summaryrefslogtreecommitdiff
path: root/src/gallium/drivers/r600/r600_state_common.c
blob: b547d647cba1492b1b5c9036dde2f40b61d73d2f (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
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
/*
 * Copyright 2010 Red Hat Inc.
 *           2010 Jerome Glisse
 *
 * 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
 * on 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
 * THE AUTHOR(S) AND/OR THEIR 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: Dave Airlie <airlied@redhat.com>
 *          Jerome Glisse <jglisse@redhat.com>
 */
#include "r600_formats.h"
#include "r600_shader.h"
#include "r600d.h"

#include "util/u_draw_quad.h"
#include "util/u_index_modify.h"
#include "util/u_memory.h"
#include "util/u_upload_mgr.h"
#include "tgsi/tgsi_parse.h"
#include <byteswap.h>

#define R600_PRIM_RECTANGLE_LIST PIPE_PRIM_MAX

void r600_init_command_buffer(struct r600_command_buffer *cb, unsigned num_dw)
{
	cb->buf = CALLOC(1, 4 * num_dw);
	cb->max_num_dw = num_dw;
}

void r600_release_command_buffer(struct r600_command_buffer *cb)
{
	FREE(cb->buf);
}

void r600_init_atom(struct r600_context *rctx,
		    struct r600_atom *atom,
		    unsigned id,
		    void (*emit)(struct r600_context *ctx, struct r600_atom *state),
		    unsigned num_dw)
{
	assert(id < R600_NUM_ATOMS);
	assert(rctx->atoms[id] == NULL);
	rctx->atoms[id] = atom;
	atom->id = id;
	atom->emit = emit;
	atom->num_dw = num_dw;
	atom->dirty = false;
}

void r600_emit_cso_state(struct r600_context *rctx, struct r600_atom *atom)
{
	r600_emit_command_buffer(rctx->rings.gfx.cs, ((struct r600_cso_state*)atom)->cb);
}

void r600_emit_alphatest_state(struct r600_context *rctx, struct r600_atom *atom)
{
	struct radeon_winsys_cs *cs = rctx->rings.gfx.cs;
	struct r600_alphatest_state *a = (struct r600_alphatest_state*)atom;
	unsigned alpha_ref = a->sx_alpha_ref;

	if (rctx->chip_class >= EVERGREEN && a->cb0_export_16bpc) {
		alpha_ref &= ~0x1FFF;
	}

	r600_write_context_reg(cs, R_028410_SX_ALPHA_TEST_CONTROL,
			       a->sx_alpha_test_control |
			       S_028410_ALPHA_TEST_BYPASS(a->bypass));
	r600_write_context_reg(cs, R_028438_SX_ALPHA_REF, alpha_ref);
}

static void r600_texture_barrier(struct pipe_context *ctx)
{
	struct r600_context *rctx = (struct r600_context *)ctx;

	rctx->flags |= R600_CONTEXT_WAIT_3D_IDLE;
	rctx->flags |= R600_CONTEXT_INVAL_READ_CACHES;
	rctx->flags |= R600_CONTEXT_FLUSH_AND_INV;
}

static unsigned r600_conv_pipe_prim(unsigned prim)
{
	static const unsigned prim_conv[] = {
		V_008958_DI_PT_POINTLIST,
		V_008958_DI_PT_LINELIST,
		V_008958_DI_PT_LINELOOP,
		V_008958_DI_PT_LINESTRIP,
		V_008958_DI_PT_TRILIST,
		V_008958_DI_PT_TRISTRIP,
		V_008958_DI_PT_TRIFAN,
		V_008958_DI_PT_QUADLIST,
		V_008958_DI_PT_QUADSTRIP,
		V_008958_DI_PT_POLYGON,
		V_008958_DI_PT_LINELIST_ADJ,
		V_008958_DI_PT_LINESTRIP_ADJ,
		V_008958_DI_PT_TRILIST_ADJ,
		V_008958_DI_PT_TRISTRIP_ADJ,
		V_008958_DI_PT_RECTLIST
	};
	return prim_conv[prim];
}

/* common state between evergreen and r600 */

static void r600_bind_blend_state_internal(struct r600_context *rctx,
		struct r600_blend_state *blend, bool blend_disable)
{
	unsigned color_control;
	bool update_cb = false;

	rctx->alpha_to_one = blend->alpha_to_one;
	rctx->dual_src_blend = blend->dual_src_blend;

	if (!blend_disable) {
		r600_set_cso_state_with_cb(&rctx->blend_state, blend, &blend->buffer);
		color_control = blend->cb_color_control;
	} else {
		/* Blending is disabled. */
		r600_set_cso_state_with_cb(&rctx->blend_state, blend, &blend->buffer_no_blend);
		color_control = blend->cb_color_control_no_blend;
	}

	/* Update derived states. */
	if (rctx->cb_misc_state.blend_colormask != blend->cb_target_mask) {
		rctx->cb_misc_state.blend_colormask = blend->cb_target_mask;
		update_cb = true;
	}
	if (rctx->chip_class <= R700 &&
	    rctx->cb_misc_state.cb_color_control != color_control) {
		rctx->cb_misc_state.cb_color_control = color_control;
		update_cb = true;
	}
	if (rctx->cb_misc_state.dual_src_blend != blend->dual_src_blend) {
		rctx->cb_misc_state.dual_src_blend = blend->dual_src_blend;
		update_cb = true;
	}
	if (update_cb) {
		rctx->cb_misc_state.atom.dirty = true;
	}
}

static void r600_bind_blend_state(struct pipe_context *ctx, void *state)
{
	struct r600_context *rctx = (struct r600_context *)ctx;
	struct r600_blend_state *blend = (struct r600_blend_state *)state;

	if (blend == NULL)
		return;

	r600_bind_blend_state_internal(rctx, blend, rctx->force_blend_disable);
}

static void r600_set_blend_color(struct pipe_context *ctx,
				 const struct pipe_blend_color *state)
{
	struct r600_context *rctx = (struct r600_context *)ctx;

	rctx->blend_color.state = *state;
	rctx->blend_color.atom.dirty = true;
}

void r600_emit_blend_color(struct r600_context *rctx, struct r600_atom *atom)
{
	struct radeon_winsys_cs *cs = rctx->rings.gfx.cs;
	struct pipe_blend_color *state = &rctx->blend_color.state;

	r600_write_context_reg_seq(cs, R_028414_CB_BLEND_RED, 4);
	r600_write_value(cs, fui(state->color[0])); /* R_028414_CB_BLEND_RED */
	r600_write_value(cs, fui(state->color[1])); /* R_028418_CB_BLEND_GREEN */
	r600_write_value(cs, fui(state->color[2])); /* R_02841C_CB_BLEND_BLUE */
	r600_write_value(cs, fui(state->color[3])); /* R_028420_CB_BLEND_ALPHA */
}

void r600_emit_vgt_state(struct r600_context *rctx, struct r600_atom *atom)
{
	struct radeon_winsys_cs *cs = rctx->rings.gfx.cs;
	struct r600_vgt_state *a = (struct r600_vgt_state *)atom;

	r600_write_context_reg(cs, R_028A94_VGT_MULTI_PRIM_IB_RESET_EN, a->vgt_multi_prim_ib_reset_en);
	r600_write_context_reg(cs, R_02840C_VGT_MULTI_PRIM_IB_RESET_INDX, a->vgt_multi_prim_ib_reset_indx);
}

void r600_emit_vgt2_state(struct r600_context *rctx, struct r600_atom *atom)
{
	struct radeon_winsys_cs *cs = rctx->rings.gfx.cs;
	struct r600_vgt2_state *a = (struct r600_vgt2_state *)atom;

	r600_write_context_reg(cs, R_028408_VGT_INDX_OFFSET, a->vgt_indx_offset);
}

static void r600_set_clip_state(struct pipe_context *ctx,
				const struct pipe_clip_state *state)
{
	struct r600_context *rctx = (struct r600_context *)ctx;
	struct pipe_constant_buffer cb;

	rctx->clip_state.state = *state;
	rctx->clip_state.atom.dirty = true;

	cb.buffer = NULL;
	cb.user_buffer = state->ucp;
	cb.buffer_offset = 0;
	cb.buffer_size = 4*4*8;
	ctx->set_constant_buffer(ctx, PIPE_SHADER_VERTEX, R600_UCP_CONST_BUFFER, &cb);
	pipe_resource_reference(&cb.buffer, NULL);
}

static void r600_set_stencil_ref(struct pipe_context *ctx,
				 const struct r600_stencil_ref *state)
{
	struct r600_context *rctx = (struct r600_context *)ctx;

	rctx->stencil_ref.state = *state;
	rctx->stencil_ref.atom.dirty = true;
}

void r600_emit_stencil_ref(struct r600_context *rctx, struct r600_atom *atom)
{
	struct radeon_winsys_cs *cs = rctx->rings.gfx.cs;
	struct r600_stencil_ref_state *a = (struct r600_stencil_ref_state*)atom;

