ext4.h 118.3 KB
Newer Older
1
/*
2
 *  ext4.h
3 4 5 6 7 8 9 10 11 12 13 14 15
 *
 * Copyright (C) 1992, 1993, 1994, 1995
 * Remy Card (card@masi.ibp.fr)
 * Laboratoire MASI - Institut Blaise Pascal
 * Universite Pierre et Marie Curie (Paris VI)
 *
 *  from
 *
 *  linux/include/linux/minix_fs.h
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

16 17
#ifndef _EXT4_H
#define _EXT4_H
18 19

#include <linux/types.h>
20
#include <linux/blkdev.h>
21
#include <linux/magic.h>
22
#include <linux/jbd2.h>
23
#include <linux/quota.h>
24 25 26 27
#include <linux/rwsem.h>
#include <linux/rbtree.h>
#include <linux/seqlock.h>
#include <linux/mutex.h>
28
#include <linux/timer.h>
29
#include <linux/version.h>
30 31 32
#include <linux/wait.h>
#include <linux/blockgroup_lock.h>
#include <linux/percpu_counter.h>
33
#include <linux/ratelimit.h>
34
#include <crypto/hash.h>
35
#include <linux/falloc.h>
36
#include <linux/percpu-rwsem.h>
37 38 39
#ifdef __KERNEL__
#include <linux/compat.h>
#endif
40

41
/*
S
Shen Feng 已提交
42
 * The fourth extended filesystem constants/structures
43 44
 */

45 46 47 48 49 50 51 52 53 54 55 56
/*
 * with AGGRESSIVE_CHECK allocator runs consistency checks over
 * structures. these checks slow things down a lot
 */
#define AGGRESSIVE_CHECK__

/*
 * with DOUBLE_CHECK defined mballoc creates persistent in-core
 * bitmaps, maintains and uses them to check for double allocations
 */
#define DOUBLE_CHECK__

57
/*
58
 * Define EXT4FS_DEBUG to produce debug messages
59
 */
60
#undef EXT4FS_DEBUG
61 62 63 64

/*
 * Debug code
 */
65 66
#ifdef EXT4FS_DEBUG
#define ext4_debug(f, a...)						\
67
	do {								\
68
		printk(KERN_DEBUG "EXT4-fs DEBUG (%s, %d): %s:",	\
69
			__FILE__, __LINE__, __func__);			\
70
		printk(KERN_DEBUG f, ## a);				\
71 72
	} while (0)
#else
73
#define ext4_debug(fmt, ...)	no_printk(fmt, ##__VA_ARGS__)
74 75
#endif

76 77 78 79 80 81 82 83 84 85
/*
 * Turn on EXT_DEBUG to get lots of info about extents operations.
 */
#define EXT_DEBUG__
#ifdef EXT_DEBUG
#define ext_debug(fmt, ...)	printk(fmt, ##__VA_ARGS__)
#else
#define ext_debug(fmt, ...)	no_printk(fmt, ##__VA_ARGS__)
#endif

86 87 88 89 90 91 92 93 94 95 96 97
/* data type for block offset of block group */
typedef int ext4_grpblk_t;

/* data type for filesystem-wide blocks number */
typedef unsigned long long ext4_fsblk_t;

/* data type for file logical block number */
typedef __u32 ext4_lblk_t;

/* data type for block group number */
typedef unsigned int ext4_group_t;

98 99 100 101 102
enum SHIFT_DIRECTION {
	SHIFT_LEFT = 0,
	SHIFT_RIGHT,
};

103
/*
104
 * Flags used in mballoc's allocation_context flags field.
105 106 107 108
 *
 * Also used to show what's going on for debugging purposes when the
 * flag field is exported via the traceport interface
 */
109

110
/* prefer goal again. length */
111
#define EXT4_MB_HINT_MERGE		0x0001
112
/* blocks already reserved */
113
#define EXT4_MB_HINT_RESERVED		0x0002
114
/* metadata is being allocated */
115
#define EXT4_MB_HINT_METADATA		0x0004
116
/* first blocks in the file */
117
#define EXT4_MB_HINT_FIRST		0x0008
118
/* search for the best chunk */
119
#define EXT4_MB_HINT_BEST		0x0010
120
/* data is being allocated */
121
#define EXT4_MB_HINT_DATA		0x0020
122
/* don't preallocate (for tails) */
123
#define EXT4_MB_HINT_NOPREALLOC		0x0040
124
/* allocate for locality group */
125
#define EXT4_MB_HINT_GROUP_ALLOC	0x0080
126
/* allocate goal blocks or none */
127
#define EXT4_MB_HINT_GOAL_ONLY		0x0100
128
/* goal is meaningful */
129
#define EXT4_MB_HINT_TRY_GOAL		0x0200
130
/* blocks already pre-reserved by delayed allocation */
131
#define EXT4_MB_DELALLOC_RESERVED	0x0400
132 133
/* We are doing stream allocation */
#define EXT4_MB_STREAM_ALLOC		0x0800
134 135
/* Use reserved root blocks if needed */
#define EXT4_MB_USE_ROOT_BLOCKS		0x1000
L
Lukas Czerner 已提交
136 137
/* Use blocks from reserved pool */
#define EXT4_MB_USE_RESERVED		0x2000
138 139 140 141

struct ext4_allocation_request {
	/* target inode for block we're allocating */
	struct inode *inode;
142 143
	/* how many blocks we want to allocate */
	unsigned int len;
144 145 146 147 148 149
	/* logical block in target inode */
	ext4_lblk_t logical;
	/* the closest logical allocated block to the left */
	ext4_lblk_t lleft;
	/* the closest logical allocated block to the right */
	ext4_lblk_t lright;
150 151 152 153 154
	/* phys. target (a hint) */
	ext4_fsblk_t goal;
	/* phys. block for the closest logical allocated block to the left */
	ext4_fsblk_t pleft;
	/* phys. block for the closest logical allocated block to the right */
155 156
	ext4_fsblk_t pright;
	/* flags. see above EXT4_MB_HINT_* */
157
	unsigned int flags;
158 159
};

160 161 162 163 164 165 166 167 168 169 170 171
/*
 * Logical to physical block mapping, used by ext4_map_blocks()
 *
 * This structure is used to pass requests into ext4_map_blocks() as
 * well as to store the information returned by ext4_map_blocks().  It
 * takes less room on the stack than a struct buffer_head.
 */
#define EXT4_MAP_NEW		(1 << BH_New)
#define EXT4_MAP_MAPPED		(1 << BH_Mapped)
#define EXT4_MAP_UNWRITTEN	(1 << BH_Unwritten)
#define EXT4_MAP_BOUNDARY	(1 << BH_Boundary)
#define EXT4_MAP_FLAGS		(EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
172
				 EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY)
173 174 175 176 177 178 179 180

struct ext4_map_blocks {
	ext4_fsblk_t m_pblk;
	ext4_lblk_t m_lblk;
	unsigned int m_len;
	unsigned int m_flags;
};

181 182 183 184 185
/*
 * Flags for ext4_io_end->flags
 */
#define	EXT4_IO_END_UNWRITTEN	0x0001

186
/*
187
 * For converting unwritten extents on a work queue. 'handle' is used for
188
 * buffered writeback.
189
 */
190
typedef struct ext4_io_end {
191
	struct list_head	list;		/* per-file finished IO list */
192 193
	handle_t		*handle;	/* handle reserved for extent
						 * conversion */
194
	struct inode		*inode;		/* file being written to */
195 196
	struct bio		*bio;		/* Linked list of completed
						 * bios covering the extent */
197
	unsigned int		flag;		/* unwritten or not */
J
Jan Kara 已提交
198
	atomic_t		count;		/* reference counter */
199 200
	loff_t			offset;		/* offset in the file */
	ssize_t			size;		/* size of the extent */
201 202
} ext4_io_end_t;

203
struct ext4_io_submit {
204
	struct writeback_control *io_wbc;
205 206 207 208 209
	struct bio		*io_bio;
	ext4_io_end_t		*io_end;
	sector_t		io_next_block;
};

210 211 212
/*
 * Special inodes numbers
 */
213 214
#define	EXT4_BAD_INO		 1	/* Bad blocks inode */
#define EXT4_ROOT_INO		 2	/* Root inode */
215 216
#define EXT4_USR_QUOTA_INO	 3	/* User quota inode */
#define EXT4_GRP_QUOTA_INO	 4	/* Group quota inode */
217 218 219 220
#define EXT4_BOOT_LOADER_INO	 5	/* Boot loader inode */
#define EXT4_UNDEL_DIR_INO	 6	/* Undelete directory inode */
#define EXT4_RESIZE_INO		 7	/* Reserved group descriptors inode */
#define EXT4_JOURNAL_INO	 8	/* Journal inode */
221

222 223
/* First non-reserved inode for old ext4 filesystems */
#define EXT4_GOOD_OLD_FIRST_INO	11
224 225 226 227

/*
 * Maximal count of links to a file
 */
228
#define EXT4_LINK_MAX		65000
229 230 231 232

/*
 * Macro-instructions used to manage several block sizes
 */
233
#define EXT4_MIN_BLOCK_SIZE		1024
234 235
#define	EXT4_MAX_BLOCK_SIZE		65536
#define EXT4_MIN_BLOCK_LOG_SIZE		10
236
#define EXT4_MAX_BLOCK_LOG_SIZE		16
237
#ifdef __KERNEL__
238
# define EXT4_BLOCK_SIZE(s)		((s)->s_blocksize)
239
#else
240
# define EXT4_BLOCK_SIZE(s)		(EXT4_MIN_BLOCK_SIZE << (s)->s_log_block_size)
241
#endif
242
#define	EXT4_ADDR_PER_BLOCK(s)		(EXT4_BLOCK_SIZE(s) / sizeof(__u32))
243 244
#define EXT4_CLUSTER_SIZE(s)		(EXT4_BLOCK_SIZE(s) << \
					 EXT4_SB(s)->s_cluster_bits)
245
#ifdef __KERNEL__
246
# define EXT4_BLOCK_SIZE_BITS(s)	((s)->s_blocksize_bits)
247
# define EXT4_CLUSTER_BITS(s)		(EXT4_SB(s)->s_cluster_bits)
248
#else
249
# define EXT4_BLOCK_SIZE_BITS(s)	((s)->s_log_block_size + 10)
250 251
#endif
#ifdef __KERNEL__
252 253 254
#define	EXT4_ADDR_PER_BLOCK_BITS(s)	(EXT4_SB(s)->s_addr_per_block_bits)
#define EXT4_INODE_SIZE(s)		(EXT4_SB(s)->s_inode_size)
#define EXT4_FIRST_INO(s)		(EXT4_SB(s)->s_first_ino)
255
#else
256 257
#define EXT4_INODE_SIZE(s)	(((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \
				 EXT4_GOOD_OLD_INODE_SIZE : \
258
				 (s)->s_inode_size)
259 260
#define EXT4_FIRST_INO(s)	(((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \
				 EXT4_GOOD_OLD_FIRST_INO : \
261 262
				 (s)->s_first_ino)
#endif
A
Amit Arora 已提交
263
#define EXT4_BLOCK_ALIGN(size, blkbits)		ALIGN((size), (1 << (blkbits)))
264

265 266 267 268 269 270 271
/* Translate a block number to a cluster number */
#define EXT4_B2C(sbi, blk)	((blk) >> (sbi)->s_cluster_bits)
/* Translate a cluster number to a block number */
#define EXT4_C2B(sbi, cluster)	((cluster) << (sbi)->s_cluster_bits)
/* Translate # of blks to # of clusters */
#define EXT4_NUM_B2C(sbi, blks)	(((blks) + (sbi)->s_cluster_ratio - 1) >> \
				 (sbi)->s_cluster_bits)
272 273 274 275 276 277 278 279 280 281
/* Mask out the low bits to get the starting block of the cluster */
#define EXT4_PBLK_CMASK(s, pblk) ((pblk) &				\
				  ~((ext4_fsblk_t) (s)->s_cluster_ratio - 1))
#define EXT4_LBLK_CMASK(s, lblk) ((lblk) &				\
				  ~((ext4_lblk_t) (s)->s_cluster_ratio - 1))
/* Get the cluster offset */
#define EXT4_PBLK_COFF(s, pblk) ((pblk) &				\
				 ((ext4_fsblk_t) (s)->s_cluster_ratio - 1))
#define EXT4_LBLK_COFF(s, lblk) ((lblk) &				\
				 ((ext4_lblk_t) (s)->s_cluster_ratio - 1))
282

283 284 285
/*
 * Structure of a blocks group descriptor
 */
286
struct ext4_group_desc
287
{
288
	__le32	bg_block_bitmap_lo;	/* Blocks bitmap block */
289 290
	__le32	bg_inode_bitmap_lo;	/* Inodes bitmap block */
	__le32	bg_inode_table_lo;	/* Inodes table block */
291 292 293
	__le16	bg_free_blocks_count_lo;/* Free blocks count */
	__le16	bg_free_inodes_count_lo;/* Free inodes count */
	__le16	bg_used_dirs_count_lo;	/* Directories count */
A
Andreas Dilger 已提交
294
	__le16	bg_flags;		/* EXT4_BG_flags (INODE_UNINIT, etc) */
295 296 297
	__le32  bg_exclude_bitmap_lo;   /* Exclude bitmap for snapshots */
	__le16  bg_block_bitmap_csum_lo;/* crc32c(s_uuid+grp_num+bbitmap) LE */
	__le16  bg_inode_bitmap_csum_lo;/* crc32c(s_uuid+grp_num+ibitmap) LE */
298
	__le16  bg_itable_unused_lo;	/* Unused inodes count */
A
Andreas Dilger 已提交
299
	__le16  bg_checksum;		/* crc16(sb_uuid+group+desc) */
300 301 302
	__le32	bg_block_bitmap_hi;	/* Blocks bitmap block MSB */
	__le32	bg_inode_bitmap_hi;	/* Inodes bitmap block MSB */
	__le32	bg_inode_table_hi;	/* Inodes table block MSB */
303 304 305
	__le16	bg_free_blocks_count_hi;/* Free blocks count MSB */
	__le16	bg_free_inodes_count_hi;/* Free inodes count MSB */
	__le16	bg_used_dirs_count_hi;	/* Directories count MSB */
306
	__le16  bg_itable_unused_hi;    /* Unused inodes count MSB */
307 308 309 310
	__le32  bg_exclude_bitmap_hi;   /* Exclude bitmap block MSB */
	__le16  bg_block_bitmap_csum_hi;/* crc32c(s_uuid+grp_num+bbitmap) BE */
	__le16  bg_inode_bitmap_csum_hi;/* crc32c(s_uuid+grp_num+ibitmap) BE */
	__u32   bg_reserved;
311 312
};

313 314 315 316 317 318 319
#define EXT4_BG_INODE_BITMAP_CSUM_HI_END	\
	(offsetof(struct ext4_group_desc, bg_inode_bitmap_csum_hi) + \
	 sizeof(__le16))
#define EXT4_BG_BLOCK_BITMAP_CSUM_HI_END	\
	(offsetof(struct ext4_group_desc, bg_block_bitmap_csum_hi) + \
	 sizeof(__le16))

320 321 322 323 324
/*
 * Structure of a flex block group info
 */

struct flex_groups {
325 326 327
	atomic64_t	free_clusters;
	atomic_t	free_inodes;
	atomic_t	used_dirs;
328 329
};

A
Andreas Dilger 已提交
330 331 332 333
#define EXT4_BG_INODE_UNINIT	0x0001 /* Inode table/bitmap not in use */
#define EXT4_BG_BLOCK_UNINIT	0x0002 /* Block bitmap not in use */
#define EXT4_BG_INODE_ZEROED	0x0004 /* On-disk itable initialized to zero */

334 335 336
/*
 * Macro-instructions used to manage group descriptors
 */
337
#define EXT4_MIN_DESC_SIZE		32
338
#define EXT4_MIN_DESC_SIZE_64BIT	64
339 340
#define	EXT4_MAX_DESC_SIZE		EXT4_MIN_BLOCK_SIZE
#define EXT4_DESC_SIZE(s)		(EXT4_SB(s)->s_desc_size)
341
#ifdef __KERNEL__
342
# define EXT4_BLOCKS_PER_GROUP(s)	(EXT4_SB(s)->s_blocks_per_group)
343
# define EXT4_CLUSTERS_PER_GROUP(s)	(EXT4_SB(s)->s_clusters_per_group)
344 345 346
# define EXT4_DESC_PER_BLOCK(s)		(EXT4_SB(s)->s_desc_per_block)
# define EXT4_INODES_PER_GROUP(s)	(EXT4_SB(s)->s_inodes_per_group)
# define EXT4_DESC_PER_BLOCK_BITS(s)	(EXT4_SB(s)->s_desc_per_block_bits)
347
#else
348
# define EXT4_BLOCKS_PER_GROUP(s)	((s)->s_blocks_per_group)
349
# define EXT4_DESC_PER_BLOCK(s)		(EXT4_BLOCK_SIZE(s) / EXT4_DESC_SIZE(s))
350
# define EXT4_INODES_PER_GROUP(s)	((s)->s_inodes_per_group)
351 352 353 354 355
#endif

/*
 * Constants relative to the data blocks
 */
356 357 358 359 360
#define	EXT4_NDIR_BLOCKS		12
#define	EXT4_IND_BLOCK			EXT4_NDIR_BLOCKS
#define	EXT4_DIND_BLOCK			(EXT4_IND_BLOCK + 1)
#define	EXT4_TIND_BLOCK			(EXT4_DIND_BLOCK + 1)
#define	EXT4_N_BLOCKS			(EXT4_TIND_BLOCK + 1)
361 362 363 364

/*
 * Inode flags
 */
365 366 367 368 369 370 371 372
#define	EXT4_SECRM_FL			0x00000001 /* Secure deletion */
#define	EXT4_UNRM_FL			0x00000002 /* Undelete */
#define	EXT4_COMPR_FL			0x00000004 /* Compress file */
#define EXT4_SYNC_FL			0x00000008 /* Synchronous updates */
#define EXT4_IMMUTABLE_FL		0x00000010 /* Immutable file */
#define EXT4_APPEND_FL			0x00000020 /* writes to file may only append */
#define EXT4_NODUMP_FL			0x00000040 /* do not dump file */
#define EXT4_NOATIME_FL			0x00000080 /* do not update atime */
373
/* Reserved for compression usage... */
374 375 376
#define EXT4_DIRTY_FL			0x00000100
#define EXT4_COMPRBLK_FL		0x00000200 /* One or more compressed clusters */
#define EXT4_NOCOMPR_FL			0x00000400 /* Don't compress */
377 378
	/* nb: was previously EXT2_ECOMPR_FL */
#define EXT4_ENCRYPT_FL			0x00000800 /* encrypted file */
379
/* End compression flags --- maybe not all used */
380 381 382 383 384 385
#define EXT4_INDEX_FL			0x00001000 /* hash-indexed directory */
#define EXT4_IMAGIC_FL			0x00002000 /* AFS directory */
#define EXT4_JOURNAL_DATA_FL		0x00004000 /* file data should be journaled */
#define EXT4_NOTAIL_FL			0x00008000 /* file tail should not be merged */
#define EXT4_DIRSYNC_FL			0x00010000 /* dirsync behaviour (directories only) */
#define EXT4_TOPDIR_FL			0x00020000 /* Top of directory hierarchies*/
A
Aneesh Kumar K.V 已提交
386
#define EXT4_HUGE_FILE_FL               0x00040000 /* Set to each huge file */
A
Alex Tomas 已提交
387
#define EXT4_EXTENTS_FL			0x00080000 /* Inode uses extents */
388
#define EXT4_EA_INODE_FL	        0x00200000 /* Inode used for large EA */
389
#define EXT4_EOFBLOCKS_FL		0x00400000 /* Blocks allocated beyond EOF */
390
#define EXT4_INLINE_DATA_FL		0x10000000 /* Inode has inline data. */
391
#define EXT4_PROJINHERIT_FL		0x20000000 /* Create with parents projid */
A
Aneesh Kumar K.V 已提交
392
#define EXT4_RESERVED_FL		0x80000000 /* reserved for ext4 lib */
393

L
Li Xi 已提交
394 395
#define EXT4_FL_USER_VISIBLE		0x304BDFFF /* User visible flags */
#define EXT4_FL_USER_MODIFIABLE		0x204380FF /* User modifiable flags */
396

397 398 399 400 401 402 403
#define EXT4_FL_XFLAG_VISIBLE		(EXT4_SYNC_FL | \
					 EXT4_IMMUTABLE_FL | \
					 EXT4_APPEND_FL | \
					 EXT4_NODUMP_FL | \
					 EXT4_NOATIME_FL | \
					 EXT4_PROJINHERIT_FL)

404 405
/* Flags that should be inherited by new inodes from their parent. */
#define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\
406
			   EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
407
			   EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\
L
Li Xi 已提交
408 409
			   EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL |\
			   EXT4_PROJINHERIT_FL)
410

411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427
/* Flags that are appropriate for regular files (all but dir-specific ones). */
#define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL))

