summaryrefslogtreecommitdiffstats
path: root/lib/librte_vhost/vhost_user.c
blob: 508228a3c65f1fde8d0c4468b2f5377be56a4ef1 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
/* SPDX-License-Identifier: BSD-3-Clause
 * Copyright(c) 2010-2018 Intel Corporation
 */

/* Security model
 * --------------
 * The vhost-user protocol connection is an external interface, so it must be
 * robust against invalid inputs.
 *
 * This is important because the vhost-user master is only one step removed
 * from the guest.  Malicious guests that have escaped will then launch further
 * attacks from the vhost-user master.
 *
 * Even in deployments where guests are trusted, a bug in the vhost-user master
 * can still cause invalid messages to be sent.  Such messages must not
 * compromise the stability of the DPDK application by causing crashes, memory
 * corruption, or other problematic behavior.
 *
 * Do not assume received VhostUserMsg fields contain sensible values!
 */

#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <fcntl.h>
#include <sys/ioctl.h>
#include <sys/mman.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <sys/syscall.h>
#include <assert.h>
#ifdef RTE_LIBRTE_VHOST_NUMA
#include <numaif.h>
#endif
#ifdef RTE_LIBRTE_VHOST_POSTCOPY
#include <linux/userfaultfd.h>
#endif

#include <rte_common.h>
#include <rte_malloc.h>
#include <rte_log.h>

#include "iotlb.h"
#include "vhost.h"
#include "vhost_user.h"

#define VIRTIO_MIN_MTU 68
#define VIRTIO_MAX_MTU 65535

static const char *vhost_message_str[VHOST_USER_MAX] = {
	[VHOST_USER_NONE] = "VHOST_USER_NONE",
	[VHOST_USER_GET_FEATURES] = "VHOST_USER_GET_FEATURES",
	[VHOST_USER_SET_FEATURES] = "VHOST_USER_SET_FEATURES",
	[VHOST_USER_SET_OWNER] = "VHOST_USER_SET_OWNER",
	[VHOST_USER_RESET_OWNER] = "VHOST_USER_RESET_OWNER",
	[VHOST_USER_SET_MEM_TABLE] = "VHOST_USER_SET_MEM_TABLE",
	[VHOST_USER_SET_LOG_BASE] = "VHOST_USER_SET_LOG_BASE",
	[VHOST_USER_SET_LOG_FD] = "VHOST_USER_SET_LOG_FD",
	[VHOST_USER_SET_VRING_NUM] = "VHOST_USER_SET_VRING_NUM",
	[VHOST_USER_SET_VRING_ADDR] = "VHOST_USER_SET_VRING_ADDR",
	[VHOST_USER_SET_VRING_BASE] = "VHOST_USER_SET_VRING_BASE",
	[VHOST_USER_GET_VRING_BASE] = "VHOST_USER_GET_VRING_BASE",
	[VHOST_USER_SET_VRING_KICK] = "VHOST_USER_SET_VRING_KICK",
	[VHOST_USER_SET_VRING_CALL] = "VHOST_USER_SET_VRING_CALL",
	[VHOST_USER_SET_VRING_ERR]  = "VHOST_USER_SET_VRING_ERR",
	[VHOST_USER_GET_PROTOCOL_FEATURES]  = "VHOST_USER_GET_PROTOCOL_FEATURES",
	[VHOST_USER_SET_PROTOCOL_FEATURES]  = "VHOST_USER_SET_PROTOCOL_FEATURES",
	[VHOST_USER_GET_QUEUE_NUM]  = "VHOST_USER_GET_QUEUE_NUM",
	[VHOST_USER_SET_VRING_ENABLE]  = "VHOST_USER_SET_VRING_ENABLE",
	[VHOST_USER_SEND_RARP]  = "VHOST_USER_SEND_RARP",
	[VHOST_USER_NET_SET_MTU]  = "VHOST_USER_NET_SET_MTU",
	[VHOST_USER_SET_SLAVE_REQ_FD]  = "VHOST_USER_SET_SLAVE_REQ_FD",
	[VHOST_USER_IOTLB_MSG]  = "VHOST_USER_IOTLB_MSG",
	[VHOST_USER_CRYPTO_CREATE_SESS] = "VHOST_USER_CRYPTO_CREATE_SESS",
	[VHOST_USER_CRYPTO_CLOSE_SESS] = "VHOST_USER_CRYPTO_CLOSE_SESS",
	[VHOST_USER_POSTCOPY_ADVISE]  = "VHOST_USER_POSTCOPY_ADVISE",
	[VHOST_USER_POSTCOPY_LISTEN]  = "VHOST_USER_POSTCOPY_LISTEN",
	[VHOST_USER_POSTCOPY_END]  = "VHOST_USER_POSTCOPY_END",
};

static int send_vhost_reply(int sockfd, struct VhostUserMsg *msg);
static int read_vhost_message(int sockfd, struct VhostUserMsg *msg);

static uint64_t
get_blk_size(int fd)
{
	struct stat stat;
	int ret;

	ret = fstat(fd, &stat);
	return ret == -1 ? (uint64_t)-1 : (uint64_t)stat.st_blksize;
}

static void
free_mem_region(struct virtio_net *dev)
{
	uint32_t i;
	struct rte_vhost_mem_region *reg;

	if (!dev || !dev->mem)
		return;

	for (i = 0; i < dev->mem->nregions; i++) {
		reg = &dev->mem->regions[i];
		if (reg->host_user_addr) {
			munmap(reg->mmap_addr, reg->mmap_size);
			close(reg->fd);
		}
	}
}

void
vhost_backend_cleanup(struct virtio_net *dev)
{
	if (dev->mem) {
		free_mem_region(dev);
		rte_free(dev->mem);
		dev->mem = NULL;
	}

	free(dev->guest_pages);
	dev->guest_pages = NULL;

	if (dev->log_addr) {
		munmap((void *)(uintptr_t)dev->log_addr, dev->log_size);
		dev->log_addr = 0;
	}

	if (dev->slave_req_fd >= 0) {
		close(dev->slave_req_fd);
		dev->slave_req_fd = -1;
	}

	if (dev->postcopy_ufd >= 0) {
		close(dev->postcopy_ufd);
		dev->postcopy_ufd = -1;
	}

	dev->postcopy_listening = 0;
}

/*
 * This function just returns success at the moment unless
 * the device hasn't been initialised.
 */
static int
vhost_user_set_owner(struct virtio_net **pdev __rte_unused,
			struct VhostUserMsg *msg __rte_unused,
			int main_fd __rte_unused)
{
	return VH_RESULT_OK;
}

static int
vhost_user_reset_owner(struct virtio_net **pdev,
			struct VhostUserMsg *msg __rte_unused,
			int main_fd __rte_unused)
{
	struct virtio_net *dev = *pdev;
	vhost_destroy_device_notify(dev);

	cleanup_device(dev, 0);
	reset_device(dev);
	return VH_RESULT_OK;
}

/*
 * The features that we support are requested.
 */
static int
vhost_user_get_features(struct virtio_net **pdev, struct VhostUserMsg *msg,
			int main_fd __rte_unused)
{
	struct virtio_net *dev = *pdev;
	uint64_t features = 0;

	rte_vhost_driver_get_features(dev->ifname, &features);

	msg->payload.u64 = features;
	msg->size = sizeof(msg->payload.u64);
	msg->fd_num = 0;

	return VH_RESULT_REPLY;
}

/*
 * The queue number that we support are requested.
 */
static int
vhost_user_get_queue_num(struct virtio_net **pdev, struct VhostUserMsg *msg,
			int main_fd __rte_unused)
{
	struct virtio_net *dev = *pdev;
	uint32_t queue_num = 0;

	rte_vhost_driver_get_queue_num(dev->ifname, &queue_num);

	msg->payload.u64 = (uint64_t)queue_num;
	msg->size = sizeof(msg->payload.u64);
	msg->fd_num = 0;

	return VH_RESULT_REPLY;
}

/*
 * We receive the negotiated features supported by us and the virtio device.
 */
static int
vhost_user_set_features(struct virtio_net **pdev, struct VhostUserMsg *msg,
			int main_fd __rte_unused)
{
	struct virtio_net *dev = *pdev;
	uint64_t features = msg->payload.u64;
	uint64_t vhost_features = 0;
	struct rte_vdpa_device *vdpa_dev;
	int did = -1;

	rte_vhost_driver_get_features(dev->ifname, &vhost_features);
	if (features & ~vhost_features) {
		RTE_LOG(ERR, VHOST_CONFIG,
			"(%d) received invalid negotiated features.\n",
			dev->vid);
		return VH_RESULT_ERR;
	}

	if (dev->flags & VIRTIO_DEV_RUNNING) {
		if (dev->features == features)
			return VH_RESULT_OK;

