ext4.h 122.7 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
#include <linux/timer.h>
30
#include <linux/version.h>
31
#include <linux/wait.h>
32
#include <linux/sched/signal.h>
33 34
#include <linux/blockgroup_lock.h>
#include <linux/percpu_counter.h>
35
#include <linux/ratelimit.h>
36
#include <crypto/hash.h>
37
#include <linux/falloc.h>
38
#include <linux/percpu-rwsem.h>
39
#include <linux/fiemap.h>
40 41 42
#ifdef __KERNEL__
#include <linux/compat.h>
#endif
43

D
Dave Chinner 已提交
44
#include <linux/fscrypt.h>
E
Eric Biggers 已提交
45
#include <linux/fsverity.h>
D
Dave Chinner 已提交
46

47 48
#include <linux/compiler.h>

49
/*
S
Shen Feng 已提交
50
 * The fourth extended filesystem constants/structures
51 52
 */

53 54 55 56 57 58 59 60 61 62 63 64
/*
 * 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__

65
/*
66
 * Define EXT4FS_DEBUG to produce debug messages
67
 */
68
#undef EXT4FS_DEBUG
69 70 71 72

/*
 * Debug code
 */
73 74
#ifdef EXT4FS_DEBUG
#define ext4_debug(f, a...)						\
75
	do {								\
76
		printk(KERN_DEBUG "EXT4-fs DEBUG (%s, %d): %s:",	\
77
			__FILE__, __LINE__, __func__);			\
78
		printk(KERN_DEBUG f, ## a);				\
79 80
	} while (0)
#else
81
#define ext4_debug(fmt, ...)	no_printk(fmt, ##__VA_ARGS__)
82 83
#endif

84 85 86 87 88
 /*
  * Turn on EXT_DEBUG to enable ext4_ext_show_path/leaf/move in extents.c
  */
#define EXT_DEBUG__

89
/*
90
 * Dynamic printk for controlled extents debugging.
91
 */
92 93 94 95 96 97
#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__)
98
#else
99
#define ext_debug(ino, fmt, ...)	no_printk(fmt, ##__VA_ARGS__)
100 101
#endif

102 103 104 105 106 107 108 109 110 111 112 113
/* 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;

114 115 116 117 118
enum SHIFT_DIRECTION {
	SHIFT_LEFT = 0,
	SHIFT_RIGHT,
};

119
/*
120
 * Flags used in mballoc's allocation_context flags field.
121 122 123 124
 *
 * Also used to show what's going on for debugging purposes when the
 * flag field is exported via the traceport interface
 */
125

126
/* prefer goal again. length */
127
#define EXT4_MB_HINT_MERGE		0x0001
128
/* blocks already reserved */
129
#define EXT4_MB_HINT_RESERVED		0x0002
130
/* metadata is being allocated */
131
#define EXT4_MB_HINT_METADATA		0x0004
132
/* first blocks in the file */
133
#define EXT4_MB_HINT_FIRST		0x0008
134
/* search for the best chunk */
135
#define EXT4_MB_HINT_BEST		0x0010
136
/* data is being allocated */
137
#define EXT4_MB_HINT_DATA		0x0020
138
/* don't preallocate (for tails) */
139
#define EXT4_MB_HINT_NOPREALLOC		0x0040
140
/* allocate for locality group */
141
#define EXT4_MB_HINT_GROUP_ALLOC	0x0080
142
/* allocate goal blocks or none */
143
#define EXT4_MB_HINT_GOAL_ONLY		0x0100
144
/* goal is meaningful */
145
#define EXT4_MB_HINT_TRY_GOAL		0x0200
146
/* blocks already pre-reserved by delayed allocation */
147
#define EXT4_MB_DELALLOC_RESERVED	0x0400
148 149
/* We are doing stream allocation */
#define EXT4_MB_STREAM_ALLOC		0x0800
150 151
/* Use reserved root blocks if needed */
#define EXT4_MB_USE_ROOT_BLOCKS		0x1000
L
Lukas Czerner 已提交
152 153
/* Use blocks from reserved pool */
#define EXT4_MB_USE_RESERVED		0x2000
154 155
/* Do strict check for free blocks while retrying block allocation */
#define EXT4_MB_STRICT_CHECK		0x4000
156 157 158 159

struct ext4_allocation_request {
	/* target inode for block we're allocating */
	struct inode *inode;
160 161
	/* how many blocks we want to allocate */
	unsigned int len;
162 163 164 165 166 167
	/* 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;
168 169 170 171 172
	/* 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 */
173 174
	ext4_fsblk_t pright;
	/* flags. see above EXT4_MB_HINT_* */
175
	unsigned int flags;
176 177
};

178 179 180 181 182 183 184
/*
 * 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.
 */
185 186 187 188
#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)
189
#define EXT4_MAP_FLAGS		(EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
190
				 EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY)
191 192 193 194 195 196 197 198

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

199 200 201 202 203 204 205 206
/*
 * Block validity checking, system zone rbtree.
 */
struct ext4_system_blocks {
	struct rb_root root;
	struct rcu_head rcu;
};

207 208 209 210 211
/*
 * Flags for ext4_io_end->flags
 */
#define	EXT4_IO_END_UNWRITTEN	0x0001

212 213 214 215 216 217
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 */
};

218
/*
219
 * For converting unwritten extents on a work queue. 'handle' is used for
220
 * buffered writeback.
221
 */
222
typedef struct ext4_io_end {
223
	struct list_head	list;		/* per-file finished IO list */
224 225
	handle_t		*handle;	/* handle reserved for extent
						 * conversion */
226
	struct inode		*inode;		/* file being written to */
227 228
	struct bio		*bio;		/* Linked list of completed
						 * bios covering the extent */
229
	unsigned int		flag;		/* unwritten or not */
J
Jan Kara 已提交
230
	atomic_t		count;		/* reference counter */
231
	struct list_head	list_vec;	/* list of ext4_io_end_vec */
232 233
} ext4_io_end_t;

234
struct ext4_io_submit {
235
	struct writeback_control *io_wbc;
236 237 238 239 240
	struct bio		*io_bio;
	ext4_io_end_t		*io_end;
	sector_t		io_next_block;
};

241 242 243
/*
 * Special inodes numbers
 */
244 245
#define	EXT4_BAD_INO		 1	/* Bad blocks inode */
#define EXT4_ROOT_INO		 2	/* Root inode */
246 247
#define EXT4_USR_QUOTA_INO	 3	/* User quota inode */
#define EXT4_GRP_QUOTA_INO	 4	/* Group quota inode */
248 249 250 251
#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 */
252

253 254
/* First non-reserved inode for old ext4 filesystems */
#define EXT4_GOOD_OLD_FIRST_INO	11
255 256 257 258

/*
 * Maximal count of links to a file
 */
259
#define EXT4_LINK_MAX		65000
260 261 262 263

/*
 * Macro-instructions used to manage several block sizes
 */
264
#define EXT4_MIN_BLOCK_SIZE		1024
265 266
#define	EXT4_MAX_BLOCK_SIZE		65536
#define EXT4_MIN_BLOCK_LOG_SIZE		10
267
#define EXT4_MAX_BLOCK_LOG_SIZE		16
268
#define EXT4_MAX_CLUSTER_LOG_SIZE	30
269
#ifdef __KERNEL__
270
# define EXT4_BLOCK_SIZE(s)		((s)->s_blocksize)
271
#else
272
# define EXT4_BLOCK_SIZE(s)		(EXT4_MIN_BLOCK_SIZE << (s)->s_log_block_size)
273
#endif
274
#define	EXT4_ADDR_PER_BLOCK(s)		(EXT4_BLOCK_SIZE(s) / sizeof(__u32))
275 276
#define EXT4_CLUSTER_SIZE(s)		(EXT4_BLOCK_SIZE(s) << \
					 EXT4_SB(s)->s_cluster_bits)
277
#ifdef __KERNEL__
278
# define EXT4_BLOCK_SIZE_BITS(s)	((s)->s_blocksize_bits)
279
# define EXT4_CLUSTER_BITS(s)		(EXT4_SB(s)->s_cluster_bits)
280
#else
281
# define EXT4_BLOCK_SIZE_BITS(s)	((s)->s_log_block_size + 10)
282 283
#endif
#ifdef __KERNEL__
284 285 286
#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)
287
#else
288 289
#define EXT4_INODE_SIZE(s)	(((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \
				 EXT4_GOOD_OLD_INODE_SIZE : \
290
				 (s)->s_inode_size)
291 292
#define EXT4_FIRST_INO(s)	(((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \
				 EXT4_GOOD_OLD_FIRST_INO : \
293 294
				 (s)->s_first_ino)
#endif
A
Amit Arora 已提交
295
#define EXT4_BLOCK_ALIGN(size, blkbits)		ALIGN((size), (1 << (blkbits)))
296 297 298
#define EXT4_MAX_BLOCKS(size, offset, blkbits) \
	((EXT4_BLOCK_ALIGN(size + offset, blkbits) >> blkbits) - (offset >> \
								  blkbits))
299

300 301 302 303 304 305 306
/* 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)
307 308 309 310 311
/* 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))
312 313 314
/* 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))
315 316 317 318 319
/* 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))
320

321 322 323
/*
 * Structure of a blocks group descriptor
 */
324
struct ext4_group_desc
325
{
326
	__le32	bg_block_bitmap_lo;	/* Blocks bitmap block */
327 328
	__le32	bg_inode_bitmap_lo;	/* Inodes bitmap block */
	__le32	bg_inode_table_lo;	/* Inodes table block */
329 330 331
	__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
332
	__le16	bg_flags;		/* EXT4_BG_flags (INODE_UNINIT, etc) */
333 334 335
	__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 */
336
	__le16  bg_itable_unused_lo;	/* Unused inodes count */
A
Andreas Dilger 已提交
337
	__le16  bg_checksum;		/* crc16(sb_uuid+group+desc) */
338 339 340
	__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 */
341 342 343
	__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 */
344
	__le16  bg_itable_unused_hi;    /* Unused inodes count MSB */
345 346 347 348
	__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;
349 350
};

351 352 353 354 355 356 357
#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))

358 359 360 361 362
/*
 * Structure of a flex block group info
 */

struct flex_groups {
363 364 365
	atomic64_t	free_clusters;
	atomic_t	free_inodes;
	atomic_t	used_dirs;
366 367
};

A
Andreas Dilger 已提交
368 369 370 371
#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 */

372 373 374
/*
 * Macro-instructions used to manage group descriptors
 */
375
#define EXT4_MIN_DESC_SIZE		32
376
#define EXT4_MIN_DESC_SIZE_64BIT	64
377 378
#define	EXT4_MAX_DESC_SIZE		EXT4_MIN_BLOCK_SIZE
#define EXT4_DESC_SIZE(s)		(EXT4_SB(s)->s_desc_size)
379
#ifdef __KERNEL__
380
# define EXT4_BLOCKS_PER_GROUP(s)	(EXT4_SB(s)->s_blocks_per_group)
381
# define EXT4_CLUSTERS_PER_GROUP(s)	(EXT4_SB(s)->s_clusters_per_group)
382 383 384
# 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)
385
#else
386
# define EXT4_BLOCKS_PER_GROUP(s)	((s)->s_blocks_per_group)
387
# define EXT4_DESC_PER_BLOCK(s)		(EXT4_BLOCK_SIZE(s) / EXT4_DESC_SIZE(s))
388
# define EXT4_INODES_PER_GROUP(s)	((s)->s_inodes_per_group)
389 390 391 392 393
#endif

/*
 * Constants relative to the data blocks
 */
394 395 396 397 398
#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)
399 400 401 402

/*
 * Inode flags
 */
403 404 405 406 407 408 409 410
#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 */
411
/* Reserved for compression usage... */
412 413 414
#define EXT4_DIRTY_FL			0x00000100
#define EXT4_COMPRBLK_FL		0x00000200 /* One or more compressed clusters */
#define EXT4_NOCOMPR_FL			0x00000400 /* Don't compress */
415 416
	/* nb: was previously EXT2_ECOMPR_FL */
#define EXT4_ENCRYPT_FL			0x00000800 /* encrypted file */
417
/* End compression flags --- maybe not all used */
418 419 420 421 422 423
#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
424
#define EXT4_HUGE_FILE_FL               0x00040000 /* Set to each huge file */
A
Alex Tomas 已提交
425
#define EXT4_EXTENTS_FL			0x00080000 /* Inode uses extents */
E
Eric Biggers 已提交
426
#define EXT4_VERITY_FL			0x00100000 /* Verity protected inode */
427
#define EXT4_EA_INODE_FL	        0x00200000 /* Inode used for large EA */
428
/* 0x00400000 was formerly EXT4_EOFBLOCKS_FL */
I
Ira Weiny 已提交
429 430 431

