fs.h 96.4 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/rwsem.h>
22
#include <linux/capability.h>
23
#include <linux/semaphore.h>
M
Mark Fasheh 已提交
24
#include <linux/fiemap.h>
25
#include <linux/rculist_bl.h>
26
#include <linux/atomic.h>
27
#include <linux/shrinker.h>
28
#include <linux/migrate_mode.h>
29
#include <linux/uidgid.h>
30
#include <linux/lockdep.h>
31
#include <linux/percpu-rwsem.h>
D
David Howells 已提交
32
#include <linux/blk_types.h>
L
Linus Torvalds 已提交
33 34

#include <asm/byteorder.h>
35
#include <uapi/linux/fs.h>
L
Linus Torvalds 已提交
36

37
struct backing_dev_info;
38
struct export_operations;
39
struct hd_geometry;
L
Linus Torvalds 已提交
40 41
struct iovec;
struct nameidata;
42
struct kiocb;
A
Alexey Dobriyan 已提交
43
struct kobject;
L
Linus Torvalds 已提交
44 45 46 47 48
struct pipe_inode_info;
struct poll_table_struct;
struct kstatfs;
struct vm_area_struct;
struct vfsmount;
49
struct cred;
50
struct swap_info_struct;
51
struct seq_file;
52
struct workqueue_struct;
53
struct iov_iter;
54
struct vm_fault;
L
Linus Torvalds 已提交
55

56
extern void __init inode_init(void);
L
Linus Torvalds 已提交
57 58 59
extern void __init inode_init_early(void);
extern void __init files_init(unsigned long);

60
extern struct files_stat_struct files_stat;
E
Eric Dumazet 已提交
61
extern unsigned long get_max_files(void);
62 63 64
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
65 66
extern int sysctl_protected_symlinks;
extern int sysctl_protected_hardlinks;
67

L
Linus Torvalds 已提交
68 69 70
struct buffer_head;
typedef int (get_block_t)(struct inode *inode, sector_t iblock,
			struct buffer_head *bh_result, int create);
71
typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
72
			ssize_t bytes, void *private);
L
Linus Torvalds 已提交
73

D
David Howells 已提交
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129
#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)

130 131
/* File needs atomic accesses to f_pos */
#define FMODE_ATOMIC_POS	((__force fmode_t)0x8000)
132 133
/* Write access to underlying fs */
#define FMODE_WRITER		((__force fmode_t)0x10000)
134 135 136 137
/* Has read method(s) */
#define FMODE_CAN_READ          ((__force fmode_t)0x20000)
/* Has write method(s) */
#define FMODE_CAN_WRITE         ((__force fmode_t)0x40000)
138

D
David Howells 已提交
139
/* File was opened by fanotify and shouldn't generate fanotify events */
140
#define FMODE_NONOTIFY		((__force fmode_t)0x4000000)
D
David Howells 已提交
141 142 143 144 145 146 147 148 149

/*
 * 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
150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205
/*
 * 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
206 207 208 209
/*
 * Attribute flags.  These should be or-ed together to figure out what
 * has been changed!
 */
210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226
#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
227

M
Miklos Szeredi 已提交
228 229 230 231 232 233 234
/*
 * 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
235 236 237 238 239 240 241 242 243 244 245 246
/*
 * 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;
247 248
	kuid_t		ia_uid;
	kgid_t		ia_gid;
L
Linus Torvalds 已提交
249 250 251 252
	loff_t		ia_size;
	struct timespec	ia_atime;
	struct timespec	ia_mtime;
	struct timespec	ia_ctime;
253 254

	/*
L
Lucas De Marchi 已提交
255
	 * Not an attribute, but an auxiliary info for filesystems wanting to
256 257 258 259
	 * 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
260 261 262 263 264 265 266
};

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

267 268 269 270 271 272
/*
 * Maximum number of layers of fs stack.  Needs to be limited to
 * prevent kernel stack overflow
 */
#define FILESYSTEM_MAX_STACK_DEPTH 2

273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290
/** 
 * 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
291
 *  			by readpage().
292 293 294 295 296 297 298 299 300 301 302 303
 *
 * 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,
};

304
#define AOP_FLAG_UNINTERRUPTIBLE	0x0001 /* will not do a short write */
N
Nick Piggin 已提交
305
#define AOP_FLAG_CONT_EXPAND		0x0002 /* called from cont_expand */
306 307 308
#define AOP_FLAG_NOFS			0x0004 /* used by filesystem to direct
						* helper code (eg buffer layer)
						* to clear GFP_FS from alloc */
309

L
Linus Torvalds 已提交
310 311 312 313 314 315 316
/*
 * oh the beauties of C type declarations.
 */
struct page;
struct address_space;
struct writeback_control;

317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338
#define IOCB_EVENTFD		(1 << 0)

struct kiocb {
	struct file		*ki_filp;
	loff_t			ki_pos;
	void (*ki_complete)(struct kiocb *iocb, long ret, long ret2);
	void			*private;
	int			ki_flags;
};

static inline bool is_sync_kiocb(struct kiocb *kiocb)
{
	return kiocb->ki_complete == NULL;
}

static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
{
	*kiocb = (struct kiocb) {
		.ki_filp = filp,
	};
}

339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359
/*
 * "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
360

L
Linus Torvalds 已提交
361 362 363 364 365 366 367
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 *);

368
	/* Set a page dirty.  Return true if this dirtied it */
L
Linus Torvalds 已提交
369 370 371 372 373
	int (*set_page_dirty)(struct page *page);

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

374 375 376 377 378 379 380
	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
381 382
	/* Unfortunately this kludge is needed for FIBMAP. Don't use it */
	sector_t (*bmap)(struct address_space *, sector_t);
383
	void (*invalidatepage) (struct page *, unsigned int, unsigned int);
A
Al Viro 已提交
384
	int (*releasepage) (struct page *, gfp_t);
385
	void (*freepage)(struct page *);
A
Al Viro 已提交
386
	ssize_t (*direct_IO)(int, struct kiocb *, struct iov_iter *iter, loff_t offset);
387
	/*
388 389
	 * migrate the contents of a page to the specified target. If
	 * migrate_mode is MIGRATE_ASYNC, it must not block.
390
	 */
391
	int (*migratepage) (struct address_space *,
392
			struct page *, struct page *, enum migrate_mode);
393
	int (*launder_page) (struct page *);
394
	int (*is_partially_uptodate) (struct page *, unsigned long,
395
					unsigned long);
396
	void (*is_dirty_writeback) (struct page *, bool *, bool *);
397
	int (*error_remove_page)(struct address_space *, struct page *);
398 399

	/* swapfile support */
400 401 402
	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
403 404
};

J
Jens Axboe 已提交
405 406
extern const struct address_space_operations empty_aops;

407 408 409 410 411 412 413 414 415 416 417 418
/*
 * 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
419 420 421
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
422
	spinlock_t		tree_lock;	/* and lock protecting it */
423
	atomic_t		i_mmap_writable;/* count VM_SHARED mappings */
424
	struct rb_root		i_mmap;		/* tree of private and shared mappings */
425
	struct rw_semaphore	i_mmap_rwsem;	/* protect tree, count, list */
426
	/* Protected by tree_lock together with the radix tree */
L
Linus Torvalds 已提交
427
	unsigned long		nrpages;	/* number of total pages */
428
	unsigned long		nrshadows;	/* number of shadow entries */
L
Linus Torvalds 已提交
429
	pgoff_t			writeback_index;/* writeback starts here */
430
	const struct address_space_operations *a_ops;	/* methods */
L
Linus Torvalds 已提交
431 432 433
	unsigned long		flags;		/* error bits/gfp mask */
	spinlock_t		private_lock;	/* for use by the address_space */
	struct list_head	private_list;	/* ditto */
434
	void			*private_data;	/* ditto */
L
Linus Torvalds 已提交
435 436 437
} __attribute__((aligned(sizeof(long))));
	/*
	 * On most architectures that alignment is already the case; but
L
Lucas De Marchi 已提交
438
	 * must be enforced here for CRIS, to let the least significant bit
L
Linus Torvalds 已提交
439 440
	 * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON.
	 */
441
struct request_queue;
L
Linus Torvalds 已提交
442 443 444

struct block_device {
	dev_t			bd_dev;  /* not a kdev_t - it's a search key */
445
	int			bd_openers;
L
Linus Torvalds 已提交
446
	struct inode *		bd_inode;	/* will die */
447
	struct super_block *	bd_super;
448
	struct mutex		bd_mutex;	/* open/close mutex */
L
Linus Torvalds 已提交
449
	struct list_head	bd_inodes;
450
	void *			bd_claiming;
L
Linus Torvalds 已提交
451 452
	void *			bd_holder;
	int			bd_holders;
453
	bool			bd_write_holder;
454
#ifdef CONFIG_SYSFS
455
	struct list_head	bd_holder_disks;
456
#endif
L
Linus Torvalds 已提交
457 458 459 460 461 462 463
	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;
464
	struct request_queue *  bd_queue;
L
Linus Torvalds 已提交
465 466 467 468 469 470 471 472
	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;
473 474 475 476 477

	/* The counter of freeze processes */
	int			bd_fsfreeze_count;
	/* Mutex for freeze */
	struct mutex		bd_fsfreeze_mutex;
L
Linus Torvalds 已提交
478 479 480 481 482 483 484 485
};

/*
 * Radix-tree tags, for tagging dirty and writeback pages within the pagecache
 * radix trees
 */
#define PAGECACHE_TAG_DIRTY	0
#define PAGECACHE_TAG_WRITEBACK	1
486
#define PAGECACHE_TAG_TOWRITE	2
L
Linus Torvalds 已提交
487 488 489

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

490 491
static inline void i_mmap_lock_write(struct address_space *mapping)
{
492
	down_write(&mapping->i_mmap_rwsem);
493 494 495 496
}

static inline void i_mmap_unlock_write(struct address_space *mapping)
{
497
	up_write(&mapping->i_mmap_rwsem);
498 499
}

D
Davidlohr Bueso 已提交
500 501 502 503 504 505 506 507 508 509
static inline void i_mmap_lock_read(struct address_space *mapping)
{
	down_read(&mapping->i_mmap_rwsem);
}

static inline void i_mmap_unlock_read(struct address_space *mapping)
{
	up_read(&mapping->i_mmap_rwsem);
}

