-
Notifications
You must be signed in to change notification settings - Fork 62.7k
Expand file tree
/
Copy pathvfio.h
More file actions
1902 lines (1759 loc) · 73.3 KB
/
vfio.h
File metadata and controls
1902 lines (1759 loc) · 73.3 KB
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
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
/*
* VFIO API definition
*
* Copyright (C) 2012 Red Hat, Inc. All rights reserved.
* Author: Alex Williamson <alex.williamson@redhat.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#ifndef _UAPIVFIO_H
#define _UAPIVFIO_H
#include <linux/types.h>
#include <linux/ioctl.h>
#include <linux/stddef.h>
#define VFIO_API_VERSION 0
/* Kernel & User level defines for VFIO IOCTLs. */
/* Extensions */
#define VFIO_TYPE1_IOMMU 1
#define VFIO_SPAPR_TCE_IOMMU 2
#define VFIO_TYPE1v2_IOMMU 3
/*
* IOMMU enforces DMA cache coherence (ex. PCIe NoSnoop stripping). This
* capability is subject to change as groups are added or removed.
*/
#define VFIO_DMA_CC_IOMMU 4
/* Check if EEH is supported */
#define VFIO_EEH 5
/* Two-stage IOMMU */
#define __VFIO_RESERVED_TYPE1_NESTING_IOMMU 6 /* Implies v2 */
#define VFIO_SPAPR_TCE_v2_IOMMU 7
/*
* The No-IOMMU IOMMU offers no translation or isolation for devices and
* supports no ioctls outside of VFIO_CHECK_EXTENSION. Use of VFIO's No-IOMMU
* code will taint the host kernel and should be used with extreme caution.
*/
#define VFIO_NOIOMMU_IOMMU 8
/* Supports VFIO_DMA_UNMAP_FLAG_ALL */
#define VFIO_UNMAP_ALL 9
/*
* Supports the vaddr flag for DMA map and unmap. Not supported for mediated
* devices, so this capability is subject to change as groups are added or
* removed.
*/
#define VFIO_UPDATE_VADDR 10
/*
* The IOCTL interface is designed for extensibility by embedding the
* structure length (argsz) and flags into structures passed between
* kernel and userspace. We therefore use the _IO() macro for these
* defines to avoid implicitly embedding a size into the ioctl request.
* As structure fields are added, argsz will increase to match and flag
* bits will be defined to indicate additional fields with valid data.
* It's *always* the caller's responsibility to indicate the size of
* the structure passed by setting argsz appropriately.
*/
#define VFIO_TYPE (';')
#define VFIO_BASE 100
/*
* For extension of INFO ioctls, VFIO makes use of a capability chain
* designed after PCI/e capabilities. A flag bit indicates whether
* this capability chain is supported and a field defined in the fixed
* structure defines the offset of the first capability in the chain.
* This field is only valid when the corresponding bit in the flags
* bitmap is set. This offset field is relative to the start of the
* INFO buffer, as is the next field within each capability header.
* The id within the header is a shared address space per INFO ioctl,
* while the version field is specific to the capability id. The
* contents following the header are specific to the capability id.
*/
struct vfio_info_cap_header {
__u16 id; /* Identifies capability */
__u16 version; /* Version specific to the capability ID */
__u32 next; /* Offset of next capability */
};
/*
* Callers of INFO ioctls passing insufficiently sized buffers will see
* the capability chain flag bit set, a zero value for the first capability
* offset (if available within the provided argsz), and argsz will be
* updated to report the necessary buffer size. For compatibility, the
* INFO ioctl will not report error in this case, but the capability chain
* will not be available.
*/
/* -------- IOCTLs for VFIO file descriptor (/dev/vfio/vfio) -------- */
/**
* VFIO_GET_API_VERSION - _IO(VFIO_TYPE, VFIO_BASE + 0)
*
* Report the version of the VFIO API. This allows us to bump the entire
* API version should we later need to add or change features in incompatible
* ways.
* Return: VFIO_API_VERSION
* Availability: Always
*/
#define VFIO_GET_API_VERSION _IO(VFIO_TYPE, VFIO_BASE + 0)
/**
* VFIO_CHECK_EXTENSION - _IOW(VFIO_TYPE, VFIO_BASE + 1, __u32)
*
* Check whether an extension is supported.
* Return: 0 if not supported, 1 (or some other positive integer) if supported.
* Availability: Always
*/
#define VFIO_CHECK_EXTENSION _IO(VFIO_TYPE, VFIO_BASE + 1)
/**
* VFIO_SET_IOMMU - _IOW(VFIO_TYPE, VFIO_BASE + 2, __s32)
*
* Set the iommu to the given type. The type must be supported by an
* iommu driver as verified by calling CHECK_EXTENSION using the same
* type. A group must be set to this file descriptor before this
* ioctl is available. The IOMMU interfaces enabled by this call are
* specific to the value set.
* Return: 0 on success, -errno on failure
* Availability: When VFIO group attached
*/
#define VFIO_SET_IOMMU _IO(VFIO_TYPE, VFIO_BASE + 2)
/* -------- IOCTLs for GROUP file descriptors (/dev/vfio/$GROUP) -------- */
/**
* VFIO_GROUP_GET_STATUS - _IOR(VFIO_TYPE, VFIO_BASE + 3,
* struct vfio_group_status)
*
* Retrieve information about the group. Fills in provided
* struct vfio_group_info. Caller sets argsz.
* Return: 0 on success, -errno on failure.
