ext4.h 133 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
#include <uapi/linux/ext4.h>
44

45
#include <linux/fscrypt.h>
46
#include <linux/fsverity.h>
47

48 49
#include <linux/compiler.h>

50
/*
Shen Feng's avatar
Shen Feng committed
51
 * The fourth extended filesystem constants/structures
52 53
 */

54 55 56 57 58 59 60 61 62 63 64 65
/*
 * 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__

66
/*
67
 * Define EXT4FS_DEBUG to produce debug messages
68
 */
69
#undef EXT4FS_DEBUG
70 71 72 73

/*
 * Debug code
 */
74 75
#ifdef EXT4FS_DEBUG
#define ext4_debug(f, a...)						\
76
	do {								\
77
		printk(KERN_DEBUG "EXT4-fs DEBUG (%s, %d): %s:",	\
78
			__FILE__, __LINE__, __func__);			\
79
		printk(KERN_DEBUG f, ## a);				\
80 81
	} while (0)
#else
82
#define ext4_debug(fmt, ...)	no_printk(fmt, ##__VA_ARGS__)
83 84
#endif

85 86 87 88 89
 /*
  * Turn on EXT_DEBUG to enable ext4_ext_show_path/leaf/move in extents.c
  */
#define EXT_DEBUG__

90
/*
91
 * Dynamic printk for controlled extents debugging.
92
 */
93 94 95 96 97 98
#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__)
99
#else
100
#define ext_debug(ino, fmt, ...)	no_printk(fmt, ##__VA_ARGS__)
101 102
#endif

103 104 105 106 107 108 109 110 111 112
#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)

113 114 115 116 117 118 119 120 121 122 123 124
/* 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;

125 126 127 128 129
enum SHIFT_DIRECTION {
	SHIFT_LEFT = 0,
	SHIFT_RIGHT,
};

130
/*
131 132 133 134 135
 * For each criteria, mballoc has slightly different way of finding
 * the required blocks nad usually, higher the criteria the slower the
 * allocation.  We start at lower criterias and keep falling back to
 * higher ones if we are not able to find any blocks.  Lower (earlier)
 * criteria are faster.
136 137
 */
enum criteria {
138
	/*
139 140 141
	 * Used when number of blocks needed is a power of 2. This
	 * doesn't trigger any disk IO except prefetch and is the
	 * fastest criteria.
142 143 144 145
	 */
	CR_POWER2_ALIGNED,

	/*
146 147 148
	 * Tries to lookup in-memory data structures to find the most
	 * suitable group that satisfies goal request. No disk IO
	 * except block prefetch.
149 150 151 152
	 */
	CR_GOAL_LEN_FAST,

        /*
153 154
	 * Same as CR_GOAL_LEN_FAST but is allowed to reduce the goal
         * length to the best available length for faster allocation.
155 156 157 158
	 */
	CR_BEST_AVAIL_LEN,

	/*
159 160 161 162
	 * Reads each block group sequentially, performing disk IO if
	 * necessary, to find find_suitable block group. Tries to
	 * allocate goal length but might trim the request if nothing
	 * is found after enough tries.
163 164 165 166
	 */
	CR_GOAL_LEN_SLOW,

	/*
167 168 169
	 * Finds the first free set of blocks and allocates
	 * those. This is only used in rare cases when
	 * CR_GOAL_LEN_SLOW also fails to allocate anything.
170 171
	 */
	CR_ANY_FREE,
172 173 174 175 176

	/*
	 * Number of criterias defined.
	 */
	EXT4_MB_NUM_CRS
177 178
};

179
/*
180
 * Flags used in mballoc's allocation_context flags field.
181 182 183 184
 *
 * Also used to show what's going on for debugging purposes when the
 * flag field is exported via the traceport interface
 */
185

186
/* prefer goal again. length */
187
#define EXT4_MB_HINT_MERGE		0x0001
188
/* blocks already reserved */
189
#define EXT4_MB_HINT_RESERVED		0x0002
190
/* metadata is being allocated */
191
#define EXT4_MB_HINT_METADATA		0x0004
192
/* first blocks in the file */
193
#define EXT4_MB_HINT_FIRST		0x0008
194
/* search for the best chunk */
195
#define EXT4_MB_HINT_BEST		0x0010
196
/* data is being allocated */
197
#define EXT4_MB_HINT_DATA		0x0020
198
/* don't preallocate (for tails) */
199
#define EXT4_MB_HINT_NOPREALLOC		0x0040
200
/* allocate for locality group */
201
#define EXT4_MB_HINT_GROUP_ALLOC	0x0080
202
/* allocate goal blocks or none */
203
#define EXT4_MB_HINT_GOAL_ONLY		0x0100
204
/* goal is meaningful */
205
#define EXT4_MB_HINT_TRY_GOAL		0x0200
206
/* blocks already pre-reserved by delayed allocation */
207
#define EXT4_MB_DELALLOC_RESERVED	0x0400
208 209
/* We are doing stream allocation */
#define EXT4_MB_STREAM_ALLOC		0x0800
210 211
/* Use reserved root blocks if needed */
#define EXT4_MB_USE_ROOT_BLOCKS		0x1000
Lukas Czerner's avatar
Lukas Czerner committed
212 213
/* Use blocks from reserved pool */
#define EXT4_MB_USE_RESERVED		0x2000
214 215
/* Do strict check for free blocks while retrying block allocation */
#define EXT4_MB_STRICT_CHECK		0x4000
216 217
/* Large fragment size list lookup succeeded at least once for
 * CR_POWER2_ALIGNED */
218
#define EXT4_MB_CR_POWER2_ALIGNED_OPTIMIZED		0x8000
219 220
/* Avg fragment size rb tree lookup succeeded at least once for
 * CR_GOAL_LEN_FAST */
221
#define EXT4_MB_CR_GOAL_LEN_FAST_OPTIMIZED		0x00010000
222 223
/* Avg fragment size rb tree lookup succeeded at least once for
 * CR_BEST_AVAIL_LEN */
224
#define EXT4_MB_CR_BEST_AVAIL_LEN_OPTIMIZED		0x00020000
225

