Free Electrons

Embedded Linux Experts

   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
/*
 * IOMMU API for ARM architected SMMUv3 implementations.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 *
 * Copyright (C) 2015 ARM Limited
 *
 * Author: Will Deacon <will.deacon@arm.com>
 *
 * This driver is powered by bad coffee and bombay mix.
 */

#include <linux/acpi.h>
#include <linux/acpi_iort.h>
#include <linux/delay.h>
#include <linux/dma-iommu.h>
#include <linux/err.h>
#include <linux/interrupt.h>
#include <linux/iommu.h>
#include <linux/iopoll.h>
#include <linux/module.h>
#include <linux/msi.h>
#include <linux/of.h>
#include <linux/of_address.h>
#include <linux/of_iommu.h>
#include <linux/of_platform.h>
#include <linux/pci.h>
#include <linux/platform_device.h>

#include <linux/amba/bus.h>

#include "io-pgtable.h"

/* MMIO registers */
#define ARM_SMMU_IDR0			0x0
#define IDR0_ST_LVL_SHIFT		27
#define IDR0_ST_LVL_MASK		0x3
#define IDR0_ST_LVL_2LVL		(1 << IDR0_ST_LVL_SHIFT)
#define IDR0_STALL_MODEL_SHIFT		24
#define IDR0_STALL_MODEL_MASK		0x3
#define IDR0_STALL_MODEL_STALL		(0 << IDR0_STALL_MODEL_SHIFT)
#define IDR0_STALL_MODEL_FORCE		(2 << IDR0_STALL_MODEL_SHIFT)
#define IDR0_TTENDIAN_SHIFT		21
#define IDR0_TTENDIAN_MASK		0x3
#define IDR0_TTENDIAN_LE		(2 << IDR0_TTENDIAN_SHIFT)
#define IDR0_TTENDIAN_BE		(3 << IDR0_TTENDIAN_SHIFT)
#define IDR0_TTENDIAN_MIXED		(0 << IDR0_TTENDIAN_SHIFT)
#define IDR0_CD2L			(1 << 19)
#define IDR0_VMID16			(1 << 18)
#define IDR0_PRI			(1 << 16)
#define IDR0_SEV			(1 << 14)
#define IDR0_MSI			(1 << 13)
#define IDR0_ASID16			(1 << 12)
#define IDR0_ATS			(1 << 10)
#define IDR0_HYP			(1 << 9)
#define IDR0_COHACC			(1 << 4)
#define IDR0_TTF_SHIFT			2
#define IDR0_TTF_MASK			0x3
#define IDR0_TTF_AARCH64		(2 << IDR0_TTF_SHIFT)
#define IDR0_TTF_AARCH32_64		(3 << IDR0_TTF_SHIFT)
#define IDR0_S1P			(1 << 1)
#define IDR0_S2P			(1 << 0)

#define ARM_SMMU_IDR1			0x4
#define IDR1_TABLES_PRESET		(1 << 30)
#define IDR1_QUEUES_PRESET		(1 << 29)
#define IDR1_REL			(1 << 28)
#define IDR1_CMDQ_SHIFT			21
#define IDR1_CMDQ_MASK			0x1f
#define IDR1_EVTQ_SHIFT			16
#define IDR1_EVTQ_MASK			0x1f
#define IDR1_PRIQ_SHIFT			11
#define IDR1_PRIQ_MASK			0x1f
#define IDR1_SSID_SHIFT			6
#define IDR1_SSID_MASK			0x1f
#define IDR1_SID_SHIFT			0
#define IDR1_SID_MASK			0x3f

#define ARM_SMMU_IDR5			0x14
#define IDR5_STALL_MAX_SHIFT		16
#define IDR5_STALL_MAX_MASK		0xffff
#define IDR5_GRAN64K			(1 << 6)
#define IDR5_GRAN16K			(1 << 5)
#define IDR5_GRAN4K			(1 << 4)
#define IDR5_OAS_SHIFT			0
#define IDR5_OAS_MASK			0x7
#define IDR5_OAS_32_BIT			(0 << IDR5_OAS_SHIFT)
#define IDR5_OAS_36_BIT			(1 << IDR5_OAS_SHIFT)
#define IDR5_OAS_40_BIT			(2 << IDR5_OAS_SHIFT)
#define IDR5_OAS_42_BIT			(3 << IDR5_OAS_SHIFT)
#define IDR5_OAS_44_BIT			(4 << IDR5_OAS_SHIFT)
#define IDR5_OAS_48_BIT			(5 << IDR5_OAS_SHIFT)

#define ARM_SMMU_CR0			0x20
#define CR0_CMDQEN			(1 << 3)
#define CR0_EVTQEN			(1 << 2)
#define CR0_PRIQEN			(1 << 1)
#define CR0_SMMUEN			(1 << 0)

#define ARM_SMMU_CR0ACK			0x24

#define ARM_SMMU_CR1			0x28
#define CR1_SH_NSH			0
#define CR1_SH_OSH			2
#define CR1_SH_ISH			3
#define CR1_CACHE_NC			0
#define CR1_CACHE_WB			1
#define CR1_CACHE_WT			2
#define CR1_TABLE_SH_SHIFT		10
#define CR1_TABLE_OC_SHIFT		8
#define CR1_TABLE_IC_SHIFT		6
#define CR1_QUEUE_SH_SHIFT		4
#define CR1_QUEUE_OC_SHIFT		2
#define CR1_QUEUE_IC_SHIFT		0

#define ARM_SMMU_CR2			0x2c
#define CR2_PTM				(1 << 2)
#define CR2_RECINVSID			(1 << 1)
#define CR2_E2H				(1 << 0)

#define ARM_SMMU_GBPA			0x44
#define GBPA_ABORT			(1 << 20)
#define GBPA_UPDATE			(1 << 31)

#define ARM_SMMU_IRQ_CTRL		0x50
#define IRQ_CTRL_EVTQ_IRQEN		(1 << 2)
#define IRQ_CTRL_PRIQ_IRQEN		(1 << 1)
#define IRQ_CTRL_GERROR_IRQEN		(1 << 0)

#define ARM_SMMU_IRQ_CTRLACK		0x54

#define ARM_SMMU_GERROR			0x60
#define GERROR_SFM_ERR			(1 << 8)
#define GERROR_MSI_GERROR_ABT_ERR	(1 << 7)
#define GERROR_MSI_PRIQ_ABT_ERR		(1 << 6)
#define GERROR_MSI_EVTQ_ABT_ERR		(1 << 5)
#define GERROR_MSI_CMDQ_ABT_ERR		(1 << 4)
#define GERROR_PRIQ_ABT_ERR		(1 << 3)
#define GERROR_EVTQ_ABT_ERR		(1 << 2)
#define GERROR_CMDQ_ERR			(1 << 0)
#define GERROR_ERR_MASK			0xfd

#define ARM_SMMU_GERRORN		0x64

#define ARM_SMMU_GERROR_IRQ_CFG0	0x68
#define ARM_SMMU_GERROR_IRQ_CFG1	0x70
#define ARM_SMMU_GERROR_IRQ_CFG2	0x74

#define ARM_SMMU_STRTAB_BASE		0x80
#define STRTAB_BASE_RA			(1UL << 62)
#define STRTAB_BASE_ADDR_SHIFT		6
#define STRTAB_BASE_ADDR_MASK		0x3ffffffffffUL

#define ARM_SMMU_STRTAB_BASE_CFG	0x88
#define STRTAB_BASE_CFG_LOG2SIZE_SHIFT	0
#define STRTAB_BASE_CFG_LOG2SIZE_MASK	0x3f
#define STRTAB_BASE_CFG_SPLIT_SHIFT	6
#define STRTAB_BASE_CFG_SPLIT_MASK	0x1f
#define STRTAB_BASE_CFG_FMT_SHIFT	16
#define STRTAB_BASE_CFG_FMT_MASK	0x3
#define STRTAB_BASE_CFG_FMT_LINEAR	(0 << STRTAB_BASE_CFG_FMT_SHIFT)
#define STRTAB_BASE_CFG_FMT_2LVL	(1 << STRTAB_BASE_CFG_FMT_SHIFT)

#define ARM_SMMU_CMDQ_BASE		0x90
#define ARM_SMMU_CMDQ_PROD		0x98
#define ARM_SMMU_CMDQ_CONS		0x9c

#define ARM_SMMU_EVTQ_BASE		0xa0
#define ARM_SMMU_EVTQ_PROD		0x100a8
#define ARM_SMMU_EVTQ_CONS		0x100ac
#define ARM_SMMU_EVTQ_IRQ_CFG0		0xb0
#define ARM_SMMU_EVTQ_IRQ_CFG1		0xb8
#define ARM_SMMU_EVTQ_IRQ_CFG2		0xbc

#define ARM_SMMU_PRIQ_BASE		0xc0
#define ARM_SMMU_PRIQ_PROD		0x100c8
#define ARM_SMMU_PRIQ_CONS		0x100cc
#define ARM_SMMU_PRIQ_IRQ_CFG0		0xd0
#define ARM_SMMU_PRIQ_IRQ_CFG1		0xd8
#define ARM_SMMU_PRIQ_IRQ_CFG2		0xdc

/* Common MSI config fields */
#define MSI_CFG0_ADDR_SHIFT		2
#define MSI_CFG0_ADDR_MASK		0x3fffffffffffUL
#define MSI_CFG2_SH_SHIFT		4
#define MSI_CFG2_SH_NSH			(0UL << MSI_CFG2_SH_SHIFT)
#define MSI_CFG2_SH_OSH			(2UL << MSI_CFG2_SH_SHIFT)
#define MSI_CFG2_SH_ISH			(3UL << MSI_CFG2_SH_SHIFT)
#define MSI_CFG2_MEMATTR_SHIFT		0
#define MSI_CFG2_MEMATTR_DEVICE_nGnRE	(0x1 << MSI_CFG2_MEMATTR_SHIFT)

#define Q_IDX(q, p)			((p) & ((1 << (q)->max_n_shift) - 1))
#define Q_WRP(q, p)			((p) & (1 << (q)->max_n_shift))
#define Q_OVERFLOW_FLAG			(1 << 31)
#define Q_OVF(q, p)			((p) & Q_OVERFLOW_FLAG)
#define Q_ENT(q, p)			((q)->base +			\
					 Q_IDX(q, p) * (q)->ent_dwords)

#define Q_BASE_RWA			(1UL << 62)
#define Q_BASE_ADDR_SHIFT		5
#define Q_BASE_ADDR_MASK		0xfffffffffffUL
#define Q_BASE_LOG2SIZE_SHIFT		0
#define Q_BASE_LOG2SIZE_MASK		0x1fUL

/*
 * Stream table.
 *
 * Linear: Enough to cover 1 << IDR1.SIDSIZE entries
 * 2lvl: 128k L1 entries,
 *       256 lazy entries per table (each table covers a PCI bus)
 */
#define STRTAB_L1_SZ_SHIFT		20
#define STRTAB_SPLIT			8

#define STRTAB_L1_DESC_DWORDS		1
#define STRTAB_L1_DESC_SPAN_SHIFT	0
#define STRTAB_L1_DESC_SPAN_MASK	0x1fUL
#define STRTAB_L1_DESC_L2PTR_SHIFT	6
#define STRTAB_L1_DESC_L2PTR_MASK	0x3ffffffffffUL

#define STRTAB_STE_DWORDS		8
#define STRTAB_STE_0_V			(1UL << 0)
#define STRTAB_STE_0_CFG_SHIFT		1
#define STRTAB_STE_0_CFG_MASK		0x7UL
#define STRTAB_STE_0_CFG_ABORT		(0UL << STRTAB_STE_0_CFG_SHIFT)
#define STRTAB_STE_0_CFG_BYPASS		(4UL << STRTAB_STE_0_CFG_SHIFT)
#define STRTAB_STE_0_CFG_S1_TRANS	(5UL << STRTAB_STE_0_CFG_SHIFT)
#define STRTAB_STE_0_CFG_S2_TRANS	(6UL << STRTAB_STE_0_CFG_SHIFT)

#define STRTAB_STE_0_S1FMT_SHIFT	4
#define STRTAB_STE_0_S1FMT_LINEAR	(0UL << STRTAB_STE_0_S1FMT_SHIFT)
#define STRTAB_STE_0_S1CTXPTR_SHIFT	6
#define STRTAB_STE_0_S1CTXPTR_MASK	0x3ffffffffffUL
#define STRTAB_STE_0_S1CDMAX_SHIFT	59
#define STRTAB_STE_0_S1CDMAX_MASK	0x1fUL

#define STRTAB_STE_1_S1C_CACHE_NC	0UL
#define STRTAB_STE_1_S1C_CACHE_WBRA	1UL
#define STRTAB_STE_1_S1C_CACHE_WT	2UL
#define STRTAB_STE_1_S1C_CACHE_WB	3UL
#define STRTAB_STE_1_S1C_SH_NSH		0UL
#define STRTAB_STE_1_S1C_SH_OSH		2UL
#define STRTAB_STE_1_S1C_SH_ISH		3UL
#define STRTAB_STE_1_S1CIR_SHIFT	2
#define STRTAB_STE_1_S1COR_SHIFT	4
#define STRTAB_STE_1_S1CSH_SHIFT	6

#define STRTAB_STE_1_S1STALLD		(1UL << 27)

#define STRTAB_STE_1_EATS_ABT		0UL
#define STRTAB_STE_1_EATS_TRANS		1UL
#define STRTAB_STE_1_EATS_S1CHK		2UL
#define STRTAB_STE_1_EATS_SHIFT		28

#define STRTAB_STE_1_STRW_NSEL1		0UL
#define STRTAB_STE_1_STRW_EL2		2UL
#define STRTAB_STE_1_STRW_SHIFT		30

