super.h 25.6 KB
Newer Older
S
Sage Weil 已提交
1 2 3
#ifndef _FS_CEPH_SUPER_H
#define _FS_CEPH_SUPER_H

4
#include <linux/ceph/ceph_debug.h>
S
Sage Weil 已提交
5 6 7 8 9 10 11 12 13

#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>
14
#include <linux/writeback.h>
15
#include <linux/slab.h>
S
Sage Weil 已提交
16

17
#include <linux/ceph/libceph.h>
S
Sage Weil 已提交
18 19 20 21 22 23

/* 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. */
S
Sage Weil 已提交
24
#define CEPH_BLOCK_SHIFT   22  /* 4 MB */
S
Sage Weil 已提交
25 26
#define CEPH_BLOCK         (1 << CEPH_BLOCK_SHIFT)

27 28 29
#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 */
Y
Yehuda Sadeh 已提交
30
#define CEPH_MOUNT_OPT_INO32           (1<<8) /* 32 bit inos */
31
#define CEPH_MOUNT_OPT_DCACHE          (1<<9) /* use dcache for readdir etc */
32

33
#define CEPH_MOUNT_OPT_DEFAULT    (CEPH_MOUNT_OPT_RBYTES)
S
Sage Weil 已提交
34

35 36 37 38
#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))
S
Sage Weil 已提交
39

S
Sage Weil 已提交
40 41
#define CEPH_RSIZE_DEFAULT             0           /* max read size */
#define CEPH_RASIZE_DEFAULT            (8192*1024) /* readahead */
42 43 44
#define CEPH_MAX_READDIR_DEFAULT        1024
#define CEPH_MAX_READDIR_BYTES_DEFAULT  (512*1024)
#define CEPH_SNAPDIRNAME_DEFAULT        ".snap"
S
Sage Weil 已提交
45

46
struct ceph_mount_options {
47
	int flags;
48 49
	int sb_flags;

S
Sage Weil 已提交
50 51 52
	int wsize;            /* max write size */
	int rsize;            /* max read size */
	int rasize;           /* max readahead */
53 54 55
	int congestion_kb;    /* max writeback in flight */
	int caps_wanted_delay_min, caps_wanted_delay_max;
	int cap_release_safety;
56 57
	int max_readdir;       /* max readdir result (entires) */
	int max_readdir_bytes; /* max readdir result (bytes) */
S
Sage Weil 已提交
58

59 60 61 62
	/*
	 * everything above this point can be memcmp'd; everything below
	 * is handled in compare_mount_options()
	 */
S
Sage Weil 已提交
63

64 65
	char *snapdir_name;   /* default ".snap" */
};
S
Sage Weil 已提交
66

67
struct ceph_fs_client {
S
Sage Weil 已提交
68 69
	struct super_block *sb;

70 71
	struct ceph_mount_options *mount_options;
	struct ceph_client *client;
S
Sage Weil 已提交
72

73
	unsigned long mount_state;
74 75
	int min_caps;                  /* min caps i added */

76
	struct ceph_mds_client *mdsc;
S
Sage Weil 已提交
77 78 79 80 81 82

	/* writeback */
	mempool_t *wb_pagevec_pool;
	struct workqueue_struct *wb_wq;
	struct workqueue_struct *pg_inv_wq;
	struct workqueue_struct *trunc_wq;
Y
Yehuda Sadeh 已提交
83
	atomic_long_t writeback_count;
S
Sage Weil 已提交
84 85

	struct backing_dev_info backing_dev_info;
86 87

#ifdef CONFIG_DEBUG_FS
88
	struct dentry *debugfs_dentry_lru, *debugfs_caps;
Y
Yehuda Sadeh 已提交
89
	struct dentry *debugfs_congestion_kb;
S
Sage Weil 已提交
90
	struct dentry *debugfs_bdi;
91
	struct dentry *debugfs_mdsc, *debugfs_mdsmap;
92
#endif
S
Sage Weil 已提交
93 94
};

95

S
Sage Weil 已提交
96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115
/*
 * 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;
116 117
	u32 seq, issue_seq, mseq;
	u32 cap_gen;      /* active/stale cycle */
S
Sage Weil 已提交
118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139
	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;

