i915_drm.h 100.0 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29
/*
 * Copyright 2003 Tungsten Graphics, Inc., Cedar Park, Texas.
 * All Rights Reserved.
 *
 * Permission is hereby granted, free of charge, to any person obtaining a
 * copy of this software and associated documentation files (the
 * "Software"), to deal in the Software without restriction, including
 * without limitation the rights to use, copy, modify, merge, publish,
 * distribute, sub license, and/or sell copies of the Software, and to
 * permit persons to whom the Software is furnished to do so, subject to
 * the following conditions:
 *
 * The above copyright notice and this permission notice (including the
 * next paragraph) shall be included in all copies or substantial portions
 * of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
 * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT.
 * IN NO EVENT SHALL TUNGSTEN GRAPHICS AND/OR ITS SUPPLIERS BE LIABLE FOR
 * ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
 * TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
 * SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 *
 */

#ifndef _UAPI_I915_DRM_H_
#define _UAPI_I915_DRM_H_

30
#include "drm.h"
31

32 33 34 35
#if defined(__cplusplus)
extern "C" {
#endif

36 37 38 39
/* Please note that modifications to all structs defined here are
 * subject to backwards-compatibility constraints.
 */

40 41 42 43 44
/**
 * DOC: uevents generated by i915 on it's device node
 *
 * I915_L3_PARITY_UEVENT - Generated when the driver receives a parity mismatch
 *	event from the gpu l3 cache. Additional information supplied is ROW,
45 46 47 48
 *	BANK, SUBBANK, SLICE of the affected cacheline. Userspace should keep
 *	track of these events and if a specific cache-line seems to have a
 *	persistent error remap it with the l3 remapping tool supplied in
 *	intel-gpu-tools.  The value supplied with the event is always 1.
49 50 51 52 53 54 55 56 57
 *
 * I915_ERROR_UEVENT - Generated upon error detection, currently only via
 *	hangcheck. The error detection event is a good indicator of when things
 *	began to go badly. The value supplied with the event is a 1 upon error
 *	detection, and a 0 upon reset completion, signifying no more error
 *	exists. NOTE: Disabling hangcheck or reset via module parameter will
 *	cause the related events to not be seen.
 *
 * 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 60 61 62 63
 *	reset via module parameter will cause this event to not be seen.
 */
#define I915_L3_PARITY_UEVENT		"L3_PARITY_ERROR"
#define I915_ERROR_UEVENT		"ERROR"
#define I915_RESET_UEVENT		"RESET"
64

65 66
/**
 * struct i915_user_extension - Base class for defining a chain of extensions
67 68 69 70 71 72 73 74 75 76 77 78
 *
 * Many interfaces need to grow over time. In most cases we can simply
 * extend the struct and have userspace pass in more data. Another option,
 * as demonstrated by Vulkan's approach to providing extensions for forward
 * and backward compatibility, is to use a list of optional structs to
 * provide those extra details.
 *
 * The key advantage to using an extension chain is that it allows us to
 * redefine the interface more easily than an ever growing struct of
 * increasing complexity, and for large parts of that interface to be
 * entirely optional. The downside is more pointer chasing; chasing across
 * the __user boundary with pointers encapsulated inside u64.
79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100
 *
 * Example chaining:
 *
 * .. code-block:: C
 *
 *	struct i915_user_extension ext3 {
 *		.next_extension = 0, // end
 *		.name = ...,
 *	};
 *	struct i915_user_extension ext2 {
 *		.next_extension = (uintptr_t)&ext3,
 *		.name = ...,
 *	};
 *	struct i915_user_extension ext1 {
 *		.next_extension = (uintptr_t)&ext2,
 *		.name = ...,
 *	};
 *
 * Typically the struct i915_user_extension would be embedded in some uAPI
 * struct, and in this case we would feed it the head of the chain(i.e ext1),
 * which would then apply all of the above extensions.
 *
101 102
 */
struct i915_user_extension {
103 104 105 106 107
	/**
	 * @next_extension:
	 *
	 * Pointer to the next struct i915_user_extension, or zero if the end.
	 */
108
	__u64 next_extension;
109 110 111 112 113 114 115 116 117
	/**
	 * @name: Name of the extension.
	 *
	 * Note that the name here is just some integer.
	 *
	 * Also note that the name space for this is not global for the whole
	 * driver, but rather its scope/meaning is limited to the specific piece
	 * of uAPI which has embedded the struct i915_user_extension.
	 */
118
	__u32 name;
119 120 121 122 123 124 125 126 127 128 129 130
	/**
	 * @flags: MBZ
	 *
	 * All undefined bits must be zero.
	 */
	__u32 flags;
	/**
	 * @rsvd: MBZ
	 *
	 * Reserved for future use; must be zero.
	 */
	__u32 rsvd[4];
131 132
};

133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156
/*
 * MOCS indexes used for GPU surfaces, defining the cacheability of the
 * surface data and the coherency for this data wrt. CPU vs. GPU accesses.
 */
enum i915_mocs_table_index {
	/*
	 * Not cached anywhere, coherency between CPU and GPU accesses is
	 * guaranteed.
	 */
	I915_MOCS_UNCACHED,
	/*
	 * Cacheability and coherency controlled by the kernel automatically
	 * based on the DRM_I915_GEM_SET_CACHING IOCTL setting and the current
	 * usage of the surface (used for display scanout or not).
	 */
	I915_MOCS_PTE,
	/*
	 * Cached in all GPU caches available on the platform.
	 * Coherency between CPU and GPU accesses to the surface is not
	 * guaranteed without extra synchronization.
	 */
	I915_MOCS_CACHED,
};

157 158 159 160 161 162 163 164 165 166 167 168 169
/*
 * Different engines serve different roles, and there may be more than one
 * engine serving each role. enum drm_i915_gem_engine_class provides a
 * classification of the role of the engine, which may be used when requesting
 * operations to be performed on a certain subset of engines, or for providing
 * information about that group.
 */
enum drm_i915_gem_engine_class {
	I915_ENGINE_CLASS_RENDER	= 0,
	I915_ENGINE_CLASS_COPY		= 1,
	I915_ENGINE_CLASS_VIDEO		= 2,
	I915_ENGINE_CLASS_VIDEO_ENHANCE	= 3,

170 171
	/* should be kept compact */

172 173 174
	I915_ENGINE_CLASS_INVALID	= -1
};

175 176 177 178 179 180 181 182 183 184
/*
 * There may be more than one engine fulfilling any role within the system.
 * Each engine of a class is given a unique instance number and therefore
 * any engine can be specified by its class:instance tuplet. APIs that allow
 * access to any engine in the system will use struct i915_engine_class_instance
 * for this identification.
 */
struct i915_engine_class_instance {
	__u16 engine_class; /* see enum drm_i915_gem_engine_class */
	__u16 engine_instance;
185
#define I915_ENGINE_CLASS_INVALID_NONE -1
186
#define I915_ENGINE_CLASS_INVALID_VIRTUAL -2
187 188
};

189 190 191 192 193 194 195 196
/**
 * DOC: perf_events exposed by i915 through /sys/bus/event_sources/drivers/i915
 *
 */

enum drm_i915_pmu_engine_sample {
	I915_SAMPLE_BUSY = 0,
	I915_SAMPLE_WAIT = 1,
197
	I915_SAMPLE_SEMA = 2
198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223
};

#define I915_PMU_SAMPLE_BITS (4)
#define I915_PMU_SAMPLE_MASK (0xf)
#define I915_PMU_SAMPLE_INSTANCE_BITS (8)
#define I915_PMU_CLASS_SHIFT \
	(I915_PMU_SAMPLE_BITS + I915_PMU_SAMPLE_INSTANCE_BITS)

#define __I915_PMU_ENGINE(class, instance, sample) \
	((class) << I915_PMU_CLASS_SHIFT | \
	(instance) << I915_PMU_SAMPLE_BITS | \
	(sample))

#define I915_PMU_ENGINE_BUSY(class, instance) \
	__I915_PMU_ENGINE(class, instance, I915_SAMPLE_BUSY)

#define I915_PMU_ENGINE_WAIT(class, instance) \
	__I915_PMU_ENGINE(class, instance, I915_SAMPLE_WAIT)

#define I915_PMU_ENGINE_SEMA(class, instance) \
	__I915_PMU_ENGINE(class, instance, I915_SAMPLE_SEMA)

#define __I915_PMU_OTHER(x) (__I915_PMU_ENGINE(0xff, 0xff, 0xf) + 1 + (x))

#define I915_PMU_ACTUAL_FREQUENCY	__I915_PMU_OTHER(0)
#define I915_PMU_REQUESTED_FREQUENCY	__I915_PMU_OTHER(1)
224
#define I915_PMU_INTERRUPTS		__I915_PMU_OTHER(2)
225
#define I915_PMU_RC6_RESIDENCY		__I915_PMU_OTHER(3)
226
#define I915_PMU_SOFTWARE_GT_AWAKE_TIME	__I915_PMU_OTHER(4)
227

228
#define I915_PMU_LAST /* Deprecated - do not use */ I915_PMU_RC6_RESIDENCY
229

230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342
/* Each region is a minimum of 16k, and there are at most 255 of them.
 */
#define I915_NR_TEX_REGIONS 255	/* table size 2k - maximum due to use
				 * of chars for next/prev indices */
#define I915_LOG_MIN_TEX_REGION_SIZE 14

typedef struct _drm_i915_init {
	enum {
		I915_INIT_DMA = 0x01,
		I915_CLEANUP_DMA = 0x02,
		I915_RESUME_DMA = 0x03
	} func;
	unsigned int mmio_offset;
	int sarea_priv_offset;
	unsigned int ring_start;
	unsigned int ring_end;
	unsigned int ring_size;
	unsigned int front_offset;
	unsigned int back_offset;
	unsigned int depth_offset;
	unsigned int w;
	unsigned int h;
	unsigned int pitch;
	unsigned int pitch_bits;
	unsigned int back_pitch;
	unsigned int depth_pitch;
	unsigned int cpp;
	unsigned int chipset;
} drm_i915_init_t;

typedef struct _drm_i915_sarea {
	struct drm_tex_region texList[I915_NR_TEX_REGIONS + 1];
	int last_upload;	/* last time texture was uploaded */
	int last_enqueue;	/* last time a buffer was enqueued */
	int last_dispatch;	/* age of the most recently dispatched buffer */
	int ctxOwner;		/* last context to upload state */
	int texAge;
	int pf_enabled;		/* is pageflipping allowed? */
	int pf_active;
	int pf_current_page;	/* which buffer is being displayed? */
	int perf_boxes;		/* performance boxes to be displayed */
	int width, height;      /* screen size in pixels */

	drm_handle_t front_handle;
	int front_offset;
	int front_size;

	drm_handle_t back_handle;
	int back_offset;
	int back_size;

	drm_handle_t depth_handle;
	int depth_offset;
	int depth_size;

	drm_handle_t tex_handle;
	int tex_offset;
	int tex_size;
	int log_tex_granularity;
	int pitch;
	int rotation;           /* 0, 90, 180 or 270 */
	int rotated_offset;
	int rotated_size;
	int rotated_pitch;
	int virtualX, virtualY;

	unsigned int front_tiled;
	unsigned int back_tiled;
	unsigned int depth_tiled;
	unsigned int rotated_tiled;
	unsigned int rotated2_tiled;

	int pipeA_x;
	int pipeA_y;
	int pipeA_w;
	int pipeA_h;
	int pipeB_x;
	int pipeB_y;
	int pipeB_w;
	int pipeB_h;

	/* fill out some space for old userspace triple buffer */
	drm_handle_t unused_handle;
	__u32 unused1, unused2, unused3;

	/* buffer object handles for static buffers. May change
	 * over the lifetime of the client.
	 */
	__u32 front_bo_handle;
	__u32 back_bo_handle;
	__u32 unused_bo_handle;
	__u32 depth_bo_handle;

} drm_i915_sarea_t;

/* due to userspace building against these headers we need some compat here */
#define planeA_x pipeA_x
#define planeA_y pipeA_y
#define planeA_w pipeA_w
#define planeA_h pipeA_h
#define planeB_x pipeB_x
#define planeB_y pipeB_y
#define planeB_w pipeB_w
#define planeB_h pipeB_h

/* Flags for perf_boxes
 */
#define I915_BOX_RING_EMPTY    0x1
#define I915_BOX_FLIP          0x2
#define I915_BOX_WAIT          0x4
#define I915_BOX_TEXTURE_LOAD  0x8
#define I915_BOX_LOST_CONTEXT  0x10

343 344 345 346 347 348
/*
 * i915 specific ioctls.
 *
 * The device specific ioctl range is [DRM_COMMAND_BASE, DRM_COMMAND_END) ie
 * [0x40, 0xa0) (a0 is excluded). The numbers below are defined as offset
 * against DRM_COMMAND_BASE and should be between [0x0, 0x60).
349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389
 */
#define DRM_I915_INIT		0x00
#define DRM_I915_FLUSH		0x01
#define DRM_I915_FLIP		0x02
#define DRM_I915_BATCHBUFFER	0x03
#define DRM_I915_IRQ_EMIT	0x04
#define DRM_I915_IRQ_WAIT	0x05
#define DRM_I915_GETPARAM	0x06
#define DRM_I915_SETPARAM	0x07
#define DRM_I915_ALLOC		0x08
#define DRM_I915_FREE		0x09
#define DRM_I915_INIT_HEAP	0x0a
#define DRM_I915_CMDBUFFER	0x0b
#define DRM_I915_DESTROY_HEAP	0x0c
#define DRM_I915_SET_VBLANK_PIPE	0x0d
#define DRM_I915_GET_VBLANK_PIPE	0x0e
#define DRM_I915_VBLANK_SWAP	0x0f
#define DRM_I915_HWS_ADDR	0x11
#define DRM_I915_GEM_INIT	0x13
#define DRM_I915_GEM_EXECBUFFER	0x14
#define DRM_I915_GEM_PIN	0x15
#define DRM_I915_GEM_UNPIN	0x16
#define DRM_I915_GEM_BUSY	0x17
#define DRM_I915_GEM_THROTTLE	0x18
#define DRM_I915_GEM_ENTERVT	0x19
#define DRM_I915_GEM_LEAVEVT	0x1a
#define DRM_I915_GEM_CREATE	0x1b
#define DRM_I915_GEM_PREAD	0x1c
#define DRM_I915_GEM_PWRITE	0x1d
#define DRM_I915_GEM_MMAP	0x1e
#define DRM_I915_GEM_SET_DOMAIN	0x1f
#define DRM_I915_GEM_SW_FINISH	0x20
#define DRM_I915_GEM_SET_TILING	0x21
#define DRM_I915_GEM_GET_TILING	0x22
#define DRM_I915_GEM_GET_APERTURE 0x23
#define DRM_I915_GEM_MMAP_GTT	0x24
#define DRM_I915_GET_PIPE_FROM_CRTC_ID	0x25
#define DRM_I915_GEM_MADVISE	0x26
#define DRM_I915_OVERLAY_PUT_IMAGE	0x27
#define DRM_I915_OVERLAY_ATTRS	0x28
#define DRM_I915_GEM_EXECBUFFER2	0x29
390
#define DRM_I915_GEM_EXECBUFFER2_WR	DRM_I915_GEM_EXECBUFFER2
391 392 393 394 395 396 397 398
#define DRM_I915_GET_SPRITE_COLORKEY	0x2a
#define DRM_I915_SET_SPRITE_COLORKEY	0x2b
#define DRM_I915_GEM_WAIT	0x2c
#define DRM_I915_GEM_CONTEXT_CREATE	0x2d
#define DRM_I915_GEM_CONTEXT_DESTROY	0x2e
#define DRM_I915_GEM_SET_CACHING	0x2f
#define DRM_I915_GEM_GET_CACHING	0x30
#define DRM_I915_REG_READ		0x31
399
#define DRM_I915_GET_RESET_STATS	0x32
400
#define DRM_I915_GEM_USERPTR		0x33
401 402
#define DRM_I915_GEM_CONTEXT_GETPARAM	0x34
#define DRM_I915_GEM_CONTEXT_SETPARAM	0x35
403
#define DRM_I915_PERF_OPEN		0x36
404 405
#define DRM_I915_PERF_ADD_CONFIG	0x37
#define DRM_I915_PERF_REMOVE_CONFIG	0x38
L
Lionel Landwerlin 已提交
406
#define DRM_I915_QUERY			0x39
407 408
#define DRM_I915_GEM_VM_CREATE		0x3a
#define DRM_I915_GEM_VM_DESTROY		0x3b
409
#define DRM_I915_GEM_CREATE_EXT		0x3c
410
/* Must be kept compact -- no holes */
411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431

