summaryrefslogtreecommitdiffstats
path: root/net/vmw_vsock/virtio_transport.c
blob: 699dfabdbccd5e6af0f4910cdf2467b36bab3b60 (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
/*
 * virtio transport for vsock
 *
 * Copyright (C) 2013-2015 Red Hat, Inc.
 * Author: Asias He <asias@redhat.com>
 *         Stefan Hajnoczi <stefanha@redhat.com>
 *
 * Some of the code is take from Gerd Hoffmann <kraxel@redhat.com>'s
 * early virtio-vsock proof-of-concept bits.
 *
 * This work is licensed under the terms of the GNU GPL, version 2.
 */
#include <linux/spinlock.h>
#include <linux/module.h>
#include <linux/list.h>
#include <linux/atomic.h>
#include <linux/virtio.h>
#include <linux/virtio_ids.h>
#include <linux/virtio_config.h>
#include <linux/virtio_vsock.h>
#include <net/sock.h>
#include <linux/mutex.h>
#include <net/af_vsock.h>

static struct workqueue_struct *virtio_vsock_workqueue;
static struct virtio_vsock *the_virtio_vsock;
static DEFINE_MUTEX(the_virtio_vsock_mutex); /* protects the_virtio_vsock */

struct virtio_vsock {
	struct virtio_device *vdev;
	struct virtqueue *vqs[VSOCK_VQ_MAX];

	/* Virtqueue processing is deferred to a workqueue */
	struct work_struct tx_work;
	struct work_struct rx_work;
	struct work_struct event_work;

	/* The following fields are protected by tx_lock.  vqs[VSOCK_VQ_TX]
	 * must be accessed with tx_lock held.
	 */
	struct mutex tx_lock;

	struct work_struct send_pkt_work;
	spinlock_t send_pkt_list_lock;
	struct list_head send_pkt_list;

	atomic_t queued_replies;

	/* The following fields are protected by rx_lock.  vqs[VSOCK_VQ_RX]
	 * must be accessed with rx_lock held.
	 */
	struct mutex rx_lock;
	int rx_buf_nr;
	int rx_buf_max_nr;

	/* The following fields are protected by event_lock.
	 * vqs[VSOCK_VQ_EVENT] must be accessed with event_lock held.
	 */
	struct mutex event_lock;
	struct virtio_vsock_event event_list[8];

	u32 guest_cid;
};

static struct virtio_vsock *virtio_vsock_get(void)
{
	return the_virtio_vsock;
}

static u32 virtio_transport_get_local_cid(void)
{
	struct virtio_vsock *vsock = virtio_vsock_get();

	return vsock->guest_cid;
}

static void
virtio_transport_send_pkt_work(struct work_struct *work)
{
	struct virtio_vsock *vsock =
		container_of(work, struct virtio_vsock, send_pkt_work);
	struct virtqueue *vq;
	bool added = false;
	bool restart_rx = false;

	mutex_lock(&vsock->tx_lock);

	vq = vsock->vqs[VSOCK_VQ_TX];

	/* Avoid unnecessary interrupts while we're processing the ring */
	virtqueue_disable_cb(vq);

	for (;;) {
		struct virtio_vsock_pkt *pkt;
		struct scatterlist hdr, buf, *sgs[2];
		int ret, in_sg = 0, out_sg = 0;
		bool reply;

		spin_lock_bh(&vsock->send_pkt_list_lock);
		if (list_empty(&vsock->send_pkt_list)) {
			spin_unlock_bh(&vsock->send_pkt_list_lock);
			virtqueue_enable_cb(vq);
			break;
		}

		pkt = list_first_entry(&vsock->send_pkt_list,
				       struct virtio_vsock_pkt, list);
		list_del_init(&pkt->list);
		spin_unlock_bh(&vsock->send_pkt_list_lock);

		reply = pkt->reply;

		sg_init_one(&hdr, &pkt->hdr, sizeof(pkt->hdr));
		sgs[out_sg++] = &hdr;
		if (pkt->buf) {
			sg_init_one(&buf, pkt->buf, pkt->len);
			sgs[out_sg++] = &buf;
		}

		ret = virtqueue_add_sgs(vq, sgs, out_sg, in_sg, pkt, GFP_KERNEL);
		if (ret < 0) {
			spin_lock_bh(&vsock->send_pkt_list_lock);
			list_add(&pkt->list, &vsock->send_pkt_list);
			spin_unlock_bh(&vsock->send_pkt_list_lock);

			if (!virtqueue_enable_cb(vq) && ret == -ENOSPC)
				continue; /* retry now that we have more space */
			break;
		}

		if (reply) {
			struct virtqueue *rx_vq = vsock->vqs[VSOCK_VQ_RX];
			int val;

			val = atomic_dec_return(&vsock->queued_replies);

