#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>
#include <linux/crc32.h>
#include <linux/nsproxy.h>
#include <linux/virtio_net.h>
+#include <linux/rcupdate.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
+#include <net/rtnetlink.h>
+#include <net/sock.h>
#include <asm/system.h>
#include <asm/uaccess.h>
unsigned char addr[FLT_EXACT_COUNT][ETH_ALEN];
};
+struct tun_file {
+ atomic_t count;
+ struct tun_struct *tun;
+ struct net *net;
+};
+
+struct tun_sock;
+
struct tun_struct {
+ struct tun_file *tfile;
unsigned int flags;
- int attached;
uid_t owner;
gid_t group;
- wait_queue_head_t read_wait;
- struct sk_buff_head readq;
-
struct net_device *dev;
struct fasync_struct *fasync;
struct tap_filter txflt;
+ struct socket socket;
+ struct socket_wq wq;
+
+ int vnet_hdr_sz;
#ifdef TUN_DEBUG
int debug;
#endif
};
+struct tun_sock {
+ struct sock sk;
+ struct tun_struct *tun;
+};
+
+static inline struct tun_sock *tun_sk(struct sock *sk)
+{
+ return container_of(sk, struct tun_sock, sk);
+}
+
static int tun_attach(struct tun_struct *tun, struct file *file)
{
- const struct cred *cred = current_cred();
+ struct tun_file *tfile = file->private_data;
+ int err;
ASSERT_RTNL();
- if (file->private_data)
- return -EINVAL;
+ netif_tx_lock_bh(tun->dev);
- if (tun->attached)
- return -EBUSY;
+ err = -EINVAL;
+ if (tfile->tun)
+ goto out;
- /* Check permissions */
- if (((tun->owner != -1 && cred->euid != tun->owner) ||
- (tun->group != -1 && cred->egid != tun->group)) &&
- !capable(CAP_NET_ADMIN))
- return -EPERM;
+ err = -EBUSY;
+ if (tun->tfile)
+ goto out;
- file->private_data = tun;
- tun->attached = 1;
- get_net(dev_net(tun->dev));
+ err = 0;
+ tfile->tun = tun;
+ tun->tfile = tfile;
+ tun->socket.file = file;
+ dev_hold(tun->dev);
+ sock_hold(tun->socket.sk);
+ atomic_inc(&tfile->count);
- return 0;
+out:
+ netif_tx_unlock_bh(tun->dev);
+ return err;
+}
+
+static void __tun_detach(struct tun_struct *tun)
+{
+ /* Detach from net device */
+ netif_tx_lock_bh(tun->dev);
+ tun->tfile = NULL;
+ tun->socket.file = NULL;
+ netif_tx_unlock_bh(tun->dev);
+
+ /* Drop read queue */
+ skb_queue_purge(&tun->socket.sk->sk_receive_queue);
+
+ /* Drop the extra count on the net device */
+ dev_put(tun->dev);
+}
+
+static void tun_detach(struct tun_struct *tun)
+{
+ rtnl_lock();
+ __tun_detach(tun);
+ rtnl_unlock();
+}
+
+static struct tun_struct *__tun_get(struct tun_file *tfile)
+{
+ struct tun_struct *tun = NULL;
+
+ if (atomic_inc_not_zero(&tfile->count))
+ tun = tfile->tun;
+
+ return tun;
+}
+
+static struct tun_struct *tun_get(struct file *file)
+{
+ return __tun_get(file->private_data);
+}
+
+static void tun_put(struct tun_struct *tun)
+{
+ struct tun_file *tfile = tun->tfile;
+
+ if (atomic_dec_and_test(&tfile->count))
+ tun_detach(tfile->tun);
}
/* TAP filterting */
nexact = n;
- /* The rest is hashed */
+ /* Remaining multicast addresses are hashed,
+ * unicast will leave the filter disabled. */
memset(filter->mask, 0, sizeof(filter->mask));
- for (; n < uf.count; n++)
+ for (; n < uf.count; n++) {
+ if (!is_multicast_ether_addr(addr[n].u)) {
+ err = 0; /* no filter */
+ goto done;
+ }
addr_hash_set(filter->mask, addr[n].u);
+ }
/* For ALLMULTI just set the mask to all ones.