226 227 228
struct ext4_allocation_request {
	/* target inode for block we're allocating */
	struct inode *inode;
229 230
	/* how many blocks we want to allocate */
	unsigned int len;
231 232 233 234 235 236
	/* 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;
237 238 239 240 241
	/* 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 */
242 243
	ext4_fsblk_t pright;
	/* flags. see above EXT4_MB_HINT_* */
244
	unsigned int flags;
245 246
};

247 248 249 250 251 252 253
/*
 * 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.
 */
254 255 256 257
#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)
258
#define EXT4_MAP_DELAYED	BIT(BH_Delay)
259
#define EXT4_MAP_FLAGS		(EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
260 261
				 EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY |\
				 EXT4_MAP_DELAYED)
262 263 264 265 266 267 268 269

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

270 271 272 273 274 275 276 277
/*
 * Block validity checking, system zone rbtree.
 */
struct ext4_system_blocks {
	struct rb_root root;
	struct rcu_head rcu;
};

278 279 280 281 282
/*
 * Flags for ext4_io_end->flags
 */
#define	EXT4_IO_END_UNWRITTEN	0x0001

283 284 285 286 287 288
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 */
};

289
/*
290
 * For converting unwritten extents on a work queue. 'handle' is used for
291
 * buffered writeback.
292
 */
293
typedef struct ext4_io_end {
294
	struct list_head	list;		/* per-file finished IO list */
295 296
	handle_t		*handle;	/* handle reserved for extent
						 * conversion */
297
	struct inode		*inode;		/* file being written to */
298 299
	struct bio		*bio;		/* Linked list of completed
						 * bios covering the extent */
300
	unsigned int		flag;		/* unwritten or not */
301
	refcount_t		count;		/* reference counter */
302
	struct list_head	list_vec;	/* list of ext4_io_end_vec */
303 304
} ext4_io_end_t;

305
struct ext4_io_submit {
306
	struct writeback_control *io_wbc;
307 308 309 310 311
	struct bio		*io_bio;
	ext4_io_end_t		*io_end;
	sector_t		io_next_block;
};

312 313 314
/*
 * Special inodes numbers
 */
315 316
#define	EXT4_BAD_INO		 1	/* Bad blocks inode */
#define EXT4_ROOT_INO		 2	/* Root inode */
317 318
#define EXT4_USR_QUOTA_INO	 3	/* User quota inode */
#define EXT4_GRP_QUOTA_INO	 4	/* Group quota inode */
319 320 321 322
#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 */
323

324 325
/* First non-reserved inode for old ext4 filesystems */
#define EXT4_GOOD_OLD_FIRST_INO	11
326 327 328 329

/*
 * Maximal count of links to a file
 */
330
#define EXT4_LINK_MAX		65000
331 332 333 334

/*
 * Macro-instructions used to manage several block sizes
 */
335
#define EXT4_MIN_BLOCK_SIZE		1024
336 337
#define	EXT4_MAX_BLOCK_SIZE		65536
#define EXT4_MIN_BLOCK_LOG_SIZE		10
338
#define EXT4_MAX_BLOCK_LOG_SIZE		16
339
#define EXT4_MAX_CLUSTER_LOG_SIZE	30
340
#ifdef __KERNEL__
341
# define EXT4_BLOCK_SIZE(s)		((s)->s_blocksize)
342
#else
343
# define EXT4_BLOCK_SIZE(s)		(EXT4_MIN_BLOCK_SIZE << (s)->s_log_block_size)
344
#endif
345
#define	EXT4_ADDR_PER_BLOCK(s)		(EXT4_BLOCK_SIZE(s) / sizeof(__u32))
346 347
#define EXT4_CLUSTER_SIZE(s)		(EXT4_BLOCK_SIZE(s) << \
					 EXT4_SB(s)->s_cluster_bits)
348
#ifdef __KERNEL__
349
# define EXT4_BLOCK_SIZE_BITS(s)	((s)->s_blocksize_bits)
350
# define EXT4_CLUSTER_BITS(s)		(EXT4_SB(s)->s_cluster_bits)
351
#else
352
# define EXT4_BLOCK_SIZE_BITS(s)	((s)->s_log_block_size + 10)
353 354
#endif
#ifdef __KERNEL__
355 356 357
#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)
358
#else
359 360
#define EXT4_INODE_SIZE(s)	(((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \
				 EXT4_GOOD_OLD_INODE_SIZE : \
361
				 (s)->s_inode_size)
362 363
#define EXT4_FIRST_INO(s)	(((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \
				 EXT4_GOOD_OLD_FIRST_INO : \
364 365
				 (s)->s_first_ino)
#endif
Amit Arora's avatar
Amit Arora committed
366
#define EXT4_BLOCK_ALIGN(size, blkbits)		ALIGN((size), (1 << (blkbits)))
367 368 369
#define EXT4_MAX_BLOCKS(size, offset, blkbits) \
	((EXT4_BLOCK_ALIGN(size + offset, blkbits) >> blkbits) - (offset >> \
								  blkbits))
370

371 372 373 374 375 376 377
/* 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)
378 379 380 381 382
/* 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))
383 384 385
/* 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))
386 387 388 389 390
/* 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))
391

