summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/i915/i915_gem_gtt.c
blob: 1411613f2174cf67280e12127327e880e8772275 (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
/*
 * Copyright © 2010 Daniel Vetter
 * Copyright © 2011-2014 Intel Corporation
 *
 * 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 (including the next
 * paragraph) shall be included in all copies or substantial portions of the
 * Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS 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.
 *
 */

#include <linux/seq_file.h>
#include <drm/drmP.h>
#include <drm/i915_drm.h>
#include "i915_drv.h"
#include "i915_trace.h"
#include "intel_drv.h"

static void bdw_setup_private_ppat(struct drm_i915_private *dev_priv);
static void chv_setup_private_ppat(struct drm_i915_private *dev_priv);

bool intel_enable_ppgtt(struct drm_device *dev, bool full)
{
	if (i915.enable_ppgtt == 0)
		return false;

	if (i915.enable_ppgtt == 1 && full)
		return false;

	return true;
}

static int sanitize_enable_ppgtt(struct drm_device *dev, int enable_ppgtt)
{
	if (enable_ppgtt == 0 || !HAS_ALIASING_PPGTT(dev))
		return 0;

	if (enable_ppgtt == 1)
		return 1;

	if (enable_ppgtt == 2 && HAS_PPGTT(dev))
		return 2;

#ifdef CONFIG_INTEL_IOMMU
	/* Disable ppgtt on SNB if VT-d is on. */
	if (INTEL_INFO(dev)->gen == 6 && intel_iommu_gfx_mapped) {
		DRM_INFO("Disabling PPGTT because VT-d is on\n");
		return 0;
	}
#endif

	/* Early VLV doesn't have this */
	if (IS_VALLEYVIEW(dev) && !IS_CHERRYVIEW(dev) &&
	    dev->pdev->revision < 0xb) {
		DRM_DEBUG_DRIVER("disabling PPGTT on pre-B3 step VLV\n");
		return 0;
	}

	return HAS_ALIASING_PPGTT(dev) ? 1 : 0;
}


static void ppgtt_bind_vma(struct i915_vma *vma,
			   enum i915_cache_level cache_level,
			   u32 flags);
static void ppgtt_unbind_vma(struct i915_vma *vma);
static int gen8_ppgtt_enable(struct i915_hw_ppgtt *ppgtt);

static inline gen8_gtt_pte_t gen8_pte_encode(dma_addr_t addr,
					     enum i915_cache_level level,
					     bool valid)
{
	gen8_gtt_pte_t pte = valid ? _PAGE_PRESENT | _PAGE_RW : 0;
	pte |= addr;

	switch (level) {
	case I915_CACHE_NONE:
		pte |= PPAT_UNCACHED_INDEX;
		break;
	case I915_CACHE_WT:
		pte |= PPAT_DISPLAY_ELLC_INDEX;
		break;
	default:
		pte |= PPAT_CACHED_INDEX;
		break;
	}

	return pte;
}

static inline gen8_ppgtt_pde_t gen8_pde_encode(struct drm_device *dev,
					     dma_addr_t addr,
					     enum i915_cache_level level)
{
	gen8_ppgtt_pde_t pde = _PAGE_PRESENT | _PAGE_RW;
	pde |= addr;
	if (level != I915_CACHE_NONE)
		pde |= PPAT_CACHED_PDE_INDEX;
	else
		pde |= PPAT_UNCACHED_INDEX;
	return pde;
}

static gen6_gtt_pte_t snb_pte_encode(dma_addr_t addr,
				     enum i915_cache_level level,
				     bool valid, u32 unused)
{
	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
	pte |= GEN6_PTE_ADDR_ENCODE(addr);

	switch (level) {
	case I915_CACHE_L3_LLC:
	case I915_CACHE_LLC:
		pte |= GEN6_PTE_CACHE_LLC;
		break;
	case I915_CACHE_NONE:
		pte |= GEN6_PTE_UNCACHED;
		break;
	default:
		WARN_ON(1);
	}

	return pte;
}

static gen6_gtt_pte_t ivb_pte_encode(dma_addr_t addr,
				     enum i915_cache_level level,
				     bool valid, u32 unused)
{
	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
	pte |= GEN6_PTE_ADDR_ENCODE(addr);

	switch (level) {
	case I915_CACHE_L3_LLC:
		pte |= GEN7_PTE_CACHE_L3_LLC;
		break;
	case I915_CACHE_LLC:
		pte |= GEN6_PTE_CACHE_LLC;
		break;
	case I915_CACHE_NONE:
		pte |= GEN6_PTE_UNCACHED;
		break;
	default:
		WARN_ON(1);
	}

	return pte;
}

static gen6_gtt_pte_t byt_pte_encode(dma_addr_t addr,
				     enum i915_cache_level level,
				     bool valid, u32 flags)
{
	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
	pte |= GEN6_PTE_ADDR_ENCODE(addr);

	/* Mark the page as writeable.  Other platforms don't have a
	 * setting for read-only/writable, so this matches that behavior.
	 */
	if (!(flags & PTE_READ_ONLY))
		pte |= BYT_PTE_WRITEABLE;

	if (level != I915_CACHE_NONE)
		pte |= BYT_PTE_SNOOPED_BY_CPU_CACHES;

	return pte;
}

static gen6_gtt_pte_t hsw_pte_encode(dma_addr_t addr,
				     enum i915_cache_level level,
				     bool valid, u32 unused)
{
	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
	pte |= HSW_PTE_ADDR_ENCODE(addr);

	if (level != I915_CACHE_NONE)
		pte |= HSW_WB_LLC_AGE3;

	return pte;
}

static gen6_gtt_pte_t iris_pte_encode(dma_addr_t addr,
				      enum i915_cache_level level,
				      bool valid, u32 unused)
{
	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
	pte |= HSW_PTE_ADDR_ENCODE(addr);

	switch (level) {
	case I915_CACHE_NONE:
		break;
	case I915_CACHE_WT:
		pte |= HSW_WT_ELLC_LLC_AGE3;
		break;
	default:
		pte |= HSW_WB_ELLC_LLC_AGE3;
		break;
	}

	return pte;
}

/* Broadwell Page Directory Pointer Descriptors */
static int gen8_write_pdp(struct intel_engine_cs *ring, unsigned entry,
			   uint64_t val, bool synchronous)
{
	struct drm_i915_private *dev_priv = ring->dev->dev_private;
	int ret;

	BUG_ON(entry >= 4);

	if (synchronous) {
		I915_WRITE(GEN8_RING_PDP_UDW(ring, entry), val >> 32);
		I915_WRITE(GEN8_RING_PDP_LDW(ring, entry), (u32)val);
		return 0;
	}

	ret = intel_ring_begin(ring, 6);
	if (ret)
		return ret;

	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
	intel_ring_emit(ring, GEN8_RING_PDP_UDW(ring, entry));
	intel_ring_emit(ring, (u32)(val >> 32));
	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
	intel_ring_emit(ring, GEN8_RING_PDP_LDW(ring, entry));
	intel_ring_emit(ring, (u32)(val));
	intel_ring_advance(ring);

	return 0;
}

static int gen8_mm_switch(struct i915_hw_ppgtt *ppgtt,
			  struct intel_engine_cs *ring,
			  bool synchronous)
{
	int i, ret;

	/* bit of a hack to find the actual last used pd */
	int used_pd = ppgtt->num_pd_entries / GEN8_PDES_PER_PAGE;

	for (i = used_pd - 1; i >= 0; i--) {
		dma_addr_t addr = ppgtt->pd_dma_addr[i];
		ret = gen8_write_pdp(ring, i, addr, synchronous);
		if (ret)
			return ret;
	}

	return 0;
}

static void gen8_ppgtt_clear_range(struct i915_address_space *vm,
				   uint64_t start,
				   uint64_t length,
				   bool use_scratch)
{
	struct i915_hw_ppgtt *ppgtt =
		container_of(vm, struct i915_hw_ppgtt, base);
	gen8_gtt_pte_t *pt_vaddr, scratch_pte;
	unsigned pdpe = start >> GEN8_PDPE_SHIFT & GEN8_PDPE_MASK;
	unsigned pde = start >> GEN8_PDE_SHIFT & GEN8_PDE_MASK;
	unsigned pte = start >> GEN8_PTE_SHIFT & GEN8_PTE_MASK;
	unsigned num_entries = length >> PAGE_SHIFT;
	unsigned last_pte, i;

	scratch_pte = gen8_pte_encode(ppgtt->base.scratch.addr,
				      I915_CACHE_LLC, use_scratch);

	while (num_entries) {
		struct page *page_table = ppgtt->gen8_pt_pages[pdpe][pde];

		last_pte = pte + num_entries;
		if (last_pte > GEN8_PTES_PER_PAGE)
			last_pte = GEN8_PTES_PER_PAGE;

		pt_vaddr = kmap_atomic(page_table);

		for (i = pte; i < last_pte; i++) {
			pt_vaddr[i] = scratch_pte;
			num_entries--;
		}

		if (!HAS_LLC(ppgtt->base.dev))
			drm_clflush_virt_range(pt_vaddr, PAGE_SIZE);
		kunmap_atomic(pt_vaddr);

		pte = 0;
		if (++pde == GEN8_PDES_PER_PAGE) {
			pdpe++;
			pde = 0;
		}
	}
}

static void gen8_ppgtt_insert_entries(struct i915_address_space *vm,
				      struct sg_table *pages,
				      uint64_t start,
				      enum i915_cache_level cache_level, u32 unused)
{
	struct i915_hw_ppgtt *ppgtt =
		container_of(vm, struct i915_hw_ppgtt, base);
	gen8_gtt_pte_t *pt_vaddr;
	unsigned pdpe = start >> GEN8_PDPE_SHIFT & GEN8_PDPE_MASK;
	unsigned pde = start >> GEN8_PDE_SHIFT & GEN8_PDE_MASK;
	unsigned pte = start >> GEN8_PTE_SHIFT & GEN8_PTE_MASK;
	struct sg_page_iter sg_iter;

