*/
/*
+ * Changes:
+ *
+ * Mike Kershaw <dragorn@kismetwireless.net> 2005/08/14
+ * Add TUNSETLINK ioctl to set the link encapsulation
+ *
+ * Mark Smith <markzzzsmith@yahoo.com.au>
+ * Use random_ether_addr() for tap MAC address.
+ *
+ * Harald Roelle <harald.roelle@ifi.lmu.de> 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 <underley@underley.eu.org>
* Modifications for 2.3.99-pre5 kernel.
*/
-#define TUN_VER "1.5"
+#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 <maxk@qualcomm.com>"
-#include <linux/config.h>
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/poll.h>
#include <linux/fcntl.h>
#include <linux/init.h>
-#include <linux/random.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 <asm/system.h>
#include <asm/uaccess.h>
/* 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)
if (!tun->attached)
goto drop;
- /* Queue packet */
- if (!(tun->flags & TUN_ONE_QUEUE)) {
- /* Normal queueing mode.
- * Packet scheduler handles dropping. */
- if (skb_queue_len(&tun->readq) >= TUN_READQ_SIZE)
+ /* 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);
- } else {
- /* Single queue mode.
- * Driver handles dropping itself. */
- if (skb_queue_len(&tun->readq) >= dev->tx_queue_len)
+
+ /* We won't see all dropped packets individually, so overrun
+ * error is more appropriate. */
+ tun->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)
return 0;
}
-static void tun_net_mclist(struct net_device *dev)
+/** 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)
{
- /* Nothing to do for multicast filters.
- * We always accept all frames. */
- return;
+ struct tun_struct *tun = netdev_priv(dev);
+ const struct dev_mc_list *mclist;
+ int i;
+ 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: %x:%x:%x:%x:%x:%x\n",
+ dev->name,
+ mclist->dmi_addr[0], mclist->dmi_addr[1], mclist->dmi_addr[2],
+ mclist->dmi_addr[3], mclist->dmi_addr[4], mclist->dmi_addr[5]);
+ }
}
static struct net_device_stats *tun_net_stats(struct net_device *dev)
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->addr_len = 0;
dev->mtu = 1500;
- /* Type PPP seems most suitable */
- dev->type = ARPHRD_PPP;
+ /* Zero header length */
+ dev->type = ARPHRD_NONE;
dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST;
- dev->tx_queue_len = 10;
+ 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;
- /* Generate random Ethernet address. */
- *(u16 *)dev->dev_addr = htons(0x00FF);
- get_random_bytes(dev->dev_addr + sizeof(u16), 4);
-
ether_setup(dev);
+ random_ether_addr(dev->dev_addr);
+ dev->tx_queue_len = TUN_READQ_SIZE; /* We prefer our own queue length */
break;
}
}
/* 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;
DBG(KERN_INFO "%s: tun_chr_poll\n", tun->dev->name);
poll_wait(file, &tun->read_wait, wait);
-
- if (skb_queue_len(&tun->readq))
+
+ if (!skb_queue_empty(&tun->readq))
mask |= POLLIN | POLLRDNORM;
return mask;
{
struct tun_pi pi = { 0, __constant_htons(ETH_P_IP) };
struct sk_buff *skb;
- size_t len = count;
+ size_t len = count, align = 0;
if (!(tun->flags & TUN_NO_PI)) {
- if ((len -= sizeof(pi)) > len)
+ if ((len -= sizeof(pi)) > count)
return -EINVAL;
if(memcpy_fromiovec((void *)&pi, iv, sizeof(pi)))
return -EFAULT;
}
-
- if (!(skb = alloc_skb(len + 2, GFP_KERNEL))) {
+
+ if ((tun->flags & TUN_TYPE_MASK) == TUN_TAP_DEV)
+ align = NET_IP_ALIGN;
+
+ if (!(skb = alloc_skb(len + align, GFP_KERNEL))) {
tun->stats.rx_dropped++;
return -ENOMEM;
}
- skb_reserve(skb, 2);
- if (memcpy_fromiovec(skb_put(skb, len), iv, len))
+ if (align)
+ skb_reserve(skb, align);
+ if (memcpy_fromiovec(skb_put(skb, len), iv, len)) {
+ tun->stats.rx_dropped++;
+ kfree_skb(skb);
return -EFAULT;
+ }
skb->dev = tun->dev;
switch (tun->flags & TUN_TYPE_MASK) {
if (tun->flags & TUN_NOCHECKSUM)
skb->ip_summed = CHECKSUM_UNNECESSARY;
-
+
netif_rx_ni(skb);
-
+ tun->dev->last_rx = jiffies;
+
tun->stats.rx_packets++;
tun->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++)
+ for (i = 0, len = 0; i < count; i++)
len += iv[i].iov_len;
return len;
}
-/* Writev */
-static ssize_t tun_chr_writev(struct file * file, const struct iovec *iv,
- unsigned long count, loff_t *pos)
+static ssize_t tun_chr_aio_write(struct kiocb *iocb, const struct iovec *iv,
+ unsigned long count, loff_t pos)
{
- struct tun_struct *tun = file->private_data;
+ struct tun_struct *tun = iocb->ki_filp->private_data;
if (!tun)
return -EBADFD;
return tun_get_user(tun, (struct iovec *) iv, iov_total(iv, count));
}
-/* Write */
-static ssize_t tun_chr_write(struct file * file, const char * buf,
- size_t count, loff_t *pos)
-{
- struct iovec iv = { (void *) buf, count };
- return tun_chr_writev(file, &iv, 1, pos);
-}
-
/* Put packet to the user space buffer */
static __inline__ ssize_t tun_put_user(struct tun_struct *tun,
struct sk_buff *skb,
/* 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);
return total;
}
-/* Readv */
-static ssize_t tun_chr_readv(struct file *file, const struct iovec *iv,
- unsigned long count, loff_t *pos)
+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;
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 */
schedule();
continue;
}
- netif_start_queue(tun->dev);
-
- ret = tun_put_user(tun, skb, (struct iovec *) iv, len);
-
- kfree_skb(skb);
- break;
+ 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.
