fs.h 84.1 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10
#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>
11
#include <linux/blk_types.h>
L
Linus Torvalds 已提交
12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29

/*
 * 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 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 42 43 44
/* 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 */
};

struct inodes_stat_t {
	int nr_inodes;
	int nr_unused;
45
	int dummy[5];		/* padding for sysctl ABI compatibility */
L
Linus Torvalds 已提交
46 47 48 49 50 51 52 53 54
};


#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
55
#define MAY_ACCESS 16
56
#define MAY_OPEN 32
E
Eric Paris 已提交
57
#define MAY_CHDIR 64
L
Linus Torvalds 已提交
58

59 60 61 62 63
/*
 * flags in file.f_mode.  Note that FMODE_READ and FMODE_WRITE must correspond
 * to O_WRONLY and O_RDWR via the strange trick in __dentry_open()
 */

64
/* file is open for reading */
65
#define FMODE_READ		((__force fmode_t)0x1)
66
/* file is open for writing */
67
#define FMODE_WRITE		((__force fmode_t)0x2)
68
/* file is seekable */
69
#define FMODE_LSEEK		((__force fmode_t)0x4)
70
/* file can be accessed using pread */
71
#define FMODE_PREAD		((__force fmode_t)0x8)
72
/* file can be accessed using pwrite */
73
#define FMODE_PWRITE		((__force fmode_t)0x10)
74
/* File is opened for execution with sys_execve / sys_uselib */
75
#define FMODE_EXEC		((__force fmode_t)0x20)
76
/* File is opened with O_NDELAY (only set for block devices) */
77
#define FMODE_NDELAY		((__force fmode_t)0x40)
78
/* File is opened with O_EXCL (only set for block devices) */
79
#define FMODE_EXCL		((__force fmode_t)0x80)
80 81
/* File is opened using open(.., 3, ..) and is writeable only for ioctls
   (specialy hack for floppy.c) */
82
#define FMODE_WRITE_IOCTL	((__force fmode_t)0x100)
83

84 85 86 87 88 89
/*
 * Don't update ctime and mtime.
 *
 * Currently a special hack for the XFS open_by_handle ioctl, but we'll
 * hopefully graduate it to a proper O_CMTIME flag supported by open(2) soon.
 */
90
#define FMODE_NOCMTIME		((__force fmode_t)0x800)
91

92
/* Expect random access pattern */
93
#define FMODE_RANDOM		((__force fmode_t)0x1000)
94

E
Eric Paris 已提交
95
/* File was opened by fanotify and shouldn't generate fanotify events */
96
#define FMODE_NONOTIFY		((__force fmode_t)0x1000000)
E
Eric Paris 已提交
97

98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124
/*
 * The below are the various read and write types that we support. Some of
 * them include behavioral modifiers that send information down to the
 * block layer and IO scheduler. Terminology:
 *
 *	The block layer uses device plugging to defer IO a little bit, in
 *	the hope that we will see more IO very shortly. This increases
 *	coalescing of adjacent IO and thus reduces the number of IOs we
 *	have to send to the device. It also allows for better queuing,
 *	if the IO isn't mergeable. If the caller is going to be waiting
 *	for the IO, then he must ensure that the device is unplugged so
 *	that the IO is dispatched to the driver.
 *
 *	All IO is handled async in Linux. This is fine for background
 *	writes, but for reads or writes that someone waits for completion
 *	on, we want to notify the block layer and IO scheduler so that they
 *	know about it. That allows them to make better scheduling
 *	decisions. So when the below references 'sync' and 'async', it
 *	is referencing this priority hint.
 *
 * With that in mind, the available types are:
 *
 * READ			A normal read operation. Device will be plugged.
 * READ_SYNC		A synchronous read. Device is not plugged, caller can
 *			immediately wait on this read without caring about
 *			unplugging.
 * READA		Used for read-ahead operations. Lower priority, and the
125
 *			block layer could (in theory) choose to ignore this
126 127 128 129 130 131 132 133 134 135 136
 *			request if it runs into resource problems.
 * WRITE		A normal async write. Device will be plugged.
 * WRITE_SYNC_PLUG	Synchronous write. Identical to WRITE, but passes down
 *			the hint that someone will be waiting on this IO
 *			shortly. The device must still be unplugged explicitly,
 *			WRITE_SYNC_PLUG does not do this as we could be
 *			submitting more writes before we actually wait on any
 *			of them.
 * WRITE_SYNC		Like WRITE_SYNC_PLUG, but also unplugs the device
 *			immediately after submission. The write equivalent
 *			of READ_SYNC.
137
 * WRITE_ODIRECT_PLUG	Special case write for O_DIRECT only.
138 139 140 141 142 143
 * WRITE_FLUSH		Like WRITE_SYNC but with preceding cache flush.
 * WRITE_FUA		Like WRITE_SYNC but data is guaranteed to be on
 *			non-volatile media on completion.
 * WRITE_FLUSH_FUA	Combination of WRITE_FLUSH and FUA. The IO is preceded
 *			by a cache flush and data is guaranteed to be on
 *			non-volatile media on completion.
144 145
 *
 */
146 147
#define RW_MASK			REQ_WRITE
#define RWA_MASK		REQ_RAHEAD
148 149

#define READ			0
150 151
#define WRITE			RW_MASK
#define READA			RWA_MASK
152 153 154 155 156 157 158

#define READ_SYNC		(READ | REQ_SYNC | REQ_UNPLUG)
#define READ_META		(READ | REQ_META)
#define WRITE_SYNC_PLUG		(WRITE | REQ_SYNC | REQ_NOIDLE)
#define WRITE_SYNC		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG)
#define WRITE_ODIRECT_PLUG	(WRITE | REQ_SYNC)
#define WRITE_META		(WRITE | REQ_META)
159 160 161 162 163 164
#define WRITE_FLUSH		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
				 REQ_FLUSH)
#define WRITE_FUA		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
				 REQ_FUA)
#define WRITE_FLUSH_FUA		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
				 REQ_FLUSH | REQ_FUA)
L
Linus Torvalds 已提交
165 166 167 168 169 170 171 172

#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
173
#define FS_HAS_SUBTYPE 4
L
Linus Torvalds 已提交
174
#define FS_REVAL_DOT	16384	/* Check the paths ".", ".." for staleness */
175 176 177 178
#define FS_RENAME_DOES_D_MOVE	32768	/* FS will handle d_move()
					 * during rename() internally.
					 */

L
Linus Torvalds 已提交
179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194
/*
 * 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
195 196 197
#define MS_VERBOSE	32768	/* War is peace. Verbosity is silence.
				   MS_VERBOSE is deprecated. */
#define MS_SILENT	32768
M
Miklos Szeredi 已提交
198
#define MS_POSIXACL	(1<<16)	/* VFS does not apply the umask */
R
Ram Pai 已提交
199
#define MS_UNBINDABLE	(1<<17)	/* change to unbindable */
200
#define MS_PRIVATE	(1<<18)	/* change to private */
R
Ram Pai 已提交
201
#define MS_SLAVE	(1<<19)	/* change to slave */
R
Ram Pai 已提交
202
#define MS_SHARED	(1<<20)	/* change to shared */
V
Valerie Henson 已提交
203
#define MS_RELATIME	(1<<21)	/* Update atime relative to mtime/ctime. */
204
#define MS_KERNMOUNT	(1<<22) /* this is a kern_mount call */
205
#define MS_I_VERSION	(1<<23) /* Update inode I_version field */
M
Matthew Garrett 已提交
206
#define MS_STRICTATIME	(1<<24) /* Always perform atime updates */
A
Al Viro 已提交
207
#define MS_BORN		(1<<29)
L
Linus Torvalds 已提交
208 209 210 211 212 213
#define MS_ACTIVE	(1<<30)
#define MS_NOUSER	(1<<31)

/*
 * Superblock flags that can be altered by MS_REMOUNT
 */
M
Mimi Zohar 已提交
214
#define MS_RMT_MASK	(MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION)
L
Linus Torvalds 已提交
215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233

/*
 * 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 */
234
#define S_IMA		1024	/* Inode has an associated IMA struct */
L
Linus Torvalds 已提交
235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256

/*
 * 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)
257
#define IS_NOATIME(inode)   __IS_FLG(inode, MS_RDONLY|MS_NOATIME)
258
#define IS_I_VERSION(inode)   __IS_FLG(inode, MS_I_VERSION)
L
Linus Torvalds 已提交
259 260 261 262 263 264 265 266 267 268

#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)
269
#define IS_IMA(inode)		((inode)->i_flags & S_IMA)
L
Linus Torvalds 已提交
270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299

/* 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) */
300 301 302 303
#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)
304
#define BLKDISCARD _IO(0x12,119)
M
Martin K. Petersen 已提交
305 306 307 308
#define BLKIOMIN _IO(0x12,120)
#define BLKIOOPT _IO(0x12,121)
#define BLKALIGNOFF _IO(0x12,122)
#define BLKPBSZGET _IO(0x12,123)
309
#define BLKDISCARDZEROES _IO(0x12,124)
A
Adrian Hunter 已提交
310
#define BLKSECDISCARD _IO(0x12,125)
L
Linus Torvalds 已提交
311 312 313 314

#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 */
315 316
#define FIFREEZE	_IOWR('X', 119, int)	/* Freeze */
#define FITHAW		_IOWR('X', 120, int)	/* Thaw */
L
Linus Torvalds 已提交
317

318 319 320 321
#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)
M
Mark Fasheh 已提交
322
#define FS_IOC_FIEMAP			_IOWR('f', 11, struct fiemap)
323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351
#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*/
352 353
#define FS_EXTENT_FL			0x00080000 /* Extents */
#define FS_DIRECTIO_FL			0x00100000 /* Use direct i/o */
354 355 356 357 358 359
#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 */


