aboutsummaryrefslogtreecommitdiff
path: root/hw/vfio/common.c
blob: 598272f4dd2708f8241733f5a994d0ea135c4e39 (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
/*
 * 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/pci.h"
#include "exec/address-spaces.h"
#include "exec/memory.h"
#include "exec/ram_addr.h"
#include "hw/hw.h"
#include "qemu/error-report.h"
#include "qemu/main-loop.h"
#include "qemu/range.h"
#include "system/kvm.h"
#include "system/reset.h"
#include "system/runstate.h"
#include "trace.h"
#include "qapi/error.h"
#include "migration/misc.h"
#include "migration/blocker.h"
#include "migration/qemu-file.h"
#include "system/tpm.h"

VFIODeviceList vfio_device_list =
    QLIST_HEAD_INITIALIZER(vfio_device_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.
 */
int vfio_kvm_device_fd = -1;
#endif

/*
 * Device state interfaces
 */

bool vfio_mig_active(void)
{
    VFIODevice *vbasedev;

    if (QLIST_EMPTY(&vfio_device_list)) {
        return false;
    }

    QLIST_FOREACH(vbasedev, &vfio_device_list, global_next) {
        if (vbasedev->migration_blocker) {
            return false;
        }
    }
    return true;
}

static Error *multiple_devices_migration_blocker;

/*
 * Multiple devices migration is allowed only if all devices support P2P
 * migration. Single device migration is allowed regardless of P2P migration
 * support.
 */
static bool vfio_multiple_devices_migration_is_supported(void)
{
    VFIODevice *vbasedev;
    unsigned int device_num = 0;
    bool all_support_p2p = true;

    QLIST_FOREACH(vbasedev, &vfio_device_list, global_next) {
        if (vbasedev->migration) {
            device_num++;

            if (!(vbasedev->migration->mig_flags & VFIO_MIGRATION_P2P)) {
                all_support_p2p = false;
            }
        }
    }

    return all_support_p2p || device_num <= 1;
}

int vfio_block_multiple_devices_migration(VFIODevice *vbasedev, Error **errp)
{
    int ret;

    if (vfio_multiple_devices_migration_is_supported()) {
        return 0;
    }

    if (vbasedev->enable_migration == ON_OFF_AUTO_ON) {
        error_setg(errp, "Multiple VFIO devices migration is supported only if "
                         "all of them support P2P migration");
        return -EINVAL;
    }

    if (multiple_devices_migration_blocker) {
        return 0;
    }

    error_setg(&multiple_devices_migration_blocker,
               "Multiple VFIO devices migration is supported only if all of "
               "them support P2P migration");
    ret = migrate_add_blocker_normal(&multiple_devices_migration_blocker, errp);

    return ret;
}

void vfio_unblock_multiple_devices_migration(void)
{
    if (!multiple_devices_migration_blocker ||
        !vfio_multiple_devices_migration_is_supported()) {
        return;
    }

    migrate_del_blocker(&multiple_devices_migration_blocker);
}

bool vfio_viommu_preset(VFIODevice *vbasedev)
{
    return vbasedev->bcontainer->space->as != &address_space_memory;
}

static void vfio_set_migration_error(int ret)
{
    if (migration_is_running()) {
        migration_file_set_error(ret, NULL);
    }
}

bool vfio_device_state_is_running(VFIODevice *vbasedev)
{
    VFIOMigration *migration = vbasedev->migration;

    return migration->device_state == VFIO_DEVICE_STATE_RUNNING ||
           migration->device_state == VFIO_DEVICE_STATE_RUNNING_P2P;
}

bool vfio_device_state_is_precopy(VFIODevice *vbasedev)
{
    VFIOMigration *migration = vbasedev->migration;

    return migration->device_state == VFIO_DEVICE_STATE_PRE_COPY ||
           migration->device_state == VFIO_DEVICE_STATE_PRE_COPY_P2P;
}

static bool vfio_devices_all_dirty_tracking(VFIOContainerBase *bcontainer)
{
    VFIODevice *vbasedev;

    if (!migration_is_active() && !migration_is_device()) {
        return false;
    }

    QLIST_FOREACH(vbasedev, &bcontainer->device_list, container_next) {
        VFIOMigration *migration = vbasedev->migration;

        if (!migration) {
            return false;
        }

        if (vbasedev->pre_copy_dirty_page_tracking == ON_OFF_AUTO_OFF &&
            (vfio_device_state_is_running(vbasedev) ||
             vfio_device_state_is_precopy(vbasedev))) {
            return false;
        }
    }
    return true;
}

bool vfio_devices_all_device_dirty_tracking(const VFIOContainerBase *bcontainer)
{
    VFIODevice *vbasedev;

    QLIST_FOREACH(vbasedev, &bcontainer->device_list, container_next) {
        if (vbasedev->device_dirty_page_tracking == ON_OFF_AUTO_OFF) {
            return false;
        }
        if (!vbasedev->dirty_pages_supported) {
            return false;
        }
    }

    return true;
}

/*
 * Check if all VFIO devices are running and migration is active, which is
 * essentially equivalent to the migration being in pre-copy phase.
 */
bool
vfio_devices_all_running_and_mig_active(const VFIOContainerBase *bcontainer)
{
    VFIODevice *vbasedev;

    if (!migration_is_active()) {
        return false;
    }

    QLIST_FOREACH(vbasedev, &bcontainer->device_list, container_next) {
        VFIOMigration *migration = vbasedev->migration;

        if (!migration) {
            return false;
        }

        if (vfio_device_state_is_running(vbasedev) ||
            vfio_device_state_is_precopy(vbasedev)) {
            continue;
        } else {
            return false;
        }
    }
    return true;
}