/* Flags that are appropriate for non-directories/regular files. */
#define EXT4_OTHER_FLMASK (EXT4_NODUMP_FL | EXT4_NOATIME_FL)

/* Mask out flags that are inappropriate for the given type of inode. */
static inline __u32 ext4_mask_flags(umode_t mode, __u32 flags)
{
	if (S_ISDIR(mode))
		return flags;
	else if (S_ISREG(mode))
		return flags & EXT4_REG_FLMASK;
	else
		return flags & EXT4_OTHER_FLMASK;
}

428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443
/*
 * Inode flags used for atomic set/get
 */
enum {
	EXT4_INODE_SECRM	= 0,	/* Secure deletion */
	EXT4_INODE_UNRM		= 1,	/* Undelete */
	EXT4_INODE_COMPR	= 2,	/* Compress file */
	EXT4_INODE_SYNC		= 3,	/* Synchronous updates */
	EXT4_INODE_IMMUTABLE	= 4,	/* Immutable file */
	EXT4_INODE_APPEND	= 5,	/* writes to file may only append */
	EXT4_INODE_NODUMP	= 6,	/* do not dump file */
	EXT4_INODE_NOATIME	= 7,	/* do not update atime */
/* Reserved for compression usage... */
	EXT4_INODE_DIRTY	= 8,
	EXT4_INODE_COMPRBLK	= 9,	/* One or more compressed clusters */
	EXT4_INODE_NOCOMPR	= 10,	/* Don't compress */
444
	EXT4_INODE_ENCRYPT	= 11,	/* Encrypted file */
445 446 447 448 449 450 451 452 453 454 455
/* End compression flags --- maybe not all used */
	EXT4_INODE_INDEX	= 12,	/* hash-indexed directory */
	EXT4_INODE_IMAGIC	= 13,	/* AFS directory */
	EXT4_INODE_JOURNAL_DATA	= 14,	/* file data should be journaled */
	EXT4_INODE_NOTAIL	= 15,	/* file tail should not be merged */
	EXT4_INODE_DIRSYNC	= 16,	/* dirsync behaviour (directories only) */
	EXT4_INODE_TOPDIR	= 17,	/* Top of directory hierarchies*/
	EXT4_INODE_HUGE_FILE	= 18,	/* Set to each huge file */
	EXT4_INODE_EXTENTS	= 19,	/* Inode uses extents */
	EXT4_INODE_EA_INODE	= 21,	/* Inode used for large EA */
	EXT4_INODE_EOFBLOCKS	= 22,	/* Blocks allocated beyond EOF */
456
	EXT4_INODE_INLINE_DATA	= 28,	/* Data in inode. */
457
	EXT4_INODE_PROJINHERIT	= 29,	/* Create with parents projid */
458 459 460 461
	EXT4_INODE_RESERVED	= 31,	/* reserved for ext4 lib */
};

/*
462 463 464 465 466 467 468 469 470
 * Since it's pretty easy to mix up bit numbers and hex values, we use a
 * build-time check to make sure that EXT4_XXX_FL is consistent with respect to
 * EXT4_INODE_XXX. If all is well, the macros will be dropped, so, it won't cost
 * any extra space in the compiled kernel image, otherwise, the build will fail.
 * It's important that these values are the same, since we are using
 * EXT4_INODE_XXX to test for flag values, but EXT4_XXX_FL must be consistent
 * with the values of FS_XXX_FL defined in include/linux/fs.h and the on-disk
 * values found in ext2, ext3 and ext4 filesystems, and of course the values
 * defined in e2fsprogs.
471 472 473
 *
 * It's not paranoia if the Murphy's Law really *is* out to get you.  :-)
 */
474 475 476
#define TEST_FLAG_VALUE(FLAG) (EXT4_##FLAG##_FL == (1 << EXT4_INODE_##FLAG))
#define CHECK_FLAG_VALUE(FLAG) BUILD_BUG_ON(!TEST_FLAG_VALUE(FLAG))

477 478 479 480 481 482 483 484 485 486 487 488 489
static inline void ext4_check_flag_values(void)
{
	CHECK_FLAG_VALUE(SECRM);
	CHECK_FLAG_VALUE(UNRM);
	CHECK_FLAG_VALUE(COMPR);
	CHECK_FLAG_VALUE(SYNC);
	CHECK_FLAG_VALUE(IMMUTABLE);
	CHECK_FLAG_VALUE(APPEND);
	CHECK_FLAG_VALUE(NODUMP);
	CHECK_FLAG_VALUE(NOATIME);
	CHECK_FLAG_VALUE(DIRTY);
	CHECK_FLAG_VALUE(COMPRBLK);
	CHECK_FLAG_VALUE(NOCOMPR);
490
	CHECK_FLAG_VALUE(ENCRYPT);
491 492 493 494 495 496 497 498 499 500
	CHECK_FLAG_VALUE(INDEX);
	CHECK_FLAG_VALUE(IMAGIC);
	CHECK_FLAG_VALUE(JOURNAL_DATA);
	CHECK_FLAG_VALUE(NOTAIL);
	CHECK_FLAG_VALUE(DIRSYNC);
	CHECK_FLAG_VALUE(TOPDIR);
	CHECK_FLAG_VALUE(HUGE_FILE);
	CHECK_FLAG_VALUE(EXTENTS);
	CHECK_FLAG_VALUE(EA_INODE);
	CHECK_FLAG_VALUE(EOFBLOCKS);
501
	CHECK_FLAG_VALUE(INLINE_DATA);
502
	CHECK_FLAG_VALUE(PROJINHERIT);
503 504 505
	CHECK_FLAG_VALUE(RESERVED);
}

506
/* Used to pass group descriptor data when online resize is done */
507
struct ext4_new_group_input {
D
Dave Kleikamp 已提交
508 509 510 511 512 513
	__u32 group;		/* Group number for this data */
	__u64 block_bitmap;	/* Absolute block number of block bitmap */
	__u64 inode_bitmap;	/* Absolute block number of inode bitmap */
	__u64 inode_table;	/* Absolute block number of inode table start */
	__u32 blocks_count;	/* Total number of blocks in this group */
	__u16 reserved_blocks;	/* Number of reserved blocks in this group */
514 515 516
	__u16 unused;
};

517 518 519 520 521 522 523 524 525 526 527 528
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
struct compat_ext4_new_group_input {
	u32 group;
	compat_u64 block_bitmap;
	compat_u64 inode_bitmap;
	compat_u64 inode_table;
	u32 blocks_count;
	u16 reserved_blocks;
	u16 unused;
};
#endif

529 530
/* The struct ext4_new_group_input in kernel space, with free_blocks_count */
struct ext4_new_group_data {
531
	__u32 group;
L
Laurent Vivier 已提交
532 533 534
	__u64 block_bitmap;
	__u64 inode_bitmap;
	__u64 inode_table;
535 536 537 538 539 540
	__u32 blocks_count;
	__u16 reserved_blocks;
	__u16 unused;
	__u32 free_blocks_count;
};

541 542 543 544 545 546 547 548
/* Indexes used to index group tables in ext4_new_group_data */
enum {
	BLOCK_BITMAP = 0,	/* block bitmap */
	INODE_BITMAP,		/* inode bitmap */
	INODE_TABLE,		/* inode tables */
	GROUP_TABLE_COUNT,
};

A
Amit Arora 已提交
549
/*
550
 * Flags used by ext4_map_blocks()
A
Amit Arora 已提交
551
 */
552
	/* Allocate any needed blocks and/or convert an unwritten
553
	   extent to be an initialized ext4 */
554
#define EXT4_GET_BLOCKS_CREATE			0x0001
555 556 557
	/* Request the creation of an unwritten extent */
#define EXT4_GET_BLOCKS_UNWRIT_EXT		0x0002
#define EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT	(EXT4_GET_BLOCKS_UNWRIT_EXT|\
558
						 EXT4_GET_BLOCKS_CREATE)
L
Lukas Czerner 已提交
559 560
	/* Caller is from the delayed allocation writeout path
	 * finally doing the actual allocation of delayed blocks */
561
#define EXT4_GET_BLOCKS_DELALLOC_RESERVE	0x0004
562
	/* caller is from the direct IO path, request to creation of an
563
	unwritten extents if not allocated, split the unwritten
564
	extent if blocks has been preallocated already*/
565
#define EXT4_GET_BLOCKS_PRE_IO			0x0008
566
#define EXT4_GET_BLOCKS_CONVERT			0x0010
567
#define EXT4_GET_BLOCKS_IO_CREATE_EXT		(EXT4_GET_BLOCKS_PRE_IO|\
568
					 EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT)
569 570
	/* Convert extent to initialized after IO complete */
#define EXT4_GET_BLOCKS_IO_CONVERT_EXT		(EXT4_GET_BLOCKS_CONVERT|\
571
					 EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT)
L
Lukas Czerner 已提交
572 573 574
	/* Eventual metadata allocation (due to growing extent tree)
	 * should not fail, so try to use reserved blocks for that.*/
#define EXT4_GET_BLOCKS_METADATA_NOFAIL		0x0020
575 576
	/* Don't normalize allocation size (used for fallocate) */
#define EXT4_GET_BLOCKS_NO_NORMALIZE		0x0040
577 578
	/* Request will not result in inode size update (user for fallocate) */
#define EXT4_GET_BLOCKS_KEEP_SIZE		0x0080
579
	/* Convert written extents to unwritten */
580
#define EXT4_GET_BLOCKS_CONVERT_UNWRITTEN	0x0100
581 582 583 584
	/* Write zeros to newly created written extents */
#define EXT4_GET_BLOCKS_ZERO			0x0200
#define EXT4_GET_BLOCKS_CREATE_ZERO		(EXT4_GET_BLOCKS_CREATE |\
					EXT4_GET_BLOCKS_ZERO)
585 586 587
	/* Caller will submit data before dropping transaction handle. This
	 * allows jbd2 to avoid submitting data before commit. */
#define EXT4_GET_BLOCKS_IO_SUBMIT		0x0400
588

589
/*
590
 * The bit position of these flags must not overlap with any of the
591
 * EXT4_GET_BLOCKS_*.  They are used by ext4_find_extent(),
592
 * read_extent_tree_block(), ext4_split_extent_at(),
593 594 595 596
 * ext4_ext_insert_extent(), and ext4_ext_create_new_leaf().
 * EXT4_EX_NOCACHE is used to indicate that the we shouldn't be
 * caching the extents when reading from the extent tree while a
 * truncate or punch hole operation is in progress.
597
 */
598 599
#define EXT4_EX_NOCACHE				0x40000000
#define EXT4_EX_FORCE_CACHE			0x20000000
600

601 602 603 604 605
/*
 * Flags used by ext4_free_blocks
 */
#define EXT4_FREE_BLOCKS_METADATA	0x0001
#define EXT4_FREE_BLOCKS_FORGET		0x0002
606
#define EXT4_FREE_BLOCKS_VALIDATED	0x0004
607
#define EXT4_FREE_BLOCKS_NO_QUOT_UPDATE	0x0008
608 609
#define EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER	0x0010
#define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER	0x0020
610

611 612 613 614 615 616 617
/* Encryption algorithms */
#define EXT4_ENCRYPTION_MODE_INVALID		0
#define EXT4_ENCRYPTION_MODE_AES_256_XTS	1
#define EXT4_ENCRYPTION_MODE_AES_256_GCM	2
#define EXT4_ENCRYPTION_MODE_AES_256_CBC	3
#define EXT4_ENCRYPTION_MODE_AES_256_CTS	4

618 619
#include "ext4_crypto.h"

620 621 622
/*
 * ioctl commands
 */
623 624 625 626 627 628 629 630
#define	EXT4_IOC_GETFLAGS		FS_IOC_GETFLAGS
#define	EXT4_IOC_SETFLAGS		FS_IOC_SETFLAGS
#define	EXT4_IOC_GETVERSION		_IOR('f', 3, long)
#define	EXT4_IOC_SETVERSION		_IOW('f', 4, long)
#define	EXT4_IOC_GETVERSION_OLD		FS_IOC_GETVERSION
#define	EXT4_IOC_SETVERSION_OLD		FS_IOC_SETVERSION
#define EXT4_IOC_GETRSVSZ		_IOR('f', 5, long)
#define EXT4_IOC_SETRSVSZ		_IOW('f', 6, long)
T
Theodore Ts'o 已提交
631 632 633
#define EXT4_IOC_GROUP_EXTEND		_IOW('f', 7, unsigned long)
#define EXT4_IOC_GROUP_ADD		_IOW('f', 8, struct ext4_new_group_input)
#define EXT4_IOC_MIGRATE		_IO('f', 9)
634
 /* note ioctl 10 reserved for an early version of the FIEMAP ioctl */
T
Theodore Ts'o 已提交
635
 /* note ioctl 11 reserved for filesystem-independent FIEMAP ioctl */
636
#define EXT4_IOC_ALLOC_DA_BLKS		_IO('f', 12)
637
#define EXT4_IOC_MOVE_EXT		_IOWR('f', 15, struct move_extent)
638
#define EXT4_IOC_RESIZE_FS		_IOW('f', 16, __u64)
639
#define EXT4_IOC_SWAP_BOOT		_IO('f', 17)
640
#define EXT4_IOC_PRECACHE_EXTENTS	_IO('f', 18)
641 642 643
#define EXT4_IOC_SET_ENCRYPTION_POLICY	_IOR('f', 19, struct ext4_encryption_policy)
#define EXT4_IOC_GET_ENCRYPTION_PWSALT	_IOW('f', 20, __u8[16])
#define EXT4_IOC_GET_ENCRYPTION_POLICY	_IOW('f', 21, struct ext4_encryption_policy)
644

645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684
#ifndef FS_IOC_FSGETXATTR
/* Until the uapi changes get merged for project quota... */

#define FS_IOC_FSGETXATTR		_IOR('X', 31, struct fsxattr)
#define FS_IOC_FSSETXATTR		_IOW('X', 32, struct fsxattr)

/*
 * Structure for FS_IOC_FSGETXATTR and FS_IOC_FSSETXATTR.
 */
struct fsxattr {
	__u32		fsx_xflags;	/* xflags field value (get/set) */
	__u32		fsx_extsize;	/* extsize field value (get/set)*/
	__u32		fsx_nextents;	/* nextents field value (get)	*/
	__u32		fsx_projid;	/* project identifier (get/set) */
	unsigned char	fsx_pad[12];
};

/*
 * Flags for the fsx_xflags field
 */
#define FS_XFLAG_REALTIME	0x00000001	/* data in realtime volume */
#define FS_XFLAG_PREALLOC	0x00000002	/* preallocated file extents */
#define FS_XFLAG_IMMUTABLE	0x00000008	/* file cannot be modified */
#define FS_XFLAG_APPEND		0x00000010	/* all writes append */
#define FS_XFLAG_SYNC		0x00000020	/* all writes synchronous */
#define FS_XFLAG_NOATIME	0x00000040	/* do not update access time */
#define FS_XFLAG_NODUMP		0x00000080	/* do not include in backups */
#define FS_XFLAG_RTINHERIT	0x00000100	/* create with rt bit set */
#define FS_XFLAG_PROJINHERIT	0x00000200	/* create with parents projid */
#define FS_XFLAG_NOSYMLINKS	0x00000400	/* disallow symlink creation */
#define FS_XFLAG_EXTSIZE	0x00000800	/* extent size allocator hint */
#define FS_XFLAG_EXTSZINHERIT	0x00001000	/* inherit inode extent size */
#define FS_XFLAG_NODEFRAG	0x00002000  	/* do not defragment */
#define FS_XFLAG_FILESTREAM	0x00004000	/* use filestream allocator */
#define FS_XFLAG_HASATTR	0x80000000	/* no DIFLAG for this */
#endif /* !defined(FS_IOC_FSGETXATTR) */

#define EXT4_IOC_FSGETXATTR		FS_IOC_FSGETXATTR
#define EXT4_IOC_FSSETXATTR		FS_IOC_FSSETXATTR

685
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
686 687 688
/*
 * ioctl commands in 32 bit emulation
 */
689 690 691 692 693 694 695
#define EXT4_IOC32_GETFLAGS		FS_IOC32_GETFLAGS
#define EXT4_IOC32_SETFLAGS		FS_IOC32_SETFLAGS
#define EXT4_IOC32_GETVERSION		_IOR('f', 3, int)
#define EXT4_IOC32_SETVERSION		_IOW('f', 4, int)
#define EXT4_IOC32_GETRSVSZ		_IOR('f', 5, int)
#define EXT4_IOC32_SETRSVSZ		_IOW('f', 6, int)
#define EXT4_IOC32_GROUP_EXTEND		_IOW('f', 7, unsigned int)
696
#define EXT4_IOC32_GROUP_ADD		_IOW('f', 8, struct compat_ext4_new_group_input)
697 698
#define EXT4_IOC32_GETVERSION_OLD	FS_IOC32_GETVERSION
#define EXT4_IOC32_SETVERSION_OLD	FS_IOC32_SETVERSION
699
#endif
700

701
/* Max physical block we can address w/o extents */
702 703
#define EXT4_MAX_BLOCK_FILE_PHYS	0xFFFFFFFF

704 705 706
/*
 * Structure of an inode on the disk
 */
707
struct ext4_inode {
708 709
	__le16	i_mode;		/* File mode */
	__le16	i_uid;		/* Low 16 bits of Owner Uid */
710
	__le32	i_size_lo;	/* Size in bytes */
711
	__le32	i_atime;	/* Access time */
K
Kalpak Shah 已提交
712
	__le32	i_ctime;	/* Inode Change time */
713 714 715 716
	__le32	i_mtime;	/* Modification time */
	__le32	i_dtime;	/* Deletion Time */
	__le16	i_gid;		/* Low 16 bits of Group Id */
	__le16	i_links_count;	/* Links count */
717
	__le32	i_blocks_lo;	/* Blocks count */
718 719 720
	__le32	i_flags;	/* File flags */
	union {
		struct {
721
			__le32  l_i_version;
722 723 724 725 726 727 728 729
		} linux1;
		struct {
			__u32  h_i_translator;
		} hurd1;
		struct {
			__u32  m_i_reserved1;
		} masix1;
	} osd1;				/* OS dependent 1 */
730
	__le32	i_block[EXT4_N_BLOCKS];/* Pointers to blocks */
731
	__le32	i_generation;	/* File version (for NFS) */
732
	__le32	i_file_acl_lo;	/* File ACL */
733
	__le32	i_size_high;
734
	__le32	i_obso_faddr;	/* Obsoleted fragment address */
735 736
	union {
		struct {
737
			__le16	l_i_blocks_high; /* were l_i_reserved1 */
B
Badari Pulavarty 已提交
738
			__le16	l_i_file_acl_high;
D
Dave Kleikamp 已提交
739
			__le16	l_i_uid_high;	/* these 2 fields */
740
			__le16	l_i_gid_high;	/* were reserved2[0] */
741 742
			__le16	l_i_checksum_lo;/* crc32c(uuid+inum+inode) LE */
			__le16	l_i_reserved;
743 744
		} linux2;
		struct {
745
			__le16	h_i_reserved1;	/* Obsoleted fragment number/size which are removed in ext4 */
746 747 748 749 750 751
			__u16	h_i_mode_high;
			__u16	h_i_uid_high;
			__u16	h_i_gid_high;
			__u32	h_i_author;
		} hurd2;
		struct {
752
			__le16	h_i_reserved1;	/* Obsoleted fragment number/size which are removed in ext4 */
B
Badari Pulavarty 已提交
753
			__le16	m_i_file_acl_high;
754 755 756 757
			__u32	m_i_reserved2[2];
		} masix2;
	} osd2;				/* OS dependent 2 */
	__le16	i_extra_isize;
758
	__le16	i_checksum_hi;	/* crc32c(uuid+inum+inode) BE */
K
Kalpak Shah 已提交
759 760 761 762 763
	__le32  i_ctime_extra;  /* extra Change time      (nsec << 2 | epoch) */
	__le32  i_mtime_extra;  /* extra Modification time(nsec << 2 | epoch) */
	__le32  i_atime_extra;  /* extra Access time      (nsec << 2 | epoch) */
	__le32  i_crtime;       /* File Creation time */
	__le32  i_crtime_extra; /* extra FileCreationtime (nsec << 2 | epoch) */
764
	__le32  i_version_hi;	/* high 32 bits for 64-bit version */
765
	__le32	i_projid;	/* Project ID */
766 767
};

768 769 770 771 772 773 774 775
struct move_extent {
	__u32 reserved;		/* should be zero */
	__u32 donor_fd;		/* donor file descriptor */
	__u64 orig_start;	/* logical start offset in block for orig */
	__u64 donor_start;	/* logical start offset in block for donor */
	__u64 len;		/* block length to be moved */
	__u64 moved_len;	/* moved block length */
};
776

K
Kalpak Shah 已提交
777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796
#define EXT4_EPOCH_BITS 2
#define EXT4_EPOCH_MASK ((1 << EXT4_EPOCH_BITS) - 1)
#define EXT4_NSEC_MASK  (~0UL << EXT4_EPOCH_BITS)

