fs.h 90.9 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1 2 3 4 5 6 7 8
#ifndef _LINUX_FS_H
#define _LINUX_FS_H


#include <linux/linkage.h>
#include <linux/wait.h>
#include <linux/kdev_t.h>
#include <linux/dcache.h>
9
#include <linux/path.h>
Linus Torvalds's avatar
Linus Torvalds committed
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>
Linus Torvalds's avatar
Linus Torvalds committed
15
#include <linux/radix-tree.h>
16
#include <linux/rbtree.h>
Linus Torvalds's avatar
Linus Torvalds committed
17
#include <linux/init.h>
18
#include <linux/pid.h>
19
#include <linux/bug.h>
20
#include <linux/mutex.h>
21
#include <linux/capability.h>
22
#include <linux/semaphore.h>
Mark Fasheh's avatar
Mark Fasheh committed
23
#include <linux/fiemap.h>
24
#include <linux/rculist_bl.h>
25
#include <linux/atomic.h>
26
#include <linux/shrinker.h>
27
#include <linux/migrate_mode.h>
28
#include <linux/uidgid.h>
29
#include <linux/lockdep.h>
30
#include <linux/percpu-rwsem.h>
31
#include <linux/blk_types.h>
Linus Torvalds's avatar
Linus Torvalds committed
32 33

#include <asm/byteorder.h>
34
#include <uapi/linux/fs.h>
Linus Torvalds's avatar
Linus Torvalds committed
35

36
struct export_operations;
37
struct hd_geometry;
Linus Torvalds's avatar
Linus Torvalds committed
38 39
struct iovec;
struct nameidata;
40
struct kiocb;
Alexey Dobriyan's avatar
Alexey Dobriyan committed
41
struct kobject;
Linus Torvalds's avatar
Linus Torvalds committed
42 43 44 45 46
struct pipe_inode_info;
struct poll_table_struct;
struct kstatfs;
struct vm_area_struct;
struct vfsmount;
47
struct cred;
48
struct swap_info_struct;
49
struct seq_file;
50
struct workqueue_struct;
Linus Torvalds's avatar
Linus Torvalds committed
51

52
extern void __init inode_init(void);
Linus Torvalds's avatar
Linus Torvalds committed
53 54 55
extern void __init inode_init_early(void);
extern void __init files_init(unsigned long);

56
extern struct files_stat_struct files_stat;
57
extern unsigned long get_max_files(void);
58 59 60
extern int sysctl_nr_open;
extern struct inodes_stat_t inodes_stat;
extern int leases_enable, lease_break_time;
Kees Cook's avatar
Kees Cook committed
61 62
extern int sysctl_protected_symlinks;
extern int sysctl_protected_hardlinks;
63

Linus Torvalds's avatar
Linus Torvalds committed
64 65 66
struct buffer_head;
typedef int (get_block_t)(struct inode *inode, sector_t iblock,
			struct buffer_head *bh_result, int create);
67
typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
68
			ssize_t bytes, void *private);
Linus Torvalds's avatar
Linus Torvalds committed
69

70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136
#define MAY_EXEC		0x00000001
#define MAY_WRITE		0x00000002
#define MAY_READ		0x00000004
#define MAY_APPEND		0x00000008
#define MAY_ACCESS		0x00000010
#define MAY_OPEN		0x00000020
#define MAY_CHDIR		0x00000040
/* called from RCU mode, don't block */
#define MAY_NOT_BLOCK		0x00000080

/*
 * flags in file.f_mode.  Note that FMODE_READ and FMODE_WRITE must correspond
 * to O_WRONLY and O_RDWR via the strange trick in __dentry_open()
 */

/* file is open for reading */
#define FMODE_READ		((__force fmode_t)0x1)
/* file is open for writing */
#define FMODE_WRITE		((__force fmode_t)0x2)
/* file is seekable */
#define FMODE_LSEEK		((__force fmode_t)0x4)
/* file can be accessed using pread */
#define FMODE_PREAD		((__force fmode_t)0x8)
/* file can be accessed using pwrite */
#define FMODE_PWRITE		((__force fmode_t)0x10)
/* File is opened for execution with sys_execve / sys_uselib */
#define FMODE_EXEC		((__force fmode_t)0x20)
/* File is opened with O_NDELAY (only set for block devices) */
#define FMODE_NDELAY		((__force fmode_t)0x40)
/* File is opened with O_EXCL (only set for block devices) */
#define FMODE_EXCL		((__force fmode_t)0x80)
/* File is opened using open(.., 3, ..) and is writeable only for ioctls
   (specialy hack for floppy.c) */
#define FMODE_WRITE_IOCTL	((__force fmode_t)0x100)
/* 32bit hashes as llseek() offset (for directories) */
#define FMODE_32BITHASH         ((__force fmode_t)0x200)
/* 64bit hashes as llseek() offset (for directories) */
#define FMODE_64BITHASH         ((__force fmode_t)0x400)

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

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

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

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

/* File was opened by fanotify and shouldn't generate fanotify events */
#define FMODE_NONOTIFY		((__force fmode_t)0x1000000)

/*
 * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector
 * that indicates that they should check the contents of the iovec are
 * valid, but not check the memory that the iovec elements
 * points too.
 */
#define CHECK_IOVEC_ONLY -1

137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194
/*
 * The below are the various read and write types that we support. Some of
 * them include behavioral modifiers that send information down to the
 * block layer and IO scheduler. Terminology:
 *
 *	The block layer uses device plugging to defer IO a little bit, in
 *	the hope that we will see more IO very shortly. This increases
 *	coalescing of adjacent IO and thus reduces the number of IOs we
 *	have to send to the device. It also allows for better queuing,
 *	if the IO isn't mergeable. If the caller is going to be waiting
 *	for the IO, then he must ensure that the device is unplugged so
 *	that the IO is dispatched to the driver.
 *
 *	All IO is handled async in Linux. This is fine for background
 *	writes, but for reads or writes that someone waits for completion
 *	on, we want to notify the block layer and IO scheduler so that they
 *	know about it. That allows them to make better scheduling
 *	decisions. So when the below references 'sync' and 'async', it
 *	is referencing this priority hint.
 *
 * With that in mind, the available types are:
 *
 * READ			A normal read operation. Device will be plugged.
 * READ_SYNC		A synchronous read. Device is not plugged, caller can
 *			immediately wait on this read without caring about
 *			unplugging.
 * READA		Used for read-ahead operations. Lower priority, and the
 *			block layer could (in theory) choose to ignore this
 *			request if it runs into resource problems.
 * WRITE		A normal async write. Device will be plugged.
 * WRITE_SYNC		Synchronous write. Identical to WRITE, but passes down
 *			the hint that someone will be waiting on this IO
 *			shortly. The write equivalent of READ_SYNC.
 * WRITE_ODIRECT	Special case write for O_DIRECT only.
 * WRITE_FLUSH		Like WRITE_SYNC but with preceding cache flush.
 * WRITE_FUA		Like WRITE_SYNC but data is guaranteed to be on
 *			non-volatile media on completion.
 * WRITE_FLUSH_FUA	Combination of WRITE_FLUSH and FUA. The IO is preceded
 *			by a cache flush and data is guaranteed to be on
 *			non-volatile media on completion.
 *
 */
#define RW_MASK			REQ_WRITE
#define RWA_MASK		REQ_RAHEAD

