aboutsummaryrefslogtreecommitdiff
path: root/hw/vfio/helpers.c
blob: ea15c79db0a3643f260fc1ce3abfeaa7001ab306 (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
/*
 * low level and IOMMU backend agnostic helpers used by VFIO devices,
 * related to regions, interrupts, capabilities
 *
 * Copyright Red Hat, Inc. 2012
 *
 * Authors:
 *  Alex Williamson <alex.williamson@redhat.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 * Based on qemu-kvm device-assignment:
 *  Adapted for KVM by Qumranet.
 *  Copyright (c) 2007, Neocleus, Alex Novik (alex@neocleus.com)
 *  Copyright (c) 2007, Neocleus, Guy Zana (guy@neocleus.com)
 *  Copyright (C) 2008, Qumranet, Amit Shah (amit.shah@qumranet.com)
 *  Copyright (C) 2008, Red Hat, Amit Shah (amit.shah@redhat.com)
 *  Copyright (C) 2008, IBM, Muli Ben-Yehuda (muli@il.ibm.com)
 */

#include "qemu/osdep.h"
#include <sys/ioctl.h>

#include "hw/vfio/vfio-common.h"
#include "hw/hw.h"
#include "trace.h"
#include "qapi/error.h"
#include "qemu/error-report.h"
#include "monitor/monitor.h"

/*
 * Common VFIO interrupt disable
 */
void vfio_disable_irqindex(VFIODevice *vbasedev, int index)
{
    struct vfio_irq_set irq_set = {
        .argsz = sizeof(irq_set),
        .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_TRIGGER,
        .index = index,
        .start = 0,
        .count = 0,
    };

    ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
}

void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index)
{
    struct vfio_irq_set irq_set = {
        .argsz = sizeof(irq_set),
        .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_UNMASK,
        .index = index,
        .start = 0,
        .count = 1,
    };

    ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
}

void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index)
{
    struct vfio_irq_set irq_set = {
        .argsz = sizeof(irq_set),
        .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_MASK,
        .index = index,
        .start = 0,
        .count = 1,
    };

    ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
}

static inline const char *action_to_str(int action)
{
    switch (action) {
    case VFIO_IRQ_SET_ACTION_MASK:
        return "MASK";
    case VFIO_IRQ_SET_ACTION_UNMASK:
        return "UNMASK";
    case VFIO_IRQ_SET_ACTION_TRIGGER:
        return "TRIGGER";
    default:
        return "UNKNOWN ACTION";
    }
}

static const char *index_to_str(VFIODevice *vbasedev, int index)
{
    if (vbasedev->type != VFIO_DEVICE_TYPE_PCI) {
        return NULL;
    }

    switch (index) {
    case VFIO_PCI_INTX_IRQ_INDEX:
        return "INTX";
    case VFIO_PCI_MSI_IRQ_INDEX:
        return "MSI";
    case VFIO_PCI_MSIX_IRQ_INDEX:
        return "MSIX";
    case VFIO_PCI_ERR_IRQ_INDEX:
        return "ERR";
    case VFIO_PCI_REQ_IRQ_INDEX:
        return "REQ";
    default:
        return NULL;
    }
}

bool vfio_set_irq_signaling(VFIODevice *vbasedev, int index, int subindex,
                            int action, int fd, Error **errp)
{
    ERRP_GUARD();
    g_autofree struct vfio_irq_set *irq_set = NULL;
    int argsz;
    const char *name;
    int32_t *pfd;

    argsz = sizeof(*irq_set) + sizeof(*pfd);

    irq_set = g_malloc0(argsz);
    irq_set->argsz = argsz;
    irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD | action;
    irq_set->index = index;
    irq_set->start = subindex;
    irq_set->count = 1;
    pfd = (int32_t *)&irq_set->data;
    *pfd = fd;

    if (!ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, irq_set)) {
        return true;
    }

    error_setg_errno(errp, errno, "VFIO_DEVICE_SET_IRQS failure");

    name = index_to_str(vbasedev, index);
    if (name) {
        error_prepend(errp, "%s-%d: ", name, subindex);
    } else {
        error_prepend(errp, "index %d-%d: ", index, subindex);
    }
    error_prepend(errp,
                  "Failed to %s %s eventfd signaling for interrupt ",
                  fd < 0 ? "tear down" : "set up", action_to_str(action));
    return false;
}

