aboutsummaryrefslogtreecommitdiff
path: root/hw/vfio/common.c
blob: 9c3796e7db4318b5cc0fc04627195d7fe71d4fc1 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
/*
 * generic functions used by VFIO devices
 *
 * 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 <sys/ioctl.h>
#ifdef CONFIG_KVM
#include <linux/kvm.h>
#endif
#include <linux/vfio.h>

#include "hw/vfio/vfio-common.h"
#include "hw/vfio/vfio.h"
#include "exec/address-spaces.h"
#include "exec/memory.h"
#include "hw/hw.h"
#include "qemu/error-report.h"
#include "qemu/range.h"
#include "sysemu/balloon.h"
#include "sysemu/kvm.h"
#include "trace.h"
#include "qapi/error.h"

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

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

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

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

void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index)
{
    struct vfio_irq_set irq_set = {
        .argsz = sizeof(irq_set),
        .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_UNMASK,
        .index = index,
        .start = 0,
        .count = 1,
    };

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

void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index)
{
    struct vfio_irq_set irq_set = {
        .argsz = sizeof(irq_set),
        .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_MASK,
        .index = index,
        .start = 0,
        .count = 1,
    };

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

/*
 * IO Port/MMIO - Beware of the endians, VFIO is always little endian
 */
void vfio_region_write(void *opaque, hwaddr addr,
                       uint64_t data, unsigned size)
{
    VFIORegion *region = opaque;
    VFIODevice *vbasedev = region->vbasedev;
    union {
        uint8_t byte;
        uint16_t word;
        uint32_t dword;
        uint64_t qword;
    } buf;

    switch (size) {
    case 1:
        buf.byte = data;
        break;
    case 2:
        buf.word = cpu_to_le16(data);
        break;
    case 4:
        buf.dword = cpu_to_le32(data);
        break;
    case 8:
        buf.qword = cpu_to_le64(data);
        break;
    default:
        hw_error("vfio: unsupported write size, %d bytes", size);
        break;
    }

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

    trace_vfio_region_write(vbasedev->name, region->nr, addr, data, size);

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

uint64_t vfio_region_read(void *opaque,
                          hwaddr addr, unsigned size)
{
    VFIORegion *region = opaque;
    VFIODevice *vbasedev = region->vbasedev;
    union {
        uint8_t byte;
        uint16_t word;
        uint32_t dword;
        uint64_t qword;
    } buf;
    uint64_t data = 0;

    if (pread(vbasedev->fd, &buf, size, region->fd_offset + addr) != size) {
        error_report("%s(%s:region%d+0x%"HWADDR_PRIx", %d) failed: %m",
                     __func__, vbasedev->name, region->nr,
                     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;
    case 8:
        data = le64_to_cpu(buf.qword);
        break;
    default:
        hw_error("vfio: unsupported read size, %d bytes", size);
        break;
    }

    trace_vfio_region_read(vbasedev->name, region->nr, addr, size, data);

    /* Same as write above */
    vbasedev->ops->vfio_eoi(vbasedev);

    return data;
}

const MemoryRegionOps vfio_region_ops = {
    .read = vfio_region_read,
    .write = vfio_region_write,
    .endianness = DEVICE_LITTLE_ENDIAN,
    .valid = {
        .min_access_size = 1,
        .max_access_size = 8,
    },
    .impl = {
        .min_access_size = 1,
        .max_access_size = 8,
    },
};

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

    while (ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, &unmap)) {
        /*
         * The type1 backend has an off-by-one bug in the kernel (71a7d3d78e3c
         * v4.15) where an overflow in its wrap-around check prevents us from
         * unmapping the last page of the address space.  Test for the error
         * condition and re-try the unmap excluding the last page.  The
         * expectation is that we've never mapped the last page anyway and this
         * unmap request comes via vIOMMU support which also makes it unlikely
         * that this page is used.  This bug was introduced well after type1 v2
         * support was introduced, so we shouldn't need to test for v1.  A fix
         * is queued for kernel v5.0 so this workaround can be removed once
         * affected kernels are sufficiently deprecated.
         */
        if (errno == EINVAL && unmap.size && !(unmap.iova + unmap.size) &&
            container->iommu_type == VFIO_TYPE1v2_IOMMU) {
            trace_vfio_dma_unmap_overflow_workaround();
            unmap.size -= 1ULL << ctz64(container->pgsizes);
            continue;
        }
        error_report("VFIO_UNMAP_DMA: %d", -errno);
        return -errno;
    }

    return 0;
}

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

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

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

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

static void vfio_host_win_add(VFIOContainer *container,
                              hwaddr min_iova, hwaddr max_iova,
                              uint64_t iova_pgsizes)
{
    VFIOHostDMAWindow *hostwin;

    QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) {
        if (ranges_overlap(hostwin->min_iova,
                           hostwin->max_iova - hostwin->min_iova + 1,
                           min_iova,
                           max_iova - min_iova + 1)) {
            hw_error("%s: Overlapped IOMMU are not enabled", __func__);
        }
    }

    hostwin = g_malloc0(sizeof(*hostwin));

    hostwin->min_iova = min_iova;
    hostwin->max_iova = max_iova;
    hostwin->iova_pgsizes = iova_pgsizes;
    QLIST_INSERT_HEAD(&container->hostwin_list, hostwin, hostwin_next);
}

static int vfio_host_win_del(VFIOContainer *container, hwaddr min_iova,
                             hwaddr max_iova)
{
    VFIOHostDMAWindow *hostwin;

    QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) {
        if (hostwin->min_iova == min_iova && hostwin->max_iova == max_iova) {
            QLIST_REMOVE(hostwin, hostwin_next);
            return 0;
        }
    }

    return -1;
}

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

/* Called with rcu_read_lock held.  */
static bool vfio_get_vaddr(IOMMUTLBEntry *iotlb, void **vaddr,
                           bool *read_only)
{
    MemoryRegion *mr;
    hwaddr xlat;
    hwaddr len = iotlb->addr_mask + 1;
    bool writable = iotlb->perm & IOMMU_WO;

    /*
     * The IOMMU TLB entry we have just covers translation through
     * this IOMMU to its immediate target.  We need to translate
     * it the rest of the way through to memory.
     */
    mr = address_space_translate(&address_space_memory,
                                 iotlb->translated_addr,
                                 &xlat, &len, writable,
                                 MEMTXATTRS_UNSPECIFIED);
    if (!memory_region_is_ram(mr)) {
        error_report("iommu map to non memory area %"HWADDR_PRIx"",
                     xlat);
        return false;
    }

    /*
     * Translation truncates length to the IOMMU page size,
     * check that it did not truncate too much.
     */
    if (len & iotlb->addr_mask) {
        error_report("iommu has granularity incompatible with target AS");
        return false;
    }

    *vaddr = memory_region_get_ram_ptr(mr) + xlat;
    *read_only = !writable || mr->readonly;

    return true;
}

static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
{
    VFIOGuestIOMMU *giommu = container_of(n, VFIOGuestIOMMU, n);
    VFIOContainer *container = giommu->container;
    hwaddr iova = iotlb->iova + giommu->iommu_offset;
    bool read_only;
    void *vaddr;
    int ret;

    trace_vfio_iommu_map_notify(iotlb->perm == IOMMU_NONE ? "UNMAP" : "MAP",
                                iova, iova + iotlb->addr_mask);

    if (iotlb->target_as != &address_space_memory) {
        error_report("Wrong target AS \"%s\", only system memory is allowed",
                     iotlb->target_as->name ? iotlb->target_as->name : "none");
        return;
    }

    rcu_read_lock();

    if ((iotlb->perm & IOMMU_RW) != IOMMU_NONE) {
        if (!vfio_get_vaddr(iotlb, &vaddr, &read_only)) {
            goto out;
        }
        /*
         * vaddr is only valid until rcu_read_unlock(). But after
         * vfio_dma_map has set up the mapping the pages will be
         * pinned by the kernel. This makes sure that the RAM backend
         * of vaddr will always be there, even if the memory object is
         * destroyed and its backing memory munmap-ed.
         */
        ret = vfio_dma_map(container, iova,
                           iotlb->addr_mask + 1, vaddr,
                           read_only);
        if (ret) {
            error_report("vfio_dma_map(%p, 0x%"HWADDR_PRIx", "
                         "0x%"HWADDR_PRIx", %p) = %d (%m)",
                         container, iova,
                         iotlb->addr_mask + 1, vaddr, ret);
        }
    } else {
        ret = vfio_dma_unmap(container, iova, iotlb->addr_mask + 1);
        if (ret) {
            error_report("vfio_dma_unmap(%p, 0x%"HWADDR_PRIx", "
                         "0x%"HWADDR_PRIx") = %d (%m)",
                         container, iova,
                         iotlb->addr_mask + 1, ret);
        }
    }
out:
    rcu_read_unlock();
}

static void vfio_listener_region_add(MemoryListener *listener,
                                     MemoryRegionSection *section)
{
    VFIOContainer *container = container_of(listener, VFIOContainer, listener);
    hwaddr iova, end;
    Int128 llend, llsize;
    void *vaddr;
    int ret;
    VFIOHostDMAWindow *hostwin;
    bool hostwin_found;

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

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

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

    if (int128_ge(int128_make64(iova), llend)) {
        return;
    }
    end = int128_get64(int128_sub(llend, int128_one()));

    if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) {
        hwaddr pgsize = 0;