/*
 * Extended fields will fit into an inode if the filesystem was formatted
 * with large inodes (-I 256 or larger) and there are not currently any EAs
 * consuming all of the available space. For new inodes we always reserve
 * enough space for the kernel's known extended fields, but for inodes
 * created with an old kernel this might not have been the case. None of
 * the extended inode fields is critical for correct filesystem operation.
 * This macro checks if a certain field fits in the inode. Note that
 * inode-size = GOOD_OLD_INODE_SIZE + i_extra_isize
 */
#define EXT4_FITS_IN_INODE(ext4_inode, einode, field)	\
	((offsetof(typeof(*ext4_inode), field) +	\
	  sizeof((ext4_inode)->field))			\
	<= (EXT4_GOOD_OLD_INODE_SIZE +			\
	    (einode)->i_extra_isize))			\

797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817
/*
 * We use an encoding that preserves the times for extra epoch "00":
 *
 * extra  msb of                         adjust for signed
 * epoch  32-bit                         32-bit tv_sec to
 * bits   time    decoded 64-bit tv_sec  64-bit tv_sec      valid time range
 * 0 0    1    -0x80000000..-0x00000001  0x000000000 1901-12-13..1969-12-31
 * 0 0    0    0x000000000..0x07fffffff  0x000000000 1970-01-01..2038-01-19
 * 0 1    1    0x080000000..0x0ffffffff  0x100000000 2038-01-19..2106-02-07
 * 0 1    0    0x100000000..0x17fffffff  0x100000000 2106-02-07..2174-02-25
 * 1 0    1    0x180000000..0x1ffffffff  0x200000000 2174-02-25..2242-03-16
 * 1 0    0    0x200000000..0x27fffffff  0x200000000 2242-03-16..2310-04-04
 * 1 1    1    0x280000000..0x2ffffffff  0x300000000 2310-04-04..2378-04-22
 * 1 1    0    0x300000000..0x37fffffff  0x300000000 2378-04-22..2446-05-10
 *
 * Note that previous versions of the kernel on 64-bit systems would
 * incorrectly use extra epoch bits 1,1 for dates between 1901 and
 * 1970.  e2fsck will correct this, assuming that it is run on the
 * affected filesystem before 2242.
 */

K
Kalpak Shah 已提交
818 819
static inline __le32 ext4_encode_extra_time(struct timespec *time)
{
820 821 822
	u32 extra = sizeof(time->tv_sec) > 4 ?
		((time->tv_sec - (s32)time->tv_sec) >> 32) & EXT4_EPOCH_MASK : 0;
	return cpu_to_le32(extra | (time->tv_nsec << EXT4_EPOCH_BITS));
K
Kalpak Shah 已提交
823 824 825 826
}

static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra)
{
827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845
	if (unlikely(sizeof(time->tv_sec) > 4 &&
			(extra & cpu_to_le32(EXT4_EPOCH_MASK)))) {
#if LINUX_VERSION_CODE < KERNEL_VERSION(4,20,0)
		/* Handle legacy encoding of pre-1970 dates with epoch
		 * bits 1,1.  We assume that by kernel version 4.20,
		 * everyone will have run fsck over the affected
		 * filesystems to correct the problem.  (This
		 * backwards compatibility may be removed before this
		 * time, at the discretion of the ext4 developers.)
		 */
		u64 extra_bits = le32_to_cpu(extra) & EXT4_EPOCH_MASK;
		if (extra_bits == 3 && ((time->tv_sec) & 0x80000000) != 0)
			extra_bits = 0;
		time->tv_sec += extra_bits << 32;
#else
		time->tv_sec += (u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK) << 32;
#endif
	}
	time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS;
K
Kalpak Shah 已提交
846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870
}

#define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode)			       \
do {									       \
	(raw_inode)->xtime = cpu_to_le32((inode)->xtime.tv_sec);	       \
	if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra))     \
		(raw_inode)->xtime ## _extra =				       \
				ext4_encode_extra_time(&(inode)->xtime);       \
} while (0)

#define EXT4_EINODE_SET_XTIME(xtime, einode, raw_inode)			       \
do {									       \
	if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime))		       \
		(raw_inode)->xtime = cpu_to_le32((einode)->xtime.tv_sec);      \
	if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra))	       \
		(raw_inode)->xtime ## _extra =				       \
				ext4_encode_extra_time(&(einode)->xtime);      \
} while (0)

#define EXT4_INODE_GET_XTIME(xtime, inode, raw_inode)			       \
do {									       \
	(inode)->xtime.tv_sec = (signed)le32_to_cpu((raw_inode)->xtime);       \
	if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra))     \
		ext4_decode_extra_time(&(inode)->xtime,			       \
				       raw_inode->xtime ## _extra);	       \
871 872
	else								       \
		(inode)->xtime.tv_nsec = 0;				       \
K
Kalpak Shah 已提交
873 874 875 876 877 878 879
} while (0)

#define EXT4_EINODE_GET_XTIME(xtime, einode, raw_inode)			       \
do {									       \
	if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime))		       \
		(einode)->xtime.tv_sec = 				       \
			(signed)le32_to_cpu((raw_inode)->xtime);	       \
880 881
	else								       \
		(einode)->xtime.tv_sec = 0;				       \
K
Kalpak Shah 已提交
882 883 884
	if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra))	       \
		ext4_decode_extra_time(&(einode)->xtime,		       \
				       raw_inode->xtime ## _extra);	       \
885 886
	else								       \
		(einode)->xtime.tv_nsec = 0;				       \
K
Kalpak Shah 已提交
887 888
} while (0)

889 890
#define i_disk_version osd1.linux1.l_i_version

891 892
#if defined(__KERNEL__) || defined(__linux__)
#define i_reserved1	osd1.linux1.l_i_reserved1
B
Badari Pulavarty 已提交
893
#define i_file_acl_high	osd2.linux2.l_i_file_acl_high
894
#define i_blocks_high	osd2.linux2.l_i_blocks_high
895 896 897 898
#define i_uid_low	i_uid
#define i_gid_low	i_gid
#define i_uid_high	osd2.linux2.l_i_uid_high
#define i_gid_high	osd2.linux2.l_i_gid_high
899
#define i_checksum_lo	osd2.linux2.l_i_checksum_lo
900 901 902 903 904 905 906 907 908 909 910

#elif defined(__GNU__)

#define i_translator	osd1.hurd1.h_i_translator
#define i_uid_high	osd2.hurd2.h_i_uid_high
#define i_gid_high	osd2.hurd2.h_i_gid_high
#define i_author	osd2.hurd2.h_i_author

#elif defined(__masix__)

#define i_reserved1	osd1.masix1.m_i_reserved1
B
Badari Pulavarty 已提交
911
#define i_file_acl_high	osd2.masix2.m_i_file_acl_high
912 913 914 915
#define i_reserved2	osd2.masix2.m_i_reserved2

#endif /* defined(__KERNEL__) || defined(__linux__) */

916 917
#include "extents_status.h"

918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940
/*
 * Lock subclasses for i_data_sem in the ext4_inode_info structure.
 *
 * These are needed to avoid lockdep false positives when we need to
 * allocate blocks to the quota inode during ext4_map_blocks(), while
 * holding i_data_sem for a normal (non-quota) inode.  Since we don't
 * do quota tracking for the quota inode, this avoids deadlock (as
 * well as infinite recursion, since it isn't turtles all the way
 * down...)
 *
 *  I_DATA_SEM_NORMAL - Used for most inodes
 *  I_DATA_SEM_OTHER  - Used by move_inode.c for the second normal inode
 *			  where the second inode has larger inode number
 *			  than the first
 *  I_DATA_SEM_QUOTA  - Used for quota inodes only
 */
enum {
	I_DATA_SEM_NORMAL = 0,
	I_DATA_SEM_OTHER,
	I_DATA_SEM_QUOTA,
};


941 942 943 944 945 946
/*
 * fourth extended file system inode data in memory
 */
struct ext4_inode_info {
	__le32	i_data[15];	/* unconverted */
	__u32	i_dtime;
947
	ext4_fsblk_t	i_file_acl;
948 949 950 951 952 953 954 955 956

	/*
	 * i_block_group is the number of the block group which contains
	 * this file's inode.  Constant across the lifetime of the inode,
	 * it is ued for making block allocation decisions - we try to
	 * place a file's data blocks near its inode block, and new inodes
	 * near to their parent directory's inode.
	 */
	ext4_group_t	i_block_group;
957
	ext4_lblk_t	i_dir_start_lookup;
958
#if (BITS_PER_LONG < 64)
959
	unsigned long	i_state_flags;		/* Dynamic state flags */
960
#endif
961
	unsigned long	i_flags;
962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001

	/*
	 * Extended attributes can be read independently of the main file
	 * data. Taking i_mutex even when reading would cause contention
	 * between readers of EAs and writers of regular file data, so
	 * instead we synchronize on xattr_sem when reading or changing
	 * EAs.
	 */
	struct rw_semaphore xattr_sem;

	struct list_head i_orphan;	/* unlinked but open inodes */

	/*
	 * i_disksize keeps track of what the inode size is ON DISK, not
	 * in memory.  During truncate, i_size is set to the new size by
	 * the VFS prior to calling ext4_truncate(), but the filesystem won't
	 * set i_disksize to 0 until the truncate is actually under way.
	 *
	 * The intent is that i_disksize always represents the blocks which
	 * are used by this file.  This allows recovery to restart truncate
	 * on orphans if we crash during truncate.  We actually write i_disksize
	 * into the on-disk inode when writing inodes out, instead of i_size.
	 *
	 * The only time when i_disksize and i_size may be different is when
	 * a truncate is in progress.  The only things which change i_disksize
	 * are ext4_get_block (growth) and ext4_truncate (shrinkth).
	 */
	loff_t	i_disksize;

	/*
	 * i_data_sem is for serialising ext4_truncate() against
	 * ext4_getblock().  In the 2.4 ext2 design, great chunks of inode's
	 * data tree are chopped off during truncate. We can't do that in
	 * ext4 because whenever we perform intermediate commits during
	 * truncate, the inode and all the metadata blocks *must* be in a
	 * consistent state which allows truncation of the orphans to restart
	 * during recovery.  Hence we must fix the get_block-vs-truncate race
	 * by other means, so we have i_data_sem.
	 */
	struct rw_semaphore i_data_sem;
1002 1003 1004 1005 1006 1007 1008 1009 1010
	/*
	 * i_mmap_sem is for serializing page faults with truncate / punch hole
	 * operations. We have to make sure that new page cannot be faulted in
	 * a section of the inode that is being punched. We cannot easily use
	 * i_data_sem for this since we need protection for the whole punch
	 * operation and i_data_sem ranks below transaction start so we have
	 * to occasionally drop it.
	 */
	struct rw_semaphore i_mmap_sem;
1011
	struct inode vfs_inode;
1012
	struct jbd2_inode *jinode;
1013

1014 1015
	spinlock_t i_raw_lock;	/* protects updates to the raw inode */

1016 1017 1018 1019 1020 1021 1022 1023 1024 1025
	/*
	 * File creation time. Its function is same as that of
	 * struct timespec i_{a,c,m}time in the generic inode.
	 */
	struct timespec i_crtime;

	/* mballoc */
	struct list_head i_prealloc_list;
	spinlock_t i_prealloc_lock;

1026 1027 1028
	/* extents status tree */
	struct ext4_es_tree i_es_tree;
	rwlock_t i_es_lock;
1029
	struct list_head i_es_list;
1030
	unsigned int i_es_all_nr;	/* protected by i_es_lock */
1031
	unsigned int i_es_shk_nr;	/* protected by i_es_lock */
1032 1033 1034
	ext4_lblk_t i_es_shrink_lblk;	/* Offset where we start searching for
					   extents to shrink. Protected by
					   i_es_lock  */
1035

1036 1037 1038 1039
	/* ialloc */
	ext4_group_t	i_last_alloc_group;

	/* allocation reservation info for delalloc */
1040
	/* In case of bigalloc, these refer to clusters rather than blocks */
1041 1042 1043
	unsigned int i_reserved_data_blocks;
	unsigned int i_reserved_meta_blocks;
	unsigned int i_allocated_meta_blocks;
1044
	ext4_lblk_t i_da_metadata_calc_last_lblock;
1045
	int i_da_metadata_calc_len;
1046 1047 1048 1049

	/* on-disk additional length */
	__u16 i_extra_isize;

1050 1051 1052 1053
	/* Indicate the inline data space. */
	u16 i_inline_off;
	u16 i_inline_size;

1054 1055 1056 1057
#ifdef CONFIG_QUOTA
	/* quota space reservation, managed internally by quota code */
	qsize_t i_reserved_quota;
#endif
1058

1059
	/* Lock protecting lists below */
1060
	spinlock_t i_completed_io_lock;
1061 1062 1063 1064 1065 1066
	/*
	 * Completed IOs that need unwritten extents handling and have
	 * transaction reserved
	 */
	struct list_head i_rsv_conversion_list;
	struct work_struct i_rsv_conversion_work;
J
Jan Kara 已提交
1067
	atomic_t i_unwritten; /* Nr. of inflight conversions pending */
1068 1069

	spinlock_t i_block_reservation_lock;
1070 1071 1072 1073 1074 1075 1076

	/*
	 * Transactions that contain inode's metadata needed to complete
	 * fsync and fdatasync, respectively.
	 */
	tid_t i_sync_tid;
	tid_t i_datasync_tid;
1077

J
Jan Kara 已提交
1078 1079 1080 1081
#ifdef CONFIG_QUOTA
	struct dquot *i_dquot[MAXQUOTAS];
#endif

1082 1083
	/* Precomputed uuid+inum+igen checksum for seeding inode checksums */
	__u32 i_csum_seed;
1084 1085 1086

#ifdef CONFIG_EXT4_FS_ENCRYPTION
	/* Encryption params */
1087
	struct ext4_crypt_info *i_crypt_info;
1088
#endif
L
Li Xi 已提交
1089
	kprojid_t i_projid;
1090 1091
};

1092 1093 1094
/*
 * File system states
 */
1095 1096 1097
#define	EXT4_VALID_FS			0x0001	/* Unmounted cleanly */
#define	EXT4_ERROR_FS			0x0002	/* Errors detected */
#define	EXT4_ORPHAN_FS			0x0004	/* Orphans being recovered */
1098

1099 1100 1101 1102 1103 1104 1105
/*
 * Misc. filesystem flags
 */
#define EXT2_FLAGS_SIGNED_HASH		0x0001  /* Signed dirhash in use */
#define EXT2_FLAGS_UNSIGNED_HASH	0x0002  /* Unsigned dirhash in use */
#define EXT2_FLAGS_TEST_FILESYS		0x0004	/* to test development code */

1106
/*
1107
 * Mount flags set via mount options or defaults
1108
 */
1109 1110 1111 1112 1113
#define EXT4_MOUNT_GRPID		0x00004	/* Create files with directory's group */
#define EXT4_MOUNT_DEBUG		0x00008	/* Some debugging messages */
#define EXT4_MOUNT_ERRORS_CONT		0x00010	/* Continue on errors */
#define EXT4_MOUNT_ERRORS_RO		0x00020	/* Remount fs ro on errors */
#define EXT4_MOUNT_ERRORS_PANIC		0x00040	/* Panic on errors */
1114
#define EXT4_MOUNT_ERRORS_MASK		0x00070
1115 1116
#define EXT4_MOUNT_MINIX_DF		0x00080	/* Mimics the Minix statfs */
#define EXT4_MOUNT_NOLOAD		0x00100	/* Don't use existing journal*/
R
Ross Zwisler 已提交
1117 1118 1119 1120 1121
#ifdef CONFIG_FS_DAX
#define EXT4_MOUNT_DAX			0x00200	/* Direct Access */
#else
#define EXT4_MOUNT_DAX			0
#endif
1122 1123 1124 1125 1126 1127 1128 1129
#define EXT4_MOUNT_DATA_FLAGS		0x00C00	/* Mode for data writes: */
#define EXT4_MOUNT_JOURNAL_DATA		0x00400	/* Write data to journal */
#define EXT4_MOUNT_ORDERED_DATA		0x00800	/* Flush data before commit */
#define EXT4_MOUNT_WRITEBACK_DATA	0x00C00	/* No data ordering */
#define EXT4_MOUNT_UPDATE_JOURNAL	0x01000	/* Update the journal format */
#define EXT4_MOUNT_NO_UID32		0x02000  /* Disable 32-bit UIDs */
#define EXT4_MOUNT_XATTR_USER		0x04000	/* Extended user attributes */
#define EXT4_MOUNT_POSIX_ACL		0x08000	/* POSIX Access Control Lists */
1130
#define EXT4_MOUNT_NO_AUTO_DA_ALLOC	0x10000	/* No auto delalloc mapping */
1131 1132 1133 1134
#define EXT4_MOUNT_BARRIER		0x20000 /* Use block barriers */
#define EXT4_MOUNT_QUOTA		0x80000 /* Some quota option set */
#define EXT4_MOUNT_USRQUOTA		0x100000 /* "old" user quota */
#define EXT4_MOUNT_GRPQUOTA		0x200000 /* "old" group quota */
1135
#define EXT4_MOUNT_DIOREAD_NOLOCK	0x400000 /* Enable support for dio read nolocking */
1136
#define EXT4_MOUNT_JOURNAL_CHECKSUM	0x800000 /* Journal checksums */
1137
#define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT	0x1000000 /* Journal Async Commit */
1138
#define EXT4_MOUNT_DELALLOC		0x8000000 /* Delalloc support */
1139
#define EXT4_MOUNT_DATA_ERR_ABORT	0x10000000 /* Abort on file data write */
1140
#define EXT4_MOUNT_BLOCK_VALIDITY	0x20000000 /* Block validity checking */
1141
#define EXT4_MOUNT_DISCARD		0x40000000 /* Issue DISCARD requests */
1142
#define EXT4_MOUNT_INIT_INODE_TABLE	0x80000000 /* Initialize uninitialized itables */
1143

1144 1145 1146 1147 1148
/*
 * Mount flags set either automatically (could not be set by mount option)
 * based on per file system feature or property or in special cases such as
 * distinguishing between explicit mount option definition and default.
 */
1149 1150
#define EXT4_MOUNT2_EXPLICIT_DELALLOC	0x00000001 /* User explicitly
						      specified delalloc */
1151 1152 1153
#define EXT4_MOUNT2_STD_GROUP_SIZE	0x00000002 /* We have standard group
						      size of blocksize * 8
						      blocks */
1154 1155
#define EXT4_MOUNT2_HURD_COMPAT		0x00000004 /* Support HURD-castrated
						      file systems */
1156

1157 1158 1159
#define EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM	0x00000008 /* User explicitly
						specified journal checksum */

1160 1161 1162 1163
#define clear_opt(sb, opt)		EXT4_SB(sb)->s_mount_opt &= \
						~EXT4_MOUNT_##opt
#define set_opt(sb, opt)		EXT4_SB(sb)->s_mount_opt |= \
						EXT4_MOUNT_##opt
1164 1165
#define test_opt(sb, opt)		(EXT4_SB(sb)->s_mount_opt & \
					 EXT4_MOUNT_##opt)
1166

1167 1168 1169 1170 1171 1172 1173
#define clear_opt2(sb, opt)		EXT4_SB(sb)->s_mount_opt2 &= \
						~EXT4_MOUNT2_##opt
#define set_opt2(sb, opt)		EXT4_SB(sb)->s_mount_opt2 |= \
						EXT4_MOUNT2_##opt
#define test_opt2(sb, opt)		(EXT4_SB(sb)->s_mount_opt2 & \
					 EXT4_MOUNT2_##opt)

1174 1175
#define ext4_test_and_set_bit		__test_and_set_bit_le
#define ext4_set_bit			__set_bit_le
1176
#define ext4_set_bit_atomic		ext2_set_bit_atomic
1177 1178
#define ext4_test_and_clear_bit		__test_and_clear_bit_le
#define ext4_clear_bit			__clear_bit_le
1179
#define ext4_clear_bit_atomic		ext2_clear_bit_atomic
A
Akinobu Mita 已提交
1180 1181 1182
#define ext4_test_bit			test_bit_le
#define ext4_find_next_zero_bit		find_next_zero_bit_le
#define ext4_find_next_bit		find_next_bit_le
1183

1184 1185
extern void ext4_set_bits(void *bm, int cur, int len);

1186 1187 1188
/*
 * Maximal mount counts between two filesystem checks
 */
1189 1190
#define EXT4_DFL_MAX_MNT_COUNT		20	/* Allow 20 mounts */
#define EXT4_DFL_CHECKINTERVAL		0	/* Don't use interval check */
1191 1192 1193 1194

/*
 * Behaviour when detecting errors
 */
1195 1196 1197 1198
#define EXT4_ERRORS_CONTINUE		1	/* Continue execution */
#define EXT4_ERRORS_RO			2	/* Remount fs read-only */
#define EXT4_ERRORS_PANIC		3	/* Panic */
#define EXT4_ERRORS_DEFAULT		EXT4_ERRORS_CONTINUE
1199

