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
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
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
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
1045
1046
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
1074
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
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
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
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
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
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
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
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
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
1483
1484
1485
1486
1487
1488
1489
1490
1491
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
1519
1520
1521
1522
1523
1524
1525
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
1584
1585
1586
1587
1588
1589
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
|
/**************************************************************************
*
* Copyright 2007 VMware, Inc.
* 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 VMWARE 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.
*
**************************************************************************/
/*
* Authors:
* Brian Paul
*/
#include "main/imports.h"
#include "main/image.h"
#include "main/bufferobj.h"
#include "main/blit.h"
#include "main/format_pack.h"
#include "main/framebuffer.h"
#include "main/macros.h"
#include "main/mtypes.h"
#include "main/pack.h"
#include "main/pbo.h"
#include "main/readpix.h"
#include "main/texformat.h"
#include "main/teximage.h"
#include "main/texstore.h"
#include "main/glformats.h"
#include "program/program.h"
#include "program/prog_print.h"
#include "program/prog_instruction.h"
#include "st_atom.h"
#include "st_atom_constbuf.h"
#include "st_cb_bitmap.h"
#include "st_cb_drawpixels.h"
#include "st_cb_readpixels.h"
#include "st_cb_fbo.h"
#include "st_context.h"
#include "st_debug.h"
#include "st_draw.h"
#include "st_format.h"
#include "st_program.h"
#include "st_scissor.h"
#include "st_texture.h"
#include "pipe/p_context.h"
#include "pipe/p_defines.h"
#include "tgsi/tgsi_ureg.h"
#include "util/u_format.h"
#include "util/u_inlines.h"
#include "util/u_math.h"
#include "util/u_tile.h"
#include "cso_cache/cso_context.h"
/**
* We have a simple glDrawPixels cache to try to optimize the case where the
* same image is drawn over and over again. It basically works as follows:
*
* 1. After we construct a texture map with the image and draw it, we do
* not discard the texture. We keep it around, plus we note the
* glDrawPixels width, height, format, etc. parameters and keep a copy
* of the image in a malloc'd buffer.
*
* 2. On the next glDrawPixels we check if the parameters match the previous
* call. If those match, we check if the image matches the previous image
* via a memcmp() call. If everything matches, we re-use the previous
* texture, thereby avoiding the cost creating a new texture and copying
* the image to it.
*
* The effectiveness of this cache depends upon:
* 1. If the memcmp() finds a difference, it happens relatively quickly.
Hopefully, not just the last pixels differ!
* 2. If the memcmp() finds no difference, doing that check is faster than
* creating and loading a texture.
*
* Notes:
* 1. We don't support any pixel unpacking parameters.
* 2. We don't try to cache images in Pixel Buffer Objects.
* 3. Instead of saving the whole image, perhaps some sort of reliable
* checksum function could be used instead.
*/
#define USE_DRAWPIXELS_CACHE 1
/**
* Create fragment program that does a TEX() instruction to get a Z and/or
* stencil value value, then writes to FRAG_RESULT_DEPTH/FRAG_RESULT_STENCIL.
* Used for glDrawPixels(GL_DEPTH_COMPONENT / GL_STENCIL_INDEX).
* Pass fragment color through as-is.
*
* \return CSO of the fragment shader.
*/
static void *
get_drawpix_z_stencil_program(struct st_context *st,
GLboolean write_depth,
GLboolean write_stencil)
{
struct ureg_program *ureg;
struct ureg_src depth_sampler, stencil_sampler;
struct ureg_src texcoord, color;
struct ureg_dst out_color, out_depth, out_stencil;
const GLuint shaderIndex = write_depth * 2 + write_stencil;
void *cso;
assert(shaderIndex < ARRAY_SIZE(st->drawpix.zs_shaders));
if (st->drawpix.zs_shaders[shaderIndex]) {
/* already have the proper shader */
return st->drawpix.zs_shaders[shaderIndex];
}
ureg = ureg_create(PIPE_SHADER_FRAGMENT);
if (ureg == NULL)
return NULL;
ureg_property(ureg, TGSI_PROPERTY_FS_COLOR0_WRITES_ALL_CBUFS, TRUE);
if (write_depth) {
color = ureg_DECL_fs_input(ureg, TGSI_SEMANTIC_COLOR, 0,
TGSI_INTERPOLATE_COLOR);
out_color = ureg_DECL_output(ureg, TGSI_SEMANTIC_COLOR, 0);
depth_sampler = ureg_DECL_sampler(ureg, 0);
ureg_DECL_sampler_view(ureg, 0, TGSI_TEXTURE_2D,
TGSI_RETURN_TYPE_FLOAT,
TGSI_RETURN_TYPE_FLOAT,
TGSI_RETURN_TYPE_FLOAT,
TGSI_RETURN_TYPE_FLOAT);
out_depth = ureg_DECL_output(ureg, TGSI_SEMANTIC_POSITION, 0);
}
if (write_stencil) {
stencil_sampler = ureg_DECL_sampler(ureg, 1);
ureg_DECL_sampler_view(ureg, 1, TGSI_TEXTURE_2D,
TGSI_RETURN_TYPE_UINT,
TGSI_RETURN_TYPE_UINT,
TGSI_RETURN_TYPE_UINT,
TGSI_RETURN_TYPE_UINT);
out_stencil = ureg_DECL_output(ureg, TGSI_SEMANTIC_STENCIL, 0);
}
texcoord = ureg_DECL_fs_input(ureg,
st->needs_texcoord_semantic ?
TGSI_SEMANTIC_TEXCOORD :
TGSI_SEMANTIC_GENERIC,
0, TGSI_INTERPOLATE_LINEAR);
if (write_depth) {
ureg_TEX(ureg, ureg_writemask(out_depth, TGSI_WRITEMASK_Z),
TGSI_TEXTURE_2D, texcoord, depth_sampler);
ureg_MOV(ureg, out_color, color);
}
if (write_stencil)
ureg_TEX(ureg, ureg_writemask(out_stencil, TGSI_WRITEMASK_Y),
TGSI_TEXTURE_2D, texcoord, stencil_sampler);
ureg_END(ureg);
cso = ureg_create_shader_and_destroy(ureg, st->pipe);
/* save the new shader */
st->drawpix.zs_shaders[shaderIndex] = cso;
return cso;
}
/**
* Create a simple vertex shader that just passes through the
* vertex position and texcoord (and optionally, color).
*/
static void *
make_passthrough_vertex_shader(struct st_context *st,
GLboolean passColor)
{
const unsigned texcoord_semantic = st->needs_texcoord_semantic ?
TGSI_SEMANTIC_TEXCOORD : TGSI_SEMANTIC_GENERIC;
if (!st->drawpix.vert_shaders[passColor]) {
struct ureg_program *ureg = ureg_create( PIPE_SHADER_VERTEX );
if (ureg == NULL)
return NULL;
/* MOV result.pos, vertex.pos; */
ureg_MOV(ureg,
ureg_DECL_output( ureg, TGSI_SEMANTIC_POSITION, 0 ),
ureg_DECL_vs_input( ureg, 0 ));
if (passColor) {
/* MOV result.color0, vertex.attr[1]; */
ureg_MOV(ureg,
ureg_DECL_output( ureg, TGSI_SEMANTIC_COLOR, 0 ),
ureg_DECL_vs_input( ureg, 1 ));
}
/* MOV result.texcoord0, vertex.attr[2]; */
ureg_MOV(ureg,
ureg_DECL_output( ureg, texcoord_semantic, 0 ),
ureg_DECL_vs_input( ureg, 2 ));
ureg_END( ureg );
st->drawpix.vert_shaders[passColor] =
ureg_create_shader_and_destroy( ureg, st->pipe );
}
return st->drawpix.vert_shaders[passColor];
}
/**
* Return a texture internalFormat for drawing/copying an image
* of the given format and type.
