summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/radeon/r300.c
blob: 7e417d8dc733157c1c3c397246619334c1cc3cc9 (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
/*
 * 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/seq_file.h>
#include <linux/slab.h>
#include <drm/drmP.h>
#include <drm/drm.h>
#include <drm/drm_crtc_helper.h>
#include "radeon_reg.h"
#include "radeon.h"
#include "radeon_asic.h"
#include <drm/radeon_drm.h>
#include "r100_track.h"
#include "r300d.h"
#include "rv350d.h"
#include "r300_reg_safe.h"

/* This files gather functions specifics to: r300,r350,rv350,rv370,rv380
 *
 * GPU Errata:
 * - HOST_PATH_CNTL: r300 family seems to dislike write to HOST_PATH_CNTL
 *   using MMIO to flush host path read cache, this lead to HARDLOCKUP.
 *   However, scheduling such write to the ring seems harmless, i suspect
 *   the CP read collide with the flush somehow, or maybe the MC, hard to
 *   tell. (Jerome Glisse)
 */

/*
 * Indirect registers accessor
 */
uint32_t rv370_pcie_rreg(struct radeon_device *rdev, uint32_t reg)
{
	unsigned long flags;
	uint32_t r;

	spin_lock_irqsave(&rdev->pcie_idx_lock, flags);
	WREG32(RADEON_PCIE_INDEX, ((reg) & rdev->pcie_reg_mask));
	r = RREG32(RADEON_PCIE_DATA);
	spin_unlock_irqrestore(&rdev->pcie_idx_lock, flags);
	return r;
}

void rv370_pcie_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v)
{
	unsigned long flags;

	spin_lock_irqsave(&rdev->pcie_idx_lock, flags);
	WREG32(RADEON_PCIE_INDEX, ((reg) & rdev->pcie_reg_mask));
	WREG32(RADEON_PCIE_DATA, (v));
	spin_unlock_irqrestore(&rdev->pcie_idx_lock, flags);
}

/*
 * rv370,rv380 PCIE GART
 */
static int rv370_debugfs_pcie_gart_info_init(struct radeon_device *rdev);

void rv370_pcie_gart_tlb_flush(struct radeon_device *rdev)
{
	uint32_t tmp;
	int i;

	/* Workaround HW bug do flush 2 times */
	for (i = 0; i < 2; i++) {
		tmp = RREG32_PCIE(RADEON_PCIE_TX_GART_CNTL);
		WREG32_PCIE(RADEON_PCIE_TX_GART_CNTL, tmp | RADEON_PCIE_TX_GART_INVALIDATE_TLB);
		(void)RREG32_PCIE(RADEON_PCIE_TX_GART_CNTL);
		WREG32_PCIE(RADEON_PCIE_TX_GART_CNTL, tmp);
	}
	mb();
}

#define R300_PTE_UNSNOOPED (1 << 0)
#define R300_PTE_WRITEABLE (1 << 2)
#define R300_PTE_READABLE  (1 << 3)

uint64_t rv370_pcie_gart_get_page_entry(uint64_t addr, uint32_t flags)
{
	addr = (lower_32_bits(addr) >> 8) |
		((upper_32_bits(addr) & 0xff) << 24);
	if (flags & RADEON_GART_PAGE_READ)
		addr |= R300_PTE_READABLE;
	if (flags & RADEON_GART_PAGE_WRITE)
		addr |= R300_PTE_WRITEABLE;
	if (!(flags & RADEON_GART_PAGE_SNOOP))
		addr |= R300_PTE_UNSNOOPED;
	return addr;
}

void rv370_pcie_gart_set_page(struct radeon_device *rdev, unsigned i,
			      uint64_t entry)
{
	void __iomem *ptr = rdev->gart.ptr;

	/* on x86 we want this to be CPU endian, on powerpc
	 * on powerpc without HW swappers, it'll get swapped on way
	 * into VRAM - so no need for cpu_to_le32 on VRAM tables */
	writel(entry, ((void __iomem *)ptr) + (i * 4));
}

int rv370_pcie_gart_init(struct radeon_device *rdev)
{
	int r;

	if (rdev->gart.robj) {
		WARN(1, "RV370 PCIE GART already initialized\n");
		return 0;
	}
	/* Initialize common gart structure */
	r = radeon_gart_init(rdev);
	if (r)
		return r;
	r = rv370_debugfs_pcie_gart_info_init(rdev);
	if (r)
		DRM_ERROR("Failed to register debugfs file for PCIE gart !\n");
	rdev->gart.table_size = rdev->gart.num_gpu_pages * 4;
	rdev->asic->gart.tlb_flush = &rv370_pcie_gart_tlb_flush;
	rdev->asic->gart.get_page_entry = &rv370_pcie_gart_get_page_entry;
	rdev->asic->gart.set_page = &rv370_pcie_gart_set_page;
	return radeon_gart_table_vram_alloc(rdev);
}

int rv370_pcie_gart_enable(struct radeon_device *rdev)
{
	uint32_t table_addr;
	uint32_t tmp;
	int r;

	if (rdev->gart.robj == NULL) {
		dev_err(rdev->dev, "No VRAM object for PCIE GART.\n");
		return -EINVAL;
	}
	r = radeon_gart_table_vram_pin(rdev);
	if (r)
		return r;
	/* discard memory request outside of configured range */
	tmp = RADEON_PCIE_TX_GART_UNMAPPED_ACCESS_DISCARD;
	WREG32_PCIE(RADEON_PCIE_TX_GART_CNTL, tmp);
	WREG32_PCIE(RADEON_PCIE_TX_GART_START_LO, rdev->mc.gtt_start);
	tmp = rdev->mc.gtt_end & ~RADEON_GPU_PAGE_MASK;
	WREG32_PCIE(RADEON_PCIE_TX_GART_END_LO, tmp);
	WREG32_PCIE(RADEON_PCIE_TX_GART_START_HI, 0);
	WREG32_PCIE(RADEON_PCIE_TX_GART_END_HI, 0);
	table_addr = rdev->gart.table_addr;
	WREG32_PCIE(RADEON_PCIE_TX_GART_BASE, table_addr);
	/* FIXME: setup default page */
	WREG32_PCIE(RADEON_PCIE_TX_DISCARD_RD_ADDR_LO, rdev->mc.vram_start);
	WREG32_PCIE(RADEON_PCIE_TX_DISCARD_RD_ADDR_HI, 0);
	/* Clear error */
	WREG32_PCIE(RADEON_PCIE_TX_GART_ERROR, 0);
	tmp = RREG32_PCIE(RADEON_PCIE_TX_GART_CNTL);
	tmp |= RADEON_PCIE_TX_GART_EN;
	tmp |= RADEON_PCIE_TX_GART_UNMAPPED_ACCESS_DISCARD;
	WREG32_PCIE(RADEON_PCIE_TX_GART_CNTL, tmp);
	rv370_pcie_gart_tlb_flush(rdev);
	DRM_INFO("PCIE GART of %uM enabled (table at 0x%016llX).\n",
		 (unsigned)(rdev->mc.gtt_size >> 20),
		 (unsigned long long)table_addr);
	rdev->gart.ready = true;
	return 0;
}

void rv370_pcie_gart_disable(struct radeon_device *rdev)
{
	u32 tmp;

