summaryrefslogtreecommitdiff
path: root/drivers/vhost/vdpa.c
blob: 0968361e3b7745906c1b7da2eab84a7bda4767bc (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
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2018-2020 Intel Corporation.
 * Copyright (C) 2020 Red Hat, Inc.
 *
 * Author: Tiwei Bie <tiwei.bie@intel.com>
 *         Jason Wang <jasowang@redhat.com>
 *
 * Thanks Michael S. Tsirkin for the valuable comments and
 * suggestions.  And thanks to Cunming Liang and Zhihong Wang for all
 * their supports.
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/cdev.h>
#include <linux/device.h>
#include <linux/iommu.h>
#include <linux/uuid.h>
#include <linux/vdpa.h>
#include <linux/nospec.h>
#include <linux/vhost.h>
#include <linux/virtio_net.h>

#include "vhost.h"

enum {
	VHOST_VDPA_FEATURES =
		(1ULL << VIRTIO_F_NOTIFY_ON_EMPTY) |
		(1ULL << VIRTIO_F_ANY_LAYOUT) |
		(1ULL << VIRTIO_F_VERSION_1) |
		(1ULL << VIRTIO_F_IOMMU_PLATFORM) |
		(1ULL << VIRTIO_F_RING_PACKED) |
		(1ULL << VIRTIO_F_ORDER_PLATFORM) |
		(1ULL << VIRTIO_RING_F_INDIRECT_DESC) |
		(1ULL << VIRTIO_RING_F_EVENT_IDX),

	VHOST_VDPA_NET_FEATURES = VHOST_VDPA_FEATURES |
		(1ULL << VIRTIO_NET_F_CSUM) |
		(1ULL << VIRTIO_NET_F_GUEST_CSUM) |
		(1ULL << VIRTIO_NET_F_MTU) |
		(1ULL << VIRTIO_NET_F_MAC) |
		(1ULL << VIRTIO_NET_F_GUEST_TSO4) |
		(1ULL << VIRTIO_NET_F_GUEST_TSO6) |
		(1ULL << VIRTIO_NET_F_GUEST_ECN) |
		(1ULL << VIRTIO_NET_F_GUEST_UFO) |
		(1ULL << VIRTIO_NET_F_HOST_TSO4) |
		(1ULL << VIRTIO_NET_F_HOST_TSO6) |
		(1ULL << VIRTIO_NET_F_HOST_ECN) |
		(1ULL << VIRTIO_NET_F_HOST_UFO) |
		(1ULL << VIRTIO_NET_F_MRG_RXBUF) |
		(1ULL << VIRTIO_NET_F_STATUS) |
		(1ULL << VIRTIO_NET_F_SPEED_DUPLEX),
};

/* Currently, only network backend w/o multiqueue is supported. */
#define VHOST_VDPA_VQ_MAX	2

#define VHOST_VDPA_DEV_MAX (1U << MINORBITS)

struct vhost_vdpa {
	struct vhost_dev vdev;
	struct iommu_domain *domain;
	struct vhost_virtqueue *vqs;
	struct completion completion;
	struct vdpa_device *vdpa;
	struct device dev;
	struct cdev cdev;
	atomic_t opened;
	int nvqs;
	int virtio_id;
	int minor;
};

static DEFINE_IDA(vhost_vdpa_ida);

static dev_t vhost_vdpa_major;

static const u64 vhost_vdpa_features[] = {
	[VIRTIO_ID_NET] = VHOST_VDPA_NET_FEATURES,
};

static void handle_vq_kick(struct vhost_work *work)
{
	struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
						  poll.work);
	struct vhost_vdpa *v = container_of(vq->dev, struct vhost_vdpa, vdev);
	const struct vdpa_config_ops *ops = v->vdpa->config;

	ops->kick_vq(v->vdpa, vq - v->vqs);
}

static irqreturn_t vhost_vdpa_virtqueue_cb(void *private)
{
	struct vhost_virtqueue *vq = private;
	struct eventfd_ctx *call_ctx = vq->call_ctx;

