Skip to content
Snippets Groups Projects
dev.c 147 KiB
Newer Older
Eric Dumazet's avatar
Eric Dumazet committed
	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_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;

	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);
	}

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;
	enum gro_result ret;

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

	if (skb_is_gso(skb) || skb_has_frags(skb))
	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;
Herbert Xu's avatar
Herbert Xu committed
		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);
	if (same_flow)
	if (NAPI_GRO_CB(skb)->flush || napi->gro_count >= MAX_GRO_SKBS)
	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;
	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);
		}
	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:
Herbert Xu's avatar
Herbert Xu committed
		kfree_skb(skb);
		break;

	case GRO_HELD:
	case GRO_MERGED:
		break;
}
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)
Herbert Xu's avatar
Herbert Xu committed
{
	struct sk_buff *skb = napi->skb;

	if (!skb) {
		skb = netdev_alloc_skb_ip_align(napi->dev, GRO_MAX_HEAD);
		if (skb)
			napi->skb = 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:
		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;
	case GRO_DROP:
	case GRO_MERGED_FREE:
		napi_reuse_skb(napi, skb);
		break;
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);

	return napi_frags_finish(napi, skb, __napi_gro_receive(napi, skb));
}
Herbert Xu's avatar
Herbert Xu committed
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)
Linus Torvalds's avatar
Linus Torvalds committed
{
	int work = 0;
Eric Dumazet's avatar
Eric Dumazet committed
	struct softnet_data *sd = container_of(napi, struct softnet_data, backlog);
Linus Torvalds's avatar
Linus Torvalds committed

#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
	local_irq_disable();
	while (work < quota) {
Linus Torvalds's avatar
Linus Torvalds committed
		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;
			}
Linus Torvalds's avatar
Linus Torvalds committed

Eric Dumazet's avatar
Eric Dumazet committed
		rps_lock(sd);
		qlen = skb_queue_len(&sd->input_pkt_queue);
			skb_queue_splice_tail_init(&sd->input_pkt_queue,
						   &sd->process_queue);
		if (qlen < quota - work) {
Eric Dumazet's avatar
Eric Dumazet committed
			/*
			 * 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;

Eric Dumazet's avatar
Eric Dumazet committed
		rps_unlock(sd);
Linus Torvalds's avatar
Linus Torvalds committed

Linus Torvalds's avatar
Linus Torvalds committed

/**
 * __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)
Linus Torvalds's avatar
Linus Torvalds committed

Eric Dumazet's avatar
Eric Dumazet committed
	____napi_schedule(&__get_cpu_var(softnet_data), n);
Linus Torvalds's avatar
Linus Torvalds committed
}
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_list = NULL;
Herbert Xu's avatar
Herbert Xu committed
	napi->skb = NULL;
	napi->poll = poll;
	napi->weight = weight;
	list_add(&napi->dev_list, &dev->napi_list);
	napi->dev = dev;
Herbert Xu's avatar
Herbert Xu committed
#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;
}
EXPORT_SYMBOL(netif_napi_del);

Linus Torvalds's avatar
Linus Torvalds committed
static void net_rx_action(struct softirq_action *h)
{
	struct softnet_data *sd = &__get_cpu_var(softnet_data);
	unsigned long time_limit = jiffies + 2;
	int budget = netdev_budget;
Linus Torvalds's avatar
Linus Torvalds committed
	local_irq_disable();

	while (!list_empty(&sd->poll_list)) {
		struct napi_struct *n;
		int work, weight;
Linus Torvalds's avatar
Linus Torvalds committed

		/* 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)))
Linus Torvalds's avatar
Linus Torvalds committed
			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_first_entry(&sd->poll_list, struct napi_struct, poll_list);
Linus Torvalds's avatar
Linus Torvalds committed

		/* 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);

		WARN_ON_ONCE(work > weight);

		budget -= work;

		local_irq_disable();