	WREG32_PCIE(RADEON_PCIE_TX_GART_START_LO, 0);
	WREG32_PCIE(RADEON_PCIE_TX_GART_END_LO, 0);
	WREG32_PCIE(RADEON_PCIE_TX_GART_START_HI, 0);
	WREG32_PCIE(RADEON_PCIE_TX_GART_END_HI, 0);
	tmp = RREG32_PCIE(RADEON_PCIE_TX_GART_CNTL);
	tmp |= RADEON_PCIE_TX_GART_UNMAPPED_ACCESS_DISCARD;
	WREG32_PCIE(RADEON_PCIE_TX_GART_CNTL, tmp & ~RADEON_PCIE_TX_GART_EN);
	radeon_gart_table_vram_unpin(rdev);
}

void rv370_pcie_gart_fini(struct radeon_device *rdev)
{
	radeon_gart_fini(rdev);
	rv370_pcie_gart_disable(rdev);
	radeon_gart_table_vram_free(rdev);
}

void r300_fence_ring_emit(struct radeon_device *rdev,
			  struct radeon_fence *fence)
{
	struct radeon_ring *ring = &rdev->ring[fence->ring];

	/* Who ever call radeon_fence_emit should call ring_lock and ask
	 * for enough space (today caller are ib schedule and buffer move) */
	/* Write SC register so SC & US assert idle */
	radeon_ring_write(ring, PACKET0(R300_RE_SCISSORS_TL, 0));
	radeon_ring_write(ring, 0);
	radeon_ring_write(ring, PACKET0(R300_RE_SCISSORS_BR, 0));
	radeon_ring_write(ring, 0);
	/* Flush 3D cache */
	radeon_ring_write(ring, PACKET0(R300_RB3D_DSTCACHE_CTLSTAT, 0));
	radeon_ring_write(ring, R300_RB3D_DC_FLUSH);
	radeon_ring_write(ring, PACKET0(R300_RB3D_ZCACHE_CTLSTAT, 0));
	radeon_ring_write(ring, R300_ZC_FLUSH);
	/* Wait until IDLE & CLEAN */
	radeon_ring_write(ring, PACKET0(RADEON_WAIT_UNTIL, 0));
	radeon_ring_write(ring, (RADEON_WAIT_3D_IDLECLEAN |
				 RADEON_WAIT_2D_IDLECLEAN |
				 RADEON_WAIT_DMA_GUI_IDLE));
	radeon_ring_write(ring, PACKET0(RADEON_HOST_PATH_CNTL, 0));
	radeon_ring_write(ring, rdev->config.r300.hdp_cntl |
				RADEON_HDP_READ_BUFFER_INVALIDATE);
	radeon_ring_write(ring, PACKET0(RADEON_HOST_PATH_CNTL, 0));
	radeon_ring_write(ring, rdev->config.r300.hdp_cntl);
	/* Emit fence sequence & fire IRQ */
	radeon_ring_write(ring, PACKET0(rdev->fence_drv[fence->ring].scratch_reg, 0));
	radeon_ring_write(ring, fence->seq);
	radeon_ring_write(ring, PACKET0(RADEON_GEN_INT_STATUS, 0));
	radeon_ring_write(ring, RADEON_SW_INT_FIRE);
}

void r300_ring_start(struct radeon_device *rdev, struct radeon_ring *ring)
{
	unsigned gb_tile_config;
	int r;

	/* Sub pixel 1/12 so we can have 4K rendering according to doc */
	gb_tile_config = (R300_ENABLE_TILING | R300_TILE_SIZE_16);
	switch(rdev->num_gb_pipes) {
	case 2:
		gb_tile_config |= R300_PIPE_COUNT_R300;
		break;
	case 3:
		gb_tile_config |= R300_PIPE_COUNT_R420_3P;
		break;
	case 4:
		gb_tile_config |= R300_PIPE_COUNT_R420;
		break;
	case 1:
	default:
		gb_tile_config |= R300_PIPE_COUNT_RV350;
		break;
	}

	r = radeon_ring_lock(rdev, ring, 64);
	if (r) {
		return;
	}
	radeon_ring_write(ring, PACKET0(RADEON_ISYNC_CNTL, 0));
	radeon_ring_write(ring,
			  RADEON_ISYNC_ANY2D_IDLE3D |
			  RADEON_ISYNC_ANY3D_IDLE2D |
			  RADEON_ISYNC_WAIT_IDLEGUI |
			  RADEON_ISYNC_CPSCRATCH_IDLEGUI);
	radeon_ring_write(ring, PACKET0(R300_GB_TILE_CONFIG, 0));
	radeon_ring_write(ring, gb_tile_config);
	radeon_ring_write(ring, PACKET0(RADEON_WAIT_UNTIL, 0));
	radeon_ring_write(ring,
			  RADEON_WAIT_2D_IDLECLEAN |
			  RADEON_WAIT_3D_IDLECLEAN);
	radeon_ring_write(ring, PACKET0(R300_DST_PIPE_CONFIG, 0));
	radeon_ring_write(ring, R300_PIPE_AUTO_CONFIG);
	radeon_ring_write(ring, PACKET0(R300_GB_SELECT, 0));
	radeon_ring_write(ring, 0);
	radeon_ring_write(ring, PACKET0(R300_GB_ENABLE, 0));
	radeon_ring_write(ring, 0);
	radeon_ring_write(ring, PACKET0(R300_RB3D_DSTCACHE_CTLSTAT, 0));
	radeon_ring_write(ring, R300_RB3D_DC_FLUSH | R300_RB3D_DC_FREE);
	radeon_ring_write(ring, PACKET0(R300_RB3D_ZCACHE_CTLSTAT, 0));
	radeon_ring_write(ring, R300_ZC_FLUSH | R300_ZC_FREE);
	radeon_ring_write(ring, PACKET0(RADEON_WAIT_UNTIL, 0));
	radeon_ring_write(ring,
			  RADEON_WAIT_2D_IDLECLEAN |
			  RADEON_WAIT_3D_IDLECLEAN);
	radeon_ring_write(ring, PACKET0(R300_GB_AA_CONFIG, 0));
	radeon_ring_write(ring, 0);
	radeon_ring_write(ring, PACKET0(R300_RB3D_DSTCACHE_CTLSTAT, 0));
	radeon_ring_write(ring, R300_RB3D_DC_FLUSH | R300_RB3D_DC_FREE);
	radeon_ring_write(ring, PACKET0(R300_RB3D_ZCACHE_CTLSTAT, 0));
	radeon_ring_write(ring, R300_ZC_FLUSH | R300_ZC_FREE);
	radeon_ring_write(ring, PACKET0(R300_GB_MSPOS0, 0));
	radeon_ring_write(ring,
			  ((6 << R300_MS_X0_SHIFT) |
			   (6 << R300_MS_Y0_SHIFT) |
			   (6 << R300_MS_X1_SHIFT) |
			   (6 << R300_MS_Y1_SHIFT) |
			   (6 << R300_MS_X2_SHIFT) |
			   (6 << R300_MS_Y2_SHIFT) |
			   (6 << R300_MSBD0_Y_SHIFT) |
			   (6 << R300_MSBD0_X_SHIFT)));
	radeon_ring_write(ring, PACKET0(R300_GB_MSPOS1, 0));
	radeon_ring_write(ring,
			  ((6 << R300_MS_X3_SHIFT) |
			   (6 << R300_MS_Y3_SHIFT) |
			   (6 << R300_MS_X4_SHIFT) |
			   (6 << R300_MS_Y4_SHIFT) |
			   (6 << R300_MS_X5_SHIFT) |
			   (6 << R300_MS_Y5_SHIFT) |
			   (6 << R300_MSBD1_SHIFT)));
	radeon_ring_write(ring, PACKET0(R300_GA_ENHANCE, 0));
	radeon_ring_write(ring, R300_GA_DEADLOCK_CNTL | R300_GA_FASTSYNC_CNTL);
	radeon_ring_write(ring, PACKET0(R300_GA_POLY_MODE, 0));
	radeon_ring_write(ring,
			  R300_FRONT_PTYPE_TRIANGE | R300_BACK_PTYPE_TRIANGE);
	radeon_ring_write(ring, PACKET0(R300_GA_ROUND_MODE, 0));
	radeon_ring_write(ring,
			  R300_GEOMETRY_ROUND_NEAREST |
			  R300_COLOR_ROUND_NEAREST);
	radeon_ring_unlock_commit(rdev, ring, false);
}

