tun.c

来自「linux 内核源代码」· C语言 代码 · 共 913 行 · 第 1/2 页

/*
 *  TUN - Universal TUN/TAP device driver.
 *  Copyright (C) 1999-2002 Maxim Krasnyansky <[e-mail]>
 *
 *  This program is free software; you can redistribute it and/or modify
 *  it under the terms of the GNU General Public License as published by
 *  the Free Software Foundation; either version 2 of the License, or
 *  (at your option) any later version.
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
 *  GNU General Public License for more details.
 *
 *  $Id: tun.c,v 1.15 2002/03/01 02:44:24 maxk Exp $
 */

/*
 *  Changes:
 *
 *  Brian Braunstein <[e-mail]> 2007/03/23
 *    Fixed hw address handling.  Now net_device.dev_addr is kept consistent
 *    with tun.dev_addr when the address is set by this module.
 *
 *  Mike Kershaw <[e-mail]> 2005/08/14
 *    Add TUNSETLINK ioctl to set the link encapsulation
 *
 *  Mark Smith <[e-mail]>
 *   Use random_ether_addr() for tap MAC address.
 *
 *  Harald Roelle <[e-mail]>  2004/04/20
 *    Fixes in packet dropping, queue length setting and queue wakeup.
 *    Increased default tx queue length.
 *    Added ethtool API.
 *    Minor cleanups
 *
 *  Daniel Podlejski <[e-mail]>
 *    Modifications for 2.3.99-pre5 kernel.
 */

#define DRV_NAME	"tun"
#define DRV_VERSION	"1.6"
#define DRV_DESCRIPTION	"Universal TUN/TAP device driver"
#define DRV_COPYRIGHT	"(C) 1999-2004 Max Krasnyansky <[e-mail]>"

#include <linux/module.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/major.h>
#include <linux/slab.h>
#include <linux/poll.h>
#include <linux/fcntl.h>
#include <linux/init.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/miscdevice.h>
#include <linux/ethtool.h>
#include <linux/rtnetlink.h>
#include <linux/if.h>
#include <linux/if_arp.h>
#include <linux/if_ether.h>
#include <linux/if_tun.h>
#include <linux/crc32.h>
#include <net/net_namespace.h>

#include <asm/system.h>
#include <asm/uaccess.h>

#ifdef TUN_DEBUG
static int debug;
#endif

/* Network device part of the driver */

static LIST_HEAD(tun_dev_list);
static const struct ethtool_ops tun_ethtool_ops;

/* Net device open. */
static int tun_net_open(struct net_device *dev)
{
	netif_start_queue(dev);
	return 0;
}

/* Net device close. */
static int tun_net_close(struct net_device *dev)
{
	netif_stop_queue(dev);
	return 0;
}

/* Net device start xmit */
static int tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct tun_struct *tun = netdev_priv(dev);

	DBG(KERN_INFO "%s: tun_net_xmit %d\n", tun->dev->name, skb->len);

	/* Drop packet if interface is not attached */
	if (!tun->attached)
		goto drop;

	/* Packet dropping */
	if (skb_queue_len(&tun->readq) >= dev->tx_queue_len) {
		if (!(tun->flags & TUN_ONE_QUEUE)) {
			/* Normal queueing mode. */
			/* Packet scheduler handles dropping of further packets. */
			netif_stop_queue(dev);

			/* We won't see all dropped packets individually, so overrun
			 * error is more appropriate. */
			dev->stats.tx_fifo_errors++;
		} else {
			/* Single queue mode.
			 * Driver handles dropping of all packets itself. */
			goto drop;
		}
	}

	/* Queue packet */
	skb_queue_tail(&tun->readq, skb);
	dev->trans_start = jiffies;

	/* Notify and wake up reader process */
	if (tun->flags & TUN_FASYNC)
		kill_fasync(&tun->fasync, SIGIO, POLL_IN);
	wake_up_interruptible(&tun->read_wait);
	return 0;

drop:
	dev->stats.tx_dropped++;
	kfree_skb(skb);
	return 0;
}

/** Add the specified Ethernet address to this multicast filter. */
static void
add_multi(u32* filter, const u8* addr)
{
	int bit_nr = ether_crc(ETH_ALEN, addr) >> 26;
	filter[bit_nr >> 5] |= 1 << (bit_nr & 31);
}

/** Remove the specified Ethernet addres from this multicast filter. */
static void
del_multi(u32* filter, const u8* addr)
{
	int bit_nr = ether_crc(ETH_ALEN, addr) >> 26;
	filter[bit_nr >> 5] &= ~(1 << (bit_nr & 31));
}

