ext4.h 96.8 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 29 30 31
#include <linux/timer.h>
#include <linux/wait.h>
#include <linux/blockgroup_lock.h>
#include <linux/percpu_counter.h>
32
#include <crypto/hash.h>
33 34 35
#ifdef __KERNEL__
#include <linux/compat.h>
#endif
36

37
/*
S
Shen Feng 已提交
38
 * The fourth extended filesystem constants/structures
39 40 41
 */

/*
42
 * Define EXT4FS_DEBUG to produce debug messages
43
 */
44
#undef EXT4FS_DEBUG
45 46 47 48

/*
 * Debug code
 */
49 50
#ifdef EXT4FS_DEBUG
#define ext4_debug(f, a...)						\
51
	do {								\
52
		printk(KERN_DEBUG "EXT4-fs DEBUG (%s, %d): %s:",	\
53
			__FILE__, __LINE__, __func__);			\
54
		printk(KERN_DEBUG f, ## a);				\
55 56
	} while (0)
#else
57
#define ext4_debug(fmt, ...)	no_printk(fmt, ##__VA_ARGS__)
58 59
#endif

60 61 62 63 64 65 66 67 68 69
/*
 * 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

70
#define EXT4_ERROR_INODE(inode, fmt, a...) \
71 72 73 74
	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)
75

76 77
#define EXT4_ERROR_FILE(file, block, fmt, a...)				\
	ext4_error_file((file), __func__, __LINE__, (block), (fmt), ## a)
78

79 80 81 82 83 84 85 86 87 88 89 90
/* 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;

91
/*
92
 * Flags used in mballoc's allocation_context flags field.
93 94 95 96
 *
 * Also used to show what's going on for debugging purposes when the
 * flag field is exported via the traceport interface
 */
97

98
/* prefer goal again. length */
99
#define EXT4_MB_HINT_MERGE		0x0001
100
/* blocks already reserved */
101
#define EXT4_MB_HINT_RESERVED		0x0002
102
/* metadata is being allocated */
103
#define EXT4_MB_HINT_METADATA		0x0004
104
/* first blocks in the file */
105
#define EXT4_MB_HINT_FIRST		0x0008
106
/* search for the best chunk */
107
#define EXT4_MB_HINT_BEST		0x0010
108
/* data is being allocated */
109
#define EXT4_MB_HINT_DATA		0x0020
110
/* don't preallocate (for tails) */
111
#define EXT4_MB_HINT_NOPREALLOC		0x0040
112
/* allocate for locality group */
113
#define EXT4_MB_HINT_GROUP_ALLOC	0x0080
114
/* allocate goal blocks or none */
115
#define EXT4_MB_HINT_GOAL_ONLY		0x0100
116
/* goal is meaningful */
117
#define EXT4_MB_HINT_TRY_GOAL		0x0200
118
/* blocks already pre-reserved by delayed allocation */
119
#define EXT4_MB_DELALLOC_RESERVED	0x0400
120 121
/* We are doing stream allocation */
#define EXT4_MB_STREAM_ALLOC		0x0800
122 123
/* Use reserved root blocks if needed */
#define EXT4_MB_USE_ROOT_BLOCKS		0x1000
L
Lukas Czerner 已提交
124 125
/* Use blocks from reserved pool */
#define EXT4_MB_USE_RESERVED		0x2000
126 127 128 129

struct ext4_allocation_request {
	/* target inode for block we're allocating */
	struct inode *inode;
130 131
	/* how many blocks we want to allocate */
	unsigned int len;
132 133 134 135 136 137
	/* 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;
138 139 140 141 142
	/* 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 */
143 144
	ext4_fsblk_t pright;
	/* flags. see above EXT4_MB_HINT_* */
145
	unsigned int flags;
146 147
};

148 149 150 151 152 153 154 155 156 157 158 159
/*
 * 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_UNINIT		(1 << BH_Uninit)
160 161 162 163 164 165 166 167
/* Sometimes (in the bigalloc case, from ext4_da_get_block_prep) the caller of
 * ext4_map_blocks wants to know whether or not the underlying cluster has
 * already been accounted for. EXT4_MAP_FROM_CLUSTER conveys to the caller that
 * the requested mapping was from previously mapped (or delayed allocated)
 * cluster. We use BH_AllocFromCluster only for this flag. BH_AllocFromCluster
 * should never appear on buffer_head's state flags.
 */
#define EXT4_MAP_FROM_CLUSTER	(1 << BH_AllocFromCluster)
168 169
#define EXT4_MAP_FLAGS		(EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
				 EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY |\
170
				 EXT4_MAP_UNINIT | EXT4_MAP_FROM_CLUSTER)
171 172 173 174 175 176 177 178

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

179 180 181 182
/*
 * Flags for ext4_io_end->flags
 */
#define	EXT4_IO_END_UNWRITTEN	0x0001
183
#define EXT4_IO_END_DIRECT	0x0002
184

185
/*
186 187
 * For converting uninitialized extents on a work queue. 'handle' is used for
 * buffered writeback.
188
 */
189
typedef struct ext4_io_end {
190
	struct list_head	list;		/* per-file finished IO list */
191 192
	handle_t		*handle;	/* handle reserved for extent
						 * conversion */
193
	struct inode		*inode;		/* file being written to */
194 195
	struct bio		*bio;		/* Linked list of completed
						 * bios covering the extent */
196
	unsigned int		flag;		/* unwritten or not */
197 198
	loff_t			offset;		/* offset in the file */
	ssize_t			size;		/* size of the extent */
199 200
	struct kiocb		*iocb;		/* iocb struct for AIO */
	int			result;		/* error value for AIO */
J
Jan Kara 已提交
201
	atomic_t		count;		/* reference counter */
202 203
} ext4_io_end_t;

204 205 206 207 208 209 210
struct ext4_io_submit {
	int			io_op;
	struct bio		*io_bio;
	ext4_io_end_t		*io_end;
	sector_t		io_next_block;
};

211 212 213
/*
 * Special inodes numbers
 */
214 215
#define	EXT4_BAD_INO		 1	/* Bad blocks inode */
#define EXT4_ROOT_INO		 2	/* Root inode */
216 217
#define EXT4_USR_QUOTA_INO	 3	/* User quota inode */
#define EXT4_GRP_QUOTA_INO	 4	/* Group quota inode */
218 219 220 221
#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 */
222

223 224
/* First non-reserved inode for old ext4 filesystems */
#define EXT4_GOOD_OLD_FIRST_INO	11
225 226 227 228

/*
 * Maximal count of links to a file
 */
229
#define EXT4_LINK_MAX		65000
230 231 232 233

/*
 * Macro-instructions used to manage several block sizes
 */
234
#define EXT4_MIN_BLOCK_SIZE		1024
235 236
#define	EXT4_MAX_BLOCK_SIZE		65536
#define EXT4_MIN_BLOCK_LOG_SIZE		10
237
#define EXT4_MAX_BLOCK_LOG_SIZE		16
238
#ifdef __KERNEL__
239
# define EXT4_BLOCK_SIZE(s)		((s)->s_blocksize)
240
#else
241
# define EXT4_BLOCK_SIZE(s)		(EXT4_MIN_BLOCK_SIZE << (s)->s_log_block_size)
242
#endif
243
#define	EXT4_ADDR_PER_BLOCK(s)		(EXT4_BLOCK_SIZE(s) / sizeof(__u32))
244 245
#define EXT4_CLUSTER_SIZE(s)		(EXT4_BLOCK_SIZE(s) << \
					 EXT4_SB(s)->s_cluster_bits)
246
#ifdef __KERNEL__
247
# define EXT4_BLOCK_SIZE_BITS(s)	((s)->s_blocksize_bits)
248
# define EXT4_CLUSTER_BITS(s)		(EXT4_SB(s)->s_cluster_bits)
249
#else
250
# define EXT4_BLOCK_SIZE_BITS(s)	((s)->s_log_block_size + 10)
251 252
#endif
#ifdef __KERNEL__
253 254 255
#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)
256
#else
257 258
#define EXT4_INODE_SIZE(s)	(((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \
				 EXT4_GOOD_OLD_INODE_SIZE : \
259
				 (s)->s_inode_size)
260 261
#define EXT4_FIRST_INO(s)	(((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \
				 EXT4_GOOD_OLD_FIRST_INO : \
262 263
				 (s)->s_first_ino)
#endif
A
Amit Arora 已提交
264
#define EXT4_BLOCK_ALIGN(size, blkbits)		ALIGN((size), (1 << (blkbits)))
265

266 267 268 269 270 271 272 273
/* 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)

274 275 276
/*
 * Structure of a blocks group descriptor
 */
277
struct ext4_group_desc
278
{
279
	__le32	bg_block_bitmap_lo;	/* Blocks bitmap block */
280 281
	__le32	bg_inode_bitmap_lo;	/* Inodes bitmap block */
	__le32	bg_inode_table_lo;	/* Inodes table block */
282 283 284
	__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
285
	__le16	bg_flags;		/* EXT4_BG_flags (INODE_UNINIT, etc) */
286 287 288
	__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 */
289
	__le16  bg_itable_unused_lo;	/* Unused inodes count */
A
Andreas Dilger 已提交
290
	__le16  bg_checksum;		/* crc16(sb_uuid+group+desc) */
291 292 293
	__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 */
294 295 296
	__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 */
297
	__le16  bg_itable_unused_hi;    /* Unused inodes count MSB */
298 299 300 301
	__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;
302 303
};

304 305 306 307 308 309 310
#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))

