super.h 31.1 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>
16
#include <linux/posix_acl.h>
17
#include <linux/refcount.h>
S
Sage Weil 已提交
18

19
#include <linux/ceph/libceph.h>
S
Sage Weil 已提交
20

21 22 23 24
#ifdef CONFIG_CEPH_FSCACHE
#include <linux/fscache.h>
#endif

S
Sage Weil 已提交
25 26 27 28 29
/* 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
30
#define CEPH_BLOCK_SHIFT   22  /* 4 MB */
S
Sage Weil 已提交
31 32
#define CEPH_BLOCK         (1 << CEPH_BLOCK_SHIFT)

33 34 35
#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 */
36
#define CEPH_MOUNT_OPT_INO32           (1<<8) /* 32 bit inos */
37
#define CEPH_MOUNT_OPT_DCACHE          (1<<9) /* use dcache for readdir etc */
38
#define CEPH_MOUNT_OPT_FSCACHE         (1<<10) /* use fscache */
39
#define CEPH_MOUNT_OPT_NOPOOLPERM      (1<<11) /* no pool permission check */
40
#define CEPH_MOUNT_OPT_MOUNTWAIT       (1<<12) /* mount waits if no mds is up */
41

42
#define CEPH_MOUNT_OPT_DEFAULT    CEPH_MOUNT_OPT_DCACHE
S
Sage Weil 已提交
43

44 45 46 47
#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
48

49 50
/* max size of osd read request, limited by libceph */
#define CEPH_MAX_READ_SIZE              CEPH_MSG_MAX_DATA_LEN
51
#define CEPH_RASIZE_DEFAULT             (8192*1024)    /* max readahead */
52 53 54
#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
55

56
struct ceph_mount_options {
57
	int flags;
58 59
	int sb_flags;

S
Sage Weil 已提交
60 61 62
	int wsize;            /* max write size */
	int rsize;            /* max read size */
	int rasize;           /* max readahead */
63 64
	int congestion_kb;    /* max writeback in flight */
	int caps_wanted_delay_min, caps_wanted_delay_max;
65 66
	int max_readdir;       /* max readdir result (entires) */
	int max_readdir_bytes; /* max readdir result (bytes) */
S
Sage Weil 已提交
67

68 69 70 71
	/*
	 * everything above this point can be memcmp'd; everything below
	 * is handled in compare_mount_options()
	 */
S
Sage Weil 已提交
72

73
	char *snapdir_name;   /* default ".snap" */
74
	char *mds_namespace;  /* default NULL */
75
	char *server_path;    /* default  "/" */
76
	char *fscache_uniq;   /* default NULL */
77
};
S
Sage Weil 已提交
78

79
struct ceph_fs_client {
S
Sage Weil 已提交
80 81
	struct super_block *sb;

82 83
	struct ceph_mount_options *mount_options;
	struct ceph_client *client;
S
Sage Weil 已提交
84

85
	unsigned long mount_state;
86 87
	int min_caps;                  /* min caps i added */

88
	struct ceph_mds_client *mdsc;
S
Sage Weil 已提交
89 90 91 92 93 94

	/* writeback */
	mempool_t *wb_pagevec_pool;
	struct workqueue_struct *wb_wq;
	struct workqueue_struct *pg_inv_wq;
	struct workqueue_struct *trunc_wq;
95
	atomic_long_t writeback_count;
S
Sage Weil 已提交
96

97
#ifdef CONFIG_DEBUG_FS
98
	struct dentry *debugfs_dentry_lru, *debugfs_caps;
99
	struct dentry *debugfs_congestion_kb;
100
	struct dentry *debugfs_bdi;
101
	struct dentry *debugfs_mdsc, *debugfs_mdsmap;
102
	struct dentry *debugfs_mds_sessions;
103
#endif
104 105 106 107

#ifdef CONFIG_CEPH_FSCACHE
	struct fscache_cookie *fscache;
#endif
S
Sage Weil 已提交
108 109
};