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

432
#define EXT4_INLINE_DATA_FL		0x10000000 /* Inode has inline data. */
433
#define EXT4_PROJINHERIT_FL		0x20000000 /* Create with parents projid */
434
#define EXT4_CASEFOLD_FL		0x40000000 /* Casefolded directory */
A
Aneesh Kumar K.V 已提交
435
#define EXT4_RESERVED_FL		0x80000000 /* reserved for ext4 lib */
436

437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464
/* 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)
465

466
/* Flags we can manipulate with through FS_IOC_FSSETXATTR */
467 468 469 470 471
#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
472 473
					 EXT4_PROJINHERIT_FL | \
					 EXT4_DAX_FL)
474

475 476
/* Flags that should be inherited by new inodes from their parent. */
#define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\
477
			   EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
478
			   EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\
L
Li Xi 已提交
479
			   EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL |\
I
Ira Weiny 已提交
480 481
			   EXT4_PROJINHERIT_FL | EXT4_CASEFOLD_FL |\
			   EXT4_DAX_FL)
482

483
/* Flags that are appropriate for regular files (all but dir-specific ones). */
484 485
#define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL | EXT4_CASEFOLD_FL |\
			   EXT4_PROJINHERIT_FL))
486 487 488 489

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

Y
yangerkun 已提交
490 491 492
/* 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
493 494 495 496
/* Flags which are mutually exclusive to DAX */
#define EXT4_DAX_MUT_EXCL (EXT4_VERITY_FL | EXT4_ENCRYPT_FL |\
			   EXT4_JOURNAL_DATA_FL)

497 498 499 500 501 502 503 504 505 506 507
/* 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;
}

508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523
/*
 * 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 */
524
	EXT4_INODE_ENCRYPT	= 11,	/* Encrypted file */
525 526 527 528 529 530 531 532 533
/* 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
534
	EXT4_INODE_VERITY	= 20,	/* Verity protected inode */
535
	EXT4_INODE_EA_INODE	= 21,	/* Inode used for large EA */
536
/* 22 was formerly EXT4_INODE_EOFBLOCKS */
I
Ira Weiny 已提交
537
	EXT4_INODE_DAX		= 25,	/* Inode is DAX */
538
	EXT4_INODE_INLINE_DATA	= 28,	/* Data in inode. */
539
	EXT4_INODE_PROJINHERIT	= 29,	/* Create with parents projid */
540
	EXT4_INODE_CASEFOLD	= 30,	/* Casefolded directory */
541 542 543 544
	EXT4_INODE_RESERVED	= 31,	/* reserved for ext4 lib */
};

/*
545 546 547 548 549 550 551 552 553
 * 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.
554 555 556
 *
 * It's not paranoia if the Murphy's Law really *is* out to get you.  :-)
 */
557 558 559
#define TEST_FLAG_VALUE(FLAG) (EXT4_##FLAG##_FL == (1 << EXT4_INODE_##FLAG))
#define CHECK_FLAG_VALUE(FLAG) BUILD_BUG_ON(!TEST_FLAG_VALUE(FLAG))

560 561 562 563 564 565 566 567 568 569 570 571 572
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);
573
	CHECK_FLAG_VALUE(ENCRYPT);
574 575 576 577 578 579 580 581
	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
582
	CHECK_FLAG_VALUE(VERITY);
583
	CHECK_FLAG_VALUE(EA_INODE);
584
	CHECK_FLAG_VALUE(INLINE_DATA);
585
	CHECK_FLAG_VALUE(PROJINHERIT);
586
	CHECK_FLAG_VALUE(CASEFOLD);
587 588 589
	CHECK_FLAG_VALUE(RESERVED);
}

590
/* Used to pass group descriptor data when online resize is done */
591
struct ext4_new_group_input {
D
Dave Kleikamp 已提交
592 593 594 595 596 597
	__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 */
598 599 600
	__u16 unused;
};

601 602 603 604 605 606 607 608 609 610 611 612
#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

613 614
/* The struct ext4_new_group_input in kernel space, with free_blocks_count */
struct ext4_new_group_data {
615
	__u32 group;
L
Laurent Vivier 已提交
616 617 618
	__u64 block_bitmap;
	__u64 inode_bitmap;
	__u64 inode_table;
619 620
	__u32 blocks_count;
	__u16 reserved_blocks;
621 622
	__u16 mdata_blocks;
	__u32 free_clusters_count;
623 624
};

625 626 627 628 629 630 631 632
/* 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
633
/*
634
 * Flags used by ext4_map_blocks()
A
Amit Arora 已提交
635
 */
636
	/* Allocate any needed blocks and/or convert an unwritten
637
	   extent to be an initialized ext4 */
638
#define EXT4_GET_BLOCKS_CREATE			0x0001
639 640 641
	/* 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|\
642
						 EXT4_GET_BLOCKS_CREATE)
L
Lukas Czerner 已提交
643 644
	/* Caller is from the delayed allocation writeout path
	 * finally doing the actual allocation of delayed blocks */
645
#define EXT4_GET_BLOCKS_DELALLOC_RESERVE	0x0004
646
	/* caller is from the direct IO path, request to creation of an
647
	unwritten extents if not allocated, split the unwritten
648
	extent if blocks has been preallocated already*/
649
#define EXT4_GET_BLOCKS_PRE_IO			0x0008
650
#define EXT4_GET_BLOCKS_CONVERT			0x0010
651
#define EXT4_GET_BLOCKS_IO_CREATE_EXT		(EXT4_GET_BLOCKS_PRE_IO|\
652
					 EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT)
653 654
	/* Convert extent to initialized after IO complete */
#define EXT4_GET_BLOCKS_IO_CONVERT_EXT		(EXT4_GET_BLOCKS_CONVERT|\
655
					 EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT)
L
Lukas Czerner 已提交
656 657 658
	/* 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
659 660
	/* Don't normalize allocation size (used for fallocate) */
#define EXT4_GET_BLOCKS_NO_NORMALIZE		0x0040
661
	/* Convert written extents to unwritten */
662
#define EXT4_GET_BLOCKS_CONVERT_UNWRITTEN	0x0100
663 664 665 666
	/* 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)
667 668 669
	/* Caller will submit data before dropping transaction handle. This
	 * allows jbd2 to avoid submitting data before commit. */
#define EXT4_GET_BLOCKS_IO_SUBMIT		0x0400
670

671
/*
672
 * The bit position of these flags must not overlap with any of the
673
 * EXT4_GET_BLOCKS_*.  They are used by ext4_find_extent(),
674
 * read_extent_tree_block(), ext4_split_extent_at(),
675 676 677 678
 * 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.
679
 */
680 681
#define EXT4_EX_NOCACHE				0x40000000
#define EXT4_EX_FORCE_CACHE			0x20000000
682
#define EXT4_EX_NOFAIL				0x10000000
683

684 685 686
/*
 * Flags used by ext4_free_blocks
 */
687 688 689 690
#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
691 692
#define EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER	0x0010
#define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER	0x0020
693
#define EXT4_FREE_BLOCKS_RERESERVE_CLUSTER      0x0040
694

695 696 697
/*
 * ioctl commands
 */
698 699 700 701 702 703
#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
704 705 706
#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)
707
 /* note ioctl 10 reserved for an early version of the FIEMAP ioctl */
T
Theodore Ts'o 已提交
708
 /* note ioctl 11 reserved for filesystem-independent FIEMAP ioctl */
709
#define EXT4_IOC_ALLOC_DA_BLKS		_IO('f', 12)
710
#define EXT4_IOC_MOVE_EXT		_IOWR('f', 15, struct move_extent)
711
#define EXT4_IOC_RESIZE_FS		_IOW('f', 16, __u64)
712
#define EXT4_IOC_SWAP_BOOT		_IO('f', 17)
713
#define EXT4_IOC_PRECACHE_EXTENTS	_IO('f', 18)
714 715
/* ioctl codes 19--39 are reserved for fscrypt */
#define EXT4_IOC_CLEAR_ES_CACHE		_IO('f', 40)
716
#define EXT4_IOC_GETSTATE		_IOW('f', 41, __u32)
717
#define EXT4_IOC_GET_ES_CACHE		_IOWR('f', 42, struct fiemap)
718

719
#define EXT4_IOC_SHUTDOWN _IOR ('X', 125, __u32)
720 721 722 723 724 725 726 727

/*
 * 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 */

728 729 730 731 732 733 734 735 736 737
/*
 * 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
738

739
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
740 741 742
/*
 * ioctl commands in 32 bit emulation
 */
743 744 745 746 747
#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)
748
#define EXT4_IOC32_GROUP_ADD		_IOW('f', 8, struct compat_ext4_new_group_input)
749 750
#define EXT4_IOC32_GETVERSION_OLD	FS_IOC32_GETVERSION
#define EXT4_IOC32_SETVERSION_OLD	FS_IOC32_SETVERSION
751
#endif
752

753 754 755 756 757 758
/*
 * 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

759
/* Max physical block we can address w/o extents */
760 761
#define EXT4_MAX_BLOCK_FILE_PHYS	0xFFFFFFFF

762
/* Max logical block we can support */
763
#define EXT4_MAX_LOGICAL_BLOCK		0xFFFFFFFE
764

765 766 767
/*
 * Structure of an inode on the disk
 */
768
struct ext4_inode {
769 770
	__le16	i_mode;		/* File mode */
	__le16	i_uid;		/* Low 16 bits of Owner Uid */
771
	__le32	i_size_lo;	/* Size in bytes */
772
	__le32	i_atime;	/* Access time */
K
Kalpak Shah 已提交
773
	__le32	i_ctime;	/* Inode Change time */
774 775 776 777
	__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 */
778
	__le32	i_blocks_lo;	/* Blocks count */
779 780 781
	__le32	i_flags;	/* File flags */
	union {
		struct {
782
			__le32  l_i_version;
783 784 785 786 787 788 789 790
		} linux1;
		struct {
			__u32  h_i_translator;
		} hurd1;
		struct {
			__u32  m_i_reserved1;
		} masix1;
	} osd1;				/* OS dependent 1 */
791
	__le32	i_block[EXT4_N_BLOCKS];/* Pointers to blocks */
792
	__le32	i_generation;	/* File version (for NFS) */
793
	__le32	i_file_acl_lo;	/* File ACL */
794
	__le32	i_size_high;
795
	__le32	i_obso_faddr;	/* Obsoleted fragment address */
796 797
	union {
		struct {
798
			__le16	l_i_blocks_high; /* were l_i_reserved1 */
B
Badari Pulavarty 已提交
799
			__le16	l_i_file_acl_high;
D
Dave Kleikamp 已提交
800
			__le16	l_i_uid_high;	/* these 2 fields */
801
			__le16	l_i_gid_high;	/* were reserved2[0] */
802 803
			__le16	l_i_checksum_lo;/* crc32c(uuid+inum+inode) LE */
			__le16	l_i_reserved;
804 805
		} linux2;
		struct {
806
			__le16	h_i_reserved1;	/* Obsoleted fragment number/size which are removed in ext4 */
807 808 809 810 811 812
			__u16	h_i_mode_high;
			__u16	h_i_uid_high;
			__u16	h_i_gid_high;
			__u32	h_i_author;
		} hurd2;
		struct {
813
			__le16	h_i_reserved1;	/* Obsoleted fragment number/size which are removed in ext4 */
B
Badari Pulavarty 已提交
814
			__le16	m_i_file_acl_high;
815 816 817 818
			__u32	m_i_reserved2[2];
		} masix2;
	} osd2;				/* OS dependent 2 */
	__le16	i_extra_isize;
819
	__le16	i_checksum_hi;	/* crc32c(uuid+inum+inode) BE */
K
Kalpak Shah 已提交
820 821 822 823 824
	__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) */
825
	__le32  i_version_hi;	/* high 32 bits for 64-bit version */
826
	__le32	i_projid;	/* Project ID */
827 828
};

829 830 831 832 833 834 835 836
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 */
};
837

K
Kalpak Shah 已提交
838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857
#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))			\

858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878
/*
 * 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.
 */

