summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/radeon/evergreen_cs.c
blob: cd4590aae154154d62906d901a63b8b368fea861 (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
/*
 * Copyright 2010 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 "drmP.h"
#include "radeon.h"
#include "evergreend.h"
#include "evergreen_reg_safe.h"
#include "cayman_reg_safe.h"

static int evergreen_cs_packet_next_reloc(struct radeon_cs_parser *p,
					  struct radeon_cs_reloc **cs_reloc);

struct evergreen_cs_track {
	u32			group_size;
	u32			nbanks;
	u32			npipes;
	u32			row_size;
	/* value we track */
	u32			nsamples;
	u32			cb_color_base_last[12];
	struct radeon_bo	*cb_color_bo[12];
	u32			cb_color_bo_offset[12];
	struct radeon_bo	*cb_color_fmask_bo[8];
	struct radeon_bo	*cb_color_cmask_bo[8];
	u32			cb_color_info[12];
	u32			cb_color_view[12];
	u32			cb_color_pitch_idx[12];
	u32			cb_color_slice_idx[12];
	u32			cb_color_dim_idx[12];
	u32			cb_color_dim[12];
	u32			cb_color_pitch[12];
	u32			cb_color_slice[12];
	u32			cb_color_cmask_slice[8];
	u32			cb_color_fmask_slice[8];
	u32			cb_target_mask;
	u32			cb_shader_mask;
	u32			vgt_strmout_config;
	u32			vgt_strmout_buffer_config;
	u32			db_depth_control;
	u32			db_depth_view;
	u32			db_depth_size;
	u32			db_depth_size_idx;
	u32			db_z_info;
	u32			db_z_idx;
	u32			db_z_read_offset;
	u32			db_z_write_offset;
	struct radeon_bo	*db_z_read_bo;
	struct radeon_bo	*db_z_write_bo;
	u32			db_s_info;
	u32			db_s_idx;
	u32			db_s_read_offset;
	u32			db_s_write_offset;
	struct radeon_bo	*db_s_read_bo;
	struct radeon_bo	*db_s_write_bo;
};

static u32 evergreen_cs_get_aray_mode(u32 tiling_flags)
{
	if (tiling_flags & RADEON_TILING_MACRO)
		return ARRAY_2D_TILED_THIN1;
	else if (tiling_flags & RADEON_TILING_MICRO)
		return ARRAY_1D_TILED_THIN1;
	else
		return ARRAY_LINEAR_GENERAL;
}

static u32 evergreen_cs_get_num_banks(u32 nbanks)
{
	switch (nbanks) {
	case 2:
		return ADDR_SURF_2_BANK;
	case 4:
		return ADDR_SURF_4_BANK;
	case 8:
	default:
		return ADDR_SURF_8_BANK;
	case 16:
		return ADDR_SURF_16_BANK;
	}
}

static u32 evergreen_cs_get_tile_split(u32 row_size)
{
	switch (row_size) {
	case 1:
	default:
		return ADDR_SURF_TILE_SPLIT_1KB;
	case 2:
		return ADDR_SURF_TILE_SPLIT_2KB;
	case 4:
		return ADDR_SURF_TILE_SPLIT_4KB;
	}
}

static void evergreen_cs_track_init(struct evergreen_cs_track *track)
{
	int i;

	for (i = 0; i < 8; i++) {
		track->cb_color_fmask_bo[i] = NULL;
		track->cb_color_cmask_bo[i] = NULL;
		track->cb_color_cmask_slice[i] = 0;
		track->cb_color_fmask_slice[i] = 0;
	}

	for (i = 0; i < 12; i++) {
		track->cb_color_base_last[i] = 0;
		track->cb_color_bo[i] = NULL;
		track->cb_color_bo_offset[i] = 0xFFFFFFFF;
		track->cb_color_info[i] = 0;
		track->cb_color_view[i] = 0;
		track->cb_color_pitch_idx[i] = 0;
		track->cb_color_slice_idx[i] = 0;
		track->cb_color_dim[i] = 0;
		track->cb_color_pitch[i] = 0;
		track->cb_color_slice[i] = 0;
		track->cb_color_dim[i] = 0;
	}
	track->cb_target_mask = 0xFFFFFFFF;
	track->cb_shader_mask = 0xFFFFFFFF;

	track->db_depth_view = 0xFFFFC000;
	track->db_depth_size = 0xFFFFFFFF;
	track->db_depth_size_idx = 0;
	track->db_depth_control = 0xFFFFFFFF;
	track->db_z_info = 0xFFFFFFFF;
	track->db_z_idx = 0xFFFFFFFF;
	track->db_z_read_offset = 0xFFFFFFFF;
	track->db_z_write_offset = 0xFFFFFFFF;
	track->db_z_read_bo = NULL;
	track->db_z_write_bo = NULL;
	track->db_s_info = 0xFFFFFFFF;
	track->db_s_idx = 0xFFFFFFFF;
	track->db_s_read_offset = 0xFFFFFFFF;
	track->db_s_write_offset = 0xFFFFFFFF;
	track->db_s_read_bo = NULL;
	track->db_s_write_bo = NULL;
}

static int evergreen_cs_track_check(struct radeon_cs_parser *p)
{
	struct evergreen_cs_track *track = p->track;