L
Linus Torvalds 已提交
510 511 512 513 514
/*
 * Might pages of this file be mapped into userspace?
 */
static inline int mapping_mapped(struct address_space *mapping)
{
515
	return	!RB_EMPTY_ROOT(&mapping->i_mmap);
L
Linus Torvalds 已提交
516 517 518 519 520 521 522
}

/*
 * 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.
523 524 525
 *
 * 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
526 527 528
 */
static inline int mapping_writably_mapped(struct address_space *mapping)
{
529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551
	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
552 553 554 555 556 557 558 559 560 561 562 563 564
}

/*
 * 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
565 566 567
struct posix_acl;
#define ACL_NOT_CACHED ((void *)(-1))

568 569 570 571 572 573 574 575 576
#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
577
struct inode {
578
	umode_t			i_mode;
579
	unsigned short		i_opflags;
580 581
	kuid_t			i_uid;
	kgid_t			i_gid;
582 583 584 585 586 587 588
	unsigned int		i_flags;

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

589 590
	const struct inode_operations	*i_op;
	struct super_block	*i_sb;
591
	struct address_space	*i_mapping;
592

593 594 595
#ifdef CONFIG_SECURITY
	void			*i_security;
#endif
596

597 598
	/* Stat data, not accessed from path walking */
	unsigned long		i_ino;
M
Miklos Szeredi 已提交
599 600 601 602 603 604 605 606 607 608 609
	/*
	 * 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;
	};
610
	dev_t			i_rdev;
611
	loff_t			i_size;
612 613 614
	struct timespec		i_atime;
	struct timespec		i_mtime;
	struct timespec		i_ctime;
615 616
	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
	unsigned short          i_bytes;
617
	unsigned int		i_blkbits;
618 619 620 621 622 623 624 625 626
	blkcnt_t		i_blocks;

#ifdef __NEED_I_SIZE_ORDERED
	seqcount_t		i_size_seqcount;
#endif

	/* Misc */
	unsigned long		i_state;
	struct mutex		i_mutex;
627

628
	unsigned long		dirtied_when;	/* jiffies of first dirtying */
629
	unsigned long		dirtied_time_when;
630

L
Linus Torvalds 已提交
631
	struct hlist_node	i_hash;
N
Nick Piggin 已提交
632 633
	struct list_head	i_wb_list;	/* backing dev IO list */
	struct list_head	i_lru;		/* inode LRU list */
L
Linus Torvalds 已提交
634
	struct list_head	i_sb_list;
N
Nick Piggin 已提交
635
	union {
A
Al Viro 已提交
636
		struct hlist_head	i_dentry;
N
Nick Piggin 已提交
637 638
		struct rcu_head		i_rcu;
	};
639
	u64			i_version;
640
	atomic_t		i_count;
C
Christoph Hellwig 已提交
641
	atomic_t		i_dio_count;
642
	atomic_t		i_writecount;
M
Mimi Zohar 已提交
643 644 645
#ifdef CONFIG_IMA
	atomic_t		i_readcount; /* struct files open RO */
#endif
646
	const struct file_operations	*i_fop;	/* former ->i_op->default_file_ops */
647
	struct file_lock_context	*i_flctx;
L
Linus Torvalds 已提交
648 649
	struct address_space	i_data;
	struct list_head	i_devices;
650 651
	union {
		struct pipe_inode_info	*i_pipe;
652
		struct block_device	*i_bdev;
653
		struct cdev		*i_cdev;
654
	};
L
Linus Torvalds 已提交
655 656 657

	__u32			i_generation;

658 659
#ifdef CONFIG_FSNOTIFY
	__u32			i_fsnotify_mask; /* all events this inode cares about */
660
	struct hlist_head	i_fsnotify_marks;
R
Robert Love 已提交
661 662
#endif

663
	void			*i_private; /* fs or device private pointer */
L
Linus Torvalds 已提交
664 665
};

A
Al Viro 已提交
666 667 668 669 670
static inline int inode_unhashed(struct inode *inode)
{
	return hlist_unhashed(&inode->i_hash);
}

I
Ingo Molnar 已提交
671 672 673 674 675 676
/*
 * inode->i_mutex nesting subclasses for the lock validator:
 *
 * 0: the object of the current VFS operation
 * 1: parent
 * 2: child/target
677 678
 * 3: xattr
 * 4: second non-directory
679 680 681
 * 5: second parent (when locking independent directories in rename)
 *
 * I_MUTEX_NONDIR2 is for certain operations (such as rename) which lock two
682
 * non-directories at once.
I
Ingo Molnar 已提交
683 684
 *
 * The locking order between these classes is
685
 * parent[2] -> child -> grandchild -> normal -> xattr -> second non-directory
I
Ingo Molnar 已提交
686 687 688 689 690 691
 */
enum inode_i_mutex_lock_class
{
	I_MUTEX_NORMAL,
	I_MUTEX_PARENT,
	I_MUTEX_CHILD,
I
Ingo Molnar 已提交
692
	I_MUTEX_XATTR,
693 694
	I_MUTEX_NONDIR2,
	I_MUTEX_PARENT2,
I
Ingo Molnar 已提交
695 696
};

697 698 699
void lock_two_nondirectories(struct inode *, struct inode*);
void unlock_two_nondirectories(struct inode *, struct inode*);

L
Linus Torvalds 已提交
700 701 702 703 704 705 706 707 708 709
/*
 * 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
710
static inline loff_t i_size_read(const struct inode *inode)
L
Linus Torvalds 已提交
711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732
{
#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
}

733 734 735 736 737
/*
 * 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
738 739 740
static inline void i_size_write(struct inode *inode, loff_t i_size)
{
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
741
	preempt_disable();
L
Linus Torvalds 已提交
742 743 744
	write_seqcount_begin(&inode->i_size_seqcount);
	inode->i_size = i_size;
	write_seqcount_end(&inode->i_size_seqcount);
745
	preempt_enable();
L
Linus Torvalds 已提交
746 747 748 749 750 751 752 753 754
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
	preempt_disable();
	inode->i_size = i_size;
	preempt_enable();
#else
	inode->i_size = i_size;
#endif
}

755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779
/* 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
780
static inline unsigned iminor(const struct inode *inode)
L
Linus Torvalds 已提交
781 782 783 784
{
	return MINOR(inode->i_rdev);
}

J
Jan Engelhardt 已提交
785
static inline unsigned imajor(const struct inode *inode)
L
Linus Torvalds 已提交
786 787 788 789 790 791 792 793
{
	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 */
794 795
	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 */
796
	kuid_t uid, euid;	/* uid/euid of process setting the owner */
L
Linus Torvalds 已提交
797 798 799 800 801 802 803
	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
804 805 806
	pgoff_t start;			/* where readahead started */
	unsigned int size;		/* # of readahead pages */
	unsigned int async_size;	/* do asynchronous readahead when
807
					   there are only # of pages ahead */
808

F
Fengguang Wu 已提交
809
	unsigned int ra_pages;		/* Maximum readahead window */
810
	unsigned int mmap_miss;		/* Cache miss stat for mmap accesses */
811
	loff_t prev_pos;		/* Cache last read() position */
L
Linus Torvalds 已提交
812 813
};

814 815 816 817 818
/*
 * Check if @index falls in the readahead windows.
 */
static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
{
819 820
	return (index >= ra->start &&
		index <  ra->start + ra->size);
821 822
}

L
Linus Torvalds 已提交
823
struct file {
E
Eric Dumazet 已提交
824
	union {
825
		struct llist_node	fu_llist;
E
Eric Dumazet 已提交
826 827
		struct rcu_head 	fu_rcuhead;
	} f_u;
828
	struct path		f_path;
829
	struct inode		*f_inode;	/* cached value */
830
	const struct file_operations	*f_op;
831 832

	/*
833
	 * Protects f_ep_links, f_flags.
834 835 836
	 * Must not be taken from IRQ context.
	 */
	spinlock_t		f_lock;
A
Al Viro 已提交
837
	atomic_long_t		f_count;
L
Linus Torvalds 已提交
838
	unsigned int 		f_flags;
839
	fmode_t			f_mode;
840
	struct mutex		f_pos_lock;
L
Linus Torvalds 已提交
841 842
	loff_t			f_pos;
	struct fown_struct	f_owner;
D
David Howells 已提交
843
	const struct cred	*f_cred;
L
Linus Torvalds 已提交
844 845
	struct file_ra_state	f_ra;

846
	u64			f_version;
847
#ifdef CONFIG_SECURITY
L
Linus Torvalds 已提交
848
	void			*f_security;
849
#endif
L
Linus Torvalds 已提交
850 851 852 853 854 855
	/* 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
856
	struct list_head	f_tfile_llink;
L
Linus Torvalds 已提交
857 858
#endif /* #ifdef CONFIG_EPOLL */
	struct address_space	*f_mapping;
A
Al Viro 已提交
859
} __attribute__((aligned(4)));	/* lest something weird decides that 2 is OK */
L
Linus Torvalds 已提交
860

861 862 863 864 865 866 867
struct file_handle {
	__u32 handle_bytes;
	int handle_type;
	/* file identifier */
	unsigned char f_handle[0];
};

A
Al Viro 已提交
868 869 870 871 872
static inline struct file *get_file(struct file *f)
{
	atomic_long_inc(&f->f_count);
	return f;
}
873
#define fput_atomic(x)	atomic_long_add_unless(&(x)->f_count, -1, 1)
A
Al Viro 已提交
874
#define file_count(x)	atomic_long_read(&(x)->f_count)
L
Linus Torvalds 已提交
875 876 877 878 879 880

#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
881
#define MAX_LFS_FILESIZE	(((loff_t)PAGE_CACHE_SIZE << (BITS_PER_LONG-1))-1) 
L
Linus Torvalds 已提交
882
#elif BITS_PER_LONG==64
883
#define MAX_LFS_FILESIZE 	((loff_t)0x7fffffffffffffffLL)
L
Linus Torvalds 已提交
884 885 886 887
#endif