* This overrides the mask populated above. */
static const struct ethtool_ops tun_ethtool_ops;
+/* Net device detach from fd. */
+static void tun_net_uninit(struct net_device *dev)
+{
+ struct tun_struct *tun = netdev_priv(dev);
+ struct tun_file *tfile = tun->tfile;
+
+ /* Inform the methods they need to stop using the dev.
+ */
+ if (tfile) {
+ wake_up_all(&tun->wq.wait);
+ if (atomic_dec_and_test(&tfile->count))
+ __tun_detach(tun);
+ }
+}
+
+static void tun_free_netdev(struct net_device *dev)
+{
+ struct tun_struct *tun = netdev_priv(dev);
+
+ sock_put(tun->socket.sk);
+}
+
/* Net device open. */
static int tun_net_open(struct net_device *dev)
{
}
/* 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);
DBG(KERN_INFO "%s: tun_net_xmit %d\n", tun->dev->name, skb->len);
/* Drop packet if interface is not attached */
- if (!tun->attached)
+ if (!tun->tfile)
goto drop;
/* Drop if the filter does not like it.
if (!check_filter(&tun->txflt, skb))
goto drop;
- if (skb_queue_len(&tun->readq) >= dev->tx_queue_len) {
+ if (tun->socket.sk->sk_filter &&
+ sk_filter(tun->socket.sk, skb))
+ goto drop;
+
+ 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. */
}
}
+ /* Orphan the skb - required as we might hang on to it
+ * for indefinite time. */
+ skb_orphan(skb);
+
/* Enqueue packet */
- skb_queue_tail(&tun->readq, skb);
- dev->trans_start = jiffies;
+ skb_queue_tail(&tun->socket.sk->sk_receive_queue, skb);
/* 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;
+ wake_up_interruptible_poll(&tun->wq.wait, POLLIN |
+ POLLRDNORM | POLLRDBAND);
+ 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)
* _rx_ path and has nothing to do with the _tx_ path.
* In rx path we always accept everything userspace gives us.
*/
- return;
}
#define MIN_MTU 68
}
static const struct net_device_ops tun_netdev_ops = {
+ .ndo_uninit = tun_net_uninit,
.ndo_open = tun_net_open,
.ndo_stop = tun_net_close,
.ndo_start_xmit = tun_net_xmit,
};
static const struct net_device_ops tap_netdev_ops = {
+ .ndo_uninit = tun_net_uninit,
.ndo_open = tun_net_open,
.ndo_stop = tun_net_close,
.ndo_start_xmit = tun_net_xmit,
/* 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;
+ struct tun_file *tfile = file->private_data;
+ struct tun_struct *tun = __tun_get(tfile);
+ struct sock *sk;
+ unsigned int mask = 0;
if (!tun)
- return -EBADFD;
+ return POLLERR;
+
+ sk = tun->socket.sk;
DBG(KERN_INFO "%s: tun_chr_poll\n", tun->dev->name);
- poll_wait(file, &tun->read_wait, wait);
+ poll_wait(file, &tun->wq.wait, wait);
- if (!skb_queue_empty(&tun->readq))
+ if (!skb_queue_empty(&sk->sk_receive_queue))
mask |= POLLIN | POLLRDNORM;
+ if (sock_writeable(sk) ||
+ (!test_and_set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
+ sock_writeable(sk)))
+ mask |= POLLOUT | POLLWRNORM;
+
+ if (tun->dev->reg_state != NETREG_REGISTERED)
+ mask = POLLERR;
+
+ tun_put(tun);
return mask;
}
/* prepad is the amount to reserve at front. len is length after that.
