fs.h 94.2 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8
#ifndef _LINUX_FS_H
#define _LINUX_FS_H


#include <linux/linkage.h>
#include <linux/wait.h>
#include <linux/kdev_t.h>
#include <linux/dcache.h>
9
#include <linux/path.h>
L
Linus Torvalds 已提交
10 11 12
#include <linux/stat.h>
#include <linux/cache.h>
#include <linux/list.h>
13
#include <linux/list_lru.h>
14
#include <linux/llist.h>
L
Linus Torvalds 已提交
15
#include <linux/radix-tree.h>
16
#include <linux/rbtree.h>
L
Linus Torvalds 已提交
17
#include <linux/init.h>
18
#include <linux/pid.h>
19
#include <linux/bug.h>
20
#include <linux/mutex.h>
21
#include <linux/capability.h>
22
#include <linux/semaphore.h>
M
Mark Fasheh 已提交
23
#include <linux/fiemap.h>
24
#include <linux/rculist_bl.h>
25
#include <linux/atomic.h>
26
#include <linux/shrinker.h>
27
#include <linux/migrate_mode.h>
28
#include <linux/uidgid.h>
29
#include <linux/lockdep.h>
30
#include <linux/percpu-rwsem.h>
D
David Howells 已提交
31
#include <linux/blk_types.h>
L
Linus Torvalds 已提交
32 33

#include <asm/byteorder.h>
34
#include <uapi/linux/fs.h>
L
Linus Torvalds 已提交
35

36
struct export_operations;
37
struct hd_geometry;
L
Linus Torvalds 已提交
38 39
struct iovec;
struct nameidata;
40
struct kiocb;
A
Alexey Dobriyan 已提交
41
struct kobject;
L
Linus Torvalds 已提交
42 43 44 45 46
struct pipe_inode_info;
struct poll_table_struct;
struct kstatfs;
struct vm_area_struct;
struct vfsmount;
47
struct cred;
48
struct swap_info_struct;
49
struct seq_file;
50
struct workqueue_struct;
51
struct iov_iter;
L
Linus Torvalds 已提交
52

53
extern void __init inode_init(void);
L
Linus Torvalds 已提交
54 55 56
extern void __init inode_init_early(void);
extern void __init files_init(unsigned long);

57
extern struct files_stat_struct files_stat;
E
Eric Dumazet 已提交
58
extern unsigned long get_max_files(void);
59 60 61
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
62 63
extern int sysctl_protected_symlinks;
extern int sysctl_protected_hardlinks;
64

L
Linus Torvalds 已提交
65 66 67
struct buffer_head;
typedef int (get_block_t)(struct inode *inode, sector_t iblock,
			struct buffer_head *bh_result, int create);
68
typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
69
			ssize_t bytes, void *private);
L
Linus Torvalds 已提交
70

D
David Howells 已提交
71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126
#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

/*
 * 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()
 */

/* file is open for reading */
#define FMODE_READ		((__force fmode_t)0x1)
/* file is open for writing */
#define FMODE_WRITE		((__force fmode_t)0x2)
/* file is seekable */
#define FMODE_LSEEK		((__force fmode_t)0x4)
/* file can be accessed using pread */
#define FMODE_PREAD		((__force fmode_t)0x8)
/* file can be accessed using pwrite */
#define FMODE_PWRITE		((__force fmode_t)0x10)
/* File is opened for execution with sys_execve / sys_uselib */
#define FMODE_EXEC		((__force fmode_t)0x20)
/* File is opened with O_NDELAY (only set for block devices) */
#define FMODE_NDELAY		((__force fmode_t)0x40)
/* File is opened with O_EXCL (only set for block devices) */
#define FMODE_EXCL		((__force fmode_t)0x80)
/* File is opened using open(.., 3, ..) and is writeable only for ioctls
   (specialy hack for floppy.c) */
#define FMODE_WRITE_IOCTL	((__force fmode_t)0x100)
/* 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)

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

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

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

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

127 128
/* File needs atomic accesses to f_pos */
#define FMODE_ATOMIC_POS	((__force fmode_t)0x8000)
129 130
/* Write access to underlying fs */
#define FMODE_WRITER		((__force fmode_t)0x10000)
131 132 133 134
/* Has read method(s) */
#define FMODE_CAN_READ          ((__force fmode_t)0x20000)
/* Has write method(s) */
#define FMODE_CAN_WRITE         ((__force fmode_t)0x40000)
135

D
David Howells 已提交
136 137 138 139 140 141 142 143 144 145 146
/* File was opened by fanotify and shouldn't generate fanotify events */
#define FMODE_NONOTIFY		((__force fmode_t)0x1000000)

/*
 * 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

D
David Howells 已提交
147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202
/*
 * The below are the various read and write types that we support. Some of
 * them include behavioral modifiers that send information down to the
 * block layer and IO scheduler. Terminology:
 *
 *	The block layer uses device plugging to defer IO a little bit, in
 *	the hope that we will see more IO very shortly. This increases
 *	coalescing of adjacent IO and thus reduces the number of IOs we
 *	have to send to the device. It also allows for better queuing,
 *	if the IO isn't mergeable. If the caller is going to be waiting
 *	for the IO, then he must ensure that the device is unplugged so
 *	that the IO is dispatched to the driver.
 *
 *	All IO is handled async in Linux. This is fine for background
 *	writes, but for reads or writes that someone waits for completion
 *	on, we want to notify the block layer and IO scheduler so that they
 *	know about it. That allows them to make better scheduling
 *	decisions. So when the below references 'sync' and 'async', it
 *	is referencing this priority hint.
 *
 * With that in mind, the available types are:
 *
 * READ			A normal read operation. Device will be plugged.
 * READ_SYNC		A synchronous read. Device is not plugged, caller can
 *			immediately wait on this read without caring about
 *			unplugging.
 * READA		Used for read-ahead operations. Lower priority, and the
 *			block layer could (in theory) choose to ignore this
 *			request if it runs into resource problems.
 * WRITE		A normal async write. Device will be plugged.
 * WRITE_SYNC		Synchronous write. Identical to WRITE, but passes down
 *			the hint that someone will be waiting on this IO
 *			shortly. The write equivalent of READ_SYNC.
 * WRITE_ODIRECT	Special case write for O_DIRECT only.
 * 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.
 *
 */
#define RW_MASK			REQ_WRITE
#define RWA_MASK		REQ_RAHEAD

#define READ			0
#define WRITE			RW_MASK
#define READA			RWA_MASK

#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
203 204 205 206
/*
 * Attribute flags.  These should be or-ed together to figure out what
 * has been changed!
 */
207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223
#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
224

M
Miklos Szeredi 已提交
225 226 227 228 229 230 231
/*
 * Whiteout is represented by a char device.  The following constants define the
 * mode and device number to use.
 */
#define WHITEOUT_MODE 0
#define WHITEOUT_DEV 0

L
Linus Torvalds 已提交
232 233 234 235 236 237 238 239 240 241 242 243
/*
 * 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;
244 245
	kuid_t		ia_uid;
	kgid_t		ia_gid;
L
Linus Torvalds 已提交
246 247 248 249
	loff_t		ia_size;
	struct timespec	ia_atime;
	struct timespec	ia_mtime;
	struct timespec	ia_ctime;
250 251

	/*
L
Lucas De Marchi 已提交
252
	 * Not an attribute, but an auxiliary info for filesystems wanting to
253 254 255 256
	 * 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
257 258 259 260 261 262 263
};

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

264 265 266 267 268 269
/*
 * Maximum number of layers of fs stack.  Needs to be limited to
 * prevent kernel stack overflow
 */
#define FILESYSTEM_MAX_STACK_DEPTH 2

270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287
/** 
 * 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
288
 *  			by readpage().
289 290 291 292 293 294 295 296 297 298 299 300
 *
 * 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,
};

301
#define AOP_FLAG_UNINTERRUPTIBLE	0x0001 /* will not do a short write */
N
Nick Piggin 已提交
302
#define AOP_FLAG_CONT_EXPAND		0x0002 /* called from cont_expand */
303 304 305
#define AOP_FLAG_NOFS			0x0004 /* used by filesystem to direct
						* helper code (eg buffer layer)
						* to clear GFP_FS from alloc */
306

L
Linus Torvalds 已提交
307 308 309 310 311 312 313
/*
 * oh the beauties of C type declarations.
 */
struct page;
struct address_space;
struct writeback_control;

314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334
/*
 * "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
335

L
Linus Torvalds 已提交
336 337 338 339 340 341 342
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 *);

343
	/* Set a page dirty.  Return true if this dirtied it */
L
Linus Torvalds 已提交
344 345 346 347 348
	int (*set_page_dirty)(struct page *page);

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

349 350 351 352 353 354 355
	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
356 357
	/* Unfortunately this kludge is needed for FIBMAP. Don't use it */
	sector_t (*bmap)(struct address_space *, sector_t);
358
	void (*invalidatepage) (struct page *, unsigned int, unsigned int);
A
Al Viro 已提交
359
	int (*releasepage) (struct page *, gfp_t);
360
	void (*freepage)(struct page *);
A
Al Viro 已提交
361
	ssize_t (*direct_IO)(int, struct kiocb *, struct iov_iter *iter, loff_t offset);
362 363
	int (*get_xip_mem)(struct address_space *, pgoff_t, int,
						void **, unsigned long *);
364
	/*
365 366
	 * migrate the contents of a page to the specified target. If
	 * migrate_mode is MIGRATE_ASYNC, it must not block.
367
	 */
368
	int (*migratepage) (struct address_space *,
369
			struct page *, struct page *, enum migrate_mode);
370
	int (*launder_page) (struct page *);
371
	int (*is_partially_uptodate) (struct page *, unsigned long,
372
					unsigned long);
373
	void (*is_dirty_writeback) (struct page *, bool *, bool *);
374
	int (*error_remove_page)(struct address_space *, struct page *);
375 376

	/* swapfile support */
377 378 379
	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
380 381
};

J
Jens Axboe 已提交
382 383
extern const struct address_space_operations empty_aops;

