summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/radeon/r600_cs.c
blob: db8ef1905d5f500f6792e7f3dfd11e5115c2b9df (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
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
/*
 * Copyright 2008 Advanced Micro Devices, Inc.
 * Copyright 2008 Red Hat Inc.
 * Copyright 2009 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
 * 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 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 HOLDER(S) OR AUTHOR(S) 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
 *          Alex Deucher
 *          Jerome Glisse
 */
#include <linux/kernel.h>
#include "drmP.h"
#include "radeon.h"
#include "r600d.h"
#include "r600_reg_safe.h"

static int r600_cs_packet_next_reloc_mm(struct radeon_cs_parser *p,
					struct radeon_cs_reloc **cs_reloc);
static int r600_cs_packet_next_reloc_nomm(struct radeon_cs_parser *p,
					struct radeon_cs_reloc **cs_reloc);
typedef int (*next_reloc_t)(struct radeon_cs_parser*, struct radeon_cs_reloc**);
static next_reloc_t r600_cs_packet_next_reloc = &r600_cs_packet_next_reloc_mm;
extern void r600_cs_legacy_get_tiling_conf(struct drm_device *dev, u32 *npipes, u32 *nbanks, u32 *group_size);


struct r600_cs_track {
	/* configuration we miror so that we use same code btw kms/ums */
	u32			group_size;
	u32			nbanks;
	u32			npipes;
	/* value we track */
	u32			sq_config;
	u32			nsamples;
	u32			cb_color_base_last[8];
	struct radeon_bo	*cb_color_bo[8];
	u64			cb_color_bo_mc[8];
	u32			cb_color_bo_offset[8];
	struct radeon_bo	*cb_color_frag_bo[8];
	struct radeon_bo	*cb_color_tile_bo[8];
	u32			cb_color_info[8];
	u32			cb_color_size_idx[8];
	u32			cb_target_mask;
	u32			cb_shader_mask;
	u32			cb_color_size[8];
	u32			vgt_strmout_en;
	u32			vgt_strmout_buffer_en;
	u32			db_depth_control;
	u32			db_depth_info;
	u32			db_depth_size_idx;
	u32			db_depth_view;
	u32			db_depth_size;
	u32			db_offset;
	struct radeon_bo	*db_bo;
	u64			db_bo_mc;
};

#define FMT_8_BIT(fmt, vc)   [fmt] = { 1, 1, 1, vc, CHIP_R600 }
#define FMT_16_BIT(fmt, vc)  [fmt] = { 1, 1, 2, vc, CHIP_R600 }
#define FMT_24_BIT(fmt)      [fmt] = { 1, 1, 3,  0, CHIP_R600 }
#define FMT_32_BIT(fmt, vc)  [fmt] = { 1, 1, 4, vc, CHIP_R600 }
#define FMT_48_BIT(fmt)      [fmt] = { 1, 1, 6,  0, CHIP_R600 }
#define FMT_64_BIT(fmt, vc)  [fmt] = { 1, 1, 8, vc, CHIP_R600 }
#define FMT_96_BIT(fmt)      [fmt] = { 1, 1, 12, 0, CHIP_R600 }
#define FMT_128_BIT(fmt, vc) [fmt] = { 1, 1, 16,vc, CHIP_R600 }

struct gpu_formats {
	unsigned blockwidth;
	unsigned blockheight;
	unsigned blocksize;
	unsigned valid_color;
	enum radeon_family min_family;
};

static const struct gpu_formats color_formats_table[] = {
	/* 8 bit */
	FMT_8_BIT(V_038004_COLOR_8, 1),
	FMT_8_BIT(V_038004_COLOR_4_4, 1),
	FMT_8_BIT(V_038004_COLOR_3_3_2, 1),
	FMT_8_BIT(V_038004_FMT_1, 0),

	/* 16-bit */
	FMT_16_BIT(V_038004_COLOR_16, 1),
	FMT_16_BIT(V_038004_COLOR_16_FLOAT, 1),
	FMT_16_BIT(V_038004_COLOR_8_8, 1),
	FMT_16_BIT(V_038004_COLOR_5_6_5, 1),
	FMT_16_BIT(V_038004_COLOR_6_5_5, 1),
	FMT_16_BIT(V_038004_COLOR_1_5_5_5, 1),
	FMT_16_BIT(V_038004_COLOR_4_4_4_4, 1),
	FMT_16_BIT(V_038004_COLOR_5_5_5_1, 1),

	/* 24-bit */
	FMT_24_BIT(V_038004_FMT_8_8_8),
					       
	/* 32-bit */
	FMT_32_BIT(V_038004_COLOR_32, 1),
	FMT_32_BIT(V_038004_COLOR_32_FLOAT, 1),
	FMT_32_BIT(V_038004_COLOR_16_16, 1),
	FMT_32_BIT(V_038004_COLOR_16_16_FLOAT, 1),
	FMT_32_BIT(V_038004_COLOR_8_24, 1),
	FMT_32_BIT(V_038004_COLOR_8_24_FLOAT, 1),
	FMT_32_BIT(V_038004_COLOR_24_8, 1),
	FMT_32_BIT(V_038004_COLOR_24_8_FLOAT, 1),
	FMT_32_BIT(V_038004_COLOR_10_11_11, 1),
	FMT_32_BIT(V_038004_COLOR_10_11_11_FLOAT, 1),
	FMT_32_BIT(V_038004_COLOR_11_11_10, 1),
	FMT_32_BIT(V_038004_COLOR_11_11_10_FLOAT, 1),
	FMT_32_BIT(V_038004_COLOR_2_10_10_10, 1),
	FMT_32_BIT(V_038004_COLOR_8_8_8_8, 1),
	FMT_32_BIT(V_038004_COLOR_10_10_10_2, 1),
	FMT_32_BIT(V_038004_FMT_5_9_9_9_SHAREDEXP, 0),
	FMT_32_BIT(V_038004_FMT_32_AS_8, 0),
	FMT_32_BIT(V_038004_FMT_32_AS_8_8, 0),

	/* 48-bit */
	FMT_48_BIT(V_038004_FMT_16_16_16),
	FMT_48_BIT(V_038004_FMT_16_16_16_FLOAT),

	/* 64-bit */
	FMT_64_BIT(V_038004_COLOR_X24_8_32_FLOAT, 1),
	FMT_64_BIT(V_038004_COLOR_32_32, 1),
	FMT_64_BIT(V_038004_COLOR_32_32_FLOAT, 1),
	FMT_64_BIT(V_038004_COLOR_16_16_16_16, 1),
	FMT_64_BIT(V_038004_COLOR_16_16_16_16_FLOAT, 1),

	FMT_96_BIT(V_038004_FMT_32_32_32),
	FMT_96_BIT(V_038004_FMT_32_32_32_FLOAT),

	/* 128-bit */
	FMT_128_BIT(V_038004_COLOR_32_32_32_32, 1),
	FMT_128_BIT(V_038004_COLOR_32_32_32_32_FLOAT, 1),

	[V_038004_FMT_GB_GR] = { 2, 1, 4, 0 },
	[V_038004_FMT_BG_RG] = { 2, 1, 4, 0 },

	/* block compressed formats */
	[V_038004_FMT_BC1] = { 4, 4, 8, 0 },
	[V_038004_FMT_BC2] = { 4, 4, 16, 0 },
	[V_038004_FMT_BC3] = { 4, 4, 16, 0 },
	[V_038004_FMT_BC4] = { 4, 4, 8, 0 },
	[V_038004_FMT_BC5] = { 4, 4, 16, 0},
	[V_038004_FMT_BC6] = { 4, 4, 16, 0, CHIP_CEDAR}, /* Evergreen-only */
	[V_038004_FMT_BC7] = { 4, 4, 16, 0, CHIP_CEDAR}, /* Evergreen-only */

	/* The other Evergreen formats */
	[V_038004_FMT_32_AS_32_32_32_32] = { 1, 1, 4, 0, CHIP_CEDAR},
};

static inline bool fmt_is_valid_color(u32 format)
{
	if (format >= ARRAY_SIZE(color_formats_table))
		return false;
	
	if (color_formats_table[format].valid_color)
		return true;

	return false;
}

static inline bool fmt_is_valid_texture(u32 format, enum radeon_family family)
{
	if (format >= ARRAY_SIZE(color_formats_table))
		return false;
	
	if (family < color_formats_table[format].min_family)
		return false;

	if (color_formats_table[format].blockwidth > 0)
		return true;

	return false;
}

static inline int fmt_get_blocksize(u32 format)
{
	if (format >= ARRAY_SIZE(color_formats_table))
		return 0;

	return color_formats_table[format].blocksize;
}

static inline int fmt_get_nblocksx(u32 format, u32 w)
{
	unsigned bw;

	if (format >= ARRAY_SIZE(color_formats_table))
		return 0;

	bw = color_formats_table[format].blockwidth;
	if (bw == 0)
		return 0;

	return (w + bw - 1) / bw;
}

static inline int fmt_get_nblocksy(u32 format, u32 h)
{
	unsigned bh;

	if (format >= ARRAY_SIZE(color_formats_table))
		return 0;

	bh = color_formats_table[format].blockheight;
	if (bh == 0)
		return 0;

	return (h + bh - 1) / bh;
}

static inline int r600_bpe_from_format(u32 *bpe, u32 format)
{
 	unsigned res;

	if (format >= ARRAY_SIZE(color_formats_table))
		goto fail;

	res = color_formats_table[format].blocksize;
	if (res == 0)
		goto fail;

	*bpe = res;
	return 0;

fail:
	*bpe = 16;
	return -EINVAL;
}

struct array_mode_checker {
	int array_mode;
	u32 group_size;
	u32 nbanks;
	u32 npipes;
	u32 nsamples;
	u32 blocksize;
};

