aboutsummaryrefslogtreecommitdiffstats
path: root/src/mesa/drivers/dri/i965/brw_context.h
blob: d7ea7fae31d18c9b5666aab2074012953fab820b (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
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
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
/*
 Copyright (C) Intel Corp.  2006.  All Rights Reserved.
 Intel funded Tungsten Graphics to
 develop this 3D driver.

 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 COPYRIGHT OWNER(S) 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:
  *   Keith Whitwell <keithw@vmware.com>
  */


#ifndef BRWCONTEXT_INC
#define BRWCONTEXT_INC

#include <stdbool.h>
#include "main/macros.h"
#include "main/mtypes.h"
#include "brw_structs.h"
#include "compiler/brw_compiler.h"

#include "isl/isl.h"
#include "blorp/blorp.h"

#include <brw_bufmgr.h>

#include "common/gen_debug.h"
#include "intel_screen.h"
#include "intel_tex_obj.h"

#ifdef __cplusplus
extern "C" {
#endif
/* Glossary:
 *
 * URB - uniform resource buffer.  A mid-sized buffer which is
 * partitioned between the fixed function units and used for passing
 * values (vertices, primitives, constants) between them.
 *
 * CURBE - constant URB entry.  An urb region (entry) used to hold
 * constant values which the fixed function units can be instructed to
 * preload into the GRF when spawning a thread.
 *
 * VUE - vertex URB entry.  An urb entry holding a vertex and usually
 * a vertex header.  The header contains control information and
 * things like primitive type, Begin/end flags and clip codes.
 *
 * PUE - primitive URB entry.  An urb entry produced by the setup (SF)
 * unit holding rasterization and interpolation parameters.
 *
 * GRF - general register file.  One of several register files
 * addressable by programmed threads.  The inputs (r0, payload, curbe,
 * urb) of the thread are preloaded to this area before the thread is
 * spawned.  The registers are individually 8 dwords wide and suitable
 * for general usage.  Registers holding thread input values are not
 * special and may be overwritten.
 *
 * MRF - message register file.  Threads communicate (and terminate)
 * by sending messages.  Message parameters are placed in contiguous
 * MRF registers.  All program output is via these messages.  URB
 * entries are populated by sending a message to the shared URB
 * function containing the new data, together with a control word,
 * often an unmodified copy of R0.
 *
 * R0 - GRF register 0.  Typically holds control information used when
 * sending messages to other threads.
 *
 * EU or GEN4 EU: The name of the programmable subsystem of the
 * i965 hardware.  Threads are executed by the EU, the registers
 * described above are part of the EU architecture.
 *
 * Fixed function units:
 *
 * CS - Command streamer.  Notional first unit, little software
 * interaction.  Holds the URB entries used for constant data, ie the
 * CURBEs.
 *
 * VF/VS - Vertex Fetch / Vertex Shader.  The fixed function part of
 * this unit is responsible for pulling vertices out of vertex buffers
 * in vram and injecting them into the processing pipe as VUEs.  If
 * enabled, it first passes them to a VS thread which is a good place
 * for the driver to implement any active vertex shader.
 *
 * HS - Hull Shader (Tessellation Control Shader)
 *
 * TE - Tessellation Engine (Tessellation Primitive Generation)
 *
 * DS - Domain Shader (Tessellation Evaluation Shader)
 *
 * GS - Geometry Shader.  This corresponds to a new DX10 concept.  If
 * enabled, incoming strips etc are passed to GS threads in individual
 * line/triangle/point units.  The GS thread may perform arbitary
 * computation and emit whatever primtives with whatever vertices it
 * chooses.  This makes GS an excellent place to implement GL's
 * unfilled polygon modes, though of course it is capable of much
 * more.  Additionally, GS is used to translate away primitives not
 * handled by latter units, including Quads and Lineloops.
 *
 * CS - Clipper.  Mesa's clipping algorithms are imported to run on
 * this unit.  The fixed function part performs cliptesting against
 * the 6 fixed clipplanes and makes descisions on whether or not the
 * incoming primitive needs to be passed to a thread for clipping.
 * User clip planes are handled via cooperation with the VS thread.
 *
 * SF - Strips Fans or Setup: Triangles are prepared for
 * rasterization.  Interpolation coefficients are calculated.
 * Flatshading and two-side lighting usually performed here.
 *
 * WM - Windower.  Interpolation of vertex attributes performed here.
 * Fragment shader implemented here.  SIMD aspects of EU taken full
 * advantage of, as pixels are processed in blocks of 16.
 *
 * CC - Color Calculator.  No EU threads associated with this unit.
 * Handles blending and (presumably) depth and stencil testing.
 */

struct brw_context;
struct brw_inst;
struct brw_vs_prog_key;
struct brw_vue_prog_key;
struct brw_wm_prog_key;
struct brw_wm_prog_data;
struct brw_cs_prog_key;
struct brw_cs_prog_data;

enum brw_pipeline {
   BRW_RENDER_PIPELINE,
   BRW_COMPUTE_PIPELINE,

   BRW_NUM_PIPELINES
};

enum brw_cache_id {
   BRW_CACHE_FS_PROG,
   BRW_CACHE_BLORP_PROG,
   BRW_CACHE_SF_PROG,
   BRW_CACHE_VS_PROG,
   BRW_CACHE_FF_GS_PROG,
   BRW_CACHE_GS_PROG,
   BRW_CACHE_TCS_PROG,
   BRW_CACHE_TES_PROG,
   BRW_CACHE_CLIP_PROG,
   BRW_CACHE_CS_PROG,

   BRW_MAX_CACHE
};

enum brw_state_id {
   /* brw_cache_ids must come first - see brw_program_cache.c */
   BRW_STATE_URB_FENCE = BRW_MAX_CACHE,
   BRW_STATE_FRAGMENT_PROGRAM,
   BRW_STATE_GEOMETRY_PROGRAM,
   BRW_STATE_TESS_PROGRAMS,
   BRW_STATE_VERTEX_PROGRAM,
   BRW_STATE_REDUCED_PRIMITIVE,
   BRW_STATE_PATCH_PRIMITIVE,
   BRW_STATE_PRIMITIVE,
   BRW_STATE_CONTEXT,
   BRW_STATE_PSP,
   BRW_STATE_SURFACES,
   BRW_STATE_BINDING_TABLE_POINTERS,
   BRW_STATE_INDICES,
   BRW_STATE_VERTICES,
   BRW_STATE_DEFAULT_TESS_LEVELS,
   BRW_STATE_BATCH,
   BRW_STATE_INDEX_BUFFER,
   BRW_STATE_VS_CONSTBUF,
   BRW_STATE_TCS_CONSTBUF,
   BRW_STATE_TES_CONSTBUF,
   BRW_STATE_GS_CONSTBUF,
   BRW_STATE_PROGRAM_CACHE,
   BRW_STATE_STATE_BASE_ADDRESS,
   BRW_STATE_VUE_MAP_GEOM_OUT,
   BRW_STATE_TRANSFORM_FEEDBACK,
   BRW_STATE_RASTERIZER_DISCARD,
   BRW_STATE_STATS_WM,
   BRW_STATE_UNIFORM_BUFFER,
   BRW_STATE_ATOMIC_BUFFER,
   BRW_STATE_IMAGE_UNITS,
   BRW_STATE_META_IN_PROGRESS,
   BRW_STATE_PUSH_CONSTANT_ALLOCATION,
   BRW_STATE_NUM_SAMPLES,
   BRW_STATE_TEXTURE_BUFFER,
   BRW_STATE_GEN4_UNIT_STATE,
   BRW_STATE_CC_VP,
   BRW_STATE_SF_VP,
   BRW_STATE_CLIP_VP,
   BRW_STATE_SAMPLER_STATE_TABLE,
   BRW_STATE_VS_ATTRIB_WORKAROUNDS,
   BRW_STATE_COMPUTE_PROGRAM,
   BRW_STATE_CS_WORK_GROUPS,
   BRW_STATE_URB_SIZE,
   BRW_STATE_CC_STATE,
   BRW_STATE_BLORP,
   BRW_STATE_VIEWPORT_COUNT,
   BRW_STATE_CONSERVATIVE_RASTERIZATION,
   BRW_NUM_STATE_BITS
};

