct sk_buff *skb) __read_mostly;
EXPORT_SYMBOL_GPL(macvlan_handle_frame_hook);

static inline struct sk_buff *handle_macvlan(struct sk_buff *skb,
					     struct packet_type **pt_prev,
					     int *ret,
					     struct net_device *orig_dev)
{
	if (skb->dev->macvlan_port == NULL)
		return skb;

	if (*pt_prev) {
		*ret = deliver_skb(skb, *pt_prev, orig_dev);
		*pt_prev = NULL;
	}
	return macvlan_handle_frame_hook(skb);
}
#else
#define handle_macvlan(skb, pt_prev, ret, orig_dev)	(skb)
#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 net_device *dev = skb->dev;
	u32 ttl = G_TC_RTTL(skb->tc_verd);
	struct netdev_queue *rxq;
	int result = TC_ACT_OK;
	struct Qdisc *q;

	if (MAX_RED_LOOP < ttl++) {
		printk(KERN_WARNING
		       "Redir loop detected Dropping packet (%d->%d)\n",
		       skb->skb_iif, dev->ifindex);
		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);

	rxq = &dev->rx_queue;

	q = rxq->qdisc;
	if (q != &noop_qdisc) {
		spin_lock(qdisc_lock(q));
		if (likely(!test_bit(__QDISC_STATE_DEACTIVATED, &q->state)))
			result = qdisc_enqueue_root(skb, q);
		spin_unlock(qdisc_lock(q));
	}

	return result;
}

static inline struct sk_buff *handle_ing(struct sk_buff *skb,
					 struct packet_type **pt_prev,
					 int *ret, struct net_device *orig_dev)
{
	if (skb->dev->rx_queue.qdisc == &noop_qdisc)
		goto out;

	if (*pt_prev) {
		*ret = deliver_skb(skb, *pt_prev, orig_dev);
		*pt_prev = NULL;
	} else {
		/* Huh? Why does turning on AF_PACKET affect this? */
		skb->tc_verd = SET_TC_OK2MUNGE(skb->tc_verd);
	}

	switch (ing_filter(skb)) {
	case TC_ACT_SHOT:
	case TC_ACT_STOLEN:
		kfree_skb(skb);
		return NULL;
	}

out:
	skb->tc_verd = 0;
	return skb;
}
#endif

/*
 * 	netif_nit_deliver - deliver received packets to network taps
 * 	@skb: buffer
 *
 * 	This function is used to deliver incoming packets to network
 * 	taps. It should be used when the normal netif_receive_skb path
 * 	is bypassed, for example because of VLAN acceleration.
 */
void netif_nit_deliver(struct sk_buff *skb)
{
	struct packet_type *ptype;

	if (list_empty(&ptype_all))
		return;

	skb_reset_network_header(skb);
	skb_reset_transport_header(skb);
	skb->mac_len = skb->network_header - skb->mac_header;

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

/**
 *	netif_receive_skb - process receive buffer from network
 *	@skb: buffer to process
 *
 *	netif_receive_skb() is the main receive data processing function.
 *	It always succeeds. The buffer may be dropped during processing
 *	for congestion control or by the protocol layers.
 *
 *	This function may only be called from softirq context and interrupts
 *	should be enabled.
 *
 *	Return values (usually ignored):
 *	NET_RX_SUCCESS: no congestion
 *	NET_RX_DROP: packet was dropped
 */
int netif_receive_skb(struct sk_buff *skb)
{
	struct packet_type *ptype, *pt_prev;
	struct net_device *orig_dev;
	struct net_device *null_or_orig;
	int ret = NET_RX_DROP;
	__be16 type;

	if (!skb->tstamp.tv64)
		net_timestamp(skb);

	if (vlan_tx_tag_present(skb) && vlan_hwaccel_do_receive(skb))
		return NET_RX_SUCCESS;

	/* if we've gotten here through NAPI, check netpoll */
	if (netpoll_receive_skb(skb))
		return NET_RX_DROP;

	if (!skb->skb_iif)
		skb->skb_iif = skb->dev->ifindex;

	null_or_orig = NULL;
	orig_dev = skb->dev;
	if (orig_dev->master) {
		if (skb_bond_should_drop(skb))
			null_or_orig = orig_dev; /* deliver only exact match */
		else
			skb->dev = orig_dev->master;
	}

	__get_cpu_var(netdev_rx_stat).total++;

	skb_reset_network_header(skb);
	skb_reset_transport_header(skb);
	skb->mac_len = skb->network_header - skb->mac_header;

	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 == null_or_orig || ptype->dev == skb->dev ||
		    ptype->dev == orig_dev) {
			if (pt_prev)
				ret = deliver_skb(skb, pt_prev, orig_dev);
			pt_prev = ptype;
		}
	}

