summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/i915/i915_gem_gtt.h
blob: 93211a96fdadd2ec10962f6fac34a160ad311433 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
/*
 * Copyright © 2014 Intel Corporation
 *
 * Permission is hereby granted, free of charge, to any person obtaining a
 * copy of this software and associated documentation files (the "Software"),
 * to deal in the Software without restriction, including without limitation
 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
 * and/or sell copies of the Software, and to permit persons to whom the
 * Software is furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice (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 NONINFRINGEMENT.  IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS 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.
 *
 * Please try to maintain the following order within this file unless it makes
 * sense to do otherwise. From top to bottom:
 * 1. typedefs
 * 2. #defines, and macros
 * 3. structure definitions
 * 4. function prototypes
 *
 * Within each section, please try to order by generation in ascending order,
 * from top to bottom (ie. gen6 on the top, gen8 on the bottom).
 */

#ifndef __I915_GEM_GTT_H__
#define __I915_GEM_GTT_H__

#include <linux/io-mapping.h>
#include <linux/mm.h>
#include <linux/pagevec.h>

#include "i915_gem_timeline.h"
#include "i915_gem_request.h"
#include "i915_selftest.h"

#define I915_GTT_PAGE_SIZE_4K BIT(12)
#define I915_GTT_PAGE_SIZE_64K BIT(16)
#define I915_GTT_PAGE_SIZE_2M BIT(21)

#define I915_GTT_PAGE_SIZE I915_GTT_PAGE_SIZE_4K
#define I915_GTT_MAX_PAGE_SIZE I915_GTT_PAGE_SIZE_2M

#define I915_GTT_MIN_ALIGNMENT I915_GTT_PAGE_SIZE

#define I915_FENCE_REG_NONE -1
#define I915_MAX_NUM_FENCES 32
/* 32 fences + sign bit for FENCE_REG_NONE */
#define I915_MAX_NUM_FENCE_BITS 6

struct drm_i915_file_private;
struct drm_i915_fence_reg;

typedef u32 gen6_pte_t;
typedef u64 gen8_pte_t;
typedef u64 gen8_pde_t;
typedef u64 gen8_ppgtt_pdpe_t;
typedef u64 gen8_ppgtt_pml4e_t;

#define ggtt_total_entries(ggtt) ((ggtt)->base.total >> PAGE_SHIFT)

/* gen6-hsw has bit 11-4 for physical addr bit 39-32 */
#define GEN6_GTT_ADDR_ENCODE(addr)	((addr) | (((addr) >> 28) & 0xff0))
#define GEN6_PTE_ADDR_ENCODE(addr)	GEN6_GTT_ADDR_ENCODE(addr)
#define GEN6_PDE_ADDR_ENCODE(addr)	GEN6_GTT_ADDR_ENCODE(addr)
#define GEN6_PTE_CACHE_LLC		(2 << 1)
#define GEN6_PTE_UNCACHED		(1 << 1)
#define GEN6_PTE_VALID			(1 << 0)

#define I915_PTES(pte_len)		((unsigned int)(PAGE_SIZE / (pte_len)))
#define I915_PTE_MASK(pte_len)		(I915_PTES(pte_len) - 1)
#define I915_PDES			512
#define I915_PDE_MASK			(I915_PDES - 1)
#define NUM_PTE(pde_shift)     (1 << (pde_shift - PAGE_SHIFT))

#define GEN6_PTES			I915_PTES(sizeof(gen6_pte_t))
#define GEN6_PD_SIZE		        (I915_PDES * PAGE_SIZE)
#define GEN6_PD_ALIGN			(PAGE_SIZE * 16)
#define GEN6_PDE_SHIFT			22
#define GEN6_PDE_VALID			(1 << 0)

#define GEN7_PTE_CACHE_L3_LLC		(3 << 1)

#define BYT_PTE_SNOOPED_BY_CPU_CACHES	(1 << 2)
#define BYT_PTE_WRITEABLE		(1 << 1)