	/* we don't support stream out buffer yet */
	if (track->vgt_strmout_config || track->vgt_strmout_buffer_config) {
		dev_warn(p->dev, "this kernel doesn't support SMX output buffer\n");
		return -EINVAL;
	}

	/* XXX fill in */
	return 0;
}

/**
 * evergreen_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 evergreen_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;
}

/**
 * evergreen_cs_packet_next_reloc() - 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 evergreen_cs_packet_next_reloc(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 = evergreen_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;
}

/**
 * evergreen_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 evergreen_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 = evergreen_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) != EVERGREEN_VLINE_STATUS) {
		DRM_ERROR("vline WAIT_REG_MEM bad reg\n");
		return -EINVAL;
	}

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

	/* jump over the NOP */
	r = evergreen_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 {
		switch (reg) {
		case EVERGREEN_VLINE_START_END:
			header &= ~R600_CP_PACKET0_REG_MASK;
			header |= (EVERGREEN_VLINE_START_END + radeon_crtc->crtc_offset) >> 2;
			ib[h_idx] = header;
			ib[h_idx + 4] = (EVERGREEN_VLINE_STATUS + radeon_crtc->crtc_offset) >> 2;
			break;
		default:
			DRM_ERROR("unknown crtc reloc\n");
			return -EINVAL;
		}
	}
	return 0;
}

static int evergreen_packet0_check(struct radeon_cs_parser *p,
				   struct radeon_cs_packet *pkt,
				   unsigned idx, unsigned reg)
{
	int r;

	switch (reg) {
	case EVERGREEN_VLINE_START_END:
		r = evergreen_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 evergreen_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 = evergreen_packet0_check(p, pkt, idx, reg);
		if (r) {
			return r;
		}
	}
	return 0;
}

/**
 * evergreen_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 evergreen_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 int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
{
	struct evergreen_cs_track *track = (struct evergreen_cs_track *)p->track;
	struct radeon_cs_reloc *reloc;
	u32 last_reg;
	u32 m, i, tmp, *ib;
	int r;

	if (p->rdev->family >= CHIP_CAYMAN)
		last_reg = ARRAY_SIZE(cayman_reg_safe_bm);
	else
		last_reg = ARRAY_SIZE(evergreen_reg_safe_bm);

