fs.h 96.0 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10
#ifndef _LINUX_FS_H
#define _LINUX_FS_H

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

#include <linux/limits.h>
#include <linux/ioctl.h>
11
#include <linux/blk_types.h>
12
#include <linux/types.h>
L
Linus Torvalds 已提交
13 14 15 16 17 18 19 20 21 22 23 24 25

/*
 * 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
26 27
#define INR_OPEN_CUR 1024	/* Initial setting for nfile rlimits */
#define INR_OPEN_MAX 4096	/* Hard limit for nfile rlimits */
L
Linus Torvalds 已提交
28 29 30 31

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

32 33 34
#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 */
35 36 37
#define SEEK_DATA	3	/* seek to the next data */
#define SEEK_HOLE	4	/* seek to the next hole */
#define SEEK_MAX	SEEK_HOLE
38

L
Lukas Czerner 已提交
39
struct fstrim_range {
40 41 42
	__u64 start;
	__u64 len;
	__u64 minlen;
L
Lukas Czerner 已提交
43 44
};

L
Linus Torvalds 已提交
45 46
/* And dynamically-tunable limits and defaults: */
struct files_stat_struct {
E
Eric Dumazet 已提交
47 48 49
	unsigned long nr_files;		/* read only */
	unsigned long nr_free_files;	/* read only */
	unsigned long max_files;		/* tunable */
L
Linus Torvalds 已提交
50 51 52 53 54
};

struct inodes_stat_t {
	int nr_inodes;
	int nr_unused;
55
	int dummy[5];		/* padding for sysctl ABI compatibility */
L
Linus Torvalds 已提交
56 57 58 59 60
};


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

61 62 63 64 65 66 67 68 69
#define MAY_EXEC		0x00000001
#define MAY_WRITE		0x00000002
#define MAY_READ		0x00000004
#define MAY_APPEND		0x00000008
#define MAY_ACCESS		0x00000010
#define MAY_OPEN		0x00000020
#define MAY_CHDIR		0x00000040
/* called from RCU mode, don't block */
#define MAY_NOT_BLOCK		0x00000080
L
Linus Torvalds 已提交
70

71 72 73 74 75
/*
 * 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()
 */

76
/* file is open for reading */
77
#define FMODE_READ		((__force fmode_t)0x1)
78
/* file is open for writing */
79
#define FMODE_WRITE		((__force fmode_t)0x2)
80
/* file is seekable */
81
#define FMODE_LSEEK		((__force fmode_t)0x4)
82
/* file can be accessed using pread */
83
#define FMODE_PREAD		((__force fmode_t)0x8)
84
/* file can be accessed using pwrite */
85
#define FMODE_PWRITE		((__force fmode_t)0x10)
86
/* File is opened for execution with sys_execve / sys_uselib */
87
#define FMODE_EXEC		((__force fmode_t)0x20)
88
/* File is opened with O_NDELAY (only set for block devices) */
89
#define FMODE_NDELAY		((__force fmode_t)0x40)
90
/* File is opened with O_EXCL (only set for block devices) */
91
#define FMODE_EXCL		((__force fmode_t)0x80)
92 93
/* File is opened using open(.., 3, ..) and is writeable only for ioctls
   (specialy hack for floppy.c) */
94
#define FMODE_WRITE_IOCTL	((__force fmode_t)0x100)
95 96 97 98
/* 32bit hashes as llseek() offset (for directories) */
#define FMODE_32BITHASH         ((__force fmode_t)0x200)
/* 64bit hashes as llseek() offset (for directories) */
#define FMODE_64BITHASH         ((__force fmode_t)0x400)
99

100 101 102 103 104 105
/*
 * 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.
 */
106
#define FMODE_NOCMTIME		((__force fmode_t)0x800)
107

108
/* Expect random access pattern */
109
#define FMODE_RANDOM		((__force fmode_t)0x1000)
110

111 112 113
/* File is huge (eg. /dev/kmem): treat loff_t as unsigned */
#define FMODE_UNSIGNED_OFFSET	((__force fmode_t)0x2000)

114 115 116
/* File is opened with O_PATH; almost nothing can be done with it */
#define FMODE_PATH		((__force fmode_t)0x4000)

E
Eric Paris 已提交
117
/* File was opened by fanotify and shouldn't generate fanotify events */
118
#define FMODE_NONOTIFY		((__force fmode_t)0x1000000)
E
Eric Paris 已提交
119

120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146
/*
 * 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
147
 *			block layer could (in theory) choose to ignore this
148 149
 *			request if it runs into resource problems.
 * WRITE		A normal async write. Device will be plugged.
J
Jens Axboe 已提交
150
 * WRITE_SYNC		Synchronous write. Identical to WRITE, but passes down
151
 *			the hint that someone will be waiting on this IO
J
Jens Axboe 已提交
152 153
 *			shortly. The write equivalent of READ_SYNC.
 * WRITE_ODIRECT	Special case write for O_DIRECT only.
154 155 156 157 158 159
 * WRITE_FLUSH		Like WRITE_SYNC but with preceding cache flush.
 * WRITE_FUA		Like WRITE_SYNC but data is guaranteed to be on
 *			non-volatile media on completion.
 * WRITE_FLUSH_FUA	Combination of WRITE_FLUSH and FUA. The IO is preceded
 *			by a cache flush and data is guaranteed to be on
 *			non-volatile media on completion.
160 161
 *
 */
162 163
#define RW_MASK			REQ_WRITE
#define RWA_MASK		REQ_RAHEAD
164 165

#define READ			0
166 167
#define WRITE			RW_MASK
#define READA			RWA_MASK
168 169
#define KERNEL_READ		(READ|REQ_KERNEL)
#define KERNEL_WRITE		(WRITE|REQ_KERNEL)
170

J
Jens Axboe 已提交
171 172 173 174 175 176
#define READ_SYNC		(READ | REQ_SYNC)
#define WRITE_SYNC		(WRITE | REQ_SYNC | REQ_NOIDLE)
#define WRITE_ODIRECT		(WRITE | REQ_SYNC)
#define WRITE_FLUSH		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH)
#define WRITE_FUA		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FUA)
#define WRITE_FLUSH_FUA		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH | REQ_FUA)
L
Linus Torvalds 已提交
177

178 179 180 181 182 183 184 185 186

/*
 * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector
 * that indicates that they should check the contents of the iovec are
 * valid, but not check the memory that the iovec elements
 * points too.
 */
#define CHECK_IOVEC_ONLY -1

L
Linus Torvalds 已提交
187 188 189 190 191 192 193
#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
194
#define FS_HAS_SUBTYPE 4
L
Linus Torvalds 已提交
195
#define FS_REVAL_DOT	16384	/* Check the paths ".", ".." for staleness */
196 197 198 199
#define FS_RENAME_DOES_D_MOVE	32768	/* FS will handle d_move()
					 * during rename() internally.
					 */

L
Linus Torvalds 已提交
200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215
/*
 * 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
216 217 218
#define MS_VERBOSE	32768	/* War is peace. Verbosity is silence.
				   MS_VERBOSE is deprecated. */
#define MS_SILENT	32768
M
Miklos Szeredi 已提交
219
#define MS_POSIXACL	(1<<16)	/* VFS does not apply the umask */
R
Ram Pai 已提交
220
#define MS_UNBINDABLE	(1<<17)	/* change to unbindable */
221
#define MS_PRIVATE	(1<<18)	/* change to private */
R
Ram Pai 已提交
222
#define MS_SLAVE	(1<<19)	/* change to slave */
R
Ram Pai 已提交
223
#define MS_SHARED	(1<<20)	/* change to shared */
V
Valerie Henson 已提交
224
#define MS_RELATIME	(1<<21)	/* Update atime relative to mtime/ctime. */
225
#define MS_KERNMOUNT	(1<<22) /* this is a kern_mount call */
226
#define MS_I_VERSION	(1<<23) /* Update inode I_version field */
M
Matthew Garrett 已提交
227
#define MS_STRICTATIME	(1<<24) /* Always perform atime updates */
A
Al Viro 已提交
228
#define MS_NOSEC	(1<<28)
A
Al Viro 已提交
229
#define MS_BORN		(1<<29)
L
Linus Torvalds 已提交
230 231 232 233 234 235
#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
236
#define MS_RMT_MASK	(MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION)
L
Linus Torvalds 已提交
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 */
256
#define S_IMA		1024	/* Inode has an associated IMA struct */
257
#define S_AUTOMOUNT	2048	/* Automount/referral quasi-directory */
258
#define S_NOSEC		4096	/* no suid or xattr security attributes */
L
Linus Torvalds 已提交
259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280

/*
 * 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)
281
#define IS_NOATIME(inode)   __IS_FLG(inode, MS_RDONLY|MS_NOATIME)
282
#define IS_I_VERSION(inode)   __IS_FLG(inode, MS_I_VERSION)
L
Linus Torvalds 已提交
283 284 285 286 287 288 289 290 291 292

#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)
293
#define IS_IMA(inode)		((inode)->i_flags & S_IMA)
294
#define IS_AUTOMOUNT(inode)	((inode)->i_flags & S_AUTOMOUNT)
295
#define IS_NOSEC(inode)		((inode)->i_flags & S_NOSEC)
L
Linus Torvalds 已提交
296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325

/* 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) */
326 327 328 329
#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)
330
#define BLKDISCARD _IO(0x12,119)
M
Martin K. Petersen 已提交
331 332 333 334
#define BLKIOMIN _IO(0x12,120)
#define BLKIOOPT _IO(0x12,121)
#define BLKALIGNOFF _IO(0x12,122)
#define BLKPBSZGET _IO(0x12,123)
335
#define BLKDISCARDZEROES _IO(0x12,124)
A
Adrian Hunter 已提交
336
#define BLKSECDISCARD _IO(0x12,125)
337
#define BLKROTATIONAL _IO(0x12,126)
338
#define BLKZEROOUT _IO(0x12,127)
L
Linus Torvalds 已提交
339 340 341 342

#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 */
343 344
#define FIFREEZE	_IOWR('X', 119, int)	/* Freeze */
#define FITHAW		_IOWR('X', 120, int)	/* Thaw */
L
Lukas Czerner 已提交
345
#define FITRIM		_IOWR('X', 121, struct fstrim_range)	/* Trim */
L
Linus Torvalds 已提交
346

347 348 349 350
#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
351
#define FS_IOC_FIEMAP			_IOWR('f', 11, struct fiemap)
352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380
#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*/
381 382
#define FS_EXTENT_FL			0x00080000 /* Extents */
#define FS_DIRECTIO_FL			0x00100000 /* Use direct i/o */
L
liubo 已提交
383
#define FS_NOCOW_FL			0x00800000 /* Do not cow file */
384 385 386 387 388 389
#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 */


390 391 392 393
#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
394 395 396 397 398 399
#ifdef __KERNEL__