1200 1201 1202
/* Metadata checksum algorithm codes */
#define EXT4_CRC32C_CHKSUM		1

1203 1204 1205
/*
 * Structure of the super block
 */
1206
struct ext4_super_block {
1207
/*00*/	__le32	s_inodes_count;		/* Inodes count */
1208
	__le32	s_blocks_count_lo;	/* Blocks count */
1209 1210
	__le32	s_r_blocks_count_lo;	/* Reserved blocks count */
	__le32	s_free_blocks_count_lo;	/* Free blocks count */
1211 1212 1213
/*10*/	__le32	s_free_inodes_count;	/* Free inodes count */
	__le32	s_first_data_block;	/* First Data Block */
	__le32	s_log_block_size;	/* Block size */
1214
	__le32	s_log_cluster_size;	/* Allocation cluster size */
1215
/*20*/	__le32	s_blocks_per_group;	/* # Blocks per group */
1216
	__le32	s_clusters_per_group;	/* # Clusters per group */
1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232
	__le32	s_inodes_per_group;	/* # Inodes per group */
	__le32	s_mtime;		/* Mount time */
/*30*/	__le32	s_wtime;		/* Write time */
	__le16	s_mnt_count;		/* Mount count */
	__le16	s_max_mnt_count;	/* Maximal mount count */
	__le16	s_magic;		/* Magic signature */
	__le16	s_state;		/* File system state */
	__le16	s_errors;		/* Behaviour when detecting errors */
	__le16	s_minor_rev_level;	/* minor revision level */
/*40*/	__le32	s_lastcheck;		/* time of last check */
	__le32	s_checkinterval;	/* max. time between checks */
	__le32	s_creator_os;		/* OS */
	__le32	s_rev_level;		/* Revision level */
/*50*/	__le16	s_def_resuid;		/* Default uid for reserved blocks */
	__le16	s_def_resgid;		/* Default gid for reserved blocks */
	/*
1233
	 * These fields are for EXT4_DYNAMIC_REV superblocks only.
1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245
	 *
	 * Note: the difference between the compatible feature set and
	 * the incompatible feature set is that if there is a bit set
	 * in the incompatible feature set that the kernel doesn't
	 * know about, it should refuse to mount the filesystem.
	 *
	 * e2fsck's requirements are more strict; if it doesn't know
	 * about a feature in either the compatible or incompatible
	 * feature set, it must abort and not try to meddle with
	 * things it doesn't understand...
	 */
	__le32	s_first_ino;		/* First non-reserved inode */
1246
	__le16  s_inode_size;		/* size of inode structure */
1247 1248 1249 1250 1251 1252 1253 1254 1255 1256
	__le16	s_block_group_nr;	/* block group # of this superblock */
	__le32	s_feature_compat;	/* compatible feature set */
/*60*/	__le32	s_feature_incompat;	/* incompatible feature set */
	__le32	s_feature_ro_compat;	/* readonly-compatible feature set */
/*68*/	__u8	s_uuid[16];		/* 128-bit uuid for volume */
/*78*/	char	s_volume_name[16];	/* volume name */
/*88*/	char	s_last_mounted[64];	/* directory where last mounted */
/*C8*/	__le32	s_algorithm_usage_bitmap; /* For compression */
	/*
	 * Performance hints.  Directory preallocation should only
1257
	 * happen if the EXT4_FEATURE_COMPAT_DIR_PREALLOC flag is on.
1258 1259 1260 1261 1262
	 */
	__u8	s_prealloc_blocks;	/* Nr of blocks to try to preallocate*/
	__u8	s_prealloc_dir_blocks;	/* Nr to preallocate for dirs */
	__le16	s_reserved_gdt_blocks;	/* Per group desc for online growth */
	/*
1263
	 * Journaling support valid if EXT4_FEATURE_COMPAT_HAS_JOURNAL set.
1264 1265 1266 1267 1268 1269 1270
	 */
/*D0*/	__u8	s_journal_uuid[16];	/* uuid of journal superblock */
/*E0*/	__le32	s_journal_inum;		/* inode number of journal file */
	__le32	s_journal_dev;		/* device number of journal file */
	__le32	s_last_orphan;		/* start of list of inodes to delete */
	__le32	s_hash_seed[4];		/* HTREE hash seed */
	__u8	s_def_hash_version;	/* Default hash version to use */
1271
	__u8	s_jnl_backup_type;
1272
	__le16  s_desc_size;		/* size of group descriptor */
L
Laurent Vivier 已提交
1273
/*100*/	__le32	s_default_mount_opts;
1274
	__le32	s_first_meta_bg;	/* First metablock block group */
L
Laurent Vivier 已提交
1275 1276 1277 1278 1279 1280
	__le32	s_mkfs_time;		/* When the filesystem was created */
	__le32	s_jnl_blocks[17];	/* Backup of the journal inode */
	/* 64bit support valid if EXT4_FEATURE_COMPAT_64BIT */
/*150*/	__le32	s_blocks_count_hi;	/* Blocks count */
	__le32	s_r_blocks_count_hi;	/* Reserved blocks count */
	__le32	s_free_blocks_count_hi;	/* Free blocks count */
A
Aneesh Kumar K.V 已提交
1281 1282 1283 1284
	__le16	s_min_extra_isize;	/* All inodes have at least # bytes */
	__le16	s_want_extra_isize; 	/* New inodes should reserve # bytes */
	__le32	s_flags;		/* Miscellaneous flags */
	__le16  s_raid_stride;		/* RAID stride */
1285
	__le16  s_mmp_update_interval;  /* # seconds to wait in MMP checking */
A
Aneesh Kumar K.V 已提交
1286 1287
	__le64  s_mmp_block;            /* Block for multi-mount protection */
	__le32  s_raid_stripe_width;    /* blocks on all data disks (N*stride)*/
1288
	__u8	s_log_groups_per_flex;  /* FLEX_BG group size */
1289
	__u8	s_checksum_type;	/* metadata checksum algorithm used */
1290 1291
	__u8	s_encryption_level;	/* versioning level for encryption */
	__u8	s_reserved_pad;		/* Padding to next 32bits */
T
Theodore Ts'o 已提交
1292
	__le64	s_kbytes_written;	/* nr of lifetime kilobytes written */
1293 1294 1295 1296 1297 1298
	__le32	s_snapshot_inum;	/* Inode number of active snapshot */
	__le32	s_snapshot_id;		/* sequential ID of active snapshot */
	__le64	s_snapshot_r_blocks_count; /* reserved blocks for active
					      snapshot's future use */
	__le32	s_snapshot_list;	/* inode number of the head of the
					   on-disk snapshot list */
1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310
#define EXT4_S_ERR_START offsetof(struct ext4_super_block, s_error_count)
	__le32	s_error_count;		/* number of fs errors */
	__le32	s_first_error_time;	/* first time an error happened */
	__le32	s_first_error_ino;	/* inode involved in first error */
	__le64	s_first_error_block;	/* block involved of first error */
	__u8	s_first_error_func[32];	/* function where the error happened */
	__le32	s_first_error_line;	/* line number where error happened */
	__le32	s_last_error_time;	/* most recent time of an error */
	__le32	s_last_error_ino;	/* inode involved in last error */
	__le32	s_last_error_line;	/* line number where error happened */
	__le64	s_last_error_block;	/* block involved of last error */
	__u8	s_last_error_func[32];	/* function where the error happened */
1311 1312
#define EXT4_S_ERR_END offsetof(struct ext4_super_block, s_mount_opts)
	__u8	s_mount_opts[64];
1313 1314 1315
	__le32	s_usr_quota_inum;	/* inode for tracking user quota */
	__le32	s_grp_quota_inum;	/* inode for tracking group quota */
	__le32	s_overhead_clusters;	/* overhead blocks/clusters in fs */
1316
	__le32	s_backup_bgs[2];	/* groups with sparse_super2 SBs */
1317
	__u8	s_encrypt_algos[4];	/* Encryption algorithms in use  */
1318 1319
	__u8	s_encrypt_pw_salt[16];	/* Salt used for string2key algorithm */
	__le32	s_lpf_ino;		/* Location of the lost+found inode */
1320
	__le32	s_prj_quota_inum;	/* inode for tracking project quota */
1321 1322
	__le32	s_checksum_seed;	/* crc32c(uuid) if csum_seed set */
	__le32	s_reserved[98];		/* Padding to the end of the block */
1323
	__le32	s_checksum;		/* crc32c(superblock) */
1324 1325
};

1326 1327
#define EXT4_S_ERR_LEN (EXT4_S_ERR_END - EXT4_S_ERR_START)

1328
#ifdef __KERNEL__
1329 1330

/*
1331
 * run-time mount flags
1332
 */
1333 1334 1335 1336 1337 1338 1339 1340 1341 1342
#define EXT4_MF_MNTDIR_SAMPLED		0x0001
#define EXT4_MF_FS_ABORTED		0x0002	/* Fatal error detected */
#define EXT4_MF_TEST_DUMMY_ENCRYPTION	0x0004

#ifdef CONFIG_EXT4_FS_ENCRYPTION
#define DUMMY_ENCRYPTION_ENABLED(sbi) (unlikely((sbi)->s_mount_flags & \
						EXT4_MF_TEST_DUMMY_ENCRYPTION))
#else
#define DUMMY_ENCRYPTION_ENABLED(sbi) (0)
#endif
1343

J
Jan Kara 已提交
1344
/* Number of quota types we support */
L
Li Xi 已提交
1345
#define EXT4_MAXQUOTAS 3
J
Jan Kara 已提交
1346

1347 1348 1349 1350 1351 1352 1353
/*
 * fourth extended-fs super-block data in memory
 */
struct ext4_sb_info {
	unsigned long s_desc_size;	/* Size of a group descriptor in bytes */
	unsigned long s_inodes_per_block;/* Number of inodes per block */
	unsigned long s_blocks_per_group;/* Number of blocks in a group */
1354
	unsigned long s_clusters_per_group; /* Number of clusters in a group */
1355 1356 1357 1358 1359
	unsigned long s_inodes_per_group;/* Number of inodes in a group */
	unsigned long s_itb_per_group;	/* Number of inode table blocks per group */
	unsigned long s_gdb_count;	/* Number of group descriptor blocks */
	unsigned long s_desc_per_block;	/* Number of group descriptors per block */
	ext4_group_t s_groups_count;	/* Number of groups in the fs */
1360
	ext4_group_t s_blockfile_groups;/* Groups acceptable for non-extent files */
1361
	unsigned long s_overhead;  /* # of fs overhead clusters */
1362 1363
	unsigned int s_cluster_ratio;	/* Number of blocks per cluster */
	unsigned int s_cluster_bits;	/* log2 of s_cluster_ratio */
1364 1365 1366 1367
	loff_t s_bitmap_maxbytes;	/* max bytes for bitmap files */
	struct buffer_head * s_sbh;	/* Buffer containing the super block */
	struct ext4_super_block *s_es;	/* Pointer to the super block in the buffer */
	struct buffer_head **s_group_desc;
1368
	unsigned int s_mount_opt;
1369
	unsigned int s_mount_opt2;
1370
	unsigned int s_mount_flags;
1371
	unsigned int s_def_mount_opt;
1372
	ext4_fsblk_t s_sb_block;
L
Lukas Czerner 已提交
1373
	atomic64_t s_resv_clusters;
1374 1375
	kuid_t s_resuid;
	kgid_t s_resgid;
1376 1377 1378 1379 1380 1381 1382
	unsigned short s_mount_state;
	unsigned short s_pad;
	int s_addr_per_block_bits;
	int s_desc_per_block_bits;
	int s_inode_size;
	int s_first_ino;
	unsigned int s_inode_readahead_blks;
1383
	unsigned int s_inode_goal;
1384 1385 1386 1387 1388
	spinlock_t s_next_gen_lock;
	u32 s_next_generation;
	u32 s_hash_seed[4];
	int s_def_hash_version;
	int s_hash_unsigned;	/* 3 if hash should be signed, 0 if not */
1389
	struct percpu_counter s_freeclusters_counter;
1390 1391
	struct percpu_counter s_freeinodes_counter;
	struct percpu_counter s_dirs_counter;
1392
	struct percpu_counter s_dirtyclusters_counter;
1393 1394 1395 1396
	struct blockgroup_lock *s_blockgroup_lock;
	struct proc_dir_entry *s_proc;
	struct kobject s_kobj;
	struct completion s_kobj_unregister;
1397
	struct super_block *s_sb;
1398 1399 1400 1401 1402

	/* Journaling */
	struct journal_s *s_journal;
	struct list_head s_orphan;
	struct mutex s_orphan_lock;
1403 1404
	unsigned long s_resize_flags;		/* Flags indicating if there
						   is a resizer */
1405 1406 1407 1408 1409
	unsigned long s_commit_interval;
	u32 s_max_batch_time;
	u32 s_min_batch_time;
	struct block_device *journal_bdev;
#ifdef CONFIG_QUOTA
J
Jan Kara 已提交
1410
	char *s_qf_names[EXT4_MAXQUOTAS];	/* Names of quota files with journalled quota */
1411 1412 1413
	int s_jquota_fmt;			/* Format of quota to use */
#endif
	unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */
1414
	struct rb_root system_blks;
1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431

#ifdef EXTENTS_STATS
	/* ext4 extents stats */
	unsigned long s_ext_min;
	unsigned long s_ext_max;
	unsigned long s_depth_max;
	spinlock_t s_ext_stats_lock;
	unsigned long s_ext_blocks;
	unsigned long s_ext_extents;
#endif

	/* for buddy allocator */
	struct ext4_group_info ***s_group_info;
	struct inode *s_buddy_cache;
	spinlock_t s_md_lock;
	unsigned short *s_mb_offsets;
	unsigned int *s_mb_maxs;
1432
	unsigned int s_group_info_size;
1433
	unsigned int s_mb_free_pending;
1434 1435 1436 1437 1438 1439 1440 1441 1442

	/* tunables */
	unsigned long s_stripe;
	unsigned int s_mb_stream_request;
	unsigned int s_mb_max_to_scan;
	unsigned int s_mb_min_to_scan;
	unsigned int s_mb_stats;
	unsigned int s_mb_order2_reqs;
	unsigned int s_mb_group_prealloc;
1443
	unsigned int s_max_dir_size_kb;
1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461
	/* where last allocation was done - for stream allocation */
	unsigned long s_mb_last_group;
	unsigned long s_mb_last_start;

	/* stats for buddy allocator */
	atomic_t s_bal_reqs;	/* number of reqs with len > 1 */
	atomic_t s_bal_success;	/* we found long enough chunks */
	atomic_t s_bal_allocated;	/* in blocks */
	atomic_t s_bal_ex_scanned;	/* total extents scanned */
	atomic_t s_bal_goals;	/* goal hits */
	atomic_t s_bal_breaks;	/* too long searches */
	atomic_t s_bal_2orders;	/* 2^order hits */
	spinlock_t s_bal_lock;
	unsigned long s_mb_buddies_generated;
	unsigned long long s_mb_generation_time;
	atomic_t s_mb_lost_chunks;
	atomic_t s_mb_preallocated;
	atomic_t s_mb_discarded;
1462
	atomic_t s_lock_busy;
1463 1464

	/* locality groups */
1465
	struct ext4_locality_group __percpu *s_locality_groups;
1466 1467 1468 1469 1470

	/* for write statistics */
	unsigned long s_sectors_written_start;
	u64 s_kbytes_written;

1471 1472 1473
	/* the size of zero-out chunk */
	unsigned int s_extent_max_zeroout_kb;

1474 1475
	unsigned int s_log_groups_per_flex;
	struct flex_groups *s_flex_groups;
1476
	ext4_group_t s_flex_groups_allocated;
1477

1478 1479
	/* workqueue for reserved extent conversions (buffered io) */
	struct workqueue_struct *rsv_conversion_wq;
1480 1481 1482

	/* timer for periodic error stats printing */
	struct timer_list s_err_report;
1483 1484 1485 1486 1487

	/* Lazy inode table initialization info */
	struct ext4_li_request *s_li_request;
	/* Wait multiplier for lazy initialization thread */
	unsigned int s_li_wait_mult;
1488 1489 1490

	/* Kernel thread for multiple mount protection */
	struct task_struct *s_mmp_tsk;
1491 1492 1493

	/* record the last minlen when FITRIM is called. */
	atomic_t s_last_trim_minblks;
1494 1495 1496

	/* Reference to checksum algorithm driver via cryptoapi */
	struct crypto_shash *s_chksum_driver;
1497 1498 1499

	/* Precomputed FS UUID checksum for seeding other checksums */
	__u32 s_csum_seed;
1500 1501 1502

	/* Reclaim extents from extent status tree */
	struct shrinker s_es_shrinker;
1503
	struct list_head s_es_list;	/* List of inodes with reclaimable extents */
1504
	long s_es_nr_inode;
1505
	struct ext4_es_stats s_es_stats;
J
Jan Kara 已提交
1506
	struct mb_cache *s_mb_cache;
1507
	spinlock_t s_es_lock ____cacheline_aligned_in_smp;
1508 1509 1510 1511 1512

	/* Ratelimit ext4 messages. */
	struct ratelimit_state s_err_ratelimit_state;
	struct ratelimit_state s_warning_ratelimit_state;
	struct ratelimit_state s_msg_ratelimit_state;
1513 1514 1515

	/* Barrier between changing inodes' journal flags and writepages ops. */
	struct percpu_rw_semaphore s_journal_flag_rwsem;
1516 1517
};

1518
static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
1519 1520 1521
{
	return sb->s_fs_info;
}
1522
static inline struct ext4_inode_info *EXT4_I(struct inode *inode)
1523
{
1524
	return container_of(inode, struct ext4_inode_info, vfs_inode);
1525 1526
}

K
Kalpak Shah 已提交
1527 1528 1529 1530 1531 1532
static inline struct timespec ext4_current_time(struct inode *inode)
{
	return (inode->i_sb->s_time_gran < NSEC_PER_SEC) ?
		current_fs_time(inode->i_sb) : CURRENT_TIME_SEC;
}

1533
static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
1534
{
1535
	return ino == EXT4_ROOT_INO ||
1536 1537
		ino == EXT4_USR_QUOTA_INO ||
		ino == EXT4_GRP_QUOTA_INO ||
1538
		ino == EXT4_BOOT_LOADER_INO ||
1539 1540 1541 1542
		ino == EXT4_JOURNAL_INO ||
		ino == EXT4_RESIZE_INO ||
		(ino >= EXT4_FIRST_INO(sb) &&
		 ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
1543
}
1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555

/*
 * Inode dynamic state flags
 */
enum {
	EXT4_STATE_JDATA,		/* journaled data exists */
	EXT4_STATE_NEW,			/* inode is newly created */
	EXT4_STATE_XATTR,		/* has in-inode xattrs */
	EXT4_STATE_NO_EXPAND,		/* No space for expansion */
	EXT4_STATE_DA_ALLOC_CLOSE,	/* Alloc DA blks on close */
	EXT4_STATE_EXT_MIGRATE,		/* Inode is migrating */
	EXT4_STATE_DIO_UNWRITTEN,	/* need convert on dio done*/
1556
	EXT4_STATE_NEWENTRY,		/* File just added to dir */
1557 1558
	EXT4_STATE_DIOREAD_LOCK,	/* Disable support for dio read
					   nolocking */
1559
	EXT4_STATE_MAY_INLINE_DATA,	/* may have in-inode data */
1560
	EXT4_STATE_EXT_PRECACHED,	/* extents have been precached */
1561 1562
};

1563
#define EXT4_INODE_BIT_FNS(name, field, offset)				\
1564 1565
static inline int ext4_test_inode_##name(struct inode *inode, int bit)	\
{									\
1566
	return test_bit(bit + (offset), &EXT4_I(inode)->i_##field);	\
1567 1568 1569
}									\
static inline void ext4_set_inode_##name(struct inode *inode, int bit)	\
{									\
1570
	set_bit(bit + (offset), &EXT4_I(inode)->i_##field);		\
1571 1572 1573
}									\
static inline void ext4_clear_inode_##name(struct inode *inode, int bit) \
{									\
1574
	clear_bit(bit + (offset), &EXT4_I(inode)->i_##field);		\
1575 1576
}

1577 1578 1579 1580 1581
/* Add these declarations here only so that these functions can be
 * found by name.  Otherwise, they are very hard to locate. */
static inline int ext4_test_inode_flag(struct inode *inode, int bit);
static inline void ext4_set_inode_flag(struct inode *inode, int bit);
static inline void ext4_clear_inode_flag(struct inode *inode, int bit);
1582
EXT4_INODE_BIT_FNS(flag, flags, 0)
1583 1584 1585 1586 1587 1588