384 385 386 387 388 389 390 391 392 393 394 395
/*
 * 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
396 397 398 399
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
400
	spinlock_t		tree_lock;	/* and lock protecting it */
401
	atomic_t		i_mmap_writable;/* count VM_SHARED mappings */
402
	struct rb_root		i_mmap;		/* tree of private and shared mappings */
L
Linus Torvalds 已提交
403
	struct list_head	i_mmap_nonlinear;/*list VM_NONLINEAR mappings */
404
	struct mutex		i_mmap_mutex;	/* protect tree, count, list */
405
	/* Protected by tree_lock together with the radix tree */
L
Linus Torvalds 已提交
406
	unsigned long		nrpages;	/* number of total pages */
407
	unsigned long		nrshadows;	/* number of shadow entries */
L
Linus Torvalds 已提交
408
	pgoff_t			writeback_index;/* writeback starts here */
409
	const struct address_space_operations *a_ops;	/* methods */
L
Linus Torvalds 已提交
410 411 412 413
	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 */
414
	void			*private_data;	/* ditto */
L
Linus Torvalds 已提交
415 416 417
} __attribute__((aligned(sizeof(long))));
	/*
	 * On most architectures that alignment is already the case; but
L
Lucas De Marchi 已提交
418
	 * must be enforced here for CRIS, to let the least significant bit
L
Linus Torvalds 已提交
419 420
	 * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON.
	 */
421
struct request_queue;
L
Linus Torvalds 已提交
422 423 424

struct block_device {
	dev_t			bd_dev;  /* not a kdev_t - it's a search key */
425
	int			bd_openers;
L
Linus Torvalds 已提交
426
	struct inode *		bd_inode;	/* will die */
427
	struct super_block *	bd_super;
428
	struct mutex		bd_mutex;	/* open/close mutex */
L
Linus Torvalds 已提交
429
	struct list_head	bd_inodes;
430
	void *			bd_claiming;
L
Linus Torvalds 已提交
431 432
	void *			bd_holder;
	int			bd_holders;
433
	bool			bd_write_holder;
434
#ifdef CONFIG_SYSFS
435
	struct list_head	bd_holder_disks;
436
#endif
L
Linus Torvalds 已提交
437 438 439 440 441 442 443
	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;
444
	struct request_queue *  bd_queue;
L
Linus Torvalds 已提交
445 446 447 448 449 450 451 452
	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;
453 454 455 456 457

	/* The counter of freeze processes */
	int			bd_fsfreeze_count;
	/* Mutex for freeze */
	struct mutex		bd_fsfreeze_mutex;
L
Linus Torvalds 已提交
458 459 460 461 462 463 464 465
};

/*
 * Radix-tree tags, for tagging dirty and writeback pages within the pagecache
 * radix trees
 */
#define PAGECACHE_TAG_DIRTY	0
#define PAGECACHE_TAG_WRITEBACK	1
466
#define PAGECACHE_TAG_TOWRITE	2
L
Linus Torvalds 已提交
467 468 469

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

470 471 472 473 474 475 476 477 478 479
static inline void i_mmap_lock_write(struct address_space *mapping)
{
	mutex_lock(&mapping->i_mmap_mutex);
}

static inline void i_mmap_unlock_write(struct address_space *mapping)
{
	mutex_unlock(&mapping->i_mmap_mutex);
}

L
Linus Torvalds 已提交
480 481 482 483 484
/*
 * Might pages of this file be mapped into userspace?
 */
static inline int mapping_mapped(struct address_space *mapping)
{
485
	return	!RB_EMPTY_ROOT(&mapping->i_mmap) ||
L
Linus Torvalds 已提交
486 487 488 489 490 491 492 493
		!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.
494 495 496
 *
 * If i_mmap_writable is negative, no new writable mappings are allowed. You
 * can only deny writable mappings, if none exists right now.
L
Linus Torvalds 已提交
497 498 499
 */
static inline int mapping_writably_mapped(struct address_space *mapping)
{
500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522
	return atomic_read(&mapping->i_mmap_writable) > 0;
}

static inline int mapping_map_writable(struct address_space *mapping)
{
	return atomic_inc_unless_negative(&mapping->i_mmap_writable) ?
		0 : -EPERM;
}

static inline void mapping_unmap_writable(struct address_space *mapping)
{
	atomic_dec(&mapping->i_mmap_writable);
}

static inline int mapping_deny_writable(struct address_space *mapping)
{
	return atomic_dec_unless_positive(&mapping->i_mmap_writable) ?
		0 : -EBUSY;
}

static inline void mapping_allow_writable(struct address_space *mapping)
{
	atomic_inc(&mapping->i_mmap_writable);
L
Linus Torvalds 已提交
523 524 525 526 527 528 529 530 531 532 533 534 535
}

/*
 * 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
536 537 538
struct posix_acl;
#define ACL_NOT_CACHED ((void *)(-1))

539 540 541 542 543 544 545 546 547
#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
548
struct inode {
549
	umode_t			i_mode;
550
	unsigned short		i_opflags;
551 552
	kuid_t			i_uid;
	kgid_t			i_gid;
553 554 555 556 557 558 559
	unsigned int		i_flags;

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

560 561
	const struct inode_operations	*i_op;
	struct super_block	*i_sb;
562
	struct address_space	*i_mapping;
563

564 565 566
#ifdef CONFIG_SECURITY
	void			*i_security;
#endif
567

568 569
	/* Stat data, not accessed from path walking */
	unsigned long		i_ino;
M
Miklos Szeredi 已提交
570 571 572 573 574 575 576 577 578 579 580
	/*
	 * 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;
	};
581
	dev_t			i_rdev;
582
	loff_t			i_size;
583 584 585
	struct timespec		i_atime;
	struct timespec		i_mtime;
	struct timespec		i_ctime;
586 587
	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
	unsigned short          i_bytes;
588
	unsigned int		i_blkbits;
589 590 591 592 593 594 595 596 597
	blkcnt_t		i_blocks;

#ifdef __NEED_I_SIZE_ORDERED
	seqcount_t		i_size_seqcount;
#endif

	/* Misc */
	unsigned long		i_state;
	struct mutex		i_mutex;
598

599 600
	unsigned long		dirtied_when;	/* jiffies of first dirtying */

L
Linus Torvalds 已提交
601
	struct hlist_node	i_hash;
N
Nick Piggin 已提交
602 603
	struct list_head	i_wb_list;	/* backing dev IO list */
	struct list_head	i_lru;		/* inode LRU list */
L
Linus Torvalds 已提交
604
	struct list_head	i_sb_list;
N
Nick Piggin 已提交
605
	union {
A
Al Viro 已提交
606
		struct hlist_head	i_dentry;
N
Nick Piggin 已提交
607 608
		struct rcu_head		i_rcu;
	};
609
	u64			i_version;
610
	atomic_t		i_count;
C
Christoph Hellwig 已提交
611
	atomic_t		i_dio_count;
612
	atomic_t		i_writecount;
M
Mimi Zohar 已提交
613 614 615
#ifdef CONFIG_IMA
	atomic_t		i_readcount; /* struct files open RO */
#endif
616
	const struct file_operations	*i_fop;	/* former ->i_op->default_file_ops */
L
Linus Torvalds 已提交
617 618 619
	struct file_lock	*i_flock;
	struct address_space	i_data;
	struct list_head	i_devices;
620 621
	union {
		struct pipe_inode_info	*i_pipe;
622
		struct block_device	*i_bdev;
623
		struct cdev		*i_cdev;
624
	};
L
Linus Torvalds 已提交
625 626 627

	__u32			i_generation;

628 629
#ifdef CONFIG_FSNOTIFY
	__u32			i_fsnotify_mask; /* all events this inode cares about */
630
	struct hlist_head	i_fsnotify_marks;
R
Robert Love 已提交
631 632
#endif

633
	void			*i_private; /* fs or device private pointer */
L
Linus Torvalds 已提交
634 635
};

A
Al Viro 已提交
636 637 638 639 640
static inline int inode_unhashed(struct inode *inode)
{
	return hlist_unhashed(&inode->i_hash);
}

I
Ingo Molnar 已提交
641 642 643 644 645 646
/*
 * inode->i_mutex nesting subclasses for the lock validator:
 *
 * 0: the object of the current VFS operation
 * 1: parent
 * 2: child/target
647 648
 * 3: xattr
 * 4: second non-directory
649 650 651
 * 5: second parent (when locking independent directories in rename)
 *
 * I_MUTEX_NONDIR2 is for certain operations (such as rename) which lock two
652
 * non-directories at once.
I
Ingo Molnar 已提交
653 654
 *
 * The locking order between these classes is
655
 * parent[2] -> child -> grandchild -> normal -> xattr -> second non-directory
I
Ingo Molnar 已提交
656 657 658 659 660 661
 */
enum inode_i_mutex_lock_class
{
	I_MUTEX_NORMAL,
	I_MUTEX_PARENT,
	I_MUTEX_CHILD,
I
Ingo Molnar 已提交
662
	I_MUTEX_XATTR,
663 664
	I_MUTEX_NONDIR2,
	I_MUTEX_PARENT2,
I
Ingo Molnar 已提交
665 666
};

667 668 669
void lock_two_nondirectories(struct inode *, struct inode*);
void unlock_two_nondirectories(struct inode *, struct inode*);

L
Linus Torvalds 已提交
670 671 672 673 674 675 676 677 678 679
/*
 * 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
680
static inline loff_t i_size_read(const struct inode *inode)
L
Linus Torvalds 已提交
681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702
{
#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
}

703 704 705 706 707
/*
 * 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
708 709 710
static inline void i_size_write(struct inode *inode, loff_t i_size)
{
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
711
	preempt_disable();
L
Linus Torvalds 已提交
712 713 714
	write_seqcount_begin(&inode->i_size_seqcount);
	inode->i_size = i_size;
	write_seqcount_end(&inode->i_size_seqcount);
715
	preempt_enable();
L
Linus Torvalds 已提交
716 717 718 719 720 721 722 723 724
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
	preempt_disable();
	inode->i_size = i_size;
	preempt_enable();
#else
	inode->i_size = i_size;
#endif
}

725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749
/* 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
750
static inline unsigned iminor(const struct inode *inode)
L
Linus Torvalds 已提交
751 752 753 754
{
	return MINOR(inode->i_rdev);
}

J
Jan Engelhardt 已提交
755
static inline unsigned imajor(const struct inode *inode)
L
Linus Torvalds 已提交
756 757 758 759 760 761 762 763
{
	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 */
764 765
	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 */
766
	kuid_t uid, euid;	/* uid/euid of process setting the owner */
L
Linus Torvalds 已提交
767 768 769 770 771 772 773
	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
774 775 776
	pgoff_t start;			/* where readahead started */
	unsigned int size;		/* # of readahead pages */
	unsigned int async_size;	/* do asynchronous readahead when
777
					   there are only # of pages ahead */
778

F
Fengguang Wu 已提交
779
	unsigned int ra_pages;		/* Maximum readahead window */
780
	unsigned int mmap_miss;		/* Cache miss stat for mmap accesses */
781
	loff_t prev_pos;		/* Cache last read() position */
L
Linus Torvalds 已提交
782 783
};

784 785 786 787 788
/*
 * Check if @index falls in the readahead windows.
 */
static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
{
789 790
	return (index >= ra->start &&
		index <  ra->start + ra->size);
791 792
}

L
Linus Torvalds 已提交
793
struct file {
E
Eric Dumazet 已提交
794
	union {
795
		struct llist_node	fu_llist;
E
Eric Dumazet 已提交
796 797
		struct rcu_head 	fu_rcuhead;
	} f_u;
798
	struct path		f_path;
799
	struct inode		*f_inode;	/* cached value */
800
	const struct file_operations	*f_op;
801 802