		/* Drivers must not modify the NAPI state if they
		 * consume the entire weight.  In such cases this code
		 * still "owns" the NAPI instance and therefore can
		 * move the instance around on the list at-will.
		 */
		if (unlikely(work == weight)) {
			if (unlikely(napi_disable_pending(n))) {
				local_irq_enable();
				napi_complete(n);
				local_irq_disable();
			} else
				list_move_tail(&n->poll_list, &sd->poll_list);
Linus Torvalds's avatar
Linus Torvalds committed
	}
out:
	net_rps_action_and_irq_enable(sd);
#ifdef CONFIG_NET_DMA
	/*
	 * There may not be any more sk_buffs coming right now, so push
	 * any pending DMA copies to hardware
	 */
Linus Torvalds's avatar
Linus Torvalds committed
	return;

softnet_break:
Changli Gao's avatar
Changli Gao committed
	sd->time_squeeze++;
Linus Torvalds's avatar
Linus Torvalds committed
	__raise_softirq_irqoff(NET_RX_SOFTIRQ);
	goto out;
}

static gifconf_func_t *gifconf_list[NPROTO];
Linus Torvalds's avatar
Linus Torvalds committed

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


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

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

static int dev_ifname(struct net *net, struct ifreq __user *arg)
Linus Torvalds's avatar
Linus Torvalds committed
{
	struct net_device *dev;
	struct ifreq ifr;

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

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

	rcu_read_lock();
	dev = dev_get_by_index_rcu(net, ifr.ifr_ifindex);
Linus Torvalds's avatar
Linus Torvalds committed
	if (!dev) {
		rcu_read_unlock();
Linus Torvalds's avatar
Linus Torvalds committed
		return -ENODEV;
	}

	strcpy(ifr.ifr_name, dev->name);
	rcu_read_unlock();
Linus Torvalds's avatar
Linus Torvalds committed

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

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

static int dev_ifconf(struct net *net, char __user *arg)
Linus Torvalds's avatar
Linus Torvalds committed
{
	struct ifconf ifc;
	struct net_device *dev;
	char __user *pos;
	int len;
	int total;
	int i;

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

	if (copy_from_user(&ifc, arg, sizeof(struct ifconf)))
		return -EFAULT;

	pos = ifc.ifc_buf;
	len = ifc.ifc_len;

	/*
	 *	Loop over the interfaces, and write an info block for each.
	 */

	total = 0;
Linus Torvalds's avatar
Linus Torvalds committed
		for (i = 0; i < NPROTO; i++) {
			if (gifconf_list[i]) {
				int done;
				if (!pos)
					done = gifconf_list[i](dev, NULL, 0);
				else
					done = gifconf_list[i](dev, pos + total,
							       len - total);
				if (done < 0)
					return -EFAULT;
				total += done;
			}
		}
Linus Torvalds's avatar
Linus Torvalds committed

	/*
	 *	All done.  Write the updated control block back to the caller.
	 */
	ifc.ifc_len = total;

	/*
	 * 	Both BSD and Solaris return 0 here, so we do too.
	 */
	return copy_to_user(arg, &ifc, sizeof(struct ifconf)) ? -EFAULT : 0;
}

#ifdef CONFIG_PROC_FS
/*
 *	This is invoked by the /proc filesystem handler to display a device
 *	in detail.
 */
void *dev_seq_start(struct seq_file *seq, loff_t *pos)
Linus Torvalds's avatar
Linus Torvalds committed
{
	struct net *net = seq_file_net(seq);
Linus Torvalds's avatar
Linus Torvalds committed
	struct net_device *dev;

	if (!*pos)
		return SEQ_START_TOKEN;
Linus Torvalds's avatar
Linus Torvalds committed

	for_each_netdev_rcu(net, dev)
		if (off++ == *pos)
			return dev;
Linus Torvalds's avatar
Linus Torvalds committed

Linus Torvalds's avatar
Linus Torvalds committed
}

void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct net_device *dev = (v == SEQ_START_TOKEN) ?
				  first_net_device(seq_file_net(seq)) :
				  next_net_device((struct net_device *)v);

Linus Torvalds's avatar
Linus Torvalds committed
	++*pos;
	return rcu_dereference(dev);
Linus Torvalds's avatar
Linus Torvalds committed
}

void dev_seq_stop(struct seq_file *seq, void *v)
Linus Torvalds's avatar
Linus Torvalds committed
{
	rcu_read_unlock();
Linus Torvalds's avatar
Linus Torvalds committed
}

static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev)
{
	struct rtnl_link_stats64 temp;
	const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp);
Linus Torvalds's avatar
Linus Torvalds committed