#define DRM_IOCTL_I915_INIT		DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t)
#define DRM_IOCTL_I915_FLUSH		DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH)
#define DRM_IOCTL_I915_FLIP		DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLIP)
#define DRM_IOCTL_I915_BATCHBUFFER	DRM_IOW( DRM_COMMAND_BASE + DRM_I915_BATCHBUFFER, drm_i915_batchbuffer_t)
#define DRM_IOCTL_I915_IRQ_EMIT         DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_IRQ_EMIT, drm_i915_irq_emit_t)
#define DRM_IOCTL_I915_IRQ_WAIT         DRM_IOW( DRM_COMMAND_BASE + DRM_I915_IRQ_WAIT, drm_i915_irq_wait_t)
#define DRM_IOCTL_I915_GETPARAM         DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GETPARAM, drm_i915_getparam_t)
#define DRM_IOCTL_I915_SETPARAM         DRM_IOW( DRM_COMMAND_BASE + DRM_I915_SETPARAM, drm_i915_setparam_t)
#define DRM_IOCTL_I915_ALLOC            DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_ALLOC, drm_i915_mem_alloc_t)
#define DRM_IOCTL_I915_FREE             DRM_IOW( DRM_COMMAND_BASE + DRM_I915_FREE, drm_i915_mem_free_t)
#define DRM_IOCTL_I915_INIT_HEAP        DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT_HEAP, drm_i915_mem_init_heap_t)
#define DRM_IOCTL_I915_CMDBUFFER	DRM_IOW( DRM_COMMAND_BASE + DRM_I915_CMDBUFFER, drm_i915_cmdbuffer_t)
#define DRM_IOCTL_I915_DESTROY_HEAP	DRM_IOW( DRM_COMMAND_BASE + DRM_I915_DESTROY_HEAP, drm_i915_mem_destroy_heap_t)
#define DRM_IOCTL_I915_SET_VBLANK_PIPE	DRM_IOW( DRM_COMMAND_BASE + DRM_I915_SET_VBLANK_PIPE, drm_i915_vblank_pipe_t)
#define DRM_IOCTL_I915_GET_VBLANK_PIPE	DRM_IOR( DRM_COMMAND_BASE + DRM_I915_GET_VBLANK_PIPE, drm_i915_vblank_pipe_t)
#define DRM_IOCTL_I915_VBLANK_SWAP	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_VBLANK_SWAP, drm_i915_vblank_swap_t)
#define DRM_IOCTL_I915_HWS_ADDR		DRM_IOW(DRM_COMMAND_BASE + DRM_I915_HWS_ADDR, struct drm_i915_gem_init)
#define DRM_IOCTL_I915_GEM_INIT		DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_INIT, struct drm_i915_gem_init)
#define DRM_IOCTL_I915_GEM_EXECBUFFER	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_EXECBUFFER, struct drm_i915_gem_execbuffer)
#define DRM_IOCTL_I915_GEM_EXECBUFFER2	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_EXECBUFFER2, struct drm_i915_gem_execbuffer2)
432
#define DRM_IOCTL_I915_GEM_EXECBUFFER2_WR	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_EXECBUFFER2_WR, struct drm_i915_gem_execbuffer2)
433 434 435 436 437 438 439 440 441
#define DRM_IOCTL_I915_GEM_PIN		DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_PIN, struct drm_i915_gem_pin)
#define DRM_IOCTL_I915_GEM_UNPIN	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_UNPIN, struct drm_i915_gem_unpin)
#define DRM_IOCTL_I915_GEM_BUSY		DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_BUSY, struct drm_i915_gem_busy)
#define DRM_IOCTL_I915_GEM_SET_CACHING		DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_SET_CACHING, struct drm_i915_gem_caching)
#define DRM_IOCTL_I915_GEM_GET_CACHING		DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_GET_CACHING, struct drm_i915_gem_caching)
#define DRM_IOCTL_I915_GEM_THROTTLE	DRM_IO ( DRM_COMMAND_BASE + DRM_I915_GEM_THROTTLE)
#define DRM_IOCTL_I915_GEM_ENTERVT	DRM_IO(DRM_COMMAND_BASE + DRM_I915_GEM_ENTERVT)
#define DRM_IOCTL_I915_GEM_LEAVEVT	DRM_IO(DRM_COMMAND_BASE + DRM_I915_GEM_LEAVEVT)
#define DRM_IOCTL_I915_GEM_CREATE	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_CREATE, struct drm_i915_gem_create)
442
#define DRM_IOCTL_I915_GEM_CREATE_EXT	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_CREATE_EXT, struct drm_i915_gem_create_ext)
443 444 445 446
#define DRM_IOCTL_I915_GEM_PREAD	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_PREAD, struct drm_i915_gem_pread)
#define DRM_IOCTL_I915_GEM_PWRITE	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_PWRITE, struct drm_i915_gem_pwrite)
#define DRM_IOCTL_I915_GEM_MMAP		DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP, struct drm_i915_gem_mmap)
#define DRM_IOCTL_I915_GEM_MMAP_GTT	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP_GTT, struct drm_i915_gem_mmap_gtt)
447
#define DRM_IOCTL_I915_GEM_MMAP_OFFSET	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP_GTT, struct drm_i915_gem_mmap_offset)
448 449 450 451 452 453 454 455 456 457
#define DRM_IOCTL_I915_GEM_SET_DOMAIN	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SET_DOMAIN, struct drm_i915_gem_set_domain)
#define DRM_IOCTL_I915_GEM_SW_FINISH	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SW_FINISH, struct drm_i915_gem_sw_finish)
#define DRM_IOCTL_I915_GEM_SET_TILING	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_SET_TILING, struct drm_i915_gem_set_tiling)
#define DRM_IOCTL_I915_GEM_GET_TILING	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_GET_TILING, struct drm_i915_gem_get_tiling)
#define DRM_IOCTL_I915_GEM_GET_APERTURE	DRM_IOR  (DRM_COMMAND_BASE + DRM_I915_GEM_GET_APERTURE, struct drm_i915_gem_get_aperture)
#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)
#define DRM_IOCTL_I915_GEM_MADVISE	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MADVISE, struct drm_i915_gem_madvise)
#define DRM_IOCTL_I915_OVERLAY_PUT_IMAGE	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_OVERLAY_PUT_IMAGE, struct drm_intel_overlay_put_image)
#define DRM_IOCTL_I915_OVERLAY_ATTRS	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_OVERLAY_ATTRS, struct drm_intel_overlay_attrs)
#define DRM_IOCTL_I915_SET_SPRITE_COLORKEY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_SET_SPRITE_COLORKEY, struct drm_intel_sprite_colorkey)
458
#define DRM_IOCTL_I915_GET_SPRITE_COLORKEY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GET_SPRITE_COLORKEY, struct drm_intel_sprite_colorkey)
459 460
#define DRM_IOCTL_I915_GEM_WAIT		DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_WAIT, struct drm_i915_gem_wait)
#define DRM_IOCTL_I915_GEM_CONTEXT_CREATE	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_CREATE, struct drm_i915_gem_context_create)
461
#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)
462 463
#define DRM_IOCTL_I915_GEM_CONTEXT_DESTROY	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_DESTROY, struct drm_i915_gem_context_destroy)
#define DRM_IOCTL_I915_REG_READ			DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_REG_READ, struct drm_i915_reg_read)
464
#define DRM_IOCTL_I915_GET_RESET_STATS		DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GET_RESET_STATS, struct drm_i915_reset_stats)
465
#define DRM_IOCTL_I915_GEM_USERPTR			DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_USERPTR, struct drm_i915_gem_userptr)
466 467
#define DRM_IOCTL_I915_GEM_CONTEXT_GETPARAM	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_GETPARAM, struct drm_i915_gem_context_param)
#define DRM_IOCTL_I915_GEM_CONTEXT_SETPARAM	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_SETPARAM, struct drm_i915_gem_context_param)
468
#define DRM_IOCTL_I915_PERF_OPEN	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_OPEN, struct drm_i915_perf_open_param)
469 470
#define DRM_IOCTL_I915_PERF_ADD_CONFIG	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_ADD_CONFIG, struct drm_i915_perf_oa_config)
#define DRM_IOCTL_I915_PERF_REMOVE_CONFIG	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_REMOVE_CONFIG, __u64)
L
Lionel Landwerlin 已提交
471
#define DRM_IOCTL_I915_QUERY			DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_QUERY, struct drm_i915_query)
472 473
#define DRM_IOCTL_I915_GEM_VM_CREATE	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_VM_CREATE, struct drm_i915_gem_vm_control)
#define DRM_IOCTL_I915_GEM_VM_DESTROY	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_VM_DESTROY, struct drm_i915_gem_vm_control)
474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508

/* Allow drivers to submit batchbuffers directly to hardware, relying
 * on the security mechanisms provided by hardware.
 */
typedef struct drm_i915_batchbuffer {
	int start;		/* agp offset */
	int used;		/* nr bytes in use */
	int DR1;		/* hw flags for GFX_OP_DRAWRECT_INFO */
	int DR4;		/* window origin for GFX_OP_DRAWRECT_INFO */
	int num_cliprects;	/* mulitpass with multiple cliprects? */
	struct drm_clip_rect __user *cliprects;	/* pointer to userspace cliprects */
} drm_i915_batchbuffer_t;

/* As above, but pass a pointer to userspace buffer which can be
 * validated by the kernel prior to sending to hardware.
 */
typedef struct _drm_i915_cmdbuffer {
	char __user *buf;	/* pointer to userspace command buffer */
	int sz;			/* nr bytes in buf */
	int DR1;		/* hw flags for GFX_OP_DRAWRECT_INFO */
	int DR4;		/* window origin for GFX_OP_DRAWRECT_INFO */
	int num_cliprects;	/* mulitpass with multiple cliprects? */
	struct drm_clip_rect __user *cliprects;	/* pointer to userspace cliprects */
} drm_i915_cmdbuffer_t;

/* Userspace can request & wait on irq's:
 */
typedef struct drm_i915_irq_emit {
	int __user *irq_seq;
} drm_i915_irq_emit_t;

typedef struct drm_i915_irq_wait {
	int irq_seq;
} drm_i915_irq_wait_t;

509 510 511 512 513 514 515 516
/*
 * Different modes of per-process Graphics Translation Table,
 * see I915_PARAM_HAS_ALIASING_PPGTT
 */
#define I915_GEM_PPGTT_NONE	0
#define I915_GEM_PPGTT_ALIASING	1
#define I915_GEM_PPGTT_FULL	2

517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539
/* Ioctl to query kernel params:
 */
#define I915_PARAM_IRQ_ACTIVE            1
#define I915_PARAM_ALLOW_BATCHBUFFER     2
#define I915_PARAM_LAST_DISPATCH         3
#define I915_PARAM_CHIPSET_ID            4
#define I915_PARAM_HAS_GEM               5
#define I915_PARAM_NUM_FENCES_AVAIL      6
#define I915_PARAM_HAS_OVERLAY           7
#define I915_PARAM_HAS_PAGEFLIPPING	 8
#define I915_PARAM_HAS_EXECBUF2          9
#define I915_PARAM_HAS_BSD		 10
#define I915_PARAM_HAS_BLT		 11
#define I915_PARAM_HAS_RELAXED_FENCING	 12
#define I915_PARAM_HAS_COHERENT_RINGS	 13
#define I915_PARAM_HAS_EXEC_CONSTANTS	 14
#define I915_PARAM_HAS_RELAXED_DELTA	 15
#define I915_PARAM_HAS_GEN7_SOL_RESET	 16
#define I915_PARAM_HAS_LLC     	 	 17
#define I915_PARAM_HAS_ALIASING_PPGTT	 18
#define I915_PARAM_HAS_WAIT_TIMEOUT	 19
#define I915_PARAM_HAS_SEMAPHORES	 20
#define I915_PARAM_HAS_PRIME_VMAP_FLUSH	 21
540
#define I915_PARAM_HAS_VEBOX		 22
541
#define I915_PARAM_HAS_SECURE_BATCHES	 23
542
#define I915_PARAM_HAS_PINNED_BATCHES	 24
543
#define I915_PARAM_HAS_EXEC_NO_RELOC	 25
544
#define I915_PARAM_HAS_EXEC_HANDLE_LUT   26
545
#define I915_PARAM_HAS_WT     	 	 27
546
#define I915_PARAM_CMD_PARSER_VERSION	 28
547
#define I915_PARAM_HAS_COHERENT_PHYS_GTT 29
548
#define I915_PARAM_MMAP_VERSION          30
549
#define I915_PARAM_HAS_BSD2		 31
N
Neil Roberts 已提交
550
#define I915_PARAM_REVISION              32
551 552
#define I915_PARAM_SUBSLICE_TOTAL	 33
#define I915_PARAM_EU_TOTAL		 34
553
#define I915_PARAM_HAS_GPU_RESET	 35
554
#define I915_PARAM_HAS_RESOURCE_STREAMER 36
555
#define I915_PARAM_HAS_EXEC_SOFTPIN	 37
556 557
#define I915_PARAM_HAS_POOLED_EU	 38
#define I915_PARAM_MIN_EU_IN_POOL	 39
558
#define I915_PARAM_MMAP_GTT_VERSION	 40
559

560 561
/*
 * Query whether DRM_I915_GEM_EXECBUFFER2 supports user defined execution
562
 * priorities and the driver will attempt to execute batches in priority order.
563 564
 * The param returns a capability bitmask, nonzero implies that the scheduler
 * is enabled, with different features present according to the mask.
565 566 567
 *
 * The initial priority for each batch is supplied by the context and is
 * controlled via I915_CONTEXT_PARAM_PRIORITY.
568 569
 */
#define I915_PARAM_HAS_SCHEDULER	 41
570 571 572
#define   I915_SCHEDULER_CAP_ENABLED	(1ul << 0)
#define   I915_SCHEDULER_CAP_PRIORITY	(1ul << 1)
#define   I915_SCHEDULER_CAP_PREEMPTION	(1ul << 2)
573
#define   I915_SCHEDULER_CAP_SEMAPHORES	(1ul << 3)
574
#define   I915_SCHEDULER_CAP_ENGINE_BUSY_STATS	(1ul << 4)
575 576 577 578 579 580 581 582 583
/*
 * Indicates the 2k user priority levels are statically mapped into 3 buckets as
 * follows:
 *
 * -1k to -1	Low priority
 * 0		Normal priority
 * 1 to 1k	Highest priority
 */
#define   I915_SCHEDULER_CAP_STATIC_PRIORITY_MAP	(1ul << 5)
584

