summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/radeon/r100.c
blob: 68e728e8be4d3cda06ca678a5c363fd95a94eb84 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
/*
 * 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 "drmP.h"
#include "drm.h"
#include "radeon_drm.h"
#include "radeon_microcode.h"
#include "radeon_reg.h"
#include "radeon.h"

/* This files gather functions specifics to:
 * r100,rv100,rs100,rv200,rs200,r200,rv250,rs300,rv280
 *
 * Some of these functions might be used by newer ASICs.
 */
void r100_hdp_reset(struct radeon_device *rdev);
void r100_gpu_init(struct radeon_device *rdev);
int r100_gui_wait_for_idle(struct radeon_device *rdev);
int r100_mc_wait_for_idle(struct radeon_device *rdev);
void r100_gpu_wait_for_vsync(struct radeon_device *rdev);
void r100_gpu_wait_for_vsync2(struct radeon_device *rdev);
int r100_debugfs_mc_info_init(struct radeon_device *rdev);


/*
 * PCI GART
 */
void r100_pci_gart_tlb_flush(struct radeon_device *rdev)
{
	/* TODO: can we do somethings here ? */
	/* It seems hw only cache one entry so we should discard this
	 * entry otherwise if first GPU GART read hit this entry it
	 * could end up in wrong address. */
}

int r100_pci_gart_enable(struct radeon_device *rdev)
{
	uint32_t tmp;
	int r;

	/* Initialize common gart structure */
	r = radeon_gart_init(rdev);
	if (r) {
		return r;
	}
	if (rdev->gart.table.ram.ptr == NULL) {
		rdev->gart.table_size = rdev->gart.num_gpu_pages * 4;
		r = radeon_gart_table_ram_alloc(rdev);
		if (r) {
			return r;
		}
	}
	/* discard memory request outside of configured range */
	tmp = RREG32(RADEON_AIC_CNTL) | RADEON_DIS_OUT_OF_PCI_GART_ACCESS;
	WREG32(RADEON_AIC_CNTL, tmp);
	/* set address range for PCI address translate */
	WREG32(RADEON_AIC_LO_ADDR, rdev->mc.gtt_location);
	tmp = rdev->mc.gtt_location + rdev->mc.gtt_size - 1;
	WREG32(RADEON_AIC_HI_ADDR, tmp);
	/* Enable bus mastering */
	tmp = RREG32(RADEON_BUS_CNTL) & ~RADEON_BUS_MASTER_DIS;
	WREG32(RADEON_BUS_CNTL, tmp);
	/* set PCI GART page-table base address */
	WREG32(RADEON_AIC_PT_BASE, rdev->gart.table_addr);
	tmp = RREG32(RADEON_AIC_CNTL) | RADEON_PCIGART_TRANSLATE_EN;
	WREG32(RADEON_AIC_CNTL, tmp);
	r100_pci_gart_tlb_flush(rdev);
	rdev->gart.ready = true;
	return 0;
}

void r100_pci_gart_disable(struct radeon_device *rdev)
{
	uint32_t tmp;

	/* discard memory request outside of configured range */
	tmp = RREG32(RADEON_AIC_CNTL) | RADEON_DIS_OUT_OF_PCI_GART_ACCESS;
	WREG32(RADEON_AIC_CNTL, tmp & ~RADEON_PCIGART_TRANSLATE_EN);
	WREG32(RADEON_AIC_LO_ADDR, 0);
	WREG32(RADEON_AIC_HI_ADDR, 0);
}

int r100_pci_gart_set_page(struct radeon_device *rdev, int i, uint64_t addr)
{
	if (i < 0 || i > rdev->gart.num_gpu_pages) {
		return -EINVAL;
	}
	rdev->gart.table.ram.ptr[i] = cpu_to_le32(lower_32_bits(addr));
	return 0;
}

int r100_gart_enable(struct radeon_device *rdev)
{
	if (rdev->flags & RADEON_IS_AGP) {
		r100_pci_gart_disable(rdev);
		return 0;
	}
	return r100_pci_gart_enable(rdev);
}


/*
 * MC
 */
void r100_mc_disable_clients(struct radeon_device *rdev)
{
	uint32_t ov0_scale_cntl, crtc_ext_cntl, crtc_gen_cntl, crtc2_gen_cntl;

	/* FIXME: is this function correct for rs100,rs200,rs300 ? */
	if (r100_gui_wait_for_idle(rdev)) {
		printk(KERN_WARNING "Failed to wait GUI idle while "
		       "programming pipes. Bad things might happen.\n");
	}

	/* stop display and memory access */
	ov0_scale_cntl = RREG32(RADEON_OV0_SCALE_CNTL);
	WREG32(RADEON_OV0_SCALE_CNTL, ov0_scale_cntl & ~RADEON_SCALER_ENABLE);
	crtc_ext_cntl = RREG32(RADEON_CRTC_EXT_CNTL);
	WREG32(RADEON_CRTC_EXT_CNTL, crtc_ext_cntl | RADEON_CRTC_DISPLAY_DIS);
	crtc_gen_cntl = RREG32(RADEON_CRTC_GEN_CNTL);

	r100_gpu_wait_for_vsync(rdev);

	WREG32(RADEON_CRTC_GEN_CNTL,
	       (crtc_gen_cntl & ~(RADEON_CRTC_CUR_EN | RADEON_CRTC_ICON_EN)) |
	       RADEON_CRTC_DISP_REQ_EN_B | RADEON_CRTC_EXT_DISP_EN);

	if (!(rdev->flags & RADEON_SINGLE_CRTC)) {
		crtc2_gen_cntl = RREG32(RADEON_CRTC2_GEN_CNTL);

		r100_gpu_wait_for_vsync2(rdev);
		WREG32(RADEON_CRTC2_GEN_CNTL,
		       (crtc2_gen_cntl &
		        ~(RADEON_CRTC2_CUR_EN | RADEON_CRTC2_ICON_EN)) |
		       RADEON_CRTC2_DISP_REQ_EN_B);
	}

	udelay(500);
}

void r100_mc_setup(struct radeon_device *rdev)
{
	uint32_t tmp;
	int r;

	r = r100_debugfs_mc_info_init(rdev);
	if (r) {
		DRM_ERROR("Failed to register debugfs file for R100 MC !\n");
	}
	/* Write VRAM size in case we are limiting it */
	WREG32(RADEON_CONFIG_MEMSIZE, rdev->mc.real_vram_size);
	/* Novell bug 204882 for RN50/M6/M7 with 8/16/32MB VRAM,
	 * if the aperture is 64MB but we have 32MB VRAM
	 * we report only 32MB VRAM but we have to set MC_FB_LOCATION
	 * to 64MB, otherwise the gpu accidentially dies */
	tmp = rdev->mc.vram_location + rdev->mc.mc_vram_size - 1;
	tmp = REG_SET(RADEON_MC_FB_TOP, tmp >> 16);
	tmp |= REG_SET(RADEON_MC_FB_START, rdev->mc.vram_location >> 16);
	WREG32(RADEON_MC_FB_LOCATION, tmp);

	/* Enable bus mastering */
	tmp = RREG32(RADEON_BUS_CNTL) & ~RADEON_BUS_MASTER_DIS;
	WREG32(RADEON_BUS_CNTL, tmp);

	if (rdev->flags & RADEON_IS_AGP) {
		tmp = rdev->mc.gtt_location + rdev->mc.gtt_size - 1;
		tmp = REG_SET(RADEON_MC_AGP_TOP, tmp >> 16);
		tmp |= REG_SET(RADEON_MC_AGP_START, rdev->mc.gtt_location >> 16);
		WREG32(RADEON_MC_AGP_LOCATION, tmp);
		WREG32(RADEON_AGP_BASE, rdev->mc.agp_base);
	} else {
		WREG32(RADEON_MC_AGP_LOCATION, 0x0FFFFFFF);
		WREG32(RADEON_AGP_BASE, 0);
	}

	tmp = RREG32(RADEON_HOST_PATH_CNTL) & RADEON_HDP_APER_CNTL;
	tmp |= (7 << 28);
	WREG32(RADEON_HOST_PATH_CNTL, tmp | RADEON_HDP_SOFT_RESET | RADEON_HDP_READ_BUFFER_INVALIDATE);
	(void)RREG32(RADEON_HOST_PATH_CNTL);
	WREG32(RADEON_HOST_PATH_CNTL, tmp);
	(void)RREG32(RADEON_HOST_PATH_CNTL);
}

int r100_mc_init(struct radeon_device *rdev)
{
	int r;

	if (r100_debugfs_rbbm_init(rdev)) {
		DRM_ERROR("Failed to register debugfs file for RBBM !\n");
	}

	r100_gpu_init(rdev);
	/* Disable gart which also disable out of gart access */
	r100_pci_gart_disable(rdev);

	/* Setup GPU memory space */
	rdev->mc.gtt_location = 0xFFFFFFFFUL;
	if (rdev->flags & RADEON_IS_AGP) {
		r = radeon_agp_init(rdev);
		if (r) {
			printk(KERN_WARNING "[drm] Disabling AGP\n");
			rdev->flags &= ~RADEON_IS_AGP;
			rdev->mc.gtt_size = radeon_gart_size * 1024 * 1024;
		} else {
			rdev->mc.gtt_location = rdev->mc.agp_base;
		}
	}
	r = radeon_mc_setup(rdev);
	if (r) {
		return r;
	}

	r100_mc_disable_clients(rdev);
	if (r100_mc_wait_for_idle(rdev)) {
		printk(KERN_WARNING "Failed to wait MC idle while "
		       "programming pipes. Bad things might happen.\n");
	}

	r100_mc_setup(rdev);
	return 0;
}

void r100_mc_fini(struct radeon_device *rdev)
{
	r100_pci_gart_disable(rdev);
	radeon_gart_table_ram_free(rdev);
	radeon_gart_fini(rdev);
}


/*
 * Interrupts
 */
int r100_irq_set(struct radeon_device *rdev)
{
	uint32_t tmp = 0;

	if (rdev->irq.sw_int) {
		tmp |= RADEON_SW_INT_ENABLE;
	}
	if (rdev->irq.crtc_vblank_int[0]) {
		tmp |= RADEON_CRTC_VBLANK_MASK;
	}
	if (rdev->irq.crtc_vblank_int[1]) {
		tmp |= RADEON_CRTC2_VBLANK_MASK;
	}
	WREG32(RADEON_GEN_INT_CNTL, tmp);
	return 0;
}

static inline uint32_t r100_irq_ack(struct radeon_device *rdev)
{
	uint32_t irqs = RREG32(RADEON_GEN_INT_STATUS);
	uint32_t irq_mask = RADEON_SW_INT_TEST | RADEON_CRTC_VBLANK_STAT |
		RADEON_CRTC2_VBLANK_STAT;

	if (irqs) {
		WREG32(RADEON_GEN_INT_STATUS, irqs);
	}
	return irqs & irq_mask;
}

int r100_irq_process(struct radeon_device *rdev)
{
	uint32_t status;

	status = r100_irq_ack(rdev);
	if (!status) {
		return IRQ_NONE;
	}
	while (status) {
		/* SW interrupt */
		if (status & RADEON_SW_INT_TEST) {
			radeon_fence_process(rdev);
		}
		/* Vertical blank interrupts */
		if (status & RADEON_CRTC_VBLANK_STAT) {
			drm_handle_vblank(rdev->ddev, 0);
		}
		if (status & RADEON_CRTC2_VBLANK_STAT) {
			drm_handle_vblank(rdev->ddev, 1);
		}
		status = r100_irq_ack(rdev);
	}
	return IRQ_HANDLED;
}

u32 r100_get_vblank_counter(struct radeon_device *rdev, int crtc)
{
	if (crtc == 0)
		return RREG32(RADEON_CRTC_CRNT_FRAME);
	else
		return RREG32(RADEON_CRTC2_CRNT_FRAME);
}


