ext4.h 134 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/refcount.h>
21
#include <linux/types.h>
22
#include <linux/blkdev.h>
23
#include <linux/magic.h>
24
#include <linux/jbd2.h>
25
#include <linux/quota.h>
26 27 28 29
#include <linux/rwsem.h>
#include <linux/rbtree.h>
#include <linux/seqlock.h>
#include <linux/mutex.h>
30 31
#include <linux/timer.h>
#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

44
#include <linux/fscrypt.h>
45
#include <linux/fsverity.h>
46

47 48
#include <linux/compiler.h>

49
/*
Shen Feng's avatar
Shen Feng committed
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
#define ASSERT(assert)						\
do {									\
	if (unlikely(!(assert))) {					\
		printk(KERN_EMERG					\
		       "Assertion failure in %s() at %s:%d: '%s'\n",	\
		       __func__, __FILE__, __LINE__, #assert);		\
		BUG();							\
	}								\
} while (0)

112 113 114 115 116 117 118 119 120 121 122 123
/* 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;

124 125 126 127 128
enum SHIFT_DIRECTION {
	SHIFT_LEFT = 0,
	SHIFT_RIGHT,
};

129
/*
130
 * Flags used in mballoc's allocation_context flags field.
131 132 133 134
 *
 * Also used to show what's going on for debugging purposes when the
 * flag field is exported via the traceport interface
 */
135

136
/* prefer goal again. length */
137
#define EXT4_MB_HINT_MERGE		0x0001
138
/* blocks already reserved */
139
#define EXT4_MB_HINT_RESERVED		0x0002
140
/* metadata is being allocated */
141
#define EXT4_MB_HINT_METADATA		0x0004
142
/* first blocks in the file */
143
#define EXT4_MB_HINT_FIRST		0x0008
144
/* search for the best chunk */
145
#define EXT4_MB_HINT_BEST		0x0010
146
/* data is being allocated */
147
#define EXT4_MB_HINT_DATA		0x0020
148
/* don't preallocate (for tails) */
149
#define EXT4_MB_HINT_NOPREALLOC		0x0040
150
/* allocate for locality group */
151
#define EXT4_MB_HINT_GROUP_ALLOC	0x0080
152
/* allocate goal blocks or none */
153
#define EXT4_MB_HINT_GOAL_ONLY		0x0100
154
/* goal is meaningful */
155
#define EXT4_MB_HINT_TRY_GOAL		0x0200
156
/* blocks already pre-reserved by delayed allocation */
157
#define EXT4_MB_DELALLOC_RESERVED	0x0400
158 159
/* We are doing stream allocation */
#define EXT4_MB_STREAM_ALLOC		0x0800
160 161
/* Use reserved root blocks if needed */
#define EXT4_MB_USE_ROOT_BLOCKS		0x1000
Lukas Czerner's avatar
Lukas Czerner committed
162 163
/* Use blocks from reserved pool */
#define EXT4_MB_USE_RESERVED		0x2000
164 165
/* Do strict check for free blocks while retrying block allocation */
#define EXT4_MB_STRICT_CHECK		0x4000
166 167 168 169 170 171
/* Large fragment size list lookup succeeded at least once for cr = 0 */
#define EXT4_MB_CR0_OPTIMIZED		0x8000
/* Avg fragment size rb tree lookup succeeded at least once for cr = 1 */
#define EXT4_MB_CR1_OPTIMIZED		0x00010000
/* Perform linear traversal for one group */
#define EXT4_MB_SEARCH_NEXT_LINEAR	0x00020000
172 173 174
struct ext4_allocation_request {
	/* target inode for block we're allocating */
	struct inode *inode;
175 176
	/* how many blocks we want to allocate */
	unsigned int len;
177 178 179 180 181 182
	/* 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;
183 184 185 186 187
	/* 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 */
188 189
	ext4_fsblk_t pright;
	/* flags. see above EXT4_MB_HINT_* */
190
	unsigned int flags;
191 192
};

193 194 195 196 197 198 199
/*
 * 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.
 */
200 201 202 203
#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)
204
#define EXT4_MAP_FLAGS		(EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
205
				 EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY)
206 207 208 209 210 211 212 213

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

214 215 216 217 218 219 220 221
/*
 * Block validity checking, system zone rbtree.
 */
struct ext4_system_blocks {
	struct rb_root root;
	struct rcu_head rcu;
};

222 223 224 225 226
/*
 * Flags for ext4_io_end->flags
 */
#define	EXT4_IO_END_UNWRITTEN	0x0001

227 228 229 230 231 232
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 */
};

233
/*
234
 * For converting unwritten extents on a work queue. 'handle' is used for
235
 * buffered writeback.
236
 */
237
typedef struct ext4_io_end {
238
	struct list_head	list;		/* per-file finished IO list */
239 240
	handle_t		*handle;	/* handle reserved for extent
						 * conversion */
241
	struct inode		*inode;		/* file being written to */
242 243
	struct bio		*bio;		/* Linked list of completed
						 * bios covering the extent */
244
	unsigned int		flag;		/* unwritten or not */
245
	refcount_t		count;		/* reference counter */
246
	struct list_head	list_vec;	/* list of ext4_io_end_vec */
247 248
} ext4_io_end_t;

249
struct ext4_io_submit {
250
	struct writeback_control *io_wbc;
251 252 253 254 255
	struct bio		*io_bio;
	ext4_io_end_t		*io_end;
	sector_t		io_next_block;
};

256 257 258
/*
 * Special inodes numbers
 */
259 260
#define	EXT4_BAD_INO		 1	/* Bad blocks inode */
#define EXT4_ROOT_INO		 2	/* Root inode */
261 262
#define EXT4_USR_QUOTA_INO	 3	/* User quota inode */
#define EXT4_GRP_QUOTA_INO	 4	/* Group quota inode */
263 264 265 266
#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 */
267

268 269
/* First non-reserved inode for old ext4 filesystems */
#define EXT4_GOOD_OLD_FIRST_INO	11
270 271 272 273

/*
 * Maximal count of links to a file
 */
274
#define EXT4_LINK_MAX		65000
275 276 277 278

/*
 * Macro-instructions used to manage several block sizes
 */
279
#define EXT4_MIN_BLOCK_SIZE		1024
280 281
#define	EXT4_MAX_BLOCK_SIZE		65536
#define EXT4_MIN_BLOCK_LOG_SIZE		10
282
#define EXT4_MAX_BLOCK_LOG_SIZE		16
283
#define EXT4_MAX_CLUSTER_LOG_SIZE	30
284
#ifdef __KERNEL__
285
# define EXT4_BLOCK_SIZE(s)		((s)->s_blocksize)
286
#else
287
# define EXT4_BLOCK_SIZE(s)		(EXT4_MIN_BLOCK_SIZE << (s)->s_log_block_size)
288
#endif
289
#define	EXT4_ADDR_PER_BLOCK(s)		(EXT4_BLOCK_SIZE(s) / sizeof(__u32))
290 291
#define EXT4_CLUSTER_SIZE(s)		(EXT4_BLOCK_SIZE(s) << \
					 EXT4_SB(s)->s_cluster_bits)
292
#ifdef __KERNEL__
293
# define EXT4_BLOCK_SIZE_BITS(s)	((s)->s_blocksize_bits)
294
# define EXT4_CLUSTER_BITS(s)		(EXT4_SB(s)->s_cluster_bits)
295
#else
296
# define EXT4_BLOCK_SIZE_BITS(s)	((s)->s_log_block_size + 10)
297 298
#endif
#ifdef __KERNEL__
299 300 301
#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)
302
#else
303 304
#define EXT4_INODE_SIZE(s)	(((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \
				 EXT4_GOOD_OLD_INODE_SIZE : \
305
				 (s)->s_inode_size)
306 307
#define EXT4_FIRST_INO(s)	(((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \
				 EXT4_GOOD_OLD_FIRST_INO : \
308 309
				 (s)->s_first_ino)
#endif
Amit Arora's avatar
Amit Arora committed
310
#define EXT4_BLOCK_ALIGN(size, blkbits)		ALIGN((size), (1 << (blkbits)))
311 312 313
#define EXT4_MAX_BLOCKS(size, offset, blkbits) \
	((EXT4_BLOCK_ALIGN(size + offset, blkbits) >> blkbits) - (offset >> \
								  blkbits))
314

315 316 317 318 319 320 321
/* 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)
322 323 324 325 326
/* 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))
327 328 329
/* 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))
330 331 332 333 334
/* 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))
335

336 337 338
/*
 * Structure of a blocks group descriptor
 */
339
struct ext4_group_desc
340
{
341
	__le32	bg_block_bitmap_lo;	/* Blocks bitmap block */
342 343
	__le32	bg_inode_bitmap_lo;	/* Inodes bitmap block */
	__le32	bg_inode_table_lo;	/* Inodes table block */
344 345 346
	__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 */
347
	__le16	bg_flags;		/* EXT4_BG_flags (INODE_UNINIT, etc) */
348 349 350
	__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 */
351
	__le16  bg_itable_unused_lo;	/* Unused inodes count */
352
	__le16  bg_checksum;		/* crc16(sb_uuid+group+desc) */
353 354 355
	__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 */
356 357 358
	__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 */
359
	__le16  bg_itable_unused_hi;    /* Unused inodes count MSB */
360 361 362 363
	__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;
364 365
};

366 367 368 369 370 371 372
#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))

373 374 375 376 377
/*
 * Structure of a flex block group info
 */

struct flex_groups {
378 379 380
	atomic64_t	free_clusters;
	atomic_t	free_inodes;
	atomic_t	used_dirs;
381 382
};

383 384 385 386
#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 */

387 388 389
/*
 * Macro-instructions used to manage group descriptors
 */
390
#define EXT4_MIN_DESC_SIZE		32
391
#define EXT4_MIN_DESC_SIZE_64BIT	64
392 393
#define	EXT4_MAX_DESC_SIZE		EXT4_MIN_BLOCK_SIZE
#define EXT4_DESC_SIZE(s)		(EXT4_SB(s)->s_desc_size)
394
#ifdef __KERNEL__
395
# define EXT4_BLOCKS_PER_GROUP(s)	(EXT4_SB(s)->s_blocks_per_group)
396
# define EXT4_CLUSTERS_PER_GROUP(s)	(EXT4_SB(s)->s_clusters_per_group)
397 398 399
# 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)
400
#else
401
# define EXT4_BLOCKS_PER_GROUP(s)	((s)->s_blocks_per_group)
402
# define EXT4_DESC_PER_BLOCK(s)		(EXT4_BLOCK_SIZE(s) / EXT4_DESC_SIZE(s))
403
# define EXT4_INODES_PER_GROUP(s)	((s)->s_inodes_per_group)
404 405 406 407 408
#endif

/*
 * Constants relative to the data blocks
 */
409 410 411 412 413
#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)
414 415 416 417

/*
 * Inode flags
 */
418 419 420 421 422 423 424 425
#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 */
426
/* Reserved for compression usage... */
427 428 429
#define EXT4_DIRTY_FL			0x00000100
#define EXT4_COMPRBLK_FL		0x00000200 /* One or more compressed clusters */
#define EXT4_NOCOMPR_FL			0x00000400 /* Don't compress */
430 431
	/* nb: was previously EXT2_ECOMPR_FL */
#define EXT4_ENCRYPT_FL			0x00000800 /* encrypted file */
432
/* End compression flags --- maybe not all used */
433 434 435 436 437 438
#define EXT4_INDEX_FL			0x00001000 /* hash-indexed directory */
#define EXT4_IMAGIC_FL			0x00002000 /* AFS directory */
#define EXT4_JOURNAL_DATA_FL		0x00004000 /* file data should be journaled */
#define EXT4_NOTAIL_FL			0x00008000 /* file tail should not be merged */
#define EXT4_DIRSYNC_FL			0x00010000 /* dirsync behaviour (directories only) */
#define EXT4_TOPDIR_FL			0x00020000 /* Top of directory hierarchies*/
Aneesh Kumar K.V's avatar
Aneesh Kumar K.V committed
439
#define EXT4_HUGE_FILE_FL               0x00040000 /* Set to each huge file */
440
#define EXT4_EXTENTS_FL			0x00080000 /* Inode uses extents */
441
#define EXT4_VERITY_FL			0x00100000 /* Verity protected inode */
442
#define EXT4_EA_INODE_FL	        0x00200000 /* Inode used for large EA */
443
/* 0x00400000 was formerly EXT4_EOFBLOCKS_FL */
Ira Weiny's avatar
Ira Weiny committed
444 445 446

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

447
#define EXT4_INLINE_DATA_FL		0x10000000 /* Inode has inline data. */
448
#define EXT4_PROJINHERIT_FL		0x20000000 /* Create with parents projid */
449
#define EXT4_CASEFOLD_FL		0x40000000 /* Casefolded directory */
Aneesh Kumar K.V's avatar
Aneesh Kumar K.V committed
450
#define EXT4_RESERVED_FL		0x80000000 /* reserved for ext4 lib */
451

452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479
/* 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)
480

481 482
/* Flags that should be inherited by new inodes from their parent. */
#define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\
483
			   EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
484
			   EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\
Li Xi's avatar
Li Xi committed
485
			   EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL |\
Ira Weiny's avatar
Ira Weiny committed
486 487
			   EXT4_PROJINHERIT_FL | EXT4_CASEFOLD_FL |\
			   EXT4_DAX_FL)
488

489
/* Flags that are appropriate for regular files (all but dir-specific ones). */
490 491
#define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL | EXT4_CASEFOLD_FL |\
			   EXT4_PROJINHERIT_FL))
492 493 494 495

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

496 497 498
/* The only flags that should be swapped */
#define EXT4_FL_SHOULD_SWAP (EXT4_HUGE_FILE_FL | EXT4_EXTENTS_FL)

Ira Weiny's avatar
Ira Weiny committed
499 500
/* Flags which are mutually exclusive to DAX */
#define EXT4_DAX_MUT_EXCL (EXT4_VERITY_FL | EXT4_ENCRYPT_FL |\
501
			   EXT4_JOURNAL_DATA_FL | EXT4_INLINE_DATA_FL)
Ira Weiny's avatar
Ira Weiny committed
502

503 504 505 506 507 508 509 510 511 512 513
/* 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;
}

514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529
/*
 * 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 */
530
	EXT4_INODE_ENCRYPT	= 11,	/* Encrypted file */
531 532 533 534 535 536 537 538 539
/* 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 */
540
	EXT4_INODE_VERITY	= 20,	/* Verity protected inode */
541
	EXT4_INODE_EA_INODE	= 21,	/* Inode used for large EA */
542
/* 22 was formerly EXT4_INODE_EOFBLOCKS */
Ira Weiny's avatar
Ira Weiny committed
543
	EXT4_INODE_DAX		= 25,	/* Inode is DAX */
544
	EXT4_INODE_INLINE_DATA	= 28,	/* Data in inode. */
545
	EXT4_INODE_PROJINHERIT	= 29,	/* Create with parents projid */
546
	EXT4_INODE_CASEFOLD	= 30,	/* Casefolded directory */
547 548 549 550
	EXT4_INODE_RESERVED	= 31,	/* reserved for ext4 lib */
};

