summaryrefslogtreecommitdiff
path: root/include/uapi/linux/kfd_ioctl.h
blob: af96af174dc47b2510a962cbe4e784c509db7163 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
/*
 * Copyright 2014 Advanced Micro Devices, Inc.
 *
 * Permission is hereby granted, free of charge, to any person obtaining a
 * copy of this software and associated documentation files (the "Software"),
 * to deal in the Software without restriction, including without limitation
 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
 * and/or sell copies of the Software, and to permit persons to whom the
 * Software is furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
 * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
 * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
 * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
 * OTHER DEALINGS IN THE SOFTWARE.
 */

#ifndef KFD_IOCTL_H_INCLUDED
#define KFD_IOCTL_H_INCLUDED

#include <drm/drm.h>
#include <linux/ioctl.h>

/*
 * - 1.1 - initial version
 * - 1.3 - Add SMI events support
 * - 1.4 - Indicate new SRAM EDC bit in device properties
 * - 1.5 - Add SVM API
 * - 1.6 - Query clear flags in SVM get_attr API
 */
#define KFD_IOCTL_MAJOR_VERSION 1
#define KFD_IOCTL_MINOR_VERSION 6

struct kfd_ioctl_get_version_args {
	__u32 major_version;	/* from KFD */
	__u32 minor_version;	/* from KFD */
};

/* For kfd_ioctl_create_queue_args.queue_type. */
#define KFD_IOC_QUEUE_TYPE_COMPUTE		0x0
#define KFD_IOC_QUEUE_TYPE_SDMA			0x1
#define KFD_IOC_QUEUE_TYPE_COMPUTE_AQL		0x2
#define KFD_IOC_QUEUE_TYPE_SDMA_XGMI		0x3

#define KFD_MAX_QUEUE_PERCENTAGE	100
#define KFD_MAX_QUEUE_PRIORITY		15

struct kfd_ioctl_create_queue_args {
	__u64 ring_base_address;	/* to KFD */
	__u64 write_pointer_address;	/* from KFD */
	__u64 read_pointer_address;	/* from KFD */
	__u64 doorbell_offset;	/* from KFD */

	__u32 ring_size;		/* to KFD */
	__u32 gpu_id;		/* to KFD */
	__u32 queue_type;		/* to KFD */
	__u32 queue_percentage;	/* to KFD */
	__u32 queue_priority;	/* to KFD */
	__u32 queue_id;		/* from KFD */

	__u64 eop_buffer_address;	/* to KFD */
	__u64 eop_buffer_size;	/* to KFD */
	__u64 ctx_save_restore_address; /* to KFD */
	__u32 ctx_save_restore_size;	/* to KFD */
	__u32 ctl_stack_size;		/* to KFD */
};

struct kfd_ioctl_destroy_queue_args {
	__u32 queue_id;		/* to KFD */
	__u32 pad;
};

struct kfd_ioctl_update_queue_args {
	__u64 ring_base_address;	/* to KFD */

	__u32 queue_id;		/* to KFD */
	__u32 ring_size;		/* to KFD */
	__u32 queue_percentage;	/* to KFD */
	__u32 queue_priority;	/* to KFD */
};

struct kfd_ioctl_set_cu_mask_args {
	__u32 queue_id;		/* to KFD */
	__u32 num_cu_mask;		/* to KFD */
	__u64 cu_mask_ptr;		/* to KFD */
};

struct kfd_ioctl_get_queue_wave_state_args {
	__u64 ctl_stack_address;	/* to KFD */
	__u32 ctl_stack_used_size;	/* from KFD */
	__u32 save_area_used_size;	/* from KFD */
	__u32 queue_id;			/* to KFD */
	__u32 pad;
};

/* For kfd_ioctl_set_memory_policy_args.default_policy and alternate_policy */
#define KFD_IOC_CACHE_POLICY_COHERENT 0
#define KFD_IOC_CACHE_POLICY_NONCOHERENT 1

struct kfd_ioctl_set_memory_policy_args {
	__u64 alternate_aperture_base;	/* to KFD */
	__u64 alternate_aperture_size;	/* to KFD */