/*
 * Fence emission
 */
void r100_fence_ring_emit(struct radeon_device *rdev,
			  struct radeon_fence *fence)
{
	/* Who ever call radeon_fence_emit should call ring_lock and ask
	 * for enough space (today caller are ib schedule and buffer move) */
	/* Wait until IDLE & CLEAN */
	radeon_ring_write(rdev, PACKET0(0x1720, 0));
	radeon_ring_write(rdev, (1 << 16) | (1 << 17));
	/* Emit fence sequence & fire IRQ */
	radeon_ring_write(rdev, PACKET0(rdev->fence_drv.scratch_reg, 0));
	radeon_ring_write(rdev, fence->seq);
	radeon_ring_write(rdev, PACKET0(RADEON_GEN_INT_STATUS, 0));
	radeon_ring_write(rdev, RADEON_SW_INT_FIRE);
}


/*
 * Writeback
 */
int r100_wb_init(struct radeon_device *rdev)
{
	int r;

	if (rdev->wb.wb_obj == NULL) {
		r = radeon_object_create(rdev, NULL, 4096,
					 true,
					 RADEON_GEM_DOMAIN_GTT,
					 false, &rdev->wb.wb_obj);
		if (r) {
			DRM_ERROR("radeon: failed to create WB buffer (%d).\n", r);
			return r;
		}
		r = radeon_object_pin(rdev->wb.wb_obj,
				      RADEON_GEM_DOMAIN_GTT,
				      &rdev->wb.gpu_addr);
		if (r) {
			DRM_ERROR("radeon: failed to pin WB buffer (%d).\n", r);
			return r;
		}
		r = radeon_object_kmap(rdev->wb.wb_obj, (void **)&rdev->wb.wb);
		if (r) {
			DRM_ERROR("radeon: failed to map WB buffer (%d).\n", r);
			return r;
		}
	}
	WREG32(0x774, rdev->wb.gpu_addr);
	WREG32(0x70C, rdev->wb.gpu_addr + 1024);
	WREG32(0x770, 0xff);
	return 0;
}

void r100_wb_fini(struct radeon_device *rdev)
{
	if (rdev->wb.wb_obj) {
		radeon_object_kunmap(rdev->wb.wb_obj);
		radeon_object_unpin(rdev->wb.wb_obj);
		radeon_object_unref(&rdev->wb.wb_obj);
		rdev->wb.wb = NULL;
		rdev->wb.wb_obj = NULL;
	}
}

int r100_copy_blit(struct radeon_device *rdev,
		   uint64_t src_offset,
		   uint64_t dst_offset,
		   unsigned num_pages,
		   struct radeon_fence *fence)
{
	uint32_t cur_pages;
	uint32_t stride_bytes = PAGE_SIZE;
	uint32_t pitch;
	uint32_t stride_pixels;
	unsigned ndw;
	int num_loops;
	int r = 0;

	/* radeon limited to 16k stride */
	stride_bytes &= 0x3fff;
	/* radeon pitch is /64 */
	pitch = stride_bytes / 64;
	stride_pixels = stride_bytes / 4;
	num_loops = DIV_ROUND_UP(num_pages, 8191);

	/* Ask for enough room for blit + flush + fence */
	ndw = 64 + (10 * num_loops);
	r = radeon_ring_lock(rdev, ndw);
	if (r) {
		DRM_ERROR("radeon: moving bo (%d) asking for %u dw.\n", r, ndw);
		return -EINVAL;
	}
	while (num_pages > 0) {
		cur_pages = num_pages;
		if (cur_pages > 8191) {
			cur_pages = 8191;
		}
		num_pages -= cur_pages;

		/* pages are in Y direction - height
		   page width in X direction - width */
		radeon_ring_write(rdev, PACKET3(PACKET3_BITBLT_MULTI, 8));
		radeon_ring_write(rdev,
				  RADEON_GMC_SRC_PITCH_OFFSET_CNTL |
				  RADEON_GMC_DST_PITCH_OFFSET_CNTL |
				  RADEON_GMC_SRC_CLIPPING |
				  RADEON_GMC_DST_CLIPPING |
				  RADEON_GMC_BRUSH_NONE |
				  (RADEON_COLOR_FORMAT_ARGB8888 << 8) |
				  RADEON_GMC_SRC_DATATYPE_COLOR |
				  RADEON_ROP3_S |
				  RADEON_DP_SRC_SOURCE_MEMORY |
				  RADEON_GMC_CLR_CMP_CNTL_DIS |
				  RADEON_GMC_WR_MSK_DIS);
		radeon_ring_write(rdev, (pitch << 22) | (src_offset >> 10));
		radeon_ring_write(rdev, (pitch << 22) | (dst_offset >> 10));
		radeon_ring_write(rdev, (0x1fff) | (0x1fff << 16));
		radeon_ring_write(rdev, 0);
		radeon_ring_write(rdev, (0x1fff) | (0x1fff << 16));
		radeon_ring_write(rdev, num_pages);
		radeon_ring_write(rdev, num_pages);
		radeon_ring_write(rdev, cur_pages | (stride_pixels << 16));
	}
	radeon_ring_write(rdev, PACKET0(RADEON_DSTCACHE_CTLSTAT, 0));
	radeon_ring_write(rdev, RADEON_RB2D_DC_FLUSH_ALL);
	radeon_ring_write(rdev, PACKET0(RADEON_WAIT_UNTIL, 0));
	radeon_ring_write(rdev,
			  RADEON_WAIT_2D_IDLECLEAN |
			  RADEON_WAIT_HOST_IDLECLEAN |
			  RADEON_WAIT_DMA_GUI_IDLE);
	if (fence) {
		r = radeon_fence_emit(rdev, fence);
	}
	radeon_ring_unlock_commit(rdev);
	return r;
}


/*
 * CP
 */
void r100_ring_start(struct radeon_device *rdev)
{
	int r;

	r = radeon_ring_lock(rdev, 2);
	if (r) {
		return;
	}
	radeon_ring_write(rdev, PACKET0(RADEON_ISYNC_CNTL, 0));
	radeon_ring_write(rdev,
			  RADEON_ISYNC_ANY2D_IDLE3D |
			  RADEON_ISYNC_ANY3D_IDLE2D |
			  RADEON_ISYNC_WAIT_IDLEGUI |
			  RADEON_ISYNC_CPSCRATCH_IDLEGUI);
	radeon_ring_unlock_commit(rdev);
}

static void r100_cp_load_microcode(struct radeon_device *rdev)
{
	int i;

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

	WREG32(RADEON_CP_ME_RAM_ADDR, 0);
	if ((rdev->family == CHIP_R100) || (rdev->family == CHIP_RV100) ||
	    (rdev->family == CHIP_RV200) || (rdev->family == CHIP_RS100) ||
	    (rdev->family == CHIP_RS200)) {
		DRM_INFO("Loading R100 Microcode\n");
		for (i = 0; i < 256; i++) {
			WREG32(RADEON_CP_ME_RAM_DATAH, R100_cp_microcode[i][1]);
			WREG32(RADEON_CP_ME_RAM_DATAL, R100_cp_microcode[i][0]);
		}
	} else if ((rdev->family == CHIP_R200) ||
		   (rdev->family == CHIP_RV250) ||
		   (rdev->family == CHIP_RV280) ||
		   (rdev->family == CHIP_RS300)) {
		DRM_INFO("Loading R200 Microcode\n");
		for (i = 0; i < 256; i++) {
			WREG32(RADEON_CP_ME_RAM_DATAH, R200_cp_microcode[i][1]);
			WREG32(RADEON_CP_ME_RAM_DATAL, R200_cp_microcode[i][0]);
		}
	} else if ((rdev->family == CHIP_R300) ||
		   (rdev->family == CHIP_R350) ||
		   (rdev->family == CHIP_RV350) ||
		   (rdev->family == CHIP_RV380) ||
		   (rdev->family == CHIP_RS400) ||
		   (rdev->family == CHIP_RS480)) {
		DRM_INFO("Loading R300 Microcode\n");
		for (i = 0; i < 256; i++) {
			WREG32(RADEON_CP_ME_RAM_DATAH, R300_cp_microcode[i][1]);
			WREG32(RADEON_CP_ME_RAM_DATAL, R300_cp_microcode[i][0]);
		}
	} else if ((rdev->family == CHIP_R420) ||
		   (rdev->family == CHIP_R423) ||
		   (rdev->family == CHIP_RV410)) {
		DRM_INFO("Loading R400 Microcode\n");
		for (i = 0; i < 256; i++) {
			WREG32(RADEON_CP_ME_RAM_DATAH, R420_cp_microcode[i][1]);
			WREG32(RADEON_CP_ME_RAM_DATAL, R420_cp_microcode[i][0]);
		}
	} else if ((rdev->family == CHIP_RS690) ||
		   (rdev->family == CHIP_RS740)) {
		DRM_INFO("Loading RS690/RS740 Microcode\n");
		for (i = 0; i < 256; i++) {
			WREG32(RADEON_CP_ME_RAM_DATAH, RS690_cp_microcode[i][1]);
			WREG32(RADEON_CP_ME_RAM_DATAL, RS690_cp_microcode[i][0]);
		}
	} else if (rdev->family == CHIP_RS600) {
		DRM_INFO("Loading RS600 Microcode\n");
		for (i = 0; i < 256; i++) {
			WREG32(RADEON_CP_ME_RAM_DATAH, RS600_cp_microcode[i][1]);
			WREG32(RADEON_CP_ME_RAM_DATAL, RS600_cp_microcode[i][0]);
		}
	} else if ((rdev->family == CHIP_RV515) ||
		   (rdev->family == CHIP_R520) ||
		   (rdev->family == CHIP_RV530) ||
		   (rdev->family == CHIP_R580) ||
		   (rdev->family == CHIP_RV560) ||
		   (rdev->family == CHIP_RV570)) {
		DRM_INFO("Loading R500 Microcode\n");
		for (i = 0; i < 256; i++) {
			WREG32(RADEON_CP_ME_RAM_DATAH, R520_cp_microcode[i][1]);
			WREG32(RADEON_CP_ME_RAM_DATAL, R520_cp_microcode[i][0]);
		}
	}
}

int r100_cp_init(struct radeon_device *rdev, unsigned ring_size)
{
	unsigned rb_bufsz;
	unsigned rb_blksz;
	unsigned max_fetch;
	unsigned pre_write_timer;
	unsigned pre_write_limit;
	unsigned indirect2_start;
	unsigned indirect1_start;
	uint32_t tmp;
	int r;

