summaryrefslogtreecommitdiffstats
path: root/drivers/virtio/virtio_pci_modern.c
blob: 3d6ae5a5e252e069a66c342cd745802e09247bf5 (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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Virtio PCI driver - modern (virtio 1.0) device support
 *
 * This module allows virtio devices to be used over a virtual PCI device.
 * This can be used with QEMU based VMMs like KVM or Xen.
 *
 * Copyright IBM Corp. 2007
 * Copyright Red Hat, Inc. 2014
 *
 * Authors:
 *  Anthony Liguori  <aliguori@us.ibm.com>
 *  Rusty Russell <rusty@rustcorp.com.au>
 *  Michael S. Tsirkin <mst@redhat.com>
 */

#include <linux/delay.h>
#define VIRTIO_PCI_NO_LEGACY
#define VIRTIO_RING_NO_LEGACY
#include "virtio_pci_common.h"

/*
 * Type-safe wrappers for io accesses.
 * Use these to enforce at compile time the following spec requirement:
 *
 * The driver MUST access each field using the “natural” access
 * method, i.e. 32-bit accesses for 32-bit fields, 16-bit accesses
 * for 16-bit fields and 8-bit accesses for 8-bit fields.
 */
static inline u8 vp_ioread8(const u8 __iomem *addr)
{
	return ioread8(addr);
}
static inline u16 vp_ioread16 (const __le16 __iomem *addr)
{
	return ioread16(addr);
}

static inline u32 vp_ioread32(const __le32 __iomem *addr)
{
	return ioread32(addr);
}

static inline void vp_iowrite8(u8 value, u8 __iomem *addr)
{
	iowrite8(value, addr);
}

static inline void vp_iowrite16(u16 value, __le16 __iomem *addr)
{
	iowrite16(value, addr);
}

static inline void vp_iowrite32(u32 value, __le32 __iomem *addr)
{
	iowrite32(value, addr);
}

static void vp_iowrite64_twopart(u64 val,
				 __le32 __iomem *lo, __le32 __iomem *hi)
{
	vp_iowrite32((u32)val, lo);
	vp_iowrite32(val >> 32, hi);
}

static void __iomem *map_capability(struct pci_dev *dev, int off,
				    size_t minlen,
				    u32 align,
				    u32 start, u32 size,
				    size_t *len)
{
	u8 bar;
	u32 offset, length;
	void __iomem *p;

	pci_read_config_byte(dev, off + offsetof(struct virtio_pci_cap,
						 bar),
			     &bar);
	pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, offset),
			     &offset);
	pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, length),
			      &length);

	if (length <= start) {
		dev_err(&dev->dev,
			"virtio_pci: bad capability len %u (>%u expected)\n",
			length, start);
		return NULL;
	}

	if (length - start < minlen) {
		dev_err(&dev->dev,
			"virtio_pci: bad capability len %u (>=%zu expected)\n",
			length, minlen);
		return NULL;
	}

	length -= start;

	if (start + offset < offset) {
		dev_err(&dev->dev,
			"virtio_pci: map wrap-around %u+%u\n",
			start, offset);
		return NULL;
	}

	offset += start;

	if (offset & (align - 1)) {
		dev_err(&dev->dev,
			"virtio_pci: offset %u not aligned to %u\n",
			offset, align);
		return NULL;
	}

	if (length > size)
		length = size;

	if (len)
		*len = length;

	if (minlen + offset < minlen ||
	    minlen + offset > pci_resource_len(dev, bar)) {
		dev_err(&dev->dev,
			"virtio_pci: map virtio %zu@%u "
			"out of range on bar %i length %lu\n",
			minlen, offset,
			bar, (unsigned long)pci_resource_len(dev, bar));
		return NULL;
	}

	p = pci_iomap_range(dev, bar, offset, length);
	if (!p)
		dev_err(&dev->dev,
			"virtio_pci: unable to map virtio %u@%u on bar %i\n",
			length, offset, bar);
	return p;
}

