summaryrefslogtreecommitdiff
path: root/include/linux/ceph/ceph_fs.h
blob: bc2699feddbeb7d1b29000dd7b51c4888276495d (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
/* SPDX-License-Identifier: GPL-2.0 */
/*
 * ceph_fs.h - Ceph constants and data types to share between kernel and
 * user space.
 *
 * Most types in this file are defined as little-endian, and are
 * primarily intended to describe data structures that pass over the
 * wire or that are stored on disk.
 *
 * LGPL2
 */

#ifndef CEPH_FS_H
#define CEPH_FS_H

#include <linux/ceph/msgr.h>
#include <linux/ceph/rados.h>

/*
 * subprotocol versions.  when specific messages types or high-level
 * protocols change, bump the affected components.  we keep rev
 * internal cluster protocols separately from the public,
 * client-facing protocol.
 */
#define CEPH_OSDC_PROTOCOL   24 /* server/client */
#define CEPH_MDSC_PROTOCOL   32 /* server/client */
#define CEPH_MONC_PROTOCOL   15 /* server/client */


#define CEPH_INO_ROOT   1
#define CEPH_INO_CEPH   2       /* hidden .ceph dir */
#define CEPH_INO_DOTDOT 3	/* used by ceph fuse for parent (..) */

/* arbitrary limit on max # of monitors (cluster of 3 is typical) */
#define CEPH_MAX_MON   31

/*
 * legacy ceph_file_layoute
 */
struct ceph_file_layout_legacy {
	/* file -> object mapping */
	__le32 fl_stripe_unit;     /* stripe unit, in bytes.  must be multiple
				      of page size. */
	__le32 fl_stripe_count;    /* over this many objects */
	__le32 fl_object_size;     /* until objects are this big, then move to
				      new objects */
	__le32 fl_cas_hash;        /* UNUSED.  0 = none; 1 = sha256 */

	/* pg -> disk layout */
	__le32 fl_object_stripe_unit;  /* UNUSED.  for per-object parity, if any */

	/* object -> pg layout */
	__le32 fl_unused;       /* unused; used to be preferred primary for pg (-1 for none) */
	__le32 fl_pg_pool;      /* namespace, crush ruleset, rep level */
} __attribute__ ((packed));

struct ceph_string;
/*
 * ceph_file_layout - describe data layout for a file/inode
 */
struct ceph_file_layout {
	/* file -> object mapping */
	u32 stripe_unit;   /* stripe unit, in bytes */
	u32 stripe_count;  /* over this many objects */
	u32 object_size;   /* until objects are this big */
	s64 pool_id;        /* rados pool id */
	struct ceph_string __rcu *pool_ns; /* rados pool namespace */
};

extern int ceph_file_layout_is_valid(const struct ceph_file_layout *layout);
extern void ceph_file_layout_from_legacy(struct ceph_file_layout *fl,
				struct ceph_file_layout_legacy *legacy);
extern void ceph_file_layout_to_legacy(struct ceph_file_layout *fl,
				struct ceph_file_layout_legacy *legacy);

#define CEPH_MIN_STRIPE_UNIT 65536

struct ceph_dir_layout {
	__u8   dl_dir_hash;   /* see ceph_hash.h for ids */
	__u8   dl_unused1;
	__u16  dl_unused2;
	__u32  dl_unused3;
} __attribute__ ((packed));

/* crypto algorithms */
#define CEPH_CRYPTO_NONE 0x0
#define CEPH_CRYPTO_AES  0x1

#define CEPH_AES_IV "cephsageyudagreg"

/* security/authentication protocols */
#define CEPH_AUTH_UNKNOWN	0x0
#define CEPH_AUTH_NONE	 	0x1
#define CEPH_AUTH_CEPHX	 	0x2

#define CEPH_AUTH_MODE_NONE		0
#define CEPH_AUTH_MODE_AUTHORIZER	1
#define CEPH_AUTH_MODE_MON		10

/* msgr2 protocol modes */
#define CEPH_CON_MODE_UNKNOWN	0x0
#define CEPH_CON_MODE_CRC	0x1
#define CEPH_CON_MODE_SECURE	0x2

#define CEPH_AUTH_UID_DEFAULT ((__u64) -1)

const char *ceph_auth_proto_name(int proto);
const char *ceph_con_mode_name(int mode);

/*********************************************
 * message layer
 */

/*
 * message types
 */

/* misc */
#define CEPH_MSG_SHUTDOWN               1
#define CEPH_MSG_PING                   2

/* client <-> monitor */
#define CEPH_MSG_MON_MAP                4
#define CEPH_MSG_MON_GET_MAP            5
#define CEPH_MSG_STATFS                 13
#define CEPH_MSG_STATFS_REPLY           14
#define CEPH_MSG_MON_SUBSCRIBE          15
#define CEPH_MSG_MON_SUBSCRIBE_ACK      16
#define CEPH_MSG_AUTH			17
#define CEPH_MSG_AUTH_REPLY		18
#define CEPH_MSG_MON_GET_VERSION        19
#define CEPH_MSG_MON_GET_VERSION_REPLY  20