	if (r100_debugfs_cp_init(rdev)) {
		DRM_ERROR("Failed to register debugfs file for CP !\n");
	}
	/* Reset CP */
	tmp = RREG32(RADEON_CP_CSQ_STAT);
	if ((tmp & (1 << 31))) {
		DRM_INFO("radeon: cp busy (0x%08X) resetting\n", tmp);
		WREG32(RADEON_CP_CSQ_MODE, 0);
		WREG32(RADEON_CP_CSQ_CNTL, 0);
		WREG32(RADEON_RBBM_SOFT_RESET, RADEON_SOFT_RESET_CP);
		tmp = RREG32(RADEON_RBBM_SOFT_RESET);
		mdelay(2);
		WREG32(RADEON_RBBM_SOFT_RESET, 0);
		tmp = RREG32(RADEON_RBBM_SOFT_RESET);
		mdelay(2);
		tmp = RREG32(RADEON_CP_CSQ_STAT);
		if ((tmp & (1 << 31))) {
			DRM_INFO("radeon: cp reset failed (0x%08X)\n", tmp);
		}
	} else {
		DRM_INFO("radeon: cp idle (0x%08X)\n", tmp);
	}
	/* Align ring size */
	rb_bufsz = drm_order(ring_size / 8);
	ring_size = (1 << (rb_bufsz + 1)) * 4;
	r100_cp_load_microcode(rdev);
	r = radeon_ring_init(rdev, ring_size);
	if (r) {
		return r;
	}
	/* Each time the cp read 1024 bytes (16 dword/quadword) update
	 * the rptr copy in system ram */
	rb_blksz = 9;
	/* cp will read 128bytes at a time (4 dwords) */
	max_fetch = 1;
	rdev->cp.align_mask = 16 - 1;
	/* Write to CP_RB_WPTR will be delayed for pre_write_timer clocks */
	pre_write_timer = 64;
	/* Force CP_RB_WPTR write if written more than one time before the
	 * delay expire
	 */
	pre_write_limit = 0;
	/* Setup the cp cache like this (cache size is 96 dwords) :
	 *	RING		0  to 15
	 *	INDIRECT1	16 to 79
	 *	INDIRECT2	80 to 95
	 * So ring cache size is 16dwords (> (2 * max_fetch = 2 * 4dwords))
	 *    indirect1 cache size is 64dwords (> (2 * max_fetch = 2 * 4dwords))
	 *    indirect2 cache size is 16dwords (> (2 * max_fetch = 2 * 4dwords))
	 * Idea being that most of the gpu cmd will be through indirect1 buffer
	 * so it gets the bigger cache.
	 */
	indirect2_start = 80;
	indirect1_start = 16;
	/* cp setup */
	WREG32(0x718, pre_write_timer | (pre_write_limit << 28));
	WREG32(RADEON_CP_RB_CNTL,
#ifdef __BIG_ENDIAN
	       RADEON_BUF_SWAP_32BIT |
#endif
	       REG_SET(RADEON_RB_BUFSZ, rb_bufsz) |
	       REG_SET(RADEON_RB_BLKSZ, rb_blksz) |
	       REG_SET(RADEON_MAX_FETCH, max_fetch) |
	       RADEON_RB_NO_UPDATE);
	/* Set ring address */
	DRM_INFO("radeon: ring at 0x%016lX\n", (unsigned long)rdev->cp.gpu_addr);
	WREG32(RADEON_CP_RB_BASE, rdev->cp.gpu_addr);
	/* Force read & write ptr to 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);
	udelay(10);
	rdev->cp.rptr = RREG32(RADEON_CP_RB_RPTR);
	rdev->cp.wptr = RREG32(RADEON_CP_RB_WPTR);
	/* Set cp mode to bus mastering & enable cp*/
	WREG32(RADEON_CP_CSQ_MODE,
	       REG_SET(RADEON_INDIRECT2_START, indirect2_start) |
	       REG_SET(RADEON_INDIRECT1_START, indirect1_start));
	WREG32(0x718, 0);
	WREG32(0x744, 0x00004D4D);
	WREG32(RADEON_CP_CSQ_CNTL, RADEON_CSQ_PRIBM_INDBM);
	radeon_ring_start(rdev);
	r = radeon_ring_test(rdev);
	if (r) {
		DRM_ERROR("radeon: cp isn't working (%d).\n", r);
		return r;
	}
	rdev->cp.ready = true;
	return 0;
}

void r100_cp_fini(struct radeon_device *rdev)
{
	/* Disable ring */
	rdev->cp.ready = false;
	WREG32(RADEON_CP_CSQ_CNTL, 0);
	radeon_ring_fini(rdev);
	DRM_INFO("radeon: cp finalized\n");
}

void r100_cp_disable(struct radeon_device *rdev)
{
	/* Disable ring */
	rdev->cp.ready = false;
	WREG32(RADEON_CP_CSQ_MODE, 0);
	WREG32(RADEON_CP_CSQ_CNTL, 0);
	if (r100_gui_wait_for_idle(rdev)) {
		printk(KERN_WARNING "Failed to wait GUI idle while "
		       "programming pipes. Bad things might happen.\n");
	}
}

int r100_cp_reset(struct radeon_device *rdev)
{
	uint32_t tmp;
	bool reinit_cp;
	int i;

	reinit_cp = rdev->cp.ready;
	rdev->cp.ready = false;
	WREG32(RADEON_CP_CSQ_MODE, 0);
	WREG32(RADEON_CP_CSQ_CNTL, 0);
	WREG32(RADEON_RBBM_SOFT_RESET, RADEON_SOFT_RESET_CP);
	(void)RREG32(RADEON_RBBM_SOFT_RESET);
	udelay(200);
	WREG32(RADEON_RBBM_SOFT_RESET, 0);
	/* Wait to prevent race in RBBM_STATUS */
	mdelay(1);
	for (i = 0; i < rdev->usec_timeout; i++) {
		tmp = RREG32(RADEON_RBBM_STATUS);
		if (!(tmp & (1 << 16))) {
			DRM_INFO("CP reset succeed (RBBM_STATUS=0x%08X)\n",
				 tmp);
			if (reinit_cp) {
				return r100_cp_init(rdev, rdev->cp.ring_size);
			}
			return 0;
		}
		DRM_UDELAY(1);
	}
	tmp = RREG32(RADEON_RBBM_STATUS);
	DRM_ERROR("Failed to reset CP (RBBM_STATUS=0x%08X)!\n", tmp);
	return -1;
}


/*
 * CS functions
 */
int r100_cs_parse_packet0(struct radeon_cs_parser *p,
			  struct radeon_cs_packet *pkt,
			  const unsigned *auth, unsigned n,
			  radeon_packet0_check_t check)
{
	unsigned reg;
	unsigned i, j, m;
	unsigned idx;
	int r;

	idx = pkt->idx + 1;
	reg = pkt->reg;
	/* Check that register fall into register range
	 * determined by the number of entry (n) in the
	 * safe register bitmap.
	 */
	if (pkt->one_reg_wr) {
		if ((reg >> 7) > n) {
			return -EINVAL;
		}
	} else {
		if (((reg + (pkt->count << 2)) >> 7) > n) {
			return -EINVAL;
		}
	}
	for (i = 0; i <= pkt->count; i++, idx++) {
		j = (reg >> 7);
		m = 1 << ((reg >> 2) & 31);
		if (auth[j] & m) {
			r = check(p, pkt, idx, reg);
			if (r) {
				return r;
			}
		}
		if (pkt->one_reg_wr) {
			if (!(auth[j] & m)) {
				break;
			}
		} else {
			reg += 4;
		}
	}
	return 0;
}

void r100_cs_dump_packet(struct radeon_cs_parser *p,
			 struct radeon_cs_packet *pkt)
{
	struct radeon_cs_chunk *ib_chunk;
	volatile uint32_t *ib;
	unsigned i;
	unsigned idx;

	ib = p->ib->ptr;
	ib_chunk = &p->chunks[p->chunk_ib_idx];
	idx = pkt->idx;
	for (i = 0; i <= (pkt->count + 1); i++, idx++) {
		DRM_INFO("ib[%d]=0x%08X\n", idx, ib[idx]);
	}
}

/**
 * r100_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 r100_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 = ib_chunk->kdata[idx];
	pkt->idx = idx;
	pkt->type = CP_PACKET_GET_TYPE(header);
	pkt->count = CP_PACKET_GET_COUNT(header);
	switch (pkt->type) {
	case PACKET_TYPE0:
		pkt->reg = CP_PACKET0_GET_REG(header);
		pkt->one_reg_wr = CP_PACKET0_GET_ONE_REG_WR(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;
}

/**
 * r100_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
 * PACKET0 - WAIT_UNTIL +_value
 * RELOC (P3) - crtc_id in reloc.
 *
 * This function parses this and relocates the VLINE START END
 * and WAIT UNTIL packets to the correct crtc.
 * It also detects a switched off crtc and nulls out the
 * wait in that case.
 */
int r100_cs_packet_parse_vline(struct radeon_cs_parser *p)
{
	struct radeon_cs_chunk *ib_chunk;
	struct drm_mode_object *obj;
	struct drm_crtc *crtc;
	struct radeon_crtc *radeon_crtc;
	struct radeon_cs_packet p3reloc, waitreloc;
	int crtc_id;
	int r;
	uint32_t header, h_idx, reg;

	ib_chunk = &p->chunks[p->chunk_ib_idx];

	/* parse the wait until */
	r = r100_cs_packet_parse(p, &waitreloc, p->idx);
	if (r)
		return r;

	/* check its a wait until and only 1 count */
	if (waitreloc.reg != RADEON_WAIT_UNTIL ||
	    waitreloc.count != 0) {
		DRM_ERROR("vline wait had illegal wait until segment\n");
		r = -EINVAL;
		return r;
	}

	if (ib_chunk->kdata[waitreloc.idx + 1] != RADEON_WAIT_CRTC_VLINE) {
		DRM_ERROR("vline wait had illegal wait until\n");
		r = -EINVAL;
		return r;
	}

	/* jump over the NOP */
	r = r100_cs_packet_parse(p, &p3reloc, p->idx);
	if (r)
		return r;

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

	header = ib_chunk->kdata[h_idx];
	crtc_id = ib_chunk->kdata[h_idx + 5];
	reg = ib_chunk->kdata[h_idx] >> 2;
	mutex_lock(&p->rdev->ddev->mode_config.mutex);
	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);
		r = -EINVAL;
		goto out;
	}
	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 until */
		ib_chunk->kdata[h_idx + 2] = PACKET2(0);
		ib_chunk->kdata[h_idx + 3] = PACKET2(0);
	} else if (crtc_id == 1) {
		switch (reg) {
		case AVIVO_D1MODE_VLINE_START_END:
			header &= R300_CP_PACKET0_REG_MASK;
			header |= AVIVO_D2MODE_VLINE_START_END >> 2;
			break;
		case RADEON_CRTC_GUI_TRIG_VLINE:
			header &= R300_CP_PACKET0_REG_MASK;
			header |= RADEON_CRTC2_GUI_TRIG_VLINE >> 2;
			break;
		default:
			DRM_ERROR("unknown crtc reloc\n");
			r = -EINVAL;
			goto out;
		}
		ib_chunk->kdata[h_idx] = header;
		ib_chunk->kdata[h_idx + 3] |= RADEON_ENG_DISPLAY_SELECT_CRTC1;
	}
out:
	mutex_unlock(&p->rdev->ddev->mode_config.mutex);
	return r;
}