/*
551 552 553 554 555 556 557 558 559
 * 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.
560 561 562
 *
 * It's not paranoia if the Murphy's Law really *is* out to get you.  :-)
 */
563 564 565
#define TEST_FLAG_VALUE(FLAG) (EXT4_##FLAG##_FL == (1 << EXT4_INODE_##FLAG))
#define CHECK_FLAG_VALUE(FLAG) BUILD_BUG_ON(!TEST_FLAG_VALUE(FLAG))

566 567 568 569 570 571 572 573 574 575 576 577 578
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);
579
	CHECK_FLAG_VALUE(ENCRYPT);
580 581 582 583 584 585 586 587
	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);
588
	CHECK_FLAG_VALUE(VERITY);
589
	CHECK_FLAG_VALUE(EA_INODE);
590
	CHECK_FLAG_VALUE(INLINE_DATA);
591
	CHECK_FLAG_VALUE(PROJINHERIT);
592
	CHECK_FLAG_VALUE(CASEFOLD);
593 594 595
	CHECK_FLAG_VALUE(RESERVED);
}

596
/* Used to pass group descriptor data when online resize is done */
597
struct ext4_new_group_input {
Dave Kleikamp's avatar
Dave Kleikamp committed
598 599 600 601 602 603
	__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 */
604 605 606
	__u16 unused;
};

607 608 609 610 611 612 613 614 615 616 617 618
#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

619 620
/* The struct ext4_new_group_input in kernel space, with free_blocks_count */
struct ext4_new_group_data {
621
	__u32 group;
Laurent Vivier's avatar
Laurent Vivier committed
622 623 624
	__u64 block_bitmap;
	__u64 inode_bitmap;
	__u64 inode_table;
625 626
	__u32 blocks_count;
	__u16 reserved_blocks;
627 628
	__u16 mdata_blocks;
	__u32 free_clusters_count;
629 630
};

631 632 633 634 635 636 637 638
/* Indexes used to index group tables in ext4_new_group_data */
enum {
	BLOCK_BITMAP = 0,	/* block bitmap */
	INODE_BITMAP,		/* inode bitmap */
	INODE_TABLE,		/* inode tables */
	GROUP_TABLE_COUNT,
};

Amit Arora's avatar
Amit Arora committed
639
/*
640
 * Flags used by ext4_map_blocks()
Amit Arora's avatar
Amit Arora committed
641
 */
642
	/* Allocate any needed blocks and/or convert an unwritten
643
	   extent to be an initialized ext4 */
644
#define EXT4_GET_BLOCKS_CREATE			0x0001
645 646 647
	/* 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|\
648
						 EXT4_GET_BLOCKS_CREATE)
Lukas Czerner's avatar
Lukas Czerner committed
649 650
	/* Caller is from the delayed allocation writeout path
	 * finally doing the actual allocation of delayed blocks */
651
#define EXT4_GET_BLOCKS_DELALLOC_RESERVE	0x0004
652
	/* caller is from the direct IO path, request to creation of an
653
	unwritten extents if not allocated, split the unwritten
654
	extent if blocks has been preallocated already*/
655
#define EXT4_GET_BLOCKS_PRE_IO			0x0008
656
#define EXT4_GET_BLOCKS_CONVERT			0x0010
657
#define EXT4_GET_BLOCKS_IO_CREATE_EXT		(EXT4_GET_BLOCKS_PRE_IO|\
658
					 EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT)
659 660
	/* Convert extent to initialized after IO complete */
#define EXT4_GET_BLOCKS_IO_CONVERT_EXT		(EXT4_GET_BLOCKS_CONVERT|\
661
					 EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT)
Lukas Czerner's avatar
Lukas Czerner committed
662 663 664
	/* 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
665 666
	/* Don't normalize allocation size (used for fallocate) */
#define EXT4_GET_BLOCKS_NO_NORMALIZE		0x0040
667
	/* Convert written extents to unwritten */
668
#define EXT4_GET_BLOCKS_CONVERT_UNWRITTEN	0x0100
669 670 671 672
	/* 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)
673 674 675
	/* Caller will submit data before dropping transaction handle. This
	 * allows jbd2 to avoid submitting data before commit. */
#define EXT4_GET_BLOCKS_IO_SUBMIT		0x0400
676 677
	/* Caller is in the atomic contex, find extent if it has been cached */
#define EXT4_GET_BLOCKS_CACHED_NOWAIT		0x0800
678

679
/*
680
 * The bit position of these flags must not overlap with any of the
681
 * EXT4_GET_BLOCKS_*.  They are used by ext4_find_extent(),
682
 * read_extent_tree_block(), ext4_split_extent_at(),
683 684 685 686
 * 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.
687
 */
688 689
#define EXT4_EX_NOCACHE				0x40000000
#define EXT4_EX_FORCE_CACHE			0x20000000
690
#define EXT4_EX_NOFAIL				0x10000000
691

692 693 694
/*
 * Flags used by ext4_free_blocks
 */
695 696 697 698
#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
699 700
#define EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER	0x0010
#define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER	0x0020
701
#define EXT4_FREE_BLOCKS_RERESERVE_CLUSTER      0x0040
702

703 704 705
/*
 * ioctl commands
 */
706 707 708 709 710 711
#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)
712 713 714
#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)
715
 /* note ioctl 10 reserved for an early version of the FIEMAP ioctl */
716
 /* note ioctl 11 reserved for filesystem-independent FIEMAP ioctl */
717
#define EXT4_IOC_ALLOC_DA_BLKS		_IO('f', 12)
718
#define EXT4_IOC_MOVE_EXT		_IOWR('f', 15, struct move_extent)
719
#define EXT4_IOC_RESIZE_FS		_IOW('f', 16, __u64)
720
#define EXT4_IOC_SWAP_BOOT		_IO('f', 17)
721
#define EXT4_IOC_PRECACHE_EXTENTS	_IO('f', 18)
722 723
/* ioctl codes 19--39 are reserved for fscrypt */
#define EXT4_IOC_CLEAR_ES_CACHE		_IO('f', 40)
724
#define EXT4_IOC_GETSTATE		_IOW('f', 41, __u32)
725
#define EXT4_IOC_GET_ES_CACHE		_IOWR('f', 42, struct fiemap)
726
#define EXT4_IOC_CHECKPOINT		_IOW('f', 43, __u32)
727 728
#define EXT4_IOC_GETFSUUID		_IOR('f', 44, struct fsuuid)
#define EXT4_IOC_SETFSUUID		_IOW('f', 44, struct fsuuid)
729

730
#define EXT4_IOC_SHUTDOWN _IOR ('X', 125, __u32)
731 732 733 734 735 736 737 738

/*
 * 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 */

739 740 741 742 743 744 745 746 747 748
/*
 * 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
749

750 751 752 753 754 755 756 757
/* flags for ioctl EXT4_IOC_CHECKPOINT */
#define EXT4_IOC_CHECKPOINT_FLAG_DISCARD	0x1
#define EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT	0x2
#define EXT4_IOC_CHECKPOINT_FLAG_DRY_RUN	0x4
#define EXT4_IOC_CHECKPOINT_FLAG_VALID		(EXT4_IOC_CHECKPOINT_FLAG_DISCARD | \
						EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT | \
						EXT4_IOC_CHECKPOINT_FLAG_DRY_RUN)

758 759 760 761 762 763 764 765 766
/*
 * Structure for EXT4_IOC_GETFSUUID/EXT4_IOC_SETFSUUID
 */
struct fsuuid {
	__u32       fsu_len;
	__u32       fsu_flags;
	__u8        fsu_uuid[];
};

767
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
768 769 770
/*
 * ioctl commands in 32 bit emulation
 */
771 772 773 774 775
#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)
776
#define EXT4_IOC32_GROUP_ADD		_IOW('f', 8, struct compat_ext4_new_group_input)
777 778
#define EXT4_IOC32_GETVERSION_OLD	FS_IOC32_GETVERSION
#define EXT4_IOC32_SETVERSION_OLD	FS_IOC32_SETVERSION
779
#endif
780

781 782 783 784 785 786
/*
 * 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

787
/* Max physical block we can address w/o extents */
788 789
#define EXT4_MAX_BLOCK_FILE_PHYS	0xFFFFFFFF

790
/* Max logical block we can support */
791
#define EXT4_MAX_LOGICAL_BLOCK		0xFFFFFFFE
792

793 794 795
/*
 * Structure of an inode on the disk
 */
796
struct ext4_inode {
797 798
	__le16	i_mode;		/* File mode */
	__le16	i_uid;		/* Low 16 bits of Owner Uid */
799
	__le32	i_size_lo;	/* Size in bytes */
800
	__le32	i_atime;	/* Access time */
Kalpak Shah's avatar
Kalpak Shah committed
801
	__le32	i_ctime;	/* Inode Change time */
802 803 804 805
	__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 */
806
	__le32	i_blocks_lo;	/* Blocks count */
807 808 809
	__le32	i_flags;	/* File flags */
	union {
		struct {
810
			__le32  l_i_version;
811 812 813 814 815 816 817 818
		} linux1;
		struct {
			__u32  h_i_translator;
		} hurd1;
		struct {
			__u32  m_i_reserved1;
		} masix1;
	} osd1;				/* OS dependent 1 */
819
	__le32	i_block[EXT4_N_BLOCKS];/* Pointers to blocks */
820
	__le32	i_generation;	/* File version (for NFS) */
821
	__le32	i_file_acl_lo;	/* File ACL */
822
	__le32	i_size_high;
823
	__le32	i_obso_faddr;	/* Obsoleted fragment address */
824 825
	union {
		struct {
826
			__le16	l_i_blocks_high; /* were l_i_reserved1 */
827
			__le16	l_i_file_acl_high;
Dave Kleikamp's avatar
Dave Kleikamp committed
828
			__le16	l_i_uid_high;	/* these 2 fields */
829
			__le16	l_i_gid_high;	/* were reserved2[0] */
830 831
			__le16	l_i_checksum_lo;/* crc32c(uuid+inum+inode) LE */
			__le16	l_i_reserved;
832 833
		} linux2;
		struct {
834
			__le16	h_i_reserved1;	/* Obsoleted fragment number/size which are removed in ext4 */
835 836 837 838 839 840
			__u16	h_i_mode_high;
			__u16	h_i_uid_high;
			__u16	h_i_gid_high;
			__u32	h_i_author;
		} hurd2;
		struct {
841
			__le16	h_i_reserved1;	/* Obsoleted fragment number/size which are removed in ext4 */
842
			__le16	m_i_file_acl_high;
843 844 845 846
			__u32	m_i_reserved2[2];
		} masix2;
	} osd2;				/* OS dependent 2 */
	__le16	i_extra_isize;
847
	__le16	i_checksum_hi;	/* crc32c(uuid+inum+inode) BE */
Kalpak Shah's avatar
Kalpak Shah committed
848 849 850 851 852
	__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) */
853
	__le32  i_version_hi;	/* high 32 bits for 64-bit version */
854
	__le32	i_projid;	/* Project ID */
855 856
};

857 858 859 860 861 862 863 864
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 */
};
865

Kalpak Shah's avatar
Kalpak Shah committed
866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885
#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))			\

886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906
/*
 * 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.
 */

907
static inline __le32 ext4_encode_extra_time(struct timespec64 *time)
Kalpak Shah's avatar
Kalpak Shah committed
908
{
909
	u32 extra =((time->tv_sec - (s32)time->tv_sec) >> 32) & EXT4_EPOCH_MASK;
910
	return cpu_to_le32(extra | (time->tv_nsec << EXT4_EPOCH_BITS));
Kalpak Shah's avatar
Kalpak Shah committed
911 912
}

913 914
static inline void ext4_decode_extra_time(struct timespec64 *time,
					  __le32 extra)
Kalpak Shah's avatar
Kalpak Shah committed
915
{
916
	if (unlikely(extra & cpu_to_le32(EXT4_EPOCH_MASK)))
917 918
		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;
Kalpak Shah's avatar
Kalpak Shah committed
919 920
}

921 922 923
#define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode)				\
do {										\
	if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra))     {\
924
		(raw_inode)->xtime = cpu_to_le32((inode)->xtime.tv_sec);	\
925
		(raw_inode)->xtime ## _extra =					\
926
				ext4_encode_extra_time(&(inode)->xtime);	\
927
		}								\
928
	else	\
929
		(raw_inode)->xtime = cpu_to_le32(clamp_t(int32_t, (inode)->xtime.tv_sec, S32_MIN, S32_MAX));	\
Kalpak Shah's avatar
Kalpak Shah committed
930 931 932 933 934 935 936 937 938 939 940
} 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)

941 942 943 944
#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)) {	\
945
		ext4_decode_extra_time(&(inode)->xtime,				\
946 947 948 949
				       raw_inode->xtime ## _extra);		\
		}								\
	else									\
		(inode)->xtime.tv_nsec = 0;					\
Kalpak Shah's avatar
Kalpak Shah committed
950 951
} while (0)

952

Kalpak Shah's avatar
Kalpak Shah committed
953 954 955 956 957
#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);	       \
958 959
	else								       \
		(einode)->xtime.tv_sec = 0;				       \
Kalpak Shah's avatar
Kalpak Shah committed
960 961 962
	if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra))	       \
		ext4_decode_extra_time(&(einode)->xtime,		       \
				       raw_inode->xtime ## _extra);	       \
963 964
	else								       \
		(einode)->xtime.tv_nsec = 0;				       \
Kalpak Shah's avatar
Kalpak Shah committed
965 966
} while (0)

967 968
#define i_disk_version osd1.linux1.l_i_version

969 970
#if defined(__KERNEL__) || defined(__linux__)
#define i_reserved1	osd1.linux1.l_i_reserved1
971
#define i_file_acl_high	osd2.linux2.l_i_file_acl_high
972
#define i_blocks_high	osd2.linux2.l_i_blocks_high
973 974 975 976
#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
977
#define i_checksum_lo	osd2.linux2.l_i_checksum_lo
978 979 980 981 982 983 984 985 986 987 988

#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
989
#define i_file_acl_high	osd2.masix2.m_i_file_acl_high
990 991 992 993
#define i_reserved2	osd2.masix2.m_i_reserved2

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

994
#include "extents_status.h"
995
#include "fast_commit.h"
996

997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019
/*
 * 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,
};


1020 1021 1022 1023 1024 1025
/*
 * fourth extended file system inode data in memory
 */
struct ext4_inode_info {
	__le32	i_data[15];	/* unconverted */
	__u32	i_dtime;
1026
	ext4_fsblk_t	i_file_acl;
1027 1028 1029 1030

	/*
	 * i_block_group is the number of the block group which contains
	 * this file's inode.  Constant across the lifetime of the inode,
1031
	 * it is used for making block allocation decisions - we try to
1032 1033 1034 1035
	 * 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;
1036
	ext4_lblk_t	i_dir_start_lookup;
1037
#if (BITS_PER_LONG < 64)
1038
	unsigned long	i_state_flags;		/* Dynamic state flags */
1039
#endif
1040
	unsigned long	i_flags;
1041 1042 1043

	/*
	 * Extended attributes can be read independently of the main file
1044
	 * data. Taking i_rwsem even when reading would cause contention
1045 1046 1047 1048 1049 1050
	 * 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;

