#include <linux/kernel.h>
#include <linux/major.h>
#include <linux/slab.h>
-#include <linux/smp_lock.h>
#include <linux/poll.h>
#include <linux/fcntl.h>
#include <linux/init.h>
#include <linux/miscdevice.h>
#include <linux/ethtool.h>
#include <linux/rtnetlink.h>
+#include <linux/compat.h>
#include <linux/if.h>
#include <linux/if_arp.h>
#include <linux/if_ether.h>
atomic_t count;
struct tun_struct *tun;
struct net *net;
- wait_queue_head_t read_wait;
};
struct tun_sock;
uid_t owner;
gid_t group;
- struct sk_buff_head readq;
-
struct net_device *dev;
struct fasync_struct *fasync;
struct tap_filter txflt;
- struct sock *sk;
struct socket socket;
#ifdef TUN_DEBUG
static int tun_attach(struct tun_struct *tun, struct file *file)
{
struct tun_file *tfile = file->private_data;
- const struct cred *cred = current_cred();
int err;
ASSERT_RTNL();
- /* Check permissions */
- if (((tun->owner != -1 && cred->euid != tun->owner) ||
- (tun->group != -1 && !in_egroup_p(tun->group))) &&
- !capable(CAP_NET_ADMIN))
- return -EPERM;
-
netif_tx_lock_bh(tun->dev);
err = -EINVAL;
tfile->tun = tun;
tun->tfile = tfile;
dev_hold(tun->dev);
- sock_hold(tun->sk);
+ sock_hold(tun->socket.sk);
atomic_inc(&tfile->count);
out:
netif_tx_unlock_bh(tun->dev);
/* Drop read queue */
- skb_queue_purge(&tun->readq);
+ skb_queue_purge(&tun->socket.sk->sk_receive_queue);
/* Drop the extra count on the net device */
dev_put(tun->dev);
/* Inform the methods they need to stop using the dev.
*/
if (tfile) {
- wake_up_all(&tfile->read_wait);
+ wake_up_all(&tun->socket.wait);
if (atomic_dec_and_test(&tfile->count))
__tun_detach(tun);
}
{
struct tun_struct *tun = netdev_priv(dev);
- sock_put(tun->sk);
+ sock_put(tun->socket.sk);
}
/* Net device open. */
}
/* Net device start xmit */
-static int tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct tun_struct *tun = netdev_priv(dev);
if (!check_filter(&tun->txflt, skb))
goto drop;
- if (skb_queue_len(&tun->readq) >= dev->tx_queue_len) {
+ if (skb_queue_len(&tun->socket.sk->sk_receive_queue) >= dev->tx_queue_len) {
if (!(tun->flags & TUN_ONE_QUEUE)) {
/* Normal queueing mode. */
/* Packet scheduler handles dropping of further packets. */
}
/* Enqueue packet */
- skb_queue_tail(&tun->readq, skb);
+ skb_queue_tail(&tun->socket.sk->sk_receive_queue, 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->tfile->read_wait);
- return 0;
+ wake_up_interruptible(&tun->socket.wait);
+ return NETDEV_TX_OK;
drop:
dev->stats.tx_dropped++;
kfree_skb(skb);
- return 0;
+ return NETDEV_TX_OK;
}
static void tun_net_mclist(struct net_device *dev)
{
struct tun_file *tfile = file->private_data;
struct tun_struct *tun = __tun_get(tfile);
- struct sock *sk = tun->sk;
+ struct sock *sk;
unsigned int mask = 0;
if (!tun)
return POLLERR;
+ sk = tun->socket.sk;
+
DBG(KERN_INFO "%s: tun_chr_poll\n", tun->dev->name);
- poll_wait(file, &tfile->read_wait, wait);
+ poll_wait(file, &tun->socket.wait, wait);
- if (!skb_queue_empty(&tun->readq))
+ if (!skb_queue_empty(&sk->sk_receive_queue))
mask |= POLLIN | POLLRDNORM;
if (sock_writeable(sk) ||