879
static inline __le32 ext4_encode_extra_time(struct timespec64 *time)
K
Kalpak Shah 已提交
880
{
881
	u32 extra =((time->tv_sec - (s32)time->tv_sec) >> 32) & EXT4_EPOCH_MASK;
882
	return cpu_to_le32(extra | (time->tv_nsec << EXT4_EPOCH_BITS));
K
Kalpak Shah 已提交
883 884
}

885 886
static inline void ext4_decode_extra_time(struct timespec64 *time,
					  __le32 extra)
K
Kalpak Shah 已提交
887
{
888
	if (unlikely(extra & cpu_to_le32(EXT4_EPOCH_MASK)))
889 890
		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
891 892
}

893 894 895
#define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode)				\
do {										\
	if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra))     {\
896
		(raw_inode)->xtime = cpu_to_le32((inode)->xtime.tv_sec);	\
897
		(raw_inode)->xtime ## _extra =					\
898
				ext4_encode_extra_time(&(inode)->xtime);	\
899
		}								\
900
	else	\
901
		(raw_inode)->xtime = cpu_to_le32(clamp_t(int32_t, (inode)->xtime.tv_sec, S32_MIN, S32_MAX));	\
K
Kalpak Shah 已提交
902 903 904 905 906 907 908 909 910 911 912
} 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)

913 914 915 916
#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)) {	\
917
		ext4_decode_extra_time(&(inode)->xtime,				\
918 919 920 921
				       raw_inode->xtime ## _extra);		\
		}								\
	else									\
		(inode)->xtime.tv_nsec = 0;					\
K
Kalpak Shah 已提交
922 923
} while (0)

924

K
Kalpak Shah 已提交
925 926 927 928 929
#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);	       \
930 931
	else								       \
		(einode)->xtime.tv_sec = 0;				       \
K
Kalpak Shah 已提交
932 933 934
	if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra))	       \
		ext4_decode_extra_time(&(einode)->xtime,		       \
				       raw_inode->xtime ## _extra);	       \
935 936
	else								       \
		(einode)->xtime.tv_nsec = 0;				       \
K
Kalpak Shah 已提交
937 938
} while (0)

939 940
#define i_disk_version osd1.linux1.l_i_version

941 942
#if defined(__KERNEL__) || defined(__linux__)
#define i_reserved1	osd1.linux1.l_i_reserved1
B
Badari Pulavarty 已提交
943
#define i_file_acl_high	osd2.linux2.l_i_file_acl_high
944
#define i_blocks_high	osd2.linux2.l_i_blocks_high
945 946 947 948
#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
949
#define i_checksum_lo	osd2.linux2.l_i_checksum_lo
950 951 952 953 954 955 956 957 958 959 960

#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
961
#define i_file_acl_high	osd2.masix2.m_i_file_acl_high
962 963 964 965
#define i_reserved2	osd2.masix2.m_i_reserved2

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

966 967
#include "extents_status.h"

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 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 1049 1050 1051

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

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

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

	/*
	 * i_data_sem is for serialising ext4_truncate() against
	 * ext4_getblock().  In the 2.4 ext2 design, great chunks of inode's
	 * data tree are chopped off during truncate. We can't do that in
	 * ext4 because whenever we perform intermediate commits during
	 * truncate, the inode and all the metadata blocks *must* be in a
	 * consistent state which allows truncation of the orphans to restart
	 * during recovery.  Hence we must fix the get_block-vs-truncate race
	 * by other means, so we have i_data_sem.
	 */
	struct rw_semaphore i_data_sem;
1052 1053 1054 1055 1056 1057 1058 1059 1060
	/*
	 * 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;
1061
	struct inode vfs_inode;
1062
	struct jbd2_inode *jinode;
1063

1064 1065
	spinlock_t i_raw_lock;	/* protects updates to the raw inode */

1066 1067
	/*
	 * File creation time. Its function is same as that of
1068
	 * struct timespec64 i_{a,c,m}time in the generic inode.
1069
	 */
1070
	struct timespec64 i_crtime;
1071 1072 1073 1074 1075

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

1076 1077 1078
	/* extents status tree */
	struct ext4_es_tree i_es_tree;
	rwlock_t i_es_lock;
1079
	struct list_head i_es_list;
1080
	unsigned int i_es_all_nr;	/* protected by i_es_lock */
1081
	unsigned int i_es_shk_nr;	/* protected by i_es_lock */
1082 1083 1084
	ext4_lblk_t i_es_shrink_lblk;	/* Offset where we start searching for
					   extents to shrink. Protected by
					   i_es_lock  */
1085

1086 1087 1088 1089
	/* ialloc */
	ext4_group_t	i_last_alloc_group;

	/* allocation reservation info for delalloc */
1090
	/* In case of bigalloc, this refer to clusters rather than blocks */
1091 1092
	unsigned int i_reserved_data_blocks;

1093 1094 1095
	/* pending cluster reservations for bigalloc file systems */
	struct ext4_pending_tree i_pending_tree;

1096 1097 1098
	/* on-disk additional length */
	__u16 i_extra_isize;

1099 1100 1101 1102
	/* Indicate the inline data space. */
	u16 i_inline_off;
	u16 i_inline_size;

1103 1104 1105 1106
#ifdef CONFIG_QUOTA
	/* quota space reservation, managed internally by quota code */
	qsize_t i_reserved_quota;
#endif
1107

1108
	/* Lock protecting lists below */
1109
	spinlock_t i_completed_io_lock;
1110 1111 1112 1113 1114 1115
	/*
	 * 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
1116
	atomic_t i_unwritten; /* Nr. of inflight conversions pending */
1117 1118

	spinlock_t i_block_reservation_lock;
1119 1120 1121 1122 1123 1124 1125

	/*
	 * Transactions that contain inode's metadata needed to complete
	 * fsync and fdatasync, respectively.
	 */
	tid_t i_sync_tid;
	tid_t i_datasync_tid;
1126

J
Jan Kara 已提交
1127 1128 1129 1130
#ifdef CONFIG_QUOTA
	struct dquot *i_dquot[MAXQUOTAS];
#endif

1131 1132
	/* Precomputed uuid+inum+igen checksum for seeding inode checksums */
	__u32 i_csum_seed;
1133

L
Li Xi 已提交
1134
	kprojid_t i_projid;
1135 1136
};

1137 1138 1139
/*
 * File system states
 */
1140 1141 1142
#define	EXT4_VALID_FS			0x0001	/* Unmounted cleanly */
#define	EXT4_ERROR_FS			0x0002	/* Errors detected */
#define	EXT4_ORPHAN_FS			0x0004	/* Orphans being recovered */
1143

1144 1145 1146 1147 1148 1149 1150
/*
 * 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 */

1151
/*
1152
 * Mount flags set via mount options or defaults
1153
 */
1154
#define EXT4_MOUNT_NO_MBCACHE		0x00001 /* Do not use mbcache */
1155 1156 1157 1158 1159
#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 */
1160
#define EXT4_MOUNT_ERRORS_MASK		0x00070
1161 1162
#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
1163
#ifdef CONFIG_FS_DAX
1164
#define EXT4_MOUNT_DAX_ALWAYS		0x00200	/* Direct Access */
R
Ross Zwisler 已提交
1165
#else
1166
#define EXT4_MOUNT_DAX_ALWAYS		0
R
Ross Zwisler 已提交
1167
#endif
1168 1169 1170 1171 1172 1173 1174 1175
#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 */
1176
#define EXT4_MOUNT_NO_AUTO_DA_ALLOC	0x10000	/* No auto delalloc mapping */
1177
#define EXT4_MOUNT_BARRIER		0x20000 /* Use block barriers */
1178 1179 1180 1181 1182 1183 1184 1185 1186
#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 */
1187
#define EXT4_MOUNT_DIOREAD_NOLOCK	0x400000 /* Enable support for dio read nolocking */
1188
#define EXT4_MOUNT_JOURNAL_CHECKSUM	0x800000 /* Journal checksums */
1189
#define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT	0x1000000 /* Journal Async Commit */
1190
#define EXT4_MOUNT_WARN_ON_ERROR	0x2000000 /* Trigger WARN_ON on error */
1191
#define EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS 0x4000000
1192
#define EXT4_MOUNT_DELALLOC		0x8000000 /* Delalloc support */
1193
#define EXT4_MOUNT_DATA_ERR_ABORT	0x10000000 /* Abort on file data write */
1194
#define EXT4_MOUNT_BLOCK_VALIDITY	0x20000000 /* Block validity checking */
1195
#define EXT4_MOUNT_DISCARD		0x40000000 /* Issue DISCARD requests */
1196
#define EXT4_MOUNT_INIT_INODE_TABLE	0x80000000 /* Initialize uninitialized itables */
1197

1198 1199 1200 1201 1202
/*
 * 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.
 */
1203 1204
#define EXT4_MOUNT2_EXPLICIT_DELALLOC	0x00000001 /* User explicitly
						      specified delalloc */
1205 1206 1207
#define EXT4_MOUNT2_STD_GROUP_SIZE	0x00000002 /* We have standard group
						      size of blocksize * 8
						      blocks */
1208 1209
#define EXT4_MOUNT2_HURD_COMPAT		0x00000004 /* Support HURD-castrated
						      file systems */
1210 1211
#define EXT4_MOUNT2_DAX_NEVER		0x00000008 /* Do not allow Direct Access */
#define EXT4_MOUNT2_DAX_INODE		0x00000010 /* For printing options only */
1212

1213 1214 1215
#define EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM	0x00000008 /* User explicitly
						specified journal checksum */

1216 1217 1218 1219
#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
1220 1221
#define test_opt(sb, opt)		(EXT4_SB(sb)->s_mount_opt & \
					 EXT4_MOUNT_##opt)
1222

1223 1224 1225 1226 1227 1228 1229
#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)

1230 1231
#define ext4_test_and_set_bit		__test_and_set_bit_le
#define ext4_set_bit			__set_bit_le
1232
#define ext4_set_bit_atomic		ext2_set_bit_atomic
1233 1234
#define ext4_test_and_clear_bit		__test_and_clear_bit_le
#define ext4_clear_bit			__clear_bit_le
1235
#define ext4_clear_bit_atomic		ext2_clear_bit_atomic
A
Akinobu Mita 已提交
1236 1237 1238
#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
1239

1240 1241
extern void ext4_set_bits(void *bm, int cur, int len);

1242 1243 1244
/*
 * Maximal mount counts between two filesystem checks
 */
1245 1246
#define EXT4_DFL_MAX_MNT_COUNT		20	/* Allow 20 mounts */
#define EXT4_DFL_CHECKINTERVAL		0	/* Don't use interval check */
1247 1248 1249 1250

/*
 * Behaviour when detecting errors
 */
1251 1252 1253 1254
#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
1255

1256 1257 1258
/* Metadata checksum algorithm codes */
#define EXT4_CRC32C_CHKSUM		1

