summaryrefslogtreecommitdiff
path: root/drivers/iommu/iommu.c
blob: 9e661cbd3d42b2c694d0f5675347399f467b572c (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2007-2008 Advanced Micro Devices, Inc.
 * Author: Joerg Roedel <jroedel@suse.de>
 */

#define pr_fmt(fmt)    "iommu: " fmt

#include <linux/amba/bus.h>
#include <linux/device.h>
#include <linux/kernel.h>
#include <linux/bits.h>
#include <linux/bug.h>
#include <linux/types.h>
#include <linux/init.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/errno.h>
#include <linux/host1x_context_bus.h>
#include <linux/iommu.h>
#include <linux/idr.h>
#include <linux/err.h>
#include <linux/pci.h>
#include <linux/pci-ats.h>
#include <linux/bitops.h>
#include <linux/platform_device.h>
#include <linux/property.h>
#include <linux/fsl/mc.h>
#include <linux/module.h>
#include <linux/cc_platform.h>
#include <linux/cdx/cdx_bus.h>
#include <trace/events/iommu.h>
#include <linux/sched/mm.h>
#include <linux/msi.h>

#include "dma-iommu.h"

#include "iommu-sva.h"

static struct kset *iommu_group_kset;
static DEFINE_IDA(iommu_group_ida);

static unsigned int iommu_def_domain_type __read_mostly;
static bool iommu_dma_strict __read_mostly = IS_ENABLED(CONFIG_IOMMU_DEFAULT_DMA_STRICT);
static u32 iommu_cmd_line __read_mostly;

struct iommu_group {
	struct kobject kobj;
	struct kobject *devices_kobj;
	struct list_head devices;
	struct xarray pasid_array;
	struct mutex mutex;
	void *iommu_data;
	void (*iommu_data_release)(void *iommu_data);
	char *name;
	int id;
	struct iommu_domain *default_domain;
	struct iommu_domain *blocking_domain;
	struct iommu_domain *domain;
	struct list_head entry;
	unsigned int owner_cnt;
	void *owner;
};

struct group_device {
	struct list_head list;
	struct device *dev;
	char *name;
};

/* Iterate over each struct group_device in a struct iommu_group */
#define for_each_group_device(group, pos) \
	list_for_each_entry(pos, &(group)->devices, list)

struct iommu_group_attribute {
	struct attribute attr;
	ssize_t (*show)(struct iommu_group *group, char *buf);
	ssize_t (*store)(struct iommu_group *group,
			 const char *buf, size_t count);
};

static const char * const iommu_group_resv_type_string[] = {
	[IOMMU_RESV_DIRECT]			= "direct",
	[IOMMU_RESV_DIRECT_RELAXABLE]		= "direct-relaxable",
	[IOMMU_RESV_RESERVED]			= "reserved",
	[IOMMU_RESV_MSI]			= "msi",
	[IOMMU_RESV_SW_MSI]			= "msi",
};

#define IOMMU_CMD_LINE_DMA_API		BIT(0)
#define IOMMU_CMD_LINE_STRICT		BIT(1)

static int iommu_bus_notifier(struct notifier_block *nb,
			      unsigned long action, void *data);
static void iommu_release_device(struct device *dev);
static int iommu_alloc_default_domain(struct iommu_group *group,
				      struct device *dev);
static struct iommu_domain *__iommu_domain_alloc(const struct bus_type *bus,
						 unsigned type);
static int __iommu_attach_device(struct iommu_domain *domain,
				 struct device *dev);
static int __iommu_attach_group(struct iommu_domain *domain,
				struct iommu_group *group);

enum {
	IOMMU_SET_DOMAIN_MUST_SUCCEED = 1 << 0,
};

static int __iommu_device_set_domain(struct iommu_group *group,
				     struct device *dev,
				     struct iommu_domain *new_domain,
				     unsigned int flags);
static int __iommu_group_set_domain_internal(struct iommu_group *group,
					     struct iommu_domain *new_domain,
					     unsigned int flags);
static int __iommu_group_set_domain(struct iommu_group *group,
				    struct iommu_domain *new_domain)
{
	return __iommu_group_set_domain_internal(group, new_domain, 0);
}
static void __iommu_group_set_domain_nofail(struct iommu_group *group,
					    struct iommu_domain *new_domain)
{
	WARN_ON(__iommu_group_set_domain_internal(
		group, new_domain, IOMMU_SET_DOMAIN_MUST_SUCCEED));
}

static int iommu_create_device_direct_mappings(struct iommu_group *group,
					       struct device *dev);
static struct iommu_group *iommu_group_get_for_dev(struct device *dev);
static ssize_t iommu_group_store_type(struct iommu_group *group,
				      const char *buf, size_t count);

#define IOMMU_GROUP_ATTR(_name, _mode, _show, _store)		\
struct iommu_group_attribute iommu_group_attr_##_name =		\
	__ATTR(_name, _mode, _show, _store)

#define to_iommu_group_attr(_attr)	\
	container_of(_attr, struct iommu_group_attribute, attr)
#define to_iommu_group(_kobj)		\
	container_of(_kobj, struct iommu_group, kobj)

static LIST_HEAD(iommu_device_list);
static DEFINE_SPINLOCK(iommu_device_lock);

static struct bus_type * const iommu_buses[] = {
	&platform_bus_type,
#ifdef CONFIG_PCI
	&pci_bus_type,
#endif
#ifdef CONFIG_ARM_AMBA
	&amba_bustype,
#endif
#ifdef CONFIG_FSL_MC_BUS
	&fsl_mc_bus_type,
#endif
#ifdef CONFIG_TEGRA_HOST1X_CONTEXT_BUS
	&host1x_context_device_bus_type,
#endif
#ifdef CONFIG_CDX_BUS
	&cdx_bus_type,
#endif
};

/*
 * Use a function instead of an array here because the domain-type is a
 * bit-field, so an array would waste memory.
 */
static const char *iommu_domain_type_str(unsigned int t)
{
	switch (t) {
	case IOMMU_DOMAIN_BLOCKED:
		return "Blocked";
	case IOMMU_DOMAIN_IDENTITY:
		return "Passthrough";
	case IOMMU_DOMAIN_UNMANAGED:
		return "Unmanaged";
	case IOMMU_DOMAIN_DMA:
	case IOMMU_DOMAIN_DMA_FQ:
		return "Translated";
	default:
		return "Unknown";
	}
}

static int __init iommu_subsys_init(void)
{
	struct notifier_block *nb;

	if (!(iommu_cmd_line & IOMMU_CMD_LINE_DMA_API)) {
		if (IS_ENABLED(CONFIG_IOMMU_DEFAULT_PASSTHROUGH))
			iommu_set_default_passthrough(false);
		else
			iommu_set_default_translated(false);

		if (iommu_default_passthrough() && cc_platform_has(CC_ATTR_MEM_ENCRYPT)) {
			pr_info("Memory encryption detected - Disabling default IOMMU Passthrough\n");
			iommu_set_default_translated(false);
		}
	}

	if (!iommu_default_passthrough() && !iommu_dma_strict)
		iommu_def_domain_type = IOMMU_DOMAIN_DMA_FQ;

	pr_info("Default domain type: %s%s\n",
		iommu_domain_type_str(iommu_def_domain_type),
		(iommu_cmd_line & IOMMU_CMD_LINE_DMA_API) ?
			" (set via kernel command line)" : "");

	if (!iommu_default_passthrough())
		pr_info("DMA domain TLB invalidation policy: %s mode%s\n",
			iommu_dma_strict ? "strict" : "lazy",
			(iommu_cmd_line & IOMMU_CMD_LINE_STRICT) ?
				" (set via kernel command line)" : "");

	nb = kcalloc(ARRAY_SIZE(iommu_buses), sizeof(*nb), GFP_KERNEL);
	if (!nb)
		return -ENOMEM;

	for (int i = 0; i < ARRAY_SIZE(iommu_buses); i++) {
		nb[i].notifier_call = iommu_bus_notifier;
		bus_register_notifier(iommu_buses[i], &nb[i]);
	}

	return 0;
}
subsys_initcall(iommu_subsys_init);

static int remove_iommu_group(struct device *dev, void *data)
{
	if (dev->iommu && dev->iommu->iommu_dev == data)
		iommu_release_device(dev);

	return 0;
}

/**
 * iommu_device_register() - Register an IOMMU hardware instance
 * @iommu: IOMMU handle for the instance
 * @ops:   IOMMU ops to associate with the instance
 * @hwdev: (optional) actual instance device, used for fwnode lookup
 *
 * Return: 0 on success, or an error.
 */
int iommu_device_register(struct iommu_device *iommu,
			  const struct iommu_ops *ops, struct device *hwdev)
{
	int err = 0;

	/* We need to be able to take module references appropriately */
	if (WARN_ON(is_module_address((unsigned long)ops) && !ops->owner))
		return -EINVAL;
	/*
	 * Temporarily enforce global restriction to a single driver. This was
	 * already the de-facto behaviour, since any possible combination of
	 * existing drivers would compete for at least the PCI or platform bus.
	 */
	if (iommu_buses[0]->iommu_ops && iommu_buses[0]->iommu_ops != ops)
		return -EBUSY;

	iommu->ops = ops;
	if (hwdev)
		iommu->fwnode = dev_fwnode(hwdev);

	spin_lock(&iommu_device_lock);
	list_add_tail(&iommu->list, &iommu_device_list);
	spin_unlock(&iommu_device_lock);

	for (int i = 0; i < ARRAY_SIZE(iommu_buses) && !err; i++) {
		iommu_buses[i]->iommu_ops = ops;
		err = bus_iommu_probe(iommu_buses[i]);
	}
	if (err)
		iommu_device_unregister(iommu);
	return err;
}
EXPORT_SYMBOL_GPL(iommu_device_register);

void iommu_device_unregister(struct iommu_device *iommu)
{
	for (int i = 0; i < ARRAY_SIZE(iommu_buses); i++)
		bus_for_each_dev(iommu_buses[i], NULL, iommu, remove_iommu_group);

	spin_lock(&iommu_device_lock);
	list_del(&iommu->list);
	spin_unlock(&iommu_device_lock);
}
EXPORT_SYMBOL_GPL(iommu_device_unregister);

static struct dev_iommu *dev_iommu_get(struct device *dev)
{
	struct dev_iommu *param = dev->iommu;

	if (param)
		return param;

	param = kzalloc(sizeof(*param), GFP_KERNEL);
	if (!param)
		return NULL;

	mutex_init(&param->lock);
	dev->iommu = param;
	return param;
}

static void dev_iommu_free(struct device *dev)
{
	struct dev_iommu *param = dev->iommu;

	dev->iommu = NULL;
	if (param->fwspec) {
		fwnode_handle_put(param->fwspec->iommu_fwnode);
		kfree(param->fwspec);
	}
	kfree(param);
}

static u32 dev_iommu_get_max_pasids(struct device *dev)
{
	u32 max_pasids = 0, bits = 0;
	int ret;

	if (dev_is_pci(dev)) {
		ret = pci_max_pasids(to_pci_dev(dev));
		if (ret > 0)
			max_pasids = ret;
	} else {
		ret = device_property_read_u32(dev, "pasid-num-bits", &bits);
		if (!ret)
			max_pasids = 1UL << bits;
	}

	return min_t(u32, max_pasids, dev->iommu->iommu_dev->max_pasids);
}

static int __iommu_probe_device(struct device *dev, struct list_head *group_list)
{
	const struct iommu_ops *ops = dev->bus->iommu_ops;
	struct iommu_device *iommu_dev;
	struct iommu_group *group;
	static DEFINE_MUTEX(iommu_probe_device_lock);
	int ret;

	if (!ops)
		return -ENODEV;
	/*
	 * Serialise to avoid races between IOMMU drivers registering in
	 * parallel and/or the "replay" calls from ACPI/OF code via client
	 * driver probe. Once the latter have been cleaned up we should
	 * probably be able to use device_lock() here to minimise the scope,
	 * but for now enforcing a simple global ordering is fine.
	 */
	mutex_lock(&iommu_probe_device_lock);
	if (!dev_iommu_get(dev)) {
		ret = -ENOMEM;
		goto err_unlock;
	}

	if (!try_module_get(ops->owner)) {
		ret = -EINVAL;
		goto err_free;
	}

	iommu_dev = ops->probe_device(dev);
	if (IS_ERR(iommu_dev)) {
		ret = PTR_ERR(iommu_dev);
		goto out_module_put;
	}

	dev->iommu->iommu_dev = iommu_dev;
	dev->iommu->max_pasids = dev_iommu_get_max_pasids(dev);
	if (ops->is_attach_deferred)
		dev->iommu->attach_deferred = ops->is_attach_deferred(dev);

	group = iommu_group_get_for_dev(dev);
	if (IS_ERR(group)) {
		ret = PTR_ERR(group);
		goto out_release;
	}

	mutex_lock(&group->mutex);
	if (group_list && !group->default_domain && list_empty(&group->entry))
		list_add_tail(&group->entry, group_list);
	mutex_unlock(&group->mutex);
	iommu_group_put(group);

	mutex_unlock(&iommu_probe_device_lock);
	iommu_device_link(iommu_dev, dev);

	return 0;

out_release:
	if (ops->release_device)
		ops->release_device(dev);

out_module_put:
	module_put(ops->owner);

err_free:
	dev_iommu_free(dev);

err_unlock:
	mutex_unlock(&iommu_probe_device_lock);

	return ret;
}

int iommu_probe_device(struct device *dev)
{
	const struct iommu_ops *ops;
	struct iommu_group *group;
	int ret;

	ret = __iommu_probe_device(dev, NULL);
	if (ret)
		goto err_out;

	group = iommu_group_get(dev);
	if (!group) {
		ret = -ENODEV;
		goto err_release;
	}

	mutex_lock(&group->mutex);

	iommu_create_device_direct_mappings(group, dev);

	if (group->domain) {
		ret = __iommu_device_set_domain(group, dev, group->domain, 0);
	} else if (!group->default_domain) {
		/*
		 * Try to allocate a default domain - needs support from the
		 * IOMMU driver. There are still some drivers which don't
		 * support default domains, so the return value is not yet
		 * checked.
		 */
		iommu_alloc_default_domain(group, dev);
		if (group->default_domain) {
			iommu_create_device_direct_mappings(group, dev);
			ret = __iommu_group_set_domain(group,
						       group->default_domain);
		}