#define STRTAB_STE_1_SHCFG_INCOMING	1UL
#define STRTAB_STE_1_SHCFG_SHIFT	44

#define STRTAB_STE_2_S2VMID_SHIFT	0
#define STRTAB_STE_2_S2VMID_MASK	0xffffUL
#define STRTAB_STE_2_VTCR_SHIFT		32
#define STRTAB_STE_2_VTCR_MASK		0x7ffffUL
#define STRTAB_STE_2_S2AA64		(1UL << 51)
#define STRTAB_STE_2_S2ENDI		(1UL << 52)
#define STRTAB_STE_2_S2PTW		(1UL << 54)
#define STRTAB_STE_2_S2R		(1UL << 58)

#define STRTAB_STE_3_S2TTB_SHIFT	4
#define STRTAB_STE_3_S2TTB_MASK		0xfffffffffffUL

/* Context descriptor (stage-1 only) */
#define CTXDESC_CD_DWORDS		8
#define CTXDESC_CD_0_TCR_T0SZ_SHIFT	0
#define ARM64_TCR_T0SZ_SHIFT		0
#define ARM64_TCR_T0SZ_MASK		0x1fUL
#define CTXDESC_CD_0_TCR_TG0_SHIFT	6
#define ARM64_TCR_TG0_SHIFT		14
#define ARM64_TCR_TG0_MASK		0x3UL
#define CTXDESC_CD_0_TCR_IRGN0_SHIFT	8
#define ARM64_TCR_IRGN0_SHIFT		8
#define ARM64_TCR_IRGN0_MASK		0x3UL
#define CTXDESC_CD_0_TCR_ORGN0_SHIFT	10
#define ARM64_TCR_ORGN0_SHIFT		10
#define ARM64_TCR_ORGN0_MASK		0x3UL
#define CTXDESC_CD_0_TCR_SH0_SHIFT	12
#define ARM64_TCR_SH0_SHIFT		12
#define ARM64_TCR_SH0_MASK		0x3UL
#define CTXDESC_CD_0_TCR_EPD0_SHIFT	14
#define ARM64_TCR_EPD0_SHIFT		7
#define ARM64_TCR_EPD0_MASK		0x1UL
#define CTXDESC_CD_0_TCR_EPD1_SHIFT	30
#define ARM64_TCR_EPD1_SHIFT		23
#define ARM64_TCR_EPD1_MASK		0x1UL

#define CTXDESC_CD_0_ENDI		(1UL << 15)
#define CTXDESC_CD_0_V			(1UL << 31)

#define CTXDESC_CD_0_TCR_IPS_SHIFT	32
#define ARM64_TCR_IPS_SHIFT		32
#define ARM64_TCR_IPS_MASK		0x7UL
#define CTXDESC_CD_0_TCR_TBI0_SHIFT	38
#define ARM64_TCR_TBI0_SHIFT		37
#define ARM64_TCR_TBI0_MASK		0x1UL

#define CTXDESC_CD_0_AA64		(1UL << 41)
#define CTXDESC_CD_0_R			(1UL << 45)
#define CTXDESC_CD_0_A			(1UL << 46)
#define CTXDESC_CD_0_ASET_SHIFT		47
#define CTXDESC_CD_0_ASET_SHARED	(0UL << CTXDESC_CD_0_ASET_SHIFT)
#define CTXDESC_CD_0_ASET_PRIVATE	(1UL << CTXDESC_CD_0_ASET_SHIFT)
#define CTXDESC_CD_0_ASID_SHIFT		48
#define CTXDESC_CD_0_ASID_MASK		0xffffUL

#define CTXDESC_CD_1_TTB0_SHIFT		4
#define CTXDESC_CD_1_TTB0_MASK		0xfffffffffffUL

#define CTXDESC_CD_3_MAIR_SHIFT		0

/* Convert between AArch64 (CPU) TCR format and SMMU CD format */
#define ARM_SMMU_TCR2CD(tcr, fld)					\
	(((tcr) >> ARM64_TCR_##fld##_SHIFT & ARM64_TCR_##fld##_MASK)	\
	 << CTXDESC_CD_0_TCR_##fld##_SHIFT)

/* Command queue */
#define CMDQ_ENT_DWORDS			2
#define CMDQ_MAX_SZ_SHIFT		8

#define CMDQ_ERR_SHIFT			24
#define CMDQ_ERR_MASK			0x7f
#define CMDQ_ERR_CERROR_NONE_IDX	0
#define CMDQ_ERR_CERROR_ILL_IDX		1
#define CMDQ_ERR_CERROR_ABT_IDX		2

#define CMDQ_0_OP_SHIFT			0
#define CMDQ_0_OP_MASK			0xffUL
#define CMDQ_0_SSV			(1UL << 11)

#define CMDQ_PREFETCH_0_SID_SHIFT	32
#define CMDQ_PREFETCH_1_SIZE_SHIFT	0
#define CMDQ_PREFETCH_1_ADDR_MASK	~0xfffUL

#define CMDQ_CFGI_0_SID_SHIFT		32
#define CMDQ_CFGI_0_SID_MASK		0xffffffffUL
#define CMDQ_CFGI_1_LEAF		(1UL << 0)
#define CMDQ_CFGI_1_RANGE_SHIFT		0
#define CMDQ_CFGI_1_RANGE_MASK		0x1fUL

#define CMDQ_TLBI_0_VMID_SHIFT		32
#define CMDQ_TLBI_0_ASID_SHIFT		48
#define CMDQ_TLBI_1_LEAF		(1UL << 0)
#define CMDQ_TLBI_1_VA_MASK		~0xfffUL
#define CMDQ_TLBI_1_IPA_MASK		0xfffffffff000UL

#define CMDQ_PRI_0_SSID_SHIFT		12
#define CMDQ_PRI_0_SSID_MASK		0xfffffUL
#define CMDQ_PRI_0_SID_SHIFT		32
#define CMDQ_PRI_0_SID_MASK		0xffffffffUL
#define CMDQ_PRI_1_GRPID_SHIFT		0
#define CMDQ_PRI_1_GRPID_MASK		0x1ffUL
#define CMDQ_PRI_1_RESP_SHIFT		12
#define CMDQ_PRI_1_RESP_DENY		(0UL << CMDQ_PRI_1_RESP_SHIFT)
#define CMDQ_PRI_1_RESP_FAIL		(1UL << CMDQ_PRI_1_RESP_SHIFT)
#define CMDQ_PRI_1_RESP_SUCC		(2UL << CMDQ_PRI_1_RESP_SHIFT)

#define CMDQ_SYNC_0_CS_SHIFT		12
#define CMDQ_SYNC_0_CS_NONE		(0UL << CMDQ_SYNC_0_CS_SHIFT)
#define CMDQ_SYNC_0_CS_SEV		(2UL << CMDQ_SYNC_0_CS_SHIFT)

/* Event queue */
#define EVTQ_ENT_DWORDS			4
#define EVTQ_MAX_SZ_SHIFT		7

#define EVTQ_0_ID_SHIFT			0
#define EVTQ_0_ID_MASK			0xffUL

/* PRI queue */
#define PRIQ_ENT_DWORDS			2
#define PRIQ_MAX_SZ_SHIFT		8

#define PRIQ_0_SID_SHIFT		0
#define PRIQ_0_SID_MASK			0xffffffffUL
#define PRIQ_0_SSID_SHIFT		32
#define PRIQ_0_SSID_MASK		0xfffffUL
#define PRIQ_0_PERM_PRIV		(1UL << 58)
#define PRIQ_0_PERM_EXEC		(1UL << 59)
#define PRIQ_0_PERM_READ		(1UL << 60)
#define PRIQ_0_PERM_WRITE		(1UL << 61)
#define PRIQ_0_PRG_LAST			(1UL << 62)
#define PRIQ_0_SSID_V			(1UL << 63)

#define PRIQ_1_PRG_IDX_SHIFT		0
#define PRIQ_1_PRG_IDX_MASK		0x1ffUL
#define PRIQ_1_ADDR_SHIFT		12
#define PRIQ_1_ADDR_MASK		0xfffffffffffffUL

/* High-level queue structures */
#define ARM_SMMU_POLL_TIMEOUT_US	100
#define ARM_SMMU_CMDQ_DRAIN_TIMEOUT_US	1000000 /* 1s! */

#define MSI_IOVA_BASE			0x8000000
#define MSI_IOVA_LENGTH			0x100000

/* Until ACPICA headers cover IORT rev. C */
#ifndef ACPI_IORT_SMMU_HISILICON_HI161X
#define ACPI_IORT_SMMU_HISILICON_HI161X		0x1
#endif

#ifndef ACPI_IORT_SMMU_V3_CAVIUM_CN99XX
#define ACPI_IORT_SMMU_V3_CAVIUM_CN99XX		0x2
#endif

static bool disable_bypass;
module_param_named(disable_bypass, disable_bypass, bool, S_IRUGO);
MODULE_PARM_DESC(disable_bypass,
	"Disable bypass streams such that incoming transactions from devices that are not attached to an iommu domain will report an abort back to the device and will not be allowed to pass through the SMMU.");

enum pri_resp {
	PRI_RESP_DENY,
	PRI_RESP_FAIL,
	PRI_RESP_SUCC,
};

enum arm_smmu_msi_index {
	EVTQ_MSI_INDEX,
	GERROR_MSI_INDEX,
	PRIQ_MSI_INDEX,
	ARM_SMMU_MAX_MSIS,
};

static phys_addr_t arm_smmu_msi_cfg[ARM_SMMU_MAX_MSIS][3] = {
	[EVTQ_MSI_INDEX] = {
		ARM_SMMU_EVTQ_IRQ_CFG0,
		ARM_SMMU_EVTQ_IRQ_CFG1,
		ARM_SMMU_EVTQ_IRQ_CFG2,
	},
	[GERROR_MSI_INDEX] = {
		ARM_SMMU_GERROR_IRQ_CFG0,
		ARM_SMMU_GERROR_IRQ_CFG1,
		ARM_SMMU_GERROR_IRQ_CFG2,
	},
	[PRIQ_MSI_INDEX] = {
		ARM_SMMU_PRIQ_IRQ_CFG0,
		ARM_SMMU_PRIQ_IRQ_CFG1,
		ARM_SMMU_PRIQ_IRQ_CFG2,
	},
};

struct arm_smmu_cmdq_ent {
	/* Common fields */
	u8				opcode;
	bool				substream_valid;

	/* Command-specific fields */
	union {
		#define CMDQ_OP_PREFETCH_CFG	0x1
		struct {
			u32			sid;
			u8			size;
			u64			addr;
		} prefetch;

		#define CMDQ_OP_CFGI_STE	0x3
		#define CMDQ_OP_CFGI_ALL	0x4
		struct {
			u32			sid;
			union {
				bool		leaf;
				u8		span;
			};
		} cfgi;

		#define CMDQ_OP_TLBI_NH_ASID	0x11
		#define CMDQ_OP_TLBI_NH_VA	0x12
		#define CMDQ_OP_TLBI_EL2_ALL	0x20
		#define CMDQ_OP_TLBI_S12_VMALL	0x28
		#define CMDQ_OP_TLBI_S2_IPA	0x2a
		#define CMDQ_OP_TLBI_NSNH_ALL	0x30
		struct {
			u16			asid;
			u16			vmid;
			bool			leaf;
			u64			addr;
		} tlbi;

		#define CMDQ_OP_PRI_RESP	0x41
		struct {
			u32			sid;
			u32			ssid;
			u16			grpid;
			enum pri_resp		resp;
		} pri;

		#define CMDQ_OP_CMD_SYNC	0x46
	};
};

struct arm_smmu_queue {
	int				irq; /* Wired interrupt */

	__le64				*base;
	dma_addr_t			base_dma;
	u64				q_base;

	size_t				ent_dwords;
	u32				max_n_shift;
	u32				prod;
	u32				cons;

	u32 __iomem			*prod_reg;
	u32 __iomem			*cons_reg;
};

struct arm_smmu_cmdq {
	struct arm_smmu_queue		q;
	spinlock_t			lock;
};

struct arm_smmu_evtq {
	struct arm_smmu_queue		q;
	u32				max_stalls;
};

struct arm_smmu_priq {
	struct arm_smmu_queue		q;
};

/* High-level stream table and context descriptor structures */
struct arm_smmu_strtab_l1_desc {
	u8				span;

	__le64				*l2ptr;
	dma_addr_t			l2ptr_dma;
};

struct arm_smmu_s1_cfg {
	__le64				*cdptr;
	dma_addr_t			cdptr_dma;

	struct arm_smmu_ctx_desc {
		u16	asid;
		u64	ttbr;
		u64	tcr;
		u64	mair;
	}				cd;
};

struct arm_smmu_s2_cfg {
	u16				vmid;
	u64				vttbr;
	u64				vtcr;
};

struct arm_smmu_strtab_ent {
	/*
	 * An STE is "assigned" if the master emitting the corresponding SID
	 * is attached to a domain. The behaviour of an unassigned STE is
	 * determined by the disable_bypass parameter, whereas an assigned
	 * STE behaves according to s1_cfg/s2_cfg, which themselves are
	 * configured according to the domain type.
	 */
	bool				assigned;
	struct arm_smmu_s1_cfg		*s1_cfg;
	struct arm_smmu_s2_cfg		*s2_cfg;
};

struct arm_smmu_strtab_cfg {
	__le64				*strtab;
	dma_addr_t			strtab_dma;
	struct arm_smmu_strtab_l1_desc	*l1_desc;
	unsigned int			num_l1_ents;

	u64				strtab_base;
	u32				strtab_base_cfg;
};

/* An SMMUv3 instance */
struct arm_smmu_device {
	struct device			*dev;
	void __iomem			*base;

#define ARM_SMMU_FEAT_2_LVL_STRTAB	(1 << 0)
#define ARM_SMMU_FEAT_2_LVL_CDTAB	(1 << 1)
#define ARM_SMMU_FEAT_TT_LE		(1 << 2)
#define ARM_SMMU_FEAT_TT_BE		(1 << 3)
#define ARM_SMMU_FEAT_PRI		(1 << 4)
#define ARM_SMMU_FEAT_ATS		(1 << 5)
#define ARM_SMMU_FEAT_SEV		(1 << 6)
#define ARM_SMMU_FEAT_MSI		(1 << 7)
#define ARM_SMMU_FEAT_COHERENCY		(1 << 8)
#define ARM_SMMU_FEAT_TRANS_S1		(1 << 9)
#define ARM_SMMU_FEAT_TRANS_S2		(1 << 10)
#define ARM_SMMU_FEAT_STALLS		(1 << 11)
#define ARM_SMMU_FEAT_HYP		(1 << 12)
	u32				features;

