summaryrefslogtreecommitdiffstats
path: root/drivers/vhost/vsock.c
blob: 97669484a3f690f5f699fd9f4cadc32719cfb65e (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
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
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
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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * vhost transport for vsock
 *
 * Copyright (C) 2013-2015 Red Hat, Inc.
 * Author: Asias He <asias@redhat.com>
 *         Stefan Hajnoczi <stefanha@redhat.com>
 */
#include <linux/miscdevice.h>
#include <linux/atomic.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/vmalloc.h>
#include <net/sock.h>
#include <linux/virtio_vsock.h>
#include <linux/vhost.h>
#include <linux/hashtable.h>

#include <net/af_vsock.h>
#include "vhost.h"

#define VHOST_VSOCK_DEFAULT_HOST_CID	2
/* Max number of bytes transferred before requeueing the job.
 * Using this limit prevents one virtqueue from starving others. */
#define VHOST_VSOCK_WEIGHT 0x80000
/* Max number of packets transferred before requeueing the job.
 * Using this limit prevents one virtqueue from starving others with
 * small pkts.
 */
#define VHOST_VSOCK_PKT_WEIGHT 256

enum {
	VHOST_VSOCK_FEATURES = VHOST_FEATURES,
};

/* Used to track all the vhost_vsock instances on the system. */
static DEFINE_MUTEX(vhost_vsock_mutex);
static DEFINE_READ_MOSTLY_HASHTABLE(vhost_vsock_hash, 8);

struct vhost_vsock {
	struct vhost_dev dev;
	struct vhost_virtqueue vqs[2];

	/* Link to global vhost_vsock_hash, writes use vhost_vsock_mutex */
	struct hlist_node hash;

	struct vhost_work send_pkt_work;
	spinlock_t send_pkt_list_lock;
	struct list_head send_pkt_list;	/* host->guest pending packets */

	atomic_t queued_replies;

	u32 guest_cid;
};

static u32 vhost_transport_get_local_cid(void)
{
	return VHOST_VSOCK_DEFAULT_HOST_CID;
}

/* Callers that dereference the return value must hold vhost_vsock_mutex or the
 * RCU read lock.
 */
static struct vhost_vsock *vhost_vsock_get(u32 guest_cid)
{
	struct vhost_vsock *vsock;

	hash_for_each_possible_rcu(vhost_vsock_hash, vsock, hash, guest_cid) {
		u32 other_cid = vsock->guest_cid;

		/* Skip instances that have no CID yet */
		if (other_cid == 0)
			continue;

		if (other_cid == guest_cid)
			return vsock;

	}

	return NULL;
}

static void
vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
			    struct vhost_virtqueue *vq)
{
	struct vhost_virtqueue *tx_vq = &vsock->vqs[VSOCK_VQ_TX];
	int pkts = 0, total_len = 0;
	bool added = false;
	bool restart_tx = false;

	mutex_lock(&vq->mutex);

	if (!vq->private_data)
		goto out;

	/* Avoid further vmexits, we're already processing the virtqueue */
	vhost_disable_notify(&vsock->dev, vq);

	do {
		struct virtio_vsock_pkt *pkt;
		struct iov_iter iov_iter;
		unsigned out, in;
		size_t nbytes;
		size_t iov_len, payload_len;
		int head;

		spin_lock_bh(&vsock->send_pkt_list_lock);
		if (list_empty(&vsock->send_pkt_list)) {
			spin_unlock_bh(&vsock->send_pkt_list_lock);
			vhost_enable_notify(&vsock->dev, 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);

		head = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov),
					 &out, &in, NULL, NULL);
		if (head < 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);
			break;
		}

		if (head == vq->num) {
			spin_lock_bh(&vsock->send_pkt_list_lock);
			list_add(&pkt->list, &vsock->send_pkt_list);
			spin_unlock_bh(&vsock->send_pkt_list_lock);

