ext4.h 127.1 KB
Newer Older
1
// SPDX-License-Identifier: GPL-2.0
2
/*
3
 *  ext4.h
4 5 6 7 8 9 10 11 12 13 14 15 16
 *
 * 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
 */

17 18
#ifndef _EXT4_H
#define _EXT4_H
19 20

#include <linux/types.h>
21
#include <linux/blkdev.h>
22
#include <linux/magic.h>
23
#include <linux/jbd2.h>
24
#include <linux/quota.h>
25 26 27 28
#include <linux/rwsem.h>
#include <linux/rbtree.h>
#include <linux/seqlock.h>
#include <linux/mutex.h>
29 30
#include <linux/timer.h>
#include <linux/wait.h>
31
#include <linux/sched/signal.h>
32 33
#include <linux/blockgroup_lock.h>
#include <linux/percpu_counter.h>
34
#include <linux/ratelimit.h>
35
#include <crypto/hash.h>
36
#include <linux/falloc.h>
37
#include <linux/percpu-rwsem.h>
38
#include <linux/fiemap.h>
39 40 41
#ifdef __KERNEL__
#include <linux/compat.h>
#endif
42

D
Dave Chinner 已提交
43
#include <linux/fscrypt.h>
E
Eric Biggers 已提交
44
#include <linux/fsverity.h>
D
Dave Chinner 已提交
45

46 47
#include <linux/compiler.h>

48
/*
S
Shen Feng 已提交
49
 * The fourth extended filesystem constants/structures
50 51
 */

52 53 54 55 56 57 58 59 60 61 62 63
/*
 * with AGGRESSIVE_CHECK allocator runs consistency checks over
 * structures. these checks slow things down a lot
 */
#define AGGRESSIVE_CHECK__

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

64
/*
65
 * Define EXT4FS_DEBUG to produce debug messages
66
 */
67
#undef EXT4FS_DEBUG
68 69 70 71

/*
 * Debug code
 */
72 73
#ifdef EXT4FS_DEBUG
#define ext4_debug(f, a...)						\
74
	do {								\
75
		printk(KERN_DEBUG "EXT4-fs DEBUG (%s, %d): %s:",	\
76
			__FILE__, __LINE__, __func__);			\
77
		printk(KERN_DEBUG f, ## a);				\
78 79
	} while (0)
#else
80
#define ext4_debug(fmt, ...)	no_printk(fmt, ##__VA_ARGS__)
81 82
#endif

83 84 85 86 87
 /*
  * Turn on EXT_DEBUG to enable ext4_ext_show_path/leaf/move in extents.c
  */
#define EXT_DEBUG__

88
/*
89
 * Dynamic printk for controlled extents debugging.
90
 */
91 92 93 94 95 96
#ifdef CONFIG_EXT4_DEBUG
#define ext_debug(ino, fmt, ...)					\
	pr_debug("[%s/%d] EXT4-fs (%s): ino %lu: (%s, %d): %s:" fmt,	\
		 current->comm, task_pid_nr(current),			\
		 ino->i_sb->s_id, ino->i_ino, __FILE__, __LINE__,	\
		 __func__, ##__VA_ARGS__)
97
#else
98
#define ext_debug(ino, fmt, ...)	no_printk(fmt, ##__VA_ARGS__)
99 100
#endif

101 102 103 104 105 106 107 108 109 110 111 112
/* 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;

113 114 115 116 117
enum SHIFT_DIRECTION {
	SHIFT_LEFT = 0,
	SHIFT_RIGHT,
};

118
/*
119
 * Flags used in mballoc's allocation_context flags field.
120 121 122 123
 *
 * Also used to show what's going on for debugging purposes when the
 * flag field is exported via the traceport interface
 */
124

125
/* prefer goal again. length */
126
#define EXT4_MB_HINT_MERGE		0x0001
127
/* blocks already reserved */
128
#define EXT4_MB_HINT_RESERVED		0x0002
129
/* metadata is being allocated */
130
#define EXT4_MB_HINT_METADATA		0x0004
131
/* first blocks in the file */
132
#define EXT4_MB_HINT_FIRST		0x0008
133
/* search for the best chunk */
134
#define EXT4_MB_HINT_BEST		0x0010
135
/* data is being allocated */
136
#define EXT4_MB_HINT_DATA		0x0020
137
/* don't preallocate (for tails) */
138
#define EXT4_MB_HINT_NOPREALLOC		0x0040
139
/* allocate for locality group */
140
#define EXT4_MB_HINT_GROUP_ALLOC	0x0080
141
/* allocate goal blocks or none */
142
#define EXT4_MB_HINT_GOAL_ONLY		0x0100
143
/* goal is meaningful */
144
#define EXT4_MB_HINT_TRY_GOAL		0x0200
145
/* blocks already pre-reserved by delayed allocation */
146
#define EXT4_MB_DELALLOC_RESERVED	0x0400
147 148
/* We are doing stream allocation */
#define EXT4_MB_STREAM_ALLOC		0x0800
149 150
/* Use reserved root blocks if needed */
#define EXT4_MB_USE_ROOT_BLOCKS		0x1000
L
Lukas Czerner 已提交
151 152
/* Use blocks from reserved pool */
#define EXT4_MB_USE_RESERVED		0x2000
153 154
/* Do strict check for free blocks while retrying block allocation */
#define EXT4_MB_STRICT_CHECK		0x4000
155 156 157 158

struct ext4_allocation_request {
	/* target inode for block we're allocating */
	struct inode *inode;
159 160
	/* how many blocks we want to allocate */
	unsigned int len;
161 162 163 164 165 166
	/* 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;
167 168 169 170 171
	/* 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 */
172 173
	ext4_fsblk_t pright;
	/* flags. see above EXT4_MB_HINT_* */
174
	unsigned int flags;
175 176
};

177 178 179 180 181 182 183
/*
 * 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.
 */
184 185 186 187
#define EXT4_MAP_NEW		BIT(BH_New)
#define EXT4_MAP_MAPPED		BIT(BH_Mapped)
#define EXT4_MAP_UNWRITTEN	BIT(BH_Unwritten)
#define EXT4_MAP_BOUNDARY	BIT(BH_Boundary)
188
#define EXT4_MAP_FLAGS		(EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
189
				 EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY)
190 191 192 193 194 195 196 197

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

198 199 200 201 202 203 204 205
/*
 * Block validity checking, system zone rbtree.
 */
struct ext4_system_blocks {
	struct rb_root root;
	struct rcu_head rcu;
};

206 207 208 209 210
/*
 * Flags for ext4_io_end->flags
 */
#define	EXT4_IO_END_UNWRITTEN	0x0001

211 212 213 214 215 216
struct ext4_io_end_vec {
	struct list_head list;		/* list of io_end_vec */
	loff_t offset;			/* offset in the file */
	ssize_t size;			/* size of the extent */
};

217
/*
218
 * For converting unwritten extents on a work queue. 'handle' is used for
219
 * buffered writeback.
220
 */
221
typedef struct ext4_io_end {
222
	struct list_head	list;		/* per-file finished IO list */
223 224
	handle_t		*handle;	/* handle reserved for extent
						 * conversion */
225
	struct inode		*inode;		/* file being written to */
226 227
	struct bio		*bio;		/* Linked list of completed
						 * bios covering the extent */
228
	unsigned int		flag;		/* unwritten or not */
J
Jan Kara 已提交
229
	atomic_t		count;		/* reference counter */
230
	struct list_head	list_vec;	/* list of ext4_io_end_vec */
231 232
} ext4_io_end_t;

233
struct ext4_io_submit {
234
	struct writeback_control *io_wbc;
235 236 237 238 239
	struct bio		*io_bio;
	ext4_io_end_t		*io_end;
	sector_t		io_next_block;
};

240 241 242
/*
 * Special inodes numbers
 */
243 244
#define	EXT4_BAD_INO		 1	/* Bad blocks inode */
#define EXT4_ROOT_INO		 2	/* Root inode */
245 246
#define EXT4_USR_QUOTA_INO	 3	/* User quota inode */
#define EXT4_GRP_QUOTA_INO	 4	/* Group quota inode */
247 248 249 250
#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 */
251

252 253
/* First non-reserved inode for old ext4 filesystems */
#define EXT4_GOOD_OLD_FIRST_INO	11
254 255 256 257

/*
 * Maximal count of links to a file
 */
258
#define EXT4_LINK_MAX		65000
259 260 261 262

/*
 * Macro-instructions used to manage several block sizes
 */
263
#define EXT4_MIN_BLOCK_SIZE		1024
264 265
#define	EXT4_MAX_BLOCK_SIZE		65536
#define EXT4_MIN_BLOCK_LOG_SIZE		10
266
#define EXT4_MAX_BLOCK_LOG_SIZE		16
267
#define EXT4_MAX_CLUSTER_LOG_SIZE	30
268
#ifdef __KERNEL__
269
# define EXT4_BLOCK_SIZE(s)		((s)->s_blocksize)
270
#else
271
# define EXT4_BLOCK_SIZE(s)		(EXT4_MIN_BLOCK_SIZE << (s)->s_log_block_size)
272
#endif
273
#define	EXT4_ADDR_PER_BLOCK(s)		(EXT4_BLOCK_SIZE(s) / sizeof(__u32))
274 275
#define EXT4_CLUSTER_SIZE(s)		(EXT4_BLOCK_SIZE(s) << \
					 EXT4_SB(s)->s_cluster_bits)
276
#ifdef __KERNEL__
277
# define EXT4_BLOCK_SIZE_BITS(s)	((s)->s_blocksize_bits)
278
# define EXT4_CLUSTER_BITS(s)		(EXT4_SB(s)->s_cluster_bits)
279
#else
280
# define EXT4_BLOCK_SIZE_BITS(s)	((s)->s_log_block_size + 10)
281 282
#endif
#ifdef __KERNEL__
283 284 285
#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)
286
#else
287 288
#define EXT4_INODE_SIZE(s)	(((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \
				 EXT4_GOOD_OLD_INODE_SIZE : \
289
				 (s)->s_inode_size)
290 291
#define EXT4_FIRST_INO(s)	(((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \
				 EXT4_GOOD_OLD_FIRST_INO : \
292 293
				 (s)->s_first_ino)
#endif
A
Amit Arora 已提交
294
#define EXT4_BLOCK_ALIGN(size, blkbits)		ALIGN((size), (1 << (blkbits)))
295 296 297
#define EXT4_MAX_BLOCKS(size, offset, blkbits) \
	((EXT4_BLOCK_ALIGN(size + offset, blkbits) >> blkbits) - (offset >> \
								  blkbits))
298

299 300 301 302 303 304 305
/* 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)
306 307 308 309 310
/* 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))
311 312 313
/* Fill in the low bits to get the last block of the cluster */
#define EXT4_LBLK_CFILL(sbi, lblk) ((lblk) |				\
				    ((ext4_lblk_t) (sbi)->s_cluster_ratio - 1))
314 315 316 317 318
/* 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))
319

320 321 322
/*
 * Structure of a blocks group descriptor
 */
323
struct ext4_group_desc
324
{
325
	__le32	bg_block_bitmap_lo;	/* Blocks bitmap block */
326 327
	__le32	bg_inode_bitmap_lo;	/* Inodes bitmap block */
	__le32	bg_inode_table_lo;	/* Inodes table block */
328 329 330
	__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
331
	__le16	bg_flags;		/* EXT4_BG_flags (INODE_UNINIT, etc) */
332 333 334
	__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 */
335
	__le16  bg_itable_unused_lo;	/* Unused inodes count */
A
Andreas Dilger 已提交
336
	__le16  bg_checksum;		/* crc16(sb_uuid+group+desc) */
337 338 339
	__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 */
340 341 342
	__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 */
343
	__le16  bg_itable_unused_hi;    /* Unused inodes count MSB */
344 345 346 347
	__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;
348 349
};

350 351 352 353 354 355 356
#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))

357 358 359 360 361
/*
 * Structure of a flex block group info
 */

struct flex_groups {
362 363 364
	atomic64_t	free_clusters;
	atomic_t	free_inodes;
	atomic_t	used_dirs;
365 366
};

A
Andreas Dilger 已提交
367 368 369 370
#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 */

371 372 373
/*
 * Macro-instructions used to manage group descriptors
 */
374
#define EXT4_MIN_DESC_SIZE		32
375
#define EXT4_MIN_DESC_SIZE_64BIT	64
376 377
#define	EXT4_MAX_DESC_SIZE		EXT4_MIN_BLOCK_SIZE
#define EXT4_DESC_SIZE(s)		(EXT4_SB(s)->s_desc_size)
378
#ifdef __KERNEL__
379
# define EXT4_BLOCKS_PER_GROUP(s)	(EXT4_SB(s)->s_blocks_per_group)
380
# define EXT4_CLUSTERS_PER_GROUP(s)	(EXT4_SB(s)->s_clusters_per_group)
381 382 383
# 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)
384
#else
385
# define EXT4_BLOCKS_PER_GROUP(s)	((s)->s_blocks_per_group)
386
# define EXT4_DESC_PER_BLOCK(s)		(EXT4_BLOCK_SIZE(s) / EXT4_DESC_SIZE(s))
387
# define EXT4_INODES_PER_GROUP(s)	((s)->s_inodes_per_group)
388 389 390 391 392
#endif

/*
 * Constants relative to the data blocks
 */
393 394 395 396 397
#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)
398 399 400 401

/*
 * Inode flags
 */
402 403 404 405 406 407 408 409
#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 */
410
/* Reserved for compression usage... */
411 412 413
#define EXT4_DIRTY_FL			0x00000100
#define EXT4_COMPRBLK_FL		0x00000200 /* One or more compressed clusters */
#define EXT4_NOCOMPR_FL			0x00000400 /* Don't compress */
414 415
	/* nb: was previously EXT2_ECOMPR_FL */
#define EXT4_ENCRYPT_FL			0x00000800 /* encrypted file */
416
/* End compression flags --- maybe not all used */
417 418 419 420 421 422
#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
423
#define EXT4_HUGE_FILE_FL               0x00040000 /* Set to each huge file */
A
Alex Tomas 已提交
424
#define EXT4_EXTENTS_FL			0x00080000 /* Inode uses extents */
E
Eric Biggers 已提交
425
#define EXT4_VERITY_FL			0x00100000 /* Verity protected inode */
426
#define EXT4_EA_INODE_FL	        0x00200000 /* Inode used for large EA */
427
/* 0x00400000 was formerly EXT4_EOFBLOCKS_FL */
I
Ira Weiny 已提交
428 429 430

#define EXT4_DAX_FL			0x02000000 /* Inode is DAX */

431
#define EXT4_INLINE_DATA_FL		0x10000000 /* Inode has inline data. */
432
#define EXT4_PROJINHERIT_FL		0x20000000 /* Create with parents projid */
433
#define EXT4_CASEFOLD_FL		0x40000000 /* Casefolded directory */
A
Aneesh Kumar K.V 已提交
434
#define EXT4_RESERVED_FL		0x80000000 /* reserved for ext4 lib */
435

436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463
/* User modifiable flags */
#define EXT4_FL_USER_MODIFIABLE		(EXT4_SECRM_FL | \
					 EXT4_UNRM_FL | \
					 EXT4_COMPR_FL | \
					 EXT4_SYNC_FL | \
					 EXT4_IMMUTABLE_FL | \
					 EXT4_APPEND_FL | \
					 EXT4_NODUMP_FL | \
					 EXT4_NOATIME_FL | \
					 EXT4_JOURNAL_DATA_FL | \
					 EXT4_NOTAIL_FL | \
					 EXT4_DIRSYNC_FL | \
					 EXT4_TOPDIR_FL | \
					 EXT4_EXTENTS_FL | \
					 0x00400000 /* EXT4_EOFBLOCKS_FL */ | \
					 EXT4_DAX_FL | \
					 EXT4_PROJINHERIT_FL | \
					 EXT4_CASEFOLD_FL)

/* User visible flags */
#define EXT4_FL_USER_VISIBLE		(EXT4_FL_USER_MODIFIABLE | \
					 EXT4_DIRTY_FL | \
					 EXT4_COMPRBLK_FL | \
					 EXT4_NOCOMPR_FL | \
					 EXT4_ENCRYPT_FL | \
					 EXT4_INDEX_FL | \
					 EXT4_VERITY_FL | \
					 EXT4_INLINE_DATA_FL)
464

465
/* Flags we can manipulate with through FS_IOC_FSSETXATTR */
466 467 468 469 470
#define EXT4_FL_XFLAG_VISIBLE		(EXT4_SYNC_FL | \
					 EXT4_IMMUTABLE_FL | \
					 EXT4_APPEND_FL | \
					 EXT4_NODUMP_FL | \
					 EXT4_NOATIME_FL | \
I
Ira Weiny 已提交
471 472
					 EXT4_PROJINHERIT_FL | \
					 EXT4_DAX_FL)
473