/* virtio config->get_features() implementation */
static u64 vp_get_features(struct virtio_device *vdev)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	u64 features;

	vp_iowrite32(0, &vp_dev->common->device_feature_select);
	features = vp_ioread32(&vp_dev->common->device_feature);
	vp_iowrite32(1, &vp_dev->common->device_feature_select);
	features |= ((u64)vp_ioread32(&vp_dev->common->device_feature) << 32);

	return features;
}

static void vp_transport_features(struct virtio_device *vdev, u64 features)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	struct pci_dev *pci_dev = vp_dev->pci_dev;

	if ((features & BIT_ULL(VIRTIO_F_SR_IOV)) &&
			pci_find_ext_capability(pci_dev, PCI_EXT_CAP_ID_SRIOV))
		__virtio_set_bit(vdev, VIRTIO_F_SR_IOV);
}

/* virtio config->finalize_features() implementation */
static int vp_finalize_features(struct virtio_device *vdev)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	u64 features = vdev->features;

	/* Give virtio_ring a chance to accept features. */
	vring_transport_features(vdev);

	/* Give virtio_pci a chance to accept features. */
	vp_transport_features(vdev, features);

	if (!__virtio_test_bit(vdev, VIRTIO_F_VERSION_1)) {
		dev_err(&vdev->dev, "virtio: device uses modern interface "
			"but does not have VIRTIO_F_VERSION_1\n");
		return -EINVAL;
	}

	vp_iowrite32(0, &vp_dev->common->guest_feature_select);
	vp_iowrite32((u32)vdev->features, &vp_dev->common->guest_feature);
	vp_iowrite32(1, &vp_dev->common->guest_feature_select);
	vp_iowrite32(vdev->features >> 32, &vp_dev->common->guest_feature);

	return 0;
}

/* virtio config->get() implementation */
static void vp_get(struct virtio_device *vdev, unsigned offset,
		   void *buf, unsigned len)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	u8 b;
	__le16 w;
	__le32 l;

	BUG_ON(offset + len > vp_dev->device_len);

	switch (len) {
	case 1:
		b = ioread8(vp_dev->device + offset);
		memcpy(buf, &b, sizeof b);
		break;
	case 2:
		w = cpu_to_le16(ioread16(vp_dev->device + offset));
		memcpy(buf, &w, sizeof w);
		break;
	case 4:
		l = cpu_to_le32(ioread32(vp_dev->device + offset));
		memcpy(buf, &l, sizeof l);
		break;
	case 8:
		l = cpu_to_le32(ioread32(vp_dev->device + offset));
		memcpy(buf, &l, sizeof l);
		l = cpu_to_le32(ioread32(vp_dev->device + offset + sizeof l));
		memcpy(buf + sizeof l, &l, sizeof l);
		break;
	default:
		BUG();
	}
}

/* the config->set() implementation.  it's symmetric to the config->get()
 * implementation */
static void vp_set(struct virtio_device *vdev, unsigned offset,
		   const void *buf, unsigned len)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	u8 b;
	__le16 w;
	__le32 l;

	BUG_ON(offset + len > vp_dev->device_len);

	switch (len) {
	case 1:
		memcpy(&b, buf, sizeof b);
		iowrite8(b, vp_dev->device + offset);
		break;
	case 2:
		memcpy(&w, buf, sizeof w);
		iowrite16(le16_to_cpu(w), vp_dev->device + offset);
		break;
	case 4:
		memcpy(&l, buf, sizeof l);
		iowrite32(le32_to_cpu(l), vp_dev->device + offset);
		break;
	case 8:
		memcpy(&l, buf, sizeof l);
		iowrite32(le32_to_cpu(l), vp_dev->device + offset);
		memcpy(&l, buf + sizeof l, sizeof l);
		iowrite32(le32_to_cpu(l), vp_dev->device + offset + sizeof l);
		break;
	default:
		BUG();
	}
}

static u32 vp_generation(struct virtio_device *vdev)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	return vp_ioread8(&vp_dev->common->config_generation);
}

