macvtap.c 21.2 KB
Newer Older
A
Arnd Bergmann 已提交
1 2 3 4 5 6 7 8 9 10 11
#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>
12
#include <linux/slab.h>
A
Arnd Bergmann 已提交
13 14 15 16 17 18 19 20
#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>
21
#include <linux/virtio_net.h>
A
Arnd Bergmann 已提交
22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39

/*
 * 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;
40
	struct socket_wq wq;
41
	int vnet_hdr_sz;
A
Arnd Bergmann 已提交
42 43
	struct macvlan_dev *vlan;
	struct file *file;
44
	unsigned int flags;
A
Arnd Bergmann 已提交
45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60
};

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.
 */
61
static dev_t macvtap_major;
A
Arnd Bergmann 已提交
62 63 64 65
#define MACVTAP_NUM_DEVS 65536
static struct class *macvtap_class;
static struct cdev macvtap_cdev;

A
Arnd Bergmann 已提交
66 67
static const struct proto_ops macvtap_socket_ops;

A
Arnd Bergmann 已提交
68 69
/*
 * RCU usage:
70 71 72
 * 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
73
 *
74 75 76 77
 * 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
78
 *
79 80 81 82
 * 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
83 84 85 86
 */
static DEFINE_SPINLOCK(macvtap_lock);

/*
87 88 89
 * get_slot: return a [unused/occupied] slot in vlan->taps[]:
 *	- if 'q' is NULL, return the first empty slot;
 *	- otherwise, return the slot this pointer occupies.
A
Arnd Bergmann 已提交
90
 */
91 92 93 94 95 96 97 98 99 100 101 102 103
static int get_slot(struct macvlan_dev *vlan, struct macvtap_queue *q)
{
	int i;

	for (i = 0; i < MAX_MACVTAP_QUEUES; i++) {
		if (rcu_dereference(vlan->taps[i]) == q)
			return i;
	}

	/* Should never happen */
	BUG_ON(1);
}

A
Arnd Bergmann 已提交
104 105 106 107
static int macvtap_set_queue(struct net_device *dev, struct file *file,
				struct macvtap_queue *q)
{
	struct macvlan_dev *vlan = netdev_priv(dev);
108
	int index;
A
Arnd Bergmann 已提交
109 110 111
	int err = -EBUSY;

	spin_lock(&macvtap_lock);
112
	if (vlan->numvtaps == MAX_MACVTAP_QUEUES)
A
Arnd Bergmann 已提交
113 114 115
		goto out;

	err = 0;
116
	index = get_slot(vlan, NULL);
117
	rcu_assign_pointer(q->vlan, vlan);
118
	rcu_assign_pointer(vlan->taps[index], q);
119
	sock_hold(&q->sk);
A
Arnd Bergmann 已提交
120 121

	q->file = file;
122
	file->private_data = q;
A
Arnd Bergmann 已提交
123

124 125
	vlan->numvtaps++;

A
Arnd Bergmann 已提交
126 127 128 129 130 131
out:
	spin_unlock(&macvtap_lock);
	return err;
}

/*
132 133 134
 * 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
135 136 137 138
 *
 * Using the spinlock makes sure that we don't get
 * to the queue again after destroying it.
 */
139
static void macvtap_put_queue(struct macvtap_queue *q)
A
Arnd Bergmann 已提交
140
{
141
	struct macvlan_dev *vlan;
A
Arnd Bergmann 已提交
142 143

	spin_lock(&macvtap_lock);
144 145
	vlan = rcu_dereference(q->vlan);
	if (vlan) {
146 147 148
		int index = get_slot(vlan, q);

		rcu_assign_pointer(vlan->taps[index], NULL);
149 150
		rcu_assign_pointer(q->vlan, NULL);
		sock_put(&q->sk);
151
		--vlan->numvtaps;
A
Arnd Bergmann 已提交
152 153 154 155 156 157 158 159 160
	}

	spin_unlock(&macvtap_lock);

	synchronize_rcu();
	sock_put(&q->sk);
}

/*
161 162 163 164 165
 * Select a queue based on the rxq of the device on which this packet
 * arrived. If the incoming device is not mq, calculate a flow hash
 * to select a queue. If all fails, find the first available queue.
 * Cache vlan->numvtaps since it can become zero during the execution
 * of this function.
A
Arnd Bergmann 已提交
166 167 168 169 170
 */
static struct macvtap_queue *macvtap_get_queue(struct net_device *dev,
					       struct sk_buff *skb)
{
	struct macvlan_dev *vlan = netdev_priv(dev);
171 172 173 174 175 176 177 178 179
	struct macvtap_queue *tap = NULL;
	int numvtaps = vlan->numvtaps;
	__u32 rxq;

	if (!numvtaps)
		goto out;

	if (likely(skb_rx_queue_recorded(skb))) {
		rxq = skb_get_rx_queue(skb);
A
Arnd Bergmann 已提交
180

