Skip to content
Snippets Groups Projects
dev.c 114 KiB
Newer Older
}
#else
#define handle_macvlan(skb, pt_prev, ret, orig_dev)	(skb)
#endif

Linus Torvalds's avatar
Linus Torvalds committed
#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
Linus Torvalds's avatar
Linus Torvalds committed
 * the ingress scheduler, you just cant add policies on ingress.
 *
 */
static int ing_filter(struct sk_buff *skb)
Linus Torvalds's avatar
Linus Torvalds committed
{
	struct Qdisc *q;
	struct net_device *dev = skb->dev;
	int result = TC_ACT_OK;
	u32 ttl = G_TC_RTTL(skb->tc_verd);
	if (MAX_RED_LOOP < ttl++) {
		printk(KERN_WARNING
		       "Redir loop detected Dropping packet (%d->%d)\n",
		       skb->iif, dev->ifindex);
		return TC_ACT_SHOT;
	}
Linus Torvalds's avatar
Linus Torvalds committed

	skb->tc_verd = SET_TC_RTTL(skb->tc_verd, ttl);
	skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS);
Linus Torvalds's avatar
Linus Torvalds committed

	spin_lock(&dev->ingress_lock);
	if ((q = dev->qdisc_ingress) != NULL)
		result = q->enqueue(skb, q);
	spin_unlock(&dev->ingress_lock);

	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->qdisc_ingress)
		goto out;
Linus Torvalds's avatar
Linus Torvalds committed

	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;
Linus Torvalds's avatar
Linus Torvalds committed
}
#endif

/**
 *	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
 */
Linus Torvalds's avatar
Linus Torvalds committed
int netif_receive_skb(struct sk_buff *skb)
{
	struct packet_type *ptype, *pt_prev;
	struct net_device *orig_dev;
Linus Torvalds's avatar
Linus Torvalds committed
	int ret = NET_RX_DROP;
Al Viro's avatar
Al Viro committed
	__be16 type;
Linus Torvalds's avatar
Linus Torvalds committed

	/* if we've gotten here through NAPI, check netpoll */
Linus Torvalds's avatar
Linus Torvalds committed
		return NET_RX_DROP;

	if (!skb->tstamp.tv64)
Linus Torvalds's avatar
Linus Torvalds committed

	if (!skb->iif)
		skb->iif = skb->dev->ifindex;
	orig_dev = skb_bond(skb);
Linus Torvalds's avatar
Linus Torvalds committed

	if (!orig_dev)
		return NET_RX_DROP;

Linus Torvalds's avatar
Linus Torvalds committed
	__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;
Linus Torvalds's avatar
Linus Torvalds committed

	pt_prev = NULL;

	rcu_read_lock();

	/* Don't receive packets in an exiting network namespace */
	if (!net_alive(dev_net(skb->dev)))
		goto out;

Linus Torvalds's avatar
Linus Torvalds committed
#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 || ptype->dev == skb->dev) {
				ret = deliver_skb(skb, pt_prev, orig_dev);
Linus Torvalds's avatar
Linus Torvalds committed
			pt_prev = ptype;
		}
	}

#ifdef CONFIG_NET_CLS_ACT
	skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
	if (!skb)
Linus Torvalds's avatar
Linus Torvalds committed
		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);
Linus Torvalds's avatar
Linus Torvalds committed
		goto out;

	type = skb->protocol;
	list_for_each_entry_rcu(ptype,
			&ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) {
Linus Torvalds's avatar
Linus Torvalds committed
		if (ptype->type == type &&
		    (!ptype->dev || ptype->dev == skb->dev)) {
				ret = deliver_skb(skb, pt_prev, orig_dev);
Linus Torvalds's avatar
Linus Torvalds committed
			pt_prev = ptype;
		}
	}

	if (pt_prev) {
		ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
Linus Torvalds's avatar
Linus Torvalds committed
	} 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;
}

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

Linus Torvalds's avatar
Linus Torvalds committed
		struct sk_buff *skb;
		struct net_device *dev;