A
Al Viro 已提交
140
	umode_t mode;
141 142
	kuid_t uid;
	kgid_t gid;
S
Sage Weil 已提交
143

144
	struct ceph_buffer *xattr_blob;
S
Sage Weil 已提交
145 146 147 148 149 150 151 152 153 154 155
	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)
{
156 157 158
	if (atomic_dec_and_test(&capsnap->nref)) {
		if (capsnap->xattr_blob)
			ceph_buffer_put(capsnap->xattr_blob);
S
Sage Weil 已提交
159
		kfree(capsnap);
160
	}
S
Sage Weil 已提交
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
}

/*
 * 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;
};

203 204 205 206 207 208 209 210 211 212 213 214 215 216
/*
 * Ceph dentry state
 */
struct ceph_dentry_info {
	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;
};

S
Sage Weil 已提交
217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240
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 ceph_vino i_vino;   /* ceph ino + snap */

241 242
	spinlock_t i_ceph_lock;

S
Sage Weil 已提交
243 244 245 246
	u64 i_version;
	u32 i_time_warp_seq;

	unsigned i_ceph_flags;
247 248
	atomic_t i_release_count;
	atomic_t i_complete_count;
S
Sage Weil 已提交
249

S
Sage Weil 已提交
250
	struct ceph_dir_layout i_dir_layout;
S
Sage Weil 已提交
251 252 253 254 255 256 257
	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;
258
	u64 i_max_offset;  /* largest readdir offset, set with complete dir */
S
Sage Weil 已提交
259 260 261 262 263 264

	struct rb_root i_fragtree;
	struct mutex i_fragtree_mutex;

	struct ceph_inode_xattrs_info i_xattrs;

265
	/* capabilities.  protected _both_ by i_ceph_lock and cap->session's
S
Sage Weil 已提交
266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284
	 * 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 */
285 286
	struct ceph_snap_context *i_head_snapc;  /* set if wr_buffer_head > 0 or
						    dirty|flushing caps */
S
Sage Weil 已提交
287 288 289 290 291 292 293 294 295 296 297 298 299 300 301
	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;
302
	int i_rd_ref, i_rdcache_ref, i_wr_ref, i_wb_ref;
S
Sage Weil 已提交
303 304
	int i_wrbuffer_ref, i_wrbuffer_ref_head;
	u32 i_shared_gen;       /* increment each time we get FILE_SHARED */
305
	u32 i_rdcache_gen;      /* incremented each time we get FILE_CACHE. */
S
Sage Weil 已提交
306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326
	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)
{
327
	return container_of(inode, struct ceph_inode_info, vfs_inode);
S
Sage Weil 已提交
328 329
}

Y
Yehuda Sadeh 已提交
330 331 332 333 334 335 336 337 338 339
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;
}

340 341 342 343 344 345 346 347
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.
 *
Y
Yehuda Sadeh 已提交
348 349 350 351 352
 *               i_ino (kernel inode)   st_ino (userspace)
 * i386          32                     32
 * x86_64+ino32  64                     32
 * x86_64        64                     64
 */
A
Amon Ott 已提交
353
static inline u32 ceph_ino_to_ino32(__u64 vino)
Y
Yehuda Sadeh 已提交
354
{
A
Amon Ott 已提交
355 356
	u32 ino = vino & 0xffffffff;
	ino ^= vino >> 32;
Y
Yehuda Sadeh 已提交
357
	if (!ino)
358
		ino = 2;
Y
Yehuda Sadeh 已提交
359 360 361 362 363
	return ino;
}

/*
 * kernel i_ino value
364 365 366 367
 */
static inline ino_t ceph_vino_to_ino(struct ceph_vino vino)
{
#if BITS_PER_LONG == 32
A
Amon Ott 已提交
368 369 370
	return ceph_ino_to_ino32(vino.ino);
#else
	return (ino_t)vino.ino;
371 372 373
#endif
}

Y
Yehuda Sadeh 已提交
374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391
/*
 * 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


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
/* 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.
 */
#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 */