	pt_vaddr = NULL;

	for_each_sg_page(pages->sgl, &sg_iter, pages->nents, 0) {
		if (WARN_ON(pdpe >= GEN8_LEGACY_PDPS))
			break;

		if (pt_vaddr == NULL)
			pt_vaddr = kmap_atomic(ppgtt->gen8_pt_pages[pdpe][pde]);

		pt_vaddr[pte] =
			gen8_pte_encode(sg_page_iter_dma_address(&sg_iter),
					cache_level, true);
		if (++pte == GEN8_PTES_PER_PAGE) {
			if (!HAS_LLC(ppgtt->base.dev))
				drm_clflush_virt_range(pt_vaddr, PAGE_SIZE);
			kunmap_atomic(pt_vaddr);
			pt_vaddr = NULL;
			if (++pde == GEN8_PDES_PER_PAGE) {
				pdpe++;
				pde = 0;
			}
			pte = 0;
		}
	}
	if (pt_vaddr) {
		if (!HAS_LLC(ppgtt->base.dev))
			drm_clflush_virt_range(pt_vaddr, PAGE_SIZE);
		kunmap_atomic(pt_vaddr);
	}
}

static void gen8_free_page_tables(struct page **pt_pages)
{
	int i;

	if (pt_pages == NULL)
		return;

	for (i = 0; i < GEN8_PDES_PER_PAGE; i++)
		if (pt_pages[i])
			__free_pages(pt_pages[i], 0);
}

static void gen8_ppgtt_free(const struct i915_hw_ppgtt *ppgtt)
{
	int i;

	for (i = 0; i < ppgtt->num_pd_pages; i++) {
		gen8_free_page_tables(ppgtt->gen8_pt_pages[i]);
		kfree(ppgtt->gen8_pt_pages[i]);
		kfree(ppgtt->gen8_pt_dma_addr[i]);
	}

	__free_pages(ppgtt->pd_pages, get_order(ppgtt->num_pd_pages << PAGE_SHIFT));
}

static void gen8_ppgtt_unmap_pages(struct i915_hw_ppgtt *ppgtt)
{
	struct pci_dev *hwdev = ppgtt->base.dev->pdev;
	int i, j;

	for (i = 0; i < ppgtt->num_pd_pages; i++) {
		/* TODO: In the future we'll support sparse mappings, so this
		 * will have to change. */
		if (!ppgtt->pd_dma_addr[i])
			continue;

		pci_unmap_page(hwdev, ppgtt->pd_dma_addr[i], PAGE_SIZE,
			       PCI_DMA_BIDIRECTIONAL);

		for (j = 0; j < GEN8_PDES_PER_PAGE; j++) {
			dma_addr_t addr = ppgtt->gen8_pt_dma_addr[i][j];
			if (addr)
				pci_unmap_page(hwdev, addr, PAGE_SIZE,
					       PCI_DMA_BIDIRECTIONAL);
		}
	}
}

static void gen8_ppgtt_cleanup(struct i915_address_space *vm)
{
	struct i915_hw_ppgtt *ppgtt =
		container_of(vm, struct i915_hw_ppgtt, base);

	list_del(&vm->global_link);
	drm_mm_takedown(&vm->mm);

	gen8_ppgtt_unmap_pages(ppgtt);
	gen8_ppgtt_free(ppgtt);
}

static struct page **__gen8_alloc_page_tables(void)
{
	struct page **pt_pages;
	int i;

	pt_pages = kcalloc(GEN8_PDES_PER_PAGE, sizeof(struct page *), GFP_KERNEL);
	if (!pt_pages)
		return ERR_PTR(-ENOMEM);

	for (i = 0; i < GEN8_PDES_PER_PAGE; i++) {
		pt_pages[i] = alloc_page(GFP_KERNEL);
		if (!pt_pages[i])
			goto bail;
	}

	return pt_pages;

bail:
	gen8_free_page_tables(pt_pages);
	kfree(pt_pages);
	return ERR_PTR(-ENOMEM);
}

static int gen8_ppgtt_allocate_page_tables(struct i915_hw_ppgtt *ppgtt,
					   const int max_pdp)
{
	struct page **pt_pages[GEN8_LEGACY_PDPS];
	int i, ret;

	for (i = 0; i < max_pdp; i++) {
		pt_pages[i] = __gen8_alloc_page_tables();
		if (IS_ERR(pt_pages[i])) {
			ret = PTR_ERR(pt_pages[i]);
			goto unwind_out;
		}
	}

	/* NB: Avoid touching gen8_pt_pages until last to keep the allocation,
	 * "atomic" - for cleanup purposes.
	 */
	for (i = 0; i < max_pdp; i++)
		ppgtt->gen8_pt_pages[i] = pt_pages[i];

	return 0;

unwind_out:
	while (i--) {
		gen8_free_page_tables(pt_pages[i]);
		kfree(pt_pages[i]);
	}

	return ret;
}

static int gen8_ppgtt_allocate_dma(struct i915_hw_ppgtt *ppgtt)
{
	int i;

	for (i = 0; i < ppgtt->num_pd_pages; i++) {
		ppgtt->gen8_pt_dma_addr[i] = kcalloc(GEN8_PDES_PER_PAGE,
						     sizeof(dma_addr_t),
						     GFP_KERNEL);
		if (!ppgtt->gen8_pt_dma_addr[i])
			return -ENOMEM;
	}

	return 0;
}

static int gen8_ppgtt_allocate_page_directories(struct i915_hw_ppgtt *ppgtt,
						const int max_pdp)
{
	ppgtt->pd_pages = alloc_pages(GFP_KERNEL, get_order(max_pdp << PAGE_SHIFT));
	if (!ppgtt->pd_pages)
		return -ENOMEM;

	ppgtt->num_pd_pages = 1 << get_order(max_pdp << PAGE_SHIFT);
	BUG_ON(ppgtt->num_pd_pages > GEN8_LEGACY_PDPS);

	return 0;
}

static int gen8_ppgtt_alloc(struct i915_hw_ppgtt *ppgtt,
			    const int max_pdp)
{
	int ret;

	ret = gen8_ppgtt_allocate_page_directories(ppgtt, max_pdp);
	if (ret)
		return ret;

	ret = gen8_ppgtt_allocate_page_tables(ppgtt, max_pdp);
	if (ret) {
		__free_pages(ppgtt->pd_pages, get_order(max_pdp << PAGE_SHIFT));
		return ret;
	}

	ppgtt->num_pd_entries = max_pdp * GEN8_PDES_PER_PAGE;

	ret = gen8_ppgtt_allocate_dma(ppgtt);
	if (ret)
		gen8_ppgtt_free(ppgtt);

	return ret;
}

static int gen8_ppgtt_setup_page_directories(struct i915_hw_ppgtt *ppgtt,
					     const int pd)
{
	dma_addr_t pd_addr;
	int ret;

	pd_addr = pci_map_page(ppgtt->base.dev->pdev,
			       &ppgtt->pd_pages[pd], 0,
			       PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);

	ret = pci_dma_mapping_error(ppgtt->base.dev->pdev, pd_addr);
	if (ret)
		return ret;

	ppgtt->pd_dma_addr[pd] = pd_addr;

	return 0;
}

static int gen8_ppgtt_setup_page_tables(struct i915_hw_ppgtt *ppgtt,
					const int pd,
					const int pt)
{
	dma_addr_t pt_addr;
	struct page *p;
	int ret;

	p = ppgtt->gen8_pt_pages[pd][pt];
	pt_addr = pci_map_page(ppgtt->base.dev->pdev,
			       p, 0, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
	ret = pci_dma_mapping_error(ppgtt->base.dev->pdev, pt_addr);
	if (ret)
		return ret;

	ppgtt->gen8_pt_dma_addr[pd][pt] = pt_addr;

	return 0;
}

/**
 * GEN8 legacy ppgtt programming is accomplished through a max 4 PDP registers
 * with a net effect resembling a 2-level page table in normal x86 terms. Each
 * PDP represents 1GB of memory 4 * 512 * 512 * 4096 = 4GB legacy 32b address
 * space.
 *
 * FIXME: split allocation into smaller pieces. For now we only ever do this
 * once, but with full PPGTT, the multiple contiguous allocations will be bad.
 * TODO: Do something with the size parameter
 */
static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size)
{
	const int max_pdp = DIV_ROUND_UP(size, 1 << 30);
	const int min_pt_pages = GEN8_PDES_PER_PAGE * max_pdp;
	int i, j, ret;

	if (size % (1<<30))
		DRM_INFO("Pages will be wasted unless GTT size (%llu) is divisible by 1GB\n", size);

	/* 1. Do all our allocations for page directories and page tables. */
	ret = gen8_ppgtt_alloc(ppgtt, max_pdp);
	if (ret)
		return ret;

	/*
	 * 2. Create DMA mappings for the page directories and page tables.
	 */
	for (i = 0; i < max_pdp; i++) {
		ret = gen8_ppgtt_setup_page_directories(ppgtt, i);
		if (ret)
			goto bail;

		for (j = 0; j < GEN8_PDES_PER_PAGE; j++) {
			ret = gen8_ppgtt_setup_page_tables(ppgtt, i, j);
			if (ret)
				goto bail;
		}
	}

