1/*
2 * Copyright 2003 Tungsten Graphics, Inc., Cedar Park, Texas.
3 * All Rights Reserved.
4 *
5 * Permission is hereby granted, free of charge, to any person obtaining a
6 * copy of this software and associated documentation files (the
7 * "Software"), to deal in the Software without restriction, including
8 * without limitation the rights to use, copy, modify, merge, publish,
9 * distribute, sub license, and/or sell copies of the Software, and to
10 * permit persons to whom the Software is furnished to do so, subject to
11 * the following conditions:
12 *
13 * The above copyright notice and this permission notice (including the
14 * next paragraph) shall be included in all copies or substantial portions
15 * of the Software.
16 *
17 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
18 * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
19 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT.
20 * IN NO EVENT SHALL TUNGSTEN GRAPHICS AND/OR ITS SUPPLIERS BE LIABLE FOR
21 * ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
22 * TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
23 * SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
24 *
25 */
26
27#ifndef _I915_DRM_H_
28#define _I915_DRM_H_
29
30#include "drm.h"
31
32#if defined(__cplusplus)
33extern "C" {
34#endif
35
36/* Please note that modifications to all structs defined here are
37 * subject to backwards-compatibility constraints.
38 */
39
40/**
41 * DOC: uevents generated by i915 on it's device node
42 *
43 * I915_L3_PARITY_UEVENT - Generated when the driver receives a parity mismatch
44 *	event from the gpu l3 cache. Additional information supplied is ROW,
45 *	BANK, SUBBANK, SLICE of the affected cacheline. Userspace should keep
46 *	track of these events and if a specific cache-line seems to have a
47 *	persistent error remap it with the l3 remapping tool supplied in
48 *	intel-gpu-tools.  The value supplied with the event is always 1.
49 *
50 * I915_ERROR_UEVENT - Generated upon error detection, currently only via
51 *	hangcheck. The error detection event is a good indicator of when things
52 *	began to go badly. The value supplied with the event is a 1 upon error
53 *	detection, and a 0 upon reset completion, signifying no more error
54 *	exists. NOTE: Disabling hangcheck or reset via module parameter will
55 *	cause the related events to not be seen.
56 *
57 * I915_RESET_UEVENT - Event is generated just before an attempt to reset the
58 *	GPU. The value supplied with the event is always 1. NOTE: Disable
59 *	reset via module parameter will cause this event to not be seen.
60 */
61#define I915_L3_PARITY_UEVENT		"L3_PARITY_ERROR"
62#define I915_ERROR_UEVENT		"ERROR"
63#define I915_RESET_UEVENT		"RESET"
64
65/**
66 * struct i915_user_extension - Base class for defining a chain of extensions
67 *
68 * Many interfaces need to grow over time. In most cases we can simply
69 * extend the struct and have userspace pass in more data. Another option,
70 * as demonstrated by Vulkan's approach to providing extensions for forward
71 * and backward compatibility, is to use a list of optional structs to
72 * provide those extra details.
73 *
74 * The key advantage to using an extension chain is that it allows us to
75 * redefine the interface more easily than an ever growing struct of
76 * increasing complexity, and for large parts of that interface to be
77 * entirely optional. The downside is more pointer chasing; chasing across
78 * the boundary with pointers encapsulated inside u64.
79 *
80 * Example chaining:
81 *
82 * .. code-block:: C
83 *
84 *	struct i915_user_extension ext3 {
85 *		.next_extension = 0, // end
86 *		.name = ...,
87 *	};
88 *	struct i915_user_extension ext2 {
89 *		.next_extension = (uintptr_t)&ext3,
90 *		.name = ...,
91 *	};
92 *	struct i915_user_extension ext1 {
93 *		.next_extension = (uintptr_t)&ext2,
94 *		.name = ...,
95 *	};
96 *
97 * Typically the struct i915_user_extension would be embedded in some uAPI
98 * struct, and in this case we would feed it the head of the chain(i.e ext1),
99 * which would then apply all of the above extensions.
100 *
101 */
102struct i915_user_extension {
103	/**
104	 * @next_extension:
105	 *
106	 * Pointer to the next struct i915_user_extension, or zero if the end.
107	 */
108	__u64 next_extension;
109	/**
110	 * @name: Name of the extension.
111	 *
112	 * Note that the name here is just some integer.
113	 *
114	 * Also note that the name space for this is not global for the whole
115	 * driver, but rather its scope/meaning is limited to the specific piece
116	 * of uAPI which has embedded the struct i915_user_extension.
117	 */
118	__u32 name;
119	/**
120	 * @flags: MBZ
121	 *
122	 * All undefined bits must be zero.
123	 */
124	__u32 flags;
125	/**
126	 * @rsvd: MBZ
127	 *
128	 * Reserved for future use; must be zero.
129	 */
130	__u32 rsvd[4];
131};
132
133/*
134 * MOCS indexes used for GPU surfaces, defining the cacheability of the
135 * surface data and the coherency for this data wrt. CPU vs. GPU accesses.
136 */
137enum i915_mocs_table_index {
138	/*
139	 * Not cached anywhere, coherency between CPU and GPU accesses is
140	 * guaranteed.
141	 */
142	I915_MOCS_UNCACHED,
143	/*
144	 * Cacheability and coherency controlled by the kernel automatically
145	 * based on the DRM_I915_GEM_SET_CACHING IOCTL setting and the current
146	 * usage of the surface (used for display scanout or not).
147	 */
148	I915_MOCS_PTE,
149	/*
150	 * Cached in all GPU caches available on the platform.
151	 * Coherency between CPU and GPU accesses to the surface is not
152	 * guaranteed without extra synchronization.
153	 */
154	I915_MOCS_CACHED,
155};
156
157/**
158 * enum drm_i915_gem_engine_class - uapi engine type enumeration
159 *
160 * Different engines serve different roles, and there may be more than one
161 * engine serving each role.  This enum provides a classification of the role
162 * of the engine, which may be used when requesting operations to be performed
163 * on a certain subset of engines, or for providing information about that
164 * group.
165 */
166enum drm_i915_gem_engine_class {
167	/**
168	 * @I915_ENGINE_CLASS_RENDER:
169	 *
170	 * Render engines support instructions used for 3D, Compute (GPGPU),
171	 * and programmable media workloads.  These instructions fetch data and
172	 * dispatch individual work items to threads that operate in parallel.
173	 * The threads run small programs (called "kernels" or "shaders") on
174	 * the GPU's execution units (EUs).
175	 */
176	I915_ENGINE_CLASS_RENDER	= 0,
177
178	/**
179	 * @I915_ENGINE_CLASS_COPY:
180	 *
181	 * Copy engines (also referred to as "blitters") support instructions
182	 * that move blocks of data from one location in memory to another,
183	 * or that fill a specified location of memory with fixed data.
184	 * Copy engines can perform pre-defined logical or bitwise operations
185	 * on the source, destination, or pattern data.
186	 */
187	I915_ENGINE_CLASS_COPY		= 1,
188
189	/**
190	 * @I915_ENGINE_CLASS_VIDEO:
191	 *
192	 * Video engines (also referred to as "bit stream decode" (BSD) or
193	 * "vdbox") support instructions that perform fixed-function media
194	 * decode and encode.
195	 */
196	I915_ENGINE_CLASS_VIDEO		= 2,
197
198	/**
199	 * @I915_ENGINE_CLASS_VIDEO_ENHANCE:
200	 *
201	 * Video enhancement engines (also referred to as "vebox") support
202	 * instructions related to image enhancement.
203	 */
204	I915_ENGINE_CLASS_VIDEO_ENHANCE	= 3,
205
206	/**
207	 * @I915_ENGINE_CLASS_COMPUTE:
208	 *
209	 * Compute engines support a subset of the instructions available
210	 * on render engines:  compute engines support Compute (GPGPU) and
211	 * programmable media workloads, but do not support the 3D pipeline.
212	 */
213	I915_ENGINE_CLASS_COMPUTE	= 4,
214
215	/* Values in this enum should be kept compact. */
216
217	/**
218	 * @I915_ENGINE_CLASS_INVALID:
219	 *
220	 * Placeholder value to represent an invalid engine class assignment.
221	 */
222	I915_ENGINE_CLASS_INVALID	= -1
223};
224
225/**
226 * struct i915_engine_class_instance - Engine class/instance identifier
227 *
228 * There may be more than one engine fulfilling any role within the system.
229 * Each engine of a class is given a unique instance number and therefore
230 * any engine can be specified by its class:instance tuplet. APIs that allow
231 * access to any engine in the system will use struct i915_engine_class_instance
232 * for this identification.
233 */
234struct i915_engine_class_instance {
235	/**
236	 * @engine_class:
237	 *
238	 * Engine class from enum drm_i915_gem_engine_class
239	 */
240	__u16 engine_class;
241#define I915_ENGINE_CLASS_INVALID_NONE -1
242#define I915_ENGINE_CLASS_INVALID_VIRTUAL -2
243
244	/**
245	 * @engine_instance:
246	 *
247	 * Engine instance.
248	 */
249	__u16 engine_instance;
250};
251
252/**
253 * DOC: perf_events exposed by i915 through /sys/bus/event_sources/drivers/i915
254 *
255 */
256
257enum drm_i915_pmu_engine_sample {
258	I915_SAMPLE_BUSY = 0,
259	I915_SAMPLE_WAIT = 1,
260	I915_SAMPLE_SEMA = 2
261};
262
263#define I915_PMU_SAMPLE_BITS (4)
264#define I915_PMU_SAMPLE_MASK (0xf)
265#define I915_PMU_SAMPLE_INSTANCE_BITS (8)
266#define I915_PMU_CLASS_SHIFT \
267	(I915_PMU_SAMPLE_BITS + I915_PMU_SAMPLE_INSTANCE_BITS)
268
269#define __I915_PMU_ENGINE(class, instance, sample) \
270	((class) << I915_PMU_CLASS_SHIFT | \
271	(instance) << I915_PMU_SAMPLE_BITS | \
272	(sample))
273
274#define I915_PMU_ENGINE_BUSY(class, instance) \
275	__I915_PMU_ENGINE(class, instance, I915_SAMPLE_BUSY)
276
277#define I915_PMU_ENGINE_WAIT(class, instance) \
278	__I915_PMU_ENGINE(class, instance, I915_SAMPLE_WAIT)
279
280#define I915_PMU_ENGINE_SEMA(class, instance) \
281	__I915_PMU_ENGINE(class, instance, I915_SAMPLE_SEMA)
282
283#define __I915_PMU_OTHER(x) (__I915_PMU_ENGINE(0xff, 0xff, 0xf) + 1 + (x))
284
285#define I915_PMU_ACTUAL_FREQUENCY	__I915_PMU_OTHER(0)
286#define I915_PMU_REQUESTED_FREQUENCY	__I915_PMU_OTHER(1)
287#define I915_PMU_INTERRUPTS		__I915_PMU_OTHER(2)
288#define I915_PMU_RC6_RESIDENCY		__I915_PMU_OTHER(3)
289#define I915_PMU_SOFTWARE_GT_AWAKE_TIME	__I915_PMU_OTHER(4)
290
291#define I915_PMU_LAST /* Deprecated - do not use */ I915_PMU_RC6_RESIDENCY
292
293/* Each region is a minimum of 16k, and there are at most 255 of them.
294 */
295#define I915_NR_TEX_REGIONS 255	/* table size 2k - maximum due to use
296				 * of chars for next/prev indices */
297#define I915_LOG_MIN_TEX_REGION_SIZE 14
298
299typedef struct _drm_i915_init {
300	enum {
301		I915_INIT_DMA = 0x01,
302		I915_CLEANUP_DMA = 0x02,
303		I915_RESUME_DMA = 0x03
304	} func;
305	unsigned int mmio_offset;
306	int sarea_priv_offset;
307	unsigned int ring_start;
308	unsigned int ring_end;
309	unsigned int ring_size;
310	unsigned int front_offset;
311	unsigned int back_offset;
312	unsigned int depth_offset;
313	unsigned int w;
314	unsigned int h;
315	unsigned int pitch;
316	unsigned int pitch_bits;
317	unsigned int back_pitch;
318	unsigned int depth_pitch;
319	unsigned int cpp;
320	unsigned int chipset;
321} drm_i915_init_t;
322
323typedef struct _drm_i915_sarea {
324	struct drm_tex_region texList[I915_NR_TEX_REGIONS + 1];
325	int last_upload;	/* last time texture was uploaded */
326	int last_enqueue;	/* last time a buffer was enqueued */
327	int last_dispatch;	/* age of the most recently dispatched buffer */
328	int ctxOwner;		/* last context to upload state */
329	int texAge;
330	int pf_enabled;		/* is pageflipping allowed? */
331	int pf_active;
332	int pf_current_page;	/* which buffer is being displayed? */
333	int perf_boxes;		/* performance boxes to be displayed */
334	int width, height;      /* screen size in pixels */
335
336	drm_handle_t front_handle;
337	int front_offset;
338	int front_size;
339
340	drm_handle_t back_handle;
341	int back_offset;
342	int back_size;
343
344	drm_handle_t depth_handle;
345	int depth_offset;
346	int depth_size;
347
348	drm_handle_t tex_handle;
349	int tex_offset;
350	int tex_size;
351	int log_tex_granularity;
352	int pitch;
353	int rotation;           /* 0, 90, 180 or 270 */
354	int rotated_offset;
355	int rotated_size;
356	int rotated_pitch;
357	int virtualX, virtualY;
358
359	unsigned int front_tiled;
360	unsigned int back_tiled;
361	unsigned int depth_tiled;
362	unsigned int rotated_tiled;
363	unsigned int rotated2_tiled;
364
365	int pipeA_x;
366	int pipeA_y;
367	int pipeA_w;
368	int pipeA_h;
369	int pipeB_x;
370	int pipeB_y;
371	int pipeB_w;
372	int pipeB_h;
373
374	/* fill out some space for old userspace triple buffer */
375	drm_handle_t unused_handle;
376	__u32 unused1, unused2, unused3;
377
378	/* buffer object handles for static buffers. May change
379	 * over the lifetime of the client.
380	 */
381	__u32 front_bo_handle;
382	__u32 back_bo_handle;
383	__u32 unused_bo_handle;
384	__u32 depth_bo_handle;
385
386} drm_i915_sarea_t;
387
388/* due to userspace building against these headers we need some compat here */
389#define planeA_x pipeA_x
390#define planeA_y pipeA_y
391#define planeA_w pipeA_w
392#define planeA_h pipeA_h
393#define planeB_x pipeB_x
394#define planeB_y pipeB_y
395#define planeB_w pipeB_w
396#define planeB_h pipeB_h
397
398/* Flags for perf_boxes
399 */
400#define I915_BOX_RING_EMPTY    0x1
401#define I915_BOX_FLIP          0x2
402#define I915_BOX_WAIT          0x4
403#define I915_BOX_TEXTURE_LOAD  0x8
404#define I915_BOX_LOST_CONTEXT  0x10
405
406/*
407 * i915 specific ioctls.
408 *
409 * The device specific ioctl range is [DRM_COMMAND_BASE, DRM_COMMAND_END) ie
410 * [0x40, 0xa0) (a0 is excluded). The numbers below are defined as offset
411 * against DRM_COMMAND_BASE and should be between [0x0, 0x60).