static void r300_errata(struct radeon_device *rdev)
{
	rdev->pll_errata = 0;

	if (rdev->family == CHIP_R300 &&
	    (RREG32(RADEON_CONFIG_CNTL) & RADEON_CFG_ATI_REV_ID_MASK) == RADEON_CFG_ATI_REV_A11) {
		rdev->pll_errata |= CHIP_ERRATA_R300_CG;
	}
}

int r300_mc_wait_for_idle(struct radeon_device *rdev)
{
	unsigned i;
	uint32_t tmp;

	for (i = 0; i < rdev->usec_timeout; i++) {
		/* read MC_STATUS */
		tmp = RREG32(RADEON_MC_STATUS);
		if (tmp & R300_MC_IDLE) {
			return 0;
		}
		DRM_UDELAY(1);
	}
	return -1;
}

static void r300_gpu_init(struct radeon_device *rdev)
{
	uint32_t gb_tile_config, tmp;

	if ((rdev->family == CHIP_R300 && rdev->pdev->device != 0x4144) ||
	    (rdev->family == CHIP_R350 && rdev->pdev->device != 0x4148)) {
		/* r300,r350 */
		rdev->num_gb_pipes = 2;
	} else {
		/* rv350,rv370,rv380,r300 AD, r350 AH */
		rdev->num_gb_pipes = 1;
	}
	rdev->num_z_pipes = 1;
	gb_tile_config = (R300_ENABLE_TILING | R300_TILE_SIZE_16);
	switch (rdev->num_gb_pipes) {
	case 2:
		gb_tile_config |= R300_PIPE_COUNT_R300;
		break;
	case 3:
		gb_tile_config |= R300_PIPE_COUNT_R420_3P;
		break;
	case 4:
		gb_tile_config |= R300_PIPE_COUNT_R420;
		break;
	default:
	case 1:
		gb_tile_config |= R300_PIPE_COUNT_RV350;
		break;
	}
	WREG32(R300_GB_TILE_CONFIG, gb_tile_config);

	if (r100_gui_wait_for_idle(rdev)) {
		printk(KERN_WARNING "Failed to wait GUI idle while "
		       "programming pipes. Bad things might happen.\n");
	}

	tmp = RREG32(R300_DST_PIPE_CONFIG);
	WREG32(R300_DST_PIPE_CONFIG, tmp | R300_PIPE_AUTO_CONFIG);

	WREG32(R300_RB2D_DSTCACHE_MODE,
	       R300_DC_AUTOFLUSH_ENABLE |
	       R300_DC_DC_DISABLE_IGNORE_PE);

	if (r100_gui_wait_for_idle(rdev)) {
		printk(KERN_WARNING "Failed to wait GUI idle while "
		       "programming pipes. Bad things might happen.\n");
	}
	if (r300_mc_wait_for_idle(rdev)) {
		printk(KERN_WARNING "Failed to wait MC idle while "
		       "programming pipes. Bad things might happen.\n");
	}
	DRM_INFO("radeon: %d quad pipes, %d Z pipes initialized.\n",
		 rdev->num_gb_pipes, rdev->num_z_pipes);
}

int r300_asic_reset(struct radeon_device *rdev, bool hard)
{
	struct r100_mc_save save;
	u32 status, tmp;
	int ret = 0;

	status = RREG32(R_000E40_RBBM_STATUS);
	if (!G_000E40_GUI_ACTIVE(status)) {
		return 0;
	}
	r100_mc_stop(rdev, &save);
	status = RREG32(R_000E40_RBBM_STATUS);
	dev_info(rdev->dev, "(%s:%d) RBBM_STATUS=0x%08X\n", __func__, __LINE__, status);
	/* stop CP */
	WREG32(RADEON_CP_CSQ_CNTL, 0);
	tmp = RREG32(RADEON_CP_RB_CNTL);
	WREG32(RADEON_CP_RB_CNTL, tmp | RADEON_RB_RPTR_WR_ENA);
	WREG32(RADEON_CP_RB_RPTR_WR, 0);
	WREG32(RADEON_CP_RB_WPTR, 0);
	WREG32(RADEON_CP_RB_CNTL, tmp);
	/* save PCI state */
	pci_save_state(rdev->pdev);
	/* disable bus mastering */
	r100_bm_disable(rdev);
	WREG32(R_0000F0_RBBM_SOFT_RESET, S_0000F0_SOFT_RESET_VAP(1) |
					S_0000F0_SOFT_RESET_GA(1));
	RREG32(R_0000F0_RBBM_SOFT_RESET);
	mdelay(500);
	WREG32(R_0000F0_RBBM_SOFT_RESET, 0);
	mdelay(1);
	status = RREG32(R_000E40_RBBM_STATUS);
	dev_info(rdev->dev, "(%s:%d) RBBM_STATUS=0x%08X\n", __func__, __LINE__, status);
	/* resetting the CP seems to be problematic sometimes it end up
	 * hard locking the computer, but it's necessary for successful
	 * reset more test & playing is needed on R3XX/R4XX to find a
	 * reliable (if any solution)
	 */
	WREG32(R_0000F0_RBBM_SOFT_RESET, S_0000F0_SOFT_RESET_CP(1));
	RREG32(R_0000F0_RBBM_SOFT_RESET);
	mdelay(500);
	WREG32(R_0000F0_RBBM_SOFT_RESET, 0);
	mdelay(1);
	status = RREG32(R_000E40_RBBM_STATUS);
	dev_info(rdev->dev, "(%s:%d) RBBM_STATUS=0x%08X\n", __func__, __LINE__, status);
	/* restore PCI & busmastering */
	pci_restore_state(rdev->pdev);
	r100_enable_bm(rdev);
	/* Check if GPU is idle */
	if (G_000E40_GA_BUSY(status) || G_000E40_VAP_BUSY(status)) {
		dev_err(rdev->dev, "failed to reset GPU\n");
		ret = -1;
	} else
		dev_info(rdev->dev, "GPU reset succeed\n");
	r100_mc_resume(rdev, &save);
	return ret;
}

/*
 * r300,r350,rv350,rv380 VRAM info
 */
void r300_mc_init(struct radeon_device *rdev)
{
	u64 base;
	u32 tmp;

	/* DDR for all card after R300 & IGP */
	rdev->mc.vram_is_ddr = true;
	tmp = RREG32(RADEON_MEM_CNTL);
	tmp &= R300_MEM_NUM_CHANNELS_MASK;
	switch (tmp) {
	case 0: rdev->mc.vram_width = 64; break;
	case 1: rdev->mc.vram_width = 128; break;
	case 2: rdev->mc.vram_width = 256; break;
	default:  rdev->mc.vram_width = 128; break;
	}
	r100_vram_init_sizes(rdev);
	base = rdev->mc.aper_base;
	if (rdev->flags & RADEON_IS_IGP)
		base = (RREG32(RADEON_NB_TOM) & 0xffff) << 16;
	radeon_vram_location(rdev, &rdev->mc, base);
	rdev->mc.gtt_base_align = 0;
	if (!(rdev->flags & RADEON_IS_AGP))
		radeon_gtt_location(rdev, &rdev->mc);
	radeon_update_bandwidth_info(rdev);
}

void rv370_set_pcie_lanes(struct radeon_device *rdev, int lanes)
{
	uint32_t link_width_cntl, mask;

	if (rdev->flags & RADEON_IS_IGP)
		return;

	if (!(rdev->flags & RADEON_IS_PCIE))
		return;