1051 1052 1053 1054 1055 1056 1057 1058
	/*
	 * Inodes with EXT4_STATE_ORPHAN_FILE use i_orphan_idx. Otherwise
	 * i_orphan is used.
	 */
	union {
		struct list_head i_orphan;	/* unlinked but open inodes */
		unsigned int i_orphan_idx;	/* Index in orphan file */
	};
1059

1060 1061
	/* Fast commit related info */

1062 1063
	/* For tracking dentry create updates */
	struct list_head i_fc_dilist;
1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083
	struct list_head i_fc_list;	/*
					 * inodes that need fast commit
					 * protected by sbi->s_fc_lock.
					 */

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

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

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

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

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

1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112
	/*
	 * i_disksize keeps track of what the inode size is ON DISK, not
	 * in memory.  During truncate, i_size is set to the new size by
	 * the VFS prior to calling ext4_truncate(), but the filesystem won't
	 * set i_disksize to 0 until the truncate is actually under way.
	 *
	 * The intent is that i_disksize always represents the blocks which
	 * are used by this file.  This allows recovery to restart truncate
	 * on orphans if we crash during truncate.  We actually write i_disksize
	 * into the on-disk inode when writing inodes out, instead of i_size.
	 *
	 * The only time when i_disksize and i_size may be different is when
	 * a truncate is in progress.  The only things which change i_disksize
	 * are ext4_get_block (growth) and ext4_truncate (shrinkth).
	 */
	loff_t	i_disksize;

	/*
	 * i_data_sem is for serialising ext4_truncate() against
	 * ext4_getblock().  In the 2.4 ext2 design, great chunks of inode's
	 * data tree are chopped off during truncate. We can't do that in
	 * ext4 because whenever we perform intermediate commits during
	 * truncate, the inode and all the metadata blocks *must* be in a
	 * consistent state which allows truncation of the orphans to restart
	 * during recovery.  Hence we must fix the get_block-vs-truncate race
	 * by other means, so we have i_data_sem.
	 */
	struct rw_semaphore i_data_sem;
	struct inode vfs_inode;
1113
	struct jbd2_inode *jinode;
1114

1115 1116
	spinlock_t i_raw_lock;	/* protects updates to the raw inode */

1117 1118
	/*
	 * File creation time. Its function is same as that of
1119
	 * struct timespec64 i_{a,c,m}time in the generic inode.
1120
	 */
1121
	struct timespec64 i_crtime;
1122 1123

	/* mballoc */
1124
	atomic_t i_prealloc_active;
1125 1126 1127
	struct list_head i_prealloc_list;
	spinlock_t i_prealloc_lock;

1128 1129 1130
	/* extents status tree */
	struct ext4_es_tree i_es_tree;
	rwlock_t i_es_lock;
1131
	struct list_head i_es_list;
1132
	unsigned int i_es_all_nr;	/* protected by i_es_lock */
1133
	unsigned int i_es_shk_nr;	/* protected by i_es_lock */
1134 1135 1136
	ext4_lblk_t i_es_shrink_lblk;	/* Offset where we start searching for
					   extents to shrink. Protected by
					   i_es_lock  */
1137

1138 1139 1140 1141
	/* ialloc */
	ext4_group_t	i_last_alloc_group;

	/* allocation reservation info for delalloc */
1142
	/* In case of bigalloc, this refer to clusters rather than blocks */
1143 1144
	unsigned int i_reserved_data_blocks;

1145 1146 1147
	/* pending cluster reservations for bigalloc file systems */
	struct ext4_pending_tree i_pending_tree;

1148 1149 1150
	/* on-disk additional length */
	__u16 i_extra_isize;

1151 1152 1153 1154
	/* Indicate the inline data space. */
	u16 i_inline_off;
	u16 i_inline_size;

1155 1156 1157 1158
#ifdef CONFIG_QUOTA
	/* quota space reservation, managed internally by quota code */
	qsize_t i_reserved_quota;
#endif
1159

1160
	/* Lock protecting lists below */
1161
	spinlock_t i_completed_io_lock;
1162 1163 1164 1165 1166 1167
	/*
	 * 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;
Jan Kara's avatar
Jan Kara committed
1168
	atomic_t i_unwritten; /* Nr. of inflight conversions pending */
1169 1170

	spinlock_t i_block_reservation_lock;
1171 1172 1173 1174 1175 1176 1177

	/*
	 * Transactions that contain inode's metadata needed to complete
	 * fsync and fdatasync, respectively.
	 */
	tid_t i_sync_tid;
	tid_t i_datasync_tid;
1178

1179 1180 1181 1182
#ifdef CONFIG_QUOTA
	struct dquot *i_dquot[MAXQUOTAS];
#endif

1183 1184
	/* Precomputed uuid+inum+igen checksum for seeding inode checksums */
	__u32 i_csum_seed;
1185

Li Xi's avatar
Li Xi committed
1186
	kprojid_t i_projid;
1187 1188
};

1189 1190 1191
/*
 * File system states
 */
1192 1193 1194
#define	EXT4_VALID_FS			0x0001	/* Unmounted cleanly */
#define	EXT4_ERROR_FS			0x0002	/* Errors detected */
#define	EXT4_ORPHAN_FS			0x0004	/* Orphans being recovered */
1195
#define EXT4_FC_REPLAY			0x0020	/* Fast commit replay ongoing */
1196

1197 1198 1199 1200 1201 1202 1203
/*
 * 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 */

1204
/*
1205
 * Mount flags set via mount options or defaults
1206
 */
1207
#define EXT4_MOUNT_NO_MBCACHE		0x00001 /* Do not use mbcache */
1208 1209 1210 1211 1212
#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 */
1213
#define EXT4_MOUNT_ERRORS_MASK		0x00070
1214 1215
#define EXT4_MOUNT_MINIX_DF		0x00080	/* Mimics the Minix statfs */
#define EXT4_MOUNT_NOLOAD		0x00100	/* Don't use existing journal*/
Ross Zwisler's avatar
Ross Zwisler committed
1216
#ifdef CONFIG_FS_DAX
1217
#define EXT4_MOUNT_DAX_ALWAYS		0x00200	/* Direct Access */
Ross Zwisler's avatar
Ross Zwisler committed
1218
#else
1219
#define EXT4_MOUNT_DAX_ALWAYS		0
Ross Zwisler's avatar
Ross Zwisler committed
1220
#endif
1221 1222 1223 1224 1225 1226 1227 1228
#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 */
1229
#define EXT4_MOUNT_NO_AUTO_DA_ALLOC	0x10000	/* No auto delalloc mapping */
1230
#define EXT4_MOUNT_BARRIER		0x20000 /* Use block barriers */
1231 1232 1233 1234 1235 1236 1237 1238 1239
#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 */
1240
#define EXT4_MOUNT_DIOREAD_NOLOCK	0x400000 /* Enable support for dio read nolocking */
1241
#define EXT4_MOUNT_JOURNAL_CHECKSUM	0x800000 /* Journal checksums */
1242
#define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT	0x1000000 /* Journal Async Commit */
1243
#define EXT4_MOUNT_WARN_ON_ERROR	0x2000000 /* Trigger WARN_ON on error */
1244
#define EXT4_MOUNT_NO_PREFETCH_BLOCK_BITMAPS 0x4000000
1245
#define EXT4_MOUNT_DELALLOC		0x8000000 /* Delalloc support */
1246
#define EXT4_MOUNT_DATA_ERR_ABORT	0x10000000 /* Abort on file data write */
1247
#define EXT4_MOUNT_BLOCK_VALIDITY	0x20000000 /* Block validity checking */
1248
#define EXT4_MOUNT_DISCARD		0x40000000 /* Issue DISCARD requests */
1249
#define EXT4_MOUNT_INIT_INODE_TABLE	0x80000000 /* Initialize uninitialized itables */
1250

1251 1252 1253 1254 1255
/*
 * 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.
 */
1256 1257
#define EXT4_MOUNT2_EXPLICIT_DELALLOC	0x00000001 /* User explicitly
						      specified delalloc */
1258 1259 1260
#define EXT4_MOUNT2_STD_GROUP_SIZE	0x00000002 /* We have standard group
						      size of blocksize * 8
						      blocks */
1261 1262
#define EXT4_MOUNT2_HURD_COMPAT		0x00000004 /* Support HURD-castrated
						      file systems */
1263 1264 1265
#define EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM	0x00000008 /* User explicitly
						specified journal checksum */

1266
#define EXT4_MOUNT2_JOURNAL_FAST_COMMIT	0x00000010 /* Journal fast commit */
1267 1268
#define EXT4_MOUNT2_DAX_NEVER		0x00000020 /* Do not allow Direct Access */
#define EXT4_MOUNT2_DAX_INODE		0x00000040 /* For printing options only */
1269 1270 1271
#define EXT4_MOUNT2_MB_OPTIMIZE_SCAN	0x00000080 /* Optimize group
						    * scanning in mballoc
						    */
1272

1273 1274 1275 1276
#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
1277 1278
#define test_opt(sb, opt)		(EXT4_SB(sb)->s_mount_opt & \
					 EXT4_MOUNT_##opt)
1279

1280 1281 1282 1283 1284 1285 1286
#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)

1287 1288
#define ext4_test_and_set_bit		__test_and_set_bit_le
#define ext4_set_bit			__set_bit_le
1289
#define ext4_set_bit_atomic		ext2_set_bit_atomic
1290 1291
#define ext4_test_and_clear_bit		__test_and_clear_bit_le
#define ext4_clear_bit			__clear_bit_le
1292
#define ext4_clear_bit_atomic		ext2_clear_bit_atomic
Akinobu Mita's avatar
Akinobu Mita committed
1293 1294 1295
#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
1296

1297
extern void mb_set_bits(void *bm, int cur, int len);
1298

1299 1300 1301
/*
 * Maximal mount counts between two filesystem checks
 */
1302 1303
#define EXT4_DFL_MAX_MNT_COUNT		20	/* Allow 20 mounts */
#define EXT4_DFL_CHECKINTERVAL		0	/* Don't use interval check */
1304 1305 1306 1307

/*
 * Behaviour when detecting errors
 */
1308 1309 1310 1311
#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
1312

1313 1314 1315
/* Metadata checksum algorithm codes */
#define EXT4_CRC32C_CHKSUM		1

1316 1317
#define EXT4_LABEL_MAX			16

1318 1319 1320
/*
 * Structure of the super block
 */
1321
struct ext4_super_block {
1322
/*00*/	__le32	s_inodes_count;		/* Inodes count */
1323
	__le32	s_blocks_count_lo;	/* Blocks count */
1324 1325
	__le32	s_r_blocks_count_lo;	/* Reserved blocks count */
	__le32	s_free_blocks_count_lo;	/* Free blocks count */
1326 1327 1328
/*10*/	__le32	s_free_inodes_count;	/* Free inodes count */
	__le32	s_first_data_block;	/* First Data Block */
	__le32	s_log_block_size;	/* Block size */
1329
	__le32	s_log_cluster_size;	/* Allocation cluster size */
1330
/*20*/	__le32	s_blocks_per_group;	/* # Blocks per group */
1331
	__le32	s_clusters_per_group;	/* # Clusters per group */
1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347
	__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 */
	/*
1348
	 * These fields are for EXT4_DYNAMIC_REV superblocks only.
1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360
	 *
	 * 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 */
1361
	__le16  s_inode_size;		/* size of inode structure */
1362 1363 1364 1365 1366
	__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 */
1367
/*78*/	char	s_volume_name[EXT4_LABEL_MAX];	/* volume name */
1368
/*88*/	char	s_last_mounted[64] __nonstring;	/* directory where last mounted */
1369 1370 1371
/*C8*/	__le32	s_algorithm_usage_bitmap; /* For compression */
	/*
	 * Performance hints.  Directory preallocation should only
1372
	 * happen if the EXT4_FEATURE_COMPAT_DIR_PREALLOC flag is on.
1373 1374 1375 1376 1377
	 */
	__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 */
	/*
1378
	 * Journaling support valid if EXT4_FEATURE_COMPAT_HAS_JOURNAL set.
1379 1380 1381 1382 1383 1384 1385
	 */
/*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 */
1386
	__u8	s_jnl_backup_type;
1387
	__le16  s_desc_size;		/* size of group descriptor */
Laurent Vivier's avatar
Laurent Vivier committed
1388
/*100*/	__le32	s_default_mount_opts;
1389
	__le32	s_first_meta_bg;	/* First metablock block group */
Laurent Vivier's avatar
Laurent Vivier committed
1390 1391 1392 1393 1394 1395
	__le32	s_mkfs_time;		/* When the filesystem was created */
	__le32	s_jnl_blocks[17];	/* Backup of the journal inode */
	/* 64bit support valid if EXT4_FEATURE_COMPAT_64BIT */
/*150*/	__le32	s_blocks_count_hi;	/* Blocks count */
	__le32	s_r_blocks_count_hi;	/* Reserved blocks count */
	__le32	s_free_blocks_count_hi;	/* Free blocks count */
Aneesh Kumar K.V's avatar
Aneesh Kumar K.V committed
1396 1397 1398 1399
	__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 */
1400
	__le16  s_mmp_update_interval;  /* # seconds to wait in MMP checking */
Aneesh Kumar K.V's avatar
Aneesh Kumar K.V committed
1401 1402
	__le64  s_mmp_block;            /* Block for multi-mount protection */
	__le32  s_raid_stripe_width;    /* blocks on all data disks (N*stride)*/
1403
	__u8	s_log_groups_per_flex;  /* FLEX_BG group size */
1404
	__u8	s_checksum_type;	/* metadata checksum algorithm used */
1405 1406
	__u8	s_encryption_level;	/* versioning level for encryption */
	__u8	s_reserved_pad;		/* Padding to next 32bits */
1407
	__le64	s_kbytes_written;	/* nr of lifetime kilobytes written */
1408 1409 1410 1411 1412 1413
	__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 */
1414 1415 1416 1417 1418
#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 */
1419
	__u8	s_first_error_func[32] __nonstring;	/* function where the error happened */
1420 1421 1422 1423 1424
	__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 */
1425
	__u8	s_last_error_func[32] __nonstring;	/* function where the error happened */
1426 1427
#define EXT4_S_ERR_END offsetof(struct ext4_super_block, s_mount_opts)
	__u8	s_mount_opts[64];
1428 1429 1430
	__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 */
1431
	__le32	s_backup_bgs[2];	/* groups with sparse_super2 SBs */
1432
	__u8	s_encrypt_algos[4];	/* Encryption algorithms in use  */
1433 1434
	__u8	s_encrypt_pw_salt[16];	/* Salt used for string2key algorithm */
	__le32	s_lpf_ino;		/* Location of the lost+found inode */
1435
	__le32	s_prj_quota_inum;	/* inode for tracking project quota */
1436
	__le32	s_checksum_seed;	/* crc32c(uuid) if csum_seed set */
1437 1438 1439 1440 1441 1442
	__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;
1443 1444
	__u8	s_first_error_errcode;
	__u8    s_last_error_errcode;
1445 1446
	__le16  s_encoding;		/* Filename charset encoding */
	__le16  s_encoding_flags;	/* Filename charset encoding flags */
1447 1448
	__le32  s_orphan_file_inum;	/* Inode for tracking orphan inodes */
	__le32	s_reserved[94];		/* Padding to the end of the block */
1449
	__le32	s_checksum;		/* crc32c(superblock) */
1450 1451
};