*/
static GLenum
internal_format(struct gl_context *ctx, GLenum format, GLenum type)
{
switch (format) {
case GL_DEPTH_COMPONENT:
switch (type) {
case GL_UNSIGNED_SHORT:
return GL_DEPTH_COMPONENT16;
case GL_UNSIGNED_INT:
return GL_DEPTH_COMPONENT32;
case GL_FLOAT:
if (ctx->Extensions.ARB_depth_buffer_float)
return GL_DEPTH_COMPONENT32F;
else
return GL_DEPTH_COMPONENT;
default:
return GL_DEPTH_COMPONENT;
}
case GL_DEPTH_STENCIL:
switch (type) {
case GL_FLOAT_32_UNSIGNED_INT_24_8_REV:
return GL_DEPTH32F_STENCIL8;
case GL_UNSIGNED_INT_24_8:
default:
return GL_DEPTH24_STENCIL8;
}
case GL_STENCIL_INDEX:
return GL_STENCIL_INDEX;
default:
if (_mesa_is_enum_format_integer(format)) {
switch (type) {
case GL_BYTE:
return GL_RGBA8I;
case GL_UNSIGNED_BYTE:
return GL_RGBA8UI;
case GL_SHORT:
return GL_RGBA16I;
case GL_UNSIGNED_SHORT:
return GL_RGBA16UI;
case GL_INT:
return GL_RGBA32I;
case GL_UNSIGNED_INT:
return GL_RGBA32UI;
default:
assert(0 && "Unexpected type in internal_format()");
return GL_RGBA_INTEGER;
}
}
else {
switch (type) {
case GL_UNSIGNED_BYTE:
case GL_UNSIGNED_INT_8_8_8_8:
case GL_UNSIGNED_INT_8_8_8_8_REV:
default:
return GL_RGBA8;
case GL_UNSIGNED_BYTE_3_3_2:
case GL_UNSIGNED_BYTE_2_3_3_REV:
return GL_R3_G3_B2;
case GL_UNSIGNED_SHORT_4_4_4_4:
case GL_UNSIGNED_SHORT_4_4_4_4_REV:
return GL_RGBA4;
case GL_UNSIGNED_SHORT_5_6_5:
case GL_UNSIGNED_SHORT_5_6_5_REV:
return GL_RGB565;
case GL_UNSIGNED_SHORT_5_5_5_1:
case GL_UNSIGNED_SHORT_1_5_5_5_REV:
return GL_RGB5_A1;
case GL_UNSIGNED_INT_10_10_10_2:
case GL_UNSIGNED_INT_2_10_10_10_REV:
return GL_RGB10_A2;
case GL_UNSIGNED_SHORT:
case GL_UNSIGNED_INT:
return GL_RGBA16;
case GL_BYTE:
return
ctx->Extensions.EXT_texture_snorm ? GL_RGBA8_SNORM : GL_RGBA8;
case GL_SHORT:
case GL_INT:
return
ctx->Extensions.EXT_texture_snorm ? GL_RGBA16_SNORM : GL_RGBA16;
case GL_HALF_FLOAT_ARB:
return
ctx->Extensions.ARB_texture_float ? GL_RGBA16F :
ctx->Extensions.EXT_texture_snorm ? GL_RGBA16_SNORM : GL_RGBA16;
case GL_FLOAT:
case GL_DOUBLE:
return
ctx->Extensions.ARB_texture_float ? GL_RGBA32F :
ctx->Extensions.EXT_texture_snorm ? GL_RGBA16_SNORM : GL_RGBA16;
case GL_UNSIGNED_INT_5_9_9_9_REV:
assert(ctx->Extensions.EXT_texture_shared_exponent);
return GL_RGB9_E5;
case GL_UNSIGNED_INT_10F_11F_11F_REV:
assert(ctx->Extensions.EXT_packed_float);
return GL_R11F_G11F_B10F;
}
}
}
}
/**
* Create a temporary texture to hold an image of the given size.
* If width, height are not POT and the driver only handles POT textures,
* allocate the next larger size of texture that is POT.
*/
static struct pipe_resource *
alloc_texture(struct st_context *st, GLsizei width, GLsizei height,
enum pipe_format texFormat, unsigned bind)
{
struct pipe_resource *pt;
pt = st_texture_create(st, st->internal_target, texFormat, 0,
width, height, 1, 1, 0, bind);
return pt;
}
/**
* Make texture containing an image for glDrawPixels image.
* If 'pixels' is NULL, leave the texture image data undefined.
*/
static struct pipe_resource *
make_texture(struct st_context *st,
GLsizei width, GLsizei height, GLenum format, GLenum type,
const struct gl_pixelstore_attrib *unpack,
const void *pixels)
{
struct gl_context *ctx = st->ctx;
struct pipe_context *pipe = st->pipe;
mesa_format mformat;
struct pipe_resource *pt = NULL;
enum pipe_format pipeFormat;
GLenum baseInternalFormat;
#if USE_DRAWPIXELS_CACHE
const GLint bpp = _mesa_bytes_per_pixel(format, type);
/* Check if the glDrawPixels() parameters and state matches the cache */
if (width == st->drawpix_cache.width &&
height == st->drawpix_cache.height &&
format == st->drawpix_cache.format &&
type == st->drawpix_cache.type &&
pixels == st->drawpix_cache.user_pointer &&
!_mesa_is_bufferobj(unpack->BufferObj) &&
(unpack->RowLength == 0 || unpack->RowLength == width) &&
unpack->SkipPixels == 0 &&
unpack->SkipRows == 0 &&
unpack->SwapBytes == GL_FALSE &&
st->drawpix_cache.image) {
assert(st->drawpix_cache.texture);
/* check if the pixel data is the same */
if (memcmp(pixels, st->drawpix_cache.image, width * height * bpp) == 0) {
/* OK, re-use the cached texture */
pipe_resource_reference(&pt, st->drawpix_cache.texture);
/* refcount of returned texture should be at least two here. One
* reference for the cache to hold on to, one for the caller (which
* it will release), and possibly more held by the driver.
*/
assert(pt->reference.count >= 2);
return pt;
}
}
/* discard the cached image and texture (if there is one) */
st->drawpix_cache.width = 0;
st->drawpix_cache.height = 0;
st->drawpix_cache.user_pointer = NULL;
if (st->drawpix_cache.image) {
free(st->drawpix_cache.image);
st->drawpix_cache.image = NULL;
}
pipe_resource_reference(&st->drawpix_cache.texture, NULL);
#endif
/* Choose a pixel format for the temp texture which will hold the
* image to draw.
