fs.h 109.1 KB
Newer Older
1
/* SPDX-License-Identifier: GPL-2.0 */
L
Linus Torvalds 已提交
2 3 4 5
#ifndef _LINUX_FS_H
#define _LINUX_FS_H

#include <linux/linkage.h>
6
#include <linux/wait_bit.h>
L
Linus Torvalds 已提交
7 8
#include <linux/kdev_t.h>
#include <linux/dcache.h>
9
#include <linux/path.h>
L
Linus Torvalds 已提交
10 11 12
#include <linux/stat.h>
#include <linux/cache.h>
#include <linux/list.h>
13
#include <linux/list_lru.h>
14
#include <linux/llist.h>
L
Linus Torvalds 已提交
15
#include <linux/radix-tree.h>
16
#include <linux/rbtree.h>
L
Linus Torvalds 已提交
17
#include <linux/init.h>
18
#include <linux/pid.h>
19
#include <linux/bug.h>
20
#include <linux/mutex.h>
21
#include <linux/rwsem.h>
22
#include <linux/mm_types.h>
23
#include <linux/capability.h>
24
#include <linux/semaphore.h>
25
#include <linux/fcntl.h>
M
Mark Fasheh 已提交
26
#include <linux/fiemap.h>
27
#include <linux/rculist_bl.h>
28
#include <linux/atomic.h>
29
#include <linux/shrinker.h>
30
#include <linux/migrate_mode.h>
31
#include <linux/uidgid.h>
32
#include <linux/lockdep.h>
33
#include <linux/percpu-rwsem.h>
34
#include <linux/workqueue.h>
35
#include <linux/delayed_call.h>
36
#include <linux/uuid.h>
37
#include <linux/errseq.h>
L
Linus Torvalds 已提交
38 39

#include <asm/byteorder.h>
40
#include <uapi/linux/fs.h>
L
Linus Torvalds 已提交
41

42
struct backing_dev_info;
43
struct bdi_writeback;
44
struct bio;
45
struct export_operations;
46
struct hd_geometry;
L
Linus Torvalds 已提交
47
struct iovec;
48
struct kiocb;
A
Alexey Dobriyan 已提交
49
struct kobject;
L
Linus Torvalds 已提交
50 51 52 53 54
struct pipe_inode_info;
struct poll_table_struct;
struct kstatfs;
struct vm_area_struct;
struct vfsmount;
55
struct cred;
56
struct swap_info_struct;
57
struct seq_file;
58
struct workqueue_struct;
59
struct iov_iter;
60 61
struct fscrypt_info;
struct fscrypt_operations;
L
Linus Torvalds 已提交
62

63
extern void __init inode_init(void);
L
Linus Torvalds 已提交
64
extern void __init inode_init_early(void);
65 66
extern void __init files_init(void);
extern void __init files_maxfiles_init(void);
L
Linus Torvalds 已提交
67

68
extern struct files_stat_struct files_stat;
E
Eric Dumazet 已提交
69
extern unsigned long get_max_files(void);
70
extern unsigned int sysctl_nr_open;
71 72
extern struct inodes_stat_t inodes_stat;
extern int leases_enable, lease_break_time;
K
Kees Cook 已提交
73 74
extern int sysctl_protected_symlinks;
extern int sysctl_protected_hardlinks;
75

C
Christoph Hellwig 已提交
76 77
typedef __kernel_rwf_t rwf_t;

L
Linus Torvalds 已提交
78 79 80
struct buffer_head;
typedef int (get_block_t)(struct inode *inode, sector_t iblock,
			struct buffer_head *bh_result, int create);
81
typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
82
			ssize_t bytes, void *private);
L
Linus Torvalds 已提交
83

D
David Howells 已提交
84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139
#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)

140 141
/* File needs atomic accesses to f_pos */
#define FMODE_ATOMIC_POS	((__force fmode_t)0x8000)
142 143
/* Write access to underlying fs */
#define FMODE_WRITER		((__force fmode_t)0x10000)
144 145 146 147
/* Has read method(s) */
#define FMODE_CAN_READ          ((__force fmode_t)0x20000)
/* Has write method(s) */
#define FMODE_CAN_WRITE         ((__force fmode_t)0x40000)
148

D
David Howells 已提交
149
/* File was opened by fanotify and shouldn't generate fanotify events */
150
#define FMODE_NONOTIFY		((__force fmode_t)0x4000000)
D
David Howells 已提交
151

152 153
/* File is capable of returning -EAGAIN if I/O will block */
#define FMODE_NOWAIT	((__force fmode_t)0x8000000)
154

D
David Howells 已提交
155 156 157 158 159 160 161 162
/*
 * 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
163 164 165 166
/*
 * Attribute flags.  These should be or-ed together to figure out what
 * has been changed!
 */
167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183
#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)
184
#define ATTR_TOUCH	(1 << 17)
L
Linus Torvalds 已提交
185

M
Miklos Szeredi 已提交
186 187 188 189 190 191 192
/*
 * 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
193 194 195 196 197 198 199 200 201 202 203 204
/*
 * 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;
205 206
	kuid_t		ia_uid;
	kgid_t		ia_gid;
L
Linus Torvalds 已提交
207 208 209 210
	loff_t		ia_size;
	struct timespec	ia_atime;
	struct timespec	ia_mtime;
	struct timespec	ia_ctime;
211 212

	/*
L
Lucas De Marchi 已提交
213
	 * Not an attribute, but an auxiliary info for filesystems wanting to
214 215 216 217
	 * 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
218 219 220 221 222 223 224
};

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

225 226 227 228 229 230
/*
 * Maximum number of layers of fs stack.  Needs to be limited to
 * prevent kernel stack overflow
 */
#define FILESYSTEM_MAX_STACK_DEPTH 2

231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248
/** 
 * 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
249
 *  			by readpage().
250 251 252 253 254 255 256 257 258 259 260 261
 *
 * 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,
};

262 263
#define AOP_FLAG_CONT_EXPAND		0x0001 /* called from cont_expand */
#define AOP_FLAG_NOFS			0x0002 /* used by filesystem to direct
264 265
						* helper code (eg buffer layer)
						* to clear GFP_FS from alloc */
266

L
Linus Torvalds 已提交
267 268 269 270 271 272 273
/*
 * oh the beauties of C type declarations.
 */
struct page;
struct address_space;
struct writeback_control;

274 275 276 277 278 279 280 281 282 283 284 285
/*
 * 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,
};

286
#define IOCB_EVENTFD		(1 << 0)
287 288
#define IOCB_APPEND		(1 << 1)
#define IOCB_DIRECT		(1 << 2)
289
#define IOCB_HIPRI		(1 << 3)
290 291
#define IOCB_DSYNC		(1 << 4)
#define IOCB_SYNC		(1 << 5)
292
#define IOCB_WRITE		(1 << 6)
293
#define IOCB_NOWAIT		(1 << 7)
294 295 296 297 298 299 300

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;
301
	enum rw_hint		ki_hint;
302
} __randomize_layout;
303 304 305 306 307 308

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

309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329
/*
 * "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
330

L
Linus Torvalds 已提交
331 332 333 334 335 336 337
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 *);

338
	/* Set a page dirty.  Return true if this dirtied it */
L
Linus Torvalds 已提交
339 340 341 342 343
	int (*set_page_dirty)(struct page *page);

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

344 345 346 347 348 349 350
	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
351 352
	/* Unfortunately this kludge is needed for FIBMAP. Don't use it */
	sector_t (*bmap)(struct address_space *, sector_t);
353
	void (*invalidatepage) (struct page *, unsigned int, unsigned int);
A
Al Viro 已提交
354
	int (*releasepage) (struct page *, gfp_t);
355
	void (*freepage)(struct page *);
356
	ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter);
357
	/*
358 359
	 * migrate the contents of a page to the specified target. If
	 * migrate_mode is MIGRATE_ASYNC, it must not block.
360
	 */
361
	int (*migratepage) (struct address_space *,
362
			struct page *, struct page *, enum migrate_mode);
363 364
	bool (*isolate_page)(struct page *, isolate_mode_t);
	void (*putback_page)(struct page *);
365
	int (*launder_page) (struct page *);
366
	int (*is_partially_uptodate) (struct page *, unsigned long,
367
					unsigned long);
368
	void (*is_dirty_writeback) (struct page *, bool *, bool *);
369
	int (*error_remove_page)(struct address_space *, struct page *);
370 371

	/* swapfile support */
372 373 374
	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
375 376
};

J
Jens Axboe 已提交
377 378
extern const struct address_space_operations empty_aops;

379 380 381 382 383 384 385 386 387 388 389 390
/*
 * 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
391 392 393
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
394
	spinlock_t		tree_lock;	/* and lock protecting it */
395
	atomic_t		i_mmap_writable;/* count VM_SHARED mappings */
396
	struct rb_root_cached	i_mmap;		/* tree of private and shared mappings */
397
	struct rw_semaphore	i_mmap_rwsem;	/* protect tree, count, list */
398
	/* Protected by tree_lock together with the radix tree */
L
Linus Torvalds 已提交
399
	unsigned long		nrpages;	/* number of total pages */
400 401
	/* number of shadow or DAX exceptional entries */
	unsigned long		nrexceptional;
L
Linus Torvalds 已提交
402
	pgoff_t			writeback_index;/* writeback starts here */
403
	const struct address_space_operations *a_ops;	/* methods */
404
	unsigned long		flags;		/* error bits */
L
Linus Torvalds 已提交
405
	spinlock_t		private_lock;	/* for use by the address_space */
406
	gfp_t			gfp_mask;	/* implicit gfp mask for allocations */
407
	struct list_head	private_list;	/* for use by the address_space */
408
	void			*private_data;	/* ditto */
409
	errseq_t		wb_err;
410
} __attribute__((aligned(sizeof(long)))) __randomize_layout;
L
Linus Torvalds 已提交
411 412
	/*
	 * On most architectures that alignment is already the case; but
L
Lucas De Marchi 已提交
413
	 * must be enforced here for CRIS, to let the least significant bit
L
Linus Torvalds 已提交
414 415
	 * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON.
	 */
416
struct request_queue;
L
Linus Torvalds 已提交
417 418 419

struct block_device {
	dev_t			bd_dev;  /* not a kdev_t - it's a search key */
420
	int			bd_openers;
L
Linus Torvalds 已提交
421
	struct inode *		bd_inode;	/* will die */
422
	struct super_block *	bd_super;
423
	struct mutex		bd_mutex;	/* open/close mutex */
424
	void *			bd_claiming;
L
Linus Torvalds 已提交
425 426
	void *			bd_holder;
	int			bd_holders;
427
	bool			bd_write_holder;
428
#ifdef CONFIG_SYSFS
429
	struct list_head	bd_holder_disks;
430
#endif
L
Linus Torvalds 已提交
431 432
	struct block_device *	bd_contains;
	unsigned		bd_block_size;
433
	u8			bd_partno;
L
Linus Torvalds 已提交
434 435 436 437 438
	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;
439
	struct request_queue *  bd_queue;
440
	struct backing_dev_info *bd_bdi;
L
Linus Torvalds 已提交
441 442 443 444 445 446 447 448
	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;
449 450 451 452 453

	/* The counter of freeze processes */
	int			bd_fsfreeze_count;
	/* Mutex for freeze */
	struct mutex		bd_fsfreeze_mutex;
454
} __randomize_layout;
L
Linus Torvalds 已提交
455 456 457 458 459 460 461

/*
 * Radix-tree tags, for tagging dirty and writeback pages within the pagecache
 * radix trees
 */
#define PAGECACHE_TAG_DIRTY	0
#define PAGECACHE_TAG_WRITEBACK	1
462
#define PAGECACHE_TAG_TOWRITE	2
L
Linus Torvalds 已提交
463 464 465

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

466 467
static inline void i_mmap_lock_write(struct address_space *mapping)
{
468
	down_write(&mapping->i_mmap_rwsem);
469 470 471 472
}

static inline void i_mmap_unlock_write(struct address_space *mapping)
{
473
	up_write(&mapping->i_mmap_rwsem);
474 475
}

D
Davidlohr Bueso 已提交
476 477 478 479 480 481 482 483 484 485
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
486 487 488 489 490
/*
 * Might pages of this file be mapped into userspace?
 */
static inline int mapping_mapped(struct address_space *mapping)
{
491
	return	!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root);
L
Linus Torvalds 已提交
492 493 494 495 496 497 498
}