#define READ			0
#define WRITE			RW_MASK
#define READA			RWA_MASK
#define KERNEL_READ		(READ|REQ_KERNEL)
#define KERNEL_WRITE		(WRITE|REQ_KERNEL)

#define READ_SYNC		(READ | REQ_SYNC)
#define WRITE_SYNC		(WRITE | REQ_SYNC | REQ_NOIDLE)
#define WRITE_ODIRECT		(WRITE | REQ_SYNC)
#define WRITE_FLUSH		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH)
#define WRITE_FUA		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FUA)
#define WRITE_FLUSH_FUA		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH | REQ_FUA)

Linus Torvalds's avatar
Linus Torvalds committed
195 196 197 198
/*
 * Attribute flags.  These should be or-ed together to figure out what
 * has been changed!
 */
199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215
#define ATTR_MODE	(1 << 0)
#define ATTR_UID	(1 << 1)
#define ATTR_GID	(1 << 2)
#define ATTR_SIZE	(1 << 3)
#define ATTR_ATIME	(1 << 4)
#define ATTR_MTIME	(1 << 5)
#define ATTR_CTIME	(1 << 6)
#define ATTR_ATIME_SET	(1 << 7)
#define ATTR_MTIME_SET	(1 << 8)
#define ATTR_FORCE	(1 << 9) /* Not a change, but a change it */
#define ATTR_ATTR_FLAG	(1 << 10)
#define ATTR_KILL_SUID	(1 << 11)
#define ATTR_KILL_SGID	(1 << 12)
#define ATTR_FILE	(1 << 13)
#define ATTR_KILL_PRIV	(1 << 14)
#define ATTR_OPEN	(1 << 15) /* Truncating from open(O_TRUNC) */
#define ATTR_TIMES_SET	(1 << 16)
Linus Torvalds's avatar
Linus Torvalds committed
216 217 218 219 220 221 222 223 224 225 226 227 228

/*
 * 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;
229 230
	kuid_t		ia_uid;
	kgid_t		ia_gid;
Linus Torvalds's avatar
Linus Torvalds committed
231 232 233 234
	loff_t		ia_size;
	struct timespec	ia_atime;
	struct timespec	ia_mtime;
	struct timespec	ia_ctime;
235 236

	/*
Lucas De Marchi's avatar
Lucas De Marchi committed
237
	 * Not an attribute, but an auxiliary info for filesystems wanting to
238 239 240 241
	 * implement an ftruncate() like method.  NOTE: filesystem should
	 * check for (ia_valid & ATTR_FILE), and not for (ia_file != NULL).
	 */
	struct file	*ia_file;
Linus Torvalds's avatar
Linus Torvalds committed
242 243 244 245 246 247 248
};

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

249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266
/** 
 * 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
267
 *  			by readpage().
268 269 270 271 272 273 274 275 276 277 278 279
 *
 * 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,
};

280
#define AOP_FLAG_UNINTERRUPTIBLE	0x0001 /* will not do a short write */
Nick Piggin's avatar
Nick Piggin committed
281
#define AOP_FLAG_CONT_EXPAND		0x0002 /* called from cont_expand */
282 283 284
#define AOP_FLAG_NOFS			0x0004 /* used by filesystem to direct
						* helper code (eg buffer layer)
						* to clear GFP_FS from alloc */
285

Linus Torvalds's avatar
Linus Torvalds committed
286 287 288 289 290 291 292
/*
 * oh the beauties of C type declarations.
 */
struct page;
struct address_space;
struct writeback_control;

Nick Piggin's avatar
Nick Piggin committed
293 294 295 296 297 298 299 300 301 302 303 304
struct iov_iter {
	const struct iovec *iov;
	unsigned long nr_segs;
	size_t iov_offset;
	size_t count;
};

size_t iov_iter_copy_from_user_atomic(struct page *page,
		struct iov_iter *i, unsigned long offset, size_t bytes);
size_t iov_iter_copy_from_user(struct page *page,
		struct iov_iter *i, unsigned long offset, size_t bytes);
void iov_iter_advance(struct iov_iter *i, size_t bytes);
305
int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes);
306
size_t iov_iter_single_seg_count(const struct iov_iter *i);
Nick Piggin's avatar
Nick Piggin committed
307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324

static inline void iov_iter_init(struct iov_iter *i,
			const struct iovec *iov, unsigned long nr_segs,
			size_t count, size_t written)
{
	i->iov = iov;
	i->nr_segs = nr_segs;
	i->iov_offset = 0;
	i->count = count + written;

	iov_iter_advance(i, written);
}

static inline size_t iov_iter_count(struct iov_iter *i)
{
	return i->count;
}

325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345
/*
 * "descriptor" for what we're up to with a read.
 * This allows us to use the same read code yet
 * have multiple different users of the data that
 * we read from a file.
 *
 * The simplest case just copies the data to user
 * mode.
 */
typedef struct {
	size_t written;
	size_t count;
	union {
		char __user *buf;
		void *data;
	} arg;
	int error;
} read_descriptor_t;

typedef int (*read_actor_t)(read_descriptor_t *, struct page *,
		unsigned long, unsigned long);
Nick Piggin's avatar
Nick Piggin committed
346

Linus Torvalds's avatar
Linus Torvalds committed
347 348 349 350 351 352 353
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 *);

354
	/* Set a page dirty.  Return true if this dirtied it */
Linus Torvalds's avatar
Linus Torvalds committed
355 356 357 358 359
	int (*set_page_dirty)(struct page *page);

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

360 361 362 363 364 365 366
	int (*write_begin)(struct file *, struct address_space *mapping,
				loff_t pos, unsigned len, unsigned flags,
				struct page **pagep, void **fsdata);
	int (*write_end)(struct file *, struct address_space *mapping,
				loff_t pos, unsigned len, unsigned copied,
				struct page *page, void *fsdata);

Linus Torvalds's avatar
Linus Torvalds committed
367 368
	/* Unfortunately this kludge is needed for FIBMAP. Don't use it */
	sector_t (*bmap)(struct address_space *, sector_t);
369
	void (*invalidatepage) (struct page *, unsigned int, unsigned int);
Al Viro's avatar
Al Viro committed
370
	int (*releasepage) (struct page *, gfp_t);
371
	void (*freepage)(struct page *);
Linus Torvalds's avatar
Linus Torvalds committed
372 373
	ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
			loff_t offset, unsigned long nr_segs);
374 375
	int (*get_xip_mem)(struct address_space *, pgoff_t, int,
						void **, unsigned long *);
376
	/*
377 378
	 * migrate the contents of a page to the specified target. If
	 * migrate_mode is MIGRATE_ASYNC, it must not block.
379
	 */
380
	int (*migratepage) (struct address_space *,
381
			struct page *, struct page *, enum migrate_mode);
382
	int (*launder_page) (struct page *);
383 384
	int (*is_partially_uptodate) (struct page *, read_descriptor_t *,
					unsigned long);
385
	void (*is_dirty_writeback) (struct page *, bool *, bool *);
386
	int (*error_remove_page)(struct address_space *, struct page *);
387 388

