summaryrefslogtreecommitdiffstats
path: root/src/mesa/drivers/dri/intel/intel_span.c
blob: 0ea8576a027af930a327d4c792c4bb843050c82e (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
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
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
/**************************************************************************
 * 
 * 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.
 * 
 **************************************************************************/

#include "glheader.h"
#include "macros.h"
#include "mtypes.h"
#include "colormac.h"

#include "intel_fbo.h"
#include "intel_screen.h"
#include "intel_span.h"
#include "intel_regions.h"
#include "intel_tex.h"

#include "swrast/swrast.h"

static void
intel_set_span_functions(struct intel_context *intel,
			 struct gl_renderbuffer *rb);

#define SPAN_CACHE_SIZE		4096

static void
get_span_cache(struct intel_renderbuffer *irb, uint32_t offset)
{
   if (irb->span_cache == NULL) {
      irb->span_cache = _mesa_malloc(SPAN_CACHE_SIZE);
      irb->span_cache_offset = -1;
   }

   if ((offset & ~(SPAN_CACHE_SIZE - 1)) != irb->span_cache_offset) {
      irb->span_cache_offset = offset & ~(SPAN_CACHE_SIZE - 1);
      dri_bo_get_subdata(irb->region->buffer, irb->span_cache_offset,
			 SPAN_CACHE_SIZE, irb->span_cache);
   }
}

static void
clear_span_cache(struct intel_renderbuffer *irb)
{
   irb->span_cache_offset = -1;
}

static uint32_t
pread_32(struct intel_renderbuffer *irb, uint32_t offset)
{
   get_span_cache(irb, offset);

   return *(uint32_t *)(irb->span_cache + (offset & (SPAN_CACHE_SIZE - 1)));
}

static uint32_t
pread_xrgb8888(struct intel_renderbuffer *irb, uint32_t offset)
{
   get_span_cache(irb, offset);

   return *(uint32_t *)(irb->span_cache + (offset & (SPAN_CACHE_SIZE - 1))) |
      0xff000000;
}

static uint16_t
pread_16(struct intel_renderbuffer *irb, uint32_t offset)
{
   get_span_cache(irb, offset);

   return *(uint16_t *)(irb->span_cache + (offset & (SPAN_CACHE_SIZE - 1)));
}

static uint8_t
pread_8(struct intel_renderbuffer *irb, uint32_t offset)
{
   get_span_cache(irb, offset);

   return *(uint8_t *)(irb->span_cache + (offset & (SPAN_CACHE_SIZE - 1)));
}

static void
pwrite_32(struct intel_renderbuffer *irb, uint32_t offset, uint32_t val)
{
   clear_span_cache(irb);

   dri_bo_subdata(irb->region->buffer, offset, 4, &val);
}

static void
pwrite_xrgb8888(struct intel_renderbuffer *irb, uint32_t offset, uint32_t val)
{
   clear_span_cache(irb);

   dri_bo_subdata(irb->region->buffer, offset, 3, &val);
}

static void
pwrite_16(struct intel_renderbuffer *irb, uint32_t offset, uint16_t val)
{
   clear_span_cache(irb);

   dri_bo_subdata(irb->region->buffer, offset, 2, &val);
}

static void
pwrite_8(struct intel_renderbuffer *irb, uint32_t offset, uint8_t val)
{
   clear_span_cache(irb);

   dri_bo_subdata(irb->region->buffer, offset, 1, &val);
}

static uint32_t no_tile_swizzle(struct intel_renderbuffer *irb,
				struct intel_context *intel,
				int x, int y)
{
	x += intel->drawX;
	y += intel->drawY;

	return (y * irb->region->pitch + x) * irb->region->cpp;
}

/*
 * Deal with tiled surfaces
 */

static uint32_t x_tile_swizzle(struct intel_renderbuffer *irb,
			       struct intel_context *intel,
			       int x, int y)
{
	int	tile_stride;
	int	xbyte;
	int	x_tile_off, y_tile_off;
	int	x_tile_number, y_tile_number;
	int	tile_off, tile_base;
	
	tile_stride = (irb->pfPitch * irb->region->cpp) << 3;
	
	x += intel->drawX;
	y += intel->drawY;

	xbyte = x * irb->region->cpp;