	/* FIXME wait for idle */

	switch (lanes) {
	case 0:
		mask = RADEON_PCIE_LC_LINK_WIDTH_X0;
		break;
	case 1:
		mask = RADEON_PCIE_LC_LINK_WIDTH_X1;
		break;
	case 2:
		mask = RADEON_PCIE_LC_LINK_WIDTH_X2;
		break;
	case 4:
		mask = RADEON_PCIE_LC_LINK_WIDTH_X4;
		break;
	case 8:
		mask = RADEON_PCIE_LC_LINK_WIDTH_X8;
		break;
	case 12:
		mask = RADEON_PCIE_LC_LINK_WIDTH_X12;
		break;
	case 16:
	default:
		mask = RADEON_PCIE_LC_LINK_WIDTH_X16;
		break;
	}

	link_width_cntl = RREG32_PCIE(RADEON_PCIE_LC_LINK_WIDTH_CNTL);

	if ((link_width_cntl & RADEON_PCIE_LC_LINK_WIDTH_RD_MASK) ==
	    (mask << RADEON_PCIE_LC_LINK_WIDTH_RD_SHIFT))
		return;

	link_width_cntl &= ~(RADEON_PCIE_LC_LINK_WIDTH_MASK |
			     RADEON_PCIE_LC_RECONFIG_NOW |
			     RADEON_PCIE_LC_RECONFIG_LATER |
			     RADEON_PCIE_LC_SHORT_RECONFIG_EN);
	link_width_cntl |= mask;
	WREG32_PCIE(RADEON_PCIE_LC_LINK_WIDTH_CNTL, link_width_cntl);
	WREG32_PCIE(RADEON_PCIE_LC_LINK_WIDTH_CNTL, (link_width_cntl |
						     RADEON_PCIE_LC_RECONFIG_NOW));

	/* wait for lane set to complete */
	link_width_cntl = RREG32_PCIE(RADEON_PCIE_LC_LINK_WIDTH_CNTL);
	while (link_width_cntl == 0xffffffff)
		link_width_cntl = RREG32_PCIE(RADEON_PCIE_LC_LINK_WIDTH_CNTL);

}

int rv370_get_pcie_lanes(struct radeon_device *rdev)
{
	u32 link_width_cntl;

	if (rdev->flags & RADEON_IS_IGP)
		return 0;

	if (!(rdev->flags & RADEON_IS_PCIE))
		return 0;

	/* FIXME wait for idle */

	link_width_cntl = RREG32_PCIE(RADEON_PCIE_LC_LINK_WIDTH_CNTL);

	switch ((link_width_cntl & RADEON_PCIE_LC_LINK_WIDTH_RD_MASK) >> RADEON_PCIE_LC_LINK_WIDTH_RD_SHIFT) {
	case RADEON_PCIE_LC_LINK_WIDTH_X0:
		return 0;
	case RADEON_PCIE_LC_LINK_WIDTH_X1:
		return 1;
	case RADEON_PCIE_LC_LINK_WIDTH_X2:
		return 2;
	case RADEON_PCIE_LC_LINK_WIDTH_X4:
		return 4;
	case RADEON_PCIE_LC_LINK_WIDTH_X8:
		return 8;
	case RADEON_PCIE_LC_LINK_WIDTH_X16:
	default:
		return 16;
	}
}

#if defined(CONFIG_DEBUG_FS)
static int rv370_debugfs_pcie_gart_info(struct seq_file *m, void *data)
{
	struct drm_info_node *node = (struct drm_info_node *) m->private;
	struct drm_device *dev = node->minor->dev;
	struct radeon_device *rdev = dev->dev_private;
	uint32_t tmp;

	tmp = RREG32_PCIE(RADEON_PCIE_TX_GART_CNTL);
	seq_printf(m, "PCIE_TX_GART_CNTL 0x%08x\n", tmp);
	tmp = RREG32_PCIE(RADEON_PCIE_TX_GART_BASE);
	seq_printf(m, "PCIE_TX_GART_BASE 0x%08x\n", tmp);
	tmp = RREG32_PCIE(RADEON_PCIE_TX_GART_START_LO);
	seq_printf(m, "PCIE_TX_GART_START_LO 0x%08x\n", tmp);
	tmp = RREG32_PCIE(RADEON_PCIE_TX_GART_START_HI);
	seq_printf(m, "PCIE_TX_GART_START_HI 0x%08x\n", tmp);
	tmp = RREG32_PCIE(RADEON_PCIE_TX_GART_END_LO);
	seq_printf(m, "PCIE_TX_GART_END_LO 0x%08x\n", tmp);
	tmp = RREG32_PCIE(RADEON_PCIE_TX_GART_END_HI);
	seq_printf(m, "PCIE_TX_GART_END_HI 0x%08x\n", tmp);
	tmp = RREG32_PCIE(RADEON_PCIE_TX_GART_ERROR);
	seq_printf(m, "PCIE_TX_GART_ERROR 0x%08x\n", tmp);
	return 0;
}

static struct drm_info_list rv370_pcie_gart_info_list[] = {
	{"rv370_pcie_gart_info", rv370_debugfs_pcie_gart_info, 0, NULL},
};
#endif

static int rv370_debugfs_pcie_gart_info_init(struct radeon_device *rdev)
{
#if defined(CONFIG_DEBUG_FS)
	return radeon_debugfs_add_files(rdev, rv370_pcie_gart_info_list, 1);
#else
	return 0;
#endif
}

static int r300_packet0_check(struct radeon_cs_parser *p,
		struct radeon_cs_packet *pkt,
		unsigned idx, unsigned reg)
{
	struct radeon_bo_list *reloc;
	struct r100_cs_track *track;
	volatile uint32_t *ib;
	uint32_t tmp, tile_flags = 0;
	unsigned i;
	int r;
	u32 idx_value;

	ib = p->ib.ptr;
	track = (struct r100_cs_track *)p->track;
	idx_value = radeon_get_ib_value(p, idx);

	switch(reg) {
	case AVIVO_D1MODE_VLINE_START_END:
	case RADEON_CRTC_GUI_TRIG_VLINE:
		r = r100_cs_packet_parse_vline(p);
		if (r) {
			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
					idx, reg);
			radeon_cs_dump_packet(p, pkt);
			return r;
		}
		break;
	case RADEON_DST_PITCH_OFFSET:
	case RADEON_SRC_PITCH_OFFSET:
		r = r100_reloc_pitch_offset(p, pkt, idx, reg);
		if (r)
			return r;
		break;
	case R300_RB3D_COLOROFFSET0:
	case R300_RB3D_COLOROFFSET1:
	case R300_RB3D_COLOROFFSET2:
	case R300_RB3D_COLOROFFSET3:
		i = (reg - R300_RB3D_COLOROFFSET0) >> 2;
		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
		if (r) {
			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
					idx, reg);
			radeon_cs_dump_packet(p, pkt);
			return r;
		}
		track->cb[i].robj = reloc->robj;
		track->cb[i].offset = idx_value;
		track->cb_dirty = true;
		ib[idx] = idx_value + ((u32)reloc->gpu_offset);
		break;
	case R300_ZB_DEPTHOFFSET:
		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
		if (r) {
			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
					idx, reg);
			radeon_cs_dump_packet(p, pkt);
			return r;
		}
		track->zb.robj = reloc->robj;
		track->zb.offset = idx_value;
		track->zb_dirty = true;
		ib[idx] = idx_value + ((u32)reloc->gpu_offset);
		break;
	case R300_TX_OFFSET_0:
	case R300_TX_OFFSET_0+4:
	case R300_TX_OFFSET_0+8:
	case R300_TX_OFFSET_0+12:
	case R300_TX_OFFSET_0+16:
	case R300_TX_OFFSET_0+20:
	case R300_TX_OFFSET_0+24:
	case R300_TX_OFFSET_0+28:
	case R300_TX_OFFSET_0+32:
	case R300_TX_OFFSET_0+36:
	case R300_TX_OFFSET_0+40:
	case R300_TX_OFFSET_0+44:
	case R300_TX_OFFSET_0+48:
	case R300_TX_OFFSET_0+52:
	case R300_TX_OFFSET_0+56:
	case R300_TX_OFFSET_0+60:
		i = (reg - R300_TX_OFFSET_0) >> 2;
		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
		if (r) {
			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
					idx, reg);
			radeon_cs_dump_packet(p, pkt);
			return r;
		}

