aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/net/virtio/virtio_pci.c
blob: 9574498fb8eab6f02d259f32f0e4c37ba425a2bf (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
/*-
 *   BSD LICENSE
 *
 *   Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
 *   All rights reserved.
 *
 *   Redistribution and use in source and binary forms, with or without
 *   modification, are permitted provided that the following conditions
 *   are met:
 *
 *     * Redistributions of source code must retain the above copyright
 *       notice, this list of conditions and the following disclaimer.
 *     * Redistributions in binary form must reproduce the above copyright
 *       notice, this list of conditions and the following disclaimer in
 *       the documentation and/or other materials provided with the
 *       distribution.
 *     * Neither the name of Intel Corporation nor the names of its
 *       contributors may be used to endorse or promote products derived
 *       from this software without specific prior written permission.
 *
 *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
 *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
 *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
 *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
 *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */
#include <stdint.h>

#ifdef RTE_EXEC_ENV_LINUXAPP
 #include <dirent.h>
 #include <fcntl.h>
#endif

#include <rte_io.h>
#include <rte_bus.h>

#include "virtio_pci.h"
#include "virtio_logs.h"
#include "virtqueue.h"

/*
 * Following macros are derived from linux/pci_regs.h, however,
 * we can't simply include that header here, as there is no such
 * file for non-Linux platform.
 */
#define PCI_CAPABILITY_LIST	0x34
#define PCI_CAP_ID_VNDR		0x09
#define PCI_CAP_ID_MSIX		0x11

/*
 * The remaining space is defined by each driver as the per-driver
 * configuration space.
 */
#define VIRTIO_PCI_CONFIG(hw) \
		(((hw)->use_msix == VIRTIO_MSIX_ENABLED) ? 24 : 20)

static inline int
check_vq_phys_addr_ok(struct virtqueue *vq)
{
	/* Virtio PCI device VIRTIO_PCI_QUEUE_PF register is 32bit,
	 * and only accepts 32 bit page frame number.
	 * Check if the allocated physical memory exceeds 16TB.
	 */
	if ((vq->vq_ring_mem + vq->vq_ring_size - 1) >>
			(VIRTIO_PCI_QUEUE_ADDR_SHIFT + 32)) {
		PMD_INIT_LOG(ERR, "vring address shouldn't be above 16TB!");
		return 0;
	}

	return 1;
}

/*
 * Since we are in legacy mode:
 * http://ozlabs.org/~rusty/virtio-spec/virtio-0.9.5.pdf
 *
 * "Note that this is possible because while the virtio header is PCI (i.e.
 * little) endian, the device-specific region is encoded in the native endian of
 * the guest (where such distinction is applicable)."
 *
 * For powerpc which supports both, qemu supposes that cpu is big endian and
 * enforces this for the virtio-net stuff.
 */
static void
legacy_read_dev_config(struct virtio_hw *hw, size_t offset,
		       void *dst, int length)
{
#ifdef RTE_ARCH_PPC_64
	int size;

	while (length > 0) {
		if (length >= 4) {
			size = 4;
			rte_pci_ioport_read(VTPCI_IO(hw), dst, size,
				VIRTIO_PCI_CONFIG(hw) + offset);
			*(uint32_t *)dst = rte_be_to_cpu_32(*(uint32_t *)dst);
		} else if (length >= 2) {
			size = 2;
			rte_pci_ioport_read(VTPCI_IO(hw), dst, size,
				VIRTIO_PCI_CONFIG(hw) + offset);
			*(uint16_t *)dst = rte_be_to_cpu_16(*(uint16_t *)dst);
		} else {
			size = 1;
			rte_pci_ioport_read(VTPCI_IO(hw), dst, size,
				VIRTIO_PCI_CONFIG(hw) + offset);
		}

		dst = (char *)dst + size;
		offset += size;
		length -= size;
	}
#else
	rte_pci_ioport_read(VTPCI_IO(hw), dst, length,
		VIRTIO_PCI_CONFIG(hw) + offset);
#endif
}

static void
legacy_write_dev_config(struct virtio_hw *hw, size_t offset,
			const void *src, int length)
{
#ifdef RTE_ARCH_PPC_64
	union {
		uint32_t u32;
		uint16_t u16;
	} tmp;
	int size;

