summaryrefslogtreecommitdiffstats
path: root/drivers/iommu/intel-iommu.c
blob: 3965e73db51cef0f3d3b5593da18c9d9fe25fd9e (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
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
5363
5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
5377
5378
5379
5380
5381
5382
5383
5384
5385
5386
5387
5388
5389
5390
5391
5392
5393
5394
5395
5396
5397
5398
5399
5400
5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
/*
 * Copyright © 2006-2014 Intel Corporation.
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms and conditions of the GNU General Public License,
 * version 2, as published by the Free Software Foundation.
 *
 * This program is distributed in the hope it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 * more details.
 *
 * Authors: David Woodhouse <dwmw2@infradead.org>,
 *          Ashok Raj <ashok.raj@intel.com>,
 *          Shaohua Li <shaohua.li@intel.com>,
 *          Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>,
 *          Fenghua Yu <fenghua.yu@intel.com>
 *          Joerg Roedel <jroedel@suse.de>
 */

#define pr_fmt(fmt)     "DMAR: " fmt

#include <linux/init.h>
#include <linux/bitmap.h>
#include <linux/debugfs.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/irq.h>
#include <linux/interrupt.h>
#include <linux/spinlock.h>
#include <linux/pci.h>
#include <linux/dmar.h>
#include <linux/dma-mapping.h>
#include <linux/mempool.h>
#include <linux/memory.h>
#include <linux/cpu.h>
#include <linux/timer.h>
#include <linux/io.h>
#include <linux/iova.h>
#include <linux/iommu.h>
#include <linux/intel-iommu.h>
#include <linux/syscore_ops.h>
#include <linux/tboot.h>
#include <linux/dmi.h>
#include <linux/pci-ats.h>
#include <linux/memblock.h>
#include <linux/dma-contiguous.h>
#include <linux/crash_dump.h>
#include <asm/irq_remapping.h>
#include <asm/cacheflush.h>
#include <asm/iommu.h>

#include "irq_remapping.h"

#define ROOT_SIZE		VTD_PAGE_SIZE
#define CONTEXT_SIZE		VTD_PAGE_SIZE

#define IS_GFX_DEVICE(pdev) ((pdev->class >> 16) == PCI_BASE_CLASS_DISPLAY)
#define IS_USB_DEVICE(pdev) ((pdev->class >> 8) == PCI_CLASS_SERIAL_USB)
#define IS_ISA_DEVICE(pdev) ((pdev->class >> 8) == PCI_CLASS_BRIDGE_ISA)
#define IS_AZALIA(pdev) ((pdev)->vendor == 0x8086 && (pdev)->device == 0x3a3e)

#define IOAPIC_RANGE_START	(0xfee00000)
#define IOAPIC_RANGE_END	(0xfeefffff)
#define IOVA_START_ADDR		(0x1000)

#define DEFAULT_DOMAIN_ADDRESS_WIDTH 48

#define MAX_AGAW_WIDTH 64
#define MAX_AGAW_PFN_WIDTH	(MAX_AGAW_WIDTH - VTD_PAGE_SHIFT)

#define __DOMAIN_MAX_PFN(gaw)  ((((uint64_t)1) << (gaw-VTD_PAGE_SHIFT)) - 1)
#define __DOMAIN_MAX_ADDR(gaw) ((((uint64_t)1) << gaw) - 1)

/* We limit DOMAIN_MAX_PFN to fit in an unsigned long, and DOMAIN_MAX_ADDR
   to match. That way, we can use 'unsigned long' for PFNs with impunity. */
#define DOMAIN_MAX_PFN(gaw)	((unsigned long) min_t(uint64_t, \
				__DOMAIN_MAX_PFN(gaw), (unsigned long)-1))
#define DOMAIN_MAX_ADDR(gaw)	(((uint64_t)__DOMAIN_MAX_PFN(gaw)) << VTD_PAGE_SHIFT)

/* IO virtual address start page frame number */
#define IOVA_START_PFN		(1)

#define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT)
#define DMA_32BIT_PFN		IOVA_PFN(DMA_BIT_MASK(32))
#define DMA_64BIT_PFN		IOVA_PFN(DMA_BIT_MASK(64))

/* page table handling */
#define LEVEL_STRIDE		(9)
#define LEVEL_MASK		(((u64)1 << LEVEL_STRIDE) - 1)

/*
 * This bitmap is used to advertise the page sizes our hardware support
 * to the IOMMU core, which will then use this information to split
 * physically contiguous memory regions it is mapping into page sizes
 * that we support.
 *
 * Traditionally the IOMMU core just handed us the mappings directly,
 * after making sure the size is an order of a 4KiB page and that the
 * mapping has natural alignment.
 *
 * To retain this behavior, we currently advertise that we support
 * all page sizes that are an order of 4KiB.
 *
 * If at some point we'd like to utilize the IOMMU core's new behavior,
 * we could change this to advertise the real page sizes we support.
 */
#define INTEL_IOMMU_PGSIZES	(~0xFFFUL)

static inline int agaw_to_level(int agaw)
{
	return agaw + 2;
}

static inline int agaw_to_width(int agaw)
{
	return min_t(int, 30 + agaw * LEVEL_STRIDE, MAX_AGAW_WIDTH);
}

static inline int width_to_agaw(int width)
{
	return DIV_ROUND_UP(width - 30, LEVEL_STRIDE);
}

static inline unsigned int level_to_offset_bits(int level)
{
	return (level - 1) * LEVEL_STRIDE;
}

static inline int pfn_level_offset(unsigned long pfn, int level)
{
	return (pfn >> level_to_offset_bits(level)) & LEVEL_MASK;
}

static inline unsigned long level_mask(int level)
{
	return -1UL << level_to_offset_bits(level);
}

static inline unsigned long level_size(int level)
{
	return 1UL << level_to_offset_bits(level);
}

static inline unsigned long align_to_level(unsigned long pfn, int level)
{
	return (pfn + level_size(level) - 1) & level_mask(level);
}

static inline unsigned long lvl_to_nr_pages(unsigned int lvl)
{
	return  1 << min_t(int, (lvl - 1) * LEVEL_STRIDE, MAX_AGAW_PFN_WIDTH);
}

/* VT-d pages must always be _smaller_ than MM pages. Otherwise things
   are never going to work. */
static inline unsigned long dma_to_mm_pfn(unsigned long dma_pfn)
{
	return dma_pfn >> (PAGE_SHIFT - VTD_PAGE_SHIFT);
}

static inline unsigned long mm_to_dma_pfn(unsigned long mm_pfn)
{
	return mm_pfn << (PAGE_SHIFT - VTD_PAGE_SHIFT);
}
static inline unsigned long page_to_dma_pfn(struct page *pg)
{
	return mm_to_dma_pfn(page_to_pfn(pg));
}
static inline unsigned long virt_to_dma_pfn(void *p)
{
	return page_to_dma_pfn(virt_to_page(p));
}

/* global iommu list, set NULL for ignored DMAR units */
static struct intel_iommu **g_iommus;

static void __init check_tylersburg_isoch(void);
static int rwbf_quirk;

/*
 * set to 1 to panic kernel if can't successfully enable VT-d
 * (used when kernel is launched w/ TXT)
 */
static int force_on = 0;

/*
 * 0: Present
 * 1-11: Reserved
 * 12-63: Context Ptr (12 - (haw-1))
 * 64-127: Reserved
 */
struct root_entry {
	u64	lo;
	u64	hi;
};
#define ROOT_ENTRY_NR (VTD_PAGE_SIZE/sizeof(struct root_entry))

/*
 * Take a root_entry and return the Lower Context Table Pointer (LCTP)
 * if marked present.
 */
static phys_addr_t root_entry_lctp(struct root_entry *re)
{
	if (!(re->lo & 1))
		return 0;

	return re->lo & VTD_PAGE_MASK;
}

/*
 * Take a root_entry and return the Upper Context Table Pointer (UCTP)
 * if marked present.
 */
static phys_addr_t root_entry_uctp(struct root_entry *re)
{
	if (!(re->hi & 1))
		return 0;

	return re->hi & VTD_PAGE_MASK;
}
/*
 * low 64 bits:
 * 0: present
 * 1: fault processing disable
 * 2-3: translation type
 * 12-63: address space root
 * high 64 bits:
 * 0-2: address width
 * 3-6: aval
 * 8-23: domain id
 */
struct context_entry {
	u64 lo;
	u64 hi;
};

static inline void context_clear_pasid_enable(struct context_entry *context)
{
	context->lo &= ~(1ULL << 11);
}

static inline bool context_pasid_enabled(struct context_entry *context)
{
	return !!(context->lo & (1ULL << 11));
}

static inline void context_set_copied(struct context_entry *context)
{
	context->hi |= (1ull << 3);
}

static inline bool context_copied(struct context_entry *context)
{
	return !!(context->hi & (1ULL << 3));
}

static inline bool __context_present(struct context_entry *context)
{
	return (context->lo & 1);
}

static inline bool context_present(struct context_entry *context)
{
	return context_pasid_enabled(context) ?
	     __context_present(context) :
	     __context_present(context) && !context_copied(context);
}

static inline void context_set_present(struct context_entry *context)
{
	context->lo |= 1;
}

static inline void context_set_fault_enable(struct context_entry *context)
{
	context->lo &= (((u64)-1) << 2) | 1;
}

static inline void context_set_translation_type(struct context_entry *context,
						unsigned long value)
{
	context->lo &= (((u64)-1) << 4) | 3;
	context->lo |= (value & 3) << 2;
}

static inline void context_set_address_root(struct context_entry *context,
					    unsigned long value)
{
	context->lo &= ~VTD_PAGE_MASK;
	context->lo |= value & VTD_PAGE_MASK;
}

static inline void context_set_address_width(struct context_entry *context,
					     unsigned long value)
{
	context->hi |= value & 7;
}

static inline void context_set_domain_id(struct context_entry *context,
					 unsigned long value)
{
	context->hi |= (value & ((1 << 16) - 1)) << 8;
}

static inline int context_domain_id(struct context_entry *c)
{
	return((c->hi >> 8) & 0xffff);
}

static inline void context_clear_entry(struct context_entry *context)
{
	context->lo = 0;
	context->hi = 0;
}

/*
 * 0: readable
 * 1: writable
 * 2-6: reserved
 * 7: super page
 * 8-10: available
 * 11: snoop behavior
 * 12-63: Host physcial address
 */
struct dma_pte {
	u64 val;
};

static inline void dma_clear_pte(struct dma_pte *pte)
{
	pte->val = 0;
}

static inline u64 dma_pte_addr(struct dma_pte *pte)
{
#ifdef CONFIG_64BIT
	return pte->val & VTD_PAGE_MASK;
#else
	/* Must have a full atomic 64-bit read */
	return  __cmpxchg64(&pte->val, 0ULL, 0ULL) & VTD_PAGE_MASK;
#endif
}

static inline bool dma_pte_present(struct dma_pte *pte)
{
	return (pte->val & 3) != 0;
}

static inline bool dma_pte_superpage(struct dma_pte *pte)
{
	return (pte->val & DMA_PTE_LARGE_PAGE);
}

static inline int first_pte_in_page(struct dma_pte *pte)
{
	return !((unsigned long)pte & ~VTD_PAGE_MASK);
}

/*
 * This domain is a statically identity mapping domain.
 *	1. This domain creats a static 1:1 mapping to all usable memory.
 * 	2. It maps to each iommu if successful.
 *	3. Each iommu mapps to this domain if successful.
 */
static struct dmar_domain *si_domain;
static int hw_pass_through = 1;

/*
 * Domain represents a virtual machine, more than one devices
 * across iommus may be owned in one domain, e.g. kvm guest.
 */
#define DOMAIN_FLAG_VIRTUAL_MACHINE	(1 << 0)

/* si_domain contains mulitple devices */
#define DOMAIN_FLAG_STATIC_IDENTITY	(1 << 1)

#define for_each_domain_iommu(idx, domain)			\
	for (idx = 0; idx < g_num_of_iommus; idx++)		\
		if (domain->iommu_refcnt[idx])

struct dmar_domain {
	int	nid;			/* node id */

	unsigned	iommu_refcnt[DMAR_UNITS_SUPPORTED];
					/* Refcount of devices per iommu */


	u16		iommu_did[DMAR_UNITS_SUPPORTED];
					/* Domain ids per IOMMU. Use u16 since
					 * domain ids are 16 bit wide according
					 * to VT-d spec, section 9.3 */

	bool has_iotlb_device;
	struct list_head devices;	/* all devices' list */
	struct iova_domain iovad;	/* iova's that belong to this domain */

	struct dma_pte	*pgd;		/* virtual address */
	int		gaw;		/* max guest address width */

	/* adjusted guest address width, 0 is level 2 30-bit */
	int		agaw;

	int		flags;		/* flags to find out type of domain */

	int		iommu_coherency;/* indicate coherency of iommu access */
	int		iommu_snooping; /* indicate snooping control feature*/
	int		iommu_count;	/* reference count of iommu */
	int		iommu_superpage;/* Level of superpages supported:
					   0 == 4KiB (no superpages), 1 == 2MiB,
					   2 == 1GiB, 3 == 512GiB, 4 == 1TiB */
	u64		max_addr;	/* maximum mapped address */

	struct iommu_domain domain;	/* generic domain data structure for
					   iommu core */
};

/* PCI domain-device relationship */
struct device_domain_info {
	struct list_head link;	/* link to domain siblings */
	struct list_head global; /* link to global list */
	u8 bus;			/* PCI bus number */
	u8 devfn;		/* PCI devfn number */
	u8 pasid_supported:3;
	u8 pasid_enabled:1;
	u8 pri_supported:1;
	u8 pri_enabled:1;
	u8 ats_supported:1;
	u8 ats_enabled:1;
	u8 ats_qdep;
	struct device *dev; /* it's NULL for PCIe-to-PCI bridge */
	struct intel_iommu *iommu; /* IOMMU used by this device */
	struct dmar_domain *domain; /* pointer to domain */
};

struct dmar_rmrr_unit {
	struct list_head list;		/* list of rmrr units	*/
	struct acpi_dmar_header *hdr;	/* ACPI header		*/
	u64	base_address;		/* reserved base address*/
	u64	end_address;		/* reserved end address */
	struct dmar_dev_scope *devices;	/* target devices */
	int	devices_cnt;		/* target device count */
};

struct dmar_atsr_unit {
	struct list_head list;		/* list of ATSR units */
	struct acpi_dmar_header *hdr;	/* ACPI header */
	struct dmar_dev_scope *devices;	/* target devices */
	int devices_cnt;		/* target device count */
	u8 include_all:1;		/* include all ports */
};

static LIST_HEAD(dmar_atsr_units);
static LIST_HEAD(dmar_rmrr_units);

#define for_each_rmrr_units(rmrr) \
	list_for_each_entry(rmrr, &dmar_rmrr_units, list)

static void flush_unmaps_timeout(unsigned long data);

struct deferred_flush_entry {
	unsigned long iova_pfn;
	unsigned long nrpages;
	struct dmar_domain *domain;
	struct page *freelist;
};

#define HIGH_WATER_MARK 250
struct deferred_flush_table {
	int next;
	struct deferred_flush_entry entries[HIGH_WATER_MARK];
};

struct deferred_flush_data {
	spinlock_t lock;
	int timer_on;
	struct timer_list timer;
	long size;
	struct deferred_flush_table *tables;
};

DEFINE_PER_CPU(struct deferred_flush_data, deferred_flush);

/* bitmap for indexing intel_iommus */
static int g_num_of_iommus;

static void domain_exit(struct dmar_domain *domain);
static void domain_remove_dev_info(struct dmar_domain *domain);
static void dmar_remove_one_dev_info(struct dmar_domain *domain,
				     struct device *dev);
static void __dmar_remove_one_dev_info(struct device_domain_info *info);
static void domain_context_clear(struct intel_iommu *iommu,
				 struct device *dev);
static int domain_detach_iommu(struct dmar_domain *domain,
			       struct intel_iommu *iommu);

#ifdef CONFIG_INTEL_IOMMU_DEFAULT_ON
int dmar_disabled = 0;
#else
int dmar_disabled = 1;
#endif /*CONFIG_INTEL_IOMMU_DEFAULT_ON*/

int intel_iommu_enabled = 0;
EXPORT_SYMBOL_GPL(intel_iommu_enabled);

static int dmar_map_gfx = 1;
static int dmar_forcedac;
static int intel_iommu_strict;
static int intel_iommu_superpage = 1;
static int intel_iommu_ecs = 1;
static int intel_iommu_pasid28;
static int iommu_identity_mapping;

#define IDENTMAP_ALL		1
#define IDENTMAP_GFX		2
#define IDENTMAP_AZALIA		4

/* Broadwell and Skylake have broken ECS support — normal so-called "second
 * level" translation of DMA requests-without-PASID doesn't actually happen
 * unless you also set the NESTE bit in an extended context-entry. Which of
 * course means that SVM doesn't work because it's trying to do nested
 * translation of the physical addresses it finds in the process page tables,
 * through the IOVA->phys mapping found in the "second level" page tables.
 *
 * The VT-d specification was retroactively changed to change the definition
 * of the capability bits and pretend that Broadwell/Skylake never happened...
 * but unfortunately the wrong bit was changed. It's ECS which is broken, but
 * for some reason it was the PASID capability bit which was redefined (from
 * bit 28 on BDW/SKL to bit 40 in future).
 *
 * So our test for ECS needs to eschew those implementations which set the old
 * PASID capabiity bit 28, since those are the ones on which ECS is broken.
 * Unless we are working around the 'pasid28' limitations, that is, by putting
 * the device into passthrough mode for normal DMA and thus masking the bug.
 */
#define ecs_enabled(iommu) (intel_iommu_ecs && ecap_ecs(iommu->ecap) && \
			    (intel_iommu_pasid28 || !ecap_broken_pasid(iommu->ecap)))
/* PASID support is thus enabled if ECS is enabled and *either* of the old
 * or new capability bits are set. */
#define pasid_enabled(iommu) (ecs_enabled(iommu) &&			\
			      (ecap_pasid(iommu->ecap) || ecap_broken_pasid(iommu->ecap)))

int intel_iommu_gfx_mapped;
EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped);

#define DUMMY_DEVICE_DOMAIN_INFO ((struct device_domain_info *)(-1))
static DEFINE_SPINLOCK(device_domain_lock);
static LIST_HEAD(device_domain_list);

static const struct iommu_ops intel_iommu_ops;

static bool translation_pre_enabled(struct intel_iommu *iommu)
{
	return (iommu->flags & VTD_FLAG_TRANS_PRE_ENABLED);
}

static void clear_translation_pre_enabled(struct intel_iommu *iommu)
{
	iommu->flags &= ~VTD_FLAG_TRANS_PRE_ENABLED;
}

static void init_translation_status(struct intel_iommu *iommu)
{
	u32 gsts;

	gsts = readl(iommu->reg + DMAR_GSTS_REG);
	if (gsts & DMA_GSTS_TES)
		iommu->flags |= VTD_FLAG_TRANS_PRE_ENABLED;
}