* Availability: Always
*/
struct vfio_group_status {
__u32 argsz;
__u32 flags;
#define VFIO_GROUP_FLAGS_VIABLE (1 << 0)
#define VFIO_GROUP_FLAGS_CONTAINER_SET (1 << 1)
};
#define VFIO_GROUP_GET_STATUS _IO(VFIO_TYPE, VFIO_BASE + 3)
/**
* VFIO_GROUP_SET_CONTAINER - _IOW(VFIO_TYPE, VFIO_BASE + 4, __s32)
*
* Set the container for the VFIO group to the open VFIO file
* descriptor provided. Groups may only belong to a single
* container. Containers may, at their discretion, support multiple
* groups. Only when a container is set are all of the interfaces
* of the VFIO file descriptor and the VFIO group file descriptor
* available to the user.
* Return: 0 on success, -errno on failure.
* Availability: Always
*/
#define VFIO_GROUP_SET_CONTAINER _IO(VFIO_TYPE, VFIO_BASE + 4)
/**
* VFIO_GROUP_UNSET_CONTAINER - _IO(VFIO_TYPE, VFIO_BASE + 5)
*
* Remove the group from the attached container. This is the
* opposite of the SET_CONTAINER call and returns the group to
* an initial state. All device file descriptors must be released
* prior to calling this interface. When removing the last group
* from a container, the IOMMU will be disabled and all state lost,
* effectively also returning the VFIO file descriptor to an initial
* state.
* Return: 0 on success, -errno on failure.
* Availability: When attached to container
*/
#define VFIO_GROUP_UNSET_CONTAINER _IO(VFIO_TYPE, VFIO_BASE + 5)
/**
* VFIO_GROUP_GET_DEVICE_FD - _IOW(VFIO_TYPE, VFIO_BASE + 6, char)
*
* Return a new file descriptor for the device object described by
* the provided string. The string should match a device listed in
* the devices subdirectory of the IOMMU group sysfs entry. The
* group containing the device must already be added to this context.
* Return: new file descriptor on success, -errno on failure.
* Availability: When attached to container
*/
#define VFIO_GROUP_GET_DEVICE_FD _IO(VFIO_TYPE, VFIO_BASE + 6)
/* --------------- IOCTLs for DEVICE file descriptors --------------- */
/**
* VFIO_DEVICE_GET_INFO - _IOR(VFIO_TYPE, VFIO_BASE + 7,
* struct vfio_device_info)
*
* Retrieve information about the device. Fills in provided
* struct vfio_device_info. Caller sets argsz.
* Return: 0 on success, -errno on failure.
*/
struct vfio_device_info {
__u32 argsz;
__u32 flags;
#define VFIO_DEVICE_FLAGS_RESET (1 << 0) /* Device supports reset */
#define VFIO_DEVICE_FLAGS_PCI (1 << 1) /* vfio-pci device */
#define VFIO_DEVICE_FLAGS_PLATFORM (1 << 2) /* vfio-platform device */
#define VFIO_DEVICE_FLAGS_AMBA (1 << 3) /* vfio-amba device */
#define VFIO_DEVICE_FLAGS_CCW (1 << 4) /* vfio-ccw device */
#define VFIO_DEVICE_FLAGS_AP (1 << 5) /* vfio-ap device */
#define VFIO_DEVICE_FLAGS_FSL_MC (1 << 6) /* vfio-fsl-mc device */
#define VFIO_DEVICE_FLAGS_CAPS (1 << 7) /* Info supports caps */
#define VFIO_DEVICE_FLAGS_CDX (1 << 8) /* vfio-cdx device */
__u32 num_regions; /* Max region index + 1 */
__u32 num_irqs; /* Max IRQ index + 1 */
__u32 cap_offset; /* Offset within info struct of first cap */
__u32 pad;
};
#define VFIO_DEVICE_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 7)
/*
* Vendor driver using Mediated device framework should provide device_api
* attribute in supported type attribute groups. Device API string should be one
* of the following corresponding to device flags in vfio_device_info structure.
*/
#define VFIO_DEVICE_API_PCI_STRING "vfio-pci"
#define VFIO_DEVICE_API_PLATFORM_STRING "vfio-platform"
#define VFIO_DEVICE_API_AMBA_STRING "vfio-amba"
#define VFIO_DEVICE_API_CCW_STRING "vfio-ccw"
#define VFIO_DEVICE_API_AP_STRING "vfio-ap"
/*
* The following capabilities are unique to s390 zPCI devices. Their contents
* are further-defined in vfio_zdev.h
*/
#define VFIO_DEVICE_INFO_CAP_ZPCI_BASE 1
#define VFIO_DEVICE_INFO_CAP_ZPCI_GROUP 2
#define VFIO_DEVICE_INFO_CAP_ZPCI_UTIL 3
#define VFIO_DEVICE_INFO_CAP_ZPCI_PFIP 4
/*
* The following VFIO_DEVICE_INFO capability reports support for PCIe AtomicOp
* completion to the root bus with supported widths provided via flags.
*/
#define VFIO_DEVICE_INFO_CAP_PCI_ATOMIC_COMP 5
struct vfio_device_info_cap_pci_atomic_comp {
struct vfio_info_cap_header header;
__u32 flags;
#define VFIO_PCI_ATOMIC_COMP32 (1 << 0)
#define VFIO_PCI_ATOMIC_COMP64 (1 << 1)
#define VFIO_PCI_ATOMIC_COMP128 (1 << 2)
__u32 reserved;
};
/**
* VFIO_DEVICE_GET_REGION_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 8,
* struct vfio_region_info)
*
* Retrieve information about a device region. Caller provides
* struct vfio_region_info with index value set. Caller sets argsz.