		/*
		 * We assume that the iommu driver starts up the device in
		 * 'set_platform_dma_ops' mode if it does not support default
		 * domains.
		 */
	}
	if (ret)
		goto err_unlock;

	mutex_unlock(&group->mutex);
	iommu_group_put(group);

	ops = dev_iommu_ops(dev);
	if (ops->probe_finalize)
		ops->probe_finalize(dev);

	return 0;

err_unlock:
	mutex_unlock(&group->mutex);
	iommu_group_put(group);
err_release:
	iommu_release_device(dev);

err_out:
	return ret;

}

/*
 * Remove a device from a group's device list and return the group device
 * if successful.
 */
static struct group_device *
__iommu_group_remove_device(struct iommu_group *group, struct device *dev)
{
	struct group_device *device;

	lockdep_assert_held(&group->mutex);
	for_each_group_device(group, device) {
		if (device->dev == dev) {
			list_del(&device->list);
			return device;
		}
	}

	return NULL;
}

/*
 * Release a device from its group and decrements the iommu group reference
 * count.
 */
static void __iommu_group_release_device(struct iommu_group *group,
					 struct group_device *grp_dev)
{
	struct device *dev = grp_dev->dev;

	sysfs_remove_link(group->devices_kobj, grp_dev->name);
	sysfs_remove_link(&dev->kobj, "iommu_group");

	trace_remove_device_from_group(group->id, dev);

	kfree(grp_dev->name);
	kfree(grp_dev);
	dev->iommu_group = NULL;
	kobject_put(group->devices_kobj);
}

static void iommu_release_device(struct device *dev)
{
	struct iommu_group *group = dev->iommu_group;
	struct group_device *device;
	const struct iommu_ops *ops;

	if (!dev->iommu || !group)
		return;

	iommu_device_unlink(dev->iommu->iommu_dev, dev);

	mutex_lock(&group->mutex);
	device = __iommu_group_remove_device(group, dev);

	/*
	 * If the group has become empty then ownership must have been released,
	 * and the current domain must be set back to NULL or the default
	 * domain.
	 */
	if (list_empty(&group->devices))
		WARN_ON(group->owner_cnt ||
			group->domain != group->default_domain);

	/*
	 * release_device() must stop using any attached domain on the device.
	 * If there are still other devices in the group they are not effected
	 * by this callback.
	 *
	 * The IOMMU driver must set the device to either an identity or
	 * blocking translation and stop using any domain pointer, as it is
	 * going to be freed.
	 */
	ops = dev_iommu_ops(dev);
	if (ops->release_device)
		ops->release_device(dev);
	mutex_unlock(&group->mutex);

	if (device)
		__iommu_group_release_device(group, device);

	module_put(ops->owner);
	dev_iommu_free(dev);
}

static int __init iommu_set_def_domain_type(char *str)
{
	bool pt;
	int ret;

	ret = kstrtobool(str, &pt);
	if (ret)
		return ret;

	if (pt)
		iommu_set_default_passthrough(true);
	else
		iommu_set_default_translated(true);

	return 0;
}
early_param("iommu.passthrough", iommu_set_def_domain_type);

static int __init iommu_dma_setup(char *str)
{
	int ret = kstrtobool(str, &iommu_dma_strict);

	if (!ret)
		iommu_cmd_line |= IOMMU_CMD_LINE_STRICT;
	return ret;
}
early_param("iommu.strict", iommu_dma_setup);

void iommu_set_dma_strict(void)
{
	iommu_dma_strict = true;
	if (iommu_def_domain_type == IOMMU_DOMAIN_DMA_FQ)
		iommu_def_domain_type = IOMMU_DOMAIN_DMA;
}

static ssize_t iommu_group_attr_show(struct kobject *kobj,
				     struct attribute *__attr, char *buf)
{
	struct iommu_group_attribute *attr = to_iommu_group_attr(__attr);
	struct iommu_group *group = to_iommu_group(kobj);
	ssize_t ret = -EIO;

	if (attr->show)
		ret = attr->show(group, buf);
	return ret;
}

static ssize_t iommu_group_attr_store(struct kobject *kobj,
				      struct attribute *__attr,
				      const char *buf, size_t count)
{
	struct iommu_group_attribute *attr = to_iommu_group_attr(__attr);
	struct iommu_group *group = to_iommu_group(kobj);
	ssize_t ret = -EIO;

	if (attr->store)
		ret = attr->store(group, buf, count);
	return ret;
}

static const struct sysfs_ops iommu_group_sysfs_ops = {
	.show = iommu_group_attr_show,
	.store = iommu_group_attr_store,
};

static int iommu_group_create_file(struct iommu_group *group,
				   struct iommu_group_attribute *attr)
{
	return sysfs_create_file(&group->kobj, &attr->attr);
}

static void iommu_group_remove_file(struct iommu_group *group,
				    struct iommu_group_attribute *attr)
{
	sysfs_remove_file(&group->kobj, &attr->attr);
}

static ssize_t iommu_group_show_name(struct iommu_group *group, char *buf)
{
	return sysfs_emit(buf, "%s\n", group->name);
}

/**
 * iommu_insert_resv_region - Insert a new region in the
 * list of reserved regions.
 * @new: new region to insert
 * @regions: list of regions
 *
 * Elements are sorted by start address and overlapping segments
 * of the same type are merged.
 */
static int iommu_insert_resv_region(struct iommu_resv_region *new,
				    struct list_head *regions)
{
	struct iommu_resv_region *iter, *tmp, *nr, *top;
	LIST_HEAD(stack);

	nr = iommu_alloc_resv_region(new->start, new->length,
				     new->prot, new->type, GFP_KERNEL);
	if (!nr)
		return -ENOMEM;

	/* First add the new element based on start address sorting */
	list_for_each_entry(iter, regions, list) {
		if (nr->start < iter->start ||
		    (nr->start == iter->start && nr->type <= iter->type))
			break;
	}
	list_add_tail(&nr->list, &iter->list);

	/* Merge overlapping segments of type nr->type in @regions, if any */
	list_for_each_entry_safe(iter, tmp, regions, list) {
		phys_addr_t top_end, iter_end = iter->start + iter->length - 1;

		/* no merge needed on elements of different types than @new */
		if (iter->type != new->type) {
			list_move_tail(&iter->list, &stack);
			continue;
		}

		/* look for the last stack element of same type as @iter */
		list_for_each_entry_reverse(top, &stack, list)
			if (top->type == iter->type)
				goto check_overlap;

		list_move_tail(&iter->list, &stack);
		continue;

check_overlap:
		top_end = top->start + top->length - 1;

		if (iter->start > top_end + 1) {
			list_move_tail(&iter->list, &stack);
		} else {
			top->length = max(top_end, iter_end) - top->start + 1;
			list_del(&iter->list);
			kfree(iter);
		}
	}
	list_splice(&stack, regions);
	return 0;
}

static int
iommu_insert_device_resv_regions(struct list_head *dev_resv_regions,
				 struct list_head *group_resv_regions)
{
	struct iommu_resv_region *entry;
	int ret = 0;

	list_for_each_entry(entry, dev_resv_regions, list) {
		ret = iommu_insert_resv_region(entry, group_resv_regions);
		if (ret)
			break;
	}
	return ret;
}

int iommu_get_group_resv_regions(struct iommu_group *group,
				 struct list_head *head)
{
	struct group_device *device;
	int ret = 0;

	mutex_lock(&group->mutex);
	for_each_group_device(group, device) {
		struct list_head dev_resv_regions;

		/*
		 * Non-API groups still expose reserved_regions in sysfs,
		 * so filter out calls that get here that way.
		 */
		if (!device->dev->iommu)
			break;

		INIT_LIST_HEAD(&dev_resv_regions);
		iommu_get_resv_regions(device->dev, &dev_resv_regions);
		ret = iommu_insert_device_resv_regions(&dev_resv_regions, head);
		iommu_put_resv_regions(device->dev, &dev_resv_regions);
		if (ret)
			break;
	}
	mutex_unlock(&group->mutex);
	return ret;
}
EXPORT_SYMBOL_GPL(iommu_get_group_resv_regions);

static ssize_t iommu_group_show_resv_regions(struct iommu_group *group,
					     char *buf)
{
	struct iommu_resv_region *region, *next;
	struct list_head group_resv_regions;
	int offset = 0;

	INIT_LIST_HEAD(&group_resv_regions);
	iommu_get_group_resv_regions(group, &group_resv_regions);

	list_for_each_entry_safe(region, next, &group_resv_regions, list) {
		offset += sysfs_emit_at(buf, offset, "0x%016llx 0x%016llx %s\n",
					(long long)region->start,
					(long long)(region->start +
						    region->length - 1),
					iommu_group_resv_type_string[region->type]);
		kfree(region);
	}

	return offset;
}

static ssize_t iommu_group_show_type(struct iommu_group *group,
				     char *buf)
{
	char *type = "unknown";

	mutex_lock(&group->mutex);
	if (group->default_domain) {
		switch (group->default_domain->type) {
		case IOMMU_DOMAIN_BLOCKED:
			type = "blocked";
			break;
		case IOMMU_DOMAIN_IDENTITY:
			type = "identity";
			break;
		case IOMMU_DOMAIN_UNMANAGED:
			type = "unmanaged";
			break;
		case IOMMU_DOMAIN_DMA:
			type = "DMA";
			break;
		case IOMMU_DOMAIN_DMA_FQ:
			type = "DMA-FQ";
			break;
		}
	}
	mutex_unlock(&group->mutex);

	return sysfs_emit(buf, "%s\n", type);
}

static IOMMU_GROUP_ATTR(name, S_IRUGO, iommu_group_show_name, NULL);

static IOMMU_GROUP_ATTR(reserved_regions, 0444,
			iommu_group_show_resv_regions, NULL);

static IOMMU_GROUP_ATTR(type, 0644, iommu_group_show_type,
			iommu_group_store_type);

static void iommu_group_release(struct kobject *kobj)
{
	struct iommu_group *group = to_iommu_group(kobj);

	pr_debug("Releasing group %d\n", group->id);

	if (group->iommu_data_release)
		group->iommu_data_release(group->iommu_data);

	ida_free(&iommu_group_ida, group->id);

	if (group->default_domain)
		iommu_domain_free(group->default_domain);
	if (group->blocking_domain)
		iommu_domain_free(group->blocking_domain);

	kfree(group->name);
	kfree(group);
}

static const struct kobj_type iommu_group_ktype = {
	.sysfs_ops = &iommu_group_sysfs_ops,
	.release = iommu_group_release,
};