/* returns alignment in pixels for pitch/height/depth and bytes for base */
static inline int r600_get_array_mode_alignment(struct array_mode_checker *values,
						u32 *pitch_align,
						u32 *height_align,
						u32 *depth_align,
						u64 *base_align)
{
	u32 tile_width = 8;
	u32 tile_height = 8;
	u32 macro_tile_width = values->nbanks;
	u32 macro_tile_height = values->npipes;
	u32 tile_bytes = tile_width * tile_height * values->blocksize * values->nsamples;
	u32 macro_tile_bytes = macro_tile_width * macro_tile_height * tile_bytes;

	switch (values->array_mode) {
	case ARRAY_LINEAR_GENERAL:
		/* technically tile_width/_height for pitch/height */
		*pitch_align = 1; /* tile_width */
		*height_align = 1; /* tile_height */
		*depth_align = 1;
		*base_align = 1;
		break;
	case ARRAY_LINEAR_ALIGNED:
		*pitch_align = max((u32)64, (u32)(values->group_size / values->blocksize));
		*height_align = tile_height;
		*depth_align = 1;
		*base_align = values->group_size;
		break;
	case ARRAY_1D_TILED_THIN1:
		*pitch_align = max((u32)tile_width,
				   (u32)(values->group_size /
					 (tile_height * values->blocksize * values->nsamples)));
		*height_align = tile_height;
		*depth_align = 1;
		*base_align = values->group_size;
		break;
	case ARRAY_2D_TILED_THIN1:
		*pitch_align = max((u32)macro_tile_width,
				  (u32)(((values->group_size / tile_height) /
					 (values->blocksize * values->nsamples)) *
					values->nbanks)) * tile_width;
		*height_align = macro_tile_height * tile_height;
		*depth_align = 1;
		*base_align = max(macro_tile_bytes,
				  (*pitch_align) * values->blocksize * (*height_align) * values->nsamples);
		break;
	default:
		return -EINVAL;
	}

	return 0;
}

static void r600_cs_track_init(struct r600_cs_track *track)
{
	int i;

	/* assume DX9 mode */
	track->sq_config = DX9_CONSTS;
	for (i = 0; i < 8; i++) {
		track->cb_color_base_last[i] = 0;
		track->cb_color_size[i] = 0;
		track->cb_color_size_idx[i] = 0;
		track->cb_color_info[i] = 0;
		track->cb_color_bo[i] = NULL;
		track->cb_color_bo_offset[i] = 0xFFFFFFFF;
		track->cb_color_bo_mc[i] = 0xFFFFFFFF;
	}
	track->cb_target_mask = 0xFFFFFFFF;
	track->cb_shader_mask = 0xFFFFFFFF;
	track->db_bo = NULL;
	track->db_bo_mc = 0xFFFFFFFF;
	/* assume the biggest format and that htile is enabled */
	track->db_depth_info = 7 | (1 << 25);
	track->db_depth_view = 0xFFFFC000;
	track->db_depth_size = 0xFFFFFFFF;
	track->db_depth_size_idx = 0;
	track->db_depth_control = 0xFFFFFFFF;
}

static inline int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i)
{
	struct r600_cs_track *track = p->track;
	u32 slice_tile_max, size, tmp;
	u32 height, height_align, pitch, pitch_align, depth_align;
	u64 base_offset, base_align;
	struct array_mode_checker array_check;
	volatile u32 *ib = p->ib->ptr;
	unsigned array_mode;
	u32 format;
	if (G_0280A0_TILE_MODE(track->cb_color_info[i])) {
		dev_warn(p->dev, "FMASK or CMASK buffer are not supported by this kernel\n");
		return -EINVAL;
	}
	size = radeon_bo_size(track->cb_color_bo[i]) - track->cb_color_bo_offset[i];
	format = G_0280A0_FORMAT(track->cb_color_info[i]);
	if (!fmt_is_valid_color(format)) {
		dev_warn(p->dev, "%s:%d cb invalid format %d for %d (0x%08X)\n",
			 __func__, __LINE__, format,
			i, track->cb_color_info[i]);
		return -EINVAL;
	}
	/* pitch in pixels */
	pitch = (G_028060_PITCH_TILE_MAX(track->cb_color_size[i]) + 1) * 8;
	slice_tile_max = G_028060_SLICE_TILE_MAX(track->cb_color_size[i]) + 1;
	slice_tile_max *= 64;
	height = slice_tile_max / pitch;
	if (height > 8192)
		height = 8192;
	array_mode = G_0280A0_ARRAY_MODE(track->cb_color_info[i]);

	base_offset = track->cb_color_bo_mc[i] + track->cb_color_bo_offset[i];
	array_check.array_mode = array_mode;
	array_check.group_size = track->group_size;
	array_check.nbanks = track->nbanks;
	array_check.npipes = track->npipes;
	array_check.nsamples = track->nsamples;
	array_check.blocksize = fmt_get_blocksize(format);
	if (r600_get_array_mode_alignment(&array_check,
					  &pitch_align, &height_align, &depth_align, &base_align)) {
		dev_warn(p->dev, "%s invalid tiling %d for %d (0x%08X)\n", __func__,
			 G_0280A0_ARRAY_MODE(track->cb_color_info[i]), i,
			 track->cb_color_info[i]);
		return -EINVAL;
	}
	switch (array_mode) {
	case V_0280A0_ARRAY_LINEAR_GENERAL:
		break;
	case V_0280A0_ARRAY_LINEAR_ALIGNED:
		break;
	case V_0280A0_ARRAY_1D_TILED_THIN1:
		/* avoid breaking userspace */
		if (height > 7)
			height &= ~0x7;
		break;
	case V_0280A0_ARRAY_2D_TILED_THIN1:
		break;
	default:
		dev_warn(p->dev, "%s invalid tiling %d for %d (0x%08X)\n", __func__,
			G_0280A0_ARRAY_MODE(track->cb_color_info[i]), i,
			track->cb_color_info[i]);
		return -EINVAL;
	}

	if (!IS_ALIGNED(pitch, pitch_align)) {
		dev_warn(p->dev, "%s:%d cb pitch (%d, 0x%x, %d) invalid\n",
			 __func__, __LINE__, pitch, pitch_align, array_mode);
		return -EINVAL;
	}
	if (!IS_ALIGNED(height, height_align)) {
		dev_warn(p->dev, "%s:%d cb height (%d, 0x%x, %d) invalid\n",
			 __func__, __LINE__, height, height_align, array_mode);
		return -EINVAL;
	}
	if (!IS_ALIGNED(base_offset, base_align)) {
		dev_warn(p->dev, "%s offset[%d] 0x%llx 0x%llx, %d not aligned\n", __func__, i,
			 base_offset, base_align, array_mode);
		return -EINVAL;
	}

	/* check offset */
	tmp = fmt_get_nblocksy(format, height) * fmt_get_nblocksx(format, pitch) * fmt_get_blocksize(format);
	if ((tmp + track->cb_color_bo_offset[i]) > radeon_bo_size(track->cb_color_bo[i])) {
		if (array_mode == V_0280A0_ARRAY_LINEAR_GENERAL) {
			/* the initial DDX does bad things with the CB size occasionally */
			/* it rounds up height too far for slice tile max but the BO is smaller */
			/* r600c,g also seem to flush at bad times in some apps resulting in
			 * bogus values here. So for linear just allow anything to avoid breaking
			 * broken userspace.
			 */
		} else {
			dev_warn(p->dev, "%s offset[%d] %d %d %d %lu too big\n", __func__, i,
				 array_mode,
				 track->cb_color_bo_offset[i], tmp,
				 radeon_bo_size(track->cb_color_bo[i]));
			return -EINVAL;
		}
	}
	/* limit max tile */
	tmp = (height * pitch) >> 6;
	if (tmp < slice_tile_max)
		slice_tile_max = tmp;
	tmp = S_028060_PITCH_TILE_MAX((pitch / 8) - 1) |
		S_028060_SLICE_TILE_MAX(slice_tile_max - 1);
	ib[track->cb_color_size_idx[i]] = tmp;
	return 0;
}

static int r600_cs_track_check(struct radeon_cs_parser *p)
{
	struct r600_cs_track *track = p->track;
	u32 tmp;
	int r, i;
	volatile u32 *ib = p->ib->ptr;

	/* on legacy kernel we don't perform advanced check */
	if (p->rdev == NULL)
		return 0;
	/* we don't support out buffer yet */
	if (track->vgt_strmout_en || track->vgt_strmout_buffer_en) {
		dev_warn(p->dev, "this kernel doesn't support SMX output buffer\n");
		return -EINVAL;
	}
	/* check that we have a cb for each enabled target, we don't check
	 * shader_mask because it seems mesa isn't always setting it :(
	 */
	tmp = track->cb_target_mask;
	for (i = 0; i < 8; i++) {
		if ((tmp >> (i * 4)) & 0xF) {
			/* at least one component is enabled */
			if (track->cb_color_bo[i] == NULL) {
				dev_warn(p->dev, "%s:%d mask 0x%08X | 0x%08X no cb for %d\n",
					__func__, __LINE__, track->cb_target_mask, track->cb_shader_mask, i);
				return -EINVAL;
			}
			/* perform rewrite of CB_COLOR[0-7]_SIZE */
			r = r600_cs_track_validate_cb(p, i);
			if (r)
				return r;
		}
	}
	/* Check depth buffer */
	if (G_028800_STENCIL_ENABLE(track->db_depth_control) ||
		G_028800_Z_ENABLE(track->db_depth_control)) {
		u32 nviews, bpe, ntiles, size, slice_tile_max;
		u32 height, height_align, pitch, pitch_align, depth_align;
		u64 base_offset, base_align;
		struct array_mode_checker array_check;
		int array_mode;