	/*
803
	 * Protects f_ep_links, f_flags.
804 805 806
	 * Must not be taken from IRQ context.
	 */
	spinlock_t		f_lock;
A
Al Viro 已提交
807
	atomic_long_t		f_count;
L
Linus Torvalds 已提交
808
	unsigned int 		f_flags;
809
	fmode_t			f_mode;
810
	struct mutex		f_pos_lock;
L
Linus Torvalds 已提交
811 812
	loff_t			f_pos;
	struct fown_struct	f_owner;
D
David Howells 已提交
813
	const struct cred	*f_cred;
L
Linus Torvalds 已提交
814 815
	struct file_ra_state	f_ra;

816
	u64			f_version;
817
#ifdef CONFIG_SECURITY
L
Linus Torvalds 已提交
818
	void			*f_security;
819
#endif
L
Linus Torvalds 已提交
820 821 822 823 824 825
	/* 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
826
	struct list_head	f_tfile_llink;
L
Linus Torvalds 已提交
827 828
#endif /* #ifdef CONFIG_EPOLL */
	struct address_space	*f_mapping;
A
Al Viro 已提交
829
} __attribute__((aligned(4)));	/* lest something weird decides that 2 is OK */
L
Linus Torvalds 已提交
830

831 832 833 834 835 836 837
struct file_handle {
	__u32 handle_bytes;
	int handle_type;
	/* file identifier */
	unsigned char f_handle[0];
};

A
Al Viro 已提交
838 839 840 841 842
static inline struct file *get_file(struct file *f)
{
	atomic_long_inc(&f->f_count);
	return f;
}
843
#define fput_atomic(x)	atomic_long_add_unless(&(x)->f_count, -1, 1)
A
Al Viro 已提交
844
#define file_count(x)	atomic_long_read(&(x)->f_count)
L
Linus Torvalds 已提交
845 846 847 848 849 850

#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
C
Chuck Lever 已提交
851
#define MAX_LFS_FILESIZE	(((loff_t)PAGE_CACHE_SIZE << (BITS_PER_LONG-1))-1) 
L
Linus Torvalds 已提交
852
#elif BITS_PER_LONG==64
853
#define MAX_LFS_FILESIZE 	((loff_t)0x7fffffffffffffffLL)
L
Linus Torvalds 已提交
854 855 856 857
#endif

#define FL_POSIX	1
#define FL_FLOCK	2
858
#define FL_DELEG	4	/* NFSv4 delegation */
L
Linus Torvalds 已提交
859
#define FL_ACCESS	8	/* not trying to lock, just looking */
860
#define FL_EXISTS	16	/* when unlocking, test for existence */
L
Linus Torvalds 已提交
861
#define FL_LEASE	32	/* lease held on this file */
862
#define FL_CLOSE	64	/* unlock on close */
L
Linus Torvalds 已提交
863
#define FL_SLEEP	128	/* A blocking lock */
864 865
#define FL_DOWNGRADE_PENDING	256 /* Lease is being downgraded */
#define FL_UNLOCK_PENDING	512 /* Lease is being broken */
866
#define FL_OFDLCK	1024	/* lock is "owned" by struct file */
L
Linus Torvalds 已提交
867

868 869 870 871 872 873
/*
 * Special return value from posix_lock_file() and vfs_lock_file() for
 * asynchronous locking.
 */
#define FILE_LOCK_DEFERRED 1

874
/* legacy typedef, should eventually be removed */
875
typedef void *fl_owner_t;
L
Linus Torvalds 已提交
876 877 878 879 880 881 882

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
883
	int (*lm_compare_owner)(struct file_lock *, struct file_lock *);
884
	unsigned long (*lm_owner_key)(struct file_lock *);
885 886
	void (*lm_get_owner)(struct file_lock *, struct file_lock *);
	void (*lm_put_owner)(struct file_lock *);
J
J. Bruce Fields 已提交
887
	void (*lm_notify)(struct file_lock *);	/* unblock callback */
888
	int (*lm_grant)(struct file_lock *, int);
J
Jeff Layton 已提交
889
	bool (*lm_break)(struct file_lock *);
890
	int (*lm_change)(struct file_lock **, int, struct list_head *);
891
	void (*lm_setup)(struct file_lock *, void **);
L
Linus Torvalds 已提交
892 893
};

894 895 896 897
struct lock_manager {
	struct list_head list;
};

898 899
struct net;
void locks_start_grace(struct net *, struct lock_manager *);
900
void locks_end_grace(struct lock_manager *);
901
int locks_in_grace(struct net *);
902

L
Linus Torvalds 已提交
903 904 905
/* that will die - we need it for nfs_lock_info */
#include <linux/nfs_fs_i.h>

906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923
/*
 * struct file_lock represents a generic "file lock". It's used to represent
 * POSIX byte range locks, BSD (flock) locks, and leases. It's important to
 * note that the same struct is used to represent both a request for a lock and
 * the lock itself, but the same object is never used for both.
 *
 * FIXME: should we create a separate "struct lock_request" to help distinguish
 * these two uses?
 *
 * The i_flock list is ordered by:
 *
 * 1) lock type -- FL_LEASEs first, then FL_FLOCK, and finally FL_POSIX
 * 2) lock owner
 * 3) lock range start
 * 4) lock range end
 *
 * Obviously, the last two criteria only matter for POSIX locks.
 */
L
Linus Torvalds 已提交
924 925
struct file_lock {
	struct file_lock *fl_next;	/* singly linked list for this inode  */
926
	struct hlist_node fl_link;	/* node in global lists */
L
Linus Torvalds 已提交
927 928
	struct list_head fl_block;	/* circular list of blocked processes */
	fl_owner_t fl_owner;
929
	unsigned int fl_flags;
930
	unsigned char fl_type;
L
Linus Torvalds 已提交
931
	unsigned int fl_pid;
932
	int fl_link_cpu;		/* what cpu's list is this on? */
933
	struct pid *fl_nspid;
L
Linus Torvalds 已提交
934 935 936 937 938 939
	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 */
940 941 942
	/* for lease breaks: */
	unsigned long fl_break_time;
	unsigned long fl_downgrade_time;
L
Linus Torvalds 已提交
943

944
	const struct file_lock_operations *fl_ops;	/* Callbacks for filesystems */
945
	const struct lock_manager_operations *fl_lmops;	/* Callbacks for lockmanagers */
L
Linus Torvalds 已提交
946 947
	union {
		struct nfs_lock_info	nfs_fl;
948
		struct nfs4_lock_info	nfs4_fl;
D
David Howells 已提交
949 950 951 952
		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
953 954 955 956 957 958 959 960 961 962 963 964
	} 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>

965 966 967
extern void send_sigio(struct fown_struct *fown, int fd, int band);

#ifdef CONFIG_FILE_LOCKING
968
extern int fcntl_getlk(struct file *, unsigned int, struct flock __user *);
969 970
extern int fcntl_setlk(unsigned int, struct file *, unsigned int,
			struct flock __user *);
L
Linus Torvalds 已提交
971 972

#if BITS_PER_LONG == 32
973
extern int fcntl_getlk64(struct file *, unsigned int, struct flock64 __user *);
974 975
extern int fcntl_setlk64(unsigned int, struct file *, unsigned int,
			struct flock64 __user *);
L
Linus Torvalds 已提交
976 977 978 979 980 981
#endif

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

/* fs/locks.c */
982
void locks_free_lock(struct file_lock *fl);
L
Linus Torvalds 已提交
983
extern void locks_init_lock(struct file_lock *);
984
extern struct file_lock * locks_alloc_lock(void);
L
Linus Torvalds 已提交
985
extern void locks_copy_lock(struct file_lock *, struct file_lock *);
986
extern void locks_copy_conflock(struct file_lock *, struct file_lock *);
L
Linus Torvalds 已提交
987
extern void locks_remove_posix(struct file *, fl_owner_t);
988
extern void locks_remove_file(struct file *);
989
extern void locks_release_private(struct file_lock *);
990
extern void posix_test_lock(struct file *, struct file_lock *);
991
extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *);
L
Linus Torvalds 已提交
992
extern int posix_lock_file_wait(struct file *, struct file_lock *);
993
extern int posix_unblock_lock(struct file_lock *);
994
extern int vfs_test_lock(struct file *, struct file_lock *);
995
extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *);
M
Marc Eshel 已提交
996
extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
L
Linus Torvalds 已提交
997
extern int flock_lock_file_wait(struct file *filp, struct file_lock *fl);
J
J. Bruce Fields 已提交
998
extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type);
L
Linus Torvalds 已提交
999
extern void lease_get_mtime(struct inode *, struct timespec *time);
1000 1001
extern int generic_setlease(struct file *, long, struct file_lock **, void **priv);
extern int vfs_setlease(struct file *, long, struct file_lock **, void **);
1002
extern int lease_modify(struct file_lock **, int, struct list_head *);
1003
#else /* !CONFIG_FILE_LOCKING */
1004 1005
static inline int fcntl_getlk(struct file *file, unsigned int cmd,
			      struct flock __user *user)
1006 1007 1008 1009 1010 1011 1012 1013 1014 1015
{
	return -EINVAL;
}

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

1016
#if BITS_PER_LONG == 32
1017 1018
static inline int fcntl_getlk64(struct file *file, unsigned int cmd,
				struct flock64 __user *user)
1019 1020 1021 1022 1023 1024 1025 1026 1027
{
	return -EINVAL;
}

static inline int fcntl_setlk64(unsigned int fd, struct file *file,
				unsigned int cmd, struct flock64 __user *user)
{
	return -EACCES;
}
1028
#endif
1029 1030
static inline int fcntl_setlease(unsigned int fd, struct file *filp, long arg)
{
1031
	return -EINVAL;
1032 1033 1034 1035
}

static inline int fcntl_getlease(struct file *filp)
{
1036
	return F_UNLCK;
1037 1038 1039 1040 1041 1042 1043
}

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

1044
static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl)
1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058
{
	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;
}

1059
static inline void locks_remove_file(struct file *filp)
1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079
{
	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;
}

1080
static inline int posix_unblock_lock(struct file_lock *waiter)
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
{
	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;
}

J
J. Bruce Fields 已提交
1107
static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
1108 1109 1110 1111 1112 1113 1114 1115 1116 1117
{
	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,
1118
				    struct file_lock **flp, void **priv)
1119 1120 1121 1122 1123
{
	return -EINVAL;
}

static inline int vfs_setlease(struct file *filp, long arg,
1124
			       struct file_lock **lease, void **priv)
1125 1126 1127 1128
{
	return -EINVAL;
}

1129 1130
static inline int lease_modify(struct file_lock **before, int arg,
			       struct list_head *dispose)
1131 1132 1133
{
	return -EINVAL;
}
1134 1135
#endif /* !CONFIG_FILE_LOCKING */

L
Linus Torvalds 已提交
1136 1137

struct fasync_struct {
1138 1139 1140 1141 1142 1143
	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
1144 1145 1146 1147 1148 1149
};