* Implementation of region mapping is bus driver specific. This is
* intended to describe MMIO, I/O port, as well as bus specific
* regions (ex. PCI config space). Zero sized regions may be used
* to describe unimplemented regions (ex. unimplemented PCI BARs).
* Return: 0 on success, -errno on failure.
*/
struct vfio_region_info {
__u32 argsz;
__u32 flags;
#define VFIO_REGION_INFO_FLAG_READ (1 << 0) /* Region supports read */
#define VFIO_REGION_INFO_FLAG_WRITE (1 << 1) /* Region supports write */
#define VFIO_REGION_INFO_FLAG_MMAP (1 << 2) /* Region supports mmap */
#define VFIO_REGION_INFO_FLAG_CAPS (1 << 3) /* Info supports caps */
__u32 index; /* Region index */
__u32 cap_offset; /* Offset within info struct of first cap */
__aligned_u64 size; /* Region size (bytes) */
__aligned_u64 offset; /* Region offset from start of device fd */
};
#define VFIO_DEVICE_GET_REGION_INFO _IO(VFIO_TYPE, VFIO_BASE + 8)
/*
* The sparse mmap capability allows finer granularity of specifying areas
* within a region with mmap support. When specified, the user should only
* mmap the offset ranges specified by the areas array. mmaps outside of the
* areas specified may fail (such as the range covering a PCI MSI-X table) or
* may result in improper device behavior.
*
* The structures below define version 1 of this capability.
*/
#define VFIO_REGION_INFO_CAP_SPARSE_MMAP 1
struct vfio_region_sparse_mmap_area {
__aligned_u64 offset; /* Offset of mmap'able area within region */
__aligned_u64 size; /* Size of mmap'able area */
};
struct vfio_region_info_cap_sparse_mmap {
struct vfio_info_cap_header header;
__u32 nr_areas;
__u32 reserved;
struct vfio_region_sparse_mmap_area areas[];
};
/*
* The device specific type capability allows regions unique to a specific
* device or class of devices to be exposed. This helps solve the problem for
* vfio bus drivers of defining which region indexes correspond to which region
* on the device, without needing to resort to static indexes, as done by
* vfio-pci. For instance, if we were to go back in time, we might remove
* VFIO_PCI_VGA_REGION_INDEX and let vfio-pci simply define that all indexes
* greater than or equal to VFIO_PCI_NUM_REGIONS are device specific and we'd
* make a "VGA" device specific type to describe the VGA access space. This
* means that non-VGA devices wouldn't need to waste this index, and thus the
* address space associated with it due to implementation of device file
* descriptor offsets in vfio-pci.
*
* The current implementation is now part of the user ABI, so we can't use this
* for VGA, but there are other upcoming use cases, such as opregions for Intel
* IGD devices and framebuffers for vGPU devices. We missed VGA, but we'll
* use this for future additions.
*
* The structure below defines version 1 of this capability.
*/
#define VFIO_REGION_INFO_CAP_TYPE 2
struct vfio_region_info_cap_type {
struct vfio_info_cap_header header;
__u32 type; /* global per bus driver */
__u32 subtype; /* type specific */
};
/*
* List of region types, global per bus driver.
* If you introduce a new type, please add it here.
*/
/* PCI region type containing a PCI vendor part */
#define VFIO_REGION_TYPE_PCI_VENDOR_TYPE (1 << 31)
#define VFIO_REGION_TYPE_PCI_VENDOR_MASK (0xffff)
#define VFIO_REGION_TYPE_GFX (1)
#define VFIO_REGION_TYPE_CCW (2)
#define VFIO_REGION_TYPE_MIGRATION_DEPRECATED (3)
/* sub-types for VFIO_REGION_TYPE_PCI_* */
/* 8086 vendor PCI sub-types */
#define VFIO_REGION_SUBTYPE_INTEL_IGD_OPREGION (1)
#define VFIO_REGION_SUBTYPE_INTEL_IGD_HOST_CFG (2)
#define VFIO_REGION_SUBTYPE_INTEL_IGD_LPC_CFG (3)
/* 10de vendor PCI sub-types */
/*
* NVIDIA GPU NVlink2 RAM is coherent RAM mapped onto the host address space.
*
* Deprecated, region no longer provided
*/
#define VFIO_REGION_SUBTYPE_NVIDIA_NVLINK2_RAM (1)
/* 1014 vendor PCI sub-types */
/*
* IBM NPU NVlink2 ATSD (Address Translation Shootdown) register of NPU
* to do TLB invalidation on a GPU.
*
* Deprecated, region no longer provided
*/
#define VFIO_REGION_SUBTYPE_IBM_NVLINK2_ATSD (1)
/* sub-types for VFIO_REGION_TYPE_GFX */
#define VFIO_REGION_SUBTYPE_GFX_EDID (1)
/**
* struct vfio_region_gfx_edid - EDID region layout.
*
* Set display link state and EDID blob.
*
* The EDID blob has monitor information such as brand, name, serial
* number, physical size, supported video modes and more.
*
* This special region allows userspace (typically qemu) set a virtual
* EDID for the virtual monitor, which allows a flexible display
* configuration.
*
* For the edid blob spec look here:
* https://en.wikipedia.org/wiki/Extended_Display_Identification_Data
*
* On linux systems you can find the EDID blob in sysfs:
* /sys/class/drm/${card}/${connector}/edid
*
* You can use the edid-decode ulility (comes with xorg-x11-utils) to
* decode the EDID blob.