585
#define I915_PARAM_HUC_STATUS		 42
586

587 588 589 590 591 592
/* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to opt-out of
 * synchronisation with implicit fencing on individual objects.
 * See EXEC_OBJECT_ASYNC.
 */
#define I915_PARAM_HAS_EXEC_ASYNC	 43

593 594 595 596 597 598 599
/* Query whether DRM_I915_GEM_EXECBUFFER2 supports explicit fence support -
 * both being able to pass in a sync_file fd to wait upon before executing,
 * and being able to return a new sync_file fd that is signaled when the
 * current request is complete. See I915_EXEC_FENCE_IN and I915_EXEC_FENCE_OUT.
 */
#define I915_PARAM_HAS_EXEC_FENCE	 44

600 601 602 603 604 605
/* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to capture
 * user specified bufffers for post-mortem debugging of GPU hangs. See
 * EXEC_OBJECT_CAPTURE.
 */
#define I915_PARAM_HAS_EXEC_CAPTURE	 45

606 607
#define I915_PARAM_SLICE_MASK		 46

608 609 610 611 612
/* Assuming it's uniform for each slice, this queries the mask of subslices
 * per-slice for this system.
 */
#define I915_PARAM_SUBSLICE_MASK	 47

613 614 615 616 617 618
/*
 * Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying the batch buffer
 * as the first execobject as opposed to the last. See I915_EXEC_BATCH_FIRST.
 */
#define I915_PARAM_HAS_EXEC_BATCH_FIRST	 48

619 620 621 622 623
/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of
 * drm_i915_gem_exec_fence structures.  See I915_EXEC_FENCE_ARRAY.
 */
#define I915_PARAM_HAS_EXEC_FENCE_ARRAY  49

624 625 626 627 628 629 630 631 632 633 634 635 636 637 638
/*
 * Query whether every context (both per-file default and user created) is
 * isolated (insofar as HW supports). If this parameter is not true, then
 * freshly created contexts may inherit values from an existing context,
 * rather than default HW values. If true, it also ensures (insofar as HW
 * supports) that all state set by this context will not leak to any other
 * context.
 *
 * As not every engine across every gen support contexts, the returned
 * value reports the support of context isolation for individual engines by
 * returning a bitmask of each engine class set to true if that class supports
 * isolation.
 */
#define I915_PARAM_HAS_CONTEXT_ISOLATION 50

639 640 641 642 643 644
/* Frequency of the command streamer timestamps given by the *_TIMESTAMP
 * registers. This used to be fixed per platform but from CNL onwards, this
 * might vary depending on the parts.
 */
#define I915_PARAM_CS_TIMESTAMP_FREQUENCY 51

645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666
/*
 * Once upon a time we supposed that writes through the GGTT would be
 * immediately in physical memory (once flushed out of the CPU path). However,
 * on a few different processors and chipsets, this is not necessarily the case
 * as the writes appear to be buffered internally. Thus a read of the backing
 * storage (physical memory) via a different path (with different physical tags
 * to the indirect write via the GGTT) will see stale values from before
 * the GGTT write. Inside the kernel, we can for the most part keep track of
 * the different read/write domains in use (e.g. set-domain), but the assumption
 * of coherency is baked into the ABI, hence reporting its true state in this
 * parameter.
 *
 * Reports true when writes via mmap_gtt are immediately visible following an
 * lfence to flush the WCB.
 *
 * Reports false when writes via mmap_gtt are indeterminately delayed in an in
 * internal buffer and are _not_ immediately visible to third parties accessing
 * directly via mmap_cpu/mmap_wc. Use of mmap_gtt as part of an IPC
 * communications channel when reporting false is strongly disadvised.
 */
#define I915_PARAM_MMAP_GTT_COHERENT	52

667 668 669 670 671 672
/*
 * Query whether DRM_I915_GEM_EXECBUFFER2 supports coordination of parallel
 * execution through use of explicit fence support.
 * See I915_EXEC_FENCE_OUT and I915_EXEC_FENCE_SUBMIT.
 */
#define I915_PARAM_HAS_EXEC_SUBMIT_FENCE 53
673 674 675 676 677 678 679

/*
 * Revision of the i915-perf uAPI. The value returned helps determine what
 * i915-perf features are available. See drm_i915_perf_property_id.
 */
#define I915_PARAM_PERF_REVISION	54

680 681 682 683 684 685
/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of
 * timeline syncobj through drm_i915_gem_execbuffer_ext_timeline_fences. See
 * I915_EXEC_USE_EXTENSIONS.
 */
#define I915_PARAM_HAS_EXEC_TIMELINE_FENCES 55

686 687 688
/* Query if the kernel supports the I915_USERPTR_PROBE flag. */
#define I915_PARAM_HAS_USERPTR_PROBE 56

689 690
/* Must be kept compact -- no holes and well documented */

691
typedef struct drm_i915_getparam {
692
	__s32 param;
693 694 695 696
	/*
	 * WARNING: Using pointers instead of fixed-size u64 means we need to write
	 * compat32 code. Don't repeat this mistake.
	 */
697 698 699 700 701 702 703 704 705
	int __user *value;
} drm_i915_getparam_t;

/* Ioctl to set kernel params:
 */
#define I915_SETPARAM_USE_MI_BATCHBUFFER_START            1
#define I915_SETPARAM_TEX_LRU_LOG_GRANULARITY             2
#define I915_SETPARAM_ALLOW_BATCHBUFFER                   3
#define I915_SETPARAM_NUM_USED_FENCES                     4
706
/* Must be kept compact -- no holes */
707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841

typedef struct drm_i915_setparam {
	int param;
	int value;
} drm_i915_setparam_t;

/* A memory manager for regions of shared memory:
 */
#define I915_MEM_REGION_AGP 1

typedef struct drm_i915_mem_alloc {
	int region;
	int alignment;
	int size;
	int __user *region_offset;	/* offset from start of fb or agp */
} drm_i915_mem_alloc_t;

typedef struct drm_i915_mem_free {
	int region;
	int region_offset;
} drm_i915_mem_free_t;

typedef struct drm_i915_mem_init_heap {
	int region;
	int size;
	int start;
} drm_i915_mem_init_heap_t;

/* Allow memory manager to be torn down and re-initialized (eg on
 * rotate):
 */
typedef struct drm_i915_mem_destroy_heap {
	int region;
} drm_i915_mem_destroy_heap_t;

/* Allow X server to configure which pipes to monitor for vblank signals
 */
#define	DRM_I915_VBLANK_PIPE_A	1
#define	DRM_I915_VBLANK_PIPE_B	2

typedef struct drm_i915_vblank_pipe {
	int pipe;
} drm_i915_vblank_pipe_t;

/* Schedule buffer swap at given vertical blank:
 */
typedef struct drm_i915_vblank_swap {
	drm_drawable_t drawable;
	enum drm_vblank_seq_type seqtype;
	unsigned int sequence;
} drm_i915_vblank_swap_t;

typedef struct drm_i915_hws_addr {
	__u64 addr;
} drm_i915_hws_addr_t;

struct drm_i915_gem_init {
	/**
	 * Beginning offset in the GTT to be managed by the DRM memory
	 * manager.
	 */
	__u64 gtt_start;
	/**
	 * Ending offset in the GTT to be managed by the DRM memory
	 * manager.
	 */
	__u64 gtt_end;
};

struct drm_i915_gem_create {
	/**
	 * Requested size for the object.
	 *
	 * The (page-aligned) allocated size for the object will be returned.
	 */
	__u64 size;
	/**
	 * Returned handle for the object.
	 *
	 * Object handles are nonzero.
	 */
	__u32 handle;
	__u32 pad;
};

struct drm_i915_gem_pread {
	/** Handle for the object being read. */
	__u32 handle;
	__u32 pad;
	/** Offset into the object to read from */
	__u64 offset;
	/** Length of data to read */
	__u64 size;
	/**
	 * Pointer to write the data into.
	 *
	 * This is a fixed-size type for 32/64 compatibility.
	 */
	__u64 data_ptr;
};

struct drm_i915_gem_pwrite {
	/** Handle for the object being written to. */
	__u32 handle;
	__u32 pad;
	/** Offset into the object to write to */
	__u64 offset;
	/** Length of data to write */
	__u64 size;
	/**
	 * Pointer to read the data from.
	 *
	 * This is a fixed-size type for 32/64 compatibility.
	 */
	__u64 data_ptr;
};

struct drm_i915_gem_mmap {
	/** Handle for the object being mapped. */
	__u32 handle;
	__u32 pad;
	/** Offset in the object to map. */
	__u64 offset;
	/**
	 * Length of data to map.
	 *
	 * The value will be page-aligned.
	 */
	__u64 size;
	/**
	 * Returned pointer the data was mapped at.
	 *
	 * This is a fixed-size type for 32/64 compatibility.
	 */
	__u64 addr_ptr;
842 843 844 845 846 847 848 849

	/**
	 * Flags for extended behaviour.
	 *
	 * Added in version 2.
	 */
	__u64 flags;
#define I915_MMAP_WC 0x1
850 851 852 853 854 855 856 857 858 859 860 861 862 863
};

struct drm_i915_gem_mmap_gtt {
	/** Handle for the object being mapped. */
	__u32 handle;
	__u32 pad;
	/**
	 * Fake offset to use for subsequent mmap call
	 *
	 * This is a fixed-size type for 32/64 compatibility.
	 */
	__u64 offset;
};

864 865 866 867 868 869 870 871 872 873
/**
 * struct drm_i915_gem_mmap_offset - Retrieve an offset so we can mmap this buffer object.
 *
 * This struct is passed as argument to the `DRM_IOCTL_I915_GEM_MMAP_OFFSET` ioctl,
 * and is used to retrieve the fake offset to mmap an object specified by &handle.
 *
 * The legacy way of using `DRM_IOCTL_I915_GEM_MMAP` is removed on gen12+.
 * `DRM_IOCTL_I915_GEM_MMAP_GTT` is an older supported alias to this struct, but will behave
 * as setting the &extensions to 0, and &flags to `I915_MMAP_OFFSET_GTT`.
 */
874
struct drm_i915_gem_mmap_offset {
875
	/** @handle: Handle for the object being mapped. */
876
	__u32 handle;
877
	/** @pad: Must be zero */
878 879
	__u32 pad;
	/**
880
	 * @offset: The fake offset to use for subsequent mmap call
881 882 883 884 885 886
	 *
	 * This is a fixed-size type for 32/64 compatibility.
	 */
	__u64 offset;

	/**
887
	 * @flags: Flags for extended behaviour.
888
	 *
889 890 891 892 893 894 895 896 897 898 899 900 901 902
	 * It is mandatory that one of the `MMAP_OFFSET` types
	 * should be included:
	 *
	 * - `I915_MMAP_OFFSET_GTT`: Use mmap with the object bound to GTT. (Write-Combined)
	 * - `I915_MMAP_OFFSET_WC`: Use Write-Combined caching.
	 * - `I915_MMAP_OFFSET_WB`: Use Write-Back caching.
	 * - `I915_MMAP_OFFSET_FIXED`: Use object placement to determine caching.
	 *
	 * On devices with local memory `I915_MMAP_OFFSET_FIXED` is the only valid
	 * type. On devices without local memory, this caching mode is invalid.
	 *
	 * As caching mode when specifying `I915_MMAP_OFFSET_FIXED`, WC or WB will
	 * be used, depending on the object placement on creation. WB will be used
	 * when the object can only exist in system memory, WC otherwise.
903 904 905
	 */
	__u64 flags;

906 907 908 909 910 911 912 913
#define I915_MMAP_OFFSET_GTT	0
#define I915_MMAP_OFFSET_WC	1
#define I915_MMAP_OFFSET_WB	2
#define I915_MMAP_OFFSET_UC	3
#define I915_MMAP_OFFSET_FIXED	4

	/**
	 * @extensions: Zero-terminated chain of extensions.
914 915 916 917 918 919
	 *
	 * No current extensions defined; mbz.
	 */
	__u64 extensions;
};

920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937
/**
 * struct drm_i915_gem_set_domain - Adjust the objects write or read domain, in
 * preparation for accessing the pages via some CPU domain.
 *
 * Specifying a new write or read domain will flush the object out of the
 * previous domain(if required), before then updating the objects domain
 * tracking with the new domain.
 *
 * Note this might involve waiting for the object first if it is still active on
 * the GPU.
 *
 * Supported values for @read_domains and @write_domain:
 *
 *	- I915_GEM_DOMAIN_WC: Uncached write-combined domain
 *	- I915_GEM_DOMAIN_CPU: CPU cache domain
 *	- I915_GEM_DOMAIN_GTT: Mappable aperture domain
 *
 * All other domains are rejected.
938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956
 *
 * Note that for discrete, starting from DG1, this is no longer supported, and
 * is instead rejected. On such platforms the CPU domain is effectively static,
 * where we also only support a single &drm_i915_gem_mmap_offset cache mode,
 * which can't be set explicitly and instead depends on the object placements,
 * as per the below.
 *
 * Implicit caching rules, starting from DG1:
 *
 *	- If any of the object placements (see &drm_i915_gem_create_ext_memory_regions)
 *	  contain I915_MEMORY_CLASS_DEVICE then the object will be allocated and
 *	  mapped as write-combined only.
 *
 *	- Everything else is always allocated and mapped as write-back, with the
 *	  guarantee that everything is also coherent with the GPU.
 *
 * Note that this is likely to change in the future again, where we might need
 * more flexibility on future devices, so making this all explicit as part of a
 * new &drm_i915_gem_create_ext extension is probable.
957
 */
958
struct drm_i915_gem_set_domain {
959
	/** @handle: Handle for the object. */
960 961
	__u32 handle;

962
	/** @read_domains: New read domains. */
963 964
	__u32 read_domains;

965 966 967 968 969 970
	/**
	 * @write_domain: New write domain.
	 *
	 * Note that having something in the write domain implies it's in the
	 * read domain, and only that read domain.
	 */
971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044
	__u32 write_domain;
};

struct drm_i915_gem_sw_finish {
	/** Handle for the object */
	__u32 handle;
};

struct drm_i915_gem_relocation_entry {
	/**
	 * Handle of the buffer being pointed to by this relocation entry.
	 *
	 * It's appealing to make this be an index into the mm_validate_entry
	 * list to refer to the buffer, but this allows the driver to create
	 * a relocation list for state buffers and not re-write it per
	 * exec using the buffer.
	 */
	__u32 target_handle;

	/**
	 * Value to be added to the offset of the target buffer to make up
	 * the relocation entry.
	 */
	__u32 delta;

	/** Offset in the buffer the relocation entry will be written into */
	__u64 offset;

	/**
	 * Offset value of the target buffer that the relocation entry was last
	 * written as.
	 *
	 * If the buffer has the same offset as last time, we can skip syncing
	 * and writing the relocation.  This value is written back out by
	 * the execbuffer ioctl when the relocation is written.
	 */
	__u64 presumed_offset;

	/**
	 * Target memory domains read by this operation.
	 */
	__u32 read_domains;