1259 1260 1261
/*
 * Structure of the super block
 */
1262
struct ext4_super_block {
1263
/*00*/	__le32	s_inodes_count;		/* Inodes count */
1264
	__le32	s_blocks_count_lo;	/* Blocks count */
1265 1266
	__le32	s_r_blocks_count_lo;	/* Reserved blocks count */
	__le32	s_free_blocks_count_lo;	/* Free blocks count */
1267 1268 1269
/*10*/	__le32	s_free_inodes_count;	/* Free inodes count */
	__le32	s_first_data_block;	/* First Data Block */
	__le32	s_log_block_size;	/* Block size */
1270
	__le32	s_log_cluster_size;	/* Allocation cluster size */
1271
/*20*/	__le32	s_blocks_per_group;	/* # Blocks per group */
1272
	__le32	s_clusters_per_group;	/* # Clusters per group */
1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288
	__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 */
	/*
1289
	 * These fields are for EXT4_DYNAMIC_REV superblocks only.
1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301
	 *
	 * 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 */
1302
	__le16  s_inode_size;		/* size of inode structure */
1303 1304 1305 1306 1307 1308
	__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 */
1309
/*88*/	char	s_last_mounted[64] __nonstring;	/* directory where last mounted */
1310 1311 1312
/*C8*/	__le32	s_algorithm_usage_bitmap; /* For compression */
	/*
	 * Performance hints.  Directory preallocation should only
1313
	 * happen if the EXT4_FEATURE_COMPAT_DIR_PREALLOC flag is on.
1314 1315 1316 1317 1318
	 */
	__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 */
	/*
1319
	 * Journaling support valid if EXT4_FEATURE_COMPAT_HAS_JOURNAL set.
1320 1321 1322 1323 1324 1325 1326
	 */
/*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 */
1327
	__u8	s_jnl_backup_type;
1328
	__le16  s_desc_size;		/* size of group descriptor */
L
Laurent Vivier 已提交
1329
/*100*/	__le32	s_default_mount_opts;
1330
	__le32	s_first_meta_bg;	/* First metablock block group */
L
Laurent Vivier 已提交
1331 1332 1333 1334 1335 1336
	__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
1337 1338 1339 1340
	__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 */
1341
	__le16  s_mmp_update_interval;  /* # seconds to wait in MMP checking */
A
Aneesh Kumar K.V 已提交
1342 1343
	__le64  s_mmp_block;            /* Block for multi-mount protection */
	__le32  s_raid_stripe_width;    /* blocks on all data disks (N*stride)*/
1344
	__u8	s_log_groups_per_flex;  /* FLEX_BG group size */
1345
	__u8	s_checksum_type;	/* metadata checksum algorithm used */
1346 1347
	__u8	s_encryption_level;	/* versioning level for encryption */
	__u8	s_reserved_pad;		/* Padding to next 32bits */
T
Theodore Ts'o 已提交
1348
	__le64	s_kbytes_written;	/* nr of lifetime kilobytes written */
1349 1350 1351 1352 1353 1354
	__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 */
1355 1356 1357 1358 1359
#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 */
1360
	__u8	s_first_error_func[32] __nonstring;	/* function where the error happened */
1361 1362 1363 1364 1365
	__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 */
1366
	__u8	s_last_error_func[32] __nonstring;	/* function where the error happened */
1367 1368
#define EXT4_S_ERR_END offsetof(struct ext4_super_block, s_mount_opts)
	__u8	s_mount_opts[64];
1369 1370 1371
	__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 */
1372
	__le32	s_backup_bgs[2];	/* groups with sparse_super2 SBs */
1373
	__u8	s_encrypt_algos[4];	/* Encryption algorithms in use  */
1374 1375
	__u8	s_encrypt_pw_salt[16];	/* Salt used for string2key algorithm */
	__le32	s_lpf_ino;		/* Location of the lost+found inode */
1376
	__le32	s_prj_quota_inum;	/* inode for tracking project quota */
1377
	__le32	s_checksum_seed;	/* crc32c(uuid) if csum_seed set */
1378 1379 1380 1381 1382 1383
	__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;
1384 1385
	__u8	s_first_error_errcode;
	__u8    s_last_error_errcode;
1386 1387 1388
	__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 */
1389
	__le32	s_checksum;		/* crc32c(superblock) */
1390 1391
};

1392 1393
#define EXT4_S_ERR_LEN (EXT4_S_ERR_END - EXT4_S_ERR_START)

1394
#ifdef __KERNEL__
1395 1396

/*
1397
 * run-time mount flags
1398
 */
1399 1400 1401
#define EXT4_MF_MNTDIR_SAMPLED		0x0001
#define EXT4_MF_FS_ABORTED		0x0002	/* Fatal error detected */

1402
#ifdef CONFIG_FS_ENCRYPTION
1403
#define DUMMY_ENCRYPTION_ENABLED(sbi) ((sbi)->s_dummy_enc_ctx.ctx != NULL)
1404 1405 1406
#else
#define DUMMY_ENCRYPTION_ENABLED(sbi) (0)
#endif
1407

J
Jan Kara 已提交
1408
/* Number of quota types we support */
L
Li Xi 已提交
1409
#define EXT4_MAXQUOTAS 3
J
Jan Kara 已提交
1410

1411 1412 1413 1414 1415 1416 1417 1418 1419 1420
#define EXT4_ENC_UTF8_12_1	1

/*
 * Flags for ext4_sb_info.s_encoding_flags.
 */
#define EXT4_ENC_STRICT_MODE_FL	(1 << 0)

#define ext4_has_strict_mode(sbi) \
	(sbi->s_encoding_flags & EXT4_ENC_STRICT_MODE_FL)

1421 1422 1423 1424 1425 1426 1427
/*
 * 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 */
1428
	unsigned long s_clusters_per_group; /* Number of clusters in a group */
1429 1430 1431 1432 1433
	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 */
1434
	ext4_group_t s_blockfile_groups;/* Groups acceptable for non-extent files */
1435
	unsigned long s_overhead;  /* # of fs overhead clusters */
1436 1437
	unsigned int s_cluster_ratio;	/* Number of blocks per cluster */
	unsigned int s_cluster_bits;	/* log2 of s_cluster_ratio */
1438 1439 1440
	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 */
1441
	struct buffer_head * __rcu *s_group_desc;
1442
	unsigned int s_mount_opt;
1443
	unsigned int s_mount_opt2;
1444
	unsigned int s_mount_flags;
1445
	unsigned int s_def_mount_opt;
1446
	ext4_fsblk_t s_sb_block;
L
Lukas Czerner 已提交
1447
	atomic64_t s_resv_clusters;
1448 1449
	kuid_t s_resuid;
	kgid_t s_resgid;
1450 1451 1452 1453 1454 1455 1456
	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;
1457
	unsigned int s_inode_goal;
1458 1459 1460
	u32 s_hash_seed[4];
	int s_def_hash_version;
	int s_hash_unsigned;	/* 3 if hash should be signed, 0 if not */
1461
	struct percpu_counter s_freeclusters_counter;
1462 1463
	struct percpu_counter s_freeinodes_counter;
	struct percpu_counter s_dirs_counter;
1464
	struct percpu_counter s_dirtyclusters_counter;
1465 1466 1467 1468
	struct blockgroup_lock *s_blockgroup_lock;
	struct proc_dir_entry *s_proc;
	struct kobject s_kobj;
	struct completion s_kobj_unregister;
1469
	struct super_block *s_sb;
1470 1471 1472 1473
#ifdef CONFIG_UNICODE
	struct unicode_map *s_encoding;
	__u16 s_encoding_flags;
#endif
1474 1475 1476 1477 1478

	/* Journaling */
	struct journal_s *s_journal;
	struct list_head s_orphan;
	struct mutex s_orphan_lock;
1479
	unsigned long s_ext4_flags;		/* Ext4 superblock flags */
1480 1481 1482 1483 1484
	unsigned long s_commit_interval;
	u32 s_max_batch_time;
	u32 s_min_batch_time;
	struct block_device *journal_bdev;
#ifdef CONFIG_QUOTA
1485 1486
	/* Names of quota files with journalled quota */
	char __rcu *s_qf_names[EXT4_MAXQUOTAS];
1487 1488 1489
	int s_jquota_fmt;			/* Format of quota to use */
#endif
	unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */
1490
	struct ext4_system_blocks __rcu *system_blks;
1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502

#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 */
1503
	struct ext4_group_info ** __rcu *s_group_info;
1504 1505 1506 1507
	struct inode *s_buddy_cache;
	spinlock_t s_md_lock;
	unsigned short *s_mb_offsets;
	unsigned int *s_mb_maxs;
1508
	unsigned int s_group_info_size;
1509
	unsigned int s_mb_free_pending;
1510 1511
	struct list_head s_freed_data_list;	/* List of blocks to be freed
						   after commit completed */
1512 1513 1514 1515 1516 1517 1518 1519 1520

	/* 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;
1521
	unsigned int s_max_dir_size_kb;
1522 1523 1524
	/* where last allocation was done - for stream allocation */
	unsigned long s_mb_last_group;
	unsigned long s_mb_last_start;
1525 1526
	unsigned int s_mb_prefetch;
	unsigned int s_mb_prefetch_limit;
1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541

	/* 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;
1542
	atomic_t s_lock_busy;
1543 1544

	/* locality groups */
1545
	struct ext4_locality_group __percpu *s_locality_groups;
1546 1547 1548 1549 1550

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

1551 1552 1553
	/* the size of zero-out chunk */
	unsigned int s_extent_max_zeroout_kb;

1554
	unsigned int s_log_groups_per_flex;
1555
	struct flex_groups * __rcu *s_flex_groups;
1556
	ext4_group_t s_flex_groups_allocated;
1557

1558 1559
	/* workqueue for reserved extent conversions (buffered io) */
	struct workqueue_struct *rsv_conversion_wq;
1560 1561 1562

	/* timer for periodic error stats printing */
	struct timer_list s_err_report;
1563 1564 1565 1566 1567

	/* Lazy inode table initialization info */
	struct ext4_li_request *s_li_request;
	/* Wait multiplier for lazy initialization thread */
	unsigned int s_li_wait_mult;
1568 1569 1570

	/* Kernel thread for multiple mount protection */
	struct task_struct *s_mmp_tsk;
1571 1572 1573

	/* record the last minlen when FITRIM is called. */
	atomic_t s_last_trim_minblks;
1574 1575 1576

	/* Reference to checksum algorithm driver via cryptoapi */
	struct crypto_shash *s_chksum_driver;
1577 1578 1579

	/* Precomputed FS UUID checksum for seeding other checksums */
	__u32 s_csum_seed;
1580 1581 1582

	/* Reclaim extents from extent status tree */
	struct shrinker s_es_shrinker;
1583
	struct list_head s_es_list;	/* List of inodes with reclaimable extents */
1584
	long s_es_nr_inode;
1585
	struct ext4_es_stats s_es_stats;
1586
	struct mb_cache *s_ea_block_cache;
T
Tahsin Erdogan 已提交
1587
	struct mb_cache *s_ea_inode_cache;
1588
	spinlock_t s_es_lock ____cacheline_aligned_in_smp;
1589 1590 1591 1592 1593

	/* Ratelimit ext4 messages. */
	struct ratelimit_state s_err_ratelimit_state;
	struct ratelimit_state s_warning_ratelimit_state;
	struct ratelimit_state s_msg_ratelimit_state;
1594 1595
	atomic_t s_warning_count;
	atomic_t s_msg_count;
1596

1597 1598 1599
	/* Encryption context for '-o test_dummy_encryption' */
	struct fscrypt_dummy_context s_dummy_enc_ctx;

1600 1601 1602 1603
	/*
	 * Barrier between writepages ops and changing any inode's JOURNAL_DATA
	 * or EXTENTS flag.
	 */
1604
	struct percpu_rw_semaphore s_writepages_rwsem;
1605
	struct dax_device *s_daxdev;
1606 1607 1608
#ifdef CONFIG_EXT4_DEBUG
	unsigned long s_simulate_fail;
#endif
1609 1610 1611
	/* Record the errseq of the backing block device */
	errseq_t s_bdev_wb_err;
	spinlock_t s_bdev_wb_lock;
1612 1613
};

1614
static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
1615 1616 1617
{
	return sb->s_fs_info;
}
1618
static inline struct ext4_inode_info *EXT4_I(struct inode *inode)
1619
{
1620
	return container_of(inode, struct ext4_inode_info, vfs_inode);
1621 1622
}

1623
static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
1624
{
1625 1626 1627
	return ino == EXT4_ROOT_INO ||
		(ino >= EXT4_FIRST_INO(sb) &&
		 ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
1628
}
1629

1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646
/*
 * 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;								   \
})

1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680
/*
 * 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);
}

1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706
/*
 * 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

1707 1708 1709 1710 1711 1712 1713 1714 1715 1716
/*
 * 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 */
1717
	EXT4_STATE_NEWENTRY,		/* File just added to dir */
1718
	EXT4_STATE_MAY_INLINE_DATA,	/* may have in-inode data */
1719
	EXT4_STATE_EXT_PRECACHED,	/* extents have been precached */
1720
	EXT4_STATE_LUSTRE_EA_INODE,	/* Lustre-style ea_inode */
E
Eric Biggers 已提交
1721
	EXT4_STATE_VERITY_IN_PROGRESS,	/* building fs-verity Merkle tree */
1722 1723
};

1724
#define EXT4_INODE_BIT_FNS(name, field, offset)				\
1725 1726
static inline int ext4_test_inode_##name(struct inode *inode, int bit)	\
{									\
1727
	return test_bit(bit + (offset), &EXT4_I(inode)->i_##field);	\
1728 1729 1730
}									\
static inline void ext4_set_inode_##name(struct inode *inode, int bit)	\
{									\
1731
	set_bit(bit + (offset), &EXT4_I(inode)->i_##field);		\
1732 1733 1734
}									\
static inline void ext4_clear_inode_##name(struct inode *inode, int bit) \
{									\
1735
	clear_bit(bit + (offset), &EXT4_I(inode)->i_##field);		\
1736 1737
}