		if (track->db_bo == NULL) {
			dev_warn(p->dev, "z/stencil with no depth buffer\n");
			return -EINVAL;
		}
		if (G_028010_TILE_SURFACE_ENABLE(track->db_depth_info)) {
			dev_warn(p->dev, "this kernel doesn't support z/stencil htile\n");
			return -EINVAL;
		}
		switch (G_028010_FORMAT(track->db_depth_info)) {
		case V_028010_DEPTH_16:
			bpe = 2;
			break;
		case V_028010_DEPTH_X8_24:
		case V_028010_DEPTH_8_24:
		case V_028010_DEPTH_X8_24_FLOAT:
		case V_028010_DEPTH_8_24_FLOAT:
		case V_028010_DEPTH_32_FLOAT:
			bpe = 4;
			break;
		case V_028010_DEPTH_X24_8_32_FLOAT:
			bpe = 8;
			break;
		default:
			dev_warn(p->dev, "z/stencil with invalid format %d\n", G_028010_FORMAT(track->db_depth_info));
			return -EINVAL;
		}
		if ((track->db_depth_size & 0xFFFFFC00) == 0xFFFFFC00) {
			if (!track->db_depth_size_idx) {
				dev_warn(p->dev, "z/stencil buffer size not set\n");
				return -EINVAL;
			}
			tmp = radeon_bo_size(track->db_bo) - track->db_offset;
			tmp = (tmp / bpe) >> 6;
			if (!tmp) {
				dev_warn(p->dev, "z/stencil buffer too small (0x%08X %d %d %ld)\n",
						track->db_depth_size, bpe, track->db_offset,
						radeon_bo_size(track->db_bo));
				return -EINVAL;
			}
			ib[track->db_depth_size_idx] = S_028000_SLICE_TILE_MAX(tmp - 1) | (track->db_depth_size & 0x3FF);
		} else {
			size = radeon_bo_size(track->db_bo);
			/* pitch in pixels */
			pitch = (G_028000_PITCH_TILE_MAX(track->db_depth_size) + 1) * 8;
			slice_tile_max = G_028000_SLICE_TILE_MAX(track->db_depth_size) + 1;
			slice_tile_max *= 64;
			height = slice_tile_max / pitch;
			if (height > 8192)
				height = 8192;
			base_offset = track->db_bo_mc + track->db_offset;
			array_mode = G_028010_ARRAY_MODE(track->db_depth_info);
			array_check.array_mode = array_mode;
			array_check.group_size = track->group_size;
			array_check.nbanks = track->nbanks;
			array_check.npipes = track->npipes;
			array_check.nsamples = track->nsamples;
			array_check.blocksize = bpe;
			if (r600_get_array_mode_alignment(&array_check,
							  &pitch_align, &height_align, &depth_align, &base_align)) {
				dev_warn(p->dev, "%s invalid tiling %d (0x%08X)\n", __func__,
					 G_028010_ARRAY_MODE(track->db_depth_info),
					 track->db_depth_info);
				return -EINVAL;
			}
			switch (array_mode) {
			case V_028010_ARRAY_1D_TILED_THIN1:
				/* don't break userspace */
				height &= ~0x7;
				break;
			case V_028010_ARRAY_2D_TILED_THIN1:
				break;
			default:
				dev_warn(p->dev, "%s invalid tiling %d (0x%08X)\n", __func__,
					 G_028010_ARRAY_MODE(track->db_depth_info),
					 track->db_depth_info);
				return -EINVAL;
			}

			if (!IS_ALIGNED(pitch, pitch_align)) {
				dev_warn(p->dev, "%s:%d db pitch (%d, 0x%x, %d) invalid\n",
					 __func__, __LINE__, pitch, pitch_align, array_mode);
				return -EINVAL;
			}
			if (!IS_ALIGNED(height, height_align)) {
				dev_warn(p->dev, "%s:%d db height (%d, 0x%x, %d) invalid\n",
					 __func__, __LINE__, height, height_align, array_mode);
				return -EINVAL;
			}
			if (!IS_ALIGNED(base_offset, base_align)) {
				dev_warn(p->dev, "%s offset[%d] 0x%llx, 0x%llx, %d not aligned\n", __func__, i,
					 base_offset, base_align, array_mode);
				return -EINVAL;
			}

			ntiles = G_028000_SLICE_TILE_MAX(track->db_depth_size) + 1;
			nviews = G_028004_SLICE_MAX(track->db_depth_view) + 1;
			tmp = ntiles * bpe * 64 * nviews;
			if ((tmp + track->db_offset) > radeon_bo_size(track->db_bo)) {
				dev_warn(p->dev, "z/stencil buffer (%d) too small (0x%08X %d %d %d -> %u have %lu)\n",
					 array_mode,
					 track->db_depth_size, ntiles, nviews, bpe, tmp + track->db_offset,
					 radeon_bo_size(track->db_bo));
				return -EINVAL;
			}
		}
	}
	return 0;
}

/**
 * r600_cs_packet_parse() - parse cp packet and point ib index to next packet
 * @parser:	parser structure holding parsing context.
 * @pkt:	where to store packet informations
 *
 * Assume that chunk_ib_index is properly set. Will return -EINVAL
 * if packet is bigger than remaining ib size. or if packets is unknown.
 **/
int r600_cs_packet_parse(struct radeon_cs_parser *p,
			struct radeon_cs_packet *pkt,
			unsigned idx)
{
	struct radeon_cs_chunk *ib_chunk = &p->chunks[p->chunk_ib_idx];
	uint32_t header;

	if (idx >= ib_chunk->length_dw) {
		DRM_ERROR("Can not parse packet at %d after CS end %d !\n",
			  idx, ib_chunk->length_dw);
		return -EINVAL;
	}
	header = radeon_get_ib_value(p, idx);
	pkt->idx = idx;
	pkt->type = CP_PACKET_GET_TYPE(header);
	pkt->count = CP_PACKET_GET_COUNT(header);
	pkt->one_reg_wr = 0;
	switch (pkt->type) {
	case PACKET_TYPE0:
		pkt->reg = CP_PACKET0_GET_REG(header);
		break;
	case PACKET_TYPE3:
		pkt->opcode = CP_PACKET3_GET_OPCODE(header);
		break;
	case PACKET_TYPE2:
		pkt->count = -1;
		break;
	default:
		DRM_ERROR("Unknown packet type %d at %d !\n", pkt->type, idx);
		return -EINVAL;
	}
	if ((pkt->count + 1 + pkt->idx) >= ib_chunk->length_dw) {
		DRM_ERROR("Packet (%d:%d:%d) end after CS buffer (%d) !\n",
			  pkt->idx, pkt->type, pkt->count, ib_chunk->length_dw);
		return -EINVAL;
	}
	return 0;
}

/**
 * r600_cs_packet_next_reloc_mm() - parse next packet which should be reloc packet3
 * @parser:		parser structure holding parsing context.
 * @data:		pointer to relocation data
 * @offset_start:	starting offset
 * @offset_mask:	offset mask (to align start offset on)
 * @reloc:		reloc informations
 *
 * Check next packet is relocation packet3, do bo validation and compute
 * GPU offset using the provided start.
 **/
static int r600_cs_packet_next_reloc_mm(struct radeon_cs_parser *p,
					struct radeon_cs_reloc **cs_reloc)
{
	struct radeon_cs_chunk *relocs_chunk;
	struct radeon_cs_packet p3reloc;
	unsigned idx;
	int r;

	if (p->chunk_relocs_idx == -1) {
		DRM_ERROR("No relocation chunk !\n");
		return -EINVAL;
	}
	*cs_reloc = NULL;
	relocs_chunk = &p->chunks[p->chunk_relocs_idx];
	r = r600_cs_packet_parse(p, &p3reloc, p->idx);
	if (r) {
		return r;
	}
	p->idx += p3reloc.count + 2;
	if (p3reloc.type != PACKET_TYPE3 || p3reloc.opcode != PACKET3_NOP) {
		DRM_ERROR("No packet3 for relocation for packet at %d.\n",
			  p3reloc.idx);
		return -EINVAL;
	}
	idx = radeon_get_ib_value(p, p3reloc.idx + 1);
	if (idx >= relocs_chunk->length_dw) {
		DRM_ERROR("Relocs at %d after relocations chunk end %d !\n",
			  idx, relocs_chunk->length_dw);
		return -EINVAL;
	}
	/* FIXME: we assume reloc size is 4 dwords */
	*cs_reloc = p->relocs_ptr[(idx / 4)];
	return 0;
}

/**
 * r600_cs_packet_next_reloc_nomm() - parse next packet which should be reloc packet3
 * @parser:		parser structure holding parsing context.
 * @data:		pointer to relocation data
 * @offset_start:	starting offset
 * @offset_mask:	offset mask (to align start offset on)
 * @reloc:		reloc informations
 *
 * Check next packet is relocation packet3, do bo validation and compute
 * GPU offset using the provided start.
 **/
static int r600_cs_packet_next_reloc_nomm(struct radeon_cs_parser *p,
					struct radeon_cs_reloc **cs_reloc)
{
	struct radeon_cs_chunk *relocs_chunk;
	struct radeon_cs_packet p3reloc;
	unsigned idx;
	int r;

	if (p->chunk_relocs_idx == -1) {
		DRM_ERROR("No relocation chunk !\n");
		return -EINVAL;
	}
	*cs_reloc = NULL;
	relocs_chunk = &p->chunks[p->chunk_relocs_idx];
	r = r600_cs_packet_parse(p, &p3reloc, p->idx);
	if (r) {
		return r;
	}
	p->idx += p3reloc.count + 2;
	if (p3reloc.type != PACKET_TYPE3 || p3reloc.opcode != PACKET3_NOP) {
		DRM_ERROR("No packet3 for relocation for packet at %d.\n",
			  p3reloc.idx);
		return -EINVAL;
	}
	idx = radeon_get_ib_value(p, p3reloc.idx + 1);
	if (idx >= relocs_chunk->length_dw) {
		DRM_ERROR("Relocs at %d after relocations chunk end %d !\n",
			  idx, relocs_chunk->length_dw);
		return -EINVAL;
	}
	*cs_reloc = p->relocs;
	(*cs_reloc)->lobj.gpu_offset = (u64)relocs_chunk->kdata[idx + 3] << 32;
	(*cs_reloc)->lobj.gpu_offset |= relocs_chunk->kdata[idx + 0];
	return 0;
}

