dev.c

{
#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;

	net_timestamp_check(netdev_tstamp_prequeue, skb);

	trace_netif_rx(skb);
#ifdef CONFIG_RPS
	if (static_key_false(&rps_needed)) {
		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
#endif
	{
		unsigned int qtail;
		ret = enqueue_to_backlog(skb, get_cpu(), &qtail);
		put_cpu();
	}
	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));
			trace_kfree_skb(skb, net_tx_action);
			__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);
				}
			}
		}
	}
}

#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 doesn't stop any functionality; if you dont have
 * the ingress scheduler, you just can't 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++)) {
		net_warn_ratelimited("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

/**
 *	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.
 *
 *	For a general description of rx_handler, see enum rx_handler_result.
 */
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_INIT_POINTER(dev->rx_handler, NULL);
	RCU_INIT_POINTER(dev->rx_handler_data, NULL);
}
EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister);

/*
 * Limit the use of PFMEMALLOC reserves to those protocols that implement
 * the special handling of PFMEMALLOC skbs.
 */
static bool skb_pfmemalloc_protocol(struct sk_buff *skb)
{
	switch (skb->protocol) {
	case __constant_htons(ETH_P_ARP):
	case __constant_htons(ETH_P_IP):
	case __constant_htons(ETH_P_IPV6):
	case __constant_htons(ETH_P_8021Q):
		return true;
	default:
		return false;
	}
}

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 *null_or_dev;
	bool deliver_exact = false;
	int ret = NET_RX_DROP;
	__be16 type;
	unsigned long pflags = current->flags;

	net_timestamp_check(!netdev_tstamp_prequeue, skb);

	trace_netif_receive_skb(skb);

	/*
	 * PFMEMALLOC skbs are special, they should
	 * - be delivered to SOCK_MEMALLOC sockets only
	 * - stay away from userspace
	 * - have bounded memory usage
	 *
	 * Use PF_MEMALLOC as this saves us from propagating the allocation
	 * context down to all allocation sites.
	 */
	if (sk_memalloc_socks() && skb_pfmemalloc(skb))
		current->flags |= PF_MEMALLOC;

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

	orig_dev = skb->dev;

	skb_reset_network_header(skb);
	skb_reset_transport_header(skb);
	skb_reset_mac_len(skb);

	pt_prev = NULL;

	rcu_read_lock();

another_round:
	skb->skb_iif = skb->dev->ifindex;

	__this_cpu_inc(softnet_data.processed);

	if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) {
		skb = vlan_untag(skb);
		if (unlikely(!skb))
			goto unlock;
	}

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

	if (sk_memalloc_socks() && skb_pfmemalloc(skb))
		goto skip_taps;

	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;
		}
	}

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

	if (sk_memalloc_socks() && skb_pfmemalloc(skb)
				&& !skb_pfmemalloc_protocol(skb))
		goto drop;

	if (vlan_tx_tag_present(skb)) {
		if (pt_prev) {
			ret = deliver_skb(skb, pt_prev, orig_dev);
			pt_prev = NULL;
		}
		if (vlan_do_receive(&skb))
			goto another_round;
		else if (unlikely(!skb))
			goto unlock;
	}

	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;
		}
		switch (rx_handler(&skb)) {
		case RX_HANDLER_CONSUMED:
			goto unlock;
		case RX_HANDLER_ANOTHER:
			goto another_round;
		case RX_HANDLER_EXACT:
			deliver_exact = true;
		case RX_HANDLER_PASS:
			break;
		default:
			BUG();
		}
	}

	if (vlan_tx_nonzero_tag_present(skb))
		skb->pkt_type = PACKET_OTHERHOST;

	/* deliver only exact match when indicated */
	null_or_dev = deliver_exact ? skb->dev : NULL;

	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_dev || 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) {
		if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC)))
			goto drop;
		else
			ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
	} else {
drop:
		atomic_long_inc(&skb->dev->rx_dropped);
		kfree_skb(skb);
		/* Jamal, now you will not able to escape explaining
		 * me how you were going to use this. :-)
		 */
		ret = NET_RX_DROP;
	}

unlock:
	rcu_read_unlock();
out:
	tsk_restore_flags(current, pflags, PF_MEMALLOC);
	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)
{
	net_timestamp_check(netdev_tstamp_prequeue, skb);

	if (skb_defer_rx_timestamp(skb))
		return NET_RX_SUCCESS;

#ifdef CONFIG_RPS
	if (static_key_false(&rps_needed)) {
		struct rps_dev_flow voidflow, *rflow = &voidflow;
		int cpu, ret;

		rcu_read_lock();

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

		if (cpu >= 0) {
			ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
			rcu_read_unlock();
			return ret;
		}
		rcu_read_unlock();
	}
#endif
	return __netif_receive_skb(skb);
}
EXPORT_SYMBOL(netif_receive_skb);

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

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

	skb_queue_walk_safe(&sd->process_queue, skb, tmp) {
		if (skb->dev == dev) {
			__skb_unlink(skb, &sd->process_queue);
			kfree_skb(skb);
			input_queue_head_incr(sd);
		}
	}
}

static int napi_gro_complete(struct sk_buff *skb)
{
	struct packet_offload *ptype;
	__be16 type = skb->protocol;
	struct list_head *head = &offload_base;
	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->callbacks.gro_complete)
			continue;

		err = ptype->callbacks.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);
}

/* napi->gro_list contains packets ordered by age.
 * youngest packets at the head of it.
 * Complete skbs in reverse order to reduce latencies.
 */
void napi_gro_flush(struct napi_struct *napi, bool flush_old)
{
	struct sk_buff *skb, *prev = NULL;

