fs.h 103 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1 2 3 4 5 6 7
#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>
8
#include <linux/path.h>
Linus Torvalds's avatar
Linus Torvalds committed
9 10 11
#include <linux/stat.h>
#include <linux/cache.h>
#include <linux/list.h>
12
#include <linux/list_lru.h>
13
#include <linux/llist.h>
Linus Torvalds's avatar
Linus Torvalds committed
14
#include <linux/radix-tree.h>
15
#include <linux/rbtree.h>
Linus Torvalds's avatar
Linus Torvalds committed
16
#include <linux/init.h>
17
#include <linux/pid.h>
18
#include <linux/bug.h>
19
#include <linux/mutex.h>
20
#include <linux/rwsem.h>
21
#include <linux/capability.h>
22
#include <linux/semaphore.h>
23
#include <linux/fiemap.h>
24
#include <linux/rculist_bl.h>
25
#include <linux/atomic.h>
26
#include <linux/shrinker.h>
27
#include <linux/migrate_mode.h>
28
#include <linux/uidgid.h>
29
#include <linux/lockdep.h>
30
#include <linux/percpu-rwsem.h>
31
#include <linux/blk_types.h>
32
#include <linux/workqueue.h>
33
#include <linux/percpu-rwsem.h>
34
#include <linux/delayed_call.h>
Linus Torvalds's avatar
Linus Torvalds committed
35 36

#include <asm/byteorder.h>
37
#include <uapi/linux/fs.h>
Linus Torvalds's avatar
Linus Torvalds committed
38

39
struct backing_dev_info;
40
struct bdi_writeback;
41
struct export_operations;
42
struct hd_geometry;
Linus Torvalds's avatar
Linus Torvalds committed
43
struct iovec;
44
struct kiocb;
Alexey Dobriyan's avatar
Alexey Dobriyan committed
45
struct kobject;
Linus Torvalds's avatar
Linus Torvalds committed
46 47 48 49 50
struct pipe_inode_info;
struct poll_table_struct;
struct kstatfs;
struct vm_area_struct;
struct vfsmount;
51
struct cred;
52
struct swap_info_struct;
53
struct seq_file;
54
struct workqueue_struct;
55
struct iov_iter;
56 57
struct fscrypt_info;
struct fscrypt_operations;
Linus Torvalds's avatar
Linus Torvalds committed
58

59
extern void __init inode_init(void);
Linus Torvalds's avatar
Linus Torvalds committed
60
extern void __init inode_init_early(void);
61 62
extern void __init files_init(void);
extern void __init files_maxfiles_init(void);
Linus Torvalds's avatar
Linus Torvalds committed
63

64
extern struct files_stat_struct files_stat;
65
extern unsigned long get_max_files(void);
66 67 68
extern int sysctl_nr_open;
extern struct inodes_stat_t inodes_stat;
extern int leases_enable, lease_break_time;
Kees Cook's avatar
Kees Cook committed
69 70
extern int sysctl_protected_symlinks;
extern int sysctl_protected_hardlinks;
71

Linus Torvalds's avatar
Linus Torvalds committed
72 73 74
struct buffer_head;
typedef int (get_block_t)(struct inode *inode, sector_t iblock,
			struct buffer_head *bh_result, int create);
75
typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
76
			ssize_t bytes, void *private);
Linus Torvalds's avatar
Linus Torvalds committed
77

78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133
#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)

134 135
/* File needs atomic accesses to f_pos */
#define FMODE_ATOMIC_POS	((__force fmode_t)0x8000)
136 137
/* Write access to underlying fs */
#define FMODE_WRITER		((__force fmode_t)0x10000)
138 139 140 141
/* Has read method(s) */
#define FMODE_CAN_READ          ((__force fmode_t)0x20000)
/* Has write method(s) */
#define FMODE_CAN_WRITE         ((__force fmode_t)0x40000)
142

143
/* File was opened by fanotify and shouldn't generate fanotify events */
144
#define FMODE_NONOTIFY		((__force fmode_t)0x4000000)
145 146 147 148 149 150 151 152 153

/*
 * 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

154
/*
155
 * The below are the various read and write flags that we support. Some of
156
 * them include behavioral modifiers that send information down to the
157 158
 * block layer and IO scheduler. They should be used along with a req_op.
 * Terminology:
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
 *
 *	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.
 * 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.
 *
 */
194
#define RW_MASK			REQ_OP_WRITE
195