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

Linus Torvalds's avatar
Linus Torvalds committed
		local_irq_enable();

		dev = skb->dev;

		netif_receive_skb(skb);

		dev_put(dev);
	} while (++work < quota && jiffies == start_time);
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

	local_irq_save(flags);
	list_add_tail(&n->poll_list, &__get_cpu_var(softnet_data).poll_list);
	__raise_softirq_irqoff(NET_RX_SOFTIRQ);
	local_irq_restore(flags);
Linus Torvalds's avatar
Linus Torvalds committed
}
Linus Torvalds's avatar
Linus Torvalds committed

static void net_rx_action(struct softirq_action *h)
{
	struct list_head *list = &__get_cpu_var(softnet_data).poll_list;
Linus Torvalds's avatar
Linus Torvalds committed
	unsigned long start_time = jiffies;
	int budget = netdev_budget;
Linus Torvalds's avatar
Linus Torvalds committed
	local_irq_disable();

	while (!list_empty(list)) {
		struct napi_struct *n;
		int work, weight;
Linus Torvalds's avatar
Linus Torvalds committed

		/* If softirq window is exhuasted then punt.
		 *
		 * Note that this is a slight policy change from the
		 * previous NAPI code, which would allow up to 2
		 * jiffies to pass before breaking out.  The test
		 * used to be "jiffies - start_time > 1".
		 */
		if (unlikely(budget <= 0 || jiffies != start_time))
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_entry(list->next, 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)))
				__napi_complete(n);
			else
				list_move_tail(&n->poll_list, list);
		}
Linus Torvalds's avatar
Linus Torvalds committed
	}
out:
#ifdef CONFIG_NET_DMA
	/*
	 * There may not be any more sk_buffs coming right now, so push
	 * any pending DMA copies to hardware
	 */
	if (!cpus_empty(net_dma.channel_mask)) {
		int chan_idx;
		for_each_cpu_mask(chan_idx, net_dma.channel_mask) {
			struct dma_chan *chan = net_dma.channels[chan_idx];
			if (chan)
				dma_async_memcpy_issue_pending(chan);
		}
Linus Torvalds's avatar
Linus Torvalds committed
	return;

softnet_break:
	__get_cpu_var(netdev_rx_stat).time_squeeze++;
	__raise_softirq_irqoff(NET_RX_SOFTIRQ);
	goto out;
}

static gifconf_func_t * gifconf_list [NPROTO];

/**
 *	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)
{
	if (family >= NPROTO)
		return -EINVAL;
	gifconf_list[family] = gifconf;
	return 0;
}


/*
 *	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;

	read_lock(&dev_base_lock);
	dev = __dev_get_by_index(net, ifr.ifr_ifindex);
Linus Torvalds's avatar
Linus Torvalds committed
	if (!dev) {
		read_unlock(&dev_base_lock);
		return -ENODEV;
	}

	strcpy(ifr.ifr_name, dev->name);
	read_unlock(&dev_base_lock);

	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)
	__acquires(dev_base_lock)
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;

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

		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 *net = seq_file_net(seq);
Linus Torvalds's avatar
Linus Torvalds committed
	++*pos;
	return v == SEQ_START_TOKEN ?
		first_net_device(net) : next_net_device((struct net_device *)v);
Linus Torvalds's avatar
Linus Torvalds committed
}

void dev_seq_stop(struct seq_file *seq, void *v)
	__releases(dev_base_lock)
Linus Torvalds's avatar
Linus Torvalds committed
{
	read_unlock(&dev_base_lock);
}

static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev)
{
	struct net_device_stats *stats = dev->get_stats(dev);
Linus Torvalds's avatar
Linus Torvalds committed

	seq_printf(seq, "%6s:%8lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu "
		   "%8lu %7lu %4lu %4lu %4lu %5lu %7lu %10lu\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;
}

static struct netif_rx_stats *softnet_get_online(loff_t *pos)
{
	struct netif_rx_stats *rc = NULL;