* linear is a hint as to how much to copy (usually headers). */
-static struct sk_buff *tun_alloc_skb(size_t prepad, size_t len, size_t linear,
- gfp_t gfp)
+static inline struct sk_buff *tun_alloc_skb(struct tun_struct *tun,
+ size_t prepad, size_t len,
+ size_t linear, int noblock)
{
+ struct sock *sk = tun->socket.sk;
struct sk_buff *skb;
- unsigned int i;
-
- skb = alloc_skb(prepad + len, gfp|__GFP_NOWARN);
- if (skb) {
- skb_reserve(skb, prepad);
- skb_put(skb, len);
- return skb;
- }
+ int err;
/* Under a page? Don't bother with paged skb. */
- if (prepad + len < PAGE_SIZE)
- return NULL;
+ if (prepad + len < PAGE_SIZE || !linear)
+ linear = len;
- /* Start with a normal skb, and add pages. */
- skb = alloc_skb(prepad + linear, gfp);
+ skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock,
+ &err);
if (!skb)
- return NULL;
+ return ERR_PTR(err);
skb_reserve(skb, prepad);
skb_put(skb, linear);
-
- len -= linear;
-
- for (i = 0; i < MAX_SKB_FRAGS; i++) {
- skb_frag_t *f = &skb_shinfo(skb)->frags[i];
-
- f->page = alloc_page(gfp|__GFP_ZERO);
- if (!f->page)
- break;
-
- f->page_offset = 0;
- f->size = PAGE_SIZE;
-
- skb->data_len += PAGE_SIZE;
- skb->len += PAGE_SIZE;
- skb->truesize += PAGE_SIZE;
- skb_shinfo(skb)->nr_frags++;
-
- if (len < PAGE_SIZE) {
- len = 0;
- break;
- }
- len -= PAGE_SIZE;
- }
-
- /* Too large, or alloc fail? */
- if (unlikely(len)) {
- kfree_skb(skb);
- skb = NULL;
- }
+ skb->data_len = len - linear;
+ skb->len += len - linear;
return skb;
}
/* Get packet from user space buffer */
-static __inline__ ssize_t tun_get_user(struct tun_struct *tun, struct iovec *iv, size_t count)
+static __inline__ ssize_t tun_get_user(struct tun_struct *tun,
+ const struct iovec *iv, size_t count,
+ int noblock)
{
- struct tun_pi pi = { 0, __constant_htons(ETH_P_IP) };
+ 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)
+ if ((len -= tun->vnet_hdr_sz) > 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 += tun->vnet_hdr_sz;
}
if ((tun->flags & TUN_TYPE_MASK) == TUN_TAP_DEV) {
align = NET_IP_ALIGN;
- if (unlikely(len < ETH_HLEN))
+ if (unlikely(len < ETH_HLEN ||
+ (gso.hdr_len && gso.hdr_len < ETH_HLEN)))
return -EINVAL;
}
- if (!(skb = tun_alloc_skb(align, len, gso.hdr_len, GFP_KERNEL))) {
- tun->dev->stats.rx_dropped++;
- return -ENOMEM;
+ skb = tun_alloc_skb(tun, align, len, gso.hdr_len, noblock);
+ if (IS_ERR(skb)) {
+ if (PTR_ERR(skb) != -EAGAIN)
+ tun->dev->stats.rx_dropped++;
+ 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);
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;
+ struct file *file = iocb->ki_filp;
+ struct tun_struct *tun = tun_get(file);
+ ssize_t result;
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_length(iv, count));
+ result = tun_get_user(tun, iv, iov_length(iv, count),
+ file->f_flags & O_NONBLOCK);
+
+ tun_put(tun);
+ return result;
}
/* 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);
}
if (tun->flags & TUN_VNET_HDR) {
struct virtio_net_hdr gso = { 0 }; /* no info leak */