/*
 * IO Port/MMIO - Beware of the endians, VFIO is always little endian
 */
void vfio_region_write(void *opaque, hwaddr addr,
                       uint64_t data, unsigned size)
{
    VFIORegion *region = opaque;
    VFIODevice *vbasedev = region->vbasedev;
    union {
        uint8_t byte;
        uint16_t word;
        uint32_t dword;
        uint64_t qword;
    } buf;

    switch (size) {
    case 1:
        buf.byte = data;
        break;
    case 2:
        buf.word = cpu_to_le16(data);
        break;
    case 4:
        buf.dword = cpu_to_le32(data);
        break;
    case 8:
        buf.qword = cpu_to_le64(data);
        break;
    default:
        hw_error("vfio: unsupported write size, %u bytes", size);
        break;
    }

    if (pwrite(vbasedev->fd, &buf, size, region->fd_offset + addr) != size) {
        error_report("%s(%s:region%d+0x%"HWADDR_PRIx", 0x%"PRIx64
                     ",%d) failed: %m",
                     __func__, vbasedev->name, region->nr,
                     addr, data, size);
    }

    trace_vfio_region_write(vbasedev->name, region->nr, addr, data, size);

    /*
     * A read or write to a BAR always signals an INTx EOI.  This will
     * do nothing if not pending (including not in INTx mode).  We assume
     * that a BAR access is in response to an interrupt and that BAR
     * accesses will service the interrupt.  Unfortunately, we don't know
     * which access will service the interrupt, so we're potentially
     * getting quite a few host interrupts per guest interrupt.
     */
    vbasedev->ops->vfio_eoi(vbasedev);
}

uint64_t vfio_region_read(void *opaque,
                          hwaddr addr, unsigned size)
{
    VFIORegion *region = opaque;
    VFIODevice *vbasedev = region->vbasedev;
    union {
        uint8_t byte;
        uint16_t word;
        uint32_t dword;
        uint64_t qword;
    } buf;
    uint64_t data = 0;

    if (pread(vbasedev->fd, &buf, size, region->fd_offset + addr) != size) {
        error_report("%s(%s:region%d+0x%"HWADDR_PRIx", %d) failed: %m",
                     __func__, vbasedev->name, region->nr,
                     addr, size);
        return (uint64_t)-1;
    }
    switch (size) {
    case 1:
        data = buf.byte;
        break;
    case 2:
        data = le16_to_cpu(buf.word);
        break;
    case 4:
        data = le32_to_cpu(buf.dword);
        break;
    case 8:
        data = le64_to_cpu(buf.qword);
        break;
    default:
        hw_error("vfio: unsupported read size, %u bytes", size);
        break;
    }

    trace_vfio_region_read(vbasedev->name, region->nr, addr, size, data);

    /* Same as write above */
    vbasedev->ops->vfio_eoi(vbasedev);

    return data;
}

const MemoryRegionOps vfio_region_ops = {
    .read = vfio_region_read,
    .write = vfio_region_write,
    .endianness = DEVICE_LITTLE_ENDIAN,
    .valid = {
        .min_access_size = 1,
        .max_access_size = 8,
    },
    .impl = {
        .min_access_size = 1,
        .max_access_size = 8,
    },
};

int vfio_bitmap_alloc(VFIOBitmap *vbmap, hwaddr size)
{
    vbmap->pages = REAL_HOST_PAGE_ALIGN(size) / qemu_real_host_page_size();
    vbmap->size = ROUND_UP(vbmap->pages, sizeof(__u64) * BITS_PER_BYTE) /
                                         BITS_PER_BYTE;
    vbmap->bitmap = g_try_malloc0(vbmap->size);
    if (!vbmap->bitmap) {
        return -ENOMEM;
    }

    return 0;
}

struct vfio_info_cap_header *
vfio_get_cap(void *ptr, uint32_t cap_offset, uint16_t id)
{
    struct vfio_info_cap_header *hdr;