181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205
		while (unlikely(rxq >= numvtaps))
			rxq -= numvtaps;

		tap = rcu_dereference(vlan->taps[rxq]);
		if (tap)
			goto out;
	}

	/* Check if we can use flow to select a queue */
	rxq = skb_get_rxhash(skb);
	if (rxq) {
		tap = rcu_dereference(vlan->taps[rxq % numvtaps]);
		if (tap)
			goto out;
	}

	/* Everything failed - find first available queue */
	for (rxq = 0; rxq < MAX_MACVTAP_QUEUES; rxq++) {
		tap = rcu_dereference(vlan->taps[rxq]);
		if (tap)
			break;
	}

out:
	return tap;
A
Arnd Bergmann 已提交
206 207
}

208 209
/*
 * The net_device is going away, give up the reference
210 211
 * that it holds on all queues and safely set the pointer
 * from the queues to NULL.
212
 */
A
Arnd Bergmann 已提交
213 214 215
static void macvtap_del_queues(struct net_device *dev)
{
	struct macvlan_dev *vlan = netdev_priv(dev);
216 217
	struct macvtap_queue *q, *qlist[MAX_MACVTAP_QUEUES];
	int i, j = 0;
218

219
	/* macvtap_put_queue can free some slots, so go through all slots */
220
	spin_lock(&macvtap_lock);
221 222 223 224 225 226 227 228
	for (i = 0; i < MAX_MACVTAP_QUEUES && vlan->numvtaps; i++) {
		q = rcu_dereference(vlan->taps[i]);
		if (q) {
			qlist[j++] = q;
			rcu_assign_pointer(vlan->taps[i], NULL);
			rcu_assign_pointer(q->vlan, NULL);
			vlan->numvtaps--;
		}
229
	}
230
	BUG_ON(vlan->numvtaps != 0);
231 232 233
	spin_unlock(&macvtap_lock);

	synchronize_rcu();
234 235 236

	for (--j; j >= 0; j--)
		sock_put(&qlist[j]->sk);
A
Arnd Bergmann 已提交
237 238 239 240 241 242 243 244 245 246 247
}

/*
 * 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)
H
Herbert Xu 已提交
248 249 250 251
		goto drop;

	if (skb_queue_len(&q->sk.sk_receive_queue) >= dev->tx_queue_len)
		goto drop;
A
Arnd Bergmann 已提交
252 253

	skb_queue_tail(&q->sk.sk_receive_queue, skb);
E
Eric Dumazet 已提交
254
	wake_up_interruptible_poll(sk_sleep(&q->sk), POLLIN | POLLRDNORM | POLLRDBAND);
H
Herbert Xu 已提交
255 256 257 258 259
	return NET_RX_SUCCESS;

drop:
	kfree_skb(skb);
	return NET_RX_DROP;
A
Arnd Bergmann 已提交
260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309
}

/*
 * 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);
}

H
Herbert Xu 已提交
310 311 312 313 314 315
static void macvtap_setup(struct net_device *dev)
{
	macvlan_common_setup(dev);
	dev->tx_queue_len = TUN_READQ_SIZE;
}

A
Arnd Bergmann 已提交
316 317
static struct rtnl_link_ops macvtap_link_ops __read_mostly = {
	.kind		= "macvtap",
H
Herbert Xu 已提交
318
	.setup		= macvtap_setup,
A
Arnd Bergmann 已提交
319 320 321 322 323 324 325
	.newlink	= macvtap_newlink,
	.dellink	= macvtap_dellink,
};


static void macvtap_sock_write_space(struct sock *sk)
{
326 327
	wait_queue_head_t *wqueue;

A
Arnd Bergmann 已提交
328 329 330 331
	if (!sock_writeable(sk) ||
	    !test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags))
		return;

332 333 334
	wqueue = sk_sleep(sk);
	if (wqueue && waitqueue_active(wqueue))
		wake_up_interruptible_poll(wqueue, POLLOUT | POLLWRNORM | POLLWRBAND);
A
Arnd Bergmann 已提交
335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358
}

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;