1452 1453
#define EXT4_S_ERR_LEN (EXT4_S_ERR_END - EXT4_S_ERR_START)

1454
#ifdef __KERNEL__
1455

Jan Kara's avatar
Jan Kara committed
1456
/* Number of quota types we support */
Li Xi's avatar
Li Xi committed
1457
#define EXT4_MAXQUOTAS 3
Jan Kara's avatar
Jan Kara committed
1458

1459 1460
#define EXT4_ENC_UTF8_12_1	1

1461 1462
/* Types of ext4 journal triggers */
enum ext4_journal_trigger_type {
1463
	EXT4_JTR_ORPHAN_FILE,
1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479
	EXT4_JTR_NONE	/* This must be the last entry for indexing to work! */
};

#define EXT4_JOURNAL_TRIGGER_COUNT EXT4_JTR_NONE

struct ext4_journal_trigger {
	struct jbd2_buffer_trigger_type tr_triggers;
	struct super_block *sb;
};

static inline struct ext4_journal_trigger *EXT4_TRIGGER(
				struct jbd2_buffer_trigger_type *trigger)
{
	return container_of(trigger, struct ext4_journal_trigger, tr_triggers);
}

1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494
#define EXT4_ORPHAN_BLOCK_MAGIC 0x0b10ca04

/* Structure at the tail of orphan block */
struct ext4_orphan_block_tail {
	__le32 ob_magic;
	__le32 ob_checksum;
};

static inline int ext4_inodes_per_orphan_block(struct super_block *sb)
{
	return (sb->s_blocksize - sizeof(struct ext4_orphan_block_tail)) /
			sizeof(u32);
}

struct ext4_orphan_block {
1495
	atomic_t ob_free_entries;	/* Number of free orphan entries in block */
1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508
	struct buffer_head *ob_bh;	/* Buffer for orphan block */
};

/*
 * Info about orphan file.
 */
struct ext4_orphan_info {
	int of_blocks;			/* Number of orphan blocks in a file */
	__u32 of_csum_seed;		/* Checksum seed for orphan file */
	struct ext4_orphan_block *of_binfo;	/* Array with info about orphan
						 * file blocks */
};

1509 1510 1511 1512 1513 1514 1515
/*
 * 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 */
1516
	unsigned long s_clusters_per_group; /* Number of clusters in a group */
1517 1518 1519 1520 1521
	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 */
1522
	ext4_group_t s_blockfile_groups;/* Groups acceptable for non-extent files */
1523
	unsigned long s_overhead;  /* # of fs overhead clusters */
1524 1525
	unsigned int s_cluster_ratio;	/* Number of blocks per cluster */
	unsigned int s_cluster_bits;	/* log2 of s_cluster_ratio */
1526 1527 1528
	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 */
1529
	struct buffer_head * __rcu *s_group_desc;
1530
	unsigned int s_mount_opt;
1531
	unsigned int s_mount_opt2;
1532
	unsigned long s_mount_flags;
1533
	unsigned int s_def_mount_opt;
1534
	ext4_fsblk_t s_sb_block;
Lukas Czerner's avatar
Lukas Czerner committed
1535
	atomic64_t s_resv_clusters;
1536 1537
	kuid_t s_resuid;
	kgid_t s_resgid;
1538 1539 1540 1541 1542 1543 1544
	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;
1545
	unsigned int s_inode_goal;
1546 1547
	u32 s_hash_seed[4];
	int s_def_hash_version;
1548
	int s_hash_unsigned;	/* 3 if hash should be unsigned, 0 if not */
1549
	struct percpu_counter s_freeclusters_counter;
1550 1551
	struct percpu_counter s_freeinodes_counter;
	struct percpu_counter s_dirs_counter;
1552
	struct percpu_counter s_dirtyclusters_counter;
1553
	struct percpu_counter s_sra_exceeded_retry_limit;
1554 1555 1556 1557
	struct blockgroup_lock *s_blockgroup_lock;
	struct proc_dir_entry *s_proc;
	struct kobject s_kobj;
	struct completion s_kobj_unregister;
1558
	struct super_block *s_sb;
1559
	struct buffer_head *s_mmp_bh;
1560 1561 1562

	/* Journaling */
	struct journal_s *s_journal;
1563
	unsigned long s_ext4_flags;		/* Ext4 superblock flags */
1564 1565 1566 1567
	struct mutex s_orphan_lock;	/* Protects on disk list changes */
	struct list_head s_orphan;	/* List of orphaned inodes in on disk
					   list */
	struct ext4_orphan_info s_orphan_info;
1568 1569 1570
	unsigned long s_commit_interval;
	u32 s_max_batch_time;
	u32 s_min_batch_time;
1571
	struct block_device *s_journal_bdev;
1572
#ifdef CONFIG_QUOTA
1573 1574
	/* Names of quota files with journalled quota */
	char __rcu *s_qf_names[EXT4_MAXQUOTAS];
1575 1576 1577
	int s_jquota_fmt;			/* Format of quota to use */
#endif
	unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */
1578
	struct ext4_system_blocks __rcu *s_system_blks;
1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590

#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 */
1591
	struct ext4_group_info ** __rcu *s_group_info;
1592 1593 1594 1595
	struct inode *s_buddy_cache;
	spinlock_t s_md_lock;
	unsigned short *s_mb_offsets;
	unsigned int *s_mb_maxs;
1596
	unsigned int s_group_info_size;
1597
	unsigned int s_mb_free_pending;
1598 1599
	struct list_head s_freed_data_list;	/* List of blocks to be freed
						   after commit completed */
1600 1601
	struct list_head s_discard_list;
	struct work_struct s_discard_work;
1602
	atomic_t s_retry_alloc_pending;
1603 1604 1605 1606
	struct rb_root s_mb_avg_fragment_size_root;
	rwlock_t s_mb_rb_lock;
	struct list_head *s_mb_largest_free_orders;
	rwlock_t *s_mb_largest_free_orders_locks;
1607 1608 1609

	/* tunables */
	unsigned long s_stripe;
1610
	unsigned int s_mb_max_linear_groups;
1611 1612 1613 1614 1615 1616
	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;
1617
	unsigned int s_mb_max_inode_prealloc;
1618
	unsigned int s_max_dir_size_kb;
1619 1620 1621
	/* where last allocation was done - for stream allocation */
	unsigned long s_mb_last_group;
	unsigned long s_mb_last_start;
1622 1623
	unsigned int s_mb_prefetch;
	unsigned int s_mb_prefetch_limit;
1624 1625 1626 1627 1628 1629

	/* 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 */
1630
	atomic_t s_bal_groups_scanned;	/* number of groups scanned */
1631 1632 1633
	atomic_t s_bal_goals;	/* goal hits */
	atomic_t s_bal_breaks;	/* too long searches */
	atomic_t s_bal_2orders;	/* 2^order hits */
1634 1635
	atomic_t s_bal_cr0_bad_suggestions;
	atomic_t s_bal_cr1_bad_suggestions;
1636 1637 1638
	atomic64_t s_bal_cX_groups_considered[4];
	atomic64_t s_bal_cX_hits[4];
	atomic64_t s_bal_cX_failed[4];		/* cX loop didn't find blocks */
1639 1640
	atomic_t s_mb_buddies_generated;	/* number of buddies generated */
	atomic64_t s_mb_generation_time;
1641 1642 1643
	atomic_t s_mb_lost_chunks;
	atomic_t s_mb_preallocated;
	atomic_t s_mb_discarded;
1644
	atomic_t s_lock_busy;
1645 1646

	/* locality groups */
1647
	struct ext4_locality_group __percpu *s_locality_groups;
1648 1649 1650 1651 1652

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

1653 1654 1655
	/* the size of zero-out chunk */
	unsigned int s_extent_max_zeroout_kb;

1656
	unsigned int s_log_groups_per_flex;
1657
	struct flex_groups * __rcu *s_flex_groups;
1658
	ext4_group_t s_flex_groups_allocated;
1659

1660 1661
	/* workqueue for reserved extent conversions (buffered io) */
	struct workqueue_struct *rsv_conversion_wq;
1662 1663 1664

	/* timer for periodic error stats printing */
	struct timer_list s_err_report;
1665 1666 1667 1668 1669

	/* Lazy inode table initialization info */
	struct ext4_li_request *s_li_request;
	/* Wait multiplier for lazy initialization thread */
	unsigned int s_li_wait_mult;
1670 1671 1672

	/* Kernel thread for multiple mount protection */
	struct task_struct *s_mmp_tsk;
1673 1674

	/* record the last minlen when FITRIM is called. */
1675
	unsigned long s_last_trim_minblks;
1676 1677 1678

	/* Reference to checksum algorithm driver via cryptoapi */
	struct crypto_shash *s_chksum_driver;
1679 1680 1681

	/* Precomputed FS UUID checksum for seeding other checksums */
	__u32 s_csum_seed;
1682 1683 1684

	/* Reclaim extents from extent status tree */
	struct shrinker s_es_shrinker;
1685
	struct list_head s_es_list;	/* List of inodes with reclaimable extents */
1686
	long s_es_nr_inode;
1687
	struct ext4_es_stats s_es_stats;
1688
	struct mb_cache *s_ea_block_cache;
1689
	struct mb_cache *s_ea_inode_cache;
1690
	spinlock_t s_es_lock ____cacheline_aligned_in_smp;
1691

1692 1693 1694
	/* Journal triggers for checksum computation */
	struct ext4_journal_trigger s_journal_triggers[EXT4_JOURNAL_TRIGGER_COUNT];

1695 1696 1697 1698
	/* Ratelimit ext4 messages. */
	struct ratelimit_state s_err_ratelimit_state;
	struct ratelimit_state s_warning_ratelimit_state;
	struct ratelimit_state s_msg_ratelimit_state;
1699 1700
	atomic_t s_warning_count;
	atomic_t s_msg_count;
1701

1702 1703
	/* Encryption policy for '-o test_dummy_encryption' */
	struct fscrypt_dummy_policy s_dummy_enc_policy;
1704

1705 1706 1707 1708
	/*
	 * Barrier between writepages ops and changing any inode's JOURNAL_DATA
	 * or EXTENTS flag.
	 */
1709
	struct percpu_rw_semaphore s_writepages_rwsem;
1710
	struct dax_device *s_daxdev;
1711
	u64 s_dax_part_off;
1712 1713 1714
#ifdef CONFIG_EXT4_DEBUG
	unsigned long s_simulate_fail;
#endif
1715 1716 1717
	/* Record the errseq of the backing block device */
	errseq_t s_bdev_wb_err;
	spinlock_t s_bdev_wb_lock;
1718

1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739
	/* Information about errors that happened during this mount */
	spinlock_t s_error_lock;
	int s_add_error_count;
	int s_first_error_code;
	__u32 s_first_error_line;
	__u32 s_first_error_ino;
	__u64 s_first_error_block;
	const char *s_first_error_func;
	time64_t s_first_error_time;
	int s_last_error_code;
	__u32 s_last_error_line;
	__u32 s_last_error_ino;
	__u64 s_last_error_block;
	const char *s_last_error_func;
	time64_t s_last_error_time;
	/*
	 * If we are in a context where we cannot update error information in
	 * the on-disk superblock, we queue this work to do it.
	 */
	struct work_struct s_error_work;

1740
	/* Ext4 fast commit sub transaction ID */
1741
	atomic_t s_fc_subtid;
1742

1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761
	/*
	 * After commit starts, the main queue gets locked, and the further
	 * updates get added in the staging queue.
	 */
#define FC_Q_MAIN	0
#define FC_Q_STAGING	1
	struct list_head s_fc_q[2];	/* Inodes staged for fast commit
					 * that have data changes in them.
					 */
	struct list_head s_fc_dentry_q[2];	/* directory entry updates */
	unsigned int s_fc_bytes;
	/*
	 * Main fast commit lock. This lock protects accesses to the
	 * following fields:
	 * ei->i_fc_list, s_fc_dentry_q, s_fc_q, s_fc_bytes, s_fc_bh.
	 */
	spinlock_t s_fc_lock;
	struct buffer_head *s_fc_bh;
	struct ext4_fc_stats s_fc_stats;
1762
	tid_t s_fc_ineligible_tid;
1763 1764 1765 1766
#ifdef CONFIG_EXT4_DEBUG
	int s_fc_debug_max_replay;
#endif
	struct ext4_fc_replay_state s_fc_replay_state;
1767 1768
};

1769
static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
1770 1771 1772
{
	return sb->s_fs_info;
}
1773
static inline struct ext4_inode_info *EXT4_I(struct inode *inode)
1774
{
1775
	return container_of(inode, struct ext4_inode_info, vfs_inode);
1776 1777
}

1778
static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
1779
{
1780 1781 1782
	return ino == EXT4_ROOT_INO ||
		(ino >= EXT4_FIRST_INO(sb) &&
		 ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
1783
}
1784

1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801
/*
 * 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;								   \
})

1802 1803 1804 1805 1806 1807
/*
 * run-time mount flags
 */
enum {
	EXT4_MF_MNTDIR_SAMPLED,
	EXT4_MF_FS_ABORTED,	/* Fatal error detected */
1808
	EXT4_MF_FC_INELIGIBLE	/* Fast commit ineligible */
1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826
};

static inline void ext4_set_mount_flag(struct super_block *sb, int bit)
{
	set_bit(bit, &EXT4_SB(sb)->s_mount_flags);
}

static inline void ext4_clear_mount_flag(struct super_block *sb, int bit)
{
	clear_bit(bit, &EXT4_SB(sb)->s_mount_flags);
}

static inline int ext4_test_mount_flag(struct super_block *sb, int bit)
{
	return test_bit(bit, &EXT4_SB(sb)->s_mount_flags);
}


1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860
/*
 * 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);
}

1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886
/*
 * 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

1887 1888 1889 1890 1891 1892 1893 1894 1895 1896
/*
 * 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 */
1897
	EXT4_STATE_NEWENTRY,		/* File just added to dir */
1898
	EXT4_STATE_MAY_INLINE_DATA,	/* may have in-inode data */
1899
	EXT4_STATE_EXT_PRECACHED,	/* extents have been precached */
1900
	EXT4_STATE_LUSTRE_EA_INODE,	/* Lustre-style ea_inode */
1901
	EXT4_STATE_VERITY_IN_PROGRESS,	/* building fs-verity Merkle tree */
1902
	EXT4_STATE_FC_COMMITTING,	/* Fast commit ongoing */
1903
	EXT4_STATE_ORPHAN_FILE,		/* Inode orphaned in orphan file */
1904 1905
};

1906
#define EXT4_INODE_BIT_FNS(name, field, offset)				\
1907 1908
static inline int ext4_test_inode_##name(struct inode *inode, int bit)	\
{									\
1909
	return test_bit(bit + (offset), &EXT4_I(inode)->i_##field);	\
1910 1911 1912
}									\
static inline void ext4_set_inode_##name(struct inode *inode, int bit)	\
{									\
1913
	set_bit(bit + (offset), &EXT4_I(inode)->i_##field);		\
1914 1915 1916
}									\
static inline void ext4_clear_inode_##name(struct inode *inode, int bit) \
{									\
1917
	clear_bit(bit + (offset), &EXT4_I(inode)->i_##field);		\
1918 1919
}