size_t prepad, size_t len,
size_t linear, int noblock)
{
- struct sock *sk = tun->sk;
+ struct sock *sk = tun->socket.sk;
struct sk_buff *skb;
int err;
/* Get packet from user space buffer */
static __inline__ ssize_t tun_get_user(struct tun_struct *tun,
- struct iovec *iv, size_t count,
+ const struct iovec *iv, size_t count,
int noblock)
{
struct tun_pi pi = { 0, cpu_to_be16(ETH_P_IP) };
struct sk_buff *skb;
size_t len = count, align = 0;
struct virtio_net_hdr gso = { 0 };
+ int offset = 0;
if (!(tun->flags & TUN_NO_PI)) {
if ((len -= sizeof(pi)) > count)
return -EINVAL;
- if(memcpy_fromiovec((void *)&pi, iv, sizeof(pi)))
+ if (memcpy_fromiovecend((void *)&pi, iv, 0, sizeof(pi)))
return -EFAULT;
+ offset += sizeof(pi);
}
if (tun->flags & TUN_VNET_HDR) {
if ((len -= sizeof(gso)) > count)
return -EINVAL;
- if (memcpy_fromiovec((void *)&gso, iv, sizeof(gso)))
+ if (memcpy_fromiovecend((void *)&gso, iv, offset, sizeof(gso)))
return -EFAULT;
+ if ((gso.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) &&
+ gso.csum_start + gso.csum_offset + 2 > gso.hdr_len)
+ gso.hdr_len = gso.csum_start + gso.csum_offset + 2;
+
if (gso.hdr_len > len)
return -EINVAL;
+ offset += sizeof(gso);
}
if ((tun->flags & TUN_TYPE_MASK) == TUN_TAP_DEV) {
return PTR_ERR(skb);
}
- if (skb_copy_datagram_from_iovec(skb, 0, iv, len)) {
+ if (skb_copy_datagram_from_iovec(skb, 0, iv, offset, len)) {
tun->dev->stats.rx_dropped++;
kfree_skb(skb);
return -EFAULT;
case VIRTIO_NET_HDR_GSO_TCPV6:
skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
break;
+ case VIRTIO_NET_HDR_GSO_UDP:
+ skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
+ break;
default:
tun->dev->stats.rx_frame_errors++;
kfree_skb(skb);
DBG(KERN_INFO "%s: tun_chr_write %ld\n", tun->dev->name, count);
- result = tun_get_user(tun, (struct iovec *)iv, iov_length(iv, count),
+ result = tun_get_user(tun, iv, iov_length(iv, count),
file->f_flags & O_NONBLOCK);
tun_put(tun);
/* 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)
+ const struct iovec *iv, int len)
{
struct tun_pi pi = { 0, skb->protocol };
ssize_t total = 0;
pi.flags |= TUN_PKT_STRIP;
}
- if (memcpy_toiovec(iv, (void *) &pi, sizeof(pi)))
+ if (memcpy_toiovecend(iv, (void *) &pi, 0, sizeof(pi)))
return -EFAULT;
total += sizeof(pi);
}
gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
else if (sinfo->gso_type & SKB_GSO_TCPV6)
gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
+ else if (sinfo->gso_type & SKB_GSO_UDP)
+ gso.gso_type = VIRTIO_NET_HDR_GSO_UDP;
else
BUG();
if (sinfo->gso_type & SKB_GSO_TCP_ECN)
gso.csum_offset = skb->csum_offset;
} /* else everything is zero */
- if (unlikely(memcpy_toiovec(iv, (void *)&gso, sizeof(gso))))
+ if (unlikely(memcpy_toiovecend(iv, (void *)&gso, total,
+ sizeof(gso))))
return -EFAULT;
total += sizeof(gso);
}
len = min_t(int, skb->len, len);
- skb_copy_datagram_iovec(skb, 0, iv, len);
+ skb_copy_datagram_const_iovec(skb, 0, iv, total, len);
total += len;
tun->dev->stats.tx_packets++;
goto out;
}
- add_wait_queue(&tfile->read_wait, &wait);