/*
 * 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.
499 500 501
 *
 * 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
502 503 504
 */
static inline int mapping_writably_mapped(struct address_space *mapping)
{
505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527
	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
528 529 530 531 532 533 534 535 536 537 538 539 540
}

/*
 * 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
541 542
struct posix_acl;
#define ACL_NOT_CACHED ((void *)(-1))
543
#define ACL_DONT_CACHE ((void *)(-3))
A
Al Viro 已提交
544

545 546 547 548 549 550 551 552 553 554 555 556
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;
}

557 558 559
#define IOP_FASTPERM	0x0001
#define IOP_LOOKUP	0x0002
#define IOP_NOFOLLOW	0x0004
560
#define IOP_XATTR	0x0008
561
#define IOP_DEFAULT_READLINK	0x0010
562

563 564
struct fsnotify_mark_connector;

565 566 567 568 569
/*
 * 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
570
struct inode {
571
	umode_t			i_mode;
572
	unsigned short		i_opflags;
573 574
	kuid_t			i_uid;
	kgid_t			i_gid;
575 576 577 578 579 580 581
	unsigned int		i_flags;

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

582 583
	const struct inode_operations	*i_op;
	struct super_block	*i_sb;
584
	struct address_space	*i_mapping;
585

586 587 588
#ifdef CONFIG_SECURITY
	void			*i_security;
#endif
589

590 591
	/* Stat data, not accessed from path walking */
	unsigned long		i_ino;
M
Miklos Szeredi 已提交
592 593 594 595 596 597 598 599 600 601 602
	/*
	 * 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;
	};
603
	dev_t			i_rdev;
604
	loff_t			i_size;
605 606 607
	struct timespec		i_atime;
	struct timespec		i_mtime;
	struct timespec		i_ctime;
608 609
	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
	unsigned short          i_bytes;
610
	unsigned int		i_blkbits;
611
	enum rw_hint		i_write_hint;
612 613 614 615 616 617 618 619
	blkcnt_t		i_blocks;

#ifdef __NEED_I_SIZE_ORDERED
	seqcount_t		i_size_seqcount;
#endif

	/* Misc */
	unsigned long		i_state;
620
	struct rw_semaphore	i_rwsem;
621

622
	unsigned long		dirtied_when;	/* jiffies of first dirtying */
623
	unsigned long		dirtied_time_when;
624

L
Linus Torvalds 已提交
625
	struct hlist_node	i_hash;
626
	struct list_head	i_io_list;	/* backing dev IO list */
627 628
#ifdef CONFIG_CGROUP_WRITEBACK
	struct bdi_writeback	*i_wb;		/* the associated cgroup wb */
629 630 631 632 633

	/* foreign inode detection, see wbc_detach_inode() */
	int			i_wb_frn_winner;
	u16			i_wb_frn_avg_time;
	u16			i_wb_frn_history;
634
#endif
N
Nick Piggin 已提交
635
	struct list_head	i_lru;		/* inode LRU list */
L
Linus Torvalds 已提交
636
	struct list_head	i_sb_list;
637
	struct list_head	i_wb_list;	/* backing dev writeback list */
N
Nick Piggin 已提交
638
	union {
A
Al Viro 已提交
639
		struct hlist_head	i_dentry;
N
Nick Piggin 已提交
640 641
		struct rcu_head		i_rcu;
	};
642
	atomic64_t		i_version;
643
	atomic_t		i_count;
C
Christoph Hellwig 已提交
644
	atomic_t		i_dio_count;
645
	atomic_t		i_writecount;
M
Mimi Zohar 已提交
646 647 648
#ifdef CONFIG_IMA
	atomic_t		i_readcount; /* struct files open RO */
#endif
649
	const struct file_operations	*i_fop;	/* former ->i_op->default_file_ops */
650
	struct file_lock_context	*i_flctx;
L
Linus Torvalds 已提交
651 652
	struct address_space	i_data;
	struct list_head	i_devices;
653 654
	union {
		struct pipe_inode_info	*i_pipe;
655
		struct block_device	*i_bdev;
656
		struct cdev		*i_cdev;
A
Al Viro 已提交
657
		char			*i_link;
A
Al Viro 已提交
658
		unsigned		i_dir_seq;
659
	};
L
Linus Torvalds 已提交
660 661 662

	__u32			i_generation;

663 664
#ifdef CONFIG_FSNOTIFY
	__u32			i_fsnotify_mask; /* all events this inode cares about */
665
	struct fsnotify_mark_connector __rcu	*i_fsnotify_marks;
R
Robert Love 已提交
666 667
#endif

668 669 670 671
#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
	struct fscrypt_info	*i_crypt_info;
#endif

672
	void			*i_private; /* fs or device private pointer */
673
} __randomize_layout;
L
Linus Torvalds 已提交
674

F
Fabian Frederick 已提交
675 676 677 678 679
static inline unsigned int i_blocksize(const struct inode *node)
{
	return (1 << node->i_blkbits);
}

A
Al Viro 已提交
680 681 682 683 684
static inline int inode_unhashed(struct inode *inode)
{
	return hlist_unhashed(&inode->i_hash);
}

I
Ingo Molnar 已提交
685 686 687 688 689 690
/*
 * inode->i_mutex nesting subclasses for the lock validator:
 *
 * 0: the object of the current VFS operation
 * 1: parent
 * 2: child/target
691 692
 * 3: xattr
 * 4: second non-directory
693 694 695
 * 5: second parent (when locking independent directories in rename)
 *
 * I_MUTEX_NONDIR2 is for certain operations (such as rename) which lock two
696
 * non-directories at once.
I
Ingo Molnar 已提交
697 698
 *
 * The locking order between these classes is
699
 * parent[2] -> child -> grandchild -> normal -> xattr -> second non-directory
I
Ingo Molnar 已提交
700 701 702 703 704 705
 */
enum inode_i_mutex_lock_class
{
	I_MUTEX_NORMAL,
	I_MUTEX_PARENT,
	I_MUTEX_CHILD,
I
Ingo Molnar 已提交
706
	I_MUTEX_XATTR,
707 708
	I_MUTEX_NONDIR2,
	I_MUTEX_PARENT2,
I
Ingo Molnar 已提交
709 710
};

A
Al Viro 已提交
711 712
static inline void inode_lock(struct inode *inode)
{
713
	down_write(&inode->i_rwsem);
A
Al Viro 已提交
714 715 716 717
}

static inline void inode_unlock(struct inode *inode)
{
718 719 720 721 722 723 724 725 726 727 728
	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
729 730 731 732
}

static inline int inode_trylock(struct inode *inode)
{
733 734 735 736 737 738
	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
739 740 741 742
}

static inline int inode_is_locked(struct inode *inode)
{
743
	return rwsem_is_locked(&inode->i_rwsem);
A
Al Viro 已提交
744 745 746 747
}

static inline void inode_lock_nested(struct inode *inode, unsigned subclass)
{
748
	down_write_nested(&inode->i_rwsem, subclass);
A
Al Viro 已提交
749 750
}

751 752 753 754 755
static inline void inode_lock_shared_nested(struct inode *inode, unsigned subclass)
{
	down_read_nested(&inode->i_rwsem, subclass);
}

756 757 758
void lock_two_nondirectories(struct inode *, struct inode*);
void unlock_two_nondirectories(struct inode *, struct inode*);

L
Linus Torvalds 已提交
759 760 761 762 763 764 765 766 767 768
/*
 * 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
769
static inline loff_t i_size_read(const struct inode *inode)
L
Linus Torvalds 已提交
770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791
{
#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
}

792 793 794 795 796
/*
 * 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
797 798 799
static inline void i_size_write(struct inode *inode, loff_t i_size)
{
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
800
	preempt_disable();
L
Linus Torvalds 已提交
801 802 803
	write_seqcount_begin(&inode->i_size_seqcount);
	inode->i_size = i_size;
	write_seqcount_end(&inode->i_size_seqcount);
804
	preempt_enable();
L
Linus Torvalds 已提交
805 806 807 808 809 810 811 812 813
#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
814
static inline unsigned iminor(const struct inode *inode)
L
Linus Torvalds 已提交
815 816 817 818
{
	return MINOR(inode->i_rdev);
}

J
Jan Engelhardt 已提交
819
static inline unsigned imajor(const struct inode *inode)
L
Linus Torvalds 已提交
820 821 822 823 824 825 826 827
{
	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 */
828 829
	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 */
830
	kuid_t uid, euid;	/* uid/euid of process setting the owner */
L
Linus Torvalds 已提交
831 832 833 834 835 836 837
	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
838 839 840
	pgoff_t start;			/* where readahead started */
	unsigned int size;		/* # of readahead pages */
	unsigned int async_size;	/* do asynchronous readahead when
841
					   there are only # of pages ahead */
842

F
Fengguang Wu 已提交
843
	unsigned int ra_pages;		/* Maximum readahead window */
844
	unsigned int mmap_miss;		/* Cache miss stat for mmap accesses */
845
	loff_t prev_pos;		/* Cache last read() position */
L
Linus Torvalds 已提交
846 847
};

848 849 850 851 852
/*
 * Check if @index falls in the readahead windows.
 */
static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
{
853 854
	return (index >= ra->start &&
		index <  ra->start + ra->size);
855 856
}

L
Linus Torvalds 已提交
857
struct file {
E
Eric Dumazet 已提交
858
	union {
859
		struct llist_node	fu_llist;
E
Eric Dumazet 已提交
860 861
		struct rcu_head 	fu_rcuhead;
	} f_u;
862
	struct path		f_path;
863
	struct inode		*f_inode;	/* cached value */
864
	const struct file_operations	*f_op;
865 866

	/*
867
	 * Protects f_ep_links, f_flags.
868 869 870
	 * Must not be taken from IRQ context.
	 */
	spinlock_t		f_lock;
871
	enum rw_hint		f_write_hint;
A
Al Viro 已提交
872
	atomic_long_t		f_count;
L
Linus Torvalds 已提交
873
	unsigned int 		f_flags;
874
	fmode_t			f_mode;
875
	struct mutex		f_pos_lock;
L
Linus Torvalds 已提交
876 877
	loff_t			f_pos;
	struct fown_struct	f_owner;
D
David Howells 已提交
878
	const struct cred	*f_cred;
L
Linus Torvalds 已提交
879 880
	struct file_ra_state	f_ra;

881
	u64			f_version;
882
#ifdef CONFIG_SECURITY
L
Linus Torvalds 已提交
883
	void			*f_security;
884
#endif
L
Linus Torvalds 已提交
885 886 887 888 889 890
	/* 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
891
	struct list_head	f_tfile_llink;
L
Linus Torvalds 已提交
892 893
#endif /* #ifdef CONFIG_EPOLL */
	struct address_space	*f_mapping;
894
	errseq_t		f_wb_err;
895 896
} __randomize_layout
  __attribute__((aligned(4)));	/* lest something weird decides that 2 is OK */
L
Linus Torvalds 已提交
897

898 899 900 901 902 903 904
struct file_handle {
	__u32 handle_bytes;
	int handle_type;
	/* file identifier */
	unsigned char f_handle[0];
};

A
Al Viro 已提交
905 906 907 908 909
static inline struct file *get_file(struct file *f)
{
	atomic_long_inc(&f->f_count);
	return f;
}
910
#define get_file_rcu(x) atomic_long_inc_not_zero(&(x)->f_count)
911
#define fput_atomic(x)	atomic_long_add_unless(&(x)->f_count, -1, 1)
A
Al Viro 已提交
912
#define file_count(x)	atomic_long_read(&(x)->f_count)
L
Linus Torvalds 已提交
913 914 915 916 917 918

#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
919
#define MAX_LFS_FILESIZE	((loff_t)ULONG_MAX << PAGE_SHIFT)
L
Linus Torvalds 已提交
920
#elif BITS_PER_LONG==64
921
#define MAX_LFS_FILESIZE 	((loff_t)LLONG_MAX)
L
Linus Torvalds 已提交
922 923 924 925
#endif

