Blame view
fs/ceph/super.h
26.2 KB
de57606c2 ceph: client types |
1 2 |
#ifndef _FS_CEPH_SUPER_H #define _FS_CEPH_SUPER_H |
3d14c5d2b ceph: factor out ... |
3 |
#include <linux/ceph/ceph_debug.h> |
de57606c2 ceph: client types |
4 5 6 7 8 9 10 11 12 |
#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> |
f1a3d5721 ceph: update for ... |
13 |
#include <linux/writeback.h> |
5a0e3ad6a include cleanup: ... |
14 |
#include <linux/slab.h> |
de57606c2 ceph: client types |
15 |
|
3d14c5d2b ceph: factor out ... |
16 |
#include <linux/ceph/libceph.h> |
de57606c2 ceph: client types |
17 18 19 20 21 22 23 24 |
/* f_type in struct statfs */ #define CEPH_SUPER_MAGIC 0x00c36400 /* large granularity for statfs utilization stats to facilitate * large volume sizes on 32-bit machines. */ #define CEPH_BLOCK_SHIFT 20 /* 1 MB */ #define CEPH_BLOCK (1 << CEPH_BLOCK_SHIFT) |
3d14c5d2b ceph: factor out ... |
25 26 27 |
#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 */ |
ad1fee96c ceph: add ino32 m... |
28 |
#define CEPH_MOUNT_OPT_INO32 (1<<8) /* 32 bit inos */ |
a40dc6cc2 ceph: enable/disa... |
29 |
#define CEPH_MOUNT_OPT_DCACHE (1<<9) /* use dcache for readdir etc */ |
6a2593823 ceph: specify sup... |
30 |
|
3d14c5d2b ceph: factor out ... |
31 |
#define CEPH_MOUNT_OPT_DEFAULT (CEPH_MOUNT_OPT_RBYTES) |
de57606c2 ceph: client types |
32 |
|
3d14c5d2b ceph: factor out ... |
33 34 35 36 |
#define ceph_set_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)) |
de57606c2 ceph: client types |
37 |
|
83817e35c ceph: rename rsiz... |
38 39 |
#define CEPH_RSIZE_DEFAULT 0 /* max read size */ #define CEPH_RASIZE_DEFAULT (8192*1024) /* readahead */ |
3d14c5d2b ceph: factor out ... |
40 41 42 |
#define CEPH_MAX_READDIR_DEFAULT 1024 #define CEPH_MAX_READDIR_BYTES_DEFAULT (512*1024) #define CEPH_SNAPDIRNAME_DEFAULT ".snap" |
de57606c2 ceph: client types |
43 |
|
3d14c5d2b ceph: factor out ... |
44 |
struct ceph_mount_options { |
6e19a16ef ceph: clean up mo... |
45 |
int flags; |
3d14c5d2b ceph: factor out ... |
46 |
int sb_flags; |
83817e35c ceph: rename rsiz... |
47 48 49 |
int wsize; /* max write size */ int rsize; /* max read size */ int rasize; /* max readahead */ |
6e19a16ef ceph: clean up mo... |
50 51 52 |
int congestion_kb; /* max writeback in flight */ int caps_wanted_delay_min, caps_wanted_delay_max; int cap_release_safety; |
23804d91f ceph: specify max... |
53 54 |
int max_readdir; /* max readdir result (entires) */ int max_readdir_bytes; /* max readdir result (bytes) */ |
de57606c2 ceph: client types |
55 |
|
3d14c5d2b ceph: factor out ... |
56 57 58 59 |
/* * everything above this point can be memcmp'd; everything below * is handled in compare_mount_options() */ |
de57606c2 ceph: client types |
60 |
|
3d14c5d2b ceph: factor out ... |
61 62 |
char *snapdir_name; /* default ".snap" */ }; |
de57606c2 ceph: client types |
63 |
|
3d14c5d2b ceph: factor out ... |
64 |
struct ceph_fs_client { |
de57606c2 ceph: client types |
65 |
struct super_block *sb; |
3d14c5d2b ceph: factor out ... |
66 67 |
struct ceph_mount_options *mount_options; struct ceph_client *client; |
de57606c2 ceph: client types |
68 |
|
3d14c5d2b ceph: factor out ... |
69 |
unsigned long mount_state; |
85ccce43a ceph: clean up re... |
70 |
int min_caps; /* min caps i added */ |
3d14c5d2b ceph: factor out ... |
71 |
struct ceph_mds_client *mdsc; |
de57606c2 ceph: client types |
72 73 74 75 76 77 |
/* writeback */ mempool_t *wb_pagevec_pool; struct workqueue_struct *wb_wq; struct workqueue_struct *pg_inv_wq; struct workqueue_struct *trunc_wq; |