	/* scan list and build reverse chain */
	for (skb = napi->gro_list; skb != NULL; skb = skb->next) {
		skb->prev = prev;
		prev = skb;
	}

	for (skb = prev; skb; skb = prev) {
		skb->next = NULL;

		if (flush_old && NAPI_GRO_CB(skb)->age == jiffies)
			return;

		prev = skb->prev;
		napi_gro_complete(skb);
		napi->gro_count--;
	}

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

static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
	struct sk_buff **pp = NULL;
	struct packet_offload *ptype;
	__be16 type = skb->protocol;
	struct list_head *head = &offload_base;
	int same_flow;
	int mac_len;
	enum gro_result ret;

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

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

	rcu_read_lock();
	list_for_each_entry_rcu(ptype, head, list) {
		if (ptype->type != type || !ptype->callbacks.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->callbacks.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;
	NAPI_GRO_CB(skb)->age = jiffies;
	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_frag_size_sub(&skb_shinfo(skb)->frags[0], grow);

		if (unlikely(!skb_frag_size(&skb_shinfo(skb)->frags[0]))) {
			skb_frag_unref(skb, 0);
			memmove(skb_shinfo(skb)->frags,
				skb_shinfo(skb)->frags + 1,
				--skb_shinfo(skb)->nr_frags * sizeof(skb_frag_t));
		}
	}

ok:
	return ret;

normal:
	ret = GRO_NORMAL;
	goto pull;
}

static inline gro_result_t
__napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
	struct sk_buff *p;
	unsigned int maclen = skb->dev->hard_header_len;

	for (p = napi->gro_list; p; p = p->next) {
		unsigned long diffs;

		diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev;
		diffs |= p->vlan_tci ^ skb->vlan_tci;
		if (maclen == ETH_HLEN)
			diffs |= compare_ether_header(skb_mac_header(p),
						      skb_gro_mac_header(skb));
		else if (!diffs)
			diffs = memcmp(skb_mac_header(p),
				       skb_gro_mac_header(skb),
				       maclen);
		NAPI_GRO_CB(p)->same_flow = !diffs;
		NAPI_GRO_CB(p)->flush = 0;
	}

	return dev_gro_receive(napi, skb);
}

static 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:
		kfree_skb(skb);
		break;

	case GRO_MERGED_FREE:
		if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD)
			kmem_cache_free(skbuff_head_cache, skb);
		else
			__kfree_skb(skb);
		break;

	case GRO_HELD:
	case GRO_MERGED:
		break;
	}

	return ret;
}

static void skb_gro_reset_offset(struct sk_buff *skb)
{
	const struct skb_shared_info *pinfo = skb_shinfo(skb);
	const skb_frag_t *frag0 = &pinfo->frags[0];

	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 &&
	    pinfo->nr_frags &&
	    !PageHighMem(skb_frag_page(frag0))) {
		NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
		NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0);
	}
}

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);

static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
{
	__skb_pull(skb, skb_headlen(skb));
	/* restore the reserve we had after netdev_alloc_skb_ip_align() */
	skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN - skb_headroom(skb));
	skb->vlan_tci = 0;
	skb->dev = napi->dev;
	skb->skb_iif = 0;

	napi->skb = 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);

static 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, skb->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;
}

static 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;
}

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);

/*
 * net_rps_action sends any pending IPI's for rps.
 * Note: called with local irq disabled, but exits with local irq enabled.
 */
static void net_rps_action_and_irq_enable(struct softnet_data *sd)
{
#ifdef CONFIG_RPS
	struct softnet_data *remsd = sd->rps_ipi_list;

	if (remsd) {
		sd->rps_ipi_list = NULL;

		local_irq_enable();

		/* Send pending IPI's to kick RPS processing on remote cpus. */
		while (remsd) {
			struct softnet_data *next = remsd->rps_ipi_next;

			if (cpu_online(remsd->cpu))
				__smp_call_function_single(remsd->cpu,
							   &remsd->csd, 0);
			remsd = next;
		}
	} else
#endif
		local_irq_enable();
}

static int process_backlog(struct napi_struct *napi, int quota)
{
	int work = 0;
	struct softnet_data *sd = container_of(napi, struct softnet_data, backlog);

#ifdef CONFIG_RPS
	/* Check if we have pending ipi, its better to send them now,
	 * not waiting net_rx_action() end.
	 */
	if (sd->rps_ipi_list) {
		local_irq_disable();
		net_rps_action_and_irq_enable(sd);
	}
#endif
	napi->weight = weight_p;
	local_irq_disable();
	while (work < quota) {
		struct sk_buff *skb;
		unsigned int qlen;

		while ((skb = __skb_dequeue(&sd->process_queue))) {
			local_irq_enable();
			__netif_receive_skb(skb);
			local_irq_disable();
			input_queue_head_incr(sd);
			if (++work >= quota) {
				local_irq_enable();
				return work;
			}
		}

		rps_lock(sd);
		qlen = skb_queue_len(&sd->input_pkt_queue);
		if (qlen)
			skb_queue_splice_tail_init(&sd->input_pkt_queue,
						   &sd->process_queue);

		if (qlen < quota - work) {
			/*
			 * Inline a custom version of __napi_complete().
			 * only current cpu owns and manipulates this napi,
			 * and NAPI_STATE_SCHED is the only possible flag set on backlog.
			 * we can use a plain write instead of clear_bit(),
			 * and we dont need an smp_mb() memory barrier.
			 */
			list_del(&napi->poll_list);
			napi->state = 0;

			quota = work + qlen;
		}
		rps_unlock(sd);
	}
	local_irq_enable();

	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);
	____napi_schedule(&__get_cpu_var(softnet_data), n);
	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, false);
	local_irq_save(flags);
	__napi_complete(n);
	local_irq_restore(flags);
}