/**
 * r600_cs_packet_next_is_pkt3_nop() - test if next packet is packet3 nop for reloc
 * @parser:		parser structure holding parsing context.
 *
 * Check next packet is relocation packet3, do bo validation and compute
 * GPU offset using the provided start.
 **/
static inline int r600_cs_packet_next_is_pkt3_nop(struct radeon_cs_parser *p)
{
	struct radeon_cs_packet p3reloc;
	int r;

	r = r600_cs_packet_parse(p, &p3reloc, p->idx);
	if (r) {
		return 0;
	}
	if (p3reloc.type != PACKET_TYPE3 || p3reloc.opcode != PACKET3_NOP) {
		return 0;
	}
	return 1;
}

/**
 * r600_cs_packet_next_vline() - parse userspace VLINE packet
 * @parser:		parser structure holding parsing context.
 *
 * Userspace sends a special sequence for VLINE waits.
 * PACKET0 - VLINE_START_END + value
 * PACKET3 - WAIT_REG_MEM poll vline status reg
 * RELOC (P3) - crtc_id in reloc.
 *
 * This function parses this and relocates the VLINE START END
 * and WAIT_REG_MEM packets to the correct crtc.
 * It also detects a switched off crtc and nulls out the
 * wait in that case.
 */
static int r600_cs_packet_parse_vline(struct radeon_cs_parser *p)
{
	struct drm_mode_object *obj;
	struct drm_crtc *crtc;
	struct radeon_crtc *radeon_crtc;
	struct radeon_cs_packet p3reloc, wait_reg_mem;
	int crtc_id;
	int r;
	uint32_t header, h_idx, reg, wait_reg_mem_info;
	volatile uint32_t *ib;

	ib = p->ib->ptr;

	/* parse the WAIT_REG_MEM */
	r = r600_cs_packet_parse(p, &wait_reg_mem, p->idx);
	if (r)
		return r;

	/* check its a WAIT_REG_MEM */
	if (wait_reg_mem.type != PACKET_TYPE3 ||
	    wait_reg_mem.opcode != PACKET3_WAIT_REG_MEM) {
		DRM_ERROR("vline wait missing WAIT_REG_MEM segment\n");
		return -EINVAL;
	}

	wait_reg_mem_info = radeon_get_ib_value(p, wait_reg_mem.idx + 1);
	/* bit 4 is reg (0) or mem (1) */
	if (wait_reg_mem_info & 0x10) {
		DRM_ERROR("vline WAIT_REG_MEM waiting on MEM rather than REG\n");
		return -EINVAL;
	}
	/* waiting for value to be equal */
	if ((wait_reg_mem_info & 0x7) != 0x3) {
		DRM_ERROR("vline WAIT_REG_MEM function not equal\n");
		return -EINVAL;
	}
	if ((radeon_get_ib_value(p, wait_reg_mem.idx + 2) << 2) != AVIVO_D1MODE_VLINE_STATUS) {
		DRM_ERROR("vline WAIT_REG_MEM bad reg\n");
		return -EINVAL;
	}

	if (radeon_get_ib_value(p, wait_reg_mem.idx + 5) != AVIVO_D1MODE_VLINE_STAT) {
		DRM_ERROR("vline WAIT_REG_MEM bad bit mask\n");
		return -EINVAL;
	}

	/* jump over the NOP */
	r = r600_cs_packet_parse(p, &p3reloc, p->idx + wait_reg_mem.count + 2);
	if (r)
		return r;

	h_idx = p->idx - 2;
	p->idx += wait_reg_mem.count + 2;
	p->idx += p3reloc.count + 2;

	header = radeon_get_ib_value(p, h_idx);
	crtc_id = radeon_get_ib_value(p, h_idx + 2 + 7 + 1);
	reg = CP_PACKET0_GET_REG(header);

	obj = drm_mode_object_find(p->rdev->ddev, crtc_id, DRM_MODE_OBJECT_CRTC);
	if (!obj) {
		DRM_ERROR("cannot find crtc %d\n", crtc_id);
		return -EINVAL;
	}
	crtc = obj_to_crtc(obj);
	radeon_crtc = to_radeon_crtc(crtc);
	crtc_id = radeon_crtc->crtc_id;

	if (!crtc->enabled) {
		/* if the CRTC isn't enabled - we need to nop out the WAIT_REG_MEM */
		ib[h_idx + 2] = PACKET2(0);
		ib[h_idx + 3] = PACKET2(0);
		ib[h_idx + 4] = PACKET2(0);
		ib[h_idx + 5] = PACKET2(0);
		ib[h_idx + 6] = PACKET2(0);
		ib[h_idx + 7] = PACKET2(0);
		ib[h_idx + 8] = PACKET2(0);
	} else if (crtc_id == 1) {
		switch (reg) {
		case AVIVO_D1MODE_VLINE_START_END:
			header &= ~R600_CP_PACKET0_REG_MASK;
			header |= AVIVO_D2MODE_VLINE_START_END >> 2;
			break;
		default:
			DRM_ERROR("unknown crtc reloc\n");
			return -EINVAL;
		}
		ib[h_idx] = header;
		ib[h_idx + 4] = AVIVO_D2MODE_VLINE_STATUS >> 2;
	}

	return 0;
}

static int r600_packet0_check(struct radeon_cs_parser *p,
				struct radeon_cs_packet *pkt,
				unsigned idx, unsigned reg)
{
	int r;

	switch (reg) {
	case AVIVO_D1MODE_VLINE_START_END:
		r = r600_cs_packet_parse_vline(p);
		if (r) {
			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
					idx, reg);
			return r;
		}
		break;
	default:
		printk(KERN_ERR "Forbidden register 0x%04X in cs at %d\n",
		       reg, idx);
		return -EINVAL;
	}
	return 0;
}

static int r600_cs_parse_packet0(struct radeon_cs_parser *p,
				struct radeon_cs_packet *pkt)
{
	unsigned reg, i;
	unsigned idx;
	int r;

	idx = pkt->idx + 1;
	reg = pkt->reg;
	for (i = 0; i <= pkt->count; i++, idx++, reg += 4) {
		r = r600_packet0_check(p, pkt, idx, reg);
		if (r) {
			return r;
		}
	}
	return 0;
}

/**
 * r600_cs_check_reg() - check if register is authorized or not
 * @parser: parser structure holding parsing context
 * @reg: register we are testing
 * @idx: index into the cs buffer
 *
 * This function will test against r600_reg_safe_bm and return 0
 * if register is safe. If register is not flag as safe this function
 * will test it against a list of register needind special handling.
 */
static inline int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
{
	struct r600_cs_track *track = (struct r600_cs_track *)p->track;
	struct radeon_cs_reloc *reloc;
	u32 last_reg = ARRAY_SIZE(r600_reg_safe_bm);
	u32 m, i, tmp, *ib;
	int r;