2baba2501 ceph: writeback c... |
78 |
atomic_long_t writeback_count; |
de57606c2 ceph: client types |
79 80 |
struct backing_dev_info backing_dev_info; |
0743304d8 ceph: fix debugfs... |
81 82 |
#ifdef CONFIG_DEBUG_FS |
3d14c5d2b ceph: factor out ... |
83 |
struct dentry *debugfs_dentry_lru, *debugfs_caps; |
2baba2501 ceph: writeback c... |
84 |
struct dentry *debugfs_congestion_kb; |
06edf046d ceph: include lin... |
85 |
struct dentry *debugfs_bdi; |
3d14c5d2b ceph: factor out ... |
86 |
struct dentry *debugfs_mdsc, *debugfs_mdsmap; |
0743304d8 ceph: fix debugfs... |
87 |
#endif |
de57606c2 ceph: client types |
88 |
}; |
3d14c5d2b ceph: factor out ... |
89 |
|
de57606c2 ceph: client types |
90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 |
/* * 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 */ int mds; u64 cap_id; /* unique cap id (mds provided) */ int issued; /* latest, from the mds */ int implemented; /* implemented superset of issued (for revocation) */ int mds_wanted; |
685f9a5d1 ceph: do not conf... |
110 111 |
u32 seq, issue_seq, mseq; u32 cap_gen; /* active/stale cycle */ |
de57606c2 ceph: client types |
112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 |
unsigned long last_used; struct list_head caps_item; }; #define CHECK_CAPS_NODELAY 1 /* do not delay any further */ #define CHECK_CAPS_AUTHONLY 2 /* only check auth cap */ #define CHECK_CAPS_FLUSH 4 /* flush any dirty caps */ /* * 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 { atomic_t nref; struct ceph_inode_info *ci; struct list_head ci_item, flushing_item; u64 follows, flush_tid; int issued, dirty; struct ceph_snap_context *context; |
5706b27de ceph: propagate u... |
133 |
umode_t mode; |
de57606c2 ceph: client types |
134 135 |
uid_t uid; gid_t gid; |
4a625be47 ceph: include dir... |
136 |
struct ceph_buffer *xattr_blob; |
de57606c2 ceph: client types |
137 138 139 140 141 142 143 144 145 146 147 |
u64 xattr_version; u64 size; struct timespec mtime, atime, ctime; u64 time_warp_seq; int writing; /* a sync write is still in progress */ int dirty_pages; /* dirty pages awaiting writeback */ }; static inline void ceph_put_cap_snap(struct ceph_cap_snap *capsnap) { |
4a625be47 ceph: include dir... |
148 149 150 |
if (atomic_dec_and_test(&capsnap->nref)) { if (capsnap->xattr_blob) ceph_buffer_put(capsnap->xattr_blob); |
de57606c2 ceph: client types |
151 |
kfree(capsnap); |
4a625be47 ceph: include dir... |
152 |
} |
de57606c2 ceph: client types |
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 |
} /* * 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; }; |
3d14c5d2b ceph: factor out ... |
194 195 196 197 |
/* * Ceph dentry state */ struct ceph_dentry_info { |
b58dc4100 ceph: clear paren... |
198 |
unsigned long flags; |
3d14c5d2b ceph: factor out ... |
199 200 201 202 203 204 205 206 207 |
struct ceph_mds_session *lease_session; u32 lease_gen, lease_shared_gen; u32 lease_seq; unsigned long lease_renew_after, lease_renew_from; struct list_head lru; struct dentry *dentry; u64 time; u64 offset; }; |
b58dc4100 ceph: clear paren... |
208 209 210 211 212 213 |
/* * dentry flags * * The locking for D_COMPLETE is a bit odd: * - we can clear it at almost any time (see ceph_d_prune) * - it is only meaningful if: |
be655596b ceph: use i_ceph_... |
214 |
* - we hold dir inode i_ceph_lock |
b58dc4100 ceph: clear paren... |
215 216 217 218 |
* - we hold dir FILE_SHARED caps * - the dentry D_COMPLETE is set */ #define CEPH_D_COMPLETE 1 /* if set, d_u.d_subdirs is complete directory */ |