392 393 394
/*
 * Structure of a blocks group descriptor
 */
395
struct ext4_group_desc
396
{
397
	__le32	bg_block_bitmap_lo;	/* Blocks bitmap block */
398 399
	__le32	bg_inode_bitmap_lo;	/* Inodes bitmap block */
	__le32	bg_inode_table_lo;	/* Inodes table block */
400 401 402
	__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 */
403
	__le16	bg_flags;		/* EXT4_BG_flags (INODE_UNINIT, etc) */
404 405 406
	__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 */
407
	__le16  bg_itable_unused_lo;	/* Unused inodes count */
408
	__le16  bg_checksum;		/* crc16(sb_uuid+group+desc) */
409 410 411
	__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 */
412 413 414
	__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 */
415
	__le16  bg_itable_unused_hi;    /* Unused inodes count MSB */
416 417 418 419
	__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;
420 421
};

422 423 424 425 426 427 428
#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))

429 430 431 432 433
/*
 * Structure of a flex block group info
 */

struct flex_groups {
434 435 436
	atomic64_t	free_clusters;
	atomic_t	free_inodes;
	atomic_t	used_dirs;
437 438
};

439 440 441 442
#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 */

443 444 445
/*
 * Macro-instructions used to manage group descriptors
 */
446
#define EXT4_MIN_DESC_SIZE		32
447
#define EXT4_MIN_DESC_SIZE_64BIT	64
448 449
#define	EXT4_MAX_DESC_SIZE		EXT4_MIN_BLOCK_SIZE
#define EXT4_DESC_SIZE(s)		(EXT4_SB(s)->s_desc_size)
450
#ifdef __KERNEL__
451
# define EXT4_BLOCKS_PER_GROUP(s)	(EXT4_SB(s)->s_blocks_per_group)
452
# define EXT4_CLUSTERS_PER_GROUP(s)	(EXT4_SB(s)->s_clusters_per_group)
453 454 455
# 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)
456
#else
457
# define EXT4_BLOCKS_PER_GROUP(s)	((s)->s_blocks_per_group)
458
# define EXT4_DESC_PER_BLOCK(s)		(EXT4_BLOCK_SIZE(s) / EXT4_DESC_SIZE(s))
459
# define EXT4_INODES_PER_GROUP(s)	((s)->s_inodes_per_group)
460 461 462 463 464
#endif

/*
 * Constants relative to the data blocks
 */
465 466 467 468 469
#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)
470 471 472 473

/*
 * Inode flags
 */
474 475 476 477 478 479 480 481
#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 */
482
/* Reserved for compression usage... */
483 484 485
#define EXT4_DIRTY_FL			0x00000100
#define EXT4_COMPRBLK_FL		0x00000200 /* One or more compressed clusters */
#define EXT4_NOCOMPR_FL			0x00000400 /* Don't compress */
486 487
	/* nb: was previously EXT2_ECOMPR_FL */
#define EXT4_ENCRYPT_FL			0x00000800 /* encrypted file */
488
/* End compression flags --- maybe not all used */
489 490 491 492 493 494
#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
495
#define EXT4_HUGE_FILE_FL               0x00040000 /* Set to each huge file */
496
#define EXT4_EXTENTS_FL			0x00080000 /* Inode uses extents */
497
#define EXT4_VERITY_FL			0x00100000 /* Verity protected inode */
498
#define EXT4_EA_INODE_FL	        0x00200000 /* Inode used for large EA */
499
/* 0x00400000 was formerly EXT4_EOFBLOCKS_FL */
Ira Weiny's avatar
Ira Weiny committed
500 501 502

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

503
#define EXT4_INLINE_DATA_FL		0x10000000 /* Inode has inline data. */
504
#define EXT4_PROJINHERIT_FL		0x20000000 /* Create with parents projid */
505
#define EXT4_CASEFOLD_FL		0x40000000 /* Casefolded directory */
Aneesh Kumar K.V's avatar
Aneesh Kumar K.V committed
506
#define EXT4_RESERVED_FL		0x80000000 /* reserved for ext4 lib */
507

508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535
/* 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)
536

537 538
/* Flags that should be inherited by new inodes from their parent. */
#define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\
539
			   EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
540
			   EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\
Li Xi's avatar
Li Xi committed
541
			   EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL |\
Ira Weiny's avatar
Ira Weiny committed
542 543
			   EXT4_PROJINHERIT_FL | EXT4_CASEFOLD_FL |\
			   EXT4_DAX_FL)
544

545
/* Flags that are appropriate for regular files (all but dir-specific ones). */
546 547
#define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL | EXT4_CASEFOLD_FL |\
			   EXT4_PROJINHERIT_FL))
548 549 550 551

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

552 553 554
/* 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
555 556
/* Flags which are mutually exclusive to DAX */
#define EXT4_DAX_MUT_EXCL (EXT4_VERITY_FL | EXT4_ENCRYPT_FL |\
557
			   EXT4_JOURNAL_DATA_FL | EXT4_INLINE_DATA_FL)
Ira Weiny's avatar
Ira Weiny committed
558

559 560 561 562 563 564 565 566 567 568 569
/* 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;
}

570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585
/*
 * 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 */
586
	EXT4_INODE_ENCRYPT	= 11,	/* Encrypted file */
587 588 589 590 591 592 593 594 595
/* 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 */
596
	EXT4_INODE_VERITY	= 20,	/* Verity protected inode */
597
	EXT4_INODE_EA_INODE	= 21,	/* Inode used for large EA */
598
/* 22 was formerly EXT4_INODE_EOFBLOCKS */
Ira Weiny's avatar
Ira Weiny committed
599
	EXT4_INODE_DAX		= 25,	/* Inode is DAX */
600
	EXT4_INODE_INLINE_DATA	= 28,	/* Data in inode. */
601
	EXT4_INODE_PROJINHERIT	= 29,	/* Create with parents projid */
602
	EXT4_INODE_CASEFOLD	= 30,	/* Casefolded directory */
603 604 605 606
	EXT4_INODE_RESERVED	= 31,	/* reserved for ext4 lib */
};

