dev.c

			/* 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;
			}
		}

		rc = ops->ndo_start_xmit(skb, dev);
		if (rc == NETDEV_TX_OK)
			txq_trans_update(txq);
		return rc;
	}

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

		skb->next = nskb->next;
		nskb->next = NULL;

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

		rc = ops->ndo_start_xmit(nskb, dev);
		if (unlikely(rc != NETDEV_TX_OK)) {
			if (rc & ~NETDEV_TX_MASK)
				goto out_kfree_gso_skb;
			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);

out_kfree_gso_skb:
	if (likely(skb->next == NULL))
		skb->destructor = DEV_GSO_CB(skb)->destructor;
out_kfree_skb:
	kfree_skb(skb);
	return rc;
}

static u32 hashrnd __read_mostly;

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 = (__force u16) skb->protocol ^ skb->rxhash;
	hash = jhash_1word(hash, hashrnd);

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

static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index)
{
	if (unlikely(queue_index >= dev->real_num_tx_queues)) {
		if (net_ratelimit()) {
			pr_warning("%s selects TX queue %d, but "
				"real number of TX queues is %d\n",
				dev->name, queue_index, dev->real_num_tx_queues);
		}
		return 0;
	}
	return queue_index;
}

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

	if (ops->ndo_select_queue) {
		queue_index = ops->ndo_select_queue(dev, skb);
		queue_index = dev_cap_txqueue(dev, queue_index);
	} else {
		struct sock *sk = skb->sk;
		queue_index = sk_tx_queue_get(sk);
		if (queue_index < 0) {

			queue_index = 0;
			if (dev->real_num_tx_queues > 1)
				queue_index = skb_tx_hash(dev, skb);

			if (sk) {
				struct dst_entry *dst = rcu_dereference_check(sk->sk_dst_cache, 1);

				if (dst && skb_dst(skb) == dst)
					sk_tx_queue_set(sk, queue_index);
			}
		}
	}

	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);
	bool contended = qdisc_is_running(q);
	int rc;

	/*
	 * Heuristic to force contended enqueues to serialize on a
	 * separate lock before trying to get qdisc main lock.
	 * This permits __QDISC_STATE_RUNNING owner to get the lock more often
	 * and dequeue packets faster.
	 */
	if (unlikely(contended))
		spin_lock(&q->busylock);

	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) &&
		   qdisc_run_begin(q)) {
		/*
		 * 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.
		 */
		if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE))
			skb_dst_force(skb);
		__qdisc_update_bstats(q, skb->len);
		if (sch_direct_xmit(skb, q, dev, txq, root_lock)) {
			if (unlikely(contended)) {
				spin_unlock(&q->busylock);
				contended = false;
			}
			__qdisc_run(q);
		} else
			qdisc_run_end(q);

		rc = NET_XMIT_SUCCESS;
	} else {
		skb_dst_force(skb);
		rc = qdisc_enqueue_root(skb, q);
		if (qdisc_run_begin(q)) {
			if (unlikely(contended)) {
				spin_unlock(&q->busylock);
				contended = false;
			}
			__qdisc_run(q);
		}
	}
	spin_unlock(root_lock);
	if (unlikely(contended))
		spin_unlock(&q->busylock);
	return rc;
}

static DEFINE_PER_CPU(int, xmit_recursion);
#define RECURSION_LIMIT 3

/**
 *	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;

	/* 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_bh(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) {

			if (__this_cpu_read(xmit_recursion) > RECURSION_LIMIT)
				goto recursion_alert;

			HARD_TX_LOCK(dev, txq, cpu);

			if (!netif_tx_queue_stopped(txq)) {
				__this_cpu_inc(xmit_recursion);
				rc = dev_hard_start_xmit(skb, dev, txq);
				__this_cpu_dec(xmit_recursion);
				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
			 */
recursion_alert:
			if (net_ratelimit())
				printk(KERN_CRIT "Dead loop on virtual device "
				       "%s, fix it urgently!\n", dev->name);
		}
	}

	rc = -ENETDOWN;
	rcu_read_unlock_bh();