*
* @edid_offset: location of the edid blob, relative to the
* start of the region (readonly).
* @edid_max_size: max size of the edid blob (readonly).
* @edid_size: actual edid size (read/write).
* @link_state: display link state (read/write).
* VFIO_DEVICE_GFX_LINK_STATE_UP: Monitor is turned on.
* VFIO_DEVICE_GFX_LINK_STATE_DOWN: Monitor is turned off.
* @max_xres: max display width (0 == no limitation, readonly).
* @max_yres: max display height (0 == no limitation, readonly).
*
* EDID update protocol:
* (1) set link-state to down.
* (2) update edid blob and size.
* (3) set link-state to up.
*/
struct vfio_region_gfx_edid {
__u32 edid_offset;
__u32 edid_max_size;
__u32 edid_size;
__u32 max_xres;
__u32 max_yres;
__u32 link_state;
#define VFIO_DEVICE_GFX_LINK_STATE_UP 1
#define VFIO_DEVICE_GFX_LINK_STATE_DOWN 2
};
/* sub-types for VFIO_REGION_TYPE_CCW */
#define VFIO_REGION_SUBTYPE_CCW_ASYNC_CMD (1)
#define VFIO_REGION_SUBTYPE_CCW_SCHIB (2)
#define VFIO_REGION_SUBTYPE_CCW_CRW (3)
/* sub-types for VFIO_REGION_TYPE_MIGRATION */
#define VFIO_REGION_SUBTYPE_MIGRATION_DEPRECATED (1)
struct vfio_device_migration_info {
__u32 device_state; /* VFIO device state */
#define VFIO_DEVICE_STATE_V1_STOP (0)
#define VFIO_DEVICE_STATE_V1_RUNNING (1 << 0)
#define VFIO_DEVICE_STATE_V1_SAVING (1 << 1)
#define VFIO_DEVICE_STATE_V1_RESUMING (1 << 2)
#define VFIO_DEVICE_STATE_MASK (VFIO_DEVICE_STATE_V1_RUNNING | \
VFIO_DEVICE_STATE_V1_SAVING | \
VFIO_DEVICE_STATE_V1_RESUMING)
#define VFIO_DEVICE_STATE_VALID(state) \
(state & VFIO_DEVICE_STATE_V1_RESUMING ? \
(state & VFIO_DEVICE_STATE_MASK) == VFIO_DEVICE_STATE_V1_RESUMING : 1)
#define VFIO_DEVICE_STATE_IS_ERROR(state) \
((state & VFIO_DEVICE_STATE_MASK) == (VFIO_DEVICE_STATE_V1_SAVING | \
VFIO_DEVICE_STATE_V1_RESUMING))
#define VFIO_DEVICE_STATE_SET_ERROR(state) \
((state & ~VFIO_DEVICE_STATE_MASK) | VFIO_DEVICE_STATE_V1_SAVING | \
VFIO_DEVICE_STATE_V1_RESUMING)
__u32 reserved;
__aligned_u64 pending_bytes;
__aligned_u64 data_offset;
__aligned_u64 data_size;
};
/*
* The MSIX mappable capability informs that MSIX data of a BAR can be mmapped
* which allows direct access to non-MSIX registers which happened to be within
* the same system page.
*
* Even though the userspace gets direct access to the MSIX data, the existing
* VFIO_DEVICE_SET_IRQS interface must still be used for MSIX configuration.
*/
#define VFIO_REGION_INFO_CAP_MSIX_MAPPABLE 3
/*
* Capability with compressed real address (aka SSA - small system address)
* where GPU RAM is mapped on a system bus. Used by a GPU for DMA routing
* and by the userspace to associate a NVLink bridge with a GPU.
*
* Deprecated, capability no longer provided
*/
#define VFIO_REGION_INFO_CAP_NVLINK2_SSATGT 4
struct vfio_region_info_cap_nvlink2_ssatgt {
struct vfio_info_cap_header header;
__aligned_u64 tgt;
};
/*
* Capability with an NVLink link speed. The value is read by
* the NVlink2 bridge driver from the bridge's "ibm,nvlink-speed"
* property in the device tree. The value is fixed in the hardware
* and failing to provide the correct value results in the link
* not working with no indication from the driver why.
*
* Deprecated, capability no longer provided
*/
#define VFIO_REGION_INFO_CAP_NVLINK2_LNKSPD 5
struct vfio_region_info_cap_nvlink2_lnkspd {
struct vfio_info_cap_header header;
__u32 link_speed;
__u32 __pad;
};
/**
* VFIO_DEVICE_GET_IRQ_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 9,
* struct vfio_irq_info)
*
* Retrieve information about a device IRQ. Caller provides
* struct vfio_irq_info with index value set. Caller sets argsz.
* Implementation of IRQ mapping is bus driver specific. Indexes
* using multiple IRQs are primarily intended to support MSI-like
* interrupt blocks. Zero count irq blocks may be used to describe
* unimplemented interrupt types.
*
* The EVENTFD flag indicates the interrupt index supports eventfd based
* signaling.
*
* The MASKABLE flags indicates the index supports MASK and UNMASK
* actions described below.
*
* AUTOMASKED indicates that after signaling, the interrupt line is
* automatically masked by VFIO and the user needs to unmask the line
* to receive new interrupts. This is primarily intended to distinguish
* level triggered interrupts.
