forked from aliguori/qemu
-
Notifications
You must be signed in to change notification settings - Fork 12
/
Copy pathcommon.c
1406 lines (1173 loc) · 42 KB
/
common.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* generic functions used by VFIO devices
*
* Copyright Red Hat, Inc. 2012
*
* Authors:
* Alex Williamson <[email protected]>
*
* 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 ([email protected])
* Copyright (c) 2007, Neocleus, Guy Zana ([email protected])
* Copyright (C) 2008, Qumranet, Amit Shah ([email protected])
* Copyright (C) 2008, Red Hat, Amit Shah ([email protected])
* Copyright (C) 2008, IBM, Muli Ben-Yehuda ([email protected])
*/
#include "qemu/osdep.h"
#include <sys/ioctl.h>
#ifdef CONFIG_KVM
#include <linux/kvm.h>
#endif
#include <linux/vfio.h>
#include "hw/vfio/vfio-common.h"
#include "hw/vfio/vfio.h"
#include "exec/address-spaces.h"
#include "exec/memory.h"
#include "hw/hw.h"
#include "qemu/error-report.h"
#include "qemu/range.h"
#include "sysemu/kvm.h"
#include "trace.h"
struct vfio_group_head vfio_group_list =
QLIST_HEAD_INITIALIZER(vfio_group_list);
struct vfio_as_head vfio_address_spaces =
QLIST_HEAD_INITIALIZER(vfio_address_spaces);
#ifdef CONFIG_KVM
/*
* We have a single VFIO pseudo device per KVM VM. Once created it lives
* for the life of the VM. Closing the file descriptor only drops our
* reference to it and the device's reference to kvm. Therefore once
* initialized, this file descriptor is only released on QEMU exit and
* we'll re-use it should another vfio device be attached before then.
*/
static int vfio_kvm_device_fd = -1;
#endif
/*
* 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);
}
/*
* 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;
default:
hw_error("vfio: unsupported write size, %d 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;
default:
hw_error("vfio: unsupported read size, %d 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,
};
/*
* DMA - Mapping and unmapping for the "type1" IOMMU interface used on x86
*/
static int vfio_dma_unmap(VFIOContainer *container,
hwaddr iova, ram_addr_t size)
{
struct vfio_iommu_type1_dma_unmap unmap = {
.argsz = sizeof(unmap),
.flags = 0,
.iova = iova,
.size = size,
};
if (ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, &unmap)) {
error_report("VFIO_UNMAP_DMA: %d", -errno);
return -errno;
}
return 0;
}
static int vfio_dma_map(VFIOContainer *container, hwaddr iova,
ram_addr_t size, void *vaddr, bool readonly)
{
struct vfio_iommu_type1_dma_map map = {
.argsz = sizeof(map),
.flags = VFIO_DMA_MAP_FLAG_READ,
.vaddr = (__u64)(uintptr_t)vaddr,
.iova = iova,
.size = size,
};
if (!readonly) {
map.flags |= VFIO_DMA_MAP_FLAG_WRITE;
}
/*
* Try the mapping, if it fails with EBUSY, unmap the region and try
* again. This shouldn't be necessary, but we sometimes see it in
* the VGA ROM space.