*/
pipeFormat = st_choose_matching_format(st, PIPE_BIND_SAMPLER_VIEW,
format, type, unpack->SwapBytes);
if (pipeFormat == PIPE_FORMAT_NONE) {
/* Use the generic approach. */
GLenum intFormat = internal_format(ctx, format, type);
pipeFormat = st_choose_format(st, intFormat, format, type,
st->internal_target, 0,
PIPE_BIND_SAMPLER_VIEW, FALSE);
assert(pipeFormat != PIPE_FORMAT_NONE);
}
mformat = st_pipe_format_to_mesa_format(pipeFormat);
baseInternalFormat = _mesa_get_format_base_format(mformat);
pixels = _mesa_map_pbo_source(ctx, unpack, pixels);
if (!pixels)
return NULL;
/* alloc temporary texture */
pt = alloc_texture(st, width, height, pipeFormat, PIPE_BIND_SAMPLER_VIEW);
if (!pt) {
_mesa_unmap_pbo_source(ctx, unpack);
return NULL;
}
{
struct pipe_transfer *transfer;
GLboolean success;
GLubyte *dest;
const GLbitfield imageTransferStateSave = ctx->_ImageTransferState;
/* we'll do pixel transfer in a fragment shader */
ctx->_ImageTransferState = 0x0;
/* map texture transfer */
dest = pipe_transfer_map(pipe, pt, 0, 0,
PIPE_TRANSFER_WRITE, 0, 0,
width, height, &transfer);
/* Put image into texture transfer.
* Note that the image is actually going to be upside down in
* the texture. We deal with that with texcoords.
*/
if ((format == GL_RGBA || format == GL_BGRA)
&& type == GL_UNSIGNED_BYTE) {
/* Use a memcpy-based texstore to avoid software pixel swizzling.
* We'll do the necessary swizzling with the pipe_sampler_view to
* give much better performance.
* XXX in the future, expand this to accomodate more format and
* type combinations.
*/
_mesa_memcpy_texture(ctx, 2,
mformat, /* mesa_format */
transfer->stride, /* dstRowStride, bytes */
&dest, /* destSlices */
width, height, 1, /* size */
format, type, /* src format/type */
pixels, /* data source */
unpack);
success = GL_TRUE;
}
else {
success = _mesa_texstore(ctx, 2, /* dims */
baseInternalFormat, /* baseInternalFormat */
mformat, /* mesa_format */
transfer->stride, /* dstRowStride, bytes */
&dest, /* destSlices */
width, height, 1, /* size */
format, type, /* src format/type */
pixels, /* data source */
unpack);
}
/* unmap */
pipe_transfer_unmap(pipe, transfer);
assert(success);
/* restore */
ctx->_ImageTransferState = imageTransferStateSave;
}
_mesa_unmap_pbo_source(ctx, unpack);
#if USE_DRAWPIXELS_CACHE
/* Save the glDrawPixels parameter and image in the cache */
if ((unpack->RowLength == 0 || unpack->RowLength == width) &&
unpack->SkipPixels == 0 &&
unpack->SkipRows == 0) {
st->drawpix_cache.width = width;
st->drawpix_cache.height = height;
st->drawpix_cache.format = format;
st->drawpix_cache.type = type;
st->drawpix_cache.user_pointer = pixels;
assert(!st->drawpix_cache.image);
st->drawpix_cache.image = malloc(width * height * bpp);
if (st->drawpix_cache.image) {
memcpy(st->drawpix_cache.image, pixels, width * height * bpp);
pipe_resource_reference(&st->drawpix_cache.texture, pt);
}
else {
/* out of memory, free/disable cached texture */
st->drawpix_cache.width = 0;
st->drawpix_cache.height = 0;
pipe_resource_reference(&st->drawpix_cache.texture, NULL);
}
}
#endif
return pt;
}
static void
draw_textured_quad(struct gl_context *ctx, GLint x, GLint y, GLfloat z,
GLsizei width, GLsizei height,
GLfloat zoomX, GLfloat zoomY,
struct pipe_sampler_view **sv,
int num_sampler_view,
void *driver_vp,
void *driver_fp,
struct st_fp_variant *fpv,
const GLfloat *color,
GLboolean invertTex,
GLboolean write_depth, GLboolean write_stencil)
{
struct st_context *st = st_context(ctx);
struct pipe_context *pipe = st->pipe;
struct cso_context *cso = st->cso_context;
const unsigned fb_width = _mesa_geometric_width(ctx->DrawBuffer);
const unsigned fb_height = _mesa_geometric_height(ctx->DrawBuffer);
GLfloat x0, y0, x1, y1;
GLsizei maxSize;
boolean normalized = sv[0]->texture->target == PIPE_TEXTURE_2D;
unsigned cso_state_mask;
assert(sv[0]->texture->target == st->internal_target);
/* limit checks */
/* XXX if DrawPixels image is larger than max texture size, break
* it up into chunks.
*/
maxSize = 1 << (pipe->screen->get_param(pipe->screen,
PIPE_CAP_MAX_TEXTURE_2D_LEVELS) - 1);
assert(width <= maxSize);
assert(height <= maxSize);
cso_state_mask = (CSO_BIT_RASTERIZER |
CSO_BIT_VIEWPORT |
CSO_BIT_FRAGMENT_SAMPLERS |
CSO_BIT_FRAGMENT_SAMPLER_VIEWS |
CSO_BIT_STREAM_OUTPUTS |
CSO_BIT_VERTEX_ELEMENTS |
CSO_BIT_AUX_VERTEX_BUFFER_SLOT |
CSO_BITS_ALL_SHADERS);
if (write_stencil) {
cso_state_mask |= (CSO_BIT_DEPTH_STENCIL_ALPHA |
CSO_BIT_BLEND);
}
cso_save_state(cso, cso_state_mask);
/* rasterizer state: just scissor */
{
struct pipe_rasterizer_state rasterizer;
memset(&rasterizer, 0, sizeof(rasterizer));
rasterizer.clamp_fragment_color = !st->clamp_frag_color_in_shader &&
ctx->Color._ClampFragmentColor;
rasterizer.half_pixel_center = 1;
rasterizer.bottom_edge_rule = 1;
rasterizer.depth_clip = !ctx->Transform.DepthClamp;
rasterizer.scissor = ctx->Scissor.EnableFlags;
cso_set_rasterizer(cso, &rasterizer);
}
if (write_stencil) {
/* Stencil writing bypasses the normal fragment pipeline to
* disable color writing and set stencil test to always pass.