/*
607 608 609 610 611 612 613 614 615
 * 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.
616 617 618
 *
 * It's not paranoia if the Murphy's Law really *is* out to get you.  :-)
 */
619
#define TEST_FLAG_VALUE(FLAG) (EXT4_##FLAG##_FL == (1U << EXT4_INODE_##FLAG))
620 621
#define CHECK_FLAG_VALUE(FLAG) BUILD_BUG_ON(!TEST_FLAG_VALUE(FLAG))

622 623 624 625 626 627 628 629 630 631 632 633 634
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);
635
	CHECK_FLAG_VALUE(ENCRYPT);
636 637 638 639 640 641 642 643
	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);
644
	CHECK_FLAG_VALUE(VERITY);
645
	CHECK_FLAG_VALUE(EA_INODE);
646
	CHECK_FLAG_VALUE(INLINE_DATA);
647
	CHECK_FLAG_VALUE(PROJINHERIT);
648
	CHECK_FLAG_VALUE(CASEFOLD);
649 650 651
	CHECK_FLAG_VALUE(RESERVED);
}

652 653 654 655 656 657 658 659 660 661 662 663
#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

664 665
/* The struct ext4_new_group_input in kernel space, with free_blocks_count */
struct ext4_new_group_data {
666
	__u32 group;
Laurent Vivier's avatar
Laurent Vivier committed
667 668 669
	__u64 block_bitmap;
	__u64 inode_bitmap;
	__u64 inode_table;
670 671
	__u32 blocks_count;
	__u16 reserved_blocks;
672 673
	__u16 mdata_blocks;
	__u32 free_clusters_count;
674 675
};

676 677 678 679 680 681 682 683
/* 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
684
/*
685
 * Flags used by ext4_map_blocks()
Amit Arora's avatar
Amit Arora committed
686
 */
687
	/* Allocate any needed blocks and/or convert an unwritten
688
	   extent to be an initialized ext4 */
689
#define EXT4_GET_BLOCKS_CREATE			0x0001
690 691 692
	/* 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|\
693
						 EXT4_GET_BLOCKS_CREATE)
Lukas Czerner's avatar
Lukas Czerner committed
694 695
	/* Caller is from the delayed allocation writeout path
	 * finally doing the actual allocation of delayed blocks */
696
#define EXT4_GET_BLOCKS_DELALLOC_RESERVE	0x0004
697
	/* caller is from the direct IO path, request to creation of an
698
	unwritten extents if not allocated, split the unwritten
699
	extent if blocks has been preallocated already*/
700
#define EXT4_GET_BLOCKS_PRE_IO			0x0008
701
#define EXT4_GET_BLOCKS_CONVERT			0x0010
702
#define EXT4_GET_BLOCKS_IO_CREATE_EXT		(EXT4_GET_BLOCKS_PRE_IO|\
703
					 EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT)
704 705
	/* Convert extent to initialized after IO complete */
#define EXT4_GET_BLOCKS_IO_CONVERT_EXT		(EXT4_GET_BLOCKS_CONVERT|\
706
					 EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT)
Lukas Czerner's avatar
Lukas Czerner committed
707 708 709
	/* 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
710 711
	/* Don't normalize allocation size (used for fallocate) */
#define EXT4_GET_BLOCKS_NO_NORMALIZE		0x0040
712
	/* Convert written extents to unwritten */
713
#define EXT4_GET_BLOCKS_CONVERT_UNWRITTEN	0x0100
714 715 716 717
	/* 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)
718 719 720
	/* Caller will submit data before dropping transaction handle. This
	 * allows jbd2 to avoid submitting data before commit. */
#define EXT4_GET_BLOCKS_IO_SUBMIT		0x0400
721 722
	/* Caller is in the atomic contex, find extent if it has been cached */
#define EXT4_GET_BLOCKS_CACHED_NOWAIT		0x0800
723

724
/*
725
 * The bit position of these flags must not overlap with any of the
726
 * EXT4_GET_BLOCKS_*.  They are used by ext4_find_extent(),
727
 * read_extent_tree_block(), ext4_split_extent_at(),
728 729 730 731
 * 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.
732
 */
733 734
#define EXT4_EX_NOCACHE				0x40000000
#define EXT4_EX_FORCE_CACHE			0x20000000
735
#define EXT4_EX_NOFAIL				0x10000000
736

737 738 739
/*
 * Flags used by ext4_free_blocks
 */
740 741 742 743
#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
744 745
#define EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER	0x0010
#define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER	0x0020
746
#define EXT4_FREE_BLOCKS_RERESERVE_CLUSTER      0x0040
747

748
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
749 750 751
/*
 * ioctl commands in 32 bit emulation
 */
752 753 754 755 756
#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)
757
#define EXT4_IOC32_GROUP_ADD		_IOW('f', 8, struct compat_ext4_new_group_input)
758 759
#define EXT4_IOC32_GETVERSION_OLD	FS_IOC32_GETVERSION
#define EXT4_IOC32_SETVERSION_OLD	FS_IOC32_SETVERSION
760
#endif
761

762
/* Max physical block we can address w/o extents */
763 764
#define EXT4_MAX_BLOCK_FILE_PHYS	0xFFFFFFFF

765
/* Max logical block we can support */
766
#define EXT4_MAX_LOGICAL_BLOCK		0xFFFFFFFE
767