/**
 * iommu_group_alloc - Allocate a new group
 *
 * This function is called by an iommu driver to allocate a new iommu
 * group.  The iommu group represents the minimum granularity of the iommu.
 * Upon successful return, the caller holds a reference to the supplied
 * group in order to hold the group until devices are added.  Use
 * iommu_group_put() to release this extra reference count, allowing the
 * group to be automatically reclaimed once it has no devices or external
 * references.
 */
struct iommu_group *iommu_group_alloc(void)
{
	struct iommu_group *group;
	int ret;

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

	group->kobj.kset = iommu_group_kset;
	mutex_init(&group->mutex);
	INIT_LIST_HEAD(&group->devices);
	INIT_LIST_HEAD(&group->entry);
	xa_init(&group->pasid_array);

	ret = ida_alloc(&iommu_group_ida, GFP_KERNEL);
	if (ret < 0) {
		kfree(group);
		return ERR_PTR(ret);
	}
	group->id = ret;

	ret = kobject_init_and_add(&group->kobj, &iommu_group_ktype,
				   NULL, "%d", group->id);
	if (ret) {
		kobject_put(&group->kobj);
		return ERR_PTR(ret);
	}

	group->devices_kobj = kobject_create_and_add("devices", &group->kobj);
	if (!group->devices_kobj) {
		kobject_put(&group->kobj); /* triggers .release & free */
		return ERR_PTR(-ENOMEM);
	}

	/*
	 * The devices_kobj holds a reference on the group kobject, so
	 * as long as that exists so will the group.  We can therefore
	 * use the devices_kobj for reference counting.
	 */
	kobject_put(&group->kobj);

	ret = iommu_group_create_file(group,
				      &iommu_group_attr_reserved_regions);
	if (ret) {
		kobject_put(group->devices_kobj);
		return ERR_PTR(ret);
	}

	ret = iommu_group_create_file(group, &iommu_group_attr_type);
	if (ret) {
		kobject_put(group->devices_kobj);
		return ERR_PTR(ret);
	}

	pr_debug("Allocated group %d\n", group->id);

	return group;
}
EXPORT_SYMBOL_GPL(iommu_group_alloc);

/**
 * iommu_group_get_iommudata - retrieve iommu_data registered for a group
 * @group: the group
 *
 * iommu drivers can store data in the group for use when doing iommu
 * operations.  This function provides a way to retrieve it.  Caller
 * should hold a group reference.
 */
void *iommu_group_get_iommudata(struct iommu_group *group)
{
	return group->iommu_data;
}
EXPORT_SYMBOL_GPL(iommu_group_get_iommudata);

/**
 * iommu_group_set_iommudata - set iommu_data for a group
 * @group: the group
 * @iommu_data: new data
 * @release: release function for iommu_data
 *
 * iommu drivers can store data in the group for use when doing iommu
 * operations.  This function provides a way to set the data after
 * the group has been allocated.  Caller should hold a group reference.
 */
void iommu_group_set_iommudata(struct iommu_group *group, void *iommu_data,
			       void (*release)(void *iommu_data))
{
	group->iommu_data = iommu_data;
	group->iommu_data_release = release;
}
EXPORT_SYMBOL_GPL(iommu_group_set_iommudata);

/**
 * iommu_group_set_name - set name for a group
 * @group: the group
 * @name: name
 *
 * Allow iommu driver to set a name for a group.  When set it will
 * appear in a name attribute file under the group in sysfs.
 */
int iommu_group_set_name(struct iommu_group *group, const char *name)
{
	int ret;

	if (group->name) {
		iommu_group_remove_file(group, &iommu_group_attr_name);
		kfree(group->name);
		group->name = NULL;
		if (!name)
			return 0;
	}

	group->name = kstrdup(name, GFP_KERNEL);
	if (!group->name)
		return -ENOMEM;

	ret = iommu_group_create_file(group, &iommu_group_attr_name);
	if (ret) {
		kfree(group->name);
		group->name = NULL;
		return ret;
	}

	return 0;
}
EXPORT_SYMBOL_GPL(iommu_group_set_name);

static int iommu_create_device_direct_mappings(struct iommu_group *group,
					       struct device *dev)
{
	struct iommu_domain *domain = group->default_domain;
	struct iommu_resv_region *entry;
	struct list_head mappings;
	unsigned long pg_size;
	int ret = 0;

	if (!domain || !iommu_is_dma_domain(domain))
		return 0;

	BUG_ON(!domain->pgsize_bitmap);

	pg_size = 1UL << __ffs(domain->pgsize_bitmap);
	INIT_LIST_HEAD(&mappings);

	iommu_get_resv_regions(dev, &mappings);

	/* We need to consider overlapping regions for different devices */
	list_for_each_entry(entry, &mappings, list) {
		dma_addr_t start, end, addr;
		size_t map_size = 0;

		start = ALIGN(entry->start, pg_size);
		end   = ALIGN(entry->start + entry->length, pg_size);

		if (entry->type != IOMMU_RESV_DIRECT &&
		    entry->type != IOMMU_RESV_DIRECT_RELAXABLE)
			continue;

		for (addr = start; addr <= end; addr += pg_size) {
			phys_addr_t phys_addr;

			if (addr == end)
				goto map_end;

			phys_addr = iommu_iova_to_phys(domain, addr);
			if (!phys_addr) {
				map_size += pg_size;
				continue;
			}

map_end:
			if (map_size) {
				ret = iommu_map(domain, addr - map_size,
						addr - map_size, map_size,
						entry->prot, GFP_KERNEL);
				if (ret)
					goto out;
				map_size = 0;
			}
		}

	}

	iommu_flush_iotlb_all(domain);

out:
	iommu_put_resv_regions(dev, &mappings);

	return ret;
}

/**
 * iommu_group_add_device - add a device to an iommu group
 * @group: the group into which to add the device (reference should be held)
 * @dev: the device
 *
 * This function is called by an iommu driver to add a device into a
 * group.  Adding a device increments the group reference count.
 */
int iommu_group_add_device(struct iommu_group *group, struct device *dev)
{
	int ret, i = 0;
	struct group_device *device;

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

	device->dev = dev;

	ret = sysfs_create_link(&dev->kobj, &group->kobj, "iommu_group");
	if (ret)
		goto err_free_device;

	device->name = kasprintf(GFP_KERNEL, "%s", kobject_name(&dev->kobj));
rename:
	if (!device->name) {
		ret = -ENOMEM;
		goto err_remove_link;
	}

	ret = sysfs_create_link_nowarn(group->devices_kobj,
				       &dev->kobj, device->name);
	if (ret) {
		if (ret == -EEXIST && i >= 0) {
			/*
			 * Account for the slim chance of collision
			 * and append an instance to the name.
			 */
			kfree(device->name);
			device->name = kasprintf(GFP_KERNEL, "%s.%d",
						 kobject_name(&dev->kobj), i++);
			goto rename;
		}
		goto err_free_name;
	}

	kobject_get(group->devices_kobj);

	dev->iommu_group = group;

	mutex_lock(&group->mutex);
	list_add_tail(&device->list, &group->devices);
	mutex_unlock(&group->mutex);
	trace_add_device_to_group(group->id, dev);

	dev_info(dev, "Adding to iommu group %d\n", group->id);

	return 0;

err_free_name:
	kfree(device->name);
err_remove_link:
	sysfs_remove_link(&dev->kobj, "iommu_group");
err_free_device:
	kfree(device);
	dev_err(dev, "Failed to add to iommu group %d: %d\n", group->id, ret);
	return ret;
}
EXPORT_SYMBOL_GPL(iommu_group_add_device);

/**
 * iommu_group_remove_device - remove a device from it's current group
 * @dev: device to be removed
 *
 * This function is called by an iommu driver to remove the device from
 * it's current group.  This decrements the iommu group reference count.
 */
void iommu_group_remove_device(struct device *dev)
{
	struct iommu_group *group = dev->iommu_group;
	struct group_device *device;

	if (!group)
		return;

	dev_info(dev, "Removing from iommu group %d\n", group->id);

	mutex_lock(&group->mutex);
	device = __iommu_group_remove_device(group, dev);
	mutex_unlock(&group->mutex);

	if (device)
		__iommu_group_release_device(group, device);
}
EXPORT_SYMBOL_GPL(iommu_group_remove_device);

static int __iommu_group_for_each_dev(struct iommu_group *group, void *data,
				      int (*fn)(struct device *, void *))
{
	struct group_device *device;
	int ret = 0;

	for_each_group_device(group, device) {
		ret = fn(device->dev, data);
		if (ret)
			break;
	}
	return ret;
}

/**
 * iommu_group_for_each_dev - iterate over each device in the group
 * @group: the group
 * @data: caller opaque data to be passed to callback function
 * @fn: caller supplied callback function
 *
 * This function is called by group users to iterate over group devices.
 * Callers should hold a reference count to the group during callback.
 * The group->mutex is held across callbacks, which will block calls to
 * iommu_group_add/remove_device.
 */
int iommu_group_for_each_dev(struct iommu_group *group, void *data,
			     int (*fn)(struct device *, void *))
{
	int ret;

	mutex_lock(&group->mutex);
	ret = __iommu_group_for_each_dev(group, data, fn);
	mutex_unlock(&group->mutex);

	return ret;
}
EXPORT_SYMBOL_GPL(iommu_group_for_each_dev);

/**
 * iommu_group_get - Return the group for a device and increment reference
 * @dev: get the group that this device belongs to
 *
 * This function is called by iommu drivers and users to get the group
 * for the specified device.  If found, the group is returned and the group
 * reference in incremented, else NULL.
 */
struct iommu_group *iommu_group_get(struct device *dev)
{
	struct iommu_group *group = dev->iommu_group;

	if (group)
		kobject_get(group->devices_kobj);

	return group;
}
EXPORT_SYMBOL_GPL(iommu_group_get);

/**
 * iommu_group_ref_get - Increment reference on a group
 * @group: the group to use, must not be NULL
 *
 * This function is called by iommu drivers to take additional references on an
 * existing group.  Returns the given group for convenience.
 */
struct iommu_group *iommu_group_ref_get(struct iommu_group *group)
{
	kobject_get(group->devices_kobj);
	return group;
}
EXPORT_SYMBOL_GPL(iommu_group_ref_get);

/**
 * iommu_group_put - Decrement group reference
 * @group: the group to use
 *
 * This function is called by iommu drivers and users to release the
 * iommu group.  Once the reference count is zero, the group is released.
 */
void iommu_group_put(struct iommu_group *group)
{
	if (group)
		kobject_put(group->devices_kobj);
}
EXPORT_SYMBOL_GPL(iommu_group_put);

/**
 * iommu_register_device_fault_handler() - Register a device fault handler
 * @dev: the device
 * @handler: the fault handler
 * @data: private data passed as argument to the handler
 *
 * When an IOMMU fault event is received, this handler gets called with the
 * fault event and data as argument. The handler should return 0 on success. If
 * the fault is recoverable (IOMMU_FAULT_PAGE_REQ), the consumer should also
 * complete the fault by calling iommu_page_response() with one of the following
 * response code:
 * - IOMMU_PAGE_RESP_SUCCESS: retry the translation
 * - IOMMU_PAGE_RESP_INVALID: terminate the fault
 * - IOMMU_PAGE_RESP_FAILURE: terminate the fault and stop reporting
 *   page faults if possible.
 *
 * Return 0 if the fault handler was installed successfully, or an error.
 */
int iommu_register_device_fault_handler(struct device *dev,
					iommu_dev_fault_handler_t handler,
					void *data)
{
	struct dev_iommu *param = dev->iommu;
	int ret = 0;

	if (!param)
		return -EINVAL;

	mutex_lock(&param->lock);
	/* Only allow one fault handler registered for each device */
	if (param->fault_param) {
		ret = -EBUSY;
		goto done_unlock;
	}

	get_device(dev);
	param->fault_param = kzalloc(sizeof(*param->fault_param), GFP_KERNEL);
	if (!param->fault_param) {
		put_device(dev);
		ret = -ENOMEM;
		goto done_unlock;
	}
	param->fault_param->handler = handler;
	param->fault_param->data = data;
	mutex_init(&param->fault_param->lock);
	INIT_LIST_HEAD(&param->fault_param->faults);

done_unlock:
	mutex_unlock(&param->lock);

	return ret;
}
EXPORT_SYMBOL_GPL(iommu_register_device_fault_handler);

/**
 * iommu_unregister_device_fault_handler() - Unregister the device fault handler
 * @dev: the device
 *
 * Remove the device fault handler installed with
 * iommu_register_device_fault_handler().
 *
 * Return 0 on success, or an error.
 */
int iommu_unregister_device_fault_handler(struct device *dev)
{
	struct dev_iommu *param = dev->iommu;
	int ret = 0;

	if (!param)
		return -EINVAL;

	mutex_lock(&param->lock);

	if (!param->fault_param)
		goto unlock;

