summaryrefslogtreecommitdiff
path: root/source3/modules/vfs_ceph.c
blob: 8864b42400849e4297a3ffdb985180c881d99458 (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
/*
   Unix SMB/CIFS implementation.
   Wrap disk only vfs functions to sidestep dodgy compilers.
   Copyright (C) Tim Potter 1998
   Copyright (C) Jeremy Allison 2007
   Copyright (C) Brian Chrisman 2011 <bchrisman@gmail.com>
   Copyright (C) Richard Sharpe 2011 <realrichardsharpe@gmail.com>

   This program is free software; you can redistribute it and/or modify
   it under the terms of the GNU General Public License as published by
   the Free Software Foundation; either version 3 of the License, or
   (at your option) any later version.

   This program is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
   GNU General Public License for more details.

   You should have received a copy of the GNU General Public License
   along with this program.  If not, see <http://www.gnu.org/licenses/>.
*/

/*
 * This VFS only works with the libceph.so user-space client. It is not needed
 * if you are using the kernel client or the FUSE client.
 *
 * Add the following smb.conf parameter to each share that will be hosted on
 * Ceph:
 *
 *   vfs objects = ceph [any others you need go here]
 */

#include "includes.h"
#include "smbd/smbd.h"
#include "system/filesys.h"
#include <dirent.h>
#include <sys/statvfs.h>
#include "cephfs/libcephfs.h"
#include "smbprofile.h"
#include "modules/posixacl_xattr.h"
#include "lib/util/tevent_unix.h"

#undef DBGC_CLASS
#define DBGC_CLASS DBGC_VFS

#ifndef LIBCEPHFS_VERSION
#define LIBCEPHFS_VERSION(maj, min, extra) ((maj << 16) + (min << 8) + extra)
#define LIBCEPHFS_VERSION_CODE LIBCEPHFS_VERSION(0, 0, 0)
#endif

/*
 * Use %llu whenever we have a 64bit unsigned int, and cast to (long long unsigned)
 */
#define llu(_var) ((long long unsigned)_var)

/*
 * Note, libceph's return code model is to return -errno! So we have to convert
 * to what Samba expects, with is set errno to -return and return -1
 */
#define WRAP_RETURN(_res) \
	errno = 0; \
	if (_res < 0) { \
		errno = -_res; \
		return -1; \
	} \
	return _res \

/*
 * We mount only one file system and then all shares are assumed to be in that.
 * FIXME: If we want to support more than one FS, then we have to deal with
 * this differently.
 *
 * So, cmount tells us if we have been this way before and whether
 * we need to mount ceph and cmount_cnt tells us how many times we have
 * connected
 */
static struct ceph_mount_info * cmount = NULL;
static uint32_t cmount_cnt = 0;

/* Check for NULL pointer parameters in cephwrap_* functions */

/* We don't want to have NULL function pointers lying around.  Someone
   is sure to try and execute them.  These stubs are used to prevent
   this possibility. */

static int cephwrap_connect(struct vfs_handle_struct *handle,  const char *service, const char *user)
{
	int ret;
	char buf[256];
	int snum = SNUM(handle->conn);
	const char *conf_file;
	const char *user_id;

	if (cmount) {
		handle->data = cmount; /* We have been here before */
		cmount_cnt++;
		return 0;
	}

	/* if config_file and/or user_id are NULL, ceph will use defaults */
	conf_file = lp_parm_const_string(snum, "ceph", "config_file", NULL);
	user_id = lp_parm_const_string(snum, "ceph", "user_id", NULL);

	DBG_DEBUG("[CEPH] calling: ceph_create\n");
	ret = ceph_create(&cmount, user_id);
	if (ret) {
		goto err_out;
	}

	DBG_DEBUG("[CEPH] calling: ceph_conf_read_file with %s\n",
		  (conf_file == NULL ? "default path" : conf_file));
	ret = ceph_conf_read_file(cmount, conf_file);
	if (ret) {
		goto err_cm_release;
	}

	DBG_DEBUG("[CEPH] calling: ceph_conf_get\n");
	ret = ceph_conf_get(cmount, "log file", buf, sizeof(buf));
	if (ret < 0) {
		goto err_cm_release;
	}

	/* libcephfs disables POSIX ACL support by default, enable it... */
	ret = ceph_conf_set(cmount, "client_acl_type", "posix_acl");
	if (ret < 0) {
		goto err_cm_release;
	}
	/* tell libcephfs to perform local permission checks */
	ret = ceph_conf_set(cmount, "fuse_default_permissions", "false");
	if (ret < 0) {
		goto err_cm_release;
	}

	DBG_DEBUG("[CEPH] calling: ceph_mount\n");
	ret = ceph_mount(cmount, NULL);
	if (ret < 0) {
		goto err_cm_release;
	}

	/*
	 * encode mount context/state into our vfs/connection holding structure
	 * cmount is a ceph_mount_t*
	 */
	handle->data = cmount;
	cmount_cnt++;

	/*
	 * Unless we have an async implementation of getxattrat turn this off.
	 */
	lp_do_parameter(SNUM(handle->conn), "smbd async dosmode", "false");

	return 0;

err_cm_release:
	ceph_release(cmount);
	cmount = NULL;
err_out:
	/*
	 * Handle the error correctly. Ceph returns -errno.
	 */
	DBG_DEBUG("[CEPH] Error return: %s\n", strerror(-ret));
	WRAP_RETURN(ret);
}

static void cephwrap_disconnect(struct vfs_handle_struct *handle)
{
	int ret;

	if (!cmount) {
		DBG_ERR("[CEPH] Error, ceph not mounted\n");
		return;
	}

	/* Should we unmount/shutdown? Only if the last disconnect? */
	if (--cmount_cnt) {
		DBG_DEBUG("[CEPH] Not shuting down CEPH because still more connections\n");
		return;
	}

	ret = ceph_unmount(cmount);
	if (ret < 0) {
		DBG_ERR("[CEPH] failed to unmount: %s\n", strerror(-ret));
	}

	ret = ceph_release(cmount);
	if (ret < 0) {
		DBG_ERR("[CEPH] failed to release: %s\n", strerror(-ret));
	}

	cmount = NULL;  /* Make it safe */
}

/* Disk operations */

static uint64_t cephwrap_disk_free(struct vfs_handle_struct *handle,
				const struct smb_filename *smb_fname,
				uint64_t *bsize,
				uint64_t *dfree,
				uint64_t *dsize)
{
	struct statvfs statvfs_buf;
	int ret;

	if (!(ret = ceph_statfs(handle->data, smb_fname->base_name,
			&statvfs_buf))) {
		/*
		 * Provide all the correct values.
		 */
		*bsize = statvfs_buf.f_bsize;
		*dfree = statvfs_buf.f_bavail;
		*dsize = statvfs_buf.f_blocks;
		DBG_DEBUG("[CEPH] bsize: %llu, dfree: %llu, dsize: %llu\n",
			llu(*bsize), llu(*dfree), llu(*dsize));
		return *dfree;
	} else {
		DBG_DEBUG("[CEPH] ceph_statfs returned %d\n", ret);
		WRAP_RETURN(ret);
	}
}