	/**
	 * Target memory domains written by this operation.
	 *
	 * Note that only one domain may be written by the whole
	 * execbuffer operation, so that where there are conflicts,
	 * the application will get -EINVAL back.
	 */
	__u32 write_domain;
};

/** @{
 * Intel memory domains
 *
 * Most of these just align with the various caches in
 * the system and are used to flush and invalidate as
 * objects end up cached in different domains.
 */
/** CPU cache */
#define I915_GEM_DOMAIN_CPU		0x00000001
/** Render cache, used by 2D and 3D drawing */
#define I915_GEM_DOMAIN_RENDER		0x00000002
/** Sampler cache, used by texture engine */
#define I915_GEM_DOMAIN_SAMPLER		0x00000004
/** Command queue, used to load batch buffers */
#define I915_GEM_DOMAIN_COMMAND		0x00000008
/** Instruction cache, used by shader programs */
#define I915_GEM_DOMAIN_INSTRUCTION	0x00000010
/** Vertex address cache */
#define I915_GEM_DOMAIN_VERTEX		0x00000020
/** GTT domain - aperture and scanout */
#define I915_GEM_DOMAIN_GTT		0x00000040
1045 1046
/** WC domain - uncached access */
#define I915_GEM_DOMAIN_WC		0x00000080
1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073
/** @} */

struct drm_i915_gem_exec_object {
	/**
	 * User's handle for a buffer to be bound into the GTT for this
	 * operation.
	 */
	__u32 handle;

	/** Number of relocations to be performed on this buffer */
	__u32 relocation_count;
	/**
	 * Pointer to array of struct drm_i915_gem_relocation_entry containing
	 * the relocations to be performed in this buffer.
	 */
	__u64 relocs_ptr;

	/** Required alignment in graphics aperture */
	__u64 alignment;

	/**
	 * Returned value of the updated offset of the object, for future
	 * presumed_offset writes.
	 */
	__u64 offset;
};

1074
/* DRM_IOCTL_I915_GEM_EXECBUFFER was removed in Linux 5.13 */
1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118
struct drm_i915_gem_execbuffer {
	/**
	 * List of buffers to be validated with their relocations to be
	 * performend on them.
	 *
	 * This is a pointer to an array of struct drm_i915_gem_validate_entry.
	 *
	 * These buffers must be listed in an order such that all relocations
	 * a buffer is performing refer to buffers that have already appeared
	 * in the validate list.
	 */
	__u64 buffers_ptr;
	__u32 buffer_count;

	/** Offset in the batchbuffer to start execution from. */
	__u32 batch_start_offset;
	/** Bytes used in batchbuffer from batch_start_offset */
	__u32 batch_len;
	__u32 DR1;
	__u32 DR4;
	__u32 num_cliprects;
	/** This is a struct drm_clip_rect *cliprects */
	__u64 cliprects_ptr;
};

struct drm_i915_gem_exec_object2 {
	/**
	 * User's handle for a buffer to be bound into the GTT for this
	 * operation.
	 */
	__u32 handle;

	/** Number of relocations to be performed on this buffer */
	__u32 relocation_count;
	/**
	 * Pointer to array of struct drm_i915_gem_relocation_entry containing
	 * the relocations to be performed in this buffer.
	 */
	__u64 relocs_ptr;

	/** Required alignment in graphics aperture */
	__u64 alignment;

	/**
1119 1120 1121 1122 1123 1124
	 * When the EXEC_OBJECT_PINNED flag is specified this is populated by
	 * the user with the GTT offset at which this object will be pinned.
	 * When the I915_EXEC_NO_RELOC flag is specified this must contain the
	 * presumed_offset of the object.
	 * During execbuffer2 the kernel populates it with the value of the
	 * current GTT offset of the object, for future presumed_offset writes.
1125 1126 1127
	 */
	__u64 offset;

1128 1129 1130
#define EXEC_OBJECT_NEEDS_FENCE		 (1<<0)
#define EXEC_OBJECT_NEEDS_GTT		 (1<<1)
#define EXEC_OBJECT_WRITE		 (1<<2)
1131
#define EXEC_OBJECT_SUPPORTS_48B_ADDRESS (1<<3)
1132
#define EXEC_OBJECT_PINNED		 (1<<4)
1133
#define EXEC_OBJECT_PAD_TO_SIZE		 (1<<5)
1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154
/* The kernel implicitly tracks GPU activity on all GEM objects, and
 * synchronises operations with outstanding rendering. This includes
 * rendering on other devices if exported via dma-buf. However, sometimes
 * this tracking is too coarse and the user knows better. For example,
 * if the object is split into non-overlapping ranges shared between different
 * clients or engines (i.e. suballocating objects), the implicit tracking
 * by kernel assumes that each operation affects the whole object rather
 * than an individual range, causing needless synchronisation between clients.
 * The kernel will also forgo any CPU cache flushes prior to rendering from
 * the object as the client is expected to be also handling such domain
 * tracking.
 *
 * The kernel maintains the implicit tracking in order to manage resources
 * used by the GPU - this flag only disables the synchronisation prior to
 * rendering with this object in this execbuf.
 *
 * Opting out of implicit synhronisation requires the user to do its own
 * explicit tracking to avoid rendering corruption. See, for example,
 * I915_PARAM_HAS_EXEC_FENCE to order execbufs and execute them asynchronously.
 */
#define EXEC_OBJECT_ASYNC		(1<<6)
1155 1156 1157 1158 1159 1160 1161
/* Request that the contents of this execobject be copied into the error
 * state upon a GPU hang involving this batch for post-mortem debugging.
 * These buffers are recorded in no particular order as "user" in
 * /sys/class/drm/cardN/error. Query I915_PARAM_HAS_EXEC_CAPTURE to see
 * if the kernel supports this flag.
 */
#define EXEC_OBJECT_CAPTURE		(1<<7)
1162
/* All remaining bits are MBZ and RESERVED FOR FUTURE USE */
1163
#define __EXEC_OBJECT_UNKNOWN_FLAGS -(EXEC_OBJECT_CAPTURE<<1)
1164
	__u64 flags;
1165

1166 1167 1168 1169
	union {
		__u64 rsvd1;
		__u64 pad_to_size;
	};
1170 1171 1172
	__u64 rsvd2;
};

1173 1174 1175 1176 1177 1178 1179 1180
struct drm_i915_gem_exec_fence {
	/**
	 * User's handle for a drm_syncobj to wait on or signal.
	 */
	__u32 handle;

#define I915_EXEC_FENCE_WAIT            (1<<0)
#define I915_EXEC_FENCE_SIGNAL          (1<<1)
1181
#define __I915_EXEC_FENCE_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SIGNAL << 1))
1182 1183 1184
	__u32 flags;
};

1185
/*
1186 1187 1188 1189
 * See drm_i915_gem_execbuffer_ext_timeline_fences.
 */
#define DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES 0

1190
/*
1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214
 * This structure describes an array of drm_syncobj and associated points for
 * timeline variants of drm_syncobj. It is invalid to append this structure to
 * the execbuf if I915_EXEC_FENCE_ARRAY is set.
 */
struct drm_i915_gem_execbuffer_ext_timeline_fences {
	struct i915_user_extension base;

	/**
	 * Number of element in the handles_ptr & value_ptr arrays.
	 */
	__u64 fence_count;

	/**
	 * Pointer to an array of struct drm_i915_gem_exec_fence of length
	 * fence_count.
	 */
	__u64 handles_ptr;

	/**
	 * Pointer to an array of u64 values of length fence_count. Values
	 * must be 0 for a binary drm_syncobj. A Value of 0 for a timeline
	 * drm_syncobj is invalid as it turns a drm_syncobj into a binary one.
	 */
	__u64 values_ptr;
1215 1216
};

1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230
struct drm_i915_gem_execbuffer2 {
	/**
	 * List of gem_exec_object2 structs
	 */
	__u64 buffers_ptr;
	__u32 buffer_count;

	/** Offset in the batchbuffer to start execution from. */
	__u32 batch_start_offset;
	/** Bytes used in batchbuffer from batch_start_offset */
	__u32 batch_len;
	__u32 DR1;
	__u32 DR4;
	__u32 num_cliprects;
1231 1232
	/**
	 * This is a struct drm_clip_rect *cliprects if I915_EXEC_FENCE_ARRAY
1233 1234 1235 1236 1237 1238 1239 1240
	 * & I915_EXEC_USE_EXTENSIONS are not set.
	 *
	 * If I915_EXEC_FENCE_ARRAY is set, then this is a pointer to an array
	 * of struct drm_i915_gem_exec_fence and num_cliprects is the length
	 * of the array.
	 *
	 * If I915_EXEC_USE_EXTENSIONS is set, then this is a pointer to a
	 * single struct i915_user_extension and num_cliprects is 0.
1241
	 */
1242
	__u64 cliprects_ptr;
C
Chris Wilson 已提交
1243
#define I915_EXEC_RING_MASK              (0x3f)
1244 1245 1246 1247
#define I915_EXEC_DEFAULT                (0<<0)
#define I915_EXEC_RENDER                 (1<<0)
#define I915_EXEC_BSD                    (2<<0)
#define I915_EXEC_BLT                    (3<<0)
1248
#define I915_EXEC_VEBOX                  (4<<0)
1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267

/* Used for switching the constants addressing mode on gen4+ RENDER ring.
 * Gen6+ only supports relative addressing to dynamic state (default) and
 * absolute addressing.
 *
 * These flags are ignored for the BSD and BLT rings.
 */
#define I915_EXEC_CONSTANTS_MASK 	(3<<6)
#define I915_EXEC_CONSTANTS_REL_GENERAL (0<<6) /* default */
#define I915_EXEC_CONSTANTS_ABSOLUTE 	(1<<6)
#define I915_EXEC_CONSTANTS_REL_SURFACE (2<<6) /* gen4/5 only */
	__u64 flags;
	__u64 rsvd1; /* now used for context info */
	__u64 rsvd2;
};

/** Resets the SO write offset registers for transform feedback on gen7. */
#define I915_EXEC_GEN7_SOL_RESET	(1<<8)

1268 1269 1270 1271 1272
/** Request a privileged ("secure") batch buffer. Note only available for
 * DRM_ROOT_ONLY | DRM_MASTER processes.
 */
#define I915_EXEC_SECURE		(1<<9)

1273 1274 1275 1276 1277 1278 1279 1280 1281
/** Inform the kernel that the batch is and will always be pinned. This
 * negates the requirement for a workaround to be performed to avoid
 * an incoherent CS (such as can be found on 830/845). If this flag is
 * not passed, the kernel will endeavour to make sure the batch is
 * coherent with the CS before execution. If this flag is passed,
 * userspace assumes the responsibility for ensuring the same.
 */
#define I915_EXEC_IS_PINNED		(1<<10)

1282
/** Provide a hint to the kernel that the command stream and auxiliary
1283 1284 1285 1286 1287 1288
 * state buffers already holds the correct presumed addresses and so the
 * relocation process may be skipped if no buffers need to be moved in
 * preparation for the execbuffer.
 */
#define I915_EXEC_NO_RELOC		(1<<11)

1289 1290 1291 1292 1293
/** Use the reloc.handle as an index into the exec object array rather
 * than as the per-file handle.
 */
#define I915_EXEC_HANDLE_LUT		(1<<12)

1294
/** Used for switching BSD rings on the platforms with two BSD rings */
1295 1296 1297 1298 1299 1300
#define I915_EXEC_BSD_SHIFT	 (13)
#define I915_EXEC_BSD_MASK	 (3 << I915_EXEC_BSD_SHIFT)
/* default ping-pong mode */
#define I915_EXEC_BSD_DEFAULT	 (0 << I915_EXEC_BSD_SHIFT)
#define I915_EXEC_BSD_RING1	 (1 << I915_EXEC_BSD_SHIFT)
#define I915_EXEC_BSD_RING2	 (2 << I915_EXEC_BSD_SHIFT)
1301

1302 1303 1304 1305 1306
/** Tell the kernel that the batchbuffer is processed by
 *  the resource streamer.
 */
#define I915_EXEC_RESOURCE_STREAMER     (1<<15)

1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331
/* Setting I915_EXEC_FENCE_IN implies that lower_32_bits(rsvd2) represent
 * a sync_file fd to wait upon (in a nonblocking manner) prior to executing
 * the batch.
 *
 * Returns -EINVAL if the sync_file fd cannot be found.
 */
#define I915_EXEC_FENCE_IN		(1<<16)

/* Setting I915_EXEC_FENCE_OUT causes the ioctl to return a sync_file fd
 * in the upper_32_bits(rsvd2) upon success. Ownership of the fd is given
 * to the caller, and it should be close() after use. (The fd is a regular
 * file descriptor and will be cleaned up on process termination. It holds
 * a reference to the request, but nothing else.)
 *
 * The sync_file fd can be combined with other sync_file and passed either
 * to execbuf using I915_EXEC_FENCE_IN, to atomic KMS ioctls (so that a flip
 * will only occur after this request completes), or to other devices.
 *
 * Using I915_EXEC_FENCE_OUT requires use of
 * DRM_IOCTL_I915_GEM_EXECBUFFER2_WR ioctl so that the result is written
 * back to userspace. Failure to do so will cause the out-fence to always
 * be reported as zero, and the real fence fd to be leaked.
 */
#define I915_EXEC_FENCE_OUT		(1<<17)

1332 1333 1334 1335 1336 1337 1338 1339 1340 1341
/*
 * Traditionally the execbuf ioctl has only considered the final element in
 * the execobject[] to be the executable batch. Often though, the client
 * will known the batch object prior to construction and being able to place
 * it into the execobject[] array first can simplify the relocation tracking.
 * Setting I915_EXEC_BATCH_FIRST tells execbuf to use element 0 of the
 * execobject[] as the * batch instead (the default is to use the last
 * element).
 */
#define I915_EXEC_BATCH_FIRST		(1<<18)
1342 1343 1344 1345 1346 1347 1348

/* Setting I915_FENCE_ARRAY implies that num_cliprects and cliprects_ptr
 * define an array of i915_gem_exec_fence structures which specify a set of
 * dma fences to wait upon or signal.
 */
#define I915_EXEC_FENCE_ARRAY   (1<<19)

1349 1350 1351 1352 1353 1354 1355 1356 1357
/*
 * Setting I915_EXEC_FENCE_SUBMIT implies that lower_32_bits(rsvd2) represent
 * a sync_file fd to wait upon (in a nonblocking manner) prior to executing
 * the batch.
 *
 * Returns -EINVAL if the sync_file fd cannot be found.
 */
#define I915_EXEC_FENCE_SUBMIT		(1 << 20)

1358 1359 1360 1361 1362 1363 1364 1365 1366 1367
/*
 * Setting I915_EXEC_USE_EXTENSIONS implies that
 * drm_i915_gem_execbuffer2.cliprects_ptr is treated as a pointer to an linked
 * list of i915_user_extension. Each i915_user_extension node is the base of a
 * larger structure. The list of supported structures are listed in the
 * drm_i915_gem_execbuffer_ext enum.
 */
#define I915_EXEC_USE_EXTENSIONS	(1 << 21)

#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_USE_EXTENSIONS << 1))
1368

1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396
#define I915_EXEC_CONTEXT_ID_MASK	(0xffffffff)
#define i915_execbuffer2_set_context_id(eb2, context) \
	(eb2).rsvd1 = context & I915_EXEC_CONTEXT_ID_MASK
#define i915_execbuffer2_get_context_id(eb2) \
	((eb2).rsvd1 & I915_EXEC_CONTEXT_ID_MASK)

struct drm_i915_gem_pin {
	/** Handle of the buffer to be pinned. */
	__u32 handle;
	__u32 pad;