/* client <-> mds */
#define CEPH_MSG_MDS_MAP                21
#define CEPH_MSG_FS_MAP_USER            103

#define CEPH_MSG_CLIENT_SESSION         22
#define CEPH_MSG_CLIENT_RECONNECT       23

#define CEPH_MSG_CLIENT_REQUEST         24
#define CEPH_MSG_CLIENT_REQUEST_FORWARD 25
#define CEPH_MSG_CLIENT_REPLY           26
#define CEPH_MSG_CLIENT_METRICS         29
#define CEPH_MSG_CLIENT_CAPS            0x310
#define CEPH_MSG_CLIENT_LEASE           0x311
#define CEPH_MSG_CLIENT_SNAP            0x312
#define CEPH_MSG_CLIENT_CAPRELEASE      0x313
#define CEPH_MSG_CLIENT_QUOTA           0x314

/* pool ops */
#define CEPH_MSG_POOLOP_REPLY           48
#define CEPH_MSG_POOLOP                 49

/* mon commands */
#define CEPH_MSG_MON_COMMAND            50
#define CEPH_MSG_MON_COMMAND_ACK        51

/* osd */
#define CEPH_MSG_OSD_MAP                41
#define CEPH_MSG_OSD_OP                 42
#define CEPH_MSG_OSD_OPREPLY            43
#define CEPH_MSG_WATCH_NOTIFY           44
#define CEPH_MSG_OSD_BACKOFF            61


/* watch-notify operations */
enum {
	CEPH_WATCH_EVENT_NOTIFY		  = 1, /* notifying watcher */
	CEPH_WATCH_EVENT_NOTIFY_COMPLETE  = 2, /* notifier notified when done */
	CEPH_WATCH_EVENT_DISCONNECT       = 3, /* we were disconnected */
};


struct ceph_mon_request_header {
	__le64 have_version;
	__le16 session_mon;
	__le64 session_mon_tid;
} __attribute__ ((packed));

struct ceph_mon_statfs {
	struct ceph_mon_request_header monhdr;
	struct ceph_fsid fsid;
	__u8 contains_data_pool;
	__le64 data_pool;
} __attribute__ ((packed));

struct ceph_statfs {
	__le64 kb, kb_used, kb_avail;
	__le64 num_objects;
} __attribute__ ((packed));

struct ceph_mon_statfs_reply {
	struct ceph_fsid fsid;
	__le64 version;
	struct ceph_statfs st;
} __attribute__ ((packed));

struct ceph_mon_command {
	struct ceph_mon_request_header monhdr;
	struct ceph_fsid fsid;
	__le32 num_strs;         /* always 1 */
	__le32 str_len;
	char str[];
} __attribute__ ((packed));

struct ceph_osd_getmap {
	struct ceph_mon_request_header monhdr;
	struct ceph_fsid fsid;
	__le32 start;
} __attribute__ ((packed));

struct ceph_mds_getmap {
	struct ceph_mon_request_header monhdr;
	struct ceph_fsid fsid;
} __attribute__ ((packed));

struct ceph_client_mount {
	struct ceph_mon_request_header monhdr;
} __attribute__ ((packed));

#define CEPH_SUBSCRIBE_ONETIME    1  /* i want only 1 update after have */

struct ceph_mon_subscribe_item {
	__le64 start;
	__u8 flags;
} __attribute__ ((packed));

struct ceph_mon_subscribe_ack {
	__le32 duration;         /* seconds */
	struct ceph_fsid fsid;
} __attribute__ ((packed));

#define CEPH_FS_CLUSTER_ID_NONE  -1

/*
 * mdsmap flags
 */
#define CEPH_MDSMAP_DOWN    (1<<0)  /* cluster deliberately down */

/*
 * mds states
 *   > 0 -> in
 *  <= 0 -> out
 */
#define CEPH_MDS_STATE_DNE          0  /* down, does not exist. */
#define CEPH_MDS_STATE_STOPPED     -1  /* down, once existed, but no subtrees.
					  empty log. */
#define CEPH_MDS_STATE_BOOT        -4  /* up, boot announcement. */
#define CEPH_MDS_STATE_STANDBY     -5  /* up, idle.  waiting for assignment. */
#define CEPH_MDS_STATE_CREATING    -6  /* up, creating MDS instance. */
#define CEPH_MDS_STATE_STARTING    -7  /* up, starting previously stopped mds */
#define CEPH_MDS_STATE_STANDBY_REPLAY -8 /* up, tailing active node's journal */
#define CEPH_MDS_STATE_REPLAYONCE   -9 /* up, replaying an active node's journal */