/**
 * BRW_NEW_*_PROG_DATA and BRW_NEW_*_PROGRAM are similar, but distinct.
 *
 * BRW_NEW_*_PROGRAM relates to the gl_shader_program/gl_program structures.
 * When the currently bound shader program differs from the previous draw
 * call, these will be flagged.  They cover brw->{stage}_program and
 * ctx->{Stage}Program->_Current.
 *
 * BRW_NEW_*_PROG_DATA is flagged when the effective shaders change, from a
 * driver perspective.  Even if the same shader is bound at the API level,
 * we may need to switch between multiple versions of that shader to handle
 * changes in non-orthagonal state.
 *
 * Additionally, multiple shader programs may have identical vertex shaders
 * (for example), or compile down to the same code in the backend.  We combine
 * those into a single program cache entry.
 *
 * BRW_NEW_*_PROG_DATA occurs when switching program cache entries, which
 * covers the brw_*_prog_data structures, and brw->*.prog_offset.
 */
#define BRW_NEW_FS_PROG_DATA            (1ull << BRW_CACHE_FS_PROG)
/* XXX: The BRW_NEW_BLORP_BLIT_PROG_DATA dirty bit is unused (as BLORP doesn't
 * use the normal state upload paths), but the cache is still used.  To avoid
 * polluting the brw_program_cache code with special cases, we retain the
 * dirty bit for now.  It should eventually be removed.
 */
#define BRW_NEW_BLORP_BLIT_PROG_DATA    (1ull << BRW_CACHE_BLORP_PROG)
#define BRW_NEW_SF_PROG_DATA            (1ull << BRW_CACHE_SF_PROG)
#define BRW_NEW_VS_PROG_DATA            (1ull << BRW_CACHE_VS_PROG)
#define BRW_NEW_FF_GS_PROG_DATA         (1ull << BRW_CACHE_FF_GS_PROG)
#define BRW_NEW_GS_PROG_DATA            (1ull << BRW_CACHE_GS_PROG)
#define BRW_NEW_TCS_PROG_DATA           (1ull << BRW_CACHE_TCS_PROG)
#define BRW_NEW_TES_PROG_DATA           (1ull << BRW_CACHE_TES_PROG)
#define BRW_NEW_CLIP_PROG_DATA          (1ull << BRW_CACHE_CLIP_PROG)
#define BRW_NEW_CS_PROG_DATA            (1ull << BRW_CACHE_CS_PROG)
#define BRW_NEW_URB_FENCE               (1ull << BRW_STATE_URB_FENCE)
#define BRW_NEW_FRAGMENT_PROGRAM        (1ull << BRW_STATE_FRAGMENT_PROGRAM)
#define BRW_NEW_GEOMETRY_PROGRAM        (1ull << BRW_STATE_GEOMETRY_PROGRAM)
#define BRW_NEW_TESS_PROGRAMS           (1ull << BRW_STATE_TESS_PROGRAMS)
#define BRW_NEW_VERTEX_PROGRAM          (1ull << BRW_STATE_VERTEX_PROGRAM)
#define BRW_NEW_REDUCED_PRIMITIVE       (1ull << BRW_STATE_REDUCED_PRIMITIVE)
#define BRW_NEW_PATCH_PRIMITIVE         (1ull << BRW_STATE_PATCH_PRIMITIVE)
#define BRW_NEW_PRIMITIVE               (1ull << BRW_STATE_PRIMITIVE)
#define BRW_NEW_CONTEXT                 (1ull << BRW_STATE_CONTEXT)
#define BRW_NEW_PSP                     (1ull << BRW_STATE_PSP)
#define BRW_NEW_SURFACES                (1ull << BRW_STATE_SURFACES)
#define BRW_NEW_BINDING_TABLE_POINTERS  (1ull << BRW_STATE_BINDING_TABLE_POINTERS)
#define BRW_NEW_INDICES                 (1ull << BRW_STATE_INDICES)
#define BRW_NEW_VERTICES                (1ull << BRW_STATE_VERTICES)
#define BRW_NEW_DEFAULT_TESS_LEVELS     (1ull << BRW_STATE_DEFAULT_TESS_LEVELS)
/**
 * Used for any batch entry with a relocated pointer that will be used
 * by any 3D rendering.
 */
#define BRW_NEW_BATCH                   (1ull << BRW_STATE_BATCH)
/** \see brw.state.depth_region */
#define BRW_NEW_INDEX_BUFFER            (1ull << BRW_STATE_INDEX_BUFFER)
#define BRW_NEW_VS_CONSTBUF             (1ull << BRW_STATE_VS_CONSTBUF)
#define BRW_NEW_TCS_CONSTBUF            (1ull << BRW_STATE_TCS_CONSTBUF)
#define BRW_NEW_TES_CONSTBUF            (1ull << BRW_STATE_TES_CONSTBUF)
#define BRW_NEW_GS_CONSTBUF             (1ull << BRW_STATE_GS_CONSTBUF)
#define BRW_NEW_PROGRAM_CACHE           (1ull << BRW_STATE_PROGRAM_CACHE)
#define BRW_NEW_STATE_BASE_ADDRESS      (1ull << BRW_STATE_STATE_BASE_ADDRESS)
#define BRW_NEW_VUE_MAP_GEOM_OUT        (1ull << BRW_STATE_VUE_MAP_GEOM_OUT)
#define BRW_NEW_VIEWPORT_COUNT          (1ull << BRW_STATE_VIEWPORT_COUNT)
#define BRW_NEW_TRANSFORM_FEEDBACK      (1ull << BRW_STATE_TRANSFORM_FEEDBACK)
#define BRW_NEW_RASTERIZER_DISCARD      (1ull << BRW_STATE_RASTERIZER_DISCARD)
#define BRW_NEW_STATS_WM                (1ull << BRW_STATE_STATS_WM)
#define BRW_NEW_UNIFORM_BUFFER          (1ull << BRW_STATE_UNIFORM_BUFFER)
#define BRW_NEW_ATOMIC_BUFFER           (1ull << BRW_STATE_ATOMIC_BUFFER)
#define BRW_NEW_IMAGE_UNITS             (1ull << BRW_STATE_IMAGE_UNITS)
#define BRW_NEW_META_IN_PROGRESS        (1ull << BRW_STATE_META_IN_PROGRESS)
#define BRW_NEW_PUSH_CONSTANT_ALLOCATION (1ull << BRW_STATE_PUSH_CONSTANT_ALLOCATION)
#define BRW_NEW_NUM_SAMPLES             (1ull << BRW_STATE_NUM_SAMPLES)
#define BRW_NEW_TEXTURE_BUFFER          (1ull << BRW_STATE_TEXTURE_BUFFER)
#define BRW_NEW_GEN4_UNIT_STATE         (1ull << BRW_STATE_GEN4_UNIT_STATE)
#define BRW_NEW_CC_VP                   (1ull << BRW_STATE_CC_VP)
#define BRW_NEW_SF_VP                   (1ull << BRW_STATE_SF_VP)
#define BRW_NEW_CLIP_VP                 (1ull << BRW_STATE_CLIP_VP)
#define BRW_NEW_SAMPLER_STATE_TABLE     (1ull << BRW_STATE_SAMPLER_STATE_TABLE)
#define BRW_NEW_VS_ATTRIB_WORKAROUNDS   (1ull << BRW_STATE_VS_ATTRIB_WORKAROUNDS)
#define BRW_NEW_COMPUTE_PROGRAM         (1ull << BRW_STATE_COMPUTE_PROGRAM)
#define BRW_NEW_CS_WORK_GROUPS          (1ull << BRW_STATE_CS_WORK_GROUPS)
#define BRW_NEW_URB_SIZE                (1ull << BRW_STATE_URB_SIZE)
#define BRW_NEW_CC_STATE                (1ull << BRW_STATE_CC_STATE)
#define BRW_NEW_BLORP                   (1ull << BRW_STATE_BLORP)
#define BRW_NEW_CONSERVATIVE_RASTERIZATION (1ull << BRW_STATE_CONSERVATIVE_RASTERIZATION)