#define FL_POSIX	1
#define FL_FLOCK	2
926
#define FL_DELEG	4	/* NFSv4 delegation */
L
Linus Torvalds 已提交
927
#define FL_ACCESS	8	/* not trying to lock, just looking */
928
#define FL_EXISTS	16	/* when unlocking, test for existence */
L
Linus Torvalds 已提交
929
#define FL_LEASE	32	/* lease held on this file */
930
#define FL_CLOSE	64	/* unlock on close */
L
Linus Torvalds 已提交
931
#define FL_SLEEP	128	/* A blocking lock */
932 933
#define FL_DOWNGRADE_PENDING	256 /* Lease is being downgraded */
#define FL_UNLOCK_PENDING	512 /* Lease is being broken */
934
#define FL_OFDLCK	1024	/* lock is "owned" by struct file */
C
Christoph Hellwig 已提交
935
#define FL_LAYOUT	2048	/* outstanding pNFS layout */
L
Linus Torvalds 已提交
936

937 938
#define FL_CLOSE_POSIX (FL_POSIX | FL_CLOSE)

939 940 941 942 943 944
/*
 * Special return value from posix_lock_file() and vfs_lock_file() for
 * asynchronous locking.
 */
#define FILE_LOCK_DEFERRED 1

945
/* legacy typedef, should eventually be removed */
946
typedef void *fl_owner_t;
L
Linus Torvalds 已提交
947

948 949
struct file_lock;

L
Linus Torvalds 已提交
950 951 952 953 954 955
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
956
	int (*lm_compare_owner)(struct file_lock *, struct file_lock *);
957
	unsigned long (*lm_owner_key)(struct file_lock *);
958 959
	fl_owner_t (*lm_get_owner)(fl_owner_t);
	void (*lm_put_owner)(fl_owner_t);
J
J. Bruce Fields 已提交
960
	void (*lm_notify)(struct file_lock *);	/* unblock callback */
961
	int (*lm_grant)(struct file_lock *, int);
J
Jeff Layton 已提交
962
	bool (*lm_break)(struct file_lock *);
963
	int (*lm_change)(struct file_lock *, int, struct list_head *);
964
	void (*lm_setup)(struct file_lock *, void **);
L
Linus Torvalds 已提交
965 966
};

967 968
struct lock_manager {
	struct list_head list;
969 970 971 972 973
	/*
	 * NFSv4 and up also want opens blocked during the grace period;
	 * NLM doesn't care:
	 */
	bool block_opens;
974 975
};

976 977
struct net;
void locks_start_grace(struct net *, struct lock_manager *);
978
void locks_end_grace(struct lock_manager *);
C
Corentin Labbe 已提交
979 980
bool locks_in_grace(struct net *);
bool opens_in_grace(struct net *);
981

L
Linus Torvalds 已提交
982 983 984
/* that will die - we need it for nfs_lock_info */
#include <linux/nfs_fs_i.h>

985 986 987 988 989 990 991 992 993
/*
 * 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?
 *
994
 * The varous i_flctx lists are ordered by:
995
 *
996 997 998
 * 1) lock owner
 * 2) lock range start
 * 3) lock range end
999 1000 1001
 *
 * Obviously, the last two criteria only matter for POSIX locks.
 */
L
Linus Torvalds 已提交
1002 1003
struct file_lock {
	struct file_lock *fl_next;	/* singly linked list for this inode  */
1004
	struct list_head fl_list;	/* link into file_lock_context */
1005
	struct hlist_node fl_link;	/* node in global lists */
L
Linus Torvalds 已提交
1006 1007
	struct list_head fl_block;	/* circular list of blocked processes */
	fl_owner_t fl_owner;
1008
	unsigned int fl_flags;
1009
	unsigned char fl_type;
L
Linus Torvalds 已提交
1010
	unsigned int fl_pid;
1011
	int fl_link_cpu;		/* what cpu's list is this on? */
L
Linus Torvalds 已提交
1012 1013 1014 1015 1016 1017
	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 */
1018 1019 1020
	/* for lease breaks: */
	unsigned long fl_break_time;
	unsigned long fl_downgrade_time;
L
Linus Torvalds 已提交
1021

1022
	const struct file_lock_operations *fl_ops;	/* Callbacks for filesystems */
1023
	const struct lock_manager_operations *fl_lmops;	/* Callbacks for lockmanagers */
L
Linus Torvalds 已提交
1024 1025
	union {
		struct nfs_lock_info	nfs_fl;
1026
		struct nfs4_lock_info	nfs4_fl;
D
David Howells 已提交
1027 1028 1029 1030
		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
1031
	} fl_u;
1032
} __randomize_layout;
L
Linus Torvalds 已提交
1033

1034
struct file_lock_context {
1035
	spinlock_t		flc_lock;
1036
	struct list_head	flc_flock;
1037
	struct list_head	flc_posix;
1038
	struct list_head	flc_lease;
1039 1040
};

L
Linus Torvalds 已提交
1041 1042 1043 1044 1045 1046 1047
/* 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

1048 1049
extern void send_sigio(struct fown_struct *fown, int fd, int band);

1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061
/*
 * 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;
}

1062
#ifdef CONFIG_FILE_LOCKING
1063
extern int fcntl_getlk(struct file *, unsigned int, struct flock *);
1064
extern int fcntl_setlk(unsigned int, struct file *, unsigned int,
1065
			struct flock *);
L
Linus Torvalds 已提交
1066 1067

#if BITS_PER_LONG == 32
1068
extern int fcntl_getlk64(struct file *, unsigned int, struct flock64 *);
1069
extern int fcntl_setlk64(unsigned int, struct file *, unsigned int,
1070
			struct flock64 *);
L
Linus Torvalds 已提交
1071 1072 1073 1074 1075 1076
#endif

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

/* fs/locks.c */
1077
void locks_free_lock_context(struct inode *inode);
1078
void locks_free_lock(struct file_lock *fl);
L
Linus Torvalds 已提交
1079
extern void locks_init_lock(struct file_lock *);
1080
extern struct file_lock * locks_alloc_lock(void);
L
Linus Torvalds 已提交
1081
extern void locks_copy_lock(struct file_lock *, struct file_lock *);
1082
extern void locks_copy_conflock(struct file_lock *, struct file_lock *);
L
Linus Torvalds 已提交
1083
extern void locks_remove_posix(struct file *, fl_owner_t);
1084
extern void locks_remove_file(struct file *);
1085
extern void locks_release_private(struct file_lock *);
1086
extern void posix_test_lock(struct file *, struct file_lock *);
1087
extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *);
1088
extern int posix_unblock_lock(struct file_lock *);
1089
extern int vfs_test_lock(struct file *, struct file_lock *);
1090
extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *);
M
Marc Eshel 已提交
1091
extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
1092
extern int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl);
J
J. Bruce Fields 已提交
1093
extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type);
L
Linus Torvalds 已提交
1094
extern void lease_get_mtime(struct inode *, struct timespec *time);
1095 1096
extern int generic_setlease(struct file *, long, struct file_lock **, void **priv);
extern int vfs_setlease(struct file *, long, struct file_lock **, void **);
1097
extern int lease_modify(struct file_lock *, int, struct list_head *);
1098 1099 1100
struct files_struct;
extern void show_fd_locks(struct seq_file *f,
			 struct file *filp, struct files_struct *files);
1101
#else /* !CONFIG_FILE_LOCKING */
1102 1103
static inline int fcntl_getlk(struct file *file, unsigned int cmd,
			      struct flock __user *user)
1104 1105 1106 1107 1108 1109 1110 1111 1112 1113
{
	return -EINVAL;
}

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

1114
#if BITS_PER_LONG == 32
1115 1116
static inline int fcntl_getlk64(struct file *file, unsigned int cmd,
				struct flock64 __user *user)
1117 1118 1119 1120 1121 1122 1123 1124 1125
{
	return -EINVAL;
}

static inline int fcntl_setlk64(unsigned int fd, struct file *file,
				unsigned int cmd, struct flock64 __user *user)
{
	return -EACCES;
}
1126
#endif
1127 1128
static inline int fcntl_setlease(unsigned int fd, struct file *filp, long arg)
{
1129
	return -EINVAL;
1130 1131 1132 1133
}

static inline int fcntl_getlease(struct file *filp)
{
1134
	return F_UNLCK;
1135 1136
}

1137
static inline void
1138
locks_free_lock_context(struct inode *inode)
1139 1140 1141
{
}

1142 1143 1144 1145 1146
static inline void locks_init_lock(struct file_lock *fl)
{
	return;
}

1147
static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl)
1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161
{
	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;
}

1162
static inline void locks_remove_file(struct file *filp)
1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177
{
	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;
}

1178
static inline int posix_unblock_lock(struct file_lock *waiter)
1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198
{
	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;
}

1199 1200 1201 1202 1203
static inline int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl)
{
	return -ENOLCK;
}

J
J. Bruce Fields 已提交
1204
static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
1205 1206 1207 1208 1209 1210 1211 1212 1213 1214
{
	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,
1215
				    struct file_lock **flp, void **priv)
1216 1217 1218 1219 1220
{
	return -EINVAL;
}

static inline int vfs_setlease(struct file *filp, long arg,
1221
			       struct file_lock **lease, void **priv)
1222 1223 1224 1225
{
	return -EINVAL;
}

1226
static inline int lease_modify(struct file_lock *fl, int arg,
1227
			       struct list_head *dispose)
1228 1229 1230
{
	return -EINVAL;
}
1231 1232 1233 1234

struct files_struct;
static inline void show_fd_locks(struct seq_file *f,
			struct file *filp, struct files_struct *files) {}
1235 1236
#endif /* !CONFIG_FILE_LOCKING */

1237 1238 1239 1240 1241
static inline struct inode *file_inode(const struct file *f)
{
	return f->f_inode;
}

M
Miklos Szeredi 已提交
1242 1243
static inline struct dentry *file_dentry(const struct file *file)
{
M
Miklos Szeredi 已提交
1244
	return d_real(file->f_path.dentry, file_inode(file), 0, 0);
M
Miklos Szeredi 已提交
1245 1246
}

1247 1248
static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl)
{
1249
	return locks_lock_inode_wait(locks_inode(filp), fl);
1250 1251
}

L
Linus Torvalds 已提交
1252
struct fasync_struct {
1253 1254 1255 1256 1257 1258
	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
1259 1260 1261 1262 1263 1264
};

#define FASYNC_MAGIC 0x4601

/* SMP safe fasync helpers: */
extern int fasync_helper(int, struct file *, int, struct fasync_struct **);
1265 1266 1267 1268 1269
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
1270 1271 1272
/* can be called from interrupts */
extern void kill_fasync(struct fasync_struct **, int, int);

1273
extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
1274
extern int f_setown(struct file *filp, unsigned long arg, int force);
L
Linus Torvalds 已提交
1275
extern void f_delown(struct file *filp);
1276
extern pid_t f_getown(struct file *filp);
L
Linus Torvalds 已提交
1277 1278
extern int send_sigurg(struct fown_struct *fown);

1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305
/*
 * sb->s_flags.  Note that these mirror the equivalent MS_* flags where
 * represented in both.
 */
#define SB_RDONLY	 1	/* Mount read-only */
#define SB_NOSUID	 2	/* Ignore suid and sgid bits */
#define SB_NODEV	 4	/* Disallow access to device special files */
#define SB_NOEXEC	 8	/* Disallow program execution */
#define SB_SYNCHRONOUS	16	/* Writes are synced at once */
#define SB_MANDLOCK	64	/* Allow mandatory locks on an FS */
#define SB_DIRSYNC	128	/* Directory modifications are synchronous */
#define SB_NOATIME	1024	/* Do not update access times. */
#define SB_NODIRATIME	2048	/* Do not update directory access times */
#define SB_SILENT	32768
#define SB_POSIXACL	(1<<16)	/* VFS does not apply the umask */
#define SB_KERNMOUNT	(1<<22) /* this is a kern_mount call */
#define SB_I_VERSION	(1<<23) /* Update inode I_version field */
#define SB_LAZYTIME	(1<<25) /* Update the on-disk [acm]times lazily */

/* These sb flags are internal to the kernel */
#define SB_SUBMOUNT     (1<<26)
#define SB_NOREMOTELOCK	(1<<27)
#define SB_NOSEC	(1<<28)
#define SB_BORN		(1<<29)
#define SB_ACTIVE	(1<<30)
#define SB_NOUSER	(1<<31)