196
#define READ			REQ_OP_READ
197
#define WRITE			REQ_OP_WRITE
198

199 200 201
#define READ_SYNC		REQ_SYNC
#define WRITE_SYNC		(REQ_SYNC | REQ_NOIDLE)
#define WRITE_ODIRECT		REQ_SYNC
202
#define WRITE_FLUSH		(REQ_SYNC | REQ_NOIDLE | REQ_PREFLUSH)
203
#define WRITE_FUA		(REQ_SYNC | REQ_NOIDLE | REQ_FUA)
204
#define WRITE_FLUSH_FUA		(REQ_SYNC | REQ_NOIDLE | REQ_PREFLUSH | REQ_FUA)
205

Linus Torvalds's avatar
Linus Torvalds committed
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)
Linus Torvalds's avatar
Linus Torvalds committed
227

Miklos Szeredi's avatar
Miklos Szeredi committed
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

Linus Torvalds's avatar
Linus Torvalds committed
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;
Linus Torvalds's avatar
Linus Torvalds committed
249 250 251 252
	loff_t		ia_size;
	struct timespec	ia_atime;
	struct timespec	ia_mtime;
	struct timespec	ia_ctime;
253 254

	/*
Lucas De Marchi's avatar
Lucas De Marchi committed
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;
Linus Torvalds's avatar
Linus Torvalds committed
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
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 */
Nick Piggin's avatar
Nick Piggin committed
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

Linus Torvalds's avatar
Linus Torvalds committed
310 311 312 313 314 315 316
/*
 * oh the beauties of C type declarations.
 */
struct page;
struct address_space;
struct writeback_control;

317
#define IOCB_EVENTFD		(1 << 0)
318 319
#define IOCB_APPEND		(1 << 1)
#define IOCB_DIRECT		(1 << 2)
320
#define IOCB_HIPRI		(1 << 3)
321 322
#define IOCB_DSYNC		(1 << 4)
#define IOCB_SYNC		(1 << 5)
323 324 325 326 327 328 329 330 331 332 333 334 335 336

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;
}

337 338
static inline int iocb_flags(struct file *file);

339 340 341 342
static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
{
	*kiocb = (struct kiocb) {
		.ki_filp = filp,
343
		.ki_flags = iocb_flags(filp),
344 345 346
	};
}

347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367
/*
 * "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);
Nick Piggin's avatar
Nick Piggin committed
368

Linus Torvalds's avatar
Linus Torvalds committed
369 370 371 372 373 374 375
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 *);

376
	/* Set a page dirty.  Return true if this dirtied it */
Linus Torvalds's avatar
Linus Torvalds committed
377 378 379 380 381
	int (*set_page_dirty)(struct page *page);

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

382 383 384 385 386 387 388
	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);

Linus Torvalds's avatar
Linus Torvalds committed
389 390
	/* Unfortunately this kludge is needed for FIBMAP. Don't use it */
	sector_t (*bmap)(struct address_space *, sector_t);
391
	void (*invalidatepage) (struct page *, unsigned int, unsigned int);
Al Viro's avatar
Al Viro committed
392
	int (*releasepage) (struct page *, gfp_t);
393
	void (*freepage)(struct page *);
394
	ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter);
395
	/*
396 397
	 * migrate the contents of a page to the specified target. If
	 * migrate_mode is MIGRATE_ASYNC, it must not block.
398
	 */
399
	int (*migratepage) (struct address_space *,
400
			struct page *, struct page *, enum migrate_mode);
401 402
	bool (*isolate_page)(struct page *, isolate_mode_t);
	void (*putback_page)(struct page *);
403
	int (*launder_page) (struct page *);
404
	int (*is_partially_uptodate) (struct page *, unsigned long,
405
					unsigned long);
406
	void (*is_dirty_writeback) (struct page *, bool *, bool *);
407
	int (*error_remove_page)(struct address_space *, struct page *);
408 409

	/* swapfile support */
410 411 412
	int (*swap_activate)(struct swap_info_struct *sis, struct file *file,
				sector_t *span);
	void (*swap_deactivate)(struct file *file);
Linus Torvalds's avatar
Linus Torvalds committed
413 414
};

Jens Axboe's avatar
Jens Axboe committed
415 416
extern const struct address_space_operations empty_aops;

417 418 419 420 421 422 423 424 425 426 427 428
/*
 * 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);