/** Update the list of multicast groups to which the network device belongs.
 * This list is used to filter packets being sent from the character device to
 * the network device. */
static void
tun_net_mclist(struct net_device *dev)
{
	struct tun_struct *tun = netdev_priv(dev);
	const struct dev_mc_list *mclist;
	int i;
	DECLARE_MAC_BUF(mac);
	DBG(KERN_DEBUG "%s: tun_net_mclist: mc_count %d\n",
			dev->name, dev->mc_count);
	memset(tun->chr_filter, 0, sizeof tun->chr_filter);
	for (i = 0, mclist = dev->mc_list; i < dev->mc_count && mclist != NULL;
			i++, mclist = mclist->next) {
		add_multi(tun->net_filter, mclist->dmi_addr);
		DBG(KERN_DEBUG "%s: tun_net_mclist: %s\n",
		    dev->name, print_mac(mac, mclist->dmi_addr));
	}
}

#define MIN_MTU 68
#define MAX_MTU 65535

static int
tun_net_change_mtu(struct net_device *dev, int new_mtu)
{
	if (new_mtu < MIN_MTU || new_mtu + dev->hard_header_len > MAX_MTU)
		return -EINVAL;
	dev->mtu = new_mtu;
	return 0;
}

/* Initialize net device. */
static void tun_net_init(struct net_device *dev)
{
	struct tun_struct *tun = netdev_priv(dev);

	switch (tun->flags & TUN_TYPE_MASK) {
	case TUN_TUN_DEV:
		/* Point-to-Point TUN Device */
		dev->hard_header_len = 0;
		dev->addr_len = 0;
		dev->mtu = 1500;
		dev->change_mtu = tun_net_change_mtu;

		/* Zero header length */
		dev->type = ARPHRD_NONE;
		dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST;
		dev->tx_queue_len = TUN_READQ_SIZE;  /* We prefer our own queue length */
		break;

	case TUN_TAP_DEV:
		/* Ethernet TAP Device */
		dev->set_multicast_list = tun_net_mclist;

		ether_setup(dev);
		dev->change_mtu = tun_net_change_mtu;

		/* random address already created for us by tun_set_iff, use it */
		memcpy(dev->dev_addr, tun->dev_addr, min(sizeof(tun->dev_addr), sizeof(dev->dev_addr)) );

		dev->tx_queue_len = TUN_READQ_SIZE;  /* We prefer our own queue length */
		break;
	}
}

/* Character device part */

/* Poll */
static unsigned int tun_chr_poll(struct file *file, poll_table * wait)
{
	struct tun_struct *tun = file->private_data;
	unsigned int mask = POLLOUT | POLLWRNORM;

	if (!tun)
		return -EBADFD;

	DBG(KERN_INFO "%s: tun_chr_poll\n", tun->dev->name);

	poll_wait(file, &tun->read_wait, wait);

	if (!skb_queue_empty(&tun->readq))
		mask |= POLLIN | POLLRDNORM;

	return mask;
}

/* Get packet from user space buffer */
static __inline__ ssize_t tun_get_user(struct tun_struct *tun, struct iovec *iv, size_t count)
{
	struct tun_pi pi = { 0, __constant_htons(ETH_P_IP) };
	struct sk_buff *skb;
	size_t len = count, align = 0;

	if (!(tun->flags & TUN_NO_PI)) {
		if ((len -= sizeof(pi)) > count)
			return -EINVAL;

		if(memcpy_fromiovec((void *)&pi, iv, sizeof(pi)))
			return -EFAULT;
	}

	if ((tun->flags & TUN_TYPE_MASK) == TUN_TAP_DEV)
		align = NET_IP_ALIGN;

	if (!(skb = alloc_skb(len + align, GFP_KERNEL))) {
		tun->dev->stats.rx_dropped++;
		return -ENOMEM;
	}

	if (align)
		skb_reserve(skb, align);
	if (memcpy_fromiovec(skb_put(skb, len), iv, len)) {
		tun->dev->stats.rx_dropped++;
		kfree_skb(skb);
		return -EFAULT;
	}

	switch (tun->flags & TUN_TYPE_MASK) {
	case TUN_TUN_DEV:
		skb_reset_mac_header(skb);
		skb->protocol = pi.proto;
		skb->dev = tun->dev;
		break;
	case TUN_TAP_DEV:
		skb->protocol = eth_type_trans(skb, tun->dev);
		break;
	};

	if (tun->flags & TUN_NOCHECKSUM)
		skb->ip_summed = CHECKSUM_UNNECESSARY;

	netif_rx_ni(skb);
	tun->dev->last_rx = jiffies;

	tun->dev->stats.rx_packets++;
	tun->dev->stats.rx_bytes += len;

	return count;
}

static inline size_t iov_total(const struct iovec *iv, unsigned long count)
{
	unsigned long i;
	size_t len;

	for (i = 0, len = 0; i < count; i++)
		len += iv[i].iov_len;

	return len;
}

static ssize_t tun_chr_aio_write(struct kiocb *iocb, const struct iovec *iv,
			      unsigned long count, loff_t pos)
{
	struct tun_struct *tun = iocb->ki_filp->private_data;

	if (!tun)
		return -EBADFD;