		if (p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS) {
			ib[idx] = (idx_value & 31) | /* keep the 1st 5 bits */
				  ((idx_value & ~31) + (u32)reloc->gpu_offset);
		} else {
			if (reloc->tiling_flags & RADEON_TILING_MACRO)
				tile_flags |= R300_TXO_MACRO_TILE;
			if (reloc->tiling_flags & RADEON_TILING_MICRO)
				tile_flags |= R300_TXO_MICRO_TILE;
			else if (reloc->tiling_flags & RADEON_TILING_MICRO_SQUARE)
				tile_flags |= R300_TXO_MICRO_TILE_SQUARE;

			tmp = idx_value + ((u32)reloc->gpu_offset);
			tmp |= tile_flags;
			ib[idx] = tmp;
		}
		track->textures[i].robj = reloc->robj;
		track->tex_dirty = true;
		break;
	/* Tracked registers */
	case 0x2084:
		/* VAP_VF_CNTL */
		track->vap_vf_cntl = idx_value;
		break;
	case 0x20B4:
		/* VAP_VTX_SIZE */
		track->vtx_size = idx_value & 0x7F;
		break;
	case 0x2134:
		/* VAP_VF_MAX_VTX_INDX */
		track->max_indx = idx_value & 0x00FFFFFFUL;
		break;
	case 0x2088:
		/* VAP_ALT_NUM_VERTICES - only valid on r500 */
		if (p->rdev->family < CHIP_RV515)
			goto fail;
		track->vap_alt_nverts = idx_value & 0xFFFFFF;
		break;
	case 0x43E4:
		/* SC_SCISSOR1 */
		track->maxy = ((idx_value >> 13) & 0x1FFF) + 1;
		if (p->rdev->family < CHIP_RV515) {
			track->maxy -= 1440;
		}
		track->cb_dirty = true;
		track->zb_dirty = true;
		break;
	case 0x4E00:
		/* RB3D_CCTL */
		if ((idx_value & (1 << 10)) && /* CMASK_ENABLE */
		    p->rdev->cmask_filp != p->filp) {
			DRM_ERROR("Invalid RB3D_CCTL: Cannot enable CMASK.\n");
			return -EINVAL;
		}
		track->num_cb = ((idx_value >> 5) & 0x3) + 1;
		track->cb_dirty = true;
		break;
	case 0x4E38:
	case 0x4E3C:
	case 0x4E40:
	case 0x4E44:
		/* RB3D_COLORPITCH0 */
		/* RB3D_COLORPITCH1 */
		/* RB3D_COLORPITCH2 */
		/* RB3D_COLORPITCH3 */
		if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
			r = radeon_cs_packet_next_reloc(p, &reloc, 0);
			if (r) {
				DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
					  idx, reg);
				radeon_cs_dump_packet(p, pkt);
				return r;
			}

			if (reloc->tiling_flags & RADEON_TILING_MACRO)
				tile_flags |= R300_COLOR_TILE_ENABLE;
			if (reloc->tiling_flags & RADEON_TILING_MICRO)
				tile_flags |= R300_COLOR_MICROTILE_ENABLE;
			else if (reloc->tiling_flags & RADEON_TILING_MICRO_SQUARE)
				tile_flags |= R300_COLOR_MICROTILE_SQUARE_ENABLE;

			tmp = idx_value & ~(0x7 << 16);
			tmp |= tile_flags;
			ib[idx] = tmp;
		}
		i = (reg - 0x4E38) >> 2;
		track->cb[i].pitch = idx_value & 0x3FFE;
		switch (((idx_value >> 21) & 0xF)) {
		case 9:
		case 11:
		case 12:
			track->cb[i].cpp = 1;
			break;
		case 3:
		case 4:
		case 13:
		case 15:
			track->cb[i].cpp = 2;
			break;
		case 5:
			if (p->rdev->family < CHIP_RV515) {
				DRM_ERROR("Invalid color buffer format (%d)!\n",
					  ((idx_value >> 21) & 0xF));
				return -EINVAL;
			}
			/* Pass through. */
		case 6:
			track->cb[i].cpp = 4;
			break;
		case 10:
			track->cb[i].cpp = 8;
			break;
		case 7:
			track->cb[i].cpp = 16;
			break;
		default:
			DRM_ERROR("Invalid color buffer format (%d) !\n",
				  ((idx_value >> 21) & 0xF));
			return -EINVAL;
		}
		track->cb_dirty = true;
		break;
	case 0x4F00:
		/* ZB_CNTL */
		if (idx_value & 2) {
			track->z_enabled = true;
		} else {
			track->z_enabled = false;
		}
		track->zb_dirty = true;
		break;
	case 0x4F10:
		/* ZB_FORMAT */
		switch ((idx_value & 0xF)) {
		case 0:
		case 1:
			track->zb.cpp = 2;
			break;
		case 2:
			track->zb.cpp = 4;
			break;
		default:
			DRM_ERROR("Invalid z buffer format (%d) !\n",
				  (idx_value & 0xF));
			return -EINVAL;
		}
		track->zb_dirty = true;
		break;
	case 0x4F24:
		/* ZB_DEPTHPITCH */
		if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
			r = radeon_cs_packet_next_reloc(p, &reloc, 0);
			if (r) {
				DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
					  idx, reg);
				radeon_cs_dump_packet(p, pkt);
				return r;
			}

			if (reloc->tiling_flags & RADEON_TILING_MACRO)
				tile_flags |= R300_DEPTHMACROTILE_ENABLE;
			if (reloc->tiling_flags & RADEON_TILING_MICRO)
				tile_flags |= R300_DEPTHMICROTILE_TILED;
			else if (reloc->tiling_flags & RADEON_TILING_MICRO_SQUARE)
				tile_flags |= R300_DEPTHMICROTILE_TILED_SQUARE;

			tmp = idx_value & ~(0x7 << 16);
			tmp |= tile_flags;
			ib[idx] = tmp;
		}
		track->zb.pitch = idx_value & 0x3FFC;
		track->zb_dirty = true;
		break;
	case 0x4104:
		/* TX_ENABLE */
		for (i = 0; i < 16; i++) {
			bool enabled;

