fs.h 68.1 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29
#ifndef _LINUX_FS_H
#define _LINUX_FS_H

/*
 * This file has definitions for some important file table
 * structures etc.
 */

#include <linux/limits.h>
#include <linux/ioctl.h>

/*
 * It's silly to have NR_OPEN bigger than NR_FILE, but you can change
 * the file limit at runtime and only root can increase the per-process
 * nr_file rlimit, so it's safe to set up a ridiculously high absolute
 * upper limit on files-per-process.
 *
 * Some programs (notably those using select()) may have to be 
 * recompiled to take full advantage of the new limits..  
 */

/* Fixed constants first: */
#undef NR_OPEN
#define NR_OPEN (1024*1024)	/* Absolute upper limit on fd num */
#define INR_OPEN 1024		/* Initial setting for nfile rlimits */

#define BLOCK_SIZE_BITS 10
#define BLOCK_SIZE (1<<BLOCK_SIZE_BITS)

30 31 32
#define SEEK_SET	0	/* seek relative to beginning of file */
#define SEEK_CUR	1	/* seek relative to current file position */
#define SEEK_END	2	/* seek relative to end of file */
33
#define SEEK_MAX	SEEK_END
34

L
Linus Torvalds 已提交
35 36 37 38 39 40 41
/* And dynamically-tunable limits and defaults: */
struct files_stat_struct {
	int nr_files;		/* read only */
	int nr_free_files;	/* read only */
	int max_files;		/* tunable */
};
extern struct files_stat_struct files_stat;
D
Dipankar Sarma 已提交
42
extern int get_max_files(void);
L
Linus Torvalds 已提交
43 44 45 46

struct inodes_stat_t {
	int nr_inodes;
	int nr_unused;
47
	int dummy[5];		/* padding for sysctl ABI compatibility */
L
Linus Torvalds 已提交
48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71
};
extern struct inodes_stat_t inodes_stat;

extern int leases_enable, lease_break_time;

#ifdef CONFIG_DNOTIFY
extern int dir_notify_enable;
#endif

#define NR_FILE  8192	/* this can well be larger on a larger system */

#define MAY_EXEC 1
#define MAY_WRITE 2
#define MAY_READ 4
#define MAY_APPEND 8

#define FMODE_READ 1
#define FMODE_WRITE 2

/* Internal kernel extensions */
#define FMODE_LSEEK	4
#define FMODE_PREAD	8
#define FMODE_PWRITE	FMODE_PREAD	/* These go hand in hand */

72 73 74 75 76
/* File is being opened for execution. Primary users of this flag are
   distributed filesystems that can use it to achieve correct ETXTBUSY
   behavior for cross-node execution/opening_for_writing of files */
#define FMODE_EXEC	16

L
Linus Torvalds 已提交
77 78 79 80 81
#define RW_MASK		1
#define RWA_MASK	2
#define READ 0
#define WRITE 1
#define READA 2		/* read-ahead  - don't block if no resources */
82
#define SWRITE 3	/* for ll_rw_block() - wait for buffer lock */
L
Linus Torvalds 已提交
83
#define READ_SYNC	(READ | (1 << BIO_RW_SYNC))
84
#define READ_META	(READ | (1 << BIO_RW_META))
L
Linus Torvalds 已提交
85 86 87 88 89 90 91 92 93 94
#define WRITE_SYNC	(WRITE | (1 << BIO_RW_SYNC))
#define WRITE_BARRIER	((1 << BIO_RW) | (1 << BIO_RW_BARRIER))

#define SEL_IN		1
#define SEL_OUT		2
#define SEL_EX		4

/* public flags for file_system_type */
#define FS_REQUIRES_DEV 1 
#define FS_BINARY_MOUNTDATA 2
M
Miklos Szeredi 已提交
95
#define FS_HAS_SUBTYPE 4
L
Linus Torvalds 已提交
96
#define FS_REVAL_DOT	16384	/* Check the paths ".", ".." for staleness */
97 98 99 100
#define FS_RENAME_DOES_D_MOVE	32768	/* FS will handle d_move()
					 * during rename() internally.
					 */

L
Linus Torvalds 已提交
101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116
/*
 * These are the fs-independent mount-flags: up to 32 flags are supported
 */
#define MS_RDONLY	 1	/* Mount read-only */
#define MS_NOSUID	 2	/* Ignore suid and sgid bits */
#define MS_NODEV	 4	/* Disallow access to device special files */
#define MS_NOEXEC	 8	/* Disallow program execution */
#define MS_SYNCHRONOUS	16	/* Writes are synced at once */
#define MS_REMOUNT	32	/* Alter flags of a mounted FS */
#define MS_MANDLOCK	64	/* Allow mandatory locks on an FS */
#define MS_DIRSYNC	128	/* Directory modifications are synchronous */
#define MS_NOATIME	1024	/* Do not update access times. */
#define MS_NODIRATIME	2048	/* Do not update directory access times */
#define MS_BIND		4096
#define MS_MOVE		8192
#define MS_REC		16384
117 118 119
#define MS_VERBOSE	32768	/* War is peace. Verbosity is silence.
				   MS_VERBOSE is deprecated. */
#define MS_SILENT	32768
M
Miklos Szeredi 已提交
120
#define MS_POSIXACL	(1<<16)	/* VFS does not apply the umask */
R
Ram Pai 已提交
121
#define MS_UNBINDABLE	(1<<17)	/* change to unbindable */
122
#define MS_PRIVATE	(1<<18)	/* change to private */
R
Ram Pai 已提交
123
#define MS_SLAVE	(1<<19)	/* change to slave */
R
Ram Pai 已提交
124
#define MS_SHARED	(1<<20)	/* change to shared */
V
Valerie Henson 已提交
125
#define MS_RELATIME	(1<<21)	/* Update atime relative to mtime/ctime. */
L
Linus Torvalds 已提交
126 127 128 129 130 131
#define MS_ACTIVE	(1<<30)
#define MS_NOUSER	(1<<31)

/*
 * Superblock flags that can be altered by MS_REMOUNT
 */
132
#define MS_RMT_MASK	(MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK)
L
Linus Torvalds 已提交
133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173

/*
 * Old magic mount flag and mask
 */
#define MS_MGC_VAL 0xC0ED0000
#define MS_MGC_MSK 0xffff0000

/* Inode flags - they have nothing to superblock flags now */

#define S_SYNC		1	/* Writes are synced at once */
#define S_NOATIME	2	/* Do not update access times */
#define S_APPEND	4	/* Append-only file */
#define S_IMMUTABLE	8	/* Immutable file */
#define S_DEAD		16	/* removed, but still open directory */
#define S_NOQUOTA	32	/* Inode is not counted to quota */
#define S_DIRSYNC	64	/* Directory modifications are synchronous */
#define S_NOCMTIME	128	/* Do not update file c/mtime */
#define S_SWAPFILE	256	/* Do not truncate: swapon got its bmaps */
#define S_PRIVATE	512	/* Inode is fs-internal */

/*
 * Note that nosuid etc flags are inode-specific: setting some file-system
 * flags just means all the inodes inherit those flags by default. It might be
 * possible to override it selectively if you really wanted to with some
 * ioctl() that is not currently implemented.
 *
 * Exception: MS_RDONLY is always applied to the entire file system.
 *
 * Unfortunately, it is possible to change a filesystems flags with it mounted
 * with files in use.  This means that all of the inodes will not have their
 * i_flags updated.  Hence, i_flags no longer inherit the superblock mount
 * flags, so these have to be checked separately. -- rmk@arm.uk.linux.org
 */
#define __IS_FLG(inode,flg) ((inode)->i_sb->s_flags & (flg))

#define IS_RDONLY(inode) ((inode)->i_sb->s_flags & MS_RDONLY)
#define IS_SYNC(inode)		(__IS_FLG(inode, MS_SYNCHRONOUS) || \
					((inode)->i_flags & S_SYNC))
#define IS_DIRSYNC(inode)	(__IS_FLG(inode, MS_SYNCHRONOUS|MS_DIRSYNC) || \
					((inode)->i_flags & (S_SYNC|S_DIRSYNC)))
#define IS_MANDLOCK(inode)	__IS_FLG(inode, MS_MANDLOCK)
174
#define IS_NOATIME(inode)   __IS_FLG(inode, MS_RDONLY|MS_NOATIME)
L
Linus Torvalds 已提交
175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214

#define IS_NOQUOTA(inode)	((inode)->i_flags & S_NOQUOTA)
#define IS_APPEND(inode)	((inode)->i_flags & S_APPEND)
#define IS_IMMUTABLE(inode)	((inode)->i_flags & S_IMMUTABLE)
#define IS_POSIXACL(inode)	__IS_FLG(inode, MS_POSIXACL)

#define IS_DEADDIR(inode)	((inode)->i_flags & S_DEAD)
#define IS_NOCMTIME(inode)	((inode)->i_flags & S_NOCMTIME)
#define IS_SWAPFILE(inode)	((inode)->i_flags & S_SWAPFILE)
#define IS_PRIVATE(inode)	((inode)->i_flags & S_PRIVATE)

/* the read-only stuff doesn't really belong here, but any other place is
   probably as bad and I don't want to create yet another include file. */

#define BLKROSET   _IO(0x12,93)	/* set device read-only (0 = read-write) */
#define BLKROGET   _IO(0x12,94)	/* get read-only status (0 = read_write) */
#define BLKRRPART  _IO(0x12,95)	/* re-read partition table */
#define BLKGETSIZE _IO(0x12,96)	/* return device size /512 (long *arg) */
#define BLKFLSBUF  _IO(0x12,97)	/* flush buffer cache */
#define BLKRASET   _IO(0x12,98)	/* set read ahead for block device */
#define BLKRAGET   _IO(0x12,99)	/* get current read ahead setting */
#define BLKFRASET  _IO(0x12,100)/* set filesystem (mm/filemap.c) read-ahead */
#define BLKFRAGET  _IO(0x12,101)/* get filesystem (mm/filemap.c) read-ahead */
#define BLKSECTSET _IO(0x12,102)/* set max sectors per request (ll_rw_blk.c) */
#define BLKSECTGET _IO(0x12,103)/* get max sectors per request (ll_rw_blk.c) */
#define BLKSSZGET  _IO(0x12,104)/* get block device sector size */
#if 0
#define BLKPG      _IO(0x12,105)/* See blkpg.h */

/* Some people are morons.  Do not use sizeof! */

#define BLKELVGET  _IOR(0x12,106,size_t)/* elevator get */
#define BLKELVSET  _IOW(0x12,107,size_t)/* elevator set */
/* This was here just to show that the number is taken -
   probably all these _IO(0x12,*) ioctls should be moved to blkpg.h. */
#endif
/* A jump here: 108-111 have been used for various private purposes. */
#define BLKBSZGET  _IOR(0x12,112,size_t)
#define BLKBSZSET  _IOW(0x12,113,size_t)
#define BLKGETSIZE64 _IOR(0x12,114,size_t)	/* return device size in bytes (u64 *arg) */
215 216 217 218
#define BLKTRACESETUP _IOWR(0x12,115,struct blk_user_trace_setup)
#define BLKTRACESTART _IO(0x12,116)
#define BLKTRACESTOP _IO(0x12,117)
#define BLKTRACETEARDOWN _IO(0x12,118)
L
Linus Torvalds 已提交
219 220 221 222 223