#define CEPH_MDS_STATE_REPLAY       8  /* up, replaying journal. */
#define CEPH_MDS_STATE_RESOLVE      9  /* up, disambiguating distributed
					  operations (import, rename, etc.) */
#define CEPH_MDS_STATE_RECONNECT    10 /* up, reconnect to clients */
#define CEPH_MDS_STATE_REJOIN       11 /* up, rejoining distributed cache */
#define CEPH_MDS_STATE_CLIENTREPLAY 12 /* up, replaying client operations */
#define CEPH_MDS_STATE_ACTIVE       13 /* up, active */
#define CEPH_MDS_STATE_STOPPING     14 /* up, but exporting metadata */

extern const char *ceph_mds_state_name(int s);


/*
 * metadata lock types.
 *  - these are bitmasks.. we can compose them
 *  - they also define the lock ordering by the MDS
 *  - a few of these are internal to the mds
 */
#define CEPH_LOCK_DVERSION    1
#define CEPH_LOCK_DN          2
#define CEPH_LOCK_ISNAP       16
#define CEPH_LOCK_IVERSION    32    /* mds internal */
#define CEPH_LOCK_IFILE       64
#define CEPH_LOCK_IAUTH       128
#define CEPH_LOCK_ILINK       256
#define CEPH_LOCK_IDFT        512   /* dir frag tree */
#define CEPH_LOCK_INEST       1024  /* mds internal */
#define CEPH_LOCK_IXATTR      2048
#define CEPH_LOCK_IFLOCK      4096  /* advisory file locks */
#define CEPH_LOCK_INO         8192  /* immutable inode bits; not a lock */
#define CEPH_LOCK_IPOLICY     16384 /* policy lock on dirs. MDS internal */

/* client_session ops */
enum {
	CEPH_SESSION_REQUEST_OPEN,
	CEPH_SESSION_OPEN,
	CEPH_SESSION_REQUEST_CLOSE,
	CEPH_SESSION_CLOSE,
	CEPH_SESSION_REQUEST_RENEWCAPS,
	CEPH_SESSION_RENEWCAPS,
	CEPH_SESSION_STALE,
	CEPH_SESSION_RECALL_STATE,
	CEPH_SESSION_FLUSHMSG,
	CEPH_SESSION_FLUSHMSG_ACK,
	CEPH_SESSION_FORCE_RO,
	CEPH_SESSION_REJECT,
	CEPH_SESSION_REQUEST_FLUSH_MDLOG,
};

extern const char *ceph_session_op_name(int op);

struct ceph_mds_session_head {
	__le32 op;
	__le64 seq;
	struct ceph_timespec stamp;
	__le32 max_caps, max_leases;
} __attribute__ ((packed));

/* client_request */
/*
 * metadata ops.
 *  & 0x001000 -> write op
 *  & 0x010000 -> follow symlink (e.g. stat(), not lstat()).
 &  & 0x100000 -> use weird ino/path trace
 */
#define CEPH_MDS_OP_WRITE        0x001000
enum {
	CEPH_MDS_OP_LOOKUP     = 0x00100,
	CEPH_MDS_OP_GETATTR    = 0x00101,
	CEPH_MDS_OP_LOOKUPHASH = 0x00102,
	CEPH_MDS_OP_LOOKUPPARENT = 0x00103,
	CEPH_MDS_OP_LOOKUPINO  = 0x00104,
	CEPH_MDS_OP_LOOKUPNAME = 0x00105,

	CEPH_MDS_OP_SETXATTR   = 0x01105,
	CEPH_MDS_OP_RMXATTR    = 0x01106,
	CEPH_MDS_OP_SETLAYOUT  = 0x01107,
	CEPH_MDS_OP_SETATTR    = 0x01108,
	CEPH_MDS_OP_SETFILELOCK= 0x01109,
	CEPH_MDS_OP_GETFILELOCK= 0x00110,
	CEPH_MDS_OP_SETDIRLAYOUT=0x0110a,

	CEPH_MDS_OP_MKNOD      = 0x01201,
	CEPH_MDS_OP_LINK       = 0x01202,
	CEPH_MDS_OP_UNLINK     = 0x01203,
	CEPH_MDS_OP_RENAME     = 0x01204,
	CEPH_MDS_OP_MKDIR      = 0x01220,
	CEPH_MDS_OP_RMDIR      = 0x01221,
	CEPH_MDS_OP_SYMLINK    = 0x01222,

	CEPH_MDS_OP_CREATE     = 0x01301,
	CEPH_MDS_OP_OPEN       = 0x00302,
	CEPH_MDS_OP_READDIR    = 0x00305,

	CEPH_MDS_OP_LOOKUPSNAP = 0x00400,
	CEPH_MDS_OP_MKSNAP     = 0x01400,
	CEPH_MDS_OP_RMSNAP     = 0x01401,
	CEPH_MDS_OP_LSSNAP     = 0x00402,
	CEPH_MDS_OP_RENAMESNAP = 0x01403,
};

extern const char *ceph_mds_op_name(int op);