- if ((len -= sizeof(gso)) < 0)
+ if ((len -= tun->vnet_hdr_sz) < 0)
return -EINVAL;
if (skb_is_gso(skb)) {
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);
+ total += tun->vnet_hdr_sz;
}
len = min_t(int, skb->len, len);
- skb_copy_datagram_iovec(skb, 0, iv, len);
- total += len;
+ skb_copy_datagram_const_iovec(skb, 0, iv, total, len);
+ total += skb->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)
+static ssize_t tun_do_read(struct tun_struct *tun,
+ struct kiocb *iocb, const struct iovec *iv,
+ ssize_t len, int noblock)
{
- 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;
-
- if (!tun)
- return -EBADFD;
+ ssize_t ret = 0;
DBG(KERN_INFO "%s: tun_chr_read\n", tun->dev->name);
- len = iov_length(iv, count);
- if (len < 0)
- return -EINVAL;
-
- add_wait_queue(&tun->read_wait, &wait);
+ add_wait_queue(&tun->wq.wait, &wait);
while (len) {
current->state = TASK_INTERRUPTIBLE;
/* Read frames from the queue */
- if (!(skb=skb_dequeue(&tun->readq))) {
- if (file->f_flags & O_NONBLOCK) {
+ if (!(skb=skb_dequeue(&tun->socket.sk->sk_receive_queue))) {
+ if (noblock) {
ret = -EAGAIN;
break;
}
ret = -ERESTARTSYS;
break;
}
+ if (tun->dev->reg_state != NETREG_REGISTERED) {
+ ret = -EIO;
+ break;
+ }
/* Nothing to read, let's sleep */
schedule();
}
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(&tun->read_wait, &wait);
+ remove_wait_queue(&tun->wq.wait, &wait);
return ret;
}
+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_file *tfile = file->private_data;
+ struct tun_struct *tun = __tun_get(tfile);
+ ssize_t len, ret;
+
+ if (!tun)
+ return -EBADFD;
+ len = iov_length(iv, count);
+ if (len < 0) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ ret = tun_do_read(tun, iocb, iv, len, file->f_flags & O_NONBLOCK);
+ ret = min_t(ssize_t, ret, len);
+out:
+ tun_put(tun);
+ 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->ethtool_ops = &tun_ethtool_ops;
- dev->destructor = free_netdev;
- dev->features |= NETIF_F_NETNS_LOCAL;
+ dev->destructor = tun_free_netdev;
+}
+
+/* Trivial set of netlink ops to allow deleting tun or tap
+ * device with netlink.
+ */
+static int tun_validate(struct nlattr *tb[], struct nlattr *data[])
+{
+ return -EINVAL;
}
+static struct rtnl_link_ops tun_link_ops __read_mostly = {
+ .kind = DRV_NAME,
+ .priv_size = sizeof(struct tun_struct),
+ .setup = tun_setup,
+ .validate = tun_validate,
+};
+
+static void tun_sock_write_space(struct sock *sk)
+{
+ struct tun_struct *tun;
+ wait_queue_head_t *wqueue;
+
+ if (!sock_writeable(sk))
+ return;
+
+ if (!test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags))
+ return;
+
+ wqueue = sk_sleep(sk);
+ if (wqueue && waitqueue_active(wqueue))
+ wake_up_interruptible_sync_poll(wqueue, POLLOUT |
+ POLLWRNORM | POLLWRBAND);
+
+ tun = tun_sk(sk)->tun;
+ kill_fasync(&tun->fasync, SIGIO, POLL_OUT);
+}
+
+static void tun_sock_destruct(struct sock *sk)
+{
+ free_netdev(tun_sk(sk)->tun->dev);
+}
+
+static int tun_sendmsg(struct kiocb *iocb, struct socket *sock,