	/* we cannot unregister handler if there are pending faults */
	if (!list_empty(&param->fault_param->faults)) {
		ret = -EBUSY;
		goto unlock;
	}

	kfree(param->fault_param);
	param->fault_param = NULL;
	put_device(dev);
unlock:
	mutex_unlock(&param->lock);

	return ret;
}
EXPORT_SYMBOL_GPL(iommu_unregister_device_fault_handler);

/**
 * iommu_report_device_fault() - Report fault event to device driver
 * @dev: the device
 * @evt: fault event data
 *
 * Called by IOMMU drivers when a fault is detected, typically in a threaded IRQ
 * handler. When this function fails and the fault is recoverable, it is the
 * caller's responsibility to complete the fault.
 *
 * Return 0 on success, or an error.
 */
int iommu_report_device_fault(struct device *dev, struct iommu_fault_event *evt)
{
	struct dev_iommu *param = dev->iommu;
	struct iommu_fault_event *evt_pending = NULL;
	struct iommu_fault_param *fparam;
	int ret = 0;

	if (!param || !evt)
		return -EINVAL;

	/* we only report device fault if there is a handler registered */
	mutex_lock(&param->lock);
	fparam = param->fault_param;
	if (!fparam || !fparam->handler) {
		ret = -EINVAL;
		goto done_unlock;
	}

	if (evt->fault.type == IOMMU_FAULT_PAGE_REQ &&
	    (evt->fault.prm.flags & IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE)) {
		evt_pending = kmemdup(evt, sizeof(struct iommu_fault_event),
				      GFP_KERNEL);
		if (!evt_pending) {
			ret = -ENOMEM;
			goto done_unlock;
		}
		mutex_lock(&fparam->lock);
		list_add_tail(&evt_pending->list, &fparam->faults);
		mutex_unlock(&fparam->lock);
	}

	ret = fparam->handler(&evt->fault, fparam->data);
	if (ret && evt_pending) {
		mutex_lock(&fparam->lock);
		list_del(&evt_pending->list);
		mutex_unlock(&fparam->lock);
		kfree(evt_pending);
	}
done_unlock:
	mutex_unlock(&param->lock);
	return ret;
}
EXPORT_SYMBOL_GPL(iommu_report_device_fault);

int iommu_page_response(struct device *dev,
			struct iommu_page_response *msg)
{
	bool needs_pasid;
	int ret = -EINVAL;
	struct iommu_fault_event *evt;
	struct iommu_fault_page_request *prm;
	struct dev_iommu *param = dev->iommu;
	const struct iommu_ops *ops = dev_iommu_ops(dev);
	bool has_pasid = msg->flags & IOMMU_PAGE_RESP_PASID_VALID;

	if (!ops->page_response)
		return -ENODEV;

	if (!param || !param->fault_param)
		return -EINVAL;

	if (msg->version != IOMMU_PAGE_RESP_VERSION_1 ||
	    msg->flags & ~IOMMU_PAGE_RESP_PASID_VALID)
		return -EINVAL;

	/* Only send response if there is a fault report pending */
	mutex_lock(&param->fault_param->lock);
	if (list_empty(&param->fault_param->faults)) {
		dev_warn_ratelimited(dev, "no pending PRQ, drop response\n");
		goto done_unlock;
	}
	/*
	 * Check if we have a matching page request pending to respond,
	 * otherwise return -EINVAL
	 */
	list_for_each_entry(evt, &param->fault_param->faults, list) {
		prm = &evt->fault.prm;
		if (prm->grpid != msg->grpid)
			continue;

		/*
		 * If the PASID is required, the corresponding request is
		 * matched using the group ID, the PASID valid bit and the PASID
		 * value. Otherwise only the group ID matches request and
		 * response.
		 */
		needs_pasid = prm->flags & IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID;
		if (needs_pasid && (!has_pasid || msg->pasid != prm->pasid))
			continue;

		if (!needs_pasid && has_pasid) {
			/* No big deal, just clear it. */
			msg->flags &= ~IOMMU_PAGE_RESP_PASID_VALID;
			msg->pasid = 0;
		}

		ret = ops->page_response(dev, evt, msg);
		list_del(&evt->list);
		kfree(evt);
		break;
	}

done_unlock:
	mutex_unlock(&param->fault_param->lock);
	return ret;
}
EXPORT_SYMBOL_GPL(iommu_page_response);

/**
 * iommu_group_id - Return ID for a group
 * @group: the group to ID
 *
 * Return the unique ID for the group matching the sysfs group number.
 */
int iommu_group_id(struct iommu_group *group)
{
	return group->id;
}
EXPORT_SYMBOL_GPL(iommu_group_id);

static struct iommu_group *get_pci_alias_group(struct pci_dev *pdev,
					       unsigned long *devfns);

/*
 * To consider a PCI device isolated, we require ACS to support Source
 * Validation, Request Redirection, Completer Redirection, and Upstream
 * Forwarding.  This effectively means that devices cannot spoof their
 * requester ID, requests and completions cannot be redirected, and all
 * transactions are forwarded upstream, even as it passes through a
 * bridge where the target device is downstream.
 */
#define REQ_ACS_FLAGS   (PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF)

/*
 * For multifunction devices which are not isolated from each other, find
 * all the other non-isolated functions and look for existing groups.  For
 * each function, we also need to look for aliases to or from other devices
 * that may already have a group.
 */
static struct iommu_group *get_pci_function_alias_group(struct pci_dev *pdev,
							unsigned long *devfns)
{
	struct pci_dev *tmp = NULL;
	struct iommu_group *group;

	if (!pdev->multifunction || pci_acs_enabled(pdev, REQ_ACS_FLAGS))
		return NULL;

	for_each_pci_dev(tmp) {
		if (tmp == pdev || tmp->bus != pdev->bus ||
		    PCI_SLOT(tmp->devfn) != PCI_SLOT(pdev->devfn) ||
		    pci_acs_enabled(tmp, REQ_ACS_FLAGS))
			continue;

		group = get_pci_alias_group(tmp, devfns);
		if (group) {
			pci_dev_put(tmp);
			return group;
		}
	}

	return NULL;
}

/*
 * Look for aliases to or from the given device for existing groups. DMA
 * aliases are only supported on the same bus, therefore the search
 * space is quite small (especially since we're really only looking at pcie
 * device, and therefore only expect multiple slots on the root complex or
 * downstream switch ports).  It's conceivable though that a pair of
 * multifunction devices could have aliases between them that would cause a
 * loop.  To prevent this, we use a bitmap to track where we've been.
 */
static struct iommu_group *get_pci_alias_group(struct pci_dev *pdev,
					       unsigned long *devfns)
{
	struct pci_dev *tmp = NULL;
	struct iommu_group *group;

	if (test_and_set_bit(pdev->devfn & 0xff, devfns))
		return NULL;

	group = iommu_group_get(&pdev->dev);
	if (group)
		return group;

	for_each_pci_dev(tmp) {
		if (tmp == pdev || tmp->bus != pdev->bus)
			continue;

		/* We alias them or they alias us */
		if (pci_devs_are_dma_aliases(pdev, tmp)) {
			group = get_pci_alias_group(tmp, devfns);
			if (group) {
				pci_dev_put(tmp);
				return group;
			}

			group = get_pci_function_alias_group(tmp, devfns);
			if (group) {
				pci_dev_put(tmp);
				return group;
			}
		}
	}

	return NULL;
}

struct group_for_pci_data {
	struct pci_dev *pdev;
	struct iommu_group *group;
};

/*
 * DMA alias iterator callback, return the last seen device.  Stop and return
 * the IOMMU group if we find one along the way.
 */
static int get_pci_alias_or_group(struct pci_dev *pdev, u16 alias, void *opaque)
{
	struct group_for_pci_data *data = opaque;

	data->pdev = pdev;
	data->group = iommu_group_get(&pdev->dev);

	return data->group != NULL;
}

/*
 * Generic device_group call-back function. It just allocates one
 * iommu-group per device.
 */
struct iommu_group *generic_device_group(struct device *dev)
{
	return iommu_group_alloc();
}
EXPORT_SYMBOL_GPL(generic_device_group);

/*
 * Use standard PCI bus topology, isolation features, and DMA alias quirks
 * to find or create an IOMMU group for a device.
 */
struct iommu_group *pci_device_group(struct device *dev)
{
	struct pci_dev *pdev = to_pci_dev(dev);
	struct group_for_pci_data data;
	struct pci_bus *bus;
	struct iommu_group *group = NULL;
	u64 devfns[4] = { 0 };

	if (WARN_ON(!dev_is_pci(dev)))
		return ERR_PTR(-EINVAL);

	/*
	 * Find the upstream DMA alias for the device.  A device must not
	 * be aliased due to topology in order to have its own IOMMU group.
	 * If we find an alias along the way that already belongs to a
	 * group, use it.
	 */
	if (pci_for_each_dma_alias(pdev, get_pci_alias_or_group, &data))
		return data.group;

	pdev = data.pdev;

	/*
	 * Continue upstream from the point of minimum IOMMU granularity
	 * due to aliases to the point where devices are protected from
	 * peer-to-peer DMA by PCI ACS.  Again, if we find an existing
	 * group, use it.
	 */
	for (bus = pdev->bus; !pci_is_root_bus(bus); bus = bus->parent) {
		if (!bus->self)
			continue;

		if (pci_acs_path_enabled(bus->self, NULL, REQ_ACS_FLAGS))
			break;

		pdev = bus->self;

		group = iommu_group_get(&pdev->dev);
		if (group)
			return group;
	}

	/*
	 * Look for existing groups on device aliases.  If we alias another
	 * device or another device aliases us, use the same group.
	 */
	group = get_pci_alias_group(pdev, (unsigned long *)devfns);
	if (group)
		return group;

	/*
	 * Look for existing groups on non-isolated functions on the same
	 * slot and aliases of those funcions, if any.  No need to clear
	 * the search bitmap, the tested devfns are still valid.
	 */
	group = get_pci_function_alias_group(pdev, (unsigned long *)devfns);
	if (group)
		return group;

	/* No shared group found, allocate new */
	return iommu_group_alloc();
}
EXPORT_SYMBOL_GPL(pci_device_group);

/* Get the IOMMU group for device on fsl-mc bus */
struct iommu_group *fsl_mc_device_group(struct device *dev)
{
	struct device *cont_dev = fsl_mc_cont_dev(dev);
	struct iommu_group *group;

	group = iommu_group_get(cont_dev);
	if (!group)
		group = iommu_group_alloc();
	return group;
}
EXPORT_SYMBOL_GPL(fsl_mc_device_group);

static int iommu_get_def_domain_type(struct device *dev)
{
	const struct iommu_ops *ops = dev_iommu_ops(dev);

	if (dev_is_pci(dev) && to_pci_dev(dev)->untrusted)
		return IOMMU_DOMAIN_DMA;

	if (ops->def_domain_type)
		return ops->def_domain_type(dev);

	return 0;
}

static int iommu_group_alloc_default_domain(const struct bus_type *bus,
					    struct iommu_group *group,
					    unsigned int type)
{
	struct iommu_domain *dom;

	dom = __iommu_domain_alloc(bus, type);
	if (!dom && type != IOMMU_DOMAIN_DMA) {
		dom = __iommu_domain_alloc(bus, IOMMU_DOMAIN_DMA);
		if (dom)
			pr_warn("Failed to allocate default IOMMU domain of type %u for group %s - Falling back to IOMMU_DOMAIN_DMA",
				type, group->name);
	}

	if (!dom)
		return -ENOMEM;

	group->default_domain = dom;
	return 0;
}

static int iommu_alloc_default_domain(struct iommu_group *group,
				      struct device *dev)
{
	unsigned int type;

	type = iommu_get_def_domain_type(dev) ? : iommu_def_domain_type;

	return iommu_group_alloc_default_domain(dev->bus, group, type);
}

/**
 * iommu_group_get_for_dev - Find or create the IOMMU group for a device
 * @dev: target device
 *
 * This function is intended to be called by IOMMU drivers and extended to
 * support common, bus-defined algorithms when determining or creating the
 * IOMMU group for a device.  On success, the caller will hold a reference
 * to the returned IOMMU group, which will already include the provided
 * device.  The reference should be released with iommu_group_put().
 */
static struct iommu_group *iommu_group_get_for_dev(struct device *dev)
{
	const struct iommu_ops *ops = dev_iommu_ops(dev);
	struct iommu_group *group;
	int ret;

	group = iommu_group_get(dev);
	if (group)
		return group;

	group = ops->device_group(dev);
	if (WARN_ON_ONCE(group == NULL))
		return ERR_PTR(-EINVAL);

	if (IS_ERR(group))
		return group;

	ret = iommu_group_add_device(group, dev);
	if (ret)
		goto out_put_group;

	return group;

out_put_group:
	iommu_group_put(group);

	return ERR_PTR(ret);
}

struct iommu_domain *iommu_group_default_domain(struct iommu_group *group)
{
	return group->default_domain;
}

static int probe_iommu_group(struct device *dev, void *data)
{
	struct list_head *group_list = data;
	struct iommu_group *group;
	int ret;