	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_tstamp_prequeue __read_mostly = 1;
int netdev_budget __read_mostly = 300;
int weight_p __read_mostly = 64;            /* old backlog weight */

/* Called with irq disabled */
static inline void ____napi_schedule(struct softnet_data *sd,
				     struct napi_struct *napi)
{
	list_add_tail(&napi->poll_list, &sd->poll_list);
	__raise_softirq_irqoff(NET_RX_SOFTIRQ);
}

/*
 * __skb_get_rxhash: calculate a flow hash based on src/dst addresses
 * and src/dst port numbers. Returns a non-zero hash number on success
 * and 0 on failure.
 */
__u32 __skb_get_rxhash(struct sk_buff *skb)
{
	int nhoff, hash = 0, poff;
	struct ipv6hdr *ip6;
	struct iphdr *ip;
	u8 ip_proto;
	u32 addr1, addr2, ihl;
	union {
		u32 v32;
		u16 v16[2];
	} ports;

	nhoff = skb_network_offset(skb);

	switch (skb->protocol) {
	case __constant_htons(ETH_P_IP):
		if (!pskb_may_pull(skb, sizeof(*ip) + nhoff))
			goto done;

		ip = (struct iphdr *) (skb->data + nhoff);
		if (ip->frag_off & htons(IP_MF | IP_OFFSET))
			ip_proto = 0;
		else
			ip_proto = ip->protocol;
		addr1 = (__force u32) ip->saddr;
		addr2 = (__force u32) ip->daddr;
		ihl = ip->ihl;
		break;
	case __constant_htons(ETH_P_IPV6):
		if (!pskb_may_pull(skb, sizeof(*ip6) + nhoff))
			goto done;

		ip6 = (struct ipv6hdr *) (skb->data + nhoff);
		ip_proto = ip6->nexthdr;
		addr1 = (__force u32) ip6->saddr.s6_addr32[3];
		addr2 = (__force u32) ip6->daddr.s6_addr32[3];
		ihl = (40 >> 2);
		break;
	default:
		goto done;
	}

	ports.v32 = 0;
	poff = proto_ports_offset(ip_proto);
	if (poff >= 0) {
		nhoff += ihl * 4 + poff;
		if (pskb_may_pull(skb, nhoff + 4)) {
			ports.v32 = * (__force u32 *) (skb->data + nhoff);
			if (ports.v16[1] < ports.v16[0])
				swap(ports.v16[0], ports.v16[1]);
		}
	}

	/* get a consistent hash (same value on both flow directions) */
	if (addr2 < addr1)
		swap(addr1, addr2);

	hash = jhash_3words(addr1, addr2, ports.v32, hashrnd);
	if (!hash)
		hash = 1;

done:
	return hash;
}
EXPORT_SYMBOL(__skb_get_rxhash);

#ifdef CONFIG_RPS

/* One global table that all flow-based protocols share. */
struct rps_sock_flow_table *rps_sock_flow_table __read_mostly;
EXPORT_SYMBOL(rps_sock_flow_table);

/*
 * get_rps_cpu is called from netif_receive_skb and returns the target
 * CPU from the RPS map of the receiving queue for a given skb.
 * rcu_read_lock must be held on entry.
 */
static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
		       struct rps_dev_flow **rflowp)
{
	struct netdev_rx_queue *rxqueue;
	struct rps_map *map = NULL;
	struct rps_dev_flow_table *flow_table;
	struct rps_sock_flow_table *sock_flow_table;
	int cpu = -1;
	u16 tcpu;

	if (skb_rx_queue_recorded(skb)) {
		u16 index = skb_get_rx_queue(skb);
		if (unlikely(index >= dev->real_num_rx_queues)) {
			WARN_ONCE(dev->real_num_rx_queues > 1,
				  "%s received packet on queue %u, but number "
				  "of RX queues is %u\n",
				  dev->name, index, dev->real_num_rx_queues);
			goto done;
		}
		rxqueue = dev->_rx + index;
	} else
		rxqueue = dev->_rx;

