ext4.h 106 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 <linux/ratelimit.h>
33
#include <crypto/hash.h>
34
#include <linux/falloc.h>
35 36 37
#ifdef __KERNEL__
#include <linux/compat.h>
#endif
38

39
/*
Shen Feng's avatar
Shen Feng committed
40
 * The fourth extended filesystem constants/structures
41 42 43
 */

/*
44
 * Define EXT4FS_DEBUG to produce debug messages
45
 */
46
#undef EXT4FS_DEBUG
47 48 49 50

/*
 * Debug code
 */
51 52
#ifdef EXT4FS_DEBUG
#define ext4_debug(f, a...)						\
53
	do {								\
54
		printk(KERN_DEBUG "EXT4-fs DEBUG (%s, %d): %s:",	\
55
			__FILE__, __LINE__, __func__);			\
56
		printk(KERN_DEBUG f, ## a);				\
57 58
	} while (0)
#else
59
#define ext4_debug(fmt, ...)	no_printk(fmt, ##__VA_ARGS__)
60 61
#endif

62 63 64 65 66 67 68 69 70 71
/*
 * 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

72
#define EXT4_ERROR_INODE(inode, fmt, a...) \
73 74 75 76
	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)
77

78 79
#define EXT4_ERROR_FILE(file, block, fmt, a...)				\
	ext4_error_file((file), __func__, __LINE__, (block), (fmt), ## a)
80

81 82 83 84 85 86 87 88 89 90 91 92
/* 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;

93
/*
94
 * Flags used in mballoc's allocation_context flags field.
95 96 97 98
 *
 * Also used to show what's going on for debugging purposes when the
 * flag field is exported via the traceport interface
 */
99

100
/* prefer goal again. length */
101
#define EXT4_MB_HINT_MERGE		0x0001
102
/* blocks already reserved */
103
#define EXT4_MB_HINT_RESERVED		0x0002
104
/* metadata is being allocated */
105
#define EXT4_MB_HINT_METADATA		0x0004
106
/* first blocks in the file */
107
#define EXT4_MB_HINT_FIRST		0x0008
108
/* search for the best chunk */
109
#define EXT4_MB_HINT_BEST		0x0010
110
/* data is being allocated */
111
#define EXT4_MB_HINT_DATA		0x0020
112
/* don't preallocate (for tails) */
113
#define EXT4_MB_HINT_NOPREALLOC		0x0040
114
/* allocate for locality group */
115
#define EXT4_MB_HINT_GROUP_ALLOC	0x0080
116
/* allocate goal blocks or none */
117
#define EXT4_MB_HINT_GOAL_ONLY		0x0100
118
/* goal is meaningful */
119
#define EXT4_MB_HINT_TRY_GOAL		0x0200
120
/* blocks already pre-reserved by delayed allocation */
121
#define EXT4_MB_DELALLOC_RESERVED	0x0400
122 123
/* We are doing stream allocation */
#define EXT4_MB_STREAM_ALLOC		0x0800
124 125
/* Use reserved root blocks if needed */
#define EXT4_MB_USE_ROOT_BLOCKS		0x1000
126 127
/* Use blocks from reserved pool */
#define EXT4_MB_USE_RESERVED		0x2000
128 129 130 131

struct ext4_allocation_request {
	/* target inode for block we're allocating */
	struct inode *inode;
132 133
	/* how many blocks we want to allocate */
	unsigned int len;
134 135 136 137 138 139
	/* 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;
140 141 142 143 144
	/* 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 */
145 146
	ext4_fsblk_t pright;
	/* flags. see above EXT4_MB_HINT_* */
147
	unsigned int flags;
148 149
};

150 151 152 153 154 155 156 157 158 159 160 161
/*
 * Logical to physical block mapping, used by ext4_map_blocks()
 *
 * This structure is used to pass requests into ext4_map_blocks() as
 * well as to store the information returned by ext4_map_blocks().  It
 * takes less room on the stack than a struct buffer_head.
 */
#define EXT4_MAP_NEW		(1 << BH_New)
#define EXT4_MAP_MAPPED		(1 << BH_Mapped)
#define EXT4_MAP_UNWRITTEN	(1 << BH_Unwritten)
#define EXT4_MAP_BOUNDARY	(1 << BH_Boundary)
#define EXT4_MAP_FLAGS		(EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
162
				 EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY)
163 164 165 166 167 168 169 170