	while (length > 0) {
		if (length >= 4) {
			size = 4;
			tmp.u32 = rte_cpu_to_be_32(*(const uint32_t *)src);
			rte_pci_ioport_write(VTPCI_IO(hw), &tmp.u32, size,
				VIRTIO_PCI_CONFIG(hw) + offset);
		} else if (length >= 2) {
			size = 2;
			tmp.u16 = rte_cpu_to_be_16(*(const uint16_t *)src);
			rte_pci_ioport_write(VTPCI_IO(hw), &tmp.u16, size,
				VIRTIO_PCI_CONFIG(hw) + offset);
		} else {
			size = 1;
			rte_pci_ioport_write(VTPCI_IO(hw), src, size,
				VIRTIO_PCI_CONFIG(hw) + offset);
		}

		src = (const char *)src + size;
		offset += size;
		length -= size;
	}
#else
	rte_pci_ioport_write(VTPCI_IO(hw), src, length,
		VIRTIO_PCI_CONFIG(hw) + offset);
#endif
}

static uint64_t
legacy_get_features(struct virtio_hw *hw)
{
	uint32_t dst;

	rte_pci_ioport_read(VTPCI_IO(hw), &dst, 4, VIRTIO_PCI_HOST_FEATURES);
	return dst;
}

static void
legacy_set_features(struct virtio_hw *hw, uint64_t features)
{
	if ((features >> 32) != 0) {
		PMD_DRV_LOG(ERR,
			"only 32 bit features are allowed for legacy virtio!");
		return;
	}
	rte_pci_ioport_write(VTPCI_IO(hw), &features, 4,
		VIRTIO_PCI_GUEST_FEATURES);
}

static uint8_t
legacy_get_status(struct virtio_hw *hw)
{
	uint8_t dst;

	rte_pci_ioport_read(VTPCI_IO(hw), &dst, 1, VIRTIO_PCI_STATUS);
	return dst;
}

static void
legacy_set_status(struct virtio_hw *hw, uint8_t status)
{
	rte_pci_ioport_write(VTPCI_IO(hw), &status, 1, VIRTIO_PCI_STATUS);
}

static void
legacy_reset(struct virtio_hw *hw)
{
	legacy_set_status(hw, VIRTIO_CONFIG_STATUS_RESET);
}

static uint8_t
legacy_get_isr(struct virtio_hw *hw)
{
	uint8_t dst;

	rte_pci_ioport_read(VTPCI_IO(hw), &dst, 1, VIRTIO_PCI_ISR);
	return dst;
}

/* Enable one vector (0) for Link State Intrerrupt */
static uint16_t
legacy_set_config_irq(struct virtio_hw *hw, uint16_t vec)
{
	uint16_t dst;

	rte_pci_ioport_write(VTPCI_IO(hw), &vec, 2, VIRTIO_MSI_CONFIG_VECTOR);
	rte_pci_ioport_read(VTPCI_IO(hw), &dst, 2, VIRTIO_MSI_CONFIG_VECTOR);
	return dst;
}

static uint16_t
legacy_set_queue_irq(struct virtio_hw *hw, struct virtqueue *vq, uint16_t vec)
{
	uint16_t dst;

	rte_pci_ioport_write(VTPCI_IO(hw), &vq->vq_queue_index, 2,
		VIRTIO_PCI_QUEUE_SEL);
	rte_pci_ioport_write(VTPCI_IO(hw), &vec, 2, VIRTIO_MSI_QUEUE_VECTOR);
	rte_pci_ioport_read(VTPCI_IO(hw), &dst, 2, VIRTIO_MSI_QUEUE_VECTOR);
	return dst;
}

static uint16_t
legacy_get_queue_num(struct virtio_hw *hw, uint16_t queue_id)
{
	uint16_t dst;

	rte_pci_ioport_write(VTPCI_IO(hw), &queue_id, 2, VIRTIO_PCI_QUEUE_SEL);
	rte_pci_ioport_read(VTPCI_IO(hw), &dst, 2, VIRTIO_PCI_QUEUE_NUM);
	return dst;
}

static int
legacy_setup_queue(struct virtio_hw *hw, struct virtqueue *vq)
{
	uint32_t src;

	if (!check_vq_phys_addr_ok(vq))
		return -1;