+ */
+ memcpy(addr, skb->data,
+ 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: %x:%x:%x:%x:%x:%x\n",
+ tun->dev->name, addr[0], addr[1], addr[2],
+ addr[3], addr[4], addr[5]);
+ ret = tun_put_user(tun, skb, (struct iovec *) iv, len);
+ kfree_skb(skb);
+ break;
+ } else {
+ DBG(KERN_DEBUG "%s: tun_chr_readv: rejected: %x:%x:%x:%x:%x:%x\n",
+ tun->dev->name, addr[0], addr[1], addr[2],
+ addr[3], addr[4], addr[5]);
+ kfree_skb(skb);
+ continue;
+ }
}
current->state = TASK_RUNNING;
return ret;
}
-/* Read */
-static ssize_t tun_chr_read(struct file * file, char * buf,
- size_t count, loff_t *pos)
-{
- struct iovec iv = { buf, count };
- return tun_chr_readv(file, &iv, 1, pos);
-}
-
static void tun_setup(struct net_device *dev)
{
struct tun_struct *tun = netdev_priv(dev);
dev->hard_start_xmit = tun_net_xmit;
dev->stop = tun_net_close;
dev->get_stats = tun_net_stats;
+ dev->ethtool_ops = &tun_ethtool_ops;
dev->destructor = free_netdev;
}
if (tun->owner != -1 &&
current->euid != tun->owner && !capable(CAP_NET_ADMIN))
return -EPERM;
- }
- else if (__dev_get_by_name(ifr->ifr_name))
+ }
+ else if (__dev_get_by_name(ifr->ifr_name))
return -EINVAL;
else {
char *name;
err = -EINVAL;
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+
/* Set dev type */
if (ifr->ifr_flags & IFF_TUN) {
/* TUN device */
/* TAP device */
flags |= TUN_TAP_DEV;
name = "tap%d";
- } else
+ } else
goto failed;
-
+
if (*ifr->ifr_name)
name = ifr->ifr_name;
tun = netdev_priv(dev);
tun->dev = dev;
tun->flags = flags;
+ /* Be promiscuous by default to maintain previous behaviour. */
+ tun->if_flags = IFF_PROMISC;
+ /* Generate random Ethernet address. */
+ *(u16 *)tun->dev_addr = htons(0x00FF);
+ get_random_bytes(tun->dev_addr + sizeof(u16), 4);
+ memset(tun->chr_filter, 0, sizeof tun->chr_filter);
tun_net_init(dev);
err = register_netdevice(tun->dev);
if (err < 0)
goto err_free_dev;
-
+
list_add(&tun->list, &tun_dev_list);
}
return err;
}
-static int tun_chr_ioctl(struct inode *inode, struct file *file,
+static int tun_chr_ioctl(struct inode *inode, struct file *file,
unsigned int cmd, unsigned long arg)
{
struct tun_struct *tun = file->private_data;
+ void __user* argp = (void __user*)arg;
+ struct ifreq ifr;
+
+ if (cmd == TUNSETIFF || _IOC_TYPE(cmd) == 0x89)
+ if (copy_from_user(&ifr, argp, sizeof ifr))
+ return -EFAULT;
if (cmd == TUNSETIFF && !tun) {
- struct ifreq ifr;
int err;
- if (copy_from_user(&ifr, (void *)arg, sizeof(ifr)))
- return -EFAULT;
ifr.ifr_name[IFNAMSIZ-1] = '\0';
rtnl_lock();
if (err)
return err;
- if (copy_to_user((void *)arg, &ifr, sizeof(ifr)))
+ if (copy_to_user(argp, &ifr, sizeof(ifr)))
return -EFAULT;
return 0;
}
DBG(KERN_INFO "%s: owner set to %d\n", tun->dev->name, tun->owner);
break;
+ case TUNSETLINK:
+ /* Only allow setting the type when the interface is down */
+ if (tun->dev->flags & IFF_UP) {
+ DBG(KERN_INFO "%s: Linktype set failed because interface is up\n",
+ tun->dev->name);
+ return -EBUSY;