#include <linux/linkage.h>
#include <linux/wait.h>
#include <linux/kdev_t.h>
#include <linux/dcache.h>
400
#include <linux/path.h>
L
Linus Torvalds 已提交
401 402 403 404 405 406
#include <linux/stat.h>
#include <linux/cache.h>
#include <linux/list.h>
#include <linux/radix-tree.h>
#include <linux/prio_tree.h>
#include <linux/init.h>
407
#include <linux/pid.h>
408
#include <linux/bug.h>
409
#include <linux/mutex.h>
410
#include <linux/capability.h>
411
#include <linux/semaphore.h>
M
Mark Fasheh 已提交
412
#include <linux/fiemap.h>
413
#include <linux/rculist_bl.h>
414
#include <linux/atomic.h>
415
#include <linux/shrinker.h>
416
#include <linux/migrate_mode.h>
417
#include <linux/uidgid.h>
418
#include <linux/lockdep.h>
L
Linus Torvalds 已提交
419 420 421

#include <asm/byteorder.h>

422
struct export_operations;
423
struct hd_geometry;
L
Linus Torvalds 已提交
424 425
struct iovec;
struct nameidata;
426
struct kiocb;
A
Alexey Dobriyan 已提交
427
struct kobject;
L
Linus Torvalds 已提交
428 429 430 431 432
struct pipe_inode_info;
struct poll_table_struct;
struct kstatfs;
struct vm_area_struct;
struct vfsmount;
433
struct cred;
434
struct swap_info_struct;
L
Linus Torvalds 已提交
435

436
extern void __init inode_init(void);
L
Linus Torvalds 已提交
437 438 439
extern void __init inode_init_early(void);
extern void __init files_init(unsigned long);

440
extern struct files_stat_struct files_stat;
E
Eric Dumazet 已提交
441
extern unsigned long get_max_files(void);
442 443 444
extern int sysctl_nr_open;
extern struct inodes_stat_t inodes_stat;
extern int leases_enable, lease_break_time;
K
Kees Cook 已提交
445 446
extern int sysctl_protected_symlinks;
extern int sysctl_protected_hardlinks;
447

L
Linus Torvalds 已提交
448 449 450
struct buffer_head;
typedef int (get_block_t)(struct inode *inode, sector_t iblock,
			struct buffer_head *bh_result, int create);
451
typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
452 453
			ssize_t bytes, void *private, int ret,
			bool is_async);
L
Linus Torvalds 已提交
454 455 456 457 458

/*
 * Attribute flags.  These should be or-ed together to figure out what
 * has been changed!
 */
459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475
#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
476 477 478 479 480 481 482 483 484 485 486 487 488

/*
 * 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;
489 490
	kuid_t		ia_uid;
	kgid_t		ia_gid;
L
Linus Torvalds 已提交
491 492 493 494
	loff_t		ia_size;
	struct timespec	ia_atime;
	struct timespec	ia_mtime;
	struct timespec	ia_ctime;
495 496

	/*
L
Lucas De Marchi 已提交
497
	 * Not an attribute, but an auxiliary info for filesystems wanting to
498 499 500 501
	 * 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
502 503 504 505 506 507 508
};

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

509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526
/** 
 * 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
527
 *  			by readpage().
528 529 530 531 532 533 534 535 536 537 538 539
 *
 * 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,
};

540
#define AOP_FLAG_UNINTERRUPTIBLE	0x0001 /* will not do a short write */
N
Nick Piggin 已提交
541
#define AOP_FLAG_CONT_EXPAND		0x0002 /* called from cont_expand */
542 543 544
#define AOP_FLAG_NOFS			0x0004 /* used by filesystem to direct
						* helper code (eg buffer layer)
						* to clear GFP_FS from alloc */
545

L
Linus Torvalds 已提交
546 547 548 549 550 551 552
/*
 * oh the beauties of C type declarations.
 */
struct page;
struct address_space;
struct writeback_control;

N
Nick Piggin 已提交
553 554 555 556 557 558 559 560 561 562 563 564
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);
565
int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes);
N
Nick Piggin 已提交
566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584
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;
}

585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605
/*
 * "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
606

L
Linus Torvalds 已提交
607 608 609 610 611 612 613
struct address_space_operations {
	int (*writepage)(struct page *page, struct writeback_control *wbc);
	int (*readpage)(struct file *, struct page *);

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

614
	/* Set a page dirty.  Return true if this dirtied it */
L
Linus Torvalds 已提交
615 616 617 618 619
	int (*set_page_dirty)(struct page *page);

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

620 621 622 623 624 625 626
	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
627 628
	/* Unfortunately this kludge is needed for FIBMAP. Don't use it */
	sector_t (*bmap)(struct address_space *, sector_t);
629
	void (*invalidatepage) (struct page *, unsigned long);
A
Al Viro 已提交
630
	int (*releasepage) (struct page *, gfp_t);
631
	void (*freepage)(struct page *);
L
Linus Torvalds 已提交
632 633
	ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
			loff_t offset, unsigned long nr_segs);
634 635
	int (*get_xip_mem)(struct address_space *, pgoff_t, int,
						void **, unsigned long *);
636 637 638 639
	/*
	 * migrate the contents of a page to the specified target. If sync
	 * is false, it must not block.
	 */
640
	int (*migratepage) (struct address_space *,
641
			struct page *, struct page *, enum migrate_mode);
642
	int (*launder_page) (struct page *);
643 644
	int (*is_partially_uptodate) (struct page *, read_descriptor_t *,
					unsigned long);
645
	int (*error_remove_page)(struct address_space *, struct page *);
646 647

	/* swapfile support */
648 649 650
	int (*swap_activate)(struct swap_info_struct *sis, struct file *file,
				sector_t *span);
	void (*swap_deactivate)(struct file *file);
L
Linus Torvalds 已提交
651 652
};

J
Jens Axboe 已提交
653 654
extern const struct address_space_operations empty_aops;

655 656 657 658 659 660 661 662 663 664 665 666
/*
 * 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
667 668 669 670
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
671
	spinlock_t		tree_lock;	/* and lock protecting it */
L
Linus Torvalds 已提交
672 673 674
	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 */
675
	struct mutex		i_mmap_mutex;	/* protect tree, count, list */
676
	/* Protected by tree_lock together with the radix tree */
L
Linus Torvalds 已提交
677 678
	unsigned long		nrpages;	/* number of total pages */
	pgoff_t			writeback_index;/* writeback starts here */
679
	const struct address_space_operations *a_ops;	/* methods */
L
Linus Torvalds 已提交
680 681 682 683 684 685 686 687
	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
L
Lucas De Marchi 已提交
688
	 * must be enforced here for CRIS, to let the least significant bit
L
Linus Torvalds 已提交
689 690
	 * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON.
	 */
691
struct request_queue;
L
Linus Torvalds 已提交
692 693 694

struct block_device {
	dev_t			bd_dev;  /* not a kdev_t - it's a search key */
695
	int			bd_openers;
L
Linus Torvalds 已提交
696
	struct inode *		bd_inode;	/* will die */
697
	struct super_block *	bd_super;
698
	struct mutex		bd_mutex;	/* open/close mutex */
L
Linus Torvalds 已提交
699
	struct list_head	bd_inodes;
700
	void *			bd_claiming;
L
Linus Torvalds 已提交
701 702
	void *			bd_holder;
	int			bd_holders;
703
	bool			bd_write_holder;
704
#ifdef CONFIG_SYSFS
705
	struct list_head	bd_holder_disks;
706
#endif
L
Linus Torvalds 已提交
707 708 709 710 711 712 713
	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;
714
	struct request_queue *  bd_queue;
L
Linus Torvalds 已提交
715 716 717 718 719 720 721 722
	struct list_head	bd_list;
	/*
	 * Private data.  You must have bd_claim'ed the block_device
	 * to use this.  NOTE:  bd_claim allows an owner to claim
	 * the same device multiple times, the owner must take special
	 * care to not mess up bd_private for that case.
	 */
	unsigned long		bd_private;
723 724 725 726 727

	/* The counter of freeze processes */
	int			bd_fsfreeze_count;
	/* Mutex for freeze */
	struct mutex		bd_fsfreeze_mutex;
L
Linus Torvalds 已提交
728 729 730 731 732 733 734 735
};

/*
 * Radix-tree tags, for tagging dirty and writeback pages within the pagecache
 * radix trees
 */
#define PAGECACHE_TAG_DIRTY	0
#define PAGECACHE_TAG_WRITEBACK	1
736
#define PAGECACHE_TAG_TOWRITE	2
L
Linus Torvalds 已提交
737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770

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
771 772 773
struct posix_acl;
#define ACL_NOT_CACHED ((void *)(-1))

774 775 776 777 778 779 780 781 782
#define IOP_FASTPERM	0x0001
#define IOP_LOOKUP	0x0002
#define IOP_NOFOLLOW	0x0004

/*
 * Keep mostly read-only and often accessed (especially for
 * the RCU path lookup and 'stat' data) fields at the beginning
 * of the 'struct inode'
 */
L
Linus Torvalds 已提交
783
struct inode {
784
	umode_t			i_mode;
785
	unsigned short		i_opflags;
786 787
	kuid_t			i_uid;
	kgid_t			i_gid;
788 789 790 791 792 793 794
	unsigned int		i_flags;

#ifdef CONFIG_FS_POSIX_ACL
	struct posix_acl	*i_acl;
	struct posix_acl	*i_default_acl;
#endif

795 796
	const struct inode_operations	*i_op;
	struct super_block	*i_sb;
797
	struct address_space	*i_mapping;
798

799 800 801
#ifdef CONFIG_SECURITY
	void			*i_security;
#endif
802

803 804
	/* Stat data, not accessed from path walking */
	unsigned long		i_ino;
M
Miklos Szeredi 已提交
805 806 807 808 809 810 811 812 813 814 815
	/*
	 * Filesystems may only read i_nlink directly.  They shall use the
	 * following functions for modification:
	 *
	 *    (set|clear|inc|drop)_nlink
	 *    inode_(inc|dec)_link_count
	 */
	union {
		const unsigned int i_nlink;
		unsigned int __i_nlink;
	};
816
	dev_t			i_rdev;
817
	loff_t			i_size;
818 819 820
	struct timespec		i_atime;
	struct timespec		i_mtime;
	struct timespec		i_ctime;
821 822
	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
	unsigned short          i_bytes;
823
	unsigned int		i_blkbits;
824 825 826 827 828 829 830 831 832
	blkcnt_t		i_blocks;