L
Linus Torvalds 已提交
1306 1307 1308 1309 1310 1311 1312
/*
 *	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 */
1313 1314
#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
1315

1316 1317
/* sb->s_iflags */
#define SB_I_CGROUPWB	0x00000001	/* cgroup-aware writeback enabled */
1318
#define SB_I_NOEXEC	0x00000002	/* Ignore executables on this fs */
1319
#define SB_I_NODEV	0x00000004	/* Ignore devices on this fs */
L
Linus Torvalds 已提交
1320

1321 1322
/* sb->s_iflags to limit user namespace mounts */
#define SB_I_USERNS_VISIBLE		0x00000010 /* fstype already mounted */
L
Linus Torvalds 已提交
1323

1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336
/* 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 {
1337 1338 1339
	int				frozen;		/* Is sb frozen? */
	wait_queue_head_t		wait_unfrozen;	/* for get_super_thawed() */
	struct percpu_rw_semaphore	rw_sem[SB_FREEZE_LEVELS];
1340 1341
};

L
Linus Torvalds 已提交
1342 1343 1344
struct super_block {
	struct list_head	s_list;		/* Keep this first */
	dev_t			s_dev;		/* search index; _not_ kdev_t */
1345 1346
	unsigned char		s_blocksize_bits;
	unsigned long		s_blocksize;
1347
	loff_t			s_maxbytes;	/* Max file size */
L
Linus Torvalds 已提交
1348
	struct file_system_type	*s_type;
1349
	const struct super_operations	*s_op;
1350
	const struct dquot_operations	*dq_op;
1351
	const struct quotactl_ops	*s_qcop;
1352
	const struct export_operations *s_export_op;
L
Linus Torvalds 已提交
1353
	unsigned long		s_flags;
1354
	unsigned long		s_iflags;	/* internal SB_I_* flags */
L
Linus Torvalds 已提交
1355 1356 1357 1358 1359
	unsigned long		s_magic;
	struct dentry		*s_root;
	struct rw_semaphore	s_umount;
	int			s_count;
	atomic_t		s_active;
1360
#ifdef CONFIG_SECURITY
L
Linus Torvalds 已提交
1361
	void                    *s_security;
1362
#endif
1363
	const struct xattr_handler **s_xattr;
L
Linus Torvalds 已提交
1364

1365 1366
	const struct fscrypt_operations	*s_cop;

1367
	struct hlist_bl_head	s_roots;	/* alternate root dentries for NFS */
1368
	struct list_head	s_mounts;	/* list of mounts; _not_ for fs use */
L
Linus Torvalds 已提交
1369
	struct block_device	*s_bdev;
J
Jens Axboe 已提交
1370
	struct backing_dev_info *s_bdi;
1371
	struct mtd_info		*s_mtd;
A
Al Viro 已提交
1372
	struct hlist_node	s_instances;
1373
	unsigned int		s_quota_types;	/* Bitmask of supported quota types */
L
Linus Torvalds 已提交
1374 1375
	struct quota_info	s_dquot;	/* Diskquota specific options */

1376
	struct sb_writers	s_writers;
L
Linus Torvalds 已提交
1377

1378 1379
	char			s_id[32];	/* Informational name */
	uuid_t			s_uuid;		/* UUID */
L
Linus Torvalds 已提交
1380 1381

	void 			*s_fs_info;	/* Filesystem private info */
1382
	unsigned int		s_max_links;
1383
	fmode_t			s_mode;
L
Linus Torvalds 已提交
1384

1385 1386 1387 1388
	/* Granularity of c/m/atime in ns.
	   Cannot be worse than a second */
	u32		   s_time_gran;

L
Linus Torvalds 已提交
1389 1390 1391 1392
	/*
	 * The next field is for VFS *only*. No filesystems have any business
	 * even looking at it. You had been warned.
	 */
1393
	struct mutex s_vfs_rename_mutex;	/* Kludge */
L
Linus Torvalds 已提交
1394

M
Miklos Szeredi 已提交
1395 1396 1397 1398 1399
	/*
	 * Filesystem subtype.  If non-empty the filesystem type field
	 * in /proc/mounts will be "type.subtype"
	 */
	char *s_subtype;
1400

A
Al Viro 已提交
1401
	const struct dentry_operations *s_d_op; /* default d_op for dentries */
1402 1403 1404 1405 1406

	/*
	 * Saved pool identifier for cleancache (-1 means none)
	 */
	int cleancache_poolid;
1407 1408

	struct shrinker s_shrink;	/* per-sb shrinker handle */
1409

M
Miklos Szeredi 已提交
1410 1411 1412
	/* Number of inodes with nlink == 0 but still referenced */
	atomic_long_t s_remove_count;

1413 1414
	/* Being remounted read-only */
	int s_readonly_remount;
1415 1416 1417

	/* AIO completions deferred from interrupt context */
	struct workqueue_struct *s_dio_done_wq;
A
Al Viro 已提交
1418
	struct hlist_head s_pins;
1419

1420 1421 1422 1423 1424 1425 1426
	/*
	 * 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;

1427 1428 1429 1430 1431 1432
	/*
	 * 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
1433
	struct rcu_head		rcu;
1434
	struct work_struct	destroy_work;
1435

1436
	struct mutex		s_sync_lock;	/* sync serialisation lock */
1437 1438 1439 1440 1441

	/*
	 * Indicates how deep in a filesystem stack this SB is
	 */
	int s_stack_depth;
1442 1443 1444 1445

	/* s_inode_list_lock protects s_inodes */
	spinlock_t		s_inode_list_lock ____cacheline_aligned_in_smp;
	struct list_head	s_inodes;	/* all inodes */
1446 1447 1448

	spinlock_t		s_inode_wblist_lock;
	struct list_head	s_inodes_wb;	/* writeback inodes */
1449
} __randomize_layout;
L
Linus Torvalds 已提交
1450

1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475
/* 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
1476
extern struct timespec current_time(struct inode *inode);
L
Linus Torvalds 已提交
1477 1478 1479 1480 1481

/*
 * Snapshotting support.
 */

1482 1483 1484
void __sb_end_write(struct super_block *sb, int level);
int __sb_start_write(struct super_block *sb, int level, bool wait);

1485
#define __sb_writers_acquired(sb, lev)	\
1486
	percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_)
1487
#define __sb_writers_release(sb, lev)	\
1488
	percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_)
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 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595
/**
 * 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
1596 1597


1598
extern bool inode_owner_or_capable(const struct inode *inode);
1599

L
Linus Torvalds 已提交
1600 1601 1602
/*
 * VFS helper functions..
 */
A
Al Viro 已提交
1603
extern int vfs_create(struct inode *, struct dentry *, umode_t, bool);
1604
extern int vfs_mkdir(struct inode *, struct dentry *, umode_t);
A
Al Viro 已提交
1605
extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
1606
extern int vfs_symlink(struct inode *, struct dentry *, const char *);
J
J. Bruce Fields 已提交
1607
extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct inode **);
L
Linus Torvalds 已提交
1608
extern int vfs_rmdir(struct inode *, struct dentry *);
1609
extern int vfs_unlink(struct inode *, struct dentry *, struct inode **);
M
Miklos Szeredi 已提交
1610
extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int);
M
Miklos Szeredi 已提交
1611
extern int vfs_whiteout(struct inode *, struct dentry *);
L
Linus Torvalds 已提交
1612

1613 1614 1615
extern struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode,
				  int open_flag);

A
Al Viro 已提交
1616 1617 1618 1619
int vfs_mkobj(struct dentry *, umode_t,
		int (*f)(struct dentry *, umode_t, void *),
		void *);

1620 1621 1622
/*
 * VFS file helper functions.
 */
1623
extern void inode_init_owner(struct inode *inode, const struct inode *dir,
A
Al Viro 已提交
1624
			umode_t mode);
1625
extern bool may_open_dev(const struct path *path);
M
Mark Fasheh 已提交
1626 1627 1628 1629 1630 1631 1632
/*
 * 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 */
1633 1634
	struct fiemap_extent __user *fi_extents_start; /* Start of
							fiemap_extent array */
M
Mark Fasheh 已提交
1635 1636 1637 1638 1639
};
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
1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661
/*
 * 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.
 */
1662 1663 1664 1665
struct dir_context;
typedef int (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64,
			 unsigned);

1666
struct dir_context {
A
Al Viro 已提交
1667
	const filldir_t actor;
1668
	loff_t pos;
1669
};
1670

1671
struct block_device_operations;
L
Linus Torvalds 已提交
1672 1673 1674 1675 1676 1677 1678

/* 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

1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698
/*
 * 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)


1699 1700
struct iov_iter;

L
Linus Torvalds 已提交
1701 1702 1703 1704 1705
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 *);
1706 1707
	ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
1708
	int (*iterate) (struct file *, struct dir_context *);
1709
	int (*iterate_shared) (struct file *, struct dir_context *);
A
Al Viro 已提交
1710
	__poll_t (*poll) (struct file *, struct poll_table_struct *);
L
Linus Torvalds 已提交
1711 1712 1713
	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 *);
1714
	unsigned long mmap_supported_flags;
L
Linus Torvalds 已提交
1715
	int (*open) (struct inode *, struct file *);
1716
	int (*flush) (struct file *, fl_owner_t id);
L
Linus Torvalds 已提交
1717
	int (*release) (struct inode *, struct file *);
1718
	int (*fsync) (struct file *, loff_t, loff_t, int datasync);
L
Linus Torvalds 已提交
1719 1720 1721 1722 1723 1724
	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 *);
1725 1726
	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);
1727
	int (*setlease)(struct file *, long, struct file_lock **, void **);
1728 1729
	long (*fallocate)(struct file *file, int mode, loff_t offset,
			  loff_t len);
1730
	void (*show_fdinfo)(struct seq_file *m, struct file *f);
1731 1732 1733
#ifndef CONFIG_MMU
	unsigned (*mmap_capabilities)(struct file *);
#endif
1734 1735 1736 1737
	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);
1738 1739
	ssize_t (*dedupe_file_range)(struct file *, u64, u64, struct file *,
			u64);
1740
} __randomize_layout;
L
Linus Torvalds 已提交
1741 1742

struct inode_operations {
A
Al Viro 已提交
1743
	struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
1744
	const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *);
1745
	int (*permission) (struct inode *, int);
1746
	struct posix_acl * (*get_acl)(struct inode *, int);
1747 1748 1749

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

A
Al Viro 已提交
1750
	int (*create) (struct inode *,struct dentry *, umode_t, bool);
L
Linus Torvalds 已提交
1751 1752 1753
	int (*link) (struct dentry *,struct inode *,struct dentry *);
	int (*unlink) (struct inode *,struct dentry *);
	int (*symlink) (struct inode *,struct dentry *,const char *);
1754
	int (*mkdir) (struct inode *,struct dentry *,umode_t);
L
Linus Torvalds 已提交
1755
	int (*rmdir) (struct inode *,struct dentry *);
A
Al Viro 已提交
1756
	int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
L
Linus Torvalds 已提交
1757
	int (*rename) (struct inode *, struct dentry *,
M
Miklos Szeredi 已提交
1758
			struct inode *, struct dentry *, unsigned int);
L
Linus Torvalds 已提交
1759
	int (*setattr) (struct dentry *, struct iattr *);
1760
	int (*getattr) (const struct path *, struct kstat *, u32, unsigned int);
L
Linus Torvalds 已提交
1761
	ssize_t (*listxattr) (struct dentry *, char *, size_t);
M
Mark Fasheh 已提交
1762 1763
	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
		      u64 len);
1764
	int (*update_time)(struct inode *, struct timespec *, int);
A
Al Viro 已提交
1765
	int (*atomic_open)(struct inode *, struct dentry *,
A
Al Viro 已提交
1766
			   struct file *, unsigned open_flag,
A
Al Viro 已提交
1767
			   umode_t create_mode, int *opened);
1768
	int (*tmpfile) (struct inode *, struct dentry *, umode_t);
1769
	int (*set_acl)(struct inode *, struct posix_acl *, int);
1770
} ____cacheline_aligned;
L
Linus Torvalds 已提交
1771

1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783
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);
}

1784 1785 1786 1787 1788
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
1789
ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
C
Christopher Yeoh 已提交
1790 1791
			      unsigned long nr_segs, unsigned long fast_segs,
			      struct iovec *fast_pointer,
1792
			      struct iovec **ret_pointer);
B
Badari Pulavarty 已提交
1793

