summaryrefslogtreecommitdiffstats
path: root/hw/virtio/vhost.c
blob: d1c4c20b8c9ae1ff2822bc4d62c2eeaeeab93c1b (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
/*
 * vhost support
 *
 * Copyright Red Hat, Inc. 2010
 *
 * Authors:
 *  Michael S. Tsirkin <mst@redhat.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 * Contributions after 2012-01-13 are licensed under the terms of the
 * GNU GPL, version 2 or (at your option) any later version.
 */

#include "qemu/osdep.h"
#include "qapi/error.h"
#include "hw/virtio/vhost.h"
#include "qemu/atomic.h"
#include "qemu/range.h"
#include "qemu/error-report.h"
#include "qemu/memfd.h"
#include "standard-headers/linux/vhost_types.h"
#include "hw/virtio/virtio-bus.h"
#include "hw/virtio/virtio-access.h"
#include "migration/blocker.h"
#include "migration/qemu-file-types.h"
#include "sysemu/dma.h"
#include "trace.h"

/* enabled until disconnected backend stabilizes */
#define _VHOST_DEBUG 1

#ifdef _VHOST_DEBUG
#define VHOST_OPS_DEBUG(retval, fmt, ...) \
    do { \
        error_report(fmt ": %s (%d)", ## __VA_ARGS__, \
                     strerror(-retval), -retval); \
    } while (0)
#else
#define VHOST_OPS_DEBUG(retval, fmt, ...) \
    do { } while (0)
#endif

static struct vhost_log *vhost_log;
static struct vhost_log *vhost_log_shm;

static unsigned int used_memslots;
static QLIST_HEAD(, vhost_dev) vhost_devices =
    QLIST_HEAD_INITIALIZER(vhost_devices);

bool vhost_has_free_slot(void)
{
    unsigned int slots_limit = ~0U;
    struct vhost_dev *hdev;

    QLIST_FOREACH(hdev, &vhost_devices, entry) {
        unsigned int r = hdev->vhost_ops->vhost_backend_memslots_limit(hdev);
        slots_limit = MIN(slots_limit, r);
    }
    return slots_limit > used_memslots;
}

static void vhost_dev_sync_region(struct vhost_dev *dev,
                                  MemoryRegionSection *section,
                                  uint64_t mfirst, uint64_t mlast,
                                  uint64_t rfirst, uint64_t rlast)
{
    vhost_log_chunk_t *log = dev->log->log;

    uint64_t start = MAX(mfirst, rfirst);
    uint64_t end = MIN(mlast, rlast);
    vhost_log_chunk_t *from = log + start / VHOST_LOG_CHUNK;
    vhost_log_chunk_t *to = log + end / VHOST_LOG_CHUNK + 1;
    uint64_t addr = QEMU_ALIGN_DOWN(start, VHOST_LOG_CHUNK);

    if (end < start) {
        return;
    }
    assert(end / VHOST_LOG_CHUNK < dev->log_size);
    assert(start / VHOST_LOG_CHUNK < dev->log_size);

    for (;from < to; ++from) {
        vhost_log_chunk_t log;
        /* We first check with non-atomic: much cheaper,
         * and we expect non-dirty to be the common case. */
        if (!*from) {
            addr += VHOST_LOG_CHUNK;
            continue;
        }
        /* Data must be read atomically. We don't really need barrier semantics
         * but it's easier to use atomic_* than roll our own. */
        log = qatomic_xchg(from, 0);
        while (log) {
            int bit = ctzl(log);
            hwaddr page_addr;
            hwaddr section_offset;
            hwaddr mr_offset;
            page_addr = addr + bit * VHOST_LOG_PAGE;
            section_offset = page_addr - section->offset_within_address_space;
            mr_offset = section_offset + section->offset_within_region;
            memory_region_set_dirty(section->mr, mr_offset, VHOST_LOG_PAGE);
            log &= ~(0x1ull << bit);
        }
        addr += VHOST_LOG_CHUNK;
    }
}

static int vhost_sync_dirty_bitmap(struct vhost_dev *dev,
                                   MemoryRegionSection *section,
                                   hwaddr first,
                                   hwaddr last)
{
    int i;
    hwaddr start_addr;
    hwaddr end_addr;

    if (!dev->log_enabled || !dev->started) {
        return 0;
    }
    start_addr = section->offset_within_address_space;
    end_addr = range_get_last(start_addr, int128_get64(section->size));
    start_addr = MAX(first, start_addr);
    end_addr = MIN(last, end_addr);

    for (i = 0; i < dev->mem->nregions; ++i) {
        struct vhost_memory_region *reg = dev->mem->regions + i;
        vhost_dev_sync_region(dev, section, start_addr, end_addr,
                              reg->guest_phys_addr,
                              range_get_last(reg->guest_phys_addr,
                                             reg->memory_size));
    }
    for (i = 0; i < dev->nvqs; ++i) {
        struct vhost_virtqueue *vq = dev->vqs + i;

        if (!vq->used_phys && !vq->used_size) {
            continue;
        }

        vhost_dev_sync_region(dev, section, start_addr, end_addr, vq->used_phys,
                              range_get_last(vq->used_phys, vq->used_size));
    }
    return 0;
}

static void vhost_log_sync(MemoryListener *listener,
                          MemoryRegionSection *section)
{
    struct vhost_dev *dev = container_of(listener, struct vhost_dev,
                                         memory_listener);
    vhost_sync_dirty_bitmap(dev, section, 0x0, ~0x0ULL);
}

static void vhost_log_sync_range(struct vhost_dev *dev,
                                 hwaddr first, hwaddr last)
{
    int i;
    /* FIXME: this is N^2 in number of sections */
    for (i = 0; i < dev->n_mem_sections; ++i) {
        MemoryRegionSection *section = &dev->mem_sections[i];
        vhost_sync_dirty_bitmap(dev, section, first, last);
    }
}

static uint64_t vhost_get_log_size(struct vhost_dev *dev)
{
    uint64_t log_size = 0;
    int i;
    for (i = 0; i < dev->mem->nregions; ++i) {
        struct vhost_memory_region *reg = dev->mem->regions + i;
        uint64_t last = range_get_last(reg->guest_phys_addr,
                                       reg->memory_size);
        log_size = MAX(log_size, last / VHOST_LOG_CHUNK + 1);
    }
    return log_size;
}

static int vhost_set_backend_type(struct vhost_dev *dev,
                                  VhostBackendType backend_type)
{
    int r = 0;

    switch (backend_type) {
#ifdef CONFIG_VHOST_KERNEL
    case VHOST_BACKEND_TYPE_KERNEL:
        dev->vhost_ops = &kernel_ops;
        break;
#endif
#ifdef CONFIG_VHOST_USER
    case VHOST_BACKEND_TYPE_USER:
        dev->vhost_ops = &user_ops;
        break;
#endif
#ifdef CONFIG_VHOST_VDPA
    case VHOST_BACKEND_TYPE_VDPA:
        dev->vhost_ops = &vdpa_ops;
        break;
#endif
    default:
        error_report("Unknown vhost backend type");
        r = -1;
    }

    return r;
}

static struct vhost_log *vhost_log_alloc(uint64_t size, bool share)
{
    Error *err = NULL;
    struct vhost_log *log;
    uint64_t logsize = size * sizeof(*(log->log));
    int fd = -1;

    log = g_new0(struct vhost_log, 1);
    if (share) {
        log->log = qemu_memfd_alloc("vhost-log", logsize,
                                    F_SEAL_GROW | F_SEAL_SHRINK | F_SEAL_SEAL,
                                    &fd, &err);
        if (err) {
            error_report_err(err);
            g_free(log);
            return NULL;
        }
        memset(log->log, 0, logsize);
    } else {
        log->log = g_malloc0(logsize);
    }

    log->size = size;
    log->refcnt = 1;
    log->fd = fd;

