aboutsummaryrefslogtreecommitdiff
path: root/block/gluster.c
blob: 1a22f2982d33c52df044230fa1784eef4eaa77cd (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
/*
 * GlusterFS backend for QEMU
 *
 * Copyright (C) 2012 Bharata B Rao <bharata@linux.vnet.ibm.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2 or later.
 * See the COPYING file in the top-level directory.
 *
 */
#include "qemu/osdep.h"
#include <glusterfs/api/glfs.h>
#include "block/block_int.h"
#include "qapi/error.h"
#include "qapi/qmp/qerror.h"
#include "qemu/uri.h"
#include "qemu/error-report.h"
#include "qemu/cutils.h"

#define GLUSTER_OPT_FILENAME        "filename"
#define GLUSTER_OPT_VOLUME          "volume"
#define GLUSTER_OPT_PATH            "path"
#define GLUSTER_OPT_TYPE            "type"
#define GLUSTER_OPT_SERVER_PATTERN  "server."
#define GLUSTER_OPT_HOST            "host"
#define GLUSTER_OPT_PORT            "port"
#define GLUSTER_OPT_TO              "to"
#define GLUSTER_OPT_IPV4            "ipv4"
#define GLUSTER_OPT_IPV6            "ipv6"
#define GLUSTER_OPT_SOCKET          "socket"
#define GLUSTER_OPT_DEBUG           "debug"
#define GLUSTER_DEFAULT_PORT        24007
#define GLUSTER_DEBUG_DEFAULT       4
#define GLUSTER_DEBUG_MAX           9
#define GLUSTER_OPT_LOGFILE         "logfile"
#define GLUSTER_LOGFILE_DEFAULT     "-" /* handled in libgfapi as /dev/stderr */

#define GERR_INDEX_HINT "hint: check in 'server' array index '%d'\n"

typedef struct GlusterAIOCB {
    int64_t size;
    int ret;
    Coroutine *coroutine;
    AioContext *aio_context;
} GlusterAIOCB;

typedef struct BDRVGlusterState {
    struct glfs *glfs;
    struct glfs_fd *fd;
    char *logfile;
    bool supports_seek_data;
    int debug;
} BDRVGlusterState;

typedef struct BDRVGlusterReopenState {
    struct glfs *glfs;
    struct glfs_fd *fd;
} BDRVGlusterReopenState;


typedef struct GlfsPreopened {
    char *volume;
    glfs_t *fs;
    int ref;
} GlfsPreopened;

typedef struct ListElement {
    QLIST_ENTRY(ListElement) list;
    GlfsPreopened saved;
} ListElement;

static QLIST_HEAD(glfs_list, ListElement) glfs_list;

static QemuOptsList qemu_gluster_create_opts = {
    .name = "qemu-gluster-create-opts",
    .head = QTAILQ_HEAD_INITIALIZER(qemu_gluster_create_opts.head),
    .desc = {
        {
            .name = BLOCK_OPT_SIZE,
            .type = QEMU_OPT_SIZE,
            .help = "Virtual disk size"
        },
        {
            .name = BLOCK_OPT_PREALLOC,
            .type = QEMU_OPT_STRING,
            .help = "Preallocation mode (allowed values: off, full)"
        },
        {
            .name = GLUSTER_OPT_DEBUG,
            .type = QEMU_OPT_NUMBER,
            .help = "Gluster log level, valid range is 0-9",
        },
        {
            .name = GLUSTER_OPT_LOGFILE,
            .type = QEMU_OPT_STRING,
            .help = "Logfile path of libgfapi",
        },
        { /* end of list */ }
    }
};

static QemuOptsList runtime_opts = {
    .name = "gluster",
    .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
    .desc = {
        {
            .name = GLUSTER_OPT_FILENAME,
            .type = QEMU_OPT_STRING,
            .help = "URL to the gluster image",
        },
        {
            .name = GLUSTER_OPT_DEBUG,
            .type = QEMU_OPT_NUMBER,
            .help = "Gluster log level, valid range is 0-9",
        },
        {
            .name = GLUSTER_OPT_LOGFILE,
            .type = QEMU_OPT_STRING,
            .help = "Logfile path of libgfapi",
        },
        { /* end of list */ }
    },
};

static QemuOptsList runtime_json_opts = {
    .name = "gluster_json",
    .head = QTAILQ_HEAD_INITIALIZER(runtime_json_opts.head),
    .desc = {
        {
            .name = GLUSTER_OPT_VOLUME,
            .type = QEMU_OPT_STRING,
            .help = "name of gluster volume where VM image resides",
        },
        {
            .name = GLUSTER_OPT_PATH,
            .type = QEMU_OPT_STRING,
            .help = "absolute path to image file in gluster volume",
        },
        {
            .name = GLUSTER_OPT_DEBUG,
            .type = QEMU_OPT_NUMBER,
            .help = "Gluster log level, valid range is 0-9",
        },
        { /* end of list */ }
    },
};

static QemuOptsList runtime_type_opts = {
    .name = "gluster_type",
    .head = QTAILQ_HEAD_INITIALIZER(runtime_type_opts.head),
    .desc = {
        {
            .name = GLUSTER_OPT_TYPE,
            .type = QEMU_OPT_STRING,
            .help = "tcp|unix",
        },
        { /* end of list */ }
    },
};

static QemuOptsList runtime_unix_opts = {
    .name = "gluster_unix",
    .head = QTAILQ_HEAD_INITIALIZER(runtime_unix_opts.head),
    .desc = {
        {
            .name = GLUSTER_OPT_SOCKET,
            .type = QEMU_OPT_STRING,
            .help = "socket file path)",
        },
        { /* end of list */ }
    },
};

static QemuOptsList runtime_tcp_opts = {
    .name = "gluster_tcp",
    .head = QTAILQ_HEAD_INITIALIZER(runtime_tcp_opts.head),
    .desc = {
        {
            .name = GLUSTER_OPT_TYPE,
            .type = QEMU_OPT_STRING,
            .help = "tcp|unix",
        },
        {
            .name = GLUSTER_OPT_HOST,
            .type = QEMU_OPT_STRING,
            .help = "host address (hostname/ipv4/ipv6 addresses)",
        },
        {
            .name = GLUSTER_OPT_PORT,
            .type = QEMU_OPT_STRING,
            .help = "port number on which glusterd is listening (default 24007)",
        },
        {
            .name = "to",
            .type = QEMU_OPT_NUMBER,
            .help = "max port number, not supported by gluster",
        },
        {
            .name = "ipv4",
            .type = QEMU_OPT_BOOL,
            .help = "ipv4 bool value, not supported by gluster",
        },
        {
            .name = "ipv6",
            .type = QEMU_OPT_BOOL,
            .help = "ipv6 bool value, not supported by gluster",
        },
        { /* end of list */ }
    },
};

static void glfs_set_preopened(const char *volume, glfs_t *fs)
{
    ListElement *entry = NULL;

    entry = g_new(ListElement, 1);

    entry->saved.volume = g_strdup(volume);

    entry->saved.fs = fs;
    entry->saved.ref = 1;