/* config->{get,set}_status() implementations */
static u8 vp_get_status(struct virtio_device *vdev)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	return vp_ioread8(&vp_dev->common->device_status);
}

static void vp_set_status(struct virtio_device *vdev, u8 status)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	/* We should never be setting status to 0. */
	BUG_ON(status == 0);
	vp_iowrite8(status, &vp_dev->common->device_status);
}

static void vp_reset(struct virtio_device *vdev)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	/* 0 status means a reset. */
	vp_iowrite8(0, &vp_dev->common->device_status);
	/* After writing 0 to device_status, the driver MUST wait for a read of
	 * device_status to return 0 before reinitializing the device.
	 * This will flush out the status write, and flush in device writes,
	 * including MSI-X interrupts, if any.
	 */
	while (vp_ioread8(&vp_dev->common->device_status))
		msleep(1);
	/* Flush pending VQ/configuration callbacks. */
	vp_synchronize_vectors(vdev);
}

static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
{
	/* Setup the vector used for configuration events */
	vp_iowrite16(vector, &vp_dev->common->msix_config);
	/* Verify we had enough resources to assign the vector */
	/* Will also flush the write out to device */
	return vp_ioread16(&vp_dev->common->msix_config);
}

static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
				  struct virtio_pci_vq_info *info,
				  unsigned index,
				  void (*callback)(struct virtqueue *vq),
				  const char *name,
				  bool ctx,
				  u16 msix_vec)
{
	struct virtio_pci_common_cfg __iomem *cfg = vp_dev->common;
	struct virtqueue *vq;
	u16 num, off;
	int err;

	if (index >= vp_ioread16(&cfg->num_queues))
		return ERR_PTR(-ENOENT);

	/* Select the queue we're interested in */
	vp_iowrite16(index, &cfg->queue_select);

	/* Check if queue is either not available or already active. */
	num = vp_ioread16(&cfg->queue_size);
	if (!num || vp_ioread16(&cfg->queue_enable))
		return ERR_PTR(-ENOENT);

	if (num & (num - 1)) {
		dev_warn(&vp_dev->pci_dev->dev, "bad queue size %u", num);
		return ERR_PTR(-EINVAL);
	}

	/* get offset of notification word for this vq */
	off = vp_ioread16(&cfg->queue_notify_off);

	info->msix_vector = msix_vec;

	/* create the vring */
	vq = vring_create_virtqueue(index, num,
				    SMP_CACHE_BYTES, &vp_dev->vdev,
				    true, true, ctx,
				    vp_notify, callback, name);
	if (!vq)
		return ERR_PTR(-ENOMEM);

	/* activate the queue */
	vp_iowrite16(virtqueue_get_vring_size(vq), &cfg->queue_size);
	vp_iowrite64_twopart(virtqueue_get_desc_addr(vq),
			     &cfg->queue_desc_lo, &cfg->queue_desc_hi);
	vp_iowrite64_twopart(virtqueue_get_avail_addr(vq),
			     &cfg->queue_avail_lo, &cfg->queue_avail_hi);
	vp_iowrite64_twopart(virtqueue_get_used_addr(vq),
			     &cfg->queue_used_lo, &cfg->queue_used_hi);

	if (vp_dev->notify_base) {
		/* offset should not wrap */
		if ((u64)off * vp_dev->notify_offset_multiplier + 2
		    > vp_dev->notify_len) {
			dev_warn(&vp_dev->pci_dev->dev,
				 "bad notification offset %u (x %u) "
				 "for queue %u > %zd",
				 off, vp_dev->notify_offset_multiplier,
				 index, vp_dev->notify_len);
			err = -EINVAL;
			goto err_map_notify;
		}
		vq->priv = (void __force *)vp_dev->notify_base +
			off * vp_dev->notify_offset_multiplier;
	} else {
		vq->priv = (void __force *)map_capability(vp_dev->pci_dev,
					  vp_dev->notify_map_cap, 2, 2,
					  off * vp_dev->notify_offset_multiplier, 2,
					  NULL);
	}

	if (!vq->priv) {
		err = -ENOMEM;
		goto err_map_notify;
	}

	if (msix_vec != VIRTIO_MSI_NO_VECTOR) {
		vp_iowrite16(msix_vec, &cfg->queue_msix_vector);
		msix_vec = vp_ioread16(&cfg->queue_msix_vector);
		if (msix_vec == VIRTIO_MSI_NO_VECTOR) {
			err = -EBUSY;
			goto err_assign_vector;
		}
	}