311 312 313 314 315
/*
 * Structure of a flex block group info
 */

struct flex_groups {
316 317 318
	atomic64_t	free_clusters;
	atomic_t	free_inodes;
	atomic_t	used_dirs;
319 320
};

A
Andreas Dilger 已提交
321 322 323 324
#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 */

325 326 327
/*
 * Macro-instructions used to manage group descriptors
 */
328
#define EXT4_MIN_DESC_SIZE		32
329
#define EXT4_MIN_DESC_SIZE_64BIT	64
330 331
#define	EXT4_MAX_DESC_SIZE		EXT4_MIN_BLOCK_SIZE
#define EXT4_DESC_SIZE(s)		(EXT4_SB(s)->s_desc_size)
332
#ifdef __KERNEL__
333
# define EXT4_BLOCKS_PER_GROUP(s)	(EXT4_SB(s)->s_blocks_per_group)
334
# define EXT4_CLUSTERS_PER_GROUP(s)	(EXT4_SB(s)->s_clusters_per_group)
335 336 337
# 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)
338
#else
339
# define EXT4_BLOCKS_PER_GROUP(s)	((s)->s_blocks_per_group)
340
# define EXT4_DESC_PER_BLOCK(s)		(EXT4_BLOCK_SIZE(s) / EXT4_DESC_SIZE(s))
341
# define EXT4_INODES_PER_GROUP(s)	((s)->s_inodes_per_group)
342 343 344 345 346
#endif

/*
 * Constants relative to the data blocks
 */
347 348 349 350 351
#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)
352 353 354 355

/*
 * Inode flags
 */
356 357 358 359 360 361 362 363
#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 */
364
/* Reserved for compression usage... */
365 366 367 368
#define EXT4_DIRTY_FL			0x00000100
#define EXT4_COMPRBLK_FL		0x00000200 /* One or more compressed clusters */
#define EXT4_NOCOMPR_FL			0x00000400 /* Don't compress */
#define EXT4_ECOMPR_FL			0x00000800 /* Compression error */
369
/* End compression flags --- maybe not all used */
370 371 372 373 374 375
#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
376
#define EXT4_HUGE_FILE_FL               0x00040000 /* Set to each huge file */
A
Alex Tomas 已提交
377
#define EXT4_EXTENTS_FL			0x00080000 /* Inode uses extents */
378
#define EXT4_EA_INODE_FL	        0x00200000 /* Inode used for large EA */
379
#define EXT4_EOFBLOCKS_FL		0x00400000 /* Blocks allocated beyond EOF */
380
#define EXT4_INLINE_DATA_FL		0x10000000 /* Inode has inline data. */
A
Aneesh Kumar K.V 已提交
381
#define EXT4_RESERVED_FL		0x80000000 /* reserved for ext4 lib */
382

383
#define EXT4_FL_USER_VISIBLE		0x004BDFFF /* User visible flags */
384
#define EXT4_FL_USER_MODIFIABLE		0x004380FF /* User modifiable flags */
385

386 387
/* Flags that should be inherited by new inodes from their parent. */
#define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\
388
			   EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
389 390 391
			   EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\
			   EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL)

392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408
/* 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;
}

409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436
/*
 * 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 */
	EXT4_INODE_ECOMPR	= 11,	/* Compression error */
/* 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 */
437
	EXT4_INODE_INLINE_DATA	= 28,	/* Data in inode. */
438 439 440 441
	EXT4_INODE_RESERVED	= 31,	/* reserved for ext4 lib */
};

/*
442 443 444 445 446 447 448 449 450
 * 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.
451 452 453
 *
 * It's not paranoia if the Murphy's Law really *is* out to get you.  :-)
 */
454 455 456
#define TEST_FLAG_VALUE(FLAG) (EXT4_##FLAG##_FL == (1 << EXT4_INODE_##FLAG))
#define CHECK_FLAG_VALUE(FLAG) BUILD_BUG_ON(!TEST_FLAG_VALUE(FLAG))

457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480
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);
	CHECK_FLAG_VALUE(ECOMPR);
	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);
481
	CHECK_FLAG_VALUE(INLINE_DATA);
482 483 484
	CHECK_FLAG_VALUE(RESERVED);
}

485
/* Used to pass group descriptor data when online resize is done */
486
struct ext4_new_group_input {
D
Dave Kleikamp 已提交
487 488 489 490 491 492
	__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 */
493 494 495
	__u16 unused;
};

496 497 498 499 500 501 502 503 504 505 506 507
#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

508 509
/* The struct ext4_new_group_input in kernel space, with free_blocks_count */
struct ext4_new_group_data {
510
	__u32 group;
L
Laurent Vivier 已提交
511 512 513
	__u64 block_bitmap;
	__u64 inode_bitmap;
	__u64 inode_table;
514 515 516 517 518 519
	__u32 blocks_count;
	__u16 reserved_blocks;
	__u16 unused;
	__u32 free_blocks_count;
};

520 521 522 523 524 525 526 527
/* 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
528
/*
529
 * Flags used by ext4_map_blocks()
A
Amit Arora 已提交
530
 */
531 532
	/* Allocate any needed blocks and/or convert an unitialized
	   extent to be an initialized ext4 */
533
#define EXT4_GET_BLOCKS_CREATE			0x0001
534
	/* Request the creation of an unitialized extent */
535
#define EXT4_GET_BLOCKS_UNINIT_EXT		0x0002
536 537
#define EXT4_GET_BLOCKS_CREATE_UNINIT_EXT	(EXT4_GET_BLOCKS_UNINIT_EXT|\
						 EXT4_GET_BLOCKS_CREATE)
L
Lukas Czerner 已提交
538 539
	/* Caller is from the delayed allocation writeout path
	 * finally doing the actual allocation of delayed blocks */
540
#define EXT4_GET_BLOCKS_DELALLOC_RESERVE	0x0004
541 542 543
	/* caller is from the direct IO path, request to creation of an
	unitialized extents if not allocated, split the uninitialized
	extent if blocks has been preallocated already*/
544
#define EXT4_GET_BLOCKS_PRE_IO			0x0008
545
#define EXT4_GET_BLOCKS_CONVERT			0x0010
546
#define EXT4_GET_BLOCKS_IO_CREATE_EXT		(EXT4_GET_BLOCKS_PRE_IO|\
547
					 EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
548 549
	/* Convert extent to initialized after IO complete */
#define EXT4_GET_BLOCKS_IO_CONVERT_EXT		(EXT4_GET_BLOCKS_CONVERT|\
550
					 EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
L
Lukas Czerner 已提交
551 552 553
	/* 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
554 555
	/* Don't normalize allocation size (used for fallocate) */
#define EXT4_GET_BLOCKS_NO_NORMALIZE		0x0040
556 557
	/* Request will not result in inode size update (user for fallocate) */
#define EXT4_GET_BLOCKS_KEEP_SIZE		0x0080
558 559
	/* Do not take i_data_sem locking in ext4_map_blocks */
#define EXT4_GET_BLOCKS_NO_LOCK			0x0100
560 561
	/* Do not put hole in extent cache */
#define EXT4_GET_BLOCKS_NO_PUT_HOLE		0x0200
562

563 564 565 566 567
/*
 * Flags used by ext4_free_blocks
 */
#define EXT4_FREE_BLOCKS_METADATA	0x0001
#define EXT4_FREE_BLOCKS_FORGET		0x0002
568
#define EXT4_FREE_BLOCKS_VALIDATED	0x0004
569
#define EXT4_FREE_BLOCKS_NO_QUOT_UPDATE	0x0008
570 571
#define EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER	0x0010
#define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER	0x0020
572

573 574 575
/*
 * ioctl commands
 */
576 577 578 579 580 581 582 583
#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
584 585 586
#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)
587
 /* note ioctl 10 reserved for an early version of the FIEMAP ioctl */
T
Theodore Ts'o 已提交
588
 /* note ioctl 11 reserved for filesystem-independent FIEMAP ioctl */
589
#define EXT4_IOC_ALLOC_DA_BLKS		_IO('f', 12)
590
#define EXT4_IOC_MOVE_EXT		_IOWR('f', 15, struct move_extent)
591
#define EXT4_IOC_RESIZE_FS		_IOW('f', 16, __u64)
592
#define EXT4_IOC_SWAP_BOOT		_IO('f', 17)
593

594
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
595 596 597
/*
 * ioctl commands in 32 bit emulation
 */
598 599 600 601 602 603 604
#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)
605
#define EXT4_IOC32_GROUP_ADD		_IOW('f', 8, struct compat_ext4_new_group_input)
606 607
#define EXT4_IOC32_GETVERSION_OLD	FS_IOC32_GETVERSION
#define EXT4_IOC32_SETVERSION_OLD	FS_IOC32_SETVERSION
608
#endif
609

610
/* Max physical block we can address w/o extents */
611 612
#define EXT4_MAX_BLOCK_FILE_PHYS	0xFFFFFFFF