474 475
/* Flags that should be inherited by new inodes from their parent. */
#define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\
476
			   EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
477
			   EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\
L
Li Xi 已提交
478
			   EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL |\
I
Ira Weiny 已提交
479 480
			   EXT4_PROJINHERIT_FL | EXT4_CASEFOLD_FL |\
			   EXT4_DAX_FL)
481

482
/* Flags that are appropriate for regular files (all but dir-specific ones). */
483 484
#define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL | EXT4_CASEFOLD_FL |\
			   EXT4_PROJINHERIT_FL))
485 486 487 488

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

Y
yangerkun 已提交
489 490 491
/* The only flags that should be swapped */
#define EXT4_FL_SHOULD_SWAP (EXT4_HUGE_FILE_FL | EXT4_EXTENTS_FL)

I
Ira Weiny 已提交
492 493
/* Flags which are mutually exclusive to DAX */
#define EXT4_DAX_MUT_EXCL (EXT4_VERITY_FL | EXT4_ENCRYPT_FL |\
494
			   EXT4_JOURNAL_DATA_FL | EXT4_INLINE_DATA_FL)
I
Ira Weiny 已提交
495

496 497 498 499 500 501 502 503 504 505 506
/* 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;
}

507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522
/*
 * 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 */
523
	EXT4_INODE_ENCRYPT	= 11,	/* Encrypted file */
524 525 526 527 528 529 530 531 532
/* 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 */
E
Eric Biggers 已提交
533
	EXT4_INODE_VERITY	= 20,	/* Verity protected inode */
534
	EXT4_INODE_EA_INODE	= 21,	/* Inode used for large EA */
535
/* 22 was formerly EXT4_INODE_EOFBLOCKS */
I
Ira Weiny 已提交
536
	EXT4_INODE_DAX		= 25,	/* Inode is DAX */
537
	EXT4_INODE_INLINE_DATA	= 28,	/* Data in inode. */
538
	EXT4_INODE_PROJINHERIT	= 29,	/* Create with parents projid */
539
	EXT4_INODE_CASEFOLD	= 30,	/* Casefolded directory */
540 541 542 543
	EXT4_INODE_RESERVED	= 31,	/* reserved for ext4 lib */
};

/*
544 545 546 547 548 549 550 551 552
 * 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.
553 554 555
 *
 * It's not paranoia if the Murphy's Law really *is* out to get you.  :-)
 */
556 557 558
#define TEST_FLAG_VALUE(FLAG) (EXT4_##FLAG##_FL == (1 << EXT4_INODE_##FLAG))
#define CHECK_FLAG_VALUE(FLAG) BUILD_BUG_ON(!TEST_FLAG_VALUE(FLAG))

559 560 561 562 563 564 565 566 567 568 569 570 571
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);
572
	CHECK_FLAG_VALUE(ENCRYPT);
573 574 575 576 577 578 579 580
	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);
E
Eric Biggers 已提交
581
	CHECK_FLAG_VALUE(VERITY);
582
	CHECK_FLAG_VALUE(EA_INODE);
583
	CHECK_FLAG_VALUE(INLINE_DATA);
584
	CHECK_FLAG_VALUE(PROJINHERIT);
585
	CHECK_FLAG_VALUE(CASEFOLD);
586 587 588
	CHECK_FLAG_VALUE(RESERVED);
}

589
/* Used to pass group descriptor data when online resize is done */
590
struct ext4_new_group_input {
D
Dave Kleikamp 已提交
591 592 593 594 595 596
	__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 */
597 598 599
	__u16 unused;
};

600 601 602 603 604 605 606 607 608 609 610 611
#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

612 613
/* The struct ext4_new_group_input in kernel space, with free_blocks_count */
struct ext4_new_group_data {
614
	__u32 group;
L
Laurent Vivier 已提交
615 616 617
	__u64 block_bitmap;
	__u64 inode_bitmap;
	__u64 inode_table;
618 619
	__u32 blocks_count;
	__u16 reserved_blocks;
620 621
	__u16 mdata_blocks;
	__u32 free_clusters_count;
622 623
};

624 625 626 627 628 629 630 631
/* 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
632
/*
633
 * Flags used by ext4_map_blocks()
A
Amit Arora 已提交
634
 */
635
	/* Allocate any needed blocks and/or convert an unwritten
636
	   extent to be an initialized ext4 */
637
#define EXT4_GET_BLOCKS_CREATE			0x0001
638 639 640
	/* 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|\
641
						 EXT4_GET_BLOCKS_CREATE)
L
Lukas Czerner 已提交
642 643
	/* Caller is from the delayed allocation writeout path
	 * finally doing the actual allocation of delayed blocks */
644
#define EXT4_GET_BLOCKS_DELALLOC_RESERVE	0x0004
645
	/* caller is from the direct IO path, request to creation of an
646
	unwritten extents if not allocated, split the unwritten
647
	extent if blocks has been preallocated already*/
648
#define EXT4_GET_BLOCKS_PRE_IO			0x0008
649
#define EXT4_GET_BLOCKS_CONVERT			0x0010
650
#define EXT4_GET_BLOCKS_IO_CREATE_EXT		(EXT4_GET_BLOCKS_PRE_IO|\
651
					 EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT)
652 653
	/* Convert extent to initialized after IO complete */
#define EXT4_GET_BLOCKS_IO_CONVERT_EXT		(EXT4_GET_BLOCKS_CONVERT|\
654
					 EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT)
L
Lukas Czerner 已提交
655 656 657
	/* 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
658 659
	/* Don't normalize allocation size (used for fallocate) */
#define EXT4_GET_BLOCKS_NO_NORMALIZE		0x0040
660
	/* Convert written extents to unwritten */
661
#define EXT4_GET_BLOCKS_CONVERT_UNWRITTEN	0x0100
662 663 664 665
	/* Write zeros to newly created written extents */
#define EXT4_GET_BLOCKS_ZERO			0x0200
#define EXT4_GET_BLOCKS_CREATE_ZERO		(EXT4_GET_BLOCKS_CREATE |\
					EXT4_GET_BLOCKS_ZERO)
666 667 668
	/* Caller will submit data before dropping transaction handle. This
	 * allows jbd2 to avoid submitting data before commit. */
#define EXT4_GET_BLOCKS_IO_SUBMIT		0x0400
669

670
/*
671
 * The bit position of these flags must not overlap with any of the
672
 * EXT4_GET_BLOCKS_*.  They are used by ext4_find_extent(),
673
 * read_extent_tree_block(), ext4_split_extent_at(),
674 675 676 677
 * 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.
678
 */
679 680
#define EXT4_EX_NOCACHE				0x40000000
#define EXT4_EX_FORCE_CACHE			0x20000000
681
#define EXT4_EX_NOFAIL				0x10000000
682

683 684 685
/*
 * Flags used by ext4_free_blocks
 */
686 687 688 689
#define EXT4_FREE_BLOCKS_METADATA		0x0001
#define EXT4_FREE_BLOCKS_FORGET			0x0002
#define EXT4_FREE_BLOCKS_VALIDATED		0x0004
#define EXT4_FREE_BLOCKS_NO_QUOT_UPDATE		0x0008
690 691
#define EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER	0x0010
#define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER	0x0020
692
#define EXT4_FREE_BLOCKS_RERESERVE_CLUSTER      0x0040
693

694 695 696
/*
 * ioctl commands
 */
697 698 699 700 701 702
#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
703 704 705
#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)
706
 /* note ioctl 10 reserved for an early version of the FIEMAP ioctl */
T
Theodore Ts'o 已提交
707
 /* note ioctl 11 reserved for filesystem-independent FIEMAP ioctl */
708
#define EXT4_IOC_ALLOC_DA_BLKS		_IO('f', 12)
709
#define EXT4_IOC_MOVE_EXT		_IOWR('f', 15, struct move_extent)
710
#define EXT4_IOC_RESIZE_FS		_IOW('f', 16, __u64)
711
#define EXT4_IOC_SWAP_BOOT		_IO('f', 17)
712
#define EXT4_IOC_PRECACHE_EXTENTS	_IO('f', 18)
713 714
/* ioctl codes 19--39 are reserved for fscrypt */
#define EXT4_IOC_CLEAR_ES_CACHE		_IO('f', 40)
715
#define EXT4_IOC_GETSTATE		_IOW('f', 41, __u32)
716
#define EXT4_IOC_GET_ES_CACHE		_IOWR('f', 42, struct fiemap)
717

718
#define EXT4_IOC_SHUTDOWN _IOR ('X', 125, __u32)
719 720 721 722 723 724 725 726

/*
 * Flags for going down operation
 */
#define EXT4_GOING_FLAGS_DEFAULT		0x0	/* going down */
#define EXT4_GOING_FLAGS_LOGFLUSH		0x1	/* flush log but not data */
#define EXT4_GOING_FLAGS_NOLOGFLUSH		0x2	/* don't flush log nor data */

727 728 729 730 731 732 733 734 735 736
/*
 * Flags returned by EXT4_IOC_GETSTATE
 *
 * We only expose to userspace a subset of the state flags in
 * i_state_flags
 */
#define EXT4_STATE_FLAG_EXT_PRECACHED	0x00000001
#define EXT4_STATE_FLAG_NEW		0x00000002
#define EXT4_STATE_FLAG_NEWENTRY	0x00000004
#define EXT4_STATE_FLAG_DA_ALLOC_CLOSE	0x00000008
737

738
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
739 740 741
/*
 * ioctl commands in 32 bit emulation
 */
742 743 744 745 746
#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)
747
#define EXT4_IOC32_GROUP_ADD		_IOW('f', 8, struct compat_ext4_new_group_input)
748 749
#define EXT4_IOC32_GETVERSION_OLD	FS_IOC32_GETVERSION
#define EXT4_IOC32_SETVERSION_OLD	FS_IOC32_SETVERSION
750
#endif
751

752 753 754 755 756 757
/*
 * Returned by EXT4_IOC_GET_ES_CACHE as an additional possible flag.
 * It indicates that the entry in extent status cache is for a hole.
 */
#define EXT4_FIEMAP_EXTENT_HOLE		0x08000000

758
/* Max physical block we can address w/o extents */
759 760
#define EXT4_MAX_BLOCK_FILE_PHYS	0xFFFFFFFF

761
/* Max logical block we can support */
762
#define EXT4_MAX_LOGICAL_BLOCK		0xFFFFFFFE
763

764 765 766
/*
 * Structure of an inode on the disk
 */
767
struct ext4_inode {
768 769
	__le16	i_mode;		/* File mode */
	__le16	i_uid;		/* Low 16 bits of Owner Uid */
770
	__le32	i_size_lo;	/* Size in bytes */
771
	__le32	i_atime;	/* Access time */
K
Kalpak Shah 已提交
772
	__le32	i_ctime;	/* Inode Change time */
773 774 775 776
	__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 */
777
	__le32	i_blocks_lo;	/* Blocks count */
778 779 780
	__le32	i_flags;	/* File flags */
	union {
		struct {
781
			__le32  l_i_version;
782 783 784 785 786 787 788 789
		} linux1;
		struct {
			__u32  h_i_translator;
		} hurd1;
		struct {
			__u32  m_i_reserved1;
		} masix1;
	} osd1;				/* OS dependent 1 */
790
	__le32	i_block[EXT4_N_BLOCKS];/* Pointers to blocks */
791
	__le32	i_generation;	/* File version (for NFS) */
792
	__le32	i_file_acl_lo;	/* File ACL */
793
	__le32	i_size_high;
794
	__le32	i_obso_faddr;	/* Obsoleted fragment address */
795 796
	union {
		struct {
797
			__le16	l_i_blocks_high; /* were l_i_reserved1 */
B
Badari Pulavarty 已提交
798
			__le16	l_i_file_acl_high;
D
Dave Kleikamp 已提交
799
			__le16	l_i_uid_high;	/* these 2 fields */
800
			__le16	l_i_gid_high;	/* were reserved2[0] */
801 802
			__le16	l_i_checksum_lo;/* crc32c(uuid+inum+inode) LE */
			__le16	l_i_reserved;
803 804
		} linux2;
		struct {
805
			__le16	h_i_reserved1;	/* Obsoleted fragment number/size which are removed in ext4 */
806 807 808 809 810 811
			__u16	h_i_mode_high;
			__u16	h_i_uid_high;
			__u16	h_i_gid_high;
			__u32	h_i_author;
		} hurd2;
		struct {
812
			__le16	h_i_reserved1;	/* Obsoleted fragment number/size which are removed in ext4 */
B
Badari Pulavarty 已提交
813
			__le16	m_i_file_acl_high;
814 815 816 817
			__u32	m_i_reserved2[2];
		} masix2;
	} osd2;				/* OS dependent 2 */
	__le16	i_extra_isize;
818
	__le16	i_checksum_hi;	/* crc32c(uuid+inum+inode) BE */
K
Kalpak Shah 已提交
819 820 821 822 823
	__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) */
824
	__le32  i_version_hi;	/* high 32 bits for 64-bit version */
825
	__le32	i_projid;	/* Project ID */
826 827
};

828 829 830 831 832 833 834 835
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 */
};
836

K
Kalpak Shah 已提交
837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856
#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))			\

857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877
/*
 * We use an encoding that preserves the times for extra epoch "00":
 *
 * extra  msb of                         adjust for signed
 * epoch  32-bit                         32-bit tv_sec to
 * bits   time    decoded 64-bit tv_sec  64-bit tv_sec      valid time range
 * 0 0    1    -0x80000000..-0x00000001  0x000000000 1901-12-13..1969-12-31
 * 0 0    0    0x000000000..0x07fffffff  0x000000000 1970-01-01..2038-01-19
 * 0 1    1    0x080000000..0x0ffffffff  0x100000000 2038-01-19..2106-02-07
 * 0 1    0    0x100000000..0x17fffffff  0x100000000 2106-02-07..2174-02-25
 * 1 0    1    0x180000000..0x1ffffffff  0x200000000 2174-02-25..2242-03-16
 * 1 0    0    0x200000000..0x27fffffff  0x200000000 2242-03-16..2310-04-04
 * 1 1    1    0x280000000..0x2ffffffff  0x300000000 2310-04-04..2378-04-22
 * 1 1    0    0x300000000..0x37fffffff  0x300000000 2378-04-22..2446-05-10
 *
 * Note that previous versions of the kernel on 64-bit systems would
 * incorrectly use extra epoch bits 1,1 for dates between 1901 and
 * 1970.  e2fsck will correct this, assuming that it is run on the
 * affected filesystem before 2242.
 */

878
static inline __le32 ext4_encode_extra_time(struct timespec64 *time)
K
Kalpak Shah 已提交
879
{
880
	u32 extra =((time->tv_sec - (s32)time->tv_sec) >> 32) & EXT4_EPOCH_MASK;
881
	return cpu_to_le32(extra | (time->tv_nsec << EXT4_EPOCH_BITS));
K
Kalpak Shah 已提交
882 883
}

884 885
static inline void ext4_decode_extra_time(struct timespec64 *time,
					  __le32 extra)
K
Kalpak Shah 已提交
886
{
887
	if (unlikely(extra & cpu_to_le32(EXT4_EPOCH_MASK)))
888 889
		time->tv_sec += (u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK) << 32;
	time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS;
K
Kalpak Shah 已提交
890 891
}

892 893 894
#define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode)				\
do {										\
	if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra))     {\
895
		(raw_inode)->xtime = cpu_to_le32((inode)->xtime.tv_sec);	\
896
		(raw_inode)->xtime ## _extra =					\
897
				ext4_encode_extra_time(&(inode)->xtime);	\
898
		}								\
899
	else	\
900
		(raw_inode)->xtime = cpu_to_le32(clamp_t(int32_t, (inode)->xtime.tv_sec, S32_MIN, S32_MAX));	\
K
Kalpak Shah 已提交
901 902 903 904 905 906 907 908 909 910 911
} 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)

912 913 914 915
#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)) {	\
916
		ext4_decode_extra_time(&(inode)->xtime,				\
917 918 919 920
				       raw_inode->xtime ## _extra);		\
		}								\
	else									\
		(inode)->xtime.tv_nsec = 0;					\
K
Kalpak Shah 已提交
921 922
} while (0)

923

K
Kalpak Shah 已提交
924 925 926 927 928
#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);	       \
929 930
	else								       \
		(einode)->xtime.tv_sec = 0;				       \
K
Kalpak Shah 已提交
931 932 933
	if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra))	       \
		ext4_decode_extra_time(&(einode)->xtime,		       \
				       raw_inode->xtime ## _extra);	       \
934 935
	else								       \
		(einode)->xtime.tv_nsec = 0;				       \
K
Kalpak Shah 已提交
936 937
} while (0)