	/* swapfile support */
389 390 391
	int (*swap_activate)(struct swap_info_struct *sis, struct file *file,
				sector_t *span);
	void (*swap_deactivate)(struct file *file);
Linus Torvalds's avatar
Linus Torvalds committed
392 393
};

Jens Axboe's avatar
Jens Axboe committed
394 395
extern const struct address_space_operations empty_aops;

396 397 398 399 400 401 402 403 404 405 406 407
/*
 * pagecache_write_begin/pagecache_write_end must be used by general code
 * to write into the pagecache.
 */
int pagecache_write_begin(struct file *, struct address_space *mapping,
				loff_t pos, unsigned len, unsigned flags,
				struct page **pagep, void **fsdata);

int pagecache_write_end(struct file *, struct address_space *mapping,
				loff_t pos, unsigned len, unsigned copied,
				struct page *page, void *fsdata);

Linus Torvalds's avatar
Linus Torvalds committed
408 409 410 411
struct backing_dev_info;
struct address_space {
	struct inode		*host;		/* owner: inode, block_device */
	struct radix_tree_root	page_tree;	/* radix tree of all pages */
Nick Piggin's avatar
Nick Piggin committed
412
	spinlock_t		tree_lock;	/* and lock protecting it */
Linus Torvalds's avatar
Linus Torvalds committed
413
	unsigned int		i_mmap_writable;/* count VM_SHARED mappings */
414
	struct rb_root		i_mmap;		/* tree of private and shared mappings */
Linus Torvalds's avatar
Linus Torvalds committed
415
	struct list_head	i_mmap_nonlinear;/*list VM_NONLINEAR mappings */
416
	struct mutex		i_mmap_mutex;	/* protect tree, count, list */
417
	/* Protected by tree_lock together with the radix tree */
Linus Torvalds's avatar
Linus Torvalds committed
418 419
	unsigned long		nrpages;	/* number of total pages */
	pgoff_t			writeback_index;/* writeback starts here */
420
	const struct address_space_operations *a_ops;	/* methods */
Linus Torvalds's avatar
Linus Torvalds committed
421 422 423 424
	unsigned long		flags;		/* error bits/gfp mask */
	struct backing_dev_info *backing_dev_info; /* device readahead, etc */
	spinlock_t		private_lock;	/* for use by the address_space */
	struct list_head	private_list;	/* ditto */
425
	void			*private_data;	/* ditto */
Linus Torvalds's avatar
Linus Torvalds committed
426 427 428
} __attribute__((aligned(sizeof(long))));
	/*
	 * On most architectures that alignment is already the case; but
Lucas De Marchi's avatar
Lucas De Marchi committed
429
	 * must be enforced here for CRIS, to let the least significant bit
Linus Torvalds's avatar
Linus Torvalds committed
430 431
	 * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON.
	 */
432
struct request_queue;
Linus Torvalds's avatar
Linus Torvalds committed
433 434 435

struct block_device {
	dev_t			bd_dev;  /* not a kdev_t - it's a search key */
436
	int			bd_openers;
Linus Torvalds's avatar
Linus Torvalds committed
437
	struct inode *		bd_inode;	/* will die */
438
	struct super_block *	bd_super;
439
	struct mutex		bd_mutex;	/* open/close mutex */
Linus Torvalds's avatar
Linus Torvalds committed
440
	struct list_head	bd_inodes;
441
	void *			bd_claiming;
Linus Torvalds's avatar
Linus Torvalds committed
442 443
	void *			bd_holder;
	int			bd_holders;
444
	bool			bd_write_holder;
445
#ifdef CONFIG_SYSFS
446
	struct list_head	bd_holder_disks;
447
#endif
Linus Torvalds's avatar
Linus Torvalds committed
448 449 450 451 452 453 454
	struct block_device *	bd_contains;
	unsigned		bd_block_size;
	struct hd_struct *	bd_part;
	/* number of times partitions within this device have been opened. */
	unsigned		bd_part_count;
	int			bd_invalidated;
	struct gendisk *	bd_disk;
455
	struct request_queue *  bd_queue;
Linus Torvalds's avatar
Linus Torvalds committed
456 457 458 459 460 461 462 463
	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;
464 465 466 467 468

	/* The counter of freeze processes */
	int			bd_fsfreeze_count;
	/* Mutex for freeze */
	struct mutex		bd_fsfreeze_mutex;
Linus Torvalds's avatar
Linus Torvalds committed
469 470 471 472 473 474 475 476
};

/*
 * Radix-tree tags, for tagging dirty and writeback pages within the pagecache
 * radix trees
 */
#define PAGECACHE_TAG_DIRTY	0
#define PAGECACHE_TAG_WRITEBACK	1
477
#define PAGECACHE_TAG_TOWRITE	2
Linus Torvalds's avatar
Linus Torvalds committed
478 479 480 481 482 483 484 485

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

/*
 * Might pages of this file be mapped into userspace?
 */
static inline int mapping_mapped(struct address_space *mapping)
{
486
	return	!RB_EMPTY_ROOT(&mapping->i_mmap) ||
Linus Torvalds's avatar
Linus Torvalds committed
487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511
		!list_empty(&mapping->i_mmap_nonlinear);
}

/*
 * Might pages of this file have been modified in userspace?
 * Note that i_mmap_writable counts all VM_SHARED vmas: do_mmap_pgoff
 * marks vma as VM_SHARED if it is shared, and the file was opened for
 * writing i.e. vma may be mprotected writable even if now readonly.
 */
static inline int mapping_writably_mapped(struct address_space *mapping)
{
	return mapping->i_mmap_writable != 0;
}

/*
 * 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

Al Viro's avatar
Al Viro committed
512 513 514
struct posix_acl;
#define ACL_NOT_CACHED ((void *)(-1))

515 516 517 518 519 520 521 522 523
#define IOP_FASTPERM	0x0001
#define IOP_LOOKUP	0x0002
#define IOP_NOFOLLOW	0x0004

/*
 * Keep mostly read-only and often accessed (especially for
 * the RCU path lookup and 'stat' data) fields at the beginning
 * of the 'struct inode'
 */
Linus Torvalds's avatar
Linus Torvalds committed
524
struct inode {
525
	umode_t			i_mode;
526
	unsigned short		i_opflags;
527 528
	kuid_t			i_uid;
	kgid_t			i_gid;
529 530 531 532 533 534 535
	unsigned int		i_flags;

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

536 537
	const struct inode_operations	*i_op;
	struct super_block	*i_sb;
538
	struct address_space	*i_mapping;
539

540 541 542
#ifdef CONFIG_SECURITY
	void			*i_security;
#endif
543

544 545
	/* Stat data, not accessed from path walking */
	unsigned long		i_ino;
Miklos Szeredi's avatar
Miklos Szeredi committed
546 547 548 549 550 551 552 553 554 555 556
	/*
	 * 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;
	};
557
	dev_t			i_rdev;
558
	loff_t			i_size;
559 560 561
	struct timespec		i_atime;
	struct timespec		i_mtime;
	struct timespec		i_ctime;
562 563
	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
	unsigned short          i_bytes;
564
	unsigned int		i_blkbits;
565 566 567 568 569 570 571 572 573
	blkcnt_t		i_blocks;