+ } else {
+ tun->dev->type = (int) arg;
+ DBG(KERN_INFO "%s: linktype set to %d\n", tun->dev->name, tun->dev->type);
+ }
+ break;
+
#ifdef TUN_DEBUG
case TUNSETDEBUG:
tun->debug = arg;
break;
#endif
+ case SIOCGIFFLAGS:
+ ifr.ifr_flags = tun->if_flags;
+ if (copy_to_user( argp, &ifr, sizeof ifr))
+ return -EFAULT;
+ return 0;
+
+ case SIOCSIFFLAGS:
+ /** Set the character device's interface flags. Currently only
+ * IFF_PROMISC and IFF_ALLMULTI are used. */
+ tun->if_flags = ifr.ifr_flags;
+ DBG(KERN_INFO "%s: interface flags 0x%lx\n",
+ tun->dev->name, tun->if_flags);
+ return 0;
+
+ case SIOCGIFHWADDR:
+ memcpy(ifr.ifr_hwaddr.sa_data, tun->dev_addr,
+ min(sizeof ifr.ifr_hwaddr.sa_data, sizeof tun->dev_addr));
+ if (copy_to_user( argp, &ifr, sizeof ifr))
+ return -EFAULT;
+ return 0;
+
+ case SIOCSIFHWADDR:
+ /** Set the character device's hardware address. This is used when
+ * filtering packets being sent from the network device to the character
+ * device. */
+ memcpy(tun->dev_addr, ifr.ifr_hwaddr.sa_data,
+ min(sizeof ifr.ifr_hwaddr.sa_data, sizeof tun->dev_addr));
+ DBG(KERN_DEBUG "%s: set hardware address: %x:%x:%x:%x:%x:%x\n",
+ tun->dev->name,
+ tun->dev_addr[0], tun->dev_addr[1], tun->dev_addr[2],
+ tun->dev_addr[3], tun->dev_addr[4], tun->dev_addr[5]);
+ return 0;
+
+ case SIOCADDMULTI:
+ /** Add the specified group to the character device's multicast filter
+ * list. */
+ add_multi(tun->chr_filter, ifr.ifr_hwaddr.sa_data);
+ DBG(KERN_DEBUG "%s: add multi: %x:%x:%x:%x:%x:%x\n",
+ tun->dev->name,
+ (u8)ifr.ifr_hwaddr.sa_data[0], (u8)ifr.ifr_hwaddr.sa_data[1],
+ (u8)ifr.ifr_hwaddr.sa_data[2], (u8)ifr.ifr_hwaddr.sa_data[3],
+ (u8)ifr.ifr_hwaddr.sa_data[4], (u8)ifr.ifr_hwaddr.sa_data[5]);
+ return 0;
+
+ case SIOCDELMULTI:
+ /** Remove the specified group from the character device's multicast
+ * filter list. */
+ del_multi(tun->chr_filter, ifr.ifr_hwaddr.sa_data);
+ DBG(KERN_DEBUG "%s: del multi: %x:%x:%x:%x:%x:%x\n",
+ tun->dev->name,
+ (u8)ifr.ifr_hwaddr.sa_data[0], (u8)ifr.ifr_hwaddr.sa_data[1],
+ (u8)ifr.ifr_hwaddr.sa_data[2], (u8)ifr.ifr_hwaddr.sa_data[3],
+ (u8)ifr.ifr_hwaddr.sa_data[4], (u8)ifr.ifr_hwaddr.sa_data[5]);
+ return 0;
+
default:
return -EINVAL;
};
DBG(KERN_INFO "%s: tun_chr_fasync %d\n", tun->dev->name, on);
if ((ret = fasync_helper(fd, file, on, &tun->fasync)) < 0)
- return ret;
-
+ return ret;
+
if (on) {
- ret = f_setown(file, current->pid, 0);
+ ret = __f_setown(file, task_pid(current), PIDTYPE_PID, 0);
if (ret)
return ret;
tun->flags |= TUN_FASYNC;
- } else
+ } else
tun->flags &= ~TUN_FASYNC;
return 0;
}
static struct file_operations tun_fops = {
- .owner = THIS_MODULE,
+ .owner = THIS_MODULE,
.llseek = no_llseek,
- .read = tun_chr_read,
- .readv = tun_chr_readv,
- .write = tun_chr_write,
- .writev = tun_chr_writev,
+ .read = do_sync_read,
+ .aio_read = tun_chr_aio_read,
+ .write = do_sync_write,
+ .aio_write = tun_chr_aio_write,
.poll = tun_chr_poll,
.ioctl = tun_chr_ioctl,