static int cephwrap_get_quota(struct vfs_handle_struct *handle,
				const struct smb_filename *smb_fname,
				enum SMB_QUOTA_TYPE qtype,
				unid_t id,
				SMB_DISK_QUOTA *qt)
{
	/* libceph: Ceph does not implement this */
#if 0
/* was ifdef HAVE_SYS_QUOTAS */
	int ret;

	ret = ceph_get_quota(handle->conn->connectpath, qtype, id, qt);

	if (ret) {
		errno = -ret;
		ret = -1;
	}

	return ret;
#else
	errno = ENOSYS;
	return -1;
#endif
}

static int cephwrap_set_quota(struct vfs_handle_struct *handle,  enum SMB_QUOTA_TYPE qtype, unid_t id, SMB_DISK_QUOTA *qt)
{
	/* libceph: Ceph does not implement this */
#if 0
/* was ifdef HAVE_SYS_QUOTAS */
	int ret;

	ret = ceph_set_quota(handle->conn->connectpath, qtype, id, qt);
	if (ret) {
		errno = -ret;
		ret = -1;
	}

	return ret;
#else
	WRAP_RETURN(-ENOSYS);
#endif
}

static int cephwrap_statvfs(struct vfs_handle_struct *handle,
				const struct smb_filename *smb_fname,
				vfs_statvfs_struct *statbuf)
{
	struct statvfs statvfs_buf;
	int ret;

	ret = ceph_statfs(handle->data, smb_fname->base_name, &statvfs_buf);
	if (ret < 0) {
		WRAP_RETURN(ret);
	}

	statbuf->OptimalTransferSize = statvfs_buf.f_frsize;
	statbuf->BlockSize = statvfs_buf.f_bsize;
	statbuf->TotalBlocks = statvfs_buf.f_blocks;
	statbuf->BlocksAvail = statvfs_buf.f_bfree;
	statbuf->UserBlocksAvail = statvfs_buf.f_bavail;
	statbuf->TotalFileNodes = statvfs_buf.f_files;
	statbuf->FreeFileNodes = statvfs_buf.f_ffree;
	statbuf->FsIdentifier = statvfs_buf.f_fsid;
	DBG_DEBUG("[CEPH] f_bsize: %ld, f_blocks: %ld, f_bfree: %ld, f_bavail: %ld\n",
		(long int)statvfs_buf.f_bsize, (long int)statvfs_buf.f_blocks,
		(long int)statvfs_buf.f_bfree, (long int)statvfs_buf.f_bavail);

	return ret;
}

static uint32_t cephwrap_fs_capabilities(struct vfs_handle_struct *handle,
					 enum timestamp_set_resolution *p_ts_res)
{
	uint32_t caps = FILE_CASE_SENSITIVE_SEARCH | FILE_CASE_PRESERVED_NAMES;

#ifdef HAVE_CEPH_STATX
	*p_ts_res = TIMESTAMP_SET_NT_OR_BETTER;
#else
	*p_ts_res = TIMESTAMP_SET_MSEC;
#endif

	return caps;
}

/* Directory operations */

static DIR *cephwrap_opendir(struct vfs_handle_struct *handle,
			     const struct smb_filename *smb_fname,
			     const char *mask, uint32_t attr)
{
	int ret = 0;
	struct ceph_dir_result *result;
	DBG_DEBUG("[CEPH] opendir(%p, %s)\n", handle, smb_fname->base_name);

	/* Returns NULL if it does not exist or there are problems ? */
	ret = ceph_opendir(handle->data, smb_fname->base_name, &result);
	if (ret < 0) {
		result = NULL;
		errno = -ret; /* We return result which is NULL in this case */
	}

	DBG_DEBUG("[CEPH] opendir(...) = %d\n", ret);
	return (DIR *) result;
}

static DIR *cephwrap_fdopendir(struct vfs_handle_struct *handle,
			       struct files_struct *fsp,
			       const char *mask,
			       uint32_t attributes)
{
	/* OpenDir_fsp() falls back to regular open */
	errno = ENOSYS;
	return NULL;
}

static struct dirent *cephwrap_readdir(struct vfs_handle_struct *handle,
				       DIR *dirp,
				       SMB_STRUCT_STAT *sbuf)
{
	struct dirent *result;

	DBG_DEBUG("[CEPH] readdir(%p, %p)\n", handle, dirp);
	result = ceph_readdir(handle->data, (struct ceph_dir_result *) dirp);
	DBG_DEBUG("[CEPH] readdir(...) = %p\n", result);

	/* Default Posix readdir() does not give us stat info.
	 * Set to invalid to indicate we didn't return this info. */
	if (sbuf)
		SET_STAT_INVALID(*sbuf);
	return result;
}

static void cephwrap_seekdir(struct vfs_handle_struct *handle, DIR *dirp, long offset)
{
	DBG_DEBUG("[CEPH] seekdir(%p, %p, %ld)\n", handle, dirp, offset);
	ceph_seekdir(handle->data, (struct ceph_dir_result *) dirp, offset);
}

static long cephwrap_telldir(struct vfs_handle_struct *handle, DIR *dirp)
{
	long ret;
	DBG_DEBUG("[CEPH] telldir(%p, %p)\n", handle, dirp);
	ret = ceph_telldir(handle->data, (struct ceph_dir_result *) dirp);
	DBG_DEBUG("[CEPH] telldir(...) = %ld\n", ret);
	WRAP_RETURN(ret);
}

static void cephwrap_rewinddir(struct vfs_handle_struct *handle, DIR *dirp)
{
	DBG_DEBUG("[CEPH] rewinddir(%p, %p)\n", handle, dirp);
	ceph_rewinddir(handle->data, (struct ceph_dir_result *) dirp);
}

static int cephwrap_mkdirat(struct vfs_handle_struct *handle,
			files_struct *dirfsp,
			const struct smb_filename *smb_fname,
			mode_t mode)
{
	int result;
	char *parent = NULL;
	const char *path = smb_fname->base_name;

	DBG_DEBUG("[CEPH] mkdir(%p, %s)\n", handle, path);

	SMB_ASSERT(dirfsp == dirfsp->conn->cwd_fsp);

	if (lp_inherit_acls(SNUM(handle->conn))
	    && parent_dirname(talloc_tos(), path, &parent, NULL)
	    && directory_has_default_acl(handle->conn, parent)) {
		mode = 0777;
	}

	TALLOC_FREE(parent);

	result = ceph_mkdir(handle->data, path, mode);
	return WRAP_RETURN(result);
}

static int cephwrap_closedir(struct vfs_handle_struct *handle, DIR *dirp)
{
	int result;

	DBG_DEBUG("[CEPH] closedir(%p, %p)\n", handle, dirp);
	result = ceph_closedir(handle->data, (struct ceph_dir_result *) dirp);
	DBG_DEBUG("[CEPH] closedir(...) = %d\n", result);
	WRAP_RETURN(result);
}