	__u32 gpu_id;			/* to KFD */
	__u32 default_policy;		/* to KFD */
	__u32 alternate_policy;		/* to KFD */
	__u32 pad;
};

/*
 * All counters are monotonic. They are used for profiling of compute jobs.
 * The profiling is done by userspace.
 *
 * In case of GPU reset, the counter should not be affected.
 */

struct kfd_ioctl_get_clock_counters_args {
	__u64 gpu_clock_counter;	/* from KFD */
	__u64 cpu_clock_counter;	/* from KFD */
	__u64 system_clock_counter;	/* from KFD */
	__u64 system_clock_freq;	/* from KFD */

	__u32 gpu_id;		/* to KFD */
	__u32 pad;
};

struct kfd_process_device_apertures {
	__u64 lds_base;		/* from KFD */
	__u64 lds_limit;		/* from KFD */
	__u64 scratch_base;		/* from KFD */
	__u64 scratch_limit;		/* from KFD */
	__u64 gpuvm_base;		/* from KFD */
	__u64 gpuvm_limit;		/* from KFD */
	__u32 gpu_id;		/* from KFD */
	__u32 pad;
};

/*
 * AMDKFD_IOC_GET_PROCESS_APERTURES is deprecated. Use
 * AMDKFD_IOC_GET_PROCESS_APERTURES_NEW instead, which supports an
 * unlimited number of GPUs.
 */
#define NUM_OF_SUPPORTED_GPUS 7
struct kfd_ioctl_get_process_apertures_args {
	struct kfd_process_device_apertures
			process_apertures[NUM_OF_SUPPORTED_GPUS];/* from KFD */

	/* from KFD, should be in the range [1 - NUM_OF_SUPPORTED_GPUS] */
	__u32 num_of_nodes;
	__u32 pad;
};

struct kfd_ioctl_get_process_apertures_new_args {
	/* User allocated. Pointer to struct kfd_process_device_apertures
	 * filled in by Kernel
	 */
	__u64 kfd_process_device_apertures_ptr;
	/* to KFD - indicates amount of memory present in
	 *  kfd_process_device_apertures_ptr
	 * from KFD - Number of entries filled by KFD.
	 */
	__u32 num_of_nodes;
	__u32 pad;
};

#define MAX_ALLOWED_NUM_POINTS    100
#define MAX_ALLOWED_AW_BUFF_SIZE 4096
#define MAX_ALLOWED_WAC_BUFF_SIZE  128

struct kfd_ioctl_dbg_register_args {
	__u32 gpu_id;		/* to KFD */
	__u32 pad;
};

struct kfd_ioctl_dbg_unregister_args {
	__u32 gpu_id;		/* to KFD */
	__u32 pad;
};

struct kfd_ioctl_dbg_address_watch_args {
	__u64 content_ptr;		/* a pointer to the actual content */
	__u32 gpu_id;		/* to KFD */
	__u32 buf_size_in_bytes;	/*including gpu_id and buf_size */
};

struct kfd_ioctl_dbg_wave_control_args {
	__u64 content_ptr;		/* a pointer to the actual content */
	__u32 gpu_id;		/* to KFD */
	__u32 buf_size_in_bytes;	/*including gpu_id and buf_size */
};

/* Matching HSA_EVENTTYPE */
#define KFD_IOC_EVENT_SIGNAL			0
#define KFD_IOC_EVENT_NODECHANGE		1
#define KFD_IOC_EVENT_DEVICESTATECHANGE		2
#define KFD_IOC_EVENT_HW_EXCEPTION		3
#define KFD_IOC_EVENT_SYSTEM_EVENT		4
#define KFD_IOC_EVENT_DEBUG_EVENT		5
#define KFD_IOC_EVENT_PROFILE_EVENT		6
#define KFD_IOC_EVENT_QUEUE_EVENT		7
#define KFD_IOC_EVENT_MEMORY			8

#define KFD_IOC_WAIT_RESULT_COMPLETE		0
#define KFD_IOC_WAIT_RESULT_TIMEOUT		1
#define KFD_IOC_WAIT_RESULT_FAIL		2