	if (rxqueue->rps_map) {
		map = rcu_dereference(rxqueue->rps_map);
		if (map && map->len == 1) {
			tcpu = map->cpus[0];
			if (cpu_online(tcpu))
				cpu = tcpu;
			goto done;
		}
	} else if (!rxqueue->rps_flow_table) {
		goto done;
	}

	skb_reset_network_header(skb);
	if (!skb_get_rxhash(skb))
		goto done;

	flow_table = rcu_dereference(rxqueue->rps_flow_table);
	sock_flow_table = rcu_dereference(rps_sock_flow_table);
	if (flow_table && sock_flow_table) {
		u16 next_cpu;
		struct rps_dev_flow *rflow;

		rflow = &flow_table->flows[skb->rxhash & flow_table->mask];
		tcpu = rflow->cpu;

		next_cpu = sock_flow_table->ents[skb->rxhash &
		    sock_flow_table->mask];

		/*
		 * If the desired CPU (where last recvmsg was done) is
		 * different from current CPU (one in the rx-queue flow
		 * table entry), switch if one of the following holds:
		 *   - Current CPU is unset (equal to RPS_NO_CPU).
		 *   - Current CPU is offline.
		 *   - The current CPU's queue tail has advanced beyond the
		 *     last packet that was enqueued using this table entry.
		 *     This guarantees that all previous packets for the flow
		 *     have been dequeued, thus preserving in order delivery.
		 */
		if (unlikely(tcpu != next_cpu) &&
		    (tcpu == RPS_NO_CPU || !cpu_online(tcpu) ||
		     ((int)(per_cpu(softnet_data, tcpu).input_queue_head -
		      rflow->last_qtail)) >= 0)) {
			tcpu = rflow->cpu = next_cpu;
			if (tcpu != RPS_NO_CPU)
				rflow->last_qtail = per_cpu(softnet_data,
				    tcpu).input_queue_head;
		}
		if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) {
			*rflowp = rflow;
			cpu = tcpu;
			goto done;
		}
	}

	if (map) {
		tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32];

		if (cpu_online(tcpu)) {
			cpu = tcpu;
			goto done;
		}
	}

done:
	return cpu;
}

/* Called from hardirq (IPI) context */
static void rps_trigger_softirq(void *data)
{
	struct softnet_data *sd = data;

	____napi_schedule(sd, &sd->backlog);
	sd->received_rps++;
}

#endif /* CONFIG_RPS */

/*
 * Check if this softnet_data structure is another cpu one
 * If yes, queue it to our IPI list and return 1
 * If no, return 0
 */
static int rps_ipi_queued(struct softnet_data *sd)
{
#ifdef CONFIG_RPS
	struct softnet_data *mysd = &__get_cpu_var(softnet_data);

	if (sd != mysd) {
		sd->rps_ipi_next = mysd->rps_ipi_list;
		mysd->rps_ipi_list = sd;

		__raise_softirq_irqoff(NET_RX_SOFTIRQ);
		return 1;
	}
#endif /* CONFIG_RPS */
	return 0;
}

/*
 * enqueue_to_backlog is called to queue an skb to a per CPU backlog
 * queue (may be a remote CPU queue).
 */
static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
			      unsigned int *qtail)
{
	struct softnet_data *sd;
	unsigned long flags;

	sd = &per_cpu(softnet_data, cpu);

	local_irq_save(flags);

	rps_lock(sd);
	if (skb_queue_len(&sd->input_pkt_queue) <= netdev_max_backlog) {
		if (skb_queue_len(&sd->input_pkt_queue)) {
enqueue:
			__skb_queue_tail(&sd->input_pkt_queue, skb);
			input_queue_tail_incr_save(sd, qtail);
			rps_unlock(sd);
			local_irq_restore(flags);
			return NET_RX_SUCCESS;
		}