static bool vfio_listener_skipped_section(MemoryRegionSection *section)
{
    return (!memory_region_is_ram(section->mr) &&
            !memory_region_is_iommu(section->mr)) ||
           memory_region_is_protected(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_xlat_addr(IOMMUTLBEntry *iotlb, void **vaddr,
                               ram_addr_t *ram_addr, bool *read_only,
                               Error **errp)
{
    bool ret, mr_has_discard_manager;

    ret = memory_get_xlat_addr(iotlb, vaddr, ram_addr, read_only,
                               &mr_has_discard_manager, errp);
    if (ret && mr_has_discard_manager) {
        /*
         * Malicious VMs might trigger discarding of IOMMU-mapped memory. The
         * pages will remain pinned inside vfio until unmapped, resulting in a
         * higher memory consumption than expected. If memory would get
         * populated again later, there would be an inconsistency between pages
         * pinned by vfio and pages seen by QEMU. This is the case until
         * unmapped from the IOMMU (e.g., during device reset).
         *
         * With malicious guests, we really only care about pinning more memory
         * than expected. RLIMIT_MEMLOCK set for the user/process can never be
         * exceeded and can be used to mitigate this problem.
         */
        warn_report_once("Using vfio with vIOMMUs and coordinated discarding of"
                         " RAM (e.g., virtio-mem) works, however, malicious"
                         " guests can trigger pinning of more memory than"
                         " intended via an IOMMU. It's possible to mitigate "
                         " by setting/adjusting RLIMIT_MEMLOCK.");
    }
    return ret;
}

static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
{
    VFIOGuestIOMMU *giommu = container_of(n, VFIOGuestIOMMU, n);
    VFIOContainerBase *bcontainer = giommu->bcontainer;
    hwaddr iova = iotlb->iova + giommu->iommu_offset;
    void *vaddr;
    int ret;
    Error *local_err = NULL;

    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");
        vfio_set_migration_error(-EINVAL);
        return;
    }

    rcu_read_lock();

    if ((iotlb->perm & IOMMU_RW) != IOMMU_NONE) {
        bool read_only;

        if (!vfio_get_xlat_addr(iotlb, &vaddr, NULL, &read_only, &local_err)) {
            error_report_err(local_err);
            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_container_dma_map(bcontainer, iova,
                                     iotlb->addr_mask + 1, vaddr,
                                     read_only);
        if (ret) {
            error_report("vfio_container_dma_map(%p, 0x%"HWADDR_PRIx", "
                         "0x%"HWADDR_PRIx", %p) = %d (%s)",
                         bcontainer, iova,
                         iotlb->addr_mask + 1, vaddr, ret, strerror(-ret));
        }
    } else {
        ret = vfio_container_dma_unmap(bcontainer, iova,
                                       iotlb->addr_mask + 1, iotlb);
        if (ret) {
            error_report("vfio_container_dma_unmap(%p, 0x%"HWADDR_PRIx", "
                         "0x%"HWADDR_PRIx") = %d (%s)",
                         bcontainer, iova,
                         iotlb->addr_mask + 1, ret, strerror(-ret));
            vfio_set_migration_error(ret);
        }
    }
out:
    rcu_read_unlock();
}

static void vfio_ram_discard_notify_discard(RamDiscardListener *rdl,
                                            MemoryRegionSection *section)
{
    VFIORamDiscardListener *vrdl = container_of(rdl, VFIORamDiscardListener,
                                                listener);
    VFIOContainerBase *bcontainer = vrdl->bcontainer;
    const hwaddr size = int128_get64(section->size);
    const hwaddr iova = section->offset_within_address_space;
    int ret;

    /* Unmap with a single call. */
    ret = vfio_container_dma_unmap(bcontainer, iova, size , NULL);
    if (ret) {
        error_report("%s: vfio_container_dma_unmap() failed: %s", __func__,
                     strerror(-ret));
    }
}

static int vfio_ram_discard_notify_populate(RamDiscardListener *rdl,
                                            MemoryRegionSection *section)
{
    VFIORamDiscardListener *vrdl = container_of(rdl, VFIORamDiscardListener,
                                                listener);
    VFIOContainerBase *bcontainer = vrdl->bcontainer;
    const hwaddr end = section->offset_within_region +
                       int128_get64(section->size);
    hwaddr start, next, iova;
    void *vaddr;
    int ret;

    /*
     * Map in (aligned within memory region) minimum granularity, so we can
     * unmap in minimum granularity later.
     */
    for (start = section->offset_within_region; start < end; start = next) {
        next = ROUND_UP(start + 1, vrdl->granularity);
        next = MIN(next, end);

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

        ret = vfio_container_dma_map(bcontainer, iova, next - start,
                                     vaddr, section->readonly);
        if (ret) {
            /* Rollback */
            vfio_ram_discard_notify_discard(rdl, section);
            return ret;
        }
    }
    return 0;
}

static void vfio_register_ram_discard_listener(VFIOContainerBase *bcontainer,
                                               MemoryRegionSection *section)
{
    RamDiscardManager *rdm = memory_region_get_ram_discard_manager(section->mr);
    VFIORamDiscardListener *vrdl;