/**
 * r100_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.
 **/
int r100_cs_packet_next_reloc(struct radeon_cs_parser *p,
			      struct radeon_cs_reloc **cs_reloc)
{
	struct radeon_cs_chunk *ib_chunk;
	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;
	ib_chunk = &p->chunks[p->chunk_ib_idx];
	relocs_chunk = &p->chunks[p->chunk_relocs_idx];
	r = r100_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);
		r100_cs_dump_packet(p, &p3reloc);
		return -EINVAL;
	}
	idx = ib_chunk->kdata[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);
		r100_cs_dump_packet(p, &p3reloc);
		return -EINVAL;
	}
	/* FIXME: we assume reloc size is 4 dwords */
	*cs_reloc = p->relocs_ptr[(idx / 4)];
	return 0;
}

static int r100_packet0_check(struct radeon_cs_parser *p,
			      struct radeon_cs_packet *pkt)
{
	struct radeon_cs_chunk *ib_chunk;
	struct radeon_cs_reloc *reloc;
	volatile uint32_t *ib;
	uint32_t tmp;
	unsigned reg;
	unsigned i;
	unsigned idx;
	bool onereg;
	int r;
	u32 tile_flags = 0;

	ib = p->ib->ptr;
	ib_chunk = &p->chunks[p->chunk_ib_idx];
	idx = pkt->idx + 1;
	reg = pkt->reg;
	onereg = false;
	if (CP_PACKET0_GET_ONE_REG_WR(ib_chunk->kdata[pkt->idx])) {
		onereg = true;
	}
	for (i = 0; i <= pkt->count; i++, idx++, reg += 4) {
		switch (reg) {
		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);
				r100_cs_dump_packet(p, pkt);
				return r;
			}
			break;
		/* FIXME: only allow PACKET3 blit? easier to check for out of
		 * range access */
		case RADEON_DST_PITCH_OFFSET:
		case RADEON_SRC_PITCH_OFFSET:
			r = r100_cs_packet_next_reloc(p, &reloc);
			if (r) {
				DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
					  idx, reg);
				r100_cs_dump_packet(p, pkt);
				return r;
			}
			tmp = ib_chunk->kdata[idx] & 0x003fffff;
			tmp += (((u32)reloc->lobj.gpu_offset) >> 10);

			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
				tile_flags |= RADEON_DST_TILE_MACRO;
			if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO) {
				if (reg == RADEON_SRC_PITCH_OFFSET) {
					DRM_ERROR("Cannot src blit from microtiled surface\n");
					r100_cs_dump_packet(p, pkt);
					return -EINVAL;
				}
				tile_flags |= RADEON_DST_TILE_MICRO;
			}

			tmp |= tile_flags;
			ib[idx] = (ib_chunk->kdata[idx] & 0x3fc00000) | tmp;
			break;
		case RADEON_RB3D_DEPTHOFFSET:
		case RADEON_RB3D_COLOROFFSET:
		case R300_RB3D_COLOROFFSET0:
		case R300_ZB_DEPTHOFFSET:
		case R200_PP_TXOFFSET_0:
		case R200_PP_TXOFFSET_1:
		case R200_PP_TXOFFSET_2:
		case R200_PP_TXOFFSET_3:
		case R200_PP_TXOFFSET_4:
		case R200_PP_TXOFFSET_5:
		case RADEON_PP_TXOFFSET_0:
		case RADEON_PP_TXOFFSET_1:
		case RADEON_PP_TXOFFSET_2:
		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:
			/* rn50 has no 3D engine so fail on any 3d setup */
			if (ASIC_IS_RN50(p->rdev)) {
				DRM_ERROR("attempt to use RN50 3D engine failed\n");
				return -EINVAL;
			}
			r = r100_cs_packet_next_reloc(p, &reloc);
			if (r) {
				DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
					  idx, reg);
				r100_cs_dump_packet(p, pkt);
				return r;
			}
			ib[idx] = ib_chunk->kdata[idx] + ((u32)reloc->lobj.gpu_offset);
			break;
		case R300_RB3D_COLORPITCH0:
		case RADEON_RB3D_COLORPITCH:
			r = r100_cs_packet_next_reloc(p, &reloc);
			if (r) {
				DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
					  idx, reg);
				r100_cs_dump_packet(p, pkt);
				return r;
			}

			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
				tile_flags |= RADEON_COLOR_TILE_ENABLE;
			if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
				tile_flags |= RADEON_COLOR_MICROTILE_ENABLE;

			tmp = ib_chunk->kdata[idx] & ~(0x7 << 16);
			tmp |= tile_flags;
			ib[idx] = tmp;
			break;
		case RADEON_RB3D_ZPASS_ADDR:
			r = r100_cs_packet_next_reloc(p, &reloc);
			if (r) {
				DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
					  idx, reg);
				r100_cs_dump_packet(p, pkt);
				return r;
			}
			ib[idx] = ib_chunk->kdata[idx] + ((u32)reloc->lobj.gpu_offset);
			break;
		default:
			/* FIXME: we don't want to allow anyothers packet */
			break;
		}
		if (onereg) {
			/* FIXME: forbid onereg write to register on relocate */
			break;
		}
	}
	return 0;
}

int r100_cs_track_check_pkt3_indx_buffer(struct radeon_cs_parser *p,
					 struct radeon_cs_packet *pkt,
					 struct radeon_object *robj)
{
	struct radeon_cs_chunk *ib_chunk;
	unsigned idx;

	ib_chunk = &p->chunks[p->chunk_ib_idx];
	idx = pkt->idx + 1;
	if ((ib_chunk->kdata[idx+2] + 1) > radeon_object_size(robj)) {
		DRM_ERROR("[drm] Buffer too small for PACKET3 INDX_BUFFER "
			  "(need %u have %lu) !\n",
			  ib_chunk->kdata[idx+2] + 1,
			  radeon_object_size(robj));
		return -EINVAL;
	}
	return 0;
}

static int r100_packet3_check(struct radeon_cs_parser *p,
			      struct radeon_cs_packet *pkt)
{
	struct radeon_cs_chunk *ib_chunk;
	struct radeon_cs_reloc *reloc;
	unsigned idx;
	unsigned i, c;
	volatile uint32_t *ib;
	int r;

	ib = p->ib->ptr;
	ib_chunk = &p->chunks[p->chunk_ib_idx];
	idx = pkt->idx + 1;
	switch (pkt->opcode) {
	case PACKET3_3D_LOAD_VBPNTR:
		c = ib_chunk->kdata[idx++];
		for (i = 0; i < (c - 1); i += 2, idx += 3) {
			r = r100_cs_packet_next_reloc(p, &reloc);
			if (r) {
				DRM_ERROR("No reloc for packet3 %d\n",
					  pkt->opcode);
				r100_cs_dump_packet(p, pkt);
				return r;
			}
			ib[idx+1] = ib_chunk->kdata[idx+1] + ((u32)reloc->lobj.gpu_offset);
			r = r100_cs_packet_next_reloc(p, &reloc);
			if (r) {
				DRM_ERROR("No reloc for packet3 %d\n",
					  pkt->opcode);
				r100_cs_dump_packet(p, pkt);
				return r;
			}
			ib[idx+2] = ib_chunk->kdata[idx+2] + ((u32)reloc->lobj.gpu_offset);
		}
		if (c & 1) {
			r = r100_cs_packet_next_reloc(p, &reloc);
			if (r) {
				DRM_ERROR("No reloc for packet3 %d\n",
					  pkt->opcode);
				r100_cs_dump_packet(p, pkt);
				return r;
			}
			ib[idx+1] = ib_chunk->kdata[idx+1] + ((u32)reloc->lobj.gpu_offset);
		}
		break;
	case PACKET3_INDX_BUFFER:
		r = r100_cs_packet_next_reloc(p, &reloc);
		if (r) {
			DRM_ERROR("No reloc for packet3 %d\n", pkt->opcode);
			r100_cs_dump_packet(p, pkt);
			return r;
		}
		ib[idx+1] = ib_chunk->kdata[idx+1] + ((u32)reloc->lobj.gpu_offset);
		r = r100_cs_track_check_pkt3_indx_buffer(p, pkt, reloc->robj);
		if (r) {
			return r;
		}
		break;
	case 0x23:
		/* FIXME: cleanup */
		/* 3D_RNDR_GEN_INDX_PRIM on r100/r200 */
		r = r100_cs_packet_next_reloc(p, &reloc);
		if (r) {
			DRM_ERROR("No reloc for packet3 %d\n", pkt->opcode);
			r100_cs_dump_packet(p, pkt);
			return r;
		}
		ib[idx] = ib_chunk->kdata[idx] + ((u32)reloc->lobj.gpu_offset);
		break;
	case PACKET3_3D_DRAW_IMMD:
		/* triggers drawing using in-packet vertex data */
	case PACKET3_3D_DRAW_IMMD_2:
		/* triggers drawing using in-packet vertex data */
	case PACKET3_3D_DRAW_VBUF_2:
		/* triggers drawing of vertex buffers setup elsewhere */
	case PACKET3_3D_DRAW_INDX_2:
		/* triggers drawing using indices to vertex buffer */
	case PACKET3_3D_DRAW_VBUF:
		/* triggers drawing of vertex buffers setup elsewhere */
	case PACKET3_3D_DRAW_INDX:
		/* triggers drawing using indices to vertex buffer */
	case PACKET3_NOP:
		break;
	default:
		DRM_ERROR("Packet3 opcode %x not supported\n", pkt->opcode);
		return -EINVAL;
	}
	return 0;
}

int r100_cs_parse(struct radeon_cs_parser *p)
{
	struct radeon_cs_packet pkt;
	int r;

	do {
		r = r100_cs_packet_parse(p, &pkt, p->idx);
		if (r) {
			return r;
		}
		p->idx += pkt.count + 2;
		switch (pkt.type) {
			case PACKET_TYPE0:
				r = r100_packet0_check(p, &pkt);
				break;
			case PACKET_TYPE2:
				break;
			case PACKET_TYPE3:
				r = r100_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->chunks[p->chunk_ib_idx].length_dw);
	return 0;
}


/*
 * Global GPU functions
 */
void r100_errata(struct radeon_device *rdev)
{
	rdev->pll_errata = 0;

	if (rdev->family == CHIP_RV200 || rdev->family == CHIP_RS200) {
		rdev->pll_errata |= CHIP_ERRATA_PLL_DUMMYREADS;
	}

	if (rdev->family == CHIP_RV100 ||
	    rdev->family == CHIP_RS100 ||
	    rdev->family == CHIP_RS200) {
		rdev->pll_errata |= CHIP_ERRATA_PLL_DELAY;
	}
}

/* Wait for vertical sync on primary CRTC */
void r100_gpu_wait_for_vsync(struct radeon_device *rdev)
{
	uint32_t crtc_gen_cntl, tmp;
	int i;

	crtc_gen_cntl = RREG32(RADEON_CRTC_GEN_CNTL);
	if ((crtc_gen_cntl & RADEON_CRTC_DISP_REQ_EN_B) ||
	    !(crtc_gen_cntl & RADEON_CRTC_EN)) {
		return;
	}
	/* Clear the CRTC_VBLANK_SAVE bit */
	WREG32(RADEON_CRTC_STATUS, RADEON_CRTC_VBLANK_SAVE_CLEAR);
	for (i = 0; i < rdev->usec_timeout; i++) {
		tmp = RREG32(RADEON_CRTC_STATUS);
		if (tmp & RADEON_CRTC_VBLANK_SAVE) {
			return;
		}
		DRM_UDELAY(1);
	}
}