	rte_pci_ioport_write(VTPCI_IO(hw), &vq->vq_queue_index, 2,
		VIRTIO_PCI_QUEUE_SEL);
	src = vq->vq_ring_mem >> VIRTIO_PCI_QUEUE_ADDR_SHIFT;
	rte_pci_ioport_write(VTPCI_IO(hw), &src, 4, VIRTIO_PCI_QUEUE_PFN);

	return 0;
}

static void
legacy_del_queue(struct virtio_hw *hw, struct virtqueue *vq)
{
	uint32_t src = 0;

	rte_pci_ioport_write(VTPCI_IO(hw), &vq->vq_queue_index, 2,
		VIRTIO_PCI_QUEUE_SEL);
	rte_pci_ioport_write(VTPCI_IO(hw), &src, 4, VIRTIO_PCI_QUEUE_PFN);
}

static void
legacy_notify_queue(struct virtio_hw *hw, struct virtqueue *vq)
{
	rte_pci_ioport_write(VTPCI_IO(hw), &vq->vq_queue_index, 2,
		VIRTIO_PCI_QUEUE_NOTIFY);
}

const struct virtio_pci_ops legacy_ops = {
	.read_dev_cfg	= legacy_read_dev_config,
	.write_dev_cfg	= legacy_write_dev_config,
	.reset		= legacy_reset,
	.get_status	= legacy_get_status,
	.set_status	= legacy_set_status,
	.get_features	= legacy_get_features,
	.set_features	= legacy_set_features,
	.get_isr	= legacy_get_isr,
	.set_config_irq	= legacy_set_config_irq,
	.set_queue_irq  = legacy_set_queue_irq,
	.get_queue_num	= legacy_get_queue_num,
	.setup_queue	= legacy_setup_queue,
	.del_queue	= legacy_del_queue,
	.notify_queue	= legacy_notify_queue,
};

static inline void
io_write64_twopart(uint64_t val, uint32_t *lo, uint32_t *hi)
{
	rte_write32(val & ((1ULL << 32) - 1), lo);
	rte_write32(val >> 32,		     hi);
}

static void
modern_read_dev_config(struct virtio_hw *hw, size_t offset,
		       void *dst, int length)
{
	int i;
	uint8_t *p;
	uint8_t old_gen, new_gen;

	do {
		old_gen = rte_read8(&hw->common_cfg->config_generation);

		p = dst;
		for (i = 0;  i < length; i++)
			*p++ = rte_read8((uint8_t *)hw->dev_cfg + offset + i);

		new_gen = rte_read8(&hw->common_cfg->config_generation);
	} while (old_gen != new_gen);
}

static void
modern_write_dev_config(struct virtio_hw *hw, size_t offset,
			const void *src, int length)
{
	int i;
	const uint8_t *p = src;

	for (i = 0;  i < length; i++)
		rte_write8((*p++), (((uint8_t *)hw->dev_cfg) + offset + i));
}

static uint64_t
modern_get_features(struct virtio_hw *hw)
{
	uint32_t features_lo, features_hi;

	rte_write32(0, &hw->common_cfg->device_feature_select);
	features_lo = rte_read32(&hw->common_cfg->device_feature);

	rte_write32(1, &hw->common_cfg->device_feature_select);
	features_hi = rte_read32(&hw->common_cfg->device_feature);

	return ((uint64_t)features_hi << 32) | features_lo;
}

static void
modern_set_features(struct virtio_hw *hw, uint64_t features)
{
	rte_write32(0, &hw->common_cfg->guest_feature_select);
	rte_write32(features & ((1ULL << 32) - 1),
		    &hw->common_cfg->guest_feature);

	rte_write32(1, &hw->common_cfg->guest_feature_select);
	rte_write32(features >> 32,
		    &hw->common_cfg->guest_feature);
}

static uint8_t
modern_get_status(struct virtio_hw *hw)
{
	return rte_read8(&hw->common_cfg->device_status);
}

static void
modern_set_status(struct virtio_hw *hw, uint8_t status)
{
	rte_write8(status, &hw->common_cfg->device_status);
}

static void
modern_reset(struct virtio_hw *hw)
{
	modern_set_status(hw, VIRTIO_CONFIG_STATUS_RESET);
	modern_get_status(hw);
}

static uint8_t
modern_get_isr(struct virtio_hw *hw)
{
	return rte_read8(hw->isr);
}

static uint16_t
modern_set_config_irq(struct virtio_hw *hw, uint16_t vec)
{
	rte_write16(vec, &hw->common_cfg->msix_config);
	return rte_read16(&hw->common_cfg->msix_config);
}