	x_tile_off = xbyte & 0x1ff;
	y_tile_off = y & 7;

	x_tile_number = xbyte >> 9;
	y_tile_number = y >> 3;

	tile_off = (y_tile_off << 9) + x_tile_off;

	switch (irb->region->bit_6_swizzle) {
	case I915_BIT_6_SWIZZLE_NONE:
	   break;
	case I915_BIT_6_SWIZZLE_9:
	   tile_off ^= ((tile_off >> 3) & 64);
	   break;
	case I915_BIT_6_SWIZZLE_9_10:
	   tile_off ^= ((tile_off >> 3) & 64) ^ ((tile_off >> 4) & 64);
	   break;
	case I915_BIT_6_SWIZZLE_9_11:
	   tile_off ^= ((tile_off >> 3) & 64) ^ ((tile_off >> 5) & 64);
	   break;
	case I915_BIT_6_SWIZZLE_9_10_11:
	   tile_off ^= ((tile_off >> 3) & 64) ^ ((tile_off >> 4) & 64) ^
	      ((tile_off >> 5) & 64);
	   break;
	default:
	   fprintf(stderr, "Unknown tile swizzling mode %d\n",
		   irb->region->bit_6_swizzle);
	   exit(1);
	}

	tile_base = (x_tile_number << 12) + y_tile_number * tile_stride;

#if 0
	printf("(%d,%d) -> %d + %d = %d (pitch = %d, tstride = %d)\n",
	       x, y, tile_off, tile_base,
	       tile_off + tile_base,
	       irb->pfPitch, tile_stride);
#endif

	return tile_base + tile_off;
}

static uint32_t y_tile_swizzle(struct intel_renderbuffer *irb,
			       struct intel_context *intel,
			       int x, int y)
{
	int	tile_stride;
	int	xbyte;
	int	x_tile_off, y_tile_off;
	int	x_tile_number, y_tile_number;
	int	tile_off, tile_base;
	
	tile_stride = (irb->pfPitch * irb->region->cpp) << 5;
	
	x += intel->drawX;
	y += intel->drawY;

	xbyte = x * irb->region->cpp;

	x_tile_off = xbyte & 0x7f;
	y_tile_off = y & 0x1f;

	x_tile_number = xbyte >> 7;
	y_tile_number = y >> 5;

	tile_off = ((x_tile_off & ~0xf) << 5) + (y_tile_off << 4) +
	   (x_tile_off & 0xf);

	switch (irb->region->bit_6_swizzle) {
	case I915_BIT_6_SWIZZLE_NONE:
	   break;
	case I915_BIT_6_SWIZZLE_9:
	   tile_off ^= ((tile_off >> 3) & 64);
	   break;
	case I915_BIT_6_SWIZZLE_9_10:
	   tile_off ^= ((tile_off >> 3) & 64) ^ ((tile_off >> 4) & 64);
	   break;
	case I915_BIT_6_SWIZZLE_9_11:
	   tile_off ^= ((tile_off >> 3) & 64) ^ ((tile_off >> 5) & 64);
	   break;
	case I915_BIT_6_SWIZZLE_9_10_11:
	   tile_off ^= ((tile_off >> 3) & 64) ^ ((tile_off >> 4) & 64) ^
	      ((tile_off >> 5) & 64);
	   break;
	default:
	   fprintf(stderr, "Unknown tile swizzling mode %d\n",
		   irb->region->bit_6_swizzle);
	   exit(1);
	}

	tile_base = (x_tile_number << 12) + y_tile_number * tile_stride;

	return tile_base + tile_off;
}

/*
  break intelWriteRGBASpan_ARGB8888
*/

#undef DBG
#define DBG 0

#define LOCAL_VARS							\
   struct intel_context *intel = intel_context(ctx);			\
   struct intel_renderbuffer *irb = intel_renderbuffer(rb);		\
   const GLint yScale = irb->RenderToTexture ? 1 : -1;			\
   const GLint yBias = irb->RenderToTexture ? 0 : irb->Base.Height - 1;	\
   GLuint p;								\
   (void) p;