412 */
413#define DRM_I915_INIT		0x00
414#define DRM_I915_FLUSH		0x01
415#define DRM_I915_FLIP		0x02
416#define DRM_I915_BATCHBUFFER	0x03
417#define DRM_I915_IRQ_EMIT	0x04
418#define DRM_I915_IRQ_WAIT	0x05
419#define DRM_I915_GETPARAM	0x06
420#define DRM_I915_SETPARAM	0x07
421#define DRM_I915_ALLOC		0x08
422#define DRM_I915_FREE		0x09
423#define DRM_I915_INIT_HEAP	0x0a
424#define DRM_I915_CMDBUFFER	0x0b
425#define DRM_I915_DESTROY_HEAP	0x0c
426#define DRM_I915_SET_VBLANK_PIPE	0x0d
427#define DRM_I915_GET_VBLANK_PIPE	0x0e
428#define DRM_I915_VBLANK_SWAP	0x0f
429#define DRM_I915_HWS_ADDR	0x11
430#define DRM_I915_GEM_INIT	0x13
431#define DRM_I915_GEM_EXECBUFFER	0x14
432#define DRM_I915_GEM_PIN	0x15
433#define DRM_I915_GEM_UNPIN	0x16
434#define DRM_I915_GEM_BUSY	0x17
435#define DRM_I915_GEM_THROTTLE	0x18
436#define DRM_I915_GEM_ENTERVT	0x19
437#define DRM_I915_GEM_LEAVEVT	0x1a
438#define DRM_I915_GEM_CREATE	0x1b
439#define DRM_I915_GEM_PREAD	0x1c
440#define DRM_I915_GEM_PWRITE	0x1d
441#define DRM_I915_GEM_MMAP	0x1e
442#define DRM_I915_GEM_SET_DOMAIN	0x1f
443#define DRM_I915_GEM_SW_FINISH	0x20
444#define DRM_I915_GEM_SET_TILING	0x21
445#define DRM_I915_GEM_GET_TILING	0x22
446#define DRM_I915_GEM_GET_APERTURE 0x23
447#define DRM_I915_GEM_MMAP_GTT	0x24
448#define DRM_I915_GET_PIPE_FROM_CRTC_ID	0x25
449#define DRM_I915_GEM_MADVISE	0x26
450#define DRM_I915_OVERLAY_PUT_IMAGE	0x27
451#define DRM_I915_OVERLAY_ATTRS	0x28
452#define DRM_I915_GEM_EXECBUFFER2	0x29
453#define DRM_I915_GEM_EXECBUFFER2_WR	DRM_I915_GEM_EXECBUFFER2
454#define DRM_I915_GET_SPRITE_COLORKEY	0x2a
455#define DRM_I915_SET_SPRITE_COLORKEY	0x2b
456#define DRM_I915_GEM_WAIT	0x2c
457#define DRM_I915_GEM_CONTEXT_CREATE	0x2d
458#define DRM_I915_GEM_CONTEXT_DESTROY	0x2e
459#define DRM_I915_GEM_SET_CACHING	0x2f
460#define DRM_I915_GEM_GET_CACHING	0x30
461#define DRM_I915_REG_READ		0x31
462#define DRM_I915_GET_RESET_STATS	0x32
463#define DRM_I915_GEM_USERPTR		0x33
464#define DRM_I915_GEM_CONTEXT_GETPARAM	0x34
465#define DRM_I915_GEM_CONTEXT_SETPARAM	0x35
466#define DRM_I915_PERF_OPEN		0x36
467#define DRM_I915_PERF_ADD_CONFIG	0x37
468#define DRM_I915_PERF_REMOVE_CONFIG	0x38
469#define DRM_I915_QUERY			0x39
470#define DRM_I915_GEM_VM_CREATE		0x3a
471#define DRM_I915_GEM_VM_DESTROY		0x3b
472#define DRM_I915_GEM_CREATE_EXT		0x3c
473/* Must be kept compact -- no holes */
474
475#define DRM_IOCTL_I915_INIT		DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t)
476#define DRM_IOCTL_I915_FLUSH		DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH)
477#define DRM_IOCTL_I915_FLIP		DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLIP)
478#define DRM_IOCTL_I915_BATCHBUFFER	DRM_IOW( DRM_COMMAND_BASE + DRM_I915_BATCHBUFFER, drm_i915_batchbuffer_t)
479#define DRM_IOCTL_I915_IRQ_EMIT         DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_IRQ_EMIT, drm_i915_irq_emit_t)
480#define DRM_IOCTL_I915_IRQ_WAIT         DRM_IOW( DRM_COMMAND_BASE + DRM_I915_IRQ_WAIT, drm_i915_irq_wait_t)
481#define DRM_IOCTL_I915_GETPARAM         DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GETPARAM, drm_i915_getparam_t)
482#define DRM_IOCTL_I915_SETPARAM         DRM_IOW( DRM_COMMAND_BASE + DRM_I915_SETPARAM, drm_i915_setparam_t)
483#define DRM_IOCTL_I915_ALLOC            DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_ALLOC, drm_i915_mem_alloc_t)
484#define DRM_IOCTL_I915_FREE             DRM_IOW( DRM_COMMAND_BASE + DRM_I915_FREE, drm_i915_mem_free_t)
485#define DRM_IOCTL_I915_INIT_HEAP        DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT_HEAP, drm_i915_mem_init_heap_t)
486#define DRM_IOCTL_I915_CMDBUFFER	DRM_IOW( DRM_COMMAND_BASE + DRM_I915_CMDBUFFER, drm_i915_cmdbuffer_t)
487#define DRM_IOCTL_I915_DESTROY_HEAP	DRM_IOW( DRM_COMMAND_BASE + DRM_I915_DESTROY_HEAP, drm_i915_mem_destroy_heap_t)
488#define DRM_IOCTL_I915_SET_VBLANK_PIPE	DRM_IOW( DRM_COMMAND_BASE + DRM_I915_SET_VBLANK_PIPE, drm_i915_vblank_pipe_t)
489#define DRM_IOCTL_I915_GET_VBLANK_PIPE	DRM_IOR( DRM_COMMAND_BASE + DRM_I915_GET_VBLANK_PIPE, drm_i915_vblank_pipe_t)
490#define DRM_IOCTL_I915_VBLANK_SWAP	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_VBLANK_SWAP, drm_i915_vblank_swap_t)
491#define DRM_IOCTL_I915_HWS_ADDR		DRM_IOW(DRM_COMMAND_BASE + DRM_I915_HWS_ADDR, struct drm_i915_gem_init)
492#define DRM_IOCTL_I915_GEM_INIT		DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_INIT, struct drm_i915_gem_init)
493#define DRM_IOCTL_I915_GEM_EXECBUFFER	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_EXECBUFFER, struct drm_i915_gem_execbuffer)
494#define DRM_IOCTL_I915_GEM_EXECBUFFER2	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_EXECBUFFER2, struct drm_i915_gem_execbuffer2)
495#define DRM_IOCTL_I915_GEM_EXECBUFFER2_WR	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_EXECBUFFER2_WR, struct drm_i915_gem_execbuffer2)
496#define DRM_IOCTL_I915_GEM_PIN		DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_PIN, struct drm_i915_gem_pin)
497#define DRM_IOCTL_I915_GEM_UNPIN	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_UNPIN, struct drm_i915_gem_unpin)
498#define DRM_IOCTL_I915_GEM_BUSY		DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_BUSY, struct drm_i915_gem_busy)
499#define DRM_IOCTL_I915_GEM_SET_CACHING		DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_SET_CACHING, struct drm_i915_gem_caching)
500#define DRM_IOCTL_I915_GEM_GET_CACHING		DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_GET_CACHING, struct drm_i915_gem_caching)
501#define DRM_IOCTL_I915_GEM_THROTTLE	DRM_IO ( DRM_COMMAND_BASE + DRM_I915_GEM_THROTTLE)
502#define DRM_IOCTL_I915_GEM_ENTERVT	DRM_IO(DRM_COMMAND_BASE + DRM_I915_GEM_ENTERVT)
503#define DRM_IOCTL_I915_GEM_LEAVEVT	DRM_IO(DRM_COMMAND_BASE + DRM_I915_GEM_LEAVEVT)
504#define DRM_IOCTL_I915_GEM_CREATE	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_CREATE, struct drm_i915_gem_create)
505#define DRM_IOCTL_I915_GEM_CREATE_EXT	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_CREATE_EXT, struct drm_i915_gem_create_ext)
506#define DRM_IOCTL_I915_GEM_PREAD	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_PREAD, struct drm_i915_gem_pread)
507#define DRM_IOCTL_I915_GEM_PWRITE	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_PWRITE, struct drm_i915_gem_pwrite)
508#define DRM_IOCTL_I915_GEM_MMAP		DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP, struct drm_i915_gem_mmap)
509#define DRM_IOCTL_I915_GEM_MMAP_GTT	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP_GTT, struct drm_i915_gem_mmap_gtt)
510#define DRM_IOCTL_I915_GEM_MMAP_OFFSET	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP_GTT, struct drm_i915_gem_mmap_offset)
511#define DRM_IOCTL_I915_GEM_SET_DOMAIN	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SET_DOMAIN, struct drm_i915_gem_set_domain)
512#define DRM_IOCTL_I915_GEM_SW_FINISH	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SW_FINISH, struct drm_i915_gem_sw_finish)
513#define DRM_IOCTL_I915_GEM_SET_TILING	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_SET_TILING, struct drm_i915_gem_set_tiling)
514#define DRM_IOCTL_I915_GEM_GET_TILING	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_GET_TILING, struct drm_i915_gem_get_tiling)
515#define DRM_IOCTL_I915_GEM_GET_APERTURE	DRM_IOR  (DRM_COMMAND_BASE + DRM_I915_GEM_GET_APERTURE, struct drm_i915_gem_get_aperture)
516#define DRM_IOCTL_I915_GET_PIPE_FROM_CRTC_ID DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GET_PIPE_FROM_CRTC_ID, struct drm_i915_get_pipe_from_crtc_id)
517#define DRM_IOCTL_I915_GEM_MADVISE	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MADVISE, struct drm_i915_gem_madvise)
518#define DRM_IOCTL_I915_OVERLAY_PUT_IMAGE	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_OVERLAY_PUT_IMAGE, struct drm_intel_overlay_put_image)
519#define DRM_IOCTL_I915_OVERLAY_ATTRS	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_OVERLAY_ATTRS, struct drm_intel_overlay_attrs)
520#define DRM_IOCTL_I915_SET_SPRITE_COLORKEY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_SET_SPRITE_COLORKEY, struct drm_intel_sprite_colorkey)
521#define DRM_IOCTL_I915_GET_SPRITE_COLORKEY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GET_SPRITE_COLORKEY, struct drm_intel_sprite_colorkey)
522#define DRM_IOCTL_I915_GEM_WAIT		DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_WAIT, struct drm_i915_gem_wait)
523#define DRM_IOCTL_I915_GEM_CONTEXT_CREATE	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_CREATE, struct drm_i915_gem_context_create)
524#define DRM_IOCTL_I915_GEM_CONTEXT_CREATE_EXT	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_CREATE, struct drm_i915_gem_context_create_ext)
525#define DRM_IOCTL_I915_GEM_CONTEXT_DESTROY	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_DESTROY, struct drm_i915_gem_context_destroy)
526#define DRM_IOCTL_I915_REG_READ			DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_REG_READ, struct drm_i915_reg_read)
527#define DRM_IOCTL_I915_GET_RESET_STATS		DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GET_RESET_STATS, struct drm_i915_reset_stats)
528#define DRM_IOCTL_I915_GEM_USERPTR			DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_USERPTR, struct drm_i915_gem_userptr)
529#define DRM_IOCTL_I915_GEM_CONTEXT_GETPARAM	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_GETPARAM, struct drm_i915_gem_context_param)
530#define DRM_IOCTL_I915_GEM_CONTEXT_SETPARAM	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_SETPARAM, struct drm_i915_gem_context_param)
531#define DRM_IOCTL_I915_PERF_OPEN	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_OPEN, struct drm_i915_perf_open_param)
532#define DRM_IOCTL_I915_PERF_ADD_CONFIG	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_ADD_CONFIG, struct drm_i915_perf_oa_config)
533#define DRM_IOCTL_I915_PERF_REMOVE_CONFIG	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_REMOVE_CONFIG, __u64)
534#define DRM_IOCTL_I915_QUERY			DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_QUERY, struct drm_i915_query)
535#define DRM_IOCTL_I915_GEM_VM_CREATE	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_VM_CREATE, struct drm_i915_gem_vm_control)
536#define DRM_IOCTL_I915_GEM_VM_DESTROY	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_VM_DESTROY, struct drm_i915_gem_vm_control)
537
538/* Allow drivers to submit batchbuffers directly to hardware, relying
539 * on the security mechanisms provided by hardware.
540 */
541typedef struct drm_i915_batchbuffer {
542	int start;		/* agp offset */
543	int used;		/* nr bytes in use */
544	int DR1;		/* hw flags for GFX_OP_DRAWRECT_INFO */
545	int DR4;		/* window origin for GFX_OP_DRAWRECT_INFO */
546	int num_cliprects;	/* mulitpass with multiple cliprects? */
547	struct drm_clip_rect *cliprects;	/* pointer to userspace cliprects */
548} drm_i915_batchbuffer_t;
549
550/* As above, but pass a pointer to userspace buffer which can be
551 * validated by the kernel prior to sending to hardware.
552 */
553typedef struct _drm_i915_cmdbuffer {
554	char *buf;	/* pointer to userspace command buffer */
555	int sz;			/* nr bytes in buf */
556	int DR1;		/* hw flags for GFX_OP_DRAWRECT_INFO */
557	int DR4;		/* window origin for GFX_OP_DRAWRECT_INFO */
558	int num_cliprects;	/* mulitpass with multiple cliprects? */
559	struct drm_clip_rect *cliprects;	/* pointer to userspace cliprects */
560} drm_i915_cmdbuffer_t;
561
562/* Userspace can request & wait on irq's:
563 */
564typedef struct drm_i915_irq_emit {
565	int *irq_seq;
566} drm_i915_irq_emit_t;
567
568typedef struct drm_i915_irq_wait {
569	int irq_seq;
570} drm_i915_irq_wait_t;
571
572/*
573 * Different modes of per-process Graphics Translation Table,
574 * see I915_PARAM_HAS_ALIASING_PPGTT
575 */
576#define I915_GEM_PPGTT_NONE	0
577#define I915_GEM_PPGTT_ALIASING	1
578#define I915_GEM_PPGTT_FULL	2
579
580/* Ioctl to query kernel params:
581 */
582#define I915_PARAM_IRQ_ACTIVE            1
583#define I915_PARAM_ALLOW_BATCHBUFFER     2
584#define I915_PARAM_LAST_DISPATCH         3
585#define I915_PARAM_CHIPSET_ID            4
586#define I915_PARAM_HAS_GEM               5
587#define I915_PARAM_NUM_FENCES_AVAIL      6
588#define I915_PARAM_HAS_OVERLAY           7
589#define I915_PARAM_HAS_PAGEFLIPPING	 8
590#define I915_PARAM_HAS_EXECBUF2          9
591#define I915_PARAM_HAS_BSD		 10
592#define I915_PARAM_HAS_BLT		 11
593#define I915_PARAM_HAS_RELAXED_FENCING	 12
594#define I915_PARAM_HAS_COHERENT_RINGS	 13
595#define I915_PARAM_HAS_EXEC_CONSTANTS	 14
596#define I915_PARAM_HAS_RELAXED_DELTA	 15
597#define I915_PARAM_HAS_GEN7_SOL_RESET	 16
598#define I915_PARAM_HAS_LLC     	 	 17
599#define I915_PARAM_HAS_ALIASING_PPGTT	 18
600#define I915_PARAM_HAS_WAIT_TIMEOUT	 19
601#define I915_PARAM_HAS_SEMAPHORES	 20
602#define I915_PARAM_HAS_PRIME_VMAP_FLUSH	 21
603#define I915_PARAM_HAS_VEBOX		 22
604#define I915_PARAM_HAS_SECURE_BATCHES	 23
605#define I915_PARAM_HAS_PINNED_BATCHES	 24
606#define I915_PARAM_HAS_EXEC_NO_RELOC	 25
607#define I915_PARAM_HAS_EXEC_HANDLE_LUT   26
608#define I915_PARAM_HAS_WT     	 	 27
609#define I915_PARAM_CMD_PARSER_VERSION	 28
610#define I915_PARAM_HAS_COHERENT_PHYS_GTT 29
611#define I915_PARAM_MMAP_VERSION          30
612#define I915_PARAM_HAS_BSD2		 31
613#define I915_PARAM_REVISION              32
614#define I915_PARAM_SUBSLICE_TOTAL	 33
615#define I915_PARAM_EU_TOTAL		 34
616#define I915_PARAM_HAS_GPU_RESET	 35
617#define I915_PARAM_HAS_RESOURCE_STREAMER 36
618#define I915_PARAM_HAS_EXEC_SOFTPIN	 37
619#define I915_PARAM_HAS_POOLED_EU	 38
620#define I915_PARAM_MIN_EU_IN_POOL	 39
621#define I915_PARAM_MMAP_GTT_VERSION	 40
622
623/*
624 * Query whether DRM_I915_GEM_EXECBUFFER2 supports user defined execution
625 * priorities and the driver will attempt to execute batches in priority order.
626 * The param returns a capability bitmask, nonzero implies that the scheduler
627 * is enabled, with different features present according to the mask.
628 *
629 * The initial priority for each batch is supplied by the context and is
630 * controlled via I915_CONTEXT_PARAM_PRIORITY.
631 */
632#define I915_PARAM_HAS_SCHEDULER	 41
633#define   I915_SCHEDULER_CAP_ENABLED	(1ul << 0)
634#define   I915_SCHEDULER_CAP_PRIORITY	(1ul << 1)
635#define   I915_SCHEDULER_CAP_PREEMPTION	(1ul << 2)
636#define   I915_SCHEDULER_CAP_SEMAPHORES	(1ul << 3)
637#define   I915_SCHEDULER_CAP_ENGINE_BUSY_STATS	(1ul << 4)
638/*
639 * Indicates the 2k user priority levels are statically mapped into 3 buckets as
640 * follows:
641 *
642 * -1k to -1	Low priority
643 * 0		Normal priority
644 * 1 to 1k	Highest priority
645 */
646#define   I915_SCHEDULER_CAP_STATIC_PRIORITY_MAP	(1ul << 5)
647
648#define I915_PARAM_HUC_STATUS		 42
649
650/* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to opt-out of
651 * synchronisation with implicit fencing on individual objects.
652 * See EXEC_OBJECT_ASYNC.
653 */
654#define I915_PARAM_HAS_EXEC_ASYNC	 43
655
656/* Query whether DRM_I915_GEM_EXECBUFFER2 supports explicit fence support -
657 * both being able to pass in a sync_file fd to wait upon before executing,
658 * and being able to return a new sync_file fd that is signaled when the
659 * current request is complete. See I915_EXEC_FENCE_IN and I915_EXEC_FENCE_OUT.
660 */
661#define I915_PARAM_HAS_EXEC_FENCE	 44
662
663/* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to capture
664 * user specified bufffers for post-mortem debugging of GPU hangs. See
665 * EXEC_OBJECT_CAPTURE.
666 */
667#define I915_PARAM_HAS_EXEC_CAPTURE	 45
668
669#define I915_PARAM_SLICE_MASK		 46
670
671/* Assuming it's uniform for each slice, this queries the mask of subslices
672 * per-slice for this system.
673 */
674#define I915_PARAM_SUBSLICE_MASK	 47
675
676/*
677 * Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying the batch buffer
678 * as the first execobject as opposed to the last. See I915_EXEC_BATCH_FIRST.
679 */
680#define I915_PARAM_HAS_EXEC_BATCH_FIRST	 48
681
682/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of
683 * drm_i915_gem_exec_fence structures.  See I915_EXEC_FENCE_ARRAY.
684 */
685#define I915_PARAM_HAS_EXEC_FENCE_ARRAY  49
686
687/*
688 * Query whether every context (both per-file default and user created) is
689 * isolated (insofar as HW supports). If this parameter is not true, then
690 * freshly created contexts may inherit values from an existing context,
691 * rather than default HW values. If true, it also ensures (insofar as HW
692 * supports) that all state set by this context will not leak to any other
693 * context.
694 *
695 * As not every engine across every gen support contexts, the returned
696 * value reports the support of context isolation for individual engines by
697 * returning a bitmask of each engine class set to true if that class supports
698 * isolation.
699 */
700#define I915_PARAM_HAS_CONTEXT_ISOLATION 50
701
702/* Frequency of the command streamer timestamps given by the *_TIMESTAMP
703 * registers. This used to be fixed per platform but from CNL onwards, this
704 * might vary depending on the parts.
705 */
706#define I915_PARAM_CS_TIMESTAMP_FREQUENCY 51
707
708/*
709 * Once upon a time we supposed that writes through the GGTT would be
710 * immediately in physical memory (once flushed out of the CPU path). However,
711 * on a few different processors and chipsets, this is not necessarily the case
712 * as the writes appear to be buffered internally. Thus a read of the backing
713 * storage (physical memory) via a different path (with different physical tags
714 * to the indirect write via the GGTT) will see stale values from before
715 * the GGTT write. Inside the kernel, we can for the most part keep track of
716 * the different read/write domains in use (e.g. set-domain), but the assumption
717 * of coherency is baked into the ABI, hence reporting its true state in this
718 * parameter.
719 *
720 * Reports true when writes via mmap_gtt are immediately visible following an
721 * lfence to flush the WCB.
722 *
723 * Reports false when writes via mmap_gtt are indeterminately delayed in an in
724 * internal buffer and are _not_ immediately visible to third parties accessing
725 * directly via mmap_cpu/mmap_wc. Use of mmap_gtt as part of an IPC
726 * communications channel when reporting false is strongly disadvised.
727 */
728#define I915_PARAM_MMAP_GTT_COHERENT	52
729
730/*
731 * Query whether DRM_I915_GEM_EXECBUFFER2 supports coordination of parallel
732 * execution through use of explicit fence support.
733 * See I915_EXEC_FENCE_OUT and I915_EXEC_FENCE_SUBMIT.
734 */
735#define I915_PARAM_HAS_EXEC_SUBMIT_FENCE 53
736
737/*
738 * Revision of the i915-perf uAPI. The value returned helps determine what
739 * i915-perf features are available. See drm_i915_perf_property_id.
740 */
741#define I915_PARAM_PERF_REVISION	54
742
743/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of
744 * timeline syncobj through drm_i915_gem_execbuffer_ext_timeline_fences. See
745 * I915_EXEC_USE_EXTENSIONS.
746 */
747#define I915_PARAM_HAS_EXEC_TIMELINE_FENCES 55
748
749/* Query if the kernel supports the I915_USERPTR_PROBE flag. */
750#define I915_PARAM_HAS_USERPTR_PROBE 56
751
752/* Must be kept compact -- no holes and well documented */
753
754/**
755 * struct drm_i915_getparam - Driver parameter query structure.
756 */
757struct drm_i915_getparam {
758	/** @param: Driver parameter to query. */
759	__s32 param;
760
761	/**
762	 * @value: Address of memory where queried value should be put.
763	 *
764	 * WARNING: Using pointers instead of fixed-size u64 means we need to write
765	 * compat32 code. Don't repeat this mistake.
766	 */
767	int *value;
768};
769
770/**
771 * typedef drm_i915_getparam_t - Driver parameter query structure.
772 * See struct drm_i915_getparam.