	if (call_ctx)
		eventfd_signal(call_ctx, 1);

	return IRQ_HANDLED;
}

static void vhost_vdpa_reset(struct vhost_vdpa *v)
{
	struct vdpa_device *vdpa = v->vdpa;
	const struct vdpa_config_ops *ops = vdpa->config;

	ops->set_status(vdpa, 0);
}

static long vhost_vdpa_get_device_id(struct vhost_vdpa *v, u8 __user *argp)
{
	struct vdpa_device *vdpa = v->vdpa;
	const struct vdpa_config_ops *ops = vdpa->config;
	u32 device_id;

	device_id = ops->get_device_id(vdpa);

	if (copy_to_user(argp, &device_id, sizeof(device_id)))
		return -EFAULT;

	return 0;
}

static long vhost_vdpa_get_status(struct vhost_vdpa *v, u8 __user *statusp)
{
	struct vdpa_device *vdpa = v->vdpa;
	const struct vdpa_config_ops *ops = vdpa->config;
	u8 status;

	status = ops->get_status(vdpa);

	if (copy_to_user(statusp, &status, sizeof(status)))
		return -EFAULT;

	return 0;
}

static long vhost_vdpa_set_status(struct vhost_vdpa *v, u8 __user *statusp)
{
	struct vdpa_device *vdpa = v->vdpa;
	const struct vdpa_config_ops *ops = vdpa->config;
	u8 status;

	if (copy_from_user(&status, statusp, sizeof(status)))
		return -EFAULT;

	/*
	 * Userspace shouldn't remove status bits unless reset the
	 * status to 0.
	 */
	if (status != 0 && (ops->get_status(vdpa) & ~status) != 0)
		return -EINVAL;

	ops->set_status(vdpa, status);

	return 0;
}

static int vhost_vdpa_config_validate(struct vhost_vdpa *v,
				      struct vhost_vdpa_config *c)
{
	long size = 0;

	switch (v->virtio_id) {
	case VIRTIO_ID_NET:
		size = sizeof(struct virtio_net_config);
		break;
	}

	if (c->len == 0)
		return -EINVAL;

	if (c->len > size - c->off)
		return -E2BIG;

	return 0;
}

static long vhost_vdpa_get_config(struct vhost_vdpa *v,
				  struct vhost_vdpa_config __user *c)
{
	struct vdpa_device *vdpa = v->vdpa;
	const struct vdpa_config_ops *ops = vdpa->config;
	struct vhost_vdpa_config config;
	unsigned long size = offsetof(struct vhost_vdpa_config, buf);
	u8 *buf;

	if (copy_from_user(&config, c, size))
		return -EFAULT;
	if (vhost_vdpa_config_validate(v, &config))
		return -EINVAL;
	buf = kvzalloc(config.len, GFP_KERNEL);
	if (!buf)
		return -ENOMEM;

	ops->get_config(vdpa, config.off, buf, config.len);

	if (copy_to_user(c->buf, buf, config.len)) {
		kvfree(buf);
		return -EFAULT;
	}

	kvfree(buf);
	return 0;
}

static long vhost_vdpa_set_config(struct vhost_vdpa *v,
				  struct vhost_vdpa_config __user *c)
{
	struct vdpa_device *vdpa = v->vdpa;
	const struct vdpa_config_ops *ops = vdpa->config;
	struct vhost_vdpa_config config;
	unsigned long size = offsetof(struct vhost_vdpa_config, buf);
	u8 *buf;

	if (copy_from_user(&config, c, size))
		return -EFAULT;
	if (vhost_vdpa_config_validate(v, &config))
		return -EINVAL;
	buf = kvzalloc(config.len, GFP_KERNEL);
	if (!buf)
		return -ENOMEM;

	if (copy_from_user(buf, c->buf, config.len)) {
		kvfree(buf);
		return -EFAULT;
	}

	ops->set_config(vdpa, config.off, buf, config.len);