de57606c2 ceph: client types |
219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 |
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. */ |
de57606c2 ceph: client types |
240 241 |
struct ceph_inode_info { struct ceph_vino i_vino; /* ceph ino + snap */ |
be655596b ceph: use i_ceph_... |
242 |
spinlock_t i_ceph_lock; |
de57606c2 ceph: client types |
243 244 245 246 247 |
u64 i_version; u32 i_time_warp_seq; unsigned i_ceph_flags; unsigned long i_release_count; |
6c0f3af72 ceph: add dir_lay... |
248 |
struct ceph_dir_layout i_dir_layout; |
de57606c2 ceph: client types |
249 250 251 252 253 254 255 |
struct ceph_file_layout i_layout; char *i_symlink; /* for dirs */ struct timespec i_rctime; u64 i_rbytes, i_rfiles, i_rsubdirs; u64 i_files, i_subdirs; |
c6ffe1001 ceph: use new D_C... |
256 |
u64 i_max_offset; /* largest readdir offset, set with D_COMPLETE */ |
de57606c2 ceph: client types |
257 258 259 260 261 |
struct rb_root i_fragtree; struct mutex i_fragtree_mutex; struct ceph_inode_xattrs_info i_xattrs; |
be655596b ceph: use i_ceph_... |
262 |
/* capabilities. protected _both_ by i_ceph_lock and cap->session's |
de57606c2 ceph: client types |
263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 |
* 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 */ struct list_head i_dirty_item, i_flushing_item; u64 i_cap_flush_seq; /* 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. */ u16 i_cap_flush_last_tid, i_cap_flush_tid[CEPH_CAP_BITS]; wait_queue_head_t i_cap_wq; /* threads waiting on a capability */ unsigned long i_hold_caps_min; /* jiffies */ unsigned long i_hold_caps_max; /* jiffies */ struct list_head i_cap_delay_list; /* for delayed cap release to mds */ int i_cap_exporting_mds; /* to handle cap migration between */ unsigned i_cap_exporting_mseq; /* mds's. */ unsigned i_cap_exporting_issued; struct ceph_cap_reservation i_cap_migration_resv; struct list_head i_cap_snaps; /* snapped state pending flush to mds */ |
7d8cb26d7 ceph: maintain i_... |
282 283 |
struct ceph_snap_context *i_head_snapc; /* set if wr_buffer_head > 0 or dirty|flushing caps */ |
de57606c2 ceph: client types |
284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 |
unsigned i_snap_caps; /* cap bits for snapped files */ int i_nr_by_mode[CEPH_FILE_MODE_NUM]; /* open file counts */ 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 */ 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; |
d3d0720d4 ceph: do not use ... |
299 |
int i_rd_ref, i_rdcache_ref, i_wr_ref, i_wb_ref; |
de57606c2 ceph: client types |
300 301 |
int i_wrbuffer_ref, i_wrbuffer_ref_head; u32 i_shared_gen; /* increment each time we get FILE_SHARED */ |
cd045cb42 ceph: fix rdcache... |
302 |
u32 i_rdcache_gen; /* incremented each time we get FILE_CACHE. */ |
de57606c2 ceph: client types |
303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 |
u32 i_rdcache_revoking; /* RDCACHE gen to async invalidate, if any */ struct list_head i_unsafe_writes; /* uncommitted sync writes */ struct list_head i_unsafe_dirops; /* uncommitted mds dir ops */ spinlock_t i_unsafe_lock; struct ceph_snap_realm *i_snap_realm; /* snap realm (if caps) */ int i_snap_realm_counter; /* snap realm (if caps) */ struct list_head i_snap_realm_item; struct list_head i_snap_flush_item; struct work_struct i_wb_work; /* writeback work */ struct work_struct i_pg_inv_work; /* page invalidation work */ struct work_struct i_vmtruncate_work; struct inode vfs_inode; /* at end */ }; static inline struct ceph_inode_info *ceph_inode(struct inode *inode) { |
fbbccec9c ceph: replace lis... |