613 614 615
/*
 * Structure of an inode on the disk
 */
616
struct ext4_inode {
617 618
	__le16	i_mode;		/* File mode */
	__le16	i_uid;		/* Low 16 bits of Owner Uid */
619
	__le32	i_size_lo;	/* Size in bytes */
620
	__le32	i_atime;	/* Access time */
K
Kalpak Shah 已提交
621
	__le32	i_ctime;	/* Inode Change time */
622 623 624 625
	__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 */
626
	__le32	i_blocks_lo;	/* Blocks count */
627 628 629
	__le32	i_flags;	/* File flags */
	union {
		struct {
630
			__le32  l_i_version;
631 632 633 634 635 636 637 638
		} linux1;
		struct {
			__u32  h_i_translator;
		} hurd1;
		struct {
			__u32  m_i_reserved1;
		} masix1;
	} osd1;				/* OS dependent 1 */
639
	__le32	i_block[EXT4_N_BLOCKS];/* Pointers to blocks */
640
	__le32	i_generation;	/* File version (for NFS) */
641
	__le32	i_file_acl_lo;	/* File ACL */
642
	__le32	i_size_high;
643
	__le32	i_obso_faddr;	/* Obsoleted fragment address */
644 645
	union {
		struct {
646
			__le16	l_i_blocks_high; /* were l_i_reserved1 */
B
Badari Pulavarty 已提交
647
			__le16	l_i_file_acl_high;
D
Dave Kleikamp 已提交
648
			__le16	l_i_uid_high;	/* these 2 fields */
649
			__le16	l_i_gid_high;	/* were reserved2[0] */
650 651
			__le16	l_i_checksum_lo;/* crc32c(uuid+inum+inode) LE */
			__le16	l_i_reserved;
652 653
		} linux2;
		struct {
654
			__le16	h_i_reserved1;	/* Obsoleted fragment number/size which are removed in ext4 */
655 656 657 658 659 660
			__u16	h_i_mode_high;
			__u16	h_i_uid_high;
			__u16	h_i_gid_high;
			__u32	h_i_author;
		} hurd2;
		struct {
661
			__le16	h_i_reserved1;	/* Obsoleted fragment number/size which are removed in ext4 */
B
Badari Pulavarty 已提交
662
			__le16	m_i_file_acl_high;
663 664 665 666
			__u32	m_i_reserved2[2];
		} masix2;
	} osd2;				/* OS dependent 2 */
	__le16	i_extra_isize;
667
	__le16	i_checksum_hi;	/* crc32c(uuid+inum+inode) BE */
K
Kalpak Shah 已提交
668 669 670 671 672
	__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) */
673
	__le32  i_version_hi;	/* high 32 bits for 64-bit version */
674 675
};

676 677 678 679 680 681 682 683
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 */
};
684

K
Kalpak Shah 已提交
685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707
#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))			\

static inline __le32 ext4_encode_extra_time(struct timespec *time)
{
       return cpu_to_le32((sizeof(time->tv_sec) > 4 ?
708 709
			   (time->tv_sec >> 32) & EXT4_EPOCH_MASK : 0) |
                          ((time->tv_nsec << EXT4_EPOCH_BITS) & EXT4_NSEC_MASK));
K
Kalpak Shah 已提交
710 711 712 713 714 715 716
}

static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra)
{
       if (sizeof(time->tv_sec) > 4)
	       time->tv_sec |= (__u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK)
			       << 32;
717
       time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS;
K
Kalpak Shah 已提交
718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742
}

#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);	       \
743 744
	else								       \
		(inode)->xtime.tv_nsec = 0;				       \
K
Kalpak Shah 已提交
745 746 747 748 749 750 751 752 753 754
} 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);	       \
	if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra))	       \
		ext4_decode_extra_time(&(einode)->xtime,		       \
				       raw_inode->xtime ## _extra);	       \
755 756
	else								       \
		(einode)->xtime.tv_nsec = 0;				       \
K
Kalpak Shah 已提交
757 758
} while (0)

759 760
#define i_disk_version osd1.linux1.l_i_version

761 762
#if defined(__KERNEL__) || defined(__linux__)
#define i_reserved1	osd1.linux1.l_i_reserved1
B
Badari Pulavarty 已提交
763
#define i_file_acl_high	osd2.linux2.l_i_file_acl_high
764
#define i_blocks_high	osd2.linux2.l_i_blocks_high
765 766 767 768
#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
769
#define i_checksum_lo	osd2.linux2.l_i_checksum_lo
770 771 772 773 774 775 776 777 778 779 780

#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
781
#define i_file_acl_high	osd2.masix2.m_i_file_acl_high
782 783 784 785
#define i_reserved2	osd2.masix2.m_i_reserved2

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

786 787
#include "extents_status.h"

788 789 790 791 792 793
/*
 * fourth extended file system inode data in memory
 */
struct ext4_inode_info {
	__le32	i_data[15];	/* unconverted */
	__u32	i_dtime;
794
	ext4_fsblk_t	i_file_acl;
795 796 797 798 799 800 801 802 803

	/*
	 * 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;
804
	ext4_lblk_t	i_dir_start_lookup;
805
#if (BITS_PER_LONG < 64)
806
	unsigned long	i_state_flags;		/* Dynamic state flags */
807
#endif
808
	unsigned long	i_flags;
809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849

	/*
	 * 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;
	struct inode vfs_inode;
850
	struct jbd2_inode *jinode;
851 852 853 854 855 856 857 858 859 860 861

	/*
	 * 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;

862 863 864
	/* extents status tree */
	struct ext4_es_tree i_es_tree;
	rwlock_t i_es_lock;
865 866
	struct list_head i_es_lru;
	unsigned int i_es_lru_nr;	/* protected by i_es_lock */
867

868 869 870 871
	/* ialloc */
	ext4_group_t	i_last_alloc_group;

	/* allocation reservation info for delalloc */
872
	/* In case of bigalloc, these refer to clusters rather than blocks */
873 874 875
	unsigned int i_reserved_data_blocks;
	unsigned int i_reserved_meta_blocks;
	unsigned int i_allocated_meta_blocks;
876
	ext4_lblk_t i_da_metadata_calc_last_lblock;
877
	int i_da_metadata_calc_len;
878 879 880 881

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

882 883 884 885
	/* Indicate the inline data space. */
	u16 i_inline_off;
	u16 i_inline_size;

886 887 888 889
#ifdef CONFIG_QUOTA
	/* quota space reservation, managed internally by quota code */
	qsize_t i_reserved_quota;
#endif
890

891
	/* Lock protecting lists below */
892
	spinlock_t i_completed_io_lock;
893 894 895 896 897 898 899 900 901 902
	/*
	 * Completed IOs that need unwritten extents handling and have
	 * transaction reserved
	 */
	struct list_head i_rsv_conversion_list;
	/*
	 * Completed IOs that need unwritten extents handling and don't have
	 * transaction reserved
	 */
	struct list_head i_unrsv_conversion_list;
903
	atomic_t i_ioend_count;	/* Number of outstanding io_end structs */
904
	atomic_t i_unwritten; /* Nr. of inflight conversions pending */
905 906
	struct work_struct i_rsv_conversion_work;
	struct work_struct i_unrsv_conversion_work;
907 908

	spinlock_t i_block_reservation_lock;
909 910 911 912 913 914 915

	/*
	 * Transactions that contain inode's metadata needed to complete
	 * fsync and fdatasync, respectively.
	 */
	tid_t i_sync_tid;
	tid_t i_datasync_tid;
916 917 918

	/* Precomputed uuid+inum+igen checksum for seeding inode checksums */
	__u32 i_csum_seed;
919 920
};

921 922 923
/*
 * File system states
 */
924 925 926
#define	EXT4_VALID_FS			0x0001	/* Unmounted cleanly */
#define	EXT4_ERROR_FS			0x0002	/* Errors detected */
#define	EXT4_ORPHAN_FS			0x0004	/* Orphans being recovered */
927

928 929 930 931 932 933 934
/*
 * 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 */

935
/*
936
 * Mount flags set via mount options or defaults
937
 */
938 939 940 941 942
#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 */
943
#define EXT4_MOUNT_ERRORS_MASK		0x00070
944 945 946 947 948 949 950 951 952 953
#define EXT4_MOUNT_MINIX_DF		0x00080	/* Mimics the Minix statfs */
#define EXT4_MOUNT_NOLOAD		0x00100	/* Don't use existing journal*/
#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 */
954
#define EXT4_MOUNT_NO_AUTO_DA_ALLOC	0x10000	/* No auto delalloc mapping */
955 956 957 958
#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 */
959
#define EXT4_MOUNT_DIOREAD_NOLOCK	0x400000 /* Enable support for dio read nolocking */
960
#define EXT4_MOUNT_JOURNAL_CHECKSUM	0x800000 /* Journal checksums */
961
#define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT	0x1000000 /* Journal Async Commit */
962
#define EXT4_MOUNT_DELALLOC		0x8000000 /* Delalloc support */
963
#define EXT4_MOUNT_DATA_ERR_ABORT	0x10000000 /* Abort on file data write */
964
#define EXT4_MOUNT_BLOCK_VALIDITY	0x20000000 /* Block validity checking */
965
#define EXT4_MOUNT_DISCARD		0x40000000 /* Issue DISCARD requests */
966
#define EXT4_MOUNT_INIT_INODE_TABLE	0x80000000 /* Initialize uninitialized itables */
967

968 969 970 971 972
/*
 * 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.
 */
973 974
#define EXT4_MOUNT2_EXPLICIT_DELALLOC	0x00000001 /* User explicitly
						      specified delalloc */
975 976 977
#define EXT4_MOUNT2_STD_GROUP_SIZE	0x00000002 /* We have standard group
						      size of blocksize * 8
						      blocks */
978

979 980 981 982
#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
983 984
#define test_opt(sb, opt)		(EXT4_SB(sb)->s_mount_opt & \
					 EXT4_MOUNT_##opt)
985

986 987 988 989 990 991 992
#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)

993 994
#define ext4_test_and_set_bit		__test_and_set_bit_le
#define ext4_set_bit			__set_bit_le
995
#define ext4_set_bit_atomic		ext2_set_bit_atomic
996 997
#define ext4_test_and_clear_bit		__test_and_clear_bit_le
#define ext4_clear_bit			__clear_bit_le
998
#define ext4_clear_bit_atomic		ext2_clear_bit_atomic
A
Akinobu Mita 已提交
999 1000 1001
#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
1002