+ add_wait_queue(&tun->socket.wait, &wait);
while (len) {
current->state = TASK_INTERRUPTIBLE;
/* Read frames from the queue */
- if (!(skb=skb_dequeue(&tun->readq))) {
+ if (!(skb=skb_dequeue(&tun->socket.sk->sk_receive_queue))) {
if (file->f_flags & O_NONBLOCK) {
ret = -EAGAIN;
break;
}
netif_wake_queue(tun->dev);
- ret = tun_put_user(tun, skb, (struct iovec *) iv, len);
+ ret = tun_put_user(tun, skb, iv, len);
kfree_skb(skb);
break;
}
current->state = TASK_RUNNING;
- remove_wait_queue(&tfile->read_wait, &wait);
+ remove_wait_queue(&tun->socket.wait, &wait);
out:
tun_put(tun);
{
struct tun_struct *tun = netdev_priv(dev);
- skb_queue_head_init(&tun->readq);
-
tun->owner = -1;
tun->group = -1;
if (!sock_writeable(sk))
return;
- if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
- wake_up_interruptible_sync(sk->sk_sleep);
-
if (!test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags))
return;
- tun = container_of(sk, struct tun_sock, sk)->tun;
+ if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+ wake_up_interruptible_sync(sk->sk_sleep);
+
+ tun = tun_sk(sk)->tun;
kill_fasync(&tun->fasync, SIGIO, POLL_OUT);
}
static void tun_sock_destruct(struct sock *sk)
{
- free_netdev(container_of(sk, struct tun_sock, sk)->tun->dev);
+ free_netdev(tun_sk(sk)->tun->dev);
}
static struct proto tun_proto = {
.obj_size = sizeof(struct tun_sock),
};
+static int tun_flags(struct tun_struct *tun)
+{
+ int flags = 0;
+
+ if (tun->flags & TUN_TUN_DEV)
+ flags |= IFF_TUN;
+ else
+ flags |= IFF_TAP;
+
+ if (tun->flags & TUN_NO_PI)
+ flags |= IFF_NO_PI;
+
+ if (tun->flags & TUN_ONE_QUEUE)
+ flags |= IFF_ONE_QUEUE;
+
+ if (tun->flags & TUN_VNET_HDR)
+ flags |= IFF_VNET_HDR;
+
+ return flags;
+}
+
+static ssize_t tun_show_flags(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct tun_struct *tun = netdev_priv(to_net_dev(dev));
+ return sprintf(buf, "0x%x\n", tun_flags(tun));
+}
+
+static ssize_t tun_show_owner(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct tun_struct *tun = netdev_priv(to_net_dev(dev));
+ return sprintf(buf, "%d\n", tun->owner);
+}
+
+static ssize_t tun_show_group(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct tun_struct *tun = netdev_priv(to_net_dev(dev));
+ return sprintf(buf, "%d\n", tun->group);
+}
+
+static DEVICE_ATTR(tun_flags, 0444, tun_show_flags, NULL);
+static DEVICE_ATTR(owner, 0444, tun_show_owner, NULL);
+static DEVICE_ATTR(group, 0444, tun_show_group, NULL);
+
static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
{
struct sock *sk;
struct tun_struct *tun;
struct net_device *dev;
- struct tun_file *tfile = file->private_data;
int err;
dev = __dev_get_by_name(net, ifr->ifr_name);
if (dev) {
+ const struct cred *cred = current_cred();
+
+ if (ifr->ifr_flags & IFF_TUN_EXCL)
+ return -EBUSY;
if ((ifr->ifr_flags & IFF_TUN) && dev->netdev_ops == &tun_netdev_ops)
tun = netdev_priv(dev);
else if ((ifr->ifr_flags & IFF_TAP) && dev->netdev_ops == &tap_netdev_ops)
else
return -EINVAL;
+ if (((tun->owner != -1 && cred->euid != tun->owner) ||
+ (tun->group != -1 && !in_egroup_p(tun->group))) &&
