};
/*
- * 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;
}
}
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();
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);
}
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 net_device *dev = dev_get_by_macvtap_minor(iminor(inode));
struct macvtap_queue *q;
int err;
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);
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 ((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)
sock_put(&q->sk);
return skb;
}
+/* set skb frags from iovec, this can move to core network code for reuse */
+static int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from,
+ int offset, size_t count)
+{
+ int len = iov_length(from, count) - offset;
+ int copy = skb_headlen(skb);
+ int size, offset1 = 0;
+ int i = 0;
+
+ /* Skip over from offset */
+ while (count && (offset >= from->iov_len)) {
+ offset -= from->iov_len;
+ ++from;
+ --count;
+ }
+
+ /* copy up to skb headlen */
+ while (count && (copy > 0)) {
+ size = min_t(unsigned int, copy, from->iov_len - offset);
+ if (copy_from_user(skb->data + offset1, from->iov_base + offset,
+ size))
+ return -EFAULT;
+ if (copy > size) {
+ ++from;
+ --count;
+ }
+ copy -= size;
+ offset1 += size;
+ offset = 0;
+ }
+
+ if (len == offset1)
+ return 0;
+
+ while (count--) {
+ struct page *page[MAX_SKB_FRAGS];
+ int num_pages;
+ unsigned long base;
+
+ len = from->iov_len - offset1;
+ if (!len) {
+ offset1 = 0;
+ ++from;
+ continue;
+ }
+ base = (unsigned long)from->iov_base + offset1;
+ size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT;
+ num_pages = get_user_pages_fast(base, size, 0, &page[i]);
+ if ((num_pages != size) ||
+ (num_pages > MAX_SKB_FRAGS - skb_shinfo(skb)->nr_frags))
+ /* put_page is in skb free */
+ return -EFAULT;
+ skb->data_len += len;
+ skb->len += len;
+ skb->truesize += len;
+ atomic_add(len, &skb->sk->sk_wmem_alloc);
+ while (len) {
+ 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 += size;
+ len -= size;
+ i++;
+ }
+ offset1 = 0;
+ ++from;
+ }
+ return 0;
+}
+
/*
* macvtap_skb_from_vnet_hdr and macvtap_skb_to_vnet_hdr should
* be shared with the tun/tap driver.
/* Get packet from user space buffer */
-static ssize_t macvtap_get_user(struct macvtap_queue *q,
- const struct iovec *iv, size_t count,
- int noblock)
+static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
+ const struct iovec *iv, unsigned long total_len,
+ size_t count, int noblock)
{
struct sk_buff *skb;
struct macvlan_dev *vlan;
- size_t len = count;
+ unsigned long len = total_len;
int err;
struct virtio_net_hdr vnet_hdr = { 0 };
int vnet_hdr_len = 0;
+ int copylen;
+ bool zerocopy = false;
if (q->flags & IFF_VNET_HDR) {
vnet_hdr_len = q->vnet_hdr_sz;
if (unlikely(len < ETH_HLEN))
goto err;
- skb = macvtap_alloc_skb(&q->sk, NET_IP_ALIGN, len, vnet_hdr.hdr_len,
- noblock, &err);
+ if (m && m->msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY))
+ zerocopy = true;
+
+ if (zerocopy) {
+ /* There are 256 bytes to be copied in skb, so there is enough
+ * room for skb expand head in case it is used.
+ * The rest buffer is mapped from userspace.
+ */
+ copylen = vnet_hdr.hdr_len;
+ if (!copylen)
+ copylen = GOODCOPY_LEN;
+ } else
+ copylen = len;
+
+ skb = macvtap_alloc_skb(&q->sk, NET_IP_ALIGN, copylen,
+ vnet_hdr.hdr_len, noblock, &err);
if (!skb)
goto err;
- err = skb_copy_datagram_from_iovec(skb, 0, iv, vnet_hdr_len, len);
+ if (zerocopy) {
+ err = zerocopy_sg_from_iovec(skb, iv, vnet_hdr_len, count);
+ skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
+ } else
+ err = skb_copy_datagram_from_iovec(skb, 0, iv, vnet_hdr_len,
+ len);
if (err)
goto err_kfree;
rcu_read_lock_bh();
vlan = rcu_dereference_bh(q->vlan);
+ /* copy skb_ubuf_info for callback when skb has no error */
+ if (zerocopy)
+ skb_shinfo(skb)->destructor_arg = m->msg_control;
if (vlan)
macvlan_start_xmit(skb, vlan->dev);
else
kfree_skb(skb);
rcu_read_unlock_bh();
- return count;
+ return total_len;
err_kfree:
kfree_skb(skb);
ssize_t result = -ENOLINK;
struct macvtap_queue *q = file->private_data;
- result = macvtap_get_user(q, iv, iov_length(iv, count),
- file->f_flags & O_NONBLOCK);
+ result = macvtap_get_user(q, NULL, iv, iov_length(iv, count), count,
+ file->f_flags & O_NONBLOCK);
return result;
}
struct msghdr *m, size_t total_len)
{
struct macvtap_queue *q = container_of(sock, struct macvtap_queue, sock);
- return macvtap_get_user(q, m->msg_iov, total_len,
+ return macvtap_get_user(q, m, m->msg_iov, total_len, m->msg_iovlen,
m->msg_flags & MSG_DONTWAIT);
}
}
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;
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:
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);