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

171 172 173 174 175
/*
 * Flags for ext4_io_end->flags
 */
#define	EXT4_IO_END_UNWRITTEN	0x0001

176
/*
177
 * For converting unwritten extents on a work queue. 'handle' is used for
178
 * buffered writeback.
179
 */
180
typedef struct ext4_io_end {
181
	struct list_head	list;		/* per-file finished IO list */
182 183
	handle_t		*handle;	/* handle reserved for extent
						 * conversion */
184
	struct inode		*inode;		/* file being written to */
185 186
	struct bio		*bio;		/* Linked list of completed
						 * bios covering the extent */
187
	unsigned int		flag;		/* unwritten or not */
188 189
	loff_t			offset;		/* offset in the file */
	ssize_t			size;		/* size of the extent */
190
	atomic_t		count;		/* reference counter */
191 192
} ext4_io_end_t;

193 194 195 196 197 198 199
struct ext4_io_submit {
	int			io_op;
	struct bio		*io_bio;
	ext4_io_end_t		*io_end;
	sector_t		io_next_block;
};

200 201 202
/*
 * Special inodes numbers
 */
203 204
#define	EXT4_BAD_INO		 1	/* Bad blocks inode */
#define EXT4_ROOT_INO		 2	/* Root inode */
205 206
#define EXT4_USR_QUOTA_INO	 3	/* User quota inode */
#define EXT4_GRP_QUOTA_INO	 4	/* Group quota inode */
207 208 209 210
#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 */
211

212 213
/* First non-reserved inode for old ext4 filesystems */
#define EXT4_GOOD_OLD_FIRST_INO	11
214 215 216 217

/*
 * Maximal count of links to a file
 */
218
#define EXT4_LINK_MAX		65000
219 220 221 222

/*
 * Macro-instructions used to manage several block sizes
 */
223
#define EXT4_MIN_BLOCK_SIZE		1024
224 225
#define	EXT4_MAX_BLOCK_SIZE		65536
#define EXT4_MIN_BLOCK_LOG_SIZE		10
226
#define EXT4_MAX_BLOCK_LOG_SIZE		16
227
#ifdef __KERNEL__
228
# define EXT4_BLOCK_SIZE(s)		((s)->s_blocksize)
229
#else
230
# define EXT4_BLOCK_SIZE(s)		(EXT4_MIN_BLOCK_SIZE << (s)->s_log_block_size)
231
#endif
232
#define	EXT4_ADDR_PER_BLOCK(s)		(EXT4_BLOCK_SIZE(s) / sizeof(__u32))
233 234
#define EXT4_CLUSTER_SIZE(s)		(EXT4_BLOCK_SIZE(s) << \
					 EXT4_SB(s)->s_cluster_bits)
235
#ifdef __KERNEL__
236
# define EXT4_BLOCK_SIZE_BITS(s)	((s)->s_blocksize_bits)
237
# define EXT4_CLUSTER_BITS(s)		(EXT4_SB(s)->s_cluster_bits)
238
#else
239
# define EXT4_BLOCK_SIZE_BITS(s)	((s)->s_log_block_size + 10)
240 241
#endif
#ifdef __KERNEL__
242 243 244
#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)
245
#else
246 247
#define EXT4_INODE_SIZE(s)	(((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \
				 EXT4_GOOD_OLD_INODE_SIZE : \
248
				 (s)->s_inode_size)
249 250
#define EXT4_FIRST_INO(s)	(((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \
				 EXT4_GOOD_OLD_FIRST_INO : \
251 252
				 (s)->s_first_ino)
#endif
Amit Arora's avatar
Amit Arora committed
253
#define EXT4_BLOCK_ALIGN(size, blkbits)		ALIGN((size), (1 << (blkbits)))
254