    return log;
}

static struct vhost_log *vhost_log_get(uint64_t size, bool share)
{
    struct vhost_log *log = share ? vhost_log_shm : vhost_log;

    if (!log || log->size != size) {
        log = vhost_log_alloc(size, share);
        if (share) {
            vhost_log_shm = log;
        } else {
            vhost_log = log;
        }
    } else {
        ++log->refcnt;
    }

    return log;
}

static void vhost_log_put(struct vhost_dev *dev, bool sync)
{
    struct vhost_log *log = dev->log;

    if (!log) {
        return;
    }

    --log->refcnt;
    if (log->refcnt == 0) {
        /* Sync only the range covered by the old log */
        if (dev->log_size && sync) {
            vhost_log_sync_range(dev, 0, dev->log_size * VHOST_LOG_CHUNK - 1);
        }

        if (vhost_log == log) {
            g_free(log->log);
            vhost_log = NULL;
        } else if (vhost_log_shm == log) {
            qemu_memfd_free(log->log, log->size * sizeof(*(log->log)),
                            log->fd);
            vhost_log_shm = NULL;
        }

        g_free(log);
    }

    dev->log = NULL;
    dev->log_size = 0;
}

static bool vhost_dev_log_is_shared(struct vhost_dev *dev)
{
    return dev->vhost_ops->vhost_requires_shm_log &&
           dev->vhost_ops->vhost_requires_shm_log(dev);
}

static inline void vhost_dev_log_resize(struct vhost_dev *dev, uint64_t size)
{
    struct vhost_log *log = vhost_log_get(size, vhost_dev_log_is_shared(dev));
    uint64_t log_base = (uintptr_t)log->log;
    int r;

    /* inform backend of log switching, this must be done before
       releasing the current log, to ensure no logging is lost */
    r = dev->vhost_ops->vhost_set_log_base(dev, log_base, log);
    if (r < 0) {
        VHOST_OPS_DEBUG(r, "vhost_set_log_base failed");
    }

    vhost_log_put(dev, true);
    dev->log = log;
    dev->log_size = size;
}

static bool vhost_dev_has_iommu(struct vhost_dev *dev)
{
    VirtIODevice *vdev = dev->vdev;

    /*
     * For vhost, VIRTIO_F_IOMMU_PLATFORM means the backend support
     * incremental memory mapping API via IOTLB API. For platform that
     * does not have IOMMU, there's no need to enable this feature
     * which may cause unnecessary IOTLB miss/update transactions.
     */
    if (vdev) {
        return virtio_bus_device_iommu_enabled(vdev) &&
            virtio_host_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM);
    } else {
        return false;
    }
}

static void *vhost_memory_map(struct vhost_dev *dev, hwaddr addr,
                              hwaddr *plen, bool is_write)
{
    if (!vhost_dev_has_iommu(dev)) {
        return cpu_physical_memory_map(addr, plen, is_write);
    } else {
        return (void *)(uintptr_t)addr;
    }
}

static void vhost_memory_unmap(struct vhost_dev *dev, void *buffer,
                               hwaddr len, int is_write,
                               hwaddr access_len)
{
    if (!vhost_dev_has_iommu(dev)) {
        cpu_physical_memory_unmap(buffer, len, is_write, access_len);
    }
}

static int vhost_verify_ring_part_mapping(void *ring_hva,
                                          uint64_t ring_gpa,
                                          uint64_t ring_size,
                                          void *reg_hva,
                                          uint64_t reg_gpa,
                                          uint64_t reg_size)
{
    uint64_t hva_ring_offset;
    uint64_t ring_last = range_get_last(ring_gpa, ring_size);
    uint64_t reg_last = range_get_last(reg_gpa, reg_size);

    if (ring_last < reg_gpa || ring_gpa > reg_last) {
        return 0;
    }
    /* check that whole ring's is mapped */
    if (ring_last > reg_last) {
        return -ENOMEM;
    }
    /* check that ring's MemoryRegion wasn't replaced */
    hva_ring_offset = ring_gpa - reg_gpa;
    if (ring_hva != reg_hva + hva_ring_offset) {
        return -EBUSY;
    }

    return 0;
}

static int vhost_verify_ring_mappings(struct vhost_dev *dev,
                                      void *reg_hva,
                                      uint64_t reg_gpa,
                                      uint64_t reg_size)
{
    int i, j;
    int r = 0;
    const char *part_name[] = {
        "descriptor table",
        "available ring",
        "used ring"
    };

    if (vhost_dev_has_iommu(dev)) {
        return 0;
    }

    for (i = 0; i < dev->nvqs; ++i) {
        struct vhost_virtqueue *vq = dev->vqs + i;

        if (vq->desc_phys == 0) {
            continue;
        }

        j = 0;
        r = vhost_verify_ring_part_mapping(
                vq->desc, vq->desc_phys, vq->desc_size,
                reg_hva, reg_gpa, reg_size);
        if (r) {
            break;
        }

        j++;
        r = vhost_verify_ring_part_mapping(
                vq->avail, vq->avail_phys, vq->avail_size,
                reg_hva, reg_gpa, reg_size);
        if (r) {
            break;
        }

        j++;
        r = vhost_verify_ring_part_mapping(
                vq->used, vq->used_phys, vq->used_size,
                reg_hva, reg_gpa, reg_size);
        if (r) {
            break;
        }
    }

    if (r == -ENOMEM) {
        error_report("Unable to map %s for ring %d", part_name[j], i);
    } else if (r == -EBUSY) {
        error_report("%s relocated for ring %d", part_name[j], i);
    }
    return r;
}

/*
 * vhost_section: identify sections needed for vhost access
 *
 * We only care about RAM sections here (where virtqueue and guest
 * internals accessed by virtio might live). If we find one we still
 * allow the backend to potentially filter it out of our list.
 */
static bool vhost_section(struct vhost_dev *dev, MemoryRegionSection *section)
{
    MemoryRegion *mr = section->mr;

    if (memory_region_is_ram(mr) && !memory_region_is_rom(mr)) {
        uint8_t dirty_mask = memory_region_get_dirty_log_mask(mr);
        uint8_t handled_dirty;

        /*
         * Kernel based vhost doesn't handle any block which is doing
         * dirty-tracking other than migration for which it has
         * specific logging support. However for TCG the kernel never
         * gets involved anyway so we can also ignore it's
         * self-modiying code detection flags. However a vhost-user
         * client could still confuse a TCG guest if it re-writes
         * executable memory that has already been translated.
         */
        handled_dirty = (1 << DIRTY_MEMORY_MIGRATION) |
            (1 << DIRTY_MEMORY_CODE);

        if (dirty_mask & ~handled_dirty) {
            trace_vhost_reject_section(mr->name, 1);
            return false;
        }

        if (dev->vhost_ops->vhost_backend_mem_section_filter &&
            !dev->vhost_ops->vhost_backend_mem_section_filter(dev, section)) {
            trace_vhost_reject_section(mr->name, 2);
            return false;
        }

        trace_vhost_section(mr->name);
        return true;
    } else {
        trace_vhost_reject_section(mr->name, 3);
        return false;
    }
}

static void vhost_begin(MemoryListener *listener)
{
    struct vhost_dev *dev = container_of(listener, struct vhost_dev,
                                         memory_listener);
    dev->tmp_sections = NULL;
    dev->n_tmp_sections = 0;
}

static void vhost_commit(MemoryListener *listener)
{
    struct vhost_dev *dev = container_of(listener, struct vhost_dev,
                                         memory_listener);
    MemoryRegionSection *old_sections;
    int n_old_sections;
    uint64_t log_size;
    size_t regions_size;
    int r;
    int i;
    bool changed = false;