#define CEPH_SETATTR_MODE   1
#define CEPH_SETATTR_UID    2
#define CEPH_SETATTR_GID    4
#define CEPH_SETATTR_MTIME  8
#define CEPH_SETATTR_ATIME 16
#define CEPH_SETATTR_SIZE  32
#define CEPH_SETATTR_CTIME 64

/*
 * Ceph setxattr request flags.
 */
#define CEPH_XATTR_CREATE  (1 << 0)
#define CEPH_XATTR_REPLACE (1 << 1)
#define CEPH_XATTR_REMOVE  (1 << 31)

/*
 * readdir request flags;
 */
#define CEPH_READDIR_REPLY_BITFLAGS	(1<<0)

/*
 * readdir reply flags.
 */
#define CEPH_READDIR_FRAG_END		(1<<0)
#define CEPH_READDIR_FRAG_COMPLETE	(1<<8)
#define CEPH_READDIR_HASH_ORDER		(1<<9)
#define CEPH_READDIR_OFFSET_HASH	(1<<10)

/*
 * open request flags
 */
#define CEPH_O_RDONLY		00000000
#define CEPH_O_WRONLY		00000001
#define CEPH_O_RDWR		00000002
#define CEPH_O_CREAT		00000100
#define CEPH_O_EXCL		00000200
#define CEPH_O_TRUNC		00001000
#define CEPH_O_DIRECTORY	00200000
#define CEPH_O_NOFOLLOW		00400000

union ceph_mds_request_args {
	struct {
		__le32 mask;                 /* CEPH_CAP_* */
	} __attribute__ ((packed)) getattr;
	struct {
		__le32 mode;
		__le32 uid;
		__le32 gid;
		struct ceph_timespec mtime;
		struct ceph_timespec atime;
		__le64 size, old_size;       /* old_size needed by truncate */
		__le32 mask;                 /* CEPH_SETATTR_* */
	} __attribute__ ((packed)) setattr;
	struct {
		__le32 frag;                 /* which dir fragment */
		__le32 max_entries;          /* how many dentries to grab */
		__le32 max_bytes;
		__le16 flags;
		__le32 offset_hash;
	} __attribute__ ((packed)) readdir;
	struct {
		__le32 mode;
		__le32 rdev;
	} __attribute__ ((packed)) mknod;
	struct {
		__le32 mode;
	} __attribute__ ((packed)) mkdir;
	struct {
		__le32 flags;
		__le32 mode;
		__le32 stripe_unit;          /* layout for newly created file */
		__le32 stripe_count;         /* ... */
		__le32 object_size;
		__le32 file_replication;
               __le32 mask;                 /* CEPH_CAP_* */
               __le32 old_size;
	} __attribute__ ((packed)) open;
	struct {
		__le32 flags;
		__le32 osdmap_epoch; /* used for setting file/dir layouts */
	} __attribute__ ((packed)) setxattr;
	struct {
		struct ceph_file_layout_legacy layout;
	} __attribute__ ((packed)) setlayout;
	struct {
		__u8 rule; /* currently fcntl or flock */
		__u8 type; /* shared, exclusive, remove*/
		__le64 owner; /* owner of the lock */
		__le64 pid; /* process id requesting the lock */
		__le64 start; /* initial location to lock */
		__le64 length; /* num bytes to lock from start */
		__u8 wait; /* will caller wait for lock to become available? */
	} __attribute__ ((packed)) filelock_change;
	struct {
		__le32 mask;                 /* CEPH_CAP_* */
		__le64 snapid;
		__le64 parent;
		__le32 hash;
	} __attribute__ ((packed)) lookupino;
} __attribute__ ((packed));

union ceph_mds_request_args_ext {
	union ceph_mds_request_args old;
	struct {
		__le32 mode;
		__le32 uid;
		__le32 gid;
		struct ceph_timespec mtime;
		struct ceph_timespec atime;
		__le64 size, old_size;       /* old_size needed by truncate */
		__le32 mask;                 /* CEPH_SETATTR_* */
		struct ceph_timespec btime;
	} __attribute__ ((packed)) setattr_ext;
};

#define CEPH_MDS_FLAG_REPLAY		1 /* this is a replayed op */
#define CEPH_MDS_FLAG_WANT_DENTRY	2 /* want dentry in reply */
#define CEPH_MDS_FLAG_ASYNC		4 /* request is asynchronous */

struct ceph_mds_request_head_old {
	__le64 oldest_client_tid;
	__le32 mdsmap_epoch;           /* on client */
	__le32 flags;                  /* CEPH_MDS_FLAG_* */
	__u8 num_retry, num_fwd;       /* count retry, fwd attempts */
	__le16 num_releases;           /* # include cap/lease release records */
	__le32 op;                     /* mds op code */
	__le32 caller_uid, caller_gid;
	__le64 ino;                    /* use this ino for openc, mkdir, mknod,
					  etc. (if replaying) */
	union ceph_mds_request_args args;
} __attribute__ ((packed));

