fs.h 106.7 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4
#ifndef _LINUX_FS_H
#define _LINUX_FS_H

#include <linux/linkage.h>
5
#include <linux/wait_bit.h>
L
Linus Torvalds 已提交
6 7
#include <linux/kdev_t.h>
#include <linux/dcache.h>
8
#include <linux/path.h>
L
Linus Torvalds 已提交
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>
L
Linus Torvalds 已提交
14
#include <linux/radix-tree.h>
15
#include <linux/rbtree.h>
L
Linus Torvalds 已提交
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/mm_types.h>
22
#include <linux/capability.h>
23
#include <linux/semaphore.h>
24
#include <linux/fcntl.h>
M
Mark Fasheh 已提交
25
#include <linux/fiemap.h>
26
#include <linux/rculist_bl.h>
27
#include <linux/atomic.h>
28
#include <linux/shrinker.h>
29
#include <linux/migrate_mode.h>
30
#include <linux/uidgid.h>
31
#include <linux/lockdep.h>
32
#include <linux/percpu-rwsem.h>
33
#include <linux/workqueue.h>
34
#include <linux/delayed_call.h>
35
#include <linux/uuid.h>
36
#include <linux/errseq.h>
L
Linus Torvalds 已提交
37 38

#include <asm/byteorder.h>
39
#include <uapi/linux/fs.h>
L
Linus Torvalds 已提交
40

41
struct backing_dev_info;
42
struct bdi_writeback;
43
struct bio;
44
struct export_operations;
45
struct hd_geometry;
L
Linus Torvalds 已提交
46
struct iovec;
47
struct kiocb;
A
Alexey Dobriyan 已提交
48
struct kobject;
L
Linus Torvalds 已提交
49 50 51 52 53
struct pipe_inode_info;
struct poll_table_struct;
struct kstatfs;
struct vm_area_struct;
struct vfsmount;
54
struct cred;
55
struct swap_info_struct;
56
struct seq_file;
57
struct workqueue_struct;
58
struct iov_iter;
59 60
struct fscrypt_info;
struct fscrypt_operations;
L
Linus Torvalds 已提交
61

62
extern void __init inode_init(void);
L
Linus Torvalds 已提交
63
extern void __init inode_init_early(void);
64 65
extern void __init files_init(void);
extern void __init files_maxfiles_init(void);
L
Linus Torvalds 已提交
66

67
extern struct files_stat_struct files_stat;
E
Eric Dumazet 已提交
68
extern unsigned long get_max_files(void);
69
extern unsigned int sysctl_nr_open;
70 71
extern struct inodes_stat_t inodes_stat;
extern int leases_enable, lease_break_time;
K
Kees Cook 已提交
72 73
extern int sysctl_protected_symlinks;
extern int sysctl_protected_hardlinks;
74

L
Linus Torvalds 已提交
75 76 77
struct buffer_head;
typedef int (get_block_t)(struct inode *inode, sector_t iblock,
			struct buffer_head *bh_result, int create);
78
typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
79
			ssize_t bytes, void *private);
L
Linus Torvalds 已提交
80

D
David Howells 已提交
81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136
#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)

137 138
/* File needs atomic accesses to f_pos */
#define FMODE_ATOMIC_POS	((__force fmode_t)0x8000)
139 140
/* Write access to underlying fs */
#define FMODE_WRITER		((__force fmode_t)0x10000)
141 142 143 144
/* Has read method(s) */
#define FMODE_CAN_READ          ((__force fmode_t)0x20000)
/* Has write method(s) */
#define FMODE_CAN_WRITE         ((__force fmode_t)0x40000)
145

D
David Howells 已提交
146
/* File was opened by fanotify and shouldn't generate fanotify events */
147
#define FMODE_NONOTIFY		((__force fmode_t)0x4000000)
D
David Howells 已提交
148

149 150 151
/* File is capable of returning -EAGAIN if AIO will block */
#define FMODE_AIO_NOWAIT	((__force fmode_t)0x8000000)

D
David Howells 已提交
152 153 154 155 156 157 158 159
/*
 * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector
 * that indicates that they should check the contents of the iovec are
 * valid, but not check the memory that the iovec elements
 * points too.
 */
#define CHECK_IOVEC_ONLY -1

L
Linus Torvalds 已提交
160 161 162 163
/*
 * Attribute flags.  These should be or-ed together to figure out what
 * has been changed!
 */
164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180
#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)
181
#define ATTR_TOUCH	(1 << 17)
L
Linus Torvalds 已提交
182

M
Miklos Szeredi 已提交
183 184 185 186 187 188 189
/*
 * 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
190 191 192 193 194 195 196 197 198 199 200 201
/*
 * 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;
202 203
	kuid_t		ia_uid;
	kgid_t		ia_gid;
L
Linus Torvalds 已提交
204 205 206 207
	loff_t		ia_size;
	struct timespec	ia_atime;
	struct timespec	ia_mtime;
	struct timespec	ia_ctime;
208 209

	/*
L
Lucas De Marchi 已提交
210
	 * Not an attribute, but an auxiliary info for filesystems wanting to
211 212 213 214
	 * 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
215 216 217 218 219 220 221
};

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

222 223 224 225 226 227
/*
 * Maximum number of layers of fs stack.  Needs to be limited to
 * prevent kernel stack overflow
 */
#define FILESYSTEM_MAX_STACK_DEPTH 2

228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245
/** 
 * 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
246
 *  			by readpage().
247 248 249 250 251 252 253 254 255 256 257 258
 *
 * 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,
};

259 260
#define AOP_FLAG_CONT_EXPAND		0x0001 /* called from cont_expand */
#define AOP_FLAG_NOFS			0x0002 /* used by filesystem to direct
261 262
						* helper code (eg buffer layer)
						* to clear GFP_FS from alloc */
263

L
Linus Torvalds 已提交
264 265 266 267 268 269 270
/*
 * oh the beauties of C type declarations.
 */
struct page;
struct address_space;
struct writeback_control;

271 272 273 274 275 276 277 278 279 280 281 282
/*
 * Write life time hint values.
 */
enum rw_hint {
	WRITE_LIFE_NOT_SET	= 0,
	WRITE_LIFE_NONE		= RWH_WRITE_LIFE_NONE,
	WRITE_LIFE_SHORT	= RWH_WRITE_LIFE_SHORT,
	WRITE_LIFE_MEDIUM	= RWH_WRITE_LIFE_MEDIUM,
	WRITE_LIFE_LONG		= RWH_WRITE_LIFE_LONG,
	WRITE_LIFE_EXTREME	= RWH_WRITE_LIFE_EXTREME,
};

283
#define IOCB_EVENTFD		(1 << 0)
284 285
#define IOCB_APPEND		(1 << 1)
#define IOCB_DIRECT		(1 << 2)
286
#define IOCB_HIPRI		(1 << 3)
287 288
#define IOCB_DSYNC		(1 << 4)
#define IOCB_SYNC		(1 << 5)
289
#define IOCB_WRITE		(1 << 6)
290
#define IOCB_NOWAIT		(1 << 7)
291 292 293 294 295 296 297

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;
298
	enum rw_hint		ki_hint;
299
} __randomize_layout;
300 301 302 303 304 305

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

306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326
/*
 * "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
327

L
Linus Torvalds 已提交
328 329 330 331 332 333 334
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 *);

335
	/* Set a page dirty.  Return true if this dirtied it */
L
Linus Torvalds 已提交
336 337 338 339 340
	int (*set_page_dirty)(struct page *page);

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

341 342 343 344 345 346 347
	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
348 349
	/* Unfortunately this kludge is needed for FIBMAP. Don't use it */
	sector_t (*bmap)(struct address_space *, sector_t);
350
	void (*invalidatepage) (struct page *, unsigned int, unsigned int);
A
Al Viro 已提交
351
	int (*releasepage) (struct page *, gfp_t);
352
	void (*freepage)(struct page *);
353
	ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter);
354
	/*
355 356
	 * migrate the contents of a page to the specified target. If
	 * migrate_mode is MIGRATE_ASYNC, it must not block.
357
	 */
358
	int (*migratepage) (struct address_space *,
359
			struct page *, struct page *, enum migrate_mode);
360 361
	bool (*isolate_page)(struct page *, isolate_mode_t);
	void (*putback_page)(struct page *);
362
	int (*launder_page) (struct page *);
363
	int (*is_partially_uptodate) (struct page *, unsigned long,
364
					unsigned long);
365
	void (*is_dirty_writeback) (struct page *, bool *, bool *);
366
	int (*error_remove_page)(struct address_space *, struct page *);
367 368

	/* swapfile support */
369 370 371
	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
372 373
};

J
Jens Axboe 已提交
374 375
extern const struct address_space_operations empty_aops;

376 377 378 379 380 381 382 383 384 385 386 387
/*
 * 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
388 389 390
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
391
	spinlock_t		tree_lock;	/* and lock protecting it */
392
	atomic_t		i_mmap_writable;/* count VM_SHARED mappings */
393
	struct rb_root		i_mmap;		/* tree of private and shared mappings */
394
	struct rw_semaphore	i_mmap_rwsem;	/* protect tree, count, list */
395
	/* Protected by tree_lock together with the radix tree */
L
Linus Torvalds 已提交
396
	unsigned long		nrpages;	/* number of total pages */
397 398
	/* number of shadow or DAX exceptional entries */
	unsigned long		nrexceptional;
L
Linus Torvalds 已提交
399
	pgoff_t			writeback_index;/* writeback starts here */
400
	const struct address_space_operations *a_ops;	/* methods */
401
	unsigned long		flags;		/* error bits */
L
Linus Torvalds 已提交
402
	spinlock_t		private_lock;	/* for use by the address_space */
403
	gfp_t			gfp_mask;	/* implicit gfp mask for allocations */
L
Linus Torvalds 已提交
404
	struct list_head	private_list;	/* ditto */
405
	void			*private_data;	/* ditto */
406
	errseq_t		wb_err;
407
} __attribute__((aligned(sizeof(long)))) __randomize_layout;
L
Linus Torvalds 已提交
408 409
	/*
	 * On most architectures that alignment is already the case; but
L
Lucas De Marchi 已提交
410
	 * must be enforced here for CRIS, to let the least significant bit
L
Linus Torvalds 已提交
411 412
	 * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON.
	 */
413
struct request_queue;
L
Linus Torvalds 已提交
414 415 416

struct block_device {
	dev_t			bd_dev;  /* not a kdev_t - it's a search key */
417
	int			bd_openers;
L
Linus Torvalds 已提交
418
	struct inode *		bd_inode;	/* will die */
419
	struct super_block *	bd_super;
420
	struct mutex		bd_mutex;	/* open/close mutex */
421
	void *			bd_claiming;
L
Linus Torvalds 已提交
422 423
	void *			bd_holder;
	int			bd_holders;
424
	bool			bd_write_holder;
425
#ifdef CONFIG_SYSFS
426
	struct list_head	bd_holder_disks;
427
#endif
L
Linus Torvalds 已提交
428 429 430 431 432 433 434
	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;
435
	struct request_queue *  bd_queue;
436
	struct backing_dev_info *bd_bdi;
L
Linus Torvalds 已提交
437 438 439 440 441 442 443 444
	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;
445 446 447 448 449

	/* The counter of freeze processes */
	int			bd_fsfreeze_count;
	/* Mutex for freeze */
	struct mutex		bd_fsfreeze_mutex;
450
} __randomize_layout;
L
Linus Torvalds 已提交
451 452 453 454 455 456 457

/*
 * Radix-tree tags, for tagging dirty and writeback pages within the pagecache
 * radix trees
 */
#define PAGECACHE_TAG_DIRTY	0
#define PAGECACHE_TAG_WRITEBACK	1
458
#define PAGECACHE_TAG_TOWRITE	2
L
Linus Torvalds 已提交
459 460 461

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

462 463
static inline void i_mmap_lock_write(struct address_space *mapping)
{
464
	down_write(&mapping->i_mmap_rwsem);
465 466 467 468
}

static inline void i_mmap_unlock_write(struct address_space *mapping)
{
469
	up_write(&mapping->i_mmap_rwsem);
470 471
}

D
Davidlohr Bueso 已提交
472 473 474 475 476 477 478 479 480 481
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
482 483 484 485 486
/*
 * Might pages of this file be mapped into userspace?
 */
static inline int mapping_mapped(struct address_space *mapping)
{
487
	return	!RB_EMPTY_ROOT(&mapping->i_mmap);
L
Linus Torvalds 已提交
488 489 490 491 492 493 494
}

/*
 * 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.
495 496 497
 *
 * 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
498 499 500
 */
static inline int mapping_writably_mapped(struct address_space *mapping)
{
501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523
	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
524 525 526 527 528 529 530 531 532 533 534 535 536
}