*/
struct pipe_depth_stencil_alpha_state dsa;
struct pipe_blend_state blend;
/* depth/stencil */
memset(&dsa, 0, sizeof(dsa));
dsa.stencil[0].enabled = 1;
dsa.stencil[0].func = PIPE_FUNC_ALWAYS;
dsa.stencil[0].writemask = ctx->Stencil.WriteMask[0] & 0xff;
dsa.stencil[0].zpass_op = PIPE_STENCIL_OP_REPLACE;
if (write_depth) {
/* writing depth+stencil: depth test always passes */
dsa.depth.enabled = 1;
dsa.depth.writemask = ctx->Depth.Mask;
dsa.depth.func = PIPE_FUNC_ALWAYS;
}
cso_set_depth_stencil_alpha(cso, &dsa);
/* blend (colormask) */
memset(&blend, 0, sizeof(blend));
cso_set_blend(cso, &blend);
}
/* fragment shader state: TEX lookup program */
cso_set_fragment_shader_handle(cso, driver_fp);
/* vertex shader state: position + texcoord pass-through */
cso_set_vertex_shader_handle(cso, driver_vp);
/* disable other shaders */
cso_set_tessctrl_shader_handle(cso, NULL);
cso_set_tesseval_shader_handle(cso, NULL);
cso_set_geometry_shader_handle(cso, NULL);
/* user samplers, plus the drawpix samplers */
{
struct pipe_sampler_state sampler;
memset(&sampler, 0, sizeof(sampler));
sampler.wrap_s = PIPE_TEX_WRAP_CLAMP;
sampler.wrap_t = PIPE_TEX_WRAP_CLAMP;
sampler.wrap_r = PIPE_TEX_WRAP_CLAMP;
sampler.min_img_filter = PIPE_TEX_FILTER_NEAREST;
sampler.min_mip_filter = PIPE_TEX_MIPFILTER_NONE;
sampler.mag_img_filter = PIPE_TEX_FILTER_NEAREST;
sampler.normalized_coords = normalized;
if (fpv) {
/* drawing a color image */
const struct pipe_sampler_state *samplers[PIPE_MAX_SAMPLERS];
uint num = MAX3(fpv->drawpix_sampler + 1,
fpv->pixelmap_sampler + 1,
st->state.num_samplers[PIPE_SHADER_FRAGMENT]);
uint i;
for (i = 0; i < st->state.num_samplers[PIPE_SHADER_FRAGMENT]; i++)
samplers[i] = &st->state.samplers[PIPE_SHADER_FRAGMENT][i];
samplers[fpv->drawpix_sampler] = &sampler;
if (sv[1])
samplers[fpv->pixelmap_sampler] = &sampler;
cso_set_samplers(cso, PIPE_SHADER_FRAGMENT, num, samplers);
} else {
/* drawing a depth/stencil image */
const struct pipe_sampler_state *samplers[2] = {&sampler, &sampler};
cso_set_samplers(cso, PIPE_SHADER_FRAGMENT, num_sampler_view, samplers);
}
}
/* user textures, plus the drawpix textures */
if (fpv) {
/* drawing a color image */
struct pipe_sampler_view *sampler_views[PIPE_MAX_SAMPLERS];
uint num = MAX3(fpv->drawpix_sampler + 1,
fpv->pixelmap_sampler + 1,
st->state.num_sampler_views[PIPE_SHADER_FRAGMENT]);
memcpy(sampler_views, st->state.sampler_views[PIPE_SHADER_FRAGMENT],
sizeof(sampler_views));
sampler_views[fpv->drawpix_sampler] = sv[0];
if (sv[1])
sampler_views[fpv->pixelmap_sampler] = sv[1];
cso_set_sampler_views(cso, PIPE_SHADER_FRAGMENT, num, sampler_views);
} else {
/* drawing a depth/stencil image */
cso_set_sampler_views(cso, PIPE_SHADER_FRAGMENT, num_sampler_view, sv);
}
/* viewport state: viewport matching window dims */
cso_set_viewport_dims(cso, fb_width, fb_height, TRUE);
cso_set_vertex_elements(cso, 3, st->util_velems);
cso_set_stream_outputs(cso, 0, NULL, NULL);
/* Compute Gallium window coords (y=0=top) with pixel zoom.
* Recall that these coords are transformed by the current
* vertex shader and viewport transformation.
*/
if (st_fb_orientation(ctx->DrawBuffer) == Y_0_BOTTOM) {
y = fb_height - (int) (y + height * ctx->Pixel.ZoomY);
invertTex = !invertTex;
}
x0 = (GLfloat) x;
x1 = x + width * ctx->Pixel.ZoomX;
y0 = (GLfloat) y;
y1 = y + height * ctx->Pixel.ZoomY;
/* convert Z from [0,1] to [-1,-1] to match viewport Z scale/bias */
z = z * 2.0f - 1.0f;
{
const float clip_x0 = x0 / (float) fb_width * 2.0f - 1.0f;
const float clip_y0 = y0 / (float) fb_height * 2.0f - 1.0f;
const float clip_x1 = x1 / (float) fb_width * 2.0f - 1.0f;
const float clip_y1 = y1 / (float) fb_height * 2.0f - 1.0f;
const float maxXcoord = normalized ?
((float) width / sv[0]->texture->width0) : (float) width;
const float maxYcoord = normalized
? ((float) height / sv[0]->texture->height0) : (float) height;
const float sLeft = 0.0f, sRight = maxXcoord;
const float tTop = invertTex ? maxYcoord : 0.0f;
const float tBot = invertTex ? 0.0f : maxYcoord;
if (!st_draw_quad(st, clip_x0, clip_y0, clip_x1, clip_y1, z,
sLeft, tBot, sRight, tTop, color, 0)) {
_mesa_error(ctx, GL_OUT_OF_MEMORY, "glDrawPixels");
}
}
/* restore state */
cso_restore_state(cso);
}
/**
* Software fallback to do glDrawPixels(GL_STENCIL_INDEX) when we
* can't use a fragment shader to write stencil values.
*/
static void
draw_stencil_pixels(struct gl_context *ctx, GLint x, GLint y,
GLsizei width, GLsizei height, GLenum format, GLenum type,
const struct gl_pixelstore_attrib *unpack,
const void *pixels)
{
struct st_context *st = st_context(ctx);
struct pipe_context *pipe = st->pipe;
struct st_renderbuffer *strb;
enum pipe_transfer_usage usage;
struct pipe_transfer *pt;
const GLboolean zoom = ctx->Pixel.ZoomX != 1.0 || ctx->Pixel.ZoomY != 1.0;
ubyte *stmap;
struct gl_pixelstore_attrib clippedUnpack = *unpack;
GLubyte *sValues;
GLuint *zValues;
if (!zoom) {
if (!_mesa_clip_drawpixels(ctx, &x, &y, &width, &height,
&clippedUnpack)) {
/* totally clipped */
return;
}
}
strb = st_renderbuffer(ctx->DrawBuffer->
Attachment[BUFFER_STENCIL].Renderbuffer);
if (st_fb_orientation(ctx->DrawBuffer) == Y_0_TOP) {
y = ctx->DrawBuffer->Height - y - height;
}
if (format == GL_STENCIL_INDEX &&
_mesa_is_format_packed_depth_stencil(strb->Base.Format)) {
/* writing stencil to a combined depth+stencil buffer */
usage = PIPE_TRANSFER_READ_WRITE;
}
else {
usage = PIPE_TRANSFER_WRITE;
}
stmap = pipe_transfer_map(pipe, strb->texture,
strb->surface->u.tex.level,
strb->surface->u.tex.first_layer,
usage, x, y,
width, height, &pt);
pixels = _mesa_map_pbo_source(ctx, &clippedUnpack, pixels);
assert(pixels);
sValues = malloc(width * sizeof(GLubyte));
zValues = malloc(width * sizeof(GLuint));
if (sValues && zValues) {
GLint row;
for (row = 0; row < height; row++) {
GLfloat *zValuesFloat = (GLfloat*)zValues;
GLenum destType = GL_UNSIGNED_BYTE;
const void *source = _mesa_image_address2d(&clippedUnpack, pixels,
width, height,
format, type,
row, 0);
_mesa_unpack_stencil_span(ctx, width, destType, sValues,
type, source, &clippedUnpack,
ctx->_ImageTransferState);
if (format == GL_DEPTH_STENCIL) {
GLenum ztype =
pt->resource->format == PIPE_FORMAT_Z32_FLOAT_S8X24_UINT ?