/* File operations */

static int cephwrap_open(struct vfs_handle_struct *handle,
			struct smb_filename *smb_fname,
			files_struct *fsp, int flags, mode_t mode)
{
	int result = -ENOENT;
	DBG_DEBUG("[CEPH] open(%p, %s, %p, %d, %d)\n", handle,
		  smb_fname_str_dbg(smb_fname), fsp, flags, mode);

	if (smb_fname->stream_name) {
		goto out;
	}

	result = ceph_open(handle->data, smb_fname->base_name, flags, mode);
out:
	DBG_DEBUG("[CEPH] open(...) = %d\n", result);
	WRAP_RETURN(result);
}

static int cephwrap_close(struct vfs_handle_struct *handle, files_struct *fsp)
{
	int result;

	DBG_DEBUG("[CEPH] close(%p, %p)\n", handle, fsp);
	result = ceph_close(handle->data, fsp->fh->fd);
	DBG_DEBUG("[CEPH] close(...) = %d\n", result);

	WRAP_RETURN(result);
}

static ssize_t cephwrap_pread(struct vfs_handle_struct *handle, files_struct *fsp, void *data,
			size_t n, off_t offset)
{
	ssize_t result;

	DBG_DEBUG("[CEPH] pread(%p, %p, %p, %llu, %llu)\n", handle, fsp, data, llu(n), llu(offset));

	result = ceph_read(handle->data, fsp->fh->fd, data, n, offset);
	DBG_DEBUG("[CEPH] pread(...) = %llu\n", llu(result));
	WRAP_RETURN(result);
}

struct cephwrap_pread_state {
	ssize_t bytes_read;
	struct vfs_aio_state vfs_aio_state;
};

/*
 * Fake up an async ceph read by calling the synchronous API.
 */
static struct tevent_req *cephwrap_pread_send(struct vfs_handle_struct *handle,
					      TALLOC_CTX *mem_ctx,
					      struct tevent_context *ev,
					      struct files_struct *fsp,
					      void *data,
					      size_t n, off_t offset)
{
	struct tevent_req *req = NULL;
	struct cephwrap_pread_state *state = NULL;
	int ret = -1;

	DBG_DEBUG("[CEPH] %s\n", __func__);
	req = tevent_req_create(mem_ctx, &state, struct cephwrap_pread_state);
	if (req == NULL) {
		return NULL;
	}

	ret = ceph_read(handle->data, fsp->fh->fd, data, n, offset);
	if (ret < 0) {
		/* ceph returns -errno on error. */
		tevent_req_error(req, -ret);
		return tevent_req_post(req, ev);
	}

	state->bytes_read = ret;
	tevent_req_done(req);
	/* Return and schedule the completion of the call. */
	return tevent_req_post(req, ev);
}

static ssize_t cephwrap_pread_recv(struct tevent_req *req,
				   struct vfs_aio_state *vfs_aio_state)
{
	struct cephwrap_pread_state *state =
		tevent_req_data(req, struct cephwrap_pread_state);

	DBG_DEBUG("[CEPH] %s\n", __func__);
	if (tevent_req_is_unix_error(req, &vfs_aio_state->error)) {
		return -1;
	}
	*vfs_aio_state = state->vfs_aio_state;
	return state->bytes_read;
}

static ssize_t cephwrap_pwrite(struct vfs_handle_struct *handle, files_struct *fsp, const void *data,
			size_t n, off_t offset)
{
	ssize_t result;

	DBG_DEBUG("[CEPH] pwrite(%p, %p, %p, %llu, %llu)\n", handle, fsp, data, llu(n), llu(offset));
	result = ceph_write(handle->data, fsp->fh->fd, data, n, offset);
	DBG_DEBUG("[CEPH] pwrite(...) = %llu\n", llu(result));
	WRAP_RETURN(result);
}

struct cephwrap_pwrite_state {
	ssize_t bytes_written;
	struct vfs_aio_state vfs_aio_state;
};

/*
 * Fake up an async ceph write by calling the synchronous API.
 */
static struct tevent_req *cephwrap_pwrite_send(struct vfs_handle_struct *handle,
					       TALLOC_CTX *mem_ctx,
					       struct tevent_context *ev,
					       struct files_struct *fsp,
					       const void *data,
					       size_t n, off_t offset)
{
	struct tevent_req *req = NULL;
	struct cephwrap_pwrite_state *state = NULL;
	int ret = -1;

	DBG_DEBUG("[CEPH] %s\n", __func__);
	req = tevent_req_create(mem_ctx, &state, struct cephwrap_pwrite_state);
	if (req == NULL) {
		return NULL;
	}

	ret = ceph_write(handle->data, fsp->fh->fd, data, n, offset);
	if (ret < 0) {
		/* ceph returns -errno on error. */
		tevent_req_error(req, -ret);
		return tevent_req_post(req, ev);
	}

	state->bytes_written = ret;
	tevent_req_done(req);
	/* Return and schedule the completion of the call. */
	return tevent_req_post(req, ev);
}

static ssize_t cephwrap_pwrite_recv(struct tevent_req *req,
				    struct vfs_aio_state *vfs_aio_state)
{
	struct cephwrap_pwrite_state *state =
		tevent_req_data(req, struct cephwrap_pwrite_state);

	DBG_DEBUG("[CEPH] %s\n", __func__);
	if (tevent_req_is_unix_error(req, &vfs_aio_state->error)) {
		return -1;
	}
	*vfs_aio_state = state->vfs_aio_state;
	return state->bytes_written;
}

static off_t cephwrap_lseek(struct vfs_handle_struct *handle, files_struct *fsp, off_t offset, int whence)
{
	off_t result = 0;

	DBG_DEBUG("[CEPH] cephwrap_lseek\n");
	result = ceph_lseek(handle->data, fsp->fh->fd, offset, whence);
	WRAP_RETURN(result);
}

static ssize_t cephwrap_sendfile(struct vfs_handle_struct *handle, int tofd, files_struct *fromfsp, const DATA_BLOB *hdr,
			off_t offset, size_t n)
{
	/*
	 * We cannot support sendfile because libceph is in user space.
	 */
	DBG_DEBUG("[CEPH] cephwrap_sendfile\n");
	errno = ENOTSUP;
	return -1;
}

static ssize_t cephwrap_recvfile(struct vfs_handle_struct *handle,
			int fromfd,
			files_struct *tofsp,
			off_t offset,
			size_t n)
{
	/*
	 * We cannot support recvfile because libceph is in user space.
	 */
	DBG_DEBUG("[CEPH] cephwrap_recvfile\n");
	errno=ENOTSUP;
	return -1;
}

static int cephwrap_renameat(struct vfs_handle_struct *handle,
			files_struct *srcfsp,
			const struct smb_filename *smb_fname_src,
			files_struct *dstfsp,
			const struct smb_filename *smb_fname_dst)
{
	int result = -1;
	DBG_DEBUG("[CEPH] cephwrap_renameat\n");
	if (smb_fname_src->stream_name || smb_fname_dst->stream_name) {
		errno = ENOENT;
		return result;
	}

	result = ceph_rename(handle->data, smb_fname_src->base_name, smb_fname_dst->base_name);
	WRAP_RETURN(result);
}

