1/* SPDX-License-Identifier: GPL-2.0 */ 2#ifndef _FS_CEPH_SUPER_H 3#define _FS_CEPH_SUPER_H 4 5#include <linux/ceph/ceph_debug.h> 6 7#include <asm/unaligned.h> 8#include <linux/backing-dev.h> 9#include <linux/completion.h> 10#include <linux/exportfs.h> 11#include <linux/fs.h> 12#include <linux/mempool.h> 13#include <linux/pagemap.h> 14#include <linux/wait.h> 15#include <linux/writeback.h> 16#include <linux/slab.h> 17#include <linux/posix_acl.h> 18#include <linux/refcount.h> 19#include <linux/security.h> 20#include <linux/netfs.h> 21#include <linux/fscache.h> 22#include <linux/hashtable.h> 23 24#include <linux/ceph/libceph.h> 25#include "crypto.h" 26 27/* large granularity for statfs utilization stats to facilitate 28 * large volume sizes on 32-bit machines. */ 29#define CEPH_BLOCK_SHIFT 22 /* 4 MB */ 30#define CEPH_BLOCK (1 << CEPH_BLOCK_SHIFT) 31#define CEPH_4K_BLOCK_SHIFT 12 /* 4 KB */ 32 33#define CEPH_MOUNT_OPT_CLEANRECOVER (1<<1) /* auto reonnect (clean mode) after blocklisted */ 34#define CEPH_MOUNT_OPT_DIRSTAT (1<<4) /* `cat dirname` for stats */ 35#define CEPH_MOUNT_OPT_RBYTES (1<<5) /* dir st_bytes = rbytes */ 36#define CEPH_MOUNT_OPT_NOASYNCREADDIR (1<<7) /* no dcache readdir */ 37#define CEPH_MOUNT_OPT_INO32 (1<<8) /* 32 bit inos */ 38#define CEPH_MOUNT_OPT_DCACHE (1<<9) /* use dcache for readdir etc */ 39#define CEPH_MOUNT_OPT_FSCACHE (1<<10) /* use fscache */ 40#define CEPH_MOUNT_OPT_NOPOOLPERM (1<<11) /* no pool permission check */ 41#define CEPH_MOUNT_OPT_MOUNTWAIT (1<<12) /* mount waits if no mds is up */ 42#define CEPH_MOUNT_OPT_NOQUOTADF (1<<13) /* no root dir quota in statfs */ 43#define CEPH_MOUNT_OPT_NOCOPYFROM (1<<14) /* don't use RADOS 'copy-from' op */ 44#define CEPH_MOUNT_OPT_ASYNC_DIROPS (1<<15) /* allow async directory ops */ 45#define CEPH_MOUNT_OPT_NOPAGECACHE (1<<16) /* bypass pagecache altogether */ 46#define CEPH_MOUNT_OPT_SPARSEREAD (1<<17) /* always do sparse reads */ 47 48#define CEPH_MOUNT_OPT_DEFAULT \ 49 (CEPH_MOUNT_OPT_DCACHE | \ 50 CEPH_MOUNT_OPT_NOCOPYFROM | \ 51 CEPH_MOUNT_OPT_ASYNC_DIROPS) 52 53#define ceph_set_mount_opt(fsc, opt) \ 54 (fsc)->mount_options->flags |= CEPH_MOUNT_OPT_##opt 55#define ceph_clear_mount_opt(fsc, opt) \ 56 (fsc)->mount_options->flags &= ~CEPH_MOUNT_OPT_##opt 57#define ceph_test_mount_opt(fsc, opt) \ 58 (!!((fsc)->mount_options->flags & CEPH_MOUNT_OPT_##opt)) 59 60/* max size of osd read request, limited by libceph */ 61#define CEPH_MAX_READ_SIZE CEPH_MSG_MAX_DATA_LEN 62/* osd has a configurable limitaion of max write size. 63 * CEPH_MSG_MAX_DATA_LEN should be small enough. */ 64#define CEPH_MAX_WRITE_SIZE CEPH_MSG_MAX_DATA_LEN 65#define CEPH_RASIZE_DEFAULT (8192*1024) /* max readahead */ 66#define CEPH_MAX_READDIR_DEFAULT 1024 67#define CEPH_MAX_READDIR_BYTES_DEFAULT (512*1024) 68#define CEPH_SNAPDIRNAME_DEFAULT ".snap" 69 70/* 71 * Delay telling the MDS we no longer want caps, in case we reopen 72 * the file. Delay a minimum amount of time, even if we send a cap 73 * message for some other reason. Otherwise, take the oppotunity to 74 * update the mds to avoid sending another message later. 75 */ 76#define CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT 5 /* cap release delay */ 77#define CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT 60 /* cap release delay */ 78 79struct ceph_mount_options { 80 unsigned int flags; 81 82 unsigned int wsize; /* max write size */ 83 unsigned int rsize; /* max read size */ 84 unsigned int rasize; /* max readahead */ 85 unsigned int congestion_kb; /* max writeback in flight */ 86 unsigned int caps_wanted_delay_min, caps_wanted_delay_max; 87 int caps_max; 88 unsigned int max_readdir; /* max readdir result (entries) */ 89 unsigned int max_readdir_bytes; /* max readdir result (bytes) */ 90 91 bool new_dev_syntax; 92 93 /* 94 * everything above this point can be memcmp'd; everything below 95 * is handled in compare_mount_options() 96 */ 97 98 char *snapdir_name; /* default ".snap" */ 99 char *mds_namespace; /* default NULL */ 100 char *server_path; /* default NULL (means "/") */ 101 char *fscache_uniq; /* default NULL */ 102 char *mon_addr; 103 struct fscrypt_dummy_policy dummy_enc_policy; 104}; 105 106/* mount state */ 107enum { 108 CEPH_MOUNT_MOUNTING, 109 CEPH_MOUNT_MOUNTED, 110 CEPH_MOUNT_UNMOUNTING, 111 CEPH_MOUNT_UNMOUNTED, 112 CEPH_MOUNT_SHUTDOWN, 113 CEPH_MOUNT_RECOVER, 114 CEPH_MOUNT_FENCE_IO, 115}; 116 117#define CEPH_ASYNC_CREATE_CONFLICT_BITS 8 118 119struct ceph_fs_client { 120 struct super_block *sb; 121 122 struct list_head metric_wakeup; 123 124 struct ceph_mount_options *mount_options; 125 struct ceph_client *client; 126 127 int mount_state; 128 129 bool blocklisted; 130 131 bool have_copy_from2; 132 133 u32 filp_gen; 134 loff_t max_file_size; 135 136 struct ceph_mds_client *mdsc; 137 138 atomic_long_t writeback_count; 139 bool write_congested; 140 141 struct workqueue_struct *inode_wq; 142 struct workqueue_struct *cap_wq; 143 144 DECLARE_HASHTABLE(async_unlink_conflict, CEPH_ASYNC_CREATE_CONFLICT_BITS); 145 spinlock_t async_unlink_conflict_lock; 146 147#ifdef CONFIG_DEBUG_FS 148 struct dentry *debugfs_dentry_lru, *debugfs_caps; 149 struct dentry *debugfs_congestion_kb; 150 struct dentry *debugfs_bdi; 151 struct dentry *debugfs_mdsc, *debugfs_mdsmap; 152 struct dentry *debugfs_status; 153 struct dentry *debugfs_mds_sessions; 154 struct dentry *debugfs_metrics_dir; 155#endif 156 157#ifdef CONFIG_CEPH_FSCACHE 158 struct fscache_volume *fscache; 159#endif 160#ifdef CONFIG_FS_ENCRYPTION 161 struct fscrypt_dummy_policy fsc_dummy_enc_policy; 162#endif 163}; 164 165/* 166 * File i/o capability. This tracks shared state with the metadata 167 * server that allows us to cache or writeback attributes or to read 168 * and write data. For any given inode, we should have one or more 169 * capabilities, one issued by each metadata server, and our 170 * cumulative access is the OR of all issued capabilities. 171 * 172 * Each cap is referenced by the inode's i_caps rbtree and by per-mds 173 * session capability lists. 