dev.c

	if (sk_tx_queue_recorded(sk)) {
		queue_index = sk_tx_queue_get(sk);
	} else {
		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 {
			queue_index = 0;
			if (dev->real_num_tx_queues > 1)
				queue_index = skb_tx_hash(dev, skb);

			if (sk && sk->sk_dst_cache)
				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);
	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;
}

/*
 * Returns true if either:
 *	1. skb has frag_list and the device doesn't support FRAGLIST, or
 *	2. skb is fragmented and the device does not support SG, or if
 *	   at least one of fragments is in highmem and device does not
 *	   support DMA from it.
 */
static inline int skb_needs_linearize(struct sk_buff *skb,
				      struct net_device *dev)
{
	return (skb_has_frags(skb) && !(dev->features & NETIF_F_FRAGLIST)) ||
	       (skb_shinfo(skb)->nr_frags && (!(dev->features & NETIF_F_SG) ||
					      illegal_highdma(dev, skb)));
}

/**
 *	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;

	/* Convert a paged skb to linear, if required */
	if (skb_needs_linearize(skb, dev) && __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_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) {

			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, };

#ifdef CONFIG_RPS
/*
 * 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.
 */
static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb)
{
	struct ipv6hdr *ip6;
	struct iphdr *ip;
	struct netdev_rx_queue *rxqueue;
	struct rps_map *map;
	int cpu = -1;
	u8 ip_proto;
	u32 addr1, addr2, ports, ihl;

	rcu_read_lock();

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

	if (!rxqueue->rps_map)
		goto done;

	if (skb->rxhash)
		goto got_hash; /* Skip hash computation on packet header */

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

		ip = (struct iphdr *) skb->data;
		ip_proto = ip->protocol;
		addr1 = ip->saddr;
		addr2 = ip->daddr;
		ihl = ip->ihl;
		break;
	case __constant_htons(ETH_P_IPV6):
		if (!pskb_may_pull(skb, sizeof(*ip6)))
			goto done;

		ip6 = (struct ipv6hdr *) skb->data;
		ip_proto = ip6->nexthdr;
		addr1 = ip6->saddr.s6_addr32[3];
		addr2 = ip6->daddr.s6_addr32[3];
		ihl = (40 >> 2);
		break;
	default:
		goto done;
	}
	ports = 0;
	switch (ip_proto) {
	case IPPROTO_TCP:
	case IPPROTO_UDP:
	case IPPROTO_DCCP:
	case IPPROTO_ESP:
	case IPPROTO_AH:
	case IPPROTO_SCTP:
	case IPPROTO_UDPLITE:
		if (pskb_may_pull(skb, (ihl * 4) + 4))
			ports = *((u32 *) (skb->data + (ihl * 4)));
		break;

	default:
		break;
	}

	skb->rxhash = jhash_3words(addr1, addr2, ports, hashrnd);
	if (!skb->rxhash)
		skb->rxhash = 1;

got_hash:
	map = rcu_dereference(rxqueue->rps_map);
	if (map) {
		u16 tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32];

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

done:
	rcu_read_unlock();
	return cpu;
}

/*
 * This structure holds the per-CPU mask of CPUs for which IPIs are scheduled
 * to be sent to kick remote softirq processing.  There are two masks since
 * the sending of IPIs must be done with interrupts enabled.  The select field
 * indicates the current mask that enqueue_backlog uses to schedule IPIs.
 * select is flipped before net_rps_action is called while still under lock,
 * net_rps_action then uses the non-selected mask to send the IPIs and clears
 * it without conflicting with enqueue_backlog operation.
 */
struct rps_remote_softirq_cpus {
	cpumask_t mask[2];
	int select;
};
static DEFINE_PER_CPU(struct rps_remote_softirq_cpus, rps_remote_softirq_cpus);

/* Called from hardirq (IPI) context */
static void trigger_softirq(void *data)
{
	struct softnet_data *queue = data;
	__napi_schedule(&queue->backlog);
	__get_cpu_var(netdev_rx_stat).received_rps++;
}
#endif /* CONFIG_SMP */

/*
 * 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)
{
	struct softnet_data *queue;
	unsigned long flags;

	queue = &per_cpu(softnet_data, cpu);

	local_irq_save(flags);
	__get_cpu_var(netdev_rx_stat).total++;

	rps_lock(queue);
	if (queue->input_pkt_queue.qlen <= netdev_max_backlog) {
		if (queue->input_pkt_queue.qlen) {
enqueue:
			__skb_queue_tail(&queue->input_pkt_queue, skb);
			rps_unlock(queue);
			local_irq_restore(flags);
			return NET_RX_SUCCESS;
		}

		/* Schedule NAPI for backlog device */
		if (napi_schedule_prep(&queue->backlog)) {
#ifdef CONFIG_RPS
			if (cpu != smp_processor_id()) {
				struct rps_remote_softirq_cpus *rcpus =
				    &__get_cpu_var(rps_remote_softirq_cpus);

				cpu_set(cpu, rcpus->mask[rcpus->select]);
				__raise_softirq_irqoff(NET_RX_SOFTIRQ);
			} else
				__napi_schedule(&queue->backlog);
#else
			__napi_schedule(&queue->backlog);
#endif
		}
		goto enqueue;
	}

	rps_unlock(queue);

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

	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 cpu;

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

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

#ifdef CONFIG_RPS
	cpu = get_rps_cpu(skb->dev, skb);
	if (cpu < 0)
		cpu = smp_processor_id();
#else
	cpu = smp_processor_id();
#endif

	return enqueue_to_backlog(skb, cpu);
}
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();
}

static int __netif_receive_skb(struct sk_buff *skb)
{
	struct packet_type *ptype, *pt_prev;
	struct net_device *orig_dev;
	struct net_device *master;
	struct net_device *null_or_orig;
	struct net_device *null_or_bond;
	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;
	master = ACCESS_ONCE(orig_dev->master);
	if (master) {
		if (skb_bond_should_drop(skb, master))
			null_or_orig = orig_dev; /* deliver only exact match */
		else
			skb->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;

	/*
	 * 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.
	 */
	null_or_bond = NULL;
	if ((skb->dev->priv_flags & IFF_802_1Q_VLAN) &&
	    (vlan_dev_real_dev(skb->dev)->priv_flags & IFF_BONDING)) {
		null_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 == null_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 {
		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;
}

/**
 *	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)
{
#ifdef CONFIG_RPS
	int cpu;

	cpu = get_rps_cpu(skb->dev, skb);

	if (cpu < 0)
		return __netif_receive_skb(skb);
	else
		return enqueue_to_backlog(skb, cpu);
#else
	return __netif_receive_skb(skb);
#endif
}
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;

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

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);
}

static 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;
}

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);