110

S
Sage Weil 已提交
111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126
/*
 * File i/o capability.  This tracks shared state with the metadata
 * server that allows us to cache or writeback attributes or to read
 * and write data.  For any given inode, we should have one or more
 * capabilities, one issued by each metadata server, and our
 * cumulative access is the OR of all issued capabilities.
 *
 * Each cap is referenced by the inode's i_caps rbtree and by per-mds
 * session capability lists.
 */
struct ceph_cap {
	struct ceph_inode_info *ci;
	struct rb_node ci_node;          /* per-ci cap tree */
	struct ceph_mds_session *session;
	struct list_head session_caps;   /* per-session caplist */
	u64 cap_id;       /* unique cap id (mds provided) */
127 128 129 130 131 132 133 134 135 136 137 138 139 140
	union {
		/* in-use caps */
		struct {
			int issued;       /* latest, from the mds */
			int implemented;  /* implemented superset of
					     issued (for revocation) */
			int mds, mds_wanted;
		};
		/* caps to release */
		struct {
			u64 cap_ino;
			int queue_release;
		};
	};
141 142
	u32 seq, issue_seq, mseq;
	u32 cap_gen;      /* active/stale cycle */
S
Sage Weil 已提交
143 144 145 146 147 148 149 150
	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 */

151 152 153
struct ceph_cap_flush {
	u64 tid;
	int caps; /* 0 means capsnap */
154
	bool wake; /* wake up flush waiters when finish ? */
155 156 157 158
	struct list_head g_list; // global
	struct list_head i_list; // per inode
};

S
Sage Weil 已提交
159 160 161 162 163 164
/*
 * 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 {
165
	refcount_t nref;
166
	struct list_head ci_item;
S
Sage Weil 已提交
167

168 169 170
	struct ceph_cap_flush cap_flush;

	u64 follows;
S
Sage Weil 已提交
171 172 173
	int issued, dirty;
	struct ceph_snap_context *context;

A
Al Viro 已提交
174
	umode_t mode;
175 176
	kuid_t uid;
	kgid_t gid;
S
Sage Weil 已提交
177

178
	struct ceph_buffer *xattr_blob;
S
Sage Weil 已提交
179 180 181 182 183
	u64 xattr_version;

	u64 size;
	struct timespec mtime, atime, ctime;
	u64 time_warp_seq;
184 185
	u64 truncate_size;
	u32 truncate_seq;
S
Sage Weil 已提交
186 187
	int writing;   /* a sync write is still in progress */
	int dirty_pages;     /* dirty pages awaiting writeback */
Y
Yan, Zheng 已提交
188
	bool inline_data;
189
	bool need_flush;
S
Sage Weil 已提交
190 191 192 193
};

static inline void ceph_put_cap_snap(struct ceph_cap_snap *capsnap)
{
194
	if (refcount_dec_and_test(&capsnap->nref)) {
195 196
		if (capsnap->xattr_blob)
			ceph_buffer_put(capsnap->xattr_blob);
S
Sage Weil 已提交
197
		kfree(capsnap);
198
	}
S
Sage Weil 已提交
199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240
}

/*
 * 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;
};

241 242 243 244 245 246 247 248 249 250
/*
 * 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;
251
	unsigned long time;
252 253 254
	u64 offset;
};

S
Sage Weil 已提交
255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278
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 */

279 280
	spinlock_t i_ceph_lock;

S
Sage Weil 已提交
281
	u64 i_version;
282
	u64 i_inline_version;
S
Sage Weil 已提交
283 284 285
	u32 i_time_warp_seq;

	unsigned i_ceph_flags;
286 287 288
	atomic64_t i_release_count;
	atomic64_t i_ordered_count;
	atomic64_t i_complete_seq[2];
S
Sage Weil 已提交
289

S
Sage Weil 已提交
290
	struct ceph_dir_layout i_dir_layout;
S
Sage Weil 已提交
291 292 293 294 295 296 297 298 299
	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;

	struct rb_root i_fragtree;
300
	int i_fragtree_nsplits;
S
Sage Weil 已提交
301 302 303 304
	struct mutex i_fragtree_mutex;

	struct ceph_inode_xattrs_info i_xattrs;