#define FASYNC_MAGIC 0x4601

/* SMP safe fasync helpers: */
extern int fasync_helper(int, struct file *, int, struct fasync_struct **);
1150 1151 1152 1153 1154
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
1155 1156 1157
/* can be called from interrupts */
extern void kill_fasync(struct fasync_struct **, int, int);

1158 1159
extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
extern void f_setown(struct file *filp, unsigned long arg, int force);
L
Linus Torvalds 已提交
1160
extern void f_delown(struct file *filp);
1161
extern pid_t f_getown(struct file *filp);
L
Linus Torvalds 已提交
1162 1163
extern int send_sigurg(struct fown_struct *fown);

1164 1165
struct mm_struct;

L
Linus Torvalds 已提交
1166 1167 1168 1169 1170 1171 1172
/*
 *	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 */
1173 1174
#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
1175 1176 1177 1178

extern struct list_head super_blocks;
extern spinlock_t sb_lock;

1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203
/* 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
1204 1205 1206
struct super_block {
	struct list_head	s_list;		/* Keep this first */
	dev_t			s_dev;		/* search index; _not_ kdev_t */
1207 1208
	unsigned char		s_blocksize_bits;
	unsigned long		s_blocksize;
1209
	loff_t			s_maxbytes;	/* Max file size */
L
Linus Torvalds 已提交
1210
	struct file_system_type	*s_type;
1211
	const struct super_operations	*s_op;
1212
	const struct dquot_operations	*dq_op;
1213
	const struct quotactl_ops	*s_qcop;
1214
	const struct export_operations *s_export_op;
L
Linus Torvalds 已提交
1215 1216 1217 1218 1219 1220
	unsigned long		s_flags;
	unsigned long		s_magic;
	struct dentry		*s_root;
	struct rw_semaphore	s_umount;
	int			s_count;
	atomic_t		s_active;
1221
#ifdef CONFIG_SECURITY
L
Linus Torvalds 已提交
1222
	void                    *s_security;
1223
#endif
1224
	const struct xattr_handler **s_xattr;
L
Linus Torvalds 已提交
1225 1226

	struct list_head	s_inodes;	/* all inodes */
1227
	struct hlist_bl_head	s_anon;		/* anonymous dentries for (nfs) exporting */
1228
	struct list_head	s_mounts;	/* list of mounts; _not_ for fs use */
L
Linus Torvalds 已提交
1229
	struct block_device	*s_bdev;
J
Jens Axboe 已提交
1230
	struct backing_dev_info *s_bdi;
1231
	struct mtd_info		*s_mtd;
A
Al Viro 已提交
1232
	struct hlist_node	s_instances;
1233
	unsigned int		s_quota_types;	/* Bitmask of supported quota types */
L
Linus Torvalds 已提交
1234 1235
	struct quota_info	s_dquot;	/* Diskquota specific options */

1236
	struct sb_writers	s_writers;
L
Linus Torvalds 已提交
1237 1238

	char s_id[32];				/* Informational name */
1239
	u8 s_uuid[16];				/* UUID */
L
Linus Torvalds 已提交
1240 1241

	void 			*s_fs_info;	/* Filesystem private info */
1242
	unsigned int		s_max_links;
1243
	fmode_t			s_mode;
L
Linus Torvalds 已提交
1244

1245 1246 1247 1248
	/* Granularity of c/m/atime in ns.
	   Cannot be worse than a second */
	u32		   s_time_gran;

L
Linus Torvalds 已提交
1249 1250 1251 1252
	/*
	 * The next field is for VFS *only*. No filesystems have any business
	 * even looking at it. You had been warned.
	 */
1253
	struct mutex s_vfs_rename_mutex;	/* Kludge */
L
Linus Torvalds 已提交
1254

M
Miklos Szeredi 已提交
1255 1256 1257 1258 1259
	/*
	 * Filesystem subtype.  If non-empty the filesystem type field
	 * in /proc/mounts will be "type.subtype"
	 */
	char *s_subtype;
1260 1261 1262 1263 1264

	/*
	 * Saved mount options for lazy filesystems using
	 * generic_show_options()
	 */
A
Arnd Bergmann 已提交
1265
	char __rcu *s_options;
A
Al Viro 已提交
1266
	const struct dentry_operations *s_d_op; /* default d_op for dentries */
1267 1268 1269 1270 1271

	/*
	 * Saved pool identifier for cleancache (-1 means none)
	 */
	int cleancache_poolid;
1272 1273

	struct shrinker s_shrink;	/* per-sb shrinker handle */
1274

M
Miklos Szeredi 已提交
1275 1276 1277
	/* Number of inodes with nlink == 0 but still referenced */
	atomic_long_t s_remove_count;

1278 1279
	/* Being remounted read-only */
	int s_readonly_remount;
1280 1281 1282

	/* AIO completions deferred from interrupt context */
	struct workqueue_struct *s_dio_done_wq;
A
Al Viro 已提交
1283
	struct hlist_head s_pins;
1284 1285 1286 1287 1288 1289 1290

	/*
	 * Keep the lru lists last in the structure so they always sit on their
	 * own individual cachelines.
	 */
	struct list_lru		s_dentry_lru ____cacheline_aligned_in_smp;
	struct list_lru		s_inode_lru ____cacheline_aligned_in_smp;
A
Al Viro 已提交
1291
	struct rcu_head		rcu;
1292 1293 1294 1295 1296

	/*
	 * Indicates how deep in a filesystem stack this SB is
	 */
	int s_stack_depth;
L
Linus Torvalds 已提交
1297 1298 1299 1300 1301 1302 1303 1304
};

extern struct timespec current_fs_time(struct super_block *sb);

/*
 * Snapshotting support.
 */

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 1410 1411 1412 1413
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
1414 1415


1416
extern bool inode_owner_or_capable(const struct inode *inode);
1417

L
Linus Torvalds 已提交
1418 1419 1420
/*
 * VFS helper functions..
 */
A
Al Viro 已提交
1421
extern int vfs_create(struct inode *, struct dentry *, umode_t, bool);
1422
extern int vfs_mkdir(struct inode *, struct dentry *, umode_t);
A
Al Viro 已提交
1423
extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
1424
extern int vfs_symlink(struct inode *, struct dentry *, const char *);
J
J. Bruce Fields 已提交
1425
extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct inode **);
L
Linus Torvalds 已提交
1426
extern int vfs_rmdir(struct inode *, struct dentry *);
1427
extern int vfs_unlink(struct inode *, struct dentry *, struct inode **);
M
Miklos Szeredi 已提交
1428
extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int);
M
Miklos Szeredi 已提交
1429
extern int vfs_whiteout(struct inode *, struct dentry *);
L
Linus Torvalds 已提交
1430 1431 1432 1433 1434 1435

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

1436 1437 1438
/*
 * VFS file helper functions.
 */
1439
extern void inode_init_owner(struct inode *inode, const struct inode *dir,
A
Al Viro 已提交
1440
			umode_t mode);
M
Mark Fasheh 已提交
1441 1442 1443 1444 1445 1446 1447
/*
 * 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 */
1448 1449
	struct fiemap_extent __user *fi_extents_start; /* Start of
							fiemap_extent array */
M
Mark Fasheh 已提交
1450 1451 1452 1453 1454
};
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
1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476
/*
 * 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.
 */
1477 1478 1479 1480
struct dir_context;
typedef int (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64,
			 unsigned);

1481
struct dir_context {
A
Al Viro 已提交
1482
	const filldir_t actor;
1483
	loff_t pos;
1484
};
1485

1486
struct block_device_operations;
L
Linus Torvalds 已提交
1487 1488 1489 1490 1491 1492 1493

/* 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

1494 1495
struct iov_iter;

L
Linus Torvalds 已提交
1496 1497 1498 1499 1500
struct file_operations {
	struct module *owner;
	loff_t (*llseek) (struct file *, loff_t, int);
	ssize_t (*read) (struct file *, char __user *, size_t, loff_t *);
	ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
1501 1502
	ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
	ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
1503 1504
	ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
1505
	int (*iterate) (struct file *, struct dir_context *);
L
Linus Torvalds 已提交
1506 1507 1508 1509 1510
	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 *);
1511
	int (*flush) (struct file *, fl_owner_t id);
L
Linus Torvalds 已提交
1512
	int (*release) (struct inode *, struct file *);
1513
	int (*fsync) (struct file *, loff_t, loff_t, int datasync);
L
Linus Torvalds 已提交
1514 1515 1516 1517 1518 1519 1520
	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 *);
1521 1522
	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);
1523
	int (*setlease)(struct file *, long, struct file_lock **, void **);
1524 1525
	long (*fallocate)(struct file *file, int mode, loff_t offset,
			  loff_t len);
1526
	void (*show_fdinfo)(struct seq_file *m, struct file *f);
L
Linus Torvalds 已提交
1527 1528 1529
};

struct inode_operations {
A
Al Viro 已提交
1530
	struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
1531
	void * (*follow_link) (struct dentry *, struct nameidata *);
1532
	int (*permission) (struct inode *, int);
1533
	struct posix_acl * (*get_acl)(struct inode *, int);
1534 1535 1536 1537

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

A
Al Viro 已提交
1538
	int (*create) (struct inode *,struct dentry *, umode_t, bool);
L
Linus Torvalds 已提交
1539 1540 1541
	int (*link) (struct dentry *,struct inode *,struct dentry *);
	int (*unlink) (struct inode *,struct dentry *);
	int (*symlink) (struct inode *,struct dentry *,const char *);
1542
	int (*mkdir) (struct inode *,struct dentry *,umode_t);
L
Linus Torvalds 已提交
1543
	int (*rmdir) (struct inode *,struct dentry *);
A
Al Viro 已提交
1544
	int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
L
Linus Torvalds 已提交
1545 1546
	int (*rename) (struct inode *, struct dentry *,
			struct inode *, struct dentry *);
M
Miklos Szeredi 已提交
1547 1548
	int (*rename2) (struct inode *, struct dentry *,
			struct inode *, struct dentry *, unsigned int);
L
Linus Torvalds 已提交
1549 1550 1551 1552 1553 1554
	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
1555 1556
	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
		      u64 len);
1557
	int (*update_time)(struct inode *, struct timespec *, int);
A
Al Viro 已提交
1558
	int (*atomic_open)(struct inode *, struct dentry *,
A
Al Viro 已提交
1559
			   struct file *, unsigned open_flag,
A
Al Viro 已提交
1560
			   umode_t create_mode, int *opened);
1561
	int (*tmpfile) (struct inode *, struct dentry *, umode_t);
1562
	int (*set_acl)(struct inode *, struct posix_acl *, int);
M
Miklos Szeredi 已提交
1563 1564 1565

	/* WARNING: probably going away soon, do not use! */
	int (*dentry_open)(struct dentry *, struct file *, const struct cred *);
1566
} ____cacheline_aligned;
L
Linus Torvalds 已提交
1567

B
Badari Pulavarty 已提交
1568
ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
C
Christopher Yeoh 已提交
1569 1570
			      unsigned long nr_segs, unsigned long fast_segs,
			      struct iovec *fast_pointer,
1571
			      struct iovec **ret_pointer);
B
Badari Pulavarty 已提交
1572