GL_FLOAT : GL_UNSIGNED_INT;
_mesa_unpack_depth_span(ctx, width, ztype, zValues,
(1 << 24) - 1, type, source,
&clippedUnpack);
}
if (zoom) {
_mesa_problem(ctx, "Gallium glDrawPixels(GL_STENCIL) with "
"zoom not complete");
}
{
GLint spanY;
if (st_fb_orientation(ctx->DrawBuffer) == Y_0_TOP) {
spanY = height - row - 1;
}
else {
spanY = row;
}
/* now pack the stencil (and Z) values in the dest format */
switch (pt->resource->format) {
case PIPE_FORMAT_S8_UINT:
{
ubyte *dest = stmap + spanY * pt->stride;
assert(usage == PIPE_TRANSFER_WRITE);
memcpy(dest, sValues, width);
}
break;
case PIPE_FORMAT_Z24_UNORM_S8_UINT:
if (format == GL_DEPTH_STENCIL) {
uint *dest = (uint *) (stmap + spanY * pt->stride);
GLint k;
assert(usage == PIPE_TRANSFER_WRITE);
for (k = 0; k < width; k++) {
dest[k] = zValues[k] | (sValues[k] << 24);
}
}
else {
uint *dest = (uint *) (stmap + spanY * pt->stride);
GLint k;
assert(usage == PIPE_TRANSFER_READ_WRITE);
for (k = 0; k < width; k++) {
dest[k] = (dest[k] & 0xffffff) | (sValues[k] << 24);
}
}
break;
case PIPE_FORMAT_S8_UINT_Z24_UNORM:
if (format == GL_DEPTH_STENCIL) {
uint *dest = (uint *) (stmap + spanY * pt->stride);
GLint k;
assert(usage == PIPE_TRANSFER_WRITE);
for (k = 0; k < width; k++) {
dest[k] = (zValues[k] << 8) | (sValues[k] & 0xff);
}
}
else {
uint *dest = (uint *) (stmap + spanY * pt->stride);
GLint k;
assert(usage == PIPE_TRANSFER_READ_WRITE);
for (k = 0; k < width; k++) {
dest[k] = (dest[k] & 0xffffff00) | (sValues[k] & 0xff);
}
}
break;
case PIPE_FORMAT_Z32_FLOAT_S8X24_UINT:
if (format == GL_DEPTH_STENCIL) {
uint *dest = (uint *) (stmap + spanY * pt->stride);
GLfloat *destf = (GLfloat*)dest;
GLint k;
assert(usage == PIPE_TRANSFER_WRITE);
for (k = 0; k < width; k++) {
destf[k*2] = zValuesFloat[k];
dest[k*2+1] = sValues[k] & 0xff;
}
}
else {
uint *dest = (uint *) (stmap + spanY * pt->stride);
GLint k;
assert(usage == PIPE_TRANSFER_READ_WRITE);
for (k = 0; k < width; k++) {
dest[k*2+1] = sValues[k] & 0xff;
}
}
break;
default:
assert(0);
}
}
}
}
else {
_mesa_error(ctx, GL_OUT_OF_MEMORY, "glDrawPixels()");
}
free(sValues);
free(zValues);
_mesa_unmap_pbo_source(ctx, &clippedUnpack);
/* unmap the stencil buffer */
pipe_transfer_unmap(pipe, pt);
}
/**
* Get fragment program variant for a glDrawPixels or glCopyPixels
* command for RGBA data.
*/
static struct st_fp_variant *
get_color_fp_variant(struct st_context *st)
{
struct gl_context *ctx = st->ctx;
struct st_fp_variant_key key;
struct st_fp_variant *fpv;
memset(&key, 0, sizeof(key));
key.st = st->has_shareable_shaders ? NULL : st;
key.drawpixels = 1;
key.scaleAndBias = (ctx->Pixel.RedBias != 0.0 ||
ctx->Pixel.RedScale != 1.0 ||
ctx->Pixel.GreenBias != 0.0 ||
ctx->Pixel.GreenScale != 1.0 ||
ctx->Pixel.BlueBias != 0.0 ||
ctx->Pixel.BlueScale != 1.0 ||
ctx->Pixel.AlphaBias != 0.0 ||
ctx->Pixel.AlphaScale != 1.0);
key.pixelMaps = ctx->Pixel.MapColorFlag;
key.clamp_color = st->clamp_frag_color_in_shader &&
ctx->Color._ClampFragmentColor;
fpv = st_get_fp_variant(st, st->fp, &key);
return fpv;
}
/**
* Clamp glDrawPixels width and height to the maximum texture size.
*/
static void
clamp_size(struct pipe_context *pipe, GLsizei *width, GLsizei *height,
struct gl_pixelstore_attrib *unpack)
{
const int maxSize =
1 << (pipe->screen->get_param(pipe->screen,
PIPE_CAP_MAX_TEXTURE_2D_LEVELS) - 1);
if (*width > maxSize) {
if (unpack->RowLength == 0)
unpack->RowLength = *width;
*width = maxSize;
}
if (*height > maxSize) {
*height = maxSize;
}
}
/**
* Search the array of 4 swizzle components for the named component and return
* its position.
*/
static unsigned
search_swizzle(const unsigned char swizzle[4], unsigned component)
{
unsigned i;
for (i = 0; i < 4; i++) {
if (swizzle[i] == component)
return i;
}
assert(!"search_swizzle() failed");
return 0;
}
/**
* Set the sampler view's swizzle terms. This is used to handle RGBA
* swizzling when the incoming image format isn't an exact match for
* the actual texture format. For example, if we have glDrawPixels(
* GL_RGBA, GL_UNSIGNED_BYTE) and we chose the texture format
* PIPE_FORMAT_B8G8R8A8 then we can do use the sampler view swizzle to
* avoid swizzling all the pixels in software in the texstore code.
*/
static void
setup_sampler_swizzle(struct pipe_sampler_view *sv, GLenum format, GLenum type)
{
if ((format == GL_RGBA || format == GL_BGRA) && type == GL_UNSIGNED_BYTE) {
const struct util_format_description *desc =
util_format_description(sv->texture->format);
unsigned c0, c1, c2, c3;
/* Every gallium driver supports at least one 32-bit packed RGBA format.
* We must have chosen one for (GL_RGBA, GL_UNSIGNED_BYTE).