#define FL_POSIX	1
#define FL_FLOCK	2
888
#define FL_DELEG	4	/* NFSv4 delegation */
L
Linus Torvalds 已提交
889
#define FL_ACCESS	8	/* not trying to lock, just looking */
890
#define FL_EXISTS	16	/* when unlocking, test for existence */
L
Linus Torvalds 已提交
891
#define FL_LEASE	32	/* lease held on this file */
892
#define FL_CLOSE	64	/* unlock on close */
L
Linus Torvalds 已提交
893
#define FL_SLEEP	128	/* A blocking lock */
894 895
#define FL_DOWNGRADE_PENDING	256 /* Lease is being downgraded */
#define FL_UNLOCK_PENDING	512 /* Lease is being broken */
896
#define FL_OFDLCK	1024	/* lock is "owned" by struct file */
C
Christoph Hellwig 已提交
897
#define FL_LAYOUT	2048	/* outstanding pNFS layout */
L
Linus Torvalds 已提交
898

899 900 901 902 903 904
/*
 * Special return value from posix_lock_file() and vfs_lock_file() for
 * asynchronous locking.
 */
#define FILE_LOCK_DEFERRED 1

905
/* legacy typedef, should eventually be removed */
906
typedef void *fl_owner_t;
L
Linus Torvalds 已提交
907

908 909
struct file_lock;

L
Linus Torvalds 已提交
910 911 912 913 914 915
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
916
	int (*lm_compare_owner)(struct file_lock *, struct file_lock *);
917
	unsigned long (*lm_owner_key)(struct file_lock *);
918 919
	void (*lm_get_owner)(struct file_lock *, struct file_lock *);
	void (*lm_put_owner)(struct file_lock *);
J
J. Bruce Fields 已提交
920
	void (*lm_notify)(struct file_lock *);	/* unblock callback */
921
	int (*lm_grant)(struct file_lock *, int);
J
Jeff Layton 已提交
922
	bool (*lm_break)(struct file_lock *);
923
	int (*lm_change)(struct file_lock *, int, struct list_head *);
924
	void (*lm_setup)(struct file_lock *, void **);
L
Linus Torvalds 已提交
925 926
};

927 928 929 930
struct lock_manager {
	struct list_head list;
};

931 932
struct net;
void locks_start_grace(struct net *, struct lock_manager *);
933
void locks_end_grace(struct lock_manager *);
934
int locks_in_grace(struct net *);
935

L
Linus Torvalds 已提交
936 937 938
/* that will die - we need it for nfs_lock_info */
#include <linux/nfs_fs_i.h>

939 940 941 942 943 944 945 946 947
/*
 * 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?
 *
948
 * The varous i_flctx lists are ordered by:
949
 *
950 951 952
 * 1) lock owner
 * 2) lock range start
 * 3) lock range end
953 954 955
 *
 * Obviously, the last two criteria only matter for POSIX locks.
 */
L
Linus Torvalds 已提交
956 957
struct file_lock {
	struct file_lock *fl_next;	/* singly linked list for this inode  */
958
	struct list_head fl_list;	/* link into file_lock_context */
959
	struct hlist_node fl_link;	/* node in global lists */
L
Linus Torvalds 已提交
960 961
	struct list_head fl_block;	/* circular list of blocked processes */
	fl_owner_t fl_owner;
962
	unsigned int fl_flags;
963
	unsigned char fl_type;
L
Linus Torvalds 已提交
964
	unsigned int fl_pid;
965
	int fl_link_cpu;		/* what cpu's list is this on? */
966
	struct pid *fl_nspid;
L
Linus Torvalds 已提交
967 968 969 970 971 972
	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 */
973 974 975
	/* for lease breaks: */
	unsigned long fl_break_time;
	unsigned long fl_downgrade_time;
L
Linus Torvalds 已提交
976

977
	const struct file_lock_operations *fl_ops;	/* Callbacks for filesystems */
978
	const struct lock_manager_operations *fl_lmops;	/* Callbacks for lockmanagers */
L
Linus Torvalds 已提交
979 980
	union {
		struct nfs_lock_info	nfs_fl;
981
		struct nfs4_lock_info	nfs4_fl;
D
David Howells 已提交
982 983 984 985
		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
986 987 988
	} fl_u;
};

989
struct file_lock_context {
990
	spinlock_t		flc_lock;
991
	struct list_head	flc_flock;
992
	struct list_head	flc_posix;
993
	struct list_head	flc_lease;
994 995
};

L
Linus Torvalds 已提交
996 997 998 999 1000 1001 1002 1003 1004
/* 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>

1005 1006 1007
extern void send_sigio(struct fown_struct *fown, int fd, int band);

#ifdef CONFIG_FILE_LOCKING
1008
extern int fcntl_getlk(struct file *, unsigned int, struct flock __user *);
1009 1010
extern int fcntl_setlk(unsigned int, struct file *, unsigned int,
			struct flock __user *);
L
Linus Torvalds 已提交
1011 1012

#if BITS_PER_LONG == 32
1013
extern int fcntl_getlk64(struct file *, unsigned int, struct flock64 __user *);
1014 1015
extern int fcntl_setlk64(unsigned int, struct file *, unsigned int,
			struct flock64 __user *);
L
Linus Torvalds 已提交
1016 1017 1018 1019 1020 1021
#endif

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

/* fs/locks.c */
1022
void locks_free_lock_context(struct file_lock_context *ctx);
1023
void locks_free_lock(struct file_lock *fl);
L
Linus Torvalds 已提交
1024
extern void locks_init_lock(struct file_lock *);
1025
extern struct file_lock * locks_alloc_lock(void);
L
Linus Torvalds 已提交
1026
extern void locks_copy_lock(struct file_lock *, struct file_lock *);
1027
extern void locks_copy_conflock(struct file_lock *, struct file_lock *);
L
Linus Torvalds 已提交
1028
extern void locks_remove_posix(struct file *, fl_owner_t);
1029
extern void locks_remove_file(struct file *);
1030
extern void locks_release_private(struct file_lock *);
1031
extern void posix_test_lock(struct file *, struct file_lock *);
1032
extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *);
L
Linus Torvalds 已提交
1033
extern int posix_lock_file_wait(struct file *, struct file_lock *);
1034
extern int posix_unblock_lock(struct file_lock *);
1035
extern int vfs_test_lock(struct file *, struct file_lock *);
1036
extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *);
M
Marc Eshel 已提交
1037
extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
L
Linus Torvalds 已提交
1038
extern int flock_lock_file_wait(struct file *filp, struct file_lock *fl);
J
J. Bruce Fields 已提交
1039
extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type);
L
Linus Torvalds 已提交
1040
extern void lease_get_mtime(struct inode *, struct timespec *time);
1041 1042
extern int generic_setlease(struct file *, long, struct file_lock **, void **priv);
extern int vfs_setlease(struct file *, long, struct file_lock **, void **);
1043
extern int lease_modify(struct file_lock *, int, struct list_head *);
1044
#else /* !CONFIG_FILE_LOCKING */
1045 1046
static inline int fcntl_getlk(struct file *file, unsigned int cmd,
			      struct flock __user *user)
1047 1048 1049 1050 1051 1052 1053 1054 1055 1056
{
	return -EINVAL;
}

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

1057
#if BITS_PER_LONG == 32
1058 1059
static inline int fcntl_getlk64(struct file *file, unsigned int cmd,
				struct flock64 __user *user)
1060 1061 1062 1063 1064 1065 1066 1067 1068
{
	return -EINVAL;
}

static inline int fcntl_setlk64(unsigned int fd, struct file *file,
				unsigned int cmd, struct flock64 __user *user)
{
	return -EACCES;
}
1069
#endif
1070 1071
static inline int fcntl_setlease(unsigned int fd, struct file *filp, long arg)
{
1072
	return -EINVAL;
1073 1074 1075 1076
}

static inline int fcntl_getlease(struct file *filp)
{
1077
	return F_UNLCK;
1078 1079
}

1080 1081 1082 1083 1084
static inline void
locks_free_lock_context(struct file_lock_context *ctx)
{
}

1085 1086 1087 1088 1089
static inline void locks_init_lock(struct file_lock *fl)
{
	return;
}

1090
static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl)
1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104
{
	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;
}

1105
static inline void locks_remove_file(struct file *filp)
1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125
{
	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;
}

1126
static inline int posix_unblock_lock(struct file_lock *waiter)
1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152
{
	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
1153
static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
1154 1155 1156 1157 1158 1159 1160 1161 1162 1163
{
	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,
1164
				    struct file_lock **flp, void **priv)
1165 1166 1167 1168 1169
{
	return -EINVAL;
}

static inline int vfs_setlease(struct file *filp, long arg,
1170
			       struct file_lock **lease, void **priv)
1171 1172 1173 1174
{
	return -EINVAL;
}

1175
static inline int lease_modify(struct file_lock *fl, int arg,
1176
			       struct list_head *dispose)
1177 1178 1179
{
	return -EINVAL;
}
1180 1181
#endif /* !CONFIG_FILE_LOCKING */

L
Linus Torvalds 已提交
1182 1183

struct fasync_struct {
1184 1185 1186 1187 1188 1189
	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
1190 1191 1192 1193 1194 1195
};

#define FASYNC_MAGIC 0x4601

/* SMP safe fasync helpers: */
extern int fasync_helper(int, struct file *, int, struct fasync_struct **);
1196 1197 1198 1199 1200
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
1201 1202 1203
/* can be called from interrupts */
extern void kill_fasync(struct fasync_struct **, int, int);

1204 1205
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
1206
extern void f_delown(struct file *filp);
1207
extern pid_t f_getown(struct file *filp);
L
Linus Torvalds 已提交
1208 1209
extern int send_sigurg(struct fown_struct *fown);

1210 1211
struct mm_struct;

L
Linus Torvalds 已提交
1212 1213 1214 1215 1216 1217 1218
/*
 *	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 */
1219 1220
#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
1221 1222


