summaryrefslogtreecommitdiff
path: root/drivers/vhost/net.c
blob: aa88911c95045d10e1089ae477b1f43eab7de614 (plain)
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
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
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
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
247
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
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
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
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
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
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
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
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
/* Copyright (C) 2009 Red Hat, Inc.
 * Author: Michael S. Tsirkin <mst@redhat.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.
 *
 * virtio-net server in host kernel.
 */

#include <linux/compat.h>
#include <linux/eventfd.h>
#include <linux/vhost.h>
#include <linux/virtio_net.h>
#include <linux/mmu_context.h>
#include <linux/miscdevice.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/workqueue.h>
#include <linux/rcupdate.h>
#include <linux/file.h>
#include <linux/slab.h>

#include <linux/net.h>
#include <linux/if_packet.h>
#include <linux/if_arp.h>
#include <linux/if_tun.h>
#include <linux/if_macvlan.h>

#include <net/sock.h>

#include "vhost.h"

/* Max number of bytes transferred before requeueing the job.
 * Using this limit prevents one virtqueue from starving others. */
#define VHOST_NET_WEIGHT 0x80000

enum {
	VHOST_NET_VQ_RX = 0,
	VHOST_NET_VQ_TX = 1,
	VHOST_NET_VQ_MAX = 2,
};

enum vhost_net_poll_state {
	VHOST_NET_POLL_DISABLED = 0,
	VHOST_NET_POLL_STARTED = 1,
	VHOST_NET_POLL_STOPPED = 2,
};

struct vhost_net {
	struct vhost_dev dev;
	struct vhost_virtqueue vqs[VHOST_NET_VQ_MAX];
	struct vhost_poll poll[VHOST_NET_VQ_MAX];
	/* Tells us whether we are polling a socket for TX.
	 * We only do this when socket buffer fills up.
	 * Protected by tx vq lock. */
	enum vhost_net_poll_state tx_poll_state;
};

/* Pop first len bytes from iovec. Return number of segments used. */
static int move_iovec_hdr(struct iovec *from, struct iovec *to,
			  size_t len, int iov_count)
{
	int seg = 0;
	size_t size;
	while (len && seg < iov_count) {
		size = min(from->iov_len, len);
		to->iov_base = from->iov_base;
		to->iov_len = size;
		from->iov_len -= size;
		from->iov_base += size;
		len -= size;
		++from;
		++to;
		++seg;
	}
	return seg;
}

/* Caller must have TX VQ lock */
static void tx_poll_stop(struct vhost_net *net)
{
	if (likely(net->tx_poll_state != VHOST_NET_POLL_STARTED))
		return;
	vhost_poll_stop(net->poll + VHOST_NET_VQ_TX);
	net->tx_poll_state = VHOST_NET_POLL_STOPPED;
}

/* Caller must have TX VQ lock */
static void tx_poll_start(struct vhost_net *net, struct socket *sock)
{
	if (unlikely(net->tx_poll_state != VHOST_NET_POLL_STOPPED))
		return;
	vhost_poll_start(net->poll + VHOST_NET_VQ_TX, sock->file);
	net->tx_poll_state = VHOST_NET_POLL_STARTED;
}

/* Expects to be always run from workqueue - which acts as
 * read-size critical section for our kind of RCU. */
static void handle_tx(struct vhost_net *net)
{
	struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_TX];
	unsigned head, out, in, s;
	struct msghdr msg = {
		.msg_name = NULL,
		.msg_namelen = 0,
		.msg_control = NULL,
		.msg_controllen = 0,
		.msg_iov = vq->iov,
		.msg_flags = MSG_DONTWAIT,
	};
	size_t len, total_len = 0;
	int err, wmem;
	size_t hdr_size;
	struct socket *sock = rcu_dereference(vq->private_data);
	if (!sock)
		return;

	wmem = atomic_read(&sock->sk->sk_wmem_alloc);
	if (wmem >= sock->sk->sk_sndbuf) {
		mutex_lock(&vq->mutex);
		tx_poll_start(net, sock);
		mutex_unlock(&vq->mutex);
		return;
	}

	use_mm(net->dev.mm);
	mutex_lock(&vq->mutex);
	vhost_disable_notify(vq);