#define BMAP_IOCTL 1		/* obsolete - kept for compatibility */
#define FIBMAP	   _IO(0x00,1)	/* bmap access */
#define FIGETBSZ   _IO(0x00,2)	/* get the block size used for bmap */

224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256
#define	FS_IOC_GETFLAGS			_IOR('f', 1, long)
#define	FS_IOC_SETFLAGS			_IOW('f', 2, long)
#define	FS_IOC_GETVERSION		_IOR('v', 1, long)
#define	FS_IOC_SETVERSION		_IOW('v', 2, long)
#define FS_IOC32_GETFLAGS		_IOR('f', 1, int)
#define FS_IOC32_SETFLAGS		_IOW('f', 2, int)
#define FS_IOC32_GETVERSION		_IOR('v', 1, int)
#define FS_IOC32_SETVERSION		_IOW('v', 2, int)

/*
 * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
 */
#define	FS_SECRM_FL			0x00000001 /* Secure deletion */
#define	FS_UNRM_FL			0x00000002 /* Undelete */
#define	FS_COMPR_FL			0x00000004 /* Compress file */
#define FS_SYNC_FL			0x00000008 /* Synchronous updates */
#define FS_IMMUTABLE_FL			0x00000010 /* Immutable file */
#define FS_APPEND_FL			0x00000020 /* writes to file may only append */
#define FS_NODUMP_FL			0x00000040 /* do not dump file */
#define FS_NOATIME_FL			0x00000080 /* do not update atime */
/* Reserved for compression usage... */
#define FS_DIRTY_FL			0x00000100
#define FS_COMPRBLK_FL			0x00000200 /* One or more compressed clusters */
#define FS_NOCOMP_FL			0x00000400 /* Don't compress */
#define FS_ECOMPR_FL			0x00000800 /* Compression error */
/* End compression flags --- maybe not all used */
#define FS_BTREE_FL			0x00001000 /* btree format dir */
#define FS_INDEX_FL			0x00001000 /* hash-indexed directory */
#define FS_IMAGIC_FL			0x00002000 /* AFS directory */
#define FS_JOURNAL_DATA_FL		0x00004000 /* Reserved for ext3 */
#define FS_NOTAIL_FL			0x00008000 /* file tail should not be merged */
#define FS_DIRSYNC_FL			0x00010000 /* dirsync behaviour (directories only) */
#define FS_TOPDIR_FL			0x00020000 /* Top of directory hierarchies*/
257 258
#define FS_EXTENT_FL			0x00080000 /* Extents */
#define FS_DIRECTIO_FL			0x00100000 /* Use direct i/o */
259 260 261 262 263 264
#define FS_RESERVED_FL			0x80000000 /* reserved for ext2 lib */

#define FS_FL_USER_VISIBLE		0x0003DFFF /* User visible flags */
#define FS_FL_USER_MODIFIABLE		0x000380FF /* User modifiable flags */


265 266 267 268
#define SYNC_FILE_RANGE_WAIT_BEFORE	1
#define SYNC_FILE_RANGE_WRITE		2
#define SYNC_FILE_RANGE_WAIT_AFTER	4

L
Linus Torvalds 已提交
269 270 271 272 273 274 275
#ifdef __KERNEL__

#include <linux/linkage.h>
#include <linux/wait.h>
#include <linux/types.h>
#include <linux/kdev_t.h>
#include <linux/dcache.h>
276
#include <linux/namei.h>
L
Linus Torvalds 已提交
277 278 279 280 281 282 283
#include <linux/stat.h>
#include <linux/cache.h>
#include <linux/kobject.h>
#include <linux/list.h>
#include <linux/radix-tree.h>
#include <linux/prio_tree.h>
#include <linux/init.h>
284
#include <linux/pid.h>
285
#include <linux/mutex.h>
286
#include <linux/sysctl.h>
287
#include <linux/capability.h>
L
Linus Torvalds 已提交
288 289 290 291 292

#include <asm/atomic.h>
#include <asm/semaphore.h>
#include <asm/byteorder.h>

293
struct export_operations;
294
struct hd_geometry;
L
Linus Torvalds 已提交
295 296
struct iovec;
struct nameidata;
297
struct kiocb;
L
Linus Torvalds 已提交
298 299 300 301 302 303 304 305 306 307 308 309 310 311
struct pipe_inode_info;
struct poll_table_struct;
struct kstatfs;
struct vm_area_struct;
struct vfsmount;

extern void __init inode_init(unsigned long);
extern void __init inode_init_early(void);
extern void __init mnt_init(unsigned long);
extern void __init files_init(unsigned long);

struct buffer_head;
typedef int (get_block_t)(struct inode *inode, sector_t iblock,
			struct buffer_head *bh_result, int create);
312
typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
L
Linus Torvalds 已提交
313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331
			ssize_t bytes, void *private);

/*
 * Attribute flags.  These should be or-ed together to figure out what
 * has been changed!
 */
#define ATTR_MODE	1
#define ATTR_UID	2
#define ATTR_GID	4
#define ATTR_SIZE	8
#define ATTR_ATIME	16
#define ATTR_MTIME	32
#define ATTR_CTIME	64
#define ATTR_ATIME_SET	128
#define ATTR_MTIME_SET	256
#define ATTR_FORCE	512	/* Not a change, but a change it */
#define ATTR_ATTR_FLAG	1024
#define ATTR_KILL_SUID	2048
#define ATTR_KILL_SGID	4096
332
#define ATTR_FILE	8192
L
Linus Torvalds 已提交
333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351

/*
 * This is the Inode Attributes structure, used for notify_change().  It
 * uses the above definitions as flags, to know which values have changed.
 * Also, in this manner, a Filesystem can look at only the values it cares
 * about.  Basically, these are the attributes that the VFS layer can
 * request to change from the FS layer.
 *
 * Derek Atkins <warlord@MIT.EDU> 94-10-20
 */
struct iattr {
	unsigned int	ia_valid;
	umode_t		ia_mode;
	uid_t		ia_uid;
	gid_t		ia_gid;
	loff_t		ia_size;
	struct timespec	ia_atime;
	struct timespec	ia_mtime;
	struct timespec	ia_ctime;
352 353 354 355 356 357 358

	/*
	 * Not an attribute, but an auxilary info for filesystems wanting to
	 * implement an ftruncate() like method.  NOTE: filesystem should
	 * check for (ia_valid & ATTR_FILE), and not for (ia_file != NULL).
	 */
	struct file	*ia_file;
L
Linus Torvalds 已提交
359 360 361 362 363 364 365
};

/*
 * Includes for diskquotas.
 */
#include <linux/quota.h>

366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396
/** 
 * enum positive_aop_returns - aop return codes with specific semantics
 *
 * @AOP_WRITEPAGE_ACTIVATE: Informs the caller that page writeback has
 * 			    completed, that the page is still locked, and
 * 			    should be considered active.  The VM uses this hint
 * 			    to return the page to the active list -- it won't
 * 			    be a candidate for writeback again in the near
 * 			    future.  Other callers must be careful to unlock
 * 			    the page if they get this return.  Returned by
 * 			    writepage(); 
 *
 * @AOP_TRUNCATED_PAGE: The AOP method that was handed a locked page has
 *  			unlocked it and the page might have been truncated.
 *  			The caller should back up to acquiring a new page and
 *  			trying again.  The aop will be taking reasonable
 *  			precautions not to livelock.  If the caller held a page
 *  			reference, it should drop it before retrying.  Returned
 *  			by readpage(), prepare_write(), and commit_write().
 *
 * address_space_operation functions return these large constants to indicate
 * special semantics to the caller.  These are much larger than the bytes in a
 * page to allow for functions that return the number of bytes operated on in a
 * given page.
 */

enum positive_aop_returns {
	AOP_WRITEPAGE_ACTIVATE	= 0x80000,
	AOP_TRUNCATED_PAGE	= 0x80001,
};

L
Linus Torvalds 已提交
397 398 399 400 401 402 403 404 405 406
/*
 * oh the beauties of C type declarations.
 */
struct page;
struct address_space;
struct writeback_control;

struct address_space_operations {
	int (*writepage)(struct page *page, struct writeback_control *wbc);
	int (*readpage)(struct file *, struct page *);
407
	void (*sync_page)(struct page *);
L
Linus Torvalds 已提交
408 409 410 411

	/* Write back some dirty pages from this mapping. */
	int (*writepages)(struct address_space *, struct writeback_control *);

412
	/* Set a page dirty.  Return true if this dirtied it */
L
Linus Torvalds 已提交
413 414 415 416 417 418 419 420 421 422 423 424 425
	int (*set_page_dirty)(struct page *page);

	int (*readpages)(struct file *filp, struct address_space *mapping,
			struct list_head *pages, unsigned nr_pages);

	/*
	 * ext3 requires that a successful prepare_write() call be followed
	 * by a commit_write() call - they must be balanced
	 */
	int (*prepare_write)(struct file *, struct page *, unsigned, unsigned);
	int (*commit_write)(struct file *, struct page *, unsigned, unsigned);
	/* Unfortunately this kludge is needed for FIBMAP. Don't use it */
	sector_t (*bmap)(struct address_space *, sector_t);
426
	void (*invalidatepage) (struct page *, unsigned long);
A
Al Viro 已提交
427
	int (*releasepage) (struct page *, gfp_t);
L
Linus Torvalds 已提交
428 429
	ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
			loff_t offset, unsigned long nr_segs);
430 431
	struct page* (*get_xip_page)(struct address_space *, sector_t,
			int);
432
	/* migrate the contents of a page to the specified target */
433 434
	int (*migratepage) (struct address_space *,
			struct page *, struct page *);
435
	int (*launder_page) (struct page *);
L
Linus Torvalds 已提交
436 437 438 439 440 441 442 443 444 445 446 447 448 449
};

struct backing_dev_info;
struct address_space {
	struct inode		*host;		/* owner: inode, block_device */
	struct radix_tree_root	page_tree;	/* radix tree of all pages */
	rwlock_t		tree_lock;	/* and rwlock protecting it */
	unsigned int		i_mmap_writable;/* count VM_SHARED mappings */
	struct prio_tree_root	i_mmap;		/* tree of private and shared mappings */
	struct list_head	i_mmap_nonlinear;/*list VM_NONLINEAR mappings */
	spinlock_t		i_mmap_lock;	/* protect tree, count, list */
	unsigned int		truncate_count;	/* Cover race condition with truncate */
	unsigned long		nrpages;	/* number of total pages */
	pgoff_t			writeback_index;/* writeback starts here */
450
	const struct address_space_operations *a_ops;	/* methods */
L
Linus Torvalds 已提交
451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466
	unsigned long		flags;		/* error bits/gfp mask */
	struct backing_dev_info *backing_dev_info; /* device readahead, etc */
	spinlock_t		private_lock;	/* for use by the address_space */
	struct list_head	private_list;	/* ditto */
	struct address_space	*assoc_mapping;	/* ditto */
} __attribute__((aligned(sizeof(long))));
	/*
	 * On most architectures that alignment is already the case; but
	 * must be enforced here for CRIS, to let the least signficant bit
	 * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON.
	 */