Linus Torvalds's avatar
Linus Torvalds committed
429 430 431
struct address_space {
	struct inode		*host;		/* owner: inode, block_device */
	struct radix_tree_root	page_tree;	/* radix tree of all pages */
Nick Piggin's avatar
Nick Piggin committed
432
	spinlock_t		tree_lock;	/* and lock protecting it */
433
	atomic_t		i_mmap_writable;/* count VM_SHARED mappings */
434
	struct rb_root		i_mmap;		/* tree of private and shared mappings */
435
	struct rw_semaphore	i_mmap_rwsem;	/* protect tree, count, list */
436
	/* Protected by tree_lock together with the radix tree */
Linus Torvalds's avatar
Linus Torvalds committed
437
	unsigned long		nrpages;	/* number of total pages */
438 439
	/* number of shadow or DAX exceptional entries */
	unsigned long		nrexceptional;
Linus Torvalds's avatar
Linus Torvalds committed
440
	pgoff_t			writeback_index;/* writeback starts here */
441
	const struct address_space_operations *a_ops;	/* methods */
Linus Torvalds's avatar
Linus Torvalds committed
442 443 444
	unsigned long		flags;		/* error bits/gfp mask */
	spinlock_t		private_lock;	/* for use by the address_space */
	struct list_head	private_list;	/* ditto */
445
	void			*private_data;	/* ditto */
Linus Torvalds's avatar
Linus Torvalds committed
446 447 448
} __attribute__((aligned(sizeof(long))));
	/*
	 * On most architectures that alignment is already the case; but
Lucas De Marchi's avatar
Lucas De Marchi committed
449
	 * must be enforced here for CRIS, to let the least significant bit
Linus Torvalds's avatar
Linus Torvalds committed
450 451
	 * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON.
	 */
452
struct request_queue;
Linus Torvalds's avatar
Linus Torvalds committed
453 454 455

struct block_device {
	dev_t			bd_dev;  /* not a kdev_t - it's a search key */
456
	int			bd_openers;
Linus Torvalds's avatar
Linus Torvalds committed
457
	struct inode *		bd_inode;	/* will die */
458
	struct super_block *	bd_super;
459
	struct mutex		bd_mutex;	/* open/close mutex */
460
	void *			bd_claiming;
Linus Torvalds's avatar
Linus Torvalds committed
461 462
	void *			bd_holder;
	int			bd_holders;
463
	bool			bd_write_holder;
464
#ifdef CONFIG_SYSFS
465
	struct list_head	bd_holder_disks;
466
#endif
Linus Torvalds's avatar
Linus Torvalds committed
467 468 469 470 471 472 473
	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;
474
	struct request_queue *  bd_queue;
Linus Torvalds's avatar
Linus Torvalds committed
475 476 477 478 479 480 481 482
	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;
483 484 485 486 487

	/* The counter of freeze processes */
	int			bd_fsfreeze_count;
	/* Mutex for freeze */
	struct mutex		bd_fsfreeze_mutex;
Linus Torvalds's avatar
Linus Torvalds committed
488 489 490 491 492 493 494 495
};

/*
 * Radix-tree tags, for tagging dirty and writeback pages within the pagecache
 * radix trees
 */
#define PAGECACHE_TAG_DIRTY	0
#define PAGECACHE_TAG_WRITEBACK	1
496
#define PAGECACHE_TAG_TOWRITE	2
Linus Torvalds's avatar
Linus Torvalds committed
497 498 499

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

500 501
static inline void i_mmap_lock_write(struct address_space *mapping)
{
502
	down_write(&mapping->i_mmap_rwsem);
503 504 505 506
}

static inline void i_mmap_unlock_write(struct address_space *mapping)
{
507
	up_write(&mapping->i_mmap_rwsem);
508 509
}

510 511 512 513 514 515 516 517 518 519
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);
}

Linus Torvalds's avatar
Linus Torvalds committed
520 521 522 523 524
/*
 * Might pages of this file be mapped into userspace?
 */
static inline int mapping_mapped(struct address_space *mapping)
{
525
	return	!RB_EMPTY_ROOT(&mapping->i_mmap);
Linus Torvalds's avatar
Linus Torvalds committed
526 527 528 529 530 531 532
}

/*
 * 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.
533 534 535
 *
 * If i_mmap_writable is negative, no new writable mappings are allowed. You
 * can only deny writable mappings, if none exists right now.
Linus Torvalds's avatar
Linus Torvalds committed
536 537 538
 */
static inline int mapping_writably_mapped(struct address_space *mapping)
{
539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561
	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);
Linus Torvalds's avatar
Linus Torvalds committed
562 563 564 565 566 567 568 569 570 571 572 573 574
}

/*
 * 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

575 576 577
struct posix_acl;
#define ACL_NOT_CACHED ((void *)(-1))

578 579 580 581 582 583 584 585 586 587 588 589
static inline struct posix_acl *
uncached_acl_sentinel(struct task_struct *task)
{
	return (void *)task + 1;
}

static inline bool
is_uncached_acl(struct posix_acl *acl)
{
	return (long)acl & 1;
}

590 591 592 593 594 595 596 597 598
#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'
 */
Linus Torvalds's avatar
Linus Torvalds committed
599
struct inode {
600
	umode_t			i_mode;
601
	unsigned short		i_opflags;
602 603
	kuid_t			i_uid;
	kgid_t			i_gid;
604 605 606 607 608 609 610
	unsigned int		i_flags;