/* Add these declarations here only so that these functions can be
 * found by name.  Otherwise, they are very hard to locate. */
static inline int ext4_test_inode_state(struct inode *inode, int bit);
static inline void ext4_set_inode_state(struct inode *inode, int bit);
static inline void ext4_clear_inode_state(struct inode *inode, int bit);
1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603
#if (BITS_PER_LONG < 64)
EXT4_INODE_BIT_FNS(state, state_flags, 0)

static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
{
	(ei)->i_state_flags = 0;
}
#else
EXT4_INODE_BIT_FNS(state, flags, 32)

static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
{
	/* We depend on the fact that callers will set i_flags */
}
#endif
1604
#else
1605
/* Assume that user mode programs are passing in an ext4fs superblock, not
1606 1607
 * a kernel struct super_block.  This will allow us to call the feature-test
 * macros from user land. */
1608
#define EXT4_SB(sb)	(sb)
1609 1610
#endif

1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622
/*
 * Returns true if the inode is inode is encrypted
 */
static inline int ext4_encrypted_inode(struct inode *inode)
{
#ifdef CONFIG_EXT4_FS_ENCRYPTION
	return ext4_test_inode_flag(inode, EXT4_INODE_ENCRYPT);
#else
	return 0;
#endif
}

1623
#define NEXT_ORPHAN(inode) EXT4_I(inode)->i_dtime
1624 1625 1626 1627

/*
 * Codes for operating systems
 */
1628 1629 1630 1631 1632
#define EXT4_OS_LINUX		0
#define EXT4_OS_HURD		1
#define EXT4_OS_MASIX		2
#define EXT4_OS_FREEBSD		3
#define EXT4_OS_LITES		4
1633 1634 1635 1636

/*
 * Revision levels
 */
1637 1638
#define EXT4_GOOD_OLD_REV	0	/* The good old (original) format */
#define EXT4_DYNAMIC_REV	1	/* V2 format w/ dynamic inode sizes */
1639

1640 1641
#define EXT4_CURRENT_REV	EXT4_GOOD_OLD_REV
#define EXT4_MAX_SUPP_REV	EXT4_DYNAMIC_REV
1642

1643
#define EXT4_GOOD_OLD_INODE_SIZE 128
1644 1645 1646 1647 1648

/*
 * Feature set definitions
 */

1649
/* Use the ext4_{has,set,clear}_feature_* helpers; these will be removed */
1650
#define EXT4_HAS_COMPAT_FEATURE(sb,mask)			\
A
Aneesh Kumar K.V 已提交
1651
	((EXT4_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask)) != 0)
1652
#define EXT4_HAS_RO_COMPAT_FEATURE(sb,mask)			\
A
Aneesh Kumar K.V 已提交
1653
	((EXT4_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask)) != 0)
1654
#define EXT4_HAS_INCOMPAT_FEATURE(sb,mask)			\
A
Aneesh Kumar K.V 已提交
1655
	((EXT4_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask)) != 0)
1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674
#define EXT4_SET_COMPAT_FEATURE(sb,mask)			\
	EXT4_SB(sb)->s_es->s_feature_compat |= cpu_to_le32(mask)
#define EXT4_SET_RO_COMPAT_FEATURE(sb,mask)			\
	EXT4_SB(sb)->s_es->s_feature_ro_compat |= cpu_to_le32(mask)
#define EXT4_SET_INCOMPAT_FEATURE(sb,mask)			\
	EXT4_SB(sb)->s_es->s_feature_incompat |= cpu_to_le32(mask)
#define EXT4_CLEAR_COMPAT_FEATURE(sb,mask)			\
	EXT4_SB(sb)->s_es->s_feature_compat &= ~cpu_to_le32(mask)
#define EXT4_CLEAR_RO_COMPAT_FEATURE(sb,mask)			\
	EXT4_SB(sb)->s_es->s_feature_ro_compat &= ~cpu_to_le32(mask)
#define EXT4_CLEAR_INCOMPAT_FEATURE(sb,mask)			\
	EXT4_SB(sb)->s_es->s_feature_incompat &= ~cpu_to_le32(mask)

#define EXT4_FEATURE_COMPAT_DIR_PREALLOC	0x0001
#define EXT4_FEATURE_COMPAT_IMAGIC_INODES	0x0002
#define EXT4_FEATURE_COMPAT_HAS_JOURNAL		0x0004
#define EXT4_FEATURE_COMPAT_EXT_ATTR		0x0008
#define EXT4_FEATURE_COMPAT_RESIZE_INODE	0x0010
#define EXT4_FEATURE_COMPAT_DIR_INDEX		0x0020
1675
#define EXT4_FEATURE_COMPAT_SPARSE_SUPER2	0x0200
1676 1677 1678 1679

#define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER	0x0001
#define EXT4_FEATURE_RO_COMPAT_LARGE_FILE	0x0002
#define EXT4_FEATURE_RO_COMPAT_BTREE_DIR	0x0004
1680
#define EXT4_FEATURE_RO_COMPAT_HUGE_FILE        0x0008
A
Andreas Dilger 已提交
1681
#define EXT4_FEATURE_RO_COMPAT_GDT_CSUM		0x0010
1682
#define EXT4_FEATURE_RO_COMPAT_DIR_NLINK	0x0020
K
Kalpak Shah 已提交
1683
#define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE	0x0040
1684
#define EXT4_FEATURE_RO_COMPAT_QUOTA		0x0100
1685
#define EXT4_FEATURE_RO_COMPAT_BIGALLOC		0x0200
1686 1687 1688 1689 1690 1691
/*
 * METADATA_CSUM also enables group descriptor checksums (GDT_CSUM).  When
 * METADATA_CSUM is set, group descriptor checksums use the same algorithm as
 * all other data structures' checksums.  However, the METADATA_CSUM and
 * GDT_CSUM bits are mutually exclusive.
 */
1692
#define EXT4_FEATURE_RO_COMPAT_METADATA_CSUM	0x0400
D
Darrick J. Wong 已提交
1693
#define EXT4_FEATURE_RO_COMPAT_READONLY		0x1000
1694
#define EXT4_FEATURE_RO_COMPAT_PROJECT		0x2000
1695 1696 1697 1698 1699 1700

#define EXT4_FEATURE_INCOMPAT_COMPRESSION	0x0001
#define EXT4_FEATURE_INCOMPAT_FILETYPE		0x0002
#define EXT4_FEATURE_INCOMPAT_RECOVER		0x0004 /* Needs recovery */
#define EXT4_FEATURE_INCOMPAT_JOURNAL_DEV	0x0008 /* Journal device */
#define EXT4_FEATURE_INCOMPAT_META_BG		0x0010
A
Alex Tomas 已提交
1701
#define EXT4_FEATURE_INCOMPAT_EXTENTS		0x0040 /* extents support */
L
Laurent Vivier 已提交
1702
#define EXT4_FEATURE_INCOMPAT_64BIT		0x0080
1703
#define EXT4_FEATURE_INCOMPAT_MMP               0x0100
J
Jose R. Santos 已提交
1704
#define EXT4_FEATURE_INCOMPAT_FLEX_BG		0x0200
1705 1706
#define EXT4_FEATURE_INCOMPAT_EA_INODE		0x0400 /* EA in inode */
#define EXT4_FEATURE_INCOMPAT_DIRDATA		0x1000 /* data in dirent */
1707
#define EXT4_FEATURE_INCOMPAT_CSUM_SEED		0x2000
1708
#define EXT4_FEATURE_INCOMPAT_LARGEDIR		0x4000 /* >2GB or 3-lvl htree */
1709
#define EXT4_FEATURE_INCOMPAT_INLINE_DATA	0x8000 /* data in inode */
1710
#define EXT4_FEATURE_INCOMPAT_ENCRYPT		0x10000
1711

1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799
#define EXT4_FEATURE_COMPAT_FUNCS(name, flagname) \
static inline bool ext4_has_feature_##name(struct super_block *sb) \
{ \
	return ((EXT4_SB(sb)->s_es->s_feature_compat & \
		cpu_to_le32(EXT4_FEATURE_COMPAT_##flagname)) != 0); \
} \
static inline void ext4_set_feature_##name(struct super_block *sb) \
{ \
	EXT4_SB(sb)->s_es->s_feature_compat |= \
		cpu_to_le32(EXT4_FEATURE_COMPAT_##flagname); \
} \
static inline void ext4_clear_feature_##name(struct super_block *sb) \
{ \
	EXT4_SB(sb)->s_es->s_feature_compat &= \
		~cpu_to_le32(EXT4_FEATURE_COMPAT_##flagname); \
}

#define EXT4_FEATURE_RO_COMPAT_FUNCS(name, flagname) \
static inline bool ext4_has_feature_##name(struct super_block *sb) \
{ \
	return ((EXT4_SB(sb)->s_es->s_feature_ro_compat & \
		cpu_to_le32(EXT4_FEATURE_RO_COMPAT_##flagname)) != 0); \
} \
static inline void ext4_set_feature_##name(struct super_block *sb) \
{ \
	EXT4_SB(sb)->s_es->s_feature_ro_compat |= \
		cpu_to_le32(EXT4_FEATURE_RO_COMPAT_##flagname); \
} \
static inline void ext4_clear_feature_##name(struct super_block *sb) \
{ \
	EXT4_SB(sb)->s_es->s_feature_ro_compat &= \
		~cpu_to_le32(EXT4_FEATURE_RO_COMPAT_##flagname); \
}

#define EXT4_FEATURE_INCOMPAT_FUNCS(name, flagname) \
static inline bool ext4_has_feature_##name(struct super_block *sb) \
{ \
	return ((EXT4_SB(sb)->s_es->s_feature_incompat & \
		cpu_to_le32(EXT4_FEATURE_INCOMPAT_##flagname)) != 0); \
} \
static inline void ext4_set_feature_##name(struct super_block *sb) \
{ \
	EXT4_SB(sb)->s_es->s_feature_incompat |= \
		cpu_to_le32(EXT4_FEATURE_INCOMPAT_##flagname); \
} \
static inline void ext4_clear_feature_##name(struct super_block *sb) \
{ \
	EXT4_SB(sb)->s_es->s_feature_incompat &= \
		~cpu_to_le32(EXT4_FEATURE_INCOMPAT_##flagname); \
}

EXT4_FEATURE_COMPAT_FUNCS(dir_prealloc,		DIR_PREALLOC)
EXT4_FEATURE_COMPAT_FUNCS(imagic_inodes,	IMAGIC_INODES)
EXT4_FEATURE_COMPAT_FUNCS(journal,		HAS_JOURNAL)
EXT4_FEATURE_COMPAT_FUNCS(xattr,		EXT_ATTR)
EXT4_FEATURE_COMPAT_FUNCS(resize_inode,		RESIZE_INODE)
EXT4_FEATURE_COMPAT_FUNCS(dir_index,		DIR_INDEX)
EXT4_FEATURE_COMPAT_FUNCS(sparse_super2,	SPARSE_SUPER2)

EXT4_FEATURE_RO_COMPAT_FUNCS(sparse_super,	SPARSE_SUPER)
EXT4_FEATURE_RO_COMPAT_FUNCS(large_file,	LARGE_FILE)
EXT4_FEATURE_RO_COMPAT_FUNCS(btree_dir,		BTREE_DIR)
EXT4_FEATURE_RO_COMPAT_FUNCS(huge_file,		HUGE_FILE)
EXT4_FEATURE_RO_COMPAT_FUNCS(gdt_csum,		GDT_CSUM)
EXT4_FEATURE_RO_COMPAT_FUNCS(dir_nlink,		DIR_NLINK)
EXT4_FEATURE_RO_COMPAT_FUNCS(extra_isize,	EXTRA_ISIZE)
EXT4_FEATURE_RO_COMPAT_FUNCS(quota,		QUOTA)
EXT4_FEATURE_RO_COMPAT_FUNCS(bigalloc,		BIGALLOC)
EXT4_FEATURE_RO_COMPAT_FUNCS(metadata_csum,	METADATA_CSUM)
EXT4_FEATURE_RO_COMPAT_FUNCS(readonly,		READONLY)
EXT4_FEATURE_RO_COMPAT_FUNCS(project,		PROJECT)

EXT4_FEATURE_INCOMPAT_FUNCS(compression,	COMPRESSION)
EXT4_FEATURE_INCOMPAT_FUNCS(filetype,		FILETYPE)
EXT4_FEATURE_INCOMPAT_FUNCS(journal_needs_recovery,	RECOVER)
EXT4_FEATURE_INCOMPAT_FUNCS(journal_dev,	JOURNAL_DEV)
EXT4_FEATURE_INCOMPAT_FUNCS(meta_bg,		META_BG)
EXT4_FEATURE_INCOMPAT_FUNCS(extents,		EXTENTS)
EXT4_FEATURE_INCOMPAT_FUNCS(64bit,		64BIT)
EXT4_FEATURE_INCOMPAT_FUNCS(mmp,		MMP)
EXT4_FEATURE_INCOMPAT_FUNCS(flex_bg,		FLEX_BG)
EXT4_FEATURE_INCOMPAT_FUNCS(ea_inode,		EA_INODE)
EXT4_FEATURE_INCOMPAT_FUNCS(dirdata,		DIRDATA)
EXT4_FEATURE_INCOMPAT_FUNCS(csum_seed,		CSUM_SEED)
EXT4_FEATURE_INCOMPAT_FUNCS(largedir,		LARGEDIR)
EXT4_FEATURE_INCOMPAT_FUNCS(inline_data,	INLINE_DATA)
EXT4_FEATURE_INCOMPAT_FUNCS(encrypt,		ENCRYPT)

1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814
#define EXT2_FEATURE_COMPAT_SUPP	EXT4_FEATURE_COMPAT_EXT_ATTR
#define EXT2_FEATURE_INCOMPAT_SUPP	(EXT4_FEATURE_INCOMPAT_FILETYPE| \
					 EXT4_FEATURE_INCOMPAT_META_BG)
#define EXT2_FEATURE_RO_COMPAT_SUPP	(EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
					 EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \
					 EXT4_FEATURE_RO_COMPAT_BTREE_DIR)

#define EXT3_FEATURE_COMPAT_SUPP	EXT4_FEATURE_COMPAT_EXT_ATTR
#define EXT3_FEATURE_INCOMPAT_SUPP	(EXT4_FEATURE_INCOMPAT_FILETYPE| \
					 EXT4_FEATURE_INCOMPAT_RECOVER| \
					 EXT4_FEATURE_INCOMPAT_META_BG)
#define EXT3_FEATURE_RO_COMPAT_SUPP	(EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
					 EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \
					 EXT4_FEATURE_RO_COMPAT_BTREE_DIR)

1815
#define EXT4_FEATURE_COMPAT_SUPP	EXT4_FEATURE_COMPAT_EXT_ATTR
1816 1817
#define EXT4_FEATURE_INCOMPAT_SUPP	(EXT4_FEATURE_INCOMPAT_FILETYPE| \
					 EXT4_FEATURE_INCOMPAT_RECOVER| \
A
Alex Tomas 已提交
1818
					 EXT4_FEATURE_INCOMPAT_META_BG| \
L
Laurent Vivier 已提交
1819
					 EXT4_FEATURE_INCOMPAT_EXTENTS| \
J
Jose R. Santos 已提交
1820
					 EXT4_FEATURE_INCOMPAT_64BIT| \
1821
					 EXT4_FEATURE_INCOMPAT_FLEX_BG| \
1822 1823
					 EXT4_FEATURE_INCOMPAT_MMP | \
					 EXT4_FEATURE_INCOMPAT_INLINE_DATA | \
1824 1825
					 EXT4_FEATURE_INCOMPAT_ENCRYPT | \
					 EXT4_FEATURE_INCOMPAT_CSUM_SEED)
1826 1827
#define EXT4_FEATURE_RO_COMPAT_SUPP	(EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
					 EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \
A
Andreas Dilger 已提交
1828
					 EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \
1829
					 EXT4_FEATURE_RO_COMPAT_DIR_NLINK | \
K
Kalpak Shah 已提交
1830
					 EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \
1831
					 EXT4_FEATURE_RO_COMPAT_BTREE_DIR |\
1832
					 EXT4_FEATURE_RO_COMPAT_HUGE_FILE |\
1833
					 EXT4_FEATURE_RO_COMPAT_BIGALLOC |\
1834
					 EXT4_FEATURE_RO_COMPAT_METADATA_CSUM|\
L
Li Xi 已提交
1835 1836
					 EXT4_FEATURE_RO_COMPAT_QUOTA |\
					 EXT4_FEATURE_RO_COMPAT_PROJECT)
1837

1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871
#define EXTN_FEATURE_FUNCS(ver) \
static inline bool ext4_has_unknown_ext##ver##_compat_features(struct super_block *sb) \
{ \
	return ((EXT4_SB(sb)->s_es->s_feature_compat & \
		cpu_to_le32(~EXT##ver##_FEATURE_COMPAT_SUPP)) != 0); \
} \
static inline bool ext4_has_unknown_ext##ver##_ro_compat_features(struct super_block *sb) \
{ \
	return ((EXT4_SB(sb)->s_es->s_feature_ro_compat & \
		cpu_to_le32(~EXT##ver##_FEATURE_RO_COMPAT_SUPP)) != 0); \
} \
static inline bool ext4_has_unknown_ext##ver##_incompat_features(struct super_block *sb) \
{ \
	return ((EXT4_SB(sb)->s_es->s_feature_incompat & \
		cpu_to_le32(~EXT##ver##_FEATURE_INCOMPAT_SUPP)) != 0); \
}

EXTN_FEATURE_FUNCS(2)
EXTN_FEATURE_FUNCS(3)
EXTN_FEATURE_FUNCS(4)

static inline bool ext4_has_compat_features(struct super_block *sb)
{
	return (EXT4_SB(sb)->s_es->s_feature_compat != 0);
}
static inline bool ext4_has_ro_compat_features(struct super_block *sb)
{
	return (EXT4_SB(sb)->s_es->s_feature_ro_compat != 0);
}
static inline bool ext4_has_incompat_features(struct super_block *sb)
{
	return (EXT4_SB(sb)->s_es->s_feature_incompat != 0);
}

1872 1873 1874
/*
 * Default values for user and/or group using reserved blocks
 */
1875 1876
#define	EXT4_DEF_RESUID		0
#define	EXT4_DEF_RESGID		0
1877

L
Li Xi 已提交
1878 1879 1880 1881 1882
/*
 * Default project ID
 */
#define	EXT4_DEF_PROJID		0

1883 1884
#define EXT4_DEF_INODE_READAHEAD_BLKS	32

1885 1886 1887
/*
 * Default mount options
 */
1888 1889 1890 1891 1892 1893 1894 1895 1896
#define EXT4_DEFM_DEBUG		0x0001
#define EXT4_DEFM_BSDGROUPS	0x0002
#define EXT4_DEFM_XATTR_USER	0x0004
#define EXT4_DEFM_ACL		0x0008
#define EXT4_DEFM_UID16		0x0010
#define EXT4_DEFM_JMODE		0x0060
#define EXT4_DEFM_JMODE_DATA	0x0020
#define EXT4_DEFM_JMODE_ORDERED	0x0040
#define EXT4_DEFM_JMODE_WBACK	0x0060
1897 1898 1899 1900
#define EXT4_DEFM_NOBARRIER	0x0100
#define EXT4_DEFM_BLOCK_VALIDITY 0x0200
#define EXT4_DEFM_DISCARD	0x0400
#define EXT4_DEFM_NODELALLOC	0x0800
1901

1902 1903 1904 1905 1906 1907
/*
 * Default journal batch times
 */
#define EXT4_DEF_MIN_BATCH_TIME	0
#define EXT4_DEF_MAX_BATCH_TIME	15000 /* 15ms */

1908 1909 1910 1911 1912 1913
/*
 * Minimum number of groups in a flexgroup before we separate out
 * directories into the first block group of a flexgroup
 */
#define EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME	4

1914 1915 1916
/*
 * Structure of a directory entry
 */
1917
#define EXT4_NAME_LEN 255
1918

1919
struct ext4_dir_entry {
1920 1921 1922
	__le32	inode;			/* Inode number */
	__le16	rec_len;		/* Directory entry length */
	__le16	name_len;		/* Name length */
1923
	char	name[EXT4_NAME_LEN];	/* File name */
1924 1925 1926
};

/*
1927
 * The new version of the directory entry.  Since EXT4 structures are
1928 1929 1930 1931
 * stored in intel byte order, and the name_len field could never be
 * bigger than 255 chars, it's safe to reclaim the extra byte for the
 * file_type field.
 */
1932
struct ext4_dir_entry_2 {
1933 1934 1935 1936
	__le32	inode;			/* Inode number */
	__le16	rec_len;		/* Directory entry length */
	__u8	name_len;		/* Name length */
	__u8	file_type;
1937
	char	name[EXT4_NAME_LEN];	/* File name */
1938 1939
};

1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951
/*
 * This is a bogus directory entry at the end of each leaf block that
 * records checksums.
 */
struct ext4_dir_entry_tail {
	__le32	det_reserved_zero1;	/* Pretend to be unused */
	__le16	det_rec_len;		/* 12 */
	__u8	det_reserved_zero2;	/* Zero name length */
	__u8	det_reserved_ft;	/* 0xDE, fake file type */
	__le32	det_checksum;		/* crc32c(uuid+inum+dirblock) */
};