struct block_device {
	dev_t			bd_dev;  /* not a kdev_t - it's a search key */
	struct inode *		bd_inode;	/* will die */
	int			bd_openers;
467
	struct mutex		bd_mutex;	/* open/close mutex */
468
	struct semaphore	bd_mount_sem;
L
Linus Torvalds 已提交
469 470 471
	struct list_head	bd_inodes;
	void *			bd_holder;
	int			bd_holders;
472 473 474
#ifdef CONFIG_SYSFS
	struct list_head	bd_holder_list;
#endif
L
Linus Torvalds 已提交
475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543
	struct block_device *	bd_contains;
	unsigned		bd_block_size;
	struct hd_struct *	bd_part;
	/* number of times partitions within this device have been opened. */
	unsigned		bd_part_count;
	int			bd_invalidated;
	struct gendisk *	bd_disk;
	struct list_head	bd_list;
	struct backing_dev_info *bd_inode_backing_dev_info;
	/*
	 * Private data.  You must have bd_claim'ed the block_device
	 * to use this.  NOTE:  bd_claim allows an owner to claim
	 * the same device multiple times, the owner must take special
	 * care to not mess up bd_private for that case.
	 */
	unsigned long		bd_private;
};

/*
 * Radix-tree tags, for tagging dirty and writeback pages within the pagecache
 * radix trees
 */
#define PAGECACHE_TAG_DIRTY	0
#define PAGECACHE_TAG_WRITEBACK	1

int mapping_tagged(struct address_space *mapping, int tag);

/*
 * Might pages of this file be mapped into userspace?
 */
static inline int mapping_mapped(struct address_space *mapping)
{
	return	!prio_tree_empty(&mapping->i_mmap) ||
		!list_empty(&mapping->i_mmap_nonlinear);
}

/*
 * Might pages of this file have been modified in userspace?
 * Note that i_mmap_writable counts all VM_SHARED vmas: do_mmap_pgoff
 * marks vma as VM_SHARED if it is shared, and the file was opened for
 * writing i.e. vma may be mprotected writable even if now readonly.
 */
static inline int mapping_writably_mapped(struct address_space *mapping)
{
	return mapping->i_mmap_writable != 0;
}

/*
 * Use sequence counter to get consistent i_size on 32-bit processors.
 */
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
#include <linux/seqlock.h>
#define __NEED_I_SIZE_ORDERED
#define i_size_ordered_init(inode) seqcount_init(&inode->i_size_seqcount)
#else
#define i_size_ordered_init(inode) do { } while (0)
#endif

struct inode {
	struct hlist_node	i_hash;
	struct list_head	i_list;
	struct list_head	i_sb_list;
	struct list_head	i_dentry;
	unsigned long		i_ino;
	atomic_t		i_count;
	unsigned int		i_nlink;
	uid_t			i_uid;
	gid_t			i_gid;
	dev_t			i_rdev;
544
	unsigned long		i_version;
L
Linus Torvalds 已提交
545
	loff_t			i_size;
546 547 548
#ifdef __NEED_I_SIZE_ORDERED
	seqcount_t		i_size_seqcount;
#endif
L
Linus Torvalds 已提交
549 550 551 552
	struct timespec		i_atime;
	struct timespec		i_mtime;
	struct timespec		i_ctime;
	unsigned int		i_blkbits;
T
Takashi Sato 已提交
553
	blkcnt_t		i_blocks;
L
Linus Torvalds 已提交
554
	unsigned short          i_bytes;
555
	umode_t			i_mode;
L
Linus Torvalds 已提交
556
	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
557
	struct mutex		i_mutex;
L
Linus Torvalds 已提交
558
	struct rw_semaphore	i_alloc_sem;
559
	const struct inode_operations	*i_op;
560
	const struct file_operations	*i_fop;	/* former ->i_op->default_file_ops */
L
Linus Torvalds 已提交
561 562 563 564 565 566 567 568
	struct super_block	*i_sb;
	struct file_lock	*i_flock;
	struct address_space	*i_mapping;
	struct address_space	i_data;
#ifdef CONFIG_QUOTA
	struct dquot		*i_dquot[MAXQUOTAS];
#endif
	struct list_head	i_devices;
569 570
	union {
		struct pipe_inode_info	*i_pipe;
571
		struct block_device	*i_bdev;
572
		struct cdev		*i_cdev;
573
	};
L
Linus Torvalds 已提交
574 575 576 577 578 579 580 581 582
	int			i_cindex;

	__u32			i_generation;

#ifdef CONFIG_DNOTIFY
	unsigned long		i_dnotify_mask; /* Directory notify events */
	struct dnotify_struct	*i_dnotify; /* for directory notifications */
#endif

R
Robert Love 已提交
583 584
#ifdef CONFIG_INOTIFY
	struct list_head	inotify_watches; /* watches on this inode */
I
Ingo Molnar 已提交
585
	struct mutex		inotify_mutex;	/* protects the watches list */
R
Robert Love 已提交
586 587
#endif

L
Linus Torvalds 已提交
588 589 590 591 592 593
	unsigned long		i_state;
	unsigned long		dirtied_when;	/* jiffies of first dirtying */

	unsigned int		i_flags;

	atomic_t		i_writecount;
594
#ifdef CONFIG_SECURITY
L
Linus Torvalds 已提交
595
	void			*i_security;
596
#endif
597
	void			*i_private; /* fs or device private pointer */
L
Linus Torvalds 已提交
598 599
};

I
Ingo Molnar 已提交
600 601 602 603 604 605 606 607 608
/*
 * inode->i_mutex nesting subclasses for the lock validator:
 *
 * 0: the object of the current VFS operation
 * 1: parent
 * 2: child/target
 * 3: quota file
 *
 * The locking order between these classes is
I
Ingo Molnar 已提交
609
 * parent -> child -> normal -> xattr -> quota
I
Ingo Molnar 已提交
610 611 612 613 614 615
 */
enum inode_i_mutex_lock_class
{
	I_MUTEX_NORMAL,
	I_MUTEX_PARENT,
	I_MUTEX_CHILD,
I
Ingo Molnar 已提交
616
	I_MUTEX_XATTR,
I
Ingo Molnar 已提交
617 618 619
	I_MUTEX_QUOTA
};

620 621 622
extern void inode_double_lock(struct inode *inode1, struct inode *inode2);
extern void inode_double_unlock(struct inode *inode1, struct inode *inode2);

L
Linus Torvalds 已提交
623 624 625 626 627 628 629 630 631 632
/*
 * NOTE: in a 32bit arch with a preemptable kernel and
 * an UP compile the i_size_read/write must be atomic
 * with respect to the local cpu (unlike with preempt disabled),
 * but they don't need to be atomic with respect to other cpus like in
 * true SMP (so they need either to either locally disable irq around
 * the read or for example on x86 they can be still implemented as a
 * cmpxchg8b without the need of the lock prefix). For SMP compiles
 * and 64bit archs it makes no difference if preempt is enabled or not.
 */
J
Jan Engelhardt 已提交
633
static inline loff_t i_size_read(const struct inode *inode)
L
Linus Torvalds 已提交
634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655
{
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
	loff_t i_size;
	unsigned int seq;

	do {
		seq = read_seqcount_begin(&inode->i_size_seqcount);
		i_size = inode->i_size;
	} while (read_seqcount_retry(&inode->i_size_seqcount, seq));
	return i_size;
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
	loff_t i_size;

	preempt_disable();
	i_size = inode->i_size;
	preempt_enable();
	return i_size;
#else
	return inode->i_size;
#endif
}

656 657 658 659 660
/*
 * NOTE: unlike i_size_read(), i_size_write() does need locking around it
 * (normally i_mutex), otherwise on 32bit/SMP an update of i_size_seqcount
 * can be lost, resulting in subsequent i_size_read() calls spinning forever.
 */
L
Linus Torvalds 已提交
661 662 663 664 665 666 667 668 669 670 671 672 673 674 675
static inline void i_size_write(struct inode *inode, loff_t i_size)
{
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
	write_seqcount_begin(&inode->i_size_seqcount);
	inode->i_size = i_size;
	write_seqcount_end(&inode->i_size_seqcount);
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
	preempt_disable();
	inode->i_size = i_size;
	preempt_enable();
#else
	inode->i_size = i_size;
#endif
}

J
Jan Engelhardt 已提交
676
static inline unsigned iminor(const struct inode *inode)
L
Linus Torvalds 已提交
677 678 679 680
{
	return MINOR(inode->i_rdev);
}

J
Jan Engelhardt 已提交
681
static inline unsigned imajor(const struct inode *inode)
L
Linus Torvalds 已提交
682 683 684 685 686 687 688 689
{
	return MAJOR(inode->i_rdev);
}

extern struct block_device *I_BDEV(struct inode *inode);

struct fown_struct {
	rwlock_t lock;          /* protects pid, uid, euid fields */
690 691
	struct pid *pid;	/* pid or -pgrp where SIGIO should be sent */
	enum pid_type pid_type;	/* Kind of process group SIGIO should be sent to */
L
Linus Torvalds 已提交
692 693 694 695 696 697 698 699 700 701 702 703
	uid_t uid, euid;	/* uid/euid of process setting the owner */
	int signum;		/* posix.1b rt signal to be delivered on IO */
};

/*
 * Track a single file's readahead state
 */
struct file_ra_state {
	unsigned long start;		/* Current window */
	unsigned long size;
	unsigned long flags;		/* ra flags RA_FLAG_xxx*/
	unsigned long cache_hit;	/* cache hit count*/
J
Jan Kara 已提交
704
	unsigned long prev_index;	/* Cache last read() position */
L
Linus Torvalds 已提交
705 706 707 708 709
	unsigned long ahead_start;	/* Ahead window */
	unsigned long ahead_size;
	unsigned long ra_pages;		/* Maximum readahead window */
	unsigned long mmap_hit;		/* Cache hit stat for mmap accesses */
	unsigned long mmap_miss;	/* Cache miss stat for mmap accesses */
J
Jan Kara 已提交
710
	unsigned int prev_offset;	/* Offset where last read() ended in a page */
L
Linus Torvalds 已提交
711 712 713 714 715
};
#define RA_FLAG_MISS 0x01	/* a cache miss occured against this file */
#define RA_FLAG_INCACHE 0x02	/* file is already in cache */

struct file {
E
Eric Dumazet 已提交
716 717 718 719 720 721 722 723
	/*
	 * fu_list becomes invalid after file_free is called and queued via
	 * fu_rcuhead for RCU freeing
	 */
	union {
		struct list_head	fu_list;
		struct rcu_head 	fu_rcuhead;
	} f_u;
724 725 726
	struct path		f_path;
#define f_dentry	f_path.dentry
#define f_vfsmnt	f_path.mnt
727
	const struct file_operations	*f_op;
L
Linus Torvalds 已提交
728 729 730 731 732 733 734 735 736
	atomic_t		f_count;
	unsigned int 		f_flags;
	mode_t			f_mode;
	loff_t			f_pos;
	struct fown_struct	f_owner;
	unsigned int		f_uid, f_gid;
	struct file_ra_state	f_ra;

	unsigned long		f_version;
737
#ifdef CONFIG_SECURITY
L
Linus Torvalds 已提交
738
	void			*f_security;
739
#endif
L
Linus Torvalds 已提交
740 741 742 743 744 745 746 747 748 749 750 751 752 753
	/* needed for tty driver, and maybe others */
	void			*private_data;