    for (hdr = ptr + cap_offset; hdr != ptr; hdr = ptr + hdr->next) {
        if (hdr->id == id) {
            return hdr;
        }
    }

    return NULL;
}

struct vfio_info_cap_header *
vfio_get_region_info_cap(struct vfio_region_info *info, uint16_t id)
{
    if (!(info->flags & VFIO_REGION_INFO_FLAG_CAPS)) {
        return NULL;
    }

    return vfio_get_cap((void *)info, info->cap_offset, id);
}

struct vfio_info_cap_header *
vfio_get_device_info_cap(struct vfio_device_info *info, uint16_t id)
{
    if (!(info->flags & VFIO_DEVICE_FLAGS_CAPS)) {
        return NULL;
    }

    return vfio_get_cap((void *)info, info->cap_offset, id);
}

static int vfio_setup_region_sparse_mmaps(VFIORegion *region,
                                          struct vfio_region_info *info)
{
    struct vfio_info_cap_header *hdr;
    struct vfio_region_info_cap_sparse_mmap *sparse;
    int i, j;

    hdr = vfio_get_region_info_cap(info, VFIO_REGION_INFO_CAP_SPARSE_MMAP);
    if (!hdr) {
        return -ENODEV;
    }

    sparse = container_of(hdr, struct vfio_region_info_cap_sparse_mmap, header);

    trace_vfio_region_sparse_mmap_header(region->vbasedev->name,
                                         region->nr, sparse->nr_areas);

    region->mmaps = g_new0(VFIOMmap, sparse->nr_areas);

    for (i = 0, j = 0; i < sparse->nr_areas; i++) {
        if (sparse->areas[i].size) {
            trace_vfio_region_sparse_mmap_entry(i, sparse->areas[i].offset,
                                            sparse->areas[i].offset +
                                            sparse->areas[i].size - 1);
            region->mmaps[j].offset = sparse->areas[i].offset;
            region->mmaps[j].size = sparse->areas[i].size;
            j++;
        }
    }

    region->nr_mmaps = j;
    region->mmaps = g_realloc(region->mmaps, j * sizeof(VFIOMmap));

    return 0;
}

int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *region,
                      int index, const char *name)
{
    g_autofree struct vfio_region_info *info = NULL;
    int ret;

    ret = vfio_get_region_info(vbasedev, index, &info);
    if (ret) {
        return ret;
    }

    region->vbasedev = vbasedev;
    region->flags = info->flags;
    region->size = info->size;
    region->fd_offset = info->offset;
    region->nr = index;

    if (region->size) {
        region->mem = g_new0(MemoryRegion, 1);
        memory_region_init_io(region->mem, obj, &vfio_region_ops,
                              region, name, region->size);

        if (!vbasedev->no_mmap &&
            region->flags & VFIO_REGION_INFO_FLAG_MMAP) {

            ret = vfio_setup_region_sparse_mmaps(region, info);

            if (ret) {
                region->nr_mmaps = 1;
                region->mmaps = g_new0(VFIOMmap, region->nr_mmaps);
                region->mmaps[0].offset = 0;
                region->mmaps[0].size = region->size;
            }
        }
    }

    trace_vfio_region_setup(vbasedev->name, index, name,
                            region->flags, region->fd_offset, region->size);
    return 0;
}

static void vfio_subregion_unmap(VFIORegion *region, int index)
{
    trace_vfio_region_unmap(memory_region_name(&region->mmaps[index].mem),
                            region->mmaps[index].offset,
                            region->mmaps[index].offset +
                            region->mmaps[index].size - 1);
    memory_region_del_subregion(region->mem, &region->mmaps[index].mem);
    munmap(region->mmaps[index].mmap, region->mmaps[index].size);
    object_unparent(OBJECT(&region->mmaps[index].mem));
    region->mmaps[index].mmap = NULL;
}

int vfio_region_mmap(VFIORegion *region)
{
    int i, prot = 0;
    char *name;

    if (!region->mem) {
        return 0;
    }

    prot |= region->flags & VFIO_REGION_INFO_FLAG_READ ? PROT_READ : 0;
    prot |= region->flags & VFIO_REGION_INFO_FLAG_WRITE ? PROT_WRITE : 0;