	/** alignment required within the aperture */
	__u64 alignment;

	/** Returned GTT offset of the buffer. */
	__u64 offset;
};

struct drm_i915_gem_unpin {
	/** Handle of the buffer to be unpinned. */
	__u32 handle;
	__u32 pad;
};

struct drm_i915_gem_busy {
	/** Handle of the buffer to check for busy */
	__u32 handle;

1397 1398 1399 1400 1401 1402
	/** Return busy status
	 *
	 * A return of 0 implies that the object is idle (after
	 * having flushed any pending activity), and a non-zero return that
	 * the object is still in-flight on the GPU. (The GPU has not yet
	 * signaled completion for all pending requests that reference the
1403 1404 1405 1406 1407 1408
	 * object.) An object is guaranteed to become idle eventually (so
	 * long as no new GPU commands are executed upon it). Due to the
	 * asynchronous nature of the hardware, an object reported
	 * as busy may become idle before the ioctl is completed.
	 *
	 * Furthermore, if the object is busy, which engine is busy is only
1409 1410 1411 1412 1413 1414
	 * provided as a guide and only indirectly by reporting its class
	 * (there may be more than one engine in each class). There are race
	 * conditions which prevent the report of which engines are busy from
	 * being always accurate.  However, the converse is not true. If the
	 * object is idle, the result of the ioctl, that all engines are idle,
	 * is accurate.
1415 1416
	 *
	 * The returned dword is split into two fields to indicate both
1417 1418
	 * the engine classess on which the object is being read, and the
	 * engine class on which it is currently being written (if any).
1419 1420 1421 1422
	 *
	 * The low word (bits 0:15) indicate if the object is being written
	 * to by any engine (there can only be one, as the GEM implicit
	 * synchronisation rules force writes to be serialised). Only the
1423 1424
	 * engine class (offset by 1, I915_ENGINE_CLASS_RENDER is reported as
	 * 1 not 0 etc) for the last write is reported.
1425
	 *
1426 1427
	 * The high word (bits 16:31) are a bitmask of which engines classes
	 * are currently reading from the object. Multiple engines may be
1428 1429
	 * reading from the object simultaneously.
	 *
1430
	 * The value of each engine class is the same as specified in the
1431
	 * I915_CONTEXT_PARAM_ENGINES context parameter and via perf, i.e.
1432
	 * I915_ENGINE_CLASS_RENDER, I915_ENGINE_CLASS_COPY, etc.
1433 1434 1435
	 * Some hardware may have parallel execution engines, e.g. multiple
	 * media engines, which are mapped to the same class identifier and so
	 * are not separately reported for busyness.
1436 1437 1438 1439 1440
	 *
	 * Caveat emptor:
	 * Only the boolean result of this query is reliable; that is whether
	 * the object is idle or busy. The report of which engines are busy
	 * should be only used as a heuristic.
1441 1442 1443 1444
	 */
	__u32 busy;
};

1445
/**
1446 1447
 * struct drm_i915_gem_caching - Set or get the caching for given object
 * handle.
1448
 *
1449 1450 1451 1452 1453
 * Allow userspace to control the GTT caching bits for a given object when the
 * object is later mapped through the ppGTT(or GGTT on older platforms lacking
 * ppGTT support, or if the object is used for scanout). Note that this might
 * require unbinding the object from the GTT first, if its current caching value
 * doesn't match.
1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482
 *
 * Note that this all changes on discrete platforms, starting from DG1, the
 * set/get caching is no longer supported, and is now rejected.  Instead the CPU
 * caching attributes(WB vs WC) will become an immutable creation time property
 * for the object, along with the GTT caching level. For now we don't expose any
 * new uAPI for this, instead on DG1 this is all implicit, although this largely
 * shouldn't matter since DG1 is coherent by default(without any way of
 * controlling it).
 *
 * Implicit caching rules, starting from DG1:
 *
 *     - If any of the object placements (see &drm_i915_gem_create_ext_memory_regions)
 *       contain I915_MEMORY_CLASS_DEVICE then the object will be allocated and
 *       mapped as write-combined only.
 *
 *     - Everything else is always allocated and mapped as write-back, with the
 *       guarantee that everything is also coherent with the GPU.
 *
 * Note that this is likely to change in the future again, where we might need
 * more flexibility on future devices, so making this all explicit as part of a
 * new &drm_i915_gem_create_ext extension is probable.
 *
 * Side note: Part of the reason for this is that changing the at-allocation-time CPU
 * caching attributes for the pages might be required(and is expensive) if we
 * need to then CPU map the pages later with different caching attributes. This
 * inconsistent caching behaviour, while supported on x86, is not universally
 * supported on other architectures. So for simplicity we opt for setting
 * everything at creation time, whilst also making it immutable, on discrete
 * platforms.
1483
 */
1484 1485
struct drm_i915_gem_caching {
	/**
1486 1487
	 * @handle: Handle of the buffer to set/get the caching level.
	 */
1488 1489 1490
	__u32 handle;

	/**
1491
	 * @caching: The GTT caching level to apply or possible return value.
1492
	 *
1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518
	 * The supported @caching values:
	 *
	 * I915_CACHING_NONE:
	 *
	 * GPU access is not coherent with CPU caches.  Default for machines
	 * without an LLC. This means manual flushing might be needed, if we
	 * want GPU access to be coherent.
	 *
	 * I915_CACHING_CACHED:
	 *
	 * GPU access is coherent with CPU caches and furthermore the data is
	 * cached in last-level caches shared between CPU cores and the GPU GT.
	 *
	 * I915_CACHING_DISPLAY:
	 *
	 * Special GPU caching mode which is coherent with the scanout engines.
	 * Transparently falls back to I915_CACHING_NONE on platforms where no
	 * special cache mode (like write-through or gfdt flushing) is
	 * available. The kernel automatically sets this mode when using a
	 * buffer as a scanout target.  Userspace can manually set this mode to
	 * avoid a costly stall and clflush in the hotpath of drawing the first
	 * frame.
	 */
#define I915_CACHING_NONE		0
#define I915_CACHING_CACHED		1
#define I915_CACHING_DISPLAY		2
1519 1520 1521 1522 1523 1524
	__u32 caching;
};

#define I915_TILING_NONE	0
#define I915_TILING_X		1
#define I915_TILING_Y		2
1525
#define I915_TILING_LAST	I915_TILING_Y
1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583

#define I915_BIT_6_SWIZZLE_NONE		0
#define I915_BIT_6_SWIZZLE_9		1
#define I915_BIT_6_SWIZZLE_9_10		2
#define I915_BIT_6_SWIZZLE_9_11		3
#define I915_BIT_6_SWIZZLE_9_10_11	4
/* Not seen by userland */
#define I915_BIT_6_SWIZZLE_UNKNOWN	5
/* Seen by userland. */
#define I915_BIT_6_SWIZZLE_9_17		6
#define I915_BIT_6_SWIZZLE_9_10_17	7

struct drm_i915_gem_set_tiling {
	/** Handle of the buffer to have its tiling state updated */
	__u32 handle;

	/**
	 * Tiling mode for the object (I915_TILING_NONE, I915_TILING_X,
	 * I915_TILING_Y).
	 *
	 * This value is to be set on request, and will be updated by the
	 * kernel on successful return with the actual chosen tiling layout.
	 *
	 * The tiling mode may be demoted to I915_TILING_NONE when the system
	 * has bit 6 swizzling that can't be managed correctly by GEM.
	 *
	 * Buffer contents become undefined when changing tiling_mode.
	 */
	__u32 tiling_mode;

	/**
	 * Stride in bytes for the object when in I915_TILING_X or
	 * I915_TILING_Y.
	 */
	__u32 stride;

	/**
	 * Returned address bit 6 swizzling required for CPU access through
	 * mmap mapping.
	 */
	__u32 swizzle_mode;
};

struct drm_i915_gem_get_tiling {
	/** Handle of the buffer to get tiling state for. */
	__u32 handle;

	/**
	 * Current tiling mode for the object (I915_TILING_NONE, I915_TILING_X,
	 * I915_TILING_Y).
	 */
	__u32 tiling_mode;

	/**
	 * Returned address bit 6 swizzling required for CPU access through
	 * mmap mapping.
	 */
	__u32 swizzle_mode;
1584 1585 1586 1587 1588 1589

	/**
	 * Returned address bit 6 swizzling required for CPU access through
	 * mmap mapping whilst bound.
	 */
	__u32 phys_swizzle_mode;
1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679
};

struct drm_i915_gem_get_aperture {
	/** Total size of the aperture used by i915_gem_execbuffer, in bytes */
	__u64 aper_size;

	/**
	 * Available space in the aperture used by i915_gem_execbuffer, in
	 * bytes
	 */
	__u64 aper_available_size;
};

struct drm_i915_get_pipe_from_crtc_id {
	/** ID of CRTC being requested **/
	__u32 crtc_id;

	/** pipe of requested CRTC **/
	__u32 pipe;
};

#define I915_MADV_WILLNEED 0
#define I915_MADV_DONTNEED 1
#define __I915_MADV_PURGED 2 /* internal state */

struct drm_i915_gem_madvise {
	/** Handle of the buffer to change the backing store advice */
	__u32 handle;

	/* Advice: either the buffer will be needed again in the near future,
	 *         or wont be and could be discarded under memory pressure.
	 */
	__u32 madv;

	/** Whether the backing store still exists. */
	__u32 retained;
};

/* flags */
#define I915_OVERLAY_TYPE_MASK 		0xff
#define I915_OVERLAY_YUV_PLANAR 	0x01
#define I915_OVERLAY_YUV_PACKED 	0x02
#define I915_OVERLAY_RGB		0x03

#define I915_OVERLAY_DEPTH_MASK		0xff00
#define I915_OVERLAY_RGB24		0x1000
#define I915_OVERLAY_RGB16		0x2000
#define I915_OVERLAY_RGB15		0x3000
#define I915_OVERLAY_YUV422		0x0100
#define I915_OVERLAY_YUV411		0x0200
#define I915_OVERLAY_YUV420		0x0300
#define I915_OVERLAY_YUV410		0x0400

#define I915_OVERLAY_SWAP_MASK		0xff0000
#define I915_OVERLAY_NO_SWAP		0x000000
#define I915_OVERLAY_UV_SWAP		0x010000
#define I915_OVERLAY_Y_SWAP		0x020000
#define I915_OVERLAY_Y_AND_UV_SWAP	0x030000

#define I915_OVERLAY_FLAGS_MASK		0xff000000
#define I915_OVERLAY_ENABLE		0x01000000

struct drm_intel_overlay_put_image {
	/* various flags and src format description */
	__u32 flags;
	/* source picture description */
	__u32 bo_handle;
	/* stride values and offsets are in bytes, buffer relative */
	__u16 stride_Y; /* stride for packed formats */
	__u16 stride_UV;
	__u32 offset_Y; /* offset for packet formats */
	__u32 offset_U;
	__u32 offset_V;
	/* in pixels */
	__u16 src_width;
	__u16 src_height;
	/* to compensate the scaling factors for partially covered surfaces */
	__u16 src_scan_width;
	__u16 src_scan_height;
	/* output crtc description */
	__u32 crtc_id;
	__u16 dst_x;
	__u16 dst_y;
	__u16 dst_width;
	__u16 dst_height;
};

/* flags */
#define I915_OVERLAY_UPDATE_ATTRS	(1<<0)
#define I915_OVERLAY_UPDATE_GAMMA	(1<<1)
1680
#define I915_OVERLAY_DISABLE_DEST_COLORKEY	(1<<2)
1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715
struct drm_intel_overlay_attrs {
	__u32 flags;
	__u32 color_key;
	__s32 brightness;
	__u32 contrast;
	__u32 saturation;
	__u32 gamma0;
	__u32 gamma1;
	__u32 gamma2;
	__u32 gamma3;
	__u32 gamma4;
	__u32 gamma5;
};

/*
 * Intel sprite handling
 *
 * Color keying works with a min/mask/max tuple.  Both source and destination
 * color keying is allowed.
 *
 * Source keying:
 * Sprite pixels within the min & max values, masked against the color channels
 * specified in the mask field, will be transparent.  All other pixels will
 * be displayed on top of the primary plane.  For RGB surfaces, only the min
 * and mask fields will be used; ranged compares are not allowed.
 *
 * Destination keying:
 * Primary plane pixels that match the min value, masked against the color
 * channels specified in the mask field, will be replaced by corresponding
 * pixels from the sprite plane.
 *
 * Note that source & destination keying are exclusive; only one can be
 * active on a given plane.
 */

1716 1717 1718
#define I915_SET_COLORKEY_NONE		(1<<0) /* Deprecated. Instead set
						* flags==0 to disable colorkeying.
						*/
1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737
#define I915_SET_COLORKEY_DESTINATION	(1<<1)
#define I915_SET_COLORKEY_SOURCE	(1<<2)
struct drm_intel_sprite_colorkey {
	__u32 plane_id;
	__u32 min_value;
	__u32 channel_mask;
	__u32 max_value;
	__u32 flags;
};

struct drm_i915_gem_wait {
	/** Handle of BO we shall wait on */
	__u32 bo_handle;
	__u32 flags;
	/** Number of nanoseconds to wait, Returns time remaining. */
	__s64 timeout_ns;
};

struct drm_i915_gem_context_create {
1738
	__u32 ctx_id; /* output: id of new context*/
1739 1740 1741
	__u32 pad;
};

1742 1743
struct drm_i915_gem_context_create_ext {
	__u32 ctx_id; /* output: id of new context*/
1744
	__u32 flags;
1745
#define I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS	(1u << 0)
1746
#define I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE	(1u << 1)
1747
#define I915_CONTEXT_CREATE_FLAGS_UNKNOWN \
1748
	(-(I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE << 1))
1749
	__u64 extensions;
1750 1751
};

1752 1753 1754 1755
struct drm_i915_gem_context_param {
	__u32 ctx_id;
	__u32 size;
	__u64 param;
C
Chris Wilson 已提交
1756
#define I915_CONTEXT_PARAM_BAN_PERIOD	0x1
1757 1758 1759 1760
/* I915_CONTEXT_PARAM_NO_ZEROMAP has been removed.  On the off chance
 * someone somewhere has attempted to use it, never re-use this context
 * param number.
 */
C
Chris Wilson 已提交
1761 1762
#define I915_CONTEXT_PARAM_NO_ZEROMAP	0x2
#define I915_CONTEXT_PARAM_GTT_SIZE	0x3
1763
#define I915_CONTEXT_PARAM_NO_ERROR_CAPTURE	0x4
1764
#define I915_CONTEXT_PARAM_BANNABLE	0x5
1765 1766 1767 1768
#define I915_CONTEXT_PARAM_PRIORITY	0x6
#define   I915_CONTEXT_MAX_USER_PRIORITY	1023 /* inclusive */
#define   I915_CONTEXT_DEFAULT_PRIORITY		0
#define   I915_CONTEXT_MIN_USER_PRIORITY	-1023 /* inclusive */
1769 1770 1771 1772 1773
	/*
	 * When using the following param, value should be a pointer to
	 * drm_i915_gem_context_param_sseu.
	 */
#define I915_CONTEXT_PARAM_SSEU		0x7
1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793