*/
assert(desc->block.bits == 32);
/* invert the format's swizzle to setup the sampler's swizzle */
if (format == GL_RGBA) {
c0 = PIPE_SWIZZLE_X;
c1 = PIPE_SWIZZLE_Y;
c2 = PIPE_SWIZZLE_Z;
c3 = PIPE_SWIZZLE_W;
}
else {
assert(format == GL_BGRA);
c0 = PIPE_SWIZZLE_Z;
c1 = PIPE_SWIZZLE_Y;
c2 = PIPE_SWIZZLE_X;
c3 = PIPE_SWIZZLE_W;
}
sv->swizzle_r = search_swizzle(desc->swizzle, c0);
sv->swizzle_g = search_swizzle(desc->swizzle, c1);
sv->swizzle_b = search_swizzle(desc->swizzle, c2);
sv->swizzle_a = search_swizzle(desc->swizzle, c3);
}
else {
/* use the default sampler swizzle */
}
}
/**
* Called via ctx->Driver.DrawPixels()
*/
static void
st_DrawPixels(struct gl_context *ctx, GLint x, GLint y,
GLsizei width, GLsizei height,
GLenum format, GLenum type,
const struct gl_pixelstore_attrib *unpack, const void *pixels)
{
void *driver_vp, *driver_fp;
struct st_context *st = st_context(ctx);
struct pipe_context *pipe = st->pipe;
GLboolean write_stencil = GL_FALSE, write_depth = GL_FALSE;
struct pipe_sampler_view *sv[2] = { NULL };
int num_sampler_view = 1;
struct gl_pixelstore_attrib clippedUnpack;
struct st_fp_variant *fpv = NULL;
struct pipe_resource *pt;
/* Mesa state should be up to date by now */
assert(ctx->NewState == 0x0);
st_flush_bitmap_cache(st);
st_invalidate_readpix_cache(st);
st_validate_state(st, ST_PIPELINE_RENDER);
/* Limit the size of the glDrawPixels to the max texture size.
* Strictly speaking, that's not correct but since we don't handle
* larger images yet, this is better than crashing.
*/
clippedUnpack = *unpack;
unpack = &clippedUnpack;
clamp_size(st->pipe, &width, &height, &clippedUnpack);
if (format == GL_DEPTH_STENCIL)
write_stencil = write_depth = GL_TRUE;
else if (format == GL_STENCIL_INDEX)
write_stencil = GL_TRUE;
else if (format == GL_DEPTH_COMPONENT)
write_depth = GL_TRUE;
if (write_stencil &&
!pipe->screen->get_param(pipe->screen, PIPE_CAP_SHADER_STENCIL_EXPORT)) {
/* software fallback */
draw_stencil_pixels(ctx, x, y, width, height, format, type,
unpack, pixels);
return;
}
/*
* Get vertex/fragment shaders
*/
if (write_depth || write_stencil) {
driver_fp = get_drawpix_z_stencil_program(st, write_depth,
write_stencil);
driver_vp = make_passthrough_vertex_shader(st, GL_TRUE);
}
else {
fpv = get_color_fp_variant(st);
driver_fp = fpv->driver_shader;
driver_vp = make_passthrough_vertex_shader(st, GL_FALSE);
if (ctx->Pixel.MapColorFlag) {
pipe_sampler_view_reference(&sv[1],
st->pixel_xfer.pixelmap_sampler_view);
num_sampler_view++;
}
/* compiling a new fragment shader variant added new state constants
* into the constant buffer, we need to update them
*/
st_upload_constants(st, st->fp->Base.Base.Parameters,
PIPE_SHADER_FRAGMENT);
}
/* Put glDrawPixels image into a texture */
pt = make_texture(st, width, height, format, type, unpack, pixels);
if (!pt) {
_mesa_error(ctx, GL_OUT_OF_MEMORY, "glDrawPixels");
return;
}
/* create sampler view for the image */
sv[0] = st_create_texture_sampler_view(st->pipe, pt);
if (!sv[0]) {
_mesa_error(ctx, GL_OUT_OF_MEMORY, "glDrawPixels");
pipe_resource_reference(&pt, NULL);
return;
}
/* Set up the sampler view's swizzle */
setup_sampler_swizzle(sv[0], format, type);
/* Create a second sampler view to read stencil. The stencil is
* written using the shader stencil export functionality.
*/
if (write_stencil) {
enum pipe_format stencil_format =
util_format_stencil_only(pt->format);
/* we should not be doing pixel map/transfer (see above) */
assert(num_sampler_view == 1);
sv[1] = st_create_texture_sampler_view_format(st->pipe, pt,
stencil_format);
if (!sv[1]) {
_mesa_error(ctx, GL_OUT_OF_MEMORY, "glDrawPixels");
pipe_resource_reference(&pt, NULL);
pipe_sampler_view_reference(&sv[0], NULL);
return;
}
num_sampler_view++;
}
draw_textured_quad(ctx, x, y, ctx->Current.RasterPos[2],
width, height,
ctx->Pixel.ZoomX, ctx->Pixel.ZoomY,
sv,
num_sampler_view,
driver_vp,
driver_fp, fpv,
ctx->Current.RasterColor,
GL_FALSE, write_depth, write_stencil);
pipe_sampler_view_reference(&sv[0], NULL);
if (num_sampler_view > 1)
pipe_sampler_view_reference(&sv[1], NULL);
/* free the texture (but may persist in the cache) */
pipe_resource_reference(&pt, NULL);
}
/**
* Software fallback for glCopyPixels(GL_STENCIL).
*/
static void
copy_stencil_pixels(struct gl_context *ctx, GLint srcx, GLint srcy,
GLsizei width, GLsizei height,
GLint dstx, GLint dsty)
{
struct st_renderbuffer *rbDraw;
struct pipe_context *pipe = st_context(ctx)->pipe;
enum pipe_transfer_usage usage;
struct pipe_transfer *ptDraw;
ubyte *drawMap;
ubyte *buffer;
int i;
buffer = malloc(width * height * sizeof(ubyte));
if (!buffer) {
_mesa_error(ctx, GL_OUT_OF_MEMORY, "glCopyPixels(stencil)");
return;
}
/* Get the dest renderbuffer */
rbDraw = st_renderbuffer(ctx->DrawBuffer->
Attachment[BUFFER_STENCIL].Renderbuffer);
/* this will do stencil pixel transfer ops */
_mesa_readpixels(ctx, srcx, srcy, width, height,
GL_STENCIL_INDEX, GL_UNSIGNED_BYTE,
&ctx->DefaultPacking, buffer);
if (0) {
/* debug code: dump stencil values */
GLint row, col;
for (row = 0; row < height; row++) {
printf("%3d: ", row);
for (col = 0; col < width; col++) {
printf("%02x ", buffer[col + row * width]);
}
printf("\n");
}
}
if (_mesa_is_format_packed_depth_stencil(rbDraw->Base.Format))
usage = PIPE_TRANSFER_READ_WRITE;
else
usage = PIPE_TRANSFER_WRITE;
if (st_fb_orientation(ctx->DrawBuffer) == Y_0_TOP) {
dsty = rbDraw->Base.Height - dsty - height;
}
assert(util_format_get_blockwidth(rbDraw->texture->format) == 1);
assert(util_format_get_blockheight(rbDraw->texture->format) == 1);
/* map the stencil buffer */
drawMap = pipe_transfer_map(pipe,
rbDraw->texture,
rbDraw->surface->u.tex.level,
rbDraw->surface->u.tex.first_layer,
usage, dstx, dsty,
width, height, &ptDraw);
/* draw */
/* XXX PixelZoom not handled yet */
for (i = 0; i < height; i++) {
ubyte *dst;
const ubyte *src;
int y;
y = i;
if (st_fb_orientation(ctx->DrawBuffer) == Y_0_TOP) {
y = height - y - 1;
}
dst = drawMap + y * ptDraw->stride;
src = buffer + i * width;
_mesa_pack_ubyte_stencil_row(rbDraw->Base.Format, width, src, dst);
}
free(buffer);
/* unmap the stencil buffer */
pipe_transfer_unmap(pipe, ptDraw);
}
/**
* Return renderbuffer to use for reading color pixels for glCopyPixels
*/
static struct st_renderbuffer *
st_get_color_read_renderbuffer(struct gl_context *ctx)
{
struct gl_framebuffer *fb = ctx->ReadBuffer;
struct st_renderbuffer *strb =
st_renderbuffer(fb->_ColorReadBuffer);
return strb;
}
/**
* Try to do a glCopyPixels for simple cases with a blit by calling
* pipe->blit().