D
Dmitry Kasatkin 已提交
1794
extern ssize_t __vfs_read(struct file *, char __user *, size_t, loff_t *);
L
Linus Torvalds 已提交
1795 1796 1797
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 *,
C
Christoph Hellwig 已提交
1798
		unsigned long, loff_t *, rwf_t);
1799 1800
extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
				   loff_t, size_t, unsigned int);
1801 1802 1803
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);
1804 1805
extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
		struct file *file_out, loff_t pos_out, u64 len);
1806 1807 1808
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);
1809 1810
extern int vfs_dedupe_file_range(struct file *file,
				 struct file_dedupe_range *same);
L
Linus Torvalds 已提交
1811 1812 1813 1814 1815

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

1816
   	void (*dirty_inode) (struct inode *, int flags);
1817
	int (*write_inode) (struct inode *, struct writeback_control *wbc);
1818
	int (*drop_inode) (struct inode *);
A
Al Viro 已提交
1819
	void (*evict_inode) (struct inode *);
L
Linus Torvalds 已提交
1820 1821
	void (*put_super) (struct super_block *);
	int (*sync_fs)(struct super_block *sb, int wait);
1822
	int (*freeze_super) (struct super_block *);
1823
	int (*freeze_fs) (struct super_block *);
1824
	int (*thaw_super) (struct super_block *);
1825
	int (*unfreeze_fs) (struct super_block *);
1826
	int (*statfs) (struct dentry *, struct kstatfs *);
L
Linus Torvalds 已提交
1827
	int (*remount_fs) (struct super_block *, int *, char *);
1828
	void (*umount_begin) (struct super_block *);
L
Linus Torvalds 已提交
1829

1830
	int (*show_options)(struct seq_file *, struct dentry *);
1831
	int (*show_devname)(struct seq_file *, struct dentry *);
1832
	int (*show_path)(struct seq_file *, struct dentry *);
1833
	int (*show_stats)(struct seq_file *, struct dentry *);
1834
#ifdef CONFIG_QUOTA
L
Linus Torvalds 已提交
1835 1836
	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);
1837
	struct dquot **(*get_dquots)(struct inode *);
1838
#endif
1839
	int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
1840 1841 1842 1843
	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
1844 1845
};

D
David Howells 已提交
1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861
/*
 * 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 */
1862
#ifdef CONFIG_FS_DAX
1863 1864 1865 1866
#define S_DAX		8192	/* Direct Access, avoiding the page cache */
#else
#define S_DAX		0	/* Make all the DAX code disappear */
#endif
1867
#define S_ENCRYPTED	16384	/* Encrypted file (using fs/crypto/) */
D
David Howells 已提交
1868 1869 1870 1871 1872 1873 1874

/*
 * 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.
 *
1875
 * Exception: SB_RDONLY is always applied to the entire file system.
D
David Howells 已提交
1876 1877 1878 1879 1880 1881 1882 1883
 *
 * 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))

1884
static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags & SB_RDONLY; }
1885
#define IS_RDONLY(inode)	sb_rdonly((inode)->i_sb)
1886
#define IS_SYNC(inode)		(__IS_FLG(inode, SB_SYNCHRONOUS) || \
D
David Howells 已提交
1887
					((inode)->i_flags & S_SYNC))
1888
#define IS_DIRSYNC(inode)	(__IS_FLG(inode, SB_SYNCHRONOUS|SB_DIRSYNC) || \
D
David Howells 已提交
1889
					((inode)->i_flags & (S_SYNC|S_DIRSYNC)))
1890 1891 1892
#define IS_MANDLOCK(inode)	__IS_FLG(inode, SB_MANDLOCK)
#define IS_NOATIME(inode)	__IS_FLG(inode, SB_RDONLY|SB_NOATIME)
#define IS_I_VERSION(inode)	__IS_FLG(inode, SB_I_VERSION)
D
David Howells 已提交
1893 1894 1895 1896

#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)
1897
#define IS_POSIXACL(inode)	__IS_FLG(inode, SB_POSIXACL)
D
David Howells 已提交
1898 1899 1900 1901 1902 1903 1904 1905

#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)
1906
#define IS_DAX(inode)		((inode)->i_flags & S_DAX)
1907
#define IS_ENCRYPTED(inode)	((inode)->i_flags & S_ENCRYPTED)
D
David Howells 已提交
1908

M
Miklos Szeredi 已提交
1909 1910 1911
#define IS_WHITEOUT(inode)	(S_ISCHR(inode->i_mode) && \
				 (inode)->i_rdev == WHITEOUT_DEV)

1912 1913 1914 1915 1916
static inline bool HAS_UNMAPPED_ID(struct inode *inode)
{
	return !uid_valid(inode->i_uid) || !gid_valid(inode->i_gid);
}

1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935
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
1936
/*
1937
 * Inode state bits.  Protected by inode->i_lock
J
Joern Engel 已提交
1938 1939 1940 1941 1942 1943 1944 1945
 *
 * 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
1946
 * Two bits are used for locking and completion notification, I_NEW and I_SYNC.
J
Joern Engel 已提交
1947
 *
J
Joern Engel 已提交
1948 1949
 * I_DIRTY_SYNC		Inode is dirty, but doesn't have to be written on
 *			fdatasync().  i_atime is the usual cause.
1950 1951 1952 1953
 * 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
1954
 * I_DIRTY_PAGES	Inode has dirty pages.  Inode itself may be clean.
C
Christoph Hellwig 已提交
1955 1956 1957 1958 1959 1960 1961 1962
 * 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
1963 1964 1965 1966 1967 1968
 * 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.
1969 1970
 * 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
1971 1972 1973 1974 1975
 *
 *			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
1976
 *			if appropriate.  I_NEW is used for waiting.
J
Joern Engel 已提交
1977
 *
1978 1979 1980 1981
 * 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
1982
 *
C
Christoph Hellwig 已提交
1983 1984 1985 1986
 * 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().
 *
1987 1988 1989 1990 1991
 * 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.
 *
1992 1993 1994
 * I_OVL_INUSE		Used by overlayfs to get exclusive ownership on upper
 *			and work dirs among overlayfs mounts.
 *
J
Joern Engel 已提交
1995 1996
 * Q: What is the difference between I_WILL_FREE and I_FREEING?
 */
1997 1998 1999
#define I_DIRTY_SYNC		(1 << 0)
#define I_DIRTY_DATASYNC	(1 << 1)
#define I_DIRTY_PAGES		(1 << 2)
C
Christoph Hellwig 已提交
2000 2001
#define __I_NEW			3
#define I_NEW			(1 << __I_NEW)
2002 2003 2004
#define I_WILL_FREE		(1 << 4)
#define I_FREEING		(1 << 5)
#define I_CLEAR			(1 << 6)
C
Christoph Hellwig 已提交
2005
#define __I_SYNC		7
J
Joern Engel 已提交
2006
#define I_SYNC			(1 << __I_SYNC)
2007
#define I_REFERENCED		(1 << 8)
C
Christoph Hellwig 已提交
2008
#define __I_DIO_WAKEUP		9
E
Eric Sandeen 已提交
2009
#define I_DIO_WAKEUP		(1 << __I_DIO_WAKEUP)
2010
#define I_LINKABLE		(1 << 10)
2011 2012 2013
#define I_DIRTY_TIME		(1 << 11)
#define __I_DIRTY_TIME_EXPIRED	12
#define I_DIRTY_TIME_EXPIRED	(1 << __I_DIRTY_TIME_EXPIRED)
2014
#define I_WB_SWITCH		(1 << 13)
2015
#define I_OVL_INUSE			(1 << 14)
L
Linus Torvalds 已提交
2016 2017

#define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES)
2018
#define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME)
L
Linus Torvalds 已提交
2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030

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
2031 2032 2033 2034
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);
2035 2036 2037 2038

static inline void inode_inc_link_count(struct inode *inode)
{
	inc_nlink(inode);
2039 2040 2041
	mark_inode_dirty(inode);
}

2042 2043 2044
static inline void inode_dec_link_count(struct inode *inode)
{
	drop_nlink(inode);
2045 2046 2047
	mark_inode_dirty(inode);
}

2048 2049 2050 2051 2052 2053 2054
enum file_time_flags {
	S_ATIME = 1,
	S_MTIME = 2,
	S_CTIME = 4,
	S_VERSION = 8,
};

A
Al Viro 已提交
2055
extern void touch_atime(const struct path *);
L
Linus Torvalds 已提交
2056 2057 2058
static inline void file_accessed(struct file *file)
{
	if (!(file->f_flags & O_NOATIME))
A
Al Viro 已提交
2059
		touch_atime(&file->f_path);
L
Linus Torvalds 已提交
2060 2061 2062
}

int sync_inode(struct inode *inode, struct writeback_control *wbc);
C
Christoph Hellwig 已提交
2063
int sync_inode_metadata(struct inode *inode, int wait);
L
Linus Torvalds 已提交
2064 2065 2066 2067

struct file_system_type {
	const char *name;
	int fs_flags;
D
David Howells 已提交
2068 2069 2070
#define FS_REQUIRES_DEV		1 
#define FS_BINARY_MOUNTDATA	2
#define FS_HAS_SUBTYPE		4
2071
#define FS_USERNS_MOUNT		8	/* Can be mounted by userns root */
D
David Howells 已提交
2072
#define FS_RENAME_DOES_D_MOVE	32768	/* FS will handle d_move() during rename() internally. */
A
Al Viro 已提交
2073 2074
	struct dentry *(*mount) (struct file_system_type *, int,
		       const char *, void *);
L
Linus Torvalds 已提交
2075 2076 2077
	void (*kill_sb) (struct super_block *);
	struct module *owner;
	struct file_system_type * next;
A
Al Viro 已提交
2078
	struct hlist_head fs_supers;
2079

I
Ingo Molnar 已提交
2080
	struct lock_class_key s_lock_key;
2081
	struct lock_class_key s_umount_key;
2082
	struct lock_class_key s_vfs_rename_key;
2083
	struct lock_class_key s_writers_key[SB_FREEZE_LEVELS];
2084 2085 2086

	struct lock_class_key i_lock_key;
	struct lock_class_key i_mutex_key;
2087
	struct lock_class_key i_mutex_dir_key;
L
Linus Torvalds 已提交
2088 2089
};

2090 2091
#define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME)

2092 2093 2094
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));
2095
#ifdef CONFIG_BLOCK
A
Al Viro 已提交
2096 2097 2098
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));
2099 2100 2101 2102 2103 2104 2105 2106
#else
static inline 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))
{
	return ERR_PTR(-ENODEV);
}
#endif
A
Al Viro 已提交
2107 2108 2109
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
2110 2111 2112
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
2113
extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path);
L
Linus Torvalds 已提交
2114
void generic_shutdown_super(struct super_block *sb);
2115
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2116
void kill_block_super(struct super_block *sb);
2117 2118 2119 2120 2121 2122
#else
static inline void kill_block_super(struct super_block *sb)
{
	BUG();
}
#endif
L
Linus Torvalds 已提交
2123 2124 2125
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
2126
void deactivate_locked_super(struct super_block *sb);
L
Linus Torvalds 已提交
2127
int set_anon_super(struct super_block *s, void *data);
2128 2129
int get_anon_bdev(dev_t *);
void free_anon_bdev(dev_t);
2130 2131 2132 2133 2134
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
2135 2136 2137
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
2138
			int flags, void *data);
2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151
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
2152 2153 2154 2155 2156 2157

/* 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)
2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168
/*
 * 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
2169 2170 2171

extern int register_filesystem(struct file_system_type *);
extern int unregister_filesystem(struct file_system_type *);
2172 2173
extern struct vfsmount *kern_mount_data(struct file_system_type *, void *data);
#define kern_mount(type) kern_mount_data(type, NULL)
2174
extern void kern_unmount(struct vfsmount *mnt);
L
Linus Torvalds 已提交
2175 2176
extern int may_umount_tree(struct vfsmount *);
extern int may_umount(struct vfsmount *);
2177 2178
extern long do_mount(const char *, const char __user *,
		     const char *, unsigned long, void *);
2179
extern struct vfsmount *collect_mounts(const struct path *);
2180
extern void drop_collected_mounts(struct vfsmount *);
A
Al Viro 已提交
2181 2182
extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *,
			  struct vfsmount *);
A
Al Viro 已提交
2183
extern int vfs_statfs(const struct path *, struct kstatfs *);
A
Al Viro 已提交
2184 2185
extern int user_statfs(const char __user *, struct kstatfs *);
extern int fd_statfs(int, struct kstatfs *);
2186 2187
extern int freeze_super(struct super_block *super);
extern int thaw_super(struct super_block *super);
2188
extern bool our_mnt(struct vfsmount *mnt);
2189 2190 2191
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
2192