			/* We cannot finish yet if more buffers snuck in while
			 * re-enabling notify.
			 */
			if (unlikely(vhost_enable_notify(&vsock->dev, vq))) {
				vhost_disable_notify(&vsock->dev, vq);
				continue;
			}
			break;
		}

		if (out) {
			virtio_transport_free_pkt(pkt);
			vq_err(vq, "Expected 0 output buffers, got %u\n", out);
			break;
		}

		iov_len = iov_length(&vq->iov[out], in);
		if (iov_len < sizeof(pkt->hdr)) {
			virtio_transport_free_pkt(pkt);
			vq_err(vq, "Buffer len [%zu] too small\n", iov_len);
			break;
		}

		iov_iter_init(&iov_iter, READ, &vq->iov[out], in, iov_len);
		payload_len = pkt->len - pkt->off;

		/* If the packet is greater than the space available in the
		 * buffer, we split it using multiple buffers.
		 */
		if (payload_len > iov_len - sizeof(pkt->hdr))
			payload_len = iov_len - sizeof(pkt->hdr);

		/* Set the correct length in the header */
		pkt->hdr.len = cpu_to_le32(payload_len);

		nbytes = copy_to_iter(&pkt->hdr, sizeof(pkt->hdr), &iov_iter);
		if (nbytes != sizeof(pkt->hdr)) {
			virtio_transport_free_pkt(pkt);
			vq_err(vq, "Faulted on copying pkt hdr\n");
			break;
		}

		nbytes = copy_to_iter(pkt->buf + pkt->off, payload_len,
				      &iov_iter);
		if (nbytes != payload_len) {
			virtio_transport_free_pkt(pkt);
			vq_err(vq, "Faulted on copying pkt buf\n");
			break;
		}

		vhost_add_used(vq, head, sizeof(pkt->hdr) + payload_len);
		added = true;

		/* Deliver to monitoring devices all correctly transmitted
		 * packets.
		 */
		virtio_transport_deliver_tap_pkt(pkt);

		pkt->off += payload_len;
		total_len += payload_len;

		/* If we didn't send all the payload we can requeue the packet
		 * to send it with the next available buffer.
		 */
		if (pkt->off < pkt->len) {
			spin_lock_bh(&vsock->send_pkt_list_lock);
			list_add(&pkt->list, &vsock->send_pkt_list);
			spin_unlock_bh(&vsock->send_pkt_list_lock);
		} else {
			if (pkt->reply) {
				int val;

				val = atomic_dec_return(&vsock->queued_replies);

				/* Do we have resources to resume tx
				 * processing?
				 */
				if (val + 1 == tx_vq->num)
					restart_tx = true;
			}

			virtio_transport_free_pkt(pkt);
		}
	} while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len)));
	if (added)
		vhost_signal(&vsock->dev, vq);

out:
	mutex_unlock(&vq->mutex);

	if (restart_tx)
		vhost_poll_queue(&tx_vq->poll);
}

static void vhost_transport_send_pkt_work(struct vhost_work *work)
{
	struct vhost_virtqueue *vq;
	struct vhost_vsock *vsock;

	vsock = container_of(work, struct vhost_vsock, send_pkt_work);
	vq = &vsock->vqs[VSOCK_VQ_RX];

	vhost_transport_do_send_pkt(vsock, vq);
}

static int
vhost_transport_send_pkt(struct virtio_vsock_pkt *pkt)
{
	struct vhost_vsock *vsock;
	int len = pkt->len;

	rcu_read_lock();

	/* Find the vhost_vsock according to guest context id  */
	vsock = vhost_vsock_get(le64_to_cpu(pkt->hdr.dst_cid));
	if (!vsock) {
		rcu_read_unlock();
		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);

	vhost_work_queue(&vsock->dev, &vsock->send_pkt_work);

	rcu_read_unlock();
	return len;
}

static int
vhost_transport_cancel_pkt(struct vsock_sock *vsk)
{
	struct vhost_vsock *vsock;
	struct virtio_vsock_pkt *pkt, *n;
	int cnt = 0;
	int ret = -ENODEV;
	LIST_HEAD(freeme);

	rcu_read_lock();