    /* Note we can be called before the device is started, but then
     * starting the device calls set_mem_table, so we need to have
     * built the data structures.
     */
    old_sections = dev->mem_sections;
    n_old_sections = dev->n_mem_sections;
    dev->mem_sections = dev->tmp_sections;
    dev->n_mem_sections = dev->n_tmp_sections;

    if (dev->n_mem_sections != n_old_sections) {
        changed = true;
    } else {
        /* Same size, lets check the contents */
        for (int i = 0; i < n_old_sections; i++) {
            if (!MemoryRegionSection_eq(&old_sections[i],
                                        &dev->mem_sections[i])) {
                changed = true;
                break;
            }
        }
    }

    trace_vhost_commit(dev->started, changed);
    if (!changed) {
        goto out;
    }

    /* Rebuild the regions list from the new sections list */
    regions_size = offsetof(struct vhost_memory, regions) +
                       dev->n_mem_sections * sizeof dev->mem->regions[0];
    dev->mem = g_realloc(dev->mem, regions_size);
    dev->mem->nregions = dev->n_mem_sections;
    used_memslots = dev->mem->nregions;
    for (i = 0; i < dev->n_mem_sections; i++) {
        struct vhost_memory_region *cur_vmr = dev->mem->regions + i;
        struct MemoryRegionSection *mrs = dev->mem_sections + i;

        cur_vmr->guest_phys_addr = mrs->offset_within_address_space;
        cur_vmr->memory_size     = int128_get64(mrs->size);
        cur_vmr->userspace_addr  =
            (uintptr_t)memory_region_get_ram_ptr(mrs->mr) +
            mrs->offset_within_region;
        cur_vmr->flags_padding   = 0;
    }

    if (!dev->started) {
        goto out;
    }

    for (i = 0; i < dev->mem->nregions; i++) {
        if (vhost_verify_ring_mappings(dev,
                       (void *)(uintptr_t)dev->mem->regions[i].userspace_addr,
                       dev->mem->regions[i].guest_phys_addr,
                       dev->mem->regions[i].memory_size)) {
            error_report("Verify ring failure on region %d", i);
            abort();
        }
    }

    if (!dev->log_enabled) {
        r = dev->vhost_ops->vhost_set_mem_table(dev, dev->mem);
        if (r < 0) {
            VHOST_OPS_DEBUG(r, "vhost_set_mem_table failed");
        }
        goto out;
    }
    log_size = vhost_get_log_size(dev);
    /* We allocate an extra 4K bytes to log,
     * to reduce the * number of reallocations. */
#define VHOST_LOG_BUFFER (0x1000 / sizeof *dev->log)
    /* To log more, must increase log size before table update. */
    if (dev->log_size < log_size) {
        vhost_dev_log_resize(dev, log_size + VHOST_LOG_BUFFER);
    }
    r = dev->vhost_ops->vhost_set_mem_table(dev, dev->mem);
    if (r < 0) {
        VHOST_OPS_DEBUG(r, "vhost_set_mem_table failed");
    }
    /* To log less, can only decrease log size after table update. */
    if (dev->log_size > log_size + VHOST_LOG_BUFFER) {
        vhost_dev_log_resize(dev, log_size);
    }

out:
    /* Deref the old list of sections, this must happen _after_ the
     * vhost_set_mem_table to ensure the client isn't still using the
     * section we're about to unref.
     */
    while (n_old_sections--) {
        memory_region_unref(old_sections[n_old_sections].mr);
    }
    g_free(old_sections);
    return;
}

/* Adds the section data to the tmp_section structure.
 * It relies on the listener calling us in memory address order
 * and for each region (via the _add and _nop methods) to
 * join neighbours.
 */
static void vhost_region_add_section(struct vhost_dev *dev,
                                     MemoryRegionSection *section)
{
    bool need_add = true;
    uint64_t mrs_size = int128_get64(section->size);
    uint64_t mrs_gpa = section->offset_within_address_space;
    uintptr_t mrs_host = (uintptr_t)memory_region_get_ram_ptr(section->mr) +
                         section->offset_within_region;
    RAMBlock *mrs_rb = section->mr->ram_block;

    trace_vhost_region_add_section(section->mr->name, mrs_gpa, mrs_size,
                                   mrs_host);

    if (dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER) {
        /* Round the section to it's page size */
        /* First align the start down to a page boundary */
        size_t mrs_page = qemu_ram_pagesize(mrs_rb);
        uint64_t alignage = mrs_host & (mrs_page - 1);
        if (alignage) {
            mrs_host -= alignage;
            mrs_size += alignage;
            mrs_gpa  -= alignage;
        }
        /* Now align the size up to a page boundary */
        alignage = mrs_size & (mrs_page - 1);
        if (alignage) {
            mrs_size += mrs_page - alignage;
        }
        trace_vhost_region_add_section_aligned(section->mr->name, mrs_gpa,
                                               mrs_size, mrs_host);
    }

    if (dev->n_tmp_sections) {
        /* Since we already have at least one section, lets see if
         * this extends it; since we're scanning in order, we only
         * have to look at the last one, and the FlatView that calls
         * us shouldn't have overlaps.
         */
        MemoryRegionSection *prev_sec = dev->tmp_sections +
                                               (dev->n_tmp_sections - 1);
        uint64_t prev_gpa_start = prev_sec->offset_within_address_space;
        uint64_t prev_size = int128_get64(prev_sec->size);
        uint64_t prev_gpa_end   = range_get_last(prev_gpa_start, prev_size);
        uint64_t prev_host_start =
                        (uintptr_t)memory_region_get_ram_ptr(prev_sec->mr) +
                        prev_sec->offset_within_region;
        uint64_t prev_host_end   = range_get_last(prev_host_start, prev_size);

        if (mrs_gpa <= (prev_gpa_end + 1)) {
            /* OK, looks like overlapping/intersecting - it's possible that
             * the rounding to page sizes has made them overlap, but they should
             * match up in the same RAMBlock if they do.
             */
            if (mrs_gpa < prev_gpa_start) {
                error_report("%s:Section '%s' rounded to %"PRIx64
                             " prior to previous '%s' %"PRIx64,
                             __func__, section->mr->name, mrs_gpa,
                             prev_sec->mr->name, prev_gpa_start);
                /* A way to cleanly fail here would be better */
                return;
            }
            /* Offset from the start of the previous GPA to this GPA */
            size_t offset = mrs_gpa - prev_gpa_start;

            if (prev_host_start + offset == mrs_host &&
                section->mr == prev_sec->mr &&
                (!dev->vhost_ops->vhost_backend_can_merge ||
                 dev->vhost_ops->vhost_backend_can_merge(dev,
                    mrs_host, mrs_size,
                    prev_host_start, prev_size))) {
                uint64_t max_end = MAX(prev_host_end, mrs_host + mrs_size);
                need_add = false;
                prev_sec->offset_within_address_space =
                    MIN(prev_gpa_start, mrs_gpa);
                prev_sec->offset_within_region =
                    MIN(prev_host_start, mrs_host) -
                    (uintptr_t)memory_region_get_ram_ptr(prev_sec->mr);
                prev_sec->size = int128_make64(max_end - MIN(prev_host_start,
                                               mrs_host));
                trace_vhost_region_add_section_merge(section->mr->name,
                                        int128_get64(prev_sec->size),
                                        prev_sec->offset_within_address_space,
                                        prev_sec->offset_within_region);
            } else {
                /* adjoining regions are fine, but overlapping ones with
                 * different blocks/offsets shouldn't happen
                 */
                if (mrs_gpa != prev_gpa_end + 1) {
                    error_report("%s: Overlapping but not coherent sections "
                                 "at %"PRIx64,
                                 __func__, mrs_gpa);
                    return;
                }
            }
        }
    }

    if (need_add) {
        ++dev->n_tmp_sections;
        dev->tmp_sections = g_renew(MemoryRegionSection, dev->tmp_sections,
                                    dev->n_tmp_sections);
        dev->tmp_sections[dev->n_tmp_sections - 1] = *section;
        /* The flatview isn't stable and we don't use it, making it NULL
         * means we can memcmp the list.
         */
        dev->tmp_sections[dev->n_tmp_sections - 1].fv = NULL;
        memory_region_ref(section->mr);
    }
}