255 256 257 258 259 260 261
/* 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)
262 263 264 265 266 267 268 269 270 271
/* Mask out the low bits to get the starting block of the cluster */
#define EXT4_PBLK_CMASK(s, pblk) ((pblk) &				\
				  ~((ext4_fsblk_t) (s)->s_cluster_ratio - 1))
#define EXT4_LBLK_CMASK(s, lblk) ((lblk) &				\
				  ~((ext4_lblk_t) (s)->s_cluster_ratio - 1))
/* Get the cluster offset */
#define EXT4_PBLK_COFF(s, pblk) ((pblk) &				\
				 ((ext4_fsblk_t) (s)->s_cluster_ratio - 1))
#define EXT4_LBLK_COFF(s, lblk) ((lblk) &				\
				 ((ext4_lblk_t) (s)->s_cluster_ratio - 1))
272

273 274 275
/*
 * Structure of a blocks group descriptor
 */
276
struct ext4_group_desc
277
{
278
	__le32	bg_block_bitmap_lo;	/* Blocks bitmap block */
279 280
	__le32	bg_inode_bitmap_lo;	/* Inodes bitmap block */
	__le32	bg_inode_table_lo;	/* Inodes table block */
281 282 283
	__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 */
284
	__le16	bg_flags;		/* EXT4_BG_flags (INODE_UNINIT, etc) */
285 286 287
	__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 */
288
	__le16  bg_itable_unused_lo;	/* Unused inodes count */
289
	__le16  bg_checksum;		/* crc16(sb_uuid+group+desc) */
290 291 292
	__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 */
293 294 295
	__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 */
296
	__le16  bg_itable_unused_hi;    /* Unused inodes count MSB */
297 298 299 300
	__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;
301 302
};

303 304 305 306 307 308 309
#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))

310 311 312 313 314
/*
 * Structure of a flex block group info
 */

struct flex_groups {
315 316 317
	atomic64_t	free_clusters;
	atomic_t	free_inodes;
	atomic_t	used_dirs;
318 319
};

320 321 322 323
#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 */

324 325 326
/*
 * Macro-instructions used to manage group descriptors
 */
327
#define EXT4_MIN_DESC_SIZE		32
328
#define EXT4_MIN_DESC_SIZE_64BIT	64
329 330
#define	EXT4_MAX_DESC_SIZE		EXT4_MIN_BLOCK_SIZE
#define EXT4_DESC_SIZE(s)		(EXT4_SB(s)->s_desc_size)
331
#ifdef __KERNEL__
332
# define EXT4_BLOCKS_PER_GROUP(s)	(EXT4_SB(s)->s_blocks_per_group)
333
# define EXT4_CLUSTERS_PER_GROUP(s)	(EXT4_SB(s)->s_clusters_per_group)
334 335 336
# 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)
337
#else
338
# define EXT4_BLOCKS_PER_GROUP(s)	((s)->s_blocks_per_group)
339
# define EXT4_DESC_PER_BLOCK(s)		(EXT4_BLOCK_SIZE(s) / EXT4_DESC_SIZE(s))
340
# define EXT4_INODES_PER_GROUP(s)	((s)->s_inodes_per_group)
341 342 343 344 345
#endif

/*
 * Constants relative to the data blocks
 */
346 347 348 349 350
#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)
351 352 353 354

/*
 * Inode flags
 */
355 356 357 358 359 360 361 362
#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 */
363
/* Reserved for compression usage... */
364 365 366
#define EXT4_DIRTY_FL			0x00000100
#define EXT4_COMPRBLK_FL		0x00000200 /* One or more compressed clusters */
#define EXT4_NOCOMPR_FL			0x00000400 /* Don't compress */
367 368
	/* nb: was previously EXT2_ECOMPR_FL */
#define EXT4_ENCRYPT_FL			0x00000800 /* encrypted file */
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*/
Aneesh Kumar K.V's avatar
Aneesh Kumar K.V committed
376
#define EXT4_HUGE_FILE_FL               0x00040000 /* Set to each huge file */
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. */
Aneesh Kumar K.V's avatar
Aneesh Kumar K.V committed
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
/*
 * 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 */
425
	EXT4_INODE_ENCRYPT	= 11,	/* Encrypted file */
426 427 428 429 430 431 432 433 434 435 436
/* 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
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);
470
	CHECK_FLAG_VALUE(ENCRYPT);
471 472 473 474 475 476 477 478 479 480
	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 {
Dave Kleikamp's avatar
Dave Kleikamp committed
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;
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,
};

