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
|
/*
* 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 "qemu/osdep.h"
#include CONFIG_DEVICES /* CONFIG_IOMMUFD */
#include <linux/vfio.h>
#include <sys/ioctl.h>
#include "hw/hw.h"
#include "hw/pci/msi.h"
#include "hw/pci/msix.h"
#include "hw/pci/pci_bridge.h"
#include "hw/qdev-properties.h"
#include "hw/qdev-properties-system.h"
#include "migration/vmstate.h"
#include "qapi/qmp/qdict.h"
#include "qemu/error-report.h"
#include "qemu/main-loop.h"
#include "qemu/module.h"
#include "qemu/range.h"
#include "qemu/units.h"
#include "sysemu/kvm.h"
#include "sysemu/runstate.h"
#include "pci.h"
#include "trace.h"
#include "qapi/error.h"
#include "migration/blocker.h"
#include "migration/qemu-file.h"
#include "sysemu/iommufd.h"
#define TYPE_VFIO_PCI_NOHOTPLUG "vfio-pci-nohotplug"
/* Protected by BQL */
static KVMRouteChange vfio_route_change;
static void vfio_disable_interrupts(VFIOPCIDevice *vdev);
static void vfio_mmap_set_enabled(VFIOPCIDevice *vdev, bool enabled);
static void vfio_msi_disable_common(VFIOPCIDevice *vdev);
/*
* 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)
{
VFIOPCIDevice *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)
{
VFIOPCIDevice *vdev = opaque;
if (!event_notifier_test_and_clear(&vdev->intx.interrupt)) {
return;
}
trace_vfio_intx_interrupt(vdev->vbasedev.name, '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_intx_eoi(VFIODevice *vbasedev)
{
VFIOPCIDevice *vdev = container_of(vbasedev, VFIOPCIDevice, vbasedev);
if (!vdev->intx.pending) {
return;
}
trace_vfio_intx_eoi(vbasedev->name);
vdev->intx.pending = false;
pci_irq_deassert(&vdev->pdev);
vfio_unmask_single_irqindex(vbasedev, VFIO_PCI_INTX_IRQ_INDEX);
}
static bool vfio_intx_enable_kvm(VFIOPCIDevice *vdev, Error **errp)
{
#ifdef CONFIG_KVM
int irq_fd = event_notifier_get_fd(&vdev->intx.interrupt);
if (vdev->no_kvm_intx || !kvm_irqfds_enabled() ||
vdev->intx.route.mode != PCI_INTX_ENABLED ||
!kvm_resamplefds_enabled()) {
return true;
}
/* Get to a known interrupt state */
qemu_set_fd_handler(irq_fd, NULL, NULL, vdev);
vfio_mask_single_irqindex(&vdev->vbasedev, VFIO_PCI_INTX_IRQ_INDEX);
vdev->intx.pending = false;
pci_irq_deassert(&vdev->pdev);
/* Get an eventfd for resample/unmask */
if (event_notifier_init(&vdev->intx.unmask, 0)) {
error_setg(errp, "event_notifier_init failed eoi");
goto fail;
}
if (kvm_irqchip_add_irqfd_notifier_gsi(kvm_state,
&vdev->intx.interrupt,
&vdev->intx.unmask,
vdev->intx.route.irq)) {
error_setg_errno(errp, errno, "failed to setup resample irqfd");
goto fail_irqfd;
}
if (!vfio_set_irq_signaling(&vdev->vbasedev, VFIO_PCI_INTX_IRQ_INDEX, 0,
VFIO_IRQ_SET_ACTION_UNMASK,
event_notifier_get_fd(&vdev->intx.unmask),
errp)) {
goto fail_vfio;
}
/* Let'em rip */
vfio_unmask_single_irqindex(&vdev->vbasedev, VFIO_PCI_INTX_IRQ_INDEX);
vdev->intx.kvm_accel = true;
trace_vfio_intx_enable_kvm(vdev->vbasedev.name);
return true;
fail_vfio:
kvm_irqchip_remove_irqfd_notifier_gsi(kvm_state, &vdev->intx.interrupt,
vdev->intx.route.irq);
fail_irqfd:
event_notifier_cleanup(&vdev->intx.unmask);
fail:
qemu_set_fd_handler(irq_fd, vfio_intx_interrupt, NULL, vdev);
vfio_unmask_single_irqindex(&vdev->vbasedev, VFIO_PCI_INTX_IRQ_INDEX);
return false;
#else
return true;
#endif
}
static void vfio_intx_disable_kvm(VFIOPCIDevice *vdev)
{
#ifdef CONFIG_KVM
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_single_irqindex(&vdev->vbasedev, VFIO_PCI_INTX_IRQ_INDEX);
vdev->intx.pending = false;
pci_irq_deassert(&vdev->pdev);
/* Tell KVM to stop listening for an INTx irqfd */
if (kvm_irqchip_remove_irqfd_notifier_gsi(kvm_state, &vdev->intx.interrupt,
vdev->intx.route.irq)) {
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(event_notifier_get_fd(&vdev->intx.interrupt),
vfio_intx_interrupt, NULL, vdev);
vdev->intx.kvm_accel = false;
/* If we've missed an event, let it re-fire through QEMU */
vfio_unmask_single_irqindex(&vdev->vbasedev, VFIO_PCI_INTX_IRQ_INDEX);
trace_vfio_intx_disable_kvm(vdev->vbasedev.name);
#endif
}
static void vfio_intx_update(VFIOPCIDevice *vdev, PCIINTxRoute *route)
{
Error *err = NULL;
trace_vfio_intx_update(vdev->vbasedev.name,
vdev->intx.route.irq, route->irq);
vfio_intx_disable_kvm(vdev);
vdev->intx.route = *route;
if (route->mode != PCI_INTX_ENABLED) {
return;
}
if (!vfio_intx_enable_kvm(vdev, &err)) {
warn_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.name);
}
/* Re-enable the interrupt in cased we missed an EOI */
vfio_intx_eoi(&vdev->vbasedev);
}
static void vfio_intx_routing_notifier(PCIDevice *pdev)
{
VFIOPCIDevice *vdev = VFIO_PCI(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)) {
vfio_intx_update(vdev, &route);
}
}
static void vfio_irqchip_change(Notifier *notify, void *data)
{
VFIOPCIDevice *vdev = container_of(notify, VFIOPCIDevice,
irqchip_change_notifier);
vfio_intx_update(vdev, &vdev->intx.route);
}
static bool vfio_intx_enable(VFIOPCIDevice *vdev, Error **errp)
{
uint8_t pin = vfio_pci_read_config(&vdev->pdev, PCI_INTERRUPT_PIN, 1);
Error *err = NULL;
int32_t fd;
int ret;
if (!pin) {
return true;
}
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_setg_errno(errp, -ret, "event_notifier_init failed");
return false;
}
fd = event_notifier_get_fd(&vdev->intx.interrupt);
qemu_set_fd_handler(fd, vfio_intx_interrupt, NULL, vdev);
if (!vfio_set_irq_signaling(&vdev->vbasedev, VFIO_PCI_INTX_IRQ_INDEX, 0,
VFIO_IRQ_SET_ACTION_TRIGGER, fd, errp)) {
qemu_set_fd_handler(fd, NULL, NULL, vdev);
event_notifier_cleanup(&vdev->intx.interrupt);
return false;
}
if (!vfio_intx_enable_kvm(vdev, &err)) {
warn_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.name);
}
vdev->interrupt = VFIO_INT_INTx;
trace_vfio_intx_enable(vdev->vbasedev.name);
return true;
}
static void vfio_intx_disable(VFIOPCIDevice *vdev)
{
int fd;
timer_del(vdev->intx.mmap_timer);
vfio_intx_disable_kvm(vdev);
vfio_disable_irqindex(&vdev->vbasedev, 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_intx_disable(vdev->vbasedev.name);
}
/*
* MSI/X
*/
static void vfio_msi_interrupt(void *opaque)
{
VFIOMSIVector *vector = opaque;
VFIOPCIDevice *vdev = vector->vdev;
MSIMessage (*get_msg)(PCIDevice *dev, unsigned vector);
void (*notify)(PCIDevice *dev, unsigned vector);
MSIMessage msg;
int nr = vector - vdev->msi_vectors;
if (!event_notifier_test_and_clear(&vector->interrupt)) {
return;
}
if (vdev->interrupt == VFIO_INT_MSIX) {
get_msg = msix_get_message;
notify = msix_notify;
/* A masked vector firing needs to use the PBA, enable it */
if (msix_is_masked(&vdev->pdev, nr)) {
set_bit(nr, vdev->msix->pending);
memory_region_set_enabled(&vdev->pdev.msix_pba_mmio, true);
trace_vfio_msix_pba_enable(vdev->vbasedev.name);
}
} else if (vdev->interrupt == VFIO_INT_MSI) {
get_msg = msi_get_message;
notify = msi_notify;
} else {
abort();
}
msg = get_msg(&vdev->pdev, nr);
trace_vfio_msi_interrupt(vdev->vbasedev.name, nr, msg.address, msg.data);
notify(&vdev->pdev, nr);
}
/*
* Get MSI-X enabled, but no vector enabled, by setting vector 0 with an invalid
* fd to kernel.
*/
static int vfio_enable_msix_no_vec(VFIOPCIDevice *vdev)
{
g_autofree struct vfio_irq_set *irq_set = NULL;
int ret = 0, argsz;
int32_t *fd;
argsz = sizeof(*irq_set) + sizeof(*fd);
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 = 0;
irq_set->count = 1;
fd = (int32_t *)&irq_set->data;
*fd = -1;
ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set);
return ret;
}
static int vfio_enable_vectors(VFIOPCIDevice *vdev, bool msix)
{
struct vfio_irq_set *irq_set;
int ret = 0, i, argsz;
int32_t *fds;
/*
* If dynamic MSI-X allocation is supported, the vectors to be allocated
* and enabled can be scattered. Before kernel enabling MSI-X, setting
* nr_vectors causes all these vectors to be allocated on host.
*
* To keep allocation as needed, use vector 0 with an invalid fd to get
* MSI-X enabled first, then set vectors with a potentially sparse set of
* eventfds to enable interrupts only when enabled in guest.
*/
if (msix && !vdev->msix->noresize) {
ret = vfio_enable_msix_no_vec(vdev);
if (ret) {
return ret;
}
}
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->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set);
g_free(irq_set);
return ret;
}
static void vfio_add_kvm_msi_virq(VFIOPCIDevice *vdev, VFIOMSIVector *vector,
int vector_n, bool msix)
{
if ((msix && vdev->no_kvm_msix) || (!msix && vdev->no_kvm_msi)) {
return;
}
vector->virq = kvm_irqchip_add_msi_route(&vfio_route_change,
vector_n, &vdev->pdev);
}
static void vfio_connect_kvm_msi_virq(VFIOMSIVector *vector)
{
if (vector->virq < 0) {
return;
}
if (event_notifier_init(&vector->kvm_interrupt, 0)) {
goto fail_notifier;
}
if (kvm_irqchip_add_irqfd_notifier_gsi(kvm_state, &vector->kvm_interrupt,
NULL, vector->virq) < 0) {
goto fail_kvm;
}
return;
fail_kvm:
event_notifier_cleanup(&vector->kvm_interrupt);
fail_notifier:
kvm_irqchip_release_virq(kvm_state, vector->virq);
vector->virq = -1;
}
static void vfio_remove_kvm_msi_virq(VFIOMSIVector *vector)
{
kvm_irqchip_remove_irqfd_notifier_gsi(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,
PCIDevice *pdev)
{
kvm_irqchip_update_msi_route(kvm_state, vector->virq, msg, pdev);
kvm_irqchip_commit_routes(kvm_state);
}
static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr,
MSIMessage *msg, IOHandler *handler)
{
VFIOPCIDevice *vdev = VFIO_PCI(pdev);
VFIOMSIVector *vector;
int ret;
bool resizing = !!(vdev->nr_vectors < nr + 1);
trace_vfio_msix_vector_do_use(vdev->vbasedev.name, 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, pdev);
}
} else {
if (msg) {
if (vdev->defer_kvm_irq_routing) {
vfio_add_kvm_msi_virq(vdev, vector, nr, true);
} else {
vfio_route_change = kvm_irqchip_begin_route_changes(kvm_state);
vfio_add_kvm_msi_virq(vdev, vector, nr, true);
kvm_irqchip_commit_route_changes(&vfio_route_change);
vfio_connect_kvm_msi_virq(vector);
}
}
}
/*
* When dynamic allocation is not supported, 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.