	kvfree(buf);
	return 0;
}

static long vhost_vdpa_get_features(struct vhost_vdpa *v, u64 __user *featurep)
{
	struct vdpa_device *vdpa = v->vdpa;
	const struct vdpa_config_ops *ops = vdpa->config;
	u64 features;

	features = ops->get_features(vdpa);
	features &= vhost_vdpa_features[v->virtio_id];

	if (copy_to_user(featurep, &features, sizeof(features)))
		return -EFAULT;

	return 0;
}

static long vhost_vdpa_set_features(struct vhost_vdpa *v, u64 __user *featurep)
{
	struct vdpa_device *vdpa = v->vdpa;
	const struct vdpa_config_ops *ops = vdpa->config;
	u64 features;

	/*
	 * It's not allowed to change the features after they have
	 * been negotiated.
	 */
	if (ops->get_status(vdpa) & VIRTIO_CONFIG_S_FEATURES_OK)
		return -EBUSY;

	if (copy_from_user(&features, featurep, sizeof(features)))
		return -EFAULT;

	if (features & ~vhost_vdpa_features[v->virtio_id])
		return -EINVAL;

	if (ops->set_features(vdpa, features))
		return -EINVAL;

	return 0;
}

static long vhost_vdpa_get_vring_num(struct vhost_vdpa *v, u16 __user *argp)
{
	struct vdpa_device *vdpa = v->vdpa;
	const struct vdpa_config_ops *ops = vdpa->config;
	u16 num;

	num = ops->get_vq_num_max(vdpa);

	if (copy_to_user(argp, &num, sizeof(num)))
		return -EFAULT;

	return 0;
}

static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
				   void __user *argp)
{
	struct vdpa_device *vdpa = v->vdpa;
	const struct vdpa_config_ops *ops = vdpa->config;
	struct vdpa_callback cb;
	struct vhost_virtqueue *vq;
	struct vhost_vring_state s;
	u32 idx;
	long r;

	r = get_user(idx, (u32 __user *)argp);
	if (r < 0)
		return r;

	if (idx >= v->nvqs)
		return -ENOBUFS;

	idx = array_index_nospec(idx, v->nvqs);
	vq = &v->vqs[idx];

	if (cmd == VHOST_VDPA_SET_VRING_ENABLE) {
		if (copy_from_user(&s, argp, sizeof(s)))
			return -EFAULT;
		ops->set_vq_ready(vdpa, idx, s.num);
		return 0;
	}

	if (cmd == VHOST_GET_VRING_BASE)
		vq->last_avail_idx = ops->get_vq_state(v->vdpa, idx);

	r = vhost_vring_ioctl(&v->vdev, cmd, argp);
	if (r)
		return r;

	switch (cmd) {
	case VHOST_SET_VRING_ADDR:
		if (ops->set_vq_address(vdpa, idx,
					(u64)(uintptr_t)vq->desc,
					(u64)(uintptr_t)vq->avail,
					(u64)(uintptr_t)vq->used))
			r = -EINVAL;
		break;

	case VHOST_SET_VRING_BASE:
		if (ops->set_vq_state(vdpa, idx, vq->last_avail_idx))
			r = -EINVAL;
		break;

	case VHOST_SET_VRING_CALL:
		if (vq->call_ctx) {
			cb.callback = vhost_vdpa_virtqueue_cb;
			cb.private = vq;
		} else {
			cb.callback = NULL;
			cb.private = NULL;
		}
		ops->set_vq_cb(vdpa, idx, &cb);
		break;

	case VHOST_SET_VRING_NUM:
		ops->set_vq_num(vdpa, idx, vq->num);
		break;
	}

	return r;
}

static long vhost_vdpa_unlocked_ioctl(struct file *filep,
				      unsigned int cmd, unsigned long arg)
{
	struct vhost_vdpa *v = filep->private_data;
	struct vhost_dev *d = &v->vdev;
	void __user *argp = (void __user *)arg;
	long r;

	mutex_lock(&d->mutex);