/* Wait for vertical sync on secondary CRTC */
void r100_gpu_wait_for_vsync2(struct radeon_device *rdev)
{
	uint32_t crtc2_gen_cntl, tmp;
	int i;

	crtc2_gen_cntl = RREG32(RADEON_CRTC2_GEN_CNTL);
	if ((crtc2_gen_cntl & RADEON_CRTC2_DISP_REQ_EN_B) ||
	    !(crtc2_gen_cntl & RADEON_CRTC2_EN))
		return;

	/* Clear the CRTC_VBLANK_SAVE bit */
	WREG32(RADEON_CRTC2_STATUS, RADEON_CRTC2_VBLANK_SAVE_CLEAR);
	for (i = 0; i < rdev->usec_timeout; i++) {
		tmp = RREG32(RADEON_CRTC2_STATUS);
		if (tmp & RADEON_CRTC2_VBLANK_SAVE) {
			return;
		}
		DRM_UDELAY(1);
	}
}

int r100_rbbm_fifo_wait_for_entry(struct radeon_device *rdev, unsigned n)
{
	unsigned i;
	uint32_t tmp;

	for (i = 0; i < rdev->usec_timeout; i++) {
		tmp = RREG32(RADEON_RBBM_STATUS) & RADEON_RBBM_FIFOCNT_MASK;
		if (tmp >= n) {
			return 0;
		}
		DRM_UDELAY(1);
	}
	return -1;
}

int r100_gui_wait_for_idle(struct radeon_device *rdev)
{
	unsigned i;
	uint32_t tmp;

	if (r100_rbbm_fifo_wait_for_entry(rdev, 64)) {
		printk(KERN_WARNING "radeon: wait for empty RBBM fifo failed !"
		       " Bad things might happen.\n");
	}
	for (i = 0; i < rdev->usec_timeout; i++) {
		tmp = RREG32(RADEON_RBBM_STATUS);
		if (!(tmp & (1 << 31))) {
			return 0;
		}
		DRM_UDELAY(1);
	}
	return -1;
}

int r100_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(0x0150);
		if (tmp & (1 << 2)) {
			return 0;
		}
		DRM_UDELAY(1);
	}
	return -1;
}

void r100_gpu_init(struct radeon_device *rdev)
{
	/* TODO: anythings to do here ? pipes ? */
	r100_hdp_reset(rdev);
}

void r100_hdp_reset(struct radeon_device *rdev)
{
	uint32_t tmp;

	tmp = RREG32(RADEON_HOST_PATH_CNTL) & RADEON_HDP_APER_CNTL;
	tmp |= (7 << 28);
	WREG32(RADEON_HOST_PATH_CNTL, tmp | RADEON_HDP_SOFT_RESET | RADEON_HDP_READ_BUFFER_INVALIDATE);
	(void)RREG32(RADEON_HOST_PATH_CNTL);
	udelay(200);
	WREG32(RADEON_RBBM_SOFT_RESET, 0);
	WREG32(RADEON_HOST_PATH_CNTL, tmp);
	(void)RREG32(RADEON_HOST_PATH_CNTL);
}

int r100_rb2d_reset(struct radeon_device *rdev)
{
	uint32_t tmp;
	int i;

	WREG32(RADEON_RBBM_SOFT_RESET, RADEON_SOFT_RESET_E2);
	(void)RREG32(RADEON_RBBM_SOFT_RESET);
	udelay(200);
	WREG32(RADEON_RBBM_SOFT_RESET, 0);
	/* Wait to prevent race in RBBM_STATUS */
	mdelay(1);
	for (i = 0; i < rdev->usec_timeout; i++) {
		tmp = RREG32(RADEON_RBBM_STATUS);
		if (!(tmp & (1 << 26))) {
			DRM_INFO("RB2D reset succeed (RBBM_STATUS=0x%08X)\n",
				 tmp);
			return 0;
		}
		DRM_UDELAY(1);
	}
	tmp = RREG32(RADEON_RBBM_STATUS);
	DRM_ERROR("Failed to reset RB2D (RBBM_STATUS=0x%08X)!\n", tmp);
	return -1;
}

int r100_gpu_reset(struct radeon_device *rdev)
{
	uint32_t status;

	/* reset order likely matter */
	status = RREG32(RADEON_RBBM_STATUS);
	/* reset HDP */
	r100_hdp_reset(rdev);
	/* reset rb2d */
	if (status & ((1 << 17) | (1 << 18) | (1 << 27))) {
		r100_rb2d_reset(rdev);
	}
	/* TODO: reset 3D engine */
	/* reset CP */
	status = RREG32(RADEON_RBBM_STATUS);
	if (status & (1 << 16)) {
		r100_cp_reset(rdev);
	}
	/* Check if GPU is idle */
	status = RREG32(RADEON_RBBM_STATUS);
	if (status & (1 << 31)) {
		DRM_ERROR("Failed to reset GPU (RBBM_STATUS=0x%08X)\n", status);
		return -1;
	}
	DRM_INFO("GPU reset succeed (RBBM_STATUS=0x%08X)\n", status);
	return 0;
}


/*
 * VRAM info
 */
static void r100_vram_get_type(struct radeon_device *rdev)
{
	uint32_t tmp;

	rdev->mc.vram_is_ddr = false;
	if (rdev->flags & RADEON_IS_IGP)
		rdev->mc.vram_is_ddr = true;
	else if (RREG32(RADEON_MEM_SDRAM_MODE_REG) & RADEON_MEM_CFG_TYPE_DDR)
		rdev->mc.vram_is_ddr = true;
	if ((rdev->family == CHIP_RV100) ||
	    (rdev->family == CHIP_RS100) ||
	    (rdev->family == CHIP_RS200)) {
		tmp = RREG32(RADEON_MEM_CNTL);
		if (tmp & RV100_HALF_MODE) {
			rdev->mc.vram_width = 32;
		} else {
			rdev->mc.vram_width = 64;
		}
		if (rdev->flags & RADEON_SINGLE_CRTC) {
			rdev->mc.vram_width /= 4;
			rdev->mc.vram_is_ddr = true;
		}
	} else if (rdev->family <= CHIP_RV280) {
		tmp = RREG32(RADEON_MEM_CNTL);
		if (tmp & RADEON_MEM_NUM_CHANNELS_MASK) {
			rdev->mc.vram_width = 128;
		} else {
			rdev->mc.vram_width = 64;
		}
	} else {
		/* newer IGPs */
		rdev->mc.vram_width = 128;
	}
}

static u32 r100_get_accessible_vram(struct radeon_device *rdev)
{
	u32 aper_size;
	u8 byte;

	aper_size = RREG32(RADEON_CONFIG_APER_SIZE);

	/* Set HDP_APER_CNTL only on cards that are known not to be broken,
	 * that is has the 2nd generation multifunction PCI interface
	 */
	if (rdev->family == CHIP_RV280 ||
	    rdev->family >= CHIP_RV350) {
		WREG32_P(RADEON_HOST_PATH_CNTL, RADEON_HDP_APER_CNTL,
		       ~RADEON_HDP_APER_CNTL);
		DRM_INFO("Generation 2 PCI interface, using max accessible memory\n");
		return aper_size * 2;
	}

	/* Older cards have all sorts of funny issues to deal with. First
	 * check if it's a multifunction card by reading the PCI config
	 * header type... Limit those to one aperture size
	 */
	pci_read_config_byte(rdev->pdev, 0xe, &byte);
	if (byte & 0x80) {
		DRM_INFO("Generation 1 PCI interface in multifunction mode\n");
		DRM_INFO("Limiting VRAM to one aperture\n");
		return aper_size;
	}

	/* Single function older card. We read HDP_APER_CNTL to see how the BIOS
	 * have set it up. We don't write this as it's broken on some ASICs but
	 * we expect the BIOS to have done the right thing (might be too optimistic...)
	 */
	if (RREG32(RADEON_HOST_PATH_CNTL) & RADEON_HDP_APER_CNTL)
		return aper_size * 2;
	return aper_size;
}

void r100_vram_init_sizes(struct radeon_device *rdev)
{
	u64 config_aper_size;
	u32 accessible;

	config_aper_size = RREG32(RADEON_CONFIG_APER_SIZE);

	if (rdev->flags & RADEON_IS_IGP) {
		uint32_t tom;
		/* read NB_TOM to get the amount of ram stolen for the GPU */
		tom = RREG32(RADEON_NB_TOM);
		rdev->mc.real_vram_size = (((tom >> 16) - (tom & 0xffff) + 1) << 16);
		/* for IGPs we need to keep VRAM where it was put by the BIOS */
		rdev->mc.vram_location = (tom & 0xffff) << 16;
		WREG32(RADEON_CONFIG_MEMSIZE, rdev->mc.real_vram_size);
		rdev->mc.mc_vram_size = rdev->mc.real_vram_size;
	} else {
		rdev->mc.real_vram_size = RREG32(RADEON_CONFIG_MEMSIZE);
		/* Some production boards of m6 will report 0
		 * if it's 8 MB
		 */
		if (rdev->mc.real_vram_size == 0) {
			rdev->mc.real_vram_size = 8192 * 1024;
			WREG32(RADEON_CONFIG_MEMSIZE, rdev->mc.real_vram_size);
		}
		/* let driver place VRAM */
		rdev->mc.vram_location = 0xFFFFFFFFUL;
		 /* Fix for RN50, M6, M7 with 8/16/32(??) MBs of VRAM - 
		  * Novell bug 204882 + along with lots of ubuntu ones */
		if (config_aper_size > rdev->mc.real_vram_size)
			rdev->mc.mc_vram_size = config_aper_size;
		else
			rdev->mc.mc_vram_size = rdev->mc.real_vram_size;
	}

	/* work out accessible VRAM */
	accessible = r100_get_accessible_vram(rdev);

	rdev->mc.aper_base = drm_get_resource_start(rdev->ddev, 0);
	rdev->mc.aper_size = drm_get_resource_len(rdev->ddev, 0);

	if (accessible > rdev->mc.aper_size)
		accessible = rdev->mc.aper_size;

	if (rdev->mc.mc_vram_size > rdev->mc.aper_size)
		rdev->mc.mc_vram_size = rdev->mc.aper_size;

	if (rdev->mc.real_vram_size > rdev->mc.aper_size)
		rdev->mc.real_vram_size = rdev->mc.aper_size;
}

void r100_vram_info(struct radeon_device *rdev)
{
	r100_vram_get_type(rdev);

	r100_vram_init_sizes(rdev);
}


/*
 * Indirect registers accessor
 */
void r100_pll_errata_after_index(struct radeon_device *rdev)
{
	if (!(rdev->pll_errata & CHIP_ERRATA_PLL_DUMMYREADS)) {
		return;
	}
	(void)RREG32(RADEON_CLOCK_CNTL_DATA);
	(void)RREG32(RADEON_CRTC_GEN_CNTL);
}

static void r100_pll_errata_after_data(struct radeon_device *rdev)
{
	/* This workarounds is necessary on RV100, RS100 and RS200 chips
	 * or the chip could hang on a subsequent access
	 */
	if (rdev->pll_errata & CHIP_ERRATA_PLL_DELAY) {
		udelay(5000);
	}