	DBG(KERN_INFO "%s: tun_chr_write %ld\n", tun->dev->name, count);

	return tun_get_user(tun, (struct iovec *) iv, iov_total(iv, count));
}

/* Put packet to the user space buffer */
static __inline__ ssize_t tun_put_user(struct tun_struct *tun,
				       struct sk_buff *skb,
				       struct iovec *iv, int len)
{
	struct tun_pi pi = { 0, skb->protocol };
	ssize_t total = 0;

	if (!(tun->flags & TUN_NO_PI)) {
		if ((len -= sizeof(pi)) < 0)
			return -EINVAL;

		if (len < skb->len) {
			/* Packet will be striped */
			pi.flags |= TUN_PKT_STRIP;
		}

		if (memcpy_toiovec(iv, (void *) &pi, sizeof(pi)))
			return -EFAULT;
		total += sizeof(pi);
	}

	len = min_t(int, skb->len, len);

	skb_copy_datagram_iovec(skb, 0, iv, len);
	total += len;

	tun->dev->stats.tx_packets++;
	tun->dev->stats.tx_bytes += len;

	return total;
}

static ssize_t tun_chr_aio_read(struct kiocb *iocb, const struct iovec *iv,
			    unsigned long count, loff_t pos)
{
	struct file *file = iocb->ki_filp;
	struct tun_struct *tun = file->private_data;
	DECLARE_WAITQUEUE(wait, current);
	struct sk_buff *skb;
	ssize_t len, ret = 0;
	DECLARE_MAC_BUF(mac);

	if (!tun)
		return -EBADFD;

	DBG(KERN_INFO "%s: tun_chr_read\n", tun->dev->name);

	len = iov_total(iv, count);
	if (len < 0)
		return -EINVAL;

	add_wait_queue(&tun->read_wait, &wait);
	while (len) {
		const u8 ones[ ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
		u8 addr[ ETH_ALEN];
		int bit_nr;

		current->state = TASK_INTERRUPTIBLE;

		/* Read frames from the queue */
		if (!(skb=skb_dequeue(&tun->readq))) {
			if (file->f_flags & O_NONBLOCK) {
				ret = -EAGAIN;
				break;
			}
			if (signal_pending(current)) {
				ret = -ERESTARTSYS;
				break;
			}

			/* Nothing to read, let's sleep */
			schedule();
			continue;
		}
		netif_wake_queue(tun->dev);

		/** Decide whether to accept this packet. This code is designed to
		 * behave identically to an Ethernet interface. Accept the packet if
		 * - we are promiscuous.
		 * - the packet is addressed to us.
		 * - the packet is broadcast.
		 * - the packet is multicast and
		 *   - we are multicast promiscous.
		 *   - we belong to the multicast group.
		 */
		skb_copy_from_linear_data(skb, addr, min_t(size_t, sizeof addr,
								   skb->len));
		bit_nr = ether_crc(sizeof addr, addr) >> 26;
		if ((tun->if_flags & IFF_PROMISC) ||
				memcmp(addr, tun->dev_addr, sizeof addr) == 0 ||
				memcmp(addr, ones, sizeof addr) == 0 ||
				(((addr[0] == 1 && addr[1] == 0 && addr[2] == 0x5e) ||
				  (addr[0] == 0x33 && addr[1] == 0x33)) &&
				 ((tun->if_flags & IFF_ALLMULTI) ||
				  (tun->chr_filter[bit_nr >> 5] & (1 << (bit_nr & 31)))))) {
			DBG(KERN_DEBUG "%s: tun_chr_readv: accepted: %s\n",
					tun->dev->name, print_mac(mac, addr));
			ret = tun_put_user(tun, skb, (struct iovec *) iv, len);
			kfree_skb(skb);
			break;
		} else {
			DBG(KERN_DEBUG "%s: tun_chr_readv: rejected: %s\n",
					tun->dev->name, print_mac(mac, addr));
			kfree_skb(skb);
			continue;
		}
	}

	current->state = TASK_RUNNING;
	remove_wait_queue(&tun->read_wait, &wait);

	return ret;
}

static void tun_setup(struct net_device *dev)
{
	struct tun_struct *tun = netdev_priv(dev);

	skb_queue_head_init(&tun->readq);
	init_waitqueue_head(&tun->read_wait);

	tun->owner = -1;
	tun->group = -1;

	dev->open = tun_net_open;
	dev->hard_start_xmit = tun_net_xmit;
	dev->stop = tun_net_close;
	dev->ethtool_ops = &tun_ethtool_ops;
	dev->destructor = free_netdev;
}

static struct tun_struct *tun_get_by_name(const char *name)
{
	struct tun_struct *tun;

	ASSERT_RTNL();
	list_for_each_entry(tun, &tun_dev_list, list) {
		if (!strncmp(tun->dev->name, name, IFNAMSIZ))