174 */ 175struct ceph_cap { 176 struct ceph_inode_info *ci; 177 struct rb_node ci_node; /* per-ci cap tree */ 178 struct ceph_mds_session *session; 179 struct list_head session_caps; /* per-session caplist */ 180 u64 cap_id; /* unique cap id (mds provided) */ 181 union { 182 /* in-use caps */ 183 struct { 184 int issued; /* latest, from the mds */ 185 int implemented; /* implemented superset of 186 issued (for revocation) */ 187 int mds; /* mds index for this cap */ 188 int mds_wanted; /* caps wanted from this mds */ 189 }; 190 /* caps to release */ 191 struct { 192 u64 cap_ino; 193 int queue_release; 194 }; 195 }; 196 u32 seq, issue_seq, mseq; 197 u32 cap_gen; /* active/stale cycle */ 198 unsigned long last_used; 199 struct list_head caps_item; 200}; 201 202#define CHECK_CAPS_AUTHONLY 1 /* only check auth cap */ 203#define CHECK_CAPS_FLUSH 2 /* flush any dirty caps */ 204#define CHECK_CAPS_NOINVAL 4 /* don't invalidate pagecache */ 205 206struct ceph_cap_flush { 207 u64 tid; 208 int caps; 209 bool wake; /* wake up flush waiters when finish ? */ 210 bool is_capsnap; /* true means capsnap */ 211 struct list_head g_list; // global 212 struct list_head i_list; // per inode 213}; 214 215/* 216 * Snapped cap state that is pending flush to mds. When a snapshot occurs, 217 * we first complete any in-process sync writes and writeback any dirty 218 * data before flushing the snapped state (tracked here) back to the MDS. 219 */ 220struct ceph_cap_snap { 221 refcount_t nref; 222 struct list_head ci_item; 223 224 struct ceph_cap_flush cap_flush; 225 226 u64 follows; 227 int issued, dirty; 228 struct ceph_snap_context *context; 229 230 umode_t mode; 231 kuid_t uid; 232 kgid_t gid; 233 234 struct ceph_buffer *xattr_blob; 235 u64 xattr_version; 236 237 u64 size; 238 u64 change_attr; 239 struct timespec64 mtime, atime, ctime, btime; 240 u64 time_warp_seq; 241 u64 truncate_size; 242 u32 truncate_seq; 243 int writing; /* a sync write is still in progress */ 244 int dirty_pages; /* dirty pages awaiting writeback */ 245 bool inline_data; 246 bool need_flush; 247}; 248 249static inline void ceph_put_cap_snap(struct ceph_cap_snap *capsnap) 250{ 251 if (refcount_dec_and_test(&capsnap->nref)) { 252 if (capsnap->xattr_blob) 253 ceph_buffer_put(capsnap->xattr_blob); 254 kmem_cache_free(ceph_cap_snap_cachep, capsnap); 255 } 256} 257 258/* 259 * The frag tree describes how a directory is fragmented, potentially across 260 * multiple metadata servers. It is also used to indicate points where 261 * metadata authority is delegated, and whether/where metadata is replicated. 262 * 263 * A _leaf_ frag will be present in the i_fragtree IFF there is 264 * delegation info. That is, if mds >= 0 || ndist > 0. 265 */ 266#define CEPH_MAX_DIRFRAG_REP 4 267 268struct ceph_inode_frag { 269 struct rb_node node; 270 271 /* fragtree state */ 272 u32 frag; 273 int split_by; /* i.e. 2^(split_by) children */ 274 275 /* delegation and replication info */ 276 int mds; /* -1 if same authority as parent */ 277 int ndist; /* >0 if replicated */ 278 int dist[CEPH_MAX_DIRFRAG_REP]; 279}; 280 281/* 282 * We cache inode xattrs as an encoded blob until they are first used, 283 * at which point we parse them into an rbtree. 284 */ 285struct ceph_inode_xattr { 286 struct rb_node node; 287 288 const char *name; 289 int name_len; 290 const char *val; 291 int val_len; 292 int dirty; 293 294 int should_free_name; 295 int should_free_val; 296}; 297 298/* 299 * Ceph dentry state 300 */ 301struct ceph_dentry_info { 302 struct dentry *dentry; 303 struct ceph_mds_session *lease_session; 304 struct list_head lease_list; 305 struct hlist_node hnode; 306 unsigned long flags; 307 int lease_shared_gen; 308 u32 lease_gen; 309 u32 lease_seq; 310 unsigned long lease_renew_after, lease_renew_from; 311 unsigned long time; 312 u64 offset; 313}; 314 315#define CEPH_DENTRY_REFERENCED (1 << 0) 316#define CEPH_DENTRY_LEASE_LIST (1 << 1) 317#define CEPH_DENTRY_SHRINK_LIST (1 << 2) 318#define CEPH_DENTRY_PRIMARY_LINK (1 << 3) 319#define CEPH_DENTRY_ASYNC_UNLINK_BIT (4) 320#define CEPH_DENTRY_ASYNC_UNLINK (1 << CEPH_DENTRY_ASYNC_UNLINK_BIT) 321#define CEPH_DENTRY_ASYNC_CREATE_BIT (5) 322#define CEPH_DENTRY_ASYNC_CREATE (1 << CEPH_DENTRY_ASYNC_CREATE_BIT) 323 324struct ceph_inode_xattrs_info { 325 /* 326 * (still encoded) xattr blob. we avoid the overhead of parsing 327 * this until someone actually calls getxattr, etc. 328 * 329 * blob->vec.iov_len == 4 implies there are no xattrs; blob == 330 * NULL means we don't know. 331 */ 332 struct ceph_buffer *blob, *prealloc_blob; 333 334 struct rb_root index; 335 bool dirty; 336 int count; 337 int names_size; 338 int vals_size; 339 u64 version, index_version; 340}; 341 342/* 343 * Ceph inode. 344 */ 345struct ceph_inode_info { 346 struct netfs_inode netfs; /* Netfslib context and vfs inode */ 347 struct ceph_vino i_vino; /* ceph ino + snap */ 348 349 spinlock_t i_ceph_lock; 350 351 u64 i_version; 352 u64 i_inline_version; 353 u32 i_time_warp_seq; 354 355 unsigned long i_ceph_flags; 356 atomic64_t i_release_count; 357 atomic64_t i_ordered_count; 358 atomic64_t i_complete_seq[2]; 359 360 struct ceph_dir_layout i_dir_layout; 361 struct ceph_file_layout i_layout; 362 struct ceph_file_layout i_cached_layout; // for async creates 363 char *i_symlink; 364 365 /* for dirs */ 366 struct timespec64 i_rctime; 367 u64 i_rbytes, i_rfiles, i_rsubdirs, i_rsnaps; 368 u64 i_files, i_subdirs; 369 370 /* quotas */ 371 u64 i_max_bytes, i_max_files; 372 373 s32 i_dir_pin; 374 375 struct rb_root i_fragtree; 376 int i_fragtree_nsplits; 377 struct mutex i_fragtree_mutex; 378 379 struct ceph_inode_xattrs_info i_xattrs; 380 381 /* capabilities. protected _both_ by i_ceph_lock and cap->session's 382 * s_mutex. */ 383 struct rb_root i_caps; /* cap list */ 384 struct ceph_cap *i_auth_cap; /* authoritative cap, if any */ 385 unsigned i_dirty_caps, i_flushing_caps; /* mask of dirtied fields */ 386 387 /* 388 * Link to the auth cap's session's s_cap_dirty list. s_cap_dirty 389 * is protected by the mdsc->cap_dirty_lock, but each individual item 390 * is also protected by the inode's i_ceph_lock. Walking s_cap_dirty 391 * requires the mdsc->cap_dirty_lock. List presence for an item can 392 * be tested under the i_ceph_lock. Changing anything requires both. 393 */ 394 struct list_head i_dirty_item; 395 396 /* 397 * Link to session's s_cap_flushing list. Protected in a similar 398 * fashion to i_dirty_item, but also by the s_mutex for changes. The 399 * s_cap_flushing list can be walked while holding either the s_mutex 400 * or msdc->cap_dirty_lock. List presence can also be checked while 401 * holding the i_ceph_lock for this inode. 