	/* This function is required to workaround a hardware bug in some (all?)
	 * revisions of the R300.  This workaround should be called after every
	 * CLOCK_CNTL_INDEX register access.  If not, register reads afterward
	 * may not be correct.
	 */
	if (rdev->pll_errata & CHIP_ERRATA_R300_CG) {
		uint32_t save, tmp;

		save = RREG32(RADEON_CLOCK_CNTL_INDEX);
		tmp = save & ~(0x3f | RADEON_PLL_WR_EN);
		WREG32(RADEON_CLOCK_CNTL_INDEX, tmp);
		tmp = RREG32(RADEON_CLOCK_CNTL_DATA);
		WREG32(RADEON_CLOCK_CNTL_INDEX, save);
	}
}

uint32_t r100_pll_rreg(struct radeon_device *rdev, uint32_t reg)
{
	uint32_t data;

	WREG8(RADEON_CLOCK_CNTL_INDEX, reg & 0x3f);
	r100_pll_errata_after_index(rdev);
	data = RREG32(RADEON_CLOCK_CNTL_DATA);
	r100_pll_errata_after_data(rdev);
	return data;
}

void r100_pll_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v)
{
	WREG8(RADEON_CLOCK_CNTL_INDEX, ((reg & 0x3f) | RADEON_PLL_WR_EN));
	r100_pll_errata_after_index(rdev);
	WREG32(RADEON_CLOCK_CNTL_DATA, v);
	r100_pll_errata_after_data(rdev);
}

int r100_init(struct radeon_device *rdev)
{
	return 0;
}

/*
 * Debugfs info
 */
#if defined(CONFIG_DEBUG_FS)
static int r100_debugfs_rbbm_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 reg, value;
	unsigned i;

	seq_printf(m, "RBBM_STATUS 0x%08x\n", RREG32(RADEON_RBBM_STATUS));
	seq_printf(m, "RBBM_CMDFIFO_STAT 0x%08x\n", RREG32(0xE7C));
	seq_printf(m, "CP_STAT 0x%08x\n", RREG32(RADEON_CP_STAT));
	for (i = 0; i < 64; i++) {
		WREG32(RADEON_RBBM_CMDFIFO_ADDR, i | 0x100);
		reg = (RREG32(RADEON_RBBM_CMDFIFO_DATA) - 1) >> 2;
		WREG32(RADEON_RBBM_CMDFIFO_ADDR, i);
		value = RREG32(RADEON_RBBM_CMDFIFO_DATA);
		seq_printf(m, "[0x%03X] 0x%04X=0x%08X\n", i, reg, value);
	}
	return 0;
}

static int r100_debugfs_cp_ring_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 rdp, wdp;
	unsigned count, i, j;

	radeon_ring_free_size(rdev);
	rdp = RREG32(RADEON_CP_RB_RPTR);
	wdp = RREG32(RADEON_CP_RB_WPTR);
	count = (rdp + rdev->cp.ring_size - wdp) & rdev->cp.ptr_mask;
	seq_printf(m, "CP_STAT 0x%08x\n", RREG32(RADEON_CP_STAT));
	seq_printf(m, "CP_RB_WPTR 0x%08x\n", wdp);
	seq_printf(m, "CP_RB_RPTR 0x%08x\n", rdp);
	seq_printf(m, "%u free dwords in ring\n", rdev->cp.ring_free_dw);
	seq_printf(m, "%u dwords in ring\n", count);
	for (j = 0; j <= count; j++) {
		i = (rdp + j) & rdev->cp.ptr_mask;
		seq_printf(m, "r[%04d]=0x%08x\n", i, rdev->cp.ring[i]);
	}
	return 0;
}


static int r100_debugfs_cp_csq_fifo(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 csq_stat, csq2_stat, tmp;
	unsigned r_rptr, r_wptr, ib1_rptr, ib1_wptr, ib2_rptr, ib2_wptr;
	unsigned i;

	seq_printf(m, "CP_STAT 0x%08x\n", RREG32(RADEON_CP_STAT));
	seq_printf(m, "CP_CSQ_MODE 0x%08x\n", RREG32(RADEON_CP_CSQ_MODE));
	csq_stat = RREG32(RADEON_CP_CSQ_STAT);
	csq2_stat = RREG32(RADEON_CP_CSQ2_STAT);
	r_rptr = (csq_stat >> 0) & 0x3ff;
	r_wptr = (csq_stat >> 10) & 0x3ff;
	ib1_rptr = (csq_stat >> 20) & 0x3ff;
	ib1_wptr = (csq2_stat >> 0) & 0x3ff;
	ib2_rptr = (csq2_stat >> 10) & 0x3ff;
	ib2_wptr = (csq2_stat >> 20) & 0x3ff;
	seq_printf(m, "CP_CSQ_STAT 0x%08x\n", csq_stat);
	seq_printf(m, "CP_CSQ2_STAT 0x%08x\n", csq2_stat);
	seq_printf(m, "Ring rptr %u\n", r_rptr);
	seq_printf(m, "Ring wptr %u\n", r_wptr);
	seq_printf(m, "Indirect1 rptr %u\n", ib1_rptr);
	seq_printf(m, "Indirect1 wptr %u\n", ib1_wptr);
	seq_printf(m, "Indirect2 rptr %u\n", ib2_rptr);
	seq_printf(m, "Indirect2 wptr %u\n", ib2_wptr);
	/* FIXME: 0, 128, 640 depends on fifo setup see cp_init_kms
	 * 128 = indirect1_start * 8 & 640 = indirect2_start * 8 */
	seq_printf(m, "Ring fifo:\n");
	for (i = 0; i < 256; i++) {
		WREG32(RADEON_CP_CSQ_ADDR, i << 2);
		tmp = RREG32(RADEON_CP_CSQ_DATA);
		seq_printf(m, "rfifo[%04d]=0x%08X\n", i, tmp);
	}
	seq_printf(m, "Indirect1 fifo:\n");
	for (i = 256; i <= 512; i++) {
		WREG32(RADEON_CP_CSQ_ADDR, i << 2);
		tmp = RREG32(RADEON_CP_CSQ_DATA);
		seq_printf(m, "ib1fifo[%04d]=0x%08X\n", i, tmp);
	}
	seq_printf(m, "Indirect2 fifo:\n");
	for (i = 640; i < ib1_wptr; i++) {
		WREG32(RADEON_CP_CSQ_ADDR, i << 2);
		tmp = RREG32(RADEON_CP_CSQ_DATA);
		seq_printf(m, "ib2fifo[%04d]=0x%08X\n", i, tmp);
	}
	return 0;
}

static int r100_debugfs_mc_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(RADEON_CONFIG_MEMSIZE);
	seq_printf(m, "CONFIG_MEMSIZE 0x%08x\n", tmp);
	tmp = RREG32(RADEON_MC_FB_LOCATION);
	seq_printf(m, "MC_FB_LOCATION 0x%08x\n", tmp);
	tmp = RREG32(RADEON_BUS_CNTL);
	seq_printf(m, "BUS_CNTL 0x%08x\n", tmp);
	tmp = RREG32(RADEON_MC_AGP_LOCATION);
	seq_printf(m, "MC_AGP_LOCATION 0x%08x\n", tmp);
	tmp = RREG32(RADEON_AGP_BASE);
	seq_printf(m, "AGP_BASE 0x%08x\n", tmp);
	tmp = RREG32(RADEON_HOST_PATH_CNTL);
	seq_printf(m, "HOST_PATH_CNTL 0x%08x\n", tmp);
	tmp = RREG32(0x01D0);
	seq_printf(m, "AIC_CTRL 0x%08x\n", tmp);
	tmp = RREG32(RADEON_AIC_LO_ADDR);
	seq_printf(m, "AIC_LO_ADDR 0x%08x\n", tmp);
	tmp = RREG32(RADEON_AIC_HI_ADDR);
	seq_printf(m, "AIC_HI_ADDR 0x%08x\n", tmp);
	tmp = RREG32(0x01E4);
	seq_printf(m, "AIC_TLB_ADDR 0x%08x\n", tmp);
	return 0;
}

static struct drm_info_list r100_debugfs_rbbm_list[] = {
	{"r100_rbbm_info", r100_debugfs_rbbm_info, 0, NULL},
};

static struct drm_info_list r100_debugfs_cp_list[] = {
	{"r100_cp_ring_info", r100_debugfs_cp_ring_info, 0, NULL},
	{"r100_cp_csq_fifo", r100_debugfs_cp_csq_fifo, 0, NULL},
};

static struct drm_info_list r100_debugfs_mc_info_list[] = {
	{"r100_mc_info", r100_debugfs_mc_info, 0, NULL},
};
#endif

int r100_debugfs_rbbm_init(struct radeon_device *rdev)
{
#if defined(CONFIG_DEBUG_FS)
	return radeon_debugfs_add_files(rdev, r100_debugfs_rbbm_list, 1);
#else
	return 0;
#endif
}

int r100_debugfs_cp_init(struct radeon_device *rdev)
{
#if defined(CONFIG_DEBUG_FS)
	return radeon_debugfs_add_files(rdev, r100_debugfs_cp_list, 2);
#else
	return 0;
#endif
}

int r100_debugfs_mc_info_init(struct radeon_device *rdev)
{
#if defined(CONFIG_DEBUG_FS)
	return radeon_debugfs_add_files(rdev, r100_debugfs_mc_info_list, 1);
#else
	return 0;
#endif
}

int r100_set_surface_reg(struct radeon_device *rdev, int reg,
			 uint32_t tiling_flags, uint32_t pitch,
			 uint32_t offset, uint32_t obj_size)
{
	int surf_index = reg * 16;
	int flags = 0;

	/* r100/r200 divide by 16 */
	if (rdev->family < CHIP_R300)
		flags = pitch / 16;
	else
		flags = pitch / 8;

	if (rdev->family <= CHIP_RS200) {
		if ((tiling_flags & (RADEON_TILING_MACRO|RADEON_TILING_MICRO))
				 == (RADEON_TILING_MACRO|RADEON_TILING_MICRO))
			flags |= RADEON_SURF_TILE_COLOR_BOTH;
		if (tiling_flags & RADEON_TILING_MACRO)
			flags |= RADEON_SURF_TILE_COLOR_MACRO;
	} else if (rdev->family <= CHIP_RV280) {
		if (tiling_flags & (RADEON_TILING_MACRO))
			flags |= R200_SURF_TILE_COLOR_MACRO;
		if (tiling_flags & RADEON_TILING_MICRO)
			flags |= R200_SURF_TILE_COLOR_MICRO;
	} else {
		if (tiling_flags & RADEON_TILING_MACRO)
			flags |= R300_SURF_TILE_MACRO;
		if (tiling_flags & RADEON_TILING_MICRO)
			flags |= R300_SURF_TILE_MICRO;
	}

