DPDK logo

Elixir Cross Referencer

  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
/*-
 *   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 <string.h>
#include <fcntl.h>
#include <linux/pci_regs.h>
#include <sys/eventfd.h>
#include <sys/socket.h>
#include <sys/ioctl.h>

#include <rte_log.h>
#include <rte_pci.h>
#include <rte_tailq.h>
#include <rte_eal_memconfig.h>
#include <rte_malloc.h>

#include "eal_filesystem.h"
#include "eal_pci_init.h"
#include "eal_vfio.h"

/**
 * @file
 * PCI probing under linux (VFIO version)
 *
 * This code tries to determine if the PCI device is bound to VFIO driver,
 * and initialize it (map BARs, set up interrupts) if that's the case.
 *
 * This file is only compiled if CONFIG_RTE_EAL_VFIO is set to "y".
 */

#ifdef VFIO_PRESENT

#define VFIO_DIR "/dev/vfio"
#define VFIO_CONTAINER_PATH "/dev/vfio/vfio"
#define VFIO_GROUP_FMT "/dev/vfio/%u"
#define VFIO_GET_REGION_ADDR(x) ((uint64_t) x << 40ULL)

/* per-process VFIO config */
static struct vfio_config vfio_cfg;

/* get PCI BAR number where MSI-X interrupts are */
static int
pci_vfio_get_msix_bar(int fd, int *msix_bar)
{
	int ret;
	uint32_t reg;
	uint8_t cap_id, cap_offset;

	/* read PCI capability pointer from config space */
	ret = pread64(fd, &reg, sizeof(reg),
			VFIO_GET_REGION_ADDR(VFIO_PCI_CONFIG_REGION_INDEX) +
			PCI_CAPABILITY_LIST);
	if (ret != sizeof(reg)) {
		RTE_LOG(ERR, EAL, "Cannot read capability pointer from PCI "
				"config space!\n");
		return -1;
	}

	/* we need first byte */
	cap_offset = reg & 0xFF;

	while (cap_offset) {

		/* read PCI capability ID */
		ret = pread64(fd, &reg, sizeof(reg),
				VFIO_GET_REGION_ADDR(VFIO_PCI_CONFIG_REGION_INDEX) +
				cap_offset);
		if (ret != sizeof(reg)) {
			RTE_LOG(ERR, EAL, "Cannot read capability ID from PCI "
					"config space!\n");
			return -1;
		}

		/* we need first byte */
		cap_id = reg & 0xFF;

		/* if we haven't reached MSI-X, check next capability */
		if (cap_id != PCI_CAP_ID_MSIX) {
			ret = pread64(fd, &reg, sizeof(reg),
					VFIO_GET_REGION_ADDR(VFIO_PCI_CONFIG_REGION_INDEX) +
					cap_offset);
			if (ret != sizeof(reg)) {
				RTE_LOG(ERR, EAL, "Cannot read capability pointer from PCI "
						"config space!\n");
				return -1;
			}

			/* we need second byte */
			cap_offset = (reg & 0xFF00) >> 8;

			continue;
		}
		/* else, read table offset */
		else {
			/* table offset resides in the next 4 bytes */
			ret = pread64(fd, &reg, sizeof(reg),
					VFIO_GET_REGION_ADDR(VFIO_PCI_CONFIG_REGION_INDEX) +
					cap_offset + 4);
			if (ret != sizeof(reg)) {
				RTE_LOG(ERR, EAL, "Cannot read table offset from PCI config "
						"space!\n");
				return -1;
			}

			*msix_bar = reg & RTE_PCI_MSIX_TABLE_BIR;

			return 0;
		}
	}
	return 0;
}

/* set PCI bus mastering */
static int
pci_vfio_set_bus_master(int dev_fd)
{
	uint16_t reg;
	int ret;

	ret = pread64(dev_fd, &reg, sizeof(reg),
			VFIO_GET_REGION_ADDR(VFIO_PCI_CONFIG_REGION_INDEX) +
			PCI_COMMAND);
	if (ret != sizeof(reg)) {
		RTE_LOG(ERR, EAL, "Cannot read command from PCI config space!\n");
		return -1;
	}