			/* Do we now have resources to resume rx processing? */
			if (val + 1 == virtqueue_get_vring_size(rx_vq))
				restart_rx = true;
		}

		added = true;
	}

	if (added)
		virtqueue_kick(vq);

	mutex_unlock(&vsock->tx_lock);

	if (restart_rx)
		queue_work(virtio_vsock_workqueue, &vsock->rx_work);
}

static int
virtio_transport_send_pkt(struct virtio_vsock_pkt *pkt)
{
	struct virtio_vsock *vsock;
	int len = pkt->len;

	vsock = virtio_vsock_get();
	if (!vsock) {
		virtio_transport_free_pkt(pkt);
		return -ENODEV;
	}

	if (pkt->reply)
		atomic_inc(&vsock->queued_replies);

	spin_lock_bh(&vsock->send_pkt_list_lock);
	list_add_tail(&pkt->list, &vsock->send_pkt_list);
	spin_unlock_bh(&vsock->send_pkt_list_lock);

	queue_work(virtio_vsock_workqueue, &vsock->send_pkt_work);
	return len;
}

static void virtio_vsock_rx_fill(struct virtio_vsock *vsock)
{
	int buf_len = VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE;
	struct virtio_vsock_pkt *pkt;
	struct scatterlist hdr, buf, *sgs[2];
	struct virtqueue *vq;
	int ret;

	vq = vsock->vqs[VSOCK_VQ_RX];

	do {
		pkt = kzalloc(sizeof(*pkt), GFP_KERNEL);
		if (!pkt)
			break;

		pkt->buf = kmalloc(buf_len, GFP_KERNEL);
		if (!pkt->buf) {
			virtio_transport_free_pkt(pkt);
			break;
		}

		pkt->len = buf_len;

		sg_init_one(&hdr, &pkt->hdr, sizeof(pkt->hdr));
		sgs[0] = &hdr;

		sg_init_one(&buf, pkt->buf, buf_len);
		sgs[1] = &buf;
		ret = virtqueue_add_sgs(vq, sgs, 0, 2, pkt, GFP_KERNEL);
		if (ret) {
			virtio_transport_free_pkt(pkt);
			break;
		}
		vsock->rx_buf_nr++;
	} while (vq->num_free);
	if (vsock->rx_buf_nr > vsock->rx_buf_max_nr)
		vsock->rx_buf_max_nr = vsock->rx_buf_nr;
	virtqueue_kick(vq);
}

static void virtio_transport_tx_work(struct work_struct *work)
{
	struct virtio_vsock *vsock =
		container_of(work, struct virtio_vsock, tx_work);
	struct virtqueue *vq;
	bool added = false;

	vq = vsock->vqs[VSOCK_VQ_TX];
	mutex_lock(&vsock->tx_lock);
	do {
		struct virtio_vsock_pkt *pkt;
		unsigned int len;

		virtqueue_disable_cb(vq);
		while ((pkt = virtqueue_get_buf(vq, &len)) != NULL) {
			virtio_transport_free_pkt(pkt);
			added = true;
		}
	} while (!virtqueue_enable_cb(vq));
	mutex_unlock(&vsock->tx_lock);

	if (added)
		queue_work(virtio_vsock_workqueue, &vsock->send_pkt_work);
}

/* Is there space left for replies to rx packets? */
static bool virtio_transport_more_replies(struct virtio_vsock *vsock)
{
	struct virtqueue *vq = vsock->vqs[VSOCK_VQ_RX];
	int val;

	smp_rmb(); /* paired with atomic_inc() and atomic_dec_return() */
	val = atomic_read(&vsock->queued_replies);

	return val < virtqueue_get_vring_size(vq);
}

static void virtio_transport_rx_work(struct work_struct *work)
{
	struct virtio_vsock *vsock =
		container_of(work, struct virtio_vsock, rx_work);
	struct virtqueue *vq;

