macvtap.c 15.1 KB
Newer Older
A
Arnd Bergmann 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60
#include <linux/etherdevice.h>
#include <linux/if_macvlan.h>
#include <linux/interrupt.h>
#include <linux/nsproxy.h>
#include <linux/compat.h>
#include <linux/if_tun.h>
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/cache.h>
#include <linux/sched.h>
#include <linux/types.h>
#include <linux/init.h>
#include <linux/wait.h>
#include <linux/cdev.h>
#include <linux/fs.h>

#include <net/net_namespace.h>
#include <net/rtnetlink.h>
#include <net/sock.h>

/*
 * 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;

A
Arnd Bergmann 已提交
61 62
static const struct proto_ops macvtap_socket_ops;

A
Arnd Bergmann 已提交
63 64
/*
 * RCU usage:
65 66 67
 * 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.
A
Arnd Bergmann 已提交
68
 *
69 70 71 72
 * 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.
A
Arnd Bergmann 已提交
73
 *
74 75 76 77
 * 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.
A
Arnd Bergmann 已提交
78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94
 */
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;
95
	rcu_assign_pointer(q->vlan, vlan);
A
Arnd Bergmann 已提交
96
	rcu_assign_pointer(vlan->tap, q);
97
	sock_hold(&q->sk);
A
Arnd Bergmann 已提交
98 99

	q->file = file;
100
	file->private_data = q;
A
Arnd Bergmann 已提交
101 102 103 104 105 106 107

out:
	spin_unlock(&macvtap_lock);
	return err;
}

/*
108 109 110
 * 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.
A
Arnd Bergmann 已提交
111 112 113 114
 *
 * Using the spinlock makes sure that we don't get
 * to the queue again after destroying it.
 */
115
static void macvtap_put_queue(struct macvtap_queue *q)
A
Arnd Bergmann 已提交
116
{
117
	struct macvlan_dev *vlan;
A
Arnd Bergmann 已提交
118 119

	spin_lock(&macvtap_lock);
120 121 122 123 124
	vlan = rcu_dereference(q->vlan);
	if (vlan) {
		rcu_assign_pointer(vlan->tap, NULL);
		rcu_assign_pointer(q->vlan, NULL);
		sock_put(&q->sk);
A
Arnd Bergmann 已提交
125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143
	}

	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);
}

144 145 146 147 148
/*
 * 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.
 */
A
Arnd Bergmann 已提交
149 150 151
static void macvtap_del_queues(struct net_device *dev)
{
	struct macvlan_dev *vlan = netdev_priv(dev);
152
	struct macvtap_queue *q;
153 154 155 156 157 158

	spin_lock(&macvtap_lock);
	q = rcu_dereference(vlan->tap);
	if (!q) {
		spin_unlock(&macvtap_lock);
		return;
159
	}
A
Arnd Bergmann 已提交
160

161 162 163 164 165
	rcu_assign_pointer(vlan->tap, NULL);
	rcu_assign_pointer(q->vlan, NULL);
	spin_unlock(&macvtap_lock);

	synchronize_rcu();
166
	sock_put(&q->sk);
A
Arnd Bergmann 已提交
167 168 169 170 171 172 173 174 175 176 177 178 179 180
}

/*
 * 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);
A
Arnd Bergmann 已提交
181
	wake_up_interruptible_poll(q->sk.sk_sleep, POLLIN | POLLRDNORM | POLLRDBAND);
A
Arnd Bergmann 已提交
182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246
	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))
A
Arnd Bergmann 已提交
247
		wake_up_interruptible_poll(sk->sk_sleep, POLLOUT | POLLWRNORM | POLLWRBAND);
A
Arnd Bergmann 已提交
248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274
}

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;
A
Arnd Bergmann 已提交
275 276
	q->sock.file = file;
	q->sock.ops = &macvtap_socket_ops;
A
Arnd Bergmann 已提交
277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292
	sock_init_data(&q->sock, &q->sk);
	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)
{
293 294
	struct macvtap_queue *q = file->private_data;
	macvtap_put_queue(q);
A
Arnd Bergmann 已提交
295 296 297 298 299
	return 0;
}

static unsigned int macvtap_poll(struct file *file, poll_table * wait)
{
300
	struct macvtap_queue *q = file->private_data;
A
Arnd Bergmann 已提交
301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326
	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:
	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;
327
	struct macvlan_dev *vlan;
A
Arnd Bergmann 已提交
328 329 330 331 332 333 334
	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);
335 336
	if (!skb)
		goto err;
A
Arnd Bergmann 已提交
337 338 339 340

	skb_reserve(skb, NET_IP_ALIGN);
	skb_put(skb, count);