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

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)
{
	struct netif_rx_stats *s = v;

	seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
		   s->total, s->dropped, s->time_squeeze, 0,
		   0, 0, 0, 0, /* was fastroute */
		   s->cpu_collision );
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 void ptype_seq_decode(struct seq_file *seq, void *sym)
{
#ifdef CONFIG_KALLSYMS
	unsigned long offset = 0, symsize;
	const char *symname;
	char *modname;
	char namebuf[128];

	symname = kallsyms_lookup((unsigned long)sym, &symsize, &offset,
				  &modname, namebuf);

	if (symname) {
		char *delim = ":";

		if (!modname)
			modname = delim = "";
		seq_printf(seq, "%s%s%s%s+0x%lx", delim, modname, delim,
			   symname, offset);
		return;
	}
#endif

	seq_printf(seq, "[%p]", sym);
}

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 ",
			   pt->dev ? pt->dev->name : "");
		ptype_seq_decode(seq,  pt->func);
		seq_putc(seq, '\n');
	}

	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
 *
 *	Changes the master device of the slave. Pass %NULL to break the
 *	bonding. The caller must hold the RTNL semaphore. On a failure
 *	a negative errno code is returned. On success the reference counts
 *	are adjusted, %RTM_NEWLINK is sent to the routing socket and the
 *	function returns zero.
 */
int netdev_set_master(struct net_device *slave, struct net_device *master)
{
	struct net_device *old = slave->master;

	ASSERT_RTNL();

	if (master) {
		if (old)
			return -EBUSY;
		dev_hold(master);
	}

	slave->master = master;
Linus Torvalds's avatar
Linus Torvalds committed
	synchronize_net();

	if (old)
		dev_put(old);

	if (master)
		slave->flags |= IFF_SLAVE;
	else
		slave->flags &= ~IFF_SLAVE;

	rtmsg_ifinfo(RTM_NEWLINK, slave, IFF_SLAVE);
	return 0;
}

static int __dev_set_promiscuity(struct net_device *dev, int inc)
Linus Torvalds's avatar
Linus Torvalds committed
{
	unsigned short old_flags = dev->flags;

	dev->flags |= IFF_PROMISC;
	dev->promiscuity += inc;
	if (dev->promiscuity == 0) {
		/*
		 * Avoid overflow.
		 * If inc causes overflow, untouch promisc and return error.
		 */
		if (inc < 0)
			dev->flags &= ~IFF_PROMISC;
		else {
			dev->promiscuity -= inc;
			printk(KERN_WARNING "%s: promiscuity touches roof, "
				"set promiscuity failed, promiscuity feature "
				"of device might be broken.\n", dev->name);
			return -EOVERFLOW;
		}
	}
Linus Torvalds's avatar
Linus Torvalds committed
		printk(KERN_INFO "device %s %s promiscuous mode\n",
		       dev->name, (dev->flags & IFF_PROMISC) ? "entered" :
		if (audit_enabled)
			audit_log(current->audit_context, GFP_ATOMIC,
				AUDIT_ANOM_PROMISCUOUS,
				"dev=%s prom=%d old_prom=%d auid=%u uid=%u gid=%u ses=%u",
				dev->name, (dev->flags & IFF_PROMISC),
				(old_flags & IFF_PROMISC),
				audit_get_loginuid(current),
				current->uid, current->gid,
				audit_get_sessionid(current));

