summaryrefslogtreecommitdiff
path: root/hw/vfio/pci.c
blob: 41244811f33cf6e4455d62293555b6b7c86a2c42 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
/*
 * vfio based device assignment support
 *
 * Copyright Red Hat, Inc. 2012
 *
 * Authors:
 *  Alex Williamson <alex.williamson@redhat.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 * Based on qemu-kvm device-assignment:
 *  Adapted for KVM by Qumranet.
 *  Copyright (c) 2007, Neocleus, Alex Novik (alex@neocleus.com)
 *  Copyright (c) 2007, Neocleus, Guy Zana (guy@neocleus.com)
 *  Copyright (C) 2008, Qumranet, Amit Shah (amit.shah@qumranet.com)
 *  Copyright (C) 2008, Red Hat, Amit Shah (amit.shah@redhat.com)
 *  Copyright (C) 2008, IBM, Muli Ben-Yehuda (muli@il.ibm.com)
 */

#include <dirent.h>
#include <linux/vfio.h>
#include <sys/ioctl.h>
#include <sys/mman.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <unistd.h>

#include "config.h"
#include "exec/address-spaces.h"
#include "exec/memory.h"
#include "hw/pci/msi.h"
#include "hw/pci/msix.h"
#include "hw/pci/pci.h"
#include "qemu-common.h"
#include "qemu/error-report.h"
#include "qemu/event_notifier.h"
#include "qemu/queue.h"
#include "qemu/range.h"
#include "sysemu/kvm.h"
#include "sysemu/sysemu.h"
#include "trace.h"
#include "hw/vfio/vfio.h"

/* Extra debugging, trap acceleration paths for more logging */
#define VFIO_ALLOW_MMAP 1
#define VFIO_ALLOW_KVM_INTX 1
#define VFIO_ALLOW_KVM_MSI 1
#define VFIO_ALLOW_KVM_MSIX 1

struct VFIODevice;

typedef struct VFIOQuirk {
    MemoryRegion mem;
    struct VFIODevice *vdev;
    QLIST_ENTRY(VFIOQuirk) next;
    struct {
        uint32_t base_offset:TARGET_PAGE_BITS;
        uint32_t address_offset:TARGET_PAGE_BITS;
        uint32_t address_size:3;
        uint32_t bar:3;

        uint32_t address_match;
        uint32_t address_mask;

        uint32_t address_val:TARGET_PAGE_BITS;
        uint32_t data_offset:TARGET_PAGE_BITS;
        uint32_t data_size:3;

        uint8_t flags;
        uint8_t read_flags;
        uint8_t write_flags;
    } data;
} VFIOQuirk;

typedef struct VFIOBAR {
    off_t fd_offset; /* offset of BAR within device fd */
    int fd; /* device fd, allows us to pass VFIOBAR as opaque data */
    MemoryRegion mem; /* slow, read/write access */
    MemoryRegion mmap_mem; /* direct mapped access */
    void *mmap;
    size_t size;
    uint32_t flags; /* VFIO region flags (rd/wr/mmap) */
    uint8_t nr; /* cache the BAR number for debug */
    bool ioport;
    bool mem64;
    QLIST_HEAD(, VFIOQuirk) quirks;
} VFIOBAR;

typedef struct VFIOVGARegion {
    MemoryRegion mem;
    off_t offset;
    int nr;
    QLIST_HEAD(, VFIOQuirk) quirks;
} VFIOVGARegion;

typedef struct VFIOVGA {
    off_t fd_offset;
    int fd;
    VFIOVGARegion region[QEMU_PCI_VGA_NUM_REGIONS];
} VFIOVGA;

typedef struct VFIOINTx {
    bool pending; /* interrupt pending */
    bool kvm_accel; /* set when QEMU bypass through KVM enabled */
    uint8_t pin; /* which pin to pull for qemu_set_irq */
    EventNotifier interrupt; /* eventfd triggered on interrupt */
    EventNotifier unmask; /* eventfd for unmask on QEMU bypass */
    PCIINTxRoute route; /* routing info for QEMU bypass */
    uint32_t mmap_timeout; /* delay to re-enable mmaps after interrupt */
    QEMUTimer *mmap_timer; /* enable mmaps after periods w/o interrupts */
} VFIOINTx;

typedef struct VFIOMSIVector {
    /*
     * Two interrupt paths are configured per vector.  The first, is only used
     * for interrupts injected via QEMU.  This is typically the non-accel path,
     * but may also be used when we want QEMU to handle masking and pending
     * bits.  The KVM path bypasses QEMU and is therefore higher performance,
     * but requires masking at the device.  virq is used to track the MSI route
     * through KVM, thus kvm_interrupt is only available when virq is set to a
     * valid (>= 0) value.
     */
    EventNotifier interrupt;
    EventNotifier kvm_interrupt;
    struct VFIODevice *vdev; /* back pointer to device */
    int virq;
    bool use;
} VFIOMSIVector;

enum {
    VFIO_INT_NONE = 0,
    VFIO_INT_INTx = 1,
    VFIO_INT_MSI  = 2,
    VFIO_INT_MSIX = 3,
};

typedef struct VFIOAddressSpace {
    AddressSpace *as;
    QLIST_HEAD(, VFIOContainer) containers;
    QLIST_ENTRY(VFIOAddressSpace) list;
} VFIOAddressSpace;

static QLIST_HEAD(, VFIOAddressSpace) vfio_address_spaces =
    QLIST_HEAD_INITIALIZER(vfio_address_spaces);

struct VFIOGroup;

typedef struct VFIOType1 {
    MemoryListener listener;
    int error;
    bool initialized;
} VFIOType1;

typedef struct VFIOContainer {
    VFIOAddressSpace *space;
    int fd; /* /dev/vfio/vfio, empowered by the attached groups */
    struct {
        /* enable abstraction to support various iommu backends */
        union {
            VFIOType1 type1;
        };
        void (*release)(struct VFIOContainer *);
    } iommu_data;
    QLIST_HEAD(, VFIOGuestIOMMU) giommu_list;
    QLIST_HEAD(, VFIOGroup) group_list;
    QLIST_ENTRY(VFIOContainer) next;
} VFIOContainer;

typedef struct VFIOGuestIOMMU {
    VFIOContainer *container;
    MemoryRegion *iommu;
    Notifier n;
    QLIST_ENTRY(VFIOGuestIOMMU) giommu_next;
} VFIOGuestIOMMU;

/* Cache of MSI-X setup plus extra mmap and memory region for split BAR map */
typedef struct VFIOMSIXInfo {
    uint8_t table_bar;
    uint8_t pba_bar;
    uint16_t entries;
    uint32_t table_offset;
    uint32_t pba_offset;
    MemoryRegion mmap_mem;
    void *mmap;
} VFIOMSIXInfo;

typedef struct VFIODevice {
    PCIDevice pdev;
    int fd;
    VFIOINTx intx;
    unsigned int config_size;
    uint8_t *emulated_config_bits; /* QEMU emulated bits, little-endian */
    off_t config_offset; /* Offset of config space region within device fd */
    unsigned int rom_size;
    off_t rom_offset; /* Offset of ROM region within device fd */
    void *rom;
    int msi_cap_size;
    VFIOMSIVector *msi_vectors;
    VFIOMSIXInfo *msix;
    int nr_vectors; /* Number of MSI/MSIX vectors currently in use */
    int interrupt; /* Current interrupt type */
    VFIOBAR bars[PCI_NUM_REGIONS - 1]; /* No ROM */
    VFIOVGA vga; /* 0xa0000, 0x3b0, 0x3c0 */
    PCIHostDeviceAddress host;
    QLIST_ENTRY(VFIODevice) next;
    struct VFIOGroup *group;
    EventNotifier err_notifier;
    uint32_t features;
#define VFIO_FEATURE_ENABLE_VGA_BIT 0
#define VFIO_FEATURE_ENABLE_VGA (1 << VFIO_FEATURE_ENABLE_VGA_BIT)
    int32_t bootindex;
    uint8_t pm_cap;
    bool reset_works;
    bool has_vga;
    bool pci_aer;
    bool has_flr;
    bool has_pm_reset;
    bool needs_reset;
    bool rom_read_failed;
} VFIODevice;

typedef struct VFIOGroup {
    int fd;
    int groupid;
    VFIOContainer *container;
    QLIST_HEAD(, VFIODevice) device_list;
    QLIST_ENTRY(VFIOGroup) next;
    QLIST_ENTRY(VFIOGroup) container_next;
} VFIOGroup;

typedef struct VFIORomBlacklistEntry {
    uint16_t vendor_id;
    uint16_t device_id;
} VFIORomBlacklistEntry;

/*
 * List of device ids/vendor ids for which to disable
 * option rom loading. This avoids the guest hangs during rom
 * execution as noticed with the BCM 57810 card for lack of a
 * more better way to handle such issues.
 * The  user can still override by specifying a romfile or
 * rombar=1.
 * Please see https://bugs.launchpad.net/qemu/+bug/1284874
 * for an analysis of the 57810 card hang. When adding
 * a new vendor id/device id combination below, please also add
 * your card/environment details and information that could
 * help in debugging to the bug tracking this issue
 */
static const VFIORomBlacklistEntry romblacklist[] = {
    /* Broadcom BCM 57810 */
    { 0x14e4, 0x168e }
};

#define MSIX_CAP_LENGTH 12

static QLIST_HEAD(, VFIOGroup)
    group_list = QLIST_HEAD_INITIALIZER(group_list);

#ifdef CONFIG_KVM
/*
 * We have a single VFIO pseudo device per KVM VM.  Once created it lives
 * for the life of the VM.  Closing the file descriptor only drops our
 * reference to it and the device's reference to kvm.  Therefore once
 * initialized, this file descriptor is only released on QEMU exit and
 * we'll re-use it should another vfio device be attached before then.
 */
static int vfio_kvm_device_fd = -1;
#endif

static void vfio_disable_interrupts(VFIODevice *vdev);
static uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len);
static void vfio_pci_write_config(PCIDevice *pdev, uint32_t addr,
                                  uint32_t val, int len);
static void vfio_mmap_set_enabled(VFIODevice *vdev, bool enabled);

/*
 * Common VFIO interrupt disable
 */
static void vfio_disable_irqindex(VFIODevice *vdev, int index)
{
    struct vfio_irq_set irq_set = {
        .argsz = sizeof(irq_set),
        .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_TRIGGER,
        .index = index,
        .start = 0,
        .count = 0,
    };

    ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
}

/*
 * INTx
 */
static void vfio_unmask_intx(VFIODevice *vdev)
{
    struct vfio_irq_set irq_set = {
        .argsz = sizeof(irq_set),
        .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_UNMASK,
        .index = VFIO_PCI_INTX_IRQ_INDEX,
        .start = 0,
        .count = 1,
    };

    ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
}

#ifdef CONFIG_KVM /* Unused outside of CONFIG_KVM code */
static void vfio_mask_intx(VFIODevice *vdev)
{
    struct vfio_irq_set irq_set = {
        .argsz = sizeof(irq_set),
        .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_MASK,
        .index = VFIO_PCI_INTX_IRQ_INDEX,
        .start = 0,
        .count = 1,
    };

    ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
}
#endif

/*
 * Disabling BAR mmaping can be slow, but toggling it around INTx can
 * also be a huge overhead.  We try to get the best of both worlds by
 * waiting until an interrupt to disable mmaps (subsequent transitions
 * to the same state are effectively no overhead).  If the interrupt has
 * been serviced and the time gap is long enough, we re-enable mmaps for
 * performance.  This works well for things like graphics cards, which
 * may not use their interrupt at all and are penalized to an unusable
 * level by read/write BAR traps.  Other devices, like NICs, have more
 * regular interrupts and see much better latency by staying in non-mmap
 * mode.  We therefore set the default mmap_timeout such that a ping
 * is just enough to keep the mmap disabled.  Users can experiment with
 * other options with the x-intx-mmap-timeout-ms parameter (a value of
 * zero disables the timer).
 */
static void vfio_intx_mmap_enable(void *opaque)
{
    VFIODevice *vdev = opaque;

    if (vdev->intx.pending) {
        timer_mod(vdev->intx.mmap_timer,
                       qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) + vdev->intx.mmap_timeout);
        return;
    }

    vfio_mmap_set_enabled(vdev, true);
}

static void vfio_intx_interrupt(void *opaque)
{
    VFIODevice *vdev = opaque;

    if (!event_notifier_test_and_clear(&vdev->intx.interrupt)) {
        return;
    }

    trace_vfio_intx_interrupt(vdev->host.domain, vdev->host.bus,
                              vdev->host.slot, vdev->host.function,
                              'A' + vdev->intx.pin);

    vdev->intx.pending = true;
    pci_irq_assert(&vdev->pdev);
    vfio_mmap_set_enabled(vdev, false);
    if (vdev->intx.mmap_timeout) {
        timer_mod(vdev->intx.mmap_timer,
                       qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) + vdev->intx.mmap_timeout);
    }
}

static void vfio_eoi(VFIODevice *vdev)
{
    if (!vdev->intx.pending) {
        return;
    }

    trace_vfio_eoi(vdev->host.domain, vdev->host.bus,
                   vdev->host.slot, vdev->host.function);

    vdev->intx.pending = false;
    pci_irq_deassert(&vdev->pdev);
    vfio_unmask_intx(vdev);
}

static void vfio_enable_intx_kvm(VFIODevice *vdev)
{
#ifdef CONFIG_KVM
    struct kvm_irqfd irqfd = {
        .fd = event_notifier_get_fd(&vdev->intx.interrupt),
        .gsi = vdev->intx.route.irq,
        .flags = KVM_IRQFD_FLAG_RESAMPLE,
    };
    struct vfio_irq_set *irq_set;
    int ret, argsz;
    int32_t *pfd;

    if (!VFIO_ALLOW_KVM_INTX || !kvm_irqfds_enabled() ||
        vdev->intx.route.mode != PCI_INTX_ENABLED ||
        !kvm_resamplefds_enabled()) {
        return;
    }

    /* Get to a known interrupt state */
    qemu_set_fd_handler(irqfd.fd, NULL, NULL, vdev);
    vfio_mask_intx(vdev);
    vdev->intx.pending = false;
    pci_irq_deassert(&vdev->pdev);

    /* Get an eventfd for resample/unmask */
    if (event_notifier_init(&vdev->intx.unmask, 0)) {
        error_report("vfio: Error: event_notifier_init failed eoi");
        goto fail;
    }

    /* KVM triggers it, VFIO listens for it */
    irqfd.resamplefd = event_notifier_get_fd(&vdev->intx.unmask);

    if (kvm_vm_ioctl(kvm_state, KVM_IRQFD, &irqfd)) {
        error_report("vfio: Error: Failed to setup resample irqfd: %m");
        goto fail_irqfd;
    }

    argsz = sizeof(*irq_set) + sizeof(*pfd);

    irq_set = g_malloc0(argsz);
    irq_set->argsz = argsz;
    irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD | VFIO_IRQ_SET_ACTION_UNMASK;
    irq_set->index = VFIO_PCI_INTX_IRQ_INDEX;
    irq_set->start = 0;
    irq_set->count = 1;
    pfd = (int32_t *)&irq_set->data;

    *pfd = irqfd.resamplefd;

    ret = ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, irq_set);
    g_free(irq_set);
    if (ret) {
        error_report("vfio: Error: Failed to setup INTx unmask fd: %m");
        goto fail_vfio;
    }

    /* Let'em rip */
    vfio_unmask_intx(vdev);

    vdev->intx.kvm_accel = true;

    trace_vfio_enable_intx_kvm(vdev->host.domain, vdev->host.bus,
                               vdev->host.slot, vdev->host.function);

    return;

fail_vfio:
    irqfd.flags = KVM_IRQFD_FLAG_DEASSIGN;
    kvm_vm_ioctl(kvm_state, KVM_IRQFD, &irqfd);
fail_irqfd:
    event_notifier_cleanup(&vdev->intx.unmask);
fail:
    qemu_set_fd_handler(irqfd.fd, vfio_intx_interrupt, NULL, vdev);
    vfio_unmask_intx(vdev);
#endif
}

static void vfio_disable_intx_kvm(VFIODevice *vdev)
{
#ifdef CONFIG_KVM
    struct kvm_irqfd irqfd = {
        .fd = event_notifier_get_fd(&vdev->intx.interrupt),
        .gsi = vdev->intx.route.irq,
        .flags = KVM_IRQFD_FLAG_DEASSIGN,
    };

    if (!vdev->intx.kvm_accel) {
        return;
    }

    /*
     * Get to a known state, hardware masked, QEMU ready to accept new
     * interrupts, QEMU IRQ de-asserted.
     */
    vfio_mask_intx(vdev);
    vdev->intx.pending = false;
    pci_irq_deassert(&vdev->pdev);

    /* Tell KVM to stop listening for an INTx irqfd */
    if (kvm_vm_ioctl(kvm_state, KVM_IRQFD, &irqfd)) {
        error_report("vfio: Error: Failed to disable INTx irqfd: %m");
    }

    /* We only need to close the eventfd for VFIO to cleanup the kernel side */
    event_notifier_cleanup(&vdev->intx.unmask);

    /* QEMU starts listening for interrupt events. */
    qemu_set_fd_handler(irqfd.fd, vfio_intx_interrupt, NULL, vdev);

    vdev->intx.kvm_accel = false;

    /* If we've missed an event, let it re-fire through QEMU */
    vfio_unmask_intx(vdev);

    trace_vfio_disable_intx_kvm(vdev->host.domain, vdev->host.bus,
                                vdev->host.slot, vdev->host.function);
#endif
}

static void vfio_update_irq(PCIDevice *pdev)
{
    VFIODevice *vdev = DO_UPCAST(VFIODevice, pdev, pdev);
    PCIINTxRoute route;

    if (vdev->interrupt != VFIO_INT_INTx) {
        return;
    }

    route = pci_device_route_intx_to_irq(&vdev->pdev, vdev->intx.pin);

    if (!pci_intx_route_changed(&vdev->intx.route, &route)) {
        return; /* Nothing changed */
    }

    trace_vfio_update_irq(vdev->host.domain, vdev->host.bus,
                          vdev->host.slot, vdev->host.function,
                          vdev->intx.route.irq, route.irq);

    vfio_disable_intx_kvm(vdev);

    vdev->intx.route = route;

    if (route.mode != PCI_INTX_ENABLED) {
        return;
    }

    vfio_enable_intx_kvm(vdev);

    /* Re-enable the interrupt in cased we missed an EOI */
    vfio_eoi(vdev);
}

static int vfio_enable_intx(VFIODevice *vdev)
{
    uint8_t pin = vfio_pci_read_config(&vdev->pdev, PCI_INTERRUPT_PIN, 1);
    int ret, argsz;
    struct vfio_irq_set *irq_set;
    int32_t *pfd;

    if (!pin) {
        return 0;
    }

    vfio_disable_interrupts(vdev);

    vdev->intx.pin = pin - 1; /* Pin A (1) -> irq[0] */
    pci_config_set_interrupt_pin(vdev->pdev.config, pin);

#ifdef CONFIG_KVM
    /*
     * Only conditional to avoid generating error messages on platforms
     * where we won't actually use the result anyway.
     */
    if (kvm_irqfds_enabled() && kvm_resamplefds_enabled()) {
        vdev->intx.route = pci_device_route_intx_to_irq(&vdev->pdev,
                                                        vdev->intx.pin);
    }
#endif

    ret = event_notifier_init(&vdev->intx.interrupt, 0);
    if (ret) {
        error_report("vfio: Error: event_notifier_init failed");
        return ret;
    }

    argsz = sizeof(*irq_set) + sizeof(*pfd);

    irq_set = g_malloc0(argsz);
    irq_set->argsz = argsz;
    irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD | VFIO_IRQ_SET_ACTION_TRIGGER;
    irq_set->index = VFIO_PCI_INTX_IRQ_INDEX;
    irq_set->start = 0;
    irq_set->count = 1;
    pfd = (int32_t *)&irq_set->data;