#ifdef __NEED_I_SIZE_ORDERED
	seqcount_t		i_size_seqcount;
#endif

	/* Misc */
	unsigned long		i_state;
	struct mutex		i_mutex;
833

834 835
	unsigned long		dirtied_when;	/* jiffies of first dirtying */

L
Linus Torvalds 已提交
836
	struct hlist_node	i_hash;
N
Nick Piggin 已提交
837 838
	struct list_head	i_wb_list;	/* backing dev IO list */
	struct list_head	i_lru;		/* inode LRU list */
L
Linus Torvalds 已提交
839
	struct list_head	i_sb_list;
N
Nick Piggin 已提交
840
	union {
A
Al Viro 已提交
841
		struct hlist_head	i_dentry;
N
Nick Piggin 已提交
842 843
		struct rcu_head		i_rcu;
	};
844
	u64			i_version;
845
	atomic_t		i_count;
C
Christoph Hellwig 已提交
846
	atomic_t		i_dio_count;
847
	atomic_t		i_writecount;
848
	const struct file_operations	*i_fop;	/* former ->i_op->default_file_ops */
L
Linus Torvalds 已提交
849 850 851 852 853 854
	struct file_lock	*i_flock;
	struct address_space	i_data;
#ifdef CONFIG_QUOTA
	struct dquot		*i_dquot[MAXQUOTAS];
#endif
	struct list_head	i_devices;
855 856
	union {
		struct pipe_inode_info	*i_pipe;
857
		struct block_device	*i_bdev;
858
		struct cdev		*i_cdev;
859
	};
L
Linus Torvalds 已提交
860 861 862

	__u32			i_generation;

863 864
#ifdef CONFIG_FSNOTIFY
	__u32			i_fsnotify_mask; /* all events this inode cares about */
865
	struct hlist_head	i_fsnotify_marks;
R
Robert Love 已提交
866 867
#endif

868
#ifdef CONFIG_IMA
M
Mimi Zohar 已提交
869
	atomic_t		i_readcount; /* struct files open RO */
870
#endif
871
	void			*i_private; /* fs or device private pointer */
L
Linus Torvalds 已提交
872 873
};

A
Al Viro 已提交
874 875 876 877 878
static inline int inode_unhashed(struct inode *inode)
{
	return hlist_unhashed(&inode->i_hash);
}

I
Ingo Molnar 已提交
879 880 881 882 883 884 885 886 887
/*
 * 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
888
 * parent -> child -> normal -> xattr -> quota
I
Ingo Molnar 已提交
889 890 891 892 893 894
 */
enum inode_i_mutex_lock_class
{
	I_MUTEX_NORMAL,
	I_MUTEX_PARENT,
	I_MUTEX_CHILD,
I
Ingo Molnar 已提交
895
	I_MUTEX_XATTR,
I
Ingo Molnar 已提交
896 897 898
	I_MUTEX_QUOTA
};

L
Linus Torvalds 已提交
899 900 901 902 903 904 905 906 907 908
/*
 * 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
909
static inline loff_t i_size_read(const struct inode *inode)
L
Linus Torvalds 已提交
910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931
{
#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
}

932 933 934 935 936
/*
 * 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
937 938 939 940 941 942 943 944 945 946 947 948 949 950 951
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
}

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
/* Helper functions so that in most cases filesystems will
 * not need to deal directly with kuid_t and kgid_t and can
 * instead deal with the raw numeric values that are stored
 * in the filesystem.
 */
static inline uid_t i_uid_read(const struct inode *inode)
{
	return from_kuid(&init_user_ns, inode->i_uid);
}

static inline gid_t i_gid_read(const struct inode *inode)
{
	return from_kgid(&init_user_ns, inode->i_gid);
}

static inline void i_uid_write(struct inode *inode, uid_t uid)
{
	inode->i_uid = make_kuid(&init_user_ns, uid);
}

static inline void i_gid_write(struct inode *inode, gid_t gid)
{
	inode->i_gid = make_kgid(&init_user_ns, gid);
}

J
Jan Engelhardt 已提交
977
static inline unsigned iminor(const struct inode *inode)
L
Linus Torvalds 已提交
978 979 980 981
{
	return MINOR(inode->i_rdev);
}

J
Jan Engelhardt 已提交
982
static inline unsigned imajor(const struct inode *inode)
L
Linus Torvalds 已提交
983 984 985 986 987 988 989 990
{
	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 */
991 992
	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 */
993
	kuid_t uid, euid;	/* uid/euid of process setting the owner */
L
Linus Torvalds 已提交
994 995 996 997 998 999 1000
	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
1001 1002 1003
	pgoff_t start;			/* where readahead started */
	unsigned int size;		/* # of readahead pages */
	unsigned int async_size;	/* do asynchronous readahead when
1004
					   there are only # of pages ahead */
1005

F
Fengguang Wu 已提交
1006
	unsigned int ra_pages;		/* Maximum readahead window */
1007
	unsigned int mmap_miss;		/* Cache miss stat for mmap accesses */
1008
	loff_t prev_pos;		/* Cache last read() position */
L
Linus Torvalds 已提交
1009 1010
};

1011 1012 1013 1014 1015
/*
 * Check if @index falls in the readahead windows.
 */
static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
{
1016 1017
	return (index >= ra->start &&
		index <  ra->start + ra->size);
1018 1019
}

1020 1021 1022
#define FILE_MNT_WRITE_TAKEN	1
#define FILE_MNT_WRITE_RELEASED	2

L
Linus Torvalds 已提交
1023
struct file {
E
Eric Dumazet 已提交
1024 1025 1026 1027 1028 1029 1030 1031
	/*
	 * 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;
1032 1033 1034
	struct path		f_path;
#define f_dentry	f_path.dentry
#define f_vfsmnt	f_path.mnt
1035
	const struct file_operations	*f_op;
1036 1037 1038 1039 1040 1041

	/*
	 * Protects f_ep_links, f_flags, f_pos vs i_size in lseek SEEK_CUR.
	 * Must not be taken from IRQ context.
	 */
	spinlock_t		f_lock;
N
Nick Piggin 已提交
1042 1043 1044
#ifdef CONFIG_SMP
	int			f_sb_list_cpu;
#endif
A
Al Viro 已提交
1045
	atomic_long_t		f_count;
L
Linus Torvalds 已提交
1046
	unsigned int 		f_flags;
1047
	fmode_t			f_mode;
L
Linus Torvalds 已提交
1048 1049
	loff_t			f_pos;
	struct fown_struct	f_owner;
D
David Howells 已提交
1050
	const struct cred	*f_cred;
L
Linus Torvalds 已提交
1051 1052
	struct file_ra_state	f_ra;

1053
	u64			f_version;
1054
#ifdef CONFIG_SECURITY
L
Linus Torvalds 已提交
1055
	void			*f_security;
1056
#endif
L
Linus Torvalds 已提交
1057 1058 1059 1060 1061 1062
	/* 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;
J
Jason Baron 已提交
1063
	struct list_head	f_tfile_llink;
L
Linus Torvalds 已提交
1064 1065
#endif /* #ifdef CONFIG_EPOLL */
	struct address_space	*f_mapping;
1066 1067 1068
#ifdef CONFIG_DEBUG_WRITECOUNT
	unsigned long f_mnt_write_state;
#endif
L
Linus Torvalds 已提交
1069 1070
};

1071 1072 1073 1074 1075 1076 1077
struct file_handle {
	__u32 handle_bytes;
	int handle_type;
	/* file identifier */
	unsigned char f_handle[0];
};

A
Al Viro 已提交
1078
#define get_file(x)	atomic_long_inc(&(x)->f_count)
1079
#define fput_atomic(x)	atomic_long_add_unless(&(x)->f_count, -1, 1)
A
Al Viro 已提交
1080
#define file_count(x)	atomic_long_read(&(x)->f_count)
L
Linus Torvalds 已提交
1081

1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124
#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
1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137
#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 */
1138
#define FL_EXISTS	16	/* when unlocking, test for existence */
L
Linus Torvalds 已提交
1139
#define FL_LEASE	32	/* lease held on this file */
1140
#define FL_CLOSE	64	/* unlock on close */
L
Linus Torvalds 已提交
1141
#define FL_SLEEP	128	/* A blocking lock */
1142 1143
#define FL_DOWNGRADE_PENDING	256 /* Lease is being downgraded */
#define FL_UNLOCK_PENDING	512 /* Lease is being broken */
L
Linus Torvalds 已提交
1144

1145 1146 1147 1148 1149 1150
/*
 * 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
1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165
/*
 * 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 {
J
J. Bruce Fields 已提交
1166 1167 1168 1169 1170
	int (*lm_compare_owner)(struct file_lock *, struct file_lock *);
	void (*lm_notify)(struct file_lock *);	/* unblock callback */
	int (*lm_grant)(struct file_lock *, struct file_lock *, int);
	void (*lm_break)(struct file_lock *);
	int (*lm_change)(struct file_lock **, int);
L
Linus Torvalds 已提交
1171 1172
};

1173 1174 1175 1176
struct lock_manager {
	struct list_head list;
};

1177 1178
struct net;
void locks_start_grace(struct net *, struct lock_manager *);
1179
void locks_end_grace(struct lock_manager *);
1180
int locks_in_grace(struct net *);
1181

L
Linus Torvalds 已提交
1182 1183 1184 1185 1186 1187 1188 1189
/* 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;
1190
	unsigned int fl_flags;
1191
	unsigned char fl_type;
L
Linus Torvalds 已提交
1192
	unsigned int fl_pid;
1193
	struct pid *fl_nspid;
L
Linus Torvalds 已提交
1194 1195 1196 1197 1198 1199
	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 */
1200 1201 1202
	/* for lease breaks: */
	unsigned long fl_break_time;
	unsigned long fl_downgrade_time;
L
Linus Torvalds 已提交
1203

1204
	const struct file_lock_operations *fl_ops;	/* Callbacks for filesystems */
1205
	const struct lock_manager_operations *fl_lmops;	/* Callbacks for lockmanagers */
L
Linus Torvalds 已提交
1206 1207
	union {
		struct nfs_lock_info	nfs_fl;
1208
		struct nfs4_lock_info	nfs4_fl;
D
David Howells 已提交
1209 1210 1211 1212
		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
1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224
	} 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>

1225 1226 1227
extern void send_sigio(struct fown_struct *fown, int fd, int band);

#ifdef CONFIG_FILE_LOCKING
L
Linus Torvalds 已提交
1228
extern int fcntl_getlk(struct file *, struct flock __user *);
1229 1230
extern int fcntl_setlk(unsigned int, struct file *, unsigned int,
			struct flock __user *);
L
Linus Torvalds 已提交
1231 1232 1233

#if BITS_PER_LONG == 32
extern int fcntl_getlk64(struct file *, struct flock64 __user *);
1234 1235
extern int fcntl_setlk64(unsigned int, struct file *, unsigned int,
			struct flock64 __user *);
L
Linus Torvalds 已提交
1236 1237 1238 1239 1240 1241
#endif