360 361 362 363
#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
364 365 366 367 368 369 370
#ifdef __KERNEL__

#include <linux/linkage.h>
#include <linux/wait.h>
#include <linux/types.h>
#include <linux/kdev_t.h>
#include <linux/dcache.h>
371
#include <linux/path.h>
L
Linus Torvalds 已提交
372 373 374 375 376 377 378
#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>
379
#include <linux/pid.h>
380
#include <linux/mutex.h>
381
#include <linux/capability.h>
382
#include <linux/semaphore.h>
M
Mark Fasheh 已提交
383
#include <linux/fiemap.h>
L
Linus Torvalds 已提交
384 385 386 387

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

388
struct export_operations;
389
struct hd_geometry;
L
Linus Torvalds 已提交
390 391
struct iovec;
struct nameidata;
392
struct kiocb;
L
Linus Torvalds 已提交
393 394 395 396 397
struct pipe_inode_info;
struct poll_table_struct;
struct kstatfs;
struct vm_area_struct;
struct vfsmount;
398
struct cred;
L
Linus Torvalds 已提交
399

400
extern void __init inode_init(void);
L
Linus Torvalds 已提交
401 402 403
extern void __init inode_init_early(void);
extern void __init files_init(unsigned long);

404 405 406 407 408 409
extern struct files_stat_struct files_stat;
extern int get_max_files(void);
extern int sysctl_nr_open;
extern struct inodes_stat_t inodes_stat;
extern int leases_enable, lease_break_time;

L
Linus Torvalds 已提交
410 411 412
struct buffer_head;
typedef int (get_block_t)(struct inode *inode, sector_t iblock,
			struct buffer_head *bh_result, int create);
413
typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
414 415
			ssize_t bytes, void *private, int ret,
			bool is_async);
L
Linus Torvalds 已提交
416 417 418 419 420

/*
 * Attribute flags.  These should be or-ed together to figure out what
 * has been changed!
 */
421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437
#define ATTR_MODE	(1 << 0)
#define ATTR_UID	(1 << 1)
#define ATTR_GID	(1 << 2)
#define ATTR_SIZE	(1 << 3)
#define ATTR_ATIME	(1 << 4)
#define ATTR_MTIME	(1 << 5)
#define ATTR_CTIME	(1 << 6)
#define ATTR_ATIME_SET	(1 << 7)
#define ATTR_MTIME_SET	(1 << 8)
#define ATTR_FORCE	(1 << 9) /* Not a change, but a change it */
#define ATTR_ATTR_FLAG	(1 << 10)
#define ATTR_KILL_SUID	(1 << 11)
#define ATTR_KILL_SGID	(1 << 12)
#define ATTR_FILE	(1 << 13)
#define ATTR_KILL_PRIV	(1 << 14)
#define ATTR_OPEN	(1 << 15) /* Truncating from open(O_TRUNC) */
#define ATTR_TIMES_SET	(1 << 16)
L
Linus Torvalds 已提交
438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456

/*
 * 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;
457 458 459 460 461 462 463

	/*
	 * 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
464 465 466 467 468 469 470
};

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

471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488
/** 
 * 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
N
Nick Piggin 已提交
489
 *  			by readpage().
490 491 492 493 494 495 496 497 498 499 500 501
 *
 * 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,
};

502
#define AOP_FLAG_UNINTERRUPTIBLE	0x0001 /* will not do a short write */
N
Nick Piggin 已提交
503
#define AOP_FLAG_CONT_EXPAND		0x0002 /* called from cont_expand */
504 505 506
#define AOP_FLAG_NOFS			0x0004 /* used by filesystem to direct
						* helper code (eg buffer layer)
						* to clear GFP_FS from alloc */
507

L
Linus Torvalds 已提交
508 509 510 511 512 513 514
/*
 * oh the beauties of C type declarations.
 */
struct page;
struct address_space;
struct writeback_control;

N
Nick Piggin 已提交
515 516 517 518 519 520 521 522 523 524 525 526
struct iov_iter {
	const struct iovec *iov;
	unsigned long nr_segs;
	size_t iov_offset;
	size_t count;
};

size_t iov_iter_copy_from_user_atomic(struct page *page,
		struct iov_iter *i, unsigned long offset, size_t bytes);
size_t iov_iter_copy_from_user(struct page *page,
		struct iov_iter *i, unsigned long offset, size_t bytes);
void iov_iter_advance(struct iov_iter *i, size_t bytes);
527
int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes);
N
Nick Piggin 已提交
528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546
size_t iov_iter_single_seg_count(struct iov_iter *i);

static inline void iov_iter_init(struct iov_iter *i,
			const struct iovec *iov, unsigned long nr_segs,
			size_t count, size_t written)
{
	i->iov = iov;
	i->nr_segs = nr_segs;
	i->iov_offset = 0;
	i->count = count + written;

	iov_iter_advance(i, written);
}

static inline size_t iov_iter_count(struct iov_iter *i)
{
	return i->count;
}

547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567
/*
 * "descriptor" for what we're up to with a read.
 * 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);
N
Nick Piggin 已提交
568

L
Linus Torvalds 已提交
569 570 571
struct address_space_operations {
	int (*writepage)(struct page *page, struct writeback_control *wbc);
	int (*readpage)(struct file *, struct page *);
572
	void (*sync_page)(struct page *);
L
Linus Torvalds 已提交
573 574 575 576

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

577
	/* Set a page dirty.  Return true if this dirtied it */
L
Linus Torvalds 已提交
578 579 580 581 582
	int (*set_page_dirty)(struct page *page);

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

583 584 585 586 587 588 589
	int (*write_begin)(struct file *, struct address_space *mapping,
				loff_t pos, unsigned len, unsigned flags,
				struct page **pagep, void **fsdata);
	int (*write_end)(struct file *, struct address_space *mapping,
				loff_t pos, unsigned len, unsigned copied,
				struct page *page, void *fsdata);

L
Linus Torvalds 已提交
590 591
	/* Unfortunately this kludge is needed for FIBMAP. Don't use it */
	sector_t (*bmap)(struct address_space *, sector_t);
592
	void (*invalidatepage) (struct page *, unsigned long);
A
Al Viro 已提交
593
	int (*releasepage) (struct page *, gfp_t);
L
Linus Torvalds 已提交
594 595
	ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
			loff_t offset, unsigned long nr_segs);
596 597
	int (*get_xip_mem)(struct address_space *, pgoff_t, int,
						void **, unsigned long *);
598
	/* migrate the contents of a page to the specified target */
599 600
	int (*migratepage) (struct address_space *,
			struct page *, struct page *);
601
	int (*launder_page) (struct page *);
602 603
	int (*is_partially_uptodate) (struct page *, read_descriptor_t *,
					unsigned long);
604
	int (*error_remove_page)(struct address_space *, struct page *);
L
Linus Torvalds 已提交
605 606
};

607 608 609 610 611 612 613 614 615 616 617 618
/*
 * pagecache_write_begin/pagecache_write_end must be used by general code
 * to write into the pagecache.
 */
int pagecache_write_begin(struct file *, struct address_space *mapping,
				loff_t pos, unsigned len, unsigned flags,
				struct page **pagep, void **fsdata);

int pagecache_write_end(struct file *, struct address_space *mapping,
				loff_t pos, unsigned len, unsigned copied,
				struct page *page, void *fsdata);

L
Linus Torvalds 已提交
619 620 621 622
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 */
N
Nick Piggin 已提交
623
	spinlock_t		tree_lock;	/* and lock protecting it */
L
Linus Torvalds 已提交
624 625 626 627 628 629 630
	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 */
631
	const struct address_space_operations *a_ops;	/* methods */
L
Linus Torvalds 已提交
632 633 634 635 636 637 638 639 640 641 642 643 644 645 646
	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 */
647
	struct super_block *	bd_super;
L
Linus Torvalds 已提交
648
	int			bd_openers;
649
	struct mutex		bd_mutex;	/* open/close mutex */
L
Linus Torvalds 已提交
650
	struct list_head	bd_inodes;
651
	void *			bd_claiming;
L
Linus Torvalds 已提交
652 653
	void *			bd_holder;
	int			bd_holders;
654 655 656
#ifdef CONFIG_SYSFS
	struct list_head	bd_holder_list;
#endif
L
Linus Torvalds 已提交
657 658 659 660 661 662 663 664 665 666 667 668 669 670 671
	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;
	/*
	 * 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;
672 673 674 675 676

	/* The counter of freeze processes */
	int			bd_fsfreeze_count;
	/* Mutex for freeze */
	struct mutex		bd_fsfreeze_mutex;
L
Linus Torvalds 已提交
677 678 679 680 681 682 683 684
};

/*
 * Radix-tree tags, for tagging dirty and writeback pages within the pagecache
 * radix trees
 */
#define PAGECACHE_TAG_DIRTY	0
#define PAGECACHE_TAG_WRITEBACK	1
685
#define PAGECACHE_TAG_TOWRITE	2
L
Linus Torvalds 已提交
686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719

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

A
Al Viro 已提交
720 721 722
struct posix_acl;
#define ACL_NOT_CACHED ((void *)(-1))