1738 1739 1740 1741 1742
/* 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);
1743
EXT4_INODE_BIT_FNS(flag, flags, 0)
1744 1745 1746 1747 1748 1749

/* 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);
1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764
#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
1765
#else
1766
/* Assume that user mode programs are passing in an ext4fs superblock, not
1767 1768
 * a kernel struct super_block.  This will allow us to call the feature-test
 * macros from user land. */
1769
#define EXT4_SB(sb)	(sb)
1770 1771
#endif

E
Eric Biggers 已提交
1772 1773 1774 1775 1776 1777
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);
}

1778
#define NEXT_ORPHAN(inode) EXT4_I(inode)->i_dtime
1779 1780 1781 1782

/*
 * Codes for operating systems
 */
1783 1784 1785 1786 1787
#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
1788 1789 1790 1791

/*
 * Revision levels
 */
1792 1793
#define EXT4_GOOD_OLD_REV	0	/* The good old (original) format */
#define EXT4_DYNAMIC_REV	1	/* V2 format w/ dynamic inode sizes */
1794

1795 1796
#define EXT4_CURRENT_REV	EXT4_GOOD_OLD_REV
#define EXT4_MAX_SUPP_REV	EXT4_DYNAMIC_REV
1797

1798
#define EXT4_GOOD_OLD_INODE_SIZE 128
1799

1800 1801 1802 1803
#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

1804 1805 1806 1807
/*
 * Feature set definitions
 */

1808 1809 1810 1811 1812 1813
#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
1814
#define EXT4_FEATURE_COMPAT_SPARSE_SUPER2	0x0200
1815
#define EXT4_FEATURE_COMPAT_STABLE_INODES	0x0800
1816 1817 1818 1819

#define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER	0x0001
#define EXT4_FEATURE_RO_COMPAT_LARGE_FILE	0x0002
#define EXT4_FEATURE_RO_COMPAT_BTREE_DIR	0x0004
1820
#define EXT4_FEATURE_RO_COMPAT_HUGE_FILE        0x0008
A
Andreas Dilger 已提交
1821
#define EXT4_FEATURE_RO_COMPAT_GDT_CSUM		0x0010
1822
#define EXT4_FEATURE_RO_COMPAT_DIR_NLINK	0x0020
K
Kalpak Shah 已提交
1823
#define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE	0x0040
1824
#define EXT4_FEATURE_RO_COMPAT_QUOTA		0x0100
1825
#define EXT4_FEATURE_RO_COMPAT_BIGALLOC		0x0200
1826 1827 1828 1829 1830 1831
/*
 * 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.
 */
1832
#define EXT4_FEATURE_RO_COMPAT_METADATA_CSUM	0x0400
D
Darrick J. Wong 已提交
1833
#define EXT4_FEATURE_RO_COMPAT_READONLY		0x1000
1834
#define EXT4_FEATURE_RO_COMPAT_PROJECT		0x2000
E
Eric Biggers 已提交
1835
#define EXT4_FEATURE_RO_COMPAT_VERITY		0x8000
1836 1837 1838 1839 1840 1841

#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
1842
#define EXT4_FEATURE_INCOMPAT_EXTENTS		0x0040 /* extents support */
L
Laurent Vivier 已提交
1843
#define EXT4_FEATURE_INCOMPAT_64BIT		0x0080
1844
#define EXT4_FEATURE_INCOMPAT_MMP               0x0100
J
Jose R. Santos 已提交
1845
#define EXT4_FEATURE_INCOMPAT_FLEX_BG		0x0200
1846 1847
#define EXT4_FEATURE_INCOMPAT_EA_INODE		0x0400 /* EA in inode */
#define EXT4_FEATURE_INCOMPAT_DIRDATA		0x1000 /* data in dirent */
1848
#define EXT4_FEATURE_INCOMPAT_CSUM_SEED		0x2000
1849
#define EXT4_FEATURE_INCOMPAT_LARGEDIR		0x4000 /* >2GB or 3-lvl htree */
1850
#define EXT4_FEATURE_INCOMPAT_INLINE_DATA	0x8000 /* data in inode */
1851
#define EXT4_FEATURE_INCOMPAT_ENCRYPT		0x10000
1852
#define EXT4_FEATURE_INCOMPAT_CASEFOLD		0x20000
1853

1854 1855
extern void ext4_update_dynamic_rev(struct super_block *sb);

1856 1857 1858 1859 1860 1861 1862 1863
#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) \
{ \
1864
	ext4_update_dynamic_rev(sb); \
1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881
	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) \
{ \
1882
	ext4_update_dynamic_rev(sb); \
1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899
	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) \
{ \
1900
	ext4_update_dynamic_rev(sb); \
1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916
	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)
1917
EXT4_FEATURE_COMPAT_FUNCS(stable_inodes,	STABLE_INODES)
1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930

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
1931
EXT4_FEATURE_RO_COMPAT_FUNCS(verity,		VERITY)
1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947

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)
1948
EXT4_FEATURE_INCOMPAT_FUNCS(casefold,		CASEFOLD)
1949

1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964
#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)

1965
#define EXT4_FEATURE_COMPAT_SUPP	EXT4_FEATURE_COMPAT_EXT_ATTR
1966 1967
#define EXT4_FEATURE_INCOMPAT_SUPP	(EXT4_FEATURE_INCOMPAT_FILETYPE| \
					 EXT4_FEATURE_INCOMPAT_RECOVER| \
A
Alex Tomas 已提交
1968
					 EXT4_FEATURE_INCOMPAT_META_BG| \
L
Laurent Vivier 已提交
1969
					 EXT4_FEATURE_INCOMPAT_EXTENTS| \
J
Jose R. Santos 已提交
1970
					 EXT4_FEATURE_INCOMPAT_64BIT| \
1971
					 EXT4_FEATURE_INCOMPAT_FLEX_BG| \
A
Andreas Dilger 已提交
1972
					 EXT4_FEATURE_INCOMPAT_EA_INODE| \
1973 1974
					 EXT4_FEATURE_INCOMPAT_MMP | \
					 EXT4_FEATURE_INCOMPAT_INLINE_DATA | \
1975
					 EXT4_FEATURE_INCOMPAT_ENCRYPT | \
1976
					 EXT4_FEATURE_INCOMPAT_CASEFOLD | \
A
Artem Blagodarenko 已提交
1977 1978
					 EXT4_FEATURE_INCOMPAT_CSUM_SEED | \
					 EXT4_FEATURE_INCOMPAT_LARGEDIR)
1979 1980
#define EXT4_FEATURE_RO_COMPAT_SUPP	(EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
					 EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \
A
Andreas Dilger 已提交
1981
					 EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \
1982
					 EXT4_FEATURE_RO_COMPAT_DIR_NLINK | \
K
Kalpak Shah 已提交
1983
					 EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \
1984
					 EXT4_FEATURE_RO_COMPAT_BTREE_DIR |\
1985
					 EXT4_FEATURE_RO_COMPAT_HUGE_FILE |\
1986
					 EXT4_FEATURE_RO_COMPAT_BIGALLOC |\
1987
					 EXT4_FEATURE_RO_COMPAT_METADATA_CSUM|\
L
Li Xi 已提交
1988
					 EXT4_FEATURE_RO_COMPAT_QUOTA |\
E
Eric Biggers 已提交
1989 1990
					 EXT4_FEATURE_RO_COMPAT_PROJECT |\
					 EXT4_FEATURE_RO_COMPAT_VERITY)
1991

1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025
#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);
}

2026 2027 2028 2029
/*
 * Superblock flags
 */
#define EXT4_FLAGS_RESIZING	0
2030
#define EXT4_FLAGS_SHUTDOWN	1
2031
#define EXT4_FLAGS_BDEV_IS_DAX	2
2032 2033 2034 2035 2036

static inline int ext4_forced_shutdown(struct ext4_sb_info *sbi)
{
	return test_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
}
2037 2038


2039 2040 2041
/*
 * Default values for user and/or group using reserved blocks
 */
2042 2043
#define	EXT4_DEF_RESUID		0
#define	EXT4_DEF_RESGID		0
2044

L
Li Xi 已提交
2045 2046 2047 2048 2049
/*
 * Default project ID
 */
#define	EXT4_DEF_PROJID		0

2050 2051
#define EXT4_DEF_INODE_READAHEAD_BLKS	32

2052 2053 2054
/*
 * Default mount options
 */
2055 2056 2057 2058 2059 2060 2061 2062 2063
#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
2064 2065 2066 2067
#define EXT4_DEFM_NOBARRIER	0x0100
#define EXT4_DEFM_BLOCK_VALIDITY 0x0200
#define EXT4_DEFM_DISCARD	0x0400
#define EXT4_DEFM_NODELALLOC	0x0800
2068

2069 2070 2071 2072 2073 2074
/*
 * Default journal batch times
 */
#define EXT4_DEF_MIN_BATCH_TIME	0
#define EXT4_DEF_MAX_BATCH_TIME	15000 /* 15ms */

2075 2076 2077 2078 2079 2080
/*
 * 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

2081 2082 2083
/*
 * Structure of a directory entry
 */
2084
#define EXT4_NAME_LEN 255
2085

2086
struct ext4_dir_entry {
2087 2088 2089
	__le32	inode;			/* Inode number */
	__le16	rec_len;		/* Directory entry length */
	__le16	name_len;		/* Name length */
2090
	char	name[EXT4_NAME_LEN];	/* File name */
2091 2092 2093
};

/*
2094
 * The new version of the directory entry.  Since EXT4 structures are
2095 2096 2097 2098
 * 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.
 */
2099
struct ext4_dir_entry_2 {
2100 2101 2102
	__le32	inode;			/* Inode number */
	__le16	rec_len;		/* Directory entry length */
	__u8	name_len;		/* Name length */
2103
	__u8	file_type;		/* See file type macros EXT4_FT_* below */
2104
	char	name[EXT4_NAME_LEN];	/* File name */
2105 2106
};

2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118
/*
 * 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) */
};

2119 2120 2121 2122 2123
#define EXT4_DIRENT_TAIL(block, blocksize) \
	((struct ext4_dir_entry_tail *)(((void *)(block)) + \
					((blocksize) - \
					 sizeof(struct ext4_dir_entry_tail))))

2124
/*
2125
 * Ext4 directory file types.  Only the low 3 bits are used.  The
2126 2127
 * other bits are reserved for now.
 */
2128 2129 2130 2131 2132 2133 2134 2135
#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
2136

2137
#define EXT4_FT_MAX		8
2138

2139 2140
#define EXT4_FT_DIR_CSUM	0xDE

2141
/*
2142
 * EXT4_DIR_PAD defines the directory entries boundaries
2143 2144 2145
 *
 * NOTE: It must be a multiple of 4
 */
2146 2147 2148 2149
#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)
2150 2151
#define EXT4_MAX_REC_LEN		((1<<16)-1)

2152 2153 2154 2155 2156 2157 2158 2159 2160
/*
 * 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);

2161
#if (PAGE_SIZE >= 65536)
2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173
	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();
2174
#if (PAGE_SIZE >= 65536)
2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188
	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
}

2189 2190 2191 2192 2193
/*
 * Hash Tree Directory indexing
 * (c) Daniel Phillips, 2001
 */

2194
#define is_dx(dir) (ext4_has_feature_dir_index((dir)->i_sb) && \
2195
		    ext4_test_inode_flag((dir), EXT4_INODE_INDEX))
A
Andreas Dilger 已提交
2196 2197
#define EXT4_DIR_LINK_MAX(dir) unlikely((dir)->i_nlink >= EXT4_LINK_MAX && \
		    !(ext4_has_feature_dir_nlink((dir)->i_sb) && is_dx(dir)))
2198
#define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2 || (dir)->i_nlink == 1)
2199 2200 2201

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

2202 2203 2204 2205
#define DX_HASH_LEGACY			0
#define DX_HASH_HALF_MD4		1
#define DX_HASH_TEA			2
#define DX_HASH_LEGACY_UNSIGNED		3
2206 2207
#define DX_HASH_HALF_MD4_UNSIGNED	4
#define DX_HASH_TEA_UNSIGNED		5
2208

2209 2210 2211 2212 2213
static inline u32 ext4_chksum(struct ext4_sb_info *sbi, u32 crc,
			      const void *address, unsigned int length)
{
	struct {
		struct shash_desc shash;
2214
		char ctx[4];
2215 2216
	} desc;

2217 2218
	BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver)!=sizeof(desc.ctx));

2219 2220 2221
	desc.shash.tfm = sbi->s_chksum_driver;
	*(u32 *)desc.ctx = crc;