1920 1921 1922 1923 1924
/* 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);
1925
EXT4_INODE_BIT_FNS(flag, flags, 0)
1926 1927 1928 1929 1930 1931

/* 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);
1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946
#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
1947
#else
1948
/* Assume that user mode programs are passing in an ext4fs superblock, not
1949 1950
 * a kernel struct super_block.  This will allow us to call the feature-test
 * macros from user land. */
1951
#define EXT4_SB(sb)	(sb)
1952 1953
#endif

1954 1955 1956 1957 1958 1959
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);
}

1960
#define NEXT_ORPHAN(inode) EXT4_I(inode)->i_dtime
1961 1962 1963 1964

/*
 * Codes for operating systems
 */
1965 1966 1967 1968 1969
#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
1970 1971 1972 1973

/*
 * Revision levels
 */
1974 1975
#define EXT4_GOOD_OLD_REV	0	/* The good old (original) format */
#define EXT4_DYNAMIC_REV	1	/* V2 format w/ dynamic inode sizes */
1976

1977
#define EXT4_MAX_SUPP_REV	EXT4_DYNAMIC_REV
1978

1979
#define EXT4_GOOD_OLD_INODE_SIZE 128
1980

1981 1982 1983 1984
#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

1985 1986 1987 1988
/*
 * Feature set definitions
 */

1989 1990 1991 1992 1993 1994
#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
1995
#define EXT4_FEATURE_COMPAT_SPARSE_SUPER2	0x0200
1996 1997 1998 1999 2000 2001 2002
/*
 * The reason why "FAST_COMMIT" is a compat feature is that, FS becomes
 * incompatible only if fast commit blocks are present in the FS. Since we
 * clear the journal (and thus the fast commit blocks), we don't mark FS as
 * incompatible. We also have a JBD2 incompat feature, which gets set when
 * there are fast commit blocks present in the journal.
 */
2003
#define EXT4_FEATURE_COMPAT_FAST_COMMIT		0x0400
2004
#define EXT4_FEATURE_COMPAT_STABLE_INODES	0x0800
2005
#define EXT4_FEATURE_COMPAT_ORPHAN_FILE		0x1000	/* Orphan file exists */
2006 2007 2008 2009

#define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER	0x0001
#define EXT4_FEATURE_RO_COMPAT_LARGE_FILE	0x0002
#define EXT4_FEATURE_RO_COMPAT_BTREE_DIR	0x0004
2010
#define EXT4_FEATURE_RO_COMPAT_HUGE_FILE        0x0008
2011
#define EXT4_FEATURE_RO_COMPAT_GDT_CSUM		0x0010
2012
#define EXT4_FEATURE_RO_COMPAT_DIR_NLINK	0x0020
Kalpak Shah's avatar
Kalpak Shah committed
2013
#define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE	0x0040
2014
#define EXT4_FEATURE_RO_COMPAT_QUOTA		0x0100
2015
#define EXT4_FEATURE_RO_COMPAT_BIGALLOC		0x0200
2016 2017 2018 2019 2020 2021
/*
 * 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.
 */
2022
#define EXT4_FEATURE_RO_COMPAT_METADATA_CSUM	0x0400
2023
#define EXT4_FEATURE_RO_COMPAT_READONLY		0x1000
2024
#define EXT4_FEATURE_RO_COMPAT_PROJECT		0x2000
2025
#define EXT4_FEATURE_RO_COMPAT_VERITY		0x8000
2026 2027
#define EXT4_FEATURE_RO_COMPAT_ORPHAN_PRESENT	0x10000 /* Orphan file may be
							   non-empty */
2028 2029 2030 2031 2032 2033

#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
2034
#define EXT4_FEATURE_INCOMPAT_EXTENTS		0x0040 /* extents support */
Laurent Vivier's avatar
Laurent Vivier committed
2035
#define EXT4_FEATURE_INCOMPAT_64BIT		0x0080
2036
#define EXT4_FEATURE_INCOMPAT_MMP               0x0100
2037
#define EXT4_FEATURE_INCOMPAT_FLEX_BG		0x0200
2038 2039
#define EXT4_FEATURE_INCOMPAT_EA_INODE		0x0400 /* EA in inode */
#define EXT4_FEATURE_INCOMPAT_DIRDATA		0x1000 /* data in dirent */
2040
#define EXT4_FEATURE_INCOMPAT_CSUM_SEED		0x2000
2041
#define EXT4_FEATURE_INCOMPAT_LARGEDIR		0x4000 /* >2GB or 3-lvl htree */
2042
#define EXT4_FEATURE_INCOMPAT_INLINE_DATA	0x8000 /* data in inode */
2043
#define EXT4_FEATURE_INCOMPAT_ENCRYPT		0x10000
2044
#define EXT4_FEATURE_INCOMPAT_CASEFOLD		0x20000
2045

2046 2047
extern void ext4_update_dynamic_rev(struct super_block *sb);

2048 2049 2050 2051 2052 2053 2054 2055
#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) \
{ \
2056
	ext4_update_dynamic_rev(sb); \
2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073
	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) \
{ \
2074
	ext4_update_dynamic_rev(sb); \
2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091
	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) \
{ \
2092
	ext4_update_dynamic_rev(sb); \
2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108
	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)
2109
EXT4_FEATURE_COMPAT_FUNCS(fast_commit,		FAST_COMMIT)
2110
EXT4_FEATURE_COMPAT_FUNCS(stable_inodes,	STABLE_INODES)
2111
EXT4_FEATURE_COMPAT_FUNCS(orphan_file,		ORPHAN_FILE)
2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124

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)
2125
EXT4_FEATURE_RO_COMPAT_FUNCS(verity,		VERITY)
2126
EXT4_FEATURE_RO_COMPAT_FUNCS(orphan_present,	ORPHAN_PRESENT)
2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142

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)
2143
EXT4_FEATURE_INCOMPAT_FUNCS(casefold,		CASEFOLD)
2144

2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159
#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)

2160 2161
#define EXT4_FEATURE_COMPAT_SUPP	(EXT4_FEATURE_COMPAT_EXT_ATTR| \
					 EXT4_FEATURE_COMPAT_ORPHAN_FILE)
2162 2163
#define EXT4_FEATURE_INCOMPAT_SUPP	(EXT4_FEATURE_INCOMPAT_FILETYPE| \
					 EXT4_FEATURE_INCOMPAT_RECOVER| \
2164
					 EXT4_FEATURE_INCOMPAT_META_BG| \
Laurent Vivier's avatar
Laurent Vivier committed
2165
					 EXT4_FEATURE_INCOMPAT_EXTENTS| \
2166
					 EXT4_FEATURE_INCOMPAT_64BIT| \
2167
					 EXT4_FEATURE_INCOMPAT_FLEX_BG| \
Andreas Dilger's avatar
Andreas Dilger committed
2168
					 EXT4_FEATURE_INCOMPAT_EA_INODE| \
2169 2170
					 EXT4_FEATURE_INCOMPAT_MMP | \
					 EXT4_FEATURE_INCOMPAT_INLINE_DATA | \
2171
					 EXT4_FEATURE_INCOMPAT_ENCRYPT | \
2172
					 EXT4_FEATURE_INCOMPAT_CASEFOLD | \
2173 2174
					 EXT4_FEATURE_INCOMPAT_CSUM_SEED | \
					 EXT4_FEATURE_INCOMPAT_LARGEDIR)
2175 2176
#define EXT4_FEATURE_RO_COMPAT_SUPP	(EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
					 EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \
2177
					 EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \
2178
					 EXT4_FEATURE_RO_COMPAT_DIR_NLINK | \
Kalpak Shah's avatar
Kalpak Shah committed
2179
					 EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \
2180
					 EXT4_FEATURE_RO_COMPAT_BTREE_DIR |\
2181
					 EXT4_FEATURE_RO_COMPAT_HUGE_FILE |\
2182
					 EXT4_FEATURE_RO_COMPAT_BIGALLOC |\
2183
					 EXT4_FEATURE_RO_COMPAT_METADATA_CSUM|\
Li Xi's avatar
Li Xi committed
2184
					 EXT4_FEATURE_RO_COMPAT_QUOTA |\
2185
					 EXT4_FEATURE_RO_COMPAT_PROJECT |\
2186 2187
					 EXT4_FEATURE_RO_COMPAT_VERITY |\
					 EXT4_FEATURE_RO_COMPAT_ORPHAN_PRESENT)
2188

2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222
#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);
}

2223 2224
extern int ext4_feature_set_ok(struct super_block *sb, int readonly);

2225 2226 2227 2228
/*
 * Superblock flags
 */
#define EXT4_FLAGS_RESIZING	0
2229
#define EXT4_FLAGS_SHUTDOWN	1
2230
#define EXT4_FLAGS_BDEV_IS_DAX	2
2231 2232 2233 2234 2235

static inline int ext4_forced_shutdown(struct ext4_sb_info *sbi)
{
	return test_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
}
2236

2237 2238 2239
/*
 * Default values for user and/or group using reserved blocks
 */
2240 2241
#define	EXT4_DEF_RESUID		0
#define	EXT4_DEF_RESGID		0
2242

Li Xi's avatar
Li Xi committed
2243 2244 2245 2246 2247
/*
 * Default project ID
 */
#define	EXT4_DEF_PROJID		0

2248 2249
#define EXT4_DEF_INODE_READAHEAD_BLKS	32

2250 2251 2252
/*
 * Default mount options
 */
2253 2254 2255 2256 2257 2258 2259 2260 2261
#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
2262 2263 2264 2265
#define EXT4_DEFM_NOBARRIER	0x0100
#define EXT4_DEFM_BLOCK_VALIDITY 0x0200
#define EXT4_DEFM_DISCARD	0x0400
#define EXT4_DEFM_NODELALLOC	0x0800
2266

2267 2268 2269 2270 2271 2272
/*
 * Default journal batch times
 */
#define EXT4_DEF_MIN_BATCH_TIME	0
#define EXT4_DEF_MAX_BATCH_TIME	15000 /* 15ms */

2273 2274 2275 2276 2277 2278
/*
 * 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

2279 2280 2281
/*
 * Structure of a directory entry
 */
2282
#define EXT4_NAME_LEN 255
2283 2284 2285 2286
/*
 * Base length of the ext4 directory entry excluding the name length
 */
#define EXT4_BASE_DIR_LEN (sizeof(struct ext4_dir_entry_2) - EXT4_NAME_LEN)
2287

2288
struct ext4_dir_entry {
2289 2290 2291
	__le32	inode;			/* Inode number */
	__le16	rec_len;		/* Directory entry length */
	__le16	name_len;		/* Name length */
2292
	char	name[EXT4_NAME_LEN];	/* File name */
2293 2294
};

2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305

/*
 * Encrypted Casefolded entries require saving the hash on disk. This structure
 * followed ext4_dir_entry_2's name[name_len] at the next 4 byte aligned
 * boundary.
 */
struct ext4_dir_entry_hash {
	__le32 hash;
	__le32 minor_hash;
};

2306
/*
2307
 * The new version of the directory entry.  Since EXT4 structures are
2308 2309 2310 2311
 * 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.
 */
2312
struct ext4_dir_entry_2 {
2313 2314 2315
	__le32	inode;			/* Inode number */
	__le16	rec_len;		/* Directory entry length */
	__u8	name_len;		/* Name length */
2316
	__u8	file_type;		/* See file type macros EXT4_FT_* below */
2317
	char	name[EXT4_NAME_LEN];	/* File name */
2318 2319
};

2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335
/*
 * Access the hashes at the end of ext4_dir_entry_2
 */
#define EXT4_DIRENT_HASHES(entry) \
	((struct ext4_dir_entry_hash *) \
		(((void *)(entry)) + \
		((8 + (entry)->name_len + EXT4_DIR_ROUND) & ~EXT4_DIR_ROUND)))
#define EXT4_DIRENT_HASH(entry) le32_to_cpu(EXT4_DIRENT_HASHES(de)->hash)
#define EXT4_DIRENT_MINOR_HASH(entry) \
		le32_to_cpu(EXT4_DIRENT_HASHES(de)->minor_hash)

static inline bool ext4_hash_in_dirent(const struct inode *inode)
{
	return IS_CASEFOLDED(inode) && IS_ENCRYPTED(inode);
}

2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347
/*
 * 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) */
};

2348 2349 2350 2351 2352
#define EXT4_DIRENT_TAIL(block, blocksize) \
	((struct ext4_dir_entry_tail *)(((void *)(block)) + \
					((blocksize) - \
					 sizeof(struct ext4_dir_entry_tail))))

2353
/*
2354
 * Ext4 directory file types.  Only the low 3 bits are used.  The
2355 2356
 * other bits are reserved for now.
 */
2357 2358 2359 2360 2361 2362 2363 2364
#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
2365

2366
#define EXT4_FT_MAX		8
2367

2368 2369
#define EXT4_FT_DIR_CSUM	0xDE

2370
/*
2371
 * EXT4_DIR_PAD defines the directory entries boundaries
2372 2373 2374
 *
 * NOTE: It must be a multiple of 4
 */
2375 2376
#define EXT4_DIR_PAD			4
#define EXT4_DIR_ROUND			(EXT4_DIR_PAD - 1)
2377 2378
#define EXT4_MAX_REC_LEN		((1<<16)-1)

2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394
/*
 * The rec_len is dependent on the type of directory. Directories that are
 * casefolded and encrypted need to store the hash as well, so we add room for
 * ext4_extended_dir_entry_2. For all entries related to '.' or '..' you should
 * pass NULL for dir, as those entries do not use the extra fields.
 */
static inline unsigned int ext4_dir_rec_len(__u8 name_len,
						const struct inode *dir)
{
	int rec_len = (name_len + 8 + EXT4_DIR_ROUND);

	if (dir && ext4_hash_in_dirent(dir))
		rec_len += sizeof(struct ext4_dir_entry_hash);
	return (rec_len & ~EXT4_DIR_ROUND);
}

2395 2396 2397 2398 2399 2400 2401 2402 2403
/*
 * 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);

2404
#if (PAGE_SIZE >= 65536)
2405 2406 2407 2408 2409 2410 2411 2412 2413 2414
	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)
{
2415
	BUG_ON((len > blocksize) || (blocksize > (1 << 18)) || (len & 3));
2416
#if (PAGE_SIZE >= 65536)
2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430
	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
}

2431 2432 2433 2434 2435
/*
 * Hash Tree Directory indexing
 * (c) Daniel Phillips, 2001
 */

2436
#define is_dx(dir) (ext4_has_feature_dir_index((dir)->i_sb) && \
2437
		    ext4_test_inode_flag((dir), EXT4_INODE_INDEX))
2438 2439
#define EXT4_DIR_LINK_MAX(dir) unlikely((dir)->i_nlink >= EXT4_LINK_MAX && \
		    !(ext4_has_feature_dir_nlink((dir)->i_sb) && is_dx(dir)))
2440
#define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2 || (dir)->i_nlink == 1)
2441 2442 2443