*
* The NORESIZE flag indicates that the interrupt lines within the index
* are setup as a set and new subindexes cannot be enabled without first
* disabling the entire index. This is used for interrupts like PCI MSI
* and MSI-X where the driver may only use a subset of the available
* indexes, but VFIO needs to enable a specific number of vectors
* upfront. In the case of MSI-X, where the user can enable MSI-X and
* then add and unmask vectors, it's up to userspace to make the decision
* whether to allocate the maximum supported number of vectors or tear
* down setup and incrementally increase the vectors as each is enabled.
* Absence of the NORESIZE flag indicates that vectors can be enabled
* and disabled dynamically without impacting other vectors within the
* index.
*/
struct vfio_irq_info {
__u32 argsz;
__u32 flags;
#define VFIO_IRQ_INFO_EVENTFD (1 << 0)
#define VFIO_IRQ_INFO_MASKABLE (1 << 1)
#define VFIO_IRQ_INFO_AUTOMASKED (1 << 2)
#define VFIO_IRQ_INFO_NORESIZE (1 << 3)
__u32 index; /* IRQ index */
__u32 count; /* Number of IRQs within this index */
};
#define VFIO_DEVICE_GET_IRQ_INFO _IO(VFIO_TYPE, VFIO_BASE + 9)
/**
* VFIO_DEVICE_SET_IRQS - _IOW(VFIO_TYPE, VFIO_BASE + 10, struct vfio_irq_set)
*
* Set signaling, masking, and unmasking of interrupts. Caller provides
* struct vfio_irq_set with all fields set. 'start' and 'count' indicate
* the range of subindexes being specified.
*
* The DATA flags specify the type of data provided. If DATA_NONE, the
* operation performs the specified action immediately on the specified
* interrupt(s). For example, to unmask AUTOMASKED interrupt [0,0]:
* flags = (DATA_NONE|ACTION_UNMASK), index = 0, start = 0, count = 1.
*
* DATA_BOOL allows sparse support for the same on arrays of interrupts.
* For example, to mask interrupts [0,1] and [0,3] (but not [0,2]):
* flags = (DATA_BOOL|ACTION_MASK), index = 0, start = 1, count = 3,
* data = {1,0,1}
*
* DATA_EVENTFD binds the specified ACTION to the provided __s32 eventfd.
* A value of -1 can be used to either de-assign interrupts if already
* assigned or skip un-assigned interrupts. For example, to set an eventfd
* to be trigger for interrupts [0,0] and [0,2]:
* flags = (DATA_EVENTFD|ACTION_TRIGGER), index = 0, start = 0, count = 3,
* data = {fd1, -1, fd2}
* If index [0,1] is previously set, two count = 1 ioctls calls would be
* required to set [0,0] and [0,2] without changing [0,1].
*
* Once a signaling mechanism is set, DATA_BOOL or DATA_NONE can be used
* with ACTION_TRIGGER to perform kernel level interrupt loopback testing
* from userspace (ie. simulate hardware triggering).
*
* Setting of an event triggering mechanism to userspace for ACTION_TRIGGER
* enables the interrupt index for the device. Individual subindex interrupts
* can be disabled using the -1 value for DATA_EVENTFD or the index can be
* disabled as a whole with: flags = (DATA_NONE|ACTION_TRIGGER), count = 0.
*
* Note that ACTION_[UN]MASK specify user->kernel signaling (irqfds) while
* ACTION_TRIGGER specifies kernel->user signaling.
*/
struct vfio_irq_set {
__u32 argsz;
__u32 flags;
#define VFIO_IRQ_SET_DATA_NONE (1 << 0) /* Data not present */
#define VFIO_IRQ_SET_DATA_BOOL (1 << 1) /* Data is bool (u8) */
#define VFIO_IRQ_SET_DATA_EVENTFD (1 << 2) /* Data is eventfd (s32) */
#define VFIO_IRQ_SET_ACTION_MASK (1 << 3) /* Mask interrupt */
#define VFIO_IRQ_SET_ACTION_UNMASK (1 << 4) /* Unmask interrupt */
#define VFIO_IRQ_SET_ACTION_TRIGGER (1 << 5) /* Trigger interrupt */
__u32 index;
__u32 start;
__u32 count;
__u8 data[];
};
#define VFIO_DEVICE_SET_IRQS _IO(VFIO_TYPE, VFIO_BASE + 10)
#define VFIO_IRQ_SET_DATA_TYPE_MASK (VFIO_IRQ_SET_DATA_NONE | \
VFIO_IRQ_SET_DATA_BOOL | \
VFIO_IRQ_SET_DATA_EVENTFD)
#define VFIO_IRQ_SET_ACTION_TYPE_MASK (VFIO_IRQ_SET_ACTION_MASK | \
VFIO_IRQ_SET_ACTION_UNMASK | \
VFIO_IRQ_SET_ACTION_TRIGGER)
/**
* VFIO_DEVICE_RESET - _IO(VFIO_TYPE, VFIO_BASE + 11)
*
* Reset a device.
*/
#define VFIO_DEVICE_RESET _IO(VFIO_TYPE, VFIO_BASE + 11)
/*
* The VFIO-PCI bus driver makes use of the following fixed region and
* IRQ index mapping. Unimplemented regions return a size of zero.
* Unimplemented IRQ types return a count of zero.
*/
enum {
VFIO_PCI_BAR0_REGION_INDEX,
VFIO_PCI_BAR1_REGION_INDEX,
VFIO_PCI_BAR2_REGION_INDEX,
VFIO_PCI_BAR3_REGION_INDEX,
VFIO_PCI_BAR4_REGION_INDEX,
VFIO_PCI_BAR5_REGION_INDEX,
VFIO_PCI_ROM_REGION_INDEX,
VFIO_PCI_CONFIG_REGION_INDEX,
/*
* Expose VGA regions defined for PCI base class 03, subclass 00.