static uint16_t
modern_set_queue_irq(struct virtio_hw *hw, struct virtqueue *vq, uint16_t vec)
{
	rte_write16(vq->vq_queue_index, &hw->common_cfg->queue_select);
	rte_write16(vec, &hw->common_cfg->queue_msix_vector);
	return rte_read16(&hw->common_cfg->queue_msix_vector);
}

static uint16_t
modern_get_queue_num(struct virtio_hw *hw, uint16_t queue_id)
{
	rte_write16(queue_id, &hw->common_cfg->queue_select);
	return rte_read16(&hw->common_cfg->queue_size);
}

static int
modern_setup_queue(struct virtio_hw *hw, struct virtqueue *vq)
{
	uint64_t desc_addr, avail_addr, used_addr;
	uint16_t notify_off;

	if (!check_vq_phys_addr_ok(vq))
		return -1;

	desc_addr = vq->vq_ring_mem;
	avail_addr = desc_addr + vq->vq_nentries * sizeof(struct vring_desc);
	used_addr = RTE_ALIGN_CEIL(avail_addr + offsetof(struct vring_avail,
							 ring[vq->vq_nentries]),
				   VIRTIO_PCI_VRING_ALIGN);

	rte_write16(vq->vq_queue_index, &hw->common_cfg->queue_select);

	io_write64_twopart(desc_addr, &hw->common_cfg->queue_desc_lo,
				      &hw->common_cfg->queue_desc_hi);
	io_write64_twopart(avail_addr, &hw->common_cfg->queue_avail_lo,
				       &hw->common_cfg->queue_avail_hi);
	io_write64_twopart(used_addr, &hw->common_cfg->queue_used_lo,
				      &hw->common_cfg->queue_used_hi);

	notify_off = rte_read16(&hw->common_cfg->queue_notify_off);
	vq->notify_addr = (void *)((uint8_t *)hw->notify_base +
				notify_off * hw->notify_off_multiplier);

	rte_write16(1, &hw->common_cfg->queue_enable);

	PMD_INIT_LOG(DEBUG, "queue %u addresses:", vq->vq_queue_index);
	PMD_INIT_LOG(DEBUG, "\t desc_addr: %" PRIx64, desc_addr);
	PMD_INIT_LOG(DEBUG, "\t aval_addr: %" PRIx64, avail_addr);
	PMD_INIT_LOG(DEBUG, "\t used_addr: %" PRIx64, used_addr);
	PMD_INIT_LOG(DEBUG, "\t notify addr: %p (notify offset: %u)",
		vq->notify_addr, notify_off);

	return 0;
}

static void
modern_del_queue(struct virtio_hw *hw, struct virtqueue *vq)
{
	rte_write16(vq->vq_queue_index, &hw->common_cfg->queue_select);

	io_write64_twopart(0, &hw->common_cfg->queue_desc_lo,
				  &hw->common_cfg->queue_desc_hi);
	io_write64_twopart(0, &hw->common_cfg->queue_avail_lo,
				  &hw->common_cfg->queue_avail_hi);
	io_write64_twopart(0, &hw->common_cfg->queue_used_lo,
				  &hw->common_cfg->queue_used_hi);

	rte_write16(0, &hw->common_cfg->queue_enable);
}

static void
modern_notify_queue(struct virtio_hw *hw __rte_unused, struct virtqueue *vq)
{
	rte_write16(vq->vq_queue_index, vq->notify_addr);
}

const struct virtio_pci_ops modern_ops = {
	.read_dev_cfg	= modern_read_dev_config,
	.write_dev_cfg	= modern_write_dev_config,
	.reset		= modern_reset,
	.get_status	= modern_get_status,
	.set_status	= modern_set_status,
	.get_features	= modern_get_features,
	.set_features	= modern_set_features,
	.get_isr	= modern_get_isr,
	.set_config_irq	= modern_set_config_irq,
	.set_queue_irq  = modern_set_queue_irq,
	.get_queue_num	= modern_get_queue_num,
	.setup_queue	= modern_setup_queue,
	.del_queue	= modern_del_queue,
	.notify_queue	= modern_notify_queue,
};


void
vtpci_read_dev_config(struct virtio_hw *hw, size_t offset,
		      void *dst, int length)
{
	VTPCI_OPS(hw)->read_dev_cfg(hw, offset, dst, length);
}

void
vtpci_write_dev_config(struct virtio_hw *hw, size_t offset,
		       const void *src, int length)
{
	VTPCI_OPS(hw)->write_dev_cfg(hw, offset, src, length);
}

uint64_t
vtpci_negotiate_features(struct virtio_hw *hw, uint64_t host_features)
{
	uint64_t features;

