summaryrefslogtreecommitdiff
path: root/fs/ceph/super.h
blob: 6e817bf1337c6539ef7ccf3341f7e633fcbf93bd (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
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _FS_CEPH_SUPER_H
#define _FS_CEPH_SUPER_H

#include <linux/ceph/ceph_debug.h>
#include <linux/ceph/osd_client.h>

#include <asm/unaligned.h>
#include <linux/backing-dev.h>
#include <linux/completion.h>
#include <linux/exportfs.h>
#include <linux/fs.h>
#include <linux/mempool.h>
#include <linux/pagemap.h>
#include <linux/wait.h>
#include <linux/writeback.h>
#include <linux/slab.h>
#include <linux/posix_acl.h>
#include <linux/refcount.h>
#include <linux/security.h>
#include <linux/netfs.h>
#include <linux/fscache.h>
#include <linux/hashtable.h>

#include <linux/ceph/libceph.h>
#include "crypto.h"

/* large granularity for statfs utilization stats to facilitate
 * large volume sizes on 32-bit machines. */
#define CEPH_BLOCK_SHIFT   22  /* 4 MB */
#define CEPH_BLOCK         (1 << CEPH_BLOCK_SHIFT)
#define CEPH_4K_BLOCK_SHIFT 12  /* 4 KB */

#define CEPH_MOUNT_OPT_CLEANRECOVER    (1<<1) /* auto reonnect (clean mode) after blocklisted */
#define CEPH_MOUNT_OPT_DIRSTAT         (1<<4) /* `cat dirname` for stats */
#define CEPH_MOUNT_OPT_RBYTES          (1<<5) /* dir st_bytes = rbytes */
#define CEPH_MOUNT_OPT_NOASYNCREADDIR  (1<<7) /* no dcache readdir */
#define CEPH_MOUNT_OPT_INO32           (1<<8) /* 32 bit inos */
#define CEPH_MOUNT_OPT_DCACHE          (1<<9) /* use dcache for readdir etc */
#define CEPH_MOUNT_OPT_FSCACHE         (1<<10) /* use fscache */
#define CEPH_MOUNT_OPT_NOPOOLPERM      (1<<11) /* no pool permission check */
#define CEPH_MOUNT_OPT_MOUNTWAIT       (1<<12) /* mount waits if no mds is up */
#define CEPH_MOUNT_OPT_NOQUOTADF       (1<<13) /* no root dir quota in statfs */
#define CEPH_MOUNT_OPT_NOCOPYFROM      (1<<14) /* don't use RADOS 'copy-from' op */
#define CEPH_MOUNT_OPT_ASYNC_DIROPS    (1<<15) /* allow async directory ops */
#define CEPH_MOUNT_OPT_NOPAGECACHE     (1<<16) /* bypass pagecache altogether */
#define CEPH_MOUNT_OPT_SPARSEREAD      (1<<17) /* always do sparse reads */

#define CEPH_MOUNT_OPT_DEFAULT			\
	(CEPH_MOUNT_OPT_DCACHE |		\
	 CEPH_MOUNT_OPT_NOCOPYFROM |		\
	 CEPH_MOUNT_OPT_ASYNC_DIROPS)

#define ceph_set_mount_opt(fsc, opt) \
	(fsc)->mount_options->flags |= CEPH_MOUNT_OPT_##opt
#define ceph_clear_mount_opt(fsc, opt) \
	(fsc)->mount_options->flags &= ~CEPH_MOUNT_OPT_##opt
#define ceph_test_mount_opt(fsc, opt) \
	(!!((fsc)->mount_options->flags & CEPH_MOUNT_OPT_##opt))

/* max size of osd read request, limited by libceph */
#define CEPH_MAX_READ_SIZE              CEPH_MSG_MAX_DATA_LEN
/* osd has a configurable limitaion of max write size.
 * CEPH_MSG_MAX_DATA_LEN should be small enough. */
#define CEPH_MAX_WRITE_SIZE		CEPH_MSG_MAX_DATA_LEN
#define CEPH_RASIZE_DEFAULT             (8192*1024)    /* max readahead */
#define CEPH_MAX_READDIR_DEFAULT        1024
#define CEPH_MAX_READDIR_BYTES_DEFAULT  (512*1024)
#define CEPH_SNAPDIRNAME_DEFAULT        ".snap"

/*
 * Delay telling the MDS we no longer want caps, in case we reopen
 * the file.  Delay a minimum amount of time, even if we send a cap
 * message for some other reason.  Otherwise, take the oppotunity to
 * update the mds to avoid sending another message later.
 */
#define CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT      5  /* cap release delay */
#define CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT     60  /* cap release delay */

struct ceph_mount_options {
	unsigned int flags;

	unsigned int wsize;            /* max write size */
	unsigned int rsize;            /* max read size */
	unsigned int rasize;           /* max readahead */
	unsigned int congestion_kb;    /* max writeback in flight */
	unsigned int caps_wanted_delay_min, caps_wanted_delay_max;
	int caps_max;
	unsigned int max_readdir;       /* max readdir result (entries) */
	unsigned int max_readdir_bytes; /* max readdir result (bytes) */

	bool new_dev_syntax;

	/*
	 * everything above this point can be memcmp'd; everything below
	 * is handled in compare_mount_options()
	 */

	char *snapdir_name;   /* default ".snap" */
	char *mds_namespace;  /* default NULL */
	char *server_path;    /* default NULL (means "/") */
	char *fscache_uniq;   /* default NULL */
	char *mon_addr;
	struct fscrypt_dummy_policy dummy_enc_policy;
};

/* mount state */
enum {
	CEPH_MOUNT_MOUNTING,
	CEPH_MOUNT_MOUNTED,
	CEPH_MOUNT_UNMOUNTING,
	CEPH_MOUNT_UNMOUNTED,
	CEPH_MOUNT_SHUTDOWN,
	CEPH_MOUNT_RECOVER,
	CEPH_MOUNT_FENCE_IO,
};

#define CEPH_ASYNC_CREATE_CONFLICT_BITS 8

struct ceph_fs_client {
	struct super_block *sb;

	struct list_head metric_wakeup;

	struct ceph_mount_options *mount_options;
	struct ceph_client *client;

	int mount_state;

	bool blocklisted;

	bool have_copy_from2;

	u32 filp_gen;
	loff_t max_file_size;

	struct ceph_mds_client *mdsc;

	atomic_long_t writeback_count;
	bool write_congested;

	struct workqueue_struct *inode_wq;
	struct workqueue_struct *cap_wq;

	DECLARE_HASHTABLE(async_unlink_conflict, CEPH_ASYNC_CREATE_CONFLICT_BITS);
	spinlock_t async_unlink_conflict_lock;

#ifdef CONFIG_DEBUG_FS
	struct dentry *debugfs_dentry_lru, *debugfs_caps;
	struct dentry *debugfs_congestion_kb;
	struct dentry *debugfs_bdi;
	struct dentry *debugfs_mdsc, *debugfs_mdsmap;
	struct dentry *debugfs_status;
	struct dentry *debugfs_mds_sessions;
	struct dentry *debugfs_metrics_dir;
#endif

