dev.c

linux 内核源代码

	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;
}

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

	napi->weight = weight_p;
	do {
		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;
		}

		local_irq_enable();

		dev = skb->dev;

		netif_receive_skb(skb);

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

	return work;
}

/**
 * __napi_schedule - schedule for receive
 * @n: entry to schedule
 *
 * The entry's receive function will be scheduled to run
 */
void fastcall __napi_schedule(struct napi_struct *n)
{
	unsigned long flags;

	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);
}
EXPORT_SYMBOL(__napi_schedule);


static void net_rx_action(struct softirq_action *h)
{
	struct list_head *list = &__get_cpu_var(softnet_data).poll_list;
	unsigned long start_time = jiffies;
	int budget = netdev_budget;
	void *have;

	local_irq_disable();

	while (!list_empty(list)) {
		struct napi_struct *n;
		int work, weight;

		/* 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))
			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);

		have = netpoll_poll_lock(n);

		weight = n->weight;

		/* 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);
		}

		netpoll_poll_unlock(have);
	}
out:
	local_irq_enable();

#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);
		}
	}
#endif

	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)
{
	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);
	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)
{
	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;
	for_each_netdev(net, dev) {
		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;
			}
		}
	}

	/*
	 *	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)
{
	struct net *net = seq->private;
	loff_t off;
	struct net_device *dev;

	read_lock(&dev_base_lock);
	if (!*pos)
		return SEQ_START_TOKEN;

	off = 1;
	for_each_netdev(net, dev)
		if (off++ == *pos)
			return dev;

	return NULL;
}

void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct net *net = seq->private;
	++*pos;
	return v == SEQ_START_TOKEN ?
		first_net_device(net) : next_net_device((struct net_device *)v);
}

void dev_seq_stop(struct seq_file *seq, void *v)
{
	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);

	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);
}

/*
 *	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_CPUS)
		if (cpu_online(*pos)) {
			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 );
	return 0;
}

static const struct seq_operations dev_seq_ops = {
	.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)
{
	struct seq_file *seq;
	int res;
	res =  seq_open(file, &dev_seq_ops);
	if (!res) {
		seq = file->private_data;
		seq->private = get_proc_net(inode);
		if (!seq->private) {
			seq_release(inode, file);
			res = -ENXIO;
		}
	}
	return res;
}

static int dev_seq_release(struct inode *inode, struct file *file)
{
	struct seq_file *seq = file->private_data;
	struct net *net = seq->private;
	put_net(net);
	return seq_release(inode, file);
}

static const struct file_operations dev_seq_fops = {
	.owner	 = THIS_MODULE,
	.open    = dev_seq_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
	.release = dev_seq_release,
};

static const struct seq_operations softnet_seq_ops = {
	.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 = {
	.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 < 16; 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) & 15;

	while (nxt == &ptype_base[hash]) {
		if (++hash >= 16)
			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 (sym