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

2444 2445 2446 2447
#define DX_HASH_LEGACY			0
#define DX_HASH_HALF_MD4		1
#define DX_HASH_TEA			2
#define DX_HASH_LEGACY_UNSIGNED		3
2448 2449
#define DX_HASH_HALF_MD4_UNSIGNED	4
#define DX_HASH_TEA_UNSIGNED		5
2450
#define DX_HASH_SIPHASH			6
2451

2452 2453 2454 2455 2456
static inline u32 ext4_chksum(struct ext4_sb_info *sbi, u32 crc,
			      const void *address, unsigned int length)
{
	struct {
		struct shash_desc shash;
2457
		char ctx[4];
2458 2459
	} desc;

2460 2461
	BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver)!=sizeof(desc.ctx));

2462 2463 2464
	desc.shash.tfm = sbi->s_chksum_driver;
	*(u32 *)desc.ctx = crc;

2465
	BUG_ON(crypto_shash_update(&desc.shash, address, length));
2466 2467 2468 2469

	return *(u32 *)desc.ctx;
}

2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480
#ifdef __KERNEL__

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

2481 2482 2483 2484 2485

/* 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)

2486 2487

/*
2488
 * Control parameters used by ext4_htree_next_block
2489 2490 2491
 */
#define HASH_NB_ALWAYS		1

2492 2493
struct ext4_filename {
	const struct qstr *usr_fname;
2494
	struct fscrypt_str disk_name;
2495
	struct dx_hash_info hinfo;
2496
#ifdef CONFIG_FS_ENCRYPTION
2497
	struct fscrypt_str crypto_buf;
2498
#endif
2499
#if IS_ENABLED(CONFIG_UNICODE)
2500 2501
	struct fscrypt_str cf_name;
#endif
2502 2503 2504
};

#define fname_name(p) ((p)->disk_name.name)
2505
#define fname_usr_name(p) ((p)->usr_fname->name)
2506
#define fname_len(p)  ((p)->disk_name.len)
2507 2508 2509 2510

/*
 * Describe an inode's exact location on disk and in memory
 */
2511
struct ext4_iloc
2512 2513 2514
{
	struct buffer_head *bh;
	unsigned long offset;
2515
	ext4_group_t block_group;
2516 2517
};

2518
static inline struct ext4_inode *ext4_raw_inode(struct ext4_iloc *iloc)
2519
{
2520
	return (struct ext4_inode *) (iloc->bh->b_data + iloc->offset);
2521 2522
}

2523 2524 2525 2526 2527
static inline bool ext4_is_quota_file(struct inode *inode)
{
	return IS_NOQUOTA(inode) &&
	       !(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL);
}
2528

2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544
/*
 * 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 */
2545
static inline ext4_fsblk_t
2546
ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no)
2547
{
2548 2549
	return group_no * (ext4_fsblk_t)EXT4_BLOCKS_PER_GROUP(sb) +
		le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
2550 2551 2552 2553 2554
}

/*
 * Special error return code only used by dx_probe() and its callers.
 */
2555
#define ERR_BAD_DX_DIR	(-(MAX_ERRNO - 1))
2556

2557 2558 2559 2560 2561 2562 2563 2564 2565 2566
/* 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;
}

2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583
/*
 * 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;
};

2584 2585 2586 2587 2588
enum ext4_li_mode {
	EXT4_LI_MODE_PREFETCH_BBITMAP,
	EXT4_LI_MODE_ITABLE,
};

2589 2590
struct ext4_li_request {
	struct super_block	*lr_super;
2591 2592
	enum ext4_li_mode	lr_mode;
	ext4_group_t		lr_first_not_zeroed;
2593 2594 2595 2596 2597 2598
	ext4_group_t		lr_next_group;
	struct list_head	lr_request;
	unsigned long		lr_next_sched;
	unsigned long		lr_timeout;
};

2599 2600 2601 2602 2603
struct ext4_features {
	struct kobject f_kobj;
	struct completion f_kobj_unregister;
};

2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635
/*
 * 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;
2636 2637
	__le32	mmp_pad2[226];
	__le32	mmp_checksum;		/* crc32c(uuid+mmp_block) */
2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665
};

/* 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

2666 2667 2668 2669 2670 2671
/*
 * Function prototypes
 */

/*
 * Ok, these declarations are also in <linux/kernel.h> but none of the
2672
 * ext4 source programs needs to include it so they are duplicated here.
2673
 */
Dave Kleikamp's avatar
Dave Kleikamp committed
2674 2675 2676
# define NORET_TYPE	/**/
# define ATTRIB_NORET	__attribute__((noreturn))
# define NORET_AND	noreturn,
2677

2678
/* bitmap.c */
2679
extern unsigned int ext4_count_free(char *bitmap, unsigned numchars);
2680 2681 2682 2683 2684 2685
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);
2686 2687
void ext4_block_bitmap_csum_set(struct super_block *sb, ext4_group_t group,
				struct ext4_group_desc *gdp,
2688
				struct buffer_head *bh);
2689 2690
int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group,
				  struct ext4_group_desc *gdp,
2691
				  struct buffer_head *bh);
2692

2693
/* balloc.c */
2694 2695 2696 2697 2698 2699 2700
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);

2701 2702 2703 2704
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);
2705 2706 2707
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);
2708
extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
2709 2710 2711 2712
					 ext4_fsblk_t goal,
					 unsigned int flags,
					 unsigned long *count,
					 int *errp);
2713 2714
extern int ext4_claim_free_clusters(struct ext4_sb_info *sbi,
				    s64 nclusters, unsigned int flags);
2715
extern ext4_fsblk_t ext4_count_free_clusters(struct super_block *);
2716
extern void ext4_check_blocks_bitmap(struct super_block *);
2717
extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
2718
						    ext4_group_t block_group,
2719
						    struct buffer_head ** bh);
2720
extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
2721 2722

extern struct buffer_head *ext4_read_block_bitmap_nowait(struct super_block *sb,
2723 2724
						ext4_group_t block_group,
						bool ignore_locked);
2725 2726 2727 2728 2729
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);
2730 2731 2732
extern unsigned ext4_free_clusters_after_init(struct super_block *sb,
					      ext4_group_t block_group,
					      struct ext4_group_desc *gdp);
2733
ext4_fsblk_t ext4_inode_to_goal_block(struct inode *);
2734

2735
#if IS_ENABLED(CONFIG_UNICODE)
2736
extern int ext4_fname_setup_ci_filename(struct inode *dir,
2737
					 const struct qstr *iname,
2738
					 struct ext4_filename *fname);
2739 2740
#endif

2741
/* ext4 encryption related stuff goes here crypto.c */
2742
#ifdef CONFIG_FS_ENCRYPTION
2743 2744
extern const struct fscrypt_operations ext4_cryptops;

2745 2746
int ext4_fname_setup_filename(struct inode *dir, const struct qstr *iname,
			      int lookup, struct ext4_filename *fname);
2747

2748 2749
int ext4_fname_prepare_lookup(struct inode *dir, struct dentry *dentry,
			      struct ext4_filename *fname);
2750

2751
void ext4_fname_free_filename(struct ext4_filename *fname);
2752

2753 2754
int ext4_ioctl_get_encryption_pwsalt(struct file *filp, void __user *arg);

2755
#else /* !CONFIG_FS_ENCRYPTION */
2756
static inline int ext4_fname_setup_filename(struct inode *dir,
2757 2758 2759
					    const struct qstr *iname,
					    int lookup,
					    struct ext4_filename *fname)
2760
{
2761
	int err = 0;
2762 2763 2764
	fname->usr_fname = iname;
	fname->disk_name.name = (unsigned char *) iname->name;
	fname->disk_name.len = iname->len;
2765

2766
#if IS_ENABLED(CONFIG_UNICODE)
2767
	err = ext4_fname_setup_ci_filename(dir, iname, fname);
2768 2769
#endif

2770
	return err;
2771
}
2772

2773 2774 2775 2776 2777 2778 2779
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);
}

2780 2781
static inline void ext4_fname_free_filename(struct ext4_filename *fname)
{
2782
#if IS_ENABLED(CONFIG_UNICODE)
2783 2784 2785 2786
	kfree(fname->cf_name.name);
	fname->cf_name.name = NULL;
#endif
}
2787 2788 2789 2790 2791 2792

static inline int ext4_ioctl_get_encryption_pwsalt(struct file *filp,
						   void __user *arg)
{
	return -EOPNOTSUPP;
}
2793
#endif /* !CONFIG_FS_ENCRYPTION */
2794

2795
/* dir.c */
2796
extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *,
2797
				  struct file *,
2798
				  struct ext4_dir_entry_2 *,
2799 2800
				  struct buffer_head *, char *, int,
				  unsigned int);
2801
#define ext4_check_dir_entry(dir, filp, de, bh, buf, size, offset) \
2802
	unlikely(__ext4_check_dir_entry(__func__, __LINE__, (dir), (filp), \
2803
				(de), (bh), (buf), (size), (offset)))
2804
extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
2805 2806
				__u32 minor_hash,
				struct ext4_dir_entry_2 *dirent,
2807
				struct fscrypt_str *ent_name);
2808
extern void ext4_htree_free_dir_info(struct dir_private_info *p);
2809 2810 2811
extern int ext4_find_dest_de(struct inode *dir, struct inode *inode,
			     struct buffer_head *bh,
			     void *buf, int buf_size,
2812
			     struct ext4_filename *fname,
2813
			     struct ext4_dir_entry_2 **dest_de);
2814
void ext4_insert_dentry(struct inode *dir, struct inode *inode,
2815 2816 2817
			struct ext4_dir_entry_2 *de,
			int buf_size,
			struct ext4_filename *fname);
2818 2819
static inline void ext4_update_dx_flag(struct inode *inode)
{
2820 2821
	if (!ext4_has_feature_dir_index(inode->i_sb) &&
	    ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) {
2822 2823
		/* ext4_iget() should have caught this... */
		WARN_ON_ONCE(ext4_has_feature_metadata_csum(inode->i_sb));
2824
		ext4_clear_inode_flag(inode, EXT4_INODE_INDEX);
2825
	}
2826
}
2827
static const unsigned char ext4_filetype_table[] = {
2828 2829 2830 2831 2832
	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)
{
2833
	if (!ext4_has_feature_filetype(sb) || filetype >= EXT4_FT_MAX)
2834 2835 2836 2837
		return DT_UNKNOWN;

	return ext4_filetype_table[filetype];
}
2838 2839
extern int ext4_check_all_de(struct inode *dir, struct buffer_head *bh,
			     void *buf, int buf_size);
2840 2841

/* fsync.c */
2842
extern int ext4_sync_file(struct file *, loff_t, loff_t, int);
2843 2844

/* hash.c */
2845 2846
extern int ext4fs_dirhash(const struct inode *dir, const char *name, int len,
			  struct dx_hash_info *hinfo);
2847 2848

/* ialloc.c */
2849
extern int ext4_mark_inode_used(struct super_block *sb, int ino);
2850 2851
extern struct inode *__ext4_new_inode(struct user_namespace *, handle_t *,
				      struct inode *, umode_t,
2852
				      const struct qstr *qstr, __u32 goal,
2853 2854 2855
				      uid_t *owner, __u32 i_flags,
				      int handle_type, unsigned int line_no,
				      int nblocks);
2856

2857 2858 2859 2860
#define ext4_new_inode(handle, dir, mode, qstr, goal, owner, i_flags)          \
	__ext4_new_inode(&init_user_ns, (handle), (dir), (mode), (qstr),       \
			 (goal), (owner), i_flags, 0, 0, 0)
#define ext4_new_inode_start_handle(mnt_userns, dir, mode, qstr, goal, owner, \
2861
				    type, nblocks)		    \
2862
	__ext4_new_inode((mnt_userns), NULL, (dir), (mode), (qstr), (goal), (owner), \
2863
			 0, (type), __LINE__, (nblocks))
2864 2865


2866 2867 2868 2869 2870
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 *);
2871
extern void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
2872 2873
extern int ext4_init_inode_table(struct super_block *sb,
				 ext4_group_t group, int barrier);
2874
extern void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate);
2875

2876
/* fast_commit.c */
2877
int ext4_fc_info_show(struct seq_file *seq, void *v);
2878
void ext4_fc_init(struct super_block *sb, journal_t *journal);
2879
void ext4_fc_init_inode(struct inode *inode);
2880
void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t start,
2881
			 ext4_lblk_t end);
2882 2883 2884 2885 2886 2887
void __ext4_fc_track_unlink(handle_t *handle, struct inode *inode,
	struct dentry *dentry);
void __ext4_fc_track_link(handle_t *handle, struct inode *inode,
	struct dentry *dentry);
void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry);
void ext4_fc_track_link(handle_t *handle, struct dentry *dentry);
2888 2889
void __ext4_fc_track_create(handle_t *handle, struct inode *inode,
			    struct dentry *dentry);
2890 2891
void ext4_fc_track_create(handle_t *handle, struct dentry *dentry);
void ext4_fc_track_inode(handle_t *handle, struct inode *inode);
2892
void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handle);
2893 2894 2895
void ext4_fc_start_update(struct inode *inode);
void ext4_fc_stop_update(struct inode *inode);
void ext4_fc_del(struct inode *inode);
2896 2897
bool ext4_fc_replay_check_excluded(struct super_block *sb, ext4_fsblk_t block);
void ext4_fc_replay_cleanup(struct super_block *sb);
2898 2899
int ext4_fc_commit(journal_t *journal, tid_t commit_tid);
int __init ext4_fc_init_dentry_cache(void);
2900
void ext4_fc_destroy_dentry_cache(void);
2901 2902 2903
int ext4_fc_record_regions(struct super_block *sb, int ino,
			   ext4_lblk_t lblk, ext4_fsblk_t pblk,
			   int len, int replay);
2904

2905
/* mballoc.c */
2906
extern const struct seq_operations ext4_mb_seq_groups_ops;
2907
extern const struct seq_operations ext4_mb_seq_structs_summary_ops;
2908 2909
extern long ext4_mb_stats;
extern long ext4_mb_max_to_scan;
2910
extern int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset);
2911
extern int ext4_mb_init(struct super_block *);
2912 2913 2914 2915
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);
2916
extern void ext4_discard_preallocations(struct inode *, unsigned int);
2917 2918
extern int __init ext4_init_mballoc(void);
extern void ext4_exit_mballoc(void);
2919 2920 2921 2922 2923 2924
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);

2925
extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
2926 2927
			     struct buffer_head *bh, ext4_fsblk_t block,
			     unsigned long count, int flags);
2928 2929
extern int ext4_mb_alloc_groupinfo(struct super_block *sb,
				   ext4_group_t ngroups);
2930
extern int ext4_mb_add_groupinfo(struct super_block *sb,
2931
		ext4_group_t i, struct ext4_group_desc *desc);
2932
extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
2933
				ext4_fsblk_t block, unsigned long count);
2934
extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);
2935
extern void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid);
2936 2937
extern void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
		       int len, int state);
2938