768 769 770
/*
 * Structure of an inode on the disk
 */
771
struct ext4_inode {
772 773
	__le16	i_mode;		/* File mode */
	__le16	i_uid;		/* Low 16 bits of Owner Uid */
774
	__le32	i_size_lo;	/* Size in bytes */
775
	__le32	i_atime;	/* Access time */
Kalpak Shah's avatar
Kalpak Shah committed
776
	__le32	i_ctime;	/* Inode Change time */
777 778 779 780
	__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 */
781
	__le32	i_blocks_lo;	/* Blocks count */
782 783 784
	__le32	i_flags;	/* File flags */
	union {
		struct {
785
			__le32  l_i_version;
786 787 788 789 790 791 792 793
		} linux1;
		struct {
			__u32  h_i_translator;
		} hurd1;
		struct {
			__u32  m_i_reserved1;
		} masix1;
	} osd1;				/* OS dependent 1 */
794
	__le32	i_block[EXT4_N_BLOCKS];/* Pointers to blocks */
795
	__le32	i_generation;	/* File version (for NFS) */
796
	__le32	i_file_acl_lo;	/* File ACL */
797
	__le32	i_size_high;
798
	__le32	i_obso_faddr;	/* Obsoleted fragment address */
799 800
	union {
		struct {
801
			__le16	l_i_blocks_high; /* were l_i_reserved1 */
802
			__le16	l_i_file_acl_high;
Dave Kleikamp's avatar
Dave Kleikamp committed
803
			__le16	l_i_uid_high;	/* these 2 fields */
804
			__le16	l_i_gid_high;	/* were reserved2[0] */
805 806
			__le16	l_i_checksum_lo;/* crc32c(uuid+inum+inode) LE */
			__le16	l_i_reserved;
807 808
		} linux2;
		struct {
809
			__le16	h_i_reserved1;	/* Obsoleted fragment number/size which are removed in ext4 */
810 811 812 813 814 815
			__u16	h_i_mode_high;
			__u16	h_i_uid_high;
			__u16	h_i_gid_high;
			__u32	h_i_author;
		} hurd2;
		struct {
816
			__le16	h_i_reserved1;	/* Obsoleted fragment number/size which are removed in ext4 */
817
			__le16	m_i_file_acl_high;
818 819 820 821
			__u32	m_i_reserved2[2];
		} masix2;
	} osd2;				/* OS dependent 2 */
	__le16	i_extra_isize;
822
	__le16	i_checksum_hi;	/* crc32c(uuid+inum+inode) BE */
Kalpak Shah's avatar
Kalpak Shah committed
823 824 825 826 827
	__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) */
828
	__le32  i_version_hi;	/* high 32 bits for 64-bit version */
829
	__le32	i_projid;	/* Project ID */
830 831
};

Kalpak Shah's avatar
Kalpak Shah committed
832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851
#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))			\

852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872
/*
 * 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.
 */

873
static inline __le32 ext4_encode_extra_time(struct timespec64 ts)
Kalpak Shah's avatar
Kalpak Shah committed
874
{
875 876
	u32 extra = ((ts.tv_sec - (s32)ts.tv_sec) >> 32) & EXT4_EPOCH_MASK;
	return cpu_to_le32(extra | (ts.tv_nsec << EXT4_EPOCH_BITS));
Kalpak Shah's avatar
Kalpak Shah committed
877 878
}

879 880
static inline struct timespec64 ext4_decode_extra_time(__le32 base,
						       __le32 extra)
Kalpak Shah's avatar
Kalpak Shah committed
881
{
882 883
	struct timespec64 ts = { .tv_sec = (signed)le32_to_cpu(base) };

884
	if (unlikely(extra & cpu_to_le32(EXT4_EPOCH_MASK)))
885 886 887
		ts.tv_sec += (u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK) << 32;
	ts.tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS;
	return ts;
Kalpak Shah's avatar
Kalpak Shah committed
888 889
}

890
#define EXT4_INODE_SET_XTIME_VAL(xtime, inode, raw_inode, ts)			\
891
do {										\
892 893 894 895 896
	if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) {	\
		(raw_inode)->xtime = cpu_to_le32((ts).tv_sec);			\
		(raw_inode)->xtime ## _extra = ext4_encode_extra_time(ts);	\
	} else									\
		(raw_inode)->xtime = cpu_to_le32(clamp_t(int32_t, (ts).tv_sec, S32_MIN, S32_MAX));	\
Kalpak Shah's avatar
Kalpak Shah committed
897 898
} while (0)

899 900
#define EXT4_INODE_SET_ATIME(inode, raw_inode)						\
	EXT4_INODE_SET_XTIME_VAL(i_atime, inode, raw_inode, inode_get_atime(inode))
901

902 903 904 905
#define EXT4_INODE_SET_MTIME(inode, raw_inode)						\
	EXT4_INODE_SET_XTIME_VAL(i_mtime, inode, raw_inode, inode_get_mtime(inode))

#define EXT4_INODE_SET_CTIME(inode, raw_inode)						\
906 907 908 909 910 911 912 913 914 915 916 917 918 919
	EXT4_INODE_SET_XTIME_VAL(i_ctime, inode, raw_inode, inode_get_ctime(inode))

#define EXT4_EINODE_SET_XTIME(xtime, einode, raw_inode)				\
	if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime))			\
		EXT4_INODE_SET_XTIME_VAL(xtime, &((einode)->vfs_inode),		\
					 raw_inode, (einode)->xtime)