	/*
	 * Limit negotiated features to what the driver, virtqueue, and
	 * host all support.
	 */
	features = host_features & hw->guest_features;
	VTPCI_OPS(hw)->set_features(hw, features);

	return features;
}

void
vtpci_reset(struct virtio_hw *hw)
{
	VTPCI_OPS(hw)->set_status(hw, VIRTIO_CONFIG_STATUS_RESET);
	/* flush status write */
	VTPCI_OPS(hw)->get_status(hw);
}

void
vtpci_reinit_complete(struct virtio_hw *hw)
{
	vtpci_set_status(hw, VIRTIO_CONFIG_STATUS_DRIVER_OK);
}

void
vtpci_set_status(struct virtio_hw *hw, uint8_t status)
{
	if (status != VIRTIO_CONFIG_STATUS_RESET)
		status |= VTPCI_OPS(hw)->get_status(hw);

	VTPCI_OPS(hw)->set_status(hw, status);
}

uint8_t
vtpci_get_status(struct virtio_hw *hw)
{
	return VTPCI_OPS(hw)->get_status(hw);
}

uint8_t
vtpci_isr(struct virtio_hw *hw)
{
	return VTPCI_OPS(hw)->get_isr(hw);
}

static void *
get_cfg_addr(struct rte_pci_device *dev, struct virtio_pci_cap *cap)
{
	uint8_t  bar    = cap->bar;
	uint32_t length = cap->length;
	uint32_t offset = cap->offset;
	uint8_t *base;

	if (bar >= PCI_MAX_RESOURCE) {
		PMD_INIT_LOG(ERR, "invalid bar: %u", bar);
		return NULL;
	}

	if (offset + length < offset) {
		PMD_INIT_LOG(ERR, "offset(%u) + length(%u) overflows",
			offset, length);
		return NULL;
	}

	if (offset + length > dev->mem_resource[bar].len) {
		PMD_INIT_LOG(ERR,
			"invalid cap: overflows bar space: %u > %" PRIu64,
			offset + length, dev->mem_resource[bar].len);
		return NULL;
	}

	base = dev->mem_resource[bar].addr;
	if (base == NULL) {
		PMD_INIT_LOG(ERR, "bar %u base addr is NULL", bar);
		return NULL;
	}

	return base + offset;
}

#define PCI_MSIX_ENABLE 0x8000

static int
virtio_read_caps(struct rte_pci_device *dev, struct virtio_hw *hw)
{
	uint8_t pos;
	struct virtio_pci_cap cap;
	int ret;

	if (rte_pci_map_device(dev)) {
		PMD_INIT_LOG(DEBUG, "failed to map pci device!");
		return -1;
	}

	ret = rte_pci_read_config(dev, &pos, 1, PCI_CAPABILITY_LIST);
	if (ret < 0) {
		PMD_INIT_LOG(DEBUG, "failed to read pci capability list");
		return -1;
	}

	while (pos) {
		ret = rte_pci_read_config(dev, &cap, sizeof(cap), pos);
		if (ret < 0) {
			PMD_INIT_LOG(ERR,
				"failed to read pci cap at pos: %x", pos);
			break;
		}

		if (cap.cap_vndr == PCI_CAP_ID_MSIX) {
			/* Transitional devices would also have this capability,
			 * that's why we also check if msix is enabled.
			 * 1st byte is cap ID; 2nd byte is the position of next
			 * cap; next two bytes are the flags.
			 */
			uint16_t flags = ((uint16_t *)&cap)[1];

			if (flags & PCI_MSIX_ENABLE)
				hw->use_msix = VIRTIO_MSIX_ENABLED;
			else
				hw->use_msix = VIRTIO_MSIX_DISABLED;
		}

		if (cap.cap_vndr != PCI_CAP_ID_VNDR) {
			PMD_INIT_LOG(DEBUG,
				"[%2x] skipping non VNDR cap id: %02x",
				pos, cap.cap_vndr);
			goto next;
		}