Amit Arora's avatar
Amit Arora committed
528
/*
529
 * Flags used by ext4_map_blocks()
Amit Arora's avatar
Amit Arora committed
530
 */
531
	/* Allocate any needed blocks and/or convert an unwritten
532
	   extent to be an initialized ext4 */
533
#define EXT4_GET_BLOCKS_CREATE			0x0001
534 535 536
	/* Request the creation of an unwritten extent */
#define EXT4_GET_BLOCKS_UNWRIT_EXT		0x0002
#define EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT	(EXT4_GET_BLOCKS_UNWRIT_EXT|\
537
						 EXT4_GET_BLOCKS_CREATE)
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
	/* caller is from the direct IO path, request to creation of an
542
	unwritten extents if not allocated, split the unwritten
543
	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_UNWRIT_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_UNWRIT_EXT)
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
	/* Convert written extents to unwritten */
561
#define EXT4_GET_BLOCKS_CONVERT_UNWRITTEN	0x0200
562

563
/*
564
 * The bit position of these flags must not overlap with any of the
565
 * EXT4_GET_BLOCKS_*.  They are used by ext4_find_extent(),
566
 * read_extent_tree_block(), ext4_split_extent_at(),
567 568 569 570
 * ext4_ext_insert_extent(), and ext4_ext_create_new_leaf().
 * EXT4_EX_NOCACHE is used to indicate that the we shouldn't be
 * caching the extents when reading from the extent tree while a
 * truncate or punch hole operation is in progress.
571
 */
572 573
#define EXT4_EX_NOCACHE				0x40000000
#define EXT4_EX_FORCE_CACHE			0x20000000
574

575 576 577 578 579
/*
 * Flags used by ext4_free_blocks
 */
#define EXT4_FREE_BLOCKS_METADATA	0x0001
#define EXT4_FREE_BLOCKS_FORGET		0x0002
580
#define EXT4_FREE_BLOCKS_VALIDATED	0x0004
581
#define EXT4_FREE_BLOCKS_NO_QUOT_UPDATE	0x0008
582 583
#define EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER	0x0010
#define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER	0x0020
584

585 586 587 588 589 590 591
/* Encryption algorithms */
#define EXT4_ENCRYPTION_MODE_INVALID		0
#define EXT4_ENCRYPTION_MODE_AES_256_XTS	1
#define EXT4_ENCRYPTION_MODE_AES_256_GCM	2
#define EXT4_ENCRYPTION_MODE_AES_256_CBC	3
#define EXT4_ENCRYPTION_MODE_AES_256_CTS	4

592 593
#include "ext4_crypto.h"

594 595 596
/*
 * ioctl commands
 */
597 598 599 600 601 602 603 604
#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)
605 606 607
#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)
608
 /* note ioctl 10 reserved for an early version of the FIEMAP ioctl */
609
 /* note ioctl 11 reserved for filesystem-independent FIEMAP ioctl */
610
#define EXT4_IOC_ALLOC_DA_BLKS		_IO('f', 12)
611
#define EXT4_IOC_MOVE_EXT		_IOWR('f', 15, struct move_extent)
612
#define EXT4_IOC_RESIZE_FS		_IOW('f', 16, __u64)
613
#define EXT4_IOC_SWAP_BOOT		_IO('f', 17)
614
#define EXT4_IOC_PRECACHE_EXTENTS	_IO('f', 18)
615 616 617
#define EXT4_IOC_SET_ENCRYPTION_POLICY	_IOR('f', 19, struct ext4_encryption_policy)
#define EXT4_IOC_GET_ENCRYPTION_PWSALT	_IOW('f', 20, __u8[16])
#define EXT4_IOC_GET_ENCRYPTION_POLICY	_IOW('f', 21, struct ext4_encryption_policy)
618

