1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
|
/*
* Copyright © 2008 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.
*
* Authors:
* Eric Anholt <eric@anholt.net>
*
*/
#include <linux/acpi.h>
#include <linux/pnp.h>
#include "linux/string.h"
#include "linux/bitops.h"
#include "drmP.h"
#include "drm.h"
#include "i915_drm.h"
#include "i915_drv.h"
/** @file i915_gem_tiling.c
*
* Support for managing tiling state of buffer objects.
*
* The idea behind tiling is to increase cache hit rates by rearranging
* pixel data so that a group of pixel accesses are in the same cacheline.
* Performance improvement from doing this on the back/depth buffer are on
* the order of 30%.
*
* Intel architectures make this somewhat more complicated, though, by
* adjustments made to addressing of data when the memory is in interleaved
* mode (matched pairs of DIMMS) to improve memory bandwidth.
* For interleaved memory, the CPU sends every sequential 64 bytes
* to an alternate memory channel so it can get the bandwidth from both.
*
* The GPU also rearranges its accesses for increased bandwidth to interleaved
* memory, and it matches what the CPU does for non-tiled. However, when tiled
* it does it a little differently, since one walks addresses not just in the
* X direction but also Y. So, along with alternating channels when bit
* 6 of the address flips, it also alternates when other bits flip -- Bits 9
* (every 512 bytes, an X tile scanline) and 10 (every two X tile scanlines)
* are common to both the 915 and 965-class hardware.
*
* The CPU also sometimes XORs in higher bits as well, to improve
* bandwidth doing strided access like we do so frequently in graphics. This
* is called "Channel XOR Randomization" in the MCH documentation. The result
* is that the CPU is XORing in either bit 11 or bit 17 to bit 6 of its address
* decode.
*
* All of this bit 6 XORing has an effect on our memory management,
* as we need to make sure that the 3d driver can correctly address object
* contents.
*
* If we don't have interleaved memory, all tiling is safe and no swizzling is
* required.
*
* When bit 17 is XORed in, we simply refuse to tile at all. Bit
* 17 is not just a page offset, so as we page an objet out and back in,
* individual pages in it will have different bit 17 addresses, resulting in
* each 64 bytes being swapped with its neighbor!
*
* Otherwise, if interleaved, we have to tell the 3d driver what the address
* swizzling it needs to do is, since it's writing with the CPU to the pages
* (bit 6 and potentially bit 11 XORed in), and the GPU is reading from the
* pages (bit 6, 9, and 10 XORed in), resulting in a cumulative bit swizzling
* required by the CPU of XORing in bit 6, 9, 10, and potentially 11, in order
* to match what the GPU expects.
*/
#define MCHBAR_I915 0x44
#define MCHBAR_I965 0x48
#define MCHBAR_SIZE (4*4096)
#define DEVEN_REG 0x54
#define DEVEN_MCHBAR_EN (1 << 28)
/* Allocate space for the MCH regs if needed, return nonzero on error */
static int
intel_alloc_mchbar_resource(struct drm_device *dev)
{
struct pci_dev *bridge_dev;
drm_i915_private_t *dev_priv = dev->dev_private;
int reg = IS_I965G(dev) ? MCHBAR_I965 : MCHBAR_I915;
u32 temp_lo, temp_hi = 0;
u64 mchbar_addr;
int ret = 0;
bridge_dev = pci_get_bus_and_slot(0, PCI_DEVFN(0,0));
if (!bridge_dev) {
DRM_DEBUG("no bridge dev?!\n");
ret = -ENODEV;
goto out;
}
if (IS_I965G(dev))
pci_read_config_dword(bridge_dev, reg + 4, &temp_hi);
pci_read_config_dword(bridge_dev, reg, &temp_lo);
mchbar_addr = ((u64)temp_hi << 32) | temp_lo;