2222
	BUG_ON(crypto_shash_update(&desc.shash, address, length));
2223 2224 2225 2226

	return *(u32 *)desc.ctx;
}

2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237
#ifdef __KERNEL__

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

2238 2239 2240 2241 2242

/* 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)

2243 2244

/*
2245
 * Control parameters used by ext4_htree_next_block
2246 2247 2248
 */
#define HASH_NB_ALWAYS		1

2249 2250
struct ext4_filename {
	const struct qstr *usr_fname;
2251
	struct fscrypt_str disk_name;
2252
	struct dx_hash_info hinfo;
2253
#ifdef CONFIG_FS_ENCRYPTION
2254
	struct fscrypt_str crypto_buf;
2255
#endif
2256 2257 2258
#ifdef CONFIG_UNICODE
	struct fscrypt_str cf_name;
#endif
2259 2260 2261 2262
};

#define fname_name(p) ((p)->disk_name.name)
#define fname_len(p)  ((p)->disk_name.len)
2263 2264 2265 2266

/*
 * Describe an inode's exact location on disk and in memory
 */
2267
struct ext4_iloc
2268 2269 2270
{
	struct buffer_head *bh;
	unsigned long offset;
2271
	ext4_group_t block_group;
2272 2273
};

2274
static inline struct ext4_inode *ext4_raw_inode(struct ext4_iloc *iloc)
2275
{
2276
	return (struct ext4_inode *) (iloc->bh->b_data + iloc->offset);
2277 2278
}

T
Tahsin Erdogan 已提交
2279 2280 2281 2282 2283
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
2284

2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300
/*
 * 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 */
2301
static inline ext4_fsblk_t
2302
ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no)
2303
{
2304 2305
	return group_no * (ext4_fsblk_t)EXT4_BLOCKS_PER_GROUP(sb) +
		le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
2306 2307 2308 2309 2310
}

/*
 * Special error return code only used by dx_probe() and its callers.
 */
2311
#define ERR_BAD_DX_DIR	(-(MAX_ERRNO - 1))
2312

A
Artem Blagodarenko 已提交
2313 2314 2315 2316 2317 2318 2319 2320 2321 2322
/* 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;
}

2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339
/*
 * 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;
};

2340 2341 2342 2343 2344
enum ext4_li_mode {
	EXT4_LI_MODE_PREFETCH_BBITMAP,
	EXT4_LI_MODE_ITABLE,
};

2345 2346
struct ext4_li_request {
	struct super_block	*lr_super;
2347 2348
	enum ext4_li_mode	lr_mode;
	ext4_group_t		lr_first_not_zeroed;
2349 2350 2351 2352 2353 2354
	ext4_group_t		lr_next_group;
	struct list_head	lr_request;
	unsigned long		lr_next_sched;
	unsigned long		lr_timeout;
};

2355 2356 2357 2358 2359
struct ext4_features {
	struct kobject f_kobj;
	struct completion f_kobj_unregister;
};

2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391
/*
 * 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;
2392 2393
	__le32	mmp_pad2[226];
	__le32	mmp_checksum;		/* crc32c(uuid+mmp_block) */
2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421
};

/* 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

2422 2423 2424 2425 2426 2427
/*
 * Function prototypes
 */

/*
 * Ok, these declarations are also in <linux/kernel.h> but none of the
2428
 * ext4 source programs needs to include it so they are duplicated here.
2429
 */
D
Dave Kleikamp 已提交
2430 2431 2432
# define NORET_TYPE	/**/
# define ATTRIB_NORET	__attribute__((noreturn))
# define NORET_AND	noreturn,
2433

2434
/* bitmap.c */
2435
extern unsigned int ext4_count_free(char *bitmap, unsigned numchars);
2436 2437 2438 2439 2440 2441
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);
2442 2443
void ext4_block_bitmap_csum_set(struct super_block *sb, ext4_group_t group,
				struct ext4_group_desc *gdp,
2444
				struct buffer_head *bh);
2445 2446
int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group,
				  struct ext4_group_desc *gdp,
2447
				  struct buffer_head *bh);
2448

2449
/* balloc.c */
2450 2451 2452 2453 2454 2455 2456
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);

2457 2458 2459 2460
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);
2461 2462 2463
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);
2464
extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
2465 2466 2467 2468
					 ext4_fsblk_t goal,
					 unsigned int flags,
					 unsigned long *count,
					 int *errp);
2469 2470
extern int ext4_claim_free_clusters(struct ext4_sb_info *sbi,
				    s64 nclusters, unsigned int flags);
2471
extern ext4_fsblk_t ext4_count_free_clusters(struct super_block *);
2472
extern void ext4_check_blocks_bitmap(struct super_block *);
2473
extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
2474
						    ext4_group_t block_group,
2475
						    struct buffer_head ** bh);
2476
extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
2477 2478

extern struct buffer_head *ext4_read_block_bitmap_nowait(struct super_block *sb,
2479 2480
						ext4_group_t block_group,
						bool ignore_locked);
2481 2482 2483 2484 2485
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);
2486 2487 2488
extern unsigned ext4_free_clusters_after_init(struct super_block *sb,
					      ext4_group_t block_group,
					      struct ext4_group_desc *gdp);
2489
ext4_fsblk_t ext4_inode_to_goal_block(struct inode *);
2490

2491 2492 2493 2494 2495 2496
#ifdef CONFIG_UNICODE
extern void ext4_fname_setup_ci_filename(struct inode *dir,
					 const struct qstr *iname,
					 struct fscrypt_str *fname);
#endif

2497
#ifdef CONFIG_FS_ENCRYPTION
2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509
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;
}

2510
static inline int ext4_fname_setup_filename(struct inode *dir,
2511 2512 2513
					    const struct qstr *iname,
					    int lookup,
					    struct ext4_filename *fname)
2514
{
2515 2516
	struct fscrypt_name name;
	int err;
2517

2518
	err = fscrypt_setup_filename(dir, iname, lookup, &name);
2519 2520
	if (err)
		return err;
2521

2522
	ext4_fname_from_fscrypt_name(fname, &name);
2523 2524 2525 2526

#ifdef CONFIG_UNICODE
	ext4_fname_setup_ci_filename(dir, iname, &fname->cf_name);
#endif
2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541
	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);
2542 2543 2544 2545

#ifdef CONFIG_UNICODE
	ext4_fname_setup_ci_filename(dir, &dentry->d_name, &fname->cf_name);
#endif
2546
	return 0;
2547 2548
}

2549
static inline void ext4_fname_free_filename(struct ext4_filename *fname)
2550
{
2551
	struct fscrypt_name name;
2552

2553 2554 2555 2556 2557 2558
	name.crypto_buf = fname->crypto_buf;
	fscrypt_free_filename(&name);

	fname->crypto_buf.name = NULL;
	fname->usr_fname = NULL;
	fname->disk_name.name = NULL;
2559 2560 2561 2562 2563

#ifdef CONFIG_UNICODE
	kfree(fname->cf_name.name);
	fname->cf_name.name = NULL;
#endif
2564
}
2565
#else /* !CONFIG_FS_ENCRYPTION */
2566
static inline int ext4_fname_setup_filename(struct inode *dir,
2567 2568 2569
					    const struct qstr *iname,
					    int lookup,
					    struct ext4_filename *fname)
2570
{
2571 2572 2573
	fname->usr_fname = iname;
	fname->disk_name.name = (unsigned char *) iname->name;
	fname->disk_name.len = iname->len;
2574 2575 2576 2577 2578

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

2579 2580
	return 0;
}
2581

2582 2583 2584 2585 2586 2587 2588
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);
}

2589 2590 2591 2592 2593 2594 2595
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
}
2596
#endif /* !CONFIG_FS_ENCRYPTION */
2597

2598
/* dir.c */
2599
extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *,
2600
				  struct file *,
2601
				  struct ext4_dir_entry_2 *,
2602 2603 2604
				  struct buffer_head *, char *, int,
				  unsigned int);
#define ext4_check_dir_entry(dir, filp, de, bh, buf, size, offset)	\
2605
	unlikely(__ext4_check_dir_entry(__func__, __LINE__, (dir), (filp), \
2606
					(de), (bh), (buf), (size), (offset)))
2607
extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
2608 2609
				__u32 minor_hash,
				struct ext4_dir_entry_2 *dirent,
2610
				struct fscrypt_str *ent_name);
2611
extern void ext4_htree_free_dir_info(struct dir_private_info *p);
2612 2613 2614
extern int ext4_find_dest_de(struct inode *dir, struct inode *inode,
			     struct buffer_head *bh,
			     void *buf, int buf_size,
2615
			     struct ext4_filename *fname,
2616
			     struct ext4_dir_entry_2 **dest_de);
2617 2618 2619 2620
void ext4_insert_dentry(struct inode *inode,
			struct ext4_dir_entry_2 *de,
			int buf_size,
			struct ext4_filename *fname);
2621 2622
static inline void ext4_update_dx_flag(struct inode *inode)
{
2623 2624 2625
	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));
2626
		ext4_clear_inode_flag(inode, EXT4_INODE_INDEX);
2627
	}
2628
}
2629
static const unsigned char ext4_filetype_table[] = {
T
Tao Ma 已提交
2630 2631 2632 2633 2634
	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)
{
2635
	if (!ext4_has_feature_filetype(sb) || filetype >= EXT4_FT_MAX)
T
Tao Ma 已提交
2636 2637 2638 2639
		return DT_UNKNOWN;

	return ext4_filetype_table[filetype];
}
2640 2641
extern int ext4_check_all_de(struct inode *dir, struct buffer_head *bh,
			     void *buf, int buf_size);
2642 2643

/* fsync.c */
2644
extern int ext4_sync_file(struct file *, loff_t, loff_t, int);
2645 2646

/* hash.c */
2647 2648
extern int ext4fs_dirhash(const struct inode *dir, const char *name, int len,
			  struct dx_hash_info *hinfo);
2649 2650

/* ialloc.c */
2651 2652
extern struct inode *__ext4_new_inode(handle_t *, struct inode *, umode_t,
				      const struct qstr *qstr, __u32 goal,
2653 2654 2655
				      uid_t *owner, __u32 i_flags,
				      int handle_type, unsigned int line_no,
				      int nblocks);
2656

2657
#define ext4_new_inode(handle, dir, mode, qstr, goal, owner, i_flags) \
2658
	__ext4_new_inode((handle), (dir), (mode), (qstr), (goal), (owner), \
2659
			 i_flags, 0, 0, 0)
2660 2661 2662
#define ext4_new_inode_start_handle(dir, mode, qstr, goal, owner, \
				    type, nblocks)		    \
	__ext4_new_inode(NULL, (dir), (mode), (qstr), (goal), (owner), \
2663
			 0, (type), __LINE__, (nblocks))
2664 2665


2666 2667 2668 2669 2670
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 *);
2671
extern void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
2672 2673
extern int ext4_init_inode_table(struct super_block *sb,
				 ext4_group_t group, int barrier);
2674
extern void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate);
2675

2676
/* mballoc.c */
C
Christoph Hellwig 已提交
2677
extern const struct seq_operations ext4_mb_seq_groups_ops;
2678 2679
extern long ext4_mb_stats;
extern long ext4_mb_max_to_scan;
2680
extern int ext4_mb_init(struct super_block *);
2681 2682 2683 2684
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);
2685
extern void ext4_discard_preallocations(struct inode *);
2686 2687
extern int __init ext4_init_mballoc(void);
extern void ext4_exit_mballoc(void);
2688 2689 2690 2691 2692 2693
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);

2694
extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
2695 2696
			     struct buffer_head *bh, ext4_fsblk_t block,
			     unsigned long count, int flags);
2697 2698
extern int ext4_mb_alloc_groupinfo(struct super_block *sb,
				   ext4_group_t ngroups);
2699
extern int ext4_mb_add_groupinfo(struct super_block *sb,
2700
		ext4_group_t i, struct ext4_group_desc *desc);
2701
extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
2702
				ext4_fsblk_t block, unsigned long count);
2703
extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);
2704
extern void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid);
2705