*/
if (ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0 ||
(errno == EBUSY && vfio_dma_unmap(container, iova, size) == 0 &&
ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0)) {
return 0;
}
error_report("VFIO_MAP_DMA: %d", -errno);
return -errno;
}
static void vfio_host_win_add(VFIOContainer *container,
hwaddr min_iova, hwaddr max_iova,
uint64_t iova_pgsizes)
{
VFIOHostDMAWindow *hostwin;
QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) {
if (ranges_overlap(hostwin->min_iova,
hostwin->max_iova - hostwin->min_iova + 1,
min_iova,
max_iova - min_iova + 1)) {
hw_error("%s: Overlapped IOMMU are not enabled", __func__);
}
}
hostwin = g_malloc0(sizeof(*hostwin));
hostwin->min_iova = min_iova;
hostwin->max_iova = max_iova;
hostwin->iova_pgsizes = iova_pgsizes;
QLIST_INSERT_HEAD(&container->hostwin_list, hostwin, hostwin_next);
}
static int vfio_host_win_del(VFIOContainer *container, hwaddr min_iova,
hwaddr max_iova)
{
VFIOHostDMAWindow *hostwin;
QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) {
if (hostwin->min_iova == min_iova && hostwin->max_iova == max_iova) {
QLIST_REMOVE(hostwin, hostwin_next);
return 0;
}
}
return -1;
}
static bool vfio_listener_skipped_section(MemoryRegionSection *section)
{
return (!memory_region_is_ram(section->mr) &&
!memory_region_is_iommu(section->mr)) ||
/*
* Sizing an enabled 64-bit BAR can cause spurious mappings to
* addresses in the upper part of the 64-bit address space. These
* are never accessed by the CPU and beyond the address width of
* some IOMMU hardware. TODO: VFIO should tell us the IOMMU width.
*/
section->offset_within_address_space & (1ULL << 63);
}
static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
{
VFIOGuestIOMMU *giommu = container_of(n, VFIOGuestIOMMU, n);
VFIOContainer *container = giommu->container;
hwaddr iova = iotlb->iova + giommu->iommu_offset;
MemoryRegion *mr;
hwaddr xlat;
hwaddr len = iotlb->addr_mask + 1;
void *vaddr;
int ret;
trace_vfio_iommu_map_notify(iova, iova + iotlb->addr_mask);
if (iotlb->target_as != &address_space_memory) {
error_report("Wrong target AS \"%s\", only system memory is allowed",
iotlb->target_as->name ? iotlb->target_as->name : "none");
return;
}
/*
* The IOMMU TLB entry we have just covers translation through
* this IOMMU to its immediate target. We need to translate
* it the rest of the way through to memory.
*/
rcu_read_lock();
mr = address_space_translate(&address_space_memory,
iotlb->translated_addr,
&xlat, &len, iotlb->perm & IOMMU_WO);
if (!memory_region_is_ram(mr)) {
error_report("iommu map to non memory area %"HWADDR_PRIx"",
xlat);
goto out;
}
/*
* Translation truncates length to the IOMMU page size,
* check that it did not truncate too much.
*/
if (len & iotlb->addr_mask) {
error_report("iommu has granularity incompatible with target AS");
goto out;
}
if ((iotlb->perm & IOMMU_RW) != IOMMU_NONE) {
vaddr = memory_region_get_ram_ptr(mr) + xlat;
ret = vfio_dma_map(container, iova,
iotlb->addr_mask + 1, vaddr,
!(iotlb->perm & IOMMU_WO) || mr->readonly);
if (ret) {
error_report("vfio_dma_map(%p, 0x%"HWADDR_PRIx", "
"0x%"HWADDR_PRIx", %p) = %d (%m)",
container, iova,
iotlb->addr_mask + 1, vaddr, ret);
}
} else {
ret = vfio_dma_unmap(container, iova, iotlb->addr_mask + 1);
if (ret) {
error_report("vfio_dma_unmap(%p, 0x%"HWADDR_PRIx", "
"0x%"HWADDR_PRIx") = %d (%m)",
container, iova,
iotlb->addr_mask + 1, ret);
}
}
out:
rcu_read_unlock();
}
static void vfio_listener_region_add(MemoryListener *listener,
MemoryRegionSection *section)
{