    QLIST_INSERT_HEAD(&glfs_list, entry, list);
}

static glfs_t *glfs_find_preopened(const char *volume)
{
    ListElement *entry = NULL;

     QLIST_FOREACH(entry, &glfs_list, list) {
        if (strcmp(entry->saved.volume, volume) == 0) {
            entry->saved.ref++;
            return entry->saved.fs;
        }
     }

    return NULL;
}

static void glfs_clear_preopened(glfs_t *fs)
{
    ListElement *entry = NULL;
    ListElement *next;

    if (fs == NULL) {
        return;
    }

    QLIST_FOREACH_SAFE(entry, &glfs_list, list, next) {
        if (entry->saved.fs == fs) {
            if (--entry->saved.ref) {
                return;
            }

            QLIST_REMOVE(entry, list);

            glfs_fini(entry->saved.fs);
            g_free(entry->saved.volume);
            g_free(entry);
        }
    }
}

static int parse_volume_options(BlockdevOptionsGluster *gconf, char *path)
{
    char *p, *q;

    if (!path) {
        return -EINVAL;
    }

    /* volume */
    p = q = path + strspn(path, "/");
    p += strcspn(p, "/");
    if (*p == '\0') {
        return -EINVAL;
    }
    gconf->volume = g_strndup(q, p - q);

    /* path */
    p += strspn(p, "/");
    if (*p == '\0') {
        return -EINVAL;
    }
    gconf->path = g_strdup(p);
    return 0;
}

/*
 * file=gluster[+transport]://[host[:port]]/volume/path[?socket=...]
 *
 * 'gluster' is the protocol.
 *
 * 'transport' specifies the transport type used to connect to gluster
 * management daemon (glusterd). Valid transport types are
 * tcp or unix. If a transport type isn't specified, then tcp type is assumed.
 *
 * 'host' specifies the host where the volume file specification for
 * the given volume resides. This can be either hostname or ipv4 address.
 * If transport type is 'unix', then 'host' field should not be specified.
 * The 'socket' field needs to be populated with the path to unix domain
 * socket.
 *
 * 'port' is the port number on which glusterd is listening. This is optional
 * and if not specified, QEMU will send 0 which will make gluster to use the
 * default port. If the transport type is unix, then 'port' should not be
 * specified.
 *
 * 'volume' is the name of the gluster volume which contains the VM image.
 *
 * 'path' is the path to the actual VM image that resides on gluster volume.
 *
 * Examples:
 *
 * file=gluster://1.2.3.4/testvol/a.img
 * file=gluster+tcp://1.2.3.4/testvol/a.img
 * file=gluster+tcp://1.2.3.4:24007/testvol/dir/a.img
 * file=gluster+tcp://host.domain.com:24007/testvol/dir/a.img
 * file=gluster+unix:///testvol/dir/a.img?socket=/tmp/glusterd.socket
 */
static int qemu_gluster_parse_uri(BlockdevOptionsGluster *gconf,
                                  const char *filename)
{
    GlusterServer *gsconf;
    URI *uri;
    QueryParams *qp = NULL;
    bool is_unix = false;
    int ret = 0;

    uri = uri_parse(filename);
    if (!uri) {
        return -EINVAL;
    }

    gconf->server = g_new0(GlusterServerList, 1);
    gconf->server->value = gsconf = g_new0(GlusterServer, 1);

    /* transport */
    if (!uri->scheme || !strcmp(uri->scheme, "gluster")) {
        gsconf->type = GLUSTER_TRANSPORT_TCP;
    } else if (!strcmp(uri->scheme, "gluster+tcp")) {
        gsconf->type = GLUSTER_TRANSPORT_TCP;
    } else if (!strcmp(uri->scheme, "gluster+unix")) {
        gsconf->type = GLUSTER_TRANSPORT_UNIX;
        is_unix = true;
    } else if (!strcmp(uri->scheme, "gluster+rdma")) {
        gsconf->type = GLUSTER_TRANSPORT_TCP;
        error_report("Warning: rdma feature is not supported, falling "
                     "back to tcp");
    } else {
        ret = -EINVAL;
        goto out;
    }

    ret = parse_volume_options(gconf, uri->path);
    if (ret < 0) {
        goto out;
    }

    qp = query_params_parse(uri->query);
    if (qp->n > 1 || (is_unix && !qp->n) || (!is_unix && qp->n)) {
        ret = -EINVAL;
        goto out;
    }

    if (is_unix) {
        if (uri->server || uri->port) {
            ret = -EINVAL;
            goto out;
        }
        if (strcmp(qp->p[0].name, "socket")) {
            ret = -EINVAL;
            goto out;
        }
        gsconf->u.q_unix.path = g_strdup(qp->p[0].value);
    } else {
        gsconf->u.tcp.host = g_strdup(uri->server ? uri->server : "localhost");
        if (uri->port) {
            gsconf->u.tcp.port = g_strdup_printf("%d", uri->port);
        } else {
            gsconf->u.tcp.port = g_strdup_printf("%d", GLUSTER_DEFAULT_PORT);
        }
    }

out:
    if (qp) {
        query_params_free(qp);
    }
    uri_free(uri);
    return ret;
}

static struct glfs *qemu_gluster_glfs_init(BlockdevOptionsGluster *gconf,
                                           Error **errp)
{
    struct glfs *glfs;
    int ret;
    int old_errno;
    GlusterServerList *server;
    unsigned long long port;

    glfs = glfs_find_preopened(gconf->volume);
    if (glfs) {
        return glfs;
    }

    glfs = glfs_new(gconf->volume);
    if (!glfs) {
        goto out;
    }

    glfs_set_preopened(gconf->volume, glfs);