#ifdef CONFIG_CEPH_FSCACHE
	struct fscache_volume *fscache;
#endif
#ifdef CONFIG_FS_ENCRYPTION
	struct fscrypt_dummy_policy fsc_dummy_enc_policy;
#endif
};

/*
 * File i/o capability.  This tracks shared state with the metadata
 * server that allows us to cache or writeback attributes or to read
 * and write data.  For any given inode, we should have one or more
 * capabilities, one issued by each metadata server, and our
 * cumulative access is the OR of all issued capabilities.
 *
 * Each cap is referenced by the inode's i_caps rbtree and by per-mds
 * session capability lists.
 */
struct ceph_cap {
	struct ceph_inode_info *ci;
	struct rb_node ci_node;          /* per-ci cap tree */
	struct ceph_mds_session *session;
	struct list_head session_caps;   /* per-session caplist */
	u64 cap_id;       /* unique cap id (mds provided) */
	union {
		/* in-use caps */
		struct {
			int issued;       /* latest, from the mds */
			int implemented;  /* implemented superset of
					     issued (for revocation) */
			int mds;	  /* mds index for this cap */
			int mds_wanted;   /* caps wanted from this mds */
		};
		/* caps to release */
		struct {
			u64 cap_ino;
			int queue_release;
		};
	};
	u32 seq, issue_seq, mseq;
	u32 cap_gen;      /* active/stale cycle */
	unsigned long last_used;
	struct list_head caps_item;
};

#define CHECK_CAPS_AUTHONLY     1  /* only check auth cap */
#define CHECK_CAPS_FLUSH        2  /* flush any dirty caps */
#define CHECK_CAPS_NOINVAL      4  /* don't invalidate pagecache */
#define CHECK_CAPS_FLUSH_FORCE  8  /* force flush any caps */

struct ceph_cap_flush {
	u64 tid;
	int caps;
	bool wake; /* wake up flush waiters when finish ? */
	bool is_capsnap; /* true means capsnap */
	struct list_head g_list; // global
	struct list_head i_list; // per inode
};

/*
 * Snapped cap state that is pending flush to mds.  When a snapshot occurs,
 * we first complete any in-process sync writes and writeback any dirty
 * data before flushing the snapped state (tracked here) back to the MDS.
 */
struct ceph_cap_snap {
	refcount_t nref;
	struct list_head ci_item;

	struct ceph_cap_flush cap_flush;

	u64 follows;
	int issued, dirty;
	struct ceph_snap_context *context;

	umode_t mode;
	kuid_t uid;
	kgid_t gid;

	struct ceph_buffer *xattr_blob;
	u64 xattr_version;

	u64 size;
	u64 change_attr;
	struct timespec64 mtime, atime, ctime, btime;
	u64 time_warp_seq;
	u64 truncate_size;
	u32 truncate_seq;
	int writing;   /* a sync write is still in progress */
	int dirty_pages;     /* dirty pages awaiting writeback */
	bool inline_data;
	bool need_flush;
};

static inline void ceph_put_cap_snap(struct ceph_cap_snap *capsnap)
{
	if (refcount_dec_and_test(&capsnap->nref)) {
		if (capsnap->xattr_blob)
			ceph_buffer_put(capsnap->xattr_blob);
		kmem_cache_free(ceph_cap_snap_cachep, capsnap);
	}
}

/*
 * The frag tree describes how a directory is fragmented, potentially across
 * multiple metadata servers.  It is also used to indicate points where
 * metadata authority is delegated, and whether/where metadata is replicated.
 *
 * A _leaf_ frag will be present in the i_fragtree IFF there is
 * delegation info.  That is, if mds >= 0 || ndist > 0.
 */
#define CEPH_MAX_DIRFRAG_REP 4

struct ceph_inode_frag {
	struct rb_node node;

	/* fragtree state */
	u32 frag;
	int split_by;         /* i.e. 2^(split_by) children */

	/* delegation and replication info */
	int mds;              /* -1 if same authority as parent */
	int ndist;            /* >0 if replicated */
	int dist[CEPH_MAX_DIRFRAG_REP];
};

/*
 * We cache inode xattrs as an encoded blob until they are first used,
 * at which point we parse them into an rbtree.
 */
struct ceph_inode_xattr {
	struct rb_node node;

	const char *name;
	int name_len;
	const char *val;
	int val_len;
	int dirty;

	int should_free_name;
	int should_free_val;
};

/*
 * Ceph dentry state
 */
struct ceph_dentry_info {
	struct dentry *dentry;
	struct ceph_mds_session *lease_session;
	struct list_head lease_list;
	struct hlist_node hnode;
	unsigned long flags;
	int lease_shared_gen;
	u32 lease_gen;
	u32 lease_seq;
	unsigned long lease_renew_after, lease_renew_from;
	unsigned long time;
	u64 offset;
};

#define CEPH_DENTRY_REFERENCED		(1 << 0)
#define CEPH_DENTRY_LEASE_LIST		(1 << 1)
#define CEPH_DENTRY_SHRINK_LIST		(1 << 2)
#define CEPH_DENTRY_PRIMARY_LINK	(1 << 3)
#define CEPH_DENTRY_ASYNC_UNLINK_BIT	(4)
#define CEPH_DENTRY_ASYNC_UNLINK	(1 << CEPH_DENTRY_ASYNC_UNLINK_BIT)
#define CEPH_DENTRY_ASYNC_CREATE_BIT	(5)
#define CEPH_DENTRY_ASYNC_CREATE	(1 << CEPH_DENTRY_ASYNC_CREATE_BIT)

struct ceph_inode_xattrs_info {
	/*
	 * (still encoded) xattr blob. we avoid the overhead of parsing
	 * this until someone actually calls getxattr, etc.
	 *
	 * blob->vec.iov_len == 4 implies there are no xattrs; blob ==
	 * NULL means we don't know.
	*/
	struct ceph_buffer *blob, *prealloc_blob;

	struct rb_root index;
	bool dirty;
	int count;
	int names_size;
	int vals_size;
	u64 version, index_version;
};

/*
 * Ceph inode.
 */
struct ceph_inode_info {
	struct netfs_inode netfs; /* Netfslib context and vfs inode */
	struct ceph_vino i_vino;   /* ceph ino + snap */

	spinlock_t i_ceph_lock;

	u64 i_version;
	u64 i_inline_version;
	u32 i_time_warp_seq;

	unsigned long i_ceph_flags;
	atomic64_t i_release_count;
	atomic64_t i_ordered_count;
	atomic64_t i_complete_seq[2];

	struct ceph_dir_layout i_dir_layout;
	struct ceph_file_layout i_layout;
	struct ceph_file_layout i_cached_layout;	// for async creates
	char *i_symlink;

	/* for dirs */
	struct timespec64 i_rctime;
	u64 i_rbytes, i_rfiles, i_rsubdirs, i_rsnaps;
	u64 i_files, i_subdirs;