        /* For now intersections are not allowed, we may relax this later */
        QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) {
            if (ranges_overlap(hostwin->min_iova,
                               hostwin->max_iova - hostwin->min_iova + 1,
                               section->offset_within_address_space,
                               int128_get64(section->size))) {
                ret = -1;
                goto fail;
            }
        }

        ret = vfio_spapr_create_window(container, section, &pgsize);
        if (ret) {
            goto fail;
        }

        vfio_host_win_add(container, section->offset_within_address_space,
                          section->offset_within_address_space +
                          int128_get64(section->size) - 1, pgsize);
#ifdef CONFIG_KVM
        if (kvm_enabled()) {
            VFIOGroup *group;
            IOMMUMemoryRegion *iommu_mr = IOMMU_MEMORY_REGION(section->mr);
            struct kvm_vfio_spapr_tce param;
            struct kvm_device_attr attr = {
                .group = KVM_DEV_VFIO_GROUP,
                .attr = KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE,
                .addr = (uint64_t)(unsigned long)&param,
            };

            if (!memory_region_iommu_get_attr(iommu_mr, IOMMU_ATTR_SPAPR_TCE_FD,
                                              &param.tablefd)) {
                QLIST_FOREACH(group, &container->group_list, container_next) {
                    param.groupfd = group->fd;
                    if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) {
                        error_report("vfio: failed to setup fd %d "
                                     "for a group with fd %d: %s",
                                     param.tablefd, param.groupfd,
                                     strerror(errno));
                        return;
                    }
                    trace_vfio_spapr_group_attach(param.groupfd, param.tablefd);
                }
            }
        }
#endif
    }

    hostwin_found = false;
    QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) {
        if (hostwin->min_iova <= iova && end <= hostwin->max_iova) {
            hostwin_found = true;
            break;
        }
    }

    if (!hostwin_found) {
        error_report("vfio: IOMMU container %p can't map guest IOVA region"
                     " 0x%"HWADDR_PRIx"..0x%"HWADDR_PRIx,
                     container, iova, end);
        ret = -EFAULT;
        goto fail;
    }

    memory_region_ref(section->mr);

    if (memory_region_is_iommu(section->mr)) {
        VFIOGuestIOMMU *giommu;
        IOMMUMemoryRegion *iommu_mr = IOMMU_MEMORY_REGION(section->mr);
        int iommu_idx;

        trace_vfio_listener_region_add_iommu(iova, end);
        /*
         * FIXME: For VFIO iommu types which have KVM acceleration to
         * avoid bouncing all map/unmaps through qemu this way, this
         * would be the right place to wire that up (tell the KVM
         * device emulation the VFIO iommu handles to use).
         */
        giommu = g_malloc0(sizeof(*giommu));
        giommu->iommu = iommu_mr;
        giommu->iommu_offset = section->offset_within_address_space -
                               section->offset_within_region;
        giommu->container = container;
        llend = int128_add(int128_make64(section->offset_within_region),
                           section->size);
        llend = int128_sub(llend, int128_one());
        iommu_idx = memory_region_iommu_attrs_to_index(iommu_mr,
                                                       MEMTXATTRS_UNSPECIFIED);
        iommu_notifier_init(&giommu->n, vfio_iommu_map_notify,
                            IOMMU_NOTIFIER_ALL,
                            section->offset_within_region,
                            int128_get64(llend),
                            iommu_idx);
        QLIST_INSERT_HEAD(&container->giommu_list, giommu, giommu_next);

        memory_region_register_iommu_notifier(section->mr, &giommu->n);
        memory_region_iommu_replay(giommu->iommu, &giommu->n);

        return;
    }

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

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

    trace_vfio_listener_region_add_ram(iova, end, vaddr);

    llsize = int128_sub(llend, int128_make64(iova));

    if (memory_region_is_ram_device(section->mr)) {
        hwaddr pgmask = (1ULL << ctz64(hostwin->iova_pgsizes)) - 1;

        if ((iova & pgmask) || (int128_get64(llsize) & pgmask)) {
            trace_vfio_listener_region_add_no_dma_map(
                memory_region_name(section->mr),
                section->offset_within_address_space,
                int128_getlo(section->size),
                pgmask + 1);
            return;
        }
    }

    ret = vfio_dma_map(container, iova, int128_get64(llsize),
                       vaddr, section->readonly);
    if (ret) {
        error_report("vfio_dma_map(%p, 0x%"HWADDR_PRIx", "
                     "0x%"HWADDR_PRIx", %p) = %d (%m)",
                     container, iova, int128_get64(llsize), vaddr, ret);
        if (memory_region_is_ram_device(section->mr)) {
            /* Allow unexpected mappings not to be fatal for RAM devices */
            return;
        }
        goto fail;
    }

    return;

fail:
    if (memory_region_is_ram_device(section->mr)) {
        error_report("failed to vfio_dma_map. pci p2p may not work");
        return;
    }
    /*
     * On the initfn path, store the first error in the container so we
     * can gracefully fail.  Runtime, there's not much we can do other
     * than throw a hardware error.
     */
    if (!container->initialized) {
        if (!container->error) {
            container->error = ret;
        }
    } else {
        hw_error("vfio: DMA mapping failed, unable to continue");
    }
}

static void vfio_listener_region_del(MemoryListener *listener,
                                     MemoryRegionSection *section)
{
    VFIOContainer *container = container_of(listener, VFIOContainer, listener);
    hwaddr iova, end;
    Int128 llend, llsize;
    int ret;
    bool try_unmap = true;