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

/* fs/locks.c */
1242
void locks_free_lock(struct file_lock *fl);
L
Linus Torvalds 已提交
1243
extern void locks_init_lock(struct file_lock *);
1244
extern struct file_lock * locks_alloc_lock(void);
L
Linus Torvalds 已提交
1245
extern void locks_copy_lock(struct file_lock *, struct file_lock *);
1246
extern void __locks_copy_lock(struct file_lock *, const struct file_lock *);
L
Linus Torvalds 已提交
1247 1248
extern void locks_remove_posix(struct file *, fl_owner_t);
extern void locks_remove_flock(struct file *);
1249
extern void locks_release_private(struct file_lock *);
1250
extern void posix_test_lock(struct file *, struct file_lock *);
1251
extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *);
L
Linus Torvalds 已提交
1252
extern int posix_lock_file_wait(struct file *, struct file_lock *);
J
J. Bruce Fields 已提交
1253
extern int posix_unblock_lock(struct file *, struct file_lock *);
1254
extern int vfs_test_lock(struct file *, struct file_lock *);
1255
extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *);
M
Marc Eshel 已提交
1256
extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
L
Linus Torvalds 已提交
1257 1258 1259
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);
1260
extern int generic_setlease(struct file *, long, struct file_lock **);
1261
extern int vfs_setlease(struct file *, long, struct file_lock **);
L
Linus Torvalds 已提交
1262 1263 1264
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);
1265
extern void locks_delete_block(struct file_lock *waiter);
1266 1267
extern void lock_flocks(void);
extern void unlock_flocks(void);
1268
#else /* !CONFIG_FILE_LOCKING */
1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279
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;
}

1280
#if BITS_PER_LONG == 32
1281 1282 1283 1284 1285 1286 1287 1288 1289 1290
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;
}
1291
#endif
1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409
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;
}

1410 1411 1412 1413
static inline void locks_delete_block(struct file_lock *waiter)
{
}

1414 1415 1416 1417 1418 1419 1420 1421
static inline void lock_flocks(void)
{
}

static inline void unlock_flocks(void)
{
}

1422 1423
#endif /* !CONFIG_FILE_LOCKING */

L
Linus Torvalds 已提交
1424 1425

struct fasync_struct {
1426 1427 1428 1429 1430 1431
	spinlock_t		fa_lock;
	int			magic;
	int			fa_fd;
	struct fasync_struct	*fa_next; /* singly linked list */
	struct file		*fa_file;
	struct rcu_head		fa_rcu;
L
Linus Torvalds 已提交
1432 1433 1434 1435 1436 1437
};

#define FASYNC_MAGIC 0x4601

/* SMP safe fasync helpers: */
extern int fasync_helper(int, struct file *, int, struct fasync_struct **);
1438 1439 1440 1441 1442
extern struct fasync_struct *fasync_insert_entry(int, struct file *, struct fasync_struct **, struct fasync_struct *);
extern int fasync_remove_entry(struct file *, struct fasync_struct **);
extern struct fasync_struct *fasync_alloc(void);
extern void fasync_free(struct fasync_struct *);

L
Linus Torvalds 已提交
1443 1444 1445
/* can be called from interrupts */
extern void kill_fasync(struct fasync_struct **, int, int);

1446
extern int __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
L
Linus Torvalds 已提交
1447 1448
extern int f_setown(struct file *filp, unsigned long arg, int force);
extern void f_delown(struct file *filp);
1449
extern pid_t f_getown(struct file *filp);
L
Linus Torvalds 已提交
1450 1451
extern int send_sigurg(struct fown_struct *fown);

1452 1453
struct mm_struct;

L
Linus Torvalds 已提交
1454 1455 1456 1457 1458 1459 1460
/*
 *	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 */
1461 1462
#define UMOUNT_NOFOLLOW	0x00000008	/* Don't follow symlink on umount */
#define UMOUNT_UNUSED	0x80000000	/* Flag guaranteed to be unused */
L
Linus Torvalds 已提交
1463 1464 1465 1466

extern struct list_head super_blocks;
extern spinlock_t sb_lock;

1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491
/* Possible states of 'frozen' field */
enum {
	SB_UNFROZEN = 0,		/* FS is unfrozen */
	SB_FREEZE_WRITE	= 1,		/* Writes, dir ops, ioctls frozen */
	SB_FREEZE_PAGEFAULT = 2,	/* Page faults stopped as well */
	SB_FREEZE_FS = 3,		/* For internal FS use (e.g. to stop
					 * internal threads if needed) */
	SB_FREEZE_COMPLETE = 4,		/* ->freeze_fs finished successfully */
};

#define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1)

struct sb_writers {
	/* Counters for counting writers at each level */
	struct percpu_counter	counter[SB_FREEZE_LEVELS];
	wait_queue_head_t	wait;		/* queue for waiting for
						   writers / faults to finish */
	int			frozen;		/* Is sb frozen? */
	wait_queue_head_t	wait_unfrozen;	/* queue for waiting for
						   sb to be thawed */
#ifdef CONFIG_DEBUG_LOCK_ALLOC
	struct lockdep_map	lock_map[SB_FREEZE_LEVELS];
#endif
};

L
Linus Torvalds 已提交
1492 1493 1494
struct super_block {
	struct list_head	s_list;		/* Keep this first */
	dev_t			s_dev;		/* search index; _not_ kdev_t */
1495 1496
	unsigned char		s_blocksize_bits;
	unsigned long		s_blocksize;
1497
	loff_t			s_maxbytes;	/* Max file size */
L
Linus Torvalds 已提交
1498
	struct file_system_type	*s_type;
1499
	const struct super_operations	*s_op;
1500
	const struct dquot_operations	*dq_op;
1501
	const struct quotactl_ops	*s_qcop;
1502
	const struct export_operations *s_export_op;
L
Linus Torvalds 已提交
1503 1504 1505 1506
	unsigned long		s_flags;
	unsigned long		s_magic;
	struct dentry		*s_root;
	struct rw_semaphore	s_umount;
1507
	struct mutex		s_lock;
L
Linus Torvalds 已提交
1508 1509
	int			s_count;
	atomic_t		s_active;
1510
#ifdef CONFIG_SECURITY
L
Linus Torvalds 已提交
1511
	void                    *s_security;
1512
#endif
1513
	const struct xattr_handler **s_xattr;
L
Linus Torvalds 已提交
1514 1515

	struct list_head	s_inodes;	/* all inodes */
1516
	struct hlist_bl_head	s_anon;		/* anonymous dentries for (nfs) exporting */
N
Nick Piggin 已提交
1517 1518 1519
#ifdef CONFIG_SMP
	struct list_head __percpu *s_files;
#else
L
Linus Torvalds 已提交
1520
	struct list_head	s_files;
N
Nick Piggin 已提交
1521
#endif
1522
	struct list_head	s_mounts;	/* list of mounts; _not_ for fs use */
N
Nick Piggin 已提交
1523
	/* s_dentry_lru, s_nr_dentry_unused protected by dcache.c lru locks */
1524 1525
	struct list_head	s_dentry_lru;	/* unused dentry lru */
	int			s_nr_dentry_unused;	/* # of dentry on lru */
L
Linus Torvalds 已提交
1526

D
Dave Chinner 已提交
1527 1528
	/* s_inode_lru_lock protects s_inode_lru and s_nr_inodes_unused */
	spinlock_t		s_inode_lru_lock ____cacheline_aligned_in_smp;
1529 1530 1531
	struct list_head	s_inode_lru;		/* unused inode lru */
	int			s_nr_inodes_unused;	/* # of inodes on lru */

L
Linus Torvalds 已提交
1532
	struct block_device	*s_bdev;
J
Jens Axboe 已提交
1533
	struct backing_dev_info *s_bdi;
1534
	struct mtd_info		*s_mtd;
A
Al Viro 已提交
1535
	struct hlist_node	s_instances;
L
Linus Torvalds 已提交
1536 1537
	struct quota_info	s_dquot;	/* Diskquota specific options */

1538
	struct sb_writers	s_writers;
L
Linus Torvalds 已提交
1539 1540

	char s_id[32];				/* Informational name */
1541
	u8 s_uuid[16];				/* UUID */
L
Linus Torvalds 已提交
1542 1543

	void 			*s_fs_info;	/* Filesystem private info */
1544
	unsigned int		s_max_links;
1545
	fmode_t			s_mode;
L
Linus Torvalds 已提交
1546

1547 1548 1549 1550
	/* Granularity of c/m/atime in ns.
	   Cannot be worse than a second */
	u32		   s_time_gran;

L
Linus Torvalds 已提交
1551 1552 1553 1554
	/*
	 * The next field is for VFS *only*. No filesystems have any business
	 * even looking at it. You had been warned.
	 */
1555
	struct mutex s_vfs_rename_mutex;	/* Kludge */
L
Linus Torvalds 已提交
1556

M
Miklos Szeredi 已提交
1557 1558 1559 1560 1561
	/*
	 * Filesystem subtype.  If non-empty the filesystem type field
	 * in /proc/mounts will be "type.subtype"
	 */
	char *s_subtype;
1562 1563 1564 1565 1566

	/*
	 * Saved mount options for lazy filesystems using
	 * generic_show_options()
	 */
A
Arnd Bergmann 已提交
1567
	char __rcu *s_options;
A
Al Viro 已提交
1568
	const struct dentry_operations *s_d_op; /* default d_op for dentries */
1569 1570 1571 1572 1573

	/*
	 * Saved pool identifier for cleancache (-1 means none)
	 */
	int cleancache_poolid;
1574 1575

	struct shrinker s_shrink;	/* per-sb shrinker handle */
1576

M
Miklos Szeredi 已提交
1577 1578 1579
	/* Number of inodes with nlink == 0 but still referenced */
	atomic_long_t s_remove_count;

1580 1581
	/* Being remounted read-only */
	int s_readonly_remount;
L
Linus Torvalds 已提交
1582 1583
};

1584 1585 1586 1587
/* superblock cache pruning functions */
extern void prune_icache_sb(struct super_block *sb, int nr_to_scan);
extern void prune_dcache_sb(struct super_block *sb, int nr_to_scan);

L
Linus Torvalds 已提交
1588 1589 1590 1591 1592 1593
extern struct timespec current_fs_time(struct super_block *sb);

/*
 * Snapshotting support.
 */

1594 1595 1596 1597 1598 1599 1600 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 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702
void __sb_end_write(struct super_block *sb, int level);
int __sb_start_write(struct super_block *sb, int level, bool wait);

/**
 * sb_end_write - drop write access to a superblock
 * @sb: the super we wrote to
 *
 * Decrement number of writers to the filesystem. Wake up possible waiters
 * wanting to freeze the filesystem.
 */
static inline void sb_end_write(struct super_block *sb)
{
	__sb_end_write(sb, SB_FREEZE_WRITE);
}

/**
 * sb_end_pagefault - drop write access to a superblock from a page fault
 * @sb: the super we wrote to
 *
 * Decrement number of processes handling write page fault to the filesystem.
 * Wake up possible waiters wanting to freeze the filesystem.
 */
static inline void sb_end_pagefault(struct super_block *sb)
{
	__sb_end_write(sb, SB_FREEZE_PAGEFAULT);
}

/**
 * sb_end_intwrite - drop write access to a superblock for internal fs purposes
 * @sb: the super we wrote to
 *
 * Decrement fs-internal number of writers to the filesystem.  Wake up possible
 * waiters wanting to freeze the filesystem.
 */
static inline void sb_end_intwrite(struct super_block *sb)
{
	__sb_end_write(sb, SB_FREEZE_FS);
}