	return vq;

err_assign_vector:
	if (!vp_dev->notify_base)
		pci_iounmap(vp_dev->pci_dev, (void __iomem __force *)vq->priv);
err_map_notify:
	vring_del_virtqueue(vq);
	return ERR_PTR(err);
}

static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned nvqs,
			      struct virtqueue *vqs[],
			      vq_callback_t *callbacks[],
			      const char * const names[], const bool *ctx,
			      struct irq_affinity *desc)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	struct virtqueue *vq;
	int rc = vp_find_vqs(vdev, nvqs, vqs, callbacks, names, ctx, desc);

	if (rc)
		return rc;

	/* Select and activate all queues. Has to be done last: once we do
	 * this, there's no way to go back except reset.
	 */
	list_for_each_entry(vq, &vdev->vqs, list) {
		vp_iowrite16(vq->index, &vp_dev->common->queue_select);
		vp_iowrite16(1, &vp_dev->common->queue_enable);
	}

	return 0;
}

static void del_vq(struct virtio_pci_vq_info *info)
{
	struct virtqueue *vq = info->vq;
	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);

	vp_iowrite16(vq->index, &vp_dev->common->queue_select);

	if (vp_dev->msix_enabled) {
		vp_iowrite16(VIRTIO_MSI_NO_VECTOR,
			     &vp_dev->common->queue_msix_vector);
		/* Flush the write out to device */
		vp_ioread16(&vp_dev->common->queue_msix_vector);
	}

	if (!vp_dev->notify_base)
		pci_iounmap(vp_dev->pci_dev, (void __force __iomem *)vq->priv);

	vring_del_virtqueue(vq);
}

static int virtio_pci_find_shm_cap(struct pci_dev *dev, u8 required_id,
				   u8 *bar, u64 *offset, u64 *len)
{
	int pos;

	for (pos = pci_find_capability(dev, PCI_CAP_ID_VNDR); pos > 0;
	     pos = pci_find_next_capability(dev, pos, PCI_CAP_ID_VNDR)) {
		u8 type, cap_len, id;
		u32 tmp32;
		u64 res_offset, res_length;

		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
							 cfg_type), &type);
		if (type != VIRTIO_PCI_CAP_SHARED_MEMORY_CFG)
			continue;

		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
							 cap_len), &cap_len);
		if (cap_len != sizeof(struct virtio_pci_cap64)) {
			dev_err(&dev->dev, "%s: shm cap with bad size offset:"
				" %d size: %d\n", __func__, pos, cap_len);
			continue;
		}

		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
							 id), &id);
		if (id != required_id)
			continue;

		/* Type, and ID match, looks good */
		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
							 bar), bar);

		/* Read the lower 32bit of length and offset */
		pci_read_config_dword(dev, pos + offsetof(struct virtio_pci_cap,
							  offset), &tmp32);
		res_offset = tmp32;
		pci_read_config_dword(dev, pos + offsetof(struct virtio_pci_cap,
							  length), &tmp32);
		res_length = tmp32;

		/* and now the top half */
		pci_read_config_dword(dev,
				      pos + offsetof(struct virtio_pci_cap64,
						     offset_hi), &tmp32);
		res_offset |= ((u64)tmp32) << 32;
		pci_read_config_dword(dev,
				      pos + offsetof(struct virtio_pci_cap64,
						     length_hi), &tmp32);
		res_length |= ((u64)tmp32) << 32;