324 |
return container_of(inode, struct ceph_inode_info, vfs_inode); |
de57606c2 ceph: client types |
325 |
} |
ad1fee96c ceph: add ino32 m... |
326 327 328 329 330 331 332 333 334 |
static inline struct ceph_fs_client *ceph_inode_to_client(struct inode *inode) { return (struct ceph_fs_client *)inode->i_sb->s_fs_info; } static inline struct ceph_fs_client *ceph_sb_to_client(struct super_block *sb) { return (struct ceph_fs_client *)sb->s_fs_info; } |
3d14c5d2b ceph: factor out ... |
335 336 337 338 339 340 341 342 |
static inline struct ceph_vino ceph_vino(struct inode *inode) { return ceph_inode(inode)->i_vino; } /* * ino_t is <64 bits on many architectures, blech. * |
ad1fee96c ceph: add ino32 m... |
343 344 345 346 347 |
* i_ino (kernel inode) st_ino (userspace) * i386 32 32 * x86_64+ino32 64 32 * x86_64 64 64 */ |
3310f7541 ceph: fix 32-bit ... |
348 |
static inline u32 ceph_ino_to_ino32(__u64 vino) |
ad1fee96c ceph: add ino32 m... |
349 |
{ |
3310f7541 ceph: fix 32-bit ... |
350 351 |
u32 ino = vino & 0xffffffff; ino ^= vino >> 32; |
ad1fee96c ceph: add ino32 m... |
352 353 354 355 356 357 358 |
if (!ino) ino = 1; return ino; } /* * kernel i_ino value |
3d14c5d2b ceph: factor out ... |
359 360 361 |
*/ static inline ino_t ceph_vino_to_ino(struct ceph_vino vino) { |
3d14c5d2b ceph: factor out ... |
362 |
#if BITS_PER_LONG == 32 |
3310f7541 ceph: fix 32-bit ... |
363 364 365 |
return ceph_ino_to_ino32(vino.ino); #else return (ino_t)vino.ino; |
3d14c5d2b ceph: factor out ... |
366 |
#endif |
3d14c5d2b ceph: factor out ... |
367 |
} |
ad1fee96c ceph: add ino32 m... |
368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 |
/* * user-visible ino (stat, filldir) */ #if BITS_PER_LONG == 32 static inline ino_t ceph_translate_ino(struct super_block *sb, ino_t ino) { return ino; } #else static inline ino_t ceph_translate_ino(struct super_block *sb, ino_t ino) { if (ceph_test_mount_opt(ceph_sb_to_client(sb), INO32)) ino = ceph_ino_to_ino32(ino); return ino; } #endif |
3d14c5d2b ceph: factor out ... |
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 |
/* 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; } 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; } static inline struct inode *ceph_find_inode(struct super_block *sb, struct ceph_vino vino) { ino_t t = ceph_vino_to_ino(vino); return ilookup5(sb, t, ceph_ino_compare, &vino); } /* * Ceph inode. */ |
3d14c5d2b ceph: factor out ... |
415 416 417 |
#define CEPH_I_NODELAY 4 /* do not delay cap release */ #define CEPH_I_FLUSH 8 /* do not delay flush of dirty metadata */ #define CEPH_I_NOFLUSH 16 /* do not flush dirty caps */ |
de57606c2 ceph: client types |
418 419 420 |
static inline void ceph_i_clear(struct inode *inode, unsigned mask) { struct ceph_inode_info *ci = ceph_inode(inode); |
be655596b ceph: use i_ceph_... |
421 |
spin_lock(&ci->i_ceph_lock); |
de57606c2 ceph: client types |
422 |
ci->i_ceph_flags &= ~mask; |
be655596b ceph: use i_ceph_... |
423 |
spin_unlock(&ci->i_ceph_lock); |
de57606c2 ceph: client types |
424 425 426 427 428 |
} static inline void ceph_i_set(struct inode *inode, unsigned mask) { struct ceph_inode_info *ci = ceph_inode(inode); |
be655596b ceph: use i_ceph_... |
429 |
spin_lock(&ci->i_ceph_lock); |
de57606c2 ceph: client types |
430 |
ci->i_ceph_flags |= mask; |
be655596b ceph: use i_ceph_... |
431 |
spin_unlock(&ci->i_ceph_lock); |
de57606c2 ceph: client types |
432 433 434 435 436 437 |
} static inline bool ceph_i_test(struct inode *inode, unsigned mask) { struct ceph_inode_info *ci = ceph_inode(inode); bool r; |