773 */
774typedef struct drm_i915_getparam drm_i915_getparam_t;
775
776/* Ioctl to set kernel params:
777 */
778#define I915_SETPARAM_USE_MI_BATCHBUFFER_START            1
779#define I915_SETPARAM_TEX_LRU_LOG_GRANULARITY             2
780#define I915_SETPARAM_ALLOW_BATCHBUFFER                   3
781#define I915_SETPARAM_NUM_USED_FENCES                     4
782/* Must be kept compact -- no holes */
783
784typedef struct drm_i915_setparam {
785	int param;
786	int value;
787} drm_i915_setparam_t;
788
789/* A memory manager for regions of shared memory:
790 */
791#define I915_MEM_REGION_AGP 1
792
793typedef struct drm_i915_mem_alloc {
794	int region;
795	int alignment;
796	int size;
797	int *region_offset;	/* offset from start of fb or agp */
798} drm_i915_mem_alloc_t;
799
800typedef struct drm_i915_mem_free {
801	int region;
802	int region_offset;
803} drm_i915_mem_free_t;
804
805typedef struct drm_i915_mem_init_heap {
806	int region;
807	int size;
808	int start;
809} drm_i915_mem_init_heap_t;
810
811/* Allow memory manager to be torn down and re-initialized (eg on
812 * rotate):
813 */
814typedef struct drm_i915_mem_destroy_heap {
815	int region;
816} drm_i915_mem_destroy_heap_t;
817
818/* Allow X server to configure which pipes to monitor for vblank signals
819 */
820#define	DRM_I915_VBLANK_PIPE_A	1
821#define	DRM_I915_VBLANK_PIPE_B	2
822
823typedef struct drm_i915_vblank_pipe {
824	int pipe;
825} drm_i915_vblank_pipe_t;
826
827/* Schedule buffer swap at given vertical blank:
828 */
829typedef struct drm_i915_vblank_swap {
830	drm_drawable_t drawable;
831	enum drm_vblank_seq_type seqtype;
832	unsigned int sequence;
833} drm_i915_vblank_swap_t;
834
835typedef struct drm_i915_hws_addr {
836	__u64 addr;
837} drm_i915_hws_addr_t;
838
839struct drm_i915_gem_init {
840	/**
841	 * Beginning offset in the GTT to be managed by the DRM memory
842	 * manager.
843	 */
844	__u64 gtt_start;
845	/**
846	 * Ending offset in the GTT to be managed by the DRM memory
847	 * manager.
848	 */
849	__u64 gtt_end;
850};
851
852struct drm_i915_gem_create {
853	/**
854	 * Requested size for the object.
855	 *
856	 * The (page-aligned) allocated size for the object will be returned.
857	 */
858	__u64 size;
859	/**
860	 * Returned handle for the object.
861	 *
862	 * Object handles are nonzero.
863	 */
864	__u32 handle;
865	__u32 pad;
866};
867
868struct drm_i915_gem_pread {
869	/** Handle for the object being read. */
870	__u32 handle;
871	__u32 pad;
872	/** Offset into the object to read from */
873	__u64 offset;
874	/** Length of data to read */
875	__u64 size;
876	/**
877	 * Pointer to write the data into.
878	 *
879	 * This is a fixed-size type for 32/64 compatibility.
880	 */
881	__u64 data_ptr;
882};
883
884struct drm_i915_gem_pwrite {
885	/** Handle for the object being written to. */
886	__u32 handle;
887	__u32 pad;
888	/** Offset into the object to write to */
889	__u64 offset;
890	/** Length of data to write */
891	__u64 size;
892	/**
893	 * Pointer to read the data from.
894	 *
895	 * This is a fixed-size type for 32/64 compatibility.
896	 */
897	__u64 data_ptr;
898};
899
900struct drm_i915_gem_mmap {
901	/** Handle for the object being mapped. */
902	__u32 handle;
903	__u32 pad;
904	/** Offset in the object to map. */
905	__u64 offset;
906	/**
907	 * Length of data to map.
908	 *
909	 * The value will be page-aligned.
910	 */
911	__u64 size;
912	/**
913	 * Returned pointer the data was mapped at.
914	 *
915	 * This is a fixed-size type for 32/64 compatibility.
916	 */
917	__u64 addr_ptr;
918
919	/**
920	 * Flags for extended behaviour.
921	 *
922	 * Added in version 2.
923	 */
924	__u64 flags;
925#define I915_MMAP_WC 0x1
926};
927
928struct drm_i915_gem_mmap_gtt {
929	/** Handle for the object being mapped. */
930	__u32 handle;
931	__u32 pad;
932	/**
933	 * Fake offset to use for subsequent mmap call
934	 *
935	 * This is a fixed-size type for 32/64 compatibility.
936	 */
937	__u64 offset;
938};
939
940/**
941 * struct drm_i915_gem_mmap_offset - Retrieve an offset so we can mmap this buffer object.
942 *
943 * This struct is passed as argument to the `DRM_IOCTL_I915_GEM_MMAP_OFFSET` ioctl,
944 * and is used to retrieve the fake offset to mmap an object specified by &handle.
945 *
946 * The legacy way of using `DRM_IOCTL_I915_GEM_MMAP` is removed on gen12+.
947 * `DRM_IOCTL_I915_GEM_MMAP_GTT` is an older supported alias to this struct, but will behave
948 * as setting the &extensions to 0, and &flags to `I915_MMAP_OFFSET_GTT`.
949 */
950struct drm_i915_gem_mmap_offset {
951	/** @handle: Handle for the object being mapped. */
952	__u32 handle;
953	/** @pad: Must be zero */
954	__u32 pad;
955	/**
956	 * @offset: The fake offset to use for subsequent mmap call
957	 *
958	 * This is a fixed-size type for 32/64 compatibility.
959	 */
960	__u64 offset;
961
962	/**
963	 * @flags: Flags for extended behaviour.
964	 *
965	 * It is mandatory that one of the `MMAP_OFFSET` types
966	 * should be included:
967	 *
968	 * - `I915_MMAP_OFFSET_GTT`: Use mmap with the object bound to GTT. (Write-Combined)
969	 * - `I915_MMAP_OFFSET_WC`: Use Write-Combined caching.
970	 * - `I915_MMAP_OFFSET_WB`: Use Write-Back caching.
971	 * - `I915_MMAP_OFFSET_FIXED`: Use object placement to determine caching.
972	 *
973	 * On devices with local memory `I915_MMAP_OFFSET_FIXED` is the only valid
974	 * type. On devices without local memory, this caching mode is invalid.
975	 *
976	 * As caching mode when specifying `I915_MMAP_OFFSET_FIXED`, WC or WB will
977	 * be used, depending on the object placement on creation. WB will be used
978	 * when the object can only exist in system memory, WC otherwise.
979	 */
980	__u64 flags;
981
982#define I915_MMAP_OFFSET_GTT	0
983#define I915_MMAP_OFFSET_WC	1
984#define I915_MMAP_OFFSET_WB	2
985#define I915_MMAP_OFFSET_UC	3
986#define I915_MMAP_OFFSET_FIXED	4
987
988	/**
989	 * @extensions: Zero-terminated chain of extensions.
990	 *
991	 * No current extensions defined; mbz.
992	 */
993	__u64 extensions;
994};
995
996/**
997 * struct drm_i915_gem_set_domain - Adjust the objects write or read domain, in
998 * preparation for accessing the pages via some CPU domain.
999 *
1000 * Specifying a new write or read domain will flush the object out of the
1001 * previous domain(if required), before then updating the objects domain
1002 * tracking with the new domain.
1003 *
1004 * Note this might involve waiting for the object first if it is still active on
1005 * the GPU.
1006 *
1007 * Supported values for @read_domains and @write_domain:
1008 *
1009 *	- I915_GEM_DOMAIN_WC: Uncached write-combined domain
1010 *	- I915_GEM_DOMAIN_CPU: CPU cache domain
1011 *	- I915_GEM_DOMAIN_GTT: Mappable aperture domain
1012 *
1013 * All other domains are rejected.
1014 *
1015 * Note that for discrete, starting from DG1, this is no longer supported, and
1016 * is instead rejected. On such platforms the CPU domain is effectively static,
1017 * where we also only support a single &drm_i915_gem_mmap_offset cache mode,
1018 * which can't be set explicitly and instead depends on the object placements,
1019 * as per the below.
1020 *
1021 * Implicit caching rules, starting from DG1:
1022 *
1023 *	- If any of the object placements (see &drm_i915_gem_create_ext_memory_regions)
1024 *	  contain I915_MEMORY_CLASS_DEVICE then the object will be allocated and
1025 *	  mapped as write-combined only.
1026 *
1027 *	- Everything else is always allocated and mapped as write-back, with the
1028 *	  guarantee that everything is also coherent with the GPU.
1029 *
1030 * Note that this is likely to change in the future again, where we might need
1031 * more flexibility on future devices, so making this all explicit as part of a
1032 * new &drm_i915_gem_create_ext extension is probable.
1033 */
1034struct drm_i915_gem_set_domain {
1035	/** @handle: Handle for the object. */
1036	__u32 handle;
1037
1038	/** @read_domains: New read domains. */
1039	__u32 read_domains;
1040
1041	/**
1042	 * @write_domain: New write domain.
1043	 *
1044	 * Note that having something in the write domain implies it's in the
1045	 * read domain, and only that read domain.
1046	 */
1047	__u32 write_domain;
1048};
1049
1050struct drm_i915_gem_sw_finish {
1051	/** Handle for the object */
1052	__u32 handle;
1053};
1054
1055struct drm_i915_gem_relocation_entry {
1056	/**
1057	 * Handle of the buffer being pointed to by this relocation entry.
1058	 *
1059	 * It's appealing to make this be an index into the mm_validate_entry
1060	 * list to refer to the buffer, but this allows the driver to create
1061	 * a relocation list for state buffers and not re-write it per
1062	 * exec using the buffer.
1063	 */
1064	__u32 target_handle;
1065
1066	/**
1067	 * Value to be added to the offset of the target buffer to make up
1068	 * the relocation entry.
1069	 */
1070	__u32 delta;
1071
1072	/** Offset in the buffer the relocation entry will be written into */
1073	__u64 offset;
1074
1075	/**
1076	 * Offset value of the target buffer that the relocation entry was last
1077	 * written as.
1078	 *
1079	 * If the buffer has the same offset as last time, we can skip syncing
1080	 * and writing the relocation.  This value is written back out by
1081	 * the execbuffer ioctl when the relocation is written.
1082	 */
1083	__u64 presumed_offset;
1084
1085	/**
1086	 * Target memory domains read by this operation.
1087	 */
1088	__u32 read_domains;
1089
1090	/**
1091	 * Target memory domains written by this operation.
1092	 *
1093	 * Note that only one domain may be written by the whole
1094	 * execbuffer operation, so that where there are conflicts,
1095	 * the application will get -EINVAL back.
1096	 */
1097	__u32 write_domain;
1098};
1099
1100/** @{
1101 * Intel memory domains
1102 *
1103 * Most of these just align with the various caches in
1104 * the system and are used to flush and invalidate as
1105 * objects end up cached in different domains.
1106 */
1107/** CPU cache */
1108#define I915_GEM_DOMAIN_CPU		0x00000001
1109/** Render cache, used by 2D and 3D drawing */
1110#define I915_GEM_DOMAIN_RENDER		0x00000002
1111/** Sampler cache, used by texture engine */
1112#define I915_GEM_DOMAIN_SAMPLER		0x00000004
1113/** Command queue, used to load batch buffers */
1114#define I915_GEM_DOMAIN_COMMAND		0x00000008
1115/** Instruction cache, used by shader programs */
1116#define I915_GEM_DOMAIN_INSTRUCTION	0x00000010
1117/** Vertex address cache */
1118#define I915_GEM_DOMAIN_VERTEX		0x00000020
1119/** GTT domain - aperture and scanout */
1120#define I915_GEM_DOMAIN_GTT		0x00000040
1121/** WC domain - uncached access */
1122#define I915_GEM_DOMAIN_WC		0x00000080
1123/** @} */
1124
1125struct drm_i915_gem_exec_object {
1126	/**
1127	 * User's handle for a buffer to be bound into the GTT for this
1128	 * operation.
1129	 */
1130	__u32 handle;
1131
1132	/** Number of relocations to be performed on this buffer */
1133	__u32 relocation_count;
1134	/**
1135	 * Pointer to array of struct drm_i915_gem_relocation_entry containing
1136	 * the relocations to be performed in this buffer.
1137	 */
1138	__u64 relocs_ptr;
1139
1140	/** Required alignment in graphics aperture */
1141	__u64 alignment;
1142
1143	/**
1144	 * Returned value of the updated offset of the object, for future
1145	 * presumed_offset writes.
1146	 */
1147	__u64 offset;
1148};
1149
1150/* DRM_IOCTL_I915_GEM_EXECBUFFER was removed in Linux 5.13 */
1151struct drm_i915_gem_execbuffer {
1152	/**
1153	 * List of buffers to be validated with their relocations to be
1154	 * performend on them.
1155	 *
1156	 * This is a pointer to an array of struct drm_i915_gem_validate_entry.
1157	 *
1158	 * These buffers must be listed in an order such that all relocations
1159	 * a buffer is performing refer to buffers that have already appeared
1160	 * in the validate list.
1161	 */
1162	__u64 buffers_ptr;
1163	__u32 buffer_count;
1164
1165	/** Offset in the batchbuffer to start execution from. */
1166	__u32 batch_start_offset;
1167	/** Bytes used in batchbuffer from batch_start_offset */
1168	__u32 batch_len;
1169	__u32 DR1;
1170	__u32 DR4;
1171	__u32 num_cliprects;
1172	/** This is a struct drm_clip_rect *cliprects */
1173	__u64 cliprects_ptr;
1174};
1175
1176struct drm_i915_gem_exec_object2 {
1177	/**
1178	 * User's handle for a buffer to be bound into the GTT for this
1179	 * operation.
1180	 */
1181	__u32 handle;
1182
1183	/** Number of relocations to be performed on this buffer */
1184	__u32 relocation_count;
1185	/**
1186	 * Pointer to array of struct drm_i915_gem_relocation_entry containing
1187	 * the relocations to be performed in this buffer.
1188	 */
1189	__u64 relocs_ptr;
1190
1191	/** Required alignment in graphics aperture */
1192	__u64 alignment;
1193
1194	/**
1195	 * When the EXEC_OBJECT_PINNED flag is specified this is populated by
1196	 * the user with the GTT offset at which this object will be pinned.
1197	 *
1198	 * When the I915_EXEC_NO_RELOC flag is specified this must contain the
1199	 * presumed_offset of the object.
1200	 *
1201	 * During execbuffer2 the kernel populates it with the value of the
1202	 * current GTT offset of the object, for future presumed_offset writes.
1203	 *
1204	 * See struct drm_i915_gem_create_ext for the rules when dealing with
1205	 * alignment restrictions with I915_MEMORY_CLASS_DEVICE, on devices with
1206	 * minimum page sizes, like DG2.
1207	 */
1208	__u64 offset;
1209
1210#define EXEC_OBJECT_NEEDS_FENCE		 (1<<0)
1211#define EXEC_OBJECT_NEEDS_GTT		 (1<<1)
1212#define EXEC_OBJECT_WRITE		 (1<<2)
1213#define EXEC_OBJECT_SUPPORTS_48B_ADDRESS (1<<3)
1214#define EXEC_OBJECT_PINNED		 (1<<4)
1215#define EXEC_OBJECT_PAD_TO_SIZE		 (1<<5)
1216/* The kernel implicitly tracks GPU activity on all GEM objects, and
1217 * synchronises operations with outstanding rendering. This includes
1218 * rendering on other devices if exported via dma-buf. However, sometimes
1219 * this tracking is too coarse and the user knows better. For example,
1220 * if the object is split into non-overlapping ranges shared between different
1221 * clients or engines (i.e. suballocating objects), the implicit tracking
1222 * by kernel assumes that each operation affects the whole object rather
1223 * than an individual range, causing needless synchronisation between clients.
1224 * The kernel will also forgo any CPU cache flushes prior to rendering from
1225 * the object as the client is expected to be also handling such domain
1226 * tracking.
1227 *
1228 * The kernel maintains the implicit tracking in order to manage resources
1229 * used by the GPU - this flag only disables the synchronisation prior to
1230 * rendering with this object in this execbuf.
1231 *
1232 * Opting out of implicit synhronisation requires the user to do its own
1233 * explicit tracking to avoid rendering corruption. See, for example,
1234 * I915_PARAM_HAS_EXEC_FENCE to order execbufs and execute them asynchronously.
1235 */
1236#define EXEC_OBJECT_ASYNC		(1<<6)
1237/* Request that the contents of this execobject be copied into the error
1238 * state upon a GPU hang involving this batch for post-mortem debugging.
1239 * These buffers are recorded in no particular order as "user" in
1240 * /sys/class/drm/cardN/error. Query I915_PARAM_HAS_EXEC_CAPTURE to see
1241 * if the kernel supports this flag.
1242 */
1243#define EXEC_OBJECT_CAPTURE		(1<<7)
1244/* All remaining bits are MBZ and RESERVED FOR FUTURE USE */
1245#define __EXEC_OBJECT_UNKNOWN_FLAGS -(EXEC_OBJECT_CAPTURE<<1)
1246	__u64 flags;
1247
1248	union {
1249		__u64 rsvd1;
1250		__u64 pad_to_size;
1251	};
1252	__u64 rsvd2;
1253};
1254
1255/**
1256 * struct drm_i915_gem_exec_fence - An input or output fence for the execbuf
1257 * ioctl.
1258 *
1259 * The request will wait for input fence to signal before submission.
1260 *
1261 * The returned output fence will be signaled after the completion of the
1262 * request.
1263 */
1264struct drm_i915_gem_exec_fence {
1265	/** @handle: User's handle for a drm_syncobj to wait on or signal. */
1266	__u32 handle;
1267
1268	/**
1269	 * @flags: Supported flags are:
1270	 *
1271	 * I915_EXEC_FENCE_WAIT:
1272	 * Wait for the input fence before request submission.
1273	 *
1274	 * I915_EXEC_FENCE_SIGNAL:
1275	 * Return request completion fence as output
1276	 */
1277	__u32 flags;
1278#define I915_EXEC_FENCE_WAIT            (1<<0)
1279#define I915_EXEC_FENCE_SIGNAL          (1<<1)
1280#define __I915_EXEC_FENCE_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SIGNAL << 1))
1281};
1282
1283/**
1284 * struct drm_i915_gem_execbuffer_ext_timeline_fences - Timeline fences
1285 * for execbuf ioctl.
1286 *
1287 * This structure describes an array of drm_syncobj and associated points for
1288 * timeline variants of drm_syncobj. It is invalid to append this structure to
1289 * the execbuf if I915_EXEC_FENCE_ARRAY is set.
1290 */
1291struct drm_i915_gem_execbuffer_ext_timeline_fences {
1292#define DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES 0
1293	/** @base: Extension link. See struct i915_user_extension. */
1294	struct i915_user_extension base;
1295
1296	/**
1297	 * @fence_count: Number of elements in the @handles_ptr & @value_ptr
1298	 * arrays.
1299	 */
1300	__u64 fence_count;
1301
1302	/**
1303	 * @handles_ptr: Pointer to an array of struct drm_i915_gem_exec_fence
1304	 * of length @fence_count.
1305	 */
1306	__u64 handles_ptr;
1307
1308	/**
1309	 * @values_ptr: Pointer to an array of u64 values of length
1310	 * @fence_count.
1311	 * Values must be 0 for a binary drm_syncobj. A Value of 0 for a
1312	 * timeline drm_syncobj is invalid as it turns a drm_syncobj into a
1313	 * binary one.
1314	 */
1315	__u64 values_ptr;
1316};
1317
1318/**
1319 * struct drm_i915_gem_execbuffer2 - Structure for DRM_I915_GEM_EXECBUFFER2
1320 * ioctl.