		*offset = res_offset;
		*len = res_length;

		return pos;
	}
	return 0;
}

static bool vp_get_shm_region(struct virtio_device *vdev,
			      struct virtio_shm_region *region, u8 id)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	struct pci_dev *pci_dev = vp_dev->pci_dev;
	u8 bar;
	u64 offset, len;
	phys_addr_t phys_addr;
	size_t bar_len;

	if (!virtio_pci_find_shm_cap(pci_dev, id, &bar, &offset, &len))
		return false;

	phys_addr = pci_resource_start(pci_dev, bar);
	bar_len = pci_resource_len(pci_dev, bar);

	if ((offset + len) < offset) {
		dev_err(&pci_dev->dev, "%s: cap offset+len overflow detected\n",
			__func__);
		return false;
	}

	if (offset + len > bar_len) {
		dev_err(&pci_dev->dev, "%s: bar shorter than cap offset+len\n",
			__func__);
		return false;
	}

	region->len = len;
	region->addr = (u64) phys_addr + offset;

	return true;
}

static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
	.get		= NULL,
	.set		= NULL,
	.generation	= vp_generation,
	.get_status	= vp_get_status,
	.set_status	= vp_set_status,
	.reset		= vp_reset,
	.find_vqs	= vp_modern_find_vqs,
	.del_vqs	= vp_del_vqs,
	.get_features	= vp_get_features,
	.finalize_features = vp_finalize_features,
	.bus_name	= vp_bus_name,
	.set_vq_affinity = vp_set_vq_affinity,
	.get_vq_affinity = vp_get_vq_affinity,
	.get_shm_region  = vp_get_shm_region,
};

static const struct virtio_config_ops virtio_pci_config_ops = {
	.get		= vp_get,
	.set		= vp_set,
	.generation	= vp_generation,
	.get_status	= vp_get_status,
	.set_status	= vp_set_status,
	.reset		= vp_reset,
	.find_vqs	= vp_modern_find_vqs,
	.del_vqs	= vp_del_vqs,
	.get_features	= vp_get_features,
	.finalize_features = vp_finalize_features,
	.bus_name	= vp_bus_name,
	.set_vq_affinity = vp_set_vq_affinity,
	.get_vq_affinity = vp_get_vq_affinity,
	.get_shm_region  = vp_get_shm_region,
};

/**
 * virtio_pci_find_capability - walk capabilities to find device info.
 * @dev: the pci device
 * @cfg_type: the VIRTIO_PCI_CAP_* value we seek
 * @ioresource_types: IORESOURCE_MEM and/or IORESOURCE_IO.
 * @bars: the bitmask of BARs
 *
 * Returns offset of the capability, or 0.
 */
static inline int virtio_pci_find_capability(struct pci_dev *dev, u8 cfg_type,
					     u32 ioresource_types, int *bars)
{
	int pos;

	for (pos = pci_find_capability(dev, PCI_CAP_ID_VNDR);
	     pos > 0;
	     pos = pci_find_next_capability(dev, pos, PCI_CAP_ID_VNDR)) {
		u8 type, bar;
		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
							 cfg_type),
				     &type);
		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
							 bar),
				     &bar);

		/* Ignore structures with reserved BAR values */
		if (bar > 0x5)
			continue;

		if (type == cfg_type) {
			if (pci_resource_len(dev, bar) &&
			    pci_resource_flags(dev, bar) & ioresource_types) {
				*bars |= (1 << bar);
				return pos;
			}
		}
	}
	return 0;
}