	/* set the master bit */
	reg |= PCI_COMMAND_MASTER;

	ret = pwrite64(dev_fd, &reg, sizeof(reg),
			VFIO_GET_REGION_ADDR(VFIO_PCI_CONFIG_REGION_INDEX) +
			PCI_COMMAND);

	if (ret != sizeof(reg)) {
		RTE_LOG(ERR, EAL, "Cannot write command to PCI config space!\n");
		return -1;
	}

	return 0;
}

/* set up DMA mappings */
static int
pci_vfio_setup_dma_maps(int vfio_container_fd)
{
	const struct rte_memseg *ms = rte_eal_get_physmem_layout();
	int i, ret;

	ret = ioctl(vfio_container_fd, VFIO_SET_IOMMU,
			VFIO_TYPE1_IOMMU);
	if (ret) {
		RTE_LOG(ERR, EAL, "  cannot set IOMMU type, "
				"error %i (%s)\n", errno, strerror(errno));
		return -1;
	}

	/* map all DPDK segments for DMA. use 1:1 PA to IOVA mapping */
	for (i = 0; i < RTE_MAX_MEMSEG; i++) {
		struct vfio_iommu_type1_dma_map dma_map;

		if (ms[i].addr == NULL)
			break;

		memset(&dma_map, 0, sizeof(dma_map));
		dma_map.argsz = sizeof(struct vfio_iommu_type1_dma_map);
		dma_map.vaddr = ms[i].addr_64;
		dma_map.size = ms[i].len;
		dma_map.iova = ms[i].phys_addr;
		dma_map.flags = VFIO_DMA_MAP_FLAG_READ | VFIO_DMA_MAP_FLAG_WRITE;

		ret = ioctl(vfio_container_fd, VFIO_IOMMU_MAP_DMA, &dma_map);

		if (ret) {
			RTE_LOG(ERR, EAL, "  cannot set up DMA remapping, "
					"error %i (%s)\n", errno, strerror(errno));
			return -1;
		}
	}

	return 0;
}

/* set up interrupt support (but not enable interrupts) */
static int
pci_vfio_setup_interrupts(struct rte_pci_device *dev, int vfio_dev_fd)
{
	int i, ret, intr_idx;

	/* default to invalid index */
	intr_idx = VFIO_PCI_NUM_IRQS;

	/* get interrupt type from internal config (MSI-X by default, can be
	 * overriden from the command line
	 */
	switch (internal_config.vfio_intr_mode) {
	case RTE_INTR_MODE_MSIX:
		intr_idx = VFIO_PCI_MSIX_IRQ_INDEX;
		break;
	case RTE_INTR_MODE_MSI:
		intr_idx = VFIO_PCI_MSI_IRQ_INDEX;
		break;
	case RTE_INTR_MODE_LEGACY:
		intr_idx = VFIO_PCI_INTX_IRQ_INDEX;
		break;
	/* don't do anything if we want to automatically determine interrupt type */
	case RTE_INTR_MODE_NONE:
		break;
	default:
		RTE_LOG(ERR, EAL, "  unknown default interrupt type!\n");
		return -1;
	}

	/* start from MSI-X interrupt type */
	for (i = VFIO_PCI_MSIX_IRQ_INDEX; i >= 0; i--) {
		struct vfio_irq_info irq = { .argsz = sizeof(irq) };
		int fd = -1;

		/* skip interrupt modes we don't want */
		if (internal_config.vfio_intr_mode != RTE_INTR_MODE_NONE &&
				i != intr_idx)
			continue;

		irq.index = i;

		ret = ioctl(vfio_dev_fd, VFIO_DEVICE_GET_IRQ_INFO, &irq);
		if (ret < 0) {
			RTE_LOG(ERR, EAL, "  cannot get IRQ info, "
					"error %i (%s)\n", errno, strerror(errno));
			return -1;
		}

