fs.h 83.9 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28
#ifndef _LINUX_FS_H
#define _LINUX_FS_H

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

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

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

/* Fixed constants first: */
#undef NR_OPEN
#define INR_OPEN 1024		/* Initial setting for nfile rlimits */

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

29 30 31
#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 */
32
#define SEEK_MAX	SEEK_END
33

L
Linus Torvalds 已提交
34 35 36 37 38 39 40 41 42 43
/* 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;
44
	int dummy[5];		/* padding for sysctl ABI compatibility */
L
Linus Torvalds 已提交
45 46 47 48 49 50 51 52 53
};


#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
54
#define MAY_ACCESS 16
55
#define MAY_OPEN 32
L
Linus Torvalds 已提交
56

57 58 59 60 61
/*
 * 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()
 */

62 63 64 65 66 67
/* file is open for reading */
#define FMODE_READ		((__force fmode_t)1)
/* file is open for writing */
#define FMODE_WRITE		((__force fmode_t)2)
/* file is seekable */
#define FMODE_LSEEK		((__force fmode_t)4)
68
/* file can be accessed using pread */
69
#define FMODE_PREAD		((__force fmode_t)8)
70 71
/* file can be accessed using pwrite */
#define FMODE_PWRITE		((__force fmode_t)16)
72
/* File is opened for execution with sys_execve / sys_uselib */
73
#define FMODE_EXEC		((__force fmode_t)32)
74
/* File is opened with O_NDELAY (only set for block devices) */
75
#define FMODE_NDELAY		((__force fmode_t)64)
76
/* File is opened with O_EXCL (only set for block devices) */
77
#define FMODE_EXCL		((__force fmode_t)128)
78 79
/* File is opened using open(.., 3, ..) and is writeable only for ioctls
   (specialy hack for floppy.c) */
80
#define FMODE_WRITE_IOCTL	((__force fmode_t)256)
81

82 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.
 */
#define FMODE_NOCMTIME		((__force fmode_t)2048)

90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143
/*
 * 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
 *			 block layer could (in theory) choose to ignore this
 *			request if it runs into resource problems.
 * WRITE		A normal async write. Device will be plugged.
 * SWRITE		Like WRITE, but a special case for ll_rw_block() that
 *			tells it to lock the buffer first. Normally a buffer
 *			must be locked before doing IO.
 * 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.
 * WRITE_ODIRECT	Special case write for O_DIRECT only.
 * SWRITE_SYNC
 * SWRITE_SYNC_PLUG	Like WRITE_SYNC/WRITE_SYNC_PLUG, but locks the buffer.
 *			See SWRITE.
 * WRITE_BARRIER	Like WRITE, but tells the block layer that all
 *			previously submitted writes must be safely on storage
 *			before this one is started. Also guarantees that when
 *			this write is complete, it itself is also safely on
 *			storage. Prevents reordering of writes on both sides
 *			of this IO.
 *
 */
L
Linus Torvalds 已提交
144 145 146 147 148
#define RW_MASK		1
#define RWA_MASK	2
#define READ 0
#define WRITE 1
#define READA 2		/* read-ahead  - don't block if no resources */
149
#define SWRITE 3	/* for ll_rw_block() - wait for buffer lock */
150
#define READ_SYNC	(READ | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG))
151
#define READ_META	(READ | (1 << BIO_RW_META))
152 153 154
#define WRITE_SYNC_PLUG	(WRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE))
#define WRITE_SYNC	(WRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG))
#define WRITE_ODIRECT	(WRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG))
155
#define SWRITE_SYNC_PLUG	\
156 157
			(SWRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE))
#define SWRITE_SYNC	(SWRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG))
D
David Woodhouse 已提交
158
#define WRITE_BARRIER	(WRITE | (1 << BIO_RW_BARRIER))
159 160 161 162 163

/*
 * These aren't really reads or writes, they pass down information about
 * parts of device that are now unused by the file system.
 */
164 165
#define DISCARD_NOBARRIER (1 << BIO_RW_DISCARD)
#define DISCARD_BARRIER ((1 << BIO_RW_DISCARD) | (1 << BIO_RW_BARRIER))
L
Linus Torvalds 已提交
166 167 168 169 170 171 172 173

#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
174
#define FS_HAS_SUBTYPE 4
L
Linus Torvalds 已提交
175
#define FS_REVAL_DOT	16384	/* Check the paths ".", ".." for staleness */
176 177 178 179
#define FS_RENAME_DOES_D_MOVE	32768	/* FS will handle d_move()
					 * during rename() internally.
					 */

L
Linus Torvalds 已提交
180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195
/*
 * 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
196 197 198
#define MS_VERBOSE	32768	/* War is peace. Verbosity is silence.
				   MS_VERBOSE is deprecated. */
#define MS_SILENT	32768
M
Miklos Szeredi 已提交
199
#define MS_POSIXACL	(1<<16)	/* VFS does not apply the umask */
R
Ram Pai 已提交
200
#define MS_UNBINDABLE	(1<<17)	/* change to unbindable */
201
#define MS_PRIVATE	(1<<18)	/* change to private */
R
Ram Pai 已提交
202
#define MS_SLAVE	(1<<19)	/* change to slave */
R
Ram Pai 已提交
203
#define MS_SHARED	(1<<20)	/* change to shared */
V
Valerie Henson 已提交
204
#define MS_RELATIME	(1<<21)	/* Update atime relative to mtime/ctime. */
205
#define MS_KERNMOUNT	(1<<22) /* this is a kern_mount call */
206
#define MS_I_VERSION	(1<<23) /* Update inode I_version field */
M
Matthew Garrett 已提交
207
#define MS_STRICTATIME	(1<<24) /* Always perform atime updates */
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
215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255

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

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

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

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

#define IS_RDONLY(inode) ((inode)->i_sb->s_flags & MS_RDONLY)
#define IS_SYNC(inode)		(__IS_FLG(inode, MS_SYNCHRONOUS) || \
					((inode)->i_flags & S_SYNC))
#define IS_DIRSYNC(inode)	(__IS_FLG(inode, MS_SYNCHRONOUS|MS_DIRSYNC) || \
					((inode)->i_flags & (S_SYNC|S_DIRSYNC)))
#define IS_MANDLOCK(inode)	__IS_FLG(inode, MS_MANDLOCK)
256
#define IS_NOATIME(inode)   __IS_FLG(inode, MS_RDONLY|MS_NOATIME)
257
#define IS_I_VERSION(inode)   __IS_FLG(inode, MS_I_VERSION)
L
Linus Torvalds 已提交
258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297

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

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

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

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

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

#define BLKELVGET  _IOR(0x12,106,size_t)/* elevator get */
#define BLKELVSET  _IOW(0x12,107,size_t)/* elevator set */
/* This was here just to show that the number is taken -
   probably all these _IO(0x12,*) ioctls should be moved to blkpg.h. */
#endif
/* A jump here: 108-111 have been used for various private purposes. */
#define BLKBSZGET  _IOR(0x12,112,size_t)
#define BLKBSZSET  _IOW(0x12,113,size_t)
#define BLKGETSIZE64 _IOR(0x12,114,size_t)	/* return device size in bytes (u64 *arg) */
298 299 300 301
#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)
302
#define BLKDISCARD _IO(0x12,119)
L
Linus Torvalds 已提交
303 304 305 306

#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 */
307 308
#define FIFREEZE	_IOWR('X', 119, int)	/* Freeze */
#define FITHAW		_IOWR('X', 120, int)	/* Thaw */
L
Linus Torvalds 已提交
309