	/* Find the vhost_vsock according to guest context id  */
	vsock = vhost_vsock_get(vsk->remote_addr.svm_cid);
	if (!vsock)
		goto out;

	spin_lock_bh(&vsock->send_pkt_list_lock);
	list_for_each_entry_safe(pkt, n, &vsock->send_pkt_list, list) {
		if (pkt->vsk != vsk)
			continue;
		list_move(&pkt->list, &freeme);
	}
	spin_unlock_bh(&vsock->send_pkt_list_lock);

	list_for_each_entry_safe(pkt, n, &freeme, list) {
		if (pkt->reply)
			cnt++;
		list_del(&pkt->list);
		virtio_transport_free_pkt(pkt);
	}

	if (cnt) {
		struct vhost_virtqueue *tx_vq = &vsock->vqs[VSOCK_VQ_TX];
		int new_cnt;

		new_cnt = atomic_sub_return(cnt, &vsock->queued_replies);
		if (new_cnt + cnt >= tx_vq->num && new_cnt < tx_vq->num)
			vhost_poll_queue(&tx_vq->poll);
	}

	ret = 0;
out:
	rcu_read_unlock();
	return ret;
}

static struct virtio_vsock_pkt *
vhost_vsock_alloc_pkt(struct vhost_virtqueue *vq,
		      unsigned int out, unsigned int in)
{
	struct virtio_vsock_pkt *pkt;
	struct iov_iter iov_iter;
	size_t nbytes;
	size_t len;

	if (in != 0) {
		vq_err(vq, "Expected 0 input buffers, got %u\n", in);
		return NULL;
	}

	pkt = kzalloc(sizeof(*pkt), GFP_KERNEL);
	if (!pkt)
		return NULL;

	len = iov_length(vq->iov, out);
	iov_iter_init(&iov_iter, WRITE, vq->iov, out, len);

	nbytes = copy_from_iter(&pkt->hdr, sizeof(pkt->hdr), &iov_iter);
	if (nbytes != sizeof(pkt->hdr)) {
		vq_err(vq, "Expected %zu bytes for pkt->hdr, got %zu bytes\n",
		       sizeof(pkt->hdr), nbytes);
		kfree(pkt);
		return NULL;
	}

	if (le16_to_cpu(pkt->hdr.type) == VIRTIO_VSOCK_TYPE_STREAM)
		pkt->len = le32_to_cpu(pkt->hdr.len);

	/* No payload */
	if (!pkt->len)
		return pkt;

	/* The pkt is too big */
	if (pkt->len > VIRTIO_VSOCK_MAX_PKT_BUF_SIZE) {
		kfree(pkt);
		return NULL;
	}

	pkt->buf = kmalloc(pkt->len, GFP_KERNEL);
	if (!pkt->buf) {
		kfree(pkt);
		return NULL;
	}

	pkt->buf_len = pkt->len;

	nbytes = copy_from_iter(pkt->buf, pkt->len, &iov_iter);
	if (nbytes != pkt->len) {
		vq_err(vq, "Expected %u byte payload, got %zu bytes\n",
		       pkt->len, nbytes);
		virtio_transport_free_pkt(pkt);
		return NULL;
	}

	return pkt;
}

/* Is there space left for replies to rx packets? */
static bool vhost_vsock_more_replies(struct vhost_vsock *vsock)
{
	struct vhost_virtqueue *vq = &vsock->vqs[VSOCK_VQ_TX];
	int val;

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

	return val < vq->num;
}

static struct virtio_transport vhost_transport = {
	.transport = {
		.module                   = THIS_MODULE,

		.get_local_cid            = vhost_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,
		.cancel_pkt               = vhost_transport_cancel_pkt,

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

		.stream_enqueue           = virtio_transport_stream_enqueue,
		.stream_dequeue           = virtio_transport_stream_dequeue,
		.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,
		.notify_buffer_size       = virtio_transport_notify_buffer_size,

	},

	.send_pkt = vhost_transport_send_pkt,
};

static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
{
	struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
						  poll.work);
	struct vhost_vsock *vsock = container_of(vq->dev, struct vhost_vsock,
						 dev);
	struct virtio_vsock_pkt *pkt;
	int head, pkts = 0, total_len = 0;
	unsigned int out, in;
	bool added = false;

	mutex_lock(&vq->mutex);

	if (!vq->private_data)
		goto out;

	vhost_disable_notify(&vsock->dev, vq);
	do {
		u32 len;