		/* if this vector cannot be used with eventfd, fail if we explicitly
		 * specified interrupt type, otherwise continue */
		if ((irq.flags & VFIO_IRQ_INFO_EVENTFD) == 0) {
			if (internal_config.vfio_intr_mode != RTE_INTR_MODE_NONE) {
				RTE_LOG(ERR, EAL,
						"  interrupt vector does not support eventfd!\n");
				return -1;
			} else
				continue;
		}

		/* set up an eventfd for interrupts */
		fd = eventfd(0, 0);
		if (fd < 0) {
			RTE_LOG(ERR, EAL, "  cannot set up eventfd, "
					"error %i (%s)\n", errno, strerror(errno));
			return -1;
		}

		dev->intr_handle.fd = fd;
		dev->intr_handle.vfio_dev_fd = vfio_dev_fd;

		switch (i) {
		case VFIO_PCI_MSIX_IRQ_INDEX:
			internal_config.vfio_intr_mode = RTE_INTR_MODE_MSIX;
			dev->intr_handle.type = RTE_INTR_HANDLE_VFIO_MSIX;
			break;
		case VFIO_PCI_MSI_IRQ_INDEX:
			internal_config.vfio_intr_mode = RTE_INTR_MODE_MSI;
			dev->intr_handle.type = RTE_INTR_HANDLE_VFIO_MSI;
			break;
		case VFIO_PCI_INTX_IRQ_INDEX:
			internal_config.vfio_intr_mode = RTE_INTR_MODE_LEGACY;
			dev->intr_handle.type = RTE_INTR_HANDLE_VFIO_LEGACY;
			break;
		default:
			RTE_LOG(ERR, EAL, "  unknown interrupt type!\n");
			return -1;
		}

		return 0;
	}

	/* if we're here, we haven't found a suitable interrupt vector */
	return -1;
}

/* open container fd or get an existing one */
int
pci_vfio_get_container_fd(void)
{
	int ret, vfio_container_fd;

	/* if we're in a primary process, try to open the container */
	if (internal_config.process_type == RTE_PROC_PRIMARY) {
		vfio_container_fd = open(VFIO_CONTAINER_PATH, O_RDWR);
		if (vfio_container_fd < 0) {
			RTE_LOG(ERR, EAL, "  cannot open VFIO container, "
					"error %i (%s)\n", errno, strerror(errno));
			return -1;
		}

		/* check VFIO API version */
		ret = ioctl(vfio_container_fd, VFIO_GET_API_VERSION);
		if (ret != VFIO_API_VERSION) {
			if (ret < 0)
				RTE_LOG(ERR, EAL, "  could not get VFIO API version, "
						"error %i (%s)\n", errno, strerror(errno));
			else
				RTE_LOG(ERR, EAL, "  unsupported VFIO API version!\n");
			close(vfio_container_fd);
			return -1;
		}

		/* check if we support IOMMU type 1 */
		ret = ioctl(vfio_container_fd, VFIO_CHECK_EXTENSION, VFIO_TYPE1_IOMMU);
		if (ret != 1) {
			if (ret < 0)
				RTE_LOG(ERR, EAL, "  could not get IOMMU type, "
						"error %i (%s)\n", errno, strerror(errno));
			else
				RTE_LOG(ERR, EAL, "  unsupported IOMMU type!\n");
			close(vfio_container_fd);
			return -1;
		}

		return vfio_container_fd;
	} else {
		/*
		 * if we're in a secondary process, request container fd from the
		 * primary process via our socket
		 */
		int socket_fd;