#define ARM_SMMU_OPT_SKIP_PREFETCH	(1 << 0)
#define ARM_SMMU_OPT_PAGE0_REGS_ONLY	(1 << 1)
	u32				options;

	struct arm_smmu_cmdq		cmdq;
	struct arm_smmu_evtq		evtq;
	struct arm_smmu_priq		priq;

	int				gerr_irq;
	int				combined_irq;

	unsigned long			ias; /* IPA */
	unsigned long			oas; /* PA */
	unsigned long			pgsize_bitmap;

#define ARM_SMMU_MAX_ASIDS		(1 << 16)
	unsigned int			asid_bits;
	DECLARE_BITMAP(asid_map, ARM_SMMU_MAX_ASIDS);

#define ARM_SMMU_MAX_VMIDS		(1 << 16)
	unsigned int			vmid_bits;
	DECLARE_BITMAP(vmid_map, ARM_SMMU_MAX_VMIDS);

	unsigned int			ssid_bits;
	unsigned int			sid_bits;

	struct arm_smmu_strtab_cfg	strtab_cfg;

	/* IOMMU core code handle */
	struct iommu_device		iommu;
};

/* SMMU private data for each master */
struct arm_smmu_master_data {
	struct arm_smmu_device		*smmu;
	struct arm_smmu_strtab_ent	ste;
};

/* SMMU private data for an IOMMU domain */
enum arm_smmu_domain_stage {
	ARM_SMMU_DOMAIN_S1 = 0,
	ARM_SMMU_DOMAIN_S2,
	ARM_SMMU_DOMAIN_NESTED,
	ARM_SMMU_DOMAIN_BYPASS,
};

struct arm_smmu_domain {
	struct arm_smmu_device		*smmu;
	struct mutex			init_mutex; /* Protects smmu pointer */

	struct io_pgtable_ops		*pgtbl_ops;

	enum arm_smmu_domain_stage	stage;
	union {
		struct arm_smmu_s1_cfg	s1_cfg;
		struct arm_smmu_s2_cfg	s2_cfg;
	};

	struct iommu_domain		domain;
};

struct arm_smmu_option_prop {
	u32 opt;
	const char *prop;
};

static struct arm_smmu_option_prop arm_smmu_options[] = {
	{ ARM_SMMU_OPT_SKIP_PREFETCH, "hisilicon,broken-prefetch-cmd" },
	{ ARM_SMMU_OPT_PAGE0_REGS_ONLY, "cavium,cn9900-broken-page1-regspace"},
	{ 0, NULL},
};

static inline void __iomem *arm_smmu_page1_fixup(unsigned long offset,
						 struct arm_smmu_device *smmu)
{
	if ((offset > SZ_64K) &&
	    (smmu->options & ARM_SMMU_OPT_PAGE0_REGS_ONLY))
		offset -= SZ_64K;

	return smmu->base + offset;
}

static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
{
	return container_of(dom, struct arm_smmu_domain, domain);
}

static void parse_driver_options(struct arm_smmu_device *smmu)
{
	int i = 0;

	do {
		if (of_property_read_bool(smmu->dev->of_node,
						arm_smmu_options[i].prop)) {
			smmu->options |= arm_smmu_options[i].opt;
			dev_notice(smmu->dev, "option %s\n",
				arm_smmu_options[i].prop);
		}
	} while (arm_smmu_options[++i].opt);
}

/* Low-level queue manipulation functions */
static bool queue_full(struct arm_smmu_queue *q)
{
	return Q_IDX(q, q->prod) == Q_IDX(q, q->cons) &&
	       Q_WRP(q, q->prod) != Q_WRP(q, q->cons);
}

static bool queue_empty(struct arm_smmu_queue *q)
{
	return Q_IDX(q, q->prod) == Q_IDX(q, q->cons) &&
	       Q_WRP(q, q->prod) == Q_WRP(q, q->cons);
}

static void queue_sync_cons(struct arm_smmu_queue *q)
{
	q->cons = readl_relaxed(q->cons_reg);
}

static void queue_inc_cons(struct arm_smmu_queue *q)
{
	u32 cons = (Q_WRP(q, q->cons) | Q_IDX(q, q->cons)) + 1;

	q->cons = Q_OVF(q, q->cons) | Q_WRP(q, cons) | Q_IDX(q, cons);
	writel(q->cons, q->cons_reg);
}

static int queue_sync_prod(struct arm_smmu_queue *q)
{
	int ret = 0;
	u32 prod = readl_relaxed(q->prod_reg);

	if (Q_OVF(q, prod) != Q_OVF(q, q->prod))
		ret = -EOVERFLOW;

	q->prod = prod;
	return ret;
}

static void queue_inc_prod(struct arm_smmu_queue *q)
{
	u32 prod = (Q_WRP(q, q->prod) | Q_IDX(q, q->prod)) + 1;

	q->prod = Q_OVF(q, q->prod) | Q_WRP(q, prod) | Q_IDX(q, prod);
	writel(q->prod, q->prod_reg);
}

/*
 * Wait for the SMMU to consume items. If drain is true, wait until the queue
 * is empty. Otherwise, wait until there is at least one free slot.
 */
static int queue_poll_cons(struct arm_smmu_queue *q, bool drain, bool wfe)
{
	ktime_t timeout;
	unsigned int delay = 1;

	/* Wait longer if it's queue drain */
	timeout = ktime_add_us(ktime_get(), drain ?
					    ARM_SMMU_CMDQ_DRAIN_TIMEOUT_US :
					    ARM_SMMU_POLL_TIMEOUT_US);

	while (queue_sync_cons(q), (drain ? !queue_empty(q) : queue_full(q))) {
		if (ktime_compare(ktime_get(), timeout) > 0)
			return -ETIMEDOUT;

		if (wfe) {
			wfe();
		} else {
			cpu_relax();
			udelay(delay);
			delay *= 2;
		}
	}

	return 0;
}

static void queue_write(__le64 *dst, u64 *src, size_t n_dwords)
{
	int i;

	for (i = 0; i < n_dwords; ++i)
		*dst++ = cpu_to_le64(*src++);
}

static int queue_insert_raw(struct arm_smmu_queue *q, u64 *ent)
{
	if (queue_full(q))
		return -ENOSPC;

	queue_write(Q_ENT(q, q->prod), ent, q->ent_dwords);
	queue_inc_prod(q);
	return 0;
}

static void queue_read(__le64 *dst, u64 *src, size_t n_dwords)
{
	int i;

	for (i = 0; i < n_dwords; ++i)
		*dst++ = le64_to_cpu(*src++);
}

static int queue_remove_raw(struct arm_smmu_queue *q, u64 *ent)
{
	if (queue_empty(q))
		return -EAGAIN;

	queue_read(ent, Q_ENT(q, q->cons), q->ent_dwords);
	queue_inc_cons(q);
	return 0;
}

/* High-level queue accessors */
static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
{
	memset(cmd, 0, CMDQ_ENT_DWORDS << 3);
	cmd[0] |= (ent->opcode & CMDQ_0_OP_MASK) << CMDQ_0_OP_SHIFT;

	switch (ent->opcode) {
	case CMDQ_OP_TLBI_EL2_ALL:
	case CMDQ_OP_TLBI_NSNH_ALL:
		break;
	case CMDQ_OP_PREFETCH_CFG:
		cmd[0] |= (u64)ent->prefetch.sid << CMDQ_PREFETCH_0_SID_SHIFT;
		cmd[1] |= ent->prefetch.size << CMDQ_PREFETCH_1_SIZE_SHIFT;
		cmd[1] |= ent->prefetch.addr & CMDQ_PREFETCH_1_ADDR_MASK;
		break;
	case CMDQ_OP_CFGI_STE:
		cmd[0] |= (u64)ent->cfgi.sid << CMDQ_CFGI_0_SID_SHIFT;
		cmd[1] |= ent->cfgi.leaf ? CMDQ_CFGI_1_LEAF : 0;
		break;
	case CMDQ_OP_CFGI_ALL:
		/* Cover the entire SID range */
		cmd[1] |= CMDQ_CFGI_1_RANGE_MASK << CMDQ_CFGI_1_RANGE_SHIFT;
		break;
	case CMDQ_OP_TLBI_NH_VA:
		cmd[0] |= (u64)ent->tlbi.asid << CMDQ_TLBI_0_ASID_SHIFT;
		cmd[1] |= ent->tlbi.leaf ? CMDQ_TLBI_1_LEAF : 0;
		cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_VA_MASK;
		break;
	case CMDQ_OP_TLBI_S2_IPA:
		cmd[0] |= (u64)ent->tlbi.vmid << CMDQ_TLBI_0_VMID_SHIFT;
		cmd[1] |= ent->tlbi.leaf ? CMDQ_TLBI_1_LEAF : 0;
		cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_IPA_MASK;
		break;
	case CMDQ_OP_TLBI_NH_ASID:
		cmd[0] |= (u64)ent->tlbi.asid << CMDQ_TLBI_0_ASID_SHIFT;
		/* Fallthrough */
	case CMDQ_OP_TLBI_S12_VMALL:
		cmd[0] |= (u64)ent->tlbi.vmid << CMDQ_TLBI_0_VMID_SHIFT;
		break;
	case CMDQ_OP_PRI_RESP:
		cmd[0] |= ent->substream_valid ? CMDQ_0_SSV : 0;
		cmd[0] |= ent->pri.ssid << CMDQ_PRI_0_SSID_SHIFT;
		cmd[0] |= (u64)ent->pri.sid << CMDQ_PRI_0_SID_SHIFT;
		cmd[1] |= ent->pri.grpid << CMDQ_PRI_1_GRPID_SHIFT;
		switch (ent->pri.resp) {
		case PRI_RESP_DENY:
			cmd[1] |= CMDQ_PRI_1_RESP_DENY;
			break;
		case PRI_RESP_FAIL:
			cmd[1] |= CMDQ_PRI_1_RESP_FAIL;
			break;
		case PRI_RESP_SUCC:
			cmd[1] |= CMDQ_PRI_1_RESP_SUCC;
			break;
		default:
			return -EINVAL;
		}
		break;
	case CMDQ_OP_CMD_SYNC:
		cmd[0] |= CMDQ_SYNC_0_CS_SEV;
		break;
	default:
		return -ENOENT;
	}

	return 0;
}

static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu)
{
	static const char *cerror_str[] = {
		[CMDQ_ERR_CERROR_NONE_IDX]	= "No error",
		[CMDQ_ERR_CERROR_ILL_IDX]	= "Illegal command",
		[CMDQ_ERR_CERROR_ABT_IDX]	= "Abort on command fetch",
	};

	int i;
	u64 cmd[CMDQ_ENT_DWORDS];
	struct arm_smmu_queue *q = &smmu->cmdq.q;
	u32 cons = readl_relaxed(q->cons_reg);
	u32 idx = cons >> CMDQ_ERR_SHIFT & CMDQ_ERR_MASK;
	struct arm_smmu_cmdq_ent cmd_sync = {
		.opcode = CMDQ_OP_CMD_SYNC,
	};

	dev_err(smmu->dev, "CMDQ error (cons 0x%08x): %s\n", cons,
		idx < ARRAY_SIZE(cerror_str) ?  cerror_str[idx] : "Unknown");

	switch (idx) {
	case CMDQ_ERR_CERROR_ABT_IDX:
		dev_err(smmu->dev, "retrying command fetch\n");
	case CMDQ_ERR_CERROR_NONE_IDX:
		return;
	case CMDQ_ERR_CERROR_ILL_IDX:
		/* Fallthrough */
	default:
		break;
	}

	/*
	 * We may have concurrent producers, so we need to be careful
	 * not to touch any of the shadow cmdq state.
	 */
	queue_read(cmd, Q_ENT(q, cons), q->ent_dwords);
	dev_err(smmu->dev, "skipping command in error state:\n");
	for (i = 0; i < ARRAY_SIZE(cmd); ++i)
		dev_err(smmu->dev, "\t0x%016llx\n", (unsigned long long)cmd[i]);

	/* Convert the erroneous command into a CMD_SYNC */
	if (arm_smmu_cmdq_build_cmd(cmd, &cmd_sync)) {
		dev_err(smmu->dev, "failed to convert to CMD_SYNC\n");
		return;
	}

	queue_write(Q_ENT(q, cons), cmd, q->ent_dwords);
}

static void arm_smmu_cmdq_issue_cmd(struct arm_smmu_device *smmu,
				    struct arm_smmu_cmdq_ent *ent)
{
	u64 cmd[CMDQ_ENT_DWORDS];
	unsigned long flags;
	bool wfe = !!(smmu->features & ARM_SMMU_FEAT_SEV);
	struct arm_smmu_queue *q = &smmu->cmdq.q;

	if (arm_smmu_cmdq_build_cmd(cmd, ent)) {
		dev_warn(smmu->dev, "ignoring unknown CMDQ opcode 0x%x\n",
			 ent->opcode);
		return;
	}

	spin_lock_irqsave(&smmu->cmdq.lock, flags);
	while (queue_insert_raw(q, cmd) == -ENOSPC) {
		if (queue_poll_cons(q, false, wfe))
			dev_err_ratelimited(smmu->dev, "CMDQ timeout\n");
	}

	if (ent->opcode == CMDQ_OP_CMD_SYNC && queue_poll_cons(q, true, wfe))
		dev_err_ratelimited(smmu->dev, "CMD_SYNC timeout\n");
	spin_unlock_irqrestore(&smmu->cmdq.lock, flags);
}

/* Context descriptor manipulation functions */
static u64 arm_smmu_cpu_tcr_to_cd(u64 tcr)
{
	u64 val = 0;