L
Linus Torvalds 已提交
1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583
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 *);

1584
   	void (*dirty_inode) (struct inode *, int flags);
1585
	int (*write_inode) (struct inode *, struct writeback_control *wbc);
1586
	int (*drop_inode) (struct inode *);
A
Al Viro 已提交
1587
	void (*evict_inode) (struct inode *);
L
Linus Torvalds 已提交
1588 1589
	void (*put_super) (struct super_block *);
	int (*sync_fs)(struct super_block *sb, int wait);
1590
	int (*freeze_super) (struct super_block *);
1591
	int (*freeze_fs) (struct super_block *);
1592
	int (*thaw_super) (struct super_block *);
1593
	int (*unfreeze_fs) (struct super_block *);
1594
	int (*statfs) (struct dentry *, struct kstatfs *);
L
Linus Torvalds 已提交
1595
	int (*remount_fs) (struct super_block *, int *, char *);
1596
	void (*umount_begin) (struct super_block *);
L
Linus Torvalds 已提交
1597

1598
	int (*show_options)(struct seq_file *, struct dentry *);
1599
	int (*show_devname)(struct seq_file *, struct dentry *);
1600
	int (*show_path)(struct seq_file *, struct dentry *);
1601
	int (*show_stats)(struct seq_file *, struct dentry *);
1602
#ifdef CONFIG_QUOTA
L
Linus Torvalds 已提交
1603 1604
	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);
1605
	struct dquot **(*get_dquots)(struct inode *);
1606
#endif
1607
	int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
1608 1609
	long (*nr_cached_objects)(struct super_block *, int);
	long (*free_cached_objects)(struct super_block *, long, int);
L
Linus Torvalds 已提交
1610 1611
};

D
David Howells 已提交
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
/*
 * Inode flags - they have no relation 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 */
#define S_IMA		1024	/* Inode has an associated IMA struct */
#define S_AUTOMOUNT	2048	/* Automount/referral quasi-directory */
#define S_NOSEC		4096	/* no suid or xattr security attributes */

/*
 * 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)
#define IS_NOATIME(inode)	__IS_FLG(inode, MS_RDONLY|MS_NOATIME)
#define IS_I_VERSION(inode)	__IS_FLG(inode, MS_I_VERSION)

#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)
#define IS_IMA(inode)		((inode)->i_flags & S_IMA)
#define IS_AUTOMOUNT(inode)	((inode)->i_flags & S_AUTOMOUNT)
#define IS_NOSEC(inode)		((inode)->i_flags & S_NOSEC)

M
Miklos Szeredi 已提交
1666 1667 1668
#define IS_WHITEOUT(inode)	(S_ISCHR(inode->i_mode) && \
				 (inode)->i_rdev == WHITEOUT_DEV)

J
Joern Engel 已提交
1669
/*
1670
 * Inode state bits.  Protected by inode->i_lock
J
Joern Engel 已提交
1671 1672 1673 1674 1675 1676 1677 1678
 *
 * 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
1679
 * Two bits are used for locking and completion notification, I_NEW and I_SYNC.
J
Joern Engel 已提交
1680
 *
J
Joern Engel 已提交
1681 1682
 * I_DIRTY_SYNC		Inode is dirty, but doesn't have to be written on
 *			fdatasync().  i_atime is the usual cause.
1683 1684 1685 1686
 * 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
1687
 * I_DIRTY_PAGES	Inode has dirty pages.  Inode itself may be clean.
C
Christoph Hellwig 已提交
1688 1689 1690 1691 1692 1693 1694 1695
 * 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
1696 1697 1698 1699 1700 1701
 * 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.
1702 1703
 * 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
1704 1705 1706 1707 1708
 *
 *			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
1709
 *			if appropriate.  I_NEW is used for waiting.
J
Joern Engel 已提交
1710
 *
1711 1712 1713 1714
 * 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
1715
 *
C
Christoph Hellwig 已提交
1716 1717 1718 1719
 * 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
1720 1721
 * Q: What is the difference between I_WILL_FREE and I_FREEING?
 */
1722 1723 1724
#define I_DIRTY_SYNC		(1 << 0)
#define I_DIRTY_DATASYNC	(1 << 1)
#define I_DIRTY_PAGES		(1 << 2)
C
Christoph Hellwig 已提交
1725 1726
#define __I_NEW			3
#define I_NEW			(1 << __I_NEW)
1727 1728 1729
#define I_WILL_FREE		(1 << 4)
#define I_FREEING		(1 << 5)
#define I_CLEAR			(1 << 6)
C
Christoph Hellwig 已提交
1730
#define __I_SYNC		7
J
Joern Engel 已提交
1731
#define I_SYNC			(1 << __I_SYNC)
1732
#define I_REFERENCED		(1 << 8)
C
Christoph Hellwig 已提交
1733 1734
#define __I_DIO_WAKEUP		9
#define I_DIO_WAKEUP		(1 << I_DIO_WAKEUP)
1735
#define I_LINKABLE		(1 << 10)
L
Linus Torvalds 已提交
1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749

#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
1750 1751 1752 1753
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);
1754 1755 1756 1757

static inline void inode_inc_link_count(struct inode *inode)
{
	inc_nlink(inode);
1758 1759 1760
	mark_inode_dirty(inode);
}

1761 1762 1763
static inline void inode_dec_link_count(struct inode *inode)
{
	drop_nlink(inode);
1764 1765 1766
	mark_inode_dirty(inode);
}

1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781
/**
 * 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);
}

1782 1783 1784 1785 1786 1787 1788
enum file_time_flags {
	S_ATIME = 1,
	S_MTIME = 2,
	S_CTIME = 4,
	S_VERSION = 8,
};

A
Al Viro 已提交
1789
extern void touch_atime(const struct path *);
L
Linus Torvalds 已提交
1790 1791 1792
static inline void file_accessed(struct file *file)
{
	if (!(file->f_flags & O_NOATIME))
A
Al Viro 已提交
1793
		touch_atime(&file->f_path);
L
Linus Torvalds 已提交
1794 1795 1796
}

int sync_inode(struct inode *inode, struct writeback_control *wbc);
C
Christoph Hellwig 已提交
1797
int sync_inode_metadata(struct inode *inode, int wait);
L
Linus Torvalds 已提交
1798 1799 1800 1801

struct file_system_type {
	const char *name;
	int fs_flags;
D
David Howells 已提交
1802 1803 1804
#define FS_REQUIRES_DEV		1 
#define FS_BINARY_MOUNTDATA	2
#define FS_HAS_SUBTYPE		4
1805 1806
#define FS_USERNS_MOUNT		8	/* Can be mounted by userns root */
#define FS_USERNS_DEV_MOUNT	16 /* A userns mount does not imply MNT_NODEV */
D
David Howells 已提交
1807
#define FS_RENAME_DOES_D_MOVE	32768	/* FS will handle d_move() during rename() internally. */
A
Al Viro 已提交
1808 1809
	struct dentry *(*mount) (struct file_system_type *, int,
		       const char *, void *);
L
Linus Torvalds 已提交
1810 1811 1812
	void (*kill_sb) (struct super_block *);
	struct module *owner;
	struct file_system_type * next;
A
Al Viro 已提交
1813
	struct hlist_head fs_supers;
1814

I
Ingo Molnar 已提交
1815
	struct lock_class_key s_lock_key;
1816
	struct lock_class_key s_umount_key;
1817
	struct lock_class_key s_vfs_rename_key;
1818
	struct lock_class_key s_writers_key[SB_FREEZE_LEVELS];
1819 1820 1821

	struct lock_class_key i_lock_key;
	struct lock_class_key i_mutex_key;
1822
	struct lock_class_key i_mutex_dir_key;
L
Linus Torvalds 已提交
1823 1824
};

1825 1826
#define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME)

A
Al Viro 已提交
1827 1828
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
1829 1830 1831
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
1832 1833 1834
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
1835 1836 1837
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
1838
extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path);
L
Linus Torvalds 已提交
1839 1840 1841 1842 1843
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
1844
void deactivate_locked_super(struct super_block *sb);
L
Linus Torvalds 已提交
1845
int set_anon_super(struct super_block *s, void *data);
1846 1847
int get_anon_bdev(dev_t *);
void free_anon_bdev(dev_t);
L
Linus Torvalds 已提交
1848 1849 1850
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
1851
			int flags, void *data);
A
Al Viro 已提交
1852
extern struct dentry *mount_pseudo(struct file_system_type *, char *,
1853 1854 1855
	const struct super_operations *ops,
	const struct dentry_operations *dops,
	unsigned long);
L
Linus Torvalds 已提交
1856 1857 1858 1859 1860 1861

/* 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)
1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872
/*
 * This one is to be used *ONLY* from ->open() instances.
 * fops must be non-NULL, pinned down *and* module dependencies
 * should be sufficient to pin the caller down as well.
 */
#define replace_fops(f, fops) \
	do {	\
		struct file *__file = (f); \
		fops_put(__file->f_op); \
		BUG_ON(!(__file->f_op = (fops))); \
	} while(0)
L
Linus Torvalds 已提交
1873 1874 1875

extern int register_filesystem(struct file_system_type *);
extern int unregister_filesystem(struct file_system_type *);
1876 1877
extern struct vfsmount *kern_mount_data(struct file_system_type *, void *data);
#define kern_mount(type) kern_mount_data(type, NULL)
1878
extern void kern_unmount(struct vfsmount *mnt);
L
Linus Torvalds 已提交
1879 1880
extern int may_umount_tree(struct vfsmount *);
extern int may_umount(struct vfsmount *);
1881 1882
extern long do_mount(const char *, const char __user *,
		     const char *, unsigned long, void *);
A
Al Viro 已提交
1883
extern struct vfsmount *collect_mounts(struct path *);
1884
extern void drop_collected_mounts(struct vfsmount *);
A
Al Viro 已提交
1885 1886
extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *,
			  struct vfsmount *);
1887
extern int vfs_statfs(struct path *, struct kstatfs *);
A
Al Viro 已提交
1888 1889
extern int user_statfs(const char __user *, struct kstatfs *);
extern int fd_statfs(int, struct kstatfs *);
A
Al Viro 已提交
1890
extern int vfs_ustat(dev_t, struct kstatfs *);
1891 1892
extern int freeze_super(struct super_block *super);
extern int thaw_super(struct super_block *super);
1893
extern bool our_mnt(struct vfsmount *mnt);
1894
extern bool fs_fully_visible(struct file_system_type *);
L
Linus Torvalds 已提交
1895

A
Al Viro 已提交
1896 1897
extern int current_umask(void);

1898 1899 1900
extern void ihold(struct inode * inode);
extern void iput(struct inode *);

A
Al Viro 已提交
1901
static inline struct inode *file_inode(const struct file *f)
1902 1903 1904 1905
{
	return f->f_inode;
}

M
Miklos Szeredi 已提交
1906
/* /sys/fs */
1907
extern struct kobject *fs_kobj;
M
Miklos Szeredi 已提交
1908