	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 (p->rdev->family >= CHIP_CAYMAN) {
		if (!(cayman_reg_safe_bm[i] & m))
			return 0;
	} else {
		if (!(evergreen_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 SQ_ESGS_RING_SIZE:
	case SQ_GSVS_RING_SIZE:
	case SQ_ESTMP_RING_SIZE:
	case SQ_GSTMP_RING_SIZE:
	case SQ_HSTMP_RING_SIZE:
	case SQ_LSTMP_RING_SIZE:
	case SQ_PSTMP_RING_SIZE:
	case SQ_VSTMP_RING_SIZE:
	case SQ_ESGS_RING_ITEMSIZE:
	case SQ_ESTMP_RING_ITEMSIZE:
	case SQ_GSTMP_RING_ITEMSIZE:
	case SQ_GSVS_RING_ITEMSIZE:
	case SQ_GS_VERT_ITEMSIZE:
	case SQ_GS_VERT_ITEMSIZE_1:
	case SQ_GS_VERT_ITEMSIZE_2:
	case SQ_GS_VERT_ITEMSIZE_3:
	case SQ_GSVS_RING_OFFSET_1:
	case SQ_GSVS_RING_OFFSET_2:
	case SQ_GSVS_RING_OFFSET_3:
	case SQ_HSTMP_RING_ITEMSIZE:
	case SQ_LSTMP_RING_ITEMSIZE:
	case SQ_PSTMP_RING_ITEMSIZE:
	case SQ_VSTMP_RING_ITEMSIZE:
	case VGT_TF_RING_SIZE:
		/* get value to populate the IB don't remove */
		/*tmp =radeon_get_ib_value(p, idx);
		  ib[idx] = 0;*/
		break;
	case SQ_ESGS_RING_BASE:
	case SQ_GSVS_RING_BASE:
	case SQ_ESTMP_RING_BASE:
	case SQ_GSTMP_RING_BASE:
	case SQ_HSTMP_RING_BASE:
	case SQ_LSTMP_RING_BASE:
	case SQ_PSTMP_RING_BASE:
	case SQ_VSTMP_RING_BASE:
		r = evergreen_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 DB_DEPTH_CONTROL:
		track->db_depth_control = radeon_get_ib_value(p, idx);
		break;
	case CAYMAN_DB_EQAA:
		if (p->rdev->family < CHIP_CAYMAN) {
			dev_warn(p->dev, "bad SET_CONTEXT_REG "
				 "0x%04X\n", reg);
			return -EINVAL;
		}
		break;
	case CAYMAN_DB_DEPTH_INFO:
		if (p->rdev->family < CHIP_CAYMAN) {
			dev_warn(p->dev, "bad SET_CONTEXT_REG "
				 "0x%04X\n", reg);
			return -EINVAL;
		}
		break;
	case DB_Z_INFO:
		track->db_z_info = radeon_get_ib_value(p, idx);
		if (!p->keep_tiling_flags) {
			r = evergreen_cs_packet_next_reloc(p, &reloc);
			if (r) {
				dev_warn(p->dev, "bad SET_CONTEXT_REG "
						"0x%04X\n", reg);
				return -EINVAL;
			}
			ib[idx] &= ~Z_ARRAY_MODE(0xf);
			track->db_z_info &= ~Z_ARRAY_MODE(0xf);
			ib[idx] |= Z_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
			track->db_z_info |= Z_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
				ib[idx] |= DB_NUM_BANKS(evergreen_cs_get_num_banks(track->nbanks));
				ib[idx] |= DB_TILE_SPLIT(evergreen_cs_get_tile_split(track->row_size));
			}
		}
		break;
	case DB_STENCIL_INFO:
		track->db_s_info = radeon_get_ib_value(p, idx);
		break;
	case DB_DEPTH_VIEW:
		track->db_depth_view = radeon_get_ib_value(p, idx);
		break;
	case DB_DEPTH_SIZE:
		track->db_depth_size = radeon_get_ib_value(p, idx);
		track->db_depth_size_idx = idx;
		break;
	case DB_Z_READ_BASE:
		r = evergreen_cs_packet_next_reloc(p, &reloc);
		if (r) {
			dev_warn(p->dev, "bad SET_CONTEXT_REG "
					"0x%04X\n", reg);
			return -EINVAL;
		}
		track->db_z_read_offset = radeon_get_ib_value(p, idx);
		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
		track->db_z_read_bo = reloc->robj;
		break;
	case DB_Z_WRITE_BASE:
		r = evergreen_cs_packet_next_reloc(p, &reloc);
		if (r) {
			dev_warn(p->dev, "bad SET_CONTEXT_REG "
					"0x%04X\n", reg);
			return -EINVAL;
		}
		track->db_z_write_offset = radeon_get_ib_value(p, idx);
		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
		track->db_z_write_bo = reloc->robj;
		break;
	case DB_STENCIL_READ_BASE:
		r = evergreen_cs_packet_next_reloc(p, &reloc);
		if (r) {
			dev_warn(p->dev, "bad SET_CONTEXT_REG "
					"0x%04X\n", reg);
			return -EINVAL;
		}
		track->db_s_read_offset = radeon_get_ib_value(p, idx);
		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
		track->db_s_read_bo = reloc->robj;
		break;
	case DB_STENCIL_WRITE_BASE:
		r = evergreen_cs_packet_next_reloc(p, &reloc);
		if (r) {
			dev_warn(p->dev, "bad SET_CONTEXT_REG "
					"0x%04X\n", reg);
			return -EINVAL;
		}
		track->db_s_write_offset = radeon_get_ib_value(p, idx);
		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
		track->db_s_write_bo = reloc->robj;
		break;
	case VGT_STRMOUT_CONFIG:
		track->vgt_strmout_config = radeon_get_ib_value(p, idx);
		break;
	case VGT_STRMOUT_BUFFER_CONFIG:
		track->vgt_strmout_buffer_config = radeon_get_ib_value(p, idx);
		break;
	case CB_TARGET_MASK:
		track->cb_target_mask = radeon_get_ib_value(p, idx);
		break;
	case CB_SHADER_MASK:
		track->cb_shader_mask = radeon_get_ib_value(p, idx);
		break;
	case PA_SC_AA_CONFIG:
		if (p->rdev->family >= CHIP_CAYMAN) {
			dev_warn(p->dev, "bad SET_CONTEXT_REG "
				 "0x%04X\n", reg);
			return -EINVAL;
		}
		tmp = radeon_get_ib_value(p, idx) & MSAA_NUM_SAMPLES_MASK;
		track->nsamples = 1 << tmp;
		break;
	case CAYMAN_PA_SC_AA_CONFIG:
		if (p->rdev->family < CHIP_CAYMAN) {
			dev_warn(p->dev, "bad SET_CONTEXT_REG "
				 "0x%04X\n", reg);
			return -EINVAL;
		}
		tmp = radeon_get_ib_value(p, idx) & CAYMAN_MSAA_NUM_SAMPLES_MASK;
		track->nsamples = 1 << tmp;
		break;
	case CB_COLOR0_VIEW:
	case CB_COLOR1_VIEW:
	case CB_COLOR2_VIEW:
	case CB_COLOR3_VIEW:
	case CB_COLOR4_VIEW:
	case CB_COLOR5_VIEW:
	case CB_COLOR6_VIEW:
	case CB_COLOR7_VIEW:
		tmp = (reg - CB_COLOR0_VIEW) / 0x3c;
		track->cb_color_view[tmp] = radeon_get_ib_value(p, idx);
		break;
	case CB_COLOR8_VIEW:
	case CB_COLOR9_VIEW:
	case CB_COLOR10_VIEW:
	case CB_COLOR11_VIEW:
		tmp = ((reg - CB_COLOR8_VIEW) / 0x1c) + 8;
		track->cb_color_view[tmp] = radeon_get_ib_value(p, idx);
		break;
	case CB_COLOR0_INFO:
	case CB_COLOR1_INFO:
	case CB_COLOR2_INFO:
	case CB_COLOR3_INFO:
	case CB_COLOR4_INFO:
	case CB_COLOR5_INFO:
	case CB_COLOR6_INFO:
	case CB_COLOR7_INFO:
		tmp = (reg - CB_COLOR0_INFO) / 0x3c;
		track->cb_color_info[tmp] = radeon_get_ib_value(p, idx);
		if (!p->keep_tiling_flags) {
			r = evergreen_cs_packet_next_reloc(p, &reloc);
			if (r) {
				dev_warn(p->dev, "bad SET_CONTEXT_REG "
						"0x%04X\n", reg);
				return -EINVAL;
			}
			ib[idx] |= CB_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
			track->cb_color_info[tmp] |= CB_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
		}
		break;
	case CB_COLOR8_INFO:
	case CB_COLOR9_INFO:
	case CB_COLOR10_INFO:
	case CB_COLOR11_INFO:
		tmp = ((reg - CB_COLOR8_INFO) / 0x1c) + 8;
		track->cb_color_info[tmp] = radeon_get_ib_value(p, idx);
		if (!p->keep_tiling_flags) {
			r = evergreen_cs_packet_next_reloc(p, &reloc);
			if (r) {
				dev_warn(p->dev, "bad SET_CONTEXT_REG "
						"0x%04X\n", reg);
				return -EINVAL;
			}
			ib[idx] |= CB_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
			track->cb_color_info[tmp] |= CB_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
		}
		break;
	case CB_COLOR0_PITCH:
	case CB_COLOR1_PITCH:
	case CB_COLOR2_PITCH:
	case CB_COLOR3_PITCH:
	case CB_COLOR4_PITCH:
	case CB_COLOR5_PITCH:
	case CB_COLOR6_PITCH:
	case CB_COLOR7_PITCH:
		tmp = (reg - CB_COLOR0_PITCH) / 0x3c;
		track->cb_color_pitch[tmp] = radeon_get_ib_value(p, idx);
		track->cb_color_pitch_idx[tmp] = idx;
		break;
	case CB_COLOR8_PITCH:
	case CB_COLOR9_PITCH:
	case CB_COLOR10_PITCH:
	case CB_COLOR11_PITCH:
		tmp = ((reg - CB_COLOR8_PITCH) / 0x1c) + 8;
		track->cb_color_pitch[tmp] = radeon_get_ib_value(p, idx);
		track->cb_color_pitch_idx[tmp] = idx;
		break;
	case CB_COLOR0_SLICE:
	case CB_COLOR1_SLICE:
	case CB_COLOR2_SLICE:
	case CB_COLOR3_SLICE:
	case CB_COLOR4_SLICE:
	case CB_COLOR5_SLICE:
	case CB_COLOR6_SLICE:
	case CB_COLOR7_SLICE:
		tmp = (reg - CB_COLOR0_SLICE) / 0x3c;
		track->cb_color_slice[tmp] = radeon_get_ib_value(p, idx);
		track->cb_color_slice_idx[tmp] = idx;
		break;
	case CB_COLOR8_SLICE:
	case CB_COLOR9_SLICE:
	case CB_COLOR10_SLICE:
	case CB_COLOR11_SLICE:
		tmp = ((reg - CB_COLOR8_SLICE) / 0x1c) + 8;
		track->cb_color_slice[tmp] = radeon_get_ib_value(p, idx);
		track->cb_color_slice_idx[tmp] = idx;
		break;
	case CB_COLOR0_ATTRIB:
	case CB_COLOR1_ATTRIB:
	case CB_COLOR2_ATTRIB:
	case CB_COLOR3_ATTRIB:
	case CB_COLOR4_ATTRIB:
	case CB_COLOR5_ATTRIB:
	case CB_COLOR6_ATTRIB:
	case CB_COLOR7_ATTRIB:
	case CB_COLOR8_ATTRIB:
	case CB_COLOR9_ATTRIB:
	case CB_COLOR10_ATTRIB:
	case CB_COLOR11_ATTRIB:
		r = evergreen_cs_packet_next_reloc(p, &reloc);
		if (r) {
			dev_warn(p->dev, "bad SET_CONTEXT_REG "
					"0x%04X\n", reg);
			return -EINVAL;
		}
		if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
			ib[idx] |= CB_NUM_BANKS(evergreen_cs_get_num_banks(track->nbanks));
			ib[idx] |= CB_TILE_SPLIT(evergreen_cs_get_tile_split(track->row_size));
		}
		break;
	case CB_COLOR0_DIM:
	case CB_COLOR1_DIM:
	case CB_COLOR2_DIM:
	case CB_COLOR3_DIM:
	case CB_COLOR4_DIM:
	case CB_COLOR5_DIM:
	case CB_COLOR6_DIM:
	case CB_COLOR7_DIM:
		tmp = (reg - CB_COLOR0_DIM) / 0x3c;
		track->cb_color_dim[tmp] = radeon_get_ib_value(p, idx);
		track->cb_color_dim_idx[tmp] = idx;
		break;
	case CB_COLOR8_DIM:
	case CB_COLOR9_DIM:
	case CB_COLOR10_DIM:
	case CB_COLOR11_DIM:
		tmp = ((reg - CB_COLOR8_DIM) / 0x1c) + 8;
		track->cb_color_dim[tmp] = radeon_get_ib_value(p, idx);
		track->cb_color_dim_idx[tmp] = idx;
		break;
	case CB_COLOR0_FMASK:
	case CB_COLOR1_FMASK:
	case CB_COLOR2_FMASK:
	case CB_COLOR3_FMASK:
	case CB_COLOR4_FMASK:
	case CB_COLOR5_FMASK:
	case CB_COLOR6_FMASK:
	case CB_COLOR7_FMASK:
		tmp = (reg - CB_COLOR0_FMASK) / 0x3c;
		r = evergreen_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_fmask_bo[tmp] = reloc->robj;
		break;
	case CB_COLOR0_CMASK:
	case CB_COLOR1_CMASK:
	case CB_COLOR2_CMASK:
	case CB_COLOR3_CMASK:
	case CB_COLOR4_CMASK:
	case CB_COLOR5_CMASK:
	case CB_COLOR6_CMASK:
	case CB_COLOR7_CMASK:
		tmp = (reg - CB_COLOR0_CMASK) / 0x3c;
		r = evergreen_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_cmask_bo[tmp] = reloc->robj;
		break;
	case CB_COLOR0_FMASK_SLICE:
	case CB_COLOR1_FMASK_SLICE:
	case CB_COLOR2_FMASK_SLICE:
	case CB_COLOR3_FMASK_SLICE:
	case CB_COLOR4_FMASK_SLICE:
	case CB_COLOR5_FMASK_SLICE:
	case CB_COLOR6_FMASK_SLICE:
	case CB_COLOR7_FMASK_SLICE:
		tmp = (reg - CB_COLOR0_FMASK_SLICE) / 0x3c;
		track->cb_color_fmask_slice[tmp] = radeon_get_ib_value(p, idx);
		break;
	case CB_COLOR0_CMASK_SLICE:
	case CB_COLOR1_CMASK_SLICE:
	case CB_COLOR2_CMASK_SLICE:
	case CB_COLOR3_CMASK_SLICE:
	case CB_COLOR4_CMASK_SLICE:
	case CB_COLOR5_CMASK_SLICE:
	case CB_COLOR6_CMASK_SLICE:
	case CB_COLOR7_CMASK_SLICE:
		tmp = (reg - CB_COLOR0_CMASK_SLICE) / 0x3c;
		track->cb_color_cmask_slice[tmp] = radeon_get_ib_value(p, idx);
		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 = evergreen_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) / 0x3c;
		track->cb_color_bo_offset[tmp] = radeon_get_ib_value(p, idx);
		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
		track->cb_color_base_last[tmp] = ib[idx];
		track->cb_color_bo[tmp] = reloc->robj;
		break;
	case CB_COLOR8_BASE:
	case CB_COLOR9_BASE:
	case CB_COLOR10_BASE:
	case CB_COLOR11_BASE:
		r = evergreen_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_COLOR8_BASE) / 0x1c) + 8;
		track->cb_color_bo_offset[tmp] = radeon_get_ib_value(p, idx);
		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
		track->cb_color_base_last[tmp] = ib[idx];
		track->cb_color_bo[tmp] = reloc->robj;
		break;
	case CB_IMMED0_BASE:
	case CB_IMMED1_BASE:
	case CB_IMMED2_BASE:
	case CB_IMMED3_BASE:
	case CB_IMMED4_BASE:
	case CB_IMMED5_BASE:
	case CB_IMMED6_BASE:
	case CB_IMMED7_BASE:
	case CB_IMMED8_BASE:
	case CB_IMMED9_BASE:
	case CB_IMMED10_BASE:
	case CB_IMMED11_BASE:
	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_PGM_START_HS:
	case SQ_PGM_START_LS:
	case SQ_CONST_MEM_BASE:
	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:
	case SQ_ALU_CONST_CACHE_HS_0:
	case SQ_ALU_CONST_CACHE_HS_1:
	case SQ_ALU_CONST_CACHE_HS_2:
	case SQ_ALU_CONST_CACHE_HS_3:
	case SQ_ALU_CONST_CACHE_HS_4:
	case SQ_ALU_CONST_CACHE_HS_5:
	case SQ_ALU_CONST_CACHE_HS_6:
	case SQ_ALU_CONST_CACHE_HS_7:
	case SQ_ALU_CONST_CACHE_HS_8:
	case SQ_ALU_CONST_CACHE_HS_9:
	case SQ_ALU_CONST_CACHE_HS_10:
	case SQ_ALU_CONST_CACHE_HS_11:
	case SQ_ALU_CONST_CACHE_HS_12:
	case SQ_ALU_CONST_CACHE_HS_13:
	case SQ_ALU_CONST_CACHE_HS_14:
	case SQ_ALU_CONST_CACHE_HS_15:
	case SQ_ALU_CONST_CACHE_LS_0:
	case SQ_ALU_CONST_CACHE_LS_1:
	case SQ_ALU_CONST_CACHE_LS_2:
	case SQ_ALU_CONST_CACHE_LS_3:
	case SQ_ALU_CONST_CACHE_LS_4:
	case SQ_ALU_CONST_CACHE_LS_5:
	case SQ_ALU_CONST_CACHE_LS_6:
	case SQ_ALU_CONST_CACHE_LS_7:
	case SQ_ALU_CONST_CACHE_LS_8:
	case SQ_ALU_CONST_CACHE_LS_9:
	case SQ_ALU_CONST_CACHE_LS_10:
	case SQ_ALU_CONST_CACHE_LS_11:
	case SQ_ALU_CONST_CACHE_LS_12:
	case SQ_ALU_CONST_CACHE_LS_13:
	case SQ_ALU_CONST_CACHE_LS_14:
	case SQ_ALU_CONST_CACHE_LS_15:
		r = evergreen_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:
		if (p->rdev->family >= CHIP_CAYMAN) {
			dev_warn(p->dev, "bad SET_CONFIG_REG "
				 "0x%04X\n", reg);
			return -EINVAL;
		}
		r = evergreen_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;
	case CAYMAN_SX_SCATTER_EXPORT_BASE:
		if (p->rdev->family < CHIP_CAYMAN) {
			dev_warn(p->dev, "bad SET_CONTEXT_REG "
				 "0x%04X\n", reg);
			return -EINVAL;
		}
		r = evergreen_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;
	default:
		dev_warn(p->dev, "forbidden register 0x%08x at %d\n", reg, idx);
		return -EINVAL;
	}
	return 0;
}