/**
 * sb_start_write - get write access to a superblock
 * @sb: the super we write to
 *
 * When a process wants to write data or metadata to a file system (i.e. dirty
 * a page or an inode), it should embed the operation in a sb_start_write() -
 * sb_end_write() pair to get exclusion against file system freezing. This
 * function increments number of writers preventing freezing. If the file
 * system is already frozen, the function waits until the file system is
 * thawed.
 *
 * Since freeze protection behaves as a lock, users have to preserve
 * ordering of freeze protection and other filesystem locks. Generally,
 * freeze protection should be the outermost lock. In particular, we have:
 *
 * sb_start_write
 *   -> i_mutex			(write path, truncate, directory ops, ...)
 *   -> s_umount		(freeze_super, thaw_super)
 */
static inline void sb_start_write(struct super_block *sb)
{
	__sb_start_write(sb, SB_FREEZE_WRITE, true);
}

static inline int sb_start_write_trylock(struct super_block *sb)
{
	return __sb_start_write(sb, SB_FREEZE_WRITE, false);
}

/**
 * sb_start_pagefault - get write access to a superblock from a page fault
 * @sb: the super we write to
 *
 * When a process starts handling write page fault, it should embed the
 * operation into sb_start_pagefault() - sb_end_pagefault() pair to get
 * exclusion against file system freezing. This is needed since the page fault
 * is going to dirty a page. This function increments number of running page
 * faults preventing freezing. If the file system is already frozen, the
 * function waits until the file system is thawed.
 *
 * Since page fault freeze protection behaves as a lock, users have to preserve
 * ordering of freeze protection and other filesystem locks. It is advised to
 * put sb_start_pagefault() close to mmap_sem in lock ordering. Page fault
 * handling code implies lock dependency:
 *
 * mmap_sem
 *   -> sb_start_pagefault
 */
static inline void sb_start_pagefault(struct super_block *sb)
{
	__sb_start_write(sb, SB_FREEZE_PAGEFAULT, true);
}

/*
 * sb_start_intwrite - get write access to a superblock for internal fs purposes
 * @sb: the super we write to
 *
 * This is the third level of protection against filesystem freezing. It is
 * free for use by a filesystem. The only requirement is that it must rank
 * below sb_start_pagefault.
 *
 * For example filesystem can call sb_start_intwrite() when starting a
 * transaction which somewhat eases handling of freezing for internal sources
 * of filesystem changes (internal fs threads, discarding preallocation on file
 * close, etc.).
 */
static inline void sb_start_intwrite(struct super_block *sb)
{
	__sb_start_write(sb, SB_FREEZE_FS, true);
}
L
Linus Torvalds 已提交
1703 1704


1705
extern bool inode_owner_or_capable(const struct inode *inode);
1706

1707 1708 1709
/* 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
1710 1711 1712 1713

/*
 * VFS helper functions..
 */
A
Al Viro 已提交
1714
extern int vfs_create(struct inode *, struct dentry *, umode_t, bool);
1715
extern int vfs_mkdir(struct inode *, struct dentry *, umode_t);
A
Al Viro 已提交
1716
extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
1717
extern int vfs_symlink(struct inode *, struct dentry *, const char *);
L
Linus Torvalds 已提交
1718 1719 1720 1721 1722 1723 1724 1725 1726 1727
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);

1728 1729 1730
/*
 * VFS file helper functions.
 */
1731
extern void inode_init_owner(struct inode *inode, const struct inode *dir,
A
Al Viro 已提交
1732
			umode_t mode);
M
Mark Fasheh 已提交
1733 1734 1735 1736 1737 1738 1739
/*
 * 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 */
1740 1741
	struct fiemap_extent __user *fi_extents_start; /* Start of
							fiemap_extent array */
M
Mark Fasheh 已提交
1742 1743 1744 1745 1746
};
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
1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768
/*
 * File types
 *
 * NOTE! These match bits 12..15 of stat.st_mode
 * (ie "(i_mode >> 12) & 15").
 */
#define DT_UNKNOWN	0
#define DT_FIFO		1
#define DT_CHR		2
#define DT_DIR		4
#define DT_BLK		6
#define DT_REG		8
#define DT_LNK		10
#define DT_SOCK		12
#define DT_WHT		14

/*
 * This is the "filldir" function type, used by readdir() to let
 * the kernel specify what kind of dirent layout it wants to have.
 * This allows the kernel to read directories into kernel space or
 * to have different dirent layouts depending on the binary type.
 */
1769
typedef int (*filldir_t)(void *, const char *, int, loff_t, u64, unsigned);
1770
struct block_device_operations;
L
Linus Torvalds 已提交
1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782

/* 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

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 *);
1783 1784
	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
1785 1786 1787 1788 1789 1790
	int (*readdir) (struct file *, void *, filldir_t);
	unsigned int (*poll) (struct file *, struct poll_table_struct *);
	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
	int (*mmap) (struct file *, struct vm_area_struct *);
	int (*open) (struct inode *, struct file *);
1791
	int (*flush) (struct file *, fl_owner_t id);
L
Linus Torvalds 已提交
1792
	int (*release) (struct inode *, struct file *);
1793
	int (*fsync) (struct file *, loff_t, loff_t, int datasync);
L
Linus Torvalds 已提交
1794 1795 1796 1797 1798 1799 1800
	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 *);
1801 1802
	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);
1803
	int (*setlease)(struct file *, long, struct file_lock **);
1804 1805
	long (*fallocate)(struct file *file, int mode, loff_t offset,
			  loff_t len);
L
Linus Torvalds 已提交
1806 1807 1808
};

struct inode_operations {
A
Al Viro 已提交
1809
	struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
1810
	void * (*follow_link) (struct dentry *, struct nameidata *);
1811
	int (*permission) (struct inode *, int);
1812
	struct posix_acl * (*get_acl)(struct inode *, int);
1813 1814 1815 1816

	int (*readlink) (struct dentry *, char __user *,int);
	void (*put_link) (struct dentry *, struct nameidata *, void *);

A
Al Viro 已提交
1817
	int (*create) (struct inode *,struct dentry *, umode_t, bool);
L
Linus Torvalds 已提交
1818 1819 1820
	int (*link) (struct dentry *,struct inode *,struct dentry *);
	int (*unlink) (struct inode *,struct dentry *);
	int (*symlink) (struct inode *,struct dentry *,const char *);
1821
	int (*mkdir) (struct inode *,struct dentry *,umode_t);
L
Linus Torvalds 已提交
1822
	int (*rmdir) (struct inode *,struct dentry *);
A
Al Viro 已提交
1823
	int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
L
Linus Torvalds 已提交
1824 1825 1826 1827 1828 1829 1830 1831 1832
	int (*rename) (struct inode *, struct dentry *,
			struct inode *, struct dentry *);
	void (*truncate) (struct inode *);
	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 *);
M
Mark Fasheh 已提交
1833 1834
	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
		      u64 len);
1835
	int (*update_time)(struct inode *, struct timespec *, int);
A
Al Viro 已提交
1836
	int (*atomic_open)(struct inode *, struct dentry *,
A
Al Viro 已提交
1837
			   struct file *, unsigned open_flag,
A
Al Viro 已提交
1838
			   umode_t create_mode, int *opened);
1839
} ____cacheline_aligned;
L
Linus Torvalds 已提交
1840 1841 1842

struct seq_file;

B
Badari Pulavarty 已提交
1843
ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
C
Christopher Yeoh 已提交
1844 1845
			      unsigned long nr_segs, unsigned long fast_segs,
			      struct iovec *fast_pointer,
1846
			      struct iovec **ret_pointer);
B
Badari Pulavarty 已提交
1847

L
Linus Torvalds 已提交
1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858
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 *);

1859
   	void (*dirty_inode) (struct inode *, int flags);
1860
	int (*write_inode) (struct inode *, struct writeback_control *wbc);
1861
	int (*drop_inode) (struct inode *);
A
Al Viro 已提交
1862
	void (*evict_inode) (struct inode *);
L
Linus Torvalds 已提交
1863 1864
	void (*put_super) (struct super_block *);
	int (*sync_fs)(struct super_block *sb, int wait);
1865 1866
	int (*freeze_fs) (struct super_block *);
	int (*unfreeze_fs) (struct super_block *);
1867
	int (*statfs) (struct dentry *, struct kstatfs *);
L
Linus Torvalds 已提交
1868
	int (*remount_fs) (struct super_block *, int *, char *);
1869
	void (*umount_begin) (struct super_block *);
L
Linus Torvalds 已提交
1870

1871
	int (*show_options)(struct seq_file *, struct dentry *);
1872
	int (*show_devname)(struct seq_file *, struct dentry *);
1873
	int (*show_path)(struct seq_file *, struct dentry *);
1874
	int (*show_stats)(struct seq_file *, struct dentry *);
1875
#ifdef CONFIG_QUOTA
L
Linus Torvalds 已提交
1876 1877
	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);
1878
#endif
1879
	int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
1880 1881
	int (*nr_cached_objects)(struct super_block *);
	void (*free_cached_objects)(struct super_block *, int);
L
Linus Torvalds 已提交
1882 1883
};

J
Joern Engel 已提交
1884
/*
1885
 * Inode state bits.  Protected by inode->i_lock
J
Joern Engel 已提交
1886 1887 1888 1889 1890 1891 1892 1893
 *
 * Three bits determine the dirty state of the inode, I_DIRTY_SYNC,
 * I_DIRTY_DATASYNC and I_DIRTY_PAGES.
 *
 * Four bits define the lifetime of an inode.  Initially, inodes are I_NEW,
 * until that flag is cleared.  I_WILL_FREE, I_FREEING and I_CLEAR are set at
 * various stages of removing an inode.
 *
C
Christoph Hellwig 已提交
1894
 * Two bits are used for locking and completion notification, I_NEW and I_SYNC.
J
Joern Engel 已提交
1895
 *
J
Joern Engel 已提交
1896 1897
 * I_DIRTY_SYNC		Inode is dirty, but doesn't have to be written on
 *			fdatasync().  i_atime is the usual cause.
1898 1899 1900 1901
 * 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
1902
 * I_DIRTY_PAGES	Inode has dirty pages.  Inode itself may be clean.
C
Christoph Hellwig 已提交
1903 1904 1905 1906 1907 1908 1909 1910
 * I_NEW		Serves as both a mutex and completion notification.
 *			New inodes set I_NEW.  If two processes both create
 *			the same inode, one of them will release its inode and
 *			wait for I_NEW to be released before returning.
 *			Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can
 *			also cause waiting on I_NEW, without I_NEW actually
 *			being set.  find_inode() uses this to prevent returning
 *			nearly-dead inodes.
J
Joern Engel 已提交
1911 1912 1913 1914 1915 1916
 * 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.
1917 1918
 * I_CLEAR		Added by clear_inode().  In this state the inode is
 *			clean and can be destroyed.  Inode keeps I_FREEING.
J
Joern Engel 已提交
1919 1920 1921 1922 1923
 *
 *			Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are
 *			prohibited for many purposes.  iget() must wait for
 *			the inode to be completely released, then create it
 *			anew.  Other functions will just ignore such inodes,
C
Christoph Hellwig 已提交
1924
 *			if appropriate.  I_NEW is used for waiting.
J
Joern Engel 已提交
1925
 *
1926 1927 1928 1929
 * I_SYNC		Writeback of inode is running. The bit is set during
 *			data writeback, and cleared with a wakeup on the bit
 *			address once it is done. The bit is also used to pin
 *			the inode in memory for flusher thread.
J
Joern Engel 已提交
1930
 *
C
Christoph Hellwig 已提交
1931 1932 1933 1934
 * I_REFERENCED		Marks the inode as recently references on the LRU list.
 *
 * I_DIO_WAKEUP		Never set.  Only used as a key for wait_on_bit().
 *
J
Joern Engel 已提交
1935 1936
 * Q: What is the difference between I_WILL_FREE and I_FREEING?
 */
1937 1938 1939
#define I_DIRTY_SYNC		(1 << 0)
#define I_DIRTY_DATASYNC	(1 << 1)
#define I_DIRTY_PAGES		(1 << 2)
C
Christoph Hellwig 已提交
1940 1941
#define __I_NEW			3
#define I_NEW			(1 << __I_NEW)
1942 1943 1944
#define I_WILL_FREE		(1 << 4)
#define I_FREEING		(1 << 5)
#define I_CLEAR			(1 << 6)
C
Christoph Hellwig 已提交
1945
#define __I_SYNC		7
J
Joern Engel 已提交
1946
#define I_SYNC			(1 << __I_SYNC)
1947
#define I_REFERENCED		(1 << 8)
C
Christoph Hellwig 已提交
1948 1949
#define __I_DIO_WAKEUP		9
#define I_DIO_WAKEUP		(1 << I_DIO_WAKEUP)
L
Linus Torvalds 已提交
1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963