359 360
	q->sock.wq = &q->wq;
	init_waitqueue_head(&q->wq.wait);
A
Arnd Bergmann 已提交
361 362
	q->sock.type = SOCK_RAW;
	q->sock.state = SS_CONNECTED;
A
Arnd Bergmann 已提交
363 364
	q->sock.file = file;
	q->sock.ops = &macvtap_socket_ops;
A
Arnd Bergmann 已提交
365 366
	sock_init_data(&q->sock, &q->sk);
	q->sk.sk_write_space = macvtap_sock_write_space;
367
	q->flags = IFF_VNET_HDR | IFF_NO_PI | IFF_TAP;
368
	q->vnet_hdr_sz = sizeof(struct virtio_net_hdr);
A
Arnd Bergmann 已提交
369 370 371 372 373 374 375 376 377 378 379 380 381 382

	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)
{
383 384
	struct macvtap_queue *q = file->private_data;
	macvtap_put_queue(q);
A
Arnd Bergmann 已提交
385 386 387 388 389
	return 0;
}

static unsigned int macvtap_poll(struct file *file, poll_table * wait)
{
390
	struct macvtap_queue *q = file->private_data;
A
Arnd Bergmann 已提交
391 392 393 394 395 396
	unsigned int mask = POLLERR;

	if (!q)
		goto out;

	mask = 0;
397
	poll_wait(file, &q->wq.wait, wait);
A
Arnd Bergmann 已提交
398 399 400 401 402 403 404 405 406 407 408 409 410

	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;
}

411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506
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;
507
		vnet_hdr->csum_start = skb_checksum_start_offset(skb);
508 509 510 511 512 513 514
		vnet_hdr->csum_offset = skb->csum_offset;
	} /* else everything is zero */

	return 0;
}


A
Arnd Bergmann 已提交
515 516 517 518 519 520
/* 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;
521
	struct macvlan_dev *vlan;
A
Arnd Bergmann 已提交
522 523
	size_t len = count;
	int err;
524 525 526 527
	struct virtio_net_hdr vnet_hdr = { 0 };
	int vnet_hdr_len = 0;

	if (q->flags & IFF_VNET_HDR) {
528
		vnet_hdr_len = q->vnet_hdr_sz;
529 530 531 532 533 534

		err = -EINVAL;
		if ((len -= vnet_hdr_len) < 0)
			goto err;

		err = memcpy_fromiovecend((void *)&vnet_hdr, iv, 0,
535
					   sizeof(vnet_hdr));
536 537 538 539 540 541 542 543 544 545 546
		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;
	}
A
Arnd Bergmann 已提交
547

548
	err = -EINVAL;
A
Arnd Bergmann 已提交
549
	if (unlikely(len < ETH_HLEN))
550
		goto err;
A
Arnd Bergmann 已提交
551

552 553
	skb = macvtap_alloc_skb(&q->sk, NET_IP_ALIGN, len, vnet_hdr.hdr_len,
				noblock, &err);
554 555
	if (!skb)
		goto err;
A
Arnd Bergmann 已提交
556

557
	err = skb_copy_datagram_from_iovec(skb, 0, iv, vnet_hdr_len, len);
558
	if (err)
559
		goto err_kfree;
A
Arnd Bergmann 已提交
560 561

	skb_set_network_header(skb, ETH_HLEN);
562 563 564 565 566 567 568 569 570
	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;
	}

571 572 573 574 575 576 577
	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
578 579

	return count;
580

581 582 583
err_kfree:
	kfree_skb(skb);

584 585 586 587
err:
	rcu_read_lock_bh();
	vlan = rcu_dereference(q->vlan);
	if (vlan)
E
Eric Dumazet 已提交
588
		vlan->dev->stats.tx_dropped++;
589 590 591
	rcu_read_unlock_bh();

	return err;
A
Arnd Bergmann 已提交
592 593 594 595 596 597 598
}

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;
599
	struct macvtap_queue *q = file->private_data;
A
Arnd Bergmann 已提交
600 601 602 603 604 605 606 607 608 609 610

	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)
{
611
	struct macvlan_dev *vlan;
A
Arnd Bergmann 已提交
612
	int ret;
613 614 615 616
	int vnet_hdr_len = 0;

	if (q->flags & IFF_VNET_HDR) {
		struct virtio_net_hdr vnet_hdr;
617
		vnet_hdr_len = q->vnet_hdr_sz;
618 619 620 621 622 623 624
		if ((len -= vnet_hdr_len) < 0)
			return -EINVAL;

		ret = macvtap_skb_to_vnet_hdr(skb, &vnet_hdr);
		if (ret)
			return ret;

625
		if (memcpy_toiovecend(iv, (void *)&vnet_hdr, 0, sizeof(vnet_hdr)))
626 627
			return -EFAULT;
	}
A
Arnd Bergmann 已提交
628 629 630