/**
 * evergreen_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 int evergreen_check_texture_resource(struct radeon_cs_parser *p,  u32 idx,
						   struct radeon_bo *texture,
						   struct radeon_bo *mipmap)
{
	/* XXX fill in */
	return 0;
}

static int evergreen_packet3_check(struct radeon_cs_parser *p,
				   struct radeon_cs_packet *pkt)
{
	struct radeon_cs_reloc *reloc;
	struct evergreen_cs_track *track;
	volatile u32 *ib;
	unsigned idx;
	unsigned i;
	unsigned start_reg, end_reg, reg;
	int r;
	u32 idx_value;

	track = (struct evergreen_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 = evergreen_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_CONTEXT_CONTROL:
		if (pkt->count != 1) {
			DRM_ERROR("bad CONTEXT_CONTROL\n");
			return -EINVAL;
		}
		break;
	case PACKET3_INDEX_TYPE:
	case PACKET3_NUM_INSTANCES:
	case PACKET3_CLEAR_STATE:
		if (pkt->count) {
			DRM_ERROR("bad INDEX_TYPE/NUM_INSTANCES/CLEAR_STATE\n");
			return -EINVAL;
		}
		break;
	case CAYMAN_PACKET3_DEALLOC_STATE:
		if (p->rdev->family < CHIP_CAYMAN) {
			DRM_ERROR("bad PACKET3_DEALLOC_STATE\n");
			return -EINVAL;
		}
		if (pkt->count) {
			DRM_ERROR("bad INDEX_TYPE/NUM_INSTANCES/CLEAR_STATE\n");
			return -EINVAL;
		}
		break;
	case PACKET3_INDEX_BASE:
		if (pkt->count != 1) {
			DRM_ERROR("bad INDEX_BASE\n");
			return -EINVAL;
		}
		r = evergreen_cs_packet_next_reloc(p, &reloc);
		if (r) {
			DRM_ERROR("bad INDEX_BASE\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 = evergreen_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:
		if (pkt->count != 3) {
			DRM_ERROR("bad DRAW_INDEX\n");
			return -EINVAL;
		}
		r = evergreen_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 = evergreen_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_2:
		if (pkt->count != 4) {
			DRM_ERROR("bad DRAW_INDEX_2\n");
			return -EINVAL;
		}
		r = evergreen_cs_packet_next_reloc(p, &reloc);
		if (r) {
			DRM_ERROR("bad DRAW_INDEX_2\n");
			return -EINVAL;
		}
		ib[idx+1] = idx_value + (u32)(reloc->lobj.gpu_offset & 0xffffffff);
		ib[idx+2] += upper_32_bits(reloc->lobj.gpu_offset) & 0xff;
		r = evergreen_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 = evergreen_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_MULTI_AUTO:
		if (pkt->count != 2) {
			DRM_ERROR("bad DRAW_INDEX_MULTI_AUTO\n");
			return -EINVAL;
		}
		r = evergreen_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:
		if (pkt->count < 2) {
			DRM_ERROR("bad DRAW_INDEX_IMMD\n");
			return -EINVAL;
		}
		r = evergreen_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_OFFSET:
		if (pkt->count != 2) {
			DRM_ERROR("bad DRAW_INDEX_OFFSET\n");
			return -EINVAL;
		}
		r = evergreen_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_OFFSET_2:
		if (pkt->count != 3) {
			DRM_ERROR("bad DRAW_INDEX_OFFSET_2\n");
			return -EINVAL;
		}
		r = evergreen_cs_track_check(p);
		if (r) {
			dev_warn(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__);
			return r;
		}
		break;
	case PACKET3_DISPATCH_DIRECT:
		if (pkt->count != 3) {
			DRM_ERROR("bad DISPATCH_DIRECT\n");
			return -EINVAL;
		}
		r = evergreen_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_DISPATCH_INDIRECT:
		if (pkt->count != 1) {
			DRM_ERROR("bad DISPATCH_INDIRECT\n");
			return -EINVAL;
		}
		r = evergreen_cs_packet_next_reloc(p, &reloc);
		if (r) {
			DRM_ERROR("bad DISPATCH_INDIRECT\n");
			return -EINVAL;
		}
		ib[idx+0] = idx_value + (u32)(reloc->lobj.gpu_offset & 0xffffffff);
		r = evergreen_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 = evergreen_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 = evergreen_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 = evergreen_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 = evergreen_cs_packet_next_reloc(p, &reloc);
		if (r) {
			DRM_ERROR("bad EVENT_WRITE_EOP\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_EOS:
		if (pkt->count != 3) {
			DRM_ERROR("bad EVENT_WRITE_EOS\n");
			return -EINVAL;
		}
		r = evergreen_cs_packet_next_reloc(p, &reloc);
		if (r) {
			DRM_ERROR("bad EVENT_WRITE_EOS\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_START;
		end_reg = 4 * pkt->count + start_reg - 4;
		if ((start_reg < PACKET3_SET_CONFIG_REG_START) ||
		    (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 = evergreen_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_START;
		end_reg = 4 * pkt->count + start_reg - 4;
		if ((start_reg < PACKET3_SET_CONTEXT_REG_START) ||
		    (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 = evergreen_cs_check_reg(p, reg, idx+1+i);
			if (r)
				return r;
		}
		break;
	case PACKET3_SET_RESOURCE:
		if (pkt->count % 8) {
			DRM_ERROR("bad SET_RESOURCE\n");
			return -EINVAL;
		}
		start_reg = (idx_value << 2) + PACKET3_SET_RESOURCE_START;
		end_reg = 4 * pkt->count + start_reg - 4;
		if ((start_reg < PACKET3_SET_RESOURCE_START) ||
		    (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 / 8); i++) {
			struct radeon_bo *texture, *mipmap;
			u32 size, offset;