#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);
}

M
Miklos Szeredi 已提交
1964 1965 1966 1967
extern void inc_nlink(struct inode *inode);
extern void drop_nlink(struct inode *inode);
extern void clear_nlink(struct inode *inode);
extern void set_nlink(struct inode *inode, unsigned int nlink);
1968 1969 1970 1971

static inline void inode_inc_link_count(struct inode *inode)
{
	inc_nlink(inode);
1972 1973 1974
	mark_inode_dirty(inode);
}

1975 1976 1977
static inline void inode_dec_link_count(struct inode *inode)
{
	drop_nlink(inode);
1978 1979 1980
	mark_inode_dirty(inode);
}

1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995
/**
 * 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);
}

1996 1997 1998 1999 2000 2001 2002
enum file_time_flags {
	S_ATIME = 1,
	S_MTIME = 2,
	S_CTIME = 4,
	S_VERSION = 8,
};

A
Al Viro 已提交
2003
extern void touch_atime(struct path *);
L
Linus Torvalds 已提交
2004 2005 2006
static inline void file_accessed(struct file *file)
{
	if (!(file->f_flags & O_NOATIME))
A
Al Viro 已提交
2007
		touch_atime(&file->f_path);
L
Linus Torvalds 已提交
2008 2009 2010
}

int sync_inode(struct inode *inode, struct writeback_control *wbc);
C
Christoph Hellwig 已提交
2011
int sync_inode_metadata(struct inode *inode, int wait);
L
Linus Torvalds 已提交
2012 2013 2014 2015

struct file_system_type {
	const char *name;
	int fs_flags;
A
Al Viro 已提交
2016 2017
	struct dentry *(*mount) (struct file_system_type *, int,
		       const char *, void *);
L
Linus Torvalds 已提交
2018 2019 2020
	void (*kill_sb) (struct super_block *);
	struct module *owner;
	struct file_system_type * next;
A
Al Viro 已提交
2021
	struct hlist_head fs_supers;
2022

I
Ingo Molnar 已提交
2023
	struct lock_class_key s_lock_key;
2024
	struct lock_class_key s_umount_key;
2025
	struct lock_class_key s_vfs_rename_key;
2026
	struct lock_class_key s_writers_key[SB_FREEZE_LEVELS];
2027 2028 2029

	struct lock_class_key i_lock_key;
	struct lock_class_key i_mutex_key;
2030
	struct lock_class_key i_mutex_dir_key;
L
Linus Torvalds 已提交
2031 2032
};

A
Al Viro 已提交
2033 2034
extern struct dentry *mount_ns(struct file_system_type *fs_type, int flags,
	void *data, int (*fill_super)(struct super_block *, void *, int));
A
Al Viro 已提交
2035 2036 2037
extern struct dentry *mount_bdev(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *data,
	int (*fill_super)(struct super_block *, void *, int));
A
Al Viro 已提交
2038 2039 2040
extern struct dentry *mount_single(struct file_system_type *fs_type,
	int flags, void *data,
	int (*fill_super)(struct super_block *, void *, int));
A
Al Viro 已提交
2041 2042 2043
extern struct dentry *mount_nodev(struct file_system_type *fs_type,
	int flags, void *data,
	int (*fill_super)(struct super_block *, void *, int));
A
Al Viro 已提交
2044
extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path);
L
Linus Torvalds 已提交
2045 2046 2047 2048 2049
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
2050
void deactivate_locked_super(struct super_block *sb);
L
Linus Torvalds 已提交
2051
int set_anon_super(struct super_block *s, void *data);
2052 2053
int get_anon_bdev(dev_t *);
void free_anon_bdev(dev_t);
L
Linus Torvalds 已提交
2054 2055 2056
struct super_block *sget(struct file_system_type *type,
			int (*test)(struct super_block *,void *),
			int (*set)(struct super_block *,void *),
D
David Howells 已提交
2057
			int flags, void *data);
A
Al Viro 已提交
2058
extern struct dentry *mount_pseudo(struct file_system_type *, char *,
2059 2060 2061
	const struct super_operations *ops,
	const struct dentry_operations *dops,
	unsigned long);
L
Linus Torvalds 已提交
2062 2063 2064 2065 2066 2067 2068 2069 2070

/* 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 *);
2071 2072
extern struct vfsmount *kern_mount_data(struct file_system_type *, void *data);
#define kern_mount(type) kern_mount_data(type, NULL)
2073
extern void kern_unmount(struct vfsmount *mnt);
L
Linus Torvalds 已提交
2074 2075 2076
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
2077
extern struct vfsmount *collect_mounts(struct path *);
2078
extern void drop_collected_mounts(struct vfsmount *);
A
Al Viro 已提交
2079 2080
extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *,
			  struct vfsmount *);
2081
extern int vfs_statfs(struct path *, struct kstatfs *);
A
Al Viro 已提交
2082 2083
extern int user_statfs(const char __user *, struct kstatfs *);
extern int fd_statfs(int, struct kstatfs *);
A
Al Viro 已提交
2084
extern int vfs_ustat(dev_t, struct kstatfs *);
2085 2086
extern int freeze_super(struct super_block *super);
extern int thaw_super(struct super_block *super);
2087
extern bool our_mnt(struct vfsmount *mnt);
L
Linus Torvalds 已提交
2088

A
Al Viro 已提交
2089 2090
extern int current_umask(void);

M
Miklos Szeredi 已提交
2091
/* /sys/fs */
2092
extern struct kobject *fs_kobj;
M
Miklos Szeredi 已提交
2093

2094
#define MAX_RW_COUNT (INT_MAX & PAGE_CACHE_MASK)
2095 2096
extern int rw_verify_area(int, struct file *, loff_t *, size_t);

L
Linus Torvalds 已提交
2097 2098 2099
#define FLOCK_VERIFY_READ  1
#define FLOCK_VERIFY_WRITE 2

2100
#ifdef CONFIG_FILE_LOCKING
L
Linus Torvalds 已提交
2101 2102 2103 2104 2105 2106 2107
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.
 */
2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122

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
2123 2124 2125

static inline int locks_verify_locked(struct inode *inode)
{
2126
	if (mandatory_lock(inode))
L
Linus Torvalds 已提交
2127 2128 2129 2130 2131 2132 2133 2134
		return locks_mandatory_locked(inode);
	return 0;
}

static inline int locks_verify_truncate(struct inode *inode,
				    struct file *filp,
				    loff_t size)
{
2135
	if (inode->i_flock && mandatory_lock(inode))
L
Linus Torvalds 已提交
2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150
		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;
}
2151
#else /* !CONFIG_FILE_LOCKING */
2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189
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;
}

2190
#endif /* CONFIG_FILE_LOCKING */
L
Linus Torvalds 已提交
2191 2192 2193

/* fs/open.c */

2194 2195
extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs,
		       struct file *filp);
2196 2197
extern int do_fallocate(struct file *file, int mode, loff_t offset,
			loff_t len);
J
Jason Uhlenkott 已提交
2198
extern long do_sys_open(int dfd, const char __user *filename, int flags,
2199 2200
			umode_t mode);
extern struct file *filp_open(const char *, int, umode_t);
A
Al Viro 已提交
2201 2202
extern struct file *file_open_root(struct dentry *, struct vfsmount *,
				   const char *, int);
2203
extern struct file * dentry_open(const struct path *, int, const struct cred *);
L
Linus Torvalds 已提交
2204 2205
extern int filp_close(struct file *, fl_owner_t id);
extern char * getname(const char __user *);
2206 2207 2208 2209
enum {
	FILE_CREATED = 1,
	FILE_OPENED = 2
};
A
Al Viro 已提交
2210 2211 2212
extern int finish_open(struct file *file, struct dentry *dentry,
			int (*open)(struct inode *, struct file *),
			int *opened);
A
Al Viro 已提交
2213
extern int finish_no_open(struct file *file, struct dentry *dentry);
L
Linus Torvalds 已提交
2214

2215 2216 2217 2218
/* fs/ioctl.c */

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

L
Linus Torvalds 已提交
2219 2220 2221 2222
/* fs/dcache.c */
extern void __init vfs_caches_init_early(void);
extern void __init vfs_caches_init(unsigned long);

2223 2224
extern struct kmem_cache *names_cachep;

V
Vegard Nossum 已提交
2225 2226 2227
#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
2228 2229 2230 2231 2232 2233
#ifndef CONFIG_AUDITSYSCALL
#define putname(name)   __putname(name)
#else
extern void putname(const char *name);
#endif