	i = (reg >> 7);
	if (i > last_reg) {
		dev_warn(p->dev, "forbidden register 0x%08x at %d\n", reg, idx);
		return -EINVAL;
	}
	m = 1 << ((reg >> 2) & 31);
	if (!(r600_reg_safe_bm[i] & m))
		return 0;
	ib = p->ib->ptr;
	switch (reg) {
	/* force following reg to 0 in an attempt to disable out buffer
	 * which will need us to better understand how it works to perform
	 * security check on it (Jerome)
	 */
	case R_0288A8_SQ_ESGS_RING_ITEMSIZE:
	case R_008C44_SQ_ESGS_RING_SIZE:
	case R_0288B0_SQ_ESTMP_RING_ITEMSIZE:
	case R_008C54_SQ_ESTMP_RING_SIZE:
	case R_0288C0_SQ_FBUF_RING_ITEMSIZE:
	case R_008C74_SQ_FBUF_RING_SIZE:
	case R_0288B4_SQ_GSTMP_RING_ITEMSIZE:
	case R_008C5C_SQ_GSTMP_RING_SIZE:
	case R_0288AC_SQ_GSVS_RING_ITEMSIZE:
	case R_008C4C_SQ_GSVS_RING_SIZE:
	case R_0288BC_SQ_PSTMP_RING_ITEMSIZE:
	case R_008C6C_SQ_PSTMP_RING_SIZE:
	case R_0288C4_SQ_REDUC_RING_ITEMSIZE:
	case R_008C7C_SQ_REDUC_RING_SIZE:
	case R_0288B8_SQ_VSTMP_RING_ITEMSIZE:
	case R_008C64_SQ_VSTMP_RING_SIZE:
	case R_0288C8_SQ_GS_VERT_ITEMSIZE:
		/* get value to populate the IB don't remove */
		tmp =radeon_get_ib_value(p, idx);
		ib[idx] = 0;
		break;
	case SQ_CONFIG:
		track->sq_config = radeon_get_ib_value(p, idx);
		break;
	case R_028800_DB_DEPTH_CONTROL:
		track->db_depth_control = radeon_get_ib_value(p, idx);
		break;
	case R_028010_DB_DEPTH_INFO:
		if (r600_cs_packet_next_is_pkt3_nop(p)) {
			r = r600_cs_packet_next_reloc(p, &reloc);
			if (r) {
				dev_warn(p->dev, "bad SET_CONTEXT_REG "
					 "0x%04X\n", reg);
				return -EINVAL;
			}
			track->db_depth_info = radeon_get_ib_value(p, idx);
			ib[idx] &= C_028010_ARRAY_MODE;
			track->db_depth_info &= C_028010_ARRAY_MODE;
			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
				ib[idx] |= S_028010_ARRAY_MODE(V_028010_ARRAY_2D_TILED_THIN1);
				track->db_depth_info |= S_028010_ARRAY_MODE(V_028010_ARRAY_2D_TILED_THIN1);
			} else {
				ib[idx] |= S_028010_ARRAY_MODE(V_028010_ARRAY_1D_TILED_THIN1);
				track->db_depth_info |= S_028010_ARRAY_MODE(V_028010_ARRAY_1D_TILED_THIN1);
			}
		} else
			track->db_depth_info = radeon_get_ib_value(p, idx);
		break;
	case R_028004_DB_DEPTH_VIEW:
		track->db_depth_view = radeon_get_ib_value(p, idx);
		break;
	case R_028000_DB_DEPTH_SIZE:
		track->db_depth_size = radeon_get_ib_value(p, idx);
		track->db_depth_size_idx = idx;
		break;
	case R_028AB0_VGT_STRMOUT_EN:
		track->vgt_strmout_en = radeon_get_ib_value(p, idx);
		break;
	case R_028B20_VGT_STRMOUT_BUFFER_EN:
		track->vgt_strmout_buffer_en = radeon_get_ib_value(p, idx);
		break;
	case R_028238_CB_TARGET_MASK:
		track->cb_target_mask = radeon_get_ib_value(p, idx);
		break;
	case R_02823C_CB_SHADER_MASK:
		track->cb_shader_mask = radeon_get_ib_value(p, idx);
		break;
	case R_028C04_PA_SC_AA_CONFIG:
		tmp = G_028C04_MSAA_NUM_SAMPLES(radeon_get_ib_value(p, idx));
		track->nsamples = 1 << tmp;
		break;
	case R_0280A0_CB_COLOR0_INFO:
	case R_0280A4_CB_COLOR1_INFO:
	case R_0280A8_CB_COLOR2_INFO:
	case R_0280AC_CB_COLOR3_INFO:
	case R_0280B0_CB_COLOR4_INFO:
	case R_0280B4_CB_COLOR5_INFO:
	case R_0280B8_CB_COLOR6_INFO:
	case R_0280BC_CB_COLOR7_INFO:
		if (r600_cs_packet_next_is_pkt3_nop(p)) {
			r = r600_cs_packet_next_reloc(p, &reloc);
			if (r) {
				dev_err(p->dev, "bad SET_CONTEXT_REG 0x%04X\n", reg);
				return -EINVAL;
			}
			tmp = (reg - R_0280A0_CB_COLOR0_INFO) / 4;
			track->cb_color_info[tmp] = radeon_get_ib_value(p, idx);
			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
				ib[idx] |= S_0280A0_ARRAY_MODE(V_0280A0_ARRAY_2D_TILED_THIN1);
				track->cb_color_info[tmp] |= S_0280A0_ARRAY_MODE(V_0280A0_ARRAY_2D_TILED_THIN1);
			} else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO) {
				ib[idx] |= S_0280A0_ARRAY_MODE(V_0280A0_ARRAY_1D_TILED_THIN1);
				track->cb_color_info[tmp] |= S_0280A0_ARRAY_MODE(V_0280A0_ARRAY_1D_TILED_THIN1);
			}
		} else {
			tmp = (reg - R_0280A0_CB_COLOR0_INFO) / 4;
			track->cb_color_info[tmp] = radeon_get_ib_value(p, idx);
		}
		break;
	case R_028060_CB_COLOR0_SIZE:
	case R_028064_CB_COLOR1_SIZE:
	case R_028068_CB_COLOR2_SIZE:
	case R_02806C_CB_COLOR3_SIZE:
	case R_028070_CB_COLOR4_SIZE:
	case R_028074_CB_COLOR5_SIZE:
	case R_028078_CB_COLOR6_SIZE:
	case R_02807C_CB_COLOR7_SIZE:
		tmp = (reg - R_028060_CB_COLOR0_SIZE) / 4;
		track->cb_color_size[tmp] = radeon_get_ib_value(p, idx);
		track->cb_color_size_idx[tmp] = idx;
		break;
		/* This register were added late, there is userspace
		 * which does provide relocation for those but set
		 * 0 offset. In order to avoid breaking old userspace
		 * we detect this and set address to point to last
		 * CB_COLOR0_BASE, note that if userspace doesn't set
		 * CB_COLOR0_BASE before this register we will report
		 * error. Old userspace always set CB_COLOR0_BASE
		 * before any of this.
		 */
	case R_0280E0_CB_COLOR0_FRAG:
	case R_0280E4_CB_COLOR1_FRAG:
	case R_0280E8_CB_COLOR2_FRAG:
	case R_0280EC_CB_COLOR3_FRAG:
	case R_0280F0_CB_COLOR4_FRAG:
	case R_0280F4_CB_COLOR5_FRAG:
	case R_0280F8_CB_COLOR6_FRAG:
	case R_0280FC_CB_COLOR7_FRAG:
		tmp = (reg - R_0280E0_CB_COLOR0_FRAG) / 4;
		if (!r600_cs_packet_next_is_pkt3_nop(p)) {
			if (!track->cb_color_base_last[tmp]) {
				dev_err(p->dev, "Broken old userspace ? no cb_color0_base supplied before trying to write 0x%08X\n", reg);
				return -EINVAL;
			}
			ib[idx] = track->cb_color_base_last[tmp];
			track->cb_color_frag_bo[tmp] = track->cb_color_bo[tmp];
		} else {
			r = r600_cs_packet_next_reloc(p, &reloc);
			if (r) {
				dev_err(p->dev, "bad SET_CONTEXT_REG 0x%04X\n", reg);
				return -EINVAL;
			}
			ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
			track->cb_color_frag_bo[tmp] = reloc->robj;
		}
		break;
	case R_0280C0_CB_COLOR0_TILE:
	case R_0280C4_CB_COLOR1_TILE:
	case R_0280C8_CB_COLOR2_TILE:
	case R_0280CC_CB_COLOR3_TILE:
	case R_0280D0_CB_COLOR4_TILE:
	case R_0280D4_CB_COLOR5_TILE:
	case R_0280D8_CB_COLOR6_TILE:
	case R_0280DC_CB_COLOR7_TILE:
		tmp = (reg - R_0280C0_CB_COLOR0_TILE) / 4;
		if (!r600_cs_packet_next_is_pkt3_nop(p)) {
			if (!track->cb_color_base_last[tmp]) {
				dev_err(p->dev, "Broken old userspace ? no cb_color0_base supplied before trying to write 0x%08X\n", reg);
				return -EINVAL;
			}
			ib[idx] = track->cb_color_base_last[tmp];
			track->cb_color_tile_bo[tmp] = track->cb_color_bo[tmp];
		} else {
			r = r600_cs_packet_next_reloc(p, &reloc);
			if (r) {
				dev_err(p->dev, "bad SET_CONTEXT_REG 0x%04X\n", reg);
				return -EINVAL;
			}
			ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
			track->cb_color_tile_bo[tmp] = reloc->robj;
		}
		break;
	case CB_COLOR0_BASE:
	case CB_COLOR1_BASE:
	case CB_COLOR2_BASE:
	case CB_COLOR3_BASE:
	case CB_COLOR4_BASE:
	case CB_COLOR5_BASE:
	case CB_COLOR6_BASE:
	case CB_COLOR7_BASE:
		r = r600_cs_packet_next_reloc(p, &reloc);
		if (r) {
			dev_warn(p->dev, "bad SET_CONTEXT_REG "
					"0x%04X\n", reg);
			return -EINVAL;
		}
		tmp = (reg - CB_COLOR0_BASE) / 4;
		track->cb_color_bo_offset[tmp] = radeon_get_ib_value(p, idx) << 8;
		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
		track->cb_color_base_last[tmp] = ib[idx];
		track->cb_color_bo[tmp] = reloc->robj;
		track->cb_color_bo_mc[tmp] = reloc->lobj.gpu_offset;
		break;
	case DB_DEPTH_BASE:
		r = r600_cs_packet_next_reloc(p, &reloc);
		if (r) {
			dev_warn(p->dev, "bad SET_CONTEXT_REG "
					"0x%04X\n", reg);
			return -EINVAL;
		}
		track->db_offset = radeon_get_ib_value(p, idx) << 8;
		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
		track->db_bo = reloc->robj;
		track->db_bo_mc = reloc->lobj.gpu_offset;
		break;
	case DB_HTILE_DATA_BASE:
	case SQ_PGM_START_FS:
	case SQ_PGM_START_ES:
	case SQ_PGM_START_VS:
	case SQ_PGM_START_GS:
	case SQ_PGM_START_PS:
	case SQ_ALU_CONST_CACHE_GS_0:
	case SQ_ALU_CONST_CACHE_GS_1:
	case SQ_ALU_CONST_CACHE_GS_2:
	case SQ_ALU_CONST_CACHE_GS_3:
	case SQ_ALU_CONST_CACHE_GS_4:
	case SQ_ALU_CONST_CACHE_GS_5:
	case SQ_ALU_CONST_CACHE_GS_6:
	case SQ_ALU_CONST_CACHE_GS_7:
	case SQ_ALU_CONST_CACHE_GS_8:
	case SQ_ALU_CONST_CACHE_GS_9:
	case SQ_ALU_CONST_CACHE_GS_10:
	case SQ_ALU_CONST_CACHE_GS_11:
	case SQ_ALU_CONST_CACHE_GS_12:
	case SQ_ALU_CONST_CACHE_GS_13:
	case SQ_ALU_CONST_CACHE_GS_14:
	case SQ_ALU_CONST_CACHE_GS_15:
	case SQ_ALU_CONST_CACHE_PS_0:
	case SQ_ALU_CONST_CACHE_PS_1:
	case SQ_ALU_CONST_CACHE_PS_2:
	case SQ_ALU_CONST_CACHE_PS_3:
	case SQ_ALU_CONST_CACHE_PS_4:
	case SQ_ALU_CONST_CACHE_PS_5:
	case SQ_ALU_CONST_CACHE_PS_6:
	case SQ_ALU_CONST_CACHE_PS_7:
	case SQ_ALU_CONST_CACHE_PS_8:
	case SQ_ALU_CONST_CACHE_PS_9:
	case SQ_ALU_CONST_CACHE_PS_10:
	case SQ_ALU_CONST_CACHE_PS_11:
	case SQ_ALU_CONST_CACHE_PS_12:
	case SQ_ALU_CONST_CACHE_PS_13:
	case SQ_ALU_CONST_CACHE_PS_14:
	case SQ_ALU_CONST_CACHE_PS_15:
	case SQ_ALU_CONST_CACHE_VS_0:
	case SQ_ALU_CONST_CACHE_VS_1:
	case SQ_ALU_CONST_CACHE_VS_2:
	case SQ_ALU_CONST_CACHE_VS_3:
	case SQ_ALU_CONST_CACHE_VS_4:
	case SQ_ALU_CONST_CACHE_VS_5:
	case SQ_ALU_CONST_CACHE_VS_6:
	case SQ_ALU_CONST_CACHE_VS_7:
	case SQ_ALU_CONST_CACHE_VS_8:
	case SQ_ALU_CONST_CACHE_VS_9:
	case SQ_ALU_CONST_CACHE_VS_10:
	case SQ_ALU_CONST_CACHE_VS_11:
	case SQ_ALU_CONST_CACHE_VS_12:
	case SQ_ALU_CONST_CACHE_VS_13:
	case SQ_ALU_CONST_CACHE_VS_14:
	case SQ_ALU_CONST_CACHE_VS_15:
		r = r600_cs_packet_next_reloc(p, &reloc);
		if (r) {
			dev_warn(p->dev, "bad SET_CONTEXT_REG "
					"0x%04X\n", reg);
			return -EINVAL;
		}
		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
		break;
	case SX_MEMORY_EXPORT_BASE:
		r = r600_cs_packet_next_reloc(p, &reloc);
		if (r) {
			dev_warn(p->dev, "bad SET_CONFIG_REG "
					"0x%04X\n", reg);
			return -EINVAL;
		}
		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
		break;
	default:
		dev_warn(p->dev, "forbidden register 0x%08x at %d\n", reg, idx);
		return -EINVAL;
	}
	return 0;
}