		/*
		 * Error out if master tries to change features while device is
		 * in running state. The exception being VHOST_F_LOG_ALL, which
		 * is enabled when the live-migration starts.
		 */
		if ((dev->features ^ features) & ~(1ULL << VHOST_F_LOG_ALL)) {
			RTE_LOG(ERR, VHOST_CONFIG,
				"(%d) features changed while device is running.\n",
				dev->vid);
			return VH_RESULT_ERR;
		}

		if (dev->notify_ops->features_changed)
			dev->notify_ops->features_changed(dev->vid, features);
	}

	dev->features = features;
	if (dev->features &
		((1 << VIRTIO_NET_F_MRG_RXBUF) | (1ULL << VIRTIO_F_VERSION_1))) {
		dev->vhost_hlen = sizeof(struct virtio_net_hdr_mrg_rxbuf);
	} else {
		dev->vhost_hlen = sizeof(struct virtio_net_hdr);
	}
	VHOST_LOG_DEBUG(VHOST_CONFIG,
		"(%d) mergeable RX buffers %s, virtio 1 %s\n",
		dev->vid,
		(dev->features & (1 << VIRTIO_NET_F_MRG_RXBUF)) ? "on" : "off",
		(dev->features & (1ULL << VIRTIO_F_VERSION_1)) ? "on" : "off");

	if ((dev->flags & VIRTIO_DEV_BUILTIN_VIRTIO_NET) &&
	    !(dev->features & (1ULL << VIRTIO_NET_F_MQ))) {
		/*
		 * Remove all but first queue pair if MQ hasn't been
		 * negotiated. This is safe because the device is not
		 * running at this stage.
		 */
		while (dev->nr_vring > 2) {
			struct vhost_virtqueue *vq;

			vq = dev->virtqueue[--dev->nr_vring];
			if (!vq)
				continue;

			dev->virtqueue[dev->nr_vring] = NULL;
			cleanup_vq(vq, 1);
			free_vq(dev, vq);
		}
	}

	did = dev->vdpa_dev_id;
	vdpa_dev = rte_vdpa_get_device(did);
	if (vdpa_dev && vdpa_dev->ops->set_features)
		vdpa_dev->ops->set_features(dev->vid);

	return VH_RESULT_OK;
}

/*
 * The virtio device sends us the size of the descriptor ring.
 */
static int
vhost_user_set_vring_num(struct virtio_net **pdev,
			struct VhostUserMsg *msg,
			int main_fd __rte_unused)
{
	struct virtio_net *dev = *pdev;
	struct vhost_virtqueue *vq = dev->virtqueue[msg->payload.state.index];

	vq->size = msg->payload.state.num;

	/* VIRTIO 1.0, 2.4 Virtqueues says:
	 *
	 *   Queue Size value is always a power of 2. The maximum Queue Size
	 *   value is 32768.
	 */
	if ((vq->size & (vq->size - 1)) || vq->size > 32768) {
		RTE_LOG(ERR, VHOST_CONFIG,
			"invalid virtqueue size %u\n", vq->size);
		return VH_RESULT_ERR;
	}

	if (dev->dequeue_zero_copy) {
		vq->nr_zmbuf = 0;
		vq->last_zmbuf_idx = 0;
		vq->zmbuf_size = vq->size;
		vq->zmbufs = rte_zmalloc(NULL, vq->zmbuf_size *
					 sizeof(struct zcopy_mbuf), 0);
		if (vq->zmbufs == NULL) {
			RTE_LOG(WARNING, VHOST_CONFIG,
				"failed to allocate mem for zero copy; "
				"zero copy is force disabled\n");
			dev->dequeue_zero_copy = 0;
		}
		TAILQ_INIT(&vq->zmbuf_list);
	}

	if (vq_is_packed(dev)) {
		vq->shadow_used_packed = rte_malloc(NULL,
				vq->size *
				sizeof(struct vring_used_elem_packed),
				RTE_CACHE_LINE_SIZE);
		if (!vq->shadow_used_packed) {
			RTE_LOG(ERR, VHOST_CONFIG,
					"failed to allocate memory for shadow used ring.\n");
			return VH_RESULT_ERR;
		}

	} else {
		vq->shadow_used_split = rte_malloc(NULL,
				vq->size * sizeof(struct vring_used_elem),
				RTE_CACHE_LINE_SIZE);
		if (!vq->shadow_used_split) {
			RTE_LOG(ERR, VHOST_CONFIG,
					"failed to allocate memory for shadow used ring.\n");
			return VH_RESULT_ERR;
		}
	}

	vq->batch_copy_elems = rte_malloc(NULL,
				vq->size * sizeof(struct batch_copy_elem),
				RTE_CACHE_LINE_SIZE);
	if (!vq->batch_copy_elems) {
		RTE_LOG(ERR, VHOST_CONFIG,
			"failed to allocate memory for batching copy.\n");
		return VH_RESULT_ERR;
	}

	return VH_RESULT_OK;
}

/*
 * Reallocate virtio_dev and vhost_virtqueue data structure to make them on the
 * same numa node as the memory of vring descriptor.
 */
#ifdef RTE_LIBRTE_VHOST_NUMA
static struct virtio_net*
numa_realloc(struct virtio_net *dev, int index)
{
	int oldnode, newnode;
	struct virtio_net *old_dev;
	struct vhost_virtqueue *old_vq, *vq;
	struct zcopy_mbuf *new_zmbuf;
	struct vring_used_elem *new_shadow_used_split;
	struct vring_used_elem_packed *new_shadow_used_packed;
	struct batch_copy_elem *new_batch_copy_elems;
	int ret;

	old_dev = dev;
	vq = old_vq = dev->virtqueue[index];

	ret = get_mempolicy(&newnode, NULL, 0, old_vq->desc,
			    MPOL_F_NODE | MPOL_F_ADDR);

	/* check if we need to reallocate vq */
	ret |= get_mempolicy(&oldnode, NULL, 0, old_vq,
			     MPOL_F_NODE | MPOL_F_ADDR);
	if (ret) {
		RTE_LOG(ERR, VHOST_CONFIG,
			"Unable to get vq numa information.\n");
		return dev;
	}
	if (oldnode != newnode) {
		RTE_LOG(INFO, VHOST_CONFIG,
			"reallocate vq from %d to %d node\n", oldnode, newnode);
		vq = rte_malloc_socket(NULL, sizeof(*vq), 0, newnode);
		if (!vq)
			return dev;

		memcpy(vq, old_vq, sizeof(*vq));
		TAILQ_INIT(&vq->zmbuf_list);

		if (dev->dequeue_zero_copy) {
			new_zmbuf = rte_malloc_socket(NULL, vq->zmbuf_size *
					sizeof(struct zcopy_mbuf), 0, newnode);
			if (new_zmbuf) {
				rte_free(vq->zmbufs);
				vq->zmbufs = new_zmbuf;
			}
		}

		if (vq_is_packed(dev)) {
			new_shadow_used_packed = rte_malloc_socket(NULL,
					vq->size *
					sizeof(struct vring_used_elem_packed),
					RTE_CACHE_LINE_SIZE,
					newnode);
			if (new_shadow_used_packed) {
				rte_free(vq->shadow_used_packed);
				vq->shadow_used_packed = new_shadow_used_packed;
			}
		} else {
			new_shadow_used_split = rte_malloc_socket(NULL,
					vq->size *
					sizeof(struct vring_used_elem),
					RTE_CACHE_LINE_SIZE,
					newnode);
			if (new_shadow_used_split) {
				rte_free(vq->shadow_used_split);
				vq->shadow_used_split = new_shadow_used_split;
			}
		}

		new_batch_copy_elems = rte_malloc_socket(NULL,
			vq->size * sizeof(struct batch_copy_elem),
			RTE_CACHE_LINE_SIZE,
			newnode);
		if (new_batch_copy_elems) {
			rte_free(vq->batch_copy_elems);
			vq->batch_copy_elems = new_batch_copy_elems;
		}

		rte_free(old_vq);
	}

	/* check if we need to reallocate dev */
	ret = get_mempolicy(&oldnode, NULL, 0, old_dev,
			    MPOL_F_NODE | MPOL_F_ADDR);
	if (ret) {
		RTE_LOG(ERR, VHOST_CONFIG,
			"Unable to get dev numa information.\n");
		goto out;
	}
	if (oldnode != newnode) {
		RTE_LOG(INFO, VHOST_CONFIG,
			"reallocate dev from %d to %d node\n",
			oldnode, newnode);
		dev = rte_malloc_socket(NULL, sizeof(*dev), 0, newnode);
		if (!dev) {
			dev = old_dev;
			goto out;
		}

		memcpy(dev, old_dev, sizeof(*dev));
		rte_free(old_dev);
	}

out:
	dev->virtqueue[index] = vq;
	vhost_devices[dev->vid] = dev;

	if (old_vq != vq)
		vhost_user_iotlb_init(dev, index);

	return dev;
}
#else
static struct virtio_net*
numa_realloc(struct virtio_net *dev, int index __rte_unused)
{
	return dev;
}
#endif

/* Converts QEMU virtual address to Vhost virtual address. */
static uint64_t
qva_to_vva(struct virtio_net *dev, uint64_t qva, uint64_t *len)
{
	struct rte_vhost_mem_region *r;
	uint32_t i;