struct brw_state_flags {
   /** State update flags signalled by mesa internals */
   GLuint mesa;
   /**
    * State update flags signalled as the result of brw_tracked_state updates
    */
   uint64_t brw;
};


/** Subclass of Mesa program */
struct brw_program {
   struct gl_program program;
   GLuint id;

   bool compiled_once;
};


struct brw_ff_gs_prog_data {
   GLuint urb_read_length;
   GLuint total_grf;

   /**
    * Gen6 transform feedback: Amount by which the streaming vertex buffer
    * indices should be incremented each time the GS is invoked.
    */
   unsigned svbi_postincrement_value;
};

/** Number of texture sampler units */
#define BRW_MAX_TEX_UNIT 32

/** Max number of UBOs in a shader */
#define BRW_MAX_UBO 14

/** Max number of SSBOs in a shader */
#define BRW_MAX_SSBO 12

/** Max number of atomic counter buffer objects in a shader */
#define BRW_MAX_ABO 16

/** Max number of image uniforms in a shader */
#define BRW_MAX_IMAGES 32

/** Maximum number of actual buffers used for stream output */
#define BRW_MAX_SOL_BUFFERS 4

#define BRW_MAX_SURFACES   (BRW_MAX_DRAW_BUFFERS +                      \
                            BRW_MAX_TEX_UNIT * 2 + /* normal, gather */ \
                            BRW_MAX_UBO +                               \
                            BRW_MAX_SSBO +                              \
                            BRW_MAX_ABO +                               \
                            BRW_MAX_IMAGES +                            \
                            2 + /* shader time, pull constants */       \
                            1 /* cs num work groups */)

struct brw_cache {
   struct brw_context *brw;

   struct brw_cache_item **items;
   struct brw_bo *bo;
   void *map;
   GLuint size, n_items;

   uint32_t next_offset;
   bool bo_used_by_gpu;
};

/* Considered adding a member to this struct to document which flags
 * an update might raise so that ordering of the state atoms can be
 * checked or derived at runtime.  Dropped the idea in favor of having
 * a debug mode where the state is monitored for flags which are
 * raised that have already been tested against.
 */
struct brw_tracked_state {
   struct brw_state_flags dirty;
   void (*emit)( struct brw_context *brw );
};

enum shader_time_shader_type {
   ST_NONE,
   ST_VS,
   ST_TCS,
   ST_TES,
   ST_GS,
   ST_FS8,
   ST_FS16,
   ST_CS,
};

struct brw_vertex_buffer {
   /** Buffer object containing the uploaded vertex data */
   struct brw_bo *bo;
   uint32_t offset;
   uint32_t size;
   /** Byte stride between elements in the uploaded array */
   GLuint stride;
   GLuint step_rate;
};
struct brw_vertex_element {
   const struct gl_vertex_array *glarray;

   int buffer;
   bool is_dual_slot;
   /** Offset of the first element within the buffer object */
   unsigned int offset;
};

struct brw_query_object {
   struct gl_query_object Base;

   /** Last query BO associated with this query. */
   struct brw_bo *bo;

   /** Last index in bo with query data for this object. */
   int last_index;

   /** True if we know the batch has been flushed since we ended the query. */
   bool flushed;
};

enum brw_gpu_ring {
   UNKNOWN_RING,
   RENDER_RING,
   BLT_RING,
};

struct intel_batchbuffer {
   /** Current batchbuffer being queued up. */
   struct brw_bo *bo;
   /** Last BO submitted to the hardware.  Used for glFinish(). */
   struct brw_bo *last_bo;

#ifdef DEBUG
   uint16_t emit, total;
#endif
   uint16_t reserved_space;
   uint32_t *map_next;
   uint32_t *map;
   uint32_t *cpu_map;
#define BATCH_SZ (8192*sizeof(uint32_t))

   uint32_t state_batch_offset;
   enum brw_gpu_ring ring;
   bool needs_sol_reset;
   bool state_base_address_emitted;

   struct drm_i915_gem_relocation_entry *relocs;
   int reloc_count;
   int reloc_array_size;
   /** The validation list */
   struct drm_i915_gem_exec_object2 *exec_objects;
   struct brw_bo **exec_bos;
   int exec_count;
   int exec_array_size;
   /** The amount of aperture space (in bytes) used by all exec_bos */
   int aperture_space;

   struct {
      uint32_t *map_next;
      int reloc_count;
      int exec_count;
   } saved;

   /** Map from batch offset to brw_state_batch data (with DEBUG_BATCH) */
   struct hash_table *state_batch_sizes;
};

#define BRW_MAX_XFB_STREAMS 4

struct brw_transform_feedback_object {
   struct gl_transform_feedback_object base;

   /** A buffer to hold SO_WRITE_OFFSET(n) values while paused. */
   struct brw_bo *offset_bo;

   /** If true, SO_WRITE_OFFSET(n) should be reset to zero at next use. */
   bool zero_offsets;

   /** The most recent primitive mode (GL_TRIANGLES/GL_POINTS/GL_LINES). */
   GLenum primitive_mode;

   /**
    * The maximum number of vertices that we can write without overflowing
    * any of the buffers currently being used for transform feedback.
    */
   unsigned max_index;

   /**
    * Count of primitives generated during this transform feedback operation.
    *  @{
    */
   uint64_t prims_generated[BRW_MAX_XFB_STREAMS];
   struct brw_bo *prim_count_bo;
   unsigned prim_count_buffer_index; /**< in number of uint64_t units */
   /** @} */

   /**
    * Number of vertices written between last Begin/EndTransformFeedback().
    *
    * Used to implement DrawTransformFeedback().
    */
   uint64_t vertices_written[BRW_MAX_XFB_STREAMS];
   bool vertices_written_valid;
};

/**
 * Data shared between each programmable stage in the pipeline (vs, gs, and
 * wm).
 */
struct brw_stage_state
{
   gl_shader_stage stage;
   struct brw_stage_prog_data *prog_data;

   /**
    * Optional scratch buffer used to store spilled register values and
    * variably-indexed GRF arrays.
    *
    * The contents of this buffer are short-lived so the same memory can be
    * re-used at will for multiple shader programs (executed by the same fixed
    * function).  However reusing a scratch BO for which shader invocations
    * are still in flight with a per-thread scratch slot size other than the
    * original can cause threads with different scratch slot size and FFTID
    * (which may be executed in parallel depending on the shader stage and
    * hardware generation) to map to an overlapping region of the scratch
    * space, which can potentially lead to mutual scratch space corruption.
    * For that reason if you borrow this scratch buffer you should only be
    * using the slot size given by the \c per_thread_scratch member below,
    * unless you're taking additional measures to synchronize thread execution
    * across slot size changes.
    */
   struct brw_bo *scratch_bo;