/* XXX FBO: this is identical to the macro in spantmp2.h except we get
 * the cliprect info from the context, not the driDrawable.
 * Move this into spantmp2.h someday.
 */
#define HW_CLIPLOOP()							\
   do {									\
      int _nc = intel->numClipRects;					\
      while ( _nc-- ) {							\
	 int minx = intel->pClipRects[_nc].x1 - intel->drawX;		\
	 int miny = intel->pClipRects[_nc].y1 - intel->drawY;		\
	 int maxx = intel->pClipRects[_nc].x2 - intel->drawX;		\
	 int maxy = intel->pClipRects[_nc].y2 - intel->drawY;
	
#if 0
      }}
#endif

#define Y_FLIP(_y) ((_y) * yScale + yBias)

/* XXX with GEM, these need to tell the kernel */
#define HW_LOCK()

#define HW_UNLOCK()

/* 16 bit, RGB565 color spanline and pixel functions
 */
#define SPANTMP_PIXEL_FMT GL_RGB
#define SPANTMP_PIXEL_TYPE GL_UNSIGNED_SHORT_5_6_5

#define TAG(x)    intel##x##_RGB565
#define TAG2(x,y) intel##x##_RGB565##y
#define GET_VALUE(X, Y) pread_16(irb, no_tile_swizzle(irb, intel, X, Y))
#define PUT_VALUE(X, Y, V) pwrite_16(irb, no_tile_swizzle(irb, intel, X, Y), V)
#include "spantmp2.h"

/* 32 bit, ARGB8888 color spanline and pixel functions
 */
#define SPANTMP_PIXEL_FMT GL_BGRA
#define SPANTMP_PIXEL_TYPE GL_UNSIGNED_INT_8_8_8_8_REV

#define TAG(x)    intel##x##_ARGB8888
#define TAG2(x,y) intel##x##_ARGB8888##y
#define GET_VALUE(X, Y) pread_32(irb, no_tile_swizzle(irb, intel, X, Y))
#define PUT_VALUE(X, Y, V) pwrite_32(irb, no_tile_swizzle(irb, intel, X, Y), V)
#include "spantmp2.h"

/* 32 bit, xRGB8888 color spanline and pixel functions
 */
#define SPANTMP_PIXEL_FMT GL_BGRA
#define SPANTMP_PIXEL_TYPE GL_UNSIGNED_INT_8_8_8_8_REV

#define TAG(x)    intel##x##_xRGB8888
#define TAG2(x,y) intel##x##_xRGB8888##y
#define GET_VALUE(X, Y) pread_xrgb8888(irb, no_tile_swizzle(irb, intel, X, Y))
#define PUT_VALUE(X, Y, V) pwrite_xrgb8888(irb, no_tile_swizzle(irb, intel, X, Y), V)
#include "spantmp2.h"

/* 16 bit RGB565 color tile spanline and pixel functions
 */

#define SPANTMP_PIXEL_FMT GL_RGB
#define SPANTMP_PIXEL_TYPE GL_UNSIGNED_SHORT_5_6_5

#define TAG(x)    intel_XTile_##x##_RGB565
#define TAG2(x,y) intel_XTile_##x##_RGB565##y
#define GET_VALUE(X, Y) pread_16(irb, x_tile_swizzle(irb, intel, X, Y))
#define PUT_VALUE(X, Y, V) pwrite_16(irb, x_tile_swizzle(irb, intel, X, Y), V)
#include "spantmp2.h"

#define SPANTMP_PIXEL_FMT GL_RGB
#define SPANTMP_PIXEL_TYPE GL_UNSIGNED_SHORT_5_6_5

#define TAG(x)    intel_YTile_##x##_RGB565
#define TAG2(x,y) intel_YTile_##x##_RGB565##y
#define GET_VALUE(X, Y) pread_16(irb, y_tile_swizzle(irb, intel, X, Y))
#define PUT_VALUE(X, Y, V) pwrite_16(irb, y_tile_swizzle(irb, intel, X, Y), V)
#include "spantmp2.h"

/* 32 bit ARGB888 color tile spanline and pixel functions
 */

#define SPANTMP_PIXEL_FMT GL_BGRA
#define SPANTMP_PIXEL_TYPE GL_UNSIGNED_INT_8_8_8_8_REV

#define TAG(x)    intel_XTile_##x##_ARGB8888
#define TAG2(x,y) intel_XTile_##x##_ARGB8888##y
#define GET_VALUE(X, Y) pread_32(irb, x_tile_swizzle(irb, intel, X, Y))
#define PUT_VALUE(X, Y, V) pwrite_32(irb, x_tile_swizzle(irb, intel, X, Y), V)
#include "spantmp2.h"