305
	/* capabilities.  protected _both_ by i_ceph_lock and cap->session's
S
Sage Weil 已提交
306 307 308 309 310 311 312 313
	 * 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;
	/* 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. */
314
	struct ceph_cap_flush *i_prealloc_cap_flush;
315
	struct list_head i_cap_flush_list;
S
Sage Weil 已提交
316 317 318 319 320 321
	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 */
	struct ceph_cap_reservation i_cap_migration_resv;
	struct list_head i_cap_snaps;   /* snapped state pending flush to mds */
322 323
	struct ceph_snap_context *i_head_snapc;  /* set if wr_buffer_head > 0 or
						    dirty|flushing caps */
S
Sage Weil 已提交
324 325
	unsigned i_snap_caps;           /* cap bits for snapped files */

326
	int i_nr_by_mode[CEPH_FILE_MODE_BITS];  /* open file counts */
S
Sage Weil 已提交
327

328
	struct mutex i_truncate_mutex;
S
Sage Weil 已提交
329 330 331 332 333 334 335 336 337 338 339
	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;
340
	int i_rd_ref, i_rdcache_ref, i_wr_ref, i_wb_ref;
S
Sage Weil 已提交
341 342
	int i_wrbuffer_ref, i_wrbuffer_ref_head;
	u32 i_shared_gen;       /* increment each time we get FILE_SHARED */
343
	u32 i_rdcache_gen;      /* incremented each time we get FILE_CACHE. */
S
Sage Weil 已提交
344 345 346
	u32 i_rdcache_revoking; /* RDCACHE gen to async invalidate, if any */

	struct list_head i_unsafe_dirops; /* uncommitted mds dir ops */
347
	struct list_head i_unsafe_iops;   /* uncommitted mds inode ops */
S
Sage Weil 已提交
348 349 350 351 352 353 354 355 356 357 358 359
	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;

360 361
#ifdef CONFIG_CEPH_FSCACHE
	struct fscache_cookie *fscache;
362
	u32 i_fscache_gen;
363
#endif
S
Sage Weil 已提交
364 365 366 367 368
	struct inode vfs_inode; /* at end */
};

static inline struct ceph_inode_info *ceph_inode(struct inode *inode)
{
369
	return container_of(inode, struct ceph_inode_info, vfs_inode);
S
Sage Weil 已提交
370 371
}

372 373 374 375 376 377 378 379 380 381
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;
}

382 383 384 385 386 387 388 389
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.
 *
390 391 392 393 394
 *               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
395
static inline u32 ceph_ino_to_ino32(__u64 vino)
396
{
A
Amon Ott 已提交
397 398
	u32 ino = vino & 0xffffffff;
	ino ^= vino >> 32;
399
	if (!ino)
400
		ino = 2;
401 402 403 404 405
	return ino;
}

/*
 * kernel i_ino value
406 407 408 409
 */
static inline ino_t ceph_vino_to_ino(struct ceph_vino vino)
{
#if BITS_PER_LONG == 32
A
Amon Ott 已提交
410 411 412
	return ceph_ino_to_ino32(vino.ino);
#else
	return (ino_t)vino.ino;
413 414 415
#endif
}

416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433
/*
 * 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


434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464
/* 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.
 */
465 466 467 468 469 470 471
#define CEPH_I_DIR_ORDERED	(1 << 0)  /* dentries in dir are ordered */
#define CEPH_I_NODELAY		(1 << 1)  /* do not delay cap release */
#define CEPH_I_FLUSH		(1 << 2)  /* do not delay flush of dirty metadata */
#define CEPH_I_NOFLUSH		(1 << 3)  /* do not flush dirty caps */
#define CEPH_I_POOL_PERM	(1 << 4)  /* pool rd/wr bits are valid */
#define CEPH_I_POOL_RD		(1 << 5)  /* can read from pool */
#define CEPH_I_POOL_WR		(1 << 6)  /* can write to pool */
472
#define CEPH_I_SEC_INITED	(1 << 7)  /* security initialized */
473
#define CEPH_I_CAP_DROPPED	(1 << 8)  /* caps were forcibly dropped */
474
#define CEPH_I_KICK_FLUSH	(1 << 9)  /* kick flushing caps */
475
#define CEPH_I_FLUSH_SNAPS	(1 << 10) /* need flush snapss */
476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501
#define CEPH_I_ERROR_WRITE	(1 << 11) /* have seen write errors */