2939
/* inode.c */
2940 2941
void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw,
			 struct ext4_inode_info *ei);
2942
int ext4_inode_is_fast_symlink(struct inode *inode);
2943
struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int);
2944
struct buffer_head *ext4_bread(handle_t *, struct inode *, ext4_lblk_t, int);
2945 2946
int ext4_bread_batch(struct inode *inode, ext4_lblk_t block, int bh_count,
		     bool wait, struct buffer_head **bhs);
2947 2948
int ext4_get_block_unwritten(struct inode *inode, sector_t iblock,
			     struct buffer_head *bh_result, int create);
2949
int ext4_get_block(struct inode *inode, sector_t iblock,
2950
		   struct buffer_head *bh_result, int create);
2951 2952
int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
			   struct buffer_head *bh, int create);
2953
int ext4_walk_page_buffers(handle_t *handle,
2954
			   struct inode *inode,
2955 2956 2957 2958
			   struct buffer_head *head,
			   unsigned from,
			   unsigned to,
			   int *partial,
2959
			   int (*fn)(handle_t *handle, struct inode *inode,
2960
				     struct buffer_head *bh));
2961
int do_journal_get_write_access(handle_t *handle, struct inode *inode,
2962
				struct buffer_head *bh);
2963 2964
#define FALL_BACK_TO_NONDELALLOC 1
#define CONVERT_INLINE_DATA	 2
2965

2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978
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__)

2979
extern int  ext4_write_inode(struct inode *, struct writeback_control *);
2980 2981 2982 2983
extern int  ext4_setattr(struct user_namespace *, struct dentry *,
			 struct iattr *);
extern int  ext4_getattr(struct user_namespace *, const struct path *,
			 struct kstat *, u32, unsigned int);
Al Viro's avatar
Al Viro committed
2984 2985
extern void ext4_evict_inode(struct inode *);
extern void ext4_clear_inode(struct inode *);
2986 2987
extern int  ext4_file_getattr(struct user_namespace *, const struct path *,
			      struct kstat *, u32, unsigned int);
2988
extern int  ext4_sync_inode(handle_t *, struct inode *);
2989
extern void ext4_dirty_inode(struct inode *, int);
2990 2991
extern int ext4_change_inode_journal_flag(struct inode *, int);
extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
2992 2993
extern int ext4_get_fc_inode_loc(struct super_block *sb, unsigned long ino,
			  struct ext4_iloc *iloc);
2994
extern int ext4_inode_attach_jinode(struct inode *inode);
2995
extern int ext4_can_truncate(struct inode *inode);
2996
extern int ext4_truncate(struct inode *);
2997
extern int ext4_break_layouts(struct inode *);
2998
extern int ext4_punch_hole(struct file *file, loff_t offset, loff_t length);
2999
extern void ext4_set_inode_flags(struct inode *, bool init);
3000
extern int ext4_alloc_da_blocks(struct inode *inode);
3001
extern void ext4_set_aops(struct inode *inode);
3002
extern int ext4_writepage_trans_blocks(struct inode *);
3003
extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
3004 3005
extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
			     loff_t lstart, loff_t lend);
3006
extern vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf);
3007
extern qsize_t *ext4_get_reserved_space(struct inode *inode);
Li Xi's avatar
Li Xi committed
3008
extern int ext4_get_projid(struct inode *inode, kprojid_t *projid);
3009
extern void ext4_da_release_space(struct inode *inode, int to_free);
3010 3011
extern void ext4_da_update_reserve_space(struct inode *inode,
					int used, int quota_claim);
Jan Kara's avatar
Jan Kara committed
3012 3013
extern int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk,
			      ext4_fsblk_t pblk, ext4_lblk_t len);
3014 3015 3016 3017

/* indirect.c */
extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
				struct ext4_map_blocks *map, int flags);
3018
extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks);
Theodore Ts'o's avatar
Theodore Ts'o committed
3019
extern void ext4_ind_truncate(handle_t *, struct inode *inode);
3020 3021
extern int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
				 ext4_lblk_t start, ext4_lblk_t end);
3022

3023
/* ioctl.c */
3024
extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
3025
extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
Miklos Szeredi's avatar
Miklos Szeredi committed
3026 3027 3028
int ext4_fileattr_set(struct user_namespace *mnt_userns,
		      struct dentry *dentry, struct fileattr *fa);
int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa);
3029
extern void ext4_reset_inode_seed(struct inode *inode);
3030
int ext4_update_overhead(struct super_block *sb, bool force);
3031

3032
/* migrate.c */
3033
extern int ext4_ext_migrate(struct inode *);
3034
extern int ext4_ind_migrate(struct inode *inode);
3035

3036
/* namei.c */
3037 3038
extern int ext4_init_new_dir(handle_t *handle, struct inode *dir,
			     struct inode *inode);
3039 3040
extern int ext4_dirblock_csum_verify(struct inode *inode,
				     struct buffer_head *bh);
3041
extern int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
3042
				__u32 start_minor_hash, __u32 *next_hash);
3043 3044 3045 3046 3047 3048 3049
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);
3050
extern int ext4_generic_delete_entry(struct inode *dir,
Tao Ma's avatar
Tao Ma committed
3051 3052 3053 3054 3055
				     struct ext4_dir_entry_2 *de_del,
				     struct buffer_head *bh,
				     void *entry_buf,
				     int buf_size,
				     int csum_size);
3056
extern bool ext4_empty_dir(struct inode *inode);
3057 3058

/* resize.c */
3059
extern void ext4_kvfree_array_rcu(void *to_free);
3060 3061 3062 3063 3064
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);
3065
extern int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count);
3066 3067 3068
extern unsigned int ext4_list_backups(struct super_block *sb,
				      unsigned int *three, unsigned int *five,
				      unsigned int *seven);
3069 3070

/* super.c */
3071
extern struct buffer_head *ext4_sb_bread(struct super_block *sb,
3072
					 sector_t block, blk_opf_t op_flags);
3073 3074
extern struct buffer_head *ext4_sb_bread_unmovable(struct super_block *sb,
						   sector_t block);
3075
extern void ext4_read_bh_nowait(struct buffer_head *bh, blk_opf_t op_flags,
3076
				bh_end_io_t *end_io);
3077
extern int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags,
3078
			bh_end_io_t *end_io);
3079
extern int ext4_read_bh_lock(struct buffer_head *bh, blk_opf_t op_flags, bool wait);
3080
extern void ext4_sb_breadahead_unmovable(struct super_block *sb, sector_t block);
3081
extern int ext4_seq_options_show(struct seq_file *seq, void *offset);
3082
extern int ext4_calculate_overhead(struct super_block *sb);
3083 3084
extern __le32 ext4_superblock_csum(struct super_block *sb,
				   struct ext4_super_block *es);
3085
extern void ext4_superblock_csum_set(struct super_block *sb);
3086 3087
extern int ext4_alloc_flex_bg_array(struct super_block *sb,
				    ext4_group_t ngroup);
3088 3089
extern const char *ext4_decode_error(struct super_block *sb, int errno,
				     char nbuf[16]);
3090 3091 3092
extern void ext4_mark_group_bitmap_corrupted(struct super_block *sb,
					     ext4_group_t block_group,
					     unsigned int flags);
3093

3094 3095 3096
extern __printf(7, 8)
void __ext4_error(struct super_block *, const char *, unsigned int, bool,
		  int, __u64, const char *, ...);
3097 3098 3099
extern __printf(6, 7)
void __ext4_error_inode(struct inode *, const char *, unsigned int,
			ext4_fsblk_t, int, const char *, ...);
3100
extern __printf(5, 6)
3101
void __ext4_error_file(struct file *, const char *, unsigned int, ext4_fsblk_t,
3102
		     const char *, ...);
3103 3104
extern void __ext4_std_error(struct super_block *, const char *,
			     unsigned int, int);
3105 3106 3107
extern __printf(4, 5)
void __ext4_warning(struct super_block *, const char *, unsigned int,
		    const char *, ...);
3108 3109 3110
extern __printf(4, 5)
void __ext4_warning_inode(const struct inode *inode, const char *function,
			  unsigned int line, const char *fmt, ...);
3111
extern __printf(3, 4)
3112
void __ext4_msg(struct super_block *, const char *, const char *, ...);
3113 3114
extern void __dump_mmp_msg(struct super_block *, struct mmp_struct *mmp,
			   const char *, unsigned int, const char *);
3115 3116 3117 3118 3119
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 *, ...);
3120

3121 3122 3123
#define EXT4_ERROR_INODE(inode, fmt, a...) \
	ext4_error_inode((inode), __func__, __LINE__, 0, (fmt), ## a)

3124 3125 3126 3127 3128 3129
#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)
3130 3131 3132 3133

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

3134 3135 3136
#define ext4_abort(sb, err, fmt, a...)					\
	__ext4_error((sb), __func__, __LINE__, true, (err), 0, (fmt), ## a)

3137 3138 3139
#ifdef CONFIG_PRINTK

#define ext4_error_inode(inode, func, line, block, fmt, ...)		\
3140 3141 3142 3143
	__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__)
3144 3145 3146
#define ext4_error_file(file, func, line, block, fmt, ...)		\
	__ext4_error_file(file, func, line, block, fmt, ##__VA_ARGS__)
#define ext4_error(sb, fmt, ...)					\
3147 3148
	__ext4_error((sb), __func__, __LINE__, false, 0, 0, (fmt),	\
		##__VA_ARGS__)
3149
#define ext4_error_err(sb, err, fmt, ...)				\
3150 3151
	__ext4_error((sb), __func__, __LINE__, false, (err), 0, (fmt),	\
		##__VA_ARGS__)
3152 3153
#define ext4_warning(sb, fmt, ...)					\
	__ext4_warning(sb, __func__, __LINE__, fmt, ##__VA_ARGS__)
3154 3155
#define ext4_warning_inode(inode, fmt, ...)				\
	__ext4_warning_inode(inode, __func__, __LINE__, fmt, ##__VA_ARGS__)
3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168
#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__);					\
3169 3170 3171 3172 3173 3174
	__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, " ");		\
3175 3176 3177 3178 3179 3180 3181 3182 3183
} 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__);					\
3184
	__ext4_error(sb, "", 0, false, 0, 0, " ");			\
3185 3186 3187 3188
} while (0)
#define ext4_error_err(sb, err, fmt, ...)				\
do {									\
	no_printk(fmt, ##__VA_ARGS__);					\
3189
	__ext4_error(sb, "", 0, false, err, 0, " ");			\
3190 3191 3192 3193 3194 3195
} while (0)
#define ext4_warning(sb, fmt, ...)					\
do {									\
	no_printk(fmt, ##__VA_ARGS__);					\
	__ext4_warning(sb, "", 0, " ");					\
} while (0)
3196 3197 3198 3199 3200
#define ext4_warning_inode(inode, fmt, ...)				\
do {									\
	no_printk(fmt, ##__VA_ARGS__);					\
	__ext4_warning_inode(inode, "", 0, " ");			\
} while (0)
3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215
#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

3216 3217 3218 3219 3220 3221
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);
3222 3223
extern __u32 ext4_free_group_clusters(struct super_block *sb,
				      struct ext4_group_desc *bg);
3224 3225 3226 3227 3228 3229
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);
3230 3231 3232 3233 3234 3235
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);
3236 3237 3238
extern void ext4_free_group_clusters_set(struct super_block *sb,
					 struct ext4_group_desc *bg,
					 __u32 count);
3239 3240 3241 3242 3243 3244
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);
3245
extern int ext4_group_desc_csum_verify(struct super_block *sb, __u32 group,
3246
				       struct ext4_group_desc *gdp);
3247 3248
extern void ext4_group_desc_csum_set(struct super_block *sb, __u32 group,
				     struct ext4_group_desc *gdp);
3249 3250
extern int ext4_register_li_request(struct super_block *sb,
				    ext4_group_t first_not_zeroed);
Laurent Vivier's avatar
Laurent Vivier committed
3251

3252 3253
static inline int ext4_has_metadata_csum(struct super_block *sb)
{
3254
	WARN_ON_ONCE(ext4_has_feature_metadata_csum(sb) &&
3255 3256
		     !EXT4_SB(sb)->s_chksum_driver);

3257 3258
	return ext4_has_feature_metadata_csum(sb) &&
	       (EXT4_SB(sb)->s_chksum_driver != NULL);
3259
}
3260 3261 3262 3263 3264 3265

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

3266 3267 3268 3269 3270
#define ext4_read_incompat_64bit_val(es, name) \
	(((es)->s_feature_incompat & cpu_to_le32(EXT4_FEATURE_INCOMPAT_64BIT) \
		? (ext4_fsblk_t)le32_to_cpu(es->name##_hi) << 32 : 0) | \
		le32_to_cpu(es->name##_lo))

Laurent Vivier's avatar
Laurent Vivier committed
3271 3272
static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es)
{
3273
	return ext4_read_incompat_64bit_val(es, s_blocks_count);
Laurent Vivier's avatar
Laurent Vivier committed
3274 3275 3276 3277
}

static inline ext4_fsblk_t ext4_r_blocks_count(struct ext4_super_block *es)
{
3278
	return ext4_read_incompat_64bit_val(es, s_r_blocks_count);
Laurent Vivier's avatar
Laurent Vivier committed
3279 3280 3281 3282
}

static inline ext4_fsblk_t ext4_free_blocks_count(struct ext4_super_block *es)
{
3283
	return ext4_read_incompat_64bit_val(es, s_free_blocks_count);
Laurent Vivier's avatar
Laurent Vivier committed
3284 3285 3286 3287 3288
}

static inline void ext4_blocks_count_set(struct ext4_super_block *es,
					 ext4_fsblk_t blk)
{
3289
	es->s_blocks_count_lo = cpu_to_le32((u32)blk);
Laurent Vivier's avatar
Laurent Vivier committed
3290 3291 3292 3293 3294 3295
	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)
{
3296
	es->s_free_blocks_count_lo = cpu_to_le32((u32)blk);
Laurent Vivier's avatar
Laurent Vivier committed
3297 3298 3299 3300 3301 3302
	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)
{
3303
	es->s_r_blocks_count_lo = cpu_to_le32((u32)blk);
Laurent Vivier's avatar
Laurent Vivier committed
3304 3305 3306
	es->s_r_blocks_count_hi = cpu_to_le32(blk >> 32);
}

3307 3308
static inline loff_t ext4_isize(struct super_block *sb,
				struct ext4_inode *raw_inode)
3309
{
3310 3311
	if (ext4_has_feature_largedir(sb) ||
	    S_ISREG(le16_to_cpu(raw_inode->i_mode)))
3312 3313
		return ((loff_t)le32_to_cpu(raw_inode->i_size_high) << 32) |
			le32_to_cpu(raw_inode->i_size_lo);
3314 3315

	return (loff_t) le32_to_cpu(raw_inode->i_size_lo);
3316
}
Laurent Vivier's avatar
Laurent Vivier committed
3317

3318 3319 3320 3321 3322
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);
}
3323