#define SPANTMP_PIXEL_FMT GL_BGRA
#define SPANTMP_PIXEL_TYPE GL_UNSIGNED_INT_8_8_8_8_REV

#define TAG(x)    intel_YTile_##x##_ARGB8888
#define TAG2(x,y) intel_YTile_##x##_ARGB8888##y
#define GET_VALUE(X, Y) pread_32(irb, y_tile_swizzle(irb, intel, X, Y))
#define PUT_VALUE(X, Y, V) pwrite_32(irb, y_tile_swizzle(irb, intel, X, Y), V)
#include "spantmp2.h"

/* 32 bit xRGB888 color tile spanline and pixel functions
 */

#define SPANTMP_PIXEL_FMT GL_BGRA
#define SPANTMP_PIXEL_TYPE GL_UNSIGNED_INT_8_8_8_8_REV

#define TAG(x)    intel_XTile_##x##_xRGB8888
#define TAG2(x,y) intel_XTile_##x##_xRGB8888##y
#define GET_VALUE(X, Y) pread_xrgb8888(irb, x_tile_swizzle(irb, intel, X, Y))
#define PUT_VALUE(X, Y, V) pwrite_xrgb8888(irb, x_tile_swizzle(irb, intel, X, Y), V)
#include "spantmp2.h"

#define SPANTMP_PIXEL_FMT GL_BGRA
#define SPANTMP_PIXEL_TYPE GL_UNSIGNED_INT_8_8_8_8_REV

#define TAG(x)    intel_YTile_##x##_xRGB8888
#define TAG2(x,y) intel_YTile_##x##_xRGB8888##y
#define GET_VALUE(X, Y) pread_xrgb8888(irb, y_tile_swizzle(irb, intel, X, Y))
#define PUT_VALUE(X, Y, V) pwrite_xrgb8888(irb, y_tile_swizzle(irb, intel, X, Y), V)
#include "spantmp2.h"

#define LOCAL_DEPTH_VARS						\
   struct intel_context *intel = intel_context(ctx);			\
   struct intel_renderbuffer *irb = intel_renderbuffer(rb);		\
   const GLint yScale = irb->RenderToTexture ? 1 : -1;			\
   const GLint yBias = irb->RenderToTexture ? 0 : irb->Base.Height - 1;


#define LOCAL_STENCIL_VARS LOCAL_DEPTH_VARS

/**
 ** 16-bit depthbuffer functions.
 **/
#define VALUE_TYPE GLushort
#define WRITE_DEPTH(_x, _y, d) \
   pwrite_16(irb, no_tile_swizzle(irb, intel, _x, _y), d)
#define READ_DEPTH(d, _x, _y) \
   d = pread_16(irb, no_tile_swizzle(irb, intel, _x, _y))
#define TAG(x) intel##x##_z16
#include "depthtmp.h"


/**
 ** 16-bit x tile depthbuffer functions.
 **/
#define VALUE_TYPE GLushort
#define WRITE_DEPTH(_x, _y, d) \
   pwrite_16(irb, x_tile_swizzle(irb, intel, _x, _y), d)
#define READ_DEPTH(d, _x, _y) \
   d = pread_16(irb, x_tile_swizzle(irb, intel, _x, _y))
#define TAG(x) intel_XTile_##x##_z16
#include "depthtmp.h"

/**
 ** 16-bit y tile depthbuffer functions.
 **/
#define VALUE_TYPE GLushort
#define WRITE_DEPTH(_x, _y, d) \
   pwrite_16(irb, y_tile_swizzle(irb, intel, _x, _y), d)
#define READ_DEPTH(d, _x, _y) \
   d = pread_16(irb, y_tile_swizzle(irb, intel, _x, _y))
#define TAG(x) intel_YTile_##x##_z16
#include "depthtmp.h"


/**
 ** 24/8-bit interleaved depth/stencil functions
 ** Note: we're actually reading back combined depth+stencil values.
 ** The wrappers in main/depthstencil.c are used to extract the depth
 ** and stencil values.
 **/
#define VALUE_TYPE GLuint