    for (server = gconf->server; server; server = server->next) {
        if (server->value->type  == GLUSTER_TRANSPORT_UNIX) {
            ret = glfs_set_volfile_server(glfs,
                                   GlusterTransport_lookup[server->value->type],
                                   server->value->u.q_unix.path, 0);
        } else {
            if (parse_uint_full(server->value->u.tcp.port, &port, 10) < 0 ||
                port > 65535) {
                error_setg(errp, "'%s' is not a valid port number",
                           server->value->u.tcp.port);
                errno = EINVAL;
                goto out;
            }
            ret = glfs_set_volfile_server(glfs,
                                   GlusterTransport_lookup[server->value->type],
                                   server->value->u.tcp.host,
                                   (int)port);
        }

        if (ret < 0) {
            goto out;
        }
    }

    ret = glfs_set_logging(glfs, gconf->logfile, gconf->debug);
    if (ret < 0) {
        goto out;
    }

    ret = glfs_init(glfs);
    if (ret) {
        error_setg(errp, "Gluster connection for volume %s, path %s failed"
                         " to connect", gconf->volume, gconf->path);
        for (server = gconf->server; server; server = server->next) {
            if (server->value->type  == GLUSTER_TRANSPORT_UNIX) {
                error_append_hint(errp, "hint: failed on socket %s ",
                                  server->value->u.q_unix.path);
            } else {
                error_append_hint(errp, "hint: failed on host %s and port %s ",
                                  server->value->u.tcp.host,
                                  server->value->u.tcp.port);
            }
        }

        error_append_hint(errp, "Please refer to gluster logs for more info\n");

        /* glfs_init sometimes doesn't set errno although docs suggest that */
        if (errno == 0) {
            errno = EINVAL;
        }

        goto out;
    }
    return glfs;

out:
    if (glfs) {
        old_errno = errno;
        glfs_clear_preopened(glfs);
        errno = old_errno;
    }
    return NULL;
}

static int qapi_enum_parse(const char *opt)
{
    int i;

    if (!opt) {
        return GLUSTER_TRANSPORT__MAX;
    }

    for (i = 0; i < GLUSTER_TRANSPORT__MAX; i++) {
        if (!strcmp(opt, GlusterTransport_lookup[i])) {
            return i;
        }
    }

    return i;
}

/*
 * Convert the json formatted command line into qapi.
*/
static int qemu_gluster_parse_json(BlockdevOptionsGluster *gconf,
                                  QDict *options, Error **errp)
{
    QemuOpts *opts;
    GlusterServer *gsconf;
    GlusterServerList *curr = NULL;
    QDict *backing_options = NULL;
    Error *local_err = NULL;
    char *str = NULL;
    const char *ptr;
    size_t num_servers;
    int i;

    /* create opts info from runtime_json_opts list */
    opts = qemu_opts_create(&runtime_json_opts, NULL, 0, &error_abort);
    qemu_opts_absorb_qdict(opts, options, &local_err);
    if (local_err) {
        goto out;
    }

    num_servers = qdict_array_entries(options, GLUSTER_OPT_SERVER_PATTERN);
    if (num_servers < 1) {
        error_setg(&local_err, QERR_MISSING_PARAMETER, "server");
        goto out;
    }

    ptr = qemu_opt_get(opts, GLUSTER_OPT_VOLUME);
    if (!ptr) {
        error_setg(&local_err, QERR_MISSING_PARAMETER, GLUSTER_OPT_VOLUME);
        goto out;
    }
    gconf->volume = g_strdup(ptr);

    ptr = qemu_opt_get(opts, GLUSTER_OPT_PATH);
    if (!ptr) {
        error_setg(&local_err, QERR_MISSING_PARAMETER, GLUSTER_OPT_PATH);
        goto out;
    }
    gconf->path = g_strdup(ptr);
    qemu_opts_del(opts);

    for (i = 0; i < num_servers; i++) {
        str = g_strdup_printf(GLUSTER_OPT_SERVER_PATTERN"%d.", i);
        qdict_extract_subqdict(options, &backing_options, str);

        /* create opts info from runtime_type_opts list */
        opts = qemu_opts_create(&runtime_type_opts, NULL, 0, &error_abort);
        qemu_opts_absorb_qdict(opts, backing_options, &local_err);
        if (local_err) {
            goto out;
        }

        ptr = qemu_opt_get(opts, GLUSTER_OPT_TYPE);
        gsconf = g_new0(GlusterServer, 1);
        gsconf->type = qapi_enum_parse(ptr);
        if (!ptr) {
            error_setg(&local_err, QERR_MISSING_PARAMETER, GLUSTER_OPT_TYPE);
            error_append_hint(&local_err, GERR_INDEX_HINT, i);
            goto out;

        }
        if (gsconf->type == GLUSTER_TRANSPORT__MAX) {
            error_setg(&local_err, QERR_INVALID_PARAMETER_VALUE,
                       GLUSTER_OPT_TYPE, "tcp or unix");
            error_append_hint(&local_err, GERR_INDEX_HINT, i);
            goto out;
        }
        qemu_opts_del(opts);

        if (gsconf->type == GLUSTER_TRANSPORT_TCP) {
            /* create opts info from runtime_tcp_opts list */
            opts = qemu_opts_create(&runtime_tcp_opts, NULL, 0, &error_abort);
            qemu_opts_absorb_qdict(opts, backing_options, &local_err);
            if (local_err) {
                goto out;
            }

            ptr = qemu_opt_get(opts, GLUSTER_OPT_HOST);
            if (!ptr) {
                error_setg(&local_err, QERR_MISSING_PARAMETER,
                           GLUSTER_OPT_HOST);
                error_append_hint(&local_err, GERR_INDEX_HINT, i);
                goto out;
            }
            gsconf->u.tcp.host = g_strdup(ptr);
            ptr = qemu_opt_get(opts, GLUSTER_OPT_PORT);
            if (!ptr) {
                error_setg(&local_err, QERR_MISSING_PARAMETER,
                           GLUSTER_OPT_PORT);
                error_append_hint(&local_err, GERR_INDEX_HINT, i);
                goto out;
            }
            gsconf->u.tcp.port = g_strdup(ptr);