1321 */
1322struct drm_i915_gem_execbuffer2 {
1323	/** @buffers_ptr: Pointer to a list of gem_exec_object2 structs */
1324	__u64 buffers_ptr;
1325
1326	/** @buffer_count: Number of elements in @buffers_ptr array */
1327	__u32 buffer_count;
1328
1329	/**
1330	 * @batch_start_offset: Offset in the batchbuffer to start execution
1331	 * from.
1332	 */
1333	__u32 batch_start_offset;
1334
1335	/**
1336	 * @batch_len: Length in bytes of the batch buffer, starting from the
1337	 * @batch_start_offset. If 0, length is assumed to be the batch buffer
1338	 * object size.
1339	 */
1340	__u32 batch_len;
1341
1342	/** @DR1: deprecated */
1343	__u32 DR1;
1344
1345	/** @DR4: deprecated */
1346	__u32 DR4;
1347
1348	/** @num_cliprects: See @cliprects_ptr */
1349	__u32 num_cliprects;
1350
1351	/**
1352	 * @cliprects_ptr: Kernel clipping was a DRI1 misfeature.
1353	 *
1354	 * It is invalid to use this field if I915_EXEC_FENCE_ARRAY or
1355	 * I915_EXEC_USE_EXTENSIONS flags are not set.
1356	 *
1357	 * If I915_EXEC_FENCE_ARRAY is set, then this is a pointer to an array
1358	 * of &drm_i915_gem_exec_fence and @num_cliprects is the length of the
1359	 * array.
1360	 *
1361	 * If I915_EXEC_USE_EXTENSIONS is set, then this is a pointer to a
1362	 * single &i915_user_extension and num_cliprects is 0.
1363	 */
1364	__u64 cliprects_ptr;
1365
1366	/** @flags: Execbuf flags */
1367	__u64 flags;
1368#define I915_EXEC_RING_MASK              (0x3f)
1369#define I915_EXEC_DEFAULT                (0<<0)
1370#define I915_EXEC_RENDER                 (1<<0)
1371#define I915_EXEC_BSD                    (2<<0)
1372#define I915_EXEC_BLT                    (3<<0)
1373#define I915_EXEC_VEBOX                  (4<<0)
1374
1375/* Used for switching the constants addressing mode on gen4+ RENDER ring.
1376 * Gen6+ only supports relative addressing to dynamic state (default) and
1377 * absolute addressing.
1378 *
1379 * These flags are ignored for the BSD and BLT rings.
1380 */
1381#define I915_EXEC_CONSTANTS_MASK 	(3<<6)
1382#define I915_EXEC_CONSTANTS_REL_GENERAL (0<<6) /* default */
1383#define I915_EXEC_CONSTANTS_ABSOLUTE 	(1<<6)
1384#define I915_EXEC_CONSTANTS_REL_SURFACE (2<<6) /* gen4/5 only */
1385
1386/** Resets the SO write offset registers for transform feedback on gen7. */
1387#define I915_EXEC_GEN7_SOL_RESET	(1<<8)
1388
1389/** Request a privileged ("secure") batch buffer. Note only available for
1390 * DRM_ROOT_ONLY | DRM_MASTER processes.
1391 */
1392#define I915_EXEC_SECURE		(1<<9)
1393
1394/** Inform the kernel that the batch is and will always be pinned. This
1395 * negates the requirement for a workaround to be performed to avoid
1396 * an incoherent CS (such as can be found on 830/845). If this flag is
1397 * not passed, the kernel will endeavour to make sure the batch is
1398 * coherent with the CS before execution. If this flag is passed,
1399 * userspace assumes the responsibility for ensuring the same.
1400 */
1401#define I915_EXEC_IS_PINNED		(1<<10)
1402
1403/** Provide a hint to the kernel that the command stream and auxiliary
1404 * state buffers already holds the correct presumed addresses and so the
1405 * relocation process may be skipped if no buffers need to be moved in
1406 * preparation for the execbuffer.
1407 */
1408#define I915_EXEC_NO_RELOC		(1<<11)
1409
1410/** Use the reloc.handle as an index into the exec object array rather
1411 * than as the per-file handle.
1412 */
1413#define I915_EXEC_HANDLE_LUT		(1<<12)
1414
1415/** Used for switching BSD rings on the platforms with two BSD rings */
1416#define I915_EXEC_BSD_SHIFT	 (13)
1417#define I915_EXEC_BSD_MASK	 (3 << I915_EXEC_BSD_SHIFT)
1418/* default ping-pong mode */
1419#define I915_EXEC_BSD_DEFAULT	 (0 << I915_EXEC_BSD_SHIFT)
1420#define I915_EXEC_BSD_RING1	 (1 << I915_EXEC_BSD_SHIFT)
1421#define I915_EXEC_BSD_RING2	 (2 << I915_EXEC_BSD_SHIFT)
1422
1423/** Tell the kernel that the batchbuffer is processed by
1424 *  the resource streamer.
1425 */
1426#define I915_EXEC_RESOURCE_STREAMER     (1<<15)
1427
1428/* Setting I915_EXEC_FENCE_IN implies that lower_32_bits(rsvd2) represent
1429 * a sync_file fd to wait upon (in a nonblocking manner) prior to executing
1430 * the batch.
1431 *
1432 * Returns -EINVAL if the sync_file fd cannot be found.
1433 */
1434#define I915_EXEC_FENCE_IN		(1<<16)
1435
1436/* Setting I915_EXEC_FENCE_OUT causes the ioctl to return a sync_file fd
1437 * in the upper_32_bits(rsvd2) upon success. Ownership of the fd is given
1438 * to the caller, and it should be close() after use. (The fd is a regular
1439 * file descriptor and will be cleaned up on process termination. It holds
1440 * a reference to the request, but nothing else.)
1441 *
1442 * The sync_file fd can be combined with other sync_file and passed either
1443 * to execbuf using I915_EXEC_FENCE_IN, to atomic KMS ioctls (so that a flip
1444 * will only occur after this request completes), or to other devices.
1445 *
1446 * Using I915_EXEC_FENCE_OUT requires use of
1447 * DRM_IOCTL_I915_GEM_EXECBUFFER2_WR ioctl so that the result is written
1448 * back to userspace. Failure to do so will cause the out-fence to always
1449 * be reported as zero, and the real fence fd to be leaked.
1450 */
1451#define I915_EXEC_FENCE_OUT		(1<<17)
1452
1453/*
1454 * Traditionally the execbuf ioctl has only considered the final element in
1455 * the execobject[] to be the executable batch. Often though, the client
1456 * will known the batch object prior to construction and being able to place
1457 * it into the execobject[] array first can simplify the relocation tracking.
1458 * Setting I915_EXEC_BATCH_FIRST tells execbuf to use element 0 of the
1459 * execobject[] as the * batch instead (the default is to use the last
1460 * element).
1461 */
1462#define I915_EXEC_BATCH_FIRST		(1<<18)
1463
1464/* Setting I915_FENCE_ARRAY implies that num_cliprects and cliprects_ptr
1465 * define an array of i915_gem_exec_fence structures which specify a set of
1466 * dma fences to wait upon or signal.
1467 */
1468#define I915_EXEC_FENCE_ARRAY   (1<<19)
1469
1470/*
1471 * Setting I915_EXEC_FENCE_SUBMIT implies that lower_32_bits(rsvd2) represent
1472 * a sync_file fd to wait upon (in a nonblocking manner) prior to executing
1473 * the batch.
1474 *
1475 * Returns -EINVAL if the sync_file fd cannot be found.
1476 */
1477#define I915_EXEC_FENCE_SUBMIT		(1 << 20)
1478
1479/*
1480 * Setting I915_EXEC_USE_EXTENSIONS implies that
1481 * drm_i915_gem_execbuffer2.cliprects_ptr is treated as a pointer to an linked
1482 * list of i915_user_extension. Each i915_user_extension node is the base of a
1483 * larger structure. The list of supported structures are listed in the
1484 * drm_i915_gem_execbuffer_ext enum.
1485 */
1486#define I915_EXEC_USE_EXTENSIONS	(1 << 21)
1487#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_USE_EXTENSIONS << 1))
1488
1489	/** @rsvd1: Context id */
1490	__u64 rsvd1;
1491
1492	/**
1493	 * @rsvd2: in and out sync_file file descriptors.
1494	 *
1495	 * When I915_EXEC_FENCE_IN or I915_EXEC_FENCE_SUBMIT flag is set, the
1496	 * lower 32 bits of this field will have the in sync_file fd (input).
1497	 *
1498	 * When I915_EXEC_FENCE_OUT flag is set, the upper 32 bits of this
1499	 * field will have the out sync_file fd (output).
1500	 */
1501	__u64 rsvd2;
1502};
1503
1504#define I915_EXEC_CONTEXT_ID_MASK	(0xffffffff)
1505#define i915_execbuffer2_set_context_id(eb2, context) \
1506	(eb2).rsvd1 = context & I915_EXEC_CONTEXT_ID_MASK
1507#define i915_execbuffer2_get_context_id(eb2) \
1508	((eb2).rsvd1 & I915_EXEC_CONTEXT_ID_MASK)
1509
1510struct drm_i915_gem_pin {
1511	/** Handle of the buffer to be pinned. */
1512	__u32 handle;
1513	__u32 pad;
1514
1515	/** alignment required within the aperture */
1516	__u64 alignment;
1517
1518	/** Returned GTT offset of the buffer. */
1519	__u64 offset;
1520};
1521
1522struct drm_i915_gem_unpin {
1523	/** Handle of the buffer to be unpinned. */
1524	__u32 handle;
1525	__u32 pad;
1526};
1527
1528struct drm_i915_gem_busy {
1529	/** Handle of the buffer to check for busy */
1530	__u32 handle;
1531
1532	/** Return busy status
1533	 *
1534	 * A return of 0 implies that the object is idle (after
1535	 * having flushed any pending activity), and a non-zero return that
1536	 * the object is still in-flight on the GPU. (The GPU has not yet
1537	 * signaled completion for all pending requests that reference the
1538	 * object.) An object is guaranteed to become idle eventually (so
1539	 * long as no new GPU commands are executed upon it). Due to the
1540	 * asynchronous nature of the hardware, an object reported
1541	 * as busy may become idle before the ioctl is completed.
1542	 *
1543	 * Furthermore, if the object is busy, which engine is busy is only
1544	 * provided as a guide and only indirectly by reporting its class
1545	 * (there may be more than one engine in each class). There are race
1546	 * conditions which prevent the report of which engines are busy from
1547	 * being always accurate.  However, the converse is not true. If the
1548	 * object is idle, the result of the ioctl, that all engines are idle,
1549	 * is accurate.
1550	 *
1551	 * The returned dword is split into two fields to indicate both
1552	 * the engine classess on which the object is being read, and the
1553	 * engine class on which it is currently being written (if any).
1554	 *
1555	 * The low word (bits 0:15) indicate if the object is being written
1556	 * to by any engine (there can only be one, as the GEM implicit
1557	 * synchronisation rules force writes to be serialised). Only the
1558	 * engine class (offset by 1, I915_ENGINE_CLASS_RENDER is reported as
1559	 * 1 not 0 etc) for the last write is reported.
1560	 *
1561	 * The high word (bits 16:31) are a bitmask of which engines classes
1562	 * are currently reading from the object. Multiple engines may be
1563	 * reading from the object simultaneously.
1564	 *
1565	 * The value of each engine class is the same as specified in the
1566	 * I915_CONTEXT_PARAM_ENGINES context parameter and via perf, i.e.
1567	 * I915_ENGINE_CLASS_RENDER, I915_ENGINE_CLASS_COPY, etc.
1568	 * Some hardware may have parallel execution engines, e.g. multiple
1569	 * media engines, which are mapped to the same class identifier and so
1570	 * are not separately reported for busyness.
1571	 *
1572	 * Caveat emptor:
1573	 * Only the boolean result of this query is reliable; that is whether
1574	 * the object is idle or busy. The report of which engines are busy
1575	 * should be only used as a heuristic.
1576	 */
1577	__u32 busy;
1578};
1579
1580/**
1581 * struct drm_i915_gem_caching - Set or get the caching for given object
1582 * handle.
1583 *
1584 * Allow userspace to control the GTT caching bits for a given object when the
1585 * object is later mapped through the ppGTT(or GGTT on older platforms lacking
1586 * ppGTT support, or if the object is used for scanout). Note that this might
1587 * require unbinding the object from the GTT first, if its current caching value
1588 * doesn't match.
1589 *
1590 * Note that this all changes on discrete platforms, starting from DG1, the
1591 * set/get caching is no longer supported, and is now rejected.  Instead the CPU
1592 * caching attributes(WB vs WC) will become an immutable creation time property
1593 * for the object, along with the GTT caching level. For now we don't expose any
1594 * new uAPI for this, instead on DG1 this is all implicit, although this largely
1595 * shouldn't matter since DG1 is coherent by default(without any way of
1596 * controlling it).
1597 *
1598 * Implicit caching rules, starting from DG1:
1599 *
1600 *     - If any of the object placements (see &drm_i915_gem_create_ext_memory_regions)
1601 *       contain I915_MEMORY_CLASS_DEVICE then the object will be allocated and
1602 *       mapped as write-combined only.
1603 *
1604 *     - Everything else is always allocated and mapped as write-back, with the
1605 *       guarantee that everything is also coherent with the GPU.
1606 *
1607 * Note that this is likely to change in the future again, where we might need
1608 * more flexibility on future devices, so making this all explicit as part of a
1609 * new &drm_i915_gem_create_ext extension is probable.
1610 *
1611 * Side note: Part of the reason for this is that changing the at-allocation-time CPU
1612 * caching attributes for the pages might be required(and is expensive) if we
1613 * need to then CPU map the pages later with different caching attributes. This
1614 * inconsistent caching behaviour, while supported on x86, is not universally
1615 * supported on other architectures. So for simplicity we opt for setting
1616 * everything at creation time, whilst also making it immutable, on discrete
1617 * platforms.
1618 */
1619struct drm_i915_gem_caching {
1620	/**
1621	 * @handle: Handle of the buffer to set/get the caching level.
1622	 */
1623	__u32 handle;
1624
1625	/**
1626	 * @caching: The GTT caching level to apply or possible return value.
1627	 *
1628	 * The supported @caching values:
1629	 *
1630	 * I915_CACHING_NONE:
1631	 *
1632	 * GPU access is not coherent with CPU caches.  Default for machines
1633	 * without an LLC. This means manual flushing might be needed, if we
1634	 * want GPU access to be coherent.
1635	 *
1636	 * I915_CACHING_CACHED:
1637	 *
1638	 * GPU access is coherent with CPU caches and furthermore the data is
1639	 * cached in last-level caches shared between CPU cores and the GPU GT.
1640	 *
1641	 * I915_CACHING_DISPLAY:
1642	 *
1643	 * Special GPU caching mode which is coherent with the scanout engines.
1644	 * Transparently falls back to I915_CACHING_NONE on platforms where no
1645	 * special cache mode (like write-through or gfdt flushing) is
1646	 * available. The kernel automatically sets this mode when using a
1647	 * buffer as a scanout target.  Userspace can manually set this mode to
1648	 * avoid a costly stall and clflush in the hotpath of drawing the first
1649	 * frame.
1650	 */
1651#define I915_CACHING_NONE		0
1652#define I915_CACHING_CACHED		1
1653#define I915_CACHING_DISPLAY		2
1654	__u32 caching;
1655};
1656
1657#define I915_TILING_NONE	0
1658#define I915_TILING_X		1
1659#define I915_TILING_Y		2
1660/*
1661 * Do not add new tiling types here.  The I915_TILING_* values are for
1662 * de-tiling fence registers that no longer exist on modern platforms.  Although
1663 * the hardware may support new types of tiling in general (e.g., Tile4), we
1664 * do not need to add them to the uapi that is specific to now-defunct ioctls.
1665 */
1666#define I915_TILING_LAST	I915_TILING_Y
1667
1668#define I915_BIT_6_SWIZZLE_NONE		0
1669#define I915_BIT_6_SWIZZLE_9		1
1670#define I915_BIT_6_SWIZZLE_9_10		2
1671#define I915_BIT_6_SWIZZLE_9_11		3
1672#define I915_BIT_6_SWIZZLE_9_10_11	4
1673/* Not seen by userland */
1674#define I915_BIT_6_SWIZZLE_UNKNOWN	5
1675/* Seen by userland. */
1676#define I915_BIT_6_SWIZZLE_9_17		6
1677#define I915_BIT_6_SWIZZLE_9_10_17	7
1678
1679struct drm_i915_gem_set_tiling {
1680	/** Handle of the buffer to have its tiling state updated */
1681	__u32 handle;
1682
1683	/**
1684	 * Tiling mode for the object (I915_TILING_NONE, I915_TILING_X,
1685	 * I915_TILING_Y).
1686	 *
1687	 * This value is to be set on request, and will be updated by the
1688	 * kernel on successful return with the actual chosen tiling layout.
1689	 *
1690	 * The tiling mode may be demoted to I915_TILING_NONE when the system
1691	 * has bit 6 swizzling that can't be managed correctly by GEM.
1692	 *
1693	 * Buffer contents become undefined when changing tiling_mode.
1694	 */
1695	__u32 tiling_mode;
1696
1697	/**
1698	 * Stride in bytes for the object when in I915_TILING_X or
1699	 * I915_TILING_Y.
1700	 */
1701	__u32 stride;
1702
1703	/**
1704	 * Returned address bit 6 swizzling required for CPU access through
1705	 * mmap mapping.
1706	 */
1707	__u32 swizzle_mode;
1708};
1709
1710struct drm_i915_gem_get_tiling {
1711	/** Handle of the buffer to get tiling state for. */
1712	__u32 handle;
1713
1714	/**
1715	 * Current tiling mode for the object (I915_TILING_NONE, I915_TILING_X,
1716	 * I915_TILING_Y).
1717	 */
1718	__u32 tiling_mode;
1719
1720	/**
1721	 * Returned address bit 6 swizzling required for CPU access through
1722	 * mmap mapping.
1723	 */
1724	__u32 swizzle_mode;
1725
1726	/**
1727	 * Returned address bit 6 swizzling required for CPU access through
1728	 * mmap mapping whilst bound.
1729	 */
1730	__u32 phys_swizzle_mode;
1731};
1732
1733struct drm_i915_gem_get_aperture {
1734	/** Total size of the aperture used by i915_gem_execbuffer, in bytes */
1735	__u64 aper_size;
1736
1737	/**
1738	 * Available space in the aperture used by i915_gem_execbuffer, in
1739	 * bytes
1740	 */
1741	__u64 aper_available_size;
1742};
1743
1744struct drm_i915_get_pipe_from_crtc_id {
1745	/** ID of CRTC being requested **/
1746	__u32 crtc_id;
1747
1748	/** pipe of requested CRTC **/
1749	__u32 pipe;
1750};
1751
1752#define I915_MADV_WILLNEED 0
1753#define I915_MADV_DONTNEED 1
1754#define __I915_MADV_PURGED 2 /* internal state */
1755
1756struct drm_i915_gem_madvise {
1757	/** Handle of the buffer to change the backing store advice */
1758	__u32 handle;
1759
1760	/* Advice: either the buffer will be needed again in the near future,
1761	 *         or wont be and could be discarded under memory pressure.