619
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
620 621 622
/*
 * ioctl commands in 32 bit emulation
 */
623 624 625 626 627 628 629
#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)
630
#define EXT4_IOC32_GROUP_ADD		_IOW('f', 8, struct compat_ext4_new_group_input)
631 632
#define EXT4_IOC32_GETVERSION_OLD	FS_IOC32_GETVERSION
#define EXT4_IOC32_SETVERSION_OLD	FS_IOC32_SETVERSION
633
#endif
634

635
/* Max physical block we can address w/o extents */
636 637
#define EXT4_MAX_BLOCK_FILE_PHYS	0xFFFFFFFF

638 639 640
/*
 * Structure of an inode on the disk
 */
641
struct ext4_inode {
642 643
	__le16	i_mode;		/* File mode */
	__le16	i_uid;		/* Low 16 bits of Owner Uid */
644
	__le32	i_size_lo;	/* Size in bytes */
645
	__le32	i_atime;	/* Access time */
646
	__le32	i_ctime;	/* Inode Change time */
647 648 649 650
	__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 */
651
	__le32	i_blocks_lo;	/* Blocks count */
652 653 654
	__le32	i_flags;	/* File flags */
	union {
		struct {
655
			__le32  l_i_version;
656 657 658 659 660 661 662 663
		} linux1;
		struct {
			__u32  h_i_translator;
		} hurd1;
		struct {
			__u32  m_i_reserved1;
		} masix1;
	} osd1;				/* OS dependent 1 */
664
	__le32	i_block[EXT4_N_BLOCKS];/* Pointers to blocks */
665
	__le32	i_generation;	/* File version (for NFS) */
666
	__le32	i_file_acl_lo;	/* File ACL */
667
	__le32	i_size_high;
668
	__le32	i_obso_faddr;	/* Obsoleted fragment address */
669 670
	union {
		struct {
671
			__le16	l_i_blocks_high; /* were l_i_reserved1 */
672
			__le16	l_i_file_acl_high;
Dave Kleikamp's avatar
Dave Kleikamp committed
673
			__le16	l_i_uid_high;	/* these 2 fields */
674
			__le16	l_i_gid_high;	/* were reserved2[0] */
675 676
			__le16	l_i_checksum_lo;/* crc32c(uuid+inum+inode) LE */
			__le16	l_i_reserved;
677 678
		} linux2;
		struct {
679
			__le16	h_i_reserved1;	/* Obsoleted fragment number/size which are removed in ext4 */
680 681 682 683 684 685
			__u16	h_i_mode_high;
			__u16	h_i_uid_high;
			__u16	h_i_gid_high;
			__u32	h_i_author;
		} hurd2;
		struct {
686
			__le16	h_i_reserved1;	/* Obsoleted fragment number/size which are removed in ext4 */
687
			__le16	m_i_file_acl_high;
688 689 690 691
			__u32	m_i_reserved2[2];
		} masix2;
	} osd2;				/* OS dependent 2 */
	__le16	i_extra_isize;
692
	__le16	i_checksum_hi;	/* crc32c(uuid+inum+inode) BE */
693 694 695 696 697
	__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) */
698
	__le32  i_version_hi;	/* high 32 bits for 64-bit version */
699 700
};

701 702 703 704 705 706 707 708
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 */
};
709

710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732
#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 ?
733 734
			   (time->tv_sec >> 32) & EXT4_EPOCH_MASK : 0) |
                          ((time->tv_nsec << EXT4_EPOCH_BITS) & EXT4_NSEC_MASK));
735 736 737 738 739 740 741
}

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;
742
       time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS;
743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767
}

#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);	       \
768 769
	else								       \
		(inode)->xtime.tv_nsec = 0;				       \
770 771 772 773 774 775 776
} 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);	       \
777 778
	else								       \
		(einode)->xtime.tv_sec = 0;				       \
779 780 781
	if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra))	       \
		ext4_decode_extra_time(&(einode)->xtime,		       \
				       raw_inode->xtime ## _extra);	       \
782 783
	else								       \
		(einode)->xtime.tv_nsec = 0;				       \
784 785
} while (0)