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

611 612
	const struct inode_operations	*i_op;
	struct super_block	*i_sb;
613
	struct address_space	*i_mapping;
614

615 616 617
#ifdef CONFIG_SECURITY
	void			*i_security;
#endif
618

619 620
	/* Stat data, not accessed from path walking */
	unsigned long		i_ino;
Miklos Szeredi's avatar
Miklos Szeredi committed
621 622 623 624 625 626 627 628 629 630 631
	/*
	 * 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;
	};
632
	dev_t			i_rdev;
633
	loff_t			i_size;
634 635 636
	struct timespec		i_atime;
	struct timespec		i_mtime;
	struct timespec		i_ctime;
637 638
	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
	unsigned short          i_bytes;
639
	unsigned int		i_blkbits;
640 641 642 643 644 645 646 647
	blkcnt_t		i_blocks;

#ifdef __NEED_I_SIZE_ORDERED
	seqcount_t		i_size_seqcount;
#endif

	/* Misc */
	unsigned long		i_state;
648
	struct rw_semaphore	i_rwsem;
649

650
	unsigned long		dirtied_when;	/* jiffies of first dirtying */
651
	unsigned long		dirtied_time_when;
652

Linus Torvalds's avatar
Linus Torvalds committed
653
	struct hlist_node	i_hash;
654
	struct list_head	i_io_list;	/* backing dev IO list */
655 656
#ifdef CONFIG_CGROUP_WRITEBACK
	struct bdi_writeback	*i_wb;		/* the associated cgroup wb */
657 658 659 660 661

	/* foreign inode detection, see wbc_detach_inode() */
	int			i_wb_frn_winner;
	u16			i_wb_frn_avg_time;
	u16			i_wb_frn_history;
662
#endif
663
	struct list_head	i_lru;		/* inode LRU list */
Linus Torvalds's avatar
Linus Torvalds committed
664
	struct list_head	i_sb_list;
665
	struct list_head	i_wb_list;	/* backing dev writeback list */
Nick Piggin's avatar
Nick Piggin committed
666
	union {
667
		struct hlist_head	i_dentry;
Nick Piggin's avatar
Nick Piggin committed
668 669
		struct rcu_head		i_rcu;
	};
670
	u64			i_version;
671
	atomic_t		i_count;
Christoph Hellwig's avatar
Christoph Hellwig committed
672
	atomic_t		i_dio_count;
673
	atomic_t		i_writecount;
Mimi Zohar's avatar
Mimi Zohar committed
674 675 676
#ifdef CONFIG_IMA
	atomic_t		i_readcount; /* struct files open RO */
#endif
677
	const struct file_operations	*i_fop;	/* former ->i_op->default_file_ops */
678
	struct file_lock_context	*i_flctx;
Linus Torvalds's avatar
Linus Torvalds committed
679 680
	struct address_space	i_data;
	struct list_head	i_devices;
681 682
	union {
		struct pipe_inode_info	*i_pipe;
683
		struct block_device	*i_bdev;
684
		struct cdev		*i_cdev;
Al Viro's avatar
Al Viro committed
685
		char			*i_link;
Al Viro's avatar
Al Viro committed
686
		unsigned		i_dir_seq;
687
	};
Linus Torvalds's avatar
Linus Torvalds committed
688 689 690

	__u32			i_generation;

691 692
#ifdef CONFIG_FSNOTIFY
	__u32			i_fsnotify_mask; /* all events this inode cares about */
693
	struct hlist_head	i_fsnotify_marks;
Robert Love's avatar
Robert Love committed
694 695
#endif

696 697 698 699
#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
	struct fscrypt_info	*i_crypt_info;
#endif

700
	void			*i_private; /* fs or device private pointer */
Linus Torvalds's avatar
Linus Torvalds committed
701 702
};

Al Viro's avatar
Al Viro committed
703 704 705 706 707
static inline int inode_unhashed(struct inode *inode)
{
	return hlist_unhashed(&inode->i_hash);
}

708 709 710 711 712 713
/*
 * inode->i_mutex nesting subclasses for the lock validator:
 *
 * 0: the object of the current VFS operation
 * 1: parent
 * 2: child/target
714 715
 * 3: xattr
 * 4: second non-directory
716 717 718
 * 5: second parent (when locking independent directories in rename)
 *
 * I_MUTEX_NONDIR2 is for certain operations (such as rename) which lock two
719
 * non-directories at once.
720 721
 *
 * The locking order between these classes is
722
 * parent[2] -> child -> grandchild -> normal -> xattr -> second non-directory
723 724 725 726 727 728
 */
enum inode_i_mutex_lock_class
{
	I_MUTEX_NORMAL,
	I_MUTEX_PARENT,
	I_MUTEX_CHILD,
729
	I_MUTEX_XATTR,
730 731
	I_MUTEX_NONDIR2,
	I_MUTEX_PARENT2,
732 733
};