	/*
	 * 3. Map all the page directory entires to point to the page tables
	 * we've allocated.
	 *
	 * For now, the PPGTT helper functions all require that the PDEs are
	 * plugged in correctly. So we do that now/here. For aliasing PPGTT, we
	 * will never need to touch the PDEs again.
	 */
	for (i = 0; i < max_pdp; i++) {
		gen8_ppgtt_pde_t *pd_vaddr;
		pd_vaddr = kmap_atomic(&ppgtt->pd_pages[i]);
		for (j = 0; j < GEN8_PDES_PER_PAGE; j++) {
			dma_addr_t addr = ppgtt->gen8_pt_dma_addr[i][j];
			pd_vaddr[j] = gen8_pde_encode(ppgtt->base.dev, addr,
						      I915_CACHE_LLC);
		}
		if (!HAS_LLC(ppgtt->base.dev))
			drm_clflush_virt_range(pd_vaddr, PAGE_SIZE);
		kunmap_atomic(pd_vaddr);
	}

	ppgtt->enable = gen8_ppgtt_enable;
	ppgtt->switch_mm = gen8_mm_switch;
	ppgtt->base.clear_range = gen8_ppgtt_clear_range;
	ppgtt->base.insert_entries = gen8_ppgtt_insert_entries;
	ppgtt->base.cleanup = gen8_ppgtt_cleanup;
	ppgtt->base.start = 0;
	ppgtt->base.total = ppgtt->num_pd_entries * GEN8_PTES_PER_PAGE * PAGE_SIZE;

	ppgtt->base.clear_range(&ppgtt->base, 0, ppgtt->base.total, true);

	DRM_DEBUG_DRIVER("Allocated %d pages for page directories (%d wasted)\n",
			 ppgtt->num_pd_pages, ppgtt->num_pd_pages - max_pdp);
	DRM_DEBUG_DRIVER("Allocated %d pages for page tables (%lld wasted)\n",
			 ppgtt->num_pd_entries,
			 (ppgtt->num_pd_entries - min_pt_pages) + size % (1<<30));
	return 0;

bail:
	gen8_ppgtt_unmap_pages(ppgtt);
	gen8_ppgtt_free(ppgtt);
	return ret;
}

static void gen6_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
{
	struct drm_i915_private *dev_priv = ppgtt->base.dev->dev_private;
	struct i915_address_space *vm = &ppgtt->base;
	gen6_gtt_pte_t __iomem *pd_addr;
	gen6_gtt_pte_t scratch_pte;
	uint32_t pd_entry;
	int pte, pde;

	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC, true, 0);

	pd_addr = (gen6_gtt_pte_t __iomem *)dev_priv->gtt.gsm +
		ppgtt->pd_offset / sizeof(gen6_gtt_pte_t);

	seq_printf(m, "  VM %p (pd_offset %x-%x):\n", vm,
		   ppgtt->pd_offset, ppgtt->pd_offset + ppgtt->num_pd_entries);
	for (pde = 0; pde < ppgtt->num_pd_entries; pde++) {
		u32 expected;
		gen6_gtt_pte_t *pt_vaddr;
		dma_addr_t pt_addr = ppgtt->pt_dma_addr[pde];
		pd_entry = readl(pd_addr + pde);
		expected = (GEN6_PDE_ADDR_ENCODE(pt_addr) | GEN6_PDE_VALID);

		if (pd_entry != expected)
			seq_printf(m, "\tPDE #%d mismatch: Actual PDE: %x Expected PDE: %x\n",
				   pde,
				   pd_entry,
				   expected);
		seq_printf(m, "\tPDE: %x\n", pd_entry);

		pt_vaddr = kmap_atomic(ppgtt->pt_pages[pde]);
		for (pte = 0; pte < I915_PPGTT_PT_ENTRIES; pte+=4) {
			unsigned long va =
				(pde * PAGE_SIZE * I915_PPGTT_PT_ENTRIES) +
				(pte * PAGE_SIZE);
			int i;
			bool found = false;
			for (i = 0; i < 4; i++)
				if (pt_vaddr[pte + i] != scratch_pte)
					found = true;
			if (!found)
				continue;

			seq_printf(m, "\t\t0x%lx [%03d,%04d]: =", va, pde, pte);
			for (i = 0; i < 4; i++) {
				if (pt_vaddr[pte + i] != scratch_pte)
					seq_printf(m, " %08x", pt_vaddr[pte + i]);
				else
					seq_puts(m, "  SCRATCH ");
			}
			seq_puts(m, "\n");
		}
		kunmap_atomic(pt_vaddr);
	}
}

static void gen6_write_pdes(struct i915_hw_ppgtt *ppgtt)
{
	struct drm_i915_private *dev_priv = ppgtt->base.dev->dev_private;
	gen6_gtt_pte_t __iomem *pd_addr;
	uint32_t pd_entry;
	int i;

	WARN_ON(ppgtt->pd_offset & 0x3f);
	pd_addr = (gen6_gtt_pte_t __iomem*)dev_priv->gtt.gsm +
		ppgtt->pd_offset / sizeof(gen6_gtt_pte_t);
	for (i = 0; i < ppgtt->num_pd_entries; i++) {
		dma_addr_t pt_addr;

		pt_addr = ppgtt->pt_dma_addr[i];
		pd_entry = GEN6_PDE_ADDR_ENCODE(pt_addr);
		pd_entry |= GEN6_PDE_VALID;

		writel(pd_entry, pd_addr + i);
	}
	readl(pd_addr);
}

static uint32_t get_pd_offset(struct i915_hw_ppgtt *ppgtt)
{
	BUG_ON(ppgtt->pd_offset & 0x3f);

	return (ppgtt->pd_offset / 64) << 16;
}

static int hsw_mm_switch(struct i915_hw_ppgtt *ppgtt,
			 struct intel_engine_cs *ring,
			 bool synchronous)
{
	struct drm_device *dev = ppgtt->base.dev;
	struct drm_i915_private *dev_priv = dev->dev_private;
	int ret;

	/* If we're in reset, we can assume the GPU is sufficiently idle to
	 * manually frob these bits. Ideally we could use the ring functions,
	 * except our error handling makes it quite difficult (can't use
	 * intel_ring_begin, ring->flush, or intel_ring_advance)
	 *
	 * FIXME: We should try not to special case reset
	 */
	if (synchronous ||
	    i915_reset_in_progress(&dev_priv->gpu_error)) {
		WARN_ON(ppgtt != dev_priv->mm.aliasing_ppgtt);
		I915_WRITE(RING_PP_DIR_DCLV(ring), PP_DIR_DCLV_2G);
		I915_WRITE(RING_PP_DIR_BASE(ring), get_pd_offset(ppgtt));
		POSTING_READ(RING_PP_DIR_BASE(ring));
		return 0;
	}

	/* NB: TLBs must be flushed and invalidated before a switch */
	ret = ring->flush(ring, I915_GEM_GPU_DOMAINS, I915_GEM_GPU_DOMAINS);
	if (ret)
		return ret;

	ret = intel_ring_begin(ring, 6);
	if (ret)
		return ret;

	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(2));
	intel_ring_emit(ring, RING_PP_DIR_DCLV(ring));
	intel_ring_emit(ring, PP_DIR_DCLV_2G);
	intel_ring_emit(ring, RING_PP_DIR_BASE(ring));
	intel_ring_emit(ring, get_pd_offset(ppgtt));
	intel_ring_emit(ring, MI_NOOP);
	intel_ring_advance(ring);

	return 0;
}

static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt,
			  struct intel_engine_cs *ring,
			  bool synchronous)
{
	struct drm_device *dev = ppgtt->base.dev;
	struct drm_i915_private *dev_priv = dev->dev_private;
	int ret;

	/* If we're in reset, we can assume the GPU is sufficiently idle to
	 * manually frob these bits. Ideally we could use the ring functions,
	 * except our error handling makes it quite difficult (can't use
	 * intel_ring_begin, ring->flush, or intel_ring_advance)
	 *
	 * FIXME: We should try not to special case reset
	 */
	if (synchronous ||
	    i915_reset_in_progress(&dev_priv->gpu_error)) {
		WARN_ON(ppgtt != dev_priv->mm.aliasing_ppgtt);
		I915_WRITE(RING_PP_DIR_DCLV(ring), PP_DIR_DCLV_2G);
		I915_WRITE(RING_PP_DIR_BASE(ring), get_pd_offset(ppgtt));
		POSTING_READ(RING_PP_DIR_BASE(ring));
		return 0;
	}

	/* NB: TLBs must be flushed and invalidated before a switch */
	ret = ring->flush(ring, I915_GEM_GPU_DOMAINS, I915_GEM_GPU_DOMAINS);
	if (ret)
		return ret;

	ret = intel_ring_begin(ring, 6);
	if (ret)
		return ret;

	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(2));
	intel_ring_emit(ring, RING_PP_DIR_DCLV(ring));
	intel_ring_emit(ring, PP_DIR_DCLV_2G);
	intel_ring_emit(ring, RING_PP_DIR_BASE(ring));
	intel_ring_emit(ring, get_pd_offset(ppgtt));
	intel_ring_emit(ring, MI_NOOP);
	intel_ring_advance(ring);

	/* XXX: RCS is the only one to auto invalidate the TLBs? */
	if (ring->id != RCS) {
		ret = ring->flush(ring, I915_GEM_GPU_DOMAINS, I915_GEM_GPU_DOMAINS);
		if (ret)
			return ret;
	}

	return 0;
}

static int gen6_mm_switch(struct i915_hw_ppgtt *ppgtt,
			  struct intel_engine_cs *ring,
			  bool synchronous)
{
	struct drm_device *dev = ppgtt->base.dev;
	struct drm_i915_private *dev_priv = dev->dev_private;

	if (!synchronous)
		return 0;