#ifdef CONFIG_EPOLL
	/* Used by fs/eventpoll.c to link all the hooks to this file */
	struct list_head	f_ep_links;
	spinlock_t		f_ep_lock;
#endif /* #ifdef CONFIG_EPOLL */
	struct address_space	*f_mapping;
};
extern spinlock_t files_lock;
#define file_list_lock() spin_lock(&files_lock);
#define file_list_unlock() spin_unlock(&files_lock);

754
#define get_file(x)	atomic_inc(&(x)->f_count)
L
Linus Torvalds 已提交
755 756 757 758 759 760 761 762 763 764 765 766 767 768 769
#define file_count(x)	atomic_read(&(x)->f_count)

#define	MAX_NON_LFS	((1UL<<31) - 1)

/* Page cache limit. The filesystems should put that into their s_maxbytes 
   limits, otherwise bad things can happen in VM. */ 
#if BITS_PER_LONG==32
#define MAX_LFS_FILESIZE	(((u64)PAGE_CACHE_SIZE << (BITS_PER_LONG-1))-1) 
#elif BITS_PER_LONG==64
#define MAX_LFS_FILESIZE 	0x7fffffffffffffffUL
#endif

#define FL_POSIX	1
#define FL_FLOCK	2
#define FL_ACCESS	8	/* not trying to lock, just looking */
770
#define FL_EXISTS	16	/* when unlocking, test for existence */
L
Linus Torvalds 已提交
771
#define FL_LEASE	32	/* lease held on this file */
772
#define FL_CLOSE	64	/* unlock on close */
L
Linus Torvalds 已提交
773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793
#define FL_SLEEP	128	/* A blocking lock */

/*
 * The POSIX file lock owner is determined by
 * the "struct files_struct" in the thread group
 * (or NULL for no owner - BSD locks).
 *
 * Lockd stuffs a "host" pointer into this.
 */
typedef struct files_struct *fl_owner_t;

struct file_lock_operations {
	void (*fl_insert)(struct file_lock *);	/* lock insertion callback */
	void (*fl_remove)(struct file_lock *);	/* lock removal callback */
	void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
	void (*fl_release_private)(struct file_lock *);
};

struct lock_manager_operations {
	int (*fl_compare_owner)(struct file_lock *, struct file_lock *);
	void (*fl_notify)(struct file_lock *);	/* unblock callback */
794
	int (*fl_grant)(struct file_lock *, struct file_lock *, int);
L
Linus Torvalds 已提交
795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824
	void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
	void (*fl_release_private)(struct file_lock *);
	void (*fl_break)(struct file_lock *);
	int (*fl_mylease)(struct file_lock *, struct file_lock *);
	int (*fl_change)(struct file_lock **, int);
};

/* that will die - we need it for nfs_lock_info */
#include <linux/nfs_fs_i.h>

struct file_lock {
	struct file_lock *fl_next;	/* singly linked list for this inode  */
	struct list_head fl_link;	/* doubly linked list of all locks */
	struct list_head fl_block;	/* circular list of blocked processes */
	fl_owner_t fl_owner;
	unsigned int fl_pid;
	wait_queue_head_t fl_wait;
	struct file *fl_file;
	unsigned char fl_flags;
	unsigned char fl_type;
	loff_t fl_start;
	loff_t fl_end;

	struct fasync_struct *	fl_fasync; /* for lease break notifications */
	unsigned long fl_break_time;	/* for nonblocking lease breaks */

	struct file_lock_operations *fl_ops;	/* Callbacks for filesystems */
	struct lock_manager_operations *fl_lmops;	/* Callbacks for lockmanagers */
	union {
		struct nfs_lock_info	nfs_fl;
825
		struct nfs4_lock_info	nfs4_fl;
D
David Howells 已提交
826 827 828 829
		struct {
			struct list_head link;	/* link in AFS vnode's pending_locks list */
			int state;		/* state of grant or error if -ve */
		} afs;
L
Linus Torvalds 已提交
830 831 832 833 834 835 836 837 838 839 840 841 842
	} fl_u;
};

/* The following constant reflects the upper bound of the file/locking space */
#ifndef OFFSET_MAX
#define INT_LIMIT(x)	(~((x)1 << (sizeof(x)*8 - 1)))
#define OFFSET_MAX	INT_LIMIT(loff_t)
#define OFFT_OFFSET_MAX	INT_LIMIT(off_t)
#endif

#include <linux/fcntl.h>

extern int fcntl_getlk(struct file *, struct flock __user *);
843 844
extern int fcntl_setlk(unsigned int, struct file *, unsigned int,
			struct flock __user *);
L
Linus Torvalds 已提交
845 846 847

#if BITS_PER_LONG == 32
extern int fcntl_getlk64(struct file *, struct flock64 __user *);
848 849
extern int fcntl_setlk64(unsigned int, struct file *, unsigned int,
			struct flock64 __user *);
L
Linus Torvalds 已提交
850 851 852 853 854 855
#endif

extern void send_sigio(struct fown_struct *fown, int fd, int band);
extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg);
extern int fcntl_getlease(struct file *filp);

A
Andrew Morton 已提交
856
/* fs/sync.c */
857 858
extern int do_sync_mapping_range(struct address_space *mapping, loff_t offset,
			loff_t endbyte, unsigned int flags);
A
Andrew Morton 已提交
859

L
Linus Torvalds 已提交
860 861 862 863 864
/* fs/locks.c */
extern void locks_init_lock(struct file_lock *);
extern void locks_copy_lock(struct file_lock *, struct file_lock *);
extern void locks_remove_posix(struct file *, fl_owner_t);
extern void locks_remove_flock(struct file *);
865
extern void posix_test_lock(struct file *, struct file_lock *);
866
extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *);
L
Linus Torvalds 已提交
867
extern int posix_lock_file_wait(struct file *, struct file_lock *);
J
J. Bruce Fields 已提交
868
extern int posix_unblock_lock(struct file *, struct file_lock *);
869
extern int vfs_test_lock(struct file *, struct file_lock *);
870
extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *);
M
Marc Eshel 已提交
871
extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
L
Linus Torvalds 已提交
872 873 874 875
extern int flock_lock_file_wait(struct file *filp, struct file_lock *fl);
extern int __break_lease(struct inode *inode, unsigned int flags);
extern void lease_get_mtime(struct inode *, struct timespec *time);
extern int setlease(struct file *, long, struct file_lock **);
876
extern int vfs_setlease(struct file *, long, struct file_lock **);
L
Linus Torvalds 已提交
877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896
extern int lease_modify(struct file_lock **, int);
extern int lock_may_read(struct inode *, loff_t start, unsigned long count);
extern int lock_may_write(struct inode *, loff_t start, unsigned long count);

struct fasync_struct {
	int	magic;
	int	fa_fd;
	struct	fasync_struct	*fa_next; /* singly linked list */
	struct	file 		*fa_file;
};

#define FASYNC_MAGIC 0x4601

/* SMP safe fasync helpers: */
extern int fasync_helper(int, struct file *, int, struct fasync_struct **);
/* can be called from interrupts */
extern void kill_fasync(struct fasync_struct **, int, int);
/* only for net: no internal synchronization */
extern void __kill_fasync(struct fasync_struct *, int, int);

897
extern int __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
L
Linus Torvalds 已提交
898 899
extern int f_setown(struct file *filp, unsigned long arg, int force);
extern void f_delown(struct file *filp);
900
extern pid_t f_getown(struct file *filp);
L
Linus Torvalds 已提交
901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923
extern int send_sigurg(struct fown_struct *fown);

/*
 *	Umount options
 */

#define MNT_FORCE	0x00000001	/* Attempt to forcibily umount */
#define MNT_DETACH	0x00000002	/* Just detach from the tree */
#define MNT_EXPIRE	0x00000004	/* Mark for expiry */

extern struct list_head super_blocks;
extern spinlock_t sb_lock;

#define sb_entry(list)	list_entry((list), struct super_block, s_list)
#define S_BIAS (1<<30)
struct super_block {
	struct list_head	s_list;		/* Keep this first */
	dev_t			s_dev;		/* search index; _not_ kdev_t */
	unsigned long		s_blocksize;
	unsigned char		s_blocksize_bits;
	unsigned char		s_dirt;
	unsigned long long	s_maxbytes;	/* Max file size */
	struct file_system_type	*s_type;
924
	const struct super_operations	*s_op;
L
Linus Torvalds 已提交
925 926 927 928 929 930 931
	struct dquot_operations	*dq_op;
 	struct quotactl_ops	*s_qcop;
	struct export_operations *s_export_op;
	unsigned long		s_flags;
	unsigned long		s_magic;
	struct dentry		*s_root;
	struct rw_semaphore	s_umount;
932
	struct mutex		s_lock;
L
Linus Torvalds 已提交
933 934 935 936
	int			s_count;
	int			s_syncing;
	int			s_need_sync_fs;
	atomic_t		s_active;
937
#ifdef CONFIG_SECURITY
L
Linus Torvalds 已提交
938
	void                    *s_security;
939
#endif
L
Linus Torvalds 已提交
940 941 942 943 944 945 946 947 948
	struct xattr_handler	**s_xattr;

	struct list_head	s_inodes;	/* all inodes */
	struct list_head	s_dirty;	/* dirty inodes */
	struct list_head	s_io;		/* parked for writeback */
	struct hlist_head	s_anon;		/* anonymous dentries for (nfs) exporting */
	struct list_head	s_files;

	struct block_device	*s_bdev;
949
	struct mtd_info		*s_mtd;
L
Linus Torvalds 已提交
950 951 952 953 954 955 956 957 958 959 960 961 962 963
	struct list_head	s_instances;
	struct quota_info	s_dquot;	/* Diskquota specific options */

	int			s_frozen;
	wait_queue_head_t	s_wait_unfrozen;

	char s_id[32];				/* Informational name */

	void 			*s_fs_info;	/* Filesystem private info */

	/*
	 * The next field is for VFS *only*. No filesystems have any business
	 * even looking at it. You had been warned.
	 */
964
	struct mutex s_vfs_rename_mutex;	/* Kludge */
L
Linus Torvalds 已提交
965