/* Used for both add and nop callbacks */
static void vhost_region_addnop(MemoryListener *listener,
                                MemoryRegionSection *section)
{
    struct vhost_dev *dev = container_of(listener, struct vhost_dev,
                                         memory_listener);

    if (!vhost_section(dev, section)) {
        return;
    }
    vhost_region_add_section(dev, section);
}

static void vhost_iommu_unmap_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
{
    struct vhost_iommu *iommu = container_of(n, struct vhost_iommu, n);
    struct vhost_dev *hdev = iommu->hdev;
    hwaddr iova = iotlb->iova + iommu->iommu_offset;

    if (vhost_backend_invalidate_device_iotlb(hdev, iova,
                                              iotlb->addr_mask + 1)) {
        error_report("Fail to invalidate device iotlb");
    }
}

static void vhost_iommu_region_add(MemoryListener *listener,
                                   MemoryRegionSection *section)
{
    struct vhost_dev *dev = container_of(listener, struct vhost_dev,
                                         iommu_listener);
    struct vhost_iommu *iommu;
    Int128 end;
    int iommu_idx;
    IOMMUMemoryRegion *iommu_mr;
    int ret;

    if (!memory_region_is_iommu(section->mr)) {
        return;
    }

    iommu_mr = IOMMU_MEMORY_REGION(section->mr);

    iommu = g_malloc0(sizeof(*iommu));
    end = int128_add(int128_make64(section->offset_within_region),
                     section->size);
    end = int128_sub(end, int128_one());
    iommu_idx = memory_region_iommu_attrs_to_index(iommu_mr,
                                                   MEMTXATTRS_UNSPECIFIED);
    iommu_notifier_init(&iommu->n, vhost_iommu_unmap_notify,
                        IOMMU_NOTIFIER_DEVIOTLB_UNMAP,
                        section->offset_within_region,
                        int128_get64(end),
                        iommu_idx);
    iommu->mr = section->mr;
    iommu->iommu_offset = section->offset_within_address_space -
                          section->offset_within_region;
    iommu->hdev = dev;
    ret = memory_region_register_iommu_notifier(section->mr, &iommu->n, NULL);
    if (ret) {
        /*
         * Some vIOMMUs do not support dev-iotlb yet.  If so, try to use the
         * UNMAP legacy message
         */
        iommu->n.notifier_flags = IOMMU_NOTIFIER_UNMAP;
        memory_region_register_iommu_notifier(section->mr, &iommu->n,
                                              &error_fatal);
    }
    QLIST_INSERT_HEAD(&dev->iommu_list, iommu, iommu_next);
    /* TODO: can replay help performance here? */
}

static void vhost_iommu_region_del(MemoryListener *listener,
                                   MemoryRegionSection *section)
{
    struct vhost_dev *dev = container_of(listener, struct vhost_dev,
                                         iommu_listener);
    struct vhost_iommu *iommu;

    if (!memory_region_is_iommu(section->mr)) {
        return;
    }

    QLIST_FOREACH(iommu, &dev->iommu_list, iommu_next) {
        if (iommu->mr == section->mr &&
            iommu->n.start == section->offset_within_region) {
            memory_region_unregister_iommu_notifier(iommu->mr,
                                                    &iommu->n);
            QLIST_REMOVE(iommu, iommu_next);
            g_free(iommu);
            break;
        }
    }
}

static int vhost_virtqueue_set_addr(struct vhost_dev *dev,
                                    struct vhost_virtqueue *vq,
                                    unsigned idx, bool enable_log)
{
    struct vhost_vring_addr addr;
    int r;
    memset(&addr, 0, sizeof(struct vhost_vring_addr));

    if (dev->vhost_ops->vhost_vq_get_addr) {
        r = dev->vhost_ops->vhost_vq_get_addr(dev, &addr, vq);
        if (r < 0) {
            VHOST_OPS_DEBUG(r, "vhost_vq_get_addr failed");
            return r;
        }
    } else {
        addr.desc_user_addr = (uint64_t)(unsigned long)vq->desc;
        addr.avail_user_addr = (uint64_t)(unsigned long)vq->avail;
        addr.used_user_addr = (uint64_t)(unsigned long)vq->used;
    }
    addr.index = idx;
    addr.log_guest_addr = vq->used_phys;
    addr.flags = enable_log ? (1 << VHOST_VRING_F_LOG) : 0;
    r = dev->vhost_ops->vhost_set_vring_addr(dev, &addr);
    if (r < 0) {
        VHOST_OPS_DEBUG(r, "vhost_set_vring_addr failed");
    }
    return r;
}

static int vhost_dev_set_features(struct vhost_dev *dev,
                                  bool enable_log)
{
    uint64_t features = dev->acked_features;
    int r;
    if (enable_log) {
        features |= 0x1ULL << VHOST_F_LOG_ALL;
    }
    if (!vhost_dev_has_iommu(dev)) {
        features &= ~(0x1ULL << VIRTIO_F_IOMMU_PLATFORM);
    }
    if (dev->vhost_ops->vhost_force_iommu) {
        if (dev->vhost_ops->vhost_force_iommu(dev) == true) {
            features |= 0x1ULL << VIRTIO_F_IOMMU_PLATFORM;
       }
    }
    r = dev->vhost_ops->vhost_set_features(dev, features);
    if (r < 0) {
        VHOST_OPS_DEBUG(r, "vhost_set_features failed");
        goto out;
    }
    if (dev->vhost_ops->vhost_set_backend_cap) {
        r = dev->vhost_ops->vhost_set_backend_cap(dev);
        if (r < 0) {
            VHOST_OPS_DEBUG(r, "vhost_set_backend_cap failed");
            goto out;
        }
    }

out:
    return r;
}

static int vhost_dev_set_log(struct vhost_dev *dev, bool enable_log)
{
    int r, i, idx;
    hwaddr addr;

    r = vhost_dev_set_features(dev, enable_log);
    if (r < 0) {
        goto err_features;
    }
    for (i = 0; i < dev->nvqs; ++i) {
        idx = dev->vhost_ops->vhost_get_vq_index(dev, dev->vq_index + i);
        addr = virtio_queue_get_desc_addr(dev->vdev, idx);
        if (!addr) {
            /*
             * The queue might not be ready for start. If this
             * is the case there is no reason to continue the process.
             * The similar logic is used by the vhost_virtqueue_start()
             * routine.
             */
            continue;
        }
        r = vhost_virtqueue_set_addr(dev, dev->vqs + i, idx,
                                     enable_log);
        if (r < 0) {
            goto err_vq;
        }
    }
    return 0;
err_vq:
    for (; i >= 0; --i) {
        idx = dev->vhost_ops->vhost_get_vq_index(dev, dev->vq_index + i);
        addr = virtio_queue_get_desc_addr(dev->vdev, idx);
        if (!addr) {
            continue;
        }
        vhost_virtqueue_set_addr(dev, dev->vqs + i, idx,
                                 dev->log_enabled);
    }
    vhost_dev_set_features(dev, dev->log_enabled);
err_features:
    return r;
}

static int vhost_migration_log(MemoryListener *listener, bool enable)
{
    struct vhost_dev *dev = container_of(listener, struct vhost_dev,
                                         memory_listener);
    int r;
    if (enable == dev->log_enabled) {
        return 0;
    }
    if (!dev->started) {
        dev->log_enabled = enable;
        return 0;
    }

    r = 0;
    if (!enable) {
        r = vhost_dev_set_log(dev, false);
        if (r < 0) {
            goto check_dev_state;
        }
        vhost_log_put(dev, false);
    } else {
        vhost_dev_log_resize(dev, vhost_get_log_size(dev));
        r = vhost_dev_set_log(dev, true);
        if (r < 0) {
            goto check_dev_state;
        }
    }

check_dev_state:
    dev->log_enabled = enable;
    /*
     * vhost-user-* devices could change their state during log
     * initialization due to disconnect. So check dev state after
     * vhost communication.
     */
    if (!dev->started) {
        /*
         * Since device is in the stopped state, it is okay for
         * migration. Return success.
         */
        r = 0;
    }
    if (r) {
        /* An error occurred. */
        dev->log_enabled = false;
    }

    return r;
}

static void vhost_log_global_start(MemoryListener *listener)
{
    int r;

    r = vhost_migration_log(listener, true);
    if (r < 0) {
        abort();
    }
}

static void vhost_log_global_stop(MemoryListener *listener)
{
    int r;

    r = vhost_migration_log(listener, false);
    if (r < 0) {
        abort();
    }
}

static void vhost_log_start(MemoryListener *listener,
                            MemoryRegionSection *section,
                            int old, int new)
{
    /* FIXME: implement */
}

static void vhost_log_stop(MemoryListener *listener,
                           MemoryRegionSection *section,
                           int old, int new)
{
    /* FIXME: implement */
}