+ struct msghdr *m, size_t total_len)
+{
+ struct tun_struct *tun = container_of(sock, struct tun_struct, socket);
+ return tun_get_user(tun, m->msg_iov, total_len,
+ m->msg_flags & MSG_DONTWAIT);
+}
+
+static int tun_recvmsg(struct kiocb *iocb, struct socket *sock,
+ struct msghdr *m, size_t total_len,
+ int flags)
+{
+ struct tun_struct *tun = container_of(sock, struct tun_struct, socket);
+ int ret;
+ if (flags & ~(MSG_DONTWAIT|MSG_TRUNC))
+ return -EINVAL;
+ ret = tun_do_read(tun, iocb, m->msg_iov, total_len,
+ flags & MSG_DONTWAIT);
+ if (ret > total_len) {
+ m->msg_flags |= MSG_TRUNC;
+ ret = flags & MSG_TRUNC ? ret : total_len;
+ }
+ return ret;
+}
+
+/* Ops structure to mimic raw sockets with tun */
+static const struct proto_ops tun_socket_ops = {
+ .sendmsg = tun_sendmsg,
+ .recvmsg = tun_recvmsg,
+};
+
+static struct proto tun_proto = {
+ .name = "tun",
+ .owner = THIS_MODULE,
+ .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;
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;
return -ENOMEM;
dev_net_set(dev, net);
+ dev->rtnl_link_ops = &tun_link_ops;
tun = netdev_priv(dev);
tun->dev = dev;
tun->flags = flags;
tun->txflt.count = 0;
+ tun->vnet_hdr_sz = sizeof(struct virtio_net_hdr);
+
+ err = -ENOMEM;
+ sk = sk_alloc(net, AF_UNSPEC, GFP_KERNEL, &tun_proto);
+ if (!sk)
+ goto err_free_dev;
+
+ tun->socket.wq = &tun->wq;
+ init_waitqueue_head(&tun->wq.wait);
+ tun->socket.ops = &tun_socket_ops;
+ sock_init_data(&tun->socket, sk);
+ sk->sk_write_space = tun_sock_write_space;
+ sk->sk_sndbuf = INT_MAX;
+
+ tun_sk(sk)->tun = tun;
+
+ security_tun_dev_post_create(sk);
tun_net_init(dev);
if (strchr(dev->name, '%')) {
err = dev_alloc_name(dev, dev->name);
if (err < 0)
- goto err_free_dev;
+ goto err_free_sk;
}
err = register_netdevice(tun->dev);
if (err < 0)
- goto err_free_dev;
+ 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);
if (err < 0)
- goto err_free_dev;
+ goto failed;
}
DBG(KERN_INFO "%s: tun_set_iff\n", tun->dev->name);
strcpy(ifr->ifr_name, tun->dev->name);
return 0;
+ err_free_sk:
+ sock_put(sk);
err_free_dev:
free_netdev(dev);
failed:
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 = file->private_data;
-
- 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;
-
- 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;
+ ifr->ifr_flags = tun_flags(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_struct *tun = file->private_data;
+ struct tun_file *tfile = file->private_data;
+ struct tun_struct *tun;
void __user* argp = (void __user*)arg;
+ struct sock_fprog fprog;
struct ifreq ifr;
+ int sndbuf;
+ int vnet_hdr_sz;
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 == TUNSETIFF && !tun) {
- int err;
-
- ifr.ifr_name[IFNAMSIZ-1] = '\0';
-
- rtnl_lock();
- err = tun_set_iff(current->nsproxy->net_ns, file, &ifr);
- rtnl_unlock();
-
- if (err)
- return err;
-
- if (copy_to_user(argp, &ifr, sizeof(ifr)))
- return -EFAULT;
- return 0;
- }
-
if (cmd == TUNGETFEATURES) {
/* Currently this just means: "what IFF flags are valid?".