be655596b ceph: use i_ceph_... |
438 |
spin_lock(&ci->i_ceph_lock); |
de57606c2 ceph: client types |
439 |
r = (ci->i_ceph_flags & mask) == mask; |
be655596b ceph: use i_ceph_... |
440 |
spin_unlock(&ci->i_ceph_lock); |
de57606c2 ceph: client types |
441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 |
return r; } /* 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); |
de57606c2 ceph: client types |
456 457 458 459 460 461 462 463 464 |
static inline struct ceph_dentry_info *ceph_dentry(struct dentry *dentry) { return (struct ceph_dentry_info *)dentry->d_fsdata; } static inline loff_t ceph_make_fpos(unsigned frag, unsigned off) { return ((loff_t)frag << 32) | (loff_t)off; } |
de57606c2 ceph: client types |
465 |
/* |
c6ffe1001 ceph: use new D_C... |
466 467 468 469 470 471 472 |
* set/clear directory D_COMPLETE flag */ void ceph_dir_set_complete(struct inode *inode); void ceph_dir_clear_complete(struct inode *inode); bool ceph_dir_test_complete(struct inode *inode); /* |
de57606c2 ceph: client types |
473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 |
* 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_other(struct ceph_inode_info *ci, struct ceph_cap *cap); static inline int ceph_caps_issued(struct ceph_inode_info *ci) { int issued; |
be655596b ceph: use i_ceph_... |
488 |
spin_lock(&ci->i_ceph_lock); |
de57606c2 ceph: client types |
489 |
issued = __ceph_caps_issued(ci, NULL); |
be655596b ceph: use i_ceph_... |
490 |
spin_unlock(&ci->i_ceph_lock); |
de57606c2 ceph: client types |
491 492 493 494 495 496 497 |
return issued; } static inline int ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch) { int r; |
be655596b ceph: use i_ceph_... |
498 |
spin_lock(&ci->i_ceph_lock); |
de57606c2 ceph: client types |
499 |
r = __ceph_caps_issued_mask(ci, mask, touch); |
be655596b ceph: use i_ceph_... |
500 |
spin_unlock(&ci->i_ceph_lock); |
de57606c2 ceph: client types |
501 502 503 504 505 506 507 |
return r; } static inline int __ceph_caps_dirty(struct ceph_inode_info *ci) { return ci->i_dirty_caps | ci->i_flushing_caps; } |
fca65b4ad ceph: do not call... |
508 |
extern int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask); |
de57606c2 ceph: client types |
509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 |
extern int ceph_caps_revoking(struct ceph_inode_info *ci, int mask); extern int __ceph_caps_used(struct ceph_inode_info *ci); extern int __ceph_caps_file_wanted(struct ceph_inode_info *ci); /* * wanted, by virtue of open file modes AND cap refs (buffered/cached data) */ static inline int __ceph_caps_wanted(struct ceph_inode_info *ci) { int w = __ceph_caps_file_wanted(ci) | __ceph_caps_used(ci); if (w & CEPH_CAP_FILE_BUFFER) w |= CEPH_CAP_FILE_EXCL; /* we want EXCL if dirty data */ return w; } /* what the mds thinks we want */ extern int __ceph_caps_mds_wanted(struct ceph_inode_info *ci); |
37151668b ceph: do caps acc... |
528 529 530 531 532 533 534 |
extern void ceph_caps_init(struct ceph_mds_client *mdsc); extern void ceph_caps_finalize(struct ceph_mds_client *mdsc); extern void ceph_adjust_min_caps(struct ceph_mds_client *mdsc, int delta); extern int ceph_reserve_caps(struct ceph_mds_client *mdsc, struct ceph_cap_reservation *ctx, int need); extern int ceph_unreserve_caps(struct ceph_mds_client *mdsc, struct ceph_cap_reservation *ctx); |
3d14c5d2b ceph: factor out ... |
535 |
extern void ceph_reservation_status(struct ceph_fs_client *client, |
de57606c2 ceph: client types |
536 |
int *total, int *avail, int *used, |