L
Linus Torvalds 已提交
723 724
struct inode {
	struct hlist_node	i_hash;
725
	struct list_head	i_list;		/* backing dev IO list */
L
Linus Torvalds 已提交
726 727 728 729 730 731 732 733
	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;
734
	unsigned int		i_blkbits;
735
	u64			i_version;
L
Linus Torvalds 已提交
736
	loff_t			i_size;
737 738 739
#ifdef __NEED_I_SIZE_ORDERED
	seqcount_t		i_size_seqcount;
#endif
L
Linus Torvalds 已提交
740 741 742
	struct timespec		i_atime;
	struct timespec		i_mtime;
	struct timespec		i_ctime;
T
Takashi Sato 已提交
743
	blkcnt_t		i_blocks;
L
Linus Torvalds 已提交
744
	unsigned short          i_bytes;
745
	umode_t			i_mode;
L
Linus Torvalds 已提交
746
	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
747
	struct mutex		i_mutex;
L
Linus Torvalds 已提交
748
	struct rw_semaphore	i_alloc_sem;
749
	const struct inode_operations	*i_op;
750
	const struct file_operations	*i_fop;	/* former ->i_op->default_file_ops */
L
Linus Torvalds 已提交
751 752 753 754 755 756 757 758
	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;
759 760
	union {
		struct pipe_inode_info	*i_pipe;
761
		struct block_device	*i_bdev;
762
		struct cdev		*i_cdev;
763
	};
L
Linus Torvalds 已提交
764 765 766

	__u32			i_generation;

767 768
#ifdef CONFIG_FSNOTIFY
	__u32			i_fsnotify_mask; /* all events this inode cares about */
769
	struct hlist_head	i_fsnotify_marks;
R
Robert Love 已提交
770 771
#endif

L
Linus Torvalds 已提交
772 773 774 775 776
	unsigned long		i_state;
	unsigned long		dirtied_when;	/* jiffies of first dirtying */

	unsigned int		i_flags;

777 778 779 780
#ifdef CONFIG_IMA
	/* protected by i_lock */
	unsigned int		i_readcount; /* struct files open RO */
#endif
L
Linus Torvalds 已提交
781
	atomic_t		i_writecount;
782
#ifdef CONFIG_SECURITY
L
Linus Torvalds 已提交
783
	void			*i_security;
A
Al Viro 已提交
784 785 786 787
#endif
#ifdef CONFIG_FS_POSIX_ACL
	struct posix_acl	*i_acl;
	struct posix_acl	*i_default_acl;
788
#endif
789
	void			*i_private; /* fs or device private pointer */
L
Linus Torvalds 已提交
790 791
};

I
Ingo Molnar 已提交
792 793 794 795 796 797 798 799 800
/*
 * 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
801
 * parent -> child -> normal -> xattr -> quota
I
Ingo Molnar 已提交
802 803 804 805 806 807
 */
enum inode_i_mutex_lock_class
{
	I_MUTEX_NORMAL,
	I_MUTEX_PARENT,
	I_MUTEX_CHILD,
I
Ingo Molnar 已提交
808
	I_MUTEX_XATTR,
I
Ingo Molnar 已提交
809 810 811
	I_MUTEX_QUOTA
};

L
Linus Torvalds 已提交
812 813 814 815 816 817 818 819 820 821
/*
 * 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
822
static inline loff_t i_size_read(const struct inode *inode)
L
Linus Torvalds 已提交
823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844
{
#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
}

845 846 847 848 849
/*
 * 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
850 851 852 853 854 855 856 857 858 859 860 861 862 863 864
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
865
static inline unsigned iminor(const struct inode *inode)
L
Linus Torvalds 已提交
866 867 868 869
{
	return MINOR(inode->i_rdev);
}

J
Jan Engelhardt 已提交
870
static inline unsigned imajor(const struct inode *inode)
L
Linus Torvalds 已提交
871 872 873 874 875 876 877 878
{
	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 */
879 880
	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
881 882 883 884 885 886 887 888
	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 {
F
Fengguang Wu 已提交
889 890 891
	pgoff_t start;			/* where readahead started */
	unsigned int size;		/* # of readahead pages */
	unsigned int async_size;	/* do asynchronous readahead when
892
					   there are only # of pages ahead */
893

F
Fengguang Wu 已提交
894
	unsigned int ra_pages;		/* Maximum readahead window */
895
	unsigned int mmap_miss;		/* Cache miss stat for mmap accesses */
896
	loff_t prev_pos;		/* Cache last read() position */
L
Linus Torvalds 已提交
897 898
};

899 900 901 902 903
/*
 * Check if @index falls in the readahead windows.
 */
static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
{
904 905
	return (index >= ra->start &&
		index <  ra->start + ra->size);
906 907
}

908 909 910
#define FILE_MNT_WRITE_TAKEN	1
#define FILE_MNT_WRITE_RELEASED	2

L
Linus Torvalds 已提交
911
struct file {
E
Eric Dumazet 已提交
912 913 914 915 916 917 918 919
	/*
	 * 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;
920 921 922
	struct path		f_path;
#define f_dentry	f_path.dentry
#define f_vfsmnt	f_path.mnt
923
	const struct file_operations	*f_op;
924
	spinlock_t		f_lock;  /* f_ep_links, f_flags, no IRQ */
N
Nick Piggin 已提交
925 926 927
#ifdef CONFIG_SMP
	int			f_sb_list_cpu;
#endif
A
Al Viro 已提交
928
	atomic_long_t		f_count;
L
Linus Torvalds 已提交
929
	unsigned int 		f_flags;
930
	fmode_t			f_mode;
L
Linus Torvalds 已提交
931 932
	loff_t			f_pos;
	struct fown_struct	f_owner;
D
David Howells 已提交
933
	const struct cred	*f_cred;
L
Linus Torvalds 已提交
934 935
	struct file_ra_state	f_ra;

936
	u64			f_version;
937
#ifdef CONFIG_SECURITY
L
Linus Torvalds 已提交
938
	void			*f_security;
939
#endif
L
Linus Torvalds 已提交
940 941 942 943 944 945 946 947
	/* 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;
#endif /* #ifdef CONFIG_EPOLL */
	struct address_space	*f_mapping;
948 949 950
#ifdef CONFIG_DEBUG_WRITECOUNT
	unsigned long f_mnt_write_state;
#endif
L
Linus Torvalds 已提交
951 952
};

A
Al Viro 已提交
953
#define get_file(x)	atomic_long_inc(&(x)->f_count)
954
#define fput_atomic(x)	atomic_long_add_unless(&(x)->f_count, -1, 1)
A
Al Viro 已提交
955
#define file_count(x)	atomic_long_read(&(x)->f_count)
L
Linus Torvalds 已提交
956

957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999
#ifdef CONFIG_DEBUG_WRITECOUNT
static inline void file_take_write(struct file *f)
{
	WARN_ON(f->f_mnt_write_state != 0);
	f->f_mnt_write_state = FILE_MNT_WRITE_TAKEN;
}
static inline void file_release_write(struct file *f)
{
	f->f_mnt_write_state |= FILE_MNT_WRITE_RELEASED;
}
static inline void file_reset_write(struct file *f)
{
	f->f_mnt_write_state = 0;
}
static inline void file_check_state(struct file *f)
{
	/*
	 * At this point, either both or neither of these bits
	 * should be set.
	 */
	WARN_ON(f->f_mnt_write_state == FILE_MNT_WRITE_TAKEN);
	WARN_ON(f->f_mnt_write_state == FILE_MNT_WRITE_RELEASED);
}
static inline int file_check_writeable(struct file *f)
{
	if (f->f_mnt_write_state == FILE_MNT_WRITE_TAKEN)
		return 0;
	printk(KERN_WARNING "writeable file with no "
			    "mnt_want_write()\n");
	WARN_ON(1);
	return -EINVAL;
}
#else /* !CONFIG_DEBUG_WRITECOUNT */
static inline void file_take_write(struct file *filp) {}
static inline void file_release_write(struct file *filp) {}
static inline void file_reset_write(struct file *filp) {}
static inline void file_check_state(struct file *filp) {}
static inline int file_check_writeable(struct file *filp)
{
	return 0;
}
#endif /* CONFIG_DEBUG_WRITECOUNT */

L
Linus Torvalds 已提交
1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012
#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 */
1013
#define FL_EXISTS	16	/* when unlocking, test for existence */
L
Linus Torvalds 已提交
1014
#define FL_LEASE	32	/* lease held on this file */
1015
#define FL_CLOSE	64	/* unlock on close */
L
Linus Torvalds 已提交
1016 1017
#define FL_SLEEP	128	/* A blocking lock */

1018 1019 1020 1021 1022 1023
/*
 * Special return value from posix_lock_file() and vfs_lock_file() for
 * asynchronous locking.
 */
#define FILE_LOCK_DEFERRED 1

L
Linus Torvalds 已提交
1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040
/*
 * 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_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 */
1041
	int (*fl_grant)(struct file_lock *, struct file_lock *, int);
L
Linus Torvalds 已提交
1042 1043 1044 1045 1046 1047 1048
	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);
};

1049 1050 1051 1052 1053 1054 1055 1056
struct lock_manager {
	struct list_head list;
};

void locks_start_grace(struct lock_manager *);
void locks_end_grace(struct lock_manager *);
int locks_in_grace(void);

L
Linus Torvalds 已提交
1057 1058 1059 1060 1061 1062 1063 1064
/* 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;
1065 1066
	unsigned char fl_flags;
	unsigned char fl_type;
L
Linus Torvalds 已提交
1067
	unsigned int fl_pid;
1068
	struct pid *fl_nspid;
L
Linus Torvalds 已提交
1069 1070 1071 1072 1073 1074 1075 1076
	wait_queue_head_t fl_wait;
	struct file *fl_file;
	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 */

