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
|
/*
* SPDX-License-Identifier: MIT
*
* Copyright © 2008 Intel Corporation
*/
#include <linux/string.h>
#include <linux/bitops.h>
#include "i915_drv.h"
#include "i915_gem.h"
#include "i915_gem_ioctls.h"
#include "i915_gem_mman.h"
#include "i915_gem_object.h"
/**
* DOC: buffer object tiling
*
* i915_gem_set_tiling_ioctl() and i915_gem_get_tiling_ioctl() is the userspace
* interface to declare fence register requirements.
*
* In principle GEM doesn't care at all about the internal data layout of an
* object, and hence it also doesn't care about tiling or swizzling. There's two
* exceptions:
*
* - For X and Y tiling the hardware provides detilers for CPU access, so called
* fences. Since there's only a limited amount of them the kernel must manage
* these, and therefore userspace must tell the kernel the object tiling if it
* wants to use fences for detiling.
* - On gen3 and gen4 platforms have a swizzling pattern for tiled objects which
* depends upon the physical page frame number. When swapping such objects the
* page frame number might change and the kernel must be able to fix this up
* and hence now the tiling. Note that on a subset of platforms with
* asymmetric memory channel population the swizzling pattern changes in an
* unknown way, and for those the kernel simply forbids swapping completely.
*
* Since neither of this applies for new tiling layouts on modern platforms like
* W, Ys and Yf tiling GEM only allows object tiling to be set to X or Y tiled.
* Anything else can be handled in userspace entirely without the kernel's
* invovlement.
*/
/**
* i915_gem_fence_size - required global GTT size for a fence
* @i915: i915 device
* @size: object size
* @tiling: tiling mode
* @stride: tiling stride
*
* Return the required global GTT size for a fence (view of a tiled object),
* taking into account potential fence register mapping.
*/
u32 i915_gem_fence_size(struct drm_i915_private *i915,
u32 size, unsigned int tiling, unsigned int stride)
{
u32 ggtt_size;
GEM_BUG_ON(!size);
if (tiling == I915_TILING_NONE)
return size;
GEM_BUG_ON(!stride);
if (INTEL_GEN(i915) >= 4) {
stride *= i915_gem_tile_height(tiling);
GEM_BUG_ON(!IS_ALIGNED(stride, I965_FENCE_PAGE));
return roundup(size, stride);
}
/* Previous chips need a power-of-two fence region when tiling */
if (IS_GEN(i915, 3))
ggtt_size = 1024*1024;
else
ggtt_size = 512*1024;
while (ggtt_size < size)
ggtt_size <<= 1;
return ggtt_size;
}
/**
* i915_gem_fence_alignment - required global GTT alignment for a fence
* @i915: i915 device
* @size: object size
* @tiling: tiling mode
* @stride: tiling stride
*
* Return the required global GTT alignment for a fence (a view of a tiled
* object), taking into account potential fence register mapping.
*/
u32 i915_gem_fence_alignment(struct drm_i915_private *i915, u32 size,
unsigned int tiling, unsigned int stride)
{
GEM_BUG_ON(!size);
/*
* Minimum alignment is 4k (GTT page size), but might be greater
* if a fence register is needed for the object.
*/
if (tiling == I915_TILING_NONE)
return I915_GTT_MIN_ALIGNMENT;
if (INTEL_GEN(i915) >= 4)
return I965_FENCE_PAGE;
/*
* Previous chips need to be aligned to the size of the smallest
* fence register that can contain the object.