	/* Device is probed already if in a group */
	group = iommu_group_get(dev);
	if (group) {
		iommu_group_put(group);
		return 0;
	}

	ret = __iommu_probe_device(dev, group_list);
	if (ret == -ENODEV)
		ret = 0;

	return ret;
}

static int iommu_bus_notifier(struct notifier_block *nb,
			      unsigned long action, void *data)
{
	struct device *dev = data;

	if (action == BUS_NOTIFY_ADD_DEVICE) {
		int ret;

		ret = iommu_probe_device(dev);
		return (ret) ? NOTIFY_DONE : NOTIFY_OK;
	} else if (action == BUS_NOTIFY_REMOVED_DEVICE) {
		iommu_release_device(dev);
		return NOTIFY_OK;
	}

	return 0;
}

/* A target_type of 0 will select the best domain type and cannot fail */
static int iommu_get_default_domain_type(struct iommu_group *group,
					 int target_type)
{
	int best_type = target_type;
	struct group_device *gdev;
	struct device *last_dev;

	lockdep_assert_held(&group->mutex);

	for_each_group_device(group, gdev) {
		unsigned int type = iommu_get_def_domain_type(gdev->dev);

		if (best_type && type && best_type != type) {
			if (target_type) {
				dev_err_ratelimited(
					gdev->dev,
					"Device cannot be in %s domain\n",
					iommu_domain_type_str(target_type));
				return -1;
			}

			dev_warn(
				gdev->dev,
				"Device needs domain type %s, but device %s in the same iommu group requires type %s - using default\n",
				iommu_domain_type_str(type), dev_name(last_dev),
				iommu_domain_type_str(best_type));
			return iommu_def_domain_type;
		}
		if (!best_type)
			best_type = type;
		last_dev = gdev->dev;
	}

	if (!best_type)
		return iommu_def_domain_type;
	return best_type;
}

static int iommu_group_do_probe_finalize(struct device *dev, void *data)
{
	const struct iommu_ops *ops = dev_iommu_ops(dev);

	if (ops->probe_finalize)
		ops->probe_finalize(dev);

	return 0;
}

static void __iommu_group_dma_finalize(struct iommu_group *group)
{
	__iommu_group_for_each_dev(group, group->default_domain,
				   iommu_group_do_probe_finalize);
}

static int iommu_do_create_direct_mappings(struct device *dev, void *data)
{
	struct iommu_group *group = data;

	iommu_create_device_direct_mappings(group, dev);

	return 0;
}

static int iommu_group_create_direct_mappings(struct iommu_group *group)
{
	return __iommu_group_for_each_dev(group, group,
					  iommu_do_create_direct_mappings);
}

int bus_iommu_probe(const struct bus_type *bus)
{
	struct iommu_group *group, *next;
	LIST_HEAD(group_list);
	int ret;

	/*
	 * This code-path does not allocate the default domain when
	 * creating the iommu group, so do it after the groups are
	 * created.
	 */
	ret = bus_for_each_dev(bus, NULL, &group_list, probe_iommu_group);
	if (ret)
		return ret;

	list_for_each_entry_safe(group, next, &group_list, entry) {
		mutex_lock(&group->mutex);

		/* Remove item from the list */
		list_del_init(&group->entry);

		/* Try to allocate default domain */
		iommu_group_alloc_default_domain(
			bus, group, iommu_get_default_domain_type(group, 0));

		if (!group->default_domain) {
			mutex_unlock(&group->mutex);
			continue;
		}

		iommu_group_create_direct_mappings(group);

		ret = __iommu_group_set_domain(group, group->default_domain);

		mutex_unlock(&group->mutex);

		if (ret)
			break;

		__iommu_group_dma_finalize(group);
	}

	return ret;
}

bool iommu_present(const struct bus_type *bus)
{
	return bus->iommu_ops != NULL;
}
EXPORT_SYMBOL_GPL(iommu_present);

/**
 * device_iommu_capable() - check for a general IOMMU capability
 * @dev: device to which the capability would be relevant, if available
 * @cap: IOMMU capability
 *
 * Return: true if an IOMMU is present and supports the given capability
 * for the given device, otherwise false.
 */
bool device_iommu_capable(struct device *dev, enum iommu_cap cap)
{
	const struct iommu_ops *ops;

	if (!dev->iommu || !dev->iommu->iommu_dev)
		return false;

	ops = dev_iommu_ops(dev);
	if (!ops->capable)
		return false;

	return ops->capable(dev, cap);
}
EXPORT_SYMBOL_GPL(device_iommu_capable);

/**
 * iommu_group_has_isolated_msi() - Compute msi_device_has_isolated_msi()
 *       for a group
 * @group: Group to query
 *
 * IOMMU groups should not have differing values of
 * msi_device_has_isolated_msi() for devices in a group. However nothing
 * directly prevents this, so ensure mistakes don't result in isolation failures
 * by checking that all the devices are the same.
 */
bool iommu_group_has_isolated_msi(struct iommu_group *group)
{
	struct group_device *group_dev;
	bool ret = true;

	mutex_lock(&group->mutex);
	for_each_group_device(group, group_dev)
		ret &= msi_device_has_isolated_msi(group_dev->dev);
	mutex_unlock(&group->mutex);
	return ret;
}
EXPORT_SYMBOL_GPL(iommu_group_has_isolated_msi);

/**
 * iommu_set_fault_handler() - set a fault handler for an iommu domain
 * @domain: iommu domain
 * @handler: fault handler
 * @token: user data, will be passed back to the fault handler
 *
 * This function should be used by IOMMU users which want to be notified
 * whenever an IOMMU fault happens.
 *
 * The fault handler itself should return 0 on success, and an appropriate
 * error code otherwise.
 */
void iommu_set_fault_handler(struct iommu_domain *domain,
					iommu_fault_handler_t handler,
					void *token)
{
	BUG_ON(!domain);

	domain->handler = handler;
	domain->handler_token = token;
}
EXPORT_SYMBOL_GPL(iommu_set_fault_handler);

static struct iommu_domain *__iommu_domain_alloc(const struct bus_type *bus,
						 unsigned type)
{
	struct iommu_domain *domain;
	unsigned int alloc_type = type & IOMMU_DOMAIN_ALLOC_FLAGS;

	if (bus == NULL || bus->iommu_ops == NULL)
		return NULL;

	domain = bus->iommu_ops->domain_alloc(alloc_type);
	if (!domain)
		return NULL;

	domain->type = type;
	/*
	 * If not already set, assume all sizes by default; the driver
	 * may override this later
	 */
	if (!domain->pgsize_bitmap)
		domain->pgsize_bitmap = bus->iommu_ops->pgsize_bitmap;

	if (!domain->ops)
		domain->ops = bus->iommu_ops->default_domain_ops;

	if (iommu_is_dma_domain(domain) && iommu_get_dma_cookie(domain)) {
		iommu_domain_free(domain);
		domain = NULL;
	}
	return domain;
}

struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus)
{
	return __iommu_domain_alloc(bus, IOMMU_DOMAIN_UNMANAGED);
}
EXPORT_SYMBOL_GPL(iommu_domain_alloc);

void iommu_domain_free(struct iommu_domain *domain)
{
	if (domain->type == IOMMU_DOMAIN_SVA)
		mmdrop(domain->mm);
	iommu_put_dma_cookie(domain);
	domain->ops->free(domain);
}
EXPORT_SYMBOL_GPL(iommu_domain_free);

/*
 * Put the group's domain back to the appropriate core-owned domain - either the
 * standard kernel-mode DMA configuration or an all-DMA-blocked domain.
 */
static void __iommu_group_set_core_domain(struct iommu_group *group)
{
	struct iommu_domain *new_domain;

	if (group->owner)
		new_domain = group->blocking_domain;
	else
		new_domain = group->default_domain;

	__iommu_group_set_domain_nofail(group, new_domain);
}

static int __iommu_attach_device(struct iommu_domain *domain,
				 struct device *dev)
{
	int ret;

	if (unlikely(domain->ops->attach_dev == NULL))
		return -ENODEV;

	ret = domain->ops->attach_dev(domain, dev);
	if (ret)
		return ret;
	dev->iommu->attach_deferred = 0;
	trace_attach_device_to_domain(dev);
	return 0;
}

/**
 * iommu_attach_device - Attach an IOMMU domain to a device
 * @domain: IOMMU domain to attach
 * @dev: Device that will be attached
 *
 * Returns 0 on success and error code on failure
 *
 * Note that EINVAL can be treated as a soft failure, indicating
 * that certain configuration of the domain is incompatible with
 * the device. In this case attaching a different domain to the
 * device may succeed.
 */
int iommu_attach_device(struct iommu_domain *domain, struct device *dev)
{
	struct iommu_group *group;
	int ret;

	group = iommu_group_get(dev);
	if (!group)
		return -ENODEV;

	/*
	 * Lock the group to make sure the device-count doesn't
	 * change while we are attaching
	 */
	mutex_lock(&group->mutex);
	ret = -EINVAL;
	if (list_count_nodes(&group->devices) != 1)
		goto out_unlock;

	ret = __iommu_attach_group(domain, group);

out_unlock:
	mutex_unlock(&group->mutex);
	iommu_group_put(group);

	return ret;
}
EXPORT_SYMBOL_GPL(iommu_attach_device);

int iommu_deferred_attach(struct device *dev, struct iommu_domain *domain)
{
	if (dev->iommu && dev->iommu->attach_deferred)
		return __iommu_attach_device(domain, dev);

	return 0;
}

void iommu_detach_device(struct iommu_domain *domain, struct device *dev)
{
	struct iommu_group *group;

	group = iommu_group_get(dev);
	if (!group)
		return;

	mutex_lock(&group->mutex);
	if (WARN_ON(domain != group->domain) ||
	    WARN_ON(list_count_nodes(&group->devices) != 1))
		goto out_unlock;
	__iommu_group_set_core_domain(group);

out_unlock:
	mutex_unlock(&group->mutex);
	iommu_group_put(group);
}
EXPORT_SYMBOL_GPL(iommu_detach_device);

struct iommu_domain *iommu_get_domain_for_dev(struct device *dev)
{
	struct iommu_domain *domain;
	struct iommu_group *group;

	group = iommu_group_get(dev);
	if (!group)
		return NULL;

	domain = group->domain;

	iommu_group_put(group);

	return domain;
}
EXPORT_SYMBOL_GPL(iommu_get_domain_for_dev);

/*
 * For IOMMU_DOMAIN_DMA implementations which already provide their own
 * guarantees that the group and its default domain are valid and correct.
 */
struct iommu_domain *iommu_get_dma_domain(struct device *dev)
{
	return dev->iommu_group->default_domain;
}

static int __iommu_attach_group(struct iommu_domain *domain,
				struct iommu_group *group)
{
	if (group->domain && group->domain != group->default_domain &&
	    group->domain != group->blocking_domain)
		return -EBUSY;

	return __iommu_group_set_domain(group, domain);
}

/**
 * iommu_attach_group - Attach an IOMMU domain to an IOMMU group
 * @domain: IOMMU domain to attach
 * @group: IOMMU group that will be attached
 *
 * Returns 0 on success and error code on failure
 *
 * Note that EINVAL can be treated as a soft failure, indicating
 * that certain configuration of the domain is incompatible with
 * the group. In this case attaching a different domain to the
 * group may succeed.
 */
int iommu_attach_group(struct iommu_domain *domain, struct iommu_group *group)
{
	int ret;

	mutex_lock(&group->mutex);
	ret = __iommu_attach_group(domain, group);
	mutex_unlock(&group->mutex);

	return ret;
}
EXPORT_SYMBOL_GPL(iommu_attach_group);

static int __iommu_device_set_domain(struct iommu_group *group,
				     struct device *dev,
				     struct iommu_domain *new_domain,
				     unsigned int flags)
{
	int ret;

	if (dev->iommu->attach_deferred) {
		if (new_domain == group->default_domain)
			return 0;
		dev->iommu->attach_deferred = 0;
	}

	ret = __iommu_attach_device(new_domain, dev);
	if (ret) {
		/*
		 * If we have a blocking domain then try to attach that in hopes
		 * of avoiding a UAF. Modern drivers should implement blocking
		 * domains as global statics that cannot fail.
		 */
		if ((flags & IOMMU_SET_DOMAIN_MUST_SUCCEED) &&
		    group->blocking_domain &&
		    group->blocking_domain != new_domain)
			__iommu_attach_device(group->blocking_domain, dev);
		return ret;
	}
	return 0;
}