966
	/* Granularity of c/m/atime in ns.
L
Linus Torvalds 已提交
967 968
	   Cannot be worse than a second */
	u32		   s_time_gran;
M
Miklos Szeredi 已提交
969 970 971 972 973 974

	/*
	 * Filesystem subtype.  If non-empty the filesystem type field
	 * in /proc/mounts will be "type.subtype"
	 */
	char *s_subtype;
L
Linus Torvalds 已提交
975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990
};

extern struct timespec current_fs_time(struct super_block *sb);

/*
 * Snapshotting support.
 */
enum {
	SB_UNFROZEN = 0,
	SB_FREEZE_WRITE	= 1,
	SB_FREEZE_TRANS = 2,
};

#define vfs_check_frozen(sb, level) \
	wait_event((sb)->s_wait_unfrozen, ((sb)->s_frozen < (level)))

991 992 993
#define get_fs_excl() atomic_inc(&current->fs_excl)
#define put_fs_excl() atomic_dec(&current->fs_excl)
#define has_fs_excl() atomic_read(&current->fs_excl)
994

995 996 997
#define is_owner_or_cap(inode)	\
	((current->fsuid == (inode)->i_uid) || capable(CAP_FOWNER))

998 999 1000
/* not quite ready to be deprecated, but... */
extern void lock_super(struct super_block *);
extern void unlock_super(struct super_block *);
L
Linus Torvalds 已提交
1001 1002 1003 1004

/*
 * VFS helper functions..
 */
1005
extern int vfs_permission(struct nameidata *, int);
L
Linus Torvalds 已提交
1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019
extern int vfs_create(struct inode *, struct dentry *, int, struct nameidata *);
extern int vfs_mkdir(struct inode *, struct dentry *, int);
extern int vfs_mknod(struct inode *, struct dentry *, int, dev_t);
extern int vfs_symlink(struct inode *, struct dentry *, const char *, int);
extern int vfs_link(struct dentry *, struct inode *, struct dentry *);
extern int vfs_rmdir(struct inode *, struct dentry *);
extern int vfs_unlink(struct inode *, struct dentry *);
extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *);

/*
 * VFS dentry helper functions.
 */
extern void dentry_unhash(struct dentry *dentry);

1020 1021 1022 1023 1024
/*
 * VFS file helper functions.
 */
extern int file_permission(struct file *, int);

L
Linus Torvalds 已提交
1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051
/*
 * File types
 *
 * NOTE! These match bits 12..15 of stat.st_mode
 * (ie "(i_mode >> 12) & 15").
 */
#define DT_UNKNOWN	0
#define DT_FIFO		1
#define DT_CHR		2
#define DT_DIR		4
#define DT_BLK		6
#define DT_REG		8
#define DT_LNK		10
#define DT_SOCK		12
#define DT_WHT		14

#define OSYNC_METADATA	(1<<0)
#define OSYNC_DATA	(1<<1)
#define OSYNC_INODE	(1<<2)
int generic_osync_inode(struct inode *, struct address_space *, int);

/*
 * This is the "filldir" function type, used by readdir() to let
 * the kernel specify what kind of dirent layout it wants to have.
 * This allows the kernel to read directories into kernel space or
 * to have different dirent layouts depending on the binary type.
 */
1052
typedef int (*filldir_t)(void *, const char *, int, loff_t, u64, unsigned);
L
Linus Torvalds 已提交
1053 1054 1055 1056 1057

struct block_device_operations {
	int (*open) (struct inode *, struct file *);
	int (*release) (struct inode *, struct file *);
	int (*ioctl) (struct inode *, struct file *, unsigned, unsigned long);
1058
	long (*unlocked_ioctl) (struct file *, unsigned, unsigned long);
L
Linus Torvalds 已提交
1059
	long (*compat_ioctl) (struct file *, unsigned, unsigned long);
1060
	int (*direct_access) (struct block_device *, sector_t, unsigned long *);
L
Linus Torvalds 已提交
1061 1062
	int (*media_changed) (struct gendisk *);
	int (*revalidate_disk) (struct gendisk *);
1063
	int (*getgeo)(struct block_device *, struct hd_geometry *);
L
Linus Torvalds 已提交
1064 1065 1066 1067
	struct module *owner;
};

/*
J
Jens Axboe 已提交
1068
 * "descriptor" for what we're up to with a read.
L
Linus Torvalds 已提交
1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103
 * This allows us to use the same read code yet
 * have multiple different users of the data that
 * we read from a file.
 *
 * The simplest case just copies the data to user
 * mode.
 */
typedef struct {
	size_t written;
	size_t count;
	union {
		char __user * buf;
		void *data;
	} arg;
	int error;
} read_descriptor_t;

typedef int (*read_actor_t)(read_descriptor_t *, struct page *, unsigned long, unsigned long);

/* These macros are for out of kernel modules to test that
 * the kernel supports the unlocked_ioctl and compat_ioctl
 * fields in struct file_operations. */
#define HAVE_COMPAT_IOCTL 1
#define HAVE_UNLOCKED_IOCTL 1

/*
 * NOTE:
 * read, write, poll, fsync, readv, writev, unlocked_ioctl and compat_ioctl
 * can be called without the big kernel lock held in all filesystems.
 */
struct file_operations {
	struct module *owner;
	loff_t (*llseek) (struct file *, loff_t, int);
	ssize_t (*read) (struct file *, char __user *, size_t, loff_t *);
	ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
1104 1105
	ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
	ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
L
Linus Torvalds 已提交
1106 1107 1108 1109 1110 1111 1112
	int (*readdir) (struct file *, void *, filldir_t);
	unsigned int (*poll) (struct file *, struct poll_table_struct *);
	int (*ioctl) (struct inode *, struct file *, unsigned int, unsigned long);
	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
	int (*mmap) (struct file *, struct vm_area_struct *);
	int (*open) (struct inode *, struct file *);
1113
	int (*flush) (struct file *, fl_owner_t id);
L
Linus Torvalds 已提交
1114 1115 1116 1117 1118 1119 1120 1121 1122 1123
	int (*release) (struct inode *, struct file *);
	int (*fsync) (struct file *, struct dentry *, int datasync);
	int (*aio_fsync) (struct kiocb *, int datasync);
	int (*fasync) (int, struct file *, int);
	int (*lock) (struct file *, int, struct file_lock *);
	ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int);
	unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
	int (*check_flags)(int);
	int (*dir_notify)(struct file *filp, unsigned long arg);
	int (*flock) (struct file *, int, struct file_lock *);
1124 1125
	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int);
	ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int);
1126
	int (*setlease)(struct file *, long, struct file_lock **);
L
Linus Torvalds 已提交
1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140
};

struct inode_operations {
	int (*create) (struct inode *,struct dentry *,int, struct nameidata *);
	struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameidata *);
	int (*link) (struct dentry *,struct inode *,struct dentry *);
	int (*unlink) (struct inode *,struct dentry *);
	int (*symlink) (struct inode *,struct dentry *,const char *);
	int (*mkdir) (struct inode *,struct dentry *,int);
	int (*rmdir) (struct inode *,struct dentry *);
	int (*mknod) (struct inode *,struct dentry *,int,dev_t);
	int (*rename) (struct inode *, struct dentry *,
			struct inode *, struct dentry *);
	int (*readlink) (struct dentry *, char __user *,int);
1141 1142
	void * (*follow_link) (struct dentry *, struct nameidata *);
	void (*put_link) (struct dentry *, struct nameidata *, void *);
L
Linus Torvalds 已提交
1143 1144 1145 1146 1147 1148 1149 1150
	void (*truncate) (struct inode *);
	int (*permission) (struct inode *, int, struct nameidata *);
	int (*setattr) (struct dentry *, struct iattr *);
	int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *);
	int (*setxattr) (struct dentry *, const char *,const void *,size_t,int);
	ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t);
	ssize_t (*listxattr) (struct dentry *, char *, size_t);
	int (*removexattr) (struct dentry *, const char *);
1151
	void (*truncate_range)(struct inode *, loff_t, loff_t);
1152 1153
	long (*fallocate)(struct inode *inode, int mode, loff_t offset,
			  loff_t len);
L
Linus Torvalds 已提交
1154 1155 1156 1157
};

struct seq_file;

B
Badari Pulavarty 已提交
1158 1159 1160 1161 1162
ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
				unsigned long nr_segs, unsigned long fast_segs,
				struct iovec *fast_pointer,
				struct iovec **ret_pointer);

L
Linus Torvalds 已提交
1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189
extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
extern ssize_t vfs_readv(struct file *, const struct iovec __user *,
		unsigned long, loff_t *);
extern ssize_t vfs_writev(struct file *, const struct iovec __user *,
		unsigned long, loff_t *);

/*
 * NOTE: write_inode, delete_inode, clear_inode, put_inode can be called
 * without the big kernel lock held in all filesystems.
 */
struct super_operations {
   	struct inode *(*alloc_inode)(struct super_block *sb);
	void (*destroy_inode)(struct inode *);

	void (*read_inode) (struct inode *);
  
   	void (*dirty_inode) (struct inode *);
	int (*write_inode) (struct inode *, int);
	void (*put_inode) (struct inode *);
	void (*drop_inode) (struct inode *);
	void (*delete_inode) (struct inode *);
	void (*put_super) (struct super_block *);
	void (*write_super) (struct super_block *);
	int (*sync_fs)(struct super_block *sb, int wait);
	void (*write_super_lockfs) (struct super_block *);
	void (*unlockfs) (struct super_block *);
1190
	int (*statfs) (struct dentry *, struct kstatfs *);
L
Linus Torvalds 已提交
1191 1192
	int (*remount_fs) (struct super_block *, int *, char *);
	void (*clear_inode) (struct inode *);
1193
	void (*umount_begin) (struct vfsmount *, int);
L
Linus Torvalds 已提交
1194 1195

	int (*show_options)(struct seq_file *, struct vfsmount *);
1196
	int (*show_stats)(struct seq_file *, struct vfsmount *);
1197
#ifdef CONFIG_QUOTA
L
Linus Torvalds 已提交
1198 1199
	ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t);
	ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
1200
#endif
L
Linus Torvalds 已提交
1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211
};

/* Inode state bits.  Protected by inode_lock. */
#define I_DIRTY_SYNC		1 /* Not dirty enough for O_DATASYNC */
#define I_DIRTY_DATASYNC	2 /* Data-related inode changes pending */
#define I_DIRTY_PAGES		4 /* Data-related inode changes pending */
#define __I_LOCK		3
#define I_LOCK			(1 << __I_LOCK)
#define I_FREEING		16
#define I_CLEAR			32
#define I_NEW			64
1212
#define I_WILL_FREE		128
L
Linus Torvalds 已提交
1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226