	I915_WRITE(RING_PP_DIR_DCLV(ring), PP_DIR_DCLV_2G);
	I915_WRITE(RING_PP_DIR_BASE(ring), get_pd_offset(ppgtt));

	POSTING_READ(RING_PP_DIR_DCLV(ring));

	return 0;
}

static int gen8_ppgtt_enable(struct i915_hw_ppgtt *ppgtt)
{
	struct drm_device *dev = ppgtt->base.dev;
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct intel_engine_cs *ring;
	int j, ret;

	for_each_ring(ring, dev_priv, j) {
		I915_WRITE(RING_MODE_GEN7(ring),
			   _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE));

		/* We promise to do a switch later with FULL PPGTT. If this is
		 * aliasing, this is the one and only switch we'll do */
		if (USES_FULL_PPGTT(dev))
			continue;

		ret = ppgtt->switch_mm(ppgtt, ring, true);
		if (ret)
			goto err_out;
	}

	return 0;

err_out:
	for_each_ring(ring, dev_priv, j)
		I915_WRITE(RING_MODE_GEN7(ring),
			   _MASKED_BIT_DISABLE(GFX_PPGTT_ENABLE));
	return ret;
}

static int gen7_ppgtt_enable(struct i915_hw_ppgtt *ppgtt)
{
	struct drm_device *dev = ppgtt->base.dev;
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct intel_engine_cs *ring;
	uint32_t ecochk, ecobits;
	int i;

	ecobits = I915_READ(GAC_ECO_BITS);
	I915_WRITE(GAC_ECO_BITS, ecobits | ECOBITS_PPGTT_CACHE64B);

	ecochk = I915_READ(GAM_ECOCHK);
	if (IS_HASWELL(dev)) {
		ecochk |= ECOCHK_PPGTT_WB_HSW;
	} else {
		ecochk |= ECOCHK_PPGTT_LLC_IVB;
		ecochk &= ~ECOCHK_PPGTT_GFDT_IVB;
	}
	I915_WRITE(GAM_ECOCHK, ecochk);

	for_each_ring(ring, dev_priv, i) {
		int ret;
		/* GFX_MODE is per-ring on gen7+ */
		I915_WRITE(RING_MODE_GEN7(ring),
			   _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE));

		/* We promise to do a switch later with FULL PPGTT. If this is
		 * aliasing, this is the one and only switch we'll do */
		if (USES_FULL_PPGTT(dev))
			continue;

		ret = ppgtt->switch_mm(ppgtt, ring, true);
		if (ret)
			return ret;
	}

	return 0;
}

static int gen6_ppgtt_enable(struct i915_hw_ppgtt *ppgtt)
{
	struct drm_device *dev = ppgtt->base.dev;
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct intel_engine_cs *ring;
	uint32_t ecochk, gab_ctl, ecobits;
	int i;

	ecobits = I915_READ(GAC_ECO_BITS);
	I915_WRITE(GAC_ECO_BITS, ecobits | ECOBITS_SNB_BIT |
		   ECOBITS_PPGTT_CACHE64B);

	gab_ctl = I915_READ(GAB_CTL);
	I915_WRITE(GAB_CTL, gab_ctl | GAB_CTL_CONT_AFTER_PAGEFAULT);

	ecochk = I915_READ(GAM_ECOCHK);
	I915_WRITE(GAM_ECOCHK, ecochk | ECOCHK_SNB_BIT | ECOCHK_PPGTT_CACHE64B);

	I915_WRITE(GFX_MODE, _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE));

	for_each_ring(ring, dev_priv, i) {
		int ret = ppgtt->switch_mm(ppgtt, ring, true);
		if (ret)
			return ret;
	}

	return 0;
}

/* PPGTT support for Sandybdrige/Gen6 and later */
static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
				   uint64_t start,
				   uint64_t length,
				   bool use_scratch)
{
	struct i915_hw_ppgtt *ppgtt =
		container_of(vm, struct i915_hw_ppgtt, base);
	gen6_gtt_pte_t *pt_vaddr, scratch_pte;
	unsigned first_entry = start >> PAGE_SHIFT;
	unsigned num_entries = length >> PAGE_SHIFT;
	unsigned act_pt = first_entry / I915_PPGTT_PT_ENTRIES;
	unsigned first_pte = first_entry % I915_PPGTT_PT_ENTRIES;
	unsigned last_pte, i;

	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC, true, 0);

	while (num_entries) {
		last_pte = first_pte + num_entries;
		if (last_pte > I915_PPGTT_PT_ENTRIES)
			last_pte = I915_PPGTT_PT_ENTRIES;

		pt_vaddr = kmap_atomic(ppgtt->pt_pages[act_pt]);

		for (i = first_pte; i < last_pte; i++)
			pt_vaddr[i] = scratch_pte;

		kunmap_atomic(pt_vaddr);

		num_entries -= last_pte - first_pte;
		first_pte = 0;
		act_pt++;
	}
}

static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
				      struct sg_table *pages,
				      uint64_t start,
				      enum i915_cache_level cache_level, u32 flags)
{
	struct i915_hw_ppgtt *ppgtt =
		container_of(vm, struct i915_hw_ppgtt, base);
	gen6_gtt_pte_t *pt_vaddr;
	unsigned first_entry = start >> PAGE_SHIFT;
	unsigned act_pt = first_entry / I915_PPGTT_PT_ENTRIES;
	unsigned act_pte = first_entry % I915_PPGTT_PT_ENTRIES;
	struct sg_page_iter sg_iter;

	pt_vaddr = NULL;
	for_each_sg_page(pages->sgl, &sg_iter, pages->nents, 0) {
		if (pt_vaddr == NULL)
			pt_vaddr = kmap_atomic(ppgtt->pt_pages[act_pt]);

		pt_vaddr[act_pte] =
			vm->pte_encode(sg_page_iter_dma_address(&sg_iter),
				       cache_level, true, flags);

		if (++act_pte == I915_PPGTT_PT_ENTRIES) {
			kunmap_atomic(pt_vaddr);
			pt_vaddr = NULL;
			act_pt++;
			act_pte = 0;
		}
	}
	if (pt_vaddr)
		kunmap_atomic(pt_vaddr);
}

static void gen6_ppgtt_unmap_pages(struct i915_hw_ppgtt *ppgtt)
{
	int i;

	if (ppgtt->pt_dma_addr) {
		for (i = 0; i < ppgtt->num_pd_entries; i++)
			pci_unmap_page(ppgtt->base.dev->pdev,
				       ppgtt->pt_dma_addr[i],
				       4096, PCI_DMA_BIDIRECTIONAL);
	}
}

static void gen6_ppgtt_free(struct i915_hw_ppgtt *ppgtt)
{
	int i;

	kfree(ppgtt->pt_dma_addr);
	for (i = 0; i < ppgtt->num_pd_entries; i++)
		__free_page(ppgtt->pt_pages[i]);
	kfree(ppgtt->pt_pages);
}

static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
{
	struct i915_hw_ppgtt *ppgtt =
		container_of(vm, struct i915_hw_ppgtt, base);

	list_del(&vm->global_link);
	drm_mm_takedown(&ppgtt->base.mm);
	drm_mm_remove_node(&ppgtt->node);

	gen6_ppgtt_unmap_pages(ppgtt);
	gen6_ppgtt_free(ppgtt);
}

static int gen6_ppgtt_allocate_page_directories(struct i915_hw_ppgtt *ppgtt)
{
	struct drm_device *dev = ppgtt->base.dev;
	struct drm_i915_private *dev_priv = dev->dev_private;
	bool retried = false;
	int ret;

	/* PPGTT PDEs reside in the GGTT and consists of 512 entries. The
	 * allocator works in address space sizes, so it's multiplied by page
	 * size. We allocate at the top of the GTT to avoid fragmentation.
	 */
	BUG_ON(!drm_mm_initialized(&dev_priv->gtt.base.mm));
alloc:
	ret = drm_mm_insert_node_in_range_generic(&dev_priv->gtt.base.mm,
						  &ppgtt->node, GEN6_PD_SIZE,
						  GEN6_PD_ALIGN, 0,
						  0, dev_priv->gtt.base.total,
						  DRM_MM_TOPDOWN);
	if (ret == -ENOSPC && !retried) {
		ret = i915_gem_evict_something(dev, &dev_priv->gtt.base,
					       GEN6_PD_SIZE, GEN6_PD_ALIGN,
					       I915_CACHE_NONE,
					       0, dev_priv->gtt.base.total,
					       0);
		if (ret)
			return ret;

		retried = true;
		goto alloc;
	}

	if (ppgtt->node.start < dev_priv->gtt.mappable_end)
		DRM_DEBUG("Forced to use aperture for PDEs\n");

	ppgtt->num_pd_entries = GEN6_PPGTT_PD_ENTRIES;
	return ret;
}

static int gen6_ppgtt_allocate_page_tables(struct i915_hw_ppgtt *ppgtt)
{
	int i;

	ppgtt->pt_pages = kcalloc(ppgtt->num_pd_entries, sizeof(struct page *),
				  GFP_KERNEL);

	if (!ppgtt->pt_pages)
		return -ENOMEM;

	for (i = 0; i < ppgtt->num_pd_entries; i++) {
		ppgtt->pt_pages[i] = alloc_page(GFP_KERNEL);
		if (!ppgtt->pt_pages[i]) {
			gen6_ppgtt_free(ppgtt);
			return -ENOMEM;
		}
	}

	return 0;
}

static int gen6_ppgtt_alloc(struct i915_hw_ppgtt *ppgtt)
{
	int ret;