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

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

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

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

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

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

    if (int128_ge(int128_make64(iova), llend)) {
        return;
    }
    end = int128_get64(int128_sub(llend, int128_one()));

    llsize = int128_sub(llend, int128_make64(iova));

    trace_vfio_listener_region_del(iova, end);

    if (memory_region_is_ram_device(section->mr)) {
        hwaddr pgmask;
        VFIOHostDMAWindow *hostwin;
        bool hostwin_found = false;

        QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) {
            if (hostwin->min_iova <= iova && end <= hostwin->max_iova) {
                hostwin_found = true;
                break;
            }
        }
        assert(hostwin_found); /* or region_add() would have failed */

        pgmask = (1ULL << ctz64(hostwin->iova_pgsizes)) - 1;
        try_unmap = !((iova & pgmask) || (int128_get64(llsize) & pgmask));
    }

    if (try_unmap) {
        ret = vfio_dma_unmap(container, iova, int128_get64(llsize));
        if (ret) {
            error_report("vfio_dma_unmap(%p, 0x%"HWADDR_PRIx", "
                         "0x%"HWADDR_PRIx") = %d (%m)",
                         container, iova, int128_get64(llsize), ret);
        }
    }

    memory_region_unref(section->mr);

    if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) {
        vfio_spapr_remove_window(container,
                                 section->offset_within_address_space);
        if (vfio_host_win_del(container,
                              section->offset_within_address_space,
                              section->offset_within_address_space +
                              int128_get64(section->size) - 1) < 0) {
            hw_error("%s: Cannot delete missing window at %"HWADDR_PRIx,
                     __func__, section->offset_within_address_space);
        }
    }
}

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

static void vfio_listener_release(VFIOContainer *container)
{
    memory_listener_unregister(&container->listener);
    if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) {
        memory_listener_unregister(&container->prereg_listener);
    }
}

static struct vfio_info_cap_header *
vfio_get_region_info_cap(struct vfio_region_info *info, uint16_t id)
{
    struct vfio_info_cap_header *hdr;
    void *ptr = info;

    if (!(info->flags & VFIO_REGION_INFO_FLAG_CAPS)) {
        return NULL;
    }

    for (hdr = ptr + info->cap_offset; hdr != ptr; hdr = ptr + hdr->next) {
        if (hdr->id == id) {
            return hdr;
        }
    }

    return NULL;
}

static int vfio_setup_region_sparse_mmaps(VFIORegion *region,
                                          struct vfio_region_info *info)
{
    struct vfio_info_cap_header *hdr;
    struct vfio_region_info_cap_sparse_mmap *sparse;
    int i, j;

    hdr = vfio_get_region_info_cap(info, VFIO_REGION_INFO_CAP_SPARSE_MMAP);
    if (!hdr) {
        return -ENODEV;
    }

    sparse = container_of(hdr, struct vfio_region_info_cap_sparse_mmap, header);

    trace_vfio_region_sparse_mmap_header(region->vbasedev->name,
                                         region->nr, sparse->nr_areas);

    region->mmaps = g_new0(VFIOMmap, sparse->nr_areas);

    for (i = 0, j = 0; i < sparse->nr_areas; i++) {
        trace_vfio_region_sparse_mmap_entry(i, sparse->areas[i].offset,
                                            sparse->areas[i].offset +
                                            sparse->areas[i].size);

        if (sparse->areas[i].size) {
            region->mmaps[j].offset = sparse->areas[i].offset;
            region->mmaps[j].size = sparse->areas[i].size;
            j++;
        }
    }

    region->nr_mmaps = j;
    region->mmaps = g_realloc(region->mmaps, j * sizeof(VFIOMmap));

    return 0;
}

int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *region,
                      int index, const char *name)
{
    struct vfio_region_info *info;
    int ret;

    ret = vfio_get_region_info(vbasedev, index, &info);
    if (ret) {
        return ret;
    }

    region->vbasedev = vbasedev;
    region->flags = info->flags;
    region->size = info->size;
    region->fd_offset = info->offset;
    region->nr = index;

    if (region->size) {
        region->mem = g_new0(MemoryRegion, 1);
        memory_region_init_io(region->mem, obj, &vfio_region_ops,
                              region, name, region->size);

        if (!vbasedev->no_mmap &&
            region->flags & VFIO_REGION_INFO_FLAG_MMAP) {

            ret = vfio_setup_region_sparse_mmaps(region, info);

            if (ret) {
                region->nr_mmaps = 1;
                region->mmaps = g_new0(VFIOMmap, region->nr_mmaps);
                region->mmaps[0].offset = 0;
                region->mmaps[0].size = region->size;
            }
        }
    }

    g_free(info);

    trace_vfio_region_setup(vbasedev->name, index, name,
                            region->flags, region->fd_offset, region->size);
    return 0;
}

int vfio_region_mmap(VFIORegion *region)
{
    int i, prot = 0;
    char *name;

    if (!region->mem) {
        return 0;
    }

    prot |= region->flags & VFIO_REGION_INFO_FLAG_READ ? PROT_READ : 0;
    prot |= region->flags & VFIO_REGION_INFO_FLAG_WRITE ? PROT_WRITE : 0;