/* If ACPI doesn't have it, assume we need to allocate it ourselves */
#ifdef CONFIG_PNP
if (mchbar_addr &&
pnp_range_reserved(mchbar_addr, mchbar_addr + MCHBAR_SIZE)) {
ret = 0;
goto out_put;
}
#endif
/* Get some space for it */
ret = pci_bus_alloc_resource(bridge_dev->bus, &dev_priv->mch_res,
MCHBAR_SIZE, MCHBAR_SIZE,
PCIBIOS_MIN_MEM,
0, pcibios_align_resource,
bridge_dev);
if (ret) {
DRM_DEBUG("failed bus alloc: %d\n", ret);
dev_priv->mch_res.start = 0;
goto out_put;
}
if (IS_I965G(dev))
pci_write_config_dword(bridge_dev, reg + 4,
upper_32_bits(dev_priv->mch_res.start));
pci_write_config_dword(bridge_dev, reg,
lower_32_bits(dev_priv->mch_res.start));
out_put:
pci_dev_put(bridge_dev);
out:
return ret;
}
/* Setup MCHBAR if possible, return true if we should disable it again */
static bool
intel_setup_mchbar(struct drm_device *dev)
{
struct pci_dev *bridge_dev;
int mchbar_reg = IS_I965G(dev) ? MCHBAR_I965 : MCHBAR_I915;
u32 temp;
bool need_disable = false, enabled;
bridge_dev = pci_get_bus_and_slot(0, PCI_DEVFN(0,0));
if (!bridge_dev) {
DRM_DEBUG("no bridge dev?!\n");
goto out;
}
if (IS_I915G(dev) || IS_I915GM(dev)) {
pci_read_config_dword(bridge_dev, DEVEN_REG, &temp);
enabled = !!(temp & DEVEN_MCHBAR_EN);
} else {
pci_read_config_dword(bridge_dev, mchbar_reg, &temp);
enabled = temp & 1;
}
/* If it's already enabled, don't have to do anything */
if (enabled)
goto out_put;
if (intel_alloc_mchbar_resource(dev))
goto out_put;
need_disable = true;
/* Space is allocated or reserved, so enable it. */
if (IS_I915G(dev) || IS_I915GM(dev)) {
pci_write_config_dword(bridge_dev, DEVEN_REG,
temp | DEVEN_MCHBAR_EN);
} else {
pci_read_config_dword(bridge_dev, mchbar_reg, &temp);
pci_write_config_dword(bridge_dev, mchbar_reg, temp | 1);
}
out_put:
pci_dev_put(bridge_dev);
out:
return need_disable;
}
static void
intel_teardown_mchbar(struct drm_device *dev, bool disable)
{
drm_i915_private_t *dev_priv = dev->dev_private;
struct pci_dev *bridge_dev;
int mchbar_reg = IS_I965G(dev) ? MCHBAR_I965 : MCHBAR_I915;
u32 temp;
bridge_dev = pci_get_bus_and_slot(0, PCI_DEVFN(0,0));
if (!bridge_dev) {
DRM_DEBUG("no bridge dev?!\n");
return;
}
if (disable) {
if (IS_I915G(dev) || IS_I915GM(dev)) {
pci_read_config_dword(bridge_dev, DEVEN_REG, &temp);
temp &= ~DEVEN_MCHBAR_EN;
pci_write_config_dword(bridge_dev, DEVEN_REG, temp);
} else {
pci_read_config_dword(bridge_dev, mchbar_reg, &temp);
temp &= ~1;
pci_write_config_dword(bridge_dev, mchbar_reg, temp);
}
}
if (dev_priv->mch_res.start)
release_resource(&dev_priv->mch_res);
}
/**
* Detects bit 6 swizzling of address lookup between IGD access and CPU
* access through main memory.
*/
void
i915_gem_detect_bit_6_swizzle(struct drm_device *dev)
{
drm_i915_private_t *dev_priv = dev->dev_private;
uint32_t swizzle_x = I915_BIT_6_SWIZZLE_UNKNOWN;
uint32_t swizzle_y = I915_BIT_6_SWIZZLE_UNKNOWN;
bool need_disable;
if (!IS_I9XX(dev)) {
/* As far as we know, the 865 doesn't have these bit 6
* swizzling issues.
*/
swizzle_x = I915_BIT_6_SWIZZLE_NONE;
swizzle_y = I915_BIT_6_SWIZZLE_NONE;
} else if (IS_MOBILE(dev)) {
uint32_t dcc;
/* Try to make sure MCHBAR is enabled before poking at it */
need_disable = intel_setup_mchbar(dev);
/* On mobile 9xx chipsets, channel interleave by the CPU is
* determined by DCC. For single-channel, neither the CPU
* nor the GPU do swizzling. For dual channel interleaved,
* the GPU's interleave is bit 9 and 10 for X tiled, and bit
* 9 for Y tiled. The CPU's interleave is independent, and
* can be based on either bit 11 (haven't seen this yet) or
* bit 17 (common).
*/
dcc = I915_READ(DCC);
switch (dcc
|