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

631
	ret = skb_copy_datagram_const_iovec(skb, 0, iv, vnet_hdr_len, len);
A
Arnd Bergmann 已提交
632

633 634
	rcu_read_lock_bh();
	vlan = rcu_dereference(q->vlan);
A
Arnd Bergmann 已提交
635 636
	if (vlan)
		macvlan_count_rx(vlan, len, ret == 0, 0);
637
	rcu_read_unlock_bh();
A
Arnd Bergmann 已提交
638

639
	return ret ? ret : (len + vnet_hdr_len);
A
Arnd Bergmann 已提交
640 641
}

A
Arnd Bergmann 已提交
642 643 644
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
645 646 647
{
	DECLARE_WAITQUEUE(wait, current);
	struct sk_buff *skb;
A
Arnd Bergmann 已提交
648
	ssize_t ret = 0;
A
Arnd Bergmann 已提交
649

E
Eric Dumazet 已提交
650
	add_wait_queue(sk_sleep(&q->sk), &wait);
A
Arnd Bergmann 已提交
651 652 653 654 655 656
	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
657
			if (noblock) {
A
Arnd Bergmann 已提交
658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674
				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;
E
Eric Dumazet 已提交
675
	remove_wait_queue(sk_sleep(&q->sk), &wait);
A
Arnd Bergmann 已提交
676 677 678 679 680 681 682 683 684
	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
685

A
Arnd Bergmann 已提交
686 687 688 689 690 691 692 693
	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
694 695 696 697 698 699 700 701 702 703
out:
	return ret;
}

/*
 * provide compatibility with generic tun/tap interface
 */
static long macvtap_ioctl(struct file *file, unsigned int cmd,
			  unsigned long arg)
{
704 705
	struct macvtap_queue *q = file->private_data;
	struct macvlan_dev *vlan;
A
Arnd Bergmann 已提交
706 707 708 709
	void __user *argp = (void __user *)arg;
	struct ifreq __user *ifr = argp;
	unsigned int __user *up = argp;
	unsigned int u;
710 711
	int __user *sp = argp;
	int s;
712
	int ret;
A
Arnd Bergmann 已提交
713 714 715 716 717 718

	switch (cmd) {
	case TUNSETIFF:
		/* ignore the name, just look at flags */
		if (get_user(u, &ifr->ifr_flags))
			return -EFAULT;
719 720 721 722 723 724 725 726

		ret = 0;
		if ((u & ~IFF_VNET_HDR) != (IFF_NO_PI | IFF_TAP))
			ret = -EINVAL;
		else
			q->flags = u;

		return ret;
A
Arnd Bergmann 已提交
727 728

	case TUNGETIFF:
729 730 731 732 733 734 735
		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
736 737
			return -ENOLINK;

738
		ret = 0;
A
Arnd Bergmann 已提交
739
		if (copy_to_user(&ifr->ifr_name, q->vlan->dev->name, IFNAMSIZ) ||
740
		    put_user(q->flags, &ifr->ifr_flags))
741 742 743
			ret = -EFAULT;
		dev_put(vlan->dev);
		return ret;
A
Arnd Bergmann 已提交
744 745

	case TUNGETFEATURES:
746
		if (put_user(IFF_TAP | IFF_NO_PI | IFF_VNET_HDR, up))
A
Arnd Bergmann 已提交
747 748 749 750 751 752 753 754 755 756
			return -EFAULT;
		return 0;

	case TUNSETSNDBUF:
		if (get_user(u, up))
			return -EFAULT;

		q->sk.sk_sndbuf = u;
		return 0;

757 758 759 760 761 762 763 764 765 766 767 768 769 770 771
	case TUNGETVNETHDRSZ:
		s = q->vnet_hdr_sz;
		if (put_user(s, sp))
			return -EFAULT;
		return 0;

	case TUNSETVNETHDRSZ:
		if (get_user(s, sp))
			return -EFAULT;
		if (s < (int)sizeof(struct virtio_net_hdr))
			return -EINVAL;

		q->vnet_hdr_sz = s;
		return 0;

A
Arnd Bergmann 已提交
772 773 774
	case TUNSETOFFLOAD:
		/* let the user check for future flags */
		if (arg & ~(TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 |
775
			    TUN_F_TSO_ECN | TUN_F_UFO))
A
Arnd Bergmann 已提交
776 777
			return -EINVAL;

778 779 780 781
		/* TODO: only accept frames with the features that
			 got enabled for forwarded frames */
		if (!(q->flags & IFF_VNET_HDR))
			return  -EINVAL;
A
Arnd Bergmann 已提交
782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810
		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
811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857
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
858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906
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");