    /* Ignore some corner cases not relevant in practice. */
    g_assert(QEMU_IS_ALIGNED(section->offset_within_region, TARGET_PAGE_SIZE));
    g_assert(QEMU_IS_ALIGNED(section->offset_within_address_space,
                             TARGET_PAGE_SIZE));
    g_assert(QEMU_IS_ALIGNED(int128_get64(section->size), TARGET_PAGE_SIZE));

    vrdl = g_new0(VFIORamDiscardListener, 1);
    vrdl->bcontainer = bcontainer;
    vrdl->mr = section->mr;
    vrdl->offset_within_address_space = section->offset_within_address_space;
    vrdl->size = int128_get64(section->size);
    vrdl->granularity = ram_discard_manager_get_min_granularity(rdm,
                                                                section->mr);

    g_assert(vrdl->granularity && is_power_of_2(vrdl->granularity));
    g_assert(bcontainer->pgsizes &&
             vrdl->granularity >= 1ULL << ctz64(bcontainer->pgsizes));

    ram_discard_listener_init(&vrdl->listener,
                              vfio_ram_discard_notify_populate,
                              vfio_ram_discard_notify_discard, true);
    ram_discard_manager_register_listener(rdm, &vrdl->listener, section);
    QLIST_INSERT_HEAD(&bcontainer->vrdl_list, vrdl, next);

    /*
     * Sanity-check if we have a theoretically problematic setup where we could
     * exceed the maximum number of possible DMA mappings over time. We assume
     * that each mapped section in the same address space as a RamDiscardManager
     * section consumes exactly one DMA mapping, with the exception of
     * RamDiscardManager sections; i.e., we don't expect to have gIOMMU sections
     * in the same address space as RamDiscardManager sections.
     *
     * We assume that each section in the address space consumes one memslot.
     * We take the number of KVM memory slots as a best guess for the maximum
     * number of sections in the address space we could have over time,
     * also consuming DMA mappings.
     */
    if (bcontainer->dma_max_mappings) {
        unsigned int vrdl_count = 0, vrdl_mappings = 0, max_memslots = 512;

#ifdef CONFIG_KVM
        if (kvm_enabled()) {
            max_memslots = kvm_get_max_memslots();
        }
#endif

        QLIST_FOREACH(vrdl, &bcontainer->vrdl_list, next) {
            hwaddr start, end;

            start = QEMU_ALIGN_DOWN(vrdl->offset_within_address_space,
                                    vrdl->granularity);
            end = ROUND_UP(vrdl->offset_within_address_space + vrdl->size,
                           vrdl->granularity);
            vrdl_mappings += (end - start) / vrdl->granularity;
            vrdl_count++;
        }

        if (vrdl_mappings + max_memslots - vrdl_count >
            bcontainer->dma_max_mappings) {
            warn_report("%s: possibly running out of DMA mappings. E.g., try"
                        " increasing the 'block-size' of virtio-mem devies."
                        " Maximum possible DMA mappings: %d, Maximum possible"
                        " memslots: %d", __func__, bcontainer->dma_max_mappings,
                        max_memslots);
        }
    }
}

static void vfio_unregister_ram_discard_listener(VFIOContainerBase *bcontainer,
                                                 MemoryRegionSection *section)
{
    RamDiscardManager *rdm = memory_region_get_ram_discard_manager(section->mr);
    VFIORamDiscardListener *vrdl = NULL;

    QLIST_FOREACH(vrdl, &bcontainer->vrdl_list, next) {
        if (vrdl->mr == section->mr &&
            vrdl->offset_within_address_space ==
            section->offset_within_address_space) {
            break;
        }
    }

    if (!vrdl) {
        hw_error("vfio: Trying to unregister missing RAM discard listener");
    }

    ram_discard_manager_unregister_listener(rdm, &vrdl->listener);
    QLIST_REMOVE(vrdl, next);
    g_free(vrdl);
}

static bool vfio_known_safe_misalignment(MemoryRegionSection *section)
{
    MemoryRegion *mr = section->mr;

    if (!TPM_IS_CRB(mr->owner)) {
        return false;
    }

    /* this is a known safe misaligned region, just trace for debug purpose */
    trace_vfio_known_safe_misalignment(memory_region_name(mr),
                                       section->offset_within_address_space,
                                       section->offset_within_region,
                                       qemu_real_host_page_size());
    return true;
}

static bool vfio_listener_valid_section(MemoryRegionSection *section,
                                        const char *name)
{
    if (vfio_listener_skipped_section(section)) {
        trace_vfio_listener_region_skip(name,
                section->offset_within_address_space,
                section->offset_within_address_space +
                int128_get64(int128_sub(section->size, int128_one())));
        return false;
    }

    if (unlikely((section->offset_within_address_space &
                  ~qemu_real_host_page_mask()) !=
                 (section->offset_within_region & ~qemu_real_host_page_mask()))) {
        if (!vfio_known_safe_misalignment(section)) {
            error_report("%s received unaligned region %s iova=0x%"PRIx64
                         " offset_within_region=0x%"PRIx64
                         " qemu_real_host_page_size=0x%"PRIxPTR,
                         __func__, memory_region_name(section->mr),
                         section->offset_within_address_space,
                         section->offset_within_region,
                         qemu_real_host_page_size());
        }
        return false;
    }

    return true;
}

static bool vfio_get_section_iova_range(VFIOContainerBase *bcontainer,
                                        MemoryRegionSection *section,
                                        hwaddr *out_iova, hwaddr *out_end,
                                        Int128 *out_llend)
{
    Int128 llend;
    hwaddr iova;

    iova = REAL_HOST_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(qemu_real_host_page_mask()));