/*
 * 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
537 538
struct posix_acl;
#define ACL_NOT_CACHED ((void *)(-1))
539
#define ACL_DONT_CACHE ((void *)(-3))
A
Al Viro 已提交
540

541 542 543 544 545 546 547 548 549 550 551 552
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;
}

553 554 555
#define IOP_FASTPERM	0x0001
#define IOP_LOOKUP	0x0002
#define IOP_NOFOLLOW	0x0004
556
#define IOP_XATTR	0x0008
557
#define IOP_DEFAULT_READLINK	0x0010
558

559 560
struct fsnotify_mark_connector;

561 562 563 564 565
/*
 * 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
566
struct inode {
567
	umode_t			i_mode;
568
	unsigned short		i_opflags;
569 570
	kuid_t			i_uid;
	kgid_t			i_gid;
571 572 573 574 575 576 577
	unsigned int		i_flags;

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

578 579
	const struct inode_operations	*i_op;
	struct super_block	*i_sb;
580
	struct address_space	*i_mapping;
581

582 583 584
#ifdef CONFIG_SECURITY
	void			*i_security;
#endif
585

586 587
	/* Stat data, not accessed from path walking */
	unsigned long		i_ino;
M
Miklos Szeredi 已提交
588 589 590 591 592 593 594 595 596 597 598
	/*
	 * 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;
	};
599
	dev_t			i_rdev;
600
	loff_t			i_size;
601 602 603
	struct timespec		i_atime;
	struct timespec		i_mtime;
	struct timespec		i_ctime;
604 605
	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
	unsigned short          i_bytes;
606
	unsigned int		i_blkbits;
607
	enum rw_hint		i_write_hint;
608 609 610 611 612 613 614 615
	blkcnt_t		i_blocks;

#ifdef __NEED_I_SIZE_ORDERED
	seqcount_t		i_size_seqcount;
#endif

	/* Misc */
	unsigned long		i_state;
616
	struct rw_semaphore	i_rwsem;
617

618
	unsigned long		dirtied_when;	/* jiffies of first dirtying */
619
	unsigned long		dirtied_time_when;
620

L
Linus Torvalds 已提交
621
	struct hlist_node	i_hash;
622
	struct list_head	i_io_list;	/* backing dev IO list */
623 624
#ifdef CONFIG_CGROUP_WRITEBACK
	struct bdi_writeback	*i_wb;		/* the associated cgroup wb */
625 626 627 628 629

	/* foreign inode detection, see wbc_detach_inode() */
	int			i_wb_frn_winner;
	u16			i_wb_frn_avg_time;
	u16			i_wb_frn_history;
630
#endif
N
Nick Piggin 已提交
631
	struct list_head	i_lru;		/* inode LRU list */
L
Linus Torvalds 已提交
632
	struct list_head	i_sb_list;
633
	struct list_head	i_wb_list;	/* backing dev writeback list */
N
Nick Piggin 已提交
634
	union {
A
Al Viro 已提交
635
		struct hlist_head	i_dentry;
N
Nick Piggin 已提交
636 637
		struct rcu_head		i_rcu;
	};
638
	u64			i_version;
639
	atomic_t		i_count;
C
Christoph Hellwig 已提交
640
	atomic_t		i_dio_count;
641
	atomic_t		i_writecount;
M
Mimi Zohar 已提交
642 643 644
#ifdef CONFIG_IMA
	atomic_t		i_readcount; /* struct files open RO */
#endif
645
	const struct file_operations	*i_fop;	/* former ->i_op->default_file_ops */
646
	struct file_lock_context	*i_flctx;
L
Linus Torvalds 已提交
647 648
	struct address_space	i_data;
	struct list_head	i_devices;
649 650
	union {
		struct pipe_inode_info	*i_pipe;
651
		struct block_device	*i_bdev;
652
		struct cdev		*i_cdev;
A
Al Viro 已提交
653
		char			*i_link;
A
Al Viro 已提交
654
		unsigned		i_dir_seq;
655
	};
L
Linus Torvalds 已提交
656 657 658

	__u32			i_generation;

659 660
#ifdef CONFIG_FSNOTIFY
	__u32			i_fsnotify_mask; /* all events this inode cares about */
661
	struct fsnotify_mark_connector __rcu	*i_fsnotify_marks;
R
Robert Love 已提交
662 663
#endif

664 665 666 667
#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
	struct fscrypt_info	*i_crypt_info;
#endif

668
	void			*i_private; /* fs or device private pointer */
669
} __randomize_layout;
L
Linus Torvalds 已提交
670

F
Fabian Frederick 已提交
671 672 673 674 675
static inline unsigned int i_blocksize(const struct inode *node)
{
	return (1 << node->i_blkbits);
}

A
Al Viro 已提交
676 677 678 679 680
static inline int inode_unhashed(struct inode *inode)
{
	return hlist_unhashed(&inode->i_hash);
}

I
Ingo Molnar 已提交
681 682 683 684 685 686
/*
 * inode->i_mutex nesting subclasses for the lock validator:
 *
 * 0: the object of the current VFS operation
 * 1: parent
 * 2: child/target
687 688
 * 3: xattr
 * 4: second non-directory
689 690 691
 * 5: second parent (when locking independent directories in rename)
 *
 * I_MUTEX_NONDIR2 is for certain operations (such as rename) which lock two
692
 * non-directories at once.
I
Ingo Molnar 已提交
693 694
 *
 * The locking order between these classes is
695
 * parent[2] -> child -> grandchild -> normal -> xattr -> second non-directory
I
Ingo Molnar 已提交
696 697 698 699 700 701
 */
enum inode_i_mutex_lock_class
{
	I_MUTEX_NORMAL,
	I_MUTEX_PARENT,
	I_MUTEX_CHILD,
I
Ingo Molnar 已提交
702
	I_MUTEX_XATTR,
703 704
	I_MUTEX_NONDIR2,
	I_MUTEX_PARENT2,
I
Ingo Molnar 已提交
705 706
};

A
Al Viro 已提交
707 708
static inline void inode_lock(struct inode *inode)
{
709
	down_write(&inode->i_rwsem);
A
Al Viro 已提交
710 711 712 713
}

static inline void inode_unlock(struct inode *inode)
{
714 715 716 717 718 719 720 721 722 723 724
	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);
A
Al Viro 已提交
725 726 727 728
}

static inline int inode_trylock(struct inode *inode)
{
729 730 731 732 733 734
	return down_write_trylock(&inode->i_rwsem);
}

static inline int inode_trylock_shared(struct inode *inode)
{
	return down_read_trylock(&inode->i_rwsem);
A
Al Viro 已提交
735 736 737 738
}

static inline int inode_is_locked(struct inode *inode)
{
739
	return rwsem_is_locked(&inode->i_rwsem);
A
Al Viro 已提交
740 741 742 743
}

static inline void inode_lock_nested(struct inode *inode, unsigned subclass)
{
744
	down_write_nested(&inode->i_rwsem, subclass);
A
Al Viro 已提交
745 746
}

747 748 749
void lock_two_nondirectories(struct inode *, struct inode*);
void unlock_two_nondirectories(struct inode *, struct inode*);

L
Linus Torvalds 已提交
750 751 752 753 754 755 756 757 758 759
/*
 * 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
760
static inline loff_t i_size_read(const struct inode *inode)
L
Linus Torvalds 已提交
761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782
{
#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
}

783 784 785 786 787
/*
 * 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
788 789 790
static inline void i_size_write(struct inode *inode, loff_t i_size)
{
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
791
	preempt_disable();
L
Linus Torvalds 已提交
792 793 794
	write_seqcount_begin(&inode->i_size_seqcount);
	inode->i_size = i_size;
	write_seqcount_end(&inode->i_size_seqcount);
795
	preempt_enable();
L
Linus Torvalds 已提交
796 797 798 799 800 801 802 803 804
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
	preempt_disable();
	inode->i_size = i_size;
	preempt_enable();
#else
	inode->i_size = i_size;
#endif
}

J
Jan Engelhardt 已提交
805
static inline unsigned iminor(const struct inode *inode)
L
Linus Torvalds 已提交
806 807 808 809
{
	return MINOR(inode->i_rdev);
}

J
Jan Engelhardt 已提交
810
static inline unsigned imajor(const struct inode *inode)
L
Linus Torvalds 已提交
811 812 813 814 815 816 817 818
{
	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 */
819 820
	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 */
821
	kuid_t uid, euid;	/* uid/euid of process setting the owner */
L
Linus Torvalds 已提交
822 823 824 825 826 827 828
	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
829 830 831
	pgoff_t start;			/* where readahead started */
	unsigned int size;		/* # of readahead pages */
	unsigned int async_size;	/* do asynchronous readahead when
832
					   there are only # of pages ahead */
833

F
Fengguang Wu 已提交
834
	unsigned int ra_pages;		/* Maximum readahead window */
835
	unsigned int mmap_miss;		/* Cache miss stat for mmap accesses */
836
	loff_t prev_pos;		/* Cache last read() position */
L
Linus Torvalds 已提交
837 838
};

839 840 841 842 843
/*
 * Check if @index falls in the readahead windows.
 */
static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
{
844 845
	return (index >= ra->start &&
		index <  ra->start + ra->size);
846 847
}

L
Linus Torvalds 已提交
848
struct file {
E
Eric Dumazet 已提交
849
	union {
850
		struct llist_node	fu_llist;
E
Eric Dumazet 已提交
851 852
		struct rcu_head 	fu_rcuhead;
	} f_u;
853
	struct path		f_path;
854
	struct inode		*f_inode;	/* cached value */
855
	const struct file_operations	*f_op;
856 857

	/*
858
	 * Protects f_ep_links, f_flags.
859 860 861
	 * Must not be taken from IRQ context.
	 */
	spinlock_t		f_lock;
862
	enum rw_hint		f_write_hint;
A
Al Viro 已提交
863
	atomic_long_t		f_count;
L
Linus Torvalds 已提交
864
	unsigned int 		f_flags;
865
	fmode_t			f_mode;
866
	struct mutex		f_pos_lock;
L
Linus Torvalds 已提交
867 868
	loff_t			f_pos;
	struct fown_struct	f_owner;
D
David Howells 已提交
869
	const struct cred	*f_cred;
L
Linus Torvalds 已提交
870 871
	struct file_ra_state	f_ra;

872
	u64			f_version;
873
#ifdef CONFIG_SECURITY
L
Linus Torvalds 已提交
874
	void			*f_security;
875
#endif
L
Linus Torvalds 已提交
876 877 878 879 880 881
	/* 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
882
	struct list_head	f_tfile_llink;
L
Linus Torvalds 已提交
883 884
#endif /* #ifdef CONFIG_EPOLL */
	struct address_space	*f_mapping;
885
	errseq_t		f_wb_err;
886 887
} __randomize_layout
  __attribute__((aligned(4)));	/* lest something weird decides that 2 is OK */
L
Linus Torvalds 已提交
888

889 890 891 892 893 894 895
struct file_handle {
	__u32 handle_bytes;
	int handle_type;
	/* file identifier */
	unsigned char f_handle[0];
};

A
Al Viro 已提交
896 897 898 899 900
static inline struct file *get_file(struct file *f)
{
	atomic_long_inc(&f->f_count);
	return f;
}
901
#define get_file_rcu(x) atomic_long_inc_not_zero(&(x)->f_count)
902
#define fput_atomic(x)	atomic_long_add_unless(&(x)->f_count, -1, 1)
A
Al Viro 已提交
903
#define file_count(x)	atomic_long_read(&(x)->f_count)
L
Linus Torvalds 已提交
904 905 906 907 908 909

#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
910
#define MAX_LFS_FILESIZE	((loff_t)ULONG_MAX << PAGE_SHIFT)
L
Linus Torvalds 已提交
911
#elif BITS_PER_LONG==64
912
#define MAX_LFS_FILESIZE 	((loff_t)LLONG_MAX)
L
Linus Torvalds 已提交
913 914 915 916
#endif

#define FL_POSIX	1
#define FL_FLOCK	2
917
#define FL_DELEG	4	/* NFSv4 delegation */
L
Linus Torvalds 已提交
918
#define FL_ACCESS	8	/* not trying to lock, just looking */
919
#define FL_EXISTS	16	/* when unlocking, test for existence */
L
Linus Torvalds 已提交
920
#define FL_LEASE	32	/* lease held on this file */
921
#define FL_CLOSE	64	/* unlock on close */
L
Linus Torvalds 已提交
922
#define FL_SLEEP	128	/* A blocking lock */
923 924
#define FL_DOWNGRADE_PENDING	256 /* Lease is being downgraded */
#define FL_UNLOCK_PENDING	512 /* Lease is being broken */
925
#define FL_OFDLCK	1024	/* lock is "owned" by struct file */
C
Christoph Hellwig 已提交
926
#define FL_LAYOUT	2048	/* outstanding pNFS layout */
L
Linus Torvalds 已提交
927