402 */ 403 struct list_head i_flushing_item; 404 405 /* we need to track cap writeback on a per-cap-bit basis, to allow 406 * overlapping, pipelined cap flushes to the mds. we can probably 407 * reduce the tid to 8 bits if we're concerned about inode size. */ 408 struct ceph_cap_flush *i_prealloc_cap_flush; 409 struct list_head i_cap_flush_list; 410 wait_queue_head_t i_cap_wq; /* threads waiting on a capability */ 411 unsigned long i_hold_caps_max; /* jiffies */ 412 struct list_head i_cap_delay_list; /* for delayed cap release to mds */ 413 struct ceph_cap_reservation i_cap_migration_resv; 414 struct list_head i_cap_snaps; /* snapped state pending flush to mds */ 415 struct ceph_snap_context *i_head_snapc; /* set if wr_buffer_head > 0 or 416 dirty|flushing caps */ 417 unsigned i_snap_caps; /* cap bits for snapped files */ 418 419 unsigned long i_last_rd; 420 unsigned long i_last_wr; 421 int i_nr_by_mode[CEPH_FILE_MODE_BITS]; /* open file counts */ 422 423 struct mutex i_truncate_mutex; 424 u32 i_truncate_seq; /* last truncate to smaller size */ 425 u64 i_truncate_size; /* and the size we last truncated down to */ 426 int i_truncate_pending; /* still need to call vmtruncate */ 427 /* 428 * For none fscrypt case it equals to i_truncate_size or it will 429 * equals to fscrypt_file_size 430 */ 431 u64 i_truncate_pagecache_size; 432 433 u64 i_max_size; /* max file size authorized by mds */ 434 u64 i_reported_size; /* (max_)size reported to or requested of mds */ 435 u64 i_wanted_max_size; /* offset we'd like to write too */ 436 u64 i_requested_max_size; /* max_size we've requested */ 437 438 /* held references to caps */ 439 int i_pin_ref; 440 int i_rd_ref, i_rdcache_ref, i_wr_ref, i_wb_ref, i_fx_ref; 441 int i_wrbuffer_ref, i_wrbuffer_ref_head; 442 atomic_t i_filelock_ref; 443 atomic_t i_shared_gen; /* increment each time we get FILE_SHARED */ 444 u32 i_rdcache_gen; /* incremented each time we get FILE_CACHE. */ 445 u32 i_rdcache_revoking; /* RDCACHE gen to async invalidate, if any */ 446 447 struct list_head i_unsafe_dirops; /* uncommitted mds dir ops */ 448 struct list_head i_unsafe_iops; /* uncommitted mds inode ops */ 449 spinlock_t i_unsafe_lock; 450 451 union { 452 struct ceph_snap_realm *i_snap_realm; /* snap realm (if caps) */ 453 struct ceph_snapid_map *i_snapid_map; /* snapid -> dev_t */ 454 }; 455 struct list_head i_snap_realm_item; 456 struct list_head i_snap_flush_item; 457 struct timespec64 i_btime; 458 struct timespec64 i_snap_btime; 459 460 struct work_struct i_work; 461 unsigned long i_work_mask; 462 463#ifdef CONFIG_FS_ENCRYPTION 464 u32 fscrypt_auth_len; 465 u32 fscrypt_file_len; 466 u8 *fscrypt_auth; 467 u8 *fscrypt_file; 468#endif 469}; 470 471struct ceph_netfs_request_data { 472 int caps; 473 474 /* 475 * Maximum size of a file readahead request. 476 * The fadvise could update the bdi's default ra_pages. 477 */ 478 unsigned int file_ra_pages; 479 480 /* Set it if fadvise disables file readahead entirely */ 481 bool file_ra_disabled; 482}; 483 484static inline struct ceph_inode_info * 485ceph_inode(const struct inode *inode) 486{ 487 return container_of(inode, struct ceph_inode_info, netfs.inode); 488} 489 490static inline struct ceph_fs_client * 491ceph_inode_to_client(const struct inode *inode) 492{ 493 return (struct ceph_fs_client *)inode->i_sb->s_fs_info; 494} 495 496static inline struct ceph_fs_client * 497ceph_sb_to_client(const struct super_block *sb) 498{ 499 return (struct ceph_fs_client *)sb->s_fs_info; 500} 501 502static inline struct ceph_mds_client * 503ceph_sb_to_mdsc(const struct super_block *sb) 504{ 505 return (struct ceph_mds_client *)ceph_sb_to_client(sb)->mdsc; 506} 507 508static inline struct ceph_vino 509ceph_vino(const struct inode *inode) 510{ 511 return ceph_inode(inode)->i_vino; 512} 513 514static inline u32 ceph_ino_to_ino32(u64 vino) 515{ 516 u32 ino = vino & 0xffffffff; 517 ino ^= vino >> 32; 518 if (!ino) 519 ino = 2; 520 return ino; 521} 522 523/* 524 * Inode numbers in cephfs are 64 bits, but inode->i_ino is 32-bits on 525 * some arches. We generally do not use this value inside the ceph driver, but 526 * we do want to set it to something, so that generic vfs code has an 527 * appropriate value for tracepoints and the like. 528 */ 529static inline ino_t ceph_vino_to_ino_t(struct ceph_vino vino) 530{ 531 if (sizeof(ino_t) == sizeof(u32)) 532 return ceph_ino_to_ino32(vino.ino); 533 return (ino_t)vino.ino; 534} 535 536/* for printf-style formatting */ 537#define ceph_vinop(i) ceph_inode(i)->i_vino.ino, ceph_inode(i)->i_vino.snap 538 539static inline u64 ceph_ino(struct inode *inode) 540{ 541 return ceph_inode(inode)->i_vino.ino; 542} 543 544static inline u64 ceph_snap(struct inode *inode) 545{ 546 return ceph_inode(inode)->i_vino.snap; 547} 548 549/** 550 * ceph_present_ino - format an inode number for presentation to userland 551 * @sb: superblock where the inode lives 552 * @ino: inode number to (possibly) convert 553 * 554 * If the user mounted with the ino32 option, then the 64-bit value needs 555 * to be converted to something that can fit inside 32 bits. Note that 556 * internal kernel code never uses this value, so this is entirely for 557 * userland consumption. 