From 20d29d7a916a47bf533b5709437fe735b6b5b79e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 30 Jan 2010 12:24:26 +0000 Subject: net: macvtap driver In order to use macvlan with qemu and other tools that require a tap file descriptor, the macvtap driver adds a small backend with a character device with the same interface as the tun driver, with a minimum set of features. Macvtap interfaces are created in the same way as macvlan interfaces using ip link, but the netif is just used as a handle for configuration and accounting, while the data goes through the chardev. Each macvtap interface has its own character device, simplifying permission management significantly over the generic tun/tap driver. Cc: Patrick McHardy Cc: Stephen Hemminger Cc: David S. Miller" Cc: "Michael S. Tsirkin" Cc: Herbert Xu Cc: Or Gerlitz Cc: netdev@vger.kernel.org Cc: bridge@lists.linux-foundation.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/macvtap.c | 581 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 581 insertions(+) create mode 100644 drivers/net/macvtap.c (limited to 'drivers/net/macvtap.c') diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c new file mode 100644 index 00000000000..ad1f6ef8930 --- /dev/null +++ b/drivers/net/macvtap.c @@ -0,0 +1,581 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +/* + * A macvtap queue is the central object of this driver, it connects + * an open character device to a macvlan interface. There can be + * multiple queues on one interface, which map back to queues + * implemented in hardware on the underlying device. + * + * macvtap_proto is used to allocate queues through the sock allocation + * mechanism. + * + * TODO: multiqueue support is currently not implemented, even though + * macvtap is basically prepared for that. We will need to add this + * here as well as in virtio-net and qemu to get line rate on 10gbit + * adapters from a guest. + */ +struct macvtap_queue { + struct sock sk; + struct socket sock; + struct macvlan_dev *vlan; + struct file *file; +}; + +static struct proto macvtap_proto = { + .name = "macvtap", + .owner = THIS_MODULE, + .obj_size = sizeof (struct macvtap_queue), +}; + +/* + * 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. + */ +static unsigned int macvtap_major; +#define MACVTAP_NUM_DEVS 65536 +static struct class *macvtap_class; +static struct cdev macvtap_cdev; + +/* + * RCU usage: + * The macvtap_queue is referenced both from the chardev struct file + * and from the struct macvlan_dev using rcu_read_lock. + * + * We never actually update the contents of a macvtap_queue atomically + * with RCU but it is used for race-free destruction of a queue when + * either the file or the macvlan_dev goes away. Pointers back to + * the dev and the file are implicitly valid as long as the queue + * exists. + * + * The callbacks from macvlan are always done with rcu_read_lock held + * already, while in the file_operations, we get it ourselves. + * + * When destroying a queue, we remove the pointers from the file and + * from the dev and then synchronize_rcu to make sure no thread is + * still using the queue. There may still be references to the struct + * sock inside of the queue from outbound SKBs, but these never + * reference back to the file or the dev. The data structure is freed + * through __sk_free when both our references and any pending SKBs + * are gone. + * + * macvtap_lock is only used to prevent multiple concurrent open() + * calls to assign a new vlan->tap pointer. It could be moved into + * the macvlan_dev itself but is extremely rarely used. + */ +static DEFINE_SPINLOCK(macvtap_lock); + +/* + * Choose the next free queue, for now there is only one + */ +static int macvtap_set_queue(struct net_device *dev, struct file *file, + struct macvtap_queue *q) +{ + struct macvlan_dev *vlan = netdev_priv(dev); + int err = -EBUSY; + + spin_lock(&macvtap_lock); + if (rcu_dereference(vlan->tap)) + goto out; + + err = 0; + q->vlan = vlan; + rcu_assign_pointer(vlan->tap, q); + + q->file = file; + rcu_assign_pointer(file->private_data, q); + +out: + spin_unlock(&macvtap_lock); + return err; +} + +/* + * We must destroy each queue exactly once, when either + * the netdev or the file go away. + * + * Using the spinlock makes sure that we don't get + * to the queue again after destroying it. + * + * synchronize_rcu serializes with the packet flow + * that uses rcu_read_lock. + */ +static void macvtap_del_queue(struct macvtap_queue **qp) +{ + struct macvtap_queue *q; + + spin_lock(&macvtap_lock); + q = rcu_dereference(*qp); + if (!q) { + spin_unlock(&macvtap_lock); + return; + } + + rcu_assign_pointer(q->vlan->tap, NULL); + rcu_assign_pointer(q->file->private_data, NULL); + spin_unlock(&macvtap_lock); + + synchronize_rcu(); + sock_put(&q->sk); +} + +/* + * Since we only support one queue, just dereference the pointer. + */ +static struct macvtap_queue *macvtap_get_queue(struct net_device *dev, + struct sk_buff *skb) +{ + struct macvlan_dev *vlan = netdev_priv(dev); + + return rcu_dereference(vlan->tap); +} + +static void macvtap_del_queues(struct net_device *dev) +{ + struct macvlan_dev *vlan = netdev_priv(dev); + macvtap_del_queue(&vlan->tap); +} + +static inline struct macvtap_queue *macvtap_file_get_queue(struct file *file) +{ + rcu_read_lock_bh(); + return rcu_dereference(file->private_data); +} + +static inline void macvtap_file_put_queue(void) +{ + rcu_read_unlock_bh(); +} + +/* + * Forward happens for data that gets sent from one macvlan + * endpoint to another one in bridge mode. We just take + * the skb and put it into the receive queue. + */ +static int macvtap_forward(struct net_device *dev, struct sk_buff *skb) +{ + struct macvtap_queue *q = macvtap_get_queue(dev, skb); + if (!q) + return -ENOLINK; + + skb_queue_tail(&q->sk.sk_receive_queue, skb); + wake_up(q->sk.sk_sleep); + return 0; +} + +/* + * Receive is for data from the external interface (lowerdev), + * in case of macvtap, we can treat that the same way as + * forward, which macvlan cannot. + */ +static int macvtap_receive(struct sk_buff *skb) +{ + skb_push(skb, ETH_HLEN); + return macvtap_forward(skb->dev, skb); +} + +static int macvtap_newlink(struct net *src_net, + struct net_device *dev, + struct nlattr *tb[], + struct nlattr *data[]) +{ + struct device *classdev; + dev_t devt; + int err; + + err = macvlan_common_newlink(src_net, dev, tb, data, + macvtap_receive, macvtap_forward); + if (err) + goto out; + + devt = MKDEV(MAJOR(macvtap_major), dev->ifindex); + + 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); + } + +out: + return err; +} + +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); +} + +static struct rtnl_link_ops macvtap_link_ops __read_mostly = { + .kind = "macvtap", + .newlink = macvtap_newlink, + .dellink = macvtap_dellink, +}; + + +static void macvtap_sock_write_space(struct sock *sk) +{ + if (!sock_writeable(sk) || + !test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags)) + return; + + if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) + wake_up_interruptible_sync(sk->sk_sleep); +} + +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 macvtap_queue *q; + int err; + + err = -ENODEV; + 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); + if (!q) + goto out; + + init_waitqueue_head(&q->sock.wait); + q->sock.type = SOCK_RAW; + q->sock.state = SS_CONNECTED; + sock_init_data(&q->sock, &q->sk); + q->sk.sk_allocation = GFP_ATOMIC; /* for now */ + q->sk.sk_write_space = macvtap_sock_write_space; + + err = macvtap_set_queue(dev, file, q); + if (err) + sock_put(&q->sk); + +out: + if (dev) + dev_put(dev); + + return err; +} + +static int macvtap_release(struct inode *inode, struct file *file) +{ + macvtap_del_queue((struct macvtap_queue **)&file->private_data); + return 0; +} + +static unsigned int macvtap_poll(struct file *file, poll_table * wait) +{ + struct macvtap_queue *q = macvtap_file_get_queue(file); + unsigned int mask = POLLERR; + + if (!q) + goto out; + + mask = 0; + poll_wait(file, &q->sock.wait, wait); + + if (!skb_queue_empty(&q->sk.sk_receive_queue)) + mask |= POLLIN | POLLRDNORM; + + if (sock_writeable(&q->sk) || + (!test_and_set_bit(SOCK_ASYNC_NOSPACE, &q->sock.flags) && + sock_writeable(&q->sk))) + mask |= POLLOUT | POLLWRNORM; + +out: + macvtap_file_put_queue(); + return mask; +} + +/* 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) +{ + struct sk_buff *skb; + size_t len = count; + int err; + + if (unlikely(len < ETH_HLEN)) + return -EINVAL; + + skb = sock_alloc_send_skb(&q->sk, NET_IP_ALIGN + len, noblock, &err); + + if (!skb) { + macvlan_count_rx(q->vlan, 0, false, false); + return err; + } + + skb_reserve(skb, NET_IP_ALIGN); + skb_put(skb, count); + + if (skb_copy_datagram_from_iovec(skb, 0, iv, 0, len)) { + macvlan_count_rx(q->vlan, 0, false, false); + kfree_skb(skb); + return -EFAULT; + } + + skb_set_network_header(skb, ETH_HLEN); + + macvlan_start_xmit(skb, q->vlan->dev); + + return count; +} + +static ssize_t macvtap_aio_write(struct kiocb *iocb, const struct iovec *iv, + unsigned long count, loff_t pos) +{ + struct file *file = iocb->ki_filp; + ssize_t result = -ENOLINK; + struct macvtap_queue *q = macvtap_file_get_queue(file); + + if (!q) + goto out; + + result = macvtap_get_user(q, iv, iov_length(iv, count), + file->f_flags & O_NONBLOCK); +out: + macvtap_file_put_queue(); + return result; +} + +/* Put packet to the user space buffer */ +static ssize_t macvtap_put_user(struct macvtap_queue *q, + const struct sk_buff *skb, + const struct iovec *iv, int len) +{ + struct macvlan_dev *vlan = q->vlan; + int ret; + + len = min_t(int, skb->len, len); + + ret = skb_copy_datagram_const_iovec(skb, 0, iv, 0, len); + + macvlan_count_rx(vlan, len, ret == 0, 0); + + return ret ? ret : len; +} + +static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv, + unsigned long count, loff_t pos) +{ + struct file *file = iocb->ki_filp; + struct macvtap_queue *q = macvtap_file_get_queue(file); + + DECLARE_WAITQUEUE(wait, current); + struct sk_buff *skb; + ssize_t len, ret = 0; + + if (!q) { + ret = -ENOLINK; + goto out; + } + + len = iov_length(iv, count); + if (len < 0) { + ret = -EINVAL; + goto out; + } + + add_wait_queue(q->sk.sk_sleep, &wait); + while (len) { + current->state = TASK_INTERRUPTIBLE; + + /* Read frames from the queue */ + skb = skb_dequeue(&q->sk.sk_receive_queue); + if (!skb) { + if (file->f_flags & O_NONBLOCK) { + ret = -EAGAIN; + break; + } + if (signal_pending(current)) { + ret = -ERESTARTSYS; + break; + } + /* Nothing to read, let's sleep */ + schedule(); + continue; + } + ret = macvtap_put_user(q, skb, iv, len); + kfree_skb(skb); + break; + } + + current->state = TASK_RUNNING; + remove_wait_queue(q->sk.sk_sleep, &wait); + +out: + macvtap_file_put_queue(); + return ret; +} + +/* + * provide compatibility with generic tun/tap interface + */ +static long macvtap_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + struct macvtap_queue *q; + void __user *argp = (void __user *)arg; + struct ifreq __user *ifr = argp; + unsigned int __user *up = argp; + unsigned int u; + char devname[IFNAMSIZ]; + + switch (cmd) { + case TUNSETIFF: + /* ignore the name, just look at flags */ + if (get_user(u, &ifr->ifr_flags)) + return -EFAULT; + if (u != (IFF_TAP | IFF_NO_PI)) + return -EINVAL; + return 0; + + case TUNGETIFF: + q = macvtap_file_get_queue(file); + if (!q) + return -ENOLINK; + memcpy(devname, q->vlan->dev->name, sizeof(devname)); + macvtap_file_put_queue(); + + if (copy_to_user(&ifr->ifr_name, q->vlan->dev->name, IFNAMSIZ) || + put_user((TUN_TAP_DEV | TUN_NO_PI), &ifr->ifr_flags)) + return -EFAULT; + return 0; + + case TUNGETFEATURES: + if (put_user((IFF_TAP | IFF_NO_PI), up)) + return -EFAULT; + return 0; + + case TUNSETSNDBUF: + if (get_user(u, up)) + return -EFAULT; + + q = macvtap_file_get_queue(file); + q->sk.sk_sndbuf = u; + macvtap_file_put_queue(); + return 0; + + case TUNSETOFFLOAD: + /* let the user check for future flags */ + if (arg & ~(TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 | + TUN_F_TSO_ECN | TUN_F_UFO)) + return -EINVAL; + + /* TODO: add support for these, so far we don't + support any offload */ + if (arg & (TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 | + TUN_F_TSO_ECN | TUN_F_UFO)) + return -EINVAL; + + return 0; + + default: + return -EINVAL; + } +} + +#ifdef CONFIG_COMPAT +static long macvtap_compat_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + return macvtap_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); +} +#endif + +static const struct file_operations macvtap_fops = { + .owner = THIS_MODULE, + .open = macvtap_open, + .release = macvtap_release, + .aio_read = macvtap_aio_read, + .aio_write = macvtap_aio_write, + .poll = macvtap_poll, + .llseek = no_llseek, + .unlocked_ioctl = macvtap_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = macvtap_compat_ioctl, +#endif +}; + +static int macvtap_init(void) +{ + int err; + + err = alloc_chrdev_region(&macvtap_major, 0, + MACVTAP_NUM_DEVS, "macvtap"); + if (err) + goto out1; + + cdev_init(&macvtap_cdev, &macvtap_fops); + err = cdev_add(&macvtap_cdev, macvtap_major, MACVTAP_NUM_DEVS); + if (err) + goto out2; + + macvtap_class = class_create(THIS_MODULE, "macvtap"); + if (IS_ERR(macvtap_class)) { + err = PTR_ERR(macvtap_class); + goto out3; + } + + err = macvlan_link_register(&macvtap_link_ops); + if (err) + goto out4; + + return 0; + +out4: + class_unregister(macvtap_class); +out3: + cdev_del(&macvtap_cdev); +out2: + unregister_chrdev_region(macvtap_major, MACVTAP_NUM_DEVS); +out1: + return err; +} +module_init(macvtap_init); + +static void macvtap_exit(void) +{ + rtnl_link_unregister(&macvtap_link_ops); + class_unregister(macvtap_class); + cdev_del(&macvtap_cdev); + unregister_chrdev_region(macvtap_major, MACVTAP_NUM_DEVS); +} +module_exit(macvtap_exit); + +MODULE_ALIAS_RTNL_LINK("macvtap"); +MODULE_AUTHOR("Arnd Bergmann "); +MODULE_LICENSE("GPL"); -- cgit v1.2.3-70-g09d2 From 564517e804c9c6d4e29c270bfc1517404d27107b Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 11 Feb 2010 05:55:39 +0000 Subject: net/macvtap: fix reference counting The RCU usage in the original code was broken because there are cases where we possibly sleep with rcu_read_lock held. As a fix, change the macvtap_file_get_queue to get a reference on the socket and the netdev instead of taking the full rcu_read_lock. Also, change macvtap_file_get_queue failure case to not require a subsequent macvtap_file_put_queue, as pointed out by Ed Swierk. Signed-off-by: Arnd Bergmann Cc: Ed Swierk Cc: Sridhar Samudrala Acked-by: Sridhar Samudrala Acked-by: Ed Swierk Signed-off-by: David S. Miller --- drivers/net/macvtap.c | 35 ++++++++++++++++++++++------------- 1 file changed, 22 insertions(+), 13 deletions(-) (limited to 'drivers/net/macvtap.c') diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index ad1f6ef8930..fe7656bf68c 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -70,7 +70,8 @@ static struct cdev macvtap_cdev; * exists. * * The callbacks from macvlan are always done with rcu_read_lock held - * already, while in the file_operations, we get it ourselves. + * already. For calls from file_operations, we use the rcu_read_lock_bh + * to get a reference count on the socket and the device. * * When destroying a queue, we remove the pointers from the file and * from the dev and then synchronize_rcu to make sure no thread is @@ -159,13 +160,21 @@ static void macvtap_del_queues(struct net_device *dev) static inline struct macvtap_queue *macvtap_file_get_queue(struct file *file) { + struct macvtap_queue *q; rcu_read_lock_bh(); - return rcu_dereference(file->private_data); + q = rcu_dereference(file->private_data); + if (q) { + sock_hold(&q->sk); + dev_hold(q->vlan->dev); + } + rcu_read_unlock_bh(); + return q; } -static inline void macvtap_file_put_queue(void) +static inline void macvtap_file_put_queue(struct macvtap_queue *q) { - rcu_read_unlock_bh(); + sock_put(&q->sk); + dev_put(q->vlan->dev); } /* @@ -314,8 +323,8 @@ static unsigned int macvtap_poll(struct file *file, poll_table * wait) sock_writeable(&q->sk))) mask |= POLLOUT | POLLWRNORM; + macvtap_file_put_queue(q); out: - macvtap_file_put_queue(); return mask; } @@ -366,8 +375,8 @@ static ssize_t macvtap_aio_write(struct kiocb *iocb, const struct iovec *iv, result = macvtap_get_user(q, iv, iov_length(iv, count), file->f_flags & O_NONBLOCK); + macvtap_file_put_queue(q); out: - macvtap_file_put_queue(); return result; } @@ -398,10 +407,8 @@ static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv, struct sk_buff *skb; ssize_t len, ret = 0; - if (!q) { - ret = -ENOLINK; - goto out; - } + if (!q) + return -ENOLINK; len = iov_length(iv, count); if (len < 0) { @@ -437,7 +444,7 @@ static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv, remove_wait_queue(q->sk.sk_sleep, &wait); out: - macvtap_file_put_queue(); + macvtap_file_put_queue(q); return ret; } @@ -468,7 +475,7 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd, if (!q) return -ENOLINK; memcpy(devname, q->vlan->dev->name, sizeof(devname)); - macvtap_file_put_queue(); + macvtap_file_put_queue(q); if (copy_to_user(&ifr->ifr_name, q->vlan->dev->name, IFNAMSIZ) || put_user((TUN_TAP_DEV | TUN_NO_PI), &ifr->ifr_flags)) @@ -485,8 +492,10 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd, return -EFAULT; q = macvtap_file_get_queue(file); + if (!q) + return -ENOLINK; q->sk.sk_sndbuf = u; - macvtap_file_put_queue(); + macvtap_file_put_queue(q); return 0; case TUNSETOFFLOAD: -- cgit v1.2.3-70-g09d2 From 02df55d28c6001a3cdb7a997a34a0b01f01d015e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 18 Feb 2010 05:45:36 +0000 Subject: macvtap: rework object lifetime rules This reworks the change done by the previous patch in a more complete way. The original macvtap code has a number of problems resulting from the use of RCU for protecting the access to struct macvtap_queue from open files. This includes - need for GFP_ATOMIC allocations for skbs - potential deadlocks when copy_*_user sleeps - inability to work with vhost-net Changing the lifetime of macvtap_queue to always depend on the open file solves all these. The RCU reference simply moves one step down to the reference on the macvlan_dev, which we only need for nonblocking operations. Signed-off-by: Arnd Bergmann Acked-by: Sridhar Samudrala Signed-off-by: David S. Miller --- drivers/net/macvtap.c | 183 +++++++++++++++++++++++++------------------------- 1 file changed, 91 insertions(+), 92 deletions(-) (limited to 'drivers/net/macvtap.c') diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index fe7656bf68c..70509974976 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -60,30 +60,19 @@ static struct cdev macvtap_cdev; /* * RCU usage: - * The macvtap_queue is referenced both from the chardev struct file - * and from the struct macvlan_dev using rcu_read_lock. + * The macvtap_queue and the macvlan_dev are loosely coupled, the + * pointers from one to the other can only be read while rcu_read_lock + * or macvtap_lock is held. * - * We never actually update the contents of a macvtap_queue atomically - * with RCU but it is used for race-free destruction of a queue when - * either the file or the macvlan_dev goes away. Pointers back to - * the dev and the file are implicitly valid as long as the queue - * exists. + * Both the file and the macvlan_dev hold a reference on the macvtap_queue + * through sock_hold(&q->sk). When the macvlan_dev goes away first, + * q->vlan becomes inaccessible. When the files gets closed, + * macvtap_get_queue() fails. * - * The callbacks from macvlan are always done with rcu_read_lock held - * already. For calls from file_operations, we use the rcu_read_lock_bh - * to get a reference count on the socket and the device. - * - * When destroying a queue, we remove the pointers from the file and - * from the dev and then synchronize_rcu to make sure no thread is - * still using the queue. There may still be references to the struct - * sock inside of the queue from outbound SKBs, but these never - * reference back to the file or the dev. The data structure is freed - * through __sk_free when both our references and any pending SKBs - * are gone. - * - * macvtap_lock is only used to prevent multiple concurrent open() - * calls to assign a new vlan->tap pointer. It could be moved into - * the macvlan_dev itself but is extremely rarely used. + * There may still be references to the struct sock inside of the + * queue from outbound SKBs, but these never reference back to the + * file or the dev. The data structure is freed through __sk_free + * when both our references and any pending SKBs are gone. */ static DEFINE_SPINLOCK(macvtap_lock); @@ -101,11 +90,12 @@ static int macvtap_set_queue(struct net_device *dev, struct file *file, goto out; err = 0; - q->vlan = vlan; + rcu_assign_pointer(q->vlan, vlan); rcu_assign_pointer(vlan->tap, q); + sock_hold(&q->sk); q->file = file; - rcu_assign_pointer(file->private_data, q); + file->private_data = q; out: spin_unlock(&macvtap_lock); @@ -113,28 +103,25 @@ out: } /* - * We must destroy each queue exactly once, when either - * the netdev or the file go away. + * The file owning the queue got closed, give up both + * the reference that the files holds as well as the + * one from the macvlan_dev if that still exists. * * Using the spinlock makes sure that we don't get * to the queue again after destroying it. - * - * synchronize_rcu serializes with the packet flow - * that uses rcu_read_lock. */ -static void macvtap_del_queue(struct macvtap_queue **qp) +static void macvtap_put_queue(struct macvtap_queue *q) { - struct macvtap_queue *q; + struct macvlan_dev *vlan; spin_lock(&macvtap_lock); - q = rcu_dereference(*qp); - if (!q) { - spin_unlock(&macvtap_lock); - return; + vlan = rcu_dereference(q->vlan); + if (vlan) { + rcu_assign_pointer(vlan->tap, NULL); + rcu_assign_pointer(q->vlan, NULL); + sock_put(&q->sk); } - rcu_assign_pointer(q->vlan->tap, NULL); - rcu_assign_pointer(q->file->private_data, NULL); spin_unlock(&macvtap_lock); synchronize_rcu(); @@ -152,29 +139,29 @@ static struct macvtap_queue *macvtap_get_queue(struct net_device *dev, return rcu_dereference(vlan->tap); } +/* + * The net_device is going away, give up the reference + * that it holds on the queue (all the queues one day) + * and safely set the pointer from the queues to NULL. + */ static void macvtap_del_queues(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); - macvtap_del_queue(&vlan->tap); -} - -static inline struct macvtap_queue *macvtap_file_get_queue(struct file *file) -{ struct macvtap_queue *q; - rcu_read_lock_bh(); - q = rcu_dereference(file->private_data); - if (q) { - sock_hold(&q->sk); - dev_hold(q->vlan->dev); + + spin_lock(&macvtap_lock); + q = rcu_dereference(vlan->tap); + if (!q) { + spin_unlock(&macvtap_lock); + return; } - rcu_read_unlock_bh(); - return q; -} -static inline void macvtap_file_put_queue(struct macvtap_queue *q) -{ + rcu_assign_pointer(vlan->tap, NULL); + rcu_assign_pointer(q->vlan, NULL); + spin_unlock(&macvtap_lock); + + synchronize_rcu(); sock_put(&q->sk); - dev_put(q->vlan->dev); } /* @@ -284,7 +271,6 @@ static int macvtap_open(struct inode *inode, struct file *file) q->sock.type = SOCK_RAW; q->sock.state = SS_CONNECTED; sock_init_data(&q->sock, &q->sk); - q->sk.sk_allocation = GFP_ATOMIC; /* for now */ q->sk.sk_write_space = macvtap_sock_write_space; err = macvtap_set_queue(dev, file, q); @@ -300,13 +286,14 @@ out: static int macvtap_release(struct inode *inode, struct file *file) { - macvtap_del_queue((struct macvtap_queue **)&file->private_data); + struct macvtap_queue *q = file->private_data; + macvtap_put_queue(q); return 0; } static unsigned int macvtap_poll(struct file *file, poll_table * wait) { - struct macvtap_queue *q = macvtap_file_get_queue(file); + struct macvtap_queue *q = file->private_data; unsigned int mask = POLLERR; if (!q) @@ -323,7 +310,6 @@ static unsigned int macvtap_poll(struct file *file, poll_table * wait) sock_writeable(&q->sk))) mask |= POLLOUT | POLLWRNORM; - macvtap_file_put_queue(q); out: return mask; } @@ -334,6 +320,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, int noblock) { struct sk_buff *skb; + struct macvlan_dev *vlan; size_t len = count; int err; @@ -341,26 +328,37 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, return -EINVAL; skb = sock_alloc_send_skb(&q->sk, NET_IP_ALIGN + len, noblock, &err); - - if (!skb) { - macvlan_count_rx(q->vlan, 0, false, false); - return err; - } + if (!skb) + goto err; skb_reserve(skb, NET_IP_ALIGN); skb_put(skb, count); - if (skb_copy_datagram_from_iovec(skb, 0, iv, 0, len)) { - macvlan_count_rx(q->vlan, 0, false, false); - kfree_skb(skb); - return -EFAULT; - } + err = skb_copy_datagram_from_iovec(skb, 0, iv, 0, len); + if (err) + goto err; skb_set_network_header(skb, ETH_HLEN); - - macvlan_start_xmit(skb, q->vlan->dev); + rcu_read_lock_bh(); + vlan = rcu_dereference(q->vlan); + if (vlan) + macvlan_start_xmit(skb, vlan->dev); + else + kfree_skb(skb); + rcu_read_unlock_bh(); return count; + +err: + rcu_read_lock_bh(); + vlan = rcu_dereference(q->vlan); + if (vlan) + macvlan_count_rx(q->vlan, 0, false, false); + rcu_read_unlock_bh(); + + kfree_skb(skb); + + return err; } static ssize_t macvtap_aio_write(struct kiocb *iocb, const struct iovec *iv, @@ -368,15 +366,10 @@ static ssize_t macvtap_aio_write(struct kiocb *iocb, const struct iovec *iv, { struct file *file = iocb->ki_filp; ssize_t result = -ENOLINK; - struct macvtap_queue *q = macvtap_file_get_queue(file); - - if (!q) - goto out; + struct macvtap_queue *q = file->private_data; result = macvtap_get_user(q, iv, iov_length(iv, count), file->f_flags & O_NONBLOCK); - macvtap_file_put_queue(q); -out: return result; } @@ -385,14 +378,17 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q, const struct sk_buff *skb, const struct iovec *iv, int len) { - struct macvlan_dev *vlan = q->vlan; + struct macvlan_dev *vlan; int ret; len = min_t(int, skb->len, len); ret = skb_copy_datagram_const_iovec(skb, 0, iv, 0, len); + rcu_read_lock_bh(); + vlan = rcu_dereference(q->vlan); macvlan_count_rx(vlan, len, ret == 0, 0); + rcu_read_unlock_bh(); return ret ? ret : len; } @@ -401,14 +397,16 @@ static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv, unsigned long count, loff_t pos) { struct file *file = iocb->ki_filp; - struct macvtap_queue *q = macvtap_file_get_queue(file); + struct macvtap_queue *q = file->private_data; DECLARE_WAITQUEUE(wait, current); struct sk_buff *skb; ssize_t len, ret = 0; - if (!q) - return -ENOLINK; + if (!q) { + ret = -ENOLINK; + goto out; + } len = iov_length(iv, count); if (len < 0) { @@ -444,7 +442,6 @@ static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv, remove_wait_queue(q->sk.sk_sleep, &wait); out: - macvtap_file_put_queue(q); return ret; } @@ -454,12 +451,13 @@ out: static long macvtap_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { - struct macvtap_queue *q; + struct macvtap_queue *q = file->private_data; + struct macvlan_dev *vlan; void __user *argp = (void __user *)arg; struct ifreq __user *ifr = argp; unsigned int __user *up = argp; unsigned int u; - char devname[IFNAMSIZ]; + int ret; switch (cmd) { case TUNSETIFF: @@ -471,16 +469,21 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd, return 0; case TUNGETIFF: - q = macvtap_file_get_queue(file); - if (!q) + rcu_read_lock_bh(); + vlan = rcu_dereference(q->vlan); + if (vlan) + dev_hold(vlan->dev); + rcu_read_unlock_bh(); + + if (!vlan) return -ENOLINK; - memcpy(devname, q->vlan->dev->name, sizeof(devname)); - macvtap_file_put_queue(q); + ret = 0; if (copy_to_user(&ifr->ifr_name, q->vlan->dev->name, IFNAMSIZ) || put_user((TUN_TAP_DEV | TUN_NO_PI), &ifr->ifr_flags)) - return -EFAULT; - return 0; + ret = -EFAULT; + dev_put(vlan->dev); + return ret; case TUNGETFEATURES: if (put_user((IFF_TAP | IFF_NO_PI), up)) @@ -491,11 +494,7 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd, if (get_user(u, up)) return -EFAULT; - q = macvtap_file_get_queue(file); - if (!q) - return -ENOLINK; q->sk.sk_sndbuf = u; - macvtap_file_put_queue(q); return 0; case TUNSETOFFLOAD: -- cgit v1.2.3-70-g09d2 From 501c774cb13c3ef8fb7fc5f08fa19473f7d9a0db Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 18 Feb 2010 05:46:50 +0000 Subject: net/macvtap: add vhost support This adds support for passing a macvtap file descriptor into vhost-net, much like we already do for tun/tap. Most of the new code is taken from the respective patch in the tun driver and may get consolidated in the future. Signed-off-by: Arnd Bergmann Acked-by: Sridhar Samudrala Signed-off-by: David S. Miller --- drivers/net/macvtap.c | 98 ++++++++++++++++++++++++++++++++++++---------- drivers/vhost/Kconfig | 2 +- drivers/vhost/net.c | 8 +++- include/linux/if_macvlan.h | 13 ++++++ 4 files changed, 97 insertions(+), 24 deletions(-) (limited to 'drivers/net/macvtap.c') diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 70509974976..e354501ab29 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -58,6 +58,8 @@ static unsigned int macvtap_major; static struct class *macvtap_class; static struct cdev macvtap_cdev; +static const struct proto_ops macvtap_socket_ops; + /* * RCU usage: * The macvtap_queue and the macvlan_dev are loosely coupled, the @@ -176,7 +178,7 @@ static int macvtap_forward(struct net_device *dev, struct sk_buff *skb) return -ENOLINK; skb_queue_tail(&q->sk.sk_receive_queue, skb); - wake_up(q->sk.sk_sleep); + wake_up_interruptible_poll(q->sk.sk_sleep, POLLIN | POLLRDNORM | POLLRDBAND); return 0; } @@ -242,7 +244,7 @@ static void macvtap_sock_write_space(struct sock *sk) return; if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible_sync(sk->sk_sleep); + wake_up_interruptible_poll(sk->sk_sleep, POLLOUT | POLLWRNORM | POLLWRBAND); } static int macvtap_open(struct inode *inode, struct file *file) @@ -270,6 +272,8 @@ static int macvtap_open(struct inode *inode, struct file *file) init_waitqueue_head(&q->sock.wait); q->sock.type = SOCK_RAW; q->sock.state = SS_CONNECTED; + q->sock.file = file; + q->sock.ops = &macvtap_socket_ops; sock_init_data(&q->sock, &q->sk); q->sk.sk_write_space = macvtap_sock_write_space; @@ -387,32 +391,20 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q, rcu_read_lock_bh(); vlan = rcu_dereference(q->vlan); - macvlan_count_rx(vlan, len, ret == 0, 0); + if (vlan) + macvlan_count_rx(vlan, len, ret == 0, 0); rcu_read_unlock_bh(); return ret ? ret : len; } -static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv, - unsigned long count, loff_t pos) +static ssize_t macvtap_do_read(struct macvtap_queue *q, struct kiocb *iocb, + const struct iovec *iv, unsigned long len, + int noblock) { - struct file *file = iocb->ki_filp; - struct macvtap_queue *q = file->private_data; - DECLARE_WAITQUEUE(wait, current); struct sk_buff *skb; - ssize_t len, ret = 0; - - if (!q) { - ret = -ENOLINK; - goto out; - } - - len = iov_length(iv, count); - if (len < 0) { - ret = -EINVAL; - goto out; - } + ssize_t ret = 0; add_wait_queue(q->sk.sk_sleep, &wait); while (len) { @@ -421,7 +413,7 @@ static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv, /* Read frames from the queue */ skb = skb_dequeue(&q->sk.sk_receive_queue); if (!skb) { - if (file->f_flags & O_NONBLOCK) { + if (noblock) { ret = -EAGAIN; break; } @@ -440,7 +432,24 @@ static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv, current->state = TASK_RUNNING; remove_wait_queue(q->sk.sk_sleep, &wait); + return ret; +} + +static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv, + unsigned long count, loff_t pos) +{ + struct file *file = iocb->ki_filp; + struct macvtap_queue *q = file->private_data; + ssize_t len, ret = 0; + len = iov_length(iv, count); + if (len < 0) { + ret = -EINVAL; + goto out; + } + + ret = macvtap_do_read(q, iocb, iv, len, file->f_flags & O_NONBLOCK); + ret = min_t(ssize_t, ret, len); /* XXX copied from tun.c. Why? */ out: return ret; } @@ -538,6 +547,53 @@ static const struct file_operations macvtap_fops = { #endif }; +static int macvtap_sendmsg(struct kiocb *iocb, struct socket *sock, + 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, + m->msg_flags & MSG_DONTWAIT); +} + +static int macvtap_recvmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t total_len, + int flags) +{ + struct macvtap_queue *q = container_of(sock, struct macvtap_queue, sock); + int ret; + if (flags & ~(MSG_DONTWAIT|MSG_TRUNC)) + return -EINVAL; + ret = macvtap_do_read(q, 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 macvtap_socket_ops = { + .sendmsg = macvtap_sendmsg, + .recvmsg = macvtap_recvmsg, +}; + +/* 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 *macvtap_get_socket(struct file *file) +{ + struct macvtap_queue *q; + if (file->f_op != &macvtap_fops) + return ERR_PTR(-EINVAL); + q = file->private_data; + if (!q) + return ERR_PTR(-EBADFD); + return &q->sock; +} +EXPORT_SYMBOL_GPL(macvtap_get_socket); + static int macvtap_init(void) { int err; diff --git a/drivers/vhost/Kconfig b/drivers/vhost/Kconfig index 9e9355367bb..e4e2fd1b510 100644 --- a/drivers/vhost/Kconfig +++ b/drivers/vhost/Kconfig @@ -1,6 +1,6 @@ config VHOST_NET tristate "Host kernel accelerator for virtio net (EXPERIMENTAL)" - depends on NET && EVENTFD && (TUN || !TUN) && EXPERIMENTAL + depends on NET && EVENTFD && (TUN || !TUN) && (MACVTAP || !MACVTAP) && EXPERIMENTAL ---help--- This kernel module can be loaded in host kernel to accelerate guest networking with virtio_net. Not to be confused with virtio_net diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 4c8928319e1..91a324cc229 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -22,6 +22,7 @@ #include #include #include +#include #include @@ -452,13 +453,16 @@ err: return ERR_PTR(r); } -static struct socket *get_tun_socket(int fd) +static struct socket *get_tap_socket(int fd) { struct file *file = fget(fd); struct socket *sock; if (!file) return ERR_PTR(-EBADF); sock = tun_get_socket(file); + if (!IS_ERR(sock)) + return sock; + sock = macvtap_get_socket(file); if (IS_ERR(sock)) fput(file); return sock; @@ -473,7 +477,7 @@ static struct socket *get_socket(int fd) sock = get_raw_socket(fd); if (!IS_ERR(sock)) return sock; - sock = get_tun_socket(fd); + sock = get_tap_socket(fd); if (!IS_ERR(sock)) return sock; return ERR_PTR(-ENOTSOCK); diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index f9cb9ba1475..b78a712247d 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -7,6 +7,19 @@ #include #include +#if defined(CONFIG_MACVTAP) || defined(CONFIG_MACVTAP_MODULE) +struct socket *macvtap_get_socket(struct file *); +#else +#include +#include +struct file; +struct socket; +static inline struct socket *macvtap_get_socket(struct file *f) +{ + return ERR_PTR(-EINVAL); +} +#endif /* CONFIG_MACVTAP */ + struct macvlan_port; struct macvtap_queue; -- cgit v1.2.3-70-g09d2 From b9fb9ee07e67fce0b7bfd517a48710465706c30a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 18 Feb 2010 05:48:17 +0000 Subject: macvtap: add GSO/csum offload support Added flags field to macvtap_queue to enable/disable processing of virtio_net_hdr via IFF_VNET_HDR. This flag is checked to prepend virtio_net_hdr in the receive path and process/skip virtio_net_hdr in the send path. Original patch by Sridhar, further changes by Arnd. Signed-off-by: Sridhar Samudrala Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/macvtap.c | 206 ++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 182 insertions(+), 24 deletions(-) (limited to 'drivers/net/macvtap.c') diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index e354501ab29..55ceae09738 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -17,6 +17,7 @@ #include #include #include +#include /* * A macvtap queue is the central object of this driver, it connects @@ -37,6 +38,7 @@ struct macvtap_queue { struct socket sock; struct macvlan_dev *vlan; struct file *file; + unsigned int flags; }; static struct proto macvtap_proto = { @@ -276,6 +278,7 @@ 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->flags = IFF_VNET_HDR | IFF_NO_PI | IFF_TAP; err = macvtap_set_queue(dev, file, q); if (err) @@ -318,6 +321,111 @@ out: return mask; } +static inline struct sk_buff *macvtap_alloc_skb(struct sock *sk, size_t prepad, + size_t len, size_t linear, + int noblock, int *err) +{ + struct sk_buff *skb; + + /* Under a page? Don't bother with paged skb. */ + if (prepad + len < PAGE_SIZE || !linear) + linear = len; + + skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock, + err); + if (!skb) + return NULL; + + skb_reserve(skb, prepad); + skb_put(skb, linear); + skb->data_len = len - linear; + skb->len += len - linear; + + return skb; +} + +/* + * macvtap_skb_from_vnet_hdr and macvtap_skb_to_vnet_hdr should + * be shared with the tun/tap driver. + */ +static int macvtap_skb_from_vnet_hdr(struct sk_buff *skb, + struct virtio_net_hdr *vnet_hdr) +{ + unsigned short gso_type = 0; + if (vnet_hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { + switch (vnet_hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { + case VIRTIO_NET_HDR_GSO_TCPV4: + gso_type = SKB_GSO_TCPV4; + break; + case VIRTIO_NET_HDR_GSO_TCPV6: + gso_type = SKB_GSO_TCPV6; + break; + case VIRTIO_NET_HDR_GSO_UDP: + gso_type = SKB_GSO_UDP; + break; + default: + return -EINVAL; + } + + if (vnet_hdr->gso_type & VIRTIO_NET_HDR_GSO_ECN) + gso_type |= SKB_GSO_TCP_ECN; + + if (vnet_hdr->gso_size == 0) + return -EINVAL; + } + + if (vnet_hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) { + if (!skb_partial_csum_set(skb, vnet_hdr->csum_start, + vnet_hdr->csum_offset)) + return -EINVAL; + } + + if (vnet_hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { + skb_shinfo(skb)->gso_size = vnet_hdr->gso_size; + skb_shinfo(skb)->gso_type = gso_type; + + /* Header must be checked, and gso_segs computed. */ + skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; + skb_shinfo(skb)->gso_segs = 0; + } + return 0; +} + +static int macvtap_skb_to_vnet_hdr(const struct sk_buff *skb, + struct virtio_net_hdr *vnet_hdr) +{ + memset(vnet_hdr, 0, sizeof(*vnet_hdr)); + + if (skb_is_gso(skb)) { + struct skb_shared_info *sinfo = skb_shinfo(skb); + + /* This is a hint as to how much should be linear. */ + vnet_hdr->hdr_len = skb_headlen(skb); + vnet_hdr->gso_size = sinfo->gso_size; + if (sinfo->gso_type & SKB_GSO_TCPV4) + vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4; + else if (sinfo->gso_type & SKB_GSO_TCPV6) + vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6; + else if (sinfo->gso_type & SKB_GSO_UDP) + vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP; + else + BUG(); + if (sinfo->gso_type & SKB_GSO_TCP_ECN) + vnet_hdr->gso_type |= VIRTIO_NET_HDR_GSO_ECN; + } else + vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_NONE; + + if (skb->ip_summed == CHECKSUM_PARTIAL) { + vnet_hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; + vnet_hdr->csum_start = skb->csum_start - + skb_headroom(skb); + vnet_hdr->csum_offset = skb->csum_offset; + } /* else everything is zero */ + + return 0; +} + + /* Get packet from user space buffer */ static ssize_t macvtap_get_user(struct macvtap_queue *q, const struct iovec *iv, size_t count, @@ -327,22 +435,53 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct macvlan_dev *vlan; size_t len = count; int err; + struct virtio_net_hdr vnet_hdr = { 0 }; + int vnet_hdr_len = 0; + + if (q->flags & IFF_VNET_HDR) { + vnet_hdr_len = sizeof(vnet_hdr); + + err = -EINVAL; + if ((len -= vnet_hdr_len) < 0) + goto err; + + err = memcpy_fromiovecend((void *)&vnet_hdr, iv, 0, + vnet_hdr_len); + if (err < 0) + goto err; + if ((vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) && + vnet_hdr.csum_start + vnet_hdr.csum_offset + 2 > + vnet_hdr.hdr_len) + vnet_hdr.hdr_len = vnet_hdr.csum_start + + vnet_hdr.csum_offset + 2; + err = -EINVAL; + if (vnet_hdr.hdr_len > len) + goto err; + } + err = -EINVAL; if (unlikely(len < ETH_HLEN)) - return -EINVAL; + goto err; - skb = sock_alloc_send_skb(&q->sk, NET_IP_ALIGN + len, noblock, &err); + skb = macvtap_alloc_skb(&q->sk, NET_IP_ALIGN, len, vnet_hdr.hdr_len, + noblock, &err); if (!skb) goto err; - skb_reserve(skb, NET_IP_ALIGN); - skb_put(skb, count); - - err = skb_copy_datagram_from_iovec(skb, 0, iv, 0, len); + err = skb_copy_datagram_from_iovec(skb, 0, iv, vnet_hdr_len, len); if (err) - goto err; + goto err_kfree; skb_set_network_header(skb, ETH_HLEN); + skb_reset_mac_header(skb); + skb->protocol = eth_hdr(skb)->h_proto; + + if (vnet_hdr_len) { + err = macvtap_skb_from_vnet_hdr(skb, &vnet_hdr); + if (err) + goto err_kfree; + } + rcu_read_lock_bh(); vlan = rcu_dereference(q->vlan); if (vlan) @@ -353,15 +492,16 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, return count; +err_kfree: + kfree_skb(skb); + err: rcu_read_lock_bh(); vlan = rcu_dereference(q->vlan); if (vlan) - macvlan_count_rx(q->vlan, 0, false, false); + netdev_get_tx_queue(vlan->dev, 0)->tx_dropped++; rcu_read_unlock_bh(); - kfree_skb(skb); - return err; } @@ -384,10 +524,25 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q, { struct macvlan_dev *vlan; int ret; + int vnet_hdr_len = 0; + + if (q->flags & IFF_VNET_HDR) { + struct virtio_net_hdr vnet_hdr; + vnet_hdr_len = sizeof (vnet_hdr); + if ((len -= vnet_hdr_len) < 0) + return -EINVAL; + + ret = macvtap_skb_to_vnet_hdr(skb, &vnet_hdr); + if (ret) + return ret; + + if (memcpy_toiovecend(iv, (void *)&vnet_hdr, 0, vnet_hdr_len)) + return -EFAULT; + } len = min_t(int, skb->len, len); - ret = skb_copy_datagram_const_iovec(skb, 0, iv, 0, len); + ret = skb_copy_datagram_const_iovec(skb, 0, iv, vnet_hdr_len, len); rcu_read_lock_bh(); vlan = rcu_dereference(q->vlan); @@ -395,7 +550,7 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q, macvlan_count_rx(vlan, len, ret == 0, 0); rcu_read_unlock_bh(); - return ret ? ret : len; + return ret ? ret : (len + vnet_hdr_len); } static ssize_t macvtap_do_read(struct macvtap_queue *q, struct kiocb *iocb, @@ -473,9 +628,14 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd, /* ignore the name, just look at flags */ if (get_user(u, &ifr->ifr_flags)) return -EFAULT; - if (u != (IFF_TAP | IFF_NO_PI)) - return -EINVAL; - return 0; + + ret = 0; + if ((u & ~IFF_VNET_HDR) != (IFF_NO_PI | IFF_TAP)) + ret = -EINVAL; + else + q->flags = u; + + return ret; case TUNGETIFF: rcu_read_lock_bh(); @@ -489,13 +649,13 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd, ret = 0; if (copy_to_user(&ifr->ifr_name, q->vlan->dev->name, IFNAMSIZ) || - put_user((TUN_TAP_DEV | TUN_NO_PI), &ifr->ifr_flags)) + put_user(q->flags, &ifr->ifr_flags)) ret = -EFAULT; dev_put(vlan->dev); return ret; case TUNGETFEATURES: - if (put_user((IFF_TAP | IFF_NO_PI), up)) + if (put_user(IFF_TAP | IFF_NO_PI | IFF_VNET_HDR, up)) return -EFAULT; return 0; @@ -509,15 +669,13 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd, case TUNSETOFFLOAD: /* let the user check for future flags */ if (arg & ~(TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 | - TUN_F_TSO_ECN | TUN_F_UFO)) - return -EINVAL; - - /* TODO: add support for these, so far we don't - support any offload */ - if (arg & (TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 | - TUN_F_TSO_ECN | TUN_F_UFO)) + TUN_F_TSO_ECN | TUN_F_UFO)) return -EINVAL; + /* TODO: only accept frames with the features that + got enabled for forwarded frames */ + if (!(q->flags & IFF_VNET_HDR)) + return -EINVAL; return 0; default: -- cgit v1.2.3-70-g09d2