/*
 * Fake up an async ceph fsync by calling the synchronous API.
 */

static struct tevent_req *cephwrap_fsync_send(struct vfs_handle_struct *handle,
					TALLOC_CTX *mem_ctx,
					struct tevent_context *ev,
					files_struct *fsp)
{
	struct tevent_req *req = NULL;
	struct vfs_aio_state *state = NULL;
	int ret = -1;

	DBG_DEBUG("[CEPH] cephwrap_fsync_send\n");

	req = tevent_req_create(mem_ctx, &state, struct vfs_aio_state);
	if (req == NULL) {
		return NULL;
	}

	/* Make sync call. */
	ret = ceph_fsync(handle->data, fsp->fh->fd, false);

	if (ret != 0) {
		/* ceph_fsync returns -errno on error. */
		tevent_req_error(req, -ret);
		return tevent_req_post(req, ev);
	}

	/* Mark it as done. */
	tevent_req_done(req);
	/* Return and schedule the completion of the call. */
	return tevent_req_post(req, ev);
}

static int cephwrap_fsync_recv(struct tevent_req *req,
				struct vfs_aio_state *vfs_aio_state)
{
	struct vfs_aio_state *state =
		tevent_req_data(req, struct vfs_aio_state);

	DBG_DEBUG("[CEPH] cephwrap_fsync_recv\n");

	if (tevent_req_is_unix_error(req, &vfs_aio_state->error)) {
		return -1;
	}
	*vfs_aio_state = *state;
	return 0;
}

#ifdef HAVE_CEPH_STATX
#define SAMBA_STATX_ATTR_MASK	(CEPH_STATX_BASIC_STATS|CEPH_STATX_BTIME)

static void init_stat_ex_from_ceph_statx(struct stat_ex *dst, const struct ceph_statx *stx)
{
	DBG_DEBUG("[CEPH]\tstx = {dev = %llx, ino = %llu, mode = 0x%x, "
		  "nlink = %llu, uid = %d, gid = %d, rdev = %llx, size = %llu, "
		  "blksize = %llu, blocks = %llu, atime = %llu, mtime = %llu, "
		  "ctime = %llu, btime = %llu}\n",
		  llu(stx->stx_dev), llu(stx->stx_ino), stx->stx_mode,
		  llu(stx->stx_nlink), stx->stx_uid, stx->stx_gid,
		  llu(stx->stx_rdev), llu(stx->stx_size), llu(stx->stx_blksize),
		  llu(stx->stx_blocks), llu(stx->stx_atime.tv_sec),
		  llu(stx->stx_mtime.tv_sec), llu(stx->stx_ctime.tv_sec),
		  llu(stx->stx_btime.tv_sec));

	if ((stx->stx_mask & SAMBA_STATX_ATTR_MASK) != SAMBA_STATX_ATTR_MASK) {
		DBG_WARNING("%s: stx->stx_mask is incorrect (wanted %x, got %x)",
				__func__, SAMBA_STATX_ATTR_MASK, stx->stx_mask);
	}

	dst->st_ex_dev = stx->stx_dev;
	dst->st_ex_rdev = stx->stx_rdev;
	dst->st_ex_ino = stx->stx_ino;
	dst->st_ex_mode = stx->stx_mode;
	dst->st_ex_uid = stx->stx_uid;
	dst->st_ex_gid = stx->stx_gid;
	dst->st_ex_size = stx->stx_size;
	dst->st_ex_nlink = stx->stx_nlink;
	dst->st_ex_atime = stx->stx_atime;
	dst->st_ex_btime = stx->stx_btime;
	dst->st_ex_ctime = stx->stx_ctime;
	dst->st_ex_mtime = stx->stx_mtime;
	dst->st_ex_itime = dst->st_ex_btime;
	dst->st_ex_iflags = ST_EX_IFLAG_CALCULATED_ITIME;
	dst->st_ex_blksize = stx->stx_blksize;
	dst->st_ex_blocks = stx->stx_blocks;
	dst->st_ex_file_id = dst->st_ex_ino;
	dst->st_ex_iflags |= ST_EX_IFLAG_CALCULATED_FILE_ID;
}

static int cephwrap_stat(struct vfs_handle_struct *handle,
			struct smb_filename *smb_fname)
{
	int result = -1;
	struct ceph_statx stx;

	DBG_DEBUG("[CEPH] stat(%p, %s)\n", handle, smb_fname_str_dbg(smb_fname));

	if (smb_fname->stream_name) {
		errno = ENOENT;
		return result;
	}

	result = ceph_statx(handle->data, smb_fname->base_name, &stx,
				SAMBA_STATX_ATTR_MASK, 0);
	DBG_DEBUG("[CEPH] statx(...) = %d\n", result);
	if (result < 0) {
		WRAP_RETURN(result);
	}

	init_stat_ex_from_ceph_statx(&smb_fname->st, &stx);
	DBG_DEBUG("[CEPH] mode = 0x%x\n", smb_fname->st.st_ex_mode);
	return result;
}

static int cephwrap_fstat(struct vfs_handle_struct *handle, files_struct *fsp, SMB_STRUCT_STAT *sbuf)
{
	int result = -1;
	struct ceph_statx stx;

	DBG_DEBUG("[CEPH] fstat(%p, %d)\n", handle, fsp->fh->fd);
	result = ceph_fstatx(handle->data, fsp->fh->fd, &stx,
				SAMBA_STATX_ATTR_MASK, 0);
	DBG_DEBUG("[CEPH] fstat(...) = %d\n", result);
	if (result < 0) {
		WRAP_RETURN(result);
	}

	init_stat_ex_from_ceph_statx(sbuf, &stx);
	DBG_DEBUG("[CEPH] mode = 0x%x\n", sbuf->st_ex_mode);
	return result;
}

static int cephwrap_lstat(struct vfs_handle_struct *handle,
			 struct smb_filename *smb_fname)
{
	int result = -1;
	struct ceph_statx stx;

	DBG_DEBUG("[CEPH] lstat(%p, %s)\n", handle, smb_fname_str_dbg(smb_fname));

	if (smb_fname->stream_name) {
		errno = ENOENT;
		return result;
	}

	result = ceph_statx(handle->data, smb_fname->base_name, &stx,
				SAMBA_STATX_ATTR_MASK, AT_SYMLINK_NOFOLLOW);
	DBG_DEBUG("[CEPH] lstat(...) = %d\n", result);
	if (result < 0) {
		WRAP_RETURN(result);
	}

	init_stat_ex_from_ceph_statx(&smb_fname->st, &stx);
	return result;
}

static int cephwrap_ntimes(struct vfs_handle_struct *handle,
			 const struct smb_filename *smb_fname,
			 struct smb_file_time *ft)
{
	struct ceph_statx stx = { 0 };
	int result;
	int mask = 0;

	if (!null_timespec(ft->atime)) {
		stx.stx_atime = ft->atime;
		mask |= CEPH_SETATTR_ATIME;
	}
	if (!null_timespec(ft->mtime)) {
		stx.stx_mtime = ft->mtime;
		mask |= CEPH_SETATTR_MTIME;
	}
	if (!null_timespec(ft->create_time)) {
		stx.stx_btime = ft->create_time;
		mask |= CEPH_SETATTR_BTIME;
	}

	if (!mask) {
		return 0;
	}

	result = ceph_setattrx(handle->data, smb_fname->base_name, &stx, mask, 0);
	DBG_DEBUG("[CEPH] ntimes(%p, %s, {%ld, %ld, %ld, %ld}) = %d\n", handle, smb_fname_str_dbg(smb_fname),
				ft->mtime.tv_sec, ft->atime.tv_sec, ft->ctime.tv_sec,
				ft->create_time.tv_sec, result);
	return result;
}