2706
/* inode.c */
2707
int ext4_inode_is_fast_symlink(struct inode *inode);
2708
struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int);
2709
struct buffer_head *ext4_bread(handle_t *, struct inode *, ext4_lblk_t, int);
2710 2711
int ext4_bread_batch(struct inode *inode, ext4_lblk_t block, int bh_count,
		     bool wait, struct buffer_head **bhs);
2712 2713
int ext4_get_block_unwritten(struct inode *inode, sector_t iblock,
			     struct buffer_head *bh_result, int create);
2714
int ext4_get_block(struct inode *inode, sector_t iblock,
2715
		   struct buffer_head *bh_result, int create);
2716 2717
int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
			   struct buffer_head *bh, int create);
2718 2719 2720 2721 2722 2723 2724 2725 2726
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);
2727 2728
#define FALL_BACK_TO_NONDELALLOC 1
#define CONVERT_INLINE_DATA	 2
2729

2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742
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__)

2743
extern int  ext4_write_inode(struct inode *, struct writeback_control *);
2744
extern int  ext4_setattr(struct dentry *, struct iattr *);
2745
extern int  ext4_getattr(const struct path *, struct kstat *, u32, unsigned int);
A
Al Viro 已提交
2746 2747
extern void ext4_evict_inode(struct inode *);
extern void ext4_clear_inode(struct inode *);
D
David Howells 已提交
2748
extern int  ext4_file_getattr(const struct path *, struct kstat *, u32, unsigned int);
2749
extern int  ext4_sync_inode(handle_t *, struct inode *);
2750
extern void ext4_dirty_inode(struct inode *, int);
2751 2752
extern int ext4_change_inode_journal_flag(struct inode *, int);
extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
2753
extern int ext4_inode_attach_jinode(struct inode *inode);
2754
extern int ext4_can_truncate(struct inode *inode);
2755
extern int ext4_truncate(struct inode *);
2756
extern int ext4_break_layouts(struct inode *);
2757
extern int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length);
2758
extern void ext4_set_inode_flags(struct inode *, bool init);
2759
extern int ext4_alloc_da_blocks(struct inode *inode);
2760
extern void ext4_set_aops(struct inode *inode);
A
Alex Tomas 已提交
2761
extern int ext4_writepage_trans_blocks(struct inode *);
2762
extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
2763 2764
extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
			     loff_t lstart, loff_t lend);
2765 2766
extern vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf);
extern vm_fault_t ext4_filemap_fault(struct vm_fault *vmf);
2767
extern qsize_t *ext4_get_reserved_space(struct inode *inode);
L
Li Xi 已提交
2768
extern int ext4_get_projid(struct inode *inode, kprojid_t *projid);
2769
extern void ext4_da_release_space(struct inode *inode, int to_free);
2770 2771
extern void ext4_da_update_reserve_space(struct inode *inode,
					int used, int quota_claim);
J
Jan Kara 已提交
2772 2773
extern int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk,
			      ext4_fsblk_t pblk, ext4_lblk_t len);
2774 2775 2776 2777

/* indirect.c */
extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
				struct ext4_map_blocks *map, int flags);
2778
extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks);
T
Theodore Ts'o 已提交
2779
extern void ext4_ind_truncate(handle_t *, struct inode *inode);
2780 2781
extern int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
				 ext4_lblk_t start, ext4_lblk_t end);
2782

2783
/* ioctl.c */
A
Andi Kleen 已提交
2784
extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
2785
extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
2786

2787
/* migrate.c */
2788
extern int ext4_ext_migrate(struct inode *);
2789
extern int ext4_ind_migrate(struct inode *inode);
2790

2791
/* namei.c */
2792 2793
extern int ext4_dirblock_csum_verify(struct inode *inode,
				     struct buffer_head *bh);
2794 2795 2796
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,
2797
				__u32 start_minor_hash, __u32 *next_hash);
2798 2799 2800 2801 2802 2803 2804
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);
T
Tao Ma 已提交
2805 2806 2807 2808 2809 2810 2811
extern int ext4_generic_delete_entry(handle_t *handle,
				     struct inode *dir,
				     struct ext4_dir_entry_2 *de_del,
				     struct buffer_head *bh,
				     void *entry_buf,
				     int buf_size,
				     int csum_size);
2812
extern bool ext4_empty_dir(struct inode *inode);
2813 2814

/* resize.c */
2815
extern void ext4_kvfree_array_rcu(void *to_free);
2816 2817 2818 2819 2820
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);
2821
extern int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count);
2822 2823

/* super.c */
2824 2825
extern struct buffer_head *ext4_sb_bread(struct super_block *sb,
					 sector_t block, int op_flags);
2826
extern int ext4_seq_options_show(struct seq_file *seq, void *offset);
2827
extern int ext4_calculate_overhead(struct super_block *sb);
2828
extern void ext4_superblock_csum_set(struct super_block *sb);
2829 2830
extern int ext4_alloc_flex_bg_array(struct super_block *sb,
				    ext4_group_t ngroup);
2831 2832
extern const char *ext4_decode_error(struct super_block *sb, int errno,
				     char nbuf[16]);
2833 2834 2835
extern void ext4_mark_group_bitmap_corrupted(struct super_block *sb,
					     ext4_group_t block_group,
					     unsigned int flags);
2836

2837 2838
extern __printf(6, 7)
void __ext4_error(struct super_block *, const char *, unsigned int, int, __u64,
2839
		  const char *, ...);
2840 2841 2842
extern __printf(6, 7)
void __ext4_error_inode(struct inode *, const char *, unsigned int,
			ext4_fsblk_t, int, const char *, ...);
2843
extern __printf(5, 6)
2844
void __ext4_error_file(struct file *, const char *, unsigned int, ext4_fsblk_t,
2845
		     const char *, ...);
2846 2847
extern void __ext4_std_error(struct super_block *, const char *,
			     unsigned int, int);
2848 2849
extern __printf(5, 6)
void __ext4_abort(struct super_block *, const char *, unsigned int, int,
2850 2851 2852 2853
		  const char *, ...);
extern __printf(4, 5)
void __ext4_warning(struct super_block *, const char *, unsigned int,
		    const char *, ...);
2854 2855 2856
extern __printf(4, 5)
void __ext4_warning_inode(const struct inode *inode, const char *function,
			  unsigned int line, const char *fmt, ...);
2857
extern __printf(3, 4)
2858
void __ext4_msg(struct super_block *, const char *, const char *, ...);
2859 2860
extern void __dump_mmp_msg(struct super_block *, struct mmp_struct *mmp,
			   const char *, unsigned int, const char *);
2861 2862 2863 2864 2865
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 *, ...);
2866

2867 2868 2869
#define EXT4_ERROR_INODE(inode, fmt, a...) \
	ext4_error_inode((inode), __func__, __LINE__, 0, (fmt), ## a)

2870 2871 2872 2873 2874 2875
#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)
2876 2877 2878 2879

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

2880 2881 2882
#ifdef CONFIG_PRINTK

#define ext4_error_inode(inode, func, line, block, fmt, ...)		\
2883 2884 2885 2886
	__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__)
2887 2888 2889
#define ext4_error_file(file, func, line, block, fmt, ...)		\
	__ext4_error_file(file, func, line, block, fmt, ##__VA_ARGS__)
#define ext4_error(sb, fmt, ...)					\
2890 2891 2892 2893 2894
	__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__)
2895 2896
#define ext4_warning(sb, fmt, ...)					\
	__ext4_warning(sb, __func__, __LINE__, fmt, ##__VA_ARGS__)
2897 2898
#define ext4_warning_inode(inode, fmt, ...)				\
	__ext4_warning_inode(inode, __func__, __LINE__, fmt, ##__VA_ARGS__)
2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911
#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__);					\
2912 2913 2914 2915 2916 2917
	__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, " ");		\
2918 2919 2920 2921 2922 2923 2924 2925 2926
} 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__);					\
2927 2928 2929 2930 2931 2932
	__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, " ");				\
2933
} while (0)
2934
#define ext4_abort(sb, err, fmt, ...)					\
2935 2936
do {									\
	no_printk(fmt, ##__VA_ARGS__);					\
2937
	__ext4_abort(sb, "", 0, err, " ");				\
2938 2939 2940 2941 2942 2943
} while (0)
#define ext4_warning(sb, fmt, ...)					\
do {									\
	no_printk(fmt, ##__VA_ARGS__);					\
	__ext4_warning(sb, "", 0, " ");					\
} while (0)
2944 2945 2946 2947 2948
#define ext4_warning_inode(inode, fmt, ...)				\
do {									\
	no_printk(fmt, ##__VA_ARGS__);					\
	__ext4_warning_inode(inode, "", 0, " ");			\
} while (0)
2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963
#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

2964 2965 2966 2967 2968 2969
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);
2970 2971
extern __u32 ext4_free_group_clusters(struct super_block *sb,
				      struct ext4_group_desc *bg);
2972 2973 2974 2975 2976 2977
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);
2978 2979 2980 2981 2982 2983
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);
2984 2985 2986
extern void ext4_free_group_clusters_set(struct super_block *sb,
					 struct ext4_group_desc *bg,
					 __u32 count);
2987 2988 2989 2990 2991 2992
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);
2993
extern int ext4_group_desc_csum_verify(struct super_block *sb, __u32 group,
2994
				       struct ext4_group_desc *gdp);
2995 2996
extern void ext4_group_desc_csum_set(struct super_block *sb, __u32 group,
				     struct ext4_group_desc *gdp);
2997 2998
extern int ext4_register_li_request(struct super_block *sb,
				    ext4_group_t first_not_zeroed);
L
Laurent Vivier 已提交
2999

3000 3001
static inline int ext4_has_metadata_csum(struct super_block *sb)
{
3002
	WARN_ON_ONCE(ext4_has_feature_metadata_csum(sb) &&
3003 3004
		     !EXT4_SB(sb)->s_chksum_driver);

T
Tahsin Erdogan 已提交
3005 3006
	return ext4_has_feature_metadata_csum(sb) &&
	       (EXT4_SB(sb)->s_chksum_driver != NULL);
3007
}
T
Tahsin Erdogan 已提交
3008 3009 3010 3011 3012 3013

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

L
Laurent Vivier 已提交
3014 3015 3016
static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es)
{
	return ((ext4_fsblk_t)le32_to_cpu(es->s_blocks_count_hi) << 32) |
3017
		le32_to_cpu(es->s_blocks_count_lo);
L
Laurent Vivier 已提交
3018 3019 3020 3021 3022
}

static inline ext4_fsblk_t ext4_r_blocks_count(struct ext4_super_block *es)
{
	return ((ext4_fsblk_t)le32_to_cpu(es->s_r_blocks_count_hi) << 32) |
3023
		le32_to_cpu(es->s_r_blocks_count_lo);
L
Laurent Vivier 已提交
3024 3025 3026 3027 3028
}

static inline ext4_fsblk_t ext4_free_blocks_count(struct ext4_super_block *es)
{
	return ((ext4_fsblk_t)le32_to_cpu(es->s_free_blocks_count_hi) << 32) |
3029
		le32_to_cpu(es->s_free_blocks_count_lo);
L
Laurent Vivier 已提交
3030 3031 3032 3033 3034
}

static inline void ext4_blocks_count_set(struct ext4_super_block *es,
					 ext4_fsblk_t blk)
{
3035
	es->s_blocks_count_lo = cpu_to_le32((u32)blk);
L
Laurent Vivier 已提交
3036 3037 3038 3039 3040 3041
	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)
{
3042
	es->s_free_blocks_count_lo = cpu_to_le32((u32)blk);
L
Laurent Vivier 已提交
3043 3044 3045 3046 3047 3048
	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)
{
3049
	es->s_r_blocks_count_lo = cpu_to_le32((u32)blk);
L
Laurent Vivier 已提交
3050 3051 3052
	es->s_r_blocks_count_hi = cpu_to_le32(blk >> 32);
}

A
Artem Blagodarenko 已提交
3053 3054
static inline loff_t ext4_isize(struct super_block *sb,
				struct ext4_inode *raw_inode)
3055
{
A
Artem Blagodarenko 已提交
3056 3057
	if (ext4_has_feature_largedir(sb) ||
	    S_ISREG(le16_to_cpu(raw_inode->i_mode)))
3058 3059
		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
3060 3061

	return (loff_t) le32_to_cpu(raw_inode->i_size_lo);
3062
}
L
Laurent Vivier 已提交
3063

3064 3065 3066 3067 3068
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);
}
3069

3070 3071
static inline
struct ext4_group_info *ext4_get_group_info(struct super_block *sb,
3072
					    ext4_group_t group)
3073
{
3074
	 struct ext4_group_info **grp_info;
3075
	 long indexv, indexh;
3076
	 BUG_ON(group >= EXT4_SB(sb)->s_groups_count);
3077 3078
	 indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb));
	 indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1);
3079 3080
	 grp_info = sbi_array_rcu_deref(EXT4_SB(sb), s_group_info, indexv);
	 return grp_info[indexh];
3081 3082
}