		/* Schedule NAPI for backlog device
		 * We can use non atomic operation since we own the queue lock
		 */
		if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state)) {
			if (!rps_ipi_queued(sd))
				____napi_schedule(sd, &sd->backlog);
		}
		goto enqueue;
	}

	sd->dropped++;
	rps_unlock(sd);

	local_irq_restore(flags);

	atomic_long_inc(&skb->dev->rx_dropped);
	kfree_skb(skb);
	return NET_RX_DROP;
}

/**
 *	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)
{
	int ret;

	/* if netpoll wants it, pretend we never saw it */
	if (netpoll_rx(skb))
		return NET_RX_DROP;

	if (netdev_tstamp_prequeue)
		net_timestamp_check(skb);

#ifdef CONFIG_RPS
	{
		struct rps_dev_flow voidflow, *rflow = &voidflow;
		int cpu;

		preempt_disable();
		rcu_read_lock();

		cpu = get_rps_cpu(skb->dev, skb, &rflow);
		if (cpu < 0)
			cpu = smp_processor_id();

		ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);

		rcu_read_unlock();
		preempt_enable();
	}
#else
	{
		unsigned int qtail;
		ret = enqueue_to_backlog(skb, get_cpu(), &qtail);
		put_cpu();
	}
#endif
	return ret;
}
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;
		sd->output_queue_tailp = &sd->output_queue;
		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)) && \
    (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

#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 netdev_queue *rxq)
{
	struct net_device *dev = skb->dev;
	u32 ttl = G_TC_RTTL(skb->tc_verd);
	int result = TC_ACT_OK;
	struct Qdisc *q;

	if (unlikely(MAX_RED_LOOP < ttl++)) {
		if (net_ratelimit())
			pr_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);

	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)
{
	struct netdev_queue *rxq = rcu_dereference(skb->dev->ingress_queue);

	if (!rxq || rxq->qdisc == &noop_qdisc)
		goto out;

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

	switch (ing_filter(skb, rxq)) {
	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();
}

/**
 *	netdev_rx_handler_register - register receive handler
 *	@dev: device to register a handler for
 *	@rx_handler: receive handler to register
 *	@rx_handler_data: data pointer that is used by rx handler
 *
 *	Register a receive hander for a device. This handler will then be
 *	called from __netif_receive_skb. A negative errno code is returned
 *	on a failure.
 *
 *	The caller must hold the rtnl_mutex.
 */
int netdev_rx_handler_register(struct net_device *dev,
			       rx_handler_func_t *rx_handler,
			       void *rx_handler_data)
{
	ASSERT_RTNL();

	if (dev->rx_handler)
		return -EBUSY;

	rcu_assign_pointer(dev->rx_handler_data, rx_handler_data);
	rcu_assign_pointer(dev->rx_handler, rx_handler);

	return 0;
}
EXPORT_SYMBOL_GPL(netdev_rx_handler_register);

/**
 *	netdev_rx_handler_unregister - unregister receive handler
 *	@dev: device to unregister a handler from
 *
 *	Unregister a receive hander from a device.
 *
 *	The caller must hold the rtnl_mutex.
 */
void netdev_rx_handler_unregister(struct net_device *dev)
{

	ASSERT_RTNL();
	rcu_assign_pointer(dev->rx_handler, NULL);
	rcu_assign_pointer(dev->rx_handler_data, NULL);
}
EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister);

static inline void skb_bond_set_mac_by_master(struct sk_buff *skb,
					      struct net_device *master)
{
	if (skb->pkt_type == PACKET_HOST) {
		u16 *dest = (u16 *) eth_hdr(skb)->h_dest;