310 311 312 313
#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
314
#define FS_IOC_FIEMAP			_IOWR('f', 11, struct fiemap)
315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343
#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*/
344 345
#define FS_EXTENT_FL			0x00080000 /* Extents */
#define FS_DIRECTIO_FL			0x00100000 /* Use direct i/o */
346 347 348 349 350 351
#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 */


352 353 354 355
#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
356 357 358 359 360 361 362
#ifdef __KERNEL__

#include <linux/linkage.h>
#include <linux/wait.h>
#include <linux/types.h>
#include <linux/kdev_t.h>
#include <linux/dcache.h>
363
#include <linux/path.h>
L
Linus Torvalds 已提交
364 365 366 367 368 369 370
#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>
371
#include <linux/pid.h>
372
#include <linux/mutex.h>
373
#include <linux/capability.h>
374
#include <linux/semaphore.h>
M
Mark Fasheh 已提交
375
#include <linux/fiemap.h>
L
Linus Torvalds 已提交
376 377 378 379

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

380
struct export_operations;
381
struct hd_geometry;
L
Linus Torvalds 已提交
382 383
struct iovec;
struct nameidata;
384
struct kiocb;
L
Linus Torvalds 已提交
385 386 387 388 389
struct pipe_inode_info;
struct poll_table_struct;
struct kstatfs;
struct vm_area_struct;
struct vfsmount;
390
struct cred;
L
Linus Torvalds 已提交
391

392
extern void __init inode_init(void);
L
Linus Torvalds 已提交
393 394 395
extern void __init inode_init_early(void);
extern void __init files_init(unsigned long);

396 397 398 399 400 401 402 403 404
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;
#ifdef CONFIG_DNOTIFY
extern int dir_notify_enable;
#endif

L
Linus Torvalds 已提交
405 406 407
struct buffer_head;
typedef int (get_block_t)(struct inode *inode, sector_t iblock,
			struct buffer_head *bh_result, int create);
408
typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
L
Linus Torvalds 已提交
409 410 411 412 413 414
			ssize_t bytes, void *private);

/*
 * Attribute flags.  These should be or-ed together to figure out what
 * has been changed!
 */
415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431
#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
432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450

/*
 * 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;
451 452 453 454 455 456 457

	/*
	 * 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
458 459 460 461 462 463 464
};

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

465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482
/** 
 * 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
483
 *  			by readpage().
484 485 486 487 488 489 490 491 492 493 494 495
 *
 * 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,
};

496
#define AOP_FLAG_UNINTERRUPTIBLE	0x0001 /* will not do a short write */
N
Nick Piggin 已提交
497
#define AOP_FLAG_CONT_EXPAND		0x0002 /* called from cont_expand */
498 499 500
#define AOP_FLAG_NOFS			0x0004 /* used by filesystem to direct
						* helper code (eg buffer layer)
						* to clear GFP_FS from alloc */
501

L
Linus Torvalds 已提交
502 503 504 505 506 507 508
/*
 * oh the beauties of C type declarations.
 */
struct page;
struct address_space;
struct writeback_control;

N
Nick Piggin 已提交
509 510 511 512 513 514 515 516 517 518 519 520
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);
521
int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes);
N
Nick Piggin 已提交
522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540
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;
}

541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561
/*
 * "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
562

L
Linus Torvalds 已提交
563 564 565
struct address_space_operations {
	int (*writepage)(struct page *page, struct writeback_control *wbc);
	int (*readpage)(struct file *, struct page *);
566
	void (*sync_page)(struct page *);
L
Linus Torvalds 已提交
567 568 569 570

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

571
	/* Set a page dirty.  Return true if this dirtied it */
L
Linus Torvalds 已提交
572 573 574 575 576
	int (*set_page_dirty)(struct page *page);

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

577 578 579 580 581 582 583
	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
584 585
	/* Unfortunately this kludge is needed for FIBMAP. Don't use it */
	sector_t (*bmap)(struct address_space *, sector_t);
586
	void (*invalidatepage) (struct page *, unsigned long);
A
Al Viro 已提交
587
	int (*releasepage) (struct page *, gfp_t);
L
Linus Torvalds 已提交
588 589
	ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
			loff_t offset, unsigned long nr_segs);
590 591
	int (*get_xip_mem)(struct address_space *, pgoff_t, int,
						void **, unsigned long *);
592
	/* migrate the contents of a page to the specified target */
593 594
	int (*migratepage) (struct address_space *,
			struct page *, struct page *);
595
	int (*launder_page) (struct page *);
596 597
	int (*is_partially_uptodate) (struct page *, read_descriptor_t *,
					unsigned long);
L
Linus Torvalds 已提交
598 599
};

600 601 602 603 604 605 606 607 608 609 610 611
/*
 * 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
612 613 614 615
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
616
	spinlock_t		tree_lock;	/* and lock protecting it */
L
Linus Torvalds 已提交
617 618 619 620 621 622 623
	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 */
624
	const struct address_space_operations *a_ops;	/* methods */
L
Linus Torvalds 已提交
625 626 627 628 629 630 631 632 633 634 635 636 637 638 639
	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 */
640
	struct super_block *	bd_super;
L
Linus Torvalds 已提交
641
	int			bd_openers;
642
	struct mutex		bd_mutex;	/* open/close mutex */
643
	struct semaphore	bd_mount_sem;
L
Linus Torvalds 已提交
644 645 646
	struct list_head	bd_inodes;
	void *			bd_holder;
	int			bd_holders;
647 648 649
#ifdef CONFIG_SYSFS
	struct list_head	bd_holder_list;
#endif
L
Linus Torvalds 已提交
650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665
	struct block_device *	bd_contains;
	unsigned		bd_block_size;
	struct hd_struct *	bd_part;
	/* number of times partitions within this device have been opened. */
	unsigned		bd_part_count;
	int			bd_invalidated;
	struct gendisk *	bd_disk;
	struct list_head	bd_list;
	struct backing_dev_info *bd_inode_backing_dev_info;
	/*
	 * Private data.  You must have bd_claim'ed the block_device
	 * to use this.  NOTE:  bd_claim allows an owner to claim
	 * the same device multiple times, the owner must take special
	 * care to not mess up bd_private for that case.
	 */
	unsigned long		bd_private;
666 667 668 669 670

	/* The counter of freeze processes */
	int			bd_fsfreeze_count;
	/* Mutex for freeze */
	struct mutex		bd_fsfreeze_mutex;
L
Linus Torvalds 已提交
671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712
};

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

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

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

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

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

A
Al Viro 已提交
713 714 715
struct posix_acl;
#define ACL_NOT_CACHED ((void *)(-1))

L
Linus Torvalds 已提交
716 717
struct inode {
	struct hlist_node	i_hash;
718
	struct list_head	i_list;		/* backing dev IO list */
L
Linus Torvalds 已提交
719 720 721 722 723 724 725 726
	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;
727
	u64			i_version;
L
Linus Torvalds 已提交
728
	loff_t			i_size;
729 730 731
#ifdef __NEED_I_SIZE_ORDERED
	seqcount_t		i_size_seqcount;
#endif
L
Linus Torvalds 已提交
732 733 734
	struct timespec		i_atime;
	struct timespec		i_mtime;
	struct timespec		i_ctime;
T
Takashi Sato 已提交
735
	blkcnt_t		i_blocks;
736
	unsigned int		i_blkbits;
L
Linus Torvalds 已提交
737
	unsigned short          i_bytes;
738
	umode_t			i_mode;
L
Linus Torvalds 已提交
739
	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
740
	struct mutex		i_mutex;
L
Linus Torvalds 已提交
741
	struct rw_semaphore	i_alloc_sem;
742
	const struct inode_operations	*i_op;
743
	const struct file_operations	*i_fop;	/* former ->i_op->default_file_ops */
L
Linus Torvalds 已提交
744 745 746 747 748 749 750 751
	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;
752 753
	union {
		struct pipe_inode_info	*i_pipe;
754
		struct block_device	*i_bdev;
755
		struct cdev		*i_cdev;
756
	};
L
Linus Torvalds 已提交
757 758 759