	switch (cmd) {
	case VHOST_VDPA_GET_DEVICE_ID:
		r = vhost_vdpa_get_device_id(v, argp);
		break;
	case VHOST_VDPA_GET_STATUS:
		r = vhost_vdpa_get_status(v, argp);
		break;
	case VHOST_VDPA_SET_STATUS:
		r = vhost_vdpa_set_status(v, argp);
		break;
	case VHOST_VDPA_GET_CONFIG:
		r = vhost_vdpa_get_config(v, argp);
		break;
	case VHOST_VDPA_SET_CONFIG:
		r = vhost_vdpa_set_config(v, argp);
		break;
	case VHOST_GET_FEATURES:
		r = vhost_vdpa_get_features(v, argp);
		break;
	case VHOST_SET_FEATURES:
		r = vhost_vdpa_set_features(v, argp);
		break;
	case VHOST_VDPA_GET_VRING_NUM:
		r = vhost_vdpa_get_vring_num(v, argp);
		break;
	case VHOST_SET_LOG_BASE:
	case VHOST_SET_LOG_FD:
		r = -ENOIOCTLCMD;
		break;
	default:
		r = vhost_dev_ioctl(&v->vdev, cmd, argp);
		if (r == -ENOIOCTLCMD)
			r = vhost_vdpa_vring_ioctl(v, cmd, argp);
		break;
	}

	mutex_unlock(&d->mutex);
	return r;
}

static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v, u64 start, u64 last)
{
	struct vhost_dev *dev = &v->vdev;
	struct vhost_iotlb *iotlb = dev->iotlb;
	struct vhost_iotlb_map *map;
	struct page *page;
	unsigned long pfn, pinned;

	while ((map = vhost_iotlb_itree_first(iotlb, start, last)) != NULL) {
		pinned = map->size >> PAGE_SHIFT;
		for (pfn = map->addr >> PAGE_SHIFT;
		     pinned > 0; pfn++, pinned--) {
			page = pfn_to_page(pfn);
			if (map->perm & VHOST_ACCESS_WO)
				set_page_dirty_lock(page);
			unpin_user_page(page);
		}
		atomic64_sub(map->size >> PAGE_SHIFT, &dev->mm->pinned_vm);
		vhost_iotlb_map_free(iotlb, map);
	}
}

static void vhost_vdpa_iotlb_free(struct vhost_vdpa *v)
{
	struct vhost_dev *dev = &v->vdev;

	vhost_vdpa_iotlb_unmap(v, 0ULL, 0ULL - 1);
	kfree(dev->iotlb);
	dev->iotlb = NULL;
}

static int perm_to_iommu_flags(u32 perm)
{
	int flags = 0;

	switch (perm) {
	case VHOST_ACCESS_WO:
		flags |= IOMMU_WRITE;
		break;
	case VHOST_ACCESS_RO:
		flags |= IOMMU_READ;
		break;
	case VHOST_ACCESS_RW:
		flags |= (IOMMU_WRITE | IOMMU_READ);
		break;
	default:
		WARN(1, "invalidate vhost IOTLB permission\n");
		break;
	}

	return flags | IOMMU_CACHE;
}

static int vhost_vdpa_map(struct vhost_vdpa *v,
			  u64 iova, u64 size, u64 pa, u32 perm)
{
	struct vhost_dev *dev = &v->vdev;
	struct vdpa_device *vdpa = v->vdpa;
	const struct vdpa_config_ops *ops = vdpa->config;
	int r = 0;

	r = vhost_iotlb_add_range(dev->iotlb, iova, iova + size - 1,
				  pa, perm);
	if (r)
		return r;

	if (ops->dma_map)
		r = ops->dma_map(vdpa, iova, size, pa, perm);
	else if (ops->set_map)
		r = ops->set_map(vdpa, dev->iotlb);
	else
		r = iommu_map(v->domain, iova, pa, size,
			      perm_to_iommu_flags(perm));

	return r;
}

static void vhost_vdpa_unmap(struct vhost_vdpa *v, u64 iova, u64 size)
{
	struct vhost_dev *dev = &v->vdev;
	struct vdpa_device *vdpa = v->vdpa;
	const struct vdpa_config_ops *ops = vdpa->config;