	/* Repack the TCR. Just care about TTBR0 for now */
	val |= ARM_SMMU_TCR2CD(tcr, T0SZ);
	val |= ARM_SMMU_TCR2CD(tcr, TG0);
	val |= ARM_SMMU_TCR2CD(tcr, IRGN0);
	val |= ARM_SMMU_TCR2CD(tcr, ORGN0);
	val |= ARM_SMMU_TCR2CD(tcr, SH0);
	val |= ARM_SMMU_TCR2CD(tcr, EPD0);
	val |= ARM_SMMU_TCR2CD(tcr, EPD1);
	val |= ARM_SMMU_TCR2CD(tcr, IPS);
	val |= ARM_SMMU_TCR2CD(tcr, TBI0);

	return val;
}

static void arm_smmu_write_ctx_desc(struct arm_smmu_device *smmu,
				    struct arm_smmu_s1_cfg *cfg)
{
	u64 val;

	/*
	 * We don't need to issue any invalidation here, as we'll invalidate
	 * the STE when installing the new entry anyway.
	 */
	val = arm_smmu_cpu_tcr_to_cd(cfg->cd.tcr) |
#ifdef __BIG_ENDIAN
	      CTXDESC_CD_0_ENDI |
#endif
	      CTXDESC_CD_0_R | CTXDESC_CD_0_A | CTXDESC_CD_0_ASET_PRIVATE |
	      CTXDESC_CD_0_AA64 | (u64)cfg->cd.asid << CTXDESC_CD_0_ASID_SHIFT |
	      CTXDESC_CD_0_V;
	cfg->cdptr[0] = cpu_to_le64(val);

	val = cfg->cd.ttbr & CTXDESC_CD_1_TTB0_MASK << CTXDESC_CD_1_TTB0_SHIFT;
	cfg->cdptr[1] = cpu_to_le64(val);

	cfg->cdptr[3] = cpu_to_le64(cfg->cd.mair << CTXDESC_CD_3_MAIR_SHIFT);
}

/* Stream table manipulation functions */
static void
arm_smmu_write_strtab_l1_desc(__le64 *dst, struct arm_smmu_strtab_l1_desc *desc)
{
	u64 val = 0;

	val |= (desc->span & STRTAB_L1_DESC_SPAN_MASK)
		<< STRTAB_L1_DESC_SPAN_SHIFT;
	val |= desc->l2ptr_dma &
	       STRTAB_L1_DESC_L2PTR_MASK << STRTAB_L1_DESC_L2PTR_SHIFT;

	*dst = cpu_to_le64(val);
}

static void arm_smmu_sync_ste_for_sid(struct arm_smmu_device *smmu, u32 sid)
{
	struct arm_smmu_cmdq_ent cmd = {
		.opcode	= CMDQ_OP_CFGI_STE,
		.cfgi	= {
			.sid	= sid,
			.leaf	= true,
		},
	};

	arm_smmu_cmdq_issue_cmd(smmu, &cmd);
	cmd.opcode = CMDQ_OP_CMD_SYNC;
	arm_smmu_cmdq_issue_cmd(smmu, &cmd);
}

static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
				      __le64 *dst, struct arm_smmu_strtab_ent *ste)
{
	/*
	 * This is hideously complicated, but we only really care about
	 * three cases at the moment:
	 *
	 * 1. Invalid (all zero) -> bypass/fault (init)
	 * 2. Bypass/fault -> translation/bypass (attach)
	 * 3. Translation/bypass -> bypass/fault (detach)
	 *
	 * Given that we can't update the STE atomically and the SMMU
	 * doesn't read the thing in a defined order, that leaves us
	 * with the following maintenance requirements:
	 *
	 * 1. Update Config, return (init time STEs aren't live)
	 * 2. Write everything apart from dword 0, sync, write dword 0, sync
	 * 3. Update Config, sync
	 */
	u64 val = le64_to_cpu(dst[0]);
	bool ste_live = false;
	struct arm_smmu_cmdq_ent prefetch_cmd = {
		.opcode		= CMDQ_OP_PREFETCH_CFG,
		.prefetch	= {
			.sid	= sid,
		},
	};

	if (val & STRTAB_STE_0_V) {
		u64 cfg;

		cfg = val & STRTAB_STE_0_CFG_MASK << STRTAB_STE_0_CFG_SHIFT;
		switch (cfg) {
		case STRTAB_STE_0_CFG_BYPASS:
			break;
		case STRTAB_STE_0_CFG_S1_TRANS:
		case STRTAB_STE_0_CFG_S2_TRANS:
			ste_live = true;
			break;
		case STRTAB_STE_0_CFG_ABORT:
			if (disable_bypass)
				break;
		default:
			BUG(); /* STE corruption */
		}
	}

	/* Nuke the existing STE_0 value, as we're going to rewrite it */
	val = STRTAB_STE_0_V;

	/* Bypass/fault */
	if (!ste->assigned || !(ste->s1_cfg || ste->s2_cfg)) {
		if (!ste->assigned && disable_bypass)
			val |= STRTAB_STE_0_CFG_ABORT;
		else
			val |= STRTAB_STE_0_CFG_BYPASS;

		dst[0] = cpu_to_le64(val);
		dst[1] = cpu_to_le64(STRTAB_STE_1_SHCFG_INCOMING
			 << STRTAB_STE_1_SHCFG_SHIFT);
		dst[2] = 0; /* Nuke the VMID */
		if (ste_live)
			arm_smmu_sync_ste_for_sid(smmu, sid);
		return;
	}

	if (ste->s1_cfg) {
		BUG_ON(ste_live);
		dst[1] = cpu_to_le64(
			 STRTAB_STE_1_S1C_CACHE_WBRA
			 << STRTAB_STE_1_S1CIR_SHIFT |
			 STRTAB_STE_1_S1C_CACHE_WBRA
			 << STRTAB_STE_1_S1COR_SHIFT |
			 STRTAB_STE_1_S1C_SH_ISH << STRTAB_STE_1_S1CSH_SHIFT |
#ifdef CONFIG_PCI_ATS
			 STRTAB_STE_1_EATS_TRANS << STRTAB_STE_1_EATS_SHIFT |
#endif
			 STRTAB_STE_1_STRW_NSEL1 << STRTAB_STE_1_STRW_SHIFT);

		if (smmu->features & ARM_SMMU_FEAT_STALLS)
			dst[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD);

		val |= (ste->s1_cfg->cdptr_dma & STRTAB_STE_0_S1CTXPTR_MASK
		        << STRTAB_STE_0_S1CTXPTR_SHIFT) |
			STRTAB_STE_0_CFG_S1_TRANS;
	}

	if (ste->s2_cfg) {
		BUG_ON(ste_live);
		dst[2] = cpu_to_le64(
			 ste->s2_cfg->vmid << STRTAB_STE_2_S2VMID_SHIFT |
			 (ste->s2_cfg->vtcr & STRTAB_STE_2_VTCR_MASK)
			  << STRTAB_STE_2_VTCR_SHIFT |
#ifdef __BIG_ENDIAN
			 STRTAB_STE_2_S2ENDI |
#endif
			 STRTAB_STE_2_S2PTW | STRTAB_STE_2_S2AA64 |
			 STRTAB_STE_2_S2R);

		dst[3] = cpu_to_le64(ste->s2_cfg->vttbr &
			 STRTAB_STE_3_S2TTB_MASK << STRTAB_STE_3_S2TTB_SHIFT);

		val |= STRTAB_STE_0_CFG_S2_TRANS;
	}

	arm_smmu_sync_ste_for_sid(smmu, sid);
	dst[0] = cpu_to_le64(val);
	arm_smmu_sync_ste_for_sid(smmu, sid);

	/* It's likely that we'll want to use the new STE soon */
	if (!(smmu->options & ARM_SMMU_OPT_SKIP_PREFETCH))
		arm_smmu_cmdq_issue_cmd(smmu, &prefetch_cmd);
}

static void arm_smmu_init_bypass_stes(u64 *strtab, unsigned int nent)
{
	unsigned int i;
	struct arm_smmu_strtab_ent ste = { .assigned = false };

	for (i = 0; i < nent; ++i) {
		arm_smmu_write_strtab_ent(NULL, -1, strtab, &ste);
		strtab += STRTAB_STE_DWORDS;
	}
}

static int arm_smmu_init_l2_strtab(struct arm_smmu_device *smmu, u32 sid)
{
	size_t size;
	void *strtab;
	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
	struct arm_smmu_strtab_l1_desc *desc = &cfg->l1_desc[sid >> STRTAB_SPLIT];

	if (desc->l2ptr)
		return 0;

	size = 1 << (STRTAB_SPLIT + ilog2(STRTAB_STE_DWORDS) + 3);
	strtab = &cfg->strtab[(sid >> STRTAB_SPLIT) * STRTAB_L1_DESC_DWORDS];

	desc->span = STRTAB_SPLIT + 1;
	desc->l2ptr = dmam_alloc_coherent(smmu->dev, size, &desc->l2ptr_dma,
					  GFP_KERNEL | __GFP_ZERO);
	if (!desc->l2ptr) {
		dev_err(smmu->dev,
			"failed to allocate l2 stream table for SID %u\n",
			sid);
		return -ENOMEM;
	}

	arm_smmu_init_bypass_stes(desc->l2ptr, 1 << STRTAB_SPLIT);
	arm_smmu_write_strtab_l1_desc(strtab, desc);
	return 0;
}

/* IRQ and event handlers */
static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev)
{
	int i;
	struct arm_smmu_device *smmu = dev;
	struct arm_smmu_queue *q = &smmu->evtq.q;
	u64 evt[EVTQ_ENT_DWORDS];

	do {
		while (!queue_remove_raw(q, evt)) {
			u8 id = evt[0] >> EVTQ_0_ID_SHIFT & EVTQ_0_ID_MASK;

			dev_info(smmu->dev, "event 0x%02x received:\n", id);
			for (i = 0; i < ARRAY_SIZE(evt); ++i)
				dev_info(smmu->dev, "\t0x%016llx\n",
					 (unsigned long long)evt[i]);

		}

		/*
		 * Not much we can do on overflow, so scream and pretend we're
		 * trying harder.
		 */
		if (queue_sync_prod(q) == -EOVERFLOW)
			dev_err(smmu->dev, "EVTQ overflow detected -- events lost\n");
	} while (!queue_empty(q));

	/* Sync our overflow flag, as we believe we're up to speed */
	q->cons = Q_OVF(q, q->prod) | Q_WRP(q, q->cons) | Q_IDX(q, q->cons);
	return IRQ_HANDLED;
}

static void arm_smmu_handle_ppr(struct arm_smmu_device *smmu, u64 *evt)
{
	u32 sid, ssid;
	u16 grpid;
	bool ssv, last;

	sid = evt[0] >> PRIQ_0_SID_SHIFT & PRIQ_0_SID_MASK;
	ssv = evt[0] & PRIQ_0_SSID_V;
	ssid = ssv ? evt[0] >> PRIQ_0_SSID_SHIFT & PRIQ_0_SSID_MASK : 0;
	last = evt[0] & PRIQ_0_PRG_LAST;
	grpid = evt[1] >> PRIQ_1_PRG_IDX_SHIFT & PRIQ_1_PRG_IDX_MASK;

	dev_info(smmu->dev, "unexpected PRI request received:\n");
	dev_info(smmu->dev,
		 "\tsid 0x%08x.0x%05x: [%u%s] %sprivileged %s%s%s access at iova 0x%016llx\n",
		 sid, ssid, grpid, last ? "L" : "",
		 evt[0] & PRIQ_0_PERM_PRIV ? "" : "un",
		 evt[0] & PRIQ_0_PERM_READ ? "R" : "",
		 evt[0] & PRIQ_0_PERM_WRITE ? "W" : "",
		 evt[0] & PRIQ_0_PERM_EXEC ? "X" : "",
		 evt[1] & PRIQ_1_ADDR_MASK << PRIQ_1_ADDR_SHIFT);

	if (last) {
		struct arm_smmu_cmdq_ent cmd = {
			.opcode			= CMDQ_OP_PRI_RESP,
			.substream_valid	= ssv,
			.pri			= {
				.sid	= sid,
				.ssid	= ssid,
				.grpid	= grpid,
				.resp	= PRI_RESP_DENY,
			},
		};

		arm_smmu_cmdq_issue_cmd(smmu, &cmd);
	}
}

static irqreturn_t arm_smmu_priq_thread(int irq, void *dev)
{
	struct arm_smmu_device *smmu = dev;
	struct arm_smmu_queue *q = &smmu->priq.q;
	u64 evt[PRIQ_ENT_DWORDS];

	do {
		while (!queue_remove_raw(q, evt))
			arm_smmu_handle_ppr(smmu, evt);

		if (queue_sync_prod(q) == -EOVERFLOW)
			dev_err(smmu->dev, "PRIQ overflow detected -- requests lost\n");
	} while (!queue_empty(q));