		if (dev->change_rx_flags)
			dev->change_rx_flags(dev, IFF_PROMISC);
Linus Torvalds's avatar
Linus Torvalds committed
	}
/**
 *	dev_set_promiscuity	- update promiscuity count on a device
 *	@dev: device
 *	@inc: modifier
 *
 *	Add or remove promiscuity from a device. While the count in the device
 *	remains above zero the interface remains promiscuous. Once it hits zero
 *	the device reverts back to normal filtering operation. A negative inc
 *	value is used to drop promiscuity on the device.
 *	Return 0 if successful or a negative errno code on error.
int dev_set_promiscuity(struct net_device *dev, int inc)
{
	unsigned short old_flags = dev->flags;
	err = __dev_set_promiscuity(dev, inc);
	if (dev->flags != old_flags)
		dev_set_rx_mode(dev);
Linus Torvalds's avatar
Linus Torvalds committed
/**
 *	dev_set_allmulti	- update allmulti count on a device
 *	@dev: device
 *	@inc: modifier
 *
 *	Add or remove reception of all multicast frames to a device. While the
 *	count in the device remains above zero the interface remains listening
 *	to all interfaces. Once it hits zero the device reverts back to normal
 *	filtering operation. A negative @inc value is used to drop the counter
 *	when releasing a resource needing all multicasts.
 *	Return 0 if successful or a negative errno code on error.
int dev_set_allmulti(struct net_device *dev, int inc)
Linus Torvalds's avatar
Linus Torvalds committed
{
	unsigned short old_flags = dev->flags;

Linus Torvalds's avatar
Linus Torvalds committed
	dev->flags |= IFF_ALLMULTI;
	dev->allmulti += inc;
	if (dev->allmulti == 0) {
		/*
		 * Avoid overflow.
		 * If inc causes overflow, untouch allmulti and return error.
		 */
		if (inc < 0)
			dev->flags &= ~IFF_ALLMULTI;
		else {
			dev->allmulti -= inc;
			printk(KERN_WARNING "%s: allmulti touches roof, "
				"set allmulti failed, allmulti feature of "
				"device might be broken.\n", dev->name);
			return -EOVERFLOW;
		}
	}
	if (dev->flags ^ old_flags) {
		if (dev->change_rx_flags)
			dev->change_rx_flags(dev, IFF_ALLMULTI);
		dev_set_rx_mode(dev);
}

/*
 *	Upload unicast and multicast address lists to device and
 *	configure RX filtering. When the device doesn't support unicast
 *	filtering it is put in promiscuous mode while unicast addresses
 *	are present.
 */
void __dev_set_rx_mode(struct net_device *dev)
{
	/* dev_open will call this function so the list will stay sane. */
	if (!(dev->flags&IFF_UP))
		return;

	if (!netif_device_present(dev))

	if (dev->set_rx_mode)
		dev->set_rx_mode(dev);
	else {
		/* Unicast addresses changes may only happen under the rtnl,
		 * therefore calling __dev_set_promiscuity here is safe.
		 */
		if (dev->uc_count > 0 && !dev->uc_promisc) {
			__dev_set_promiscuity(dev, 1);
			dev->uc_promisc = 1;
		} else if (dev->uc_count == 0 && dev->uc_promisc) {
			__dev_set_promiscuity(dev, -1);
			dev->uc_promisc = 0;
		}

		if (dev->set_multicast_list)
			dev->set_multicast_list(dev);
	}
}

void dev_set_rx_mode(struct net_device *dev)
{
	netif_tx_lock_bh(dev);
	__dev_set_rx_mode(dev);
	netif_tx_unlock_bh(dev);
int __dev_addr_delete(struct dev_addr_list **list, int *count,
		      void *addr, int alen, int glbl)
{
	struct dev_addr_list *da;

	for (; (da = *list) != NULL; list = &da->next) {
		if (memcmp(da->da_addr, addr, da->da_addrlen) == 0 &&
		    alen == da->da_addrlen) {
			if (glbl) {
				int old_glbl = da->da_gusers;
				da->da_gusers = 0;
				if (old_glbl == 0)
					break;
			}
			if (--da->da_users)
				return 0;

			*list = da->next;
			kfree(da);
int __dev_addr_add(struct dev_addr_list **list, int *count,
		   void *addr, int alen, int glbl)
{
	struct dev_addr_list *da;

	for (da = *list; da != NULL; da = da->next) {
		if (memcmp(da->da_addr, addr, da->da_addrlen) == 0 &&
		    da->da_addrlen == alen) {
			if (glbl) {
				int old_glbl = da->da_gusers;
				da->da_gusers = 1;
				if (old_glbl)
					return 0;
			}
			da->da_users++;
			return 0;