            /* defend for unsupported fields in InetSocketAddress,
             * i.e. @ipv4, @ipv6  and @to
             */
            ptr = qemu_opt_get(opts, GLUSTER_OPT_TO);
            if (ptr) {
                gsconf->u.tcp.has_to = true;
            }
            ptr = qemu_opt_get(opts, GLUSTER_OPT_IPV4);
            if (ptr) {
                gsconf->u.tcp.has_ipv4 = true;
            }
            ptr = qemu_opt_get(opts, GLUSTER_OPT_IPV6);
            if (ptr) {
                gsconf->u.tcp.has_ipv6 = true;
            }
            if (gsconf->u.tcp.has_to) {
                error_setg(&local_err, "Parameter 'to' not supported");
                goto out;
            }
            if (gsconf->u.tcp.has_ipv4 || gsconf->u.tcp.has_ipv6) {
                error_setg(&local_err, "Parameters 'ipv4/ipv6' not supported");
                goto out;
            }
            qemu_opts_del(opts);
        } else {
            /* create opts info from runtime_unix_opts list */
            opts = qemu_opts_create(&runtime_unix_opts, NULL, 0, &error_abort);
            qemu_opts_absorb_qdict(opts, backing_options, &local_err);
            if (local_err) {
                goto out;
            }

            ptr = qemu_opt_get(opts, GLUSTER_OPT_SOCKET);
            if (!ptr) {
                error_setg(&local_err, QERR_MISSING_PARAMETER,
                           GLUSTER_OPT_SOCKET);
                error_append_hint(&local_err, GERR_INDEX_HINT, i);
                goto out;
            }
            gsconf->u.q_unix.path = g_strdup(ptr);
            qemu_opts_del(opts);
        }

        if (gconf->server == NULL) {
            gconf->server = g_new0(GlusterServerList, 1);
            gconf->server->value = gsconf;
            curr = gconf->server;
        } else {
            curr->next = g_new0(GlusterServerList, 1);
            curr->next->value = gsconf;
            curr = curr->next;
        }

        qdict_del(backing_options, str);
        g_free(str);
        str = NULL;
    }

    return 0;

out:
    error_propagate(errp, local_err);
    qemu_opts_del(opts);
    if (str) {
        qdict_del(backing_options, str);
        g_free(str);
    }
    errno = EINVAL;
    return -errno;
}

static struct glfs *qemu_gluster_init(BlockdevOptionsGluster *gconf,
                                      const char *filename,
                                      QDict *options, Error **errp)
{
    int ret;
    if (filename) {
        ret = qemu_gluster_parse_uri(gconf, filename);
        if (ret < 0) {
            error_setg(errp, "invalid URI");
            error_append_hint(errp, "Usage: file=gluster[+transport]://"
                                    "[host[:port]]volume/path[?socket=...]"
                                    "[,file.debug=N]"
                                    "[,file.logfile=/path/filename.log]\n");
            errno = -ret;
            return NULL;
        }
    } else {
        ret = qemu_gluster_parse_json(gconf, options, errp);
        if (ret < 0) {
            error_append_hint(errp, "Usage: "
                             "-drive driver=qcow2,file.driver=gluster,"
                             "file.volume=testvol,file.path=/path/a.qcow2"
                             "[,file.debug=9]"
                             "[,file.logfile=/path/filename.log],"
                             "file.server.0.type=tcp,"
                             "file.server.0.host=1.2.3.4,"
                             "file.server.0.port=24007,"
                             "file.server.1.transport=unix,"
                             "file.server.1.socket=/var/run/glusterd.socket ..."
                             "\n");
            errno = -ret;
            return NULL;
        }

    }

    return qemu_gluster_glfs_init(gconf, errp);
}

static void qemu_gluster_complete_aio(void *opaque)
{
    GlusterAIOCB *acb = (GlusterAIOCB *)opaque;

    qemu_coroutine_enter(acb->coroutine);
}

/*
 * AIO callback routine called from GlusterFS thread.
 */
static void gluster_finish_aiocb(struct glfs_fd *fd, ssize_t ret, void *arg)
{
    GlusterAIOCB *acb = (GlusterAIOCB *)arg;

    if (!ret || ret == acb->size) {
        acb->ret = 0; /* Success */
    } else if (ret < 0) {
        acb->ret = -errno; /* Read/Write failed */
    } else {
        acb->ret = -EIO; /* Partial read/write - fail it */
    }

    aio_bh_schedule_oneshot(acb->aio_context, qemu_gluster_complete_aio, acb);
}

static void qemu_gluster_parse_flags(int bdrv_flags, int *open_flags)
{
    assert(open_flags != NULL);

    *open_flags |= O_BINARY;

    if (bdrv_flags & BDRV_O_RDWR) {
        *open_flags |= O_RDWR;
    } else {
        *open_flags |= O_RDONLY;
    }

    if ((bdrv_flags & BDRV_O_NOCACHE)) {
        *open_flags |= O_DIRECT;
    }
}

/*
 * Do SEEK_DATA/HOLE to detect if it is functional. Older broken versions of
 * gfapi incorrectly return the current offset when SEEK_DATA/HOLE is used.
 * - Corrected versions return -1 and set errno to EINVAL.
 * - Versions that support SEEK_DATA/HOLE correctly, will return -1 and set
 *   errno to ENXIO when SEEK_DATA is called with a position of EOF.
 */
static bool qemu_gluster_test_seek(struct glfs_fd *fd)
{
    off_t ret = 0;

#if defined SEEK_HOLE && defined SEEK_DATA
    off_t eof;

    eof = glfs_lseek(fd, 0, SEEK_END);
    if (eof < 0) {
        /* this should never occur */
        return false;
    }

    /* this should always fail with ENXIO if SEEK_DATA is supported */
    ret = glfs_lseek(fd, eof, SEEK_DATA);
#endif

    return (ret < 0) && (errno == ENXIO);
}

static int qemu_gluster_open(BlockDriverState *bs,  QDict *options,
                             int bdrv_flags, Error **errp)
{
    BDRVGlusterState *s = bs->opaque;
    int open_flags = 0;
    int ret = 0;
    BlockdevOptionsGluster *gconf = NULL;
    QemuOpts *opts;
    Error *local_err = NULL;
    const char *filename, *logfile;

    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
    qemu_opts_absorb_qdict(opts, options, &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        ret = -EINVAL;
        goto out;
    }

    filename = qemu_opt_get(opts, GLUSTER_OPT_FILENAME);

    s->debug = qemu_opt_get_number(opts, GLUSTER_OPT_DEBUG,
                                   GLUSTER_DEBUG_DEFAULT);
    if (s->debug < 0) {
        s->debug = 0;
    } else if (s->debug > GLUSTER_DEBUG_MAX) {
        s->debug = GLUSTER_DEBUG_MAX;
    }

    gconf = g_new0(BlockdevOptionsGluster, 1);
    gconf->debug = s->debug;
    gconf->has_debug = true;

    logfile = qemu_opt_get(opts, GLUSTER_OPT_LOGFILE);
    s->logfile = g_strdup(logfile ? logfile : GLUSTER_LOGFILE_DEFAULT);

    gconf->logfile = g_strdup(s->logfile);
    gconf->has_logfile = true;

    s->glfs = qemu_gluster_init(gconf, filename, options, errp);
    if (!s->glfs) {
        ret = -errno;
        goto out;
    }