1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247
/* 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
1248 1249 1250
struct super_block {
	struct list_head	s_list;		/* Keep this first */
	dev_t			s_dev;		/* search index; _not_ kdev_t */
1251 1252
	unsigned char		s_blocksize_bits;
	unsigned long		s_blocksize;
1253
	loff_t			s_maxbytes;	/* Max file size */
L
Linus Torvalds 已提交
1254
	struct file_system_type	*s_type;
1255
	const struct super_operations	*s_op;
1256
	const struct dquot_operations	*dq_op;
1257
	const struct quotactl_ops	*s_qcop;
1258
	const struct export_operations *s_export_op;
L
Linus Torvalds 已提交
1259 1260 1261 1262 1263 1264
	unsigned long		s_flags;
	unsigned long		s_magic;
	struct dentry		*s_root;
	struct rw_semaphore	s_umount;
	int			s_count;
	atomic_t		s_active;
1265
#ifdef CONFIG_SECURITY
L
Linus Torvalds 已提交
1266
	void                    *s_security;
1267
#endif
1268
	const struct xattr_handler **s_xattr;
L
Linus Torvalds 已提交
1269 1270

	struct list_head	s_inodes;	/* all inodes */
1271
	struct hlist_bl_head	s_anon;		/* anonymous dentries for (nfs) exporting */
1272
	struct list_head	s_mounts;	/* list of mounts; _not_ for fs use */
L
Linus Torvalds 已提交
1273
	struct block_device	*s_bdev;
J
Jens Axboe 已提交
1274
	struct backing_dev_info *s_bdi;
1275
	struct mtd_info		*s_mtd;
A
Al Viro 已提交
1276
	struct hlist_node	s_instances;
1277
	unsigned int		s_quota_types;	/* Bitmask of supported quota types */
L
Linus Torvalds 已提交
1278 1279
	struct quota_info	s_dquot;	/* Diskquota specific options */

1280
	struct sb_writers	s_writers;
L
Linus Torvalds 已提交
1281 1282

	char s_id[32];				/* Informational name */
1283
	u8 s_uuid[16];				/* UUID */
L
Linus Torvalds 已提交
1284 1285

	void 			*s_fs_info;	/* Filesystem private info */
1286
	unsigned int		s_max_links;
1287
	fmode_t			s_mode;
L
Linus Torvalds 已提交
1288

1289 1290 1291 1292
	/* Granularity of c/m/atime in ns.
	   Cannot be worse than a second */
	u32		   s_time_gran;

L
Linus Torvalds 已提交
1293 1294 1295 1296
	/*
	 * The next field is for VFS *only*. No filesystems have any business
	 * even looking at it. You had been warned.
	 */
1297
	struct mutex s_vfs_rename_mutex;	/* Kludge */
L
Linus Torvalds 已提交
1298

M
Miklos Szeredi 已提交
1299 1300 1301 1302 1303
	/*
	 * Filesystem subtype.  If non-empty the filesystem type field
	 * in /proc/mounts will be "type.subtype"
	 */
	char *s_subtype;
1304 1305 1306 1307 1308

	/*
	 * Saved mount options for lazy filesystems using
	 * generic_show_options()
	 */
A
Arnd Bergmann 已提交
1309
	char __rcu *s_options;
A
Al Viro 已提交
1310
	const struct dentry_operations *s_d_op; /* default d_op for dentries */
1311 1312 1313 1314 1315

	/*
	 * Saved pool identifier for cleancache (-1 means none)
	 */
	int cleancache_poolid;
1316 1317

	struct shrinker s_shrink;	/* per-sb shrinker handle */
1318

M
Miklos Szeredi 已提交
1319 1320 1321
	/* Number of inodes with nlink == 0 but still referenced */
	atomic_long_t s_remove_count;

1322 1323
	/* Being remounted read-only */
	int s_readonly_remount;
1324 1325 1326

	/* AIO completions deferred from interrupt context */
	struct workqueue_struct *s_dio_done_wq;
A
Al Viro 已提交
1327
	struct hlist_head s_pins;
1328 1329 1330 1331 1332 1333 1334

	/*
	 * 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
1335
	struct rcu_head		rcu;
1336 1337 1338 1339 1340

	/*
	 * Indicates how deep in a filesystem stack this SB is
	 */
	int s_stack_depth;
L
Linus Torvalds 已提交
1341 1342 1343 1344 1345 1346 1347 1348
};

extern struct timespec current_fs_time(struct super_block *sb);

/*
 * Snapshotting support.
 */

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 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457
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
1458 1459


1460
extern bool inode_owner_or_capable(const struct inode *inode);
1461

L
Linus Torvalds 已提交
1462 1463 1464
/*
 * VFS helper functions..
 */
A
Al Viro 已提交
1465
extern int vfs_create(struct inode *, struct dentry *, umode_t, bool);
1466
extern int vfs_mkdir(struct inode *, struct dentry *, umode_t);
A
Al Viro 已提交
1467
extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
1468
extern int vfs_symlink(struct inode *, struct dentry *, const char *);
J
J. Bruce Fields 已提交
1469
extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct inode **);
L
Linus Torvalds 已提交
1470
extern int vfs_rmdir(struct inode *, struct dentry *);
1471
extern int vfs_unlink(struct inode *, struct dentry *, struct inode **);
M
Miklos Szeredi 已提交
1472
extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int);
M
Miklos Szeredi 已提交
1473
extern int vfs_whiteout(struct inode *, struct dentry *);
L
Linus Torvalds 已提交
1474 1475 1476 1477 1478 1479

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

1480 1481 1482
/*
 * VFS file helper functions.
 */
1483
extern void inode_init_owner(struct inode *inode, const struct inode *dir,
A
Al Viro 已提交
1484
			umode_t mode);
M
Mark Fasheh 已提交
1485 1486 1487 1488 1489 1490 1491
/*
 * 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 */
1492 1493
	struct fiemap_extent __user *fi_extents_start; /* Start of
							fiemap_extent array */
M
Mark Fasheh 已提交
1494 1495 1496 1497 1498
};
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
1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520
/*
 * 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.
 */
1521 1522 1523 1524
struct dir_context;
typedef int (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64,
			 unsigned);

1525
struct dir_context {
A
Al Viro 已提交
1526
	const filldir_t actor;
1527
	loff_t pos;
1528
};
1529

1530
struct block_device_operations;
L
Linus Torvalds 已提交
1531 1532 1533 1534 1535 1536 1537

/* 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

1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557
/*
 * These flags let !MMU mmap() govern direct device mapping vs immediate
 * copying more easily for MAP_PRIVATE, especially for ROM filesystems.
 *
 * NOMMU_MAP_COPY:	Copy can be mapped (MAP_PRIVATE)
 * NOMMU_MAP_DIRECT:	Can be mapped directly (MAP_SHARED)
 * NOMMU_MAP_READ:	Can be mapped for reading
 * NOMMU_MAP_WRITE:	Can be mapped for writing
 * NOMMU_MAP_EXEC:	Can be mapped for execution
 */
#define NOMMU_MAP_COPY		0x00000001
#define NOMMU_MAP_DIRECT	0x00000008
#define NOMMU_MAP_READ		VM_MAYREAD
#define NOMMU_MAP_WRITE		VM_MAYWRITE
#define NOMMU_MAP_EXEC		VM_MAYEXEC

#define NOMMU_VMFLAGS \
	(NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC)


1558 1559
struct iov_iter;

L
Linus Torvalds 已提交
1560 1561 1562 1563 1564
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 *);
1565 1566
	ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
1567
	int (*iterate) (struct file *, struct dir_context *);
L
Linus Torvalds 已提交
1568 1569 1570 1571
	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 *);
1572
	void (*mremap)(struct file *, struct vm_area_struct *);
L
Linus Torvalds 已提交
1573
	int (*open) (struct inode *, struct file *);
1574
	int (*flush) (struct file *, fl_owner_t id);
L
Linus Torvalds 已提交
1575
	int (*release) (struct inode *, struct file *);
1576
	int (*fsync) (struct file *, loff_t, loff_t, int datasync);
L
Linus Torvalds 已提交
1577 1578 1579 1580 1581 1582 1583
	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 *);
1584 1585
	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);
1586
	int (*setlease)(struct file *, long, struct file_lock **, void **);
1587 1588
	long (*fallocate)(struct file *file, int mode, loff_t offset,
			  loff_t len);
1589
	void (*show_fdinfo)(struct seq_file *m, struct file *f);
1590 1591 1592
#ifndef CONFIG_MMU
	unsigned (*mmap_capabilities)(struct file *);
#endif
L
Linus Torvalds 已提交
1593 1594 1595
};

struct inode_operations {
A
Al Viro 已提交
1596
	struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
1597
	void * (*follow_link) (struct dentry *, struct nameidata *);
1598
	int (*permission) (struct inode *, int);
1599
	struct posix_acl * (*get_acl)(struct inode *, int);
1600 1601 1602 1603

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

A
Al Viro 已提交
1604
	int (*create) (struct inode *,struct dentry *, umode_t, bool);
L
Linus Torvalds 已提交
1605 1606 1607
	int (*link) (struct dentry *,struct inode *,struct dentry *);
	int (*unlink) (struct inode *,struct dentry *);
	int (*symlink) (struct inode *,struct dentry *,const char *);
1608
	int (*mkdir) (struct inode *,struct dentry *,umode_t);
L
Linus Torvalds 已提交
1609
	int (*rmdir) (struct inode *,struct dentry *);
A
Al Viro 已提交
1610
	int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
L
Linus Torvalds 已提交
1611 1612
	int (*rename) (struct inode *, struct dentry *,
			struct inode *, struct dentry *);
M
Miklos Szeredi 已提交
1613 1614
	int (*rename2) (struct inode *, struct dentry *,
			struct inode *, struct dentry *, unsigned int);
L
Linus Torvalds 已提交
1615 1616 1617 1618 1619 1620
	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
1621 1622
	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
		      u64 len);
1623
	int (*update_time)(struct inode *, struct timespec *, int);
A
Al Viro 已提交
1624
	int (*atomic_open)(struct inode *, struct dentry *,
A
Al Viro 已提交
1625
			   struct file *, unsigned open_flag,
A
Al Viro 已提交
1626
			   umode_t create_mode, int *opened);
1627
	int (*tmpfile) (struct inode *, struct dentry *, umode_t);
1628
	int (*set_acl)(struct inode *, struct posix_acl *, int);
M
Miklos Szeredi 已提交
1629 1630 1631

	/* WARNING: probably going away soon, do not use! */
	int (*dentry_open)(struct dentry *, struct file *, const struct cred *);
1632
} ____cacheline_aligned;
L
Linus Torvalds 已提交
1633