	__u32			i_generation;

760 761 762 763 764
#ifdef CONFIG_FSNOTIFY
	__u32			i_fsnotify_mask; /* all events this inode cares about */
	struct hlist_head	i_fsnotify_mark_entries; /* fsnotify mark entries */
#endif

R
Robert Love 已提交
765 766
#ifdef CONFIG_INOTIFY
	struct list_head	inotify_watches; /* watches on this inode */
I
Ingo Molnar 已提交
767
	struct mutex		inotify_mutex;	/* protects the watches list */
R
Robert Love 已提交
768 769
#endif

L
Linus Torvalds 已提交
770 771 772 773 774 775
	unsigned long		i_state;
	unsigned long		dirtied_when;	/* jiffies of first dirtying */

	unsigned int		i_flags;

	atomic_t		i_writecount;
776
#ifdef CONFIG_SECURITY
L
Linus Torvalds 已提交
777
	void			*i_security;
A
Al Viro 已提交
778 779 780 781
#endif
#ifdef CONFIG_FS_POSIX_ACL
	struct posix_acl	*i_acl;
	struct posix_acl	*i_default_acl;
782
#endif
783
	void			*i_private; /* fs or device private pointer */
L
Linus Torvalds 已提交
784 785
};

I
Ingo Molnar 已提交
786 787 788 789 790 791 792 793 794
/*
 * 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
795
 * parent -> child -> normal -> xattr -> quota
I
Ingo Molnar 已提交
796 797 798 799 800 801
 */
enum inode_i_mutex_lock_class
{
	I_MUTEX_NORMAL,
	I_MUTEX_PARENT,
	I_MUTEX_CHILD,
I
Ingo Molnar 已提交
802
	I_MUTEX_XATTR,
I
Ingo Molnar 已提交
803 804 805
	I_MUTEX_QUOTA
};

L
Linus Torvalds 已提交
806 807 808 809 810 811 812 813 814 815
/*
 * 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
816
static inline loff_t i_size_read(const struct inode *inode)
L
Linus Torvalds 已提交
817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838
{
#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
}

839 840 841 842 843
/*
 * 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
844 845 846 847 848 849 850 851 852 853 854 855 856 857 858
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
859
static inline unsigned iminor(const struct inode *inode)
L
Linus Torvalds 已提交
860 861 862 863
{
	return MINOR(inode->i_rdev);
}

J
Jan Engelhardt 已提交
864
static inline unsigned imajor(const struct inode *inode)
L
Linus Torvalds 已提交
865 866 867 868 869 870 871 872
{
	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 */
873 874
	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
875 876 877 878 879 880 881 882
	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
883 884 885
	pgoff_t start;			/* where readahead started */
	unsigned int size;		/* # of readahead pages */
	unsigned int async_size;	/* do asynchronous readahead when
886
					   there are only # of pages ahead */
887

F
Fengguang Wu 已提交
888
	unsigned int ra_pages;		/* Maximum readahead window */
889
	unsigned int mmap_miss;		/* Cache miss stat for mmap accesses */
890
	loff_t prev_pos;		/* Cache last read() position */
L
Linus Torvalds 已提交
891 892
};

893 894 895 896 897
/*
 * Check if @index falls in the readahead windows.
 */
static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
{
898 899
	return (index >= ra->start &&
		index <  ra->start + ra->size);
900 901
}

902 903 904
#define FILE_MNT_WRITE_TAKEN	1
#define FILE_MNT_WRITE_RELEASED	2

L
Linus Torvalds 已提交
905
struct file {
E
Eric Dumazet 已提交
906 907 908 909 910 911 912 913
	/*
	 * 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;
914 915 916
	struct path		f_path;
#define f_dentry	f_path.dentry
#define f_vfsmnt	f_path.mnt
917
	const struct file_operations	*f_op;
918
	spinlock_t		f_lock;  /* f_ep_links, f_flags, no IRQ */
A
Al Viro 已提交
919
	atomic_long_t		f_count;
L
Linus Torvalds 已提交
920
	unsigned int 		f_flags;
921
	fmode_t			f_mode;
L
Linus Torvalds 已提交
922 923
	loff_t			f_pos;
	struct fown_struct	f_owner;
D
David Howells 已提交
924
	const struct cred	*f_cred;
L
Linus Torvalds 已提交
925 926
	struct file_ra_state	f_ra;

927
	u64			f_version;
928
#ifdef CONFIG_SECURITY
L
Linus Torvalds 已提交
929
	void			*f_security;
930
#endif
L
Linus Torvalds 已提交
931 932 933 934 935 936 937 938
	/* 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;
939 940 941
#ifdef CONFIG_DEBUG_WRITECOUNT
	unsigned long f_mnt_write_state;
#endif
L
Linus Torvalds 已提交
942 943 944 945 946
};
extern spinlock_t files_lock;
#define file_list_lock() spin_lock(&files_lock);
#define file_list_unlock() spin_unlock(&files_lock);

A
Al Viro 已提交
947 948
#define get_file(x)	atomic_long_inc(&(x)->f_count)
#define file_count(x)	atomic_long_read(&(x)->f_count)
L
Linus Torvalds 已提交
949

950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992
#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
993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005
#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 */
1006
#define FL_EXISTS	16	/* when unlocking, test for existence */
L
Linus Torvalds 已提交
1007
#define FL_LEASE	32	/* lease held on this file */
1008
#define FL_CLOSE	64	/* unlock on close */
L
Linus Torvalds 已提交
1009 1010
#define FL_SLEEP	128	/* A blocking lock */

1011 1012 1013 1014 1015 1016
/*
 * 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
1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033
/*
 * 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 */
1034
	int (*fl_grant)(struct file_lock *, struct file_lock *, int);
L
Linus Torvalds 已提交
1035 1036 1037 1038 1039 1040 1041
	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);
};

1042 1043 1044 1045 1046 1047 1048 1049
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
1050 1051 1052 1053 1054 1055 1056 1057
/* 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;
1058 1059
	unsigned char fl_flags;
	unsigned char fl_type;
L
Linus Torvalds 已提交
1060
	unsigned int fl_pid;
1061
	struct pid *fl_nspid;
L
Linus Torvalds 已提交
1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073
	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 */

	struct file_lock_operations *fl_ops;	/* Callbacks for filesystems */
	struct lock_manager_operations *fl_lmops;	/* Callbacks for lockmanagers */
	union {
		struct nfs_lock_info	nfs_fl;
1074
		struct nfs4_lock_info	nfs4_fl;
D
David Howells 已提交
1075 1076 1077 1078
		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
1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090
	} 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>

1091 1092 1093 1094 1095 1096 1097
extern void send_sigio(struct fown_struct *fown, int fd, int band);

/* fs/sync.c */
extern int do_sync_mapping_range(struct address_space *mapping, loff_t offset,
			loff_t endbyte, unsigned int flags);

#ifdef CONFIG_FILE_LOCKING
L
Linus Torvalds 已提交
1098
extern int fcntl_getlk(struct file *, struct flock __user *);
1099 1100
extern int fcntl_setlk(unsigned int, struct file *, unsigned int,
			struct flock __user *);
L
Linus Torvalds 已提交
1101 1102 1103