#define EXT4_INODE_GET_XTIME_VAL(xtime, inode, raw_inode)			\
	(EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra) ?	\
		ext4_decode_extra_time((raw_inode)->xtime,				\
				       (raw_inode)->xtime ## _extra) :		\
		(struct timespec64) {						\
			.tv_sec = (signed)le32_to_cpu((raw_inode)->xtime)	\
		})
Kalpak Shah's avatar
Kalpak Shah committed
920

921 922 923 924 925 926 927
#define EXT4_INODE_GET_ATIME(inode, raw_inode)					\
do {										\
	inode_set_atime_to_ts(inode,						\
		EXT4_INODE_GET_XTIME_VAL(i_atime, inode, raw_inode));		\
} while (0)

#define EXT4_INODE_GET_MTIME(inode, raw_inode)					\
928
do {										\
929 930
	inode_set_mtime_to_ts(inode,						\
		EXT4_INODE_GET_XTIME_VAL(i_mtime, inode, raw_inode));		\
Kalpak Shah's avatar
Kalpak Shah committed
931 932
} while (0)

933 934 935 936 937
#define EXT4_INODE_GET_CTIME(inode, raw_inode)					\
do {										\
	inode_set_ctime_to_ts(inode,						\
		EXT4_INODE_GET_XTIME_VAL(i_ctime, inode, raw_inode));		\
} while (0)
938

939 940 941 942 943 944 945 946
#define EXT4_EINODE_GET_XTIME(xtime, einode, raw_inode)				\
do {										\
	if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime)) 			\
		(einode)->xtime =						\
			EXT4_INODE_GET_XTIME_VAL(xtime, &(einode->vfs_inode),	\
						 raw_inode);			\
	else									\
		(einode)->xtime = (struct timespec64){0, 0};			\
Kalpak Shah's avatar
Kalpak Shah committed
947 948
} while (0)

949 950
#define i_disk_version osd1.linux1.l_i_version

951 952
#if defined(__KERNEL__) || defined(__linux__)
#define i_reserved1	osd1.linux1.l_i_reserved1
953
#define i_file_acl_high	osd2.linux2.l_i_file_acl_high
954
#define i_blocks_high	osd2.linux2.l_i_blocks_high
955 956 957 958
#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
959
#define i_checksum_lo	osd2.linux2.l_i_checksum_lo
960 961 962 963 964 965 966 967 968 969 970

#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
971
#define i_file_acl_high	osd2.masix2.m_i_file_acl_high
972 973 974 975
#define i_reserved2	osd2.masix2.m_i_reserved2

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

976
#include "extents_status.h"
977
#include "fast_commit.h"
978

979 980 981 982 983 984 985 986 987 988 989 990 991 992 993
/*
 * 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
994
 *  I_DATA_SEM_EA     - Used for ea_inodes only
995 996 997 998 999
 */
enum {
	I_DATA_SEM_NORMAL = 0,
	I_DATA_SEM_OTHER,
	I_DATA_SEM_QUOTA,
1000
	I_DATA_SEM_EA
1001 1002 1003
};


1004 1005 1006 1007 1008 1009
/*
 * fourth extended file system inode data in memory
 */
struct ext4_inode_info {
	__le32	i_data[15];	/* unconverted */
	__u32	i_dtime;
1010
	ext4_fsblk_t	i_file_acl;
1011 1012 1013 1014

	/*
	 * i_block_group is the number of the block group which contains
	 * this file's inode.  Constant across the lifetime of the inode,
1015
	 * it is used for making block allocation decisions - we try to
1016 1017 1018 1019
	 * 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;
1020
	ext4_lblk_t	i_dir_start_lookup;
1021
#if (BITS_PER_LONG < 64)
1022
	unsigned long	i_state_flags;		/* Dynamic state flags */
1023
#endif
1024
	unsigned long	i_flags;
1025 1026 1027

	/*
	 * Extended attributes can be read independently of the main file
1028
	 * data. Taking i_rwsem even when reading would cause contention
1029 1030 1031 1032 1033 1034
	 * 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;

1035 1036 1037 1038 1039 1040 1041 1042
	/*
	 * 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 */
	};
1043

1044 1045
	/* Fast commit related info */

1046 1047
	/* For tracking dentry create updates */
	struct list_head i_fc_dilist;
1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060
	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;
1061
	atomic_t i_unwritten; /* Nr. of inflight conversions pending */
1062 1063 1064 1065 1066 1067 1068

	/* 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;

1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097
	/*
	 * 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;
1098
	struct jbd2_inode *jinode;
1099

1100 1101
	spinlock_t i_raw_lock;	/* protects updates to the raw inode */

1102 1103
	/*
	 * File creation time. Its function is same as that of
1104
	 * struct timespec64 i_{a,c,m}time in the generic inode.
1105
	 */
1106
	struct timespec64 i_crtime;
1107 1108

	/* mballoc */
1109
	atomic_t i_prealloc_active;
1110 1111 1112 1113

	/* allocation reservation info for delalloc */
	/* In case of bigalloc, this refer to clusters rather than blocks */
	unsigned int i_reserved_data_blocks;
1114 1115
	struct rb_root i_prealloc_node;
	rwlock_t i_prealloc_lock;
1116

1117 1118 1119
	/* extents status tree */
	struct ext4_es_tree i_es_tree;
	rwlock_t i_es_lock;
1120
	struct list_head i_es_list;
1121
	unsigned int i_es_all_nr;	/* protected by i_es_lock */
1122
	unsigned int i_es_shk_nr;	/* protected by i_es_lock */
1123 1124 1125
	ext4_lblk_t i_es_shrink_lblk;	/* Offset where we start searching for
					   extents to shrink. Protected by
					   i_es_lock  */
1126

1127 1128 1129
	/* ialloc */
	ext4_group_t	i_last_alloc_group;