/* Convert generic 'struct iommu_domain to private struct dmar_domain */
static struct dmar_domain *to_dmar_domain(struct iommu_domain *dom)
{
	return container_of(dom, struct dmar_domain, domain);
}

static int __init intel_iommu_setup(char *str)
{
	if (!str)
		return -EINVAL;
	while (*str) {
		if (!strncmp(str, "on", 2)) {
			dmar_disabled = 0;
			pr_info("IOMMU enabled\n");
		} else if (!strncmp(str, "off", 3)) {
			dmar_disabled = 1;
			pr_info("IOMMU disabled\n");
		} else if (!strncmp(str, "igfx_off", 8)) {
			dmar_map_gfx = 0;
			pr_info("Disable GFX device mapping\n");
		} else if (!strncmp(str, "forcedac", 8)) {
			pr_info("Forcing DAC for PCI devices\n");
			dmar_forcedac = 1;
		} else if (!strncmp(str, "strict", 6)) {
			pr_info("Disable batched IOTLB flush\n");
			intel_iommu_strict = 1;
		} else if (!strncmp(str, "sp_off", 6)) {
			pr_info("Disable supported super page\n");
			intel_iommu_superpage = 0;
		} else if (!strncmp(str, "ecs_off", 7)) {
			printk(KERN_INFO
				"Intel-IOMMU: disable extended context table support\n");
			intel_iommu_ecs = 0;
		} else if (!strncmp(str, "pasid28", 7)) {
			printk(KERN_INFO
				"Intel-IOMMU: enable pre-production PASID support\n");
			intel_iommu_pasid28 = 1;
			iommu_identity_mapping |= IDENTMAP_GFX;
		}

		str += strcspn(str, ",");
		while (*str == ',')
			str++;
	}
	return 0;
}
__setup("intel_iommu=", intel_iommu_setup);

static struct kmem_cache *iommu_domain_cache;
static struct kmem_cache *iommu_devinfo_cache;

static struct dmar_domain* get_iommu_domain(struct intel_iommu *iommu, u16 did)
{
	struct dmar_domain **domains;
	int idx = did >> 8;

	domains = iommu->domains[idx];
	if (!domains)
		return NULL;

	return domains[did & 0xff];
}

static void set_iommu_domain(struct intel_iommu *iommu, u16 did,
			     struct dmar_domain *domain)
{
	struct dmar_domain **domains;
	int idx = did >> 8;

	if (!iommu->domains[idx]) {
		size_t size = 256 * sizeof(struct dmar_domain *);
		iommu->domains[idx] = kzalloc(size, GFP_ATOMIC);
	}

	domains = iommu->domains[idx];
	if (WARN_ON(!domains))
		return;
	else
		domains[did & 0xff] = domain;
}

static inline void *alloc_pgtable_page(int node)
{
	struct page *page;
	void *vaddr = NULL;

	page = alloc_pages_node(node, GFP_ATOMIC | __GFP_ZERO, 0);
	if (page)
		vaddr = page_address(page);
	return vaddr;
}

static inline void free_pgtable_page(void *vaddr)
{
	free_page((unsigned long)vaddr);
}

static inline void *alloc_domain_mem(void)
{
	return kmem_cache_alloc(iommu_domain_cache, GFP_ATOMIC);
}

static void free_domain_mem(void *vaddr)
{
	kmem_cache_free(iommu_domain_cache, vaddr);
}

static inline void * alloc_devinfo_mem(void)
{
	return kmem_cache_alloc(iommu_devinfo_cache, GFP_ATOMIC);
}

static inline void free_devinfo_mem(void *vaddr)
{
	kmem_cache_free(iommu_devinfo_cache, vaddr);
}

static inline int domain_type_is_vm(struct dmar_domain *domain)
{
	return domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE;
}

static inline int domain_type_is_si(struct dmar_domain *domain)
{
	return domain->flags & DOMAIN_FLAG_STATIC_IDENTITY;
}

static inline int domain_type_is_vm_or_si(struct dmar_domain *domain)
{
	return domain->flags & (DOMAIN_FLAG_VIRTUAL_MACHINE |
				DOMAIN_FLAG_STATIC_IDENTITY);
}

static inline int domain_pfn_supported(struct dmar_domain *domain,
				       unsigned long pfn)
{
	int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;

	return !(addr_width < BITS_PER_LONG && pfn >> addr_width);
}

static int __iommu_calculate_agaw(struct intel_iommu *iommu, int max_gaw)
{
	unsigned long sagaw;
	int agaw = -1;

	sagaw = cap_sagaw(iommu->cap);
	for (agaw = width_to_agaw(max_gaw);
	     agaw >= 0; agaw--) {
		if (test_bit(agaw, &sagaw))
			break;
	}

	return agaw;
}

/*
 * Calculate max SAGAW for each iommu.
 */
int iommu_calculate_max_sagaw(struct intel_iommu *iommu)
{
	return __iommu_calculate_agaw(iommu, MAX_AGAW_WIDTH);
}

/*
 * calculate agaw for each iommu.
 * "SAGAW" may be different across iommus, use a default agaw, and
 * get a supported less agaw for iommus that don't support the default agaw.
 */
int iommu_calculate_agaw(struct intel_iommu *iommu)
{
	return __iommu_calculate_agaw(iommu, DEFAULT_DOMAIN_ADDRESS_WIDTH);
}

/* This functionin only returns single iommu in a domain */
static struct intel_iommu *domain_get_iommu(struct dmar_domain *domain)
{
	int iommu_id;

	/* si_domain and vm domain should not get here. */
	BUG_ON(domain_type_is_vm_or_si(domain));
	for_each_domain_iommu(iommu_id, domain)
		break;

	if (iommu_id < 0 || iommu_id >= g_num_of_iommus)
		return NULL;

	return g_iommus[iommu_id];
}

static void domain_update_iommu_coherency(struct dmar_domain *domain)
{
	struct dmar_drhd_unit *drhd;
	struct intel_iommu *iommu;
	bool found = false;
	int i;

	domain->iommu_coherency = 1;

	for_each_domain_iommu(i, domain) {
		found = true;
		if (!ecap_coherent(g_iommus[i]->ecap)) {
			domain->iommu_coherency = 0;
			break;
		}
	}
	if (found)
		return;

	/* No hardware attached; use lowest common denominator */
	rcu_read_lock();
	for_each_active_iommu(iommu, drhd) {
		if (!ecap_coherent(iommu->ecap)) {
			domain->iommu_coherency = 0;
			break;
		}
	}
	rcu_read_unlock();
}

static int domain_update_iommu_snooping(struct intel_iommu *skip)
{
	struct dmar_drhd_unit *drhd;
	struct intel_iommu *iommu;
	int ret = 1;

	rcu_read_lock();
	for_each_active_iommu(iommu, drhd) {
		if (iommu != skip) {
			if (!ecap_sc_support(iommu->ecap)) {
				ret = 0;
				break;
			}
		}
	}
	rcu_read_unlock();

	return ret;
}

static int domain_update_iommu_superpage(struct intel_iommu *skip)
{
	struct dmar_drhd_unit *drhd;
	struct intel_iommu *iommu;
	int mask = 0xf;

	if (!intel_iommu_superpage) {
		return 0;
	}

	/* set iommu_superpage to the smallest common denominator */
	rcu_read_lock();
	for_each_active_iommu(iommu, drhd) {
		if (iommu != skip) {
			mask &= cap_super_page_val(iommu->cap);
			if (!mask)
				break;
		}
	}
	rcu_read_unlock();

	return fls(mask);
}

/* Some capabilities may be different across iommus */
static void domain_update_iommu_cap(struct dmar_domain *domain)
{
	domain_update_iommu_coherency(domain);
	domain->iommu_snooping = domain_update_iommu_snooping(NULL);
	domain->iommu_superpage = domain_update_iommu_superpage(NULL);
}

static inline struct context_entry *iommu_context_addr(struct intel_iommu *iommu,
						       u8 bus, u8 devfn, int alloc)
{
	struct root_entry *root = &iommu->root_entry[bus];
	struct context_entry *context;
	u64 *entry;

	entry = &root->lo;
	if (ecs_enabled(iommu)) {
		if (devfn >= 0x80) {
			devfn -= 0x80;
			entry = &root->hi;
		}
		devfn *= 2;
	}
	if (*entry & 1)
		context = phys_to_virt(*entry & VTD_PAGE_MASK);
	else {
		unsigned long phy_addr;
		if (!alloc)
			return NULL;

		context = alloc_pgtable_page(iommu->node);
		if (!context)
			return NULL;

		__iommu_flush_cache(iommu, (void *)context, CONTEXT_SIZE);
		phy_addr = virt_to_phys((void *)context);
		*entry = phy_addr | 1;
		__iommu_flush_cache(iommu, entry, sizeof(*entry));
	}
	return &context[devfn];
}

static int iommu_dummy(struct device *dev)
{
	return dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO;
}

static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn)
{
	struct dmar_drhd_unit *drhd = NULL;
	struct intel_iommu *iommu;
	struct device *tmp;
	struct pci_dev *ptmp, *pdev = NULL;
	u16 segment = 0;
	int i;

	if (iommu_dummy(dev))
		return NULL;

	if (dev_is_pci(dev)) {
		pdev = to_pci_dev(dev);
		segment = pci_domain_nr(pdev->bus);
	} else if (has_acpi_companion(dev))
		dev = &ACPI_COMPANION(dev)->dev;

	rcu_read_lock();
	for_each_active_iommu(iommu, drhd) {
		if (pdev && segment != drhd->segment)
			continue;

		for_each_active_dev_scope(drhd->devices,
					  drhd->devices_cnt, i, tmp) {
			if (tmp == dev) {
				*bus = drhd->devices[i].bus;
				*devfn = drhd->devices[i].devfn;
				goto out;
			}

			if (!pdev || !dev_is_pci(tmp))
				continue;

			ptmp = to_pci_dev(tmp);
			if (ptmp->subordinate &&
			    ptmp->subordinate->number <= pdev->bus->number &&
			    ptmp->subordinate->busn_res.end >= pdev->bus->number)
				goto got_pdev;
		}

		if (pdev && drhd->include_all) {
		got_pdev:
			*bus = pdev->bus->number;
			*devfn = pdev->devfn;
			goto out;
		}
	}
	iommu = NULL;
 out:
	rcu_read_unlock();

	return iommu;
}

static void domain_flush_cache(struct dmar_domain *domain,
			       void *addr, int size)
{
	if (!domain->iommu_coherency)
		clflush_cache_range(addr, size);
}

static int device_context_mapped(struct intel_iommu *iommu, u8 bus, u8 devfn)
{
	struct context_entry *context;
	int ret = 0;
	unsigned long flags;

	spin_lock_irqsave(&iommu->lock, flags);
	context = iommu_context_addr(iommu, bus, devfn, 0);
	if (context)
		ret = context_present(context);
	spin_unlock_irqrestore(&iommu->lock, flags);
	return ret;
}

static void clear_context_table(struct intel_iommu *iommu, u8 bus, u8 devfn)
{
	struct context_entry *context;
	unsigned long flags;

	spin_lock_irqsave(&iommu->lock, flags);
	context = iommu_context_addr(iommu, bus, devfn, 0);
	if (context) {
		context_clear_entry(context);
		__iommu_flush_cache(iommu, context, sizeof(*context));
	}
	spin_unlock_irqrestore(&iommu->lock, flags);
}

static void free_context_table(struct intel_iommu *iommu)
{
	int i;
	unsigned long flags;
	struct context_entry *context;

	spin_lock_irqsave(&iommu->lock, flags);
	if (!iommu->root_entry) {
		goto out;
	}
	for (i = 0; i < ROOT_ENTRY_NR; i++) {
		context = iommu_context_addr(iommu, i, 0, 0);
		if (context)
			free_pgtable_page(context);

		if (!ecs_enabled(iommu))
			continue;

		context = iommu_context_addr(iommu, i, 0x80, 0);
		if (context)
			free_pgtable_page(context);

	}
	free_pgtable_page(iommu->root_entry);
	iommu->root_entry = NULL;
out:
	spin_unlock_irqrestore(&iommu->lock, flags);
}

static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
				      unsigned long pfn, int *target_level)
{
	struct dma_pte *parent, *pte = NULL;
	int level = agaw_to_level(domain->agaw);
	int offset;

	BUG_ON(!domain->pgd);

	if (!domain_pfn_supported(domain, pfn))
		/* Address beyond IOMMU's addressing capabilities. */
		return NULL;

	parent = domain->pgd;

	while (1) {
		void *tmp_page;

		offset = pfn_level_offset(pfn, level);
		pte = &parent[offset];
		if (!*target_level && (dma_pte_superpage(pte) || !dma_pte_present(pte)))
			break;
		if (level == *target_level)
			break;

		if (!dma_pte_present(pte)) {
			uint64_t pteval;

			tmp_page = alloc_pgtable_page(domain->nid);

			if (!tmp_page)
				return NULL;

			domain_flush_cache(domain, tmp_page, VTD_PAGE_SIZE);
			pteval = ((uint64_t)virt_to_dma_pfn(tmp_page) << VTD_PAGE_SHIFT) | DMA_PTE_READ | DMA_PTE_WRITE;
			if (cmpxchg64(&pte->val, 0ULL, pteval))
				/* Someone else set it while we were thinking; use theirs. */
				free_pgtable_page(tmp_page);
			else
				domain_flush_cache(domain, pte, sizeof(*pte));
		}
		if (level == 1)
			break;

		parent = phys_to_virt(dma_pte_addr(pte));
		level--;
	}

	if (!*target_level)
		*target_level = level;

	return pte;
}


/* return address's pte at specific level */
static struct dma_pte *dma_pfn_level_pte(struct dmar_domain *domain,
					 unsigned long pfn,
					 int level, int *large_page)
{
	struct dma_pte *parent, *pte = NULL;
	int total = agaw_to_level(domain->agaw);
	int offset;

	parent = domain->pgd;
	while (level <= total) {
		offset = pfn_level_offset(pfn, total);
		pte = &parent[offset];
		if (level == total)
			return pte;

		if (!dma_pte_present(pte)) {
			*large_page = total;
			break;
		}

		if (dma_pte_superpage(pte)) {
			*large_page = total;
			return pte;
		}

		parent = phys_to_virt(dma_pte_addr(pte));
		total--;
	}
	return NULL;
}

/* clear last level pte, a tlb flush should be followed */
static void dma_pte_clear_range(struct dmar_domain *domain,
				unsigned long start_pfn,
				unsigned long last_pfn)
{
	unsigned int large_page = 1;
	struct dma_pte *first_pte, *pte;

	BUG_ON(!domain_pfn_supported(domain, start_pfn));
	BUG_ON(!domain_pfn_supported(domain, last_pfn));
	BUG_ON(start_pfn > last_pfn);

	/* we don't need lock here; nobody else touches the iova range */
	do {
		large_page = 1;
		first_pte = pte = dma_pfn_level_pte(domain, start_pfn, 1, &large_page);
		if (!pte) {
			start_pfn = align_to_level(start_pfn + 1, large_page + 1);
			continue;
		}
		do {
			dma_clear_pte(pte);
			start_pfn += lvl_to_nr_pages(large_page);
			pte++;
		} while (start_pfn <= last_pfn && !first_pte_in_page(pte));

		domain_flush_cache(domain, first_pte,
				   (void *)pte - (void *)first_pte);

	} while (start_pfn && start_pfn <= last_pfn);
}

static void dma_pte_free_level(struct dmar_domain *domain, int level,
			       struct dma_pte *pte, unsigned long pfn,
			       unsigned long start_pfn, unsigned long last_pfn)
{
	pfn = max(start_pfn, pfn);
	pte = &pte[pfn_level_offset(pfn, level)];

	do {
		unsigned long level_pfn;
		struct dma_pte *level_pte;

		if (!dma_pte_present(pte) || dma_pte_superpage(pte))
			goto next;

		level_pfn = pfn & level_mask(level - 1);
		level_pte = phys_to_virt(dma_pte_addr(pte));

		if (level > 2)
			dma_pte_free_level(domain, level - 1, level_pte,
					   level_pfn, start_pfn, last_pfn);

		/* If range covers entire pagetable, free it */
		if (!(start_pfn > level_pfn ||
		      last_pfn < level_pfn + level_size(level) - 1)) {
			dma_clear_pte(pte);
			domain_flush_cache(domain, pte, sizeof(*pte));
			free_pgtable_page(level_pte);
		}
next:
		pfn += level_size(level);
	} while (!first_pte_in_page(++pte) && pfn <= last_pfn);
}

/* clear last level (leaf) ptes and free page table pages. */
static void dma_pte_free_pagetable(struct dmar_domain *domain,
				   unsigned long start_pfn,
				   unsigned long last_pfn)
{
	BUG_ON(!domain_pfn_supported(domain, start_pfn));
	BUG_ON(!domain_pfn_supported(domain, last_pfn));
	BUG_ON(start_pfn > last_pfn);

	dma_pte_clear_range(domain, start_pfn, last_pfn);

	/* We don't need lock here; nobody else touches the iova range */
	dma_pte_free_level(domain, agaw_to_level(domain->agaw),
			   domain->pgd, 0, start_pfn, last_pfn);

	/* free pgd */
	if (start_pfn == 0 && last_pfn == DOMAIN_MAX_PFN(domain->gaw)) {
		free_pgtable_page(domain->pgd);
		domain->pgd = NULL;
	}
}

/* When a page at a given level is being unlinked from its parent, we don't
   need to *modify* it at all. All we need to do is make a list of all the
   pages which can be freed just as soon as we've flushed the IOTLB and we
   know the hardware page-walk will no longer touch them.
   The 'pte' argument is the *parent* PTE, pointing to the page that is to
   be freed. */
static struct page *dma_pte_list_pagetables(struct dmar_domain *domain,
					    int level, struct dma_pte *pte,
					    struct page *freelist)
{
	struct page *pg;

	pg = pfn_to_page(dma_pte_addr(pte) >> PAGE_SHIFT);
	pg->freelist = freelist;
	freelist = pg;

	if (level == 1)
		return freelist;

	pte = page_address(pg);
	do {
		if (dma_pte_present(pte) && !dma_pte_superpage(pte))
			freelist = dma_pte_list_pagetables(domain, level - 1,
							   pte, freelist);
		pte++;
	} while (!first_pte_in_page(pte));

	return freelist;
}

static struct page *dma_pte_clear_level(struct dmar_domain *domain, int level,
					struct dma_pte *pte, unsigned long pfn,
					unsigned long start_pfn,
					unsigned long last_pfn,
					struct page *freelist)
{
	struct dma_pte *first_pte = NULL, *last_pte = NULL;

	pfn = max(start_pfn, pfn);
	pte = &pte[pfn_level_offset(pfn, level)];

	do {
		unsigned long level_pfn;

		if (!dma_pte_present(pte))
			goto next;

		level_pfn = pfn & level_mask(level);

		/* If range covers entire pagetable, free it */
		if (start_pfn <= level_pfn &&
		    last_pfn >= level_pfn + level_size(level) - 1) {
			/* These suborbinate page tables are going away entirely. Don't
			   bother to clear them; we're just going to *free* them. */
			if (level > 1 && !dma_pte_superpage(pte))
				freelist = dma_pte_list_pagetables(domain, level - 1, pte, freelist);

			dma_clear_pte(pte);
			if (!first_pte)
				first_pte = pte;
			last_pte = pte;
		} else if (level > 1) {
			/* Recurse down into a level that isn't *entirely* obsolete */
			freelist = dma_pte_clear_level(domain, level - 1,
						       phys_to_virt(dma_pte_addr(pte)),
						       level_pfn, start_pfn, last_pfn,
						       freelist);
		}
next:
		pfn += level_size(level);
	} while (!first_pte_in_page(++pte) && pfn <= last_pfn);

	if (first_pte)
		domain_flush_cache(domain, first_pte,
				   (void *)++last_pte - (void *)first_pte);

	return freelist;
}

/* We can't just free the pages because the IOMMU may still be walking
   the page tables, and may have cached the intermediate levels. The
   pages can only be freed after the IOTLB flush has been done. */
static struct page *domain_unmap(struct dmar_domain *domain,
				 unsigned long start_pfn,
				 unsigned long last_pfn)
{
	struct page *freelist = NULL;

	BUG_ON(!domain_pfn_supported(domain, start_pfn));
	BUG_ON(!domain_pfn_supported(domain, last_pfn));
	BUG_ON(start_pfn > last_pfn);

	/* we don't need lock here; nobody else touches the iova range */
	freelist = dma_pte_clear_level(domain, agaw_to_level(domain->agaw),
				       domain->pgd, 0, start_pfn, last_pfn, NULL);

	/* free pgd */
	if (start_pfn == 0 && last_pfn == DOMAIN_MAX_PFN(domain->gaw)) {
		struct page *pgd_page = virt_to_page(domain->pgd);
		pgd_page->freelist = freelist;
		freelist = pgd_page;

		domain->pgd = NULL;
	}

	return freelist;
}

static void dma_free_pagelist(struct page *freelist)
{
	struct page *pg;

	while ((pg = freelist)) {
		freelist = pg->freelist;
		free_pgtable_page(page_address(pg));
	}
}

/* iommu handling */
static int iommu_alloc_root_entry(struct intel_iommu *iommu)
{
	struct root_entry *root;
	unsigned long flags;

	root = (struct root_entry *)alloc_pgtable_page(iommu->node);
	if (!root) {
		pr_err("Allocating root entry for %s failed\n",
			iommu->name);
		return -ENOMEM;
	}

	__iommu_flush_cache(iommu, root, ROOT_SIZE);

	spin_lock_irqsave(&iommu->lock, flags);
	iommu->root_entry = root;
	spin_unlock_irqrestore(&iommu->lock, flags);

	return 0;
}

static void iommu_set_root_entry(struct intel_iommu *iommu)
{
	u64 addr;
	u32 sts;
	unsigned long flag;

	addr = virt_to_phys(iommu->root_entry);
	if (ecs_enabled(iommu))
		addr |= DMA_RTADDR_RTT;

	raw_spin_lock_irqsave(&iommu->register_lock, flag);
	dmar_writeq(iommu->reg + DMAR_RTADDR_REG, addr);

	writel(iommu->gcmd | DMA_GCMD_SRTP, iommu->reg + DMAR_GCMD_REG);

	/* Make sure hardware complete it */
	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
		      readl, (sts & DMA_GSTS_RTPS), sts);

	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
}

static void iommu_flush_write_buffer(struct intel_iommu *iommu)
{
	u32 val;
	unsigned long flag;

	if (!rwbf_quirk && !cap_rwbf(iommu->cap))
		return;

	raw_spin_lock_irqsave(&iommu->register_lock, flag);
	writel(iommu->gcmd | DMA_GCMD_WBF, iommu->reg + DMAR_GCMD_REG);

	/* Make sure hardware complete it */
	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
		      readl, (!(val & DMA_GSTS_WBFS)), val);