    *pfd = event_notifier_get_fd(&vdev->intx.interrupt);
    qemu_set_fd_handler(*pfd, vfio_intx_interrupt, NULL, vdev);

    ret = ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, irq_set);
    g_free(irq_set);
    if (ret) {
        error_report("vfio: Error: Failed to setup INTx fd: %m");
        qemu_set_fd_handler(*pfd, NULL, NULL, vdev);
        event_notifier_cleanup(&vdev->intx.interrupt);
        return -errno;
    }

    vfio_enable_intx_kvm(vdev);

    vdev->interrupt = VFIO_INT_INTx;

    trace_vfio_enable_intx(vdev->host.domain, vdev->host.bus,
                           vdev->host.slot, vdev->host.function);

    return 0;
}

static void vfio_disable_intx(VFIODevice *vdev)
{
    int fd;

    timer_del(vdev->intx.mmap_timer);
    vfio_disable_intx_kvm(vdev);
    vfio_disable_irqindex(vdev, VFIO_PCI_INTX_IRQ_INDEX);
    vdev->intx.pending = false;
    pci_irq_deassert(&vdev->pdev);
    vfio_mmap_set_enabled(vdev, true);

    fd = event_notifier_get_fd(&vdev->intx.interrupt);
    qemu_set_fd_handler(fd, NULL, NULL, vdev);
    event_notifier_cleanup(&vdev->intx.interrupt);

    vdev->interrupt = VFIO_INT_NONE;

    trace_vfio_disable_intx(vdev->host.domain, vdev->host.bus,
                            vdev->host.slot, vdev->host.function);
}

/*
 * MSI/X
 */
static void vfio_msi_interrupt(void *opaque)
{
    VFIOMSIVector *vector = opaque;
    VFIODevice *vdev = vector->vdev;
    int nr = vector - vdev->msi_vectors;

    if (!event_notifier_test_and_clear(&vector->interrupt)) {
        return;
    }

#ifdef DEBUG_VFIO
    MSIMessage msg;

    if (vdev->interrupt == VFIO_INT_MSIX) {
        msg = msix_get_message(&vdev->pdev, nr);
    } else if (vdev->interrupt == VFIO_INT_MSI) {
        msg = msi_get_message(&vdev->pdev, nr);
    } else {
        abort();
    }

    trace_vfio_msi_interrupt(vdev->host.domain, vdev->host.bus,
                             vdev->host.slot, vdev->host.function,
                             nr, msg.address, msg.data);
#endif

    if (vdev->interrupt == VFIO_INT_MSIX) {
        msix_notify(&vdev->pdev, nr);
    } else if (vdev->interrupt == VFIO_INT_MSI) {
        msi_notify(&vdev->pdev, nr);
    } else {
        error_report("vfio: MSI interrupt receieved, but not enabled?");
    }
}

static int vfio_enable_vectors(VFIODevice *vdev, bool msix)
{
    struct vfio_irq_set *irq_set;
    int ret = 0, i, argsz;
    int32_t *fds;

    argsz = sizeof(*irq_set) + (vdev->nr_vectors * sizeof(*fds));

    irq_set = g_malloc0(argsz);
    irq_set->argsz = argsz;
    irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD | VFIO_IRQ_SET_ACTION_TRIGGER;
    irq_set->index = msix ? VFIO_PCI_MSIX_IRQ_INDEX : VFIO_PCI_MSI_IRQ_INDEX;
    irq_set->start = 0;
    irq_set->count = vdev->nr_vectors;
    fds = (int32_t *)&irq_set->data;

    for (i = 0; i < vdev->nr_vectors; i++) {
        int fd = -1;

        /*
         * MSI vs MSI-X - The guest has direct access to MSI mask and pending
         * bits, therefore we always use the KVM signaling path when setup.
         * MSI-X mask and pending bits are emulated, so we want to use the
         * KVM signaling path only when configured and unmasked.
         */
        if (vdev->msi_vectors[i].use) {
            if (vdev->msi_vectors[i].virq < 0 ||
                (msix && msix_is_masked(&vdev->pdev, i))) {
                fd = event_notifier_get_fd(&vdev->msi_vectors[i].interrupt);
            } else {
                fd = event_notifier_get_fd(&vdev->msi_vectors[i].kvm_interrupt);
            }
        }

        fds[i] = fd;
    }

    ret = ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, irq_set);

    g_free(irq_set);

    return ret;
}

static void vfio_add_kvm_msi_virq(VFIOMSIVector *vector, MSIMessage *msg,
                                  bool msix)
{
    int virq;

    if ((msix && !VFIO_ALLOW_KVM_MSIX) ||
        (!msix && !VFIO_ALLOW_KVM_MSI) || !msg) {
        return;
    }

    if (event_notifier_init(&vector->kvm_interrupt, 0)) {
        return;
    }

    virq = kvm_irqchip_add_msi_route(kvm_state, *msg);
    if (virq < 0) {
        event_notifier_cleanup(&vector->kvm_interrupt);
        return;
    }

    if (kvm_irqchip_add_irqfd_notifier(kvm_state, &vector->kvm_interrupt,
                                       NULL, virq) < 0) {
        kvm_irqchip_release_virq(kvm_state, virq);
        event_notifier_cleanup(&vector->kvm_interrupt);
        return;
    }

    vector->virq = virq;
}

static void vfio_remove_kvm_msi_virq(VFIOMSIVector *vector)
{
    kvm_irqchip_remove_irqfd_notifier(kvm_state, &vector->kvm_interrupt,
                                      vector->virq);
    kvm_irqchip_release_virq(kvm_state, vector->virq);
    vector->virq = -1;
    event_notifier_cleanup(&vector->kvm_interrupt);
}

static void vfio_update_kvm_msi_virq(VFIOMSIVector *vector, MSIMessage msg)
{
    kvm_irqchip_update_msi_route(kvm_state, vector->virq, msg);
}

static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr,
                                   MSIMessage *msg, IOHandler *handler)
{
    VFIODevice *vdev = DO_UPCAST(VFIODevice, pdev, pdev);
    VFIOMSIVector *vector;
    int ret;

    trace_vfio_msix_vector_do_use(vdev->host.domain, vdev->host.bus,
                                  vdev->host.slot, vdev->host.function,
                                  nr);

    vector = &vdev->msi_vectors[nr];

    if (!vector->use) {
        vector->vdev = vdev;
        vector->virq = -1;
        if (event_notifier_init(&vector->interrupt, 0)) {
            error_report("vfio: Error: event_notifier_init failed");
        }
        vector->use = true;
        msix_vector_use(pdev, nr);
    }

    qemu_set_fd_handler(event_notifier_get_fd(&vector->interrupt),
                        handler, NULL, vector);

    /*
     * Attempt to enable route through KVM irqchip,
     * default to userspace handling if unavailable.
     */
    if (vector->virq >= 0) {
        if (!msg) {
            vfio_remove_kvm_msi_virq(vector);
        } else {
            vfio_update_kvm_msi_virq(vector, *msg);
        }
    } else {
        vfio_add_kvm_msi_virq(vector, msg, true);
    }

    /*
     * We don't want to have the host allocate all possible MSI vectors
     * for a device if they're not in use, so we shutdown and incrementally
     * increase them as needed.
     */
    if (vdev->nr_vectors < nr + 1) {
        vfio_disable_irqindex(vdev, VFIO_PCI_MSIX_IRQ_INDEX);
        vdev->nr_vectors = nr + 1;
        ret = vfio_enable_vectors(vdev, true);
        if (ret) {
            error_report("vfio: failed to enable vectors, %d", ret);
        }
    } else {
        int argsz;
        struct vfio_irq_set *irq_set;
        int32_t *pfd;

        argsz = sizeof(*irq_set) + sizeof(*pfd);

        irq_set = g_malloc0(argsz);
        irq_set->argsz = argsz;
        irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD |
                         VFIO_IRQ_SET_ACTION_TRIGGER;
        irq_set->index = VFIO_PCI_MSIX_IRQ_INDEX;
        irq_set->start = nr;
        irq_set->count = 1;
        pfd = (int32_t *)&irq_set->data;

        if (vector->virq >= 0) {
            *pfd = event_notifier_get_fd(&vector->kvm_interrupt);
        } else {
            *pfd = event_notifier_get_fd(&vector->interrupt);
        }

        ret = ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, irq_set);
        g_free(irq_set);
        if (ret) {
            error_report("vfio: failed to modify vector, %d", ret);
        }
    }

    return 0;
}

static int vfio_msix_vector_use(PCIDevice *pdev,
                                unsigned int nr, MSIMessage msg)
{
    return vfio_msix_vector_do_use(pdev, nr, &msg, vfio_msi_interrupt);
}

static void vfio_msix_vector_release(PCIDevice *pdev, unsigned int nr)
{
    VFIODevice *vdev = DO_UPCAST(VFIODevice, pdev, pdev);
    VFIOMSIVector *vector = &vdev->msi_vectors[nr];

    trace_vfio_msix_vector_release(vdev->host.domain, vdev->host.bus,
                                   vdev->host.slot, vdev->host.function,
                                   nr);

    /*
     * There are still old guests that mask and unmask vectors on every
     * interrupt.  If we're using QEMU bypass with a KVM irqfd, leave all of
     * the KVM setup in place, simply switch VFIO to use the non-bypass
     * eventfd.  We'll then fire the interrupt through QEMU and the MSI-X
     * core will mask the interrupt and set pending bits, allowing it to
     * be re-asserted on unmask.  Nothing to do if already using QEMU mode.
     */
    if (vector->virq >= 0) {
        int argsz;
        struct vfio_irq_set *irq_set;
        int32_t *pfd;

        argsz = sizeof(*irq_set) + sizeof(*pfd);

        irq_set = g_malloc0(argsz);
        irq_set->argsz = argsz;
        irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD |
                         VFIO_IRQ_SET_ACTION_TRIGGER;
        irq_set->index = VFIO_PCI_MSIX_IRQ_INDEX;
        irq_set->start = nr;
        irq_set->count = 1;
        pfd = (int32_t *)&irq_set->data;

        *pfd = event_notifier_get_fd(&vector->interrupt);

        ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, irq_set);

        g_free(irq_set);
    }
}

static void vfio_enable_msix(VFIODevice *vdev)
{
    vfio_disable_interrupts(vdev);

    vdev->msi_vectors = g_malloc0(vdev->msix->entries * sizeof(VFIOMSIVector));

    vdev->interrupt = VFIO_INT_MSIX;

    /*
     * Some communication channels between VF & PF or PF & fw rely on the
     * physical state of the device and expect that enabling MSI-X from the
     * guest enables the same on the host.  When our guest is Linux, the
     * guest driver call to pci_enable_msix() sets the enabling bit in the
     * MSI-X capability, but leaves the vector table masked.  We therefore
     * can't rely on a vector_use callback (from request_irq() in the guest)
     * to switch the physical device into MSI-X mode because that may come a
     * long time after pci_enable_msix().  This code enables vector 0 with
     * triggering to userspace, then immediately release the vector, leaving
     * the physical device with no vectors enabled, but MSI-X enabled, just
     * like the guest view.
     */
    vfio_msix_vector_do_use(&vdev->pdev, 0, NULL, NULL);
    vfio_msix_vector_release(&vdev->pdev, 0);

    if (msix_set_vector_notifiers(&vdev->pdev, vfio_msix_vector_use,
                                  vfio_msix_vector_release, NULL)) {
        error_report("vfio: msix_set_vector_notifiers failed");
    }

    trace_vfio_enable_msix(vdev->host.domain, vdev->host.bus,
                           vdev->host.slot, vdev->host.function);
}

static void vfio_enable_msi(VFIODevice *vdev)
{
    int ret, i;

    vfio_disable_interrupts(vdev);

    vdev->nr_vectors = msi_nr_vectors_allocated(&vdev->pdev);
retry:
    vdev->msi_vectors = g_malloc0(vdev->nr_vectors * sizeof(VFIOMSIVector));

    for (i = 0; i < vdev->nr_vectors; i++) {
        VFIOMSIVector *vector = &vdev->msi_vectors[i];
        MSIMessage msg = msi_get_message(&vdev->pdev, i);

        vector->vdev = vdev;
        vector->virq = -1;
        vector->use = true;

        if (event_notifier_init(&vector->interrupt, 0)) {
            error_report("vfio: Error: event_notifier_init failed");
        }

        qemu_set_fd_handler(event_notifier_get_fd(&vector->interrupt),
                            vfio_msi_interrupt, NULL, vector);

        /*
         * Attempt to enable route through KVM irqchip,
         * default to userspace handling if unavailable.
         */
        vfio_add_kvm_msi_virq(vector, &msg, false);
    }

    /* Set interrupt type prior to possible interrupts */
    vdev->interrupt = VFIO_INT_MSI;

    ret = vfio_enable_vectors(vdev, false);
    if (ret) {
        if (ret < 0) {
            error_report("vfio: Error: Failed to setup MSI fds: %m");
        } else if (ret != vdev->nr_vectors) {
            error_report("vfio: Error: Failed to enable %d "
                         "MSI vectors, retry with %d", vdev->nr_vectors, ret);
        }

        for (i = 0; i < vdev->nr_vectors; i++) {
            VFIOMSIVector *vector = &vdev->msi_vectors[i];
            if (vector->virq >= 0) {
                vfio_remove_kvm_msi_virq(vector);
            }
            qemu_set_fd_handler(event_notifier_get_fd(&vector->interrupt),
                                NULL, NULL, NULL);
            event_notifier_cleanup(&vector->interrupt);
        }

        g_free(vdev->msi_vectors);

        if (ret > 0 && ret != vdev->nr_vectors) {
            vdev->nr_vectors = ret;
            goto retry;
        }
        vdev->nr_vectors = 0;

        /*
         * Failing to setup MSI doesn't really fall within any specification.
         * Let's try leaving interrupts disabled and hope the guest figures
         * out to fall back to INTx for this device.
         */
        error_report("vfio: Error: Failed to enable MSI");
        vdev->interrupt = VFIO_INT_NONE;

        return;
    }

    trace_vfio_enable_msi(vdev->host.domain, vdev->host.bus,
                          vdev->host.slot, vdev->host.function,
                          vdev->nr_vectors);
}

static void vfio_disable_msi_common(VFIODevice *vdev)
{
    int i;

    for (i = 0; i < vdev->nr_vectors; i++) {
        VFIOMSIVector *vector = &vdev->msi_vectors[i];
        if (vdev->msi_vectors[i].use) {
            if (vector->virq >= 0) {
                vfio_remove_kvm_msi_virq(vector);
            }
            qemu_set_fd_handler(event_notifier_get_fd(&vector->interrupt),
                                NULL, NULL, NULL);
            event_notifier_cleanup(&vector->interrupt);
        }
    }

    g_free(vdev->msi_vectors);
    vdev->msi_vectors = NULL;
    vdev->nr_vectors = 0;
    vdev->interrupt = VFIO_INT_NONE;

    vfio_enable_intx(vdev);
}

static void vfio_disable_msix(VFIODevice *vdev)
{
    int i;

    msix_unset_vector_notifiers(&vdev->pdev);

    /*
     * MSI-X will only release vectors if MSI-X is still enabled on the
     * device, check through the rest and release it ourselves if necessary.
     */
    for (i = 0; i < vdev->nr_vectors; i++) {
        if (vdev->msi_vectors[i].use) {
            vfio_msix_vector_release(&vdev->pdev, i);
            msix_vector_unuse(&vdev->pdev, i);
        }
    }

    if (vdev->nr_vectors) {
        vfio_disable_irqindex(vdev, VFIO_PCI_MSIX_IRQ_INDEX);
    }

    vfio_disable_msi_common(vdev);

    trace_vfio_disable_msix(vdev->host.domain, vdev->host.bus,
                            vdev->host.slot, vdev->host.function);
}

static void vfio_disable_msi(VFIODevice *vdev)
{
    vfio_disable_irqindex(vdev, VFIO_PCI_MSI_IRQ_INDEX);
    vfio_disable_msi_common(vdev);

    trace_vfio_disable_msi(vdev->host.domain, vdev->host.bus,
                           vdev->host.slot, vdev->host.function);
}

static void vfio_update_msi(VFIODevice *vdev)
{
    int i;

    for (i = 0; i < vdev->nr_vectors; i++) {
        VFIOMSIVector *vector = &vdev->msi_vectors[i];
        MSIMessage msg;

        if (!vector->use || vector->virq < 0) {
            continue;
        }

        msg = msi_get_message(&vdev->pdev, i);
        vfio_update_kvm_msi_virq(vector, msg);
    }
}

/*
 * IO Port/MMIO - Beware of the endians, VFIO is always little endian
 */
static void vfio_bar_write(void *opaque, hwaddr addr,
                           uint64_t data, unsigned size)
{
    VFIOBAR *bar = opaque;
    union {
        uint8_t byte;
        uint16_t word;
        uint32_t dword;
        uint64_t qword;
    } buf;

    switch (size) {
    case 1:
        buf.byte = data;
        break;
    case 2:
        buf.word = cpu_to_le16(data);
        break;
    case 4:
        buf.dword = cpu_to_le32(data);
        break;
    default:
        hw_error("vfio: unsupported write size, %d bytes", size);
        break;
    }

    if (pwrite(bar->fd, &buf, size, bar->fd_offset + addr) != size) {
        error_report("%s(,0x%"HWADDR_PRIx", 0x%"PRIx64", %d) failed: %m",
                     __func__, addr, data, size);
    }

#ifdef DEBUG_VFIO
    {
        VFIODevice *vdev = container_of(bar, VFIODevice, bars[bar->nr]);

        trace_vfio_bar_write(vdev->host.domain, vdev->host.bus,
                             vdev->host.slot, vdev->host.function,
                             region->nr, addr, data, size);
    }
#endif

    /*
     * A read or write to a BAR always signals an INTx EOI.  This will
     * do nothing if not pending (including not in INTx mode).  We assume
     * that a BAR access is in response to an interrupt and that BAR
     * accesses will service the interrupt.  Unfortunately, we don't know
     * which access will service the interrupt, so we're potentially
     * getting quite a few host interrupts per guest interrupt.
     */
    vfio_eoi(container_of(bar, VFIODevice, bars[bar->nr]));
}

static uint64_t vfio_bar_read(void *opaque,
                              hwaddr addr, unsigned size)
{
    VFIOBAR *bar = opaque;
    union {
        uint8_t byte;
        uint16_t word;
        uint32_t dword;
        uint64_t qword;
    } buf;
    uint64_t data = 0;

    if (pread(bar->fd, &buf, size, bar->fd_offset + addr) != size) {
        error_report("%s(,0x%"HWADDR_PRIx", %d) failed: %m",
                     __func__, addr, size);
        return (uint64_t)-1;
    }

    switch (size) {
    case 1:
        data = buf.byte;
        break;
    case 2:
        data = le16_to_cpu(buf.word);
        break;
    case 4:
        data = le32_to_cpu(buf.dword);
        break;
    default:
        hw_error("vfio: unsupported read size, %d bytes", size);
        break;
    }

#ifdef DEBUG_VFIO
    {
        VFIODevice *vdev = container_of(bar, VFIODevice, bars[bar->nr]);

        trace_vfio_bar_read(vdev->host.domain, vdev->host.bus,
                            vdev->host.slot, vdev->host.function,
                            region->nr, addr, size, data);
    }
#endif