	/* quotas */
	u64 i_max_bytes, i_max_files;

	s32 i_dir_pin;

	struct rb_root i_fragtree;
	int i_fragtree_nsplits;
	struct mutex i_fragtree_mutex;

	struct ceph_inode_xattrs_info i_xattrs;

	/* capabilities.  protected _both_ by i_ceph_lock and cap->session's
	 * s_mutex. */
	struct rb_root i_caps;           /* cap list */
	struct ceph_cap *i_auth_cap;     /* authoritative cap, if any */
	unsigned i_dirty_caps, i_flushing_caps;     /* mask of dirtied fields */

	/*
	 * Link to the auth cap's session's s_cap_dirty list. s_cap_dirty
	 * is protected by the mdsc->cap_dirty_lock, but each individual item
	 * is also protected by the inode's i_ceph_lock. Walking s_cap_dirty
	 * requires the mdsc->cap_dirty_lock. List presence for an item can
	 * be tested under the i_ceph_lock. Changing anything requires both.
	 */
	struct list_head i_dirty_item;

	/*
	 * Link to session's s_cap_flushing list. Protected in a similar
	 * fashion to i_dirty_item, but also by the s_mutex for changes. The
	 * s_cap_flushing list can be walked while holding either the s_mutex
	 * or msdc->cap_dirty_lock. List presence can also be checked while
	 * holding the i_ceph_lock for this inode.
	 */
	struct list_head i_flushing_item;

	/* we need to track cap writeback on a per-cap-bit basis, to allow
	 * overlapping, pipelined cap flushes to the mds.  we can probably
	 * reduce the tid to 8 bits if we're concerned about inode size. */
	struct ceph_cap_flush *i_prealloc_cap_flush;
	struct list_head i_cap_flush_list;
	wait_queue_head_t i_cap_wq;      /* threads waiting on a capability */
	unsigned long i_hold_caps_max; /* jiffies */
	struct list_head i_cap_delay_list;  /* for delayed cap release to mds */
	struct ceph_cap_reservation i_cap_migration_resv;
	struct list_head i_cap_snaps;   /* snapped state pending flush to mds */
	struct ceph_snap_context *i_head_snapc;  /* set if wr_buffer_head > 0 or
						    dirty|flushing caps */
	unsigned i_snap_caps;           /* cap bits for snapped files */

	unsigned long i_last_rd;
	unsigned long i_last_wr;
	int i_nr_by_mode[CEPH_FILE_MODE_BITS];  /* open file counts */

	struct mutex i_truncate_mutex;
	u32 i_truncate_seq;        /* last truncate to smaller size */
	u64 i_truncate_size;       /*  and the size we last truncated down to */
	int i_truncate_pending;    /*  still need to call vmtruncate */
	/*
	 * For none fscrypt case it equals to i_truncate_size or it will
	 * equals to fscrypt_file_size
	 */
	u64 i_truncate_pagecache_size;

	u64 i_max_size;            /* max file size authorized by mds */
	u64 i_reported_size; /* (max_)size reported to or requested of mds */
	u64 i_wanted_max_size;     /* offset we'd like to write too */
	u64 i_requested_max_size;  /* max_size we've requested */

	/* held references to caps */
	int i_pin_ref;
	int i_rd_ref, i_rdcache_ref, i_wr_ref, i_wb_ref, i_fx_ref;
	int i_wrbuffer_ref, i_wrbuffer_ref_head;
	atomic_t i_filelock_ref;
	atomic_t i_shared_gen;       /* increment each time we get FILE_SHARED */
	u32 i_rdcache_gen;      /* incremented each time we get FILE_CACHE. */
	u32 i_rdcache_revoking; /* RDCACHE gen to async invalidate, if any */

	struct list_head i_unsafe_dirops; /* uncommitted mds dir ops */
	struct list_head i_unsafe_iops;   /* uncommitted mds inode ops */
	spinlock_t i_unsafe_lock;

	union {
		struct ceph_snap_realm *i_snap_realm; /* snap realm (if caps) */
		struct ceph_snapid_map *i_snapid_map; /* snapid -> dev_t */
	};
	struct list_head i_snap_realm_item;
	struct list_head i_snap_flush_item;
	struct timespec64 i_btime;
	struct timespec64 i_snap_btime;

	struct work_struct i_work;
	unsigned long  i_work_mask;

#ifdef CONFIG_FS_ENCRYPTION
	u32 fscrypt_auth_len;
	u32 fscrypt_file_len;
	u8 *fscrypt_auth;
	u8 *fscrypt_file;
#endif
};

struct ceph_netfs_request_data {
	int caps;

	/*
	 * Maximum size of a file readahead request.
	 * The fadvise could update the bdi's default ra_pages.
	 */
	unsigned int file_ra_pages;

	/* Set it if fadvise disables file readahead entirely */
	bool file_ra_disabled;
};

static inline struct ceph_inode_info *
ceph_inode(const struct inode *inode)
{
	return container_of(inode, struct ceph_inode_info, netfs.inode);
}

static inline struct ceph_fs_client *
ceph_inode_to_fs_client(const struct inode *inode)
{
	return (struct ceph_fs_client *)inode->i_sb->s_fs_info;
}

static inline struct ceph_fs_client *
ceph_sb_to_fs_client(const struct super_block *sb)
{
	return (struct ceph_fs_client *)sb->s_fs_info;
}

static inline struct ceph_mds_client *
ceph_sb_to_mdsc(const struct super_block *sb)
{
	return (struct ceph_mds_client *)ceph_sb_to_fs_client(sb)->mdsc;
}

static inline struct ceph_client *
ceph_inode_to_client(const struct inode *inode)
{
	return (struct ceph_client *)ceph_inode_to_fs_client(inode)->client;
}

static inline struct ceph_vino
ceph_vino(const struct inode *inode)
{
	return ceph_inode(inode)->i_vino;
}

static inline u32 ceph_ino_to_ino32(u64 vino)
{
	u32 ino = vino & 0xffffffff;
	ino ^= vino >> 32;
	if (!ino)
		ino = 2;
	return ino;
}

/*
 * Inode numbers in cephfs are 64 bits, but inode->i_ino is 32-bits on
 * some arches. We generally do not use this value inside the ceph driver, but
 * we do want to set it to something, so that generic vfs code has an
 * appropriate value for tracepoints and the like.
 */
static inline ino_t ceph_vino_to_ino_t(struct ceph_vino vino)
{
	if (sizeof(ino_t) == sizeof(u32))
		return ceph_ino_to_ino32(vino.ino);
	return (ino_t)vino.ino;
}

/* for printf-style formatting */
#define ceph_vinop(i) ceph_inode(i)->i_vino.ino, ceph_inode(i)->i_vino.snap

static inline u64 ceph_ino(struct inode *inode)
{
	return ceph_inode(inode)->i_vino.ino;
}

static inline u64 ceph_snap(struct inode *inode)
{
	return ceph_inode(inode)->i_vino.snap;
}