938 939
#define i_disk_version osd1.linux1.l_i_version

940 941
#if defined(__KERNEL__) || defined(__linux__)
#define i_reserved1	osd1.linux1.l_i_reserved1
B
Badari Pulavarty 已提交
942
#define i_file_acl_high	osd2.linux2.l_i_file_acl_high
943
#define i_blocks_high	osd2.linux2.l_i_blocks_high
944 945 946 947
#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
948
#define i_checksum_lo	osd2.linux2.l_i_checksum_lo
949 950 951 952 953 954 955 956 957 958 959

#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
960
#define i_file_acl_high	osd2.masix2.m_i_file_acl_high
961 962 963 964
#define i_reserved2	osd2.masix2.m_i_reserved2

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

965
#include "extents_status.h"
966
#include "fast_commit.h"
967

968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990
/*
 * Lock subclasses for i_data_sem in the ext4_inode_info structure.
 *
 * These are needed to avoid lockdep false positives when we need to
 * allocate blocks to the quota inode during ext4_map_blocks(), while
 * holding i_data_sem for a normal (non-quota) inode.  Since we don't
 * do quota tracking for the quota inode, this avoids deadlock (as
 * well as infinite recursion, since it isn't turtles all the way
 * down...)
 *
 *  I_DATA_SEM_NORMAL - Used for most inodes
 *  I_DATA_SEM_OTHER  - Used by move_inode.c for the second normal inode
 *			  where the second inode has larger inode number
 *			  than the first
 *  I_DATA_SEM_QUOTA  - Used for quota inodes only
 */
enum {
	I_DATA_SEM_NORMAL = 0,
	I_DATA_SEM_OTHER,
	I_DATA_SEM_QUOTA,
};


991 992 993 994 995 996
/*
 * fourth extended file system inode data in memory
 */
struct ext4_inode_info {
	__le32	i_data[15];	/* unconverted */
	__u32	i_dtime;
997
	ext4_fsblk_t	i_file_acl;
998 999 1000 1001

	/*
	 * i_block_group is the number of the block group which contains
	 * this file's inode.  Constant across the lifetime of the inode,
1002
	 * it is used for making block allocation decisions - we try to
1003 1004 1005 1006
	 * 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;
1007
	ext4_lblk_t	i_dir_start_lookup;
1008
#if (BITS_PER_LONG < 64)
1009
	unsigned long	i_state_flags;		/* Dynamic state flags */
1010
#endif
1011
	unsigned long	i_flags;
1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023

	/*
	 * 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 */

1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048
	/* Fast commit related info */

	struct list_head i_fc_list;	/*
					 * inodes that need fast commit
					 * protected by sbi->s_fc_lock.
					 */

	/* Fast commit subtid when this inode was committed */
	unsigned int i_fc_committed_subtid;

	/* Start of lblk range that needs to be committed in this fast commit */
	ext4_lblk_t i_fc_lblk_start;

	/* End of lblk range that needs to be committed in this fast commit */
	ext4_lblk_t i_fc_lblk_len;

	/* Number of ongoing updates on this inode */
	atomic_t  i_fc_updates;

	/* Fast commit wait queue for this inode */
	wait_queue_head_t i_fc_wait;

	/* Protect concurrent accesses on i_fc_lblk_start, i_fc_lblk_len */
	struct mutex i_fc_lock;

1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076
	/*
	 * 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;
1077 1078 1079 1080 1081 1082 1083 1084 1085
	/*
	 * i_mmap_sem is for serializing page faults with truncate / punch hole
	 * operations. We have to make sure that new page cannot be faulted in
	 * a section of the inode that is being punched. We cannot easily use
	 * i_data_sem for this since we need protection for the whole punch
	 * operation and i_data_sem ranks below transaction start so we have
	 * to occasionally drop it.
	 */
	struct rw_semaphore i_mmap_sem;
1086
	struct inode vfs_inode;
1087
	struct jbd2_inode *jinode;
1088

1089 1090
	spinlock_t i_raw_lock;	/* protects updates to the raw inode */

1091 1092
	/*
	 * File creation time. Its function is same as that of
1093
	 * struct timespec64 i_{a,c,m}time in the generic inode.
1094
	 */
1095
	struct timespec64 i_crtime;
1096 1097

	/* mballoc */
1098
	atomic_t i_prealloc_active;
1099 1100 1101
	struct list_head i_prealloc_list;
	spinlock_t i_prealloc_lock;

1102 1103 1104
	/* extents status tree */
	struct ext4_es_tree i_es_tree;
	rwlock_t i_es_lock;
1105
	struct list_head i_es_list;
1106
	unsigned int i_es_all_nr;	/* protected by i_es_lock */
1107
	unsigned int i_es_shk_nr;	/* protected by i_es_lock */
1108 1109 1110
	ext4_lblk_t i_es_shrink_lblk;	/* Offset where we start searching for
					   extents to shrink. Protected by
					   i_es_lock  */
1111

1112 1113 1114 1115
	/* ialloc */
	ext4_group_t	i_last_alloc_group;

	/* allocation reservation info for delalloc */
1116
	/* In case of bigalloc, this refer to clusters rather than blocks */
1117 1118
	unsigned int i_reserved_data_blocks;

1119 1120 1121
	/* pending cluster reservations for bigalloc file systems */
	struct ext4_pending_tree i_pending_tree;

1122 1123 1124
	/* on-disk additional length */
	__u16 i_extra_isize;

1125 1126 1127 1128
	/* Indicate the inline data space. */
	u16 i_inline_off;
	u16 i_inline_size;

1129 1130 1131 1132
#ifdef CONFIG_QUOTA
	/* quota space reservation, managed internally by quota code */
	qsize_t i_reserved_quota;
#endif
1133

1134
	/* Lock protecting lists below */
1135
	spinlock_t i_completed_io_lock;
1136 1137 1138 1139 1140 1141
	/*
	 * Completed IOs that need unwritten extents handling and have
	 * transaction reserved
	 */
	struct list_head i_rsv_conversion_list;
	struct work_struct i_rsv_conversion_work;
J
Jan Kara 已提交
1142
	atomic_t i_unwritten; /* Nr. of inflight conversions pending */
1143 1144

	spinlock_t i_block_reservation_lock;
1145 1146 1147 1148 1149 1150 1151

	/*
	 * Transactions that contain inode's metadata needed to complete
	 * fsync and fdatasync, respectively.
	 */
	tid_t i_sync_tid;
	tid_t i_datasync_tid;
1152

J
Jan Kara 已提交
1153 1154 1155 1156
#ifdef CONFIG_QUOTA
	struct dquot *i_dquot[MAXQUOTAS];
#endif

1157 1158
	/* Precomputed uuid+inum+igen checksum for seeding inode checksums */
	__u32 i_csum_seed;
1159

L
Li Xi 已提交
1160
	kprojid_t i_projid;
1161 1162
};

1163 1164 1165
/*
 * File system states
 */
1166 1167 1168
#define	EXT4_VALID_FS			0x0001	/* Unmounted cleanly */
#define	EXT4_ERROR_FS			0x0002	/* Errors detected */
#define	EXT4_ORPHAN_FS			0x0004	/* Orphans being recovered */
1169
#define EXT4_FC_REPLAY			0x0020	/* Fast commit replay ongoing */
1170

1171 1172 1173 1174 1175 1176 1177
/*
 * 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 */

1178
/*
1179
 * Mount flags set via mount options or defaults
1180
 */
1181
#define EXT4_MOUNT_NO_MBCACHE		0x00001 /* Do not use mbcache */
1182 1183 1184 1185 1186
#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 */
1187
#define EXT4_MOUNT_ERRORS_MASK		0x00070
1188 1189
#define EXT4_MOUNT_MINIX_DF		0x00080	/* Mimics the Minix statfs */
#define EXT4_MOUNT_NOLOAD		0x00100	/* Don't use existing journal*/
R
Ross Zwisler 已提交
1190
#ifdef CONFIG_FS_DAX
1191
#define EXT4_MOUNT_DAX_ALWAYS		0x00200	/* Direct Access */
R
Ross Zwisler 已提交
1192
#else
1193
#define EXT4_MOUNT_DAX_ALWAYS		0
R
Ross Zwisler 已提交
1194
#endif
1195 1196 1197 1198 1199 1200 1201 1202
#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 */
1203
#define EXT4_MOUNT_NO_AUTO_DA_ALLOC	0x10000	/* No auto delalloc mapping */
1204
#define EXT4_MOUNT_BARRIER		0x20000 /* Use block barriers */
1205 1206 1207 1208 1209 1210 1211 1212 1213
#define EXT4_MOUNT_QUOTA		0x40000 /* Some quota option set */
#define EXT4_MOUNT_USRQUOTA		0x80000 /* "old" user quota,
						 * enable enforcement for hidden
						 * quota files */
#define EXT4_MOUNT_GRPQUOTA		0x100000 /* "old" group quota, enable
						  * enforcement for hidden quota
						  * files */
#define EXT4_MOUNT_PRJQUOTA		0x200000 /* Enable project quota
						  * enforcement */
1214
#define EXT4_MOUNT_DIOREAD_NOLOCK	0x400000 /* Enable support for dio read nolocking */
1215
#define EXT4_MOUNT_JOURNAL_CHECKSUM	0x800000 /* Journal checksums */
1216
#define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT	0x1000000 /* Journal Async Commit */
1217
#define EXT4_MOUNT_WARN_ON_ERROR	0x2000000 /* Trigger WARN_ON on error */
1218
#define EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS 0x4000000
1219
#define EXT4_MOUNT_DELALLOC		0x8000000 /* Delalloc support */
1220
#define EXT4_MOUNT_DATA_ERR_ABORT	0x10000000 /* Abort on file data write */
1221
#define EXT4_MOUNT_BLOCK_VALIDITY	0x20000000 /* Block validity checking */
1222
#define EXT4_MOUNT_DISCARD		0x40000000 /* Issue DISCARD requests */
1223
#define EXT4_MOUNT_INIT_INODE_TABLE	0x80000000 /* Initialize uninitialized itables */
1224

1225 1226 1227 1228 1229
/*
 * 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.
 */
1230 1231
#define EXT4_MOUNT2_EXPLICIT_DELALLOC	0x00000001 /* User explicitly
						      specified delalloc */
1232 1233 1234
#define EXT4_MOUNT2_STD_GROUP_SIZE	0x00000002 /* We have standard group
						      size of blocksize * 8
						      blocks */
1235 1236
#define EXT4_MOUNT2_HURD_COMPAT		0x00000004 /* Support HURD-castrated
						      file systems */
1237 1238
#define EXT4_MOUNT2_DAX_NEVER		0x00000008 /* Do not allow Direct Access */
#define EXT4_MOUNT2_DAX_INODE		0x00000010 /* For printing options only */
1239

1240 1241 1242
#define EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM	0x00000008 /* User explicitly
						specified journal checksum */

1243 1244
#define EXT4_MOUNT2_JOURNAL_FAST_COMMIT	0x00000010 /* Journal fast commit */

1245 1246 1247 1248
#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
1249 1250
#define test_opt(sb, opt)		(EXT4_SB(sb)->s_mount_opt & \
					 EXT4_MOUNT_##opt)
1251

1252 1253 1254 1255 1256 1257 1258
#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)

1259 1260
#define ext4_test_and_set_bit		__test_and_set_bit_le
#define ext4_set_bit			__set_bit_le
1261
#define ext4_set_bit_atomic		ext2_set_bit_atomic
1262 1263
#define ext4_test_and_clear_bit		__test_and_clear_bit_le
#define ext4_clear_bit			__clear_bit_le
1264
#define ext4_clear_bit_atomic		ext2_clear_bit_atomic
A
Akinobu Mita 已提交
1265 1266 1267
#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
1268

1269 1270
extern void ext4_set_bits(void *bm, int cur, int len);

1271 1272 1273
/*
 * Maximal mount counts between two filesystem checks
 */
1274 1275
#define EXT4_DFL_MAX_MNT_COUNT		20	/* Allow 20 mounts */
#define EXT4_DFL_CHECKINTERVAL		0	/* Don't use interval check */
1276 1277 1278 1279

/*
 * Behaviour when detecting errors
 */
1280 1281 1282 1283
#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
1284

1285 1286 1287
/* Metadata checksum algorithm codes */
#define EXT4_CRC32C_CHKSUM		1

1288 1289 1290
/*
 * Structure of the super block
 */
1291
struct ext4_super_block {
1292
/*00*/	__le32	s_inodes_count;		/* Inodes count */
1293
	__le32	s_blocks_count_lo;	/* Blocks count */
1294 1295
	__le32	s_r_blocks_count_lo;	/* Reserved blocks count */
	__le32	s_free_blocks_count_lo;	/* Free blocks count */
1296 1297 1298
/*10*/	__le32	s_free_inodes_count;	/* Free inodes count */
	__le32	s_first_data_block;	/* First Data Block */
	__le32	s_log_block_size;	/* Block size */
1299
	__le32	s_log_cluster_size;	/* Allocation cluster size */
1300
/*20*/	__le32	s_blocks_per_group;	/* # Blocks per group */
1301
	__le32	s_clusters_per_group;	/* # Clusters per group */
1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317
	__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 */
	/*
1318
	 * These fields are for EXT4_DYNAMIC_REV superblocks only.
1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330
	 *
	 * 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 */
1331
	__le16  s_inode_size;		/* size of inode structure */
1332 1333 1334 1335 1336 1337
	__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 */
1338
/*88*/	char	s_last_mounted[64] __nonstring;	/* directory where last mounted */
1339 1340 1341
/*C8*/	__le32	s_algorithm_usage_bitmap; /* For compression */
	/*
	 * Performance hints.  Directory preallocation should only
1342
	 * happen if the EXT4_FEATURE_COMPAT_DIR_PREALLOC flag is on.
1343 1344 1345 1346 1347
	 */
	__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 */
	/*
1348
	 * Journaling support valid if EXT4_FEATURE_COMPAT_HAS_JOURNAL set.
1349 1350 1351 1352 1353 1354 1355
	 */
/*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 */
1356
	__u8	s_jnl_backup_type;
1357
	__le16  s_desc_size;		/* size of group descriptor */
L
Laurent Vivier 已提交
1358
/*100*/	__le32	s_default_mount_opts;
1359
	__le32	s_first_meta_bg;	/* First metablock block group */
L
Laurent Vivier 已提交
1360 1361 1362 1363 1364 1365
	__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
1366 1367 1368 1369
	__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 */
1370
	__le16  s_mmp_update_interval;  /* # seconds to wait in MMP checking */
A
Aneesh Kumar K.V 已提交
1371 1372
	__le64  s_mmp_block;            /* Block for multi-mount protection */
	__le32  s_raid_stripe_width;    /* blocks on all data disks (N*stride)*/
1373
	__u8	s_log_groups_per_flex;  /* FLEX_BG group size */
1374
	__u8	s_checksum_type;	/* metadata checksum algorithm used */
1375 1376
	__u8	s_encryption_level;	/* versioning level for encryption */
	__u8	s_reserved_pad;		/* Padding to next 32bits */
T
Theodore Ts'o 已提交
1377
	__le64	s_kbytes_written;	/* nr of lifetime kilobytes written */
1378 1379 1380 1381 1382 1383
	__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 */
1384 1385 1386 1387 1388
#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 */
1389
	__u8	s_first_error_func[32] __nonstring;	/* function where the error happened */
1390 1391 1392 1393 1394
	__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 */
1395
	__u8	s_last_error_func[32] __nonstring;	/* function where the error happened */
1396 1397
#define EXT4_S_ERR_END offsetof(struct ext4_super_block, s_mount_opts)
	__u8	s_mount_opts[64];
1398 1399 1400
	__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 */
1401
	__le32	s_backup_bgs[2];	/* groups with sparse_super2 SBs */
1402
	__u8	s_encrypt_algos[4];	/* Encryption algorithms in use  */
1403 1404
	__u8	s_encrypt_pw_salt[16];	/* Salt used for string2key algorithm */
	__le32	s_lpf_ino;		/* Location of the lost+found inode */
1405
	__le32	s_prj_quota_inum;	/* inode for tracking project quota */
1406
	__le32	s_checksum_seed;	/* crc32c(uuid) if csum_seed set */
1407 1408 1409 1410 1411 1412
	__u8	s_wtime_hi;
	__u8	s_mtime_hi;
	__u8	s_mkfs_time_hi;
	__u8	s_lastcheck_hi;
	__u8	s_first_error_time_hi;
	__u8	s_last_error_time_hi;
1413 1414
	__u8	s_first_error_errcode;
	__u8    s_last_error_errcode;
1415 1416 1417
	__le16  s_encoding;		/* Filename charset encoding */
	__le16  s_encoding_flags;	/* Filename charset encoding flags */
	__le32	s_reserved[95];		/* Padding to the end of the block */
1418
	__le32	s_checksum;		/* crc32c(superblock) */
1419 1420
};

1421 1422
#define EXT4_S_ERR_LEN (EXT4_S_ERR_END - EXT4_S_ERR_START)