A
Al Viro 已提交
2193 2194
extern int current_umask(void);

2195 2196
extern void ihold(struct inode * inode);
extern void iput(struct inode *);
2197
extern int generic_update_time(struct inode *, struct timespec *, int);
2198

M
Miklos Szeredi 已提交
2199
/* /sys/fs */
2200
extern struct kobject *fs_kobj;
M
Miklos Szeredi 已提交
2201

2202
#define MAX_RW_COUNT (INT_MAX & PAGE_MASK)
2203

2204
#ifdef CONFIG_MANDATORY_FILE_LOCKING
2205
extern int locks_mandatory_locked(struct file *);
2206
extern int locks_mandatory_area(struct inode *, struct file *, loff_t, loff_t, unsigned char);
L
Linus Torvalds 已提交
2207 2208 2209 2210 2211

/*
 * Candidates for mandatory locking have the setgid bit set
 * but no group execute bit -  an otherwise meaningless combination.
 */
2212 2213 2214 2215 2216 2217 2218

static inline int __mandatory_lock(struct inode *ino)
{
	return (ino->i_mode & (S_ISGID | S_IXGRP)) == S_ISGID;
}

/*
2219
 * ... and these candidates should be on SB_MANDLOCK mounted fs,
2220 2221 2222 2223 2224 2225 2226
 * 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
2227

2228
static inline int locks_verify_locked(struct file *file)
L
Linus Torvalds 已提交
2229
{
2230
	if (mandatory_lock(locks_inode(file)))
2231
		return locks_mandatory_locked(file);
L
Linus Torvalds 已提交
2232 2233 2234 2235
	return 0;
}

static inline int locks_verify_truncate(struct inode *inode,
2236
				    struct file *f,
L
Linus Torvalds 已提交
2237 2238
				    loff_t size)
{
2239 2240 2241 2242 2243 2244 2245 2246 2247 2248
	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
2249 2250
}

2251 2252 2253 2254 2255 2256 2257
#else /* !CONFIG_MANDATORY_FILE_LOCKING */

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

2258 2259
static inline int locks_mandatory_area(struct inode *inode, struct file *filp,
                                       loff_t start, loff_t end, unsigned char type)
2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288
{
	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
2289 2290
static inline int break_lease(struct inode *inode, unsigned int mode)
{
2291 2292
	/*
	 * Since this check is lockless, we must ensure that any refcounts
2293 2294 2295
	 * 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.
2296 2297
	 */
	smp_mb();
2298
	if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
J
J. Bruce Fields 已提交
2299
		return __break_lease(inode, mode, FL_LEASE);
L
Linus Torvalds 已提交
2300 2301
	return 0;
}
J
J. Bruce Fields 已提交
2302 2303 2304

static inline int break_deleg(struct inode *inode, unsigned int mode)
{
2305 2306
	/*
	 * Since this check is lockless, we must ensure that any refcounts
2307 2308 2309
	 * 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.
2310 2311
	 */
	smp_mb();
2312
	if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
J
J. Bruce Fields 已提交
2313
		return __break_lease(inode, mode, FL_DELEG);
L
Linus Torvalds 已提交
2314 2315
	return 0;
}
J
J. Bruce Fields 已提交
2316

2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338
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
2339 2340 2341 2342 2343 2344 2345 2346 2347 2348
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;
}

2349
#else /* !CONFIG_FILE_LOCKING */
2350 2351 2352 2353 2354
static inline int break_lease(struct inode *inode, unsigned int mode)
{
	return 0;
}

J
J. Bruce Fields 已提交
2355 2356 2357 2358
static inline int break_deleg(struct inode *inode, unsigned int mode)
{
	return 0;
}
2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370

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
2371 2372 2373 2374 2375
static inline int break_layout(struct inode *inode, bool wait)
{
	return 0;
}

2376
#endif /* CONFIG_FILE_LOCKING */
L
Linus Torvalds 已提交
2377 2378

/* fs/open.c */
2379
struct audit_names;
2380
struct filename {
2381 2382 2383
	const char		*name;	/* pointer to actual string */
	const __user char	*uptr;	/* original userland pointer */
	struct audit_names	*aname;
2384
	int			refcnt;
A
Al Viro 已提交
2385
	const char		iname[];
2386
};
L
Linus Torvalds 已提交
2387

A
Al Viro 已提交
2388
extern long vfs_truncate(const struct path *, loff_t);
2389 2390
extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs,
		       struct file *filp);
2391
extern int vfs_fallocate(struct file *file, int mode, loff_t offset,
2392
			loff_t len);
J
Jason Uhlenkott 已提交
2393
extern long do_sys_open(int dfd, const char __user *filename, int flags,
2394
			umode_t mode);
2395
extern struct file *file_open_name(struct filename *, int, umode_t);
2396
extern struct file *filp_open(const char *, int, umode_t);
A
Al Viro 已提交
2397
extern struct file *file_open_root(struct dentry *, struct vfsmount *,
2398
				   const char *, int, umode_t);
2399
extern struct file * dentry_open(const struct path *, int, const struct cred *);
L
Linus Torvalds 已提交
2400
extern int filp_close(struct file *, fl_owner_t id);
2401

2402
extern struct filename *getname_flags(const char __user *, int, int *);
2403
extern struct filename *getname(const char __user *);
2404
extern struct filename *getname_kernel(const char *);
2405
extern void putname(struct filename *name);
2406

2407 2408 2409 2410
enum {
	FILE_CREATED = 1,
	FILE_OPENED = 2
};
A
Al Viro 已提交
2411 2412 2413
extern int finish_open(struct file *file, struct dentry *dentry,
			int (*open)(struct inode *, struct file *),
			int *opened);
A
Al Viro 已提交
2414
extern int finish_no_open(struct file *file, struct dentry *dentry);
L
Linus Torvalds 已提交
2415

2416 2417 2418 2419
/* fs/ioctl.c */

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

L
Linus Torvalds 已提交
2420 2421
/* fs/dcache.c */
extern void __init vfs_caches_init_early(void);
2422
extern void __init vfs_caches_init(void);
L
Linus Torvalds 已提交
2423

2424 2425
extern struct kmem_cache *names_cachep;

2426
#define __getname()		kmem_cache_alloc(names_cachep, GFP_KERNEL)
V
Vegard Nossum 已提交
2427
#define __putname(name)		kmem_cache_free(names_cachep, (void *)(name))
L
Linus Torvalds 已提交
2428

2429
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2430
extern int register_blkdev(unsigned int, const char *);
A
Akinobu Mita 已提交
2431
extern void unregister_blkdev(unsigned int, const char *);
2432
extern void bdev_unhash_inode(dev_t dev);
L
Linus Torvalds 已提交
2433
extern struct block_device *bdget(dev_t);
2434
extern struct block_device *bdgrab(struct block_device *bdev);
L
Linus Torvalds 已提交
2435 2436 2437
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
2438
extern void invalidate_bdev(struct block_device *);
2439
extern void iterate_bdevs(void (*)(struct block_device *, void *), void *);
N
Nick Piggin 已提交
2440
extern int sync_blockdev(struct block_device *bdev);
A
Al Viro 已提交
2441
extern void kill_bdev(struct block_device *);
N
Nick Piggin 已提交
2442
extern struct super_block *freeze_bdev(struct block_device *);
2443
extern void emergency_thaw_all(void);
N
Nick Piggin 已提交
2444 2445
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
2446 2447 2448 2449 2450 2451 2452

extern struct super_block *blockdev_superblock;

static inline bool sb_is_blkdev_sb(struct super_block *sb)
{
	return sb == blockdev_superblock;
}
2453 2454
#else
static inline void bd_forget(struct inode *inode) {}
2455
static inline int sync_blockdev(struct block_device *bdev) { return 0; }
A
Al Viro 已提交
2456
static inline void kill_bdev(struct block_device *bdev) {}
2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467
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;
}
2468 2469 2470 2471

static inline void iterate_bdevs(void (*f)(struct block_device *, void *), void *arg)
{
}
2472

2473
static inline bool sb_is_blkdev_sb(struct super_block *sb)
2474
{
2475
	return false;
2476
}
2477
#endif
2478
extern int sync_filesystem(struct super_block *);
2479
extern const struct file_operations def_blk_fops;
2480
extern const struct file_operations def_chr_fops;
2481
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2482
extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long);
2483
extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long);
L
Linus Torvalds 已提交
2484
extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long);
2485
extern int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder);
2486 2487 2488 2489
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
2490
extern void blkdev_put(struct block_device *bdev, fmode_t mode);
2491 2492 2493
extern int __blkdev_reread_part(struct block_device *bdev);
extern int blkdev_reread_part(struct block_device *bdev);

2494
#ifdef CONFIG_SYSFS
2495
extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk);
2496 2497
extern void bd_unlink_disk_holder(struct block_device *bdev,
				  struct gendisk *disk);
2498
#else
2499 2500 2501 2502 2503
static inline int bd_link_disk_holder(struct block_device *bdev,
				      struct gendisk *disk)
{
	return 0;
}
2504 2505 2506 2507
static inline void bd_unlink_disk_holder(struct block_device *bdev,
					 struct gendisk *disk)
{
}
2508
#endif
2509
#endif
L
Linus Torvalds 已提交
2510 2511

/* fs/char_dev.c */
2512
#define CHRDEV_MAJOR_MAX 512
2513 2514
/* Marks the bottom of the first segment of free char majors */
#define CHRDEV_MAJOR_DYN_END 234
2515 2516 2517 2518
/* Marks the top and bottom of the second segment of free char majors */
#define CHRDEV_MAJOR_DYN_EXT_START 511
#define CHRDEV_MAJOR_DYN_EXT_END 384

L
Linus Torvalds 已提交
2519 2520
extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *);
extern int register_chrdev_region(dev_t, unsigned, const char *);
2521 2522 2523 2524 2525
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
2526
extern void unregister_chrdev_region(dev_t, unsigned);
2527
extern void chrdev_show(struct seq_file *,off_t);
L
Linus Torvalds 已提交
2528

2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539
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
2540 2541
/* fs/block_dev.c */
#define BDEVNAME_SIZE	32	/* Largest string for a blockdev identifier */
2542
#define BDEVT_SIZE	10	/* Largest string for MAJ:MIN for blkdev */
2543 2544

#ifdef CONFIG_BLOCK
2545
#define BLKDEV_MAJOR_MAX	512
L
Linus Torvalds 已提交
2546 2547 2548
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 *);
2549
extern void blkdev_show(struct seq_file *,off_t);
2550

2551
#else
2552
#define BLKDEV_MAJOR_MAX	0
2553
#endif
L
Linus Torvalds 已提交
2554 2555 2556 2557 2558

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 *);
2559
extern bool is_bad_inode(struct inode *);
L
Linus Torvalds 已提交
2560

2561
#ifdef CONFIG_BLOCK
2562 2563
extern void check_disk_size_change(struct gendisk *disk,
				   struct block_device *bdev);
2564
extern int revalidate_disk(struct gendisk *);
L
Linus Torvalds 已提交
2565
extern int check_disk_change(struct block_device *);
2566
extern int __invalidate_device(struct block_device *, bool);
L
Linus Torvalds 已提交
2567
extern int invalidate_partition(struct gendisk *, int);
2568
#endif
L
Linus Torvalds 已提交
2569 2570
unsigned long invalidate_mapping_pages(struct address_space *mapping,
					pgoff_t start, pgoff_t end);
2571

L
Linus Torvalds 已提交
2572 2573 2574 2575
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))
2576
		invalidate_mapping_pages(inode->i_mapping, 0, -1);
L
Linus Torvalds 已提交
2577 2578 2579 2580 2581 2582 2583
}
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 *);
2584
extern int filemap_fdatawait_keep_errors(struct address_space *mapping);
2585 2586
extern int filemap_fdatawait_range(struct address_space *, loff_t lstart,
				   loff_t lend);
2587 2588 2589 2590 2591 2592

static inline int filemap_fdatawait(struct address_space *mapping)
{
	return filemap_fdatawait_range(mapping, 0, LLONG_MAX);
}