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

    *out_iova = iova;
    *out_end = int128_get64(int128_sub(llend, int128_one()));
    if (out_llend) {
        *out_llend = llend;
    }
    return true;
}

static void vfio_listener_region_add(MemoryListener *listener,
                                     MemoryRegionSection *section)
{
    VFIOContainerBase *bcontainer = container_of(listener, VFIOContainerBase,
                                                 listener);
    hwaddr iova, end;
    Int128 llend, llsize;
    void *vaddr;
    int ret;
    Error *err = NULL;

    if (!vfio_listener_valid_section(section, "region_add")) {
        return;
    }

    if (!vfio_get_section_iova_range(bcontainer, section, &iova, &end,
                                     &llend)) {
        if (memory_region_is_ram_device(section->mr)) {
            trace_vfio_listener_region_add_no_dma_map(
                memory_region_name(section->mr),
                section->offset_within_address_space,
                int128_getlo(section->size),
                qemu_real_host_page_size());
        }
        return;
    }

    if (!vfio_container_add_section_window(bcontainer, section, &err)) {
        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(section->mr->name, 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_mr = iommu_mr;
        giommu->iommu_offset = section->offset_within_address_space -
                               section->offset_within_region;
        giommu->bcontainer = bcontainer;
        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_IOTLB_EVENTS,
                            section->offset_within_region,
                            int128_get64(llend),
                            iommu_idx);

        ret = memory_region_register_iommu_notifier(section->mr, &giommu->n,
                                                    &err);
        if (ret) {
            g_free(giommu);
            goto fail;
        }
        QLIST_INSERT_HEAD(&bcontainer->giommu_list, giommu, giommu_next);
        memory_region_iommu_replay(giommu->iommu_mr, &giommu->n);

        return;
    }

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

    /*
     * For RAM memory regions with a RamDiscardManager, we only want to map the
     * actually populated parts - and update the mapping whenever we're notified
     * about changes.
     */
    if (memory_region_has_ram_discard_manager(section->mr)) {
        vfio_register_ram_discard_listener(bcontainer, section);
        return;
    }

    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(bcontainer->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_container_dma_map(bcontainer, iova, int128_get64(llsize),
                                 vaddr, section->readonly);
    if (ret) {
        error_setg(&err, "vfio_container_dma_map(%p, 0x%"HWADDR_PRIx", "
                   "0x%"HWADDR_PRIx", %p) = %d (%s)",
                   bcontainer, iova, int128_get64(llsize), vaddr, ret,
                   strerror(-ret));
        if (memory_region_is_ram_device(section->mr)) {
            /* Allow unexpected mappings not to be fatal for RAM devices */
            error_report_err(err);
            return;
        }
        goto fail;
    }

    return;

fail:
    if (memory_region_is_ram_device(section->mr)) {
        error_reportf_err(err, "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 (!bcontainer->initialized) {
        if (!bcontainer->error) {
            error_propagate_prepend(&bcontainer->error, err,
                                    "Region %s: ",
                                    memory_region_name(section->mr));
        } else {
            error_free(err);
        }
    } else {
        error_report_err(err);
        hw_error("vfio: DMA mapping failed, unable to continue");
    }
}

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

    if (!vfio_listener_valid_section(section, "region_del")) {
        return;
    }

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

        trace_vfio_listener_region_del_iommu(section->mr->name);
        QLIST_FOREACH(giommu, &bcontainer->giommu_list, giommu_next) {
            if (MEMORY_REGION(giommu->iommu_mr) == 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.
         */
    }

    if (!vfio_get_section_iova_range(bcontainer, section, &iova, &end,
                                     &llend)) {
        return;
    }

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

    trace_vfio_listener_region_del(iova, end);

    if (memory_region_is_ram_device(section->mr)) {
        hwaddr pgmask;

        pgmask = (1ULL << ctz64(bcontainer->pgsizes)) - 1;
        try_unmap = !((iova & pgmask) || (int128_get64(llsize) & pgmask));
    } else if (memory_region_has_ram_discard_manager(section->mr)) {
        vfio_unregister_ram_discard_listener(bcontainer, section);
        /* Unregistering will trigger an unmap. */
        try_unmap = false;
    }

    if (try_unmap) {
        if (int128_eq(llsize, int128_2_64())) {
            /* The unmap ioctl doesn't accept a full 64-bit span. */
            llsize = int128_rshift(llsize, 1);
            ret = vfio_container_dma_unmap(bcontainer, iova,
                                           int128_get64(llsize), NULL);
            if (ret) {
                error_report("vfio_container_dma_unmap(%p, 0x%"HWADDR_PRIx", "
                             "0x%"HWADDR_PRIx") = %d (%s)",
                             bcontainer, iova, int128_get64(llsize), ret,
                             strerror(-ret));
            }
            iova += int128_get64(llsize);
        }
        ret = vfio_container_dma_unmap(bcontainer, iova,
                                       int128_get64(llsize), NULL);
        if (ret) {
            error_report("vfio_container_dma_unmap(%p, 0x%"HWADDR_PRIx", "
                         "0x%"HWADDR_PRIx") = %d (%s)",
                         bcontainer, iova, int128_get64(llsize), ret,
                         strerror(-ret));
        }
    }

    memory_region_unref(section->mr);

    vfio_container_del_section_window(bcontainer, section);
}

typedef struct VFIODirtyRanges {
    hwaddr min32;
    hwaddr max32;
    hwaddr min64;
    hwaddr max64;
    hwaddr minpci64;
    hwaddr maxpci64;
} VFIODirtyRanges;

typedef struct VFIODirtyRangesListener {
    VFIOContainerBase *bcontainer;
    VFIODirtyRanges ranges;
    MemoryListener listener;
} VFIODirtyRangesListener;

static bool vfio_section_is_vfio_pci(MemoryRegionSection *section,
                                     VFIOContainerBase *bcontainer)
{
    VFIOPCIDevice *pcidev;
    VFIODevice *vbasedev;
    Object *owner;

    owner = memory_region_owner(section->mr);

    QLIST_FOREACH(vbasedev, &bcontainer->device_list, container_next) {
        if (vbasedev->type != VFIO_DEVICE_TYPE_PCI) {
            continue;
        }
        pcidev = container_of(vbasedev, VFIOPCIDevice, vbasedev);
        if (OBJECT(pcidev) == owner) {
            return true;
        }
    }

    return false;
}

static void vfio_dirty_tracking_update_range(VFIODirtyRanges *range,
                                             hwaddr iova, hwaddr end,
                                             bool update_pci)
{
    hwaddr *min, *max;