1003 1004
extern void ext4_set_bits(void *bm, int cur, int len);

1005 1006 1007
/*
 * Maximal mount counts between two filesystem checks
 */
1008 1009
#define EXT4_DFL_MAX_MNT_COUNT		20	/* Allow 20 mounts */
#define EXT4_DFL_CHECKINTERVAL		0	/* Don't use interval check */
1010 1011 1012 1013

/*
 * Behaviour when detecting errors
 */
1014 1015 1016 1017
#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
1018

1019 1020 1021
/* Metadata checksum algorithm codes */
#define EXT4_CRC32C_CHKSUM		1

1022 1023 1024
/*
 * Structure of the super block
 */
1025
struct ext4_super_block {
1026
/*00*/	__le32	s_inodes_count;		/* Inodes count */
1027
	__le32	s_blocks_count_lo;	/* Blocks count */
1028 1029
	__le32	s_r_blocks_count_lo;	/* Reserved blocks count */
	__le32	s_free_blocks_count_lo;	/* Free blocks count */
1030 1031 1032
/*10*/	__le32	s_free_inodes_count;	/* Free inodes count */
	__le32	s_first_data_block;	/* First Data Block */
	__le32	s_log_block_size;	/* Block size */
1033
	__le32	s_log_cluster_size;	/* Allocation cluster size */
1034
/*20*/	__le32	s_blocks_per_group;	/* # Blocks per group */
1035
	__le32	s_clusters_per_group;	/* # Clusters per group */
1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051
	__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 */
	/*
1052
	 * These fields are for EXT4_DYNAMIC_REV superblocks only.
1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064
	 *
	 * 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 */
1065
	__le16  s_inode_size;		/* size of inode structure */
1066 1067 1068 1069 1070 1071 1072 1073 1074 1075
	__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
1076
	 * happen if the EXT4_FEATURE_COMPAT_DIR_PREALLOC flag is on.
1077 1078 1079 1080 1081
	 */
	__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 */
	/*
1082
	 * Journaling support valid if EXT4_FEATURE_COMPAT_HAS_JOURNAL set.
1083 1084 1085 1086 1087 1088 1089
	 */
/*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 */
1090
	__u8	s_jnl_backup_type;
1091
	__le16  s_desc_size;		/* size of group descriptor */
L
Laurent Vivier 已提交
1092
/*100*/	__le32	s_default_mount_opts;
1093
	__le32	s_first_meta_bg;	/* First metablock block group */
L
Laurent Vivier 已提交
1094 1095 1096 1097 1098 1099
	__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
1100 1101 1102 1103
	__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 */
1104
	__le16  s_mmp_update_interval;  /* # seconds to wait in MMP checking */
A
Aneesh Kumar K.V 已提交
1105 1106
	__le64  s_mmp_block;            /* Block for multi-mount protection */
	__le32  s_raid_stripe_width;    /* blocks on all data disks (N*stride)*/
1107
	__u8	s_log_groups_per_flex;  /* FLEX_BG group size */
1108
	__u8	s_checksum_type;	/* metadata checksum algorithm used */
1109
	__le16  s_reserved_pad;
T
Theodore Ts'o 已提交
1110
	__le64	s_kbytes_written;	/* nr of lifetime kilobytes written */
1111 1112 1113 1114 1115 1116
	__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 */
1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128
#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 */
1129 1130
#define EXT4_S_ERR_END offsetof(struct ext4_super_block, s_mount_opts)
	__u8	s_mount_opts[64];
1131 1132 1133
	__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 */
1134 1135
	__le32	s_reserved[108];	/* Padding to the end of the block */
	__le32	s_checksum;		/* crc32c(superblock) */
1136 1137
};

1138 1139
#define EXT4_S_ERR_LEN (EXT4_S_ERR_END - EXT4_S_ERR_START)

1140
#ifdef __KERNEL__
1141 1142

/*
1143
 * run-time mount flags
1144 1145
 */
#define EXT4_MF_MNTDIR_SAMPLED	0x0001
1146
#define EXT4_MF_FS_ABORTED	0x0002	/* Fatal error detected */
1147

1148 1149 1150 1151 1152 1153 1154
/*
 * 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 */
1155
	unsigned long s_clusters_per_group; /* Number of clusters in a group */
1156 1157 1158 1159 1160
	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 */
1161
	ext4_group_t s_blockfile_groups;/* Groups acceptable for non-extent files */
1162
	unsigned long s_overhead;  /* # of fs overhead clusters */
1163 1164
	unsigned int s_cluster_ratio;	/* Number of blocks per cluster */
	unsigned int s_cluster_bits;	/* log2 of s_cluster_ratio */
1165 1166 1167 1168
	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;
1169
	unsigned int s_mount_opt;
1170
	unsigned int s_mount_opt2;
1171
	unsigned int s_mount_flags;
1172
	unsigned int s_def_mount_opt;
1173
	ext4_fsblk_t s_sb_block;
L
Lukas Czerner 已提交
1174
	atomic64_t s_resv_clusters;
1175 1176
	kuid_t s_resuid;
	kgid_t s_resgid;
1177 1178 1179 1180 1181 1182 1183
	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;
1184
	unsigned int s_inode_goal;
1185 1186 1187 1188 1189
	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 */
1190
	struct percpu_counter s_freeclusters_counter;
1191 1192
	struct percpu_counter s_freeinodes_counter;
	struct percpu_counter s_dirs_counter;
1193
	struct percpu_counter s_dirtyclusters_counter;
1194 1195 1196 1197
	struct blockgroup_lock *s_blockgroup_lock;
	struct proc_dir_entry *s_proc;
	struct kobject s_kobj;
	struct completion s_kobj_unregister;
1198
	struct super_block *s_sb;
1199 1200 1201 1202 1203

	/* Journaling */
	struct journal_s *s_journal;
	struct list_head s_orphan;
	struct mutex s_orphan_lock;
1204 1205
	unsigned long s_resize_flags;		/* Flags indicating if there
						   is a resizer */
1206 1207 1208 1209 1210 1211 1212 1213 1214
	unsigned long s_commit_interval;
	u32 s_max_batch_time;
	u32 s_min_batch_time;
	struct block_device *journal_bdev;
#ifdef CONFIG_QUOTA
	char *s_qf_names[MAXQUOTAS];		/* Names of quota files with journalled quota */
	int s_jquota_fmt;			/* Format of quota to use */
#endif
	unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */
1215
	struct rb_root system_blks;
1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232

#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;
1233
	unsigned int s_group_info_size;
1234 1235 1236 1237 1238 1239 1240 1241 1242

	/* 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;
1243
	unsigned int s_max_dir_size_kb;
1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261
	/* 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;
1262
	atomic_t s_lock_busy;
1263 1264

	/* locality groups */
1265
	struct ext4_locality_group __percpu *s_locality_groups;
1266 1267 1268 1269 1270

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

1271 1272 1273
	/* the size of zero-out chunk */
	unsigned int s_extent_max_zeroout_kb;

1274 1275
	unsigned int s_log_groups_per_flex;
	struct flex_groups *s_flex_groups;
1276
	ext4_group_t s_flex_groups_allocated;
1277

1278 1279 1280 1281
	/* workqueue for unreserved extent convertions (dio) */
	struct workqueue_struct *unrsv_conversion_wq;
	/* workqueue for reserved extent conversions (buffered io) */
	struct workqueue_struct *rsv_conversion_wq;
1282 1283 1284

	/* timer for periodic error stats printing */
	struct timer_list s_err_report;
1285 1286 1287 1288 1289

	/* Lazy inode table initialization info */
	struct ext4_li_request *s_li_request;
	/* Wait multiplier for lazy initialization thread */
	unsigned int s_li_wait_mult;
1290 1291 1292

	/* Kernel thread for multiple mount protection */
	struct task_struct *s_mmp_tsk;
1293 1294 1295

	/* record the last minlen when FITRIM is called. */
	atomic_t s_last_trim_minblks;
1296 1297 1298

	/* Reference to checksum algorithm driver via cryptoapi */
	struct crypto_shash *s_chksum_driver;
1299 1300 1301

	/* Precomputed FS UUID checksum for seeding other checksums */
	__u32 s_csum_seed;
1302 1303 1304 1305

	/* Reclaim extents from extent status tree */
	struct shrinker s_es_shrinker;
	struct list_head s_es_lru;
1306
	struct percpu_counter s_extent_cache_cnt;
1307
	spinlock_t s_es_lru_lock ____cacheline_aligned_in_smp;
1308 1309
};

1310
static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
1311 1312 1313
{
	return sb->s_fs_info;
}
1314
static inline struct ext4_inode_info *EXT4_I(struct inode *inode)
1315
{
1316
	return container_of(inode, struct ext4_inode_info, vfs_inode);
1317 1318
}

K
Kalpak Shah 已提交
1319 1320 1321 1322 1323 1324
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;
}

1325
static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
1326
{
1327
	return ino == EXT4_ROOT_INO ||
1328 1329
		ino == EXT4_USR_QUOTA_INO ||
		ino == EXT4_GRP_QUOTA_INO ||
1330
		ino == EXT4_BOOT_LOADER_INO ||
1331 1332 1333 1334
		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));
1335
}
1336

1337 1338 1339 1340
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)) {
1341 1342 1343
		/* Writeback has to have coversion transaction reserved */
		WARN_ON(EXT4_SB(inode->i_sb)->s_journal && !io_end->handle &&
			!(io_end->flag & EXT4_IO_END_DIRECT));
1344
		io_end->flag |= EXT4_IO_END_UNWRITTEN;
1345
		atomic_inc(&EXT4_I(inode)->i_unwritten);
1346 1347 1348
	}
}