*
* We can do this when we're copying color pixels (depth/stencil
* eventually) with no pixel zoom, no pixel transfer ops, no
* per-fragment ops, and the src/dest regions don't overlap.
*/
static GLboolean
blit_copy_pixels(struct gl_context *ctx, GLint srcx, GLint srcy,
GLsizei width, GLsizei height,
GLint dstx, GLint dsty, GLenum type)
{
struct st_context *st = st_context(ctx);
struct pipe_context *pipe = st->pipe;
struct pipe_screen *screen = pipe->screen;
struct gl_pixelstore_attrib pack, unpack;
GLint readX, readY, readW, readH, drawX, drawY, drawW, drawH;
if (type == GL_COLOR &&
ctx->Pixel.ZoomX == 1.0 &&
ctx->Pixel.ZoomY == 1.0 &&
ctx->_ImageTransferState == 0x0 &&
!ctx->Color.BlendEnabled &&
!ctx->Color.AlphaEnabled &&
(!ctx->Color.ColorLogicOpEnabled || ctx->Color.LogicOp == GL_COPY) &&
!ctx->Depth.Test &&
!ctx->Fog.Enabled &&
!ctx->Stencil.Enabled &&
!ctx->FragmentProgram.Enabled &&
!ctx->VertexProgram.Enabled &&
!ctx->_Shader->CurrentProgram[MESA_SHADER_FRAGMENT] &&
!ctx->ATIFragmentShader._Enabled &&
ctx->DrawBuffer->_NumColorDrawBuffers == 1 &&
!ctx->Query.CondRenderQuery &&
!ctx->Query.CurrentOcclusionObject) {
struct st_renderbuffer *rbRead, *rbDraw;
/*
* Clip the read region against the src buffer bounds.
* We'll still allocate a temporary buffer/texture for the original
* src region size but we'll only read the region which is on-screen.
* This may mean that we draw garbage pixels into the dest region, but
* that's expected.
*/
readX = srcx;
readY = srcy;
readW = width;
readH = height;
pack = ctx->DefaultPacking;
if (!_mesa_clip_readpixels(ctx, &readX, &readY, &readW, &readH, &pack))
return GL_TRUE; /* all done */
/* clip against dest buffer bounds and scissor box */
drawX = dstx + pack.SkipPixels;
drawY = dsty + pack.SkipRows;
unpack = pack;
if (!_mesa_clip_drawpixels(ctx, &drawX, &drawY, &readW, &readH, &unpack))
return GL_TRUE; /* all done */
readX = readX - pack.SkipPixels + unpack.SkipPixels;
readY = readY - pack.SkipRows + unpack.SkipRows;
drawW = readW;
drawH = readH;
rbRead = st_get_color_read_renderbuffer(ctx);
rbDraw = st_renderbuffer(ctx->DrawBuffer->_ColorDrawBuffers[0]);
/* Flip src/dst position depending on the orientation of buffers. */
if (st_fb_orientation(ctx->ReadBuffer) == Y_0_TOP) {
readY = rbRead->Base.Height - readY;
readH = -readH;
}
if (st_fb_orientation(ctx->DrawBuffer) == Y_0_TOP) {
/* We can't flip the destination for pipe->blit, so we only adjust
* its position and flip the source.
*/
drawY = rbDraw->Base.Height - drawY - drawH;
readY += readH;
readH = -readH;
}
if (rbRead != rbDraw ||
!_mesa_regions_overlap(readX, readY, readX + readW, readY + readH,
drawX, drawY, drawX + drawW, drawY + drawH)) {
struct pipe_blit_info blit;
memset(&blit, 0, sizeof(blit));
blit.src.resource = rbRead->texture;
blit.src.level = rbRead->surface->u.tex.level;
blit.src.format = rbRead->texture->format;
blit.src.box.x = readX;
blit.src.box.y = readY;
blit.src.box.z = rbRead->surface->u.tex.first_layer;
blit.src.box.width = readW;
blit.src.box.height = readH;
blit.src.box.depth = 1;
blit.dst.resource = rbDraw->texture;
blit.dst.level = rbDraw->surface->u.tex.level;
blit.dst.format = rbDraw->texture->format;
blit.dst.box.x = drawX;
blit.dst.box.y = drawY;
blit.dst.box.z = rbDraw->surface->u.tex.first_layer;
blit.dst.box.width = drawW;
blit.dst.box.height = drawH;
blit.dst.box.depth = 1;
blit.mask = PIPE_MASK_RGBA;
blit.filter = PIPE_TEX_FILTER_NEAREST;
if (ctx->DrawBuffer != ctx->WinSysDrawBuffer)
st_window_rectangles_to_blit(ctx, &blit);
if (screen->is_format_supported(screen, blit.src.format,
blit.src.resource->target,
blit.src.resource->nr_samples,
PIPE_BIND_SAMPLER_VIEW) &&
screen->is_format_supported(screen, blit.dst.format,
blit.dst.resource->target,
blit.dst.resource->nr_samples,
PIPE_BIND_RENDER_TARGET)) {
pipe->blit(pipe, &blit);
return GL_TRUE;
}
}
}
return GL_FALSE;
}
static void
st_CopyPixels(struct gl_context *ctx, GLint srcx, GLint srcy,
GLsizei width, GLsizei height,
GLint dstx, GLint dsty, GLenum type)
{
struct st_context *st = st_context(ctx);
struct pipe_context *pipe = st->pipe;
struct pipe_screen *screen = pipe->screen;
struct st_renderbuffer *rbRead;
void *driver_vp, *driver_fp;
struct pipe_resource *pt;
struct pipe_sampler_view *sv[2] = { NULL };
struct st_fp_variant *fpv = NULL;
int num_sampler_view = 1;
enum pipe_format srcFormat;
unsigned srcBind;
GLboolean invertTex = GL_FALSE;
GLint readX, readY, readW, readH;
struct gl_pixelstore_attrib pack = ctx->DefaultPacking;
st_flush_bitmap_cache(st);
st_invalidate_readpix_cache(st);
st_validate_state(st, ST_PIPELINE_RENDER);
if (type == GL_DEPTH_STENCIL) {
/* XXX make this more efficient */
st_CopyPixels(ctx, srcx, srcy, width, height, dstx, dsty, GL_STENCIL);
st_CopyPixels(ctx, srcx, srcy, width, height, dstx, dsty, GL_DEPTH);
return;
}
if (type == GL_STENCIL) {
/* can't use texturing to do stencil */
copy_stencil_pixels(ctx, srcx, srcy, width, height, dstx, dsty);
return;
}
if (blit_copy_pixels(ctx, srcx, srcy, width, height, dstx, dsty, type))
return;
/*
* The subsequent code implements glCopyPixels by copying the source
* pixels into a temporary texture that's then applied to a textured quad.