#define CEPH_MDS_REQUEST_HEAD_VERSION  1

struct ceph_mds_request_head {
	__le16 version;                /* struct version */
	__le64 oldest_client_tid;
	__le32 mdsmap_epoch;           /* on client */
	__le32 flags;                  /* CEPH_MDS_FLAG_* */
	__u8 num_retry, num_fwd;       /* count retry, fwd attempts */
	__le16 num_releases;           /* # include cap/lease release records */
	__le32 op;                     /* mds op code */
	__le32 caller_uid, caller_gid;
	__le64 ino;                    /* use this ino for openc, mkdir, mknod,
					  etc. (if replaying) */
	union ceph_mds_request_args_ext args;
} __attribute__ ((packed));

/* cap/lease release record */
struct ceph_mds_request_release {
	__le64 ino, cap_id;            /* ino and unique cap id */
	__le32 caps, wanted;           /* new issued, wanted */
	__le32 seq, issue_seq, mseq;
	__le32 dname_seq;              /* if releasing a dentry lease, a */
	__le32 dname_len;              /* string follows. */
} __attribute__ ((packed));

/* client reply */
struct ceph_mds_reply_head {
	__le32 op;
	__le32 result;
	__le32 mdsmap_epoch;
	__u8 safe;                     /* true if committed to disk */
	__u8 is_dentry, is_target;     /* true if dentry, target inode records
					  are included with reply */
} __attribute__ ((packed));

/* one for each node split */
struct ceph_frag_tree_split {
	__le32 frag;                   /* this frag splits... */
	__le32 by;                     /* ...by this many bits */
} __attribute__ ((packed));

struct ceph_frag_tree_head {
	__le32 nsplits;                /* num ceph_frag_tree_split records */
	struct ceph_frag_tree_split splits[];
} __attribute__ ((packed));

/* capability issue, for bundling with mds reply */
struct ceph_mds_reply_cap {
	__le32 caps, wanted;           /* caps issued, wanted */
	__le64 cap_id;
	__le32 seq, mseq;
	__le64 realm;                  /* snap realm */
	__u8 flags;                    /* CEPH_CAP_FLAG_* */
} __attribute__ ((packed));

#define CEPH_CAP_FLAG_AUTH	(1 << 0)  /* cap is issued by auth mds */
#define CEPH_CAP_FLAG_RELEASE	(1 << 1)  /* release the cap */

/* inode record, for bundling with mds reply */
struct ceph_mds_reply_inode {
	__le64 ino;
	__le64 snapid;
	__le32 rdev;
	__le64 version;                /* inode version */
	__le64 xattr_version;          /* version for xattr blob */
	struct ceph_mds_reply_cap cap; /* caps issued for this inode */
	struct ceph_file_layout_legacy layout;
	struct ceph_timespec ctime, mtime, atime;
	__le32 time_warp_seq;
	__le64 size, max_size, truncate_size;
	__le32 truncate_seq;
	__le32 mode, uid, gid;
	__le32 nlink;
	__le64 files, subdirs, rbytes, rfiles, rsubdirs;  /* dir stats */
	struct ceph_timespec rctime;
	struct ceph_frag_tree_head fragtree;  /* (must be at end of struct) */
} __attribute__ ((packed));
/* followed by frag array, symlink string, dir layout, xattr blob */

/* reply_lease follows dname, and reply_inode */
struct ceph_mds_reply_lease {
	__le16 mask;            /* lease type(s) */
	__le32 duration_ms;     /* lease duration */
	__le32 seq;
} __attribute__ ((packed));

#define CEPH_LEASE_VALID        (1 | 2) /* old and new bit values */
#define CEPH_LEASE_PRIMARY_LINK 4       /* primary linkage */

struct ceph_mds_reply_dirfrag {
	__le32 frag;            /* fragment */
	__le32 auth;            /* auth mds, if this is a delegation point */
	__le32 ndist;           /* number of mds' this is replicated on */
	__le32 dist[];
} __attribute__ ((packed));

#define CEPH_LOCK_FCNTL		1
#define CEPH_LOCK_FLOCK		2
#define CEPH_LOCK_FCNTL_INTR    3
#define CEPH_LOCK_FLOCK_INTR    4


#define CEPH_LOCK_SHARED   1
#define CEPH_LOCK_EXCL     2
#define CEPH_LOCK_UNLOCK   4

struct ceph_filelock {
	__le64 start;/* file offset to start lock at */
	__le64 length; /* num bytes to lock; 0 for all following start */
	__le64 client; /* which client holds the lock */
	__le64 owner; /* owner the lock */
	__le64 pid; /* process id holding the lock on the client */
	__u8 type; /* shared lock, exclusive lock, or unlock */
} __attribute__ ((packed));