D
Dmitry Monakhov 已提交
1349 1350 1351 1352 1353 1354 1355 1356 1357 1358
static inline ext4_io_end_t *ext4_inode_aio(struct inode *inode)
{
	return inode->i_private;
}

static inline void ext4_inode_aio_set(struct inode *inode, ext4_io_end_t *io)
{
	inode->i_private = io;
}

1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369
/*
 * 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*/
1370
	EXT4_STATE_NEWENTRY,		/* File just added to dir */
1371
	EXT4_STATE_DELALLOC_RESERVED,	/* blks already reserved for delalloc */
1372 1373
	EXT4_STATE_DIOREAD_LOCK,	/* Disable support for dio read
					   nolocking */
1374
	EXT4_STATE_MAY_INLINE_DATA,	/* may have in-inode data */
1375
	EXT4_STATE_ORDERED_MODE,	/* data=ordered mode */
1376 1377
};

1378
#define EXT4_INODE_BIT_FNS(name, field, offset)				\
1379 1380
static inline int ext4_test_inode_##name(struct inode *inode, int bit)	\
{									\
1381
	return test_bit(bit + (offset), &EXT4_I(inode)->i_##field);	\
1382 1383 1384
}									\
static inline void ext4_set_inode_##name(struct inode *inode, int bit)	\
{									\
1385
	set_bit(bit + (offset), &EXT4_I(inode)->i_##field);		\
1386 1387 1388
}									\
static inline void ext4_clear_inode_##name(struct inode *inode, int bit) \
{									\
1389
	clear_bit(bit + (offset), &EXT4_I(inode)->i_##field);		\
1390 1391
}

1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407
EXT4_INODE_BIT_FNS(flag, flags, 0)
#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
1408
#else
1409
/* Assume that user mode programs are passing in an ext4fs superblock, not
1410 1411
 * a kernel struct super_block.  This will allow us to call the feature-test
 * macros from user land. */
1412
#define EXT4_SB(sb)	(sb)
1413 1414
#endif

1415
#define NEXT_ORPHAN(inode) EXT4_I(inode)->i_dtime
1416 1417 1418 1419

/*
 * Codes for operating systems
 */
1420 1421 1422 1423 1424
#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
1425 1426 1427 1428

/*
 * Revision levels
 */
1429 1430
#define EXT4_GOOD_OLD_REV	0	/* The good old (original) format */
#define EXT4_DYNAMIC_REV	1	/* V2 format w/ dynamic inode sizes */
1431

1432 1433
#define EXT4_CURRENT_REV	EXT4_GOOD_OLD_REV
#define EXT4_MAX_SUPP_REV	EXT4_DYNAMIC_REV
1434

1435
#define EXT4_GOOD_OLD_INODE_SIZE 128
1436 1437 1438 1439 1440

/*
 * Feature set definitions
 */

1441
#define EXT4_HAS_COMPAT_FEATURE(sb,mask)			\
A
Aneesh Kumar K.V 已提交
1442
	((EXT4_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask)) != 0)
1443
#define EXT4_HAS_RO_COMPAT_FEATURE(sb,mask)			\
A
Aneesh Kumar K.V 已提交
1444
	((EXT4_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask)) != 0)
1445
#define EXT4_HAS_INCOMPAT_FEATURE(sb,mask)			\
A
Aneesh Kumar K.V 已提交
1446
	((EXT4_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask)) != 0)
1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469
#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

#define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER	0x0001
#define EXT4_FEATURE_RO_COMPAT_LARGE_FILE	0x0002
#define EXT4_FEATURE_RO_COMPAT_BTREE_DIR	0x0004
1470
#define EXT4_FEATURE_RO_COMPAT_HUGE_FILE        0x0008
A
Andreas Dilger 已提交
1471
#define EXT4_FEATURE_RO_COMPAT_GDT_CSUM		0x0010
1472
#define EXT4_FEATURE_RO_COMPAT_DIR_NLINK	0x0020
K
Kalpak Shah 已提交
1473
#define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE	0x0040
1474
#define EXT4_FEATURE_RO_COMPAT_QUOTA		0x0100
1475
#define EXT4_FEATURE_RO_COMPAT_BIGALLOC		0x0200
1476 1477 1478 1479 1480 1481
/*
 * 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.
 */
1482
#define EXT4_FEATURE_RO_COMPAT_METADATA_CSUM	0x0400
1483 1484 1485 1486 1487 1488

#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
1489
#define EXT4_FEATURE_INCOMPAT_EXTENTS		0x0040 /* extents support */
L
Laurent Vivier 已提交
1490
#define EXT4_FEATURE_INCOMPAT_64BIT		0x0080
1491
#define EXT4_FEATURE_INCOMPAT_MMP               0x0100
J
Jose R. Santos 已提交
1492
#define EXT4_FEATURE_INCOMPAT_FLEX_BG		0x0200
1493 1494
#define EXT4_FEATURE_INCOMPAT_EA_INODE		0x0400 /* EA in inode */
#define EXT4_FEATURE_INCOMPAT_DIRDATA		0x1000 /* data in dirent */
1495
#define EXT4_FEATURE_INCOMPAT_BG_USE_META_CSUM	0x2000 /* use crc32c for bg */
1496
#define EXT4_FEATURE_INCOMPAT_LARGEDIR		0x4000 /* >2GB or 3-lvl htree */
1497
#define EXT4_FEATURE_INCOMPAT_INLINE_DATA	0x8000 /* data in inode */
1498

1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513
#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)

1514 1515 1516
#define EXT4_FEATURE_COMPAT_SUPP	EXT2_FEATURE_COMPAT_EXT_ATTR
#define EXT4_FEATURE_INCOMPAT_SUPP	(EXT4_FEATURE_INCOMPAT_FILETYPE| \
					 EXT4_FEATURE_INCOMPAT_RECOVER| \
A
Alex Tomas 已提交
1517
					 EXT4_FEATURE_INCOMPAT_META_BG| \
L
Laurent Vivier 已提交
1518
					 EXT4_FEATURE_INCOMPAT_EXTENTS| \
J
Jose R. Santos 已提交
1519
					 EXT4_FEATURE_INCOMPAT_64BIT| \
1520
					 EXT4_FEATURE_INCOMPAT_FLEX_BG| \
T
Tao Ma 已提交
1521 1522
					 EXT4_FEATURE_INCOMPAT_MMP |	\
					 EXT4_FEATURE_INCOMPAT_INLINE_DATA)
1523 1524
#define EXT4_FEATURE_RO_COMPAT_SUPP	(EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
					 EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \
A
Andreas Dilger 已提交
1525
					 EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \
1526
					 EXT4_FEATURE_RO_COMPAT_DIR_NLINK | \
K
Kalpak Shah 已提交
1527
					 EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \
1528
					 EXT4_FEATURE_RO_COMPAT_BTREE_DIR |\
1529
					 EXT4_FEATURE_RO_COMPAT_HUGE_FILE |\
1530
					 EXT4_FEATURE_RO_COMPAT_BIGALLOC |\
1531 1532
					 EXT4_FEATURE_RO_COMPAT_METADATA_CSUM|\
					 EXT4_FEATURE_RO_COMPAT_QUOTA)
1533 1534 1535 1536

/*
 * Default values for user and/or group using reserved blocks
 */
1537 1538
#define	EXT4_DEF_RESUID		0
#define	EXT4_DEF_RESGID		0
1539

1540 1541
#define EXT4_DEF_INODE_READAHEAD_BLKS	32

1542 1543 1544
/*
 * Default mount options
 */
1545 1546 1547 1548 1549 1550 1551 1552 1553
#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
1554 1555 1556 1557
#define EXT4_DEFM_NOBARRIER	0x0100
#define EXT4_DEFM_BLOCK_VALIDITY 0x0200
#define EXT4_DEFM_DISCARD	0x0400
#define EXT4_DEFM_NODELALLOC	0x0800
1558

1559 1560 1561 1562 1563 1564
/*
 * Default journal batch times
 */
#define EXT4_DEF_MIN_BATCH_TIME	0
#define EXT4_DEF_MAX_BATCH_TIME	15000 /* 15ms */

1565 1566 1567 1568 1569 1570
/*
 * 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

1571 1572 1573
/*
 * Structure of a directory entry
 */
1574
#define EXT4_NAME_LEN 255
1575

1576
struct ext4_dir_entry {
1577 1578 1579
	__le32	inode;			/* Inode number */
	__le16	rec_len;		/* Directory entry length */
	__le16	name_len;		/* Name length */
1580
	char	name[EXT4_NAME_LEN];	/* File name */
1581 1582 1583
};

/*
1584
 * The new version of the directory entry.  Since EXT4 structures are
1585 1586 1587 1588
 * 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.
 */
1589
struct ext4_dir_entry_2 {
1590 1591 1592 1593
	__le32	inode;			/* Inode number */
	__le16	rec_len;		/* Directory entry length */
	__u8	name_len;		/* Name length */
	__u8	file_type;
1594
	char	name[EXT4_NAME_LEN];	/* File name */
1595 1596
};

1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608
/*
 * 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) */
};

1609 1610 1611 1612 1613
#define EXT4_DIRENT_TAIL(block, blocksize) \
	((struct ext4_dir_entry_tail *)(((void *)(block)) + \
					((blocksize) - \
					 sizeof(struct ext4_dir_entry_tail))))

1614
/*
1615
 * Ext4 directory file types.  Only the low 3 bits are used.  The
1616 1617
 * other bits are reserved for now.
 */
1618 1619 1620 1621 1622 1623 1624 1625
#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
1626