558 */ 559static inline u64 ceph_present_ino(struct super_block *sb, u64 ino) 560{ 561 if (unlikely(ceph_test_mount_opt(ceph_sb_to_client(sb), INO32))) 562 return ceph_ino_to_ino32(ino); 563 return ino; 564} 565 566static inline u64 ceph_present_inode(struct inode *inode) 567{ 568 return ceph_present_ino(inode->i_sb, ceph_ino(inode)); 569} 570 571static inline int ceph_ino_compare(struct inode *inode, void *data) 572{ 573 struct ceph_vino *pvino = (struct ceph_vino *)data; 574 struct ceph_inode_info *ci = ceph_inode(inode); 575 return ci->i_vino.ino == pvino->ino && 576 ci->i_vino.snap == pvino->snap; 577} 578 579/* 580 * The MDS reserves a set of inodes for its own usage. These should never 581 * be accessible by clients, and so the MDS has no reason to ever hand these 582 * out. The range is CEPH_MDS_INO_MDSDIR_OFFSET..CEPH_INO_SYSTEM_BASE. 583 * 584 * These come from src/mds/mdstypes.h in the ceph sources. 585 */ 586#define CEPH_MAX_MDS 0x100 587#define CEPH_NUM_STRAY 10 588#define CEPH_MDS_INO_MDSDIR_OFFSET (1 * CEPH_MAX_MDS) 589#define CEPH_MDS_INO_LOG_OFFSET (2 * CEPH_MAX_MDS) 590#define CEPH_INO_SYSTEM_BASE ((6*CEPH_MAX_MDS) + (CEPH_MAX_MDS * CEPH_NUM_STRAY)) 591 592static inline bool ceph_vino_is_reserved(const struct ceph_vino vino) 593{ 594 if (vino.ino >= CEPH_INO_SYSTEM_BASE || 595 vino.ino < CEPH_MDS_INO_MDSDIR_OFFSET) 596 return false; 597 598 /* Don't warn on mdsdirs */ 599 WARN_RATELIMIT(vino.ino >= CEPH_MDS_INO_LOG_OFFSET, 600 "Attempt to access reserved inode number 0x%llx", 601 vino.ino); 602 return true; 603} 604 605static inline struct inode *ceph_find_inode(struct super_block *sb, 606 struct ceph_vino vino) 607{ 608 if (ceph_vino_is_reserved(vino)) 609 return NULL; 610 611 /* 612 * NB: The hashval will be run through the fs/inode.c hash function 613 * anyway, so there is no need to squash the inode number down to 614 * 32-bits first. Just use low-order bits on arches with 32-bit long. 615 */ 616 return ilookup5(sb, (unsigned long)vino.ino, ceph_ino_compare, &vino); 617} 618 619 620/* 621 * Ceph inode. 622 */ 623#define CEPH_I_DIR_ORDERED (1 << 0) /* dentries in dir are ordered */ 624#define CEPH_I_FLUSH (1 << 2) /* do not delay flush of dirty metadata */ 625#define CEPH_I_POOL_PERM (1 << 3) /* pool rd/wr bits are valid */ 626#define CEPH_I_POOL_RD (1 << 4) /* can read from pool */ 627#define CEPH_I_POOL_WR (1 << 5) /* can write to pool */ 628#define CEPH_I_SEC_INITED (1 << 6) /* security initialized */ 629#define CEPH_I_KICK_FLUSH (1 << 7) /* kick flushing caps */ 630#define CEPH_I_FLUSH_SNAPS (1 << 8) /* need flush snapss */ 631#define CEPH_I_ERROR_WRITE (1 << 9) /* have seen write errors */ 632#define CEPH_I_ERROR_FILELOCK (1 << 10) /* have seen file lock errors */ 633#define CEPH_I_ODIRECT (1 << 11) /* inode in direct I/O mode */ 634#define CEPH_ASYNC_CREATE_BIT (12) /* async create in flight for this */ 635#define CEPH_I_ASYNC_CREATE (1 << CEPH_ASYNC_CREATE_BIT) 636#define CEPH_I_SHUTDOWN (1 << 13) /* inode is no longer usable */ 637#define CEPH_I_ASYNC_CHECK_CAPS (1 << 14) /* check caps immediately after async 638 creating finishes */ 639 640/* 641 * Masks of ceph inode work. 642 */ 643#define CEPH_I_WORK_WRITEBACK 0 644#define CEPH_I_WORK_INVALIDATE_PAGES 1 645#define CEPH_I_WORK_VMTRUNCATE 2 646#define CEPH_I_WORK_CHECK_CAPS 3 647#define CEPH_I_WORK_FLUSH_SNAPS 4 648 649/* 650 * We set the ERROR_WRITE bit when we start seeing write errors on an inode 651 * and then clear it when they start succeeding. Note that we do a lockless 652 * check first, and only take the lock if it looks like it needs to be changed. 653 * The write submission code just takes this as a hint, so we're not too 654 * worried if a few slip through in either direction. 655 */ 656static inline void ceph_set_error_write(struct ceph_inode_info *ci) 657{ 658 if (!(READ_ONCE(ci->i_ceph_flags) & CEPH_I_ERROR_WRITE)) { 659 spin_lock(&ci->i_ceph_lock); 660 ci->i_ceph_flags |= CEPH_I_ERROR_WRITE; 661 spin_unlock(&ci->i_ceph_lock); 662 } 663} 664 665static inline void ceph_clear_error_write(struct ceph_inode_info *ci) 666{ 667 if (READ_ONCE(ci->i_ceph_flags) & CEPH_I_ERROR_WRITE) { 668 spin_lock(&ci->i_ceph_lock); 669 ci->i_ceph_flags &= ~CEPH_I_ERROR_WRITE; 670 spin_unlock(&ci->i_ceph_lock); 671 } 672} 673 674static inline void __ceph_dir_set_complete(struct ceph_inode_info *ci, 675 long long release_count, 676 long long ordered_count) 677{ 678 /* 679 * Makes sure operations that setup readdir cache (update page 680 * cache and i_size) are strongly ordered w.r.t. the following 681 * atomic64_set() operations. 682 */ 683 smp_mb(); 684 atomic64_set(&ci->i_complete_seq[0], release_count); 685 atomic64_set(&ci->i_complete_seq[1], ordered_count); 686} 687 688static inline void __ceph_dir_clear_complete(struct ceph_inode_info *ci) 689{ 690 atomic64_inc(&ci->i_release_count); 691} 692 693static inline void __ceph_dir_clear_ordered(struct ceph_inode_info *ci) 694{ 695 atomic64_inc(&ci->i_ordered_count); 696} 697 698static inline bool __ceph_dir_is_complete(struct ceph_inode_info *ci) 699{ 700 return atomic64_read(&ci->i_complete_seq[0]) == 701 atomic64_read(&ci->i_release_count); 702} 703 704static inline bool __ceph_dir_is_complete_ordered(struct ceph_inode_info *ci) 705{ 706 return atomic64_read(&ci->i_complete_seq[0]) == 707 atomic64_read(&ci->i_release_count) && 708 atomic64_read(&ci->i_complete_seq[1]) == 709 atomic64_read(&ci->i_ordered_count); 710} 711 712static inline void ceph_dir_clear_complete(struct inode *inode) 713{ 714 __ceph_dir_clear_complete(ceph_inode(inode)); 715} 716 717static inline void ceph_dir_clear_ordered(struct inode *inode) 718{ 719 __ceph_dir_clear_ordered(ceph_inode(inode)); 720} 721 722static inline bool ceph_dir_is_complete_ordered(struct inode *inode) 723{ 724 bool ret = __ceph_dir_is_complete_ordered(ceph_inode(inode)); 725 smp_rmb(); 726 return ret; 727} 728 729/* find a specific frag @f */ 730extern struct ceph_inode_frag *__ceph_find_frag(struct ceph_inode_info *ci, 731 u32 f); 732 733/* 734 * choose fragment for value @v. copy frag content to pfrag, if leaf 735 * exists 736 */ 737extern u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v, 738 struct ceph_inode_frag *pfrag, 739 int *found); 740 741static inline struct ceph_dentry_info *ceph_dentry(const struct dentry *dentry) 742{ 743 return (struct ceph_dentry_info *)dentry->d_fsdata; 744} 745 746/* 747 * caps helpers 748 */ 749static inline bool __ceph_is_any_real_caps(struct ceph_inode_info *ci) 750{ 751 return !RB_EMPTY_ROOT(&ci->i_caps); 752} 753 754extern