    /*
     * The address space passed to the dirty tracker is reduced to three ranges:
     * one for 32-bit DMA ranges, one for 64-bit DMA ranges and one for the
     * PCI 64-bit hole.
     *
     * The underlying reports of dirty will query a sub-interval of each of
     * these ranges.
     *
     * The purpose of the three range handling is to handle known cases of big
     * holes in the address space, like the x86 AMD 1T hole, and firmware (like
     * OVMF) which may relocate the pci-hole64 to the end of the address space.
     * The latter would otherwise generate large ranges for tracking, stressing
     * the limits of supported hardware. The pci-hole32 will always be below 4G
     * (overlapping or not) so it doesn't need special handling and is part of
     * the 32-bit range.
     *
     * The alternative would be an IOVATree but that has a much bigger runtime
     * overhead and unnecessary complexity.
     */
    if (update_pci && iova >= UINT32_MAX) {
        min = &range->minpci64;
        max = &range->maxpci64;
    } else {
        min = (end <= UINT32_MAX) ? &range->min32 : &range->min64;
        max = (end <= UINT32_MAX) ? &range->max32 : &range->max64;
    }
    if (*min > iova) {
        *min = iova;
    }
    if (*max < end) {
        *max = end;
    }

    trace_vfio_device_dirty_tracking_update(iova, end, *min, *max);
}

static void vfio_dirty_tracking_update(MemoryListener *listener,
                                       MemoryRegionSection *section)
{
    VFIODirtyRangesListener *dirty =
        container_of(listener, VFIODirtyRangesListener, listener);
    hwaddr iova, end;

    if (!vfio_listener_valid_section(section, "tracking_update") ||
        !vfio_get_section_iova_range(dirty->bcontainer, section,
                                     &iova, &end, NULL)) {
        return;
    }

    vfio_dirty_tracking_update_range(&dirty->ranges, iova, end,
                      vfio_section_is_vfio_pci(section, dirty->bcontainer));
}

static const MemoryListener vfio_dirty_tracking_listener = {
    .name = "vfio-tracking",
    .region_add = vfio_dirty_tracking_update,
};

static void vfio_dirty_tracking_init(VFIOContainerBase *bcontainer,
                                     VFIODirtyRanges *ranges)
{
    VFIODirtyRangesListener dirty;

    memset(&dirty, 0, sizeof(dirty));
    dirty.ranges.min32 = UINT32_MAX;
    dirty.ranges.min64 = UINT64_MAX;
    dirty.ranges.minpci64 = UINT64_MAX;
    dirty.listener = vfio_dirty_tracking_listener;
    dirty.bcontainer = bcontainer;

    memory_listener_register(&dirty.listener,
                             bcontainer->space->as);

    *ranges = dirty.ranges;

    /*
     * The memory listener is synchronous, and used to calculate the range
     * to dirty tracking. Unregister it after we are done as we are not
     * interested in any follow-up updates.
     */
    memory_listener_unregister(&dirty.listener);
}

static void vfio_devices_dma_logging_stop(VFIOContainerBase *bcontainer)
{
    uint64_t buf[DIV_ROUND_UP(sizeof(struct vfio_device_feature),
                              sizeof(uint64_t))] = {};
    struct vfio_device_feature *feature = (struct vfio_device_feature *)buf;
    VFIODevice *vbasedev;

    feature->argsz = sizeof(buf);
    feature->flags = VFIO_DEVICE_FEATURE_SET |
                     VFIO_DEVICE_FEATURE_DMA_LOGGING_STOP;

    QLIST_FOREACH(vbasedev, &bcontainer->device_list, container_next) {
        if (!vbasedev->dirty_tracking) {
            continue;
        }

        if (ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature)) {
            warn_report("%s: Failed to stop DMA logging, err %d (%s)",
                        vbasedev->name, -errno, strerror(errno));
        }
        vbasedev->dirty_tracking = false;
    }
}

static struct vfio_device_feature *
vfio_device_feature_dma_logging_start_create(VFIOContainerBase *bcontainer,
                                             VFIODirtyRanges *tracking)
{
    struct vfio_device_feature *feature;
    size_t feature_size;
    struct vfio_device_feature_dma_logging_control *control;
    struct vfio_device_feature_dma_logging_range *ranges;

    feature_size = sizeof(struct vfio_device_feature) +
                   sizeof(struct vfio_device_feature_dma_logging_control);
    feature = g_try_malloc0(feature_size);
    if (!feature) {
        errno = ENOMEM;
        return NULL;
    }
    feature->argsz = feature_size;
    feature->flags = VFIO_DEVICE_FEATURE_SET |
                     VFIO_DEVICE_FEATURE_DMA_LOGGING_START;

    control = (struct vfio_device_feature_dma_logging_control *)feature->data;
    control->page_size = qemu_real_host_page_size();