	/* Find the region where the address lives. */
	for (i = 0; i < dev->mem->nregions; i++) {
		r = &dev->mem->regions[i];

		if (qva >= r->guest_user_addr &&
		    qva <  r->guest_user_addr + r->size) {

			if (unlikely(*len > r->guest_user_addr + r->size - qva))
				*len = r->guest_user_addr + r->size - qva;

			return qva - r->guest_user_addr +
			       r->host_user_addr;
		}
	}
	*len = 0;

	return 0;
}


/*
 * Converts ring address to Vhost virtual address.
 * If IOMMU is enabled, the ring address is a guest IO virtual address,
 * else it is a QEMU virtual address.
 */
static uint64_t
ring_addr_to_vva(struct virtio_net *dev, struct vhost_virtqueue *vq,
		uint64_t ra, uint64_t *size)
{
	if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM)) {
		uint64_t vva;

		vva = vhost_user_iotlb_cache_find(vq, ra,
					size, VHOST_ACCESS_RW);
		if (!vva)
			vhost_user_iotlb_miss(dev, ra, VHOST_ACCESS_RW);

		return vva;
	}

	return qva_to_vva(dev, ra, size);
}

static struct virtio_net *
translate_ring_addresses(struct virtio_net *dev, int vq_index)
{
	struct vhost_virtqueue *vq = dev->virtqueue[vq_index];
	struct vhost_vring_addr *addr = &vq->ring_addrs;
	uint64_t len;

	if (vq_is_packed(dev)) {
		len = sizeof(struct vring_packed_desc) * vq->size;
		vq->desc_packed = (struct vring_packed_desc *)(uintptr_t)
			ring_addr_to_vva(dev, vq, addr->desc_user_addr, &len);
		vq->log_guest_addr = 0;
		if (vq->desc_packed == NULL ||
				len != sizeof(struct vring_packed_desc) *
				vq->size) {
			RTE_LOG(DEBUG, VHOST_CONFIG,
				"(%d) failed to map desc_packed ring.\n",
				dev->vid);
			return dev;
		}

		dev = numa_realloc(dev, vq_index);
		vq = dev->virtqueue[vq_index];
		addr = &vq->ring_addrs;

		len = sizeof(struct vring_packed_desc_event);
		vq->driver_event = (struct vring_packed_desc_event *)
					(uintptr_t)ring_addr_to_vva(dev,
					vq, addr->avail_user_addr, &len);
		if (vq->driver_event == NULL ||
				len != sizeof(struct vring_packed_desc_event)) {
			RTE_LOG(DEBUG, VHOST_CONFIG,
				"(%d) failed to find driver area address.\n",
				dev->vid);
			return dev;
		}

		len = sizeof(struct vring_packed_desc_event);
		vq->device_event = (struct vring_packed_desc_event *)
					(uintptr_t)ring_addr_to_vva(dev,
					vq, addr->used_user_addr, &len);
		if (vq->device_event == NULL ||
				len != sizeof(struct vring_packed_desc_event)) {
			RTE_LOG(DEBUG, VHOST_CONFIG,
				"(%d) failed to find device area address.\n",
				dev->vid);
			return dev;
		}

		return dev;
	}

	/* The addresses are converted from QEMU virtual to Vhost virtual. */
	if (vq->desc && vq->avail && vq->used)
		return dev;

	len = sizeof(struct vring_desc) * vq->size;
	vq->desc = (struct vring_desc *)(uintptr_t)ring_addr_to_vva(dev,
			vq, addr->desc_user_addr, &len);
	if (vq->desc == 0 || len != sizeof(struct vring_desc) * vq->size) {
		RTE_LOG(DEBUG, VHOST_CONFIG,
			"(%d) failed to map desc ring.\n",
			dev->vid);
		return dev;
	}

	dev = numa_realloc(dev, vq_index);
	vq = dev->virtqueue[vq_index];
	addr = &vq->ring_addrs;

	len = sizeof(struct vring_avail) + sizeof(uint16_t) * vq->size;
	vq->avail = (struct vring_avail *)(uintptr_t)ring_addr_to_vva(dev,
			vq, addr->avail_user_addr, &len);
	if (vq->avail == 0 ||
			len != sizeof(struct vring_avail) +
			sizeof(uint16_t) * vq->size) {
		RTE_LOG(DEBUG, VHOST_CONFIG,
			"(%d) failed to map avail ring.\n",
			dev->vid);
		return dev;
	}

	len = sizeof(struct vring_used) +
		sizeof(struct vring_used_elem) * vq->size;
	vq->used = (struct vring_used *)(uintptr_t)ring_addr_to_vva(dev,
			vq, addr->used_user_addr, &len);
	if (vq->used == 0 || len != sizeof(struct vring_used) +
			sizeof(struct vring_used_elem) * vq->size) {
		RTE_LOG(DEBUG, VHOST_CONFIG,
			"(%d) failed to map used ring.\n",
			dev->vid);
		return dev;
	}

	if (vq->last_used_idx != vq->used->idx) {
		RTE_LOG(WARNING, VHOST_CONFIG,
			"last_used_idx (%u) and vq->used->idx (%u) mismatches; "
			"some packets maybe resent for Tx and dropped for Rx\n",
			vq->last_used_idx, vq->used->idx);
		vq->last_used_idx  = vq->used->idx;
		vq->last_avail_idx = vq->used->idx;
	}

	vq->log_guest_addr = addr->log_guest_addr;

	VHOST_LOG_DEBUG(VHOST_CONFIG, "(%d) mapped address desc: %p\n",
			dev->vid, vq->desc);
	VHOST_LOG_DEBUG(VHOST_CONFIG, "(%d) mapped address avail: %p\n",
			dev->vid, vq->avail);
	VHOST_LOG_DEBUG(VHOST_CONFIG, "(%d) mapped address used: %p\n",
			dev->vid, vq->used);
	VHOST_LOG_DEBUG(VHOST_CONFIG, "(%d) log_guest_addr: %" PRIx64 "\n",
			dev->vid, vq->log_guest_addr);

	return dev;
}

/*
 * The virtio device sends us the desc, used and avail ring addresses.
 * This function then converts these to our address space.
 */
static int
vhost_user_set_vring_addr(struct virtio_net **pdev, struct VhostUserMsg *msg,
			int main_fd __rte_unused)
{
	struct virtio_net *dev = *pdev;
	struct vhost_virtqueue *vq;
	struct vhost_vring_addr *addr = &msg->payload.addr;

	if (dev->mem == NULL)
		return VH_RESULT_ERR;

	/* addr->index refers to the queue index. The txq 1, rxq is 0. */
	vq = dev->virtqueue[msg->payload.addr.index];

	/*
	 * Rings addresses should not be interpreted as long as the ring is not
	 * started and enabled
	 */
	memcpy(&vq->ring_addrs, addr, sizeof(*addr));

	vring_invalidate(dev, vq);

	if (vq->enabled && (dev->features &
				(1ULL << VHOST_USER_F_PROTOCOL_FEATURES))) {
		dev = translate_ring_addresses(dev, msg->payload.addr.index);
		if (!dev)
			return VH_RESULT_ERR;

		*pdev = dev;
	}

	return VH_RESULT_OK;
}

/*
 * The virtio device sends us the available ring last used index.
 */
static int
vhost_user_set_vring_base(struct virtio_net **pdev,
			struct VhostUserMsg *msg,
			int main_fd __rte_unused)
{
	struct virtio_net *dev = *pdev;
	dev->virtqueue[msg->payload.state.index]->last_used_idx  =
			msg->payload.state.num;
	dev->virtqueue[msg->payload.state.index]->last_avail_idx =
			msg->payload.state.num;

	return VH_RESULT_OK;
}

static int
add_one_guest_page(struct virtio_net *dev, uint64_t guest_phys_addr,
		   uint64_t host_phys_addr, uint64_t size)
{
	struct guest_page *page, *last_page;

	if (dev->nr_guest_pages == dev->max_guest_pages) {
		dev->max_guest_pages *= 2;
		dev->guest_pages = realloc(dev->guest_pages,
					dev->max_guest_pages * sizeof(*page));
		if (!dev->guest_pages) {
			RTE_LOG(ERR, VHOST_CONFIG, "cannot realloc guest_pages\n");
			return -1;
		}
	}

	if (dev->nr_guest_pages > 0) {
		last_page = &dev->guest_pages[dev->nr_guest_pages - 1];
		/* merge if the two pages are continuous */
		if (host_phys_addr == last_page->host_phys_addr +
				      last_page->size) {
			last_page->size += size;
			return 0;
		}
	}

	page = &dev->guest_pages[dev->nr_guest_pages++];
	page->guest_phys_addr = guest_phys_addr;
	page->host_phys_addr  = host_phys_addr;
	page->size = size;

	return 0;
}

static int
add_guest_pages(struct virtio_net *dev, struct rte_vhost_mem_region *reg,
		uint64_t page_size)
{
	uint64_t reg_size = reg->size;
	uint64_t host_user_addr  = reg->host_user_addr;
	uint64_t guest_phys_addr = reg->guest_phys_addr;
	uint64_t host_phys_addr;
	uint64_t size;

	host_phys_addr = rte_mem_virt2iova((void *)(uintptr_t)host_user_addr);
	size = page_size - (guest_phys_addr & (page_size - 1));
	size = RTE_MIN(size, reg_size);

	if (add_one_guest_page(dev, guest_phys_addr, host_phys_addr, size) < 0)
		return -1;

	host_user_addr  += size;
	guest_phys_addr += size;
	reg_size -= size;

	while (reg_size > 0) {
		size = RTE_MIN(reg_size, page_size);
		host_phys_addr = rte_mem_virt2iova((void *)(uintptr_t)
						  host_user_addr);
		if (add_one_guest_page(dev, guest_phys_addr, host_phys_addr,
				size) < 0)
			return -1;

		host_user_addr  += size;
		guest_phys_addr += size;
		reg_size -= size;
	}

	return 0;
}

#ifdef RTE_LIBRTE_VHOST_DEBUG
/* TODO: enable it only in debug mode? */
static void
dump_guest_pages(struct virtio_net *dev)
{
	uint32_t i;
	struct guest_page *page;

	for (i = 0; i < dev->nr_guest_pages; i++) {
		page = &dev->guest_pages[i];