/* This is part of the ABI.  Don't screw with it. */
static inline void check_offsets(void)
{
	/* Note: disk space was harmed in compilation of this function. */
	BUILD_BUG_ON(VIRTIO_PCI_CAP_VNDR !=
		     offsetof(struct virtio_pci_cap, cap_vndr));
	BUILD_BUG_ON(VIRTIO_PCI_CAP_NEXT !=
		     offsetof(struct virtio_pci_cap, cap_next));
	BUILD_BUG_ON(VIRTIO_PCI_CAP_LEN !=
		     offsetof(struct virtio_pci_cap, cap_len));
	BUILD_BUG_ON(VIRTIO_PCI_CAP_CFG_TYPE !=
		     offsetof(struct virtio_pci_cap, cfg_type));
	BUILD_BUG_ON(VIRTIO_PCI_CAP_BAR !=
		     offsetof(struct virtio_pci_cap, bar));
	BUILD_BUG_ON(VIRTIO_PCI_CAP_OFFSET !=
		     offsetof(struct virtio_pci_cap, offset));
	BUILD_BUG_ON(VIRTIO_PCI_CAP_LENGTH !=
		     offsetof(struct virtio_pci_cap, length));
	BUILD_BUG_ON(VIRTIO_PCI_NOTIFY_CAP_MULT !=
		     offsetof(struct virtio_pci_notify_cap,
			      notify_off_multiplier));
	BUILD_BUG_ON(VIRTIO_PCI_COMMON_DFSELECT !=
		     offsetof(struct virtio_pci_common_cfg,
			      device_feature_select));
	BUILD_BUG_ON(VIRTIO_PCI_COMMON_DF !=
		     offsetof(struct virtio_pci_common_cfg, device_feature));
	BUILD_BUG_ON(VIRTIO_PCI_COMMON_GFSELECT !=
		     offsetof(struct virtio_pci_common_cfg,
			      guest_feature_select));
	BUILD_BUG_ON(VIRTIO_PCI_COMMON_GF !=
		     offsetof(struct virtio_pci_common_cfg, guest_feature));
	BUILD_BUG_ON(VIRTIO_PCI_COMMON_MSIX !=
		     offsetof(struct virtio_pci_common_cfg, msix_config));
	BUILD_BUG_ON(VIRTIO_PCI_COMMON_NUMQ !=
		     offsetof(struct virtio_pci_common_cfg, num_queues));
	BUILD_BUG_ON(VIRTIO_PCI_COMMON_STATUS !=
		     offsetof(struct virtio_pci_common_cfg, device_status));
	BUILD_BUG_ON(VIRTIO_PCI_COMMON_CFGGENERATION !=
		     offsetof(struct virtio_pci_common_cfg, config_generation));
	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SELECT !=
		     offsetof(struct virtio_pci_common_cfg, queue_select));
	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SIZE !=
		     offsetof(struct virtio_pci_common_cfg, queue_size));
	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_MSIX !=
		     offsetof(struct virtio_pci_common_cfg, queue_msix_vector));
	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_ENABLE !=
		     offsetof(struct virtio_pci_common_cfg, queue_enable));
	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_NOFF !=
		     offsetof(struct virtio_pci_common_cfg, queue_notify_off));
	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCLO !=
		     offsetof(struct virtio_pci_common_cfg, queue_desc_lo));
	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCHI !=
		     offsetof(struct virtio_pci_common_cfg, queue_desc_hi));
	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILLO !=
		     offsetof(struct virtio_pci_common_cfg, queue_avail_lo));
	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILHI !=
		     offsetof(struct virtio_pci_common_cfg, queue_avail_hi));
	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDLO !=
		     offsetof(struct virtio_pci_common_cfg, queue_used_lo));
	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDHI !=
		     offsetof(struct virtio_pci_common_cfg, queue_used_hi));
}

/* the PCI probing function */
int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
{
	struct pci_dev *pci_dev = vp_dev->pci_dev;
	int err, common, isr, notify, device;
	u32 notify_length;
	u32 notify_offset;

	check_offsets();

	/* We only own devices >= 0x1000 and <= 0x107f: leave the rest. */
	if (pci_dev->device < 0x1000 || pci_dev->device > 0x107f)
		return -ENODEV;

	if (pci_dev->device < 0x1040) {
		/* Transitional devices: use the PCI subsystem device id as
		 * virtio device id, same as legacy driver always did.
		 */
		vp_dev->vdev.id.device = pci_dev->subsystem_device;
	} else {
		/* Modern devices: simply use PCI device id, but start from 0x1040. */
		vp_dev->vdev.id.device = pci_dev->device - 0x1040;
	}
	vp_dev->vdev.id.vendor = pci_dev->subsystem_vendor;

	/* check for a common config: if not, use legacy mode (bar 0). */
	common = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_COMMON_CFG,
					    IORESOURCE_IO | IORESOURCE_MEM,
					    &vp_dev->modern_bars);
	if (!common) {
		dev_info(&pci_dev->dev,
			 "virtio_pci: leaving for legacy driver\n");
		return -ENODEV;
	}