    /*
     * DMA logging uAPI guarantees to support at least a number of ranges that
     * fits into a single host kernel base page.
     */
    control->num_ranges = !!tracking->max32 + !!tracking->max64 +
        !!tracking->maxpci64;
    ranges = g_try_new0(struct vfio_device_feature_dma_logging_range,
                        control->num_ranges);
    if (!ranges) {
        g_free(feature);
        errno = ENOMEM;

        return NULL;
    }

    control->ranges = (uintptr_t)ranges;
    if (tracking->max32) {
        ranges->iova = tracking->min32;
        ranges->length = (tracking->max32 - tracking->min32) + 1;
        ranges++;
    }
    if (tracking->max64) {
        ranges->iova = tracking->min64;
        ranges->length = (tracking->max64 - tracking->min64) + 1;
        ranges++;
    }
    if (tracking->maxpci64) {
        ranges->iova = tracking->minpci64;
        ranges->length = (tracking->maxpci64 - tracking->minpci64) + 1;
    }

    trace_vfio_device_dirty_tracking_start(control->num_ranges,
                                           tracking->min32, tracking->max32,
                                           tracking->min64, tracking->max64,
                                           tracking->minpci64, tracking->maxpci64);

    return feature;
}

static void vfio_device_feature_dma_logging_start_destroy(
    struct vfio_device_feature *feature)
{
    struct vfio_device_feature_dma_logging_control *control =
        (struct vfio_device_feature_dma_logging_control *)feature->data;
    struct vfio_device_feature_dma_logging_range *ranges =
        (struct vfio_device_feature_dma_logging_range *)(uintptr_t)control->ranges;

    g_free(ranges);
    g_free(feature);
}

static bool vfio_devices_dma_logging_start(VFIOContainerBase *bcontainer,
                                          Error **errp)
{
    struct vfio_device_feature *feature;
    VFIODirtyRanges ranges;
    VFIODevice *vbasedev;
    int ret = 0;

    vfio_dirty_tracking_init(bcontainer, &ranges);
    feature = vfio_device_feature_dma_logging_start_create(bcontainer,
                                                           &ranges);
    if (!feature) {
        error_setg_errno(errp, errno, "Failed to prepare DMA logging");
        return false;
    }

    QLIST_FOREACH(vbasedev, &bcontainer->device_list, container_next) {
        if (vbasedev->dirty_tracking) {
            continue;
        }

        ret = ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature);
        if (ret) {
            ret = -errno;
            error_setg_errno(errp, errno, "%s: Failed to start DMA logging",
                             vbasedev->name);
            goto out;
        }
        vbasedev->dirty_tracking = true;
    }

out:
    if (ret) {
        vfio_devices_dma_logging_stop(bcontainer);
    }

    vfio_device_feature_dma_logging_start_destroy(feature);

    return ret == 0;
}

static bool vfio_listener_log_global_start(MemoryListener *listener,
                                           Error **errp)
{
    ERRP_GUARD();
    VFIOContainerBase *bcontainer = container_of(listener, VFIOContainerBase,
                                                 listener);
    bool ret;

    if (vfio_devices_all_device_dirty_tracking(bcontainer)) {
        ret = vfio_devices_dma_logging_start(bcontainer, errp);
    } else {
        ret = vfio_container_set_dirty_page_tracking(bcontainer, true, errp) == 0;
    }

    if (!ret) {
        error_prepend(errp, "vfio: Could not start dirty page tracking - ");
    }
    return ret;
}

static void vfio_listener_log_global_stop(MemoryListener *listener)
{
    VFIOContainerBase *bcontainer = container_of(listener, VFIOContainerBase,
                                                 listener);
    Error *local_err = NULL;
    int ret = 0;

    if (vfio_devices_all_device_dirty_tracking(bcontainer)) {
        vfio_devices_dma_logging_stop(bcontainer);
    } else {
        ret = vfio_container_set_dirty_page_tracking(bcontainer, false,
                                                     &local_err);
    }

    if (ret) {
        error_prepend(&local_err,
                      "vfio: Could not stop dirty page tracking - ");
        error_report_err(local_err);
        vfio_set_migration_error(ret);
    }
}

static int vfio_device_dma_logging_report(VFIODevice *vbasedev, hwaddr iova,
                                          hwaddr size, void *bitmap)
{
    uint64_t buf[DIV_ROUND_UP(sizeof(struct vfio_device_feature) +
                        sizeof(struct vfio_device_feature_dma_logging_report),
                        sizeof(uint64_t))] = {};
    struct vfio_device_feature *feature = (struct vfio_device_feature *)buf;
    struct vfio_device_feature_dma_logging_report *report =
        (struct vfio_device_feature_dma_logging_report *)feature->data;

    report->iova = iova;
    report->length = size;
    report->page_size = qemu_real_host_page_size();
    report->bitmap = (uintptr_t)bitmap;

    feature->argsz = sizeof(buf);
    feature->flags = VFIO_DEVICE_FEATURE_GET |
                     VFIO_DEVICE_FEATURE_DMA_LOGGING_REPORT;

    if (ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature)) {
        return -errno;
    }

    return 0;
}

int vfio_devices_query_dirty_bitmap(const VFIOContainerBase *bcontainer,
                 VFIOBitmap *vbmap, hwaddr iova, hwaddr size, Error **errp)
{
    VFIODevice *vbasedev;
    int ret;

    QLIST_FOREACH(vbasedev, &bcontainer->device_list, container_next) {
        ret = vfio_device_dma_logging_report(vbasedev, iova, size,
                                             vbmap->bitmap);
        if (ret) {
            error_setg_errno(errp, -ret,
                             "%s: Failed to get DMA logging report, iova: "
                             "0x%" HWADDR_PRIx ", size: 0x%" HWADDR_PRIx,
                             vbasedev->name, iova, size);

            return ret;
        }
    }

    return 0;
}

int vfio_get_dirty_bitmap(const VFIOContainerBase *bcontainer, uint64_t iova,
                          uint64_t size, ram_addr_t ram_addr, Error **errp)
{
    bool all_device_dirty_tracking =
        vfio_devices_all_device_dirty_tracking(bcontainer);
    uint64_t dirty_pages;
    VFIOBitmap vbmap;
    int ret;