int __ceph_caps_issued(struct ceph_inode_info *ci, int *implemented); 755extern int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int t); 756extern int __ceph_caps_issued_mask_metric(struct ceph_inode_info *ci, int mask, 757 int t); 758extern int __ceph_caps_issued_other(struct ceph_inode_info *ci, 759 struct ceph_cap *cap); 760 761static inline int ceph_caps_issued(struct ceph_inode_info *ci) 762{ 763 int issued; 764 spin_lock(&ci->i_ceph_lock); 765 issued = __ceph_caps_issued(ci, NULL); 766 spin_unlock(&ci->i_ceph_lock); 767 return issued; 768} 769 770static inline int ceph_caps_issued_mask_metric(struct ceph_inode_info *ci, 771 int mask, int touch) 772{ 773 int r; 774 spin_lock(&ci->i_ceph_lock); 775 r = __ceph_caps_issued_mask_metric(ci, mask, touch); 776 spin_unlock(&ci->i_ceph_lock); 777 return r; 778} 779 780static inline int __ceph_caps_dirty(struct ceph_inode_info *ci) 781{ 782 return ci->i_dirty_caps | ci->i_flushing_caps; 783} 784extern struct ceph_cap_flush *ceph_alloc_cap_flush(void); 785extern void ceph_free_cap_flush(struct ceph_cap_flush *cf); 786extern int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask, 787 struct ceph_cap_flush **pcf); 788 789extern int __ceph_caps_revoking_other(struct ceph_inode_info *ci, 790 struct ceph_cap *ocap, int mask); 791extern int ceph_caps_revoking(struct ceph_inode_info *ci, int mask); 792extern int __ceph_caps_used(struct ceph_inode_info *ci); 793 794static inline bool __ceph_is_file_opened(struct ceph_inode_info *ci) 795{ 796 return ci->i_nr_by_mode[0]; 797} 798extern int __ceph_caps_file_wanted(struct ceph_inode_info *ci); 799extern int __ceph_caps_wanted(struct ceph_inode_info *ci); 800 801/* what the mds thinks we want */ 802extern int __ceph_caps_mds_wanted(struct ceph_inode_info *ci, bool check); 803 804extern void ceph_caps_init(struct ceph_mds_client *mdsc); 805extern void ceph_caps_finalize(struct ceph_mds_client *mdsc); 806extern void ceph_adjust_caps_max_min(struct ceph_mds_client *mdsc, 807 struct ceph_mount_options *fsopt); 808extern int ceph_reserve_caps(struct ceph_mds_client *mdsc, 809 struct ceph_cap_reservation *ctx, int need); 810extern void ceph_unreserve_caps(struct ceph_mds_client *mdsc, 811 struct ceph_cap_reservation *ctx); 812extern void ceph_reservation_status(struct ceph_fs_client *client, 813 int *total, int *avail, int *used, 814 int *reserved, int *min); 815extern void change_auth_cap_ses(struct ceph_inode_info *ci, 816 struct ceph_mds_session *session); 817 818 819 820/* 821 * we keep buffered readdir results attached to file->private_data 822 */ 823#define CEPH_F_SYNC 1 824#define CEPH_F_ATEND 2 825 826struct ceph_file_info { 827 short fmode; /* initialized on open */ 828 short flags; /* CEPH_F_* */ 829 830 spinlock_t rw_contexts_lock; 831 struct list_head rw_contexts; 832 833 u32 filp_gen; 834}; 835 836struct ceph_dir_file_info { 837 struct ceph_file_info file_info; 838 839 /* readdir: position within the dir */ 840 u32 frag; 841 struct ceph_mds_request *last_readdir; 842 843 /* readdir: position within a frag */ 844 unsigned next_offset; /* offset of next chunk (last_name's + 1) */ 845 char *last_name; /* last entry in previous chunk */ 846 long long dir_release_count; 847 long long dir_ordered_count; 848 int readdir_cache_idx; 849 850 /* used for -o dirstat read() on directory thing */ 851 char *dir_info; 852 int dir_info_len; 853}; 854 855struct ceph_rw_context { 856 struct list_head list; 857 struct task_struct *thread; 858 int caps; 859}; 860 861#define CEPH_DEFINE_RW_CONTEXT(_name, _caps) \ 862 struct ceph_rw_context _name = { \ 863 .thread = current, \ 864 .caps = _caps, \ 865 } 866 867static inline void ceph_add_rw_context(struct ceph_file_info *cf, 868 struct ceph_rw_context *ctx) 869{ 870 spin_lock(&cf->rw_contexts_lock); 871 list_add(&ctx->list, &cf->rw_contexts); 872 spin_unlock(&cf->rw_contexts_lock); 873} 874 875static inline void ceph_del_rw_context(struct ceph_file_info *cf, 876 struct ceph_rw_context *ctx) 877{ 878 spin_lock(&cf->rw_contexts_lock); 879 list_del(&ctx->list); 880 spin_unlock(&cf->rw_contexts_lock); 881} 882 883static inline struct ceph_rw_context* 884ceph_find_rw_context(struct ceph_file_info *cf) 885{ 886 struct ceph_rw_context *ctx, *found = NULL; 887 spin_lock(&cf->rw_contexts_lock); 888 list_for_each_entry(ctx, &cf->rw_contexts, list) { 889 if (ctx->thread == current) { 890 found = ctx; 891 break; 892 } 893 } 894 spin_unlock(&cf->rw_contexts_lock); 895 return found; 896} 897 898struct ceph_readdir_cache_control { 899 struct page *page; 900 struct dentry **dentries; 901 int index; 902}; 903 904/* 905 * A "snap realm" describes a subset of the file hierarchy sharing 906 * the same set of snapshots that apply to it. The realms themselves 907 * are organized into a hierarchy, such that children inherit (some of) 908 * the snapshots of their parents. 909 * 910 * All inodes within the realm that have capabilities are linked into a 911 * per-realm list. 912 */ 913struct ceph_snap_realm { 914 u64 ino; 915 struct inode *inode; 916 atomic_t nref; 917 struct rb_node node; 918 919 u64 created, seq; 920 u64 parent_ino; 921 u64 parent_since; /* snapid when our current parent became so */ 922 923 u64 *prior_parent_snaps; /* snaps inherited from any parents we */ 924 u32 num_prior_parent_snaps; /* had prior to parent_since */ 925 u64 *snaps; /* snaps specific to this realm */ 926 u32 num_snaps; 927 928 struct ceph_snap_realm *parent; 929 struct list_head children; /* list of child realms */ 930 struct list_head child_item; 931 932 struct list_head empty_item; /* if i have ref==0 */ 933 934 struct list_head dirty_item; /* if realm needs new context */ 935 936 struct list_head rebuild_item; /* rebuild snap realms _downward_ in hierarchy */ 937 938 /* the current set of snaps for this realm */ 939 struct ceph_snap_context *cached_context; 940 941 struct list_head inodes_with_caps; 942 spinlock_t inodes_with_caps_lock; 943}; 944 945static inline int default_congestion_kb(void) 946{ 947 int congestion_kb; 948 949 /* 950 * Copied from NFS 951 * 952 * congestion size, scale with available memory. 