    /* Same as write above */
    vfio_eoi(container_of(bar, VFIODevice, bars[bar->nr]));

    return data;
}

static const MemoryRegionOps vfio_bar_ops = {
    .read = vfio_bar_read,
    .write = vfio_bar_write,
    .endianness = DEVICE_LITTLE_ENDIAN,
};

static void vfio_pci_load_rom(VFIODevice *vdev)
{
    struct vfio_region_info reg_info = {
        .argsz = sizeof(reg_info),
        .index = VFIO_PCI_ROM_REGION_INDEX
    };
    uint64_t size;
    off_t off = 0;
    size_t bytes;

    if (ioctl(vdev->fd, VFIO_DEVICE_GET_REGION_INFO, &reg_info)) {
        error_report("vfio: Error getting ROM info: %m");
        return;
    }

    trace_vfio_pci_load_rom(vdev->host.domain, vdev->host.bus,
                            vdev->host.slot, vdev->host.function,
                            (unsigned long)reg_info.size,
                            (unsigned long)reg_info.offset,
                            (unsigned long)reg_info.flags);

    vdev->rom_size = size = reg_info.size;
    vdev->rom_offset = reg_info.offset;

    if (!vdev->rom_size) {
        vdev->rom_read_failed = true;
        error_report("vfio-pci: Cannot read device rom at "
                    "%04x:%02x:%02x.%x",
                    vdev->host.domain, vdev->host.bus, vdev->host.slot,
                    vdev->host.function);
        error_printf("Device option ROM contents are probably invalid "
                    "(check dmesg).\nSkip option ROM probe with rombar=0, "
                    "or load from file with romfile=\n");
        return;
    }

    vdev->rom = g_malloc(size);
    memset(vdev->rom, 0xff, size);

    while (size) {
        bytes = pread(vdev->fd, vdev->rom + off, size, vdev->rom_offset + off);
        if (bytes == 0) {
            break;
        } else if (bytes > 0) {
            off += bytes;
            size -= bytes;
        } else {
            if (errno == EINTR || errno == EAGAIN) {
                continue;
            }
            error_report("vfio: Error reading device ROM: %m");
            break;
        }
    }
}

static uint64_t vfio_rom_read(void *opaque, hwaddr addr, unsigned size)
{
    VFIODevice *vdev = opaque;
    union {
        uint8_t byte;
        uint16_t word;
        uint32_t dword;
        uint64_t qword;
    } val;
    uint64_t data = 0;

    /* Load the ROM lazily when the guest tries to read it */
    if (unlikely(!vdev->rom && !vdev->rom_read_failed)) {
        vfio_pci_load_rom(vdev);
    }

    memcpy(&val, vdev->rom + addr,
           (addr < vdev->rom_size) ? MIN(size, vdev->rom_size - addr) : 0);

    switch (size) {
    case 1:
        data = val.byte;
        break;
    case 2:
        data = le16_to_cpu(val.word);
        break;
    case 4:
        data = le32_to_cpu(val.dword);
        break;
    default:
        hw_error("vfio: unsupported read size, %d bytes\n", size);
        break;
    }

    trace_vfio_rom_read(vdev->host.domain, vdev->host.bus,
                        vdev->host.slot, vdev->host.function,
                        addr, size, data);

    return data;
}

static void vfio_rom_write(void *opaque, hwaddr addr,
                           uint64_t data, unsigned size)
{
}

static const MemoryRegionOps vfio_rom_ops = {
    .read = vfio_rom_read,
    .write = vfio_rom_write,
    .endianness = DEVICE_LITTLE_ENDIAN,
};

static bool vfio_blacklist_opt_rom(VFIODevice *vdev)
{
    PCIDevice *pdev = &vdev->pdev;
    uint16_t vendor_id, device_id;
    int count = 0;

    vendor_id = pci_get_word(pdev->config + PCI_VENDOR_ID);
    device_id = pci_get_word(pdev->config + PCI_DEVICE_ID);

    while (count < ARRAY_SIZE(romblacklist)) {
        if (romblacklist[count].vendor_id == vendor_id &&
            romblacklist[count].device_id == device_id) {
                return true;
        }
        count++;
    }

    return false;
}

static void vfio_pci_size_rom(VFIODevice *vdev)
{
    uint32_t orig, size = cpu_to_le32((uint32_t)PCI_ROM_ADDRESS_MASK);
    off_t offset = vdev->config_offset + PCI_ROM_ADDRESS;
    DeviceState *dev = DEVICE(vdev);
    char name[32];

    if (vdev->pdev.romfile || !vdev->pdev.rom_bar) {
        /* Since pci handles romfile, just print a message and return */
        if (vfio_blacklist_opt_rom(vdev) && vdev->pdev.romfile) {
            error_printf("Warning : Device at %04x:%02x:%02x.%x "
                         "is known to cause system instability issues during "
                         "option rom execution. "
                         "Proceeding anyway since user specified romfile\n",
                         vdev->host.domain, vdev->host.bus, vdev->host.slot,
                         vdev->host.function);
        }
        return;
    }

    /*
     * Use the same size ROM BAR as the physical device.  The contents
     * will get filled in later when the guest tries to read it.
     */
    if (pread(vdev->fd, &orig, 4, offset) != 4 ||
        pwrite(vdev->fd, &size, 4, offset) != 4 ||
        pread(vdev->fd, &size, 4, offset) != 4 ||
        pwrite(vdev->fd, &orig, 4, offset) != 4) {
        error_report("%s(%04x:%02x:%02x.%x) failed: %m",
                     __func__, vdev->host.domain, vdev->host.bus,
                     vdev->host.slot, vdev->host.function);
        return;
    }

    size = ~(le32_to_cpu(size) & PCI_ROM_ADDRESS_MASK) + 1;

    if (!size) {
        return;
    }

    if (vfio_blacklist_opt_rom(vdev)) {
        if (dev->opts && qemu_opt_get(dev->opts, "rombar")) {
            error_printf("Warning : Device at %04x:%02x:%02x.%x "
                         "is known to cause system instability issues during "
                         "option rom execution. "
                         "Proceeding anyway since user specified non zero value for "
                         "rombar\n",
                         vdev->host.domain, vdev->host.bus, vdev->host.slot,
                         vdev->host.function);
        } else {
            error_printf("Warning : Rom loading for device at "
                         "%04x:%02x:%02x.%x has been disabled due to "
                         "system instability issues. "
                         "Specify rombar=1 or romfile to force\n",
                         vdev->host.domain, vdev->host.bus, vdev->host.slot,
                         vdev->host.function);
            return;
        }
    }

    trace_vfio_pci_size_rom(vdev->host.domain, vdev->host.bus,
                            vdev->host.slot, vdev->host.function,
                            size);

    snprintf(name, sizeof(name), "vfio[%04x:%02x:%02x.%x].rom",
             vdev->host.domain, vdev->host.bus, vdev->host.slot,
             vdev->host.function);

    memory_region_init_io(&vdev->pdev.rom, OBJECT(vdev),
                          &vfio_rom_ops, vdev, name, size);

    pci_register_bar(&vdev->pdev, PCI_ROM_SLOT,
                     PCI_BASE_ADDRESS_SPACE_MEMORY, &vdev->pdev.rom);

    vdev->pdev.has_rom = true;
    vdev->rom_read_failed = false;
}

static void vfio_vga_write(void *opaque, hwaddr addr,
                           uint64_t data, unsigned size)
{
    VFIOVGARegion *region = opaque;
    VFIOVGA *vga = container_of(region, VFIOVGA, region[region->nr]);
    union {
        uint8_t byte;
        uint16_t word;
        uint32_t dword;
        uint64_t qword;
    } buf;
    off_t offset = vga->fd_offset + region->offset + addr;

    switch (size) {
    case 1:
        buf.byte = data;
        break;
    case 2:
        buf.word = cpu_to_le16(data);
        break;
    case 4:
        buf.dword = cpu_to_le32(data);
        break;
    default:
        hw_error("vfio: unsupported write size, %d bytes", size);
        break;
    }

    if (pwrite(vga->fd, &buf, size, offset) != size) {
        error_report("%s(,0x%"HWADDR_PRIx", 0x%"PRIx64", %d) failed: %m",
                     __func__, region->offset + addr, data, size);
    }

    trace_vfio_vga_write(region->offset + addr, data, size);
}

static uint64_t vfio_vga_read(void *opaque, hwaddr addr, unsigned size)
{
    VFIOVGARegion *region = opaque;
    VFIOVGA *vga = container_of(region, VFIOVGA, region[region->nr]);
    union {
        uint8_t byte;
        uint16_t word;
        uint32_t dword;
        uint64_t qword;
    } buf;
    uint64_t data = 0;
    off_t offset = vga->fd_offset + region->offset + addr;

    if (pread(vga->fd, &buf, size, offset) != size) {
        error_report("%s(,0x%"HWADDR_PRIx", %d) failed: %m",
                     __func__, region->offset + addr, size);
        return (uint64_t)-1;
    }

    switch (size) {
    case 1:
        data = buf.byte;
        break;
    case 2:
        data = le16_to_cpu(buf.word);
        break;
    case 4:
        data = le32_to_cpu(buf.dword);
        break;
    default:
        hw_error("vfio: unsupported read size, %d bytes", size);
        break;
    }

    trace_vfio_vga_read(region->offset + addr, size, data);

    return data;
}

static const MemoryRegionOps vfio_vga_ops = {
    .read = vfio_vga_read,
    .write = vfio_vga_write,
    .endianness = DEVICE_LITTLE_ENDIAN,
};

/*
 * Device specific quirks
 */

/* Is range1 fully contained within range2?  */
static bool vfio_range_contained(uint64_t first1, uint64_t len1,
                                 uint64_t first2, uint64_t len2) {
    return (first1 >= first2 && first1 + len1 <= first2 + len2);
}

static bool vfio_flags_enabled(uint8_t flags, uint8_t mask)
{
    return (mask && (flags & mask) == mask);
}

static uint64_t vfio_generic_window_quirk_read(void *opaque,
                                               hwaddr addr, unsigned size)
{
    VFIOQuirk *quirk = opaque;
    VFIODevice *vdev = quirk->vdev;
    uint64_t data;

    if (vfio_flags_enabled(quirk->data.flags, quirk->data.read_flags) &&
        ranges_overlap(addr, size,
                       quirk->data.data_offset, quirk->data.data_size)) {
        hwaddr offset = addr - quirk->data.data_offset;

        if (!vfio_range_contained(addr, size, quirk->data.data_offset,
                                  quirk->data.data_size)) {
            hw_error("%s: window data read not fully contained: %s",
                     __func__, memory_region_name(&quirk->mem));
        }

        data = vfio_pci_read_config(&vdev->pdev,
                                    quirk->data.address_val + offset, size);

        trace_vfio_generic_window_quirk_read(memory_region_name(&quirk->mem),
                                             vdev->host.domain,
                                             vdev->host.bus,
                                             vdev->host.slot,
                                             vdev->host.function,
                                             quirk->data.bar,
                                             addr, size, data);
    } else {
        data = vfio_bar_read(&vdev->bars[quirk->data.bar],
                             addr + quirk->data.base_offset, size);
    }

    return data;
}

static void vfio_generic_window_quirk_write(void *opaque, hwaddr addr,
                                            uint64_t data, unsigned size)
{
    VFIOQuirk *quirk = opaque;
    VFIODevice *vdev = quirk->vdev;

    if (ranges_overlap(addr, size,
                       quirk->data.address_offset, quirk->data.address_size)) {

        if (addr != quirk->data.address_offset) {
            hw_error("%s: offset write into address window: %s",
                     __func__, memory_region_name(&quirk->mem));
        }

        if ((data & ~quirk->data.address_mask) == quirk->data.address_match) {
            quirk->data.flags |= quirk->data.write_flags |
                                 quirk->data.read_flags;
            quirk->data.address_val = data & quirk->data.address_mask;
        } else {
            quirk->data.flags &= ~(quirk->data.write_flags |
                                   quirk->data.read_flags);
        }
    }

    if (vfio_flags_enabled(quirk->data.flags, quirk->data.write_flags) &&
        ranges_overlap(addr, size,
                       quirk->data.data_offset, quirk->data.data_size)) {
        hwaddr offset = addr - quirk->data.data_offset;

        if (!vfio_range_contained(addr, size, quirk->data.data_offset,
                                  quirk->data.data_size)) {
            hw_error("%s: window data write not fully contained: %s",
                     __func__, memory_region_name(&quirk->mem));
        }

        vfio_pci_write_config(&vdev->pdev,
                              quirk->data.address_val + offset, data, size);

        trace_vfio_generic_window_quirk_write(memory_region_name(&quirk->mem),
                                             vdev->host.domain,
                                             vdev->host.bus,
                                             vdev->host.slot,
                                             vdev->host.function,
                                             quirk->data.bar,
                                             addr, data, size);
        return;
    }

    vfio_bar_write(&vdev->bars[quirk->data.bar],
                   addr + quirk->data.base_offset, data, size);
}

static const MemoryRegionOps vfio_generic_window_quirk = {
    .read = vfio_generic_window_quirk_read,
    .write = vfio_generic_window_quirk_write,
    .endianness = DEVICE_LITTLE_ENDIAN,
};

static uint64_t vfio_generic_quirk_read(void *opaque,
                                        hwaddr addr, unsigned size)
{
    VFIOQuirk *quirk = opaque;
    VFIODevice *vdev = quirk->vdev;
    hwaddr base = quirk->data.address_match & TARGET_PAGE_MASK;
    hwaddr offset = quirk->data.address_match & ~TARGET_PAGE_MASK;
    uint64_t data;

    if (vfio_flags_enabled(quirk->data.flags, quirk->data.read_flags) &&
        ranges_overlap(addr, size, offset, quirk->data.address_mask + 1)) {
        if (!vfio_range_contained(addr, size, offset,
                                  quirk->data.address_mask + 1)) {
            hw_error("%s: read not fully contained: %s",
                     __func__, memory_region_name(&quirk->mem));
        }

        data = vfio_pci_read_config(&vdev->pdev, addr - offset, size);

        trace_vfio_generic_quirk_read(memory_region_name(&quirk->mem),
                                      vdev->host.domain,
                                      vdev->host.bus,
                                      vdev->host.slot,
                                      vdev->host.function,
                                      quirk->data.bar,
                                      addr + base, size, data);
    } else {
        data = vfio_bar_read(&vdev->bars[quirk->data.bar], addr + base, size);
    }

    return data;
}

static void vfio_generic_quirk_write(void *opaque, hwaddr addr,
                                     uint64_t data, unsigned size)
{
    VFIOQuirk *quirk = opaque;
    VFIODevice *vdev = quirk->vdev;
    hwaddr base = quirk->data.address_match & TARGET_PAGE_MASK;
    hwaddr offset = quirk->data.address_match & ~TARGET_PAGE_MASK;

    if (vfio_flags_enabled(quirk->data.flags, quirk->data.write_flags) &&
        ranges_overlap(addr, size, offset, quirk->data.address_mask + 1)) {
        if (!vfio_range_contained(addr, size, offset,
                                  quirk->data.address_mask + 1)) {
            hw_error("%s: write not fully contained: %s",
                     __func__, memory_region_name(&quirk->mem));
        }

        vfio_pci_write_config(&vdev->pdev, addr - offset, data, size);

        trace_vfio_generic_quirk_write(memory_region_name(&quirk->mem),
                                       vdev->host.domain,
                                       vdev->host.bus,
                                       vdev->host.slot,
                                       vdev->host.function,
                                       quirk->data.bar,
                                       addr + base, data, size);
    } else {
        vfio_bar_write(&vdev->bars[quirk->data.bar], addr + base, data, size);
    }
}

static const MemoryRegionOps vfio_generic_quirk = {
    .read = vfio_generic_quirk_read,
    .write = vfio_generic_quirk_write,
    .endianness = DEVICE_LITTLE_ENDIAN,
};

#define PCI_VENDOR_ID_ATI               0x1002

/*
 * Radeon HD cards (HD5450 & HD7850) report the upper byte of the I/O port BAR
 * through VGA register 0x3c3.  On newer cards, the I/O port BAR is always
 * BAR4 (older cards like the X550 used BAR1, but we don't care to support
 * those).  Note that on bare metal, a read of 0x3c3 doesn't always return the
 * I/O port BAR address.  Originally this was coded to return the virtual BAR
 * address only if the physical register read returns the actual BAR address,
 * but users have reported greater success if we return the virtual address
 * unconditionally.
 */
static uint64_t vfio_ati_3c3_quirk_read(void *opaque,
                                        hwaddr addr, unsigned size)
{
    VFIOQuirk *quirk = opaque;
    VFIODevice *vdev = quirk->vdev;
    uint64_t data = vfio_pci_read_config(&vdev->pdev,
                                         PCI_BASE_ADDRESS_0 + (4 * 4) + 1,
                                         size);
    trace_vfio_ati_3c3_quirk_read(data);

    return data;
}

static const MemoryRegionOps vfio_ati_3c3_quirk = {
    .read = vfio_ati_3c3_quirk_read,
    .endianness = DEVICE_LITTLE_ENDIAN,
};

static void vfio_vga_probe_ati_3c3_quirk(VFIODevice *vdev)
{
    PCIDevice *pdev = &vdev->pdev;
    VFIOQuirk *quirk;

    if (pci_get_word(pdev->config + PCI_VENDOR_ID) != PCI_VENDOR_ID_ATI) {
        return;
    }

    /*
     * As long as the BAR is >= 256 bytes it will be aligned such that the
     * lower byte is always zero.  Filter out anything else, if it exists.
     */
    if (!vdev->bars[4].ioport || vdev->bars[4].size < 256) {
        return;
    }

    quirk = g_malloc0(sizeof(*quirk));
    quirk->vdev = vdev;

    memory_region_init_io(&quirk->mem, OBJECT(vdev), &vfio_ati_3c3_quirk, quirk,
                          "vfio-ati-3c3-quirk", 1);
    memory_region_add_subregion(&vdev->vga.region[QEMU_PCI_VGA_IO_HI].mem,
                                3 /* offset 3 bytes from 0x3c0 */, &quirk->mem);

    QLIST_INSERT_HEAD(&vdev->vga.region[QEMU_PCI_VGA_IO_HI].quirks,
                      quirk, next);

    trace_vfio_vga_probe_ati_3c3_quirk(vdev->host.domain, vdev->host.bus,
                                       vdev->host.slot, vdev->host.function);
}

/*
 * Newer ATI/AMD devices, including HD5450 and HD7850, have a window to PCI
 * config space through MMIO BAR2 at offset 0x4000.  Nothing seems to access
 * the MMIO space directly, but a window to this space is provided through
 * I/O port BAR4.  Offset 0x0 is the address register and offset 0x4 is the
 * data register.  When the address is programmed to a range of 0x4000-0x4fff
 * PCI configuration space is available.  Experimentation seems to indicate
 * that only read-only access is provided, but we drop writes when the window
 * is enabled to config space nonetheless.
 */
static void vfio_probe_ati_bar4_window_quirk(VFIODevice *vdev, int nr)
{
    PCIDevice *pdev = &vdev->pdev;
    VFIOQuirk *quirk;

    if (!vdev->has_vga || nr != 4 ||
        pci_get_word(pdev->config + PCI_VENDOR_ID) != PCI_VENDOR_ID_ATI) {
        return;
    }

    quirk = g_malloc0(sizeof(*quirk));
    quirk->vdev = vdev;
    quirk->data.address_size = 4;
    quirk->data.data_offset = 4;
    quirk->data.data_size = 4;
    quirk->data.address_match = 0x4000;
    quirk->data.address_mask = PCIE_CONFIG_SPACE_SIZE - 1;
    quirk->data.bar = nr;
    quirk->data.read_flags = quirk->data.write_flags = 1;

    memory_region_init_io(&quirk->mem, OBJECT(vdev),
                          &vfio_generic_window_quirk, quirk,
                          "vfio-ati-bar4-window-quirk", 8);
    memory_region_add_subregion_overlap(&vdev->bars[nr].mem,
                          quirk->data.base_offset, &quirk->mem, 1);