1762	 */
1763	__u32 madv;
1764
1765	/** Whether the backing store still exists. */
1766	__u32 retained;
1767};
1768
1769/* flags */
1770#define I915_OVERLAY_TYPE_MASK 		0xff
1771#define I915_OVERLAY_YUV_PLANAR 	0x01
1772#define I915_OVERLAY_YUV_PACKED 	0x02
1773#define I915_OVERLAY_RGB		0x03
1774
1775#define I915_OVERLAY_DEPTH_MASK		0xff00
1776#define I915_OVERLAY_RGB24		0x1000
1777#define I915_OVERLAY_RGB16		0x2000
1778#define I915_OVERLAY_RGB15		0x3000
1779#define I915_OVERLAY_YUV422		0x0100
1780#define I915_OVERLAY_YUV411		0x0200
1781#define I915_OVERLAY_YUV420		0x0300
1782#define I915_OVERLAY_YUV410		0x0400
1783
1784#define I915_OVERLAY_SWAP_MASK		0xff0000
1785#define I915_OVERLAY_NO_SWAP		0x000000
1786#define I915_OVERLAY_UV_SWAP		0x010000
1787#define I915_OVERLAY_Y_SWAP		0x020000
1788#define I915_OVERLAY_Y_AND_UV_SWAP	0x030000
1789
1790#define I915_OVERLAY_FLAGS_MASK		0xff000000
1791#define I915_OVERLAY_ENABLE		0x01000000
1792
1793struct drm_intel_overlay_put_image {
1794	/* various flags and src format description */
1795	__u32 flags;
1796	/* source picture description */
1797	__u32 bo_handle;
1798	/* stride values and offsets are in bytes, buffer relative */
1799	__u16 stride_Y; /* stride for packed formats */
1800	__u16 stride_UV;
1801	__u32 offset_Y; /* offset for packet formats */
1802	__u32 offset_U;
1803	__u32 offset_V;
1804	/* in pixels */
1805	__u16 src_width;
1806	__u16 src_height;
1807	/* to compensate the scaling factors for partially covered surfaces */
1808	__u16 src_scan_width;
1809	__u16 src_scan_height;
1810	/* output crtc description */
1811	__u32 crtc_id;
1812	__u16 dst_x;
1813	__u16 dst_y;
1814	__u16 dst_width;
1815	__u16 dst_height;
1816};
1817
1818/* flags */
1819#define I915_OVERLAY_UPDATE_ATTRS	(1<<0)
1820#define I915_OVERLAY_UPDATE_GAMMA	(1<<1)
1821#define I915_OVERLAY_DISABLE_DEST_COLORKEY	(1<<2)
1822struct drm_intel_overlay_attrs {
1823	__u32 flags;
1824	__u32 color_key;
1825	__s32 brightness;
1826	__u32 contrast;
1827	__u32 saturation;
1828	__u32 gamma0;
1829	__u32 gamma1;
1830	__u32 gamma2;
1831	__u32 gamma3;
1832	__u32 gamma4;
1833	__u32 gamma5;
1834};
1835
1836/*
1837 * Intel sprite handling
1838 *
1839 * Color keying works with a min/mask/max tuple.  Both source and destination
1840 * color keying is allowed.
1841 *
1842 * Source keying:
1843 * Sprite pixels within the min & max values, masked against the color channels
1844 * specified in the mask field, will be transparent.  All other pixels will
1845 * be displayed on top of the primary plane.  For RGB surfaces, only the min
1846 * and mask fields will be used; ranged compares are not allowed.
1847 *
1848 * Destination keying:
1849 * Primary plane pixels that match the min value, masked against the color
1850 * channels specified in the mask field, will be replaced by corresponding
1851 * pixels from the sprite plane.
1852 *
1853 * Note that source & destination keying are exclusive; only one can be
1854 * active on a given plane.
1855 */
1856
1857#define I915_SET_COLORKEY_NONE		(1<<0) /* Deprecated. Instead set
1858						* flags==0 to disable colorkeying.
1859						*/
1860#define I915_SET_COLORKEY_DESTINATION	(1<<1)
1861#define I915_SET_COLORKEY_SOURCE	(1<<2)
1862struct drm_intel_sprite_colorkey {
1863	__u32 plane_id;
1864	__u32 min_value;
1865	__u32 channel_mask;
1866	__u32 max_value;
1867	__u32 flags;
1868};
1869
1870struct drm_i915_gem_wait {
1871	/** Handle of BO we shall wait on */
1872	__u32 bo_handle;
1873	__u32 flags;
1874	/** Number of nanoseconds to wait, Returns time remaining. */
1875	__s64 timeout_ns;
1876};
1877
1878struct drm_i915_gem_context_create {
1879	__u32 ctx_id; /* output: id of new context*/
1880	__u32 pad;
1881};
1882
1883/**
1884 * struct drm_i915_gem_context_create_ext - Structure for creating contexts.
1885 */
1886struct drm_i915_gem_context_create_ext {
1887	/** @ctx_id: Id of the created context (output) */
1888	__u32 ctx_id;
1889
1890	/**
1891	 * @flags: Supported flags are:
1892	 *
1893	 * I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS:
1894	 *
1895	 * Extensions may be appended to this structure and driver must check
1896	 * for those. See @extensions.
1897	 *
1898	 * I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE
1899	 *
1900	 * Created context will have single timeline.
1901	 */
1902	__u32 flags;
1903#define I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS	(1u << 0)
1904#define I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE	(1u << 1)
1905#define I915_CONTEXT_CREATE_FLAGS_UNKNOWN \
1906	(-(I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE << 1))
1907
1908	/**
1909	 * @extensions: Zero-terminated chain of extensions.
1910	 *
1911	 * I915_CONTEXT_CREATE_EXT_SETPARAM:
1912	 * Context parameter to set or query during context creation.
1913	 * See struct drm_i915_gem_context_create_ext_setparam.
1914	 *
1915	 * I915_CONTEXT_CREATE_EXT_CLONE:
1916	 * This extension has been removed. On the off chance someone somewhere
1917	 * has attempted to use it, never re-use this extension number.
1918	 */
1919	__u64 extensions;
1920#define I915_CONTEXT_CREATE_EXT_SETPARAM 0
1921#define I915_CONTEXT_CREATE_EXT_CLONE 1
1922};
1923
1924/**
1925 * struct drm_i915_gem_context_param - Context parameter to set or query.
1926 */
1927struct drm_i915_gem_context_param {
1928	/** @ctx_id: Context id */
1929	__u32 ctx_id;
1930
1931	/** @size: Size of the parameter @value */
1932	__u32 size;
1933
1934	/** @param: Parameter to set or query */
1935	__u64 param;
1936#define I915_CONTEXT_PARAM_BAN_PERIOD	0x1
1937/* I915_CONTEXT_PARAM_NO_ZEROMAP has been removed.  On the off chance
1938 * someone somewhere has attempted to use it, never re-use this context
1939 * param number.
1940 */
1941#define I915_CONTEXT_PARAM_NO_ZEROMAP	0x2
1942#define I915_CONTEXT_PARAM_GTT_SIZE	0x3
1943#define I915_CONTEXT_PARAM_NO_ERROR_CAPTURE	0x4
1944#define I915_CONTEXT_PARAM_BANNABLE	0x5
1945#define I915_CONTEXT_PARAM_PRIORITY	0x6
1946#define   I915_CONTEXT_MAX_USER_PRIORITY	1023 /* inclusive */
1947#define   I915_CONTEXT_DEFAULT_PRIORITY		0
1948#define   I915_CONTEXT_MIN_USER_PRIORITY	-1023 /* inclusive */
1949	/*
1950	 * When using the following param, value should be a pointer to
1951	 * drm_i915_gem_context_param_sseu.
1952	 */
1953#define I915_CONTEXT_PARAM_SSEU		0x7
1954
1955/*
1956 * Not all clients may want to attempt automatic recover of a context after
1957 * a hang (for example, some clients may only submit very small incremental
1958 * batches relying on known logical state of previous batches which will never
1959 * recover correctly and each attempt will hang), and so would prefer that
1960 * the context is forever banned instead.
1961 *
1962 * If set to false (0), after a reset, subsequent (and in flight) rendering
1963 * from this context is discarded, and the client will need to create a new
1964 * context to use instead.
1965 *
1966 * If set to true (1), the kernel will automatically attempt to recover the
1967 * context by skipping the hanging batch and executing the next batch starting
1968 * from the default context state (discarding the incomplete logical context
1969 * state lost due to the reset).
1970 *
1971 * On creation, all new contexts are marked as recoverable.
1972 */
1973#define I915_CONTEXT_PARAM_RECOVERABLE	0x8
1974
1975	/*
1976	 * The id of the associated virtual memory address space (ppGTT) of
1977	 * this context. Can be retrieved and passed to another context
1978	 * (on the same fd) for both to use the same ppGTT and so share
1979	 * address layouts, and avoid reloading the page tables on context
1980	 * switches between themselves.
1981	 *
1982	 * See DRM_I915_GEM_VM_CREATE and DRM_I915_GEM_VM_DESTROY.
1983	 */
1984#define I915_CONTEXT_PARAM_VM		0x9
1985
1986/*
1987 * I915_CONTEXT_PARAM_ENGINES:
1988 *
1989 * Bind this context to operate on this subset of available engines. Henceforth,
1990 * the I915_EXEC_RING selector for DRM_IOCTL_I915_GEM_EXECBUFFER2 operates as
1991 * an index into this array of engines; I915_EXEC_DEFAULT selecting engine[0]
1992 * and upwards. Slots 0...N are filled in using the specified (class, instance).
1993 * Use
1994 *	engine_class: I915_ENGINE_CLASS_INVALID,
1995 *	engine_instance: I915_ENGINE_CLASS_INVALID_NONE
1996 * to specify a gap in the array that can be filled in later, e.g. by a
1997 * virtual engine used for load balancing.
1998 *
1999 * Setting the number of engines bound to the context to 0, by passing a zero
2000 * sized argument, will revert back to default settings.
2001 *
2002 * See struct i915_context_param_engines.
2003 *
2004 * Extensions:
2005 *   i915_context_engines_load_balance (I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE)
2006 *   i915_context_engines_bond (I915_CONTEXT_ENGINES_EXT_BOND)
2007 *   i915_context_engines_parallel_submit (I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT)
2008 */
2009#define I915_CONTEXT_PARAM_ENGINES	0xa
2010
2011/*
2012 * I915_CONTEXT_PARAM_PERSISTENCE:
2013 *
2014 * Allow the context and active rendering to survive the process until
2015 * completion. Persistence allows fire-and-forget clients to queue up a
2016 * bunch of work, hand the output over to a display server and then quit.
2017 * If the context is marked as not persistent, upon closing (either via
2018 * an explicit DRM_I915_GEM_CONTEXT_DESTROY or implicitly from file closure
2019 * or process termination), the context and any outstanding requests will be
2020 * cancelled (and exported fences for cancelled requests marked as -EIO).
2021 *
2022 * By default, new contexts allow persistence.
2023 */
2024#define I915_CONTEXT_PARAM_PERSISTENCE	0xb
2025
2026/* This API has been removed.  On the off chance someone somewhere has
2027 * attempted to use it, never re-use this context param number.
2028 */
2029#define I915_CONTEXT_PARAM_RINGSIZE	0xc
2030
2031/*
2032 * I915_CONTEXT_PARAM_PROTECTED_CONTENT:
2033 *
2034 * Mark that the context makes use of protected content, which will result
2035 * in the context being invalidated when the protected content session is.
2036 * Given that the protected content session is killed on suspend, the device
2037 * is kept awake for the lifetime of a protected context, so the user should
2038 * make sure to dispose of them once done.
2039 * This flag can only be set at context creation time and, when set to true,
2040 * must be preceded by an explicit setting of I915_CONTEXT_PARAM_RECOVERABLE
2041 * to false. This flag can't be set to true in conjunction with setting the
2042 * I915_CONTEXT_PARAM_BANNABLE flag to false. Creation example:
2043 *
2044 * .. code-block:: C
2045 *
2046 *	struct drm_i915_gem_context_create_ext_setparam p_protected = {
2047 *		.base = {
2048 *			.name = I915_CONTEXT_CREATE_EXT_SETPARAM,
2049 *		},
2050 *		.param = {
2051 *			.param = I915_CONTEXT_PARAM_PROTECTED_CONTENT,
2052 *			.value = 1,
2053 *		}
2054 *	};
2055 *	struct drm_i915_gem_context_create_ext_setparam p_norecover = {
2056 *		.base = {
2057 *			.name = I915_CONTEXT_CREATE_EXT_SETPARAM,
2058 *			.next_extension = to_user_pointer(&p_protected),
2059 *		},
2060 *		.param = {
2061 *			.param = I915_CONTEXT_PARAM_RECOVERABLE,
2062 *			.value = 0,
2063 *		}
2064 *	};
2065 *	struct drm_i915_gem_context_create_ext create = {
2066 *		.flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS,
2067 *		.extensions = to_user_pointer(&p_norecover);
2068 *	};
2069 *
2070 *	ctx_id = gem_context_create_ext(drm_fd, &create);
2071 *
2072 * In addition to the normal failure cases, setting this flag during context
2073 * creation can result in the following errors:
2074 *
2075 * -ENODEV: feature not available
2076 * -EPERM: trying to mark a recoverable or not bannable context as protected
2077 */
2078#define I915_CONTEXT_PARAM_PROTECTED_CONTENT    0xd
2079/* Must be kept compact -- no holes and well documented */
2080
2081	/** @value: Context parameter value to be set or queried */
2082	__u64 value;
2083};
2084
2085/*
2086 * Context SSEU programming
2087 *
2088 * It may be necessary for either functional or performance reason to configure
2089 * a context to run with a reduced number of SSEU (where SSEU stands for Slice/
2090 * Sub-slice/EU).
2091 *
2092 * This is done by configuring SSEU configuration using the below
2093 * @struct drm_i915_gem_context_param_sseu for every supported engine which
2094 * userspace intends to use.
2095 *
2096 * Not all GPUs or engines support this functionality in which case an error
2097 * code -ENODEV will be returned.
2098 *
2099 * Also, flexibility of possible SSEU configuration permutations varies between
2100 * GPU generations and software imposed limitations. Requesting such a
2101 * combination will return an error code of -EINVAL.
2102 *
2103 * NOTE: When perf/OA is active the context's SSEU configuration is ignored in
2104 * favour of a single global setting.
2105 */
2106struct drm_i915_gem_context_param_sseu {
2107	/*
2108	 * Engine class & instance to be configured or queried.
2109	 */
2110	struct i915_engine_class_instance engine;
2111
2112	/*
2113	 * Unknown flags must be cleared to zero.
2114	 */
2115	__u32 flags;
2116#define I915_CONTEXT_SSEU_FLAG_ENGINE_INDEX (1u << 0)
2117
2118	/*
2119	 * Mask of slices to enable for the context. Valid values are a subset
2120	 * of the bitmask value returned for I915_PARAM_SLICE_MASK.
2121	 */
2122	__u64 slice_mask;
2123
2124	/*
2125	 * Mask of subslices to enable for the context. Valid values are a
2126	 * subset of the bitmask value return by I915_PARAM_SUBSLICE_MASK.
2127	 */
2128	__u64 subslice_mask;
2129
2130	/*
2131	 * Minimum/Maximum number of EUs to enable per subslice for the
2132	 * context. min_eus_per_subslice must be inferior or equal to
2133	 * max_eus_per_subslice.
2134	 */
2135	__u16 min_eus_per_subslice;
2136	__u16 max_eus_per_subslice;
2137
2138	/*
2139	 * Unused for now. Must be cleared to zero.
2140	 */
2141	__u32 rsvd;
2142};
2143
2144/**
2145 * DOC: Virtual Engine uAPI
2146 *
2147 * Virtual engine is a concept where userspace is able to configure a set of
2148 * physical engines, submit a batch buffer, and let the driver execute it on any
2149 * engine from the set as it sees fit.
2150 *
2151 * This is primarily useful on parts which have multiple instances of a same
2152 * class engine, like for example GT3+ Skylake parts with their two VCS engines.
2153 *
2154 * For instance userspace can enumerate all engines of a certain class using the
2155 * previously described `Engine Discovery uAPI`_. After that userspace can
2156 * create a GEM context with a placeholder slot for the virtual engine (using
2157 * `I915_ENGINE_CLASS_INVALID` and `I915_ENGINE_CLASS_INVALID_NONE` for class
2158 * and instance respectively) and finally using the
2159 * `I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE` extension place a virtual engine in
2160 * the same reserved slot.
2161 *
2162 * Example of creating a virtual engine and submitting a batch buffer to it:
2163 *
2164 * .. code-block:: C
2165 *
2166 * 	I915_DEFINE_CONTEXT_ENGINES_LOAD_BALANCE(virtual, 2) = {
2167 * 		.base.name = I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE,
2168 * 		.engine_index = 0, // Place this virtual engine into engine map slot 0
2169 * 		.num_siblings = 2,
2170 * 		.engines = { { I915_ENGINE_CLASS_VIDEO, 0 },
2171 * 			     { I915_ENGINE_CLASS_VIDEO, 1 }, },
2172 * 	};
2173 * 	I915_DEFINE_CONTEXT_PARAM_ENGINES(engines, 1) = {
2174 * 		.engines = { { I915_ENGINE_CLASS_INVALID,
2175 * 			       I915_ENGINE_CLASS_INVALID_NONE } },
2176 * 		.extensions = to_user_pointer(&virtual), // Chains after load_balance extension
2177 * 	};
2178 * 	struct drm_i915_gem_context_create_ext_setparam p_engines = {
2179 * 		.base = {
2180 * 			.name = I915_CONTEXT_CREATE_EXT_SETPARAM,
2181 * 		},
2182 * 		.param = {
2183 * 			.param = I915_CONTEXT_PARAM_ENGINES,
2184 * 			.value = to_user_pointer(&engines),
2185 * 			.size = sizeof(engines),
2186 * 		},
2187 * 	};
2188 * 	struct drm_i915_gem_context_create_ext create = {
2189 * 		.flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS,
2190 * 		.extensions = to_user_pointer(&p_engines);
2191 * 	};
2192 *
2193 * 	ctx_id = gem_context_create_ext(drm_fd, &create);
2194 *
2195 * 	// Now we have created a GEM context with its engine map containing a
2196 * 	// single virtual engine. Submissions to this slot can go either to
2197 * 	// vcs0 or vcs1, depending on the load balancing algorithm used inside
2198 * 	// the driver. The load balancing is dynamic from one batch buffer to
2199 * 	// another and transparent to userspace.
2200 *
2201 * 	...
2202 * 	execbuf.rsvd1 = ctx_id;
2203 * 	execbuf.flags = 0; // Submits to index 0 which is the virtual engine
2204 * 	gem_execbuf(drm_fd, &execbuf);
2205 */
2206
2207/*
2208 * i915_context_engines_load_balance:
2209 *
2210 * Enable load balancing across this set of engines.
2211 *
2212 * Into the I915_EXEC_DEFAULT slot [0], a virtual engine is created that when
2213 * used will proxy the execbuffer request onto one of the set of engines
2214 * in such a way as to distribute the load evenly across the set.
2215 *
2216 * The set of engines must be compatible (e.g. the same HW class) as they
2217 * will share the same logical GPU context and ring.
2218 *
2219 * To intermix rendering with the virtual engine and direct rendering onto
2220 * the backing engines (bypassing the load balancing proxy), the context must
2221 * be defined to use a single timeline for all engines.