		socket_fd = vfio_mp_sync_connect_to_primary();
		if (socket_fd < 0) {
			RTE_LOG(ERR, EAL, "  cannot connect to primary process!\n");
			return -1;
		}
		if (vfio_mp_sync_send_request(socket_fd, SOCKET_REQ_CONTAINER) < 0) {
			RTE_LOG(ERR, EAL, "  cannot request container fd!\n");
			close(socket_fd);
			return -1;
		}
		vfio_container_fd = vfio_mp_sync_receive_fd(socket_fd);
		if (vfio_container_fd < 0) {
			RTE_LOG(ERR, EAL, "  cannot get container fd!\n");
			close(socket_fd);
			return -1;
		}
		close(socket_fd);
		return vfio_container_fd;
	}

	return -1;
}

/* open group fd or get an existing one */
int
pci_vfio_get_group_fd(int iommu_group_no)
{
	int i;
	int vfio_group_fd;
	char filename[PATH_MAX];

	/* check if we already have the group descriptor open */
	for (i = 0; i < vfio_cfg.vfio_group_idx; i++)
		if (vfio_cfg.vfio_groups[i].group_no == iommu_group_no)
			return vfio_cfg.vfio_groups[i].fd;

	/* if primary, try to open the group */
	if (internal_config.process_type == RTE_PROC_PRIMARY) {
		snprintf(filename, sizeof(filename),
				 VFIO_GROUP_FMT, iommu_group_no);
		vfio_group_fd = open(filename, O_RDWR);
		if (vfio_group_fd < 0) {
			/* if file not found, it's not an error */
			if (errno != ENOENT) {
				RTE_LOG(ERR, EAL, "Cannot open %s: %s\n", filename,
						strerror(errno));
				return -1;
			}
			return 0;
		}

		/* if the fd is valid, create a new group for it */
		if (vfio_cfg.vfio_group_idx == VFIO_MAX_GROUPS) {
			RTE_LOG(ERR, EAL, "Maximum number of VFIO groups reached!\n");
			return -1;
		}
		vfio_cfg.vfio_groups[vfio_cfg.vfio_group_idx].group_no = iommu_group_no;
		vfio_cfg.vfio_groups[vfio_cfg.vfio_group_idx].fd = vfio_group_fd;
		return vfio_group_fd;
	}
	/* if we're in a secondary process, request group fd from the primary
	 * process via our socket
	 */
	else {
		int socket_fd, ret;

		socket_fd = vfio_mp_sync_connect_to_primary();

		if (socket_fd < 0) {
			RTE_LOG(ERR, EAL, "  cannot connect to primary process!\n");
			return -1;
		}
		if (vfio_mp_sync_send_request(socket_fd, SOCKET_REQ_GROUP) < 0) {
			RTE_LOG(ERR, EAL, "  cannot request container fd!\n");
			close(socket_fd);
			return -1;
		}
		if (vfio_mp_sync_send_request(socket_fd, iommu_group_no) < 0) {
			RTE_LOG(ERR, EAL, "  cannot send group number!\n");
			close(socket_fd);
			return -1;
		}
		ret = vfio_mp_sync_receive_request(socket_fd);
		switch (ret) {
		case SOCKET_NO_FD:
			close(socket_fd);
			return 0;
		case SOCKET_OK:
			vfio_group_fd = vfio_mp_sync_receive_fd(socket_fd);
			/* if we got the fd, return it */
			if (vfio_group_fd > 0) {
				close(socket_fd);
				return vfio_group_fd;
			}
			/* fall-through on error */
		default:
			RTE_LOG(ERR, EAL, "  cannot get container fd!\n");
			close(socket_fd);
			return -1;
		}
	}
	return -1;
}

/* parse IOMMU group number for a PCI device
 * returns -1 for errors, 0 for non-existent group */
static int
pci_vfio_get_group_no(const char *pci_addr)
{
	char linkname[PATH_MAX];
	char filename[PATH_MAX];
	char *tok[16], *group_tok, *end;
	int ret, iommu_group_no;

	memset(linkname, 0, sizeof(linkname));
	memset(filename, 0, sizeof(filename));