928 929
#define FL_CLOSE_POSIX (FL_POSIX | FL_CLOSE)

930 931 932 933 934 935
/*
 * Special return value from posix_lock_file() and vfs_lock_file() for
 * asynchronous locking.
 */
#define FILE_LOCK_DEFERRED 1

936
/* legacy typedef, should eventually be removed */
937
typedef void *fl_owner_t;
L
Linus Torvalds 已提交
938

939 940
struct file_lock;

L
Linus Torvalds 已提交
941 942 943 944 945 946
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
947
	int (*lm_compare_owner)(struct file_lock *, struct file_lock *);
948
	unsigned long (*lm_owner_key)(struct file_lock *);
949 950
	fl_owner_t (*lm_get_owner)(fl_owner_t);
	void (*lm_put_owner)(fl_owner_t);
J
J. Bruce Fields 已提交
951
	void (*lm_notify)(struct file_lock *);	/* unblock callback */
952
	int (*lm_grant)(struct file_lock *, int);
J
Jeff Layton 已提交
953
	bool (*lm_break)(struct file_lock *);
954
	int (*lm_change)(struct file_lock *, int, struct list_head *);
955
	void (*lm_setup)(struct file_lock *, void **);
L
Linus Torvalds 已提交
956 957
};

958 959
struct lock_manager {
	struct list_head list;
960 961 962 963 964
	/*
	 * NFSv4 and up also want opens blocked during the grace period;
	 * NLM doesn't care:
	 */
	bool block_opens;
965 966
};

967 968
struct net;
void locks_start_grace(struct net *, struct lock_manager *);
969
void locks_end_grace(struct lock_manager *);
970
int locks_in_grace(struct net *);
971
int opens_in_grace(struct net *);
972

L
Linus Torvalds 已提交
973 974 975
/* that will die - we need it for nfs_lock_info */
#include <linux/nfs_fs_i.h>

976 977 978 979 980 981 982 983 984
/*
 * 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?
 *
985
 * The varous i_flctx lists are ordered by:
986
 *
987 988 989
 * 1) lock owner
 * 2) lock range start
 * 3) lock range end
990 991 992
 *
 * Obviously, the last two criteria only matter for POSIX locks.
 */
L
Linus Torvalds 已提交
993 994
struct file_lock {
	struct file_lock *fl_next;	/* singly linked list for this inode  */
995
	struct list_head fl_list;	/* link into file_lock_context */
996
	struct hlist_node fl_link;	/* node in global lists */
L
Linus Torvalds 已提交
997 998
	struct list_head fl_block;	/* circular list of blocked processes */
	fl_owner_t fl_owner;
999
	unsigned int fl_flags;
1000
	unsigned char fl_type;
L
Linus Torvalds 已提交
1001
	unsigned int fl_pid;
1002
	int fl_link_cpu;		/* what cpu's list is this on? */
1003
	struct pid *fl_nspid;
L
Linus Torvalds 已提交
1004 1005 1006 1007 1008 1009
	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 */
1010 1011 1012
	/* for lease breaks: */
	unsigned long fl_break_time;
	unsigned long fl_downgrade_time;
L
Linus Torvalds 已提交
1013

1014
	const struct file_lock_operations *fl_ops;	/* Callbacks for filesystems */
1015
	const struct lock_manager_operations *fl_lmops;	/* Callbacks for lockmanagers */
L
Linus Torvalds 已提交
1016 1017
	union {
		struct nfs_lock_info	nfs_fl;
1018
		struct nfs4_lock_info	nfs4_fl;
D
David Howells 已提交
1019 1020 1021 1022
		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
1023
	} fl_u;
1024
} __randomize_layout;
L
Linus Torvalds 已提交
1025

1026
struct file_lock_context {
1027
	spinlock_t		flc_lock;
1028
	struct list_head	flc_flock;
1029
	struct list_head	flc_posix;
1030
	struct list_head	flc_lease;
1031 1032
};

L
Linus Torvalds 已提交
1033 1034 1035 1036 1037 1038 1039
/* 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

1040 1041
extern void send_sigio(struct fown_struct *fown, int fd, int band);

1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053
/*
 * Return the inode to use for locking
 *
 * For overlayfs this should be the overlay inode, not the real inode returned
 * by file_inode().  For any other fs file_inode(filp) and locks_inode(filp) are
 * equal.
 */
static inline struct inode *locks_inode(const struct file *f)
{
	return f->f_path.dentry->d_inode;
}

1054
#ifdef CONFIG_FILE_LOCKING
1055
extern int fcntl_getlk(struct file *, unsigned int, struct flock *);
1056
extern int fcntl_setlk(unsigned int, struct file *, unsigned int,
1057
			struct flock *);
L
Linus Torvalds 已提交
1058 1059

#if BITS_PER_LONG == 32
1060
extern int fcntl_getlk64(struct file *, unsigned int, struct flock64 *);
1061
extern int fcntl_setlk64(unsigned int, struct file *, unsigned int,
1062
			struct flock64 *);
L
Linus Torvalds 已提交
1063 1064 1065 1066 1067 1068
#endif

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

/* fs/locks.c */
1069
void locks_free_lock_context(struct inode *inode);
1070
void locks_free_lock(struct file_lock *fl);
L
Linus Torvalds 已提交
1071
extern void locks_init_lock(struct file_lock *);
1072
extern struct file_lock * locks_alloc_lock(void);
L
Linus Torvalds 已提交
1073
extern void locks_copy_lock(struct file_lock *, struct file_lock *);
1074
extern void locks_copy_conflock(struct file_lock *, struct file_lock *);
L
Linus Torvalds 已提交
1075
extern void locks_remove_posix(struct file *, fl_owner_t);
1076
extern void locks_remove_file(struct file *);
1077
extern void locks_release_private(struct file_lock *);
1078
extern void posix_test_lock(struct file *, struct file_lock *);
1079
extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *);
1080
extern int posix_unblock_lock(struct file_lock *);
1081
extern int vfs_test_lock(struct file *, struct file_lock *);
1082
extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *);
M
Marc Eshel 已提交
1083
extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
1084
extern int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl);
J
J. Bruce Fields 已提交
1085
extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type);
L
Linus Torvalds 已提交
1086
extern void lease_get_mtime(struct inode *, struct timespec *time);
1087 1088
extern int generic_setlease(struct file *, long, struct file_lock **, void **priv);
extern int vfs_setlease(struct file *, long, struct file_lock **, void **);
1089
extern int lease_modify(struct file_lock *, int, struct list_head *);
1090 1091 1092
struct files_struct;
extern void show_fd_locks(struct seq_file *f,
			 struct file *filp, struct files_struct *files);
1093
#else /* !CONFIG_FILE_LOCKING */
1094 1095
static inline int fcntl_getlk(struct file *file, unsigned int cmd,
			      struct flock __user *user)
1096 1097 1098 1099 1100 1101 1102 1103 1104 1105
{
	return -EINVAL;
}

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

1106
#if BITS_PER_LONG == 32
1107 1108
static inline int fcntl_getlk64(struct file *file, unsigned int cmd,
				struct flock64 __user *user)
1109 1110 1111 1112 1113 1114 1115 1116 1117
{
	return -EINVAL;
}

static inline int fcntl_setlk64(unsigned int fd, struct file *file,
				unsigned int cmd, struct flock64 __user *user)
{
	return -EACCES;
}
1118
#endif
1119 1120
static inline int fcntl_setlease(unsigned int fd, struct file *filp, long arg)
{
1121
	return -EINVAL;
1122 1123 1124 1125
}

static inline int fcntl_getlease(struct file *filp)
{
1126
	return F_UNLCK;
1127 1128
}

1129
static inline void
1130
locks_free_lock_context(struct inode *inode)
1131 1132 1133
{
}

1134 1135 1136 1137 1138
static inline void locks_init_lock(struct file_lock *fl)
{
	return;
}

1139
static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl)
1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153
{
	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;
}

1154
static inline void locks_remove_file(struct file *filp)
1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169
{
	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;
}

1170
static inline int posix_unblock_lock(struct file_lock *waiter)
1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190
{
	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;
}

1191 1192 1193 1194 1195
static inline int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl)
{
	return -ENOLCK;
}

J
J. Bruce Fields 已提交
1196
static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
1197 1198 1199 1200 1201 1202 1203 1204 1205 1206
{
	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,
1207
				    struct file_lock **flp, void **priv)
1208 1209 1210 1211 1212
{
	return -EINVAL;
}

static inline int vfs_setlease(struct file *filp, long arg,
1213
			       struct file_lock **lease, void **priv)
1214 1215 1216 1217
{
	return -EINVAL;
}

1218
static inline int lease_modify(struct file_lock *fl, int arg,
1219
			       struct list_head *dispose)
1220 1221 1222
{
	return -EINVAL;
}
1223 1224 1225 1226

struct files_struct;
static inline void show_fd_locks(struct seq_file *f,
			struct file *filp, struct files_struct *files) {}
1227 1228
#endif /* !CONFIG_FILE_LOCKING */

1229 1230 1231 1232 1233
static inline struct inode *file_inode(const struct file *f)
{
	return f->f_inode;
}

M
Miklos Szeredi 已提交
1234 1235
static inline struct dentry *file_dentry(const struct file *file)
{
1236
	return d_real(file->f_path.dentry, file_inode(file), 0);
M
Miklos Szeredi 已提交
1237 1238
}

1239 1240
static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl)
{
1241
	return locks_lock_inode_wait(locks_inode(filp), fl);
1242 1243
}

L
Linus Torvalds 已提交
1244
struct fasync_struct {
1245 1246 1247 1248 1249 1250
	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
1251 1252 1253 1254 1255 1256
};

#define FASYNC_MAGIC 0x4601

/* SMP safe fasync helpers: */
extern int fasync_helper(int, struct file *, int, struct fasync_struct **);
1257 1258 1259 1260 1261
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
1262 1263 1264
/* can be called from interrupts */
extern void kill_fasync(struct fasync_struct **, int, int);

1265
extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
1266
extern int f_setown(struct file *filp, unsigned long arg, int force);
L
Linus Torvalds 已提交
1267
extern void f_delown(struct file *filp);
1268
extern pid_t f_getown(struct file *filp);
L
Linus Torvalds 已提交
1269 1270
extern int send_sigurg(struct fown_struct *fown);

1271 1272
struct mm_struct;

L
Linus Torvalds 已提交
1273 1274 1275 1276 1277 1278 1279
/*
 *	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 */
1280 1281
#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
1282

1283 1284
/* sb->s_iflags */
#define SB_I_CGROUPWB	0x00000001	/* cgroup-aware writeback enabled */
1285
#define SB_I_NOEXEC	0x00000002	/* Ignore executables on this fs */
1286
#define SB_I_NODEV	0x00000004	/* Ignore devices on this fs */
L
Linus Torvalds 已提交
1287

1288 1289
/* sb->s_iflags to limit user namespace mounts */
#define SB_I_USERNS_VISIBLE		0x00000010 /* fstype already mounted */
L
Linus Torvalds 已提交
1290

1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303
/* 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 {
1304 1305 1306
	int				frozen;		/* Is sb frozen? */
	wait_queue_head_t		wait_unfrozen;	/* for get_super_thawed() */
	struct percpu_rw_semaphore	rw_sem[SB_FREEZE_LEVELS];
1307 1308
};

L
Linus Torvalds 已提交
1309 1310 1311
struct super_block {
	struct list_head	s_list;		/* Keep this first */
	dev_t			s_dev;		/* search index; _not_ kdev_t */
1312 1313
	unsigned char		s_blocksize_bits;
	unsigned long		s_blocksize;
1314
	loff_t			s_maxbytes;	/* Max file size */
L
Linus Torvalds 已提交
1315
	struct file_system_type	*s_type;
1316
	const struct super_operations	*s_op;
1317
	const struct dquot_operations	*dq_op;
1318
	const struct quotactl_ops	*s_qcop;
1319
	const struct export_operations *s_export_op;
L
Linus Torvalds 已提交
1320
	unsigned long		s_flags;
1321
	unsigned long		s_iflags;	/* internal SB_I_* flags */
L
Linus Torvalds 已提交
1322 1323 1324 1325 1326
	unsigned long		s_magic;
	struct dentry		*s_root;
	struct rw_semaphore	s_umount;
	int			s_count;
	atomic_t		s_active;
1327
#ifdef CONFIG_SECURITY
L
Linus Torvalds 已提交
1328
	void                    *s_security;
1329
#endif
1330
	const struct xattr_handler **s_xattr;
L
Linus Torvalds 已提交
1331

1332 1333
	const struct fscrypt_operations	*s_cop;