VFIOContainer *container = container_of(listener, VFIOContainer, listener);
hwaddr iova, end;
Int128 llend, llsize;
void *vaddr;
int ret;
VFIOHostDMAWindow *hostwin;
bool hostwin_found;
if (vfio_listener_skipped_section(section)) {
trace_vfio_listener_region_add_skip(
section->offset_within_address_space,
section->offset_within_address_space +
int128_get64(int128_sub(section->size, int128_one())));
return;
}
if (unlikely((section->offset_within_address_space & ~TARGET_PAGE_MASK) !=
(section->offset_within_region & ~TARGET_PAGE_MASK))) {
error_report("%s received unaligned region", __func__);
return;
}
iova = TARGET_PAGE_ALIGN(section->offset_within_address_space);
llend = int128_make64(section->offset_within_address_space);
llend = int128_add(llend, section->size);
llend = int128_and(llend, int128_exts64(TARGET_PAGE_MASK));
if (int128_ge(int128_make64(iova), llend)) {
return;
}
end = int128_get64(int128_sub(llend, int128_one()));
if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) {
VFIOHostDMAWindow *hostwin;
hwaddr pgsize = 0;
/* For now intersections are not allowed, we may relax this later */
QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) {
if (ranges_overlap(hostwin->min_iova,
hostwin->max_iova - hostwin->min_iova + 1,
section->offset_within_address_space,
int128_get64(section->size))) {
ret = -1;
goto fail;
}
}
ret = vfio_spapr_create_window(container, section, &pgsize);
if (ret) {
goto fail;
}
vfio_host_win_add(container, section->offset_within_address_space,
section->offset_within_address_space +
int128_get64(section->size) - 1, pgsize);
}
hostwin_found = false;
QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) {
if (hostwin->min_iova <= iova && end <= hostwin->max_iova) {
hostwin_found = true;
break;
}
}
if (!hostwin_found) {
error_report("vfio: IOMMU container %p can't map guest IOVA region"
" 0x%"HWADDR_PRIx"..0x%"HWADDR_PRIx,
container, iova, end);
ret = -EFAULT;
goto fail;
}
memory_region_ref(section->mr);
if (memory_region_is_iommu(section->mr)) {
VFIOGuestIOMMU *giommu;
trace_vfio_listener_region_add_iommu(iova, end);
/*
* FIXME: For VFIO iommu types which have KVM acceleration to
* avoid bouncing all map/unmaps through qemu this way, this
* would be the right place to wire that up (tell the KVM
* device emulation the VFIO iommu handles to use).
*/
giommu = g_malloc0(sizeof(*giommu));
giommu->iommu = section->mr;
giommu->iommu_offset = section->offset_within_address_space -
section->offset_within_region;
giommu->container = container;
giommu->n.notify = vfio_iommu_map_notify;
giommu->n.notifier_flags = IOMMU_NOTIFIER_ALL;
QLIST_INSERT_HEAD(&container->giommu_list, giommu, giommu_next);
memory_region_register_iommu_notifier(giommu->iommu, &giommu->n);
memory_region_iommu_replay(giommu->iommu, &giommu->n, false);
return;
}
/* Here we assume that memory_region_is_ram(section->mr)==true */
vaddr = memory_region_get_ram_ptr(section->mr) +
section->offset_within_region +
(iova - section->offset_within_address_space);
trace_vfio_listener_region_add_ram(iova, end, vaddr);
llsize = int128_sub(llend, int128_make64(iova));
ret = vfio_dma_map(container, iova, int128_get64(llsize),
vaddr, section->readonly);
if (ret) {
error_report("vfio_dma_map(%p, 0x%"HWADDR_PRIx", "
"0x%"HWADDR_PRIx", %p) = %d (%m)",
container, iova, int128_get64(llsize), vaddr, ret);
goto fail;
}
return;
fail:
/*
* On the initfn path, store the first error in the container so we
* can gracefully fail. Runtime, there's not much we can do other
* than throw a hardware error.