#else /* HAVE_CEPH_STATX */

static int cephwrap_stat(struct vfs_handle_struct *handle,
			struct smb_filename *smb_fname)
{
	int result = -1;
	struct stat stbuf;

	DBG_DEBUG("[CEPH] stat(%p, %s)\n", handle, smb_fname_str_dbg(smb_fname));

	if (smb_fname->stream_name) {
		errno = ENOENT;
		return result;
	}

	result = ceph_stat(handle->data, smb_fname->base_name, (struct stat *) &stbuf);
	DBG_DEBUG("[CEPH] stat(...) = %d\n", result);
	if (result < 0) {
		WRAP_RETURN(result);
	}

	DBG_DEBUG("[CEPH]\tstbuf = {dev = %llu, ino = %llu, mode = 0x%x, nlink = %llu, "
		   "uid = %d, gid = %d, rdev = %llu, size = %llu, blksize = %llu, "
		   "blocks = %llu, atime = %llu, mtime = %llu, ctime = %llu}\n",
		   llu(stbuf.st_dev), llu(stbuf.st_ino), stbuf.st_mode, llu(stbuf.st_nlink),
		   stbuf.st_uid, stbuf.st_gid, llu(stbuf.st_rdev), llu(stbuf.st_size), llu(stbuf.st_blksize),
		   llu(stbuf.st_blocks), llu(stbuf.st_atime), llu(stbuf.st_mtime), llu(stbuf.st_ctime));

	init_stat_ex_from_stat(
			&smb_fname->st, &stbuf,
			lp_fake_directory_create_times(SNUM(handle->conn)));
	DBG_DEBUG("[CEPH] mode = 0x%x\n", smb_fname->st.st_ex_mode);
	return result;
}

static int cephwrap_fstat(struct vfs_handle_struct *handle, files_struct *fsp, SMB_STRUCT_STAT *sbuf)
{
	int result = -1;
	struct stat stbuf;

	DBG_DEBUG("[CEPH] fstat(%p, %d)\n", handle, fsp->fh->fd);
	result = ceph_fstat(handle->data, fsp->fh->fd, (struct stat *) &stbuf);
	DBG_DEBUG("[CEPH] fstat(...) = %d\n", result);
	if (result < 0) {
		WRAP_RETURN(result);
	}

	DBG_DEBUG("[CEPH]\tstbuf = {dev = %llu, ino = %llu, mode = 0x%x, nlink = %llu, "
		   "uid = %d, gid = %d, rdev = %llu, size = %llu, blksize = %llu, "
		   "blocks = %llu, atime = %llu, mtime = %llu, ctime = %llu}\n",
		   llu(stbuf.st_dev), llu(stbuf.st_ino), stbuf.st_mode, llu(stbuf.st_nlink),
		   stbuf.st_uid, stbuf.st_gid, llu(stbuf.st_rdev), llu(stbuf.st_size), llu(stbuf.st_blksize),
		   llu(stbuf.st_blocks), llu(stbuf.st_atime), llu(stbuf.st_mtime), llu(stbuf.st_ctime));

	init_stat_ex_from_stat(
			sbuf, &stbuf,
			lp_fake_directory_create_times(SNUM(handle->conn)));
	DBG_DEBUG("[CEPH] mode = 0x%x\n", sbuf->st_ex_mode);
	return result;
}

static int cephwrap_lstat(struct vfs_handle_struct *handle,
			 struct smb_filename *smb_fname)
{
	int result = -1;
	struct stat stbuf;

	DBG_DEBUG("[CEPH] lstat(%p, %s)\n", handle, smb_fname_str_dbg(smb_fname));

	if (smb_fname->stream_name) {
		errno = ENOENT;
		return result;
	}

	result = ceph_lstat(handle->data, smb_fname->base_name, &stbuf);
	DBG_DEBUG("[CEPH] lstat(...) = %d\n", result);
	if (result < 0) {
		WRAP_RETURN(result);
	}

	init_stat_ex_from_stat(
			&smb_fname->st, &stbuf,
			lp_fake_directory_create_times(SNUM(handle->conn)));
	return result;
}

static int cephwrap_ntimes(struct vfs_handle_struct *handle,
			 const struct smb_filename *smb_fname,
			 struct smb_file_time *ft)
{
	struct utimbuf buf;
	int result;

	if (null_timespec(ft->atime)) {
		buf.actime = smb_fname->st.st_ex_atime.tv_sec;
	} else {
		buf.actime = ft->atime.tv_sec;
	}
	if (null_timespec(ft->mtime)) {
		buf.modtime = smb_fname->st.st_ex_mtime.tv_sec;
	} else {
		buf.modtime = ft->mtime.tv_sec;
	}
	if (!null_timespec(ft->create_time)) {
		set_create_timespec_ea(handle->conn, smb_fname,
				       ft->create_time);
	}
	if (buf.actime == smb_fname->st.st_ex_atime.tv_sec &&
	    buf.modtime == smb_fname->st.st_ex_mtime.tv_sec) {
		return 0;
	}

	result = ceph_utime(handle->data, smb_fname->base_name, &buf);
	DBG_DEBUG("[CEPH] ntimes(%p, %s, {%ld, %ld, %ld, %ld}) = %d\n", handle, smb_fname_str_dbg(smb_fname),
				ft->mtime.tv_sec, ft->atime.tv_sec, ft->ctime.tv_sec,
				ft->create_time.tv_sec, result);
	return result;
}
#endif /* HAVE_CEPH_STATX */

static int cephwrap_unlinkat(struct vfs_handle_struct *handle,
			struct files_struct *dirfsp,
			const struct smb_filename *smb_fname,
			int flags)
{
	int result = -1;

	DBG_DEBUG("[CEPH] unlink(%p, %s)\n",
		handle,
		smb_fname_str_dbg(smb_fname));
	SMB_ASSERT(dirfsp == dirfsp->conn->cwd_fsp);
	if (smb_fname->stream_name) {
		errno = ENOENT;
		return result;
	}
	if (flags & AT_REMOVEDIR) {
		result = ceph_rmdir(handle->data, smb_fname->base_name);
	} else {
		result = ceph_unlink(handle->data, smb_fname->base_name);
	}
	DBG_DEBUG("[CEPH] unlink(...) = %d\n", result);
	WRAP_RETURN(result);
}

static int cephwrap_chmod(struct vfs_handle_struct *handle,
			const struct smb_filename *smb_fname,
			mode_t mode)
{
	int result;