2234
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2235
extern int register_blkdev(unsigned int, const char *);
A
Akinobu Mita 已提交
2236
extern void unregister_blkdev(unsigned int, const char *);
L
Linus Torvalds 已提交
2237
extern struct block_device *bdget(dev_t);
2238
extern struct block_device *bdgrab(struct block_device *bdev);
L
Linus Torvalds 已提交
2239
extern void bd_set_size(struct block_device *, loff_t size);
2240
extern sector_t blkdev_max_block(struct block_device *bdev);
L
Linus Torvalds 已提交
2241 2242
extern void bd_forget(struct inode *inode);
extern void bdput(struct block_device *);
N
Nick Piggin 已提交
2243
extern void invalidate_bdev(struct block_device *);
2244
extern void iterate_bdevs(void (*)(struct block_device *, void *), void *);
N
Nick Piggin 已提交
2245
extern int sync_blockdev(struct block_device *bdev);
A
Al Viro 已提交
2246
extern void kill_bdev(struct block_device *);
N
Nick Piggin 已提交
2247
extern struct super_block *freeze_bdev(struct block_device *);
2248
extern void emergency_thaw_all(void);
N
Nick Piggin 已提交
2249 2250
extern int thaw_bdev(struct block_device *bdev, struct super_block *sb);
extern int fsync_bdev(struct block_device *);
2251 2252
#else
static inline void bd_forget(struct inode *inode) {}
2253
static inline int sync_blockdev(struct block_device *bdev) { return 0; }
A
Al Viro 已提交
2254
static inline void kill_bdev(struct block_device *bdev) {}
2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265
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;
}
2266 2267 2268 2269

static inline void iterate_bdevs(void (*f)(struct block_device *, void *), void *arg)
{
}
2270
#endif
2271
extern int sync_filesystem(struct super_block *);
2272
extern const struct file_operations def_blk_fops;
2273 2274 2275
extern const struct file_operations def_chr_fops;
extern const struct file_operations bad_sock_fops;
extern const struct file_operations def_fifo_fops;
2276
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2277
extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long);
2278
extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long);
L
Linus Torvalds 已提交
2279
extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long);
2280
extern int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder);
2281 2282 2283 2284
extern struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
					       void *holder);
extern struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode,
					      void *holder);
2285
extern int blkdev_put(struct block_device *bdev, fmode_t mode);
2286
#ifdef CONFIG_SYSFS
2287
extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk);
2288 2289
extern void bd_unlink_disk_holder(struct block_device *bdev,
				  struct gendisk *disk);
2290
#else
2291 2292 2293 2294 2295
static inline int bd_link_disk_holder(struct block_device *bdev,
				      struct gendisk *disk)
{
	return 0;
}
2296 2297 2298 2299
static inline void bd_unlink_disk_holder(struct block_device *bdev,
					 struct gendisk *disk)
{
}
2300
#endif
2301
#endif
L
Linus Torvalds 已提交
2302 2303

/* fs/char_dev.c */
2304
#define CHRDEV_MAJOR_HASH_SIZE	255
L
Linus Torvalds 已提交
2305 2306
extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *);
extern int register_chrdev_region(dev_t, unsigned, const char *);
2307 2308 2309 2310 2311
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
2312
extern void unregister_chrdev_region(dev_t, unsigned);
2313
extern void chrdev_show(struct seq_file *,off_t);
L
Linus Torvalds 已提交
2314

2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325
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
2326 2327
/* fs/block_dev.c */
#define BDEVNAME_SIZE	32	/* Largest string for a blockdev identifier */
2328
#define BDEVT_SIZE	10	/* Largest string for MAJ:MIN for blkdev */
2329 2330 2331

#ifdef CONFIG_BLOCK
#define BLKDEV_MAJOR_HASH_SIZE	255
L
Linus Torvalds 已提交
2332 2333 2334
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 *);
2335
extern void blkdev_show(struct seq_file *,off_t);
2336

2337 2338 2339
#else
#define BLKDEV_MAJOR_HASH_SIZE	0
#endif
L
Linus Torvalds 已提交
2340 2341 2342 2343 2344 2345 2346

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 *);

2347 2348 2349
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
2350

2351
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2352 2353 2354 2355 2356 2357 2358 2359 2360 2361
/*
 * 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)

2362 2363
extern void check_disk_size_change(struct gendisk *disk,
				   struct block_device *bdev);
2364
extern int revalidate_disk(struct gendisk *);
L
Linus Torvalds 已提交
2365
extern int check_disk_change(struct block_device *);
2366
extern int __invalidate_device(struct block_device *, bool);
L
Linus Torvalds 已提交
2367
extern int invalidate_partition(struct gendisk *, int);
2368
#endif
L
Linus Torvalds 已提交
2369 2370
unsigned long invalidate_mapping_pages(struct address_space *mapping,
					pgoff_t start, pgoff_t end);
2371

L
Linus Torvalds 已提交
2372 2373 2374 2375
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))
2376
		invalidate_mapping_pages(inode->i_mapping, 0, -1);
L
Linus Torvalds 已提交
2377 2378 2379 2380 2381 2382 2383 2384
}
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 *);
2385 2386
extern int filemap_fdatawait_range(struct address_space *, loff_t lstart,
				   loff_t lend);
L
Linus Torvalds 已提交
2387 2388 2389
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);
2390 2391
extern int __filemap_fdatawrite_range(struct address_space *mapping,
				loff_t start, loff_t end, int sync_mode);
2392 2393
extern int filemap_fdatawrite_range(struct address_space *mapping,
				loff_t start, loff_t end);
2394

2395 2396 2397
extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end,
			   int datasync);
extern int vfs_fsync(struct file *file, int datasync);
2398
extern int generic_write_sync(struct file *file, loff_t pos, loff_t count);
L
Linus Torvalds 已提交
2399 2400
extern void emergency_sync(void);
extern void emergency_remount(void);
2401
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2402
extern sector_t bmap(struct inode *, sector_t);
2403
#endif
L
Linus Torvalds 已提交
2404
extern int notify_change(struct dentry *, struct iattr *);
2405
extern int inode_permission(struct inode *, int);
2406
extern int generic_permission(struct inode *, int);
L
Linus Torvalds 已提交
2407

2408 2409 2410 2411 2412
static inline bool execute_ok(struct inode *inode)
{
	return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode);
}

2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437
/*
 * get_write_access() gets write permission for a file.
 * put_write_access() releases this write permission.
 * This is used for regular files.
 * We cannot support write (and maybe mmap read-write shared) accesses and
 * MAP_DENYWRITE mmappings simultaneously. The i_writecount field of an inode
 * can have the following values:
 * 0: no writers, no VM_DENYWRITE mappings
 * < 0: (-i_writecount) vm_area_structs with VM_DENYWRITE set exist
 * > 0: (i_writecount) users are writing to the file.
 *
 * Normally we operate on that counter with atomic_{inc,dec} and it's safe
 * except for the cases where we don't hold i_writecount yet. Then we need to
 * use {get,deny}_write_access() - these functions check the sign and refuse
 * to do the change if sign is wrong.
 */
static inline int get_write_access(struct inode *inode)
{
	return atomic_inc_unless_negative(&inode->i_writecount) ? 0 : -ETXTBSY;
}
static inline int deny_write_access(struct file *file)
{
	struct inode *inode = file->f_path.dentry->d_inode;
	return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY;
}
L
Linus Torvalds 已提交
2438 2439 2440 2441 2442 2443 2444
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)
2445
		atomic_inc(&file->f_path.dentry->d_inode->i_writecount);
L
Linus Torvalds 已提交
2446
}
M
Mimi Zohar 已提交
2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466
#ifdef CONFIG_IMA
static inline void i_readcount_dec(struct inode *inode)
{
	BUG_ON(!atomic_read(&inode->i_readcount));
	atomic_dec(&inode->i_readcount);
}
static inline void i_readcount_inc(struct inode *inode)
{
	atomic_inc(&inode->i_readcount);
}
#else
static inline void i_readcount_dec(struct inode *inode)
{
	return;
}
static inline void i_readcount_inc(struct inode *inode)
{
	return;
}
#endif
U
Ulrich Drepper 已提交
2467
extern int do_pipe_flags(int *, int);
L
Linus Torvalds 已提交
2468

M
Mimi Zohar 已提交
2469
extern int kernel_read(struct file *, loff_t, char *, unsigned long);
L
Linus Torvalds 已提交
2470 2471 2472 2473
extern struct file * open_exec(const char *);
 
/* fs/dcache.c -- generic fs support functions */
extern int is_subdir(struct dentry *, struct dentry *);
2474
extern int path_is_under(struct path *, struct path *);
L
Linus Torvalds 已提交
2475 2476 2477 2478 2479 2480 2481 2482 2483
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);

2484
extern int inode_init_always(struct super_block *, struct inode *);
L
Linus Torvalds 已提交
2485
extern void inode_init_once(struct inode *);
2486
extern void address_space_init_once(struct address_space *mapping);
A
Al Viro 已提交
2487
extern void ihold(struct inode * inode);
L
Linus Torvalds 已提交
2488 2489 2490 2491
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);
2492
extern int generic_delete_inode(struct inode *inode);
2493 2494 2495 2496
static inline int generic_drop_inode(struct inode *inode)
{
	return !inode->i_nlink || inode_unhashed(inode);
}
L
Linus Torvalds 已提交
2497

2498 2499 2500
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
2501 2502 2503 2504 2505 2506
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
2507 2508
extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *);
extern int insert_inode_locked(struct inode *);
2509 2510 2511 2512 2513
#ifdef CONFIG_DEBUG_LOCK_ALLOC
extern void lockdep_annotate_inode_mutex_key(struct inode *inode);
#else
static inline void lockdep_annotate_inode_mutex_key(struct inode *inode) { };
#endif
L
Linus Torvalds 已提交
2514
extern void unlock_new_inode(struct inode *);
2515
extern unsigned int get_next_ino(void);
L
Linus Torvalds 已提交
2516 2517

extern void __iget(struct inode * inode);
2518
extern void iget_failed(struct inode *);
2519
extern void clear_inode(struct inode *);
C
Christoph Hellwig 已提交
2520
extern void __destroy_inode(struct inode *);
2521 2522
extern struct inode *new_inode_pseudo(struct super_block *sb);
extern struct inode *new_inode(struct super_block *sb);
2523
extern void free_inode_nonrcu(struct inode *inode);
2524
extern int should_remove_suid(struct dentry *);
2525
extern int file_remove_suid(struct file *);
L
Linus Torvalds 已提交
2526 2527

extern void __insert_inode_hash(struct inode *, unsigned long hashval);
2528 2529
static inline void insert_inode_hash(struct inode *inode)
{
L
Linus Torvalds 已提交
2530 2531
	__insert_inode_hash(inode, inode->i_ino);
}
2532 2533 2534 2535 2536 2537 2538 2539

extern void __remove_inode_hash(struct inode *);
static inline void remove_inode_hash(struct inode *inode)
{
	if (!inode_unhashed(inode))
		__remove_inode_hash(inode);
}

2540
extern void inode_sb_list_add(struct inode *inode);
L
Linus Torvalds 已提交
2541

2542
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2543 2544
extern void submit_bio(int, struct bio *);
extern int bdev_read_only(struct block_device *);
2545
#endif
L
Linus Torvalds 已提交
2546 2547 2548 2549 2550 2551 2552 2553
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);
2554
extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t);
2555 2556
extern ssize_t __generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long,
		loff_t *);
2557
extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t);
L
Linus Torvalds 已提交
2558 2559 2560 2561 2562 2563
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);
2564 2565
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
2566

2567 2568 2569
/* fs/block_dev.c */
extern ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
				unsigned long nr_segs, loff_t pos);
2570 2571
extern int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
			int datasync);
A
Al Viro 已提交
2572
extern void block_sync_page(struct page *page);
2573