		RTE_LOG(INFO, VHOST_CONFIG,
			"guest physical page region %u\n"
			"\t guest_phys_addr: %" PRIx64 "\n"
			"\t host_phys_addr : %" PRIx64 "\n"
			"\t size           : %" PRIx64 "\n",
			i,
			page->guest_phys_addr,
			page->host_phys_addr,
			page->size);
	}
}
#else
#define dump_guest_pages(dev)
#endif

static bool
vhost_memory_changed(struct VhostUserMemory *new,
		     struct rte_vhost_memory *old)
{
	uint32_t i;

	if (new->nregions != old->nregions)
		return true;

	for (i = 0; i < new->nregions; ++i) {
		VhostUserMemoryRegion *new_r = &new->regions[i];
		struct rte_vhost_mem_region *old_r = &old->regions[i];

		if (new_r->guest_phys_addr != old_r->guest_phys_addr)
			return true;
		if (new_r->memory_size != old_r->size)
			return true;
		if (new_r->userspace_addr != old_r->guest_user_addr)
			return true;
	}

	return false;
}

static int
vhost_user_set_mem_table(struct virtio_net **pdev, struct VhostUserMsg *msg,
			int main_fd)
{
	struct virtio_net *dev = *pdev;
	struct VhostUserMemory *memory = &msg->payload.memory;
	struct rte_vhost_mem_region *reg;
	void *mmap_addr;
	uint64_t mmap_size;
	uint64_t mmap_offset;
	uint64_t alignment;
	uint32_t i;
	int populate;
	int fd;

	if (memory->nregions > VHOST_MEMORY_MAX_NREGIONS) {
		RTE_LOG(ERR, VHOST_CONFIG,
			"too many memory regions (%u)\n", memory->nregions);
		return VH_RESULT_ERR;
	}

	if (dev->mem && !vhost_memory_changed(memory, dev->mem)) {
		RTE_LOG(INFO, VHOST_CONFIG,
			"(%d) memory regions not changed\n", dev->vid);

		for (i = 0; i < memory->nregions; i++)
			close(msg->fds[i]);

		return VH_RESULT_OK;
	}

	if (dev->mem) {
		free_mem_region(dev);
		rte_free(dev->mem);
		dev->mem = NULL;
	}

	/* Flush IOTLB cache as previous HVAs are now invalid */
	if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
		for (i = 0; i < dev->nr_vring; i++)
			vhost_user_iotlb_flush_all(dev->virtqueue[i]);

	dev->nr_guest_pages = 0;
	if (!dev->guest_pages) {
		dev->max_guest_pages = 8;
		dev->guest_pages = malloc(dev->max_guest_pages *
						sizeof(struct guest_page));
		if (dev->guest_pages == NULL) {
			RTE_LOG(ERR, VHOST_CONFIG,
				"(%d) failed to allocate memory "
				"for dev->guest_pages\n",
				dev->vid);
			return VH_RESULT_ERR;
		}
	}

	dev->mem = rte_zmalloc("vhost-mem-table", sizeof(struct rte_vhost_memory) +
		sizeof(struct rte_vhost_mem_region) * memory->nregions, 0);
	if (dev->mem == NULL) {
		RTE_LOG(ERR, VHOST_CONFIG,
			"(%d) failed to allocate memory for dev->mem\n",
			dev->vid);
		return VH_RESULT_ERR;
	}
	dev->mem->nregions = memory->nregions;

	for (i = 0; i < memory->nregions; i++) {
		fd  = msg->fds[i];
		reg = &dev->mem->regions[i];

		reg->guest_phys_addr = memory->regions[i].guest_phys_addr;
		reg->guest_user_addr = memory->regions[i].userspace_addr;
		reg->size            = memory->regions[i].memory_size;
		reg->fd              = fd;

		mmap_offset = memory->regions[i].mmap_offset;

		/* Check for memory_size + mmap_offset overflow */
		if (mmap_offset >= -reg->size) {
			RTE_LOG(ERR, VHOST_CONFIG,
				"mmap_offset (%#"PRIx64") and memory_size "
				"(%#"PRIx64") overflow\n",
				mmap_offset, reg->size);
			goto err_mmap;
		}

		mmap_size = reg->size + mmap_offset;

		/* mmap() without flag of MAP_ANONYMOUS, should be called
		 * with length argument aligned with hugepagesz at older
		 * longterm version Linux, like 2.6.32 and 3.2.72, or
		 * mmap() will fail with EINVAL.
		 *
		 * to avoid failure, make sure in caller to keep length
		 * aligned.
		 */
		alignment = get_blk_size(fd);
		if (alignment == (uint64_t)-1) {
			RTE_LOG(ERR, VHOST_CONFIG,
				"couldn't get hugepage size through fstat\n");
			goto err_mmap;
		}
		mmap_size = RTE_ALIGN_CEIL(mmap_size, alignment);

		populate = (dev->dequeue_zero_copy) ? MAP_POPULATE : 0;
		mmap_addr = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE,
				 MAP_SHARED | populate, fd, 0);

		if (mmap_addr == MAP_FAILED) {
			RTE_LOG(ERR, VHOST_CONFIG,
				"mmap region %u failed.\n", i);
			goto err_mmap;
		}

		reg->mmap_addr = mmap_addr;
		reg->mmap_size = mmap_size;
		reg->host_user_addr = (uint64_t)(uintptr_t)mmap_addr +
				      mmap_offset;

		if (dev->dequeue_zero_copy)
			if (add_guest_pages(dev, reg, alignment) < 0) {
				RTE_LOG(ERR, VHOST_CONFIG,
					"adding guest pages to region %u failed.\n",
					i);
				goto err_mmap;
			}

		RTE_LOG(INFO, VHOST_CONFIG,
			"guest memory region %u, size: 0x%" PRIx64 "\n"
			"\t guest physical addr: 0x%" PRIx64 "\n"
			"\t guest virtual  addr: 0x%" PRIx64 "\n"
			"\t host  virtual  addr: 0x%" PRIx64 "\n"
			"\t mmap addr : 0x%" PRIx64 "\n"
			"\t mmap size : 0x%" PRIx64 "\n"
			"\t mmap align: 0x%" PRIx64 "\n"
			"\t mmap off  : 0x%" PRIx64 "\n",
			i, reg->size,
			reg->guest_phys_addr,
			reg->guest_user_addr,
			reg->host_user_addr,
			(uint64_t)(uintptr_t)mmap_addr,
			mmap_size,
			alignment,
			mmap_offset);

		if (dev->postcopy_listening) {
			/*
			 * We haven't a better way right now than sharing
			 * DPDK's virtual address with Qemu, so that Qemu can
			 * retrieve the region offset when handling userfaults.
			 */
			memory->regions[i].userspace_addr =
				reg->host_user_addr;
		}
	}
	if (dev->postcopy_listening) {
		/* Send the addresses back to qemu */
		msg->fd_num = 0;
		send_vhost_reply(main_fd, msg);

		/* Wait for qemu to acknolwedge it's got the addresses
		 * we've got to wait before we're allowed to generate faults.
		 */
		VhostUserMsg ack_msg;
		if (read_vhost_message(main_fd, &ack_msg) <= 0) {
			RTE_LOG(ERR, VHOST_CONFIG,
				"Failed to read qemu ack on postcopy set-mem-table\n");
			goto err_mmap;
		}
		if (ack_msg.request.master != VHOST_USER_SET_MEM_TABLE) {
			RTE_LOG(ERR, VHOST_CONFIG,
				"Bad qemu ack on postcopy set-mem-table (%d)\n",
				ack_msg.request.master);
			goto err_mmap;
		}

		/* Now userfault register and we can use the memory */
		for (i = 0; i < memory->nregions; i++) {
#ifdef RTE_LIBRTE_VHOST_POSTCOPY
			reg = &dev->mem->regions[i];
			struct uffdio_register reg_struct;

			/*
			 * Let's register all the mmap'ed area to ensure
			 * alignment on page boundary.
			 */
			reg_struct.range.start =
				(uint64_t)(uintptr_t)reg->mmap_addr;
			reg_struct.range.len = reg->mmap_size;
			reg_struct.mode = UFFDIO_REGISTER_MODE_MISSING;

			if (ioctl(dev->postcopy_ufd, UFFDIO_REGISTER,
						&reg_struct)) {
				RTE_LOG(ERR, VHOST_CONFIG,
					"Failed to register ufd for region %d: (ufd = %d) %s\n",
					i, dev->postcopy_ufd,
					strerror(errno));
				goto err_mmap;
			}
			RTE_LOG(INFO, VHOST_CONFIG,
				"\t userfaultfd registered for range : %llx - %llx\n",
				reg_struct.range.start,
				reg_struct.range.start +
				reg_struct.range.len - 1);
#else
			goto err_mmap;
#endif
		}
	}

	for (i = 0; i < dev->nr_vring; i++) {
		struct vhost_virtqueue *vq = dev->virtqueue[i];

		if (vq->desc || vq->avail || vq->used) {
			/*
			 * If the memory table got updated, the ring addresses
			 * need to be translated again as virtual addresses have
			 * changed.
			 */
			vring_invalidate(dev, vq);

			dev = translate_ring_addresses(dev, i);
			if (!dev) {
				dev = *pdev;
				goto err_mmap;
			}