.open = tun_chr_open,
.release = tun_chr_close,
- .fasync = tun_chr_fasync
+ .fasync = tun_chr_fasync
};
static struct miscdevice tun_miscdev = {
.minor = TUN_MINOR,
.name = "tun",
.fops = &tun_fops,
- .devfs_name = "net/tun",
};
-int __init tun_init(void)
+/* ethtool interface */
+
+static int tun_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+{
+ cmd->supported = 0;
+ cmd->advertising = 0;
+ cmd->speed = SPEED_10;
+ cmd->duplex = DUPLEX_FULL;
+ cmd->port = PORT_TP;
+ cmd->phy_address = 0;
+ cmd->transceiver = XCVR_INTERNAL;
+ cmd->autoneg = AUTONEG_DISABLE;
+ cmd->maxtxpkt = 0;
+ cmd->maxrxpkt = 0;
+ return 0;
+}
+
+static void tun_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
+{
+ struct tun_struct *tun = netdev_priv(dev);
+
+ strcpy(info->driver, DRV_NAME);
+ strcpy(info->version, DRV_VERSION);
+ strcpy(info->fw_version, "N/A");
+
+ switch (tun->flags & TUN_TYPE_MASK) {
+ case TUN_TUN_DEV:
+ strcpy(info->bus_info, "tun");
+ break;
+ case TUN_TAP_DEV:
+ strcpy(info->bus_info, "tap");
+ break;
+ }
+}
+
+static u32 tun_get_msglevel(struct net_device *dev)
+{
+#ifdef TUN_DEBUG
+ struct tun_struct *tun = netdev_priv(dev);
+ return tun->debug;
+#else
+ return -EOPNOTSUPP;
+#endif
+}
+
+static void tun_set_msglevel(struct net_device *dev, u32 value)
+{
+#ifdef TUN_DEBUG
+ struct tun_struct *tun = netdev_priv(dev);
+ tun->debug = value;
+#endif
+}
+
+static u32 tun_get_link(struct net_device *dev)
+{
+ struct tun_struct *tun = netdev_priv(dev);
+ return tun->attached;
+}
+
+static u32 tun_get_rx_csum(struct net_device *dev)
+{
+ struct tun_struct *tun = netdev_priv(dev);
+ return (tun->flags & TUN_NOCHECKSUM) == 0;
+}
+
+static int tun_set_rx_csum(struct net_device *dev, u32 data)
+{
+ struct tun_struct *tun = netdev_priv(dev);
+ if (data)
+ tun->flags &= ~TUN_NOCHECKSUM;
+ else
+ tun->flags |= TUN_NOCHECKSUM;
+ return 0;
+}
+
+static const struct ethtool_ops tun_ethtool_ops = {
+ .get_settings = tun_get_settings,
+ .get_drvinfo = tun_get_drvinfo,
+ .get_msglevel = tun_get_msglevel,
+ .set_msglevel = tun_set_msglevel,
+ .get_link = tun_get_link,
+ .get_rx_csum = tun_get_rx_csum,
+ .set_rx_csum = tun_set_rx_csum
+};
+
+static int __init tun_init(void)
{
int ret = 0;
- printk(KERN_INFO "Universal TUN/TAP device driver %s "
- "(C)1999-2002 Maxim Krasnyansky\n", TUN_VER);
+ printk(KERN_INFO "tun: %s, %s\n", DRV_DESCRIPTION, DRV_VERSION);
+ printk(KERN_INFO "tun: %s\n", DRV_COPYRIGHT);
ret = misc_register(&tun_miscdev);
if (ret)
return ret;
}
-void tun_cleanup(void)
+static void tun_cleanup(void)
{
struct tun_struct *tun, *nxt;
- misc_deregister(&tun_miscdev);
+ misc_deregister(&tun_miscdev);
rtnl_lock();
list_for_each_entry_safe(tun, nxt, &tun_dev_list, list) {
unregister_netdevice(tun->dev);
}
rtnl_unlock();
-
+
}
module_init(tun_init);
module_exit(tun_cleanup);
+MODULE_DESCRIPTION(DRV_DESCRIPTION);
+MODULE_AUTHOR(DRV_COPYRIGHT);
MODULE_LICENSE("GPL");
MODULE_ALIAS_MISCDEV(TUN_MINOR);