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

		head = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov),
					 &out, &in, NULL, NULL);
		if (head < 0)
			break;

		if (head == vq->num) {
			if (unlikely(vhost_enable_notify(&vsock->dev, vq))) {
				vhost_disable_notify(&vsock->dev, vq);
				continue;
			}
			break;
		}

		pkt = vhost_vsock_alloc_pkt(vq, out, in);
		if (!pkt) {
			vq_err(vq, "Faulted on pkt\n");
			continue;
		}

		len = pkt->len;

		/* Deliver to monitoring devices all received packets */
		virtio_transport_deliver_tap_pkt(pkt);

		/* Only accept correctly addressed packets */
		if (le64_to_cpu(pkt->hdr.src_cid) == vsock->guest_cid &&
		    le64_to_cpu(pkt->hdr.dst_cid) ==
		    vhost_transport_get_local_cid())
			virtio_transport_recv_pkt(&vhost_transport, pkt);
		else
			virtio_transport_free_pkt(pkt);

		len += sizeof(pkt->hdr);
		vhost_add_used(vq, head, len);
		total_len += len;
		added = true;
	} while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len)));

no_more_replies:
	if (added)
		vhost_signal(&vsock->dev, vq);

out:
	mutex_unlock(&vq->mutex);
}

static void vhost_vsock_handle_rx_kick(struct vhost_work *work)
{
	struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
						poll.work);
	struct vhost_vsock *vsock = container_of(vq->dev, struct vhost_vsock,
						 dev);

	vhost_transport_do_send_pkt(vsock, vq);
}

static int vhost_vsock_start(struct vhost_vsock *vsock)
{
	struct vhost_virtqueue *vq;
	size_t i;
	int ret;

	mutex_lock(&vsock->dev.mutex);

	ret = vhost_dev_check_owner(&vsock->dev);
	if (ret)
		goto err;

	for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) {
		vq = &vsock->vqs[i];

		mutex_lock(&vq->mutex);

		if (!vhost_vq_access_ok(vq)) {
			ret = -EFAULT;
			goto err_vq;
		}

		if (!vq->private_data) {
			vq->private_data = vsock;
			ret = vhost_vq_init_access(vq);
			if (ret)
				goto err_vq;
		}

		mutex_unlock(&vq->mutex);
	}

	mutex_unlock(&vsock->dev.mutex);
	return 0;

err_vq:
	vq->private_data = NULL;
	mutex_unlock(&vq->mutex);

	for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) {
		vq = &vsock->vqs[i];

		mutex_lock(&vq->mutex);
		vq->private_data = NULL;
		mutex_unlock(&vq->mutex);
	}
err:
	mutex_unlock(&vsock->dev.mutex);
	return ret;
}

static int vhost_vsock_stop(struct vhost_vsock *vsock)
{
	size_t i;
	int ret;

	mutex_lock(&vsock->dev.mutex);

	ret = vhost_dev_check_owner(&vsock->dev);
	if (ret)
		goto err;

	for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) {
		struct vhost_virtqueue *vq = &vsock->vqs[i];

		mutex_lock(&vq->mutex);
		vq->private_data = NULL;
		mutex_unlock(&vq->mutex);
	}

err:
	mutex_unlock(&vsock->dev.mutex);
	return ret;
}

static void vhost_vsock_free(struct vhost_vsock *vsock)
{
	kvfree(vsock);
}

static int vhost_vsock_dev_open(struct inode *inode, struct file *file)
{
	struct vhost_virtqueue **vqs;
	struct vhost_vsock *vsock;
	int ret;