1077
	const struct file_lock_operations *fl_ops;	/* Callbacks for filesystems */
1078
	const struct lock_manager_operations *fl_lmops;	/* Callbacks for lockmanagers */
L
Linus Torvalds 已提交
1079 1080
	union {
		struct nfs_lock_info	nfs_fl;
1081
		struct nfs4_lock_info	nfs4_fl;
D
David Howells 已提交
1082 1083 1084 1085
		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
1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097
	} 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>

1098 1099 1100
extern void send_sigio(struct fown_struct *fown, int fd, int band);

#ifdef CONFIG_FILE_LOCKING
L
Linus Torvalds 已提交
1101
extern int fcntl_getlk(struct file *, struct flock __user *);
1102 1103
extern int fcntl_setlk(unsigned int, struct file *, unsigned int,
			struct flock __user *);
L
Linus Torvalds 已提交
1104 1105 1106

#if BITS_PER_LONG == 32
extern int fcntl_getlk64(struct file *, struct flock64 __user *);
1107 1108
extern int fcntl_setlk64(unsigned int, struct file *, unsigned int,
			struct flock64 __user *);
L
Linus Torvalds 已提交
1109 1110 1111 1112 1113 1114 1115 1116
#endif

extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg);
extern int fcntl_getlease(struct file *filp);

/* fs/locks.c */
extern void locks_init_lock(struct file_lock *);
extern void locks_copy_lock(struct file_lock *, struct file_lock *);
1117
extern void __locks_copy_lock(struct file_lock *, const struct file_lock *);
L
Linus Torvalds 已提交
1118 1119
extern void locks_remove_posix(struct file *, fl_owner_t);
extern void locks_remove_flock(struct file *);
1120
extern void locks_release_private(struct file_lock *);
1121
extern void posix_test_lock(struct file *, struct file_lock *);
1122
extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *);
L
Linus Torvalds 已提交
1123
extern int posix_lock_file_wait(struct file *, struct file_lock *);
J
J. Bruce Fields 已提交
1124
extern int posix_unblock_lock(struct file *, struct file_lock *);
1125
extern int vfs_test_lock(struct file *, struct file_lock *);
1126
extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *);
M
Marc Eshel 已提交
1127
extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
L
Linus Torvalds 已提交
1128 1129 1130
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);
1131
extern int generic_setlease(struct file *, long, struct file_lock **);
1132
extern int vfs_setlease(struct file *, long, struct file_lock **);
L
Linus Torvalds 已提交
1133 1134 1135
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);
1136 1137
extern void lock_flocks(void);
extern void unlock_flocks(void);
1138
#else /* !CONFIG_FILE_LOCKING */
1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149
static inline int fcntl_getlk(struct file *file, struct flock __user *user)
{
	return -EINVAL;
}

static inline int fcntl_setlk(unsigned int fd, struct file *file,
			      unsigned int cmd, struct flock __user *user)
{
	return -EACCES;
}

1150
#if BITS_PER_LONG == 32
1151 1152 1153 1154 1155 1156 1157 1158 1159 1160
static inline int fcntl_getlk64(struct file *file, struct flock64 __user *user)
{
	return -EINVAL;
}

static inline int fcntl_setlk64(unsigned int fd, struct file *file,
				unsigned int cmd, struct flock64 __user *user)
{
	return -EACCES;
}
1161
#endif
1162 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 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279
static inline int fcntl_setlease(unsigned int fd, struct file *filp, long arg)
{
	return 0;
}

static inline int fcntl_getlease(struct file *filp)
{
	return 0;
}

static inline void locks_init_lock(struct file_lock *fl)
{
	return;
}

static inline void __locks_copy_lock(struct file_lock *new, struct file_lock *fl)
{
	return;
}

static inline void locks_copy_lock(struct file_lock *new, struct file_lock *fl)
{
	return;
}

static inline void locks_remove_posix(struct file *filp, fl_owner_t owner)
{
	return;
}

static inline void locks_remove_flock(struct file *filp)
{
	return;
}

static inline void posix_test_lock(struct file *filp, struct file_lock *fl)
{
	return;
}

static inline int posix_lock_file(struct file *filp, struct file_lock *fl,
				  struct file_lock *conflock)
{
	return -ENOLCK;
}

static inline int posix_lock_file_wait(struct file *filp, struct file_lock *fl)
{
	return -ENOLCK;
}

static inline int posix_unblock_lock(struct file *filp,
				     struct file_lock *waiter)
{
	return -ENOENT;
}

static inline int vfs_test_lock(struct file *filp, struct file_lock *fl)
{
	return 0;
}

static inline int vfs_lock_file(struct file *filp, unsigned int cmd,
				struct file_lock *fl, struct file_lock *conf)
{
	return -ENOLCK;
}

static inline int vfs_cancel_lock(struct file *filp, struct file_lock *fl)
{
	return 0;
}

static inline int flock_lock_file_wait(struct file *filp,
				       struct file_lock *request)
{
	return -ENOLCK;
}

static inline int __break_lease(struct inode *inode, unsigned int mode)
{
	return 0;
}

static inline void lease_get_mtime(struct inode *inode, struct timespec *time)
{
	return;
}

static inline int generic_setlease(struct file *filp, long arg,
				    struct file_lock **flp)
{
	return -EINVAL;
}

static inline int vfs_setlease(struct file *filp, long arg,
			       struct file_lock **lease)
{
	return -EINVAL;
}

static inline int lease_modify(struct file_lock **before, int arg)
{
	return -EINVAL;
}

static inline int lock_may_read(struct inode *inode, loff_t start,
				unsigned long len)
{
	return 1;
}

static inline int lock_may_write(struct inode *inode, loff_t start,
				 unsigned long len)
{
	return 1;
}

1280 1281 1282 1283 1284 1285 1286 1287
static inline void lock_flocks(void)
{
}

static inline void unlock_flocks(void)
{
}

1288 1289
#endif /* !CONFIG_FILE_LOCKING */

L
Linus Torvalds 已提交
1290 1291

struct fasync_struct {
1292 1293 1294 1295 1296 1297
	spinlock_t		fa_lock;
	int			magic;
	int			fa_fd;
	struct fasync_struct	*fa_next; /* singly linked list */
	struct file		*fa_file;
	struct rcu_head		fa_rcu;
L
Linus Torvalds 已提交
1298 1299 1300 1301 1302 1303 1304 1305 1306
};

#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);

1307
extern int __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
L
Linus Torvalds 已提交
1308 1309
extern int f_setown(struct file *filp, unsigned long arg, int force);
extern void f_delown(struct file *filp);
1310
extern pid_t f_getown(struct file *filp);
L
Linus Torvalds 已提交
1311 1312 1313 1314 1315 1316 1317 1318 1319
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 */
1320 1321
#define UMOUNT_NOFOLLOW	0x00000008	/* Don't follow symlink on umount */
#define UMOUNT_UNUSED	0x80000000	/* Flag guaranteed to be unused */
L
Linus Torvalds 已提交
1322 1323 1324 1325 1326 1327 1328 1329

extern struct list_head super_blocks;
extern spinlock_t sb_lock;

struct super_block {
	struct list_head	s_list;		/* Keep this first */
	dev_t			s_dev;		/* search index; _not_ kdev_t */
	unsigned char		s_dirt;
1330 1331
	unsigned char		s_blocksize_bits;
	unsigned long		s_blocksize;
1332
	loff_t			s_maxbytes;	/* Max file size */
L
Linus Torvalds 已提交
1333
	struct file_system_type	*s_type;
1334
	const struct super_operations	*s_op;
1335
	const struct dquot_operations	*dq_op;
1336
	const struct quotactl_ops	*s_qcop;
1337
	const struct export_operations *s_export_op;
L
Linus Torvalds 已提交
1338 1339 1340 1341
	unsigned long		s_flags;
	unsigned long		s_magic;
	struct dentry		*s_root;
	struct rw_semaphore	s_umount;
1342
	struct mutex		s_lock;
L
Linus Torvalds 已提交
1343 1344
	int			s_count;
	atomic_t		s_active;
1345
#ifdef CONFIG_SECURITY
L
Linus Torvalds 已提交
1346
	void                    *s_security;
1347
#endif
1348
	const struct xattr_handler **s_xattr;
L
Linus Torvalds 已提交
1349 1350 1351

	struct list_head	s_inodes;	/* all inodes */
	struct hlist_head	s_anon;		/* anonymous dentries for (nfs) exporting */
N
Nick Piggin 已提交
1352 1353 1354
#ifdef CONFIG_SMP
	struct list_head __percpu *s_files;
#else
L
Linus Torvalds 已提交
1355
	struct list_head	s_files;
N
Nick Piggin 已提交
1356
#endif
1357 1358 1359
	/* s_dentry_lru and s_nr_dentry_unused are protected by dcache_lock */
	struct list_head	s_dentry_lru;	/* unused dentry lru */
	int			s_nr_dentry_unused;	/* # of dentry on lru */
L
Linus Torvalds 已提交
1360 1361

	struct block_device	*s_bdev;
J
Jens Axboe 已提交
1362
	struct backing_dev_info *s_bdi;
1363
	struct mtd_info		*s_mtd;
L
Linus Torvalds 已提交
1364 1365 1366 1367 1368 1369 1370 1371 1372
	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 */
1373
	fmode_t			s_mode;
L
Linus Torvalds 已提交
1374

1375 1376 1377 1378
	/* Granularity of c/m/atime in ns.
	   Cannot be worse than a second */
	u32		   s_time_gran;

L
Linus Torvalds 已提交
1379 1380 1381 1382
	/*
	 * The next field is for VFS *only*. No filesystems have any business
	 * even looking at it. You had been warned.
	 */
1383
	struct mutex s_vfs_rename_mutex;	/* Kludge */
L
Linus Torvalds 已提交
1384