/* Change ZZZS -> SZZZ */
#define WRITE_DEPTH(_x, _y, d)					\
   pwrite_32(irb, no_tile_swizzle(irb, intel, _x, _y),		\
	     ((d) >> 8) | ((d) << 24))

/* Change SZZZ -> ZZZS */
#define READ_DEPTH( d, _x, _y ) {				\
   GLuint tmp = pread_32(irb, no_tile_swizzle(irb, intel, _x, _y));	\
   d = (tmp << 8) | (tmp >> 24);				\
}

#define TAG(x) intel##x##_z24_s8
#include "depthtmp.h"


/**
 ** 24/8-bit x-tile interleaved depth/stencil functions
 ** Note: we're actually reading back combined depth+stencil values.
 ** The wrappers in main/depthstencil.c are used to extract the depth
 ** and stencil values.
 **/
#define VALUE_TYPE GLuint

/* Change ZZZS -> SZZZ */
#define WRITE_DEPTH(_x, _y, d)					\
   pwrite_32(irb, x_tile_swizzle(irb, intel, _x, _y),		\
	     ((d) >> 8) | ((d) << 24))				\

/* Change SZZZ -> ZZZS */
#define READ_DEPTH( d, _x, _y ) {				\
   GLuint tmp = pread_32(irb, x_tile_swizzle(irb, intel, _x, _y));	\
   d = (tmp << 8) | (tmp >> 24);				\
}

#define TAG(x) intel_XTile_##x##_z24_s8
#include "depthtmp.h"

/**
 ** 24/8-bit y-tile interleaved depth/stencil functions
 ** Note: we're actually reading back combined depth+stencil values.
 ** The wrappers in main/depthstencil.c are used to extract the depth
 ** and stencil values.
 **/
#define VALUE_TYPE GLuint

/* Change ZZZS -> SZZZ */
#define WRITE_DEPTH(_x, _y, d)					\
   pwrite_32(irb, y_tile_swizzle(irb, intel, _x, _y),		\
	     ((d) >> 8) | ((d) << 24))

/* Change SZZZ -> ZZZS */
#define READ_DEPTH( d, _x, _y ) {				\
   GLuint tmp = pread_32(irb, y_tile_swizzle(irb, intel, _x, _y));	\
   d = (tmp << 8) | (tmp >> 24);				\
}

#define TAG(x) intel_YTile_##x##_z24_s8
#include "depthtmp.h"


/**
 ** 8-bit stencil function (XXX FBO: This is obsolete)
 **/
#define WRITE_STENCIL(_x, _y, d)				\
   pwrite_8(irb, no_tile_swizzle(irb, intel, _x, _y) + 3, d)

#define READ_STENCIL(d, _x, _y)					\
   d = pread_8(irb, no_tile_swizzle(irb, intel, _x, _y) + 3);

#define TAG(x) intel##x##_z24_s8
#include "stenciltmp.h"

/**
 ** 8-bit x-tile stencil function (XXX FBO: This is obsolete)
 **/
#define WRITE_STENCIL(_x, _y, d)				\
   pwrite_8(irb, x_tile_swizzle(irb, intel, _x, _y) + 3, d)

#define READ_STENCIL(d, _x, _y)					\
   d = pread_8(irb, x_tile_swizzle(irb, intel, _x, _y) + 3);

#define TAG(x) intel_XTile_##x##_z24_s8
#include "stenciltmp.h"

/**
 ** 8-bit y-tile stencil function (XXX FBO: This is obsolete)
 **/
#define WRITE_STENCIL(_x, _y, d)				\
   pwrite_8(irb, y_tile_swizzle(irb, intel, _x, _y) + 3, d)

#define READ_STENCIL(d, _x, _y)					\
   d = pread_8(irb, y_tile_swizzle(irb, intel, _x, _y) + 3)