    for (i = 0; i < region->nr_mmaps; i++) {
        region->mmaps[i].mmap = mmap(NULL, region->mmaps[i].size, prot,
                                     MAP_SHARED, region->vbasedev->fd,
                                     region->fd_offset +
                                     region->mmaps[i].offset);
        if (region->mmaps[i].mmap == MAP_FAILED) {
            int ret = -errno;

            trace_vfio_region_mmap_fault(memory_region_name(region->mem), i,
                                         region->fd_offset +
                                         region->mmaps[i].offset,
                                         region->fd_offset +
                                         region->mmaps[i].offset +
                                         region->mmaps[i].size - 1, ret);

            region->mmaps[i].mmap = NULL;

            for (i--; i >= 0; i--) {
                memory_region_del_subregion(region->mem, &region->mmaps[i].mem);
                munmap(region->mmaps[i].mmap, region->mmaps[i].size);
                object_unparent(OBJECT(&region->mmaps[i].mem));
                region->mmaps[i].mmap = NULL;
            }

            return ret;
        }

        name = g_strdup_printf("%s mmaps[%d]",
                               memory_region_name(region->mem), i);
        memory_region_init_ram_device_ptr(&region->mmaps[i].mem,
                                          memory_region_owner(region->mem),
                                          name, region->mmaps[i].size,
                                          region->mmaps[i].mmap);
        g_free(name);
        memory_region_add_subregion(region->mem, region->mmaps[i].offset,
                                    &region->mmaps[i].mem);

        trace_vfio_region_mmap(memory_region_name(&region->mmaps[i].mem),
                               region->mmaps[i].offset,
                               region->mmaps[i].offset +
                               region->mmaps[i].size - 1);
    }

    return 0;
}

void vfio_region_exit(VFIORegion *region)
{
    int i;

    if (!region->mem) {
        return;
    }

    for (i = 0; i < region->nr_mmaps; i++) {
        if (region->mmaps[i].mmap) {
            memory_region_del_subregion(region->mem, &region->mmaps[i].mem);
        }
    }

    trace_vfio_region_exit(region->vbasedev->name, region->nr);
}

void vfio_region_finalize(VFIORegion *region)
{
    int i;

    if (!region->mem) {
        return;
    }

    for (i = 0; i < region->nr_mmaps; i++) {
        if (region->mmaps[i].mmap) {
            munmap(region->mmaps[i].mmap, region->mmaps[i].size);
            object_unparent(OBJECT(&region->mmaps[i].mem));
        }
    }

    object_unparent(OBJECT(region->mem));

    g_free(region->mem);
    g_free(region->mmaps);

    trace_vfio_region_finalize(region->vbasedev->name, region->nr);

    region->mem = NULL;
    region->mmaps = NULL;
    region->nr_mmaps = 0;
    region->size = 0;
    region->flags = 0;
    region->nr = 0;
}

void vfio_region_mmaps_set_enabled(VFIORegion *region, bool enabled)
{
    int i;

    if (!region->mem) {
        return;
    }

    for (i = 0; i < region->nr_mmaps; i++) {
        if (region->mmaps[i].mmap) {
            memory_region_set_enabled(&region->mmaps[i].mem, enabled);
        }
    }

    trace_vfio_region_mmaps_set_enabled(memory_region_name(region->mem),
                                        enabled);
}

void vfio_reset_handler(void *opaque)
{
    VFIOGroup *group;
    VFIODevice *vbasedev;

    QLIST_FOREACH(group, &vfio_group_list, next) {
        QLIST_FOREACH(vbasedev, &group->device_list, next) {
            if (vbasedev->dev->realized) {
                vbasedev->ops->vfio_compute_needs_reset(vbasedev);
            }
        }
    }

    QLIST_FOREACH(group, &vfio_group_list, next) {
        QLIST_FOREACH(vbasedev, &group->device_list, next) {
            if (vbasedev->dev->realized && vbasedev->needs_reset) {
                vbasedev->ops->vfio_hot_reset_multi(vbasedev);
            }
        }
    }
}

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

    if (!kvm_enabled()) {
        return;
    }

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

        if (kvm_vm_ioctl(kvm_state, KVM_CREATE_DEVICE, &cd)) {
            error_report("Failed to create KVM VFIO device: %m");
            return;
        }

        vfio_kvm_device_fd = cd.fd;
    }

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

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

    if (vfio_kvm_device_fd < 0) {
        return;
    }

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

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

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

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

    QLIST_INSERT_HEAD(&vfio_address_spaces, space, list);

    return space;
}

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

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

    space = vfio_get_address_space(as);