B
Badari Pulavarty 已提交
1634
ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
C
Christopher Yeoh 已提交
1635 1636
			      unsigned long nr_segs, unsigned long fast_segs,
			      struct iovec *fast_pointer,
1637
			      struct iovec **ret_pointer);
B
Badari Pulavarty 已提交
1638

D
Dmitry Kasatkin 已提交
1639
extern ssize_t __vfs_read(struct file *, char __user *, size_t, loff_t *);
A
Al Viro 已提交
1640
extern ssize_t __vfs_write(struct file *, const char __user *, size_t, loff_t *);
L
Linus Torvalds 已提交
1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651
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 *);

1652
   	void (*dirty_inode) (struct inode *, int flags);
1653
	int (*write_inode) (struct inode *, struct writeback_control *wbc);
1654
	int (*drop_inode) (struct inode *);
A
Al Viro 已提交
1655
	void (*evict_inode) (struct inode *);
L
Linus Torvalds 已提交
1656 1657
	void (*put_super) (struct super_block *);
	int (*sync_fs)(struct super_block *sb, int wait);
1658
	int (*freeze_super) (struct super_block *);
1659
	int (*freeze_fs) (struct super_block *);
1660
	int (*thaw_super) (struct super_block *);
1661
	int (*unfreeze_fs) (struct super_block *);
1662
	int (*statfs) (struct dentry *, struct kstatfs *);
L
Linus Torvalds 已提交
1663
	int (*remount_fs) (struct super_block *, int *, char *);
1664
	void (*umount_begin) (struct super_block *);
L
Linus Torvalds 已提交
1665

1666
	int (*show_options)(struct seq_file *, struct dentry *);
1667
	int (*show_devname)(struct seq_file *, struct dentry *);
1668
	int (*show_path)(struct seq_file *, struct dentry *);
1669
	int (*show_stats)(struct seq_file *, struct dentry *);
1670
#ifdef CONFIG_QUOTA
L
Linus Torvalds 已提交
1671 1672
	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);
1673
	struct dquot **(*get_dquots)(struct inode *);
1674
#endif
1675
	int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
1676 1677 1678 1679
	long (*nr_cached_objects)(struct super_block *,
				  struct shrink_control *);
	long (*free_cached_objects)(struct super_block *,
				    struct shrink_control *);
L
Linus Torvalds 已提交
1680 1681
};

D
David Howells 已提交
1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697
/*
 * 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 */
1698
#ifdef CONFIG_FS_DAX
1699 1700 1701 1702
#define S_DAX		8192	/* Direct Access, avoiding the page cache */
#else
#define S_DAX		0	/* Make all the DAX code disappear */
#endif
D
David Howells 已提交
1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739

/*
 * 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)
1740
#define IS_DAX(inode)		((inode)->i_flags & S_DAX)
D
David Howells 已提交
1741

M
Miklos Szeredi 已提交
1742 1743 1744
#define IS_WHITEOUT(inode)	(S_ISCHR(inode->i_mode) && \
				 (inode)->i_rdev == WHITEOUT_DEV)

J
Joern Engel 已提交
1745
/*
1746
 * Inode state bits.  Protected by inode->i_lock
J
Joern Engel 已提交
1747 1748 1749 1750 1751 1752 1753 1754
 *
 * 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
1755
 * Two bits are used for locking and completion notification, I_NEW and I_SYNC.
J
Joern Engel 已提交
1756
 *
J
Joern Engel 已提交
1757 1758
 * I_DIRTY_SYNC		Inode is dirty, but doesn't have to be written on
 *			fdatasync().  i_atime is the usual cause.
1759 1760 1761 1762
 * 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
1763
 * I_DIRTY_PAGES	Inode has dirty pages.  Inode itself may be clean.
C
Christoph Hellwig 已提交
1764 1765 1766 1767 1768 1769 1770 1771
 * 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
1772 1773 1774 1775 1776 1777
 * 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.
1778 1779
 * 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
1780 1781 1782 1783 1784
 *
 *			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
1785
 *			if appropriate.  I_NEW is used for waiting.
J
Joern Engel 已提交
1786
 *
1787 1788 1789 1790
 * 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
1791
 *
C
Christoph Hellwig 已提交
1792 1793 1794 1795
 * 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
1796 1797
 * Q: What is the difference between I_WILL_FREE and I_FREEING?
 */
1798 1799 1800
#define I_DIRTY_SYNC		(1 << 0)
#define I_DIRTY_DATASYNC	(1 << 1)
#define I_DIRTY_PAGES		(1 << 2)
C
Christoph Hellwig 已提交
1801 1802
#define __I_NEW			3
#define I_NEW			(1 << __I_NEW)
1803 1804 1805
#define I_WILL_FREE		(1 << 4)
#define I_FREEING		(1 << 5)
#define I_CLEAR			(1 << 6)
C
Christoph Hellwig 已提交
1806
#define __I_SYNC		7
J
Joern Engel 已提交
1807
#define I_SYNC			(1 << __I_SYNC)
1808
#define I_REFERENCED		(1 << 8)
C
Christoph Hellwig 已提交
1809 1810
#define __I_DIO_WAKEUP		9
#define I_DIO_WAKEUP		(1 << I_DIO_WAKEUP)
1811
#define I_LINKABLE		(1 << 10)
1812 1813 1814
#define I_DIRTY_TIME		(1 << 11)
#define __I_DIRTY_TIME_EXPIRED	12
#define I_DIRTY_TIME_EXPIRED	(1 << __I_DIRTY_TIME_EXPIRED)
L
Linus Torvalds 已提交
1815 1816

#define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES)
1817
#define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME)
L
Linus Torvalds 已提交
1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829

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
1830 1831 1832 1833
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);
1834 1835 1836 1837

static inline void inode_inc_link_count(struct inode *inode)
{
	inc_nlink(inode);
1838 1839 1840
	mark_inode_dirty(inode);
}

1841 1842 1843
static inline void inode_dec_link_count(struct inode *inode)
{
	drop_nlink(inode);
1844 1845 1846
	mark_inode_dirty(inode);
}

1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861
/**
 * 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);
}

1862 1863 1864 1865 1866 1867 1868
enum file_time_flags {
	S_ATIME = 1,
	S_MTIME = 2,
	S_CTIME = 4,
	S_VERSION = 8,
};

A
Al Viro 已提交
1869
extern void touch_atime(const struct path *);
L
Linus Torvalds 已提交
1870 1871 1872
static inline void file_accessed(struct file *file)
{
	if (!(file->f_flags & O_NOATIME))
A
Al Viro 已提交
1873
		touch_atime(&file->f_path);
L
Linus Torvalds 已提交
1874 1875 1876
}

int sync_inode(struct inode *inode, struct writeback_control *wbc);
C
Christoph Hellwig 已提交
1877
int sync_inode_metadata(struct inode *inode, int wait);
L
Linus Torvalds 已提交
1878 1879 1880 1881

struct file_system_type {
	const char *name;
	int fs_flags;
D
David Howells 已提交
1882 1883 1884
#define FS_REQUIRES_DEV		1 
#define FS_BINARY_MOUNTDATA	2
#define FS_HAS_SUBTYPE		4
1885 1886
#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
1887
#define FS_RENAME_DOES_D_MOVE	32768	/* FS will handle d_move() during rename() internally. */
A
Al Viro 已提交
1888 1889
	struct dentry *(*mount) (struct file_system_type *, int,
		       const char *, void *);
L
Linus Torvalds 已提交
1890 1891 1892
	void (*kill_sb) (struct super_block *);
	struct module *owner;
	struct file_system_type * next;
A
Al Viro 已提交
1893
	struct hlist_head fs_supers;
1894

I
Ingo Molnar 已提交
1895
	struct lock_class_key s_lock_key;
1896
	struct lock_class_key s_umount_key;
1897
	struct lock_class_key s_vfs_rename_key;
1898
	struct lock_class_key s_writers_key[SB_FREEZE_LEVELS];
1899 1900 1901

	struct lock_class_key i_lock_key;
	struct lock_class_key i_mutex_key;
1902
	struct lock_class_key i_mutex_dir_key;
L
Linus Torvalds 已提交
1903 1904
};

1905 1906
#define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME)

A
Al Viro 已提交
1907 1908
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
1909 1910 1911
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
1912 1913 1914
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
1915 1916 1917
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
1918
extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path);
L
Linus Torvalds 已提交
1919 1920 1921 1922 1923
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
1924
void deactivate_locked_super(struct super_block *sb);
L
Linus Torvalds 已提交
1925
int set_anon_super(struct super_block *s, void *data);
1926 1927
int get_anon_bdev(dev_t *);
void free_anon_bdev(dev_t);
L
Linus Torvalds 已提交
1928 1929 1930
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
1931
			int flags, void *data);
A
Al Viro 已提交
1932
extern struct dentry *mount_pseudo(struct file_system_type *, char *,
1933 1934 1935
	const struct super_operations *ops,
	const struct dentry_operations *dops,
	unsigned long);
L
Linus Torvalds 已提交
1936 1937 1938 1939 1940 1941

/* 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)
1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952
/*
 * 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
1953 1954 1955

extern int register_filesystem(struct file_system_type *);
extern int unregister_filesystem(struct file_system_type *);
1956 1957
extern struct vfsmount *kern_mount_data(struct file_system_type *, void *data);
#define kern_mount(type) kern_mount_data(type, NULL)
1958
extern void kern_unmount(struct vfsmount *mnt);
L
Linus Torvalds 已提交
1959 1960
extern int may_umount_tree(struct vfsmount *);
extern int may_umount(struct vfsmount *);
1961 1962
extern long do_mount(const char *, const char __user *,
		     const char *, unsigned long, void *);
A
Al Viro 已提交
1963
extern struct vfsmount *collect_mounts(struct path *);
1964
extern void drop_collected_mounts(struct vfsmount *);
A
Al Viro 已提交
1965 1966
extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *,
			  struct vfsmount *);
1967
extern int vfs_statfs(struct path *, struct kstatfs *);
A
Al Viro 已提交
1968 1969
extern int user_statfs(const char __user *, struct kstatfs *);
extern int fd_statfs(int, struct kstatfs *);
A
Al Viro 已提交
1970
extern int vfs_ustat(dev_t, struct kstatfs *);
1971 1972
extern int freeze_super(struct super_block *super);
extern int thaw_super(struct super_block *super);
1973
extern bool our_mnt(struct vfsmount *mnt);
1974
extern bool fs_fully_visible(struct file_system_type *);
L
Linus Torvalds 已提交
1975