	/* This struct is large and allocation could fail, fall back to vmalloc
	 * if there is no other way.
	 */
	vsock = kvmalloc(sizeof(*vsock), GFP_KERNEL | __GFP_RETRY_MAYFAIL);
	if (!vsock)
		return -ENOMEM;

	vqs = kmalloc_array(ARRAY_SIZE(vsock->vqs), sizeof(*vqs), GFP_KERNEL);
	if (!vqs) {
		ret = -ENOMEM;
		goto out;
	}

	vsock->guest_cid = 0; /* no CID assigned yet */

	atomic_set(&vsock->queued_replies, 0);

	vqs[VSOCK_VQ_TX] = &vsock->vqs[VSOCK_VQ_TX];
	vqs[VSOCK_VQ_RX] = &vsock->vqs[VSOCK_VQ_RX];
	vsock->vqs[VSOCK_VQ_TX].handle_kick = vhost_vsock_handle_tx_kick;
	vsock->vqs[VSOCK_VQ_RX].handle_kick = vhost_vsock_handle_rx_kick;

	vhost_dev_init(&vsock->dev, vqs, ARRAY_SIZE(vsock->vqs),
		       UIO_MAXIOV, VHOST_VSOCK_PKT_WEIGHT,
		       VHOST_VSOCK_WEIGHT, NULL);

	file->private_data = vsock;
	spin_lock_init(&vsock->send_pkt_list_lock);
	INIT_LIST_HEAD(&vsock->send_pkt_list);
	vhost_work_init(&vsock->send_pkt_work, vhost_transport_send_pkt_work);
	return 0;

out:
	vhost_vsock_free(vsock);
	return ret;
}

static void vhost_vsock_flush(struct vhost_vsock *vsock)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++)
		if (vsock->vqs[i].handle_kick)
			vhost_poll_flush(&vsock->vqs[i].poll);
	vhost_work_flush(&vsock->dev, &vsock->send_pkt_work);
}

static void vhost_vsock_reset_orphans(struct sock *sk)
{
	struct vsock_sock *vsk = vsock_sk(sk);

	/* vmci_transport.c doesn't take sk_lock here either.  At least we're
	 * under vsock_table_lock so the sock cannot disappear while we're
	 * executing.
	 */

	/* If the peer is still valid, no need to reset connection */
	if (vhost_vsock_get(vsk->remote_addr.svm_cid))
		return;

	/* If the close timeout is pending, let it expire.  This avoids races
	 * with the timeout callback.
	 */
	if (vsk->close_work_scheduled)
		return;

	sock_set_flag(sk, SOCK_DONE);
	vsk->peer_shutdown = SHUTDOWN_MASK;
	sk->sk_state = SS_UNCONNECTED;
	sk->sk_err = ECONNRESET;
	sk->sk_error_report(sk);
}

static int vhost_vsock_dev_release(struct inode *inode, struct file *file)
{
	struct vhost_vsock *vsock = file->private_data;

	mutex_lock(&vhost_vsock_mutex);
	if (vsock->guest_cid)
		hash_del_rcu(&vsock->hash);
	mutex_unlock(&vhost_vsock_mutex);

	/* Wait for other CPUs to finish using vsock */
	synchronize_rcu();

	/* Iterating over all connections for all CIDs to find orphans is
	 * inefficient.  Room for improvement here. */
	vsock_for_each_connected_socket(vhost_vsock_reset_orphans);

	vhost_vsock_stop(vsock);
	vhost_vsock_flush(vsock);
	vhost_dev_stop(&vsock->dev);

	spin_lock_bh(&vsock->send_pkt_list_lock);
	while (!list_empty(&vsock->send_pkt_list)) {
		struct virtio_vsock_pkt *pkt;

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

	vhost_dev_cleanup(&vsock->dev);
	kfree(vsock->dev.vqs);
	vhost_vsock_free(vsock);
	return 0;
}

static int vhost_vsock_set_cid(struct vhost_vsock *vsock, u64 guest_cid)
{
	struct vhost_vsock *other;

	/* Refuse reserved CIDs */
	if (guest_cid <= VMADDR_CID_HOST ||
	    guest_cid == U32_MAX)
		return -EINVAL;

	/* 64-bit CIDs are not yet supported */
	if (guest_cid > U32_MAX)
		return -EINVAL;

	/* Refuse if CID is assigned to the guest->host transport (i.e. nested
	 * VM), to make the loopback work.
	 */
	if (vsock_find_cid(guest_cid))
		return -EADDRINUSE;