	r600_write_context_reg_seq(cs, R_028430_DB_STENCILREFMASK, 2);
	r600_write_value(cs, /* R_028430_DB_STENCILREFMASK */
			 S_028430_STENCILREF(a->state.ref_value[0]) |
			 S_028430_STENCILMASK(a->state.valuemask[0]) |
			 S_028430_STENCILWRITEMASK(a->state.writemask[0]));
	r600_write_value(cs, /* R_028434_DB_STENCILREFMASK_BF */
			 S_028434_STENCILREF_BF(a->state.ref_value[1]) |
			 S_028434_STENCILMASK_BF(a->state.valuemask[1]) |
			 S_028434_STENCILWRITEMASK_BF(a->state.writemask[1]));
}

static void r600_set_pipe_stencil_ref(struct pipe_context *ctx,
				      const struct pipe_stencil_ref *state)
{
	struct r600_context *rctx = (struct r600_context *)ctx;
	struct r600_dsa_state *dsa = (struct r600_dsa_state*)rctx->dsa_state.cso;
	struct r600_stencil_ref ref;

	rctx->stencil_ref.pipe_state = *state;

	if (!dsa)
		return;

	ref.ref_value[0] = state->ref_value[0];
	ref.ref_value[1] = state->ref_value[1];
	ref.valuemask[0] = dsa->valuemask[0];
	ref.valuemask[1] = dsa->valuemask[1];
	ref.writemask[0] = dsa->writemask[0];
	ref.writemask[1] = dsa->writemask[1];

	r600_set_stencil_ref(ctx, &ref);
}

static void r600_bind_dsa_state(struct pipe_context *ctx, void *state)
{
	struct r600_context *rctx = (struct r600_context *)ctx;
	struct r600_dsa_state *dsa = state;
	struct r600_stencil_ref ref;

	if (state == NULL)
		return;

	r600_set_cso_state_with_cb(&rctx->dsa_state, dsa, &dsa->buffer);

	ref.ref_value[0] = rctx->stencil_ref.pipe_state.ref_value[0];
	ref.ref_value[1] = rctx->stencil_ref.pipe_state.ref_value[1];
	ref.valuemask[0] = dsa->valuemask[0];
	ref.valuemask[1] = dsa->valuemask[1];
	ref.writemask[0] = dsa->writemask[0];
	ref.writemask[1] = dsa->writemask[1];

	r600_set_stencil_ref(ctx, &ref);

	/* Update alphatest state. */
	if (rctx->alphatest_state.sx_alpha_test_control != dsa->sx_alpha_test_control ||
	    rctx->alphatest_state.sx_alpha_ref != dsa->alpha_ref) {
		rctx->alphatest_state.sx_alpha_test_control = dsa->sx_alpha_test_control;
		rctx->alphatest_state.sx_alpha_ref = dsa->alpha_ref;
		rctx->alphatest_state.atom.dirty = true;
	}
}

static void r600_bind_rs_state(struct pipe_context *ctx, void *state)
{
	struct r600_rasterizer_state *rs = (struct r600_rasterizer_state *)state;
	struct r600_context *rctx = (struct r600_context *)ctx;

	if (state == NULL)
		return;

	rctx->rasterizer = rs;

	r600_set_cso_state_with_cb(&rctx->rasterizer_state, rs, &rs->buffer);

	if (rs->offset_enable &&
	    (rs->offset_units != rctx->poly_offset_state.offset_units ||
	     rs->offset_scale != rctx->poly_offset_state.offset_scale)) {
		rctx->poly_offset_state.offset_units = rs->offset_units;
		rctx->poly_offset_state.offset_scale = rs->offset_scale;
		rctx->poly_offset_state.atom.dirty = true;
	}

	/* Update clip_misc_state. */
	if (rctx->clip_misc_state.pa_cl_clip_cntl != rs->pa_cl_clip_cntl ||
	    rctx->clip_misc_state.clip_plane_enable != rs->clip_plane_enable) {
		rctx->clip_misc_state.pa_cl_clip_cntl = rs->pa_cl_clip_cntl;
		rctx->clip_misc_state.clip_plane_enable = rs->clip_plane_enable;
		rctx->clip_misc_state.atom.dirty = true;
	}

	/* Workaround for a missing scissor enable on r600. */
	if (rctx->chip_class == R600 &&
	    rs->scissor_enable != rctx->scissor.enable) {
		rctx->scissor.enable = rs->scissor_enable;
		rctx->scissor.atom.dirty = true;
	}

	/* Re-emit PA_SC_LINE_STIPPLE. */
	rctx->last_primitive_type = -1;
}

static void r600_delete_rs_state(struct pipe_context *ctx, void *state)
{
	struct r600_rasterizer_state *rs = (struct r600_rasterizer_state *)state;

	r600_release_command_buffer(&rs->buffer);
	FREE(rs);
}

static void r600_sampler_view_destroy(struct pipe_context *ctx,
				      struct pipe_sampler_view *state)
{
	struct r600_pipe_sampler_view *resource = (struct r600_pipe_sampler_view *)state;

	pipe_resource_reference(&state->texture, NULL);
	FREE(resource);
}

void r600_sampler_states_dirty(struct r600_context *rctx,
			       struct r600_sampler_states *state)
{
	if (state->dirty_mask) {
		if (state->dirty_mask & state->has_bordercolor_mask) {
			rctx->flags |= R600_CONTEXT_WAIT_3D_IDLE;
		}
		state->atom.num_dw =
			util_bitcount(state->dirty_mask & state->has_bordercolor_mask) * 11 +
			util_bitcount(state->dirty_mask & ~state->has_bordercolor_mask) * 5;
		state->atom.dirty = true;
	}
}

static void r600_bind_sampler_states(struct pipe_context *pipe,
                               unsigned shader,
			       unsigned start,
			       unsigned count, void **states)
{
	struct r600_context *rctx = (struct r600_context *)pipe;
	struct r600_textures_info *dst = &rctx->samplers[shader];
	struct r600_pipe_sampler_state **rstates = (struct r600_pipe_sampler_state**)states;
	int seamless_cube_map = -1;
	unsigned i;
	/* This sets 1-bit for states with index >= count. */
	uint32_t disable_mask = ~((1ull << count) - 1);
	/* These are the new states set by this function. */
	uint32_t new_mask = 0;

	assert(start == 0); /* XXX fix below */

	for (i = 0; i < count; i++) {
		struct r600_pipe_sampler_state *rstate = rstates[i];

		if (rstate == dst->states.states[i]) {
			continue;
		}

		if (rstate) {
			if (rstate->border_color_use) {
				dst->states.has_bordercolor_mask |= 1 << i;
			} else {
				dst->states.has_bordercolor_mask &= ~(1 << i);
			}
			seamless_cube_map = rstate->seamless_cube_map;

			new_mask |= 1 << i;
		} else {
			disable_mask |= 1 << i;
		}
	}

	memcpy(dst->states.states, rstates, sizeof(void*) * count);
	memset(dst->states.states + count, 0, sizeof(void*) * (NUM_TEX_UNITS - count));

	dst->states.enabled_mask &= ~disable_mask;
	dst->states.dirty_mask &= dst->states.enabled_mask;
	dst->states.enabled_mask |= new_mask;
	dst->states.dirty_mask |= new_mask;
	dst->states.has_bordercolor_mask &= dst->states.enabled_mask;

	r600_sampler_states_dirty(rctx, &dst->states);

	/* Seamless cubemap state. */
	if (rctx->chip_class <= R700 &&
	    seamless_cube_map != -1 &&
	    seamless_cube_map != rctx->seamless_cube_map.enabled) {
		/* change in TA_CNTL_AUX need a pipeline flush */
		rctx->flags |= R600_CONTEXT_WAIT_3D_IDLE;
		rctx->seamless_cube_map.enabled = seamless_cube_map;
		rctx->seamless_cube_map.atom.dirty = true;
	}
}

static void r600_bind_vs_sampler_states(struct pipe_context *ctx, unsigned count, void **states)
{
	r600_bind_sampler_states(ctx, PIPE_SHADER_VERTEX, 0, count, states);
}

static void r600_bind_ps_sampler_states(struct pipe_context *ctx, unsigned count, void **states)
{
	r600_bind_sampler_states(ctx, PIPE_SHADER_FRAGMENT, 0, count, states);
}

static void r600_delete_sampler_state(struct pipe_context *ctx, void *state)
{
	free(state);
}

static void r600_delete_blend_state(struct pipe_context *ctx, void *state)
{
	struct r600_blend_state *blend = (struct r600_blend_state*)state;

	r600_release_command_buffer(&blend->buffer);
	r600_release_command_buffer(&blend->buffer_no_blend);
	FREE(blend);
}

static void r600_delete_dsa_state(struct pipe_context *ctx, void *state)
{
	struct r600_dsa_state *dsa = (struct r600_dsa_state *)state;

	r600_release_command_buffer(&dsa->buffer);
	free(dsa);
}

static void r600_bind_vertex_elements(struct pipe_context *ctx, void *state)
{
	struct r600_context *rctx = (struct r600_context *)ctx;