    /*
     * VFIO is currently incompatible with memory ballooning insofar as the
     * madvise to purge (zap) the page from QEMU's address space does not
     * interact with the memory API and therefore leaves stale virtual to
     * physical mappings in the IOMMU if the page was previously pinned.  We
     * therefore add a balloon inhibit for each group added to a container,
     * whether the container is used individually or shared.  This provides
     * us with options to allow devices within a group to opt-in and allow
     * ballooning, so long as it is done consistently for a group (for instance
     * if the device is an mdev device where it is known that the host vendor
     * driver will never pin pages outside of the working set of the guest
     * driver, which would thus not be ballooning candidates).
     *
     * The first opportunity to induce pinning occurs here where we attempt to
     * attach the group to existing containers within the AddressSpace.  If any
     * pages are already zapped from the virtual address space, such as from a
     * previous ballooning opt-in, new pinning will cause valid mappings to be
     * re-established.  Likewise, when the overall MemoryListener for a new
     * container is registered, a replay of mappings within the AddressSpace
     * will occur, re-establishing any previously zapped pages as well.
     *
     * NB. Balloon inhibiting does not currently block operation of the
     * balloon driver or revoke previously pinned pages, it only prevents
     * calling madvise to modify the virtual mapping of ballooned pages.
     */
    qemu_balloon_inhibit(true);

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

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

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

    container = g_malloc0(sizeof(*container));
    container->space = space;
    container->fd = fd;
    QLIST_INIT(&container->giommu_list);
    QLIST_INIT(&container->hostwin_list);
    if (ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_TYPE1_IOMMU) ||
        ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_TYPE1v2_IOMMU)) {
        bool v2 = !!ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_TYPE1v2_IOMMU);
        struct vfio_iommu_type1_info info;

        ret = ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &fd);
        if (ret) {
            error_setg_errno(errp, errno, "failed to set group container");
            ret = -errno;
            goto free_container_exit;
        }

        container->iommu_type = v2 ? VFIO_TYPE1v2_IOMMU : VFIO_TYPE1_IOMMU;
        ret = ioctl(fd, VFIO_SET_IOMMU, container->iommu_type);
        if (ret) {
            error_setg_errno(errp, errno, "failed to set iommu for container");
            ret = -errno;
            goto free_container_exit;
        }

        /*
         * FIXME: This assumes that a Type1 IOMMU can map any 64-bit
         * IOVA whatsoever.  That's not actually true, but the current
         * kernel interface doesn't tell us what it can map, and the
         * existing Type1 IOMMUs generally support any IOVA we're
         * going to actually try in practice.
         */
        info.argsz = sizeof(info);
        ret = ioctl(fd, VFIO_IOMMU_GET_INFO, &info);
        /* Ignore errors */
        if (ret || !(info.flags & VFIO_IOMMU_INFO_PGSIZES)) {
            /* Assume 4k IOVA page size */
            info.iova_pgsizes = 4096;
        }
        vfio_host_win_add(container, 0, (hwaddr)-1, info.iova_pgsizes);
        container->pgsizes = info.iova_pgsizes;
    } else if (ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_IOMMU) ||
               ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_v2_IOMMU)) {
        struct vfio_iommu_spapr_tce_info info;
        bool v2 = !!ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_v2_IOMMU);

        ret = ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &fd);
        if (ret) {
            error_setg_errno(errp, errno, "failed to set group container");
            ret = -errno;
            goto free_container_exit;
        }
        container->iommu_type =
            v2 ? VFIO_SPAPR_TCE_v2_IOMMU : VFIO_SPAPR_TCE_IOMMU;
        ret = ioctl(fd, VFIO_SET_IOMMU, container->iommu_type);
        if (ret) {
            container->iommu_type = VFIO_SPAPR_TCE_IOMMU;
            v2 = false;
            ret = ioctl(fd, VFIO_SET_IOMMU, container->iommu_type);
        }
        if (ret) {
            error_setg_errno(errp, errno, "failed to set iommu for container");
            ret = -errno;
            goto free_container_exit;
        }

        /*
         * The host kernel code implementing VFIO_IOMMU_DISABLE is called
         * when container fd is closed so we do not call it explicitly
         * in this file.
         */
        if (!v2) {
            ret = ioctl(fd, VFIO_IOMMU_ENABLE);
            if (ret) {
                error_setg_errno(errp, errno, "failed to enable container");
                ret = -errno;
                goto free_container_exit;
            }
        } else {
            container->prereg_listener = vfio_prereg_listener;

            memory_listener_register(&container->prereg_listener,
                                     &address_space_memory);
            if (container->error) {
                memory_listener_unregister(&container->prereg_listener);
                ret = container->error;
                error_setg(errp,
                    "RAM memory listener initialization failed for container");
                goto free_container_exit;
            }
        }

        info.argsz = sizeof(info);
        ret = ioctl(fd, VFIO_IOMMU_SPAPR_TCE_GET_INFO, &info);
        if (ret) {
            error_setg_errno(errp, errno,
                             "VFIO_IOMMU_SPAPR_TCE_GET_INFO failed");
            ret = -errno;
            if (v2) {
                memory_listener_unregister(&container->prereg_listener);
            }
            goto free_container_exit;
        }

        if (v2) {
            container->pgsizes = info.ddw.pgsizes;
            /*
             * There is a default window in just created container.
             * To make region_add/del simpler, we better remove this
             * window now and let those iommu_listener callbacks
             * create/remove them when needed.
             */
            ret = vfio_spapr_remove_window(container, info.dma32_window_start);
            if (ret) {
                error_setg_errno(errp, -ret,
                                 "failed to remove existing window");
                goto free_container_exit;
            }
        } else {
            /* The default table uses 4K pages */
            container->pgsizes = 0x1000;
            vfio_host_win_add(container, info.dma32_window_start,
                              info.dma32_window_start +
                              info.dma32_window_size - 1,
                              0x1000);
        }
    } else {
        error_setg(errp, "No available IOMMU models");
        ret = -EINVAL;
        goto free_container_exit;
    }

    vfio_kvm_device_add_group(group);