85ccce43a ceph: clean up re... |
537 |
int *reserved, int *min); |
de57606c2 ceph: client types |
538 |
|
de57606c2 ceph: client types |
539 |
|
de57606c2 ceph: client types |
540 541 542 543 |
/* * we keep buffered readdir results attached to file->private_data */ |
4918b6d14 ceph: add F_SYNC ... |
544 |
#define CEPH_F_SYNC 1 |
9cfa1098d ceph: use flag bi... |
545 |
#define CEPH_F_ATEND 2 |
4918b6d14 ceph: add F_SYNC ... |
546 |
|
de57606c2 ceph: client types |
547 |
struct ceph_file_info { |
252c6728d ceph: add flags f... |
548 549 |
short fmode; /* initialized on open */ short flags; /* CEPH_F_* */ |
de57606c2 ceph: client types |
550 551 552 553 |
/* readdir: position within the dir */ u32 frag; struct ceph_mds_request *last_readdir; |
de57606c2 ceph: client types |
554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 |
/* readdir: position within a frag */ unsigned offset; /* offset of last chunk, adjusted for . and .. */ u64 next_offset; /* offset of next chunk (last_name's + 1) */ char *last_name; /* last entry in previous chunk */ struct dentry *dentry; /* next dentry (for dcache readdir) */ unsigned long dir_release_count; /* used for -o dirstat read() on directory thing */ char *dir_info; int dir_info_len; }; /* |
de57606c2 ceph: client types |
570 571 572 573 574 575 576 577 578 579 580 |
* 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; atomic_t nref; |
a105f00cf ceph: use rbtree ... |
581 |
struct rb_node node; |
de57606c2 ceph: client types |
582 583 584 585 586 587 588 589 590 591 592 593 594 595 |
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 */ int num_prior_parent_snaps; /* had prior to parent_since */ u64 *snaps; /* snaps specific to this realm */ int 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 */ |
ae00d4f37 ceph: fix cap_sna... |
596 |
struct list_head dirty_item; /* if realm needs new context */ |
de57606c2 ceph: client types |
597 598 599 600 601 602 |
/* 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; }; |
3d14c5d2b ceph: factor out ... |
603 |
static inline int default_congestion_kb(void) |
de57606c2 ceph: client types |
604 |
{ |
3d14c5d2b ceph: factor out ... |
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 |
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; |
de57606c2 ceph: client types |
630 631 632 633 634 635 636 637 638 639 640 641 642 643 |
} /* 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); extern void ceph_handle_snap(struct ceph_mds_client *mdsc, |
2600d2dd5 ceph: drop messag... |
644 |
struct ceph_mds_session *session, |
de57606c2 ceph: client types |
645 |
struct ceph_msg *msg); |
fc837c8f0 ceph: queue_cap_s... |
646 |
extern void ceph_queue_cap_snap(struct ceph_inode_info *ci); |
de57606c2 ceph: client types |
647 648 649 650 651 652 653 654 655 656 657 658 659 660 |
extern int __ceph_finish_cap_snap(struct ceph_inode_info *ci, struct ceph_cap_snap *capsnap); extern void ceph_cleanup_empty_realms(struct ceph_mds_client *mdsc); /* * 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_entry(ci->i_cap_snaps.prev, struct ceph_cap_snap, ci_item)->writing; } |
de57606c2 ceph: client types |
661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 |
/* inode.c */ extern const struct inode_operations ceph_file_iops; extern struct inode *ceph_alloc_inode(struct super_block *sb); extern void ceph_destroy_inode(struct inode *inode); extern struct inode *ceph_get_inode(struct super_block *sb, struct ceph_vino vino); 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 timespec *ctime, struct timespec *mtime, struct timespec *atime); extern int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, struct ceph_mds_session *session); 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 int ceph_inode_set_size(struct inode *inode, loff_t size); |