	DBG_DEBUG("[CEPH] chmod(%p, %s, %d)\n", handle, smb_fname->base_name, mode);
	result = ceph_chmod(handle->data, smb_fname->base_name, mode);
	DBG_DEBUG("[CEPH] chmod(...) = %d\n", result);
	WRAP_RETURN(result);
}

static int cephwrap_fchmod(struct vfs_handle_struct *handle, files_struct *fsp, mode_t mode)
{
	int result;

	DBG_DEBUG("[CEPH] fchmod(%p, %p, %d)\n", handle, fsp, mode);
	result = ceph_fchmod(handle->data, fsp->fh->fd, mode);
	DBG_DEBUG("[CEPH] fchmod(...) = %d\n", result);
	WRAP_RETURN(result);
}

static int cephwrap_fchown(struct vfs_handle_struct *handle, files_struct *fsp, uid_t uid, gid_t gid)
{
	int result;

	DBG_DEBUG("[CEPH] fchown(%p, %p, %d, %d)\n", handle, fsp, uid, gid);
	result = ceph_fchown(handle->data, fsp->fh->fd, uid, gid);
	DBG_DEBUG("[CEPH] fchown(...) = %d\n", result);
	WRAP_RETURN(result);
}

static int cephwrap_lchown(struct vfs_handle_struct *handle,
			const struct smb_filename *smb_fname,
			uid_t uid,
			gid_t gid)
{
	int result;
	DBG_DEBUG("[CEPH] lchown(%p, %s, %d, %d)\n", handle, smb_fname->base_name, uid, gid);
	result = ceph_lchown(handle->data, smb_fname->base_name, uid, gid);
	DBG_DEBUG("[CEPH] lchown(...) = %d\n", result);
	WRAP_RETURN(result);
}

static int cephwrap_chdir(struct vfs_handle_struct *handle,
			const struct smb_filename *smb_fname)
{
	int result = -1;
	DBG_DEBUG("[CEPH] chdir(%p, %s)\n", handle, smb_fname->base_name);
	result = ceph_chdir(handle->data, smb_fname->base_name);
	DBG_DEBUG("[CEPH] chdir(...) = %d\n", result);
	WRAP_RETURN(result);
}

static struct smb_filename *cephwrap_getwd(struct vfs_handle_struct *handle,
			TALLOC_CTX *ctx)
{
	const char *cwd = ceph_getcwd(handle->data);
	DBG_DEBUG("[CEPH] getwd(%p) = %s\n", handle, cwd);
	return synthetic_smb_fname(ctx,
				cwd,
				NULL,
				NULL,
				0);
}

static int strict_allocate_ftruncate(struct vfs_handle_struct *handle, files_struct *fsp, off_t len)
{
	off_t space_to_write;
	int result;
	NTSTATUS status;
	SMB_STRUCT_STAT *pst;

	status = vfs_stat_fsp(fsp);
	if (!NT_STATUS_IS_OK(status)) {
		return -1;
	}
	pst = &fsp->fsp_name->st;

#ifdef S_ISFIFO
	if (S_ISFIFO(pst->st_ex_mode))
		return 0;
#endif

	if (pst->st_ex_size == len)
		return 0;

	/* Shrink - just ftruncate. */
	if (pst->st_ex_size > len) {
		result = ceph_ftruncate(handle->data, fsp->fh->fd, len);
		WRAP_RETURN(result);
	}

	space_to_write = len - pst->st_ex_size;
	result = ceph_fallocate(handle->data, fsp->fh->fd, 0, pst->st_ex_size,
				space_to_write);
	WRAP_RETURN(result);
}

static int cephwrap_ftruncate(struct vfs_handle_struct *handle, files_struct *fsp, off_t len)
{
	int result = -1;

	DBG_DEBUG("[CEPH] ftruncate(%p, %p, %llu\n", handle, fsp, llu(len));

	if (lp_strict_allocate(SNUM(fsp->conn))) {
		return strict_allocate_ftruncate(handle, fsp, len);
	}

	result = ceph_ftruncate(handle->data, fsp->fh->fd, len);
	WRAP_RETURN(result);
}

static int cephwrap_fallocate(struct vfs_handle_struct *handle,
			      struct files_struct *fsp,
			      uint32_t mode,
			      off_t offset,
			      off_t len)
{
	int result;

	DBG_DEBUG("[CEPH] fallocate(%p, %p, %u, %llu, %llu\n",
		  handle, fsp, mode, llu(offset), llu(len));
	/* unsupported mode flags are rejected by libcephfs */
	result = ceph_fallocate(handle->data, fsp->fh->fd, mode, offset, len);
	DBG_DEBUG("[CEPH] fallocate(...) = %d\n", result);
	WRAP_RETURN(result);
}

static bool cephwrap_lock(struct vfs_handle_struct *handle, files_struct *fsp, int op, off_t offset, off_t count, int type)
{
	DBG_DEBUG("[CEPH] lock\n");
	return true;
}

static int cephwrap_kernel_flock(struct vfs_handle_struct *handle, files_struct *fsp,
				uint32_t share_mode, uint32_t access_mask)
{
	DBG_ERR("[CEPH] flock unsupported! Consider setting "
		"\"kernel share modes = no\"\n");

	errno = ENOSYS;
	return -1;
}

static bool cephwrap_getlock(struct vfs_handle_struct *handle, files_struct *fsp, off_t *poffset, off_t *pcount, int *ptype, pid_t *ppid)
{
	DBG_DEBUG("[CEPH] getlock returning false and errno=0\n");

	errno = 0;
	return false;
}

/*
 * We cannot let this fall through to the default, because the file might only
 * be accessible from libceph (which is a user-space client) but the fd might
 * be for some file the kernel knows about.
 */
static int cephwrap_linux_setlease(struct vfs_handle_struct *handle, files_struct *fsp,
				int leasetype)
{
	int result = -1;

	DBG_DEBUG("[CEPH] linux_setlease\n");
	errno = ENOSYS;
	return result;
}

static int cephwrap_symlinkat(struct vfs_handle_struct *handle,
		const char *link_target,
		struct files_struct *dirfsp,
		const struct smb_filename *new_smb_fname)
{
	int result = -1;
	DBG_DEBUG("[CEPH] symlink(%p, %s, %s)\n", handle,
			link_target,
			new_smb_fname->base_name);

	SMB_ASSERT(dirfsp == dirfsp->conn->cwd_fsp);

	result = ceph_symlink(handle->data,
			link_target,
			new_smb_fname->base_name);
	DBG_DEBUG("[CEPH] symlink(...) = %d\n", result);
	WRAP_RETURN(result);
}

static int cephwrap_readlinkat(struct vfs_handle_struct *handle,
		files_struct *dirfsp,
		const struct smb_filename *smb_fname,
		char *buf,
		size_t bufsiz)
{
	int result = -1;
	DBG_DEBUG("[CEPH] readlink(%p, %s, %p, %llu)\n", handle,
			smb_fname->base_name, buf, llu(bufsiz));