			enabled = !!(idx_value & (1 << i));
			track->textures[i].enabled = enabled;
		}
		track->tex_dirty = true;
		break;
	case 0x44C0:
	case 0x44C4:
	case 0x44C8:
	case 0x44CC:
	case 0x44D0:
	case 0x44D4:
	case 0x44D8:
	case 0x44DC:
	case 0x44E0:
	case 0x44E4:
	case 0x44E8:
	case 0x44EC:
	case 0x44F0:
	case 0x44F4:
	case 0x44F8:
	case 0x44FC:
		/* TX_FORMAT1_[0-15] */
		i = (reg - 0x44C0) >> 2;
		tmp = (idx_value >> 25) & 0x3;
		track->textures[i].tex_coord_type = tmp;
		switch ((idx_value & 0x1F)) {
		case R300_TX_FORMAT_X8:
		case R300_TX_FORMAT_Y4X4:
		case R300_TX_FORMAT_Z3Y3X2:
			track->textures[i].cpp = 1;
			track->textures[i].compress_format = R100_TRACK_COMP_NONE;
			break;
		case R300_TX_FORMAT_X16:
		case R300_TX_FORMAT_FL_I16:
		case R300_TX_FORMAT_Y8X8:
		case R300_TX_FORMAT_Z5Y6X5:
		case R300_TX_FORMAT_Z6Y5X5:
		case R300_TX_FORMAT_W4Z4Y4X4:
		case R300_TX_FORMAT_W1Z5Y5X5:
		case R300_TX_FORMAT_D3DMFT_CxV8U8:
		case R300_TX_FORMAT_B8G8_B8G8:
		case R300_TX_FORMAT_G8R8_G8B8:
			track->textures[i].cpp = 2;
			track->textures[i].compress_format = R100_TRACK_COMP_NONE;
			break;
		case R300_TX_FORMAT_Y16X16:
		case R300_TX_FORMAT_FL_I16A16:
		case R300_TX_FORMAT_Z11Y11X10:
		case R300_TX_FORMAT_Z10Y11X11:
		case R300_TX_FORMAT_W8Z8Y8X8:
		case R300_TX_FORMAT_W2Z10Y10X10:
		case 0x17:
		case R300_TX_FORMAT_FL_I32:
		case 0x1e:
			track->textures[i].cpp = 4;
			track->textures[i].compress_format = R100_TRACK_COMP_NONE;
			break;
		case R300_TX_FORMAT_W16Z16Y16X16:
		case R300_TX_FORMAT_FL_R16G16B16A16:
		case R300_TX_FORMAT_FL_I32A32:
			track->textures[i].cpp = 8;
			track->textures[i].compress_format = R100_TRACK_COMP_NONE;
			break;
		case R300_TX_FORMAT_FL_R32G32B32A32:
			track->textures[i].cpp = 16;
			track->textures[i].compress_format = R100_TRACK_COMP_NONE;
			break;
		case R300_TX_FORMAT_DXT1:
			track->textures[i].cpp = 1;
			track->textures[i].compress_format = R100_TRACK_COMP_DXT1;
			break;
		case R300_TX_FORMAT_ATI2N:
			if (p->rdev->family < CHIP_R420) {
				DRM_ERROR("Invalid texture format %u\n",
					  (idx_value & 0x1F));
				return -EINVAL;
			}
			/* The same rules apply as for DXT3/5. */
			/* Pass through. */
		case R300_TX_FORMAT_DXT3:
		case R300_TX_FORMAT_DXT5:
			track->textures[i].cpp = 1;
			track->textures[i].compress_format = R100_TRACK_COMP_DXT35;
			break;
		default:
			DRM_ERROR("Invalid texture format %u\n",
				  (idx_value & 0x1F));
			return -EINVAL;
		}
		track->tex_dirty = true;
		break;
	case 0x4400:
	case 0x4404:
	case 0x4408:
	case 0x440C:
	case 0x4410:
	case 0x4414:
	case 0x4418:
	case 0x441C:
	case 0x4420:
	case 0x4424:
	case 0x4428:
	case 0x442C:
	case 0x4430:
	case 0x4434:
	case 0x4438:
	case 0x443C:
		/* TX_FILTER0_[0-15] */
		i = (reg - 0x4400) >> 2;
		tmp = idx_value & 0x7;
		if (tmp == 2 || tmp == 4 || tmp == 6) {
			track->textures[i].roundup_w = false;
		}
		tmp = (idx_value >> 3) & 0x7;
		if (tmp == 2 || tmp == 4 || tmp == 6) {
			track->textures[i].roundup_h = false;
		}
		track->tex_dirty = true;
		break;
	case 0x4500:
	case 0x4504:
	case 0x4508:
	case 0x450C:
	case 0x4510:
	case 0x4514:
	case 0x4518:
	case 0x451C:
	case 0x4520:
	case 0x4524:
	case 0x4528:
	case 0x452C:
	case 0x4530:
	case 0x4534:
	case 0x4538:
	case 0x453C:
		/* TX_FORMAT2_[0-15] */
		i = (reg - 0x4500) >> 2;
		tmp = idx_value & 0x3FFF;
		track->textures[i].pitch = tmp + 1;
		if (p->rdev->family >= CHIP_RV515) {
			tmp = ((idx_value >> 15) & 1) << 11;
			track->textures[i].width_11 = tmp;
			tmp = ((idx_value >> 16) & 1) << 11;
			track->textures[i].height_11 = tmp;

			/* ATI1N */
			if (idx_value & (1 << 14)) {
				/* The same rules apply as for DXT1. */
				track->textures[i].compress_format =
					R100_TRACK_COMP_DXT1;
			}
		} else if (idx_value & (1 << 14)) {
			DRM_ERROR("Forbidden bit TXFORMAT_MSB\n");
			return -EINVAL;
		}
		track->tex_dirty = true;
		break;
	case 0x4480:
	case 0x4484:
	case 0x4488:
	case 0x448C:
	case 0x4490:
	case 0x4494:
	case 0x4498:
	case 0x449C:
	case 0x44A0:
	case 0x44A4:
	case 0x44A8:
	case 0x44AC:
	case 0x44B0:
	case 0x44B4:
	case 0x44B8:
	case 0x44BC:
		/* TX_FORMAT0_[0-15] */
		i = (reg - 0x4480) >> 2;
		tmp = idx_value & 0x7FF;
		track->textures[i].width = tmp + 1;
		tmp = (idx_value >> 11) & 0x7FF;
		track->textures[i].height = tmp + 1;
		tmp = (idx_value >> 26) & 0xF;
		track->textures[i].num_levels = tmp;
		tmp = idx_value & (1 << 31);
		track->textures[i].use_pitch = !!tmp;
		tmp = (idx_value >> 22) & 0xF;
		track->textures[i].txdepth = tmp;
		track->tex_dirty = true;
		break;
	case R300_ZB_ZPASS_ADDR:
		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
		if (r) {
			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
					idx, reg);
			radeon_cs_dump_packet(p, pkt);
			return r;
		}
		ib[idx] = idx_value + ((u32)reloc->gpu_offset);
		break;
	case 0x4e0c:
		/* RB3D_COLOR_CHANNEL_MASK */
		track->color_channel_mask = idx_value;
		track->cb_dirty = true;
		break;
	case 0x43a4:
		/* SC_HYPERZ_EN */
		/* r300c emits this register - we need to disable hyperz for it
		 * without complaining */
		if (p->rdev->hyperz_filp != p->filp) {
			if (idx_value & 0x1)
				ib[idx] = idx_value & ~1;
		}
		break;
	case 0x4f1c:
		/* ZB_BW_CNTL */
		track->zb_cb_clear = !!(idx_value & (1 << 5));
		track->cb_dirty = true;
		track->zb_dirty = true;
		if (p->rdev->hyperz_filp != p->filp) {
			if (idx_value & (R300_HIZ_ENABLE |
					 R300_RD_COMP_ENABLE |
					 R300_WR_COMP_ENABLE |
					 R300_FAST_FILL_ENABLE))
				goto fail;
		}
		break;
	case 0x4e04:
		/* RB3D_BLENDCNTL */
		track->blend_read_enable = !!(idx_value & (1 << 2));
		track->cb_dirty = true;
		break;
	case R300_RB3D_AARESOLVE_OFFSET:
		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
		if (r) {
			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
				  idx, reg);
			radeon_cs_dump_packet(p, pkt);
			return r;
		}
		track->aa.robj = reloc->robj;
		track->aa.offset = idx_value;
		track->aa_dirty = true;
		ib[idx] = idx_value + ((u32)reloc->gpu_offset);
		break;
	case R300_RB3D_AARESOLVE_PITCH:
		track->aa.pitch = idx_value & 0x3FFE;
		track->aa_dirty = true;
		break;
	case R300_RB3D_AARESOLVE_CTL:
		track->aaresolve = idx_value & 0x1;
		track->aa_dirty = true;
		break;
	case 0x4f30: /* ZB_MASK_OFFSET */
	case 0x4f34: /* ZB_ZMASK_PITCH */
	case 0x4f44: /* ZB_HIZ_OFFSET */
	case 0x4f54: /* ZB_HIZ_PITCH */
		if (idx_value && (p->rdev->hyperz_filp != p->filp))
			goto fail;
		break;
	case 0x4028:
		if (idx_value && (p->rdev->hyperz_filp != p->filp))
			goto fail;
		/* GB_Z_PEQ_CONFIG */
		if (p->rdev->family >= CHIP_RV350)
			break;
		goto fail;
		break;
	case 0x4be8:
		/* valid register only on RV530 */
		if (p->rdev->family == CHIP_RV530)
			break;
		/* fallthrough do not move */
	default:
		goto fail;
	}
	return 0;
fail:
	printk(KERN_ERR "Forbidden register 0x%04X in cs at %d (val=%08x)\n",
	       reg, idx, idx_value);
	return -EINVAL;
}