2593 2594
extern bool filemap_range_has_page(struct address_space *, loff_t lstart,
				  loff_t lend);
2595 2596
extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart,
						loff_t lend);
L
Linus Torvalds 已提交
2597 2598 2599
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);
2600 2601
extern int __filemap_fdatawrite_range(struct address_space *mapping,
				loff_t start, loff_t end, int sync_mode);
2602 2603
extern int filemap_fdatawrite_range(struct address_space *mapping,
				loff_t start, loff_t end);
2604
extern int filemap_check_errors(struct address_space *mapping);
2605
extern void __filemap_set_wb_err(struct address_space *mapping, int err);
2606 2607 2608

extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart,
						loff_t lend);
2609 2610 2611 2612
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);

2613 2614 2615 2616 2617
static inline int file_write_and_wait(struct file *file)
{
	return file_write_and_wait_range(file, 0, LLONG_MAX);
}

2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666
/**
 * 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.
 */
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);
}

2667 2668 2669
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);
2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686

/*
 * 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;
2687
}
2688

L
Linus Torvalds 已提交
2689 2690
extern void emergency_sync(void);
extern void emergency_remount(void);
2691
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2692
extern sector_t bmap(struct inode *, sector_t);
2693
#endif
2694
extern int notify_change(struct dentry *, struct iattr *, struct inode **);
2695
extern int inode_permission(struct inode *, int);
2696
extern int generic_permission(struct inode *, int);
M
Miklos Szeredi 已提交
2697
extern int __check_sticky(struct inode *dir, struct inode *inode);
L
Linus Torvalds 已提交
2698

2699 2700 2701 2702 2703
static inline bool execute_ok(struct inode *inode)
{
	return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode);
}

2704 2705 2706 2707 2708 2709 2710
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);
}

2711 2712 2713 2714 2715 2716 2717
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);
}

2718 2719 2720 2721 2722 2723 2724
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);
}

2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737
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;
}

2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759
/*
 * 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
2760
	struct inode *inode = file_inode(file);
2761 2762
	return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY;
}
L
Linus Torvalds 已提交
2763 2764 2765 2766 2767 2768 2769
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
2770
		atomic_inc(&file_inode(file)->i_writecount);
L
Linus Torvalds 已提交
2771
}
2772 2773 2774 2775 2776
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
2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796
#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
2797
extern int do_pipe_flags(int *, int);
L
Linus Torvalds 已提交
2798

2799 2800 2801
#define __kernel_read_file_id(id) \
	id(UNKNOWN, unknown)		\
	id(FIRMWARE, firmware)		\
2802
	id(FIRMWARE_PREALLOC_BUFFER, firmware)	\
2803 2804 2805 2806
	id(MODULE, kernel-module)		\
	id(KEXEC_IMAGE, kexec-image)		\
	id(KEXEC_INITRAMFS, kexec-initramfs)	\
	id(POLICY, security-policy)		\
2807
	id(X509_CERTIFICATE, x509-certificate)	\
2808 2809 2810 2811 2812
	id(MAX_ID, )

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

2813
enum kernel_read_file_id {
2814 2815 2816 2817 2818
	__kernel_read_file_id(__fid_enumify)
};

static const char * const kernel_read_file_str[] = {
	__kernel_read_file_id(__fid_stringify)
2819 2820
};

K
Kees Cook 已提交
2821
static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id)
2822
{
2823
	if ((unsigned)id >= READING_MAX_ID)
2824 2825 2826 2827 2828
		return kernel_read_file_str[READING_UNKNOWN];

	return kernel_read_file_str[id];
}

2829 2830
extern int kernel_read_file(struct file *, void **, loff_t *, loff_t,
			    enum kernel_read_file_id);
2831
extern int kernel_read_file_from_path(const char *, void **, loff_t *, loff_t,
2832
				      enum kernel_read_file_id);
2833 2834
extern int kernel_read_file_from_fd(int, void **, loff_t *, loff_t,
				    enum kernel_read_file_id);
2835
extern ssize_t kernel_read(struct file *, void *, size_t, loff_t *);
2836
extern ssize_t kernel_write(struct file *, const void *, size_t, loff_t *);
2837
extern ssize_t __kernel_write(struct file *, const void *, size_t, loff_t *);
L
Linus Torvalds 已提交
2838 2839 2840
extern struct file * open_exec(const char *);
 
/* fs/dcache.c -- generic fs support functions */
Y
Yaowei Bai 已提交
2841
extern bool is_subdir(struct dentry *, struct dentry *);
2842
extern bool path_is_under(const struct path *, const struct path *);
L
Linus Torvalds 已提交
2843

M
Miklos Szeredi 已提交
2844 2845
extern char *file_path(struct file *, char *, int);

L
Linus Torvalds 已提交
2846 2847 2848
#include <linux/err.h>

/* needed for stackable file system support */
2849
extern loff_t default_llseek(struct file *file, loff_t offset, int whence);
L
Linus Torvalds 已提交
2850

2851
extern loff_t vfs_llseek(struct file *file, loff_t offset, int whence);
L
Linus Torvalds 已提交
2852

2853
extern int inode_init_always(struct super_block *, struct inode *);
L
Linus Torvalds 已提交
2854
extern void inode_init_once(struct inode *);
2855
extern void address_space_init_once(struct address_space *mapping);
L
Linus Torvalds 已提交
2856 2857 2858
extern struct inode * igrab(struct inode *);
extern ino_t iunique(struct super_block *, ino_t);
extern int inode_needs_sync(struct inode *inode);
2859
extern int generic_delete_inode(struct inode *inode);
2860 2861 2862 2863
static inline int generic_drop_inode(struct inode *inode)
{
	return !inode->i_nlink || inode_unhashed(inode);
}
L
Linus Torvalds 已提交
2864

2865 2866 2867
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
2868 2869 2870 2871 2872 2873
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);
2874 2875 2876 2877 2878
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
2879 2880
extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *);
extern int insert_inode_locked(struct inode *);
2881 2882 2883 2884 2885
#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
2886
extern void unlock_new_inode(struct inode *);
2887
extern unsigned int get_next_ino(void);
2888
extern void evict_inodes(struct super_block *sb);
L
Linus Torvalds 已提交
2889 2890

extern void __iget(struct inode * inode);
2891
extern void iget_failed(struct inode *);
2892
extern void clear_inode(struct inode *);
C
Christoph Hellwig 已提交
2893
extern void __destroy_inode(struct inode *);
2894 2895
extern struct inode *new_inode_pseudo(struct super_block *sb);
extern struct inode *new_inode(struct super_block *sb);
2896
extern void free_inode_nonrcu(struct inode *inode);
2897
extern int should_remove_suid(struct dentry *);
2898
extern int file_remove_privs(struct file *);
L
Linus Torvalds 已提交
2899 2900

extern void __insert_inode_hash(struct inode *, unsigned long hashval);
2901 2902
static inline void insert_inode_hash(struct inode *inode)
{
L
Linus Torvalds 已提交
2903 2904
	__insert_inode_hash(inode, inode->i_ino);
}
2905 2906 2907 2908

extern void __remove_inode_hash(struct inode *);
static inline void remove_inode_hash(struct inode *inode)
{
2909
	if (!inode_unhashed(inode) && !hlist_fake(&inode->i_hash))
2910 2911 2912
		__remove_inode_hash(inode);
}

2913
extern void inode_sb_list_add(struct inode *inode);
L
Linus Torvalds 已提交
2914

2915
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
2916
extern int bdev_read_only(struct block_device *);
2917
#endif
L
Linus Torvalds 已提交
2918 2919 2920 2921 2922 2923
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 *);
2924
extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *);
A
Al Viro 已提交
2925
extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *);
2926 2927
extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *);
extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *);
2928
extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *);
2929
extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t);
A
Andrew Morton 已提交
2930

2931
ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos,
C
Christoph Hellwig 已提交
2932
		rwf_t flags);
2933
ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos,
C
Christoph Hellwig 已提交
2934
		rwf_t flags);
2935

2936
/* fs/block_dev.c */
2937
extern ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to);
2938
extern ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from);
2939 2940
extern int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
			int datasync);
A
Al Viro 已提交
2941
extern void block_sync_page(struct page *page);
2942

A
Andrew Morton 已提交
2943
/* fs/splice.c */
2944
extern ssize_t generic_file_splice_read(struct file *, loff_t *,
A
Andrew Morton 已提交
2945
		struct pipe_inode_info *, size_t, unsigned int);
A
Al Viro 已提交
2946
extern ssize_t iter_file_splice_write(struct pipe_inode_info *,
2947
		struct file *, loff_t *, size_t, unsigned int);
A
Andrew Morton 已提交
2948
extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
2949
		struct file *out, loff_t *, size_t len, unsigned int flags);
2950 2951 2952
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
2953

L
Linus Torvalds 已提交
2954 2955
extern void
file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping);
2956 2957
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
2958
extern loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize);
2959
extern loff_t generic_file_llseek(struct file *file, loff_t offset, int whence);
A
Andi Kleen 已提交
2960
extern loff_t generic_file_llseek_size(struct file *file, loff_t offset,
2961
		int whence, loff_t maxsize, loff_t eof);
A
Al Viro 已提交
2962 2963
extern loff_t fixed_size_llseek(struct file *file, loff_t offset,
		int whence, loff_t size);
2964 2965
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
2966 2967 2968
extern int generic_file_open(struct inode * inode, struct file * filp);
extern int nonseekable_open(struct inode * inode, struct file * filp);

2969
#ifdef CONFIG_BLOCK
2970
typedef void (dio_submit_t)(struct bio *bio, struct inode *inode,
2971
			    loff_t file_offset);
L
Linus Torvalds 已提交
2972 2973

enum {
2974 2975 2976 2977 2978
	/* need locking between buffered and direct access */
	DIO_LOCKING	= 0x01,

	/* filesystem does not support filling holes */
	DIO_SKIP_HOLES	= 0x02,
2979 2980 2981

	/* filesystem can handle aio writes beyond i_size */
	DIO_ASYNC_EXTEND = 0x04,
2982 2983 2984

	/* inode/fs/bdev does not need truncate protection */
	DIO_SKIP_DIO_COUNT = 0x08,
L
Linus Torvalds 已提交
2985 2986
};

2987
void dio_end_io(struct bio *bio);
2988
void dio_warn_stale_pagecache(struct file *filp);
2989

2990 2991
ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
			     struct block_device *bdev, struct iov_iter *iter,
2992
			     get_block_t get_block,
2993 2994
			     dio_iodone_t end_io, dio_submit_t submit_io,
			     int flags);
2995

2996 2997
static inline ssize_t blockdev_direct_IO(struct kiocb *iocb,
					 struct inode *inode,
2998
					 struct iov_iter *iter,
2999
					 get_block_t get_block)
L
Linus Torvalds 已提交
3000
{
3001
	return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
3002
			get_block, NULL, NULL, DIO_LOCKING | DIO_SKIP_HOLES);
L
Linus Torvalds 已提交
3003
}
3004
#endif
L
Linus Torvalds 已提交
3005

3006
void inode_dio_wait(struct inode *inode);
3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031

/*
 * 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);
}
3032

3033 3034 3035
extern void inode_set_flags(struct inode *inode, unsigned int flags,
			    unsigned int mask);

3036
extern const struct file_operations generic_ro_fops;
L
Linus Torvalds 已提交
3037 3038 3039