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

static inline void ceph_clear_error_write(struct ceph_inode_info *ci)
{
	if (READ_ONCE(ci->i_ceph_flags) & CEPH_I_ERROR_WRITE) {
		spin_lock(&ci->i_ceph_lock);
		ci->i_ceph_flags &= ~CEPH_I_ERROR_WRITE;
		spin_unlock(&ci->i_ceph_lock);
	}
}
502

503
static inline void __ceph_dir_set_complete(struct ceph_inode_info *ci,
504 505
					   long long release_count,
					   long long ordered_count)
S
Sage Weil 已提交
506
{
507 508 509
	smp_mb__before_atomic();
	atomic64_set(&ci->i_complete_seq[0], release_count);
	atomic64_set(&ci->i_complete_seq[1], ordered_count);
S
Sage Weil 已提交
510 511
}

512
static inline void __ceph_dir_clear_complete(struct ceph_inode_info *ci)
S
Sage Weil 已提交
513
{
514 515 516 517 518 519
	atomic64_inc(&ci->i_release_count);
}

static inline void __ceph_dir_clear_ordered(struct ceph_inode_info *ci)
{
	atomic64_inc(&ci->i_ordered_count);
520
}
S
Sage Weil 已提交
521

522 523
static inline bool __ceph_dir_is_complete(struct ceph_inode_info *ci)
{
524 525
	return atomic64_read(&ci->i_complete_seq[0]) ==
		atomic64_read(&ci->i_release_count);
S
Sage Weil 已提交
526 527
}

528 529
static inline bool __ceph_dir_is_complete_ordered(struct ceph_inode_info *ci)
{
530 531 532 533
	return  atomic64_read(&ci->i_complete_seq[0]) ==
		atomic64_read(&ci->i_release_count) &&
		atomic64_read(&ci->i_complete_seq[1]) ==
		atomic64_read(&ci->i_ordered_count);
534 535
}

536
static inline void ceph_dir_clear_complete(struct inode *inode)
S
Sage Weil 已提交
537
{
538 539
	__ceph_dir_clear_complete(ceph_inode(inode));
}
S
Sage Weil 已提交
540

541
static inline void ceph_dir_clear_ordered(struct inode *inode)
542
{
543
	__ceph_dir_clear_ordered(ceph_inode(inode));
S
Sage Weil 已提交
544 545
}

546 547
static inline bool ceph_dir_is_complete_ordered(struct inode *inode)
{
548 549
	bool ret = __ceph_dir_is_complete_ordered(ceph_inode(inode));
	smp_rmb();
550 551
	return ret;
}
S
Sage Weil 已提交
552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585

/* 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;
}

/*
 * 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;
586
	spin_lock(&ci->i_ceph_lock);
S
Sage Weil 已提交
587
	issued = __ceph_caps_issued(ci, NULL);
588
	spin_unlock(&ci->i_ceph_lock);
S
Sage Weil 已提交
589 590 591 592 593 594 595
	return issued;
}

static inline int ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask,
					int touch)
{
	int r;
596
	spin_lock(&ci->i_ceph_lock);
S
Sage Weil 已提交
597
	r = __ceph_caps_issued_mask(ci, mask, touch);
598
	spin_unlock(&ci->i_ceph_lock);
S
Sage Weil 已提交
599 600 601 602 603 604 605
	return r;
}

static inline int __ceph_caps_dirty(struct ceph_inode_info *ci)
{
	return ci->i_dirty_caps | ci->i_flushing_caps;
}
606 607 608 609
extern struct ceph_cap_flush *ceph_alloc_cap_flush(void);
extern void ceph_free_cap_flush(struct ceph_cap_flush *cf);
extern int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask,
				  struct ceph_cap_flush **pcf);
S
Sage Weil 已提交
610