	r600_set_cso_state(&rctx->vertex_fetch_shader, state);
}

static void r600_delete_vertex_elements(struct pipe_context *ctx, void *state)
{
	struct r600_fetch_shader *shader = (struct r600_fetch_shader*)state;
	pipe_resource_reference((struct pipe_resource**)&shader->buffer, NULL);
	FREE(shader);
}

static void r600_set_index_buffer(struct pipe_context *ctx,
			   const struct pipe_index_buffer *ib)
{
	struct r600_context *rctx = (struct r600_context *)ctx;

	if (ib) {
		pipe_resource_reference(&rctx->index_buffer.buffer, ib->buffer);
	        memcpy(&rctx->index_buffer, ib, sizeof(*ib));
	} else {
		pipe_resource_reference(&rctx->index_buffer.buffer, NULL);
	}
}

void r600_vertex_buffers_dirty(struct r600_context *rctx)
{
	if (rctx->vertex_buffer_state.dirty_mask) {
		rctx->flags |= R600_CONTEXT_INVAL_READ_CACHES;
		rctx->vertex_buffer_state.atom.num_dw = (rctx->chip_class >= EVERGREEN ? 12 : 11) *
					       util_bitcount(rctx->vertex_buffer_state.dirty_mask);
		rctx->vertex_buffer_state.atom.dirty = true;
	}
}

static void r600_set_vertex_buffers(struct pipe_context *ctx,
				    unsigned start_slot, unsigned count,
				    const struct pipe_vertex_buffer *input)
{
	struct r600_context *rctx = (struct r600_context *)ctx;
	struct r600_vertexbuf_state *state = &rctx->vertex_buffer_state;
	struct pipe_vertex_buffer *vb = state->vb + start_slot;
	unsigned i;
	uint32_t disable_mask = 0;
	/* These are the new buffers set by this function. */
	uint32_t new_buffer_mask = 0;

	/* Set vertex buffers. */
	if (input) {
		for (i = 0; i < count; i++) {
			if (memcmp(&input[i], &vb[i], sizeof(struct pipe_vertex_buffer))) {
				if (input[i].buffer) {
					vb[i].stride = input[i].stride;
					vb[i].buffer_offset = input[i].buffer_offset;
					pipe_resource_reference(&vb[i].buffer, input[i].buffer);
					new_buffer_mask |= 1 << i;
				} else {
					pipe_resource_reference(&vb[i].buffer, NULL);
					disable_mask |= 1 << i;
				}
			}
		}
	} else {
		for (i = 0; i < count; i++) {
			pipe_resource_reference(&vb[i].buffer, NULL);
		}
		disable_mask = ((1ull << count) - 1);
	}

	disable_mask <<= start_slot;
	new_buffer_mask <<= start_slot;

	rctx->vertex_buffer_state.enabled_mask &= ~disable_mask;
	rctx->vertex_buffer_state.dirty_mask &= rctx->vertex_buffer_state.enabled_mask;
	rctx->vertex_buffer_state.enabled_mask |= new_buffer_mask;
	rctx->vertex_buffer_state.dirty_mask |= new_buffer_mask;

	r600_vertex_buffers_dirty(rctx);
}

void r600_sampler_views_dirty(struct r600_context *rctx,
			      struct r600_samplerview_state *state)
{
	if (state->dirty_mask) {
		rctx->flags |= R600_CONTEXT_INVAL_READ_CACHES;
		state->atom.num_dw = (rctx->chip_class >= EVERGREEN ? 14 : 13) *
				     util_bitcount(state->dirty_mask);
		state->atom.dirty = true;
	}
}

static void r600_set_sampler_views(struct pipe_context *pipe, unsigned shader,
				   unsigned start, unsigned count,
				   struct pipe_sampler_view **views)
{
	struct r600_context *rctx = (struct r600_context *) pipe;
	struct r600_textures_info *dst = &rctx->samplers[shader];
	struct r600_pipe_sampler_view **rviews = (struct r600_pipe_sampler_view **)views;
	uint32_t dirty_sampler_states_mask = 0;
	unsigned i;
	/* This sets 1-bit for textures with index >= count. */
	uint32_t disable_mask = ~((1ull << count) - 1);
	/* These are the new textures set by this function. */
	uint32_t new_mask = 0;

	/* Set textures with index >= count to NULL. */
	uint32_t remaining_mask;

	assert(start == 0); /* XXX fix below */

	remaining_mask = dst->views.enabled_mask & disable_mask;

	while (remaining_mask) {
		i = u_bit_scan(&remaining_mask);
		assert(dst->views.views[i]);

		pipe_sampler_view_reference((struct pipe_sampler_view **)&dst->views.views[i], NULL);
	}

	for (i = 0; i < count; i++) {
		if (rviews[i] == dst->views.views[i]) {
			continue;
		}

		if (rviews[i]) {
			struct r600_texture *rtex =
				(struct r600_texture*)rviews[i]->base.texture;

			if (rviews[i]->base.texture->target != PIPE_BUFFER) {
				if (rtex->is_depth && !rtex->is_flushing_texture) {
					dst->views.compressed_depthtex_mask |= 1 << i;
				} else {
					dst->views.compressed_depthtex_mask &= ~(1 << i);
				}

				/* Track compressed colorbuffers. */
				if (rtex->cmask_size && rtex->fmask_size) {
					dst->views.compressed_colortex_mask |= 1 << i;
				} else {
					dst->views.compressed_colortex_mask &= ~(1 << i);
				}
			}
			/* Changing from array to non-arrays textures and vice versa requires
			 * updating TEX_ARRAY_OVERRIDE in sampler states on R6xx-R7xx. */
			if (rctx->chip_class <= R700 &&
			    (dst->states.enabled_mask & (1 << i)) &&
			    (rviews[i]->base.texture->target == PIPE_TEXTURE_1D_ARRAY ||
			     rviews[i]->base.texture->target == PIPE_TEXTURE_2D_ARRAY) != dst->is_array_sampler[i]) {
				dirty_sampler_states_mask |= 1 << i;
			}

			pipe_sampler_view_reference((struct pipe_sampler_view **)&dst->views.views[i], views[i]);
			new_mask |= 1 << i;
		} else {
			pipe_sampler_view_reference((struct pipe_sampler_view **)&dst->views.views[i], NULL);
			disable_mask |= 1 << i;
		}
	}

	dst->views.enabled_mask &= ~disable_mask;
	dst->views.dirty_mask &= dst->views.enabled_mask;
	dst->views.enabled_mask |= new_mask;
	dst->views.dirty_mask |= new_mask;
	dst->views.compressed_depthtex_mask &= dst->views.enabled_mask;
	dst->views.compressed_colortex_mask &= dst->views.enabled_mask;
	dst->views.dirty_txq_constants = TRUE;
	dst->views.dirty_buffer_constants = TRUE;
	r600_sampler_views_dirty(rctx, &dst->views);

	if (dirty_sampler_states_mask) {
		dst->states.dirty_mask |= dirty_sampler_states_mask;
		r600_sampler_states_dirty(rctx, &dst->states);
	}
}

static void r600_set_vs_sampler_views(struct pipe_context *ctx, unsigned count,
				      struct pipe_sampler_view **views)
{
	r600_set_sampler_views(ctx, PIPE_SHADER_VERTEX, 0, count, views);
}

static void r600_set_ps_sampler_views(struct pipe_context *ctx, unsigned count,
				      struct pipe_sampler_view **views)
{
	r600_set_sampler_views(ctx, PIPE_SHADER_FRAGMENT, 0, count, views);
}

static void r600_set_viewport_state(struct pipe_context *ctx,
				    const struct pipe_viewport_state *state)
{
	struct r600_context *rctx = (struct r600_context *)ctx;

	rctx->viewport.state = *state;
	rctx->viewport.atom.dirty = true;
}

void r600_emit_viewport_state(struct r600_context *rctx, struct r600_atom *atom)
{
	struct radeon_winsys_cs *cs = rctx->rings.gfx.cs;
	struct pipe_viewport_state *state = &rctx->viewport.state;

	r600_write_context_reg_seq(cs, R_02843C_PA_CL_VPORT_XSCALE_0, 6);
	r600_write_value(cs, fui(state->scale[0]));     /* R_02843C_PA_CL_VPORT_XSCALE_0  */
	r600_write_value(cs, fui(state->translate[0])); /* R_028440_PA_CL_VPORT_XOFFSET_0 */
	r600_write_value(cs, fui(state->scale[1]));     /* R_028444_PA_CL_VPORT_YSCALE_0  */
	r600_write_value(cs, fui(state->translate[1])); /* R_028448_PA_CL_VPORT_YOFFSET_0 */
	r600_write_value(cs, fui(state->scale[2]));     /* R_02844C_PA_CL_VPORT_ZSCALE_0  */
	r600_write_value(cs, fui(state->translate[2])); /* R_028450_PA_CL_VPORT_ZOFFSET_0 */
}