/*
 * If 0 is returned the group's domain is new_domain. If an error is returned
 * then the group's domain will be set back to the existing domain unless
 * IOMMU_SET_DOMAIN_MUST_SUCCEED, otherwise an error is returned and the group's
 * domains is left inconsistent. This is a driver bug to fail attach with a
 * previously good domain. We try to avoid a kernel UAF because of this.
 *
 * IOMMU groups are really the natural working unit of the IOMMU, but the IOMMU
 * API works on domains and devices.  Bridge that gap by iterating over the
 * devices in a group.  Ideally we'd have a single device which represents the
 * requestor ID of the group, but we also allow IOMMU drivers to create policy
 * defined minimum sets, where the physical hardware may be able to distiguish
 * members, but we wish to group them at a higher level (ex. untrusted
 * multi-function PCI devices).  Thus we attach each device.
 */
static int __iommu_group_set_domain_internal(struct iommu_group *group,
					     struct iommu_domain *new_domain,
					     unsigned int flags)
{
	struct group_device *last_gdev;
	struct group_device *gdev;
	int result;
	int ret;

	lockdep_assert_held(&group->mutex);

	if (group->domain == new_domain)
		return 0;

	/*
	 * New drivers should support default domains, so set_platform_dma()
	 * op will never be called. Otherwise the NULL domain represents some
	 * platform specific behavior.
	 */
	if (!new_domain) {
		for_each_group_device(group, gdev) {
			const struct iommu_ops *ops = dev_iommu_ops(gdev->dev);

			if (!WARN_ON(!ops->set_platform_dma_ops))
				ops->set_platform_dma_ops(gdev->dev);
		}
		group->domain = NULL;
		return 0;
	}

	/*
	 * Changing the domain is done by calling attach_dev() on the new
	 * domain. This switch does not have to be atomic and DMA can be
	 * discarded during the transition. DMA must only be able to access
	 * either new_domain or group->domain, never something else.
	 */
	result = 0;
	for_each_group_device(group, gdev) {
		ret = __iommu_device_set_domain(group, gdev->dev, new_domain,
						flags);
		if (ret) {
			result = ret;
			/*
			 * Keep trying the other devices in the group. If a
			 * driver fails attach to an otherwise good domain, and
			 * does not support blocking domains, it should at least
			 * drop its reference on the current domain so we don't
			 * UAF.
			 */
			if (flags & IOMMU_SET_DOMAIN_MUST_SUCCEED)
				continue;
			goto err_revert;
		}
	}
	group->domain = new_domain;
	return result;

err_revert:
	/*
	 * This is called in error unwind paths. A well behaved driver should
	 * always allow us to attach to a domain that was already attached.
	 */
	last_gdev = gdev;
	for_each_group_device(group, gdev) {
		const struct iommu_ops *ops = dev_iommu_ops(gdev->dev);

		/*
		 * If set_platform_dma_ops is not present a NULL domain can
		 * happen only for first probe, in which case we leave
		 * group->domain as NULL and let release clean everything up.
		 */
		if (group->domain)
			WARN_ON(__iommu_device_set_domain(
				group, gdev->dev, group->domain,
				IOMMU_SET_DOMAIN_MUST_SUCCEED));
		else if (ops->set_platform_dma_ops)
			ops->set_platform_dma_ops(gdev->dev);
		if (gdev == last_gdev)
			break;
	}
	return ret;
}

void iommu_detach_group(struct iommu_domain *domain, struct iommu_group *group)
{
	mutex_lock(&group->mutex);
	__iommu_group_set_core_domain(group);
	mutex_unlock(&group->mutex);
}
EXPORT_SYMBOL_GPL(iommu_detach_group);

phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova)
{
	if (domain->type == IOMMU_DOMAIN_IDENTITY)
		return iova;

	if (domain->type == IOMMU_DOMAIN_BLOCKED)
		return 0;

	return domain->ops->iova_to_phys(domain, iova);
}
EXPORT_SYMBOL_GPL(iommu_iova_to_phys);

static size_t iommu_pgsize(struct iommu_domain *domain, unsigned long iova,
			   phys_addr_t paddr, size_t size, size_t *count)
{
	unsigned int pgsize_idx, pgsize_idx_next;
	unsigned long pgsizes;
	size_t offset, pgsize, pgsize_next;
	unsigned long addr_merge = paddr | iova;

	/* Page sizes supported by the hardware and small enough for @size */
	pgsizes = domain->pgsize_bitmap & GENMASK(__fls(size), 0);

	/* Constrain the page sizes further based on the maximum alignment */
	if (likely(addr_merge))
		pgsizes &= GENMASK(__ffs(addr_merge), 0);

	/* Make sure we have at least one suitable page size */
	BUG_ON(!pgsizes);

	/* Pick the biggest page size remaining */
	pgsize_idx = __fls(pgsizes);
	pgsize = BIT(pgsize_idx);
	if (!count)
		return pgsize;

	/* Find the next biggest support page size, if it exists */
	pgsizes = domain->pgsize_bitmap & ~GENMASK(pgsize_idx, 0);
	if (!pgsizes)
		goto out_set_count;

	pgsize_idx_next = __ffs(pgsizes);
	pgsize_next = BIT(pgsize_idx_next);

	/*
	 * There's no point trying a bigger page size unless the virtual
	 * and physical addresses are similarly offset within the larger page.
	 */
	if ((iova ^ paddr) & (pgsize_next - 1))
		goto out_set_count;

	/* Calculate the offset to the next page size alignment boundary */
	offset = pgsize_next - (addr_merge & (pgsize_next - 1));

	/*
	 * If size is big enough to accommodate the larger page, reduce
	 * the number of smaller pages.
	 */
	if (offset + pgsize_next <= size)
		size = offset;

out_set_count:
	*count = size >> pgsize_idx;
	return pgsize;
}

static int __iommu_map_pages(struct iommu_domain *domain, unsigned long iova,
			     phys_addr_t paddr, size_t size, int prot,
			     gfp_t gfp, size_t *mapped)
{
	const struct iommu_domain_ops *ops = domain->ops;
	size_t pgsize, count;
	int ret;

	pgsize = iommu_pgsize(domain, iova, paddr, size, &count);

	pr_debug("mapping: iova 0x%lx pa %pa pgsize 0x%zx count %zu\n",
		 iova, &paddr, pgsize, count);

	if (ops->map_pages) {
		ret = ops->map_pages(domain, iova, paddr, pgsize, count, prot,
				     gfp, mapped);
	} else {
		ret = ops->map(domain, iova, paddr, pgsize, prot, gfp);
		*mapped = ret ? 0 : pgsize;
	}

	return ret;
}

static int __iommu_map(struct iommu_domain *domain, unsigned long iova,
		       phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
{
	const struct iommu_domain_ops *ops = domain->ops;
	unsigned long orig_iova = iova;
	unsigned int min_pagesz;
	size_t orig_size = size;
	phys_addr_t orig_paddr = paddr;
	int ret = 0;

	if (unlikely(!(ops->map || ops->map_pages) ||
		     domain->pgsize_bitmap == 0UL))
		return -ENODEV;

	if (unlikely(!(domain->type & __IOMMU_DOMAIN_PAGING)))
		return -EINVAL;

	/* find out the minimum page size supported */
	min_pagesz = 1 << __ffs(domain->pgsize_bitmap);

	/*
	 * both the virtual address and the physical one, as well as
	 * the size of the mapping, must be aligned (at least) to the
	 * size of the smallest page supported by the hardware
	 */
	if (!IS_ALIGNED(iova | paddr | size, min_pagesz)) {
		pr_err("unaligned: iova 0x%lx pa %pa size 0x%zx min_pagesz 0x%x\n",
		       iova, &paddr, size, min_pagesz);
		return -EINVAL;
	}

	pr_debug("map: iova 0x%lx pa %pa size 0x%zx\n", iova, &paddr, size);

	while (size) {
		size_t mapped = 0;

		ret = __iommu_map_pages(domain, iova, paddr, size, prot, gfp,
					&mapped);
		/*
		 * Some pages may have been mapped, even if an error occurred,
		 * so we should account for those so they can be unmapped.
		 */
		size -= mapped;

		if (ret)
			break;

		iova += mapped;
		paddr += mapped;
	}

	/* unroll mapping in case something went wrong */
	if (ret)
		iommu_unmap(domain, orig_iova, orig_size - size);
	else
		trace_map(orig_iova, orig_paddr, orig_size);

	return ret;
}

int iommu_map(struct iommu_domain *domain, unsigned long iova,
	      phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
{
	const struct iommu_domain_ops *ops = domain->ops;
	int ret;

	might_sleep_if(gfpflags_allow_blocking(gfp));

	/* Discourage passing strange GFP flags */
	if (WARN_ON_ONCE(gfp & (__GFP_COMP | __GFP_DMA | __GFP_DMA32 |
				__GFP_HIGHMEM)))
		return -EINVAL;

	ret = __iommu_map(domain, iova, paddr, size, prot, gfp);
	if (ret == 0 && ops->iotlb_sync_map)
		ops->iotlb_sync_map(domain, iova, size);

	return ret;
}
EXPORT_SYMBOL_GPL(iommu_map);

static size_t __iommu_unmap_pages(struct iommu_domain *domain,
				  unsigned long iova, size_t size,
				  struct iommu_iotlb_gather *iotlb_gather)
{
	const struct iommu_domain_ops *ops = domain->ops;
	size_t pgsize, count;

	pgsize = iommu_pgsize(domain, iova, iova, size, &count);
	return ops->unmap_pages ?
	       ops->unmap_pages(domain, iova, pgsize, count, iotlb_gather) :
	       ops->unmap(domain, iova, pgsize, iotlb_gather);
}

static size_t __iommu_unmap(struct iommu_domain *domain,
			    unsigned long iova, size_t size,
			    struct iommu_iotlb_gather *iotlb_gather)
{
	const struct iommu_domain_ops *ops = domain->ops;
	size_t unmapped_page, unmapped = 0;
	unsigned long orig_iova = iova;
	unsigned int min_pagesz;

	if (unlikely(!(ops->unmap || ops->unmap_pages) ||
		     domain->pgsize_bitmap == 0UL))
		return 0;

	if (unlikely(!(domain->type & __IOMMU_DOMAIN_PAGING)))
		return 0;

	/* find out the minimum page size supported */
	min_pagesz = 1 << __ffs(domain->pgsize_bitmap);

	/*
	 * The virtual address, as well as the size of the mapping, must be
	 * aligned (at least) to the size of the smallest page supported
	 * by the hardware
	 */
	if (!IS_ALIGNED(iova | size, min_pagesz)) {
		pr_err("unaligned: iova 0x%lx size 0x%zx min_pagesz 0x%x\n",
		       iova, size, min_pagesz);
		return 0;
	}

	pr_debug("unmap this: iova 0x%lx size 0x%zx\n", iova, size);

	/*
	 * Keep iterating until we either unmap 'size' bytes (or more)
	 * or we hit an area that isn't mapped.
	 */
	while (unmapped < size) {
		unmapped_page = __iommu_unmap_pages(domain, iova,
						    size - unmapped,
						    iotlb_gather);
		if (!unmapped_page)
			break;

		pr_debug("unmapped: iova 0x%lx size 0x%zx\n",
			 iova, unmapped_page);

		iova += unmapped_page;
		unmapped += unmapped_page;
	}

	trace_unmap(orig_iova, size, unmapped);
	return unmapped;
}

size_t iommu_unmap(struct iommu_domain *domain,
		   unsigned long iova, size_t size)
{
	struct iommu_iotlb_gather iotlb_gather;
	size_t ret;

	iommu_iotlb_gather_init(&iotlb_gather);
	ret = __iommu_unmap(domain, iova, size, &iotlb_gather);
	iommu_iotlb_sync(domain, &iotlb_gather);

	return ret;
}
EXPORT_SYMBOL_GPL(iommu_unmap);

size_t iommu_unmap_fast(struct iommu_domain *domain,
			unsigned long iova, size_t size,
			struct iommu_iotlb_gather *iotlb_gather)
{
	return __iommu_unmap(domain, iova, size, iotlb_gather);
}
EXPORT_SYMBOL_GPL(iommu_unmap_fast);

ssize_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
		     struct scatterlist *sg, unsigned int nents, int prot,
		     gfp_t gfp)
{
	const struct iommu_domain_ops *ops = domain->ops;
	size_t len = 0, mapped = 0;
	phys_addr_t start;
	unsigned int i = 0;
	int ret;

	might_sleep_if(gfpflags_allow_blocking(gfp));