de57606c2 ceph: client types |
684 |
extern void __ceph_do_pending_vmtruncate(struct inode *inode); |
3c6f6b79a ceph: cleanup asy... |
685 686 687 688 |
extern void ceph_queue_vmtruncate(struct inode *inode); extern void ceph_queue_invalidate(struct inode *inode); extern void ceph_queue_writeback(struct inode *inode); |
de57606c2 ceph: client types |
689 690 |
extern int ceph_do_getattr(struct inode *inode, int mask); |
10556cb21 ->permission() sa... |
691 |
extern int ceph_permission(struct inode *inode, int mask); |
de57606c2 ceph: client types |
692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 |
extern int ceph_setattr(struct dentry *dentry, struct iattr *attr); extern int ceph_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat); /* xattr.c */ extern int ceph_setxattr(struct dentry *, const char *, const void *, size_t, int); extern ssize_t ceph_getxattr(struct dentry *, const char *, void *, size_t); extern ssize_t ceph_listxattr(struct dentry *, char *, size_t); extern int ceph_removexattr(struct dentry *, const char *); extern void __ceph_build_xattrs_blob(struct ceph_inode_info *ci); extern void __ceph_destroy_xattrs(struct ceph_inode_info *ci); /* 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 int ceph_add_cap(struct inode *inode, struct ceph_mds_session *session, u64 cap_id, int fmode, unsigned issued, unsigned wanted, unsigned cap, unsigned seq, u64 realmino, int flags, struct ceph_cap_reservation *caps_reservation); |
7c1332b8c ceph: fix iterate... |
714 |
extern void __ceph_remove_cap(struct ceph_cap *cap); |
de57606c2 ceph: client types |
715 716 |
static inline void ceph_remove_cap(struct ceph_cap *cap) { |
be655596b ceph: use i_ceph_... |
717 |
spin_lock(&cap->ci->i_ceph_lock); |
7c1332b8c ceph: fix iterate... |
718 |
__ceph_remove_cap(cap); |
be655596b ceph: use i_ceph_... |
719 |
spin_unlock(&cap->ci->i_ceph_lock); |
de57606c2 ceph: client types |
720 |
} |
37151668b ceph: do caps acc... |
721 722 |
extern void ceph_put_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap); |
de57606c2 ceph: client types |
723 724 |
extern void ceph_queue_caps_release(struct inode *inode); |
f1a3d5721 ceph: update for ... |
725 |
extern int ceph_write_inode(struct inode *inode, struct writeback_control *wbc); |
02c24a821 fs: push i_mutex ... |
726 727 |
extern int ceph_fsync(struct file *file, loff_t start, loff_t end, int datasync); |
de57606c2 ceph: client types |
728 729 |
extern void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc, struct ceph_mds_session *session); |
2bc50259f ceph: add ceph_ge... |
730 731 |
extern struct ceph_cap *ceph_get_cap_for_mds(struct ceph_inode_info *ci, int mds); |
de57606c2 ceph: client types |
732 733 734 735 736 737 |
extern int ceph_get_cap_mds(struct inode *inode); 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_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr, struct ceph_snap_context *snapc); extern void __ceph_flush_snaps(struct ceph_inode_info *ci, |
e835124c2 ceph: only send o... |
738 739 |
struct ceph_mds_session **psession, int again); |
de57606c2 ceph: client types |
740 741 |
extern void ceph_check_caps(struct ceph_inode_info *ci, int flags, struct ceph_mds_session *session); |
afcdaea3f ceph: flush dirty... |
742 743 |