/* Compute the key for the hw shader variant */
static INLINE struct r600_shader_key r600_shader_selector_key(struct pipe_context * ctx,
		struct r600_pipe_shader_selector * sel)
{
	struct r600_context *rctx = (struct r600_context *)ctx;
	struct r600_shader_key key;
	memset(&key, 0, sizeof(key));

	if (sel->type == PIPE_SHADER_FRAGMENT) {
		key.color_two_side = rctx->rasterizer && rctx->rasterizer->two_side;
		key.alpha_to_one = rctx->alpha_to_one &&
				   rctx->rasterizer && rctx->rasterizer->multisample_enable &&
				   !rctx->framebuffer.cb0_is_integer;
		key.nr_cbufs = rctx->framebuffer.state.nr_cbufs;
		/* Dual-source blending only makes sense with nr_cbufs == 1. */
		if (key.nr_cbufs == 1 && rctx->dual_src_blend)
			key.nr_cbufs = 2;
	}
	return key;
}

/* Select the hw shader variant depending on the current state.
 * (*dirty) is set to 1 if current variant was changed */
static int r600_shader_select(struct pipe_context *ctx,
        struct r600_pipe_shader_selector* sel,
        unsigned *dirty)
{
	struct r600_shader_key key;
	struct r600_context *rctx = (struct r600_context *)ctx;
	struct r600_pipe_shader * shader = NULL;
	int r;

	key = r600_shader_selector_key(ctx, sel);

	/* Check if we don't need to change anything.
	 * This path is also used for most shaders that don't need multiple
	 * variants, it will cost just a computation of the key and this
	 * test. */
	if (likely(sel->current && memcmp(&sel->current->key, &key, sizeof(key)) == 0)) {
		return 0;
	}

	/* lookup if we have other variants in the list */
	if (sel->num_shaders > 1) {
		struct r600_pipe_shader *p = sel->current, *c = p->next_variant;

		while (c && memcmp(&c->key, &key, sizeof(key)) != 0) {
			p = c;
			c = c->next_variant;
		}

		if (c) {
			p->next_variant = c->next_variant;
			shader = c;
		}
	}

	if (unlikely(!shader)) {
		shader = CALLOC(1, sizeof(struct r600_pipe_shader));
		shader->selector = sel;

		r = r600_pipe_shader_create(ctx, shader, key);
		if (unlikely(r)) {
			R600_ERR("Failed to build shader variant (type=%u) %d\n",
				 sel->type, r);
			sel->current = NULL;
			return r;
		}

		/* We don't know the value of nr_ps_max_color_exports until we built
		 * at least one variant, so we may need to recompute the key after
		 * building first variant. */
		if (sel->type == PIPE_SHADER_FRAGMENT &&
				sel->num_shaders == 0) {
			sel->nr_ps_max_color_exports = shader->shader.nr_ps_max_color_exports;
			key = r600_shader_selector_key(ctx, sel);
		}

		shader->key = key;
		sel->num_shaders++;
	}

	if (dirty)
		*dirty = 1;

	shader->next_variant = sel->current;
	sel->current = shader;

	if (rctx->ps_shader &&
	    rctx->cb_misc_state.nr_ps_color_outputs != rctx->ps_shader->current->nr_ps_color_outputs) {
		rctx->cb_misc_state.nr_ps_color_outputs = rctx->ps_shader->current->nr_ps_color_outputs;
		rctx->cb_misc_state.atom.dirty = true;
	}
	return 0;
}

static void *r600_create_shader_state(struct pipe_context *ctx,
			       const struct pipe_shader_state *state,
			       unsigned pipe_shader_type)
{
	struct r600_pipe_shader_selector *sel = CALLOC_STRUCT(r600_pipe_shader_selector);
	int r;

	sel->type = pipe_shader_type;
	sel->tokens = tgsi_dup_tokens(state->tokens);
	sel->so = state->stream_output;

	r = r600_shader_select(ctx, sel, NULL);
	if (r)
	    return NULL;

	return sel;
}

static void *r600_create_ps_state(struct pipe_context *ctx,
					 const struct pipe_shader_state *state)
{
	return r600_create_shader_state(ctx, state, PIPE_SHADER_FRAGMENT);
}

static void *r600_create_vs_state(struct pipe_context *ctx,
					 const struct pipe_shader_state *state)
{
	return r600_create_shader_state(ctx, state, PIPE_SHADER_VERTEX);
}

static void r600_bind_ps_state(struct pipe_context *ctx, void *state)
{
	struct r600_context *rctx = (struct r600_context *)ctx;

	if (!state)
		state = rctx->dummy_pixel_shader;

	rctx->ps_shader = (struct r600_pipe_shader_selector *)state;
	r600_context_pipe_state_set(rctx, &rctx->ps_shader->current->rstate);

	if (rctx->chip_class <= R700) {
		bool multiwrite = rctx->ps_shader->current->shader.fs_write_all;

		if (rctx->cb_misc_state.multiwrite != multiwrite) {
			rctx->cb_misc_state.multiwrite = multiwrite;
			rctx->cb_misc_state.atom.dirty = true;
		}
	}

	if (rctx->cb_misc_state.nr_ps_color_outputs != rctx->ps_shader->current->nr_ps_color_outputs) {
		rctx->cb_misc_state.nr_ps_color_outputs = rctx->ps_shader->current->nr_ps_color_outputs;
		rctx->cb_misc_state.atom.dirty = true;
	}

	if (rctx->chip_class >= EVERGREEN) {
		evergreen_update_db_shader_control(rctx);
	} else {
		r600_update_db_shader_control(rctx);
	}
}

static void r600_bind_vs_state(struct pipe_context *ctx, void *state)
{
	struct r600_context *rctx = (struct r600_context *)ctx;

	rctx->vs_shader = (struct r600_pipe_shader_selector *)state;
	if (state) {
		r600_context_pipe_state_set(rctx, &rctx->vs_shader->current->rstate);

		/* Update clip misc state. */
		if (rctx->vs_shader->current->pa_cl_vs_out_cntl != rctx->clip_misc_state.pa_cl_vs_out_cntl ||
		    rctx->vs_shader->current->shader.clip_dist_write != rctx->clip_misc_state.clip_dist_write) {
			rctx->clip_misc_state.pa_cl_vs_out_cntl = rctx->vs_shader->current->pa_cl_vs_out_cntl;
			rctx->clip_misc_state.clip_dist_write = rctx->vs_shader->current->shader.clip_dist_write;
			rctx->clip_misc_state.atom.dirty = true;
		}
	}
}

static void r600_delete_shader_selector(struct pipe_context *ctx,
		struct r600_pipe_shader_selector *sel)
{
	struct r600_pipe_shader *p = sel->current, *c;
	while (p) {
		c = p->next_variant;
		r600_pipe_shader_destroy(ctx, p);
		free(p);
		p = c;
	}

	free(sel->tokens);
	free(sel);
}


static void r600_delete_ps_state(struct pipe_context *ctx, void *state)
{
	struct r600_context *rctx = (struct r600_context *)ctx;
	struct r600_pipe_shader_selector *sel = (struct r600_pipe_shader_selector *)state;

	if (rctx->ps_shader == sel) {
		rctx->ps_shader = NULL;
	}

	r600_delete_shader_selector(ctx, sel);
}

static void r600_delete_vs_state(struct pipe_context *ctx, void *state)
{
	struct r600_context *rctx = (struct r600_context *)ctx;
	struct r600_pipe_shader_selector *sel = (struct r600_pipe_shader_selector *)state;

	if (rctx->vs_shader == sel) {
		rctx->vs_shader = NULL;
	}

	r600_delete_shader_selector(ctx, sel);
}

void r600_constant_buffers_dirty(struct r600_context *rctx, struct r600_constbuf_state *state)
{
	if (state->dirty_mask) {
		rctx->flags |= R600_CONTEXT_INVAL_READ_CACHES;
		state->atom.num_dw = rctx->chip_class >= EVERGREEN ? util_bitcount(state->dirty_mask)*20
								   : util_bitcount(state->dirty_mask)*19;
		state->atom.dirty = true;
	}
}

static void r600_set_constant_buffer(struct pipe_context *ctx, uint shader, uint index,
				     struct pipe_constant_buffer *input)
{
	struct r600_context *rctx = (struct r600_context *)ctx;
	struct r600_constbuf_state *state = &rctx->constbuf_state[shader];
	struct pipe_constant_buffer *cb;
	const uint8_t *ptr;