	/* Refuse if CID is already in use */
	mutex_lock(&vhost_vsock_mutex);
	other = vhost_vsock_get(guest_cid);
	if (other && other != vsock) {
		mutex_unlock(&vhost_vsock_mutex);
		return -EADDRINUSE;
	}

	if (vsock->guest_cid)
		hash_del_rcu(&vsock->hash);

	vsock->guest_cid = guest_cid;
	hash_add_rcu(vhost_vsock_hash, &vsock->hash, vsock->guest_cid);
	mutex_unlock(&vhost_vsock_mutex);

	return 0;
}

static int vhost_vsock_set_features(struct vhost_vsock *vsock, u64 features)
{
	struct vhost_virtqueue *vq;
	int i;

	if (features & ~VHOST_VSOCK_FEATURES)
		return -EOPNOTSUPP;

	mutex_lock(&vsock->dev.mutex);
	if ((features & (1 << VHOST_F_LOG_ALL)) &&
	    !vhost_log_access_ok(&vsock->dev)) {
		mutex_unlock(&vsock->dev.mutex);
		return -EFAULT;
	}

	for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) {
		vq = &vsock->vqs[i];
		mutex_lock(&vq->mutex);
		vq->acked_features = features;
		mutex_unlock(&vq->mutex);
	}
	mutex_unlock(&vsock->dev.mutex);
	return 0;
}

static long vhost_vsock_dev_ioctl(struct file *f, unsigned int ioctl,
				  unsigned long arg)
{
	struct vhost_vsock *vsock = f->private_data;
	void __user *argp = (void __user *)arg;
	u64 guest_cid;
	u64 features;
	int start;
	int r;

	switch (ioctl) {
	case VHOST_VSOCK_SET_GUEST_CID:
		if (copy_from_user(&guest_cid, argp, sizeof(guest_cid)))
			return -EFAULT;
		return vhost_vsock_set_cid(vsock, guest_cid);
	case VHOST_VSOCK_SET_RUNNING:
		if (copy_from_user(&start, argp, sizeof(start)))
			return -EFAULT;
		if (start)
			return vhost_vsock_start(vsock);
		else
			return vhost_vsock_stop(vsock);
	case VHOST_GET_FEATURES:
		features = VHOST_VSOCK_FEATURES;
		if (copy_to_user(argp, &features, sizeof(features)))
			return -EFAULT;
		return 0;
	case VHOST_SET_FEATURES:
		if (copy_from_user(&features, argp, sizeof(features)))
			return -EFAULT;
		return vhost_vsock_set_features(vsock, features);
	default:
		mutex_lock(&vsock->dev.mutex);
		r = vhost_dev_ioctl(&vsock->dev, ioctl, argp);
		if (r == -ENOIOCTLCMD)
			r = vhost_vring_ioctl(&vsock->dev, ioctl, argp);
		else
			vhost_vsock_flush(vsock);
		mutex_unlock(&vsock->dev.mutex);
		return r;
	}
}

static const struct file_operations vhost_vsock_fops = {
	.owner          = THIS_MODULE,
	.open           = vhost_vsock_dev_open,
	.release        = vhost_vsock_dev_release,
	.llseek		= noop_llseek,
	.unlocked_ioctl = vhost_vsock_dev_ioctl,
	.compat_ioctl   = compat_ptr_ioctl,
};

static struct miscdevice vhost_vsock_misc = {
	.minor = VHOST_VSOCK_MINOR,
	.name = "vhost-vsock",
	.fops = &vhost_vsock_fops,
};

static int __init vhost_vsock_init(void)
{
	int ret;

	ret = vsock_core_register(&vhost_transport.transport,
				  VSOCK_TRANSPORT_F_H2G);
	if (ret < 0)
		return ret;
	return misc_register(&vhost_vsock_misc);
};

static void __exit vhost_vsock_exit(void)
{
	misc_deregister(&vhost_vsock_misc);
	vsock_core_unregister(&vhost_transport.transport);
};

module_init(vhost_vsock_init);
module_exit(vhost_vsock_exit);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Asias He");
MODULE_DESCRIPTION("vhost transport for vsock ");
MODULE_ALIAS_MISCDEV(VHOST_VSOCK_MINOR);
MODULE_ALIAS("devname:vhost-vsock");