	if (wmem < sock->sk->sk_sndbuf / 2)
		tx_poll_stop(net);
	hdr_size = vq->hdr_size;

	for (;;) {
		head = vhost_get_vq_desc(&net->dev, vq, vq->iov,
					 ARRAY_SIZE(vq->iov),
					 &out, &in,
					 NULL, NULL);
		/* Nothing new?  Wait for eventfd to tell us they refilled. */
		if (head == vq->num) {
			wmem = atomic_read(&sock->sk->sk_wmem_alloc);
			if (wmem >= sock->sk->sk_sndbuf * 3 / 4) {
				tx_poll_start(net, sock);
				set_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
				break;
			}
			if (unlikely(vhost_enable_notify(vq))) {
				vhost_disable_notify(vq);
				continue;
			}
			break;
		}
		if (in) {
			vq_err(vq, "Unexpected descriptor format for TX: "
			       "out %d, int %d\n", out, in);
			break;
		}
		/* Skip header. TODO: support TSO. */
		s = move_iovec_hdr(vq->iov, vq->hdr, hdr_size, out);
		msg.msg_iovlen = out;
		len = iov_length(vq->iov, out);
		/* Sanity check */
		if (!len) {
			vq_err(vq, "Unexpected header len for TX: "
			       "%zd expected %zd\n",
			       iov_length(vq->hdr, s), hdr_size);
			break;
		}
		/* TODO: Check specific error and bomb out unless ENOBUFS? */
		err = sock->ops->sendmsg(NULL, sock, &msg, len);
		if (unlikely(err < 0)) {
			vhost_discard_vq_desc(vq);
			tx_poll_start(net, sock);
			break;
		}
		if (err != len)
			pr_err("Truncated TX packet: "
			       " len %d != %zd\n", err, len);
		vhost_add_used_and_signal(&net->dev, vq, head, 0);
		total_len += len;
		if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
			vhost_poll_queue(&vq->poll);
			break;
		}
	}

	mutex_unlock(&vq->mutex);
	unuse_mm(net->dev.mm);
}

/* Expects to be always run from workqueue - which acts as
 * read-size critical section for our kind of RCU. */
static void handle_rx(struct vhost_net *net)
{
	struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_RX];
	unsigned head, out, in, log, s;
	struct vhost_log *vq_log;
	struct msghdr msg = {
		.msg_name = NULL,
		.msg_namelen = 0,
		.msg_control = NULL, /* FIXME: get and handle RX aux data. */
		.msg_controllen = 0,
		.msg_iov = vq->iov,
		.msg_flags = MSG_DONTWAIT,
	};

	struct virtio_net_hdr hdr = {
		.flags = 0,
		.gso_type = VIRTIO_NET_HDR_GSO_NONE
	};

	size_t len, total_len = 0;
	int err;
	size_t hdr_size;
	struct socket *sock = rcu_dereference(vq->private_data);
	if (!sock || skb_queue_empty(&sock->sk->sk_receive_queue))
		return;

	use_mm(net->dev.mm);
	mutex_lock(&vq->mutex);
	vhost_disable_notify(vq);
	hdr_size = vq->hdr_size;

	vq_log = unlikely(vhost_has_feature(&net->dev, VHOST_F_LOG_ALL)) ?
		vq->log : NULL;