1909
#define MAX_RW_COUNT (INT_MAX & PAGE_CACHE_MASK)
1910

L
Linus Torvalds 已提交
1911 1912 1913
#define FLOCK_VERIFY_READ  1
#define FLOCK_VERIFY_WRITE 2

1914
#ifdef CONFIG_FILE_LOCKING
1915
extern int locks_mandatory_locked(struct file *);
L
Linus Torvalds 已提交
1916 1917 1918 1919 1920 1921
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.
 */
1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936

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
1937

1938
static inline int locks_verify_locked(struct file *file)
L
Linus Torvalds 已提交
1939
{
1940 1941
	if (mandatory_lock(file_inode(file)))
		return locks_mandatory_locked(file);
L
Linus Torvalds 已提交
1942 1943 1944 1945 1946 1947 1948
	return 0;
}

static inline int locks_verify_truncate(struct inode *inode,
				    struct file *filp,
				    loff_t size)
{
1949
	if (inode->i_flock && mandatory_lock(inode))
L
Linus Torvalds 已提交
1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960
		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)
{
1961 1962 1963 1964 1965 1966
	/*
	 * Since this check is lockless, we must ensure that any refcounts
	 * taken are done before checking inode->i_flock. Otherwise, we could
	 * end up racing with tasks trying to set a new lease on this file.
	 */
	smp_mb();
L
Linus Torvalds 已提交
1967
	if (inode->i_flock)
J
J. Bruce Fields 已提交
1968
		return __break_lease(inode, mode, FL_LEASE);
L
Linus Torvalds 已提交
1969 1970
	return 0;
}
J
J. Bruce Fields 已提交
1971 1972 1973

static inline int break_deleg(struct inode *inode, unsigned int mode)
{
1974 1975 1976 1977 1978 1979
	/*
	 * Since this check is lockless, we must ensure that any refcounts
	 * taken are done before checking inode->i_flock. Otherwise, we could
	 * end up racing with tasks trying to set a new lease on this file.
	 */
	smp_mb();
J
J. Bruce Fields 已提交
1980 1981
	if (inode->i_flock)
		return __break_lease(inode, mode, FL_DELEG);
L
Linus Torvalds 已提交
1982 1983
	return 0;
}
J
J. Bruce Fields 已提交
1984

1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006
static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode)
{
	int ret;

	ret = break_deleg(inode, O_WRONLY|O_NONBLOCK);
	if (ret == -EWOULDBLOCK && delegated_inode) {
		*delegated_inode = inode;
		ihold(inode);
	}
	return ret;
}

static inline int break_deleg_wait(struct inode **delegated_inode)
{
	int ret;

	ret = break_deleg(*delegated_inode, O_WRONLY);
	iput(*delegated_inode);
	*delegated_inode = NULL;
	return ret;
}

2007
#else /* !CONFIG_FILE_LOCKING */
2008
static inline int locks_mandatory_locked(struct file *file)
2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029
{
	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;
}

2030
static inline int locks_verify_locked(struct file *file)
2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045
{
	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;
}

J
J. Bruce Fields 已提交
2046 2047 2048 2049
static inline int break_deleg(struct inode *inode, unsigned int mode)
{
	return 0;
}
2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061

static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode)
{
	return 0;
}

static inline int break_deleg_wait(struct inode **delegated_inode)
{
	BUG();
	return 0;
}

2062
#endif /* CONFIG_FILE_LOCKING */
L
Linus Torvalds 已提交
2063 2064

/* fs/open.c */
2065
struct audit_names;
2066
struct filename {
2067 2068 2069
	const char		*name;	/* pointer to actual string */
	const __user char	*uptr;	/* original userland pointer */
	struct audit_names	*aname;
2070
	bool			separate; /* should "name" be freed? */
2071
};
L
Linus Torvalds 已提交
2072

2073
extern long vfs_truncate(struct path *, loff_t);
2074 2075
extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs,
		       struct file *filp);
2076 2077
extern int do_fallocate(struct file *file, int mode, loff_t offset,
			loff_t len);
J
Jason Uhlenkott 已提交
2078
extern long do_sys_open(int dfd, const char __user *filename, int flags,
2079
			umode_t mode);
2080
extern struct file *file_open_name(struct filename *, int, umode_t);
2081
extern struct file *filp_open(const char *, int, umode_t);
A
Al Viro 已提交
2082 2083
extern struct file *file_open_root(struct dentry *, struct vfsmount *,
				   const char *, int);
M
Miklos Szeredi 已提交
2084
extern int vfs_open(const struct path *, struct file *, const struct cred *);
2085
extern struct file * dentry_open(const struct path *, int, const struct cred *);
L
Linus Torvalds 已提交
2086
extern int filp_close(struct file *, fl_owner_t id);
2087 2088

extern struct filename *getname(const char __user *);
2089
extern struct filename *getname_kernel(const char *);
2090

2091 2092 2093 2094
enum {
	FILE_CREATED = 1,
	FILE_OPENED = 2
};
A
Al Viro 已提交
2095 2096 2097
extern int finish_open(struct file *file, struct dentry *dentry,
			int (*open)(struct inode *, struct file *),
			int *opened);
A
Al Viro 已提交
2098
extern int finish_no_open(struct file *file, struct dentry *dentry);
L
Linus Torvalds 已提交
2099

2100 2101 2102 2103
/* fs/ioctl.c */

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

L
Linus Torvalds 已提交
2104 2105 2106 2107
/* fs/dcache.c */
extern void __init vfs_caches_init_early(void);
extern void __init vfs_caches_init(unsigned long);

2108 2109
extern struct kmem_cache *names_cachep;

2110 2111
extern void final_putname(struct filename *name);

2112
#define __getname()		kmem_cache_alloc(names_cachep, GFP_KERNEL)
V
Vegard Nossum 已提交
2113
#define __putname(name)		kmem_cache_free(names_cachep, (void *)(name))
L
Linus Torvalds 已提交
2114
#ifndef CONFIG_AUDITSYSCALL
2115
#define putname(name)		final_putname(name)
L
Linus Torvalds 已提交
2116
#else
2117
extern void putname(struct filename *name);
L
Linus Torvalds 已提交
2118 2119
#endif

2120
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2121
extern int register_blkdev(unsigned int, const char *);
A
Akinobu Mita 已提交
2122
extern void unregister_blkdev(unsigned int, const char *);
L
Linus Torvalds 已提交
2123
extern struct block_device *bdget(dev_t);
2124
extern struct block_device *bdgrab(struct block_device *bdev);
L
Linus Torvalds 已提交
2125 2126 2127
extern void bd_set_size(struct block_device *, loff_t size);
extern void bd_forget(struct inode *inode);
extern void bdput(struct block_device *);
N
Nick Piggin 已提交
2128
extern void invalidate_bdev(struct block_device *);
2129
extern void iterate_bdevs(void (*)(struct block_device *, void *), void *);
N
Nick Piggin 已提交
2130
extern int sync_blockdev(struct block_device *bdev);
A
Al Viro 已提交
2131
extern void kill_bdev(struct block_device *);
N
Nick Piggin 已提交
2132
extern struct super_block *freeze_bdev(struct block_device *);
2133
extern void emergency_thaw_all(void);
N
Nick Piggin 已提交
2134 2135
extern int thaw_bdev(struct block_device *bdev, struct super_block *sb);
extern int fsync_bdev(struct block_device *);
2136
extern int sb_is_blkdev_sb(struct super_block *sb);
2137 2138
#else
static inline void bd_forget(struct inode *inode) {}
2139
static inline int sync_blockdev(struct block_device *bdev) { return 0; }
A
Al Viro 已提交
2140
static inline void kill_bdev(struct block_device *bdev) {}
2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151
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;
}
2152 2153 2154 2155

static inline void iterate_bdevs(void (*f)(struct block_device *, void *), void *arg)
{
}
2156 2157 2158 2159 2160

static inline int sb_is_blkdev_sb(struct super_block *sb)
{
	return 0;
}
2161
#endif
2162
extern int sync_filesystem(struct super_block *);
2163
extern const struct file_operations def_blk_fops;
2164 2165
extern const struct file_operations def_chr_fops;
extern const struct file_operations bad_sock_fops;
2166
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2167
extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long);
2168
extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long);
L
Linus Torvalds 已提交
2169
extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long);
2170
extern int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder);
2171 2172 2173 2174
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);
A
Al Viro 已提交
2175
extern void blkdev_put(struct block_device *bdev, fmode_t mode);
2176
#ifdef CONFIG_SYSFS
2177
extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk);
2178 2179
extern void bd_unlink_disk_holder(struct block_device *bdev,
				  struct gendisk *disk);
2180
#else
2181 2182 2183 2184 2185
static inline int bd_link_disk_holder(struct block_device *bdev,
				      struct gendisk *disk)
{
	return 0;
}
2186 2187 2188 2189
static inline void bd_unlink_disk_holder(struct block_device *bdev,
					 struct gendisk *disk)
{
}
2190
#endif
2191
#endif
L
Linus Torvalds 已提交
2192 2193

/* fs/char_dev.c */
2194
#define CHRDEV_MAJOR_HASH_SIZE	255
L
Linus Torvalds 已提交
2195 2196
extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *);
extern int register_chrdev_region(dev_t, unsigned, const char *);
2197 2198 2199 2200 2201
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
2202
extern void unregister_chrdev_region(dev_t, unsigned);
2203
extern void chrdev_show(struct seq_file *,off_t);
L
Linus Torvalds 已提交
2204

2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215
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
2216 2217
/* fs/block_dev.c */
#define BDEVNAME_SIZE	32	/* Largest string for a blockdev identifier */
2218
#define BDEVT_SIZE	10	/* Largest string for MAJ:MIN for blkdev */
2219 2220 2221

#ifdef CONFIG_BLOCK
#define BLKDEV_MAJOR_HASH_SIZE	255
L
Linus Torvalds 已提交
2222 2223 2224
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 *);
2225
extern void blkdev_show(struct seq_file *,off_t);
2226

2227 2228 2229
#else
#define BLKDEV_MAJOR_HASH_SIZE	0
#endif
L
Linus Torvalds 已提交
2230 2231 2232 2233 2234 2235 2236

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 *);

2237
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2238 2239 2240 2241 2242 2243 2244 2245 2246 2247
/*
 * 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)

2248 2249
extern void check_disk_size_change(struct gendisk *disk,
				   struct block_device *bdev);
2250
extern int revalidate_disk(struct gendisk *);
L
Linus Torvalds 已提交
2251
extern int check_disk_change(struct block_device *);
2252
extern int __invalidate_device(struct block_device *, bool);
L
Linus Torvalds 已提交
2253
extern int invalidate_partition(struct gendisk *, int);
2254
#endif
L
Linus Torvalds 已提交
2255 2256
unsigned long invalidate_mapping_pages(struct address_space *mapping,
					pgoff_t start, pgoff_t end);
2257