	/* try to find out IOMMU group for this device */
	snprintf(linkname, sizeof(linkname),
			 SYSFS_PCI_DEVICES "/%s/iommu_group", pci_addr);

	ret = readlink(linkname, filename, sizeof(filename));

	/* if the link doesn't exist, no VFIO for us */
	if (ret < 0)
		return 0;

	ret = rte_strsplit(filename, sizeof(filename),
			tok, RTE_DIM(tok), '/');

	if (ret <= 0) {
		RTE_LOG(ERR, EAL, "  %s cannot get IOMMU group\n", pci_addr);
		return -1;
	}

	/* IOMMU group is always the last token */
	errno = 0;
	group_tok = tok[ret - 1];
	end = group_tok;
	iommu_group_no = strtol(group_tok, &end, 10);
	if ((end != group_tok && *end != '\0') || errno != 0) {
		RTE_LOG(ERR, EAL, "  %s error parsing IOMMU number!\n", pci_addr);
		return -1;
	}

	return iommu_group_no;
}

static void
clear_current_group(void)
{
	vfio_cfg.vfio_groups[vfio_cfg.vfio_group_idx].group_no = 0;
	vfio_cfg.vfio_groups[vfio_cfg.vfio_group_idx].fd = -1;
}


/*
 * map the PCI resources of a PCI device in virtual memory (VFIO version).
 * primary and secondary processes follow almost exactly the same path
 */
int
pci_vfio_map_resource(struct rte_pci_device *dev)
{
	struct vfio_group_status group_status = {
			.argsz = sizeof(group_status)
	};
	struct vfio_device_info device_info = { .argsz = sizeof(device_info) };
	int vfio_group_fd, vfio_dev_fd;
	int iommu_group_no;
	char pci_addr[PATH_MAX] = {0};
	struct rte_pci_addr *loc = &dev->addr;
	int i, ret, msix_bar;
	struct mapped_pci_resource *vfio_res = NULL;
	struct pci_map *maps;

	dev->intr_handle.fd = -1;
	dev->intr_handle.type = RTE_INTR_HANDLE_UNKNOWN;

	/* store PCI address string */
	snprintf(pci_addr, sizeof(pci_addr), PCI_PRI_FMT,
			loc->domain, loc->bus, loc->devid, loc->function);

	/* get group number */
	iommu_group_no = pci_vfio_get_group_no(pci_addr);

	/* if 0, group doesn't exist */
	if (iommu_group_no == 0) {
		RTE_LOG(WARNING, EAL, "  %s not managed by VFIO driver, skipping\n",
				pci_addr);
		return 1;
	}
	/* if negative, something failed */
	else if (iommu_group_no < 0)
		return -1;

	/* get the actual group fd */
	vfio_group_fd = pci_vfio_get_group_fd(iommu_group_no);
	if (vfio_group_fd < 0)
		return -1;

	/* store group fd */
	vfio_cfg.vfio_groups[vfio_cfg.vfio_group_idx].group_no = iommu_group_no;
	vfio_cfg.vfio_groups[vfio_cfg.vfio_group_idx].fd = vfio_group_fd;

	/* if group_fd == 0, that means the device isn't managed by VFIO */
	if (vfio_group_fd == 0) {
		RTE_LOG(WARNING, EAL, "  %s not managed by VFIO driver, skipping\n",
				pci_addr);
		/* we store 0 as group fd to distinguish between existing but
		 * unbound VFIO groups, and groups that don't exist at all.
		 */
		vfio_cfg.vfio_group_idx++;
		return 1;
	}

	/*
	 * at this point, we know at least one port on this device is bound to VFIO,
	 * so we can proceed to try and set this particular port up
	 */