static inline unsigned mip_minify(unsigned size, unsigned level)
{
	unsigned val;

	val = max(1U, size >> level);
	if (level > 0)
		val = roundup_pow_of_two(val);
	return val;
}

static void r600_texture_size(unsigned nfaces, unsigned blevel, unsigned llevel,
			      unsigned w0, unsigned h0, unsigned d0, unsigned format,
			      unsigned block_align, unsigned height_align, unsigned base_align,
			      unsigned *l0_size, unsigned *mipmap_size)
{
	unsigned offset, i, level;
	unsigned width, height, depth, size;
	unsigned blocksize;
	unsigned nbx, nby;
	unsigned nlevels = llevel - blevel + 1;

	*l0_size = -1;
	blocksize = fmt_get_blocksize(format);

	w0 = mip_minify(w0, 0);
	h0 = mip_minify(h0, 0);
	d0 = mip_minify(d0, 0);
	for(i = 0, offset = 0, level = blevel; i < nlevels; i++, level++) {
		width = mip_minify(w0, i);
		nbx = fmt_get_nblocksx(format, width);

		nbx = round_up(nbx, block_align);

		height = mip_minify(h0, i);
		nby = fmt_get_nblocksy(format, height);
		nby = round_up(nby, height_align);

		depth = mip_minify(d0, i);

		size = nbx * nby * blocksize;
		if (nfaces)
			size *= nfaces;
		else
			size *= depth;

		if (i == 0)
			*l0_size = size;

		if (i == 0 || i == 1)
			offset = round_up(offset, base_align);

		offset += size;
	}
	*mipmap_size = offset;
	if (llevel == 0)
		*mipmap_size = *l0_size;
	if (!blevel)
		*mipmap_size -= *l0_size;
}

/**
 * r600_check_texture_resource() - check if register is authorized or not
 * @p: parser structure holding parsing context
 * @idx: index into the cs buffer
 * @texture: texture's bo structure
 * @mipmap: mipmap's bo structure
 *
 * This function will check that the resource has valid field and that
 * the texture and mipmap bo object are big enough to cover this resource.
 */
static inline int r600_check_texture_resource(struct radeon_cs_parser *p,  u32 idx,
					      struct radeon_bo *texture,
					      struct radeon_bo *mipmap,
					      u64 base_offset,
					      u64 mip_offset,
					      u32 tiling_flags)
{
	struct r600_cs_track *track = p->track;
	u32 nfaces, llevel, blevel, w0, h0, d0;
	u32 word0, word1, l0_size, mipmap_size, word2, word3;
	u32 height_align, pitch, pitch_align, depth_align;
	u32 array, barray, larray;
	u64 base_align;
	struct array_mode_checker array_check;
	u32 format;

	/* on legacy kernel we don't perform advanced check */
	if (p->rdev == NULL)
		return 0;

	/* convert to bytes */
	base_offset <<= 8;
	mip_offset <<= 8;

	word0 = radeon_get_ib_value(p, idx + 0);
	if (tiling_flags & RADEON_TILING_MACRO)
		word0 |= S_038000_TILE_MODE(V_038000_ARRAY_2D_TILED_THIN1);
	else if (tiling_flags & RADEON_TILING_MICRO)
		word0 |= S_038000_TILE_MODE(V_038000_ARRAY_1D_TILED_THIN1);
	word1 = radeon_get_ib_value(p, idx + 1);
	w0 = G_038000_TEX_WIDTH(word0) + 1;
	h0 = G_038004_TEX_HEIGHT(word1) + 1;
	d0 = G_038004_TEX_DEPTH(word1);
	nfaces = 1;
	switch (G_038000_DIM(word0)) {
	case V_038000_SQ_TEX_DIM_1D:
	case V_038000_SQ_TEX_DIM_2D:
	case V_038000_SQ_TEX_DIM_3D:
		break;
	case V_038000_SQ_TEX_DIM_CUBEMAP:
		if (p->family >= CHIP_RV770)
			nfaces = 8;
		else
			nfaces = 6;
		break;
	case V_038000_SQ_TEX_DIM_1D_ARRAY:
	case V_038000_SQ_TEX_DIM_2D_ARRAY:
		array = 1;
		break;
	case V_038000_SQ_TEX_DIM_2D_MSAA:
	case V_038000_SQ_TEX_DIM_2D_ARRAY_MSAA:
	default:
		dev_warn(p->dev, "this kernel doesn't support %d texture dim\n", G_038000_DIM(word0));
		return -EINVAL;
	}
	format = G_038004_DATA_FORMAT(word1);
	if (!fmt_is_valid_texture(format, p->family)) {
		dev_warn(p->dev, "%s:%d texture invalid format %d\n",
			 __func__, __LINE__, format);
		return -EINVAL;
	}

	/* pitch in texels */
	pitch = (G_038000_PITCH(word0) + 1) * 8;
	array_check.array_mode = G_038000_TILE_MODE(word0);
	array_check.group_size = track->group_size;
	array_check.nbanks = track->nbanks;
	array_check.npipes = track->npipes;
	array_check.nsamples = 1;
	array_check.blocksize = fmt_get_blocksize(format);
	if (r600_get_array_mode_alignment(&array_check,
					  &pitch_align, &height_align, &depth_align, &base_align)) {
		dev_warn(p->dev, "%s:%d tex array mode (%d) invalid\n",
			 __func__, __LINE__, G_038000_TILE_MODE(word0));
		return -EINVAL;
	}

	/* XXX check height as well... */

	if (!IS_ALIGNED(pitch, pitch_align)) {
		dev_warn(p->dev, "%s:%d tex pitch (%d, 0x%x, %d) invalid\n",
			 __func__, __LINE__, pitch, pitch_align, G_038000_TILE_MODE(word0));
		return -EINVAL;
	}
	if (!IS_ALIGNED(base_offset, base_align)) {
		dev_warn(p->dev, "%s:%d tex base offset (0x%llx, 0x%llx, %d) invalid\n",
			 __func__, __LINE__, base_offset, base_align, G_038000_TILE_MODE(word0));
		return -EINVAL;
	}
	if (!IS_ALIGNED(mip_offset, base_align)) {
		dev_warn(p->dev, "%s:%d tex mip offset (0x%llx, 0x%llx, %d) invalid\n",
			 __func__, __LINE__, mip_offset, base_align, G_038000_TILE_MODE(word0));
		return -EINVAL;
	}

	word2 = radeon_get_ib_value(p, idx + 2) << 8;
	word3 = radeon_get_ib_value(p, idx + 3) << 8;

	word0 = radeon_get_ib_value(p, idx + 4);
	word1 = radeon_get_ib_value(p, idx + 5);
	blevel = G_038010_BASE_LEVEL(word0);
	llevel = G_038014_LAST_LEVEL(word1);
	if (array == 1) {
		barray = G_038014_BASE_ARRAY(word1);
		larray = G_038014_LAST_ARRAY(word1);

		nfaces = larray - barray + 1;
	}
	r600_texture_size(nfaces, blevel, llevel, w0, h0, d0, format,
			  pitch_align, height_align, base_align,
			  &l0_size, &mipmap_size);
	/* using get ib will give us the offset into the texture bo */
	if ((l0_size + word2) > radeon_bo_size(texture)) {
		dev_warn(p->dev, "texture bo too small (%d %d %d %d -> %d have %ld)\n",
			w0, h0, format, word2, l0_size, radeon_bo_size(texture));
		dev_warn(p->dev, "alignments %d %d %d %lld\n", pitch, pitch_align, height_align, base_align);
		return -EINVAL;
	}
	/* using get ib will give us the offset into the mipmap bo */
	word3 = radeon_get_ib_value(p, idx + 3) << 8;
	if ((mipmap_size + word3) > radeon_bo_size(mipmap)) {
		/*dev_warn(p->dev, "mipmap bo too small (%d %d %d %d %d %d -> %d have %ld)\n",
		  w0, h0, format, blevel, nlevels, word3, mipmap_size, radeon_bo_size(texture));*/
	}
	return 0;
}

static int r600_packet3_check(struct radeon_cs_parser *p,
				struct radeon_cs_packet *pkt)
{
	struct radeon_cs_reloc *reloc;
	struct r600_cs_track *track;
	volatile u32 *ib;
	unsigned idx;
	unsigned i;
	unsigned start_reg, end_reg, reg;
	int r;
	u32 idx_value;

	track = (struct r600_cs_track *)p->track;
	ib = p->ib->ptr;
	idx = pkt->idx + 1;
	idx_value = radeon_get_ib_value(p, idx);

	switch (pkt->opcode) {
	case PACKET3_SET_PREDICATION:
	{
		int pred_op;
		int tmp;
		if (pkt->count != 1) {
			DRM_ERROR("bad SET PREDICATION\n");
			return -EINVAL;
		}

		tmp = radeon_get_ib_value(p, idx + 1);
		pred_op = (tmp >> 16) & 0x7;