    QLIST_INSERT_HEAD(&vdev->bars[nr].quirks, quirk, next);

    trace_vfio_probe_ati_bar4_window_quirk(vdev->host.domain,
                                           vdev->host.bus,
                                           vdev->host.slot,
                                           vdev->host.function);
}

#define PCI_VENDOR_ID_REALTEK 0x10ec

/*
 * RTL8168 devices have a backdoor that can access the MSI-X table.  At BAR2
 * offset 0x70 there is a dword data register, offset 0x74 is a dword address
 * register.  According to the Linux r8169 driver, the MSI-X table is addressed
 * when the "type" portion of the address register is set to 0x1.  This appears
 * to be bits 16:30.  Bit 31 is both a write indicator and some sort of
 * "address latched" indicator.  Bits 12:15 are a mask field, which we can
 * ignore because the MSI-X table should always be accessed as a dword (full
 * mask).  Bits 0:11 is offset within the type.
 *
 * Example trace:
 *
 * Read from MSI-X table offset 0
 * vfio: vfio_bar_write(0000:05:00.0:BAR2+0x74, 0x1f000, 4) // store read addr
 * vfio: vfio_bar_read(0000:05:00.0:BAR2+0x74, 4) = 0x8001f000 // latch
 * vfio: vfio_bar_read(0000:05:00.0:BAR2+0x70, 4) = 0xfee00398 // read data
 *
 * Write 0xfee00000 to MSI-X table offset 0
 * vfio: vfio_bar_write(0000:05:00.0:BAR2+0x70, 0xfee00000, 4) // write data
 * vfio: vfio_bar_write(0000:05:00.0:BAR2+0x74, 0x8001f000, 4) // do write
 * vfio: vfio_bar_read(0000:05:00.0:BAR2+0x74, 4) = 0x1f000 // complete
 */

static uint64_t vfio_rtl8168_window_quirk_read(void *opaque,
                                               hwaddr addr, unsigned size)
{
    VFIOQuirk *quirk = opaque;
    VFIODevice *vdev = quirk->vdev;

    switch (addr) {
    case 4: /* address */
        if (quirk->data.flags) {
            trace_vfio_rtl8168_window_quirk_read_fake(
                    memory_region_name(&quirk->mem),
                    vdev->host.domain, vdev->host.bus,
                    vdev->host.slot, vdev->host.function);

            return quirk->data.address_match ^ 0x10000000U;
        }
        break;
    case 0: /* data */
        if (quirk->data.flags) {
            uint64_t val;

            trace_vfio_rtl8168_window_quirk_read_table(
                    memory_region_name(&quirk->mem),
                    vdev->host.domain, vdev->host.bus,
                    vdev->host.slot, vdev->host.function
               );

            if (!(vdev->pdev.cap_present & QEMU_PCI_CAP_MSIX)) {
                return 0;
            }

            io_mem_read(&vdev->pdev.msix_table_mmio,
                        (hwaddr)(quirk->data.address_match & 0xfff),
                        &val, size);
            return val;
        }
    }

    trace_vfio_rtl8168_window_quirk_read_direct(
                        memory_region_name(&quirk->mem),
                        vdev->host.domain, vdev->host.bus,
                        vdev->host.slot, vdev->host.function);

    return vfio_bar_read(&vdev->bars[quirk->data.bar], addr + 0x70, size);
}

static void vfio_rtl8168_window_quirk_write(void *opaque, hwaddr addr,
                                            uint64_t data, unsigned size)
{
    VFIOQuirk *quirk = opaque;
    VFIODevice *vdev = quirk->vdev;

    switch (addr) {
    case 4: /* address */
        if ((data & 0x7fff0000) == 0x10000) {
            if (data & 0x10000000U &&
                vdev->pdev.cap_present & QEMU_PCI_CAP_MSIX) {

                trace_vfio_rtl8168_window_quirk_write_table(
                        memory_region_name(&quirk->mem),
                        vdev->host.domain, vdev->host.bus,
                        vdev->host.slot, vdev->host.function);

                io_mem_write(&vdev->pdev.msix_table_mmio,
                             (hwaddr)(quirk->data.address_match & 0xfff),
                             data, size);
            }

            quirk->data.flags = 1;
            quirk->data.address_match = data;

            return;
        }
        quirk->data.flags = 0;
        break;
    case 0: /* data */
        quirk->data.address_mask = data;
        break;
    }

    trace_vfio_rtl8168_window_quirk_write_direct(
            memory_region_name(&quirk->mem),
            vdev->host.domain, vdev->host.bus,
            vdev->host.slot, vdev->host.function);

    vfio_bar_write(&vdev->bars[quirk->data.bar], addr + 0x70, data, size);
}

static const MemoryRegionOps vfio_rtl8168_window_quirk = {
    .read = vfio_rtl8168_window_quirk_read,
    .write = vfio_rtl8168_window_quirk_write,
    .valid = {
        .min_access_size = 4,
        .max_access_size = 4,
        .unaligned = false,
    },
    .endianness = DEVICE_LITTLE_ENDIAN,
};

static void vfio_probe_rtl8168_bar2_window_quirk(VFIODevice *vdev, int nr)
{
    PCIDevice *pdev = &vdev->pdev;
    VFIOQuirk *quirk;

    if (pci_get_word(pdev->config + PCI_VENDOR_ID) != PCI_VENDOR_ID_REALTEK ||
        pci_get_word(pdev->config + PCI_DEVICE_ID) != 0x8168 || nr != 2) {
        return;
    }

    quirk = g_malloc0(sizeof(*quirk));
    quirk->vdev = vdev;
    quirk->data.bar = nr;

    memory_region_init_io(&quirk->mem, OBJECT(vdev), &vfio_rtl8168_window_quirk,
                          quirk, "vfio-rtl8168-window-quirk", 8);
    memory_region_add_subregion_overlap(&vdev->bars[nr].mem,
                                        0x70, &quirk->mem, 1);

    QLIST_INSERT_HEAD(&vdev->bars[nr].quirks, quirk, next);

    trace_vfio_probe_rtl8168_bar2_window_quirk(vdev->host.domain,
                                               vdev->host.bus,
                                               vdev->host.slot,
                                               vdev->host.function);
}
/*
 * Trap the BAR2 MMIO window to config space as well.
 */
static void vfio_probe_ati_bar2_4000_quirk(VFIODevice *vdev, int nr)
{
    PCIDevice *pdev = &vdev->pdev;
    VFIOQuirk *quirk;

    /* Only enable on newer devices where BAR2 is 64bit */
    if (!vdev->has_vga || nr != 2 || !vdev->bars[2].mem64 ||
        pci_get_word(pdev->config + PCI_VENDOR_ID) != PCI_VENDOR_ID_ATI) {
        return;
    }

    quirk = g_malloc0(sizeof(*quirk));
    quirk->vdev = vdev;
    quirk->data.flags = quirk->data.read_flags = quirk->data.write_flags = 1;
    quirk->data.address_match = 0x4000;
    quirk->data.address_mask = PCIE_CONFIG_SPACE_SIZE - 1;
    quirk->data.bar = nr;

    memory_region_init_io(&quirk->mem, OBJECT(vdev), &vfio_generic_quirk, quirk,
                          "vfio-ati-bar2-4000-quirk",
                          TARGET_PAGE_ALIGN(quirk->data.address_mask + 1));
    memory_region_add_subregion_overlap(&vdev->bars[nr].mem,
                          quirk->data.address_match & TARGET_PAGE_MASK,
                          &quirk->mem, 1);

    QLIST_INSERT_HEAD(&vdev->bars[nr].quirks, quirk, next);

    trace_vfio_probe_ati_bar2_4000_quirk(vdev->host.domain,
                                         vdev->host.bus,
                                         vdev->host.slot,
                                         vdev->host.function);
}

/*
 * Older ATI/AMD cards like the X550 have a similar window to that above.
 * I/O port BAR1 provides a window to a mirror of PCI config space located
 * in BAR2 at offset 0xf00.  We don't care to support such older cards, but
 * note it for future reference.
 */

#define PCI_VENDOR_ID_NVIDIA                    0x10de

/*
 * Nvidia has several different methods to get to config space, the
 * nouveu project has several of these documented here:
 * https://github.com/pathscale/envytools/tree/master/hwdocs
 *
 * The first quirk is actually not documented in envytools and is found
 * on 10de:01d1 (NVIDIA Corporation G72 [GeForce 7300 LE]).  This is an
 * NV46 chipset.  The backdoor uses the legacy VGA I/O ports to access
 * the mirror of PCI config space found at BAR0 offset 0x1800.  The access
 * sequence first writes 0x338 to I/O port 0x3d4.  The target offset is
 * then written to 0x3d0.  Finally 0x538 is written for a read and 0x738
 * is written for a write to 0x3d4.  The BAR0 offset is then accessible
 * through 0x3d0.  This quirk doesn't seem to be necessary on newer cards
 * that use the I/O port BAR5 window but it doesn't hurt to leave it.
 */
enum {
    NV_3D0_NONE = 0,
    NV_3D0_SELECT,
    NV_3D0_WINDOW,
    NV_3D0_READ,
    NV_3D0_WRITE,
};

static uint64_t vfio_nvidia_3d0_quirk_read(void *opaque,
                                           hwaddr addr, unsigned size)
{
    VFIOQuirk *quirk = opaque;
    VFIODevice *vdev = quirk->vdev;
    PCIDevice *pdev = &vdev->pdev;
    uint64_t data = vfio_vga_read(&vdev->vga.region[QEMU_PCI_VGA_IO_HI],
                                  addr + quirk->data.base_offset, size);

    if (quirk->data.flags == NV_3D0_READ && addr == quirk->data.data_offset) {
        data = vfio_pci_read_config(pdev, quirk->data.address_val, size);
        trace_vfio_nvidia_3d0_quirk_read(size, data);
    }

    quirk->data.flags = NV_3D0_NONE;

    return data;
}

static void vfio_nvidia_3d0_quirk_write(void *opaque, hwaddr addr,
                                        uint64_t data, unsigned size)
{
    VFIOQuirk *quirk = opaque;
    VFIODevice *vdev = quirk->vdev;
    PCIDevice *pdev = &vdev->pdev;

    switch (quirk->data.flags) {
    case NV_3D0_NONE:
        if (addr == quirk->data.address_offset && data == 0x338) {
            quirk->data.flags = NV_3D0_SELECT;
        }
        break;
    case NV_3D0_SELECT:
        quirk->data.flags = NV_3D0_NONE;
        if (addr == quirk->data.data_offset &&
            (data & ~quirk->data.address_mask) == quirk->data.address_match) {
            quirk->data.flags = NV_3D0_WINDOW;
            quirk->data.address_val = data & quirk->data.address_mask;
        }
        break;
    case NV_3D0_WINDOW:
        quirk->data.flags = NV_3D0_NONE;
        if (addr == quirk->data.address_offset) {
            if (data == 0x538) {
                quirk->data.flags = NV_3D0_READ;
            } else if (data == 0x738) {
                quirk->data.flags = NV_3D0_WRITE;
            }
        }
        break;
    case NV_3D0_WRITE:
        quirk->data.flags = NV_3D0_NONE;
        if (addr == quirk->data.data_offset) {
            vfio_pci_write_config(pdev, quirk->data.address_val, data, size);
            trace_vfio_nvidia_3d0_quirk_write(data, size);
            return;
        }
        break;
    }

    vfio_vga_write(&vdev->vga.region[QEMU_PCI_VGA_IO_HI],
                   addr + quirk->data.base_offset, data, size);
}

static const MemoryRegionOps vfio_nvidia_3d0_quirk = {
    .read = vfio_nvidia_3d0_quirk_read,
    .write = vfio_nvidia_3d0_quirk_write,
    .endianness = DEVICE_LITTLE_ENDIAN,
};

static void vfio_vga_probe_nvidia_3d0_quirk(VFIODevice *vdev)
{
    PCIDevice *pdev = &vdev->pdev;
    VFIOQuirk *quirk;

    if (pci_get_word(pdev->config + PCI_VENDOR_ID) != PCI_VENDOR_ID_NVIDIA ||
        !vdev->bars[1].size) {
        return;
    }

    quirk = g_malloc0(sizeof(*quirk));
    quirk->vdev = vdev;
    quirk->data.base_offset = 0x10;
    quirk->data.address_offset = 4;
    quirk->data.address_size = 2;
    quirk->data.address_match = 0x1800;
    quirk->data.address_mask = PCI_CONFIG_SPACE_SIZE - 1;
    quirk->data.data_offset = 0;
    quirk->data.data_size = 4;

    memory_region_init_io(&quirk->mem, OBJECT(vdev), &vfio_nvidia_3d0_quirk,
                          quirk, "vfio-nvidia-3d0-quirk", 6);
    memory_region_add_subregion(&vdev->vga.region[QEMU_PCI_VGA_IO_HI].mem,
                                quirk->data.base_offset, &quirk->mem);

    QLIST_INSERT_HEAD(&vdev->vga.region[QEMU_PCI_VGA_IO_HI].quirks,
                      quirk, next);

    trace_vfio_vga_probe_nvidia_3d0_quirk(vdev->host.domain,
                                          vdev->host.bus,
                                          vdev->host.slot,
                                          vdev->host.function);
}

/*
 * The second quirk is documented in envytools.  The I/O port BAR5 is just
 * a set of address/data ports to the MMIO BARs.  The BAR we care about is
 * again BAR0.  This backdoor is apparently a bit newer than the one above
 * so we need to not only trap 256 bytes @0x1800, but all of PCI config
 * space, including extended space is available at the 4k @0x88000.
 */
enum {
    NV_BAR5_ADDRESS = 0x1,
    NV_BAR5_ENABLE = 0x2,
    NV_BAR5_MASTER = 0x4,
    NV_BAR5_VALID = 0x7,
};

static void vfio_nvidia_bar5_window_quirk_write(void *opaque, hwaddr addr,
                                                uint64_t data, unsigned size)
{
    VFIOQuirk *quirk = opaque;

    switch (addr) {
    case 0x0:
        if (data & 0x1) {
            quirk->data.flags |= NV_BAR5_MASTER;
        } else {
            quirk->data.flags &= ~NV_BAR5_MASTER;
        }
        break;
    case 0x4:
        if (data & 0x1) {
            quirk->data.flags |= NV_BAR5_ENABLE;
        } else {
            quirk->data.flags &= ~NV_BAR5_ENABLE;
        }
        break;
    case 0x8:
        if (quirk->data.flags & NV_BAR5_MASTER) {
            if ((data & ~0xfff) == 0x88000) {
                quirk->data.flags |= NV_BAR5_ADDRESS;
                quirk->data.address_val = data & 0xfff;
            } else if ((data & ~0xff) == 0x1800) {
                quirk->data.flags |= NV_BAR5_ADDRESS;
                quirk->data.address_val = data & 0xff;
            } else {
                quirk->data.flags &= ~NV_BAR5_ADDRESS;
            }
        }
        break;
    }

    vfio_generic_window_quirk_write(opaque, addr, data, size);
}

static const MemoryRegionOps vfio_nvidia_bar5_window_quirk = {
    .read = vfio_generic_window_quirk_read,
    .write = vfio_nvidia_bar5_window_quirk_write,
    .valid.min_access_size = 4,
    .endianness = DEVICE_LITTLE_ENDIAN,
};

static void vfio_probe_nvidia_bar5_window_quirk(VFIODevice *vdev, int nr)
{
    PCIDevice *pdev = &vdev->pdev;
    VFIOQuirk *quirk;

    if (!vdev->has_vga || nr != 5 ||
        pci_get_word(pdev->config + PCI_VENDOR_ID) != PCI_VENDOR_ID_NVIDIA) {
        return;
    }

    quirk = g_malloc0(sizeof(*quirk));
    quirk->vdev = vdev;
    quirk->data.read_flags = quirk->data.write_flags = NV_BAR5_VALID;
    quirk->data.address_offset = 0x8;
    quirk->data.address_size = 0; /* actually 4, but avoids generic code */
    quirk->data.data_offset = 0xc;
    quirk->data.data_size = 4;
    quirk->data.bar = nr;

    memory_region_init_io(&quirk->mem, OBJECT(vdev),
                          &vfio_nvidia_bar5_window_quirk, quirk,
                          "vfio-nvidia-bar5-window-quirk", 16);
    memory_region_add_subregion_overlap(&vdev->bars[nr].mem, 0, &quirk->mem, 1);

    QLIST_INSERT_HEAD(&vdev->bars[nr].quirks, quirk, next);

    trace_vfio_probe_nvidia_bar5_window_quirk(vdev->host.domain,
                                              vdev->host.bus,
                                              vdev->host.slot,
                                              vdev->host.function);
}

static void vfio_nvidia_88000_quirk_write(void *opaque, hwaddr addr,
                                          uint64_t data, unsigned size)
{
    VFIOQuirk *quirk = opaque;
    VFIODevice *vdev = quirk->vdev;
    PCIDevice *pdev = &vdev->pdev;
    hwaddr base = quirk->data.address_match & TARGET_PAGE_MASK;

    vfio_generic_quirk_write(opaque, addr, data, size);

    /*
     * Nvidia seems to acknowledge MSI interrupts by writing 0xff to the
     * MSI capability ID register.  Both the ID and next register are
     * read-only, so we allow writes covering either of those to real hw.
     * NB - only fixed for the 0x88000 MMIO window.
     */
    if ((pdev->cap_present & QEMU_PCI_CAP_MSI) &&
        vfio_range_contained(addr, size, pdev->msi_cap, PCI_MSI_FLAGS)) {
        vfio_bar_write(&vdev->bars[quirk->data.bar], addr + base, data, size);
    }
}

static const MemoryRegionOps vfio_nvidia_88000_quirk = {
    .read = vfio_generic_quirk_read,
    .write = vfio_nvidia_88000_quirk_write,
    .endianness = DEVICE_LITTLE_ENDIAN,
};

/*
 * Finally, BAR0 itself.  We want to redirect any accesses to either
 * 0x1800 or 0x88000 through the PCI config space access functions.
 *
 * NB - quirk at a page granularity or else they don't seem to work when
 *      BARs are mmap'd
 *
 * Here's offset 0x88000...
 */
static void vfio_probe_nvidia_bar0_88000_quirk(VFIODevice *vdev, int nr)
{
    PCIDevice *pdev = &vdev->pdev;
    VFIOQuirk *quirk;
    uint16_t vendor, class;

    vendor = pci_get_word(pdev->config + PCI_VENDOR_ID);
    class = pci_get_word(pdev->config + PCI_CLASS_DEVICE);

    if (nr != 0 || vendor != PCI_VENDOR_ID_NVIDIA ||
        class != PCI_CLASS_DISPLAY_VGA) {
        return;
    }

    quirk = g_malloc0(sizeof(*quirk));
    quirk->vdev = vdev;
    quirk->data.flags = quirk->data.read_flags = quirk->data.write_flags = 1;
    quirk->data.address_match = 0x88000;
    quirk->data.address_mask = PCIE_CONFIG_SPACE_SIZE - 1;
    quirk->data.bar = nr;

    memory_region_init_io(&quirk->mem, OBJECT(vdev), &vfio_nvidia_88000_quirk,
                          quirk, "vfio-nvidia-bar0-88000-quirk",
                          TARGET_PAGE_ALIGN(quirk->data.address_mask + 1));
    memory_region_add_subregion_overlap(&vdev->bars[nr].mem,
                          quirk->data.address_match & TARGET_PAGE_MASK,
                          &quirk->mem, 1);