/**
 * ceph_present_ino - format an inode number for presentation to userland
 * @sb: superblock where the inode lives
 * @ino: inode number to (possibly) convert
 *
 * If the user mounted with the ino32 option, then the 64-bit value needs
 * to be converted to something that can fit inside 32 bits. Note that
 * internal kernel code never uses this value, so this is entirely for
 * userland consumption.
 */
static inline u64 ceph_present_ino(struct super_block *sb, u64 ino)
{
	if (unlikely(ceph_test_mount_opt(ceph_sb_to_fs_client(sb), INO32)))
		return ceph_ino_to_ino32(ino);
	return ino;
}

static inline u64 ceph_present_inode(struct inode *inode)
{
	return ceph_present_ino(inode->i_sb, ceph_ino(inode));
}

static inline int ceph_ino_compare(struct inode *inode, void *data)
{
	struct ceph_vino *pvino = (struct ceph_vino *)data;
	struct ceph_inode_info *ci = ceph_inode(inode);
	return ci->i_vino.ino == pvino->ino &&
		ci->i_vino.snap == pvino->snap;
}

/*
 * The MDS reserves a set of inodes for its own usage. These should never
 * be accessible by clients, and so the MDS has no reason to ever hand these
 * out. The range is CEPH_MDS_INO_MDSDIR_OFFSET..CEPH_INO_SYSTEM_BASE.
 *
 * These come from src/mds/mdstypes.h in the ceph sources.
 */
#define CEPH_MAX_MDS			0x100
#define CEPH_NUM_STRAY			10
#define CEPH_MDS_INO_MDSDIR_OFFSET	(1 * CEPH_MAX_MDS)
#define CEPH_MDS_INO_LOG_OFFSET		(2 * CEPH_MAX_MDS)
#define CEPH_INO_SYSTEM_BASE		((6*CEPH_MAX_MDS) + (CEPH_MAX_MDS * CEPH_NUM_STRAY))

static inline bool ceph_vino_is_reserved(const struct ceph_vino vino)
{
	if (vino.ino >= CEPH_INO_SYSTEM_BASE ||
	    vino.ino < CEPH_MDS_INO_MDSDIR_OFFSET)
		return false;

	/* Don't warn on mdsdirs */
	WARN_RATELIMIT(vino.ino >= CEPH_MDS_INO_LOG_OFFSET,
			"Attempt to access reserved inode number 0x%llx",
			vino.ino);
	return true;
}

static inline struct inode *ceph_find_inode(struct super_block *sb,
					    struct ceph_vino vino)
{
	if (ceph_vino_is_reserved(vino))
		return NULL;

	/*
	 * NB: The hashval will be run through the fs/inode.c hash function
	 * anyway, so there is no need to squash the inode number down to
	 * 32-bits first. Just use low-order bits on arches with 32-bit long.
	 */
	return ilookup5(sb, (unsigned long)vino.ino, ceph_ino_compare, &vino);
}


/*
 * Ceph inode.
 */
#define CEPH_I_DIR_ORDERED	(1 << 0)  /* dentries in dir are ordered */
#define CEPH_I_FLUSH		(1 << 2)  /* do not delay flush of dirty metadata */
#define CEPH_I_POOL_PERM	(1 << 3)  /* pool rd/wr bits are valid */
#define CEPH_I_POOL_RD		(1 << 4)  /* can read from pool */
#define CEPH_I_POOL_WR		(1 << 5)  /* can write to pool */
#define CEPH_I_SEC_INITED	(1 << 6)  /* security initialized */
#define CEPH_I_KICK_FLUSH	(1 << 7)  /* kick flushing caps */
#define CEPH_I_FLUSH_SNAPS	(1 << 8)  /* need flush snapss */
#define CEPH_I_ERROR_WRITE	(1 << 9) /* have seen write errors */
#define CEPH_I_ERROR_FILELOCK	(1 << 10) /* have seen file lock errors */
#define CEPH_I_ODIRECT		(1 << 11) /* inode in direct I/O mode */
#define CEPH_ASYNC_CREATE_BIT	(12)	  /* async create in flight for this */
#define CEPH_I_ASYNC_CREATE	(1 << CEPH_ASYNC_CREATE_BIT)
#define CEPH_I_SHUTDOWN		(1 << 13) /* inode is no longer usable */
#define CEPH_I_ASYNC_CHECK_CAPS	(1 << 14) /* check caps immediately after async
					     creating finishes */

/*
 * Masks of ceph inode work.
 */
#define CEPH_I_WORK_WRITEBACK		0
#define CEPH_I_WORK_INVALIDATE_PAGES	1
#define CEPH_I_WORK_VMTRUNCATE		2
#define CEPH_I_WORK_CHECK_CAPS		3
#define CEPH_I_WORK_FLUSH_SNAPS		4

/*
 * We set the ERROR_WRITE bit when we start seeing write errors on an inode
 * and then clear it when they start succeeding. Note that we do a lockless
 * check first, and only take the lock if it looks like it needs to be changed.
 * The write submission code just takes this as a hint, so we're not too
 * worried if a few slip through in either direction.
 */
static inline void ceph_set_error_write(struct ceph_inode_info *ci)
{
	if (!(READ_ONCE(ci->i_ceph_flags) & CEPH_I_ERROR_WRITE)) {
		spin_lock(&ci->i_ceph_lock);
		ci->i_ceph_flags |= CEPH_I_ERROR_WRITE;
		spin_unlock(&ci->i_ceph_lock);
	}
}

static inline void ceph_clear_error_write(struct ceph_inode_info *ci)
{
	if (READ_ONCE(ci->i_ceph_flags) & CEPH_I_ERROR_WRITE) {
		spin_lock(&ci->i_ceph_lock);
		ci->i_ceph_flags &= ~CEPH_I_ERROR_WRITE;
		spin_unlock(&ci->i_ceph_lock);
	}
}

static inline void __ceph_dir_set_complete(struct ceph_inode_info *ci,
					   long long release_count,
					   long long ordered_count)
{
	/*
	 * Makes sure operations that setup readdir cache (update page
	 * cache and i_size) are strongly ordered w.r.t. the following
	 * atomic64_set() operations.
	 */
	smp_mb();
	atomic64_set(&ci->i_complete_seq[0], release_count);
	atomic64_set(&ci->i_complete_seq[1], ordered_count);
}

static inline void __ceph_dir_clear_complete(struct ceph_inode_info *ci)
{
	atomic64_inc(&ci->i_release_count);
}

static inline void __ceph_dir_clear_ordered(struct ceph_inode_info *ci)
{
	atomic64_inc(&ci->i_ordered_count);
}

static inline bool __ceph_dir_is_complete(struct ceph_inode_info *ci)
{
	return atomic64_read(&ci->i_complete_seq[0]) ==
		atomic64_read(&ci->i_release_count);
}

static inline bool __ceph_dir_is_complete_ordered(struct ceph_inode_info *ci)
{
	return  atomic64_read(&ci->i_complete_seq[0]) ==
		atomic64_read(&ci->i_release_count) &&
		atomic64_read(&ci->i_complete_seq[1]) ==
		atomic64_read(&ci->i_ordered_count);
}

static inline void ceph_dir_clear_complete(struct inode *inode)
{
	__ceph_dir_clear_complete(ceph_inode(inode));
}

static inline void ceph_dir_clear_ordered(struct inode *inode)
{
	__ceph_dir_clear_ordered(ceph_inode(inode));
}

static inline bool ceph_dir_is_complete_ordered(struct inode *inode)
{
	bool ret = __ceph_dir_is_complete_ordered(ceph_inode(inode));
	smp_rmb();
	return ret;
}