1130 1131 1132
	/* pending cluster reservations for bigalloc file systems */
	struct ext4_pending_tree i_pending_tree;

1133 1134 1135
	/* on-disk additional length */
	__u16 i_extra_isize;

1136 1137 1138 1139
	/* Indicate the inline data space. */
	u16 i_inline_off;
	u16 i_inline_size;

1140 1141 1142 1143
#ifdef CONFIG_QUOTA
	/* quota space reservation, managed internally by quota code */
	qsize_t i_reserved_quota;
#endif
1144

1145
	/* Lock protecting lists below */
1146
	spinlock_t i_completed_io_lock;
1147 1148 1149 1150 1151 1152
	/*
	 * 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;
1153 1154

	spinlock_t i_block_reservation_lock;
1155 1156 1157 1158 1159 1160 1161

	/*
	 * Transactions that contain inode's metadata needed to complete
	 * fsync and fdatasync, respectively.
	 */
	tid_t i_sync_tid;
	tid_t i_datasync_tid;
1162

1163
#ifdef CONFIG_QUOTA
1164
	struct dquot __rcu *i_dquot[MAXQUOTAS];
1165 1166
#endif

1167 1168
	/* Precomputed uuid+inum+igen checksum for seeding inode checksums */
	__u32 i_csum_seed;
1169

Li Xi's avatar
Li Xi committed
1170
	kprojid_t i_projid;
1171 1172
};

1173 1174 1175
/*
 * File system states
 */
1176 1177 1178
#define	EXT4_VALID_FS			0x0001	/* Unmounted cleanly */
#define	EXT4_ERROR_FS			0x0002	/* Errors detected */
#define	EXT4_ORPHAN_FS			0x0004	/* Orphans being recovered */
1179
#define EXT4_FC_REPLAY			0x0020	/* Fast commit replay ongoing */
1180

1181 1182 1183 1184 1185 1186 1187
/*
 * 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 */

1188
/*
1189
 * Mount flags set via mount options or defaults
1190
 */
1191
#define EXT4_MOUNT_NO_MBCACHE		0x00001 /* Do not use mbcache */
1192 1193 1194 1195 1196
#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 */
1197
#define EXT4_MOUNT_ERRORS_MASK		0x00070
1198 1199
#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
1200
#ifdef CONFIG_FS_DAX
1201
#define EXT4_MOUNT_DAX_ALWAYS		0x00200	/* Direct Access */
Ross Zwisler's avatar
Ross Zwisler committed
1202
#else
1203
#define EXT4_MOUNT_DAX_ALWAYS		0
Ross Zwisler's avatar
Ross Zwisler committed
1204
#endif
1205 1206 1207 1208 1209 1210 1211 1212
#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 */
1213
#define EXT4_MOUNT_NO_AUTO_DA_ALLOC	0x10000	/* No auto delalloc mapping */
1214
#define EXT4_MOUNT_BARRIER		0x20000 /* Use block barriers */
1215 1216 1217 1218 1219 1220 1221 1222 1223
#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 */
1224
#define EXT4_MOUNT_DIOREAD_NOLOCK	0x400000 /* Enable support for dio read nolocking */
1225
#define EXT4_MOUNT_JOURNAL_CHECKSUM	0x800000 /* Journal checksums */
1226
#define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT	0x1000000 /* Journal Async Commit */
1227
#define EXT4_MOUNT_WARN_ON_ERROR	0x2000000 /* Trigger WARN_ON on error */
1228
#define EXT4_MOUNT_NO_PREFETCH_BLOCK_BITMAPS 0x4000000
1229
#define EXT4_MOUNT_DELALLOC		0x8000000 /* Delalloc support */
1230
#define EXT4_MOUNT_DATA_ERR_ABORT	0x10000000 /* Abort on file data write */
1231
#define EXT4_MOUNT_BLOCK_VALIDITY	0x20000000 /* Block validity checking */
1232
#define EXT4_MOUNT_DISCARD		0x40000000 /* Issue DISCARD requests */
1233
#define EXT4_MOUNT_INIT_INODE_TABLE	0x80000000 /* Initialize uninitialized itables */
1234

1235 1236 1237 1238 1239
/*
 * 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.
 */
1240 1241
#define EXT4_MOUNT2_EXPLICIT_DELALLOC	0x00000001 /* User explicitly
						      specified delalloc */
1242 1243 1244
#define EXT4_MOUNT2_STD_GROUP_SIZE	0x00000002 /* We have standard group
						      size of blocksize * 8
						      blocks */
1245 1246
#define EXT4_MOUNT2_HURD_COMPAT		0x00000004 /* Support HURD-castrated
						      file systems */
1247 1248 1249
#define EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM	0x00000008 /* User explicitly
						specified journal checksum */

1250
#define EXT4_MOUNT2_JOURNAL_FAST_COMMIT	0x00000010 /* Journal fast commit */
1251 1252
#define EXT4_MOUNT2_DAX_NEVER		0x00000020 /* Do not allow Direct Access */
#define EXT4_MOUNT2_DAX_INODE		0x00000040 /* For printing options only */
1253 1254 1255
#define EXT4_MOUNT2_MB_OPTIMIZE_SCAN	0x00000080 /* Optimize group
						    * scanning in mballoc
						    */
1256
#define EXT4_MOUNT2_ABORT		0x00000100 /* Abort filesystem */
1257

1258 1259 1260 1261
#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
1262 1263
#define test_opt(sb, opt)		(EXT4_SB(sb)->s_mount_opt & \
					 EXT4_MOUNT_##opt)
1264

1265 1266 1267 1268 1269 1270 1271
#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)