M
Miklos Szeredi 已提交
1385 1386 1387 1388 1389
	/*
	 * Filesystem subtype.  If non-empty the filesystem type field
	 * in /proc/mounts will be "type.subtype"
	 */
	char *s_subtype;
1390 1391 1392 1393 1394

	/*
	 * Saved mount options for lazy filesystems using
	 * generic_show_options()
	 */
A
Arnd Bergmann 已提交
1395
	char __rcu *s_options;
L
Linus Torvalds 已提交
1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411
};

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)))

1412 1413 1414
#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)
1415

1416
#define is_owner_or_cap(inode)	\
1417
	((current_fsuid() == (inode)->i_uid) || capable(CAP_FOWNER))
1418

1419 1420 1421
/* 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
1422 1423 1424 1425 1426 1427 1428

/*
 * VFS helper functions..
 */
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);
1429
extern int vfs_symlink(struct inode *, struct dentry *, const char *);
L
Linus Torvalds 已提交
1430 1431 1432 1433 1434 1435 1436 1437 1438 1439
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);

1440 1441 1442 1443
/*
 * VFS file helper functions.
 */
extern int file_permission(struct file *, int);
1444 1445
extern void inode_init_owner(struct inode *inode, const struct inode *dir,
			mode_t mode);
M
Mark Fasheh 已提交
1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459
/*
 * VFS FS_IOC_FIEMAP helper definitions.
 */
struct fiemap_extent_info {
	unsigned int fi_flags;		/* Flags as passed from user */
	unsigned int fi_extents_mapped;	/* Number of mapped extents */
	unsigned int fi_extents_max;	/* Size of fiemap_extent array */
	struct fiemap_extent *fi_extents_start; /* Start of fiemap_extent
						 * array */
};
int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical,
			    u64 phys, u64 len, u32 flags);
int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags);

L
Linus Torvalds 已提交
1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481
/*
 * 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

/*
 * 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.
 */
1482
typedef int (*filldir_t)(void *, const char *, int, loff_t, u64, unsigned);
1483
struct block_device_operations;
L
Linus Torvalds 已提交
1484 1485 1486 1487 1488 1489 1490 1491 1492

/* 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:
1493 1494
 * all file operations except setlease can be called without
 * the big kernel lock held in all filesystems.
L
Linus Torvalds 已提交
1495 1496 1497 1498 1499 1500
 */
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 *);
1501 1502
	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
1503 1504 1505 1506 1507 1508
	int (*readdir) (struct file *, void *, filldir_t);
	unsigned int (*poll) (struct file *, struct poll_table_struct *);
	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 *);
1509
	int (*flush) (struct file *, fl_owner_t id);
L
Linus Torvalds 已提交
1510
	int (*release) (struct inode *, struct file *);
1511
	int (*fsync) (struct file *, int datasync);
L
Linus Torvalds 已提交
1512 1513 1514 1515 1516 1517 1518
	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 (*flock) (struct file *, int, struct file_lock *);
1519 1520
	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);
1521
	int (*setlease)(struct file *, long, struct file_lock **);
L
Linus Torvalds 已提交
1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535
};

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);
1536 1537
	void * (*follow_link) (struct dentry *, struct nameidata *);
	void (*put_link) (struct dentry *, struct nameidata *, void *);
L
Linus Torvalds 已提交
1538
	void (*truncate) (struct inode *);
1539
	int (*permission) (struct inode *, int);
1540
	int (*check_acl)(struct inode *, int);
L
Linus Torvalds 已提交
1541 1542 1543 1544 1545 1546
	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 *);
1547
	void (*truncate_range)(struct inode *, loff_t, loff_t);
1548 1549
	long (*fallocate)(struct inode *inode, int mode, loff_t offset,
			  loff_t len);
M
Mark Fasheh 已提交
1550 1551
	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
		      u64 len);
L
Linus Torvalds 已提交
1552 1553 1554 1555
};

struct seq_file;

B
Badari Pulavarty 已提交
1556 1557 1558 1559 1560
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
1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572
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 *);

struct super_operations {
   	struct inode *(*alloc_inode)(struct super_block *sb);
	void (*destroy_inode)(struct inode *);

   	void (*dirty_inode) (struct inode *);
1573
	int (*write_inode) (struct inode *, struct writeback_control *wbc);
1574
	int (*drop_inode) (struct inode *);
A
Al Viro 已提交
1575
	void (*evict_inode) (struct inode *);
L
Linus Torvalds 已提交
1576 1577 1578
	void (*put_super) (struct super_block *);
	void (*write_super) (struct super_block *);
	int (*sync_fs)(struct super_block *sb, int wait);
1579 1580
	int (*freeze_fs) (struct super_block *);
	int (*unfreeze_fs) (struct super_block *);
1581
	int (*statfs) (struct dentry *, struct kstatfs *);
L
Linus Torvalds 已提交
1582
	int (*remount_fs) (struct super_block *, int *, char *);
1583
	void (*umount_begin) (struct super_block *);
L
Linus Torvalds 已提交
1584 1585

	int (*show_options)(struct seq_file *, struct vfsmount *);
1586
	int (*show_stats)(struct seq_file *, struct vfsmount *);
1587
#ifdef CONFIG_QUOTA
L
Linus Torvalds 已提交
1588 1589
	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);
1590
#endif
1591
	int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
L
Linus Torvalds 已提交
1592 1593
};

J
Joern Engel 已提交
1594 1595 1596 1597 1598 1599 1600 1601 1602 1603
/*
 * Inode state bits.  Protected by inode_lock.
 *
 * Three bits determine the dirty state of the inode, I_DIRTY_SYNC,
 * I_DIRTY_DATASYNC and I_DIRTY_PAGES.
 *
 * Four bits define the lifetime of an inode.  Initially, inodes are I_NEW,
 * until that flag is cleared.  I_WILL_FREE, I_FREEING and I_CLEAR are set at
 * various stages of removing an inode.
 *
C
Christoph Hellwig 已提交
1604
 * Two bits are used for locking and completion notification, I_NEW and I_SYNC.
J
Joern Engel 已提交
1605
 *
J
Joern Engel 已提交
1606 1607
 * I_DIRTY_SYNC		Inode is dirty, but doesn't have to be written on
 *			fdatasync().  i_atime is the usual cause.
1608 1609 1610 1611
 * I_DIRTY_DATASYNC	Data-related inode changes pending. We keep track of
 *			these changes separately from I_DIRTY_SYNC so that we
 *			don't have to write inode on fdatasync() when only
 *			mtime has changed in it.
J
Joern Engel 已提交
1612
 * I_DIRTY_PAGES	Inode has dirty pages.  Inode itself may be clean.
C
Christoph Hellwig 已提交
1613 1614 1615 1616 1617 1618 1619 1620
 * I_NEW		Serves as both a mutex and completion notification.
 *			New inodes set I_NEW.  If two processes both create
 *			the same inode, one of them will release its inode and
 *			wait for I_NEW to be released before returning.
 *			Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can
 *			also cause waiting on I_NEW, without I_NEW actually
 *			being set.  find_inode() uses this to prevent returning
 *			nearly-dead inodes.
J
Joern Engel 已提交
1621 1622 1623 1624 1625 1626
 * I_WILL_FREE		Must be set when calling write_inode_now() if i_count
 *			is zero.  I_FREEING must be set when I_WILL_FREE is
 *			cleared.
 * I_FREEING		Set when inode is about to be freed but still has dirty
 *			pages or buffers attached or the inode itself is still
 *			dirty.
1627
 * I_CLEAR		Added by end_writeback().  In this state the inode is clean
A
Al Viro 已提交
1628
 *			and can be destroyed.  Inode keeps I_FREEING.
J
Joern Engel 已提交
1629 1630 1631 1632 1633
 *
 *			Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are
 *			prohibited for many purposes.  iget() must wait for
 *			the inode to be completely released, then create it
 *			anew.  Other functions will just ignore such inodes,
C
Christoph Hellwig 已提交
1634
 *			if appropriate.  I_NEW is used for waiting.
J
Joern Engel 已提交
1635
 *
C
Christoph Hellwig 已提交
1636 1637 1638
 * I_SYNC		Synchonized write of dirty inode data.  The bits is
 *			set during data writeback, and cleared with a wakeup
 *			on the bit address once it is done.
J
Joern Engel 已提交
1639 1640 1641 1642 1643 1644
 *
 * Q: What is the difference between I_WILL_FREE and I_FREEING?
 */
#define I_DIRTY_SYNC		1
#define I_DIRTY_DATASYNC	2
#define I_DIRTY_PAGES		4
C
Christoph Hellwig 已提交
1645 1646
#define __I_NEW			3
#define I_NEW			(1 << __I_NEW)
J
Joern Engel 已提交
1647 1648 1649
#define I_WILL_FREE		16
#define I_FREEING		32
#define I_CLEAR			64
C
Christoph Hellwig 已提交
1650
#define __I_SYNC		7
J
Joern Engel 已提交
1651
#define I_SYNC			(1 << __I_SYNC)
L
Linus Torvalds 已提交
1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665

#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
1666 1667 1668 1669 1670 1671 1672 1673
/**
 * 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().
 */
1674
static inline void inc_nlink(struct inode *inode)
1675 1676
{
	inode->i_nlink++;
1677 1678 1679 1680 1681
}

static inline void inode_inc_link_count(struct inode *inode)
{
	inc_nlink(inode);
1682 1683 1684
	mark_inode_dirty(inode);
}