#ifdef CONFIG_NET_CLS_ACT
	skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
	if (!skb)
		goto out;
ncls:
#endif

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

	type = skb->protocol;
	list_for_each_entry_rcu(ptype,
			&ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) {
		if (ptype->type == type &&
		    (ptype->dev == null_or_orig || ptype->dev == skb->dev ||
		     ptype->dev == orig_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;
}
EXPORT_SYMBOL(netif_receive_skb);

/* Network device is going away, flush any packets still pending  */
static void flush_backlog(void *arg)
{
	struct net_device *dev = arg;
	struct softnet_data *queue = &__get_cpu_var(softnet_data);
	struct sk_buff *skb, *tmp;

	skb_queue_walk_safe(&queue->input_pkt_queue, skb, tmp)
		if (skb->dev == dev) {
			__skb_unlink(skb, &queue->input_pkt_queue);
			kfree_skb(skb);
		}
}

static int napi_gro_complete(struct sk_buff *skb)
{
	struct packet_type *ptype;
	__be16 type = skb->protocol;
	struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK];
	int err = -ENOENT;

	if (NAPI_GRO_CB(skb)->count == 1) {
		skb_shinfo(skb)->gso_size = 0;
		goto out;
	}

	rcu_read_lock();
	list_for_each_entry_rcu(ptype, head, list) {
		if (ptype->type != type || ptype->dev || !ptype->gro_complete)
			continue;

		err = ptype->gro_complete(skb);
		break;
	}
	rcu_read_unlock();

	if (err) {
		WARN_ON(&ptype->list == head);
		kfree_skb(skb);
		return NET_RX_SUCCESS;
	}

out:
	return netif_receive_skb(skb);
}

void napi_gro_flush(struct napi_struct *napi)
{
	struct sk_buff *skb, *next;

	for (skb = napi->gro_list; skb; skb = next) {
		next = skb->next;
		skb->next = NULL;
		napi_gro_complete(skb);
	}

	napi->gro_count = 0;
	napi->gro_list = NULL;
}
EXPORT_SYMBOL(napi_gro_flush);

enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
	struct sk_buff **pp = NULL;
	struct packet_type *ptype;
	__be16 type = skb->protocol;
	struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK];
	int same_flow;
	int mac_len;
	enum gro_result ret;

	if (!(skb->dev->features & NETIF_F_GRO))
		goto normal;

	if (skb_is_gso(skb) || skb_has_frags(skb))
		goto normal;

	rcu_read_lock();
	list_for_each_entry_rcu(ptype, head, list) {
		if (ptype->type != type || ptype->dev || !ptype->gro_receive)
			continue;

		skb_set_network_header(skb, skb_gro_offset(skb));
		mac_len = skb->network_header - skb->mac_header;
		skb->mac_len = mac_len;
		NAPI_GRO_CB(skb)->same_flow = 0;
		NAPI_GRO_CB(skb)->flush = 0;
		NAPI_GRO_CB(skb)->free = 0;

		pp = ptype->gro_receive(&napi->gro_list, skb);
		break;
	}
	rcu_read_unlock();

	if (&ptype->list == head)
		goto normal;

	same_flow = NAPI_GRO_CB(skb)->same_flow;
	ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED;

	if (pp) {
		struct sk_buff *nskb = *pp;

		*pp = nskb->next;
		nskb->next = NULL;
		napi_gro_complete(nskb);
		napi->gro_count--;
	}

	if (same_flow)
		goto ok;

	if (NAPI_GRO_CB(skb)->flush || napi->gro_count >= MAX_GRO_SKBS)
		goto normal;

	napi->gro_count++;
	NAPI_GRO_CB(skb)->count = 1;
	skb_shinfo(skb)->gso_size = skb_gro_len(skb);
	skb->next = napi->gro_list;
	napi->gro_list = skb;
	ret = GRO_HELD;

pull:
	if (skb_headlen(skb) < skb_gro_offset(skb)) {
		int grow = skb_gro_offset(skb) - skb_headlen(skb);