#ifdef CONFIG_GLUSTERFS_XLATOR_OPT
    /* Without this, if fsync fails for a recoverable reason (for instance,
     * ENOSPC), gluster will dump its cache, preventing retries.  This means
     * almost certain data loss.  Not all gluster versions support the
     * 'resync-failed-syncs-after-fsync' key value, but there is no way to
     * discover during runtime if it is supported (this api returns success for
     * unknown key/value pairs) */
    ret = glfs_set_xlator_option(s->glfs, "*-write-behind",
                                          "resync-failed-syncs-after-fsync",
                                          "on");
    if (ret < 0) {
        error_setg_errno(errp, errno, "Unable to set xlator key/value pair");
        ret = -errno;
        goto out;
    }
#endif

    qemu_gluster_parse_flags(bdrv_flags, &open_flags);

    s->fd = glfs_open(s->glfs, gconf->path, open_flags);
    if (!s->fd) {
        ret = -errno;
    }

    s->supports_seek_data = qemu_gluster_test_seek(s->fd);

out:
    qemu_opts_del(opts);
    qapi_free_BlockdevOptionsGluster(gconf);
    if (!ret) {
        return ret;
    }
    g_free(s->logfile);
    if (s->fd) {
        glfs_close(s->fd);
    }

    glfs_clear_preopened(s->glfs);

    return ret;
}

static int qemu_gluster_reopen_prepare(BDRVReopenState *state,
                                       BlockReopenQueue *queue, Error **errp)
{
    int ret = 0;
    BDRVGlusterState *s;
    BDRVGlusterReopenState *reop_s;
    BlockdevOptionsGluster *gconf;
    int open_flags = 0;

    assert(state != NULL);
    assert(state->bs != NULL);

    s = state->bs->opaque;

    state->opaque = g_new0(BDRVGlusterReopenState, 1);
    reop_s = state->opaque;

    qemu_gluster_parse_flags(state->flags, &open_flags);

    gconf = g_new0(BlockdevOptionsGluster, 1);
    gconf->debug = s->debug;
    gconf->has_debug = true;
    gconf->logfile = g_strdup(s->logfile);
    gconf->has_logfile = true;
    reop_s->glfs = qemu_gluster_init(gconf, state->bs->filename, NULL, errp);
    if (reop_s->glfs == NULL) {
        ret = -errno;
        goto exit;
    }

#ifdef CONFIG_GLUSTERFS_XLATOR_OPT
    ret = glfs_set_xlator_option(reop_s->glfs, "*-write-behind",
                                 "resync-failed-syncs-after-fsync", "on");
    if (ret < 0) {
        error_setg_errno(errp, errno, "Unable to set xlator key/value pair");
        ret = -errno;
        goto exit;
    }
#endif

    reop_s->fd = glfs_open(reop_s->glfs, gconf->path, open_flags);
    if (reop_s->fd == NULL) {
        /* reops->glfs will be cleaned up in _abort */
        ret = -errno;
        goto exit;
    }

exit:
    /* state->opaque will be freed in either the _abort or _commit */
    qapi_free_BlockdevOptionsGluster(gconf);
    return ret;
}

static void qemu_gluster_reopen_commit(BDRVReopenState *state)
{
    BDRVGlusterReopenState *reop_s = state->opaque;
    BDRVGlusterState *s = state->bs->opaque;


    /* close the old */
    if (s->fd) {
        glfs_close(s->fd);
    }

    glfs_clear_preopened(s->glfs);

    /* use the newly opened image / connection */
    s->fd         = reop_s->fd;
    s->glfs       = reop_s->glfs;

    g_free(state->opaque);
    state->opaque = NULL;

    return;
}


static void qemu_gluster_reopen_abort(BDRVReopenState *state)
{
    BDRVGlusterReopenState *reop_s = state->opaque;

    if (reop_s == NULL) {
        return;
    }

    if (reop_s->fd) {
        glfs_close(reop_s->fd);
    }

    glfs_clear_preopened(reop_s->glfs);

    g_free(state->opaque);
    state->opaque = NULL;

    return;
}

#ifdef CONFIG_GLUSTERFS_ZEROFILL
static coroutine_fn int qemu_gluster_co_pwrite_zeroes(BlockDriverState *bs,
                                                      int64_t offset,
                                                      int size,
                                                      BdrvRequestFlags flags)
{
    int ret;
    GlusterAIOCB acb;
    BDRVGlusterState *s = bs->opaque;

    acb.size = size;
    acb.ret = 0;
    acb.coroutine = qemu_coroutine_self();
    acb.aio_context = bdrv_get_aio_context(bs);

    ret = glfs_zerofill_async(s->fd, offset, size, gluster_finish_aiocb, &acb);
    if (ret < 0) {
        return -errno;
    }

    qemu_coroutine_yield();
    return acb.ret;
}

static inline bool gluster_supports_zerofill(void)
{
    return 1;
}

static inline int qemu_gluster_zerofill(struct glfs_fd *fd, int64_t offset,
                                        int64_t size)
{
    return glfs_zerofill(fd, offset, size);
}