	/* Sync our overflow flag, as we believe we're up to speed */
	q->cons = Q_OVF(q, q->prod) | Q_WRP(q, q->cons) | Q_IDX(q, q->cons);
	return IRQ_HANDLED;
}

static irqreturn_t arm_smmu_cmdq_sync_handler(int irq, void *dev)
{
	/* We don't actually use CMD_SYNC interrupts for anything */
	return IRQ_HANDLED;
}

static int arm_smmu_device_disable(struct arm_smmu_device *smmu);

static irqreturn_t arm_smmu_gerror_handler(int irq, void *dev)
{
	u32 gerror, gerrorn, active;
	struct arm_smmu_device *smmu = dev;

	gerror = readl_relaxed(smmu->base + ARM_SMMU_GERROR);
	gerrorn = readl_relaxed(smmu->base + ARM_SMMU_GERRORN);

	active = gerror ^ gerrorn;
	if (!(active & GERROR_ERR_MASK))
		return IRQ_NONE; /* No errors pending */

	dev_warn(smmu->dev,
		 "unexpected global error reported (0x%08x), this could be serious\n",
		 active);

	if (active & GERROR_SFM_ERR) {
		dev_err(smmu->dev, "device has entered Service Failure Mode!\n");
		arm_smmu_device_disable(smmu);
	}

	if (active & GERROR_MSI_GERROR_ABT_ERR)
		dev_warn(smmu->dev, "GERROR MSI write aborted\n");

	if (active & GERROR_MSI_PRIQ_ABT_ERR)
		dev_warn(smmu->dev, "PRIQ MSI write aborted\n");

	if (active & GERROR_MSI_EVTQ_ABT_ERR)
		dev_warn(smmu->dev, "EVTQ MSI write aborted\n");

	if (active & GERROR_MSI_CMDQ_ABT_ERR) {
		dev_warn(smmu->dev, "CMDQ MSI write aborted\n");
		arm_smmu_cmdq_sync_handler(irq, smmu->dev);
	}

	if (active & GERROR_PRIQ_ABT_ERR)
		dev_err(smmu->dev, "PRIQ write aborted -- events may have been lost\n");

	if (active & GERROR_EVTQ_ABT_ERR)
		dev_err(smmu->dev, "EVTQ write aborted -- events may have been lost\n");

	if (active & GERROR_CMDQ_ERR)
		arm_smmu_cmdq_skip_err(smmu);

	writel(gerror, smmu->base + ARM_SMMU_GERRORN);
	return IRQ_HANDLED;
}

static irqreturn_t arm_smmu_combined_irq_thread(int irq, void *dev)
{
	struct arm_smmu_device *smmu = dev;

	arm_smmu_evtq_thread(irq, dev);
	if (smmu->features & ARM_SMMU_FEAT_PRI)
		arm_smmu_priq_thread(irq, dev);

	return IRQ_HANDLED;
}

static irqreturn_t arm_smmu_combined_irq_handler(int irq, void *dev)
{
	arm_smmu_gerror_handler(irq, dev);
	arm_smmu_cmdq_sync_handler(irq, dev);
	return IRQ_WAKE_THREAD;
}

/* IO_PGTABLE API */
static void __arm_smmu_tlb_sync(struct arm_smmu_device *smmu)
{
	struct arm_smmu_cmdq_ent cmd;

	cmd.opcode = CMDQ_OP_CMD_SYNC;
	arm_smmu_cmdq_issue_cmd(smmu, &cmd);
}

static void arm_smmu_tlb_sync(void *cookie)
{
	struct arm_smmu_domain *smmu_domain = cookie;
	__arm_smmu_tlb_sync(smmu_domain->smmu);
}

static void arm_smmu_tlb_inv_context(void *cookie)
{
	struct arm_smmu_domain *smmu_domain = cookie;
	struct arm_smmu_device *smmu = smmu_domain->smmu;
	struct arm_smmu_cmdq_ent cmd;

	if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
		cmd.opcode	= CMDQ_OP_TLBI_NH_ASID;
		cmd.tlbi.asid	= smmu_domain->s1_cfg.cd.asid;
		cmd.tlbi.vmid	= 0;
	} else {
		cmd.opcode	= CMDQ_OP_TLBI_S12_VMALL;
		cmd.tlbi.vmid	= smmu_domain->s2_cfg.vmid;
	}

	arm_smmu_cmdq_issue_cmd(smmu, &cmd);
	__arm_smmu_tlb_sync(smmu);
}

static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size,
					  size_t granule, bool leaf, void *cookie)
{
	struct arm_smmu_domain *smmu_domain = cookie;
	struct arm_smmu_device *smmu = smmu_domain->smmu;
	struct arm_smmu_cmdq_ent cmd = {
		.tlbi = {
			.leaf	= leaf,
			.addr	= iova,
		},
	};

	if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
		cmd.opcode	= CMDQ_OP_TLBI_NH_VA;
		cmd.tlbi.asid	= smmu_domain->s1_cfg.cd.asid;
	} else {
		cmd.opcode	= CMDQ_OP_TLBI_S2_IPA;
		cmd.tlbi.vmid	= smmu_domain->s2_cfg.vmid;
	}

	do {
		arm_smmu_cmdq_issue_cmd(smmu, &cmd);
		cmd.tlbi.addr += granule;
	} while (size -= granule);
}

static const struct iommu_gather_ops arm_smmu_gather_ops = {
	.tlb_flush_all	= arm_smmu_tlb_inv_context,
	.tlb_add_flush	= arm_smmu_tlb_inv_range_nosync,
	.tlb_sync	= arm_smmu_tlb_sync,
};

/* IOMMU API */
static bool arm_smmu_capable(enum iommu_cap cap)
{
	switch (cap) {
	case IOMMU_CAP_CACHE_COHERENCY:
		return true;
	case IOMMU_CAP_NOEXEC:
		return true;
	default:
		return false;
	}
}

static struct iommu_domain *arm_smmu_domain_alloc(unsigned type)
{
	struct arm_smmu_domain *smmu_domain;

	if (type != IOMMU_DOMAIN_UNMANAGED &&
	    type != IOMMU_DOMAIN_DMA &&
	    type != IOMMU_DOMAIN_IDENTITY)
		return NULL;

	/*
	 * Allocate the domain and initialise some of its data structures.
	 * We can't really do anything meaningful until we've added a
	 * master.
	 */
	smmu_domain = kzalloc(sizeof(*smmu_domain), GFP_KERNEL);
	if (!smmu_domain)
		return NULL;

	if (type == IOMMU_DOMAIN_DMA &&
	    iommu_get_dma_cookie(&smmu_domain->domain)) {
		kfree(smmu_domain);
		return NULL;
	}

	mutex_init(&smmu_domain->init_mutex);
	return &smmu_domain->domain;
}

static int arm_smmu_bitmap_alloc(unsigned long *map, int span)
{
	int idx, size = 1 << span;

	do {
		idx = find_first_zero_bit(map, size);
		if (idx == size)
			return -ENOSPC;
	} while (test_and_set_bit(idx, map));

	return idx;
}

static void arm_smmu_bitmap_free(unsigned long *map, int idx)
{
	clear_bit(idx, map);
}

static void arm_smmu_domain_free(struct iommu_domain *domain)
{
	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
	struct arm_smmu_device *smmu = smmu_domain->smmu;

	iommu_put_dma_cookie(domain);
	free_io_pgtable_ops(smmu_domain->pgtbl_ops);

	/* Free the CD and ASID, if we allocated them */
	if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
		struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg;

		if (cfg->cdptr) {
			dmam_free_coherent(smmu_domain->smmu->dev,
					   CTXDESC_CD_DWORDS << 3,
					   cfg->cdptr,
					   cfg->cdptr_dma);

			arm_smmu_bitmap_free(smmu->asid_map, cfg->cd.asid);
		}
	} else {
		struct arm_smmu_s2_cfg *cfg = &smmu_domain->s2_cfg;
		if (cfg->vmid)
			arm_smmu_bitmap_free(smmu->vmid_map, cfg->vmid);
	}

	kfree(smmu_domain);
}

static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain,
				       struct io_pgtable_cfg *pgtbl_cfg)
{
	int ret;
	int asid;
	struct arm_smmu_device *smmu = smmu_domain->smmu;
	struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg;

	asid = arm_smmu_bitmap_alloc(smmu->asid_map, smmu->asid_bits);
	if (asid < 0)
		return asid;

	cfg->cdptr = dmam_alloc_coherent(smmu->dev, CTXDESC_CD_DWORDS << 3,
					 &cfg->cdptr_dma,
					 GFP_KERNEL | __GFP_ZERO);
	if (!cfg->cdptr) {
		dev_warn(smmu->dev, "failed to allocate context descriptor\n");
		ret = -ENOMEM;
		goto out_free_asid;
	}

	cfg->cd.asid	= (u16)asid;
	cfg->cd.ttbr	= pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0];
	cfg->cd.tcr	= pgtbl_cfg->arm_lpae_s1_cfg.tcr;
	cfg->cd.mair	= pgtbl_cfg->arm_lpae_s1_cfg.mair[0];
	return 0;

out_free_asid:
	arm_smmu_bitmap_free(smmu->asid_map, asid);
	return ret;
}

static int arm_smmu_domain_finalise_s2(struct arm_smmu_domain *smmu_domain,
				       struct io_pgtable_cfg *pgtbl_cfg)
{
	int vmid;
	struct arm_smmu_device *smmu = smmu_domain->smmu;
	struct arm_smmu_s2_cfg *cfg = &smmu_domain->s2_cfg;

	vmid = arm_smmu_bitmap_alloc(smmu->vmid_map, smmu->vmid_bits);
	if (vmid < 0)
		return vmid;

	cfg->vmid	= (u16)vmid;
	cfg->vttbr	= pgtbl_cfg->arm_lpae_s2_cfg.vttbr;
	cfg->vtcr	= pgtbl_cfg->arm_lpae_s2_cfg.vtcr;
	return 0;
}

static int arm_smmu_domain_finalise(struct iommu_domain *domain)
{
	int ret;
	unsigned long ias, oas;
	enum io_pgtable_fmt fmt;
	struct io_pgtable_cfg pgtbl_cfg;
	struct io_pgtable_ops *pgtbl_ops;
	int (*finalise_stage_fn)(struct arm_smmu_domain *,
				 struct io_pgtable_cfg *);
	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
	struct arm_smmu_device *smmu = smmu_domain->smmu;

	if (domain->type == IOMMU_DOMAIN_IDENTITY) {
		smmu_domain->stage = ARM_SMMU_DOMAIN_BYPASS;
		return 0;
	}

	/* Restrict the stage to what we can actually support */
	if (!(smmu->features & ARM_SMMU_FEAT_TRANS_S1))
		smmu_domain->stage = ARM_SMMU_DOMAIN_S2;
	if (!(smmu->features & ARM_SMMU_FEAT_TRANS_S2))
		smmu_domain->stage = ARM_SMMU_DOMAIN_S1;

	switch (smmu_domain->stage) {
	case ARM_SMMU_DOMAIN_S1:
		ias = VA_BITS;
		oas = smmu->ias;
		fmt = ARM_64_LPAE_S1;
		finalise_stage_fn = arm_smmu_domain_finalise_s1;
		break;
	case ARM_SMMU_DOMAIN_NESTED:
	case ARM_SMMU_DOMAIN_S2:
		ias = smmu->ias;
		oas = smmu->oas;
		fmt = ARM_64_LPAE_S2;
		finalise_stage_fn = arm_smmu_domain_finalise_s2;
		break;
	default:
		return -EINVAL;
	}

	pgtbl_cfg = (struct io_pgtable_cfg) {
		.pgsize_bitmap	= smmu->pgsize_bitmap,
		.ias		= ias,
		.oas		= oas,
		.tlb		= &arm_smmu_gather_ops,
		.iommu_dev	= smmu->dev,
	};

	if (smmu->features & ARM_SMMU_FEAT_COHERENCY)
		pgtbl_cfg.quirks = IO_PGTABLE_QUIRK_NO_DMA;

	pgtbl_ops = alloc_io_pgtable_ops(fmt, &pgtbl_cfg, smmu_domain);
	if (!pgtbl_ops)
		return -ENOMEM;

	domain->pgsize_bitmap = pgtbl_cfg.pgsize_bitmap;
	domain->geometry.aperture_end = (1UL << ias) - 1;
	domain->geometry.force_aperture = true;
	smmu_domain->pgtbl_ops = pgtbl_ops;

	ret = finalise_stage_fn(smmu_domain, &pgtbl_cfg);
	if (ret < 0)
		free_io_pgtable_ops(pgtbl_ops);

	return ret;
}

static __le64 *arm_smmu_get_step_for_sid(struct arm_smmu_device *smmu, u32 sid)
{
	__le64 *step;
	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;

	if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB) {
		struct arm_smmu_strtab_l1_desc *l1_desc;
		int idx;

		/* Two-level walk */
		idx = (sid >> STRTAB_SPLIT) * STRTAB_L1_DESC_DWORDS;
		l1_desc = &cfg->l1_desc[idx];
		idx = (sid & ((1 << STRTAB_SPLIT) - 1)) * STRTAB_STE_DWORDS;
		step = &l1_desc->l2ptr[idx];
	} else {
		/* Simple linear lookup */
		step = &cfg->strtab[sid * STRTAB_STE_DWORDS];
	}

	return step;
}

static void arm_smmu_install_ste_for_dev(struct iommu_fwspec *fwspec)
{
	int i;
	struct arm_smmu_master_data *master = fwspec->iommu_priv;
	struct arm_smmu_device *smmu = master->smmu;

	for (i = 0; i < fwspec->num_ids; ++i) {
		u32 sid = fwspec->ids[i];
		__le64 *step = arm_smmu_get_step_for_sid(smmu, sid);

		arm_smmu_write_strtab_ent(smmu, sid, step, &master->ste);
	}
}

static void arm_smmu_detach_dev(struct device *dev)
{
	struct arm_smmu_master_data *master = dev->iommu_fwspec->iommu_priv;

	master->ste.assigned = false;
	arm_smmu_install_ste_for_dev(dev->iommu_fwspec);
}

static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
{
	int ret = 0;
	struct arm_smmu_device *smmu;
	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
	struct arm_smmu_master_data *master;
	struct arm_smmu_strtab_ent *ste;

	if (!dev->iommu_fwspec)
		return -ENOENT;

	master = dev->iommu_fwspec->iommu_priv;
	smmu = master->smmu;
	ste = &master->ste;