	/* Note that the state tracker can unbind constant buffers by
	 * passing NULL here.
	 */
	if (unlikely(!input)) {
		state->enabled_mask &= ~(1 << index);
		state->dirty_mask &= ~(1 << index);
		pipe_resource_reference(&state->cb[index].buffer, NULL);
		return;
	}

	cb = &state->cb[index];
	cb->buffer_size = input->buffer_size;

	ptr = input->user_buffer;

	if (ptr) {
		/* Upload the user buffer. */
		if (R600_BIG_ENDIAN) {
			uint32_t *tmpPtr;
			unsigned i, size = input->buffer_size;

			if (!(tmpPtr = malloc(size))) {
				R600_ERR("Failed to allocate BE swap buffer.\n");
				return;
			}

			for (i = 0; i < size / 4; ++i) {
				tmpPtr[i] = bswap_32(((uint32_t *)ptr)[i]);
			}

			u_upload_data(rctx->uploader, 0, size, tmpPtr, &cb->buffer_offset, &cb->buffer);
			free(tmpPtr);
		} else {
			u_upload_data(rctx->uploader, 0, input->buffer_size, ptr, &cb->buffer_offset, &cb->buffer);
		}
	} else {
		/* Setup the hw buffer. */
		cb->buffer_offset = input->buffer_offset;
		pipe_resource_reference(&cb->buffer, input->buffer);
	}

	state->enabled_mask |= 1 << index;
	state->dirty_mask |= 1 << index;
	r600_constant_buffers_dirty(rctx, state);
}

static struct pipe_stream_output_target *
r600_create_so_target(struct pipe_context *ctx,
		      struct pipe_resource *buffer,
		      unsigned buffer_offset,
		      unsigned buffer_size)
{
	struct r600_context *rctx = (struct r600_context *)ctx;
	struct r600_so_target *t;

	t = CALLOC_STRUCT(r600_so_target);
	if (!t) {
		return NULL;
	}

	u_suballocator_alloc(rctx->allocator_so_filled_size, 4,
			     &t->buf_filled_size_offset,
			     (struct pipe_resource**)&t->buf_filled_size);
	if (!t->buf_filled_size) {
		FREE(t);
		return NULL;
	}

	t->b.reference.count = 1;
	t->b.context = ctx;
	pipe_resource_reference(&t->b.buffer, buffer);
	t->b.buffer_offset = buffer_offset;
	t->b.buffer_size = buffer_size;
	return &t->b;
}

static void r600_so_target_destroy(struct pipe_context *ctx,
				   struct pipe_stream_output_target *target)
{
	struct r600_so_target *t = (struct r600_so_target*)target;
	pipe_resource_reference(&t->b.buffer, NULL);
	pipe_resource_reference((struct pipe_resource**)&t->buf_filled_size, NULL);
	FREE(t);
}

static void r600_set_so_targets(struct pipe_context *ctx,
				unsigned num_targets,
				struct pipe_stream_output_target **targets,
				unsigned append_bitmask)
{
	struct r600_context *rctx = (struct r600_context *)ctx;
	unsigned i;

	/* Stop streamout. */
	if (rctx->num_so_targets && !rctx->streamout_start) {
		r600_context_streamout_end(rctx);
	}

	/* Set the new targets. */
	for (i = 0; i < num_targets; i++) {
		pipe_so_target_reference((struct pipe_stream_output_target**)&rctx->so_targets[i], targets[i]);
	}
	for (; i < rctx->num_so_targets; i++) {
		pipe_so_target_reference((struct pipe_stream_output_target**)&rctx->so_targets[i], NULL);
	}

	rctx->num_so_targets = num_targets;
	rctx->streamout_start = num_targets != 0;
	rctx->streamout_append_bitmask = append_bitmask;
}

static void r600_set_sample_mask(struct pipe_context *pipe, unsigned sample_mask)
{
	struct r600_context *rctx = (struct r600_context*)pipe;

	if (rctx->sample_mask.sample_mask == (uint16_t)sample_mask)
		return;

	rctx->sample_mask.sample_mask = sample_mask;
	rctx->sample_mask.atom.dirty = true;
}

/*
 * On r600/700 hw we don't have vertex fetch swizzle, though TBO
 * doesn't require full swizzles it does need masking and setting alpha
 * to one, so we setup a set of 5 constants with the masks + alpha value
 * then in the shader, we AND the 4 components with 0xffffffff or 0,
 * then OR the alpha with the value given here.
 * We use a 6th constant to store the txq buffer size in
 */
static void r600_setup_buffer_constants(struct r600_context *rctx, int shader_type)
{
	struct r600_textures_info *samplers = &rctx->samplers[shader_type];
	int bits;
	uint32_t array_size;
	struct pipe_constant_buffer cb;
	int i, j;

	if (!samplers->views.dirty_buffer_constants)
		return;

	samplers->views.dirty_buffer_constants = FALSE;

	bits = util_last_bit(samplers->views.enabled_mask);
	array_size = bits * 8 * sizeof(uint32_t) * 4;
	samplers->buffer_constants = realloc(samplers->buffer_constants, array_size);
	memset(samplers->buffer_constants, 0, array_size);
	for (i = 0; i < bits; i++) {
		if (samplers->views.enabled_mask & (1 << i)) {
			int offset = i * 8;
			const struct util_format_description *desc;
			desc = util_format_description(samplers->views.views[i]->base.format);

			for (j = 0; j < 4; j++)
				if (j < desc->nr_channels)
					samplers->buffer_constants[offset+j] = 0xffffffff;
				else
					samplers->buffer_constants[offset+j] = 0x0;
			if (desc->nr_channels < 4) {
				if (desc->channel[0].pure_integer)
					samplers->buffer_constants[offset+4] = 1;
				else
					samplers->buffer_constants[offset+4] = 0x3f800000;
			} else
				samplers->buffer_constants[offset + 4] = 0;

			samplers->buffer_constants[offset + 5] = samplers->views.views[i]->base.texture->width0 / util_format_get_blocksize(samplers->views.views[i]->base.format);
		}
	}

	cb.buffer = NULL;
	cb.user_buffer = samplers->buffer_constants;
	cb.buffer_offset = 0;
	cb.buffer_size = array_size;
	rctx->context.set_constant_buffer(&rctx->context, shader_type, R600_BUFFER_INFO_CONST_BUFFER, &cb);
	pipe_resource_reference(&cb.buffer, NULL);
}

/* On evergreen we only need to store the buffer size for TXQ */
static void eg_setup_buffer_constants(struct r600_context *rctx, int shader_type)
{
	struct r600_textures_info *samplers = &rctx->samplers[shader_type];
	int bits;
	uint32_t array_size;
	struct pipe_constant_buffer cb;
	int i;

	if (!samplers->views.dirty_buffer_constants)
		return;

	samplers->views.dirty_buffer_constants = FALSE;

	bits = util_last_bit(samplers->views.enabled_mask);
	array_size = bits * sizeof(uint32_t) * 4;
	samplers->buffer_constants = realloc(samplers->buffer_constants, array_size);
	memset(samplers->buffer_constants, 0, array_size);
	for (i = 0; i < bits; i++)
		if (samplers->views.enabled_mask & (1 << i))
		   samplers->buffer_constants[i] = samplers->views.views[i]->base.texture->width0 / util_format_get_blocksize(samplers->views.views[i]->base.format);

	cb.buffer = NULL;
	cb.user_buffer = samplers->buffer_constants;
	cb.buffer_offset = 0;
	cb.buffer_size = array_size;
	rctx->context.set_constant_buffer(&rctx->context, shader_type, R600_BUFFER_INFO_CONST_BUFFER, &cb);
	pipe_resource_reference(&cb.buffer, NULL);
}

static void r600_setup_txq_cube_array_constants(struct r600_context *rctx, int shader_type)
{
	struct r600_textures_info *samplers = &rctx->samplers[shader_type];
	int bits;
	uint32_t array_size;
	struct pipe_constant_buffer cb;
	int i;

	if (!samplers->views.dirty_txq_constants)
		return;

	samplers->views.dirty_txq_constants = FALSE;

	bits = util_last_bit(samplers->views.enabled_mask);
	array_size = bits * sizeof(uint32_t) * 4;
	samplers->txq_constants = realloc(samplers->txq_constants, array_size);
	memset(samplers->txq_constants, 0, array_size);
	for (i = 0; i < bits; i++)
		if (samplers->views.enabled_mask & (1 << i))
			samplers->txq_constants[i] = samplers->views.views[i]->base.texture->array_size / 6;

	cb.buffer = NULL;
	cb.user_buffer = samplers->txq_constants;
	cb.buffer_offset = 0;
	cb.buffer_size = array_size;
	rctx->context.set_constant_buffer(&rctx->context, shader_type, R600_TXQ_CONST_BUFFER, &cb);
	pipe_resource_reference(&cb.buffer, NULL);
}

static bool r600_update_derived_state(struct r600_context *rctx)
{
	struct pipe_context * ctx = (struct pipe_context*)rctx;
	unsigned ps_dirty = 0;
	bool blend_disable;

	if (!rctx->blitter->running) {
		unsigned i;

		/* Decompress textures if needed. */
		for (i = 0; i < PIPE_SHADER_TYPES; i++) {
			struct r600_samplerview_state *views = &rctx->samplers[i].views;
			if (views->compressed_depthtex_mask) {
				r600_decompress_depth_textures(rctx, views);
			}
			if (views->compressed_colortex_mask) {
				r600_decompress_color_textures(rctx, views);
			}
		}
	}

	r600_shader_select(ctx, rctx->ps_shader, &ps_dirty);

	if (rctx->ps_shader && rctx->rasterizer &&
	    ((rctx->rasterizer->sprite_coord_enable != rctx->ps_shader->current->sprite_coord_enable) ||
	     (rctx->rasterizer->flatshade != rctx->ps_shader->current->flatshade))) {

		if (rctx->chip_class >= EVERGREEN)
			evergreen_pipe_shader_ps(ctx, rctx->ps_shader->current);
		else
			r600_pipe_shader_ps(ctx, rctx->ps_shader->current);

		ps_dirty = 1;
	}

	if (ps_dirty)
		r600_context_pipe_state_set(rctx, &rctx->ps_shader->current->rstate);