* nr_vectors represents the total number of vectors allocated.
*
* When dynamic allocation is supported, let the host only allocate
* and enable a vector when it is in use in guest. nr_vectors represents
* the upper bound of vectors being enabled (but not all of the ranges
* is allocated or enabled).
*/
if (resizing) {
vdev->nr_vectors = nr + 1;
}
if (!vdev->defer_kvm_irq_routing) {
if (vdev->msix->noresize && resizing) {
vfio_disable_irqindex(&vdev->vbasedev, VFIO_PCI_MSIX_IRQ_INDEX);
ret = vfio_enable_vectors(vdev, true);
if (ret) {
error_report("vfio: failed to enable vectors, %d", ret);
}
} else {
Error *err = NULL;
int32_t fd;
if (vector->virq >= 0) {
fd = event_notifier_get_fd(&vector->kvm_interrupt);
} else {
fd = event_notifier_get_fd(&vector->interrupt);
}
if (!vfio_set_irq_signaling(&vdev->vbasedev,
VFIO_PCI_MSIX_IRQ_INDEX, nr,
VFIO_IRQ_SET_ACTION_TRIGGER, fd,
&err)) {
error_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.name);
}
}
}
/* Disable PBA emulation when nothing more is pending. */
clear_bit(nr, vdev->msix->pending);
if (find_first_bit(vdev->msix->pending,
vdev->nr_vectors) == vdev->nr_vectors) {
memory_region_set_enabled(&vdev->pdev.msix_pba_mmio, false);
trace_vfio_msix_pba_disable(vdev->vbasedev.name);
}
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)
{
VFIOPCIDevice *vdev = VFIO_PCI(pdev);
VFIOMSIVector *vector = &vdev->msi_vectors[nr];
trace_vfio_msix_vector_release(vdev->vbasedev.name, 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) {
int32_t fd = event_notifier_get_fd(&vector->interrupt);
Error *err = NULL;
if (!vfio_set_irq_signaling(&vdev->vbasedev, VFIO_PCI_MSIX_IRQ_INDEX,
nr, VFIO_IRQ_SET_ACTION_TRIGGER, fd,
&err)) {
error_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.name);
}
}
}
static void vfio_prepare_kvm_msi_virq_batch(VFIOPCIDevice *vdev)
{
assert(!vdev->defer_kvm_irq_routing);
vdev->defer_kvm_irq_routing = true;
vfio_route_change = kvm_irqchip_begin_route_changes(kvm_state);
}
static void vfio_commit_kvm_msi_virq_batch(VFIOPCIDevice *vdev)
{
int i;
assert(vdev->defer_kvm_irq_routing);
vdev->defer_kvm_irq_routing = false;
kvm_irqchip_commit_route_changes(&vfio_route_change);
for (i = 0; i < vdev->nr_vectors; i++) {
vfio_connect_kvm_msi_virq(&vdev->msi_vectors[i]);
}
}
static void vfio_msix_enable(VFIOPCIDevice *vdev)
{
int ret;
vfio_disable_interrupts(vdev);
vdev->msi_vectors = g_new0(VFIOMSIVector, vdev->msix->entries);
vdev->interrupt = VFIO_INT_MSIX;
/*
* Setting vector notifiers triggers synchronous vector-use
* callbacks for each active vector. Deferring to commit the KVM
* routes once rather than per vector provides a substantial
* performance improvement.
*/
vfio_prepare_kvm_msi_virq_batch(vdev);
if (msix_set_vector_notifiers(&vdev->pdev, vfio_msix_vector_use,
vfio_msix_vector_release, NULL)) {
error_report("vfio: msix_set_vector_notifiers failed");
}
vfio_commit_kvm_msi_virq_batch(vdev);
if (vdev->nr_vectors) {
ret = vfio_enable_vectors(vdev, true);
if (ret) {
error_report("vfio: failed to enable vectors, %d", ret);
}
} else {
/*
* 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 sets vector 0 with an
* invalid fd to make the physical device MSI-X enabled, but with no
* vectors enabled, just like the guest view.
*/
ret = vfio_enable_msix_no_vec(vdev);
if (ret) {
error_report("vfio: failed to enable MSI-X, %d", ret);
}
}
trace_vfio_msix_enable(vdev->vbasedev.name);
}
static void vfio_msi_enable(VFIOPCIDevice *vdev)
{
int ret, i;
vfio_disable_interrupts(vdev);
vdev->nr_vectors = msi_nr_vectors_allocated(&vdev->pdev);
retry:
/*
* Setting vector notifiers needs to enable route for each vector.
* Deferring to commit the KVM routes once rather than per vector
* provides a substantial performance improvement.
*/
vfio_prepare_kvm_msi_virq_batch(vdev);
vdev->msi_vectors = g_new0(VFIOMSIVector, vdev->nr_vectors);
for (i = 0; i < vdev->nr_vectors; i++) {
VFIOMSIVector *vector = &vdev->msi_vectors[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(vdev, vector, i, false);
}
vfio_commit_kvm_msi_virq_batch(vdev);
/* 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 {
error_report("vfio: Error: Failed to enable %d "
"MSI vectors, retry with %d", vdev->nr_vectors, ret);
}
vfio_msi_disable_common(vdev);
if (ret > 0) {
vdev->nr_vectors = ret;
goto retry;
}
/*
* 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");
return;
}
trace_vfio_msi_enable(vdev->vbasedev.name, vdev->nr_vectors);
}
static void vfio_msi_disable_common(VFIOPCIDevice *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;
}
static void vfio_msix_disable(VFIOPCIDevice *vdev)
{
Error *err = NULL;
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);
}
}
/*
* Always clear MSI-X IRQ index. A PF device could have enabled
* MSI-X with no vectors. See vfio_msix_enable().
*/
vfio_disable_irqindex(&vdev->vbasedev, VFIO_PCI_MSIX_IRQ_INDEX);
vfio_msi_disable_common(vdev);
if (!vfio_intx_enable(vdev, &err)) {
error_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.name);
}
memset(vdev->msix->pending, 0,
BITS_TO_LONGS(vdev->msix->entries) * sizeof(unsigned long));
trace_vfio_msix_disable(vdev->vbasedev.name);
}
static void vfio_msi_disable(VFIOPCIDevice *vdev)
{
Error *err = NULL;
vfio_disable_irqindex(&vdev->vbasedev, VFIO_PCI_MSI_IRQ_INDEX);
vfio_msi_disable_common(vdev);
vfio_intx_enable(vdev, &err);
if (err) {
error_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.name);
}
trace_vfio_msi_disable(vdev->vbasedev.name);
}
static void vfio_update_msi(VFIOPCIDevice *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, &vdev->pdev);
}
}
static void vfio_pci_load_rom(VFIOPCIDevice *vdev)
{
struct vfio_region_info *reg_info;
uint64_t size;
off_t off = 0;
ssize_t bytes;
if (vfio_get_region_info(&vdev->vbasedev,
VFIO_PCI_ROM_REGION_INDEX, ®_info)) {
error_report("vfio: Error getting ROM info: %m");
return;
}
trace_vfio_pci_load_rom(vdev->vbasedev.name, (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;
g_free(reg_info);
if (!vdev->rom_size) {
vdev->rom_read_failed = true;
error_report("vfio-pci: Cannot read device rom at "
"%s", vdev->vbasedev.name);
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->vbasedev.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;
}
}
/*
* Test the ROM signature against our device, if the vendor is correct
* but the device ID doesn't match, store the correct device ID and
* recompute the checksum. Intel IGD devices need this and are known
* to have bogus checksums so we can't simply adjust the checksum.
*/
if (pci_get_word(vdev->rom) == 0xaa55 &&
pci_get_word(vdev->rom + 0x18) + 8 < vdev->rom_size &&
!memcmp(vdev->rom + pci_get_word(vdev->rom + 0x18), "PCIR", 4)) {
uint16_t vid, did;
vid = pci_get_word(vdev->rom + pci_get_word(vdev->rom + 0x18) + 4);
did = pci_get_word(vdev->rom + pci_get_word(vdev->rom + 0x18) + 6);
if (vid == vdev->vendor_id && did != vdev->device_id) {
int i;
uint8_t csum, *data = vdev->rom;
pci_set_word(vdev->rom + pci_get_word(vdev->rom + 0x18) + 6,
vdev->device_id);
data[6] = 0;
for (csum = 0, i = 0; i < vdev->rom_size; i++) {
csum += data[i];
}
data[6] = -csum;
}
}
}
static uint64_t vfio_rom_read(void *opaque, hwaddr addr, unsigned size)
{
VFIOPCIDevice *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->vbasedev.name, 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 void vfio_pci_size_rom(VFIOPCIDevice *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;
int fd = vdev->vbasedev.fd;
if (vdev->pdev.romfile || !vdev->pdev.rom_bar) {
/* Since pci handles romfile, just print a message and return */
if (vfio_opt_rom_in_denylist(vdev) && vdev->pdev.romfile) {
warn_report("Device at %s is known to cause system instability"
" issues during option rom execution",
vdev->vbasedev.name);
error_printf("Proceeding anyway since user specified romfile\n");
}
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(fd, &orig, 4, offset) != 4 ||
pwrite(fd, &size, 4, offset) != 4 ||
pread(fd, &size, 4, offset) != 4 ||
pwrite(fd, &orig, 4, offset) != 4) {
error_report("%s(%s) failed: %m", __func__, vdev->vbasedev.name);
return;
}
size = ~(le32_to_cpu(size) & PCI_ROM_ADDRESS_MASK) + 1;
if (!size) {
return;
}
if (vfio_opt_rom_in_denylist(vdev)) {
if (dev->opts && qdict_haskey(dev->opts, "rombar")) {
warn_report("Device at %s is known to cause system instability"
" issues during option rom execution",
vdev->vbasedev.name);
error_printf("Proceeding anyway since user specified"
" non zero value for rombar\n");
} else {
warn_report("Rom loading for device at %s has been disabled"
" due to system instability issues",
vdev->vbasedev.name);
error_printf("Specify rombar=1 or romfile to force\n");
return;
}
}
trace_vfio_pci_size_rom(vdev->vbasedev.name, size);
name = g_strdup_printf("vfio[%s].rom", vdev->vbasedev.name);
memory_region_init_io(&vdev->pdev.rom, OBJECT(vdev),
&vfio_rom_ops, vdev, name, size);
g_free(name);
pci_register_bar(&vdev->pdev, PCI_ROM_SLOT,
PCI_BASE_ADDRESS_SPACE_MEMORY, &vdev->pdev.rom);
vdev->rom_read_failed = false;
}
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);
}
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,
};
/*
* Expand memory region of sub-page(size < PAGE_SIZE) MMIO BAR to page
* size if the BAR is in an exclusive page in host so that we could map
* this BAR to guest. But this sub-page BAR may not occupy an exclusive
* page in guest. So we should set the priority of the expanded memory
* region to zero in case of overlap with BARs which share the same page
* with the sub-page BAR in guest. Besides, we should also recover the
* size of this sub-page BAR when its base address is changed in guest
* and not page aligned any more.