786 787
#define i_disk_version osd1.linux1.l_i_version

788 789
#if defined(__KERNEL__) || defined(__linux__)
#define i_reserved1	osd1.linux1.l_i_reserved1
790
#define i_file_acl_high	osd2.linux2.l_i_file_acl_high
791
#define i_blocks_high	osd2.linux2.l_i_blocks_high
792 793 794 795
#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
796
#define i_checksum_lo	osd2.linux2.l_i_checksum_lo
797 798 799 800 801 802 803 804 805 806 807

#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
808
#define i_file_acl_high	osd2.masix2.m_i_file_acl_high
809 810 811 812
#define i_reserved2	osd2.masix2.m_i_reserved2

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

813 814
#include "extents_status.h"

815 816 817 818 819 820
/*
 * fourth extended file system inode data in memory
 */
struct ext4_inode_info {
	__le32	i_data[15];	/* unconverted */
	__u32	i_dtime;
821
	ext4_fsblk_t	i_file_acl;
822 823 824 825 826 827 828 829 830

	/*
	 * 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;
831
	ext4_lblk_t	i_dir_start_lookup;
832
#if (BITS_PER_LONG < 64)
833
	unsigned long	i_state_flags;		/* Dynamic state flags */
834
#endif
835
	unsigned long	i_flags;
836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876

	/*
	 * 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;
877
	struct jbd2_inode *jinode;
878

879 880
	spinlock_t i_raw_lock;	/* protects updates to the raw inode */

881 882 883 884 885 886 887 888 889 890
	/*
	 * 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;

891 892 893
	/* extents status tree */
	struct ext4_es_tree i_es_tree;
	rwlock_t i_es_lock;
894
	struct list_head i_es_list;
895
	unsigned int i_es_all_nr;	/* protected by i_es_lock */
896
	unsigned int i_es_shk_nr;	/* protected by i_es_lock */
897 898 899
	ext4_lblk_t i_es_shrink_lblk;	/* Offset where we start searching for
					   extents to shrink. Protected by
					   i_es_lock  */
900

901 902 903 904
	/* ialloc */
	ext4_group_t	i_last_alloc_group;

	/* allocation reservation info for delalloc */
905
	/* In case of bigalloc, these refer to clusters rather than blocks */
906 907 908
	unsigned int i_reserved_data_blocks;
	unsigned int i_reserved_meta_blocks;
	unsigned int i_allocated_meta_blocks;
909
	ext4_lblk_t i_da_metadata_calc_last_lblock;
910
	int i_da_metadata_calc_len;
911 912 913

	/* on-disk additional length */
	__u16 i_extra_isize;
914
	char i_crypt_policy_flags;
915

916 917 918 919
	/* Indicate the inline data space. */
	u16 i_inline_off;
	u16 i_inline_size;

920 921 922 923
#ifdef CONFIG_QUOTA
	/* quota space reservation, managed internally by quota code */
	qsize_t i_reserved_quota;
#endif
924

925
	/* Lock protecting lists below */
926
	spinlock_t i_completed_io_lock;
927 928 929 930 931 932 933 934 935
	/*
	 * 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
	 */
936
	atomic_t i_ioend_count;	/* Number of outstanding io_end structs */
937
	atomic_t i_unwritten; /* Nr. of inflight conversions pending */
938
	struct work_struct i_rsv_conversion_work;
939 940

	spinlock_t i_block_reservation_lock;
941 942 943 944 945 946 947

	/*
	 * Transactions that contain inode's metadata needed to complete
	 * fsync and fdatasync, respectively.
	 */
	tid_t i_sync_tid;
	tid_t i_datasync_tid;
948

949 950 951 952
#ifdef CONFIG_QUOTA
	struct dquot *i_dquot[MAXQUOTAS];
#endif

953 954
	/* Precomputed uuid+inum+igen checksum for seeding inode checksums */
	__u32 i_csum_seed;
955 956 957 958 959

#ifdef CONFIG_EXT4_FS_ENCRYPTION
	/* Encryption params */
	struct ext4_encryption_key i_encryption_key;
#endif
960 961
};