#if BITS_PER_LONG == 32
extern int fcntl_getlk64(struct file *, struct flock64 __user *);
1104 1105
extern int fcntl_setlk64(unsigned int, struct file *, unsigned int,
			struct flock64 __user *);
L
Linus Torvalds 已提交
1106 1107 1108 1109 1110 1111 1112 1113
#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 *);
1114
extern void __locks_copy_lock(struct file_lock *, const struct file_lock *);
L
Linus Torvalds 已提交
1115 1116
extern void locks_remove_posix(struct file *, fl_owner_t);
extern void locks_remove_flock(struct file *);
1117
extern void locks_release_private(struct file_lock *);
1118
extern void posix_test_lock(struct file *, struct file_lock *);
1119
extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *);
L
Linus Torvalds 已提交
1120
extern int posix_lock_file_wait(struct file *, struct file_lock *);
J
J. Bruce Fields 已提交
1121
extern int posix_unblock_lock(struct file *, struct file_lock *);
1122
extern int vfs_test_lock(struct file *, struct file_lock *);
1123
extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *);
M
Marc Eshel 已提交
1124
extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
L
Linus Torvalds 已提交
1125 1126 1127
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);
1128
extern int generic_setlease(struct file *, long, struct file_lock **);
1129
extern int vfs_setlease(struct file *, long, struct file_lock **);
L
Linus Torvalds 已提交
1130 1131 1132
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);
1133
#else /* !CONFIG_FILE_LOCKING */
1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144
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;
}

1145
#if BITS_PER_LONG == 32
1146 1147 1148 1149 1150 1151 1152 1153 1154 1155
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;
}
1156
#endif
1157 1158 1159 1160 1161 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
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;
}

1275 1276
#endif /* !CONFIG_FILE_LOCKING */

L
Linus Torvalds 已提交
1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293

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

#define FASYNC_MAGIC 0x4601

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

1294
extern int __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
L
Linus Torvalds 已提交
1295 1296
extern int f_setown(struct file *filp, unsigned long arg, int force);
extern void f_delown(struct file *filp);
1297
extern pid_t f_getown(struct file *filp);
L
Linus Torvalds 已提交
1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310
extern int send_sigurg(struct fown_struct *fown);

/*
 *	Umount options
 */

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

extern struct list_head super_blocks;
extern spinlock_t sb_lock;

1311
#define sb_entry(list)  list_entry((list), struct super_block, s_list)
L
Linus Torvalds 已提交
1312 1313 1314 1315 1316 1317 1318 1319 1320
#define S_BIAS (1<<30)
struct super_block {
	struct list_head	s_list;		/* Keep this first */
	dev_t			s_dev;		/* search index; _not_ kdev_t */
	unsigned long		s_blocksize;
	unsigned char		s_blocksize_bits;
	unsigned char		s_dirt;
	unsigned long long	s_maxbytes;	/* Max file size */
	struct file_system_type	*s_type;
1321
	const struct super_operations	*s_op;
L
Linus Torvalds 已提交
1322 1323
	struct dquot_operations	*dq_op;
 	struct quotactl_ops	*s_qcop;
1324
	const struct export_operations *s_export_op;
L
Linus Torvalds 已提交
1325 1326 1327 1328
	unsigned long		s_flags;
	unsigned long		s_magic;
	struct dentry		*s_root;
	struct rw_semaphore	s_umount;
1329
	struct mutex		s_lock;
L
Linus Torvalds 已提交
1330
	int			s_count;
1331
	int			s_need_sync;
L
Linus Torvalds 已提交
1332
	atomic_t		s_active;
1333
#ifdef CONFIG_SECURITY
L
Linus Torvalds 已提交
1334
	void                    *s_security;
1335
#endif
L
Linus Torvalds 已提交
1336 1337 1338 1339 1340
	struct xattr_handler	**s_xattr;

	struct list_head	s_inodes;	/* all inodes */
	struct hlist_head	s_anon;		/* anonymous dentries for (nfs) exporting */
	struct list_head	s_files;
1341 1342 1343
	/* 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
1344 1345

	struct block_device	*s_bdev;
1346
	struct mtd_info		*s_mtd;
L
Linus Torvalds 已提交
1347 1348 1349 1350 1351 1352 1353 1354 1355
	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 */
1356
	fmode_t			s_mode;
L
Linus Torvalds 已提交
1357 1358 1359 1360 1361

	/*
	 * The next field is for VFS *only*. No filesystems have any business
	 * even looking at it. You had been warned.
	 */
1362
	struct mutex s_vfs_rename_mutex;	/* Kludge */
L
Linus Torvalds 已提交
1363

1364
	/* Granularity of c/m/atime in ns.
L
Linus Torvalds 已提交
1365 1366
	   Cannot be worse than a second */
	u32		   s_time_gran;
M
Miklos Szeredi 已提交
1367 1368 1369 1370 1371 1372

	/*
	 * Filesystem subtype.  If non-empty the filesystem type field
	 * in /proc/mounts will be "type.subtype"
	 */
	char *s_subtype;
1373 1374 1375 1376 1377 1378

	/*
	 * Saved mount options for lazy filesystems using
	 * generic_show_options()
	 */
	char *s_options;
L
Linus Torvalds 已提交
1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394
};

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)))

1395 1396 1397
#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)
1398

1399
#define is_owner_or_cap(inode)	\
1400
	((current_fsuid() == (inode)->i_uid) || capable(CAP_FOWNER))
1401

1402 1403 1404
/* 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
1405 1406 1407 1408 1409 1410 1411

/*
 * 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);
1412
extern int vfs_symlink(struct inode *, struct dentry *, const char *);
L
Linus Torvalds 已提交
1413 1414 1415 1416 1417 1418 1419 1420 1421 1422
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);

1423 1424 1425 1426 1427
/*
 * VFS file helper functions.
 */
extern int file_permission(struct file *, int);

M
Mark Fasheh 已提交
1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441
/*
 * 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
1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468
/*
 * File types
 *
 * NOTE! These match bits 12..15 of stat.st_mode
 * (ie "(i_mode >> 12) & 15").
 */
#define DT_UNKNOWN	0
#define DT_FIFO		1
#define DT_CHR		2
#define DT_DIR		4
#define DT_BLK		6
#define DT_REG		8
#define DT_LNK		10
#define DT_SOCK		12
#define DT_WHT		14

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

/*
 * This is the "filldir" function type, used by readdir() to let
 * the kernel specify what kind of dirent layout it wants to have.
 * This allows the kernel to read directories into kernel space or
 * to have different dirent layouts depending on the binary type.
 */
1469
typedef int (*filldir_t)(void *, const char *, int, loff_t, u64, unsigned);
1470
struct block_device_operations;
L
Linus Torvalds 已提交
1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487

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

/*
 * NOTE:
 * read, write, poll, fsync, readv, writev, unlocked_ioctl and compat_ioctl
 * can be called without the big kernel lock held in all filesystems.
 */
struct file_operations {
	struct module *owner;
	loff_t (*llseek) (struct file *, loff_t, int);
	ssize_t (*read) (struct file *, char __user *, size_t, loff_t *);
	ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
1488 1489
	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
1490 1491 1492 1493 1494 1495 1496
	int (*readdir) (struct file *, void *, filldir_t);
	unsigned int (*poll) (struct file *, struct poll_table_struct *);
	int (*ioctl) (struct inode *, struct file *, unsigned int, unsigned long);
	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
	int (*mmap) (struct file *, struct vm_area_struct *);
	int (*open) (struct inode *, struct file *);
1497
	int (*flush) (struct file *, fl_owner_t id);
L
Linus Torvalds 已提交
1498 1499 1500 1501 1502 1503 1504 1505 1506
	int (*release) (struct inode *, struct file *);
	int (*fsync) (struct file *, struct dentry *, int datasync);
	int (*aio_fsync) (struct kiocb *, int datasync);
	int (*fasync) (int, struct file *, int);
	int (*lock) (struct file *, int, struct file_lock *);
	ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int);
	unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
	int (*check_flags)(int);
	int (*flock) (struct file *, int, struct file_lock *);
1507 1508
	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);
1509
	int (*setlease)(struct file *, long, struct file_lock **);
L
Linus Torvalds 已提交
1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523
};