*/
static void vfio_sub_page_bar_update_mapping(PCIDevice *pdev, int bar)
{
VFIOPCIDevice *vdev = VFIO_PCI(pdev);
VFIORegion *region = &vdev->bars[bar].region;
MemoryRegion *mmap_mr, *region_mr, *base_mr;
PCIIORegion *r;
pcibus_t bar_addr;
uint64_t size = region->size;
/* Make sure that the whole region is allowed to be mmapped */
if (region->nr_mmaps != 1 || !region->mmaps[0].mmap ||
region->mmaps[0].size != region->size) {
return;
}
r = &pdev->io_regions[bar];
bar_addr = r->addr;
base_mr = vdev->bars[bar].mr;
region_mr = region->mem;
mmap_mr = ®ion->mmaps[0].mem;
/* If BAR is mapped and page aligned, update to fill PAGE_SIZE */
if (bar_addr != PCI_BAR_UNMAPPED &&
!(bar_addr & ~qemu_real_host_page_mask())) {
size = qemu_real_host_page_size();
}
memory_region_transaction_begin();
if (vdev->bars[bar].size < size) {
memory_region_set_size(base_mr, size);
}
memory_region_set_size(region_mr, size);
memory_region_set_size(mmap_mr, size);
if (size != vdev->bars[bar].size && memory_region_is_mapped(base_mr)) {
memory_region_del_subregion(r->address_space, base_mr);
memory_region_add_subregion_overlap(r->address_space,
bar_addr, base_mr, 0);
}
memory_region_transaction_commit();
}
/*
* PCI config space
*/
uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len)
{
VFIOPCIDevice *vdev = VFIO_PCI(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->vbasedev.fd, &phys_val, len,
vdev->config_offset + addr);
if (ret != len) {
error_report("%s(%s, 0x%x, 0x%x) failed: %m",
__func__, vdev->vbasedev.name, 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->vbasedev.name, addr, len, val);
return val;
}
void vfio_pci_write_config(PCIDevice *pdev,
uint32_t addr, uint32_t val, int len)
{
VFIOPCIDevice *vdev = VFIO_PCI(pdev);
uint32_t val_le = cpu_to_le32(val);
trace_vfio_pci_write_config(vdev->vbasedev.name, addr, val, len);
/* Write everything to VFIO, let it filter out what we can't write */
if (pwrite(vdev->vbasedev.fd, &val_le, len, vdev->config_offset + addr)
!= len) {
error_report("%s(%s, 0x%x, 0x%x, 0x%x) failed: %m",
__func__, vdev->vbasedev.name, 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_msi_enable(vdev);
}
} else {
if (!is_enabled) {
vfio_msi_disable(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_msix_enable(vdev);
} else if (was_enabled && !is_enabled) {
vfio_msix_disable(vdev);
}
} else if (ranges_overlap(addr, len, PCI_BASE_ADDRESS_0, 24) ||
range_covers_byte(addr, len, PCI_COMMAND)) {
pcibus_t old_addr[PCI_NUM_REGIONS - 1];
int bar;
for (bar = 0; bar < PCI_ROM_SLOT; bar++) {
old_addr[bar] = pdev->io_regions[bar].addr;
}
pci_default_write_config(pdev, addr, val, len);
for (bar = 0; bar < PCI_ROM_SLOT; bar++) {
if (old_addr[bar] != pdev->io_regions[bar].addr &&
vdev->bars[bar].region.size > 0 &&
vdev->bars[bar].region.size < qemu_real_host_page_size()) {
vfio_sub_page_bar_update_mapping(pdev, bar);
}
}
} else {
/* Write everything to QEMU to keep emulated bits correct */
pci_default_write_config(pdev, addr, val, len);
}
}
/*
* Interrupt setup
*/
static void vfio_disable_interrupts(VFIOPCIDevice *vdev)
{
/*
* More complicated than it looks. Disabling MSI/X transitions the
* device to INTx mode (if supported). Therefore we need to first
* disable MSI/X and then cleanup by disabling INTx.
*/
if (vdev->interrupt == VFIO_INT_MSIX) {
vfio_msix_disable(vdev);
} else if (vdev->interrupt == VFIO_INT_MSI) {
vfio_msi_disable(vdev);
}
if (vdev->interrupt == VFIO_INT_INTx) {
vfio_intx_disable(vdev);
}
}
static bool vfio_msi_setup(VFIOPCIDevice *vdev, int pos, Error **errp)
{
uint16_t ctrl;
bool msi_64bit, msi_maskbit;
int ret, entries;
Error *err = NULL;
if (pread(vdev->vbasedev.fd, &ctrl, sizeof(ctrl),
vdev->config_offset + pos + PCI_CAP_FLAGS) != sizeof(ctrl)) {
error_setg_errno(errp, errno, "failed reading MSI PCI_CAP_FLAGS");
return false;
}
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_msi_setup(vdev->vbasedev.name, pos);
ret = msi_init(&vdev->pdev, pos, entries, msi_64bit, msi_maskbit, &err);
if (ret < 0) {
if (ret == -ENOTSUP) {
return true;
}
error_propagate_prepend(errp, err, "msi_init failed: ");
return false;
}
vdev->msi_cap_size = 0xa + (msi_maskbit ? 0xa : 0) + (msi_64bit ? 0x4 : 0);
return true;
}
static void vfio_pci_fixup_msix_region(VFIOPCIDevice *vdev)
{
off_t start, end;
VFIORegion *region = &vdev->bars[vdev->msix->table_bar].region;
/*
* If the host driver allows mapping of a MSIX data, we are going to
* do map the entire BAR and emulate MSIX table on top of that.
*/
if (vfio_has_region_cap(&vdev->vbasedev, region->nr,
VFIO_REGION_INFO_CAP_MSIX_MAPPABLE)) {
return;
}
/*
* We expect to find a single mmap covering the whole BAR, anything else
* means it's either unsupported or already setup.
*/
if (region->nr_mmaps != 1 || region->mmaps[0].offset ||
region->size != region->mmaps[0].size) {
return;
}
/* MSI-X table start and end aligned to host page size */
start = vdev->msix->table_offset & qemu_real_host_page_mask();
end = REAL_HOST_PAGE_ALIGN((uint64_t)vdev->msix->table_offset +
(vdev->msix->entries * PCI_MSIX_ENTRY_SIZE));
/*
* Does the MSI-X table cover the beginning of the BAR? The whole BAR?
* NB - Host page size is necessarily a power of two and so is the PCI
* BAR (not counting EA yet), therefore if we have host page aligned
* @start and @end, then any remainder of the BAR before or after those
* must be at least host page sized and therefore mmap'able.
*/
if (!start) {
if (end >= region->size) {
region->nr_mmaps = 0;
g_free(region->mmaps);
region->mmaps = NULL;
trace_vfio_msix_fixup(vdev->vbasedev.name,
vdev->msix->table_bar, 0, 0);
} else {
region->mmaps[0].offset = end;
region->mmaps[0].size = region->size - end;
trace_vfio_msix_fixup(vdev->vbasedev.name,
vdev->msix->table_bar, region->mmaps[0].offset,
region->mmaps[0].offset + region->mmaps[0].size);
}
/* Maybe it's aligned at the end of the BAR */
} else if (end >= region->size) {
region->mmaps[0].size = start;
trace_vfio_msix_fixup(vdev->vbasedev.name,
vdev->msix->table_bar, region->mmaps[0].offset,
region->mmaps[0].offset + region->mmaps[0].size);
/* Otherwise it must split the BAR */
} else {
region->nr_mmaps = 2;
region->mmaps = g_renew(VFIOMmap, region->mmaps, 2);
memcpy(®ion->mmaps[1], ®ion->mmaps[0], sizeof(VFIOMmap));
region->mmaps[0].size = start;
trace_vfio_msix_fixup(vdev->vbasedev.name,
vdev->msix->table_bar, region->mmaps[0].offset,
region->mmaps[0].offset + region->mmaps[0].size);
region->mmaps[1].offset = end;
region->mmaps[1].size = region->size - end;
trace_vfio_msix_fixup(vdev->vbasedev.name,
vdev->msix->table_bar, region->mmaps[1].offset,
region->mmaps[1].offset + region->mmaps[1].size);
}
}
static bool vfio_pci_relocate_msix(VFIOPCIDevice *vdev, Error **errp)
{
int target_bar = -1;
size_t msix_sz;
if (!vdev->msix || vdev->msix_relo == OFF_AUTOPCIBAR_OFF) {
return true;
}
/* The actual minimum size of MSI-X structures */
msix_sz = (vdev->msix->entries * PCI_MSIX_ENTRY_SIZE) +
(QEMU_ALIGN_UP(vdev->msix->entries, 64) / 8);
/* Round up to host pages, we don't want to share a page */
msix_sz = REAL_HOST_PAGE_ALIGN(msix_sz);
/* PCI BARs must be a power of 2 */
msix_sz = pow2ceil(msix_sz);
if (vdev->msix_relo == OFF_AUTOPCIBAR_AUTO) {
/*
* TODO: Lookup table for known devices.
*
* Logically we might use an algorithm here to select the BAR adding
* the least additional MMIO space, but we cannot programmatically
* predict the driver dependency on BAR ordering or sizing, therefore
* 'auto' becomes a lookup for combinations reported to work.
*/
if (target_bar < 0) {
error_setg(errp, "No automatic MSI-X relocation available for "
"device %04x:%04x", vdev->vendor_id, vdev->device_id);
return false;
}
} else {
target_bar = (int)(vdev->msix_relo - OFF_AUTOPCIBAR_BAR0);
}
/* I/O port BARs cannot host MSI-X structures */
if (vdev->bars[target_bar].ioport) {
error_setg(errp, "Invalid MSI-X relocation BAR %d, "
"I/O port BAR", target_bar);
return false;
}
/* Cannot use a BAR in the "shadow" of a 64-bit BAR */
if (!vdev->bars[target_bar].size &&
target_bar > 0 && vdev->bars[target_bar - 1].mem64) {
error_setg(errp, "Invalid MSI-X relocation BAR %d, "
"consumed by 64-bit BAR %d", target_bar, target_bar - 1);
return false;
}
/* 2GB max size for 32-bit BARs, cannot double if already > 1G */
if (vdev->bars[target_bar].size > 1 * GiB &&
!vdev->bars[target_bar].mem64) {
error_setg(errp, "Invalid MSI-X relocation BAR %d, "
"no space to extend 32-bit BAR", target_bar);
return false;
}
/*
* If adding a new BAR, test if we can make it 64bit. We make it
* prefetchable since QEMU MSI-X emulation has no read side effects
* and doing so makes mapping more flexible.
*/
if (!vdev->bars[target_bar].size) {
if (target_bar < (PCI_ROM_SLOT - 1) &&
!vdev->bars[target_bar + 1].size) {
vdev->bars[target_bar].mem64 = true;
vdev->bars[target_bar].type = PCI_BASE_ADDRESS_MEM_TYPE_64;
}
vdev->bars[target_bar].type |= PCI_BASE_ADDRESS_MEM_PREFETCH;
vdev->bars[target_bar].size = msix_sz;
vdev->msix->table_offset = 0;
} else {
vdev->bars[target_bar].size = MAX(vdev->bars[target_bar].size * 2,
msix_sz * 2);
/*
* Due to above size calc, MSI-X always starts halfway into the BAR,
* which will always be a separate host page.