/* file access modes */
#define CEPH_FILE_MODE_PIN        0
#define CEPH_FILE_MODE_RD         1
#define CEPH_FILE_MODE_WR         2
#define CEPH_FILE_MODE_RDWR       3  /* RD | WR */
#define CEPH_FILE_MODE_LAZY       4  /* lazy io */
#define CEPH_FILE_MODE_BITS       4
#define CEPH_FILE_MODE_MASK       ((1 << CEPH_FILE_MODE_BITS) - 1)

int ceph_flags_to_mode(int flags);

#define CEPH_INLINE_NONE	((__u64)-1)

/* capability bits */
#define CEPH_CAP_PIN         1  /* no specific capabilities beyond the pin */

/* generic cap bits */
#define CEPH_CAP_GSHARED     1  /* client can reads */
#define CEPH_CAP_GEXCL       2  /* client can read and update */
#define CEPH_CAP_GCACHE      4  /* (file) client can cache reads */
#define CEPH_CAP_GRD         8  /* (file) client can read */
#define CEPH_CAP_GWR        16  /* (file) client can write */
#define CEPH_CAP_GBUFFER    32  /* (file) client can buffer writes */
#define CEPH_CAP_GWREXTEND  64  /* (file) client can extend EOF */
#define CEPH_CAP_GLAZYIO   128  /* (file) client can perform lazy io */

#define CEPH_CAP_SIMPLE_BITS  2
#define CEPH_CAP_FILE_BITS    8

/* per-lock shift */
#define CEPH_CAP_SAUTH      2
#define CEPH_CAP_SLINK      4
#define CEPH_CAP_SXATTR     6
#define CEPH_CAP_SFILE      8
#define CEPH_CAP_SFLOCK    20

#define CEPH_CAP_BITS      22

/* composed values */
#define CEPH_CAP_AUTH_SHARED  (CEPH_CAP_GSHARED  << CEPH_CAP_SAUTH)
#define CEPH_CAP_AUTH_EXCL     (CEPH_CAP_GEXCL     << CEPH_CAP_SAUTH)
#define CEPH_CAP_LINK_SHARED  (CEPH_CAP_GSHARED  << CEPH_CAP_SLINK)
#define CEPH_CAP_LINK_EXCL     (CEPH_CAP_GEXCL     << CEPH_CAP_SLINK)
#define CEPH_CAP_XATTR_SHARED (CEPH_CAP_GSHARED  << CEPH_CAP_SXATTR)
#define CEPH_CAP_XATTR_EXCL    (CEPH_CAP_GEXCL     << CEPH_CAP_SXATTR)
#define CEPH_CAP_FILE(x)    (x << CEPH_CAP_SFILE)
#define CEPH_CAP_FILE_SHARED   (CEPH_CAP_GSHARED   << CEPH_CAP_SFILE)
#define CEPH_CAP_FILE_EXCL     (CEPH_CAP_GEXCL     << CEPH_CAP_SFILE)
#define CEPH_CAP_FILE_CACHE    (CEPH_CAP_GCACHE    << CEPH_CAP_SFILE)
#define CEPH_CAP_FILE_RD       (CEPH_CAP_GRD       << CEPH_CAP_SFILE)
#define CEPH_CAP_FILE_WR       (CEPH_CAP_GWR       << CEPH_CAP_SFILE)
#define CEPH_CAP_FILE_BUFFER   (CEPH_CAP_GBUFFER   << CEPH_CAP_SFILE)
#define CEPH_CAP_FILE_WREXTEND (CEPH_CAP_GWREXTEND << CEPH_CAP_SFILE)
#define CEPH_CAP_FILE_LAZYIO   (CEPH_CAP_GLAZYIO   << CEPH_CAP_SFILE)
#define CEPH_CAP_FLOCK_SHARED  (CEPH_CAP_GSHARED   << CEPH_CAP_SFLOCK)
#define CEPH_CAP_FLOCK_EXCL    (CEPH_CAP_GEXCL     << CEPH_CAP_SFLOCK)


/* cap masks (for getattr) */
#define CEPH_STAT_CAP_INODE    CEPH_CAP_PIN
#define CEPH_STAT_CAP_TYPE     CEPH_CAP_PIN  /* mode >> 12 */
#define CEPH_STAT_CAP_SYMLINK  CEPH_CAP_PIN
#define CEPH_STAT_CAP_UID      CEPH_CAP_AUTH_SHARED
#define CEPH_STAT_CAP_GID      CEPH_CAP_AUTH_SHARED
#define CEPH_STAT_CAP_MODE     CEPH_CAP_AUTH_SHARED
#define CEPH_STAT_CAP_NLINK    CEPH_CAP_LINK_SHARED
#define CEPH_STAT_CAP_LAYOUT   CEPH_CAP_FILE_SHARED
#define CEPH_STAT_CAP_MTIME    CEPH_CAP_FILE_SHARED
#define CEPH_STAT_CAP_SIZE     CEPH_CAP_FILE_SHARED
#define CEPH_STAT_CAP_ATIME    CEPH_CAP_FILE_SHARED  /* fixme */
#define CEPH_STAT_CAP_XATTR    CEPH_CAP_XATTR_SHARED
#define CEPH_STAT_CAP_INODE_ALL (CEPH_CAP_PIN |			\
				 CEPH_CAP_AUTH_SHARED |	\
				 CEPH_CAP_LINK_SHARED |	\
				 CEPH_CAP_FILE_SHARED |	\
				 CEPH_CAP_XATTR_SHARED)
#define CEPH_STAT_CAP_INLINE_DATA (CEPH_CAP_FILE_SHARED | \
				   CEPH_CAP_FILE_RD)
#define CEPH_STAT_RSTAT CEPH_CAP_FILE_WREXTEND