#else
static inline bool gluster_supports_zerofill(void)
{
    return 0;
}

static inline int qemu_gluster_zerofill(struct glfs_fd *fd, int64_t offset,
                                        int64_t size)
{
    return 0;
}
#endif

static int qemu_gluster_create(const char *filename,
                               QemuOpts *opts, Error **errp)
{
    BlockdevOptionsGluster *gconf;
    struct glfs *glfs;
    struct glfs_fd *fd;
    int ret = 0;
    int prealloc = 0;
    int64_t total_size = 0;
    char *tmp = NULL;

    gconf = g_new0(BlockdevOptionsGluster, 1);
    gconf->debug = qemu_opt_get_number_del(opts, GLUSTER_OPT_DEBUG,
                                           GLUSTER_DEBUG_DEFAULT);
    if (gconf->debug < 0) {
        gconf->debug = 0;
    } else if (gconf->debug > GLUSTER_DEBUG_MAX) {
        gconf->debug = GLUSTER_DEBUG_MAX;
    }
    gconf->has_debug = true;

    gconf->logfile = qemu_opt_get_del(opts, GLUSTER_OPT_LOGFILE);
    if (!gconf->logfile) {
        gconf->logfile = g_strdup(GLUSTER_LOGFILE_DEFAULT);
    }
    gconf->has_logfile = true;

    glfs = qemu_gluster_init(gconf, filename, NULL, errp);
    if (!glfs) {
        ret = -errno;
        goto out;
    }

    total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
                          BDRV_SECTOR_SIZE);

    tmp = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC);
    if (!tmp || !strcmp(tmp, "off")) {
        prealloc = 0;
    } else if (!strcmp(tmp, "full") && gluster_supports_zerofill()) {
        prealloc = 1;
    } else {
        error_setg(errp, "Invalid preallocation mode: '%s'"
                         " or GlusterFS doesn't support zerofill API", tmp);
        ret = -EINVAL;
        goto out;
    }

    fd = glfs_creat(glfs, gconf->path,
                    O_WRONLY | O_CREAT | O_TRUNC | O_BINARY, S_IRUSR | S_IWUSR);
    if (!fd) {
        ret = -errno;
    } else {
        if (!glfs_ftruncate(fd, total_size)) {
            if (prealloc && qemu_gluster_zerofill(fd, 0, total_size)) {
                ret = -errno;
            }
        } else {
            ret = -errno;
        }

        if (glfs_close(fd) != 0) {
            ret = -errno;
        }
    }
out:
    g_free(tmp);
    qapi_free_BlockdevOptionsGluster(gconf);
    glfs_clear_preopened(glfs);
    return ret;
}

static coroutine_fn int qemu_gluster_co_rw(BlockDriverState *bs,
                                           int64_t sector_num, int nb_sectors,
                                           QEMUIOVector *qiov, int write)
{
    int ret;
    GlusterAIOCB acb;
    BDRVGlusterState *s = bs->opaque;
    size_t size = nb_sectors * BDRV_SECTOR_SIZE;
    off_t offset = sector_num * BDRV_SECTOR_SIZE;

    acb.size = size;
    acb.ret = 0;
    acb.coroutine = qemu_coroutine_self();
    acb.aio_context = bdrv_get_aio_context(bs);

    if (write) {
        ret = glfs_pwritev_async(s->fd, qiov->iov, qiov->niov, offset, 0,
                                 gluster_finish_aiocb, &acb);
    } else {
        ret = glfs_preadv_async(s->fd, qiov->iov, qiov->niov, offset, 0,
                                gluster_finish_aiocb, &acb);
    }

    if (ret < 0) {
        return -errno;
    }

    qemu_coroutine_yield();
    return acb.ret;
}

static int qemu_gluster_truncate(BlockDriverState *bs, int64_t offset)
{
    int ret;
    BDRVGlusterState *s = bs->opaque;

    ret = glfs_ftruncate(s->fd, offset);
    if (ret < 0) {
        return -errno;
    }

    return 0;
}

static coroutine_fn int qemu_gluster_co_readv(BlockDriverState *bs,
                                              int64_t sector_num,
                                              int nb_sectors,
                                              QEMUIOVector *qiov)
{
    return qemu_gluster_co_rw(bs, sector_num, nb_sectors, qiov, 0);
}

static coroutine_fn int qemu_gluster_co_writev(BlockDriverState *bs,
                                               int64_t sector_num,
                                               int nb_sectors,
                                               QEMUIOVector *qiov)
{
    return qemu_gluster_co_rw(bs, sector_num, nb_sectors, qiov, 1);
}

static void qemu_gluster_close(BlockDriverState *bs)
{
    BDRVGlusterState *s = bs->opaque;

    g_free(s->logfile);
    if (s->fd) {
        glfs_close(s->fd);
        s->fd = NULL;
    }
    glfs_clear_preopened(s->glfs);
}

static coroutine_fn int qemu_gluster_co_flush_to_disk(BlockDriverState *bs)
{
    int ret;
    GlusterAIOCB acb;
    BDRVGlusterState *s = bs->opaque;

    acb.size = 0;
    acb.ret = 0;
    acb.coroutine = qemu_coroutine_self();
    acb.aio_context = bdrv_get_aio_context(bs);

    ret = glfs_fsync_async(s->fd, gluster_finish_aiocb, &acb);
    if (ret < 0) {
        ret = -errno;
        goto error;
    }

    qemu_coroutine_yield();
    if (acb.ret < 0) {
        ret = acb.ret;
        goto error;
    }

    return acb.ret;

error:
    /* Some versions of Gluster (3.5.6 -> 3.5.8?) will not retain its cache
     * after a fsync failure, so we have no way of allowing the guest to safely
     * continue.  Gluster versions prior to 3.5.6 don't retain the cache
     * either, but will invalidate the fd on error, so this is again our only
     * option.
     *
     * The 'resync-failed-syncs-after-fsync' xlator option for the
     * write-behind cache will cause later gluster versions to retain its
     * cache after error, so long as the fd remains open.  However, we
     * currently have no way of knowing if this option is supported.
     *
     * TODO: Once gluster provides a way for us to determine if the option
     * is supported, bypass the closure and setting drv to NULL.  */
    qemu_gluster_close(bs);
    bs->drv = NULL;
    return ret;
}

#ifdef CONFIG_GLUSTERFS_DISCARD
static coroutine_fn int qemu_gluster_co_pdiscard(BlockDriverState *bs,
                                                 int64_t offset, int size)
{
    int ret;
    GlusterAIOCB acb;
    BDRVGlusterState *s = bs->opaque;

    acb.size = 0;
    acb.ret = 0;
    acb.coroutine = qemu_coroutine_self();
    acb.aio_context = bdrv_get_aio_context(bs);

    ret = glfs_discard_async(s->fd, offset, size, gluster_finish_aiocb, &acb);
    if (ret < 0) {
        return -errno;
    }

    qemu_coroutine_yield();
    return acb.ret;
}
#endif

static int64_t qemu_gluster_getlength(BlockDriverState *bs)
{
    BDRVGlusterState *s = bs->opaque;
    int64_t ret;

    ret = glfs_lseek(s->fd, 0, SEEK_END);
    if (ret < 0) {
        return -errno;
    } else {
        return ret;
    }
}

static int64_t qemu_gluster_allocated_file_size(BlockDriverState *bs)
{
    BDRVGlusterState *s = bs->opaque;
    struct stat st;
    int ret;

    ret = glfs_fstat(s->fd, &st);
    if (ret < 0) {
        return -errno;
    } else {
        return st.st_blocks * 512;
    }
}

static int qemu_gluster_has_zero_init(BlockDriverState *bs)
{
    /* GlusterFS volume could be backed by a block device */
    return 0;
}