*/
vdev->msix->table_offset = vdev->bars[target_bar].size / 2;
}
vdev->msix->table_bar = target_bar;
vdev->msix->pba_bar = target_bar;
/* Requires 8-byte alignment, but PCI_MSIX_ENTRY_SIZE guarantees that */
vdev->msix->pba_offset = vdev->msix->table_offset +
(vdev->msix->entries * PCI_MSIX_ENTRY_SIZE);
trace_vfio_msix_relo(vdev->vbasedev.name,
vdev->msix->table_bar, vdev->msix->table_offset);
return true;
}
/*
* 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 bool vfio_msix_early_setup(VFIOPCIDevice *vdev, Error **errp)
{
uint8_t pos;
uint16_t ctrl;
uint32_t table, pba;
int ret, fd = vdev->vbasedev.fd;
struct vfio_irq_info irq_info = { .argsz = sizeof(irq_info),
.index = VFIO_PCI_MSIX_IRQ_INDEX };
VFIOMSIXInfo *msix;
pos = pci_find_capability(&vdev->pdev, PCI_CAP_ID_MSIX);
if (!pos) {
return true;
}
if (pread(fd, &ctrl, sizeof(ctrl),
vdev->config_offset + pos + PCI_MSIX_FLAGS) != sizeof(ctrl)) {
error_setg_errno(errp, errno, "failed to read PCI MSIX FLAGS");
return false;
}
if (pread(fd, &table, sizeof(table),
vdev->config_offset + pos + PCI_MSIX_TABLE) != sizeof(table)) {
error_setg_errno(errp, errno, "failed to read PCI MSIX TABLE");
return false;
}
if (pread(fd, &pba, sizeof(pba),
vdev->config_offset + pos + PCI_MSIX_PBA) != sizeof(pba)) {
error_setg_errno(errp, errno, "failed to read PCI MSIX PBA");
return false;
}
ctrl = le16_to_cpu(ctrl);
table = le32_to_cpu(table);
pba = le32_to_cpu(pba);
msix = g_malloc0(sizeof(*msix));
msix->table_bar = table & PCI_MSIX_FLAGS_BIRMASK;
msix->table_offset = table & ~PCI_MSIX_FLAGS_BIRMASK;
msix->pba_bar = pba & PCI_MSIX_FLAGS_BIRMASK;
msix->pba_offset = pba & ~PCI_MSIX_FLAGS_BIRMASK;
msix->entries = (ctrl & PCI_MSIX_FLAGS_QSIZE) + 1;
ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_IRQ_INFO, &irq_info);
if (ret < 0) {
error_setg_errno(errp, -ret, "failed to get MSI-X irq info");
g_free(msix);
return false;
}
msix->noresize = !!(irq_info.flags & VFIO_IRQ_INFO_NORESIZE);
/*
* Test the size of the pba_offset variable and catch if it extends outside
* of the specified BAR. If it is the case, we need to apply a hardware
* specific quirk if the device is known or we have a broken configuration.
*/
if (msix->pba_offset >= vdev->bars[msix->pba_bar].region.size) {
/*
* Chelsio T5 Virtual Function devices are encoded as 0x58xx for T5
* adapters. The T5 hardware returns an incorrect value of 0x8000 for
* the VF PBA offset while the BAR itself is only 8k. The correct value
* is 0x1000, so we hard code that here.
*/
if (vdev->vendor_id == PCI_VENDOR_ID_CHELSIO &&
(vdev->device_id & 0xff00) == 0x5800) {
msix->pba_offset = 0x1000;
/*
* BAIDU KUNLUN Virtual Function devices for KUNLUN AI processor
* return an incorrect value of 0x460000 for the VF PBA offset while
* the BAR itself is only 0x10000. The correct value is 0xb400.
*/
} else if (vfio_pci_is(vdev, PCI_VENDOR_ID_BAIDU,
PCI_DEVICE_ID_KUNLUN_VF)) {
msix->pba_offset = 0xb400;
} else if (vdev->msix_relo == OFF_AUTOPCIBAR_OFF) {
error_setg(errp, "hardware reports invalid configuration, "
"MSIX PBA outside of specified BAR");
g_free(msix);
return false;
}
}
trace_vfio_msix_early_setup(vdev->vbasedev.name, pos, msix->table_bar,
msix->table_offset, msix->entries,
msix->noresize);
vdev->msix = msix;
vfio_pci_fixup_msix_region(vdev);
return vfio_pci_relocate_msix(vdev, errp);
}
static bool vfio_msix_setup(VFIOPCIDevice *vdev, int pos, Error **errp)
{
int ret;
Error *err = NULL;
vdev->msix->pending = g_new0(unsigned long,
BITS_TO_LONGS(vdev->msix->entries));
ret = msix_init(&vdev->pdev, vdev->msix->entries,
vdev->bars[vdev->msix->table_bar].mr,
vdev->msix->table_bar, vdev->msix->table_offset,
vdev->bars[vdev->msix->pba_bar].mr,
vdev->msix->pba_bar, vdev->msix->pba_offset, pos,
&err);
if (ret < 0) {
if (ret == -ENOTSUP) {
warn_report_err(err);
return true;
}
error_propagate(errp, err);
return false;
}
/*
* The PCI spec suggests that devices provide additional alignment for
* MSI-X structures and avoid overlapping non-MSI-X related registers.
* For an assigned device, this hopefully means that emulation of MSI-X
* structures does not affect the performance of the device. If devices
* fail to provide that alignment, a significant performance penalty may
* result, for instance Mellanox MT27500 VFs:
* http://www.spinics.net/lists/kvm/msg125881.html
*
* The PBA is simply not that important for such a serious regression and
* most drivers do not appear to look at it. The solution for this is to
* disable the PBA MemoryRegion unless it's being used. We disable it
* here and only enable it if a masked vector fires through QEMU. As the
* vector-use notifier is called, which occurs on unmask, we test whether
* PBA emulation is needed and again disable if not.
*/
memory_region_set_enabled(&vdev->pdev.msix_pba_mmio, false);
/*
* The emulated machine may provide a paravirt interface for MSIX setup
* so it is not strictly necessary to emulate MSIX here. This becomes
* helpful when frequently accessed MMIO registers are located in
* subpages adjacent to the MSIX table but the MSIX data containing page
* cannot be mapped because of a host page size bigger than the MSIX table
* alignment.
*/
if (object_property_get_bool(OBJECT(qdev_get_machine()),
"vfio-no-msix-emulation", NULL)) {
memory_region_set_enabled(&vdev->pdev.msix_table_mmio, false);
}
return true;
}
static void vfio_teardown_msi(VFIOPCIDevice *vdev)
{
msi_uninit(&vdev->pdev);
if (vdev->msix) {
msix_uninit(&vdev->pdev,
vdev->bars[vdev->msix->table_bar].mr,
vdev->bars[vdev->msix->pba_bar].mr);
g_free(vdev->msix->pending);
}
}
/*
* Resource setup
*/
static void vfio_mmap_set_enabled(VFIOPCIDevice *vdev, bool enabled)
{
int i;
for (i = 0; i < PCI_ROM_SLOT; i++) {
vfio_region_mmaps_set_enabled(&vdev->bars[i].region, enabled);
}
}
static void vfio_bar_prepare(VFIOPCIDevice *vdev, int nr)
{
VFIOBAR *bar = &vdev->bars[nr];
uint32_t pci_bar;
int ret;
/* Skip both unimplemented BARs and the upper half of 64bit BARS. */
if (!bar->region.size) {
return;
}
/* Determine what type of BAR this is for registration */
ret = pread(vdev->vbasedev.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);
bar->type = pci_bar & (bar->ioport ? ~PCI_BASE_ADDRESS_IO_MASK :
~PCI_BASE_ADDRESS_MEM_MASK);
bar->size = bar->region.size;
}
static void vfio_bars_prepare(VFIOPCIDevice *vdev)
{
int i;
for (i = 0; i < PCI_ROM_SLOT; i++) {
vfio_bar_prepare(vdev, i);
}
}
static void vfio_bar_register(VFIOPCIDevice *vdev, int nr)
{
VFIOBAR *bar = &vdev->bars[nr];
char *name;
if (!bar->size) {
return;
}
bar->mr = g_new0(MemoryRegion, 1);
name = g_strdup_printf("%s base BAR %d", vdev->vbasedev.name, nr);
memory_region_init_io(bar->mr, OBJECT(vdev), NULL, NULL, name, bar->size);
g_free(name);
if (bar->region.size) {
memory_region_add_subregion(bar->mr, 0, bar->region.mem);
if (vfio_region_mmap(&bar->region)) {
error_report("Failed to mmap %s BAR %d. Performance may be slow",
vdev->vbasedev.name, nr);
}
}
pci_register_bar(&vdev->pdev, nr, bar->type, bar->mr);
}
static void vfio_bars_register(VFIOPCIDevice *vdev)
{
int i;
for (i = 0; i < PCI_ROM_SLOT; i++) {
vfio_bar_register(vdev, i);
}
}
static void vfio_bars_exit(VFIOPCIDevice *vdev)
{
int i;
for (i = 0; i < PCI_ROM_SLOT; i++) {
VFIOBAR *bar = &vdev->bars[i];
vfio_bar_quirk_exit(vdev, i);
vfio_region_exit(&bar->region);
if (bar->region.size) {
memory_region_del_subregion(bar->mr, bar->region.mem);
}
}
if (vdev->vga) {
pci_unregister_vga(&vdev->pdev);
vfio_vga_quirk_exit(vdev);
}
}
static void vfio_bars_finalize(VFIOPCIDevice *vdev)
{
int i;
for (i = 0; i < PCI_ROM_SLOT; i++) {
VFIOBAR *bar = &vdev->bars[i];
vfio_bar_quirk_finalize(vdev, i);
vfio_region_finalize(&bar->region);
if (bar->mr) {
assert(bar->size);
object_unparent(OBJECT(bar->mr));
g_free(bar->mr);
bar->mr = NULL;
}
}
if (vdev->vga) {
vfio_vga_quirk_finalize(vdev);
for (i = 0; i < ARRAY_SIZE(vdev->vga->region); i++) {
object_unparent(OBJECT(&vdev->vga->region[i].mem));
}
g_free(vdev->vga);
}
}
/*
* General setup
*/
static uint8_t vfio_std_cap_max_size(PCIDevice *pdev, uint8_t pos)
{
uint8_t tmp;
uint16_t next = PCI_CONFIG_SPACE_SIZE;
for (tmp = pdev->config[PCI_CAPABILITY_LIST]; tmp;
tmp = pdev->config[tmp + PCI_CAP_LIST_NEXT]) {
if (tmp > pos && tmp < next) {
next = tmp;
}
}
return next - pos;
}
static uint16_t vfio_ext_cap_max_size(const uint8_t *config, uint16_t pos)
{
uint16_t tmp, next = PCIE_CONFIG_SPACE_SIZE;
for (tmp = PCI_CONFIG_SPACE_SIZE; tmp;
tmp = PCI_EXT_CAP_NEXT(pci_get_long(config + tmp))) {
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(VFIOPCIDevice *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(VFIOPCIDevice *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 void vfio_pci_enable_rp_atomics(VFIOPCIDevice *vdev)
{
struct vfio_device_info_cap_pci_atomic_comp *cap;
g_autofree struct vfio_device_info *info = NULL;
PCIBus *bus = pci_get_bus(&vdev->pdev);
PCIDevice *parent = bus->parent_dev;
struct vfio_info_cap_header *hdr;
uint32_t mask = 0;
uint8_t *pos;
/*
* PCIe Atomic Ops completer support is only added automatically for single
* function devices downstream of a root port supporting DEVCAP2. Support
* is added during realize and, if added, removed during device exit. The
* single function requirement avoids conflicting requirements should a
* slot be composed of multiple devices with differing capabilities.