#define KFD_SIGNAL_EVENT_LIMIT			4096

/* For kfd_event_data.hw_exception_data.reset_type. */
#define KFD_HW_EXCEPTION_WHOLE_GPU_RESET	0
#define KFD_HW_EXCEPTION_PER_ENGINE_RESET	1

/* For kfd_event_data.hw_exception_data.reset_cause. */
#define KFD_HW_EXCEPTION_GPU_HANG	0
#define KFD_HW_EXCEPTION_ECC		1

/* For kfd_hsa_memory_exception_data.ErrorType */
#define KFD_MEM_ERR_NO_RAS		0
#define KFD_MEM_ERR_SRAM_ECC		1
#define KFD_MEM_ERR_POISON_CONSUMED	2
#define KFD_MEM_ERR_GPU_HANG		3

struct kfd_ioctl_create_event_args {
	__u64 event_page_offset;	/* from KFD */
	__u32 event_trigger_data;	/* from KFD - signal events only */
	__u32 event_type;		/* to KFD */
	__u32 auto_reset;		/* to KFD */
	__u32 node_id;		/* to KFD - only valid for certain
							event types */
	__u32 event_id;		/* from KFD */
	__u32 event_slot_index;	/* from KFD */
};

struct kfd_ioctl_destroy_event_args {
	__u32 event_id;		/* to KFD */
	__u32 pad;
};

struct kfd_ioctl_set_event_args {
	__u32 event_id;		/* to KFD */
	__u32 pad;
};

struct kfd_ioctl_reset_event_args {
	__u32 event_id;		/* to KFD */
	__u32 pad;
};

struct kfd_memory_exception_failure {
	__u32 NotPresent;	/* Page not present or supervisor privilege */
	__u32 ReadOnly;	/* Write access to a read-only page */
	__u32 NoExecute;	/* Execute access to a page marked NX */
	__u32 imprecise;	/* Can't determine the	exact fault address */
};

/* memory exception data */
struct kfd_hsa_memory_exception_data {
	struct kfd_memory_exception_failure failure;
	__u64 va;
	__u32 gpu_id;
	__u32 ErrorType; /* 0 = no RAS error,
			  * 1 = ECC_SRAM,
			  * 2 = Link_SYNFLOOD (poison),
			  * 3 = GPU hang (not attributable to a specific cause),
			  * other values reserved
			  */
};

/* hw exception data */
struct kfd_hsa_hw_exception_data {
	__u32 reset_type;
	__u32 reset_cause;
	__u32 memory_lost;
	__u32 gpu_id;
};

/* Event data */
struct kfd_event_data {
	union {
		struct kfd_hsa_memory_exception_data memory_exception_data;
		struct kfd_hsa_hw_exception_data hw_exception_data;
	};				/* From KFD */
	__u64 kfd_event_data_ext;	/* pointer to an extension structure
					   for future exception types */
	__u32 event_id;		/* to KFD */
	__u32 pad;
};

struct kfd_ioctl_wait_events_args {
	__u64 events_ptr;		/* pointed to struct
					   kfd_event_data array, to KFD */
	__u32 num_events;		/* to KFD */
	__u32 wait_for_all;		/* to KFD */
	__u32 timeout;		/* to KFD */
	__u32 wait_result;		/* from KFD */
};

struct kfd_ioctl_set_scratch_backing_va_args {
	__u64 va_addr;	/* to KFD */
	__u32 gpu_id;	/* to KFD */
	__u32 pad;
};

struct kfd_ioctl_get_tile_config_args {
	/* to KFD: pointer to tile array */
	__u64 tile_config_ptr;
	/* to KFD: pointer to macro tile array */
	__u64 macro_tile_config_ptr;
	/* to KFD: array size allocated by user mode
	 * from KFD: array size filled by kernel
	 */
	__u32 num_tile_configs;
	/* to KFD: array size allocated by user mode
	 * from KFD: array size filled by kernel
	 */
	__u32 num_macro_tile_configs;