#ifdef __NEED_I_SIZE_ORDERED
	seqcount_t		i_size_seqcount;
#endif

	/* Misc */
	unsigned long		i_state;
	struct mutex		i_mutex;
574

575 576
	unsigned long		dirtied_when;	/* jiffies of first dirtying */

Linus Torvalds's avatar
Linus Torvalds committed
577
	struct hlist_node	i_hash;
Nick Piggin's avatar
Nick Piggin committed
578 579
	struct list_head	i_wb_list;	/* backing dev IO list */
	struct list_head	i_lru;		/* inode LRU list */
Linus Torvalds's avatar
Linus Torvalds committed
580
	struct list_head	i_sb_list;
Nick Piggin's avatar
Nick Piggin committed
581
	union {
582
		struct hlist_head	i_dentry;
Nick Piggin's avatar
Nick Piggin committed
583 584
		struct rcu_head		i_rcu;
	};
585
	u64			i_version;
586
	atomic_t		i_count;
Christoph Hellwig's avatar
Christoph Hellwig committed
587
	atomic_t		i_dio_count;
588
	atomic_t		i_writecount;
589
	const struct file_operations	*i_fop;	/* former ->i_op->default_file_ops */
Linus Torvalds's avatar
Linus Torvalds committed
590 591 592 593 594 595
	struct file_lock	*i_flock;
	struct address_space	i_data;
#ifdef CONFIG_QUOTA
	struct dquot		*i_dquot[MAXQUOTAS];
#endif
	struct list_head	i_devices;
596 597
	union {
		struct pipe_inode_info	*i_pipe;
598
		struct block_device	*i_bdev;
599
		struct cdev		*i_cdev;
600
	};
Linus Torvalds's avatar
Linus Torvalds committed
601 602 603

	__u32			i_generation;

604 605
#ifdef CONFIG_FSNOTIFY
	__u32			i_fsnotify_mask; /* all events this inode cares about */
606
	struct hlist_head	i_fsnotify_marks;
Robert Love's avatar
Robert Love committed
607 608
#endif

609
#ifdef CONFIG_IMA
610
	atomic_t		i_readcount; /* struct files open RO */
611
#endif
612
	void			*i_private; /* fs or device private pointer */
Linus Torvalds's avatar
Linus Torvalds committed
613 614
};

Al Viro's avatar
Al Viro committed
615 616 617 618 619
static inline int inode_unhashed(struct inode *inode)
{
	return hlist_unhashed(&inode->i_hash);
}

620 621 622 623 624 625 626 627 628
/*
 * inode->i_mutex nesting subclasses for the lock validator:
 *
 * 0: the object of the current VFS operation
 * 1: parent
 * 2: child/target
 * 3: quota file
 *
 * The locking order between these classes is
629
 * parent -> child -> normal -> xattr -> quota
630 631 632 633 634 635
 */
enum inode_i_mutex_lock_class
{
	I_MUTEX_NORMAL,
	I_MUTEX_PARENT,
	I_MUTEX_CHILD,
636
	I_MUTEX_XATTR,
637 638 639
	I_MUTEX_QUOTA
};

Linus Torvalds's avatar
Linus Torvalds committed
640 641 642 643 644 645 646 647 648 649
/*
 * 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.
 */
650
static inline loff_t i_size_read(const struct inode *inode)
Linus Torvalds's avatar
Linus Torvalds committed
651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672
{
#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
}

673 674 675 676 677
/*
 * NOTE: unlike i_size_read(), i_size_write() does need locking around it
 * (normally i_mutex), otherwise on 32bit/SMP an update of i_size_seqcount
 * can be lost, resulting in subsequent i_size_read() calls spinning forever.
 */
Linus Torvalds's avatar
Linus Torvalds committed
678 679 680
static inline void i_size_write(struct inode *inode, loff_t i_size)
{
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
681
	preempt_disable();
Linus Torvalds's avatar
Linus Torvalds committed
682 683 684
	write_seqcount_begin(&inode->i_size_seqcount);
	inode->i_size = i_size;
	write_seqcount_end(&inode->i_size_seqcount);
685
	preempt_enable();
Linus Torvalds's avatar
Linus Torvalds committed
686 687 688 689 690 691 692 693 694
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
	preempt_disable();
	inode->i_size = i_size;
	preempt_enable();
#else
	inode->i_size = i_size;
#endif
}

695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719
/* Helper functions so that in most cases filesystems will
 * not need to deal directly with kuid_t and kgid_t and can
 * instead deal with the raw numeric values that are stored
 * in the filesystem.
 */
static inline uid_t i_uid_read(const struct inode *inode)
{
	return from_kuid(&init_user_ns, inode->i_uid);
}

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

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

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

720
static inline unsigned iminor(const struct inode *inode)
Linus Torvalds's avatar
Linus Torvalds committed
721 722 723 724
{
	return MINOR(inode->i_rdev);
}

725
static inline unsigned imajor(const struct inode *inode)
Linus Torvalds's avatar
Linus Torvalds committed
726 727 728 729 730 731 732 733
{
	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 */
734 735
	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 */
736
	kuid_t uid, euid;	/* uid/euid of process setting the owner */
Linus Torvalds's avatar
Linus Torvalds committed
737 738 739 740 741 742 743
	int signum;		/* posix.1b rt signal to be delivered on IO */
};

/*
 * Track a single file's readahead state
 */
struct file_ra_state {
744 745 746
	pgoff_t start;			/* where readahead started */
	unsigned int size;		/* # of readahead pages */
	unsigned int async_size;	/* do asynchronous readahead when
747
					   there are only # of pages ahead */
748

749
	unsigned int ra_pages;		/* Maximum readahead window */
750
	unsigned int mmap_miss;		/* Cache miss stat for mmap accesses */
751
	loff_t prev_pos;		/* Cache last read() position */
Linus Torvalds's avatar
Linus Torvalds committed
752 753
};

754 755 756 757 758
/*
 * Check if @index falls in the readahead windows.
 */
static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
{
759 760
	return (index >= ra->start &&
		index <  ra->start + ra->size);
761 762
}

763 764 765
#define FILE_MNT_WRITE_TAKEN	1
#define FILE_MNT_WRITE_RELEASED	2

Linus Torvalds's avatar
Linus Torvalds committed
766
struct file {
767
	union {
768
		struct llist_node	fu_llist;
769 770
		struct rcu_head 	fu_rcuhead;
	} f_u;
771 772
	struct path		f_path;
#define f_dentry	f_path.dentry
773
	struct inode		*f_inode;	/* cached value */
774
	const struct file_operations	*f_op;
775 776 777 778 779 780

	/*
	 * Protects f_ep_links, f_flags, f_pos vs i_size in lseek SEEK_CUR.
	 * Must not be taken from IRQ context.
	 */
	spinlock_t		f_lock;
Al Viro's avatar
Al Viro committed
781
	atomic_long_t		f_count;
Linus Torvalds's avatar
Linus Torvalds committed
782
	unsigned int 		f_flags;
783
	fmode_t			f_mode;
Linus Torvalds's avatar
Linus Torvalds committed
784 785
	loff_t			f_pos;
	struct fown_struct	f_owner;
786
	const struct cred	*f_cred;
Linus Torvalds's avatar
Linus Torvalds committed
787 788
	struct file_ra_state	f_ra;