/*
 * Not all clients may want to attempt automatic recover of a context after
 * a hang (for example, some clients may only submit very small incremental
 * batches relying on known logical state of previous batches which will never
 * recover correctly and each attempt will hang), and so would prefer that
 * the context is forever banned instead.
 *
 * If set to false (0), after a reset, subsequent (and in flight) rendering
 * from this context is discarded, and the client will need to create a new
 * context to use instead.
 *
 * If set to true (1), the kernel will automatically attempt to recover the
 * context by skipping the hanging batch and executing the next batch starting
 * from the default context state (discarding the incomplete logical context
 * state lost due to the reset).
 *
 * On creation, all new contexts are marked as recoverable.
 */
#define I915_CONTEXT_PARAM_RECOVERABLE	0x8
1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804

	/*
	 * The id of the associated virtual memory address space (ppGTT) of
	 * this context. Can be retrieved and passed to another context
	 * (on the same fd) for both to use the same ppGTT and so share
	 * address layouts, and avoid reloading the page tables on context
	 * switches between themselves.
	 *
	 * See DRM_I915_GEM_VM_CREATE and DRM_I915_GEM_VM_DESTROY.
	 */
#define I915_CONTEXT_PARAM_VM		0x9
1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822

/*
 * I915_CONTEXT_PARAM_ENGINES:
 *
 * Bind this context to operate on this subset of available engines. Henceforth,
 * the I915_EXEC_RING selector for DRM_IOCTL_I915_GEM_EXECBUFFER2 operates as
 * an index into this array of engines; I915_EXEC_DEFAULT selecting engine[0]
 * and upwards. Slots 0...N are filled in using the specified (class, instance).
 * Use
 *	engine_class: I915_ENGINE_CLASS_INVALID,
 *	engine_instance: I915_ENGINE_CLASS_INVALID_NONE
 * to specify a gap in the array that can be filled in later, e.g. by a
 * virtual engine used for load balancing.
 *
 * Setting the number of engines bound to the context to 0, by passing a zero
 * sized argument, will revert back to default settings.
 *
 * See struct i915_context_param_engines.
1823 1824 1825 1826
 *
 * Extensions:
 *   i915_context_engines_load_balance (I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE)
 *   i915_context_engines_bond (I915_CONTEXT_ENGINES_EXT_BOND)
1827 1828
 */
#define I915_CONTEXT_PARAM_ENGINES	0xa
1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843

/*
 * I915_CONTEXT_PARAM_PERSISTENCE:
 *
 * Allow the context and active rendering to survive the process until
 * completion. Persistence allows fire-and-forget clients to queue up a
 * bunch of work, hand the output over to a display server and then quit.
 * If the context is marked as not persistent, upon closing (either via
 * an explicit DRM_I915_GEM_CONTEXT_DESTROY or implicitly from file closure
 * or process termination), the context and any outstanding requests will be
 * cancelled (and exported fences for cancelled requests marked as -EIO).
 *
 * By default, new contexts allow persistence.
 */
#define I915_CONTEXT_PARAM_PERSISTENCE	0xb
1844

1845 1846
/* This API has been removed.  On the off chance someone somewhere has
 * attempted to use it, never re-use this context param number.
1847 1848
 */
#define I915_CONTEXT_PARAM_RINGSIZE	0xc
1849
/* Must be kept compact -- no holes and well documented */
1850

1851 1852 1853
	__u64 value;
};

1854
/*
1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878
 * Context SSEU programming
 *
 * It may be necessary for either functional or performance reason to configure
 * a context to run with a reduced number of SSEU (where SSEU stands for Slice/
 * Sub-slice/EU).
 *
 * This is done by configuring SSEU configuration using the below
 * @struct drm_i915_gem_context_param_sseu for every supported engine which
 * userspace intends to use.
 *
 * Not all GPUs or engines support this functionality in which case an error
 * code -ENODEV will be returned.
 *
 * Also, flexibility of possible SSEU configuration permutations varies between
 * GPU generations and software imposed limitations. Requesting such a
 * combination will return an error code of -EINVAL.
 *
 * NOTE: When perf/OA is active the context's SSEU configuration is ignored in
 * favour of a single global setting.
 */
struct drm_i915_gem_context_param_sseu {
	/*
	 * Engine class & instance to be configured or queried.
	 */
1879
	struct i915_engine_class_instance engine;
1880 1881

	/*
1882
	 * Unknown flags must be cleared to zero.
1883 1884
	 */
	__u32 flags;
1885
#define I915_CONTEXT_SSEU_FLAG_ENGINE_INDEX (1u << 0)
1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912

	/*
	 * Mask of slices to enable for the context. Valid values are a subset
	 * of the bitmask value returned for I915_PARAM_SLICE_MASK.
	 */
	__u64 slice_mask;

	/*
	 * Mask of subslices to enable for the context. Valid values are a
	 * subset of the bitmask value return by I915_PARAM_SUBSLICE_MASK.
	 */
	__u64 subslice_mask;

	/*
	 * Minimum/Maximum number of EUs to enable per subslice for the
	 * context. min_eus_per_subslice must be inferior or equal to
	 * max_eus_per_subslice.
	 */
	__u16 min_eus_per_subslice;
	__u16 max_eus_per_subslice;

	/*
	 * Unused for now. Must be cleared to zero.
	 */
	__u32 rsvd;
};

1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975
/**
 * DOC: Virtual Engine uAPI
 *
 * Virtual engine is a concept where userspace is able to configure a set of
 * physical engines, submit a batch buffer, and let the driver execute it on any
 * engine from the set as it sees fit.
 *
 * This is primarily useful on parts which have multiple instances of a same
 * class engine, like for example GT3+ Skylake parts with their two VCS engines.
 *
 * For instance userspace can enumerate all engines of a certain class using the
 * previously described `Engine Discovery uAPI`_. After that userspace can
 * create a GEM context with a placeholder slot for the virtual engine (using
 * `I915_ENGINE_CLASS_INVALID` and `I915_ENGINE_CLASS_INVALID_NONE` for class
 * and instance respectively) and finally using the
 * `I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE` extension place a virtual engine in
 * the same reserved slot.
 *
 * Example of creating a virtual engine and submitting a batch buffer to it:
 *
 * .. code-block:: C
 *
 * 	I915_DEFINE_CONTEXT_ENGINES_LOAD_BALANCE(virtual, 2) = {
 * 		.base.name = I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE,
 * 		.engine_index = 0, // Place this virtual engine into engine map slot 0
 * 		.num_siblings = 2,
 * 		.engines = { { I915_ENGINE_CLASS_VIDEO, 0 },
 * 			     { I915_ENGINE_CLASS_VIDEO, 1 }, },
 * 	};
 * 	I915_DEFINE_CONTEXT_PARAM_ENGINES(engines, 1) = {
 * 		.engines = { { I915_ENGINE_CLASS_INVALID,
 * 			       I915_ENGINE_CLASS_INVALID_NONE } },
 * 		.extensions = to_user_pointer(&virtual), // Chains after load_balance extension
 * 	};
 * 	struct drm_i915_gem_context_create_ext_setparam p_engines = {
 * 		.base = {
 * 			.name = I915_CONTEXT_CREATE_EXT_SETPARAM,
 * 		},
 * 		.param = {
 * 			.param = I915_CONTEXT_PARAM_ENGINES,
 * 			.value = to_user_pointer(&engines),
 * 			.size = sizeof(engines),
 * 		},
 * 	};
 * 	struct drm_i915_gem_context_create_ext create = {
 * 		.flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS,
 * 		.extensions = to_user_pointer(&p_engines);
 * 	};
 *
 * 	ctx_id = gem_context_create_ext(drm_fd, &create);
 *
 * 	// Now we have created a GEM context with its engine map containing a
 * 	// single virtual engine. Submissions to this slot can go either to
 * 	// vcs0 or vcs1, depending on the load balancing algorithm used inside
 * 	// the driver. The load balancing is dynamic from one batch buffer to
 * 	// another and transparent to userspace.
 *
 * 	...
 * 	execbuf.rsvd1 = ctx_id;
 * 	execbuf.flags = 0; // Submits to index 0 which is the virtual engine
 * 	gem_execbuf(drm_fd, &execbuf);
 */

1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012
/*
 * i915_context_engines_load_balance:
 *
 * Enable load balancing across this set of engines.
 *
 * Into the I915_EXEC_DEFAULT slot [0], a virtual engine is created that when
 * used will proxy the execbuffer request onto one of the set of engines
 * in such a way as to distribute the load evenly across the set.
 *
 * The set of engines must be compatible (e.g. the same HW class) as they
 * will share the same logical GPU context and ring.
 *
 * To intermix rendering with the virtual engine and direct rendering onto
 * the backing engines (bypassing the load balancing proxy), the context must
 * be defined to use a single timeline for all engines.
 */
struct i915_context_engines_load_balance {
	struct i915_user_extension base;

	__u16 engine_index;
	__u16 num_siblings;
	__u32 flags; /* all undefined flags must be zero */

	__u64 mbz64; /* reserved for future use; must be zero */

	struct i915_engine_class_instance engines[0];
} __attribute__((packed));

#define I915_DEFINE_CONTEXT_ENGINES_LOAD_BALANCE(name__, N__) struct { \
	struct i915_user_extension base; \
	__u16 engine_index; \
	__u16 num_siblings; \
	__u32 flags; \
	__u64 mbz64; \
	struct i915_engine_class_instance engines[N__]; \
} __attribute__((packed)) name__

2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051
/*
 * i915_context_engines_bond:
 *
 * Constructed bonded pairs for execution within a virtual engine.
 *
 * All engines are equal, but some are more equal than others. Given
 * the distribution of resources in the HW, it may be preferable to run
 * a request on a given subset of engines in parallel to a request on a
 * specific engine. We enable this selection of engines within a virtual
 * engine by specifying bonding pairs, for any given master engine we will
 * only execute on one of the corresponding siblings within the virtual engine.
 *
 * To execute a request in parallel on the master engine and a sibling requires
 * coordination with a I915_EXEC_FENCE_SUBMIT.
 */
struct i915_context_engines_bond {
	struct i915_user_extension base;

	struct i915_engine_class_instance master;

	__u16 virtual_index; /* index of virtual engine in ctx->engines[] */
	__u16 num_bonds;

	__u64 flags; /* all undefined flags must be zero */
	__u64 mbz64[4]; /* reserved for future use; must be zero */

	struct i915_engine_class_instance engines[0];
} __attribute__((packed));

#define I915_DEFINE_CONTEXT_ENGINES_BOND(name__, N__) struct { \
	struct i915_user_extension base; \
	struct i915_engine_class_instance master; \
	__u16 virtual_index; \
	__u16 num_bonds; \
	__u64 flags; \
	__u64 mbz64[4]; \
	struct i915_engine_class_instance engines[N__]; \
} __attribute__((packed)) name__

2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106
/**
 * DOC: Context Engine Map uAPI
 *
 * Context engine map is a new way of addressing engines when submitting batch-
 * buffers, replacing the existing way of using identifiers like `I915_EXEC_BLT`
 * inside the flags field of `struct drm_i915_gem_execbuffer2`.
 *
 * To use it created GEM contexts need to be configured with a list of engines
 * the user is intending to submit to. This is accomplished using the
 * `I915_CONTEXT_PARAM_ENGINES` parameter and `struct
 * i915_context_param_engines`.
 *
 * For such contexts the `I915_EXEC_RING_MASK` field becomes an index into the
 * configured map.
 *
 * Example of creating such context and submitting against it:
 *
 * .. code-block:: C
 *
 * 	I915_DEFINE_CONTEXT_PARAM_ENGINES(engines, 2) = {
 * 		.engines = { { I915_ENGINE_CLASS_RENDER, 0 },
 * 			     { I915_ENGINE_CLASS_COPY, 0 } }
 * 	};
 * 	struct drm_i915_gem_context_create_ext_setparam p_engines = {
 * 		.base = {
 * 			.name = I915_CONTEXT_CREATE_EXT_SETPARAM,
 * 		},
 * 		.param = {
 * 			.param = I915_CONTEXT_PARAM_ENGINES,
 * 			.value = to_user_pointer(&engines),
 * 			.size = sizeof(engines),
 * 		},
 * 	};
 * 	struct drm_i915_gem_context_create_ext create = {
 * 		.flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS,
 * 		.extensions = to_user_pointer(&p_engines);
 * 	};
 *
 * 	ctx_id = gem_context_create_ext(drm_fd, &create);
 *
 * 	// We have now created a GEM context with two engines in the map:
 * 	// Index 0 points to rcs0 while index 1 points to bcs0. Other engines
 * 	// will not be accessible from this context.
 *
 * 	...
 * 	execbuf.rsvd1 = ctx_id;
 * 	execbuf.flags = 0; // Submits to index 0, which is rcs0 for this context
 * 	gem_execbuf(drm_fd, &execbuf);
 *
 * 	...
 * 	execbuf.rsvd1 = ctx_id;
 * 	execbuf.flags = 1; // Submits to index 0, which is bcs0 for this context
 * 	gem_execbuf(drm_fd, &execbuf);
 */

2107 2108
struct i915_context_param_engines {
	__u64 extensions; /* linked chain of extension blocks, 0 terminates */
2109
#define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */
2110
#define I915_CONTEXT_ENGINES_EXT_BOND 1 /* see i915_context_engines_bond */
2111 2112 2113 2114 2115 2116 2117 2118
	struct i915_engine_class_instance engines[0];
} __attribute__((packed));

#define I915_DEFINE_CONTEXT_PARAM_ENGINES(name__, N__) struct { \
	__u64 extensions; \
	struct i915_engine_class_instance engines[N__]; \
} __attribute__((packed)) name__

2119 2120 2121 2122 2123 2124
struct drm_i915_gem_context_create_ext_setparam {
#define I915_CONTEXT_CREATE_EXT_SETPARAM 0
	struct i915_user_extension base;
	struct drm_i915_gem_context_param param;
};

2125 2126 2127
/* This API has been removed.  On the off chance someone somewhere has
 * attempted to use it, never re-use this extension number.
 */
2128 2129
#define I915_CONTEXT_CREATE_EXT_CLONE 1

2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199
struct drm_i915_gem_context_destroy {
	__u32 ctx_id;
	__u32 pad;
};

/*
 * DRM_I915_GEM_VM_CREATE -
 *
 * Create a new virtual memory address space (ppGTT) for use within a context
 * on the same file. Extensions can be provided to configure exactly how the
 * address space is setup upon creation.
 *
 * The id of new VM (bound to the fd) for use with I915_CONTEXT_PARAM_VM is
 * returned in the outparam @id.
 *
 * No flags are defined, with all bits reserved and must be zero.
 *
 * An extension chain maybe provided, starting with @extensions, and terminated
 * by the @next_extension being 0. Currently, no extensions are defined.
 *
 * DRM_I915_GEM_VM_DESTROY -
 *
 * Destroys a previously created VM id, specified in @id.
 *
 * No extensions or flags are allowed currently, and so must be zero.
 */
struct drm_i915_gem_vm_control {
	__u64 extensions;
	__u32 flags;
	__u32 vm_id;
};

struct drm_i915_reg_read {
	/*
	 * Register offset.
	 * For 64bit wide registers where the upper 32bits don't immediately
	 * follow the lower 32bits, the offset of the lower 32bits must
	 * be specified
	 */
	__u64 offset;
#define I915_REG_READ_8B_WA (1ul << 0)