3324 3325
static inline
struct ext4_group_info *ext4_get_group_info(struct super_block *sb,
3326
					    ext4_group_t group)
3327
{
3328
	 struct ext4_group_info **grp_info;
3329
	 long indexv, indexh;
3330
	 BUG_ON(group >= EXT4_SB(sb)->s_groups_count);
3331 3332
	 indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb));
	 indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1);
3333 3334
	 grp_info = sbi_array_rcu_deref(EXT4_SB(sb), s_group_info, indexv);
	 return grp_info[indexh];
3335 3336
}

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

3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360
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;
}

3361
#define ext4_std_error(sb, errno)				\
3362 3363
do {								\
	if ((errno))						\
3364
		__ext4_std_error((sb), __func__, __LINE__, (errno));	\
3365 3366
} while (0)

3367
#ifdef CONFIG_SMP
3368 3369
/* Each CPU can accumulate percpu_counter_batch clusters in their local
 * counters. So we need to make sure we have free clusters more
3370
 * than percpu_counter_batch  * nr_cpu_ids. Also add a window of 4 times.
3371
 */
3372
#define EXT4_FREECLUSTERS_WATERMARK (4 * (percpu_counter_batch * nr_cpu_ids))
3373
#else
3374
#define EXT4_FREECLUSTERS_WATERMARK 0
3375 3376
#endif

3377
/* Update i_disksize. Requires i_rwsem to avoid races with truncate */
3378 3379
static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
{
3380
	WARN_ON_ONCE(S_ISREG(inode->i_mode) &&
Al Viro's avatar
Al Viro committed
3381
		     !inode_is_locked(inode));
3382 3383
	down_write(&EXT4_I(inode)->i_data_sem);
	if (newsize > EXT4_I(inode)->i_disksize)
3384
		WRITE_ONCE(EXT4_I(inode)->i_disksize, newsize);
3385 3386 3387
	up_write(&EXT4_I(inode)->i_data_sem);
}

3388
/* Update i_size, i_disksize. Requires i_rwsem to avoid races with truncate */
3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403
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;
}

3404 3405 3406
int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
				      loff_t len);

3407 3408
struct ext4_group_info {
	unsigned long   bb_state;
3409 3410 3411
#ifdef AGGRESSIVE_CHECK
	unsigned long	bb_check_counter;
#endif
3412
	struct rb_root  bb_free_root;
3413 3414 3415
	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 */
3416
	ext4_grpblk_t	bb_largest_free_order;/* order of largest frag in BG */
3417
	ext4_group_t	bb_group;	/* Group number */
3418 3419 3420 3421 3422
	struct          list_head bb_prealloc_list;
#ifdef DOUBLE_CHECK
	void            *bb_bitmap;
#endif
	struct rw_semaphore alloc_sem;
3423 3424
	struct rb_node	bb_avg_fragment_size_rb;
	struct list_head bb_largest_free_order_node;
3425 3426 3427 3428
	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. */
3429 3430
};

3431 3432
#define EXT4_GROUP_INFO_NEED_INIT_BIT		0
#define EXT4_GROUP_INFO_WAS_TRIMMED_BIT		1
3433
#define EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT	2
3434
#define EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT	3
3435 3436 3437 3438
#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)
3439
#define EXT4_GROUP_INFO_BBITMAP_READ_BIT	4
3440 3441 3442

#define EXT4_MB_GRP_NEED_INIT(grp)	\
	(test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
3443 3444
#define EXT4_MB_GRP_BBITMAP_CORRUPT(grp)	\
	(test_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &((grp)->bb_state)))
3445 3446
#define EXT4_MB_GRP_IBITMAP_CORRUPT(grp)	\
	(test_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &((grp)->bb_state)))
3447

3448 3449 3450 3451 3452 3453
#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)))
3454 3455
#define EXT4_MB_GRP_TEST_AND_SET_READ(grp)	\
	(test_and_set_bit(EXT4_GROUP_INFO_BBITMAP_READ_BIT, &((grp)->bb_state)))
3456

3457 3458 3459
#define EXT4_MAX_CONTENTION		8
#define EXT4_CONTENTION_THRESHOLD	2

3460 3461
static inline spinlock_t *ext4_group_lock_ptr(struct super_block *sb,
					      ext4_group_t group)
3462
{
3463 3464
	return bgl_lock_ptr(EXT4_SB(sb)->s_blockgroup_lock, group);
}
3465

3466 3467 3468 3469 3470 3471 3472 3473 3474
/*
 * 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);
}

3475 3476
static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group)
{
3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492
	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);
	}
3493 3494 3495 3496 3497
}

static inline void ext4_unlock_group(struct super_block *sb,
					ext4_group_t group)
{
3498
	spin_unlock(ext4_group_lock_ptr(sb, group));
3499 3500
}

3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513
#ifdef CONFIG_QUOTA
static inline bool ext4_quota_capable(struct super_block *sb)
{
	return (test_opt(sb, QUOTA) || ext4_has_feature_quota(sb));
}

static inline bool ext4_is_quota_journalled(struct super_block *sb)
{
	struct ext4_sb_info *sbi = EXT4_SB(sb);

	return (ext4_has_feature_quota(sb) ||
		sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]);
}
3514
int ext4_enable_quotas(struct super_block *sb);
3515 3516
#endif

3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529
/*
 * 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)

3530 3531 3532 3533 3534
/*
 * Inodes and files operations
 */

/* dir.c */
3535
extern const struct file_operations ext4_dir_operations;
3536 3537

/* file.c */
3538
extern const struct inode_operations ext4_file_inode_operations;
3539
extern const struct file_operations ext4_file_operations;
3540
extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
3541

3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566
/* 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,
					 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,
					   struct page **pagep,
					   void **fsdata);
3567 3568
extern int ext4_try_add_inline_entry(handle_t *handle,
				     struct ext4_filename *fname,
3569
				     struct inode *dir, struct inode *inode);
3570 3571 3572 3573
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,
Al Viro's avatar
Al Viro committed
3574
				struct dir_context *ctx,
3575
				int *has_inline_data);
3576 3577 3578 3579 3580
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);
3581
extern struct buffer_head *ext4_find_inline_entry(struct inode *dir,
3582
					struct ext4_filename *fname,
3583 3584 3585 3586 3587 3588 3589
					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);
3590
extern bool empty_inline_dir(struct inode *dir, int *has_inline_data);
3591 3592 3593 3594 3595
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,
3596
				   int *has_inline, __u64 start, __u64 len);
3597
extern void *ext4_read_inline_link(struct inode *inode);
3598 3599 3600 3601

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

3602
extern int ext4_inline_data_truncate(struct inode *inode, int *has_inline);
3603 3604 3605

extern int ext4_convert_inline_data(struct inode *inode);

3606 3607 3608 3609 3610 3611
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;
}

3612
/* namei.c */
3613 3614
extern const struct inode_operations ext4_dir_inode_operations;
extern const struct inode_operations ext4_special_inode_operations;
3615
extern struct dentry *ext4_get_parent(struct dentry *child);
3616 3617 3618 3619
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);
3620 3621
extern void ext4_initialize_dirent_tail(struct buffer_head *bh,
					unsigned int blocksize);
3622 3623
extern int ext4_handle_dirty_dirblock(handle_t *handle, struct inode *inode,
				      struct buffer_head *bh);
3624
extern int __ext4_unlink(handle_t *handle, struct inode *dir, const struct qstr *d_name,
3625 3626 3627
			 struct inode *inode);
extern int __ext4_link(struct inode *dir, struct inode *inode,
		       struct dentry *dentry);
3628

3629
#define S_SHIFT 12
3630
static const unsigned char ext4_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = {
3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642
	[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) {
3643
	if (ext4_has_feature_filetype(sb))
3644 3645 3646
		de->file_type = ext4_type_by_mode[(mode & S_IFMT)>>S_SHIFT];
}

3647
/* readpages.c */
3648
extern int ext4_mpage_readpages(struct inode *inode,
3649
		struct readahead_control *rac, struct page *page);
3650 3651
extern int __init ext4_init_post_read_processing(void);
extern void ext4_exit_post_read_processing(void);
3652 3653

/* symlink.c */
3654
extern const struct inode_operations ext4_encrypted_symlink_inode_operations;
3655 3656
extern const struct inode_operations ext4_symlink_inode_operations;
extern const struct inode_operations ext4_fast_symlink_inode_operations;
3657

3658
/* sysfs.c */
3659
extern void ext4_notify_error_sysfs(struct ext4_sb_info *sbi);
3660
extern int ext4_register_sysfs(struct super_block *sb);
3661
extern void ext4_unregister_sysfs(struct super_block *sb);
3662 3663 3664
extern int __init ext4_init_sysfs(void);
extern void ext4_exit_sysfs(void);

3665 3666 3667
/* block_validity */
extern void ext4_release_system_zone(struct super_block *sb);
extern int ext4_setup_system_zone(struct super_block *sb);
3668 3669
extern int __init ext4_init_system_zone(void);
extern void ext4_exit_system_zone(void);
3670 3671 3672
extern int ext4_inode_block_valid(struct inode *inode,
				  ext4_fsblk_t start_blk,
				  unsigned int count);
3673 3674
extern int ext4_check_blockref(const char *, unsigned int,
			       struct inode *, __le32 *, unsigned int);
3675 3676 3677
extern int ext4_sb_block_valid(struct super_block *sb, struct inode *inode,
				ext4_fsblk_t start_blk, unsigned int count);

3678

3679
/* extents.c */
3680 3681 3682
struct ext4_ext_path;
struct ext4_extent;

Zheng Liu's avatar
Zheng Liu committed
3683 3684 3685 3686 3687 3688
/*
 * Maximum number of logical blocks in a file; ext4_extent's ee_block is
 * __le32.
 */
#define EXT_MAX_BLOCKS	0xffffffff

3689
extern void ext4_ext_tree_init(handle_t *handle, struct inode *inode);
3690
extern int ext4_ext_index_trans_blocks(struct inode *inode, int extents);
3691 3692
extern int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
			       struct ext4_map_blocks *map, int flags);
3693
extern int ext4_ext_truncate(handle_t *, struct inode *);
Theodore Ts'o's avatar
Theodore Ts'o committed
3694 3695
extern int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
				 ext4_lblk_t end);
3696 3697
extern void ext4_ext_init(struct super_block *);
extern void ext4_ext_release(struct super_block *);
3698
extern long ext4_fallocate(struct file *file, int mode, loff_t offset,
Amit Arora's avatar
Amit Arora committed
3699
			  loff_t len);
3700 3701
extern int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode,
					  loff_t offset, ssize_t len);
3702 3703
extern int ext4_convert_unwritten_io_end_vec(handle_t *handle,
					     ext4_io_end_t *io_end);
3704 3705
extern int ext4_map_blocks(handle_t *handle, struct inode *inode,
			   struct ext4_map_blocks *map, int flags);
3706 3707 3708 3709
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 *,
3710
				  struct ext4_ext_path **,
3711
				  struct ext4_extent *, int);
3712 3713 3714
extern struct ext4_ext_path *ext4_find_extent(struct inode *, ext4_lblk_t,
					      struct ext4_ext_path **,
					      int flags);
3715 3716
extern void ext4_ext_drop_refs(struct ext4_ext_path *);
extern int ext4_ext_check_inode(struct inode *inode);
3717
extern ext4_lblk_t ext4_ext_next_allocated_block(struct ext4_ext_path *path);
Aneesh Kumar K.V's avatar
Aneesh Kumar K.V committed
3718 3719
extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
			__u64 start, __u64 len);
3720 3721 3722
extern int ext4_get_es_cache(struct inode *inode,
			     struct fiemap_extent_info *fieinfo,
			     __u64 start, __u64 len);
3723
extern int ext4_ext_precache(struct inode *inode);
3724 3725 3726 3727
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);
3728
extern int ext4_clu_mapped(struct inode *inode, ext4_lblk_t lclu);
3729
extern int ext4_datasem_ensure_credits(handle_t *handle, struct inode *inode,
3730 3731
				       int check_cred, int restart_cred,
				       int revoke_cred);
3732 3733 3734 3735 3736
extern void ext4_ext_replay_shrink_inode(struct inode *inode, ext4_lblk_t end);
extern int ext4_ext_replay_set_iblocks(struct inode *inode);
extern int ext4_ext_replay_update_ex(struct inode *inode, ext4_lblk_t start,
		int len, int unwritten, ext4_fsblk_t pblk);
extern int ext4_ext_clear_bb(struct inode *inode);
3737

3738

3739
/* move_extent.c */
3740 3741 3742 3743
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);
3744 3745 3746 3747
extern int ext4_move_extents(struct file *o_filp, struct file *d_filp,
			     __u64 start_orig, __u64 start_donor,
			     __u64 len, __u64 *moved_len);

3748
/* page-io.c */
3749 3750
extern int __init ext4_init_pageio(void);
extern void ext4_exit_pageio(void);
3751
extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags);
Jan Kara's avatar
Jan Kara committed
3752 3753 3754 3755 3756
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);
3757
extern void ext4_end_io_rsv_work(struct work_struct *work);
3758 3759 3760 3761
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,
3762
			       bool keep_towrite);
3763 3764
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);
Aneesh Kumar K.V's avatar
Aneesh Kumar K.V committed
3765

3766 3767 3768
/* mmp.c */
extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);

3769 3770 3771
/* mmp.c */
extern void ext4_stop_mmpd(struct ext4_sb_info *sbi);

3772 3773 3774
/* verity.c */
extern const struct fsverity_operations ext4_verityops;

3775 3776 3777 3778 3779
/* orphan.c */
extern int ext4_orphan_add(handle_t *, struct inode *);
extern int ext4_orphan_del(handle_t *, struct inode *);
extern void ext4_orphan_cleanup(struct super_block *sb,
				struct ext4_super_block *es);
3780 3781 3782 3783 3784 3785 3786
extern void ext4_release_orphan_info(struct super_block *sb);
extern int ext4_init_orphan_info(struct super_block *sb);
extern int ext4_orphan_file_empty(struct super_block *sb);
extern void ext4_orphan_file_block_trigger(
				struct jbd2_buffer_trigger_type *triggers,
				struct buffer_head *bh,
				void *data, size_t size);
3787

3788
/*
3789
 * Add new method to test whether block and inode bitmaps are properly
3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804
 * 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);
}

3805 3806
#define in_range(b, first, len)	((b) >= (first) && (b) <= (first) + (len) - 1)

3807 3808 3809 3810 3811 3812
/* 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];

3813
extern int ext4_resize_begin(struct super_block *sb);
3814
extern int ext4_resize_end(struct super_block *sb, bool update_backups);
3815

3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836
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));
	}
}

3837
extern const struct iomap_ops ext4_iomap_ops;
Jan Kara's avatar
Jan Kara committed
3838
extern const struct iomap_ops ext4_iomap_overwrite_ops;
3839
extern const struct iomap_ops ext4_iomap_report_ops;
3840

3841 3842 3843 3844 3845 3846 3847 3848
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.
	 */
3849
	if (buffer_write_io_error(bh))
3850 3851 3852 3853
		set_buffer_uptodate(bh);
	return buffer_uptodate(bh);
}

3854 3855
#endif	/* __KERNEL__ */

3856 3857 3858
#define EFSBADCRC	EBADMSG		/* Bad CRC detected */
#define EFSCORRUPTED	EUCLEAN		/* Filesystem is corrupted */

3859
#endif	/* _EXT4_H */