	__u32 gpu_id;		/* to KFD */
	__u32 gb_addr_config;	/* from KFD */
	__u32 num_banks;		/* from KFD */
	__u32 num_ranks;		/* from KFD */
	/* struct size can be extended later if needed
	 * without breaking ABI compatibility
	 */
};

struct kfd_ioctl_set_trap_handler_args {
	__u64 tba_addr;		/* to KFD */
	__u64 tma_addr;		/* to KFD */
	__u32 gpu_id;		/* to KFD */
	__u32 pad;
};

struct kfd_ioctl_acquire_vm_args {
	__u32 drm_fd;	/* to KFD */
	__u32 gpu_id;	/* to KFD */
};

/* Allocation flags: memory types */
#define KFD_IOC_ALLOC_MEM_FLAGS_VRAM		(1 << 0)
#define KFD_IOC_ALLOC_MEM_FLAGS_GTT		(1 << 1)
#define KFD_IOC_ALLOC_MEM_FLAGS_USERPTR		(1 << 2)
#define KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL	(1 << 3)
#define KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP	(1 << 4)
/* Allocation flags: attributes/access options */
#define KFD_IOC_ALLOC_MEM_FLAGS_WRITABLE	(1 << 31)
#define KFD_IOC_ALLOC_MEM_FLAGS_EXECUTABLE	(1 << 30)
#define KFD_IOC_ALLOC_MEM_FLAGS_PUBLIC		(1 << 29)
#define KFD_IOC_ALLOC_MEM_FLAGS_NO_SUBSTITUTE	(1 << 28)
#define KFD_IOC_ALLOC_MEM_FLAGS_AQL_QUEUE_MEM	(1 << 27)
#define KFD_IOC_ALLOC_MEM_FLAGS_COHERENT	(1 << 26)
#define KFD_IOC_ALLOC_MEM_FLAGS_UNCACHED	(1 << 25)

/* Allocate memory for later SVM (shared virtual memory) mapping.
 *
 * @va_addr:     virtual address of the memory to be allocated
 *               all later mappings on all GPUs will use this address
 * @size:        size in bytes
 * @handle:      buffer handle returned to user mode, used to refer to
 *               this allocation for mapping, unmapping and freeing
 * @mmap_offset: for CPU-mapping the allocation by mmapping a render node
 *               for userptrs this is overloaded to specify the CPU address
 * @gpu_id:      device identifier
 * @flags:       memory type and attributes. See KFD_IOC_ALLOC_MEM_FLAGS above
 */
struct kfd_ioctl_alloc_memory_of_gpu_args {
	__u64 va_addr;		/* to KFD */
	__u64 size;		/* to KFD */
	__u64 handle;		/* from KFD */
	__u64 mmap_offset;	/* to KFD (userptr), from KFD (mmap offset) */
	__u32 gpu_id;		/* to KFD */
	__u32 flags;
};

/* Free memory allocated with kfd_ioctl_alloc_memory_of_gpu
 *
 * @handle: memory handle returned by alloc
 */
struct kfd_ioctl_free_memory_of_gpu_args {
	__u64 handle;		/* to KFD */
};

/* Map memory to one or more GPUs
 *
 * @handle:                memory handle returned by alloc
 * @device_ids_array_ptr:  array of gpu_ids (__u32 per device)
 * @n_devices:             number of devices in the array
 * @n_success:             number of devices mapped successfully
 *
 * @n_success returns information to the caller how many devices from
 * the start of the array have mapped the buffer successfully. It can
 * be passed into a subsequent retry call to skip those devices. For
 * the first call the caller should initialize it to 0.
 *
 * If the ioctl completes with return code 0 (success), n_success ==
 * n_devices.
 */
struct kfd_ioctl_map_memory_to_gpu_args {
	__u64 handle;			/* to KFD */
	__u64 device_ids_array_ptr;	/* to KFD */
	__u32 n_devices;		/* to KFD */
	__u32 n_success;		/* to/from KFD */
};

/* Unmap memory from one or more GPUs
 *
 * same arguments as for mapping
 */
struct kfd_ioctl_unmap_memory_from_gpu_args {
	__u64 handle;			/* to KFD */
	__u64 device_ids_array_ptr;	/* to KFD */
	__u32 n_devices;		/* to KFD */
	__u32 n_success;		/* to/from KFD */
};