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);
1524 1525
	void * (*follow_link) (struct dentry *, struct nameidata *);
	void (*put_link) (struct dentry *, struct nameidata *, void *);
L
Linus Torvalds 已提交
1526
	void (*truncate) (struct inode *);
1527
	int (*permission) (struct inode *, int);
1528
	int (*check_acl)(struct inode *, int);
L
Linus Torvalds 已提交
1529 1530 1531 1532 1533 1534
	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 *);
1535
	void (*truncate_range)(struct inode *, loff_t, loff_t);
1536 1537
	long (*fallocate)(struct inode *inode, int mode, loff_t offset,
			  loff_t len);
M
Mark Fasheh 已提交
1538 1539
	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
		      u64 len);
L
Linus Torvalds 已提交
1540 1541 1542 1543
};

struct seq_file;

B
Badari Pulavarty 已提交
1544 1545 1546 1547 1548
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
1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566
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 *);
	int (*write_inode) (struct inode *, int);
	void (*drop_inode) (struct inode *);
	void (*delete_inode) (struct inode *);
	void (*put_super) (struct super_block *);
	void (*write_super) (struct super_block *);
	int (*sync_fs)(struct super_block *sb, int wait);
1567 1568
	int (*freeze_fs) (struct super_block *);
	int (*unfreeze_fs) (struct super_block *);
1569
	int (*statfs) (struct dentry *, struct kstatfs *);
L
Linus Torvalds 已提交
1570 1571
	int (*remount_fs) (struct super_block *, int *, char *);
	void (*clear_inode) (struct inode *);
1572
	void (*umount_begin) (struct super_block *);
L
Linus Torvalds 已提交
1573 1574

	int (*show_options)(struct seq_file *, struct vfsmount *);
1575
	int (*show_stats)(struct seq_file *, struct vfsmount *);
1576
#ifdef CONFIG_QUOTA
L
Linus Torvalds 已提交
1577 1578
	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);
1579
#endif
1580
	int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
L
Linus Torvalds 已提交
1581 1582
};

J
Joern Engel 已提交
1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594
/*
 * 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.
 *
 * Two bits are used for locking and completion notification, I_LOCK and I_SYNC.
 *
J
Joern Engel 已提交
1595 1596
 * I_DIRTY_SYNC		Inode is dirty, but doesn't have to be written on
 *			fdatasync().  i_atime is the usual cause.
1597 1598 1599 1600
 * 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
1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627
 * I_DIRTY_PAGES	Inode has dirty pages.  Inode itself may be clean.
 * I_NEW		get_new_inode() sets i_state to I_LOCK|I_NEW.  Both
 *			are cleared by unlock_new_inode(), called from iget().
 * 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.
 * I_CLEAR		Set by clear_inode().  In this state the inode is clean
 *			and can be destroyed.
 *
 *			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,
 *			if appropriate.  I_LOCK is used for waiting.
 *
 * I_LOCK		Serves as both a mutex and completion notification.
 *			New inodes set I_LOCK.  If two processes both create
 *			the same inode, one of them will release its inode and
 *			wait for I_LOCK to be released before returning.
 *			Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can
 *			also cause waiting on I_LOCK, without I_LOCK actually
 *			being set.  find_inode() uses this to prevent returning
 *			nearly-dead inodes.
 * I_SYNC		Similar to I_LOCK, but limited in scope to writeback
J
Joe Perches 已提交
1628
 *			of inode dirty data.  Having a separate lock for this
J
Joern Engel 已提交
1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643
 *			purpose reduces latency and prevents some filesystem-
 *			specific deadlocks.
 *
 * Q: What is the difference between I_WILL_FREE and I_FREEING?
 * Q: igrab() only checks on (I_FREEING|I_WILL_FREE).  Should it also check on
 *    I_CLEAR?  If not, why?
 */
#define I_DIRTY_SYNC		1
#define I_DIRTY_DATASYNC	2
#define I_DIRTY_PAGES		4
#define I_NEW			8
#define I_WILL_FREE		16
#define I_FREEING		32
#define I_CLEAR			64
#define __I_LOCK		7
L
Linus Torvalds 已提交
1644
#define I_LOCK			(1 << __I_LOCK)
J
Joern Engel 已提交
1645 1646
#define __I_SYNC		8
#define I_SYNC			(1 << __I_SYNC)
L
Linus Torvalds 已提交
1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660

#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
1661 1662 1663 1664 1665 1666 1667 1668
/**
 * 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().
 */
1669
static inline void inc_nlink(struct inode *inode)
1670 1671
{
	inode->i_nlink++;
1672 1673 1674 1675 1676
}

static inline void inode_inc_link_count(struct inode *inode)
{
	inc_nlink(inode);
1677 1678 1679
	mark_inode_dirty(inode);
}

D
Dave Hansen 已提交
1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690
/**
 * 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.
 */
1691
static inline void drop_nlink(struct inode *inode)
1692 1693
{
	inode->i_nlink--;
1694 1695
}

D
Dave Hansen 已提交
1696 1697 1698 1699 1700 1701 1702 1703
/**
 * 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.
 */
1704 1705 1706 1707 1708
static inline void clear_nlink(struct inode *inode)
{
	inode->i_nlink = 0;
}

1709 1710 1711
static inline void inode_dec_link_count(struct inode *inode)
{
	drop_nlink(inode);
1712 1713 1714
	mark_inode_dirty(inode);
}

1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729
/**
 * 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
1730
extern void touch_atime(struct vfsmount *mnt, struct dentry *dentry);
L
Linus Torvalds 已提交
1731 1732 1733
static inline void file_accessed(struct file *file)
{
	if (!(file->f_flags & O_NOATIME))
1734
		touch_atime(file->f_path.mnt, file->f_path.dentry);
L
Linus Torvalds 已提交
1735 1736 1737 1738 1739 1740 1741
}

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

struct file_system_type {
	const char *name;
	int fs_flags;
1742 1743
	int (*get_sb) (struct file_system_type *, int,
		       const char *, void *, struct vfsmount *);
L
Linus Torvalds 已提交
1744 1745 1746 1747
	void (*kill_sb) (struct super_block *);
	struct module *owner;
	struct file_system_type * next;
	struct list_head fs_supers;
1748

I
Ingo Molnar 已提交
1749
	struct lock_class_key s_lock_key;
1750
	struct lock_class_key s_umount_key;
1751 1752 1753

	struct lock_class_key i_lock_key;
	struct lock_class_key i_mutex_key;
1754
	struct lock_class_key i_mutex_dir_key;
1755
	struct lock_class_key i_alloc_sem_key;
L
Linus Torvalds 已提交
1756 1757
};

1758 1759 1760
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);
1761
extern int get_sb_bdev(struct file_system_type *fs_type,
L
Linus Torvalds 已提交
1762
	int flags, const char *dev_name, void *data,
1763 1764 1765
	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
1766
	int flags, void *data,
1767 1768 1769
	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
1770
	int flags, void *data,
1771 1772
	int (*fill_super)(struct super_block *, void *, int),
	struct vfsmount *mnt);
L
Linus Torvalds 已提交
1773 1774 1775 1776 1777
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
1778
void deactivate_locked_super(struct super_block *sb);
L
Linus Torvalds 已提交
1779 1780 1781 1782 1783
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);
1784
extern int get_sb_pseudo(struct file_system_type *, char *,
1785
	const struct super_operations *ops, unsigned long,
1786
	struct vfsmount *mnt);
1787
extern void simple_set_mnt(struct vfsmount *mnt, struct super_block *sb);
L
Linus Torvalds 已提交
1788
int __put_super_and_need_restart(struct super_block *sb);
1789
void put_super(struct super_block *sb);
L
Linus Torvalds 已提交
1790 1791 1792 1793 1794 1795 1796 1797 1798