1627
#define EXT4_FT_MAX		8
1628

1629 1630
#define EXT4_FT_DIR_CSUM	0xDE

1631
/*
1632
 * EXT4_DIR_PAD defines the directory entries boundaries
1633 1634 1635
 *
 * NOTE: It must be a multiple of 4
 */
1636 1637 1638 1639
#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)
1640 1641
#define EXT4_MAX_REC_LEN		((1<<16)-1)

1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678
/*
 * 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);

#if (PAGE_CACHE_SIZE >= 65536)
	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();
#if (PAGE_CACHE_SIZE >= 65536)
	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
}

1679 1680 1681 1682 1683
/*
 * Hash Tree Directory indexing
 * (c) Daniel Phillips, 2001
 */

1684 1685
#define is_dx(dir) (EXT4_HAS_COMPAT_FEATURE(dir->i_sb, \
				      EXT4_FEATURE_COMPAT_DIR_INDEX) && \
1686
		    ext4_test_inode_flag((dir), EXT4_INODE_INDEX))
1687 1688
#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)
1689 1690 1691 1692 1693 1694

/* 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
1695 1696 1697
#define DX_HASH_LEGACY_UNSIGNED	3
#define DX_HASH_HALF_MD4_UNSIGNED	4
#define DX_HASH_TEA_UNSIGNED		5
1698

1699 1700 1701 1702 1703
static inline u32 ext4_chksum(struct ext4_sb_info *sbi, u32 crc,
			      const void *address, unsigned int length)
{
	struct {
		struct shash_desc shash;
1704
		char ctx[4];
1705 1706 1707
	} desc;
	int err;

1708 1709
	BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver)!=sizeof(desc.ctx));

1710 1711 1712 1713 1714 1715 1716 1717 1718 1719
	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;
}

1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730
#ifdef __KERNEL__

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

1731 1732 1733 1734 1735

/* 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)

1736 1737

/*
1738
 * Control parameters used by ext4_htree_next_block
1739 1740 1741 1742 1743 1744 1745
 */
#define HASH_NB_ALWAYS		1


/*
 * Describe an inode's exact location on disk and in memory
 */
1746
struct ext4_iloc
1747 1748 1749
{
	struct buffer_head *bh;
	unsigned long offset;
1750
	ext4_group_t block_group;
1751 1752
};

1753
static inline struct ext4_inode *ext4_raw_inode(struct ext4_iloc *iloc)
1754
{
1755
	return (struct ext4_inode *) (iloc->bh->b_data + iloc->offset);
1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773
}

/*
 * 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 */
1774
static inline ext4_fsblk_t
1775
ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no)
1776
{
1777 1778
	return group_no * (ext4_fsblk_t)EXT4_BLOCKS_PER_GROUP(sb) +
		le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
1779 1780 1781 1782 1783 1784 1785
}

/*
 * Special error return code only used by dx_probe() and its callers.
 */
#define ERR_BAD_DX_DIR	-75000

1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811
/*
 * 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;
};

1812 1813 1814 1815 1816
struct ext4_features {
	struct kobject f_kobj;
	struct completion f_kobj_unregister;
};

1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848
/*
 * 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;
1849 1850
	__le32	mmp_pad2[226];
	__le32	mmp_checksum;		/* crc32c(uuid+mmp_block) */
1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878
};

/* 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

1879 1880 1881 1882 1883 1884
/*
 * Function prototypes
 */

/*
 * Ok, these declarations are also in <linux/kernel.h> but none of the
1885
 * ext4 source programs needs to include it so they are duplicated here.
1886
 */
D
Dave Kleikamp 已提交
1887 1888 1889
# define NORET_TYPE	/**/
# define ATTRIB_NORET	__attribute__((noreturn))
# define NORET_AND	noreturn,
1890

1891
/* bitmap.c */
1892
extern unsigned int ext4_count_free(char *bitmap, unsigned numchars);
1893 1894 1895 1896 1897 1898
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);
1899 1900
void ext4_block_bitmap_csum_set(struct super_block *sb, ext4_group_t group,
				struct ext4_group_desc *gdp,
1901
				struct buffer_head *bh);
1902 1903
int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group,
				  struct ext4_group_desc *gdp,
1904
				  struct buffer_head *bh);
1905

1906
/* balloc.c */
1907 1908 1909 1910 1911 1912 1913
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);

1914 1915 1916 1917
extern void ext4_validate_block_bitmap(struct super_block *sb,
				       struct ext4_group_desc *desc,
				       unsigned int block_group,
				       struct buffer_head *bh);
1918 1919 1920 1921
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);
1922 1923 1924
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);
1925
extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
1926 1927 1928 1929
					 ext4_fsblk_t goal,
					 unsigned int flags,
					 unsigned long *count,
					 int *errp);
1930 1931
extern int ext4_claim_free_clusters(struct ext4_sb_info *sbi,
				    s64 nclusters, unsigned int flags);
1932
extern ext4_fsblk_t ext4_count_free_clusters(struct super_block *);
1933
extern void ext4_check_blocks_bitmap(struct super_block *);
1934
extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
1935
						    ext4_group_t block_group,
1936
						    struct buffer_head ** bh);
1937
extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
1938 1939 1940 1941 1942 1943 1944 1945

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);
1946 1947 1948 1949
extern void ext4_init_block_bitmap(struct super_block *sb,
				   struct buffer_head *bh,
				   ext4_group_t group,
				   struct ext4_group_desc *desc);
1950 1951 1952
extern unsigned ext4_free_clusters_after_init(struct super_block *sb,
					      ext4_group_t block_group,
					      struct ext4_group_desc *gdp);
1953 1954 1955
extern unsigned ext4_num_overhead_clusters(struct super_block *sb,
					   ext4_group_t block_group,
					   struct ext4_group_desc *gdp);
1956
ext4_fsblk_t ext4_inode_to_goal_block(struct inode *);
1957 1958

/* dir.c */
1959
extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *,
1960
				  struct file *,
1961
				  struct ext4_dir_entry_2 *,
1962 1963 1964
				  struct buffer_head *, char *, int,
				  unsigned int);
#define ext4_check_dir_entry(dir, filp, de, bh, buf, size, offset)	\
1965
	unlikely(__ext4_check_dir_entry(__func__, __LINE__, (dir), (filp), \
1966
					(de), (bh), (buf), (size), (offset)))
1967
extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
1968
				    __u32 minor_hash,
1969 1970
				    struct ext4_dir_entry_2 *dirent);
extern void ext4_htree_free_dir_info(struct dir_private_info *p);
1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985
extern int ext4_find_dest_de(struct inode *dir, struct inode *inode,
			     struct buffer_head *bh,
			     void *buf, int buf_size,
			     const char *name, int namelen,
			     struct ext4_dir_entry_2 **dest_de);
void ext4_insert_dentry(struct inode *inode,
			struct ext4_dir_entry_2 *de,
			int buf_size,
			const char *name, int namelen);
static inline void ext4_update_dx_flag(struct inode *inode)
{
	if (!EXT4_HAS_COMPAT_FEATURE(inode->i_sb,
				     EXT4_FEATURE_COMPAT_DIR_INDEX))
		ext4_clear_inode_flag(inode, EXT4_INODE_INDEX);
}
T
Tao Ma 已提交
1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997
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)
{
	if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FILETYPE) ||
	    (filetype >= EXT4_FT_MAX))
		return DT_UNKNOWN;

	return ext4_filetype_table[filetype];
}
1998 1999

/* fsync.c */
2000
extern int ext4_sync_file(struct file *, loff_t, loff_t, int);
2001 2002

/* hash.c */
2003
extern int ext4fs_dirhash(const char *name, int len, struct
2004 2005 2006
			  dx_hash_info *hinfo);

/* ialloc.c */
2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020
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))


2021 2022 2023 2024 2025
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 *);
2026
extern void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
2027 2028
extern int ext4_init_inode_table(struct super_block *sb,
				 ext4_group_t group, int barrier);
2029
extern void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate);
2030

2031 2032 2033
/* mballoc.c */
extern long ext4_mb_stats;
extern long ext4_mb_max_to_scan;
2034
extern int ext4_mb_init(struct super_block *);
2035 2036 2037 2038
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);
2039
extern void ext4_discard_preallocations(struct inode *);
2040 2041
extern int __init ext4_init_mballoc(void);
extern void ext4_exit_mballoc(void);
2042
extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
2043 2044
			     struct buffer_head *bh, ext4_fsblk_t block,
			     unsigned long count, int flags);
2045 2046
extern int ext4_mb_alloc_groupinfo(struct super_block *sb,
				   ext4_group_t ngroups);
2047
extern int ext4_mb_add_groupinfo(struct super_block *sb,
2048
		ext4_group_t i, struct ext4_group_desc *desc);
2049
extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
2050
				ext4_fsblk_t block, unsigned long count);
2051 2052
extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);

2053
/* inode.c */
A
Aneesh Kumar K.V 已提交
2054 2055 2056 2057
struct buffer_head *ext4_getblk(handle_t *, struct inode *,
						ext4_lblk_t, int, int *);
struct buffer_head *ext4_bread(handle_t *, struct inode *,
						ext4_lblk_t, int, int *);
2058 2059
int ext4_get_block_write(struct inode *inode, sector_t iblock,
			 struct buffer_head *bh_result, int create);
2060 2061
int ext4_get_block(struct inode *inode, sector_t iblock,
				struct buffer_head *bh_result, int create);
2062 2063
int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
			   struct buffer_head *bh, int create);
2064 2065 2066 2067 2068 2069 2070 2071 2072
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);
2073 2074
#define FALL_BACK_TO_NONDELALLOC 1
#define CONVERT_INLINE_DATA	 2
2075