2222 */
2223struct i915_context_engines_load_balance {
2224	struct i915_user_extension base;
2225
2226	__u16 engine_index;
2227	__u16 num_siblings;
2228	__u32 flags; /* all undefined flags must be zero */
2229
2230	__u64 mbz64; /* reserved for future use; must be zero */
2231
2232	struct i915_engine_class_instance engines[0];
2233} __attribute__((packed));
2234
2235#define I915_DEFINE_CONTEXT_ENGINES_LOAD_BALANCE(name__, N__) struct { \
2236	struct i915_user_extension base; \
2237	__u16 engine_index; \
2238	__u16 num_siblings; \
2239	__u32 flags; \
2240	__u64 mbz64; \
2241	struct i915_engine_class_instance engines[N__]; \
2242} __attribute__((packed)) name__
2243
2244/*
2245 * i915_context_engines_bond:
2246 *
2247 * Constructed bonded pairs for execution within a virtual engine.
2248 *
2249 * All engines are equal, but some are more equal than others. Given
2250 * the distribution of resources in the HW, it may be preferable to run
2251 * a request on a given subset of engines in parallel to a request on a
2252 * specific engine. We enable this selection of engines within a virtual
2253 * engine by specifying bonding pairs, for any given master engine we will
2254 * only execute on one of the corresponding siblings within the virtual engine.
2255 *
2256 * To execute a request in parallel on the master engine and a sibling requires
2257 * coordination with a I915_EXEC_FENCE_SUBMIT.
2258 */
2259struct i915_context_engines_bond {
2260	struct i915_user_extension base;
2261
2262	struct i915_engine_class_instance master;
2263
2264	__u16 virtual_index; /* index of virtual engine in ctx->engines[] */
2265	__u16 num_bonds;
2266
2267	__u64 flags; /* all undefined flags must be zero */
2268	__u64 mbz64[4]; /* reserved for future use; must be zero */
2269
2270	struct i915_engine_class_instance engines[0];
2271} __attribute__((packed));
2272
2273#define I915_DEFINE_CONTEXT_ENGINES_BOND(name__, N__) struct { \
2274	struct i915_user_extension base; \
2275	struct i915_engine_class_instance master; \
2276	__u16 virtual_index; \
2277	__u16 num_bonds; \
2278	__u64 flags; \
2279	__u64 mbz64[4]; \
2280	struct i915_engine_class_instance engines[N__]; \
2281} __attribute__((packed)) name__
2282
2283/**
2284 * struct i915_context_engines_parallel_submit - Configure engine for
2285 * parallel submission.
2286 *
2287 * Setup a slot in the context engine map to allow multiple BBs to be submitted
2288 * in a single execbuf IOCTL. Those BBs will then be scheduled to run on the GPU
2289 * in parallel. Multiple hardware contexts are created internally in the i915 to
2290 * run these BBs. Once a slot is configured for N BBs only N BBs can be
2291 * submitted in each execbuf IOCTL and this is implicit behavior e.g. The user
2292 * doesn't tell the execbuf IOCTL there are N BBs, the execbuf IOCTL knows how
2293 * many BBs there are based on the slot's configuration. The N BBs are the last
2294 * N buffer objects or first N if I915_EXEC_BATCH_FIRST is set.
2295 *
2296 * The default placement behavior is to create implicit bonds between each
2297 * context if each context maps to more than 1 physical engine (e.g. context is
2298 * a virtual engine). Also we only allow contexts of same engine class and these
2299 * contexts must be in logically contiguous order. Examples of the placement
2300 * behavior are described below. Lastly, the default is to not allow BBs to be
2301 * preempted mid-batch. Rather insert coordinated preemption points on all
2302 * hardware contexts between each set of BBs. Flags could be added in the future
2303 * to change both of these default behaviors.
2304 *
2305 * Returns -EINVAL if hardware context placement configuration is invalid or if
2306 * the placement configuration isn't supported on the platform / submission
2307 * interface.
2308 * Returns -ENODEV if extension isn't supported on the platform / submission
2309 * interface.
2310 *
2311 * .. code-block:: none
2312 *
2313 *	Examples syntax:
2314 *	CS[X] = generic engine of same class, logical instance X
2315 *	INVALID = I915_ENGINE_CLASS_INVALID, I915_ENGINE_CLASS_INVALID_NONE
2316 *
2317 *	Example 1 pseudo code:
2318 *	set_engines(INVALID)
2319 *	set_parallel(engine_index=0, width=2, num_siblings=1,
2320 *		     engines=CS[0],CS[1])
2321 *
2322 *	Results in the following valid placement:
2323 *	CS[0], CS[1]
2324 *
2325 *	Example 2 pseudo code:
2326 *	set_engines(INVALID)
2327 *	set_parallel(engine_index=0, width=2, num_siblings=2,
2328 *		     engines=CS[0],CS[2],CS[1],CS[3])
2329 *
2330 *	Results in the following valid placements:
2331 *	CS[0], CS[1]
2332 *	CS[2], CS[3]
2333 *
2334 *	This can be thought of as two virtual engines, each containing two
2335 *	engines thereby making a 2D array. However, there are bonds tying the
2336 *	entries together and placing restrictions on how they can be scheduled.
2337 *	Specifically, the scheduler can choose only vertical columns from the 2D
2338 *	array. That is, CS[0] is bonded to CS[1] and CS[2] to CS[3]. So if the
2339 *	scheduler wants to submit to CS[0], it must also choose CS[1] and vice
2340 *	versa. Same for CS[2] requires also using CS[3].
2341 *	VE[0] = CS[0], CS[2]
2342 *	VE[1] = CS[1], CS[3]
2343 *
2344 *	Example 3 pseudo code:
2345 *	set_engines(INVALID)
2346 *	set_parallel(engine_index=0, width=2, num_siblings=2,
2347 *		     engines=CS[0],CS[1],CS[1],CS[3])
2348 *
2349 *	Results in the following valid and invalid placements:
2350 *	CS[0], CS[1]
2351 *	CS[1], CS[3] - Not logically contiguous, return -EINVAL
2352 */
2353struct i915_context_engines_parallel_submit {
2354	/**
2355	 * @base: base user extension.
2356	 */
2357	struct i915_user_extension base;
2358
2359	/**
2360	 * @engine_index: slot for parallel engine
2361	 */
2362	__u16 engine_index;
2363
2364	/**
2365	 * @width: number of contexts per parallel engine or in other words the
2366	 * number of batches in each submission
2367	 */
2368	__u16 width;
2369
2370	/**
2371	 * @num_siblings: number of siblings per context or in other words the
2372	 * number of possible placements for each submission
2373	 */
2374	__u16 num_siblings;
2375
2376	/**
2377	 * @mbz16: reserved for future use; must be zero
2378	 */
2379	__u16 mbz16;
2380
2381	/**
2382	 * @flags: all undefined flags must be zero, currently not defined flags
2383	 */
2384	__u64 flags;
2385
2386	/**
2387	 * @mbz64: reserved for future use; must be zero
2388	 */
2389	__u64 mbz64[3];
2390
2391	/**
2392	 * @engines: 2-d array of engine instances to configure parallel engine
2393	 *
2394	 * length = width (i) * num_siblings (j)
2395	 * index = j + i * num_siblings
2396	 */
2397	struct i915_engine_class_instance engines[0];
2398
2399} __attribute__((packed));
2400
2401#define I915_DEFINE_CONTEXT_ENGINES_PARALLEL_SUBMIT(name__, N__) struct { \
2402	struct i915_user_extension base; \
2403	__u16 engine_index; \
2404	__u16 width; \
2405	__u16 num_siblings; \
2406	__u16 mbz16; \
2407	__u64 flags; \
2408	__u64 mbz64[3]; \
2409	struct i915_engine_class_instance engines[N__]; \
2410} __attribute__((packed)) name__
2411
2412/**
2413 * DOC: Context Engine Map uAPI
2414 *
2415 * Context engine map is a new way of addressing engines when submitting batch-
2416 * buffers, replacing the existing way of using identifiers like `I915_EXEC_BLT`
2417 * inside the flags field of `struct drm_i915_gem_execbuffer2`.
2418 *
2419 * To use it created GEM contexts need to be configured with a list of engines
2420 * the user is intending to submit to. This is accomplished using the
2421 * `I915_CONTEXT_PARAM_ENGINES` parameter and `struct
2422 * i915_context_param_engines`.
2423 *
2424 * For such contexts the `I915_EXEC_RING_MASK` field becomes an index into the
2425 * configured map.
2426 *
2427 * Example of creating such context and submitting against it:
2428 *
2429 * .. code-block:: C
2430 *
2431 * 	I915_DEFINE_CONTEXT_PARAM_ENGINES(engines, 2) = {
2432 * 		.engines = { { I915_ENGINE_CLASS_RENDER, 0 },
2433 * 			     { I915_ENGINE_CLASS_COPY, 0 } }
2434 * 	};
2435 * 	struct drm_i915_gem_context_create_ext_setparam p_engines = {
2436 * 		.base = {
2437 * 			.name = I915_CONTEXT_CREATE_EXT_SETPARAM,
2438 * 		},
2439 * 		.param = {
2440 * 			.param = I915_CONTEXT_PARAM_ENGINES,
2441 * 			.value = to_user_pointer(&engines),
2442 * 			.size = sizeof(engines),
2443 * 		},
2444 * 	};
2445 * 	struct drm_i915_gem_context_create_ext create = {
2446 * 		.flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS,
2447 * 		.extensions = to_user_pointer(&p_engines);
2448 * 	};
2449 *
2450 * 	ctx_id = gem_context_create_ext(drm_fd, &create);
2451 *
2452 * 	// We have now created a GEM context with two engines in the map:
2453 * 	// Index 0 points to rcs0 while index 1 points to bcs0. Other engines
2454 * 	// will not be accessible from this context.
2455 *
2456 * 	...
2457 * 	execbuf.rsvd1 = ctx_id;
2458 * 	execbuf.flags = 0; // Submits to index 0, which is rcs0 for this context
2459 * 	gem_execbuf(drm_fd, &execbuf);
2460 *
2461 * 	...
2462 * 	execbuf.rsvd1 = ctx_id;
2463 * 	execbuf.flags = 1; // Submits to index 0, which is bcs0 for this context
2464 * 	gem_execbuf(drm_fd, &execbuf);
2465 */
2466
2467struct i915_context_param_engines {
2468	__u64 extensions; /* linked chain of extension blocks, 0 terminates */
2469#define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */
2470#define I915_CONTEXT_ENGINES_EXT_BOND 1 /* see i915_context_engines_bond */
2471#define I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT 2 /* see i915_context_engines_parallel_submit */
2472	struct i915_engine_class_instance engines[0];
2473} __attribute__((packed));
2474
2475#define I915_DEFINE_CONTEXT_PARAM_ENGINES(name__, N__) struct { \
2476	__u64 extensions; \
2477	struct i915_engine_class_instance engines[N__]; \
2478} __attribute__((packed)) name__
2479
2480/**
2481 * struct drm_i915_gem_context_create_ext_setparam - Context parameter
2482 * to set or query during context creation.
2483 */
2484struct drm_i915_gem_context_create_ext_setparam {
2485	/** @base: Extension link. See struct i915_user_extension. */
2486	struct i915_user_extension base;
2487
2488	/**
2489	 * @param: Context parameter to set or query.
2490	 * See struct drm_i915_gem_context_param.
2491	 */
2492	struct drm_i915_gem_context_param param;
2493};
2494
2495struct drm_i915_gem_context_destroy {
2496	__u32 ctx_id;
2497	__u32 pad;
2498};
2499
2500/**
2501 * struct drm_i915_gem_vm_control - Structure to create or destroy VM.
2502 *
2503 * DRM_I915_GEM_VM_CREATE -
2504 *
2505 * Create a new virtual memory address space (ppGTT) for use within a context
2506 * on the same file. Extensions can be provided to configure exactly how the
2507 * address space is setup upon creation.
2508 *
2509 * The id of new VM (bound to the fd) for use with I915_CONTEXT_PARAM_VM is
2510 * returned in the outparam @id.
2511 *
2512 * An extension chain maybe provided, starting with @extensions, and terminated
2513 * by the @next_extension being 0. Currently, no extensions are defined.
2514 *
2515 * DRM_I915_GEM_VM_DESTROY -
2516 *
2517 * Destroys a previously created VM id, specified in @vm_id.
2518 *
2519 * No extensions or flags are allowed currently, and so must be zero.
2520 */
2521struct drm_i915_gem_vm_control {
2522	/** @extensions: Zero-terminated chain of extensions. */
2523	__u64 extensions;
2524
2525	/** @flags: reserved for future usage, currently MBZ */
2526	__u32 flags;
2527
2528	/** @vm_id: Id of the VM created or to be destroyed */
2529	__u32 vm_id;
2530};
2531
2532struct drm_i915_reg_read {
2533	/*
2534	 * Register offset.
2535	 * For 64bit wide registers where the upper 32bits don't immediately
2536	 * follow the lower 32bits, the offset of the lower 32bits must
2537	 * be specified
2538	 */
2539	__u64 offset;
2540#define I915_REG_READ_8B_WA (1ul << 0)
2541
2542	__u64 val; /* Return value */
2543};
2544
2545/* Known registers:
2546 *
2547 * Render engine timestamp - 0x2358 + 64bit - gen7+
2548 * - Note this register returns an invalid value if using the default
2549 *   single instruction 8byte read, in order to workaround that pass
2550 *   flag I915_REG_READ_8B_WA in offset field.
2551 *
2552 */
2553
2554struct drm_i915_reset_stats {
2555	__u32 ctx_id;
2556	__u32 flags;
2557
2558	/* All resets since boot/module reload, for all contexts */
2559	__u32 reset_count;
2560
2561	/* Number of batches lost when active in GPU, for this context */
2562	__u32 batch_active;
2563
2564	/* Number of batches lost pending for execution, for this context */
2565	__u32 batch_pending;
2566
2567	__u32 pad;
2568};
2569
2570/**
2571 * struct drm_i915_gem_userptr - Create GEM object from user allocated memory.
2572 *
2573 * Userptr objects have several restrictions on what ioctls can be used with the
2574 * object handle.
2575 */
2576struct drm_i915_gem_userptr {
2577	/**
2578	 * @user_ptr: The pointer to the allocated memory.
2579	 *
2580	 * Needs to be aligned to PAGE_SIZE.
2581	 */
2582	__u64 user_ptr;
2583
2584	/**
2585	 * @user_size:
2586	 *
2587	 * The size in bytes for the allocated memory. This will also become the
2588	 * object size.
2589	 *
2590	 * Needs to be aligned to PAGE_SIZE, and should be at least PAGE_SIZE,
2591	 * or larger.
2592	 */
2593	__u64 user_size;
2594
2595	/**
2596	 * @flags:
2597	 *
2598	 * Supported flags:
2599	 *
2600	 * I915_USERPTR_READ_ONLY:
2601	 *
2602	 * Mark the object as readonly, this also means GPU access can only be
2603	 * readonly. This is only supported on HW which supports readonly access
2604	 * through the GTT. If the HW can't support readonly access, an error is
2605	 * returned.
2606	 *
2607	 * I915_USERPTR_PROBE:
2608	 *
2609	 * Probe the provided @user_ptr range and validate that the @user_ptr is
2610	 * indeed pointing to normal memory and that the range is also valid.
2611	 * For example if some garbage address is given to the kernel, then this
2612	 * should complain.
2613	 *
2614	 * Returns -EFAULT if the probe failed.
2615	 *
2616	 * Note that this doesn't populate the backing pages, and also doesn't
2617	 * guarantee that the object will remain valid when the object is
2618	 * eventually used.
2619	 *
2620	 * The kernel supports this feature if I915_PARAM_HAS_USERPTR_PROBE
2621	 * returns a non-zero value.
2622	 *
2623	 * I915_USERPTR_UNSYNCHRONIZED:
2624	 *
2625	 * NOT USED. Setting this flag will result in an error.
2626	 */
2627	__u32 flags;
2628#define I915_USERPTR_READ_ONLY 0x1
2629#define I915_USERPTR_PROBE 0x2
2630#define I915_USERPTR_UNSYNCHRONIZED 0x80000000
2631	/**
2632	 * @handle: Returned handle for the object.
2633	 *
2634	 * Object handles are nonzero.
2635	 */
2636	__u32 handle;
2637};
2638
2639enum drm_i915_oa_format {
2640	I915_OA_FORMAT_A13 = 1,	    /* HSW only */
2641	I915_OA_FORMAT_A29,	    /* HSW only */
2642	I915_OA_FORMAT_A13_B8_C8,   /* HSW only */
2643	I915_OA_FORMAT_B4_C8,	    /* HSW only */
2644	I915_OA_FORMAT_A45_B8_C8,   /* HSW only */
2645	I915_OA_FORMAT_B4_C8_A16,   /* HSW only */
2646	I915_OA_FORMAT_C4_B8,	    /* HSW+ */
2647
2648	/* Gen8+ */
2649	I915_OA_FORMAT_A12,
2650	I915_OA_FORMAT_A12_B8_C8,
2651	I915_OA_FORMAT_A32u40_A4u32_B8_C8,
2652
2653	I915_OA_FORMAT_MAX	    /* non-ABI */
2654};
2655
2656enum drm_i915_perf_property_id {
2657	/**
2658	 * Open the stream for a specific context handle (as used with
2659	 * execbuffer2). A stream opened for a specific context this way
2660	 * won't typically require root privileges.
2661	 *
2662	 * This property is available in perf revision 1.
2663	 */
2664	DRM_I915_PERF_PROP_CTX_HANDLE = 1,
2665
2666	/**
2667	 * A value of 1 requests the inclusion of raw OA unit reports as
2668	 * part of stream samples.
2669	 *
2670	 * This property is available in perf revision 1.
2671	 */
2672	DRM_I915_PERF_PROP_SAMPLE_OA,
2673
2674	/**
2675	 * The value specifies which set of OA unit metrics should be
2676	 * configured, defining the contents of any OA unit reports.
2677	 *
2678	 * This property is available in perf revision 1.
2679	 */
2680	DRM_I915_PERF_PROP_OA_METRICS_SET,
2681
2682	/**
2683	 * The value specifies the size and layout of OA unit reports.
2684	 *
2685	 * This property is available in perf revision 1.
2686	 */
2687	DRM_I915_PERF_PROP_OA_FORMAT,
2688
2689	/**
2690	 * Specifying this property implicitly requests periodic OA unit
2691	 * sampling and (at least on Haswell) the sampling frequency is derived
2692	 * from this exponent as follows:
2693	 *
2694	 *   80ns * 2^(period_exponent + 1)
2695	 *
2696	 * This property is available in perf revision 1.
2697	 */
2698	DRM_I915_PERF_PROP_OA_EXPONENT,
2699
2700	/**
2701	 * Specifying this property is only valid when specify a context to
2702	 * filter with DRM_I915_PERF_PROP_CTX_HANDLE. Specifying this property
2703	 * will hold preemption of the particular context we want to gather
2704	 * performance data about. The execbuf2 submissions must include a
2705	 * drm_i915_gem_execbuffer_ext_perf parameter for this to apply.
2706	 *
2707	 * This property is available in perf revision 3.
2708	 */
2709	DRM_I915_PERF_PROP_HOLD_PREEMPTION,
2710
2711	/**
2712	 * Specifying this pins all contexts to the specified SSEU power
2713	 * configuration for the duration of the recording.
2714	 *
2715	 * This parameter's value is a pointer to a struct
2716	 * drm_i915_gem_context_param_sseu.
2717	 *
2718	 * This property is available in perf revision 4.
2719	 */
2720	DRM_I915_PERF_PROP_GLOBAL_SSEU,
2721
2722	/**
2723	 * This optional parameter specifies the timer interval in nanoseconds
2724	 * at which the i915 driver will check the OA buffer for available data.