/* Cacheability Control is a 4-bit value. The low three bits are stored in bits
 * 3:1 of the PTE, while the fourth bit is stored in bit 11 of the PTE.
 */
#define HSW_CACHEABILITY_CONTROL(bits)	((((bits) & 0x7) << 1) | \
					 (((bits) & 0x8) << (11 - 3)))
#define HSW_WB_LLC_AGE3			HSW_CACHEABILITY_CONTROL(0x2)
#define HSW_WB_LLC_AGE0			HSW_CACHEABILITY_CONTROL(0x3)
#define HSW_WB_ELLC_LLC_AGE3		HSW_CACHEABILITY_CONTROL(0x8)
#define HSW_WB_ELLC_LLC_AGE0		HSW_CACHEABILITY_CONTROL(0xb)
#define HSW_WT_ELLC_LLC_AGE3		HSW_CACHEABILITY_CONTROL(0x7)
#define HSW_WT_ELLC_LLC_AGE0		HSW_CACHEABILITY_CONTROL(0x6)
#define HSW_PTE_UNCACHED		(0)
#define HSW_GTT_ADDR_ENCODE(addr)	((addr) | (((addr) >> 28) & 0x7f0))
#define HSW_PTE_ADDR_ENCODE(addr)	HSW_GTT_ADDR_ENCODE(addr)

/* GEN8 32b style address is defined as a 3 level page table:
 * 31:30 | 29:21 | 20:12 |  11:0
 * PDPE  |  PDE  |  PTE  | offset
 * The difference as compared to normal x86 3 level page table is the PDPEs are
 * programmed via register.
 */
#define GEN8_3LVL_PDPES			4
#define GEN8_PDE_SHIFT			21
#define GEN8_PDE_MASK			0x1ff
#define GEN8_PTE_SHIFT			12
#define GEN8_PTE_MASK			0x1ff
#define GEN8_PTES			I915_PTES(sizeof(gen8_pte_t))

/* GEN8 48b style address is defined as a 4 level page table:
 * 47:39 | 38:30 | 29:21 | 20:12 |  11:0
 * PML4E | PDPE  |  PDE  |  PTE  | offset
 */
#define GEN8_PML4ES_PER_PML4		512
#define GEN8_PML4E_SHIFT		39
#define GEN8_PML4E_MASK			(GEN8_PML4ES_PER_PML4 - 1)
#define GEN8_PDPE_SHIFT			30
/* NB: GEN8_PDPE_MASK is untrue for 32b platforms, but it has no impact on 32b page
 * tables */
#define GEN8_PDPE_MASK			0x1ff

#define PPAT_UNCACHED			(_PAGE_PWT | _PAGE_PCD)
#define PPAT_CACHED_PDE			0 /* WB LLC */
#define PPAT_CACHED			_PAGE_PAT /* WB LLCeLLC */
#define PPAT_DISPLAY_ELLC		_PAGE_PCD /* WT eLLC */

#define CHV_PPAT_SNOOP			(1<<6)
#define GEN8_PPAT_AGE(x)		((x)<<4)
#define GEN8_PPAT_LLCeLLC		(3<<2)
#define GEN8_PPAT_LLCELLC		(2<<2)
#define GEN8_PPAT_LLC			(1<<2)
#define GEN8_PPAT_WB			(3<<0)
#define GEN8_PPAT_WT			(2<<0)
#define GEN8_PPAT_WC			(1<<0)
#define GEN8_PPAT_UC			(0<<0)
#define GEN8_PPAT_ELLC_OVERRIDE		(0<<2)
#define GEN8_PPAT(i, x)			((u64)(x) << ((i) * 8))

#define GEN8_PPAT_GET_CA(x) ((x) & 3)
#define GEN8_PPAT_GET_TC(x) ((x) & (3 << 2))
#define GEN8_PPAT_GET_AGE(x) ((x) & (3 << 4))
#define CHV_PPAT_GET_SNOOP(x) ((x) & (1 << 6))

#define GEN8_PDE_IPS_64K BIT(11)
#define GEN8_PDE_PS_2M   BIT(7)

struct sg_table;

struct intel_rotation_info {
	struct intel_rotation_plane_info {
		/* tiles */
		unsigned int width, height, stride, offset;
	} plane[2];
} __packed;

static inline void assert_intel_rotation_info_is_packed(void)
{
	BUILD_BUG_ON(sizeof(struct intel_rotation_info) != 8*sizeof(unsigned int));
}

struct intel_partial_info {
	u64 offset;
	unsigned int size;
} __packed;

static inline void assert_intel_partial_info_is_packed(void)
{
	BUILD_BUG_ON(sizeof(struct intel_partial_info) != sizeof(u64) + sizeof(unsigned int));
}

enum i915_ggtt_view_type {
	I915_GGTT_VIEW_NORMAL = 0,
	I915_GGTT_VIEW_ROTATED = sizeof(struct intel_rotation_info),
	I915_GGTT_VIEW_PARTIAL = sizeof(struct intel_partial_info),
};