	/* on R600 we stuff masks + txq info into one constant buffer */
	/* on evergreen we only need a txq info one */
	if (rctx->chip_class < EVERGREEN) {
		if (rctx->ps_shader && rctx->ps_shader->current->shader.uses_tex_buffers)
			r600_setup_buffer_constants(rctx, PIPE_SHADER_FRAGMENT);
		if (rctx->vs_shader && rctx->vs_shader->current->shader.uses_tex_buffers)
			r600_setup_buffer_constants(rctx, PIPE_SHADER_VERTEX);
	} else {
		if (rctx->ps_shader && rctx->ps_shader->current->shader.uses_tex_buffers)
			eg_setup_buffer_constants(rctx, PIPE_SHADER_FRAGMENT);
		if (rctx->vs_shader && rctx->vs_shader->current->shader.uses_tex_buffers)
			eg_setup_buffer_constants(rctx, PIPE_SHADER_VERTEX);
	}


	if (rctx->ps_shader && rctx->ps_shader->current->shader.has_txq_cube_array_z_comp)
		r600_setup_txq_cube_array_constants(rctx, PIPE_SHADER_FRAGMENT);
	if (rctx->vs_shader && rctx->vs_shader->current->shader.has_txq_cube_array_z_comp)
		r600_setup_txq_cube_array_constants(rctx, PIPE_SHADER_VERTEX);

	if (rctx->chip_class < EVERGREEN && rctx->ps_shader && rctx->vs_shader) {
		if (!r600_adjust_gprs(rctx)) {
			/* discard rendering */
			return false;
		}
	}

	blend_disable = (rctx->dual_src_blend &&
			rctx->ps_shader->current->nr_ps_color_outputs < 2);

	if (blend_disable != rctx->force_blend_disable) {
		rctx->force_blend_disable = blend_disable;
		r600_bind_blend_state_internal(rctx,
					       rctx->blend_state.cso,
					       blend_disable);
	}
	return true;
}

static unsigned r600_conv_prim_to_gs_out(unsigned mode)
{
	static const int prim_conv[] = {
		V_028A6C_OUTPRIM_TYPE_POINTLIST,
		V_028A6C_OUTPRIM_TYPE_LINESTRIP,
		V_028A6C_OUTPRIM_TYPE_LINESTRIP,
		V_028A6C_OUTPRIM_TYPE_LINESTRIP,
		V_028A6C_OUTPRIM_TYPE_TRISTRIP,
		V_028A6C_OUTPRIM_TYPE_TRISTRIP,
		V_028A6C_OUTPRIM_TYPE_TRISTRIP,
		V_028A6C_OUTPRIM_TYPE_TRISTRIP,
		V_028A6C_OUTPRIM_TYPE_TRISTRIP,
		V_028A6C_OUTPRIM_TYPE_TRISTRIP,
		V_028A6C_OUTPRIM_TYPE_LINESTRIP,
		V_028A6C_OUTPRIM_TYPE_LINESTRIP,
		V_028A6C_OUTPRIM_TYPE_TRISTRIP,
		V_028A6C_OUTPRIM_TYPE_TRISTRIP,
		V_028A6C_OUTPRIM_TYPE_TRISTRIP
	};
	assert(mode < Elements(prim_conv));

	return prim_conv[mode];
}

void r600_emit_clip_misc_state(struct r600_context *rctx, struct r600_atom *atom)
{
	struct radeon_winsys_cs *cs = rctx->rings.gfx.cs;
	struct r600_clip_misc_state *state = &rctx->clip_misc_state;

	r600_write_context_reg(cs, R_028810_PA_CL_CLIP_CNTL,
			       state->pa_cl_clip_cntl |
			       (state->clip_dist_write ? 0 : state->clip_plane_enable & 0x3F));
	r600_write_context_reg(cs, R_02881C_PA_CL_VS_OUT_CNTL,
			       state->pa_cl_vs_out_cntl |
			       (state->clip_plane_enable & state->clip_dist_write));
}

static void r600_draw_vbo(struct pipe_context *ctx, const struct pipe_draw_info *dinfo)
{
	struct r600_context *rctx = (struct r600_context *)ctx;
	struct pipe_draw_info info = *dinfo;
	struct pipe_index_buffer ib = {};
	unsigned i;
	struct r600_block *dirty_block = NULL, *next_block = NULL;
	struct radeon_winsys_cs *cs = rctx->rings.gfx.cs;

	if (!info.count && (info.indexed || !info.count_from_stream_output)) {
		assert(0);
		return;
	}

	if (!rctx->vs_shader) {
		assert(0);
		return;
	}

	/* make sure that the gfx ring is only one active */
	rctx->rings.dma.flush(rctx, RADEON_FLUSH_ASYNC);

	if (!r600_update_derived_state(rctx)) {
		/* useless to render because current rendering command
		 * can't be achieved
		 */
		return;
	}

	if (info.indexed) {
		/* Initialize the index buffer struct. */
		pipe_resource_reference(&ib.buffer, rctx->index_buffer.buffer);
		ib.user_buffer = rctx->index_buffer.user_buffer;
		ib.index_size = rctx->index_buffer.index_size;
		ib.offset = rctx->index_buffer.offset + info.start * ib.index_size;

		/* Translate 8-bit indices to 16-bit. */
		if (ib.index_size == 1) {
			struct pipe_resource *out_buffer = NULL;
			unsigned out_offset;
			void *ptr;

			u_upload_alloc(rctx->uploader, 0, info.count * 2,
				       &out_offset, &out_buffer, &ptr);

			util_shorten_ubyte_elts_to_userptr(
						&rctx->context, &ib, 0, ib.offset, info.count, ptr);

			pipe_resource_reference(&ib.buffer, NULL);
			ib.user_buffer = NULL;
			ib.buffer = out_buffer;
			ib.offset = out_offset;
			ib.index_size = 2;
		}

		/* Upload the index buffer.
		 * The upload is skipped for small index counts on little-endian machines
		 * and the indices are emitted via PKT3_DRAW_INDEX_IMMD.
		 * Note: Instanced rendering in combination with immediate indices hangs. */
		if (ib.user_buffer && (R600_BIG_ENDIAN || info.instance_count > 1 ||
				       info.count*ib.index_size > 20)) {
			u_upload_data(rctx->uploader, 0, info.count * ib.index_size,
				      ib.user_buffer, &ib.offset, &ib.buffer);
			ib.user_buffer = NULL;
		}
	} else {
		info.index_bias = info.start;
	}

	/* Enable stream out if needed. */
	if (rctx->streamout_start) {
		r600_context_streamout_begin(rctx);
		rctx->streamout_start = FALSE;
	}

	/* Set the index offset and multi primitive */
	if (rctx->vgt2_state.vgt_indx_offset != info.index_bias) {
		rctx->vgt2_state.vgt_indx_offset = info.index_bias;
		rctx->vgt2_state.atom.dirty = true;
	}
	if (rctx->vgt_state.vgt_multi_prim_ib_reset_en != info.primitive_restart ||
	    rctx->vgt_state.vgt_multi_prim_ib_reset_indx != info.restart_index) {
		rctx->vgt_state.vgt_multi_prim_ib_reset_en = info.primitive_restart;
		rctx->vgt_state.vgt_multi_prim_ib_reset_indx = info.restart_index;
		rctx->vgt_state.atom.dirty = true;
	}

	/* Emit states. */
	r600_need_cs_space(rctx, ib.user_buffer ? 5 : 0, TRUE);
	r600_flush_emit(rctx);

	for (i = 0; i < R600_NUM_ATOMS; i++) {
		if (rctx->atoms[i] == NULL || !rctx->atoms[i]->dirty) {
			continue;
		}
		r600_emit_atom(rctx, rctx->atoms[i]);
	}
	LIST_FOR_EACH_ENTRY_SAFE(dirty_block, next_block, &rctx->dirty,list) {
		r600_context_block_emit_dirty(rctx, dirty_block, 0 /* pkt_flags */);
	}
	rctx->pm4_dirty_cdwords = 0;

	/* Update start instance. */
	if (rctx->last_start_instance != info.start_instance) {
		r600_write_ctl_const(cs, R_03CFF4_SQ_VTX_START_INST_LOC, info.start_instance);
		rctx->last_start_instance = info.start_instance;
	}