	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
}

/* return value determine if we need a write buffer flush */
static void __iommu_flush_context(struct intel_iommu *iommu,
				  u16 did, u16 source_id, u8 function_mask,
				  u64 type)
{
	u64 val = 0;
	unsigned long flag;

	switch (type) {
	case DMA_CCMD_GLOBAL_INVL:
		val = DMA_CCMD_GLOBAL_INVL;
		break;
	case DMA_CCMD_DOMAIN_INVL:
		val = DMA_CCMD_DOMAIN_INVL|DMA_CCMD_DID(did);
		break;
	case DMA_CCMD_DEVICE_INVL:
		val = DMA_CCMD_DEVICE_INVL|DMA_CCMD_DID(did)
			| DMA_CCMD_SID(source_id) | DMA_CCMD_FM(function_mask);
		break;
	default:
		BUG();
	}
	val |= DMA_CCMD_ICC;

	raw_spin_lock_irqsave(&iommu->register_lock, flag);
	dmar_writeq(iommu->reg + DMAR_CCMD_REG, val);

	/* Make sure hardware complete it */
	IOMMU_WAIT_OP(iommu, DMAR_CCMD_REG,
		dmar_readq, (!(val & DMA_CCMD_ICC)), val);

	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
}

/* return value determine if we need a write buffer flush */
static void __iommu_flush_iotlb(struct intel_iommu *iommu, u16 did,
				u64 addr, unsigned int size_order, u64 type)
{
	int tlb_offset = ecap_iotlb_offset(iommu->ecap);
	u64 val = 0, val_iva = 0;
	unsigned long flag;

	switch (type) {
	case DMA_TLB_GLOBAL_FLUSH:
		/* global flush doesn't need set IVA_REG */
		val = DMA_TLB_GLOBAL_FLUSH|DMA_TLB_IVT;
		break;
	case DMA_TLB_DSI_FLUSH:
		val = DMA_TLB_DSI_FLUSH|DMA_TLB_IVT|DMA_TLB_DID(did);
		break;
	case DMA_TLB_PSI_FLUSH:
		val = DMA_TLB_PSI_FLUSH|DMA_TLB_IVT|DMA_TLB_DID(did);
		/* IH bit is passed in as part of address */
		val_iva = size_order | addr;
		break;
	default:
		BUG();
	}
	/* Note: set drain read/write */
#if 0
	/*
	 * This is probably to be super secure.. Looks like we can
	 * ignore it without any impact.
	 */
	if (cap_read_drain(iommu->cap))
		val |= DMA_TLB_READ_DRAIN;
#endif
	if (cap_write_drain(iommu->cap))
		val |= DMA_TLB_WRITE_DRAIN;

	raw_spin_lock_irqsave(&iommu->register_lock, flag);
	/* Note: Only uses first TLB reg currently */
	if (val_iva)
		dmar_writeq(iommu->reg + tlb_offset, val_iva);
	dmar_writeq(iommu->reg + tlb_offset + 8, val);

	/* Make sure hardware complete it */
	IOMMU_WAIT_OP(iommu, tlb_offset + 8,
		dmar_readq, (!(val & DMA_TLB_IVT)), val);

	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);

	/* check IOTLB invalidation granularity */
	if (DMA_TLB_IAIG(val) == 0)
		pr_err("Flush IOTLB failed\n");
	if (DMA_TLB_IAIG(val) != DMA_TLB_IIRG(type))
		pr_debug("TLB flush request %Lx, actual %Lx\n",
			(unsigned long long)DMA_TLB_IIRG(type),
			(unsigned long long)DMA_TLB_IAIG(val));
}

static struct device_domain_info *
iommu_support_dev_iotlb (struct dmar_domain *domain, struct intel_iommu *iommu,
			 u8 bus, u8 devfn)
{
	struct device_domain_info *info;

	assert_spin_locked(&device_domain_lock);

	if (!iommu->qi)
		return NULL;

	list_for_each_entry(info, &domain->devices, link)
		if (info->iommu == iommu && info->bus == bus &&
		    info->devfn == devfn) {
			if (info->ats_supported && info->dev)
				return info;
			break;
		}

	return NULL;
}

static void domain_update_iotlb(struct dmar_domain *domain)
{
	struct device_domain_info *info;
	bool has_iotlb_device = false;

	assert_spin_locked(&device_domain_lock);

	list_for_each_entry(info, &domain->devices, link) {
		struct pci_dev *pdev;

		if (!info->dev || !dev_is_pci(info->dev))
			continue;

		pdev = to_pci_dev(info->dev);
		if (pdev->ats_enabled) {
			has_iotlb_device = true;
			break;
		}
	}

	domain->has_iotlb_device = has_iotlb_device;
}

static void iommu_enable_dev_iotlb(struct device_domain_info *info)
{
	struct pci_dev *pdev;

	assert_spin_locked(&device_domain_lock);

	if (!info || !dev_is_pci(info->dev))
		return;

	pdev = to_pci_dev(info->dev);

#ifdef CONFIG_INTEL_IOMMU_SVM
	/* The PCIe spec, in its wisdom, declares that the behaviour of
	   the device if you enable PASID support after ATS support is
	   undefined. So always enable PASID support on devices which
	   have it, even if we can't yet know if we're ever going to
	   use it. */
	if (info->pasid_supported && !pci_enable_pasid(pdev, info->pasid_supported & ~1))
		info->pasid_enabled = 1;

	if (info->pri_supported && !pci_reset_pri(pdev) && !pci_enable_pri(pdev, 32))
		info->pri_enabled = 1;
#endif
	if (info->ats_supported && !pci_enable_ats(pdev, VTD_PAGE_SHIFT)) {
		info->ats_enabled = 1;
		domain_update_iotlb(info->domain);
		info->ats_qdep = pci_ats_queue_depth(pdev);
	}
}

static void iommu_disable_dev_iotlb(struct device_domain_info *info)
{
	struct pci_dev *pdev;

	assert_spin_locked(&device_domain_lock);

	if (!dev_is_pci(info->dev))
		return;

	pdev = to_pci_dev(info->dev);

	if (info->ats_enabled) {
		pci_disable_ats(pdev);
		info->ats_enabled = 0;
		domain_update_iotlb(info->domain);
	}
#ifdef CONFIG_INTEL_IOMMU_SVM
	if (info->pri_enabled) {
		pci_disable_pri(pdev);
		info->pri_enabled = 0;
	}
	if (info->pasid_enabled) {
		pci_disable_pasid(pdev);
		info->pasid_enabled = 0;
	}
#endif
}

static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
				  u64 addr, unsigned mask)
{
	u16 sid, qdep;
	unsigned long flags;
	struct device_domain_info *info;

	if (!domain->has_iotlb_device)
		return;

	spin_lock_irqsave(&device_domain_lock, flags);
	list_for_each_entry(info, &domain->devices, link) {
		if (!info->ats_enabled)
			continue;

		sid = info->bus << 8 | info->devfn;
		qdep = info->ats_qdep;
		qi_flush_dev_iotlb(info->iommu, sid, qdep, addr, mask);
	}
	spin_unlock_irqrestore(&device_domain_lock, flags);
}

static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
				  struct dmar_domain *domain,
				  unsigned long pfn, unsigned int pages,
				  int ih, int map)
{
	unsigned int mask = ilog2(__roundup_pow_of_two(pages));
	uint64_t addr = (uint64_t)pfn << VTD_PAGE_SHIFT;
	u16 did = domain->iommu_did[iommu->seq_id];

	BUG_ON(pages == 0);

	if (ih)
		ih = 1 << 6;
	/*
	 * Fallback to domain selective flush if no PSI support or the size is
	 * too big.
	 * PSI requires page size to be 2 ^ x, and the base address is naturally
	 * aligned to the size
	 */
	if (!cap_pgsel_inv(iommu->cap) || mask > cap_max_amask_val(iommu->cap))
		iommu->flush.flush_iotlb(iommu, did, 0, 0,
						DMA_TLB_DSI_FLUSH);
	else
		iommu->flush.flush_iotlb(iommu, did, addr | ih, mask,
						DMA_TLB_PSI_FLUSH);

	/*
	 * In caching mode, changes of pages from non-present to present require
	 * flush. However, device IOTLB doesn't need to be flushed in this case.
	 */
	if (!cap_caching_mode(iommu->cap) || !map)
		iommu_flush_dev_iotlb(get_iommu_domain(iommu, did),
				      addr, mask);
}

static void iommu_disable_protect_mem_regions(struct intel_iommu *iommu)
{
	u32 pmen;
	unsigned long flags;

	raw_spin_lock_irqsave(&iommu->register_lock, flags);
	pmen = readl(iommu->reg + DMAR_PMEN_REG);
	pmen &= ~DMA_PMEN_EPM;
	writel(pmen, iommu->reg + DMAR_PMEN_REG);

	/* wait for the protected region status bit to clear */
	IOMMU_WAIT_OP(iommu, DMAR_PMEN_REG,
		readl, !(pmen & DMA_PMEN_PRS), pmen);

	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
}

static void iommu_enable_translation(struct intel_iommu *iommu)
{
	u32 sts;
	unsigned long flags;

	raw_spin_lock_irqsave(&iommu->register_lock, flags);
	iommu->gcmd |= DMA_GCMD_TE;
	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);

	/* Make sure hardware complete it */
	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
		      readl, (sts & DMA_GSTS_TES), sts);

	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
}

static void iommu_disable_translation(struct intel_iommu *iommu)
{
	u32 sts;
	unsigned long flag;

	raw_spin_lock_irqsave(&iommu->register_lock, flag);
	iommu->gcmd &= ~DMA_GCMD_TE;
	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);

	/* Make sure hardware complete it */
	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
		      readl, (!(sts & DMA_GSTS_TES)), sts);

	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
}


static int iommu_init_domains(struct intel_iommu *iommu)
{
	u32 ndomains, nlongs;
	size_t size;

	ndomains = cap_ndoms(iommu->cap);
	pr_debug("%s: Number of Domains supported <%d>\n",
		 iommu->name, ndomains);
	nlongs = BITS_TO_LONGS(ndomains);

	spin_lock_init(&iommu->lock);

	iommu->domain_ids = kcalloc(nlongs, sizeof(unsigned long), GFP_KERNEL);
	if (!iommu->domain_ids) {
		pr_err("%s: Allocating domain id array failed\n",
		       iommu->name);
		return -ENOMEM;
	}

	size = (ALIGN(ndomains, 256) >> 8) * sizeof(struct dmar_domain **);
	iommu->domains = kzalloc(size, GFP_KERNEL);

	if (iommu->domains) {
		size = 256 * sizeof(struct dmar_domain *);
		iommu->domains[0] = kzalloc(size, GFP_KERNEL);
	}

	if (!iommu->domains || !iommu->domains[0]) {
		pr_err("%s: Allocating domain array failed\n",
		       iommu->name);
		kfree(iommu->domain_ids);
		kfree(iommu->domains);
		iommu->domain_ids = NULL;
		iommu->domains    = NULL;
		return -ENOMEM;
	}



	/*
	 * If Caching mode is set, then invalid translations are tagged
	 * with domain-id 0, hence we need to pre-allocate it. We also
	 * use domain-id 0 as a marker for non-allocated domain-id, so
	 * make sure it is not used for a real domain.
	 */
	set_bit(0, iommu->domain_ids);

	return 0;
}

static void disable_dmar_iommu(struct intel_iommu *iommu)
{
	struct device_domain_info *info, *tmp;
	unsigned long flags;

	if (!iommu->domains || !iommu->domain_ids)
		return;

again:
	spin_lock_irqsave(&device_domain_lock, flags);
	list_for_each_entry_safe(info, tmp, &device_domain_list, global) {
		struct dmar_domain *domain;

		if (info->iommu != iommu)
			continue;

		if (!info->dev || !info->domain)
			continue;

		domain = info->domain;

		__dmar_remove_one_dev_info(info);

		if (!domain_type_is_vm_or_si(domain)) {
			/*
			 * The domain_exit() function  can't be called under
			 * device_domain_lock, as it takes this lock itself.
			 * So release the lock here and re-run the loop
			 * afterwards.
			 */
			spin_unlock_irqrestore(&device_domain_lock, flags);
			domain_exit(domain);
			goto again;
		}
	}
	spin_unlock_irqrestore(&device_domain_lock, flags);

	if (iommu->gcmd & DMA_GCMD_TE)
		iommu_disable_translation(iommu);
}

static void free_dmar_iommu(struct intel_iommu *iommu)
{
	if ((iommu->domains) && (iommu->domain_ids)) {
		int elems = ALIGN(cap_ndoms(iommu->cap), 256) >> 8;
		int i;

		for (i = 0; i < elems; i++)
			kfree(iommu->domains[i]);
		kfree(iommu->domains);
		kfree(iommu->domain_ids);
		iommu->domains = NULL;
		iommu->domain_ids = NULL;
	}

	g_iommus[iommu->seq_id] = NULL;

	/* free context mapping */
	free_context_table(iommu);

#ifdef CONFIG_INTEL_IOMMU_SVM
	if (pasid_enabled(iommu)) {
		if (ecap_prs(iommu->ecap))
			intel_svm_finish_prq(iommu);
		intel_svm_free_pasid_tables(iommu);
	}
#endif
}

static struct dmar_domain *alloc_domain(int flags)
{
	struct dmar_domain *domain;

	domain = alloc_domain_mem();
	if (!domain)
		return NULL;

	memset(domain, 0, sizeof(*domain));
	domain->nid = -1;
	domain->flags = flags;
	domain->has_iotlb_device = false;
	INIT_LIST_HEAD(&domain->devices);

	return domain;
}

/* Must be called with iommu->lock */
static int domain_attach_iommu(struct dmar_domain *domain,
			       struct intel_iommu *iommu)
{
	unsigned long ndomains;
	int num;

	assert_spin_locked(&device_domain_lock);
	assert_spin_locked(&iommu->lock);

	domain->iommu_refcnt[iommu->seq_id] += 1;
	domain->iommu_count += 1;
	if (domain->iommu_refcnt[iommu->seq_id] == 1) {
		ndomains = cap_ndoms(iommu->cap);
		num      = find_first_zero_bit(iommu->domain_ids, ndomains);

		if (num >= ndomains) {
			pr_err("%s: No free domain ids\n", iommu->name);
			domain->iommu_refcnt[iommu->seq_id] -= 1;
			domain->iommu_count -= 1;
			return -ENOSPC;
		}

		set_bit(num, iommu->domain_ids);
		set_iommu_domain(iommu, num, domain);

		domain->iommu_did[iommu->seq_id] = num;
		domain->nid			 = iommu->node;

		domain_update_iommu_cap(domain);
	}

	return 0;
}

static int domain_detach_iommu(struct dmar_domain *domain,
			       struct intel_iommu *iommu)
{
	int num, count = INT_MAX;

	assert_spin_locked(&device_domain_lock);
	assert_spin_locked(&iommu->lock);

	domain->iommu_refcnt[iommu->seq_id] -= 1;
	count = --domain->iommu_count;
	if (domain->iommu_refcnt[iommu->seq_id] == 0) {
		num = domain->iommu_did[iommu->seq_id];
		clear_bit(num, iommu->domain_ids);
		set_iommu_domain(iommu, num, NULL);

		domain_update_iommu_cap(domain);
		domain->iommu_did[iommu->seq_id] = 0;
	}

	return count;
}

static struct iova_domain reserved_iova_list;
static struct lock_class_key reserved_rbtree_key;

static int dmar_init_reserved_ranges(void)
{
	struct pci_dev *pdev = NULL;
	struct iova *iova;
	int i;

	init_iova_domain(&reserved_iova_list, VTD_PAGE_SIZE, IOVA_START_PFN,
			DMA_32BIT_PFN);

	lockdep_set_class(&reserved_iova_list.iova_rbtree_lock,
		&reserved_rbtree_key);

	/* IOAPIC ranges shouldn't be accessed by DMA */
	iova = reserve_iova(&reserved_iova_list, IOVA_PFN(IOAPIC_RANGE_START),
		IOVA_PFN(IOAPIC_RANGE_END));
	if (!iova) {
		pr_err("Reserve IOAPIC range failed\n");
		return -ENODEV;
	}

	/* Reserve all PCI MMIO to avoid peer-to-peer access */
	for_each_pci_dev(pdev) {
		struct resource *r;

		for (i = 0; i < PCI_NUM_RESOURCES; i++) {
			r = &pdev->resource[i];
			if (!r->flags || !(r->flags & IORESOURCE_MEM))
				continue;
			iova = reserve_iova(&reserved_iova_list,
					    IOVA_PFN(r->start),
					    IOVA_PFN(r->end));
			if (!iova) {
				pr_err("Reserve iova failed\n");
				return -ENODEV;
			}
		}
	}
	return 0;
}

static void domain_reserve_special_ranges(struct dmar_domain *domain)
{
	copy_reserved_iova(&reserved_iova_list, &domain->iovad);
}

static inline int guestwidth_to_adjustwidth(int gaw)
{
	int agaw;
	int r = (gaw - 12) % 9;

	if (r == 0)
		agaw = gaw;
	else
		agaw = gaw + 9 - r;
	if (agaw > 64)
		agaw = 64;
	return agaw;
}

static int domain_init(struct dmar_domain *domain, struct intel_iommu *iommu,
		       int guest_width)
{
	int adjust_width, agaw;
	unsigned long sagaw;

	init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN,
			DMA_32BIT_PFN);
	domain_reserve_special_ranges(domain);

	/* calculate AGAW */
	if (guest_width > cap_mgaw(iommu->cap))
		guest_width = cap_mgaw(iommu->cap);
	domain->gaw = guest_width;
	adjust_width = guestwidth_to_adjustwidth(guest_width);
	agaw = width_to_agaw(adjust_width);
	sagaw = cap_sagaw(iommu->cap);
	if (!test_bit(agaw, &sagaw)) {
		/* hardware doesn't support it, choose a bigger one */
		pr_debug("Hardware doesn't support agaw %d\n", agaw);
		agaw = find_next_bit(&sagaw, 5, agaw);
		if (agaw >= 5)
			return -ENODEV;
	}
	domain->agaw = agaw;

	if (ecap_coherent(iommu->ecap))
		domain->iommu_coherency = 1;
	else
		domain->iommu_coherency = 0;

	if (ecap_sc_support(iommu->ecap))
		domain->iommu_snooping = 1;
	else
		domain->iommu_snooping = 0;

	if (intel_iommu_superpage)
		domain->iommu_superpage = fls(cap_super_page_val(iommu->cap));
	else
		domain->iommu_superpage = 0;

	domain->nid = iommu->node;

	/* always allocate the top pgd */
	domain->pgd = (struct dma_pte *)alloc_pgtable_page(domain->nid);
	if (!domain->pgd)
		return -ENOMEM;
	__iommu_flush_cache(iommu, domain->pgd, PAGE_SIZE);
	return 0;
}

static void domain_exit(struct dmar_domain *domain)
{
	struct page *freelist = NULL;

	/* Domain 0 is reserved, so dont process it */
	if (!domain)
		return;

	/* Flush any lazy unmaps that may reference this domain */
	if (!intel_iommu_strict) {
		int cpu;

		for_each_possible_cpu(cpu)
			flush_unmaps_timeout(cpu);
	}

	/* Remove associated devices and clear attached or cached domains */
	rcu_read_lock();
	domain_remove_dev_info(domain);
	rcu_read_unlock();

	/* destroy iovas */
	put_iova_domain(&domain->iovad);

	freelist = domain_unmap(domain, 0, DOMAIN_MAX_PFN(domain->gaw));

	dma_free_pagelist(freelist);

	free_domain_mem(domain);
}

static int domain_context_mapping_one(struct dmar_domain *domain,
				      struct intel_iommu *iommu,
				      u8 bus, u8 devfn)
{
	u16 did = domain->iommu_did[iommu->seq_id];
	int translation = CONTEXT_TT_MULTI_LEVEL;
	struct device_domain_info *info = NULL;
	struct context_entry *context;
	unsigned long flags;
	struct dma_pte *pgd;
	int ret, agaw;

	WARN_ON(did == 0);

	if (hw_pass_through && domain_type_is_si(domain))
		translation = CONTEXT_TT_PASS_THROUGH;

	pr_debug("Set context mapping for %02x:%02x.%d\n",
		bus, PCI_SLOT(devfn), PCI_FUNC(devfn));

	BUG_ON(!domain->pgd);

	spin_lock_irqsave(&device_domain_lock, flags);
	spin_lock(&iommu->lock);

	ret = -ENOMEM;
	context = iommu_context_addr(iommu, bus, devfn, 1);
	if (!context)
		goto out_unlock;

	ret = 0;
	if (context_present(context))
		goto out_unlock;

	pgd = domain->pgd;

	context_clear_entry(context);
	context_set_domain_id(context, did);