	/* Already attached to a different domain? */
	if (ste->assigned)
		arm_smmu_detach_dev(dev);

	mutex_lock(&smmu_domain->init_mutex);

	if (!smmu_domain->smmu) {
		smmu_domain->smmu = smmu;
		ret = arm_smmu_domain_finalise(domain);
		if (ret) {
			smmu_domain->smmu = NULL;
			goto out_unlock;
		}
	} else if (smmu_domain->smmu != smmu) {
		dev_err(dev,
			"cannot attach to SMMU %s (upstream of %s)\n",
			dev_name(smmu_domain->smmu->dev),
			dev_name(smmu->dev));
		ret = -ENXIO;
		goto out_unlock;
	}

	ste->assigned = true;

	if (smmu_domain->stage == ARM_SMMU_DOMAIN_BYPASS) {
		ste->s1_cfg = NULL;
		ste->s2_cfg = NULL;
	} else if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
		ste->s1_cfg = &smmu_domain->s1_cfg;
		ste->s2_cfg = NULL;
		arm_smmu_write_ctx_desc(smmu, ste->s1_cfg);
	} else {
		ste->s1_cfg = NULL;
		ste->s2_cfg = &smmu_domain->s2_cfg;
	}

	arm_smmu_install_ste_for_dev(dev->iommu_fwspec);
out_unlock:
	mutex_unlock(&smmu_domain->init_mutex);
	return ret;
}

static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova,
			phys_addr_t paddr, size_t size, int prot)
{
	struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops;

	if (!ops)
		return -ENODEV;

	return ops->map(ops, iova, paddr, size, prot);
}

static size_t
arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size)
{
	struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops;

	if (!ops)
		return 0;

	return ops->unmap(ops, iova, size);
}

static phys_addr_t
arm_smmu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova)
{
	struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops;

	if (domain->type == IOMMU_DOMAIN_IDENTITY)
		return iova;

	if (!ops)
		return 0;

	return ops->iova_to_phys(ops, iova);
}

static struct platform_driver arm_smmu_driver;

static int arm_smmu_match_node(struct device *dev, void *data)
{
	return dev->fwnode == data;
}

static
struct arm_smmu_device *arm_smmu_get_by_fwnode(struct fwnode_handle *fwnode)
{
	struct device *dev = driver_find_device(&arm_smmu_driver.driver, NULL,
						fwnode, arm_smmu_match_node);
	put_device(dev);
	return dev ? dev_get_drvdata(dev) : NULL;
}

static bool arm_smmu_sid_in_range(struct arm_smmu_device *smmu, u32 sid)
{
	unsigned long limit = smmu->strtab_cfg.num_l1_ents;

	if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB)
		limit *= 1UL << STRTAB_SPLIT;

	return sid < limit;
}

static struct iommu_ops arm_smmu_ops;

static int arm_smmu_add_device(struct device *dev)
{
	int i, ret;
	struct arm_smmu_device *smmu;
	struct arm_smmu_master_data *master;
	struct iommu_fwspec *fwspec = dev->iommu_fwspec;
	struct iommu_group *group;

	if (!fwspec || fwspec->ops != &arm_smmu_ops)
		return -ENODEV;
	/*
	 * We _can_ actually withstand dodgy bus code re-calling add_device()
	 * without an intervening remove_device()/of_xlate() sequence, but
	 * we're not going to do so quietly...
	 */
	if (WARN_ON_ONCE(fwspec->iommu_priv)) {
		master = fwspec->iommu_priv;
		smmu = master->smmu;
	} else {
		smmu = arm_smmu_get_by_fwnode(fwspec->iommu_fwnode);
		if (!smmu)
			return -ENODEV;
		master = kzalloc(sizeof(*master), GFP_KERNEL);
		if (!master)
			return -ENOMEM;

		master->smmu = smmu;
		fwspec->iommu_priv = master;
	}

	/* Check the SIDs are in range of the SMMU and our stream table */
	for (i = 0; i < fwspec->num_ids; i++) {
		u32 sid = fwspec->ids[i];

		if (!arm_smmu_sid_in_range(smmu, sid))
			return -ERANGE;

		/* Ensure l2 strtab is initialised */
		if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB) {
			ret = arm_smmu_init_l2_strtab(smmu, sid);
			if (ret)
				return ret;
		}
	}

	group = iommu_group_get_for_dev(dev);
	if (!IS_ERR(group)) {
		iommu_group_put(group);
		iommu_device_link(&smmu->iommu, dev);
	}

	return PTR_ERR_OR_ZERO(group);
}

static void arm_smmu_remove_device(struct device *dev)
{
	struct iommu_fwspec *fwspec = dev->iommu_fwspec;
	struct arm_smmu_master_data *master;
	struct arm_smmu_device *smmu;

	if (!fwspec || fwspec->ops != &arm_smmu_ops)
		return;

	master = fwspec->iommu_priv;
	smmu = master->smmu;
	if (master && master->ste.assigned)
		arm_smmu_detach_dev(dev);
	iommu_group_remove_device(dev);
	iommu_device_unlink(&smmu->iommu, dev);
	kfree(master);
	iommu_fwspec_free(dev);
}

static struct iommu_group *arm_smmu_device_group(struct device *dev)
{
	struct iommu_group *group;

	/*
	 * We don't support devices sharing stream IDs other than PCI RID
	 * aliases, since the necessary ID-to-device lookup becomes rather
	 * impractical given a potential sparse 32-bit stream ID space.
	 */
	if (dev_is_pci(dev))
		group = pci_device_group(dev);
	else
		group = generic_device_group(dev);

	return group;
}

static int arm_smmu_domain_get_attr(struct iommu_domain *domain,
				    enum iommu_attr attr, void *data)
{
	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);

	if (domain->type != IOMMU_DOMAIN_UNMANAGED)
		return -EINVAL;

	switch (attr) {
	case DOMAIN_ATTR_NESTING:
		*(int *)data = (smmu_domain->stage == ARM_SMMU_DOMAIN_NESTED);
		return 0;
	default:
		return -ENODEV;
	}
}

static int arm_smmu_domain_set_attr(struct iommu_domain *domain,
				    enum iommu_attr attr, void *data)
{
	int ret = 0;
	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);

	if (domain->type != IOMMU_DOMAIN_UNMANAGED)
		return -EINVAL;

	mutex_lock(&smmu_domain->init_mutex);

	switch (attr) {
	case DOMAIN_ATTR_NESTING:
		if (smmu_domain->smmu) {
			ret = -EPERM;
			goto out_unlock;
		}

		if (*(int *)data)
			smmu_domain->stage = ARM_SMMU_DOMAIN_NESTED;
		else
			smmu_domain->stage = ARM_SMMU_DOMAIN_S1;

		break;
	default:
		ret = -ENODEV;
	}

out_unlock:
	mutex_unlock(&smmu_domain->init_mutex);
	return ret;
}

static int arm_smmu_of_xlate(struct device *dev, struct of_phandle_args *args)
{
	return iommu_fwspec_add_ids(dev, args->args, 1);
}

static void arm_smmu_get_resv_regions(struct device *dev,
				      struct list_head *head)
{
	struct iommu_resv_region *region;
	int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;

	region = iommu_alloc_resv_region(MSI_IOVA_BASE, MSI_IOVA_LENGTH,
					 prot, IOMMU_RESV_SW_MSI);
	if (!region)
		return;

	list_add_tail(&region->list, head);

	iommu_dma_get_resv_regions(dev, head);
}

static void arm_smmu_put_resv_regions(struct device *dev,
				      struct list_head *head)
{
	struct iommu_resv_region *entry, *next;

	list_for_each_entry_safe(entry, next, head, list)
		kfree(entry);
}

static struct iommu_ops arm_smmu_ops = {
	.capable		= arm_smmu_capable,
	.domain_alloc		= arm_smmu_domain_alloc,
	.domain_free		= arm_smmu_domain_free,
	.attach_dev		= arm_smmu_attach_dev,
	.map			= arm_smmu_map,
	.unmap			= arm_smmu_unmap,
	.map_sg			= default_iommu_map_sg,
	.iova_to_phys		= arm_smmu_iova_to_phys,
	.add_device		= arm_smmu_add_device,
	.remove_device		= arm_smmu_remove_device,
	.device_group		= arm_smmu_device_group,
	.domain_get_attr	= arm_smmu_domain_get_attr,
	.domain_set_attr	= arm_smmu_domain_set_attr,
	.of_xlate		= arm_smmu_of_xlate,
	.get_resv_regions	= arm_smmu_get_resv_regions,
	.put_resv_regions	= arm_smmu_put_resv_regions,
	.pgsize_bitmap		= -1UL, /* Restricted during device attach */
};

/* Probing and initialisation functions */
static int arm_smmu_init_one_queue(struct arm_smmu_device *smmu,
				   struct arm_smmu_queue *q,
				   unsigned long prod_off,
				   unsigned long cons_off,
				   size_t dwords)
{
	size_t qsz = ((1 << q->max_n_shift) * dwords) << 3;

	q->base = dmam_alloc_coherent(smmu->dev, qsz, &q->base_dma, GFP_KERNEL);
	if (!q->base) {
		dev_err(smmu->dev, "failed to allocate queue (0x%zx bytes)\n",
			qsz);
		return -ENOMEM;
	}

	q->prod_reg	= arm_smmu_page1_fixup(prod_off, smmu);
	q->cons_reg	= arm_smmu_page1_fixup(cons_off, smmu);
	q->ent_dwords	= dwords;

	q->q_base  = Q_BASE_RWA;
	q->q_base |= q->base_dma & Q_BASE_ADDR_MASK << Q_BASE_ADDR_SHIFT;
	q->q_base |= (q->max_n_shift & Q_BASE_LOG2SIZE_MASK)
		     << Q_BASE_LOG2SIZE_SHIFT;

	q->prod = q->cons = 0;
	return 0;
}

static int arm_smmu_init_queues(struct arm_smmu_device *smmu)
{
	int ret;

	/* cmdq */
	spin_lock_init(&smmu->cmdq.lock);
	ret = arm_smmu_init_one_queue(smmu, &smmu->cmdq.q, ARM_SMMU_CMDQ_PROD,
				      ARM_SMMU_CMDQ_CONS, CMDQ_ENT_DWORDS);
	if (ret)
		return ret;

	/* evtq */
	ret = arm_smmu_init_one_queue(smmu, &smmu->evtq.q, ARM_SMMU_EVTQ_PROD,
				      ARM_SMMU_EVTQ_CONS, EVTQ_ENT_DWORDS);
	if (ret)
		return ret;

	/* priq */
	if (!(smmu->features & ARM_SMMU_FEAT_PRI))
		return 0;

	return arm_smmu_init_one_queue(smmu, &smmu->priq.q, ARM_SMMU_PRIQ_PROD,
				       ARM_SMMU_PRIQ_CONS, PRIQ_ENT_DWORDS);
}

static int arm_smmu_init_l1_strtab(struct arm_smmu_device *smmu)
{
	unsigned int i;
	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
	size_t size = sizeof(*cfg->l1_desc) * cfg->num_l1_ents;
	void *strtab = smmu->strtab_cfg.strtab;

	cfg->l1_desc = devm_kzalloc(smmu->dev, size, GFP_KERNEL);
	if (!cfg->l1_desc) {
		dev_err(smmu->dev, "failed to allocate l1 stream table desc\n");
		return -ENOMEM;
	}

	for (i = 0; i < cfg->num_l1_ents; ++i) {
		arm_smmu_write_strtab_l1_desc(strtab, &cfg->l1_desc[i]);
		strtab += STRTAB_L1_DESC_DWORDS << 3;
	}

	return 0;
}

static int arm_smmu_init_strtab_2lvl(struct arm_smmu_device *smmu)
{
	void *strtab;
	u64 reg;
	u32 size, l1size;
	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;

	/* Calculate the L1 size, capped to the SIDSIZE. */
	size = STRTAB_L1_SZ_SHIFT - (ilog2(STRTAB_L1_DESC_DWORDS) + 3);
	size = min(size, smmu->sid_bits - STRTAB_SPLIT);
	cfg->num_l1_ents = 1 << size;

	size += STRTAB_SPLIT;
	if (size < smmu->sid_bits)
		dev_warn(smmu->dev,
			 "2-level strtab only covers %u/%u bits of SID\n",
			 size, smmu->sid_bits);

	l1size = cfg->num_l1_ents * (STRTAB_L1_DESC_DWORDS << 3);
	strtab = dmam_alloc_coherent(smmu->dev, l1size, &cfg->strtab_dma,
				     GFP_KERNEL | __GFP_ZERO);
	if (!strtab) {
		dev_err(smmu->dev,
			"failed to allocate l1 stream table (%u bytes)\n",
			size);
		return -ENOMEM;
	}
	cfg->strtab = strtab;

	/* Configure strtab_base_cfg for 2 levels */
	reg  = STRTAB_BASE_CFG_FMT_2LVL;
	reg |= (size & STRTAB_BASE_CFG_LOG2SIZE_MASK)
		<< STRTAB_BASE_CFG_LOG2SIZE_SHIFT;
	reg |= (STRTAB_SPLIT & STRTAB_BASE_CFG_SPLIT_MASK)
		<< STRTAB_BASE_CFG_SPLIT_SHIFT;
	cfg->strtab_base_cfg = reg;

	return arm_smmu_init_l1_strtab(smmu);
}

static int arm_smmu_init_strtab_linear(struct arm_smmu_device *smmu)
{
	void *strtab;
	u64 reg;
	u32 size;
	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;

	size = (1 << smmu->sid_bits) * (STRTAB_STE_DWORDS << 3);
	strtab = dmam_alloc_coherent(smmu->dev, size, &cfg->strtab_dma,
				     GFP_KERNEL | __GFP_ZERO);
	if (!strtab) {
		dev_err(smmu->dev,
			"failed to allocate linear stream table (%u bytes)\n",
			size);
		return -ENOMEM;
	}
	cfg->strtab = strtab;
	cfg->num_l1_ents = 1 << smmu->sid_bits;

	/* Configure strtab_base_cfg for a linear table covering all SIDs */
	reg  = STRTAB_BASE_CFG_FMT_LINEAR;
	reg |= (smmu->sid_bits & STRTAB_BASE_CFG_LOG2SIZE_MASK)
		<< STRTAB_BASE_CFG_LOG2SIZE_SHIFT;
	cfg->strtab_base_cfg = reg;

	arm_smmu_init_bypass_stes(strtab, cfg->num_l1_ents);
	return 0;
}

static int arm_smmu_init_strtab(struct arm_smmu_device *smmu)
{
	u64 reg;
	int ret;

	if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB)
		ret = arm_smmu_init_strtab_2lvl(smmu);
	else
		ret = arm_smmu_init_strtab_linear(smmu);

	if (ret)
		return ret;

	/* Set the strtab base address */
	reg  = smmu->strtab_cfg.strtab_dma &
	       STRTAB_BASE_ADDR_MASK << STRTAB_BASE_ADDR_SHIFT;
	reg |= STRTAB_BASE_RA;
	smmu->strtab_cfg.strtab_base = reg;