1423
#ifdef __KERNEL__
1424 1425

/*
1426
 * run-time mount flags
1427
 */
1428 1429
#define EXT4_MF_MNTDIR_SAMPLED		0x0001
#define EXT4_MF_FS_ABORTED		0x0002	/* Fatal error detected */
1430 1431 1432 1433
#define EXT4_MF_FC_INELIGIBLE		0x0004	/* Fast commit ineligible */
#define EXT4_MF_FC_COMMITTING		0x0008	/* File system underoing a fast
						 * commit.
						 */
1434

1435
#ifdef CONFIG_FS_ENCRYPTION
1436
#define DUMMY_ENCRYPTION_ENABLED(sbi) ((sbi)->s_dummy_enc_policy.policy != NULL)
1437 1438 1439
#else
#define DUMMY_ENCRYPTION_ENABLED(sbi) (0)
#endif
1440

J
Jan Kara 已提交
1441
/* Number of quota types we support */
L
Li Xi 已提交
1442
#define EXT4_MAXQUOTAS 3
J
Jan Kara 已提交
1443

1444 1445
#define EXT4_ENC_UTF8_12_1	1

1446 1447 1448 1449 1450 1451 1452
/*
 * 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 */
1453
	unsigned long s_clusters_per_group; /* Number of clusters in a group */
1454 1455 1456 1457 1458
	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 */
1459
	ext4_group_t s_blockfile_groups;/* Groups acceptable for non-extent files */
1460
	unsigned long s_overhead;  /* # of fs overhead clusters */
1461 1462
	unsigned int s_cluster_ratio;	/* Number of blocks per cluster */
	unsigned int s_cluster_bits;	/* log2 of s_cluster_ratio */
1463 1464 1465
	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 */
1466
	struct buffer_head * __rcu *s_group_desc;
1467
	unsigned int s_mount_opt;
1468
	unsigned int s_mount_opt2;
1469
	unsigned int s_mount_flags;
1470
	unsigned int s_def_mount_opt;
1471
	ext4_fsblk_t s_sb_block;
L
Lukas Czerner 已提交
1472
	atomic64_t s_resv_clusters;
1473 1474
	kuid_t s_resuid;
	kgid_t s_resgid;
1475 1476 1477 1478 1479 1480 1481
	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;
1482
	unsigned int s_inode_goal;
1483 1484 1485
	u32 s_hash_seed[4];
	int s_def_hash_version;
	int s_hash_unsigned;	/* 3 if hash should be signed, 0 if not */
1486
	struct percpu_counter s_freeclusters_counter;
1487 1488
	struct percpu_counter s_freeinodes_counter;
	struct percpu_counter s_dirs_counter;
1489
	struct percpu_counter s_dirtyclusters_counter;
1490 1491 1492 1493
	struct blockgroup_lock *s_blockgroup_lock;
	struct proc_dir_entry *s_proc;
	struct kobject s_kobj;
	struct completion s_kobj_unregister;
1494
	struct super_block *s_sb;
1495 1496 1497 1498 1499

	/* Journaling */
	struct journal_s *s_journal;
	struct list_head s_orphan;
	struct mutex s_orphan_lock;
1500
	unsigned long s_ext4_flags;		/* Ext4 superblock flags */
1501 1502 1503
	unsigned long s_commit_interval;
	u32 s_max_batch_time;
	u32 s_min_batch_time;
1504
	struct block_device *s_journal_bdev;
1505
#ifdef CONFIG_QUOTA
1506 1507
	/* Names of quota files with journalled quota */
	char __rcu *s_qf_names[EXT4_MAXQUOTAS];
1508 1509 1510
	int s_jquota_fmt;			/* Format of quota to use */
#endif
	unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */
1511
	struct ext4_system_blocks __rcu *s_system_blks;
1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523

#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 */
1524
	struct ext4_group_info ** __rcu *s_group_info;
1525 1526 1527 1528
	struct inode *s_buddy_cache;
	spinlock_t s_md_lock;
	unsigned short *s_mb_offsets;
	unsigned int *s_mb_maxs;
1529
	unsigned int s_group_info_size;
1530
	unsigned int s_mb_free_pending;
1531 1532
	struct list_head s_freed_data_list;	/* List of blocks to be freed
						   after commit completed */
1533 1534 1535 1536 1537 1538 1539 1540 1541

	/* 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;
1542
	unsigned int s_mb_max_inode_prealloc;
1543
	unsigned int s_max_dir_size_kb;
1544 1545 1546
	/* where last allocation was done - for stream allocation */
	unsigned long s_mb_last_group;
	unsigned long s_mb_last_start;
1547 1548
	unsigned int s_mb_prefetch;
	unsigned int s_mb_prefetch_limit;
1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563

	/* 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;
1564
	atomic_t s_lock_busy;
1565 1566

	/* locality groups */
1567
	struct ext4_locality_group __percpu *s_locality_groups;
1568 1569 1570 1571 1572

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

1573 1574 1575
	/* the size of zero-out chunk */
	unsigned int s_extent_max_zeroout_kb;

1576
	unsigned int s_log_groups_per_flex;
1577
	struct flex_groups * __rcu *s_flex_groups;
1578
	ext4_group_t s_flex_groups_allocated;
1579

1580 1581
	/* workqueue for reserved extent conversions (buffered io) */
	struct workqueue_struct *rsv_conversion_wq;
1582 1583 1584

	/* timer for periodic error stats printing */
	struct timer_list s_err_report;
1585 1586 1587 1588 1589

	/* Lazy inode table initialization info */
	struct ext4_li_request *s_li_request;
	/* Wait multiplier for lazy initialization thread */
	unsigned int s_li_wait_mult;
1590 1591 1592

	/* Kernel thread for multiple mount protection */
	struct task_struct *s_mmp_tsk;
1593 1594 1595

	/* record the last minlen when FITRIM is called. */
	atomic_t s_last_trim_minblks;
1596 1597 1598

	/* Reference to checksum algorithm driver via cryptoapi */
	struct crypto_shash *s_chksum_driver;
1599 1600 1601

	/* Precomputed FS UUID checksum for seeding other checksums */
	__u32 s_csum_seed;
1602 1603 1604

	/* Reclaim extents from extent status tree */
	struct shrinker s_es_shrinker;
1605
	struct list_head s_es_list;	/* List of inodes with reclaimable extents */
1606
	long s_es_nr_inode;
1607
	struct ext4_es_stats s_es_stats;
1608
	struct mb_cache *s_ea_block_cache;
T
Tahsin Erdogan 已提交
1609
	struct mb_cache *s_ea_inode_cache;
1610
	spinlock_t s_es_lock ____cacheline_aligned_in_smp;
1611 1612 1613 1614 1615

	/* Ratelimit ext4 messages. */
	struct ratelimit_state s_err_ratelimit_state;
	struct ratelimit_state s_warning_ratelimit_state;
	struct ratelimit_state s_msg_ratelimit_state;
1616 1617
	atomic_t s_warning_count;
	atomic_t s_msg_count;
1618

1619 1620
	/* Encryption policy for '-o test_dummy_encryption' */
	struct fscrypt_dummy_policy s_dummy_enc_policy;
1621

1622 1623 1624 1625
	/*
	 * Barrier between writepages ops and changing any inode's JOURNAL_DATA
	 * or EXTENTS flag.
	 */
1626
	struct percpu_rw_semaphore s_writepages_rwsem;
1627
	struct dax_device *s_daxdev;
1628 1629 1630
#ifdef CONFIG_EXT4_DEBUG
	unsigned long s_simulate_fail;
#endif
1631 1632 1633
	/* Record the errseq of the backing block device */
	errseq_t s_bdev_wb_err;
	spinlock_t s_bdev_wb_lock;
1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657

	/* Ext4 fast commit stuff */
	atomic_t s_fc_subtid;
	atomic_t s_fc_ineligible_updates;
	/*
	 * After commit starts, the main queue gets locked, and the further
	 * updates get added in the staging queue.
	 */
#define FC_Q_MAIN	0
#define FC_Q_STAGING	1
	struct list_head s_fc_q[2];	/* Inodes staged for fast commit
					 * that have data changes in them.
					 */
	struct list_head s_fc_dentry_q[2];	/* directory entry updates */
	unsigned int s_fc_bytes;
	/*
	 * Main fast commit lock. This lock protects accesses to the
	 * following fields:
	 * ei->i_fc_list, s_fc_dentry_q, s_fc_q, s_fc_bytes, s_fc_bh.
	 */
	spinlock_t s_fc_lock;
	struct buffer_head *s_fc_bh;
	struct ext4_fc_stats s_fc_stats;
	u64 s_fc_avg_commit_time;
1658 1659 1660 1661
#ifdef CONFIG_EXT4_DEBUG
	int s_fc_debug_max_replay;
#endif
	struct ext4_fc_replay_state s_fc_replay_state;
1662 1663
};

1664
static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
1665 1666 1667
{
	return sb->s_fs_info;
}
1668
static inline struct ext4_inode_info *EXT4_I(struct inode *inode)
1669
{
1670
	return container_of(inode, struct ext4_inode_info, vfs_inode);
1671 1672
}

1673
static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
1674
{
1675 1676 1677
	return ino == EXT4_ROOT_INO ||
		(ino >= EXT4_FIRST_INO(sb) &&
		 ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
1678
}
1679

1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696
/*
 * Returns: sbi->field[index]
 * Used to access an array element from the following sbi fields which require
 * rcu protection to avoid dereferencing an invalid pointer due to reassignment
 * - s_group_desc
 * - s_group_info
 * - s_flex_group
 */
#define sbi_array_rcu_deref(sbi, field, index)				   \
({									   \
	typeof(*((sbi)->field)) _v;					   \
	rcu_read_lock();						   \
	_v = ((typeof(_v)*)rcu_dereference((sbi)->field))[index];	   \
	rcu_read_unlock();						   \
	_v;								   \
})

1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730
/*
 * Simulate_fail codes
 */
#define EXT4_SIM_BBITMAP_EIO	1
#define EXT4_SIM_BBITMAP_CRC	2
#define EXT4_SIM_IBITMAP_EIO	3
#define EXT4_SIM_IBITMAP_CRC	4
#define EXT4_SIM_INODE_EIO	5
#define EXT4_SIM_INODE_CRC	6
#define EXT4_SIM_DIRBLOCK_EIO	7
#define EXT4_SIM_DIRBLOCK_CRC	8

static inline bool ext4_simulate_fail(struct super_block *sb,
				     unsigned long code)
{
#ifdef CONFIG_EXT4_DEBUG
	struct ext4_sb_info *sbi = EXT4_SB(sb);

	if (unlikely(sbi->s_simulate_fail == code)) {
		sbi->s_simulate_fail = 0;
		return true;
	}
#endif
	return false;
}

static inline void ext4_simulate_fail_bh(struct super_block *sb,
					 struct buffer_head *bh,
					 unsigned long code)
{
	if (!IS_ERR(bh) && ext4_simulate_fail(sb, code))
		clear_buffer_uptodate(bh);
}

1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756
/*
 * Error number codes for s_{first,last}_error_errno
 *
 * Linux errno numbers are architecture specific, so we need to translate
 * them into something which is architecture independent.   We don't define
 * codes for all errno's; just the ones which are most likely to be the cause
 * of an ext4_error() call.
 */
#define EXT4_ERR_UNKNOWN	 1
#define EXT4_ERR_EIO		 2
#define EXT4_ERR_ENOMEM		 3
#define EXT4_ERR_EFSBADCRC	 4
#define EXT4_ERR_EFSCORRUPTED	 5
#define EXT4_ERR_ENOSPC		 6
#define EXT4_ERR_ENOKEY		 7
#define EXT4_ERR_EROFS		 8
#define EXT4_ERR_EFBIG		 9
#define EXT4_ERR_EEXIST		10
#define EXT4_ERR_ERANGE		11
#define EXT4_ERR_EOVERFLOW	12
#define EXT4_ERR_EBUSY		13
#define EXT4_ERR_ENOTDIR	14
#define EXT4_ERR_ENOTEMPTY	15
#define EXT4_ERR_ESHUTDOWN	16
#define EXT4_ERR_EFAULT		17

1757 1758 1759 1760 1761 1762 1763 1764 1765 1766
/*
 * 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 */
1767
	EXT4_STATE_NEWENTRY,		/* File just added to dir */
1768
	EXT4_STATE_MAY_INLINE_DATA,	/* may have in-inode data */
1769
	EXT4_STATE_EXT_PRECACHED,	/* extents have been precached */
1770
	EXT4_STATE_LUSTRE_EA_INODE,	/* Lustre-style ea_inode */
E
Eric Biggers 已提交
1771
	EXT4_STATE_VERITY_IN_PROGRESS,	/* building fs-verity Merkle tree */
1772
	EXT4_STATE_FC_COMMITTING,	/* Fast commit ongoing */
1773 1774
};

1775
#define EXT4_INODE_BIT_FNS(name, field, offset)				\
1776 1777
static inline int ext4_test_inode_##name(struct inode *inode, int bit)	\
{									\
1778
	return test_bit(bit + (offset), &EXT4_I(inode)->i_##field);	\
1779 1780 1781
}									\
static inline void ext4_set_inode_##name(struct inode *inode, int bit)	\
{									\
1782
	set_bit(bit + (offset), &EXT4_I(inode)->i_##field);		\
1783 1784 1785
}									\
static inline void ext4_clear_inode_##name(struct inode *inode, int bit) \
{									\
1786
	clear_bit(bit + (offset), &EXT4_I(inode)->i_##field);		\
1787 1788
}

1789 1790 1791 1792 1793
/* Add these declarations here only so that these functions can be
 * found by name.  Otherwise, they are very hard to locate. */
static inline int ext4_test_inode_flag(struct inode *inode, int bit);
static inline void ext4_set_inode_flag(struct inode *inode, int bit);
static inline void ext4_clear_inode_flag(struct inode *inode, int bit);
1794
EXT4_INODE_BIT_FNS(flag, flags, 0)
1795 1796 1797 1798 1799 1800

/* Add these declarations here only so that these functions can be
 * found by name.  Otherwise, they are very hard to locate. */
static inline int ext4_test_inode_state(struct inode *inode, int bit);
static inline void ext4_set_inode_state(struct inode *inode, int bit);
static inline void ext4_clear_inode_state(struct inode *inode, int bit);
1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815
#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
1816
#else
1817
/* Assume that user mode programs are passing in an ext4fs superblock, not
1818 1819
 * a kernel struct super_block.  This will allow us to call the feature-test
 * macros from user land. */
1820
#define EXT4_SB(sb)	(sb)
1821 1822
#endif

E
Eric Biggers 已提交
1823 1824 1825 1826 1827 1828
static inline bool ext4_verity_in_progress(struct inode *inode)
{
	return IS_ENABLED(CONFIG_FS_VERITY) &&
	       ext4_test_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS);
}

1829
#define NEXT_ORPHAN(inode) EXT4_I(inode)->i_dtime
1830 1831 1832 1833

/*
 * Codes for operating systems
 */
1834 1835 1836 1837 1838
#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
1839 1840 1841 1842

/*
 * Revision levels
 */
1843 1844
#define EXT4_GOOD_OLD_REV	0	/* The good old (original) format */
#define EXT4_DYNAMIC_REV	1	/* V2 format w/ dynamic inode sizes */
1845

1846 1847
#define EXT4_CURRENT_REV	EXT4_GOOD_OLD_REV
#define EXT4_MAX_SUPP_REV	EXT4_DYNAMIC_REV
1848

1849
#define EXT4_GOOD_OLD_INODE_SIZE 128
1850

1851 1852 1853 1854
#define EXT4_EXTRA_TIMESTAMP_MAX	(((s64)1 << 34) - 1  + S32_MIN)
#define EXT4_NON_EXTRA_TIMESTAMP_MAX	S32_MAX
#define EXT4_TIMESTAMP_MIN		S32_MIN

1855 1856 1857 1858
/*
 * Feature set definitions
 */

1859 1860 1861 1862 1863 1864
#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
1865
#define EXT4_FEATURE_COMPAT_SPARSE_SUPER2	0x0200
1866
#define EXT4_FEATURE_COMPAT_FAST_COMMIT		0x0400
1867
#define EXT4_FEATURE_COMPAT_STABLE_INODES	0x0800
1868 1869 1870 1871

#define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER	0x0001
#define EXT4_FEATURE_RO_COMPAT_LARGE_FILE	0x0002
#define EXT4_FEATURE_RO_COMPAT_BTREE_DIR	0x0004
1872
#define EXT4_FEATURE_RO_COMPAT_HUGE_FILE        0x0008
A
Andreas Dilger 已提交
1873
#define EXT4_FEATURE_RO_COMPAT_GDT_CSUM		0x0010
1874
#define EXT4_FEATURE_RO_COMPAT_DIR_NLINK	0x0020
K
Kalpak Shah 已提交
1875
#define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE	0x0040
1876
#define EXT4_FEATURE_RO_COMPAT_QUOTA		0x0100
1877
#define EXT4_FEATURE_RO_COMPAT_BIGALLOC		0x0200
1878 1879 1880 1881 1882 1883
/*
 * 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.
 */
1884
#define EXT4_FEATURE_RO_COMPAT_METADATA_CSUM	0x0400
D
Darrick J. Wong 已提交
1885
#define EXT4_FEATURE_RO_COMPAT_READONLY		0x1000
1886
#define EXT4_FEATURE_RO_COMPAT_PROJECT		0x2000
E
Eric Biggers 已提交
1887
#define EXT4_FEATURE_RO_COMPAT_VERITY		0x8000
1888 1889 1890 1891 1892 1893