			*pdev = dev;
		}
	}

	dump_guest_pages(dev);

	return VH_RESULT_OK;

err_mmap:
	free_mem_region(dev);
	rte_free(dev->mem);
	dev->mem = NULL;
	return VH_RESULT_ERR;
}

static bool
vq_is_ready(struct virtio_net *dev, struct vhost_virtqueue *vq)
{
	bool rings_ok;

	if (!vq)
		return false;

	if (vq_is_packed(dev))
		rings_ok = !!vq->desc_packed;
	else
		rings_ok = vq->desc && vq->avail && vq->used;

	return rings_ok &&
	       vq->kickfd != VIRTIO_UNINITIALIZED_EVENTFD &&
	       vq->callfd != VIRTIO_UNINITIALIZED_EVENTFD;
}

static int
virtio_is_ready(struct virtio_net *dev)
{
	struct vhost_virtqueue *vq;
	uint32_t i;

	if (dev->nr_vring == 0)
		return 0;

	for (i = 0; i < dev->nr_vring; i++) {
		vq = dev->virtqueue[i];

		if (!vq_is_ready(dev, vq))
			return 0;
	}

	RTE_LOG(INFO, VHOST_CONFIG,
		"virtio is now ready for processing.\n");
	return 1;
}

static int
vhost_user_set_vring_call(struct virtio_net **pdev, struct VhostUserMsg *msg,
			int main_fd __rte_unused)
{
	struct virtio_net *dev = *pdev;
	struct vhost_vring_file file;
	struct vhost_virtqueue *vq;

	file.index = msg->payload.u64 & VHOST_USER_VRING_IDX_MASK;
	if (msg->payload.u64 & VHOST_USER_VRING_NOFD_MASK)
		file.fd = VIRTIO_INVALID_EVENTFD;
	else
		file.fd = msg->fds[0];
	RTE_LOG(INFO, VHOST_CONFIG,
		"vring call idx:%d file:%d\n", file.index, file.fd);

	vq = dev->virtqueue[file.index];
	if (vq->callfd >= 0)
		close(vq->callfd);

	vq->callfd = file.fd;

	return VH_RESULT_OK;
}

static int vhost_user_set_vring_err(struct virtio_net **pdev __rte_unused,
			struct VhostUserMsg *msg,
			int main_fd __rte_unused)
{
	if (!(msg->payload.u64 & VHOST_USER_VRING_NOFD_MASK))
		close(msg->fds[0]);
	RTE_LOG(INFO, VHOST_CONFIG, "not implemented\n");

	return VH_RESULT_OK;
}

static int
vhost_user_set_vring_kick(struct virtio_net **pdev, struct VhostUserMsg *msg,
			int main_fd __rte_unused)
{
	struct virtio_net *dev = *pdev;
	struct vhost_vring_file file;
	struct vhost_virtqueue *vq;

	file.index = msg->payload.u64 & VHOST_USER_VRING_IDX_MASK;
	if (msg->payload.u64 & VHOST_USER_VRING_NOFD_MASK)
		file.fd = VIRTIO_INVALID_EVENTFD;
	else
		file.fd = msg->fds[0];
	RTE_LOG(INFO, VHOST_CONFIG,
		"vring kick idx:%d file:%d\n", file.index, file.fd);

	/* Interpret ring addresses only when ring is started. */
	dev = translate_ring_addresses(dev, file.index);
	if (!dev)
		return VH_RESULT_ERR;

	*pdev = dev;

	vq = dev->virtqueue[file.index];

	/*
	 * When VHOST_USER_F_PROTOCOL_FEATURES is not negotiated,
	 * the ring starts already enabled. Otherwise, it is enabled via
	 * the SET_VRING_ENABLE message.
	 */
	if (!(dev->features & (1ULL << VHOST_USER_F_PROTOCOL_FEATURES)))
		vq->enabled = 1;

	if (vq->kickfd >= 0)
		close(vq->kickfd);
	vq->kickfd = file.fd;

	return VH_RESULT_OK;
}

static void
free_zmbufs(struct vhost_virtqueue *vq)
{
	struct zcopy_mbuf *zmbuf, *next;

	for (zmbuf = TAILQ_FIRST(&vq->zmbuf_list);
	     zmbuf != NULL; zmbuf = next) {
		next = TAILQ_NEXT(zmbuf, next);

		rte_pktmbuf_free(zmbuf->mbuf);
		TAILQ_REMOVE(&vq->zmbuf_list, zmbuf, next);
	}

	rte_free(vq->zmbufs);
}

/*
 * when virtio is stopped, qemu will send us the GET_VRING_BASE message.
 */
static int
vhost_user_get_vring_base(struct virtio_net **pdev,
			struct VhostUserMsg *msg,
			int main_fd __rte_unused)
{
	struct virtio_net *dev = *pdev;
	struct vhost_virtqueue *vq = dev->virtqueue[msg->payload.state.index];

	/* We have to stop the queue (virtio) if it is running. */
	vhost_destroy_device_notify(dev);

	dev->flags &= ~VIRTIO_DEV_READY;
	dev->flags &= ~VIRTIO_DEV_VDPA_CONFIGURED;

	/* Here we are safe to get the last avail index */
	msg->payload.state.num = vq->last_avail_idx;

	RTE_LOG(INFO, VHOST_CONFIG,
		"vring base idx:%d file:%d\n", msg->payload.state.index,
		msg->payload.state.num);
	/*
	 * Based on current qemu vhost-user implementation, this message is
	 * sent and only sent in vhost_vring_stop.
	 * TODO: cleanup the vring, it isn't usable since here.
	 */
	if (vq->kickfd >= 0)
		close(vq->kickfd);

	vq->kickfd = VIRTIO_UNINITIALIZED_EVENTFD;

	if (vq->callfd >= 0)
		close(vq->callfd);

	vq->callfd = VIRTIO_UNINITIALIZED_EVENTFD;

	if (dev->dequeue_zero_copy)
		free_zmbufs(vq);
	if (vq_is_packed(dev)) {
		rte_free(vq->shadow_used_packed);
		vq->shadow_used_packed = NULL;
	} else {
		rte_free(vq->shadow_used_split);
		vq->shadow_used_split = NULL;
	}

	rte_free(vq->batch_copy_elems);
	vq->batch_copy_elems = NULL;

	msg->size = sizeof(msg->payload.state);
	msg->fd_num = 0;

	return VH_RESULT_REPLY;
}

/*
 * when virtio queues are ready to work, qemu will send us to
 * enable the virtio queue pair.
 */
static int
vhost_user_set_vring_enable(struct virtio_net **pdev,
			struct VhostUserMsg *msg,
			int main_fd __rte_unused)
{
	struct virtio_net *dev = *pdev;
	int enable = (int)msg->payload.state.num;
	int index = (int)msg->payload.state.index;
	struct rte_vdpa_device *vdpa_dev;
	int did = -1;

	RTE_LOG(INFO, VHOST_CONFIG,
		"set queue enable: %d to qp idx: %d\n",
		enable, index);

	did = dev->vdpa_dev_id;
	vdpa_dev = rte_vdpa_get_device(did);
	if (vdpa_dev && vdpa_dev->ops->set_vring_state)
		vdpa_dev->ops->set_vring_state(dev->vid, index, enable);

	if (dev->notify_ops->vring_state_changed)
		dev->notify_ops->vring_state_changed(dev->vid,
				index, enable);

	dev->virtqueue[index]->enabled = enable;

	return VH_RESULT_OK;
}

static int
vhost_user_get_protocol_features(struct virtio_net **pdev,
			struct VhostUserMsg *msg,
			int main_fd __rte_unused)
{
	struct virtio_net *dev = *pdev;
	uint64_t features, protocol_features;

	rte_vhost_driver_get_features(dev->ifname, &features);
	rte_vhost_driver_get_protocol_features(dev->ifname, &protocol_features);

	/*
	 * REPLY_ACK protocol feature is only mandatory for now
	 * for IOMMU feature. If IOMMU is explicitly disabled by the
	 * application, disable also REPLY_ACK feature for older buggy
	 * Qemu versions (from v2.7.0 to v2.9.0).
	 */
	if (!(features & (1ULL << VIRTIO_F_IOMMU_PLATFORM)))
		protocol_features &= ~(1ULL << VHOST_USER_PROTOCOL_F_REPLY_ACK);

	msg->payload.u64 = protocol_features;
	msg->size = sizeof(msg->payload.u64);
	msg->fd_num = 0;

	return VH_RESULT_REPLY;
}

static int
vhost_user_set_protocol_features(struct virtio_net **pdev,
			struct VhostUserMsg *msg,
			int main_fd __rte_unused)
{
	struct virtio_net *dev = *pdev;
	uint64_t protocol_features = msg->payload.u64;
	uint64_t slave_protocol_features = 0;

	rte_vhost_driver_get_protocol_features(dev->ifname,
			&slave_protocol_features);
	if (protocol_features & ~slave_protocol_features) {
		RTE_LOG(ERR, VHOST_CONFIG,
			"(%d) received invalid protocol features.\n",
			dev->vid);
		return VH_RESULT_ERR;
	}

	dev->protocol_features = protocol_features;

	return VH_RESULT_OK;
}

static int
vhost_user_set_log_base(struct virtio_net **pdev, struct VhostUserMsg *msg,
			int main_fd __rte_unused)
{
	struct virtio_net *dev = *pdev;
	int fd = msg->fds[0];
	uint64_t size, off;
	void *addr;

	if (fd < 0) {
		RTE_LOG(ERR, VHOST_CONFIG, "invalid log fd: %d\n", fd);
		return VH_RESULT_ERR;
	}

	if (msg->size != sizeof(VhostUserLog)) {
		RTE_LOG(ERR, VHOST_CONFIG,
			"invalid log base msg size: %"PRId32" != %d\n",
			msg->size, (int)sizeof(VhostUserLog));
		return VH_RESULT_ERR;
	}

	size = msg->payload.log.mmap_size;
	off  = msg->payload.log.mmap_offset;