1334
	struct hlist_bl_head	s_anon;		/* anonymous dentries for (nfs) exporting */
1335
	struct list_head	s_mounts;	/* list of mounts; _not_ for fs use */
L
Linus Torvalds 已提交
1336
	struct block_device	*s_bdev;
J
Jens Axboe 已提交
1337
	struct backing_dev_info *s_bdi;
1338
	struct mtd_info		*s_mtd;
A
Al Viro 已提交
1339
	struct hlist_node	s_instances;
1340
	unsigned int		s_quota_types;	/* Bitmask of supported quota types */
L
Linus Torvalds 已提交
1341 1342
	struct quota_info	s_dquot;	/* Diskquota specific options */

1343
	struct sb_writers	s_writers;
L
Linus Torvalds 已提交
1344

1345 1346
	char			s_id[32];	/* Informational name */
	uuid_t			s_uuid;		/* UUID */
L
Linus Torvalds 已提交
1347 1348

	void 			*s_fs_info;	/* Filesystem private info */
1349
	unsigned int		s_max_links;
1350
	fmode_t			s_mode;
L
Linus Torvalds 已提交
1351

1352 1353 1354 1355
	/* Granularity of c/m/atime in ns.
	   Cannot be worse than a second */
	u32		   s_time_gran;

L
Linus Torvalds 已提交
1356 1357 1358 1359
	/*
	 * The next field is for VFS *only*. No filesystems have any business
	 * even looking at it. You had been warned.
	 */
1360
	struct mutex s_vfs_rename_mutex;	/* Kludge */
L
Linus Torvalds 已提交
1361

M
Miklos Szeredi 已提交
1362 1363 1364 1365 1366
	/*
	 * Filesystem subtype.  If non-empty the filesystem type field
	 * in /proc/mounts will be "type.subtype"
	 */
	char *s_subtype;
1367

A
Al Viro 已提交
1368
	const struct dentry_operations *s_d_op; /* default d_op for dentries */
1369 1370 1371 1372 1373

	/*
	 * Saved pool identifier for cleancache (-1 means none)
	 */
	int cleancache_poolid;
1374 1375

	struct shrinker s_shrink;	/* per-sb shrinker handle */
1376

M
Miklos Szeredi 已提交
1377 1378 1379
	/* Number of inodes with nlink == 0 but still referenced */
	atomic_long_t s_remove_count;

1380 1381
	/* Being remounted read-only */
	int s_readonly_remount;
1382 1383 1384

	/* AIO completions deferred from interrupt context */
	struct workqueue_struct *s_dio_done_wq;
A
Al Viro 已提交
1385
	struct hlist_head s_pins;
1386

1387 1388 1389 1390 1391 1392 1393
	/*
	 * Owning user namespace and default context in which to
	 * interpret filesystem uids, gids, quotas, device nodes,
	 * xattrs and security labels.
	 */
	struct user_namespace *s_user_ns;

1394 1395 1396 1397 1398 1399
	/*
	 * 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
1400
	struct rcu_head		rcu;
1401
	struct work_struct	destroy_work;
1402

1403
	struct mutex		s_sync_lock;	/* sync serialisation lock */
1404 1405 1406 1407 1408

	/*
	 * Indicates how deep in a filesystem stack this SB is
	 */
	int s_stack_depth;
1409 1410 1411 1412

	/* s_inode_list_lock protects s_inodes */
	spinlock_t		s_inode_list_lock ____cacheline_aligned_in_smp;
	struct list_head	s_inodes;	/* all inodes */
1413 1414 1415

	spinlock_t		s_inode_wblist_lock;
	struct list_head	s_inodes_wb;	/* writeback inodes */
1416
} __randomize_layout;
L
Linus Torvalds 已提交
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
/* 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(inode->i_sb->s_user_ns, inode->i_uid);
}

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

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

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

D
Deepa Dinamani 已提交
1443
extern struct timespec current_time(struct inode *inode);
L
Linus Torvalds 已提交
1444 1445 1446 1447 1448

/*
 * Snapshotting support.
 */

1449 1450 1451
void __sb_end_write(struct super_block *sb, int level);
int __sb_start_write(struct super_block *sb, int level, bool wait);

1452
#define __sb_writers_acquired(sb, lev)	\
1453
	percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_)
1454
#define __sb_writers_release(sb, lev)	\
1455
	percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_)
1456

1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562
/**
 * 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
1563 1564


1565
extern bool inode_owner_or_capable(const struct inode *inode);
1566

L
Linus Torvalds 已提交
1567 1568 1569
/*
 * VFS helper functions..
 */
A
Al Viro 已提交
1570
extern int vfs_create(struct inode *, struct dentry *, umode_t, bool);
1571
extern int vfs_mkdir(struct inode *, struct dentry *, umode_t);
A
Al Viro 已提交
1572
extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
1573
extern int vfs_symlink(struct inode *, struct dentry *, const char *);
J
J. Bruce Fields 已提交
1574
extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct inode **);
L
Linus Torvalds 已提交
1575
extern int vfs_rmdir(struct inode *, struct dentry *);
1576
extern int vfs_unlink(struct inode *, struct dentry *, struct inode **);
M
Miklos Szeredi 已提交
1577
extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int);
M
Miklos Szeredi 已提交
1578
extern int vfs_whiteout(struct inode *, struct dentry *);
L
Linus Torvalds 已提交
1579

1580 1581 1582
extern struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode,
				  int open_flag);

1583 1584 1585
/*
 * VFS file helper functions.
 */
1586
extern void inode_init_owner(struct inode *inode, const struct inode *dir,
A
Al Viro 已提交
1587
			umode_t mode);
1588
extern bool may_open_dev(const struct path *path);
M
Mark Fasheh 已提交
1589 1590 1591 1592 1593 1594 1595
/*
 * 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 */
1596 1597
	struct fiemap_extent __user *fi_extents_start; /* Start of
							fiemap_extent array */
M
Mark Fasheh 已提交
1598 1599 1600 1601 1602
};
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
1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624
/*
 * 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.
 */
1625 1626 1627 1628
struct dir_context;
typedef int (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64,
			 unsigned);

1629
struct dir_context {
A
Al Viro 已提交
1630
	const filldir_t actor;
1631
	loff_t pos;
1632
};
1633

1634
struct block_device_operations;
L
Linus Torvalds 已提交
1635 1636 1637 1638 1639 1640 1641

/* 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

1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661
/*
 * 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)


1662 1663
struct iov_iter;

L
Linus Torvalds 已提交
1664 1665 1666 1667 1668
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 *);
1669 1670
	ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
1671
	int (*iterate) (struct file *, struct dir_context *);
1672
	int (*iterate_shared) (struct file *, struct dir_context *);
L
Linus Torvalds 已提交
1673 1674 1675 1676 1677
	unsigned int (*poll) (struct file *, struct poll_table_struct *);
	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
	int (*mmap) (struct file *, struct vm_area_struct *);
	int (*open) (struct inode *, struct file *);
1678
	int (*flush) (struct file *, fl_owner_t id);
L
Linus Torvalds 已提交
1679
	int (*release) (struct inode *, struct file *);
1680
	int (*fsync) (struct file *, loff_t, loff_t, int datasync);
L
Linus Torvalds 已提交
1681 1682 1683 1684 1685 1686
	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 *);
1687 1688
	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);
1689
	int (*setlease)(struct file *, long, struct file_lock **, void **);
1690 1691
	long (*fallocate)(struct file *file, int mode, loff_t offset,
			  loff_t len);
1692
	void (*show_fdinfo)(struct seq_file *m, struct file *f);
1693 1694 1695
#ifndef CONFIG_MMU
	unsigned (*mmap_capabilities)(struct file *);
#endif
1696 1697 1698 1699
	ssize_t (*copy_file_range)(struct file *, loff_t, struct file *,
			loff_t, size_t, unsigned int);
	int (*clone_file_range)(struct file *, loff_t, struct file *, loff_t,
			u64);
1700 1701
	ssize_t (*dedupe_file_range)(struct file *, u64, u64, struct file *,
			u64);
1702
} __randomize_layout;
L
Linus Torvalds 已提交
1703 1704

struct inode_operations {
A
Al Viro 已提交
1705
	struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
1706
	const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *);
1707
	int (*permission) (struct inode *, int);
1708
	struct posix_acl * (*get_acl)(struct inode *, int);
1709 1710 1711

	int (*readlink) (struct dentry *, char __user *,int);

A
Al Viro 已提交
1712
	int (*create) (struct inode *,struct dentry *, umode_t, bool);
L
Linus Torvalds 已提交
1713 1714 1715
	int (*link) (struct dentry *,struct inode *,struct dentry *);
	int (*unlink) (struct inode *,struct dentry *);
	int (*symlink) (struct inode *,struct dentry *,const char *);
1716
	int (*mkdir) (struct inode *,struct dentry *,umode_t);
L
Linus Torvalds 已提交
1717
	int (*rmdir) (struct inode *,struct dentry *);
A
Al Viro 已提交
1718
	int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
L
Linus Torvalds 已提交
1719
	int (*rename) (struct inode *, struct dentry *,
M
Miklos Szeredi 已提交
1720
			struct inode *, struct dentry *, unsigned int);
L
Linus Torvalds 已提交
1721
	int (*setattr) (struct dentry *, struct iattr *);
1722
	int (*getattr) (const struct path *, struct kstat *, u32, unsigned int);
L
Linus Torvalds 已提交
1723
	ssize_t (*listxattr) (struct dentry *, char *, size_t);
M
Mark Fasheh 已提交
1724 1725
	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
		      u64 len);
1726
	int (*update_time)(struct inode *, struct timespec *, int);
A
Al Viro 已提交
1727
	int (*atomic_open)(struct inode *, struct dentry *,
A
Al Viro 已提交
1728
			   struct file *, unsigned open_flag,
A
Al Viro 已提交
1729
			   umode_t create_mode, int *opened);
1730
	int (*tmpfile) (struct inode *, struct dentry *, umode_t);
1731
	int (*set_acl)(struct inode *, struct posix_acl *, int);
1732
} ____cacheline_aligned;
L
Linus Torvalds 已提交
1733

1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745
static inline ssize_t call_read_iter(struct file *file, struct kiocb *kio,
				     struct iov_iter *iter)
{
	return file->f_op->read_iter(kio, iter);
}

static inline ssize_t call_write_iter(struct file *file, struct kiocb *kio,
				      struct iov_iter *iter)
{
	return file->f_op->write_iter(kio, iter);
}

1746 1747 1748 1749 1750
static inline int call_mmap(struct file *file, struct vm_area_struct *vma)
{
	return file->f_op->mmap(file, vma);
}

B
Badari Pulavarty 已提交
1751
ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
C
Christopher Yeoh 已提交
1752 1753
			      unsigned long nr_segs, unsigned long fast_segs,
			      struct iovec *fast_pointer,
1754
			      struct iovec **ret_pointer);
B
Badari Pulavarty 已提交
1755

D
Dmitry Kasatkin 已提交
1756
extern ssize_t __vfs_read(struct file *, char __user *, size_t, loff_t *);
A
Al Viro 已提交
1757
extern ssize_t __vfs_write(struct file *, const char __user *, size_t, loff_t *);
L
Linus Torvalds 已提交
1758 1759 1760
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 *,
1761
		unsigned long, loff_t *, int);
L
Linus Torvalds 已提交
1762
extern ssize_t vfs_writev(struct file *, const struct iovec __user *,
1763
		unsigned long, loff_t *, int);
1764 1765
extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
				   loff_t, size_t, unsigned int);
1766 1767 1768
extern int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in,
				      struct inode *inode_out, loff_t pos_out,
				      u64 *len, bool is_dedupe);
1769 1770
extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
		struct file *file_out, loff_t pos_out, u64 len);
1771 1772 1773
extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
					 struct inode *dest, loff_t destoff,
					 loff_t len, bool *is_same);
1774 1775
extern int vfs_dedupe_file_range(struct file *file,
				 struct file_dedupe_range *same);
L
Linus Torvalds 已提交
1776 1777 1778 1779 1780

struct super_operations {
   	struct inode *(*alloc_inode)(struct super_block *sb);
	void (*destroy_inode)(struct inode *);

1781
   	void (*dirty_inode) (struct inode *, int flags);
1782
	int (*write_inode) (struct inode *, struct writeback_control *wbc);
1783
	int (*drop_inode) (struct inode *);
A
Al Viro 已提交
1784
	void (*evict_inode) (struct inode *);
L
Linus Torvalds 已提交
1785 1786
	void (*put_super) (struct super_block *);
	int (*sync_fs)(struct super_block *sb, int wait);
1787
	int (*freeze_super) (struct super_block *);
1788
	int (*freeze_fs) (struct super_block *);
1789
	int (*thaw_super) (struct super_block *);
1790
	int (*unfreeze_fs) (struct super_block *);
1791
	int (*statfs) (struct dentry *, struct kstatfs *);
L
Linus Torvalds 已提交
1792
	int (*remount_fs) (struct super_block *, int *, char *);
1793
	void (*umount_begin) (struct super_block *);
L
Linus Torvalds 已提交
1794