D
Dave Hansen 已提交
1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695
/**
 * 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.
 */
1696
static inline void drop_nlink(struct inode *inode)
1697 1698
{
	inode->i_nlink--;
1699 1700
}

D
Dave Hansen 已提交
1701 1702 1703 1704 1705 1706 1707 1708
/**
 * 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.
 */
1709 1710 1711 1712 1713
static inline void clear_nlink(struct inode *inode)
{
	inode->i_nlink = 0;
}

1714 1715 1716
static inline void inode_dec_link_count(struct inode *inode)
{
	drop_nlink(inode);
1717 1718 1719
	mark_inode_dirty(inode);
}

1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734
/**
 * inode_inc_iversion - increments i_version
 * @inode: inode that need to be updated
 *
 * Every time the inode is modified, the i_version field will be incremented.
 * The filesystem has to be mounted with i_version flag
 */

static inline void inode_inc_iversion(struct inode *inode)
{
       spin_lock(&inode->i_lock);
       inode->i_version++;
       spin_unlock(&inode->i_lock);
}

C
Christoph Hellwig 已提交
1735
extern void touch_atime(struct vfsmount *mnt, struct dentry *dentry);
L
Linus Torvalds 已提交
1736 1737 1738
static inline void file_accessed(struct file *file)
{
	if (!(file->f_flags & O_NOATIME))
1739
		touch_atime(file->f_path.mnt, file->f_path.dentry);
L
Linus Torvalds 已提交
1740 1741 1742 1743 1744 1745 1746
}

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

struct file_system_type {
	const char *name;
	int fs_flags;
1747 1748
	int (*get_sb) (struct file_system_type *, int,
		       const char *, void *, struct vfsmount *);
L
Linus Torvalds 已提交
1749 1750 1751 1752
	void (*kill_sb) (struct super_block *);
	struct module *owner;
	struct file_system_type * next;
	struct list_head fs_supers;
1753

I
Ingo Molnar 已提交
1754
	struct lock_class_key s_lock_key;
1755
	struct lock_class_key s_umount_key;
1756
	struct lock_class_key s_vfs_rename_key;
1757 1758 1759

	struct lock_class_key i_lock_key;
	struct lock_class_key i_mutex_key;
1760
	struct lock_class_key i_mutex_dir_key;
1761
	struct lock_class_key i_alloc_sem_key;
L
Linus Torvalds 已提交
1762 1763
};

1764 1765 1766
extern int get_sb_ns(struct file_system_type *fs_type, int flags, void *data,
	int (*fill_super)(struct super_block *, void *, int),
	struct vfsmount *mnt);
1767
extern int get_sb_bdev(struct file_system_type *fs_type,
L
Linus Torvalds 已提交
1768
	int flags, const char *dev_name, void *data,
1769 1770 1771
	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
1772
	int flags, void *data,
1773 1774 1775
	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
1776
	int flags, void *data,
1777 1778
	int (*fill_super)(struct super_block *, void *, int),
	struct vfsmount *mnt);
L
Linus Torvalds 已提交
1779 1780 1781 1782 1783
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);
A
Al Viro 已提交
1784
void deactivate_locked_super(struct super_block *sb);
L
Linus Torvalds 已提交
1785 1786 1787 1788 1789
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);
1790
extern int get_sb_pseudo(struct file_system_type *, char *,
1791
	const struct super_operations *ops, unsigned long,
1792
	struct vfsmount *mnt);
1793
extern void simple_set_mnt(struct vfsmount *mnt, struct super_block *sb);
L
Linus Torvalds 已提交
1794

1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807
static inline void sb_mark_dirty(struct super_block *sb)
{
	sb->s_dirt = 1;
}
static inline void sb_mark_clean(struct super_block *sb)
{
	sb->s_dirt = 0;
}
static inline int sb_is_dirty(struct super_block *sb)
{
	return sb->s_dirt;
}

L
Linus Torvalds 已提交
1808 1809 1810 1811 1812 1813 1814 1815
/* 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 *);
1816 1817
extern struct vfsmount *kern_mount_data(struct file_system_type *, void *data);
#define kern_mount(type) kern_mount_data(type, NULL)
L
Linus Torvalds 已提交
1818 1819 1820
extern int may_umount_tree(struct vfsmount *);
extern int may_umount(struct vfsmount *);
extern long do_mount(char *, char *, char *, unsigned long, void *);
A
Al Viro 已提交
1821
extern struct vfsmount *collect_mounts(struct path *);
1822
extern void drop_collected_mounts(struct vfsmount *);
A
Al Viro 已提交
1823 1824
extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *,
			  struct vfsmount *);
1825 1826
extern int vfs_statfs(struct path *, struct kstatfs *);
extern int statfs_by_dentry(struct dentry *, struct kstatfs *);
1827 1828
extern int freeze_super(struct super_block *super);
extern int thaw_super(struct super_block *super);
L
Linus Torvalds 已提交
1829

A
Al Viro 已提交
1830 1831
extern int current_umask(void);

M
Miklos Szeredi 已提交
1832
/* /sys/fs */
1833
extern struct kobject *fs_kobj;
M
Miklos Szeredi 已提交
1834

1835 1836
extern int rw_verify_area(int, struct file *, loff_t *, size_t);

L
Linus Torvalds 已提交
1837 1838 1839
#define FLOCK_VERIFY_READ  1
#define FLOCK_VERIFY_WRITE 2

1840
#ifdef CONFIG_FILE_LOCKING
L
Linus Torvalds 已提交
1841 1842 1843 1844 1845 1846 1847
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.
 */
1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862

static inline int __mandatory_lock(struct inode *ino)
{
	return (ino->i_mode & (S_ISGID | S_IXGRP)) == S_ISGID;
}

/*
 * ... and these candidates should be on MS_MANDLOCK mounted fs,
 * otherwise these will be advisory locks
 */

static inline int mandatory_lock(struct inode *ino)
{
	return IS_MANDLOCK(ino) && __mandatory_lock(ino);
}
L
Linus Torvalds 已提交
1863 1864 1865

static inline int locks_verify_locked(struct inode *inode)
{
1866
	if (mandatory_lock(inode))
L
Linus Torvalds 已提交
1867 1868 1869 1870 1871 1872 1873 1874
		return locks_mandatory_locked(inode);
	return 0;
}

static inline int locks_verify_truncate(struct inode *inode,
				    struct file *filp,
				    loff_t size)
{
1875
	if (inode->i_flock && mandatory_lock(inode))
L
Linus Torvalds 已提交
1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890
		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;
}
1891
#else /* !CONFIG_FILE_LOCKING */
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
static inline int locks_mandatory_locked(struct inode *inode)
{
	return 0;
}

static inline int locks_mandatory_area(int rw, struct inode *inode,
				       struct file *filp, loff_t offset,
				       size_t count)
{
	return 0;
}

static inline int __mandatory_lock(struct inode *inode)
{
	return 0;
}

static inline int mandatory_lock(struct inode *inode)
{
	return 0;
}

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

static inline int locks_verify_truncate(struct inode *inode, struct file *filp,
					size_t size)
{
	return 0;
}

static inline int break_lease(struct inode *inode, unsigned int mode)
{
	return 0;
}

1930
#endif /* CONFIG_FILE_LOCKING */
L
Linus Torvalds 已提交
1931 1932 1933

/* fs/open.c */

1934 1935
extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs,
		       struct file *filp);
1936 1937
extern int do_fallocate(struct file *file, int mode, loff_t offset,
			loff_t len);
J
Jason Uhlenkott 已提交
1938
extern long do_sys_open(int dfd, const char __user *filename, int flags,
1939
			int mode);
L
Linus Torvalds 已提交
1940
extern struct file *filp_open(const char *, int, int);
1941 1942
extern struct file * dentry_open(struct dentry *, struct vfsmount *, int,
				 const struct cred *);
L
Linus Torvalds 已提交
1943 1944 1945
extern int filp_close(struct file *, fl_owner_t id);
extern char * getname(const char __user *);

1946 1947 1948 1949
/* fs/ioctl.c */

extern int ioctl_preallocate(struct file *filp, void __user *argp);

L
Linus Torvalds 已提交
1950 1951 1952 1953
/* fs/dcache.c */
extern void __init vfs_caches_init_early(void);
extern void __init vfs_caches_init(unsigned long);

1954 1955
extern struct kmem_cache *names_cachep;

V
Vegard Nossum 已提交
1956 1957 1958
#define __getname_gfp(gfp)	kmem_cache_alloc(names_cachep, (gfp))
#define __getname()		__getname_gfp(GFP_KERNEL)
#define __putname(name)		kmem_cache_free(names_cachep, (void *)(name))
L
Linus Torvalds 已提交
1959 1960 1961 1962 1963 1964
#ifndef CONFIG_AUDITSYSCALL
#define putname(name)   __putname(name)
#else
extern void putname(const char *name);
#endif