    QLIST_INSERT_HEAD(&vdev->bars[nr].quirks, quirk, next);

    trace_vfio_probe_nvidia_bar0_88000_quirk(vdev->host.domain,
                                             vdev->host.bus,
                                             vdev->host.slot,
                                             vdev->host.function);
}

/*
 * And here's the same for BAR0 offset 0x1800...
 */
static void vfio_probe_nvidia_bar0_1800_quirk(VFIODevice *vdev, int nr)
{
    PCIDevice *pdev = &vdev->pdev;
    VFIOQuirk *quirk;

    if (!vdev->has_vga || nr != 0 ||
        pci_get_word(pdev->config + PCI_VENDOR_ID) != PCI_VENDOR_ID_NVIDIA) {
        return;
    }

    /* Log the chipset ID */
    trace_vfio_probe_nvidia_bar0_1800_quirk_id(
            (unsigned int)(vfio_bar_read(&vdev->bars[0], 0, 4) >> 20) & 0xff);

    quirk = g_malloc0(sizeof(*quirk));
    quirk->vdev = vdev;
    quirk->data.flags = quirk->data.read_flags = quirk->data.write_flags = 1;
    quirk->data.address_match = 0x1800;
    quirk->data.address_mask = PCI_CONFIG_SPACE_SIZE - 1;
    quirk->data.bar = nr;

    memory_region_init_io(&quirk->mem, OBJECT(vdev), &vfio_generic_quirk, quirk,
                          "vfio-nvidia-bar0-1800-quirk",
                          TARGET_PAGE_ALIGN(quirk->data.address_mask + 1));
    memory_region_add_subregion_overlap(&vdev->bars[nr].mem,
                          quirk->data.address_match & TARGET_PAGE_MASK,
                          &quirk->mem, 1);

    QLIST_INSERT_HEAD(&vdev->bars[nr].quirks, quirk, next);

    trace_vfio_probe_nvidia_bar0_1800_quirk(vdev->host.domain,
                                            vdev->host.bus,
                                            vdev->host.slot,
                                            vdev->host.function);
}

/*
 * TODO - Some Nvidia devices provide config access to their companion HDA
 * device and even to their parent bridge via these config space mirrors.
 * Add quirks for those regions.
 */

/*
 * Common quirk probe entry points.
 */
static void vfio_vga_quirk_setup(VFIODevice *vdev)
{
    vfio_vga_probe_ati_3c3_quirk(vdev);
    vfio_vga_probe_nvidia_3d0_quirk(vdev);
}

static void vfio_vga_quirk_teardown(VFIODevice *vdev)
{
    int i;

    for (i = 0; i < ARRAY_SIZE(vdev->vga.region); i++) {
        while (!QLIST_EMPTY(&vdev->vga.region[i].quirks)) {
            VFIOQuirk *quirk = QLIST_FIRST(&vdev->vga.region[i].quirks);
            memory_region_del_subregion(&vdev->vga.region[i].mem, &quirk->mem);
            object_unparent(OBJECT(&quirk->mem));
            QLIST_REMOVE(quirk, next);
            g_free(quirk);
        }
    }
}

static void vfio_bar_quirk_setup(VFIODevice *vdev, int nr)
{
    vfio_probe_ati_bar4_window_quirk(vdev, nr);
    vfio_probe_ati_bar2_4000_quirk(vdev, nr);
    vfio_probe_nvidia_bar5_window_quirk(vdev, nr);
    vfio_probe_nvidia_bar0_88000_quirk(vdev, nr);
    vfio_probe_nvidia_bar0_1800_quirk(vdev, nr);
    vfio_probe_rtl8168_bar2_window_quirk(vdev, nr);
}

static void vfio_bar_quirk_teardown(VFIODevice *vdev, int nr)
{
    VFIOBAR *bar = &vdev->bars[nr];

    while (!QLIST_EMPTY(&bar->quirks)) {
        VFIOQuirk *quirk = QLIST_FIRST(&bar->quirks);
        memory_region_del_subregion(&bar->mem, &quirk->mem);
        object_unparent(OBJECT(&quirk->mem));
        QLIST_REMOVE(quirk, next);
        g_free(quirk);
    }
}

/*
 * PCI config space
 */
static uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len)
{
    VFIODevice *vdev = DO_UPCAST(VFIODevice, pdev, pdev);
    uint32_t emu_bits = 0, emu_val = 0, phys_val = 0, val;

    memcpy(&emu_bits, vdev->emulated_config_bits + addr, len);
    emu_bits = le32_to_cpu(emu_bits);

    if (emu_bits) {
        emu_val = pci_default_read_config(pdev, addr, len);
    }

    if (~emu_bits & (0xffffffffU >> (32 - len * 8))) {
        ssize_t ret;

        ret = pread(vdev->fd, &phys_val, len, vdev->config_offset + addr);
        if (ret != len) {
            error_report("%s(%04x:%02x:%02x.%x, 0x%x, 0x%x) failed: %m",
                         __func__, vdev->host.domain, vdev->host.bus,
                         vdev->host.slot, vdev->host.function, addr, len);
            return -errno;
        }
        phys_val = le32_to_cpu(phys_val);
    }

    val = (emu_val & emu_bits) | (phys_val & ~emu_bits);

    trace_vfio_pci_read_config(vdev->host.domain, vdev->host.bus,
                               vdev->host.slot, vdev->host.function,
                               addr, len, val);

    return val;
}

static void vfio_pci_write_config(PCIDevice *pdev, uint32_t addr,
                                  uint32_t val, int len)
{
    VFIODevice *vdev = DO_UPCAST(VFIODevice, pdev, pdev);
    uint32_t val_le = cpu_to_le32(val);

    trace_vfio_pci_write_config(vdev->host.domain, vdev->host.bus,
                                vdev->host.slot, vdev->host.function,
                                addr, val, len);

    /* Write everything to VFIO, let it filter out what we can't write */
    if (pwrite(vdev->fd, &val_le, len, vdev->config_offset + addr) != len) {
        error_report("%s(%04x:%02x:%02x.%x, 0x%x, 0x%x, 0x%x) failed: %m",
                     __func__, vdev->host.domain, vdev->host.bus,
                     vdev->host.slot, vdev->host.function, addr, val, len);
    }

    /* MSI/MSI-X Enabling/Disabling */
    if (pdev->cap_present & QEMU_PCI_CAP_MSI &&
        ranges_overlap(addr, len, pdev->msi_cap, vdev->msi_cap_size)) {
        int is_enabled, was_enabled = msi_enabled(pdev);

        pci_default_write_config(pdev, addr, val, len);

        is_enabled = msi_enabled(pdev);

        if (!was_enabled) {
            if (is_enabled) {
                vfio_enable_msi(vdev);
            }
        } else {
            if (!is_enabled) {
                vfio_disable_msi(vdev);
            } else {
                vfio_update_msi(vdev);
            }
        }
    } else if (pdev->cap_present & QEMU_PCI_CAP_MSIX &&
        ranges_overlap(addr, len, pdev->msix_cap, MSIX_CAP_LENGTH)) {
        int is_enabled, was_enabled = msix_enabled(pdev);

        pci_default_write_config(pdev, addr, val, len);

        is_enabled = msix_enabled(pdev);

        if (!was_enabled && is_enabled) {
            vfio_enable_msix(vdev);
        } else if (was_enabled && !is_enabled) {
            vfio_disable_msix(vdev);
        }
    } else {
        /* Write everything to QEMU to keep emulated bits correct */
        pci_default_write_config(pdev, addr, val, len);
    }
}

/*
 * DMA - Mapping and unmapping for the "type1" IOMMU interface used on x86
 */
static int vfio_dma_unmap(VFIOContainer *container,
                          hwaddr iova, ram_addr_t size)
{
    struct vfio_iommu_type1_dma_unmap unmap = {
        .argsz = sizeof(unmap),
        .flags = 0,
        .iova = iova,
        .size = size,
    };

    if (ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, &unmap)) {
        error_report("VFIO_UNMAP_DMA: %d\n", -errno);
        return -errno;
    }

    return 0;
}

static int vfio_dma_map(VFIOContainer *container, hwaddr iova,
                        ram_addr_t size, void *vaddr, bool readonly)
{
    struct vfio_iommu_type1_dma_map map = {
        .argsz = sizeof(map),
        .flags = VFIO_DMA_MAP_FLAG_READ,
        .vaddr = (__u64)(uintptr_t)vaddr,
        .iova = iova,
        .size = size,
    };

    if (!readonly) {
        map.flags |= VFIO_DMA_MAP_FLAG_WRITE;
    }

    /*
     * Try the mapping, if it fails with EBUSY, unmap the region and try
     * again.  This shouldn't be necessary, but we sometimes see it in
     * the the VGA ROM space.
     */
    if (ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0 ||
        (errno == EBUSY && vfio_dma_unmap(container, iova, size) == 0 &&
         ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0)) {
        return 0;
    }

    error_report("VFIO_MAP_DMA: %d\n", -errno);
    return -errno;
}

static bool vfio_listener_skipped_section(MemoryRegionSection *section)
{
    return (!memory_region_is_ram(section->mr) &&
            !memory_region_is_iommu(section->mr)) ||
           /*
            * Sizing an enabled 64-bit BAR can cause spurious mappings to
            * addresses in the upper part of the 64-bit address space.  These
            * are never accessed by the CPU and beyond the address width of
            * some IOMMU hardware.  TODO: VFIO should tell us the IOMMU width.
            */
           section->offset_within_address_space & (1ULL << 63);
}

static void vfio_iommu_map_notify(Notifier *n, void *data)
{
    VFIOGuestIOMMU *giommu = container_of(n, VFIOGuestIOMMU, n);
    VFIOContainer *container = giommu->container;
    IOMMUTLBEntry *iotlb = data;
    MemoryRegion *mr;
    hwaddr xlat;
    hwaddr len = iotlb->addr_mask + 1;
    void *vaddr;
    int ret;

    trace_vfio_iommu_map_notify(iotlb->iova,
                                iotlb->iova + iotlb->addr_mask);

    /*
     * The IOMMU TLB entry we have just covers translation through
     * this IOMMU to its immediate target.  We need to translate
     * it the rest of the way through to memory.
     */
    mr = address_space_translate(&address_space_memory,
                                 iotlb->translated_addr,
                                 &xlat, &len, iotlb->perm & IOMMU_WO);
    if (!memory_region_is_ram(mr)) {
        error_report("iommu map to non memory area %"HWADDR_PRIx"\n",
                xlat);
        return;
    }
    /*
     * Translation truncates length to the IOMMU page size,
     * check that it did not truncate too much.
     */
    if (len & iotlb->addr_mask) {
        error_report("iommu has granularity incompatible with target AS\n");
        return;
    }

    if ((iotlb->perm & IOMMU_RW) != IOMMU_NONE) {
        vaddr = memory_region_get_ram_ptr(mr) + xlat;

        ret = vfio_dma_map(container, iotlb->iova,
                           iotlb->addr_mask + 1, vaddr,
                           !(iotlb->perm & IOMMU_WO) || mr->readonly);
        if (ret) {
            error_report("vfio_dma_map(%p, 0x%"HWADDR_PRIx", "
                         "0x%"HWADDR_PRIx", %p) = %d (%m)",
                         container, iotlb->iova,
                         iotlb->addr_mask + 1, vaddr, ret);
        }
    } else {
        ret = vfio_dma_unmap(container, iotlb->iova, iotlb->addr_mask + 1);
        if (ret) {
            error_report("vfio_dma_unmap(%p, 0x%"HWADDR_PRIx", "
                         "0x%"HWADDR_PRIx") = %d (%m)",
                         container, iotlb->iova,
                         iotlb->addr_mask + 1, ret);
        }
    }
}

static void vfio_listener_region_add(MemoryListener *listener,
                                     MemoryRegionSection *section)
{
    VFIOContainer *container = container_of(listener, VFIOContainer,
                                            iommu_data.type1.listener);
    hwaddr iova, end;
    Int128 llend;
    void *vaddr;
    int ret;

    if (vfio_listener_skipped_section(section)) {
        trace_vfio_listener_region_add_skip(
                section->offset_within_address_space,
                section->offset_within_address_space +
                int128_get64(int128_sub(section->size, int128_one())));
        return;
    }

    if (unlikely((section->offset_within_address_space & ~TARGET_PAGE_MASK) !=
                 (section->offset_within_region & ~TARGET_PAGE_MASK))) {
        error_report("%s received unaligned region", __func__);
        return;
    }

    iova = TARGET_PAGE_ALIGN(section->offset_within_address_space);
    llend = int128_make64(section->offset_within_address_space);
    llend = int128_add(llend, section->size);
    llend = int128_and(llend, int128_exts64(TARGET_PAGE_MASK));

    if (int128_ge(int128_make64(iova), llend)) {
        return;
    }

    memory_region_ref(section->mr);

    if (memory_region_is_iommu(section->mr)) {
        VFIOGuestIOMMU *giommu;

        trace_vfio_listener_region_add_iommu(iova,
                    int128_get64(int128_sub(llend, int128_one())));
        /*
         * FIXME: We should do some checking to see if the
         * capabilities of the host VFIO IOMMU are adequate to model
         * the guest IOMMU
         *
         * FIXME: For VFIO iommu types which have KVM acceleration to
         * avoid bouncing all map/unmaps through qemu this way, this
         * would be the right place to wire that up (tell the KVM
         * device emulation the VFIO iommu handles to use).
         */
        /*
         * This assumes that the guest IOMMU is empty of
         * mappings at this point.
         *
         * One way of doing this is:
         * 1. Avoid sharing IOMMUs between emulated devices or different
         * IOMMU groups.
         * 2. Implement VFIO_IOMMU_ENABLE in the host kernel to fail if
         * there are some mappings in IOMMU.
         *
         * VFIO on SPAPR does that. Other IOMMU models may do that different,
         * they must make sure there are no existing mappings or
         * loop through existing mappings to map them into VFIO.
         */
        giommu = g_malloc0(sizeof(*giommu));
        giommu->iommu = section->mr;
        giommu->container = container;
        giommu->n.notify = vfio_iommu_map_notify;
        QLIST_INSERT_HEAD(&container->giommu_list, giommu, giommu_next);
        memory_region_register_iommu_notifier(giommu->iommu, &giommu->n);

        return;
    }

    /* Here we assume that memory_region_is_ram(section->mr)==true */

    end = int128_get64(llend);
    vaddr = memory_region_get_ram_ptr(section->mr) +
            section->offset_within_region +
            (iova - section->offset_within_address_space);

    trace_vfio_listener_region_add_ram(iova, end - 1, vaddr);

    ret = vfio_dma_map(container, iova, end - iova, vaddr, section->readonly);
    if (ret) {
        error_report("vfio_dma_map(%p, 0x%"HWADDR_PRIx", "
                     "0x%"HWADDR_PRIx", %p) = %d (%m)",
                     container, iova, end - iova, vaddr, ret);

        /*
         * On the initfn path, store the first error in the container so we
         * can gracefully fail.  Runtime, there's not much we can do other
         * than throw a hardware error.
         */
        if (!container->iommu_data.type1.initialized) {
            if (!container->iommu_data.type1.error) {
                container->iommu_data.type1.error = ret;
            }
        } else {
            hw_error("vfio: DMA mapping failed, unable to continue");
        }
    }
}

static void vfio_listener_region_del(MemoryListener *listener,
                                     MemoryRegionSection *section)
{
    VFIOContainer *container = container_of(listener, VFIOContainer,
                                            iommu_data.type1.listener);
    hwaddr iova, end;
    int ret;

    if (vfio_listener_skipped_section(section)) {
        trace_vfio_listener_region_del_skip(
                section->offset_within_address_space,
                section->offset_within_address_space +
                int128_get64(int128_sub(section->size, int128_one())));
        return;
    }

    if (unlikely((section->offset_within_address_space & ~TARGET_PAGE_MASK) !=
                 (section->offset_within_region & ~TARGET_PAGE_MASK))) {
        error_report("%s received unaligned region", __func__);
        return;
    }

    if (memory_region_is_iommu(section->mr)) {
        VFIOGuestIOMMU *giommu;

        QLIST_FOREACH(giommu, &container->giommu_list, giommu_next) {
            if (giommu->iommu == section->mr) {
                memory_region_unregister_iommu_notifier(&giommu->n);
                QLIST_REMOVE(giommu, giommu_next);
                g_free(giommu);
                break;
            }
        }

        /*
         * FIXME: We assume the one big unmap below is adequate to
         * remove any individual page mappings in the IOMMU which
         * might have been copied into VFIO. This works for a page table
         * based IOMMU where a big unmap flattens a large range of IO-PTEs.
         * That may not be true for all IOMMU types.
         */
    }

    iova = TARGET_PAGE_ALIGN(section->offset_within_address_space);
    end = (section->offset_within_address_space + int128_get64(section->size)) &
          TARGET_PAGE_MASK;

    if (iova >= end) {
        return;
    }

    trace_vfio_listener_region_del(iova, end - 1);

    ret = vfio_dma_unmap(container, iova, end - iova);
    memory_region_unref(section->mr);
    if (ret) {
        error_report("vfio_dma_unmap(%p, 0x%"HWADDR_PRIx", "
                     "0x%"HWADDR_PRIx") = %d (%m)",
                     container, iova, end - iova, ret);
    }
}

static MemoryListener vfio_memory_listener = {
    .region_add = vfio_listener_region_add,
    .region_del = vfio_listener_region_del,
};

static void vfio_listener_release(VFIOContainer *container)
{
    memory_listener_unregister(&container->iommu_data.type1.listener);
}