static inline void assert_i915_ggtt_view_type_is_unique(void)
{
	/* As we encode the size of each branch inside the union into its type,
	 * we have to be careful that each branch has a unique size.
	 */
	switch ((enum i915_ggtt_view_type)0) {
	case I915_GGTT_VIEW_NORMAL:
	case I915_GGTT_VIEW_PARTIAL:
	case I915_GGTT_VIEW_ROTATED:
		/* gcc complains if these are identical cases */
		break;
	}
}

struct i915_ggtt_view {
	enum i915_ggtt_view_type type;
	union {
		/* Members need to contain no holes/padding */
		struct intel_partial_info partial;
		struct intel_rotation_info rotated;
	};
};

enum i915_cache_level;

struct i915_vma;

struct i915_page_dma {
	struct page *page;
	int order;
	union {
		dma_addr_t daddr;

		/* For gen6/gen7 only. This is the offset in the GGTT
		 * where the page directory entries for PPGTT begin
		 */
		u32 ggtt_offset;
	};
};

#define px_base(px) (&(px)->base)
#define px_page(px) (px_base(px)->page)
#define px_dma(px) (px_base(px)->daddr)

struct i915_page_table {
	struct i915_page_dma base;
	unsigned int used_ptes;
};

struct i915_page_directory {
	struct i915_page_dma base;

	struct i915_page_table *page_table[I915_PDES]; /* PDEs */
	unsigned int used_pdes;
};

struct i915_page_directory_pointer {
	struct i915_page_dma base;
	struct i915_page_directory **page_directory;
	unsigned int used_pdpes;
};

struct i915_pml4 {
	struct i915_page_dma base;
	struct i915_page_directory_pointer *pdps[GEN8_PML4ES_PER_PML4];
};

struct i915_address_space {
	struct drm_mm mm;
	struct i915_gem_timeline timeline;
	struct drm_i915_private *i915;
	struct device *dma;
	/* Every address space belongs to a struct file - except for the global
	 * GTT that is owned by the driver (and so @file is set to NULL). In
	 * principle, no information should leak from one context to another
	 * (or between files/processes etc) unless explicitly shared by the
	 * owner. Tracking the owner is important in order to free up per-file
	 * objects along with the file, to aide resource tracking, and to
	 * assign blame.
	 */
	struct drm_i915_file_private *file;
	struct list_head global_link;
	u64 total;		/* size addr space maps (ex. 2GB for ggtt) */
	u64 reserved;		/* size addr space reserved */

	bool closed;

	struct i915_page_dma scratch_page;
	struct i915_page_table *scratch_pt;
	struct i915_page_directory *scratch_pd;
	struct i915_page_directory_pointer *scratch_pdp; /* GEN8+ & 48b PPGTT */

	/**
	 * List of objects currently involved in rendering.
	 *
	 * Includes buffers having the contents of their GPU caches
	 * flushed, not necessarily primitives. last_read_req
	 * represents when the rendering involved will be completed.
	 *
	 * A reference is held on the buffer while on this list.
	 */
	struct list_head active_list;

	/**
	 * LRU list of objects which are not in the ringbuffer and
	 * are ready to unbind, but are still in the GTT.
	 *
	 * last_read_req is NULL while an object is in this list.
	 *
	 * A reference is not held on the buffer while on this list,
	 * as merely being GTT-bound shouldn't prevent its being
	 * freed, and we'll pull it off the list in the free path.
	 */
	struct list_head inactive_list;

	/**
	 * List of vma that have been unbound.
	 *
	 * A reference is not held on the buffer while on this list.
	 */
	struct list_head unbound_list;

	struct pagevec free_pages;
	bool pt_kmap_wc;