*/
if (pci_bus_is_root(bus) || !parent || !parent->exp.exp_cap ||
pcie_cap_get_type(parent) != PCI_EXP_TYPE_ROOT_PORT ||
pcie_cap_get_version(parent) != PCI_EXP_FLAGS_VER2 ||
vdev->pdev.devfn ||
vdev->pdev.cap_present & QEMU_PCI_CAP_MULTIFUNCTION) {
return;
}
pos = parent->config + parent->exp.exp_cap + PCI_EXP_DEVCAP2;
/* Abort if there'a already an Atomic Ops configuration on the root port */
if (pci_get_long(pos) & (PCI_EXP_DEVCAP2_ATOMIC_COMP32 |
PCI_EXP_DEVCAP2_ATOMIC_COMP64 |
PCI_EXP_DEVCAP2_ATOMIC_COMP128)) {
return;
}
info = vfio_get_device_info(vdev->vbasedev.fd);
if (!info) {
return;
}
hdr = vfio_get_device_info_cap(info, VFIO_DEVICE_INFO_CAP_PCI_ATOMIC_COMP);
if (!hdr) {
return;
}
cap = (void *)hdr;
if (cap->flags & VFIO_PCI_ATOMIC_COMP32) {
mask |= PCI_EXP_DEVCAP2_ATOMIC_COMP32;
}
if (cap->flags & VFIO_PCI_ATOMIC_COMP64) {
mask |= PCI_EXP_DEVCAP2_ATOMIC_COMP64;
}
if (cap->flags & VFIO_PCI_ATOMIC_COMP128) {
mask |= PCI_EXP_DEVCAP2_ATOMIC_COMP128;
}
if (!mask) {
return;
}
pci_long_test_and_set_mask(pos, mask);
vdev->clear_parent_atomics_on_exit = true;
}
static void vfio_pci_disable_rp_atomics(VFIOPCIDevice *vdev)
{
if (vdev->clear_parent_atomics_on_exit) {
PCIDevice *parent = pci_get_bus(&vdev->pdev)->parent_dev;
uint8_t *pos = parent->config + parent->exp.exp_cap + PCI_EXP_DEVCAP2;
pci_long_test_and_clear_mask(pos, PCI_EXP_DEVCAP2_ATOMIC_COMP32 |
PCI_EXP_DEVCAP2_ATOMIC_COMP64 |
PCI_EXP_DEVCAP2_ATOMIC_COMP128);
}
}
static bool vfio_setup_pcie_cap(VFIOPCIDevice *vdev, int pos, uint8_t size,
Error **errp)
{
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_setg(errp, "assignment of PCIe type 0x%x "
"devices is not currently supported", type);
return false;
}
if (!pci_bus_is_express(pci_get_bus(&vdev->pdev))) {
PCIBus *bus = pci_get_bus(&vdev->pdev);
PCIDevice *bridge;
/*
* Traditionally PCI device assignment exposes the PCIe capability
* as-is on non-express buses. The reason being that some drivers
* simply assume that it's there, for example tg3. However when
* we're running on a native PCIe machine type, like Q35, we need
* to hide the PCIe capability. The reason for this is twofold;
* first Windows guests get a Code 10 error when the PCIe capability
* is exposed in this configuration. Therefore express devices won't
* work at all unless they're attached to express buses in the VM.
* Second, a native PCIe machine introduces the possibility of fine
* granularity IOMMUs supporting both translation and isolation.
* Guest code to discover the IOMMU visibility of a device, such as
* IOMMU grouping code on Linux, is very aware of device types and
* valid transitions between bus types. An express device on a non-
* express bus is not a valid combination on bare metal systems.
*
* Drivers that require a PCIe capability to make the device
* functional are simply going to need to have their devices placed
* on a PCIe bus in the VM.
*/
while (!pci_bus_is_root(bus)) {
bridge = pci_bridge_get_device(bus);
bus = pci_get_bus(bridge);
}
if (pci_bus_is_express(bus)) {
return true;
}
} else if (pci_bus_is_root(pci_get_bus(&vdev->pdev))) {
/*
* 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 true;
}
} 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,
QEMU_PCI_EXP_LNKCAP_MLW(QEMU_PCI_EXP_LNK_X1) |
QEMU_PCI_EXP_LNKCAP_MLS(QEMU_PCI_EXP_LNK_2_5GT), ~0);
vfio_add_emulated_word(vdev, pos + PCI_EXP_LNKCTL, 0, ~0);
}
vfio_pci_enable_rp_atomics(vdev);
}
/*
* Intel 82599 SR-IOV VFs report an invalid PCIe capability version 0
* (Niantic errate #35) causing Windows to error with a Code 10 for the
* device on Q35. Fixup any such devices to report version 1. If we
* were to remove the capability entirely the guest would lose extended
* config space.
*/
if ((flags & PCI_EXP_FLAGS_VERS) == 0) {
vfio_add_emulated_word(vdev, pos + PCI_CAP_FLAGS,
1, PCI_EXP_FLAGS_VERS);
}
pos = pci_add_capability(&vdev->pdev, PCI_CAP_ID_EXP, pos, size,
errp);
if (pos < 0) {
return false;
}
vdev->pdev.exp.exp_cap = pos;
return true;
}
static void vfio_check_pcie_flr(VFIOPCIDevice *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->vbasedev.name);
vdev->has_flr = true;
}
}
static void vfio_check_pm_reset(VFIOPCIDevice *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->vbasedev.name);
vdev->has_pm_reset = true;
}
}
static void vfio_check_af_flr(VFIOPCIDevice *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->vbasedev.name);
vdev->has_flr = true;
}
}
static bool vfio_add_vendor_specific_cap(VFIOPCIDevice *vdev, int pos,
uint8_t size, Error **errp)
{
PCIDevice *pdev = &vdev->pdev;
pos = pci_add_capability(pdev, PCI_CAP_ID_VNDR, pos, size, errp);
if (pos < 0) {
return false;
}
/*
* Exempt config space check for Vendor Specific Information during
* restore/load.
* Config space check is still enforced for 3 byte VSC header.
*/
if (vdev->skip_vsc_check && size > 3) {
memset(pdev->cmask + pos + 3, 0, size - 3);
}
return true;
}
static bool vfio_add_std_cap(VFIOPCIDevice *vdev, uint8_t pos, Error **errp)
{
ERRP_GUARD();
PCIDevice *pdev = &vdev->pdev;
uint8_t cap_id, next, size;
bool ret;
cap_id = pdev->config[pos];
next = pdev->config[pos + PCI_CAP_LIST_NEXT];
/*
* 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-calculate size above as cached config space
* will be changed as we unwind the stack.
*/
if (next) {
if (!vfio_add_std_cap(vdev, next, errp)) {
return false;
}
} 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;
ret = vfio_add_virt_caps(vdev, errp);
if (ret) {
return false;
}
}
/* Scale down size, esp in case virt caps were added above */
size = MIN(size, vfio_std_cap_max_size(pdev, pos));
/* Use emulated next pointer to allow dropping caps */
pci_set_byte(vdev->emulated_config_bits + pos + PCI_CAP_LIST_NEXT, 0xff);
switch (cap_id) {
case PCI_CAP_ID_MSI:
ret = vfio_msi_setup(vdev, pos, errp);
break;
case PCI_CAP_ID_EXP:
vfio_check_pcie_flr(vdev, pos);
ret = vfio_setup_pcie_cap(vdev, pos, size, errp);
break;
case PCI_CAP_ID_MSIX:
ret = vfio_msix_setup(vdev, pos, errp);
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, errp) >= 0;
break;
case PCI_CAP_ID_AF:
vfio_check_af_flr(vdev, pos);
ret = pci_add_capability(pdev, cap_id, pos, size, errp) >= 0;
break;
case PCI_CAP_ID_VNDR:
ret = vfio_add_vendor_specific_cap(vdev, pos, size, errp);
break;
default:
ret = pci_add_capability(pdev, cap_id, pos, size, errp) >= 0;
break;
}
if (!ret) {
error_prepend(errp,
"failed to add PCI capability 0x%x[0x%x]@0x%x: ",
cap_id, size, pos);
}
return ret;
}
static int vfio_setup_rebar_ecap(VFIOPCIDevice *vdev, uint16_t pos)
{
uint32_t ctrl;
int i, nbar;
ctrl = pci_get_long(vdev->pdev.config + pos + PCI_REBAR_CTRL);
nbar = (ctrl & PCI_REBAR_CTRL_NBAR_MASK) >> PCI_REBAR_CTRL_NBAR_SHIFT;
for (i = 0; i < nbar; i++) {
uint32_t cap;
int size;
ctrl = pci_get_long(vdev->pdev.config + pos + PCI_REBAR_CTRL + (i * 8));
size = (ctrl & PCI_REBAR_CTRL_BAR_SIZE) >> PCI_REBAR_CTRL_BAR_SHIFT;
/* The cap register reports sizes 1MB to 128TB, with 4 reserved bits */
cap = size <= 27 ? 1U << (size + 4) : 0;
/*
* The PCIe spec (v6.0.1, 7.8.6) requires HW to support at least one
* size in the range 1MB to 512GB. We intend to mask all sizes except
* the one currently enabled in the size field, therefore if it's
* outside the range, hide the whole capability as this virtualization
* trick won't work. If >512GB resizable BARs start to appear, we
* might need an opt-in or reservation scheme in the kernel.
*/
if (!(cap & PCI_REBAR_CAP_SIZES)) {
return -EINVAL;
}
/* Hide all sizes reported in the ctrl reg per above requirement. */
ctrl &= (PCI_REBAR_CTRL_BAR_SIZE |
PCI_REBAR_CTRL_NBAR_MASK |
PCI_REBAR_CTRL_BAR_IDX);
/*
* The BAR size field is RW, however we've mangled the capability
* register such that we only report a single size, ie. the current
* BAR size. A write of an unsupported value is undefined, therefore
* the register field is essentially RO.
*/
vfio_add_emulated_long(vdev, pos + PCI_REBAR_CAP + (i * 8), cap, ~0);
vfio_add_emulated_long(vdev, pos + PCI_REBAR_CTRL + (i * 8), ctrl, ~0);
}
return 0;
}
static void vfio_add_ext_cap(VFIOPCIDevice *vdev)
{
PCIDevice *pdev = &vdev->pdev;
uint32_t header;
uint16_t cap_id, next, size;
uint8_t cap_ver;
uint8_t *config;
/* Only add extended caps if we have them and the guest can see them */
if (!pci_is_express(pdev) || !pci_bus_is_express(pci_get_bus(pdev)) ||
!pci_get_long(pdev->config + PCI_CONFIG_SPACE_SIZE)) {
return;
}
/*
* pcie_add_capability always inserts the new capability at the tail
* of the chain. Therefore to end up with a chain that matches the
* physical device, we cache the config space to avoid overwriting
* the original config space when we parse the extended capabilities.
*/
config = g_memdup(pdev->config, vdev->config_size);
/*
* Extended capabilities are chained with each pointing to the next, so we
* can drop anything other than the head of the chain simply by modifying
* the previous next pointer. Seed the head of the chain here such that
* we can simply skip any capabilities we want to drop below, regardless
* of their position in the chain. If this stub capability still exists
* after we add the capabilities we want to expose, update the capability
* ID to zero. Note that we cannot seed with the capability header being
* zero as this conflicts with definition of an absent capability chain
* and prevents capabilities beyond the head of the list from being added.
* By replacing the dummy capability ID with zero after walking the device
* chain, we also transparently mark extended capabilities as absent if
* no capabilities were added. Note that the PCIe spec defines an absence
* of extended capabilities to be determined by a value of zero for the
* capability ID, version, AND next pointer. A non-zero next pointer
* should be sufficient to indicate additional capabilities are present,
* which will occur if we call pcie_add_capability() below. The entire
* first dword is emulated to support this.
*
* NB. The kernel side does similar masking, so be prepared that our
* view of the device may also contain a capability ID zero in the head
* of the chain. Skip it for the same reason that we cannot seed the
* chain with a zero capability.