#define CEPH_CAP_ANY_SHARED (CEPH_CAP_AUTH_SHARED |			\
			      CEPH_CAP_LINK_SHARED |			\
			      CEPH_CAP_XATTR_SHARED |			\
			      CEPH_CAP_FILE_SHARED)
#define CEPH_CAP_ANY_RD   (CEPH_CAP_ANY_SHARED | CEPH_CAP_FILE_RD |	\
			   CEPH_CAP_FILE_CACHE)

#define CEPH_CAP_ANY_EXCL (CEPH_CAP_AUTH_EXCL |		\
			   CEPH_CAP_LINK_EXCL |		\
			   CEPH_CAP_XATTR_EXCL |	\
			   CEPH_CAP_FILE_EXCL)
#define CEPH_CAP_ANY_FILE_RD (CEPH_CAP_FILE_RD | CEPH_CAP_FILE_CACHE | \
			      CEPH_CAP_FILE_SHARED)
#define CEPH_CAP_ANY_FILE_WR (CEPH_CAP_FILE_WR | CEPH_CAP_FILE_BUFFER |	\
			      CEPH_CAP_FILE_EXCL)
#define CEPH_CAP_ANY_WR   (CEPH_CAP_ANY_EXCL | CEPH_CAP_ANY_FILE_WR)
#define CEPH_CAP_ANY      (CEPH_CAP_ANY_RD | CEPH_CAP_ANY_EXCL | \
			   CEPH_CAP_ANY_FILE_WR | CEPH_CAP_FILE_LAZYIO | \
			   CEPH_CAP_PIN)
#define CEPH_CAP_ALL_FILE (CEPH_CAP_PIN | CEPH_CAP_ANY_SHARED | \
			   CEPH_CAP_AUTH_EXCL | CEPH_CAP_XATTR_EXCL | \
			   CEPH_CAP_ANY_FILE_RD | CEPH_CAP_ANY_FILE_WR)

#define CEPH_CAP_LOCKS (CEPH_LOCK_IFILE | CEPH_LOCK_IAUTH | CEPH_LOCK_ILINK | \
			CEPH_LOCK_IXATTR)

/* cap masks async dir operations */
#define CEPH_CAP_DIR_CREATE	CEPH_CAP_FILE_CACHE
#define CEPH_CAP_DIR_UNLINK	CEPH_CAP_FILE_RD
#define CEPH_CAP_ANY_DIR_OPS	(CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_RD | \
				 CEPH_CAP_FILE_WREXTEND | CEPH_CAP_FILE_LAZYIO)

int ceph_caps_for_mode(int mode);

enum {
	CEPH_CAP_OP_GRANT,         /* mds->client grant */
	CEPH_CAP_OP_REVOKE,        /* mds->client revoke */
	CEPH_CAP_OP_TRUNC,         /* mds->client trunc notify */
	CEPH_CAP_OP_EXPORT,        /* mds has exported the cap */
	CEPH_CAP_OP_IMPORT,        /* mds has imported the cap */
	CEPH_CAP_OP_UPDATE,        /* client->mds update */
	CEPH_CAP_OP_DROP,          /* client->mds drop cap bits */
	CEPH_CAP_OP_FLUSH,         /* client->mds cap writeback */
	CEPH_CAP_OP_FLUSH_ACK,     /* mds->client flushed */
	CEPH_CAP_OP_FLUSHSNAP,     /* client->mds flush snapped metadata */
	CEPH_CAP_OP_FLUSHSNAP_ACK, /* mds->client flushed snapped metadata */
	CEPH_CAP_OP_RELEASE,       /* client->mds release (clean) cap */
	CEPH_CAP_OP_RENEW,         /* client->mds renewal request */
};

extern const char *ceph_cap_op_name(int op);

/* flags field in client cap messages (version >= 10) */
#define CEPH_CLIENT_CAPS_SYNC			(1<<0)
#define CEPH_CLIENT_CAPS_NO_CAPSNAP		(1<<1)
#define CEPH_CLIENT_CAPS_PENDING_CAPSNAP	(1<<2)