*/
if (!container->initialized) {
if (!container->error) {
container->error = ret;
}
} else {
hw_error("vfio: DMA mapping failed, unable to continue");
}
}
static void vfio_listener_region_del(MemoryListener *listener,
MemoryRegionSection *section)
{
VFIOContainer *container = container_of(listener, VFIOContainer, listener);
hwaddr iova, end;
Int128 llend, llsize;
int ret;
if (vfio_listener_skipped_section(section)) {
trace_vfio_listener_region_del_skip(
section->offset_within_address_space,
section->offset_within_address_space +
int128_get64(int128_sub(section->size, int128_one())));
return;
}
if (unlikely((section->offset_within_address_space & ~TARGET_PAGE_MASK) !=
(section->offset_within_region & ~TARGET_PAGE_MASK))) {
error_report("%s received unaligned region", __func__);
return;
}
if (memory_region_is_iommu(section->mr)) {
VFIOGuestIOMMU *giommu;
QLIST_FOREACH(giommu, &container->giommu_list, giommu_next) {
if (giommu->iommu == section->mr) {
memory_region_unregister_iommu_notifier(giommu->iommu,
&giommu->n);
QLIST_REMOVE(giommu, giommu_next);
g_free(giommu);
break;
}
}
/*
* FIXME: We assume the one big unmap below is adequate to
* remove any individual page mappings in the IOMMU which
* might have been copied into VFIO. This works for a page table
* based IOMMU where a big unmap flattens a large range of IO-PTEs.
* That may not be true for all IOMMU types.
*/
}
iova = TARGET_PAGE_ALIGN(section->offset_within_address_space);
llend = int128_make64(section->offset_within_address_space);
llend = int128_add(llend, section->size);
llend = int128_and(llend, int128_exts64(TARGET_PAGE_MASK));
if (int128_ge(int128_make64(iova), llend)) {
return;
}
end = int128_get64(int128_sub(llend, int128_one()));
llsize = int128_sub(llend, int128_make64(iova));
trace_vfio_listener_region_del(iova, end);
ret = vfio_dma_unmap(container, iova, int128_get64(llsize));
memory_region_unref(section->mr);
if (ret) {
error_report("vfio_dma_unmap(%p, 0x%"HWADDR_PRIx", "
"0x%"HWADDR_PRIx") = %d (%m)",
container, iova, int128_get64(llsize), ret);
}
if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) {
vfio_spapr_remove_window(container,
section->offset_within_address_space);
if (vfio_host_win_del(container,
section->offset_within_address_space,
section->offset_within_address_space +
int128_get64(section->size) - 1) < 0) {
hw_error("%s: Cannot delete missing window at %"HWADDR_PRIx,
__func__, section->offset_within_address_space);
}
}
}
static const MemoryListener vfio_memory_listener = {
.region_add = vfio_listener_region_add,
.region_del = vfio_listener_region_del,
};
static void vfio_listener_release(VFIOContainer *container)
{
memory_listener_unregister(&container->listener);
if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) {
memory_listener_unregister(&container->prereg_listener);
}
}
static struct vfio_info_cap_header *
vfio_get_region_info_cap(struct vfio_region_info *info, uint16_t id)
{
struct vfio_info_cap_header *hdr;
void *ptr = info;
if (!(info->flags & VFIO_REGION_INFO_FLAG_CAPS)) {
return NULL;
}
for (hdr = ptr + info->cap_offset; hdr != ptr; hdr = ptr + hdr->next) {
if (hdr->id == id) {
return hdr;
}
}
return NULL;
}
static void 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;
hdr = vfio_get_region_info_cap(info, VFIO_REGION_INFO_CAP_SPARSE_MMAP);
if (!hdr) {
return;
}
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->nr_mmaps = sparse->nr_areas;
region->mmaps = g_new0(VFIOMmap, region->nr_mmaps);