static int r300_packet3_check(struct radeon_cs_parser *p,
			      struct radeon_cs_packet *pkt)
{
	struct radeon_bo_list *reloc;
	struct r100_cs_track *track;
	volatile uint32_t *ib;
	unsigned idx;
	int r;

	ib = p->ib.ptr;
	idx = pkt->idx + 1;
	track = (struct r100_cs_track *)p->track;
	switch(pkt->opcode) {
	case PACKET3_3D_LOAD_VBPNTR:
		r = r100_packet3_load_vbpntr(p, pkt, idx);
		if (r)
			return r;
		break;
	case PACKET3_INDX_BUFFER:
		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
		if (r) {
			DRM_ERROR("No reloc for packet3 %d\n", pkt->opcode);
			radeon_cs_dump_packet(p, pkt);
			return r;
		}
		ib[idx+1] = radeon_get_ib_value(p, idx + 1) + ((u32)reloc->gpu_offset);
		r = r100_cs_track_check_pkt3_indx_buffer(p, pkt, reloc->robj);
		if (r) {
			return r;
		}
		break;
	/* Draw packet */
	case PACKET3_3D_DRAW_IMMD:
		/* Number of dwords is vtx_size * (num_vertices - 1)
		 * PRIM_WALK must be equal to 3 vertex data in embedded
		 * in cmd stream */
		if (((radeon_get_ib_value(p, idx + 1) >> 4) & 0x3) != 3) {
			DRM_ERROR("PRIM_WALK must be 3 for IMMD draw\n");
			return -EINVAL;
		}
		track->vap_vf_cntl = radeon_get_ib_value(p, idx + 1);
		track->immd_dwords = pkt->count - 1;
		r = r100_cs_track_check(p->rdev, track);
		if (r) {
			return r;
		}
		break;
	case PACKET3_3D_DRAW_IMMD_2:
		/* Number of dwords is vtx_size * (num_vertices - 1)
		 * PRIM_WALK must be equal to 3 vertex data in embedded
		 * in cmd stream */
		if (((radeon_get_ib_value(p, idx) >> 4) & 0x3) != 3) {
			DRM_ERROR("PRIM_WALK must be 3 for IMMD draw\n");
			return -EINVAL;
		}
		track->vap_vf_cntl = radeon_get_ib_value(p, idx);
		track->immd_dwords = pkt->count;
		r = r100_cs_track_check(p->rdev, track);
		if (r) {
			return r;
		}
		break;
	case PACKET3_3D_DRAW_VBUF:
		track->vap_vf_cntl = radeon_get_ib_value(p, idx + 1);
		r = r100_cs_track_check(p->rdev, track);
		if (r) {
			return r;
		}
		break;
	case PACKET3_3D_DRAW_VBUF_2:
		track->vap_vf_cntl = radeon_get_ib_value(p, idx);
		r = r100_cs_track_check(p->rdev, track);
		if (r) {
			return r;
		}
		break;
	case PACKET3_3D_DRAW_INDX:
		track->vap_vf_cntl = radeon_get_ib_value(p, idx + 1);
		r = r100_cs_track_check(p->rdev, track);
		if (r) {
			return r;
		}
		break;
	case PACKET3_3D_DRAW_INDX_2:
		track->vap_vf_cntl = radeon_get_ib_value(p, idx);
		r = r100_cs_track_check(p->rdev, track);
		if (r) {
			return r;
		}
		break;
	case PACKET3_3D_CLEAR_HIZ:
	case PACKET3_3D_CLEAR_ZMASK:
		if (p->rdev->hyperz_filp != p->filp)
			return -EINVAL;
		break;
	case PACKET3_3D_CLEAR_CMASK:
		if (p->rdev->cmask_filp != p->filp)
			return -EINVAL;
		break;
	case PACKET3_NOP:
		break;
	default:
		DRM_ERROR("Packet3 opcode %x not supported\n", pkt->opcode);
		return -EINVAL;
	}
	return 0;
}

int r300_cs_parse(struct radeon_cs_parser *p)
{
	struct radeon_cs_packet pkt;
	struct r100_cs_track *track;
	int r;

	track = kzalloc(sizeof(*track), GFP_KERNEL);
	if (track == NULL)
		return -ENOMEM;
	r100_cs_track_clear(p->rdev, track);
	p->track = track;
	do {
		r = radeon_cs_packet_parse(p, &pkt, p->idx);
		if (r) {
			return r;
		}
		p->idx += pkt.count + 2;
		switch (pkt.type) {
		case RADEON_PACKET_TYPE0:
			r = r100_cs_parse_packet0(p, &pkt,
						  p->rdev->config.r300.reg_safe_bm,
						  p->rdev->config.r300.reg_safe_bm_size,
						  &r300_packet0_check);
			break;
		case RADEON_PACKET_TYPE2:
			break;
		case RADEON_PACKET_TYPE3:
			r = r300_packet3_check(p, &pkt);
			break;
		default:
			DRM_ERROR("Unknown packet type %d !\n", pkt.type);
			return -EINVAL;
		}
		if (r) {
			return r;
		}
	} while (p->idx < p->chunk_ib->length_dw);
	return 0;
}

void r300_set_reg_safe(struct radeon_device *rdev)
{
	rdev->config.r300.reg_safe_bm = r300_reg_safe_bm;
	rdev->config.r300.reg_safe_bm_size = ARRAY_SIZE(r300_reg_safe_bm);
}

void r300_mc_program(struct radeon_device *rdev)
{
	struct r100_mc_save save;
	int r;

	r = r100_debugfs_mc_info_init(rdev);
	if (r) {
		dev_err(rdev->dev, "Failed to create r100_mc debugfs file.\n");
	}

	/* Stops all mc clients */
	r100_mc_stop(rdev, &save);
	if (rdev->flags & RADEON_IS_AGP) {
		WREG32(R_00014C_MC_AGP_LOCATION,
			S_00014C_MC_AGP_START(rdev->mc.gtt_start >> 16) |
			S_00014C_MC_AGP_TOP(rdev->mc.gtt_end >> 16));
		WREG32(R_000170_AGP_BASE, lower_32_bits(rdev->mc.agp_base));
		WREG32(R_00015C_AGP_BASE_2,
			upper_32_bits(rdev->mc.agp_base) & 0xff);
	} else {
		WREG32(R_00014C_MC_AGP_LOCATION, 0x0FFFFFFF);
		WREG32(R_000170_AGP_BASE, 0);
		WREG32(R_00015C_AGP_BASE_2, 0);
	}
	/* Wait for mc idle */
	if (r300_mc_wait_for_idle(rdev))
		DRM_INFO("Failed to wait MC idle before programming MC.\n");
	/* Program MC, should be a 32bits limited address space */
	WREG32(R_000148_MC_FB_LOCATION,
		S_000148_MC_FB_START(rdev->mc.vram_start >> 16) |
		S_000148_MC_FB_TOP(rdev->mc.vram_end >> 16));
	r100_mc_resume(rdev, &save);
}

void r300_clock_startup(struct radeon_device *rdev)
{
	u32 tmp;

	if (radeon_dynclks != -1 && radeon_dynclks)
		radeon_legacy_set_clock_gating(rdev, 1);
	/* We need to force on some of the block */
	tmp = RREG32_PLL(R_00000D_SCLK_CNTL);
	tmp |= S_00000D_FORCE_CP(1) | S_00000D_FORCE_VIP(1);
	if ((rdev->family == CHIP_RV350) || (rdev->family == CHIP_RV380))
		tmp |= S_00000D_FORCE_VAP(1);
	WREG32_PLL(R_00000D_SCLK_CNTL, tmp);
}

static int r300_startup(struct radeon_device *rdev)
{
	int r;