* This is needed because we never checked for invalid flags on
(unsigned int __user*)argp);
}
+ rtnl_lock();
+
+ tun = __tun_get(tfile);
+ if (cmd == TUNSETIFF && !tun) {
+ ifr.ifr_name[IFNAMSIZ-1] = '\0';
+
+ ret = tun_set_iff(tfile->net, file, &ifr);
+
+ if (ret)
+ goto unlock;
+
+ 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)
- return ret;
+ break;
- if (copy_to_user(argp, &ifr, sizeof(ifr)))
- return -EFAULT;
+ if (copy_to_user(argp, &ifr, ifreq_len))
+ ret = -EFAULT;
break;
case TUNSETNOCSUM:
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();
- return ret;
+ break;
#ifdef TUN_DEBUG
case TUNSETDEBUG:
break;
#endif
case TUNSETOFFLOAD:
- rtnl_lock();
ret = set_offload(tun->dev, arg);
- rtnl_unlock();
- return ret;
+ break;
case TUNSETTXFILTER:
/* Can be set only for TAPs */
+ ret = -EINVAL;
if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
- return -EINVAL;
- rtnl_lock();
+ break;
ret = update_filter(&tun->txflt, (void __user *)arg);
- rtnl_unlock();
- return ret;
+ 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))
- return -EFAULT;
- return 0;
+ if (copy_to_user(argp, &ifr, ifreq_len))
+ ret = -EFAULT;
+ break;
case SIOCSIFHWADDR:
/* Set hw address */
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();
- return ret;
+ break;
+
+ case TUNGETSNDBUF:
+ sndbuf = tun->socket.sk->sk_sndbuf;
+ if (copy_to_user(argp, &sndbuf, sizeof(sndbuf)))
+ ret = -EFAULT;
+ break;
+
+ case TUNSETSNDBUF:
+ if (copy_from_user(&sndbuf, argp, sizeof(sndbuf))) {
+ ret = -EFAULT;
+ break;
+ }
+
+ tun->socket.sk->sk_sndbuf = sndbuf;
+ break;
+
+ case TUNGETVNETHDRSZ:
+ vnet_hdr_sz = tun->vnet_hdr_sz;
+ if (copy_to_user(argp, &vnet_hdr_sz, sizeof(vnet_hdr_sz)))
+ ret = -EFAULT;
+ break;
+
+ case TUNSETVNETHDRSZ:
+ if (copy_from_user(&vnet_hdr_sz, argp, sizeof(vnet_hdr_sz))) {
+ ret = -EFAULT;
+ break;
+ }
+ if (vnet_hdr_sz < (int)sizeof(struct virtio_net_hdr)) {
+ ret = -EINVAL;
+ break;
+ }
+
+ tun->vnet_hdr_sz = vnet_hdr_sz;
+ break;
+
+ case TUNATTACHFILTER:
+ /* Can be set only for TAPs */
+ ret = -EINVAL;
+ if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
+ break;
+ ret = -EFAULT;
+ if (copy_from_user(&fprog, argp, sizeof(fprog)))
+ break;
+
+ ret = sk_attach_filter(&fprog, tun->socket.sk);
+ break;
+
+ case TUNDETACHFILTER:
+ /* Can be set only for TAPs */
+ ret = -EINVAL;
+ if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
+ break;
+ ret = sk_detach_filter(tun->socket.sk);
+ break;
default:
- return -EINVAL;
+ ret = -EINVAL;
+ break;
};
- return 0;
+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 = file->private_data;
+ struct tun_struct *tun = tun_get(file);
int ret;
if (!tun)
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)
{
- cycle_kernel_lock();
+ struct tun_file *tfile;
+
DBG1(KERN_INFO "tunX: tun_chr_open\n");
- file->private_data = NULL;
+
+ tfile = kmalloc(sizeof(*tfile), GFP_KERNEL);
+ if (!tfile)
+ return -ENOMEM;
+ atomic_set(&tfile->count, 0);
+ tfile->tun = NULL;
+ tfile->net = get_net(current->nsproxy->net_ns);
+ file->private_data = tfile;
return 0;
}
static int tun_chr_close(struct inode *inode, struct file *file)