1795
	int (*show_options)(struct seq_file *, struct dentry *);
1796
	int (*show_devname)(struct seq_file *, struct dentry *);
1797
	int (*show_path)(struct seq_file *, struct dentry *);
1798
	int (*show_stats)(struct seq_file *, struct dentry *);
1799
#ifdef CONFIG_QUOTA
L
Linus Torvalds 已提交
1800 1801
	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);
1802
	struct dquot **(*get_dquots)(struct inode *);
1803
#endif
1804
	int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
1805 1806 1807 1808
	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
1809 1810
};

D
David Howells 已提交
1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826
/*
 * 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 */
1827
#ifdef CONFIG_FS_DAX
1828 1829 1830 1831
#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
1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868

/*
 * 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)
1869
#define IS_DAX(inode)		((inode)->i_flags & S_DAX)
D
David Howells 已提交
1870

M
Miklos Szeredi 已提交
1871 1872 1873
#define IS_WHITEOUT(inode)	(S_ISCHR(inode->i_mode) && \
				 (inode)->i_rdev == WHITEOUT_DEV)

1874 1875 1876 1877 1878
static inline bool HAS_UNMAPPED_ID(struct inode *inode)
{
	return !uid_valid(inode->i_uid) || !gid_valid(inode->i_gid);
}

1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897
static inline enum rw_hint file_write_hint(struct file *file)
{
	if (file->f_write_hint != WRITE_LIFE_NOT_SET)
		return file->f_write_hint;

	return file_inode(file)->i_write_hint;
}

static inline int iocb_flags(struct file *file);

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

J
Joern Engel 已提交
1898
/*
1899
 * Inode state bits.  Protected by inode->i_lock
J
Joern Engel 已提交
1900 1901 1902 1903 1904 1905 1906 1907
 *
 * 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
1908
 * Two bits are used for locking and completion notification, I_NEW and I_SYNC.
J
Joern Engel 已提交
1909
 *
J
Joern Engel 已提交
1910 1911
 * I_DIRTY_SYNC		Inode is dirty, but doesn't have to be written on
 *			fdatasync().  i_atime is the usual cause.
1912 1913 1914 1915
 * 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
1916
 * I_DIRTY_PAGES	Inode has dirty pages.  Inode itself may be clean.
C
Christoph Hellwig 已提交
1917 1918 1919 1920 1921 1922 1923 1924
 * 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
1925 1926 1927 1928 1929 1930
 * 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.
1931 1932
 * 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
1933 1934 1935 1936 1937
 *
 *			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
1938
 *			if appropriate.  I_NEW is used for waiting.
J
Joern Engel 已提交
1939
 *
1940 1941 1942 1943
 * 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
1944
 *
C
Christoph Hellwig 已提交
1945 1946 1947 1948
 * 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().
 *
1949 1950 1951 1952 1953
 * I_WB_SWITCH		Cgroup bdi_writeback switching in progress.  Used to
 *			synchronize competing switching instances and to tell
 *			wb stat updates to grab mapping->tree_lock.  See
 *			inode_switch_wb_work_fn() for details.
 *
1954 1955 1956
 * I_OVL_INUSE		Used by overlayfs to get exclusive ownership on upper
 *			and work dirs among overlayfs mounts.
 *
J
Joern Engel 已提交
1957 1958
 * Q: What is the difference between I_WILL_FREE and I_FREEING?
 */
1959 1960 1961
#define I_DIRTY_SYNC		(1 << 0)
#define I_DIRTY_DATASYNC	(1 << 1)
#define I_DIRTY_PAGES		(1 << 2)
C
Christoph Hellwig 已提交
1962 1963
#define __I_NEW			3
#define I_NEW			(1 << __I_NEW)
1964 1965 1966
#define I_WILL_FREE		(1 << 4)
#define I_FREEING		(1 << 5)
#define I_CLEAR			(1 << 6)
C
Christoph Hellwig 已提交
1967
#define __I_SYNC		7
J
Joern Engel 已提交
1968
#define I_SYNC			(1 << __I_SYNC)
1969
#define I_REFERENCED		(1 << 8)
C
Christoph Hellwig 已提交
1970
#define __I_DIO_WAKEUP		9
E
Eric Sandeen 已提交
1971
#define I_DIO_WAKEUP		(1 << __I_DIO_WAKEUP)
1972
#define I_LINKABLE		(1 << 10)
1973 1974 1975
#define I_DIRTY_TIME		(1 << 11)
#define __I_DIRTY_TIME_EXPIRED	12
#define I_DIRTY_TIME_EXPIRED	(1 << __I_DIRTY_TIME_EXPIRED)
1976
#define I_WB_SWITCH		(1 << 13)
1977
#define I_OVL_INUSE			(1 << 14)
L
Linus Torvalds 已提交
1978 1979

#define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES)
1980
#define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME)
L
Linus Torvalds 已提交
1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992

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
1993 1994 1995 1996
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);
1997 1998 1999 2000

static inline void inode_inc_link_count(struct inode *inode)
{
	inc_nlink(inode);
2001 2002 2003
	mark_inode_dirty(inode);
}

2004 2005 2006
static inline void inode_dec_link_count(struct inode *inode)
{
	drop_nlink(inode);
2007 2008 2009
	mark_inode_dirty(inode);
}

2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024
/**
 * 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);
}

2025 2026 2027 2028 2029 2030 2031
enum file_time_flags {
	S_ATIME = 1,
	S_MTIME = 2,
	S_CTIME = 4,
	S_VERSION = 8,
};

A
Al Viro 已提交
2032
extern void touch_atime(const struct path *);
L
Linus Torvalds 已提交
2033 2034 2035
static inline void file_accessed(struct file *file)
{
	if (!(file->f_flags & O_NOATIME))
A
Al Viro 已提交
2036
		touch_atime(&file->f_path);
L
Linus Torvalds 已提交
2037 2038 2039
}

int sync_inode(struct inode *inode, struct writeback_control *wbc);
C
Christoph Hellwig 已提交
2040
int sync_inode_metadata(struct inode *inode, int wait);
L
Linus Torvalds 已提交
2041 2042 2043 2044

struct file_system_type {
	const char *name;
	int fs_flags;
D
David Howells 已提交
2045 2046 2047
#define FS_REQUIRES_DEV		1 
#define FS_BINARY_MOUNTDATA	2
#define FS_HAS_SUBTYPE		4
2048
#define FS_USERNS_MOUNT		8	/* Can be mounted by userns root */
D
David Howells 已提交
2049
#define FS_RENAME_DOES_D_MOVE	32768	/* FS will handle d_move() during rename() internally. */
A
Al Viro 已提交
2050 2051
	struct dentry *(*mount) (struct file_system_type *, int,
		       const char *, void *);
L
Linus Torvalds 已提交
2052 2053 2054
	void (*kill_sb) (struct super_block *);
	struct module *owner;
	struct file_system_type * next;
A
Al Viro 已提交
2055
	struct hlist_head fs_supers;
2056

I
Ingo Molnar 已提交
2057
	struct lock_class_key s_lock_key;
2058
	struct lock_class_key s_umount_key;
2059
	struct lock_class_key s_vfs_rename_key;
2060
	struct lock_class_key s_writers_key[SB_FREEZE_LEVELS];
2061 2062 2063

	struct lock_class_key i_lock_key;
	struct lock_class_key i_mutex_key;
2064
	struct lock_class_key i_mutex_dir_key;
L
Linus Torvalds 已提交
2065 2066
};

2067 2068
#define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME)

2069 2070 2071
extern struct dentry *mount_ns(struct file_system_type *fs_type,
	int flags, void *data, void *ns, struct user_namespace *user_ns,
	int (*fill_super)(struct super_block *, void *, int));
A
Al Viro 已提交
2072 2073 2074
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
2075 2076 2077
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
2078 2079 2080
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
2081
extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path);
L
Linus Torvalds 已提交
2082 2083 2084 2085 2086
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
2087
void deactivate_locked_super(struct super_block *sb);
L
Linus Torvalds 已提交
2088
int set_anon_super(struct super_block *s, void *data);
2089 2090
int get_anon_bdev(dev_t *);
void free_anon_bdev(dev_t);
2091 2092 2093 2094 2095
struct super_block *sget_userns(struct file_system_type *type,
			int (*test)(struct super_block *,void *),
			int (*set)(struct super_block *,void *),
			int flags, struct user_namespace *user_ns,
			void *data);
L
Linus Torvalds 已提交
2096 2097 2098
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
2099
			int flags, void *data);
2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112
extern struct dentry *mount_pseudo_xattr(struct file_system_type *, char *,
					 const struct super_operations *ops,
					 const struct xattr_handler **xattr,
					 const struct dentry_operations *dops,
					 unsigned long);

static inline struct dentry *
mount_pseudo(struct file_system_type *fs_type, char *name,
	     const struct super_operations *ops,
	     const struct dentry_operations *dops, unsigned long magic)
{
	return mount_pseudo_xattr(fs_type, name, ops, NULL, dops, magic);
}
L
Linus Torvalds 已提交
2113 2114 2115 2116 2117 2118

/* 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)
2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129
/*
 * 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
2130 2131 2132

extern int register_filesystem(struct file_system_type *);
extern int unregister_filesystem(struct file_system_type *);
2133 2134
extern struct vfsmount *kern_mount_data(struct file_system_type *, void *data);
#define kern_mount(type) kern_mount_data(type, NULL)
2135
extern void kern_unmount(struct vfsmount *mnt);
L
Linus Torvalds 已提交
2136 2137
extern int may_umount_tree(struct vfsmount *);
extern int may_umount(struct vfsmount *);
2138 2139
extern long do_mount(const char *, const char __user *,
		     const char *, unsigned long, void *);
2140
extern struct vfsmount *collect_mounts(const struct path *);
2141
extern void drop_collected_mounts(struct vfsmount *);
A
Al Viro 已提交
2142 2143
extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *,
			  struct vfsmount *);
A
Al Viro 已提交
2144
extern int vfs_statfs(const struct path *, struct kstatfs *);
A
Al Viro 已提交
2145 2146
extern int user_statfs(const char __user *, struct kstatfs *);
extern int fd_statfs(int, struct kstatfs *);
A
Al Viro 已提交
2147
extern int vfs_ustat(dev_t, struct kstatfs *);
2148 2149
extern int freeze_super(struct super_block *super);
extern int thaw_super(struct super_block *super);
2150
extern bool our_mnt(struct vfsmount *mnt);
2151 2152 2153
extern __printf(2, 3)
int super_setup_bdi_name(struct super_block *sb, char *fmt, ...);
extern int super_setup_bdi(struct super_block *sb);
L
Linus Torvalds 已提交
2154

A
Al Viro 已提交
2155 2156
extern int current_umask(void);

2157 2158
extern void ihold(struct inode * inode);
extern void iput(struct inode *);
2159
extern int generic_update_time(struct inode *, struct timespec *, int);
2160

M
Miklos Szeredi 已提交
2161
/* /sys/fs */
2162
extern struct kobject *fs_kobj;
M
Miklos Szeredi 已提交
2163

2164
#define MAX_RW_COUNT (INT_MAX & PAGE_MASK)
2165

2166
#ifdef CONFIG_MANDATORY_FILE_LOCKING
2167
extern int locks_mandatory_locked(struct file *);
2168
extern int locks_mandatory_area(struct inode *, struct file *, loff_t, loff_t, unsigned char);
L
Linus Torvalds 已提交
2169 2170 2171 2172 2173

/*
 * Candidates for mandatory locking have the setgid bit set
 * but no group execute bit -  an otherwise meaningless combination.
 */
2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188

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
2189

2190
static inline int locks_verify_locked(struct file *file)
L
Linus Torvalds 已提交
2191
{
2192
	if (mandatory_lock(locks_inode(file)))
2193
		return locks_mandatory_locked(file);
L
Linus Torvalds 已提交
2194 2195 2196 2197
	return 0;
}

static inline int locks_verify_truncate(struct inode *inode,
2198
				    struct file *f,
L
Linus Torvalds 已提交
2199 2200
				    loff_t size)
{
2201 2202 2203 2204 2205 2206 2207 2208 2209 2210
	if (!inode->i_flctx || !mandatory_lock(inode))
		return 0;

	if (size < inode->i_size) {
		return locks_mandatory_area(inode, f, size, inode->i_size - 1,
				F_WRLCK);
	} else {
		return locks_mandatory_area(inode, f, inode->i_size, size - 1,
				F_WRLCK);
	}
L
Linus Torvalds 已提交
2211 2212
}