* This includes I/O port ranges 0x3b0 to 0x3bb and 0x3c0 to 0x3df
* as well as the MMIO range 0xa0000 to 0xbffff. Each implemented
* range is found at it's identity mapped offset from the region
* offset, for example 0x3b0 is region_info.offset + 0x3b0. Areas
* between described ranges are unimplemented.
*/
VFIO_PCI_VGA_REGION_INDEX,
VFIO_PCI_NUM_REGIONS = 9 /* Fixed user ABI, region indexes >=9 use */
/* device specific cap to define content. */
};
enum {
VFIO_PCI_INTX_IRQ_INDEX,
VFIO_PCI_MSI_IRQ_INDEX,
VFIO_PCI_MSIX_IRQ_INDEX,
VFIO_PCI_ERR_IRQ_INDEX,
VFIO_PCI_REQ_IRQ_INDEX,
VFIO_PCI_NUM_IRQS
};
/*
* The vfio-ccw bus driver makes use of the following fixed region and
* IRQ index mapping. Unimplemented regions return a size of zero.
* Unimplemented IRQ types return a count of zero.
*/
enum {
VFIO_CCW_CONFIG_REGION_INDEX,
VFIO_CCW_NUM_REGIONS
};
enum {
VFIO_CCW_IO_IRQ_INDEX,
VFIO_CCW_CRW_IRQ_INDEX,
VFIO_CCW_REQ_IRQ_INDEX,
VFIO_CCW_NUM_IRQS
};
/*
* The vfio-ap bus driver makes use of the following IRQ index mapping.
* Unimplemented IRQ types return a count of zero.
*/
enum {
VFIO_AP_REQ_IRQ_INDEX,
VFIO_AP_CFG_CHG_IRQ_INDEX,
VFIO_AP_NUM_IRQS
};
/**
* VFIO_DEVICE_GET_PCI_HOT_RESET_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 12,
* struct vfio_pci_hot_reset_info)
*
* This command is used to query the affected devices in the hot reset for
* a given device.
*
* This command always reports the segment, bus, and devfn information for
* each affected device, and selectively reports the group_id or devid per
* the way how the calling device is opened.
*
* - If the calling device is opened via the traditional group/container
* API, group_id is reported. User should check if it has owned all
* the affected devices and provides a set of group fds to prove the
* ownership in VFIO_DEVICE_PCI_HOT_RESET ioctl.
*
* - If the calling device is opened as a cdev, devid is reported.
* Flag VFIO_PCI_HOT_RESET_FLAG_DEV_ID is set to indicate this
* data type. All the affected devices should be represented in
* the dev_set, ex. bound to a vfio driver, and also be owned by
* this interface which is determined by the following conditions:
* 1) Has a valid devid within the iommufd_ctx of the calling device.
* Ownership cannot be determined across separate iommufd_ctx and
* the cdev calling conventions do not support a proof-of-ownership
* model as provided in the legacy group interface. In this case
* valid devid with value greater than zero is provided in the return
* structure.
* 2) Does not have a valid devid within the iommufd_ctx of the calling
* device, but belongs to the same IOMMU group as the calling device
* or another opened device that has a valid devid within the
* iommufd_ctx of the calling device. This provides implicit ownership
* for devices within the same DMA isolation context. In this case
* the devid value of VFIO_PCI_DEVID_OWNED is provided in the return
* structure.
*
* A devid value of VFIO_PCI_DEVID_NOT_OWNED is provided in the return
* structure for affected devices where device is NOT represented in the
* dev_set or ownership is not available. Such devices prevent the use
* of VFIO_DEVICE_PCI_HOT_RESET ioctl outside of the proof-of-ownership
* calling conventions (ie. via legacy group accessed devices). Flag
* VFIO_PCI_HOT_RESET_FLAG_DEV_ID_OWNED would be set when all the
* affected devices are represented in the dev_set and also owned by
* the user. This flag is available only when
* flag VFIO_PCI_HOT_RESET_FLAG_DEV_ID is set, otherwise reserved.
* When set, user could invoke VFIO_DEVICE_PCI_HOT_RESET with a zero
* length fd array on the calling device as the ownership is validated
* by iommufd_ctx.
*
* Return: 0 on success, -errno on failure:
* -enospc = insufficient buffer, -enodev = unsupported for device.
*/
struct vfio_pci_dependent_device {
union {
__u32 group_id;
__u32 devid;
#define VFIO_PCI_DEVID_OWNED 0
#define VFIO_PCI_DEVID_NOT_OWNED -1
};
__u16 segment;
__u8 bus;
__u8 devfn; /* Use PCI_SLOT/PCI_FUNC */
};
struct vfio_pci_hot_reset_info {
__u32 argsz;
__u32 flags;
#define VFIO_PCI_HOT_RESET_FLAG_DEV_ID (1 << 0)
#define VFIO_PCI_HOT_RESET_FLAG_DEV_ID_OWNED (1 << 1)
__u32 count;
struct vfio_pci_dependent_device devices[];
};
#define VFIO_DEVICE_GET_PCI_HOT_RESET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12)
/**
* VFIO_DEVICE_PCI_HOT_RESET - _IOW(VFIO_TYPE, VFIO_BASE + 13,
* struct vfio_pci_hot_reset)
*
* A PCI hot reset results in either a bus or slot reset which may affect
* other devices sharing the bus/slot. The calling user must have
* ownership of the full set of affected devices as determined by the
* VFIO_DEVICE_GET_PCI_HOT_RESET_INFO ioctl.