	vhost_vdpa_iotlb_unmap(v, iova, iova + size - 1);

	if (ops->dma_map)
		ops->dma_unmap(vdpa, iova, size);
	else if (ops->set_map)
		ops->set_map(vdpa, dev->iotlb);
	else
		iommu_unmap(v->domain, iova, size);
}

static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v,
					   struct vhost_iotlb_msg *msg)
{
	struct vhost_dev *dev = &v->vdev;
	struct vhost_iotlb *iotlb = dev->iotlb;
	struct page **page_list;
	unsigned long list_size = PAGE_SIZE / sizeof(struct page *);
	unsigned int gup_flags = FOLL_LONGTERM;
	unsigned long npages, cur_base, map_pfn, last_pfn = 0;
	unsigned long locked, lock_limit, pinned, i;
	u64 iova = msg->iova;
	int ret = 0;

	if (vhost_iotlb_itree_first(iotlb, msg->iova,
				    msg->iova + msg->size - 1))
		return -EEXIST;

	page_list = (struct page **) __get_free_page(GFP_KERNEL);
	if (!page_list)
		return -ENOMEM;

	if (msg->perm & VHOST_ACCESS_WO)
		gup_flags |= FOLL_WRITE;

	npages = PAGE_ALIGN(msg->size + (iova & ~PAGE_MASK)) >> PAGE_SHIFT;
	if (!npages)
		return -EINVAL;

	down_read(&dev->mm->mmap_sem);

	locked = atomic64_add_return(npages, &dev->mm->pinned_vm);
	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;

	if (locked > lock_limit) {
		ret = -ENOMEM;
		goto out;
	}

	cur_base = msg->uaddr & PAGE_MASK;
	iova &= PAGE_MASK;

	while (npages) {
		pinned = min_t(unsigned long, npages, list_size);
		ret = pin_user_pages(cur_base, pinned,
				     gup_flags, page_list, NULL);
		if (ret != pinned)
			goto out;

		if (!last_pfn)
			map_pfn = page_to_pfn(page_list[0]);

		for (i = 0; i < ret; i++) {
			unsigned long this_pfn = page_to_pfn(page_list[i]);
			u64 csize;

			if (last_pfn && (this_pfn != last_pfn + 1)) {
				/* Pin a contiguous chunk of memory */
				csize = (last_pfn - map_pfn + 1) << PAGE_SHIFT;
				if (vhost_vdpa_map(v, iova, csize,
						   map_pfn << PAGE_SHIFT,
						   msg->perm))
					goto out;
				map_pfn = this_pfn;
				iova += csize;
			}

			last_pfn = this_pfn;
		}

		cur_base += ret << PAGE_SHIFT;
		npages -= ret;
	}

	/* Pin the rest chunk */
	ret = vhost_vdpa_map(v, iova, (last_pfn - map_pfn + 1) << PAGE_SHIFT,
			     map_pfn << PAGE_SHIFT, msg->perm);
out:
	if (ret) {
		vhost_vdpa_unmap(v, msg->iova, msg->size);
		atomic64_sub(npages, &dev->mm->pinned_vm);
	}
	up_read(&dev->mm->mmap_sem);
	free_page((unsigned long)page_list);
	return ret;
}

static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev,
					struct vhost_iotlb_msg *msg)
{
	struct vhost_vdpa *v = container_of(dev, struct vhost_vdpa, vdev);
	int r = 0;

	r = vhost_dev_check_owner(dev);
	if (r)
		return r;

	switch (msg->type) {
	case VHOST_IOTLB_UPDATE:
		r = vhost_vdpa_process_iotlb_update(v, msg);
		break;
	case VHOST_IOTLB_INVALIDATE:
		vhost_vdpa_unmap(v, msg->iova, msg->size);
		break;
	default:
		r = -EINVAL;
		break;
	}

	return r;
}

static ssize_t vhost_vdpa_chr_write_iter(struct kiocb *iocb,
					 struct iov_iter *from)
{
	struct file *file = iocb->ki_filp;
	struct vhost_vdpa *v = file->private_data;
	struct vhost_dev *dev = &v->vdev;

	return vhost_chr_write_iter(dev, from);
}

static int vhost_vdpa_alloc_domain(struct vhost_vdpa *v)
{
	struct vdpa_device *vdpa = v->vdpa;
	const struct vdpa_config_ops *ops = vdpa->config;
	struct device *dma_dev = vdpa_get_dma_dev(vdpa);
	struct bus_type *bus;
	int ret;