	/* check if the group is viable */
	ret = ioctl(vfio_group_fd, VFIO_GROUP_GET_STATUS, &group_status);
	if (ret) {
		RTE_LOG(ERR, EAL, "  %s cannot get group status, "
				"error %i (%s)\n", pci_addr, errno, strerror(errno));
		close(vfio_group_fd);
		clear_current_group();
		return -1;
	} else if (!(group_status.flags & VFIO_GROUP_FLAGS_VIABLE)) {
		RTE_LOG(ERR, EAL, "  %s VFIO group is not viable!\n", pci_addr);
		close(vfio_group_fd);
		clear_current_group();
		return -1;
	}

	/*
	 * at this point, we know that this group is viable (meaning, all devices
	 * are either bound to VFIO or not bound to anything)
	 */

	/* check if group does not have a container yet */
	if (!(group_status.flags & VFIO_GROUP_FLAGS_CONTAINER_SET)) {

		/* add group to a container */
		ret = ioctl(vfio_group_fd, VFIO_GROUP_SET_CONTAINER,
				&vfio_cfg.vfio_container_fd);
		if (ret) {
			RTE_LOG(ERR, EAL, "  %s cannot add VFIO group to container, "
					"error %i (%s)\n", pci_addr, errno, strerror(errno));
			close(vfio_group_fd);
			clear_current_group();
			return -1;
		}
		/*
		 * at this point we know that this group has been successfully
		 * initialized, so we increment vfio_group_idx to indicate that we can
		 * add new groups.
		 */
		vfio_cfg.vfio_group_idx++;
	}

	/*
	 * set up DMA mappings for container
	 *
	 * needs to be done only once, only when at least one group is assigned to
	 * a container and only in primary process
	 */
	if (internal_config.process_type == RTE_PROC_PRIMARY &&
			vfio_cfg.vfio_container_has_dma == 0) {
		ret = pci_vfio_setup_dma_maps(vfio_cfg.vfio_container_fd);
		if (ret) {
			RTE_LOG(ERR, EAL, "  %s DMA remapping failed, "
					"error %i (%s)\n", pci_addr, errno, strerror(errno));
			return -1;
		}
		vfio_cfg.vfio_container_has_dma = 1;
	}

	/* get a file descriptor for the device */
	vfio_dev_fd = ioctl(vfio_group_fd, VFIO_GROUP_GET_DEVICE_FD, pci_addr);
	if (vfio_dev_fd < 0) {
		/* if we cannot get a device fd, this simply means that this
		 * particular port is not bound to VFIO
		 */
		RTE_LOG(WARNING, EAL, "  %s not managed by VFIO driver, skipping\n",
				pci_addr);
		return 1;
	}

	/* test and setup the device */
	ret = ioctl(vfio_dev_fd, VFIO_DEVICE_GET_INFO, &device_info);
	if (ret) {
		RTE_LOG(ERR, EAL, "  %s cannot get device info, "
				"error %i (%s)\n", pci_addr, errno, strerror(errno));
		close(vfio_dev_fd);
		return -1;
	}

	/* get MSI-X BAR, if any (we have to know where it is because we can't
	 * mmap it when using VFIO) */
	msix_bar = -1;
	ret = pci_vfio_get_msix_bar(vfio_dev_fd, &msix_bar);
	if (ret < 0) {
		RTE_LOG(ERR, EAL, "  %s cannot get MSI-X BAR number!\n", pci_addr);
		close(vfio_dev_fd);
		return -1;
	}

	/* if we're in a primary process, allocate vfio_res and get region info */
	if (internal_config.process_type == RTE_PROC_PRIMARY) {
		vfio_res = rte_zmalloc("VFIO_RES", sizeof(*vfio_res), 0);
		if (vfio_res == NULL) {
			RTE_LOG(ERR, EAL,
				"%s(): cannot store uio mmap details\n", __func__);
			close(vfio_dev_fd);
			return -1;
		}
		memcpy(&vfio_res->pci_addr, &dev->addr, sizeof(vfio_res->pci_addr));