/*
 * Interrupt setup
 */
static void vfio_disable_interrupts(VFIODevice *vdev)
{
    switch (vdev->interrupt) {
    case VFIO_INT_INTx:
        vfio_disable_intx(vdev);
        break;
    case VFIO_INT_MSI:
        vfio_disable_msi(vdev);
        break;
    case VFIO_INT_MSIX:
        vfio_disable_msix(vdev);
        break;
    }
}

static int vfio_setup_msi(VFIODevice *vdev, int pos)
{
    uint16_t ctrl;
    bool msi_64bit, msi_maskbit;
    int ret, entries;

    if (pread(vdev->fd, &ctrl, sizeof(ctrl),
              vdev->config_offset + pos + PCI_CAP_FLAGS) != sizeof(ctrl)) {
        return -errno;
    }
    ctrl = le16_to_cpu(ctrl);

    msi_64bit = !!(ctrl & PCI_MSI_FLAGS_64BIT);
    msi_maskbit = !!(ctrl & PCI_MSI_FLAGS_MASKBIT);
    entries = 1 << ((ctrl & PCI_MSI_FLAGS_QMASK) >> 1);

    trace_vfio_setup_msi(vdev->host.domain, vdev->host.bus,
                         vdev->host.slot, vdev->host.function, pos);

    ret = msi_init(&vdev->pdev, pos, entries, msi_64bit, msi_maskbit);
    if (ret < 0) {
        if (ret == -ENOTSUP) {
            return 0;
        }
        error_report("vfio: msi_init failed");
        return ret;
    }
    vdev->msi_cap_size = 0xa + (msi_maskbit ? 0xa : 0) + (msi_64bit ? 0x4 : 0);

    return 0;
}

/*
 * We don't have any control over how pci_add_capability() inserts
 * capabilities into the chain.  In order to setup MSI-X we need a
 * MemoryRegion for the BAR.  In order to setup the BAR and not
 * attempt to mmap the MSI-X table area, which VFIO won't allow, we
 * need to first look for where the MSI-X table lives.  So we
 * unfortunately split MSI-X setup across two functions.
 */
static int vfio_early_setup_msix(VFIODevice *vdev)
{
    uint8_t pos;
    uint16_t ctrl;
    uint32_t table, pba;

    pos = pci_find_capability(&vdev->pdev, PCI_CAP_ID_MSIX);
    if (!pos) {
        return 0;
    }

    if (pread(vdev->fd, &ctrl, sizeof(ctrl),
              vdev->config_offset + pos + PCI_CAP_FLAGS) != sizeof(ctrl)) {
        return -errno;
    }

    if (pread(vdev->fd, &table, sizeof(table),
              vdev->config_offset + pos + PCI_MSIX_TABLE) != sizeof(table)) {
        return -errno;
    }

    if (pread(vdev->fd, &pba, sizeof(pba),
              vdev->config_offset + pos + PCI_MSIX_PBA) != sizeof(pba)) {
        return -errno;
    }

    ctrl = le16_to_cpu(ctrl);
    table = le32_to_cpu(table);
    pba = le32_to_cpu(pba);

    vdev->msix = g_malloc0(sizeof(*(vdev->msix)));
    vdev->msix->table_bar = table & PCI_MSIX_FLAGS_BIRMASK;
    vdev->msix->table_offset = table & ~PCI_MSIX_FLAGS_BIRMASK;
    vdev->msix->pba_bar = pba & PCI_MSIX_FLAGS_BIRMASK;
    vdev->msix->pba_offset = pba & ~PCI_MSIX_FLAGS_BIRMASK;
    vdev->msix->entries = (ctrl & PCI_MSIX_FLAGS_QSIZE) + 1;

    trace_vfio_early_setup_msix(vdev->host.domain, vdev->host.bus,
                                vdev->host.slot, vdev->host.function,
                                pos, vdev->msix->table_bar,
                                vdev->msix->table_offset,
                                vdev->msix->entries);

    return 0;
}

static int vfio_setup_msix(VFIODevice *vdev, int pos)
{
    int ret;

    ret = msix_init(&vdev->pdev, vdev->msix->entries,
                    &vdev->bars[vdev->msix->table_bar].mem,
                    vdev->msix->table_bar, vdev->msix->table_offset,
                    &vdev->bars[vdev->msix->pba_bar].mem,
                    vdev->msix->pba_bar, vdev->msix->pba_offset, pos);
    if (ret < 0) {
        if (ret == -ENOTSUP) {
            return 0;
        }
        error_report("vfio: msix_init failed");
        return ret;
    }

    return 0;
}

static void vfio_teardown_msi(VFIODevice *vdev)
{
    msi_uninit(&vdev->pdev);

    if (vdev->msix) {
        msix_uninit(&vdev->pdev, &vdev->bars[vdev->msix->table_bar].mem,
                    &vdev->bars[vdev->msix->pba_bar].mem);
    }
}

/*
 * Resource setup
 */
static void vfio_mmap_set_enabled(VFIODevice *vdev, bool enabled)
{
    int i;

    for (i = 0; i < PCI_ROM_SLOT; i++) {
        VFIOBAR *bar = &vdev->bars[i];

        if (!bar->size) {
            continue;
        }

        memory_region_set_enabled(&bar->mmap_mem, enabled);
        if (vdev->msix && vdev->msix->table_bar == i) {
            memory_region_set_enabled(&vdev->msix->mmap_mem, enabled);
        }
    }
}

static void vfio_unmap_bar(VFIODevice *vdev, int nr)
{
    VFIOBAR *bar = &vdev->bars[nr];

    if (!bar->size) {
        return;
    }

    vfio_bar_quirk_teardown(vdev, nr);

    memory_region_del_subregion(&bar->mem, &bar->mmap_mem);
    munmap(bar->mmap, memory_region_size(&bar->mmap_mem));

    if (vdev->msix && vdev->msix->table_bar == nr) {
        memory_region_del_subregion(&bar->mem, &vdev->msix->mmap_mem);
        munmap(vdev->msix->mmap, memory_region_size(&vdev->msix->mmap_mem));
    }
}

static int vfio_mmap_bar(VFIODevice *vdev, VFIOBAR *bar,
                         MemoryRegion *mem, MemoryRegion *submem,
                         void **map, size_t size, off_t offset,
                         const char *name)
{
    int ret = 0;

    if (VFIO_ALLOW_MMAP && size && bar->flags & VFIO_REGION_INFO_FLAG_MMAP) {
        int prot = 0;

        if (bar->flags & VFIO_REGION_INFO_FLAG_READ) {
            prot |= PROT_READ;
        }

        if (bar->flags & VFIO_REGION_INFO_FLAG_WRITE) {
            prot |= PROT_WRITE;
        }

        *map = mmap(NULL, size, prot, MAP_SHARED,
                    bar->fd, bar->fd_offset + offset);
        if (*map == MAP_FAILED) {
            *map = NULL;
            ret = -errno;
            goto empty_region;
        }

        memory_region_init_ram_ptr(submem, OBJECT(vdev), name, size, *map);
        memory_region_set_skip_dump(submem);
    } else {
empty_region:
        /* Create a zero sized sub-region to make cleanup easy. */
        memory_region_init(submem, OBJECT(vdev), name, 0);
    }

    memory_region_add_subregion(mem, offset, submem);

    return ret;
}

static void vfio_map_bar(VFIODevice *vdev, int nr)
{
    VFIOBAR *bar = &vdev->bars[nr];
    unsigned size = bar->size;
    char name[64];
    uint32_t pci_bar;
    uint8_t type;
    int ret;

    /* Skip both unimplemented BARs and the upper half of 64bit BARS. */
    if (!size) {
        return;
    }

    snprintf(name, sizeof(name), "VFIO %04x:%02x:%02x.%x BAR %d",
             vdev->host.domain, vdev->host.bus, vdev->host.slot,
             vdev->host.function, nr);

    /* Determine what type of BAR this is for registration */
    ret = pread(vdev->fd, &pci_bar, sizeof(pci_bar),
                vdev->config_offset + PCI_BASE_ADDRESS_0 + (4 * nr));
    if (ret != sizeof(pci_bar)) {
        error_report("vfio: Failed to read BAR %d (%m)", nr);
        return;
    }

    pci_bar = le32_to_cpu(pci_bar);
    bar->ioport = (pci_bar & PCI_BASE_ADDRESS_SPACE_IO);
    bar->mem64 = bar->ioport ? 0 : (pci_bar & PCI_BASE_ADDRESS_MEM_TYPE_64);
    type = pci_bar & (bar->ioport ? ~PCI_BASE_ADDRESS_IO_MASK :
                                    ~PCI_BASE_ADDRESS_MEM_MASK);

    /* A "slow" read/write mapping underlies all BARs */
    memory_region_init_io(&bar->mem, OBJECT(vdev), &vfio_bar_ops,
                          bar, name, size);
    pci_register_bar(&vdev->pdev, nr, type, &bar->mem);

    /*
     * We can't mmap areas overlapping the MSIX vector table, so we
     * potentially insert a direct-mapped subregion before and after it.
     */
    if (vdev->msix && vdev->msix->table_bar == nr) {
        size = vdev->msix->table_offset & qemu_host_page_mask;
    }

    strncat(name, " mmap", sizeof(name) - strlen(name) - 1);
    if (vfio_mmap_bar(vdev, bar, &bar->mem,
                      &bar->mmap_mem, &bar->mmap, size, 0, name)) {
        error_report("%s unsupported. Performance may be slow", name);
    }

    if (vdev->msix && vdev->msix->table_bar == nr) {
        unsigned start;

        start = HOST_PAGE_ALIGN(vdev->msix->table_offset +
                                (vdev->msix->entries * PCI_MSIX_ENTRY_SIZE));

        size = start < bar->size ? bar->size - start : 0;
        strncat(name, " msix-hi", sizeof(name) - strlen(name) - 1);
        /* VFIOMSIXInfo contains another MemoryRegion for this mapping */
        if (vfio_mmap_bar(vdev, bar, &bar->mem, &vdev->msix->mmap_mem,
                          &vdev->msix->mmap, size, start, name)) {
            error_report("%s unsupported. Performance may be slow", name);
        }
    }

    vfio_bar_quirk_setup(vdev, nr);
}

static void vfio_map_bars(VFIODevice *vdev)
{
    int i;

    for (i = 0; i < PCI_ROM_SLOT; i++) {
        vfio_map_bar(vdev, i);
    }

    if (vdev->has_vga) {
        memory_region_init_io(&vdev->vga.region[QEMU_PCI_VGA_MEM].mem,
                              OBJECT(vdev), &vfio_vga_ops,
                              &vdev->vga.region[QEMU_PCI_VGA_MEM],
                              "vfio-vga-mmio@0xa0000",
                              QEMU_PCI_VGA_MEM_SIZE);
        memory_region_init_io(&vdev->vga.region[QEMU_PCI_VGA_IO_LO].mem,
                              OBJECT(vdev), &vfio_vga_ops,
                              &vdev->vga.region[QEMU_PCI_VGA_IO_LO],
                              "vfio-vga-io@0x3b0",
                              QEMU_PCI_VGA_IO_LO_SIZE);
        memory_region_init_io(&vdev->vga.region[QEMU_PCI_VGA_IO_HI].mem,
                              OBJECT(vdev), &vfio_vga_ops,
                              &vdev->vga.region[QEMU_PCI_VGA_IO_HI],
                              "vfio-vga-io@0x3c0",
                              QEMU_PCI_VGA_IO_HI_SIZE);

        pci_register_vga(&vdev->pdev, &vdev->vga.region[QEMU_PCI_VGA_MEM].mem,
                         &vdev->vga.region[QEMU_PCI_VGA_IO_LO].mem,
                         &vdev->vga.region[QEMU_PCI_VGA_IO_HI].mem);
        vfio_vga_quirk_setup(vdev);
    }
}

static void vfio_unmap_bars(VFIODevice *vdev)
{
    int i;

    for (i = 0; i < PCI_ROM_SLOT; i++) {
        vfio_unmap_bar(vdev, i);
    }

    if (vdev->has_vga) {
        vfio_vga_quirk_teardown(vdev);
        pci_unregister_vga(&vdev->pdev);
    }
}

/*
 * General setup
 */
static uint8_t vfio_std_cap_max_size(PCIDevice *pdev, uint8_t pos)
{
    uint8_t tmp, next = 0xff;

    for (tmp = pdev->config[PCI_CAPABILITY_LIST]; tmp;
         tmp = pdev->config[tmp + 1]) {
        if (tmp > pos && tmp < next) {
            next = tmp;
        }
    }

    return next - pos;
}

static void vfio_set_word_bits(uint8_t *buf, uint16_t val, uint16_t mask)
{
    pci_set_word(buf, (pci_get_word(buf) & ~mask) | val);
}

static void vfio_add_emulated_word(VFIODevice *vdev, int pos,
                                   uint16_t val, uint16_t mask)
{
    vfio_set_word_bits(vdev->pdev.config + pos, val, mask);
    vfio_set_word_bits(vdev->pdev.wmask + pos, ~mask, mask);
    vfio_set_word_bits(vdev->emulated_config_bits + pos, mask, mask);
}

static void vfio_set_long_bits(uint8_t *buf, uint32_t val, uint32_t mask)
{
    pci_set_long(buf, (pci_get_long(buf) & ~mask) | val);
}

static void vfio_add_emulated_long(VFIODevice *vdev, int pos,
                                   uint32_t val, uint32_t mask)
{
    vfio_set_long_bits(vdev->pdev.config + pos, val, mask);
    vfio_set_long_bits(vdev->pdev.wmask + pos, ~mask, mask);
    vfio_set_long_bits(vdev->emulated_config_bits + pos, mask, mask);
}

static int vfio_setup_pcie_cap(VFIODevice *vdev, int pos, uint8_t size)
{
    uint16_t flags;
    uint8_t type;

    flags = pci_get_word(vdev->pdev.config + pos + PCI_CAP_FLAGS);
    type = (flags & PCI_EXP_FLAGS_TYPE) >> 4;

    if (type != PCI_EXP_TYPE_ENDPOINT &&
        type != PCI_EXP_TYPE_LEG_END &&
        type != PCI_EXP_TYPE_RC_END) {

        error_report("vfio: Assignment of PCIe type 0x%x "
                     "devices is not currently supported", type);
        return -EINVAL;
    }

    if (!pci_bus_is_express(vdev->pdev.bus)) {
        /*
         * Use express capability as-is on PCI bus.  It doesn't make much
         * sense to even expose, but some drivers (ex. tg3) depend on it
         * and guests don't seem to be particular about it.  We'll need
         * to revist this or force express devices to express buses if we
         * ever expose an IOMMU to the guest.
         */
    } else if (pci_bus_is_root(vdev->pdev.bus)) {
        /*
         * On a Root Complex bus Endpoints become Root Complex Integrated
         * Endpoints, which changes the type and clears the LNK & LNK2 fields.
         */
        if (type == PCI_EXP_TYPE_ENDPOINT) {
            vfio_add_emulated_word(vdev, pos + PCI_CAP_FLAGS,
                                   PCI_EXP_TYPE_RC_END << 4,
                                   PCI_EXP_FLAGS_TYPE);

            /* Link Capabilities, Status, and Control goes away */
            if (size > PCI_EXP_LNKCTL) {
                vfio_add_emulated_long(vdev, pos + PCI_EXP_LNKCAP, 0, ~0);
                vfio_add_emulated_word(vdev, pos + PCI_EXP_LNKCTL, 0, ~0);
                vfio_add_emulated_word(vdev, pos + PCI_EXP_LNKSTA, 0, ~0);

#ifndef PCI_EXP_LNKCAP2
#define PCI_EXP_LNKCAP2 44
#endif
#ifndef PCI_EXP_LNKSTA2
#define PCI_EXP_LNKSTA2 50
#endif
                /* Link 2 Capabilities, Status, and Control goes away */
                if (size > PCI_EXP_LNKCAP2) {
                    vfio_add_emulated_long(vdev, pos + PCI_EXP_LNKCAP2, 0, ~0);
                    vfio_add_emulated_word(vdev, pos + PCI_EXP_LNKCTL2, 0, ~0);
                    vfio_add_emulated_word(vdev, pos + PCI_EXP_LNKSTA2, 0, ~0);
                }
            }

        } else if (type == PCI_EXP_TYPE_LEG_END) {
            /*
             * Legacy endpoints don't belong on the root complex.  Windows
             * seems to be happier with devices if we skip the capability.
             */
            return 0;
        }

    } else {
        /*
         * Convert Root Complex Integrated Endpoints to regular endpoints.
         * These devices don't support LNK/LNK2 capabilities, so make them up.
         */
        if (type == PCI_EXP_TYPE_RC_END) {
            vfio_add_emulated_word(vdev, pos + PCI_CAP_FLAGS,
                                   PCI_EXP_TYPE_ENDPOINT << 4,
                                   PCI_EXP_FLAGS_TYPE);
            vfio_add_emulated_long(vdev, pos + PCI_EXP_LNKCAP,
                                   PCI_EXP_LNK_MLW_1 | PCI_EXP_LNK_LS_25, ~0);
            vfio_add_emulated_word(vdev, pos + PCI_EXP_LNKCTL, 0, ~0);
        }

        /* Mark the Link Status bits as emulated to allow virtual negotiation */
        vfio_add_emulated_word(vdev, pos + PCI_EXP_LNKSTA,
                               pci_get_word(vdev->pdev.config + pos +
                                            PCI_EXP_LNKSTA),
                               PCI_EXP_LNKCAP_MLW | PCI_EXP_LNKCAP_SLS);
    }

    pos = pci_add_capability(&vdev->pdev, PCI_CAP_ID_EXP, pos, size);
    if (pos >= 0) {
        vdev->pdev.exp.exp_cap = pos;
    }

    return pos;
}

static void vfio_check_pcie_flr(VFIODevice *vdev, uint8_t pos)
{
    uint32_t cap = pci_get_long(vdev->pdev.config + pos + PCI_EXP_DEVCAP);

    if (cap & PCI_EXP_DEVCAP_FLR) {
        trace_vfio_check_pcie_flr(vdev->host.domain, vdev->host.bus,
                                  vdev->host.slot, vdev->host.function);
        vdev->has_flr = true;
    }
}

static void vfio_check_pm_reset(VFIODevice *vdev, uint8_t pos)
{
    uint16_t csr = pci_get_word(vdev->pdev.config + pos + PCI_PM_CTRL);

    if (!(csr & PCI_PM_CTRL_NO_SOFT_RESET)) {
        trace_vfio_check_pm_reset(vdev->host.domain, vdev->host.bus,
                                  vdev->host.slot, vdev->host.function);
        vdev->has_pm_reset = true;
    }
}

static void vfio_check_af_flr(VFIODevice *vdev, uint8_t pos)
{
    uint8_t cap = pci_get_byte(vdev->pdev.config + pos + PCI_AF_CAP);

    if ((cap & PCI_AF_CAP_TP) && (cap & PCI_AF_CAP_FLR)) {
        trace_vfio_check_af_flr(vdev->host.domain, vdev->host.bus,
                                vdev->host.slot, vdev->host.function);
        vdev->has_flr = true;
    }
}

static int vfio_add_std_cap(VFIODevice *vdev, uint8_t pos)
{
    PCIDevice *pdev = &vdev->pdev;
    uint8_t cap_id, next, size;
    int ret;

    cap_id = pdev->config[pos];
    next = pdev->config[pos + 1];

    /*
     * If it becomes important to configure capabilities to their actual
     * size, use this as the default when it's something we don't recognize.
     * Since QEMU doesn't actually handle many of the config accesses,
     * exact size doesn't seem worthwhile.
     */
    size = vfio_std_cap_max_size(pdev, pos);

    /*
     * pci_add_capability always inserts the new capability at the head
     * of the chain.  Therefore to end up with a chain that matches the
     * physical device, we insert from the end by making this recursive.
     * This is also why we pre-caclulate size above as cached config space
     * will be changed as we unwind the stack.
     */
    if (next) {
        ret = vfio_add_std_cap(vdev, next);
        if (ret) {
            return ret;
        }
    } else {
        /* Begin the rebuild, use QEMU emulated list bits */
        pdev->config[PCI_CAPABILITY_LIST] = 0;
        vdev->emulated_config_bits[PCI_CAPABILITY_LIST] = 0xff;
        vdev->emulated_config_bits[PCI_STATUS] |= PCI_STATUS_CAP_LIST;
    }

    /* Use emulated next pointer to allow dropping caps */
    pci_set_byte(vdev->emulated_config_bits + pos + 1, 0xff);

    switch (cap_id) {
    case PCI_CAP_ID_MSI:
        ret = vfio_setup_msi(vdev, pos);
        break;
    case PCI_CAP_ID_EXP:
        vfio_check_pcie_flr(vdev, pos);
        ret = vfio_setup_pcie_cap(vdev, pos, size);
        break;
    case PCI_CAP_ID_MSIX:
        ret = vfio_setup_msix(vdev, pos);
        break;
    case PCI_CAP_ID_PM:
        vfio_check_pm_reset(vdev, pos);
        vdev->pm_cap = pos;
        ret = pci_add_capability(pdev, cap_id, pos, size);
        break;
    case PCI_CAP_ID_AF:
        vfio_check_af_flr(vdev, pos);
        ret = pci_add_capability(pdev, cap_id, pos, size);
        break;
    default:
        ret = pci_add_capability(pdev, cap_id, pos, size);
        break;
    }

    if (ret < 0) {
        error_report("vfio: %04x:%02x:%02x.%x Error adding PCI capability "
                     "0x%x[0x%x]@0x%x: %d", vdev->host.domain,
                     vdev->host.bus, vdev->host.slot, vdev->host.function,
                     cap_id, size, pos, ret);
        return ret;
    }

    return 0;
}

static int vfio_add_capabilities(VFIODevice *vdev)
{
    PCIDevice *pdev = &vdev->pdev;

    if (!(pdev->config[PCI_STATUS] & PCI_STATUS_CAP_LIST) ||
        !pdev->config[PCI_CAPABILITY_LIST]) {
        return 0; /* Nothing to add */
    }

    return vfio_add_std_cap(vdev, pdev->config[PCI_CAPABILITY_LIST]);
}

static void vfio_pci_pre_reset(VFIODevice *vdev)
{
    PCIDevice *pdev = &vdev->pdev;
    uint16_t cmd;

    vfio_disable_interrupts(vdev);