	__u64 val; /* Return value */
};

/* Known registers:
 *
 * Render engine timestamp - 0x2358 + 64bit - gen7+
 * - Note this register returns an invalid value if using the default
 *   single instruction 8byte read, in order to workaround that pass
 *   flag I915_REG_READ_8B_WA in offset field.
 *
 */

struct drm_i915_reset_stats {
	__u32 ctx_id;
	__u32 flags;

	/* All resets since boot/module reload, for all contexts */
	__u32 reset_count;

	/* Number of batches lost when active in GPU, for this context */
	__u32 batch_active;

	/* Number of batches lost pending for execution, for this context */
	__u32 batch_pending;

	__u32 pad;
};

2200 2201 2202 2203 2204 2205
/**
 * struct drm_i915_gem_userptr - Create GEM object from user allocated memory.
 *
 * Userptr objects have several restrictions on what ioctls can be used with the
 * object handle.
 */
2206
struct drm_i915_gem_userptr {
2207 2208 2209 2210 2211
	/**
	 * @user_ptr: The pointer to the allocated memory.
	 *
	 * Needs to be aligned to PAGE_SIZE.
	 */
2212
	__u64 user_ptr;
2213 2214 2215 2216 2217 2218 2219 2220 2221 2222

	/**
	 * @user_size:
	 *
	 * The size in bytes for the allocated memory. This will also become the
	 * object size.
	 *
	 * Needs to be aligned to PAGE_SIZE, and should be at least PAGE_SIZE,
	 * or larger.
	 */
2223
	__u64 user_size;
2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236

	/**
	 * @flags:
	 *
	 * Supported flags:
	 *
	 * I915_USERPTR_READ_ONLY:
	 *
	 * Mark the object as readonly, this also means GPU access can only be
	 * readonly. This is only supported on HW which supports readonly access
	 * through the GTT. If the HW can't support readonly access, an error is
	 * returned.
	 *
2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252
	 * I915_USERPTR_PROBE:
	 *
	 * Probe the provided @user_ptr range and validate that the @user_ptr is
	 * indeed pointing to normal memory and that the range is also valid.
	 * For example if some garbage address is given to the kernel, then this
	 * should complain.
	 *
	 * Returns -EFAULT if the probe failed.
	 *
	 * Note that this doesn't populate the backing pages, and also doesn't
	 * guarantee that the object will remain valid when the object is
	 * eventually used.
	 *
	 * The kernel supports this feature if I915_PARAM_HAS_USERPTR_PROBE
	 * returns a non-zero value.
	 *
2253 2254 2255 2256
	 * I915_USERPTR_UNSYNCHRONIZED:
	 *
	 * NOT USED. Setting this flag will result in an error.
	 */
2257 2258
	__u32 flags;
#define I915_USERPTR_READ_ONLY 0x1
2259
#define I915_USERPTR_PROBE 0x2
2260 2261
#define I915_USERPTR_UNSYNCHRONIZED 0x80000000
	/**
2262
	 * @handle: Returned handle for the object.
2263 2264 2265 2266 2267 2268
	 *
	 * Object handles are nonzero.
	 */
	__u32 handle;
};

2269
enum drm_i915_oa_format {
2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281
	I915_OA_FORMAT_A13 = 1,	    /* HSW only */
	I915_OA_FORMAT_A29,	    /* HSW only */
	I915_OA_FORMAT_A13_B8_C8,   /* HSW only */
	I915_OA_FORMAT_B4_C8,	    /* HSW only */
	I915_OA_FORMAT_A45_B8_C8,   /* HSW only */
	I915_OA_FORMAT_B4_C8_A16,   /* HSW only */
	I915_OA_FORMAT_C4_B8,	    /* HSW+ */

	/* Gen8+ */
	I915_OA_FORMAT_A12,
	I915_OA_FORMAT_A12_B8_C8,
	I915_OA_FORMAT_A32u40_A4u32_B8_C8,
2282 2283 2284 2285

	I915_OA_FORMAT_MAX	    /* non-ABI */
};

2286 2287 2288 2289 2290
enum drm_i915_perf_property_id {
	/**
	 * Open the stream for a specific context handle (as used with
	 * execbuffer2). A stream opened for a specific context this way
	 * won't typically require root privileges.
2291 2292
	 *
	 * This property is available in perf revision 1.
2293 2294 2295
	 */
	DRM_I915_PERF_PROP_CTX_HANDLE = 1,

2296 2297 2298
	/**
	 * A value of 1 requests the inclusion of raw OA unit reports as
	 * part of stream samples.
2299 2300
	 *
	 * This property is available in perf revision 1.
2301 2302 2303 2304 2305
	 */
	DRM_I915_PERF_PROP_SAMPLE_OA,

	/**
	 * The value specifies which set of OA unit metrics should be
2306
	 * configured, defining the contents of any OA unit reports.
2307 2308
	 *
	 * This property is available in perf revision 1.
2309 2310 2311 2312 2313
	 */
	DRM_I915_PERF_PROP_OA_METRICS_SET,

	/**
	 * The value specifies the size and layout of OA unit reports.
2314 2315
	 *
	 * This property is available in perf revision 1.
2316 2317 2318 2319 2320 2321 2322 2323 2324
	 */
	DRM_I915_PERF_PROP_OA_FORMAT,

	/**
	 * Specifying this property implicitly requests periodic OA unit
	 * sampling and (at least on Haswell) the sampling frequency is derived
	 * from this exponent as follows:
	 *
	 *   80ns * 2^(period_exponent + 1)
2325 2326
	 *
	 * This property is available in perf revision 1.
2327 2328 2329
	 */
	DRM_I915_PERF_PROP_OA_EXPONENT,

2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340
	/**
	 * Specifying this property is only valid when specify a context to
	 * filter with DRM_I915_PERF_PROP_CTX_HANDLE. Specifying this property
	 * will hold preemption of the particular context we want to gather
	 * performance data about. The execbuf2 submissions must include a
	 * drm_i915_gem_execbuffer_ext_perf parameter for this to apply.
	 *
	 * This property is available in perf revision 3.
	 */
	DRM_I915_PERF_PROP_HOLD_PREEMPTION,

2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351
	/**
	 * Specifying this pins all contexts to the specified SSEU power
	 * configuration for the duration of the recording.
	 *
	 * This parameter's value is a pointer to a struct
	 * drm_i915_gem_context_param_sseu.
	 *
	 * This property is available in perf revision 4.
	 */
	DRM_I915_PERF_PROP_GLOBAL_SSEU,

2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364
	/**
	 * This optional parameter specifies the timer interval in nanoseconds
	 * at which the i915 driver will check the OA buffer for available data.
	 * Minimum allowed value is 100 microseconds. A default value is used by
	 * the driver if this parameter is not specified. Note that larger timer
	 * values will reduce cpu consumption during OA perf captures. However,
	 * excessively large values would potentially result in OA buffer
	 * overwrites as captures reach end of the OA buffer.
	 *
	 * This property is available in perf revision 5.
	 */
	DRM_I915_PERF_PROP_POLL_OA_PERIOD,

2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380
	DRM_I915_PERF_PROP_MAX /* non-ABI */
};

struct drm_i915_perf_open_param {
	__u32 flags;
#define I915_PERF_FLAG_FD_CLOEXEC	(1<<0)
#define I915_PERF_FLAG_FD_NONBLOCK	(1<<1)
#define I915_PERF_FLAG_DISABLED		(1<<2)

	/** The number of u64 (id, value) pairs */
	__u32 num_properties;

	/**
	 * Pointer to array of u64 (id, value) pairs configuring the stream
	 * to open.
	 */
2381
	__u64 properties_ptr;
2382 2383
};

2384
/*
2385 2386 2387 2388 2389 2390 2391 2392
 * Enable data capture for a stream that was either opened in a disabled state
 * via I915_PERF_FLAG_DISABLED or was later disabled via
 * I915_PERF_IOCTL_DISABLE.
 *
 * It is intended to be cheaper to disable and enable a stream than it may be
 * to close and re-open a stream with the same configuration.
 *
 * It's undefined whether any pending data for the stream will be lost.
2393 2394
 *
 * This ioctl is available in perf revision 1.
2395
 */
2396
#define I915_PERF_IOCTL_ENABLE	_IO('i', 0x0)
2397

2398
/*
2399 2400 2401
 * Disable data capture for a stream.
 *
 * It is an error to try and read a stream that is disabled.
2402 2403
 *
 * This ioctl is available in perf revision 1.
2404
 */
2405 2406
#define I915_PERF_IOCTL_DISABLE	_IO('i', 0x1)

2407
/*
2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419
 * Change metrics_set captured by a stream.
 *
 * If the stream is bound to a specific context, the configuration change
 * will performed inline with that context such that it takes effect before
 * the next execbuf submission.
 *
 * Returns the previously bound metrics set id, or a negative error code.
 *
 * This ioctl is available in perf revision 2.
 */
#define I915_PERF_IOCTL_CONFIG	_IO('i', 0x2)

2420
/*
2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440
 * Common to all i915 perf records
 */
struct drm_i915_perf_record_header {
	__u32 type;
	__u16 pad;
	__u16 size;
};

enum drm_i915_perf_record_type {

	/**
	 * Samples are the work horse record type whose contents are extensible
	 * and defined when opening an i915 perf stream based on the given
	 * properties.
	 *
	 * Boolean properties following the naming convention
	 * DRM_I915_PERF_SAMPLE_xyz_PROP request the inclusion of 'xyz' data in
	 * every sample.
	 *
	 * The order of these sample properties given by userspace has no
2441
	 * affect on the ordering of data within a sample. The order is
2442 2443 2444 2445 2446
	 * documented here.
	 *
	 * struct {
	 *     struct drm_i915_perf_record_header header;
	 *
2447
	 *     { u32 oa_report[]; } && DRM_I915_PERF_PROP_SAMPLE_OA
2448 2449 2450 2451
	 * };
	 */
	DRM_I915_PERF_RECORD_SAMPLE = 1,

2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464
	/*
	 * Indicates that one or more OA reports were not written by the
	 * hardware. This can happen for example if an MI_REPORT_PERF_COUNT
	 * command collides with periodic sampling - which would be more likely
	 * at higher sampling frequencies.
	 */
	DRM_I915_PERF_RECORD_OA_REPORT_LOST = 2,

	/**
	 * An error occurred that resulted in all pending OA reports being lost.
	 */
	DRM_I915_PERF_RECORD_OA_BUFFER_LOST = 3,

2465 2466 2467
	DRM_I915_PERF_RECORD_MAX /* non-ABI */
};

2468
/*
2469 2470 2471 2472 2473 2474 2475 2476 2477 2478
 * Structure to upload perf dynamic configuration into the kernel.
 */
struct drm_i915_perf_oa_config {
	/** String formatted like "%08x-%04x-%04x-%04x-%012x" */
	char uuid[36];

	__u32 n_mux_regs;
	__u32 n_boolean_regs;
	__u32 n_flex_regs;

2479
	/*
L
Lionel Landwerlin 已提交
2480 2481 2482
	 * These fields are pointers to tuples of u32 values (register address,
	 * value). For example the expected length of the buffer pointed by
	 * mux_regs_ptr is (2 * sizeof(u32) * n_mux_regs).
2483
	 */
2484 2485 2486
	__u64 mux_regs_ptr;
	__u64 boolean_regs_ptr;
	__u64 flex_regs_ptr;
2487 2488
};

2489 2490 2491 2492 2493 2494
/**
 * struct drm_i915_query_item - An individual query for the kernel to process.
 *
 * The behaviour is determined by the @query_id. Note that exactly what
 * @data_ptr is also depends on the specific @query_id.
 */
L
Lionel Landwerlin 已提交
2495
struct drm_i915_query_item {
2496
	/** @query_id: The id for this query */
L
Lionel Landwerlin 已提交
2497
	__u64 query_id;
2498
#define DRM_I915_QUERY_TOPOLOGY_INFO    1
2499
#define DRM_I915_QUERY_ENGINE_INFO	2
2500
#define DRM_I915_QUERY_PERF_CONFIG      3
2501
#define DRM_I915_QUERY_MEMORY_REGIONS   4
2502
/* Must be kept compact -- no holes and well documented */
L
Lionel Landwerlin 已提交
2503

2504 2505 2506
	/**
	 * @length:
	 *
L
Lionel Landwerlin 已提交
2507
	 * When set to zero by userspace, this is filled with the size of the
2508
	 * data to be written at the @data_ptr pointer. The kernel sets this
L
Lionel Landwerlin 已提交
2509 2510 2511 2512 2513
	 * value to a negative value to signal an error on a particular query
	 * item.
	 */
	__s32 length;

2514 2515 2516
	/**
	 * @flags:
	 *
2517 2518 2519
	 * When query_id == DRM_I915_QUERY_TOPOLOGY_INFO, must be 0.
	 *
	 * When query_id == DRM_I915_QUERY_PERF_CONFIG, must be one of the
2520 2521 2522 2523 2524
	 * following:
	 *
	 *	- DRM_I915_QUERY_PERF_CONFIG_LIST
	 *      - DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID
	 *      - DRM_I915_QUERY_PERF_CONFIG_FOR_UUID
L
Lionel Landwerlin 已提交
2525 2526
	 */
	__u32 flags;
2527 2528 2529
#define DRM_I915_QUERY_PERF_CONFIG_LIST          1
#define DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID 2
#define DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID   3
L
Lionel Landwerlin 已提交
2530

2531 2532 2533 2534 2535
	/**
	 * @data_ptr:
	 *
	 * Data will be written at the location pointed by @data_ptr when the
	 * value of @length matches the length of the data to be written by the
L
Lionel Landwerlin 已提交
2536 2537 2538 2539 2540
	 * kernel.
	 */
	__u64 data_ptr;
};

2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563
/**
 * struct drm_i915_query - Supply an array of struct drm_i915_query_item for the
 * kernel to fill out.
 *
 * Note that this is generally a two step process for each struct
 * drm_i915_query_item in the array:
 *
 * 1. Call the DRM_IOCTL_I915_QUERY, giving it our array of struct
 *    drm_i915_query_item, with &drm_i915_query_item.length set to zero. The
 *    kernel will then fill in the size, in bytes, which tells userspace how
 *    memory it needs to allocate for the blob(say for an array of properties).
 *
 * 2. Next we call DRM_IOCTL_I915_QUERY again, this time with the
 *    &drm_i915_query_item.data_ptr equal to our newly allocated blob. Note that
 *    the &drm_i915_query_item.length should still be the same as what the
 *    kernel previously set. At this point the kernel can fill in the blob.
 *
 * Note that for some query items it can make sense for userspace to just pass
 * in a buffer/blob equal to or larger than the required size. In this case only
 * a single ioctl call is needed. For some smaller query items this can work
 * quite well.
 *
 */
L
Lionel Landwerlin 已提交
2564
struct drm_i915_query {
2565
	/** @num_items: The number of elements in the @items_ptr array */
L
Lionel Landwerlin 已提交
2566 2567
	__u32 num_items;

2568 2569
	/**
	 * @flags: Unused for now. Must be cleared to zero.
L
Lionel Landwerlin 已提交
2570 2571 2572
	 */
	__u32 flags;

2573 2574 2575 2576 2577
	/**
	 * @items_ptr:
	 *
	 * Pointer to an array of struct drm_i915_query_item. The number of
	 * array elements is @num_items.
L
Lionel Landwerlin 已提交
2578 2579 2580 2581
	 */
	__u64 items_ptr;
};