A
Al Viro 已提交
1976 1977
extern int current_umask(void);

1978 1979
extern void ihold(struct inode * inode);
extern void iput(struct inode *);
1980
extern int generic_update_time(struct inode *, struct timespec *, int);
1981

A
Al Viro 已提交
1982
static inline struct inode *file_inode(const struct file *f)
1983 1984 1985 1986
{
	return f->f_inode;
}

M
Miklos Szeredi 已提交
1987
/* /sys/fs */
1988
extern struct kobject *fs_kobj;
M
Miklos Szeredi 已提交
1989

1990
#define MAX_RW_COUNT (INT_MAX & PAGE_CACHE_MASK)
1991

L
Linus Torvalds 已提交
1992 1993 1994
#define FLOCK_VERIFY_READ  1
#define FLOCK_VERIFY_WRITE 2

1995
#ifdef CONFIG_FILE_LOCKING
1996
extern int locks_mandatory_locked(struct file *);
L
Linus Torvalds 已提交
1997 1998 1999 2000 2001 2002
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.
 */
2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017

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
2018

2019
static inline int locks_verify_locked(struct file *file)
L
Linus Torvalds 已提交
2020
{
2021 2022
	if (mandatory_lock(file_inode(file)))
		return locks_mandatory_locked(file);
L
Linus Torvalds 已提交
2023 2024 2025 2026 2027 2028 2029
	return 0;
}

static inline int locks_verify_truncate(struct inode *inode,
				    struct file *filp,
				    loff_t size)
{
2030
	if (inode->i_flctx && mandatory_lock(inode))
L
Linus Torvalds 已提交
2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041
		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)
{
2042 2043
	/*
	 * Since this check is lockless, we must ensure that any refcounts
2044 2045 2046
	 * taken are done before checking i_flctx->flc_lease. Otherwise, we
	 * could end up racing with tasks trying to set a new lease on this
	 * file.
2047 2048
	 */
	smp_mb();
2049
	if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
J
J. Bruce Fields 已提交
2050
		return __break_lease(inode, mode, FL_LEASE);
L
Linus Torvalds 已提交
2051 2052
	return 0;
}
J
J. Bruce Fields 已提交
2053 2054 2055

static inline int break_deleg(struct inode *inode, unsigned int mode)
{
2056 2057
	/*
	 * Since this check is lockless, we must ensure that any refcounts
2058 2059 2060
	 * taken are done before checking i_flctx->flc_lease. Otherwise, we
	 * could end up racing with tasks trying to set a new lease on this
	 * file.
2061 2062
	 */
	smp_mb();
2063
	if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
J
J. Bruce Fields 已提交
2064
		return __break_lease(inode, mode, FL_DELEG);
L
Linus Torvalds 已提交
2065 2066
	return 0;
}
J
J. Bruce Fields 已提交
2067

2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089
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;
}

C
Christoph Hellwig 已提交
2090 2091 2092 2093 2094 2095 2096 2097 2098 2099
static inline int break_layout(struct inode *inode, bool wait)
{
	smp_mb();
	if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
		return __break_lease(inode,
				wait ? O_WRONLY : O_WRONLY | O_NONBLOCK,
				FL_LAYOUT);
	return 0;
}

2100
#else /* !CONFIG_FILE_LOCKING */
2101
static inline int locks_mandatory_locked(struct file *file)
2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122
{
	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;
}

2123
static inline int locks_verify_locked(struct file *file)
2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138
{
	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
2139 2140 2141 2142
static inline int break_deleg(struct inode *inode, unsigned int mode)
{
	return 0;
}
2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154

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;
}

C
Christoph Hellwig 已提交
2155 2156 2157 2158 2159
static inline int break_layout(struct inode *inode, bool wait)
{
	return 0;
}

2160
#endif /* CONFIG_FILE_LOCKING */
L
Linus Torvalds 已提交
2161 2162

/* fs/open.c */
2163
struct audit_names;
2164
struct filename {
2165 2166 2167
	const char		*name;	/* pointer to actual string */
	const __user char	*uptr;	/* original userland pointer */
	struct audit_names	*aname;
2168
	int			refcnt;
A
Al Viro 已提交
2169
	const char		iname[];
2170
};
L
Linus Torvalds 已提交
2171

2172
extern long vfs_truncate(struct path *, loff_t);
2173 2174
extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs,
		       struct file *filp);
2175
extern int vfs_fallocate(struct file *file, int mode, loff_t offset,
2176
			loff_t len);
J
Jason Uhlenkott 已提交
2177
extern long do_sys_open(int dfd, const char __user *filename, int flags,
2178
			umode_t mode);
2179
extern struct file *file_open_name(struct filename *, int, umode_t);
2180
extern struct file *filp_open(const char *, int, umode_t);
A
Al Viro 已提交
2181 2182
extern struct file *file_open_root(struct dentry *, struct vfsmount *,
				   const char *, int);
M
Miklos Szeredi 已提交
2183
extern int vfs_open(const struct path *, struct file *, const struct cred *);
2184
extern struct file * dentry_open(const struct path *, int, const struct cred *);
L
Linus Torvalds 已提交
2185
extern int filp_close(struct file *, fl_owner_t id);
2186

2187
extern struct filename *getname_flags(const char __user *, int, int *);
2188
extern struct filename *getname(const char __user *);
2189
extern struct filename *getname_kernel(const char *);
2190
extern void putname(struct filename *name);
2191

2192 2193 2194 2195
enum {
	FILE_CREATED = 1,
	FILE_OPENED = 2
};
A
Al Viro 已提交
2196 2197 2198
extern int finish_open(struct file *file, struct dentry *dentry,
			int (*open)(struct inode *, struct file *),
			int *opened);
A
Al Viro 已提交
2199
extern int finish_no_open(struct file *file, struct dentry *dentry);
L
Linus Torvalds 已提交
2200

2201 2202 2203 2204
/* fs/ioctl.c */

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

L
Linus Torvalds 已提交
2205 2206 2207 2208
/* fs/dcache.c */
extern void __init vfs_caches_init_early(void);
extern void __init vfs_caches_init(unsigned long);

2209 2210
extern struct kmem_cache *names_cachep;

2211
#define __getname()		kmem_cache_alloc(names_cachep, GFP_KERNEL)
V
Vegard Nossum 已提交
2212
#define __putname(name)		kmem_cache_free(names_cachep, (void *)(name))
L
Linus Torvalds 已提交
2213

2214
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2215
extern int register_blkdev(unsigned int, const char *);
A
Akinobu Mita 已提交
2216
extern void unregister_blkdev(unsigned int, const char *);
L
Linus Torvalds 已提交
2217
extern struct block_device *bdget(dev_t);
2218
extern struct block_device *bdgrab(struct block_device *bdev);
L
Linus Torvalds 已提交
2219 2220 2221
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
2222
extern void invalidate_bdev(struct block_device *);
2223
extern void iterate_bdevs(void (*)(struct block_device *, void *), void *);
N
Nick Piggin 已提交
2224
extern int sync_blockdev(struct block_device *bdev);
A
Al Viro 已提交
2225
extern void kill_bdev(struct block_device *);
N
Nick Piggin 已提交
2226
extern struct super_block *freeze_bdev(struct block_device *);
2227
extern void emergency_thaw_all(void);
N
Nick Piggin 已提交
2228 2229
extern int thaw_bdev(struct block_device *bdev, struct super_block *sb);
extern int fsync_bdev(struct block_device *);
2230
extern int sb_is_blkdev_sb(struct super_block *sb);
2231 2232
#else
static inline void bd_forget(struct inode *inode) {}
2233
static inline int sync_blockdev(struct block_device *bdev) { return 0; }
A
Al Viro 已提交
2234
static inline void kill_bdev(struct block_device *bdev) {}
2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245
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;
}
2246 2247 2248 2249

static inline void iterate_bdevs(void (*f)(struct block_device *, void *), void *arg)
{
}
2250 2251 2252 2253 2254

static inline int sb_is_blkdev_sb(struct super_block *sb)
{
	return 0;
}
2255
#endif
2256
extern int sync_filesystem(struct super_block *);
2257
extern const struct file_operations def_blk_fops;
2258
extern const struct file_operations def_chr_fops;
2259
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2260
extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long);
2261
extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long);
L
Linus Torvalds 已提交
2262
extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long);
2263
extern int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder);
2264 2265 2266 2267
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
2268
extern void blkdev_put(struct block_device *bdev, fmode_t mode);
2269
#ifdef CONFIG_SYSFS
2270
extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk);
2271 2272
extern void bd_unlink_disk_holder(struct block_device *bdev,
				  struct gendisk *disk);
2273
#else
2274 2275 2276 2277 2278
static inline int bd_link_disk_holder(struct block_device *bdev,
				      struct gendisk *disk)
{
	return 0;
}
2279 2280 2281 2282
static inline void bd_unlink_disk_holder(struct block_device *bdev,
					 struct gendisk *disk)
{
}
2283
#endif
2284
#endif
L
Linus Torvalds 已提交
2285 2286

/* fs/char_dev.c */
2287
#define CHRDEV_MAJOR_HASH_SIZE	255
L
Linus Torvalds 已提交
2288 2289
extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *);
extern int register_chrdev_region(dev_t, unsigned, const char *);
2290 2291 2292 2293 2294
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
2295
extern void unregister_chrdev_region(dev_t, unsigned);
2296
extern void chrdev_show(struct seq_file *,off_t);
L
Linus Torvalds 已提交
2297

2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308
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
2309 2310
/* fs/block_dev.c */
#define BDEVNAME_SIZE	32	/* Largest string for a blockdev identifier */
2311
#define BDEVT_SIZE	10	/* Largest string for MAJ:MIN for blkdev */
2312 2313 2314