	/* Don't allow mmap_offset to point outside the mmap region */
	if (off > size) {
		RTE_LOG(ERR, VHOST_CONFIG,
			"log offset %#"PRIx64" exceeds log size %#"PRIx64"\n",
			off, size);
		return VH_RESULT_ERR;
	}

	RTE_LOG(INFO, VHOST_CONFIG,
		"log mmap size: %"PRId64", offset: %"PRId64"\n",
		size, off);

	/*
	 * mmap from 0 to workaround a hugepage mmap bug: mmap will
	 * fail when offset is not page size aligned.
	 */
	addr = mmap(0, size + off, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
	close(fd);
	if (addr == MAP_FAILED) {
		RTE_LOG(ERR, VHOST_CONFIG, "mmap log base failed!\n");
		return VH_RESULT_ERR;
	}

	/*
	 * Free previously mapped log memory on occasionally
	 * multiple VHOST_USER_SET_LOG_BASE.
	 */
	if (dev->log_addr) {
		munmap((void *)(uintptr_t)dev->log_addr, dev->log_size);
	}
	dev->log_addr = (uint64_t)(uintptr_t)addr;
	dev->log_base = dev->log_addr + off;
	dev->log_size = size;

	/*
	 * The spec is not clear about it (yet), but QEMU doesn't expect
	 * any payload in the reply.
	 */
	msg->size = 0;
	msg->fd_num = 0;

	return VH_RESULT_REPLY;
}

static int vhost_user_set_log_fd(struct virtio_net **pdev __rte_unused,
			struct VhostUserMsg *msg,
			int main_fd __rte_unused)
{
	close(msg->fds[0]);
	RTE_LOG(INFO, VHOST_CONFIG, "not implemented.\n");

	return VH_RESULT_OK;
}

/*
 * An rarp packet is constructed and broadcasted to notify switches about
 * the new location of the migrated VM, so that packets from outside will
 * not be lost after migration.
 *
 * However, we don't actually "send" a rarp packet here, instead, we set
 * a flag 'broadcast_rarp' to let rte_vhost_dequeue_burst() inject it.
 */
static int
vhost_user_send_rarp(struct virtio_net **pdev, struct VhostUserMsg *msg,
			int main_fd __rte_unused)
{
	struct virtio_net *dev = *pdev;
	uint8_t *mac = (uint8_t *)&msg->payload.u64;
	struct rte_vdpa_device *vdpa_dev;
	int did = -1;

	RTE_LOG(DEBUG, VHOST_CONFIG,
		":: mac: %02x:%02x:%02x:%02x:%02x:%02x\n",
		mac[0], mac[1], mac[2], mac[3], mac[4], mac[5]);
	memcpy(dev->mac.addr_bytes, mac, 6);

	/*
	 * Set the flag to inject a RARP broadcast packet at
	 * rte_vhost_dequeue_burst().
	 *
	 * rte_smp_wmb() is for making sure the mac is copied
	 * before the flag is set.
	 */
	rte_smp_wmb();
	rte_atomic16_set(&dev->broadcast_rarp, 1);
	did = dev->vdpa_dev_id;
	vdpa_dev = rte_vdpa_get_device(did);
	if (vdpa_dev && vdpa_dev->ops->migration_done)
		vdpa_dev->ops->migration_done(dev->vid);

	return VH_RESULT_OK;
}

static int
vhost_user_net_set_mtu(struct virtio_net **pdev, struct VhostUserMsg *msg,
			int main_fd __rte_unused)
{
	struct virtio_net *dev = *pdev;
	if (msg->payload.u64 < VIRTIO_MIN_MTU ||
			msg->payload.u64 > VIRTIO_MAX_MTU) {
		RTE_LOG(ERR, VHOST_CONFIG, "Invalid MTU size (%"PRIu64")\n",
				msg->payload.u64);

		return VH_RESULT_ERR;
	}

	dev->mtu = msg->payload.u64;

	return VH_RESULT_OK;
}

static int
vhost_user_set_req_fd(struct virtio_net **pdev, struct VhostUserMsg *msg,
			int main_fd __rte_unused)
{
	struct virtio_net *dev = *pdev;
	int fd = msg->fds[0];

	if (fd < 0) {
		RTE_LOG(ERR, VHOST_CONFIG,
				"Invalid file descriptor for slave channel (%d)\n",
				fd);
		return VH_RESULT_ERR;
	}

	dev->slave_req_fd = fd;

	return VH_RESULT_OK;
}

static int
is_vring_iotlb_update(struct vhost_virtqueue *vq, struct vhost_iotlb_msg *imsg)
{
	struct vhost_vring_addr *ra;
	uint64_t start, end;

	start = imsg->iova;
	end = start + imsg->size;

	ra = &vq->ring_addrs;
	if (ra->desc_user_addr >= start && ra->desc_user_addr < end)
		return 1;
	if (ra->avail_user_addr >= start && ra->avail_user_addr < end)
		return 1;
	if (ra->used_user_addr >= start && ra->used_user_addr < end)
		return 1;

	return 0;
}

static int
is_vring_iotlb_invalidate(struct vhost_virtqueue *vq,
				struct vhost_iotlb_msg *imsg)
{
	uint64_t istart, iend, vstart, vend;

	istart = imsg->iova;
	iend = istart + imsg->size - 1;

	vstart = (uintptr_t)vq->desc;
	vend = vstart + sizeof(struct vring_desc) * vq->size - 1;
	if (vstart <= iend && istart <= vend)
		return 1;

	vstart = (uintptr_t)vq->avail;
	vend = vstart + sizeof(struct vring_avail);
	vend += sizeof(uint16_t) * vq->size - 1;
	if (vstart <= iend && istart <= vend)
		return 1;

	vstart = (uintptr_t)vq->used;
	vend = vstart + sizeof(struct vring_used);
	vend += sizeof(struct vring_used_elem) * vq->size - 1;
	if (vstart <= iend && istart <= vend)
		return 1;

	return 0;
}

static int
vhost_user_iotlb_msg(struct virtio_net **pdev, struct VhostUserMsg *msg,
			int main_fd __rte_unused)
{
	struct virtio_net *dev = *pdev;
	struct vhost_iotlb_msg *imsg = &msg->payload.iotlb;
	uint16_t i;
	uint64_t vva, len;

	switch (imsg->type) {
	case VHOST_IOTLB_UPDATE:
		len = imsg->size;
		vva = qva_to_vva(dev, imsg->uaddr, &len);
		if (!vva)
			return VH_RESULT_ERR;

		for (i = 0; i < dev->nr_vring; i++) {
			struct vhost_virtqueue *vq = dev->virtqueue[i];

			vhost_user_iotlb_cache_insert(vq, imsg->iova, vva,
					len, imsg->perm);

			if (is_vring_iotlb_update(vq, imsg))
				*pdev = dev = translate_ring_addresses(dev, i);
		}
		break;
	case VHOST_IOTLB_INVALIDATE:
		for (i = 0; i < dev->nr_vring; i++) {
			struct vhost_virtqueue *vq = dev->virtqueue[i];

			vhost_user_iotlb_cache_remove(vq, imsg->iova,
					imsg->size);

			if (is_vring_iotlb_invalidate(vq, imsg))
				vring_invalidate(dev, vq);
		}
		break;
	default:
		RTE_LOG(ERR, VHOST_CONFIG, "Invalid IOTLB message type (%d)\n",
				imsg->type);
		return VH_RESULT_ERR;
	}

	return VH_RESULT_OK;
}

static int
vhost_user_set_postcopy_advise(struct virtio_net **pdev,
			struct VhostUserMsg *msg,
			int main_fd __rte_unused)
{
	struct virtio_net *dev = *pdev;
#ifdef RTE_LIBRTE_VHOST_POSTCOPY
	struct uffdio_api api_struct;

	dev->postcopy_ufd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);

	if (dev->postcopy_ufd == -1) {
		RTE_LOG(ERR, VHOST_CONFIG, "Userfaultfd not available: %s\n",
			strerror(errno));
		return VH_RESULT_ERR;
	}
	api_struct.api = UFFD_API;
	api_struct.features = 0;
	if (ioctl(dev->postcopy_ufd, UFFDIO_API, &api_struct)) {
		RTE_LOG(ERR, VHOST_CONFIG, "UFFDIO_API ioctl failure: %s\n",
			strerror(errno));
		close(dev->postcopy_ufd);
		dev->postcopy_ufd = -1;
		return VH_RESULT_ERR;
	}
	msg->fds[0] = dev->postcopy_ufd;
	msg->fd_num = 1;

	return VH_RESULT_REPLY;
#else
	dev->postcopy_ufd = -1;
	msg->fd_num = 0;

	return VH_RESULT_ERR;
#endif
}

static int
vhost_user_set_postcopy_listen(struct virtio_net **pdev,
			struct VhostUserMsg *msg __rte_unused,
			int main_fd __rte_unused)
{
	struct virtio_net *dev = *pdev;

	if (dev->mem && dev->mem->nregions) {
		RTE_LOG(ERR, VHOST_CONFIG,
			"Regions already registered at postcopy-listen\n");
		return VH_RESULT_ERR;
	}
	dev->postcopy_listening = 1;

	return VH_RESULT_OK;
}

static int
vhost_user_postcopy_end(struct virtio_net **pdev, struct VhostUserMsg *msg,
			int main_fd __rte_unused)
{
	struct virtio_net *dev = *pdev;