1952 1953 1954 1955 1956
#define EXT4_DIRENT_TAIL(block, blocksize) \
	((struct ext4_dir_entry_tail *)(((void *)(block)) + \
					((blocksize) - \
					 sizeof(struct ext4_dir_entry_tail))))

1957
/*
1958
 * Ext4 directory file types.  Only the low 3 bits are used.  The
1959 1960
 * other bits are reserved for now.
 */
1961 1962 1963 1964 1965 1966 1967 1968
#define EXT4_FT_UNKNOWN		0
#define EXT4_FT_REG_FILE	1
#define EXT4_FT_DIR		2
#define EXT4_FT_CHRDEV		3
#define EXT4_FT_BLKDEV		4
#define EXT4_FT_FIFO		5
#define EXT4_FT_SOCK		6
#define EXT4_FT_SYMLINK		7
1969

1970
#define EXT4_FT_MAX		8
1971

1972 1973
#define EXT4_FT_DIR_CSUM	0xDE

1974
/*
1975
 * EXT4_DIR_PAD defines the directory entries boundaries
1976 1977 1978
 *
 * NOTE: It must be a multiple of 4
 */
1979 1980 1981 1982
#define EXT4_DIR_PAD			4
#define EXT4_DIR_ROUND			(EXT4_DIR_PAD - 1)
#define EXT4_DIR_REC_LEN(name_len)	(((name_len) + 8 + EXT4_DIR_ROUND) & \
					 ~EXT4_DIR_ROUND)
1983 1984
#define EXT4_MAX_REC_LEN		((1<<16)-1)

1985 1986 1987 1988 1989 1990 1991 1992 1993
/*
 * If we ever get support for fs block sizes > page_size, we'll need
 * to remove the #if statements in the next two functions...
 */
static inline unsigned int
ext4_rec_len_from_disk(__le16 dlen, unsigned blocksize)
{
	unsigned len = le16_to_cpu(dlen);

1994
#if (PAGE_SIZE >= 65536)
1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006
	if (len == EXT4_MAX_REC_LEN || len == 0)
		return blocksize;
	return (len & 65532) | ((len & 3) << 16);
#else
	return len;
#endif
}

static inline __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize)
{
	if ((len > blocksize) || (blocksize > (1 << 18)) || (len & 3))
		BUG();
2007
#if (PAGE_SIZE >= 65536)
2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021
	if (len < 65536)
		return cpu_to_le16(len);
	if (len == blocksize) {
		if (blocksize == 65536)
			return cpu_to_le16(EXT4_MAX_REC_LEN);
		else
			return cpu_to_le16(0);
	}
	return cpu_to_le16((len & 65532) | ((len >> 16) & 3));
#else
	return cpu_to_le16(len);
#endif
}

2022 2023 2024 2025 2026
/*
 * Hash Tree Directory indexing
 * (c) Daniel Phillips, 2001
 */

2027
#define is_dx(dir) (ext4_has_feature_dir_index((dir)->i_sb) && \
2028
		    ext4_test_inode_flag((dir), EXT4_INODE_INDEX))
2029 2030
#define EXT4_DIR_LINK_MAX(dir) (!is_dx(dir) && (dir)->i_nlink >= EXT4_LINK_MAX)
#define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2 || (dir)->i_nlink == 1)
2031 2032 2033 2034 2035 2036

/* Legal values for the dx_root hash_version field: */

#define DX_HASH_LEGACY		0
#define DX_HASH_HALF_MD4	1
#define DX_HASH_TEA		2
2037 2038 2039
#define DX_HASH_LEGACY_UNSIGNED	3
#define DX_HASH_HALF_MD4_UNSIGNED	4
#define DX_HASH_TEA_UNSIGNED		5
2040

2041 2042 2043 2044 2045
static inline u32 ext4_chksum(struct ext4_sb_info *sbi, u32 crc,
			      const void *address, unsigned int length)
{
	struct {
		struct shash_desc shash;
2046
		char ctx[4];
2047 2048 2049
	} desc;
	int err;

2050 2051
	BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver)!=sizeof(desc.ctx));

2052 2053 2054 2055 2056 2057 2058 2059 2060 2061
	desc.shash.tfm = sbi->s_chksum_driver;
	desc.shash.flags = 0;
	*(u32 *)desc.ctx = crc;

	err = crypto_shash_update(&desc.shash, address, length);
	BUG_ON(err);

	return *(u32 *)desc.ctx;
}

2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072
#ifdef __KERNEL__

/* hash info structure used by the directory hash */
struct dx_hash_info
{
	u32		hash;
	u32		minor_hash;
	int		hash_version;
	u32		*seed;
};

2073 2074 2075 2076 2077

/* 32 and 64 bit signed EOF for dx directories */
#define EXT4_HTREE_EOF_32BIT   ((1UL  << (32 - 1)) - 1)
#define EXT4_HTREE_EOF_64BIT   ((1ULL << (64 - 1)) - 1)

2078 2079

/*
2080
 * Control parameters used by ext4_htree_next_block
2081 2082 2083
 */
#define HASH_NB_ALWAYS		1

2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094
struct ext4_filename {
	const struct qstr *usr_fname;
	struct ext4_str disk_name;
	struct dx_hash_info hinfo;
#ifdef CONFIG_EXT4_FS_ENCRYPTION
	struct ext4_str crypto_buf;
#endif
};

#define fname_name(p) ((p)->disk_name.name)
#define fname_len(p)  ((p)->disk_name.len)
2095 2096 2097 2098

/*
 * Describe an inode's exact location on disk and in memory
 */
2099
struct ext4_iloc
2100 2101 2102
{
	struct buffer_head *bh;
	unsigned long offset;
2103
	ext4_group_t block_group;
2104 2105
};

2106
static inline struct ext4_inode *ext4_raw_inode(struct ext4_iloc *iloc)
2107
{
2108
	return (struct ext4_inode *) (iloc->bh->b_data + iloc->offset);
2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126
}

/*
 * This structure is stuffed into the struct file's private_data field
 * for directories.  It is where we put information so that we can do
 * readdir operations in hash tree order.
 */
struct dir_private_info {
	struct rb_root	root;
	struct rb_node	*curr_node;
	struct fname	*extra_fname;
	loff_t		last_pos;
	__u32		curr_hash;
	__u32		curr_minor_hash;
	__u32		next_hash;
};

/* calculate the first block number of the group */
2127
static inline ext4_fsblk_t
2128
ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no)
2129
{
2130 2131
	return group_no * (ext4_fsblk_t)EXT4_BLOCKS_PER_GROUP(sb) +
		le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
2132 2133 2134 2135 2136
}

/*
 * Special error return code only used by dx_probe() and its callers.
 */
2137
#define ERR_BAD_DX_DIR	(-(MAX_ERRNO - 1))
2138

2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164
/*
 * Timeout and state flag for lazy initialization inode thread.
 */
#define EXT4_DEF_LI_WAIT_MULT			10
#define EXT4_DEF_LI_MAX_START_DELAY		5
#define EXT4_LAZYINIT_QUIT			0x0001
#define EXT4_LAZYINIT_RUNNING			0x0002

/*
 * Lazy inode table initialization info
 */
struct ext4_lazy_init {
	unsigned long		li_state;
	struct list_head	li_request_list;
	struct mutex		li_list_mtx;
};

struct ext4_li_request {
	struct super_block	*lr_super;
	struct ext4_sb_info	*lr_sbi;
	ext4_group_t		lr_next_group;
	struct list_head	lr_request;
	unsigned long		lr_next_sched;
	unsigned long		lr_timeout;
};

2165 2166 2167 2168 2169
struct ext4_features {
	struct kobject f_kobj;
	struct completion f_kobj_unregister;
};

2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201
/*
 * This structure will be used for multiple mount protection. It will be
 * written into the block number saved in the s_mmp_block field in the
 * superblock. Programs that check MMP should assume that if
 * SEQ_FSCK (or any unknown code above SEQ_MAX) is present then it is NOT safe
 * to use the filesystem, regardless of how old the timestamp is.
 */
#define EXT4_MMP_MAGIC     0x004D4D50U /* ASCII for MMP */
#define EXT4_MMP_SEQ_CLEAN 0xFF4D4D50U /* mmp_seq value for clean unmount */
#define EXT4_MMP_SEQ_FSCK  0xE24D4D50U /* mmp_seq value when being fscked */
#define EXT4_MMP_SEQ_MAX   0xE24D4D4FU /* maximum valid mmp_seq value */

struct mmp_struct {
	__le32	mmp_magic;		/* Magic number for MMP */
	__le32	mmp_seq;		/* Sequence no. updated periodically */

	/*
	 * mmp_time, mmp_nodename & mmp_bdevname are only used for information
	 * purposes and do not affect the correctness of the algorithm
	 */
	__le64	mmp_time;		/* Time last updated */
	char	mmp_nodename[64];	/* Node which last updated MMP block */
	char	mmp_bdevname[32];	/* Bdev which last updated MMP block */

	/*
	 * mmp_check_interval is used to verify if the MMP block has been
	 * updated on the block device. The value is updated based on the
	 * maximum time to write the MMP block during an update cycle.
	 */
	__le16	mmp_check_interval;

	__le16	mmp_pad1;
2202 2203
	__le32	mmp_pad2[226];
	__le32	mmp_checksum;		/* crc32c(uuid+mmp_block) */
2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231
};

/* arguments passed to the mmp thread */
struct mmpd_data {
	struct buffer_head *bh; /* bh from initial read_mmp_block() */
	struct super_block *sb;  /* super block of the fs */
};

/*
 * Check interval multiplier
 * The MMP block is written every update interval and initially checked every
 * update interval x the multiplier (the value is then adapted based on the
 * write latency). The reason is that writes can be delayed under load and we
 * don't want readers to incorrectly assume that the filesystem is no longer
 * in use.
 */
#define EXT4_MMP_CHECK_MULT		2UL

/*
 * Minimum interval for MMP checking in seconds.
 */
#define EXT4_MMP_MIN_CHECK_INTERVAL	5UL

/*
 * Maximum interval for MMP checking in seconds.
 */
#define EXT4_MMP_MAX_CHECK_INTERVAL	300UL

2232 2233 2234 2235 2236 2237
/*
 * Function prototypes
 */

/*
 * Ok, these declarations are also in <linux/kernel.h> but none of the
2238
 * ext4 source programs needs to include it so they are duplicated here.
2239
 */
D
Dave Kleikamp 已提交
2240 2241 2242
# define NORET_TYPE	/**/
# define ATTRIB_NORET	__attribute__((noreturn))
# define NORET_AND	noreturn,
2243

2244
/* bitmap.c */
2245
extern unsigned int ext4_count_free(char *bitmap, unsigned numchars);
2246 2247 2248 2249 2250 2251
void ext4_inode_bitmap_csum_set(struct super_block *sb, ext4_group_t group,
				struct ext4_group_desc *gdp,
				struct buffer_head *bh, int sz);
int ext4_inode_bitmap_csum_verify(struct super_block *sb, ext4_group_t group,
				  struct ext4_group_desc *gdp,
				  struct buffer_head *bh, int sz);
2252 2253
void ext4_block_bitmap_csum_set(struct super_block *sb, ext4_group_t group,
				struct ext4_group_desc *gdp,
2254
				struct buffer_head *bh);
2255 2256
int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group,
				  struct ext4_group_desc *gdp,
2257
				  struct buffer_head *bh);
2258

2259
/* balloc.c */
2260 2261 2262 2263 2264 2265 2266
extern void ext4_get_group_no_and_offset(struct super_block *sb,
					 ext4_fsblk_t blocknr,
					 ext4_group_t *blockgrpp,
					 ext4_grpblk_t *offsetp);
extern ext4_group_t ext4_get_group_number(struct super_block *sb,
					  ext4_fsblk_t block);

2267 2268 2269 2270
extern unsigned int ext4_block_group(struct super_block *sb,
			ext4_fsblk_t blocknr);
extern ext4_grpblk_t ext4_block_group_offset(struct super_block *sb,
			ext4_fsblk_t blocknr);
2271 2272 2273
extern int ext4_bg_has_super(struct super_block *sb, ext4_group_t group);
extern unsigned long ext4_bg_num_gdb(struct super_block *sb,
			ext4_group_t group);
2274
extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
2275 2276 2277 2278
					 ext4_fsblk_t goal,
					 unsigned int flags,
					 unsigned long *count,
					 int *errp);
2279 2280
extern int ext4_claim_free_clusters(struct ext4_sb_info *sbi,
				    s64 nclusters, unsigned int flags);
2281
extern ext4_fsblk_t ext4_count_free_clusters(struct super_block *);
2282
extern void ext4_check_blocks_bitmap(struct super_block *);
2283
extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
2284
						    ext4_group_t block_group,
2285
						    struct buffer_head ** bh);
2286
extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
2287 2288 2289 2290 2291 2292 2293 2294

extern struct buffer_head *ext4_read_block_bitmap_nowait(struct super_block *sb,
						ext4_group_t block_group);
extern int ext4_wait_block_bitmap(struct super_block *sb,
				  ext4_group_t block_group,
				  struct buffer_head *bh);
extern struct buffer_head *ext4_read_block_bitmap(struct super_block *sb,
						  ext4_group_t block_group);
2295 2296 2297
extern unsigned ext4_free_clusters_after_init(struct super_block *sb,
					      ext4_group_t block_group,
					      struct ext4_group_desc *gdp);
2298
ext4_fsblk_t ext4_inode_to_goal_block(struct inode *);
2299

2300 2301 2302 2303 2304 2305 2306 2307 2308 2309
/* crypto_policy.c */
int ext4_is_child_context_consistent_with_parent(struct inode *parent,
						 struct inode *child);
int ext4_inherit_context(struct inode *parent, struct inode *child);
void ext4_to_hex(char *dst, char *src, size_t src_size);
int ext4_process_policy(const struct ext4_encryption_policy *policy,
			struct inode *inode);
int ext4_get_policy(struct inode *inode,
		    struct ext4_encryption_policy *policy);

2310
/* crypto.c */
T
Theodore Ts'o 已提交
2311
extern struct kmem_cache *ext4_crypt_info_cachep;
2312 2313 2314
bool ext4_valid_contents_enc_mode(uint32_t mode);
uint32_t ext4_validate_encryption_key_size(uint32_t mode, uint32_t size);
extern struct workqueue_struct *ext4_read_workqueue;
2315 2316
struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode,
					    gfp_t gfp_flags);
2317 2318 2319
void ext4_release_crypto_ctx(struct ext4_crypto_ctx *ctx);
void ext4_restore_control_page(struct page *data_page);
struct page *ext4_encrypt(struct inode *inode,
2320 2321
			  struct page *plaintext_page,
			  gfp_t gfp_flags);
2322
int ext4_decrypt(struct page *page);
J
Jan Kara 已提交
2323 2324
int ext4_encrypted_zeroout(struct inode *inode, ext4_lblk_t lblk,
			   ext4_fsblk_t pblk, ext4_lblk_t len);
2325
extern const struct dentry_operations ext4_encrypted_d_ops;
2326 2327 2328 2329 2330 2331

#ifdef CONFIG_EXT4_FS_ENCRYPTION
int ext4_init_crypto(void);
void ext4_exit_crypto(void);
static inline int ext4_sb_has_crypto(struct super_block *sb)
{
2332
	return ext4_has_feature_encrypt(sb);
2333 2334 2335 2336 2337 2338 2339 2340 2341 2342
}
#else
static inline int ext4_init_crypto(void) { return 0; }
static inline void ext4_exit_crypto(void) { }
static inline int ext4_sb_has_crypto(struct super_block *sb)
{
	return 0;
}
#endif

2343 2344 2345
/* crypto_fname.c */
bool ext4_valid_filenames_enc_mode(uint32_t mode);
u32 ext4_fname_crypto_round_up(u32 size, u32 blksize);
2346
unsigned ext4_fname_encrypted_size(struct inode *inode, u32 ilen);
2347
int ext4_fname_crypto_alloc_buffer(struct inode *inode,
2348
				   u32 ilen, struct ext4_str *crypto_str);
2349
int _ext4_fname_disk_to_usr(struct inode *inode,
2350
			    struct dx_hash_info *hinfo,
2351 2352
			    const struct ext4_str *iname,
			    struct ext4_str *oname);
2353
int ext4_fname_disk_to_usr(struct inode *inode,
2354
			   struct dx_hash_info *hinfo,
2355 2356
			   const struct ext4_dir_entry_2 *de,
			   struct ext4_str *oname);
2357
int ext4_fname_usr_to_disk(struct inode *inode,
2358 2359 2360 2361
			   const struct qstr *iname,
			   struct ext4_str *oname);
#ifdef CONFIG_EXT4_FS_ENCRYPTION
void ext4_fname_crypto_free_buffer(struct ext4_str *crypto_str);
2362 2363 2364
int ext4_fname_setup_filename(struct inode *dir, const struct qstr *iname,
			      int lookup, struct ext4_filename *fname);
void ext4_fname_free_filename(struct ext4_filename *fname);
2365 2366
#else
static inline
2367
int ext4_setup_fname_crypto(struct inode *inode)
2368
{
2369
	return 0;
2370 2371
}
static inline void ext4_fname_crypto_free_buffer(struct ext4_str *p) { }
2372 2373 2374 2375 2376 2377 2378 2379 2380 2381
static inline int ext4_fname_setup_filename(struct inode *dir,
				     const struct qstr *iname,
				     int lookup, struct ext4_filename *fname)
{
	fname->usr_fname = iname;
	fname->disk_name.name = (unsigned char *) iname->name;
	fname->disk_name.len = iname->len;
	return 0;
}
static inline void ext4_fname_free_filename(struct ext4_filename *fname) { }
2382 2383 2384
#endif


2385
/* crypto_key.c */
2386 2387
void ext4_free_crypt_info(struct ext4_crypt_info *ci);
void ext4_free_encryption_info(struct inode *inode, struct ext4_crypt_info *ci);
2388
int _ext4_get_encryption_info(struct inode *inode);
2389 2390 2391

#ifdef CONFIG_EXT4_FS_ENCRYPTION
int ext4_has_encryption_key(struct inode *inode);
2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405

static inline int ext4_get_encryption_info(struct inode *inode)
{
	struct ext4_crypt_info *ci = EXT4_I(inode)->i_crypt_info;

	if (!ci ||
	    (ci->ci_keyring_key &&
	     (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
					   (1 << KEY_FLAG_REVOKED) |
					   (1 << KEY_FLAG_DEAD)))))
		return _ext4_get_encryption_info(inode);
	return 0;
}

2406 2407 2408 2409 2410
static inline struct ext4_crypt_info *ext4_encryption_info(struct inode *inode)
{
	return EXT4_I(inode)->i_crypt_info;
}

2411 2412 2413 2414 2415
#else
static inline int ext4_has_encryption_key(struct inode *inode)
{
	return 0;
}
2416 2417 2418 2419
static inline int ext4_get_encryption_info(struct inode *inode)
{
	return 0;
}
2420 2421 2422 2423
static inline struct ext4_crypt_info *ext4_encryption_info(struct inode *inode)
{
	return NULL;
}
2424 2425 2426
#endif


2427
/* dir.c */
2428
extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *,
2429
				  struct file *,
2430
				  struct ext4_dir_entry_2 *,
2431 2432 2433
				  struct buffer_head *, char *, int,
				  unsigned int);
#define ext4_check_dir_entry(dir, filp, de, bh, buf, size, offset)	\
2434
	unlikely(__ext4_check_dir_entry(__func__, __LINE__, (dir), (filp), \
2435
					(de), (bh), (buf), (size), (offset)))
2436
extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
2437 2438 2439
				__u32 minor_hash,
				struct ext4_dir_entry_2 *dirent,
				struct ext4_str *ent_name);
2440
extern void ext4_htree_free_dir_info(struct dir_private_info *p);
2441 2442 2443
extern int ext4_find_dest_de(struct inode *dir, struct inode *inode,
			     struct buffer_head *bh,
			     void *buf, int buf_size,
2444
			     struct ext4_filename *fname,
2445
			     struct ext4_dir_entry_2 **dest_de);
2446
int ext4_insert_dentry(struct inode *dir,
2447 2448 2449 2450
		       struct inode *inode,
		       struct ext4_dir_entry_2 *de,
		       int buf_size,
		       struct ext4_filename *fname);
2451 2452
static inline void ext4_update_dx_flag(struct inode *inode)
{
2453
	if (!ext4_has_feature_dir_index(inode->i_sb))
2454 2455
		ext4_clear_inode_flag(inode, EXT4_INODE_INDEX);
}
T
Tao Ma 已提交
2456 2457 2458 2459 2460 2461
static unsigned char ext4_filetype_table[] = {
	DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
};

static inline  unsigned char get_dtype(struct super_block *sb, int filetype)
{
2462
	if (!ext4_has_feature_filetype(sb) || filetype >= EXT4_FT_MAX)
T
Tao Ma 已提交
2463 2464 2465 2466
		return DT_UNKNOWN;

	return ext4_filetype_table[filetype];
}
2467 2468
extern int ext4_check_all_de(struct inode *dir, struct buffer_head *bh,
			     void *buf, int buf_size);
2469 2470