	/*
	 * Skip top levels of page tables for iommu which has less agaw
	 * than default.  Unnecessary for PT mode.
	 */
	if (translation != CONTEXT_TT_PASS_THROUGH) {
		for (agaw = domain->agaw; agaw != iommu->agaw; agaw--) {
			ret = -ENOMEM;
			pgd = phys_to_virt(dma_pte_addr(pgd));
			if (!dma_pte_present(pgd))
				goto out_unlock;
		}

		info = iommu_support_dev_iotlb(domain, iommu, bus, devfn);
		if (info && info->ats_supported)
			translation = CONTEXT_TT_DEV_IOTLB;
		else
			translation = CONTEXT_TT_MULTI_LEVEL;

		context_set_address_root(context, virt_to_phys(pgd));
		context_set_address_width(context, iommu->agaw);
	} else {
		/*
		 * In pass through mode, AW must be programmed to
		 * indicate the largest AGAW value supported by
		 * hardware. And ASR is ignored by hardware.
		 */
		context_set_address_width(context, iommu->msagaw);
	}

	context_set_translation_type(context, translation);
	context_set_fault_enable(context);
	context_set_present(context);
	domain_flush_cache(domain, context, sizeof(*context));

	/*
	 * It's a non-present to present mapping. If hardware doesn't cache
	 * non-present entry we only need to flush the write-buffer. If the
	 * _does_ cache non-present entries, then it does so in the special
	 * domain #0, which we have to flush:
	 */
	if (cap_caching_mode(iommu->cap)) {
		iommu->flush.flush_context(iommu, 0,
					   (((u16)bus) << 8) | devfn,
					   DMA_CCMD_MASK_NOBIT,
					   DMA_CCMD_DEVICE_INVL);
		iommu->flush.flush_iotlb(iommu, did, 0, 0, DMA_TLB_DSI_FLUSH);
	} else {
		iommu_flush_write_buffer(iommu);
	}
	iommu_enable_dev_iotlb(info);

	ret = 0;

out_unlock:
	spin_unlock(&iommu->lock);
	spin_unlock_irqrestore(&device_domain_lock, flags);

	return ret;
}

struct domain_context_mapping_data {
	struct dmar_domain *domain;
	struct intel_iommu *iommu;
};

static int domain_context_mapping_cb(struct pci_dev *pdev,
				     u16 alias, void *opaque)
{
	struct domain_context_mapping_data *data = opaque;

	return domain_context_mapping_one(data->domain, data->iommu,
					  PCI_BUS_NUM(alias), alias & 0xff);
}

static int
domain_context_mapping(struct dmar_domain *domain, struct device *dev)
{
	struct intel_iommu *iommu;
	u8 bus, devfn;
	struct domain_context_mapping_data data;

	iommu = device_to_iommu(dev, &bus, &devfn);
	if (!iommu)
		return -ENODEV;

	if (!dev_is_pci(dev))
		return domain_context_mapping_one(domain, iommu, bus, devfn);

	data.domain = domain;
	data.iommu = iommu;

	return pci_for_each_dma_alias(to_pci_dev(dev),
				      &domain_context_mapping_cb, &data);
}

static int domain_context_mapped_cb(struct pci_dev *pdev,
				    u16 alias, void *opaque)
{
	struct intel_iommu *iommu = opaque;

	return !device_context_mapped(iommu, PCI_BUS_NUM(alias), alias & 0xff);
}

static int domain_context_mapped(struct device *dev)
{
	struct intel_iommu *iommu;
	u8 bus, devfn;

	iommu = device_to_iommu(dev, &bus, &devfn);
	if (!iommu)
		return -ENODEV;

	if (!dev_is_pci(dev))
		return device_context_mapped(iommu, bus, devfn);

	return !pci_for_each_dma_alias(to_pci_dev(dev),
				       domain_context_mapped_cb, iommu);
}

/* Returns a number of VTD pages, but aligned to MM page size */
static inline unsigned long aligned_nrpages(unsigned long host_addr,
					    size_t size)
{
	host_addr &= ~PAGE_MASK;
	return PAGE_ALIGN(host_addr + size) >> VTD_PAGE_SHIFT;
}

/* Return largest possible superpage level for a given mapping */
static inline int hardware_largepage_caps(struct dmar_domain *domain,
					  unsigned long iov_pfn,
					  unsigned long phy_pfn,
					  unsigned long pages)
{
	int support, level = 1;
	unsigned long pfnmerge;

	support = domain->iommu_superpage;

	/* To use a large page, the virtual *and* physical addresses
	   must be aligned to 2MiB/1GiB/etc. Lower bits set in either
	   of them will mean we have to use smaller pages. So just
	   merge them and check both at once. */
	pfnmerge = iov_pfn | phy_pfn;

	while (support && !(pfnmerge & ~VTD_STRIDE_MASK)) {
		pages >>= VTD_STRIDE_SHIFT;
		if (!pages)
			break;
		pfnmerge >>= VTD_STRIDE_SHIFT;
		level++;
		support--;
	}
	return level;
}

static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
			    struct scatterlist *sg, unsigned long phys_pfn,
			    unsigned long nr_pages, int prot)
{
	struct dma_pte *first_pte = NULL, *pte = NULL;
	phys_addr_t uninitialized_var(pteval);
	unsigned long sg_res = 0;
	unsigned int largepage_lvl = 0;
	unsigned long lvl_pages = 0;

	BUG_ON(!domain_pfn_supported(domain, iov_pfn + nr_pages - 1));

	if ((prot & (DMA_PTE_READ|DMA_PTE_WRITE)) == 0)
		return -EINVAL;

	prot &= DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP;

	if (!sg) {
		sg_res = nr_pages;
		pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | prot;
	}

	while (nr_pages > 0) {
		uint64_t tmp;

		if (!sg_res) {
			sg_res = aligned_nrpages(sg->offset, sg->length);
			sg->dma_address = ((dma_addr_t)iov_pfn << VTD_PAGE_SHIFT) + sg->offset;
			sg->dma_length = sg->length;
			pteval = page_to_phys(sg_page(sg)) | prot;
			phys_pfn = pteval >> VTD_PAGE_SHIFT;
		}

		if (!pte) {
			largepage_lvl = hardware_largepage_caps(domain, iov_pfn, phys_pfn, sg_res);

			first_pte = pte = pfn_to_dma_pte(domain, iov_pfn, &largepage_lvl);
			if (!pte)
				return -ENOMEM;
			/* It is large page*/
			if (largepage_lvl > 1) {
				unsigned long nr_superpages, end_pfn;

				pteval |= DMA_PTE_LARGE_PAGE;
				lvl_pages = lvl_to_nr_pages(largepage_lvl);

				nr_superpages = sg_res / lvl_pages;
				end_pfn = iov_pfn + nr_superpages * lvl_pages - 1;

				/*
				 * Ensure that old small page tables are
				 * removed to make room for superpage(s).
				 */
				dma_pte_free_pagetable(domain, iov_pfn, end_pfn);
			} else {
				pteval &= ~(uint64_t)DMA_PTE_LARGE_PAGE;
			}

		}
		/* We don't need lock here, nobody else
		 * touches the iova range
		 */
		tmp = cmpxchg64_local(&pte->val, 0ULL, pteval);
		if (tmp) {
			static int dumps = 5;
			pr_crit("ERROR: DMA PTE for vPFN 0x%lx already set (to %llx not %llx)\n",
				iov_pfn, tmp, (unsigned long long)pteval);
			if (dumps) {
				dumps--;
				debug_dma_dump_mappings(NULL);
			}
			WARN_ON(1);
		}

		lvl_pages = lvl_to_nr_pages(largepage_lvl);

		BUG_ON(nr_pages < lvl_pages);
		BUG_ON(sg_res < lvl_pages);

		nr_pages -= lvl_pages;
		iov_pfn += lvl_pages;
		phys_pfn += lvl_pages;
		pteval += lvl_pages * VTD_PAGE_SIZE;
		sg_res -= lvl_pages;

		/* If the next PTE would be the first in a new page, then we
		   need to flush the cache on the entries we've just written.
		   And then we'll need to recalculate 'pte', so clear it and
		   let it get set again in the if (!pte) block above.

		   If we're done (!nr_pages) we need to flush the cache too.

		   Also if we've been setting superpages, we may need to
		   recalculate 'pte' and switch back to smaller pages for the
		   end of the mapping, if the trailing size is not enough to
		   use another superpage (i.e. sg_res < lvl_pages). */
		pte++;
		if (!nr_pages || first_pte_in_page(pte) ||
		    (largepage_lvl > 1 && sg_res < lvl_pages)) {
			domain_flush_cache(domain, first_pte,
					   (void *)pte - (void *)first_pte);
			pte = NULL;
		}

		if (!sg_res && nr_pages)
			sg = sg_next(sg);
	}
	return 0;
}

static inline int domain_sg_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
				    struct scatterlist *sg, unsigned long nr_pages,
				    int prot)
{
	return __domain_mapping(domain, iov_pfn, sg, 0, nr_pages, prot);
}

static inline int domain_pfn_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
				     unsigned long phys_pfn, unsigned long nr_pages,
				     int prot)
{
	return __domain_mapping(domain, iov_pfn, NULL, phys_pfn, nr_pages, prot);
}

static void domain_context_clear_one(struct intel_iommu *iommu, u8 bus, u8 devfn)
{
	if (!iommu)
		return;

	clear_context_table(iommu, bus, devfn);
	iommu->flush.flush_context(iommu, 0, 0, 0,
					   DMA_CCMD_GLOBAL_INVL);
	iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
}

static inline void unlink_domain_info(struct device_domain_info *info)
{
	assert_spin_locked(&device_domain_lock);
	list_del(&info->link);
	list_del(&info->global);
	if (info->dev)
		info->dev->archdata.iommu = NULL;
}

static void domain_remove_dev_info(struct dmar_domain *domain)
{
	struct device_domain_info *info, *tmp;
	unsigned long flags;

	spin_lock_irqsave(&device_domain_lock, flags);
	list_for_each_entry_safe(info, tmp, &domain->devices, link)
		__dmar_remove_one_dev_info(info);
	spin_unlock_irqrestore(&device_domain_lock, flags);
}

/*
 * find_domain
 * Note: we use struct device->archdata.iommu stores the info
 */
static struct dmar_domain *find_domain(struct device *dev)
{
	struct device_domain_info *info;

	/* No lock here, assumes no domain exit in normal case */
	info = dev->archdata.iommu;
	if (info)
		return info->domain;
	return NULL;
}

static inline struct device_domain_info *
dmar_search_domain_by_dev_info(int segment, int bus, int devfn)
{
	struct device_domain_info *info;

	list_for_each_entry(info, &device_domain_list, global)
		if (info->iommu->segment == segment && info->bus == bus &&
		    info->devfn == devfn)
			return info;

	return NULL;
}

static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
						    int bus, int devfn,
						    struct device *dev,
						    struct dmar_domain *domain)
{
	struct dmar_domain *found = NULL;
	struct device_domain_info *info;
	unsigned long flags;
	int ret;

	info = alloc_devinfo_mem();
	if (!info)
		return NULL;

	info->bus = bus;
	info->devfn = devfn;
	info->ats_supported = info->pasid_supported = info->pri_supported = 0;
	info->ats_enabled = info->pasid_enabled = info->pri_enabled = 0;
	info->ats_qdep = 0;
	info->dev = dev;
	info->domain = domain;
	info->iommu = iommu;

	if (dev && dev_is_pci(dev)) {
		struct pci_dev *pdev = to_pci_dev(info->dev);

		if (ecap_dev_iotlb_support(iommu->ecap) &&
		    pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ATS) &&
		    dmar_find_matched_atsr_unit(pdev))
			info->ats_supported = 1;

		if (ecs_enabled(iommu)) {
			if (pasid_enabled(iommu)) {
				int features = pci_pasid_features(pdev);
				if (features >= 0)
					info->pasid_supported = features | 1;
			}

			if (info->ats_supported && ecap_prs(iommu->ecap) &&
			    pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI))
				info->pri_supported = 1;
		}
	}

	spin_lock_irqsave(&device_domain_lock, flags);
	if (dev)
		found = find_domain(dev);

	if (!found) {
		struct device_domain_info *info2;
		info2 = dmar_search_domain_by_dev_info(iommu->segment, bus, devfn);
		if (info2) {
			found      = info2->domain;
			info2->dev = dev;
		}
	}

	if (found) {
		spin_unlock_irqrestore(&device_domain_lock, flags);
		free_devinfo_mem(info);
		/* Caller must free the original domain */
		return found;
	}

	spin_lock(&iommu->lock);
	ret = domain_attach_iommu(domain, iommu);
	spin_unlock(&iommu->lock);

	if (ret) {
		spin_unlock_irqrestore(&device_domain_lock, flags);
		free_devinfo_mem(info);
		return NULL;
	}

	list_add(&info->link, &domain->devices);
	list_add(&info->global, &device_domain_list);
	if (dev)
		dev->archdata.iommu = info;
	spin_unlock_irqrestore(&device_domain_lock, flags);

	if (dev && domain_context_mapping(domain, dev)) {
		pr_err("Domain context map for %s failed\n", dev_name(dev));
		dmar_remove_one_dev_info(domain, dev);
		return NULL;
	}

	return domain;
}

static int get_last_alias(struct pci_dev *pdev, u16 alias, void *opaque)
{
	*(u16 *)opaque = alias;
	return 0;
}

static struct dmar_domain *find_or_alloc_domain(struct device *dev, int gaw)
{
	struct device_domain_info *info = NULL;
	struct dmar_domain *domain = NULL;
	struct intel_iommu *iommu;
	u16 req_id, dma_alias;
	unsigned long flags;
	u8 bus, devfn;

	iommu = device_to_iommu(dev, &bus, &devfn);
	if (!iommu)
		return NULL;

	req_id = ((u16)bus << 8) | devfn;

	if (dev_is_pci(dev)) {
		struct pci_dev *pdev = to_pci_dev(dev);

		pci_for_each_dma_alias(pdev, get_last_alias, &dma_alias);

		spin_lock_irqsave(&device_domain_lock, flags);
		info = dmar_search_domain_by_dev_info(pci_domain_nr(pdev->bus),
						      PCI_BUS_NUM(dma_alias),
						      dma_alias & 0xff);
		if (info) {
			iommu = info->iommu;
			domain = info->domain;
		}
		spin_unlock_irqrestore(&device_domain_lock, flags);

		/* DMA alias already has a domain, use it */
		if (info)
			goto out;
	}

	/* Allocate and initialize new domain for the device */
	domain = alloc_domain(0);
	if (!domain)
		return NULL;
	if (domain_init(domain, iommu, gaw)) {
		domain_exit(domain);
		return NULL;
	}

out:

	return domain;
}

static struct dmar_domain *set_domain_for_dev(struct device *dev,
					      struct dmar_domain *domain)
{
	struct intel_iommu *iommu;
	struct dmar_domain *tmp;
	u16 req_id, dma_alias;
	u8 bus, devfn;

	iommu = device_to_iommu(dev, &bus, &devfn);
	if (!iommu)
		return NULL;

	req_id = ((u16)bus << 8) | devfn;

	if (dev_is_pci(dev)) {
		struct pci_dev *pdev = to_pci_dev(dev);

		pci_for_each_dma_alias(pdev, get_last_alias, &dma_alias);

		/* register PCI DMA alias device */
		if (req_id != dma_alias) {
			tmp = dmar_insert_one_dev_info(iommu, PCI_BUS_NUM(dma_alias),
					dma_alias & 0xff, NULL, domain);

			if (!tmp || tmp != domain)
				return tmp;
		}
	}

	tmp = dmar_insert_one_dev_info(iommu, bus, devfn, dev, domain);
	if (!tmp || tmp != domain)
		return tmp;

	return domain;
}

static struct dmar_domain *get_domain_for_dev(struct device *dev, int gaw)
{
	struct dmar_domain *domain, *tmp;

	domain = find_domain(dev);
	if (domain)
		goto out;

	domain = find_or_alloc_domain(dev, gaw);
	if (!domain)
		goto out;

	tmp = set_domain_for_dev(dev, domain);
	if (!tmp || domain != tmp) {
		domain_exit(domain);
		domain = tmp;
	}

out:

	return domain;
}

static int iommu_domain_identity_map(struct dmar_domain *domain,
				     unsigned long long start,
				     unsigned long long end)
{
	unsigned long first_vpfn = start >> VTD_PAGE_SHIFT;
	unsigned long last_vpfn = end >> VTD_PAGE_SHIFT;

	if (!reserve_iova(&domain->iovad, dma_to_mm_pfn(first_vpfn),
			  dma_to_mm_pfn(last_vpfn))) {
		pr_err("Reserving iova failed\n");
		return -ENOMEM;
	}

	pr_debug("Mapping reserved region %llx-%llx\n", start, end);
	/*
	 * RMRR range might have overlap with physical memory range,
	 * clear it first
	 */
	dma_pte_clear_range(domain, first_vpfn, last_vpfn);

	return domain_pfn_mapping(domain, first_vpfn, first_vpfn,
				  last_vpfn - first_vpfn + 1,
				  DMA_PTE_READ|DMA_PTE_WRITE);
}

static int domain_prepare_identity_map(struct device *dev,
				       struct dmar_domain *domain,
				       unsigned long long start,
				       unsigned long long end)
{
	/* For _hardware_ passthrough, don't bother. But for software
	   passthrough, we do it anyway -- it may indicate a memory
	   range which is reserved in E820, so which didn't get set
	   up to start with in si_domain */
	if (domain == si_domain && hw_pass_through) {
		pr_warn("Ignoring identity map for HW passthrough device %s [0x%Lx - 0x%Lx]\n",
			dev_name(dev), start, end);
		return 0;
	}

	pr_info("Setting identity map for device %s [0x%Lx - 0x%Lx]\n",
		dev_name(dev), start, end);

	if (end < start) {
		WARN(1, "Your BIOS is broken; RMRR ends before it starts!\n"
			"BIOS vendor: %s; Ver: %s; Product Version: %s\n",
			dmi_get_system_info(DMI_BIOS_VENDOR),
			dmi_get_system_info(DMI_BIOS_VERSION),
		     dmi_get_system_info(DMI_PRODUCT_VERSION));
		return -EIO;
	}

	if (end >> agaw_to_width(domain->agaw)) {
		WARN(1, "Your BIOS is broken; RMRR exceeds permitted address width (%d bits)\n"
		     "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
		     agaw_to_width(domain->agaw),
		     dmi_get_system_info(DMI_BIOS_VENDOR),
		     dmi_get_system_info(DMI_BIOS_VERSION),
		     dmi_get_system_info(DMI_PRODUCT_VERSION));
		return -EIO;
	}

	return iommu_domain_identity_map(domain, start, end);
}

static int iommu_prepare_identity_map(struct device *dev,
				      unsigned long long start,
				      unsigned long long end)
{
	struct dmar_domain *domain;
	int ret;

	domain = get_domain_for_dev(dev, DEFAULT_DOMAIN_ADDRESS_WIDTH);
	if (!domain)
		return -ENOMEM;

	ret = domain_prepare_identity_map(dev, domain, start, end);
	if (ret)
		domain_exit(domain);

	return ret;
}

static inline int iommu_prepare_rmrr_dev(struct dmar_rmrr_unit *rmrr,
					 struct device *dev)
{
	if (dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO)
		return 0;
	return iommu_prepare_identity_map(dev, rmrr->base_address,
					  rmrr->end_address);
}

#ifdef CONFIG_INTEL_IOMMU_FLOPPY_WA
static inline void iommu_prepare_isa(void)
{
	struct pci_dev *pdev;
	int ret;

	pdev = pci_get_class(PCI_CLASS_BRIDGE_ISA << 8, NULL);
	if (!pdev)
		return;

	pr_info("Prepare 0-16MiB unity mapping for LPC\n");
	ret = iommu_prepare_identity_map(&pdev->dev, 0, 16*1024*1024 - 1);

	if (ret)
		pr_err("Failed to create 0-16MiB identity map - floppy might not work\n");

	pci_dev_put(pdev);
}
#else
static inline void iommu_prepare_isa(void)
{
	return;
}
#endif /* !CONFIG_INTEL_IOMMU_FLPY_WA */

static int md_domain_init(struct dmar_domain *domain, int guest_width);

static int __init si_domain_init(int hw)
{
	int nid, ret = 0;

	si_domain = alloc_domain(DOMAIN_FLAG_STATIC_IDENTITY);
	if (!si_domain)
		return -EFAULT;

	if (md_domain_init(si_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) {
		domain_exit(si_domain);
		return -EFAULT;
	}

	pr_debug("Identity mapping domain allocated\n");

	if (hw)
		return 0;

	for_each_online_node(nid) {
		unsigned long start_pfn, end_pfn;
		int i;

		for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) {
			ret = iommu_domain_identity_map(si_domain,
					PFN_PHYS(start_pfn), PFN_PHYS(end_pfn));
			if (ret)
				return ret;
		}
	}

	return 0;
}

static int identity_mapping(struct device *dev)
{
	struct device_domain_info *info;

	if (likely(!iommu_identity_mapping))
		return 0;

	info = dev->archdata.iommu;
	if (info && info != DUMMY_DEVICE_DOMAIN_INFO)
		return (info->domain == si_domain);

	return 0;
}

static int domain_add_dev_info(struct dmar_domain *domain, struct device *dev)
{
	struct dmar_domain *ndomain;
	struct intel_iommu *iommu;
	u8 bus, devfn;

	iommu = device_to_iommu(dev, &bus, &devfn);
	if (!iommu)
		return -ENODEV;

	ndomain = dmar_insert_one_dev_info(iommu, bus, devfn, dev, domain);
	if (ndomain != domain)
		return -EBUSY;

	return 0;
}

static bool device_has_rmrr(struct device *dev)
{
	struct dmar_rmrr_unit *rmrr;
	struct device *tmp;
	int i;

	rcu_read_lock();
	for_each_rmrr_units(rmrr) {
		/*
		 * Return TRUE if this RMRR contains the device that
		 * is passed in.
		 */
		for_each_active_dev_scope(rmrr->devices,
					  rmrr->devices_cnt, i, tmp)
			if (tmp == dev) {
				rcu_read_unlock();
				return true;
			}
	}
	rcu_read_unlock();
	return false;
}

