diff options
Diffstat (limited to 'drivers/net/macvtap.c')
| -rw-r--r-- | drivers/net/macvtap.c | 183 |
1 files changed, 134 insertions, 49 deletions
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index ab96c319a240..1b7082d08f33 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -51,15 +51,13 @@ static struct proto macvtap_proto = { }; /* - * Minor number matches netdev->ifindex, so need a potentially - * large value. This also makes it possible to split the - * tap functionality out again in the future by offering it - * from other drivers besides macvtap. As long as every device - * only has one tap, the interface numbers assure that the - * device nodes are unique. + * Variables for dealing with macvtaps device numbers. */ static dev_t macvtap_major; -#define MACVTAP_NUM_DEVS 65536 +#define MACVTAP_NUM_DEVS (1U << MINORBITS) +static DEFINE_MUTEX(minor_lock); +static DEFINE_IDR(minor_idr); + #define GOODCOPY_LEN 128 static struct class *macvtap_class; static struct cdev macvtap_cdev; @@ -231,6 +229,8 @@ static void macvtap_del_queues(struct net_device *dev) } } BUG_ON(vlan->numvtaps != 0); + /* guarantee that any future macvtap_set_queue will fail */ + vlan->numvtaps = MAX_MACVTAP_QUEUES; spin_unlock(&macvtap_lock); synchronize_rcu(); @@ -273,39 +273,73 @@ static int macvtap_receive(struct sk_buff *skb) return macvtap_forward(skb->dev, skb); } -static int macvtap_newlink(struct net *src_net, - struct net_device *dev, - struct nlattr *tb[], - struct nlattr *data[]) +static int macvtap_get_minor(struct macvlan_dev *vlan) { - struct device *classdev; - dev_t devt; - int err; + int retval = -ENOMEM; + int id; + + mutex_lock(&minor_lock); + if (idr_pre_get(&minor_idr, GFP_KERNEL) == 0) + goto exit; + + retval = idr_get_new_above(&minor_idr, vlan, 1, &id); + if (retval < 0) { + if (retval == -EAGAIN) + retval = -ENOMEM; + goto exit; + } + if (id < MACVTAP_NUM_DEVS) { + vlan->minor = id; + } else { + printk(KERN_ERR "too many macvtap devices\n"); + retval = -EINVAL; + idr_remove(&minor_idr, id); + } +exit: + mutex_unlock(&minor_lock); + return retval; +} - err = macvlan_common_newlink(src_net, dev, tb, data, - macvtap_receive, macvtap_forward); - if (err) - goto out; +static void macvtap_free_minor(struct macvlan_dev *vlan) +{ + mutex_lock(&minor_lock); + if (vlan->minor) { + idr_remove(&minor_idr, vlan->minor); + vlan->minor = 0; + } + mutex_unlock(&minor_lock); +} - devt = MKDEV(MAJOR(macvtap_major), dev->ifindex); +static struct net_device *dev_get_by_macvtap_minor(int minor) +{ + struct net_device *dev = NULL; + struct macvlan_dev *vlan; - classdev = device_create(macvtap_class, &dev->dev, devt, - dev, "tap%d", dev->ifindex); - if (IS_ERR(classdev)) { - err = PTR_ERR(classdev); - macvtap_del_queues(dev); + mutex_lock(&minor_lock); + vlan = idr_find(&minor_idr, minor); + if (vlan) { + dev = vlan->dev; + dev_hold(dev); } + mutex_unlock(&minor_lock); + return dev; +} -out: - return err; +static int macvtap_newlink(struct net *src_net, + struct net_device *dev, + struct nlattr *tb[], + struct nlattr *data[]) +{ + /* Don't put anything that may fail after macvlan_common_newlink + * because we can't undo what it does. + */ + return macvlan_common_newlink(src_net, dev, tb, data, + macvtap_receive, macvtap_forward); } static void macvtap_dellink(struct net_device *dev, struct list_head *head) { - device_destroy(macvtap_class, - MKDEV(MAJOR(macvtap_major), dev->ifindex)); - macvtap_del_queues(dev); macvlan_dellink(dev, head); } @@ -337,11 +371,15 @@ static void macvtap_sock_write_space(struct sock *sk) wake_up_interruptible_poll(wqueue, POLLOUT | POLLWRNORM | POLLWRBAND); } +static void macvtap_sock_destruct(struct sock *sk) +{ + skb_queue_purge(&sk->sk_receive_queue); +} + static int macvtap_open(struct inode *inode, struct file *file) { struct net *net = current->nsproxy->net_ns; - struct net_device *dev = dev_get_by_index(net, iminor(inode)); - struct macvlan_dev *vlan = netdev_priv(dev); + struct net_device *dev = dev_get_by_macvtap_minor(iminor(inode)); struct macvtap_queue *q; int err; @@ -349,11 +387,6 @@ static int macvtap_open(struct inode *inode, struct file *file) if (!dev) goto out; - /* check if this is a macvtap device */ - err = -EINVAL; - if (dev->rtnl_link_ops != &macvtap_link_ops) - goto out; - err = -ENOMEM; q = (struct macvtap_queue *)sk_alloc(net, AF_UNSPEC, GFP_KERNEL, &macvtap_proto); @@ -368,18 +401,19 @@ static int macvtap_open(struct inode *inode, struct file *file) q->sock.ops = &macvtap_socket_ops; sock_init_data(&q->sock, &q->sk); q->sk.sk_write_space = macvtap_sock_write_space; + q->sk.sk_destruct = macvtap_sock_destruct; q->flags = IFF_VNET_HDR | IFF_NO_PI | IFF_TAP; q->vnet_hdr_sz = sizeof(struct virtio_net_hdr); /* * so far only KVM virtio_net uses macvtap, enable zero copy between * guest kernel and host kernel when lower device supports zerocopy + * + * The macvlan supports zerocopy iff the lower device supports zero + * copy so we don't have to look at the lower device directly. */ - if (vlan) { - if ((vlan->lowerdev->features & NETIF_F_HIGHDMA) && - (vlan->lowerdev->features & NETIF_F_SG)) - sock_set_flag(&q->sk, SOCK_ZEROCOPY); - } + if ((dev->features & NETIF_F_HIGHDMA) && (dev->features & NETIF_F_SG)) + sock_set_flag(&q->sk, SOCK_ZEROCOPY); err = macvtap_set_queue(dev, file, q); if (err) @@ -453,7 +487,6 @@ static int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from, int copy = skb_headlen(skb); int size, offset1 = 0; int i = 0; - skb_frag_t *f; /* Skip over from offset */ while (count && (offset >= from->iov_len)) { @@ -503,14 +536,13 @@ static int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from, skb->truesize += len; atomic_add(len, &skb->sk->sk_wmem_alloc); while (len) { - f = &skb_shinfo(skb)->frags[i]; - f->page = page[i]; - f->page_offset = base & ~PAGE_MASK; - f->size = min_t(int, len, PAGE_SIZE - f->page_offset); + int off = base & ~PAGE_MASK; + int size = min_t(int, len, PAGE_SIZE - off); + __skb_fill_page_desc(skb, i, page[i], off, size); skb_shinfo(skb)->nr_frags++; /* increase sk_wmem_alloc */ - base += f->size; - len -= f->size; + base += size; + len -= size; i++; } offset1 = 0; @@ -970,6 +1002,52 @@ struct socket *macvtap_get_socket(struct file *file) } EXPORT_SYMBOL_GPL(macvtap_get_socket); +static int macvtap_device_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = ptr; + struct macvlan_dev *vlan; + struct device *classdev; + dev_t devt; + int err; + + if (dev->rtnl_link_ops != &macvtap_link_ops) + return NOTIFY_DONE; + + vlan = netdev_priv(dev); + + switch (event) { + case NETDEV_REGISTER: + /* Create the device node here after the network device has + * been registered but before register_netdevice has + * finished running. + */ + err = macvtap_get_minor(vlan); + if (err) + return notifier_from_errno(err); + + devt = MKDEV(MAJOR(macvtap_major), vlan->minor); + classdev = device_create(macvtap_class, &dev->dev, devt, + dev, "tap%d", dev->ifindex); + if (IS_ERR(classdev)) { + macvtap_free_minor(vlan); + return notifier_from_errno(PTR_ERR(classdev)); + } + break; + case NETDEV_UNREGISTER: + devt = MKDEV(MAJOR(macvtap_major), vlan->minor); + device_destroy(macvtap_class, devt); + macvtap_free_minor(vlan); + break; + } + + return NOTIFY_DONE; +} + +static struct notifier_block macvtap_notifier_block __read_mostly = { + .notifier_call = macvtap_device_event, +}; + static int macvtap_init(void) { int err; @@ -990,12 +1068,18 @@ static int macvtap_init(void) goto out3; } - err = macvlan_link_register(&macvtap_link_ops); + err = register_netdevice_notifier(&macvtap_notifier_block); if (err) goto out4; + err = macvlan_link_register(&macvtap_link_ops); + if (err) + goto out5; + return 0; +out5: + unregister_netdevice_notifier(&macvtap_notifier_block); out4: class_unregister(macvtap_class); out3: @@ -1010,6 +1094,7 @@ module_init(macvtap_init); static void macvtap_exit(void) { rtnl_link_unregister(&macvtap_link_ops); + unregister_netdevice_notifier(&macvtap_notifier_block); class_unregister(macvtap_class); cdev_del(&macvtap_cdev); unregister_chrdev_region(macvtap_major, MACVTAP_NUM_DEVS); |