*/
pci_set_long(pdev->config + PCI_CONFIG_SPACE_SIZE,
PCI_EXT_CAP(0xFFFF, 0, 0));
pci_set_long(pdev->wmask + PCI_CONFIG_SPACE_SIZE, 0);
pci_set_long(vdev->emulated_config_bits + PCI_CONFIG_SPACE_SIZE, ~0);
for (next = PCI_CONFIG_SPACE_SIZE; next;
next = PCI_EXT_CAP_NEXT(pci_get_long(config + next))) {
header = pci_get_long(config + next);
cap_id = PCI_EXT_CAP_ID(header);
cap_ver = PCI_EXT_CAP_VER(header);
/*
* If it becomes important to configure extended 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_ext_cap_max_size(config, next);
/* Use emulated next pointer to allow dropping extended caps */
pci_long_test_and_set_mask(vdev->emulated_config_bits + next,
PCI_EXT_CAP_NEXT_MASK);
switch (cap_id) {
case 0: /* kernel masked capability */
case PCI_EXT_CAP_ID_SRIOV: /* Read-only VF BARs confuse OVMF */
case PCI_EXT_CAP_ID_ARI: /* XXX Needs next function virtualization */
trace_vfio_add_ext_cap_dropped(vdev->vbasedev.name, cap_id, next);
break;
case PCI_EXT_CAP_ID_REBAR:
if (!vfio_setup_rebar_ecap(vdev, next)) {
pcie_add_capability(pdev, cap_id, cap_ver, next, size);
}
break;
default:
pcie_add_capability(pdev, cap_id, cap_ver, next, size);
}
}
/* Cleanup chain head ID if necessary */
if (pci_get_word(pdev->config + PCI_CONFIG_SPACE_SIZE) == 0xFFFF) {
pci_set_word(pdev->config + PCI_CONFIG_SPACE_SIZE, 0);
}
g_free(config);
return;
}
static bool vfio_add_capabilities(VFIOPCIDevice *vdev, Error **errp)
{
PCIDevice *pdev = &vdev->pdev;
if (!(pdev->config[PCI_STATUS] & PCI_STATUS_CAP_LIST) ||
!pdev->config[PCI_CAPABILITY_LIST]) {
return true; /* Nothing to add */
}
if (!vfio_add_std_cap(vdev, pdev->config[PCI_CAPABILITY_LIST], errp)) {
return false;
}
vfio_add_ext_cap(vdev);
return true;
}
void vfio_pci_pre_reset(VFIOPCIDevice *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 disconnecting 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);
}
void vfio_pci_post_reset(VFIOPCIDevice *vdev)
{
Error *err = NULL;
int nr;
if (!vfio_intx_enable(vdev, &err)) {
error_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.name);
}
for (nr = 0; nr < PCI_NUM_REGIONS - 1; ++nr) {
off_t addr = vdev->config_offset + PCI_BASE_ADDRESS_0 + (4 * nr);
uint32_t val = 0;
uint32_t len = sizeof(val);
if (pwrite(vdev->vbasedev.fd, &val, len, addr) != len) {
error_report("%s(%s) reset bar %d failed: %m", __func__,
vdev->vbasedev.name, nr);
}
}
vfio_quirk_reset(vdev);
}
bool vfio_pci_host_match(PCIHostDeviceAddress *addr, const char *name)
{
char tmp[13];
sprintf(tmp, "%04x:%02x:%02x.%1x", addr->domain,
addr->bus, addr->slot, addr->function);
return (strcmp(tmp, name) == 0);
}
int vfio_pci_get_pci_hot_reset_info(VFIOPCIDevice *vdev,
struct vfio_pci_hot_reset_info **info_p)
{
struct vfio_pci_hot_reset_info *info;
int ret, count;
assert(info_p && !*info_p);
info = g_malloc0(sizeof(*info));
info->argsz = sizeof(*info);
ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_PCI_HOT_RESET_INFO, info);
if (ret && errno != ENOSPC) {
ret = -errno;
g_free(info);
if (!vdev->has_pm_reset) {
error_report("vfio: Cannot reset device %s, "
"no available reset mechanism.", vdev->vbasedev.name);
}
return ret;
}
count = info->count;
info = g_realloc(info, sizeof(*info) + (count * sizeof(info->devices[0])));
info->argsz = sizeof(*info) + (count * sizeof(info->devices[0]));
ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_PCI_HOT_RESET_INFO, info);
if (ret) {
ret = -errno;
g_free(info);
error_report("vfio: hot reset info failed: %m");
return ret;
}
*info_p = info;
return 0;
}
static int vfio_pci_hot_reset(VFIOPCIDevice *vdev, bool single)
{
VFIODevice *vbasedev = &vdev->vbasedev;
const VFIOIOMMUClass *ops = vbasedev->bcontainer->ops;
return ops->pci_hot_reset(vbasedev, single);
}
/*
* We want to differentiate hot reset of multiple 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(VFIOPCIDevice *vdev)
{
return vfio_pci_hot_reset(vdev, true);
}
static int vfio_pci_hot_reset_multi(VFIODevice *vbasedev)
{
VFIOPCIDevice *vdev = container_of(vbasedev, VFIOPCIDevice, vbasedev);
return vfio_pci_hot_reset(vdev, false);
}
static void vfio_pci_compute_needs_reset(VFIODevice *vbasedev)
{
VFIOPCIDevice *vdev = container_of(vbasedev, VFIOPCIDevice, vbasedev);
if (!vbasedev->reset_works || (!vdev->has_flr && vdev->has_pm_reset)) {
vbasedev->needs_reset = true;
}
}
static Object *vfio_pci_get_object(VFIODevice *vbasedev)
{
VFIOPCIDevice *vdev = container_of(vbasedev, VFIOPCIDevice, vbasedev);
return OBJECT(vdev);
}
static bool vfio_msix_present(void *opaque, int version_id)
{
PCIDevice *pdev = opaque;
return msix_present(pdev);
}
static bool vfio_display_migration_needed(void *opaque)
{
VFIOPCIDevice *vdev = opaque;
/*
* We need to migrate the VFIODisplay object if ramfb *migration* was
* explicitly requested (in which case we enforced both ramfb=on and
* display=on), or ramfb migration was left at the default "auto"
* setting, and *ramfb* was explicitly requested (in which case we
* enforced display=on).
*/
return vdev->ramfb_migrate == ON_OFF_AUTO_ON ||
(vdev->ramfb_migrate == ON_OFF_AUTO_AUTO && vdev->enable_ramfb);
}
static const VMStateDescription vmstate_vfio_display = {
.name = "VFIOPCIDevice/VFIODisplay",
.version_id = 1,
.minimum_version_id = 1,
.needed = vfio_display_migration_needed,
.fields = (const VMStateField[]){
VMSTATE_STRUCT_POINTER(dpy, VFIOPCIDevice, vfio_display_vmstate,
VFIODisplay),
VMSTATE_END_OF_LIST()
}
};
static const VMStateDescription vmstate_vfio_pci_config = {
.name = "VFIOPCIDevice",
.version_id = 1,
.minimum_version_id = 1,
.fields = (const VMStateField[]) {
VMSTATE_PCI_DEVICE(pdev, VFIOPCIDevice),
VMSTATE_MSIX_TEST(pdev, VFIOPCIDevice, vfio_msix_present),
VMSTATE_END_OF_LIST()
},
.subsections = (const VMStateDescription * const []) {
&vmstate_vfio_display,
NULL
}
};
static int vfio_pci_save_config(VFIODevice *vbasedev, QEMUFile *f, Error **errp)
{
VFIOPCIDevice *vdev = container_of(vbasedev, VFIOPCIDevice, vbasedev);
return vmstate_save_state_with_err(f, &vmstate_vfio_pci_config, vdev, NULL,
errp);
}
static int vfio_pci_load_config(VFIODevice *vbasedev, QEMUFile *f)
{
VFIOPCIDevice *vdev = container_of(vbasedev, VFIOPCIDevice, vbasedev);
PCIDevice *pdev = &vdev->pdev;
pcibus_t old_addr[PCI_NUM_REGIONS - 1];
int bar, ret;
for (bar = 0; bar < PCI_ROM_SLOT; bar++) {
old_addr[bar] = pdev->io_regions[bar].addr;
}
ret = vmstate_load_state(f, &vmstate_vfio_pci_config, vdev, 1);
if (ret) {
return ret;
}
vfio_pci_write_config(pdev, PCI_COMMAND,
pci_get_word(pdev->config + PCI_COMMAND), 2);
for (bar = 0; bar < PCI_ROM_SLOT; bar++) {
/*
* The address may not be changed in some scenarios
* (e.g. the VF driver isn't loaded in VM).