/*
 * Find allocation range in @bs around offset @start.
 * May change underlying file descriptor's file offset.
 * If @start is not in a hole, store @start in @data, and the
 * beginning of the next hole in @hole, and return 0.
 * If @start is in a non-trailing hole, store @start in @hole and the
 * beginning of the next non-hole in @data, and return 0.
 * If @start is in a trailing hole or beyond EOF, return -ENXIO.
 * If we can't find out, return a negative errno other than -ENXIO.
 *
 * (Shamefully copied from file-posix.c, only miniscule adaptions.)
 */
static int find_allocation(BlockDriverState *bs, off_t start,
                           off_t *data, off_t *hole)
{
    BDRVGlusterState *s = bs->opaque;

    if (!s->supports_seek_data) {
        goto exit;
    }

#if defined SEEK_HOLE && defined SEEK_DATA
    off_t offs;

    /*
     * SEEK_DATA cases:
     * D1. offs == start: start is in data
     * D2. offs > start: start is in a hole, next data at offs
     * D3. offs < 0, errno = ENXIO: either start is in a trailing hole
     *                              or start is beyond EOF
     *     If the latter happens, the file has been truncated behind
     *     our back since we opened it.  All bets are off then.
     *     Treating like a trailing hole is simplest.
     * D4. offs < 0, errno != ENXIO: we learned nothing
     */
    offs = glfs_lseek(s->fd, start, SEEK_DATA);
    if (offs < 0) {
        return -errno;          /* D3 or D4 */
    }
    assert(offs >= start);

    if (offs > start) {
        /* D2: in hole, next data at offs */
        *hole = start;
        *data = offs;
        return 0;
    }

    /* D1: in data, end not yet known */

    /*
     * SEEK_HOLE cases:
     * H1. offs == start: start is in a hole
     *     If this happens here, a hole has been dug behind our back
     *     since the previous lseek().
     * H2. offs > start: either start is in data, next hole at offs,
     *                   or start is in trailing hole, EOF at offs
     *     Linux treats trailing holes like any other hole: offs ==
     *     start.  Solaris seeks to EOF instead: offs > start (blech).
     *     If that happens here, a hole has been dug behind our back
     *     since the previous lseek().
     * H3. offs < 0, errno = ENXIO: start is beyond EOF
     *     If this happens, the file has been truncated behind our
     *     back since we opened it.  Treat it like a trailing hole.
     * H4. offs < 0, errno != ENXIO: we learned nothing
     *     Pretend we know nothing at all, i.e. "forget" about D1.
     */
    offs = glfs_lseek(s->fd, start, SEEK_HOLE);
    if (offs < 0) {
        return -errno;          /* D1 and (H3 or H4) */
    }
    assert(offs >= start);

    if (offs > start) {
        /*
         * D1 and H2: either in data, next hole at offs, or it was in
         * data but is now in a trailing hole.  In the latter case,
         * all bets are off.  Treating it as if it there was data all
         * the way to EOF is safe, so simply do that.
         */
        *data = start;
        *hole = offs;
        return 0;
    }

    /* D1 and H1 */
    return -EBUSY;
#endif

exit:
    return -ENOTSUP;
}

/*
 * Returns the allocation status of the specified sectors.
 *
 * If 'sector_num' is beyond the end of the disk image the return value is 0
 * and 'pnum' is set to 0.
 *
 * 'pnum' is set to the number of sectors (including and immediately following
 * the specified sector) that are known to be in the same
 * allocated/unallocated state.
 *
 * 'nb_sectors' is the max value 'pnum' should be set to.  If nb_sectors goes
 * beyond the end of the disk image it will be clamped.
 *
 * (Based on raw_co_get_block_status() from file-posix.c.)
 */
static int64_t coroutine_fn qemu_gluster_co_get_block_status(
        BlockDriverState *bs, int64_t sector_num, int nb_sectors, int *pnum,
        BlockDriverState **file)
{
    BDRVGlusterState *s = bs->opaque;
    off_t start, data = 0, hole = 0;
    int64_t total_size;
    int ret = -EINVAL;

    if (!s->fd) {
        return ret;
    }

    start = sector_num * BDRV_SECTOR_SIZE;
    total_size = bdrv_getlength(bs);
    if (total_size < 0) {
        return total_size;
    } else if (start >= total_size) {
        *pnum = 0;
        return 0;
    } else if (start + nb_sectors * BDRV_SECTOR_SIZE > total_size) {
        nb_sectors = DIV_ROUND_UP(total_size - start, BDRV_SECTOR_SIZE);
    }

    ret = find_allocation(bs, start, &data, &hole);
    if (ret == -ENXIO) {
        /* Trailing hole */
        *pnum = nb_sectors;
        ret = BDRV_BLOCK_ZERO;
    } else if (ret < 0) {
        /* No info available, so pretend there are no holes */
        *pnum = nb_sectors;
        ret = BDRV_BLOCK_DATA;
    } else if (data == start) {
        /* On a data extent, compute sectors to the end of the extent,
         * possibly including a partial sector at EOF. */
        *pnum = MIN(nb_sectors, DIV_ROUND_UP(hole - start, BDRV_SECTOR_SIZE));
        ret = BDRV_BLOCK_DATA;
    } else {
        /* On a hole, compute sectors to the beginning of the next extent.  */
        assert(hole == start);
        *pnum = MIN(nb_sectors, (data - start) / BDRV_SECTOR_SIZE);
        ret = BDRV_BLOCK_ZERO;
    }