#define TAG(x) intel_YTile_##x##_z24_s8
#include "stenciltmp.h"

void
intel_renderbuffer_map(struct intel_context *intel, struct gl_renderbuffer *rb)
{
   struct intel_renderbuffer *irb = intel_renderbuffer(rb);

   if (irb == NULL || irb->region == NULL)
      return;

   irb->pfPitch = irb->region->pitch;

   intel_set_span_functions(intel, rb);
}

void
intel_renderbuffer_unmap(struct intel_context *intel,
			 struct gl_renderbuffer *rb)
{
   struct intel_renderbuffer *irb = intel_renderbuffer(rb);

   if (irb == NULL || irb->region == NULL)
      return;

   clear_span_cache(irb);
   irb->pfPitch = 0;

   rb->GetRow = NULL;
   rb->PutRow = NULL;
}

/**
 * Map or unmap all the renderbuffers which we may need during
 * software rendering.
 * XXX in the future, we could probably convey extra information to
 * reduce the number of mappings needed.  I.e. if doing a glReadPixels
 * from the depth buffer, we really only need one mapping.
 *
 * XXX Rewrite this function someday.
 * We can probably just loop over all the renderbuffer attachments,
 * map/unmap all of them, and not worry about the _ColorDrawBuffers
 * _ColorReadBuffer, _DepthBuffer or _StencilBuffer fields.
 */
static void
intel_map_unmap_buffers(struct intel_context *intel, GLboolean map)
{
   GLcontext *ctx = &intel->ctx;
   GLuint i, j;

   /* color draw buffers */
   for (j = 0; j < ctx->DrawBuffer->_NumColorDrawBuffers; j++) {
      if (map)
	 intel_renderbuffer_map(intel, ctx->DrawBuffer->_ColorDrawBuffers[j]);
      else
	 intel_renderbuffer_unmap(intel, ctx->DrawBuffer->_ColorDrawBuffers[j]);
   }

   /* check for render to textures */
   for (i = 0; i < BUFFER_COUNT; i++) {
      struct gl_renderbuffer_attachment *att =
         ctx->DrawBuffer->Attachment + i;
      struct gl_texture_object *tex = att->Texture;
      if (tex) {
         /* render to texture */
         ASSERT(att->Renderbuffer);
         if (map) {
            struct gl_texture_image *texImg;
            texImg = tex->Image[att->CubeMapFace][att->TextureLevel];
            intel_tex_map_images(intel, intel_texture_object(tex));
         }
         else {
            intel_tex_unmap_images(intel, intel_texture_object(tex));
         }
      }
   }

   /* color read buffers */
   if (map)
      intel_renderbuffer_map(intel, ctx->ReadBuffer->_ColorReadBuffer);
   else
      intel_renderbuffer_unmap(intel, ctx->ReadBuffer->_ColorReadBuffer);

   /* depth buffer (Note wrapper!) */
   if (ctx->DrawBuffer->_DepthBuffer) {
      if (map)
	 intel_renderbuffer_map(intel, ctx->DrawBuffer->_DepthBuffer->Wrapped);
      else
	 intel_renderbuffer_unmap(intel,
				  ctx->DrawBuffer->_DepthBuffer->Wrapped);
   }

   /* stencil buffer (Note wrapper!) */
   if (ctx->DrawBuffer->_StencilBuffer) {
      if (map)
	 intel_renderbuffer_map(intel,
				ctx->DrawBuffer->_StencilBuffer->Wrapped);
      else
	 intel_renderbuffer_unmap(intel,
				  ctx->DrawBuffer->_StencilBuffer->Wrapped);
   }
}



/**
 * Prepare for softare rendering.  Map current read/draw framebuffers'
 * renderbuffes and all currently bound texture objects.
 *
 * Old note: Moved locking out to get reasonable span performance.
 */
void
intelSpanRenderStart(GLcontext * ctx)
{
   struct intel_context *intel = intel_context(ctx);
   GLuint i;

   intelFlush(&intel->ctx);
   LOCK_HARDWARE(intel);

   for (i = 0; i < ctx->Const.MaxTextureCoordUnits; i++) {
      if (ctx->Texture.Unit[i]._ReallyEnabled) {
         struct gl_texture_object *texObj = ctx->Texture.Unit[i]._Current;
         intel_tex_map_images(intel, intel_texture_object(texObj));
      }
   }

   intel_map_unmap_buffers(intel, GL_TRUE);
}

/**
 * Called when done softare rendering.  Unmap the buffers we mapped in
 * the above function.
 */
void
intelSpanRenderFinish(GLcontext * ctx)
{
   struct intel_context *intel = intel_context(ctx);
   GLuint i;