/* find a specific frag @f */
extern struct ceph_inode_frag *__ceph_find_frag(struct ceph_inode_info *ci,
						u32 f);

/*
 * choose fragment for value @v.  copy frag content to pfrag, if leaf
 * exists
 */
extern u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
			    struct ceph_inode_frag *pfrag,
			    int *found);

static inline struct ceph_dentry_info *ceph_dentry(const struct dentry *dentry)
{
	return (struct ceph_dentry_info *)dentry->d_fsdata;
}

/*
 * caps helpers
 */
static inline bool __ceph_is_any_real_caps(struct ceph_inode_info *ci)
{
	return !RB_EMPTY_ROOT(&ci->i_caps);
}

extern int __ceph_caps_issued(struct ceph_inode_info *ci, int *implemented);
extern int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int t);
extern int __ceph_caps_issued_mask_metric(struct ceph_inode_info *ci, int mask,
					  int t);
extern int __ceph_caps_issued_other(struct ceph_inode_info *ci,
				    struct ceph_cap *cap);

static inline int ceph_caps_issued(struct ceph_inode_info *ci)
{
	int issued;
	spin_lock(&ci->i_ceph_lock);
	issued = __ceph_caps_issued(ci, NULL);
	spin_unlock(&ci->i_ceph_lock);
	return issued;
}

static inline int ceph_caps_issued_mask_metric(struct ceph_inode_info *ci,
					       int mask, int touch)
{
	int r;
	spin_lock(&ci->i_ceph_lock);
	r = __ceph_caps_issued_mask_metric(ci, mask, touch);
	spin_unlock(&ci->i_ceph_lock);
	return r;
}

static inline int __ceph_caps_dirty(struct ceph_inode_info *ci)
{
	return ci->i_dirty_caps | ci->i_flushing_caps;
}
extern struct ceph_cap_flush *ceph_alloc_cap_flush(void);
extern void ceph_free_cap_flush(struct ceph_cap_flush *cf);
extern int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask,
				  struct ceph_cap_flush **pcf);

extern int __ceph_caps_revoking_other(struct ceph_inode_info *ci,
				      struct ceph_cap *ocap, int mask);
extern int ceph_caps_revoking(struct ceph_inode_info *ci, int mask);
extern int __ceph_caps_used(struct ceph_inode_info *ci);

static inline bool __ceph_is_file_opened(struct ceph_inode_info *ci)
{
	return ci->i_nr_by_mode[0];
}
extern int __ceph_caps_file_wanted(struct ceph_inode_info *ci);
extern int __ceph_caps_wanted(struct ceph_inode_info *ci);

/* what the mds thinks we want */
extern int __ceph_caps_mds_wanted(struct ceph_inode_info *ci, bool check);

extern void ceph_caps_init(struct ceph_mds_client *mdsc);
extern void ceph_caps_finalize(struct ceph_mds_client *mdsc);
extern void ceph_adjust_caps_max_min(struct ceph_mds_client *mdsc,
				     struct ceph_mount_options *fsopt);
extern int ceph_reserve_caps(struct ceph_mds_client *mdsc,
			     struct ceph_cap_reservation *ctx, int need);
extern void ceph_unreserve_caps(struct ceph_mds_client *mdsc,
			       struct ceph_cap_reservation *ctx);
extern void ceph_reservation_status(struct ceph_fs_client *client,
				    int *total, int *avail, int *used,
				    int *reserved, int *min);
extern void change_auth_cap_ses(struct ceph_inode_info *ci,
				struct ceph_mds_session *session);



/*
 * we keep buffered readdir results attached to file->private_data
 */
#define CEPH_F_SYNC     1
#define CEPH_F_ATEND    2

struct ceph_file_info {
	short fmode;     /* initialized on open */
	short flags;     /* CEPH_F_* */

	spinlock_t rw_contexts_lock;
	struct list_head rw_contexts;

	u32 filp_gen;
};

struct ceph_dir_file_info {
	struct ceph_file_info file_info;

	/* readdir: position within the dir */
	u32 frag;
	struct ceph_mds_request *last_readdir;

	/* readdir: position within a frag */
	unsigned next_offset;  /* offset of next chunk (last_name's + 1) */
	char *last_name;       /* last entry in previous chunk */
	long long dir_release_count;
	long long dir_ordered_count;
	int readdir_cache_idx;

	/* used for -o dirstat read() on directory thing */
	char *dir_info;
	int dir_info_len;
};

struct ceph_rw_context {
	struct list_head list;
	struct task_struct *thread;
	int caps;
};

#define CEPH_DEFINE_RW_CONTEXT(_name, _caps)	\
	struct ceph_rw_context _name = {	\
		.thread = current,		\
		.caps = _caps,			\
	}

static inline void ceph_add_rw_context(struct ceph_file_info *cf,
				       struct ceph_rw_context *ctx)
{
	spin_lock(&cf->rw_contexts_lock);
	list_add(&ctx->list, &cf->rw_contexts);
	spin_unlock(&cf->rw_contexts_lock);
}

static inline void ceph_del_rw_context(struct ceph_file_info *cf,
				       struct ceph_rw_context *ctx)
{
	spin_lock(&cf->rw_contexts_lock);
	list_del(&ctx->list);
	spin_unlock(&cf->rw_contexts_lock);
}

static inline struct ceph_rw_context*
ceph_find_rw_context(struct ceph_file_info *cf)
{
	struct ceph_rw_context *ctx, *found = NULL;
	spin_lock(&cf->rw_contexts_lock);
	list_for_each_entry(ctx, &cf->rw_contexts, list) {
		if (ctx->thread == current) {
			found = ctx;
			break;
		}
	}
	spin_unlock(&cf->rw_contexts_lock);
	return found;
}

struct ceph_readdir_cache_control {
	struct page  *page;
	struct dentry **dentries;
	int index;
};

/*
 * A "snap realm" describes a subset of the file hierarchy sharing
 * the same set of snapshots that apply to it.  The realms themselves
 * are organized into a hierarchy, such that children inherit (some of)
 * the snapshots of their parents.
 *
 * All inodes within the realm that have capabilities are linked into a
 * per-realm list.
 */
struct ceph_snap_realm {
	u64 ino;
	struct inode *inode;
	atomic_t nref;
	struct rb_node node;

	u64 created, seq;
	u64 parent_ino;
	u64 parent_since;   /* snapid when our current parent became so */

	u64 *prior_parent_snaps;      /* snaps inherited from any parents we */
	u32 num_prior_parent_snaps;   /*  had prior to parent_since */
	u64 *snaps;                   /* snaps specific to this realm */
	u32 num_snaps;

	struct ceph_snap_realm *parent;
	struct list_head children;       /* list of child realms */
	struct list_head child_item;

	struct list_head empty_item;     /* if i have ref==0 */

	struct list_head dirty_item;     /* if realm needs new context */

	struct list_head rebuild_item;   /* rebuild snap realms _downward_ in hierarchy */