	ret = gen6_ppgtt_allocate_page_directories(ppgtt);
	if (ret)
		return ret;

	ret = gen6_ppgtt_allocate_page_tables(ppgtt);
	if (ret) {
		drm_mm_remove_node(&ppgtt->node);
		return ret;
	}

	ppgtt->pt_dma_addr = kcalloc(ppgtt->num_pd_entries, sizeof(dma_addr_t),
				     GFP_KERNEL);
	if (!ppgtt->pt_dma_addr) {
		drm_mm_remove_node(&ppgtt->node);
		gen6_ppgtt_free(ppgtt);
		return -ENOMEM;
	}

	return 0;
}

static int gen6_ppgtt_setup_page_tables(struct i915_hw_ppgtt *ppgtt)
{
	struct drm_device *dev = ppgtt->base.dev;
	int i;

	for (i = 0; i < ppgtt->num_pd_entries; i++) {
		dma_addr_t pt_addr;

		pt_addr = pci_map_page(dev->pdev, ppgtt->pt_pages[i], 0, 4096,
				       PCI_DMA_BIDIRECTIONAL);

		if (pci_dma_mapping_error(dev->pdev, pt_addr)) {
			gen6_ppgtt_unmap_pages(ppgtt);
			return -EIO;
		}

		ppgtt->pt_dma_addr[i] = pt_addr;
	}

	return 0;
}

static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
{
	struct drm_device *dev = ppgtt->base.dev;
	struct drm_i915_private *dev_priv = dev->dev_private;
	int ret;

	ppgtt->base.pte_encode = dev_priv->gtt.base.pte_encode;
	if (IS_GEN6(dev)) {
		ppgtt->enable = gen6_ppgtt_enable;
		ppgtt->switch_mm = gen6_mm_switch;
	} else if (IS_HASWELL(dev)) {
		ppgtt->enable = gen7_ppgtt_enable;
		ppgtt->switch_mm = hsw_mm_switch;
	} else if (IS_GEN7(dev)) {
		ppgtt->enable = gen7_ppgtt_enable;
		ppgtt->switch_mm = gen7_mm_switch;
	} else
		BUG();

	ret = gen6_ppgtt_alloc(ppgtt);
	if (ret)
		return ret;

	ret = gen6_ppgtt_setup_page_tables(ppgtt);
	if (ret) {
		gen6_ppgtt_free(ppgtt);
		return ret;
	}

	ppgtt->base.clear_range = gen6_ppgtt_clear_range;
	ppgtt->base.insert_entries = gen6_ppgtt_insert_entries;
	ppgtt->base.cleanup = gen6_ppgtt_cleanup;
	ppgtt->base.start = 0;
	ppgtt->base.total =  ppgtt->num_pd_entries * I915_PPGTT_PT_ENTRIES * PAGE_SIZE;
	ppgtt->debug_dump = gen6_dump_ppgtt;

	ppgtt->pd_offset =
		ppgtt->node.start / PAGE_SIZE * sizeof(gen6_gtt_pte_t);

	ppgtt->base.clear_range(&ppgtt->base, 0, ppgtt->base.total, true);

	DRM_DEBUG_DRIVER("Allocated pde space (%ldM) at GTT entry: %lx\n",
			 ppgtt->node.size >> 20,
			 ppgtt->node.start / PAGE_SIZE);

	return 0;
}

int i915_gem_init_ppgtt(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	int ret = 0;

	ppgtt->base.dev = dev;
	ppgtt->base.scratch = dev_priv->gtt.base.scratch;

	if (INTEL_INFO(dev)->gen < 8)
		ret = gen6_ppgtt_init(ppgtt);
	else if (IS_GEN8(dev))
		ret = gen8_ppgtt_init(ppgtt, dev_priv->gtt.base.total);
	else
		BUG();

	if (!ret) {
		struct drm_i915_private *dev_priv = dev->dev_private;
		kref_init(&ppgtt->ref);
		drm_mm_init(&ppgtt->base.mm, ppgtt->base.start,
			    ppgtt->base.total);
		i915_init_vm(dev_priv, &ppgtt->base);
		if (INTEL_INFO(dev)->gen < 8) {
			gen6_write_pdes(ppgtt);
			DRM_DEBUG("Adding PPGTT at offset %x\n",
				  ppgtt->pd_offset << 10);
		}
	}

	return ret;
}

static void
ppgtt_bind_vma(struct i915_vma *vma,
	       enum i915_cache_level cache_level,
	       u32 flags)
{
	/* Currently applicable only to VLV */
	if (vma->obj->gt_ro)
		flags |= PTE_READ_ONLY;

	vma->vm->insert_entries(vma->vm, vma->obj->pages, vma->node.start,
				cache_level, flags);
}

static void ppgtt_unbind_vma(struct i915_vma *vma)
{
	vma->vm->clear_range(vma->vm,
			     vma->node.start,
			     vma->obj->base.size,
			     true);
}

extern int intel_iommu_gfx_mapped;
/* Certain Gen5 chipsets require require idling the GPU before
 * unmapping anything from the GTT when VT-d is enabled.
 */
static inline bool needs_idle_maps(struct drm_device *dev)
{
#ifdef CONFIG_INTEL_IOMMU
	/* Query intel_iommu to see if we need the workaround. Presumably that
	 * was loaded first.
	 */
	if (IS_GEN5(dev) && IS_MOBILE(dev) && intel_iommu_gfx_mapped)
		return true;
#endif
	return false;
}

static bool do_idling(struct drm_i915_private *dev_priv)
{
	bool ret = dev_priv->mm.interruptible;

	if (unlikely(dev_priv->gtt.do_idle_maps)) {
		dev_priv->mm.interruptible = false;
		if (i915_gpu_idle(dev_priv->dev)) {
			DRM_ERROR("Couldn't idle GPU\n");
			/* Wait a bit, in hopes it avoids the hang */
			udelay(10);
		}
	}

	return ret;
}

static void undo_idling(struct drm_i915_private *dev_priv, bool interruptible)
{
	if (unlikely(dev_priv->gtt.do_idle_maps))
		dev_priv->mm.interruptible = interruptible;
}

void i915_check_and_clear_faults(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct intel_engine_cs *ring;
	int i;

	if (INTEL_INFO(dev)->gen < 6)
		return;

	for_each_ring(ring, dev_priv, i) {
		u32 fault_reg;
		fault_reg = I915_READ(RING_FAULT_REG(ring));
		if (fault_reg & RING_FAULT_VALID) {
			DRM_DEBUG_DRIVER("Unexpected fault\n"
					 "\tAddr: 0x%08lx\\n"
					 "\tAddress space: %s\n"
					 "\tSource ID: %d\n"
					 "\tType: %d\n",
					 fault_reg & PAGE_MASK,
					 fault_reg & RING_FAULT_GTTSEL_MASK ? "GGTT" : "PPGTT",
					 RING_FAULT_SRCID(fault_reg),
					 RING_FAULT_FAULT_TYPE(fault_reg));
			I915_WRITE(RING_FAULT_REG(ring),
				   fault_reg & ~RING_FAULT_VALID);
		}
	}
	POSTING_READ(RING_FAULT_REG(&dev_priv->ring[RCS]));
}

void i915_gem_suspend_gtt_mappings(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = dev->dev_private;

	/* Don't bother messing with faults pre GEN6 as we have little
	 * documentation supporting that it's a good idea.
	 */
	if (INTEL_INFO(dev)->gen < 6)
		return;

	i915_check_and_clear_faults(dev);

	dev_priv->gtt.base.clear_range(&dev_priv->gtt.base,
				       dev_priv->gtt.base.start,
				       dev_priv->gtt.base.total,
				       true);
}

void i915_gem_restore_gtt_mappings(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct drm_i915_gem_object *obj;
	struct i915_address_space *vm;

	i915_check_and_clear_faults(dev);

	/* First fill our portion of the GTT with scratch pages */
	dev_priv->gtt.base.clear_range(&dev_priv->gtt.base,
				       dev_priv->gtt.base.start,
				       dev_priv->gtt.base.total,
				       true);

	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
		struct i915_vma *vma = i915_gem_obj_to_vma(obj,
							   &dev_priv->gtt.base);
		if (!vma)
			continue;

		i915_gem_clflush_object(obj, obj->pin_display);
		/* The bind_vma code tries to be smart about tracking mappings.
		 * Unfortunately above, we've just wiped out the mappings
		 * without telling our object about it. So we need to fake it.
		 */
		obj->has_global_gtt_mapping = 0;
		vma->bind_vma(vma, obj->cache_level, GLOBAL_BIND);
	}


	if (INTEL_INFO(dev)->gen >= 8) {
		if (IS_CHERRYVIEW(dev))
			chv_setup_private_ppat(dev_priv);
		else
			bdw_setup_private_ppat(dev_priv);

		return;
	}

	list_for_each_entry(vm, &dev_priv->vm_list, global_link) {
		/* TODO: Perhaps it shouldn't be gen6 specific */
		if (i915_is_ggtt(vm)) {
			if (dev_priv->mm.aliasing_ppgtt)
				gen6_write_pdes(dev_priv->mm.aliasing_ppgtt);
			continue;
		}

		gen6_write_pdes(container_of(vm, struct i915_hw_ppgtt, base));
	}

	i915_gem_chipset_flush(dev);
}

int i915_gem_gtt_prepare_object(struct drm_i915_gem_object *obj)
{
	if (obj->has_dma_mapping)
		return 0;

	if (!dma_map_sg(&obj->base.dev->pdev->dev,
			obj->pages->sgl, obj->pages->nents,
			PCI_DMA_BIDIRECTIONAL))
		return -ENOSPC;

	return 0;
}

static inline void gen8_set_pte(void __iomem *addr, gen8_gtt_pte_t pte)
{
#ifdef writeq
	writeq(pte, addr);
#else
	iowrite32((u32)pte, addr);
	iowrite32(pte >> 32, addr + 4);
#endif
}

static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
				     struct sg_table *st,
				     uint64_t start,
				     enum i915_cache_level level, u32 unused)
{
	struct drm_i915_private *dev_priv = vm->dev->dev_private;
	unsigned first_entry = start >> PAGE_SHIFT;
	gen8_gtt_pte_t __iomem *gtt_entries =
		(gen8_gtt_pte_t __iomem *)dev_priv->gtt.gsm + first_entry;
	int i = 0;
	struct sg_page_iter sg_iter;
	dma_addr_t addr = 0; /* shut up gcc */

	for_each_sg_page(st->sgl, &sg_iter, st->nents, 0) {
		addr = sg_dma_address(sg_iter.sg) +
			(sg_iter.sg_pgoffset << PAGE_SHIFT);
		gen8_set_pte(&gtt_entries[i],
			     gen8_pte_encode(addr, level, true));
		i++;
	}