#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
1894
#define EXT4_FEATURE_INCOMPAT_EXTENTS		0x0040 /* extents support */
L
Laurent Vivier 已提交
1895
#define EXT4_FEATURE_INCOMPAT_64BIT		0x0080
1896
#define EXT4_FEATURE_INCOMPAT_MMP               0x0100
J
Jose R. Santos 已提交
1897
#define EXT4_FEATURE_INCOMPAT_FLEX_BG		0x0200
1898 1899
#define EXT4_FEATURE_INCOMPAT_EA_INODE		0x0400 /* EA in inode */
#define EXT4_FEATURE_INCOMPAT_DIRDATA		0x1000 /* data in dirent */
1900
#define EXT4_FEATURE_INCOMPAT_CSUM_SEED		0x2000
1901
#define EXT4_FEATURE_INCOMPAT_LARGEDIR		0x4000 /* >2GB or 3-lvl htree */
1902
#define EXT4_FEATURE_INCOMPAT_INLINE_DATA	0x8000 /* data in inode */
1903
#define EXT4_FEATURE_INCOMPAT_ENCRYPT		0x10000
1904
#define EXT4_FEATURE_INCOMPAT_CASEFOLD		0x20000
1905

1906 1907
extern void ext4_update_dynamic_rev(struct super_block *sb);

1908 1909 1910 1911 1912 1913 1914 1915
#define EXT4_FEATURE_COMPAT_FUNCS(name, flagname) \
static inline bool ext4_has_feature_##name(struct super_block *sb) \
{ \
	return ((EXT4_SB(sb)->s_es->s_feature_compat & \
		cpu_to_le32(EXT4_FEATURE_COMPAT_##flagname)) != 0); \
} \
static inline void ext4_set_feature_##name(struct super_block *sb) \
{ \
1916
	ext4_update_dynamic_rev(sb); \
1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933
	EXT4_SB(sb)->s_es->s_feature_compat |= \
		cpu_to_le32(EXT4_FEATURE_COMPAT_##flagname); \
} \
static inline void ext4_clear_feature_##name(struct super_block *sb) \
{ \
	EXT4_SB(sb)->s_es->s_feature_compat &= \
		~cpu_to_le32(EXT4_FEATURE_COMPAT_##flagname); \
}

#define EXT4_FEATURE_RO_COMPAT_FUNCS(name, flagname) \
static inline bool ext4_has_feature_##name(struct super_block *sb) \
{ \
	return ((EXT4_SB(sb)->s_es->s_feature_ro_compat & \
		cpu_to_le32(EXT4_FEATURE_RO_COMPAT_##flagname)) != 0); \
} \
static inline void ext4_set_feature_##name(struct super_block *sb) \
{ \
1934
	ext4_update_dynamic_rev(sb); \
1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951
	EXT4_SB(sb)->s_es->s_feature_ro_compat |= \
		cpu_to_le32(EXT4_FEATURE_RO_COMPAT_##flagname); \
} \
static inline void ext4_clear_feature_##name(struct super_block *sb) \
{ \
	EXT4_SB(sb)->s_es->s_feature_ro_compat &= \
		~cpu_to_le32(EXT4_FEATURE_RO_COMPAT_##flagname); \
}

#define EXT4_FEATURE_INCOMPAT_FUNCS(name, flagname) \
static inline bool ext4_has_feature_##name(struct super_block *sb) \
{ \
	return ((EXT4_SB(sb)->s_es->s_feature_incompat & \
		cpu_to_le32(EXT4_FEATURE_INCOMPAT_##flagname)) != 0); \
} \
static inline void ext4_set_feature_##name(struct super_block *sb) \
{ \
1952
	ext4_update_dynamic_rev(sb); \
1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968
	EXT4_SB(sb)->s_es->s_feature_incompat |= \
		cpu_to_le32(EXT4_FEATURE_INCOMPAT_##flagname); \
} \
static inline void ext4_clear_feature_##name(struct super_block *sb) \
{ \
	EXT4_SB(sb)->s_es->s_feature_incompat &= \
		~cpu_to_le32(EXT4_FEATURE_INCOMPAT_##flagname); \
}

EXT4_FEATURE_COMPAT_FUNCS(dir_prealloc,		DIR_PREALLOC)
EXT4_FEATURE_COMPAT_FUNCS(imagic_inodes,	IMAGIC_INODES)
EXT4_FEATURE_COMPAT_FUNCS(journal,		HAS_JOURNAL)
EXT4_FEATURE_COMPAT_FUNCS(xattr,		EXT_ATTR)
EXT4_FEATURE_COMPAT_FUNCS(resize_inode,		RESIZE_INODE)
EXT4_FEATURE_COMPAT_FUNCS(dir_index,		DIR_INDEX)
EXT4_FEATURE_COMPAT_FUNCS(sparse_super2,	SPARSE_SUPER2)
1969
EXT4_FEATURE_COMPAT_FUNCS(fast_commit,		FAST_COMMIT)
1970
EXT4_FEATURE_COMPAT_FUNCS(stable_inodes,	STABLE_INODES)
1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983

EXT4_FEATURE_RO_COMPAT_FUNCS(sparse_super,	SPARSE_SUPER)
EXT4_FEATURE_RO_COMPAT_FUNCS(large_file,	LARGE_FILE)
EXT4_FEATURE_RO_COMPAT_FUNCS(btree_dir,		BTREE_DIR)
EXT4_FEATURE_RO_COMPAT_FUNCS(huge_file,		HUGE_FILE)
EXT4_FEATURE_RO_COMPAT_FUNCS(gdt_csum,		GDT_CSUM)
EXT4_FEATURE_RO_COMPAT_FUNCS(dir_nlink,		DIR_NLINK)
EXT4_FEATURE_RO_COMPAT_FUNCS(extra_isize,	EXTRA_ISIZE)
EXT4_FEATURE_RO_COMPAT_FUNCS(quota,		QUOTA)
EXT4_FEATURE_RO_COMPAT_FUNCS(bigalloc,		BIGALLOC)
EXT4_FEATURE_RO_COMPAT_FUNCS(metadata_csum,	METADATA_CSUM)
EXT4_FEATURE_RO_COMPAT_FUNCS(readonly,		READONLY)
EXT4_FEATURE_RO_COMPAT_FUNCS(project,		PROJECT)
E
Eric Biggers 已提交
1984
EXT4_FEATURE_RO_COMPAT_FUNCS(verity,		VERITY)
1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000

EXT4_FEATURE_INCOMPAT_FUNCS(compression,	COMPRESSION)
EXT4_FEATURE_INCOMPAT_FUNCS(filetype,		FILETYPE)
EXT4_FEATURE_INCOMPAT_FUNCS(journal_needs_recovery,	RECOVER)
EXT4_FEATURE_INCOMPAT_FUNCS(journal_dev,	JOURNAL_DEV)
EXT4_FEATURE_INCOMPAT_FUNCS(meta_bg,		META_BG)
EXT4_FEATURE_INCOMPAT_FUNCS(extents,		EXTENTS)
EXT4_FEATURE_INCOMPAT_FUNCS(64bit,		64BIT)
EXT4_FEATURE_INCOMPAT_FUNCS(mmp,		MMP)
EXT4_FEATURE_INCOMPAT_FUNCS(flex_bg,		FLEX_BG)
EXT4_FEATURE_INCOMPAT_FUNCS(ea_inode,		EA_INODE)
EXT4_FEATURE_INCOMPAT_FUNCS(dirdata,		DIRDATA)
EXT4_FEATURE_INCOMPAT_FUNCS(csum_seed,		CSUM_SEED)
EXT4_FEATURE_INCOMPAT_FUNCS(largedir,		LARGEDIR)
EXT4_FEATURE_INCOMPAT_FUNCS(inline_data,	INLINE_DATA)
EXT4_FEATURE_INCOMPAT_FUNCS(encrypt,		ENCRYPT)
2001
EXT4_FEATURE_INCOMPAT_FUNCS(casefold,		CASEFOLD)
2002

2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017
#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)

2018
#define EXT4_FEATURE_COMPAT_SUPP	EXT4_FEATURE_COMPAT_EXT_ATTR
2019 2020
#define EXT4_FEATURE_INCOMPAT_SUPP	(EXT4_FEATURE_INCOMPAT_FILETYPE| \
					 EXT4_FEATURE_INCOMPAT_RECOVER| \
A
Alex Tomas 已提交
2021
					 EXT4_FEATURE_INCOMPAT_META_BG| \
L
Laurent Vivier 已提交
2022
					 EXT4_FEATURE_INCOMPAT_EXTENTS| \
J
Jose R. Santos 已提交
2023
					 EXT4_FEATURE_INCOMPAT_64BIT| \
2024
					 EXT4_FEATURE_INCOMPAT_FLEX_BG| \
A
Andreas Dilger 已提交
2025
					 EXT4_FEATURE_INCOMPAT_EA_INODE| \
2026 2027
					 EXT4_FEATURE_INCOMPAT_MMP | \
					 EXT4_FEATURE_INCOMPAT_INLINE_DATA | \
2028
					 EXT4_FEATURE_INCOMPAT_ENCRYPT | \
2029
					 EXT4_FEATURE_INCOMPAT_CASEFOLD | \
A
Artem Blagodarenko 已提交
2030 2031
					 EXT4_FEATURE_INCOMPAT_CSUM_SEED | \
					 EXT4_FEATURE_INCOMPAT_LARGEDIR)
2032 2033
#define EXT4_FEATURE_RO_COMPAT_SUPP	(EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
					 EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \
A
Andreas Dilger 已提交
2034
					 EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \
2035
					 EXT4_FEATURE_RO_COMPAT_DIR_NLINK | \
K
Kalpak Shah 已提交
2036
					 EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \
2037
					 EXT4_FEATURE_RO_COMPAT_BTREE_DIR |\
2038
					 EXT4_FEATURE_RO_COMPAT_HUGE_FILE |\
2039
					 EXT4_FEATURE_RO_COMPAT_BIGALLOC |\
2040
					 EXT4_FEATURE_RO_COMPAT_METADATA_CSUM|\
L
Li Xi 已提交
2041
					 EXT4_FEATURE_RO_COMPAT_QUOTA |\
E
Eric Biggers 已提交
2042 2043
					 EXT4_FEATURE_RO_COMPAT_PROJECT |\
					 EXT4_FEATURE_RO_COMPAT_VERITY)
2044

2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078
#define EXTN_FEATURE_FUNCS(ver) \
static inline bool ext4_has_unknown_ext##ver##_compat_features(struct super_block *sb) \
{ \
	return ((EXT4_SB(sb)->s_es->s_feature_compat & \
		cpu_to_le32(~EXT##ver##_FEATURE_COMPAT_SUPP)) != 0); \
} \
static inline bool ext4_has_unknown_ext##ver##_ro_compat_features(struct super_block *sb) \
{ \
	return ((EXT4_SB(sb)->s_es->s_feature_ro_compat & \
		cpu_to_le32(~EXT##ver##_FEATURE_RO_COMPAT_SUPP)) != 0); \
} \
static inline bool ext4_has_unknown_ext##ver##_incompat_features(struct super_block *sb) \
{ \
	return ((EXT4_SB(sb)->s_es->s_feature_incompat & \
		cpu_to_le32(~EXT##ver##_FEATURE_INCOMPAT_SUPP)) != 0); \
}

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

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

2079 2080 2081 2082
/*
 * Superblock flags
 */
#define EXT4_FLAGS_RESIZING	0
2083
#define EXT4_FLAGS_SHUTDOWN	1
2084
#define EXT4_FLAGS_BDEV_IS_DAX	2
2085 2086 2087 2088 2089

static inline int ext4_forced_shutdown(struct ext4_sb_info *sbi)
{
	return test_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
}
2090 2091


2092 2093 2094
/*
 * Default values for user and/or group using reserved blocks
 */
2095 2096
#define	EXT4_DEF_RESUID		0
#define	EXT4_DEF_RESGID		0
2097

L
Li Xi 已提交
2098 2099 2100 2101 2102
/*
 * Default project ID
 */
#define	EXT4_DEF_PROJID		0

2103 2104
#define EXT4_DEF_INODE_READAHEAD_BLKS	32

2105 2106 2107
/*
 * Default mount options
 */
2108 2109 2110 2111 2112 2113 2114 2115 2116
#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
2117 2118 2119 2120
#define EXT4_DEFM_NOBARRIER	0x0100
#define EXT4_DEFM_BLOCK_VALIDITY 0x0200
#define EXT4_DEFM_DISCARD	0x0400
#define EXT4_DEFM_NODELALLOC	0x0800
2121

2122 2123 2124 2125 2126 2127
/*
 * Default journal batch times
 */
#define EXT4_DEF_MIN_BATCH_TIME	0
#define EXT4_DEF_MAX_BATCH_TIME	15000 /* 15ms */

2128 2129 2130 2131 2132 2133
/*
 * 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

2134 2135 2136
/*
 * Structure of a directory entry
 */
2137
#define EXT4_NAME_LEN 255
2138

2139
struct ext4_dir_entry {
2140 2141 2142
	__le32	inode;			/* Inode number */
	__le16	rec_len;		/* Directory entry length */
	__le16	name_len;		/* Name length */
2143
	char	name[EXT4_NAME_LEN];	/* File name */
2144 2145 2146
};

/*
2147
 * The new version of the directory entry.  Since EXT4 structures are
2148 2149 2150 2151
 * 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.
 */
2152
struct ext4_dir_entry_2 {
2153 2154 2155
	__le32	inode;			/* Inode number */
	__le16	rec_len;		/* Directory entry length */
	__u8	name_len;		/* Name length */
2156
	__u8	file_type;		/* See file type macros EXT4_FT_* below */
2157
	char	name[EXT4_NAME_LEN];	/* File name */
2158 2159
};

2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171
/*
 * 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) */
};

2172 2173 2174 2175 2176
#define EXT4_DIRENT_TAIL(block, blocksize) \
	((struct ext4_dir_entry_tail *)(((void *)(block)) + \
					((blocksize) - \
					 sizeof(struct ext4_dir_entry_tail))))

2177
/*
2178
 * Ext4 directory file types.  Only the low 3 bits are used.  The
2179 2180
 * other bits are reserved for now.
 */
2181 2182 2183 2184 2185 2186 2187 2188
#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
2189

2190
#define EXT4_FT_MAX		8
2191

2192 2193
#define EXT4_FT_DIR_CSUM	0xDE

2194
/*
2195
 * EXT4_DIR_PAD defines the directory entries boundaries
2196 2197 2198
 *
 * NOTE: It must be a multiple of 4
 */
2199 2200 2201 2202
#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)
2203 2204
#define EXT4_MAX_REC_LEN		((1<<16)-1)

2205 2206 2207 2208 2209 2210 2211 2212 2213
/*
 * 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);

2214
#if (PAGE_SIZE >= 65536)
2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226
	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();
2227
#if (PAGE_SIZE >= 65536)
2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241
	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
}

2242 2243 2244 2245 2246
/*
 * Hash Tree Directory indexing
 * (c) Daniel Phillips, 2001
 */

2247
#define is_dx(dir) (ext4_has_feature_dir_index((dir)->i_sb) && \
2248
		    ext4_test_inode_flag((dir), EXT4_INODE_INDEX))
A
Andreas Dilger 已提交
2249 2250
#define EXT4_DIR_LINK_MAX(dir) unlikely((dir)->i_nlink >= EXT4_LINK_MAX && \
		    !(ext4_has_feature_dir_nlink((dir)->i_sb) && is_dx(dir)))
2251
#define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2 || (dir)->i_nlink == 1)
2252 2253 2254

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

2255 2256 2257 2258
#define DX_HASH_LEGACY			0
#define DX_HASH_HALF_MD4		1
#define DX_HASH_TEA			2
#define DX_HASH_LEGACY_UNSIGNED		3
2259 2260
#define DX_HASH_HALF_MD4_UNSIGNED	4
#define DX_HASH_TEA_UNSIGNED		5
2261

2262 2263 2264 2265 2266
static inline u32 ext4_chksum(struct ext4_sb_info *sbi, u32 crc,
			      const void *address, unsigned int length)
{
	struct {
		struct shash_desc shash;
2267
		char ctx[4];
2268 2269
	} desc;