   /**
    * Scratch slot size allocated for each thread in the buffer object given
    * by \c scratch_bo.
    */
   uint32_t per_thread_scratch;

   /** Offset in the program cache to the program */
   uint32_t prog_offset;

   /** Offset in the batchbuffer to Gen4-5 pipelined state (VS/WM/GS_STATE). */
   uint32_t state_offset;

   struct brw_bo *push_const_bo; /* NULL if using the batchbuffer */
   uint32_t push_const_offset; /* Offset in the push constant BO or batch */
   int push_const_size; /* in 256-bit register increments */

   /* Binding table: pointers to SURFACE_STATE entries. */
   uint32_t bind_bo_offset;
   uint32_t surf_offset[BRW_MAX_SURFACES];

   /** SAMPLER_STATE count and table offset */
   uint32_t sampler_count;
   uint32_t sampler_offset;
};

enum brw_predicate_state {
   /* The first two states are used if we can determine whether to draw
    * without having to look at the values in the query object buffer. This
    * will happen if there is no conditional render in progress, if the query
    * object is already completed or if something else has already added
    * samples to the preliminary result such as via a BLT command.
    */
   BRW_PREDICATE_STATE_RENDER,
   BRW_PREDICATE_STATE_DONT_RENDER,
   /* In this case whether to draw or not depends on the result of an
    * MI_PREDICATE command so the predicate enable bit needs to be checked.
    */
   BRW_PREDICATE_STATE_USE_BIT,
   /* In this case, either MI_PREDICATE doesn't exist or we lack the
    * necessary kernel features to use it.  Stall for the query result.
    */
   BRW_PREDICATE_STATE_STALL_FOR_QUERY,
};

struct shader_times;

struct gen_l3_config;

enum brw_query_kind {
   OA_COUNTERS,
   PIPELINE_STATS
};

struct brw_perf_query_info
{
   enum brw_query_kind kind;
   const char *name;
   const char *guid;
   struct brw_perf_query_counter *counters;
   int n_counters;
   size_t data_size;

   /* OA specific */
   uint64_t oa_metrics_set_id;
   int oa_format;

   /* For indexing into the accumulator[] ... */
   int gpu_time_offset;
   int gpu_clock_offset;
   int a_offset;
   int b_offset;
   int c_offset;
};

/**
 * brw_context is derived from gl_context.
 */
struct brw_context
{
   struct gl_context ctx; /**< base class, must be first field */

   struct
   {
      uint32_t (*update_renderbuffer_surface)(struct brw_context *brw,
                                              struct gl_renderbuffer *rb,
                                              uint32_t flags, unsigned unit,
                                              uint32_t surf_index);
      void (*emit_null_surface_state)(struct brw_context *brw,
                                      unsigned width,
                                      unsigned height,
                                      unsigned samples,
                                      uint32_t *out_offset);

      /**
       * Send the appropriate state packets to configure depth, stencil, and
       * HiZ buffers (i965+ only)
       */
      void (*emit_depth_stencil_hiz)(struct brw_context *brw,
                                     struct intel_mipmap_tree *depth_mt,
                                     uint32_t depth_offset,
                                     uint32_t depthbuffer_format,
                                     uint32_t depth_surface_type,
                                     struct intel_mipmap_tree *stencil_mt,
                                     bool hiz, bool separate_stencil,
                                     uint32_t width, uint32_t height,
                                     uint32_t tile_x, uint32_t tile_y);

      /**
       * Emit an MI_REPORT_PERF_COUNT command packet.
       *
       * This asks the GPU to write a report of the current OA counter values
       * into @bo at the given offset and containing the given @report_id
       * which we can cross-reference when parsing the report (gen7+ only).
       */
      void (*emit_mi_report_perf_count)(struct brw_context *brw,
                                        struct brw_bo *bo,
                                        uint32_t offset_in_bytes,
                                        uint32_t report_id);
   } vtbl;

   struct brw_bufmgr *bufmgr;

   uint32_t hw_ctx;

   /** BO for post-sync nonzero writes for gen6 workaround. */
   struct brw_bo *workaround_bo;
   uint8_t pipe_controls_since_last_cs_stall;

   /**
    * Set of struct brw_bo * that have been rendered to within this batchbuffer
    * and would need flushing before being used from another cache domain that
    * isn't coherent with it (i.e. the sampler).
    */
   struct set *render_cache;

   /**
    * Number of resets observed in the system at context creation.
    *
    * This is tracked in the context so that we can determine that another
    * reset has occurred.
    */
   uint32_t reset_count;

   struct intel_batchbuffer batch;
   bool no_batch_wrap;

   struct {
      struct brw_bo *bo;
      void *map;
      uint32_t next_offset;
   } upload;

   /**
    * Set if rendering has occurred to the drawable's front buffer.
    *
    * This is used in the DRI2 case to detect that glFlush should also copy
    * the contents of the fake front buffer to the real front buffer.
    */
   bool front_buffer_dirty;

   /** Framerate throttling: @{ */
   struct brw_bo *throttle_batch[2];

   /* Limit the number of outstanding SwapBuffers by waiting for an earlier
    * frame of rendering to complete. This gives a very precise cap to the
    * latency between input and output such that rendering never gets more
    * than a frame behind the user. (With the caveat that we technically are
    * not using the SwapBuffers itself as a barrier but the first batch
    * submitted afterwards, which may be immediately prior to the next
    * SwapBuffers.)
    */
   bool need_swap_throttle;

   /** General throttling, not caught by throttling between SwapBuffers */
   bool need_flush_throttle;
   /** @} */

   GLuint stats_wm;

   /**
    * drirc options:
    * @{
    */
   bool no_rast;
   bool always_flush_batch;
   bool always_flush_cache;
   bool disable_throttling;
   bool precompile;
   bool dual_color_blend_by_location;

   driOptionCache optionCache;
   /** @} */

   GLuint primitive; /**< Hardware primitive, such as _3DPRIM_TRILIST. */

   GLenum reduced_primitive;

   /**
    * Set if we're either a debug context or the INTEL_DEBUG=perf environment
    * variable is set, this is the flag indicating to do expensive work that
    * might lead to a perf_debug() call.
    */
   bool perf_debug;

   uint64_t max_gtt_map_object_size;

   int gen;
   int gt;

   bool is_g4x;
   bool is_baytrail;
   bool is_haswell;
   bool is_cherryview;
   bool is_broxton;

   bool has_hiz;
   bool has_separate_stencil;
   bool must_use_separate_stencil;
   bool has_llc;
   bool has_swizzling;
   bool has_surface_tile_offset;
   bool has_compr4;
   bool has_negative_rhw_bug;
   bool has_pln;
   bool no_simd8;

   /**
    * Some versions of Gen hardware don't do centroid interpolation correctly
    * on unlit pixels, causing incorrect values for derivatives near triangle
    * edges.  Enabling this flag causes the fragment shader to use
    * non-centroid interpolation for unlit pixels, at the expense of two extra
    * fragment shader instructions.
    */
   bool needs_unlit_centroid_workaround;

   /** Derived stencil states. */
   bool stencil_enabled;
   bool stencil_two_sided;
   bool stencil_write_enabled;
   /** Derived polygon state. */
   bool polygon_front_bit; /**< 0=GL_CCW, 1=GL_CW */

   struct isl_device isl_dev;

   struct blorp_context blorp;