/* Allocate GWS for specific queue
 *
 * @queue_id:    queue's id that GWS is allocated for
 * @num_gws:     how many GWS to allocate
 * @first_gws:   index of the first GWS allocated.
 *               only support contiguous GWS allocation
 */
struct kfd_ioctl_alloc_queue_gws_args {
	__u32 queue_id;		/* to KFD */
	__u32 num_gws;		/* to KFD */
	__u32 first_gws;	/* from KFD */
	__u32 pad;
};

struct kfd_ioctl_get_dmabuf_info_args {
	__u64 size;		/* from KFD */
	__u64 metadata_ptr;	/* to KFD */
	__u32 metadata_size;	/* to KFD (space allocated by user)
				 * from KFD (actual metadata size)
				 */
	__u32 gpu_id;	/* from KFD */
	__u32 flags;		/* from KFD (KFD_IOC_ALLOC_MEM_FLAGS) */
	__u32 dmabuf_fd;	/* to KFD */
};

struct kfd_ioctl_import_dmabuf_args {
	__u64 va_addr;	/* to KFD */
	__u64 handle;	/* from KFD */
	__u32 gpu_id;	/* to KFD */
	__u32 dmabuf_fd;	/* to KFD */
};

/*
 * KFD SMI(System Management Interface) events
 */
enum kfd_smi_event {
	KFD_SMI_EVENT_NONE = 0, /* not used */
	KFD_SMI_EVENT_VMFAULT = 1, /* event start counting at 1 */
	KFD_SMI_EVENT_THERMAL_THROTTLE = 2,
	KFD_SMI_EVENT_GPU_PRE_RESET = 3,
	KFD_SMI_EVENT_GPU_POST_RESET = 4,
};

#define KFD_SMI_EVENT_MASK_FROM_INDEX(i) (1ULL << ((i) - 1))

struct kfd_ioctl_smi_events_args {
	__u32 gpuid;	/* to KFD */
	__u32 anon_fd;	/* from KFD */
};

/* Register offset inside the remapped mmio page
 */
enum kfd_mmio_remap {
	KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL = 0,
	KFD_MMIO_REMAP_HDP_REG_FLUSH_CNTL = 4,
};

/* Guarantee host access to memory */
#define KFD_IOCTL_SVM_FLAG_HOST_ACCESS 0x00000001
/* Fine grained coherency between all devices with access */
#define KFD_IOCTL_SVM_FLAG_COHERENT    0x00000002
/* Use any GPU in same hive as preferred device */
#define KFD_IOCTL_SVM_FLAG_HIVE_LOCAL  0x00000004
/* GPUs only read, allows replication */
#define KFD_IOCTL_SVM_FLAG_GPU_RO      0x00000008
/* Allow execution on GPU */
#define KFD_IOCTL_SVM_FLAG_GPU_EXEC    0x00000010
/* GPUs mostly read, may allow similar optimizations as RO, but writes fault */
#define KFD_IOCTL_SVM_FLAG_GPU_READ_MOSTLY     0x00000020

/**
 * kfd_ioctl_svm_op - SVM ioctl operations
 *
 * @KFD_IOCTL_SVM_OP_SET_ATTR: Modify one or more attributes
 * @KFD_IOCTL_SVM_OP_GET_ATTR: Query one or more attributes
 */
enum kfd_ioctl_svm_op {
	KFD_IOCTL_SVM_OP_SET_ATTR,
	KFD_IOCTL_SVM_OP_GET_ATTR
};

/** kfd_ioctl_svm_location - Enum for preferred and prefetch locations
 *
 * GPU IDs are used to specify GPUs as preferred and prefetch locations.
 * Below definitions are used for system memory or for leaving the preferred
 * location unspecified.
 */
enum kfd_ioctl_svm_location {
	KFD_IOCTL_SVM_LOCATION_SYSMEM = 0,
	KFD_IOCTL_SVM_LOCATION_UNDEFINED = 0xffffffff
};