/* fsync.c */
2471
extern int ext4_sync_file(struct file *, loff_t, loff_t, int);
2472 2473

/* hash.c */
2474
extern int ext4fs_dirhash(const char *name, int len, struct
2475 2476 2477
			  dx_hash_info *hinfo);

/* ialloc.c */
2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491
extern struct inode *__ext4_new_inode(handle_t *, struct inode *, umode_t,
				      const struct qstr *qstr, __u32 goal,
				      uid_t *owner, int handle_type,
				      unsigned int line_no, int nblocks);

#define ext4_new_inode(handle, dir, mode, qstr, goal, owner) \
	__ext4_new_inode((handle), (dir), (mode), (qstr), (goal), (owner), \
			 0, 0, 0)
#define ext4_new_inode_start_handle(dir, mode, qstr, goal, owner, \
				    type, nblocks)		    \
	__ext4_new_inode(NULL, (dir), (mode), (qstr), (goal), (owner), \
			 (type), __LINE__, (nblocks))


2492 2493 2494 2495 2496
extern void ext4_free_inode(handle_t *, struct inode *);
extern struct inode * ext4_orphan_get(struct super_block *, unsigned long);
extern unsigned long ext4_count_free_inodes(struct super_block *);
extern unsigned long ext4_count_dirs(struct super_block *);
extern void ext4_check_inodes_bitmap(struct super_block *);
2497
extern void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
2498 2499
extern int ext4_init_inode_table(struct super_block *sb,
				 ext4_group_t group, int barrier);
2500
extern void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate);
2501

2502
/* mballoc.c */
2503
extern const struct file_operations ext4_seq_mb_groups_fops;
2504 2505
extern long ext4_mb_stats;
extern long ext4_mb_max_to_scan;
2506
extern int ext4_mb_init(struct super_block *);
2507 2508 2509 2510
extern int ext4_mb_release(struct super_block *);
extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *,
				struct ext4_allocation_request *, int *);
extern int ext4_mb_reserve_blocks(struct super_block *, int);
2511
extern void ext4_discard_preallocations(struct inode *);
2512 2513
extern int __init ext4_init_mballoc(void);
extern void ext4_exit_mballoc(void);
2514
extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
2515 2516
			     struct buffer_head *bh, ext4_fsblk_t block,
			     unsigned long count, int flags);
2517 2518
extern int ext4_mb_alloc_groupinfo(struct super_block *sb,
				   ext4_group_t ngroups);
2519
extern int ext4_mb_add_groupinfo(struct super_block *sb,
2520
		ext4_group_t i, struct ext4_group_desc *desc);
2521
extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
2522
				ext4_fsblk_t block, unsigned long count);
2523 2524
extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);

2525
/* inode.c */
2526
int ext4_inode_is_fast_symlink(struct inode *inode);
2527
struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int);
2528
struct buffer_head *ext4_bread(handle_t *, struct inode *, ext4_lblk_t, int);
2529 2530
int ext4_get_block_unwritten(struct inode *inode, sector_t iblock,
			     struct buffer_head *bh_result, int create);
2531 2532
int ext4_dax_get_block(struct inode *inode, sector_t iblock,
		       struct buffer_head *bh_result, int create);
2533
int ext4_get_block(struct inode *inode, sector_t iblock,
2534 2535 2536
		   struct buffer_head *bh_result, int create);
int ext4_dio_get_block(struct inode *inode, sector_t iblock,
		       struct buffer_head *bh_result, int create);
2537 2538
int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
			   struct buffer_head *bh, int create);
2539 2540 2541 2542 2543 2544 2545 2546 2547
int ext4_walk_page_buffers(handle_t *handle,
			   struct buffer_head *head,
			   unsigned from,
			   unsigned to,
			   int *partial,
			   int (*fn)(handle_t *handle,
				     struct buffer_head *bh));
int do_journal_get_write_access(handle_t *handle,
				struct buffer_head *bh);
2548 2549
#define FALL_BACK_TO_NONDELALLOC 1
#define CONVERT_INLINE_DATA	 2
2550

2551
extern struct inode *ext4_iget(struct super_block *, unsigned long);
2552
extern struct inode *ext4_iget_normal(struct super_block *, unsigned long);
2553
extern int  ext4_write_inode(struct inode *, struct writeback_control *);
2554
extern int  ext4_setattr(struct dentry *, struct iattr *);
2555 2556
extern int  ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
				struct kstat *stat);
A
Al Viro 已提交
2557 2558
extern void ext4_evict_inode(struct inode *);
extern void ext4_clear_inode(struct inode *);
2559
extern int  ext4_sync_inode(handle_t *, struct inode *);
2560
extern void ext4_dirty_inode(struct inode *, int);
2561 2562
extern int ext4_change_inode_journal_flag(struct inode *, int);
extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
2563
extern int ext4_inode_attach_jinode(struct inode *inode);
2564
extern int ext4_can_truncate(struct inode *inode);
2565
extern void ext4_truncate(struct inode *);
2566
extern int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length);
2567
extern int ext4_truncate_restart_trans(handle_t *, struct inode *, int nblocks);
2568
extern void ext4_set_inode_flags(struct inode *);
2569
extern void ext4_get_inode_flags(struct ext4_inode_info *);
2570
extern int ext4_alloc_da_blocks(struct inode *inode);
2571
extern void ext4_set_aops(struct inode *inode);
A
Alex Tomas 已提交
2572
extern int ext4_writepage_trans_blocks(struct inode *);
2573
extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
2574 2575
extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
			     loff_t lstart, loff_t lend);
2576
extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
2577
extern int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf);
2578
extern qsize_t *ext4_get_reserved_space(struct inode *inode);
L
Li Xi 已提交
2579
extern int ext4_get_projid(struct inode *inode, kprojid_t *projid);
2580 2581
extern void ext4_da_update_reserve_space(struct inode *inode,
					int used, int quota_claim);
J
Jan Kara 已提交
2582 2583
extern int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk,
			      ext4_fsblk_t pblk, ext4_lblk_t len);
2584 2585 2586
extern int ext4_get_next_extent(struct inode *inode, ext4_lblk_t lblk,
				unsigned int map_len,
				struct extent_status *result);
2587 2588 2589 2590 2591

/* indirect.c */
extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
				struct ext4_map_blocks *map, int flags);
extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock);
2592
extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks);
T
Theodore Ts'o 已提交
2593
extern void ext4_ind_truncate(handle_t *, struct inode *inode);
2594 2595
extern int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
				 ext4_lblk_t start, ext4_lblk_t end);
2596

2597
/* ioctl.c */
A
Andi Kleen 已提交
2598
extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
2599
extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
2600

2601
/* migrate.c */
2602
extern int ext4_ext_migrate(struct inode *);
2603
extern int ext4_ind_migrate(struct inode *inode);
2604

2605
/* namei.c */
2606 2607
extern int ext4_dirent_csum_verify(struct inode *inode,
				   struct ext4_dir_entry *dirent);
2608 2609 2610
extern int ext4_orphan_add(handle_t *, struct inode *);
extern int ext4_orphan_del(handle_t *, struct inode *);
extern int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
2611
				__u32 start_minor_hash, __u32 *next_hash);
2612 2613 2614 2615 2616 2617 2618 2619
extern int ext4_search_dir(struct buffer_head *bh,
			   char *search_buf,
			   int buf_size,
			   struct inode *dir,
			   struct ext4_filename *fname,
			   const struct qstr *d_name,
			   unsigned int offset,
			   struct ext4_dir_entry_2 **res_dir);
T
Tao Ma 已提交
2620 2621 2622 2623 2624 2625 2626
extern int ext4_generic_delete_entry(handle_t *handle,
				     struct inode *dir,
				     struct ext4_dir_entry_2 *de_del,
				     struct buffer_head *bh,
				     void *entry_buf,
				     int buf_size,
				     int csum_size);
2627
extern int ext4_empty_dir(struct inode *inode);
2628 2629

/* resize.c */
2630 2631 2632 2633 2634
extern int ext4_group_add(struct super_block *sb,
				struct ext4_new_group_data *input);
extern int ext4_group_extend(struct super_block *sb,
				struct ext4_super_block *es,
				ext4_fsblk_t n_blocks_count);
2635
extern int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count);
2636 2637

/* super.c */
2638
extern int ext4_seq_options_show(struct seq_file *seq, void *offset);
2639
extern int ext4_calculate_overhead(struct super_block *sb);
2640
extern void ext4_superblock_csum_set(struct super_block *sb);
2641 2642
extern void *ext4_kvmalloc(size_t size, gfp_t flags);
extern void *ext4_kvzalloc(size_t size, gfp_t flags);
2643 2644
extern int ext4_alloc_flex_bg_array(struct super_block *sb,
				    ext4_group_t ngroup);
2645 2646
extern const char *ext4_decode_error(struct super_block *sb, int errno,
				     char nbuf[16]);
2647

2648 2649 2650 2651
extern __printf(4, 5)
void __ext4_error(struct super_block *, const char *, unsigned int,
		  const char *, ...);
extern __printf(5, 6)
2652
void __ext4_error_inode(struct inode *, const char *, unsigned int, ext4_fsblk_t,
2653 2654
		      const char *, ...);
extern __printf(5, 6)
2655
void __ext4_error_file(struct file *, const char *, unsigned int, ext4_fsblk_t,
2656
		     const char *, ...);
2657 2658
extern void __ext4_std_error(struct super_block *, const char *,
			     unsigned int, int);
2659 2660 2661 2662 2663 2664
extern __printf(4, 5)
void __ext4_abort(struct super_block *, const char *, unsigned int,
		  const char *, ...);
extern __printf(4, 5)
void __ext4_warning(struct super_block *, const char *, unsigned int,
		    const char *, ...);
2665 2666 2667
extern __printf(4, 5)
void __ext4_warning_inode(const struct inode *inode, const char *function,
			  unsigned int line, const char *fmt, ...);
2668
extern __printf(3, 4)
2669
void __ext4_msg(struct super_block *, const char *, const char *, ...);
2670 2671
extern void __dump_mmp_msg(struct super_block *, struct mmp_struct *mmp,
			   const char *, unsigned int, const char *);
2672 2673 2674 2675 2676
extern __printf(7, 8)
void __ext4_grp_locked_error(const char *, unsigned int,
			     struct super_block *, ext4_group_t,
			     unsigned long, ext4_fsblk_t,
			     const char *, ...);
2677

2678 2679 2680 2681 2682 2683 2684 2685 2686
#define EXT4_ERROR_INODE(inode, fmt, a...) \
	ext4_error_inode((inode), __func__, __LINE__, 0, (fmt), ## a)

#define EXT4_ERROR_INODE_BLOCK(inode, block, fmt, a...)			\
	ext4_error_inode((inode), __func__, __LINE__, (block), (fmt), ## a)

#define EXT4_ERROR_FILE(file, block, fmt, a...)				\
	ext4_error_file((file), __func__, __LINE__, (block), (fmt), ## a)

2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698
#ifdef CONFIG_PRINTK

#define ext4_error_inode(inode, func, line, block, fmt, ...)		\
	__ext4_error_inode(inode, func, line, block, fmt, ##__VA_ARGS__)
#define ext4_error_file(file, func, line, block, fmt, ...)		\
	__ext4_error_file(file, func, line, block, fmt, ##__VA_ARGS__)
#define ext4_error(sb, fmt, ...)					\
	__ext4_error(sb, __func__, __LINE__, fmt, ##__VA_ARGS__)
#define ext4_abort(sb, fmt, ...)					\
	__ext4_abort(sb, __func__, __LINE__, fmt, ##__VA_ARGS__)
#define ext4_warning(sb, fmt, ...)					\
	__ext4_warning(sb, __func__, __LINE__, fmt, ##__VA_ARGS__)
2699 2700
#define ext4_warning_inode(inode, fmt, ...)				\
	__ext4_warning_inode(inode, __func__, __LINE__, fmt, ##__VA_ARGS__)
2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735
#define ext4_msg(sb, level, fmt, ...)				\
	__ext4_msg(sb, level, fmt, ##__VA_ARGS__)
#define dump_mmp_msg(sb, mmp, msg)					\
	__dump_mmp_msg(sb, mmp, __func__, __LINE__, msg)
#define ext4_grp_locked_error(sb, grp, ino, block, fmt, ...)		\
	__ext4_grp_locked_error(__func__, __LINE__, sb, grp, ino, block, \
				fmt, ##__VA_ARGS__)

#else

#define ext4_error_inode(inode, func, line, block, fmt, ...)		\
do {									\
	no_printk(fmt, ##__VA_ARGS__);					\
	__ext4_error_inode(inode, "", 0, block, " ");			\
} while (0)
#define ext4_error_file(file, func, line, block, fmt, ...)		\
do {									\
	no_printk(fmt, ##__VA_ARGS__);					\
	__ext4_error_file(file, "", 0, block, " ");			\
} while (0)
#define ext4_error(sb, fmt, ...)					\
do {									\
	no_printk(fmt, ##__VA_ARGS__);					\
	__ext4_error(sb, "", 0, " ");					\
} while (0)
#define ext4_abort(sb, fmt, ...)					\
do {									\
	no_printk(fmt, ##__VA_ARGS__);					\
	__ext4_abort(sb, "", 0, " ");					\
} while (0)
#define ext4_warning(sb, fmt, ...)					\
do {									\
	no_printk(fmt, ##__VA_ARGS__);					\
	__ext4_warning(sb, "", 0, " ");					\
} while (0)
2736 2737 2738 2739 2740
#define ext4_warning_inode(inode, fmt, ...)				\
do {									\
	no_printk(fmt, ##__VA_ARGS__);					\
	__ext4_warning_inode(inode, "", 0, " ");			\
} while (0)
2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755
#define ext4_msg(sb, level, fmt, ...)					\
do {									\
	no_printk(fmt, ##__VA_ARGS__);					\
	__ext4_msg(sb, "", " ");					\
} while (0)
#define dump_mmp_msg(sb, mmp, msg)					\
	__dump_mmp_msg(sb, mmp, "", 0, "")
#define ext4_grp_locked_error(sb, grp, ino, block, fmt, ...)		\
do {									\
	no_printk(fmt, ##__VA_ARGS__);				\
	__ext4_grp_locked_error("", 0, sb, grp, ino, block, " ");	\
} while (0)

#endif

2756
extern void ext4_update_dynamic_rev(struct super_block *sb);
2757 2758 2759 2760 2761 2762
extern int ext4_update_compat_feature(handle_t *handle, struct super_block *sb,
					__u32 compat);
extern int ext4_update_rocompat_feature(handle_t *handle,
					struct super_block *sb,	__u32 rocompat);
extern int ext4_update_incompat_feature(handle_t *handle,
					struct super_block *sb,	__u32 incompat);
2763 2764 2765 2766 2767 2768
extern ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
				      struct ext4_group_desc *bg);
extern ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb,
				      struct ext4_group_desc *bg);
extern ext4_fsblk_t ext4_inode_table(struct super_block *sb,
				     struct ext4_group_desc *bg);
2769 2770
extern __u32 ext4_free_group_clusters(struct super_block *sb,
				      struct ext4_group_desc *bg);
2771 2772 2773 2774 2775 2776
extern __u32 ext4_free_inodes_count(struct super_block *sb,
				 struct ext4_group_desc *bg);
extern __u32 ext4_used_dirs_count(struct super_block *sb,
				struct ext4_group_desc *bg);
extern __u32 ext4_itable_unused_count(struct super_block *sb,
				   struct ext4_group_desc *bg);
2777 2778 2779 2780 2781 2782
extern void ext4_block_bitmap_set(struct super_block *sb,
				  struct ext4_group_desc *bg, ext4_fsblk_t blk);
extern void ext4_inode_bitmap_set(struct super_block *sb,
				  struct ext4_group_desc *bg, ext4_fsblk_t blk);
extern void ext4_inode_table_set(struct super_block *sb,
				 struct ext4_group_desc *bg, ext4_fsblk_t blk);
2783 2784 2785
extern void ext4_free_group_clusters_set(struct super_block *sb,
					 struct ext4_group_desc *bg,
					 __u32 count);
2786 2787 2788 2789 2790 2791
extern void ext4_free_inodes_set(struct super_block *sb,
				struct ext4_group_desc *bg, __u32 count);
extern void ext4_used_dirs_set(struct super_block *sb,
				struct ext4_group_desc *bg, __u32 count);
extern void ext4_itable_unused_set(struct super_block *sb,
				   struct ext4_group_desc *bg, __u32 count);
2792
extern int ext4_group_desc_csum_verify(struct super_block *sb, __u32 group,
2793
				       struct ext4_group_desc *gdp);
2794 2795
extern void ext4_group_desc_csum_set(struct super_block *sb, __u32 group,
				     struct ext4_group_desc *gdp);
2796 2797
extern int ext4_register_li_request(struct super_block *sb,
				    ext4_group_t first_not_zeroed);
L
Laurent Vivier 已提交
2798

2799 2800
static inline int ext4_has_group_desc_csum(struct super_block *sb)
{
2801 2802
	return ext4_has_feature_gdt_csum(sb) ||
	       EXT4_SB(sb)->s_chksum_driver != NULL;
2803
}
L
Laurent Vivier 已提交
2804

2805 2806
static inline int ext4_has_metadata_csum(struct super_block *sb)
{
2807
	WARN_ON_ONCE(ext4_has_feature_metadata_csum(sb) &&
2808 2809 2810 2811
		     !EXT4_SB(sb)->s_chksum_driver);

	return (EXT4_SB(sb)->s_chksum_driver != NULL);
}
L
Laurent Vivier 已提交
2812 2813 2814
static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es)
{
	return ((ext4_fsblk_t)le32_to_cpu(es->s_blocks_count_hi) << 32) |
2815
		le32_to_cpu(es->s_blocks_count_lo);
L
Laurent Vivier 已提交
2816 2817 2818 2819 2820
}

static inline ext4_fsblk_t ext4_r_blocks_count(struct ext4_super_block *es)
{
	return ((ext4_fsblk_t)le32_to_cpu(es->s_r_blocks_count_hi) << 32) |
2821
		le32_to_cpu(es->s_r_blocks_count_lo);
L
Laurent Vivier 已提交
2822 2823 2824 2825 2826
}

static inline ext4_fsblk_t ext4_free_blocks_count(struct ext4_super_block *es)
{
	return ((ext4_fsblk_t)le32_to_cpu(es->s_free_blocks_count_hi) << 32) |
2827
		le32_to_cpu(es->s_free_blocks_count_lo);
L
Laurent Vivier 已提交
2828 2829 2830 2831 2832
}

static inline void ext4_blocks_count_set(struct ext4_super_block *es,
					 ext4_fsblk_t blk)
{
2833
	es->s_blocks_count_lo = cpu_to_le32((u32)blk);
L
Laurent Vivier 已提交
2834 2835 2836 2837 2838 2839
	es->s_blocks_count_hi = cpu_to_le32(blk >> 32);
}

static inline void ext4_free_blocks_count_set(struct ext4_super_block *es,
					      ext4_fsblk_t blk)
{
2840
	es->s_free_blocks_count_lo = cpu_to_le32((u32)blk);
L
Laurent Vivier 已提交
2841 2842 2843 2844 2845 2846
	es->s_free_blocks_count_hi = cpu_to_le32(blk >> 32);
}

static inline void ext4_r_blocks_count_set(struct ext4_super_block *es,
					   ext4_fsblk_t blk)
{
2847
	es->s_r_blocks_count_lo = cpu_to_le32((u32)blk);
L
Laurent Vivier 已提交
2848 2849 2850
	es->s_r_blocks_count_hi = cpu_to_le32(blk >> 32);
}

2851 2852
static inline loff_t ext4_isize(struct ext4_inode *raw_inode)
{
2853 2854 2855 2856 2857
	if (S_ISREG(le16_to_cpu(raw_inode->i_mode)))
		return ((loff_t)le32_to_cpu(raw_inode->i_size_high) << 32) |
			le32_to_cpu(raw_inode->i_size_lo);
	else
		return (loff_t) le32_to_cpu(raw_inode->i_size_lo);
2858
}
L
Laurent Vivier 已提交
2859

2860 2861 2862 2863 2864
static inline void ext4_isize_set(struct ext4_inode *raw_inode, loff_t i_size)
{
	raw_inode->i_size_lo = cpu_to_le32(i_size);
	raw_inode->i_size_high = cpu_to_le32(i_size >> 32);
}
2865

2866 2867
static inline
struct ext4_group_info *ext4_get_group_info(struct super_block *sb,
2868
					    ext4_group_t group)
2869 2870 2871
{
	 struct ext4_group_info ***grp_info;
	 long indexv, indexh;
2872
	 BUG_ON(group >= EXT4_SB(sb)->s_groups_count);
2873 2874 2875 2876 2877 2878
	 grp_info = EXT4_SB(sb)->s_group_info;
	 indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb));
	 indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1);
	 return grp_info[indexv][indexh];
}