789
	u64			f_version;
790
#ifdef CONFIG_SECURITY
Linus Torvalds's avatar
Linus Torvalds committed
791
	void			*f_security;
792
#endif
Linus Torvalds's avatar
Linus Torvalds committed
793 794 795 796 797 798
	/* needed for tty driver, and maybe others */
	void			*private_data;

#ifdef CONFIG_EPOLL
	/* Used by fs/eventpoll.c to link all the hooks to this file */
	struct list_head	f_ep_links;
Jason Baron's avatar
Jason Baron committed
799
	struct list_head	f_tfile_llink;
Linus Torvalds's avatar
Linus Torvalds committed
800 801
#endif /* #ifdef CONFIG_EPOLL */
	struct address_space	*f_mapping;
802 803 804
#ifdef CONFIG_DEBUG_WRITECOUNT
	unsigned long f_mnt_write_state;
#endif
Linus Torvalds's avatar
Linus Torvalds committed
805 806
};

807 808 809 810 811 812 813
struct file_handle {
	__u32 handle_bytes;
	int handle_type;
	/* file identifier */
	unsigned char f_handle[0];
};

Al Viro's avatar
Al Viro committed
814 815 816 817 818
static inline struct file *get_file(struct file *f)
{
	atomic_long_inc(&f->f_count);
	return f;
}
819
#define fput_atomic(x)	atomic_long_add_unless(&(x)->f_count, -1, 1)
Al Viro's avatar
Al Viro committed
820
#define file_count(x)	atomic_long_read(&(x)->f_count)
Linus Torvalds's avatar
Linus Torvalds committed
821

822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864
#ifdef CONFIG_DEBUG_WRITECOUNT
static inline void file_take_write(struct file *f)
{
	WARN_ON(f->f_mnt_write_state != 0);
	f->f_mnt_write_state = FILE_MNT_WRITE_TAKEN;
}
static inline void file_release_write(struct file *f)
{
	f->f_mnt_write_state |= FILE_MNT_WRITE_RELEASED;
}
static inline void file_reset_write(struct file *f)
{
	f->f_mnt_write_state = 0;
}
static inline void file_check_state(struct file *f)
{
	/*
	 * At this point, either both or neither of these bits
	 * should be set.
	 */
	WARN_ON(f->f_mnt_write_state == FILE_MNT_WRITE_TAKEN);
	WARN_ON(f->f_mnt_write_state == FILE_MNT_WRITE_RELEASED);
}
static inline int file_check_writeable(struct file *f)
{
	if (f->f_mnt_write_state == FILE_MNT_WRITE_TAKEN)
		return 0;
	printk(KERN_WARNING "writeable file with no "
			    "mnt_want_write()\n");
	WARN_ON(1);
	return -EINVAL;
}
#else /* !CONFIG_DEBUG_WRITECOUNT */
static inline void file_take_write(struct file *filp) {}
static inline void file_release_write(struct file *filp) {}
static inline void file_reset_write(struct file *filp) {}
static inline void file_check_state(struct file *filp) {}
static inline int file_check_writeable(struct file *filp)
{
	return 0;
}
#endif /* CONFIG_DEBUG_WRITECOUNT */

Linus Torvalds's avatar
Linus Torvalds committed
865 866 867 868 869
#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
870
#define MAX_LFS_FILESIZE	(((loff_t)PAGE_CACHE_SIZE << (BITS_PER_LONG-1))-1) 
Linus Torvalds's avatar
Linus Torvalds committed
871
#elif BITS_PER_LONG==64
872
#define MAX_LFS_FILESIZE 	((loff_t)0x7fffffffffffffffLL)
Linus Torvalds's avatar
Linus Torvalds committed
873 874 875 876 877
#endif

#define FL_POSIX	1
#define FL_FLOCK	2
#define FL_ACCESS	8	/* not trying to lock, just looking */
878
#define FL_EXISTS	16	/* when unlocking, test for existence */
Linus Torvalds's avatar
Linus Torvalds committed
879
#define FL_LEASE	32	/* lease held on this file */
880
#define FL_CLOSE	64	/* unlock on close */
Linus Torvalds's avatar
Linus Torvalds committed
881
#define FL_SLEEP	128	/* A blocking lock */
882 883
#define FL_DOWNGRADE_PENDING	256 /* Lease is being downgraded */
#define FL_UNLOCK_PENDING	512 /* Lease is being broken */
Linus Torvalds's avatar
Linus Torvalds committed
884

885 886 887 888 889 890
/*
 * Special return value from posix_lock_file() and vfs_lock_file() for
 * asynchronous locking.
 */
#define FILE_LOCK_DEFERRED 1

Linus Torvalds's avatar
Linus Torvalds committed
891 892 893 894 895 896 897 898 899 900 901 902 903 904 905
/*
 * The POSIX file lock owner is determined by
 * the "struct files_struct" in the thread group
 * (or NULL for no owner - BSD locks).
 *
 * Lockd stuffs a "host" pointer into this.
 */
typedef struct files_struct *fl_owner_t;

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 {
906
	int (*lm_compare_owner)(struct file_lock *, struct file_lock *);
907
	unsigned long (*lm_owner_key)(struct file_lock *);
908 909 910 911
	void (*lm_notify)(struct file_lock *);	/* unblock callback */
	int (*lm_grant)(struct file_lock *, struct file_lock *, int);
	void (*lm_break)(struct file_lock *);
	int (*lm_change)(struct file_lock **, int);
Linus Torvalds's avatar
Linus Torvalds committed
912 913
};

914 915 916 917
struct lock_manager {
	struct list_head list;
};

918 919
struct net;
void locks_start_grace(struct net *, struct lock_manager *);
920
void locks_end_grace(struct lock_manager *);
921
int locks_in_grace(struct net *);
922

Linus Torvalds's avatar
Linus Torvalds committed
923 924 925
/* that will die - we need it for nfs_lock_info */
#include <linux/nfs_fs_i.h>

926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943
/*
 * struct file_lock represents a generic "file lock". It's used to represent
 * POSIX byte range locks, BSD (flock) locks, and leases. It's important to
 * note that the same struct is used to represent both a request for a lock and
 * the lock itself, but the same object is never used for both.
 *
 * FIXME: should we create a separate "struct lock_request" to help distinguish
 * these two uses?
 *
 * The i_flock list is ordered by:
 *
 * 1) lock type -- FL_LEASEs first, then FL_FLOCK, and finally FL_POSIX
 * 2) lock owner
 * 3) lock range start
 * 4) lock range end
 *
 * Obviously, the last two criteria only matter for POSIX locks.
 */
Linus Torvalds's avatar
Linus Torvalds committed
944 945
struct file_lock {
	struct file_lock *fl_next;	/* singly linked list for this inode  */
946
	struct hlist_node fl_link;	/* node in global lists */
Linus Torvalds's avatar
Linus Torvalds committed
947 948
	struct list_head fl_block;	/* circular list of blocked processes */
	fl_owner_t fl_owner;
949
	unsigned int fl_flags;
950
	unsigned char fl_type;
Linus Torvalds's avatar
Linus Torvalds committed
951
	unsigned int fl_pid;
952
	int fl_link_cpu;		/* what cpu's list is this on? */
953
	struct pid *fl_nspid;
Linus Torvalds's avatar
Linus Torvalds committed
954 955 956 957 958 959
	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 */
960 961 962
	/* for lease breaks: */
	unsigned long fl_break_time;
	unsigned long fl_downgrade_time;
Linus Torvalds's avatar
Linus Torvalds committed
963