/* 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 *);
1799 1800
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
1801 1802 1803
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
1804
extern struct vfsmount *collect_mounts(struct path *);
1805
extern void drop_collected_mounts(struct vfsmount *);
L
Linus Torvalds 已提交
1806

1807
extern int vfs_statfs(struct dentry *, struct kstatfs *);
L
Linus Torvalds 已提交
1808

A
Al Viro 已提交
1809 1810
extern int current_umask(void);

M
Miklos Szeredi 已提交
1811
/* /sys/fs */
1812
extern struct kobject *fs_kobj;
M
Miklos Szeredi 已提交
1813

1814 1815
extern int rw_verify_area(int, struct file *, loff_t *, size_t);

L
Linus Torvalds 已提交
1816 1817 1818
#define FLOCK_VERIFY_READ  1
#define FLOCK_VERIFY_WRITE 2

1819
#ifdef CONFIG_FILE_LOCKING
L
Linus Torvalds 已提交
1820 1821 1822 1823 1824 1825 1826
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.
 */
1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841

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
1842 1843 1844

static inline int locks_verify_locked(struct inode *inode)
{
1845
	if (mandatory_lock(inode))
L
Linus Torvalds 已提交
1846 1847 1848 1849 1850 1851 1852 1853
		return locks_mandatory_locked(inode);
	return 0;
}

static inline int locks_verify_truncate(struct inode *inode,
				    struct file *filp,
				    loff_t size)
{
1854
	if (inode->i_flock && mandatory_lock(inode))
L
Linus Torvalds 已提交
1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869
		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;
}
1870
#else /* !CONFIG_FILE_LOCKING */
1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908
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;
}

1909
#endif /* CONFIG_FILE_LOCKING */
L
Linus Torvalds 已提交
1910 1911 1912

/* fs/open.c */

1913 1914
extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs,
		       struct file *filp);
1915 1916
extern int do_fallocate(struct file *file, int mode, loff_t offset,
			loff_t len);
J
Jason Uhlenkott 已提交
1917
extern long do_sys_open(int dfd, const char __user *filename, int flags,
1918
			int mode);
L
Linus Torvalds 已提交
1919
extern struct file *filp_open(const char *, int, int);
1920 1921
extern struct file * dentry_open(struct dentry *, struct vfsmount *, int,
				 const struct cred *);
L
Linus Torvalds 已提交
1922 1923 1924
extern int filp_close(struct file *, fl_owner_t id);
extern char * getname(const char __user *);

1925 1926 1927 1928
/* fs/ioctl.c */

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

L
Linus Torvalds 已提交
1929 1930 1931 1932
/* fs/dcache.c */
extern void __init vfs_caches_init_early(void);
extern void __init vfs_caches_init(unsigned long);

1933 1934
extern struct kmem_cache *names_cachep;

V
Vegard Nossum 已提交
1935 1936 1937
#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
1938 1939 1940 1941 1942 1943
#ifndef CONFIG_AUDITSYSCALL
#define putname(name)   __putname(name)
#else
extern void putname(const char *name);
#endif

1944
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
1945
extern int register_blkdev(unsigned int, const char *);
A
Akinobu Mita 已提交
1946
extern void unregister_blkdev(unsigned int, const char *);
L
Linus Torvalds 已提交
1947
extern struct block_device *bdget(dev_t);
1948
extern struct block_device *bdgrab(struct block_device *bdev);
L
Linus Torvalds 已提交
1949 1950 1951
extern void bd_set_size(struct block_device *, loff_t size);
extern void bd_forget(struct inode *inode);
extern void bdput(struct block_device *);
1952
extern struct block_device *open_by_devnum(dev_t, fmode_t);
N
Nick Piggin 已提交
1953 1954 1955
extern void invalidate_bdev(struct block_device *);
extern int sync_blockdev(struct block_device *bdev);
extern struct super_block *freeze_bdev(struct block_device *);
1956
extern void emergency_thaw_all(void);
N
Nick Piggin 已提交
1957 1958
extern int thaw_bdev(struct block_device *bdev, struct super_block *sb);
extern int fsync_bdev(struct block_device *);
1959 1960
#else
static inline void bd_forget(struct inode *inode) {}
1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972
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;
}
1973
#endif
1974
extern int sync_filesystem(struct super_block *);
1975
extern const struct file_operations def_blk_fops;
1976 1977 1978
extern const struct file_operations def_chr_fops;
extern const struct file_operations bad_sock_fops;
extern const struct file_operations def_fifo_fops;
1979
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
1980
extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long);
1981
extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long);
L
Linus Torvalds 已提交
1982
extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long);
1983
extern int blkdev_get(struct block_device *, fmode_t);
A
Al Viro 已提交
1984
extern int blkdev_put(struct block_device *, fmode_t);
L
Linus Torvalds 已提交
1985 1986
extern int bd_claim(struct block_device *, void *);
extern void bd_release(struct block_device *);
1987 1988 1989 1990 1991 1992 1993
#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
1994
#endif
L
Linus Torvalds 已提交
1995 1996

/* fs/char_dev.c */
1997
#define CHRDEV_MAJOR_HASH_SIZE	255
L
Linus Torvalds 已提交
1998 1999
extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *);
extern int register_chrdev_region(dev_t, unsigned, const char *);
2000 2001 2002 2003 2004
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
2005
extern void unregister_chrdev_region(dev_t, unsigned);
2006
extern void chrdev_show(struct seq_file *,off_t);
L
Linus Torvalds 已提交
2007

2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018
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
2019 2020
/* fs/block_dev.c */
#define BDEVNAME_SIZE	32	/* Largest string for a blockdev identifier */
2021
#define BDEVT_SIZE	10	/* Largest string for MAJ:MIN for blkdev */
2022 2023 2024

#ifdef CONFIG_BLOCK
#define BLKDEV_MAJOR_HASH_SIZE	255
L
Linus Torvalds 已提交
2025 2026 2027
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 *);
2028 2029
extern struct block_device *open_bdev_exclusive(const char *, fmode_t, void *);
extern void close_bdev_exclusive(struct block_device *, fmode_t);
2030
extern void blkdev_show(struct seq_file *,off_t);
2031

2032 2033 2034
#else
#define BLKDEV_MAJOR_HASH_SIZE	0
#endif
L
Linus Torvalds 已提交
2035 2036 2037 2038 2039 2040 2041

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 *);

2042 2043 2044
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
2045 2046 2047

extern int fs_may_remount_ro(struct super_block *);

2048
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2049 2050 2051 2052 2053 2054 2055 2056 2057 2058
/*
 * 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)

2059 2060
extern void check_disk_size_change(struct gendisk *disk,
				   struct block_device *bdev);
2061
extern int revalidate_disk(struct gendisk *);
L
Linus Torvalds 已提交
2062
extern int check_disk_change(struct block_device *);
2063
extern int __invalidate_device(struct block_device *);
L
Linus Torvalds 已提交
2064
extern int invalidate_partition(struct gendisk *, int);
2065 2066
#endif
extern int invalidate_inodes(struct super_block *);
L
Linus Torvalds 已提交
2067 2068
unsigned long invalidate_mapping_pages(struct address_space *mapping,
					pgoff_t start, pgoff_t end);
2069

2070
static inline unsigned long __deprecated
2071 2072 2073 2074 2075
invalidate_inode_pages(struct address_space *mapping)
{
	return invalidate_mapping_pages(mapping, 0, ~0UL);
}