		memcpy(dest, master->dev_addr, ETH_ALEN);
	}
}

/* On bonding slaves other than the currently active slave, suppress
 * duplicates except for 802.3ad ETH_P_SLOW, alb non-mcast/bcast, and
 * ARP on active-backup slaves with arp_validate enabled.
 */
int __skb_bond_should_drop(struct sk_buff *skb, struct net_device *master)
{
	struct net_device *dev = skb->dev;

	if (master->priv_flags & IFF_MASTER_ARPMON)
		dev->last_rx = jiffies;

	if ((master->priv_flags & IFF_MASTER_ALB) &&
	    (master->priv_flags & IFF_BRIDGE_PORT)) {
		/* Do address unmangle. The local destination address
		 * will be always the one master has. Provides the right
		 * functionality in a bridge.
		 */
		skb_bond_set_mac_by_master(skb, master);
	}

	if (dev->priv_flags & IFF_SLAVE_INACTIVE) {
		if ((dev->priv_flags & IFF_SLAVE_NEEDARP) &&
		    skb->protocol == __cpu_to_be16(ETH_P_ARP))
			return 0;

		if (master->priv_flags & IFF_MASTER_ALB) {
			if (skb->pkt_type != PACKET_BROADCAST &&
			    skb->pkt_type != PACKET_MULTICAST)
				return 0;
		}
		if (master->priv_flags & IFF_MASTER_8023AD &&
		    skb->protocol == __cpu_to_be16(ETH_P_SLOW))
			return 0;

		return 1;
	}
	return 0;
}
EXPORT_SYMBOL(__skb_bond_should_drop);

static int __netif_receive_skb(struct sk_buff *skb)
{
	struct packet_type *ptype, *pt_prev;
	rx_handler_func_t *rx_handler;
	struct net_device *orig_dev;
	struct net_device *master;
	struct net_device *null_or_orig;
	struct net_device *orig_or_bond;
	int ret = NET_RX_DROP;
	__be16 type;

	if (!netdev_tstamp_prequeue)
		net_timestamp_check(skb);

	if (vlan_tx_tag_present(skb))
		vlan_hwaccel_do_receive(skb);

	/* 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;

	/*
	 * bonding note: skbs received on inactive slaves should only
	 * be delivered to pkt handlers that are exact matches.  Also
	 * the deliver_no_wcard flag will be set.  If packet handlers
	 * are sensitive to duplicate packets these skbs will need to
	 * be dropped at the handler.  The vlan accel path may have
	 * already set the deliver_no_wcard flag.
	 */
	null_or_orig = NULL;
	orig_dev = skb->dev;
	master = ACCESS_ONCE(orig_dev->master);
	if (skb->deliver_no_wcard)
		null_or_orig = orig_dev;
	else if (master) {
		if (skb_bond_should_drop(skb, master)) {
			skb->deliver_no_wcard = 1;
			null_or_orig = orig_dev; /* deliver only exact match */
		} else
			skb->dev = master;
	}

	__this_cpu_inc(softnet_data.processed);
	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

	/* Handle special case of bridge or macvlan */
	rx_handler = rcu_dereference(skb->dev->rx_handler);
	if (rx_handler) {
		if (pt_prev) {
			ret = deliver_skb(skb, pt_prev, orig_dev);
			pt_prev = NULL;
		}
		skb = rx_handler(skb);
		if (!skb)
			goto out;
	}

	/*
	 * Make sure frames received on VLAN interfaces stacked on
	 * bonding interfaces still make their way to any base bonding
	 * device that may have registered for a specific ptype.  The
	 * handler may have to adjust skb->dev and orig_dev.
	 */
	orig_or_bond = orig_dev;
	if ((skb->dev->priv_flags & IFF_802_1Q_VLAN) &&
	    (vlan_dev_real_dev(skb->dev)->priv_flags & IFF_BONDING)) {
		orig_or_bond = vlan_dev_real_dev(skb->dev);
	}

	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 ||
		     ptype->dev == orig_or_bond)) {
			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 {
		atomic_long_inc(&skb->dev->rx_dropped);