	/* the current set of snaps for this realm */
	struct ceph_snap_context *cached_context;

	struct list_head inodes_with_caps;
	spinlock_t inodes_with_caps_lock;
};

static inline int default_congestion_kb(void)
{
	int congestion_kb;

	/*
	 * Copied from NFS
	 *
	 * congestion size, scale with available memory.
	 *
	 *  64MB:    8192k
	 * 128MB:   11585k
	 * 256MB:   16384k
	 * 512MB:   23170k
	 *   1GB:   32768k
	 *   2GB:   46340k
	 *   4GB:   65536k
	 *   8GB:   92681k
	 *  16GB:  131072k
	 *
	 * This allows larger machines to have larger/more transfers.
	 * Limit the default to 256M
	 */
	congestion_kb = (16*int_sqrt(totalram_pages())) << (PAGE_SHIFT-10);
	if (congestion_kb > 256*1024)
		congestion_kb = 256*1024;

	return congestion_kb;
}


/* super.c */
extern int ceph_force_reconnect(struct super_block *sb);
/* snap.c */
struct ceph_snap_realm *ceph_lookup_snap_realm(struct ceph_mds_client *mdsc,
					       u64 ino);
extern void ceph_get_snap_realm(struct ceph_mds_client *mdsc,
				struct ceph_snap_realm *realm);
extern void ceph_put_snap_realm(struct ceph_mds_client *mdsc,
				struct ceph_snap_realm *realm);
extern int ceph_update_snap_trace(struct ceph_mds_client *m,
				  void *p, void *e, bool deletion,
				  struct ceph_snap_realm **realm_ret);
void ceph_change_snap_realm(struct inode *inode, struct ceph_snap_realm *realm);
extern void ceph_handle_snap(struct ceph_mds_client *mdsc,
			     struct ceph_mds_session *session,
			     struct ceph_msg *msg);
extern int __ceph_finish_cap_snap(struct ceph_inode_info *ci,
				  struct ceph_cap_snap *capsnap);
extern void ceph_cleanup_global_and_empty_realms(struct ceph_mds_client *mdsc);

extern struct ceph_snapid_map *ceph_get_snapid_map(struct ceph_mds_client *mdsc,
						   u64 snap);
extern void ceph_put_snapid_map(struct ceph_mds_client* mdsc,
				struct ceph_snapid_map *sm);
extern void ceph_trim_snapid_map(struct ceph_mds_client *mdsc);
extern void ceph_cleanup_snapid_map(struct ceph_mds_client *mdsc);
void ceph_umount_begin(struct super_block *sb);


/*
 * a cap_snap is "pending" if it is still awaiting an in-progress
 * sync write (that may/may not still update size, mtime, etc.).
 */
static inline bool __ceph_have_pending_cap_snap(struct ceph_inode_info *ci)
{
	return !list_empty(&ci->i_cap_snaps) &&
	       list_last_entry(&ci->i_cap_snaps, struct ceph_cap_snap,
			       ci_item)->writing;
}

/* inode.c */
struct ceph_mds_reply_info_in;
struct ceph_mds_reply_dirfrag;
struct ceph_acl_sec_ctx;

extern const struct inode_operations ceph_file_iops;

extern struct inode *ceph_alloc_inode(struct super_block *sb);
extern void ceph_evict_inode(struct inode *inode);
extern void ceph_free_inode(struct inode *inode);

struct inode *ceph_new_inode(struct inode *dir, struct dentry *dentry,
			     umode_t *mode, struct ceph_acl_sec_ctx *as_ctx);
void ceph_as_ctx_to_req(struct ceph_mds_request *req,
			struct ceph_acl_sec_ctx *as_ctx);

extern struct inode *ceph_get_inode(struct super_block *sb,
				    struct ceph_vino vino,
				    struct inode *newino);
extern struct inode *ceph_get_snapdir(struct inode *parent);
extern int ceph_fill_file_size(struct inode *inode, int issued,
			       u32 truncate_seq, u64 truncate_size, u64 size);
extern void ceph_fill_file_time(struct inode *inode, int issued,
				u64 time_warp_seq, struct timespec64 *ctime,
				struct timespec64 *mtime,
				struct timespec64 *atime);
extern int ceph_fill_inode(struct inode *inode, struct page *locked_page,
		    struct ceph_mds_reply_info_in *iinfo,
		    struct ceph_mds_reply_dirfrag *dirinfo,
		    struct ceph_mds_session *session, int cap_fmode,
		    struct ceph_cap_reservation *caps_reservation);
extern int ceph_fill_trace(struct super_block *sb,
			   struct ceph_mds_request *req);
extern int ceph_readdir_prepopulate(struct ceph_mds_request *req,
				    struct ceph_mds_session *session);

extern int ceph_inode_holds_cap(struct inode *inode, int mask);

extern bool ceph_inode_set_size(struct inode *inode, loff_t size);
extern void __ceph_do_pending_vmtruncate(struct inode *inode);

void ceph_queue_inode_work(struct inode *inode, int work_bit);

static inline void ceph_queue_vmtruncate(struct inode *inode)
{
	ceph_queue_inode_work(inode, CEPH_I_WORK_VMTRUNCATE);
}

static inline void ceph_queue_invalidate(struct inode *inode)
{
	ceph_queue_inode_work(inode, CEPH_I_WORK_INVALIDATE_PAGES);
}

static inline void ceph_queue_writeback(struct inode *inode)
{
	ceph_queue_inode_work(inode, CEPH_I_WORK_WRITEBACK);
}

static inline void ceph_queue_check_caps(struct inode *inode)
{
	ceph_queue_inode_work(inode, CEPH_I_WORK_CHECK_CAPS);
}

static inline void ceph_queue_flush_snaps(struct inode *inode)
{
	ceph_queue_inode_work(inode, CEPH_I_WORK_FLUSH_SNAPS);
}

extern int ceph_try_to_choose_auth_mds(struct inode *inode, int mask);
extern int __ceph_do_getattr(struct inode *inode, struct page *locked_page,
			     int mask, bool force);
static inline int ceph_do_getattr(struct inode *inode, int mask, bool force)
{
	return __ceph_do_getattr(inode, NULL, mask, force);
}
extern int ceph_permission(struct mnt_idmap *idmap,
			   struct inode *inode, int mask);

struct ceph_iattr {
	struct ceph_fscrypt_auth	*fscrypt_auth;
};

extern int __ceph_setattr(struct mnt_idmap *idmap, struct inode *inode,
			  struct iattr *attr, struct ceph_iattr *cia);
extern int ceph_setattr(struct mnt_idmap *idmap,
			struct dentry *dentry, struct iattr *attr);
extern int ceph_getattr(struct mnt_idmap *idmap,
			const struct path *path, struct kstat *stat,
			u32 request_mask, unsigned int flags);
void ceph_inode_shutdown(struct inode *inode);