964
	const struct file_lock_operations *fl_ops;	/* Callbacks for filesystems */
965
	const struct lock_manager_operations *fl_lmops;	/* Callbacks for lockmanagers */
Linus Torvalds's avatar
Linus Torvalds committed
966 967
	union {
		struct nfs_lock_info	nfs_fl;
968
		struct nfs4_lock_info	nfs4_fl;
David Howells's avatar
David Howells committed
969 970 971 972
		struct {
			struct list_head link;	/* link in AFS vnode's pending_locks list */
			int state;		/* state of grant or error if -ve */
		} afs;
Linus Torvalds's avatar
Linus Torvalds committed
973 974 975 976 977 978 979 980 981 982 983 984
	} fl_u;
};

/* The following constant reflects the upper bound of the file/locking space */
#ifndef OFFSET_MAX
#define INT_LIMIT(x)	(~((x)1 << (sizeof(x)*8 - 1)))
#define OFFSET_MAX	INT_LIMIT(loff_t)
#define OFFT_OFFSET_MAX	INT_LIMIT(off_t)
#endif

#include <linux/fcntl.h>

985 986 987
extern void send_sigio(struct fown_struct *fown, int fd, int band);

#ifdef CONFIG_FILE_LOCKING
Linus Torvalds's avatar
Linus Torvalds committed
988
extern int fcntl_getlk(struct file *, struct flock __user *);
989 990
extern int fcntl_setlk(unsigned int, struct file *, unsigned int,
			struct flock __user *);
Linus Torvalds's avatar
Linus Torvalds committed
991 992 993

#if BITS_PER_LONG == 32
extern int fcntl_getlk64(struct file *, struct flock64 __user *);
994 995
extern int fcntl_setlk64(unsigned int, struct file *, unsigned int,
			struct flock64 __user *);
Linus Torvalds's avatar
Linus Torvalds committed
996 997 998 999 1000 1001
#endif

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

/* fs/locks.c */
1002
void locks_free_lock(struct file_lock *fl);
Linus Torvalds's avatar
Linus Torvalds committed
1003
extern void locks_init_lock(struct file_lock *);
1004
extern struct file_lock * locks_alloc_lock(void);
Linus Torvalds's avatar
Linus Torvalds committed
1005
extern void locks_copy_lock(struct file_lock *, struct file_lock *);
1006
extern void __locks_copy_lock(struct file_lock *, const struct file_lock *);
Linus Torvalds's avatar
Linus Torvalds committed
1007 1008
extern void locks_remove_posix(struct file *, fl_owner_t);
extern void locks_remove_flock(struct file *);
1009
extern void locks_release_private(struct file_lock *);
1010
extern void posix_test_lock(struct file *, struct file_lock *);
1011
extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *);
Linus Torvalds's avatar
Linus Torvalds committed
1012
extern int posix_lock_file_wait(struct file *, struct file_lock *);
1013
extern int posix_unblock_lock(struct file_lock *);
1014
extern int vfs_test_lock(struct file *, struct file_lock *);
1015
extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *);
Marc Eshel's avatar
Marc Eshel committed
1016
extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
Linus Torvalds's avatar
Linus Torvalds committed
1017 1018 1019
extern int flock_lock_file_wait(struct file *filp, struct file_lock *fl);
extern int __break_lease(struct inode *inode, unsigned int flags);
extern void lease_get_mtime(struct inode *, struct timespec *time);
1020
extern int generic_setlease(struct file *, long, struct file_lock **);
1021
extern int vfs_setlease(struct file *, long, struct file_lock **);
Linus Torvalds's avatar
Linus Torvalds committed
1022 1023 1024
extern int lease_modify(struct file_lock **, int);
extern int lock_may_read(struct inode *, loff_t start, unsigned long count);
extern int lock_may_write(struct inode *, loff_t start, unsigned long count);
1025
#else /* !CONFIG_FILE_LOCKING */
1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036
static inline int fcntl_getlk(struct file *file, struct flock __user *user)
{
	return -EINVAL;
}

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

1037
#if BITS_PER_LONG == 32
1038 1039 1040 1041 1042 1043 1044 1045 1046 1047
static inline int fcntl_getlk64(struct file *file, struct flock64 __user *user)
{
	return -EINVAL;
}

static inline int fcntl_setlk64(unsigned int fd, struct file *file,
				unsigned int cmd, struct flock64 __user *user)
{
	return -EACCES;
}
1048
#endif
1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099
static inline int fcntl_setlease(unsigned int fd, struct file *filp, long arg)
{
	return 0;
}

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

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

static inline void __locks_copy_lock(struct file_lock *new, struct file_lock *fl)
{
	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;
}

static inline void locks_remove_flock(struct file *filp)
{
	return;
}

static inline void posix_test_lock(struct file *filp, struct file_lock *fl)
{
	return;
}

static inline int posix_lock_file(struct file *filp, struct file_lock *fl,
				  struct file_lock *conflock)
{
	return -ENOLCK;
}

static inline int posix_lock_file_wait(struct file *filp, struct file_lock *fl)
{
	return -ENOLCK;
}

1100
static inline int posix_unblock_lock(struct file_lock *waiter)
1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164
{
	return -ENOENT;
}

static inline int vfs_test_lock(struct file *filp, struct file_lock *fl)
{
	return 0;
}

static inline int vfs_lock_file(struct file *filp, unsigned int cmd,
				struct file_lock *fl, struct file_lock *conf)
{
	return -ENOLCK;
}

static inline int vfs_cancel_lock(struct file *filp, struct file_lock *fl)
{
	return 0;
}

static inline int flock_lock_file_wait(struct file *filp,
				       struct file_lock *request)
{
	return -ENOLCK;
}

static inline int __break_lease(struct inode *inode, unsigned int mode)
{
	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,
				    struct file_lock **flp)
{
	return -EINVAL;
}

static inline int vfs_setlease(struct file *filp, long arg,
			       struct file_lock **lease)
{
	return -EINVAL;
}

static inline int lease_modify(struct file_lock **before, int arg)
{
	return -EINVAL;
}

static inline int lock_may_read(struct inode *inode, loff_t start,
				unsigned long len)
{
	return 1;
}

static inline int lock_may_write(struct inode *inode, loff_t start,
				 unsigned long len)
{
	return 1;
}
1165 1166
#endif /* !CONFIG_FILE_LOCKING */

Linus Torvalds's avatar
Linus Torvalds committed
1167 1168

struct fasync_struct {
1169 1170 1171 1172 1173 1174
	spinlock_t		fa_lock;
	int			magic;
	int			fa_fd;
	struct fasync_struct	*fa_next; /* singly linked list */
	struct file		*fa_file;
	struct rcu_head		fa_rcu;
Linus Torvalds's avatar
Linus Torvalds committed
1175 1176 1177 1178 1179 1180
};