	/* If common is there, these should be too... */
	isr = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_ISR_CFG,
					 IORESOURCE_IO | IORESOURCE_MEM,
					 &vp_dev->modern_bars);
	notify = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_NOTIFY_CFG,
					    IORESOURCE_IO | IORESOURCE_MEM,
					    &vp_dev->modern_bars);
	if (!isr || !notify) {
		dev_err(&pci_dev->dev,
			"virtio_pci: missing capabilities %i/%i/%i\n",
			common, isr, notify);
		return -EINVAL;
	}

	err = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(64));
	if (err)
		err = dma_set_mask_and_coherent(&pci_dev->dev,
						DMA_BIT_MASK(32));
	if (err)
		dev_warn(&pci_dev->dev, "Failed to enable 64-bit or 32-bit DMA.  Trying to continue, but this might not work.\n");

	/* Device capability is only mandatory for devices that have
	 * device-specific configuration.
	 */
	device = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_DEVICE_CFG,
					    IORESOURCE_IO | IORESOURCE_MEM,
					    &vp_dev->modern_bars);

	err = pci_request_selected_regions(pci_dev, vp_dev->modern_bars,
					   "virtio-pci-modern");
	if (err)
		return err;

	err = -EINVAL;
	vp_dev->common = map_capability(pci_dev, common,
					sizeof(struct virtio_pci_common_cfg), 4,
					0, sizeof(struct virtio_pci_common_cfg),
					NULL);
	if (!vp_dev->common)
		goto err_map_common;
	vp_dev->isr = map_capability(pci_dev, isr, sizeof(u8), 1,
				     0, 1,
				     NULL);
	if (!vp_dev->isr)
		goto err_map_isr;

	/* Read notify_off_multiplier from config space. */
	pci_read_config_dword(pci_dev,
			      notify + offsetof(struct virtio_pci_notify_cap,
						notify_off_multiplier),
			      &vp_dev->notify_offset_multiplier);
	/* Read notify length and offset from config space. */
	pci_read_config_dword(pci_dev,
			      notify + offsetof(struct virtio_pci_notify_cap,
						cap.length),
			      &notify_length);

	pci_read_config_dword(pci_dev,
			      notify + offsetof(struct virtio_pci_notify_cap,
						cap.offset),
			      &notify_offset);

	/* We don't know how many VQs we'll map, ahead of the time.
	 * If notify length is small, map it all now.
	 * Otherwise, map each VQ individually later.
	 */
	if ((u64)notify_length + (notify_offset % PAGE_SIZE) <= PAGE_SIZE) {
		vp_dev->notify_base = map_capability(pci_dev, notify, 2, 2,
						     0, notify_length,
						     &vp_dev->notify_len);
		if (!vp_dev->notify_base)
			goto err_map_notify;
	} else {
		vp_dev->notify_map_cap = notify;
	}

	/* Again, we don't know how much we should map, but PAGE_SIZE
	 * is more than enough for all existing devices.
	 */
	if (device) {
		vp_dev->device = map_capability(pci_dev, device, 0, 4,
						0, PAGE_SIZE,
						&vp_dev->device_len);
		if (!vp_dev->device)
			goto err_map_device;

		vp_dev->vdev.config = &virtio_pci_config_ops;
	} else {
		vp_dev->vdev.config = &virtio_pci_config_nodev_ops;
	}

	vp_dev->config_vector = vp_config_vector;
	vp_dev->setup_vq = setup_vq;
	vp_dev->del_vq = del_vq;

	return 0;

err_map_device:
	if (vp_dev->notify_base)
		pci_iounmap(pci_dev, vp_dev->notify_base);
err_map_notify:
	pci_iounmap(pci_dev, vp_dev->isr);
err_map_isr:
	pci_iounmap(pci_dev, vp_dev->common);
err_map_common:
	return err;
}

void virtio_pci_modern_remove(struct virtio_pci_device *vp_dev)
{
	struct pci_dev *pci_dev = vp_dev->pci_dev;

	if (vp_dev->device)
		pci_iounmap(pci_dev, vp_dev->device);
	if (vp_dev->notify_base)
		pci_iounmap(pci_dev, vp_dev->notify_base);
	pci_iounmap(pci_dev, vp_dev->isr);
	pci_iounmap(pci_dev, vp_dev->common);
	pci_release_selected_regions(pci_dev, vp_dev->modern_bars);
}