#define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES)

extern void __mark_inode_dirty(struct inode *, int);
static inline void mark_inode_dirty(struct inode *inode)
{
	__mark_inode_dirty(inode, I_DIRTY);
}

static inline void mark_inode_dirty_sync(struct inode *inode)
{
	__mark_inode_dirty(inode, I_DIRTY_SYNC);
}

D
Dave Hansen 已提交
1227 1228 1229 1230 1231 1232 1233 1234
/**
 * inc_nlink - directly increment an inode's link count
 * @inode: inode
 *
 * This is a low-level filesystem helper to replace any
 * direct filesystem manipulation of i_nlink.  Currently,
 * it is only here for parity with dec_nlink().
 */
1235
static inline void inc_nlink(struct inode *inode)
1236 1237
{
	inode->i_nlink++;
1238 1239 1240 1241 1242
}

static inline void inode_inc_link_count(struct inode *inode)
{
	inc_nlink(inode);
1243 1244 1245
	mark_inode_dirty(inode);
}

D
Dave Hansen 已提交
1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256
/**
 * drop_nlink - directly drop an inode's link count
 * @inode: inode
 *
 * This is a low-level filesystem helper to replace any
 * direct filesystem manipulation of i_nlink.  In cases
 * where we are attempting to track writes to the
 * filesystem, a decrement to zero means an imminent
 * write when the file is truncated and actually unlinked
 * on the filesystem.
 */
1257
static inline void drop_nlink(struct inode *inode)
1258 1259
{
	inode->i_nlink--;
1260 1261
}

D
Dave Hansen 已提交
1262 1263 1264 1265 1266 1267 1268 1269
/**
 * clear_nlink - directly zero an inode's link count
 * @inode: inode
 *
 * This is a low-level filesystem helper to replace any
 * direct filesystem manipulation of i_nlink.  See
 * drop_nlink() for why we care about i_nlink hitting zero.
 */
1270 1271 1272 1273 1274
static inline void clear_nlink(struct inode *inode)
{
	inode->i_nlink = 0;
}

1275 1276 1277
static inline void inode_dec_link_count(struct inode *inode)
{
	drop_nlink(inode);
1278 1279 1280
	mark_inode_dirty(inode);
}

C
Christoph Hellwig 已提交
1281
extern void touch_atime(struct vfsmount *mnt, struct dentry *dentry);
L
Linus Torvalds 已提交
1282 1283 1284
static inline void file_accessed(struct file *file)
{
	if (!(file->f_flags & O_NOATIME))
1285
		touch_atime(file->f_path.mnt, file->f_path.dentry);
L
Linus Torvalds 已提交
1286 1287 1288 1289 1290 1291 1292
}

int sync_inode(struct inode *inode, struct writeback_control *wbc);

struct file_system_type {
	const char *name;
	int fs_flags;
1293 1294
	int (*get_sb) (struct file_system_type *, int,
		       const char *, void *, struct vfsmount *);
L
Linus Torvalds 已提交
1295 1296 1297 1298
	void (*kill_sb) (struct super_block *);
	struct module *owner;
	struct file_system_type * next;
	struct list_head fs_supers;
I
Ingo Molnar 已提交
1299
	struct lock_class_key s_lock_key;
1300
	struct lock_class_key s_umount_key;
L
Linus Torvalds 已提交
1301 1302
};

1303
extern int get_sb_bdev(struct file_system_type *fs_type,
L
Linus Torvalds 已提交
1304
	int flags, const char *dev_name, void *data,
1305 1306 1307
	int (*fill_super)(struct super_block *, void *, int),
	struct vfsmount *mnt);
extern int get_sb_single(struct file_system_type *fs_type,
L
Linus Torvalds 已提交
1308
	int flags, void *data,
1309 1310 1311
	int (*fill_super)(struct super_block *, void *, int),
	struct vfsmount *mnt);
extern int get_sb_nodev(struct file_system_type *fs_type,
L
Linus Torvalds 已提交
1312
	int flags, void *data,
1313 1314
	int (*fill_super)(struct super_block *, void *, int),
	struct vfsmount *mnt);
L
Linus Torvalds 已提交
1315 1316 1317 1318 1319 1320 1321 1322 1323 1324
void generic_shutdown_super(struct super_block *sb);
void kill_block_super(struct super_block *sb);
void kill_anon_super(struct super_block *sb);
void kill_litter_super(struct super_block *sb);
void deactivate_super(struct super_block *sb);
int set_anon_super(struct super_block *s, void *data);
struct super_block *sget(struct file_system_type *type,
			int (*test)(struct super_block *,void *),
			int (*set)(struct super_block *,void *),
			void *data);
1325
extern int get_sb_pseudo(struct file_system_type *, char *,
1326
	const struct super_operations *ops, unsigned long,
1327 1328
	struct vfsmount *mnt);
extern int simple_set_mnt(struct vfsmount *mnt, struct super_block *sb);
L
Linus Torvalds 已提交
1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343
int __put_super(struct super_block *sb);
int __put_super_and_need_restart(struct super_block *sb);
void unnamed_dev_init(void);

/* Alas, no aliases. Too much hassle with bringing module.h everywhere */
#define fops_get(fops) \
	(((fops) && try_module_get((fops)->owner) ? (fops) : NULL))
#define fops_put(fops) \
	do { if (fops) module_put((fops)->owner); } while(0)

extern int register_filesystem(struct file_system_type *);
extern int unregister_filesystem(struct file_system_type *);
extern struct vfsmount *kern_mount(struct file_system_type *);
extern int may_umount_tree(struct vfsmount *);
extern int may_umount(struct vfsmount *);
R
Ram Pai 已提交
1344
extern void umount_tree(struct vfsmount *, int, struct list_head *);
1345
extern void release_mounts(struct list_head *);
L
Linus Torvalds 已提交
1346
extern long do_mount(char *, char *, char *, unsigned long, void *);
1347 1348 1349
extern struct vfsmount *copy_tree(struct vfsmount *, struct dentry *, int);
extern void mnt_set_mountpoint(struct vfsmount *, struct dentry *,
				  struct vfsmount *);
L
Linus Torvalds 已提交
1350

1351
extern int vfs_statfs(struct dentry *, struct kstatfs *);
L
Linus Torvalds 已提交
1352

M
Miklos Szeredi 已提交
1353
/* /sys/fs */
1354
extern struct kset fs_subsys;
M
Miklos Szeredi 已提交
1355

L
Linus Torvalds 已提交
1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400
#define FLOCK_VERIFY_READ  1
#define FLOCK_VERIFY_WRITE 2

extern int locks_mandatory_locked(struct inode *);
extern int locks_mandatory_area(int, struct inode *, struct file *, loff_t, size_t);

/*
 * Candidates for mandatory locking have the setgid bit set
 * but no group execute bit -  an otherwise meaningless combination.
 */
#define MANDATORY_LOCK(inode) \
	(IS_MANDLOCK(inode) && ((inode)->i_mode & (S_ISGID | S_IXGRP)) == S_ISGID)

static inline int locks_verify_locked(struct inode *inode)
{
	if (MANDATORY_LOCK(inode))
		return locks_mandatory_locked(inode);
	return 0;
}

extern int rw_verify_area(int, struct file *, loff_t *, size_t);

static inline int locks_verify_truncate(struct inode *inode,
				    struct file *filp,
				    loff_t size)
{
	if (inode->i_flock && MANDATORY_LOCK(inode))
		return locks_mandatory_area(
			FLOCK_VERIFY_WRITE, inode, filp,
			size < inode->i_size ? size : inode->i_size,
			(size < inode->i_size ? inode->i_size - size
			 : size - inode->i_size)
		);
	return 0;
}

static inline int break_lease(struct inode *inode, unsigned int mode)
{
	if (inode->i_flock)
		return __break_lease(inode, mode);
	return 0;
}

/* fs/open.c */

1401 1402
extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs,
		       struct file *filp);
1403 1404
extern long do_sys_open(int fdf, const char __user *filename, int flags,
			int mode);
L
Linus Torvalds 已提交
1405 1406 1407 1408 1409 1410 1411 1412 1413
extern struct file *filp_open(const char *, int, int);
extern struct file * dentry_open(struct dentry *, struct vfsmount *, int);
extern int filp_close(struct file *, fl_owner_t id);
extern char * getname(const char __user *);

/* fs/dcache.c */
extern void __init vfs_caches_init_early(void);
extern void __init vfs_caches_init(unsigned long);

1414 1415
extern struct kmem_cache *names_cachep;

1416
#define __getname()	kmem_cache_alloc(names_cachep, GFP_KERNEL)
L
Linus Torvalds 已提交
1417 1418 1419 1420 1421 1422 1423
#define __putname(name) kmem_cache_free(names_cachep, (void *)(name))
#ifndef CONFIG_AUDITSYSCALL
#define putname(name)   __putname(name)
#else
extern void putname(const char *name);
#endif

1424
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
1425
extern int register_blkdev(unsigned int, const char *);
A
Akinobu Mita 已提交
1426
extern void unregister_blkdev(unsigned int, const char *);
L
Linus Torvalds 已提交
1427 1428 1429 1430 1431
extern struct block_device *bdget(dev_t);
extern void bd_set_size(struct block_device *, loff_t size);
extern void bd_forget(struct inode *inode);
extern void bdput(struct block_device *);
extern struct block_device *open_by_devnum(dev_t, unsigned);
1432
extern const struct address_space_operations def_blk_aops;
1433 1434 1435 1436
#else
static inline void bd_forget(struct inode *inode) {}
#endif
extern const struct file_operations def_blk_fops;
1437 1438 1439
extern const struct file_operations def_chr_fops;
extern const struct file_operations bad_sock_fops;
extern const struct file_operations def_fifo_fops;
1440
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
1441 1442
extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long);
extern int blkdev_ioctl(struct inode *, struct file *, unsigned, unsigned long);
1443 1444 1445
extern int blkdev_driver_ioctl(struct inode *inode, struct file *file,
			       struct gendisk *disk, unsigned cmd,
			       unsigned long arg);
L
Linus Torvalds 已提交
1446 1447 1448 1449 1450
extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long);
extern int blkdev_get(struct block_device *, mode_t, unsigned);
extern int blkdev_put(struct block_device *);
extern int bd_claim(struct block_device *, void *);
extern void bd_release(struct block_device *);
1451 1452 1453 1454 1455 1456 1457
#ifdef CONFIG_SYSFS
extern int bd_claim_by_disk(struct block_device *, void *, struct gendisk *);
extern void bd_release_from_disk(struct block_device *, struct gendisk *);
#else
#define bd_claim_by_disk(bdev, holder, disk)	bd_claim(bdev, holder)
#define bd_release_from_disk(bdev, disk)	bd_release(bdev)
#endif
1458
#endif
L
Linus Torvalds 已提交
1459 1460