2270 2271
	BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver)!=sizeof(desc.ctx));

2272 2273 2274
	desc.shash.tfm = sbi->s_chksum_driver;
	*(u32 *)desc.ctx = crc;

2275
	BUG_ON(crypto_shash_update(&desc.shash, address, length));
2276 2277 2278 2279

	return *(u32 *)desc.ctx;
}

2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290
#ifdef __KERNEL__

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

2291 2292 2293 2294 2295

/* 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)

2296 2297

/*
2298
 * Control parameters used by ext4_htree_next_block
2299 2300 2301
 */
#define HASH_NB_ALWAYS		1

2302 2303
struct ext4_filename {
	const struct qstr *usr_fname;
2304
	struct fscrypt_str disk_name;
2305
	struct dx_hash_info hinfo;
2306
#ifdef CONFIG_FS_ENCRYPTION
2307
	struct fscrypt_str crypto_buf;
2308
#endif
2309 2310 2311
#ifdef CONFIG_UNICODE
	struct fscrypt_str cf_name;
#endif
2312 2313 2314 2315
};

#define fname_name(p) ((p)->disk_name.name)
#define fname_len(p)  ((p)->disk_name.len)
2316 2317 2318 2319

/*
 * Describe an inode's exact location on disk and in memory
 */
2320
struct ext4_iloc
2321 2322 2323
{
	struct buffer_head *bh;
	unsigned long offset;
2324
	ext4_group_t block_group;
2325 2326
};

2327
static inline struct ext4_inode *ext4_raw_inode(struct ext4_iloc *iloc)
2328
{
2329
	return (struct ext4_inode *) (iloc->bh->b_data + iloc->offset);
2330 2331
}

T
Tahsin Erdogan 已提交
2332 2333 2334 2335 2336
static inline bool ext4_is_quota_file(struct inode *inode)
{
	return IS_NOQUOTA(inode) &&
	       !(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL);
}
T
Tahsin Erdogan 已提交
2337

2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353
/*
 * 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 */
2354
static inline ext4_fsblk_t
2355
ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no)
2356
{
2357 2358
	return group_no * (ext4_fsblk_t)EXT4_BLOCKS_PER_GROUP(sb) +
		le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
2359 2360 2361 2362 2363
}

/*
 * Special error return code only used by dx_probe() and its callers.
 */
2364
#define ERR_BAD_DX_DIR	(-(MAX_ERRNO - 1))
2365

A
Artem Blagodarenko 已提交
2366 2367 2368 2369 2370 2371 2372 2373 2374 2375
/* htree levels for ext4 */
#define	EXT4_HTREE_LEVEL_COMPAT	2
#define	EXT4_HTREE_LEVEL	3

static inline int ext4_dir_htree_level(struct super_block *sb)
{
	return ext4_has_feature_largedir(sb) ?
		EXT4_HTREE_LEVEL : EXT4_HTREE_LEVEL_COMPAT;
}

2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392
/*
 * 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;
};

2393 2394 2395 2396 2397
enum ext4_li_mode {
	EXT4_LI_MODE_PREFETCH_BBITMAP,
	EXT4_LI_MODE_ITABLE,
};

2398 2399
struct ext4_li_request {
	struct super_block	*lr_super;
2400 2401
	enum ext4_li_mode	lr_mode;
	ext4_group_t		lr_first_not_zeroed;
2402 2403 2404 2405 2406 2407
	ext4_group_t		lr_next_group;
	struct list_head	lr_request;
	unsigned long		lr_next_sched;
	unsigned long		lr_timeout;
};

2408 2409 2410 2411 2412
struct ext4_features {
	struct kobject f_kobj;
	struct completion f_kobj_unregister;
};

2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444
/*
 * 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;
2445 2446
	__le32	mmp_pad2[226];
	__le32	mmp_checksum;		/* crc32c(uuid+mmp_block) */
2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474
};

/* 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

2475 2476 2477 2478 2479 2480
/*
 * Function prototypes
 */

/*
 * Ok, these declarations are also in <linux/kernel.h> but none of the
2481
 * ext4 source programs needs to include it so they are duplicated here.
2482
 */
D
Dave Kleikamp 已提交
2483 2484 2485
# define NORET_TYPE	/**/
# define ATTRIB_NORET	__attribute__((noreturn))
# define NORET_AND	noreturn,
2486

2487
/* bitmap.c */
2488
extern unsigned int ext4_count_free(char *bitmap, unsigned numchars);
2489 2490 2491 2492 2493 2494
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);
2495 2496
void ext4_block_bitmap_csum_set(struct super_block *sb, ext4_group_t group,
				struct ext4_group_desc *gdp,
2497
				struct buffer_head *bh);
2498 2499
int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group,
				  struct ext4_group_desc *gdp,
2500
				  struct buffer_head *bh);
2501

2502
/* balloc.c */
2503 2504 2505 2506 2507 2508 2509
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);

2510 2511 2512 2513
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);
2514 2515 2516
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);
2517
extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
2518 2519 2520 2521
					 ext4_fsblk_t goal,
					 unsigned int flags,
					 unsigned long *count,
					 int *errp);
2522 2523
extern int ext4_claim_free_clusters(struct ext4_sb_info *sbi,
				    s64 nclusters, unsigned int flags);
2524
extern ext4_fsblk_t ext4_count_free_clusters(struct super_block *);
2525
extern void ext4_check_blocks_bitmap(struct super_block *);
2526
extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
2527
						    ext4_group_t block_group,
2528
						    struct buffer_head ** bh);
2529
extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
2530 2531

extern struct buffer_head *ext4_read_block_bitmap_nowait(struct super_block *sb,
2532 2533
						ext4_group_t block_group,
						bool ignore_locked);
2534 2535 2536 2537 2538
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);
2539 2540 2541
extern unsigned ext4_free_clusters_after_init(struct super_block *sb,
					      ext4_group_t block_group,
					      struct ext4_group_desc *gdp);
2542
ext4_fsblk_t ext4_inode_to_goal_block(struct inode *);
2543

2544 2545 2546 2547 2548 2549
#ifdef CONFIG_UNICODE
extern void ext4_fname_setup_ci_filename(struct inode *dir,
					 const struct qstr *iname,
					 struct fscrypt_str *fname);
#endif

2550
#ifdef CONFIG_FS_ENCRYPTION
2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562
static inline void ext4_fname_from_fscrypt_name(struct ext4_filename *dst,
						const struct fscrypt_name *src)
{
	memset(dst, 0, sizeof(*dst));

	dst->usr_fname = src->usr_fname;
	dst->disk_name = src->disk_name;
	dst->hinfo.hash = src->hash;
	dst->hinfo.minor_hash = src->minor_hash;
	dst->crypto_buf = src->crypto_buf;
}

2563
static inline int ext4_fname_setup_filename(struct inode *dir,
2564 2565 2566
					    const struct qstr *iname,
					    int lookup,
					    struct ext4_filename *fname)
2567
{
2568 2569
	struct fscrypt_name name;
	int err;
2570

2571
	err = fscrypt_setup_filename(dir, iname, lookup, &name);
2572 2573
	if (err)
		return err;
2574

2575
	ext4_fname_from_fscrypt_name(fname, &name);
2576 2577 2578 2579

#ifdef CONFIG_UNICODE
	ext4_fname_setup_ci_filename(dir, iname, &fname->cf_name);
#endif
2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594
	return 0;
}

static inline int ext4_fname_prepare_lookup(struct inode *dir,
					    struct dentry *dentry,
					    struct ext4_filename *fname)
{
	struct fscrypt_name name;
	int err;

	err = fscrypt_prepare_lookup(dir, dentry, &name);
	if (err)
		return err;

	ext4_fname_from_fscrypt_name(fname, &name);
2595 2596 2597 2598

#ifdef CONFIG_UNICODE
	ext4_fname_setup_ci_filename(dir, &dentry->d_name, &fname->cf_name);
#endif
2599
	return 0;
2600 2601
}

2602
static inline void ext4_fname_free_filename(struct ext4_filename *fname)
2603
{
2604
	struct fscrypt_name name;
2605

2606 2607 2608 2609 2610 2611
	name.crypto_buf = fname->crypto_buf;
	fscrypt_free_filename(&name);

	fname->crypto_buf.name = NULL;
	fname->usr_fname = NULL;
	fname->disk_name.name = NULL;
2612 2613 2614 2615 2616

#ifdef CONFIG_UNICODE
	kfree(fname->cf_name.name);
	fname->cf_name.name = NULL;
#endif
2617
}
2618
#else /* !CONFIG_FS_ENCRYPTION */
2619
static inline int ext4_fname_setup_filename(struct inode *dir,
2620 2621 2622
					    const struct qstr *iname,
					    int lookup,
					    struct ext4_filename *fname)
2623
{
2624 2625 2626
	fname->usr_fname = iname;
	fname->disk_name.name = (unsigned char *) iname->name;
	fname->disk_name.len = iname->len;
2627 2628 2629 2630 2631

#ifdef CONFIG_UNICODE
	ext4_fname_setup_ci_filename(dir, iname, &fname->cf_name);
#endif

2632 2633
	return 0;
}
2634

2635 2636 2637 2638 2639 2640 2641
static inline int ext4_fname_prepare_lookup(struct inode *dir,
					    struct dentry *dentry,
					    struct ext4_filename *fname)
{
	return ext4_fname_setup_filename(dir, &dentry->d_name, 1, fname);
}

2642 2643 2644 2645 2646 2647 2648
static inline void ext4_fname_free_filename(struct ext4_filename *fname)
{
#ifdef CONFIG_UNICODE
	kfree(fname->cf_name.name);
	fname->cf_name.name = NULL;
#endif
}
2649
#endif /* !CONFIG_FS_ENCRYPTION */
2650

2651
/* dir.c */
2652
extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *,
2653
				  struct file *,
2654
				  struct ext4_dir_entry_2 *,
2655 2656 2657
				  struct buffer_head *, char *, int,
				  unsigned int);
#define ext4_check_dir_entry(dir, filp, de, bh, buf, size, offset)	\
2658
	unlikely(__ext4_check_dir_entry(__func__, __LINE__, (dir), (filp), \
2659
					(de), (bh), (buf), (size), (offset)))
2660
extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
2661 2662
				__u32 minor_hash,
				struct ext4_dir_entry_2 *dirent,
2663
				struct fscrypt_str *ent_name);
2664
extern void ext4_htree_free_dir_info(struct dir_private_info *p);
2665 2666 2667
extern int ext4_find_dest_de(struct inode *dir, struct inode *inode,
			     struct buffer_head *bh,
			     void *buf, int buf_size,
2668
			     struct ext4_filename *fname,
2669
			     struct ext4_dir_entry_2 **dest_de);
2670 2671 2672 2673
void ext4_insert_dentry(struct inode *inode,
			struct ext4_dir_entry_2 *de,
			int buf_size,
			struct ext4_filename *fname);
2674 2675
static inline void ext4_update_dx_flag(struct inode *inode)
{
2676 2677 2678
	if (!ext4_has_feature_dir_index(inode->i_sb)) {
		/* ext4_iget() should have caught this... */
		WARN_ON_ONCE(ext4_has_feature_metadata_csum(inode->i_sb));
2679
		ext4_clear_inode_flag(inode, EXT4_INODE_INDEX);
2680
	}
2681
}
2682
static const unsigned char ext4_filetype_table[] = {
T
Tao Ma 已提交
2683 2684 2685 2686 2687
	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)
{
2688
	if (!ext4_has_feature_filetype(sb) || filetype >= EXT4_FT_MAX)
T
Tao Ma 已提交
2689 2690 2691 2692
		return DT_UNKNOWN;

	return ext4_filetype_table[filetype];
}
2693 2694
extern int ext4_check_all_de(struct inode *dir, struct buffer_head *bh,
			     void *buf, int buf_size);
2695 2696

/* fsync.c */
2697
extern int ext4_sync_file(struct file *, loff_t, loff_t, int);
2698 2699

/* hash.c */
2700 2701
extern int ext4fs_dirhash(const struct inode *dir, const char *name, int len,
			  struct dx_hash_info *hinfo);
2702 2703

/* ialloc.c */
2704
extern int ext4_mark_inode_used(struct super_block *sb, int ino);
2705 2706
extern struct inode *__ext4_new_inode(handle_t *, struct inode *, umode_t,
				      const struct qstr *qstr, __u32 goal,
2707 2708 2709
				      uid_t *owner, __u32 i_flags,
				      int handle_type, unsigned int line_no,
				      int nblocks);
2710

2711
#define ext4_new_inode(handle, dir, mode, qstr, goal, owner, i_flags) \
2712
	__ext4_new_inode((handle), (dir), (mode), (qstr), (goal), (owner), \
2713
			 i_flags, 0, 0, 0)
2714 2715 2716
#define ext4_new_inode_start_handle(dir, mode, qstr, goal, owner, \
				    type, nblocks)		    \
	__ext4_new_inode(NULL, (dir), (mode), (qstr), (goal), (owner), \
2717
			 0, (type), __LINE__, (nblocks))
2718 2719


2720 2721 2722 2723 2724
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 *);
2725
extern void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
2726 2727
extern int ext4_init_inode_table(struct super_block *sb,
				 ext4_group_t group, int barrier);
2728
extern void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate);
2729

2730
/* fast_commit.c */
2731
int ext4_fc_info_show(struct seq_file *seq, void *v);
2732
void ext4_fc_init(struct super_block *sb, journal_t *journal);
2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745
void ext4_fc_init_inode(struct inode *inode);
void ext4_fc_track_range(struct inode *inode, ext4_lblk_t start,
			 ext4_lblk_t end);
void ext4_fc_track_unlink(struct inode *inode, struct dentry *dentry);
void ext4_fc_track_link(struct inode *inode, struct dentry *dentry);
void ext4_fc_track_create(struct inode *inode, struct dentry *dentry);
void ext4_fc_track_inode(struct inode *inode);
void ext4_fc_mark_ineligible(struct super_block *sb, int reason);
void ext4_fc_start_ineligible(struct super_block *sb, int reason);
void ext4_fc_stop_ineligible(struct super_block *sb);
void ext4_fc_start_update(struct inode *inode);
void ext4_fc_stop_update(struct inode *inode);
void ext4_fc_del(struct inode *inode);
2746 2747
bool ext4_fc_replay_check_excluded(struct super_block *sb, ext4_fsblk_t block);
void ext4_fc_replay_cleanup(struct super_block *sb);
2748 2749 2750
int ext4_fc_commit(journal_t *journal, tid_t commit_tid);
int __init ext4_fc_init_dentry_cache(void);

2751
/* mballoc.c */
C
Christoph Hellwig 已提交
2752
extern const struct seq_operations ext4_mb_seq_groups_ops;
2753 2754
extern long ext4_mb_stats;
extern long ext4_mb_max_to_scan;
2755
extern int ext4_mb_init(struct super_block *);
2756 2757 2758 2759
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);
2760
extern void ext4_discard_preallocations(struct inode *, unsigned int);
2761 2762
extern int __init ext4_init_mballoc(void);
extern void ext4_exit_mballoc(void);
2763 2764 2765 2766 2767 2768
extern ext4_group_t ext4_mb_prefetch(struct super_block *sb,
				     ext4_group_t group,
				     unsigned int nr, int *cnt);
extern void ext4_mb_prefetch_fini(struct super_block *sb, ext4_group_t group,
				  unsigned int nr);

2769
extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
2770 2771
			     struct buffer_head *bh, ext4_fsblk_t block,
			     unsigned long count, int flags);
2772 2773
extern int ext4_mb_alloc_groupinfo(struct super_block *sb,
				   ext4_group_t ngroups);
2774
extern int ext4_mb_add_groupinfo(struct super_block *sb,
2775
		ext4_group_t i, struct ext4_group_desc *desc);
2776
extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
2777
				ext4_fsblk_t block, unsigned long count);
2778
extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);
2779
extern void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid);
2780 2781
extern void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
		       int len, int state);
2782

2783
/* inode.c */
2784 2785
void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw,
			 struct ext4_inode_info *ei);
2786
int ext4_inode_is_fast_symlink(struct inode *inode);
2787
struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int);
2788
struct buffer_head *ext4_bread(handle_t *, struct inode *, ext4_lblk_t, int);
2789 2790
int ext4_bread_batch(struct inode *inode, ext4_lblk_t block, int bh_count,
		     bool wait, struct buffer_head **bhs);
2791 2792
int ext4_get_block_unwritten(struct inode *inode, sector_t iblock,
			     struct buffer_head *bh_result, int create);
2793
int ext4_get_block(struct inode *inode, sector_t iblock,
2794
		   struct buffer_head *bh_result, int create);
2795 2796
int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
			   struct buffer_head *bh, int create);
2797 2798 2799 2800 2801 2802 2803 2804 2805
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);
2806 2807
#define FALL_BACK_TO_NONDELALLOC 1
#define CONVERT_INLINE_DATA	 2
2808