341 342 343
	err = skb_copy_datagram_from_iovec(skb, 0, iv, 0, len);
	if (err)
		goto err;
A
Arnd Bergmann 已提交
344 345

	skb_set_network_header(skb, ETH_HLEN);
346 347 348 349 350 351 352
	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();
A
Arnd Bergmann 已提交
353 354

	return count;
355 356 357 358 359 360 361 362 363 364 365

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;
A
Arnd Bergmann 已提交
366 367 368 369 370 371 372
}

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;
373
	struct macvtap_queue *q = file->private_data;
A
Arnd Bergmann 已提交
374 375 376 377 378 379 380 381 382 383 384

	result = macvtap_get_user(q, iv, iov_length(iv, count),
			      file->f_flags & O_NONBLOCK);
	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)
{
385
	struct macvlan_dev *vlan;
A
Arnd Bergmann 已提交
386 387 388 389 390 391
	int ret;

	len = min_t(int, skb->len, len);

	ret = skb_copy_datagram_const_iovec(skb, 0, iv, 0, len);

392 393
	rcu_read_lock_bh();
	vlan = rcu_dereference(q->vlan);
A
Arnd Bergmann 已提交
394 395
	if (vlan)
		macvlan_count_rx(vlan, len, ret == 0, 0);
396
	rcu_read_unlock_bh();
A
Arnd Bergmann 已提交
397 398 399 400

	return ret ? ret : len;
}

A
Arnd Bergmann 已提交
401 402 403
static ssize_t macvtap_do_read(struct macvtap_queue *q, struct kiocb *iocb,
			       const struct iovec *iv, unsigned long len,
			       int noblock)
A
Arnd Bergmann 已提交
404 405 406
{
	DECLARE_WAITQUEUE(wait, current);
	struct sk_buff *skb;
A
Arnd Bergmann 已提交
407
	ssize_t ret = 0;
A
Arnd Bergmann 已提交
408 409 410 411 412 413 414 415

	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) {
A
Arnd Bergmann 已提交
416
			if (noblock) {
A
Arnd Bergmann 已提交
417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434
				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);
A
Arnd Bergmann 已提交
435 436 437 438 439 440 441 442 443
	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;
A
Arnd Bergmann 已提交
444

A
Arnd Bergmann 已提交
445 446 447 448 449 450 451 452
	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? */
A
Arnd Bergmann 已提交
453 454 455 456 457 458 459 460 461 462
out:
	return ret;
}

/*
 * provide compatibility with generic tun/tap interface
 */
static long macvtap_ioctl(struct file *file, unsigned int cmd,
			  unsigned long arg)
{
463 464
	struct macvtap_queue *q = file->private_data;
	struct macvlan_dev *vlan;
A
Arnd Bergmann 已提交
465 466 467 468
	void __user *argp = (void __user *)arg;
	struct ifreq __user *ifr = argp;
	unsigned int __user *up = argp;
	unsigned int u;
469
	int ret;
A
Arnd Bergmann 已提交
470 471 472 473 474 475 476 477 478 479 480

	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:
481 482 483 484 485 486 487
		rcu_read_lock_bh();
		vlan = rcu_dereference(q->vlan);
		if (vlan)
			dev_hold(vlan->dev);
		rcu_read_unlock_bh();

		if (!vlan)
A
Arnd Bergmann 已提交
488 489
			return -ENOLINK;

490
		ret = 0;
A
Arnd Bergmann 已提交
491 492
		if (copy_to_user(&ifr->ifr_name, q->vlan->dev->name, IFNAMSIZ) ||
		    put_user((TUN_TAP_DEV | TUN_NO_PI), &ifr->ifr_flags))
493 494 495
			ret = -EFAULT;
		dev_put(vlan->dev);
		return ret;
A
Arnd Bergmann 已提交
496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549

	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->sk.sk_sndbuf = u;
		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
};

A
Arnd Bergmann 已提交
550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596
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);

A
Arnd Bergmann 已提交
597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645
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 <arnd@arndb.de>");
MODULE_LICENSE("GPL");