* When we draw the textured quad, all the usual per-fragment operations
* are handled.
*/
/*
* Get vertex/fragment shaders
*/
if (type == GL_COLOR) {
fpv = get_color_fp_variant(st);
rbRead = st_get_color_read_renderbuffer(ctx);
driver_fp = fpv->driver_shader;
driver_vp = make_passthrough_vertex_shader(st, GL_FALSE);
if (ctx->Pixel.MapColorFlag) {
pipe_sampler_view_reference(&sv[1],
st->pixel_xfer.pixelmap_sampler_view);
num_sampler_view++;
}
/* compiling a new fragment shader variant added new state constants
* into the constant buffer, we need to update them
*/
st_upload_constants(st, st->fp->Base.Base.Parameters,
PIPE_SHADER_FRAGMENT);
}
else {
assert(type == GL_DEPTH);
rbRead = st_renderbuffer(ctx->ReadBuffer->
Attachment[BUFFER_DEPTH].Renderbuffer);
driver_fp = get_drawpix_z_stencil_program(st, GL_TRUE, GL_FALSE);
driver_vp = make_passthrough_vertex_shader(st, GL_TRUE);
}
/* Choose the format for the temporary texture. */
srcFormat = rbRead->texture->format;
srcBind = PIPE_BIND_SAMPLER_VIEW |
(type == GL_COLOR ? PIPE_BIND_RENDER_TARGET : PIPE_BIND_DEPTH_STENCIL);
if (!screen->is_format_supported(screen, srcFormat, st->internal_target, 0,
srcBind)) {
/* srcFormat is non-renderable. Find a compatible renderable format. */
if (type == GL_DEPTH) {
srcFormat = st_choose_format(st, GL_DEPTH_COMPONENT, GL_NONE,
GL_NONE, st->internal_target, 0,
srcBind, FALSE);
}
else {
assert(type == GL_COLOR);
if (util_format_is_float(srcFormat)) {
srcFormat = st_choose_format(st, GL_RGBA32F, GL_NONE,
GL_NONE, st->internal_target, 0,
srcBind, FALSE);
}
else if (util_format_is_pure_sint(srcFormat)) {
srcFormat = st_choose_format(st, GL_RGBA32I, GL_NONE,
GL_NONE, st->internal_target, 0,
srcBind, FALSE);
}
else if (util_format_is_pure_uint(srcFormat)) {
srcFormat = st_choose_format(st, GL_RGBA32UI, GL_NONE,
GL_NONE, st->internal_target, 0,
srcBind, FALSE);
}
else if (util_format_is_snorm(srcFormat)) {
srcFormat = st_choose_format(st, GL_RGBA16_SNORM, GL_NONE,
GL_NONE, st->internal_target, 0,
srcBind, FALSE);
}
else {
srcFormat = st_choose_format(st, GL_RGBA, GL_NONE,
GL_NONE, st->internal_target, 0,
srcBind, FALSE);
}
}
if (srcFormat == PIPE_FORMAT_NONE) {
assert(0 && "cannot choose a format for src of CopyPixels");
return;
}
}
/* Invert src region if needed */
if (st_fb_orientation(ctx->ReadBuffer) == Y_0_TOP) {
srcy = ctx->ReadBuffer->Height - srcy - height;
invertTex = !invertTex;
}
/* Clip the read region against the src buffer bounds.
* We'll still allocate a temporary buffer/texture for the original
* src region size but we'll only read the region which is on-screen.
* This may mean that we draw garbage pixels into the dest region, but
* that's expected.
*/
readX = srcx;
readY = srcy;
readW = width;
readH = height;
if (!_mesa_clip_readpixels(ctx, &readX, &readY, &readW, &readH, &pack)) {
/* The source region is completely out of bounds. Do nothing.
* The GL spec says "Results of copies from outside the window,
* or from regions of the window that are not exposed, are
* hardware dependent and undefined."
*/
return;
}
readW = MAX2(0, readW);
readH = MAX2(0, readH);
/* Allocate the temporary texture. */
pt = alloc_texture(st, width, height, srcFormat, srcBind);
if (!pt)
return;
sv[0] = st_create_texture_sampler_view(st->pipe, pt);
if (!sv[0]) {
pipe_resource_reference(&pt, NULL);
return;
}
/* Copy the src region to the temporary texture. */
{
struct pipe_blit_info blit;
memset(&blit, 0, sizeof(blit));
blit.src.resource = rbRead->texture;
blit.src.level = rbRead->surface->u.tex.level;
blit.src.format = rbRead->texture->format;
blit.src.box.x = readX;
blit.src.box.y = readY;
blit.src.box.z = rbRead->surface->u.tex.first_layer;
blit.src.box.width = readW;
blit.src.box.height = readH;
blit.src.box.depth = 1;
blit.dst.resource = pt;
blit.dst.level = 0;
blit.dst.format = pt->format;
blit.dst.box.x = pack.SkipPixels;
blit.dst.box.y = pack.SkipRows;
blit.dst.box.z = 0;
blit.dst.box.width = readW;
blit.dst.box.height = readH;
blit.dst.box.depth = 1;
blit.mask = util_format_get_mask(pt->format) & ~PIPE_MASK_S;
blit.filter = PIPE_TEX_FILTER_NEAREST;
pipe->blit(pipe, &blit);
}
/* OK, the texture 'pt' contains the src image/pixels. Now draw a
* textured quad with that texture.
*/
draw_textured_quad(ctx, dstx, dsty, ctx->Current.RasterPos[2],
width, height, ctx->Pixel.ZoomX, ctx->Pixel.ZoomY,
sv,
num_sampler_view,
driver_vp,
driver_fp, fpv,
ctx->Current.Attrib[VERT_ATTRIB_COLOR0],
invertTex, GL_FALSE, GL_FALSE);
pipe_resource_reference(&pt, NULL);
pipe_sampler_view_reference(&sv[0], NULL);
}
void st_init_drawpixels_functions(struct dd_function_table *functions)
{
functions->DrawPixels = st_DrawPixels;
functions->CopyPixels = st_CopyPixels;
}
void
st_destroy_drawpix(struct st_context *st)
{
GLuint i;
for (i = 0; i < ARRAY_SIZE(st->drawpix.zs_shaders); i++) {
if (st->drawpix.zs_shaders[i])
cso_delete_fragment_shader(st->cso_context,
st->drawpix.zs_shaders[i]);
}
if (st->drawpix.vert_shaders[0])
cso_delete_vertex_shader(st->cso_context, st->drawpix.vert_shaders[0]);
if (st->drawpix.vert_shaders[1])
cso_delete_vertex_shader(st->cso_context, st->drawpix.vert_shaders[1]);
}
|