	/* Allocate the first VMID for stage-2 bypass STEs */
	set_bit(0, smmu->vmid_map);
	return 0;
}

static int arm_smmu_init_structures(struct arm_smmu_device *smmu)
{
	int ret;

	ret = arm_smmu_init_queues(smmu);
	if (ret)
		return ret;

	return arm_smmu_init_strtab(smmu);
}

static int arm_smmu_write_reg_sync(struct arm_smmu_device *smmu, u32 val,
				   unsigned int reg_off, unsigned int ack_off)
{
	u32 reg;

	writel_relaxed(val, smmu->base + reg_off);
	return readl_relaxed_poll_timeout(smmu->base + ack_off, reg, reg == val,
					  1, ARM_SMMU_POLL_TIMEOUT_US);
}

/* GBPA is "special" */
static int arm_smmu_update_gbpa(struct arm_smmu_device *smmu, u32 set, u32 clr)
{
	int ret;
	u32 reg, __iomem *gbpa = smmu->base + ARM_SMMU_GBPA;

	ret = readl_relaxed_poll_timeout(gbpa, reg, !(reg & GBPA_UPDATE),
					 1, ARM_SMMU_POLL_TIMEOUT_US);
	if (ret)
		return ret;

	reg &= ~clr;
	reg |= set;
	writel_relaxed(reg | GBPA_UPDATE, gbpa);
	return readl_relaxed_poll_timeout(gbpa, reg, !(reg & GBPA_UPDATE),
					  1, ARM_SMMU_POLL_TIMEOUT_US);
}

static void arm_smmu_free_msis(void *data)
{
	struct device *dev = data;
	platform_msi_domain_free_irqs(dev);
}

static void arm_smmu_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg)
{
	phys_addr_t doorbell;
	struct device *dev = msi_desc_to_dev(desc);
	struct arm_smmu_device *smmu = dev_get_drvdata(dev);
	phys_addr_t *cfg = arm_smmu_msi_cfg[desc->platform.msi_index];

	doorbell = (((u64)msg->address_hi) << 32) | msg->address_lo;
	doorbell &= MSI_CFG0_ADDR_MASK << MSI_CFG0_ADDR_SHIFT;

	writeq_relaxed(doorbell, smmu->base + cfg[0]);
	writel_relaxed(msg->data, smmu->base + cfg[1]);
	writel_relaxed(MSI_CFG2_MEMATTR_DEVICE_nGnRE, smmu->base + cfg[2]);
}

static void arm_smmu_setup_msis(struct arm_smmu_device *smmu)
{
	struct msi_desc *desc;
	int ret, nvec = ARM_SMMU_MAX_MSIS;
	struct device *dev = smmu->dev;

	/* Clear the MSI address regs */
	writeq_relaxed(0, smmu->base + ARM_SMMU_GERROR_IRQ_CFG0);
	writeq_relaxed(0, smmu->base + ARM_SMMU_EVTQ_IRQ_CFG0);

	if (smmu->features & ARM_SMMU_FEAT_PRI)
		writeq_relaxed(0, smmu->base + ARM_SMMU_PRIQ_IRQ_CFG0);
	else
		nvec--;

	if (!(smmu->features & ARM_SMMU_FEAT_MSI))
		return;

	/* Allocate MSIs for evtq, gerror and priq. Ignore cmdq */
	ret = platform_msi_domain_alloc_irqs(dev, nvec, arm_smmu_write_msi_msg);
	if (ret) {
		dev_warn(dev, "failed to allocate MSIs\n");
		return;
	}

	for_each_msi_entry(desc, dev) {
		switch (desc->platform.msi_index) {
		case EVTQ_MSI_INDEX:
			smmu->evtq.q.irq = desc->irq;
			break;
		case GERROR_MSI_INDEX:
			smmu->gerr_irq = desc->irq;
			break;
		case PRIQ_MSI_INDEX:
			smmu->priq.q.irq = desc->irq;
			break;
		default:	/* Unknown */
			continue;
		}
	}

	/* Add callback to free MSIs on teardown */
	devm_add_action(dev, arm_smmu_free_msis, dev);
}

static void arm_smmu_setup_unique_irqs(struct arm_smmu_device *smmu)
{
	int irq, ret;

	arm_smmu_setup_msis(smmu);

	/* Request interrupt lines */
	irq = smmu->evtq.q.irq;
	if (irq) {
		ret = devm_request_threaded_irq(smmu->dev, irq, NULL,
						arm_smmu_evtq_thread,
						IRQF_ONESHOT,
						"arm-smmu-v3-evtq", smmu);
		if (ret < 0)
			dev_warn(smmu->dev, "failed to enable evtq irq\n");
	}

	irq = smmu->cmdq.q.irq;
	if (irq) {
		ret = devm_request_irq(smmu->dev, irq,
				       arm_smmu_cmdq_sync_handler, 0,
				       "arm-smmu-v3-cmdq-sync", smmu);
		if (ret < 0)
			dev_warn(smmu->dev, "failed to enable cmdq-sync irq\n");
	}

	irq = smmu->gerr_irq;
	if (irq) {
		ret = devm_request_irq(smmu->dev, irq, arm_smmu_gerror_handler,
				       0, "arm-smmu-v3-gerror", smmu);
		if (ret < 0)
			dev_warn(smmu->dev, "failed to enable gerror irq\n");
	}

	if (smmu->features & ARM_SMMU_FEAT_PRI) {
		irq = smmu->priq.q.irq;
		if (irq) {
			ret = devm_request_threaded_irq(smmu->dev, irq, NULL,
							arm_smmu_priq_thread,
							IRQF_ONESHOT,
							"arm-smmu-v3-priq",
							smmu);
			if (ret < 0)
				dev_warn(smmu->dev,
					 "failed to enable priq irq\n");
		}
	}
}

static int arm_smmu_setup_irqs(struct arm_smmu_device *smmu)
{
	int ret, irq;
	u32 irqen_flags = IRQ_CTRL_EVTQ_IRQEN | IRQ_CTRL_GERROR_IRQEN;

	/* Disable IRQs first */
	ret = arm_smmu_write_reg_sync(smmu, 0, ARM_SMMU_IRQ_CTRL,
				      ARM_SMMU_IRQ_CTRLACK);
	if (ret) {
		dev_err(smmu->dev, "failed to disable irqs\n");
		return ret;
	}

	irq = smmu->combined_irq;
	if (irq) {
		/*
		 * Cavium ThunderX2 implementation doesn't not support unique
		 * irq lines. Use single irq line for all the SMMUv3 interrupts.
		 */
		ret = devm_request_threaded_irq(smmu->dev, irq,
					arm_smmu_combined_irq_handler,
					arm_smmu_combined_irq_thread,
					IRQF_ONESHOT,
					"arm-smmu-v3-combined-irq", smmu);
		if (ret < 0)
			dev_warn(smmu->dev, "failed to enable combined irq\n");
	} else
		arm_smmu_setup_unique_irqs(smmu);

	if (smmu->features & ARM_SMMU_FEAT_PRI)
		irqen_flags |= IRQ_CTRL_PRIQ_IRQEN;

	/* Enable interrupt generation on the SMMU */
	ret = arm_smmu_write_reg_sync(smmu, irqen_flags,
				      ARM_SMMU_IRQ_CTRL, ARM_SMMU_IRQ_CTRLACK);
	if (ret)
		dev_warn(smmu->dev, "failed to enable irqs\n");

	return 0;
}

static int arm_smmu_device_disable(struct arm_smmu_device *smmu)
{
	int ret;

	ret = arm_smmu_write_reg_sync(smmu, 0, ARM_SMMU_CR0, ARM_SMMU_CR0ACK);
	if (ret)
		dev_err(smmu->dev, "failed to clear cr0\n");

	return ret;
}

static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass)
{
	int ret;
	u32 reg, enables;
	struct arm_smmu_cmdq_ent cmd;

	/* Clear CR0 and sync (disables SMMU and queue processing) */
	reg = readl_relaxed(smmu->base + ARM_SMMU_CR0);
	if (reg & CR0_SMMUEN)
		dev_warn(smmu->dev, "SMMU currently enabled! Resetting...\n");

	ret = arm_smmu_device_disable(smmu);
	if (ret)
		return ret;

	/* CR1 (table and queue memory attributes) */
	reg = (CR1_SH_ISH << CR1_TABLE_SH_SHIFT) |
	      (CR1_CACHE_WB << CR1_TABLE_OC_SHIFT) |
	      (CR1_CACHE_WB << CR1_TABLE_IC_SHIFT) |
	      (CR1_SH_ISH << CR1_QUEUE_SH_SHIFT) |
	      (CR1_CACHE_WB << CR1_QUEUE_OC_SHIFT) |
	      (CR1_CACHE_WB << CR1_QUEUE_IC_SHIFT);
	writel_relaxed(reg, smmu->base + ARM_SMMU_CR1);

	/* CR2 (random crap) */
	reg = CR2_PTM | CR2_RECINVSID | CR2_E2H;
	writel_relaxed(reg, smmu->base + ARM_SMMU_CR2);

	/* Stream table */
	writeq_relaxed(smmu->strtab_cfg.strtab_base,
		       smmu->base + ARM_SMMU_STRTAB_BASE);
	writel_relaxed(smmu->strtab_cfg.strtab_base_cfg,
		       smmu->base + ARM_SMMU_STRTAB_BASE_CFG);

	/* Command queue */
	writeq_relaxed(smmu->cmdq.q.q_base, smmu->base + ARM_SMMU_CMDQ_BASE);
	writel_relaxed(smmu->cmdq.q.prod, smmu->base + ARM_SMMU_CMDQ_PROD);
	writel_relaxed(smmu->cmdq.q.cons, smmu->base + ARM_SMMU_CMDQ_CONS);

	enables = CR0_CMDQEN;
	ret = arm_smmu_write_reg_sync(smmu, enables, ARM_SMMU_CR0,
				      ARM_SMMU_CR0ACK);
	if (ret) {
		dev_err(smmu->dev, "failed to enable command queue\n");
		return ret;
	}

	/* Invalidate any cached configuration */
	cmd.opcode = CMDQ_OP_CFGI_ALL;
	arm_smmu_cmdq_issue_cmd(smmu, &cmd);
	cmd.opcode = CMDQ_OP_CMD_SYNC;
	arm_smmu_cmdq_issue_cmd(smmu, &cmd);

	/* Invalidate any stale TLB entries */
	if (smmu->features & ARM_SMMU_FEAT_HYP) {
		cmd.opcode = CMDQ_OP_TLBI_EL2_ALL;
		arm_smmu_cmdq_issue_cmd(smmu, &cmd);
	}

	cmd.opcode = CMDQ_OP_TLBI_NSNH_ALL;
	arm_smmu_cmdq_issue_cmd(smmu, &cmd);
	cmd.opcode = CMDQ_OP_CMD_SYNC;
	arm_smmu_cmdq_issue_cmd(smmu, &cmd);

	/* Event queue */
	writeq_relaxed(smmu->evtq.q.q_base, smmu->base + ARM_SMMU_EVTQ_BASE);
	writel_relaxed(smmu->evtq.q.prod,
		       arm_smmu_page1_fixup(ARM_SMMU_EVTQ_PROD, smmu));
	writel_relaxed(smmu->evtq.q.cons,
		       arm_smmu_page1_fixup(ARM_SMMU_EVTQ_CONS, smmu));

	enables |= CR0_EVTQEN;
	ret = arm_smmu_write_reg_sync(smmu, enables, ARM_SMMU_CR0,
				      ARM_SMMU_CR0ACK);
	if (ret) {
		dev_err(smmu->dev, "failed to enable event queue\n");
		return ret;
	}

	/* PRI queue */
	if (smmu->features & ARM_SMMU_FEAT_PRI) {
		writeq_relaxed(smmu->priq.q.q_base,
			       smmu->base + ARM_SMMU_PRIQ_BASE);
		writel_relaxed(smmu->priq.q.prod,
			       arm_smmu_page1_fixup(ARM_SMMU_PRIQ_PROD, smmu));
		writel_relaxed(smmu->priq.q.cons,
			       arm_smmu_page1_fixup(ARM_SMMU_PRIQ_CONS, smmu));

		enables |= CR0_PRIQEN;
		ret = arm_smmu_write_reg_sync(smmu, enables, ARM_SMMU_CR0,
					      ARM_SMMU_CR0ACK);
		if (ret) {
			dev_err(smmu->dev, "failed to enable PRI queue\n");
			return ret;
		}
	}

	ret = arm_smmu_setup_irqs(smmu);
	if (ret) {
		dev_err(smmu->dev, "failed to setup irqs\n");
		return ret;
	}


	/* Enable the SMMU interface, or ensure bypass */
	if (!bypass || disable_bypass) {
		enables |= CR0_SMMUEN;
	} else {
		ret = arm_smmu_update_gbpa(smmu, 0, GBPA_ABORT);
		if (ret) {
			dev_err(smmu->dev, "GBPA not responding to update\n");
			return ret;
		}
	}
	ret = arm_smmu_write_reg_sync(smmu, enables, ARM_SMMU_CR0,
				      ARM_SMMU_CR0ACK);
	if (ret) {
		dev_err(smmu->dev, "failed to enable SMMU interface\n");
		return ret;
	}

	return 0;
}

static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
{
	u32 reg;
	bool coherent = smmu->features & ARM_SMMU_FEAT_COHERENCY;

	/* IDR0 */
	reg = readl_relaxed(smmu->base + ARM_SMMU_IDR0);

	/* 2-level structures */
	if ((reg & IDR0_ST_LVL_MASK << IDR0_ST_LVL_SHIFT) == IDR0_ST_LVL_2LVL)
		smmu->features |= ARM_SMMU_FEAT_2_LVL_STRTAB;

	if (reg & IDR0_CD2L)
		smmu->features |= ARM_SMMU_FEAT_2_LVL_CDTAB;