L
Linus Torvalds 已提交
2258 2259 2260 2261
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))
2262
		invalidate_mapping_pages(inode->i_mapping, 0, -1);
L
Linus Torvalds 已提交
2263 2264 2265 2266 2267 2268 2269 2270
}
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 *);
2271 2272
extern int filemap_fdatawait_range(struct address_space *, loff_t lstart,
				   loff_t lend);
L
Linus Torvalds 已提交
2273 2274 2275
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);
2276 2277
extern int __filemap_fdatawrite_range(struct address_space *mapping,
				loff_t start, loff_t end, int sync_mode);
2278 2279
extern int filemap_fdatawrite_range(struct address_space *mapping,
				loff_t start, loff_t end);
2280

2281 2282 2283
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);
2284 2285 2286 2287 2288 2289 2290
static inline int generic_write_sync(struct file *file, loff_t pos, loff_t count)
{
	if (!(file->f_flags & O_DSYNC) && !IS_SYNC(file->f_mapping->host))
		return 0;
	return vfs_fsync_range(file, pos, pos + count - 1,
			       (file->f_flags & __O_SYNC) ? 0 : 1);
}
L
Linus Torvalds 已提交
2291 2292
extern void emergency_sync(void);
extern void emergency_remount(void);
2293
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2294
extern sector_t bmap(struct inode *, sector_t);
2295
#endif
2296
extern int notify_change(struct dentry *, struct iattr *, struct inode **);
2297
extern int inode_permission(struct inode *, int);
2298
extern int __inode_permission(struct inode *, int);
2299
extern int generic_permission(struct inode *, int);
M
Miklos Szeredi 已提交
2300
extern int __check_sticky(struct inode *dir, struct inode *inode);
L
Linus Torvalds 已提交
2301

2302 2303 2304 2305 2306
static inline bool execute_ok(struct inode *inode)
{
	return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode);
}

2307 2308 2309 2310 2311 2312 2313
static inline void file_start_write(struct file *file)
{
	if (!S_ISREG(file_inode(file)->i_mode))
		return;
	__sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true);
}

2314 2315 2316 2317 2318 2319 2320
static inline bool file_start_write_trylock(struct file *file)
{
	if (!S_ISREG(file_inode(file)->i_mode))
		return true;
	return __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, false);
}

2321 2322 2323 2324 2325 2326 2327
static inline void file_end_write(struct file *file)
{
	if (!S_ISREG(file_inode(file)->i_mode))
		return;
	__sb_end_write(file_inode(file)->i_sb, SB_FREEZE_WRITE);
}

2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349
/*
 * 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)
{
A
Al Viro 已提交
2350
	struct inode *inode = file_inode(file);
2351 2352
	return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY;
}
L
Linus Torvalds 已提交
2353 2354 2355 2356 2357 2358 2359
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)
A
Al Viro 已提交
2360
		atomic_inc(&file_inode(file)->i_writecount);
L
Linus Torvalds 已提交
2361
}
2362 2363 2364 2365 2366
static inline bool inode_is_open_for_write(const struct inode *inode)
{
	return atomic_read(&inode->i_writecount) > 0;
}

M
Mimi Zohar 已提交
2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386
#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
2387
extern int do_pipe_flags(int *, int);
L
Linus Torvalds 已提交
2388

M
Mimi Zohar 已提交
2389
extern int kernel_read(struct file *, loff_t, char *, unsigned long);
2390
extern ssize_t kernel_write(struct file *, const char *, size_t, loff_t);
A
Al Viro 已提交
2391
extern ssize_t __kernel_write(struct file *, const char *, size_t, loff_t *);
L
Linus Torvalds 已提交
2392 2393 2394 2395
extern struct file * open_exec(const char *);
 
/* fs/dcache.c -- generic fs support functions */
extern int is_subdir(struct dentry *, struct dentry *);
2396
extern int path_is_under(struct path *, struct path *);
L
Linus Torvalds 已提交
2397 2398 2399 2400

#include <linux/err.h>

/* needed for stackable file system support */
2401
extern loff_t default_llseek(struct file *file, loff_t offset, int whence);
L
Linus Torvalds 已提交
2402

2403
extern loff_t vfs_llseek(struct file *file, loff_t offset, int whence);
L
Linus Torvalds 已提交
2404

2405
extern int inode_init_always(struct super_block *, struct inode *);
L
Linus Torvalds 已提交
2406
extern void inode_init_once(struct inode *);
2407
extern void address_space_init_once(struct address_space *mapping);
L
Linus Torvalds 已提交
2408 2409 2410
extern struct inode * igrab(struct inode *);
extern ino_t iunique(struct super_block *, ino_t);
extern int inode_needs_sync(struct inode *inode);
2411
extern int generic_delete_inode(struct inode *inode);
2412 2413 2414 2415
static inline int generic_drop_inode(struct inode *inode)
{
	return !inode->i_nlink || inode_unhashed(inode);
}
L
Linus Torvalds 已提交
2416

2417 2418 2419
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
2420 2421 2422 2423 2424 2425
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
2426 2427
extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *);
extern int insert_inode_locked(struct inode *);
2428 2429 2430 2431 2432
#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
2433
extern void unlock_new_inode(struct inode *);
2434
extern unsigned int get_next_ino(void);
L
Linus Torvalds 已提交
2435 2436

extern void __iget(struct inode * inode);
2437
extern void iget_failed(struct inode *);
2438
extern void clear_inode(struct inode *);
C
Christoph Hellwig 已提交
2439
extern void __destroy_inode(struct inode *);
2440 2441
extern struct inode *new_inode_pseudo(struct super_block *sb);
extern struct inode *new_inode(struct super_block *sb);
2442
extern void free_inode_nonrcu(struct inode *inode);
2443
extern int should_remove_suid(struct dentry *);
2444
extern int file_remove_suid(struct file *);
L
Linus Torvalds 已提交
2445 2446

extern void __insert_inode_hash(struct inode *, unsigned long hashval);
2447 2448
static inline void insert_inode_hash(struct inode *inode)
{
L
Linus Torvalds 已提交
2449 2450
	__insert_inode_hash(inode, inode->i_ino);
}
2451 2452 2453 2454 2455 2456 2457 2458

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

2459
extern void inode_sb_list_add(struct inode *inode);
L
Linus Torvalds 已提交
2460

2461
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2462 2463
extern void submit_bio(int, struct bio *);
extern int bdev_read_only(struct block_device *);
2464
#endif
L
Linus Torvalds 已提交
2465 2466 2467 2468 2469 2470
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 *);
2471 2472
extern int generic_file_remap_pages(struct vm_area_struct *, unsigned long addr,
		unsigned long size, pgoff_t pgoff);
L
Linus Torvalds 已提交
2473
int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk);
A
Al Viro 已提交
2474
extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *);
2475 2476
extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *);
extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *);
A
Al Viro 已提交
2477
extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *, loff_t);
2478
extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t);
L
Linus Torvalds 已提交
2479 2480
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);
2481 2482
extern ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos);
extern ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos);
A
Andrew Morton 已提交
2483

2484
/* fs/block_dev.c */
2485
extern ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to);
2486
extern ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from);
2487 2488
extern int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
			int datasync);
A
Al Viro 已提交
2489
extern void block_sync_page(struct page *page);
2490

A
Andrew Morton 已提交
2491
/* fs/splice.c */
2492
extern ssize_t generic_file_splice_read(struct file *, loff_t *,
A
Andrew Morton 已提交
2493
		struct pipe_inode_info *, size_t, unsigned int);
2494 2495
extern ssize_t default_file_splice_read(struct file *, loff_t *,
		struct pipe_inode_info *, size_t, unsigned int);
A
Al Viro 已提交
2496
extern ssize_t iter_file_splice_write(struct pipe_inode_info *,
2497
		struct file *, loff_t *, size_t, unsigned int);
A
Andrew Morton 已提交
2498
extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
2499
		struct file *out, loff_t *, size_t len, unsigned int flags);
2500 2501 2502
extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
		loff_t *opos, size_t len, unsigned int flags);

A
Andrew Morton 已提交
2503

L
Linus Torvalds 已提交
2504 2505
extern void
file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping);
2506 2507
extern loff_t noop_llseek(struct file *file, loff_t offset, int whence);
extern loff_t no_llseek(struct file *file, loff_t offset, int whence);
J
Jie Liu 已提交
2508
extern loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize);
2509
extern loff_t generic_file_llseek(struct file *file, loff_t offset, int whence);
A
Andi Kleen 已提交
2510
extern loff_t generic_file_llseek_size(struct file *file, loff_t offset,
2511
		int whence, loff_t maxsize, loff_t eof);
A
Al Viro 已提交
2512 2513
extern loff_t fixed_size_llseek(struct file *file, loff_t offset,
		int whence, loff_t size);
L
Linus Torvalds 已提交
2514 2515 2516
extern int generic_file_open(struct inode * inode, struct file * filp);
extern int nonseekable_open(struct inode * inode, struct file * filp);

2517
#ifdef CONFIG_FS_XIP
2518 2519
extern ssize_t xip_file_read(struct file *filp, char __user *buf, size_t len,
			     loff_t *ppos);
2520
extern int xip_file_mmap(struct file * file, struct vm_area_struct * vma);
2521 2522
extern ssize_t xip_file_write(struct file *filp, const char __user *buf,
			      size_t len, loff_t *ppos);
2523
extern int xip_truncate_page(struct address_space *mapping, loff_t from);
2524 2525 2526 2527 2528
#else
static inline int xip_truncate_page(struct address_space *mapping, loff_t from)
{
	return 0;
}
2529 2530
#endif

2531
#ifdef CONFIG_BLOCK
2532 2533
typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode,
			    loff_t file_offset);
L
Linus Torvalds 已提交
2534 2535

enum {
2536 2537 2538 2539 2540
	/* need locking between buffered and direct access */
	DIO_LOCKING	= 0x01,

	/* filesystem does not support filling holes */
	DIO_SKIP_HOLES	= 0x02,
2541 2542 2543

	/* filesystem can handle aio writes beyond i_size */
	DIO_ASYNC_EXTEND = 0x04,
L
Linus Torvalds 已提交
2544 2545
};

2546 2547 2548
void dio_end_io(struct bio *bio, int error);

ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
2549 2550
	struct block_device *bdev, struct iov_iter *iter, loff_t offset,
	get_block_t get_block, dio_iodone_t end_io,
2551
	dio_submit_t submit_io,	int flags);
2552

L
Linus Torvalds 已提交
2553
static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb,
2554 2555
		struct inode *inode, struct iov_iter *iter, loff_t offset,
		get_block_t get_block)
L
Linus Torvalds 已提交
2556
{
2557 2558
	return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iter,
				    offset, get_block, NULL, NULL,
2559
				    DIO_LOCKING | DIO_SKIP_HOLES);
L
Linus Torvalds 已提交
2560
}
2561
#endif
L
Linus Torvalds 已提交
2562