Y
Yan, Zheng 已提交
611 612
extern int __ceph_caps_revoking_other(struct ceph_inode_info *ci,
				      struct ceph_cap *ocap, int mask);
S
Sage Weil 已提交
613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629
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 */
630
extern int __ceph_caps_mds_wanted(struct ceph_inode_info *ci, bool check);
S
Sage Weil 已提交
631

632 633 634
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);
635
extern void ceph_reserve_caps(struct ceph_mds_client *mdsc,
636 637 638
			     struct ceph_cap_reservation *ctx, int need);
extern int ceph_unreserve_caps(struct ceph_mds_client *mdsc,
			       struct ceph_cap_reservation *ctx);
639
extern void ceph_reservation_status(struct ceph_fs_client *client,
S
Sage Weil 已提交
640
				    int *total, int *avail, int *used,
641
				    int *reserved, int *min);
S
Sage Weil 已提交
642 643 644 645 646 647



/*
 * we keep buffered readdir results attached to file->private_data
 */
648
#define CEPH_F_SYNC     1
649
#define CEPH_F_ATEND    2
650

S
Sage Weil 已提交
651
struct ceph_file_info {
652 653
	short fmode;     /* initialized on open */
	short flags;     /* CEPH_F_* */
S
Sage Weil 已提交
654 655 656 657 658 659

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

	/* readdir: position within a frag */
Y
Yan, Zheng 已提交
660
	unsigned next_offset;  /* offset of next chunk (last_name's + 1) */
S
Sage Weil 已提交
661
	char *last_name;       /* last entry in previous chunk */
662 663 664
	long long dir_release_count;
	long long dir_ordered_count;
	int readdir_cache_idx;
S
Sage Weil 已提交
665 666 667 668 669 670

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

671 672 673 674 675
struct ceph_readdir_cache_control {
	struct page  *page;
	struct dentry **dentries;
	int index;
};
S
Sage Weil 已提交
676 677 678 679 680 681 682 683 684 685 686 687 688

/*
 * 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;
689 690
	struct rb_node node;

S
Sage Weil 已提交
691 692 693 694 695
	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 */
696
	u32 num_prior_parent_snaps;   /*  had prior to parent_since */
S
Sage Weil 已提交
697
	u64 *snaps;                   /* snaps specific to this realm */
698
	u32 num_snaps;
S
Sage Weil 已提交
699 700 701 702 703 704 705

	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 */

706 707
	struct list_head dirty_item;     /* if realm needs new context */

S
Sage Weil 已提交
708 709 710 711 712 713 714
	/* 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;
};

715
static inline int default_congestion_kb(void)
S
Sage Weil 已提交
716
{
717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741
	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
742 743 744 745 746 747 748 749 750 751 752 753
}



/* 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,
754 755
				  void *p, void *e, bool deletion,
				  struct ceph_snap_realm **realm_ret);
S
Sage Weil 已提交
756
extern void ceph_handle_snap(struct ceph_mds_client *mdsc,
757
			     struct ceph_mds_session *session,
S
Sage Weil 已提交
758
			     struct ceph_msg *msg);
759
extern void ceph_queue_cap_snap(struct ceph_inode_info *ci);
S
Sage Weil 已提交
760 761 762 763 764 765 766 767 768 769 770
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) &&
771 772
	       list_last_entry(&ci->i_cap_snaps, struct ceph_cap_snap,
			       ci_item)->writing;
S
Sage Weil 已提交
773 774 775 776 777 778 779
}

/* 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);
780
extern int ceph_drop_inode(struct inode *inode);
S
Sage Weil 已提交
781 782 783 784 785 786 787 788 789 790

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,
791
			   struct ceph_mds_request *req);
S
Sage Weil 已提交
792 793 794 795 796
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);

797
extern bool ceph_inode_set_size(struct inode *inode, loff_t size);
798
extern void __ceph_do_pending_vmtruncate(struct inode *inode);
799 800 801 802
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
803