/**
 * kfd_ioctl_svm_attr_type - SVM attribute types
 *
 * @KFD_IOCTL_SVM_ATTR_PREFERRED_LOC: gpuid of the preferred location, 0 for
 *                                    system memory
 * @KFD_IOCTL_SVM_ATTR_PREFETCH_LOC: gpuid of the prefetch location, 0 for
 *                                   system memory. Setting this triggers an
 *                                   immediate prefetch (migration).
 * @KFD_IOCTL_SVM_ATTR_ACCESS:
 * @KFD_IOCTL_SVM_ATTR_ACCESS_IN_PLACE:
 * @KFD_IOCTL_SVM_ATTR_NO_ACCESS: specify memory access for the gpuid given
 *                                by the attribute value
 * @KFD_IOCTL_SVM_ATTR_SET_FLAGS: bitmask of flags to set (see
 *                                KFD_IOCTL_SVM_FLAG_...)
 * @KFD_IOCTL_SVM_ATTR_CLR_FLAGS: bitmask of flags to clear
 * @KFD_IOCTL_SVM_ATTR_GRANULARITY: migration granularity
 *                                  (log2 num pages)
 */
enum kfd_ioctl_svm_attr_type {
	KFD_IOCTL_SVM_ATTR_PREFERRED_LOC,
	KFD_IOCTL_SVM_ATTR_PREFETCH_LOC,
	KFD_IOCTL_SVM_ATTR_ACCESS,
	KFD_IOCTL_SVM_ATTR_ACCESS_IN_PLACE,
	KFD_IOCTL_SVM_ATTR_NO_ACCESS,
	KFD_IOCTL_SVM_ATTR_SET_FLAGS,
	KFD_IOCTL_SVM_ATTR_CLR_FLAGS,
	KFD_IOCTL_SVM_ATTR_GRANULARITY
};

/**
 * kfd_ioctl_svm_attribute - Attributes as pairs of type and value
 *
 * The meaning of the @value depends on the attribute type.
 *
 * @type: attribute type (see enum @kfd_ioctl_svm_attr_type)
 * @value: attribute value
 */
struct kfd_ioctl_svm_attribute {
	__u32 type;
	__u32 value;
};

/**
 * kfd_ioctl_svm_args - Arguments for SVM ioctl
 *
 * @op specifies the operation to perform (see enum
 * @kfd_ioctl_svm_op).  @start_addr and @size are common for all
 * operations.
 *
 * A variable number of attributes can be given in @attrs.
 * @nattr specifies the number of attributes. New attributes can be
 * added in the future without breaking the ABI. If unknown attributes
 * are given, the function returns -EINVAL.
 *
 * @KFD_IOCTL_SVM_OP_SET_ATTR sets attributes for a virtual address
 * range. It may overlap existing virtual address ranges. If it does,
 * the existing ranges will be split such that the attribute changes
 * only apply to the specified address range.
 *
 * @KFD_IOCTL_SVM_OP_GET_ATTR returns the intersection of attributes
 * over all memory in the given range and returns the result as the
 * attribute value. If different pages have different preferred or
 * prefetch locations, 0xffffffff will be returned for
 * @KFD_IOCTL_SVM_ATTR_PREFERRED_LOC or
 * @KFD_IOCTL_SVM_ATTR_PREFETCH_LOC resepctively. For
 * @KFD_IOCTL_SVM_ATTR_SET_FLAGS, flags of all pages will be
 * aggregated by bitwise AND. That means, a flag will be set in the
 * output, if that flag is set for all pages in the range. For
 * @KFD_IOCTL_SVM_ATTR_CLR_FLAGS, flags of all pages will be
 * aggregated by bitwise NOR. That means, a flag will be set in the
 * output, if that flag is clear for all pages in the range.
 * The minimum migration granularity throughout the range will be
 * returned for @KFD_IOCTL_SVM_ATTR_GRANULARITY.
 *
 * Querying of accessibility attributes works by initializing the
 * attribute type to @KFD_IOCTL_SVM_ATTR_ACCESS and the value to the
 * GPUID being queried. Multiple attributes can be given to allow
 * querying multiple GPUIDs. The ioctl function overwrites the
 * attribute type to indicate the access for the specified GPU.
 */
struct kfd_ioctl_svm_args {
	__u64 start_addr;
	__u64 size;
	__u32 op;
	__u32 nattr;
	/* Variable length array of attributes */
	struct kfd_ioctl_svm_attribute attrs[0];
};