   GLuint NewGLState;
   struct {
      struct brw_state_flags pipelines[BRW_NUM_PIPELINES];
   } state;

   enum brw_pipeline last_pipeline;

   struct brw_cache cache;

   /** IDs for meta stencil blit shader programs. */
   struct gl_shader_program *meta_stencil_blit_programs[2];

   /* Whether a meta-operation is in progress. */
   bool meta_in_progress;

   /* Whether the last depth/stencil packets were both NULL. */
   bool no_depth_or_stencil;

   /* The last PMA stall bits programmed. */
   uint32_t pma_stall_bits;

   struct {
      struct {
         /** The value of gl_BaseVertex for the current _mesa_prim. */
         int gl_basevertex;

         /** The value of gl_BaseInstance for the current _mesa_prim. */
         int gl_baseinstance;
      } params;

      /**
       * Buffer and offset used for GL_ARB_shader_draw_parameters
       * (for now, only gl_BaseVertex).
       */
      struct brw_bo *draw_params_bo;
      uint32_t draw_params_offset;

      /**
       * The value of gl_DrawID for the current _mesa_prim. This always comes
       * in from it's own vertex buffer since it's not part of the indirect
       * draw parameters.
       */
      int gl_drawid;
      struct brw_bo *draw_id_bo;
      uint32_t draw_id_offset;
   } draw;

   struct {
      /**
       * For gl_NumWorkGroups: If num_work_groups_bo is non NULL, then it is
       * an indirect call, and num_work_groups_offset is valid. Otherwise,
       * num_work_groups is set based on glDispatchCompute.
       */
      struct brw_bo *num_work_groups_bo;
      GLintptr num_work_groups_offset;
      const GLuint *num_work_groups;
   } compute;

   struct {
      struct brw_vertex_element inputs[VERT_ATTRIB_MAX];
      struct brw_vertex_buffer buffers[VERT_ATTRIB_MAX];

      struct brw_vertex_element *enabled[VERT_ATTRIB_MAX];
      GLuint nr_enabled;
      GLuint nr_buffers;

      /* Summary of size and varying of active arrays, so we can check
       * for changes to this state:
       */
      bool index_bounds_valid;
      unsigned int min_index, max_index;

      /* Offset from start of vertex buffer so we can avoid redefining
       * the same VB packed over and over again.
       */
      unsigned int start_vertex_bias;

      /**
       * Certain vertex attribute formats aren't natively handled by the
       * hardware and require special VS code to fix up their values.
       *
       * These bitfields indicate which workarounds are needed.
       */
      uint8_t attrib_wa_flags[VERT_ATTRIB_MAX];
   } vb;

   struct {
      /**
       * Index buffer for this draw_prims call.
       *
       * Updates are signaled by BRW_NEW_INDICES.
       */
      const struct _mesa_index_buffer *ib;

      /* Updates are signaled by BRW_NEW_INDEX_BUFFER. */
      struct brw_bo *bo;
      uint32_t size;
      unsigned index_size;

      /* Offset to index buffer index to use in CMD_3D_PRIM so that we can
       * avoid re-uploading the IB packet over and over if we're actually
       * referencing the same index buffer.
       */
      unsigned int start_vertex_offset;
   } ib;

   /* Active vertex program:
    */
   const struct gl_program *vertex_program;
   const struct gl_program *geometry_program;
   const struct gl_program *tess_ctrl_program;
   const struct gl_program *tess_eval_program;
   const struct gl_program *fragment_program;
   const struct gl_program *compute_program;

   /**
    * Number of samples in ctx->DrawBuffer, updated by BRW_NEW_NUM_SAMPLES so
    * that we don't have to reemit that state every time we change FBOs.
    */
   int num_samples;

   /* BRW_NEW_URB_ALLOCATIONS:
    */
   struct {
      GLuint vsize;		/* vertex size plus header in urb registers */
      GLuint gsize;	        /* GS output size in urb registers */
      GLuint hsize;             /* Tessellation control output size in urb registers */
      GLuint dsize;             /* Tessellation evaluation output size in urb registers */
      GLuint csize;		/* constant buffer size in urb registers */
      GLuint sfsize;		/* setup data size in urb registers */

      bool constrained;

      GLuint nr_vs_entries;
      GLuint nr_hs_entries;
      GLuint nr_ds_entries;
      GLuint nr_gs_entries;
      GLuint nr_clip_entries;
      GLuint nr_sf_entries;
      GLuint nr_cs_entries;

      GLuint vs_start;
      GLuint hs_start;
      GLuint ds_start;
      GLuint gs_start;
      GLuint clip_start;
      GLuint sf_start;
      GLuint cs_start;
      /**
       * URB size in the current configuration.  The units this is expressed
       * in are somewhat inconsistent, see gen_device_info::urb::size.
       *
       * FINISHME: Represent the URB size consistently in KB on all platforms.
       */
      GLuint size;

      /* True if the most recently sent _3DSTATE_URB message allocated
       * URB space for the GS.
       */
      bool gs_present;

      /* True if the most recently sent _3DSTATE_URB message allocated
       * URB space for the HS and DS.
       */
      bool tess_present;
   } urb;


   /* BRW_NEW_PUSH_CONSTANT_ALLOCATION */
   struct {
      GLuint wm_start;  /**< pos of first wm const in CURBE buffer */
      GLuint wm_size;   /**< number of float[4] consts, multiple of 16 */
      GLuint clip_start;
      GLuint clip_size;
      GLuint vs_start;
      GLuint vs_size;
      GLuint total_size;

      /**
       * Pointer to the (intel_upload.c-generated) BO containing the uniforms
       * for upload to the CURBE.
       */
      struct brw_bo *curbe_bo;
      /** Offset within curbe_bo of space for current curbe entry */
      GLuint curbe_offset;
   } curbe;

   /**
    * Layout of vertex data exiting the geometry portion of the pipleine.
    * This comes from the last enabled shader stage (GS, DS, or VS).
    *
    * BRW_NEW_VUE_MAP_GEOM_OUT is flagged when the VUE map changes.
    */
   struct brw_vue_map vue_map_geom_out;

   struct {
      struct brw_stage_state base;
   } vs;

   struct {
      struct brw_stage_state base;
   } tcs;

   struct {
      struct brw_stage_state base;
   } tes;

   struct {
      struct brw_stage_state base;

      /**
       * True if the 3DSTATE_GS command most recently emitted to the 3D
       * pipeline enabled the GS; false otherwise.
       */
      bool enabled;
   } gs;

   struct {
      struct brw_ff_gs_prog_data *prog_data;

      bool prog_active;
      /** Offset in the program cache to the CLIP program pre-gen6 */
      uint32_t prog_offset;
      uint32_t state_offset;

      uint32_t bind_bo_offset;
      /**
       * Surface offsets for the binding table. We only need surfaces to
       * implement transform feedback so BRW_MAX_SOL_BINDINGS is all that we
       * need in this case.
       */
      uint32_t surf_offset[BRW_MAX_SOL_BINDINGS];
   } ff_gs;

   struct {
      struct brw_clip_prog_data *prog_data;

      /** Offset in the program cache to the CLIP program pre-gen6 */
      uint32_t prog_offset;

      /* Offset in the batch to the CLIP state on pre-gen6. */
      uint32_t state_offset;

      /* As of gen6, this is the offset in the batch to the CLIP VP,
       * instead of vp_bo.
       */
      uint32_t vp_offset;

      /**
       * The number of viewports to use.  If gl_ViewportIndex is written,
       * we can have up to ctx->Const.MaxViewports viewports.  If not,
       * the viewport index is always 0, so we can only emit one.
       */
      uint8_t viewport_count;
   } clip;


   struct {
      struct brw_sf_prog_data *prog_data;