#ifdef CONFIG_BLOCK
#define BLKDEV_MAJOR_HASH_SIZE	255
L
Linus Torvalds 已提交
2315 2316 2317
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 *);
2318
extern void blkdev_show(struct seq_file *,off_t);
2319

2320 2321 2322
#else
#define BLKDEV_MAJOR_HASH_SIZE	0
#endif
L
Linus Torvalds 已提交
2323 2324 2325 2326 2327 2328 2329

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 *);

2330
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2331 2332 2333 2334 2335 2336 2337 2338 2339 2340
/*
 * 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)

2341 2342
extern void check_disk_size_change(struct gendisk *disk,
				   struct block_device *bdev);
2343
extern int revalidate_disk(struct gendisk *);
L
Linus Torvalds 已提交
2344
extern int check_disk_change(struct block_device *);
2345
extern int __invalidate_device(struct block_device *, bool);
L
Linus Torvalds 已提交
2346
extern int invalidate_partition(struct gendisk *, int);
2347
#endif
L
Linus Torvalds 已提交
2348 2349
unsigned long invalidate_mapping_pages(struct address_space *mapping,
					pgoff_t start, pgoff_t end);
2350

L
Linus Torvalds 已提交
2351 2352 2353 2354
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))
2355
		invalidate_mapping_pages(inode->i_mapping, 0, -1);
L
Linus Torvalds 已提交
2356 2357 2358 2359 2360 2361 2362 2363
}
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 *);
2364 2365
extern int filemap_fdatawait_range(struct address_space *, loff_t lstart,
				   loff_t lend);
L
Linus Torvalds 已提交
2366 2367 2368
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);
2369 2370
extern int __filemap_fdatawrite_range(struct address_space *mapping,
				loff_t start, loff_t end, int sync_mode);
2371 2372
extern int filemap_fdatawrite_range(struct address_space *mapping,
				loff_t start, loff_t end);
2373

2374 2375 2376
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);
2377 2378 2379 2380 2381 2382 2383
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
2384 2385
extern void emergency_sync(void);
extern void emergency_remount(void);
2386
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2387
extern sector_t bmap(struct inode *, sector_t);
2388
#endif
2389
extern int notify_change(struct dentry *, struct iattr *, struct inode **);
2390
extern int inode_permission(struct inode *, int);
2391
extern int __inode_permission(struct inode *, int);
2392
extern int generic_permission(struct inode *, int);
M
Miklos Szeredi 已提交
2393
extern int __check_sticky(struct inode *dir, struct inode *inode);
L
Linus Torvalds 已提交
2394

2395 2396 2397 2398 2399
static inline bool execute_ok(struct inode *inode)
{
	return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode);
}

2400 2401 2402 2403 2404 2405 2406
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);
}

2407 2408 2409 2410 2411 2412 2413
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);
}

2414 2415 2416 2417 2418 2419 2420
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);
}

2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442
/*
 * 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
2443
	struct inode *inode = file_inode(file);
2444 2445
	return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY;
}
L
Linus Torvalds 已提交
2446 2447 2448 2449 2450 2451 2452
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
2453
		atomic_inc(&file_inode(file)->i_writecount);
L
Linus Torvalds 已提交
2454
}
2455 2456 2457 2458 2459
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
2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479
#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
2480
extern int do_pipe_flags(int *, int);
L
Linus Torvalds 已提交
2481

M
Mimi Zohar 已提交
2482
extern int kernel_read(struct file *, loff_t, char *, unsigned long);
2483
extern ssize_t kernel_write(struct file *, const char *, size_t, loff_t);
A
Al Viro 已提交
2484
extern ssize_t __kernel_write(struct file *, const char *, size_t, loff_t *);
L
Linus Torvalds 已提交
2485 2486 2487 2488
extern struct file * open_exec(const char *);
 
/* fs/dcache.c -- generic fs support functions */
extern int is_subdir(struct dentry *, struct dentry *);
2489
extern int path_is_under(struct path *, struct path *);
L
Linus Torvalds 已提交
2490 2491 2492 2493

#include <linux/err.h>

/* needed for stackable file system support */
2494
extern loff_t default_llseek(struct file *file, loff_t offset, int whence);
L
Linus Torvalds 已提交
2495

2496
extern loff_t vfs_llseek(struct file *file, loff_t offset, int whence);
L
Linus Torvalds 已提交
2497

2498
extern int inode_init_always(struct super_block *, struct inode *);
L
Linus Torvalds 已提交
2499
extern void inode_init_once(struct inode *);
2500
extern void address_space_init_once(struct address_space *mapping);
L
Linus Torvalds 已提交
2501 2502 2503
extern struct inode * igrab(struct inode *);
extern ino_t iunique(struct super_block *, ino_t);
extern int inode_needs_sync(struct inode *inode);
2504
extern int generic_delete_inode(struct inode *inode);
2505 2506 2507 2508
static inline int generic_drop_inode(struct inode *inode)
{
	return !inode->i_nlink || inode_unhashed(inode);
}
L
Linus Torvalds 已提交
2509

2510 2511 2512
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
2513 2514 2515 2516 2517 2518
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);
2519 2520 2521 2522 2523
extern struct inode *find_inode_nowait(struct super_block *,
				       unsigned long,
				       int (*match)(struct inode *,
						    unsigned long, void *),
				       void *data);
A
Al Viro 已提交
2524 2525
extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *);
extern int insert_inode_locked(struct inode *);
2526 2527 2528 2529 2530
#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
2531
extern void unlock_new_inode(struct inode *);
2532
extern unsigned int get_next_ino(void);
L
Linus Torvalds 已提交
2533 2534

extern void __iget(struct inode * inode);
2535
extern void iget_failed(struct inode *);
2536
extern void clear_inode(struct inode *);
C
Christoph Hellwig 已提交
2537
extern void __destroy_inode(struct inode *);
2538 2539
extern struct inode *new_inode_pseudo(struct super_block *sb);
extern struct inode *new_inode(struct super_block *sb);
2540
extern void free_inode_nonrcu(struct inode *inode);
2541
extern int should_remove_suid(struct dentry *);
2542
extern int file_remove_suid(struct file *);
L
Linus Torvalds 已提交
2543 2544

extern void __insert_inode_hash(struct inode *, unsigned long hashval);
2545 2546
static inline void insert_inode_hash(struct inode *inode)
{
L
Linus Torvalds 已提交
2547 2548
	__insert_inode_hash(inode, inode->i_ino);
}
2549 2550 2551 2552 2553 2554 2555 2556

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

2557
extern void inode_sb_list_add(struct inode *inode);
L
Linus Torvalds 已提交
2558

2559
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2560 2561
extern void submit_bio(int, struct bio *);
extern int bdev_read_only(struct block_device *);
2562
#endif
L
Linus Torvalds 已提交
2563 2564 2565 2566 2567 2568 2569
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 *);
int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk);
A
Al Viro 已提交
2570
extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *);
2571 2572
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
2573
extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *, loff_t);
2574
extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t);
A
Andrew Morton 已提交
2575

2576 2577 2578
ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos);
ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos);

2579
/* fs/block_dev.c */
2580
extern ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to);
2581
extern ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from);
2582 2583
extern int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
			int datasync);
A
Al Viro 已提交
2584
extern void block_sync_page(struct page *page);
2585

A
Andrew Morton 已提交
2586
/* fs/splice.c */
2587
extern ssize_t generic_file_splice_read(struct file *, loff_t *,
A
Andrew Morton 已提交
2588
		struct pipe_inode_info *, size_t, unsigned int);
2589 2590
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
2591
extern ssize_t iter_file_splice_write(struct pipe_inode_info *,
2592
		struct file *, loff_t *, size_t, unsigned int);
A
Andrew Morton 已提交
2593
extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
2594
		struct file *out, loff_t *, size_t len, unsigned int flags);
2595 2596 2597
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
2598

L
Linus Torvalds 已提交
2599 2600
extern void
file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping);
2601 2602
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
2603
extern loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize);
2604
extern loff_t generic_file_llseek(struct file *file, loff_t offset, int whence);
A
Andi Kleen 已提交
2605
extern loff_t generic_file_llseek_size(struct file *file, loff_t offset,
2606
		int whence, loff_t maxsize, loff_t eof);
A
Al Viro 已提交
2607 2608
extern loff_t fixed_size_llseek(struct file *file, loff_t offset,
		int whence, loff_t size);
L
Linus Torvalds 已提交
2609 2610 2611
extern int generic_file_open(struct inode * inode, struct file * filp);
extern int nonseekable_open(struct inode * inode, struct file * filp);

2612 2613
ssize_t dax_do_io(int rw, struct kiocb *, struct inode *, struct iov_iter *,
		loff_t, get_block_t, dio_iodone_t, int flags);
2614
int dax_clear_blocks(struct inode *, sector_t block, long size);
M
Matthew Wilcox 已提交
2615
int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
2616
int dax_truncate_page(struct inode *, loff_t from, get_block_t);
2617 2618
int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t);
#define dax_mkwrite(vma, vmf, gb)	dax_fault(vma, vmf, gb)
2619

2620
#ifdef CONFIG_BLOCK
2621 2622
typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode,
			    loff_t file_offset);
L
Linus Torvalds 已提交
2623 2624

enum {
2625 2626 2627 2628 2629
	/* need locking between buffered and direct access */
	DIO_LOCKING	= 0x01,

	/* filesystem does not support filling holes */
	DIO_SKIP_HOLES	= 0x02,
2630 2631 2632

	/* filesystem can handle aio writes beyond i_size */
	DIO_ASYNC_EXTEND = 0x04,
L
Linus Torvalds 已提交
2633 2634
};

2635 2636
void dio_end_io(struct bio *bio, int error);

2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648
ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
			     struct block_device *bdev, struct iov_iter *iter,
			     loff_t offset, get_block_t get_block,
			     dio_iodone_t end_io, dio_submit_t submit_io,
			     int flags);

static inline ssize_t blockdev_direct_IO(struct kiocb *iocb,
					 struct inode *inode,
					 struct iov_iter *iter, loff_t offset,
					 get_block_t get_block)
{
	return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
2649
				    offset, get_block, NULL, NULL,
2650
				    DIO_LOCKING | DIO_SKIP_HOLES);
L
Linus Torvalds 已提交
2651
}
2652
#endif
L
Linus Torvalds 已提交
2653