/* The vhost driver natively knows how to handle the vrings of non
 * cross-endian legacy devices and modern devices. Only legacy devices
 * exposed to a bi-endian guest may require the vhost driver to use a
 * specific endianness.
 */
static inline bool vhost_needs_vring_endian(VirtIODevice *vdev)
{
    if (virtio_vdev_has_feature(vdev, VIRTIO_F_VERSION_1)) {
        return false;
    }
#if HOST_BIG_ENDIAN
    return vdev->device_endian == VIRTIO_DEVICE_ENDIAN_LITTLE;
#else
    return vdev->device_endian == VIRTIO_DEVICE_ENDIAN_BIG;
#endif
}

static int vhost_virtqueue_set_vring_endian_legacy(struct vhost_dev *dev,
                                                   bool is_big_endian,
                                                   int vhost_vq_index)
{
    int r;
    struct vhost_vring_state s = {
        .index = vhost_vq_index,
        .num = is_big_endian
    };

    r = dev->vhost_ops->vhost_set_vring_endian(dev, &s);
    if (r < 0) {
        VHOST_OPS_DEBUG(r, "vhost_set_vring_endian failed");
    }
    return r;
}

static int vhost_memory_region_lookup(struct vhost_dev *hdev,
                                      uint64_t gpa, uint64_t *uaddr,
                                      uint64_t *len)
{
    int i;

    for (i = 0; i < hdev->mem->nregions; i++) {
        struct vhost_memory_region *reg = hdev->mem->regions + i;

        if (gpa >= reg->guest_phys_addr &&
            reg->guest_phys_addr + reg->memory_size > gpa) {
            *uaddr = reg->userspace_addr + gpa - reg->guest_phys_addr;
            *len = reg->guest_phys_addr + reg->memory_size - gpa;
            return 0;
        }
    }

    return -EFAULT;
}

int vhost_device_iotlb_miss(struct vhost_dev *dev, uint64_t iova, int write)
{
    IOMMUTLBEntry iotlb;
    uint64_t uaddr, len;
    int ret = -EFAULT;

    RCU_READ_LOCK_GUARD();

    trace_vhost_iotlb_miss(dev, 1);

    iotlb = address_space_get_iotlb_entry(dev->vdev->dma_as,
                                          iova, write,
                                          MEMTXATTRS_UNSPECIFIED);
    if (iotlb.target_as != NULL) {
        ret = vhost_memory_region_lookup(dev, iotlb.translated_addr,
                                         &uaddr, &len);
        if (ret) {
            trace_vhost_iotlb_miss(dev, 3);
            error_report("Fail to lookup the translated address "
                         "%"PRIx64, iotlb.translated_addr);
            goto out;
        }

        len = MIN(iotlb.addr_mask + 1, len);
        iova = iova & ~iotlb.addr_mask;

        ret = vhost_backend_update_device_iotlb(dev, iova, uaddr,
                                                len, iotlb.perm);
        if (ret) {
            trace_vhost_iotlb_miss(dev, 4);
            error_report("Fail to update device iotlb");
            goto out;
        }
    }

    trace_vhost_iotlb_miss(dev, 2);

out:
    return ret;
}

int vhost_virtqueue_start(struct vhost_dev *dev,
                          struct VirtIODevice *vdev,
                          struct vhost_virtqueue *vq,
                          unsigned idx)
{
    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
    VirtioBusState *vbus = VIRTIO_BUS(qbus);
    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(vbus);
    hwaddr s, l, a;
    int r;
    int vhost_vq_index = dev->vhost_ops->vhost_get_vq_index(dev, idx);
    struct vhost_vring_file file = {
        .index = vhost_vq_index
    };
    struct vhost_vring_state state = {
        .index = vhost_vq_index
    };
    struct VirtQueue *vvq = virtio_get_queue(vdev, idx);

    a = virtio_queue_get_desc_addr(vdev, idx);
    if (a == 0) {
        /* Queue might not be ready for start */
        return 0;
    }

    vq->num = state.num = virtio_queue_get_num(vdev, idx);
    r = dev->vhost_ops->vhost_set_vring_num(dev, &state);
    if (r) {
        VHOST_OPS_DEBUG(r, "vhost_set_vring_num failed");
        return r;
    }

    state.num = virtio_queue_get_last_avail_idx(vdev, idx);
    r = dev->vhost_ops->vhost_set_vring_base(dev, &state);
    if (r) {
        VHOST_OPS_DEBUG(r, "vhost_set_vring_base failed");
        return r;
    }

    if (vhost_needs_vring_endian(vdev)) {
        r = vhost_virtqueue_set_vring_endian_legacy(dev,
                                                    virtio_is_big_endian(vdev),
                                                    vhost_vq_index);
        if (r) {
            return r;
        }
    }

    vq->desc_size = s = l = virtio_queue_get_desc_size(vdev, idx);
    vq->desc_phys = a;
    vq->desc = vhost_memory_map(dev, a, &l, false);
    if (!vq->desc || l != s) {
        r = -ENOMEM;
        goto fail_alloc_desc;
    }
    vq->avail_size = s = l = virtio_queue_get_avail_size(vdev, idx);
    vq->avail_phys = a = virtio_queue_get_avail_addr(vdev, idx);
    vq->avail = vhost_memory_map(dev, a, &l, false);
    if (!vq->avail || l != s) {
        r = -ENOMEM;
        goto fail_alloc_avail;
    }
    vq->used_size = s = l = virtio_queue_get_used_size(vdev, idx);
    vq->used_phys = a = virtio_queue_get_used_addr(vdev, idx);
    vq->used = vhost_memory_map(dev, a, &l, true);
    if (!vq->used || l != s) {
        r = -ENOMEM;
        goto fail_alloc_used;
    }

    r = vhost_virtqueue_set_addr(dev, vq, vhost_vq_index, dev->log_enabled);
    if (r < 0) {
        goto fail_alloc;
    }

    file.fd = event_notifier_get_fd(virtio_queue_get_host_notifier(vvq));
    r = dev->vhost_ops->vhost_set_vring_kick(dev, &file);
    if (r) {
        VHOST_OPS_DEBUG(r, "vhost_set_vring_kick failed");
        goto fail_kick;
    }

    /* Clear and discard previous events if any. */
    event_notifier_test_and_clear(&vq->masked_notifier);