2213 2214 2215 2216 2217 2218 2219
#else /* !CONFIG_MANDATORY_FILE_LOCKING */

static inline int locks_mandatory_locked(struct file *file)
{
	return 0;
}

2220 2221
static inline int locks_mandatory_area(struct inode *inode, struct file *filp,
                                       loff_t start, loff_t end, unsigned char type)
2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250
{
	return 0;
}

static inline int __mandatory_lock(struct inode *inode)
{
	return 0;
}

static inline int mandatory_lock(struct inode *inode)
{
	return 0;
}

static inline int locks_verify_locked(struct file *file)
{
	return 0;
}

static inline int locks_verify_truncate(struct inode *inode, struct file *filp,
					size_t size)
{
	return 0;
}

#endif /* CONFIG_MANDATORY_FILE_LOCKING */


#ifdef CONFIG_FILE_LOCKING
L
Linus Torvalds 已提交
2251 2252
static inline int break_lease(struct inode *inode, unsigned int mode)
{
2253 2254
	/*
	 * Since this check is lockless, we must ensure that any refcounts
2255 2256 2257
	 * 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.
2258 2259
	 */
	smp_mb();
2260
	if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
J
J. Bruce Fields 已提交
2261
		return __break_lease(inode, mode, FL_LEASE);
L
Linus Torvalds 已提交
2262 2263
	return 0;
}
J
J. Bruce Fields 已提交
2264 2265 2266

static inline int break_deleg(struct inode *inode, unsigned int mode)
{
2267 2268
	/*
	 * Since this check is lockless, we must ensure that any refcounts
2269 2270 2271
	 * 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.
2272 2273
	 */
	smp_mb();
2274
	if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
J
J. Bruce Fields 已提交
2275
		return __break_lease(inode, mode, FL_DELEG);
L
Linus Torvalds 已提交
2276 2277
	return 0;
}
J
J. Bruce Fields 已提交
2278

2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300
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
2301 2302 2303 2304 2305 2306 2307 2308 2309 2310
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;
}

2311
#else /* !CONFIG_FILE_LOCKING */
2312 2313 2314 2315 2316
static inline int break_lease(struct inode *inode, unsigned int mode)
{
	return 0;
}

J
J. Bruce Fields 已提交
2317 2318 2319 2320
static inline int break_deleg(struct inode *inode, unsigned int mode)
{
	return 0;
}
2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332

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
2333 2334 2335 2336 2337
static inline int break_layout(struct inode *inode, bool wait)
{
	return 0;
}

2338
#endif /* CONFIG_FILE_LOCKING */
L
Linus Torvalds 已提交
2339 2340

/* fs/open.c */
2341
struct audit_names;
2342
struct filename {
2343 2344 2345
	const char		*name;	/* pointer to actual string */
	const __user char	*uptr;	/* original userland pointer */
	struct audit_names	*aname;
2346
	int			refcnt;
A
Al Viro 已提交
2347
	const char		iname[];
2348
};
L
Linus Torvalds 已提交
2349

A
Al Viro 已提交
2350
extern long vfs_truncate(const struct path *, loff_t);
2351 2352
extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs,
		       struct file *filp);
2353
extern int vfs_fallocate(struct file *file, int mode, loff_t offset,
2354
			loff_t len);
J
Jason Uhlenkott 已提交
2355
extern long do_sys_open(int dfd, const char __user *filename, int flags,
2356
			umode_t mode);
2357
extern struct file *file_open_name(struct filename *, int, umode_t);
2358
extern struct file *filp_open(const char *, int, umode_t);
A
Al Viro 已提交
2359
extern struct file *file_open_root(struct dentry *, struct vfsmount *,
2360
				   const char *, int, umode_t);
2361
extern struct file * dentry_open(const struct path *, int, const struct cred *);
L
Linus Torvalds 已提交
2362
extern int filp_close(struct file *, fl_owner_t id);
2363

2364
extern struct filename *getname_flags(const char __user *, int, int *);
2365
extern struct filename *getname(const char __user *);
2366
extern struct filename *getname_kernel(const char *);
2367
extern void putname(struct filename *name);
2368

2369 2370 2371 2372
enum {
	FILE_CREATED = 1,
	FILE_OPENED = 2
};
A
Al Viro 已提交
2373 2374 2375
extern int finish_open(struct file *file, struct dentry *dentry,
			int (*open)(struct inode *, struct file *),
			int *opened);
A
Al Viro 已提交
2376
extern int finish_no_open(struct file *file, struct dentry *dentry);
L
Linus Torvalds 已提交
2377

2378 2379 2380 2381
/* fs/ioctl.c */

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

L
Linus Torvalds 已提交
2382 2383
/* fs/dcache.c */
extern void __init vfs_caches_init_early(void);
2384
extern void __init vfs_caches_init(void);
L
Linus Torvalds 已提交
2385

2386 2387
extern struct kmem_cache *names_cachep;

2388
#define __getname()		kmem_cache_alloc(names_cachep, GFP_KERNEL)
V
Vegard Nossum 已提交
2389
#define __putname(name)		kmem_cache_free(names_cachep, (void *)(name))
L
Linus Torvalds 已提交
2390

2391
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2392
extern int register_blkdev(unsigned int, const char *);
A
Akinobu Mita 已提交
2393
extern void unregister_blkdev(unsigned int, const char *);
2394
extern void bdev_unhash_inode(dev_t dev);
L
Linus Torvalds 已提交
2395
extern struct block_device *bdget(dev_t);
2396
extern struct block_device *bdgrab(struct block_device *bdev);
L
Linus Torvalds 已提交
2397 2398 2399
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
2400
extern void invalidate_bdev(struct block_device *);
2401
extern void iterate_bdevs(void (*)(struct block_device *, void *), void *);
N
Nick Piggin 已提交
2402
extern int sync_blockdev(struct block_device *bdev);
A
Al Viro 已提交
2403
extern void kill_bdev(struct block_device *);
N
Nick Piggin 已提交
2404
extern struct super_block *freeze_bdev(struct block_device *);
2405
extern void emergency_thaw_all(void);
N
Nick Piggin 已提交
2406 2407
extern int thaw_bdev(struct block_device *bdev, struct super_block *sb);
extern int fsync_bdev(struct block_device *);
T
Tejun Heo 已提交
2408 2409 2410 2411 2412 2413 2414

extern struct super_block *blockdev_superblock;

static inline bool sb_is_blkdev_sb(struct super_block *sb)
{
	return sb == blockdev_superblock;
}
2415 2416
#else
static inline void bd_forget(struct inode *inode) {}
2417
static inline int sync_blockdev(struct block_device *bdev) { return 0; }
A
Al Viro 已提交
2418
static inline void kill_bdev(struct block_device *bdev) {}
2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429
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;
}
2430 2431 2432 2433

static inline void iterate_bdevs(void (*f)(struct block_device *, void *), void *arg)
{
}
2434

2435
static inline bool sb_is_blkdev_sb(struct super_block *sb)
2436
{
2437
	return false;
2438
}
2439
#endif
2440
extern int sync_filesystem(struct super_block *);
2441
extern const struct file_operations def_blk_fops;
2442
extern const struct file_operations def_chr_fops;
2443
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2444
extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long);
2445
extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long);
L
Linus Torvalds 已提交
2446
extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long);
2447
extern int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder);
2448 2449 2450 2451
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
2452
extern void blkdev_put(struct block_device *bdev, fmode_t mode);
2453 2454 2455
extern int __blkdev_reread_part(struct block_device *bdev);
extern int blkdev_reread_part(struct block_device *bdev);

2456
#ifdef CONFIG_SYSFS
2457
extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk);
2458 2459
extern void bd_unlink_disk_holder(struct block_device *bdev,
				  struct gendisk *disk);
2460
#else
2461 2462 2463 2464 2465
static inline int bd_link_disk_holder(struct block_device *bdev,
				      struct gendisk *disk)
{
	return 0;
}
2466 2467 2468 2469
static inline void bd_unlink_disk_holder(struct block_device *bdev,
					 struct gendisk *disk)
{
}
2470
#endif
2471
#endif
L
Linus Torvalds 已提交
2472 2473

/* fs/char_dev.c */
2474
#define CHRDEV_MAJOR_HASH_SIZE	255
2475 2476
/* Marks the bottom of the first segment of free char majors */
#define CHRDEV_MAJOR_DYN_END 234
L
Linus Torvalds 已提交
2477 2478
extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *);
extern int register_chrdev_region(dev_t, unsigned, const char *);
2479 2480 2481 2482 2483
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
2484
extern void unregister_chrdev_region(dev_t, unsigned);
2485
extern void chrdev_show(struct seq_file *,off_t);
L
Linus Torvalds 已提交
2486

2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497
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
2498 2499
/* fs/block_dev.c */
#define BDEVNAME_SIZE	32	/* Largest string for a blockdev identifier */
2500
#define BDEVT_SIZE	10	/* Largest string for MAJ:MIN for blkdev */
2501 2502 2503

#ifdef CONFIG_BLOCK
#define BLKDEV_MAJOR_HASH_SIZE	255
L
Linus Torvalds 已提交
2504 2505 2506
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 *);
2507
extern void blkdev_show(struct seq_file *,off_t);
2508

2509 2510 2511
#else
#define BLKDEV_MAJOR_HASH_SIZE	0
#endif
L
Linus Torvalds 已提交
2512 2513 2514 2515 2516

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 *);
2517
extern bool is_bad_inode(struct inode *);
L
Linus Torvalds 已提交
2518

2519
#ifdef CONFIG_BLOCK
2520 2521
extern void check_disk_size_change(struct gendisk *disk,
				   struct block_device *bdev);
2522
extern int revalidate_disk(struct gendisk *);
L
Linus Torvalds 已提交
2523
extern int check_disk_change(struct block_device *);
2524
extern int __invalidate_device(struct block_device *, bool);
L
Linus Torvalds 已提交
2525
extern int invalidate_partition(struct gendisk *, int);
2526
#endif
L
Linus Torvalds 已提交
2527 2528
unsigned long invalidate_mapping_pages(struct address_space *mapping,
					pgoff_t start, pgoff_t end);
2529

L
Linus Torvalds 已提交
2530 2531 2532 2533
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))
2534
		invalidate_mapping_pages(inode->i_mapping, 0, -1);
L
Linus Torvalds 已提交
2535 2536 2537 2538 2539 2540 2541 2542
}
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 *);
2543
extern int filemap_fdatawait_keep_errors(struct address_space *mapping);
2544 2545
extern int filemap_fdatawait_range(struct address_space *, loff_t lstart,
				   loff_t lend);
2546 2547
extern bool filemap_range_has_page(struct address_space *, loff_t lstart,
				  loff_t lend);
L
Linus Torvalds 已提交
2548 2549 2550
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);
2551 2552
extern int __filemap_fdatawrite_range(struct address_space *mapping,
				loff_t start, loff_t end, int sync_mode);
2553 2554
extern int filemap_fdatawrite_range(struct address_space *mapping,
				loff_t start, loff_t end);
2555
extern int filemap_check_errors(struct address_space *mapping);
2556

2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612
extern void __filemap_set_wb_err(struct address_space *mapping, int err);
extern int __must_check file_check_and_advance_wb_err(struct file *file);
extern int __must_check file_write_and_wait_range(struct file *file,
						loff_t start, loff_t end);

/**
 * filemap_set_wb_err - set a writeback error on an address_space
 * @mapping: mapping in which to set writeback error
 * @err: error to be set in mapping
 *
 * When writeback fails in some way, we must record that error so that
 * userspace can be informed when fsync and the like are called.  We endeavor
 * to report errors on any file that was open at the time of the error.  Some
 * internal callers also need to know when writeback errors have occurred.
 *
 * When a writeback error occurs, most filesystems will want to call
 * filemap_set_wb_err to record the error in the mapping so that it will be
 * automatically reported whenever fsync is called on the file.
 *
 * FIXME: mention FS_* flag here?
 */
static inline void filemap_set_wb_err(struct address_space *mapping, int err)
{
	/* Fastpath for common case of no error */
	if (unlikely(err))
		__filemap_set_wb_err(mapping, err);
}

/**
 * filemap_check_wb_error - has an error occurred since the mark was sampled?
 * @mapping: mapping to check for writeback errors
 * @since: previously-sampled errseq_t
 *
 * Grab the errseq_t value from the mapping, and see if it has changed "since"
 * the given value was sampled.
 *
 * If it has then report the latest error set, otherwise return 0.
 */
static inline int filemap_check_wb_err(struct address_space *mapping,
					errseq_t since)
{
	return errseq_check(&mapping->wb_err, since);
}