A
Andrew Morton 已提交
2574
/* fs/splice.c */
2575
extern ssize_t generic_file_splice_read(struct file *, loff_t *,
A
Andrew Morton 已提交
2576
		struct pipe_inode_info *, size_t, unsigned int);
2577 2578
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
2579
extern ssize_t generic_file_splice_write(struct pipe_inode_info *,
2580
		struct file *, loff_t *, size_t, unsigned int);
A
Andrew Morton 已提交
2581
extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
2582 2583
		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
2584 2585
		size_t len, unsigned int flags);

L
Linus Torvalds 已提交
2586 2587
extern void
file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping);
J
jan Blunck 已提交
2588
extern loff_t noop_llseek(struct file *file, loff_t offset, int origin);
L
Linus Torvalds 已提交
2589 2590
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
2591
extern loff_t generic_file_llseek_size(struct file *file, loff_t offset,
2592
		int origin, loff_t maxsize, loff_t eof);
L
Linus Torvalds 已提交
2593 2594 2595
extern int generic_file_open(struct inode * inode, struct file * filp);
extern int nonseekable_open(struct inode * inode, struct file * filp);

2596
#ifdef CONFIG_FS_XIP
2597 2598
extern ssize_t xip_file_read(struct file *filp, char __user *buf, size_t len,
			     loff_t *ppos);
2599
extern int xip_file_mmap(struct file * file, struct vm_area_struct * vma);
2600 2601
extern ssize_t xip_file_write(struct file *filp, const char __user *buf,
			      size_t len, loff_t *ppos);
2602
extern int xip_truncate_page(struct address_space *mapping, loff_t from);
2603 2604 2605 2606 2607
#else
static inline int xip_truncate_page(struct address_space *mapping, loff_t from)
{
	return 0;
}
2608 2609
#endif

2610
#ifdef CONFIG_BLOCK
2611 2612
typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode,
			    loff_t file_offset);
L
Linus Torvalds 已提交
2613 2614

enum {
2615 2616 2617 2618 2619
	/* need locking between buffered and direct access */
	DIO_LOCKING	= 0x01,

	/* filesystem does not support filling holes */
	DIO_SKIP_HOLES	= 0x02,
L
Linus Torvalds 已提交
2620 2621
};

2622 2623 2624 2625 2626 2627
void dio_end_io(struct bio *bio, int error);

ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
	struct block_device *bdev, const struct iovec *iov, loff_t offset,
	unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io,
	dio_submit_t submit_io,	int flags);
2628

L
Linus Torvalds 已提交
2629
static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb,
2630 2631
		struct inode *inode, const struct iovec *iov, loff_t offset,
		unsigned long nr_segs, get_block_t get_block)
L
Linus Torvalds 已提交
2632
{
2633 2634
	return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
				    offset, nr_segs, get_block, NULL, NULL,
2635
				    DIO_LOCKING | DIO_SKIP_HOLES);
L
Linus Torvalds 已提交
2636
}
2637
#endif
L
Linus Torvalds 已提交
2638

2639 2640 2641
void inode_dio_wait(struct inode *inode);
void inode_dio_done(struct inode *inode);

2642
extern const struct file_operations generic_ro_fops;
L
Linus Torvalds 已提交
2643 2644 2645 2646 2647 2648

#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);
2649 2650
extern void *page_follow_link_light(struct dentry *, struct nameidata *);
extern void page_put_link(struct dentry *, struct nameidata *, void *);
2651
extern int __page_symlink(struct inode *inode, const char *symname, int len,
2652
		int nofs);
L
Linus Torvalds 已提交
2653
extern int page_symlink(struct inode *inode, const char *symname, int len);
2654
extern const struct inode_operations page_symlink_inode_operations;
L
Linus Torvalds 已提交
2655 2656 2657
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 *);
2658
void __inode_add_bytes(struct inode *inode, loff_t bytes);
L
Linus Torvalds 已提交
2659 2660 2661 2662 2663 2664 2665
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 *);

2666 2667
extern int vfs_stat(const char __user *, struct kstat *);
extern int vfs_lstat(const char __user *, struct kstat *);
L
Linus Torvalds 已提交
2668
extern int vfs_fstat(unsigned int, struct kstat *);
2669
extern int vfs_fstatat(int , const char __user *, struct kstat *, int);
L
Linus Torvalds 已提交
2670

2671 2672
extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
		    unsigned long arg);
2673
extern int __generic_block_fiemap(struct inode *inode,
J
Josef Bacik 已提交
2674 2675 2676
				  struct fiemap_extent_info *fieinfo,
				  loff_t start, loff_t len,
				  get_block_t *get_block);
2677 2678 2679
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
2680

2681 2682
extern void get_filesystem(struct file_system_type *fs);
extern void put_filesystem(struct file_system_type *fs);
L
Linus Torvalds 已提交
2683 2684
extern struct file_system_type *get_fs_type(const char *name);
extern struct super_block *get_super(struct block_device *);
2685
extern struct super_block *get_super_thawed(struct block_device *);
2686
extern struct super_block *get_active_super(struct block_device *bdev);
L
Linus Torvalds 已提交
2687
extern void drop_super(struct super_block *sb);
A
Al Viro 已提交
2688
extern void iterate_supers(void (*)(struct super_block *, void *), void *);
A
Al Viro 已提交
2689 2690
extern void iterate_supers_type(struct file_system_type *,
			        void (*)(struct super_block *, void *), void *);
L
Linus Torvalds 已提交
2691 2692 2693 2694 2695

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);
2696
extern int simple_setattr(struct dentry *, struct iattr *);
L
Linus Torvalds 已提交
2697
extern int simple_getattr(struct vfsmount *, struct dentry *, struct kstat *);
2698
extern int simple_statfs(struct dentry *, struct kstatfs *);
S
Stephen Boyd 已提交
2699
extern int simple_open(struct inode *inode, struct file *file);
L
Linus Torvalds 已提交
2700 2701 2702 2703
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 *);
2704
extern int noop_fsync(struct file *, loff_t, loff_t, int);
L
Linus Torvalds 已提交
2705 2706
extern int simple_empty(struct dentry *);
extern int simple_readpage(struct file *file, struct page *page);
2707 2708 2709 2710 2711 2712
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
2713

A
Al Viro 已提交
2714
extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags);
L
Linus Torvalds 已提交
2715
extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *);
2716
extern const struct file_operations simple_dir_operations;
2717
extern const struct inode_operations simple_dir_inode_operations;
2718
struct tree_descr { char *name; const struct file_operations *ops; int mode; };
L
Linus Torvalds 已提交
2719
struct dentry *d_alloc_name(struct dentry *, const char *);
2720
extern int simple_fill_super(struct super_block *, unsigned long, struct tree_descr *);
2721
extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count);
L
Linus Torvalds 已提交
2722 2723
extern void simple_release_fs(struct vfsmount **mount, int *count);

2724 2725
extern ssize_t simple_read_from_buffer(void __user *to, size_t count,
			loff_t *ppos, const void *from, size_t available);
2726 2727
extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos,
		const void __user *from, size_t count);
L
Linus Torvalds 已提交
2728

2729
extern int generic_file_fsync(struct file *, loff_t, loff_t, int);
A
Al Viro 已提交
2730

2731 2732
extern int generic_check_addressable(unsigned, u64);

2733
#ifdef CONFIG_MIGRATION
2734
extern int buffer_migrate_page(struct address_space *,
2735 2736
				struct page *, struct page *,
				enum migrate_mode);
2737 2738 2739 2740
#else
#define buffer_migrate_page NULL
#endif

N
npiggin@suse.de 已提交
2741 2742
extern int inode_change_ok(const struct inode *, struct iattr *);
extern int inode_newsize_ok(const struct inode *, loff_t offset);
C
Christoph Hellwig 已提交
2743
extern void setattr_copy(struct inode *inode, const struct iattr *attr);
L
Linus Torvalds 已提交
2744

2745
extern int file_update_time(struct file *file);
L
Linus Torvalds 已提交
2746

2747
extern int generic_show_options(struct seq_file *m, struct dentry *root);
2748
extern void save_mount_options(struct super_block *sb, char *options);
2749
extern void replace_mount_options(struct super_block *sb, char *options);
2750

L
Linus Torvalds 已提交
2751 2752 2753 2754
static inline ino_t parent_ino(struct dentry *dentry)
{
	ino_t res;

N
Nick Piggin 已提交
2755 2756 2757 2758
	/*
	 * Don't strictly need d_lock here? If the parent ino could change
	 * then surely we'd have a deeper race in the caller?
	 */
L
Linus Torvalds 已提交
2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783
	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);

2784
void simple_transaction_set(struct file *file, size_t n);
L
Linus Torvalds 已提交
2785

2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807
/*
 * 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);	\
}									\
2808
static const struct file_operations __fops = {				\
2809 2810
	.owner	 = THIS_MODULE,						\
	.open	 = __fops ## _open,					\
2811
	.release = simple_attr_release,					\
2812 2813
	.read	 = simple_attr_read,					\
	.write	 = simple_attr_write,					\
2814
	.llseek	 = generic_file_llseek,					\
2815 2816
};

2817 2818
static inline __printf(1, 2)
void __simple_attr_check_format(const char *fmt, ...)
2819 2820 2821 2822 2823
{
	/* don't do anything, just let the compiler check the arguments; */
}

int simple_attr_open(struct inode *inode, struct file *file,
2824
		     int (*get)(void *, u64 *), int (*set)(void *, u64),
2825
		     const char *fmt);
2826
int simple_attr_release(struct inode *inode, struct file *file);
2827 2828 2829 2830 2831
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
2832
struct ctl_table;
2833
int proc_nr_files(struct ctl_table *table, int write,
2834
		  void __user *buffer, size_t *lenp, loff_t *ppos);
2835 2836
int proc_nr_dentry(struct ctl_table *table, int write,
		  void __user *buffer, size_t *lenp, loff_t *ppos);
2837 2838
int proc_nr_inodes(struct ctl_table *table, int write,
		   void __user *buffer, size_t *lenp, loff_t *ppos);
2839
int __init get_filesystem_list(char *buf);
2840

N
Namhyung Kim 已提交
2841
#define __FMODE_EXEC		((__force int) FMODE_EXEC)
2842 2843
#define __FMODE_NONOTIFY	((__force int) FMODE_NONOTIFY)

A
Al Viro 已提交
2844
#define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE])
E
Eric Paris 已提交
2845
#define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \
2846
					    (flag & __FMODE_NONOTIFY)))
A
Al Viro 已提交
2847

A
Al Viro 已提交
2848
static inline int is_sxid(umode_t mode)
2849 2850 2851 2852 2853 2854
{
	return (mode & S_ISUID) || ((mode & S_ISGID) && (mode & S_IXGRP));
}

static inline void inode_has_no_xattr(struct inode *inode)
{
A
Al Viro 已提交
2855
	if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & MS_NOSEC))
2856 2857 2858
		inode->i_flags |= S_NOSEC;
}

L
Linus Torvalds 已提交
2859 2860
#endif /* __KERNEL__ */
#endif /* _LINUX_FS_H */