	for (;;) {
		head = vhost_get_vq_desc(&net->dev, vq, vq->iov,
					 ARRAY_SIZE(vq->iov),
					 &out, &in,
					 vq_log, &log);
		/* OK, now we need to know about added descriptors. */
		if (head == vq->num) {
			if (unlikely(vhost_enable_notify(vq))) {
				/* They have slipped one in as we were
				 * doing that: check again. */
				vhost_disable_notify(vq);
				continue;
			}
			/* Nothing new?  Wait for eventfd to tell us
			 * they refilled. */
			break;
		}
		/* We don't need to be notified again. */
		if (out) {
			vq_err(vq, "Unexpected descriptor format for RX: "
			       "out %d, int %d\n",
			       out, in);
			break;
		}
		/* Skip header. TODO: support TSO/mergeable rx buffers. */
		s = move_iovec_hdr(vq->iov, vq->hdr, hdr_size, in);
		msg.msg_iovlen = in;
		len = iov_length(vq->iov, in);
		/* Sanity check */
		if (!len) {
			vq_err(vq, "Unexpected header len for RX: "
			       "%zd expected %zd\n",
			       iov_length(vq->hdr, s), hdr_size);
			break;
		}
		err = sock->ops->recvmsg(NULL, sock, &msg,
					 len, MSG_DONTWAIT | MSG_TRUNC);
		/* TODO: Check specific error and bomb out unless EAGAIN? */
		if (err < 0) {
			vhost_discard_vq_desc(vq);
			break;
		}
		/* TODO: Should check and handle checksum. */
		if (err > len) {
			pr_err("Discarded truncated rx packet: "
			       " len %d > %zd\n", err, len);
			vhost_discard_vq_desc(vq);
			continue;
		}
		len = err;
		err = memcpy_toiovec(vq->hdr, (unsigned char *)&hdr, hdr_size);
		if (err) {
			vq_err(vq, "Unable to write vnet_hdr at addr %p: %d\n",
			       vq->iov->iov_base, err);
			break;
		}
		len += hdr_size;
		vhost_add_used_and_signal(&net->dev, vq, head, len);
		if (unlikely(vq_log))
			vhost_log_write(vq, vq_log, log, len);
		total_len += len;
		if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
			vhost_poll_queue(&vq->poll);
			break;
		}
	}

	mutex_unlock(&vq->mutex);
	unuse_mm(net->dev.mm);
}

static void handle_tx_kick(struct work_struct *work)
{
	struct vhost_virtqueue *vq;
	struct vhost_net *net;
	vq = container_of(work, struct vhost_virtqueue, poll.work);
	net = container_of(vq->dev, struct vhost_net, dev);
	handle_tx(net);
}

static void handle_rx_kick(struct work_struct *work)
{
	struct vhost_virtqueue *vq;
	struct vhost_net *net;
	vq = container_of(work, struct vhost_virtqueue, poll.work);
	net = container_of(vq->dev, struct vhost_net, dev);
	handle_rx(net);
}

static void handle_tx_net(struct work_struct *work)
{
	struct vhost_net *net;
	net = container_of(work, struct vhost_net, poll[VHOST_NET_VQ_TX].work);
	handle_tx(net);
}

static void handle_rx_net(struct work_struct *work)
{
	struct vhost_net *net;
	net = container_of(work, struct vhost_net, poll[VHOST_NET_VQ_RX].work);
	handle_rx(net);
}

static int vhost_net_open(struct inode *inode, struct file *f)
{
	struct vhost_net *n = kmalloc(sizeof *n, GFP_KERNEL);
	int r;
	if (!n)
		return -ENOMEM;
	n->vqs[VHOST_NET_VQ_TX].handle_kick = handle_tx_kick;
	n->vqs[VHOST_NET_VQ_RX].handle_kick = handle_rx_kick;
	r = vhost_dev_init(&n->dev, n->vqs, VHOST_NET_VQ_MAX);
	if (r < 0) {
		kfree(n);
		return r;
	}

	vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, POLLOUT);
	vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, POLLIN);
	n->tx_poll_state = VHOST_NET_POLL_DISABLED;

	f->private_data = n;

	return 0;
}

static void vhost_net_disable_vq(struct vhost_net *n,
				 struct vhost_virtqueue *vq)
{
	if (!vq->private_data)
		return;
	if (vq == n->vqs + VHOST_NET_VQ_TX) {
		tx_poll_stop(n);
		n->tx_poll_state = VHOST_NET_POLL_DISABLED;
	} else
		vhost_poll_stop(n->poll + VHOST_NET_VQ_RX);
}

static void vhost_net_enable_vq(struct vhost_net *n,
				struct vhost_virtqueue *vq)
{
	struct socket *sock = vq->private_data;
	if (!sock)
		return;
	if (vq == n->vqs + VHOST_NET_VQ_TX) {
		n->tx_poll_state = VHOST_NET_POLL_STOPPED;
		tx_poll_start(n, sock);
	} else
		vhost_poll_start(n->poll + VHOST_NET_VQ_RX, sock->file);
}