Al Viro's avatar
Al Viro committed
734 735
static inline void inode_lock(struct inode *inode)
{
736
	down_write(&inode->i_rwsem);
Al Viro's avatar
Al Viro committed
737 738 739 740
}

static inline void inode_unlock(struct inode *inode)
{
741 742 743 744 745 746 747 748 749 750 751
	up_write(&inode->i_rwsem);
}

static inline void inode_lock_shared(struct inode *inode)
{
	down_read(&inode->i_rwsem);
}

static inline void inode_unlock_shared(struct inode *inode)
{
	up_read(&inode->i_rwsem);
Al Viro's avatar
Al Viro committed
752 753 754 755
}

static inline int inode_trylock(struct inode *inode)
{
756 757 758 759 760 761
	return down_write_trylock(&inode->i_rwsem);
}

static inline int inode_trylock_shared(struct inode *inode)
{
	return down_read_trylock(&inode->i_rwsem);
Al Viro's avatar
Al Viro committed
762 763 764 765
}

static inline int inode_is_locked(struct inode *inode)
{
766
	return rwsem_is_locked(&inode->i_rwsem);
Al Viro's avatar
Al Viro committed
767 768 769 770
}

static inline void inode_lock_nested(struct inode *inode, unsigned subclass)
{
771
	down_write_nested(&inode->i_rwsem, subclass);
Al Viro's avatar
Al Viro committed
772 773
}

774 775 776
void lock_two_nondirectories(struct inode *, struct inode*);
void unlock_two_nondirectories(struct inode *, struct inode*);

Linus Torvalds's avatar
Linus Torvalds committed
777 778 779 780 781 782 783 784 785 786
/*
 * 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.
 */
787
static inline loff_t i_size_read(const struct inode *inode)
Linus Torvalds's avatar
Linus Torvalds committed
788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809
{
#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
}

810 811 812 813 814
/*
 * 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.
 */
Linus Torvalds's avatar
Linus Torvalds committed
815 816 817
static inline void i_size_write(struct inode *inode, loff_t i_size)
{
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
818
	preempt_disable();
Linus Torvalds's avatar
Linus Torvalds committed
819 820 821
	write_seqcount_begin(&inode->i_size_seqcount);
	inode->i_size = i_size;
	write_seqcount_end(&inode->i_size_seqcount);
822
	preempt_enable();
Linus Torvalds's avatar
Linus Torvalds committed
823 824 825 826 827 828 829 830 831
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
	preempt_disable();
	inode->i_size = i_size;
	preempt_enable();
#else
	inode->i_size = i_size;
#endif
}

832
static inline unsigned iminor(const struct inode *inode)
Linus Torvalds's avatar
Linus Torvalds committed
833 834 835 836
{
	return MINOR(inode->i_rdev);
}

837
static inline unsigned imajor(const struct inode *inode)
Linus Torvalds's avatar
Linus Torvalds committed
838 839 840 841 842 843 844 845
{
	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 */
846 847
	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 */
848
	kuid_t uid, euid;	/* uid/euid of process setting the owner */
Linus Torvalds's avatar
Linus Torvalds committed
849 850 851 852 853 854 855
	int signum;		/* posix.1b rt signal to be delivered on IO */
};

/*
 * Track a single file's readahead state
 */
struct file_ra_state {
856 857 858
	pgoff_t start;			/* where readahead started */
	unsigned int size;		/* # of readahead pages */
	unsigned int async_size;	/* do asynchronous readahead when
859
					   there are only # of pages ahead */
860

861
	unsigned int ra_pages;		/* Maximum readahead window */
862
	unsigned int mmap_miss;		/* Cache miss stat for mmap accesses */
863
	loff_t prev_pos;		/* Cache last read() position */
Linus Torvalds's avatar
Linus Torvalds committed
864 865
};

866 867 868 869 870
/*
 * Check if @index falls in the readahead windows.
 */
static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
{
871 872
	return (index >= ra->start &&
		index <  ra->start + ra->size);
873 874
}

Linus Torvalds's avatar
Linus Torvalds committed
875
struct file {
876
	union {
877
		struct llist_node	fu_llist;
878 879
		struct rcu_head 	fu_rcuhead;
	} f_u;
880
	struct path		f_path;
881
	struct inode		*f_inode;	/* cached value */
882
	const struct file_operations	*f_op;
883 884