	/* Device want to do DMA by itself */
	if (ops->set_map || ops->dma_map)
		return 0;

	bus = dma_dev->bus;
	if (!bus)
		return -EFAULT;

	if (!iommu_capable(bus, IOMMU_CAP_CACHE_COHERENCY))
		return -ENOTSUPP;

	v->domain = iommu_domain_alloc(bus);
	if (!v->domain)
		return -EIO;

	ret = iommu_attach_device(v->domain, dma_dev);
	if (ret)
		goto err_attach;

	return 0;

err_attach:
	iommu_domain_free(v->domain);
	return ret;
}

static void vhost_vdpa_free_domain(struct vhost_vdpa *v)
{
	struct vdpa_device *vdpa = v->vdpa;
	struct device *dma_dev = vdpa_get_dma_dev(vdpa);

	if (v->domain) {
		iommu_detach_device(v->domain, dma_dev);
		iommu_domain_free(v->domain);
	}

	v->domain = NULL;
}

static int vhost_vdpa_open(struct inode *inode, struct file *filep)
{
	struct vhost_vdpa *v;
	struct vhost_dev *dev;
	struct vhost_virtqueue **vqs;
	int nvqs, i, r, opened;

	v = container_of(inode->i_cdev, struct vhost_vdpa, cdev);

	opened = atomic_cmpxchg(&v->opened, 0, 1);
	if (opened)
		return -EBUSY;

	nvqs = v->nvqs;
	vhost_vdpa_reset(v);

	vqs = kmalloc_array(nvqs, sizeof(*vqs), GFP_KERNEL);
	if (!vqs) {
		r = -ENOMEM;
		goto err;
	}

	dev = &v->vdev;
	for (i = 0; i < nvqs; i++) {
		vqs[i] = &v->vqs[i];
		vqs[i]->handle_kick = handle_vq_kick;
	}
	vhost_dev_init(dev, vqs, nvqs, 0, 0, 0,
		       vhost_vdpa_process_iotlb_msg);

	dev->iotlb = vhost_iotlb_alloc(0, 0);
	if (!dev->iotlb) {
		r = -ENOMEM;
		goto err_init_iotlb;
	}

	r = vhost_vdpa_alloc_domain(v);
	if (r)
		goto err_init_iotlb;

	filep->private_data = v;

	return 0;

err_init_iotlb:
	vhost_dev_cleanup(&v->vdev);
err:
	atomic_dec(&v->opened);
	return r;
}

static int vhost_vdpa_release(struct inode *inode, struct file *filep)
{
	struct vhost_vdpa *v = filep->private_data;
	struct vhost_dev *d = &v->vdev;

	mutex_lock(&d->mutex);
	filep->private_data = NULL;
	vhost_vdpa_reset(v);
	vhost_dev_stop(&v->vdev);
	vhost_vdpa_iotlb_free(v);
	vhost_vdpa_free_domain(v);
	vhost_dev_cleanup(&v->vdev);
	kfree(v->vdev.vqs);
	mutex_unlock(&d->mutex);

	atomic_dec(&v->opened);
	complete(&v->completion);

	return 0;
}

static const struct file_operations vhost_vdpa_fops = {
	.owner		= THIS_MODULE,
	.open		= vhost_vdpa_open,
	.release	= vhost_vdpa_release,
	.write_iter	= vhost_vdpa_chr_write_iter,
	.unlocked_ioctl	= vhost_vdpa_unlocked_ioctl,
	.compat_ioctl	= compat_ptr_ioctl,
};