			switch (G__SQ_CONSTANT_TYPE(radeon_get_ib_value(p, idx+1+(i*8)+7))) {
			case SQ_TEX_VTX_VALID_TEXTURE:
				/* tex base */
				r = evergreen_cs_packet_next_reloc(p, &reloc);
				if (r) {
					DRM_ERROR("bad SET_RESOURCE (tex)\n");
					return -EINVAL;
				}
				ib[idx+1+(i*8)+2] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
				if (!p->keep_tiling_flags) {
					ib[idx+1+(i*8)+1] |=
						TEX_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
					if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
						ib[idx+1+(i*8)+6] |=
							TEX_TILE_SPLIT(evergreen_cs_get_tile_split(track->row_size));
						ib[idx+1+(i*8)+7] |=
							TEX_NUM_BANKS(evergreen_cs_get_num_banks(track->nbanks));
					}
				}
				texture = reloc->robj;
				/* tex mip base */
				r = evergreen_cs_packet_next_reloc(p, &reloc);
				if (r) {
					DRM_ERROR("bad SET_RESOURCE (tex)\n");
					return -EINVAL;
				}
				ib[idx+1+(i*8)+3] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
				mipmap = reloc->robj;
				r = evergreen_check_texture_resource(p,  idx+1+(i*8),
						texture, mipmap);
				if (r)
					return r;
				break;
			case SQ_TEX_VTX_VALID_BUFFER:
				/* vtx base */
				r = evergreen_cs_packet_next_reloc(p, &reloc);
				if (r) {
					DRM_ERROR("bad SET_RESOURCE (vtx)\n");
					return -EINVAL;
				}
				offset = radeon_get_ib_value(p, idx+1+(i*8)+0);
				size = radeon_get_ib_value(p, idx+1+(i*8)+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 for the bo\n");
					ib[idx+1+(i*8)+1] = radeon_bo_size(reloc->robj);
				}
				ib[idx+1+(i*8)+0] += (u32)((reloc->lobj.gpu_offset) & 0xffffffff);
				ib[idx+1+(i*8)+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:
		/* XXX fix me ALU const buffers only */
		break;
	case PACKET3_SET_BOOL_CONST:
		start_reg = (idx_value << 2) + PACKET3_SET_BOOL_CONST_START;
		end_reg = 4 * pkt->count + start_reg - 4;
		if ((start_reg < PACKET3_SET_BOOL_CONST_START) ||
		    (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_START;
		end_reg = 4 * pkt->count + start_reg - 4;
		if ((start_reg < PACKET3_SET_LOOP_CONST_START) ||
		    (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_START;
		end_reg = 4 * pkt->count + start_reg - 4;
		if ((start_reg < PACKET3_SET_CTL_CONST_START) ||
		    (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_START;
		end_reg = 4 * pkt->count + start_reg - 4;
		if ((start_reg < PACKET3_SET_SAMPLER_START) ||
		    (start_reg >= PACKET3_SET_SAMPLER_END) ||
		    (end_reg >= PACKET3_SET_SAMPLER_END)) {
			DRM_ERROR("bad SET_SAMPLER\n");
			return -EINVAL;
		}
		break;
	case PACKET3_NOP:
		break;
	default:
		DRM_ERROR("Packet3 opcode %x not supported\n", pkt->opcode);
		return -EINVAL;
	}
	return 0;
}