    /* Init vring in unmasked state, unless guest_notifier_mask
     * will do it later.
     */
    if (!vdev->use_guest_notifier_mask) {
        /* TODO: check and handle errors. */
        vhost_virtqueue_mask(dev, vdev, idx, false);
    }

    if (k->query_guest_notifiers &&
        k->query_guest_notifiers(qbus->parent) &&
        virtio_queue_vector(vdev, idx) == VIRTIO_NO_VECTOR) {
        file.fd = -1;
        r = dev->vhost_ops->vhost_set_vring_call(dev, &file);
        if (r) {
            goto fail_vector;
        }
    }

    return 0;

fail_vector:
fail_kick:
fail_alloc:
    vhost_memory_unmap(dev, vq->used, virtio_queue_get_used_size(vdev, idx),
                       0, 0);
fail_alloc_used:
    vhost_memory_unmap(dev, vq->avail, virtio_queue_get_avail_size(vdev, idx),
                       0, 0);
fail_alloc_avail:
    vhost_memory_unmap(dev, vq->desc, virtio_queue_get_desc_size(vdev, idx),
                       0, 0);
fail_alloc_desc:
    return r;
}

void vhost_virtqueue_stop(struct vhost_dev *dev,
                          struct VirtIODevice *vdev,
                          struct vhost_virtqueue *vq,
                          unsigned idx)
{
    int vhost_vq_index = dev->vhost_ops->vhost_get_vq_index(dev, idx);
    struct vhost_vring_state state = {
        .index = vhost_vq_index,
    };
    int r;

    if (virtio_queue_get_desc_addr(vdev, idx) == 0) {
        /* Don't stop the virtqueue which might have not been started */
        return;
    }

    r = dev->vhost_ops->vhost_get_vring_base(dev, &state);
    if (r < 0) {
        VHOST_OPS_DEBUG(r, "vhost VQ %u ring restore failed: %d", idx, r);
        /* Connection to the backend is broken, so let's sync internal
         * last avail idx to the device used idx.
         */
        virtio_queue_restore_last_avail_idx(vdev, idx);
    } else {
        virtio_queue_set_last_avail_idx(vdev, idx, state.num);
    }
    virtio_queue_invalidate_signalled_used(vdev, idx);
    virtio_queue_update_used_idx(vdev, idx);

    /* In the cross-endian case, we need to reset the vring endianness to
     * native as legacy devices expect so by default.
     */
    if (vhost_needs_vring_endian(vdev)) {
        vhost_virtqueue_set_vring_endian_legacy(dev,
                                                !virtio_is_big_endian(vdev),
                                                vhost_vq_index);
    }

    vhost_memory_unmap(dev, vq->used, virtio_queue_get_used_size(vdev, idx),
                       1, virtio_queue_get_used_size(vdev, idx));
    vhost_memory_unmap(dev, vq->avail, virtio_queue_get_avail_size(vdev, idx),
                       0, virtio_queue_get_avail_size(vdev, idx));
    vhost_memory_unmap(dev, vq->desc, virtio_queue_get_desc_size(vdev, idx),
                       0, virtio_queue_get_desc_size(vdev, idx));
}

static void vhost_eventfd_add(MemoryListener *listener,
                              MemoryRegionSection *section,
                              bool match_data, uint64_t data, EventNotifier *e)
{
}

static void vhost_eventfd_del(MemoryListener *listener,
                              MemoryRegionSection *section,
                              bool match_data, uint64_t data, EventNotifier *e)
{
}

static int vhost_virtqueue_set_busyloop_timeout(struct vhost_dev *dev,
                                                int n, uint32_t timeout)
{
    int vhost_vq_index = dev->vhost_ops->vhost_get_vq_index(dev, n);
    struct vhost_vring_state state = {
        .index = vhost_vq_index,
        .num = timeout,
    };
    int r;

    if (!dev->vhost_ops->vhost_set_vring_busyloop_timeout) {
        return -EINVAL;
    }

    r = dev->vhost_ops->vhost_set_vring_busyloop_timeout(dev, &state);
    if (r) {
        VHOST_OPS_DEBUG(r, "vhost_set_vring_busyloop_timeout failed");
        return r;
    }

    return 0;
}

static void vhost_virtqueue_error_notifier(EventNotifier *n)
{
    struct vhost_virtqueue *vq = container_of(n, struct vhost_virtqueue,
                                              error_notifier);
    struct vhost_dev *dev = vq->dev;
    int index = vq - dev->vqs;

    if (event_notifier_test_and_clear(n) && dev->vdev) {
        VHOST_OPS_DEBUG(-EINVAL,  "vhost vring error in virtqueue %d",
                        dev->vq_index + index);
    }
}

static int vhost_virtqueue_init(struct vhost_dev *dev,
                                struct vhost_virtqueue *vq, int n)
{
    int vhost_vq_index = dev->vhost_ops->vhost_get_vq_index(dev, n);
    struct vhost_vring_file file = {
        .index = vhost_vq_index,
    };
    int r = event_notifier_init(&vq->masked_notifier, 0);
    if (r < 0) {
        return r;
    }

    file.fd = event_notifier_get_wfd(&vq->masked_notifier);
    r = dev->vhost_ops->vhost_set_vring_call(dev, &file);
    if (r) {
        VHOST_OPS_DEBUG(r, "vhost_set_vring_call failed");
        goto fail_call;
    }

    vq->dev = dev;

    if (dev->vhost_ops->vhost_set_vring_err) {
        r = event_notifier_init(&vq->error_notifier, 0);
        if (r < 0) {
            goto fail_call;
        }

        file.fd = event_notifier_get_fd(&vq->error_notifier);
        r = dev->vhost_ops->vhost_set_vring_err(dev, &file);
        if (r) {
            VHOST_OPS_DEBUG(r, "vhost_set_vring_err failed");
            goto fail_err;
        }

        event_notifier_set_handler(&vq->error_notifier,
                                   vhost_virtqueue_error_notifier);
    }

    return 0;

fail_err:
    event_notifier_cleanup(&vq->error_notifier);
fail_call:
    event_notifier_cleanup(&vq->masked_notifier);
    return r;
}

static void vhost_virtqueue_cleanup(struct vhost_virtqueue *vq)
{
    event_notifier_cleanup(&vq->masked_notifier);
    if (vq->dev->vhost_ops->vhost_set_vring_err) {
        event_notifier_set_handler(&vq->error_notifier, NULL);
        event_notifier_cleanup(&vq->error_notifier);
    }
}

int vhost_dev_init(struct vhost_dev *hdev, void *opaque,
                   VhostBackendType backend_type, uint32_t busyloop_timeout,
                   Error **errp)
{
    uint64_t features;
    int i, r, n_initialized_vqs = 0;

    hdev->vdev = NULL;
    hdev->migration_blocker = NULL;

    r = vhost_set_backend_type(hdev, backend_type);
    assert(r >= 0);

    r = hdev->vhost_ops->vhost_backend_init(hdev, opaque, errp);
    if (r < 0) {
        goto fail;
    }

    r = hdev->vhost_ops->vhost_set_owner(hdev);
    if (r < 0) {
        error_setg_errno(errp, -r, "vhost_set_owner failed");
        goto fail;
    }

    r = hdev->vhost_ops->vhost_get_features(hdev, &features);
    if (r < 0) {
        error_setg_errno(errp, -r, "vhost_get_features failed");
        goto fail;
    }

    for (i = 0; i < hdev->nvqs; ++i, ++n_initialized_vqs) {
        r = vhost_virtqueue_init(hdev, hdev->vqs + i, hdev->vq_index + i);
        if (r < 0) {
            error_setg_errno(errp, -r, "Failed to initialize virtqueue %d", i);
            goto fail;
        }
    }

    if (busyloop_timeout) {
        for (i = 0; i < hdev->nvqs; ++i) {
            r = vhost_virtqueue_set_busyloop_timeout(hdev, hdev->vq_index + i,
                                                     busyloop_timeout);
            if (r < 0) {
                error_setg_errno(errp, -r, "Failed to set busyloop timeout");
                goto fail_busyloop;
            }
        }
    }

    hdev->features = features;