427 428
static inline void __ceph_dir_set_complete(struct ceph_inode_info *ci,
					   int release_count)
S
Sage Weil 已提交
429
{
430
	atomic_set(&ci->i_complete_count, release_count);
S
Sage Weil 已提交
431 432
}

433
static inline void __ceph_dir_clear_complete(struct ceph_inode_info *ci)
S
Sage Weil 已提交
434
{
435 436
	atomic_inc(&ci->i_release_count);
}
S
Sage Weil 已提交
437

438 439 440 441
static inline bool __ceph_dir_is_complete(struct ceph_inode_info *ci)
{
	return atomic_read(&ci->i_complete_count) ==
		atomic_read(&ci->i_release_count);
S
Sage Weil 已提交
442 443
}

444
static inline void ceph_dir_clear_complete(struct inode *inode)
S
Sage Weil 已提交
445
{
446 447
	__ceph_dir_clear_complete(ceph_inode(inode));
}
S
Sage Weil 已提交
448

449 450 451
static inline bool ceph_dir_is_complete(struct inode *inode)
{
	return __ceph_dir_is_complete(ceph_inode(inode));
S
Sage Weil 已提交
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
}


/* 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(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;
}

/*
 * 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;
493
	spin_lock(&ci->i_ceph_lock);
S
Sage Weil 已提交
494
	issued = __ceph_caps_issued(ci, NULL);
495
	spin_unlock(&ci->i_ceph_lock);
S
Sage Weil 已提交
496 497 498 499 500 501 502
	return issued;
}

static inline int ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask,
					int touch)
{
	int r;
503
	spin_lock(&ci->i_ceph_lock);
S
Sage Weil 已提交
504
	r = __ceph_caps_issued_mask(ci, mask, touch);
505
	spin_unlock(&ci->i_ceph_lock);
S
Sage Weil 已提交
506 507 508 509 510 511 512
	return r;
}

static inline int __ceph_caps_dirty(struct ceph_inode_info *ci)
{
	return ci->i_dirty_caps | ci->i_flushing_caps;
}
513
extern int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask);
S
Sage Weil 已提交
514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533

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);

534 535 536 537 538 539 540
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);
541
extern void ceph_reservation_status(struct ceph_fs_client *client,
S
Sage Weil 已提交
542
				    int *total, int *avail, int *used,
543
				    int *reserved, int *min);
S
Sage Weil 已提交
544 545 546 547 548 549



/*
 * we keep buffered readdir results attached to file->private_data
 */
550
#define CEPH_F_SYNC     1
551
#define CEPH_F_ATEND    2
552

S
Sage Weil 已提交
553
struct ceph_file_info {
S
Sage Weil 已提交
554 555
	short fmode;     /* initialized on open */
	short flags;     /* CEPH_F_* */
S
Sage Weil 已提交
556 557 558 559 560 561 562 563 564 565

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

	/* 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) */
566
	int dir_release_count;
S
Sage Weil 已提交
567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586

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



/*
 * 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;
S
Sage Weil 已提交
587 588
	struct rb_node node;

S
Sage Weil 已提交
589 590 591 592 593
	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 */
594
	u32 num_prior_parent_snaps;   /*  had prior to parent_since */
S
Sage Weil 已提交
595
	u64 *snaps;                   /* snaps specific to this realm */
596
	u32 num_snaps;
S
Sage Weil 已提交
597 598 599 600 601 602 603

	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 */

S
Sage Weil 已提交
604 605
	struct list_head dirty_item;     /* if realm needs new context */

S
Sage Weil 已提交
606 607 608 609 610 611 612
	/* 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;
};

613
static inline int default_congestion_kb(void)
S
Sage Weil 已提交
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
	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;
S
Sage Weil 已提交
640 641 642 643 644 645 646 647 648 649 650 651 652 653
}



/* 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,
654
			     struct ceph_mds_session *session,
S
Sage Weil 已提交
655
			     struct ceph_msg *msg);
656
extern void ceph_queue_cap_snap(struct ceph_inode_info *ci);
S
Sage Weil 已提交
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
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;
}