    if (!bcontainer->dirty_pages_supported && !all_device_dirty_tracking) {
        cpu_physical_memory_set_dirty_range(ram_addr, size,
                                            tcg_enabled() ? DIRTY_CLIENTS_ALL :
                                            DIRTY_CLIENTS_NOCODE);
        return 0;
    }

    ret = vfio_bitmap_alloc(&vbmap, size);
    if (ret) {
        error_setg_errno(errp, -ret,
                         "Failed to allocate dirty tracking bitmap");
        return ret;
    }

    if (all_device_dirty_tracking) {
        ret = vfio_devices_query_dirty_bitmap(bcontainer, &vbmap, iova, size,
                                              errp);
    } else {
        ret = vfio_container_query_dirty_bitmap(bcontainer, &vbmap, iova, size,
                                                errp);
    }

    if (ret) {
        goto out;
    }

    dirty_pages = cpu_physical_memory_set_dirty_lebitmap(vbmap.bitmap, ram_addr,
                                                         vbmap.pages);

    trace_vfio_get_dirty_bitmap(iova, size, vbmap.size, ram_addr, dirty_pages);
out:
    g_free(vbmap.bitmap);

    return ret;
}

typedef struct {
    IOMMUNotifier n;
    VFIOGuestIOMMU *giommu;
} vfio_giommu_dirty_notifier;

static void vfio_iommu_map_dirty_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
{
    vfio_giommu_dirty_notifier *gdn = container_of(n,
                                                vfio_giommu_dirty_notifier, n);
    VFIOGuestIOMMU *giommu = gdn->giommu;
    VFIOContainerBase *bcontainer = giommu->bcontainer;
    hwaddr iova = iotlb->iova + giommu->iommu_offset;
    ram_addr_t translated_addr;
    Error *local_err = NULL;
    int ret = -EINVAL;

    trace_vfio_iommu_map_dirty_notify(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");
        goto out;
    }

    rcu_read_lock();
    if (!vfio_get_xlat_addr(iotlb, NULL, &translated_addr, NULL, &local_err)) {
        error_report_err(local_err);
        goto out_unlock;
    }

    ret = vfio_get_dirty_bitmap(bcontainer, iova, iotlb->addr_mask + 1,
                                translated_addr, &local_err);
    if (ret) {
        error_prepend(&local_err,
                      "vfio_iommu_map_dirty_notify(%p, 0x%"HWADDR_PRIx", "
                      "0x%"HWADDR_PRIx") failed - ", bcontainer, iova,
                      iotlb->addr_mask + 1);
        error_report_err(local_err);
    }

out_unlock:
    rcu_read_unlock();

out:
    if (ret) {
        vfio_set_migration_error(ret);
    }
}

static int vfio_ram_discard_get_dirty_bitmap(MemoryRegionSection *section,
                                             void *opaque)
{
    const hwaddr size = int128_get64(section->size);
    const hwaddr iova = section->offset_within_address_space;
    const ram_addr_t ram_addr = memory_region_get_ram_addr(section->mr) +
                                section->offset_within_region;
    VFIORamDiscardListener *vrdl = opaque;
    Error *local_err = NULL;
    int ret;

    /*
     * Sync the whole mapped region (spanning multiple individual mappings)
     * in one go.
     */
    ret = vfio_get_dirty_bitmap(vrdl->bcontainer, iova, size, ram_addr,
                                &local_err);
    if (ret) {
        error_report_err(local_err);
    }
    return ret;
}

static int
vfio_sync_ram_discard_listener_dirty_bitmap(VFIOContainerBase *bcontainer,
                                            MemoryRegionSection *section)
{
    RamDiscardManager *rdm = memory_region_get_ram_discard_manager(section->mr);
    VFIORamDiscardListener *vrdl = NULL;

    QLIST_FOREACH(vrdl, &bcontainer->vrdl_list, next) {
        if (vrdl->mr == section->mr &&
            vrdl->offset_within_address_space ==
            section->offset_within_address_space) {
            break;
        }
    }

    if (!vrdl) {
        hw_error("vfio: Trying to sync missing RAM discard listener");
    }

    /*
     * We only want/can synchronize the bitmap for actually mapped parts -
     * which correspond to populated parts. Replay all populated parts.
     */
    return ram_discard_manager_replay_populated(rdm, section,
                                              vfio_ram_discard_get_dirty_bitmap,
                                                &vrdl);
}

static int vfio_sync_iommu_dirty_bitmap(VFIOContainerBase *bcontainer,
                                        MemoryRegionSection *section)
{
    VFIOGuestIOMMU *giommu;
    bool found = false;
    Int128 llend;
    vfio_giommu_dirty_notifier gdn;
    int idx;

    QLIST_FOREACH(giommu, &bcontainer->giommu_list, giommu_next) {
        if (MEMORY_REGION(giommu->iommu_mr) == section->mr &&
            giommu->n.start == section->offset_within_region) {
            found = true;
            break;
        }
    }

    if (!found) {
        return 0;
    }

    gdn.giommu = giommu;
    idx = memory_region_iommu_attrs_to_index(giommu->iommu_mr,
                                             MEMTXATTRS_UNSPECIFIED);

    llend = int128_add(int128_make64(section->offset_within_region),
                       section->size);
    llend = int128_sub(llend, int128_one());

    iommu_notifier_init(&gdn.n, vfio_iommu_map_dirty_notify, IOMMU_NOTIFIER_MAP,
                        section->offset_within_region, int128_get64(llend),
                        idx);
    memory_region_iommu_replay(giommu->iommu_mr, &gdn.n);

    return 0;
}

static int vfio_sync_dirty_bitmap(VFIOContainerBase *bcontainer,
                                  MemoryRegionSection *section, Error **errp)
{
    ram_addr_t ram_addr;