	/*
	 * XXX: This serves as a posting read to make sure that the PTE has
	 * actually been updated. There is some concern that even though
	 * registers and PTEs are within the same BAR that they are potentially
	 * of NUMA access patterns. Therefore, even with the way we assume
	 * hardware should work, we must keep this posting read for paranoia.
	 */
	if (i != 0)
		WARN_ON(readq(&gtt_entries[i-1])
			!= gen8_pte_encode(addr, level, true));

	/* This next bit makes the above posting read even more important. We
	 * want to flush the TLBs only after we're certain all the PTE updates
	 * have finished.
	 */
	I915_WRITE(GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
	POSTING_READ(GFX_FLSH_CNTL_GEN6);
}

/*
 * Binds an object into the global gtt with the specified cache level. The object
 * will be accessible to the GPU via commands whose operands reference offsets
 * within the global GTT as well as accessible by the GPU through the GMADR
 * mapped BAR (dev_priv->mm.gtt->gtt).
 */
static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
				     struct sg_table *st,
				     uint64_t start,
				     enum i915_cache_level level, u32 flags)
{
	struct drm_i915_private *dev_priv = vm->dev->dev_private;
	unsigned first_entry = start >> PAGE_SHIFT;
	gen6_gtt_pte_t __iomem *gtt_entries =
		(gen6_gtt_pte_t __iomem *)dev_priv->gtt.gsm + first_entry;
	int i = 0;
	struct sg_page_iter sg_iter;
	dma_addr_t addr = 0;

	for_each_sg_page(st->sgl, &sg_iter, st->nents, 0) {
		addr = sg_page_iter_dma_address(&sg_iter);
		iowrite32(vm->pte_encode(addr, level, true, flags), &gtt_entries[i]);
		i++;
	}

	/* XXX: This serves as a posting read to make sure that the PTE has
	 * actually been updated. There is some concern that even though
	 * registers and PTEs are within the same BAR that they are potentially
	 * of NUMA access patterns. Therefore, even with the way we assume
	 * hardware should work, we must keep this posting read for paranoia.
	 */
	if (i != 0) {
		unsigned long gtt = readl(&gtt_entries[i-1]);
		WARN_ON(gtt != vm->pte_encode(addr, level, true, flags));
	}

	/* This next bit makes the above posting read even more important. We
	 * want to flush the TLBs only after we're certain all the PTE updates
	 * have finished.
	 */
	I915_WRITE(GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
	POSTING_READ(GFX_FLSH_CNTL_GEN6);
}

static void gen8_ggtt_clear_range(struct i915_address_space *vm,
				  uint64_t start,
				  uint64_t length,
				  bool use_scratch)
{
	struct drm_i915_private *dev_priv = vm->dev->dev_private;
	unsigned first_entry = start >> PAGE_SHIFT;
	unsigned num_entries = length >> PAGE_SHIFT;
	gen8_gtt_pte_t scratch_pte, __iomem *gtt_base =
		(gen8_gtt_pte_t __iomem *) dev_priv->gtt.gsm + first_entry;
	const int max_entries = gtt_total_entries(dev_priv->gtt) - first_entry;
	int i;

	if (WARN(num_entries > max_entries,
		 "First entry = %d; Num entries = %d (max=%d)\n",
		 first_entry, num_entries, max_entries))
		num_entries = max_entries;

	scratch_pte = gen8_pte_encode(vm->scratch.addr,
				      I915_CACHE_LLC,
				      use_scratch);
	for (i = 0; i < num_entries; i++)
		gen8_set_pte(&gtt_base[i], scratch_pte);
	readl(gtt_base);
}

static void gen6_ggtt_clear_range(struct i915_address_space *vm,
				  uint64_t start,
				  uint64_t length,
				  bool use_scratch)
{
	struct drm_i915_private *dev_priv = vm->dev->dev_private;
	unsigned first_entry = start >> PAGE_SHIFT;
	unsigned num_entries = length >> PAGE_SHIFT;
	gen6_gtt_pte_t scratch_pte, __iomem *gtt_base =
		(gen6_gtt_pte_t __iomem *) dev_priv->gtt.gsm + first_entry;
	const int max_entries = gtt_total_entries(dev_priv->gtt) - first_entry;
	int i;

	if (WARN(num_entries > max_entries,
		 "First entry = %d; Num entries = %d (max=%d)\n",
		 first_entry, num_entries, max_entries))
		num_entries = max_entries;

	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC, use_scratch, 0);

	for (i = 0; i < num_entries; i++)
		iowrite32(scratch_pte, &gtt_base[i]);
	readl(gtt_base);
}


static void i915_ggtt_bind_vma(struct i915_vma *vma,
			       enum i915_cache_level cache_level,
			       u32 unused)
{
	const unsigned long entry = vma->node.start >> PAGE_SHIFT;
	unsigned int flags = (cache_level == I915_CACHE_NONE) ?
		AGP_USER_MEMORY : AGP_USER_CACHED_MEMORY;

	BUG_ON(!i915_is_ggtt(vma->vm));
	intel_gtt_insert_sg_entries(vma->obj->pages, entry, flags);
	vma->obj->has_global_gtt_mapping = 1;
}

static void i915_ggtt_clear_range(struct i915_address_space *vm,
				  uint64_t start,
				  uint64_t length,
				  bool unused)
{
	unsigned first_entry = start >> PAGE_SHIFT;
	unsigned num_entries = length >> PAGE_SHIFT;
	intel_gtt_clear_range(first_entry, num_entries);
}

static void i915_ggtt_unbind_vma(struct i915_vma *vma)
{
	const unsigned int first = vma->node.start >> PAGE_SHIFT;
	const unsigned int size = vma->obj->base.size >> PAGE_SHIFT;

	BUG_ON(!i915_is_ggtt(vma->vm));
	vma->obj->has_global_gtt_mapping = 0;
	intel_gtt_clear_range(first, size);
}

static void ggtt_bind_vma(struct i915_vma *vma,
			  enum i915_cache_level cache_level,
			  u32 flags)
{
	struct drm_device *dev = vma->vm->dev;
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct drm_i915_gem_object *obj = vma->obj;

	/* Currently applicable only to VLV */
	if (obj->gt_ro)
		flags |= PTE_READ_ONLY;

	/* If there is no aliasing PPGTT, or the caller needs a global mapping,
	 * or we have a global mapping already but the cacheability flags have
	 * changed, set the global PTEs.
	 *
	 * If there is an aliasing PPGTT it is anecdotally faster, so use that
	 * instead if none of the above hold true.
	 *
	 * NB: A global mapping should only be needed for special regions like
	 * "gtt mappable", SNB errata, or if specified via special execbuf
	 * flags. At all other times, the GPU will use the aliasing PPGTT.
	 */
	if (!dev_priv->mm.aliasing_ppgtt || flags & GLOBAL_BIND) {
		if (!obj->has_global_gtt_mapping ||
		    (cache_level != obj->cache_level)) {
			vma->vm->insert_entries(vma->vm, obj->pages,
						vma->node.start,
						cache_level, flags);
			obj->has_global_gtt_mapping = 1;
		}
	}

	if (dev_priv->mm.aliasing_ppgtt &&
	    (!obj->has_aliasing_ppgtt_mapping ||
	     (cache_level != obj->cache_level))) {
		struct i915_hw_ppgtt *appgtt = dev_priv->mm.aliasing_ppgtt;
		appgtt->base.insert_entries(&appgtt->base,
					    vma->obj->pages,
					    vma->node.start,
					    cache_level, flags);
		vma->obj->has_aliasing_ppgtt_mapping = 1;
	}
}

static void ggtt_unbind_vma(struct i915_vma *vma)
{
	struct drm_device *dev = vma->vm->dev;
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct drm_i915_gem_object *obj = vma->obj;

	if (obj->has_global_gtt_mapping) {
		vma->vm->clear_range(vma->vm,
				     vma->node.start,
				     obj->base.size,
				     true);
		obj->has_global_gtt_mapping = 0;
	}

	if (obj->has_aliasing_ppgtt_mapping) {
		struct i915_hw_ppgtt *appgtt = dev_priv->mm.aliasing_ppgtt;
		appgtt->base.clear_range(&appgtt->base,
					 vma->node.start,
					 obj->base.size,
					 true);
		obj->has_aliasing_ppgtt_mapping = 0;
	}
}

void i915_gem_gtt_finish_object(struct drm_i915_gem_object *obj)
{
	struct drm_device *dev = obj->base.dev;
	struct drm_i915_private *dev_priv = dev->dev_private;
	bool interruptible;