    /* Make sure the device is in D0 */
    if (vdev->pm_cap) {
        uint16_t pmcsr;
        uint8_t state;

        pmcsr = vfio_pci_read_config(pdev, vdev->pm_cap + PCI_PM_CTRL, 2);
        state = pmcsr & PCI_PM_CTRL_STATE_MASK;
        if (state) {
            pmcsr &= ~PCI_PM_CTRL_STATE_MASK;
            vfio_pci_write_config(pdev, vdev->pm_cap + PCI_PM_CTRL, pmcsr, 2);
            /* vfio handles the necessary delay here */
            pmcsr = vfio_pci_read_config(pdev, vdev->pm_cap + PCI_PM_CTRL, 2);
            state = pmcsr & PCI_PM_CTRL_STATE_MASK;
            if (state) {
                error_report("vfio: Unable to power on device, stuck in D%d",
                             state);
            }
        }
    }

    /*
     * Stop any ongoing DMA by disconecting I/O, MMIO, and bus master.
     * Also put INTx Disable in known state.
     */
    cmd = vfio_pci_read_config(pdev, PCI_COMMAND, 2);
    cmd &= ~(PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER |
             PCI_COMMAND_INTX_DISABLE);
    vfio_pci_write_config(pdev, PCI_COMMAND, cmd, 2);
}

static void vfio_pci_post_reset(VFIODevice *vdev)
{
    vfio_enable_intx(vdev);
}

static bool vfio_pci_host_match(PCIHostDeviceAddress *host1,
                                PCIHostDeviceAddress *host2)
{
    return (host1->domain == host2->domain && host1->bus == host2->bus &&
            host1->slot == host2->slot && host1->function == host2->function);
}

static int vfio_pci_hot_reset(VFIODevice *vdev, bool single)
{
    VFIOGroup *group;
    struct vfio_pci_hot_reset_info *info;
    struct vfio_pci_dependent_device *devices;
    struct vfio_pci_hot_reset *reset;
    int32_t *fds;
    int ret, i, count;
    bool multi = false;

    trace_vfio_pci_hot_reset(vdev->host.domain, vdev->host.bus,
                             vdev->host.slot, vdev->host.function,
                             single ? "one" : "multi");

    vfio_pci_pre_reset(vdev);
    vdev->needs_reset = false;

    info = g_malloc0(sizeof(*info));
    info->argsz = sizeof(*info);

    ret = ioctl(vdev->fd, VFIO_DEVICE_GET_PCI_HOT_RESET_INFO, info);
    if (ret && errno != ENOSPC) {
        ret = -errno;
        if (!vdev->has_pm_reset) {
            error_report("vfio: Cannot reset device %04x:%02x:%02x.%x, "
                         "no available reset mechanism.", vdev->host.domain,
                         vdev->host.bus, vdev->host.slot, vdev->host.function);
        }
        goto out_single;
    }

    count = info->count;
    info = g_realloc(info, sizeof(*info) + (count * sizeof(*devices)));
    info->argsz = sizeof(*info) + (count * sizeof(*devices));
    devices = &info->devices[0];

    ret = ioctl(vdev->fd, VFIO_DEVICE_GET_PCI_HOT_RESET_INFO, info);
    if (ret) {
        ret = -errno;
        error_report("vfio: hot reset info failed: %m");
        goto out_single;
    }

    trace_vfio_pci_hot_reset_has_dep_devices(vdev->host.domain,
                                             vdev->host.bus,
                                             vdev->host.slot,
                                             vdev->host.function);

    /* Verify that we have all the groups required */
    for (i = 0; i < info->count; i++) {
        PCIHostDeviceAddress host;
        VFIODevice *tmp;

        host.domain = devices[i].segment;
        host.bus = devices[i].bus;
        host.slot = PCI_SLOT(devices[i].devfn);
        host.function = PCI_FUNC(devices[i].devfn);

        trace_vfio_pci_hot_reset_dep_devices(host.domain,
                host.bus, host.slot, host.function, devices[i].group_id);

        if (vfio_pci_host_match(&host, &vdev->host)) {
            continue;
        }

        QLIST_FOREACH(group, &group_list, next) {
            if (group->groupid == devices[i].group_id) {
                break;
            }
        }

        if (!group) {
            if (!vdev->has_pm_reset) {
                error_report("vfio: Cannot reset device %04x:%02x:%02x.%x, "
                             "depends on group %d which is not owned.",
                             vdev->host.domain, vdev->host.bus, vdev->host.slot,
                             vdev->host.function, devices[i].group_id);
            }
            ret = -EPERM;
            goto out;
        }

        /* Prep dependent devices for reset and clear our marker. */
        QLIST_FOREACH(tmp, &group->device_list, next) {
            if (vfio_pci_host_match(&host, &tmp->host)) {
                if (single) {
                    error_report("vfio: found another in-use device "
                            "%04x:%02x:%02x.%x\n", host.domain, host.bus,
                            host.slot, host.function);
                    ret = -EINVAL;
                    goto out_single;
                }
                vfio_pci_pre_reset(tmp);
                tmp->needs_reset = false;
                multi = true;
                break;
            }
        }
    }

    if (!single && !multi) {
        error_report("vfio: No other in-use devices for multi hot reset\n");
        ret = -EINVAL;
        goto out_single;
    }

    /* Determine how many group fds need to be passed */
    count = 0;
    QLIST_FOREACH(group, &group_list, next) {
        for (i = 0; i < info->count; i++) {
            if (group->groupid == devices[i].group_id) {
                count++;
                break;
            }
        }
    }

    reset = g_malloc0(sizeof(*reset) + (count * sizeof(*fds)));
    reset->argsz = sizeof(*reset) + (count * sizeof(*fds));
    fds = &reset->group_fds[0];

    /* Fill in group fds */
    QLIST_FOREACH(group, &group_list, next) {
        for (i = 0; i < info->count; i++) {
            if (group->groupid == devices[i].group_id) {
                fds[reset->count++] = group->fd;
                break;
            }
        }
    }

    /* Bus reset! */
    ret = ioctl(vdev->fd, VFIO_DEVICE_PCI_HOT_RESET, reset);
    g_free(reset);

    trace_vfio_pci_hot_reset_result(vdev->host.domain,
                                    vdev->host.bus,
                                    vdev->host.slot,
                                    vdev->host.function,
                                    ret ? "%m" : "Success");

out:
    /* Re-enable INTx on affected devices */
    for (i = 0; i < info->count; i++) {
        PCIHostDeviceAddress host;
        VFIODevice *tmp;

        host.domain = devices[i].segment;
        host.bus = devices[i].bus;
        host.slot = PCI_SLOT(devices[i].devfn);
        host.function = PCI_FUNC(devices[i].devfn);

        if (vfio_pci_host_match(&host, &vdev->host)) {
            continue;
        }

        QLIST_FOREACH(group, &group_list, next) {
            if (group->groupid == devices[i].group_id) {
                break;
            }
        }

        if (!group) {
            break;
        }

        QLIST_FOREACH(tmp, &group->device_list, next) {
            if (vfio_pci_host_match(&host, &tmp->host)) {
                vfio_pci_post_reset(tmp);
                break;
            }
        }
    }
out_single:
    vfio_pci_post_reset(vdev);
    g_free(info);

    return ret;
}

/*
 * We want to differentiate hot reset of mulitple in-use devices vs hot reset
 * of a single in-use device.  VFIO_DEVICE_RESET will already handle the case
 * of doing hot resets when there is only a single device per bus.  The in-use
 * here refers to how many VFIODevices are affected.  A hot reset that affects
 * multiple devices, but only a single in-use device, means that we can call
 * it from our bus ->reset() callback since the extent is effectively a single
 * device.  This allows us to make use of it in the hotplug path.  When there
 * are multiple in-use devices, we can only trigger the hot reset during a
 * system reset and thus from our reset handler.  We separate _one vs _multi
 * here so that we don't overlap and do a double reset on the system reset
 * path where both our reset handler and ->reset() callback are used.  Calling
 * _one() will only do a hot reset for the one in-use devices case, calling
 * _multi() will do nothing if a _one() would have been sufficient.
 */
static int vfio_pci_hot_reset_one(VFIODevice *vdev)
{
    return vfio_pci_hot_reset(vdev, true);
}

static int vfio_pci_hot_reset_multi(VFIODevice *vdev)
{
    return vfio_pci_hot_reset(vdev, false);
}

static void vfio_pci_reset_handler(void *opaque)
{
    VFIOGroup *group;
    VFIODevice *vdev;

    QLIST_FOREACH(group, &group_list, next) {
        QLIST_FOREACH(vdev, &group->device_list, next) {
            if (!vdev->reset_works || (!vdev->has_flr && vdev->has_pm_reset)) {
                vdev->needs_reset = true;
            }
        }
    }

    QLIST_FOREACH(group, &group_list, next) {
        QLIST_FOREACH(vdev, &group->device_list, next) {
            if (vdev->needs_reset) {
                vfio_pci_hot_reset_multi(vdev);
            }
        }
    }
}

static void vfio_kvm_device_add_group(VFIOGroup *group)
{
#ifdef CONFIG_KVM
    struct kvm_device_attr attr = {
        .group = KVM_DEV_VFIO_GROUP,
        .attr = KVM_DEV_VFIO_GROUP_ADD,
        .addr = (uint64_t)(unsigned long)&group->fd,
    };

    if (!kvm_enabled()) {
        return;
    }

    if (vfio_kvm_device_fd < 0) {
        struct kvm_create_device cd = {
            .type = KVM_DEV_TYPE_VFIO,
        };

        if (kvm_vm_ioctl(kvm_state, KVM_CREATE_DEVICE, &cd)) {
            error_report("KVM_CREATE_DEVICE: %m\n");
            return;
        }

        vfio_kvm_device_fd = cd.fd;
    }

    if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) {
        error_report("Failed to add group %d to KVM VFIO device: %m",
                     group->groupid);
    }
#endif
}

static void vfio_kvm_device_del_group(VFIOGroup *group)
{
#ifdef CONFIG_KVM
    struct kvm_device_attr attr = {
        .group = KVM_DEV_VFIO_GROUP,
        .attr = KVM_DEV_VFIO_GROUP_DEL,
        .addr = (uint64_t)(unsigned long)&group->fd,
    };

    if (vfio_kvm_device_fd < 0) {
        return;
    }

    if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) {
        error_report("Failed to remove group %d from KVM VFIO device: %m",
                     group->groupid);
    }
#endif
}

static VFIOAddressSpace *vfio_get_address_space(AddressSpace *as)
{
    VFIOAddressSpace *space;

    QLIST_FOREACH(space, &vfio_address_spaces, list) {
        if (space->as == as) {
            return space;
        }
    }

    /* No suitable VFIOAddressSpace, create a new one */
    space = g_malloc0(sizeof(*space));
    space->as = as;
    QLIST_INIT(&space->containers);

    QLIST_INSERT_HEAD(&vfio_address_spaces, space, list);

    return space;
}

static void vfio_put_address_space(VFIOAddressSpace *space)
{
    if (QLIST_EMPTY(&space->containers)) {
        QLIST_REMOVE(space, list);
        g_free(space);
    }
}

static int vfio_connect_container(VFIOGroup *group, AddressSpace *as)
{
    VFIOContainer *container;
    int ret, fd;
    VFIOAddressSpace *space;

    space = vfio_get_address_space(as);

    QLIST_FOREACH(container, &space->containers, next) {
        if (!ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &container->fd)) {
            group->container = container;
            QLIST_INSERT_HEAD(&container->group_list, group, container_next);
            return 0;
        }
    }

    fd = qemu_open("/dev/vfio/vfio", O_RDWR);
    if (fd < 0) {
        error_report("vfio: failed to open /dev/vfio/vfio: %m");
        ret = -errno;
        goto put_space_exit;
    }

    ret = ioctl(fd, VFIO_GET_API_VERSION);
    if (ret != VFIO_API_VERSION) {
        error_report("vfio: supported vfio version: %d, "
                     "reported version: %d", VFIO_API_VERSION, ret);
        ret = -EINVAL;
        goto close_fd_exit;
    }

    container = g_malloc0(sizeof(*container));
    container->space = space;
    container->fd = fd;

    if (ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_TYPE1_IOMMU)) {
        ret = ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &fd);
        if (ret) {
            error_report("vfio: failed to set group container: %m");
            ret = -errno;
            goto free_container_exit;
        }

        ret = ioctl(fd, VFIO_SET_IOMMU, VFIO_TYPE1_IOMMU);
        if (ret) {
            error_report("vfio: failed to set iommu for container: %m");
            ret = -errno;
            goto free_container_exit;
        }

        container->iommu_data.type1.listener = vfio_memory_listener;
        container->iommu_data.release = vfio_listener_release;

        memory_listener_register(&container->iommu_data.type1.listener,
                                 container->space->as);

        if (container->iommu_data.type1.error) {
            ret = container->iommu_data.type1.error;
            error_report("vfio: memory listener initialization failed for container");
            goto listener_release_exit;
        }

        container->iommu_data.type1.initialized = true;

    } else if (ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_IOMMU)) {
        ret = ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &fd);
        if (ret) {
            error_report("vfio: failed to set group container: %m");
            ret = -errno;
            goto free_container_exit;
        }

        ret = ioctl(fd, VFIO_SET_IOMMU, VFIO_SPAPR_TCE_IOMMU);
        if (ret) {
            error_report("vfio: failed to set iommu for container: %m");
            ret = -errno;
            goto free_container_exit;
        }

        /*
         * The host kernel code implementing VFIO_IOMMU_DISABLE is called
         * when container fd is closed so we do not call it explicitly
         * in this file.
         */
        ret = ioctl(fd, VFIO_IOMMU_ENABLE);
        if (ret) {
            error_report("vfio: failed to enable container: %m");
            ret = -errno;
            goto free_container_exit;
        }

        container->iommu_data.type1.listener = vfio_memory_listener;
        container->iommu_data.release = vfio_listener_release;

        memory_listener_register(&container->iommu_data.type1.listener,
                                 container->space->as);

    } else {
        error_report("vfio: No available IOMMU models");
        ret = -EINVAL;
        goto free_container_exit;
    }

    QLIST_INIT(&container->group_list);
    QLIST_INSERT_HEAD(&space->containers, container, next);

    group->container = container;
    QLIST_INSERT_HEAD(&container->group_list, group, container_next);

    return 0;

listener_release_exit:
    vfio_listener_release(container);

free_container_exit:
    g_free(container);

close_fd_exit:
    close(fd);

put_space_exit:
    vfio_put_address_space(space);

    return ret;
}

static void vfio_disconnect_container(VFIOGroup *group)
{
    VFIOContainer *container = group->container;

    if (ioctl(group->fd, VFIO_GROUP_UNSET_CONTAINER, &container->fd)) {
        error_report("vfio: error disconnecting group %d from container",
                     group->groupid);
    }

    QLIST_REMOVE(group, container_next);
    group->container = NULL;

    if (QLIST_EMPTY(&container->group_list)) {
        VFIOAddressSpace *space = container->space;

        if (container->iommu_data.release) {
            container->iommu_data.release(container);
        }
        QLIST_REMOVE(container, next);
        trace_vfio_disconnect_container(container->fd);
        close(container->fd);
        g_free(container);

        vfio_put_address_space(space);
    }
}

static VFIOGroup *vfio_get_group(int groupid, AddressSpace *as)
{
    VFIOGroup *group;
    char path[32];
    struct vfio_group_status status = { .argsz = sizeof(status) };

    QLIST_FOREACH(group, &group_list, next) {
        if (group->groupid == groupid) {
            /* Found it.  Now is it already in the right context? */
            if (group->container->space->as == as) {
                return group;
            } else {
                error_report("vfio: group %d used in multiple address spaces",
                             group->groupid);
                return NULL;
            }
        }
    }

    group = g_malloc0(sizeof(*group));

    snprintf(path, sizeof(path), "/dev/vfio/%d", groupid);
    group->fd = qemu_open(path, O_RDWR);
    if (group->fd < 0) {
        error_report("vfio: error opening %s: %m", path);
        goto free_group_exit;
    }

    if (ioctl(group->fd, VFIO_GROUP_GET_STATUS, &status)) {
        error_report("vfio: error getting group status: %m");
        goto close_fd_exit;
    }

    if (!(status.flags & VFIO_GROUP_FLAGS_VIABLE)) {
        error_report("vfio: error, group %d is not viable, please ensure "
                     "all devices within the iommu_group are bound to their "
                     "vfio bus driver.", groupid);
        goto close_fd_exit;
    }

    group->groupid = groupid;
    QLIST_INIT(&group->device_list);

    if (vfio_connect_container(group, as)) {
        error_report("vfio: failed to setup container for group %d", groupid);
        goto close_fd_exit;
    }

    if (QLIST_EMPTY(&group_list)) {
        qemu_register_reset(vfio_pci_reset_handler, NULL);
    }

    QLIST_INSERT_HEAD(&group_list, group, next);

    vfio_kvm_device_add_group(group);

    return group;

close_fd_exit:
    close(group->fd);

free_group_exit:
    g_free(group);

    return NULL;
}

static void vfio_put_group(VFIOGroup *group)
{
    if (!QLIST_EMPTY(&group->device_list)) {
        return;
    }

    vfio_kvm_device_del_group(group);
    vfio_disconnect_container(group);
    QLIST_REMOVE(group, next);
    trace_vfio_put_group(group->fd);
    close(group->fd);
    g_free(group);

    if (QLIST_EMPTY(&group_list)) {
        qemu_unregister_reset(vfio_pci_reset_handler, NULL);
    }
}

static int vfio_get_device(VFIOGroup *group, const char *name, VFIODevice *vdev)
{
    struct vfio_device_info dev_info = { .argsz = sizeof(dev_info) };
    struct vfio_region_info reg_info = { .argsz = sizeof(reg_info) };
    struct vfio_irq_info irq_info = { .argsz = sizeof(irq_info) };
    int ret, i;

    ret = ioctl(group->fd, VFIO_GROUP_GET_DEVICE_FD, name);
    if (ret < 0) {
        error_report("vfio: error getting device %s from group %d: %m",
                     name, group->groupid);
        error_printf("Verify all devices in group %d are bound to vfio-pci "
                     "or pci-stub and not already in use\n", group->groupid);
        return ret;
    }

    vdev->fd = ret;
    vdev->group = group;
    QLIST_INSERT_HEAD(&group->device_list, vdev, next);