/**
 * kfd_ioctl_set_xnack_mode_args - Arguments for set_xnack_mode
 *
 * @xnack_enabled:       [in/out] Whether to enable XNACK mode for this process
 *
 * @xnack_enabled indicates whether recoverable page faults should be
 * enabled for the current process. 0 means disabled, positive means
 * enabled, negative means leave unchanged. If enabled, virtual address
 * translations on GFXv9 and later AMD GPUs can return XNACK and retry
 * the access until a valid PTE is available. This is used to implement
 * device page faults.
 *
 * On output, @xnack_enabled returns the (new) current mode (0 or
 * positive). Therefore, a negative input value can be used to query
 * the current mode without changing it.
 *
 * The XNACK mode fundamentally changes the way SVM managed memory works
 * in the driver, with subtle effects on application performance and
 * functionality.
 *
 * Enabling XNACK mode requires shader programs to be compiled
 * differently. Furthermore, not all GPUs support changing the mode
 * per-process. Therefore changing the mode is only allowed while no
 * user mode queues exist in the process. This ensure that no shader
 * code is running that may be compiled for the wrong mode. And GPUs
 * that cannot change to the requested mode will prevent the XNACK
 * mode from occurring. All GPUs used by the process must be in the
 * same XNACK mode.
 *
 * GFXv8 or older GPUs do not support 48 bit virtual addresses or SVM.
 * Therefore those GPUs are not considered for the XNACK mode switch.
 *
 * Return: 0 on success, -errno on failure
 */
struct kfd_ioctl_set_xnack_mode_args {
	__s32 xnack_enabled;
};

#define AMDKFD_IOCTL_BASE 'K'
#define AMDKFD_IO(nr)			_IO(AMDKFD_IOCTL_BASE, nr)
#define AMDKFD_IOR(nr, type)		_IOR(AMDKFD_IOCTL_BASE, nr, type)
#define AMDKFD_IOW(nr, type)		_IOW(AMDKFD_IOCTL_BASE, nr, type)
#define AMDKFD_IOWR(nr, type)		_IOWR(AMDKFD_IOCTL_BASE, nr, type)

#define AMDKFD_IOC_GET_VERSION			\
		AMDKFD_IOR(0x01, struct kfd_ioctl_get_version_args)

#define AMDKFD_IOC_CREATE_QUEUE			\
		AMDKFD_IOWR(0x02, struct kfd_ioctl_create_queue_args)

#define AMDKFD_IOC_DESTROY_QUEUE		\
		AMDKFD_IOWR(0x03, struct kfd_ioctl_destroy_queue_args)

#define AMDKFD_IOC_SET_MEMORY_POLICY		\
		AMDKFD_IOW(0x04, struct kfd_ioctl_set_memory_policy_args)

#define AMDKFD_IOC_GET_CLOCK_COUNTERS		\
		AMDKFD_IOWR(0x05, struct kfd_ioctl_get_clock_counters_args)

#define AMDKFD_IOC_GET_PROCESS_APERTURES	\
		AMDKFD_IOR(0x06, struct kfd_ioctl_get_process_apertures_args)

#define AMDKFD_IOC_UPDATE_QUEUE			\
		AMDKFD_IOW(0x07, struct kfd_ioctl_update_queue_args)

#define AMDKFD_IOC_CREATE_EVENT			\
		AMDKFD_IOWR(0x08, struct kfd_ioctl_create_event_args)

#define AMDKFD_IOC_DESTROY_EVENT		\
		AMDKFD_IOW(0x09, struct kfd_ioctl_destroy_event_args)

#define AMDKFD_IOC_SET_EVENT			\
		AMDKFD_IOW(0x0A, struct kfd_ioctl_set_event_args)