804 805 806 807 808 809
extern int __ceph_do_getattr(struct inode *inode, struct page *locked_page,
			     int mask, bool force);
static inline int ceph_do_getattr(struct inode *inode, int mask, bool force)
{
	return __ceph_do_getattr(inode, NULL, mask, force);
}
810
extern int ceph_permission(struct inode *inode, int mask);
811
extern int __ceph_setattr(struct inode *inode, struct iattr *attr);
S
Sage Weil 已提交
812
extern int ceph_setattr(struct dentry *dentry, struct iattr *attr);
813 814
extern int ceph_getattr(const struct path *path, struct kstat *stat,
			u32 request_mask, unsigned int flags);
S
Sage Weil 已提交
815 816

/* xattr.c */
817
int __ceph_setxattr(struct inode *, const char *, const void *, size_t, int);
818
ssize_t __ceph_getxattr(struct inode *, const char *, void *, size_t);
S
Sage Weil 已提交
819 820 821
extern ssize_t ceph_listxattr(struct dentry *, char *, size_t);
extern void __ceph_build_xattrs_blob(struct ceph_inode_info *ci);
extern void __ceph_destroy_xattrs(struct ceph_inode_info *ci);
822 823
extern void __init ceph_xattr_init(void);
extern void ceph_xattr_exit(void);
824
extern const struct xattr_handler *ceph_xattr_handlers[];
S
Sage Weil 已提交
825

826 827 828 829 830 831 832 833 834 835 836 837 838 839
#ifdef CONFIG_SECURITY
extern bool ceph_security_xattr_deadlock(struct inode *in);
extern bool ceph_security_xattr_wanted(struct inode *in);
#else
static inline bool ceph_security_xattr_deadlock(struct inode *in)
{
	return false;
}
static inline bool ceph_security_xattr_wanted(struct inode *in)
{
	return false;
}
#endif

840
/* acl.c */
841 842 843 844 845
struct ceph_acls_info {
	void *default_acl;
	void *acl;
	struct ceph_pagelist *pagelist;
};
846 847 848 849

#ifdef CONFIG_CEPH_FS_POSIX_ACL

struct posix_acl *ceph_get_acl(struct inode *, int);
S
Sage Weil 已提交
850
int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type);
851 852 853 854
int ceph_pre_init_acls(struct inode *dir, umode_t *mode,
		       struct ceph_acls_info *info);
void ceph_init_inode_acls(struct inode *inode, struct ceph_acls_info *info);
void ceph_release_acls_info(struct ceph_acls_info *info);
855 856 857 858 859

static inline void ceph_forget_all_cached_acls(struct inode *inode)
{
       forget_all_cached_acls(inode);
}
860 861 862 863

#else

#define ceph_get_acl NULL
S
Sage Weil 已提交
864
#define ceph_set_acl NULL
865

866 867
static inline int ceph_pre_init_acls(struct inode *dir, umode_t *mode,
				     struct ceph_acls_info *info)
868 869 870
{
	return 0;
}
871 872 873 874 875 876 877
static inline void ceph_init_inode_acls(struct inode *inode,
					struct ceph_acls_info *info)
{
}
static inline void ceph_release_acls_info(struct ceph_acls_info *info)
{
}
878 879 880 881 882 883 884 885 886 887 888
static inline int ceph_acl_chmod(struct dentry *dentry, struct inode *inode)
{
	return 0;
}

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

#endif

S
Sage Weil 已提交
889 890 891 892
/* caps.c */
extern const char *ceph_cap_string(int c);
extern void ceph_handle_caps(struct ceph_mds_session *session,
			     struct ceph_msg *msg);
893 894 895 896 897 898 899
extern struct ceph_cap *ceph_get_cap(struct ceph_mds_client *mdsc,
				     struct ceph_cap_reservation *ctx);
extern void ceph_add_cap(struct inode *inode,
			 struct ceph_mds_session *session, u64 cap_id,
			 int fmode, unsigned issued, unsigned wanted,
			 unsigned cap, unsigned seq, u64 realmino, int flags,
			 struct ceph_cap **new_cap);
900
extern void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release);
901 902
extern void ceph_put_cap(struct ceph_mds_client *mdsc,
			 struct ceph_cap *cap);
903
extern int ceph_is_any_caps(struct inode *inode);
S
Sage Weil 已提交
904 905