		/* for the clear predicate operation */
		if (pred_op == 0)
			return 0;

		if (pred_op > 2) {
			DRM_ERROR("bad SET PREDICATION operation %d\n", pred_op);
			return -EINVAL;
		}

		r = r600_cs_packet_next_reloc(p, &reloc);
		if (r) {
			DRM_ERROR("bad SET PREDICATION\n");
			return -EINVAL;
		}

		ib[idx + 0] = idx_value + (u32)(reloc->lobj.gpu_offset & 0xffffffff);
		ib[idx + 1] = tmp + (upper_32_bits(reloc->lobj.gpu_offset) & 0xff);
	}
	break;

	case PACKET3_START_3D_CMDBUF:
		if (p->family >= CHIP_RV770 || pkt->count) {
			DRM_ERROR("bad START_3D\n");
			return -EINVAL;
		}
		break;
	case PACKET3_CONTEXT_CONTROL:
		if (pkt->count != 1) {
			DRM_ERROR("bad CONTEXT_CONTROL\n");
			return -EINVAL;
		}
		break;
	case PACKET3_INDEX_TYPE:
	case PACKET3_NUM_INSTANCES:
		if (pkt->count) {
			DRM_ERROR("bad INDEX_TYPE/NUM_INSTANCES\n");
			return -EINVAL;
		}
		break;
	case PACKET3_DRAW_INDEX:
		if (pkt->count != 3) {
			DRM_ERROR("bad DRAW_INDEX\n");
			return -EINVAL;
		}
		r = r600_cs_packet_next_reloc(p, &reloc);
		if (r) {
			DRM_ERROR("bad DRAW_INDEX\n");
			return -EINVAL;
		}
		ib[idx+0] = idx_value + (u32)(reloc->lobj.gpu_offset & 0xffffffff);
		ib[idx+1] += upper_32_bits(reloc->lobj.gpu_offset) & 0xff;
		r = r600_cs_track_check(p);
		if (r) {
			dev_warn(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__);
			return r;
		}
		break;
	case PACKET3_DRAW_INDEX_AUTO:
		if (pkt->count != 1) {
			DRM_ERROR("bad DRAW_INDEX_AUTO\n");
			return -EINVAL;
		}
		r = r600_cs_track_check(p);
		if (r) {
			dev_warn(p->dev, "%s:%d invalid cmd stream %d\n", __func__, __LINE__, idx);
			return r;
		}
		break;
	case PACKET3_DRAW_INDEX_IMMD_BE:
	case PACKET3_DRAW_INDEX_IMMD:
		if (pkt->count < 2) {
			DRM_ERROR("bad DRAW_INDEX_IMMD\n");
			return -EINVAL;
		}
		r = r600_cs_track_check(p);
		if (r) {
			dev_warn(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__);
			return r;
		}
		break;
	case PACKET3_WAIT_REG_MEM:
		if (pkt->count != 5) {
			DRM_ERROR("bad WAIT_REG_MEM\n");
			return -EINVAL;
		}
		/* bit 4 is reg (0) or mem (1) */
		if (idx_value & 0x10) {
			r = r600_cs_packet_next_reloc(p, &reloc);
			if (r) {
				DRM_ERROR("bad WAIT_REG_MEM\n");
				return -EINVAL;
			}
			ib[idx+1] += (u32)(reloc->lobj.gpu_offset & 0xffffffff);
			ib[idx+2] += upper_32_bits(reloc->lobj.gpu_offset) & 0xff;
		}
		break;
	case PACKET3_SURFACE_SYNC:
		if (pkt->count != 3) {
			DRM_ERROR("bad SURFACE_SYNC\n");
			return -EINVAL;
		}
		/* 0xffffffff/0x0 is flush all cache flag */
		if (radeon_get_ib_value(p, idx + 1) != 0xffffffff ||
		    radeon_get_ib_value(p, idx + 2) != 0) {
			r = r600_cs_packet_next_reloc(p, &reloc);
			if (r) {
				DRM_ERROR("bad SURFACE_SYNC\n");
				return -EINVAL;
			}
			ib[idx+2] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
		}
		break;
	case PACKET3_EVENT_WRITE:
		if (pkt->count != 2 && pkt->count != 0) {
			DRM_ERROR("bad EVENT_WRITE\n");
			return -EINVAL;
		}
		if (pkt->count) {
			r = r600_cs_packet_next_reloc(p, &reloc);
			if (r) {
				DRM_ERROR("bad EVENT_WRITE\n");
				return -EINVAL;
			}
			ib[idx+1] += (u32)(reloc->lobj.gpu_offset & 0xffffffff);
			ib[idx+2] += upper_32_bits(reloc->lobj.gpu_offset) & 0xff;
		}
		break;
	case PACKET3_EVENT_WRITE_EOP:
		if (pkt->count != 4) {
			DRM_ERROR("bad EVENT_WRITE_EOP\n");
			return -EINVAL;
		}
		r = r600_cs_packet_next_reloc(p, &reloc);
		if (r) {
			DRM_ERROR("bad EVENT_WRITE\n");
			return -EINVAL;
		}
		ib[idx+1] += (u32)(reloc->lobj.gpu_offset & 0xffffffff);
		ib[idx+2] += upper_32_bits(reloc->lobj.gpu_offset) & 0xff;
		break;
	case PACKET3_SET_CONFIG_REG:
		start_reg = (idx_value << 2) + PACKET3_SET_CONFIG_REG_OFFSET;
		end_reg = 4 * pkt->count + start_reg - 4;
		if ((start_reg < PACKET3_SET_CONFIG_REG_OFFSET) ||
		    (start_reg >= PACKET3_SET_CONFIG_REG_END) ||
		    (end_reg >= PACKET3_SET_CONFIG_REG_END)) {
			DRM_ERROR("bad PACKET3_SET_CONFIG_REG\n");
			return -EINVAL;
		}
		for (i = 0; i < pkt->count; i++) {
			reg = start_reg + (4 * i);
			r = r600_cs_check_reg(p, reg, idx+1+i);
			if (r)
				return r;
		}
		break;
	case PACKET3_SET_CONTEXT_REG:
		start_reg = (idx_value << 2) + PACKET3_SET_CONTEXT_REG_OFFSET;
		end_reg = 4 * pkt->count + start_reg - 4;
		if ((start_reg < PACKET3_SET_CONTEXT_REG_OFFSET) ||
		    (start_reg >= PACKET3_SET_CONTEXT_REG_END) ||
		    (end_reg >= PACKET3_SET_CONTEXT_REG_END)) {
			DRM_ERROR("bad PACKET3_SET_CONTEXT_REG\n");
			return -EINVAL;
		}
		for (i = 0; i < pkt->count; i++) {
			reg = start_reg + (4 * i);
			r = r600_cs_check_reg(p, reg, idx+1+i);
			if (r)
				return r;
		}
		break;
	case PACKET3_SET_RESOURCE:
		if (pkt->count % 7) {
			DRM_ERROR("bad SET_RESOURCE\n");
			return -EINVAL;
		}
		start_reg = (idx_value << 2) + PACKET3_SET_RESOURCE_OFFSET;
		end_reg = 4 * pkt->count + start_reg - 4;
		if ((start_reg < PACKET3_SET_RESOURCE_OFFSET) ||
		    (start_reg >= PACKET3_SET_RESOURCE_END) ||
		    (end_reg >= PACKET3_SET_RESOURCE_END)) {
			DRM_ERROR("bad SET_RESOURCE\n");
			return -EINVAL;
		}
		for (i = 0; i < (pkt->count / 7); i++) {
			struct radeon_bo *texture, *mipmap;
			u32 size, offset, base_offset, mip_offset;