    *file = bs;

    return ret | BDRV_BLOCK_OFFSET_VALID | start;
}


static BlockDriver bdrv_gluster = {
    .format_name                  = "gluster",
    .protocol_name                = "gluster",
    .instance_size                = sizeof(BDRVGlusterState),
    .bdrv_needs_filename          = false,
    .bdrv_file_open               = qemu_gluster_open,
    .bdrv_reopen_prepare          = qemu_gluster_reopen_prepare,
    .bdrv_reopen_commit           = qemu_gluster_reopen_commit,
    .bdrv_reopen_abort            = qemu_gluster_reopen_abort,
    .bdrv_close                   = qemu_gluster_close,
    .bdrv_create                  = qemu_gluster_create,
    .bdrv_getlength               = qemu_gluster_getlength,
    .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
    .bdrv_truncate                = qemu_gluster_truncate,
    .bdrv_co_readv                = qemu_gluster_co_readv,
    .bdrv_co_writev               = qemu_gluster_co_writev,
    .bdrv_co_flush_to_disk        = qemu_gluster_co_flush_to_disk,
    .bdrv_has_zero_init           = qemu_gluster_has_zero_init,
#ifdef CONFIG_GLUSTERFS_DISCARD
    .bdrv_co_pdiscard             = qemu_gluster_co_pdiscard,
#endif
#ifdef CONFIG_GLUSTERFS_ZEROFILL
    .bdrv_co_pwrite_zeroes        = qemu_gluster_co_pwrite_zeroes,
#endif
    .bdrv_co_get_block_status     = qemu_gluster_co_get_block_status,
    .create_opts                  = &qemu_gluster_create_opts,
};

static BlockDriver bdrv_gluster_tcp = {
    .format_name                  = "gluster",
    .protocol_name                = "gluster+tcp",
    .instance_size                = sizeof(BDRVGlusterState),
    .bdrv_needs_filename          = false,
    .bdrv_file_open               = qemu_gluster_open,
    .bdrv_reopen_prepare          = qemu_gluster_reopen_prepare,
    .bdrv_reopen_commit           = qemu_gluster_reopen_commit,
    .bdrv_reopen_abort            = qemu_gluster_reopen_abort,
    .bdrv_close                   = qemu_gluster_close,
    .bdrv_create                  = qemu_gluster_create,
    .bdrv_getlength               = qemu_gluster_getlength,
    .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
    .bdrv_truncate                = qemu_gluster_truncate,
    .bdrv_co_readv                = qemu_gluster_co_readv,
    .bdrv_co_writev               = qemu_gluster_co_writev,
    .bdrv_co_flush_to_disk        = qemu_gluster_co_flush_to_disk,
    .bdrv_has_zero_init           = qemu_gluster_has_zero_init,
#ifdef CONFIG_GLUSTERFS_DISCARD
    .bdrv_co_pdiscard             = qemu_gluster_co_pdiscard,
#endif
#ifdef CONFIG_GLUSTERFS_ZEROFILL
    .bdrv_co_pwrite_zeroes        = qemu_gluster_co_pwrite_zeroes,
#endif
    .bdrv_co_get_block_status     = qemu_gluster_co_get_block_status,
    .create_opts                  = &qemu_gluster_create_opts,
};

static BlockDriver bdrv_gluster_unix = {
    .format_name                  = "gluster",
    .protocol_name                = "gluster+unix",
    .instance_size                = sizeof(BDRVGlusterState),
    .bdrv_needs_filename          = true,
    .bdrv_file_open               = qemu_gluster_open,
    .bdrv_reopen_prepare          = qemu_gluster_reopen_prepare,
    .bdrv_reopen_commit           = qemu_gluster_reopen_commit,
    .bdrv_reopen_abort            = qemu_gluster_reopen_abort,
    .bdrv_close                   = qemu_gluster_close,
    .bdrv_create                  = qemu_gluster_create,
    .bdrv_getlength               = qemu_gluster_getlength,
    .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
    .bdrv_truncate                = qemu_gluster_truncate,
    .bdrv_co_readv                = qemu_gluster_co_readv,
    .bdrv_co_writev               = qemu_gluster_co_writev,
    .bdrv_co_flush_to_disk        = qemu_gluster_co_flush_to_disk,
    .bdrv_has_zero_init           = qemu_gluster_has_zero_init,
#ifdef CONFIG_GLUSTERFS_DISCARD
    .bdrv_co_pdiscard             = qemu_gluster_co_pdiscard,
#endif
#ifdef CONFIG_GLUSTERFS_ZEROFILL
    .bdrv_co_pwrite_zeroes        = qemu_gluster_co_pwrite_zeroes,
#endif
    .bdrv_co_get_block_status     = qemu_gluster_co_get_block_status,
    .create_opts                  = &qemu_gluster_create_opts,
};

/* rdma is deprecated (actually never supported for volfile fetch).
 * Let's maintain it for the protocol compatibility, to make sure things
 * won't break immediately. For now, gluster+rdma will fall back to gluster+tcp
 * protocol with a warning.
 * TODO: remove gluster+rdma interface support
 */
static BlockDriver bdrv_gluster_rdma = {
    .format_name                  = "gluster",
    .protocol_name                = "gluster+rdma",
    .instance_size                = sizeof(BDRVGlusterState),
    .bdrv_needs_filename          = true,
    .bdrv_file_open               = qemu_gluster_open,
    .bdrv_reopen_prepare          = qemu_gluster_reopen_prepare,
    .bdrv_reopen_commit           = qemu_gluster_reopen_commit,
    .bdrv_reopen_abort            = qemu_gluster_reopen_abort,
    .bdrv_close                   = qemu_gluster_close,
    .bdrv_create                  = qemu_gluster_create,
    .bdrv_getlength               = qemu_gluster_getlength,
    .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
    .bdrv_truncate                = qemu_gluster_truncate,
    .bdrv_co_readv                = qemu_gluster_co_readv,
    .bdrv_co_writev               = qemu_gluster_co_writev,
    .bdrv_co_flush_to_disk        = qemu_gluster_co_flush_to_disk,
    .bdrv_has_zero_init           = qemu_gluster_has_zero_init,
#ifdef CONFIG_GLUSTERFS_DISCARD
    .bdrv_co_pdiscard             = qemu_gluster_co_pdiscard,
#endif
#ifdef CONFIG_GLUSTERFS_ZEROFILL
    .bdrv_co_pwrite_zeroes        = qemu_gluster_co_pwrite_zeroes,
#endif
    .bdrv_co_get_block_status     = qemu_gluster_co_get_block_status,
    .create_opts                  = &qemu_gluster_create_opts,
};

static void bdrv_gluster_init(void)
{
    bdrv_register(&bdrv_gluster_rdma);
    bdrv_register(&bdrv_gluster_unix);
    bdrv_register(&bdrv_gluster_tcp);
    bdrv_register(&bdrv_gluster);
}

block_init(bdrv_gluster_init);