+ !capable(CAP_NET_ADMIN))
+ return -EPERM;
+ err = security_tun_dev_attach(tun->socket.sk);
+ if (err < 0)
+ return err;
+
err = tun_attach(tun, file);
if (err < 0)
return err;
char *name;
unsigned long flags = 0;
- err = -EINVAL;
-
if (!capable(CAP_NET_ADMIN))
return -EPERM;
+ err = security_tun_dev_create();
+ if (err < 0)
+ return err;
/* Set dev type */
if (ifr->ifr_flags & IFF_TUN) {
flags |= TUN_TAP_DEV;
name = "tap%d";
} else
- goto failed;
+ return -EINVAL;
if (*ifr->ifr_name)
name = ifr->ifr_name;
if (!sk)
goto err_free_dev;
+ init_waitqueue_head(&tun->socket.wait);
sock_init_data(&tun->socket, sk);
sk->sk_write_space = tun_sock_write_space;
sk->sk_sndbuf = INT_MAX;
- sk->sk_sleep = &tfile->read_wait;
- tun->sk = sk;
- container_of(sk, struct tun_sock, sk)->tun = tun;
+ tun_sk(sk)->tun = tun;
+
+ security_tun_dev_post_create(sk);
tun_net_init(dev);
goto err_free_sk;
}
- err = -EINVAL;
err = register_netdevice(tun->dev);
if (err < 0)
goto err_free_sk;
+ if (device_create_file(&tun->dev->dev, &dev_attr_tun_flags) ||
+ device_create_file(&tun->dev->dev, &dev_attr_owner) ||
+ device_create_file(&tun->dev->dev, &dev_attr_group))
+ printk(KERN_ERR "Failed to create tun sysfs files\n");
+
sk->sk_destruct = tun_sock_destruct;
err = tun_attach(tun, file);
return err;
}
-static int tun_get_iff(struct net *net, struct file *file, struct ifreq *ifr)
+static int tun_get_iff(struct net *net, struct tun_struct *tun,
+ struct ifreq *ifr)
{
- struct tun_struct *tun = tun_get(file);
-
- if (!tun)
- return -EBADFD;
-
DBG(KERN_INFO "%s: tun_get_iff\n", tun->dev->name);
strcpy(ifr->ifr_name, tun->dev->name);
- ifr->ifr_flags = 0;
+ ifr->ifr_flags = tun_flags(tun);
- if (ifr->ifr_flags & TUN_TUN_DEV)
- ifr->ifr_flags |= IFF_TUN;
- else
- ifr->ifr_flags |= IFF_TAP;
-
- if (tun->flags & TUN_NO_PI)
- ifr->ifr_flags |= IFF_NO_PI;
-
- if (tun->flags & TUN_ONE_QUEUE)
- ifr->ifr_flags |= IFF_ONE_QUEUE;
-
- if (tun->flags & TUN_VNET_HDR)
- ifr->ifr_flags |= IFF_VNET_HDR;
-
- tun_put(tun);
return 0;
}
old_features = dev->features;
/* Unset features, set them as we chew on the arg. */
features = (old_features & ~(NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST
- |NETIF_F_TSO_ECN|NETIF_F_TSO|NETIF_F_TSO6));
+ |NETIF_F_TSO_ECN|NETIF_F_TSO|NETIF_F_TSO6
+ |NETIF_F_UFO));
if (arg & TUN_F_CSUM) {
features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST;
features |= NETIF_F_TSO6;
arg &= ~(TUN_F_TSO4|TUN_F_TSO6);
}
+
+ if (arg & TUN_F_UFO) {
+ features |= NETIF_F_UFO;
+ arg &= ~TUN_F_UFO;
+ }
}
/* This gives the user a way to test for new features in future by
return 0;
}
-static int tun_chr_ioctl(struct inode *inode, struct file *file,
- unsigned int cmd, unsigned long arg)
+static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
+ unsigned long arg, int ifreq_len)
{
struct tun_file *tfile = file->private_data;
struct tun_struct *tun;
int ret;
if (cmd == TUNSETIFF || _IOC_TYPE(cmd) == 0x89)
- if (copy_from_user(&ifr, argp, sizeof ifr))
+ if (copy_from_user(&ifr, argp, ifreq_len))
return -EFAULT;
if (cmd == TUNGETFEATURES) {