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

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

    container->listener = vfio_memory_listener;

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

    if (container->error) {
        ret = container->error;
        error_setg_errno(errp, -ret,
                         "memory listener initialization failed for container");
        goto listener_release_exit;
    }

    container->initialized = true;

    return 0;
listener_release_exit:
    QLIST_REMOVE(group, container_next);
    QLIST_REMOVE(container, next);
    vfio_kvm_device_del_group(group);
    vfio_listener_release(container);

free_container_exit:
    g_free(container);

close_fd_exit:
    close(fd);

put_space_exit:
    qemu_balloon_inhibit(false);
    vfio_put_address_space(space);

    return ret;
}

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

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

    /*
     * Explicitly release the listener first before unset container,
     * since unset may destroy the backend container if it's the last
     * group.
     */
    if (QLIST_EMPTY(&container->group_list)) {
        vfio_listener_release(container);
    }

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

    if (QLIST_EMPTY(&container->group_list)) {
        VFIOAddressSpace *space = container->space;
        VFIOGuestIOMMU *giommu, *tmp;

        QLIST_REMOVE(container, next);

        QLIST_FOREACH_SAFE(giommu, &container->giommu_list, giommu_next, tmp) {
            memory_region_unregister_iommu_notifier(
                    MEMORY_REGION(giommu->iommu), &giommu->n);
            QLIST_REMOVE(giommu, giommu_next);
            g_free(giommu);
        }

        trace_vfio_disconnect_container(container->fd);
        close(container->fd);
        g_free(container);

        vfio_put_address_space(space);
    }
}

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

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

    group = g_malloc0(sizeof(*group));

    snprintf(path, sizeof(path), "/dev/vfio/%d", groupid);
    group->fd = qemu_open(path, O_RDWR);
    if (group->fd < 0) {
        error_setg_errno(errp, errno, "failed to open %s", path);
        goto free_group_exit;
    }

    if (ioctl(group->fd, VFIO_GROUP_GET_STATUS, &status)) {
        error_setg_errno(errp, errno, "failed to get group %d status", groupid);
        goto close_fd_exit;
    }

    if (!(status.flags & VFIO_GROUP_FLAGS_VIABLE)) {
        error_setg(errp, "group %d is not viable", groupid);
        error_append_hint(errp,
                          "Please ensure all devices within the iommu_group "
                          "are bound to their vfio bus driver.\n");
        goto close_fd_exit;
    }

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

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

    if (QLIST_EMPTY(&vfio_group_list)) {
        qemu_register_reset(vfio_reset_handler, NULL);
    }

    QLIST_INSERT_HEAD(&vfio_group_list, group, next);

    return group;

close_fd_exit:
    close(group->fd);

free_group_exit:
    g_free(group);

    return NULL;
}

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

    if (!group->balloon_allowed) {
        qemu_balloon_inhibit(false);
    }
    vfio_kvm_device_del_group(group);
    vfio_disconnect_container(group);
    QLIST_REMOVE(group, next);
    trace_vfio_put_group(group->fd);
    close(group->fd);
    g_free(group);

    if (QLIST_EMPTY(&vfio_group_list)) {
        qemu_unregister_reset(vfio_reset_handler, NULL);
    }
}

int vfio_get_device(VFIOGroup *group, const char *name,
                    VFIODevice *vbasedev, Error **errp)
{
    struct vfio_device_info dev_info = { .argsz = sizeof(dev_info) };
    int ret, fd;

    fd = ioctl(group->fd, VFIO_GROUP_GET_DEVICE_FD, name);
    if (fd < 0) {
        error_setg_errno(errp, errno, "error getting device from group %d",
                         group->groupid);
        error_append_hint(errp,
                      "Verify all devices in group %d are bound to vfio-<bus> "
                      "or pci-stub and not already in use\n", group->groupid);
        return fd;
    }

    ret = ioctl(fd, VFIO_DEVICE_GET_INFO, &dev_info);
    if (ret) {
        error_setg_errno(errp, errno, "error getting device info");
        close(fd);
        return ret;
    }

    /*
     * Clear the balloon inhibitor for this group if the driver knows the
     * device operates compatibly with ballooning.  Setting must be consistent
     * per group, but since compatibility is really only possible with mdev
     * currently, we expect singleton groups.
     */
    if (vbasedev->balloon_allowed != group->balloon_allowed) {
        if (!QLIST_EMPTY(&group->device_list)) {
            error_setg(errp,
                       "Inconsistent device balloon setting within group");
            close(fd);
            return -1;
        }

        if (!group->balloon_allowed) {
            group->balloon_allowed = true;
            qemu_balloon_inhibit(false);
        }
    }