   _swrast_flush(ctx);

   for (i = 0; i < ctx->Const.MaxTextureCoordUnits; i++) {
      if (ctx->Texture.Unit[i]._ReallyEnabled) {
         struct gl_texture_object *texObj = ctx->Texture.Unit[i]._Current;
         intel_tex_unmap_images(intel, intel_texture_object(texObj));
      }
   }

   intel_map_unmap_buffers(intel, GL_FALSE);

   UNLOCK_HARDWARE(intel);
}


void
intelInitSpanFuncs(GLcontext * ctx)
{
   struct swrast_device_driver *swdd = _swrast_GetDeviceDriverReference(ctx);
   swdd->SpanRenderStart = intelSpanRenderStart;
   swdd->SpanRenderFinish = intelSpanRenderFinish;
}


/**
 * Plug in appropriate span read/write functions for the given renderbuffer.
 * These are used for the software fallbacks.
 */
static void
intel_set_span_functions(struct intel_context *intel,
			 struct gl_renderbuffer *rb)
{
   struct intel_renderbuffer *irb = (struct intel_renderbuffer *) rb;
   uint32_t tiling;

   /* If in GEM mode, we need to do the tile address swizzling ourselves,
    * instead of the fence registers handling it.
    */
   if (intel->ttm)
      tiling = irb->region->tiling;
   else
      tiling = I915_TILING_NONE;

   if (rb->_ActualFormat == GL_RGB5) {
      /* 565 RGB */
      switch (tiling) {
      case I915_TILING_NONE:
      default:
	 intelInitPointers_RGB565(rb);
	 break;
      case I915_TILING_X:
	 intel_XTile_InitPointers_RGB565(rb);
	 break;
      case I915_TILING_Y:
	 intel_YTile_InitPointers_RGB565(rb);
	 break;
      }
   }
   else if (rb->_ActualFormat == GL_RGB8) {
      /* 8888 RGBx */
      switch (tiling) {
      case I915_TILING_NONE:
      default:
	 intelInitPointers_xRGB8888(rb);
	 break;
      case I915_TILING_X:
	 intel_XTile_InitPointers_xRGB8888(rb);
	 break;
      case I915_TILING_Y:
	 intel_YTile_InitPointers_xRGB8888(rb);
	 break;
      }
   }
   else if (rb->_ActualFormat == GL_RGBA8) {
      /* 8888 RGBA */
      switch (tiling) {
      case I915_TILING_NONE:
      default:
	 intelInitPointers_ARGB8888(rb);
	 break;
      case I915_TILING_X:
	 intel_XTile_InitPointers_ARGB8888(rb);
	 break;
      case I915_TILING_Y:
	 intel_YTile_InitPointers_ARGB8888(rb);
	 break;
      }
   }
   else if (rb->_ActualFormat == GL_DEPTH_COMPONENT16) {
      switch (tiling) {
      case I915_TILING_NONE:
      default:
	 intelInitDepthPointers_z16(rb);
	 break;
      case I915_TILING_X:
	 intel_XTile_InitDepthPointers_z16(rb);
	 break;
      case I915_TILING_Y:
	 intel_YTile_InitDepthPointers_z16(rb);
	 break;
      }
   }
   else if (rb->_ActualFormat == GL_DEPTH_COMPONENT24 ||        /* XXX FBO remove */
            rb->_ActualFormat == GL_DEPTH24_STENCIL8_EXT) {
      switch (tiling) {
      case I915_TILING_NONE:
      default:
	 intelInitDepthPointers_z24_s8(rb);
	 break;
      case I915_TILING_X:
	 intel_XTile_InitDepthPointers_z24_s8(rb);
	 break;
      case I915_TILING_Y:
	 intel_YTile_InitDepthPointers_z24_s8(rb);
	 break;
      }
   }
   else if (rb->_ActualFormat == GL_STENCIL_INDEX8_EXT) {
      switch (tiling) {
      case I915_TILING_NONE:
      default:
	 intelInitStencilPointers_z24_s8(rb);
	 break;
      case I915_TILING_X:
	 intel_XTile_InitStencilPointers_z24_s8(rb);
	 break;
      case I915_TILING_Y:
	 intel_YTile_InitStencilPointers_z24_s8(rb);
	 break;
      }
   }
   else {
      _mesa_problem(NULL,
                    "Unexpected _ActualFormat in intelSetSpanFunctions");
   }
}