	dev->postcopy_listening = 0;
	if (dev->postcopy_ufd >= 0) {
		close(dev->postcopy_ufd);
		dev->postcopy_ufd = -1;
	}

	msg->payload.u64 = 0;
	msg->size = sizeof(msg->payload.u64);
	msg->fd_num = 0;

	return VH_RESULT_REPLY;
}

typedef int (*vhost_message_handler_t)(struct virtio_net **pdev,
					struct VhostUserMsg *msg,
					int main_fd);
static vhost_message_handler_t vhost_message_handlers[VHOST_USER_MAX] = {
	[VHOST_USER_NONE] = NULL,
	[VHOST_USER_GET_FEATURES] = vhost_user_get_features,
	[VHOST_USER_SET_FEATURES] = vhost_user_set_features,
	[VHOST_USER_SET_OWNER] = vhost_user_set_owner,
	[VHOST_USER_RESET_OWNER] = vhost_user_reset_owner,
	[VHOST_USER_SET_MEM_TABLE] = vhost_user_set_mem_table,
	[VHOST_USER_SET_LOG_BASE] = vhost_user_set_log_base,
	[VHOST_USER_SET_LOG_FD] = vhost_user_set_log_fd,
	[VHOST_USER_SET_VRING_NUM] = vhost_user_set_vring_num,
	[VHOST_USER_SET_VRING_ADDR] = vhost_user_set_vring_addr,
	[VHOST_USER_SET_VRING_BASE] = vhost_user_set_vring_base,
	[VHOST_USER_GET_VRING_BASE] = vhost_user_get_vring_base,
	[VHOST_USER_SET_VRING_KICK] = vhost_user_set_vring_kick,
	[VHOST_USER_SET_VRING_CALL] = vhost_user_set_vring_call,
	[VHOST_USER_SET_VRING_ERR] = vhost_user_set_vring_err,
	[VHOST_USER_GET_PROTOCOL_FEATURES] = vhost_user_get_protocol_features,
	[VHOST_USER_SET_PROTOCOL_FEATURES] = vhost_user_set_protocol_features,
	[VHOST_USER_GET_QUEUE_NUM] = vhost_user_get_queue_num,
	[VHOST_USER_SET_VRING_ENABLE] = vhost_user_set_vring_enable,
	[VHOST_USER_SEND_RARP] = vhost_user_send_rarp,
	[VHOST_USER_NET_SET_MTU] = vhost_user_net_set_mtu,
	[VHOST_USER_SET_SLAVE_REQ_FD] = vhost_user_set_req_fd,
	[VHOST_USER_IOTLB_MSG] = vhost_user_iotlb_msg,
	[VHOST_USER_POSTCOPY_ADVISE] = vhost_user_set_postcopy_advise,
	[VHOST_USER_POSTCOPY_LISTEN] = vhost_user_set_postcopy_listen,
	[VHOST_USER_POSTCOPY_END] = vhost_user_postcopy_end,
};


/* return bytes# of read on success or negative val on failure. */
static int
read_vhost_message(int sockfd, struct VhostUserMsg *msg)
{
	int ret;

	ret = read_fd_message(sockfd, (char *)msg, VHOST_USER_HDR_SIZE,
		msg->fds, VHOST_MEMORY_MAX_NREGIONS, &msg->fd_num);
	if (ret <= 0)
		return ret;

	if (msg && msg->size) {
		if (msg->size > sizeof(msg->payload)) {
			RTE_LOG(ERR, VHOST_CONFIG,
				"invalid msg size: %d\n", msg->size);
			return -1;
		}
		ret = read(sockfd, &msg->payload, msg->size);
		if (ret <= 0)
			return ret;
		if (ret != (int)msg->size) {
			RTE_LOG(ERR, VHOST_CONFIG,
				"read control message failed\n");
			return -1;
		}
	}

	return ret;
}

static int
send_vhost_message(int sockfd, struct VhostUserMsg *msg)
{
	if (!msg)
		return 0;

	return send_fd_message(sockfd, (char *)msg,
		VHOST_USER_HDR_SIZE + msg->size, msg->fds, msg->fd_num);
}

static int
send_vhost_reply(int sockfd, struct VhostUserMsg *msg)
{
	if (!msg)
		return 0;

	msg->flags &= ~VHOST_USER_VERSION_MASK;
	msg->flags &= ~VHOST_USER_NEED_REPLY;
	msg->flags |= VHOST_USER_VERSION;
	msg->flags |= VHOST_USER_REPLY_MASK;

	return send_vhost_message(sockfd, msg);
}

static int
send_vhost_slave_message(struct virtio_net *dev, struct VhostUserMsg *msg)
{
	int ret;

	if (msg->flags & VHOST_USER_NEED_REPLY)
		rte_spinlock_lock(&dev->slave_req_lock);

	ret = send_vhost_message(dev->slave_req_fd, msg);
	if (ret < 0 && (msg->flags & VHOST_USER_NEED_REPLY))
		rte_spinlock_unlock(&dev->slave_req_lock);

	return ret;
}

/*
 * Allocate a queue pair if it hasn't been allocated yet
 */
static int
vhost_user_check_and_alloc_queue_pair(struct virtio_net *dev,
			struct VhostUserMsg *msg)
{
	uint16_t vring_idx;

	switch (msg->request.master) {
	case VHOST_USER_SET_VRING_KICK:
	case VHOST_USER_SET_VRING_CALL:
	case VHOST_USER_SET_VRING_ERR:
		vring_idx = msg->payload.u64 & VHOST_USER_VRING_IDX_MASK;
		break;
	case VHOST_USER_SET_VRING_NUM:
	case VHOST_USER_SET_VRING_BASE:
	case VHOST_USER_SET_VRING_ENABLE:
		vring_idx = msg->payload.state.index;
		break;
	case VHOST_USER_SET_VRING_ADDR:
		vring_idx = msg->payload.addr.index;
		break;
	default:
		return 0;
	}

	if (vring_idx >= VHOST_MAX_VRING) {
		RTE_LOG(ERR, VHOST_CONFIG,
			"invalid vring index: %u\n", vring_idx);
		return -1;
	}

	if (dev->virtqueue[vring_idx])
		return 0;

	return alloc_vring_queue(dev, vring_idx);
}

static void
vhost_user_lock_all_queue_pairs(struct virtio_net *dev)
{
	unsigned int i = 0;
	unsigned int vq_num = 0;

	while (vq_num < dev->nr_vring) {
		struct vhost_virtqueue *vq = dev->virtqueue[i];

		if (vq) {
			rte_spinlock_lock(&vq->access_lock);
			vq_num++;
		}
		i++;
	}
}

static void
vhost_user_unlock_all_queue_pairs(struct virtio_net *dev)
{
	unsigned int i = 0;
	unsigned int vq_num = 0;

	while (vq_num < dev->nr_vring) {
		struct vhost_virtqueue *vq = dev->virtqueue[i];

		if (vq) {
			rte_spinlock_unlock(&vq->access_lock);
			vq_num++;
		}
		i++;
	}
}

int
vhost_user_msg_handler(int vid, int fd)
{
	struct virtio_net *dev;
	struct VhostUserMsg msg;
	struct rte_vdpa_device *vdpa_dev;
	int did = -1;
	int ret;
	int unlock_required = 0;
	uint32_t skip_master = 0;
	int request;

	dev = get_device(vid);
	if (dev == NULL)
		return -1;

	if (!dev->notify_ops) {
		dev->notify_ops = vhost_driver_callback_get(dev->ifname);
		if (!dev->notify_ops) {
			RTE_LOG(ERR, VHOST_CONFIG,
				"failed to get callback ops for driver %s\n",
				dev->ifname);
			return -1;
		}
	}

	ret = read_vhost_message(fd, &msg);
	if (ret <= 0 || msg.request.master >= VHOST_USER_MAX) {
		if (ret < 0)
			RTE_LOG(ERR, VHOST_CONFIG,
				"vhost read message failed\n");
		else if (ret == 0)
			RTE_LOG(INFO, VHOST_CONFIG,
				"vhost peer closed\n");
		else
			RTE_LOG(ERR, VHOST_CONFIG,
				"vhost read incorrect message\n");

		return -1;
	}

	ret = 0;
	if (msg.request.master != VHOST_USER_IOTLB_MSG)
		RTE_LOG(INFO, VHOST_CONFIG, "read message %s\n",
			vhost_message_str[msg.request.master]);
	else
		RTE_LOG(DEBUG, VHOST_CONFIG, "read message %s\n",
			vhost_message_str[msg.request.master]);

	ret = vhost_user_check_and_alloc_queue_pair(dev, &msg);
	if (ret < 0) {
		RTE_LOG(ERR, VHOST_CONFIG,
			"failed to alloc queue\n");
		return -1;
	}

	/*
	 * Note: we don't lock all queues on VHOST_USER_GET_VRING_BASE
	 * and VHOST_USER_RESET_OWNER, since it is sent when virtio stops
	 * and device is destroyed. destroy_device waits for queues to be
	 * inactive, so it is safe. Otherwise taking the access_lock
	 * would cause a dead lock.
	 */
	switch (msg.request.master) {
	case VHOST_USER_SET_FEATURES:
	case VHOST_USER_SET_PROTOCOL_FEATURES:
	case VHOST_USER_SET_OWNER:
	case VHOST_USER_SET_MEM_TABLE:
	case VHOST_USER_SET_LOG_BASE:
	case VHOST_USER_SET_LOG_FD:
	case VHOST_USER_SET_VRING_NUM:
	case VHOST_USER_SET_VRING_ADDR:
	case VHOST_USER_SET_VRING_BASE:
	case VHOST_USER_SET_VRING_KICK:
	case VHOST_USER_SET_VRING_CALL:
	case VHOST_USER_SET_VRING_ERR:
	case VHOST_USER_SET_VRING_ENABLE:
	case VHOST_USER_SEND_RARP:
	case VHOST_USER_NET_SET_MTU:
	case VHOST_USER_SET_SLAVE_REQ_FD:
		vhost_user_lock_all_queue_pairs(dev);
		unlock_required = 1;
		break;
	default:
		break;