#define AMDKFD_IOC_RESET_EVENT			\
		AMDKFD_IOW(0x0B, struct kfd_ioctl_reset_event_args)

#define AMDKFD_IOC_WAIT_EVENTS			\
		AMDKFD_IOWR(0x0C, struct kfd_ioctl_wait_events_args)

#define AMDKFD_IOC_DBG_REGISTER			\
		AMDKFD_IOW(0x0D, struct kfd_ioctl_dbg_register_args)

#define AMDKFD_IOC_DBG_UNREGISTER		\
		AMDKFD_IOW(0x0E, struct kfd_ioctl_dbg_unregister_args)

#define AMDKFD_IOC_DBG_ADDRESS_WATCH		\
		AMDKFD_IOW(0x0F, struct kfd_ioctl_dbg_address_watch_args)

#define AMDKFD_IOC_DBG_WAVE_CONTROL		\
		AMDKFD_IOW(0x10, struct kfd_ioctl_dbg_wave_control_args)

#define AMDKFD_IOC_SET_SCRATCH_BACKING_VA	\
		AMDKFD_IOWR(0x11, struct kfd_ioctl_set_scratch_backing_va_args)

#define AMDKFD_IOC_GET_TILE_CONFIG                                      \
		AMDKFD_IOWR(0x12, struct kfd_ioctl_get_tile_config_args)

#define AMDKFD_IOC_SET_TRAP_HANDLER		\
		AMDKFD_IOW(0x13, struct kfd_ioctl_set_trap_handler_args)

#define AMDKFD_IOC_GET_PROCESS_APERTURES_NEW	\
		AMDKFD_IOWR(0x14,		\
			struct kfd_ioctl_get_process_apertures_new_args)

#define AMDKFD_IOC_ACQUIRE_VM			\
		AMDKFD_IOW(0x15, struct kfd_ioctl_acquire_vm_args)

#define AMDKFD_IOC_ALLOC_MEMORY_OF_GPU		\
		AMDKFD_IOWR(0x16, struct kfd_ioctl_alloc_memory_of_gpu_args)

#define AMDKFD_IOC_FREE_MEMORY_OF_GPU		\
		AMDKFD_IOW(0x17, struct kfd_ioctl_free_memory_of_gpu_args)

#define AMDKFD_IOC_MAP_MEMORY_TO_GPU		\
		AMDKFD_IOWR(0x18, struct kfd_ioctl_map_memory_to_gpu_args)

#define AMDKFD_IOC_UNMAP_MEMORY_FROM_GPU	\
		AMDKFD_IOWR(0x19, struct kfd_ioctl_unmap_memory_from_gpu_args)

#define AMDKFD_IOC_SET_CU_MASK		\
		AMDKFD_IOW(0x1A, struct kfd_ioctl_set_cu_mask_args)

#define AMDKFD_IOC_GET_QUEUE_WAVE_STATE		\
		AMDKFD_IOWR(0x1B, struct kfd_ioctl_get_queue_wave_state_args)

#define AMDKFD_IOC_GET_DMABUF_INFO		\
		AMDKFD_IOWR(0x1C, struct kfd_ioctl_get_dmabuf_info_args)

#define AMDKFD_IOC_IMPORT_DMABUF		\
		AMDKFD_IOWR(0x1D, struct kfd_ioctl_import_dmabuf_args)

#define AMDKFD_IOC_ALLOC_QUEUE_GWS		\
		AMDKFD_IOWR(0x1E, struct kfd_ioctl_alloc_queue_gws_args)

#define AMDKFD_IOC_SMI_EVENTS			\
		AMDKFD_IOWR(0x1F, struct kfd_ioctl_smi_events_args)

#define AMDKFD_IOC_SVM	AMDKFD_IOWR(0x20, struct kfd_ioctl_svm_args)

#define AMDKFD_IOC_SET_XNACK_MODE		\
		AMDKFD_IOWR(0x21, struct kfd_ioctl_set_xnack_mode_args)

#define AMDKFD_COMMAND_START		0x01
#define AMDKFD_COMMAND_END		0x22

#endif