/* fs/char_dev.c */
1461
#define CHRDEV_MAJOR_HASH_SIZE	255
L
Linus Torvalds 已提交
1462 1463 1464
extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *);
extern int register_chrdev_region(dev_t, unsigned, const char *);
extern int register_chrdev(unsigned int, const char *,
1465
			   const struct file_operations *);
A
Akinobu Mita 已提交
1466
extern void unregister_chrdev(unsigned int, const char *);
L
Linus Torvalds 已提交
1467 1468
extern void unregister_chrdev_region(dev_t, unsigned);
extern int chrdev_open(struct inode *, struct file *);
1469
extern void chrdev_show(struct seq_file *,off_t);
L
Linus Torvalds 已提交
1470 1471 1472

/* fs/block_dev.c */
#define BDEVNAME_SIZE	32	/* Largest string for a blockdev identifier */
1473 1474 1475

#ifdef CONFIG_BLOCK
#define BLKDEV_MAJOR_HASH_SIZE	255
L
Linus Torvalds 已提交
1476 1477 1478 1479 1480
extern const char *__bdevname(dev_t, char *buffer);
extern const char *bdevname(struct block_device *bdev, char *buffer);
extern struct block_device *lookup_bdev(const char *);
extern struct block_device *open_bdev_excl(const char *, int, void *);
extern void close_bdev_excl(struct block_device *);
1481
extern void blkdev_show(struct seq_file *,off_t);
1482 1483 1484
#else
#define BLKDEV_MAJOR_HASH_SIZE	0
#endif
L
Linus Torvalds 已提交
1485 1486 1487 1488 1489 1490 1491

extern void init_special_inode(struct inode *, umode_t, dev_t);

/* Invalid inode operations -- fs/bad_inode.c */
extern void make_bad_inode(struct inode *);
extern int is_bad_inode(struct inode *);

1492 1493 1494
extern const struct file_operations read_fifo_fops;
extern const struct file_operations write_fifo_fops;
extern const struct file_operations rdwr_fifo_fops;
L
Linus Torvalds 已提交
1495 1496 1497

extern int fs_may_remount_ro(struct super_block *);

1498
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509
/*
 * return READ, READA, or WRITE
 */
#define bio_rw(bio)		((bio)->bi_rw & (RW_MASK | RWA_MASK))

/*
 * return data direction, READ or WRITE
 */
#define bio_data_dir(bio)	((bio)->bi_rw & 1)

extern int check_disk_change(struct block_device *);
1510
extern int __invalidate_device(struct block_device *);
L
Linus Torvalds 已提交
1511
extern int invalidate_partition(struct gendisk *, int);
1512 1513
#endif
extern int invalidate_inodes(struct super_block *);
1514 1515 1516
unsigned long __invalidate_mapping_pages(struct address_space *mapping,
					pgoff_t start, pgoff_t end,
					bool be_atomic);
L
Linus Torvalds 已提交
1517 1518
unsigned long invalidate_mapping_pages(struct address_space *mapping,
					pgoff_t start, pgoff_t end);
1519

1520
static inline unsigned long __deprecated
1521 1522 1523 1524 1525
invalidate_inode_pages(struct address_space *mapping)
{
	return invalidate_mapping_pages(mapping, 0, ~0UL);
}

L
Linus Torvalds 已提交
1526 1527 1528 1529
static inline void invalidate_remote_inode(struct inode *inode)
{
	if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
	    S_ISLNK(inode->i_mode))
1530
		invalidate_mapping_pages(inode->i_mapping, 0, -1);
L
Linus Torvalds 已提交
1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541
}
extern int invalidate_inode_pages2(struct address_space *mapping);
extern int invalidate_inode_pages2_range(struct address_space *mapping,
					 pgoff_t start, pgoff_t end);
extern int write_inode_now(struct inode *, int);
extern int filemap_fdatawrite(struct address_space *);
extern int filemap_flush(struct address_space *);
extern int filemap_fdatawait(struct address_space *);
extern int filemap_write_and_wait(struct address_space *mapping);
extern int filemap_write_and_wait_range(struct address_space *mapping,
				        loff_t lstart, loff_t lend);
1542 1543 1544 1545 1546
extern int wait_on_page_writeback_range(struct address_space *mapping,
				pgoff_t start, pgoff_t end);
extern int __filemap_fdatawrite_range(struct address_space *mapping,
				loff_t start, loff_t end, int sync_mode);

1547
extern long do_fsync(struct file *file, int datasync);
L
Linus Torvalds 已提交
1548 1549
extern void sync_supers(void);
extern void sync_filesystems(int wait);
1550
extern void __fsync_super(struct super_block *sb);
L
Linus Torvalds 已提交
1551 1552 1553 1554
extern void emergency_sync(void);
extern void emergency_remount(void);
extern int do_remount_sb(struct super_block *sb, int flags,
			 void *data, int force);
1555
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
1556
extern sector_t bmap(struct inode *, sector_t);
1557
#endif
L
Linus Torvalds 已提交
1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571
extern int notify_change(struct dentry *, struct iattr *);
extern int permission(struct inode *, int, struct nameidata *);
extern int generic_permission(struct inode *, int,
		int (*check_acl)(struct inode *, int));

extern int get_write_access(struct inode *);
extern int deny_write_access(struct file *);
static inline void put_write_access(struct inode * inode)
{
	atomic_dec(&inode->i_writecount);
}
static inline void allow_write_access(struct file *file)
{
	if (file)
1572
		atomic_inc(&file->f_path.dentry->d_inode->i_writecount);
L
Linus Torvalds 已提交
1573 1574
}
extern int do_pipe(int *);
A
Andi Kleen 已提交
1575 1576 1577
extern struct file *create_read_pipe(struct file *f);
extern struct file *create_write_pipe(void);
extern void free_write_pipe(struct file *);
L
Linus Torvalds 已提交
1578

1579
extern int open_namei(int dfd, const char *, int, int, struct nameidata *);
L
Linus Torvalds 已提交
1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601
extern int may_open(struct nameidata *, int, int);

extern int kernel_read(struct file *, unsigned long, char *, unsigned long);
extern struct file * open_exec(const char *);
 
/* fs/dcache.c -- generic fs support functions */
extern int is_subdir(struct dentry *, struct dentry *);
extern ino_t find_inode_number(struct dentry *, struct qstr *);

#include <linux/err.h>

/* needed for stackable file system support */
extern loff_t default_llseek(struct file *file, loff_t offset, int origin);

extern loff_t vfs_llseek(struct file *file, loff_t offset, int origin);

extern void inode_init_once(struct inode *);
extern void iput(struct inode *);
extern struct inode * igrab(struct inode *);
extern ino_t iunique(struct super_block *, ino_t);
extern int inode_needs_sync(struct inode *inode);
extern void generic_delete_inode(struct inode *inode);
1602
extern void generic_drop_inode(struct inode *inode);
L
Linus Torvalds 已提交
1603

1604 1605 1606
extern struct inode *ilookup5_nowait(struct super_block *sb,
		unsigned long hashval, int (*test)(struct inode *, void *),
		void *data);
L
Linus Torvalds 已提交
1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630
extern struct inode *ilookup5(struct super_block *sb, unsigned long hashval,
		int (*test)(struct inode *, void *), void *data);
extern struct inode *ilookup(struct super_block *sb, unsigned long ino);

extern struct inode * iget5_locked(struct super_block *, unsigned long, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *);
extern struct inode * iget_locked(struct super_block *, unsigned long);
extern void unlock_new_inode(struct inode *);

static inline struct inode *iget(struct super_block *sb, unsigned long ino)
{
	struct inode *inode = iget_locked(sb, ino);
	
	if (inode && (inode->i_state & I_NEW)) {
		sb->s_op->read_inode(inode);
		unlock_new_inode(inode);
	}

	return inode;
}

extern void __iget(struct inode * inode);
extern void clear_inode(struct inode *);
extern void destroy_inode(struct inode *);
extern struct inode *new_inode(struct super_block *);
1631 1632
extern int __remove_suid(struct dentry *, int);
extern int should_remove_suid(struct dentry *);
L
Linus Torvalds 已提交
1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643
extern int remove_suid(struct dentry *);

extern void __insert_inode_hash(struct inode *, unsigned long hashval);
extern void remove_inode_hash(struct inode *);
static inline void insert_inode_hash(struct inode *inode) {
	__insert_inode_hash(inode, inode->i_ino);
}

extern struct file * get_empty_filp(void);
extern void file_move(struct file *f, struct list_head *list);
extern void file_kill(struct file *f);
1644
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
1645 1646 1647
struct bio;
extern void submit_bio(int, struct bio *);
extern int bdev_read_only(struct block_device *);
1648
#endif
L
Linus Torvalds 已提交
1649 1650 1651 1652 1653 1654 1655 1656 1657
extern int set_blocksize(struct block_device *, int);
extern int sb_set_blocksize(struct super_block *, int);
extern int sb_min_blocksize(struct super_block *, int);

extern int generic_file_mmap(struct file *, struct vm_area_struct *);
extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
extern int file_read_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size);
extern int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size);
int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk);
1658 1659
extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t);
extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t);
L
Linus Torvalds 已提交
1660
extern ssize_t generic_file_aio_write_nolock(struct kiocb *, const struct iovec *,
1661
		unsigned long, loff_t);
L
Linus Torvalds 已提交
1662 1663 1664 1665 1666 1667 1668 1669 1670
extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *,
		unsigned long *, loff_t, loff_t *, size_t, size_t);
extern ssize_t generic_file_buffered_write(struct kiocb *, const struct iovec *,
		unsigned long, loff_t, loff_t *, size_t, ssize_t);
extern ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos);
extern ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos);
extern void do_generic_mapping_read(struct address_space *mapping,
				    struct file_ra_state *, struct file *,
				    loff_t *, read_descriptor_t *, read_actor_t);
1671 1672
extern int generic_segment_checks(const struct iovec *iov,
		unsigned long *nr_segs, size_t *count, int access_flags);
A
Andrew Morton 已提交
1673 1674

/* fs/splice.c */
1675
extern ssize_t generic_file_splice_read(struct file *, loff_t *,
A
Andrew Morton 已提交
1676 1677
		struct pipe_inode_info *, size_t, unsigned int);
extern ssize_t generic_file_splice_write(struct pipe_inode_info *,
1678
		struct file *, loff_t *, size_t, unsigned int);
1679 1680
extern ssize_t generic_file_splice_write_nolock(struct pipe_inode_info *,
		struct file *, loff_t *, size_t, unsigned int);
A
Andrew Morton 已提交
1681
extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
1682 1683
		struct file *out, loff_t *, size_t len, unsigned int flags);
extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
A
Andrew Morton 已提交
1684 1685
		size_t len, unsigned int flags);

L
Linus Torvalds 已提交
1686 1687 1688 1689 1690 1691 1692 1693
extern void
file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping);
extern loff_t no_llseek(struct file *file, loff_t offset, int origin);
extern loff_t generic_file_llseek(struct file *file, loff_t offset, int origin);
extern loff_t remote_llseek(struct file *file, loff_t offset, int origin);
extern int generic_file_open(struct inode * inode, struct file * filp);
extern int nonseekable_open(struct inode * inode, struct file * filp);