	vq = vsock->vqs[VSOCK_VQ_RX];

	mutex_lock(&vsock->rx_lock);

	do {
		virtqueue_disable_cb(vq);
		for (;;) {
			struct virtio_vsock_pkt *pkt;
			unsigned int len;

			if (!virtio_transport_more_replies(vsock)) {
				/* Stop rx until the device processes already
				 * pending replies.  Leave rx virtqueue
				 * callbacks disabled.
				 */
				goto out;
			}

			pkt = virtqueue_get_buf(vq, &len);
			if (!pkt) {
				break;
			}

			vsock->rx_buf_nr--;

			/* Drop short/long packets */
			if (unlikely(len < sizeof(pkt->hdr) ||
				     len > sizeof(pkt->hdr) + pkt->len)) {
				virtio_transport_free_pkt(pkt);
				continue;
			}

			pkt->len = len - sizeof(pkt->hdr);
			virtio_transport_recv_pkt(pkt);
		}
	} while (!virtqueue_enable_cb(vq));

out:
	if (vsock->rx_buf_nr < vsock->rx_buf_max_nr / 2)
		virtio_vsock_rx_fill(vsock);
	mutex_unlock(&vsock->rx_lock);
}

/* event_lock must be held */
static int virtio_vsock_event_fill_one(struct virtio_vsock *vsock,
				       struct virtio_vsock_event *event)
{
	struct scatterlist sg;
	struct virtqueue *vq;

	vq = vsock->vqs[VSOCK_VQ_EVENT];

	sg_init_one(&sg, event, sizeof(*event));

	return virtqueue_add_inbuf(vq, &sg, 1, event, GFP_KERNEL);
}

/* event_lock must be held */
static void virtio_vsock_event_fill(struct virtio_vsock *vsock)
{
	size_t i;

	for (i = 0; i < ARRAY_SIZE(vsock->event_list); i++) {
		struct virtio_vsock_event *event = &vsock->event_list[i];

		virtio_vsock_event_fill_one(vsock, event);
	}

	virtqueue_kick(vsock->vqs[VSOCK_VQ_EVENT]);
}

static void virtio_vsock_reset_sock(struct sock *sk)
{
	lock_sock(sk);
	sk->sk_state = SS_UNCONNECTED;
	sk->sk_err = ECONNRESET;
	sk->sk_error_report(sk);
	release_sock(sk);
}

static void virtio_vsock_update_guest_cid(struct virtio_vsock *vsock)
{
	struct virtio_device *vdev = vsock->vdev;
	u64 guest_cid;

	vdev->config->get(vdev, offsetof(struct virtio_vsock_config, guest_cid),
			  &guest_cid, sizeof(guest_cid));
	vsock->guest_cid = le64_to_cpu(guest_cid);
}

/* event_lock must be held */
static void virtio_vsock_event_handle(struct virtio_vsock *vsock,
				      struct virtio_vsock_event *event)
{
	switch (le32_to_cpu(event->id)) {
	case VIRTIO_VSOCK_EVENT_TRANSPORT_RESET:
		virtio_vsock_update_guest_cid(vsock);
		vsock_for_each_connected_socket(virtio_vsock_reset_sock);
		break;
	}
}

static void virtio_transport_event_work(struct work_struct *work)
{
	struct virtio_vsock *vsock =
		container_of(work, struct virtio_vsock, event_work);
	struct virtqueue *vq;

	vq = vsock->vqs[VSOCK_VQ_EVENT];

	mutex_lock(&vsock->event_lock);

	do {
		struct virtio_vsock_event *event;
		unsigned int len;

		virtqueue_disable_cb(vq);
		while ((event = virtqueue_get_buf(vq, &len)) != NULL) {
			if (len == sizeof(*event))
				virtio_vsock_event_handle(vsock, event);

			virtio_vsock_event_fill_one(vsock, event);
		}
	} while (!virtqueue_enable_cb(vq));

	virtqueue_kick(vsock->vqs[VSOCK_VQ_EVENT]);

	mutex_unlock(&vsock->event_lock);
}

static void virtio_vsock_event_done(struct virtqueue *vq)
{
	struct virtio_vsock *vsock = vq->vdev->priv;