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

    vbasedev->num_irqs = dev_info.num_irqs;
    vbasedev->num_regions = dev_info.num_regions;
    vbasedev->flags = dev_info.flags;

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

    vbasedev->reset_works = !!(dev_info.flags & VFIO_DEVICE_FLAGS_RESET);
    return 0;
}

void vfio_put_base_device(VFIODevice *vbasedev)
{
    if (!vbasedev->group) {
        return;
    }
    QLIST_REMOVE(vbasedev, next);
    vbasedev->group = NULL;
    trace_vfio_put_base_device(vbasedev->fd);
    close(vbasedev->fd);
}

int vfio_get_region_info(VFIODevice *vbasedev, int index,
                         struct vfio_region_info **info)
{
    size_t argsz = sizeof(struct vfio_region_info);

    *info = g_malloc0(argsz);

    (*info)->index = index;
retry:
    (*info)->argsz = argsz;

    if (ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, *info)) {
        g_free(*info);
        *info = NULL;
        return -errno;
    }

    if ((*info)->argsz > argsz) {
        argsz = (*info)->argsz;
        *info = g_realloc(*info, argsz);

        goto retry;
    }

    return 0;
}

int vfio_get_dev_region_info(VFIODevice *vbasedev, uint32_t type,
                             uint32_t subtype, struct vfio_region_info **info)
{
    int i;

    for (i = 0; i < vbasedev->num_regions; i++) {
        struct vfio_info_cap_header *hdr;
        struct vfio_region_info_cap_type *cap_type;

        if (vfio_get_region_info(vbasedev, i, info)) {
            continue;
        }

        hdr = vfio_get_region_info_cap(*info, VFIO_REGION_INFO_CAP_TYPE);
        if (!hdr) {
            g_free(*info);
            continue;
        }

        cap_type = container_of(hdr, struct vfio_region_info_cap_type, header);

        trace_vfio_get_dev_region(vbasedev->name, i,
                                  cap_type->type, cap_type->subtype);

        if (cap_type->type == type && cap_type->subtype == subtype) {
            return 0;
        }

        g_free(*info);
    }

    *info = NULL;
    return -ENODEV;
}

bool vfio_has_region_cap(VFIODevice *vbasedev, int region, uint16_t cap_type)
{
    struct vfio_region_info *info = NULL;
    bool ret = false;

    if (!vfio_get_region_info(vbasedev, region, &info)) {
        if (vfio_get_region_info_cap(info, cap_type)) {
            ret = true;
        }
        g_free(info);
    }

    return ret;
}

/*
 * Interfaces for IBM EEH (Enhanced Error Handling)
 */
static bool vfio_eeh_container_ok(VFIOContainer *container)
{
    /*
     * As of 2016-03-04 (linux-4.5) the host kernel EEH/VFIO
     * implementation is broken if there are multiple groups in a
     * container.  The hardware works in units of Partitionable
     * Endpoints (== IOMMU groups) and the EEH operations naively
     * iterate across all groups in the container, without any logic
     * to make sure the groups have their state synchronized.  For
     * certain operations (ENABLE) that might be ok, until an error
     * occurs, but for others (GET_STATE) it's clearly broken.
     */

    /*
     * XXX Once fixed kernels exist, test for them here
     */

    if (QLIST_EMPTY(&container->group_list)) {
        return false;
    }

    if (QLIST_NEXT(QLIST_FIRST(&container->group_list), container_next)) {
        return false;
    }

    return true;
}

static int vfio_eeh_container_op(VFIOContainer *container, uint32_t op)
{
    struct vfio_eeh_pe_op pe_op = {
        .argsz = sizeof(pe_op),
        .op = op,
    };
    int ret;

    if (!vfio_eeh_container_ok(container)) {
        error_report("vfio/eeh: EEH_PE_OP 0x%x: "
                     "kernel requires a container with exactly one group", op);
        return -EPERM;
    }

    ret = ioctl(container->fd, VFIO_EEH_PE_OP, &pe_op);
    if (ret < 0) {
        error_report("vfio/eeh: EEH_PE_OP 0x%x failed: %m", op);
        return -errno;
    }

    return ret;
}

static VFIOContainer *vfio_eeh_as_container(AddressSpace *as)
{
    VFIOAddressSpace *space = vfio_get_address_space(as);
    VFIOContainer *container = NULL;

    if (QLIST_EMPTY(&space->containers)) {
        /* No containers to act on */
        goto out;
    }

    container = QLIST_FIRST(&space->containers);

    if (QLIST_NEXT(container, next)) {
        /* We don't yet have logic to synchronize EEH state across
         * multiple containers */
        container = NULL;
        goto out;
    }

out:
    vfio_put_address_space(space);
    return container;
}

bool vfio_eeh_as_ok(AddressSpace *as)
{
    VFIOContainer *container = vfio_eeh_as_container(as);

    return (container != NULL) && vfio_eeh_container_ok(container);
}

int vfio_eeh_as_op(AddressSpace *as, uint32_t op)
{
    VFIOContainer *container = vfio_eeh_as_container(as);

    if (!container) {
        return -ENODEV;
    }
    return vfio_eeh_container_op(container, op);
}