2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821
typedef enum {
	EXT4_IGET_NORMAL =	0,
	EXT4_IGET_SPECIAL =	0x0001, /* OK to iget a system inode */
	EXT4_IGET_HANDLE = 	0x0002	/* Inode # is from a handle */
} ext4_iget_flags;

extern struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
				 ext4_iget_flags flags, const char *function,
				 unsigned int line);

#define ext4_iget(sb, ino, flags) \
	__ext4_iget((sb), (ino), (flags), __func__, __LINE__)

2822
extern int  ext4_write_inode(struct inode *, struct writeback_control *);
2823
extern int  ext4_setattr(struct dentry *, struct iattr *);
2824
extern int  ext4_getattr(const struct path *, struct kstat *, u32, unsigned int);
A
Al Viro 已提交
2825 2826
extern void ext4_evict_inode(struct inode *);
extern void ext4_clear_inode(struct inode *);
D
David Howells 已提交
2827
extern int  ext4_file_getattr(const struct path *, struct kstat *, u32, unsigned int);
2828
extern int  ext4_sync_inode(handle_t *, struct inode *);
2829
extern void ext4_dirty_inode(struct inode *, int);
2830 2831
extern int ext4_change_inode_journal_flag(struct inode *, int);
extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
2832 2833
extern int ext4_get_fc_inode_loc(struct super_block *sb, unsigned long ino,
			  struct ext4_iloc *iloc);
2834
extern int ext4_inode_attach_jinode(struct inode *inode);
2835
extern int ext4_can_truncate(struct inode *inode);
2836
extern int ext4_truncate(struct inode *);
2837
extern int ext4_break_layouts(struct inode *);
2838
extern int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length);
2839
extern void ext4_set_inode_flags(struct inode *, bool init);
2840
extern int ext4_alloc_da_blocks(struct inode *inode);
2841
extern void ext4_set_aops(struct inode *inode);
A
Alex Tomas 已提交
2842
extern int ext4_writepage_trans_blocks(struct inode *);
2843
extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
2844 2845
extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
			     loff_t lstart, loff_t lend);
2846 2847
extern vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf);
extern vm_fault_t ext4_filemap_fault(struct vm_fault *vmf);
2848
extern qsize_t *ext4_get_reserved_space(struct inode *inode);
L
Li Xi 已提交
2849
extern int ext4_get_projid(struct inode *inode, kprojid_t *projid);
2850
extern void ext4_da_release_space(struct inode *inode, int to_free);
2851 2852
extern void ext4_da_update_reserve_space(struct inode *inode,
					int used, int quota_claim);
J
Jan Kara 已提交
2853 2854
extern int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk,
			      ext4_fsblk_t pblk, ext4_lblk_t len);
2855 2856 2857 2858

/* indirect.c */
extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
				struct ext4_map_blocks *map, int flags);
2859
extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks);
T
Theodore Ts'o 已提交
2860
extern void ext4_ind_truncate(handle_t *, struct inode *inode);
2861 2862
extern int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
				 ext4_lblk_t start, ext4_lblk_t end);
2863

2864
/* ioctl.c */
A
Andi Kleen 已提交
2865
extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
2866
extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
2867
extern void ext4_reset_inode_seed(struct inode *inode);
2868

2869
/* migrate.c */
2870
extern int ext4_ext_migrate(struct inode *);
2871
extern int ext4_ind_migrate(struct inode *inode);
2872

2873
/* namei.c */
2874 2875
extern int ext4_init_new_dir(handle_t *handle, struct inode *dir,
			     struct inode *inode);
2876 2877
extern int ext4_dirblock_csum_verify(struct inode *inode,
				     struct buffer_head *bh);
2878 2879 2880
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,
2881
				__u32 start_minor_hash, __u32 *next_hash);
2882 2883 2884 2885 2886 2887 2888
extern int ext4_search_dir(struct buffer_head *bh,
			   char *search_buf,
			   int buf_size,
			   struct inode *dir,
			   struct ext4_filename *fname,
			   unsigned int offset,
			   struct ext4_dir_entry_2 **res_dir);
2889
extern int ext4_generic_delete_entry(struct inode *dir,
T
Tao Ma 已提交
2890 2891 2892 2893 2894
				     struct ext4_dir_entry_2 *de_del,
				     struct buffer_head *bh,
				     void *entry_buf,
				     int buf_size,
				     int csum_size);
2895
extern bool ext4_empty_dir(struct inode *inode);
2896 2897

/* resize.c */
2898
extern void ext4_kvfree_array_rcu(void *to_free);
2899 2900 2901 2902 2903
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);
2904
extern int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count);
2905 2906

/* super.c */
2907 2908
extern struct buffer_head *ext4_sb_bread(struct super_block *sb,
					 sector_t block, int op_flags);
2909 2910
extern struct buffer_head *ext4_sb_bread_unmovable(struct super_block *sb,
						   sector_t block);
2911 2912 2913 2914 2915
extern void ext4_read_bh_nowait(struct buffer_head *bh, int op_flags,
				bh_end_io_t *end_io);
extern int ext4_read_bh(struct buffer_head *bh, int op_flags,
			bh_end_io_t *end_io);
extern int ext4_read_bh_lock(struct buffer_head *bh, int op_flags, bool wait);
2916
extern void ext4_sb_breadahead_unmovable(struct super_block *sb, sector_t block);
2917
extern int ext4_seq_options_show(struct seq_file *seq, void *offset);
2918
extern int ext4_calculate_overhead(struct super_block *sb);
2919
extern void ext4_superblock_csum_set(struct super_block *sb);
2920 2921
extern int ext4_alloc_flex_bg_array(struct super_block *sb,
				    ext4_group_t ngroup);
2922 2923
extern const char *ext4_decode_error(struct super_block *sb, int errno,
				     char nbuf[16]);
2924 2925 2926
extern void ext4_mark_group_bitmap_corrupted(struct super_block *sb,
					     ext4_group_t block_group,
					     unsigned int flags);
2927

2928 2929
extern __printf(6, 7)
void __ext4_error(struct super_block *, const char *, unsigned int, int, __u64,
2930
		  const char *, ...);
2931 2932 2933
extern __printf(6, 7)
void __ext4_error_inode(struct inode *, const char *, unsigned int,
			ext4_fsblk_t, int, const char *, ...);
2934
extern __printf(5, 6)
2935
void __ext4_error_file(struct file *, const char *, unsigned int, ext4_fsblk_t,
2936
		     const char *, ...);
2937 2938
extern void __ext4_std_error(struct super_block *, const char *,
			     unsigned int, int);
2939 2940
extern __printf(5, 6)
void __ext4_abort(struct super_block *, const char *, unsigned int, int,
2941 2942 2943 2944
		  const char *, ...);
extern __printf(4, 5)
void __ext4_warning(struct super_block *, const char *, unsigned int,
		    const char *, ...);
2945 2946 2947
extern __printf(4, 5)
void __ext4_warning_inode(const struct inode *inode, const char *function,
			  unsigned int line, const char *fmt, ...);
2948
extern __printf(3, 4)
2949
void __ext4_msg(struct super_block *, const char *, const char *, ...);
2950 2951
extern void __dump_mmp_msg(struct super_block *, struct mmp_struct *mmp,
			   const char *, unsigned int, const char *);
2952 2953 2954 2955 2956
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 *, ...);
2957

2958 2959 2960
#define EXT4_ERROR_INODE(inode, fmt, a...) \
	ext4_error_inode((inode), __func__, __LINE__, 0, (fmt), ## a)

2961 2962 2963 2964 2965 2966
#define EXT4_ERROR_INODE_ERR(inode, err, fmt, a...)			\
	__ext4_error_inode((inode), __func__, __LINE__, 0, (err), (fmt), ## a)

#define ext4_error_inode_block(inode, block, err, fmt, a...)		\
	__ext4_error_inode((inode), __func__, __LINE__, (block), (err),	\
			   (fmt), ## a)
2967 2968 2969 2970

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

2971 2972 2973
#ifdef CONFIG_PRINTK

#define ext4_error_inode(inode, func, line, block, fmt, ...)		\
2974 2975 2976 2977
	__ext4_error_inode(inode, func, line, block, 0, fmt, ##__VA_ARGS__)
#define ext4_error_inode_err(inode, func, line, block, err, fmt, ...)	\
	__ext4_error_inode((inode), (func), (line), (block), 		\
			   (err), (fmt), ##__VA_ARGS__)
2978 2979 2980
#define ext4_error_file(file, func, line, block, fmt, ...)		\
	__ext4_error_file(file, func, line, block, fmt, ##__VA_ARGS__)
#define ext4_error(sb, fmt, ...)					\
2981 2982 2983 2984 2985
	__ext4_error((sb), __func__, __LINE__, 0, 0, (fmt), ##__VA_ARGS__)
#define ext4_error_err(sb, err, fmt, ...)				\
	__ext4_error((sb), __func__, __LINE__, (err), 0, (fmt), ##__VA_ARGS__)
#define ext4_abort(sb, err, fmt, ...)					\
	__ext4_abort((sb), __func__, __LINE__, (err), (fmt), ##__VA_ARGS__)
2986 2987
#define ext4_warning(sb, fmt, ...)					\
	__ext4_warning(sb, __func__, __LINE__, fmt, ##__VA_ARGS__)
2988 2989
#define ext4_warning_inode(inode, fmt, ...)				\
	__ext4_warning_inode(inode, __func__, __LINE__, fmt, ##__VA_ARGS__)
2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002
#define ext4_msg(sb, level, fmt, ...)				\
	__ext4_msg(sb, level, fmt, ##__VA_ARGS__)
#define dump_mmp_msg(sb, mmp, msg)					\
	__dump_mmp_msg(sb, mmp, __func__, __LINE__, msg)
#define ext4_grp_locked_error(sb, grp, ino, block, fmt, ...)		\
	__ext4_grp_locked_error(__func__, __LINE__, sb, grp, ino, block, \
				fmt, ##__VA_ARGS__)

#else

#define ext4_error_inode(inode, func, line, block, fmt, ...)		\
do {									\
	no_printk(fmt, ##__VA_ARGS__);					\
3003 3004 3005 3006 3007 3008
	__ext4_error_inode(inode, "", 0, block, 0, " ");		\
} while (0)
#define ext4_error_inode_err(inode, func, line, block, err, fmt, ...)	\
do {									\
	no_printk(fmt, ##__VA_ARGS__);					\
	__ext4_error_inode(inode, "", 0, block, err, " ");		\
3009 3010 3011 3012 3013 3014 3015 3016 3017
} while (0)
#define ext4_error_file(file, func, line, block, fmt, ...)		\
do {									\
	no_printk(fmt, ##__VA_ARGS__);					\
	__ext4_error_file(file, "", 0, block, " ");			\
} while (0)
#define ext4_error(sb, fmt, ...)					\
do {									\
	no_printk(fmt, ##__VA_ARGS__);					\
3018 3019 3020 3021 3022 3023
	__ext4_error(sb, "", 0, 0, 0, " ");				\
} while (0)
#define ext4_error_err(sb, err, fmt, ...)				\
do {									\
	no_printk(fmt, ##__VA_ARGS__);					\
	__ext4_error(sb, "", 0, err, 0, " ");				\
3024
} while (0)
3025
#define ext4_abort(sb, err, fmt, ...)					\
3026 3027
do {									\
	no_printk(fmt, ##__VA_ARGS__);					\
3028
	__ext4_abort(sb, "", 0, err, " ");				\
3029 3030 3031 3032 3033 3034
} while (0)
#define ext4_warning(sb, fmt, ...)					\
do {									\
	no_printk(fmt, ##__VA_ARGS__);					\
	__ext4_warning(sb, "", 0, " ");					\
} while (0)
3035 3036 3037 3038 3039
#define ext4_warning_inode(inode, fmt, ...)				\
do {									\
	no_printk(fmt, ##__VA_ARGS__);					\
	__ext4_warning_inode(inode, "", 0, " ");			\
} while (0)
3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054
#define ext4_msg(sb, level, fmt, ...)					\
do {									\
	no_printk(fmt, ##__VA_ARGS__);					\
	__ext4_msg(sb, "", " ");					\
} while (0)
#define dump_mmp_msg(sb, mmp, msg)					\
	__dump_mmp_msg(sb, mmp, "", 0, "")
#define ext4_grp_locked_error(sb, grp, ino, block, fmt, ...)		\
do {									\
	no_printk(fmt, ##__VA_ARGS__);				\
	__ext4_grp_locked_error("", 0, sb, grp, ino, block, " ");	\
} while (0)

#endif

3055 3056 3057 3058 3059 3060
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);
3061 3062
extern __u32 ext4_free_group_clusters(struct super_block *sb,
				      struct ext4_group_desc *bg);
3063 3064 3065 3066 3067 3068
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);
3069 3070 3071 3072 3073 3074
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);
3075 3076 3077
extern void ext4_free_group_clusters_set(struct super_block *sb,
					 struct ext4_group_desc *bg,
					 __u32 count);
3078 3079 3080 3081 3082 3083
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);
3084
extern int ext4_group_desc_csum_verify(struct super_block *sb, __u32 group,
3085
				       struct ext4_group_desc *gdp);
3086 3087
extern void ext4_group_desc_csum_set(struct super_block *sb, __u32 group,
				     struct ext4_group_desc *gdp);
3088 3089
extern int ext4_register_li_request(struct super_block *sb,
				    ext4_group_t first_not_zeroed);
L
Laurent Vivier 已提交
3090

3091 3092
static inline int ext4_has_metadata_csum(struct super_block *sb)
{
3093
	WARN_ON_ONCE(ext4_has_feature_metadata_csum(sb) &&
3094 3095
		     !EXT4_SB(sb)->s_chksum_driver);

T
Tahsin Erdogan 已提交
3096 3097
	return ext4_has_feature_metadata_csum(sb) &&
	       (EXT4_SB(sb)->s_chksum_driver != NULL);
3098
}
T
Tahsin Erdogan 已提交
3099 3100 3101 3102 3103 3104

static inline int ext4_has_group_desc_csum(struct super_block *sb)
{
	return ext4_has_feature_gdt_csum(sb) || ext4_has_metadata_csum(sb);
}

3105 3106 3107 3108 3109
#define ext4_read_incompat_64bit_val(es, name) \
	(((es)->s_feature_incompat & cpu_to_le32(EXT4_FEATURE_INCOMPAT_64BIT) \
		? (ext4_fsblk_t)le32_to_cpu(es->name##_hi) << 32 : 0) | \
		le32_to_cpu(es->name##_lo))

L
Laurent Vivier 已提交
3110 3111
static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es)
{
3112
	return ext4_read_incompat_64bit_val(es, s_blocks_count);
L
Laurent Vivier 已提交
3113 3114 3115 3116
}

static inline ext4_fsblk_t ext4_r_blocks_count(struct ext4_super_block *es)
{
3117
	return ext4_read_incompat_64bit_val(es, s_r_blocks_count);
L
Laurent Vivier 已提交
3118 3119 3120 3121
}

static inline ext4_fsblk_t ext4_free_blocks_count(struct ext4_super_block *es)
{
3122
	return ext4_read_incompat_64bit_val(es, s_free_blocks_count);
L
Laurent Vivier 已提交
3123 3124 3125 3126 3127
}

static inline void ext4_blocks_count_set(struct ext4_super_block *es,
					 ext4_fsblk_t blk)
{
3128
	es->s_blocks_count_lo = cpu_to_le32((u32)blk);
L
Laurent Vivier 已提交
3129 3130 3131 3132 3133 3134
	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)
{
3135
	es->s_free_blocks_count_lo = cpu_to_le32((u32)blk);
L
Laurent Vivier 已提交
3136 3137 3138 3139 3140 3141
	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)
{
3142
	es->s_r_blocks_count_lo = cpu_to_le32((u32)blk);
L
Laurent Vivier 已提交
3143 3144 3145
	es->s_r_blocks_count_hi = cpu_to_le32(blk >> 32);
}

A
Artem Blagodarenko 已提交
3146 3147
static inline loff_t ext4_isize(struct super_block *sb,
				struct ext4_inode *raw_inode)
3148
{
A
Artem Blagodarenko 已提交
3149 3150
	if (ext4_has_feature_largedir(sb) ||
	    S_ISREG(le16_to_cpu(raw_inode->i_mode)))
3151 3152
		return ((loff_t)le32_to_cpu(raw_inode->i_size_high) << 32) |
			le32_to_cpu(raw_inode->i_size_lo);
A
Artem Blagodarenko 已提交
3153 3154

	return (loff_t) le32_to_cpu(raw_inode->i_size_lo);
3155
}
L
Laurent Vivier 已提交
3156

3157 3158 3159 3160 3161
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);
}
3162