	SMB_ASSERT(dirfsp == dirfsp->conn->cwd_fsp);

	result = ceph_readlink(handle->data, smb_fname->base_name, buf, bufsiz);
	DBG_DEBUG("[CEPH] readlink(...) = %d\n", result);
	WRAP_RETURN(result);
}

static int cephwrap_linkat(struct vfs_handle_struct *handle,
		files_struct *srcfsp,
		const struct smb_filename *old_smb_fname,
		files_struct *dstfsp,
		const struct smb_filename *new_smb_fname,
		int flags)
{
	int result = -1;
	DBG_DEBUG("[CEPH] link(%p, %s, %s)\n", handle,
			old_smb_fname->base_name,
			new_smb_fname->base_name);

	SMB_ASSERT(srcfsp == srcfsp->conn->cwd_fsp);
	SMB_ASSERT(dstfsp == dstfsp->conn->cwd_fsp);

	result = ceph_link(handle->data,
				old_smb_fname->base_name,
				new_smb_fname->base_name);
	DBG_DEBUG("[CEPH] link(...) = %d\n", result);
	WRAP_RETURN(result);
}

static int cephwrap_mknodat(struct vfs_handle_struct *handle,
		files_struct *dirfsp,
		const struct smb_filename *smb_fname,
		mode_t mode,
		SMB_DEV_T dev)
{
	int result = -1;
	DBG_DEBUG("[CEPH] mknodat(%p, %s)\n", handle, smb_fname->base_name);
	SMB_ASSERT(dirfsp == dirfsp->conn->cwd_fsp);
	result = ceph_mknod(handle->data, smb_fname->base_name, mode, dev);
	DBG_DEBUG("[CEPH] mknodat(...) = %d\n", result);
	WRAP_RETURN(result);
}

/*
 * This is a simple version of real-path ... a better version is needed to
 * ask libceph about symbolic links.
 */
static struct smb_filename *cephwrap_realpath(struct vfs_handle_struct *handle,
				TALLOC_CTX *ctx,
				const struct smb_filename *smb_fname)
{
	char *result = NULL;
	const char *path = smb_fname->base_name;
	size_t len = strlen(path);
	struct smb_filename *result_fname = NULL;
	int r = -1;

	if (len && (path[0] == '/')) {
		r = asprintf(&result, "%s", path);
	} else if ((len >= 2) && (path[0] == '.') && (path[1] == '/')) {
		if (len == 2) {
			r = asprintf(&result, "%s",
					handle->conn->cwd_fsp->fsp_name->base_name);
		} else {
			r = asprintf(&result, "%s/%s",
					handle->conn->cwd_fsp->fsp_name->base_name, &path[2]);
		}
	} else {
		r = asprintf(&result, "%s/%s",
				handle->conn->cwd_fsp->fsp_name->base_name, path);
	}

	if (r < 0) {
		return NULL;
	}

	DBG_DEBUG("[CEPH] realpath(%p, %s) = %s\n", handle, path, result);
	result_fname = synthetic_smb_fname(ctx,
				result,
				NULL,
				NULL,
				0);
	SAFE_FREE(result);
	return result_fname;
}

static int cephwrap_chflags(struct vfs_handle_struct *handle,
			const struct smb_filename *smb_fname,
			unsigned int flags)
{
	errno = ENOSYS;
	return -1;
}

static int cephwrap_get_real_filename(struct vfs_handle_struct *handle,
				     const char *path,
				     const char *name,
				     TALLOC_CTX *mem_ctx,
				     char **found_name)
{
	/*
	 * Don't fall back to get_real_filename so callers can differentiate
	 * between a full directory scan and an actual case-insensitive stat.
	 */
	errno = EOPNOTSUPP;
	return -1;
}

static const char *cephwrap_connectpath(struct vfs_handle_struct *handle,
				       const struct smb_filename *smb_fname)
{
	return handle->conn->connectpath;
}

/****************************************************************
 Extended attribute operations.
*****************************************************************/

static ssize_t cephwrap_getxattr(struct vfs_handle_struct *handle,
			const struct smb_filename *smb_fname,
			const char *name,
			void *value,
			size_t size)
{
	int ret;
	DBG_DEBUG("[CEPH] getxattr(%p, %s, %s, %p, %llu)\n", handle,
			smb_fname->base_name, name, value, llu(size));
	ret = ceph_getxattr(handle->data,
			smb_fname->base_name, name, value, size);
	DBG_DEBUG("[CEPH] getxattr(...) = %d\n", ret);
	if (ret < 0) {
		WRAP_RETURN(ret);
	}
	return (ssize_t)ret;
}

static ssize_t cephwrap_fgetxattr(struct vfs_handle_struct *handle, struct files_struct *fsp, const char *name, void *value, size_t size)
{
	int ret;
	DBG_DEBUG("[CEPH] fgetxattr(%p, %p, %s, %p, %llu)\n", handle, fsp, name, value, llu(size));
#if LIBCEPHFS_VERSION_CODE >= LIBCEPHFS_VERSION(0, 94, 0)
	ret = ceph_fgetxattr(handle->data, fsp->fh->fd, name, value, size);
#else
	ret = ceph_getxattr(handle->data, fsp->fsp_name->base_name, name, value, size);
#endif
	DBG_DEBUG("[CEPH] fgetxattr(...) = %d\n", ret);
	if (ret < 0) {
		WRAP_RETURN(ret);
	}
	return (ssize_t)ret;
}

static ssize_t cephwrap_listxattr(struct vfs_handle_struct *handle,
			const struct smb_filename *smb_fname,
			char *list,
			size_t size)
{
	int ret;
	DBG_DEBUG("[CEPH] listxattr(%p, %s, %p, %llu)\n", handle,
			smb_fname->base_name, list, llu(size));
	ret = ceph_listxattr(handle->data, smb_fname->base_name, list, size);
	DBG_DEBUG("[CEPH] listxattr(...) = %d\n", ret);
	if (ret < 0) {
		WRAP_RETURN(ret);
	}
	return (ssize_t)ret;
}

static ssize_t cephwrap_flistxattr(struct vfs_handle_struct *handle, struct files_struct *fsp, char *list, size_t size)
{
	int ret;
	DBG_DEBUG("[CEPH] flistxattr(%p, %p, %p, %llu)\n",
		  handle, fsp, list, llu(size));
#if LIBCEPHFS_VERSION_CODE >= LIBCEPHFS_VERSION(0, 94, 0)
	ret = ceph_flistxattr(handle->data, fsp->fh->fd, list, size);
#else
	ret = ceph_listxattr(handle->data, fsp->fsp_name->base_name, list, size);
#endif
	DBG_DEBUG("[CEPH] flistxattr(...) = %d\n", ret);
	if (ret < 0) {
		WRAP_RETURN(ret);
	}
	return (ssize_t)ret;
}

static int cephwrap_removexattr(struct vfs_handle_struct *handle,
				const struct smb_filename *smb_fname,
				const char *name)
{
	int ret;
	DBG_DEBUG("[CEPH] removexattr(%p, %s, %s)\n", handle,
			smb_fname->base_name, name);
	ret = ceph_removexattr(handle->data, smb_fname->base_name, name);
	DBG_DEBUG("[CEPH] removexattr(...) = %d\n", ret);
	WRAP_RETURN(ret);
}