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

A
Al Viro 已提交
3040
extern int readlink_copy(char __user *, int, const char *);
L
Linus Torvalds 已提交
3041
extern int page_readlink(struct dentry *, char __user *, int);
3042 3043 3044
extern const char *page_get_link(struct dentry *, struct inode *,
				 struct delayed_call *);
extern void page_put_link(void *);
3045
extern int __page_symlink(struct inode *inode, const char *symname, int len,
3046
		int nofs);
L
Linus Torvalds 已提交
3047
extern int page_symlink(struct inode *inode, const char *symname, int len);
3048
extern const struct inode_operations page_symlink_inode_operations;
3049
extern void kfree_link(void *);
L
Linus Torvalds 已提交
3050
extern void generic_fillattr(struct inode *, struct kstat *);
3051 3052
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);
3053
void __inode_add_bytes(struct inode *inode, loff_t bytes);
L
Linus Torvalds 已提交
3054
void inode_add_bytes(struct inode *inode, loff_t bytes);
3055
void __inode_sub_bytes(struct inode *inode, loff_t bytes);
L
Linus Torvalds 已提交
3056
void inode_sub_bytes(struct inode *inode, loff_t bytes);
J
Jan Kara 已提交
3057 3058 3059 3060
static inline loff_t __inode_get_bytes(struct inode *inode)
{
	return (((loff_t)inode->i_blocks) << 9) + inode->i_bytes;
}
L
Linus Torvalds 已提交
3061 3062
loff_t inode_get_bytes(struct inode *inode);
void inode_set_bytes(struct inode *inode, loff_t bytes);
3063 3064
const char *simple_get_link(struct dentry *, struct inode *,
			    struct delayed_call *);
A
Al Viro 已提交
3065
extern const struct inode_operations simple_symlink_inode_operations;
L
Linus Torvalds 已提交
3066

3067
extern int iterate_dir(struct file *, struct dir_context *);
L
Linus Torvalds 已提交
3068

3069 3070 3071 3072 3073
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)
{
3074 3075
	return vfs_statx(AT_FDCWD, filename, AT_NO_AUTOMOUNT,
			 stat, STATX_BASIC_STATS);
3076 3077 3078
}
static inline int vfs_lstat(const char __user *name, struct kstat *stat)
{
3079
	return vfs_statx(AT_FDCWD, name, AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT,
3080 3081 3082 3083 3084
			 stat, STATX_BASIC_STATS);
}
static inline int vfs_fstatat(int dfd, const char __user *filename,
			      struct kstat *stat, int flags)
{
3085 3086
	return vfs_statx(dfd, filename, flags | AT_NO_AUTOMOUNT,
			 stat, STATX_BASIC_STATS);
3087 3088 3089 3090 3091 3092 3093
}
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
3094
extern const char *vfs_get_link(struct dentry *, struct delayed_call *);
3095
extern int vfs_readlink(struct dentry *, char __user *, int);
L
Linus Torvalds 已提交
3096

3097
extern int __generic_block_fiemap(struct inode *inode,
J
Josef Bacik 已提交
3098 3099 3100
				  struct fiemap_extent_info *fieinfo,
				  loff_t start, loff_t len,
				  get_block_t *get_block);
3101 3102 3103
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
3104

3105
extern struct file_system_type *get_filesystem(struct file_system_type *fs);
3106
extern void put_filesystem(struct file_system_type *fs);
L
Linus Torvalds 已提交
3107 3108
extern struct file_system_type *get_fs_type(const char *name);
extern struct super_block *get_super(struct block_device *);
3109
extern struct super_block *get_super_thawed(struct block_device *);
3110
extern struct super_block *get_super_exclusive_thawed(struct block_device *bdev);
3111
extern struct super_block *get_active_super(struct block_device *bdev);
L
Linus Torvalds 已提交
3112
extern void drop_super(struct super_block *sb);
3113
extern void drop_super_exclusive(struct super_block *sb);
A
Al Viro 已提交
3114
extern void iterate_supers(void (*)(struct super_block *, void *), void *);
A
Al Viro 已提交
3115 3116
extern void iterate_supers_type(struct file_system_type *,
			        void (*)(struct super_block *, void *), void *);
L
Linus Torvalds 已提交
3117 3118 3119 3120

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);
3121
extern int dcache_readdir(struct file *, struct dir_context *);
3122
extern int simple_setattr(struct dentry *, struct iattr *);
3123
extern int simple_getattr(const struct path *, struct kstat *, u32, unsigned int);
3124
extern int simple_statfs(struct dentry *, struct kstatfs *);
S
Stephen Boyd 已提交
3125
extern int simple_open(struct inode *inode, struct file *file);
L
Linus Torvalds 已提交
3126 3127 3128
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 *);
3129 3130
extern int simple_rename(struct inode *, struct dentry *,
			 struct inode *, struct dentry *, unsigned int);
3131
extern int noop_fsync(struct file *, loff_t, loff_t, int);
L
Linus Torvalds 已提交
3132 3133
extern int simple_empty(struct dentry *);
extern int simple_readpage(struct file *file, struct page *page);
3134 3135 3136 3137 3138 3139
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);
3140
extern int always_delete_dentry(const struct dentry *);
A
Al Viro 已提交
3141
extern struct inode *alloc_anon_inode(struct super_block *);
3142
extern int simple_nosetlease(struct file *, long, struct file_lock **, void **);
3143
extern const struct dentry_operations simple_dentry_operations;
L
Linus Torvalds 已提交
3144

A
Al Viro 已提交
3145
extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags);
L
Linus Torvalds 已提交
3146
extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *);
3147
extern const struct file_operations simple_dir_operations;
3148
extern const struct inode_operations simple_dir_inode_operations;
3149 3150
extern void make_empty_dir_inode(struct inode *inode);
extern bool is_empty_dir_inode(struct inode *inode);
3151
struct tree_descr { const char *name; const struct file_operations *ops; int mode; };
L
Linus Torvalds 已提交
3152
struct dentry *d_alloc_name(struct dentry *, const char *);
3153 3154
extern int simple_fill_super(struct super_block *, unsigned long,
			     const struct tree_descr *);
3155
extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count);
L
Linus Torvalds 已提交
3156 3157
extern void simple_release_fs(struct vfsmount **mount, int *count);

3158 3159
extern ssize_t simple_read_from_buffer(void __user *to, size_t count,
			loff_t *ppos, const void *from, size_t available);
3160 3161
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
3162

3163
extern int __generic_file_fsync(struct file *, loff_t, loff_t, int);
3164
extern int generic_file_fsync(struct file *, loff_t, loff_t, int);
A
Al Viro 已提交
3165

3166 3167
extern int generic_check_addressable(unsigned, u64);

3168
#ifdef CONFIG_MIGRATION
3169
extern int buffer_migrate_page(struct address_space *,
3170 3171
				struct page *, struct page *,
				enum migrate_mode);
3172 3173 3174 3175
#else
#define buffer_migrate_page NULL
#endif

3176
extern int setattr_prepare(struct dentry *, struct iattr *);
N
npiggin@suse.de 已提交
3177
extern int inode_newsize_ok(const struct inode *, loff_t offset);
C
Christoph Hellwig 已提交
3178
extern void setattr_copy(struct inode *inode, const struct iattr *attr);
L
Linus Torvalds 已提交
3179

3180
extern int file_update_time(struct file *file);
L
Linus Torvalds 已提交
3181

3182 3183
static inline bool io_is_direct(struct file *filp)
{
3184
	return (filp->f_flags & O_DIRECT) || IS_DAX(filp->f_mapping->host);
3185 3186
}

3187 3188 3189 3190 3191
static inline bool vma_is_dax(struct vm_area_struct *vma)
{
	return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host);
}

3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205
static inline bool vma_is_fsdax(struct vm_area_struct *vma)
{
	struct inode *inode;

	if (!vma->vm_file)
		return false;
	if (!vma_is_dax(vma))
		return false;
	inode = file_inode(vma->vm_file);
	if (inode->i_mode == S_IFCHR)
		return false; /* device-dax */
	return true;
}

3206 3207 3208 3209 3210 3211 3212
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;
3213 3214 3215 3216
	if ((file->f_flags & O_DSYNC) || IS_SYNC(file->f_mapping->host))
		res |= IOCB_DSYNC;
	if (file->f_flags & __O_SYNC)
		res |= IOCB_SYNC;
3217 3218 3219
	return res;
}

C
Christoph Hellwig 已提交
3220
static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
3221 3222 3223 3224
{
	if (unlikely(flags & ~RWF_SUPPORTED))
		return -EOPNOTSUPP;

3225
	if (flags & RWF_NOWAIT) {
3226
		if (!(ki->ki_filp->f_mode & FMODE_NOWAIT))
3227 3228 3229
			return -EOPNOTSUPP;
		ki->ki_flags |= IOCB_NOWAIT;
	}
3230 3231 3232 3233 3234 3235
	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);
J
Jürg Billeter 已提交
3236 3237
	if (flags & RWF_APPEND)
		ki->ki_flags |= IOCB_APPEND;
3238 3239 3240
	return 0;
}

L
Linus Torvalds 已提交
3241 3242 3243 3244
static inline ino_t parent_ino(struct dentry *dentry)
{
	ino_t res;

N
Nick Piggin 已提交
3245 3246 3247 3248
	/*
	 * 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
3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273
	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);

3274
void simple_transaction_set(struct file *file, size_t n);
L
Linus Torvalds 已提交
3275

3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297
/*
 * 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);	\
}									\
3298
static const struct file_operations __fops = {				\
3299 3300
	.owner	 = THIS_MODULE,						\
	.open	 = __fops ## _open,					\
3301
	.release = simple_attr_release,					\
3302 3303
	.read	 = simple_attr_read,					\
	.write	 = simple_attr_write,					\
3304
	.llseek	 = generic_file_llseek,					\
3305
}
3306

3307 3308
static inline __printf(1, 2)
void __simple_attr_check_format(const char *fmt, ...)
3309 3310 3311 3312 3313
{
	/* don't do anything, just let the compiler check the arguments; */
}

int simple_attr_open(struct inode *inode, struct file *file,
3314
		     int (*get)(void *, u64 *), int (*set)(void *, u64),
3315
		     const char *fmt);
3316
int simple_attr_release(struct inode *inode, struct file *file);
3317 3318 3319 3320 3321
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
3322
struct ctl_table;
3323
int proc_nr_files(struct ctl_table *table, int write,
3324
		  void __user *buffer, size_t *lenp, loff_t *ppos);
3325 3326
int proc_nr_dentry(struct ctl_table *table, int write,
		  void __user *buffer, size_t *lenp, loff_t *ppos);
3327 3328
int proc_nr_inodes(struct ctl_table *table, int write,
		   void __user *buffer, size_t *lenp, loff_t *ppos);
3329
int __init get_filesystem_list(char *buf);
3330

N
Namhyung Kim 已提交
3331
#define __FMODE_EXEC		((__force int) FMODE_EXEC)
3332 3333
#define __FMODE_NONOTIFY	((__force int) FMODE_NONOTIFY)

A
Al Viro 已提交
3334
#define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE])
E
Eric Paris 已提交
3335
#define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \
3336
					    (flag & __FMODE_NONOTIFY)))
A
Al Viro 已提交
3337

Y
Yaowei Bai 已提交
3338
static inline bool is_sxid(umode_t mode)
3339 3340 3341 3342
{
	return (mode & S_ISUID) || ((mode & S_ISGID) && (mode & S_IXGRP));
}

M
Miklos Szeredi 已提交
3343 3344 3345 3346 3347 3348 3349 3350
static inline int check_sticky(struct inode *dir, struct inode *inode)
{
	if (!(dir->i_mode & S_ISVTX))
		return 0;

	return __check_sticky(dir, inode);
}

3351 3352
static inline void inode_has_no_xattr(struct inode *inode)
{
3353
	if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & SB_NOSEC))
3354 3355 3356
		inode->i_flags |= S_NOSEC;
}

A
Al Viro 已提交
3357 3358 3359 3360 3361
static inline bool is_root_inode(struct inode *inode)
{
	return inode == inode->i_sb->s_root->d_inode;
}

3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391
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
3392 3393
static inline bool dir_relax(struct inode *inode)
{
A
Al Viro 已提交
3394 3395
	inode_unlock(inode);
	inode_lock(inode);
A
Al Viro 已提交
3396 3397
	return !IS_DEADDIR(inode);
}
3398

A
Al Viro 已提交
3399 3400 3401 3402 3403 3404 3405
static inline bool dir_relax_shared(struct inode *inode)
{
	inode_unlock_shared(inode);
	inode_lock_shared(inode);
	return !IS_DEADDIR(inode);
}

3406
extern bool path_noexec(const struct path *path);
3407
extern void inode_nohighmem(struct inode *inode);
3408

L
Linus Torvalds 已提交
3409
#endif /* _LINUX_FS_H */