	interruptible = do_idling(dev_priv);

	if (!obj->has_dma_mapping)
		dma_unmap_sg(&dev->pdev->dev,
			     obj->pages->sgl, obj->pages->nents,
			     PCI_DMA_BIDIRECTIONAL);

	undo_idling(dev_priv, interruptible);
}

static void i915_gtt_color_adjust(struct drm_mm_node *node,
				  unsigned long color,
				  unsigned long *start,
				  unsigned long *end)
{
	if (node->color != color)
		*start += 4096;

	if (!list_empty(&node->node_list)) {
		node = list_entry(node->node_list.next,
				  struct drm_mm_node,
				  node_list);
		if (node->allocated && node->color != color)
			*end -= 4096;
	}
}

void i915_gem_setup_global_gtt(struct drm_device *dev,
			       unsigned long start,
			       unsigned long mappable_end,
			       unsigned long end)
{
	/* Let GEM Manage all of the aperture.
	 *
	 * However, leave one page at the end still bound to the scratch page.
	 * There are a number of places where the hardware apparently prefetches
	 * past the end of the object, and we've seen multiple hangs with the
	 * GPU head pointer stuck in a batchbuffer bound at the last page of the
	 * aperture.  One page should be enough to keep any prefetching inside
	 * of the aperture.
	 */
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct i915_address_space *ggtt_vm = &dev_priv->gtt.base;
	struct drm_mm_node *entry;
	struct drm_i915_gem_object *obj;
	unsigned long hole_start, hole_end;

	BUG_ON(mappable_end > end);

	/* Subtract the guard page ... */
	drm_mm_init(&ggtt_vm->mm, start, end - start - PAGE_SIZE);
	if (!HAS_LLC(dev))
		dev_priv->gtt.base.mm.color_adjust = i915_gtt_color_adjust;

	/* Mark any preallocated objects as occupied */
	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
		struct i915_vma *vma = i915_gem_obj_to_vma(obj, ggtt_vm);
		int ret;
		DRM_DEBUG_KMS("reserving preallocated space: %lx + %zx\n",
			      i915_gem_obj_ggtt_offset(obj), obj->base.size);

		WARN_ON(i915_gem_obj_ggtt_bound(obj));
		ret = drm_mm_reserve_node(&ggtt_vm->mm, &vma->node);
		if (ret)
			DRM_DEBUG_KMS("Reservation failed\n");
		obj->has_global_gtt_mapping = 1;
	}

	dev_priv->gtt.base.start = start;
	dev_priv->gtt.base.total = end - start;

	/* Clear any non-preallocated blocks */
	drm_mm_for_each_hole(entry, &ggtt_vm->mm, hole_start, hole_end) {
		DRM_DEBUG_KMS("clearing unused GTT space: [%lx, %lx]\n",
			      hole_start, hole_end);
		ggtt_vm->clear_range(ggtt_vm, hole_start,
				     hole_end - hole_start, true);
	}

	/* And finally clear the reserved guard page */
	ggtt_vm->clear_range(ggtt_vm, end - PAGE_SIZE, PAGE_SIZE, true);
}

void i915_gem_init_global_gtt(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	unsigned long gtt_size, mappable_size;

	gtt_size = dev_priv->gtt.base.total;
	mappable_size = dev_priv->gtt.mappable_end;

	i915_gem_setup_global_gtt(dev, 0, mappable_size, gtt_size);
}

static int setup_scratch_page(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct page *page;
	dma_addr_t dma_addr;

	page = alloc_page(GFP_KERNEL | GFP_DMA32 | __GFP_ZERO);
	if (page == NULL)
		return -ENOMEM;
	get_page(page);
	set_pages_uc(page, 1);

#ifdef CONFIG_INTEL_IOMMU
	dma_addr = pci_map_page(dev->pdev, page, 0, PAGE_SIZE,
				PCI_DMA_BIDIRECTIONAL);
	if (pci_dma_mapping_error(dev->pdev, dma_addr))
		return -EINVAL;
#else
	dma_addr = page_to_phys(page);
#endif
	dev_priv->gtt.base.scratch.page = page;
	dev_priv->gtt.base.scratch.addr = dma_addr;

	return 0;
}

static void teardown_scratch_page(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct page *page = dev_priv->gtt.base.scratch.page;

	set_pages_wb(page, 1);
	pci_unmap_page(dev->pdev, dev_priv->gtt.base.scratch.addr,
		       PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
	put_page(page);
	__free_page(page);
}

static inline unsigned int gen6_get_total_gtt_size(u16 snb_gmch_ctl)
{
	snb_gmch_ctl >>= SNB_GMCH_GGMS_SHIFT;
	snb_gmch_ctl &= SNB_GMCH_GGMS_MASK;
	return snb_gmch_ctl << 20;
}

static inline unsigned int gen8_get_total_gtt_size(u16 bdw_gmch_ctl)
{
	bdw_gmch_ctl >>= BDW_GMCH_GGMS_SHIFT;
	bdw_gmch_ctl &= BDW_GMCH_GGMS_MASK;
	if (bdw_gmch_ctl)
		bdw_gmch_ctl = 1 << bdw_gmch_ctl;

#ifdef CONFIG_X86_32
	/* Limit 32b platforms to a 2GB GGTT: 4 << 20 / pte size * PAGE_SIZE */
	if (bdw_gmch_ctl > 4)
		bdw_gmch_ctl = 4;
#endif

	return bdw_gmch_ctl << 20;
}

static inline unsigned int chv_get_total_gtt_size(u16 gmch_ctrl)
{
	gmch_ctrl >>= SNB_GMCH_GGMS_SHIFT;
	gmch_ctrl &= SNB_GMCH_GGMS_MASK;

	if (gmch_ctrl)
		return 1 << (20 + gmch_ctrl);

	return 0;
}

static inline size_t gen6_get_stolen_size(u16 snb_gmch_ctl)
{
	snb_gmch_ctl >>= SNB_GMCH_GMS_SHIFT;
	snb_gmch_ctl &= SNB_GMCH_GMS_MASK;
	return snb_gmch_ctl << 25; /* 32 MB units */
}

static inline size_t gen8_get_stolen_size(u16 bdw_gmch_ctl)
{
	bdw_gmch_ctl >>= BDW_GMCH_GMS_SHIFT;
	bdw_gmch_ctl &= BDW_GMCH_GMS_MASK;
	return bdw_gmch_ctl << 25; /* 32 MB units */
}

static size_t chv_get_stolen_size(u16 gmch_ctrl)
{
	gmch_ctrl >>= SNB_GMCH_GMS_SHIFT;
	gmch_ctrl &= SNB_GMCH_GMS_MASK;

	/*
	 * 0x0  to 0x10: 32MB increments starting at 0MB
	 * 0x11 to 0x16: 4MB increments starting at 8MB
	 * 0x17 to 0x1d: 4MB increments start at 36MB
	 */
	if (gmch_ctrl < 0x11)
		return gmch_ctrl << 25;
	else if (gmch_ctrl < 0x17)
		return (gmch_ctrl - 0x11 + 2) << 22;
	else
		return (gmch_ctrl - 0x17 + 9) << 22;
}

static int ggtt_probe_common(struct drm_device *dev,
			     size_t gtt_size)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	phys_addr_t gtt_phys_addr;
	int ret;

	/* For Modern GENs the PTEs and register space are split in the BAR */
	gtt_phys_addr = pci_resource_start(dev->pdev, 0) +
		(pci_resource_len(dev->pdev, 0) / 2);

	dev_priv->gtt.gsm = ioremap_wc(gtt_phys_addr, gtt_size);
	if (!dev_priv->gtt.gsm) {
		DRM_ERROR("Failed to map the gtt page table\n");
		return -ENOMEM;
	}

	ret = setup_scratch_page(dev);
	if (ret) {
		DRM_ERROR("Scratch setup failed\n");
		/* iounmap will also get called at remove, but meh */
		iounmap(dev_priv->gtt.gsm);
	}

	return ret;
}

/* The GGTT and PPGTT need a private PPAT setup in order to handle cacheability
 * bits. When using advanced contexts each context stores its own PAT, but
 * writing this data shouldn't be harmful even in those cases. */
static void bdw_setup_private_ppat(struct drm_i915_private *dev_priv)
{
	uint64_t pat;

	pat = GEN8_PPAT(0, GEN8_PPAT_WB | GEN8_PPAT_LLC)     | /* for normal objects, no eLLC */
	      GEN8_PPAT(1, GEN8_PPAT_WC | GEN8_PPAT_LLCELLC) | /* for something pointing to ptes? */
	      GEN8_PPAT(2, GEN8_PPAT_WT | GEN8_PPAT_LLCELLC) | /* for scanout with eLLC */
	      GEN8_PPAT(3, GEN8_PPAT_UC)                     | /* Uncached objects, mostly for scanout */
	      GEN8_PPAT(4, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(0)) |
	      GEN8_PPAT(5, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(1)) |
	      GEN8_PPAT(6, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(2)) |
	      GEN8_PPAT(7, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3));

	/* XXX: spec defines this as 2 distinct registers. It's unclear if a 64b
	 * write would work. */
	I915_WRITE(GEN8_PRIVATE_PAT, pat);
	I915_WRITE(GEN8_PRIVATE_PAT + 4, pat >> 32);
}

static void chv_setup_private_ppat(struct drm_i915_private *dev_priv)
{
	uint64_t pat;