static struct socket *vhost_net_stop_vq(struct vhost_net *n,
					struct vhost_virtqueue *vq)
{
	struct socket *sock;

	mutex_lock(&vq->mutex);
	sock = vq->private_data;
	vhost_net_disable_vq(n, vq);
	rcu_assign_pointer(vq->private_data, NULL);
	mutex_unlock(&vq->mutex);
	return sock;
}

static void vhost_net_stop(struct vhost_net *n, struct socket **tx_sock,
			   struct socket **rx_sock)
{
	*tx_sock = vhost_net_stop_vq(n, n->vqs + VHOST_NET_VQ_TX);
	*rx_sock = vhost_net_stop_vq(n, n->vqs + VHOST_NET_VQ_RX);
}

static void vhost_net_flush_vq(struct vhost_net *n, int index)
{
	vhost_poll_flush(n->poll + index);
	vhost_poll_flush(&n->dev.vqs[index].poll);
}

static void vhost_net_flush(struct vhost_net *n)
{
	vhost_net_flush_vq(n, VHOST_NET_VQ_TX);
	vhost_net_flush_vq(n, VHOST_NET_VQ_RX);
}

static int vhost_net_release(struct inode *inode, struct file *f)
{
	struct vhost_net *n = f->private_data;
	struct socket *tx_sock;
	struct socket *rx_sock;

	vhost_net_stop(n, &tx_sock, &rx_sock);
	vhost_net_flush(n);
	vhost_dev_cleanup(&n->dev);
	if (tx_sock)
		fput(tx_sock->file);
	if (rx_sock)
		fput(rx_sock->file);
	/* We do an extra flush before freeing memory,
	 * since jobs can re-queue themselves. */
	vhost_net_flush(n);
	kfree(n);
	return 0;
}

static struct socket *get_raw_socket(int fd)
{
	struct {
		struct sockaddr_ll sa;
		char  buf[MAX_ADDR_LEN];
	} uaddr;
	int uaddr_len = sizeof uaddr, r;
	struct socket *sock = sockfd_lookup(fd, &r);
	if (!sock)
		return ERR_PTR(-ENOTSOCK);

	/* Parameter checking */
	if (sock->sk->sk_type != SOCK_RAW) {
		r = -ESOCKTNOSUPPORT;
		goto err;
	}

	r = sock->ops->getname(sock, (struct sockaddr *)&uaddr.sa,
			       &uaddr_len, 0);
	if (r)
		goto err;

	if (uaddr.sa.sll_family != AF_PACKET) {
		r = -EPFNOSUPPORT;
		goto err;
	}
	return sock;
err:
	fput(sock->file);
	return ERR_PTR(r);
}

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;
}

static struct socket *get_socket(int fd)
{
	struct socket *sock;
	/* special case to disable backend */
	if (fd == -1)
		return NULL;
	sock = get_raw_socket(fd);
	if (!IS_ERR(sock))
		return sock;
	sock = get_tap_socket(fd);
	if (!IS_ERR(sock))
		return sock;
	return ERR_PTR(-ENOTSOCK);
}

static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
{
	struct socket *sock, *oldsock;
	struct vhost_virtqueue *vq;
	int r;

	mutex_lock(&n->dev.mutex);
	r = vhost_dev_check_owner(&n->dev);
	if (r)
		goto err;

	if (index >= VHOST_NET_VQ_MAX) {
		r = -ENOBUFS;
		goto err;
	}
	vq = n->vqs + index;
	mutex_lock(&vq->mutex);

	/* Verify that ring has been setup correctly. */
	if (!vhost_vq_access_ok(vq)) {
		r = -EFAULT;
		goto err_vq;
	}
	sock = get_socket(fd);
	if (IS_ERR(sock)) {
		r = PTR_ERR(sock);
		goto err_vq;
	}