L
Linus Torvalds 已提交
2076 2077 2078 2079
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))
2080
		invalidate_mapping_pages(inode->i_mapping, 0, -1);
L
Linus Torvalds 已提交
2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091
}
extern int invalidate_inode_pages2(struct address_space *mapping);
extern int invalidate_inode_pages2_range(struct address_space *mapping,
					 pgoff_t start, pgoff_t end);
extern int write_inode_now(struct inode *, int);
extern int filemap_fdatawrite(struct address_space *);
extern int filemap_flush(struct address_space *);
extern int filemap_fdatawait(struct address_space *);
extern int filemap_write_and_wait(struct address_space *mapping);
extern int filemap_write_and_wait_range(struct address_space *mapping,
				        loff_t lstart, loff_t lend);
2092 2093 2094 2095
extern int wait_on_page_writeback_range(struct address_space *mapping,
				pgoff_t start, pgoff_t end);
extern int __filemap_fdatawrite_range(struct address_space *mapping,
				loff_t start, loff_t end, int sync_mode);
2096 2097
extern int filemap_fdatawrite_range(struct address_space *mapping,
				loff_t start, loff_t end);
2098

C
Christoph Hellwig 已提交
2099
extern int vfs_fsync(struct file *file, struct dentry *dentry, int datasync);
L
Linus Torvalds 已提交
2100 2101 2102
extern void sync_supers(void);
extern void emergency_sync(void);
extern void emergency_remount(void);
2103
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2104
extern sector_t bmap(struct inode *, sector_t);
2105
#endif
L
Linus Torvalds 已提交
2106
extern int notify_change(struct dentry *, struct iattr *);
2107
extern int inode_permission(struct inode *, int);
L
Linus Torvalds 已提交
2108 2109 2110
extern int generic_permission(struct inode *, int,
		int (*check_acl)(struct inode *, int));

2111 2112 2113 2114 2115
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
2116 2117 2118 2119 2120 2121 2122 2123 2124
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)
2125
		atomic_inc(&file->f_path.dentry->d_inode->i_writecount);
L
Linus Torvalds 已提交
2126
}
U
Ulrich Drepper 已提交
2127
extern int do_pipe_flags(int *, int);
2128 2129
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
2130
extern void free_write_pipe(struct file *);
L
Linus Torvalds 已提交
2131

2132
extern struct file *do_filp_open(int dfd, const char *pathname,
2133
		int open_flag, int mode, int acc_mode);
2134
extern int may_open(struct path *, int, int);
L
Linus Torvalds 已提交
2135

M
Mimi Zohar 已提交
2136
extern int kernel_read(struct file *, loff_t, char *, unsigned long);
L
Linus Torvalds 已提交
2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149
extern struct file * open_exec(const char *);
 
/* fs/dcache.c -- generic fs support functions */
extern int is_subdir(struct dentry *, struct dentry *);
extern ino_t find_inode_number(struct dentry *, struct qstr *);

#include <linux/err.h>

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

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

2150
extern int inode_init_always(struct super_block *, struct inode *);
L
Linus Torvalds 已提交
2151
extern void inode_init_once(struct inode *);
2152
extern void inode_add_to_lists(struct super_block *, struct inode *);
L
Linus Torvalds 已提交
2153 2154 2155 2156 2157
extern void iput(struct inode *);
extern struct inode * igrab(struct inode *);
extern ino_t iunique(struct super_block *, ino_t);
extern int inode_needs_sync(struct inode *inode);
extern void generic_delete_inode(struct inode *inode);
2158
extern void generic_drop_inode(struct inode *inode);
L
Linus Torvalds 已提交
2159

2160 2161 2162
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
2163 2164 2165 2166 2167 2168
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
2169 2170
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
2171 2172 2173
extern void unlock_new_inode(struct inode *);

extern void __iget(struct inode * inode);
2174
extern void iget_failed(struct inode *);
L
Linus Torvalds 已提交
2175 2176
extern void clear_inode(struct inode *);
extern void destroy_inode(struct inode *);
C
Christoph Hellwig 已提交
2177
extern void __destroy_inode(struct inode *);
L
Linus Torvalds 已提交
2178
extern struct inode *new_inode(struct super_block *);
2179
extern int should_remove_suid(struct dentry *);
2180
extern int file_remove_suid(struct file *);
L
Linus Torvalds 已提交
2181 2182 2183 2184 2185 2186 2187 2188 2189 2190

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

extern struct file * get_empty_filp(void);
extern void file_move(struct file *f, struct list_head *list);
extern void file_kill(struct file *f);
2191
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2192 2193 2194
struct bio;
extern void submit_bio(int, struct bio *);
extern int bdev_read_only(struct block_device *);
2195
#endif
L
Linus Torvalds 已提交
2196 2197 2198 2199 2200 2201 2202 2203
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);
2204 2205
extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t);
extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t);
L
Linus Torvalds 已提交
2206
extern ssize_t generic_file_aio_write_nolock(struct kiocb *, const struct iovec *,
2207
		unsigned long, loff_t);
L
Linus Torvalds 已提交
2208 2209 2210 2211 2212 2213
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);
2214 2215
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
2216 2217

/* fs/splice.c */
2218
extern ssize_t generic_file_splice_read(struct file *, loff_t *,
A
Andrew Morton 已提交
2219
		struct pipe_inode_info *, size_t, unsigned int);
2220 2221
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
2222
extern ssize_t generic_file_splice_write(struct pipe_inode_info *,
2223
		struct file *, loff_t *, size_t, unsigned int);
A
Andrew Morton 已提交
2224
extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
2225 2226
		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
2227 2228
		size_t len, unsigned int flags);

L
Linus Torvalds 已提交
2229 2230 2231 2232
extern void
file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping);
extern loff_t no_llseek(struct file *file, loff_t offset, int origin);
extern loff_t generic_file_llseek(struct file *file, loff_t offset, int origin);
A
Andi Kleen 已提交
2233 2234
extern loff_t generic_file_llseek_unlocked(struct file *file, loff_t offset,
			int origin);
L
Linus Torvalds 已提交
2235 2236 2237
extern int generic_file_open(struct inode * inode, struct file * filp);
extern int nonseekable_open(struct inode * inode, struct file * filp);

2238
#ifdef CONFIG_FS_XIP
2239 2240
extern ssize_t xip_file_read(struct file *filp, char __user *buf, size_t len,
			     loff_t *ppos);
2241
extern int xip_file_mmap(struct file * file, struct vm_area_struct * vma);
2242 2243
extern ssize_t xip_file_write(struct file *filp, const char __user *buf,
			      size_t len, loff_t *ppos);
2244
extern int xip_truncate_page(struct address_space *mapping, loff_t from);
2245 2246 2247 2248 2249
#else
static inline int xip_truncate_page(struct address_space *mapping, loff_t from)
{
	return 0;
}
2250 2251
#endif

2252
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2253 2254
ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
	struct block_device *bdev, const struct iovec *iov, loff_t offset,
2255
	unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io,
L
Linus Torvalds 已提交
2256 2257 2258 2259 2260 2261 2262 2263 2264 2265
	int lock_type);