*/
return i915_gem_fence_size(i915, size, tiling, stride);
}
/* Check pitch constriants for all chips & tiling formats */
static bool
i915_tiling_ok(struct drm_i915_gem_object *obj,
unsigned int tiling, unsigned int stride)
{
struct drm_i915_private *i915 = to_i915(obj->base.dev);
unsigned int tile_width;
/* Linear is always fine */
if (tiling == I915_TILING_NONE)
return true;
if (tiling > I915_TILING_LAST)
return false;
/* check maximum stride & object size */
/* i965+ stores the end address of the gtt mapping in the fence
* reg, so dont bother to check the size */
if (INTEL_GEN(i915) >= 7) {
if (stride / 128 > GEN7_FENCE_MAX_PITCH_VAL)
return false;
} else if (INTEL_GEN(i915) >= 4) {
if (stride / 128 > I965_FENCE_MAX_PITCH_VAL)
return false;
} else {
if (stride > 8192)
return false;
if (!is_power_of_2(stride))
return false;
}
if (IS_GEN(i915, 2) ||
(tiling == I915_TILING_Y && HAS_128_BYTE_Y_TILING(i915)))
tile_width = 128;
else
tile_width = 512;
if (!stride || !IS_ALIGNED(stride, tile_width))
return false;
return true;
}
static bool i915_vma_fence_prepare(struct i915_vma *vma,
int tiling_mode, unsigned int stride)
{
struct drm_i915_private *i915 = vma->vm->i915;
u32 size, alignment;
if (!i915_vma_is_map_and_fenceable(vma))
return true;
size = i915_gem_fence_size(i915, vma->size, tiling_mode, stride);
if (vma->node.size < size)
return false;
alignment = i915_gem_fence_alignment(i915, vma->size, tiling_mode, stride);
if (!IS_ALIGNED(vma->node.start, alignment))
return false;
return true;
}
/* Make the current GTT allocation valid for the change in tiling. */
static int
i915_gem_object_fence_prepare(struct drm_i915_gem_object *obj,
int tiling_mode, unsigned int stride)
{
struct i915_ggtt *ggtt = &to_i915(obj->base.dev)->ggtt;
struct i915_vma *vma, *vn;
LIST_HEAD(unbind);
int ret = 0;
if (tiling_mode == I915_TILING_NONE)
return 0;
mutex_lock(&ggtt->vm.mutex);
spin_lock(&obj->vma.lock);
for_each_ggtt_vma(vma, obj) {
GEM_BUG_ON(vma->vm != &ggtt->vm);
if (i915_vma_fence_prepare(vma, tiling_mode, stride))
continue;
list_move(&vma->vm_link, &unbind);
}
spin_unlock(&obj->vma.lock);
list_for_each_entry_safe(vma, vn, &unbind, vm_link) {
ret = __i915_vma_unbind(vma);
if (ret) {
/* Restore the remaining vma on an error */
list_splice(&unbind, &ggtt->vm.bound_list);
break;
}
}
mutex_unlock(&ggtt->vm.mutex);
return ret;
}
int
i915_gem_object_set_tiling(struct drm_i915_gem_object *obj,
unsigned int tiling, unsigned int stride)
{
struct drm_i915_private *i915 = to_i915(obj->base.dev);
struct i915_vma *vma;
int err;
/* Make sure we don't cross-contaminate obj->tiling_and_stride */
BUILD_BUG_ON(I915_TILING_LAST & STRIDE_MASK);
GEM_BUG_ON(!i915_tiling_ok(obj, tiling, stride));
GEM_BUG_ON(!stride ^ (tiling == I915_TILING_NONE));
if ((tiling | stride) == obj->tiling_and_stride)
return 0;
if (i915_gem_object_is_framebuffer(obj))
return -EBUSY;
/* We need to rebind the object if its current allocation
* no longer meets the alignment restrictions for its new
* tiling mode. Otherwise we can just leave it alone, but
* need to ensure that any fence register is updated before
* the next fenced (either through the GTT or by the BLT unit
* on older GPUs) access.
*
* After updating the tiling parameters, we then flag whether
* we need to update an associated fence register. Note this
* has to also include the unfenced register the GPU uses
* whilst executing a fenced command for an untiled object.
*/
i915_gem_object_lock(obj);
if (i915_gem_object_is_framebuffer(obj)) {
i915_gem_object_unlock(obj);
return -EBUSY;
}
err = i915_gem_object_fence_prepare(obj, tiling, stride);
if (err) {
i915_gem_object_unlock(obj);
return err;
}
/* If the memory has unknown (i.e. varying) swizzling, we pin the
* pages to prevent them being swapped out and causing corruption
* due to the change in swizzling.
*/
mutex_lock(&obj->mm.lock);
if (i915_gem_object_has_pages(obj) &&
obj->mm.madv == I915_MADV_WILLNEED &&
i915->quirks & QUIRK_PIN_SWIZZLED_PAGES) {
if (tiling == I915_TILING_NONE) {
GEM_BUG_ON(!obj->mm.quirked);
__i915_gem_object_unpin_pages(obj);
obj->mm.quirked = false;
}
if (!i915_gem_object_is_tiled(obj)) {
GEM_BUG_ON(obj->mm.quirked);
__i915_gem_object_pin_pages(obj);
obj->mm.quirked = true;
}
}
mutex_unlock(&obj->mm.lock);
spin_lock(&obj->vma.lock);
for_each_ggtt_vma(vma, obj) {
vma->fence_size =
i915_gem_fence_size(i915, vma->size, tiling, stride);
vma->fence_alignment =
i915_gem_fence_alignment(i915,
vma
|