2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890
/*
 * Reading s_groups_count requires using smp_rmb() afterwards.  See
 * the locking protocol documented in the comments of ext4_group_add()
 * in resize.c
 */
static inline ext4_group_t ext4_get_groups_count(struct super_block *sb)
{
	ext4_group_t	ngroups = EXT4_SB(sb)->s_groups_count;

	smp_rmb();
	return ngroups;
}
2891

2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902
static inline ext4_group_t ext4_flex_group(struct ext4_sb_info *sbi,
					     ext4_group_t block_group)
{
	return block_group >> sbi->s_log_groups_per_flex;
}

static inline unsigned int ext4_flex_bg_size(struct ext4_sb_info *sbi)
{
	return 1 << sbi->s_log_groups_per_flex;
}

2903
#define ext4_std_error(sb, errno)				\
2904 2905
do {								\
	if ((errno))						\
2906
		__ext4_std_error((sb), __func__, __LINE__, (errno));	\
2907 2908
} while (0)

2909
#ifdef CONFIG_SMP
2910 2911
/* Each CPU can accumulate percpu_counter_batch clusters in their local
 * counters. So we need to make sure we have free clusters more
2912
 * than percpu_counter_batch  * nr_cpu_ids. Also add a window of 4 times.
2913
 */
2914
#define EXT4_FREECLUSTERS_WATERMARK (4 * (percpu_counter_batch * nr_cpu_ids))
2915
#else
2916
#define EXT4_FREECLUSTERS_WATERMARK 0
2917 2918
#endif

2919
/* Update i_disksize. Requires i_mutex to avoid races with truncate */
2920 2921
static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
{
2922
	WARN_ON_ONCE(S_ISREG(inode->i_mode) &&
A
Al Viro 已提交
2923
		     !inode_is_locked(inode));
2924 2925 2926 2927 2928 2929
	down_write(&EXT4_I(inode)->i_data_sem);
	if (newsize > EXT4_I(inode)->i_disksize)
		EXT4_I(inode)->i_disksize = newsize;
	up_write(&EXT4_I(inode)->i_data_sem);
}

2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945
/* Update i_size, i_disksize. Requires i_mutex to avoid races with truncate */
static inline int ext4_update_inode_size(struct inode *inode, loff_t newsize)
{
	int changed = 0;

	if (newsize > inode->i_size) {
		i_size_write(inode, newsize);
		changed = 1;
	}
	if (newsize > EXT4_I(inode)->i_disksize) {
		ext4_update_i_disksize(inode, newsize);
		changed |= 2;
	}
	return changed;
}

2946 2947 2948
int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
				      loff_t len);

2949 2950 2951
struct ext4_group_info {
	unsigned long   bb_state;
	struct rb_root  bb_free_root;
2952 2953 2954
	ext4_grpblk_t	bb_first_free;	/* first free block */
	ext4_grpblk_t	bb_free;	/* total free blocks */
	ext4_grpblk_t	bb_fragments;	/* nr of freespace fragments */
2955
	ext4_grpblk_t	bb_largest_free_order;/* order of largest frag in BG */
2956 2957 2958 2959 2960
	struct          list_head bb_prealloc_list;
#ifdef DOUBLE_CHECK
	void            *bb_bitmap;
#endif
	struct rw_semaphore alloc_sem;
2961 2962 2963 2964
	ext4_grpblk_t	bb_counters[];	/* Nr of free power-of-two-block
					 * regions, index is order.
					 * bb_counters[3] = 5 means
					 * 5 free 8-block regions. */
2965 2966
};

2967 2968
#define EXT4_GROUP_INFO_NEED_INIT_BIT		0
#define EXT4_GROUP_INFO_WAS_TRIMMED_BIT		1
2969
#define EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT	2
2970
#define EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT	3
2971 2972 2973

#define EXT4_MB_GRP_NEED_INIT(grp)	\
	(test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
2974 2975
#define EXT4_MB_GRP_BBITMAP_CORRUPT(grp)	\
	(test_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &((grp)->bb_state)))
2976 2977
#define EXT4_MB_GRP_IBITMAP_CORRUPT(grp)	\
	(test_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &((grp)->bb_state)))
2978

2979 2980 2981 2982 2983 2984 2985
#define EXT4_MB_GRP_WAS_TRIMMED(grp)	\
	(test_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state)))
#define EXT4_MB_GRP_SET_TRIMMED(grp)	\
	(set_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state)))
#define EXT4_MB_GRP_CLEAR_TRIMMED(grp)	\
	(clear_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state)))

2986 2987 2988
#define EXT4_MAX_CONTENTION		8
#define EXT4_CONTENTION_THRESHOLD	2

2989 2990
static inline spinlock_t *ext4_group_lock_ptr(struct super_block *sb,
					      ext4_group_t group)
2991
{
2992 2993
	return bgl_lock_ptr(EXT4_SB(sb)->s_blockgroup_lock, group);
}
2994

2995 2996 2997 2998 2999 3000 3001 3002 3003
/*
 * Returns true if the filesystem is busy enough that attempts to
 * access the block group locks has run into contention.
 */
static inline int ext4_fs_is_busy(struct ext4_sb_info *sbi)
{
	return (atomic_read(&sbi->s_lock_busy) > EXT4_CONTENTION_THRESHOLD);
}

3004 3005
static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group)
{
3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021
	spinlock_t *lock = ext4_group_lock_ptr(sb, group);
	if (spin_trylock(lock))
		/*
		 * We're able to grab the lock right away, so drop the
		 * lock contention counter.
		 */
		atomic_add_unless(&EXT4_SB(sb)->s_lock_busy, -1, 0);
	else {
		/*
		 * The lock is busy, so bump the contention counter,
		 * and then wait on the spin lock.
		 */
		atomic_add_unless(&EXT4_SB(sb)->s_lock_busy, 1,
				  EXT4_MAX_CONTENTION);
		spin_lock(lock);
	}
3022 3023 3024 3025 3026
}

static inline void ext4_unlock_group(struct super_block *sb,
					ext4_group_t group)
{
3027
	spin_unlock(ext4_group_lock_ptr(sb, group));
3028 3029
}

3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042
/*
 * Block validity checking
 */
#define ext4_check_indirect_blockref(inode, bh)				\
	ext4_check_blockref(__func__, __LINE__, inode,			\
			    (__le32 *)(bh)->b_data,			\
			    EXT4_ADDR_PER_BLOCK((inode)->i_sb))

#define ext4_ind_check_inode(inode)					\
	ext4_check_blockref(__func__, __LINE__, inode,			\
			    EXT4_I(inode)->i_data,			\
			    EXT4_NDIR_BLOCKS)

3043 3044 3045 3046 3047
/*
 * Inodes and files operations
 */

/* dir.c */
3048
extern const struct file_operations ext4_dir_operations;
3049 3050

/* file.c */
3051
extern const struct inode_operations ext4_file_inode_operations;
3052
extern const struct file_operations ext4_file_operations;
3053
extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
3054

3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084
/* inline.c */
extern int ext4_get_max_inline_size(struct inode *inode);
extern int ext4_find_inline_data_nolock(struct inode *inode);
extern int ext4_init_inline_data(handle_t *handle, struct inode *inode,
				 unsigned int len);
extern int ext4_destroy_inline_data(handle_t *handle, struct inode *inode);

extern int ext4_readpage_inline(struct inode *inode, struct page *page);
extern int ext4_try_to_write_inline_data(struct address_space *mapping,
					 struct inode *inode,
					 loff_t pos, unsigned len,
					 unsigned flags,
					 struct page **pagep);
extern int ext4_write_inline_data_end(struct inode *inode,
				      loff_t pos, unsigned len,
				      unsigned copied,
				      struct page *page);
extern struct buffer_head *
ext4_journalled_write_inline_data(struct inode *inode,
				  unsigned len,
				  struct page *page);
extern int ext4_da_write_inline_data_begin(struct address_space *mapping,
					   struct inode *inode,
					   loff_t pos, unsigned len,
					   unsigned flags,
					   struct page **pagep,
					   void **fsdata);
extern int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos,
					 unsigned len, unsigned copied,
					 struct page *page);
3085 3086
extern int ext4_try_add_inline_entry(handle_t *handle,
				     struct ext4_filename *fname,
3087
				     struct inode *dir, struct inode *inode);
3088 3089 3090 3091
extern int ext4_try_create_inline_dir(handle_t *handle,
				      struct inode *parent,
				      struct inode *inode);
extern int ext4_read_inline_dir(struct file *filp,
A
Al Viro 已提交
3092
				struct dir_context *ctx,
3093
				int *has_inline_data);
3094 3095 3096 3097 3098
extern int htree_inlinedir_to_tree(struct file *dir_file,
				   struct inode *dir, ext4_lblk_t block,
				   struct dx_hash_info *hinfo,
				   __u32 start_hash, __u32 start_minor_hash,
				   int *has_inline_data);
3099
extern struct buffer_head *ext4_find_inline_entry(struct inode *dir,
3100
					struct ext4_filename *fname,
3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114
					const struct qstr *d_name,
					struct ext4_dir_entry_2 **res_dir,
					int *has_inline_data);
extern int ext4_delete_inline_entry(handle_t *handle,
				    struct inode *dir,
				    struct ext4_dir_entry_2 *de_del,
				    struct buffer_head *bh,
				    int *has_inline_data);
extern int empty_inline_dir(struct inode *dir, int *has_inline_data);
extern struct buffer_head *ext4_get_first_inline_block(struct inode *inode,
					struct ext4_dir_entry_2 **parent_de,
					int *retval);
extern int ext4_inline_data_fiemap(struct inode *inode,
				   struct fiemap_extent_info *fieinfo,
3115
				   int *has_inline, __u64 start, __u64 len);
3116 3117 3118 3119 3120 3121 3122
extern int ext4_try_to_evict_inline_data(handle_t *handle,
					 struct inode *inode,
					 int needed);
extern void ext4_inline_data_truncate(struct inode *inode, int *has_inline);

extern int ext4_convert_inline_data(struct inode *inode);

3123 3124 3125 3126 3127 3128
static inline int ext4_has_inline_data(struct inode *inode)
{
	return ext4_test_inode_flag(inode, EXT4_INODE_INLINE_DATA) &&
	       EXT4_I(inode)->i_inline_off;
}

3129
/* namei.c */
3130 3131
extern const struct inode_operations ext4_dir_inode_operations;
extern const struct inode_operations ext4_special_inode_operations;
3132
extern struct dentry *ext4_get_parent(struct dentry *child);
3133 3134 3135 3136
extern struct ext4_dir_entry_2 *ext4_init_dot_dotdot(struct inode *inode,
				 struct ext4_dir_entry_2 *de,
				 int blocksize, int csum_size,
				 unsigned int parent_ino, int dotdot_real_len);
3137 3138 3139 3140 3141
extern void initialize_dirent_tail(struct ext4_dir_entry_tail *t,
				   unsigned int blocksize);
extern int ext4_handle_dirty_dirent_node(handle_t *handle,
					 struct inode *inode,
					 struct buffer_head *bh);
3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155
#define S_SHIFT 12
static unsigned char ext4_type_by_mode[S_IFMT >> S_SHIFT] = {
	[S_IFREG >> S_SHIFT]	= EXT4_FT_REG_FILE,
	[S_IFDIR >> S_SHIFT]	= EXT4_FT_DIR,
	[S_IFCHR >> S_SHIFT]	= EXT4_FT_CHRDEV,
	[S_IFBLK >> S_SHIFT]	= EXT4_FT_BLKDEV,
	[S_IFIFO >> S_SHIFT]	= EXT4_FT_FIFO,
	[S_IFSOCK >> S_SHIFT]	= EXT4_FT_SOCK,
	[S_IFLNK >> S_SHIFT]	= EXT4_FT_SYMLINK,
};

static inline void ext4_set_de_type(struct super_block *sb,
				struct ext4_dir_entry_2 *de,
				umode_t mode) {
3156
	if (ext4_has_feature_filetype(sb))
3157 3158 3159
		de->file_type = ext4_type_by_mode[(mode & S_IFMT)>>S_SHIFT];
}

3160 3161 3162 3163
/* readpages.c */
extern int ext4_mpage_readpages(struct address_space *mapping,
				struct list_head *pages, struct page *page,
				unsigned nr_pages);
3164 3165

/* symlink.c */
3166
extern const struct inode_operations ext4_encrypted_symlink_inode_operations;
3167 3168
extern const struct inode_operations ext4_symlink_inode_operations;
extern const struct inode_operations ext4_fast_symlink_inode_operations;
3169

3170 3171
/* sysfs.c */
extern int ext4_register_sysfs(struct super_block *sb);
3172
extern void ext4_unregister_sysfs(struct super_block *sb);
3173 3174 3175
extern int __init ext4_init_sysfs(void);
extern void ext4_exit_sysfs(void);

3176 3177 3178
/* block_validity */
extern void ext4_release_system_zone(struct super_block *sb);
extern int ext4_setup_system_zone(struct super_block *sb);
3179 3180
extern int __init ext4_init_system_zone(void);
extern void ext4_exit_system_zone(void);
3181 3182 3183
extern int ext4_data_block_valid(struct ext4_sb_info *sbi,
				 ext4_fsblk_t start_blk,
				 unsigned int count);
3184 3185
extern int ext4_check_blockref(const char *, unsigned int,
			       struct inode *, __le32 *, unsigned int);
3186

A
Alex Tomas 已提交
3187
/* extents.c */
3188 3189 3190
struct ext4_ext_path;
struct ext4_extent;

Z
Zheng Liu 已提交
3191 3192 3193 3194 3195 3196
/*
 * Maximum number of logical blocks in a file; ext4_extent's ee_block is
 * __le32.
 */
#define EXT_MAX_BLOCKS	0xffffffff

A
Alex Tomas 已提交
3197 3198
extern int ext4_ext_tree_init(handle_t *handle, struct inode *);
extern int ext4_ext_writepage_trans_blocks(struct inode *, int);
3199
extern int ext4_ext_index_trans_blocks(struct inode *inode, int extents);
3200 3201
extern int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
			       struct ext4_map_blocks *map, int flags);
T
Theodore Ts'o 已提交
3202
extern void ext4_ext_truncate(handle_t *, struct inode *);
T
Theodore Ts'o 已提交
3203 3204
extern int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
				 ext4_lblk_t end);
A
Alex Tomas 已提交
3205 3206
extern void ext4_ext_init(struct super_block *);
extern void ext4_ext_release(struct super_block *);
3207
extern long ext4_fallocate(struct file *file, int mode, loff_t offset,
A
Amit Arora 已提交
3208
			  loff_t len);
3209 3210
extern int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode,
					  loff_t offset, ssize_t len);
3211 3212
extern int ext4_map_blocks(handle_t *handle, struct inode *inode,
			   struct ext4_map_blocks *map, int flags);
3213 3214 3215 3216 3217 3218 3219 3220 3221
extern int ext4_ext_calc_metadata_amount(struct inode *inode,
					 ext4_lblk_t lblocks);
extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode,
						   int num,
						   struct ext4_ext_path *path);
extern int ext4_can_extents_be_merged(struct inode *inode,
				      struct ext4_extent *ex1,
				      struct ext4_extent *ex2);
extern int ext4_ext_insert_extent(handle_t *, struct inode *,
3222
				  struct ext4_ext_path **,
3223
				  struct ext4_extent *, int);
3224 3225 3226
extern struct ext4_ext_path *ext4_find_extent(struct inode *, ext4_lblk_t,
					      struct ext4_ext_path **,
					      int flags);
3227 3228
extern void ext4_ext_drop_refs(struct ext4_ext_path *);
extern int ext4_ext_check_inode(struct inode *inode);
3229 3230 3231
extern int ext4_find_delalloc_range(struct inode *inode,
				    ext4_lblk_t lblk_start,
				    ext4_lblk_t lblk_end);
3232
extern int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk);
3233
extern ext4_lblk_t ext4_ext_next_allocated_block(struct ext4_ext_path *path);
A
Aneesh Kumar K.V 已提交
3234 3235
extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
			__u64 start, __u64 len);
3236
extern int ext4_ext_precache(struct inode *inode);
3237
extern int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len);
3238
extern int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len);
3239 3240 3241 3242
extern int ext4_swap_extents(handle_t *handle, struct inode *inode1,
				struct inode *inode2, ext4_lblk_t lblk1,
			     ext4_lblk_t lblk2,  ext4_lblk_t count,
			     int mark_unwritten,int *err);
3243

3244
/* move_extent.c */
3245 3246 3247 3248
extern void ext4_double_down_write_data_sem(struct inode *first,
					    struct inode *second);
extern void ext4_double_up_write_data_sem(struct inode *orig_inode,
					  struct inode *donor_inode);
3249 3250 3251 3252
extern int ext4_move_extents(struct file *o_filp, struct file *d_filp,
			     __u64 start_orig, __u64 start_donor,
			     __u64 len, __u64 *moved_len);

3253
/* page-io.c */
3254 3255
extern int __init ext4_init_pageio(void);
extern void ext4_exit_pageio(void);
3256
extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags);
J
Jan Kara 已提交
3257 3258 3259 3260 3261
extern ext4_io_end_t *ext4_get_io_end(ext4_io_end_t *io_end);
extern int ext4_put_io_end(ext4_io_end_t *io_end);
extern void ext4_put_io_end_defer(ext4_io_end_t *io_end);
extern void ext4_io_submit_init(struct ext4_io_submit *io,
				struct writeback_control *wbc);
3262
extern void ext4_end_io_rsv_work(struct work_struct *work);
3263 3264 3265 3266
extern void ext4_io_submit(struct ext4_io_submit *io);
extern int ext4_bio_write_page(struct ext4_io_submit *io,
			       struct page *page,
			       int len,
3267 3268
			       struct writeback_control *wbc,
			       bool keep_towrite);
A
Aneesh Kumar K.V 已提交
3269

3270 3271 3272
/* mmp.c */
extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);

3273
/*
3274
 * Add new method to test whether block and inode bitmaps are properly
3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289
 * initialized. With uninit_bg reading the block from disk is not enough
 * to mark the bitmap uptodate. We need to also zero-out the bitmap
 */
#define BH_BITMAP_UPTODATE BH_JBDPrivateStart

static inline int bitmap_uptodate(struct buffer_head *bh)
{
	return (buffer_uptodate(bh) &&
			test_bit(BH_BITMAP_UPTODATE, &(bh)->b_state));
}
static inline void set_bitmap_uptodate(struct buffer_head *bh)
{
	set_bit(BH_BITMAP_UPTODATE, &(bh)->b_state);
}

3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304
/*
 * Disable DIO read nolock optimization, so new dioreaders will be forced
 * to grab i_mutex
 */
static inline void ext4_inode_block_unlocked_dio(struct inode *inode)
{
	ext4_set_inode_state(inode, EXT4_STATE_DIOREAD_LOCK);
	smp_mb();
}
static inline void ext4_inode_resume_unlocked_dio(struct inode *inode)
{
	smp_mb();
	ext4_clear_inode_state(inode, EXT4_STATE_DIOREAD_LOCK);
}

3305 3306
#define in_range(b, first, len)	((b) >= (first) && (b) <= (first) + (len) - 1)

3307 3308 3309 3310 3311 3312
/* For ioend & aio unwritten conversion wait queues */
#define EXT4_WQ_HASH_SZ		37
#define ext4_ioend_wq(v)   (&ext4__ioend_wq[((unsigned long)(v)) %\
					    EXT4_WQ_HASH_SZ])
extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];

3313 3314 3315 3316
#define EXT4_RESIZING	0
extern int ext4_resize_begin(struct super_block *sb);
extern void ext4_resize_end(struct super_block *sb);

3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337
static inline void ext4_set_io_unwritten_flag(struct inode *inode,
					      struct ext4_io_end *io_end)
{
	if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
		io_end->flag |= EXT4_IO_END_UNWRITTEN;
		atomic_inc(&EXT4_I(inode)->i_unwritten);
	}
}

static inline void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end)
{
	struct inode *inode = io_end->inode;

	if (io_end->flag & EXT4_IO_END_UNWRITTEN) {
		io_end->flag &= ~EXT4_IO_END_UNWRITTEN;
		/* Wake up anyone waiting on unwritten extent conversion */
		if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten))
			wake_up_all(ext4_ioend_wq(inode));
	}
}

3338 3339 3340 3341 3342 3343 3344
static inline bool ext4_aligned_io(struct inode *inode, loff_t off, loff_t len)
{
	int blksize = 1 << inode->i_blkbits;

	return IS_ALIGNED(off, blksize) && IS_ALIGNED(len, blksize);
}

3345 3346
#endif	/* __KERNEL__ */

3347 3348 3349
#define EFSBADCRC	EBADMSG		/* Bad CRC detected */
#define EFSCORRUPTED	EUCLEAN		/* Filesystem is corrupted */

3350
#endif	/* _EXT4_H */