	seq_printf(seq, "%6s: %7llu %7llu %4llu %4llu %4llu %5llu %10llu %9llu "
		   "%8llu %7llu %4llu %4llu %4llu %5llu %7llu %10llu\n",
		   dev->name, stats->rx_bytes, stats->rx_packets,
		   stats->rx_errors,
		   stats->rx_dropped + stats->rx_missed_errors,
		   stats->rx_fifo_errors,
		   stats->rx_length_errors + stats->rx_over_errors +
		    stats->rx_crc_errors + stats->rx_frame_errors,
		   stats->rx_compressed, stats->multicast,
		   stats->tx_bytes, stats->tx_packets,
		   stats->tx_errors, stats->tx_dropped,
		   stats->tx_fifo_errors, stats->collisions,
		   stats->tx_carrier_errors +
		    stats->tx_aborted_errors +
		    stats->tx_window_errors +
		    stats->tx_heartbeat_errors,
		   stats->tx_compressed);
Linus Torvalds's avatar
Linus Torvalds committed
}

/*
 *	Called from the PROCfs module. This now uses the new arbitrary sized
 *	/proc/net interface to create /proc/net/dev
 */
static int dev_seq_show(struct seq_file *seq, void *v)
{
	if (v == SEQ_START_TOKEN)
		seq_puts(seq, "Inter-|   Receive                            "
			      "                    |  Transmit\n"
			      " face |bytes    packets errs drop fifo frame "
			      "compressed multicast|bytes    packets errs "
			      "drop fifo colls carrier compressed\n");
	else
		dev_seq_printf_stats(seq, v);
	return 0;
}

Changli Gao's avatar
Changli Gao committed
static struct softnet_data *softnet_get_online(loff_t *pos)
Linus Torvalds's avatar
Linus Torvalds committed
{
Changli Gao's avatar
Changli Gao committed
	struct softnet_data *sd = NULL;
Linus Torvalds's avatar
Linus Torvalds committed

	while (*pos < nr_cpu_ids)
		if (cpu_online(*pos)) {
Changli Gao's avatar
Changli Gao committed
			sd = &per_cpu(softnet_data, *pos);
Linus Torvalds's avatar
Linus Torvalds committed
			break;
		} else
			++*pos;
Changli Gao's avatar
Changli Gao committed
	return sd;
Linus Torvalds's avatar
Linus Torvalds committed
}

static void *softnet_seq_start(struct seq_file *seq, loff_t *pos)
{
	return softnet_get_online(pos);
}

static void *softnet_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	++*pos;
	return softnet_get_online(pos);
}

static void softnet_seq_stop(struct seq_file *seq, void *v)
{
}

static int softnet_seq_show(struct seq_file *seq, void *v)
{
Changli Gao's avatar
Changli Gao committed
	struct softnet_data *sd = v;
Linus Torvalds's avatar
Linus Torvalds committed

	seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
Changli Gao's avatar
Changli Gao committed
		   sd->processed, sd->dropped, sd->time_squeeze, 0,
		   0, 0, 0, 0, /* was fastroute */
Changli Gao's avatar
Changli Gao committed
		   sd->cpu_collision, sd->received_rps);
Linus Torvalds's avatar
Linus Torvalds committed
	return 0;
}

static const struct seq_operations dev_seq_ops = {
Linus Torvalds's avatar
Linus Torvalds committed
	.start = dev_seq_start,
	.next  = dev_seq_next,
	.stop  = dev_seq_stop,
	.show  = dev_seq_show,
};

static int dev_seq_open(struct inode *inode, struct file *file)
{
	return seq_open_net(inode, file, &dev_seq_ops,
			    sizeof(struct seq_net_private));
static const struct file_operations dev_seq_fops = {
Linus Torvalds's avatar
Linus Torvalds committed
	.owner	 = THIS_MODULE,
	.open    = dev_seq_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
static const struct seq_operations softnet_seq_ops = {
Linus Torvalds's avatar
Linus Torvalds committed
	.start = softnet_seq_start,
	.next  = softnet_seq_next,
	.stop  = softnet_seq_stop,
	.show  = softnet_seq_show,
};

static int softnet_seq_open(struct inode *inode, struct file *file)
{
	return seq_open(file, &softnet_seq_ops);
}

static const struct file_operations softnet_seq_fops = {
Linus Torvalds's avatar
Linus Torvalds committed
	.owner	 = THIS_MODULE,
	.open    = softnet_seq_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
	.release = seq_release,
};

static void *ptype_get_idx(loff_t pos)
{
	struct packet_type *pt = NULL;
	loff_t i = 0;
	int t;

	list_for_each_entry_rcu(pt, &ptype_all, list) {
		if (i == pos)
			return pt;
		++i;
	}

	for (t = 0; t < PTYPE_HASH_SIZE; t++) {
		list_for_each_entry_rcu(pt, &ptype_base[t], list) {
			if (i == pos)
				return pt;
			++i;
		}
	}
	return NULL;
}

static void *ptype_seq_start(struct seq_file *seq, loff_t *pos)
{
	rcu_read_lock();
	return *pos ? ptype_get_idx(*pos - 1) : SEQ_START_TOKEN;
}

static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct packet_type *pt;
	struct list_head *nxt;
	int hash;