2725	 * Minimum allowed value is 100 microseconds. A default value is used by
2726	 * the driver if this parameter is not specified. Note that larger timer
2727	 * values will reduce cpu consumption during OA perf captures. However,
2728	 * excessively large values would potentially result in OA buffer
2729	 * overwrites as captures reach end of the OA buffer.
2730	 *
2731	 * This property is available in perf revision 5.
2732	 */
2733	DRM_I915_PERF_PROP_POLL_OA_PERIOD,
2734
2735	DRM_I915_PERF_PROP_MAX /* non-ABI */
2736};
2737
2738struct drm_i915_perf_open_param {
2739	__u32 flags;
2740#define I915_PERF_FLAG_FD_CLOEXEC	(1<<0)
2741#define I915_PERF_FLAG_FD_NONBLOCK	(1<<1)
2742#define I915_PERF_FLAG_DISABLED		(1<<2)
2743
2744	/** The number of u64 (id, value) pairs */
2745	__u32 num_properties;
2746
2747	/**
2748	 * Pointer to array of u64 (id, value) pairs configuring the stream
2749	 * to open.
2750	 */
2751	__u64 properties_ptr;
2752};
2753
2754/*
2755 * Enable data capture for a stream that was either opened in a disabled state
2756 * via I915_PERF_FLAG_DISABLED or was later disabled via
2757 * I915_PERF_IOCTL_DISABLE.
2758 *
2759 * It is intended to be cheaper to disable and enable a stream than it may be
2760 * to close and re-open a stream with the same configuration.
2761 *
2762 * It's undefined whether any pending data for the stream will be lost.
2763 *
2764 * This ioctl is available in perf revision 1.
2765 */
2766#define I915_PERF_IOCTL_ENABLE	_IO('i', 0x0)
2767
2768/*
2769 * Disable data capture for a stream.
2770 *
2771 * It is an error to try and read a stream that is disabled.
2772 *
2773 * This ioctl is available in perf revision 1.
2774 */
2775#define I915_PERF_IOCTL_DISABLE	_IO('i', 0x1)
2776
2777/*
2778 * Change metrics_set captured by a stream.
2779 *
2780 * If the stream is bound to a specific context, the configuration change
2781 * will performed __inline__ with that context such that it takes effect before
2782 * the next execbuf submission.
2783 *
2784 * Returns the previously bound metrics set id, or a negative error code.
2785 *
2786 * This ioctl is available in perf revision 2.
2787 */
2788#define I915_PERF_IOCTL_CONFIG	_IO('i', 0x2)
2789
2790/*
2791 * Common to all i915 perf records
2792 */
2793struct drm_i915_perf_record_header {
2794	__u32 type;
2795	__u16 pad;
2796	__u16 size;
2797};
2798
2799enum drm_i915_perf_record_type {
2800
2801	/**
2802	 * Samples are the work horse record type whose contents are extensible
2803	 * and defined when opening an i915 perf stream based on the given
2804	 * properties.
2805	 *
2806	 * Boolean properties following the naming convention
2807	 * DRM_I915_PERF_SAMPLE_xyz_PROP request the inclusion of 'xyz' data in
2808	 * every sample.
2809	 *
2810	 * The order of these sample properties given by userspace has no
2811	 * affect on the ordering of data within a sample. The order is
2812	 * documented here.
2813	 *
2814	 * struct {
2815	 *     struct drm_i915_perf_record_header header;
2816	 *
2817	 *     { u32 oa_report[]; } && DRM_I915_PERF_PROP_SAMPLE_OA
2818	 * };
2819	 */
2820	DRM_I915_PERF_RECORD_SAMPLE = 1,
2821
2822	/*
2823	 * Indicates that one or more OA reports were not written by the
2824	 * hardware. This can happen for example if an MI_REPORT_PERF_COUNT
2825	 * command collides with periodic sampling - which would be more likely
2826	 * at higher sampling frequencies.
2827	 */
2828	DRM_I915_PERF_RECORD_OA_REPORT_LOST = 2,
2829
2830	/**
2831	 * An error occurred that resulted in all pending OA reports being lost.
2832	 */
2833	DRM_I915_PERF_RECORD_OA_BUFFER_LOST = 3,
2834
2835	DRM_I915_PERF_RECORD_MAX /* non-ABI */
2836};
2837
2838/**
2839 * struct drm_i915_perf_oa_config
2840 *
2841 * Structure to upload perf dynamic configuration into the kernel.
2842 */
2843struct drm_i915_perf_oa_config {
2844	/**
2845	 * @uuid:
2846	 *
2847	 * String formatted like "%\08x-%\04x-%\04x-%\04x-%\012x"
2848	 */
2849	char uuid[36];
2850
2851	/**
2852	 * @n_mux_regs:
2853	 *
2854	 * Number of mux regs in &mux_regs_ptr.
2855	 */
2856	__u32 n_mux_regs;
2857
2858	/**
2859	 * @n_boolean_regs:
2860	 *
2861	 * Number of boolean regs in &boolean_regs_ptr.
2862	 */
2863	__u32 n_boolean_regs;
2864
2865	/**
2866	 * @n_flex_regs:
2867	 *
2868	 * Number of flex regs in &flex_regs_ptr.
2869	 */
2870	__u32 n_flex_regs;
2871
2872	/**
2873	 * @mux_regs_ptr:
2874	 *
2875	 * Pointer to tuples of u32 values (register address, value) for mux
2876	 * registers.  Expected length of buffer is (2 * sizeof(u32) *
2877	 * &n_mux_regs).
2878	 */
2879	__u64 mux_regs_ptr;
2880
2881	/**
2882	 * @boolean_regs_ptr:
2883	 *
2884	 * Pointer to tuples of u32 values (register address, value) for mux
2885	 * registers.  Expected length of buffer is (2 * sizeof(u32) *
2886	 * &n_boolean_regs).
2887	 */
2888	__u64 boolean_regs_ptr;
2889
2890	/**
2891	 * @flex_regs_ptr:
2892	 *
2893	 * Pointer to tuples of u32 values (register address, value) for mux
2894	 * registers.  Expected length of buffer is (2 * sizeof(u32) *
2895	 * &n_flex_regs).
2896	 */
2897	__u64 flex_regs_ptr;
2898};
2899
2900/**
2901 * struct drm_i915_query_item - An individual query for the kernel to process.
2902 *
2903 * The behaviour is determined by the @query_id. Note that exactly what
2904 * @data_ptr is also depends on the specific @query_id.
2905 */
2906struct drm_i915_query_item {
2907	/**
2908	 * @query_id:
2909	 *
2910	 * The id for this query.  Currently accepted query IDs are:
2911	 *  - %DRM_I915_QUERY_TOPOLOGY_INFO (see struct drm_i915_query_topology_info)
2912	 *  - %DRM_I915_QUERY_ENGINE_INFO (see struct drm_i915_engine_info)
2913	 *  - %DRM_I915_QUERY_PERF_CONFIG (see struct drm_i915_query_perf_config)
2914	 *  - %DRM_I915_QUERY_MEMORY_REGIONS (see struct drm_i915_query_memory_regions)
2915	 *  - %DRM_I915_QUERY_HWCONFIG_BLOB (see `GuC HWCONFIG blob uAPI`)
2916	 *  - %DRM_I915_QUERY_GEOMETRY_SUBSLICES (see struct drm_i915_query_topology_info)
2917	 */
2918	__u64 query_id;
2919#define DRM_I915_QUERY_TOPOLOGY_INFO		1
2920#define DRM_I915_QUERY_ENGINE_INFO		2
2921#define DRM_I915_QUERY_PERF_CONFIG		3
2922#define DRM_I915_QUERY_MEMORY_REGIONS		4
2923#define DRM_I915_QUERY_HWCONFIG_BLOB		5
2924#define DRM_I915_QUERY_GEOMETRY_SUBSLICES	6
2925/* Must be kept compact -- no holes and well documented */
2926
2927	/**
2928	 * @length:
2929	 *
2930	 * When set to zero by userspace, this is filled with the size of the
2931	 * data to be written at the @data_ptr pointer. The kernel sets this
2932	 * value to a negative value to signal an error on a particular query
2933	 * item.
2934	 */
2935	__s32 length;
2936
2937	/**
2938	 * @flags:
2939	 *
2940	 * When &query_id == %DRM_I915_QUERY_TOPOLOGY_INFO, must be 0.
2941	 *
2942	 * When &query_id == %DRM_I915_QUERY_PERF_CONFIG, must be one of the
2943	 * following:
2944	 *
2945	 *	- %DRM_I915_QUERY_PERF_CONFIG_LIST
2946	 *      - %DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID
2947	 *      - %DRM_I915_QUERY_PERF_CONFIG_FOR_UUID
2948	 *
2949	 * When &query_id == %DRM_I915_QUERY_GEOMETRY_SUBSLICES must contain
2950	 * a struct i915_engine_class_instance that references a render engine.
2951	 */
2952	__u32 flags;
2953#define DRM_I915_QUERY_PERF_CONFIG_LIST          1
2954#define DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID 2
2955#define DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID   3
2956
2957	/**
2958	 * @data_ptr:
2959	 *
2960	 * Data will be written at the location pointed by @data_ptr when the
2961	 * value of @length matches the length of the data to be written by the
2962	 * kernel.
2963	 */
2964	__u64 data_ptr;
2965};
2966
2967/**
2968 * struct drm_i915_query - Supply an array of struct drm_i915_query_item for the
2969 * kernel to fill out.
2970 *
2971 * Note that this is generally a two step process for each struct
2972 * drm_i915_query_item in the array:
2973 *
2974 * 1. Call the DRM_IOCTL_I915_QUERY, giving it our array of struct
2975 *    drm_i915_query_item, with &drm_i915_query_item.length set to zero. The
2976 *    kernel will then fill in the size, in bytes, which tells userspace how
2977 *    memory it needs to allocate for the blob(say for an array of properties).
2978 *
2979 * 2. Next we call DRM_IOCTL_I915_QUERY again, this time with the
2980 *    &drm_i915_query_item.data_ptr equal to our newly allocated blob. Note that
2981 *    the &drm_i915_query_item.length should still be the same as what the
2982 *    kernel previously set. At this point the kernel can fill in the blob.
2983 *
2984 * Note that for some query items it can make sense for userspace to just pass
2985 * in a buffer/blob equal to or larger than the required size. In this case only
2986 * a single ioctl call is needed. For some smaller query items this can work
2987 * quite well.
2988 *
2989 */
2990struct drm_i915_query {
2991	/** @num_items: The number of elements in the @items_ptr array */
2992	__u32 num_items;
2993
2994	/**
2995	 * @flags: Unused for now. Must be cleared to zero.
2996	 */
2997	__u32 flags;
2998
2999	/**
3000	 * @items_ptr:
3001	 *
3002	 * Pointer to an array of struct drm_i915_query_item. The number of
3003	 * array elements is @num_items.
3004	 */
3005	__u64 items_ptr;
3006};
3007
3008/**
3009 * struct drm_i915_query_topology_info
3010 *
3011 * Describes slice/subslice/EU information queried by
3012 * %DRM_I915_QUERY_TOPOLOGY_INFO
3013 */
3014struct drm_i915_query_topology_info {
3015	/**
3016	 * @flags:
3017	 *
3018	 * Unused for now. Must be cleared to zero.
3019	 */
3020	__u16 flags;
3021
3022	/**
3023	 * @max_slices:
3024	 *
3025	 * The number of bits used to express the slice mask.
3026	 */
3027	__u16 max_slices;
3028
3029	/**
3030	 * @max_subslices:
3031	 *
3032	 * The number of bits used to express the subslice mask.
3033	 */
3034	__u16 max_subslices;
3035
3036	/**
3037	 * @max_eus_per_subslice:
3038	 *
3039	 * The number of bits in the EU mask that correspond to a single
3040	 * subslice's EUs.
3041	 */
3042	__u16 max_eus_per_subslice;
3043
3044	/**
3045	 * @subslice_offset:
3046	 *
3047	 * Offset in data[] at which the subslice masks are stored.
3048	 */
3049	__u16 subslice_offset;
3050
3051	/**
3052	 * @subslice_stride:
3053	 *
3054	 * Stride at which each of the subslice masks for each slice are
3055	 * stored.
3056	 */
3057	__u16 subslice_stride;
3058
3059	/**
3060	 * @eu_offset:
3061	 *
3062	 * Offset in data[] at which the EU masks are stored.
3063	 */
3064	__u16 eu_offset;
3065
3066	/**
3067	 * @eu_stride:
3068	 *
3069	 * Stride at which each of the EU masks for each subslice are stored.
3070	 */
3071	__u16 eu_stride;
3072
3073	/**
3074	 * @data:
3075	 *
3076	 * Contains 3 pieces of information :
3077	 *
3078	 * - The slice mask with one bit per slice telling whether a slice is
3079	 *   available. The availability of slice X can be queried with the
3080	 *   following formula :
3081	 *
3082	 *   .. code:: c
3083	 *
3084	 *      (data[X / 8] >> (X % 8)) & 1
3085	 *
3086	 *   Starting with Xe_HP platforms, Intel hardware no longer has
3087	 *   traditional slices so i915 will always report a single slice
3088	 *   (hardcoded slicemask = 0x1) which contains all of the platform's
3089	 *   subslices.  I.e., the mask here does not reflect any of the newer
3090	 *   hardware concepts such as "gslices" or "cslices" since userspace
3091	 *   is capable of inferring those from the subslice mask.
3092	 *
3093	 * - The subslice mask for each slice with one bit per subslice telling
3094	 *   whether a subslice is available.  Starting with Gen12 we use the
3095	 *   term "subslice" to refer to what the hardware documentation
3096	 *   describes as a "dual-subslices."  The availability of subslice Y
3097	 *   in slice X can be queried with the following formula :
3098	 *
3099	 *   .. code:: c
3100	 *
3101	 *      (data[subslice_offset + X * subslice_stride + Y / 8] >> (Y % 8)) & 1
3102	 *
3103	 * - The EU mask for each subslice in each slice, with one bit per EU
3104	 *   telling whether an EU is available. The availability of EU Z in
3105	 *   subslice Y in slice X can be queried with the following formula :
3106	 *
3107	 *   .. code:: c
3108	 *
3109	 *      (data[eu_offset +
3110	 *            (X * max_subslices + Y) * eu_stride +
3111	 *            Z / 8
3112	 *       ] >> (Z % 8)) & 1
3113	 */
3114	__u8 data[];
3115};
3116
3117/**
3118 * DOC: Engine Discovery uAPI
3119 *
3120 * Engine discovery uAPI is a way of enumerating physical engines present in a
3121 * GPU associated with an open i915 DRM file descriptor. This supersedes the old
3122 * way of using `DRM_IOCTL_I915_GETPARAM` and engine identifiers like
3123 * `I915_PARAM_HAS_BLT`.
3124 *
3125 * The need for this interface came starting with Icelake and newer GPUs, which
3126 * started to establish a pattern of having multiple engines of a same class,
3127 * where not all instances were always completely functionally equivalent.
3128 *
3129 * Entry point for this uapi is `DRM_IOCTL_I915_QUERY` with the
3130 * `DRM_I915_QUERY_ENGINE_INFO` as the queried item id.
3131 *
3132 * Example for getting the list of engines:
3133 *
3134 * .. code-block:: C
3135 *
3136 * 	struct drm_i915_query_engine_info *info;
3137 * 	struct drm_i915_query_item item = {
3138 * 		.query_id = DRM_I915_QUERY_ENGINE_INFO;
3139 * 	};
3140 * 	struct drm_i915_query query = {
3141 * 		.num_items = 1,
3142 * 		.items_ptr = (uintptr_t)&item,
3143 * 	};
3144 * 	int err, i;
3145 *
3146 * 	// First query the size of the blob we need, this needs to be large
3147 * 	// enough to hold our array of engines. The kernel will fill out the
3148 * 	// item.length for us, which is the number of bytes we need.
3149 * 	//
3150 * 	// Alternatively a large buffer can be allocated straight away enabling
3151 * 	// querying in one pass, in which case item.length should contain the
3152 * 	// length of the provided buffer.
3153 * 	err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
3154 * 	if (err) ...
3155 *
3156 * 	info = calloc(1, item.length);
3157 * 	// Now that we allocated the required number of bytes, we call the ioctl
3158 * 	// again, this time with the data_ptr pointing to our newly allocated
3159 * 	// blob, which the kernel can then populate with info on all engines.
3160 * 	item.data_ptr = (uintptr_t)&info,
3161 *
3162 * 	err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
3163 * 	if (err) ...
3164 *
3165 * 	// We can now access each engine in the array
3166 * 	for (i = 0; i < info->num_engines; i++) {
3167 * 		struct drm_i915_engine_info einfo = info->engines[i];
3168 * 		u16 class = einfo.engine.class;
3169 * 		u16 instance = einfo.engine.instance;
3170 * 		....
3171 * 	}
3172 *
3173 * 	free(info);
3174 *
3175 * Each of the enumerated engines, apart from being defined by its class and
3176 * instance (see `struct i915_engine_class_instance`), also can have flags and
3177 * capabilities defined as documented in i915_drm.h.
3178 *
3179 * For instance video engines which support HEVC encoding will have the
3180 * `I915_VIDEO_CLASS_CAPABILITY_HEVC` capability bit set.
3181 *
3182 * Engine discovery only fully comes to its own when combined with the new way
3183 * of addressing engines when submitting batch buffers using contexts with
3184 * engine maps configured.
3185 */
3186
3187/**
3188 * struct drm_i915_engine_info
3189 *
3190 * Describes one engine and it's capabilities as known to the driver.
3191 */
3192struct drm_i915_engine_info {
3193	/** @engine: Engine class and instance. */
3194	struct i915_engine_class_instance engine;
3195
3196	/** @rsvd0: Reserved field. */
3197	__u32 rsvd0;
3198
3199	/** @flags: Engine flags. */
3200	__u64 flags;
3201#define I915_ENGINE_INFO_HAS_LOGICAL_INSTANCE		(1 << 0)
3202
3203	/** @capabilities: Capabilities of this engine. */
3204	__u64 capabilities;
3205#define I915_VIDEO_CLASS_CAPABILITY_HEVC		(1 << 0)
3206#define I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC	(1 << 1)
3207
3208	/** @logical_instance: Logical instance of engine */
3209	__u16 logical_instance;
3210
3211	/** @rsvd1: Reserved fields. */
3212	__u16 rsvd1[3];
3213	/** @rsvd2: Reserved fields. */
3214	__u64 rsvd2[3];
3215};
3216
3217/**
3218 * struct drm_i915_query_engine_info
3219 *
3220 * Engine info query enumerates all engines known to the driver by filling in
3221 * an array of struct drm_i915_engine_info structures.
3222 */
3223struct drm_i915_query_engine_info {
3224	/** @num_engines: Number of struct drm_i915_engine_info structs following. */
3225	__u32 num_engines;
3226
3227	/** @rsvd: MBZ */
3228	__u32 rsvd[3];
3229
3230	/** @engines: Marker for drm_i915_engine_info structures. */
3231	struct drm_i915_engine_info engines[];
3232};
3233
3234/**
3235 * struct drm_i915_query_perf_config
3236 *
3237 * Data written by the kernel with query %DRM_I915_QUERY_PERF_CONFIG and
3238 * %DRM_I915_QUERY_GEOMETRY_SUBSLICES.
3239 */
3240struct drm_i915_query_perf_config {
3241	union {
3242		/**
3243		 * @n_configs:
3244		 *
3245		 * When &drm_i915_query_item.flags ==
3246		 * %DRM_I915_QUERY_PERF_CONFIG_LIST, i915 sets this fields to
3247		 * the number of configurations available.