*/
if (old_addr[bar] != pdev->io_regions[bar].addr &&
vdev->bars[bar].region.size > 0 &&
vdev->bars[bar].region.size < qemu_real_host_page_size()) {
vfio_sub_page_bar_update_mapping(pdev, bar);
}
}
if (msi_enabled(pdev)) {
vfio_msi_enable(vdev);
} else if (msix_enabled(pdev)) {
vfio_msix_enable(vdev);
}
return ret;
}
static VFIODeviceOps vfio_pci_ops = {
.vfio_compute_needs_reset = vfio_pci_compute_needs_reset,
.vfio_hot_reset_multi = vfio_pci_hot_reset_multi,
.vfio_eoi = vfio_intx_eoi,
.vfio_get_object = vfio_pci_get_object,
.vfio_save_config = vfio_pci_save_config,
.vfio_load_config = vfio_pci_load_config,
};
bool vfio_populate_vga(VFIOPCIDevice *vdev, Error **errp)
{
VFIODevice *vbasedev = &vdev->vbasedev;
struct vfio_region_info *reg_info;
int ret;
ret = vfio_get_region_info(vbasedev, VFIO_PCI_VGA_REGION_INDEX, ®_info);
if (ret) {
error_setg_errno(errp, -ret,
"failed getting region info for VGA region index %d",
VFIO_PCI_VGA_REGION_INDEX);
return false;
}
if (!(reg_info->flags & VFIO_REGION_INFO_FLAG_READ) ||
!(reg_info->flags & VFIO_REGION_INFO_FLAG_WRITE) ||
reg_info->size < 0xbffff + 1) {
error_setg(errp, "unexpected VGA info, flags 0x%lx, size 0x%lx",
(unsigned long)reg_info->flags,
(unsigned long)reg_info->size);
g_free(reg_info);
return false;
}
vdev->vga = g_new0(VFIOVGA, 1);
vdev->vga->fd_offset = reg_info->offset;
vdev->vga->fd = vdev->vbasedev.fd;
g_free(reg_info);
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);
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);
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);
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);
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);
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);
return true;
}
static bool vfio_populate_device(VFIOPCIDevice *vdev, Error **errp)
{
VFIODevice *vbasedev = &vdev->vbasedev;
struct vfio_region_info *reg_info;
struct vfio_irq_info irq_info = { .argsz = sizeof(irq_info) };
int i, ret = -1;
/* Sanity check device */
if (!(vbasedev->flags & VFIO_DEVICE_FLAGS_PCI)) {
error_setg(errp, "this isn't a PCI device");
return false;
}
if (vbasedev->num_regions < VFIO_PCI_CONFIG_REGION_INDEX + 1) {
error_setg(errp, "unexpected number of io regions %u",
vbasedev->num_regions);
return false;
}
if (vbasedev->num_irqs < VFIO_PCI_MSIX_IRQ_INDEX + 1) {
error_setg(errp, "unexpected number of irqs %u", vbasedev->num_irqs);
return false;
}
for (i = VFIO_PCI_BAR0_REGION_INDEX; i < VFIO_PCI_ROM_REGION_INDEX; i++) {
char *name = g_strdup_printf("%s BAR %d", vbasedev->name, i);
ret = vfio_region_setup(OBJECT(vdev), vbasedev,
&vdev->bars[i].region, i, name);
g_free(name);
if (ret) {
error_setg_errno(errp, -ret, "failed to get region %d info", i);
return false;
}
QLIST_INIT(&vdev->bars[i].quirks);
}
ret = vfio_get_region_info(vbasedev,
VFIO_PCI_CONFIG_REGION_INDEX, ®_info);
if (ret) {
error_setg_errno(errp, -ret, "failed to get config info");
return false;
}
trace_vfio_populate_device_config(vdev->vbasedev.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;
g_free(reg_info);
if (vdev->features & VFIO_FEATURE_ENABLE_VGA) {
if (!vfio_populate_vga(vdev, errp)) {
error_append_hint(errp, "device does not support "
"requested feature x-vga\n");
return false;
}
}
irq_info.index = VFIO_PCI_ERR_IRQ_INDEX;
ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_IRQ_INFO, &irq_info);
if (ret) {
/* This can fail for an old kernel or legacy PCI dev */
trace_vfio_populate_device_get_irq_info_failure(strerror(errno));
} else if (irq_info.count == 1) {
vdev->pci_aer = true;
} else {
warn_report(VFIO_MSG_PREFIX
"Could not enable error recovery for the device",
vbasedev->name);
}
return true;
}
static void vfio_pci_put_device(VFIOPCIDevice *vdev)
{
vfio_detach_device(&vdev->vbasedev);
g_free(vdev->vbasedev.name);
g_free(vdev->msix);
}
static void vfio_err_notifier_handler(void *opaque)
{
VFIOPCIDevice *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(%s) Unrecoverable error detected. Please collect any data possible and then kill the guest", __func__, vdev->vbasedev.name);
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(VFIOPCIDevice *vdev)
{
Error *err = NULL;
int32_t fd;
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;
}
fd = event_notifier_get_fd(&vdev->err_notifier);
qemu_set_fd_handler(fd, vfio_err_notifier_handler, NULL, vdev);
if (!vfio_set_irq_signaling(&vdev->vbasedev, VFIO_PCI_ERR_IRQ_INDEX, 0,
VFIO_IRQ_SET_ACTION_TRIGGER, fd, &err)) {
error_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.name);
qemu_set_fd_handler(fd, NULL, NULL, vdev);
event_notifier_cleanup(&vdev->err_notifier);
vdev->pci_aer = false;
}
}
static void vfio_unregister_err_notifier(VFIOPCIDevice *vdev)
{
Error *err = NULL;
if (!vdev->pci_aer) {
return;
}
if (!vfio_set_irq_signaling(&vdev->vbasedev, VFIO_PCI_ERR_IRQ_INDEX, 0,
VFIO_IRQ_SET_ACTION_TRIGGER, -1, &err)) {
error_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.name);
}
qemu_set_fd_handler(event_notifier_get_fd(&vdev->err_notifier),
NULL, NULL, vdev);
event_notifier_cleanup(&vdev->err_notifier);
}
static void vfio_req_notifier_handler(void *opaque)
{
VFIOPCIDevice *vdev = opaque;
Error *err = NULL;
if (!event_notifier_test_and_clear(&vdev->req_notifier)) {
return;
}
qdev_unplug(DEVICE(vdev), &err);
if (err) {
warn_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.name);
}
}
static void vfio_register_req_notifier(VFIOPCIDevice *vdev)
{
struct vfio_irq_info irq_info = { .argsz = sizeof(irq_info),
.index = VFIO_PCI_REQ_IRQ_INDEX };
Error *err = NULL;
int32_t fd;
if (!(vdev->features & VFIO_FEATURE_ENABLE_REQ)) {
return;
}
if (ioctl(vdev->vbasedev.fd,
VFIO_DEVICE_GET_IRQ_INFO, &irq_info) < 0 || irq_info.count < 1) {
return;
}
if (event_notifier_init(&vdev->req_notifier, 0)) {
error_report("vfio: Unable to init event notifier for device request");
return;
}
fd = event_notifier_get_fd(&vdev->req_notifier);
qemu_set_fd_handler(fd, vfio_req_notifier_handler, NULL, vdev);
if (!vfio_set_irq_signaling(&vdev->vbasedev, VFIO_PCI_REQ_IRQ_INDEX, 0,
VFIO_IRQ_SET_ACTION_TRIGGER, fd, &err)) {
error_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.name);
qemu_set_fd_handler(fd, NULL, NULL, vdev);
event_notifier_cleanup(&vdev->req_notifier);
} else {
vdev->req_enabled = true;
}
}
static void vfio_unregister_req_notifier(VFIOPCIDevice *vdev)
{
Error *err = NULL;
if (!vdev->req_enabled) {
return;
}
if (!vfio_set_irq_signaling(&vdev->vbasedev, VFIO_PCI_REQ_IRQ_INDEX, 0,
VFIO_IRQ_SET_ACTION_TRIGGER, -1, &err)) {
error_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.name);
}
qemu_set_fd_handler(event_notifier_get_fd(&vdev->req_notifier),
NULL, NULL, vdev);
event_notifier_cleanup(&vdev->req_notifier);
vdev->req_enabled = false;
}
static void vfio_realize(PCIDevice *pdev, Error **errp)
{
ERRP_GUARD();
VFIOPCIDevice *vdev = VFIO_PCI(pdev);
VFIODevice *vbasedev = &vdev->vbasedev;
char *subsys;
int i, ret;
bool is_mdev;
char uuid[UUID_STR_LEN];
g_autofree char *name = NULL;
g_autofree char *tmp = NULL;
if (vbasedev->fd < 0 && !vbasedev->sysfsdev) {
if (!(~vdev->host.domain || ~vdev->host.bus ||
~vdev->host.slot || ~vdev->host.function)) {
error_setg(errp, "No provided host device");
error_append_hint(errp, "Use -device vfio-pci,host=DDDD:BB:DD.F "
#ifdef CONFIG_IOMMUFD
"or -device vfio-pci,fd=DEVICE_FD "
#endif
"or -device vfio-pci,sysfsdev=PATH_TO_DEVICE\n");
return;
}
vbasedev->sysfsdev =
g_strdup_printf("/sys/bus/pci/devices/%04x:%02x:%02x.%01x",
vdev->host.domain, vdev->host.bus,
vdev->host.slot, vdev->host.function);
}
if (!vfio_device_get_name(vbasedev, errp)) {
return;
}
/*
* Mediated devices *might* operate compatibly with discarding of RAM, but
* we cannot know for certain, it depends on whether the mdev vendor driver
* stays in sync with the active working set of the guest driver. Prevent
* the x-balloon-allowed option unless this is minimally an mdev device.
*/
tmp = g_strdup_printf("%s/subsystem", vbasedev->sysfsdev);
subsys = realpath(tmp, NULL);
is_mdev = subsys && (strcmp(subsys, "/sys/bus/mdev") == 0);
free(subsys);
trace_vfio_mdev(vbasedev->name, is_mdev);
if (vbasedev->ram_block_discard_allowed && !is_mdev) {
error_setg(errp, "x-balloon-allowed only potentially compatible "
"with mdev devices");
goto error;
}
if (!qemu_uuid_is_null(&vdev->vf_token)) {
qemu_uuid_unparse(&vdev->vf_token, uuid);
name = g_strdup_printf("%s vf_token=%s", vbasedev->name, uuid);
} else {
name = g_strdup(vbasedev->name);
}
if (!vfio_attach_device(name, vbasedev,
pci_device_iommu_address_space(pdev), errp)) {
goto error;
}
if (!vfio_populate_device(vdev, errp)) {
goto error;
}
/* Get a copy of config space */
ret = pread(vbasedev->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_setg_errno(errp, -ret, "failed to read device config space");
goto error;
}
/* 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 also add or extend BARs */
memset(vdev->emulated_config_bits + PCI_BASE_ADDRESS_0, 0xff, 6 * 4);
/*
* The PCI spec reserves vendor ID 0xffff as an invalid value. The
* device ID is managed by the vendor and need only be a 16-bit value.
* Allow any 16-bit value for subsystem so they can be hidden or changed.
*/
if (vdev->vendor_id != PCI_ANY_ID) {
if (vdev->vendor_id >= 0xffff) {
error_setg(errp, "invalid PCI vendor ID provided");
goto error;
}
vfio_add_emulated_word(vdev, PCI_VENDOR_ID, vdev->vendor_id, ~0);
trace_vfio_pci_emulated_vendor_id(vbasedev->name, vdev->vendor_id);
} else {
vdev->vendor_id = pci_get_word(pdev->config + PCI_VENDOR_ID);
}
if (vdev->device_id != PCI_ANY_ID) {
if (vdev->device_id > 0xffff) {
error_setg(errp, "invalid PCI device ID provided");
goto error;
}
vfio_add_emulated_word(vdev, PCI_DEVICE_ID, vdev->device_id, ~0);
trace_vfio_pci_emulated_device_id(vbasedev->name, vdev->device_id);
} else {
vdev->device_id = pci_get_word(pdev->config + PCI_DEVICE_ID);
}
if (vdev->sub_vendor_id != PCI_ANY_ID) {
if (vdev->sub_vendor_id > 0xffff) {
error_setg(errp, "invalid PCI subsystem vendor ID provided");
goto error;
}
vfio_add_emulated_word(vdev, PCI_SUBSYSTEM_VENDOR_ID,
vdev->sub_vendor_id, ~0);
trace_vfio_pci_emulated_sub_vendor_id(vbasedev->name,
vdev->sub_vendor_id);
}
if (vdev->sub_device_id != PCI_ANY_ID) {
if (vdev->sub_device_id > 0xffff) {
error_setg(errp, "invalid PCI subsystem device ID provided");
goto error;
}
vfio_add_emulated_word(vdev, PCI_SUBSYSTEM_ID, vdev->sub_device_id, ~0);
trace_vfio_pci_emulated_sub_device_id(vbasedev->name,
vdev->sub_device_id);
}
/* 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);
vfio_bars_prepare(vdev);
if (!vfio_msix_early_setup(vdev, errp)) {
goto error;
}
vfio_bars_register(vdev);
if (!vfio_add_capabilities(vdev, errp)) {
goto out_teardown;
}
if (vdev->vga) {
vfio_vga_quirk_setup(vdev);
}
for (i = 0; i < PCI_ROM_SLOT; i++) {
vfio_bar_quirk_setup(vdev, i);
}
if (!vdev->igd_opregion &&
vdev->features & VFIO_FEATURE_ENABLE_IGD_OPREGION) {
g_autofree struct vfio_region_info *opregion = NULL;
if (vdev->pdev.qdev.hotplugged) {
error_setg(errp,
"cannot support IGD OpRegion feature on hotplugged "
"device");
goto out_teardown;
}
ret = vfio_get_dev_region_info(vbasedev,
VFIO_REGION_TYPE_PCI_VENDOR_TYPE | PCI_VENDOR_ID_INTEL,
VFIO_REGION_SUBTYPE_INTEL_IGD_OPREGION, &opregion);
if (ret) {
error_setg_errno(errp, -ret,
"does not support requested IGD OpRegion feature");
goto out_teardown;
}
ret = vfio_pci_igd_opregion_init(vdev, opregion, errp);
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_intx_routing_notifier);
vdev->irqchip_change_notifier.notify = vfio_irqchip_change;
kvm_irqchip_add_change_notifier(&vdev->irqchip_change_notifier);
if (!vfio_intx_enable(vdev, errp)) {
goto out_deregister;
}
}
if (vdev->display != ON_OFF_AUTO_OFF) {
if (!vfio_display_probe(vdev, errp)) {
goto out_deregister;
}
}
if (vdev->enable_ramfb && vdev->dpy == NULL) {
error_setg(errp, "ramfb=on requires display=on");
goto out_deregister;
}
if (vdev->display_xres || vdev->display_yres) {
if (vdev->dpy == NULL) {
error_setg(errp, "xres and yres properties require display=on");
goto out_deregister;
}
if (vdev->dpy->edid_regs == NULL) {
error_setg(errp, "xres and yres properties need edid support");
goto out_deregister;
}
}
if (vdev->ramfb_migrate == ON_OFF_AUTO_ON && !vdev->enable_ramfb) {
warn_report("x-ramfb-migrate=on but ramfb=off. "
"Forcing x-ramfb-migrate to off.");
vdev->ramfb_migrate = ON_OFF_AUTO_OFF;
}
if (vbasedev->enable_migration == ON_OFF_AUTO_OFF) {
if (vdev->ramfb_migrate == ON_OFF_AUTO_AUTO) {
vdev->ramfb_migrate = ON_OFF_AUTO_OFF;
} else if (vdev->ramfb_migrate == ON_OFF_AUTO_ON) {
error_setg(errp, "x-ramfb-migrate requires enable-migration");
goto out_deregister;
}
}
if (!pdev->failover_pair_id) {
if (!vfio_migration_realize(vbasedev, errp)) {
goto out_deregister;
}
}
vfio_register_err_notifier(vdev);
vfio_register_req_notifier(vdev);
vfio_setup_resetfn_quirk(vdev);
return;
out_deregister:
if (vdev->interrupt == VFIO_INT_INTx) {
vfio_intx_disable(vdev);
}
pci_device_set_intx_routing_notifier(&vdev->pdev, NULL);
if (vdev->irqchip_change_notifier.notify) {
kvm_irqchip_remove_change_notifier(&vdev->irqchip_change_notifier);
}
if (vdev->intx.mmap_timer) {
timer_free(vdev->intx.mmap_timer);
}
out_teardown:
vfio_teardown_msi(vdev);
vfio_bars_exit(vdev);
error:
error_prepend(errp, VFIO_MSG_PREFIX, vbasedev->name);
}
static void vfio_instance_finalize(Object *obj)
{
VFIOPCIDevice *vdev = VFIO_PCI(obj);
vfio_display_finalize(vdev);
vfio_bars_finalize(vdev);
g_free(vdev->emulated_config_bits);
g_free(vdev->rom);
/*
* XXX Leaking igd_opregion is not an oversight, we can't remove the
* fw_cfg entry therefore leaking this allocation seems like the safest
* option.