/*
 * There are a couple cases where we need to restrict the functionality of
 * devices associated with RMRRs.  The first is when evaluating a device for
 * identity mapping because problems exist when devices are moved in and out
 * of domains and their respective RMRR information is lost.  This means that
 * a device with associated RMRRs will never be in a "passthrough" domain.
 * The second is use of the device through the IOMMU API.  This interface
 * expects to have full control of the IOVA space for the device.  We cannot
 * satisfy both the requirement that RMRR access is maintained and have an
 * unencumbered IOVA space.  We also have no ability to quiesce the device's
 * use of the RMRR space or even inform the IOMMU API user of the restriction.
 * We therefore prevent devices associated with an RMRR from participating in
 * the IOMMU API, which eliminates them from device assignment.
 *
 * In both cases we assume that PCI USB devices with RMRRs have them largely
 * for historical reasons and that the RMRR space is not actively used post
 * boot.  This exclusion may change if vendors begin to abuse it.
 *
 * The same exception is made for graphics devices, with the requirement that
 * any use of the RMRR regions will be torn down before assigning the device
 * to a guest.
 */
static bool device_is_rmrr_locked(struct device *dev)
{
	if (!device_has_rmrr(dev))
		return false;

	if (dev_is_pci(dev)) {
		struct pci_dev *pdev = to_pci_dev(dev);

		if (IS_USB_DEVICE(pdev) || IS_GFX_DEVICE(pdev))
			return false;
	}

	return true;
}

static int iommu_should_identity_map(struct device *dev, int startup)
{

	if (dev_is_pci(dev)) {
		struct pci_dev *pdev = to_pci_dev(dev);

		if (device_is_rmrr_locked(dev))
			return 0;

		if ((iommu_identity_mapping & IDENTMAP_AZALIA) && IS_AZALIA(pdev))
			return 1;

		if ((iommu_identity_mapping & IDENTMAP_GFX) && IS_GFX_DEVICE(pdev))
			return 1;

		if (!(iommu_identity_mapping & IDENTMAP_ALL))
			return 0;

		/*
		 * We want to start off with all devices in the 1:1 domain, and
		 * take them out later if we find they can't access all of memory.
		 *
		 * However, we can't do this for PCI devices behind bridges,
		 * because all PCI devices behind the same bridge will end up
		 * with the same source-id on their transactions.
		 *
		 * Practically speaking, we can't change things around for these
		 * devices at run-time, because we can't be sure there'll be no
		 * DMA transactions in flight for any of their siblings.
		 *
		 * So PCI devices (unless they're on the root bus) as well as
		 * their parent PCI-PCI or PCIe-PCI bridges must be left _out_ of
		 * the 1:1 domain, just in _case_ one of their siblings turns out
		 * not to be able to map all of memory.
		 */
		if (!pci_is_pcie(pdev)) {
			if (!pci_is_root_bus(pdev->bus))
				return 0;
			if (pdev->class >> 8 == PCI_CLASS_BRIDGE_PCI)
				return 0;
		} else if (pci_pcie_type(pdev) == PCI_EXP_TYPE_PCI_BRIDGE)
			return 0;
	} else {
		if (device_has_rmrr(dev))
			return 0;
	}

	/*
	 * At boot time, we don't yet know if devices will be 64-bit capable.
	 * Assume that they will — if they turn out not to be, then we can
	 * take them out of the 1:1 domain later.
	 */
	if (!startup) {
		/*
		 * If the device's dma_mask is less than the system's memory
		 * size then this is not a candidate for identity mapping.
		 */
		u64 dma_mask = *dev->dma_mask;

		if (dev->coherent_dma_mask &&
		    dev->coherent_dma_mask < dma_mask)
			dma_mask = dev->coherent_dma_mask;

		return dma_mask >= dma_get_required_mask(dev);
	}

	return 1;
}

static int __init dev_prepare_static_identity_mapping(struct device *dev, int hw)
{
	int ret;

	if (!iommu_should_identity_map(dev, 1))
		return 0;

	ret = domain_add_dev_info(si_domain, dev);
	if (!ret)
		pr_info("%s identity mapping for device %s\n",
			hw ? "Hardware" : "Software", dev_name(dev));
	else if (ret == -ENODEV)
		/* device not associated with an iommu */
		ret = 0;

	return ret;
}


static int __init iommu_prepare_static_identity_mapping(int hw)
{
	struct pci_dev *pdev = NULL;
	struct dmar_drhd_unit *drhd;
	struct intel_iommu *iommu;
	struct device *dev;
	int i;
	int ret = 0;

	for_each_pci_dev(pdev) {
		ret = dev_prepare_static_identity_mapping(&pdev->dev, hw);
		if (ret)
			return ret;
	}

	for_each_active_iommu(iommu, drhd)
		for_each_active_dev_scope(drhd->devices, drhd->devices_cnt, i, dev) {
			struct acpi_device_physical_node *pn;
			struct acpi_device *adev;

			if (dev->bus != &acpi_bus_type)
				continue;

			adev= to_acpi_device(dev);
			mutex_lock(&adev->physical_node_lock);
			list_for_each_entry(pn, &adev->physical_node_list, node) {
				ret = dev_prepare_static_identity_mapping(pn->dev, hw);
				if (ret)
					break;
			}
			mutex_unlock(&adev->physical_node_lock);
			if (ret)
				return ret;
		}

	return 0;
}

static void intel_iommu_init_qi(struct intel_iommu *iommu)
{
	/*
	 * Start from the sane iommu hardware state.
	 * If the queued invalidation is already initialized by us
	 * (for example, while enabling interrupt-remapping) then
	 * we got the things already rolling from a sane state.
	 */
	if (!iommu->qi) {
		/*
		 * Clear any previous faults.
		 */
		dmar_fault(-1, iommu);
		/*
		 * Disable queued invalidation if supported and already enabled
		 * before OS handover.
		 */
		dmar_disable_qi(iommu);
	}

	if (dmar_enable_qi(iommu)) {
		/*
		 * Queued Invalidate not enabled, use Register Based Invalidate
		 */
		iommu->flush.flush_context = __iommu_flush_context;
		iommu->flush.flush_iotlb = __iommu_flush_iotlb;
		pr_info("%s: Using Register based invalidation\n",
			iommu->name);
	} else {
		iommu->flush.flush_context = qi_flush_context;
		iommu->flush.flush_iotlb = qi_flush_iotlb;
		pr_info("%s: Using Queued invalidation\n", iommu->name);
	}
}

static int copy_context_table(struct intel_iommu *iommu,
			      struct root_entry *old_re,
			      struct context_entry **tbl,
			      int bus, bool ext)
{
	int tbl_idx, pos = 0, idx, devfn, ret = 0, did;
	struct context_entry *new_ce = NULL, ce;
	struct context_entry *old_ce = NULL;
	struct root_entry re;
	phys_addr_t old_ce_phys;

	tbl_idx = ext ? bus * 2 : bus;
	memcpy(&re, old_re, sizeof(re));

	for (devfn = 0; devfn < 256; devfn++) {
		/* First calculate the correct index */
		idx = (ext ? devfn * 2 : devfn) % 256;

		if (idx == 0) {
			/* First save what we may have and clean up */
			if (new_ce) {
				tbl[tbl_idx] = new_ce;
				__iommu_flush_cache(iommu, new_ce,
						    VTD_PAGE_SIZE);
				pos = 1;
			}

			if (old_ce)
				iounmap(old_ce);

			ret = 0;
			if (devfn < 0x80)
				old_ce_phys = root_entry_lctp(&re);
			else
				old_ce_phys = root_entry_uctp(&re);

			if (!old_ce_phys) {
				if (ext && devfn == 0) {
					/* No LCTP, try UCTP */
					devfn = 0x7f;
					continue;
				} else {
					goto out;
				}
			}

			ret = -ENOMEM;
			old_ce = memremap(old_ce_phys, PAGE_SIZE,
					MEMREMAP_WB);
			if (!old_ce)
				goto out;

			new_ce = alloc_pgtable_page(iommu->node);
			if (!new_ce)
				goto out_unmap;

			ret = 0;
		}

		/* Now copy the context entry */
		memcpy(&ce, old_ce + idx, sizeof(ce));

		if (!__context_present(&ce))
			continue;

		did = context_domain_id(&ce);
		if (did >= 0 && did < cap_ndoms(iommu->cap))
			set_bit(did, iommu->domain_ids);

		/*
		 * We need a marker for copied context entries. This
		 * marker needs to work for the old format as well as
		 * for extended context entries.
		 *
		 * Bit 67 of the context entry is used. In the old
		 * format this bit is available to software, in the
		 * extended format it is the PGE bit, but PGE is ignored
		 * by HW if PASIDs are disabled (and thus still
		 * available).
		 *
		 * So disable PASIDs first and then mark the entry
		 * copied. This means that we don't copy PASID
		 * translations from the old kernel, but this is fine as
		 * faults there are not fatal.
		 */
		context_clear_pasid_enable(&ce);
		context_set_copied(&ce);

		new_ce[idx] = ce;
	}

	tbl[tbl_idx + pos] = new_ce;

	__iommu_flush_cache(iommu, new_ce, VTD_PAGE_SIZE);

out_unmap:
	memunmap(old_ce);

out:
	return ret;
}

static int copy_translation_tables(struct intel_iommu *iommu)
{
	struct context_entry **ctxt_tbls;
	struct root_entry *old_rt;
	phys_addr_t old_rt_phys;
	int ctxt_table_entries;
	unsigned long flags;
	u64 rtaddr_reg;
	int bus, ret;
	bool new_ext, ext;

	rtaddr_reg = dmar_readq(iommu->reg + DMAR_RTADDR_REG);
	ext        = !!(rtaddr_reg & DMA_RTADDR_RTT);
	new_ext    = !!ecap_ecs(iommu->ecap);

	/*
	 * The RTT bit can only be changed when translation is disabled,
	 * but disabling translation means to open a window for data
	 * corruption. So bail out and don't copy anything if we would
	 * have to change the bit.
	 */
	if (new_ext != ext)
		return -EINVAL;

	old_rt_phys = rtaddr_reg & VTD_PAGE_MASK;
	if (!old_rt_phys)
		return -EINVAL;

	old_rt = memremap(old_rt_phys, PAGE_SIZE, MEMREMAP_WB);
	if (!old_rt)
		return -ENOMEM;

	/* This is too big for the stack - allocate it from slab */
	ctxt_table_entries = ext ? 512 : 256;
	ret = -ENOMEM;
	ctxt_tbls = kzalloc(ctxt_table_entries * sizeof(void *), GFP_KERNEL);
	if (!ctxt_tbls)
		goto out_unmap;

	for (bus = 0; bus < 256; bus++) {
		ret = copy_context_table(iommu, &old_rt[bus],
					 ctxt_tbls, bus, ext);
		if (ret) {
			pr_err("%s: Failed to copy context table for bus %d\n",
				iommu->name, bus);
			continue;
		}
	}

	spin_lock_irqsave(&iommu->lock, flags);

	/* Context tables are copied, now write them to the root_entry table */
	for (bus = 0; bus < 256; bus++) {
		int idx = ext ? bus * 2 : bus;
		u64 val;

		if (ctxt_tbls[idx]) {
			val = virt_to_phys(ctxt_tbls[idx]) | 1;
			iommu->root_entry[bus].lo = val;
		}

		if (!ext || !ctxt_tbls[idx + 1])
			continue;

		val = virt_to_phys(ctxt_tbls[idx + 1]) | 1;
		iommu->root_entry[bus].hi = val;
	}

	spin_unlock_irqrestore(&iommu->lock, flags);

	kfree(ctxt_tbls);

	__iommu_flush_cache(iommu, iommu->root_entry, PAGE_SIZE);

	ret = 0;

out_unmap:
	memunmap(old_rt);

	return ret;
}

static int __init init_dmars(void)
{
	struct dmar_drhd_unit *drhd;
	struct dmar_rmrr_unit *rmrr;
	bool copied_tables = false;
	struct device *dev;
	struct intel_iommu *iommu;
	int i, ret, cpu;

	/*
	 * for each drhd
	 *    allocate root
	 *    initialize and program root entry to not present
	 * endfor
	 */
	for_each_drhd_unit(drhd) {
		/*
		 * lock not needed as this is only incremented in the single
		 * threaded kernel __init code path all other access are read
		 * only
		 */
		if (g_num_of_iommus < DMAR_UNITS_SUPPORTED) {
			g_num_of_iommus++;
			continue;
		}
		pr_err_once("Exceeded %d IOMMUs\n", DMAR_UNITS_SUPPORTED);
	}

	/* Preallocate enough resources for IOMMU hot-addition */
	if (g_num_of_iommus < DMAR_UNITS_SUPPORTED)
		g_num_of_iommus = DMAR_UNITS_SUPPORTED;

	g_iommus = kcalloc(g_num_of_iommus, sizeof(struct intel_iommu *),
			GFP_KERNEL);
	if (!g_iommus) {
		pr_err("Allocating global iommu array failed\n");
		ret = -ENOMEM;
		goto error;
	}

	for_each_possible_cpu(cpu) {
		struct deferred_flush_data *dfd = per_cpu_ptr(&deferred_flush,
							      cpu);

		dfd->tables = kzalloc(g_num_of_iommus *
				      sizeof(struct deferred_flush_table),
				      GFP_KERNEL);
		if (!dfd->tables) {
			ret = -ENOMEM;
			goto free_g_iommus;
		}

		spin_lock_init(&dfd->lock);
		setup_timer(&dfd->timer, flush_unmaps_timeout, cpu);
	}

	for_each_active_iommu(iommu, drhd) {
		g_iommus[iommu->seq_id] = iommu;

		intel_iommu_init_qi(iommu);

		ret = iommu_init_domains(iommu);
		if (ret)
			goto free_iommu;

		init_translation_status(iommu);

		if (translation_pre_enabled(iommu) && !is_kdump_kernel()) {
			iommu_disable_translation(iommu);
			clear_translation_pre_enabled(iommu);
			pr_warn("Translation was enabled for %s but we are not in kdump mode\n",
				iommu->name);
		}

		/*
		 * TBD:
		 * we could share the same root & context tables
		 * among all IOMMU's. Need to Split it later.
		 */
		ret = iommu_alloc_root_entry(iommu);
		if (ret)
			goto free_iommu;

		if (translation_pre_enabled(iommu)) {
			pr_info("Translation already enabled - trying to copy translation structures\n");

			ret = copy_translation_tables(iommu);
			if (ret) {
				/*
				 * We found the IOMMU with translation
				 * enabled - but failed to copy over the
				 * old root-entry table. Try to proceed
				 * by disabling translation now and
				 * allocating a clean root-entry table.
				 * This might cause DMAR faults, but
				 * probably the dump will still succeed.
				 */
				pr_err("Failed to copy translation tables from previous kernel for %s\n",
				       iommu->name);
				iommu_disable_translation(iommu);
				clear_translation_pre_enabled(iommu);
			} else {
				pr_info("Copied translation tables from previous kernel for %s\n",
					iommu->name);
				copied_tables = true;
			}
		}

		if (!ecap_pass_through(iommu->ecap))
			hw_pass_through = 0;
#ifdef CONFIG_INTEL_IOMMU_SVM
		if (pasid_enabled(iommu))
			intel_svm_alloc_pasid_tables(iommu);
#endif
	}

	/*
	 * Now that qi is enabled on all iommus, set the root entry and flush
	 * caches. This is required on some Intel X58 chipsets, otherwise the
	 * flush_context function will loop forever and the boot hangs.
	 */
	for_each_active_iommu(iommu, drhd) {
		iommu_flush_write_buffer(iommu);
		iommu_set_root_entry(iommu);
		iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL);
		iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
	}

	if (iommu_pass_through)
		iommu_identity_mapping |= IDENTMAP_ALL;

#ifdef CONFIG_INTEL_IOMMU_BROKEN_GFX_WA
	iommu_identity_mapping |= IDENTMAP_GFX;
#endif

	if (iommu_identity_mapping) {
		ret = si_domain_init(hw_pass_through);
		if (ret)
			goto free_iommu;
	}

	check_tylersburg_isoch();

	/*
	 * If we copied translations from a previous kernel in the kdump
	 * case, we can not assign the devices to domains now, as that
	 * would eliminate the old mappings. So skip this part and defer
	 * the assignment to device driver initialization time.
	 */
	if (copied_tables)
		goto domains_done;

	/*
	 * If pass through is not set or not enabled, setup context entries for
	 * identity mappings for rmrr, gfx, and isa and may fall back to static
	 * identity mapping if iommu_identity_mapping is set.
	 */
	if (iommu_identity_mapping) {
		ret = iommu_prepare_static_identity_mapping(hw_pass_through);
		if (ret) {
			pr_crit("Failed to setup IOMMU pass-through\n");
			goto free_iommu;
		}
	}
	/*
	 * For each rmrr
	 *   for each dev attached to rmrr
	 *   do
	 *     locate drhd for dev, alloc domain for dev
	 *     allocate free domain
	 *     allocate page table entries for rmrr
	 *     if context not allocated for bus
	 *           allocate and init context
	 *           set present in root table for this bus
	 *     init context with domain, translation etc
	 *    endfor
	 * endfor
	 */
	pr_info("Setting RMRR:\n");
	for_each_rmrr_units(rmrr) {
		/* some BIOS lists non-exist devices in DMAR table. */
		for_each_active_dev_scope(rmrr->devices, rmrr->devices_cnt,
					  i, dev) {
			ret = iommu_prepare_rmrr_dev(rmrr, dev);
			if (ret)
				pr_err("Mapping reserved region failed\n");
		}
	}

	iommu_prepare_isa();

domains_done:

	/*
	 * for each drhd
	 *   enable fault log
	 *   global invalidate context cache
	 *   global invalidate iotlb
	 *   enable translation
	 */
	for_each_iommu(iommu, drhd) {
		if (drhd->ignored) {
			/*
			 * we always have to disable PMRs or DMA may fail on
			 * this device
			 */
			if (force_on)
				iommu_disable_protect_mem_regions(iommu);
			continue;
		}

		iommu_flush_write_buffer(iommu);

#ifdef CONFIG_INTEL_IOMMU_SVM
		if (pasid_enabled(iommu) && ecap_prs(iommu->ecap)) {
			ret = intel_svm_enable_prq(iommu);
			if (ret)
				goto free_iommu;
		}
#endif
		ret = dmar_set_interrupt(iommu);
		if (ret)
			goto free_iommu;

		if (!translation_pre_enabled(iommu))
			iommu_enable_translation(iommu);

		iommu_disable_protect_mem_regions(iommu);
	}

	return 0;

free_iommu:
	for_each_active_iommu(iommu, drhd) {
		disable_dmar_iommu(iommu);
		free_dmar_iommu(iommu);
	}
free_g_iommus:
	for_each_possible_cpu(cpu)
		kfree(per_cpu_ptr(&deferred_flush, cpu)->tables);
	kfree(g_iommus);
error:
	return ret;
}

/* This takes a number of _MM_ pages, not VTD pages */
static unsigned long intel_alloc_iova(struct device *dev,
				     struct dmar_domain *domain,
				     unsigned long nrpages, uint64_t dma_mask)
{
	unsigned long iova_pfn = 0;

	/* Restrict dma_mask to the width that the iommu can handle */
	dma_mask = min_t(uint64_t, DOMAIN_MAX_ADDR(domain->gaw), dma_mask);
	/* Ensure we reserve the whole size-aligned region */
	nrpages = __roundup_pow_of_two(nrpages);

	if (!dmar_forcedac && dma_mask > DMA_BIT_MASK(32)) {
		/*
		 * First try to allocate an io virtual address in
		 * DMA_BIT_MASK(32) and if that fails then try allocating
		 * from higher range
		 */
		iova_pfn = alloc_iova_fast(&domain->iovad, nrpages,
					   IOVA_PFN(DMA_BIT_MASK(32)));
		if (iova_pfn)
			return iova_pfn;
	}
	iova_pfn = alloc_iova_fast(&domain->iovad, nrpages, IOVA_PFN(dma_mask));
	if (unlikely(!iova_pfn)) {
		pr_err("Allocating %ld-page iova for %s failed",
		       nrpages, dev_name(dev));
		return 0;
	}

	return iova_pfn;
}

static struct dmar_domain *__get_valid_domain_for_dev(struct device *dev)
{
	struct dmar_domain *domain, *tmp;
	struct dmar_rmrr_unit *rmrr;
	struct device *i_dev;
	int i, ret;

	domain = find_domain(dev);
	if (domain)
		goto out;

	domain = find_or_alloc_domain(dev, DEFAULT_DOMAIN_ADDRESS_WIDTH);
	if (!domain)
		goto out;