	/*
	 * Translation table endianness.
	 * We currently require the same endianness as the CPU, but this
	 * could be changed later by adding a new IO_PGTABLE_QUIRK.
	 */
	switch (reg & IDR0_TTENDIAN_MASK << IDR0_TTENDIAN_SHIFT) {
	case IDR0_TTENDIAN_MIXED:
		smmu->features |= ARM_SMMU_FEAT_TT_LE | ARM_SMMU_FEAT_TT_BE;
		break;
#ifdef __BIG_ENDIAN
	case IDR0_TTENDIAN_BE:
		smmu->features |= ARM_SMMU_FEAT_TT_BE;
		break;
#else
	case IDR0_TTENDIAN_LE:
		smmu->features |= ARM_SMMU_FEAT_TT_LE;
		break;
#endif
	default:
		dev_err(smmu->dev, "unknown/unsupported TT endianness!\n");
		return -ENXIO;
	}

	/* Boolean feature flags */
	if (IS_ENABLED(CONFIG_PCI_PRI) && reg & IDR0_PRI)
		smmu->features |= ARM_SMMU_FEAT_PRI;

	if (IS_ENABLED(CONFIG_PCI_ATS) && reg & IDR0_ATS)
		smmu->features |= ARM_SMMU_FEAT_ATS;

	if (reg & IDR0_SEV)
		smmu->features |= ARM_SMMU_FEAT_SEV;

	if (reg & IDR0_MSI)
		smmu->features |= ARM_SMMU_FEAT_MSI;

	if (reg & IDR0_HYP)
		smmu->features |= ARM_SMMU_FEAT_HYP;

	/*
	 * The coherency feature as set by FW is used in preference to the ID
	 * register, but warn on mismatch.
	 */
	if (!!(reg & IDR0_COHACC) != coherent)
		dev_warn(smmu->dev, "IDR0.COHACC overridden by dma-coherent property (%s)\n",
			 coherent ? "true" : "false");

	switch (reg & IDR0_STALL_MODEL_MASK << IDR0_STALL_MODEL_SHIFT) {
	case IDR0_STALL_MODEL_STALL:
		/* Fallthrough */
	case IDR0_STALL_MODEL_FORCE:
		smmu->features |= ARM_SMMU_FEAT_STALLS;
	}

	if (reg & IDR0_S1P)
		smmu->features |= ARM_SMMU_FEAT_TRANS_S1;

	if (reg & IDR0_S2P)
		smmu->features |= ARM_SMMU_FEAT_TRANS_S2;

	if (!(reg & (IDR0_S1P | IDR0_S2P))) {
		dev_err(smmu->dev, "no translation support!\n");
		return -ENXIO;
	}

	/* We only support the AArch64 table format at present */
	switch (reg & IDR0_TTF_MASK << IDR0_TTF_SHIFT) {
	case IDR0_TTF_AARCH32_64:
		smmu->ias = 40;
		/* Fallthrough */
	case IDR0_TTF_AARCH64:
		break;
	default:
		dev_err(smmu->dev, "AArch64 table format not supported!\n");
		return -ENXIO;
	}

	/* ASID/VMID sizes */
	smmu->asid_bits = reg & IDR0_ASID16 ? 16 : 8;
	smmu->vmid_bits = reg & IDR0_VMID16 ? 16 : 8;

	/* IDR1 */
	reg = readl_relaxed(smmu->base + ARM_SMMU_IDR1);
	if (reg & (IDR1_TABLES_PRESET | IDR1_QUEUES_PRESET | IDR1_REL)) {
		dev_err(smmu->dev, "embedded implementation not supported\n");
		return -ENXIO;
	}

	/* Queue sizes, capped at 4k */
	smmu->cmdq.q.max_n_shift = min((u32)CMDQ_MAX_SZ_SHIFT,
				       reg >> IDR1_CMDQ_SHIFT & IDR1_CMDQ_MASK);
	if (!smmu->cmdq.q.max_n_shift) {
		/* Odd alignment restrictions on the base, so ignore for now */
		dev_err(smmu->dev, "unit-length command queue not supported\n");
		return -ENXIO;
	}

	smmu->evtq.q.max_n_shift = min((u32)EVTQ_MAX_SZ_SHIFT,
				       reg >> IDR1_EVTQ_SHIFT & IDR1_EVTQ_MASK);
	smmu->priq.q.max_n_shift = min((u32)PRIQ_MAX_SZ_SHIFT,
				       reg >> IDR1_PRIQ_SHIFT & IDR1_PRIQ_MASK);

	/* SID/SSID sizes */
	smmu->ssid_bits = reg >> IDR1_SSID_SHIFT & IDR1_SSID_MASK;
	smmu->sid_bits = reg >> IDR1_SID_SHIFT & IDR1_SID_MASK;

	/*
	 * If the SMMU supports fewer bits than would fill a single L2 stream
	 * table, use a linear table instead.
	 */
	if (smmu->sid_bits <= STRTAB_SPLIT)
		smmu->features &= ~ARM_SMMU_FEAT_2_LVL_STRTAB;

	/* IDR5 */
	reg = readl_relaxed(smmu->base + ARM_SMMU_IDR5);

	/* Maximum number of outstanding stalls */
	smmu->evtq.max_stalls = reg >> IDR5_STALL_MAX_SHIFT
				& IDR5_STALL_MAX_MASK;

	/* Page sizes */
	if (reg & IDR5_GRAN64K)
		smmu->pgsize_bitmap |= SZ_64K | SZ_512M;
	if (reg & IDR5_GRAN16K)
		smmu->pgsize_bitmap |= SZ_16K | SZ_32M;
	if (reg & IDR5_GRAN4K)
		smmu->pgsize_bitmap |= SZ_4K | SZ_2M | SZ_1G;

	if (arm_smmu_ops.pgsize_bitmap == -1UL)
		arm_smmu_ops.pgsize_bitmap = smmu->pgsize_bitmap;
	else
		arm_smmu_ops.pgsize_bitmap |= smmu->pgsize_bitmap;

	/* Output address size */
	switch (reg & IDR5_OAS_MASK << IDR5_OAS_SHIFT) {
	case IDR5_OAS_32_BIT:
		smmu->oas = 32;
		break;
	case IDR5_OAS_36_BIT:
		smmu->oas = 36;
		break;
	case IDR5_OAS_40_BIT:
		smmu->oas = 40;
		break;
	case IDR5_OAS_42_BIT:
		smmu->oas = 42;
		break;
	case IDR5_OAS_44_BIT:
		smmu->oas = 44;
		break;
	default:
		dev_info(smmu->dev,
			"unknown output address size. Truncating to 48-bit\n");
		/* Fallthrough */
	case IDR5_OAS_48_BIT:
		smmu->oas = 48;
	}

	/* Set the DMA mask for our table walker */
	if (dma_set_mask_and_coherent(smmu->dev, DMA_BIT_MASK(smmu->oas)))
		dev_warn(smmu->dev,
			 "failed to set DMA mask for table walker\n");

	smmu->ias = max(smmu->ias, smmu->oas);

	dev_info(smmu->dev, "ias %lu-bit, oas %lu-bit (features 0x%08x)\n",
		 smmu->ias, smmu->oas, smmu->features);
	return 0;
}

#ifdef CONFIG_ACPI
static void acpi_smmu_get_options(u32 model, struct arm_smmu_device *smmu)
{
	switch (model) {
	case ACPI_IORT_SMMU_V3_CAVIUM_CN99XX:
		smmu->options |= ARM_SMMU_OPT_PAGE0_REGS_ONLY;
		break;
	case ACPI_IORT_SMMU_HISILICON_HI161X:
		smmu->options |= ARM_SMMU_OPT_SKIP_PREFETCH;
		break;
	}

	dev_notice(smmu->dev, "option mask 0x%x\n", smmu->options);
}

static int arm_smmu_device_acpi_probe(struct platform_device *pdev,
				      struct arm_smmu_device *smmu)
{
	struct acpi_iort_smmu_v3 *iort_smmu;
	struct device *dev = smmu->dev;
	struct acpi_iort_node *node;

	node = *(struct acpi_iort_node **)dev_get_platdata(dev);

	/* Retrieve SMMUv3 specific data */
	iort_smmu = (struct acpi_iort_smmu_v3 *)node->node_data;

	acpi_smmu_get_options(iort_smmu->model, smmu);

	if (iort_smmu->flags & ACPI_IORT_SMMU_V3_COHACC_OVERRIDE)
		smmu->features |= ARM_SMMU_FEAT_COHERENCY;

	return 0;
}
#else
static inline int arm_smmu_device_acpi_probe(struct platform_device *pdev,
					     struct arm_smmu_device *smmu)
{
	return -ENODEV;
}
#endif

static int arm_smmu_device_dt_probe(struct platform_device *pdev,
				    struct arm_smmu_device *smmu)
{
	struct device *dev = &pdev->dev;
	u32 cells;
	int ret = -EINVAL;

	if (of_property_read_u32(dev->of_node, "#iommu-cells", &cells))
		dev_err(dev, "missing #iommu-cells property\n");
	else if (cells != 1)
		dev_err(dev, "invalid #iommu-cells value (%d)\n", cells);
	else
		ret = 0;

	parse_driver_options(smmu);

	if (of_dma_is_coherent(dev->of_node))
		smmu->features |= ARM_SMMU_FEAT_COHERENCY;

	return ret;
}

static unsigned long arm_smmu_resource_size(struct arm_smmu_device *smmu)
{
	if (smmu->options & ARM_SMMU_OPT_PAGE0_REGS_ONLY)
		return SZ_64K;
	else
		return SZ_128K;
}

static int arm_smmu_device_probe(struct platform_device *pdev)
{
	int irq, ret;
	struct resource *res;
	resource_size_t ioaddr;
	struct arm_smmu_device *smmu;
	struct device *dev = &pdev->dev;
	bool bypass;

	smmu = devm_kzalloc(dev, sizeof(*smmu), GFP_KERNEL);
	if (!smmu) {
		dev_err(dev, "failed to allocate arm_smmu_device\n");
		return -ENOMEM;
	}
	smmu->dev = dev;

	if (dev->of_node) {
		ret = arm_smmu_device_dt_probe(pdev, smmu);
	} else {
		ret = arm_smmu_device_acpi_probe(pdev, smmu);
		if (ret == -ENODEV)
			return ret;
	}

	/* Set bypass mode according to firmware probing result */
	bypass = !!ret;

	/* Base address */
	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
	if (resource_size(res) + 1 < arm_smmu_resource_size(smmu)) {
		dev_err(dev, "MMIO region too small (%pr)\n", res);
		return -EINVAL;
	}
	ioaddr = res->start;

	smmu->base = devm_ioremap_resource(dev, res);
	if (IS_ERR(smmu->base))
		return PTR_ERR(smmu->base);

	/* Interrupt lines */

	irq = platform_get_irq_byname(pdev, "combined");
	if (irq > 0)
		smmu->combined_irq = irq;
	else {
		irq = platform_get_irq_byname(pdev, "eventq");
		if (irq > 0)
			smmu->evtq.q.irq = irq;

		irq = platform_get_irq_byname(pdev, "priq");
		if (irq > 0)
			smmu->priq.q.irq = irq;

		irq = platform_get_irq_byname(pdev, "cmdq-sync");
		if (irq > 0)
			smmu->cmdq.q.irq = irq;

		irq = platform_get_irq_byname(pdev, "gerror");
		if (irq > 0)
			smmu->gerr_irq = irq;
	}
	/* Probe the h/w */
	ret = arm_smmu_device_hw_probe(smmu);
	if (ret)
		return ret;

	/* Initialise in-memory data structures */
	ret = arm_smmu_init_structures(smmu);
	if (ret)
		return ret;

	/* Record our private device structure */
	platform_set_drvdata(pdev, smmu);

	/* Reset the device */
	ret = arm_smmu_device_reset(smmu, bypass);
	if (ret)
		return ret;

	/* And we're up. Go go go! */
	ret = iommu_device_sysfs_add(&smmu->iommu, dev, NULL,
				     "smmu3.%pa", &ioaddr);
	if (ret)
		return ret;

	iommu_device_set_ops(&smmu->iommu, &arm_smmu_ops);
	iommu_device_set_fwnode(&smmu->iommu, dev->fwnode);

	ret = iommu_device_register(&smmu->iommu);
	if (ret) {
		dev_err(dev, "Failed to register iommu\n");
		return ret;
	}

#ifdef CONFIG_PCI
	if (pci_bus_type.iommu_ops != &arm_smmu_ops) {
		pci_request_acs();
		ret = bus_set_iommu(&pci_bus_type, &arm_smmu_ops);
		if (ret)
			return ret;
	}
#endif
#ifdef CONFIG_ARM_AMBA
	if (amba_bustype.iommu_ops != &arm_smmu_ops) {
		ret = bus_set_iommu(&amba_bustype, &arm_smmu_ops);
		if (ret)
			return ret;
	}
#endif
	if (platform_bus_type.iommu_ops != &arm_smmu_ops) {
		ret = bus_set_iommu(&platform_bus_type, &arm_smmu_ops);
		if (ret)
			return ret;
	}
	return 0;
}

static int arm_smmu_device_remove(struct platform_device *pdev)
{
	struct arm_smmu_device *smmu = platform_get_drvdata(pdev);

	arm_smmu_device_disable(smmu);
	return 0;
}

static const struct of_device_id arm_smmu_of_match[] = {
	{ .compatible = "arm,smmu-v3", },
	{ },
};
MODULE_DEVICE_TABLE(of, arm_smmu_of_match);

static struct platform_driver arm_smmu_driver = {
	.driver	= {
		.name		= "arm-smmu-v3",
		.of_match_table	= of_match_ptr(arm_smmu_of_match),
	},
	.probe	= arm_smmu_device_probe,
	.remove	= arm_smmu_device_remove,
};
module_platform_driver(arm_smmu_driver);

IOMMU_OF_DECLARE(arm_smmuv3, "arm,smmu-v3", NULL);

MODULE_DESCRIPTION("IOMMU API for ARM architected SMMUv3 implementations");
MODULE_AUTHOR("Will Deacon <will.deacon@arm.com>");
MODULE_LICENSE("GPL v2");