	/* start polling new socket */
	oldsock = vq->private_data;
	if (sock == oldsock)
		goto done;

	vhost_net_disable_vq(n, vq);
	rcu_assign_pointer(vq->private_data, sock);
	vhost_net_enable_vq(n, vq);
done:
	if (oldsock) {
		vhost_net_flush_vq(n, index);
		fput(oldsock->file);
	}

err_vq:
	mutex_unlock(&vq->mutex);
err:
	mutex_unlock(&n->dev.mutex);
	return r;
}

static long vhost_net_reset_owner(struct vhost_net *n)
{
	struct socket *tx_sock = NULL;
	struct socket *rx_sock = NULL;
	long err;
	mutex_lock(&n->dev.mutex);
	err = vhost_dev_check_owner(&n->dev);
	if (err)
		goto done;
	vhost_net_stop(n, &tx_sock, &rx_sock);
	vhost_net_flush(n);
	err = vhost_dev_reset_owner(&n->dev);
done:
	mutex_unlock(&n->dev.mutex);
	if (tx_sock)
		fput(tx_sock->file);
	if (rx_sock)
		fput(rx_sock->file);
	return err;
}

static int vhost_net_set_features(struct vhost_net *n, u64 features)
{
	size_t hdr_size = features & (1 << VHOST_NET_F_VIRTIO_NET_HDR) ?
		sizeof(struct virtio_net_hdr) : 0;
	int i;
	mutex_lock(&n->dev.mutex);
	if ((features & (1 << VHOST_F_LOG_ALL)) &&
	    !vhost_log_access_ok(&n->dev)) {
		mutex_unlock(&n->dev.mutex);
		return -EFAULT;
	}
	n->dev.acked_features = features;
	smp_wmb();
	for (i = 0; i < VHOST_NET_VQ_MAX; ++i) {
		mutex_lock(&n->vqs[i].mutex);
		n->vqs[i].hdr_size = hdr_size;
		mutex_unlock(&n->vqs[i].mutex);
	}
	vhost_net_flush(n);
	mutex_unlock(&n->dev.mutex);
	return 0;
}

static long vhost_net_ioctl(struct file *f, unsigned int ioctl,
			    unsigned long arg)
{
	struct vhost_net *n = f->private_data;
	void __user *argp = (void __user *)arg;
	u64 __user *featurep = argp;
	struct vhost_vring_file backend;
	u64 features;
	int r;
	switch (ioctl) {
	case VHOST_NET_SET_BACKEND:
		r = copy_from_user(&backend, argp, sizeof backend);
		if (r < 0)
			return r;
		return vhost_net_set_backend(n, backend.index, backend.fd);
	case VHOST_GET_FEATURES:
		features = VHOST_FEATURES;
		return copy_to_user(featurep, &features, sizeof features);
	case VHOST_SET_FEATURES:
		r = copy_from_user(&features, featurep, sizeof features);
		if (r < 0)
			return r;
		if (features & ~VHOST_FEATURES)
			return -EOPNOTSUPP;
		return vhost_net_set_features(n, features);
	case VHOST_RESET_OWNER:
		return vhost_net_reset_owner(n);
	default:
		mutex_lock(&n->dev.mutex);
		r = vhost_dev_ioctl(&n->dev, ioctl, arg);
		vhost_net_flush(n);
		mutex_unlock(&n->dev.mutex);
		return r;
	}
}

#ifdef CONFIG_COMPAT
static long vhost_net_compat_ioctl(struct file *f, unsigned int ioctl,
				   unsigned long arg)
{
	return vhost_net_ioctl(f, ioctl, (unsigned long)compat_ptr(arg));
}
#endif

const static struct file_operations vhost_net_fops = {
	.owner          = THIS_MODULE,
	.release        = vhost_net_release,
	.unlocked_ioctl = vhost_net_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl   = vhost_net_compat_ioctl,
#endif
	.open           = vhost_net_open,
};

static struct miscdevice vhost_net_misc = {
	VHOST_NET_MINOR,
	"vhost-net",
	&vhost_net_fops,
};

static int vhost_net_init(void)
{
	int r = vhost_init();
	if (r)
		goto err_init;
	r = misc_register(&vhost_net_misc);
	if (r)
		goto err_reg;
	return 0;
err_reg:
	vhost_cleanup();
err_init:
	return r;

}
module_init(vhost_net_init);

static void vhost_net_exit(void)
{
	misc_deregister(&vhost_net_misc);
	vhost_cleanup();
}
module_exit(vhost_net_exit);

MODULE_VERSION("0.0.1");
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Michael S. Tsirkin");
MODULE_DESCRIPTION("Host kernel accelerator for virtio net");