    hdev->memory_listener = (MemoryListener) {
        .name = "vhost",
        .begin = vhost_begin,
        .commit = vhost_commit,
        .region_add = vhost_region_addnop,
        .region_nop = vhost_region_addnop,
        .log_start = vhost_log_start,
        .log_stop = vhost_log_stop,
        .log_sync = vhost_log_sync,
        .log_global_start = vhost_log_global_start,
        .log_global_stop = vhost_log_global_stop,
        .eventfd_add = vhost_eventfd_add,
        .eventfd_del = vhost_eventfd_del,
        .priority = 10
    };

    hdev->iommu_listener = (MemoryListener) {
        .name = "vhost-iommu",
        .region_add = vhost_iommu_region_add,
        .region_del = vhost_iommu_region_del,
    };

    if (hdev->migration_blocker == NULL) {
        if (!(hdev->features & (0x1ULL << VHOST_F_LOG_ALL))) {
            error_setg(&hdev->migration_blocker,
                       "Migration disabled: vhost lacks VHOST_F_LOG_ALL feature.");
        } else if (vhost_dev_log_is_shared(hdev) && !qemu_memfd_alloc_check()) {
            error_setg(&hdev->migration_blocker,
                       "Migration disabled: failed to allocate shared memory");
        }
    }

    if (hdev->migration_blocker != NULL) {
        r = migrate_add_blocker(hdev->migration_blocker, errp);
        if (r < 0) {
            error_free(hdev->migration_blocker);
            goto fail_busyloop;
        }
    }

    hdev->mem = g_malloc0(offsetof(struct vhost_memory, regions));
    hdev->n_mem_sections = 0;
    hdev->mem_sections = NULL;
    hdev->log = NULL;
    hdev->log_size = 0;
    hdev->log_enabled = false;
    hdev->started = false;
    memory_listener_register(&hdev->memory_listener, &address_space_memory);
    QLIST_INSERT_HEAD(&vhost_devices, hdev, entry);

    if (used_memslots > hdev->vhost_ops->vhost_backend_memslots_limit(hdev)) {
        error_setg(errp, "vhost backend memory slots limit is less"
                   " than current number of present memory slots");
        r = -EINVAL;
        goto fail_busyloop;
    }

    return 0;

fail_busyloop:
    if (busyloop_timeout) {
        while (--i >= 0) {
            vhost_virtqueue_set_busyloop_timeout(hdev, hdev->vq_index + i, 0);
        }
    }
fail:
    hdev->nvqs = n_initialized_vqs;
    vhost_dev_cleanup(hdev);
    return r;
}

void vhost_dev_cleanup(struct vhost_dev *hdev)
{
    int i;

    trace_vhost_dev_cleanup(hdev);

    for (i = 0; i < hdev->nvqs; ++i) {
        vhost_virtqueue_cleanup(hdev->vqs + i);
    }
    if (hdev->mem) {
        /* those are only safe after successful init */
        memory_listener_unregister(&hdev->memory_listener);
        QLIST_REMOVE(hdev, entry);
    }
    if (hdev->migration_blocker) {
        migrate_del_blocker(hdev->migration_blocker);
        error_free(hdev->migration_blocker);
    }
    g_free(hdev->mem);
    g_free(hdev->mem_sections);
    if (hdev->vhost_ops) {
        hdev->vhost_ops->vhost_backend_cleanup(hdev);
    }
    assert(!hdev->log);

    memset(hdev, 0, sizeof(struct vhost_dev));
}

/* Stop processing guest IO notifications in qemu.
 * Start processing them in vhost in kernel.
 */
int vhost_dev_enable_notifiers(struct vhost_dev *hdev, VirtIODevice *vdev)
{
    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
    int i, r, e;

    /* We will pass the notifiers to the kernel, make sure that QEMU
     * doesn't interfere.
     */
    r = virtio_device_grab_ioeventfd(vdev);
    if (r < 0) {
        error_report("binding does not support host notifiers");
        goto fail;
    }

    for (i = 0; i < hdev->nvqs; ++i) {
        r = virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), hdev->vq_index + i,
                                         true);
        if (r < 0) {
            error_report("vhost VQ %d notifier binding failed: %d", i, -r);
            goto fail_vq;
        }
    }

    return 0;
fail_vq:
    while (--i >= 0) {
        e = virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), hdev->vq_index + i,
                                         false);
        if (e < 0) {
            error_report("vhost VQ %d notifier cleanup error: %d", i, -r);
        }
        assert (e >= 0);
        virtio_bus_cleanup_host_notifier(VIRTIO_BUS(qbus), hdev->vq_index + i);
    }
    virtio_device_release_ioeventfd(vdev);
fail:
    return r;
}

/* Stop processing guest IO notifications in vhost.
 * Start processing them in qemu.
 * This might actually run the qemu handlers right away,
 * so virtio in qemu must be completely setup when this is called.
 */
void vhost_dev_disable_notifiers(struct vhost_dev *hdev, VirtIODevice *vdev)
{
    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
    int i, r;

    for (i = 0; i < hdev->nvqs; ++i) {
        r = virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), hdev->vq_index + i,
                                         false);
        if (r < 0) {
            error_report("vhost VQ %d notifier cleanup failed: %d", i, -r);
        }
        assert (r >= 0);
        virtio_bus_cleanup_host_notifier(VIRTIO_BUS(qbus), hdev->vq_index + i);
    }
    virtio_device_release_ioeventfd(vdev);
}

/* Test and clear event pending status.
 * Should be called after unmask to avoid losing events.
 */
bool vhost_virtqueue_pending(struct vhost_dev *hdev, int n)
{
    struct vhost_virtqueue *vq = hdev->vqs + n - hdev->vq_index;
    assert(n >= hdev->vq_index && n < hdev->vq_index + hdev->nvqs);
    return event_notifier_test_and_clear(&vq->masked_notifier);
}

/* Mask/unmask events from this vq. */
void vhost_virtqueue_mask(struct vhost_dev *hdev, VirtIODevice *vdev, int n,
                         bool mask)
{
    struct VirtQueue *vvq = virtio_get_queue(vdev, n);
    int r, index = n - hdev->vq_index;
    struct vhost_vring_file file;

    /* should only be called after backend is connected */
    assert(hdev->vhost_ops);

    if (mask) {
        assert(vdev->use_guest_notifier_mask);
        file.fd = event_notifier_get_wfd(&hdev->vqs[index].masked_notifier);
    } else {
        file.fd = event_notifier_get_wfd(virtio_queue_get_guest_notifier(vvq));
    }

    file.index = hdev->vhost_ops->vhost_get_vq_index(hdev, n);
    r = hdev->vhost_ops->vhost_set_vring_call(hdev, &file);
    if (r < 0) {
        VHOST_OPS_DEBUG(r, "vhost_set_vring_call failed");
    }
}

uint64_t vhost_get_features(struct vhost_dev *hdev, const int *feature_bits,
                            uint64_t features)
{
    const int *bit = feature_bits;
    while (*bit != VHOST_INVALID_FEATURE_BIT) {
        uint64_t bit_mask = (1ULL << *bit);
        if (!(hdev->features & bit_mask)) {
            features &= ~bit_mask;
        }
        bit++;
    }
    return features;
}

void vhost_ack_features(struct vhost_dev *hdev, const int *feature_bits,
                        uint64_t features)
{
    const int *bit = feature_bits;
    while (*bit != VHOST_INVALID_FEATURE_BIT) {
        uint64_t bit_mask = (1ULL << *bit);
        if (features & bit_mask) {
            hdev->acked_features |= bit_mask;
        }
        bit++;
    }
}

int vhost_dev_get_config(struct vhost_dev *hdev, uint8_t *config,
                         uint32_t config_len, Error **errp)
{
    assert(hdev->vhost_ops);

    if (hdev->vhost_ops->vhost_get_config) {
        return hdev->vhost_ops->vhost_get_config(hdev, config, config_len,
                                                 errp);
    }