		BUG_ON(skb->end - skb->tail < grow);

		memcpy(skb_tail_pointer(skb), NAPI_GRO_CB(skb)->frag0, grow);

		skb->tail += grow;
		skb->data_len -= grow;

		skb_shinfo(skb)->frags[0].page_offset += grow;
		skb_shinfo(skb)->frags[0].size -= grow;

		if (unlikely(!skb_shinfo(skb)->frags[0].size)) {
			put_page(skb_shinfo(skb)->frags[0].page);
			memmove(skb_shinfo(skb)->frags,
				skb_shinfo(skb)->frags + 1,
				--skb_shinfo(skb)->nr_frags);
		}
	}

ok:
	return ret;

normal:
	ret = GRO_NORMAL;
	goto pull;
}
EXPORT_SYMBOL(dev_gro_receive);

static gro_result_t
__napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
	struct sk_buff *p;

	if (netpoll_rx_on(skb))
		return GRO_NORMAL;

	for (p = napi->gro_list; p; p = p->next) {
		NAPI_GRO_CB(p)->same_flow =
			(p->dev == skb->dev) &&
			!compare_ether_header(skb_mac_header(p),
					      skb_gro_mac_header(skb));
		NAPI_GRO_CB(p)->flush = 0;
	}

	return dev_gro_receive(napi, skb);
}

gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
{
	switch (ret) {
	case GRO_NORMAL:
		if (netif_receive_skb(skb))
			ret = GRO_DROP;
		break;

	case GRO_DROP:
	case GRO_MERGED_FREE:
		kfree_skb(skb);
		break;

	case GRO_HELD:
	case GRO_MERGED:
		break;
	}

	return ret;
}
EXPORT_SYMBOL(napi_skb_finish);

void skb_gro_reset_offset(struct sk_buff *skb)
{
	NAPI_GRO_CB(skb)->data_offset = 0;
	NAPI_GRO_CB(skb)->frag0 = NULL;
	NAPI_GRO_CB(skb)->frag0_len = 0;

	if (skb->mac_header == skb->tail &&
	    !PageHighMem(skb_shinfo(skb)->frags[0].page)) {
		NAPI_GRO_CB(skb)->frag0 =
			page_address(skb_shinfo(skb)->frags[0].page) +
			skb_shinfo(skb)->frags[0].page_offset;
		NAPI_GRO_CB(skb)->frag0_len = skb_shinfo(skb)->frags[0].size;
	}
}
EXPORT_SYMBOL(skb_gro_reset_offset);

gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
	skb_gro_reset_offset(skb);

	return napi_skb_finish(__napi_gro_receive(napi, skb), skb);
}
EXPORT_SYMBOL(napi_gro_receive);

void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
{
	__skb_pull(skb, skb_headlen(skb));
	skb_reserve(skb, NET_IP_ALIGN - skb_headroom(skb));

	napi->skb = skb;
}
EXPORT_SYMBOL(napi_reuse_skb);

struct sk_buff *napi_get_frags(struct napi_struct *napi)
{
	struct sk_buff *skb = napi->skb;

	if (!skb) {
		skb = netdev_alloc_skb_ip_align(napi->dev, GRO_MAX_HEAD);
		if (skb)
			napi->skb = skb;
	}
	return skb;
}
EXPORT_SYMBOL(napi_get_frags);

gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb,
			       gro_result_t ret)
{
	switch (ret) {
	case GRO_NORMAL:
	case GRO_HELD:
		skb->protocol = eth_type_trans(skb, napi->dev);

		if (ret == GRO_HELD)
			skb_gro_pull(skb, -ETH_HLEN);
		else if (netif_receive_skb(skb))
			ret = GRO_DROP;
		break;

	case GRO_DROP:
	case GRO_MERGED_FREE:
		napi_reuse_skb(napi, skb);
		break;

	case GRO_MERGED:
		break;
	}

	return ret;
}
EXPORT_SYMBOL(napi_frags_finish);

struct sk_buff *napi_frags_skb(struct napi_struct *napi)
{
	struct sk_buff *skb = napi->skb;
	struct ethhdr *eth;
	unsigned int hlen;
	unsigned int off;

	napi->skb = NULL;

	skb_reset_mac_header(skb);
	skb_gro_reset_offset(skb);

	off = skb_gro_offset(skb);
	hlen = off + sizeof(*eth);
	eth = skb_gro_header_fast(skb, off);
	if (skb_gro_header_hard(skb, hlen)) {
		eth = skb_gro_header_slow(skb, hlen, off);
		if (unlikely(!eth)) {
			napi_reuse_skb(napi, skb);
			skb = NULL;
			goto out;
		}
	}

	skb_gro_pull(skb, sizeof(*eth));