/**
 * filemap_sample_wb_err - sample the current errseq_t to test for later errors
 * @mapping: mapping to be sampled
 *
 * Writeback errors are always reported relative to a particular sample point
 * in the past. This function provides those sample points.
 */
static inline errseq_t filemap_sample_wb_err(struct address_space *mapping)
{
	return errseq_sample(&mapping->wb_err);
}

2613 2614 2615
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);
2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632

/*
 * Sync the bytes written if this was a synchronous write.  Expect ki_pos
 * to already be updated for the write, and will return either the amount
 * of bytes passed in, or an error if syncing the file failed.
 */
static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count)
{
	if (iocb->ki_flags & IOCB_DSYNC) {
		int ret = vfs_fsync_range(iocb->ki_filp,
				iocb->ki_pos - count, iocb->ki_pos - 1,
				(iocb->ki_flags & IOCB_SYNC) ? 0 : 1);
		if (ret)
			return ret;
	}

	return count;
2633
}
2634

L
Linus Torvalds 已提交
2635 2636
extern void emergency_sync(void);
extern void emergency_remount(void);
2637
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2638
extern sector_t bmap(struct inode *, sector_t);
2639
#endif
2640
extern int notify_change(struct dentry *, struct iattr *, struct inode **);
2641
extern int inode_permission(struct inode *, int);
2642
extern int __inode_permission(struct inode *, int);
2643
extern int generic_permission(struct inode *, int);
M
Miklos Szeredi 已提交
2644
extern int __check_sticky(struct inode *dir, struct inode *inode);
L
Linus Torvalds 已提交
2645

2646 2647 2648 2649 2650
static inline bool execute_ok(struct inode *inode)
{
	return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode);
}

2651 2652 2653 2654 2655 2656 2657
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);
}

2658 2659 2660 2661 2662 2663 2664
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);
}

2665 2666 2667 2668 2669 2670 2671
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);
}

2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684
static inline int do_clone_file_range(struct file *file_in, loff_t pos_in,
				      struct file *file_out, loff_t pos_out,
				      u64 len)
{
	int ret;

	file_start_write(file_out);
	ret = vfs_clone_file_range(file_in, pos_in, file_out, pos_out, len);
	file_end_write(file_out);

	return ret;
}

2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706
/*
 * 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
2707
	struct inode *inode = file_inode(file);
2708 2709
	return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY;
}
L
Linus Torvalds 已提交
2710 2711 2712 2713 2714 2715 2716
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
2717
		atomic_inc(&file_inode(file)->i_writecount);
L
Linus Torvalds 已提交
2718
}
2719 2720 2721 2722 2723
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
2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743
#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
2744
extern int do_pipe_flags(int *, int);
L
Linus Torvalds 已提交
2745

2746 2747 2748
#define __kernel_read_file_id(id) \
	id(UNKNOWN, unknown)		\
	id(FIRMWARE, firmware)		\
2749
	id(FIRMWARE_PREALLOC_BUFFER, firmware)	\
2750 2751 2752 2753 2754 2755 2756 2757 2758
	id(MODULE, kernel-module)		\
	id(KEXEC_IMAGE, kexec-image)		\
	id(KEXEC_INITRAMFS, kexec-initramfs)	\
	id(POLICY, security-policy)		\
	id(MAX_ID, )

#define __fid_enumify(ENUM, dummy) READING_ ## ENUM,
#define __fid_stringify(dummy, str) #str,

2759
enum kernel_read_file_id {
2760 2761 2762 2763 2764
	__kernel_read_file_id(__fid_enumify)
};

static const char * const kernel_read_file_str[] = {
	__kernel_read_file_id(__fid_stringify)
2765 2766
};

K
Kees Cook 已提交
2767
static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id)
2768
{
2769
	if ((unsigned)id >= READING_MAX_ID)
2770 2771 2772 2773 2774
		return kernel_read_file_str[READING_UNKNOWN];

	return kernel_read_file_str[id];
}

M
Mimi Zohar 已提交
2775
extern int kernel_read(struct file *, loff_t, char *, unsigned long);
2776 2777
extern int kernel_read_file(struct file *, void **, loff_t *, loff_t,
			    enum kernel_read_file_id);
2778 2779
extern int kernel_read_file_from_path(char *, void **, loff_t *, loff_t,
				      enum kernel_read_file_id);
2780 2781
extern int kernel_read_file_from_fd(int, void **, loff_t *, loff_t,
				    enum kernel_read_file_id);
2782
extern ssize_t kernel_write(struct file *, const char *, size_t, loff_t);
A
Al Viro 已提交
2783
extern ssize_t __kernel_write(struct file *, const char *, size_t, loff_t *);
L
Linus Torvalds 已提交
2784 2785 2786
extern struct file * open_exec(const char *);
 
/* fs/dcache.c -- generic fs support functions */
Y
Yaowei Bai 已提交
2787
extern bool is_subdir(struct dentry *, struct dentry *);
2788
extern bool path_is_under(const struct path *, const struct path *);
L
Linus Torvalds 已提交
2789

M
Miklos Szeredi 已提交
2790 2791
extern char *file_path(struct file *, char *, int);

L
Linus Torvalds 已提交
2792 2793 2794
#include <linux/err.h>

/* needed for stackable file system support */
2795
extern loff_t default_llseek(struct file *file, loff_t offset, int whence);
L
Linus Torvalds 已提交
2796

2797
extern loff_t vfs_llseek(struct file *file, loff_t offset, int whence);
L
Linus Torvalds 已提交
2798

2799
extern int inode_init_always(struct super_block *, struct inode *);
L
Linus Torvalds 已提交
2800
extern void inode_init_once(struct inode *);
2801
extern void address_space_init_once(struct address_space *mapping);
L
Linus Torvalds 已提交
2802 2803 2804
extern struct inode * igrab(struct inode *);
extern ino_t iunique(struct super_block *, ino_t);
extern int inode_needs_sync(struct inode *inode);
2805
extern int generic_delete_inode(struct inode *inode);
2806 2807 2808 2809
static inline int generic_drop_inode(struct inode *inode)
{
	return !inode->i_nlink || inode_unhashed(inode);
}
L
Linus Torvalds 已提交
2810

2811 2812 2813
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
2814 2815 2816 2817 2818 2819
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);
2820 2821 2822 2823 2824
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
2825 2826
extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *);
extern int insert_inode_locked(struct inode *);
2827 2828 2829 2830 2831
#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
2832
extern void unlock_new_inode(struct inode *);
2833
extern unsigned int get_next_ino(void);
L
Linus Torvalds 已提交
2834 2835

extern void __iget(struct inode * inode);
2836
extern void iget_failed(struct inode *);
2837
extern void clear_inode(struct inode *);
C
Christoph Hellwig 已提交
2838
extern void __destroy_inode(struct inode *);
2839 2840
extern struct inode *new_inode_pseudo(struct super_block *sb);
extern struct inode *new_inode(struct super_block *sb);
2841
extern void free_inode_nonrcu(struct inode *inode);
2842
extern int should_remove_suid(struct dentry *);
2843
extern int file_remove_privs(struct file *);
L
Linus Torvalds 已提交
2844 2845

extern void __insert_inode_hash(struct inode *, unsigned long hashval);
2846 2847
static inline void insert_inode_hash(struct inode *inode)
{
L
Linus Torvalds 已提交
2848 2849
	__insert_inode_hash(inode, inode->i_ino);
}
2850 2851 2852 2853

extern void __remove_inode_hash(struct inode *);
static inline void remove_inode_hash(struct inode *inode)
{
2854
	if (!inode_unhashed(inode) && !hlist_fake(&inode->i_hash))
2855 2856 2857
		__remove_inode_hash(inode);
}

2858
extern void inode_sb_list_add(struct inode *inode);
L
Linus Torvalds 已提交
2859

2860
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2861
extern int bdev_read_only(struct block_device *);
2862
#endif
L
Linus Torvalds 已提交
2863 2864 2865 2866 2867 2868
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 *);
2869
extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *);
A
Al Viro 已提交
2870
extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *);
2871 2872
extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *);
extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *);
2873
extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *);
2874
extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t);
A
Andrew Morton 已提交
2875

2876 2877
ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos,
		int flags);
2878 2879
ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos,
		int flags);
2880

2881
/* fs/block_dev.c */
2882
extern ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to);
2883
extern ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from);
2884 2885
extern int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
			int datasync);
A
Al Viro 已提交
2886
extern void block_sync_page(struct page *page);
2887

A
Andrew Morton 已提交
2888
/* fs/splice.c */
2889
extern ssize_t generic_file_splice_read(struct file *, loff_t *,
A
Andrew Morton 已提交
2890
		struct pipe_inode_info *, size_t, unsigned int);
A
Al Viro 已提交
2891
extern ssize_t iter_file_splice_write(struct pipe_inode_info *,
2892
		struct file *, loff_t *, size_t, unsigned int);
A
Andrew Morton 已提交
2893
extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
2894
		struct file *out, loff_t *, size_t len, unsigned int flags);
2895 2896 2897
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
2898

L
Linus Torvalds 已提交
2899 2900
extern void
file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping);
2901 2902
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
2903
extern loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize);
2904
extern loff_t generic_file_llseek(struct file *file, loff_t offset, int whence);
A
Andi Kleen 已提交
2905
extern loff_t generic_file_llseek_size(struct file *file, loff_t offset,
2906
		int whence, loff_t maxsize, loff_t eof);
A
Al Viro 已提交
2907 2908
extern loff_t fixed_size_llseek(struct file *file, loff_t offset,
		int whence, loff_t size);
2909 2910
extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t);
extern loff_t no_seek_end_llseek(struct file *, loff_t, int);
L
Linus Torvalds 已提交
2911 2912 2913
extern int generic_file_open(struct inode * inode, struct file * filp);
extern int nonseekable_open(struct inode * inode, struct file * filp);

2914
#ifdef CONFIG_BLOCK
2915
typedef void (dio_submit_t)(struct bio *bio, struct inode *inode,
2916
			    loff_t file_offset);
L
Linus Torvalds 已提交
2917 2918

enum {
2919 2920 2921 2922 2923
	/* need locking between buffered and direct access */
	DIO_LOCKING	= 0x01,

	/* filesystem does not support filling holes */
	DIO_SKIP_HOLES	= 0x02,
2924 2925 2926

	/* filesystem can handle aio writes beyond i_size */
	DIO_ASYNC_EXTEND = 0x04,
2927 2928 2929

	/* inode/fs/bdev does not need truncate protection */
	DIO_SKIP_DIO_COUNT = 0x08,
L
Linus Torvalds 已提交
2930 2931
};

2932
void dio_end_io(struct bio *bio);
2933

2934 2935
ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
			     struct block_device *bdev, struct iov_iter *iter,
2936
			     get_block_t get_block,
2937 2938
			     dio_iodone_t end_io, dio_submit_t submit_io,
			     int flags);
2939

2940 2941
static inline ssize_t blockdev_direct_IO(struct kiocb *iocb,
					 struct inode *inode,
2942
					 struct iov_iter *iter,
2943
					 get_block_t get_block)
L
Linus Torvalds 已提交
2944
{
2945
	return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
2946
			get_block, NULL, NULL, DIO_LOCKING | DIO_SKIP_HOLES);
L
Linus Torvalds 已提交
2947
}
2948
#endif
L
Linus Torvalds 已提交
2949

2950
void inode_dio_wait(struct inode *inode);
2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975

/*
 * inode_dio_begin - signal start of a direct I/O requests
 * @inode: inode the direct I/O happens on
 *
 * This is called once we've finished processing a direct I/O request,
 * and is used to wake up callers waiting for direct I/O to be quiesced.
 */
static inline void inode_dio_begin(struct inode *inode)
{
	atomic_inc(&inode->i_dio_count);
}

/*
 * inode_dio_end - signal finish of a direct I/O requests
 * @inode: inode the direct I/O happens on
 *
 * This is called once we've finished processing a direct I/O request,
 * and is used to wake up callers waiting for direct I/O to be quiesced.
 */
static inline void inode_dio_end(struct inode *inode)
{
	if (atomic_dec_and_test(&inode->i_dio_count))
		wake_up_bit(&inode->i_state, __I_DIO_WAKEUP);
}
2976

2977 2978 2979
extern void inode_set_flags(struct inode *inode, unsigned int flags,
			    unsigned int mask);

2980
extern const struct file_operations generic_ro_fops;
L
Linus Torvalds 已提交
2981 2982 2983