    error_setg(errp, "vhost_get_config not implemented");
    return -ENOSYS;
}

int vhost_dev_set_config(struct vhost_dev *hdev, const uint8_t *data,
                         uint32_t offset, uint32_t size, uint32_t flags)
{
    assert(hdev->vhost_ops);

    if (hdev->vhost_ops->vhost_set_config) {
        return hdev->vhost_ops->vhost_set_config(hdev, data, offset,
                                                 size, flags);
    }

    return -ENOSYS;
}

void vhost_dev_set_config_notifier(struct vhost_dev *hdev,
                                   const VhostDevConfigOps *ops)
{
    hdev->config_ops = ops;
}

void vhost_dev_free_inflight(struct vhost_inflight *inflight)
{
    if (inflight && inflight->addr) {
        qemu_memfd_free(inflight->addr, inflight->size, inflight->fd);
        inflight->addr = NULL;
        inflight->fd = -1;
    }
}

static int vhost_dev_resize_inflight(struct vhost_inflight *inflight,
                                     uint64_t new_size)
{
    Error *err = NULL;
    int fd = -1;
    void *addr = qemu_memfd_alloc("vhost-inflight", new_size,
                                  F_SEAL_GROW | F_SEAL_SHRINK | F_SEAL_SEAL,
                                  &fd, &err);

    if (err) {
        error_report_err(err);
        return -ENOMEM;
    }

    vhost_dev_free_inflight(inflight);
    inflight->offset = 0;
    inflight->addr = addr;
    inflight->fd = fd;
    inflight->size = new_size;

    return 0;
}

void vhost_dev_save_inflight(struct vhost_inflight *inflight, QEMUFile *f)
{
    if (inflight->addr) {
        qemu_put_be64(f, inflight->size);
        qemu_put_be16(f, inflight->queue_size);
        qemu_put_buffer(f, inflight->addr, inflight->size);
    } else {
        qemu_put_be64(f, 0);
    }
}

int vhost_dev_load_inflight(struct vhost_inflight *inflight, QEMUFile *f)
{
    uint64_t size;

    size = qemu_get_be64(f);
    if (!size) {
        return 0;
    }

    if (inflight->size != size) {
        int ret = vhost_dev_resize_inflight(inflight, size);
        if (ret < 0) {
            return ret;
        }
    }
    inflight->queue_size = qemu_get_be16(f);

    qemu_get_buffer(f, inflight->addr, size);

    return 0;
}

int vhost_dev_prepare_inflight(struct vhost_dev *hdev, VirtIODevice *vdev)
{
    int r;

    if (hdev->vhost_ops->vhost_get_inflight_fd == NULL ||
        hdev->vhost_ops->vhost_set_inflight_fd == NULL) {
        return 0;
    }

    hdev->vdev = vdev;

    r = vhost_dev_set_features(hdev, hdev->log_enabled);
    if (r < 0) {
        VHOST_OPS_DEBUG(r, "vhost_dev_prepare_inflight failed");
        return r;
    }

    return 0;
}

int vhost_dev_set_inflight(struct vhost_dev *dev,
                           struct vhost_inflight *inflight)
{
    int r;

    if (dev->vhost_ops->vhost_set_inflight_fd && inflight->addr) {
        r = dev->vhost_ops->vhost_set_inflight_fd(dev, inflight);
        if (r) {
            VHOST_OPS_DEBUG(r, "vhost_set_inflight_fd failed");
            return r;
        }
    }

    return 0;
}

int vhost_dev_get_inflight(struct vhost_dev *dev, uint16_t queue_size,
                           struct vhost_inflight *inflight)
{
    int r;

    if (dev->vhost_ops->vhost_get_inflight_fd) {
        r = dev->vhost_ops->vhost_get_inflight_fd(dev, queue_size, inflight);
        if (r) {
            VHOST_OPS_DEBUG(r, "vhost_get_inflight_fd failed");
            return r;
        }
    }

    return 0;
}

/* Host notifiers must be enabled at this point. */
int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev)
{
    int i, r;

    /* should only be called after backend is connected */
    assert(hdev->vhost_ops);

    trace_vhost_dev_start(hdev, vdev->name);

    vdev->vhost_started = true;
    hdev->started = true;
    hdev->vdev = vdev;

    r = vhost_dev_set_features(hdev, hdev->log_enabled);
    if (r < 0) {
        goto fail_features;
    }

    if (vhost_dev_has_iommu(hdev)) {
        memory_listener_register(&hdev->iommu_listener, vdev->dma_as);
    }

    r = hdev->vhost_ops->vhost_set_mem_table(hdev, hdev->mem);
    if (r < 0) {
        VHOST_OPS_DEBUG(r, "vhost_set_mem_table failed");
        goto fail_mem;
    }
    for (i = 0; i < hdev->nvqs; ++i) {
        r = vhost_virtqueue_start(hdev,
                                  vdev,
                                  hdev->vqs + i,
                                  hdev->vq_index + i);
        if (r < 0) {
            goto fail_vq;
        }
    }

    if (hdev->log_enabled) {
        uint64_t log_base;

        hdev->log_size = vhost_get_log_size(hdev);
        hdev->log = vhost_log_get(hdev->log_size,
                                  vhost_dev_log_is_shared(hdev));
        log_base = (uintptr_t)hdev->log->log;
        r = hdev->vhost_ops->vhost_set_log_base(hdev,
                                                hdev->log_size ? log_base : 0,
                                                hdev->log);
        if (r < 0) {
            VHOST_OPS_DEBUG(r, "vhost_set_log_base failed");
            goto fail_log;
        }
    }
    if (hdev->vhost_ops->vhost_dev_start) {
        r = hdev->vhost_ops->vhost_dev_start(hdev, true);
        if (r) {
            goto fail_log;
        }
    }
    if (vhost_dev_has_iommu(hdev) &&
        hdev->vhost_ops->vhost_set_iotlb_callback) {
            hdev->vhost_ops->vhost_set_iotlb_callback(hdev, true);

        /* Update used ring information for IOTLB to work correctly,
         * vhost-kernel code requires for this.*/
        for (i = 0; i < hdev->nvqs; ++i) {
            struct vhost_virtqueue *vq = hdev->vqs + i;
            vhost_device_iotlb_miss(hdev, vq->used_phys, true);
        }
    }
    return 0;
fail_log:
    vhost_log_put(hdev, false);
fail_vq:
    while (--i >= 0) {
        vhost_virtqueue_stop(hdev,
                             vdev,
                             hdev->vqs + i,
                             hdev->vq_index + i);
    }

fail_mem:
fail_features:
    vdev->vhost_started = false;
    hdev->started = false;
    return r;
}

/* Host notifiers must be enabled at this point. */
void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev)
{
    int i;

    /* should only be called after backend is connected */
    assert(hdev->vhost_ops);

    trace_vhost_dev_stop(hdev, vdev->name);

    if (hdev->vhost_ops->vhost_dev_start) {
        hdev->vhost_ops->vhost_dev_start(hdev, false);
    }
    for (i = 0; i < hdev->nvqs; ++i) {
        vhost_virtqueue_stop(hdev,
                             vdev,
                             hdev->vqs + i,
                             hdev->vq_index + i);
    }

    if (vhost_dev_has_iommu(hdev)) {
        if (hdev->vhost_ops->vhost_set_iotlb_callback) {
            hdev->vhost_ops->vhost_set_iotlb_callback(hdev, false);
        }
        memory_listener_unregister(&hdev->iommu_listener);
    }
    vhost_log_put(hdev, true);
    hdev->started = false;
    vdev->vhost_started = false;
    hdev->vdev = NULL;
}

int vhost_net_set_backend(struct vhost_dev *hdev,
                          struct vhost_vring_file *file)
{
    if (hdev->vhost_ops->vhost_net_set_backend) {
        return hdev->vhost_ops->vhost_net_set_backend(hdev, file);
    }

    return -ENOSYS;
}