(unsigned int __user*)argp);
}
+ rtnl_lock();
+
tun = __tun_get(tfile);
if (cmd == TUNSETIFF && !tun) {
- int err;
-
ifr.ifr_name[IFNAMSIZ-1] = '\0';
- rtnl_lock();
- err = tun_set_iff(tfile->net, file, &ifr);
- rtnl_unlock();
+ ret = tun_set_iff(tfile->net, file, &ifr);
- if (err)
- return err;
+ if (ret)
+ goto unlock;
- if (copy_to_user(argp, &ifr, sizeof(ifr)))
- return -EFAULT;
- return 0;
+ if (copy_to_user(argp, &ifr, ifreq_len))
+ ret = -EFAULT;
+ goto unlock;
}
-
+ ret = -EBADFD;
if (!tun)
- return -EBADFD;
+ goto unlock;
DBG(KERN_INFO "%s: tun_chr_ioctl cmd %d\n", tun->dev->name, cmd);
ret = 0;
switch (cmd) {
case TUNGETIFF:
- ret = tun_get_iff(current->nsproxy->net_ns, file, &ifr);
+ ret = tun_get_iff(current->nsproxy->net_ns, tun, &ifr);
if (ret)
break;
- if (copy_to_user(argp, &ifr, sizeof(ifr)))
+ if (copy_to_user(argp, &ifr, ifreq_len))
ret = -EFAULT;
break;
case TUNSETLINK:
/* Only allow setting the type when the interface is down */
- rtnl_lock();
if (tun->dev->flags & IFF_UP) {
DBG(KERN_INFO "%s: Linktype set failed because interface is up\n",
tun->dev->name);
DBG(KERN_INFO "%s: linktype set to %d\n", tun->dev->name, tun->dev->type);
ret = 0;
}
- rtnl_unlock();
break;
#ifdef TUN_DEBUG
break;
#endif
case TUNSETOFFLOAD:
- rtnl_lock();
ret = set_offload(tun->dev, arg);
- rtnl_unlock();
break;
case TUNSETTXFILTER:
ret = -EINVAL;
if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
break;
- rtnl_lock();
ret = update_filter(&tun->txflt, (void __user *)arg);
- rtnl_unlock();
break;
case SIOCGIFHWADDR:
/* Get hw addres */
memcpy(ifr.ifr_hwaddr.sa_data, tun->dev->dev_addr, ETH_ALEN);
ifr.ifr_hwaddr.sa_family = tun->dev->type;
- if (copy_to_user(argp, &ifr, sizeof ifr))
+ if (copy_to_user(argp, &ifr, ifreq_len))
ret = -EFAULT;
break;
DBG(KERN_DEBUG "%s: set hw address: %pM\n",
tun->dev->name, ifr.ifr_hwaddr.sa_data);
- rtnl_lock();
ret = dev_set_mac_address(tun->dev, &ifr.ifr_hwaddr);
- rtnl_unlock();
break;
case TUNGETSNDBUF:
- sndbuf = tun->sk->sk_sndbuf;
+ sndbuf = tun->socket.sk->sk_sndbuf;
if (copy_to_user(argp, &sndbuf, sizeof(sndbuf)))
ret = -EFAULT;
break;
break;
}
- tun->sk->sk_sndbuf = sndbuf;
+ tun->socket.sk->sk_sndbuf = sndbuf;
break;
default:
break;
};
- tun_put(tun);
+unlock:
+ rtnl_unlock();
+ if (tun)
+ tun_put(tun);
return ret;
}
+static long tun_chr_ioctl(struct file *file,
+ unsigned int cmd, unsigned long arg)
+{
+ return __tun_chr_ioctl(file, cmd, arg, sizeof (struct ifreq));
+}
+
+#ifdef CONFIG_COMPAT
+static long tun_chr_compat_ioctl(struct file *file,
+ unsigned int cmd, unsigned long arg)
+{
+ switch (cmd) {
+ case TUNSETIFF:
+ case TUNGETIFF:
+ case TUNSETTXFILTER:
+ case TUNGETSNDBUF:
+ case TUNSETSNDBUF:
+ case SIOCGIFHWADDR:
+ case SIOCSIFHWADDR:
+ arg = (unsigned long)compat_ptr(arg);
+ break;
+ default:
+ arg = (compat_ulong_t)arg;
+ break;
+ }
+
+ /*
+ * compat_ifreq is shorter than ifreq, so we must not access beyond
+ * the end of that structure. All fields that are used in this
+ * driver are compatible though, we don't need to convert the
+ * contents.