	/* Discourage passing strange GFP flags */
	if (WARN_ON_ONCE(gfp & (__GFP_COMP | __GFP_DMA | __GFP_DMA32 |
				__GFP_HIGHMEM)))
		return -EINVAL;

	while (i <= nents) {
		phys_addr_t s_phys = sg_phys(sg);

		if (len && s_phys != start + len) {
			ret = __iommu_map(domain, iova + mapped, start,
					len, prot, gfp);

			if (ret)
				goto out_err;

			mapped += len;
			len = 0;
		}

		if (sg_is_dma_bus_address(sg))
			goto next;

		if (len) {
			len += sg->length;
		} else {
			len = sg->length;
			start = s_phys;
		}

next:
		if (++i < nents)
			sg = sg_next(sg);
	}

	if (ops->iotlb_sync_map)
		ops->iotlb_sync_map(domain, iova, mapped);
	return mapped;

out_err:
	/* undo mappings already done */
	iommu_unmap(domain, iova, mapped);

	return ret;
}
EXPORT_SYMBOL_GPL(iommu_map_sg);

/**
 * report_iommu_fault() - report about an IOMMU fault to the IOMMU framework
 * @domain: the iommu domain where the fault has happened
 * @dev: the device where the fault has happened
 * @iova: the faulting address
 * @flags: mmu fault flags (e.g. IOMMU_FAULT_READ/IOMMU_FAULT_WRITE/...)
 *
 * This function should be called by the low-level IOMMU implementations
 * whenever IOMMU faults happen, to allow high-level users, that are
 * interested in such events, to know about them.
 *
 * This event may be useful for several possible use cases:
 * - mere logging of the event
 * - dynamic TLB/PTE loading
 * - if restarting of the faulting device is required
 *
 * Returns 0 on success and an appropriate error code otherwise (if dynamic
 * PTE/TLB loading will one day be supported, implementations will be able
 * to tell whether it succeeded or not according to this return value).
 *
 * Specifically, -ENOSYS is returned if a fault handler isn't installed
 * (though fault handlers can also return -ENOSYS, in case they want to
 * elicit the default behavior of the IOMMU drivers).
 */
int report_iommu_fault(struct iommu_domain *domain, struct device *dev,
		       unsigned long iova, int flags)
{
	int ret = -ENOSYS;

	/*
	 * if upper layers showed interest and installed a fault handler,
	 * invoke it.
	 */
	if (domain->handler)
		ret = domain->handler(domain, dev, iova, flags,
						domain->handler_token);

	trace_io_page_fault(dev, iova, flags);
	return ret;
}
EXPORT_SYMBOL_GPL(report_iommu_fault);

static int __init iommu_init(void)
{
	iommu_group_kset = kset_create_and_add("iommu_groups",
					       NULL, kernel_kobj);
	BUG_ON(!iommu_group_kset);

	iommu_debugfs_setup();

	return 0;
}
core_initcall(iommu_init);

int iommu_enable_nesting(struct iommu_domain *domain)
{
	if (domain->type != IOMMU_DOMAIN_UNMANAGED)
		return -EINVAL;
	if (!domain->ops->enable_nesting)
		return -EINVAL;
	return domain->ops->enable_nesting(domain);
}
EXPORT_SYMBOL_GPL(iommu_enable_nesting);

int iommu_set_pgtable_quirks(struct iommu_domain *domain,
		unsigned long quirk)
{
	if (domain->type != IOMMU_DOMAIN_UNMANAGED)
		return -EINVAL;
	if (!domain->ops->set_pgtable_quirks)
		return -EINVAL;
	return domain->ops->set_pgtable_quirks(domain, quirk);
}
EXPORT_SYMBOL_GPL(iommu_set_pgtable_quirks);

void iommu_get_resv_regions(struct device *dev, struct list_head *list)
{
	const struct iommu_ops *ops = dev_iommu_ops(dev);

	if (ops->get_resv_regions)
		ops->get_resv_regions(dev, list);
}

/**
 * iommu_put_resv_regions - release resered regions
 * @dev: device for which to free reserved regions
 * @list: reserved region list for device
 *
 * This releases a reserved region list acquired by iommu_get_resv_regions().
 */
void iommu_put_resv_regions(struct device *dev, struct list_head *list)
{
	struct iommu_resv_region *entry, *next;

	list_for_each_entry_safe(entry, next, list, list) {
		if (entry->free)
			entry->free(dev, entry);
		else
			kfree(entry);
	}
}
EXPORT_SYMBOL(iommu_put_resv_regions);

struct iommu_resv_region *iommu_alloc_resv_region(phys_addr_t start,
						  size_t length, int prot,
						  enum iommu_resv_type type,
						  gfp_t gfp)
{
	struct iommu_resv_region *region;

	region = kzalloc(sizeof(*region), gfp);
	if (!region)
		return NULL;

	INIT_LIST_HEAD(&region->list);
	region->start = start;
	region->length = length;
	region->prot = prot;
	region->type = type;
	return region;
}
EXPORT_SYMBOL_GPL(iommu_alloc_resv_region);

void iommu_set_default_passthrough(bool cmd_line)
{
	if (cmd_line)
		iommu_cmd_line |= IOMMU_CMD_LINE_DMA_API;
	iommu_def_domain_type = IOMMU_DOMAIN_IDENTITY;
}

void iommu_set_default_translated(bool cmd_line)
{
	if (cmd_line)
		iommu_cmd_line |= IOMMU_CMD_LINE_DMA_API;
	iommu_def_domain_type = IOMMU_DOMAIN_DMA;
}

bool iommu_default_passthrough(void)
{
	return iommu_def_domain_type == IOMMU_DOMAIN_IDENTITY;
}
EXPORT_SYMBOL_GPL(iommu_default_passthrough);

const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode)
{
	const struct iommu_ops *ops = NULL;
	struct iommu_device *iommu;

	spin_lock(&iommu_device_lock);
	list_for_each_entry(iommu, &iommu_device_list, list)
		if (iommu->fwnode == fwnode) {
			ops = iommu->ops;
			break;
		}
	spin_unlock(&iommu_device_lock);
	return ops;
}

int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode,
		      const struct iommu_ops *ops)
{
	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);

	if (fwspec)
		return ops == fwspec->ops ? 0 : -EINVAL;

	if (!dev_iommu_get(dev))
		return -ENOMEM;

	/* Preallocate for the overwhelmingly common case of 1 ID */
	fwspec = kzalloc(struct_size(fwspec, ids, 1), GFP_KERNEL);
	if (!fwspec)
		return -ENOMEM;

	of_node_get(to_of_node(iommu_fwnode));
	fwspec->iommu_fwnode = iommu_fwnode;
	fwspec->ops = ops;
	dev_iommu_fwspec_set(dev, fwspec);
	return 0;
}
EXPORT_SYMBOL_GPL(iommu_fwspec_init);

void iommu_fwspec_free(struct device *dev)
{
	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);

	if (fwspec) {
		fwnode_handle_put(fwspec->iommu_fwnode);
		kfree(fwspec);
		dev_iommu_fwspec_set(dev, NULL);
	}
}
EXPORT_SYMBOL_GPL(iommu_fwspec_free);

int iommu_fwspec_add_ids(struct device *dev, u32 *ids, int num_ids)
{
	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
	int i, new_num;

	if (!fwspec)
		return -EINVAL;

	new_num = fwspec->num_ids + num_ids;
	if (new_num > 1) {
		fwspec = krealloc(fwspec, struct_size(fwspec, ids, new_num),
				  GFP_KERNEL);
		if (!fwspec)
			return -ENOMEM;

		dev_iommu_fwspec_set(dev, fwspec);
	}

	for (i = 0; i < num_ids; i++)
		fwspec->ids[fwspec->num_ids + i] = ids[i];

	fwspec->num_ids = new_num;
	return 0;
}
EXPORT_SYMBOL_GPL(iommu_fwspec_add_ids);

/*
 * Per device IOMMU features.
 */
int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features feat)
{
	if (dev->iommu && dev->iommu->iommu_dev) {
		const struct iommu_ops *ops = dev->iommu->iommu_dev->ops;

		if (ops->dev_enable_feat)
			return ops->dev_enable_feat(dev, feat);
	}

	return -ENODEV;
}
EXPORT_SYMBOL_GPL(iommu_dev_enable_feature);

/*
 * The device drivers should do the necessary cleanups before calling this.
 */
int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat)
{
	if (dev->iommu && dev->iommu->iommu_dev) {
		const struct iommu_ops *ops = dev->iommu->iommu_dev->ops;

		if (ops->dev_disable_feat)
			return ops->dev_disable_feat(dev, feat);
	}

	return -EBUSY;
}
EXPORT_SYMBOL_GPL(iommu_dev_disable_feature);

/*
 * Changes the default domain of an iommu group
 *
 * @group: The group for which the default domain should be changed
 * @dev: The first device in the group
 * @type: The type of the new default domain that gets associated with the group
 *
 * Returns 0 on success and error code on failure
 *
 * Note:
 * 1. Presently, this function is called only when user requests to change the
 *    group's default domain type through /sys/kernel/iommu_groups/<grp_id>/type
 *    Please take a closer look if intended to use for other purposes.
 */
static int iommu_change_dev_def_domain(struct iommu_group *group,
				       struct device *dev, int type)
{
	struct iommu_domain *prev_dom;
	int ret;

	lockdep_assert_held(&group->mutex);

	prev_dom = group->default_domain;
	type = iommu_get_default_domain_type(group, type);
	if (type < 0)
		return -EINVAL;

	/*
	 * Switch to a new domain only if the requested domain type is different
	 * from the existing default domain type
	 */
	if (prev_dom->type == type)
		return 0;

	group->default_domain = NULL;
	group->domain = NULL;

	/* Sets group->default_domain to the newly allocated domain */
	ret = iommu_group_alloc_default_domain(dev->bus, group, type);
	if (ret)
		goto restore_old_domain;

	group->domain = prev_dom;
	ret = iommu_create_device_direct_mappings(group, dev);
	if (ret)
		goto free_new_domain;

	ret = __iommu_group_set_domain(group, group->default_domain);
	if (ret)
		goto free_new_domain;

	iommu_domain_free(prev_dom);

	return 0;

free_new_domain:
	iommu_domain_free(group->default_domain);
restore_old_domain:
	group->default_domain = prev_dom;

	return ret;
}

/*
 * Changing the default domain through sysfs requires the users to unbind the
 * drivers from the devices in the iommu group, except for a DMA -> DMA-FQ
 * transition. Return failure if this isn't met.
 *
 * We need to consider the race between this and the device release path.
 * group->mutex is used here to guarantee that the device release path
 * will not be entered at the same time.
 */
static ssize_t iommu_group_store_type(struct iommu_group *group,
				      const char *buf, size_t count)
{
	struct group_device *grp_dev;
	struct device *dev;
	int ret, req_type;

	if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO))
		return -EACCES;

	if (WARN_ON(!group) || !group->default_domain)
		return -EINVAL;

	if (sysfs_streq(buf, "identity"))
		req_type = IOMMU_DOMAIN_IDENTITY;
	else if (sysfs_streq(buf, "DMA"))
		req_type = IOMMU_DOMAIN_DMA;
	else if (sysfs_streq(buf, "DMA-FQ"))
		req_type = IOMMU_DOMAIN_DMA_FQ;
	else if (sysfs_streq(buf, "auto"))
		req_type = 0;
	else
		return -EINVAL;

	mutex_lock(&group->mutex);
	/* We can bring up a flush queue without tearing down the domain. */
	if (req_type == IOMMU_DOMAIN_DMA_FQ &&
	    group->default_domain->type == IOMMU_DOMAIN_DMA) {
		ret = iommu_dma_init_fq(group->default_domain);
		if (!ret)
			group->default_domain->type = IOMMU_DOMAIN_DMA_FQ;
		mutex_unlock(&group->mutex);

		return ret ?: count;
	}

	/* Otherwise, ensure that device exists and no driver is bound. */
	if (list_empty(&group->devices) || group->owner_cnt) {
		mutex_unlock(&group->mutex);
		return -EPERM;
	}

	grp_dev = list_first_entry(&group->devices, struct group_device, list);
	dev = grp_dev->dev;

	ret = iommu_change_dev_def_domain(group, dev, req_type);