953 * 954 * 64MB: 8192k 955 * 128MB: 11585k 956 * 256MB: 16384k 957 * 512MB: 23170k 958 * 1GB: 32768k 959 * 2GB: 46340k 960 * 4GB: 65536k 961 * 8GB: 92681k 962 * 16GB: 131072k 963 * 964 * This allows larger machines to have larger/more transfers. 965 * Limit the default to 256M 966 */ 967 congestion_kb = (16*int_sqrt(totalram_pages())) << (PAGE_SHIFT-10); 968 if (congestion_kb > 256*1024) 969 congestion_kb = 256*1024; 970 971 return congestion_kb; 972} 973 974 975/* super.c */ 976extern int ceph_force_reconnect(struct super_block *sb); 977/* snap.c */ 978struct ceph_snap_realm *ceph_lookup_snap_realm(struct ceph_mds_client *mdsc, 979 u64 ino); 980extern void ceph_get_snap_realm(struct ceph_mds_client *mdsc, 981 struct ceph_snap_realm *realm); 982extern void ceph_put_snap_realm(struct ceph_mds_client *mdsc, 983 struct ceph_snap_realm *realm); 984extern int ceph_update_snap_trace(struct ceph_mds_client *m, 985 void *p, void *e, bool deletion, 986 struct ceph_snap_realm **realm_ret); 987void ceph_change_snap_realm(struct inode *inode, struct ceph_snap_realm *realm); 988extern void ceph_handle_snap(struct ceph_mds_client *mdsc, 989 struct ceph_mds_session *session, 990 struct ceph_msg *msg); 991extern int __ceph_finish_cap_snap(struct ceph_inode_info *ci, 992 struct ceph_cap_snap *capsnap); 993extern void ceph_cleanup_global_and_empty_realms(struct ceph_mds_client *mdsc); 994 995extern struct ceph_snapid_map *ceph_get_snapid_map(struct ceph_mds_client *mdsc, 996 u64 snap); 997extern void ceph_put_snapid_map(struct ceph_mds_client* mdsc, 998 struct ceph_snapid_map *sm); 999extern void ceph_trim_snapid_map(struct ceph_mds_client *mdsc); 1000extern void ceph_cleanup_snapid_map(struct ceph_mds_client *mdsc); 1001void ceph_umount_begin(struct super_block *sb); 1002 1003 1004/* 1005 * a cap_snap is "pending" if it is still awaiting an in-progress 1006 * sync write (that may/may not still update size, mtime, etc.). 1007 */ 1008static inline bool __ceph_have_pending_cap_snap(struct ceph_inode_info *ci) 1009{ 1010 return !list_empty(&ci->i_cap_snaps) && 1011 list_last_entry(&ci->i_cap_snaps, struct ceph_cap_snap, 1012 ci_item)->writing; 1013} 1014 1015/* inode.c */ 1016struct ceph_mds_reply_info_in; 1017struct ceph_mds_reply_dirfrag; 1018struct ceph_acl_sec_ctx; 1019 1020extern const struct inode_operations ceph_file_iops; 1021 1022extern struct inode *ceph_alloc_inode(struct super_block *sb); 1023extern void ceph_evict_inode(struct inode *inode); 1024extern void ceph_free_inode(struct inode *inode); 1025 1026struct inode *ceph_new_inode(struct inode *dir, struct dentry *dentry, 1027 umode_t *mode, struct ceph_acl_sec_ctx *as_ctx); 1028void ceph_as_ctx_to_req(struct ceph_mds_request *req, 1029 struct ceph_acl_sec_ctx *as_ctx); 1030 1031extern struct inode *ceph_get_inode(struct super_block *sb, 1032 struct ceph_vino vino, 1033 struct inode *newino); 1034extern struct inode *ceph_get_snapdir(struct inode *parent); 1035extern int ceph_fill_file_size(struct inode *inode, int issued, 1036 u32 truncate_seq, u64 truncate_size, u64 size); 1037extern void ceph_fill_file_time(struct inode *inode, int issued, 1038 u64 time_warp_seq, struct timespec64 *ctime, 1039 struct timespec64 *mtime, 1040 struct timespec64 *atime); 1041extern int ceph_fill_inode(struct inode *inode, struct page *locked_page, 1042 struct ceph_mds_reply_info_in *iinfo, 1043 struct ceph_mds_reply_dirfrag *dirinfo, 1044 struct ceph_mds_session *session, int cap_fmode, 1045 struct ceph_cap_reservation *caps_reservation); 1046extern int ceph_fill_trace(struct super_block *sb, 1047 struct ceph_mds_request *req); 1048extern int ceph_readdir_prepopulate(struct ceph_mds_request *req, 1049 struct ceph_mds_session *session); 1050 1051extern int ceph_inode_holds_cap(struct inode *inode, int mask); 1052 1053extern bool ceph_inode_set_size(struct inode *inode, loff_t size); 1054extern void __ceph_do_pending_vmtruncate(struct inode *inode); 1055 1056void ceph_queue_inode_work(struct inode *inode, int work_bit); 1057 1058static inline void ceph_queue_vmtruncate(struct inode *inode) 1059{ 1060 ceph_queue_inode_work(inode, CEPH_I_WORK_VMTRUNCATE); 1061} 1062 1063static inline void ceph_queue_invalidate(struct inode *inode) 1064{ 1065 ceph_queue_inode_work(inode, CEPH_I_WORK_INVALIDATE_PAGES); 1066} 1067 1068static inline void ceph_queue_writeback(struct inode *inode) 1069{ 1070 ceph_queue_inode_work(inode, CEPH_I_WORK_WRITEBACK); 1071} 1072 1073static inline void ceph_queue_check_caps(struct inode *inode) 1074{ 1075 ceph_queue_inode_work(inode, CEPH_I_WORK_CHECK_CAPS); 1076} 1077 1078static inline void ceph_queue_flush_snaps(struct inode *inode) 1079{ 1080 ceph_queue_inode_work(inode, CEPH_I_WORK_FLUSH_SNAPS); 1081} 1082 1083extern int ceph_try_to_choose_auth_mds(struct inode *inode, int mask); 1084extern int __ceph_do_getattr(struct inode *inode, struct page *locked_page, 1085 int mask, bool force); 1086static inline int ceph_do_getattr(struct inode *inode, int mask, bool force) 1087{ 1088 return __ceph_do_getattr(inode, NULL, mask, force); 1089} 1090extern int ceph_permission(struct mnt_idmap *idmap, 1091 struct inode *inode, int mask); 1092 1093struct ceph_iattr { 1094 struct ceph_fscrypt_auth *fscrypt_auth; 1095}; 1096 1097extern int __ceph_setattr(struct inode *inode, struct iattr *attr, 1098 struct ceph_iattr *cia); 1099extern int ceph_setattr(struct mnt_idmap *idmap, 1100 struct dentry *dentry, struct iattr *attr); 1101extern int ceph_getattr(struct mnt_idmap *idmap, 1102 const struct path *path, struct kstat *stat, 1103 u32 request_mask, unsigned int flags); 1104void ceph_inode_shutdown(struct inode *inode); 1105 1106static inline bool ceph_inode_is_shutdown(struct inode *inode) 1107{ 1108 unsigned long flags = READ_ONCE(ceph_inode(inode)->i_ceph_flags); 1109 struct ceph_fs_client *fsc = ceph_inode_to_client(inode); 1110 int state = READ_ONCE(fsc->mount_state); 1111 1112 return (flags & CEPH_I_SHUTDOWN) || state >= CEPH_MOUNT_SHUTDOWN; 1113} 1114 1115/* xattr.c */ 1116int __ceph_setxattr(struct inode *, const char *, const void *, size_t, int); 1117int ceph_do_getvxattr(struct