2076
extern struct inode *ext4_iget(struct super_block *, unsigned long);
2077
extern int  ext4_write_inode(struct inode *, struct writeback_control *);
2078
extern int  ext4_setattr(struct dentry *, struct iattr *);
2079 2080
extern int  ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
				struct kstat *stat);
A
Al Viro 已提交
2081 2082
extern void ext4_evict_inode(struct inode *);
extern void ext4_clear_inode(struct inode *);
2083
extern int  ext4_sync_inode(handle_t *, struct inode *);
2084
extern void ext4_dirty_inode(struct inode *, int);
2085 2086
extern int ext4_change_inode_journal_flag(struct inode *, int);
extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
2087
extern int ext4_can_truncate(struct inode *inode);
2088
extern void ext4_truncate(struct inode *);
2089
extern int ext4_punch_hole(struct file *file, loff_t offset, loff_t length);
2090
extern int ext4_truncate_restart_trans(handle_t *, struct inode *, int nblocks);
2091
extern void ext4_set_inode_flags(struct inode *);
2092
extern void ext4_get_inode_flags(struct ext4_inode_info *);
2093
extern int ext4_alloc_da_blocks(struct inode *inode);
2094
extern void ext4_set_aops(struct inode *inode);
A
Alex Tomas 已提交
2095
extern int ext4_writepage_trans_blocks(struct inode *);
2096
extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
2097 2098 2099 2100
extern int ext4_block_truncate_page(handle_t *handle,
		struct address_space *mapping, loff_t from);
extern int ext4_block_zero_page_range(handle_t *handle,
		struct address_space *mapping, loff_t from, loff_t length);
2101 2102
extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
			     loff_t lstart, loff_t lend);
2103
extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
2104
extern qsize_t *ext4_get_reserved_space(struct inode *inode);
2105 2106
extern void ext4_da_update_reserve_space(struct inode *inode,
					int used, int quota_claim);
2107 2108 2109 2110 2111 2112 2113 2114

/* indirect.c */
extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
				struct ext4_map_blocks *map, int flags);
extern ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
				const struct iovec *iov, loff_t offset,
				unsigned long nr_segs);
extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock);
2115
extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks);
T
Theodore Ts'o 已提交
2116
extern void ext4_ind_truncate(handle_t *, struct inode *inode);
T
Theodore Ts'o 已提交
2117 2118
extern int ext4_free_hole_blocks(handle_t *handle, struct inode *inode,
				 ext4_lblk_t first, ext4_lblk_t stop);
2119

2120
/* ioctl.c */
A
Andi Kleen 已提交
2121
extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
2122
extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
2123

2124
/* migrate.c */
2125
extern int ext4_ext_migrate(struct inode *);
2126
extern int ext4_ind_migrate(struct inode *inode);
2127

2128
/* namei.c */
2129 2130
extern int ext4_dirent_csum_verify(struct inode *inode,
				   struct ext4_dir_entry *dirent);
2131 2132 2133
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,
2134
				__u32 start_minor_hash, __u32 *next_hash);
T
Tao Ma 已提交
2135 2136 2137 2138 2139 2140 2141
extern int search_dir(struct buffer_head *bh,
		      char *search_buf,
		      int buf_size,
		      struct inode *dir,
		      const struct qstr *d_name,
		      unsigned int offset,
		      struct ext4_dir_entry_2 **res_dir);
T
Tao Ma 已提交
2142 2143 2144 2145 2146 2147 2148
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);
2149 2150

/* resize.c */
2151 2152 2153 2154 2155
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);
2156
extern int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count);
2157 2158

/* super.c */
2159
extern int ext4_calculate_overhead(struct super_block *sb);
2160 2161
extern int ext4_superblock_csum_verify(struct super_block *sb,
				       struct ext4_super_block *es);
2162
extern void ext4_superblock_csum_set(struct super_block *sb);
2163 2164 2165
extern void *ext4_kvmalloc(size_t size, gfp_t flags);
extern void *ext4_kvzalloc(size_t size, gfp_t flags);
extern void ext4_kvfree(void *ptr);
2166 2167
extern int ext4_alloc_flex_bg_array(struct super_block *sb,
				    ext4_group_t ngroup);
2168 2169
extern const char *ext4_decode_error(struct super_block *sb, int errno,
				     char nbuf[16]);
2170 2171 2172
extern __printf(4, 5)
void __ext4_error(struct super_block *, const char *, unsigned int,
		  const char *, ...);
2173 2174
#define ext4_error(sb, message...)	__ext4_error(sb, __func__,	\
						     __LINE__, ## message)
2175 2176 2177 2178 2179 2180
extern __printf(5, 6)
void ext4_error_inode(struct inode *, const char *, unsigned int, ext4_fsblk_t,
		      const char *, ...);
extern __printf(5, 6)
void ext4_error_file(struct file *, const char *, unsigned int, ext4_fsblk_t,
		     const char *, ...);
2181 2182
extern void __ext4_std_error(struct super_block *, const char *,
			     unsigned int, int);
2183 2184 2185
extern __printf(4, 5)
void __ext4_abort(struct super_block *, const char *, unsigned int,
		  const char *, ...);
2186
#define ext4_abort(sb, message...)	__ext4_abort(sb, __func__, \
2187
						       __LINE__, ## message)
2188 2189 2190
extern __printf(4, 5)
void __ext4_warning(struct super_block *, const char *, unsigned int,
		    const char *, ...);
2191 2192
#define ext4_warning(sb, message...)	__ext4_warning(sb, __func__, \
						       __LINE__, ## message)
2193 2194
extern __printf(3, 4)
void ext4_msg(struct super_block *, const char *, const char *, ...);
2195 2196 2197 2198
extern void __dump_mmp_msg(struct super_block *, struct mmp_struct *mmp,
			   const char *, unsigned int, const char *);
#define dump_mmp_msg(sb, mmp, msg)	__dump_mmp_msg(sb, mmp, __func__, \
						       __LINE__, msg)
2199 2200 2201 2202 2203
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 *, ...);
2204 2205
#define ext4_grp_locked_error(sb, grp, message...) \
	__ext4_grp_locked_error(__func__, __LINE__, (sb), (grp), ## message)
2206
extern void ext4_update_dynamic_rev(struct super_block *sb);
2207 2208 2209 2210 2211 2212
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);
2213 2214 2215 2216 2217 2218
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);
2219 2220
extern __u32 ext4_free_group_clusters(struct super_block *sb,
				      struct ext4_group_desc *bg);
2221 2222 2223 2224 2225 2226
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);
2227 2228 2229 2230 2231 2232
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);
2233 2234 2235
extern void ext4_free_group_clusters_set(struct super_block *sb,
					 struct ext4_group_desc *bg,
					 __u32 count);
2236 2237 2238 2239 2240 2241
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);
2242
extern int ext4_group_desc_csum_verify(struct super_block *sb, __u32 group,
2243
				       struct ext4_group_desc *gdp);
2244 2245
extern void ext4_group_desc_csum_set(struct super_block *sb, __u32 group,
				     struct ext4_group_desc *gdp);
2246 2247
extern int ext4_register_li_request(struct super_block *sb,
				    ext4_group_t first_not_zeroed);
L
Laurent Vivier 已提交
2248

2249 2250 2251 2252 2253 2254
static inline int ext4_has_group_desc_csum(struct super_block *sb)
{
	return EXT4_HAS_RO_COMPAT_FEATURE(sb,
					  EXT4_FEATURE_RO_COMPAT_GDT_CSUM |
					  EXT4_FEATURE_RO_COMPAT_METADATA_CSUM);
}
L
Laurent Vivier 已提交
2255 2256 2257 2258

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) |
2259
		le32_to_cpu(es->s_blocks_count_lo);
L
Laurent Vivier 已提交
2260 2261 2262 2263 2264
}

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) |
2265
		le32_to_cpu(es->s_r_blocks_count_lo);
L
Laurent Vivier 已提交
2266 2267 2268 2269 2270
}

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) |
2271
		le32_to_cpu(es->s_free_blocks_count_lo);
L
Laurent Vivier 已提交
2272 2273 2274 2275 2276
}

static inline void ext4_blocks_count_set(struct ext4_super_block *es,
					 ext4_fsblk_t blk)
{
2277
	es->s_blocks_count_lo = cpu_to_le32((u32)blk);
L
Laurent Vivier 已提交
2278 2279 2280 2281 2282 2283
	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)
{
2284
	es->s_free_blocks_count_lo = cpu_to_le32((u32)blk);
L
Laurent Vivier 已提交
2285 2286 2287 2288 2289 2290
	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)
{
2291
	es->s_r_blocks_count_lo = cpu_to_le32((u32)blk);
L
Laurent Vivier 已提交
2292 2293 2294
	es->s_r_blocks_count_hi = cpu_to_le32(blk >> 32);
}

2295 2296
static inline loff_t ext4_isize(struct ext4_inode *raw_inode)
{
2297 2298 2299 2300 2301
	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);
2302
}
L
Laurent Vivier 已提交
2303

2304 2305 2306 2307 2308
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);
}
2309

2310 2311
static inline
struct ext4_group_info *ext4_get_group_info(struct super_block *sb,
2312
					    ext4_group_t group)
2313 2314 2315
{
	 struct ext4_group_info ***grp_info;
	 long indexv, indexh;
2316
	 BUG_ON(group >= EXT4_SB(sb)->s_groups_count);
2317 2318 2319 2320 2321 2322
	 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];
}