	if (!vsock)
		return;
	queue_work(virtio_vsock_workqueue, &vsock->event_work);
}

static void virtio_vsock_tx_done(struct virtqueue *vq)
{
	struct virtio_vsock *vsock = vq->vdev->priv;

	if (!vsock)
		return;
	queue_work(virtio_vsock_workqueue, &vsock->tx_work);
}

static void virtio_vsock_rx_done(struct virtqueue *vq)
{
	struct virtio_vsock *vsock = vq->vdev->priv;

	if (!vsock)
		return;
	queue_work(virtio_vsock_workqueue, &vsock->rx_work);
}

static struct virtio_transport virtio_transport = {
	.transport = {
		.get_local_cid            = virtio_transport_get_local_cid,

		.init                     = virtio_transport_do_socket_init,
		.destruct                 = virtio_transport_destruct,
		.release                  = virtio_transport_release,
		.connect                  = virtio_transport_connect,
		.shutdown                 = virtio_transport_shutdown,

		.dgram_bind               = virtio_transport_dgram_bind,
		.dgram_dequeue            = virtio_transport_dgram_dequeue,
		.dgram_enqueue            = virtio_transport_dgram_enqueue,
		.dgram_allow              = virtio_transport_dgram_allow,

		.stream_dequeue           = virtio_transport_stream_dequeue,
		.stream_enqueue           = virtio_transport_stream_enqueue,
		.stream_has_data          = virtio_transport_stream_has_data,
		.stream_has_space         = virtio_transport_stream_has_space,
		.stream_rcvhiwat          = virtio_transport_stream_rcvhiwat,
		.stream_is_active         = virtio_transport_stream_is_active,
		.stream_allow             = virtio_transport_stream_allow,

		.notify_poll_in           = virtio_transport_notify_poll_in,
		.notify_poll_out          = virtio_transport_notify_poll_out,
		.notify_recv_init         = virtio_transport_notify_recv_init,
		.notify_recv_pre_block    = virtio_transport_notify_recv_pre_block,
		.notify_recv_pre_dequeue  = virtio_transport_notify_recv_pre_dequeue,
		.notify_recv_post_dequeue = virtio_transport_notify_recv_post_dequeue,
		.notify_send_init         = virtio_transport_notify_send_init,
		.notify_send_pre_block    = virtio_transport_notify_send_pre_block,
		.notify_send_pre_enqueue  = virtio_transport_notify_send_pre_enqueue,
		.notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue,

		.set_buffer_size          = virtio_transport_set_buffer_size,
		.set_min_buffer_size      = virtio_transport_set_min_buffer_size,
		.set_max_buffer_size      = virtio_transport_set_max_buffer_size,
		.get_buffer_size          = virtio_transport_get_buffer_size,
		.get_min_buffer_size      = virtio_transport_get_min_buffer_size,
		.get_max_buffer_size      = virtio_transport_get_max_buffer_size,
	},

	.send_pkt = virtio_transport_send_pkt,
};

static int virtio_vsock_probe(struct virtio_device *vdev)
{
	vq_callback_t *callbacks[] = {
		virtio_vsock_rx_done,
		virtio_vsock_tx_done,
		virtio_vsock_event_done,
	};
	static const char * const names[] = {
		"rx",
		"tx",
		"event",
	};
	struct virtio_vsock *vsock = NULL;
	int ret;

	ret = mutex_lock_interruptible(&the_virtio_vsock_mutex);
	if (ret)
		return ret;

	/* Only one virtio-vsock device per guest is supported */
	if (the_virtio_vsock) {
		ret = -EBUSY;
		goto out;
	}

	vsock = kzalloc(sizeof(*vsock), GFP_KERNEL);
	if (!vsock) {
		ret = -ENOMEM;
		goto out;
	}

	vsock->vdev = vdev;

	ret = vsock->vdev->config->find_vqs(vsock->vdev, VSOCK_VQ_MAX,
					    vsock->vqs, callbacks, names);
	if (ret < 0)
		goto out;

	virtio_vsock_update_guest_cid(vsock);

	ret = vsock_core_init(&virtio_transport.transport);
	if (ret < 0)
		goto out_vqs;

	vsock->rx_buf_nr = 0;
	vsock->rx_buf_max_nr = 0;
	atomic_set(&vsock->queued_replies, 0);