static inline bool ceph_inode_is_shutdown(struct inode *inode)
{
	unsigned long flags = READ_ONCE(ceph_inode(inode)->i_ceph_flags);
	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
	int state = READ_ONCE(fsc->mount_state);

	return (flags & CEPH_I_SHUTDOWN) || state >= CEPH_MOUNT_SHUTDOWN;
}

/* xattr.c */
int __ceph_setxattr(struct inode *, const char *, const void *, size_t, int);
int ceph_do_getvxattr(struct inode *inode, const char *name, void *value, size_t size);
ssize_t __ceph_getxattr(struct inode *, const char *, void *, size_t);
extern ssize_t ceph_listxattr(struct dentry *, char *, size_t);
extern struct ceph_buffer *__ceph_build_xattrs_blob(struct ceph_inode_info *ci);
extern void __ceph_destroy_xattrs(struct ceph_inode_info *ci);
extern const struct xattr_handler * const ceph_xattr_handlers[];

struct ceph_acl_sec_ctx {
#ifdef CONFIG_CEPH_FS_POSIX_ACL
	void *default_acl;
	void *acl;
#endif
#ifdef CONFIG_CEPH_FS_SECURITY_LABEL
	void *sec_ctx;
	u32 sec_ctxlen;
#endif
#ifdef CONFIG_FS_ENCRYPTION
	struct ceph_fscrypt_auth *fscrypt_auth;
#endif
	struct ceph_pagelist *pagelist;
};

#ifdef CONFIG_SECURITY
extern bool ceph_security_xattr_deadlock(struct inode *in);
extern bool ceph_security_xattr_wanted(struct inode *in);
#else
static inline bool ceph_security_xattr_deadlock(struct inode *in)
{
	return false;
}
static inline bool ceph_security_xattr_wanted(struct inode *in)
{
	return false;
}
#endif

#ifdef CONFIG_CEPH_FS_SECURITY_LABEL
extern int ceph_security_init_secctx(struct dentry *dentry, umode_t mode,
				     struct ceph_acl_sec_ctx *ctx);
static inline void ceph_security_invalidate_secctx(struct inode *inode)
{
	security_inode_invalidate_secctx(inode);
}
#else
static inline int ceph_security_init_secctx(struct dentry *dentry, umode_t mode,
					    struct ceph_acl_sec_ctx *ctx)
{
	return 0;
}
static inline void ceph_security_invalidate_secctx(struct inode *inode)
{
}
#endif

void ceph_release_acl_sec_ctx(struct ceph_acl_sec_ctx *as_ctx);

/* acl.c */
#ifdef CONFIG_CEPH_FS_POSIX_ACL

struct posix_acl *ceph_get_acl(struct inode *, int, bool);
int ceph_set_acl(struct mnt_idmap *idmap,
		 struct dentry *dentry, struct posix_acl *acl, int type);
int ceph_pre_init_acls(struct inode *dir, umode_t *mode,
		       struct ceph_acl_sec_ctx *as_ctx);
void ceph_init_inode_acls(struct inode *inode,
			  struct ceph_acl_sec_ctx *as_ctx);

static inline void ceph_forget_all_cached_acls(struct inode *inode)
{
       forget_all_cached_acls(inode);
}

#else

#define ceph_get_acl NULL
#define ceph_set_acl NULL

static inline int ceph_pre_init_acls(struct inode *dir, umode_t *mode,
				     struct ceph_acl_sec_ctx *as_ctx)
{
	return 0;
}
static inline void ceph_init_inode_acls(struct inode *inode,
					struct ceph_acl_sec_ctx *as_ctx)
{
}
static inline int ceph_acl_chmod(struct dentry *dentry, struct inode *inode)
{
	return 0;
}

static inline void ceph_forget_all_cached_acls(struct inode *inode)
{
}

#endif

/* caps.c */
extern const char *ceph_cap_string(int c);
extern void ceph_handle_caps(struct ceph_mds_session *session,
			     struct ceph_msg *msg);
extern struct ceph_cap *ceph_get_cap(struct ceph_mds_client *mdsc,
				     struct ceph_cap_reservation *ctx);
extern void ceph_add_cap(struct inode *inode,
			 struct ceph_mds_session *session, u64 cap_id,
			 unsigned issued, unsigned wanted,
			 unsigned cap, unsigned seq, u64 realmino, int flags,
			 struct ceph_cap **new_cap);
extern void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release);
extern void ceph_remove_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
			    bool queue_release);
extern void __ceph_remove_caps(struct ceph_inode_info *ci);
extern void ceph_put_cap(struct ceph_mds_client *mdsc,
			 struct ceph_cap *cap);
extern int ceph_is_any_caps(struct inode *inode);

extern int ceph_write_inode(struct inode *inode, struct writeback_control *wbc);
extern int ceph_fsync(struct file *file, loff_t start, loff_t end,
		      int datasync);
extern void ceph_early_kick_flushing_caps(struct ceph_mds_client *mdsc,
					  struct ceph_mds_session *session);
extern void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc,
				    struct ceph_mds_session *session);
void ceph_kick_flushing_inode_caps(struct ceph_mds_session *session,
				   struct ceph_inode_info *ci);
extern struct ceph_cap *__get_cap_for_mds(struct ceph_inode_info *ci,
					  int mds);
extern struct ceph_cap *ceph_get_cap_for_mds(struct ceph_inode_info *ci,
					     int mds);
extern void ceph_take_cap_refs(struct ceph_inode_info *ci, int caps,
				bool snap_rwsem_locked);
extern void ceph_get_cap_refs(struct ceph_inode_info *ci, int caps);
extern void ceph_put_cap_refs(struct ceph_inode_info *ci, int had);
extern void ceph_put_cap_refs_async(struct ceph_inode_info *ci, int had);
extern void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
				       struct ceph_snap_context *snapc);
extern void __ceph_remove_capsnap(struct inode *inode,
				  struct ceph_cap_snap *capsnap,
				  bool *wake_ci, bool *wake_mdsc);
extern void ceph_remove_capsnap(struct inode *inode,
				struct ceph_cap_snap *capsnap,
				bool *wake_ci, bool *wake_mdsc);
extern void ceph_flush_snaps(struct ceph_inode_info *ci,
			     struct ceph_mds_session **psession);
extern bool __ceph_should_report_size(struct ceph_inode_info *ci);
extern void ceph_check_caps(struct ceph_inode_info *ci, int flags);
extern unsigned long ceph_check_delayed_caps(struct ceph_mds_client *mdsc);
extern void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc);
extern int  ceph_drop_caps_for_unlink(struct inode *inode);
extern int ceph_encode_inode_release(void **p, struct inode *inode,
				     int mds, int drop, int unless, int force);
extern int ceph_encode_dentry_release(void **p, struct dentry *dn,
				      struct inode *dir,
				      int mds, int drop, int unless);

extern int __ceph_get_caps(struct inode *inode, struct ceph_file_info *fi,
			   int need, int want, loff_t endoff, int *got);
extern int ceph_get_caps(struct file *filp, int need, int want,
			 loff_t endoff, int *got);
extern int ceph_try_get_caps(struct inode *inode,
			     int need, int want, bool nonblock, int *got);