	/*
885
	 * Protects f_ep_links, f_flags.
886 887 888
	 * Must not be taken from IRQ context.
	 */
	spinlock_t		f_lock;
Al Viro's avatar
Al Viro committed
889
	atomic_long_t		f_count;
Linus Torvalds's avatar
Linus Torvalds committed
890
	unsigned int 		f_flags;
891
	fmode_t			f_mode;
892
	struct mutex		f_pos_lock;
Linus Torvalds's avatar
Linus Torvalds committed
893 894
	loff_t			f_pos;
	struct fown_struct	f_owner;
895
	const struct cred	*f_cred;
Linus Torvalds's avatar
Linus Torvalds committed
896 897
	struct file_ra_state	f_ra;

898
	u64			f_version;
899
#ifdef CONFIG_SECURITY
Linus Torvalds's avatar
Linus Torvalds committed
900
	void			*f_security;
901
#endif
Linus Torvalds's avatar
Linus Torvalds committed
902 903 904 905 906 907
	/* 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;
Jason Baron's avatar
Jason Baron committed
908
	struct list_head	f_tfile_llink;
Linus Torvalds's avatar
Linus Torvalds committed
909 910
#endif /* #ifdef CONFIG_EPOLL */
	struct address_space	*f_mapping;
Al Viro's avatar
Al Viro committed
911
} __attribute__((aligned(4)));	/* lest something weird decides that 2 is OK */
Linus Torvalds's avatar
Linus Torvalds committed
912

913 914 915 916 917 918 919
struct file_handle {
	__u32 handle_bytes;
	int handle_type;
	/* file identifier */
	unsigned char f_handle[0];
};

920 921 922 923 924
static inline struct file *get_file(struct file *f)
{
	atomic_long_inc(&f->f_count);
	return f;
}
925
#define get_file_rcu(x) atomic_long_inc_not_zero(&(x)->f_count)
926
#define fput_atomic(x)	atomic_long_add_unless(&(x)->f_count, -1, 1)
Al Viro's avatar
Al Viro committed
927
#define file_count(x)	atomic_long_read(&(x)->f_count)
Linus Torvalds's avatar
Linus Torvalds committed
928 929 930 931 932 933

#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
934
#define MAX_LFS_FILESIZE	(((loff_t)PAGE_SIZE << (BITS_PER_LONG-1))-1)
Linus Torvalds's avatar
Linus Torvalds committed
935
#elif BITS_PER_LONG==64
936
#define MAX_LFS_FILESIZE 	((loff_t)0x7fffffffffffffffLL)
Linus Torvalds's avatar
Linus Torvalds committed
937 938 939 940
#endif

#define FL_POSIX	1
#define FL_FLOCK	2
941
#define FL_DELEG	4	/* NFSv4 delegation */
Linus Torvalds's avatar
Linus Torvalds committed
942
#define FL_ACCESS	8	/* not trying to lock, just looking */
943
#define FL_EXISTS	16	/* when unlocking, test for existence */
Linus Torvalds's avatar
Linus Torvalds committed
944
#define FL_LEASE	32	/* lease held on this file */
945
#define FL_CLOSE	64	/* unlock on close */
Linus Torvalds's avatar
Linus Torvalds committed
946
#define FL_SLEEP	128	/* A blocking lock */
947 948
#define FL_DOWNGRADE_PENDING	256 /* Lease is being downgraded */
#define FL_UNLOCK_PENDING	512 /* Lease is being broken */
949
#define FL_OFDLCK	1024	/* lock is "owned" by struct file */
950
#define FL_LAYOUT	2048	/* outstanding pNFS layout */
Linus Torvalds's avatar
Linus Torvalds committed
951

952 953 954 955 956 957
/*
 * Special return value from posix_lock_file() and vfs_lock_file() for
 * asynchronous locking.
 */
#define FILE_LOCK_DEFERRED 1

958
/* legacy typedef, should eventually be removed */
959
typedef void *fl_owner_t;
Linus Torvalds's avatar
Linus Torvalds committed
960

961 962
struct file_lock;

Linus Torvalds's avatar
Linus Torvalds committed
963 964 965 966 967 968
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 {
969
	int (*lm_compare_owner)(struct file_lock *, struct file_lock *);
970
	unsigned long (*lm_owner_key)(struct file_lock *);
971 972
	fl_owner_t (*lm_get_owner)(fl_owner_t);
	void (*lm_put_owner)(fl_owner_t);
973
	void (*lm_notify)(struct file_lock *);	/* unblock callback */
974
	int (*lm_grant)(struct file_lock *, int);
975
	bool (*lm_break)(struct file_lock *);
976
	int (*lm_change)(struct file_lock *, int, struct list_head *);
977
	void (*lm_setup)(struct file_lock *, void **);
Linus Torvalds's avatar
Linus Torvalds committed
978 979
};