/*
 * caps message, used for capability callbacks, acks, requests, etc.
 */
struct ceph_mds_caps {
	__le32 op;                  /* CEPH_CAP_OP_* */
	__le64 ino, realm;
	__le64 cap_id;
	__le32 seq, issue_seq;
	__le32 caps, wanted, dirty; /* latest issued/wanted/dirty */
	__le32 migrate_seq;
	__le64 snap_follows;
	__le32 snap_trace_len;

	/* authlock */
	__le32 uid, gid, mode;

	/* linklock */
	__le32 nlink;

	/* xattrlock */
	__le32 xattr_len;
	__le64 xattr_version;

	/* filelock */
	__le64 size, max_size, truncate_size;
	__le32 truncate_seq;
	struct ceph_timespec mtime, atime, ctime;
	struct ceph_file_layout_legacy layout;
	__le32 time_warp_seq;
} __attribute__ ((packed));

struct ceph_mds_cap_peer {
	__le64 cap_id;
	__le32 seq;
	__le32 mseq;
	__le32 mds;
	__u8   flags;
} __attribute__ ((packed));

/* cap release msg head */
struct ceph_mds_cap_release {
	__le32 num;                /* number of cap_items that follow */
} __attribute__ ((packed));

struct ceph_mds_cap_item {
	__le64 ino;
	__le64 cap_id;
	__le32 migrate_seq, seq;
} __attribute__ ((packed));

#define CEPH_MDS_LEASE_REVOKE           1  /*    mds  -> client */
#define CEPH_MDS_LEASE_RELEASE          2  /* client  -> mds    */
#define CEPH_MDS_LEASE_RENEW            3  /* client <-> mds    */
#define CEPH_MDS_LEASE_REVOKE_ACK       4  /* client  -> mds    */

extern const char *ceph_lease_op_name(int o);

/* lease msg header */
struct ceph_mds_lease {
	__u8 action;            /* CEPH_MDS_LEASE_* */
	__le16 mask;            /* which lease */
	__le64 ino;
	__le64 first, last;     /* snap range */
	__le32 seq;
	__le32 duration_ms;     /* duration of renewal */
} __attribute__ ((packed));
/* followed by a __le32+string for dname */

/* client reconnect */
struct ceph_mds_cap_reconnect {
	__le64 cap_id;
	__le32 wanted;
	__le32 issued;
	__le64 snaprealm;
	__le64 pathbase;        /* base ino for our path to this ino */
	__le32 flock_len;       /* size of flock state blob, if any */
} __attribute__ ((packed));
/* followed by flock blob */

struct ceph_mds_cap_reconnect_v1 {
	__le64 cap_id;
	__le32 wanted;
	__le32 issued;
	__le64 size;
	struct ceph_timespec mtime, atime;
	__le64 snaprealm;
	__le64 pathbase;        /* base ino for our path to this ino */
} __attribute__ ((packed));

struct ceph_mds_snaprealm_reconnect {
	__le64 ino;     /* snap realm base */
	__le64 seq;     /* snap seq for this snap realm */
	__le64 parent;  /* parent realm */
} __attribute__ ((packed));

/*
 * snaps
 */
enum {
	CEPH_SNAP_OP_UPDATE,  /* CREATE or DESTROY */
	CEPH_SNAP_OP_CREATE,
	CEPH_SNAP_OP_DESTROY,
	CEPH_SNAP_OP_SPLIT,
};

extern const char *ceph_snap_op_name(int o);

/* snap msg header */
struct ceph_mds_snap_head {
	__le32 op;                /* CEPH_SNAP_OP_* */
	__le64 split;             /* ino to split off, if any */
	__le32 num_split_inos;    /* # inos belonging to new child realm */
	__le32 num_split_realms;  /* # child realms udner new child realm */
	__le32 trace_len;         /* size of snap trace blob */
} __attribute__ ((packed));
/* followed by split ino list, then split realms, then the trace blob */

/*
 * encode info about a snaprealm, as viewed by a client
 */
struct ceph_mds_snap_realm {
	__le64 ino;           /* ino */
	__le64 created;       /* snap: when created */
	__le64 parent;        /* ino: parent realm */
	__le64 parent_since;  /* snap: same parent since */
	__le64 seq;           /* snap: version */
	__le32 num_snaps;
	__le32 num_prior_parent_snaps;
} __attribute__ ((packed));
/* followed by my snap list, then prior parent snap list */

/*
 * quotas
 */
struct ceph_mds_quota {
	__le64 ino;		/* ino */
	struct ceph_timespec rctime;
	__le64 rbytes;		/* dir stats */
	__le64 rfiles;
	__le64 rsubdirs;
	__u8 struct_v;		/* compat */
	__u8 struct_compat;
	__le32 struct_len;
	__le64 max_bytes;	/* quota max. bytes */
	__le64 max_files;	/* quota max. files */
} __attribute__ ((packed));

#endif