	/* Update the primitive type. */
	if (rctx->last_primitive_type != info.mode) {
		unsigned ls_mask = 0;

		if (info.mode == PIPE_PRIM_LINES)
			ls_mask = 1;
		else if (info.mode == PIPE_PRIM_LINE_STRIP ||
			 info.mode == PIPE_PRIM_LINE_LOOP)
			ls_mask = 2;

		r600_write_context_reg(cs, R_028A0C_PA_SC_LINE_STIPPLE,
				       S_028A0C_AUTO_RESET_CNTL(ls_mask) |
				       (rctx->rasterizer ? rctx->rasterizer->pa_sc_line_stipple : 0));
		r600_write_context_reg(cs, R_028A6C_VGT_GS_OUT_PRIM_TYPE,
				       r600_conv_prim_to_gs_out(info.mode));
		r600_write_config_reg(cs, R_008958_VGT_PRIMITIVE_TYPE,
				      r600_conv_pipe_prim(info.mode));

		rctx->last_primitive_type = info.mode;
	}

	/* Draw packets. */
	cs->buf[cs->cdw++] = PKT3(PKT3_NUM_INSTANCES, 0, rctx->predicate_drawing);
	cs->buf[cs->cdw++] = info.instance_count;
	if (info.indexed) {
		cs->buf[cs->cdw++] = PKT3(PKT3_INDEX_TYPE, 0, rctx->predicate_drawing);
		cs->buf[cs->cdw++] = ib.index_size == 4 ?
					(VGT_INDEX_32 | (R600_BIG_ENDIAN ? VGT_DMA_SWAP_32_BIT : 0)) :
					(VGT_INDEX_16 | (R600_BIG_ENDIAN ? VGT_DMA_SWAP_16_BIT : 0));

		if (ib.user_buffer) {
			unsigned size_bytes = info.count*ib.index_size;
			unsigned size_dw = align(size_bytes, 4) / 4;
			cs->buf[cs->cdw++] = PKT3(PKT3_DRAW_INDEX_IMMD, 1 + size_dw, rctx->predicate_drawing);
			cs->buf[cs->cdw++] = info.count;
			cs->buf[cs->cdw++] = V_0287F0_DI_SRC_SEL_IMMEDIATE;
			memcpy(cs->buf+cs->cdw, ib.user_buffer, size_bytes);
			cs->cdw += size_dw;
		} else {
			uint64_t va = r600_resource_va(ctx->screen, ib.buffer) + ib.offset;
			cs->buf[cs->cdw++] = PKT3(PKT3_DRAW_INDEX, 3, rctx->predicate_drawing);
			cs->buf[cs->cdw++] = va;
			cs->buf[cs->cdw++] = (va >> 32UL) & 0xFF;
			cs->buf[cs->cdw++] = info.count;
			cs->buf[cs->cdw++] = V_0287F0_DI_SRC_SEL_DMA;
			cs->buf[cs->cdw++] = PKT3(PKT3_NOP, 0, rctx->predicate_drawing);
			cs->buf[cs->cdw++] = r600_context_bo_reloc(rctx, &rctx->rings.gfx, (struct r600_resource*)ib.buffer, RADEON_USAGE_READ);
		}
	} else {
		if (info.count_from_stream_output) {
			struct r600_so_target *t = (struct r600_so_target*)info.count_from_stream_output;
			uint64_t va = r600_resource_va(&rctx->screen->screen, (void*)t->buf_filled_size) + t->buf_filled_size_offset;

			r600_write_context_reg(cs, R_028B30_VGT_STRMOUT_DRAW_OPAQUE_VERTEX_STRIDE, t->stride_in_dw);

			cs->buf[cs->cdw++] = PKT3(PKT3_COPY_DW, 4, 0);
			cs->buf[cs->cdw++] = COPY_DW_SRC_IS_MEM | COPY_DW_DST_IS_REG;
			cs->buf[cs->cdw++] = va & 0xFFFFFFFFUL;     /* src address lo */
			cs->buf[cs->cdw++] = (va >> 32UL) & 0xFFUL; /* src address hi */
			cs->buf[cs->cdw++] = R_028B2C_VGT_STRMOUT_DRAW_OPAQUE_BUFFER_FILLED_SIZE >> 2; /* dst register */
			cs->buf[cs->cdw++] = 0; /* unused */

			cs->buf[cs->cdw++] = PKT3(PKT3_NOP, 0, 0);
			cs->buf[cs->cdw++] = r600_context_bo_reloc(rctx, &rctx->rings.gfx, t->buf_filled_size, RADEON_USAGE_READ);
		}

		cs->buf[cs->cdw++] = PKT3(PKT3_DRAW_INDEX_AUTO, 1, rctx->predicate_drawing);
		cs->buf[cs->cdw++] = info.count;
		cs->buf[cs->cdw++] = V_0287F0_DI_SRC_SEL_AUTO_INDEX |
					(info.count_from_stream_output ? S_0287F0_USE_OPAQUE(1) : 0);
	}

#if R600_TRACE_CS
	if (rctx->screen->trace_bo) {
		r600_trace_emit(rctx);
	}
#endif

	/* Set the depth buffer as dirty. */
	if (rctx->framebuffer.state.zsbuf) {
		struct pipe_surface *surf = rctx->framebuffer.state.zsbuf;
		struct r600_texture *rtex = (struct r600_texture *)surf->texture;

		rtex->dirty_level_mask |= 1 << surf->u.tex.level;
	}
	if (rctx->framebuffer.compressed_cb_mask) {
		struct pipe_surface *surf;
		struct r600_texture *rtex;
		unsigned mask = rctx->framebuffer.compressed_cb_mask;

		do {
			unsigned i = u_bit_scan(&mask);
			surf = rctx->framebuffer.state.cbufs[i];
			rtex = (struct r600_texture*)surf->texture;

			rtex->dirty_level_mask |= 1 << surf->u.tex.level;

		} while (mask);
	}

	pipe_resource_reference(&ib.buffer, NULL);
}

void r600_draw_rectangle(struct blitter_context *blitter,
			 int x1, int y1, int x2, int y2, float depth,
			 enum blitter_attrib_type type, const union pipe_color_union *attrib)
{
	struct r600_context *rctx = (struct r600_context*)util_blitter_get_pipe(blitter);
	struct pipe_viewport_state viewport;
	struct pipe_resource *buf = NULL;
	unsigned offset = 0;
	float *vb;

	if (type == UTIL_BLITTER_ATTRIB_TEXCOORD) {
		util_blitter_draw_rectangle(blitter, x1, y1, x2, y2, depth, type, attrib);
		return;
	}

	/* Some operations (like color resolve on r6xx) don't work
	 * with the conventional primitive types.
	 * One that works is PT_RECTLIST, which we use here. */

	/* setup viewport */
	viewport.scale[0] = 1.0f;
	viewport.scale[1] = 1.0f;
	viewport.scale[2] = 1.0f;
	viewport.scale[3] = 1.0f;
	viewport.translate[0] = 0.0f;
	viewport.translate[1] = 0.0f;
	viewport.translate[2] = 0.0f;
	viewport.translate[3] = 0.0f;
	rctx->context.set_viewport_state(&rctx->context, &viewport);

	/* Upload vertices. The hw rectangle has only 3 vertices,
	 * I guess the 4th one is derived from the first 3.
	 * The vertex specification should match u_blitter's vertex element state. */
	u_upload_alloc(rctx->uploader, 0, sizeof(float) * 24, &offset, &buf, (void**)&vb);
	vb[0] = x1;
	vb[1] = y1;
	vb[2] = depth;
	vb[3] = 1;

	vb[8] = x1;
	vb[9] = y2;
	vb[10] = depth;
	vb[11] = 1;

	vb[16] = x2;
	vb[17] = y1;
	vb[18] = depth;
	vb[19] = 1;

	if (attrib) {
		memcpy(vb+4, attrib->f, sizeof(float)*4);
		memcpy(vb+12, attrib->f, sizeof(float)*4);
		memcpy(vb+20, attrib->f, sizeof(float)*4);
	}

	/* draw */
	util_draw_vertex_buffer(&rctx->context, NULL, buf, rctx->blitter->vb_slot, offset,
				R600_PRIM_RECTANGLE_LIST, 3, 2);
	pipe_resource_reference(&buf, NULL);
}

void _r600_pipe_state_add_reg_bo(struct r600_context *ctx,
				 struct r600_pipe_state *state,
				 uint32_t offset, uint32_t value,
				 uint32_t range_id, uint32_t block_id,
				 struct r600_resource *bo,
				 enum radeon_bo_usage usage)
			      