1965
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
1966
extern int register_blkdev(unsigned int, const char *);
A
Akinobu Mita 已提交
1967
extern void unregister_blkdev(unsigned int, const char *);
L
Linus Torvalds 已提交
1968
extern struct block_device *bdget(dev_t);
1969
extern struct block_device *bdgrab(struct block_device *bdev);
L
Linus Torvalds 已提交
1970 1971 1972
extern void bd_set_size(struct block_device *, loff_t size);
extern void bd_forget(struct inode *inode);
extern void bdput(struct block_device *);
1973
extern struct block_device *open_by_devnum(dev_t, fmode_t);
N
Nick Piggin 已提交
1974 1975 1976
extern void invalidate_bdev(struct block_device *);
extern int sync_blockdev(struct block_device *bdev);
extern struct super_block *freeze_bdev(struct block_device *);
1977
extern void emergency_thaw_all(void);
N
Nick Piggin 已提交
1978 1979
extern int thaw_bdev(struct block_device *bdev, struct super_block *sb);
extern int fsync_bdev(struct block_device *);
1980 1981
#else
static inline void bd_forget(struct inode *inode) {}
1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993
static inline int sync_blockdev(struct block_device *bdev) { return 0; }
static inline void invalidate_bdev(struct block_device *bdev) {}

static inline struct super_block *freeze_bdev(struct block_device *sb)
{
	return NULL;
}

static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb)
{
	return 0;
}
1994
#endif
1995
extern int sync_filesystem(struct super_block *);
1996
extern const struct file_operations def_blk_fops;
1997 1998 1999
extern const struct file_operations def_chr_fops;
extern const struct file_operations bad_sock_fops;
extern const struct file_operations def_fifo_fops;
2000
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2001
extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long);
2002
extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long);
L
Linus Torvalds 已提交
2003
extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long);
2004
extern int blkdev_get(struct block_device *, fmode_t);
A
Al Viro 已提交
2005
extern int blkdev_put(struct block_device *, fmode_t);
L
Linus Torvalds 已提交
2006 2007
extern int bd_claim(struct block_device *, void *);
extern void bd_release(struct block_device *);
2008 2009 2010 2011 2012 2013 2014
#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
2015
#endif
L
Linus Torvalds 已提交
2016 2017

/* fs/char_dev.c */
2018
#define CHRDEV_MAJOR_HASH_SIZE	255
L
Linus Torvalds 已提交
2019 2020
extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *);
extern int register_chrdev_region(dev_t, unsigned, const char *);
2021 2022 2023 2024 2025
extern int __register_chrdev(unsigned int major, unsigned int baseminor,
			     unsigned int count, const char *name,
			     const struct file_operations *fops);
extern void __unregister_chrdev(unsigned int major, unsigned int baseminor,
				unsigned int count, const char *name);
L
Linus Torvalds 已提交
2026
extern void unregister_chrdev_region(dev_t, unsigned);
2027
extern void chrdev_show(struct seq_file *,off_t);
L
Linus Torvalds 已提交
2028

2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039
static inline int register_chrdev(unsigned int major, const char *name,
				  const struct file_operations *fops)
{
	return __register_chrdev(major, 0, 256, name, fops);
}

static inline void unregister_chrdev(unsigned int major, const char *name)
{
	__unregister_chrdev(major, 0, 256, name);
}

L
Linus Torvalds 已提交
2040 2041
/* fs/block_dev.c */
#define BDEVNAME_SIZE	32	/* Largest string for a blockdev identifier */
2042
#define BDEVT_SIZE	10	/* Largest string for MAJ:MIN for blkdev */
2043 2044 2045

#ifdef CONFIG_BLOCK
#define BLKDEV_MAJOR_HASH_SIZE	255
L
Linus Torvalds 已提交
2046 2047 2048
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 *);
2049 2050
extern struct block_device *open_bdev_exclusive(const char *, fmode_t, void *);
extern void close_bdev_exclusive(struct block_device *, fmode_t);
2051
extern void blkdev_show(struct seq_file *,off_t);
2052

2053 2054 2055
#else
#define BLKDEV_MAJOR_HASH_SIZE	0
#endif
L
Linus Torvalds 已提交
2056 2057 2058 2059 2060 2061 2062

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 *);

2063 2064 2065
extern const struct file_operations read_pipefifo_fops;
extern const struct file_operations write_pipefifo_fops;
extern const struct file_operations rdwr_pipefifo_fops;
L
Linus Torvalds 已提交
2066 2067 2068

extern int fs_may_remount_ro(struct super_block *);

2069
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2070 2071 2072 2073 2074 2075 2076 2077 2078 2079
/*
 * 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)

2080 2081
extern void check_disk_size_change(struct gendisk *disk,
				   struct block_device *bdev);
2082
extern int revalidate_disk(struct gendisk *);
L
Linus Torvalds 已提交
2083
extern int check_disk_change(struct block_device *);
2084
extern int __invalidate_device(struct block_device *);
L
Linus Torvalds 已提交
2085
extern int invalidate_partition(struct gendisk *, int);
2086 2087
#endif
extern int invalidate_inodes(struct super_block *);
L
Linus Torvalds 已提交
2088 2089
unsigned long invalidate_mapping_pages(struct address_space *mapping,
					pgoff_t start, pgoff_t end);
2090

L
Linus Torvalds 已提交
2091 2092 2093 2094
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))
2095
		invalidate_mapping_pages(inode->i_mapping, 0, -1);
L
Linus Torvalds 已提交
2096 2097 2098 2099 2100 2101 2102 2103
}
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 *);
2104 2105
extern int filemap_fdatawait_range(struct address_space *, loff_t lstart,
				   loff_t lend);
L
Linus Torvalds 已提交
2106 2107 2108
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);
2109 2110
extern int __filemap_fdatawrite_range(struct address_space *mapping,
				loff_t start, loff_t end, int sync_mode);
2111 2112
extern int filemap_fdatawrite_range(struct address_space *mapping,
				loff_t start, loff_t end);
2113

2114 2115 2116
extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end,
			   int datasync);
extern int vfs_fsync(struct file *file, int datasync);
2117
extern int generic_write_sync(struct file *file, loff_t pos, loff_t count);
L
Linus Torvalds 已提交
2118 2119 2120
extern void sync_supers(void);
extern void emergency_sync(void);
extern void emergency_remount(void);
2121
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2122
extern sector_t bmap(struct inode *, sector_t);
2123
#endif
L
Linus Torvalds 已提交
2124
extern int notify_change(struct dentry *, struct iattr *);
2125
extern int inode_permission(struct inode *, int);
L
Linus Torvalds 已提交
2126 2127 2128
extern int generic_permission(struct inode *, int,
		int (*check_acl)(struct inode *, int));

2129 2130 2131 2132 2133
static inline bool execute_ok(struct inode *inode)
{
	return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode);
}

L
Linus Torvalds 已提交
2134 2135 2136 2137 2138 2139 2140 2141 2142
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)
2143
		atomic_inc(&file->f_path.dentry->d_inode->i_writecount);
L
Linus Torvalds 已提交
2144
}
U
Ulrich Drepper 已提交
2145
extern int do_pipe_flags(int *, int);
2146 2147
extern struct file *create_read_pipe(struct file *f, int flags);
extern struct file *create_write_pipe(int flags);
A
Andi Kleen 已提交
2148
extern void free_write_pipe(struct file *);
L
Linus Torvalds 已提交
2149

2150
extern struct file *do_filp_open(int dfd, const char *pathname,
2151
		int open_flag, int mode, int acc_mode);
2152
extern int may_open(struct path *, int, int);
L
Linus Torvalds 已提交
2153

M
Mimi Zohar 已提交
2154
extern int kernel_read(struct file *, loff_t, char *, unsigned long);
L
Linus Torvalds 已提交
2155 2156 2157 2158
extern struct file * open_exec(const char *);
 
/* fs/dcache.c -- generic fs support functions */
extern int is_subdir(struct dentry *, struct dentry *);
2159
extern int path_is_under(struct path *, struct path *);
L
Linus Torvalds 已提交
2160 2161 2162 2163 2164 2165 2166 2167 2168
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);

2169
extern int inode_init_always(struct super_block *, struct inode *);
L
Linus Torvalds 已提交
2170
extern void inode_init_once(struct inode *);
2171
extern void inode_add_to_lists(struct super_block *, struct inode *);
L
Linus Torvalds 已提交
2172 2173 2174 2175
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);
2176 2177
extern int generic_delete_inode(struct inode *inode);
extern int generic_drop_inode(struct inode *inode);
L
Linus Torvalds 已提交
2178

2179 2180 2181
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
2182 2183 2184 2185 2186 2187
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);
A
Al Viro 已提交
2188 2189
extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *);
extern int insert_inode_locked(struct inode *);
L
Linus Torvalds 已提交
2190 2191 2192
extern void unlock_new_inode(struct inode *);

extern void __iget(struct inode * inode);
2193
extern void iget_failed(struct inode *);
A
Al Viro 已提交
2194
extern void end_writeback(struct inode *);
L
Linus Torvalds 已提交
2195
extern void destroy_inode(struct inode *);
C
Christoph Hellwig 已提交
2196
extern void __destroy_inode(struct inode *);
L
Linus Torvalds 已提交
2197
extern struct inode *new_inode(struct super_block *);
2198
extern int should_remove_suid(struct dentry *);
2199
extern int file_remove_suid(struct file *);
L
Linus Torvalds 已提交
2200 2201 2202 2203 2204 2205 2206

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);
}

2207
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2208 2209
extern void submit_bio(int, struct bio *);
extern int bdev_read_only(struct block_device *);
2210
#endif
L
Linus Torvalds 已提交
2211 2212 2213 2214 2215 2216 2217 2218
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);
int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk);
2219
extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t);
2220 2221
extern ssize_t __generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long,
		loff_t *);
2222
extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t);
L
Linus Torvalds 已提交
2223 2224 2225 2226 2227 2228
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);
2229 2230
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
2231

2232 2233 2234
/* fs/block_dev.c */
extern ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
				unsigned long nr_segs, loff_t pos);
2235
extern int blkdev_fsync(struct file *filp, int datasync);
2236