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

static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb,
	struct inode *inode, struct block_device *bdev, const struct iovec *iov,
2266
	loff_t offset, unsigned long nr_segs, get_block_t get_block,
L
Linus Torvalds 已提交
2267 2268 2269
	dio_iodone_t end_io)
{
	return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
2270
				nr_segs, get_block, end_io, DIO_LOCKING);
L
Linus Torvalds 已提交
2271 2272 2273 2274
}

static inline ssize_t blockdev_direct_IO_no_locking(int rw, struct kiocb *iocb,
	struct inode *inode, struct block_device *bdev, const struct iovec *iov,
2275
	loff_t offset, unsigned long nr_segs, get_block_t get_block,
L
Linus Torvalds 已提交
2276 2277 2278
	dio_iodone_t end_io)
{
	return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
2279
				nr_segs, get_block, end_io, DIO_NO_LOCKING);
L
Linus Torvalds 已提交
2280 2281 2282 2283
}

static inline ssize_t blockdev_direct_IO_own_locking(int rw, struct kiocb *iocb,
	struct inode *inode, struct block_device *bdev, const struct iovec *iov,
2284
	loff_t offset, unsigned long nr_segs, get_block_t get_block,
L
Linus Torvalds 已提交
2285 2286 2287
	dio_iodone_t end_io)
{
	return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
2288
				nr_segs, get_block, end_io, DIO_OWN_LOCKING);
L
Linus Torvalds 已提交
2289
}
2290
#endif
L
Linus Torvalds 已提交
2291

2292
extern const struct file_operations generic_ro_fops;
L
Linus Torvalds 已提交
2293 2294 2295 2296 2297 2298

#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);
2299 2300
extern void *page_follow_link_light(struct dentry *, struct nameidata *);
extern void page_put_link(struct dentry *, struct nameidata *, void *);
2301
extern int __page_symlink(struct inode *inode, const char *symname, int len,
2302
		int nofs);
L
Linus Torvalds 已提交
2303
extern int page_symlink(struct inode *inode, const char *symname, int len);
2304
extern const struct inode_operations page_symlink_inode_operations;
L
Linus Torvalds 已提交
2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317
extern int generic_readlink(struct dentry *, char __user *, int);
extern void generic_fillattr(struct inode *, struct kstat *);
extern int vfs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
void inode_add_bytes(struct inode *inode, loff_t bytes);
void inode_sub_bytes(struct inode *inode, loff_t bytes);
loff_t inode_get_bytes(struct inode *inode);
void inode_set_bytes(struct inode *inode, loff_t bytes);

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

extern int vfs_stat(char __user *, struct kstat *);
extern int vfs_lstat(char __user *, struct kstat *);
extern int vfs_fstat(unsigned int, struct kstat *);
2318
extern int vfs_fstatat(int , char __user *, struct kstat *, int);
L
Linus Torvalds 已提交
2319

2320 2321
extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
		    unsigned long arg);
2322 2323 2324
extern int __generic_block_fiemap(struct inode *inode,
				  struct fiemap_extent_info *fieinfo, u64 start,
				  u64 len, get_block_t *get_block);
2325 2326 2327
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
2328

2329 2330
extern void get_filesystem(struct file_system_type *fs);
extern void put_filesystem(struct file_system_type *fs);
L
Linus Torvalds 已提交
2331 2332 2333 2334 2335 2336 2337 2338 2339 2340
extern struct file_system_type *get_fs_type(const char *name);
extern struct super_block *get_super(struct block_device *);
extern struct super_block *user_get_super(dev_t);
extern void drop_super(struct super_block *sb);

extern int dcache_dir_open(struct inode *, struct file *);
extern int dcache_dir_close(struct inode *, struct file *);
extern loff_t dcache_dir_lseek(struct file *, loff_t, int);
extern int dcache_readdir(struct file *, void *, filldir_t);
extern int simple_getattr(struct vfsmount *, struct dentry *, struct kstat *);
2341
extern int simple_statfs(struct dentry *, struct kstatfs *);
L
Linus Torvalds 已提交
2342 2343 2344 2345 2346 2347 2348 2349 2350
extern int simple_link(struct dentry *, struct inode *, struct dentry *);
extern int simple_unlink(struct inode *, struct dentry *);
extern int simple_rmdir(struct inode *, struct dentry *);
extern int simple_rename(struct inode *, struct dentry *, struct inode *, struct dentry *);
extern int simple_sync_file(struct file *, struct dentry *, int);
extern int simple_empty(struct dentry *);
extern int simple_readpage(struct file *file, struct page *page);
extern int simple_prepare_write(struct file *file, struct page *page,
			unsigned offset, unsigned to);
2351 2352 2353 2354 2355 2356
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
2357 2358 2359

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 *);
2360
extern const struct file_operations simple_dir_operations;
2361
extern const struct inode_operations simple_dir_inode_operations;
2362
struct tree_descr { char *name; const struct file_operations *ops; int mode; };
L
Linus Torvalds 已提交
2363 2364
struct dentry *d_alloc_name(struct dentry *, const char *);
extern int simple_fill_super(struct super_block *, int, struct tree_descr *);
2365
extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count);
L
Linus Torvalds 已提交
2366 2367
extern void simple_release_fs(struct vfsmount **mount, int *count);

2368 2369
extern ssize_t simple_read_from_buffer(void __user *to, size_t count,
			loff_t *ppos, const void *from, size_t available);
L
Linus Torvalds 已提交
2370

A
Al Viro 已提交
2371 2372
extern int simple_fsync(struct file *, struct dentry *, int);

2373
#ifdef CONFIG_MIGRATION
2374 2375
extern int buffer_migrate_page(struct address_space *,
				struct page *, struct page *);
2376 2377 2378 2379
#else
#define buffer_migrate_page NULL
#endif

L
Linus Torvalds 已提交
2380 2381 2382
extern int inode_change_ok(struct inode *, struct iattr *);
extern int __must_check inode_setattr(struct inode *, struct iattr *);

2383
extern void file_update_time(struct file *file);
L
Linus Torvalds 已提交
2384

2385 2386
extern int generic_show_options(struct seq_file *m, struct vfsmount *mnt);
extern void save_mount_options(struct super_block *sb, char *options);
2387
extern void replace_mount_options(struct super_block *sb, char *options);
2388

L
Linus Torvalds 已提交
2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417
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);

2418
void simple_transaction_set(struct file *file, size_t n);
L
Linus Torvalds 已提交
2419

2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444
/*
 * simple attribute files
 *
 * These attributes behave similar to those in sysfs:
 *
 * Writing to an attribute immediately sets a value, an open file can be
 * written to multiple times.
 *
 * Reading from an attribute creates a buffer from the value that might get
 * read with multiple read calls. When the attribute has been read
 * completely, no further read calls are possible until the file is opened
 * again.
 *
 * All attributes contain a text representation of a numeric value
 * that are accessed with the get() and set() functions.
 */
#define DEFINE_SIMPLE_ATTRIBUTE(__fops, __get, __set, __fmt)		\
static int __fops ## _open(struct inode *inode, struct file *file)	\
{									\
	__simple_attr_check_format(__fmt, 0ull);			\
	return simple_attr_open(inode, file, __get, __set, __fmt);	\
}									\
static struct file_operations __fops = {				\
	.owner	 = THIS_MODULE,						\
	.open	 = __fops ## _open,					\
2445
	.release = simple_attr_release,					\
2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456
	.read	 = simple_attr_read,					\
	.write	 = simple_attr_write,					\
};

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

int simple_attr_open(struct inode *inode, struct file *file,
2457
		     int (*get)(void *, u64 *), int (*set)(void *, u64),
2458
		     const char *fmt);
2459
int simple_attr_release(struct inode *inode, struct file *file);
2460 2461 2462 2463 2464
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
2465 2466
struct ctl_table;
int proc_nr_files(struct ctl_table *table, int write, struct file *filp,
2467 2468
		  void __user *buffer, size_t *lenp, loff_t *ppos);

2469
int __init get_filesystem_list(char *buf);
2470

L
Linus Torvalds 已提交
2471 2472
#endif /* __KERNEL__ */
#endif /* _LINUX_FS_H */