962 963 964
/*
 * File system states
 */
965 966 967
#define	EXT4_VALID_FS			0x0001	/* Unmounted cleanly */
#define	EXT4_ERROR_FS			0x0002	/* Errors detected */
#define	EXT4_ORPHAN_FS			0x0004	/* Orphans being recovered */
968

969 970 971 972 973 974 975
/*
 * 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 */

976
/*
977
 * Mount flags set via mount options or defaults
978
 */
979 980 981 982 983
#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 */
984
#define EXT4_MOUNT_ERRORS_MASK		0x00070
985 986
#define EXT4_MOUNT_MINIX_DF		0x00080	/* Mimics the Minix statfs */
#define EXT4_MOUNT_NOLOAD		0x00100	/* Don't use existing journal*/
Ross Zwisler's avatar
Ross Zwisler committed
987 988 989 990 991
#ifdef CONFIG_FS_DAX
#define EXT4_MOUNT_DAX			0x00200	/* Direct Access */
#else
#define EXT4_MOUNT_DAX			0
#endif
992 993 994 995 996 997 998 999
#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 */
1000
#define EXT4_MOUNT_NO_AUTO_DA_ALLOC	0x10000	/* No auto delalloc mapping */
1001 1002 1003 1004
#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 */
1005
#define EXT4_MOUNT_DIOREAD_NOLOCK	0x400000 /* Enable support for dio read nolocking */
1006
#define EXT4_MOUNT_JOURNAL_CHECKSUM	0x800000 /* Journal checksums */
1007
#define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT	0x1000000 /* Journal Async Commit */
1008
#define EXT4_MOUNT_DELALLOC		0x8000000 /* Delalloc support */
1009
#define EXT4_MOUNT_DATA_ERR_ABORT	0x10000000 /* Abort on file data write */
1010
#define EXT4_MOUNT_BLOCK_VALIDITY	0x20000000 /* Block validity checking */
1011
#define EXT4_MOUNT_DISCARD		0x40000000 /* Issue DISCARD requests */
1012
#define EXT4_MOUNT_INIT_INODE_TABLE	0x80000000 /* Initialize uninitialized itables */
1013

1014 1015 1016 1017 1018
/*
 * 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.
 */
1019 1020
#define EXT4_MOUNT2_EXPLICIT_DELALLOC	0x00000001 /* User explicitly
						      specified delalloc */
1021 1022 1023
#define EXT4_MOUNT2_STD_GROUP_SIZE	0x00000002 /* We have standard group
						      size of blocksize * 8
						      blocks */
1024 1025
#define EXT4_MOUNT2_HURD_COMPAT		0x00000004 /* Support HURD-castrated
						      file systems */
1026

1027 1028 1029 1030
#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
1031 1032
#define test_opt(sb, opt)		(EXT4_SB(sb)->s_mount_opt & \
					 EXT4_MOUNT_##opt)
1033

1034 1035 1036 1037 1038 1039 1040
#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)

1041 1042
#define ext4_test_and_set_bit		__test_and_set_bit_le
#define ext4_set_bit			__set_bit_le
1043
#define ext4_set_bit_atomic		ext2_set_bit_atomic
1044 1045
#define ext4_test_and_clear_bit		__test_and_clear_bit_le
#define ext4_clear_bit			__clear_bit_le
1046
#define ext4_clear_bit_atomic		ext2_clear_bit_atomic
1047 1048 1049
#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
1050

1051 1052
extern void ext4_set_bits(void *bm, int cur, int len);

1053 1054 1055
/*
 * Maximal mount counts between two filesystem checks
 */
1056 1057
#define EXT4_DFL_MAX_MNT_COUNT		20	/* Allow 20 mounts */
#define EXT4_DFL_CHECKINTERVAL		0	/* Don't use interval check */
1058 1059 1060 1061

/*
 * Behaviour when detecting errors
 */
1062 1063 1064 1065
#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
1066

1067 1068 1069
/* Metadata checksum algorithm codes */
#define EXT4_CRC32C_CHKSUM		1