    for (i = 0; i < region->nr_mmaps; i++) {
        region->mmaps[i].mmap = mmap(NULL, region->mmaps[i].size, prot,
                                     MAP_SHARED, region->vbasedev->fd,
                                     region->fd_offset +
                                     region->mmaps[i].offset);
        if (region->mmaps[i].mmap == MAP_FAILED) {
            int ret = -errno;

            trace_vfio_region_mmap_fault(memory_region_name(region->mem), i,
                                         region->fd_offset +
                                         region->mmaps[i].offset,
                                         region->fd_offset +
                                         region->mmaps[i].offset +
                                         region->mmaps[i].size - 1, ret);

            region->mmaps[i].mmap = NULL;

            for (i--; i >= 0; i--) {
                vfio_subregion_unmap(region, i);
            }

            return ret;
        }

        name = g_strdup_printf("%s mmaps[%d]",
                               memory_region_name(region->mem), i);
        memory_region_init_ram_device_ptr(&region->mmaps[i].mem,
                                          memory_region_owner(region->mem),
                                          name, region->mmaps[i].size,
                                          region->mmaps[i].mmap);
        g_free(name);
        memory_region_add_subregion(region->mem, region->mmaps[i].offset,
                                    &region->mmaps[i].mem);

        trace_vfio_region_mmap(memory_region_name(&region->mmaps[i].mem),
                               region->mmaps[i].offset,
                               region->mmaps[i].offset +
                               region->mmaps[i].size - 1);
    }

    return 0;
}

void vfio_region_unmap(VFIORegion *region)
{
    int i;

    if (!region->mem) {
        return;
    }

    for (i = 0; i < region->nr_mmaps; i++) {
        if (region->mmaps[i].mmap) {
            vfio_subregion_unmap(region, i);
        }
    }
}

void vfio_region_exit(VFIORegion *region)
{
    int i;

    if (!region->mem) {
        return;
    }

    for (i = 0; i < region->nr_mmaps; i++) {
        if (region->mmaps[i].mmap) {
            memory_region_del_subregion(region->mem, &region->mmaps[i].mem);
        }
    }

    trace_vfio_region_exit(region->vbasedev->name, region->nr);
}

void vfio_region_finalize(VFIORegion *region)
{
    int i;

    if (!region->mem) {
        return;
    }

    for (i = 0; i < region->nr_mmaps; i++) {
        if (region->mmaps[i].mmap) {
            munmap(region->mmaps[i].mmap, region->mmaps[i].size);
            object_unparent(OBJECT(&region->mmaps[i].mem));
        }
    }

    object_unparent(OBJECT(region->mem));

    g_free(region->mem);
    g_free(region->mmaps);

    trace_vfio_region_finalize(region->vbasedev->name, region->nr);

    region->mem = NULL;
    region->mmaps = NULL;
    region->nr_mmaps = 0;
    region->size = 0;
    region->flags = 0;
    region->nr = 0;
}

void vfio_region_mmaps_set_enabled(VFIORegion *region, bool enabled)
{
    int i;

    if (!region->mem) {
        return;
    }

    for (i = 0; i < region->nr_mmaps; i++) {
        if (region->mmaps[i].mmap) {
            memory_region_set_enabled(&region->mmaps[i].mem, enabled);
        }
    }

    trace_vfio_region_mmaps_set_enabled(memory_region_name(region->mem),
                                        enabled);
}

int vfio_get_region_info(VFIODevice *vbasedev, int index,
                         struct vfio_region_info **info)
{
    size_t argsz = sizeof(struct vfio_region_info);

    *info = g_malloc0(argsz);