+ */
+ return __tun_chr_ioctl(file, cmd, arg, sizeof(struct compat_ifreq));
+}
+#endif /* CONFIG_COMPAT */
+
static int tun_chr_fasync(int fd, struct file *file, int on)
{
struct tun_struct *tun = tun_get(file);
DBG(KERN_INFO "%s: tun_chr_fasync %d\n", tun->dev->name, on);
- lock_kernel();
if ((ret = fasync_helper(fd, file, on, &tun->fasync)) < 0)
goto out;
tun->flags &= ~TUN_FASYNC;
ret = 0;
out:
- unlock_kernel();
tun_put(tun);
return ret;
}
static int tun_chr_open(struct inode *inode, struct file * file)
{
struct tun_file *tfile;
- cycle_kernel_lock();
+
DBG1(KERN_INFO "tunX: tun_chr_open\n");
tfile = kmalloc(sizeof(*tfile), GFP_KERNEL);
atomic_set(&tfile->count, 0);
tfile->tun = NULL;
tfile->net = get_net(current->nsproxy->net_ns);
- init_waitqueue_head(&tfile->read_wait);
file->private_data = tfile;
return 0;
}
static int tun_chr_close(struct inode *inode, struct file *file)
{
struct tun_file *tfile = file->private_data;
- struct tun_struct *tun = __tun_get(tfile);
-
+ struct tun_struct *tun;
+ tun = __tun_get(tfile);
if (tun) {
- DBG(KERN_INFO "%s: tun_chr_close\n", tun->dev->name);
+ struct net_device *dev = tun->dev;
+
+ DBG(KERN_INFO "%s: tun_chr_close\n", dev->name);
- rtnl_lock();
__tun_detach(tun);
/* If desireable, unregister the netdevice. */
- if (!(tun->flags & TUN_PERSIST))
- unregister_netdevice(tun->dev);
-
- rtnl_unlock();
+ if (!(tun->flags & TUN_PERSIST)) {
+ rtnl_lock();
+ if (dev->reg_state == NETREG_REGISTERED)
+ unregister_netdevice(dev);
+ rtnl_unlock();
+ }
}
tun = tfile->tun;
if (tun)
- sock_put(tun->sk);
+ sock_put(tun->socket.sk);
put_net(tfile->net);
kfree(tfile);
.write = do_sync_write,
.aio_write = tun_chr_aio_write,
.poll = tun_chr_poll,
- .ioctl = tun_chr_ioctl,
+ .unlocked_ioctl = tun_chr_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = tun_chr_compat_ioctl,
+#endif
.open = tun_chr_open,
.release = tun_chr_close,
.fasync = tun_chr_fasync
static struct miscdevice tun_miscdev = {
.minor = TUN_MINOR,
.name = "tun",
+ .nodename = "net/tun",
.fops = &tun_fops,
};