2563 2564 2565
void inode_dio_wait(struct inode *inode);
void inode_dio_done(struct inode *inode);

2566 2567 2568
extern void inode_set_flags(struct inode *inode, unsigned int flags,
			    unsigned int mask);

2569
extern const struct file_operations generic_ro_fops;
L
Linus Torvalds 已提交
2570 2571 2572

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

A
Al Viro 已提交
2573
extern int readlink_copy(char __user *, int, const char *);
L
Linus Torvalds 已提交
2574
extern int page_readlink(struct dentry *, char __user *, int);
2575 2576
extern void *page_follow_link_light(struct dentry *, struct nameidata *);
extern void page_put_link(struct dentry *, struct nameidata *, void *);
2577
extern int __page_symlink(struct inode *inode, const char *symname, int len,
2578
		int nofs);
L
Linus Torvalds 已提交
2579
extern int page_symlink(struct inode *inode, const char *symname, int len);
2580
extern const struct inode_operations page_symlink_inode_operations;
A
Al Viro 已提交
2581
extern void kfree_put_link(struct dentry *, struct nameidata *, void *);
L
Linus Torvalds 已提交
2582 2583
extern int generic_readlink(struct dentry *, char __user *, int);
extern void generic_fillattr(struct inode *, struct kstat *);
J
J. Bruce Fields 已提交
2584
int vfs_getattr_nosec(struct path *path, struct kstat *stat);
A
Al Viro 已提交
2585
extern int vfs_getattr(struct path *, struct kstat *);
2586
void __inode_add_bytes(struct inode *inode, loff_t bytes);
L
Linus Torvalds 已提交
2587
void inode_add_bytes(struct inode *inode, loff_t bytes);
2588
void __inode_sub_bytes(struct inode *inode, loff_t bytes);
L
Linus Torvalds 已提交
2589 2590 2591 2592 2593
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 *);
2594
extern int iterate_dir(struct file *, struct dir_context *);
L
Linus Torvalds 已提交
2595

2596 2597
extern int vfs_stat(const char __user *, struct kstat *);
extern int vfs_lstat(const char __user *, struct kstat *);
L
Linus Torvalds 已提交
2598
extern int vfs_fstat(unsigned int, struct kstat *);
2599
extern int vfs_fstatat(int , const char __user *, struct kstat *, int);
L
Linus Torvalds 已提交
2600

2601 2602
extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
		    unsigned long arg);
2603
extern int __generic_block_fiemap(struct inode *inode,
J
Josef Bacik 已提交
2604 2605 2606
				  struct fiemap_extent_info *fieinfo,
				  loff_t start, loff_t len,
				  get_block_t *get_block);
2607 2608 2609
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
2610

2611 2612
extern void get_filesystem(struct file_system_type *fs);
extern void put_filesystem(struct file_system_type *fs);
L
Linus Torvalds 已提交
2613 2614
extern struct file_system_type *get_fs_type(const char *name);
extern struct super_block *get_super(struct block_device *);
2615
extern struct super_block *get_super_thawed(struct block_device *);
2616
extern struct super_block *get_active_super(struct block_device *bdev);
L
Linus Torvalds 已提交
2617
extern void drop_super(struct super_block *sb);
A
Al Viro 已提交
2618
extern void iterate_supers(void (*)(struct super_block *, void *), void *);
A
Al Viro 已提交
2619 2620
extern void iterate_supers_type(struct file_system_type *,
			        void (*)(struct super_block *, void *), void *);
L
Linus Torvalds 已提交
2621 2622 2623 2624

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);
2625
extern int dcache_readdir(struct file *, struct dir_context *);
2626
extern int simple_setattr(struct dentry *, struct iattr *);
L
Linus Torvalds 已提交
2627
extern int simple_getattr(struct vfsmount *, struct dentry *, struct kstat *);
2628
extern int simple_statfs(struct dentry *, struct kstatfs *);
S
Stephen Boyd 已提交
2629
extern int simple_open(struct inode *inode, struct file *file);
L
Linus Torvalds 已提交
2630 2631 2632 2633
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 *);
2634
extern int noop_fsync(struct file *, loff_t, loff_t, int);
L
Linus Torvalds 已提交
2635 2636
extern int simple_empty(struct dentry *);
extern int simple_readpage(struct file *file, struct page *page);
2637 2638 2639 2640 2641 2642
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);
2643
extern int always_delete_dentry(const struct dentry *);
A
Al Viro 已提交
2644
extern struct inode *alloc_anon_inode(struct super_block *);
2645
extern int simple_nosetlease(struct file *, long, struct file_lock **, void **);
2646
extern const struct dentry_operations simple_dentry_operations;
L
Linus Torvalds 已提交
2647

A
Al Viro 已提交
2648
extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags);
L
Linus Torvalds 已提交
2649
extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *);
2650
extern const struct file_operations simple_dir_operations;
2651
extern const struct inode_operations simple_dir_inode_operations;
2652
struct tree_descr { char *name; const struct file_operations *ops; int mode; };
L
Linus Torvalds 已提交
2653
struct dentry *d_alloc_name(struct dentry *, const char *);
2654
extern int simple_fill_super(struct super_block *, unsigned long, struct tree_descr *);
2655
extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count);
L
Linus Torvalds 已提交
2656 2657
extern void simple_release_fs(struct vfsmount **mount, int *count);

2658 2659
extern ssize_t simple_read_from_buffer(void __user *to, size_t count,
			loff_t *ppos, const void *from, size_t available);
2660 2661
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
2662

2663
extern int __generic_file_fsync(struct file *, loff_t, loff_t, int);
2664
extern int generic_file_fsync(struct file *, loff_t, loff_t, int);
A
Al Viro 已提交
2665

2666 2667
extern int generic_check_addressable(unsigned, u64);

2668
#ifdef CONFIG_MIGRATION
2669
extern int buffer_migrate_page(struct address_space *,
2670 2671
				struct page *, struct page *,
				enum migrate_mode);
2672 2673 2674 2675
#else
#define buffer_migrate_page NULL
#endif

N
npiggin@suse.de 已提交
2676 2677
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
2678
extern void setattr_copy(struct inode *inode, const struct iattr *attr);
L
Linus Torvalds 已提交
2679

2680
extern int file_update_time(struct file *file);
L
Linus Torvalds 已提交
2681

2682
extern int generic_show_options(struct seq_file *m, struct dentry *root);
2683
extern void save_mount_options(struct super_block *sb, char *options);
2684
extern void replace_mount_options(struct super_block *sb, char *options);
2685

L
Linus Torvalds 已提交
2686 2687 2688 2689
static inline ino_t parent_ino(struct dentry *dentry)
{
	ino_t res;

N
Nick Piggin 已提交
2690 2691 2692 2693
	/*
	 * 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
2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718
	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);

2719
void simple_transaction_set(struct file *file, size_t n);
L
Linus Torvalds 已提交
2720

2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742
/*
 * 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);	\
}									\
2743
static const struct file_operations __fops = {				\
2744 2745
	.owner	 = THIS_MODULE,						\
	.open	 = __fops ## _open,					\
2746
	.release = simple_attr_release,					\
2747 2748
	.read	 = simple_attr_read,					\
	.write	 = simple_attr_write,					\
2749
	.llseek	 = generic_file_llseek,					\
2750
}
2751

2752 2753
static inline __printf(1, 2)
void __simple_attr_check_format(const char *fmt, ...)
2754 2755 2756 2757 2758
{
	/* don't do anything, just let the compiler check the arguments; */
}

int simple_attr_open(struct inode *inode, struct file *file,
2759
		     int (*get)(void *, u64 *), int (*set)(void *, u64),
2760
		     const char *fmt);
2761
int simple_attr_release(struct inode *inode, struct file *file);
2762 2763 2764 2765 2766
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
2767
struct ctl_table;
2768
int proc_nr_files(struct ctl_table *table, int write,
2769
		  void __user *buffer, size_t *lenp, loff_t *ppos);
2770 2771
int proc_nr_dentry(struct ctl_table *table, int write,
		  void __user *buffer, size_t *lenp, loff_t *ppos);
2772 2773
int proc_nr_inodes(struct ctl_table *table, int write,
		   void __user *buffer, size_t *lenp, loff_t *ppos);
2774
int __init get_filesystem_list(char *buf);
2775

N
Namhyung Kim 已提交
2776
#define __FMODE_EXEC		((__force int) FMODE_EXEC)
2777 2778
#define __FMODE_NONOTIFY	((__force int) FMODE_NONOTIFY)

A
Al Viro 已提交
2779
#define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE])
E
Eric Paris 已提交
2780
#define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \
2781
					    (flag & __FMODE_NONOTIFY)))
A
Al Viro 已提交
2782

A
Al Viro 已提交
2783
static inline int is_sxid(umode_t mode)
2784 2785 2786 2787
{
	return (mode & S_ISUID) || ((mode & S_ISGID) && (mode & S_IXGRP));
}

M
Miklos Szeredi 已提交
2788 2789 2790 2791 2792 2793 2794 2795
static inline int check_sticky(struct inode *dir, struct inode *inode)
{
	if (!(dir->i_mode & S_ISVTX))
		return 0;

	return __check_sticky(dir, inode);
}

2796 2797
static inline void inode_has_no_xattr(struct inode *inode)
{
A
Al Viro 已提交
2798
	if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & MS_NOSEC))
2799 2800 2801
		inode->i_flags |= S_NOSEC;
}

A
Al Viro 已提交
2802 2803 2804 2805 2806
static inline bool is_root_inode(struct inode *inode)
{
	return inode == inode->i_sb->s_root->d_inode;
}

2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836
static inline bool dir_emit(struct dir_context *ctx,
			    const char *name, int namelen,
			    u64 ino, unsigned type)
{
	return ctx->actor(ctx, name, namelen, ctx->pos, ino, type) == 0;
}
static inline bool dir_emit_dot(struct file *file, struct dir_context *ctx)
{
	return ctx->actor(ctx, ".", 1, ctx->pos,
			  file->f_path.dentry->d_inode->i_ino, DT_DIR) == 0;
}
static inline bool dir_emit_dotdot(struct file *file, struct dir_context *ctx)
{
	return ctx->actor(ctx, "..", 2, ctx->pos,
			  parent_ino(file->f_path.dentry), DT_DIR) == 0;
}
static inline bool dir_emit_dots(struct file *file, struct dir_context *ctx)
{
	if (ctx->pos == 0) {
		if (!dir_emit_dot(file, ctx))
			return false;
		ctx->pos = 1;
	}
	if (ctx->pos == 1) {
		if (!dir_emit_dotdot(file, ctx))
			return false;
		ctx->pos = 2;
	}
	return true;
}
A
Al Viro 已提交
2837 2838 2839 2840 2841 2842
static inline bool dir_relax(struct inode *inode)
{
	mutex_unlock(&inode->i_mutex);
	mutex_lock(&inode->i_mutex);
	return !IS_DEADDIR(inode);
}
2843

L
Linus Torvalds 已提交
2844
#endif /* _LINUX_FS_H */