	vdev->priv = vsock;
	the_virtio_vsock = vsock;
	mutex_init(&vsock->tx_lock);
	mutex_init(&vsock->rx_lock);
	mutex_init(&vsock->event_lock);
	spin_lock_init(&vsock->send_pkt_list_lock);
	INIT_LIST_HEAD(&vsock->send_pkt_list);
	INIT_WORK(&vsock->rx_work, virtio_transport_rx_work);
	INIT_WORK(&vsock->tx_work, virtio_transport_tx_work);
	INIT_WORK(&vsock->event_work, virtio_transport_event_work);
	INIT_WORK(&vsock->send_pkt_work, virtio_transport_send_pkt_work);

	mutex_lock(&vsock->rx_lock);
	virtio_vsock_rx_fill(vsock);
	mutex_unlock(&vsock->rx_lock);

	mutex_lock(&vsock->event_lock);
	virtio_vsock_event_fill(vsock);
	mutex_unlock(&vsock->event_lock);

	mutex_unlock(&the_virtio_vsock_mutex);
	return 0;

out_vqs:
	vsock->vdev->config->del_vqs(vsock->vdev);
out:
	kfree(vsock);
	mutex_unlock(&the_virtio_vsock_mutex);
	return ret;
}

static void virtio_vsock_remove(struct virtio_device *vdev)
{
	struct virtio_vsock *vsock = vdev->priv;
	struct virtio_vsock_pkt *pkt;

	flush_work(&vsock->rx_work);
	flush_work(&vsock->tx_work);
	flush_work(&vsock->event_work);
	flush_work(&vsock->send_pkt_work);

	vdev->config->reset(vdev);

	mutex_lock(&vsock->rx_lock);
	while ((pkt = virtqueue_detach_unused_buf(vsock->vqs[VSOCK_VQ_RX])))
		virtio_transport_free_pkt(pkt);
	mutex_unlock(&vsock->rx_lock);

	mutex_lock(&vsock->tx_lock);
	while ((pkt = virtqueue_detach_unused_buf(vsock->vqs[VSOCK_VQ_TX])))
		virtio_transport_free_pkt(pkt);
	mutex_unlock(&vsock->tx_lock);

	spin_lock_bh(&vsock->send_pkt_list_lock);
	while (!list_empty(&vsock->send_pkt_list)) {
		pkt = list_first_entry(&vsock->send_pkt_list,
				       struct virtio_vsock_pkt, list);
		list_del(&pkt->list);
		virtio_transport_free_pkt(pkt);
	}
	spin_unlock_bh(&vsock->send_pkt_list_lock);

	mutex_lock(&the_virtio_vsock_mutex);
	the_virtio_vsock = NULL;
	vsock_core_exit();
	mutex_unlock(&the_virtio_vsock_mutex);

	vdev->config->del_vqs(vdev);

	kfree(vsock);
}

static struct virtio_device_id id_table[] = {
	{ VIRTIO_ID_VSOCK, VIRTIO_DEV_ANY_ID },
	{ 0 },
};

static unsigned int features[] = {
};

static struct virtio_driver virtio_vsock_driver = {
	.feature_table = features,
	.feature_table_size = ARRAY_SIZE(features),
	.driver.name = KBUILD_MODNAME,
	.driver.owner = THIS_MODULE,
	.id_table = id_table,
	.probe = virtio_vsock_probe,
	.remove = virtio_vsock_remove,
};

static int __init virtio_vsock_init(void)
{
	int ret;

	virtio_vsock_workqueue = alloc_workqueue("virtio_vsock", 0, 0);
	if (!virtio_vsock_workqueue)
		return -ENOMEM;
	ret = register_virtio_driver(&virtio_vsock_driver);
	if (ret)
		destroy_workqueue(virtio_vsock_workqueue);
	return ret;
}

static void __exit virtio_vsock_exit(void)
{
	unregister_virtio_driver(&virtio_vsock_driver);
	destroy_workqueue(virtio_vsock_workqueue);
}

module_init(virtio_vsock_init);
module_exit(virtio_vsock_exit);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Asias He");
MODULE_DESCRIPTION("virtio transport for vsock");
MODULE_DEVICE_TABLE(virtio, id_table);