/* for counting open files by mode */
extern void ceph_get_fmode(struct ceph_inode_info *ci, int mode, int count);
extern void ceph_put_fmode(struct ceph_inode_info *ci, int mode, int count);
extern void __ceph_touch_fmode(struct ceph_inode_info *ci,
			       struct ceph_mds_client *mdsc, int fmode);

/* addr.c */
extern const struct address_space_operations ceph_aops;
extern const struct netfs_request_ops ceph_netfs_ops;
extern int ceph_mmap(struct file *file, struct vm_area_struct *vma);
extern int ceph_uninline_data(struct file *file);
extern int ceph_pool_perm_check(struct inode *inode, int need);
extern void ceph_pool_perm_destroy(struct ceph_mds_client* mdsc);
int ceph_purge_inode_cap(struct inode *inode, struct ceph_cap *cap, bool *invalidate);

static inline bool ceph_has_inline_data(struct ceph_inode_info *ci)
{
	if (ci->i_inline_version == CEPH_INLINE_NONE ||
	    ci->i_inline_version == 1) /* initial version, no data */
		return false;
	return true;
}

/* file.c */
extern const struct file_operations ceph_file_fops;

extern int ceph_renew_caps(struct inode *inode, int fmode);
extern int ceph_open(struct inode *inode, struct file *file);
extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
			    struct file *file, unsigned flags, umode_t mode);
extern ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
				struct iov_iter *to, int *retry_op,
				u64 *last_objver);
extern int ceph_release(struct inode *inode, struct file *filp);
extern void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
				  char *data, size_t len);

/* dir.c */
extern const struct file_operations ceph_dir_fops;
extern const struct file_operations ceph_snapdir_fops;
extern const struct inode_operations ceph_dir_iops;
extern const struct inode_operations ceph_snapdir_iops;
extern const struct dentry_operations ceph_dentry_ops;

extern loff_t ceph_make_fpos(unsigned high, unsigned off, bool hash_order);
extern int ceph_handle_notrace_create(struct inode *dir, struct dentry *dentry);
extern struct dentry *ceph_handle_snapdir(struct ceph_mds_request *req,
			       struct dentry *dentry);
extern struct dentry *ceph_finish_lookup(struct ceph_mds_request *req,
					 struct dentry *dentry, int err);

extern void __ceph_dentry_lease_touch(struct ceph_dentry_info *di);
extern void __ceph_dentry_dir_lease_touch(struct ceph_dentry_info *di);
extern void ceph_invalidate_dentry_lease(struct dentry *dentry);
extern int ceph_trim_dentries(struct ceph_mds_client *mdsc);
extern unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn);
extern void ceph_readdir_cache_release(struct ceph_readdir_cache_control *ctl);

/* ioctl.c */
extern long ceph_ioctl(struct file *file, unsigned int cmd, unsigned long arg);

/* export.c */
extern const struct export_operations ceph_export_ops;
struct inode *ceph_lookup_inode(struct super_block *sb, u64 ino);

/* locks.c */
extern __init void ceph_flock_init(void);
extern int ceph_lock(struct file *file, int cmd, struct file_lock *fl);
extern int ceph_flock(struct file *file, int cmd, struct file_lock *fl);
extern void ceph_count_locks(struct inode *inode, int *p_num, int *f_num);
extern int ceph_encode_locks_to_buffer(struct inode *inode,
				       struct ceph_filelock *flocks,
				       int num_fcntl_locks,
				       int num_flock_locks);
extern int ceph_locks_to_pagelist(struct ceph_filelock *flocks,
				  struct ceph_pagelist *pagelist,
				  int num_fcntl_locks, int num_flock_locks);

/* debugfs.c */
extern void ceph_fs_debugfs_init(struct ceph_fs_client *client);
extern void ceph_fs_debugfs_cleanup(struct ceph_fs_client *client);

/* quota.c */

enum quota_get_realm {
	QUOTA_GET_MAX_FILES,
	QUOTA_GET_MAX_BYTES,
	QUOTA_GET_ANY
};

static inline bool __ceph_has_quota(struct ceph_inode_info *ci,
				    enum quota_get_realm which)
{
	bool has_quota = false;

	switch (which) {
	case QUOTA_GET_MAX_BYTES:
		has_quota = !!ci->i_max_bytes;
		break;
	case QUOTA_GET_MAX_FILES:
		has_quota = !!ci->i_max_files;
		break;
	default:
		has_quota = !!(ci->i_max_files || ci->i_max_bytes);
	}
	return has_quota;
}

extern void ceph_adjust_quota_realms_count(struct inode *inode, bool inc);

static inline void __ceph_update_quota(struct ceph_inode_info *ci,
				       u64 max_bytes, u64 max_files)
{
	bool had_quota, has_quota;
	had_quota = __ceph_has_quota(ci, QUOTA_GET_ANY);
	ci->i_max_bytes = max_bytes;
	ci->i_max_files = max_files;
	has_quota = __ceph_has_quota(ci, QUOTA_GET_ANY);

	if (had_quota != has_quota)
		ceph_adjust_quota_realms_count(&ci->netfs.inode, has_quota);
}

static inline int __ceph_sparse_read_ext_count(struct inode *inode, u64 len)
{
	int cnt = 0;

	if (IS_ENCRYPTED(inode)) {
		cnt = len >> CEPH_FSCRYPT_BLOCK_SHIFT;
		if (cnt > CEPH_SPARSE_EXT_ARRAY_INITIAL)
			cnt = 0;
	}

	return cnt;
}

extern void ceph_handle_quota(struct ceph_mds_client *mdsc,
			      struct ceph_mds_session *session,
			      struct ceph_msg *msg);
extern bool ceph_quota_is_max_files_exceeded(struct inode *inode);
extern bool ceph_quota_is_same_realm(struct inode *old, struct inode *new);
extern bool ceph_quota_is_max_bytes_exceeded(struct inode *inode,
					     loff_t newlen);
extern bool ceph_quota_is_max_bytes_approaching(struct inode *inode,
						loff_t newlen);
extern bool ceph_quota_update_statfs(struct ceph_fs_client *fsc,
				     struct kstatfs *buf);
extern void ceph_cleanup_quotarealms_inodes(struct ceph_mds_client *mdsc);

bool ceph_inc_mds_stopping_blocker(struct ceph_mds_client *mdsc,
			       struct ceph_mds_session *session);
void ceph_dec_mds_stopping_blocker(struct ceph_mds_client *mdsc);
bool ceph_inc_osd_stopping_blocker(struct ceph_mds_client *mdsc);
void ceph_dec_osd_stopping_blocker(struct ceph_mds_client *mdsc);
#endif /* _FS_CEPH_SUPER_H */