{
- struct tun_struct *tun = file->private_data;
-
- if (!tun)
- return 0;
+ struct tun_file *tfile = file->private_data;
+ struct tun_struct *tun;
- DBG(KERN_INFO "%s: tun_chr_close\n", tun->dev->name);
+ tun = __tun_get(tfile);
+ if (tun) {
+ struct net_device *dev = tun->dev;
- rtnl_lock();
+ DBG(KERN_INFO "%s: tun_chr_close\n", dev->name);
- /* Detach from net device */
- file->private_data = NULL;
- tun->attached = 0;
- put_net(dev_net(tun->dev));
+ __tun_detach(tun);
- /* Drop read queue */
- skb_queue_purge(&tun->readq);
+ /* If desirable, unregister the netdevice. */
+ if (!(tun->flags & TUN_PERSIST)) {
+ rtnl_lock();
+ if (dev->reg_state == NETREG_REGISTERED)
+ unregister_netdevice(dev);
+ rtnl_unlock();
+ }
+ }
- if (!(tun->flags & TUN_PERSIST))
- unregister_netdevice(tun->dev);
+ tun = tfile->tun;
+ if (tun)
+ sock_put(tun->socket.sk);
- rtnl_unlock();
+ put_net(tfile->net);
+ kfree(tfile);
return 0;
}
.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,
};
static u32 tun_get_link(struct net_device *dev)
{
struct tun_struct *tun = netdev_priv(dev);
- return tun->attached;
+ return !!tun->tfile;
}
static u32 tun_get_rx_csum(struct net_device *dev)
.set_rx_csum = tun_set_rx_csum
};
-static int tun_init_net(struct net *net)
-{
- return 0;
-}
-
-static void tun_exit_net(struct net *net)
-{
- struct net_device *dev, *next;
-
- rtnl_lock();
- for_each_netdev_safe(net, dev, next) {
- if (dev->ethtool_ops != &tun_ethtool_ops)
- continue;
- DBG(KERN_INFO "%s cleaned up\n", dev->name);
- unregister_netdevice(dev);
- }
- rtnl_unlock();
-}
-
-static struct pernet_operations tun_net_ops = {
- .init = tun_init_net,
- .exit = tun_exit_net,
-};
static int __init tun_init(void)
{
printk(KERN_INFO "tun: %s, %s\n", DRV_DESCRIPTION, DRV_VERSION);
printk(KERN_INFO "tun: %s\n", DRV_COPYRIGHT);
- ret = register_pernet_device(&tun_net_ops);
+ ret = rtnl_link_register(&tun_link_ops);
if (ret) {
- printk(KERN_ERR "tun: Can't register pernet ops\n");
- goto err_pernet;
+ printk(KERN_ERR "tun: Can't register link_ops\n");
+ goto err_linkops;
}
ret = misc_register(&tun_miscdev);
printk(KERN_ERR "tun: Can't register misc device %d\n", TUN_MINOR);
goto err_misc;
}
- return 0;
-
+ return 0;
err_misc:
- unregister_pernet_device(&tun_net_ops);
-err_pernet:
+ rtnl_link_unregister(&tun_link_ops);
+err_linkops:
return ret;
}
static void tun_cleanup(void)
{
misc_deregister(&tun_miscdev);
- unregister_pernet_device(&tun_net_ops);
+ rtnl_link_unregister(&tun_link_ops);
+}
+
+/* Get an underlying socket object from tun file. Returns error unless file is
+ * attached to a device. The returned object works like a packet socket, it
+ * can be used for sock_sendmsg/sock_recvmsg. The caller is responsible for
+ * holding a reference to the file for as long as the socket is in use. */
+struct socket *tun_get_socket(struct file *file)
+{
+ struct tun_struct *tun;
+ if (file->f_op != &tun_fops)
+ return ERR_PTR(-EINVAL);
+ tun = tun_get(file);
+ if (!tun)
+ return ERR_PTR(-EBADFD);
+ tun_put(tun);
+ return &tun->socket;
}
+EXPORT_SYMBOL_GPL(tun_get_socket);
module_init(tun_init);
module_exit(tun_cleanup);