{
	struct r600_range *range;
	struct r600_block *block;

	if (bo) assert(usage);

	range = &ctx->range[range_id];
	block = range->blocks[block_id];
	state->regs[state->nregs].block = block;
	state->regs[state->nregs].id = (offset - block->start_offset) >> 2;

	state->regs[state->nregs].value = value;
	state->regs[state->nregs].bo = bo;
	state->regs[state->nregs].bo_usage = usage;

	state->nregs++;
	assert(state->nregs < R600_BLOCK_MAX_REG);
}

void _r600_pipe_state_add_reg(struct r600_context *ctx,
			      struct r600_pipe_state *state,
			      uint32_t offset, uint32_t value,
			      uint32_t range_id, uint32_t block_id)
{
	_r600_pipe_state_add_reg_bo(ctx, state, offset, value,
				    range_id, block_id, NULL, 0);
}

uint32_t r600_translate_stencil_op(int s_op)
{
	switch (s_op) {
	case PIPE_STENCIL_OP_KEEP:
		return V_028800_STENCIL_KEEP;
	case PIPE_STENCIL_OP_ZERO:
		return V_028800_STENCIL_ZERO;
	case PIPE_STENCIL_OP_REPLACE:
		return V_028800_STENCIL_REPLACE;
	case PIPE_STENCIL_OP_INCR:
		return V_028800_STENCIL_INCR;
	case PIPE_STENCIL_OP_DECR:
		return V_028800_STENCIL_DECR;
	case PIPE_STENCIL_OP_INCR_WRAP:
		return V_028800_STENCIL_INCR_WRAP;
	case PIPE_STENCIL_OP_DECR_WRAP:
		return V_028800_STENCIL_DECR_WRAP;
	case PIPE_STENCIL_OP_INVERT:
		return V_028800_STENCIL_INVERT;
	default:
		R600_ERR("Unknown stencil op %d", s_op);
		assert(0);
		break;
	}
	return 0;
}

uint32_t r600_translate_fill(uint32_t func)
{
	switch(func) {
	case PIPE_POLYGON_MODE_FILL:
		return 2;
	case PIPE_POLYGON_MODE_LINE:
		return 1;
	case PIPE_POLYGON_MODE_POINT:
		return 0;
	default:
		assert(0);
		return 0;
	}
}

unsigned r600_tex_wrap(unsigned wrap)
{
	switch (wrap) {
	default:
	case PIPE_TEX_WRAP_REPEAT:
		return V_03C000_SQ_TEX_WRAP;
	case PIPE_TEX_WRAP_CLAMP:
		return V_03C000_SQ_TEX_CLAMP_HALF_BORDER;
	case PIPE_TEX_WRAP_CLAMP_TO_EDGE:
		return V_03C000_SQ_TEX_CLAMP_LAST_TEXEL;
	case PIPE_TEX_WRAP_CLAMP_TO_BORDER:
		return V_03C000_SQ_TEX_CLAMP_BORDER;
	case PIPE_TEX_WRAP_MIRROR_REPEAT:
		return V_03C000_SQ_TEX_MIRROR;
	case PIPE_TEX_WRAP_MIRROR_CLAMP:
		return V_03C000_SQ_TEX_MIRROR_ONCE_HALF_BORDER;
	case PIPE_TEX_WRAP_MIRROR_CLAMP_TO_EDGE:
		return V_03C000_SQ_TEX_MIRROR_ONCE_LAST_TEXEL;
	case PIPE_TEX_WRAP_MIRROR_CLAMP_TO_BORDER:
		return V_03C000_SQ_TEX_MIRROR_ONCE_BORDER;
	}
}

unsigned r600_tex_filter(unsigned filter)
{
	switch (filter) {
	default:
	case PIPE_TEX_FILTER_NEAREST:
		return V_03C000_SQ_TEX_XY_FILTER_POINT;
	case PIPE_TEX_FILTER_LINEAR:
		return V_03C000_SQ_TEX_XY_FILTER_BILINEAR;
	}
}

unsigned r600_tex_mipfilter(unsigned filter)
{
	switch (filter) {
	case PIPE_TEX_MIPFILTER_NEAREST:
		return V_03C000_SQ_TEX_Z_FILTER_POINT;
	case PIPE_TEX_MIPFILTER_LINEAR:
		return V_03C000_SQ_TEX_Z_FILTER_LINEAR;
	default:
	case PIPE_TEX_MIPFILTER_NONE:
		return V_03C000_SQ_TEX_Z_FILTER_NONE;
	}
}

unsigned r600_tex_compare(unsigned compare)
{
	switch (compare) {
	default:
	case PIPE_FUNC_NEVER:
		return V_03C000_SQ_TEX_DEPTH_COMPARE_NEVER;
	case PIPE_FUNC_LESS:
		return V_03C000_SQ_TEX_DEPTH_COMPARE_LESS;
	case PIPE_FUNC_EQUAL:
		return V_03C000_SQ_TEX_DEPTH_COMPARE_EQUAL;
	case PIPE_FUNC_LEQUAL:
		return V_03C000_SQ_TEX_DEPTH_COMPARE_LESSEQUAL;
	case PIPE_FUNC_GREATER:
		return V_03C000_SQ_TEX_DEPTH_COMPARE_GREATER;
	case PIPE_FUNC_NOTEQUAL:
		return V_03C000_SQ_TEX_DEPTH_COMPARE_NOTEQUAL;
	case PIPE_FUNC_GEQUAL:
		return V_03C000_SQ_TEX_DEPTH_COMPARE_GREATEREQUAL;
	case PIPE_FUNC_ALWAYS:
		return V_03C000_SQ_TEX_DEPTH_COMPARE_ALWAYS;
	}
}

static bool wrap_mode_uses_border_color(unsigned wrap, bool linear_filter)
{
	return wrap == PIPE_TEX_WRAP_CLAMP_TO_BORDER ||
	       wrap == PIPE_TEX_WRAP_MIRROR_CLAMP_TO_BORDER ||
	       (linear_filter &&
	        (wrap == PIPE_TEX_WRAP_CLAMP ||
		 wrap == PIPE_TEX_WRAP_MIRROR_CLAMP));
}

bool sampler_state_needs_border_color(const struct pipe_sampler_state *state)
{
	bool linear_filter = state->min_img_filter != PIPE_TEX_FILTER_NEAREST ||
			     state->mag_img_filter != PIPE_TEX_FILTER_NEAREST;

	return (state->border_color.ui[0] || state->border_color.ui[1] ||
		state->border_color.ui[2] || state->border_color.ui[3]) &&
	       (wrap_mode_uses_border_color(state->wrap_s, linear_filter) ||
		wrap_mode_uses_border_color(state->wrap_t, linear_filter) ||
		wrap_mode_uses_border_color(state->wrap_r, linear_filter));
}

/* keep this at the end of this file, please */
void r600_init_common_state_functions(struct r600_context *rctx)
{
	rctx->context.create_fs_state = r600_create_ps_state;
	rctx->context.create_vs_state = r600_create_vs_state;
	rctx->context.create_vertex_elements_state = r600_create_vertex_fetch_shader;
	rctx->context.bind_blend_state = r600_bind_blend_state;
	rctx->context.bind_depth_stencil_alpha_state = r600_bind_dsa_state;
	rctx->context.bind_fragment_sampler_states = r600_bind_ps_sampler_states;
	rctx->context.bind_fs_state = r600_bind_ps_state;
	rctx->context.bind_rasterizer_state = r600_bind_rs_state;
	rctx->context.bind_vertex_elements_state = r600_bind_vertex_elements;
	rctx->context.bind_vertex_sampler_states = r600_bind_vs_sampler_states;
	rctx->context.bind_vs_state = r600_bind_vs_state;
	rctx->context.delete_blend_state = r600_delete_blend_state;
	rctx->context.delete_depth_stencil_alpha_state = r600_delete_dsa_state;
	rctx->context.delete_fs_state = r600_delete_ps_state;
	rctx->context.delete_rasterizer_state = r600_delete_rs_state;
	rctx->context.delete_sampler_state = r600_delete_sampler_state;
	rctx->context.delete_vertex_elements_state = r600_delete_vertex_elements;
	rctx->context.delete_vs_state = r600_delete_vs_state;
	rctx->context.set_blend_color = r600_set_blend_color;
	rctx->context.set_clip_state = r600_set_clip_state;
	rctx->context.set_constant_buffer = r600_set_constant_buffer;
	rctx->context.set_sample_mask = r600_set_sample_mask;
	rctx->context.set_stencil_ref = r600_set_pipe_stencil_ref;
	rctx->context.set_viewport_state = r600_set_viewport_state;
	rctx->context.set_vertex_buffers = r600_set_vertex_buffers;
	rctx->context.set_index_buffer = r600_set_index_buffer;
	rctx->context.set_fragment_sampler_views = r600_set_ps_sampler_views;
	rctx->context.set_vertex_sampler_views = r600_set_vs_sampler_views;
	rctx->context.sampler_view_destroy = r600_sampler_view_destroy;
	rctx->context.texture_barrier = r600_texture_barrier;
	rctx->context.create_stream_output_target = r600_create_so_target;
	rctx->context.stream_output_target_destroy = r600_so_target_destroy;
	rctx->context.set_stream_output_targets = r600_set_so_targets;
	rctx->context.draw_vbo = r600_draw_vbo;
}

#if R600_TRACE_CS
void r600_trace_emit(struct r600_context *rctx)
{
	struct r600_screen *rscreen = rctx->screen;
	struct radeon_winsys_cs *cs = rctx->rings.gfx.cs;
	uint64_t va;
	uint32_t reloc;

	va = r600_resource_va(&rscreen->screen, (void*)rscreen->trace_bo);
	reloc = r600_context_bo_reloc(rctx, &rctx->rings.gfx, rscreen->trace_bo, RADEON_USAGE_READWRITE);
	r600_write_value(cs, PKT3(PKT3_MEM_WRITE, 3, 0));
	r600_write_value(cs, va & 0xFFFFFFFFUL);
	r600_write_value(cs, (va >> 32UL) & 0xFFUL);
	r600_write_value(cs, cs->cdw);
	r600_write_value(cs, rscreen->cs_count);
	r600_write_value(cs, PKT3(PKT3_NOP, 0, 0));
	r600_write_value(cs, reloc);
}
#endif