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

A
Al Viro 已提交
2984
extern int readlink_copy(char __user *, int, const char *);
L
Linus Torvalds 已提交
2985
extern int page_readlink(struct dentry *, char __user *, int);
2986 2987 2988
extern const char *page_get_link(struct dentry *, struct inode *,
				 struct delayed_call *);
extern void page_put_link(void *);
2989
extern int __page_symlink(struct inode *inode, const char *symname, int len,
2990
		int nofs);
L
Linus Torvalds 已提交
2991
extern int page_symlink(struct inode *inode, const char *symname, int len);
2992
extern const struct inode_operations page_symlink_inode_operations;
2993
extern void kfree_link(void *);
L
Linus Torvalds 已提交
2994
extern void generic_fillattr(struct inode *, struct kstat *);
2995 2996
extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int);
extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int);
2997
void __inode_add_bytes(struct inode *inode, loff_t bytes);
L
Linus Torvalds 已提交
2998
void inode_add_bytes(struct inode *inode, loff_t bytes);
2999
void __inode_sub_bytes(struct inode *inode, loff_t bytes);
L
Linus Torvalds 已提交
3000 3001 3002
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);
3003 3004
const char *simple_get_link(struct dentry *, struct inode *,
			    struct delayed_call *);
A
Al Viro 已提交
3005
extern const struct inode_operations simple_symlink_inode_operations;
L
Linus Torvalds 已提交
3006

3007
extern int iterate_dir(struct file *, struct dir_context *);
L
Linus Torvalds 已提交
3008

3009 3010 3011 3012 3013
extern int vfs_statx(int, const char __user *, int, struct kstat *, u32);
extern int vfs_statx_fd(unsigned int, struct kstat *, u32, unsigned int);

static inline int vfs_stat(const char __user *filename, struct kstat *stat)
{
3014 3015
	return vfs_statx(AT_FDCWD, filename, AT_NO_AUTOMOUNT,
			 stat, STATX_BASIC_STATS);
3016 3017 3018
}
static inline int vfs_lstat(const char __user *name, struct kstat *stat)
{
3019
	return vfs_statx(AT_FDCWD, name, AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT,
3020 3021 3022 3023 3024
			 stat, STATX_BASIC_STATS);
}
static inline int vfs_fstatat(int dfd, const char __user *filename,
			      struct kstat *stat, int flags)
{
3025 3026
	return vfs_statx(dfd, filename, flags | AT_NO_AUTOMOUNT,
			 stat, STATX_BASIC_STATS);
3027 3028 3029 3030 3031 3032 3033
}
static inline int vfs_fstat(int fd, struct kstat *stat)
{
	return vfs_statx_fd(fd, stat, STATX_BASIC_STATS, 0);
}


M
Miklos Szeredi 已提交
3034
extern const char *vfs_get_link(struct dentry *, struct delayed_call *);
3035
extern int vfs_readlink(struct dentry *, char __user *, int);
L
Linus Torvalds 已提交
3036

3037
extern int __generic_block_fiemap(struct inode *inode,
J
Josef Bacik 已提交
3038 3039 3040
				  struct fiemap_extent_info *fieinfo,
				  loff_t start, loff_t len,
				  get_block_t *get_block);
3041 3042 3043
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
3044

3045
extern struct file_system_type *get_filesystem(struct file_system_type *fs);
3046
extern void put_filesystem(struct file_system_type *fs);
L
Linus Torvalds 已提交
3047 3048
extern struct file_system_type *get_fs_type(const char *name);
extern struct super_block *get_super(struct block_device *);
3049
extern struct super_block *get_super_thawed(struct block_device *);
3050
extern struct super_block *get_super_exclusive_thawed(struct block_device *bdev);
3051
extern struct super_block *get_active_super(struct block_device *bdev);
L
Linus Torvalds 已提交
3052
extern void drop_super(struct super_block *sb);
3053
extern void drop_super_exclusive(struct super_block *sb);
A
Al Viro 已提交
3054
extern void iterate_supers(void (*)(struct super_block *, void *), void *);
A
Al Viro 已提交
3055 3056
extern void iterate_supers_type(struct file_system_type *,
			        void (*)(struct super_block *, void *), void *);
L
Linus Torvalds 已提交
3057 3058 3059 3060

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);
3061
extern int dcache_readdir(struct file *, struct dir_context *);
3062
extern int simple_setattr(struct dentry *, struct iattr *);
3063
extern int simple_getattr(const struct path *, struct kstat *, u32, unsigned int);
3064
extern int simple_statfs(struct dentry *, struct kstatfs *);
S
Stephen Boyd 已提交
3065
extern int simple_open(struct inode *inode, struct file *file);
L
Linus Torvalds 已提交
3066 3067 3068
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 *);
3069 3070
extern int simple_rename(struct inode *, struct dentry *,
			 struct inode *, struct dentry *, unsigned int);
3071
extern int noop_fsync(struct file *, loff_t, loff_t, int);
L
Linus Torvalds 已提交
3072 3073
extern int simple_empty(struct dentry *);
extern int simple_readpage(struct file *file, struct page *page);
3074 3075 3076 3077 3078 3079
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);
3080
extern int always_delete_dentry(const struct dentry *);
A
Al Viro 已提交
3081
extern struct inode *alloc_anon_inode(struct super_block *);
3082
extern int simple_nosetlease(struct file *, long, struct file_lock **, void **);
3083
extern const struct dentry_operations simple_dentry_operations;
L
Linus Torvalds 已提交
3084

A
Al Viro 已提交
3085
extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags);
L
Linus Torvalds 已提交
3086
extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *);
3087
extern const struct file_operations simple_dir_operations;
3088
extern const struct inode_operations simple_dir_inode_operations;
3089 3090
extern void make_empty_dir_inode(struct inode *inode);
extern bool is_empty_dir_inode(struct inode *inode);
3091
struct tree_descr { const char *name; const struct file_operations *ops; int mode; };
L
Linus Torvalds 已提交
3092
struct dentry *d_alloc_name(struct dentry *, const char *);
3093 3094
extern int simple_fill_super(struct super_block *, unsigned long,
			     const struct tree_descr *);
3095
extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count);
L
Linus Torvalds 已提交
3096 3097
extern void simple_release_fs(struct vfsmount **mount, int *count);

3098 3099
extern ssize_t simple_read_from_buffer(void __user *to, size_t count,
			loff_t *ppos, const void *from, size_t available);
3100 3101
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
3102

3103
extern int __generic_file_fsync(struct file *, loff_t, loff_t, int);
3104
extern int generic_file_fsync(struct file *, loff_t, loff_t, int);
A
Al Viro 已提交
3105

3106 3107
extern int generic_check_addressable(unsigned, u64);

3108
#ifdef CONFIG_MIGRATION
3109
extern int buffer_migrate_page(struct address_space *,
3110 3111
				struct page *, struct page *,
				enum migrate_mode);
3112 3113 3114 3115
#else
#define buffer_migrate_page NULL
#endif

3116
extern int setattr_prepare(struct dentry *, struct iattr *);
N
npiggin@suse.de 已提交
3117
extern int inode_newsize_ok(const struct inode *, loff_t offset);
C
Christoph Hellwig 已提交
3118
extern void setattr_copy(struct inode *inode, const struct iattr *attr);
L
Linus Torvalds 已提交
3119

3120
extern int file_update_time(struct file *file);
L
Linus Torvalds 已提交
3121

3122 3123
static inline bool io_is_direct(struct file *filp)
{
3124
	return (filp->f_flags & O_DIRECT) || IS_DAX(filp->f_mapping->host);
3125 3126
}

3127 3128 3129 3130 3131
static inline bool vma_is_dax(struct vm_area_struct *vma)
{
	return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host);
}

3132 3133 3134 3135 3136 3137 3138
static inline int iocb_flags(struct file *file)
{
	int res = 0;
	if (file->f_flags & O_APPEND)
		res |= IOCB_APPEND;
	if (io_is_direct(file))
		res |= IOCB_DIRECT;
3139 3140 3141 3142
	if ((file->f_flags & O_DSYNC) || IS_SYNC(file->f_mapping->host))
		res |= IOCB_DSYNC;
	if (file->f_flags & __O_SYNC)
		res |= IOCB_SYNC;
3143 3144 3145
	return res;
}

3146 3147 3148 3149 3150
static inline int kiocb_set_rw_flags(struct kiocb *ki, int flags)
{
	if (unlikely(flags & ~RWF_SUPPORTED))
		return -EOPNOTSUPP;

3151 3152 3153 3154 3155
	if (flags & RWF_NOWAIT) {
		if (!(ki->ki_filp->f_mode & FMODE_AIO_NOWAIT))
			return -EOPNOTSUPP;
		ki->ki_flags |= IOCB_NOWAIT;
	}
3156 3157 3158 3159 3160 3161 3162 3163 3164
	if (flags & RWF_HIPRI)
		ki->ki_flags |= IOCB_HIPRI;
	if (flags & RWF_DSYNC)
		ki->ki_flags |= IOCB_DSYNC;
	if (flags & RWF_SYNC)
		ki->ki_flags |= (IOCB_DSYNC | IOCB_SYNC);
	return 0;
}

L
Linus Torvalds 已提交
3165 3166 3167 3168
static inline ino_t parent_ino(struct dentry *dentry)
{
	ino_t res;

N
Nick Piggin 已提交
3169 3170 3171 3172
	/*
	 * 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
3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197
	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);

3198
void simple_transaction_set(struct file *file, size_t n);
L
Linus Torvalds 已提交
3199

3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221
/*
 * 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);	\
}									\
3222
static const struct file_operations __fops = {				\
3223 3224
	.owner	 = THIS_MODULE,						\
	.open	 = __fops ## _open,					\
3225
	.release = simple_attr_release,					\
3226 3227
	.read	 = simple_attr_read,					\
	.write	 = simple_attr_write,					\
3228
	.llseek	 = generic_file_llseek,					\
3229
}
3230

3231 3232
static inline __printf(1, 2)
void __simple_attr_check_format(const char *fmt, ...)
3233 3234 3235 3236 3237
{
	/* don't do anything, just let the compiler check the arguments; */
}

int simple_attr_open(struct inode *inode, struct file *file,
3238
		     int (*get)(void *, u64 *), int (*set)(void *, u64),
3239
		     const char *fmt);
3240
int simple_attr_release(struct inode *inode, struct file *file);
3241 3242 3243 3244 3245
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
3246
struct ctl_table;
3247
int proc_nr_files(struct ctl_table *table, int write,
3248
		  void __user *buffer, size_t *lenp, loff_t *ppos);
3249 3250
int proc_nr_dentry(struct ctl_table *table, int write,
		  void __user *buffer, size_t *lenp, loff_t *ppos);
3251 3252
int proc_nr_inodes(struct ctl_table *table, int write,
		   void __user *buffer, size_t *lenp, loff_t *ppos);
3253
int __init get_filesystem_list(char *buf);
3254

N
Namhyung Kim 已提交
3255
#define __FMODE_EXEC		((__force int) FMODE_EXEC)
3256 3257
#define __FMODE_NONOTIFY	((__force int) FMODE_NONOTIFY)

A
Al Viro 已提交
3258
#define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE])
E
Eric Paris 已提交
3259
#define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \
3260
					    (flag & __FMODE_NONOTIFY)))
A
Al Viro 已提交
3261

Y
Yaowei Bai 已提交
3262
static inline bool is_sxid(umode_t mode)
3263 3264 3265 3266
{
	return (mode & S_ISUID) || ((mode & S_ISGID) && (mode & S_IXGRP));
}

M
Miklos Szeredi 已提交
3267 3268 3269 3270 3271 3272 3273 3274
static inline int check_sticky(struct inode *dir, struct inode *inode)
{
	if (!(dir->i_mode & S_ISVTX))
		return 0;

	return __check_sticky(dir, inode);
}

3275 3276
static inline void inode_has_no_xattr(struct inode *inode)
{
A
Al Viro 已提交
3277
	if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & MS_NOSEC))
3278 3279 3280
		inode->i_flags |= S_NOSEC;
}

A
Al Viro 已提交
3281 3282 3283 3284 3285
static inline bool is_root_inode(struct inode *inode)
{
	return inode == inode->i_sb->s_root->d_inode;
}

3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315
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
3316 3317
static inline bool dir_relax(struct inode *inode)
{
A
Al Viro 已提交
3318 3319
	inode_unlock(inode);
	inode_lock(inode);
A
Al Viro 已提交
3320 3321
	return !IS_DEADDIR(inode);
}
3322

A
Al Viro 已提交
3323 3324 3325 3326 3327 3328 3329
static inline bool dir_relax_shared(struct inode *inode)
{
	inode_unlock_shared(inode);
	inode_lock_shared(inode);
	return !IS_DEADDIR(inode);
}

3330
extern bool path_noexec(const struct path *path);
3331
extern void inode_nohighmem(struct inode *inode);
3332

L
Linus Torvalds 已提交
3333
#endif /* _LINUX_FS_H */