	++*pos;
	if (v == SEQ_START_TOKEN)
		return ptype_get_idx(0);

	pt = v;
	nxt = pt->list.next;
	if (pt->type == htons(ETH_P_ALL)) {
		if (nxt != &ptype_all)
			goto found;
		hash = 0;
		nxt = ptype_base[0].next;
	} else
		hash = ntohs(pt->type) & PTYPE_HASH_MASK;

	while (nxt == &ptype_base[hash]) {
		if (++hash >= PTYPE_HASH_SIZE)
			return NULL;
		nxt = ptype_base[hash].next;
	}
found:
	return list_entry(nxt, struct packet_type, list);
}

static void ptype_seq_stop(struct seq_file *seq, void *v)
{
	rcu_read_unlock();
}

static int ptype_seq_show(struct seq_file *seq, void *v)
{
	struct packet_type *pt = v;

	if (v == SEQ_START_TOKEN)
		seq_puts(seq, "Type Device      Function\n");
	else if (pt->dev == NULL || dev_net(pt->dev) == seq_file_net(seq)) {
		if (pt->type == htons(ETH_P_ALL))
			seq_puts(seq, "ALL ");
		else
			seq_printf(seq, "%04x", ntohs(pt->type));

		seq_printf(seq, " %-8s %pF\n",
			   pt->dev ? pt->dev->name : "", pt->func);
	}

	return 0;
}

static const struct seq_operations ptype_seq_ops = {
	.start = ptype_seq_start,
	.next  = ptype_seq_next,
	.stop  = ptype_seq_stop,
	.show  = ptype_seq_show,
};

static int ptype_seq_open(struct inode *inode, struct file *file)
{
	return seq_open_net(inode, file, &ptype_seq_ops,
			sizeof(struct seq_net_private));
}

static const struct file_operations ptype_seq_fops = {
	.owner	 = THIS_MODULE,
	.open    = ptype_seq_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
	.release = seq_release_net,
static int __net_init dev_proc_net_init(struct net *net)
Linus Torvalds's avatar
Linus Torvalds committed
{
	int rc = -ENOMEM;

	if (!proc_net_fops_create(net, "dev", S_IRUGO, &dev_seq_fops))
Linus Torvalds's avatar
Linus Torvalds committed
		goto out;
	if (!proc_net_fops_create(net, "softnet_stat", S_IRUGO, &softnet_seq_fops))
Linus Torvalds's avatar
Linus Torvalds committed
		goto out_dev;
	if (!proc_net_fops_create(net, "ptype", S_IRUGO, &ptype_seq_fops))
Linus Torvalds's avatar
Linus Torvalds committed
	rc = 0;
out:
	return rc;
Linus Torvalds's avatar
Linus Torvalds committed
out_softnet:
	proc_net_remove(net, "softnet_stat");
Linus Torvalds's avatar
Linus Torvalds committed
out_dev:
Linus Torvalds's avatar
Linus Torvalds committed
	goto out;
}
static void __net_exit dev_proc_net_exit(struct net *net)
{
	wext_proc_exit(net);

	proc_net_remove(net, "ptype");
	proc_net_remove(net, "softnet_stat");
	proc_net_remove(net, "dev");
}

static struct pernet_operations __net_initdata dev_proc_ops = {
	.init = dev_proc_net_init,
	.exit = dev_proc_net_exit,
};

static int __init dev_proc_init(void)
{
	return register_pernet_subsys(&dev_proc_ops);
}
Linus Torvalds's avatar
Linus Torvalds committed
#else
#define dev_proc_init() 0
#endif	/* CONFIG_PROC_FS */


/**
 *	netdev_set_master	-	set up master/slave pair
 *	@slave: slave device
 *	@master: new master device
 *