	/* FIXME: Need a more generic return type */
	gen6_pte_t (*pte_encode)(dma_addr_t addr,
				 enum i915_cache_level level,
				 u32 flags); /* Create a valid PTE */
	/* flags for pte_encode */
#define PTE_READ_ONLY	(1<<0)
	int (*allocate_va_range)(struct i915_address_space *vm,
				 u64 start, u64 length);
	void (*clear_range)(struct i915_address_space *vm,
			    u64 start, u64 length);
	void (*insert_page)(struct i915_address_space *vm,
			    dma_addr_t addr,
			    u64 offset,
			    enum i915_cache_level cache_level,
			    u32 flags);
	void (*insert_entries)(struct i915_address_space *vm,
			       struct i915_vma *vma,
			       enum i915_cache_level cache_level,
			       u32 flags);
	void (*cleanup)(struct i915_address_space *vm);
	/** Unmap an object from an address space. This usually consists of
	 * setting the valid PTE entries to a reserved scratch page. */
	void (*unbind_vma)(struct i915_vma *vma);
	/* Map an object into an address space with the given cache flags. */
	int (*bind_vma)(struct i915_vma *vma,
			enum i915_cache_level cache_level,
			u32 flags);
	int (*set_pages)(struct i915_vma *vma);
	void (*clear_pages)(struct i915_vma *vma);

	I915_SELFTEST_DECLARE(struct fault_attr fault_attr);
};

#define i915_is_ggtt(V) (!(V)->file)

static inline bool
i915_vm_is_48bit(const struct i915_address_space *vm)
{
	return (vm->total - 1) >> 32;
}

static inline bool
i915_vm_has_scratch_64K(struct i915_address_space *vm)
{
	return vm->scratch_page.order == get_order(I915_GTT_PAGE_SIZE_64K);
}

/* The Graphics Translation Table is the way in which GEN hardware translates a
 * Graphics Virtual Address into a Physical Address. In addition to the normal
 * collateral associated with any va->pa translations GEN hardware also has a
 * portion of the GTT which can be mapped by the CPU and remain both coherent
 * and correct (in cases like swizzling). That region is referred to as GMADR in
 * the spec.
 */
struct i915_ggtt {
	struct i915_address_space base;
	struct io_mapping mappable;	/* Mapping to our CPU mappable region */

	phys_addr_t mappable_base;	/* PA of our GMADR */
	u64 mappable_end;		/* End offset that we can CPU map */

	/* Stolen memory is segmented in hardware with different portions
	 * offlimits to certain functions.
	 *
	 * The drm_mm is initialised to the total accessible range, as found
	 * from the PCI config. On Broadwell+, this is further restricted to
	 * avoid the first page! The upper end of stolen memory is reserved for
	 * hardware functions and similarly removed from the accessible range.
	 */
	u32 stolen_size;		/* Total size of stolen memory */
	u32 stolen_usable_size;	/* Total size minus reserved ranges */
	u32 stolen_reserved_base;
	u32 stolen_reserved_size;

	/** "Graphics Stolen Memory" holds the global PTEs */
	void __iomem *gsm;
	void (*invalidate)(struct drm_i915_private *dev_priv);

	bool do_idle_maps;

	int mtrr;

	struct drm_mm_node error_capture;
};

struct i915_hw_ppgtt {
	struct i915_address_space base;
	struct kref ref;
	struct drm_mm_node node;
	unsigned long pd_dirty_rings;
	union {
		struct i915_pml4 pml4;		/* GEN8+ & 48b PPGTT */
		struct i915_page_directory_pointer pdp;	/* GEN8+ */
		struct i915_page_directory pd;		/* GEN6-7 */
	};

	gen6_pte_t __iomem *pd_addr;

	int (*switch_mm)(struct i915_hw_ppgtt *ppgtt,
			 struct drm_i915_gem_request *req);
	void (*debug_dump)(struct i915_hw_ppgtt *ppgtt, struct seq_file *m);
};

/*
 * gen6_for_each_pde() iterates over every pde from start until start+length.
 * If start and start+length are not perfectly divisible, the macro will round
 * down and up as needed. Start=0 and length=2G effectively iterates over
 * every PDE in the system. The macro modifies ALL its parameters except 'pd',
 * so each of the other parameters should preferably be a simple variable, or
 * at most an lvalue with no side-effects!
 */
#define gen6_for_each_pde(pt, pd, start, length, iter)			\
	for (iter = gen6_pde_index(start);				\
	     length > 0 && iter < I915_PDES &&				\
		(pt = (pd)->page_table[iter], true);			\
	     ({ u32 temp = ALIGN(start+1, 1 << GEN6_PDE_SHIFT);		\
		    temp = min(temp - start, length);			\
		    start += temp, length -= temp; }), ++iter)