			switch (G__SQ_VTX_CONSTANT_TYPE(radeon_get_ib_value(p, idx+(i*7)+6+1))) {
			case SQ_TEX_VTX_VALID_TEXTURE:
				/* tex base */
				r = r600_cs_packet_next_reloc(p, &reloc);
				if (r) {
					DRM_ERROR("bad SET_RESOURCE\n");
					return -EINVAL;
				}
				base_offset = (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
				if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
					ib[idx+1+(i*7)+0] |= S_038000_TILE_MODE(V_038000_ARRAY_2D_TILED_THIN1);
				else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
					ib[idx+1+(i*7)+0] |= S_038000_TILE_MODE(V_038000_ARRAY_1D_TILED_THIN1);
				texture = reloc->robj;
				/* tex mip base */
				r = r600_cs_packet_next_reloc(p, &reloc);
				if (r) {
					DRM_ERROR("bad SET_RESOURCE\n");
					return -EINVAL;
				}
				mip_offset = (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
				mipmap = reloc->robj;
				r = r600_check_texture_resource(p,  idx+(i*7)+1,
								texture, mipmap,
								base_offset + radeon_get_ib_value(p, idx+1+(i*7)+2),
								mip_offset + radeon_get_ib_value(p, idx+1+(i*7)+3),
								reloc->lobj.tiling_flags);
				if (r)
					return r;
				ib[idx+1+(i*7)+2] += base_offset;
				ib[idx+1+(i*7)+3] += mip_offset;
				break;
			case SQ_TEX_VTX_VALID_BUFFER:
				/* vtx base */
				r = r600_cs_packet_next_reloc(p, &reloc);
				if (r) {
					DRM_ERROR("bad SET_RESOURCE\n");
					return -EINVAL;
				}
				offset = radeon_get_ib_value(p, idx+1+(i*7)+0);
				size = radeon_get_ib_value(p, idx+1+(i*7)+1) + 1;
				if (p->rdev && (size + offset) > radeon_bo_size(reloc->robj)) {
					/* force size to size of the buffer */
					dev_warn(p->dev, "vbo resource seems too big (%d) for the bo (%ld)\n",
						 size + offset, radeon_bo_size(reloc->robj));
					ib[idx+1+(i*7)+1] = radeon_bo_size(reloc->robj);
				}
				ib[idx+1+(i*7)+0] += (u32)((reloc->lobj.gpu_offset) & 0xffffffff);
				ib[idx+1+(i*7)+2] += upper_32_bits(reloc->lobj.gpu_offset) & 0xff;
				break;
			case SQ_TEX_VTX_INVALID_TEXTURE:
			case SQ_TEX_VTX_INVALID_BUFFER:
			default:
				DRM_ERROR("bad SET_RESOURCE\n");
				return -EINVAL;
			}
		}
		break;
	case PACKET3_SET_ALU_CONST:
		if (track->sq_config & DX9_CONSTS) {
			start_reg = (idx_value << 2) + PACKET3_SET_ALU_CONST_OFFSET;
			end_reg = 4 * pkt->count + start_reg - 4;
			if ((start_reg < PACKET3_SET_ALU_CONST_OFFSET) ||
			    (start_reg >= PACKET3_SET_ALU_CONST_END) ||
			    (end_reg >= PACKET3_SET_ALU_CONST_END)) {
				DRM_ERROR("bad SET_ALU_CONST\n");
				return -EINVAL;
			}
		}
		break;
	case PACKET3_SET_BOOL_CONST:
		start_reg = (idx_value << 2) + PACKET3_SET_BOOL_CONST_OFFSET;
		end_reg = 4 * pkt->count + start_reg - 4;
		if ((start_reg < PACKET3_SET_BOOL_CONST_OFFSET) ||
		    (start_reg >= PACKET3_SET_BOOL_CONST_END) ||
		    (end_reg >= PACKET3_SET_BOOL_CONST_END)) {
			DRM_ERROR("bad SET_BOOL_CONST\n");
			return -EINVAL;
		}
		break;
	case PACKET3_SET_LOOP_CONST:
		start_reg = (idx_value << 2) + PACKET3_SET_LOOP_CONST_OFFSET;
		end_reg = 4 * pkt->count + start_reg - 4;
		if ((start_reg < PACKET3_SET_LOOP_CONST_OFFSET) ||
		    (start_reg >= PACKET3_SET_LOOP_CONST_END) ||
		    (end_reg >= PACKET3_SET_LOOP_CONST_END)) {
			DRM_ERROR("bad SET_LOOP_CONST\n");
			return -EINVAL;
		}
		break;
	case PACKET3_SET_CTL_CONST:
		start_reg = (idx_value << 2) + PACKET3_SET_CTL_CONST_OFFSET;
		end_reg = 4 * pkt->count + start_reg - 4;
		if ((start_reg < PACKET3_SET_CTL_CONST_OFFSET) ||
		    (start_reg >= PACKET3_SET_CTL_CONST_END) ||
		    (end_reg >= PACKET3_SET_CTL_CONST_END)) {
			DRM_ERROR("bad SET_CTL_CONST\n");
			return -EINVAL;
		}
		break;
	case PACKET3_SET_SAMPLER:
		if (pkt->count % 3) {
			DRM_ERROR("bad SET_SAMPLER\n");
			return -EINVAL;
		}
		start_reg = (idx_value << 2) + PACKET3_SET_SAMPLER_OFFSET;
		end_reg = 4 * pkt->count + start_reg - 4;
		if ((start_reg < PACKET3_SET_SAMPLER_OFFSET) ||
		    (start_reg >= PACKET3_SET_SAMPLER_END) ||
		    (end_reg >= PACKET3_SET_SAMPLER_END)) {
			DRM_ERROR("bad SET_SAMPLER\n");
			return -EINVAL;
		}
		break;
	case PACKET3_SURFACE_BASE_UPDATE:
		if (p->family >= CHIP_RV770 || p->family == CHIP_R600) {
			DRM_ERROR("bad SURFACE_BASE_UPDATE\n");
			return -EINVAL;
		}
		if (pkt->count) {
			DRM_ERROR("bad SURFACE_BASE_UPDATE\n");
			return -EINVAL;
		}
		break;
	case PACKET3_NOP:
		break;
	default:
		DRM_ERROR("Packet3 opcode %x not supported\n", pkt->opcode);
		return -EINVAL;
	}
	return 0;
}

int r600_cs_parse(struct radeon_cs_parser *p)
{
	struct radeon_cs_packet pkt;
	struct r600_cs_track *track;
	int r;

	if (p->track == NULL) {
		/* initialize tracker, we are in kms */
		track = kzalloc(sizeof(*track), GFP_KERNEL);
		if (track == NULL)
			return -ENOMEM;
		r600_cs_track_init(track);
		if (p->rdev->family < CHIP_RV770) {
			track->npipes = p->rdev->config.r600.tiling_npipes;
			track->nbanks = p->rdev->config.r600.tiling_nbanks;
			track->group_size = p->rdev->config.r600.tiling_group_size;
		} else if (p->rdev->family <= CHIP_RV740) {
			track->npipes = p->rdev->config.rv770.tiling_npipes;
			track->nbanks = p->rdev->config.rv770.tiling_nbanks;
			track->group_size = p->rdev->config.rv770.tiling_group_size;
		}
		p->track = track;
	}
	do {
		r = r600_cs_packet_parse(p, &pkt, p->idx);
		if (r) {
			kfree(p->track);
			p->track = NULL;
			return r;
		}
		p->idx += pkt.count + 2;
		switch (pkt.type) {
		case PACKET_TYPE0:
			r = r600_cs_parse_packet0(p, &pkt);
			break;
		case PACKET_TYPE2:
			break;
		case PACKET_TYPE3:
			r = r600_packet3_check(p, &pkt);
			break;
		default:
			DRM_ERROR("Unknown packet type %d !\n", pkt.type);
			kfree(p->track);
			p->track = NULL;
			return -EINVAL;
		}
		if (r) {
			kfree(p->track);
			p->track = NULL;
			return r;
		}
	} while (p->idx < p->chunks[p->chunk_ib_idx].length_dw);
#if 0
	for (r = 0; r < p->ib->length_dw; r++) {
		printk(KERN_INFO "%05d  0x%08X\n", r, p->ib->ptr[r]);
		mdelay(1);
	}
#endif
	kfree(p->track);
	p->track = NULL;
	return 0;
}

static int r600_cs_parser_relocs_legacy(struct radeon_cs_parser *p)
{
	if (p->chunk_relocs_idx == -1) {
		return 0;
	}
	p->relocs = kzalloc(sizeof(struct radeon_cs_reloc), GFP_KERNEL);
	if (p->relocs == NULL) {
		return -ENOMEM;
	}
	return 0;
}

/**
 * cs_parser_fini() - clean parser states
 * @parser:	parser structure holding parsing context.
 * @error:	error number
 *
 * If error is set than unvalidate buffer, otherwise just free memory
 * used by parsing context.
 **/
static void r600_cs_parser_fini(struct radeon_cs_parser *parser, int error)
{
	unsigned i;

	kfree(parser->relocs);
	for (i = 0; i < parser->nchunks; i++) {
		kfree(parser->chunks[i].kdata);
		kfree(parser->chunks[i].kpage[0]);
		kfree(parser->chunks[i].kpage[1]);
	}
	kfree(parser->chunks);
	kfree(parser->chunks_array);
}

int r600_cs_legacy(struct drm_device *dev, void *data, struct drm_file *filp,
			unsigned family, u32 *ib, int *l)
{
	struct radeon_cs_parser parser;
	struct radeon_cs_chunk *ib_chunk;
	struct radeon_ib fake_ib;
	struct r600_cs_track *track;
	int r;

	/* initialize tracker */
	track = kzalloc(sizeof(*track), GFP_KERNEL);
	if (track == NULL)
		return -ENOMEM;
	r600_cs_track_init(track);
	r600_cs_legacy_get_tiling_conf(dev, &track->npipes, &track->nbanks, &track->group_size);
	/* initialize parser */
	memset(&parser, 0, sizeof(struct radeon_cs_parser));
	parser.filp = filp;
	parser.dev = &dev->pdev->dev;
	parser.rdev = NULL;
	parser.family = family;
	parser.ib = &fake_ib;
	parser.track = track;
	fake_ib.ptr = ib;
	r = radeon_cs_parser_init(&parser, data);
	if (r) {
		DRM_ERROR("Failed to initialize parser !\n");
		r600_cs_parser_fini(&parser, r);
		return r;
	}
	r = r600_cs_parser_relocs_legacy(&parser);
	if (r) {
		DRM_ERROR("Failed to parse relocation !\n");
		r600_cs_parser_fini(&parser, r);
		return r;
	}
	/* Copy the packet into the IB, the parser will read from the
	 * input memory (cached) and write to the IB (which can be
	 * uncached). */
	ib_chunk = &parser.chunks[parser.chunk_ib_idx];
	parser.ib->length_dw = ib_chunk->length_dw;
	*l = parser.ib->length_dw;
	r = r600_cs_parse(&parser);
	if (r) {
		DRM_ERROR("Invalid command stream !\n");
		r600_cs_parser_fini(&parser, r);
		return r;
	}
	r = radeon_cs_finish_pages(&parser);
	if (r) {
		DRM_ERROR("Invalid command stream !\n");
		r600_cs_parser_fini(&parser, r);
		return r;
	}
	r600_cs_parser_fini(&parser, r);
	return r;
}

void r600_cs_legacy_init(void)
{
	r600_cs_packet_next_reloc = &r600_cs_packet_next_reloc_nomm;
}