inode *inode, const char *name, void *value, size_t size); 1118ssize_t __ceph_getxattr(struct inode *, const char *, void *, size_t); 1119extern ssize_t ceph_listxattr(struct dentry *, char *, size_t); 1120extern struct ceph_buffer *__ceph_build_xattrs_blob(struct ceph_inode_info *ci); 1121extern void __ceph_destroy_xattrs(struct ceph_inode_info *ci); 1122extern const struct xattr_handler *ceph_xattr_handlers[]; 1123 1124struct ceph_acl_sec_ctx { 1125#ifdef CONFIG_CEPH_FS_POSIX_ACL 1126 void *default_acl; 1127 void *acl; 1128#endif 1129#ifdef CONFIG_CEPH_FS_SECURITY_LABEL 1130 void *sec_ctx; 1131 u32 sec_ctxlen; 1132#endif 1133#ifdef CONFIG_FS_ENCRYPTION 1134 struct ceph_fscrypt_auth *fscrypt_auth; 1135#endif 1136 struct ceph_pagelist *pagelist; 1137}; 1138 1139#ifdef CONFIG_SECURITY 1140extern bool ceph_security_xattr_deadlock(struct inode *in); 1141extern bool ceph_security_xattr_wanted(struct inode *in); 1142#else 1143static inline bool ceph_security_xattr_deadlock(struct inode *in) 1144{ 1145 return false; 1146} 1147static inline bool ceph_security_xattr_wanted(struct inode *in) 1148{ 1149 return false; 1150} 1151#endif 1152 1153#ifdef CONFIG_CEPH_FS_SECURITY_LABEL 1154extern int ceph_security_init_secctx(struct dentry *dentry, umode_t mode, 1155 struct ceph_acl_sec_ctx *ctx); 1156static inline void ceph_security_invalidate_secctx(struct inode *inode) 1157{ 1158 security_inode_invalidate_secctx(inode); 1159} 1160#else 1161static inline int ceph_security_init_secctx(struct dentry *dentry, umode_t mode, 1162 struct ceph_acl_sec_ctx *ctx) 1163{ 1164 return 0; 1165} 1166static inline void ceph_security_invalidate_secctx(struct inode *inode) 1167{ 1168} 1169#endif 1170 1171void ceph_release_acl_sec_ctx(struct ceph_acl_sec_ctx *as_ctx); 1172 1173/* acl.c */ 1174#ifdef CONFIG_CEPH_FS_POSIX_ACL 1175 1176struct posix_acl *ceph_get_acl(struct inode *, int, bool); 1177int ceph_set_acl(struct mnt_idmap *idmap, 1178 struct dentry *dentry, struct posix_acl *acl, int type); 1179int ceph_pre_init_acls(struct inode *dir, umode_t *mode, 1180 struct ceph_acl_sec_ctx *as_ctx); 1181void ceph_init_inode_acls(struct inode *inode, 1182 struct ceph_acl_sec_ctx *as_ctx); 1183 1184static inline void ceph_forget_all_cached_acls(struct inode *inode) 1185{ 1186 forget_all_cached_acls(inode); 1187} 1188 1189#else 1190 1191#define ceph_get_acl NULL 1192#define ceph_set_acl NULL 1193 1194static inline int ceph_pre_init_acls(struct inode *dir, umode_t *mode, 1195 struct ceph_acl_sec_ctx *as_ctx) 1196{ 1197 return 0; 1198} 1199static inline void ceph_init_inode_acls(struct inode *inode, 1200 struct ceph_acl_sec_ctx *as_ctx) 1201{ 1202} 1203static inline int ceph_acl_chmod(struct dentry *dentry, struct inode *inode) 1204{ 1205 return 0; 1206} 1207 1208static inline void ceph_forget_all_cached_acls(struct inode *inode) 1209{ 1210} 1211 1212#endif 1213 1214/* caps.c */ 1215extern const char *ceph_cap_string(int c); 1216extern void ceph_handle_caps(struct ceph_mds_session *session, 1217 struct ceph_msg *msg); 1218extern struct ceph_cap *ceph_get_cap(struct ceph_mds_client *mdsc, 1219 struct ceph_cap_reservation *ctx); 1220extern void ceph_add_cap(struct inode *inode, 1221 struct ceph_mds_session *session, u64 cap_id, 1222 unsigned issued, unsigned wanted, 1223 unsigned cap, unsigned seq, u64 realmino, int flags, 1224 struct ceph_cap **new_cap); 1225extern void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release); 1226extern void ceph_remove_cap(struct ceph_cap *cap, bool queue_release); 1227extern void __ceph_remove_caps(struct ceph_inode_info *ci); 1228extern void ceph_put_cap(struct ceph_mds_client *mdsc, 1229 struct ceph_cap *cap); 1230extern int ceph_is_any_caps(struct inode *inode); 1231 1232extern int ceph_write_inode(struct inode *inode, struct writeback_control *wbc); 1233extern int ceph_fsync(struct file *file, loff_t start, loff_t end, 1234 int datasync); 1235extern void ceph_early_kick_flushing_caps(struct ceph_mds_client *mdsc, 1236 struct ceph_mds_session *session); 1237extern void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc, 1238 struct ceph_mds_session *session); 1239void ceph_kick_flushing_inode_caps(struct ceph_mds_session *session, 1240 struct ceph_inode_info *ci); 1241extern struct ceph_cap *__get_cap_for_mds(struct ceph_inode_info *ci, 1242 int mds); 1243extern struct ceph_cap *ceph_get_cap_for_mds(struct ceph_inode_info *ci, 1244 int mds); 1245extern void ceph_take_cap_refs(struct ceph_inode_info *ci, int caps, 1246 bool snap_rwsem_locked); 1247extern void ceph_get_cap_refs(struct ceph_inode_info *ci, int caps); 1248extern void ceph_put_cap_refs(struct ceph_inode_info *ci, int had); 1249extern void ceph_put_cap_refs_async(struct ceph_inode_info *ci, int had); 1250extern void ceph_put_cap_refs_no_check_caps(struct ceph_inode_info *ci, 1251 int had); 1252extern void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr, 1253 struct ceph_snap_context *snapc); 1254extern void __ceph_remove_capsnap(struct inode *inode, 1255 struct ceph_cap_snap *capsnap, 1256 bool *wake_ci, bool *wake_mdsc); 1257extern void ceph_remove_capsnap(struct inode *inode, 1258 struct ceph_cap_snap *capsnap, 1259 bool *wake_ci, bool *wake_mdsc); 1260extern void ceph_flush_snaps(struct ceph_inode_info *ci, 1261 struct ceph_mds_session **psession); 1262extern bool __ceph_should_report_size(struct ceph_inode_info *ci); 1263extern void ceph_check_caps(struct ceph_inode_info *ci, int flags); 1264extern unsigned long ceph_check_delayed_caps(struct ceph_mds_client *mdsc); 1265extern void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc); 1266extern int ceph_drop_caps_for_unlink(struct inode *inode); 1267extern int ceph_encode_inode_release(void **p, struct inode *inode, 1268 int mds, int drop, int unless, int force); 1269extern int ceph_encode_dentry_release(void **p, struct dentry *dn, 1270 struct inode *dir, 1271 int mds, int drop, int unless); 1272 1273extern int __ceph_get_caps(struct inode *inode, struct ceph_file_info *fi, 1274 int need, int want, loff_t endoff, int *got); 1275extern int ceph_get_caps(struct file *filp, int