1694
#ifdef CONFIG_FS_XIP
1695 1696
extern ssize_t xip_file_read(struct file *filp, char __user *buf, size_t len,
			     loff_t *ppos);
1697
extern int xip_file_mmap(struct file * file, struct vm_area_struct * vma);
1698 1699
extern ssize_t xip_file_write(struct file *filp, const char __user *buf,
			      size_t len, loff_t *ppos);
1700
extern int xip_truncate_page(struct address_space *mapping, loff_t from);
1701 1702 1703 1704 1705
#else
static inline int xip_truncate_page(struct address_space *mapping, loff_t from)
{
	return 0;
}
1706 1707
#endif

L
Linus Torvalds 已提交
1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719
static inline void do_generic_file_read(struct file * filp, loff_t *ppos,
					read_descriptor_t * desc,
					read_actor_t actor)
{
	do_generic_mapping_read(filp->f_mapping,
				&filp->f_ra,
				filp,
				ppos,
				desc,
				actor);
}

1720
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
1721 1722
ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
	struct block_device *bdev, const struct iovec *iov, loff_t offset,
1723
	unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io,
L
Linus Torvalds 已提交
1724 1725 1726 1727 1728 1729 1730 1731 1732 1733
	int lock_type);

enum {
	DIO_LOCKING = 1, /* need locking between buffered and direct access */
	DIO_NO_LOCKING,  /* bdev; no locking at all between buffered/direct */
	DIO_OWN_LOCKING, /* filesystem locks buffered and direct internally */
};

static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb,
	struct inode *inode, struct block_device *bdev, const struct iovec *iov,
1734
	loff_t offset, unsigned long nr_segs, get_block_t get_block,
L
Linus Torvalds 已提交
1735 1736 1737
	dio_iodone_t end_io)
{
	return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
1738
				nr_segs, get_block, end_io, DIO_LOCKING);
L
Linus Torvalds 已提交
1739 1740 1741 1742
}

static inline ssize_t blockdev_direct_IO_no_locking(int rw, struct kiocb *iocb,
	struct inode *inode, struct block_device *bdev, const struct iovec *iov,
1743
	loff_t offset, unsigned long nr_segs, get_block_t get_block,
L
Linus Torvalds 已提交
1744 1745 1746
	dio_iodone_t end_io)
{
	return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
1747
				nr_segs, get_block, end_io, DIO_NO_LOCKING);
L
Linus Torvalds 已提交
1748 1749 1750 1751
}

static inline ssize_t blockdev_direct_IO_own_locking(int rw, struct kiocb *iocb,
	struct inode *inode, struct block_device *bdev, const struct iovec *iov,
1752
	loff_t offset, unsigned long nr_segs, get_block_t get_block,
L
Linus Torvalds 已提交
1753 1754 1755
	dio_iodone_t end_io)
{
	return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
1756
				nr_segs, get_block, end_io, DIO_OWN_LOCKING);
L
Linus Torvalds 已提交
1757
}
1758
#endif
L
Linus Torvalds 已提交
1759

1760
extern const struct file_operations generic_ro_fops;
L
Linus Torvalds 已提交
1761 1762 1763 1764 1765 1766

#define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m))

extern int vfs_readlink(struct dentry *, char __user *, int, const char *);
extern int vfs_follow_link(struct nameidata *, const char *);
extern int page_readlink(struct dentry *, char __user *, int);
1767 1768
extern void *page_follow_link_light(struct dentry *, struct nameidata *);
extern void page_put_link(struct dentry *, struct nameidata *, void *);
1769 1770
extern int __page_symlink(struct inode *inode, const char *symname, int len,
		gfp_t gfp_mask);
L
Linus Torvalds 已提交
1771
extern int page_symlink(struct inode *inode, const char *symname, int len);
1772
extern const struct inode_operations page_symlink_inode_operations;
L
Linus Torvalds 已提交
1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784
extern int generic_readlink(struct dentry *, char __user *, int);
extern void generic_fillattr(struct inode *, struct kstat *);
extern int vfs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
void inode_add_bytes(struct inode *inode, loff_t bytes);
void inode_sub_bytes(struct inode *inode, loff_t bytes);
loff_t inode_get_bytes(struct inode *inode);
void inode_set_bytes(struct inode *inode, loff_t bytes);

extern int vfs_readdir(struct file *, filldir_t, void *);

extern int vfs_stat(char __user *, struct kstat *);
extern int vfs_lstat(char __user *, struct kstat *);
1785 1786
extern int vfs_stat_fd(int dfd, char __user *, struct kstat *);
extern int vfs_lstat_fd(int dfd, char __user *, struct kstat *);
L
Linus Torvalds 已提交
1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800
extern int vfs_fstat(unsigned int, struct kstat *);

extern int vfs_ioctl(struct file *, unsigned int, unsigned int, unsigned long);

extern struct file_system_type *get_fs_type(const char *name);
extern struct super_block *get_super(struct block_device *);
extern struct super_block *user_get_super(dev_t);
extern void drop_super(struct super_block *sb);

extern int dcache_dir_open(struct inode *, struct file *);
extern int dcache_dir_close(struct inode *, struct file *);
extern loff_t dcache_dir_lseek(struct file *, loff_t, int);
extern int dcache_readdir(struct file *, void *, filldir_t);
extern int simple_getattr(struct vfsmount *, struct dentry *, struct kstat *);
1801
extern int simple_statfs(struct dentry *, struct kstatfs *);
L
Linus Torvalds 已提交
1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815
extern int simple_link(struct dentry *, struct inode *, struct dentry *);
extern int simple_unlink(struct inode *, struct dentry *);
extern int simple_rmdir(struct inode *, struct dentry *);
extern int simple_rename(struct inode *, struct dentry *, struct inode *, struct dentry *);
extern int simple_sync_file(struct file *, struct dentry *, int);
extern int simple_empty(struct dentry *);
extern int simple_readpage(struct file *file, struct page *page);
extern int simple_prepare_write(struct file *file, struct page *page,
			unsigned offset, unsigned to);
extern int simple_commit_write(struct file *file, struct page *page,
				unsigned offset, unsigned to);

extern struct dentry *simple_lookup(struct inode *, struct dentry *, struct nameidata *);
extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *);
1816
extern const struct file_operations simple_dir_operations;
1817
extern const struct inode_operations simple_dir_inode_operations;
1818
struct tree_descr { char *name; const struct file_operations *ops; int mode; };
L
Linus Torvalds 已提交
1819 1820
struct dentry *d_alloc_name(struct dentry *, const char *);
extern int simple_fill_super(struct super_block *, int, struct tree_descr *);
1821
extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count);
L
Linus Torvalds 已提交
1822 1823 1824 1825
extern void simple_release_fs(struct vfsmount **mount, int *count);

extern ssize_t simple_read_from_buffer(void __user *, size_t, loff_t *, const void *, size_t);

1826
#ifdef CONFIG_MIGRATION
1827 1828
extern int buffer_migrate_page(struct address_space *,
				struct page *, struct page *);
1829 1830 1831 1832
#else
#define buffer_migrate_page NULL
#endif

L
Linus Torvalds 已提交
1833 1834 1835
extern int inode_change_ok(struct inode *, struct iattr *);
extern int __must_check inode_setattr(struct inode *, struct iattr *);

1836
extern void file_update_time(struct file *file);
L
Linus Torvalds 已提交
1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883

static inline ino_t parent_ino(struct dentry *dentry)
{
	ino_t res;

	spin_lock(&dentry->d_lock);
	res = dentry->d_parent->d_inode->i_ino;
	spin_unlock(&dentry->d_lock);
	return res;
}

/* kernel/fork.c */
extern int unshare_files(void);

/* Transaction based IO helpers */

/*
 * An argresp is stored in an allocated page and holds the
 * size of the argument or response, along with its content
 */
struct simple_transaction_argresp {
	ssize_t size;
	char data[0];
};

#define SIMPLE_TRANSACTION_LIMIT (PAGE_SIZE - sizeof(struct simple_transaction_argresp))

char *simple_transaction_get(struct file *file, const char __user *buf,
				size_t size);
ssize_t simple_transaction_read(struct file *file, char __user *buf,
				size_t size, loff_t *pos);
int simple_transaction_release(struct inode *inode, struct file *file);

static inline void simple_transaction_set(struct file *file, size_t n)
{
	struct simple_transaction_argresp *ar = file->private_data;

	BUG_ON(n > SIMPLE_TRANSACTION_LIMIT);

	/*
	 * The barrier ensures that ar->size will really remain zero until
	 * ar->data is ready for reading.
	 */
	smp_mb();
	ar->size = n;
}

1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929
/*
 * simple attribute files
 *
 * These attributes behave similar to those in sysfs:
 *
 * Writing to an attribute immediately sets a value, an open file can be
 * written to multiple times.
 *
 * Reading from an attribute creates a buffer from the value that might get
 * read with multiple read calls. When the attribute has been read
 * completely, no further read calls are possible until the file is opened
 * again.
 *
 * All attributes contain a text representation of a numeric value
 * that are accessed with the get() and set() functions.
 */
#define DEFINE_SIMPLE_ATTRIBUTE(__fops, __get, __set, __fmt)		\
static int __fops ## _open(struct inode *inode, struct file *file)	\
{									\
	__simple_attr_check_format(__fmt, 0ull);			\
	return simple_attr_open(inode, file, __get, __set, __fmt);	\
}									\
static struct file_operations __fops = {				\
	.owner	 = THIS_MODULE,						\
	.open	 = __fops ## _open,					\
	.release = simple_attr_close,					\
	.read	 = simple_attr_read,					\
	.write	 = simple_attr_write,					\
};

static inline void __attribute__((format(printf, 1, 2)))
__simple_attr_check_format(const char *fmt, ...)
{
	/* don't do anything, just let the compiler check the arguments; */
}

int simple_attr_open(struct inode *inode, struct file *file,
		     u64 (*get)(void *), void (*set)(void *, u64),
		     const char *fmt);
int simple_attr_close(struct inode *inode, struct file *file);
ssize_t simple_attr_read(struct file *file, char __user *buf,
			 size_t len, loff_t *ppos);
ssize_t simple_attr_write(struct file *file, const char __user *buf,
			  size_t len, loff_t *ppos);


L
Linus Torvalds 已提交
1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949
#ifdef CONFIG_SECURITY
static inline char *alloc_secdata(void)
{
	return (char *)get_zeroed_page(GFP_KERNEL);
}

static inline void free_secdata(void *secdata)
{
	free_page((unsigned long)secdata);
}
#else
static inline char *alloc_secdata(void)
{
	return (char *)1;
}

static inline void free_secdata(void *secdata)
{ }
#endif	/* CONFIG_SECURITY */

1950 1951 1952 1953
int proc_nr_files(ctl_table *table, int write, struct file *filp,
		  void __user *buffer, size_t *lenp, loff_t *ppos);


L
Linus Torvalds 已提交
1954 1955
#endif /* __KERNEL__ */
#endif /* _LINUX_FS_H */