	/*
	 * Map WB on BDW to snooped on CHV.
	 *
	 * Only the snoop bit has meaning for CHV, the rest is
	 * ignored.
	 *
	 * Note that the harware enforces snooping for all page
	 * table accesses. The snoop bit is actually ignored for
	 * PDEs.
	 */
	pat = GEN8_PPAT(0, CHV_PPAT_SNOOP) |
	      GEN8_PPAT(1, 0) |
	      GEN8_PPAT(2, 0) |
	      GEN8_PPAT(3, 0) |
	      GEN8_PPAT(4, CHV_PPAT_SNOOP) |
	      GEN8_PPAT(5, CHV_PPAT_SNOOP) |
	      GEN8_PPAT(6, CHV_PPAT_SNOOP) |
	      GEN8_PPAT(7, CHV_PPAT_SNOOP);

	I915_WRITE(GEN8_PRIVATE_PAT, pat);
	I915_WRITE(GEN8_PRIVATE_PAT + 4, pat >> 32);
}

static int gen8_gmch_probe(struct drm_device *dev,
			   size_t *gtt_total,
			   size_t *stolen,
			   phys_addr_t *mappable_base,
			   unsigned long *mappable_end)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	unsigned int gtt_size;
	u16 snb_gmch_ctl;
	int ret;

	/* TODO: We're not aware of mappable constraints on gen8 yet */
	*mappable_base = pci_resource_start(dev->pdev, 2);
	*mappable_end = pci_resource_len(dev->pdev, 2);

	if (!pci_set_dma_mask(dev->pdev, DMA_BIT_MASK(39)))
		pci_set_consistent_dma_mask(dev->pdev, DMA_BIT_MASK(39));

	pci_read_config_word(dev->pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);

	if (IS_CHERRYVIEW(dev)) {
		*stolen = chv_get_stolen_size(snb_gmch_ctl);
		gtt_size = chv_get_total_gtt_size(snb_gmch_ctl);
	} else {
		*stolen = gen8_get_stolen_size(snb_gmch_ctl);
		gtt_size = gen8_get_total_gtt_size(snb_gmch_ctl);
	}

	*gtt_total = (gtt_size / sizeof(gen8_gtt_pte_t)) << PAGE_SHIFT;

	if (IS_CHERRYVIEW(dev))
		chv_setup_private_ppat(dev_priv);
	else
		bdw_setup_private_ppat(dev_priv);

	ret = ggtt_probe_common(dev, gtt_size);

	dev_priv->gtt.base.clear_range = gen8_ggtt_clear_range;
	dev_priv->gtt.base.insert_entries = gen8_ggtt_insert_entries;

	return ret;
}

static int gen6_gmch_probe(struct drm_device *dev,
			   size_t *gtt_total,
			   size_t *stolen,
			   phys_addr_t *mappable_base,
			   unsigned long *mappable_end)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	unsigned int gtt_size;
	u16 snb_gmch_ctl;
	int ret;

	*mappable_base = pci_resource_start(dev->pdev, 2);
	*mappable_end = pci_resource_len(dev->pdev, 2);

	/* 64/512MB is the current min/max we actually know of, but this is just
	 * a coarse sanity check.
	 */
	if ((*mappable_end < (64<<20) || (*mappable_end > (512<<20)))) {
		DRM_ERROR("Unknown GMADR size (%lx)\n",
			  dev_priv->gtt.mappable_end);
		return -ENXIO;
	}

	if (!pci_set_dma_mask(dev->pdev, DMA_BIT_MASK(40)))
		pci_set_consistent_dma_mask(dev->pdev, DMA_BIT_MASK(40));
	pci_read_config_word(dev->pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);

	*stolen = gen6_get_stolen_size(snb_gmch_ctl);

	gtt_size = gen6_get_total_gtt_size(snb_gmch_ctl);
	*gtt_total = (gtt_size / sizeof(gen6_gtt_pte_t)) << PAGE_SHIFT;

	ret = ggtt_probe_common(dev, gtt_size);

	dev_priv->gtt.base.clear_range = gen6_ggtt_clear_range;
	dev_priv->gtt.base.insert_entries = gen6_ggtt_insert_entries;

	return ret;
}

static void gen6_gmch_remove(struct i915_address_space *vm)
{

	struct i915_gtt *gtt = container_of(vm, struct i915_gtt, base);

	if (drm_mm_initialized(&vm->mm)) {
		drm_mm_takedown(&vm->mm);
		list_del(&vm->global_link);
	}
	iounmap(gtt->gsm);
	teardown_scratch_page(vm->dev);
}

static int i915_gmch_probe(struct drm_device *dev,
			   size_t *gtt_total,
			   size_t *stolen,
			   phys_addr_t *mappable_base,
			   unsigned long *mappable_end)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	int ret;

	ret = intel_gmch_probe(dev_priv->bridge_dev, dev_priv->dev->pdev, NULL);
	if (!ret) {
		DRM_ERROR("failed to set up gmch\n");
		return -EIO;
	}

	intel_gtt_get(gtt_total, stolen, mappable_base, mappable_end);

	dev_priv->gtt.do_idle_maps = needs_idle_maps(dev_priv->dev);
	dev_priv->gtt.base.clear_range = i915_ggtt_clear_range;

	if (unlikely(dev_priv->gtt.do_idle_maps))
		DRM_INFO("applying Ironlake quirks for intel_iommu\n");

	return 0;
}

static void i915_gmch_remove(struct i915_address_space *vm)
{
	if (drm_mm_initialized(&vm->mm)) {
		drm_mm_takedown(&vm->mm);
		list_del(&vm->global_link);
	}
	intel_gmch_remove();
}

int i915_gem_gtt_init(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct i915_gtt *gtt = &dev_priv->gtt;
	int ret;

	if (INTEL_INFO(dev)->gen <= 5) {
		gtt->gtt_probe = i915_gmch_probe;
		gtt->base.cleanup = i915_gmch_remove;
	} else if (INTEL_INFO(dev)->gen < 8) {
		gtt->gtt_probe = gen6_gmch_probe;
		gtt->base.cleanup = gen6_gmch_remove;
		if (IS_HASWELL(dev) && dev_priv->ellc_size)
			gtt->base.pte_encode = iris_pte_encode;
		else if (IS_HASWELL(dev))
			gtt->base.pte_encode = hsw_pte_encode;
		else if (IS_VALLEYVIEW(dev))
			gtt->base.pte_encode = byt_pte_encode;
		else if (INTEL_INFO(dev)->gen >= 7)
			gtt->base.pte_encode = ivb_pte_encode;
		else
			gtt->base.pte_encode = snb_pte_encode;
	} else {
		dev_priv->gtt.gtt_probe = gen8_gmch_probe;
		dev_priv->gtt.base.cleanup = gen6_gmch_remove;
	}

	ret = gtt->gtt_probe(dev, &gtt->base.total, &gtt->stolen_size,
			     &gtt->mappable_base, &gtt->mappable_end);
	if (ret)
		return ret;

	gtt->base.dev = dev;

	/* GMADR is the PCI mmio aperture into the global GTT. */
	DRM_INFO("Memory usable by graphics device = %zdM\n",
		 gtt->base.total >> 20);
	DRM_DEBUG_DRIVER("GMADR size = %ldM\n", gtt->mappable_end >> 20);
	DRM_DEBUG_DRIVER("GTT stolen size = %zdM\n", gtt->stolen_size >> 20);
#ifdef CONFIG_INTEL_IOMMU
	if (intel_iommu_gfx_mapped)
		DRM_INFO("VT-d active for gfx access\n");
#endif
	/*
	 * i915.enable_ppgtt is read-only, so do an early pass to validate the
	 * user's requested state against the hardware/driver capabilities.  We
	 * do this now so that we can print out any log messages once rather
	 * than every time we check intel_enable_ppgtt().
	 */
	i915.enable_ppgtt = sanitize_enable_ppgtt(dev, i915.enable_ppgtt);
	DRM_DEBUG_DRIVER("ppgtt mode: %i\n", i915.enable_ppgtt);

	return 0;
}

static struct i915_vma *__i915_gem_vma_create(struct drm_i915_gem_object *obj,
					      struct i915_address_space *vm)
{
	struct i915_vma *vma = kzalloc(sizeof(*vma), GFP_KERNEL);
	if (vma == NULL)
		return ERR_PTR(-ENOMEM);

	INIT_LIST_HEAD(&vma->vma_link);
	INIT_LIST_HEAD(&vma->mm_list);
	INIT_LIST_HEAD(&vma->exec_list);
	vma->vm = vm;
	vma->obj = obj;

	switch (INTEL_INFO(vm->dev)->gen) {
	case 8:
	case 7:
	case 6:
		if (i915_is_ggtt(vm)) {
			vma->unbind_vma = ggtt_unbind_vma;
			vma->bind_vma = ggtt_bind_vma;
		} else {
			vma->unbind_vma = ppgtt_unbind_vma;
			vma->bind_vma = ppgtt_bind_vma;
		}
		break;
	case 5:
	case 4:
	case 3:
	case 2:
		BUG_ON(!i915_is_ggtt(vm));
		vma->unbind_vma = i915_ggtt_unbind_vma;
		vma->bind_vma = i915_ggtt_bind_vma;
		break;
	default:
		BUG();
	}

	/* Keep GGTT vmas first to make debug easier */
	if (i915_is_ggtt(vm))
		list_add(&vma->vma_link, &obj->vma_list);
	else
		list_add_tail(&vma->vma_link, &obj->vma_list);

	return vma;
}

struct i915_vma *
i915_gem_obj_lookup_or_create_vma(struct drm_i915_gem_object *obj,
				  struct i915_address_space *vm)
{
	struct i915_vma *vma;

	vma = i915_gem_obj_to_vma(obj, vm);
	if (!vma)
		vma = __i915_gem_vma_create(obj, vm);

	return vma;
}