		PMD_INIT_LOG(DEBUG,
			"[%2x] cfg type: %u, bar: %u, offset: %04x, len: %u",
			pos, cap.cfg_type, cap.bar, cap.offset, cap.length);

		switch (cap.cfg_type) {
		case VIRTIO_PCI_CAP_COMMON_CFG:
			hw->common_cfg = get_cfg_addr(dev, &cap);
			break;
		case VIRTIO_PCI_CAP_NOTIFY_CFG:
			rte_pci_read_config(dev, &hw->notify_off_multiplier,
					4, pos + sizeof(cap));
			hw->notify_base = get_cfg_addr(dev, &cap);
			break;
		case VIRTIO_PCI_CAP_DEVICE_CFG:
			hw->dev_cfg = get_cfg_addr(dev, &cap);
			break;
		case VIRTIO_PCI_CAP_ISR_CFG:
			hw->isr = get_cfg_addr(dev, &cap);
			break;
		}

next:
		pos = cap.cap_next;
	}

	if (hw->common_cfg == NULL || hw->notify_base == NULL ||
	    hw->dev_cfg == NULL    || hw->isr == NULL) {
		PMD_INIT_LOG(INFO, "no modern virtio pci device found.");
		return -1;
	}

	PMD_INIT_LOG(INFO, "found modern virtio pci device.");

	PMD_INIT_LOG(DEBUG, "common cfg mapped at: %p", hw->common_cfg);
	PMD_INIT_LOG(DEBUG, "device cfg mapped at: %p", hw->dev_cfg);
	PMD_INIT_LOG(DEBUG, "isr cfg mapped at: %p", hw->isr);
	PMD_INIT_LOG(DEBUG, "notify base: %p, notify off multiplier: %u",
		hw->notify_base, hw->notify_off_multiplier);

	return 0;
}

/*
 * Return -1:
 *   if there is error mapping with VFIO/UIO.
 *   if port map error when driver type is KDRV_NONE.
 *   if whitelisted but driver type is KDRV_UNKNOWN.
 * Return 1 if kernel driver is managing the device.
 * Return 0 on success.
 */
int
vtpci_init(struct rte_pci_device *dev, struct virtio_hw *hw)
{
	/*
	 * Try if we can succeed reading virtio pci caps, which exists
	 * only on modern pci device. If failed, we fallback to legacy
	 * virtio handling.
	 */
	if (virtio_read_caps(dev, hw) == 0) {
		PMD_INIT_LOG(INFO, "modern virtio pci detected.");
		virtio_hw_internal[hw->port_id].vtpci_ops = &modern_ops;
		hw->modern = 1;
		return 0;
	}

	PMD_INIT_LOG(INFO, "trying with legacy virtio pci.");
	if (rte_pci_ioport_map(dev, 0, VTPCI_IO(hw)) < 0) {
		if (dev->kdrv == RTE_KDRV_UNKNOWN &&
		    (!dev->device.devargs ||
		     dev->device.devargs->bus !=
		     rte_bus_find_by_name("pci"))) {
			PMD_INIT_LOG(INFO,
				"skip kernel managed virtio device.");
			return 1;
		}
		return -1;
	}

	virtio_hw_internal[hw->port_id].vtpci_ops = &legacy_ops;
	hw->modern   = 0;

	return 0;
}

enum virtio_msix_status
vtpci_msix_detect(struct rte_pci_device *dev)
{
	uint8_t pos;
	struct virtio_pci_cap cap;
	int ret;

	ret = rte_pci_read_config(dev, &pos, 1, PCI_CAPABILITY_LIST);
	if (ret < 0) {
		PMD_INIT_LOG(DEBUG, "failed to read pci capability list");
		return VIRTIO_MSIX_NONE;
	}

	while (pos) {
		ret = rte_pci_read_config(dev, &cap, sizeof(cap), pos);
		if (ret < 0) {
			PMD_INIT_LOG(ERR,
				"failed to read pci cap at pos: %x", pos);
			break;
		}

		if (cap.cap_vndr == PCI_CAP_ID_MSIX) {
			uint16_t flags = ((uint16_t *)&cap)[1];

			if (flags & PCI_MSIX_ENABLE)
				return VIRTIO_MSIX_ENABLED;
			else
				return VIRTIO_MSIX_DISABLED;
		}

		pos = cap.cap_next;
	}

	return VIRTIO_MSIX_NONE;
}