2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593
/*
 * Data written by the kernel with query DRM_I915_QUERY_TOPOLOGY_INFO :
 *
 * data: contains the 3 pieces of information :
 *
 * - the slice mask with one bit per slice telling whether a slice is
 *   available. The availability of slice X can be queried with the following
 *   formula :
 *
 *           (data[X / 8] >> (X % 8)) & 1
 *
 * - the subslice mask for each slice with one bit per subslice telling
2594 2595 2596 2597
 *   whether a subslice is available. Gen12 has dual-subslices, which are
 *   similar to two gen11 subslices. For gen12, this array represents dual-
 *   subslices. The availability of subslice Y in slice X can be queried
 *   with the following formula :
2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644
 *
 *           (data[subslice_offset +
 *                 X * subslice_stride +
 *                 Y / 8] >> (Y % 8)) & 1
 *
 * - the EU mask for each subslice in each slice with one bit per EU telling
 *   whether an EU is available. The availability of EU Z in subslice Y in
 *   slice X can be queried with the following formula :
 *
 *           (data[eu_offset +
 *                 (X * max_subslices + Y) * eu_stride +
 *                 Z / 8] >> (Z % 8)) & 1
 */
struct drm_i915_query_topology_info {
	/*
	 * Unused for now. Must be cleared to zero.
	 */
	__u16 flags;

	__u16 max_slices;
	__u16 max_subslices;
	__u16 max_eus_per_subslice;

	/*
	 * Offset in data[] at which the subslice masks are stored.
	 */
	__u16 subslice_offset;

	/*
	 * Stride at which each of the subslice masks for each slice are
	 * stored.
	 */
	__u16 subslice_stride;

	/*
	 * Offset in data[] at which the EU masks are stored.
	 */
	__u16 eu_offset;

	/*
	 * Stride at which each of the EU masks for each subslice are stored.
	 */
	__u16 eu_stride;

	__u8 data[];
};

2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714
/**
 * DOC: Engine Discovery uAPI
 *
 * Engine discovery uAPI is a way of enumerating physical engines present in a
 * GPU associated with an open i915 DRM file descriptor. This supersedes the old
 * way of using `DRM_IOCTL_I915_GETPARAM` and engine identifiers like
 * `I915_PARAM_HAS_BLT`.
 *
 * The need for this interface came starting with Icelake and newer GPUs, which
 * started to establish a pattern of having multiple engines of a same class,
 * where not all instances were always completely functionally equivalent.
 *
 * Entry point for this uapi is `DRM_IOCTL_I915_QUERY` with the
 * `DRM_I915_QUERY_ENGINE_INFO` as the queried item id.
 *
 * Example for getting the list of engines:
 *
 * .. code-block:: C
 *
 * 	struct drm_i915_query_engine_info *info;
 * 	struct drm_i915_query_item item = {
 * 		.query_id = DRM_I915_QUERY_ENGINE_INFO;
 * 	};
 * 	struct drm_i915_query query = {
 * 		.num_items = 1,
 * 		.items_ptr = (uintptr_t)&item,
 * 	};
 * 	int err, i;
 *
 * 	// First query the size of the blob we need, this needs to be large
 * 	// enough to hold our array of engines. The kernel will fill out the
 * 	// item.length for us, which is the number of bytes we need.
 * 	//
 * 	// Alternatively a large buffer can be allocated straight away enabling
 * 	// querying in one pass, in which case item.length should contain the
 * 	// length of the provided buffer.
 * 	err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
 * 	if (err) ...
 *
 * 	info = calloc(1, item.length);
 * 	// Now that we allocated the required number of bytes, we call the ioctl
 * 	// again, this time with the data_ptr pointing to our newly allocated
 * 	// blob, which the kernel can then populate with info on all engines.
 * 	item.data_ptr = (uintptr_t)&info,
 *
 * 	err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
 * 	if (err) ...
 *
 * 	// We can now access each engine in the array
 * 	for (i = 0; i < info->num_engines; i++) {
 * 		struct drm_i915_engine_info einfo = info->engines[i];
 * 		u16 class = einfo.engine.class;
 * 		u16 instance = einfo.engine.instance;
 * 		....
 * 	}
 *
 * 	free(info);
 *
 * Each of the enumerated engines, apart from being defined by its class and
 * instance (see `struct i915_engine_class_instance`), also can have flags and
 * capabilities defined as documented in i915_drm.h.
 *
 * For instance video engines which support HEVC encoding will have the
 * `I915_VIDEO_CLASS_CAPABILITY_HEVC` capability bit set.
 *
 * Engine discovery only fully comes to its own when combined with the new way
 * of addressing engines when submitting batch buffers using contexts with
 * engine maps configured.
 */

2715 2716 2717 2718 2719 2720
/**
 * struct drm_i915_engine_info
 *
 * Describes one engine and it's capabilities as known to the driver.
 */
struct drm_i915_engine_info {
2721
	/** @engine: Engine class and instance. */
2722 2723
	struct i915_engine_class_instance engine;

2724
	/** @rsvd0: Reserved field. */
2725 2726
	__u32 rsvd0;

2727
	/** @flags: Engine flags. */
2728 2729
	__u64 flags;

2730
	/** @capabilities: Capabilities of this engine. */
2731 2732 2733 2734
	__u64 capabilities;
#define I915_VIDEO_CLASS_CAPABILITY_HEVC		(1 << 0)
#define I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC	(1 << 1)

2735
	/** @rsvd1: Reserved fields. */
2736 2737 2738 2739 2740 2741 2742 2743 2744 2745
	__u64 rsvd1[4];
};

/**
 * struct drm_i915_query_engine_info
 *
 * Engine info query enumerates all engines known to the driver by filling in
 * an array of struct drm_i915_engine_info structures.
 */
struct drm_i915_query_engine_info {
2746
	/** @num_engines: Number of struct drm_i915_engine_info structs following. */
2747 2748
	__u32 num_engines;

2749
	/** @rsvd: MBZ */
2750 2751
	__u32 rsvd[3];

2752
	/** @engines: Marker for drm_i915_engine_info structures. */
2753 2754 2755
	struct drm_i915_engine_info engines[];
};

2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805
/*
 * Data written by the kernel with query DRM_I915_QUERY_PERF_CONFIG.
 */
struct drm_i915_query_perf_config {
	union {
		/*
		 * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_LIST, i915 sets
		 * this fields to the number of configurations available.
		 */
		__u64 n_configs;

		/*
		 * When query_id == DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID,
		 * i915 will use the value in this field as configuration
		 * identifier to decide what data to write into config_ptr.
		 */
		__u64 config;

		/*
		 * When query_id == DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID,
		 * i915 will use the value in this field as configuration
		 * identifier to decide what data to write into config_ptr.
		 *
		 * String formatted like "%08x-%04x-%04x-%04x-%012x"
		 */
		char uuid[36];
	};

	/*
	 * Unused for now. Must be cleared to zero.
	 */
	__u32 flags;

	/*
	 * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_LIST, i915 will
	 * write an array of __u64 of configuration identifiers.
	 *
	 * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_DATA, i915 will
	 * write a struct drm_i915_perf_oa_config. If the following fields of
	 * drm_i915_perf_oa_config are set not set to 0, i915 will write into
	 * the associated pointers the values of submitted when the
	 * configuration was created :
	 *
	 *         - n_mux_regs
	 *         - n_boolean_regs
	 *         - n_flex_regs
	 */
	__u8 data[];
};

2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938
/**
 * enum drm_i915_gem_memory_class - Supported memory classes
 */
enum drm_i915_gem_memory_class {
	/** @I915_MEMORY_CLASS_SYSTEM: System memory */
	I915_MEMORY_CLASS_SYSTEM = 0,
	/** @I915_MEMORY_CLASS_DEVICE: Device local-memory */
	I915_MEMORY_CLASS_DEVICE,
};

/**
 * struct drm_i915_gem_memory_class_instance - Identify particular memory region
 */
struct drm_i915_gem_memory_class_instance {
	/** @memory_class: See enum drm_i915_gem_memory_class */
	__u16 memory_class;

	/** @memory_instance: Which instance */
	__u16 memory_instance;
};

/**
 * struct drm_i915_memory_region_info - Describes one region as known to the
 * driver.
 *
 * Note that we reserve some stuff here for potential future work. As an example
 * we might want expose the capabilities for a given region, which could include
 * things like if the region is CPU mappable/accessible, what are the supported
 * mapping types etc.
 *
 * Note that to extend struct drm_i915_memory_region_info and struct
 * drm_i915_query_memory_regions in the future the plan is to do the following:
 *
 * .. code-block:: C
 *
 *	struct drm_i915_memory_region_info {
 *		struct drm_i915_gem_memory_class_instance region;
 *		union {
 *			__u32 rsvd0;
 *			__u32 new_thing1;
 *		};
 *		...
 *		union {
 *			__u64 rsvd1[8];
 *			struct {
 *				__u64 new_thing2;
 *				__u64 new_thing3;
 *				...
 *			};
 *		};
 *	};
 *
 * With this things should remain source compatible between versions for
 * userspace, even as we add new fields.
 *
 * Note this is using both struct drm_i915_query_item and struct drm_i915_query.
 * For this new query we are adding the new query id DRM_I915_QUERY_MEMORY_REGIONS
 * at &drm_i915_query_item.query_id.
 */
struct drm_i915_memory_region_info {
	/** @region: The class:instance pair encoding */
	struct drm_i915_gem_memory_class_instance region;

	/** @rsvd0: MBZ */
	__u32 rsvd0;

	/** @probed_size: Memory probed by the driver (-1 = unknown) */
	__u64 probed_size;

	/** @unallocated_size: Estimate of memory remaining (-1 = unknown) */
	__u64 unallocated_size;

	/** @rsvd1: MBZ */
	__u64 rsvd1[8];
};

/**
 * struct drm_i915_query_memory_regions
 *
 * The region info query enumerates all regions known to the driver by filling
 * in an array of struct drm_i915_memory_region_info structures.
 *
 * Example for getting the list of supported regions:
 *
 * .. code-block:: C
 *
 *	struct drm_i915_query_memory_regions *info;
 *	struct drm_i915_query_item item = {
 *		.query_id = DRM_I915_QUERY_MEMORY_REGIONS;
 *	};
 *	struct drm_i915_query query = {
 *		.num_items = 1,
 *		.items_ptr = (uintptr_t)&item,
 *	};
 *	int err, i;
 *
 *	// First query the size of the blob we need, this needs to be large
 *	// enough to hold our array of regions. The kernel will fill out the
 *	// item.length for us, which is the number of bytes we need.
 *	err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
 *	if (err) ...
 *
 *	info = calloc(1, item.length);
 *	// Now that we allocated the required number of bytes, we call the ioctl
 *	// again, this time with the data_ptr pointing to our newly allocated
 *	// blob, which the kernel can then populate with the all the region info.
 *	item.data_ptr = (uintptr_t)&info,
 *
 *	err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
 *	if (err) ...
 *
 *	// We can now access each region in the array
 *	for (i = 0; i < info->num_regions; i++) {
 *		struct drm_i915_memory_region_info mr = info->regions[i];
 *		u16 class = mr.region.class;
 *		u16 instance = mr.region.instance;
 *
 *		....
 *	}
 *
 *	free(info);
 */
struct drm_i915_query_memory_regions {
	/** @num_regions: Number of supported regions */
	__u32 num_regions;

	/** @rsvd: MBZ */
	__u32 rsvd[3];

	/** @regions: Info about each supported region */
	struct drm_i915_memory_region_info regions[];
};

2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954
/**
 * struct drm_i915_gem_create_ext - Existing gem_create behaviour, with added
 * extension support using struct i915_user_extension.
 *
 * Note that in the future we want to have our buffer flags here, at least for
 * the stuff that is immutable. Previously we would have two ioctls, one to
 * create the object with gem_create, and another to apply various parameters,
 * however this creates some ambiguity for the params which are considered
 * immutable. Also in general we're phasing out the various SET/GET ioctls.
 */
struct drm_i915_gem_create_ext {
	/**
	 * @size: Requested size for the object.
	 *
	 * The (page-aligned) allocated size for the object will be returned.
	 *
2955 2956 2957 2958 2959
	 * Note that for some devices we have might have further minimum
	 * page-size restrictions(larger than 4K), like for device local-memory.
	 * However in general the final size here should always reflect any
	 * rounding up, if for example using the I915_GEM_CREATE_EXT_MEMORY_REGIONS
	 * extension to place the object in device local-memory.
2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979
	 */
	__u64 size;
	/**
	 * @handle: Returned handle for the object.
	 *
	 * Object handles are nonzero.
	 */
	__u32 handle;
	/** @flags: MBZ */
	__u32 flags;
	/**
	 * @extensions: The chain of extensions to apply to this object.
	 *
	 * This will be useful in the future when we need to support several
	 * different extensions, and we need to apply more than one when
	 * creating the object. See struct i915_user_extension.
	 *
	 * If we don't supply any extensions then we get the same old gem_create
	 * behaviour.
	 *
2980 2981
	 * For I915_GEM_CREATE_EXT_MEMORY_REGIONS usage see
	 * struct drm_i915_gem_create_ext_memory_regions.
2982
	 */
2983
#define I915_GEM_CREATE_EXT_MEMORY_REGIONS 0
2984 2985 2986
	__u64 extensions;
};

2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040
/**
 * struct drm_i915_gem_create_ext_memory_regions - The
 * I915_GEM_CREATE_EXT_MEMORY_REGIONS extension.
 *
 * Set the object with the desired set of placements/regions in priority
 * order. Each entry must be unique and supported by the device.
 *
 * This is provided as an array of struct drm_i915_gem_memory_class_instance, or
 * an equivalent layout of class:instance pair encodings. See struct
 * drm_i915_query_memory_regions and DRM_I915_QUERY_MEMORY_REGIONS for how to
 * query the supported regions for a device.
 *
 * As an example, on discrete devices, if we wish to set the placement as
 * device local-memory we can do something like:
 *
 * .. code-block:: C
 *
 *	struct drm_i915_gem_memory_class_instance region_lmem = {
 *              .memory_class = I915_MEMORY_CLASS_DEVICE,
 *              .memory_instance = 0,
 *      };
 *      struct drm_i915_gem_create_ext_memory_regions regions = {
 *              .base = { .name = I915_GEM_CREATE_EXT_MEMORY_REGIONS },
 *              .regions = (uintptr_t)&region_lmem,
 *              .num_regions = 1,
 *      };
 *      struct drm_i915_gem_create_ext create_ext = {
 *              .size = 16 * PAGE_SIZE,
 *              .extensions = (uintptr_t)&regions,
 *      };
 *
 *      int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext);
 *      if (err) ...
 *
 * At which point we get the object handle in &drm_i915_gem_create_ext.handle,
 * along with the final object size in &drm_i915_gem_create_ext.size, which
 * should account for any rounding up, if required.
 */
struct drm_i915_gem_create_ext_memory_regions {
	/** @base: Extension link. See struct i915_user_extension. */
	struct i915_user_extension base;

	/** @pad: MBZ */
	__u32 pad;
	/** @num_regions: Number of elements in the @regions array. */
	__u32 num_regions;
	/**
	 * @regions: The regions/placements array.
	 *
	 * An array of struct drm_i915_gem_memory_class_instance.
	 */
	__u64 regions;
};

3041 3042 3043 3044
#if defined(__cplusplus)
}
#endif

3045
#endif /* _UAPI_I915_DRM_H_ */