2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334
/*
 * 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;
}
2335

2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346
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;
}

2347
#define ext4_std_error(sb, errno)				\
2348 2349
do {								\
	if ((errno))						\
2350
		__ext4_std_error((sb), __func__, __LINE__, (errno));	\
2351 2352
} while (0)

2353
#ifdef CONFIG_SMP
2354 2355
/* Each CPU can accumulate percpu_counter_batch clusters in their local
 * counters. So we need to make sure we have free clusters more
2356
 * than percpu_counter_batch  * nr_cpu_ids. Also add a window of 4 times.
2357
 */
2358
#define EXT4_FREECLUSTERS_WATERMARK (4 * (percpu_counter_batch * nr_cpu_ids))
2359
#else
2360
#define EXT4_FREECLUSTERS_WATERMARK 0
2361 2362
#endif

2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373
static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
{
	/*
	 * XXX: replace with spinlock if seen contended -bzzz
	 */
	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);
	return ;
}
2374

2375 2376 2377
struct ext4_group_info {
	unsigned long   bb_state;
	struct rb_root  bb_free_root;
2378 2379 2380
	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 */
2381
	ext4_grpblk_t	bb_largest_free_order;/* order of largest frag in BG */
2382 2383 2384 2385 2386
	struct          list_head bb_prealloc_list;
#ifdef DOUBLE_CHECK
	void            *bb_bitmap;
#endif
	struct rw_semaphore alloc_sem;
2387 2388 2389 2390
	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. */
2391 2392
};

2393 2394
#define EXT4_GROUP_INFO_NEED_INIT_BIT		0
#define EXT4_GROUP_INFO_WAS_TRIMMED_BIT		1
2395 2396 2397 2398

#define EXT4_MB_GRP_NEED_INIT(grp)	\
	(test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))

2399 2400 2401 2402 2403 2404 2405
#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)))

2406 2407 2408
#define EXT4_MAX_CONTENTION		8
#define EXT4_CONTENTION_THRESHOLD	2

2409 2410
static inline spinlock_t *ext4_group_lock_ptr(struct super_block *sb,
					      ext4_group_t group)
2411
{
2412 2413
	return bgl_lock_ptr(EXT4_SB(sb)->s_blockgroup_lock, group);
}
2414

2415 2416 2417 2418 2419 2420 2421 2422 2423
/*
 * 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);
}

2424 2425
static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group)
{
2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441
	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);
	}
2442 2443 2444 2445 2446
}

static inline void ext4_unlock_group(struct super_block *sb,
					ext4_group_t group)
{
2447
	spin_unlock(ext4_group_lock_ptr(sb, group));
2448 2449
}

2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462
/*
 * 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)

2463 2464 2465 2466 2467
/*
 * Inodes and files operations
 */

/* dir.c */
2468
extern const struct file_operations ext4_dir_operations;
2469 2470

/* file.c */
2471
extern const struct inode_operations ext4_file_inode_operations;
2472
extern const struct file_operations ext4_file_operations;
2473
extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
2474
extern void ext4_unwritten_wait(struct inode *inode);
2475

2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521
/* inline.c */
extern int ext4_has_inline_data(struct inode *inode);
extern int ext4_get_inline_size(struct inode *inode);
extern int ext4_get_max_inline_size(struct inode *inode);
extern int ext4_find_inline_data_nolock(struct inode *inode);
extern void ext4_write_inline_data(struct inode *inode,
				   struct ext4_iloc *iloc,
				   void *buffer, loff_t pos,
				   unsigned int len);
extern int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
				    unsigned int len);
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);
extern int ext4_try_add_inline_entry(handle_t *handle, struct dentry *dentry,
				     struct inode *inode);
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,
				void *dirent, filldir_t filldir,
				int *has_inline_data);
2522 2523 2524 2525 2526
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);
2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549
extern struct buffer_head *ext4_find_inline_entry(struct inode *dir,
					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,
				   int *has_inline);
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);

2550
/* namei.c */
2551 2552
extern const struct inode_operations ext4_dir_inode_operations;
extern const struct inode_operations ext4_special_inode_operations;
2553
extern struct dentry *ext4_get_parent(struct dentry *child);
2554 2555 2556 2557
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);
2558 2559 2560 2561 2562
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);
2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580
#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) {
	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FILETYPE))
		de->file_type = ext4_type_by_mode[(mode & S_IFMT)>>S_SHIFT];
}

2581 2582

/* symlink.c */
2583 2584
extern const struct inode_operations ext4_symlink_inode_operations;
extern const struct inode_operations ext4_fast_symlink_inode_operations;
2585

2586 2587 2588
/* block_validity */
extern void ext4_release_system_zone(struct super_block *sb);
extern int ext4_setup_system_zone(struct super_block *sb);
2589 2590
extern int __init ext4_init_system_zone(void);
extern void ext4_exit_system_zone(void);
2591 2592 2593
extern int ext4_data_block_valid(struct ext4_sb_info *sbi,
				 ext4_fsblk_t start_blk,
				 unsigned int count);
2594 2595
extern int ext4_check_blockref(const char *, unsigned int,
			       struct inode *, __le32 *, unsigned int);
2596

A
Alex Tomas 已提交
2597
/* extents.c */
2598 2599 2600
struct ext4_ext_path;
struct ext4_extent;

A
Alex Tomas 已提交
2601 2602
extern int ext4_ext_tree_init(handle_t *handle, struct inode *);
extern int ext4_ext_writepage_trans_blocks(struct inode *, int);
2603
extern int ext4_ext_index_trans_blocks(struct inode *inode, int extents);
2604 2605
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
2606
extern void ext4_ext_truncate(handle_t *, struct inode *);
T
Theodore Ts'o 已提交
2607 2608
extern int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
				 ext4_lblk_t end);
A
Alex Tomas 已提交
2609 2610
extern void ext4_ext_init(struct super_block *);
extern void ext4_ext_release(struct super_block *);
2611
extern long ext4_fallocate(struct file *file, int mode, loff_t offset,
A
Amit Arora 已提交
2612
			  loff_t len);
2613 2614
extern int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode,
					  loff_t offset, ssize_t len);
2615 2616
extern int ext4_map_blocks(handle_t *handle, struct inode *inode,
			   struct ext4_map_blocks *map, int flags);
2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632
extern int ext4_ext_calc_metadata_amount(struct inode *inode,
					 ext4_lblk_t lblocks);
extern int ext4_extent_tree_init(handle_t *, struct inode *);
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 *,
				  struct ext4_ext_path *,
				  struct ext4_extent *, int);
extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t,
						  struct ext4_ext_path *);
extern void ext4_ext_drop_refs(struct ext4_ext_path *);
extern int ext4_ext_check_inode(struct inode *inode);
2633 2634 2635
extern int ext4_find_delalloc_range(struct inode *inode,
				    ext4_lblk_t lblk_start,
				    ext4_lblk_t lblk_end);
2636
extern int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk);
A
Aneesh Kumar K.V 已提交
2637 2638
extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
			__u64 start, __u64 len);
2639 2640


2641
/* move_extent.c */
2642 2643 2644 2645 2646 2647
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);
void ext4_inode_double_lock(struct inode *inode1, struct inode *inode2);
void ext4_inode_double_unlock(struct inode *inode1, struct inode *inode2);
2648 2649 2650 2651
extern int ext4_move_extents(struct file *o_filp, struct file *d_filp,
			     __u64 start_orig, __u64 start_donor,
			     __u64 len, __u64 *moved_len);

2652
/* page-io.c */
2653 2654
extern int __init ext4_init_pageio(void);
extern void ext4_exit_pageio(void);
2655
extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags);
J
Jan Kara 已提交
2656 2657 2658 2659 2660
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);
2661 2662
extern void ext4_end_io_rsv_work(struct work_struct *work);
extern void ext4_end_io_unrsv_work(struct work_struct *work);
2663 2664 2665 2666 2667
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,
			       struct writeback_control *wbc);
A
Aneesh Kumar K.V 已提交
2668

2669 2670
/* mmp.c */
extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);
2671 2672 2673
extern void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp);
extern int ext4_mmp_csum_verify(struct super_block *sb,
				struct mmp_struct *mmp);
2674

J
Jan Kara 已提交
2675 2676 2677 2678
/*
 * Note that these flags will never ever appear in a buffer_head's state flag.
 * See EXT4_MAP_... to see where this is used.
 */
2679 2680
enum ext4_state_bits {
	BH_Uninit	/* blocks are allocated but uninitialized on disk */
J
Jan Kara 已提交
2681
	 = BH_JBDPrivateStart,
2682
	BH_AllocFromCluster,	/* allocated blocks were part of already
J
Jan Kara 已提交
2683
				 * allocated cluster. */
2684 2685
};

2686
/*
2687
 * Add new method to test whether block and inode bitmaps are properly
2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702
 * 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);
}

2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717
/*
 * 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);
}

2718 2719
#define in_range(b, first, len)	((b) >= (first) && (b) <= (first) + (len) - 1)

2720 2721 2722 2723 2724 2725 2726 2727 2728
/* 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])
#define ext4_aio_mutex(v)  (&ext4__aio_mutex[((unsigned long)(v)) %\
					     EXT4_WQ_HASH_SZ])
extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
extern struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ];

2729 2730 2731 2732
#define EXT4_RESIZING	0
extern int ext4_resize_begin(struct super_block *sb);
extern void ext4_resize_end(struct super_block *sb);

2733 2734
#endif	/* __KERNEL__ */

2735
#endif	/* _EXT4_H */