      /** Offset in the program cache to the CLIP program pre-gen6 */
      uint32_t prog_offset;
      uint32_t state_offset;
      uint32_t vp_offset;
   } sf;

   struct {
      struct brw_stage_state base;

      GLuint render_surf;

      /**
       * Buffer object used in place of multisampled null render targets on
       * Gen6.  See brw_emit_null_surface_state().
       */
      struct brw_bo *multisampled_null_render_target_bo;
      uint32_t fast_clear_op;

      float offset_clamp;
   } wm;

   struct {
      struct brw_stage_state base;
   } cs;

   struct {
      uint32_t state_offset;
      uint32_t blend_state_offset;
      uint32_t depth_stencil_state_offset;
      uint32_t vp_offset;
   } cc;

   struct {
      struct brw_query_object *obj;
      bool begin_emitted;
   } query;

   struct {
      enum brw_predicate_state state;
      bool supported;
   } predicate;

   struct {
      /* Variables referenced in the XML meta data for OA performance
       * counters, e.g in the normalization equations.
       *
       * All uint64_t for consistent operand types in generated code
       */
      struct {
         uint64_t timestamp_frequency; /** $GpuTimestampFrequency */
         uint64_t n_eus;               /** $EuCoresTotalCount */
         uint64_t n_eu_slices;         /** $EuSlicesTotalCount */
         uint64_t n_eu_sub_slices;     /** $EuSubslicesTotalCount */
         uint64_t eu_threads_count;    /** $EuThreadsCount */
         uint64_t slice_mask;          /** $SliceMask */
         uint64_t subslice_mask;       /** $SubsliceMask */
         uint64_t gt_min_freq;         /** $GpuMinFrequency */
         uint64_t gt_max_freq;         /** $GpuMaxFrequency */
      } sys_vars;

      /* OA metric sets, indexed by GUID, as know by Mesa at build time,
       * to cross-reference with the GUIDs of configs advertised by the
       * kernel at runtime
       */
      struct hash_table *oa_metrics_table;

      struct brw_perf_query_info *queries;
      int n_queries;

      /* The i915 perf stream we open to setup + enable the OA counters */
      int oa_stream_fd;

      /* An i915 perf stream fd gives exclusive access to the OA unit that will
       * report counter snapshots for a specific counter set/profile in a
       * specific layout/format so we can only start OA queries that are
       * compatible with the currently open fd...
       */
      int current_oa_metrics_set_id;
      int current_oa_format;

      /* List of buffers containing OA reports */
      struct exec_list sample_buffers;

      /* Cached list of empty sample buffers */
      struct exec_list free_sample_buffers;

      int n_active_oa_queries;
      int n_active_pipeline_stats_queries;

      /* The number of queries depending on running OA counters which
       * extends beyond brw_end_perf_query() since we need to wait until
       * the last MI_RPC command has parsed by the GPU.
       *
       * Accurate accounting is important here as emitting an
       * MI_REPORT_PERF_COUNT command while the OA unit is disabled will
       * effectively hang the gpu.
       */
      int n_oa_users;

      /* To help catch an spurious problem with the hardware or perf
       * forwarding samples, we emit each MI_REPORT_PERF_COUNT command
       * with a unique ID that we can explicitly check for...
       */
      int next_query_start_report_id;

      /**
       * An array of queries whose results haven't yet been assembled
       * based on the data in buffer objects.
       *
       * These may be active, or have already ended.  However, the
       * results have not been requested.
       */
      struct brw_perf_query_object **unaccumulated;
      int unaccumulated_elements;
      int unaccumulated_array_size;

      /* The total number of query objects so we can relinquish
       * our exclusive access to perf if the application deletes
       * all of its objects. (NB: We only disable perf while
       * there are no active queries)
       */
      int n_query_instances;
   } perfquery;

   int num_atoms[BRW_NUM_PIPELINES];
   const struct brw_tracked_state render_atoms[76];
   const struct brw_tracked_state compute_atoms[11];

   const enum isl_format *mesa_to_isl_render_format;
   const bool *mesa_format_supports_render;

   /* PrimitiveRestart */
   struct {
      bool in_progress;
      bool enable_cut_index;
   } prim_restart;

   /** Computed depth/stencil/hiz state from the current attached
    * renderbuffers, valid only during the drawing state upload loop after
    * brw_workaround_depthstencil_alignment().
    */
   struct {
      /* Inter-tile (page-aligned) byte offsets. */
      uint32_t depth_offset;
      /* Intra-tile x,y offsets for drawing to combined depth-stencil. Only
       * used for Gen < 6.
       */
      uint32_t tile_x, tile_y;
   } depthstencil;

   uint32_t num_instances;
   int basevertex;
   int baseinstance;

   struct {
      const struct gen_l3_config *config;
   } l3;

   struct {
      struct brw_bo *bo;
      const char **names;
      int *ids;
      enum shader_time_shader_type *types;
      struct shader_times *cumulative;
      int num_entries;
      int max_entries;
      double report_time;
   } shader_time;

   struct brw_fast_clear_state *fast_clear_state;

   /* Array of flags telling if auxiliary buffer is disabled for corresponding
    * renderbuffer. If draw_aux_buffer_disabled[i] is set then use of
    * auxiliary buffer for gl_framebuffer::_ColorDrawBuffers[i] is
    * disabled.
    * This is needed in case the same underlying buffer is also configured
    * to be sampled but with a format that the sampling engine can't treat
    * compressed or fast cleared.
    */
   bool draw_aux_buffer_disabled[MAX_DRAW_BUFFERS];

   __DRIcontext *driContext;
   struct intel_screen *screen;
};

/* brw_clear.c */
extern void intelInitClearFuncs(struct dd_function_table *functions);

/*======================================================================
 * brw_context.c
 */
extern const char *const brw_vendor_string;

extern const char *
brw_get_renderer_string(const struct intel_screen *screen);

enum {
   DRI_CONF_BO_REUSE_DISABLED,
   DRI_CONF_BO_REUSE_ALL
};

void intel_update_renderbuffers(__DRIcontext *context,
                                __DRIdrawable *drawable);
void intel_prepare_render(struct brw_context *brw);

void brw_predraw_resolve_inputs(struct brw_context *brw);

void intel_resolve_for_dri2_flush(struct brw_context *brw,
                                  __DRIdrawable *drawable);

GLboolean brwCreateContext(gl_api api,
		      const struct gl_config *mesaVis,
		      __DRIcontext *driContextPriv,
                      unsigned major_version,
                      unsigned minor_version,
                      uint32_t flags,
                      bool notify_reset,
                      unsigned *error,
		      void *sharedContextPrivate);

/*======================================================================
 * brw_misc_state.c
 */
void
brw_meta_resolve_color(struct brw_context *brw,
                       struct intel_mipmap_tree *mt);

/*======================================================================
 * brw_misc_state.c
 */
void brw_workaround_depthstencil_alignment(struct brw_context *brw,
                                           GLbitfield clear_mask);

/* brw_object_purgeable.c */
void brw_init_object_purgeable_functions(struct dd_function_table *functions);

/*======================================================================
 * brw_queryobj.c
 */
void brw_init_common_queryobj_functions(struct dd_function_table *functions);
void gen4_init_queryobj_functions(struct dd_function_table *functions);
void brw_emit_query_begin(struct brw_context *brw);
void brw_emit_query_end(struct brw_context *brw);
void brw_query_counter(struct gl_context *ctx, struct gl_query_object *q);
bool brw_is_query_pipelined(struct brw_query_object *query);
uint64_t brw_timebase_scale(struct brw_context *brw, uint64_t gpu_timestamp);
uint64_t brw_raw_timestamp_delta(struct brw_context *brw,
                                 uint64_t time0, uint64_t time1);