	/* set common regs */
	r100_set_common_regs(rdev);
	/* program mc */
	r300_mc_program(rdev);
	/* Resume clock */
	r300_clock_startup(rdev);
	/* Initialize GPU configuration (# pipes, ...) */
	r300_gpu_init(rdev);
	/* Initialize GART (initialize after TTM so we can allocate
	 * memory through TTM but finalize after TTM) */
	if (rdev->flags & RADEON_IS_PCIE) {
		r = rv370_pcie_gart_enable(rdev);
		if (r)
			return r;
	}

	if (rdev->family == CHIP_R300 ||
	    rdev->family == CHIP_R350 ||
	    rdev->family == CHIP_RV350)
		r100_enable_bm(rdev);

	if (rdev->flags & RADEON_IS_PCI) {
		r = r100_pci_gart_enable(rdev);
		if (r)
			return r;
	}

	/* allocate wb buffer */
	r = radeon_wb_init(rdev);
	if (r)
		return r;

	r = radeon_fence_driver_start_ring(rdev, RADEON_RING_TYPE_GFX_INDEX);
	if (r) {
		dev_err(rdev->dev, "failed initializing CP fences (%d).\n", r);
		return r;
	}

	/* Enable IRQ */
	if (!rdev->irq.installed) {
		r = radeon_irq_kms_init(rdev);
		if (r)
			return r;
	}

	r100_irq_set(rdev);
	rdev->config.r300.hdp_cntl = RREG32(RADEON_HOST_PATH_CNTL);
	/* 1M ring buffer */
	r = r100_cp_init(rdev, 1024 * 1024);
	if (r) {
		dev_err(rdev->dev, "failed initializing CP (%d).\n", r);
		return r;
	}

	r = radeon_ib_pool_init(rdev);
	if (r) {
		dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
		return r;
	}

	return 0;
}

int r300_resume(struct radeon_device *rdev)
{
	int r;

	/* Make sur GART are not working */
	if (rdev->flags & RADEON_IS_PCIE)
		rv370_pcie_gart_disable(rdev);
	if (rdev->flags & RADEON_IS_PCI)
		r100_pci_gart_disable(rdev);
	/* Resume clock before doing reset */
	r300_clock_startup(rdev);
	/* Reset gpu before posting otherwise ATOM will enter infinite loop */
	if (radeon_asic_reset(rdev)) {
		dev_warn(rdev->dev, "GPU reset failed ! (0xE40=0x%08X, 0x7C0=0x%08X)\n",
			RREG32(R_000E40_RBBM_STATUS),
			RREG32(R_0007C0_CP_STAT));
	}
	/* post */
	radeon_combios_asic_init(rdev->ddev);
	/* Resume clock after posting */
	r300_clock_startup(rdev);
	/* Initialize surface registers */
	radeon_surface_init(rdev);

	rdev->accel_working = true;
	r = r300_startup(rdev);
	if (r) {
		rdev->accel_working = false;
	}
	return r;
}

int r300_suspend(struct radeon_device *rdev)
{
	radeon_pm_suspend(rdev);
	r100_cp_disable(rdev);
	radeon_wb_disable(rdev);
	r100_irq_disable(rdev);
	if (rdev->flags & RADEON_IS_PCIE)
		rv370_pcie_gart_disable(rdev);
	if (rdev->flags & RADEON_IS_PCI)
		r100_pci_gart_disable(rdev);
	return 0;
}

void r300_fini(struct radeon_device *rdev)
{
	radeon_pm_fini(rdev);
	r100_cp_fini(rdev);
	radeon_wb_fini(rdev);
	radeon_ib_pool_fini(rdev);
	radeon_gem_fini(rdev);
	if (rdev->flags & RADEON_IS_PCIE)
		rv370_pcie_gart_fini(rdev);
	if (rdev->flags & RADEON_IS_PCI)
		r100_pci_gart_fini(rdev);
	radeon_agp_fini(rdev);
	radeon_irq_kms_fini(rdev);
	radeon_fence_driver_fini(rdev);
	radeon_bo_fini(rdev);
	radeon_atombios_fini(rdev);
	kfree(rdev->bios);
	rdev->bios = NULL;
}

int r300_init(struct radeon_device *rdev)
{
	int r;

	/* Disable VGA */
	r100_vga_render_disable(rdev);
	/* Initialize scratch registers */
	radeon_scratch_init(rdev);
	/* Initialize surface registers */
	radeon_surface_init(rdev);
	/* TODO: disable VGA need to use VGA request */
	/* restore some register to sane defaults */
	r100_restore_sanity(rdev);
	/* BIOS*/
	if (!radeon_get_bios(rdev)) {
		if (ASIC_IS_AVIVO(rdev))
			return -EINVAL;
	}
	if (rdev->is_atom_bios) {
		dev_err(rdev->dev, "Expecting combios for RS400/RS480 GPU\n");
		return -EINVAL;
	} else {
		r = radeon_combios_init(rdev);
		if (r)
			return r;
	}
	/* Reset gpu before posting otherwise ATOM will enter infinite loop */
	if (radeon_asic_reset(rdev)) {
		dev_warn(rdev->dev,
			"GPU reset failed ! (0xE40=0x%08X, 0x7C0=0x%08X)\n",
			RREG32(R_000E40_RBBM_STATUS),
			RREG32(R_0007C0_CP_STAT));
	}
	/* check if cards are posted or not */
	if (radeon_boot_test_post_card(rdev) == false)
		return -EINVAL;
	/* Set asic errata */
	r300_errata(rdev);
	/* Initialize clocks */
	radeon_get_clock_info(rdev->ddev);
	/* initialize AGP */
	if (rdev->flags & RADEON_IS_AGP) {
		r = radeon_agp_init(rdev);
		if (r) {
			radeon_agp_disable(rdev);
		}
	}
	/* initialize memory controller */
	r300_mc_init(rdev);
	/* Fence driver */
	r = radeon_fence_driver_init(rdev);
	if (r)
		return r;
	/* Memory manager */
	r = radeon_bo_init(rdev);
	if (r)
		return r;
	if (rdev->flags & RADEON_IS_PCIE) {
		r = rv370_pcie_gart_init(rdev);
		if (r)
			return r;
	}
	if (rdev->flags & RADEON_IS_PCI) {
		r = r100_pci_gart_init(rdev);
		if (r)
			return r;
	}
	r300_set_reg_safe(rdev);

	/* Initialize power management */
	radeon_pm_init(rdev);

	rdev->accel_working = true;
	r = r300_startup(rdev);
	if (r) {
		/* Something went wrong with the accel init, so stop accel */
		dev_err(rdev->dev, "Disabling GPU acceleration\n");
		r100_cp_fini(rdev);
		radeon_wb_fini(rdev);
		radeon_ib_pool_fini(rdev);
		radeon_irq_kms_fini(rdev);
		if (rdev->flags & RADEON_IS_PCIE)
			rv370_pcie_gart_fini(rdev);
		if (rdev->flags & RADEON_IS_PCI)
			r100_pci_gart_fini(rdev);
		radeon_agp_fini(rdev);
		rdev->accel_working = false;
	}
	return 0;
}