3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094
/*
 * 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;
}
3095

3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106
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;
}

3107
#define ext4_std_error(sb, errno)				\
3108 3109
do {								\
	if ((errno))						\
3110
		__ext4_std_error((sb), __func__, __LINE__, (errno));	\
3111 3112
} while (0)

3113
#ifdef CONFIG_SMP
3114 3115
/* Each CPU can accumulate percpu_counter_batch clusters in their local
 * counters. So we need to make sure we have free clusters more
3116
 * than percpu_counter_batch  * nr_cpu_ids. Also add a window of 4 times.
3117
 */
3118
#define EXT4_FREECLUSTERS_WATERMARK (4 * (percpu_counter_batch * nr_cpu_ids))
3119
#else
3120
#define EXT4_FREECLUSTERS_WATERMARK 0
3121 3122
#endif

3123
/* Update i_disksize. Requires i_mutex to avoid races with truncate */
3124 3125
static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
{
3126
	WARN_ON_ONCE(S_ISREG(inode->i_mode) &&
A
Al Viro 已提交
3127
		     !inode_is_locked(inode));
3128 3129
	down_write(&EXT4_I(inode)->i_data_sem);
	if (newsize > EXT4_I(inode)->i_disksize)
3130
		WRITE_ONCE(EXT4_I(inode)->i_disksize, newsize);
3131 3132 3133
	up_write(&EXT4_I(inode)->i_data_sem);
}

3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149
/* 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;
}

3150 3151 3152
int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
				      loff_t len);

3153 3154 3155
struct ext4_group_info {
	unsigned long   bb_state;
	struct rb_root  bb_free_root;
3156 3157 3158
	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 */
3159
	ext4_grpblk_t	bb_largest_free_order;/* order of largest frag in BG */
3160 3161 3162 3163 3164
	struct          list_head bb_prealloc_list;
#ifdef DOUBLE_CHECK
	void            *bb_bitmap;
#endif
	struct rw_semaphore alloc_sem;
3165 3166 3167 3168
	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. */
3169 3170
};

3171 3172
#define EXT4_GROUP_INFO_NEED_INIT_BIT		0
#define EXT4_GROUP_INFO_WAS_TRIMMED_BIT		1
3173
#define EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT	2
3174
#define EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT	3
3175 3176 3177 3178
#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)
3179
#define EXT4_GROUP_INFO_BBITMAP_READ_BIT	4
3180 3181 3182

#define EXT4_MB_GRP_NEED_INIT(grp)	\
	(test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
3183 3184
#define EXT4_MB_GRP_BBITMAP_CORRUPT(grp)	\
	(test_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &((grp)->bb_state)))
3185 3186
#define EXT4_MB_GRP_IBITMAP_CORRUPT(grp)	\
	(test_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &((grp)->bb_state)))
3187

3188 3189 3190 3191 3192 3193
#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)))
3194 3195
#define EXT4_MB_GRP_TEST_AND_SET_READ(grp)	\
	(test_and_set_bit(EXT4_GROUP_INFO_BBITMAP_READ_BIT, &((grp)->bb_state)))
3196

3197 3198 3199
#define EXT4_MAX_CONTENTION		8
#define EXT4_CONTENTION_THRESHOLD	2

3200 3201
static inline spinlock_t *ext4_group_lock_ptr(struct super_block *sb,
					      ext4_group_t group)
3202
{
3203 3204
	return bgl_lock_ptr(EXT4_SB(sb)->s_blockgroup_lock, group);
}
3205

3206 3207 3208 3209 3210 3211 3212 3213 3214
/*
 * 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);
}

3215 3216
static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group)
{
3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232
	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);
	}
3233 3234 3235 3236 3237
}

static inline void ext4_unlock_group(struct super_block *sb,
					ext4_group_t group)
{
3238
	spin_unlock(ext4_group_lock_ptr(sb, group));
3239 3240
}

3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253
/*
 * 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)

3254 3255 3256 3257 3258
/*
 * Inodes and files operations
 */

/* dir.c */
3259
extern const struct file_operations ext4_dir_operations;
3260

3261 3262 3263 3264
#ifdef CONFIG_UNICODE
extern const struct dentry_operations ext4_dentry_ops;
#endif

3265
/* file.c */
3266
extern const struct inode_operations ext4_file_inode_operations;
3267
extern const struct file_operations ext4_file_operations;
3268
extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
3269

3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299
/* 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);
3300 3301
extern int ext4_try_add_inline_entry(handle_t *handle,
				     struct ext4_filename *fname,
3302
				     struct inode *dir, struct inode *inode);
3303 3304 3305 3306
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
3307
				struct dir_context *ctx,
3308
				int *has_inline_data);
3309 3310 3311 3312 3313
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);
3314
extern struct buffer_head *ext4_find_inline_entry(struct inode *dir,
3315
					struct ext4_filename *fname,
3316 3317 3318 3319 3320 3321 3322
					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);
3323
extern bool empty_inline_dir(struct inode *dir, int *has_inline_data);
3324 3325 3326 3327 3328
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,
3329
				   int *has_inline, __u64 start, __u64 len);
3330 3331 3332 3333

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

3334
extern int ext4_inline_data_truncate(struct inode *inode, int *has_inline);
3335 3336 3337

extern int ext4_convert_inline_data(struct inode *inode);

3338 3339 3340 3341 3342 3343
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;
}

3344
/* namei.c */
3345 3346
extern const struct inode_operations ext4_dir_inode_operations;
extern const struct inode_operations ext4_special_inode_operations;
3347
extern struct dentry *ext4_get_parent(struct dentry *child);
3348 3349 3350 3351
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);
3352 3353
extern void ext4_initialize_dirent_tail(struct buffer_head *bh,
					unsigned int blocksize);
3354 3355
extern int ext4_handle_dirty_dirblock(handle_t *handle, struct inode *inode,
				      struct buffer_head *bh);
3356
extern int ext4_ci_compare(const struct inode *parent,
3357 3358
			   const struct qstr *fname,
			   const struct qstr *entry, bool quick);
3359

3360
#define S_SHIFT 12
3361
static const unsigned char ext4_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = {
3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373
	[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) {
3374
	if (ext4_has_feature_filetype(sb))
3375 3376 3377
		de->file_type = ext4_type_by_mode[(mode & S_IFMT)>>S_SHIFT];
}

3378
/* readpages.c */
3379
extern int ext4_mpage_readpages(struct inode *inode,
3380
		struct readahead_control *rac, struct page *page);
E
Eric Biggers 已提交
3381 3382
extern int __init ext4_init_post_read_processing(void);
extern void ext4_exit_post_read_processing(void);
3383 3384

/* symlink.c */
3385
extern const struct inode_operations ext4_encrypted_symlink_inode_operations;
3386 3387
extern const struct inode_operations ext4_symlink_inode_operations;
extern const struct inode_operations ext4_fast_symlink_inode_operations;
3388

3389 3390
/* sysfs.c */
extern int ext4_register_sysfs(struct super_block *sb);
3391
extern void ext4_unregister_sysfs(struct super_block *sb);
3392 3393 3394
extern int __init ext4_init_sysfs(void);
extern void ext4_exit_sysfs(void);

3395 3396 3397
/* block_validity */
extern void ext4_release_system_zone(struct super_block *sb);
extern int ext4_setup_system_zone(struct super_block *sb);
3398 3399
extern int __init ext4_init_system_zone(void);
extern void ext4_exit_system_zone(void);
3400 3401 3402
extern int ext4_data_block_valid(struct ext4_sb_info *sbi,
				 ext4_fsblk_t start_blk,
				 unsigned int count);
3403 3404
extern int ext4_check_blockref(const char *, unsigned int,
			       struct inode *, __le32 *, unsigned int);
3405

A
Alex Tomas 已提交
3406
/* extents.c */
3407 3408 3409
struct ext4_ext_path;
struct ext4_extent;

Z
Zheng Liu 已提交
3410 3411 3412 3413 3414 3415
/*
 * Maximum number of logical blocks in a file; ext4_extent's ee_block is
 * __le32.
 */
#define EXT_MAX_BLOCKS	0xffffffff

3416
extern void ext4_ext_tree_init(handle_t *handle, struct inode *inode);
3417
extern int ext4_ext_index_trans_blocks(struct inode *inode, int extents);
3418 3419
extern int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
			       struct ext4_map_blocks *map, int flags);
3420
extern int ext4_ext_truncate(handle_t *, struct inode *);
T
Theodore Ts'o 已提交
3421 3422
extern int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
				 ext4_lblk_t end);
A
Alex Tomas 已提交
3423 3424
extern void ext4_ext_init(struct super_block *);
extern void ext4_ext_release(struct super_block *);
3425
extern long ext4_fallocate(struct file *file, int mode, loff_t offset,
A
Amit Arora 已提交
3426
			  loff_t len);
3427 3428
extern int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode,
					  loff_t offset, ssize_t len);
3429 3430
extern int ext4_convert_unwritten_io_end_vec(handle_t *handle,
					     ext4_io_end_t *io_end);
3431 3432
extern int ext4_map_blocks(handle_t *handle, struct inode *inode,
			   struct ext4_map_blocks *map, int flags);
3433 3434 3435 3436
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 *,
3437
				  struct ext4_ext_path **,
3438
				  struct ext4_extent *, int);
3439 3440 3441
extern struct ext4_ext_path *ext4_find_extent(struct inode *, ext4_lblk_t,
					      struct ext4_ext_path **,
					      int flags);
3442 3443
extern void ext4_ext_drop_refs(struct ext4_ext_path *);
extern int ext4_ext_check_inode(struct inode *inode);
3444
extern ext4_lblk_t ext4_ext_next_allocated_block(struct ext4_ext_path *path);
A
Aneesh Kumar K.V 已提交
3445 3446
extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
			__u64 start, __u64 len);
3447 3448 3449
extern int ext4_get_es_cache(struct inode *inode,
			     struct fiemap_extent_info *fieinfo,
			     __u64 start, __u64 len);
3450
extern int ext4_ext_precache(struct inode *inode);
3451 3452 3453 3454
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);
3455
extern int ext4_clu_mapped(struct inode *inode, ext4_lblk_t lclu);
3456
extern int ext4_datasem_ensure_credits(handle_t *handle, struct inode *inode,
3457 3458
				       int check_cred, int restart_cred,
				       int revoke_cred);
3459

3460

3461
/* move_extent.c */
3462 3463 3464 3465
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);
3466 3467 3468 3469
extern int ext4_move_extents(struct file *o_filp, struct file *d_filp,
			     __u64 start_orig, __u64 start_donor,
			     __u64 len, __u64 *moved_len);

3470
/* page-io.c */
3471 3472
extern int __init ext4_init_pageio(void);
extern void ext4_exit_pageio(void);
3473
extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags);
J
Jan Kara 已提交
3474 3475 3476 3477 3478
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);
3479
extern void ext4_end_io_rsv_work(struct work_struct *work);
3480 3481 3482 3483
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,
3484 3485
			       struct writeback_control *wbc,
			       bool keep_towrite);
3486 3487
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
3488

3489 3490 3491
/* mmp.c */
extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);

E
Eric Biggers 已提交
3492 3493 3494
/* verity.c */
extern const struct fsverity_operations ext4_verityops;

3495
/*
3496
 * Add new method to test whether block and inode bitmaps are properly
3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511
 * 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);
}

3512 3513
#define in_range(b, first, len)	((b) >= (first) && (b) <= (first) + (len) - 1)

3514 3515 3516 3517 3518 3519
/* 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];

3520 3521 3522
extern int ext4_resize_begin(struct super_block *sb);
extern void ext4_resize_end(struct super_block *sb);

3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543
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));
	}
}

3544
extern const struct iomap_ops ext4_iomap_ops;
J
Jan Kara 已提交
3545
extern const struct iomap_ops ext4_iomap_overwrite_ops;
3546
extern const struct iomap_ops ext4_iomap_report_ops;
3547

3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560
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);
}

3561 3562
#endif	/* __KERNEL__ */

3563 3564 3565
#define EFSBADCRC	EBADMSG		/* Bad CRC detected */
#define EFSCORRUPTED	EUCLEAN		/* Filesystem is corrupted */

3566
#endif	/* _EXT4_H */