int evergreen_cs_parse(struct radeon_cs_parser *p)
{
	struct radeon_cs_packet pkt;
	struct evergreen_cs_track *track;
	u32 tmp;
	int r;

	if (p->track == NULL) {
		/* initialize tracker, we are in kms */
		track = kzalloc(sizeof(*track), GFP_KERNEL);
		if (track == NULL)
			return -ENOMEM;
		evergreen_cs_track_init(track);
		if (p->rdev->family >= CHIP_CAYMAN)
			tmp = p->rdev->config.cayman.tile_config;
		else
			tmp = p->rdev->config.evergreen.tile_config;

		switch (tmp & 0xf) {
		case 0:
			track->npipes = 1;
			break;
		case 1:
		default:
			track->npipes = 2;
			break;
		case 2:
			track->npipes = 4;
			break;
		case 3:
			track->npipes = 8;
			break;
		}

		switch ((tmp & 0xf0) >> 4) {
		case 0:
			track->nbanks = 4;
			break;
		case 1:
		default:
			track->nbanks = 8;
			break;
		case 2:
			track->nbanks = 16;
			break;
		}

		switch ((tmp & 0xf00) >> 8) {
		case 0:
			track->group_size = 256;
			break;
		case 1:
		default:
			track->group_size = 512;
			break;
		}

		switch ((tmp & 0xf000) >> 12) {
		case 0:
			track->row_size = 1;
			break;
		case 1:
		default:
			track->row_size = 2;
			break;
		case 2:
			track->row_size = 4;
			break;
		}

		p->track = track;
	}
	do {
		r = evergreen_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 = evergreen_cs_parse_packet0(p, &pkt);
			break;
		case PACKET_TYPE2:
			break;
		case PACKET_TYPE3:
			r = evergreen_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;
}

OpenPOWER on IntegriCloud