#define FASYNC_MAGIC 0x4601

/* SMP safe fasync helpers: */
extern int fasync_helper(int, struct file *, int, struct fasync_struct **);
1181 1182 1183 1184 1185
extern struct fasync_struct *fasync_insert_entry(int, struct file *, struct fasync_struct **, struct fasync_struct *);
extern int fasync_remove_entry(struct file *, struct fasync_struct **);
extern struct fasync_struct *fasync_alloc(void);
extern void fasync_free(struct fasync_struct *);

Linus Torvalds's avatar
Linus Torvalds committed
1186 1187 1188
/* can be called from interrupts */
extern void kill_fasync(struct fasync_struct **, int, int);

1189
extern int __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
Linus Torvalds's avatar
Linus Torvalds committed
1190 1191
extern int f_setown(struct file *filp, unsigned long arg, int force);
extern void f_delown(struct file *filp);
1192
extern pid_t f_getown(struct file *filp);
Linus Torvalds's avatar
Linus Torvalds committed
1193 1194
extern int send_sigurg(struct fown_struct *fown);

1195 1196
struct mm_struct;

Linus Torvalds's avatar
Linus Torvalds committed
1197 1198 1199 1200 1201 1202 1203
/*
 *	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 */
1204 1205
#define UMOUNT_NOFOLLOW	0x00000008	/* Don't follow symlink on umount */
#define UMOUNT_UNUSED	0x80000000	/* Flag guaranteed to be unused */
Linus Torvalds's avatar
Linus Torvalds committed
1206 1207 1208 1209

extern struct list_head super_blocks;
extern spinlock_t sb_lock;

1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234
/* Possible states of 'frozen' field */
enum {
	SB_UNFROZEN = 0,		/* FS is unfrozen */
	SB_FREEZE_WRITE	= 1,		/* Writes, dir ops, ioctls frozen */
	SB_FREEZE_PAGEFAULT = 2,	/* Page faults stopped as well */
	SB_FREEZE_FS = 3,		/* For internal FS use (e.g. to stop
					 * internal threads if needed) */
	SB_FREEZE_COMPLETE = 4,		/* ->freeze_fs finished successfully */
};

#define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1)

struct sb_writers {
	/* Counters for counting writers at each level */
	struct percpu_counter	counter[SB_FREEZE_LEVELS];
	wait_queue_head_t	wait;		/* queue for waiting for
						   writers / faults to finish */
	int			frozen;		/* Is sb frozen? */
	wait_queue_head_t	wait_unfrozen;	/* queue for waiting for
						   sb to be thawed */
#ifdef CONFIG_DEBUG_LOCK_ALLOC
	struct lockdep_map	lock_map[SB_FREEZE_LEVELS];
#endif
};

Linus Torvalds's avatar
Linus Torvalds committed
1235 1236 1237
struct super_block {
	struct list_head	s_list;		/* Keep this first */
	dev_t			s_dev;		/* search index; _not_ kdev_t */
1238 1239
	unsigned char		s_blocksize_bits;
	unsigned long		s_blocksize;
1240
	loff_t			s_maxbytes;	/* Max file size */
Linus Torvalds's avatar
Linus Torvalds committed
1241
	struct file_system_type	*s_type;
1242
	const struct super_operations	*s_op;
1243
	const struct dquot_operations	*dq_op;
1244
	const struct quotactl_ops	*s_qcop;
1245
	const struct export_operations *s_export_op;
Linus Torvalds's avatar
Linus Torvalds committed
1246 1247 1248 1249 1250 1251
	unsigned long		s_flags;
	unsigned long		s_magic;
	struct dentry		*s_root;
	struct rw_semaphore	s_umount;
	int			s_count;
	atomic_t		s_active;
1252
#ifdef CONFIG_SECURITY
Linus Torvalds's avatar
Linus Torvalds committed
1253
	void                    *s_security;
1254
#endif
1255
	const struct xattr_handler **s_xattr;
Linus Torvalds's avatar
Linus Torvalds committed
1256 1257

	struct list_head	s_inodes;	/* all inodes */
1258
	struct hlist_bl_head	s_anon;		/* anonymous dentries for (nfs) exporting */
1259
	struct list_head	s_mounts;	/* list of mounts; _not_ for fs use */
Linus Torvalds's avatar
Linus Torvalds committed
1260
	struct block_device	*s_bdev;
Jens Axboe's avatar
Jens Axboe committed
1261
	struct backing_dev_info *s_bdi;
1262
	struct mtd_info		*s_mtd;
Al Viro's avatar
Al Viro committed
1263
	struct hlist_node	s_instances;
Linus Torvalds's avatar
Linus Torvalds committed
1264 1265
	struct quota_info	s_dquot;	/* Diskquota specific options */

1266
	struct sb_writers	s_writers;
Linus Torvalds's avatar
Linus Torvalds committed
1267 1268

	char s_id[32];				/* Informational name */
1269
	u8 s_uuid[16];				/* UUID */
Linus Torvalds's avatar
Linus Torvalds committed
1270 1271

	void 			*s_fs_info;	/* Filesystem private info */
1272
	unsigned int		s_max_links;
1273
	fmode_t			s_mode;
Linus Torvalds's avatar
Linus Torvalds committed
1274

1275 1276 1277 1278
	/* Granularity of c/m/atime in ns.
	   Cannot be worse than a second */
	u32		   s_time_gran;

Linus Torvalds's avatar
Linus Torvalds committed
1279 1280 1281 1282
	/*
	 * The next field is for VFS *only*. No filesystems have any business
	 * even looking at it. You had been warned.
	 */
1283
	struct mutex s_vfs_rename_mutex;	/* Kludge */
Linus Torvalds's avatar
Linus Torvalds committed
1284

1285 1286 1287 1288 1289
	/*
	 * Filesystem subtype.  If non-empty the filesystem type field
	 * in /proc/mounts will be "type.subtype"
	 */
	char *s_subtype;
1290 1291 1292 1293 1294

	/*
	 * Saved mount options for lazy filesystems using
	 * generic_show_options()
	 */
Arnd Bergmann's avatar
Arnd Bergmann committed
1295
	char __rcu *s_options;
Al Viro's avatar
Al Viro committed
1296
	const struct dentry_operations *s_d_op; /* default d_op for dentries */
1297 1298 1299 1300 1301

	/*
	 * Saved pool identifier for cleancache (-1 means none)
	 */
	int cleancache_poolid;
1302 1303

	struct shrinker s_shrink;	/* per-sb shrinker handle */
1304

Miklos Szeredi's avatar
Miklos Szeredi committed
1305 1306 1307
	/* Number of inodes with nlink == 0 but still referenced */
	atomic_long_t s_remove_count;

1308 1309
	/* Being remounted read-only */
	int s_readonly_remount;
1310 1311 1312

	/* AIO completions deferred from interrupt context */
	struct workqueue_struct *s_dio_done_wq;
1313 1314 1315 1316 1317 1318 1319