3248		 */
3249		__u64 n_configs;
3250
3251		/**
3252		 * @config:
3253		 *
3254		 * When &drm_i915_query_item.flags ==
3255		 * %DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID, i915 will use the
3256		 * value in this field as configuration identifier to decide
3257		 * what data to write into config_ptr.
3258		 */
3259		__u64 config;
3260
3261		/**
3262		 * @uuid:
3263		 *
3264		 * When &drm_i915_query_item.flags ==
3265		 * %DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID, i915 will use the
3266		 * value in this field as configuration identifier to decide
3267		 * what data to write into config_ptr.
3268		 *
3269		 * String formatted like "%08x-%04x-%04x-%04x-%012x"
3270		 */
3271		char uuid[36];
3272	};
3273
3274	/**
3275	 * @flags:
3276	 *
3277	 * Unused for now. Must be cleared to zero.
3278	 */
3279	__u32 flags;
3280
3281	/**
3282	 * @data:
3283	 *
3284	 * When &drm_i915_query_item.flags == %DRM_I915_QUERY_PERF_CONFIG_LIST,
3285	 * i915 will write an array of __u64 of configuration identifiers.
3286	 *
3287	 * When &drm_i915_query_item.flags == %DRM_I915_QUERY_PERF_CONFIG_DATA,
3288	 * i915 will write a struct drm_i915_perf_oa_config. If the following
3289	 * fields of struct drm_i915_perf_oa_config are not set to 0, i915 will
3290	 * write into the associated pointers the values of submitted when the
3291	 * configuration was created :
3292	 *
3293	 *  - &drm_i915_perf_oa_config.n_mux_regs
3294	 *  - &drm_i915_perf_oa_config.n_boolean_regs
3295	 *  - &drm_i915_perf_oa_config.n_flex_regs
3296	 */
3297	__u8 data[];
3298};
3299
3300/**
3301 * enum drm_i915_gem_memory_class - Supported memory classes
3302 */
3303enum drm_i915_gem_memory_class {
3304	/** @I915_MEMORY_CLASS_SYSTEM: System memory */
3305	I915_MEMORY_CLASS_SYSTEM = 0,
3306	/** @I915_MEMORY_CLASS_DEVICE: Device local-memory */
3307	I915_MEMORY_CLASS_DEVICE,
3308};
3309
3310/**
3311 * struct drm_i915_gem_memory_class_instance - Identify particular memory region
3312 */
3313struct drm_i915_gem_memory_class_instance {
3314	/** @memory_class: See enum drm_i915_gem_memory_class */
3315	__u16 memory_class;
3316
3317	/** @memory_instance: Which instance */
3318	__u16 memory_instance;
3319};
3320
3321/**
3322 * struct drm_i915_memory_region_info - Describes one region as known to the
3323 * driver.
3324 *
3325 * Note this is using both struct drm_i915_query_item and struct drm_i915_query.
3326 * For this new query we are adding the new query id DRM_I915_QUERY_MEMORY_REGIONS
3327 * at &drm_i915_query_item.query_id.
3328 */
3329struct drm_i915_memory_region_info {
3330	/** @region: The class:instance pair encoding */
3331	struct drm_i915_gem_memory_class_instance region;
3332
3333	/** @rsvd0: MBZ */
3334	__u32 rsvd0;
3335
3336	/**
3337	 * @probed_size: Memory probed by the driver
3338	 *
3339	 * Note that it should not be possible to ever encounter a zero value
3340	 * here, also note that no current region type will ever return -1 here.
3341	 * Although for future region types, this might be a possibility. The
3342	 * same applies to the other size fields.
3343	 */
3344	__u64 probed_size;
3345
3346	/**
3347	 * @unallocated_size: Estimate of memory remaining
3348	 *
3349	 * Requires CAP_PERFMON or CAP_SYS_ADMIN to get reliable accounting.
3350	 * Without this (or if this is an older kernel) the value here will
3351	 * always equal the @probed_size. Note this is only currently tracked
3352	 * for I915_MEMORY_CLASS_DEVICE regions (for other types the value here
3353	 * will always equal the @probed_size).
3354	 */
3355	__u64 unallocated_size;
3356
3357	union {
3358		/** @rsvd1: MBZ */
3359		__u64 rsvd1[8];
3360		struct {
3361			/**
3362			 * @probed_cpu_visible_size: Memory probed by the driver
3363			 * that is CPU accessible.
3364			 *
3365			 * This will be always be <= @probed_size, and the
3366			 * remainder (if there is any) will not be CPU
3367			 * accessible.
3368			 *
3369			 * On systems without small BAR, the @probed_size will
3370			 * always equal the @probed_cpu_visible_size, since all
3371			 * of it will be CPU accessible.
3372			 *
3373			 * Note this is only tracked for
3374			 * I915_MEMORY_CLASS_DEVICE regions (for other types the
3375			 * value here will always equal the @probed_size).
3376			 *
3377			 * Note that if the value returned here is zero, then
3378			 * this must be an old kernel which lacks the relevant
3379			 * small-bar uAPI support (including
3380			 * I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS), but on
3381			 * such systems we should never actually end up with a
3382			 * small BAR configuration, assuming we are able to load
3383			 * the kernel module. Hence it should be safe to treat
3384			 * this the same as when @probed_cpu_visible_size ==
3385			 * @probed_size.
3386			 */
3387			__u64 probed_cpu_visible_size;
3388
3389			/**
3390			 * @unallocated_cpu_visible_size: Estimate of CPU
3391			 * visible memory remaining.
3392			 *
3393			 * Note this is only tracked for
3394			 * I915_MEMORY_CLASS_DEVICE regions (for other types the
3395			 * value here will always equal the
3396			 * @probed_cpu_visible_size).
3397			 *
3398			 * Requires CAP_PERFMON or CAP_SYS_ADMIN to get reliable
3399			 * accounting.  Without this the value here will always
3400			 * equal the @probed_cpu_visible_size. Note this is only
3401			 * currently tracked for I915_MEMORY_CLASS_DEVICE
3402			 * regions (for other types the value here will also
3403			 * always equal the @probed_cpu_visible_size).
3404			 *
3405			 * If this is an older kernel the value here will be
3406			 * zero, see also @probed_cpu_visible_size.
3407			 */
3408			__u64 unallocated_cpu_visible_size;
3409		};
3410	};
3411};
3412
3413/**
3414 * struct drm_i915_query_memory_regions
3415 *
3416 * The region info query enumerates all regions known to the driver by filling
3417 * in an array of struct drm_i915_memory_region_info structures.
3418 *
3419 * Example for getting the list of supported regions:
3420 *
3421 * .. code-block:: C
3422 *
3423 *	struct drm_i915_query_memory_regions *info;
3424 *	struct drm_i915_query_item item = {
3425 *		.query_id = DRM_I915_QUERY_MEMORY_REGIONS;
3426 *	};
3427 *	struct drm_i915_query query = {
3428 *		.num_items = 1,
3429 *		.items_ptr = (uintptr_t)&item,
3430 *	};
3431 *	int err, i;
3432 *
3433 *	// First query the size of the blob we need, this needs to be large
3434 *	// enough to hold our array of regions. The kernel will fill out the
3435 *	// item.length for us, which is the number of bytes we need.
3436 *	err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
3437 *	if (err) ...
3438 *
3439 *	info = calloc(1, item.length);
3440 *	// Now that we allocated the required number of bytes, we call the ioctl
3441 *	// again, this time with the data_ptr pointing to our newly allocated
3442 *	// blob, which the kernel can then populate with the all the region info.
3443 *	item.data_ptr = (uintptr_t)&info,
3444 *
3445 *	err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
3446 *	if (err) ...
3447 *
3448 *	// We can now access each region in the array
3449 *	for (i = 0; i < info->num_regions; i++) {
3450 *		struct drm_i915_memory_region_info mr = info->regions[i];
3451 *		u16 class = mr.region.class;
3452 *		u16 instance = mr.region.instance;
3453 *
3454 *		....
3455 *	}
3456 *
3457 *	free(info);
3458 */
3459struct drm_i915_query_memory_regions {
3460	/** @num_regions: Number of supported regions */
3461	__u32 num_regions;
3462
3463	/** @rsvd: MBZ */
3464	__u32 rsvd[3];
3465
3466	/** @regions: Info about each supported region */
3467	struct drm_i915_memory_region_info regions[];
3468};
3469
3470/**
3471 * DOC: GuC HWCONFIG blob uAPI
3472 *
3473 * The GuC produces a blob with information about the current device.
3474 * i915 reads this blob from GuC and makes it available via this uAPI.
3475 *
3476 * The format and meaning of the blob content are documented in the
3477 * Programmer's Reference Manual.
3478 */
3479
3480/**
3481 * struct drm_i915_gem_create_ext - Existing gem_create behaviour, with added
3482 * extension support using struct i915_user_extension.
3483 *
3484 * Note that new buffer flags should be added here, at least for the stuff that
3485 * is immutable. Previously we would have two ioctls, one to create the object
3486 * with gem_create, and another to apply various parameters, however this
3487 * creates some ambiguity for the params which are considered immutable. Also in
3488 * general we're phasing out the various SET/GET ioctls.
3489 */
3490struct drm_i915_gem_create_ext {
3491	/**
3492	 * @size: Requested size for the object.
3493	 *
3494	 * The (page-aligned) allocated size for the object will be returned.
3495	 *
3496	 * DG2 64K min page size implications:
3497	 *
3498	 * On discrete platforms, starting from DG2, we have to contend with GTT
3499	 * page size restrictions when dealing with I915_MEMORY_CLASS_DEVICE
3500	 * objects.  Specifically the hardware only supports 64K or larger GTT
3501	 * page sizes for such memory. The kernel will already ensure that all
3502	 * I915_MEMORY_CLASS_DEVICE memory is allocated using 64K or larger page
3503	 * sizes underneath.
3504	 *
3505	 * Note that the returned size here will always reflect any required
3506	 * rounding up done by the kernel, i.e 4K will now become 64K on devices
3507	 * such as DG2. The kernel will always select the largest minimum
3508	 * page-size for the set of possible placements as the value to use when
3509	 * rounding up the @size.
3510	 *
3511	 * Special DG2 GTT address alignment requirement:
3512	 *
3513	 * The GTT alignment will also need to be at least 2M for such objects.
3514	 *
3515	 * Note that due to how the hardware implements 64K GTT page support, we
3516	 * have some further complications:
3517	 *
3518	 *   1) The entire PDE (which covers a 2MB virtual address range), must
3519	 *   contain only 64K PTEs, i.e mixing 4K and 64K PTEs in the same
3520	 *   PDE is forbidden by the hardware.
3521	 *
3522	 *   2) We still need to support 4K PTEs for I915_MEMORY_CLASS_SYSTEM
3523	 *   objects.
3524	 *
3525	 * To keep things simple for userland, we mandate that any GTT mappings
3526	 * must be aligned to and rounded up to 2MB. The kernel will internally
3527	 * pad them out to the next 2MB boundary. As this only wastes virtual
3528	 * address space and avoids userland having to copy any needlessly
3529	 * complicated PDE sharing scheme (coloring) and only affects DG2, this
3530	 * is deemed to be a good compromise.
3531	 */
3532	__u64 size;
3533
3534	/**
3535	 * @handle: Returned handle for the object.
3536	 *
3537	 * Object handles are nonzero.
3538	 */
3539	__u32 handle;
3540
3541	/**
3542	 * @flags: Optional flags.
3543	 *
3544	 * Supported values:
3545	 *
3546	 * I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS - Signal to the kernel that
3547	 * the object will need to be accessed via the CPU.
3548	 *
3549	 * Only valid when placing objects in I915_MEMORY_CLASS_DEVICE, and only
3550	 * strictly required on configurations where some subset of the device
3551	 * memory is directly visible/mappable through the CPU (which we also
3552	 * call small BAR), like on some DG2+ systems. Note that this is quite
3553	 * undesirable, but due to various factors like the client CPU, BIOS etc
3554	 * it's something we can expect to see in the wild. See
3555	 * &drm_i915_memory_region_info.probed_cpu_visible_size for how to
3556	 * determine if this system applies.
3557	 *
3558	 * Note that one of the placements MUST be I915_MEMORY_CLASS_SYSTEM, to
3559	 * ensure the kernel can always spill the allocation to system memory,
3560	 * if the object can't be allocated in the mappable part of
3561	 * I915_MEMORY_CLASS_DEVICE.
3562	 *
3563	 * Also note that since the kernel only supports flat-CCS on objects
3564	 * that can *only* be placed in I915_MEMORY_CLASS_DEVICE, we therefore
3565	 * don't support I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS together with
3566	 * flat-CCS.
3567	 *
3568	 * Without this hint, the kernel will assume that non-mappable
3569	 * I915_MEMORY_CLASS_DEVICE is preferred for this object. Note that the
3570	 * kernel can still migrate the object to the mappable part, as a last
3571	 * resort, if userspace ever CPU faults this object, but this might be
3572	 * expensive, and so ideally should be avoided.
3573	 *
3574	 * On older kernels which lack the relevant small-bar uAPI support (see
3575	 * also &drm_i915_memory_region_info.probed_cpu_visible_size),
3576	 * usage of the flag will result in an error, but it should NEVER be
3577	 * possible to end up with a small BAR configuration, assuming we can
3578	 * also successfully load the i915 kernel module. In such cases the
3579	 * entire I915_MEMORY_CLASS_DEVICE region will be CPU accessible, and as
3580	 * such there are zero restrictions on where the object can be placed.
3581	 */
3582#define I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS (1 << 0)
3583	__u32 flags;
3584
3585	/**
3586	 * @extensions: The chain of extensions to apply to this object.
3587	 *
3588	 * This will be useful in the future when we need to support several
3589	 * different extensions, and we need to apply more than one when
3590	 * creating the object. See struct i915_user_extension.
3591	 *
3592	 * If we don't supply any extensions then we get the same old gem_create
3593	 * behaviour.
3594	 *
3595	 * For I915_GEM_CREATE_EXT_MEMORY_REGIONS usage see
3596	 * struct drm_i915_gem_create_ext_memory_regions.
3597	 *
3598	 * For I915_GEM_CREATE_EXT_PROTECTED_CONTENT usage see
3599	 * struct drm_i915_gem_create_ext_protected_content.
3600	 */
3601#define I915_GEM_CREATE_EXT_MEMORY_REGIONS 0
3602#define I915_GEM_CREATE_EXT_PROTECTED_CONTENT 1
3603	__u64 extensions;
3604};
3605
3606/**
3607 * struct drm_i915_gem_create_ext_memory_regions - The
3608 * I915_GEM_CREATE_EXT_MEMORY_REGIONS extension.
3609 *
3610 * Set the object with the desired set of placements/regions in priority
3611 * order. Each entry must be unique and supported by the device.
3612 *
3613 * This is provided as an array of struct drm_i915_gem_memory_class_instance, or
3614 * an equivalent layout of class:instance pair encodings. See struct
3615 * drm_i915_query_memory_regions and DRM_I915_QUERY_MEMORY_REGIONS for how to
3616 * query the supported regions for a device.
3617 *
3618 * As an example, on discrete devices, if we wish to set the placement as
3619 * device local-memory we can do something like:
3620 *
3621 * .. code-block:: C
3622 *
3623 *	struct drm_i915_gem_memory_class_instance region_lmem = {
3624 *              .memory_class = I915_MEMORY_CLASS_DEVICE,
3625 *              .memory_instance = 0,
3626 *      };
3627 *      struct drm_i915_gem_create_ext_memory_regions regions = {
3628 *              .base = { .name = I915_GEM_CREATE_EXT_MEMORY_REGIONS },
3629 *              .regions = (uintptr_t)&region_lmem,
3630 *              .num_regions = 1,
3631 *      };
3632 *      struct drm_i915_gem_create_ext create_ext = {
3633 *              .size = 16 * PAGE_SIZE,
3634 *              .extensions = (uintptr_t)&regions,
3635 *      };
3636 *
3637 *      int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext);
3638 *      if (err) ...
3639 *
3640 * At which point we get the object handle in &drm_i915_gem_create_ext.handle,
3641 * along with the final object size in &drm_i915_gem_create_ext.size, which
3642 * should account for any rounding up, if required.
3643 *
3644 * Note that userspace has no means of knowing the current backing region
3645 * for objects where @num_regions is larger than one. The kernel will only
3646 * ensure that the priority order of the @regions array is honoured, either
3647 * when initially placing the object, or when moving memory around due to
3648 * memory pressure
3649 *
3650 * On Flat-CCS capable HW, compression is supported for the objects residing
3651 * in I915_MEMORY_CLASS_DEVICE. When such objects (compressed) have other
3652 * memory class in @regions and migrated (by i915, due to memory
3653 * constraints) to the non I915_MEMORY_CLASS_DEVICE region, then i915 needs to
3654 * decompress the content. But i915 doesn't have the required information to
3655 * decompress the userspace compressed objects.
3656 *
3657 * So i915 supports Flat-CCS, on the objects which can reside only on
3658 * I915_MEMORY_CLASS_DEVICE regions.
3659 */
3660struct drm_i915_gem_create_ext_memory_regions {
3661	/** @base: Extension link. See struct i915_user_extension. */
3662	struct i915_user_extension base;
3663
3664	/** @pad: MBZ */
3665	__u32 pad;
3666	/** @num_regions: Number of elements in the @regions array. */
3667	__u32 num_regions;
3668	/**
3669	 * @regions: The regions/placements array.
3670	 *
3671	 * An array of struct drm_i915_gem_memory_class_instance.
3672	 */
3673	__u64 regions;
3674};
3675
3676/**
3677 * struct drm_i915_gem_create_ext_protected_content - The
3678 * I915_OBJECT_PARAM_PROTECTED_CONTENT extension.
3679 *
3680 * If this extension is provided, buffer contents are expected to be protected
3681 * by PXP encryption and require decryption for scan out and processing. This
3682 * is only possible on platforms that have PXP enabled, on all other scenarios
3683 * using this extension will cause the ioctl to fail and return -ENODEV. The
3684 * flags parameter is reserved for future expansion and must currently be set
3685 * to zero.
3686 *
3687 * The buffer contents are considered invalid after a PXP session teardown.
3688 *
3689 * The encryption is guaranteed to be processed correctly only if the object
3690 * is submitted with a context created using the
3691 * I915_CONTEXT_PARAM_PROTECTED_CONTENT flag. This will also enable extra checks
3692 * at submission time on the validity of the objects involved.
3693 *
3694 * Below is an example on how to create a protected object:
3695 *
3696 * .. code-block:: C
3697 *
3698 *      struct drm_i915_gem_create_ext_protected_content protected_ext = {
3699 *              .base = { .name = I915_GEM_CREATE_EXT_PROTECTED_CONTENT },
3700 *              .flags = 0,
3701 *      };
3702 *      struct drm_i915_gem_create_ext create_ext = {
3703 *              .size = PAGE_SIZE,
3704 *              .extensions = (uintptr_t)&protected_ext,
3705 *      };
3706 *
3707 *      int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext);
3708 *      if (err) ...
3709 */
3710struct drm_i915_gem_create_ext_protected_content {
3711	/** @base: Extension link. See struct i915_user_extension. */
3712	struct i915_user_extension base;
3713	/** @flags: reserved for future usage, currently MBZ */
3714	__u32 flags;
3715};
3716
3717/* ID of the protected content session managed by i915 when PXP is active */
3718#define I915_PROTECTED_CONTENT_DEFAULT_SESSION 0xf
3719
3720#if defined(__cplusplus)
3721}
3722#endif
3723
3724#endif /* _I915_DRM_H_ */
3725