3163 3164
static inline
struct ext4_group_info *ext4_get_group_info(struct super_block *sb,
3165
					    ext4_group_t group)
3166
{
3167
	 struct ext4_group_info **grp_info;
3168
	 long indexv, indexh;
3169
	 BUG_ON(group >= EXT4_SB(sb)->s_groups_count);
3170 3171
	 indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb));
	 indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1);
3172 3173
	 grp_info = sbi_array_rcu_deref(EXT4_SB(sb), s_group_info, indexv);
	 return grp_info[indexh];
3174 3175
}

3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187
/*
 * 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;
}
3188

3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199
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;
}

3200
#define ext4_std_error(sb, errno)				\
3201 3202
do {								\
	if ((errno))						\
3203
		__ext4_std_error((sb), __func__, __LINE__, (errno));	\
3204 3205
} while (0)

3206
#ifdef CONFIG_SMP
3207 3208
/* Each CPU can accumulate percpu_counter_batch clusters in their local
 * counters. So we need to make sure we have free clusters more
3209
 * than percpu_counter_batch  * nr_cpu_ids. Also add a window of 4 times.
3210
 */
3211
#define EXT4_FREECLUSTERS_WATERMARK (4 * (percpu_counter_batch * nr_cpu_ids))
3212
#else
3213
#define EXT4_FREECLUSTERS_WATERMARK 0
3214 3215
#endif

3216
/* Update i_disksize. Requires i_mutex to avoid races with truncate */
3217 3218
static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
{
3219
	WARN_ON_ONCE(S_ISREG(inode->i_mode) &&
A
Al Viro 已提交
3220
		     !inode_is_locked(inode));
3221 3222
	down_write(&EXT4_I(inode)->i_data_sem);
	if (newsize > EXT4_I(inode)->i_disksize)
3223
		WRITE_ONCE(EXT4_I(inode)->i_disksize, newsize);
3224 3225 3226
	up_write(&EXT4_I(inode)->i_data_sem);
}

3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242
/* Update i_size, i_disksize. Requires i_mutex to avoid races with truncate */
static inline int ext4_update_inode_size(struct inode *inode, loff_t newsize)
{
	int changed = 0;

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

3243 3244 3245
int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
				      loff_t len);

3246 3247
struct ext4_group_info {
	unsigned long   bb_state;
3248 3249 3250
#ifdef AGGRESSIVE_CHECK
	unsigned long	bb_check_counter;
#endif
3251
	struct rb_root  bb_free_root;
3252 3253 3254
	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 */
3255
	ext4_grpblk_t	bb_largest_free_order;/* order of largest frag in BG */
3256 3257 3258 3259 3260
	struct          list_head bb_prealloc_list;
#ifdef DOUBLE_CHECK
	void            *bb_bitmap;
#endif
	struct rw_semaphore alloc_sem;
3261 3262 3263 3264
	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. */
3265 3266
};

3267 3268
#define EXT4_GROUP_INFO_NEED_INIT_BIT		0
#define EXT4_GROUP_INFO_WAS_TRIMMED_BIT		1
3269
#define EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT	2
3270
#define EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT	3
3271 3272 3273 3274
#define EXT4_GROUP_INFO_BBITMAP_CORRUPT		\
	(1 << EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT)
#define EXT4_GROUP_INFO_IBITMAP_CORRUPT		\
	(1 << EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT)
3275
#define EXT4_GROUP_INFO_BBITMAP_READ_BIT	4
3276 3277 3278

#define EXT4_MB_GRP_NEED_INIT(grp)	\
	(test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
3279 3280
#define EXT4_MB_GRP_BBITMAP_CORRUPT(grp)	\
	(test_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &((grp)->bb_state)))
3281 3282
#define EXT4_MB_GRP_IBITMAP_CORRUPT(grp)	\
	(test_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &((grp)->bb_state)))
3283

3284 3285 3286 3287 3288 3289
#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)))
3290 3291
#define EXT4_MB_GRP_TEST_AND_SET_READ(grp)	\
	(test_and_set_bit(EXT4_GROUP_INFO_BBITMAP_READ_BIT, &((grp)->bb_state)))
3292

3293 3294 3295
#define EXT4_MAX_CONTENTION		8
#define EXT4_CONTENTION_THRESHOLD	2

3296 3297
static inline spinlock_t *ext4_group_lock_ptr(struct super_block *sb,
					      ext4_group_t group)
3298
{
3299 3300
	return bgl_lock_ptr(EXT4_SB(sb)->s_blockgroup_lock, group);
}
3301

3302 3303 3304 3305 3306 3307 3308 3309 3310
/*
 * 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);
}

3311 3312
static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group)
{
3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328
	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);
	}
3329 3330 3331 3332 3333
}

static inline void ext4_unlock_group(struct super_block *sb,
					ext4_group_t group)
{
3334
	spin_unlock(ext4_group_lock_ptr(sb, group));
3335 3336
}

3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349
/*
 * 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)

3350 3351 3352 3353 3354
/*
 * Inodes and files operations
 */

/* dir.c */
3355
extern const struct file_operations ext4_dir_operations;
3356

3357 3358 3359 3360
#ifdef CONFIG_UNICODE
extern const struct dentry_operations ext4_dentry_ops;
#endif

3361
/* file.c */
3362
extern const struct inode_operations ext4_file_inode_operations;
3363
extern const struct file_operations ext4_file_operations;
3364
extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
3365

3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395
/* inline.c */
extern int ext4_get_max_inline_size(struct inode *inode);
extern int ext4_find_inline_data_nolock(struct inode *inode);
extern int ext4_init_inline_data(handle_t *handle, struct inode *inode,
				 unsigned int len);
extern int ext4_destroy_inline_data(handle_t *handle, struct inode *inode);

extern int ext4_readpage_inline(struct inode *inode, struct page *page);
extern int ext4_try_to_write_inline_data(struct address_space *mapping,
					 struct inode *inode,
					 loff_t pos, unsigned len,
					 unsigned flags,
					 struct page **pagep);
extern int ext4_write_inline_data_end(struct inode *inode,
				      loff_t pos, unsigned len,
				      unsigned copied,
				      struct page *page);
extern struct buffer_head *
ext4_journalled_write_inline_data(struct inode *inode,
				  unsigned len,
				  struct page *page);
extern int ext4_da_write_inline_data_begin(struct address_space *mapping,
					   struct inode *inode,
					   loff_t pos, unsigned len,
					   unsigned flags,
					   struct page **pagep,
					   void **fsdata);
extern int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos,
					 unsigned len, unsigned copied,
					 struct page *page);
3396 3397
extern int ext4_try_add_inline_entry(handle_t *handle,
				     struct ext4_filename *fname,
3398
				     struct inode *dir, struct inode *inode);
3399 3400 3401 3402
extern int ext4_try_create_inline_dir(handle_t *handle,
				      struct inode *parent,
				      struct inode *inode);
extern int ext4_read_inline_dir(struct file *filp,
A
Al Viro 已提交
3403
				struct dir_context *ctx,
3404
				int *has_inline_data);
3405 3406 3407 3408 3409
extern int ext4_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);
3410
extern struct buffer_head *ext4_find_inline_entry(struct inode *dir,
3411
					struct ext4_filename *fname,
3412 3413 3414 3415 3416 3417 3418
					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);
3419
extern bool empty_inline_dir(struct inode *dir, int *has_inline_data);
3420 3421 3422 3423 3424
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,
3425
				   int *has_inline, __u64 start, __u64 len);
3426 3427 3428 3429

struct iomap;
extern int ext4_inline_data_iomap(struct inode *inode, struct iomap *iomap);

3430
extern int ext4_inline_data_truncate(struct inode *inode, int *has_inline);
3431 3432 3433

extern int ext4_convert_inline_data(struct inode *inode);

3434 3435 3436 3437 3438 3439
static inline int ext4_has_inline_data(struct inode *inode)
{
	return ext4_test_inode_flag(inode, EXT4_INODE_INLINE_DATA) &&
	       EXT4_I(inode)->i_inline_off;
}

3440
/* namei.c */
3441 3442
extern const struct inode_operations ext4_dir_inode_operations;
extern const struct inode_operations ext4_special_inode_operations;
3443
extern struct dentry *ext4_get_parent(struct dentry *child);
3444 3445 3446 3447
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);
3448 3449
extern void ext4_initialize_dirent_tail(struct buffer_head *bh,
					unsigned int blocksize);
3450 3451
extern int ext4_handle_dirty_dirblock(handle_t *handle, struct inode *inode,
				      struct buffer_head *bh);
3452
extern int ext4_ci_compare(const struct inode *parent,
3453 3454
			   const struct qstr *fname,
			   const struct qstr *entry, bool quick);
3455 3456 3457 3458
extern int __ext4_unlink(struct inode *dir, const struct qstr *d_name,
			 struct inode *inode);
extern int __ext4_link(struct inode *dir, struct inode *inode,
		       struct dentry *dentry);
3459

3460
#define S_SHIFT 12
3461
static const unsigned char ext4_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = {
3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473
	[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) {
3474
	if (ext4_has_feature_filetype(sb))
3475 3476 3477
		de->file_type = ext4_type_by_mode[(mode & S_IFMT)>>S_SHIFT];
}

3478
/* readpages.c */
3479
extern int ext4_mpage_readpages(struct inode *inode,
3480
		struct readahead_control *rac, struct page *page);
E
Eric Biggers 已提交
3481 3482
extern int __init ext4_init_post_read_processing(void);
extern void ext4_exit_post_read_processing(void);
3483 3484

/* symlink.c */
3485
extern const struct inode_operations ext4_encrypted_symlink_inode_operations;
3486 3487
extern const struct inode_operations ext4_symlink_inode_operations;
extern const struct inode_operations ext4_fast_symlink_inode_operations;
3488

3489 3490
/* sysfs.c */
extern int ext4_register_sysfs(struct super_block *sb);
3491
extern void ext4_unregister_sysfs(struct super_block *sb);
3492 3493 3494
extern int __init ext4_init_sysfs(void);
extern void ext4_exit_sysfs(void);

3495 3496 3497
/* block_validity */
extern void ext4_release_system_zone(struct super_block *sb);
extern int ext4_setup_system_zone(struct super_block *sb);
3498 3499
extern int __init ext4_init_system_zone(void);
extern void ext4_exit_system_zone(void);
3500 3501 3502
extern int ext4_inode_block_valid(struct inode *inode,
				  ext4_fsblk_t start_blk,
				  unsigned int count);
3503 3504
extern int ext4_check_blockref(const char *, unsigned int,
			       struct inode *, __le32 *, unsigned int);
3505

A
Alex Tomas 已提交
3506
/* extents.c */
3507 3508 3509
struct ext4_ext_path;
struct ext4_extent;

Z
Zheng Liu 已提交
3510 3511 3512 3513 3514 3515
/*
 * Maximum number of logical blocks in a file; ext4_extent's ee_block is
 * __le32.
 */
#define EXT_MAX_BLOCKS	0xffffffff

3516
extern void ext4_ext_tree_init(handle_t *handle, struct inode *inode);
3517
extern int ext4_ext_index_trans_blocks(struct inode *inode, int extents);
3518 3519
extern int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
			       struct ext4_map_blocks *map, int flags);
3520
extern int ext4_ext_truncate(handle_t *, struct inode *);
T
Theodore Ts'o 已提交
3521 3522
extern int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
				 ext4_lblk_t end);
A
Alex Tomas 已提交
3523 3524
extern void ext4_ext_init(struct super_block *);
extern void ext4_ext_release(struct super_block *);
3525
extern long ext4_fallocate(struct file *file, int mode, loff_t offset,
A
Amit Arora 已提交
3526
			  loff_t len);
3527 3528
extern int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode,
					  loff_t offset, ssize_t len);
3529 3530
extern int ext4_convert_unwritten_io_end_vec(handle_t *handle,
					     ext4_io_end_t *io_end);
3531 3532
extern int ext4_map_blocks(handle_t *handle, struct inode *inode,
			   struct ext4_map_blocks *map, int flags);
3533 3534 3535 3536
extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode,
						   int num,
						   struct ext4_ext_path *path);
extern int ext4_ext_insert_extent(handle_t *, struct inode *,
3537
				  struct ext4_ext_path **,
3538
				  struct ext4_extent *, int);
3539 3540 3541
extern struct ext4_ext_path *ext4_find_extent(struct inode *, ext4_lblk_t,
					      struct ext4_ext_path **,
					      int flags);
3542 3543
extern void ext4_ext_drop_refs(struct ext4_ext_path *);
extern int ext4_ext_check_inode(struct inode *inode);
3544
extern ext4_lblk_t ext4_ext_next_allocated_block(struct ext4_ext_path *path);
A
Aneesh Kumar K.V 已提交
3545 3546
extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
			__u64 start, __u64 len);
3547 3548 3549
extern int ext4_get_es_cache(struct inode *inode,
			     struct fiemap_extent_info *fieinfo,
			     __u64 start, __u64 len);
3550
extern int ext4_ext_precache(struct inode *inode);
3551 3552 3553 3554
extern int ext4_swap_extents(handle_t *handle, struct inode *inode1,
				struct inode *inode2, ext4_lblk_t lblk1,
			     ext4_lblk_t lblk2,  ext4_lblk_t count,
			     int mark_unwritten,int *err);
3555
extern int ext4_clu_mapped(struct inode *inode, ext4_lblk_t lclu);
3556
extern int ext4_datasem_ensure_credits(handle_t *handle, struct inode *inode,
3557 3558
				       int check_cred, int restart_cred,
				       int revoke_cred);
3559 3560 3561 3562 3563
extern void ext4_ext_replay_shrink_inode(struct inode *inode, ext4_lblk_t end);
extern int ext4_ext_replay_set_iblocks(struct inode *inode);
extern int ext4_ext_replay_update_ex(struct inode *inode, ext4_lblk_t start,
		int len, int unwritten, ext4_fsblk_t pblk);
extern int ext4_ext_clear_bb(struct inode *inode);
3564

3565

3566
/* move_extent.c */
3567 3568 3569 3570
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);
3571 3572 3573 3574
extern int ext4_move_extents(struct file *o_filp, struct file *d_filp,
			     __u64 start_orig, __u64 start_donor,
			     __u64 len, __u64 *moved_len);

3575
/* page-io.c */
3576 3577
extern int __init ext4_init_pageio(void);
extern void ext4_exit_pageio(void);
3578
extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags);
J
Jan Kara 已提交
3579 3580 3581 3582 3583
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);
3584
extern void ext4_end_io_rsv_work(struct work_struct *work);
3585 3586 3587 3588
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,
3589 3590
			       struct writeback_control *wbc,
			       bool keep_towrite);
3591 3592
extern struct ext4_io_end_vec *ext4_alloc_io_end_vec(ext4_io_end_t *io_end);
extern struct ext4_io_end_vec *ext4_last_io_end_vec(ext4_io_end_t *io_end);
A
Aneesh Kumar K.V 已提交
3593

3594 3595 3596
/* mmp.c */
extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);

E
Eric Biggers 已提交
3597 3598 3599
/* verity.c */
extern const struct fsverity_operations ext4_verityops;

3600
/*
3601
 * Add new method to test whether block and inode bitmaps are properly
3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616
 * 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);
}

3617 3618
#define in_range(b, first, len)	((b) >= (first) && (b) <= (first) + (len) - 1)

3619 3620 3621 3622 3623 3624
/* For ioend & aio unwritten conversion wait queues */
#define EXT4_WQ_HASH_SZ		37
#define ext4_ioend_wq(v)   (&ext4__ioend_wq[((unsigned long)(v)) %\
					    EXT4_WQ_HASH_SZ])
extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];

3625 3626 3627
extern int ext4_resize_begin(struct super_block *sb);
extern void ext4_resize_end(struct super_block *sb);

3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648
static inline void ext4_set_io_unwritten_flag(struct inode *inode,
					      struct ext4_io_end *io_end)
{
	if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
		io_end->flag |= EXT4_IO_END_UNWRITTEN;
		atomic_inc(&EXT4_I(inode)->i_unwritten);
	}
}

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

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

3649
extern const struct iomap_ops ext4_iomap_ops;
J
Jan Kara 已提交
3650
extern const struct iomap_ops ext4_iomap_overwrite_ops;
3651
extern const struct iomap_ops ext4_iomap_report_ops;
3652

3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665
static inline int ext4_buffer_uptodate(struct buffer_head *bh)
{
	/*
	 * If the buffer has the write error flag, we have failed
	 * to write out data in the block.  In this  case, we don't
	 * have to read the block because we may read the old data
	 * successfully.
	 */
	if (!buffer_uptodate(bh) && buffer_write_io_error(bh))
		set_buffer_uptodate(bh);
	return buffer_uptodate(bh);
}

3666 3667
#endif	/* __KERNEL__ */

3668 3669 3670
#define EFSBADCRC	EBADMSG		/* Bad CRC detected */
#define EFSCORRUPTED	EUCLEAN		/* Filesystem is corrupted */

3671
#endif	/* _EXT4_H */