for (i = 0; i < region->nr_mmaps; i++) {
region->mmaps[i].offset = sparse->areas[i].offset;
region->mmaps[i].size = sparse->areas[i].size;
trace_vfio_region_sparse_mmap_entry(i, region->mmaps[i].offset,
region->mmaps[i].offset +
region->mmaps[i].size);
}
}
int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *region,
int index, const char *name)
{
struct vfio_region_info *info;
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 &&
!(region->size & ~qemu_real_host_page_mask)) {
vfio_setup_region_sparse_mmaps(region, info);
if (!region->nr_mmaps) {
region->nr_mmaps = 1;
region->mmaps = g_new0(VFIOMmap, region->nr_mmaps);
region->mmaps[0].offset = 0;
region->mmaps[0].size = region->size;
}
}
}
g_free(info);
trace_vfio_region_setup(vbasedev->name, index, name,
region->flags, region->fd_offset, region->size);
return 0;
}
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--) {
memory_region_del_subregion(region->mem, ®ion->mmaps[i].mem);
munmap(region->mmaps[i].mmap, region->mmaps[i].size);
object_unparent(OBJECT(®ion->mmaps[i].mem));
region->mmaps[i].mmap = NULL;
}
return ret;
}
name = g_strdup_printf("%s mmaps[%d]",
memory_region_name(region->mem), i);
memory_region_init_ram_ptr(®ion->mmaps[i].mem,
memory_region_owner(region->mem),
name, region->mmaps[i].size,
region->mmaps[i].mmap);
g_free(name);
memory_region_set_skip_dump(®ion->mmaps[i].mem);
memory_region_add_subregion(region->mem, region->mmaps[i].offset,
®ion->mmaps[i].mem);
trace_vfio_region_mmap(memory_region_name(®ion->mmaps[i].mem),
region->mmaps[i].offset,
region->mmaps[i].offset +
region->mmaps[i].size - 1);
}
return 0;
}
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, ®ion->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(®ion->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);
}
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(®ion->mmaps[i].mem, enabled);
}
}
trace_vfio_region_mmaps_set_enabled(memory_region_name(region->mem),
enabled);
}
void vfio_reset_handler(void *opaque)
{
VFIOGroup *group;
VFIODevice *vbasedev;
QLIST_FOREACH(group, &vfio_group_list, next) {
QLIST_FOREACH(vbasedev, &group->device_list, next) {
vbasedev->ops->vfio_compute_needs_reset(vbasedev);
}
}
QLIST_FOREACH(group, &vfio_group_list, next) {
QLIST_FOREACH(vbasedev, &group->device_list, next) {
if (vbasedev->needs_reset) {
vbasedev->ops->vfio_hot_reset_multi(vbasedev);
}
}
}
}
static void vfio_kvm_device_add_group(VFIOGroup *group)
{
#ifdef CONFIG_KVM
struct kvm_device_attr attr = {
.group = KVM_DEV_VFIO_GROUP,
.attr = KVM_DEV_VFIO_GROUP_ADD,
.addr = (uint64_t)(unsigned long)&group->fd,
};
if (!kvm_enabled()) {
return;
}
if (vfio_kvm_device_fd < 0) {
struct kvm_create_device cd = {
.type = KVM_DEV_TYPE_VFIO,
};
if (kvm_vm_ioctl(kvm_state, KVM_CREATE_DEVICE, &cd)) {
error_report("Failed to create KVM VFIO device: %m");
return;
}
vfio_kvm_device_fd = cd.fd;
}
if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) {
error_report("Failed to add group %d to KVM VFIO device: %m",
group->groupid);
}
#endif
}
static void vfio_kvm_device_del_group(VFIOGroup *group)
{
#ifdef CONFIG_KVM
struct kvm_device_attr attr = {
.group = KVM_DEV_VFIO_GROUP,
.attr = KVM_DEV_VFIO_GROUP_DEL,
.addr = (uint64_t)(unsigned long)&group->fd,
};
if (vfio_kvm_device_fd < 0) {
return;
}
if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) {
error_report("Failed to remove group %d from KVM VFIO device: %m",
group->groupid);
}
#endif
}
static VFIOAddressSpace *vfio_get_address_space(AddressSpace *as)
{