A
Andrew Morton 已提交
2237
/* fs/splice.c */
2238
extern ssize_t generic_file_splice_read(struct file *, loff_t *,
A
Andrew Morton 已提交
2239
		struct pipe_inode_info *, size_t, unsigned int);
2240 2241
extern ssize_t default_file_splice_read(struct file *, loff_t *,
		struct pipe_inode_info *, size_t, unsigned int);
A
Andrew Morton 已提交
2242
extern ssize_t generic_file_splice_write(struct pipe_inode_info *,
2243
		struct file *, loff_t *, size_t, unsigned int);
A
Andrew Morton 已提交
2244
extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
2245 2246
		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
2247 2248
		size_t len, unsigned int flags);

L
Linus Torvalds 已提交
2249 2250
extern void
file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping);
J
jan Blunck 已提交
2251
extern loff_t noop_llseek(struct file *file, loff_t offset, int origin);
L
Linus Torvalds 已提交
2252 2253
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);
A
Andi Kleen 已提交
2254 2255
extern loff_t generic_file_llseek_unlocked(struct file *file, loff_t offset,
			int origin);
L
Linus Torvalds 已提交
2256 2257 2258
extern int generic_file_open(struct inode * inode, struct file * filp);
extern int nonseekable_open(struct inode * inode, struct file * filp);

2259
#ifdef CONFIG_FS_XIP
2260 2261
extern ssize_t xip_file_read(struct file *filp, char __user *buf, size_t len,
			     loff_t *ppos);
2262
extern int xip_file_mmap(struct file * file, struct vm_area_struct * vma);
2263 2264
extern ssize_t xip_file_write(struct file *filp, const char __user *buf,
			      size_t len, loff_t *ppos);
2265
extern int xip_truncate_page(struct address_space *mapping, loff_t from);
2266 2267 2268 2269 2270
#else
static inline int xip_truncate_page(struct address_space *mapping, loff_t from)
{
	return 0;
}
2271 2272
#endif

2273
#ifdef CONFIG_BLOCK
2274 2275
typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode,
			    loff_t file_offset);
L
Linus Torvalds 已提交
2276 2277

enum {
2278 2279 2280 2281 2282
	/* need locking between buffered and direct access */
	DIO_LOCKING	= 0x01,

	/* filesystem does not support filling holes */
	DIO_SKIP_HOLES	= 0x02,
L
Linus Torvalds 已提交
2283 2284
};

2285 2286 2287 2288 2289 2290
void dio_end_io(struct bio *bio, int error);

ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
	struct block_device *bdev, const struct iovec *iov, loff_t offset,
	unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io,
	dio_submit_t submit_io,	int flags);
2291

L
Linus Torvalds 已提交
2292 2293
static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb,
	struct inode *inode, struct block_device *bdev, const struct iovec *iov,
2294
	loff_t offset, unsigned long nr_segs, get_block_t get_block,
L
Linus Torvalds 已提交
2295 2296 2297
	dio_iodone_t end_io)
{
	return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
2298
				    nr_segs, get_block, end_io, NULL,
2299
				    DIO_LOCKING | DIO_SKIP_HOLES);
L
Linus Torvalds 已提交
2300
}
2301
#endif
L
Linus Torvalds 已提交
2302

2303
extern const struct file_operations generic_ro_fops;
L
Linus Torvalds 已提交
2304 2305 2306 2307 2308 2309

#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);
2310 2311
extern void *page_follow_link_light(struct dentry *, struct nameidata *);
extern void page_put_link(struct dentry *, struct nameidata *, void *);
2312
extern int __page_symlink(struct inode *inode, const char *symname, int len,
2313
		int nofs);
L
Linus Torvalds 已提交
2314
extern int page_symlink(struct inode *inode, const char *symname, int len);
2315
extern const struct inode_operations page_symlink_inode_operations;
L
Linus Torvalds 已提交
2316 2317 2318
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 *);
2319
void __inode_add_bytes(struct inode *inode, loff_t bytes);
L
Linus Torvalds 已提交
2320 2321 2322 2323 2324 2325 2326
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 *);

2327 2328
extern int vfs_stat(const char __user *, struct kstat *);
extern int vfs_lstat(const char __user *, struct kstat *);
L
Linus Torvalds 已提交
2329
extern int vfs_fstat(unsigned int, struct kstat *);
2330
extern int vfs_fstatat(int , const char __user *, struct kstat *, int);
L
Linus Torvalds 已提交
2331

2332 2333
extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
		    unsigned long arg);
2334
extern int __generic_block_fiemap(struct inode *inode,
J
Josef Bacik 已提交
2335 2336 2337
				  struct fiemap_extent_info *fieinfo,
				  loff_t start, loff_t len,
				  get_block_t *get_block);
2338 2339 2340
extern int generic_block_fiemap(struct inode *inode,
				struct fiemap_extent_info *fieinfo, u64 start,
				u64 len, get_block_t *get_block);
L
Linus Torvalds 已提交
2341

2342 2343
extern void get_filesystem(struct file_system_type *fs);
extern void put_filesystem(struct file_system_type *fs);
L
Linus Torvalds 已提交
2344 2345
extern struct file_system_type *get_fs_type(const char *name);
extern struct super_block *get_super(struct block_device *);
2346
extern struct super_block *get_active_super(struct block_device *bdev);
L
Linus Torvalds 已提交
2347 2348
extern struct super_block *user_get_super(dev_t);
extern void drop_super(struct super_block *sb);
A
Al Viro 已提交
2349
extern void iterate_supers(void (*)(struct super_block *, void *), void *);
L
Linus Torvalds 已提交
2350 2351 2352 2353 2354

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);
2355
extern int simple_setattr(struct dentry *, struct iattr *);
L
Linus Torvalds 已提交
2356
extern int simple_getattr(struct vfsmount *, struct dentry *, struct kstat *);
2357
extern int simple_statfs(struct dentry *, struct kstatfs *);
L
Linus Torvalds 已提交
2358 2359 2360 2361
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 *);
2362
extern int noop_fsync(struct file *, int);
L
Linus Torvalds 已提交
2363 2364
extern int simple_empty(struct dentry *);
extern int simple_readpage(struct file *file, struct page *page);
2365 2366 2367 2368 2369 2370
extern int simple_write_begin(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned flags,
			struct page **pagep, void **fsdata);
extern int simple_write_end(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned copied,
			struct page *page, void *fsdata);
L
Linus Torvalds 已提交
2371 2372 2373

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 *);
2374
extern const struct file_operations simple_dir_operations;
2375
extern const struct inode_operations simple_dir_inode_operations;
2376
struct tree_descr { char *name; const struct file_operations *ops; int mode; };
L
Linus Torvalds 已提交
2377
struct dentry *d_alloc_name(struct dentry *, const char *);
2378
extern int simple_fill_super(struct super_block *, unsigned long, struct tree_descr *);
2379
extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count);
L
Linus Torvalds 已提交
2380 2381
extern void simple_release_fs(struct vfsmount **mount, int *count);

2382 2383
extern ssize_t simple_read_from_buffer(void __user *to, size_t count,
			loff_t *ppos, const void *from, size_t available);
2384 2385
extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos,
		const void __user *from, size_t count);
L
Linus Torvalds 已提交
2386

2387
extern int generic_file_fsync(struct file *, int);
A
Al Viro 已提交
2388

2389 2390
extern int generic_check_addressable(unsigned, u64);

2391
#ifdef CONFIG_MIGRATION
2392 2393
extern int buffer_migrate_page(struct address_space *,
				struct page *, struct page *);
2394 2395 2396 2397
#else
#define buffer_migrate_page NULL
#endif

N
npiggin@suse.de 已提交
2398 2399
extern int inode_change_ok(const struct inode *, struct iattr *);
extern int inode_newsize_ok(const struct inode *, loff_t offset);
C
Christoph Hellwig 已提交
2400
extern void setattr_copy(struct inode *inode, const struct iattr *attr);
L
Linus Torvalds 已提交
2401

2402
extern void file_update_time(struct file *file);
L
Linus Torvalds 已提交
2403

2404 2405
extern int generic_show_options(struct seq_file *m, struct vfsmount *mnt);
extern void save_mount_options(struct super_block *sb, char *options);
2406
extern void replace_mount_options(struct super_block *sb, char *options);
2407

L
Linus Torvalds 已提交
2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436
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;
}

/* 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);

2437
void simple_transaction_set(struct file *file, size_t n);
L
Linus Torvalds 已提交
2438

2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460
/*
 * 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);	\
}									\
2461
static const struct file_operations __fops = {				\
2462 2463
	.owner	 = THIS_MODULE,						\
	.open	 = __fops ## _open,					\
2464
	.release = simple_attr_release,					\
2465 2466
	.read	 = simple_attr_read,					\
	.write	 = simple_attr_write,					\
2467
	.llseek	 = generic_file_llseek,					\
2468 2469 2470 2471 2472 2473 2474 2475 2476
};

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,
2477
		     int (*get)(void *, u64 *), int (*set)(void *, u64),
2478
		     const char *fmt);
2479
int simple_attr_release(struct inode *inode, struct file *file);
2480 2481 2482 2483 2484
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);

A
Alexey Dobriyan 已提交
2485
struct ctl_table;
2486
int proc_nr_files(struct ctl_table *table, int write,
2487 2488
		  void __user *buffer, size_t *lenp, loff_t *ppos);

2489
int __init get_filesystem_list(char *buf);
2490

A
Al Viro 已提交
2491
#define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE])
E
Eric Paris 已提交
2492 2493
#define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \
					    (flag & FMODE_NONOTIFY)))
A
Al Viro 已提交
2494

L
Linus Torvalds 已提交
2495 2496
#endif /* __KERNEL__ */
#endif /* _LINUX_FS_H */