	/*
	 * Release the mutex here because ops->probe_finalize() call-back of
	 * some vendor IOMMU drivers calls arm_iommu_attach_device() which
	 * in-turn might call back into IOMMU core code, where it tries to take
	 * group->mutex, resulting in a deadlock.
	 */
	mutex_unlock(&group->mutex);

	/* Make sure dma_ops is appropriatley set */
	if (!ret)
		__iommu_group_dma_finalize(group);

	return ret ?: count;
}

static bool iommu_is_default_domain(struct iommu_group *group)
{
	if (group->domain == group->default_domain)
		return true;

	/*
	 * If the default domain was set to identity and it is still an identity
	 * domain then we consider this a pass. This happens because of
	 * amd_iommu_init_device() replacing the default idenytity domain with an
	 * identity domain that has a different configuration for AMDGPU.
	 */
	if (group->default_domain &&
	    group->default_domain->type == IOMMU_DOMAIN_IDENTITY &&
	    group->domain && group->domain->type == IOMMU_DOMAIN_IDENTITY)
		return true;
	return false;
}

/**
 * iommu_device_use_default_domain() - Device driver wants to handle device
 *                                     DMA through the kernel DMA API.
 * @dev: The device.
 *
 * The device driver about to bind @dev wants to do DMA through the kernel
 * DMA API. Return 0 if it is allowed, otherwise an error.
 */
int iommu_device_use_default_domain(struct device *dev)
{
	struct iommu_group *group = iommu_group_get(dev);
	int ret = 0;

	if (!group)
		return 0;

	mutex_lock(&group->mutex);
	if (group->owner_cnt) {
		if (group->owner || !iommu_is_default_domain(group) ||
		    !xa_empty(&group->pasid_array)) {
			ret = -EBUSY;
			goto unlock_out;
		}
	}

	group->owner_cnt++;

unlock_out:
	mutex_unlock(&group->mutex);
	iommu_group_put(group);

	return ret;
}

/**
 * iommu_device_unuse_default_domain() - Device driver stops handling device
 *                                       DMA through the kernel DMA API.
 * @dev: The device.
 *
 * The device driver doesn't want to do DMA through kernel DMA API anymore.
 * It must be called after iommu_device_use_default_domain().
 */
void iommu_device_unuse_default_domain(struct device *dev)
{
	struct iommu_group *group = iommu_group_get(dev);

	if (!group)
		return;

	mutex_lock(&group->mutex);
	if (!WARN_ON(!group->owner_cnt || !xa_empty(&group->pasid_array)))
		group->owner_cnt--;

	mutex_unlock(&group->mutex);
	iommu_group_put(group);
}

static int __iommu_group_alloc_blocking_domain(struct iommu_group *group)
{
	struct group_device *dev =
		list_first_entry(&group->devices, struct group_device, list);

	if (group->blocking_domain)
		return 0;

	group->blocking_domain =
		__iommu_domain_alloc(dev->dev->bus, IOMMU_DOMAIN_BLOCKED);
	if (!group->blocking_domain) {
		/*
		 * For drivers that do not yet understand IOMMU_DOMAIN_BLOCKED
		 * create an empty domain instead.
		 */
		group->blocking_domain = __iommu_domain_alloc(
			dev->dev->bus, IOMMU_DOMAIN_UNMANAGED);
		if (!group->blocking_domain)
			return -EINVAL;
	}
	return 0;
}

static int __iommu_take_dma_ownership(struct iommu_group *group, void *owner)
{
	int ret;

	if ((group->domain && group->domain != group->default_domain) ||
	    !xa_empty(&group->pasid_array))
		return -EBUSY;

	ret = __iommu_group_alloc_blocking_domain(group);
	if (ret)
		return ret;
	ret = __iommu_group_set_domain(group, group->blocking_domain);
	if (ret)
		return ret;

	group->owner = owner;
	group->owner_cnt++;
	return 0;
}

/**
 * iommu_group_claim_dma_owner() - Set DMA ownership of a group
 * @group: The group.
 * @owner: Caller specified pointer. Used for exclusive ownership.
 *
 * This is to support backward compatibility for vfio which manages the dma
 * ownership in iommu_group level. New invocations on this interface should be
 * prohibited. Only a single owner may exist for a group.
 */
int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner)
{
	int ret = 0;

	if (WARN_ON(!owner))
		return -EINVAL;

	mutex_lock(&group->mutex);
	if (group->owner_cnt) {
		ret = -EPERM;
		goto unlock_out;
	}

	ret = __iommu_take_dma_ownership(group, owner);
unlock_out:
	mutex_unlock(&group->mutex);

	return ret;
}
EXPORT_SYMBOL_GPL(iommu_group_claim_dma_owner);

/**
 * iommu_device_claim_dma_owner() - Set DMA ownership of a device
 * @dev: The device.
 * @owner: Caller specified pointer. Used for exclusive ownership.
 *
 * Claim the DMA ownership of a device. Multiple devices in the same group may
 * concurrently claim ownership if they present the same owner value. Returns 0
 * on success and error code on failure
 */
int iommu_device_claim_dma_owner(struct device *dev, void *owner)
{
	struct iommu_group *group;
	int ret = 0;

	if (WARN_ON(!owner))
		return -EINVAL;

	group = iommu_group_get(dev);
	if (!group)
		return -ENODEV;

	mutex_lock(&group->mutex);
	if (group->owner_cnt) {
		if (group->owner != owner) {
			ret = -EPERM;
			goto unlock_out;
		}
		group->owner_cnt++;
		goto unlock_out;
	}

	ret = __iommu_take_dma_ownership(group, owner);
unlock_out:
	mutex_unlock(&group->mutex);
	iommu_group_put(group);

	return ret;
}
EXPORT_SYMBOL_GPL(iommu_device_claim_dma_owner);

static void __iommu_release_dma_ownership(struct iommu_group *group)
{
	if (WARN_ON(!group->owner_cnt || !group->owner ||
		    !xa_empty(&group->pasid_array)))
		return;

	group->owner_cnt = 0;
	group->owner = NULL;
	__iommu_group_set_domain_nofail(group, group->default_domain);
}

/**
 * iommu_group_release_dma_owner() - Release DMA ownership of a group
 * @dev: The device
 *
 * Release the DMA ownership claimed by iommu_group_claim_dma_owner().
 */
void iommu_group_release_dma_owner(struct iommu_group *group)
{
	mutex_lock(&group->mutex);
	__iommu_release_dma_ownership(group);
	mutex_unlock(&group->mutex);
}
EXPORT_SYMBOL_GPL(iommu_group_release_dma_owner);

/**
 * iommu_device_release_dma_owner() - Release DMA ownership of a device
 * @group: The device.
 *
 * Release the DMA ownership claimed by iommu_device_claim_dma_owner().
 */
void iommu_device_release_dma_owner(struct device *dev)
{
	struct iommu_group *group = iommu_group_get(dev);

	mutex_lock(&group->mutex);
	if (group->owner_cnt > 1)
		group->owner_cnt--;
	else
		__iommu_release_dma_ownership(group);
	mutex_unlock(&group->mutex);
	iommu_group_put(group);
}
EXPORT_SYMBOL_GPL(iommu_device_release_dma_owner);

/**
 * iommu_group_dma_owner_claimed() - Query group dma ownership status
 * @group: The group.
 *
 * This provides status query on a given group. It is racy and only for
 * non-binding status reporting.
 */
bool iommu_group_dma_owner_claimed(struct iommu_group *group)
{
	unsigned int user;

	mutex_lock(&group->mutex);
	user = group->owner_cnt;
	mutex_unlock(&group->mutex);

	return user;
}
EXPORT_SYMBOL_GPL(iommu_group_dma_owner_claimed);

static int __iommu_set_group_pasid(struct iommu_domain *domain,
				   struct iommu_group *group, ioasid_t pasid)
{
	struct group_device *device;
	int ret = 0;

	for_each_group_device(group, device) {
		ret = domain->ops->set_dev_pasid(domain, device->dev, pasid);
		if (ret)
			break;
	}

	return ret;
}

static void __iommu_remove_group_pasid(struct iommu_group *group,
				       ioasid_t pasid)
{
	struct group_device *device;
	const struct iommu_ops *ops;

	for_each_group_device(group, device) {
		ops = dev_iommu_ops(device->dev);
		ops->remove_dev_pasid(device->dev, pasid);
	}
}

/*
 * iommu_attach_device_pasid() - Attach a domain to pasid of device
 * @domain: the iommu domain.
 * @dev: the attached device.
 * @pasid: the pasid of the device.
 *
 * Return: 0 on success, or an error.
 */
int iommu_attach_device_pasid(struct iommu_domain *domain,
			      struct device *dev, ioasid_t pasid)
{
	struct iommu_group *group;
	void *curr;
	int ret;

	if (!domain->ops->set_dev_pasid)
		return -EOPNOTSUPP;

	group = iommu_group_get(dev);
	if (!group)
		return -ENODEV;

	mutex_lock(&group->mutex);
	curr = xa_cmpxchg(&group->pasid_array, pasid, NULL, domain, GFP_KERNEL);
	if (curr) {
		ret = xa_err(curr) ? : -EBUSY;
		goto out_unlock;
	}

	ret = __iommu_set_group_pasid(domain, group, pasid);
	if (ret) {
		__iommu_remove_group_pasid(group, pasid);
		xa_erase(&group->pasid_array, pasid);
	}
out_unlock:
	mutex_unlock(&group->mutex);
	iommu_group_put(group);

	return ret;
}
EXPORT_SYMBOL_GPL(iommu_attach_device_pasid);

/*
 * iommu_detach_device_pasid() - Detach the domain from pasid of device
 * @domain: the iommu domain.
 * @dev: the attached device.
 * @pasid: the pasid of the device.
 *
 * The @domain must have been attached to @pasid of the @dev with
 * iommu_attach_device_pasid().
 */
void iommu_detach_device_pasid(struct iommu_domain *domain, struct device *dev,
			       ioasid_t pasid)
{
	struct iommu_group *group = iommu_group_get(dev);

	mutex_lock(&group->mutex);
	__iommu_remove_group_pasid(group, pasid);
	WARN_ON(xa_erase(&group->pasid_array, pasid) != domain);
	mutex_unlock(&group->mutex);

	iommu_group_put(group);
}
EXPORT_SYMBOL_GPL(iommu_detach_device_pasid);

/*
 * iommu_get_domain_for_dev_pasid() - Retrieve domain for @pasid of @dev
 * @dev: the queried device
 * @pasid: the pasid of the device
 * @type: matched domain type, 0 for any match
 *
 * This is a variant of iommu_get_domain_for_dev(). It returns the existing
 * domain attached to pasid of a device. Callers must hold a lock around this
 * function, and both iommu_attach/detach_dev_pasid() whenever a domain of
 * type is being manipulated. This API does not internally resolve races with
 * attach/detach.
 *
 * Return: attached domain on success, NULL otherwise.
 */
struct iommu_domain *iommu_get_domain_for_dev_pasid(struct device *dev,
						    ioasid_t pasid,
						    unsigned int type)
{
	struct iommu_domain *domain;
	struct iommu_group *group;

	group = iommu_group_get(dev);
	if (!group)
		return NULL;

	xa_lock(&group->pasid_array);
	domain = xa_load(&group->pasid_array, pasid);
	if (type && domain && domain->type != type)
		domain = ERR_PTR(-EBUSY);
	xa_unlock(&group->pasid_array);
	iommu_group_put(group);

	return domain;
}
EXPORT_SYMBOL_GPL(iommu_get_domain_for_dev_pasid);

struct iommu_domain *iommu_sva_domain_alloc(struct device *dev,
					    struct mm_struct *mm)
{
	const struct iommu_ops *ops = dev_iommu_ops(dev);
	struct iommu_domain *domain;

	domain = ops->domain_alloc(IOMMU_DOMAIN_SVA);
	if (!domain)
		return NULL;

	domain->type = IOMMU_DOMAIN_SVA;
	mmgrab(mm);
	domain->mm = mm;
	domain->iopf_handler = iommu_sva_handle_iopf;
	domain->fault_data = mm;

	return domain;
}