*
* When called on a device file descriptor acquired through the vfio
* group interface, the user is required to provide proof of ownership
* of those affected devices via the group_fds array in struct
* vfio_pci_hot_reset.
*
* When called on a direct cdev opened vfio device, the flags field of
* struct vfio_pci_hot_reset_info reports the ownership status of the
* affected devices and this ioctl must be called with an empty group_fds
* array. See above INFO ioctl definition for ownership requirements.
*
* Mixed usage of legacy groups and cdevs across the set of affected
* devices is not supported.
*
* Return: 0 on success, -errno on failure.
*/
struct vfio_pci_hot_reset {
__u32 argsz;
__u32 flags;
__u32 count;
__s32 group_fds[];
};
#define VFIO_DEVICE_PCI_HOT_RESET _IO(VFIO_TYPE, VFIO_BASE + 13)
/**
* VFIO_DEVICE_QUERY_GFX_PLANE - _IOW(VFIO_TYPE, VFIO_BASE + 14,
* struct vfio_device_query_gfx_plane)
*
* Set the drm_plane_type and flags, then retrieve the gfx plane info.
*
* flags supported:
* - VFIO_GFX_PLANE_TYPE_PROBE and VFIO_GFX_PLANE_TYPE_DMABUF are set
* to ask if the mdev supports dma-buf. 0 on support, -EINVAL on no
* support for dma-buf.
* - VFIO_GFX_PLANE_TYPE_PROBE and VFIO_GFX_PLANE_TYPE_REGION are set
* to ask if the mdev supports region. 0 on support, -EINVAL on no
* support for region.
* - VFIO_GFX_PLANE_TYPE_DMABUF or VFIO_GFX_PLANE_TYPE_REGION is set
* with each call to query the plane info.
* - Others are invalid and return -EINVAL.
*
* Note:
* 1. Plane could be disabled by guest. In that case, success will be
* returned with zero-initialized drm_format, size, width and height
* fields.
* 2. x_hot/y_hot is set to 0xFFFFFFFF if no hotspot information available
*
* Return: 0 on success, -errno on other failure.
*/
struct vfio_device_gfx_plane_info {
__u32 argsz;
__u32 flags;
#define VFIO_GFX_PLANE_TYPE_PROBE (1 << 0)
#define VFIO_GFX_PLANE_TYPE_DMABUF (1 << 1)
#define VFIO_GFX_PLANE_TYPE_REGION (1 << 2)
/* in */
__u32 drm_plane_type; /* type of plane: DRM_PLANE_TYPE_* */
/* out */
__u32 drm_format; /* drm format of plane */
__aligned_u64 drm_format_mod; /* tiled mode */
__u32 width; /* width of plane */
__u32 height; /* height of plane */
__u32 stride; /* stride of plane */
__u32 size; /* size of plane in bytes, align on page*/
__u32 x_pos; /* horizontal position of cursor plane */
__u32 y_pos; /* vertical position of cursor plane*/
__u32 x_hot; /* horizontal position of cursor hotspot */
__u32 y_hot; /* vertical position of cursor hotspot */
union {
__u32 region_index; /* region index */
__u32 dmabuf_id; /* dma-buf id */
};
__u32 reserved;
};
#define VFIO_DEVICE_QUERY_GFX_PLANE _IO(VFIO_TYPE, VFIO_BASE + 14)
/**
* VFIO_DEVICE_GET_GFX_DMABUF - _IOW(VFIO_TYPE, VFIO_BASE + 15, __u32)
*
* Return a new dma-buf file descriptor for an exposed guest framebuffer
* described by the provided dmabuf_id. The dmabuf_id is returned from VFIO_
* DEVICE_QUERY_GFX_PLANE as a token of the exposed guest framebuffer.
*/
#define VFIO_DEVICE_GET_GFX_DMABUF _IO(VFIO_TYPE, VFIO_BASE + 15)
/**
* VFIO_DEVICE_IOEVENTFD - _IOW(VFIO_TYPE, VFIO_BASE + 16,
* struct vfio_device_ioeventfd)
*
* Perform a write to the device at the specified device fd offset, with
* the specified data and width when the provided eventfd is triggered.
* vfio bus drivers may not support this for all regions, for all widths,
* or at all. vfio-pci currently only enables support for BAR regions,
* excluding the MSI-X vector table.
*
* Return: 0 on success, -errno on failure.
*/
struct vfio_device_ioeventfd {
__u32 argsz;
__u32 flags;
#define VFIO_DEVICE_IOEVENTFD_8 (1 << 0) /* 1-byte write */
#define VFIO_DEVICE_IOEVENTFD_16 (1 << 1) /* 2-byte write */
#define VFIO_DEVICE_IOEVENTFD_32 (1 << 2) /* 4-byte write */
#define VFIO_DEVICE_IOEVENTFD_64 (1 << 3) /* 8-byte write */
#define VFIO_DEVICE_IOEVENTFD_SIZE_MASK (0xf)
__aligned_u64 offset; /* device fd offset of write */
__aligned_u64 data; /* data to be written */
__s32 fd; /* -1 for de-assignment */
__u32 reserved;
};
#define VFIO_DEVICE_IOEVENTFD _IO(VFIO_TYPE, VFIO_BASE + 16)
/**
* VFIO_DEVICE_FEATURE - _IOWR(VFIO_TYPE, VFIO_BASE + 17,
* struct vfio_device_feature)
*
* Get, set, or probe feature data of the device. The feature is selected
* using the FEATURE_MASK portion of the flags field. Support for a feature
* can be probed by setting both the FEATURE_MASK and PROBE bits. A probe
* may optionally include the GET and/or SET bits to determine read vs write
* access of the feature respectively. Probing a feature will return success
* if the feature is supported and all of the optionally indicated GET/SET
* methods are supported. The format of the data portion of the structure is
* specific to the given feature. The data portion is not required for
* probing. GET and SET are mutually exclusive, except for use with PROBE.