/** gen6_queryobj.c */
void gen6_init_queryobj_functions(struct dd_function_table *functions);
void brw_write_timestamp(struct brw_context *brw, struct brw_bo *bo, int idx);
void brw_write_depth_count(struct brw_context *brw, struct brw_bo *bo, int idx);

/** hsw_queryobj.c */
void hsw_overflow_result_to_gpr0(struct brw_context *brw,
                                 struct brw_query_object *query,
                                 int count);
void hsw_init_queryobj_functions(struct dd_function_table *functions);

/** brw_conditional_render.c */
void brw_init_conditional_render_functions(struct dd_function_table *functions);
bool brw_check_conditional_render(struct brw_context *brw);

/** intel_batchbuffer.c */
void brw_load_register_mem(struct brw_context *brw,
                           uint32_t reg,
                           struct brw_bo *bo,
                           uint32_t read_domains, uint32_t write_domain,
                           uint32_t offset);
void brw_load_register_mem64(struct brw_context *brw,
                             uint32_t reg,
                             struct brw_bo *bo,
                             uint32_t read_domains, uint32_t write_domain,
                             uint32_t offset);
void brw_store_register_mem32(struct brw_context *brw,
                              struct brw_bo *bo, uint32_t reg, uint32_t offset);
void brw_store_register_mem64(struct brw_context *brw,
                              struct brw_bo *bo, uint32_t reg, uint32_t offset);
void brw_load_register_imm32(struct brw_context *brw,
                             uint32_t reg, uint32_t imm);
void brw_load_register_imm64(struct brw_context *brw,
                             uint32_t reg, uint64_t imm);
void brw_load_register_reg(struct brw_context *brw, uint32_t src,
                           uint32_t dest);
void brw_load_register_reg64(struct brw_context *brw, uint32_t src,
                             uint32_t dest);
void brw_store_data_imm32(struct brw_context *brw, struct brw_bo *bo,
                          uint32_t offset, uint32_t imm);
void brw_store_data_imm64(struct brw_context *brw, struct brw_bo *bo,
                          uint32_t offset, uint64_t imm);

/*======================================================================
 * intel_tex_validate.c
 */
void brw_validate_textures( struct brw_context *brw );


/*======================================================================
 * brw_program.c
 */
static inline bool
key_debug(struct brw_context *brw, const char *name, int a, int b)
{
   if (a != b) {
      perf_debug("  %s %d->%d\n", name, a, b);
      return true;
   }
   return false;
}

void brwInitFragProgFuncs( struct dd_function_table *functions );

void brw_get_scratch_bo(struct brw_context *brw,
			struct brw_bo **scratch_bo, int size);
void brw_alloc_stage_scratch(struct brw_context *brw,
                             struct brw_stage_state *stage_state,
                             unsigned per_thread_size,
                             unsigned thread_count);
void brw_init_shader_time(struct brw_context *brw);
int brw_get_shader_time_index(struct brw_context *brw,
                              struct gl_program *prog,
                              enum shader_time_shader_type type,
                              bool is_glsl_sh);
void brw_collect_and_report_shader_time(struct brw_context *brw);
void brw_destroy_shader_time(struct brw_context *brw);

/* brw_urb.c
 */
void brw_calculate_urb_fence(struct brw_context *brw, unsigned csize,
                             unsigned vsize, unsigned sfsize);
void brw_upload_urb_fence(struct brw_context *brw);

/* brw_curbe.c
 */
void brw_upload_cs_urb_state(struct brw_context *brw);

/* brw_vs.c */
gl_clip_plane *brw_select_clip_planes(struct gl_context *ctx);

/* brw_draw_upload.c */
unsigned brw_get_vertex_surface_type(struct brw_context *brw,
                                     const struct gl_vertex_array *glarray);

static inline unsigned
brw_get_index_type(unsigned index_size)
{
   /* The hw needs 0x00, 0x01, and 0x02 for ubyte, ushort, and uint,
    * respectively.
    */
   return index_size >> 1;
}

void brw_prepare_vertices(struct brw_context *brw);

/* brw_wm_surface_state.c */
void brw_create_constant_surface(struct brw_context *brw,
                                 struct brw_bo *bo,
                                 uint32_t offset,
                                 uint32_t size,
                                 uint32_t *out_offset);
void brw_create_buffer_surface(struct brw_context *brw,
                               struct brw_bo *bo,
                               uint32_t offset,
                               uint32_t size,
                               uint32_t *out_offset);
void brw_update_buffer_texture_surface(struct gl_context *ctx,
                                       unsigned unit,
                                       uint32_t *surf_offset);
void
brw_update_sol_surface(struct brw_context *brw,
                       struct gl_buffer_object *buffer_obj,
                       uint32_t *out_offset, unsigned num_vector_components,
                       unsigned stride_dwords, unsigned offset_dwords);
void brw_upload_ubo_surfaces(struct brw_context *brw, struct gl_program *prog,
                             struct brw_stage_state *stage_state,
                             struct brw_stage_prog_data *prog_data);
void brw_upload_abo_surfaces(struct brw_context *brw,
                             const struct gl_program *prog,
                             struct brw_stage_state *stage_state,
                             struct brw_stage_prog_data *prog_data);
void brw_upload_image_surfaces(struct brw_context *brw,
                               const struct gl_program *prog,
                               struct brw_stage_state *stage_state,
                               struct brw_stage_prog_data *prog_data);

/* brw_surface_formats.c */
void intel_screen_init_surface_formats(struct intel_screen *screen);
void brw_init_surface_formats(struct brw_context *brw);
bool brw_render_target_supported(struct brw_context *brw,
                                 struct gl_renderbuffer *rb);
uint32_t brw_depth_format(struct brw_context *brw, mesa_format format);

/* brw_performance_query.c */
void brw_init_performance_queries(struct brw_context *brw);

/* intel_extensions.c */
extern void intelInitExtensions(struct gl_context *ctx);

/* intel_state.c */
extern int intel_translate_shadow_compare_func(GLenum func);
extern int intel_translate_compare_func(GLenum func);
extern int intel_translate_stencil_op(GLenum op);
extern int intel_translate_logic_op(GLenum opcode);

/* brw_sync.c */
void brw_init_syncobj_functions(struct dd_function_table *functions);

/* gen6_sol.c */
struct gl_transform_feedback_object *
brw_new_transform_feedback(struct gl_context *ctx, GLuint name);
void
brw_delete_transform_feedback(struct gl_context *ctx,
                              struct gl_transform_feedback_object *obj);
void
brw_begin_transform_feedback(struct gl_context *ctx, GLenum mode,
			     struct gl_transform_feedback_object *obj);
void
brw_end_transform_feedback(struct gl_context *ctx,
                           struct gl_transform_feedback_object *obj);
void
brw_pause_transform_feedback(struct gl_context *ctx,
                             struct gl_transform_feedback_object *obj);
void
brw_resume_transform_feedback(struct gl_context *ctx,
                              struct gl_transform_feedback_object *obj);
void
brw_save_primitives_written_counters(struct brw_context *brw,
                                     struct brw_transform_feedback_object *obj);
void
brw_compute_xfb_vertices_written(struct brw_context *brw,
                                 struct brw_transform_feedback_object *obj);
GLsizei
brw_get_transform_feedback_vertex_count(struct gl_context *ctx,
                                        struct gl_transform_feedback_object *obj,
                                        GLuint stream);