    (*info)->index = index;
retry:
    (*info)->argsz = argsz;

    if (ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, *info)) {
        g_free(*info);
        *info = NULL;
        return -errno;
    }

    if ((*info)->argsz > argsz) {
        argsz = (*info)->argsz;
        *info = g_realloc(*info, argsz);

        goto retry;
    }

    return 0;
}

int vfio_get_dev_region_info(VFIODevice *vbasedev, uint32_t type,
                             uint32_t subtype, struct vfio_region_info **info)
{
    int i;

    for (i = 0; i < vbasedev->num_regions; i++) {
        struct vfio_info_cap_header *hdr;
        struct vfio_region_info_cap_type *cap_type;

        if (vfio_get_region_info(vbasedev, i, info)) {
            continue;
        }

        hdr = vfio_get_region_info_cap(*info, VFIO_REGION_INFO_CAP_TYPE);
        if (!hdr) {
            g_free(*info);
            continue;
        }

        cap_type = container_of(hdr, struct vfio_region_info_cap_type, header);

        trace_vfio_get_dev_region(vbasedev->name, i,
                                  cap_type->type, cap_type->subtype);

        if (cap_type->type == type && cap_type->subtype == subtype) {
            return 0;
        }

        g_free(*info);
    }

    *info = NULL;
    return -ENODEV;
}

bool vfio_has_region_cap(VFIODevice *vbasedev, int region, uint16_t cap_type)
{
    g_autofree struct vfio_region_info *info = NULL;
    bool ret = false;

    if (!vfio_get_region_info(vbasedev, region, &info)) {
        if (vfio_get_region_info_cap(info, cap_type)) {
            ret = true;
        }
    }

    return ret;
}

bool vfio_device_get_name(VFIODevice *vbasedev, Error **errp)
{
    ERRP_GUARD();
    struct stat st;

    if (vbasedev->fd < 0) {
        if (stat(vbasedev->sysfsdev, &st) < 0) {
            error_setg_errno(errp, errno, "no such host device");
            error_prepend(errp, VFIO_MSG_PREFIX, vbasedev->sysfsdev);
            return false;
        }
        /* User may specify a name, e.g: VFIO platform device */
        if (!vbasedev->name) {
            vbasedev->name = g_path_get_basename(vbasedev->sysfsdev);
        }
    } else {
        if (!vbasedev->iommufd) {
            error_setg(errp, "Use FD passing only with iommufd backend");
            return false;
        }
        /*
         * Give a name with fd so any function printing out vbasedev->name
         * will not break.
         */
        if (!vbasedev->name) {
            vbasedev->name = g_strdup_printf("VFIO_FD%d", vbasedev->fd);
        }
    }

    return true;
}

void vfio_device_set_fd(VFIODevice *vbasedev, const char *str, Error **errp)
{
    ERRP_GUARD();
    int fd = monitor_fd_param(monitor_cur(), str, errp);

    if (fd < 0) {
        error_prepend(errp, "Could not parse remote object fd %s:", str);
        return;
    }
    vbasedev->fd = fd;
}

void vfio_device_init(VFIODevice *vbasedev, int type, VFIODeviceOps *ops,
                      DeviceState *dev, bool ram_discard)
{
    vbasedev->type = type;
    vbasedev->ops = ops;
    vbasedev->dev = dev;
    vbasedev->fd = -1;

    vbasedev->ram_block_discard_allowed = ram_discard;
}

int vfio_device_get_aw_bits(VFIODevice *vdev)
{
    /*
     * iova_ranges is a sorted list. For old kernels that support
     * VFIO but not support query of iova ranges, iova_ranges is NULL,
     * in this case HOST_IOMMU_DEVICE_CAP_AW_BITS_MAX(64) is returned.
     */
    GList *l = g_list_last(vdev->bcontainer->iova_ranges);

    if (l) {
        Range *range = l->data;
        return range_get_last_bit(range) + 1;
    }

    return HOST_IOMMU_DEVICE_CAP_AW_BITS_MAX;
}

bool vfio_device_is_mdev(VFIODevice *vbasedev)
{
    g_autofree char *subsys = NULL;
    g_autofree char *tmp = NULL;

    if (!vbasedev->sysfsdev) {
        return false;
    }

    tmp = g_strdup_printf("%s/subsystem", vbasedev->sysfsdev);
    subsys = realpath(tmp, NULL);
    return subsys && (strcmp(subsys, "/sys/bus/mdev") == 0);
}

bool vfio_device_hiod_realize(VFIODevice *vbasedev, Error **errp)
{
    HostIOMMUDevice *hiod = vbasedev->hiod;

    if (!hiod) {
        return true;
    }

    return HOST_IOMMU_DEVICE_GET_CLASS(hiod)->realize(hiod, vbasedev, errp);
}