extern void ceph_queue_caps_release(struct inode *inode);
906
extern int ceph_write_inode(struct inode *inode, struct writeback_control *wbc);
907 908
extern int ceph_fsync(struct file *file, loff_t start, loff_t end,
		      int datasync);
909 910
extern void ceph_early_kick_flushing_caps(struct ceph_mds_client *mdsc,
					  struct ceph_mds_session *session);
S
Sage Weil 已提交
911 912
extern void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc,
				    struct ceph_mds_session *session);
913 914
extern struct ceph_cap *ceph_get_cap_for_mds(struct ceph_inode_info *ci,
					     int mds);
S
Sage Weil 已提交
915 916 917 918 919
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);
920 921
extern void ceph_flush_snaps(struct ceph_inode_info *ci,
			     struct ceph_mds_session **psession);
922
extern bool __ceph_should_report_size(struct ceph_inode_info *ci);
S
Sage Weil 已提交
923 924
extern void ceph_check_caps(struct ceph_inode_info *ci, int flags,
			    struct ceph_mds_session *session);
925 926
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
927 928 929 930

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,
931
				      struct inode *dir,
S
Sage Weil 已提交
932 933 934
				      int mds, int drop, int unless);

extern int ceph_get_caps(struct ceph_inode_info *ci, int need, int want,
935
			 loff_t endoff, int *got, struct page **pinned_page);
936 937
extern int ceph_try_get_caps(struct ceph_inode_info *ci,
			     int need, int want, int *got);
S
Sage Weil 已提交
938 939

/* for counting open files by mode */
940
extern void __ceph_get_fmode(struct ceph_inode_info *ci, int mode);
S
Sage Weil 已提交
941 942 943 944 945
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);
946 947 948
extern int ceph_uninline_data(struct file *filp, struct page *locked_page);
extern int ceph_pool_perm_check(struct ceph_inode_info *ci, int need);
extern void ceph_pool_perm_destroy(struct ceph_mds_client* mdsc);
S
Sage Weil 已提交
949 950 951

/* file.c */
extern const struct file_operations ceph_file_fops;
952

953
extern int ceph_renew_caps(struct inode *inode);
S
Sage Weil 已提交
954
extern int ceph_open(struct inode *inode, struct file *file);
955 956 957
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
958
extern int ceph_release(struct inode *inode, struct file *filp);
959 960
extern void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
				  char *data, size_t len);
961

S
Sage Weil 已提交
962 963
/* dir.c */
extern const struct file_operations ceph_dir_fops;
964
extern const struct file_operations ceph_snapdir_fops;
S
Sage Weil 已提交
965
extern const struct inode_operations ceph_dir_iops;
966
extern const struct inode_operations ceph_snapdir_iops;
967
extern const struct dentry_operations ceph_dentry_ops;
S
Sage Weil 已提交
968

969
extern loff_t ceph_make_fpos(unsigned high, unsigned off, bool hash_order);
S
Sage Weil 已提交
970
extern int ceph_handle_notrace_create(struct inode *dir, struct dentry *dentry);
971 972
extern int ceph_handle_snapdir(struct ceph_mds_request *req,
			       struct dentry *dentry, int err);
S
Sage Weil 已提交
973 974 975 976 977 978
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);
979
extern void ceph_invalidate_dentry_lease(struct dentry *dentry);
980
extern unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn);
981
extern void ceph_readdir_cache_release(struct ceph_readdir_cache_control *ctl);
S
Sage Weil 已提交
982 983 984 985 986 987 988

/* 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;

989
/* locks.c */
990
extern __init void ceph_flock_init(void);
991 992 993
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);
994 995 996 997 998 999 1000
extern int ceph_encode_locks_to_buffer(struct inode *inode,
				       struct ceph_filelock *flocks,
				       int num_fcntl_locks,
				       int num_flock_locks);
extern int ceph_locks_to_pagelist(struct ceph_filelock *flocks,
				  struct ceph_pagelist *pagelist,
				  int num_fcntl_locks, int num_flock_locks);
1001 1002
extern int lock_to_ceph_filelock(struct file_lock *fl, struct ceph_filelock *c);

1003 1004 1005 1006
/* 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
1007
#endif /* _FS_CEPH_SUPER_H */
新手
引导
客服 返回
顶部