	DRM_DEBUG("writing surface %d %d %x %x\n", reg, flags, offset, offset+obj_size-1);
	WREG32(RADEON_SURFACE0_INFO + surf_index, flags);
	WREG32(RADEON_SURFACE0_LOWER_BOUND + surf_index, offset);
	WREG32(RADEON_SURFACE0_UPPER_BOUND + surf_index, offset + obj_size - 1);
	return 0;
}

void r100_clear_surface_reg(struct radeon_device *rdev, int reg)
{
	int surf_index = reg * 16;
	WREG32(RADEON_SURFACE0_INFO + surf_index, 0);
}

void r100_bandwidth_update(struct radeon_device *rdev)
{
	fixed20_12 trcd_ff, trp_ff, tras_ff, trbs_ff, tcas_ff;
	fixed20_12 sclk_ff, mclk_ff, sclk_eff_ff, sclk_delay_ff;
	fixed20_12 peak_disp_bw, mem_bw, pix_clk, pix_clk2, temp_ff, crit_point_ff;
	uint32_t temp, data, mem_trcd, mem_trp, mem_tras;
	fixed20_12 memtcas_ff[8] = {
		fixed_init(1),
		fixed_init(2),
		fixed_init(3),
		fixed_init(0),
		fixed_init_half(1),
		fixed_init_half(2),
		fixed_init(0),
	};
	fixed20_12 memtcas_rs480_ff[8] = {
		fixed_init(0),
		fixed_init(1),
		fixed_init(2),
		fixed_init(3),
		fixed_init(0),
		fixed_init_half(1),
		fixed_init_half(2),
		fixed_init_half(3),
	};
	fixed20_12 memtcas2_ff[8] = {
		fixed_init(0),
		fixed_init(1),
		fixed_init(2),
		fixed_init(3),
		fixed_init(4),
		fixed_init(5),
		fixed_init(6),
		fixed_init(7),
	};
	fixed20_12 memtrbs[8] = {
		fixed_init(1),
		fixed_init_half(1),
		fixed_init(2),
		fixed_init_half(2),
		fixed_init(3),
		fixed_init_half(3),
		fixed_init(4),
		fixed_init_half(4)
	};
	fixed20_12 memtrbs_r4xx[8] = {
		fixed_init(4),
		fixed_init(5),
		fixed_init(6),
		fixed_init(7),
		fixed_init(8),
		fixed_init(9),
		fixed_init(10),
		fixed_init(11)
	};
	fixed20_12 min_mem_eff;
	fixed20_12 mc_latency_sclk, mc_latency_mclk, k1;
	fixed20_12 cur_latency_mclk, cur_latency_sclk;
	fixed20_12 disp_latency, disp_latency_overhead, disp_drain_rate,
		disp_drain_rate2, read_return_rate;
	fixed20_12 time_disp1_drop_priority;
	int c;
	int cur_size = 16;       /* in octawords */
	int critical_point = 0, critical_point2;
/* 	uint32_t read_return_rate, time_disp1_drop_priority; */
	int stop_req, max_stop_req;
	struct drm_display_mode *mode1 = NULL;
	struct drm_display_mode *mode2 = NULL;
	uint32_t pixel_bytes1 = 0;
	uint32_t pixel_bytes2 = 0;

	if (rdev->mode_info.crtcs[0]->base.enabled) {
		mode1 = &rdev->mode_info.crtcs[0]->base.mode;
		pixel_bytes1 = rdev->mode_info.crtcs[0]->base.fb->bits_per_pixel / 8;
	}
	if (rdev->mode_info.crtcs[1]->base.enabled) {
		mode2 = &rdev->mode_info.crtcs[1]->base.mode;
		pixel_bytes2 = rdev->mode_info.crtcs[1]->base.fb->bits_per_pixel / 8;
	}

	min_mem_eff.full = rfixed_const_8(0);
	/* get modes */
	if ((rdev->disp_priority == 2) && ASIC_IS_R300(rdev)) {
		uint32_t mc_init_misc_lat_timer = RREG32(R300_MC_INIT_MISC_LAT_TIMER);
		mc_init_misc_lat_timer &= ~(R300_MC_DISP1R_INIT_LAT_MASK << R300_MC_DISP1R_INIT_LAT_SHIFT);
		mc_init_misc_lat_timer &= ~(R300_MC_DISP0R_INIT_LAT_MASK << R300_MC_DISP0R_INIT_LAT_SHIFT);
		/* check crtc enables */
		if (mode2)
			mc_init_misc_lat_timer |= (1 << R300_MC_DISP1R_INIT_LAT_SHIFT);
		if (mode1)
			mc_init_misc_lat_timer |= (1 << R300_MC_DISP0R_INIT_LAT_SHIFT);
		WREG32(R300_MC_INIT_MISC_LAT_TIMER, mc_init_misc_lat_timer);
	}

	/*
	 * determine is there is enough bw for current mode
	 */
	mclk_ff.full = rfixed_const(rdev->clock.default_mclk);
	temp_ff.full = rfixed_const(100);
	mclk_ff.full = rfixed_div(mclk_ff, temp_ff);
	sclk_ff.full = rfixed_const(rdev->clock.default_sclk);
	sclk_ff.full = rfixed_div(sclk_ff, temp_ff);

	temp = (rdev->mc.vram_width / 8) * (rdev->mc.vram_is_ddr ? 2 : 1);
	temp_ff.full = rfixed_const(temp);
	mem_bw.full = rfixed_mul(mclk_ff, temp_ff);

	pix_clk.full = 0;
	pix_clk2.full = 0;
	peak_disp_bw.full = 0;
	if (mode1) {
		temp_ff.full = rfixed_const(1000);
		pix_clk.full = rfixed_const(mode1->clock); /* convert to fixed point */
		pix_clk.full = rfixed_div(pix_clk, temp_ff);
		temp_ff.full = rfixed_const(pixel_bytes1);
		peak_disp_bw.full += rfixed_mul(pix_clk, temp_ff);
	}
	if (mode2) {
		temp_ff.full = rfixed_const(1000);
		pix_clk2.full = rfixed_const(mode2->clock); /* convert to fixed point */
		pix_clk2.full = rfixed_div(pix_clk2, temp_ff);
		temp_ff.full = rfixed_const(pixel_bytes2);
		peak_disp_bw.full += rfixed_mul(pix_clk2, temp_ff);
	}

	mem_bw.full = rfixed_mul(mem_bw, min_mem_eff);
	if (peak_disp_bw.full >= mem_bw.full) {
		DRM_ERROR("You may not have enough display bandwidth for current mode\n"
			  "If you have flickering problem, try to lower resolution, refresh rate, or color depth\n");
	}

	/*  Get values from the EXT_MEM_CNTL register...converting its contents. */
	temp = RREG32(RADEON_MEM_TIMING_CNTL);
	if ((rdev->family == CHIP_RV100) || (rdev->flags & RADEON_IS_IGP)) { /* RV100, M6, IGPs */
		mem_trcd = ((temp >> 2) & 0x3) + 1;
		mem_trp  = ((temp & 0x3)) + 1;
		mem_tras = ((temp & 0x70) >> 4) + 1;
	} else if (rdev->family == CHIP_R300 ||
		   rdev->family == CHIP_R350) { /* r300, r350 */
		mem_trcd = (temp & 0x7) + 1;
		mem_trp = ((temp >> 8) & 0x7) + 1;
		mem_tras = ((temp >> 11) & 0xf) + 4;
	} else if (rdev->family == CHIP_RV350 ||
		   rdev->family <= CHIP_RV380) {
		/* rv3x0 */
		mem_trcd = (temp & 0x7) + 3;
		mem_trp = ((temp >> 8) & 0x7) + 3;
		mem_tras = ((temp >> 11) & 0xf) + 6;
	} else if (rdev->family == CHIP_R420 ||
		   rdev->family == CHIP_R423 ||
		   rdev->family == CHIP_RV410) {
		/* r4xx */
		mem_trcd = (temp & 0xf) + 3;
		if (mem_trcd > 15)
			mem_trcd = 15;
		mem_trp = ((temp >> 8) & 0xf) + 3;
		if (mem_trp > 15)
			mem_trp = 15;
		mem_tras = ((temp >> 12) & 0x1f) + 6;
		if (mem_tras > 31)
			mem_tras = 31;
	} else { /* RV200, R200 */
		mem_trcd = (temp & 0x7) + 1;
		mem_trp = ((temp >> 8) & 0x7) + 1;
		mem_tras = ((temp >> 12) & 0xf) + 4;
	}
	/* convert to FF */
	trcd_ff.full = rfixed_const(mem_trcd);
	trp_ff.full = rfixed_const(mem_trp);
	tras_ff.full = rfixed_const(mem_tras);

	/* Get values from the MEM_SDRAM_MODE_REG register...converting its */
	temp = RREG32(RADEON_MEM_SDRAM_MODE_REG);
	data = (temp & (7 << 20)) >> 20;
	if ((rdev->family == CHIP_RV100) || rdev->flags & RADEON_IS_IGP) {
		if (rdev->family == CHIP_RS480) /* don't think rs400 */
			tcas_ff = memtcas_rs480_ff[data];
		else
			tcas_ff = memtcas_ff[data];
	} else
		tcas_ff = memtcas2_ff[data];

	if (rdev->family == CHIP_RS400 ||
	    rdev->family == CHIP_RS480) {
		/* extra cas latency stored in bits 23-25 0-4 clocks */
		data = (temp >> 23) & 0x7;
		if (data < 5)
			tcas_ff.full += rfixed_const(data);
	}

	if (ASIC_IS_R300(rdev) && !(rdev->flags & RADEON_IS_IGP)) {
		/* on the R300, Tcas is included in Trbs.
		 */
		temp = RREG32(RADEON_MEM_CNTL);
		data = (R300_MEM_NUM_CHANNELS_MASK & temp);
		if (data == 1) {
			if (R300_MEM_USE_CD_CH_ONLY & temp) {
				temp = RREG32(R300_MC_IND_INDEX);
				temp &= ~R300_MC_IND_ADDR_MASK;
				temp |= R300_MC_READ_CNTL_CD_mcind;
				WREG32(R300_MC_IND_INDEX, temp);
				temp = RREG32(R300_MC_IND_DATA);
				data = (R300_MEM_RBS_POSITION_C_MASK & temp);
			} else {
				temp = RREG32(R300_MC_READ_CNTL_AB);
				data = (R300_MEM_RBS_POSITION_A_MASK & temp);
			}
		} else {
			temp = RREG32(R300_MC_READ_CNTL_AB);
			data = (R300_MEM_RBS_POSITION_A_MASK & temp);
		}
		if (rdev->family == CHIP_RV410 ||
		    rdev->family == CHIP_R420 ||
		    rdev->family == CHIP_R423)
			trbs_ff = memtrbs_r4xx[data];
		else
			trbs_ff = memtrbs[data];
		tcas_ff.full += trbs_ff.full;
	}

	sclk_eff_ff.full = sclk_ff.full;

	if (rdev->flags & RADEON_IS_AGP) {
		fixed20_12 agpmode_ff;
		agpmode_ff.full = rfixed_const(radeon_agpmode);
		temp_ff.full = rfixed_const_666(16);
		sclk_eff_ff.full -= rfixed_mul(agpmode_ff, temp_ff);
	}
	/* TODO PCIE lanes may affect this - agpmode == 16?? */

	if (ASIC_IS_R300(rdev)) {
		sclk_delay_ff.full = rfixed_const(250);
	} else {
		if ((rdev->family == CHIP_RV100) ||
		    rdev->flags & RADEON_IS_IGP) {
			if (rdev->mc.vram_is_ddr)
				sclk_delay_ff.full = rfixed_const(41);
			else
				sclk_delay_ff.full = rfixed_const(33);
		} else {
			if (rdev->mc.vram_width == 128)
				sclk_delay_ff.full = rfixed_const(57);
			else
				sclk_delay_ff.full = rfixed_const(41);
		}
	}

	mc_latency_sclk.full = rfixed_div(sclk_delay_ff, sclk_eff_ff);

	if (rdev->mc.vram_is_ddr) {
		if (rdev->mc.vram_width == 32) {
			k1.full = rfixed_const(40);
			c  = 3;
		} else {
			k1.full = rfixed_const(20);
			c  = 1;
		}
	} else {
		k1.full = rfixed_const(40);
		c  = 3;
	}

	temp_ff.full = rfixed_const(2);
	mc_latency_mclk.full = rfixed_mul(trcd_ff, temp_ff);
	temp_ff.full = rfixed_const(c);
	mc_latency_mclk.full += rfixed_mul(tcas_ff, temp_ff);
	temp_ff.full = rfixed_const(4);
	mc_latency_mclk.full += rfixed_mul(tras_ff, temp_ff);
	mc_latency_mclk.full += rfixed_mul(trp_ff, temp_ff);
	mc_latency_mclk.full += k1.full;

	mc_latency_mclk.full = rfixed_div(mc_latency_mclk, mclk_ff);
	mc_latency_mclk.full += rfixed_div(temp_ff, sclk_eff_ff);