	/*
	 * This works because the only protocols we care about don't require
	 * special handling.  We'll fix it up properly at the end.
	 */
	skb->protocol = eth->h_proto;

out:
	return skb;
}
EXPORT_SYMBOL(napi_frags_skb);

gro_result_t napi_gro_frags(struct napi_struct *napi)
{
	struct sk_buff *skb = napi_frags_skb(napi);

	if (!skb)
		return GRO_DROP;

	return napi_frags_finish(napi, skb, __napi_gro_receive(napi, skb));
}
EXPORT_SYMBOL(napi_gro_frags);

static int process_backlog(struct napi_struct *napi, int quota)
{
	int work = 0;
	struct softnet_data *queue = &__get_cpu_var(softnet_data);
	unsigned long start_time = jiffies;

	napi->weight = weight_p;
	do {
		struct sk_buff *skb;

		local_irq_disable();
		skb = __skb_dequeue(&queue->input_pkt_queue);
		if (!skb) {
			__napi_complete(napi);
			local_irq_enable();
			break;
		}
		local_irq_enable();

		netif_receive_skb(skb);
	} while (++work < quota && jiffies == start_time);

	return work;
}

/**
 * __napi_schedule - schedule for receive
 * @n: entry to schedule
 *
 * The entry's receive function will be scheduled to run
 */
void __napi_schedule(struct napi_struct *n)
{
	unsigned long flags;

	local_irq_save(flags);
	list_add_tail(&n->poll_list, &__get_cpu_var(softnet_data).poll_list);
	__raise_softirq_irqoff(NET_RX_SOFTIRQ);
	local_irq_restore(flags);
}
EXPORT_SYMBOL(__napi_schedule);

void __napi_complete(struct napi_struct *n)
{
	BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state));
	BUG_ON(n->gro_list);

	list_del(&n->poll_list);
	smp_mb__before_clear_bit();
	clear_bit(NAPI_STATE_SCHED, &n->state);
}
EXPORT_SYMBOL(__napi_complete);

void napi_complete(struct napi_struct *n)
{
	unsigned long flags;

	/*
	 * don't let napi dequeue from the cpu poll list
	 * just in case its running on a different cpu
	 */
	if (unlikely(test_bit(NAPI_STATE_NPSVC, &n->state)))
		return;

	napi_gro_flush(n);
	local_irq_save(flags);
	__napi_complete(n);
	local_irq_restore(flags);
}
EXPORT_SYMBOL(napi_complete);

void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
		    int (*poll)(struct napi_struct *, int), int weight)
{
	INIT_LIST_HEAD(&napi->poll_list);
	napi->gro_count = 0;
	napi->gro_list = NULL;
	napi->skb = NULL;
	napi->poll = poll;
	napi->weight = weight;
	list_add(&napi->dev_list, &dev->napi_list);
	napi->dev = dev;
#ifdef CONFIG_NETPOLL
	spin_lock_init(&napi->poll_lock);
	napi->poll_owner = -1;
#endif
	set_bit(NAPI_STATE_SCHED, &napi->state);
}
EXPORT_SYMBOL(netif_napi_add);

void netif_napi_del(struct napi_struct *napi)
{
	struct sk_buff *skb, *next;

	list_del_init(&napi->dev_list);
	napi_free_frags(napi);

	for (skb = napi->gro_list; skb; skb = next) {
		next = skb->next;
		skb->next = NULL;
		kfree_skb(skb);
	}

	napi->gro_list = NULL;
	napi->gro_count = 0;
}
EXPORT_SYMBOL(netif_napi_del);


static void net_rx_action(struct softirq_action *h)
{
	struct list_head *list = &__get_cpu_var(softnet_data).poll_list;
	unsigned long time_limit = jiffies + 2;
	int budget = netdev_budget;
	void *have;

	local_irq_disable();

	while (!list_empty(list)) {
		struct napi_struct *n;
		int work, weight;

		/* If softirq window is exhuasted then punt.
		 * Allow this to run for 2 jiffies since which will allow
		 * an average latency of 1.5/HZ.
		 */
		if (unlikely(budget <= 0 || time_after(jiffies, time_limit)))
			goto softnet_break;

		local_irq_enable();

		/* Even though interrupts have been re-enabled, this
		 * access is safe because interrupts can only add new
		 * entries to the tail of this list, and only ->poll()
		 * calls can remove this head entry from the list.
		 */
		n = list_entry(list->next, struct napi_struct, poll_list);

		have = netpoll_poll_lock(n);

		weight = n->weight;

		/* This NAPI_STATE_SCHED test is for avoiding a race
		 * with netpoll's poll_napi().  Only the entity which
		 * obtains the lock and sees NAPI_STATE_SCHED set will
		 * actually make the ->poll() call.  Therefore we avoid
		 * accidently calling ->poll() when NAPI is not scheduled.
		 */
		work = 0;
		if (test_bit(NAPI_STATE_SCHED, &n->state)) {
			work = n->poll(n, weight);
			trace_napi_poll(n);
		}

		WARN_ON_ONCE(work > weight);

		budget -= work;

		local_irq_disable();