/* gen7_sol_state.c */
void
gen7_begin_transform_feedback(struct gl_context *ctx, GLenum mode,
                              struct gl_transform_feedback_object *obj);
void
gen7_end_transform_feedback(struct gl_context *ctx,
			    struct gl_transform_feedback_object *obj);
void
gen7_pause_transform_feedback(struct gl_context *ctx,
                              struct gl_transform_feedback_object *obj);
void
gen7_resume_transform_feedback(struct gl_context *ctx,
                               struct gl_transform_feedback_object *obj);

/* hsw_sol.c */
void
hsw_begin_transform_feedback(struct gl_context *ctx, GLenum mode,
                             struct gl_transform_feedback_object *obj);
void
hsw_end_transform_feedback(struct gl_context *ctx,
                           struct gl_transform_feedback_object *obj);
void
hsw_pause_transform_feedback(struct gl_context *ctx,
                             struct gl_transform_feedback_object *obj);
void
hsw_resume_transform_feedback(struct gl_context *ctx,
                              struct gl_transform_feedback_object *obj);

/* brw_blorp_blit.cpp */
GLbitfield
brw_blorp_framebuffer(struct brw_context *brw,
                      struct gl_framebuffer *readFb,
                      struct gl_framebuffer *drawFb,
                      GLint srcX0, GLint srcY0, GLint srcX1, GLint srcY1,
                      GLint dstX0, GLint dstY0, GLint dstX1, GLint dstY1,
                      GLbitfield mask, GLenum filter);

bool
brw_blorp_copytexsubimage(struct brw_context *brw,
                          struct gl_renderbuffer *src_rb,
                          struct gl_texture_image *dst_image,
                          int slice,
                          int srcX0, int srcY0,
                          int dstX0, int dstY0,
                          int width, int height);

void
gen6_get_sample_position(struct gl_context *ctx,
                         struct gl_framebuffer *fb,
                         GLuint index,
                         GLfloat *result);
void
gen6_set_sample_maps(struct gl_context *ctx);

/* gen8_multisample_state.c */
void gen8_emit_3dstate_multisample(struct brw_context *brw, unsigned num_samp);
void gen8_emit_3dstate_sample_pattern(struct brw_context *brw);

/* gen7_urb.c */
void
gen7_emit_push_constant_state(struct brw_context *brw, unsigned vs_size,
                              unsigned hs_size, unsigned ds_size,
                              unsigned gs_size, unsigned fs_size);

void
gen6_upload_urb(struct brw_context *brw, unsigned vs_size,
                bool gs_present, unsigned gs_size);
void
gen7_upload_urb(struct brw_context *brw, unsigned vs_size,
                bool gs_present, bool tess_present);

/* brw_reset.c */
extern GLenum
brw_get_graphics_reset_status(struct gl_context *ctx);
void
brw_check_for_reset(struct brw_context *brw);

/* brw_compute.c */
extern void
brw_init_compute_functions(struct dd_function_table *functions);

/*======================================================================
 * Inline conversion functions.  These are better-typed than the
 * macros used previously:
 */
static inline struct brw_context *
brw_context( struct gl_context *ctx )
{
   return (struct brw_context *)ctx;
}

static inline struct brw_program *
brw_program(struct gl_program *p)
{
   return (struct brw_program *) p;
}

static inline const struct brw_program *
brw_program_const(const struct gl_program *p)
{
   return (const struct brw_program *) p;
}

static inline bool
brw_depth_writes_enabled(const struct brw_context *brw)
{
   const struct gl_context *ctx = &brw->ctx;

   /* We consider depth writes disabled if the depth function is GL_EQUAL,
    * because it would just overwrite the existing depth value with itself.
    *
    * These bonus depth writes not only use bandwidth, but they also can
    * prevent early depth processing.  For example, if the pixel shader
    * discards, the hardware must invoke the to determine whether or not
    * to do the depth write.  If writes are disabled, we may still be able
    * to do the depth test before the shader, and skip the shader execution.
    *
    * The Broadwell 3DSTATE_WM_DEPTH_STENCIL documentation also contains
    * a programming note saying to disable depth writes for EQUAL.
    */
   return ctx->Depth.Test && ctx->Depth.Mask && ctx->Depth.Func != GL_EQUAL;
}

void
brw_emit_depthbuffer(struct brw_context *brw);

void
brw_emit_depth_stencil_hiz(struct brw_context *brw,
                           struct intel_mipmap_tree *depth_mt,
                           uint32_t depth_offset, uint32_t depthbuffer_format,
                           uint32_t depth_surface_type,
                           struct intel_mipmap_tree *stencil_mt,
                           bool hiz, bool separate_stencil,
                           uint32_t width, uint32_t height,
                           uint32_t tile_x, uint32_t tile_y);

void
gen6_emit_depth_stencil_hiz(struct brw_context *brw,
                            struct intel_mipmap_tree *depth_mt,
                            uint32_t depth_offset, uint32_t depthbuffer_format,
                            uint32_t depth_surface_type,
                            struct intel_mipmap_tree *stencil_mt,
                            bool hiz, bool separate_stencil,
                            uint32_t width, uint32_t height,
                            uint32_t tile_x, uint32_t tile_y);

void
gen7_emit_depth_stencil_hiz(struct brw_context *brw,
                            struct intel_mipmap_tree *depth_mt,
                            uint32_t depth_offset, uint32_t depthbuffer_format,
                            uint32_t depth_surface_type,
                            struct intel_mipmap_tree *stencil_mt,
                            bool hiz, bool separate_stencil,
                            uint32_t width, uint32_t height,
                            uint32_t tile_x, uint32_t tile_y);
void
gen8_emit_depth_stencil_hiz(struct brw_context *brw,
                            struct intel_mipmap_tree *depth_mt,
                            uint32_t depth_offset, uint32_t depthbuffer_format,
                            uint32_t depth_surface_type,
                            struct intel_mipmap_tree *stencil_mt,
                            bool hiz, bool separate_stencil,
                            uint32_t width, uint32_t height,
                            uint32_t tile_x, uint32_t tile_y);

uint32_t get_hw_prim_for_gl_prim(int mode);

void
gen6_upload_push_constants(struct brw_context *brw,
                           const struct gl_program *prog,
                           const struct brw_stage_prog_data *prog_data,
                           struct brw_stage_state *stage_state);

bool
gen9_use_linear_1d_layout(const struct brw_context *brw,
                          const struct intel_mipmap_tree *mt);

/* brw_pipe_control.c */
int brw_init_pipe_control(struct brw_context *brw,
			  const struct gen_device_info *info);
void brw_fini_pipe_control(struct brw_context *brw);

void brw_emit_pipe_control_flush(struct brw_context *brw, uint32_t flags);
void brw_emit_pipe_control_write(struct brw_context *brw, uint32_t flags,
                                 struct brw_bo *bo, uint32_t offset,
                                 uint64_t imm);
void brw_emit_end_of_pipe_sync(struct brw_context *brw, uint32_t flags);
void brw_emit_mi_flush(struct brw_context *brw);
void brw_emit_post_sync_nonzero_flush(struct brw_context *brw);
void brw_emit_depth_stall_flushes(struct brw_context *brw);
void gen7_emit_vs_workaround_flush(struct brw_context *brw);
void gen7_emit_cs_stall_flush(struct brw_context *brw);

/* brw_queryformat.c */
void brw_query_internal_format(struct gl_context *ctx, GLenum target,
                               GLenum internalFormat, GLenum pname,
                               GLint *params);

#ifdef __cplusplus
}
#endif

#endif