	}

	if (dev->extern_ops.pre_msg_handle) {
		ret = (*dev->extern_ops.pre_msg_handle)(dev->vid,
				(void *)&msg, &skip_master);
		if (ret == VH_RESULT_ERR)
			goto skip_to_reply;
		else if (ret == VH_RESULT_REPLY)
			send_vhost_reply(fd, &msg);

		if (skip_master)
			goto skip_to_post_handle;
	}

	request = msg.request.master;
	if (request > VHOST_USER_NONE && request < VHOST_USER_MAX) {
		if (!vhost_message_handlers[request])
			goto skip_to_post_handle;
		ret = vhost_message_handlers[request](&dev, &msg, fd);

		switch (ret) {
		case VH_RESULT_ERR:
			RTE_LOG(ERR, VHOST_CONFIG,
				"Processing %s failed.\n",
				vhost_message_str[request]);
			break;
		case VH_RESULT_OK:
			RTE_LOG(DEBUG, VHOST_CONFIG,
				"Processing %s succeeded.\n",
				vhost_message_str[request]);
			break;
		case VH_RESULT_REPLY:
			RTE_LOG(DEBUG, VHOST_CONFIG,
				"Processing %s succeeded and needs reply.\n",
				vhost_message_str[request]);
			send_vhost_reply(fd, &msg);
			break;
		}
	} else {
		RTE_LOG(ERR, VHOST_CONFIG,
			"Requested invalid message type %d.\n", request);
		ret = VH_RESULT_ERR;
	}

skip_to_post_handle:
	if (ret != VH_RESULT_ERR && dev->extern_ops.post_msg_handle) {
		ret = (*dev->extern_ops.post_msg_handle)(
				dev->vid, (void *)&msg);
		if (ret == VH_RESULT_ERR)
			goto skip_to_reply;
		else if (ret == VH_RESULT_REPLY)
			send_vhost_reply(fd, &msg);
	}

skip_to_reply:
	if (unlock_required)
		vhost_user_unlock_all_queue_pairs(dev);

	/*
	 * If the request required a reply that was already sent,
	 * this optional reply-ack won't be sent as the
	 * VHOST_USER_NEED_REPLY was cleared in send_vhost_reply().
	 */
	if (msg.flags & VHOST_USER_NEED_REPLY) {
		msg.payload.u64 = ret == VH_RESULT_ERR;
		msg.size = sizeof(msg.payload.u64);
		msg.fd_num = 0;
		send_vhost_reply(fd, &msg);
	} else if (ret == VH_RESULT_ERR) {
		RTE_LOG(ERR, VHOST_CONFIG,
			"vhost message handling failed.\n");
		return -1;
	}

	if (!(dev->flags & VIRTIO_DEV_RUNNING) && virtio_is_ready(dev)) {
		dev->flags |= VIRTIO_DEV_READY;

		if (!(dev->flags & VIRTIO_DEV_RUNNING)) {
			if (dev->dequeue_zero_copy) {
				RTE_LOG(INFO, VHOST_CONFIG,
						"dequeue zero copy is enabled\n");
			}

			if (dev->notify_ops->new_device(dev->vid) == 0)
				dev->flags |= VIRTIO_DEV_RUNNING;
		}
	}

	did = dev->vdpa_dev_id;
	vdpa_dev = rte_vdpa_get_device(did);
	if (vdpa_dev && virtio_is_ready(dev) &&
			!(dev->flags & VIRTIO_DEV_VDPA_CONFIGURED) &&
			msg.request.master == VHOST_USER_SET_VRING_ENABLE) {
		if (vdpa_dev->ops->dev_conf)
			vdpa_dev->ops->dev_conf(dev->vid);
		dev->flags |= VIRTIO_DEV_VDPA_CONFIGURED;
		if (vhost_user_host_notifier_ctrl(dev->vid, true) != 0) {
			RTE_LOG(INFO, VHOST_CONFIG,
				"(%d) software relay is used for vDPA, performance may be low.\n",
				dev->vid);
		}
	}

	return 0;
}

static int process_slave_message_reply(struct virtio_net *dev,
				       const struct VhostUserMsg *msg)
{
	struct VhostUserMsg msg_reply;
	int ret;

	if ((msg->flags & VHOST_USER_NEED_REPLY) == 0)
		return 0;

	if (read_vhost_message(dev->slave_req_fd, &msg_reply) < 0) {
		ret = -1;
		goto out;
	}

	if (msg_reply.request.slave != msg->request.slave) {
		RTE_LOG(ERR, VHOST_CONFIG,
			"Received unexpected msg type (%u), expected %u\n",
			msg_reply.request.slave, msg->request.slave);
		ret = -1;
		goto out;
	}

	ret = msg_reply.payload.u64 ? -1 : 0;

out:
	rte_spinlock_unlock(&dev->slave_req_lock);
	return ret;
}

int
vhost_user_iotlb_miss(struct virtio_net *dev, uint64_t iova, uint8_t perm)
{
	int ret;
	struct VhostUserMsg msg = {
		.request.slave = VHOST_USER_SLAVE_IOTLB_MSG,
		.flags = VHOST_USER_VERSION,
		.size = sizeof(msg.payload.iotlb),
		.payload.iotlb = {
			.iova = iova,
			.perm = perm,
			.type = VHOST_IOTLB_MISS,
		},
	};

	ret = send_vhost_message(dev->slave_req_fd, &msg);
	if (ret < 0) {
		RTE_LOG(ERR, VHOST_CONFIG,
				"Failed to send IOTLB miss message (%d)\n",
				ret);
		return ret;
	}

	return 0;
}

static int vhost_user_slave_set_vring_host_notifier(struct virtio_net *dev,
						    int index, int fd,
						    uint64_t offset,
						    uint64_t size)
{
	int ret;
	struct VhostUserMsg msg = {
		.request.slave = VHOST_USER_SLAVE_VRING_HOST_NOTIFIER_MSG,
		.flags = VHOST_USER_VERSION | VHOST_USER_NEED_REPLY,
		.size = sizeof(msg.payload.area),
		.payload.area = {
			.u64 = index & VHOST_USER_VRING_IDX_MASK,
			.size = size,
			.offset = offset,
		},
	};

	if (fd < 0)
		msg.payload.area.u64 |= VHOST_USER_VRING_NOFD_MASK;
	else {
		msg.fds[0] = fd;
		msg.fd_num = 1;
	}

	ret = send_vhost_slave_message(dev, &msg);
	if (ret < 0) {
		RTE_LOG(ERR, VHOST_CONFIG,
			"Failed to set host notifier (%d)\n", ret);
		return ret;
	}

	return process_slave_message_reply(dev, &msg);
}

int vhost_user_host_notifier_ctrl(int vid, bool enable)
{
	struct virtio_net *dev;
	struct rte_vdpa_device *vdpa_dev;
	int vfio_device_fd, did, ret = 0;
	uint64_t offset, size;
	unsigned int i;

	dev = get_device(vid);
	if (!dev)
		return -ENODEV;

	did = dev->vdpa_dev_id;
	if (did < 0)
		return -EINVAL;

	if (!(dev->features & (1ULL << VIRTIO_F_VERSION_1)) ||
	    !(dev->features & (1ULL << VHOST_USER_F_PROTOCOL_FEATURES)) ||
	    !(dev->protocol_features &
			(1ULL << VHOST_USER_PROTOCOL_F_SLAVE_REQ)) ||
	    !(dev->protocol_features &
			(1ULL << VHOST_USER_PROTOCOL_F_SLAVE_SEND_FD)) ||
	    !(dev->protocol_features &
			(1ULL << VHOST_USER_PROTOCOL_F_HOST_NOTIFIER)))
		return -ENOTSUP;

	vdpa_dev = rte_vdpa_get_device(did);
	if (!vdpa_dev)
		return -ENODEV;

	RTE_FUNC_PTR_OR_ERR_RET(vdpa_dev->ops->get_vfio_device_fd, -ENOTSUP);
	RTE_FUNC_PTR_OR_ERR_RET(vdpa_dev->ops->get_notify_area, -ENOTSUP);

	vfio_device_fd = vdpa_dev->ops->get_vfio_device_fd(vid);
	if (vfio_device_fd < 0)
		return -ENOTSUP;

	if (enable) {
		for (i = 0; i < dev->nr_vring; i++) {
			if (vdpa_dev->ops->get_notify_area(vid, i, &offset,
					&size) < 0) {
				ret = -ENOTSUP;
				goto disable;
			}

			if (vhost_user_slave_set_vring_host_notifier(dev, i,
					vfio_device_fd, offset, size) < 0) {
				ret = -EFAULT;
				goto disable;
			}
		}
	} else {
disable:
		for (i = 0; i < dev->nr_vring; i++) {
			vhost_user_slave_set_vring_host_notifier(dev, i, -1,
					0, 0);
		}
	}

	return ret;
}