/* 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);
695
extern void __ceph_do_pending_vmtruncate(struct inode *inode, bool needlock);
696 697 698 699
extern void ceph_queue_vmtruncate(struct inode *inode);

extern void ceph_queue_invalidate(struct inode *inode);
extern void ceph_queue_writeback(struct inode *inode);
S
Sage Weil 已提交
700 701

extern int ceph_do_getattr(struct inode *inode, int mask);
702
extern int ceph_permission(struct inode *inode, int mask);
S
Sage Weil 已提交
703 704 705 706 707 708 709 710 711 712 713 714
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);
715 716
extern void __init ceph_xattr_init(void);
extern void ceph_xattr_exit(void);
S
Sage Weil 已提交
717 718 719 720 721 722 723 724 725 726

/* 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);
S
Sage Weil 已提交
727
extern void __ceph_remove_cap(struct ceph_cap *cap);
S
Sage Weil 已提交
728 729
static inline void ceph_remove_cap(struct ceph_cap *cap)
{
730
	spin_lock(&cap->ci->i_ceph_lock);
S
Sage Weil 已提交
731
	__ceph_remove_cap(cap);
732
	spin_unlock(&cap->ci->i_ceph_lock);
S
Sage Weil 已提交
733
}
734 735
extern void ceph_put_cap(struct ceph_mds_client *mdsc,
			 struct ceph_cap *cap);
S
Sage Weil 已提交
736

737 738
extern void __queue_cap_release(struct ceph_mds_session *session, u64 ino,
				u64 cap_id, u32 migrate_seq, u32 issue_seq);
S
Sage Weil 已提交
739
extern void ceph_queue_caps_release(struct inode *inode);
740
extern int ceph_write_inode(struct inode *inode, struct writeback_control *wbc);
741 742
extern int ceph_fsync(struct file *file, loff_t start, loff_t end,
		      int datasync);
S
Sage Weil 已提交
743 744
extern void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc,
				    struct ceph_mds_session *session);
745 746
extern struct ceph_cap *ceph_get_cap_for_mds(struct ceph_inode_info *ci,
					     int mds);
S
Sage Weil 已提交
747 748 749 750 751 752
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,
753 754
			       struct ceph_mds_session **psession,
			       int again);
S
Sage Weil 已提交
755 756
extern void ceph_check_caps(struct ceph_inode_info *ci, int flags,
			    struct ceph_mds_session *session);
757 758
extern void ceph_check_delayed_caps(struct ceph_mds_client *mdsc);
extern void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc);
S
Sage Weil 已提交
759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781

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;
782

S
Sage Weil 已提交
783
extern int ceph_open(struct inode *inode, struct file *file);
S
Sage Weil 已提交
784 785 786
extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
			    struct file *file, unsigned flags, umode_t mode,
			    int *opened);
S
Sage Weil 已提交
787 788 789 790 791
extern int ceph_release(struct inode *inode, struct file *filp);

/* dir.c */
extern const struct file_operations ceph_dir_fops;
extern const struct inode_operations ceph_dir_iops;
S
Sage Weil 已提交
792
extern const struct dentry_operations ceph_dentry_ops, ceph_snap_dentry_ops,
S
Sage Weil 已提交
793 794 795
	ceph_snapdir_dentry_ops;

extern int ceph_handle_notrace_create(struct inode *dir, struct dentry *dentry);
796 797
extern int ceph_handle_snapdir(struct ceph_mds_request *req,
			       struct dentry *dentry, int err);
S
Sage Weil 已提交
798 799 800 801 802 803
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);
804
extern void ceph_invalidate_dentry_lease(struct dentry *dentry);
805
extern unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn);
S
Sage Weil 已提交
806
extern struct inode *ceph_get_dentry_parent_inode(struct dentry *dentry);
S
Sage Weil 已提交
807 808 809 810 811 812 813 814 815 816 817 818 819 820

/*
 * 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;

G
Greg Farnum 已提交
821 822 823 824 825 826 827 828
/* 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);

829 830 831 832
/* debugfs.c */
extern int ceph_fs_debugfs_init(struct ceph_fs_client *client);
extern void ceph_fs_debugfs_cleanup(struct ceph_fs_client *client);

S
Sage Weil 已提交
833
#endif /* _FS_CEPH_SUPER_H */