	/*
	 * 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;
Al Viro's avatar
Al Viro committed
1320
	struct rcu_head		rcu;
Linus Torvalds's avatar
Linus Torvalds committed
1321 1322 1323 1324 1325 1326 1327 1328
};

extern struct timespec current_fs_time(struct super_block *sb);

/*
 * Snapshotting support.
 */

1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437
void __sb_end_write(struct super_block *sb, int level);
int __sb_start_write(struct super_block *sb, int level, bool wait);

/**
 * sb_end_write - drop write access to a superblock
 * @sb: the super we wrote to
 *
 * Decrement number of writers to the filesystem. Wake up possible waiters
 * wanting to freeze the filesystem.
 */
static inline void sb_end_write(struct super_block *sb)
{
	__sb_end_write(sb, SB_FREEZE_WRITE);
}

/**
 * sb_end_pagefault - drop write access to a superblock from a page fault
 * @sb: the super we wrote to
 *
 * Decrement number of processes handling write page fault to the filesystem.
 * Wake up possible waiters wanting to freeze the filesystem.
 */
static inline void sb_end_pagefault(struct super_block *sb)
{
	__sb_end_write(sb, SB_FREEZE_PAGEFAULT);
}

/**
 * sb_end_intwrite - drop write access to a superblock for internal fs purposes
 * @sb: the super we wrote to
 *
 * Decrement fs-internal number of writers to the filesystem.  Wake up possible
 * waiters wanting to freeze the filesystem.
 */
static inline void sb_end_intwrite(struct super_block *sb)
{
	__sb_end_write(sb, SB_FREEZE_FS);
}

/**
 * sb_start_write - get write access to a superblock
 * @sb: the super we write to
 *
 * When a process wants to write data or metadata to a file system (i.e. dirty
 * a page or an inode), it should embed the operation in a sb_start_write() -
 * sb_end_write() pair to get exclusion against file system freezing. This
 * function increments number of writers preventing freezing. If the file
 * system is already frozen, the function waits until the file system is
 * thawed.
 *
 * Since freeze protection behaves as a lock, users have to preserve
 * ordering of freeze protection and other filesystem locks. Generally,
 * freeze protection should be the outermost lock. In particular, we have:
 *
 * sb_start_write
 *   -> i_mutex			(write path, truncate, directory ops, ...)
 *   -> s_umount		(freeze_super, thaw_super)
 */
static inline void sb_start_write(struct super_block *sb)
{
	__sb_start_write(sb, SB_FREEZE_WRITE, true);
}

static inline int sb_start_write_trylock(struct super_block *sb)
{
	return __sb_start_write(sb, SB_FREEZE_WRITE, false);
}

/**
 * sb_start_pagefault - get write access to a superblock from a page fault
 * @sb: the super we write to
 *
 * When a process starts handling write page fault, it should embed the
 * operation into sb_start_pagefault() - sb_end_pagefault() pair to get
 * exclusion against file system freezing. This is needed since the page fault
 * is going to dirty a page. This function increments number of running page
 * faults preventing freezing. If the file system is already frozen, the
 * function waits until the file system is thawed.
 *
 * Since page fault freeze protection behaves as a lock, users have to preserve
 * ordering of freeze protection and other filesystem locks. It is advised to
 * put sb_start_pagefault() close to mmap_sem in lock ordering. Page fault
 * handling code implies lock dependency:
 *
 * mmap_sem
 *   -> sb_start_pagefault
 */
static inline void sb_start_pagefault(struct super_block *sb)
{
	__sb_start_write(sb, SB_FREEZE_PAGEFAULT, true);
}

/*
 * sb_start_intwrite - get write access to a superblock for internal fs purposes
 * @sb: the super we write to
 *
 * This is the third level of protection against filesystem freezing. It is
 * free for use by a filesystem. The only requirement is that it must rank
 * below sb_start_pagefault.
 *
 * For example filesystem can call sb_start_intwrite() when starting a
 * transaction which somewhat eases handling of freezing for internal sources
 * of filesystem changes (internal fs threads, discarding preallocation on file
 * close, etc.).
 */
static inline void sb_start_intwrite(struct super_block *sb)
{
	__sb_start_write(sb, SB_FREEZE_FS, true);
}
Linus Torvalds's avatar
Linus Torvalds committed
1438 1439


1440
extern bool inode_owner_or_capable(const struct inode *inode);
1441

Linus Torvalds's avatar
Linus Torvalds committed
1442 1443 1444
/*
 * VFS helper functions..
 */
1445
extern int vfs_create(struct inode *, struct dentry *, umode_t, bool);
1446
extern int vfs_mkdir(struct inode *, struct dentry *, umode_t);
Al Viro's avatar
Al Viro committed
1447
extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
1448
extern int vfs_symlink(struct inode *, struct dentry *, const char *);
Linus Torvalds's avatar
Linus Torvalds committed
1449 1450 1451 1452 1453 1454 1455 1456 1457 1458
extern int vfs_link(struct dentry *, struct inode *, struct dentry *);
extern int vfs_rmdir(struct inode *, struct dentry *);
extern int vfs_unlink(struct inode *, struct dentry *);
extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *);

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

1459 1460 1461
/*
 * VFS file helper functions.
 */
1462
extern void inode_init_owner(struct inode *inode, const struct inode *dir,
Al Viro's avatar
Al Viro committed
1463
			umode_t mode);
Mark Fasheh's avatar
Mark Fasheh committed
1464 1465 1466 1467 1468 1469 1470
/*
 * 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 */
1471 1472
	struct fiemap_extent __user *fi_extents_start; /* Start of
							fiemap_extent array */
Mark Fasheh's avatar
Mark Fasheh committed
1473 1474 1475 1476 1477
};
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);

Linus Torvalds's avatar
Linus Torvalds committed
1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499
/*
 * 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.
 */
1500
typedef int (*filldir_t)(void *, const char *, int, loff_t, u64, unsigned);
1501
struct dir_context {
Al Viro's avatar
Al Viro committed
1502
	const filldir_t actor;
1503
	loff_t pos;
1504
};
1505

1506
struct block_device_operations;
Linus Torvalds's avatar
Linus Torvalds committed
1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518

/* 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

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 *);
1519 1520
	ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
	ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
1521
	int (*iterate) (struct file *, struct dir_context *);
Linus Torvalds's avatar
Linus Torvalds committed
1522 1523 1524 1525 1526
	unsigned int (*poll) (struct file *, struct poll_table_struct *);
	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
	int (*mmap) (struct file *, struct vm_area_struct *);
	int (*open) (struct inode *, struct file *);
1527
	int (*flush) (struct file *, fl_owner_t id);
Linus Torvalds's avatar
Linus Torvalds committed
1528
	int (*release) (struct inode *, struct file *);
1529
	int (*fsync) (struct file *, loff_t, loff_t, int datasync);
Linus Torvalds's avatar
Linus Torvalds committed
1530 1531 1532 1533 1534 1535 1536
	int (*aio_fsync) (struct kiocb *, int datasync);
	int (*fasync) (int, struct file *, int);
	int (*lock) (struct file *, int, struct file_lock *);
	ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int);
	unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
	int (*check_flags)(int);
	int (*flock) (struct file *, int, struct file_lock *);
1537 1538
	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);
1539
	int (*setlease)(struct file