#define gen6_for_all_pdes(pt, pd, iter)					\
	for (iter = 0;							\
	     iter < I915_PDES &&					\
		(pt = (pd)->page_table[iter], true);			\
	     ++iter)

static inline u32 i915_pte_index(u64 address, unsigned int pde_shift)
{
	const u32 mask = NUM_PTE(pde_shift) - 1;

	return (address >> PAGE_SHIFT) & mask;
}

/* Helper to counts the number of PTEs within the given length. This count
 * does not cross a page table boundary, so the max value would be
 * GEN6_PTES for GEN6, and GEN8_PTES for GEN8.
*/
static inline u32 i915_pte_count(u64 addr, u64 length, unsigned int pde_shift)
{
	const u64 mask = ~((1ULL << pde_shift) - 1);
	u64 end;

	WARN_ON(length == 0);
	WARN_ON(offset_in_page(addr|length));

	end = addr + length;

	if ((addr & mask) != (end & mask))
		return NUM_PTE(pde_shift) - i915_pte_index(addr, pde_shift);

	return i915_pte_index(end, pde_shift) - i915_pte_index(addr, pde_shift);
}

static inline u32 i915_pde_index(u64 addr, u32 shift)
{
	return (addr >> shift) & I915_PDE_MASK;
}

static inline u32 gen6_pte_index(u32 addr)
{
	return i915_pte_index(addr, GEN6_PDE_SHIFT);
}

static inline u32 gen6_pte_count(u32 addr, u32 length)
{
	return i915_pte_count(addr, length, GEN6_PDE_SHIFT);
}

static inline u32 gen6_pde_index(u32 addr)
{
	return i915_pde_index(addr, GEN6_PDE_SHIFT);
}

static inline unsigned int
i915_pdpes_per_pdp(const struct i915_address_space *vm)
{
	if (i915_vm_is_48bit(vm))
		return GEN8_PML4ES_PER_PML4;

	return GEN8_3LVL_PDPES;
}

/* Equivalent to the gen6 version, For each pde iterates over every pde
 * between from start until start + length. On gen8+ it simply iterates
 * over every page directory entry in a page directory.
 */
#define gen8_for_each_pde(pt, pd, start, length, iter)			\
	for (iter = gen8_pde_index(start);				\
	     length > 0 && iter < I915_PDES &&				\
		(pt = (pd)->page_table[iter], true);			\
	     ({ u64 temp = ALIGN(start+1, 1 << GEN8_PDE_SHIFT);		\
		    temp = min(temp - start, length);			\
		    start += temp, length -= temp; }), ++iter)

#define gen8_for_each_pdpe(pd, pdp, start, length, iter)		\
	for (iter = gen8_pdpe_index(start);				\
	     length > 0 && iter < i915_pdpes_per_pdp(vm) &&		\
		(pd = (pdp)->page_directory[iter], true);		\
	     ({ u64 temp = ALIGN(start+1, 1 << GEN8_PDPE_SHIFT);	\
		    temp = min(temp - start, length);			\
		    start += temp, length -= temp; }), ++iter)

#define gen8_for_each_pml4e(pdp, pml4, start, length, iter)		\
	for (iter = gen8_pml4e_index(start);				\
	     length > 0 && iter < GEN8_PML4ES_PER_PML4 &&		\
		(pdp = (pml4)->pdps[iter], true);			\
	     ({ u64 temp = ALIGN(start+1, 1ULL << GEN8_PML4E_SHIFT);	\
		    temp = min(temp - start, length);			\
		    start += temp, length -= temp; }), ++iter)

static inline u32 gen8_pte_index(u64 address)
{
	return i915_pte_index(address, GEN8_PDE_SHIFT);
}

static inline u32 gen8_pde_index(u64 address)
{
	return i915_pde_index(address, GEN8_PDE_SHIFT);
}

static inline u32 gen8_pdpe_index(u64 address)
{
	return (address >> GEN8_PDPE_SHIFT) & GEN8_PDPE_MASK;
}

static inline u32 gen8_pml4e_index(u64 address)
{
	return (address >> GEN8_PML4E_SHIFT) & GEN8_PML4E_MASK;
}

static inline u64 gen8_pte_count(u64 address, u64 length)
{
	return i915_pte_count(address, length, GEN8_PDE_SHIFT);
}

static inline dma_addr_t
i915_page_dir_dma_addr(const struct i915_hw_ppgtt *ppgtt, const unsigned n)
{
	return px_dma(ppgtt->pdp.page_directory[n]);
}

static inline struct i915_ggtt *
i915_vm_to_ggtt(struct i915_address_space *vm)
{
	GEM_BUG_ON(!i915_is_ggtt(vm));
	return container_of(vm, struct i915_ggtt, base);
}