VFIOAddressSpace *space;
QLIST_FOREACH(space, &vfio_address_spaces, list) {
if (space->as == as) {
return space;
}
}
/* No suitable VFIOAddressSpace, create a new one */
space = g_malloc0(sizeof(*space));
space->as = as;
QLIST_INIT(&space->containers);
QLIST_INSERT_HEAD(&vfio_address_spaces, space, list);
return space;
}
static void vfio_put_address_space(VFIOAddressSpace *space)
{
if (QLIST_EMPTY(&space->containers)) {
QLIST_REMOVE(space, list);
g_free(space);
}
}
static int vfio_connect_container(VFIOGroup *group, AddressSpace *as)
{
VFIOContainer *container;
int ret, fd;
VFIOAddressSpace *space;
space = vfio_get_address_space(as);
QLIST_FOREACH(container, &space->containers, next) {
if (!ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &container->fd)) {
group->container = container;
QLIST_INSERT_HEAD(&container->group_list, group, container_next);
return 0;
}
}
fd = qemu_open("/dev/vfio/vfio", O_RDWR);
if (fd < 0) {
error_report("vfio: failed to open /dev/vfio/vfio: %m");
ret = -errno;
goto put_space_exit;
}
ret = ioctl(fd, VFIO_GET_API_VERSION);
if (ret != VFIO_API_VERSION) {
error_report("vfio: supported vfio version: %d, "
"reported version: %d", VFIO_API_VERSION, ret);
ret = -EINVAL;
goto close_fd_exit;
}
container = g_malloc0(sizeof(*container));
container->space = space;
container->fd = fd;
if (ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_TYPE1_IOMMU) ||
ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_TYPE1v2_IOMMU)) {
bool v2 = !!ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_TYPE1v2_IOMMU);
struct vfio_iommu_type1_info info;
ret = ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &fd);
if (ret) {
error_report("vfio: failed to set group container: %m");
ret = -errno;
goto free_container_exit;
}
container->iommu_type = v2 ? VFIO_TYPE1v2_IOMMU : VFIO_TYPE1_IOMMU;
ret = ioctl(fd, VFIO_SET_IOMMU, container->iommu_type);
if (ret) {
error_report("vfio: failed to set iommu for container: %m");
ret = -errno;
goto free_container_exit;
}
/*
* FIXME: This assumes that a Type1 IOMMU can map any 64-bit
* IOVA whatsoever. That's not actually true, but the current
* kernel interface doesn't tell us what it can map, and the
* existing Type1 IOMMUs generally support any IOVA we're
* going to actually try in practice.
*/
info.argsz = sizeof(info);
ret = ioctl(fd, VFIO_IOMMU_GET_INFO, &info);
/* Ignore errors */
if (ret || !(info.flags & VFIO_IOMMU_INFO_PGSIZES)) {
/* Assume 4k IOVA page size */
info.iova_pgsizes = 4096;
}
vfio_host_win_add(container, 0, (hwaddr)-1, info.iova_pgsizes);
} else if (ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_IOMMU) ||
ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_v2_IOMMU)) {
struct vfio_iommu_spapr_tce_info info;
bool v2 = !!ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_v2_IOMMU);
ret = ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &fd);
if (ret) {
error_report("vfio: failed to set group container: %m");
ret = -errno;
goto free_container_exit;
}
container->iommu_type =
v2 ? VFIO_SPAPR_TCE_v2_IOMMU : VFIO_SPAPR_TCE_IOMMU;
ret = ioctl(fd, VFIO_SET_IOMMU, container->iommu_type);
if (ret) {
error_report("vfio: failed to set iommu for container: %m");
ret = -errno;
goto free_container_exit;
}
/*
* The host kernel code implementing VFIO_IOMMU_DISABLE is called
* when container fd is closed so we do not call it explicitly
* in this file.
*/
if (!v2) {
ret = ioctl(fd, VFIO_IOMMU_ENABLE);
if (ret) {
error_report("vfio: failed to enable container: %m");