*
* g_free(vdev->igd_opregion);
*/
vfio_pci_put_device(vdev);
}
static void vfio_exitfn(PCIDevice *pdev)
{
VFIOPCIDevice *vdev = VFIO_PCI(pdev);
vfio_unregister_req_notifier(vdev);
vfio_unregister_err_notifier(vdev);
pci_device_set_intx_routing_notifier(&vdev->pdev, NULL);
if (vdev->irqchip_change_notifier.notify) {
kvm_irqchip_remove_change_notifier(&vdev->irqchip_change_notifier);
}
vfio_disable_interrupts(vdev);
if (vdev->intx.mmap_timer) {
timer_free(vdev->intx.mmap_timer);
}
vfio_teardown_msi(vdev);
vfio_pci_disable_rp_atomics(vdev);
vfio_bars_exit(vdev);
vfio_migration_exit(&vdev->vbasedev);
}
static void vfio_pci_reset(DeviceState *dev)
{
VFIOPCIDevice *vdev = VFIO_PCI(dev);
trace_vfio_pci_reset(vdev->vbasedev.name);
vfio_pci_pre_reset(vdev);
if (vdev->display != ON_OFF_AUTO_OFF) {
vfio_display_reset(vdev);
}
if (vdev->resetfn && !vdev->resetfn(vdev)) {
goto post_reset;
}
if (vdev->vbasedev.reset_works &&
(vdev->has_flr || !vdev->has_pm_reset) &&
!ioctl(vdev->vbasedev.fd, VFIO_DEVICE_RESET)) {
trace_vfio_pci_reset_flr(vdev->vbasedev.name);
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->vbasedev.reset_works && vdev->has_pm_reset &&
!ioctl(vdev->vbasedev.fd, VFIO_DEVICE_RESET)) {
trace_vfio_pci_reset_pm(vdev->vbasedev.name);
goto post_reset;
}
post_reset:
vfio_pci_post_reset(vdev);
}
static void vfio_instance_init(Object *obj)
{
PCIDevice *pci_dev = PCI_DEVICE(obj);
VFIOPCIDevice *vdev = VFIO_PCI(obj);
VFIODevice *vbasedev = &vdev->vbasedev;
device_add_bootindex_property(obj, &vdev->bootindex,
"bootindex", NULL,
&pci_dev->qdev);
vdev->host.domain = ~0U;
vdev->host.bus = ~0U;
vdev->host.slot = ~0U;
vdev->host.function = ~0U;
vfio_device_init(vbasedev, VFIO_DEVICE_TYPE_PCI, &vfio_pci_ops,
DEVICE(vdev), false);
vdev->nv_gpudirect_clique = 0xFF;
/* QEMU_PCI_CAP_EXPRESS initialization does not depend on QEMU command
* line, therefore, no need to wait to realize like other devices */
pci_dev->cap_present |= QEMU_PCI_CAP_EXPRESS;
}
static Property vfio_pci_dev_properties[] = {
DEFINE_PROP_PCI_HOST_DEVADDR("host", VFIOPCIDevice, host),
DEFINE_PROP_UUID_NODEFAULT("vf-token", VFIOPCIDevice, vf_token),
DEFINE_PROP_STRING("sysfsdev", VFIOPCIDevice, vbasedev.sysfsdev),
DEFINE_PROP_ON_OFF_AUTO("x-pre-copy-dirty-page-tracking", VFIOPCIDevice,
vbasedev.pre_copy_dirty_page_tracking,
ON_OFF_AUTO_ON),
DEFINE_PROP_ON_OFF_AUTO("display", VFIOPCIDevice,
display, ON_OFF_AUTO_OFF),
DEFINE_PROP_UINT32("xres", VFIOPCIDevice, display_xres, 0),
DEFINE_PROP_UINT32("yres", VFIOPCIDevice, display_yres, 0),
DEFINE_PROP_UINT32("x-intx-mmap-timeout-ms", VFIOPCIDevice,
intx.mmap_timeout, 1100),
DEFINE_PROP_BIT("x-vga", VFIOPCIDevice, features,
VFIO_FEATURE_ENABLE_VGA_BIT, false),
DEFINE_PROP_BIT("x-req", VFIOPCIDevice, features,
VFIO_FEATURE_ENABLE_REQ_BIT, true),
DEFINE_PROP_BIT("x-igd-opregion", VFIOPCIDevice, features,
VFIO_FEATURE_ENABLE_IGD_OPREGION_BIT, false),
DEFINE_PROP_ON_OFF_AUTO("enable-migration", VFIOPCIDevice,
vbasedev.enable_migration, ON_OFF_AUTO_AUTO),
DEFINE_PROP_BOOL("migration-events", VFIOPCIDevice,
vbasedev.migration_events, false),
DEFINE_PROP_BOOL("x-no-mmap", VFIOPCIDevice, vbasedev.no_mmap, false),
DEFINE_PROP_BOOL("x-balloon-allowed", VFIOPCIDevice,
vbasedev.ram_block_discard_allowed, false),
DEFINE_PROP_BOOL("x-no-kvm-intx", VFIOPCIDevice, no_kvm_intx, false),
DEFINE_PROP_BOOL("x-no-kvm-msi", VFIOPCIDevice, no_kvm_msi, false),
DEFINE_PROP_BOOL("x-no-kvm-msix", VFIOPCIDevice, no_kvm_msix, false),
DEFINE_PROP_BOOL("x-no-geforce-quirks", VFIOPCIDevice,
no_geforce_quirks, false),
DEFINE_PROP_BOOL("x-no-kvm-ioeventfd", VFIOPCIDevice, no_kvm_ioeventfd,
false),
DEFINE_PROP_BOOL("x-no-vfio-ioeventfd", VFIOPCIDevice, no_vfio_ioeventfd,
false),
DEFINE_PROP_UINT32("x-pci-vendor-id", VFIOPCIDevice, vendor_id, PCI_ANY_ID),
DEFINE_PROP_UINT32("x-pci-device-id", VFIOPCIDevice, device_id, PCI_ANY_ID),
DEFINE_PROP_UINT32("x-pci-sub-vendor-id", VFIOPCIDevice,
sub_vendor_id, PCI_ANY_ID),
DEFINE_PROP_UINT32("x-pci-sub-device-id", VFIOPCIDevice,
sub_device_id, PCI_ANY_ID),
DEFINE_PROP_UINT32("x-igd-gms", VFIOPCIDevice, igd_gms, 0),
DEFINE_PROP_UNSIGNED_NODEFAULT("x-nv-gpudirect-clique", VFIOPCIDevice,
nv_gpudirect_clique,
qdev_prop_nv_gpudirect_clique, uint8_t),
DEFINE_PROP_OFF_AUTO_PCIBAR("x-msix-relocation", VFIOPCIDevice, msix_relo,
OFF_AUTOPCIBAR_OFF),
#ifdef CONFIG_IOMMUFD
DEFINE_PROP_LINK("iommufd", VFIOPCIDevice, vbasedev.iommufd,
TYPE_IOMMUFD_BACKEND, IOMMUFDBackend *),
#endif
DEFINE_PROP_BOOL("skip-vsc-check", VFIOPCIDevice, skip_vsc_check, true),
DEFINE_PROP_END_OF_LIST(),
};
#ifdef CONFIG_IOMMUFD
static void vfio_pci_set_fd(Object *obj, const char *str, Error **errp)
{
vfio_device_set_fd(&VFIO_PCI(obj)->vbasedev, str, errp);
}
#endif
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;
device_class_set_props(dc, vfio_pci_dev_properties);
#ifdef CONFIG_IOMMUFD
object_class_property_add_str(klass, "fd", NULL, vfio_pci_set_fd);
#endif
dc->desc = "VFIO-based PCI device assignment";
set_bit(DEVICE_CATEGORY_MISC, dc->categories);
pdc->realize = vfio_realize;
pdc->exit = vfio_exitfn;
pdc->config_read = vfio_pci_read_config;
pdc->config_write = vfio_pci_write_config;
}
static const TypeInfo vfio_pci_dev_info = {
.name = TYPE_VFIO_PCI,
.parent = TYPE_PCI_DEVICE,
.instance_size = sizeof(VFIOPCIDevice),
.class_init = vfio_pci_dev_class_init,
.instance_init = vfio_instance_init,
.instance_finalize = vfio_instance_finalize,
.interfaces = (InterfaceInfo[]) {
{ INTERFACE_PCIE_DEVICE },
{ INTERFACE_CONVENTIONAL_PCI_DEVICE },
{ }
},
};
static Property vfio_pci_dev_nohotplug_properties[] = {
DEFINE_PROP_BOOL("ramfb", VFIOPCIDevice, enable_ramfb, false),
DEFINE_PROP_ON_OFF_AUTO("x-ramfb-migrate", VFIOPCIDevice, ramfb_migrate,
ON_OFF_AUTO_AUTO),
DEFINE_PROP_END_OF_LIST(),
};
static void vfio_pci_nohotplug_dev_class_init(ObjectClass *klass, void *data)
{
DeviceClass *dc = DEVICE_CLASS(klass);
device_class_set_props(dc, vfio_pci_dev_nohotplug_properties);
dc->hotpluggable = false;
}
static const TypeInfo vfio_pci_nohotplug_dev_info = {
.name = TYPE_VFIO_PCI_NOHOTPLUG,
.parent = TYPE_VFIO_PCI,
.instance_size = sizeof(VFIOPCIDevice),
.class_init = vfio_pci_nohotplug_dev_class_init,
};
static void register_vfio_pci_dev_type(void)
{
type_register_static(&vfio_pci_dev_info);
type_register_static(&vfio_pci_nohotplug_dev_info);
}
type_init(register_vfio_pci_dev_type)
|