980 981
struct lock_manager {
	struct list_head list;
982 983 984 985 986
	/*
	 * NFSv4 and up also want opens blocked during the grace period;
	 * NLM doesn't care:
	 */
	bool block_opens;
987 988
};

989 990
struct net;
void locks_start_grace(struct net *, struct lock_manager *);
991
void locks_end_grace(struct lock_manager *);
992
int locks_in_grace(struct net *);
993
int opens_in_grace(struct net *);
994

Linus Torvalds's avatar
Linus Torvalds committed
995 996 997
/* that will die - we need it for nfs_lock_info */
#include <linux/nfs_fs_i.h>

998 999 1000 1001 1002 1003 1004 1005 1006
/*
 * 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?
 *
1007
 * The varous i_flctx lists are ordered by:
1008
 *
1009 1010 1011
 * 1) lock owner
 * 2) lock range start
 * 3) lock range end
1012 1013 1014
 *
 * Obviously, the last two criteria only matter for POSIX locks.
 */
Linus Torvalds's avatar
Linus Torvalds committed
1015 1016
struct file_lock {
	struct file_lock *fl_next;	/* singly linked list for this inode  */
1017
	struct list_head fl_list;	/* link into file_lock_context */
1018
	struct hlist_node fl_link;	/* node in global lists */
Linus Torvalds's avatar
Linus Torvalds committed
1019 1020
	struct list_head fl_block;	/* circular list of blocked processes */
	fl_owner_t fl_owner;
1021
	unsigned int fl_flags;
1022
	unsigned char fl_type;
Linus Torvalds's avatar
Linus Torvalds committed
1023
	unsigned int fl_pid;
1024
	int fl_link_cpu;		/* what cpu's list is this on? */
1025
	struct pid *fl_nspid;
Linus Torvalds's avatar
Linus Torvalds committed
1026 1027 1028 1029 1030 1031
	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 */
1032 1033 1034
	/* for lease breaks: */
	unsigned long fl_break_time;
	unsigned long fl_downgrade_time;
Linus Torvalds's avatar
Linus Torvalds committed
1035

1036
	const struct file_lock_operations *fl_ops;	/* Callbacks for filesystems */
1037
	const struct lock_manager_operations *fl_lmops;	/* Callbacks for lockmanagers */
Linus Torvalds's avatar
Linus Torvalds committed
1038 1039
	union {
		struct nfs_lock_info	nfs_fl;
1040
		struct nfs4_lock_info	nfs4_fl;
David Howells's avatar
David Howells committed
1041 1042 1043 1044
		struct {
			struct list_head link;	/* link in AFS vnode's pending_locks list */
			int state;		/* state of grant or error if -ve */
		} afs;
Linus Torvalds's avatar
Linus Torvalds committed
1045 1046 1047
	} fl_u;
};

1048
struct file_lock_context {
1049
	spinlock_t		flc_lock;
1050
	struct list_head	flc_flock;
1051
	struct list_head	flc_posix;
1052
	struct list_head	flc_lease;
1053 1054
};

Linus Torvalds's avatar
Linus Torvalds committed
1055 1056 1057 1058 1059 1060 1061 1062 1063
/* 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>

1064 1065 1066
extern void send_sigio(struct fown_struct *fown, int fd, int band);

#ifdef CONFIG_FILE_LOCKING
1067
extern int fcntl_getlk(struct file *, unsigned int, struct flock __user *);
1068 1069
extern int fcntl_setlk(unsigned int, struct file *, unsigned int,
			struct flock __user *);
Linus Torvalds's avatar
Linus Torvalds committed
1070 1071

#if BITS_PER_LONG == 32
1072
extern int fcntl_getlk64(struct file *, unsigned int, struct flock64 __user *);
1073 1074
extern int fcntl_setlk64(unsigned int, struct file *, unsigned int,
			struct flock64 __user *);
Linus Torvalds's avatar
Linus Torvalds committed
1075 1076 1077 1078 1079 1080
#endif