    if (memory_region_is_iommu(section->mr)) {
        return vfio_sync_iommu_dirty_bitmap(bcontainer, section);
    } else if (memory_region_has_ram_discard_manager(section->mr)) {
        int ret;

        ret = vfio_sync_ram_discard_listener_dirty_bitmap(bcontainer, section);
        if (ret) {
            error_setg(errp,
                       "Failed to sync dirty bitmap with RAM discard listener");
        }
        return ret;
    }

    ram_addr = memory_region_get_ram_addr(section->mr) +
               section->offset_within_region;

    return vfio_get_dirty_bitmap(bcontainer,
                   REAL_HOST_PAGE_ALIGN(section->offset_within_address_space),
                                 int128_get64(section->size), ram_addr, errp);
}

static void vfio_listener_log_sync(MemoryListener *listener,
        MemoryRegionSection *section)
{
    VFIOContainerBase *bcontainer = container_of(listener, VFIOContainerBase,
                                                 listener);
    int ret;
    Error *local_err = NULL;

    if (vfio_listener_skipped_section(section)) {
        return;
    }

    if (vfio_devices_all_dirty_tracking(bcontainer)) {
        ret = vfio_sync_dirty_bitmap(bcontainer, section, &local_err);
        if (ret) {
            error_report_err(local_err);
            vfio_set_migration_error(ret);
        }
    }
}

const MemoryListener vfio_memory_listener = {
    .name = "vfio",
    .region_add = vfio_listener_region_add,
    .region_del = vfio_listener_region_del,
    .log_global_start = vfio_listener_log_global_start,
    .log_global_stop = vfio_listener_log_global_stop,
    .log_sync = vfio_listener_log_sync,
};

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

    QLIST_FOREACH(vbasedev, &vfio_device_list, global_next) {
        if (vbasedev->dev->realized) {
            vbasedev->ops->vfio_compute_needs_reset(vbasedev);
        }
    }

    QLIST_FOREACH(vbasedev, &vfio_device_list, global_next) {
        if (vbasedev->dev->realized && vbasedev->needs_reset) {
            vbasedev->ops->vfio_hot_reset_multi(vbasedev);
        }
    }
}

int vfio_kvm_device_add_fd(int fd, Error **errp)
{
#ifdef CONFIG_KVM
    struct kvm_device_attr attr = {
        .group = KVM_DEV_VFIO_FILE,
        .attr = KVM_DEV_VFIO_FILE_ADD,
        .addr = (uint64_t)(unsigned long)&fd,
    };

    if (!kvm_enabled()) {
        return 0;
    }

    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_setg_errno(errp, errno, "Failed to create KVM VFIO device");
            return -errno;
        }

        vfio_kvm_device_fd = cd.fd;
    }

    if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) {
        error_setg_errno(errp, errno, "Failed to add fd %d to KVM VFIO device",
                         fd);
        return -errno;
    }
#endif
    return 0;
}

int vfio_kvm_device_del_fd(int fd, Error **errp)
{
#ifdef CONFIG_KVM
    struct kvm_device_attr attr = {
        .group = KVM_DEV_VFIO_FILE,
        .attr = KVM_DEV_VFIO_FILE_DEL,
        .addr = (uint64_t)(unsigned long)&fd,
    };

    if (vfio_kvm_device_fd < 0) {
        error_setg(errp, "KVM VFIO device isn't created yet");
        return -EINVAL;
    }

    if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) {
        error_setg_errno(errp, errno,
                         "Failed to remove fd %d from KVM VFIO device", fd);
        return -errno;
    }
#endif
    return 0;
}

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);

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

    QLIST_INSERT_HEAD(&vfio_address_spaces, space, list);

    return space;
}

void vfio_put_address_space(VFIOAddressSpace *space)
{
    if (!QLIST_EMPTY(&space->containers)) {
        return;
    }

    QLIST_REMOVE(space, list);
    g_free(space);

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

void vfio_address_space_insert(VFIOAddressSpace *space,
                               VFIOContainerBase *bcontainer)
{
    QLIST_INSERT_HEAD(&space->containers, bcontainer, next);
    bcontainer->space = space;
}

struct vfio_device_info *vfio_get_device_info(int fd)
{
    struct vfio_device_info *info;
    uint32_t argsz = sizeof(*info);

    info = g_malloc0(argsz);

retry:
    info->argsz = argsz;

    if (ioctl(fd, VFIO_DEVICE_GET_INFO, info)) {
        g_free(info);
        return NULL;
    }

    if (info->argsz > argsz) {
        argsz = info->argsz;
        info = g_realloc(info, argsz);
        goto retry;
    }

    return info;
}

bool vfio_attach_device(char *name, VFIODevice *vbasedev,
                        AddressSpace *as, Error **errp)
{
    const VFIOIOMMUClass *ops =
        VFIO_IOMMU_CLASS(object_class_by_name(TYPE_VFIO_IOMMU_LEGACY));
    HostIOMMUDevice *hiod = NULL;

    if (vbasedev->iommufd) {
        ops = VFIO_IOMMU_CLASS(object_class_by_name(TYPE_VFIO_IOMMU_IOMMUFD));
    }

    assert(ops);


    if (!vbasedev->mdev) {
        hiod = HOST_IOMMU_DEVICE(object_new(ops->hiod_typename));
        vbasedev->hiod = hiod;
    }

    if (!ops->attach_device(name, vbasedev, as, errp)) {
        object_unref(hiod);
        vbasedev->hiod = NULL;
        return false;
    }

    return true;
}

void vfio_detach_device(VFIODevice *vbasedev)
{
    if (!vbasedev->bcontainer) {
        return;
    }
    object_unref(vbasedev->hiod);
    VFIO_IOMMU_GET_CLASS(vbasedev->bcontainer)->detach_device(vbasedev);
}