	/* We have a new domain - setup possible RMRRs for the device */
	rcu_read_lock();
	for_each_rmrr_units(rmrr) {
		for_each_active_dev_scope(rmrr->devices, rmrr->devices_cnt,
					  i, i_dev) {
			if (i_dev != dev)
				continue;

			ret = domain_prepare_identity_map(dev, domain,
							  rmrr->base_address,
							  rmrr->end_address);
			if (ret)
				dev_err(dev, "Mapping reserved region failed\n");
		}
	}
	rcu_read_unlock();

	tmp = set_domain_for_dev(dev, domain);
	if (!tmp || domain != tmp) {
		domain_exit(domain);
		domain = tmp;
	}

out:

	if (!domain)
		pr_err("Allocating domain for %s failed\n", dev_name(dev));


	return domain;
}

static inline struct dmar_domain *get_valid_domain_for_dev(struct device *dev)
{
	struct device_domain_info *info;

	/* No lock here, assumes no domain exit in normal case */
	info = dev->archdata.iommu;
	if (likely(info))
		return info->domain;

	return __get_valid_domain_for_dev(dev);
}

/* Check if the dev needs to go through non-identity map and unmap process.*/
static int iommu_no_mapping(struct device *dev)
{
	int found;

	if (iommu_dummy(dev))
		return 1;

	if (!iommu_identity_mapping)
		return 0;

	found = identity_mapping(dev);
	if (found) {
		if (iommu_should_identity_map(dev, 0))
			return 1;
		else {
			/*
			 * 32 bit DMA is removed from si_domain and fall back
			 * to non-identity mapping.
			 */
			dmar_remove_one_dev_info(si_domain, dev);
			pr_info("32bit %s uses non-identity mapping\n",
				dev_name(dev));
			return 0;
		}
	} else {
		/*
		 * In case of a detached 64 bit DMA device from vm, the device
		 * is put into si_domain for identity mapping.
		 */
		if (iommu_should_identity_map(dev, 0)) {
			int ret;
			ret = domain_add_dev_info(si_domain, dev);
			if (!ret) {
				pr_info("64bit %s uses identity mapping\n",
					dev_name(dev));
				return 1;
			}
		}
	}

	return 0;
}

static dma_addr_t __intel_map_single(struct device *dev, phys_addr_t paddr,
				     size_t size, int dir, u64 dma_mask)
{
	struct dmar_domain *domain;
	phys_addr_t start_paddr;
	unsigned long iova_pfn;
	int prot = 0;
	int ret;
	struct intel_iommu *iommu;
	unsigned long paddr_pfn = paddr >> PAGE_SHIFT;

	BUG_ON(dir == DMA_NONE);

	if (iommu_no_mapping(dev))
		return paddr;

	domain = get_valid_domain_for_dev(dev);
	if (!domain)
		return 0;

	iommu = domain_get_iommu(domain);
	size = aligned_nrpages(paddr, size);

	iova_pfn = intel_alloc_iova(dev, domain, dma_to_mm_pfn(size), dma_mask);
	if (!iova_pfn)
		goto error;

	/*
	 * Check if DMAR supports zero-length reads on write only
	 * mappings..
	 */
	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL || \
			!cap_zlr(iommu->cap))
		prot |= DMA_PTE_READ;
	if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)
		prot |= DMA_PTE_WRITE;
	/*
	 * paddr - (paddr + size) might be partial page, we should map the whole
	 * page.  Note: if two part of one page are separately mapped, we
	 * might have two guest_addr mapping to the same host paddr, but this
	 * is not a big problem
	 */
	ret = domain_pfn_mapping(domain, mm_to_dma_pfn(iova_pfn),
				 mm_to_dma_pfn(paddr_pfn), size, prot);
	if (ret)
		goto error;

	/* it's a non-present to present mapping. Only flush if caching mode */
	if (cap_caching_mode(iommu->cap))
		iommu_flush_iotlb_psi(iommu, domain,
				      mm_to_dma_pfn(iova_pfn),
				      size, 0, 1);
	else
		iommu_flush_write_buffer(iommu);

	start_paddr = (phys_addr_t)iova_pfn << PAGE_SHIFT;
	start_paddr += paddr & ~PAGE_MASK;
	return start_paddr;

error:
	if (iova_pfn)
		free_iova_fast(&domain->iovad, iova_pfn, dma_to_mm_pfn(size));
	pr_err("Device %s request: %zx@%llx dir %d --- failed\n",
		dev_name(dev), size, (unsigned long long)paddr, dir);
	return 0;
}

static dma_addr_t intel_map_page(struct device *dev, struct page *page,
				 unsigned long offset, size_t size,
				 enum dma_data_direction dir,
				 unsigned long attrs)
{
	return __intel_map_single(dev, page_to_phys(page) + offset, size,
				  dir, *dev->dma_mask);
}

static void flush_unmaps(struct deferred_flush_data *flush_data)
{
	int i, j;

	flush_data->timer_on = 0;

	/* just flush them all */
	for (i = 0; i < g_num_of_iommus; i++) {
		struct intel_iommu *iommu = g_iommus[i];
		struct deferred_flush_table *flush_table =
				&flush_data->tables[i];
		if (!iommu)
			continue;

		if (!flush_table->next)
			continue;

		/* In caching mode, global flushes turn emulation expensive */
		if (!cap_caching_mode(iommu->cap))
			iommu->flush.flush_iotlb(iommu, 0, 0, 0,
					 DMA_TLB_GLOBAL_FLUSH);
		for (j = 0; j < flush_table->next; j++) {
			unsigned long mask;
			struct deferred_flush_entry *entry =
						&flush_table->entries[j];
			unsigned long iova_pfn = entry->iova_pfn;
			unsigned long nrpages = entry->nrpages;
			struct dmar_domain *domain = entry->domain;
			struct page *freelist = entry->freelist;

			/* On real hardware multiple invalidations are expensive */
			if (cap_caching_mode(iommu->cap))
				iommu_flush_iotlb_psi(iommu, domain,
					mm_to_dma_pfn(iova_pfn),
					nrpages, !freelist, 0);
			else {
				mask = ilog2(nrpages);
				iommu_flush_dev_iotlb(domain,
						(uint64_t)iova_pfn << PAGE_SHIFT, mask);
			}
			free_iova_fast(&domain->iovad, iova_pfn, nrpages);
			if (freelist)
				dma_free_pagelist(freelist);
		}
		flush_table->next = 0;
	}

	flush_data->size = 0;
}

static void flush_unmaps_timeout(unsigned long cpuid)
{
	struct deferred_flush_data *flush_data = per_cpu_ptr(&deferred_flush, cpuid);
	unsigned long flags;

	spin_lock_irqsave(&flush_data->lock, flags);
	flush_unmaps(flush_data);
	spin_unlock_irqrestore(&flush_data->lock, flags);
}

static void add_unmap(struct dmar_domain *dom, unsigned long iova_pfn,
		      unsigned long nrpages, struct page *freelist)
{
	unsigned long flags;
	int entry_id, iommu_id;
	struct intel_iommu *iommu;
	struct deferred_flush_entry *entry;
	struct deferred_flush_data *flush_data;
	unsigned int cpuid;

	cpuid = get_cpu();
	flush_data = per_cpu_ptr(&deferred_flush, cpuid);

	/* Flush all CPUs' entries to avoid deferring too much.  If
	 * this becomes a bottleneck, can just flush us, and rely on
	 * flush timer for the rest.
	 */
	if (flush_data->size == HIGH_WATER_MARK) {
		int cpu;

		for_each_online_cpu(cpu)
			flush_unmaps_timeout(cpu);
	}

	spin_lock_irqsave(&flush_data->lock, flags);

	iommu = domain_get_iommu(dom);
	iommu_id = iommu->seq_id;

	entry_id = flush_data->tables[iommu_id].next;
	++(flush_data->tables[iommu_id].next);

	entry = &flush_data->tables[iommu_id].entries[entry_id];
	entry->domain = dom;
	entry->iova_pfn = iova_pfn;
	entry->nrpages = nrpages;
	entry->freelist = freelist;

	if (!flush_data->timer_on) {
		mod_timer(&flush_data->timer, jiffies + msecs_to_jiffies(10));
		flush_data->timer_on = 1;
	}
	flush_data->size++;
	spin_unlock_irqrestore(&flush_data->lock, flags);

	put_cpu();
}

static void intel_unmap(struct device *dev, dma_addr_t dev_addr, size_t size)
{
	struct dmar_domain *domain;
	unsigned long start_pfn, last_pfn;
	unsigned long nrpages;
	unsigned long iova_pfn;
	struct intel_iommu *iommu;
	struct page *freelist;

	if (iommu_no_mapping(dev))
		return;

	domain = find_domain(dev);
	BUG_ON(!domain);

	iommu = domain_get_iommu(domain);

	iova_pfn = IOVA_PFN(dev_addr);

	nrpages = aligned_nrpages(dev_addr, size);
	start_pfn = mm_to_dma_pfn(iova_pfn);
	last_pfn = start_pfn + nrpages - 1;

	pr_debug("Device %s unmapping: pfn %lx-%lx\n",
		 dev_name(dev), start_pfn, last_pfn);

	freelist = domain_unmap(domain, start_pfn, last_pfn);

	if (intel_iommu_strict) {
		iommu_flush_iotlb_psi(iommu, domain, start_pfn,
				      nrpages, !freelist, 0);
		/* free iova */
		free_iova_fast(&domain->iovad, iova_pfn, dma_to_mm_pfn(nrpages));
		dma_free_pagelist(freelist);
	} else {
		add_unmap(domain, iova_pfn, nrpages, freelist);
		/*
		 * queue up the release of the unmap to save the 1/6th of the
		 * cpu used up by the iotlb flush operation...
		 */
	}
}

static void intel_unmap_page(struct device *dev, dma_addr_t dev_addr,
			     size_t size, enum dma_data_direction dir,
			     unsigned long attrs)
{
	intel_unmap(dev, dev_addr, size);
}

static void *intel_alloc_coherent(struct device *dev, size_t size,
				  dma_addr_t *dma_handle, gfp_t flags,
				  unsigned long attrs)
{
	struct page *page = NULL;
	int order;

	size = PAGE_ALIGN(size);
	order = get_order(size);

	if (!iommu_no_mapping(dev))
		flags &= ~(GFP_DMA | GFP_DMA32);
	else if (dev->coherent_dma_mask < dma_get_required_mask(dev)) {
		if (dev->coherent_dma_mask < DMA_BIT_MASK(32))
			flags |= GFP_DMA;
		else
			flags |= GFP_DMA32;
	}

	if (gfpflags_allow_blocking(flags)) {
		unsigned int count = size >> PAGE_SHIFT;

		page = dma_alloc_from_contiguous(dev, count, order);
		if (page && iommu_no_mapping(dev) &&
		    page_to_phys(page) + size > dev->coherent_dma_mask) {
			dma_release_from_contiguous(dev, page, count);
			page = NULL;
		}
	}

	if (!page)
		page = alloc_pages(flags, order);
	if (!page)
		return NULL;
	memset(page_address(page), 0, size);

	*dma_handle = __intel_map_single(dev, page_to_phys(page), size,
					 DMA_BIDIRECTIONAL,
					 dev->coherent_dma_mask);
	if (*dma_handle)
		return page_address(page);
	if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
		__free_pages(page, order);

	return NULL;
}

static void intel_free_coherent(struct device *dev, size_t size, void *vaddr,
				dma_addr_t dma_handle, unsigned long attrs)
{
	int order;
	struct page *page = virt_to_page(vaddr);

	size = PAGE_ALIGN(size);
	order = get_order(size);

	intel_unmap(dev, dma_handle, size);
	if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
		__free_pages(page, order);
}

static void intel_unmap_sg(struct device *dev, struct scatterlist *sglist,
			   int nelems, enum dma_data_direction dir,
			   unsigned long attrs)
{
	dma_addr_t startaddr = sg_dma_address(sglist) & PAGE_MASK;
	unsigned long nrpages = 0;
	struct scatterlist *sg;
	int i;

	for_each_sg(sglist, sg, nelems, i) {
		nrpages += aligned_nrpages(sg_dma_address(sg), sg_dma_len(sg));
	}

	intel_unmap(dev, startaddr, nrpages << VTD_PAGE_SHIFT);
}

static int intel_nontranslate_map_sg(struct device *hddev,
	struct scatterlist *sglist, int nelems, int dir)
{
	int i;
	struct scatterlist *sg;

	for_each_sg(sglist, sg, nelems, i) {
		BUG_ON(!sg_page(sg));
		sg->dma_address = page_to_phys(sg_page(sg)) + sg->offset;
		sg->dma_length = sg->length;
	}
	return nelems;
}

static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nelems,
			enum dma_data_direction dir, unsigned long attrs)
{
	int i;
	struct dmar_domain *domain;
	size_t size = 0;
	int prot = 0;
	unsigned long iova_pfn;
	int ret;
	struct scatterlist *sg;
	unsigned long start_vpfn;
	struct intel_iommu *iommu;

	BUG_ON(dir == DMA_NONE);
	if (iommu_no_mapping(dev))
		return intel_nontranslate_map_sg(dev, sglist, nelems, dir);

	domain = get_valid_domain_for_dev(dev);
	if (!domain)
		return 0;

	iommu = domain_get_iommu(domain);

	for_each_sg(sglist, sg, nelems, i)
		size += aligned_nrpages(sg->offset, sg->length);

	iova_pfn = intel_alloc_iova(dev, domain, dma_to_mm_pfn(size),
				*dev->dma_mask);
	if (!iova_pfn) {
		sglist->dma_length = 0;
		return 0;
	}

	/*
	 * Check if DMAR supports zero-length reads on write only
	 * mappings..
	 */
	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL || \
			!cap_zlr(iommu->cap))
		prot |= DMA_PTE_READ;
	if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)
		prot |= DMA_PTE_WRITE;

	start_vpfn = mm_to_dma_pfn(iova_pfn);

	ret = domain_sg_mapping(domain, start_vpfn, sglist, size, prot);
	if (unlikely(ret)) {
		dma_pte_free_pagetable(domain, start_vpfn,
				       start_vpfn + size - 1);
		free_iova_fast(&domain->iovad, iova_pfn, dma_to_mm_pfn(size));
		return 0;
	}

	/* it's a non-present to present mapping. Only flush if caching mode */
	if (cap_caching_mode(iommu->cap))
		iommu_flush_iotlb_psi(iommu, domain, start_vpfn, size, 0, 1);
	else
		iommu_flush_write_buffer(iommu);

	return nelems;
}

static int intel_mapping_error(struct device *dev, dma_addr_t dma_addr)
{
	return !dma_addr;
}

struct dma_map_ops intel_dma_ops = {
	.alloc = intel_alloc_coherent,
	.free = intel_free_coherent,
	.map_sg = intel_map_sg,
	.unmap_sg = intel_unmap_sg,
	.map_page = intel_map_page,
	.unmap_page = intel_unmap_page,
	.mapping_error = intel_mapping_error,
};

static inline int iommu_domain_cache_init(void)
{
	int ret = 0;

	iommu_domain_cache = kmem_cache_create("iommu_domain",
					 sizeof(struct dmar_domain),
					 0,
					 SLAB_HWCACHE_ALIGN,

					 NULL);
	if (!iommu_domain_cache) {
		pr_err("Couldn't create iommu_domain cache\n");
		ret = -ENOMEM;
	}

	return ret;
}

static inline int iommu_devinfo_cache_init(void)
{
	int ret = 0;

	iommu_devinfo_cache = kmem_cache_create("iommu_devinfo",
					 sizeof(struct device_domain_info),
					 0,
					 SLAB_HWCACHE_ALIGN,
					 NULL);
	if (!iommu_devinfo_cache) {
		pr_err("Couldn't create devinfo cache\n");
		ret = -ENOMEM;
	}

	return ret;
}

static int __init iommu_init_mempool(void)
{
	int ret;
	ret = iova_cache_get();
	if (ret)
		return ret;

	ret = iommu_domain_cache_init();
	if (ret)
		goto domain_error;

	ret = iommu_devinfo_cache_init();
	if (!ret)
		return ret;

	kmem_cache_destroy(iommu_domain_cache);
domain_error:
	iova_cache_put();

	return -ENOMEM;
}

static void __init iommu_exit_mempool(void)
{
	kmem_cache_destroy(iommu_devinfo_cache);
	kmem_cache_destroy(iommu_domain_cache);
	iova_cache_put();
}

static void quirk_ioat_snb_local_iommu(struct pci_dev *pdev)
{
	struct dmar_drhd_unit *drhd;
	u32 vtbar;
	int rc;

	/* We know that this device on this chipset has its own IOMMU.
	 * If we find it under a different IOMMU, then the BIOS is lying
	 * to us. Hope that the IOMMU for this device is actually
	 * disabled, and it needs no translation...
	 */
	rc = pci_bus_read_config_dword(pdev->bus, PCI_DEVFN(0, 0), 0xb0, &vtbar);
	if (rc) {
		/* "can't" happen */
		dev_info(&pdev->dev, "failed to run vt-d quirk\n");
		return;
	}
	vtbar &= 0xffff0000;

	/* we know that the this iommu should be at offset 0xa000 from vtbar */
	drhd = dmar_find_matched_drhd_unit(pdev);
	if (WARN_TAINT_ONCE(!drhd || drhd->reg_base_addr - vtbar != 0xa000,
			    TAINT_FIRMWARE_WORKAROUND,
			    "BIOS assigned incorrect VT-d unit for Intel(R) QuickData Technology device\n"))
		pdev->dev.archdata.iommu = DUMMY_DEVICE_DOMAIN_INFO;
}
DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB, quirk_ioat_snb_local_iommu);

static void __init init_no_remapping_devices(void)
{
	struct dmar_drhd_unit *drhd;
	struct device *dev;
	int i;

	for_each_drhd_unit(drhd) {
		if (!drhd->include_all) {
			for_each_active_dev_scope(drhd->devices,
						  drhd->devices_cnt, i, dev)
				break;
			/* ignore DMAR unit if no devices exist */
			if (i == drhd->devices_cnt)
				drhd->ignored = 1;
		}
	}

	for_each_active_drhd_unit(drhd) {
		if (drhd->include_all)
			continue;

		for_each_active_dev_scope(drhd->devices,
					  drhd->devices_cnt, i, dev)
			if (!dev_is_pci(dev) || !IS_GFX_DEVICE(to_pci_dev(dev)))
				break;
		if (i < drhd->devices_cnt)
			continue;

		/* This IOMMU has *only* gfx devices. Either bypass it or
		   set the gfx_mapped flag, as appropriate */
		if (dmar_map_gfx) {
			intel_iommu_gfx_mapped = 1;
		} else {
			drhd->ignored = 1;
			for_each_active_dev_scope(drhd->devices,
						  drhd->devices_cnt, i, dev)
				dev->archdata.iommu = DUMMY_DEVICE_DOMAIN_INFO;
		}
	}
}