1070 1071 1072 1073 1074 1075
/* Encryption algorithms */
#define EXT4_ENCRYPTION_MODE_INVALID		0
#define EXT4_ENCRYPTION_MODE_AES_256_XTS	1
#define EXT4_ENCRYPTION_MODE_AES_256_GCM	2
#define EXT4_ENCRYPTION_MODE_AES_256_CBC	3

1076 1077 1078
/*
 * Structure of the super block
 */
1079
struct ext4_super_block {
1080
/*00*/	__le32	s_inodes_count;		/* Inodes count */
1081
	__le32	s_blocks_count_lo;	/* Blocks count */
1082 1083
	__le32	s_r_blocks_count_lo;	/* Reserved blocks count */
	__le32	s_free_blocks_count_lo;	/* Free blocks count */
1084 1085 1086
/*10*/	__le32	s_free_inodes_count;	/* Free inodes count */
	__le32	s_first_data_block;	/* First Data Block */
	__le32	s_log_block_size;	/* Block size */
1087
	__le32	s_log_cluster_size;	/* Allocation cluster size */
1088
/*20*/	__le32	s_blocks_per_group;	/* # Blocks per group */
1089
	__le32	s_clusters_per_group;	/* # Clusters per group */
1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105
	__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 */
	/*
1106
	 * These fields are for EXT4_DYNAMIC_REV superblocks only.
1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118
	 *
	 * 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 */
1119
	__le16  s_inode_size;		/* size of inode structure */
1120 1121 1122 1123 1124 1125 1126 1127 1128 1129
	__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
1130
	 * happen if the EXT4_FEATURE_COMPAT_DIR_PREALLOC flag is on.
1131 1132 1133 1134 1135
	 */
	__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 */
	/*
1136
	 * Journaling support valid if EXT4_FEATURE_COMPAT_HAS_JOURNAL set.
1137 1138 1139 1140 1141 1142 1143
	 */
/*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 */
1144
	__u8	s_jnl_backup_type;
1145
	__le16  s_desc_size;		/* size of group descriptor */
1146
/*100*/	__le32	s_default_mount_opts;
1147
	__le32	s_first_meta_bg;	/* First metablock block group */
1148 1149 1150 1151 1152 1153
	__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 */
Aneesh Kumar K.V's avatar
Aneesh Kumar K.V committed
1154 1155 1156 1157
	__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 */
1158
	__le16  s_mmp_update_interval;  /* # seconds to wait in MMP checking */
Aneesh Kumar K.V's avatar
Aneesh Kumar K.V committed
1159 1160
	__le64  s_mmp_block;            /* Block for multi-mount protection */
	__le32  s_raid_stripe_width;    /* blocks on all data disks (N*stride)*/
1161
	__u8	s_log_groups_per_flex;  /* FLEX_BG group size */
1162
	__u8	s_checksum_type;	/* metadata checksum algorithm used */
1163 1164
	__u8	s_encryption_level;	/* versioning level for encryption */
	__u8	s_reserved_pad;		/* Padding to next 32bits */
1165
	__le64	s_kbytes_written;	/* nr of lifetime kilobytes written */
1166 1167 1168 1169 1170 1171
	__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 */
1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183
#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 */
1184 1185
#define EXT4_S_ERR_END offsetof(struct ext4_super_block, s_mount_opts)
	__u8	s_mount_opts[64];
1186 1187 1188
	__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 */
1189
	__le32	s_backup_bgs[2];	/* groups with sparse_super2 SBs */
1190
	__u8	s_encrypt_algos[4];	/* Encryption algorithms in use  */
1191 1192 1193
	__u8	s_encrypt_pw_salt[16];	/* Salt used for string2key algorithm */
	__le32	s_lpf_ino;		/* Location of the lost+found inode */
	__le32	s_reserved[100];	/* Padding to the end of the block */
1194
	__le32	s_checksum;		/* crc32c(superblock) */
1195 1196
};

1197 1198
#define EXT4_S_ERR_LEN (EXT4_S_ERR_END - EXT4_S_ERR_START)

1199
#ifdef __KERNEL__
1200 1201

/*
1202
 * run-time mount flags
1203
 */