need, int want, 1276 loff_t endoff, int *got); 1277extern int ceph_try_get_caps(struct inode *inode, 1278 int need, int want, bool nonblock, int *got); 1279 1280/* for counting open files by mode */ 1281extern void ceph_get_fmode(struct ceph_inode_info *ci, int mode, int count); 1282extern void ceph_put_fmode(struct ceph_inode_info *ci, int mode, int count); 1283extern void __ceph_touch_fmode(struct ceph_inode_info *ci, 1284 struct ceph_mds_client *mdsc, int fmode); 1285 1286/* addr.c */ 1287extern const struct address_space_operations ceph_aops; 1288extern const struct netfs_request_ops ceph_netfs_ops; 1289extern int ceph_mmap(struct file *file, struct vm_area_struct *vma); 1290extern int ceph_uninline_data(struct file *file); 1291extern int ceph_pool_perm_check(struct inode *inode, int need); 1292extern void ceph_pool_perm_destroy(struct ceph_mds_client* mdsc); 1293int ceph_purge_inode_cap(struct inode *inode, struct ceph_cap *cap, bool *invalidate); 1294 1295static inline bool ceph_has_inline_data(struct ceph_inode_info *ci) 1296{ 1297 if (ci->i_inline_version == CEPH_INLINE_NONE || 1298 ci->i_inline_version == 1) /* initial version, no data */ 1299 return false; 1300 return true; 1301} 1302 1303/* file.c */ 1304extern const struct file_operations ceph_file_fops; 1305 1306extern int ceph_renew_caps(struct inode *inode, int fmode); 1307extern int ceph_open(struct inode *inode, struct file *file); 1308extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry, 1309 struct file *file, unsigned flags, umode_t mode); 1310extern ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, 1311 struct iov_iter *to, int *retry_op, 1312 u64 *last_objver); 1313extern int ceph_release(struct inode *inode, struct file *filp); 1314extern void ceph_fill_inline_data(struct inode *inode, struct page *locked_page, 1315 char *data, size_t len); 1316 1317/* dir.c */ 1318extern const struct file_operations ceph_dir_fops; 1319extern const struct file_operations ceph_snapdir_fops; 1320extern const struct inode_operations ceph_dir_iops; 1321extern const struct inode_operations ceph_snapdir_iops; 1322extern const struct dentry_operations ceph_dentry_ops; 1323 1324extern loff_t ceph_make_fpos(unsigned high, unsigned off, bool hash_order); 1325extern int ceph_handle_notrace_create(struct inode *dir, struct dentry *dentry); 1326extern struct dentry *ceph_handle_snapdir(struct ceph_mds_request *req, 1327 struct dentry *dentry); 1328extern struct dentry *ceph_finish_lookup(struct ceph_mds_request *req, 1329 struct dentry *dentry, int err); 1330 1331extern void __ceph_dentry_lease_touch(struct ceph_dentry_info *di); 1332extern void __ceph_dentry_dir_lease_touch(struct ceph_dentry_info *di); 1333extern void ceph_invalidate_dentry_lease(struct dentry *dentry); 1334extern int ceph_trim_dentries(struct ceph_mds_client *mdsc); 1335extern unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn); 1336extern void ceph_readdir_cache_release(struct ceph_readdir_cache_control *ctl); 1337 1338/* ioctl.c */ 1339extern long ceph_ioctl(struct file *file, unsigned int cmd, unsigned long arg); 1340 1341/* export.c */ 1342extern const struct export_operations ceph_export_ops; 1343struct inode *ceph_lookup_inode(struct super_block *sb, u64 ino); 1344 1345/* locks.c */ 1346extern __init void ceph_flock_init(void); 1347extern int ceph_lock(struct file *file, int cmd, struct file_lock *fl); 1348extern int ceph_flock(struct file *file, int cmd, struct file_lock *fl); 1349extern void ceph_count_locks(struct inode *inode, int *p_num, int *f_num); 1350extern int ceph_encode_locks_to_buffer(struct inode *inode, 1351 struct ceph_filelock *flocks, 1352 int num_fcntl_locks, 1353 int num_flock_locks); 1354extern int ceph_locks_to_pagelist(struct ceph_filelock *flocks, 1355 struct ceph_pagelist *pagelist, 1356 int num_fcntl_locks, int num_flock_locks); 1357 1358/* debugfs.c */ 1359extern void ceph_fs_debugfs_init(struct ceph_fs_client *client); 1360extern void ceph_fs_debugfs_cleanup(struct ceph_fs_client *client); 1361 1362/* quota.c */ 1363 1364enum quota_get_realm { 1365 QUOTA_GET_MAX_FILES, 1366 QUOTA_GET_MAX_BYTES, 1367 QUOTA_GET_ANY 1368}; 1369 1370static inline bool __ceph_has_quota(struct ceph_inode_info *ci, 1371 enum quota_get_realm which) 1372{ 1373 bool has_quota = false; 1374 1375 switch (which) { 1376 case QUOTA_GET_MAX_BYTES: 1377 has_quota = !!ci->i_max_bytes; 1378 break; 1379 case QUOTA_GET_MAX_FILES: 1380 has_quota = !!ci->i_max_files; 1381 break; 1382 default: 1383 has_quota = !!(ci->i_max_files || ci->i_max_bytes); 1384 } 1385 return has_quota; 1386} 1387 1388extern void ceph_adjust_quota_realms_count(struct inode *inode, bool inc); 1389 1390static inline void __ceph_update_quota(struct ceph_inode_info *ci, 1391 u64 max_bytes, u64 max_files) 1392{ 1393 bool had_quota, has_quota; 1394 had_quota = __ceph_has_quota(ci, QUOTA_GET_ANY); 1395 ci->i_max_bytes = max_bytes; 1396 ci->i_max_files = max_files; 1397 has_quota = __ceph_has_quota(ci, QUOTA_GET_ANY); 1398 1399 if (had_quota != has_quota) 1400 ceph_adjust_quota_realms_count(&ci->netfs.inode, has_quota); 1401} 1402 1403extern void ceph_handle_quota(struct ceph_mds_client *mdsc, 1404 struct ceph_mds_session *session, 1405 struct ceph_msg *msg); 1406extern bool ceph_quota_is_max_files_exceeded(struct inode *inode); 1407extern bool ceph_quota_is_same_realm(struct inode *old, struct inode *new); 1408extern bool ceph_quota_is_max_bytes_exceeded(struct inode *inode, 1409 loff_t newlen); 1410extern bool ceph_quota_is_max_bytes_approaching(struct inode *inode, 1411 loff_t newlen); 1412extern bool ceph_quota_update_statfs(struct ceph_fs_client *fsc, 1413 struct kstatfs *buf); 1414extern void ceph_cleanup_quotarealms_inodes(struct ceph_mds_client *mdsc); 1415 1416bool ceph_inc_mds_stopping_blocker(struct ceph_mds_client *mdsc, 1417 struct ceph_mds_session *session); 1418void ceph_dec_mds_stopping_blocker(struct ceph_mds_client *mdsc); 1419bool ceph_inc_osd_stopping_blocker(struct ceph_mds_client *mdsc); 1420void ceph_dec_osd_stopping_blocker(struct ceph_mds_client *mdsc); 1421#endif /* _FS_CEPH_SUPER_H */ 1422