	/*
	  HW cursor time assuming worst case of full size colour cursor.
	*/
	temp_ff.full = rfixed_const((2 * (cur_size - (rdev->mc.vram_is_ddr + 1))));
	temp_ff.full += trcd_ff.full;
	if (temp_ff.full < tras_ff.full)
		temp_ff.full = tras_ff.full;
	cur_latency_mclk.full = rfixed_div(temp_ff, mclk_ff);

	temp_ff.full = rfixed_const(cur_size);
	cur_latency_sclk.full = rfixed_div(temp_ff, sclk_eff_ff);
	/*
	  Find the total latency for the display data.
	*/
	disp_latency_overhead.full = rfixed_const(80);
	disp_latency_overhead.full = rfixed_div(disp_latency_overhead, sclk_ff);
	mc_latency_mclk.full += disp_latency_overhead.full + cur_latency_mclk.full;
	mc_latency_sclk.full += disp_latency_overhead.full + cur_latency_sclk.full;

	if (mc_latency_mclk.full > mc_latency_sclk.full)
		disp_latency.full = mc_latency_mclk.full;
	else
		disp_latency.full = mc_latency_sclk.full;

	/* setup Max GRPH_STOP_REQ default value */
	if (ASIC_IS_RV100(rdev))
		max_stop_req = 0x5c;
	else
		max_stop_req = 0x7c;

	if (mode1) {
		/*  CRTC1
		    Set GRPH_BUFFER_CNTL register using h/w defined optimal values.
		    GRPH_STOP_REQ <= MIN[ 0x7C, (CRTC_H_DISP + 1) * (bit depth) / 0x10 ]
		*/
		stop_req = mode1->hdisplay * pixel_bytes1 / 16;

		if (stop_req > max_stop_req)
			stop_req = max_stop_req;

		/*
		  Find the drain rate of the display buffer.
		*/
		temp_ff.full = rfixed_const((16/pixel_bytes1));
		disp_drain_rate.full = rfixed_div(pix_clk, temp_ff);

		/*
		  Find the critical point of the display buffer.
		*/
		crit_point_ff.full = rfixed_mul(disp_drain_rate, disp_latency);
		crit_point_ff.full += rfixed_const_half(0);

		critical_point = rfixed_trunc(crit_point_ff);

		if (rdev->disp_priority == 2) {
			critical_point = 0;
		}

		/*
		  The critical point should never be above max_stop_req-4.  Setting
		  GRPH_CRITICAL_CNTL = 0 will thus force high priority all the time.
		*/
		if (max_stop_req - critical_point < 4)
			critical_point = 0;

		if (critical_point == 0 && mode2 && rdev->family == CHIP_R300) {
			/* some R300 cards have problem with this set to 0, when CRTC2 is enabled.*/
			critical_point = 0x10;
		}

		temp = RREG32(RADEON_GRPH_BUFFER_CNTL);
		temp &= ~(RADEON_GRPH_STOP_REQ_MASK);
		temp |= (stop_req << RADEON_GRPH_STOP_REQ_SHIFT);
		temp &= ~(RADEON_GRPH_START_REQ_MASK);
		if ((rdev->family == CHIP_R350) &&
		    (stop_req > 0x15)) {
			stop_req -= 0x10;
		}
		temp |= (stop_req << RADEON_GRPH_START_REQ_SHIFT);
		temp |= RADEON_GRPH_BUFFER_SIZE;
		temp &= ~(RADEON_GRPH_CRITICAL_CNTL   |
			  RADEON_GRPH_CRITICAL_AT_SOF |
			  RADEON_GRPH_STOP_CNTL);
		/*
		  Write the result into the register.
		*/
		WREG32(RADEON_GRPH_BUFFER_CNTL, ((temp & ~RADEON_GRPH_CRITICAL_POINT_MASK) |
						       (critical_point << RADEON_GRPH_CRITICAL_POINT_SHIFT)));

#if 0
		if ((rdev->family == CHIP_RS400) ||
		    (rdev->family == CHIP_RS480)) {
			/* attempt to program RS400 disp regs correctly ??? */
			temp = RREG32(RS400_DISP1_REG_CNTL);
			temp &= ~(RS400_DISP1_START_REQ_LEVEL_MASK |
				  RS400_DISP1_STOP_REQ_LEVEL_MASK);
			WREG32(RS400_DISP1_REQ_CNTL1, (temp |
						       (critical_point << RS400_DISP1_START_REQ_LEVEL_SHIFT) |
						       (critical_point << RS400_DISP1_STOP_REQ_LEVEL_SHIFT)));
			temp = RREG32(RS400_DMIF_MEM_CNTL1);
			temp &= ~(RS400_DISP1_CRITICAL_POINT_START_MASK |
				  RS400_DISP1_CRITICAL_POINT_STOP_MASK);
			WREG32(RS400_DMIF_MEM_CNTL1, (temp |
						      (critical_point << RS400_DISP1_CRITICAL_POINT_START_SHIFT) |
						      (critical_point << RS400_DISP1_CRITICAL_POINT_STOP_SHIFT)));
		}
#endif

		DRM_DEBUG("GRPH_BUFFER_CNTL from to %x\n",
			  /* 	  (unsigned int)info->SavedReg->grph_buffer_cntl, */
			  (unsigned int)RREG32(RADEON_GRPH_BUFFER_CNTL));
	}

	if (mode2) {
		u32 grph2_cntl;
		stop_req = mode2->hdisplay * pixel_bytes2 / 16;

		if (stop_req > max_stop_req)
			stop_req = max_stop_req;

		/*
		  Find the drain rate of the display buffer.
		*/
		temp_ff.full = rfixed_const((16/pixel_bytes2));
		disp_drain_rate2.full = rfixed_div(pix_clk2, temp_ff);

		grph2_cntl = RREG32(RADEON_GRPH2_BUFFER_CNTL);
		grph2_cntl &= ~(RADEON_GRPH_STOP_REQ_MASK);
		grph2_cntl |= (stop_req << RADEON_GRPH_STOP_REQ_SHIFT);
		grph2_cntl &= ~(RADEON_GRPH_START_REQ_MASK);
		if ((rdev->family == CHIP_R350) &&
		    (stop_req > 0x15)) {
			stop_req -= 0x10;
		}
		grph2_cntl |= (stop_req << RADEON_GRPH_START_REQ_SHIFT);
		grph2_cntl |= RADEON_GRPH_BUFFER_SIZE;
		grph2_cntl &= ~(RADEON_GRPH_CRITICAL_CNTL   |
			  RADEON_GRPH_CRITICAL_AT_SOF |
			  RADEON_GRPH_STOP_CNTL);

		if ((rdev->family == CHIP_RS100) ||
		    (rdev->family == CHIP_RS200))
			critical_point2 = 0;
		else {
			temp = (rdev->mc.vram_width * rdev->mc.vram_is_ddr + 1)/128;
			temp_ff.full = rfixed_const(temp);
			temp_ff.full = rfixed_mul(mclk_ff, temp_ff);
			if (sclk_ff.full < temp_ff.full)
				temp_ff.full = sclk_ff.full;

			read_return_rate.full = temp_ff.full;

			if (mode1) {
				temp_ff.full = read_return_rate.full - disp_drain_rate.full;
				time_disp1_drop_priority.full = rfixed_div(crit_point_ff, temp_ff);
			} else {
				time_disp1_drop_priority.full = 0;
			}
			crit_point_ff.full = disp_latency.full + time_disp1_drop_priority.full + disp_latency.full;
			crit_point_ff.full = rfixed_mul(crit_point_ff, disp_drain_rate2);
			crit_point_ff.full += rfixed_const_half(0);

			critical_point2 = rfixed_trunc(crit_point_ff);

			if (rdev->disp_priority == 2) {
				critical_point2 = 0;
			}

			if (max_stop_req - critical_point2 < 4)
				critical_point2 = 0;

		}

		if (critical_point2 == 0 && rdev->family == CHIP_R300) {
			/* some R300 cards have problem with this set to 0 */
			critical_point2 = 0x10;
		}

		WREG32(RADEON_GRPH2_BUFFER_CNTL, ((grph2_cntl & ~RADEON_GRPH_CRITICAL_POINT_MASK) |
						  (critical_point2 << RADEON_GRPH_CRITICAL_POINT_SHIFT)));

		if ((rdev->family == CHIP_RS400) ||
		    (rdev->family == CHIP_RS480)) {
#if 0
			/* attempt to program RS400 disp2 regs correctly ??? */
			temp = RREG32(RS400_DISP2_REQ_CNTL1);
			temp &= ~(RS400_DISP2_START_REQ_LEVEL_MASK |
				  RS400_DISP2_STOP_REQ_LEVEL_MASK);
			WREG32(RS400_DISP2_REQ_CNTL1, (temp |
						       (critical_point2 << RS400_DISP1_START_REQ_LEVEL_SHIFT) |
						       (critical_point2 << RS400_DISP1_STOP_REQ_LEVEL_SHIFT)));
			temp = RREG32(RS400_DISP2_REQ_CNTL2);
			temp &= ~(RS400_DISP2_CRITICAL_POINT_START_MASK |
				  RS400_DISP2_CRITICAL_POINT_STOP_MASK);
			WREG32(RS400_DISP2_REQ_CNTL2, (temp |
						       (critical_point2 << RS400_DISP2_CRITICAL_POINT_START_SHIFT) |
						       (critical_point2 << RS400_DISP2_CRITICAL_POINT_STOP_SHIFT)));
#endif
			WREG32(RS400_DISP2_REQ_CNTL1, 0x105DC1CC);
			WREG32(RS400_DISP2_REQ_CNTL2, 0x2749D000);
			WREG32(RS400_DMIF_MEM_CNTL1,  0x29CA71DC);
			WREG32(RS400_DISP1_REQ_CNTL1, 0x28FBC3AC);
		}

		DRM_DEBUG("GRPH2_BUFFER_CNTL from to %x\n",
			  (unsigned int)RREG32(RADEON_GRPH2_BUFFER_CNTL));
	}
}