#ifdef CONFIG_SUSPEND
static int init_iommu_hw(void)
{
	struct dmar_drhd_unit *drhd;
	struct intel_iommu *iommu = NULL;

	for_each_active_iommu(iommu, drhd)
		if (iommu->qi)
			dmar_reenable_qi(iommu);

	for_each_iommu(iommu, drhd) {
		if (drhd->ignored) {
			/*
			 * we always have to disable PMRs or DMA may fail on
			 * this device
			 */
			if (force_on)
				iommu_disable_protect_mem_regions(iommu);
			continue;
		}
	
		iommu_flush_write_buffer(iommu);

		iommu_set_root_entry(iommu);

		iommu->flush.flush_context(iommu, 0, 0, 0,
					   DMA_CCMD_GLOBAL_INVL);
		iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
		iommu_enable_translation(iommu);
		iommu_disable_protect_mem_regions(iommu);
	}

	return 0;
}

static void iommu_flush_all(void)
{
	struct dmar_drhd_unit *drhd;
	struct intel_iommu *iommu;

	for_each_active_iommu(iommu, drhd) {
		iommu->flush.flush_context(iommu, 0, 0, 0,
					   DMA_CCMD_GLOBAL_INVL);
		iommu->flush.flush_iotlb(iommu, 0, 0, 0,
					 DMA_TLB_GLOBAL_FLUSH);
	}
}

static int iommu_suspend(void)
{
	struct dmar_drhd_unit *drhd;
	struct intel_iommu *iommu = NULL;
	unsigned long flag;

	for_each_active_iommu(iommu, drhd) {
		iommu->iommu_state = kzalloc(sizeof(u32) * MAX_SR_DMAR_REGS,
						 GFP_ATOMIC);
		if (!iommu->iommu_state)
			goto nomem;
	}

	iommu_flush_all();

	for_each_active_iommu(iommu, drhd) {
		iommu_disable_translation(iommu);

		raw_spin_lock_irqsave(&iommu->register_lock, flag);

		iommu->iommu_state[SR_DMAR_FECTL_REG] =
			readl(iommu->reg + DMAR_FECTL_REG);
		iommu->iommu_state[SR_DMAR_FEDATA_REG] =
			readl(iommu->reg + DMAR_FEDATA_REG);
		iommu->iommu_state[SR_DMAR_FEADDR_REG] =
			readl(iommu->reg + DMAR_FEADDR_REG);
		iommu->iommu_state[SR_DMAR_FEUADDR_REG] =
			readl(iommu->reg + DMAR_FEUADDR_REG);

		raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
	}
	return 0;

nomem:
	for_each_active_iommu(iommu, drhd)
		kfree(iommu->iommu_state);

	return -ENOMEM;
}

static void iommu_resume(void)
{
	struct dmar_drhd_unit *drhd;
	struct intel_iommu *iommu = NULL;
	unsigned long flag;

	if (init_iommu_hw()) {
		if (force_on)
			panic("tboot: IOMMU setup failed, DMAR can not resume!\n");
		else
			WARN(1, "IOMMU setup failed, DMAR can not resume!\n");
		return;
	}

	for_each_active_iommu(iommu, drhd) {

		raw_spin_lock_irqsave(&iommu->register_lock, flag);

		writel(iommu->iommu_state[SR_DMAR_FECTL_REG],
			iommu->reg + DMAR_FECTL_REG);
		writel(iommu->iommu_state[SR_DMAR_FEDATA_REG],
			iommu->reg + DMAR_FEDATA_REG);
		writel(iommu->iommu_state[SR_DMAR_FEADDR_REG],
			iommu->reg + DMAR_FEADDR_REG);
		writel(iommu->iommu_state[SR_DMAR_FEUADDR_REG],
			iommu->reg + DMAR_FEUADDR_REG);

		raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
	}

	for_each_active_iommu(iommu, drhd)
		kfree(iommu->iommu_state);
}

static struct syscore_ops iommu_syscore_ops = {
	.resume		= iommu_resume,
	.suspend	= iommu_suspend,
};

static void __init init_iommu_pm_ops(void)
{
	register_syscore_ops(&iommu_syscore_ops);
}

#else
static inline void init_iommu_pm_ops(void) {}
#endif	/* CONFIG_PM */


int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg)
{
	struct acpi_dmar_reserved_memory *rmrr;
	struct dmar_rmrr_unit *rmrru;

	rmrru = kzalloc(sizeof(*rmrru), GFP_KERNEL);
	if (!rmrru)
		return -ENOMEM;

	rmrru->hdr = header;
	rmrr = (struct acpi_dmar_reserved_memory *)header;
	rmrru->base_address = rmrr->base_address;
	rmrru->end_address = rmrr->end_address;
	rmrru->devices = dmar_alloc_dev_scope((void *)(rmrr + 1),
				((void *)rmrr) + rmrr->header.length,
				&rmrru->devices_cnt);
	if (rmrru->devices_cnt && rmrru->devices == NULL) {
		kfree(rmrru);
		return -ENOMEM;
	}

	list_add(&rmrru->list, &dmar_rmrr_units);

	return 0;
}

static struct dmar_atsr_unit *dmar_find_atsr(struct acpi_dmar_atsr *atsr)
{
	struct dmar_atsr_unit *atsru;
	struct acpi_dmar_atsr *tmp;

	list_for_each_entry_rcu(atsru, &dmar_atsr_units, list) {
		tmp = (struct acpi_dmar_atsr *)atsru->hdr;
		if (atsr->segment != tmp->segment)
			continue;
		if (atsr->header.length != tmp->header.length)
			continue;
		if (memcmp(atsr, tmp, atsr->header.length) == 0)
			return atsru;
	}

	return NULL;
}

int dmar_parse_one_atsr(struct acpi_dmar_header *hdr, void *arg)
{
	struct acpi_dmar_atsr *atsr;
	struct dmar_atsr_unit *atsru;

	if (system_state != SYSTEM_BOOTING && !intel_iommu_enabled)
		return 0;

	atsr = container_of(hdr, struct acpi_dmar_atsr, header);
	atsru = dmar_find_atsr(atsr);
	if (atsru)
		return 0;

	atsru = kzalloc(sizeof(*atsru) + hdr->length, GFP_KERNEL);
	if (!atsru)
		return -ENOMEM;

	/*
	 * If memory is allocated from slab by ACPI _DSM method, we need to
	 * copy the memory content because the memory buffer will be freed
	 * on return.
	 */
	atsru->hdr = (void *)(atsru + 1);
	memcpy(atsru->hdr, hdr, hdr->length);
	atsru->include_all = atsr->flags & 0x1;
	if (!atsru->include_all) {
		atsru->devices = dmar_alloc_dev_scope((void *)(atsr + 1),
				(void *)atsr + atsr->header.length,
				&atsru->devices_cnt);
		if (atsru->devices_cnt && atsru->devices == NULL) {
			kfree(atsru);
			return -ENOMEM;
		}
	}

	list_add_rcu(&atsru->list, &dmar_atsr_units);

	return 0;
}

static void intel_iommu_free_atsr(struct dmar_atsr_unit *atsru)
{
	dmar_free_dev_scope(&atsru->devices, &atsru->devices_cnt);
	kfree(atsru);
}

int dmar_release_one_atsr(struct acpi_dmar_header *hdr, void *arg)
{
	struct acpi_dmar_atsr *atsr;
	struct dmar_atsr_unit *atsru;

	atsr = container_of(hdr, struct acpi_dmar_atsr, header);
	atsru = dmar_find_atsr(atsr);
	if (atsru) {
		list_del_rcu(&atsru->list);
		synchronize_rcu();
		intel_iommu_free_atsr(atsru);
	}

	return 0;
}

int dmar_check_one_atsr(struct acpi_dmar_header *hdr, void *arg)
{
	int i;
	struct device *dev;
	struct acpi_dmar_atsr *atsr;
	struct dmar_atsr_unit *atsru;

	atsr = container_of(hdr, struct acpi_dmar_atsr, header);
	atsru = dmar_find_atsr(atsr);
	if (!atsru)
		return 0;

	if (!atsru->include_all && atsru->devices && atsru->devices_cnt) {
		for_each_active_dev_scope(atsru->devices, atsru->devices_cnt,
					  i, dev)
			return -EBUSY;
	}

	return 0;
}

static int intel_iommu_add(struct dmar_drhd_unit *dmaru)
{
	int sp, ret = 0;
	struct intel_iommu *iommu = dmaru->iommu;

	if (g_iommus[iommu->seq_id])
		return 0;

	if (hw_pass_through && !ecap_pass_through(iommu->ecap)) {
		pr_warn("%s: Doesn't support hardware pass through.\n",
			iommu->name);
		return -ENXIO;
	}
	if (!ecap_sc_support(iommu->ecap) &&
	    domain_update_iommu_snooping(iommu)) {
		pr_warn("%s: Doesn't support snooping.\n",
			iommu->name);
		return -ENXIO;
	}
	sp = domain_update_iommu_superpage(iommu) - 1;
	if (sp >= 0 && !(cap_super_page_val(iommu->cap) & (1 << sp))) {
		pr_warn("%s: Doesn't support large page.\n",
			iommu->name);
		return -ENXIO;
	}

	/*
	 * Disable translation if already enabled prior to OS handover.
	 */
	if (iommu->gcmd & DMA_GCMD_TE)
		iommu_disable_translation(iommu);

	g_iommus[iommu->seq_id] = iommu;
	ret = iommu_init_domains(iommu);
	if (ret == 0)
		ret = iommu_alloc_root_entry(iommu);
	if (ret)
		goto out;

#ifdef CONFIG_INTEL_IOMMU_SVM
	if (pasid_enabled(iommu))
		intel_svm_alloc_pasid_tables(iommu);
#endif

	if (dmaru->ignored) {
		/*
		 * we always have to disable PMRs or DMA may fail on this device
		 */
		if (force_on)
			iommu_disable_protect_mem_regions(iommu);
		return 0;
	}

	intel_iommu_init_qi(iommu);
	iommu_flush_write_buffer(iommu);

#ifdef CONFIG_INTEL_IOMMU_SVM
	if (pasid_enabled(iommu) && ecap_prs(iommu->ecap)) {
		ret = intel_svm_enable_prq(iommu);
		if (ret)
			goto disable_iommu;
	}
#endif
	ret = dmar_set_interrupt(iommu);
	if (ret)
		goto disable_iommu;

	iommu_set_root_entry(iommu);
	iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL);
	iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
	iommu_enable_translation(iommu);

	iommu_disable_protect_mem_regions(iommu);
	return 0;

disable_iommu:
	disable_dmar_iommu(iommu);
out:
	free_dmar_iommu(iommu);
	return ret;
}

int dmar_iommu_hotplug(struct dmar_drhd_unit *dmaru, bool insert)
{
	int ret = 0;
	struct intel_iommu *iommu = dmaru->iommu;

	if (!intel_iommu_enabled)
		return 0;
	if (iommu == NULL)
		return -EINVAL;

	if (insert) {
		ret = intel_iommu_add(dmaru);
	} else {
		disable_dmar_iommu(iommu);
		free_dmar_iommu(iommu);
	}

	return ret;
}

static void intel_iommu_free_dmars(void)
{
	struct dmar_rmrr_unit *rmrru, *rmrr_n;
	struct dmar_atsr_unit *atsru, *atsr_n;

	list_for_each_entry_safe(rmrru, rmrr_n, &dmar_rmrr_units, list) {
		list_del(&rmrru->list);
		dmar_free_dev_scope(&rmrru->devices, &rmrru->devices_cnt);
		kfree(rmrru);
	}

	list_for_each_entry_safe(atsru, atsr_n, &dmar_atsr_units, list) {
		list_del(&atsru->list);
		intel_iommu_free_atsr(atsru);
	}
}

int dmar_find_matched_atsr_unit(struct pci_dev *dev)
{
	int i, ret = 1;
	struct pci_bus *bus;
	struct pci_dev *bridge = NULL;
	struct device *tmp;
	struct acpi_dmar_atsr *atsr;
	struct dmar_atsr_unit *atsru;

	dev = pci_physfn(dev);
	for (bus = dev->bus; bus; bus = bus->parent) {
		bridge = bus->self;
		/* If it's an integrated device, allow ATS */
		if (!bridge)
			return 1;
		/* Connected via non-PCIe: no ATS */
		if (!pci_is_pcie(bridge) ||
		    pci_pcie_type(bridge) == PCI_EXP_TYPE_PCI_BRIDGE)
			return 0;
		/* If we found the root port, look it up in the ATSR */
		if (pci_pcie_type(bridge) == PCI_EXP_TYPE_ROOT_PORT)
			break;
	}

	rcu_read_lock();
	list_for_each_entry_rcu(atsru, &dmar_atsr_units, list) {
		atsr = container_of(atsru->hdr, struct acpi_dmar_atsr, header);
		if (atsr->segment != pci_domain_nr(dev->bus))
			continue;

		for_each_dev_scope(atsru->devices, atsru->devices_cnt, i, tmp)
			if (tmp == &bridge->dev)
				goto out;

		if (atsru->include_all)
			goto out;
	}
	ret = 0;
out:
	rcu_read_unlock();

	return ret;
}

int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info)
{
	int ret = 0;
	struct dmar_rmrr_unit *rmrru;
	struct dmar_atsr_unit *atsru;
	struct acpi_dmar_atsr *atsr;
	struct acpi_dmar_reserved_memory *rmrr;

	if (!intel_iommu_enabled && system_state != SYSTEM_BOOTING)
		return 0;

	list_for_each_entry(rmrru, &dmar_rmrr_units, list) {
		rmrr = container_of(rmrru->hdr,
				    struct acpi_dmar_reserved_memory, header);
		if (info->event == BUS_NOTIFY_ADD_DEVICE) {
			ret = dmar_insert_dev_scope(info, (void *)(rmrr + 1),
				((void *)rmrr) + rmrr->header.length,
				rmrr->segment, rmrru->devices,
				rmrru->devices_cnt);
			if(ret < 0)
				return ret;
		} else if (info->event == BUS_NOTIFY_REMOVED_DEVICE) {
			dmar_remove_dev_scope(info, rmrr->segment,
				rmrru->devices, rmrru->devices_cnt);
		}
	}

	list_for_each_entry(atsru, &dmar_atsr_units, list) {
		if (atsru->include_all)
			continue;

		atsr = container_of(atsru->hdr, struct acpi_dmar_atsr, header);
		if (info->event == BUS_NOTIFY_ADD_DEVICE) {
			ret = dmar_insert_dev_scope(info, (void *)(atsr + 1),
					(void *)atsr + atsr->header.length,
					atsr->segment, atsru->devices,
					atsru->devices_cnt);
			if (ret > 0)
				break;
			else if(ret < 0)
				return ret;
		} else if (info->event == BUS_NOTIFY_REMOVED_DEVICE) {
			if (dmar_remove_dev_scope(info, atsr->segment,
					atsru->devices, atsru->devices_cnt))
				break;
		}
	}

	return 0;
}

/*
 * Here we only respond to action of unbound device from driver.
 *
 * Added device is not attached to its DMAR domain here yet. That will happen
 * when mapping the device to iova.
 */
static int device_notifier(struct notifier_block *nb,
				  unsigned long action, void *data)
{
	struct device *dev = data;
	struct dmar_domain *domain;

	if (iommu_dummy(dev))
		return 0;

	if (action != BUS_NOTIFY_REMOVED_DEVICE)
		return 0;

	domain = find_domain(dev);
	if (!domain)
		return 0;

	dmar_remove_one_dev_info(domain, dev);
	if (!domain_type_is_vm_or_si(domain) && list_empty(&domain->devices))
		domain_exit(domain);

	return 0;
}

static struct notifier_block device_nb = {
	.notifier_call = device_notifier,
};

static int intel_iommu_memory_notifier(struct notifier_block *nb,
				       unsigned long val, void *v)
{
	struct memory_notify *mhp = v;
	unsigned long long start, end;
	unsigned long start_vpfn, last_vpfn;

	switch (val) {
	case MEM_GOING_ONLINE:
		start = mhp->start_pfn << PAGE_SHIFT;
		end = ((mhp->start_pfn + mhp->nr_pages) << PAGE_SHIFT) - 1;
		if (iommu_domain_identity_map(si_domain, start, end)) {
			pr_warn("Failed to build identity map for [%llx-%llx]\n",
				start, end);
			return NOTIFY_BAD;
		}
		break;

	case MEM_OFFLINE:
	case MEM_CANCEL_ONLINE:
		start_vpfn = mm_to_dma_pfn(mhp->start_pfn);
		last_vpfn = mm_to_dma_pfn(mhp->start_pfn + mhp->nr_pages - 1);
		while (start_vpfn <= last_vpfn) {
			struct iova *iova;
			struct dmar_drhd_unit *drhd;
			struct intel_iommu *iommu;
			struct page *freelist;

			iova = find_iova(&si_domain->iovad, start_vpfn);
			if (iova == NULL) {
				pr_debug("Failed get IOVA for PFN %lx\n",
					 start_vpfn);
				break;
			}

			iova = split_and_remove_iova(&si_domain->iovad, iova,
						     start_vpfn, last_vpfn);
			if (iova == NULL) {
				pr_warn("Failed to split IOVA PFN [%lx-%lx]\n",
					start_vpfn, last_vpfn);
				return NOTIFY_BAD;
			}

			freelist = domain_unmap(si_domain, iova->pfn_lo,
					       iova->pfn_hi);

			rcu_read_lock();
			for_each_active_iommu(iommu, drhd)
				iommu_flush_iotlb_psi(iommu, si_domain,
					iova->pfn_lo, iova_size(iova),
					!freelist, 0);
			rcu_read_unlock();
			dma_free_pagelist(freelist);

			start_vpfn = iova->pfn_hi + 1;
			free_iova_mem(iova);
		}
		break;
	}

	return NOTIFY_OK;
}

static struct notifier_block intel_iommu_memory_nb = {
	.notifier_call = intel_iommu_memory_notifier,
	.priority = 0
};

static void free_all_cpu_cached_iovas(unsigned int cpu)
{
	int i;

	for (i = 0; i < g_num_of_iommus; i++) {
		struct intel_iommu *iommu = g_iommus[i];
		struct dmar_domain *domain;
		int did;

		if (!iommu)
			continue;

		for (did = 0; did < cap_ndoms(iommu->cap); did++) {
			domain = get_iommu_domain(iommu, (u16)did);

			if (!domain)
				continue;
			free_cpu_cached_iovas(cpu, &domain->iovad);
		}
	}
}

static int intel_iommu_cpu_notifier(struct notifier_block *nfb,
				    unsigned long action, void *v)
{
	unsigned int cpu = (unsigned long)v;

	switch (action) {
	case CPU_DEAD:
	case CPU_DEAD_FROZEN:
		free_all_cpu_cached_iovas(cpu);
		flush_unmaps_timeout(cpu);
		break;
	}
	return NOTIFY_OK;
}

static struct notifier_block intel_iommu_cpu_nb = {
	.notifier_call = intel_iommu_cpu_notifier,
};

static ssize_t intel_iommu_show_version(struct device *dev,
					struct device_attribute *attr,
					char *buf)
{
	struct intel_iommu *iommu = dev_get_drvdata(dev);
	u32 ver = readl(iommu->reg + DMAR_VER_REG);
	return sprintf(buf, "%d:%d\n",
		       DMAR_VER_MAJOR(ver), DMAR_VER_MINOR(ver));
}
static DEVICE_ATTR(version, S_IRUGO, intel_iommu_show_version, NULL);

static ssize_t intel_iommu_show_address(struct device *dev,
					struct device_attribute *attr,
					char *buf)
{
	struct intel_iommu *iommu = dev_get_drvdata(dev);
	return sprintf(buf, "%llx\n", iommu->reg_phys);
}
static DEVICE_ATTR(address, S_IRUGO, intel_iommu_show_address, NULL);

static ssize_t intel_iommu_show_cap(struct device *dev,
				    struct device_attribute *attr,
				    char *buf)
{
	struct intel_iommu *iommu = dev_get_drvdata(dev);
	return sprintf(buf, "%llx\n", iommu->cap);
}
static DEVICE_ATTR(cap, S_IRUGO, intel_iommu_show_cap, NULL);

static ssize_t intel_iommu_show_ecap(struct device *dev,
				    struct device_attribute *attr,
				    char *buf)
{
	struct intel_iommu *iommu = dev_get_drvdata(dev);
	return sprintf(buf, "%llx\n", iommu->ecap);
}
static DEVICE_ATTR(ecap, S_IRUGO, intel_iommu_show_ecap, NULL);

static ssize_t intel_iommu_show_ndoms(struct device *dev,
				      struct device_attribute *attr,
				      char *buf)
{
	struct intel_iommu *iommu = dev_get_drvdata(dev);
	return sprintf(buf, "%ld\n", cap_ndoms(iommu->cap));
}
static DEVICE_ATTR(domains_supported, S_IRUGO, intel_iommu_show_ndoms, NULL);

static ssize_t intel_iommu_show_ndoms_used(struct device *dev,
					   struct device_attribute *attr,
					   char *buf)
{
	struct intel_iommu *iommu = dev_get_drvdata(dev);
	return sprintf(buf, "%d\n", bitmap_weight(iommu->domain_ids,
						  cap_ndoms(iommu->cap)));
}
static DEVICE_ATTR(domains_used, S_IRUGO, intel_iommu_show_ndoms_used, NULL);

static struct attribute *intel_iommu_attrs[] = {
	&dev_attr_version.attr,
	&dev_attr_address.attr,
	&dev_attr_cap.attr,
	&dev_attr_ecap.attr,
	&dev_attr_domains_supported.attr,
	&dev_attr_domains_used.attr,
	NULL,
};

static struct attribute_group intel_iommu_group = {
	.name = "intel-iommu",
	.attrs = intel_iommu_attrs,
};

const struct attribute_group *intel_iommu_groups[] = {
	&intel_iommu_group,
	NULL,
};

int __init intel_iommu_init(void)
{
	int ret = -ENODEV;
	struct dmar_drhd_unit *drhd;
	struct intel_iommu *iommu;