static void vhost_vdpa_release_dev(struct device *device)
{
	struct vhost_vdpa *v =
	       container_of(device, struct vhost_vdpa, dev);

	ida_simple_remove(&vhost_vdpa_ida, v->minor);
	kfree(v->vqs);
	kfree(v);
}

static int vhost_vdpa_probe(struct vdpa_device *vdpa)
{
	const struct vdpa_config_ops *ops = vdpa->config;
	struct vhost_vdpa *v;
	int minor, nvqs = VHOST_VDPA_VQ_MAX;
	int r;

	/* Currently, we only accept the network devices. */
	if (ops->get_device_id(vdpa) != VIRTIO_ID_NET)
		return -ENOTSUPP;

	v = kzalloc(sizeof(*v), GFP_KERNEL | __GFP_RETRY_MAYFAIL);
	if (!v)
		return -ENOMEM;

	minor = ida_simple_get(&vhost_vdpa_ida, 0,
			       VHOST_VDPA_DEV_MAX, GFP_KERNEL);
	if (minor < 0) {
		kfree(v);
		return minor;
	}

	atomic_set(&v->opened, 0);
	v->minor = minor;
	v->vdpa = vdpa;
	v->nvqs = nvqs;
	v->virtio_id = ops->get_device_id(vdpa);

	device_initialize(&v->dev);
	v->dev.release = vhost_vdpa_release_dev;
	v->dev.parent = &vdpa->dev;
	v->dev.devt = MKDEV(MAJOR(vhost_vdpa_major), minor);
	v->vqs = kmalloc_array(nvqs, sizeof(struct vhost_virtqueue),
			       GFP_KERNEL);
	if (!v->vqs) {
		r = -ENOMEM;
		goto err;
	}

	r = dev_set_name(&v->dev, "vhost-vdpa-%u", minor);
	if (r)
		goto err;

	cdev_init(&v->cdev, &vhost_vdpa_fops);
	v->cdev.owner = THIS_MODULE;

	r = cdev_device_add(&v->cdev, &v->dev);
	if (r)
		goto err;

	init_completion(&v->completion);
	vdpa_set_drvdata(vdpa, v);

	return 0;

err:
	put_device(&v->dev);
	return r;
}

static void vhost_vdpa_remove(struct vdpa_device *vdpa)
{
	struct vhost_vdpa *v = vdpa_get_drvdata(vdpa);
	int opened;

	cdev_device_del(&v->cdev, &v->dev);

	do {
		opened = atomic_cmpxchg(&v->opened, 0, 1);
		if (!opened)
			break;
		wait_for_completion(&v->completion);
	} while (1);

	put_device(&v->dev);
}

static struct vdpa_driver vhost_vdpa_driver = {
	.driver = {
		.name	= "vhost_vdpa",
	},
	.probe	= vhost_vdpa_probe,
	.remove	= vhost_vdpa_remove,
};

static int __init vhost_vdpa_init(void)
{
	int r;

	r = alloc_chrdev_region(&vhost_vdpa_major, 0, VHOST_VDPA_DEV_MAX,
				"vhost-vdpa");
	if (r)
		goto err_alloc_chrdev;

	r = vdpa_register_driver(&vhost_vdpa_driver);
	if (r)
		goto err_vdpa_register_driver;

	return 0;

err_vdpa_register_driver:
	unregister_chrdev_region(vhost_vdpa_major, VHOST_VDPA_DEV_MAX);
err_alloc_chrdev:
	return r;
}
module_init(vhost_vdpa_init);

static void __exit vhost_vdpa_exit(void)
{
	vdpa_unregister_driver(&vhost_vdpa_driver);
	unregister_chrdev_region(vhost_vdpa_major, VHOST_VDPA_DEV_MAX);
}
module_exit(vhost_vdpa_exit);

MODULE_VERSION("0.0.1");
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Intel Corporation");
MODULE_DESCRIPTION("vDPA-based vhost backend for virtio");