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

/* fs/locks.c */
1081
void locks_free_lock_context(struct inode *inode);
1082
void locks_free_lock(struct file_lock *fl);
Linus Torvalds's avatar
Linus Torvalds committed
1083
extern void locks_init_lock(struct file_lock *);
1084
extern struct file_lock * locks_alloc_lock(void);
Linus Torvalds's avatar
Linus Torvalds committed
1085
extern void locks_copy_lock(struct file_lock *, struct file_lock *);
1086
extern void locks_copy_conflock(struct file_lock *, struct file_lock *);
Linus Torvalds's avatar
Linus Torvalds committed
1087
extern void locks_remove_posix(struct file *, fl_owner_t);
1088
extern void locks_remove_file(struct file *);
1089
extern void locks_release_private(struct file_lock *);
1090
extern void posix_test_lock(struct file *, struct file_lock *);
1091
extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *);
1092
extern int posix_unblock_lock(struct file_lock *);
1093
extern int vfs_test_lock(struct file *, struct file_lock *);
1094
extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *);
Marc Eshel's avatar
Marc Eshel committed
1095
extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
1096
extern int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl);
1097
extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type);
Linus Torvalds's avatar
Linus Torvalds committed
1098
extern void lease_get_mtime(struct inode *, struct timespec *time);
1099 1100
extern int generic_setlease(struct file *, long, struct file_lock **, void **priv);
extern int vfs_setlease(struct file *, long, struct file_lock **, void **);
1101
extern int lease_modify(struct file_lock *, int, struct list_head *);
1102 1103 1104
struct files_struct;
extern void show_fd_locks(struct seq_file *f,
			 struct file *filp, struct files_struct *files);
1105
#else /* !CONFIG_FILE_LOCKING */
1106 1107
static inline int fcntl_getlk(struct file *file, unsigned int cmd,
			      struct flock __user *user)
1108 1109 1110 1111 1112 1113 1114 1115 1116 1117
{
	return -EINVAL;
}

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

1118
#if BITS_PER_LONG == 32
1119 1120
static inline int fcntl_getlk64(struct file *file, unsigned int cmd,
				struct flock64 __user *user)
1121 1122 1123 1124 1125 1126 1127 1128 1129
{
	return -EINVAL;
}

static inline int fcntl_setlk64(unsigned int fd, struct file *file,
				unsigned int cmd, struct flock64 __user *user)
{
	return -EACCES;
}
1130
#endif
1131 1132
static inline int fcntl_setlease(unsigned int fd, struct file *filp, long arg)
{
1133
	return -EINVAL;
1134 1135 1136 1137
}

static inline int fcntl_getlease(struct file *filp)
{
1138
	return F_UNLCK;
1139 1140
}

1141
static inline void
1142
locks_free_lock_context(struct inode *inode)
1143 1144 1145
{
}

1146 1147 1148 1149 1150
static inline void locks_init_lock(struct file_lock *fl)
{
	return;
}

1151
static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl)
1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165
{
	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;
}

1166
static inline void locks_remove_file(struct file *filp)
1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181
{
	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;
}

1182
static inline int posix_unblock_lock(struct file_lock *waiter)
1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202
{
	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;
}

1203 1204 1205 1206 1207
static inline int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl)
{
	return -ENOLCK;
}

1208
static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
1209 1210 1211 1212 1213 1214 1215 1216 1217 1218
{
	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,
1219
				    struct file_lock **flp, void **priv)
1220 1221 1222 1223 1224
{
	return -EINVAL;
}

static inline int vfs_setlease(struct file *filp, long arg,
1225
			       struct file_lock **lease, void **priv)
1226 1227 1228 1229
{
	return -EINVAL;
}

1230
static inline int lease_modify(struct file_lock *fl, int arg,
1231
			       struct list_head *dispose)
1232 1233 1234
{
	return -EINVAL;
}
1235 1236 1237 1238

struct files_struct;
static inline void show_fd_locks(struct seq_file *f,
			struct file *filp, struct files_struct *files) {}
1239 1240
#endif /* !CONFIG_FILE_LOCKING */

1241 1242 1243 1244 1245
static inline struct inode *file_inode(const struct file *f)
{
	return f->f_inode;
}

Miklos Szeredi's avatar
Miklos Szeredi committed
1246 1247
static inline struct dentry *file_dentry(const struct file *file)
{
1248
	return d_real(file->f_path.dentry, file_inode(file), 0);
Miklos Szeredi's avatar
Miklos Szeredi committed
1249 1250
}

1251 1252 1253 1254 1255
static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl)
{
	return locks_lock_inode_wait(file_inode(filp), fl);
}

Linus Torvalds's avatar
Linus Torvalds committed
1256
struct fasync_struct {
1257 1258 1259 1260 1261 1262
	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;
Linus Torvalds's avatar
Linus Torvalds committed
1263 1264 1265 1266 1267 1268
};

#define FASYNC_MAGIC 0x4601

/* SMP safe fasync helpers: */
extern int fasync_helper(int, struct file *, int, struct fasync_struct **);
1269 1270 1271 1272 1273
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 *);

Linus Torvalds's avatar
Linus Torvalds committed
1274 1275 1276
/* can be called from interrupts */
extern void kill_fasync(struct fasync_struct **, int, int);

1277 1278
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);
Linus Torvalds's avatar
Linus Torvalds committed
1279
extern void f_delown(struct file *filp);
1280
extern pid_t f_getown(struct file *filp);
Linus Torvalds's avatar
Linus Torvalds committed