*
* Return 0 on success, -errno on failure.
*/
struct vfio_device_feature {
__u32 argsz;
__u32 flags;
#define VFIO_DEVICE_FEATURE_MASK (0xffff) /* 16-bit feature index */
#define VFIO_DEVICE_FEATURE_GET (1 << 16) /* Get feature into data[] */
#define VFIO_DEVICE_FEATURE_SET (1 << 17) /* Set feature from data[] */
#define VFIO_DEVICE_FEATURE_PROBE (1 << 18) /* Probe feature support */
__u8 data[];
};
#define VFIO_DEVICE_FEATURE _IO(VFIO_TYPE, VFIO_BASE + 17)
/*
* VFIO_DEVICE_BIND_IOMMUFD - _IOR(VFIO_TYPE, VFIO_BASE + 18,
* struct vfio_device_bind_iommufd)
* @argsz: User filled size of this data.
* @flags: Must be 0 or a bit flags of VFIO_DEVICE_BIND_*
* @iommufd: iommufd to bind.
* @out_devid: The device id generated by this bind. devid is a handle for
* this device/iommufd bond and can be used in IOMMUFD commands.
* @token_uuid_ptr: Valid if VFIO_DEVICE_BIND_FLAG_TOKEN. Points to a 16 byte
* UUID in the same format as VFIO_DEVICE_FEATURE_PCI_VF_TOKEN.
*
* Bind a vfio_device to the specified iommufd.
*
* User is restricted from accessing the device before the binding operation
* is completed. Only allowed on cdev fds.
*
* Unbind is automatically conducted when device fd is closed.
*
* A token is sometimes required to open the device, unless this is known to be
* needed VFIO_DEVICE_BIND_FLAG_TOKEN should not be set and token_uuid_ptr is
* ignored. The only case today is a PF/VF relationship where the VF bind must
* be provided the same token as VFIO_DEVICE_FEATURE_PCI_VF_TOKEN provided to
* the PF.
*
* Return: 0 on success, -errno on failure.
*/
struct vfio_device_bind_iommufd {
__u32 argsz;
__u32 flags;
#define VFIO_DEVICE_BIND_FLAG_TOKEN (1 << 0)
__s32 iommufd;
__u32 out_devid;
__aligned_u64 token_uuid_ptr;
};
#define VFIO_DEVICE_BIND_IOMMUFD _IO(VFIO_TYPE, VFIO_BASE + 18)
/*
* VFIO_DEVICE_ATTACH_IOMMUFD_PT - _IOW(VFIO_TYPE, VFIO_BASE + 19,
* struct vfio_device_attach_iommufd_pt)
* @argsz: User filled size of this data.
* @flags: Flags for attach.
* @pt_id: Input the target id which can represent an ioas or a hwpt
* allocated via iommufd subsystem.
* Output the input ioas id or the attached hwpt id which could
* be the specified hwpt itself or a hwpt automatically created
* for the specified ioas by kernel during the attachment.
* @pasid: The pasid to be attached, only meaningful when
* VFIO_DEVICE_ATTACH_PASID is set in @flags
*
* Associate the device with an address space within the bound iommufd.
* Undo by VFIO_DEVICE_DETACH_IOMMUFD_PT or device fd close. This is only
* allowed on cdev fds.
*
* If a vfio device or a pasid of this device is currently attached to a valid
* hw_pagetable (hwpt), without doing a VFIO_DEVICE_DETACH_IOMMUFD_PT, a second
* VFIO_DEVICE_ATTACH_IOMMUFD_PT ioctl passing in another hwpt id is allowed.
* This action, also known as a hw_pagetable replacement, will replace the
* currently attached hwpt of the device or the pasid of this device with a new
* hwpt corresponding to the given pt_id.
*
* Return: 0 on success, -errno on failure.
*
* When a device is resetting, -EBUSY will be returned to reject any concurrent
* attachment to the resetting device itself or any sibling device in the IOMMU
* group having the resetting device.
*/
struct vfio_device_attach_iommufd_pt {
__u32 argsz;
__u32 flags;
#define VFIO_DEVICE_ATTACH_PASID (1 << 0)
__u32 pt_id;
__u32 pasid;
};
#define VFIO_DEVICE_ATTACH_IOMMUFD_PT _IO(VFIO_TYPE, VFIO_BASE + 19)
/*
* VFIO_DEVICE_DETACH_IOMMUFD_PT - _IOW(VFIO_TYPE, VFIO_BASE + 20,
* struct vfio_device_detach_iommufd_pt)
* @argsz: User filled size of this data.
* @flags: Flags for detach.
* @pasid: The pasid to be detached, only meaningful when
* VFIO_DEVICE_DETACH_PASID is set in @flags
*
* Remove the association of the device or a pasid of the device and its current
* associated address space. After it, the device or the pasid should be in a
* blocking DMA state. This is only allowed on cdev fds.
*
* Return: 0 on success, -errno on failure.
*/
struct vfio_device_detach_iommufd_pt {
__u32 argsz;
__u32 flags;
#define VFIO_DEVICE_DETACH_PASID (1 << 0)
__u32 pasid;