		/* get number of registers (up to BAR5) */
		vfio_res->nb_maps = RTE_MIN((int) device_info.num_regions,
				VFIO_PCI_BAR5_REGION_INDEX + 1);
	} else {
		/* if we're in a secondary process, just find our tailq entry */
		TAILQ_FOREACH(vfio_res, pci_res_list, next) {
			if (memcmp(&vfio_res->pci_addr, &dev->addr, sizeof(dev->addr)))
				continue;
			break;
		}
		/* if we haven't found our tailq entry, something's wrong */
		if (vfio_res == NULL) {
			RTE_LOG(ERR, EAL, "  %s cannot find TAILQ entry for PCI device!\n",
					pci_addr);
			close(vfio_dev_fd);
			return -1;
		}
	}

	/* map BARs */
	maps = vfio_res->maps;

	for (i = 0; i < (int) vfio_res->nb_maps; i++) {
		struct vfio_region_info reg = { .argsz = sizeof(reg) };
		void *bar_addr;

		reg.index = i;

		ret = ioctl(vfio_dev_fd, VFIO_DEVICE_GET_REGION_INFO, &reg);

		if (ret) {
			RTE_LOG(ERR, EAL, "  %s cannot get device region info "
					"error %i (%s)\n", pci_addr, errno, strerror(errno));
			close(vfio_dev_fd);
			if (internal_config.process_type == RTE_PROC_PRIMARY)
				rte_free(vfio_res);
			return -1;
		}

		/* skip non-mmapable BARs */
		if ((reg.flags & VFIO_REGION_INFO_FLAG_MMAP) == 0)
			continue;

		/* skip MSI-X BAR */
		if (i == msix_bar)
			continue;

		bar_addr = pci_map_resource(maps[i].addr, vfio_dev_fd, reg.offset,
				reg.size);

		if (bar_addr == NULL) {
			RTE_LOG(ERR, EAL, "  %s mapping BAR%i failed: %s\n", pci_addr, i,
					strerror(errno));
			close(vfio_dev_fd);
			if (internal_config.process_type == RTE_PROC_PRIMARY)
				rte_free(vfio_res);
			return -1;
		}

		maps[i].addr = bar_addr;
		maps[i].offset = reg.offset;
		maps[i].size = reg.size;
		dev->mem_resource[i].addr = bar_addr;
	}

	/* if secondary process, do not set up interrupts */
	if (internal_config.process_type == RTE_PROC_PRIMARY) {
		if (pci_vfio_setup_interrupts(dev, vfio_dev_fd) != 0) {
			RTE_LOG(ERR, EAL, "  %s error setting up interrupts!\n", pci_addr);
			close(vfio_dev_fd);
			rte_free(vfio_res);
			return -1;
		}

		/* set bus mastering for the device */
		if (pci_vfio_set_bus_master(vfio_dev_fd)) {
			RTE_LOG(ERR, EAL, "  %s cannot set up bus mastering!\n", pci_addr);
			close(vfio_dev_fd);
			rte_free(vfio_res);
			return -1;
		}

		/* Reset the device */
		ioctl(vfio_dev_fd, VFIO_DEVICE_RESET);
	}

	if (internal_config.process_type == RTE_PROC_PRIMARY)
		TAILQ_INSERT_TAIL(pci_res_list, vfio_res, next);

	return 0;
}

int
pci_vfio_enable(void)
{
	/* initialize group list */
	int i;

	for (i = 0; i < VFIO_MAX_GROUPS; i++) {
		vfio_cfg.vfio_groups[i].fd = -1;
		vfio_cfg.vfio_groups[i].group_no = -1;
	}
	vfio_cfg.vfio_container_fd = pci_vfio_get_container_fd();

	/* check if we have VFIO driver enabled */
	if (vfio_cfg.vfio_container_fd != -1)
		vfio_cfg.vfio_enabled = 1;
	else
		RTE_LOG(INFO, EAL, "VFIO support could not be initialized\n");

	return 0;
}

int
pci_vfio_is_enabled(void)
{
	return vfio_cfg.vfio_enabled;
}
#endif