2654 2655 2656
void inode_dio_wait(struct inode *inode);
void inode_dio_done(struct inode *inode);

2657 2658 2659
extern void inode_set_flags(struct inode *inode, unsigned int flags,
			    unsigned int mask);

2660
extern const struct file_operations generic_ro_fops;
L
Linus Torvalds 已提交
2661 2662 2663

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

A
Al Viro 已提交
2664
extern int readlink_copy(char __user *, int, const char *);
L
Linus Torvalds 已提交
2665
extern int page_readlink(struct dentry *, char __user *, int);
2666 2667
extern void *page_follow_link_light(struct dentry *, struct nameidata *);
extern void page_put_link(struct dentry *, struct nameidata *, void *);
2668
extern int __page_symlink(struct inode *inode, const char *symname, int len,
2669
		int nofs);
L
Linus Torvalds 已提交
2670
extern int page_symlink(struct inode *inode, const char *symname, int len);
2671
extern const struct inode_operations page_symlink_inode_operations;
A
Al Viro 已提交
2672
extern void kfree_put_link(struct dentry *, struct nameidata *, void *);
L
Linus Torvalds 已提交
2673 2674
extern int generic_readlink(struct dentry *, char __user *, int);
extern void generic_fillattr(struct inode *, struct kstat *);
J
J. Bruce Fields 已提交
2675
int vfs_getattr_nosec(struct path *path, struct kstat *stat);
A
Al Viro 已提交
2676
extern int vfs_getattr(struct path *, struct kstat *);
2677
void __inode_add_bytes(struct inode *inode, loff_t bytes);
L
Linus Torvalds 已提交
2678
void inode_add_bytes(struct inode *inode, loff_t bytes);
2679
void __inode_sub_bytes(struct inode *inode, loff_t bytes);
L
Linus Torvalds 已提交
2680 2681 2682 2683 2684
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 *);
2685
extern int iterate_dir(struct file *, struct dir_context *);
L
Linus Torvalds 已提交
2686

2687 2688
extern int vfs_stat(const char __user *, struct kstat *);
extern int vfs_lstat(const char __user *, struct kstat *);
L
Linus Torvalds 已提交
2689
extern int vfs_fstat(unsigned int, struct kstat *);
2690
extern int vfs_fstatat(int , const char __user *, struct kstat *, int);
L
Linus Torvalds 已提交
2691

2692 2693
extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
		    unsigned long arg);
2694
extern int __generic_block_fiemap(struct inode *inode,
J
Josef Bacik 已提交
2695 2696 2697
				  struct fiemap_extent_info *fieinfo,
				  loff_t start, loff_t len,
				  get_block_t *get_block);
2698 2699 2700
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
2701

2702 2703
extern void get_filesystem(struct file_system_type *fs);
extern void put_filesystem(struct file_system_type *fs);
L
Linus Torvalds 已提交
2704 2705
extern struct file_system_type *get_fs_type(const char *name);
extern struct super_block *get_super(struct block_device *);
2706
extern struct super_block *get_super_thawed(struct block_device *);
2707
extern struct super_block *get_active_super(struct block_device *bdev);
L
Linus Torvalds 已提交
2708
extern void drop_super(struct super_block *sb);
A
Al Viro 已提交
2709
extern void iterate_supers(void (*)(struct super_block *, void *), void *);
A
Al Viro 已提交
2710 2711
extern void iterate_supers_type(struct file_system_type *,
			        void (*)(struct super_block *, void *), void *);
L
Linus Torvalds 已提交
2712 2713 2714 2715

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);
2716
extern int dcache_readdir(struct file *, struct dir_context *);
2717
extern int simple_setattr(struct dentry *, struct iattr *);
L
Linus Torvalds 已提交
2718
extern int simple_getattr(struct vfsmount *, struct dentry *, struct kstat *);
2719
extern int simple_statfs(struct dentry *, struct kstatfs *);
S
Stephen Boyd 已提交
2720
extern int simple_open(struct inode *inode, struct file *file);
L
Linus Torvalds 已提交
2721 2722 2723 2724
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 *);
2725
extern int noop_fsync(struct file *, loff_t, loff_t, int);
L
Linus Torvalds 已提交
2726 2727
extern int simple_empty(struct dentry *);
extern int simple_readpage(struct file *file, struct page *page);
2728 2729 2730 2731 2732 2733
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);
2734
extern int always_delete_dentry(const struct dentry *);
A
Al Viro 已提交
2735
extern struct inode *alloc_anon_inode(struct super_block *);
2736
extern int simple_nosetlease(struct file *, long, struct file_lock **, void **);
2737
extern const struct dentry_operations simple_dentry_operations;
L
Linus Torvalds 已提交
2738

A
Al Viro 已提交
2739
extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags);
L
Linus Torvalds 已提交
2740
extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *);
2741
extern const struct file_operations simple_dir_operations;
2742
extern const struct inode_operations simple_dir_inode_operations;
2743
struct tree_descr { char *name; const struct file_operations *ops; int mode; };
L
Linus Torvalds 已提交
2744
struct dentry *d_alloc_name(struct dentry *, const char *);
2745
extern int simple_fill_super(struct super_block *, unsigned long, struct tree_descr *);
2746
extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count);
L
Linus Torvalds 已提交
2747 2748
extern void simple_release_fs(struct vfsmount **mount, int *count);

2749 2750
extern ssize_t simple_read_from_buffer(void __user *to, size_t count,
			loff_t *ppos, const void *from, size_t available);
2751 2752
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
2753

2754
extern int __generic_file_fsync(struct file *, loff_t, loff_t, int);
2755
extern int generic_file_fsync(struct file *, loff_t, loff_t, int);
A
Al Viro 已提交
2756

2757 2758
extern int generic_check_addressable(unsigned, u64);

2759
#ifdef CONFIG_MIGRATION
2760
extern int buffer_migrate_page(struct address_space *,
2761 2762
				struct page *, struct page *,
				enum migrate_mode);
2763 2764 2765 2766
#else
#define buffer_migrate_page NULL
#endif

N
npiggin@suse.de 已提交
2767 2768
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
2769
extern void setattr_copy(struct inode *inode, const struct iattr *attr);
L
Linus Torvalds 已提交
2770

2771
extern int file_update_time(struct file *file);
L
Linus Torvalds 已提交
2772

2773
extern int generic_show_options(struct seq_file *m, struct dentry *root);
2774
extern void save_mount_options(struct super_block *sb, char *options);
2775
extern void replace_mount_options(struct super_block *sb, char *options);
2776

2777 2778 2779 2780 2781
static inline bool io_is_direct(struct file *filp)
{
	return (filp->f_flags & O_DIRECT) || IS_DAX(file_inode(filp));
}

L
Linus Torvalds 已提交
2782 2783 2784 2785
static inline ino_t parent_ino(struct dentry *dentry)
{
	ino_t res;

N
Nick Piggin 已提交
2786 2787 2788 2789
	/*
	 * 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
2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814
	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);

2815
void simple_transaction_set(struct file *file, size_t n);
L
Linus Torvalds 已提交
2816

2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838
/*
 * 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);	\
}									\
2839
static const struct file_operations __fops = {				\
2840 2841
	.owner	 = THIS_MODULE,						\
	.open	 = __fops ## _open,					\
2842
	.release = simple_attr_release,					\
2843 2844
	.read	 = simple_attr_read,					\
	.write	 = simple_attr_write,					\
2845
	.llseek	 = generic_file_llseek,					\
2846
}
2847

2848 2849
static inline __printf(1, 2)
void __simple_attr_check_format(const char *fmt, ...)
2850 2851 2852 2853 2854
{
	/* don't do anything, just let the compiler check the arguments; */
}

int simple_attr_open(struct inode *inode, struct file *file,
2855
		     int (*get)(void *, u64 *), int (*set)(void *, u64),
2856
		     const char *fmt);
2857
int simple_attr_release(struct inode *inode, struct file *file);
2858 2859 2860 2861 2862
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
2863
struct ctl_table;
2864
int proc_nr_files(struct ctl_table *table, int write,
2865
		  void __user *buffer, size_t *lenp, loff_t *ppos);
2866 2867
int proc_nr_dentry(struct ctl_table *table, int write,
		  void __user *buffer, size_t *lenp, loff_t *ppos);
2868 2869
int proc_nr_inodes(struct ctl_table *table, int write,
		   void __user *buffer, size_t *lenp, loff_t *ppos);
2870
int __init get_filesystem_list(char *buf);
2871

N
Namhyung Kim 已提交
2872
#define __FMODE_EXEC		((__force int) FMODE_EXEC)
2873 2874
#define __FMODE_NONOTIFY	((__force int) FMODE_NONOTIFY)

A
Al Viro 已提交
2875
#define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE])
E
Eric Paris 已提交
2876
#define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \
2877
					    (flag & __FMODE_NONOTIFY)))
A
Al Viro 已提交
2878

A
Al Viro 已提交
2879
static inline int is_sxid(umode_t mode)
2880 2881 2882 2883
{
	return (mode & S_ISUID) || ((mode & S_ISGID) && (mode & S_IXGRP));
}

M
Miklos Szeredi 已提交
2884 2885 2886 2887 2888 2889 2890 2891
static inline int check_sticky(struct inode *dir, struct inode *inode)
{
	if (!(dir->i_mode & S_ISVTX))
		return 0;

	return __check_sticky(dir, inode);
}

2892 2893
static inline void inode_has_no_xattr(struct inode *inode)
{
A
Al Viro 已提交
2894
	if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & MS_NOSEC))
2895 2896 2897
		inode->i_flags |= S_NOSEC;
}

A
Al Viro 已提交
2898 2899 2900 2901 2902
static inline bool is_root_inode(struct inode *inode)
{
	return inode == inode->i_sb->s_root->d_inode;
}

2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932
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
2933 2934 2935 2936 2937 2938
static inline bool dir_relax(struct inode *inode)
{
	mutex_unlock(&inode->i_mutex);
	mutex_lock(&inode->i_mutex);
	return !IS_DEADDIR(inode);
}
2939

L
Linus Torvalds 已提交
2940
#endif /* _LINUX_FS_H */