	/* VT-d is required for a TXT/tboot launch, so enforce that */
	force_on = tboot_force_iommu();

	if (iommu_init_mempool()) {
		if (force_on)
			panic("tboot: Failed to initialize iommu memory\n");
		return -ENOMEM;
	}

	down_write(&dmar_global_lock);
	if (dmar_table_init()) {
		if (force_on)
			panic("tboot: Failed to initialize DMAR table\n");
		goto out_free_dmar;
	}

	if (dmar_dev_scope_init() < 0) {
		if (force_on)
			panic("tboot: Failed to initialize DMAR device scope\n");
		goto out_free_dmar;
	}

	if (no_iommu || dmar_disabled)
		goto out_free_dmar;

	if (list_empty(&dmar_rmrr_units))
		pr_info("No RMRR found\n");

	if (list_empty(&dmar_atsr_units))
		pr_info("No ATSR found\n");

	if (dmar_init_reserved_ranges()) {
		if (force_on)
			panic("tboot: Failed to reserve iommu ranges\n");
		goto out_free_reserved_range;
	}

	init_no_remapping_devices();

	ret = init_dmars();
	if (ret) {
		if (force_on)
			panic("tboot: Failed to initialize DMARs\n");
		pr_err("Initialization failed\n");
		goto out_free_reserved_range;
	}
	up_write(&dmar_global_lock);
	pr_info("Intel(R) Virtualization Technology for Directed I/O\n");

#ifdef CONFIG_SWIOTLB
	swiotlb = 0;
#endif
	dma_ops = &intel_dma_ops;

	init_iommu_pm_ops();

	for_each_active_iommu(iommu, drhd)
		iommu->iommu_dev = iommu_device_create(NULL, iommu,
						       intel_iommu_groups,
						       "%s", iommu->name);

	bus_set_iommu(&pci_bus_type, &intel_iommu_ops);
	bus_register_notifier(&pci_bus_type, &device_nb);
	if (si_domain && !hw_pass_through)
		register_memory_notifier(&intel_iommu_memory_nb);
	register_hotcpu_notifier(&intel_iommu_cpu_nb);

	intel_iommu_enabled = 1;

	return 0;

out_free_reserved_range:
	put_iova_domain(&reserved_iova_list);
out_free_dmar:
	intel_iommu_free_dmars();
	up_write(&dmar_global_lock);
	iommu_exit_mempool();
	return ret;
}

static int domain_context_clear_one_cb(struct pci_dev *pdev, u16 alias, void *opaque)
{
	struct intel_iommu *iommu = opaque;

	domain_context_clear_one(iommu, PCI_BUS_NUM(alias), alias & 0xff);
	return 0;
}

/*
 * NB - intel-iommu lacks any sort of reference counting for the users of
 * dependent devices.  If multiple endpoints have intersecting dependent
 * devices, unbinding the driver from any one of them will possibly leave
 * the others unable to operate.
 */
static void domain_context_clear(struct intel_iommu *iommu, struct device *dev)
{
	if (!iommu || !dev || !dev_is_pci(dev))
		return;

	pci_for_each_dma_alias(to_pci_dev(dev), &domain_context_clear_one_cb, iommu);
}

static void __dmar_remove_one_dev_info(struct device_domain_info *info)
{
	struct intel_iommu *iommu;
	unsigned long flags;

	assert_spin_locked(&device_domain_lock);

	if (WARN_ON(!info))
		return;

	iommu = info->iommu;

	if (info->dev) {
		iommu_disable_dev_iotlb(info);
		domain_context_clear(iommu, info->dev);
	}

	unlink_domain_info(info);

	spin_lock_irqsave(&iommu->lock, flags);
	domain_detach_iommu(info->domain, iommu);
	spin_unlock_irqrestore(&iommu->lock, flags);

	free_devinfo_mem(info);
}

static void dmar_remove_one_dev_info(struct dmar_domain *domain,
				     struct device *dev)
{
	struct device_domain_info *info;
	unsigned long flags;

	spin_lock_irqsave(&device_domain_lock, flags);
	info = dev->archdata.iommu;
	__dmar_remove_one_dev_info(info);
	spin_unlock_irqrestore(&device_domain_lock, flags);
}

static int md_domain_init(struct dmar_domain *domain, int guest_width)
{
	int adjust_width;

	init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN,
			DMA_32BIT_PFN);
	domain_reserve_special_ranges(domain);

	/* calculate AGAW */
	domain->gaw = guest_width;
	adjust_width = guestwidth_to_adjustwidth(guest_width);
	domain->agaw = width_to_agaw(adjust_width);

	domain->iommu_coherency = 0;
	domain->iommu_snooping = 0;
	domain->iommu_superpage = 0;
	domain->max_addr = 0;

	/* always allocate the top pgd */
	domain->pgd = (struct dma_pte *)alloc_pgtable_page(domain->nid);
	if (!domain->pgd)
		return -ENOMEM;
	domain_flush_cache(domain, domain->pgd, PAGE_SIZE);
	return 0;
}

static struct iommu_domain *intel_iommu_domain_alloc(unsigned type)
{
	struct dmar_domain *dmar_domain;
	struct iommu_domain *domain;

	if (type != IOMMU_DOMAIN_UNMANAGED)
		return NULL;

	dmar_domain = alloc_domain(DOMAIN_FLAG_VIRTUAL_MACHINE);
	if (!dmar_domain) {
		pr_err("Can't allocate dmar_domain\n");
		return NULL;
	}
	if (md_domain_init(dmar_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) {
		pr_err("Domain initialization failed\n");
		domain_exit(dmar_domain);
		return NULL;
	}
	domain_update_iommu_cap(dmar_domain);

	domain = &dmar_domain->domain;
	domain->geometry.aperture_start = 0;
	domain->geometry.aperture_end   = __DOMAIN_MAX_ADDR(dmar_domain->gaw);
	domain->geometry.force_aperture = true;

	return domain;
}

static void intel_iommu_domain_free(struct iommu_domain *domain)
{
	domain_exit(to_dmar_domain(domain));
}

static int intel_iommu_attach_device(struct iommu_domain *domain,
				     struct device *dev)
{
	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
	struct intel_iommu *iommu;
	int addr_width;
	u8 bus, devfn;

	if (device_is_rmrr_locked(dev)) {
		dev_warn(dev, "Device is ineligible for IOMMU domain attach due to platform RMRR requirement.  Contact your platform vendor.\n");
		return -EPERM;
	}

	/* normally dev is not mapped */
	if (unlikely(domain_context_mapped(dev))) {
		struct dmar_domain *old_domain;

		old_domain = find_domain(dev);
		if (old_domain) {
			rcu_read_lock();
			dmar_remove_one_dev_info(old_domain, dev);
			rcu_read_unlock();

			if (!domain_type_is_vm_or_si(old_domain) &&
			     list_empty(&old_domain->devices))
				domain_exit(old_domain);
		}
	}

	iommu = device_to_iommu(dev, &bus, &devfn);
	if (!iommu)
		return -ENODEV;

	/* check if this iommu agaw is sufficient for max mapped address */
	addr_width = agaw_to_width(iommu->agaw);
	if (addr_width > cap_mgaw(iommu->cap))
		addr_width = cap_mgaw(iommu->cap);

	if (dmar_domain->max_addr > (1LL << addr_width)) {
		pr_err("%s: iommu width (%d) is not "
		       "sufficient for the mapped address (%llx)\n",
		       __func__, addr_width, dmar_domain->max_addr);
		return -EFAULT;
	}
	dmar_domain->gaw = addr_width;

	/*
	 * Knock out extra levels of page tables if necessary
	 */
	while (iommu->agaw < dmar_domain->agaw) {
		struct dma_pte *pte;

		pte = dmar_domain->pgd;
		if (dma_pte_present(pte)) {
			dmar_domain->pgd = (struct dma_pte *)
				phys_to_virt(dma_pte_addr(pte));
			free_pgtable_page(pte);
		}
		dmar_domain->agaw--;
	}

	return domain_add_dev_info(dmar_domain, dev);
}

static void intel_iommu_detach_device(struct iommu_domain *domain,
				      struct device *dev)
{
	dmar_remove_one_dev_info(to_dmar_domain(domain), dev);
}

static int intel_iommu_map(struct iommu_domain *domain,
			   unsigned long iova, phys_addr_t hpa,
			   size_t size, int iommu_prot)
{
	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
	u64 max_addr;
	int prot = 0;
	int ret;

	if (iommu_prot & IOMMU_READ)
		prot |= DMA_PTE_READ;
	if (iommu_prot & IOMMU_WRITE)
		prot |= DMA_PTE_WRITE;
	if ((iommu_prot & IOMMU_CACHE) && dmar_domain->iommu_snooping)
		prot |= DMA_PTE_SNP;

	max_addr = iova + size;
	if (dmar_domain->max_addr < max_addr) {
		u64 end;

		/* check if minimum agaw is sufficient for mapped address */
		end = __DOMAIN_MAX_ADDR(dmar_domain->gaw) + 1;
		if (end < max_addr) {
			pr_err("%s: iommu width (%d) is not "
			       "sufficient for the mapped address (%llx)\n",
			       __func__, dmar_domain->gaw, max_addr);
			return -EFAULT;
		}
		dmar_domain->max_addr = max_addr;
	}
	/* Round up size to next multiple of PAGE_SIZE, if it and
	   the low bits of hpa would take us onto the next page */
	size = aligned_nrpages(hpa, size);
	ret = domain_pfn_mapping(dmar_domain, iova >> VTD_PAGE_SHIFT,
				 hpa >> VTD_PAGE_SHIFT, size, prot);
	return ret;
}

static size_t intel_iommu_unmap(struct iommu_domain *domain,
				unsigned long iova, size_t size)
{
	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
	struct page *freelist = NULL;
	struct intel_iommu *iommu;
	unsigned long start_pfn, last_pfn;
	unsigned int npages;
	int iommu_id, level = 0;

	/* Cope with horrid API which requires us to unmap more than the
	   size argument if it happens to be a large-page mapping. */
	BUG_ON(!pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level));

	if (size < VTD_PAGE_SIZE << level_to_offset_bits(level))
		size = VTD_PAGE_SIZE << level_to_offset_bits(level);

	start_pfn = iova >> VTD_PAGE_SHIFT;
	last_pfn = (iova + size - 1) >> VTD_PAGE_SHIFT;

	freelist = domain_unmap(dmar_domain, start_pfn, last_pfn);

	npages = last_pfn - start_pfn + 1;

	for_each_domain_iommu(iommu_id, dmar_domain) {
		iommu = g_iommus[iommu_id];

		iommu_flush_iotlb_psi(g_iommus[iommu_id], dmar_domain,
				      start_pfn, npages, !freelist, 0);
	}

	dma_free_pagelist(freelist);

	if (dmar_domain->max_addr == iova + size)
		dmar_domain->max_addr = iova;

	return size;
}

static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
					    dma_addr_t iova)
{
	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
	struct dma_pte *pte;
	int level = 0;
	u64 phys = 0;

	pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level);
	if (pte)
		phys = dma_pte_addr(pte);

	return phys;
}

static bool intel_iommu_capable(enum iommu_cap cap)
{
	if (cap == IOMMU_CAP_CACHE_COHERENCY)
		return domain_update_iommu_snooping(NULL) == 1;
	if (cap == IOMMU_CAP_INTR_REMAP)
		return irq_remapping_enabled == 1;

	return false;
}

static int intel_iommu_add_device(struct device *dev)
{
	struct intel_iommu *iommu;
	struct iommu_group *group;
	u8 bus, devfn;

	iommu = device_to_iommu(dev, &bus, &devfn);
	if (!iommu)
		return -ENODEV;

	iommu_device_link(iommu->iommu_dev, dev);

	group = iommu_group_get_for_dev(dev);

	if (IS_ERR(group))
		return PTR_ERR(group);

	iommu_group_put(group);
	return 0;
}

static void intel_iommu_remove_device(struct device *dev)
{
	struct intel_iommu *iommu;
	u8 bus, devfn;

	iommu = device_to_iommu(dev, &bus, &devfn);
	if (!iommu)
		return;

	iommu_group_remove_device(dev);

	iommu_device_unlink(iommu->iommu_dev, dev);
}

#ifdef CONFIG_INTEL_IOMMU_SVM
int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sdev)
{
	struct device_domain_info *info;
	struct context_entry *context;
	struct dmar_domain *domain;
	unsigned long flags;
	u64 ctx_lo;
	int ret;

	domain = get_valid_domain_for_dev(sdev->dev);
	if (!domain)
		return -EINVAL;

	spin_lock_irqsave(&device_domain_lock, flags);
	spin_lock(&iommu->lock);

	ret = -EINVAL;
	info = sdev->dev->archdata.iommu;
	if (!info || !info->pasid_supported)
		goto out;

	context = iommu_context_addr(iommu, info->bus, info->devfn, 0);
	if (WARN_ON(!context))
		goto out;

	ctx_lo = context[0].lo;

	sdev->did = domain->iommu_did[iommu->seq_id];
	sdev->sid = PCI_DEVID(info->bus, info->devfn);

	if (!(ctx_lo & CONTEXT_PASIDE)) {
		context[1].hi = (u64)virt_to_phys(iommu->pasid_state_table);
		context[1].lo = (u64)virt_to_phys(iommu->pasid_table) | ecap_pss(iommu->ecap);
		wmb();
		/* CONTEXT_TT_MULTI_LEVEL and CONTEXT_TT_DEV_IOTLB are both
		 * extended to permit requests-with-PASID if the PASIDE bit
		 * is set. which makes sense. For CONTEXT_TT_PASS_THROUGH,
		 * however, the PASIDE bit is ignored and requests-with-PASID
		 * are unconditionally blocked. Which makes less sense.
		 * So convert from CONTEXT_TT_PASS_THROUGH to one of the new
		 * "guest mode" translation types depending on whether ATS
		 * is available or not. Annoyingly, we can't use the new
		 * modes *unless* PASIDE is set. */
		if ((ctx_lo & CONTEXT_TT_MASK) == (CONTEXT_TT_PASS_THROUGH << 2)) {
			ctx_lo &= ~CONTEXT_TT_MASK;
			if (info->ats_supported)
				ctx_lo |= CONTEXT_TT_PT_PASID_DEV_IOTLB << 2;
			else
				ctx_lo |= CONTEXT_TT_PT_PASID << 2;
		}
		ctx_lo |= CONTEXT_PASIDE;
		if (iommu->pasid_state_table)
			ctx_lo |= CONTEXT_DINVE;
		if (info->pri_supported)
			ctx_lo |= CONTEXT_PRS;
		context[0].lo = ctx_lo;
		wmb();
		iommu->flush.flush_context(iommu, sdev->did, sdev->sid,
					   DMA_CCMD_MASK_NOBIT,
					   DMA_CCMD_DEVICE_INVL);
	}

	/* Enable PASID support in the device, if it wasn't already */
	if (!info->pasid_enabled)
		iommu_enable_dev_iotlb(info);

	if (info->ats_enabled) {
		sdev->dev_iotlb = 1;
		sdev->qdep = info->ats_qdep;
		if (sdev->qdep >= QI_DEV_EIOTLB_MAX_INVS)
			sdev->qdep = 0;
	}
	ret = 0;

 out:
	spin_unlock(&iommu->lock);
	spin_unlock_irqrestore(&device_domain_lock, flags);

	return ret;
}

struct intel_iommu *intel_svm_device_to_iommu(struct device *dev)
{
	struct intel_iommu *iommu;
	u8 bus, devfn;

	if (iommu_dummy(dev)) {
		dev_warn(dev,
			 "No IOMMU translation for device; cannot enable SVM\n");
		return NULL;
	}

	iommu = device_to_iommu(dev, &bus, &devfn);
	if ((!iommu)) {
		dev_err(dev, "No IOMMU for device; cannot enable SVM\n");
		return NULL;
	}

	if (!iommu->pasid_table) {
		dev_err(dev, "PASID not enabled on IOMMU; cannot enable SVM\n");
		return NULL;
	}

	return iommu;
}
#endif /* CONFIG_INTEL_IOMMU_SVM */

static const struct iommu_ops intel_iommu_ops = {
	.capable	= intel_iommu_capable,
	.domain_alloc	= intel_iommu_domain_alloc,
	.domain_free	= intel_iommu_domain_free,
	.attach_dev	= intel_iommu_attach_device,
	.detach_dev	= intel_iommu_detach_device,
	.map		= intel_iommu_map,
	.unmap		= intel_iommu_unmap,
	.map_sg		= default_iommu_map_sg,
	.iova_to_phys	= intel_iommu_iova_to_phys,
	.add_device	= intel_iommu_add_device,
	.remove_device	= intel_iommu_remove_device,
	.device_group   = pci_device_group,
	.pgsize_bitmap	= INTEL_IOMMU_PGSIZES,
};

static void quirk_iommu_g4x_gfx(struct pci_dev *dev)
{
	/* G4x/GM45 integrated gfx dmar support is totally busted. */
	pr_info("Disabling IOMMU for graphics on this chipset\n");
	dmar_map_gfx = 0;
}

DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2a40, quirk_iommu_g4x_gfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e00, quirk_iommu_g4x_gfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e10, quirk_iommu_g4x_gfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e20, quirk_iommu_g4x_gfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e30, quirk_iommu_g4x_gfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e40, quirk_iommu_g4x_gfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e90, quirk_iommu_g4x_gfx);

static void quirk_iommu_rwbf(struct pci_dev *dev)
{
	/*
	 * Mobile 4 Series Chipset neglects to set RWBF capability,
	 * but needs it. Same seems to hold for the desktop versions.
	 */
	pr_info("Forcing write-buffer flush capability\n");
	rwbf_quirk = 1;
}

DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2a40, quirk_iommu_rwbf);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e00, quirk_iommu_rwbf);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e10, quirk_iommu_rwbf);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e20, quirk_iommu_rwbf);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e30, quirk_iommu_rwbf);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e40, quirk_iommu_rwbf);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e90, quirk_iommu_rwbf);

#define GGC 0x52
#define GGC_MEMORY_SIZE_MASK	(0xf << 8)
#define GGC_MEMORY_SIZE_NONE	(0x0 << 8)
#define GGC_MEMORY_SIZE_1M	(0x1 << 8)
#define GGC_MEMORY_SIZE_2M	(0x3 << 8)
#define GGC_MEMORY_VT_ENABLED	(0x8 << 8)
#define GGC_MEMORY_SIZE_2M_VT	(0x9 << 8)
#define GGC_MEMORY_SIZE_3M_VT	(0xa << 8)
#define GGC_MEMORY_SIZE_4M_VT	(0xb << 8)

static void quirk_calpella_no_shadow_gtt(struct pci_dev *dev)
{
	unsigned short ggc;

	if (pci_read_config_word(dev, GGC, &ggc))
		return;

	if (!(ggc & GGC_MEMORY_VT_ENABLED)) {
		pr_info("BIOS has allocated no shadow GTT; disabling IOMMU for graphics\n");
		dmar_map_gfx = 0;
	} else if (dmar_map_gfx) {
		/* we have to ensure the gfx device is idle before we flush */
		pr_info("Disabling batched IOTLB flush on Ironlake\n");
		intel_iommu_strict = 1;
       }
}
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0040, quirk_calpella_no_shadow_gtt);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0044, quirk_calpella_no_shadow_gtt);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0062, quirk_calpella_no_shadow_gtt);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x006a, quirk_calpella_no_shadow_gtt);

/* On Tylersburg chipsets, some BIOSes have been known to enable the
   ISOCH DMAR unit for the Azalia sound device, but not give it any
   TLB entries, which causes it to deadlock. Check for that.  We do
   this in a function called from init_dmars(), instead of in a PCI
   quirk, because we don't want to print the obnoxious "BIOS broken"
   message if VT-d is actually disabled.
*/
static void __init check_tylersburg_isoch(void)
{
	struct pci_dev *pdev;
	uint32_t vtisochctrl;

	/* If there's no Azalia in the system anyway, forget it. */
	pdev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x3a3e, NULL);
	if (!pdev)
		return;
	pci_dev_put(pdev);

	/* System Management Registers. Might be hidden, in which case
	   we can't do the sanity check. But that's OK, because the
	   known-broken BIOSes _don't_ actually hide it, so far. */
	pdev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x342e, NULL);
	if (!pdev)
		return;

	if (pci_read_config_dword(pdev, 0x188, &vtisochctrl)) {
		pci_dev_put(pdev);
		return;
	}

	pci_dev_put(pdev);

	/* If Azalia DMA is routed to the non-isoch DMAR unit, fine. */
	if (vtisochctrl & 1)
		return;

	/* Drop all bits other than the number of TLB entries */
	vtisochctrl &= 0x1c;

	/* If we have the recommended number of TLB entries (16), fine. */
	if (vtisochctrl == 0x10)
		return;

	/* Zero TLB entries? You get to ride the short bus to school. */
	if (!vtisochctrl) {
		WARN(1, "Your BIOS is broken; DMA routed to ISOCH DMAR unit but no TLB space.\n"
		     "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
		     dmi_get_system_info(DMI_BIOS_VENDOR),
		     dmi_get_system_info(DMI_BIOS_VERSION),
		     dmi_get_system_info(DMI_PRODUCT_VERSION));
		iommu_identity_mapping |= IDENTMAP_AZALIA;
		return;
	}

	pr_warn("Recommended TLB entries for ISOCH unit is 16; your BIOS set %d\n",
	       vtisochctrl);
}