extern void ceph_check_delayed_caps(struct ceph_mds_client *mdsc); extern void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc); |
de57606c2 ceph: client types |
744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 |
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, int mds, int drop, int unless); extern int ceph_get_caps(struct ceph_inode_info *ci, int need, int want, int *got, loff_t endoff); /* for counting open files by mode */ static inline void __ceph_get_fmode(struct ceph_inode_info *ci, int mode) { ci->i_nr_by_mode[mode]++; } extern void ceph_put_fmode(struct ceph_inode_info *ci, int mode); /* addr.c */ extern const struct address_space_operations ceph_aops; extern int ceph_mmap(struct file *file, struct vm_area_struct *vma); /* file.c */ extern const struct file_operations ceph_file_fops; extern const struct address_space_operations ceph_aops; |
3d14c5d2b ceph: factor out ... |
767 768 769 770 771 772 773 |
extern int ceph_copy_to_page_vector(struct page **pages, const char *data, loff_t off, size_t len); extern int ceph_copy_from_page_vector(struct page **pages, char *data, loff_t off, size_t len); extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags); |
de57606c2 ceph: client types |
774 775 776 777 778 |
extern int ceph_open(struct inode *inode, struct file *file); extern struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry, struct nameidata *nd, int mode, int locked_dir); extern int ceph_release(struct inode *inode, struct file *filp); |
de57606c2 ceph: client types |
779 780 781 782 |
/* dir.c */ extern const struct file_operations ceph_dir_fops; extern const struct inode_operations ceph_dir_iops; |
52dfb8ac0 ceph: constify de... |
783 |
extern const struct dentry_operations ceph_dentry_ops, ceph_snap_dentry_ops, |
de57606c2 ceph: client types |
784 785 786 |
ceph_snapdir_dentry_ops; extern int ceph_handle_notrace_create(struct inode *dir, struct dentry *dentry); |
468640e32 ceph: fix ceph_lo... |
787 788 |
extern int ceph_handle_snapdir(struct ceph_mds_request *req, struct dentry *dentry, int err); |
de57606c2 ceph: client types |
789 790 791 792 793 794 |
extern struct dentry *ceph_finish_lookup(struct ceph_mds_request *req, struct dentry *dentry, int err); extern void ceph_dentry_lru_add(struct dentry *dn); extern void ceph_dentry_lru_touch(struct dentry *dn); extern void ceph_dentry_lru_del(struct dentry *dn); |
81a6cf2d3 ceph: invalidate ... |
795 |
extern void ceph_invalidate_dentry_lease(struct dentry *dentry); |
e5f86dc37 ceph: avoid d_par... |
796 |
extern unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn); |
5f21c96dd ceph: protect acc... |
797 |
extern struct inode *ceph_get_dentry_parent_inode(struct dentry *dentry); |
de57606c2 ceph: client types |
798 799 800 801 802 803 804 805 806 807 808 809 810 |
/* * our d_ops vary depending on whether the inode is live, * snapshotted (read-only), or a virtual ".snap" directory. */ int ceph_init_dentry(struct dentry *dentry); /* 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; |
40819f6fb ceph: add flock/f... |
811 812 813 814 815 816 817 |
/* locks.c */ 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(struct inode *i, struct ceph_pagelist *p, int p_locks, int f_locks); extern int lock_to_ceph_filelock(struct file_lock *fl, struct ceph_filelock *c); |
3d14c5d2b ceph: factor out ... |
818 819 820 |
/* debugfs.c */ extern int ceph_fs_debugfs_init(struct ceph_fs_client *client); extern void ceph_fs_debugfs_cleanup(struct ceph_fs_client *client); |
de57606c2 ceph: client types |
821 |
#endif /* _FS_CEPH_SUPER_H */ |