    /* Sanity check device */
    ret = ioctl(vdev->fd, VFIO_DEVICE_GET_INFO, &dev_info);
    if (ret) {
        error_report("vfio: error getting device info: %m");
        goto error;
    }

    trace_vfio_get_device_irq(name, dev_info.flags,
                              dev_info.num_regions, dev_info.num_irqs);

    if (!(dev_info.flags & VFIO_DEVICE_FLAGS_PCI)) {
        error_report("vfio: Um, this isn't a PCI device");
        goto error;
    }

    vdev->reset_works = !!(dev_info.flags & VFIO_DEVICE_FLAGS_RESET);

    if (dev_info.num_regions < VFIO_PCI_CONFIG_REGION_INDEX + 1) {
        error_report("vfio: unexpected number of io regions %u",
                     dev_info.num_regions);
        goto error;
    }

    if (dev_info.num_irqs < VFIO_PCI_MSIX_IRQ_INDEX + 1) {
        error_report("vfio: unexpected number of irqs %u", dev_info.num_irqs);
        goto error;
    }

    for (i = VFIO_PCI_BAR0_REGION_INDEX; i < VFIO_PCI_ROM_REGION_INDEX; i++) {
        reg_info.index = i;

        ret = ioctl(vdev->fd, VFIO_DEVICE_GET_REGION_INFO, &reg_info);
        if (ret) {
            error_report("vfio: Error getting region %d info: %m", i);
            goto error;
        }

        trace_vfio_get_device_region(name, i,
                                     (unsigned long)reg_info.size,
                                     (unsigned long)reg_info.offset,
                                     (unsigned long)reg_info.flags);

        vdev->bars[i].flags = reg_info.flags;
        vdev->bars[i].size = reg_info.size;
        vdev->bars[i].fd_offset = reg_info.offset;
        vdev->bars[i].fd = vdev->fd;
        vdev->bars[i].nr = i;
        QLIST_INIT(&vdev->bars[i].quirks);
    }

    reg_info.index = VFIO_PCI_CONFIG_REGION_INDEX;

    ret = ioctl(vdev->fd, VFIO_DEVICE_GET_REGION_INFO, &reg_info);
    if (ret) {
        error_report("vfio: Error getting config info: %m");
        goto error;
    }

    trace_vfio_get_device_config(name, (unsigned long)reg_info.size,
                                 (unsigned long)reg_info.offset,
                                 (unsigned long)reg_info.flags);

    vdev->config_size = reg_info.size;
    if (vdev->config_size == PCI_CONFIG_SPACE_SIZE) {
        vdev->pdev.cap_present &= ~QEMU_PCI_CAP_EXPRESS;
    }
    vdev->config_offset = reg_info.offset;

    if ((vdev->features & VFIO_FEATURE_ENABLE_VGA) &&
        dev_info.num_regions > VFIO_PCI_VGA_REGION_INDEX) {
        struct vfio_region_info vga_info = {
            .argsz = sizeof(vga_info),
            .index = VFIO_PCI_VGA_REGION_INDEX,
         };

        ret = ioctl(vdev->fd, VFIO_DEVICE_GET_REGION_INFO, &vga_info);
        if (ret) {
            error_report(
                "vfio: Device does not support requested feature x-vga");
            goto error;
        }

        if (!(vga_info.flags & VFIO_REGION_INFO_FLAG_READ) ||
            !(vga_info.flags & VFIO_REGION_INFO_FLAG_WRITE) ||
            vga_info.size < 0xbffff + 1) {
            error_report("vfio: Unexpected VGA info, flags 0x%lx, size 0x%lx",
                         (unsigned long)vga_info.flags,
                         (unsigned long)vga_info.size);
            goto error;
        }

        vdev->vga.fd_offset = vga_info.offset;
        vdev->vga.fd = vdev->fd;

        vdev->vga.region[QEMU_PCI_VGA_MEM].offset = QEMU_PCI_VGA_MEM_BASE;
        vdev->vga.region[QEMU_PCI_VGA_MEM].nr = QEMU_PCI_VGA_MEM;
        QLIST_INIT(&vdev->vga.region[QEMU_PCI_VGA_MEM].quirks);

        vdev->vga.region[QEMU_PCI_VGA_IO_LO].offset = QEMU_PCI_VGA_IO_LO_BASE;
        vdev->vga.region[QEMU_PCI_VGA_IO_LO].nr = QEMU_PCI_VGA_IO_LO;
        QLIST_INIT(&vdev->vga.region[QEMU_PCI_VGA_IO_LO].quirks);

        vdev->vga.region[QEMU_PCI_VGA_IO_HI].offset = QEMU_PCI_VGA_IO_HI_BASE;
        vdev->vga.region[QEMU_PCI_VGA_IO_HI].nr = QEMU_PCI_VGA_IO_HI;
        QLIST_INIT(&vdev->vga.region[QEMU_PCI_VGA_IO_HI].quirks);

        vdev->has_vga = true;
    }
    irq_info.index = VFIO_PCI_ERR_IRQ_INDEX;

    ret = ioctl(vdev->fd, VFIO_DEVICE_GET_IRQ_INFO, &irq_info);
    if (ret) {
        /* This can fail for an old kernel or legacy PCI dev */
        trace_vfio_get_device_get_irq_info_failure();
        ret = 0;
    } else if (irq_info.count == 1) {
        vdev->pci_aer = true;
    } else {
        error_report("vfio: %04x:%02x:%02x.%x "
                     "Could not enable error recovery for the device",
                     vdev->host.domain, vdev->host.bus, vdev->host.slot,
                     vdev->host.function);
    }

error:
    if (ret) {
        QLIST_REMOVE(vdev, next);
        vdev->group = NULL;
        close(vdev->fd);
    }
    return ret;
}

static void vfio_put_device(VFIODevice *vdev)
{
    QLIST_REMOVE(vdev, next);
    vdev->group = NULL;
    trace_vfio_put_device(vdev->fd);
    close(vdev->fd);
    if (vdev->msix) {
        g_free(vdev->msix);
        vdev->msix = NULL;
    }
}

static void vfio_err_notifier_handler(void *opaque)
{
    VFIODevice *vdev = opaque;

    if (!event_notifier_test_and_clear(&vdev->err_notifier)) {
        return;
    }

    /*
     * TBD. Retrieve the error details and decide what action
     * needs to be taken. One of the actions could be to pass
     * the error to the guest and have the guest driver recover
     * from the error. This requires that PCIe capabilities be
     * exposed to the guest. For now, we just terminate the
     * guest to contain the error.
     */

    error_report("%s(%04x:%02x:%02x.%x) Unrecoverable error detected.  "
                 "Please collect any data possible and then kill the guest",
                 __func__, vdev->host.domain, vdev->host.bus,
                 vdev->host.slot, vdev->host.function);

    vm_stop(RUN_STATE_INTERNAL_ERROR);
}

/*
 * Registers error notifier for devices supporting error recovery.
 * If we encounter a failure in this function, we report an error
 * and continue after disabling error recovery support for the
 * device.
 */
static void vfio_register_err_notifier(VFIODevice *vdev)
{
    int ret;
    int argsz;
    struct vfio_irq_set *irq_set;
    int32_t *pfd;

    if (!vdev->pci_aer) {
        return;
    }

    if (event_notifier_init(&vdev->err_notifier, 0)) {
        error_report("vfio: Unable to init event notifier for error detection");
        vdev->pci_aer = false;
        return;
    }

    argsz = sizeof(*irq_set) + sizeof(*pfd);

    irq_set = g_malloc0(argsz);
    irq_set->argsz = argsz;
    irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD |
                     VFIO_IRQ_SET_ACTION_TRIGGER;
    irq_set->index = VFIO_PCI_ERR_IRQ_INDEX;
    irq_set->start = 0;
    irq_set->count = 1;
    pfd = (int32_t *)&irq_set->data;

    *pfd = event_notifier_get_fd(&vdev->err_notifier);
    qemu_set_fd_handler(*pfd, vfio_err_notifier_handler, NULL, vdev);

    ret = ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, irq_set);
    if (ret) {
        error_report("vfio: Failed to set up error notification");
        qemu_set_fd_handler(*pfd, NULL, NULL, vdev);
        event_notifier_cleanup(&vdev->err_notifier);
        vdev->pci_aer = false;
    }
    g_free(irq_set);
}

static void vfio_unregister_err_notifier(VFIODevice *vdev)
{
    int argsz;
    struct vfio_irq_set *irq_set;
    int32_t *pfd;
    int ret;

    if (!vdev->pci_aer) {
        return;
    }

    argsz = sizeof(*irq_set) + sizeof(*pfd);

    irq_set = g_malloc0(argsz);
    irq_set->argsz = argsz;
    irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD |
                     VFIO_IRQ_SET_ACTION_TRIGGER;
    irq_set->index = VFIO_PCI_ERR_IRQ_INDEX;
    irq_set->start = 0;
    irq_set->count = 1;
    pfd = (int32_t *)&irq_set->data;
    *pfd = -1;

    ret = ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, irq_set);
    if (ret) {
        error_report("vfio: Failed to de-assign error fd: %m");
    }
    g_free(irq_set);
    qemu_set_fd_handler(event_notifier_get_fd(&vdev->err_notifier),
                        NULL, NULL, vdev);
    event_notifier_cleanup(&vdev->err_notifier);
}

static int vfio_initfn(PCIDevice *pdev)
{
    VFIODevice *pvdev, *vdev = DO_UPCAST(VFIODevice, pdev, pdev);
    VFIOGroup *group;
    char path[PATH_MAX], iommu_group_path[PATH_MAX], *group_name;
    ssize_t len;
    struct stat st;
    int groupid;
    int ret;

    /* Check that the host device exists */
    snprintf(path, sizeof(path),
             "/sys/bus/pci/devices/%04x:%02x:%02x.%01x/",
             vdev->host.domain, vdev->host.bus, vdev->host.slot,
             vdev->host.function);
    if (stat(path, &st) < 0) {
        error_report("vfio: error: no such host device: %s", path);
        return -errno;
    }

    strncat(path, "iommu_group", sizeof(path) - strlen(path) - 1);

    len = readlink(path, iommu_group_path, sizeof(path));
    if (len <= 0 || len >= sizeof(path)) {
        error_report("vfio: error no iommu_group for device");
        return len < 0 ? -errno : ENAMETOOLONG;
    }

    iommu_group_path[len] = 0;
    group_name = basename(iommu_group_path);

    if (sscanf(group_name, "%d", &groupid) != 1) {
        error_report("vfio: error reading %s: %m", path);
        return -errno;
    }

    trace_vfio_initfn(vdev->host.domain, vdev->host.bus,
                      vdev->host.slot, vdev->host.function, groupid);

    group = vfio_get_group(groupid, pci_device_iommu_address_space(pdev));
    if (!group) {
        error_report("vfio: failed to get group %d", groupid);
        return -ENOENT;
    }

    snprintf(path, sizeof(path), "%04x:%02x:%02x.%01x",
            vdev->host.domain, vdev->host.bus, vdev->host.slot,
            vdev->host.function);

    QLIST_FOREACH(pvdev, &group->device_list, next) {
        if (pvdev->host.domain == vdev->host.domain &&
            pvdev->host.bus == vdev->host.bus &&
            pvdev->host.slot == vdev->host.slot &&
            pvdev->host.function == vdev->host.function) {

            error_report("vfio: error: device %s is already attached", path);
            vfio_put_group(group);
            return -EBUSY;
        }
    }

    ret = vfio_get_device(group, path, vdev);
    if (ret) {
        error_report("vfio: failed to get device %s", path);
        vfio_put_group(group);
        return ret;
    }

    /* Get a copy of config space */
    ret = pread(vdev->fd, vdev->pdev.config,
                MIN(pci_config_size(&vdev->pdev), vdev->config_size),
                vdev->config_offset);
    if (ret < (int)MIN(pci_config_size(&vdev->pdev), vdev->config_size)) {
        ret = ret < 0 ? -errno : -EFAULT;
        error_report("vfio: Failed to read device config space");
        goto out_put;
    }

    /* vfio emulates a lot for us, but some bits need extra love */
    vdev->emulated_config_bits = g_malloc0(vdev->config_size);

    /* QEMU can choose to expose the ROM or not */
    memset(vdev->emulated_config_bits + PCI_ROM_ADDRESS, 0xff, 4);

    /* QEMU can change multi-function devices to single function, or reverse */
    vdev->emulated_config_bits[PCI_HEADER_TYPE] =
                                              PCI_HEADER_TYPE_MULTI_FUNCTION;

    /* Restore or clear multifunction, this is always controlled by QEMU */
    if (vdev->pdev.cap_present & QEMU_PCI_CAP_MULTIFUNCTION) {
        vdev->pdev.config[PCI_HEADER_TYPE] |= PCI_HEADER_TYPE_MULTI_FUNCTION;
    } else {
        vdev->pdev.config[PCI_HEADER_TYPE] &= ~PCI_HEADER_TYPE_MULTI_FUNCTION;
    }

    /*
     * Clear host resource mapping info.  If we choose not to register a
     * BAR, such as might be the case with the option ROM, we can get
     * confusing, unwritable, residual addresses from the host here.
     */
    memset(&vdev->pdev.config[PCI_BASE_ADDRESS_0], 0, 24);
    memset(&vdev->pdev.config[PCI_ROM_ADDRESS], 0, 4);

    vfio_pci_size_rom(vdev);

    ret = vfio_early_setup_msix(vdev);
    if (ret) {
        goto out_put;
    }

    vfio_map_bars(vdev);

    ret = vfio_add_capabilities(vdev);
    if (ret) {
        goto out_teardown;
    }

    /* QEMU emulates all of MSI & MSIX */
    if (pdev->cap_present & QEMU_PCI_CAP_MSIX) {
        memset(vdev->emulated_config_bits + pdev->msix_cap, 0xff,
               MSIX_CAP_LENGTH);
    }

    if (pdev->cap_present & QEMU_PCI_CAP_MSI) {
        memset(vdev->emulated_config_bits + pdev->msi_cap, 0xff,
               vdev->msi_cap_size);
    }

    if (vfio_pci_read_config(&vdev->pdev, PCI_INTERRUPT_PIN, 1)) {
        vdev->intx.mmap_timer = timer_new_ms(QEMU_CLOCK_VIRTUAL,
                                                  vfio_intx_mmap_enable, vdev);
        pci_device_set_intx_routing_notifier(&vdev->pdev, vfio_update_irq);
        ret = vfio_enable_intx(vdev);
        if (ret) {
            goto out_teardown;
        }
    }

    vfio_register_err_notifier(vdev);

    return 0;

out_teardown:
    pci_device_set_intx_routing_notifier(&vdev->pdev, NULL);
    vfio_teardown_msi(vdev);
    vfio_unmap_bars(vdev);
out_put:
    g_free(vdev->emulated_config_bits);
    vfio_put_device(vdev);
    vfio_put_group(group);
    return ret;
}

static void vfio_exitfn(PCIDevice *pdev)
{
    VFIODevice *vdev = DO_UPCAST(VFIODevice, pdev, pdev);
    VFIOGroup *group = vdev->group;

    vfio_unregister_err_notifier(vdev);
    pci_device_set_intx_routing_notifier(&vdev->pdev, NULL);
    vfio_disable_interrupts(vdev);
    if (vdev->intx.mmap_timer) {
        timer_free(vdev->intx.mmap_timer);
    }
    vfio_teardown_msi(vdev);
    vfio_unmap_bars(vdev);
    g_free(vdev->emulated_config_bits);
    g_free(vdev->rom);
    vfio_put_device(vdev);
    vfio_put_group(group);
}

static void vfio_pci_reset(DeviceState *dev)
{
    PCIDevice *pdev = DO_UPCAST(PCIDevice, qdev, dev);
    VFIODevice *vdev = DO_UPCAST(VFIODevice, pdev, pdev);

    trace_vfio_pci_reset(vdev->host.domain, vdev->host.bus,
                         vdev->host.slot, vdev->host.function);

    vfio_pci_pre_reset(vdev);

    if (vdev->reset_works && (vdev->has_flr || !vdev->has_pm_reset) &&
        !ioctl(vdev->fd, VFIO_DEVICE_RESET)) {
        trace_vfio_pci_reset_flr(vdev->host.domain, vdev->host.bus,
                                  vdev->host.slot, vdev->host.function);
        goto post_reset;
    }

    /* See if we can do our own bus reset */
    if (!vfio_pci_hot_reset_one(vdev)) {
        goto post_reset;
    }

    /* If nothing else works and the device supports PM reset, use it */
    if (vdev->reset_works && vdev->has_pm_reset &&
        !ioctl(vdev->fd, VFIO_DEVICE_RESET)) {
        trace_vfio_pci_reset_pm(vdev->host.domain, vdev->host.bus,
                                vdev->host.slot, vdev->host.function);
        goto post_reset;
    }

post_reset:
    vfio_pci_post_reset(vdev);
}

static void vfio_instance_init(Object *obj)
{
    PCIDevice *pci_dev = PCI_DEVICE(obj);
    VFIODevice *vdev = DO_UPCAST(VFIODevice, pdev, PCI_DEVICE(obj));

    device_add_bootindex_property(obj, &vdev->bootindex,
                                  "bootindex", NULL,
                                  &pci_dev->qdev, NULL);
}

static Property vfio_pci_dev_properties[] = {
    DEFINE_PROP_PCI_HOST_DEVADDR("host", VFIODevice, host),
    DEFINE_PROP_UINT32("x-intx-mmap-timeout-ms", VFIODevice,
                       intx.mmap_timeout, 1100),
    DEFINE_PROP_BIT("x-vga", VFIODevice, features,
                    VFIO_FEATURE_ENABLE_VGA_BIT, false),
    /*
     * TODO - support passed fds... is this necessary?
     * DEFINE_PROP_STRING("vfiofd", VFIODevice, vfiofd_name),
     * DEFINE_PROP_STRING("vfiogroupfd, VFIODevice, vfiogroupfd_name),
     */
    DEFINE_PROP_END_OF_LIST(),
};

static const VMStateDescription vfio_pci_vmstate = {
    .name = "vfio-pci",
    .unmigratable = 1,
};

static void vfio_pci_dev_class_init(ObjectClass *klass, void *data)
{
    DeviceClass *dc = DEVICE_CLASS(klass);
    PCIDeviceClass *pdc = PCI_DEVICE_CLASS(klass);

    dc->reset = vfio_pci_reset;
    dc->props = vfio_pci_dev_properties;
    dc->vmsd = &vfio_pci_vmstate;
    dc->desc = "VFIO-based PCI device assignment";
    set_bit(DEVICE_CATEGORY_MISC, dc->categories);
    pdc->init = vfio_initfn;
    pdc->exit = vfio_exitfn;
    pdc->config_read = vfio_pci_read_config;
    pdc->config_write = vfio_pci_write_config;
    pdc->is_express = 1; /* We might be */
}

static const TypeInfo vfio_pci_dev_info = {
    .name = "vfio-pci",
    .parent = TYPE_PCI_DEVICE,
    .instance_size = sizeof(VFIODevice),
    .class_init = vfio_pci_dev_class_init,
    .instance_init = vfio_instance_init,
};

static void register_vfio_pci_dev_type(void)
{
    type_register_static(&vfio_pci_dev_info);
}

type_init(register_vfio_pci_dev_type)

static int vfio_container_do_ioctl(AddressSpace *as, int32_t groupid,
                                   int req, void *param)
{
    VFIOGroup *group;
    VFIOContainer *container;
    int ret = -1;

    group = vfio_get_group(groupid, as);
    if (!group) {
        error_report("vfio: group %d not registered", groupid);
        return ret;
    }

    container = group->container;
    if (group->container) {
        ret = ioctl(container->fd, req, param);
        if (ret < 0) {
            error_report("vfio: failed to ioctl container: ret=%d, %s",
                         ret, strerror(errno));
        }
    }

    vfio_put_group(group);

    return ret;
}

int vfio_container_ioctl(AddressSpace *as, int32_t groupid,
                         int req, void *param)
{
    /* We allow only certain ioctls to the container */
    switch (req) {
    case VFIO_CHECK_EXTENSION:
    case VFIO_IOMMU_SPAPR_TCE_GET_INFO:
        break;
    default:
        /* Return an error on unknown requests */
        error_report("vfio: unsupported ioctl %X", req);
        return -1;
    }

    return vfio_container_do_ioctl(as, groupid, req, param);
}