static int cephwrap_fremovexattr(struct vfs_handle_struct *handle, struct files_struct *fsp, const char *name)
{
	int ret;
	DBG_DEBUG("[CEPH] fremovexattr(%p, %p, %s)\n", handle, fsp, name);
#if LIBCEPHFS_VERSION_CODE >= LIBCEPHFS_VERSION(0, 94, 0)
	ret = ceph_fremovexattr(handle->data, fsp->fh->fd, name);
#else
	ret = ceph_removexattr(handle->data, fsp->fsp_name->base_name, name);
#endif
	DBG_DEBUG("[CEPH] fremovexattr(...) = %d\n", ret);
	WRAP_RETURN(ret);
}

static int cephwrap_setxattr(struct vfs_handle_struct *handle,
				const struct smb_filename *smb_fname,
				const char *name,
				const void *value,
				size_t size,
				int flags)
{
	int ret;
	DBG_DEBUG("[CEPH] setxattr(%p, %s, %s, %p, %llu, %d)\n", handle,
			smb_fname->base_name, name, value, llu(size), flags);
	ret = ceph_setxattr(handle->data, smb_fname->base_name,
			name, value, size, flags);
	DBG_DEBUG("[CEPH] setxattr(...) = %d\n", ret);
	WRAP_RETURN(ret);
}

static int cephwrap_fsetxattr(struct vfs_handle_struct *handle, struct files_struct *fsp, const char *name, const void *value, size_t size, int flags)
{
	int ret;
	DBG_DEBUG("[CEPH] fsetxattr(%p, %p, %s, %p, %llu, %d)\n", handle, fsp, name, value, llu(size), flags);
#if LIBCEPHFS_VERSION_CODE >= LIBCEPHFS_VERSION(0, 94, 0)
	ret = ceph_fsetxattr(handle->data, fsp->fh->fd,
			     name, value, size, flags);
#else
	ret = ceph_setxattr(handle->data, fsp->fsp_name->base_name, name, value, size, flags);
#endif
	DBG_DEBUG("[CEPH] fsetxattr(...) = %d\n", ret);
	WRAP_RETURN(ret);
}

static bool cephwrap_aio_force(struct vfs_handle_struct *handle, struct files_struct *fsp)
{

	/*
	 * We do not support AIO yet.
	 */

	DBG_DEBUG("[CEPH] cephwrap_aio_force(%p, %p) = false (errno = ENOTSUP)\n", handle, fsp);
	errno = ENOTSUP;
	return false;
}

static struct vfs_fn_pointers ceph_fns = {
	/* Disk operations */

	.connect_fn = cephwrap_connect,
	.disconnect_fn = cephwrap_disconnect,
	.disk_free_fn = cephwrap_disk_free,
	.get_quota_fn = cephwrap_get_quota,
	.set_quota_fn = cephwrap_set_quota,
	.statvfs_fn = cephwrap_statvfs,
	.fs_capabilities_fn = cephwrap_fs_capabilities,

	/* Directory operations */

	.opendir_fn = cephwrap_opendir,
	.fdopendir_fn = cephwrap_fdopendir,
	.readdir_fn = cephwrap_readdir,
	.seekdir_fn = cephwrap_seekdir,
	.telldir_fn = cephwrap_telldir,
	.rewind_dir_fn = cephwrap_rewinddir,
	.mkdirat_fn = cephwrap_mkdirat,
	.closedir_fn = cephwrap_closedir,

	/* File operations */

	.open_fn = cephwrap_open,
	.close_fn = cephwrap_close,
	.pread_fn = cephwrap_pread,
	.pread_send_fn = cephwrap_pread_send,
	.pread_recv_fn = cephwrap_pread_recv,
	.pwrite_fn = cephwrap_pwrite,
	.pwrite_send_fn = cephwrap_pwrite_send,
	.pwrite_recv_fn = cephwrap_pwrite_recv,
	.lseek_fn = cephwrap_lseek,
	.sendfile_fn = cephwrap_sendfile,
	.recvfile_fn = cephwrap_recvfile,
	.renameat_fn = cephwrap_renameat,
	.fsync_send_fn = cephwrap_fsync_send,
	.fsync_recv_fn = cephwrap_fsync_recv,
	.stat_fn = cephwrap_stat,
	.fstat_fn = cephwrap_fstat,
	.lstat_fn = cephwrap_lstat,
	.unlinkat_fn = cephwrap_unlinkat,
	.chmod_fn = cephwrap_chmod,
	.fchmod_fn = cephwrap_fchmod,
	.fchown_fn = cephwrap_fchown,
	.lchown_fn = cephwrap_lchown,
	.chdir_fn = cephwrap_chdir,
	.getwd_fn = cephwrap_getwd,
	.ntimes_fn = cephwrap_ntimes,
	.ftruncate_fn = cephwrap_ftruncate,
	.fallocate_fn = cephwrap_fallocate,
	.lock_fn = cephwrap_lock,
	.kernel_flock_fn = cephwrap_kernel_flock,
	.linux_setlease_fn = cephwrap_linux_setlease,
	.getlock_fn = cephwrap_getlock,
	.symlinkat_fn = cephwrap_symlinkat,
	.readlinkat_fn = cephwrap_readlinkat,
	.linkat_fn = cephwrap_linkat,
	.mknodat_fn = cephwrap_mknodat,
	.realpath_fn = cephwrap_realpath,
	.chflags_fn = cephwrap_chflags,
	.get_real_filename_fn = cephwrap_get_real_filename,
	.connectpath_fn = cephwrap_connectpath,

	/* EA operations. */
	.getxattr_fn = cephwrap_getxattr,
	.getxattrat_send_fn = vfs_not_implemented_getxattrat_send,
	.getxattrat_recv_fn = vfs_not_implemented_getxattrat_recv,
	.fgetxattr_fn = cephwrap_fgetxattr,
	.listxattr_fn = cephwrap_listxattr,
	.flistxattr_fn = cephwrap_flistxattr,
	.removexattr_fn = cephwrap_removexattr,
	.fremovexattr_fn = cephwrap_fremovexattr,
	.setxattr_fn = cephwrap_setxattr,
	.fsetxattr_fn = cephwrap_fsetxattr,

	/* Posix ACL Operations */
	.sys_acl_get_file_fn = posixacl_xattr_acl_get_file,
	.sys_acl_get_fd_fn = posixacl_xattr_acl_get_fd,
	.sys_acl_blob_get_file_fn = posix_sys_acl_blob_get_file,
	.sys_acl_blob_get_fd_fn = posix_sys_acl_blob_get_fd,
	.sys_acl_set_file_fn = posixacl_xattr_acl_set_file,
	.sys_acl_set_fd_fn = posixacl_xattr_acl_set_fd,
	.sys_acl_delete_def_file_fn = posixacl_xattr_acl_delete_def_file,

	/* aio operations */
	.aio_force_fn = cephwrap_aio_force,
};

static_decl_vfs;
NTSTATUS vfs_ceph_init(TALLOC_CTX *ctx)
{
	return smb_register_vfs(SMB_VFS_INTERFACE_VERSION,
				"ceph", &ceph_fns);
}