#define INTEL_MAX_PPAT_ENTRIES 8
#define INTEL_PPAT_PERFECT_MATCH (~0U)

struct intel_ppat;

struct intel_ppat_entry {
	struct intel_ppat *ppat;
	struct kref ref;
	u8 value;
};

struct intel_ppat {
	struct intel_ppat_entry entries[INTEL_MAX_PPAT_ENTRIES];
	DECLARE_BITMAP(used, INTEL_MAX_PPAT_ENTRIES);
	DECLARE_BITMAP(dirty, INTEL_MAX_PPAT_ENTRIES);
	unsigned int max_entries;
	u8 clear_value;
	/*
	 * Return a score to show how two PPAT values match,
	 * a INTEL_PPAT_PERFECT_MATCH indicates a perfect match
	 */
	unsigned int (*match)(u8 src, u8 dst);
	void (*update_hw)(struct drm_i915_private *i915);

	struct drm_i915_private *i915;
};

const struct intel_ppat_entry *
intel_ppat_get(struct drm_i915_private *i915, u8 value);
void intel_ppat_put(const struct intel_ppat_entry *entry);

int i915_gem_init_aliasing_ppgtt(struct drm_i915_private *i915);
void i915_gem_fini_aliasing_ppgtt(struct drm_i915_private *i915);

int i915_ggtt_probe_hw(struct drm_i915_private *dev_priv);
int i915_ggtt_init_hw(struct drm_i915_private *dev_priv);
int i915_ggtt_enable_hw(struct drm_i915_private *dev_priv);
void i915_ggtt_enable_guc(struct drm_i915_private *i915);
void i915_ggtt_disable_guc(struct drm_i915_private *i915);
int i915_gem_init_ggtt(struct drm_i915_private *dev_priv);
void i915_ggtt_cleanup_hw(struct drm_i915_private *dev_priv);

int i915_ppgtt_init_hw(struct drm_i915_private *dev_priv);
void i915_ppgtt_release(struct kref *kref);
struct i915_hw_ppgtt *i915_ppgtt_create(struct drm_i915_private *dev_priv,
					struct drm_i915_file_private *fpriv,
					const char *name);
void i915_ppgtt_close(struct i915_address_space *vm);
static inline void i915_ppgtt_get(struct i915_hw_ppgtt *ppgtt)
{
	if (ppgtt)
		kref_get(&ppgtt->ref);
}
static inline void i915_ppgtt_put(struct i915_hw_ppgtt *ppgtt)
{
	if (ppgtt)
		kref_put(&ppgtt->ref, i915_ppgtt_release);
}

void i915_check_and_clear_faults(struct drm_i915_private *dev_priv);
void i915_gem_suspend_gtt_mappings(struct drm_i915_private *dev_priv);
void i915_gem_restore_gtt_mappings(struct drm_i915_private *dev_priv);

int __must_check i915_gem_gtt_prepare_pages(struct drm_i915_gem_object *obj,
					    struct sg_table *pages);
void i915_gem_gtt_finish_pages(struct drm_i915_gem_object *obj,
			       struct sg_table *pages);

int i915_gem_gtt_reserve(struct i915_address_space *vm,
			 struct drm_mm_node *node,
			 u64 size, u64 offset, unsigned long color,
			 unsigned int flags);

int i915_gem_gtt_insert(struct i915_address_space *vm,
			struct drm_mm_node *node,
			u64 size, u64 alignment, unsigned long color,
			u64 start, u64 end, unsigned int flags);

/* Flags used by pin/bind&friends. */
#define PIN_NONBLOCK		BIT(0)
#define PIN_MAPPABLE		BIT(1)
#define PIN_ZONE_4G		BIT(2)
#define PIN_NONFAULT		BIT(3)
#define PIN_NOEVICT		BIT(4)

#define PIN_MBZ			BIT(5) /* I915_VMA_PIN_OVERFLOW */
#define PIN_GLOBAL		BIT(6) /* I915_VMA_GLOBAL_BIND */
#define PIN_USER		BIT(7) /* I915_VMA_LOCAL_BIND */
#define PIN_UPDATE		BIT(8)

#define PIN_HIGH		BIT(9)
#define PIN_OFFSET_BIAS		BIT(10)
#define PIN_OFFSET_FIXED	BIT(11)
#define PIN_OFFSET_MASK		(-I915_GTT_PAGE_SIZE)

#endif