1272 1273 1274 1275
#define ext4_test_and_set_bit		__test_and_set_bit_le
#define ext4_set_bit			__set_bit_le
#define ext4_test_and_clear_bit		__test_and_clear_bit_le
#define ext4_clear_bit			__clear_bit_le
Akinobu Mita's avatar
Akinobu Mita committed
1276 1277 1278
#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
1279

1280
extern void mb_set_bits(void *bm, int cur, int len);
1281

1282 1283 1284
/*
 * Maximal mount counts between two filesystem checks
 */
1285 1286
#define EXT4_DFL_MAX_MNT_COUNT		20	/* Allow 20 mounts */
#define EXT4_DFL_CHECKINTERVAL		0	/* Don't use interval check */
1287 1288 1289 1290

/*
 * Behaviour when detecting errors
 */
1291 1292 1293 1294
#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
1295

1296 1297 1298
/* Metadata checksum algorithm codes */
#define EXT4_CRC32C_CHKSUM		1

1299 1300
#define EXT4_LABEL_MAX			16

1301 1302 1303
/*
 * Structure of the super block
 */
1304
struct ext4_super_block {
1305
/*00*/	__le32	s_inodes_count;		/* Inodes count */
1306
	__le32	s_blocks_count_lo;	/* Blocks count */
1307 1308
	__le32	s_r_blocks_count_lo;	/* Reserved blocks count */
	__le32	s_free_blocks_count_lo;	/* Free blocks count */
1309 1310 1311
/*10*/	__le32	s_free_inodes_count;	/* Free inodes count */
	__le32	s_first_data_block;	/* First Data Block */
	__le32	s_log_block_size;	/* Block size */
1312
	__le32	s_log_cluster_size;	/* Allocation cluster size */
1313
/*20*/	__le32	s_blocks_per_group;	/* # Blocks per group */
1314
	__le32	s_clusters_per_group;	/* # Clusters per group */
1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330
	__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 */
	/*
1331
	 * These fields are for EXT4_DYNAMIC_REV superblocks only.
1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343
	 *
	 * 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 */
1344
	__le16  s_inode_size;		/* size of inode structure */
1345 1346 1347 1348 1349
	__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 */
1350
/*78*/	char	s_volume_name[EXT4_LABEL_MAX] __nonstring; /* volume name */
1351
/*88*/	char	s_last_mounted[64] __nonstring;	/* directory where last mounted */
1352 1353 1354
/*C8*/	__le32	s_algorithm_usage_bitmap; /* For compression */
	/*
	 * Performance hints.  Directory preallocation should only
1355
	 * happen if the EXT4_FEATURE_COMPAT_DIR_PREALLOC flag is on.
1356 1357 1358 1359 1360
	 */
	__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 */
	/*
1361
	 * Journaling support valid if EXT4_FEATURE_COMPAT_HAS_JOURNAL set.
1362 1363 1364 1365 1366 1367 1368
	 */
/*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 */
1369
	__u8	s_jnl_backup_type;
1370
	__le16  s_desc_size;		/* size of group descriptor */
Laurent Vivier's avatar
Laurent Vivier committed
1371
/*100*/	__le32	s_default_mount_opts;
1372
	__le32	s_first_meta_bg;	/* First metablock block group */
Laurent Vivier's avatar
Laurent Vivier committed
1373 1374
	__le32	s_mkfs_time;		/* When the filesystem was created */
	__le32	s_jnl_blocks[17];	/* Backup of the journal inode */
1375
	/* 64bit support valid if EXT4_FEATURE_INCOMPAT_64BIT */
Laurent Vivier's avatar
Laurent Vivier committed
1376 1377 1378
/*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
1379 1380 1381 1382
	__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 */
1383
	__le16  s_mmp_update_interval;  /* # seconds to wait in MMP checking */
Aneesh Kumar K.V's avatar
Aneesh Kumar K.V committed
1384 1385
	__le64  s_mmp_block;            /* Block for multi-mount protection */
	__le32  s_raid_stripe_width;    /* blocks on all data disks (N*stride)*/
1386
	__u8	s_log_groups_per_flex;  /* FLEX_BG group size */
1387
	__u8	s_checksum_type;	/* metadata checksum algorithm used */
1388 1389
	__u8	s_encryption_level;	/* versioning level for encryption */
	__u8	s_reserved_pad;		/* Padding to next 32bits */
1390
	__le64	s_kbytes_written;	/* nr of lifetime kilobytes written */
1391 1392 1393 1394 1395 1396
	__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 */
1397 1398 1399 1400 1401
#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 */
1402
	__u8	s_first_error_func[32] __nonstring;	/* function where the error happened */
1403 1404 1405 1406 1407
	__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 */
1408
	__u8	s_last_error_func[32] __nonstring;	/* function where the error happened */
1409 1410
#define EXT4_S_ERR_END offsetof(struct ext4_super_block, s_mount_opts)
	__u8	s_mount_opts[64];
1411 1412 1413
	__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 */
1414
	__le32	s_backup_bgs[2];	/* groups with sparse_super2 SBs */
1415
	__u8	s_encrypt_algos[4];	/* Encryption algorithms in use  */
1416 1417
	__u8	s_encrypt_pw_salt[16];	/* Salt used for string2key algorithm */
	__le32	s_lpf_ino;		/* Location of the lost+found inode */
1418
	__le32	s_prj_quota_inum;	/* inode for tracking project quota */
1419
	__le32	s_checksum_seed;	/* crc32c(uuid) if csum_seed set */
1420 1421 1422 1423 1424 1425
	__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;
1426 1427
	__u8	s_first_error_errcode;
	__u8    s_last_error_errcode;
1428 1429
	__le16  s_encoding;		/* Filename charset encoding */
	__le16  s_encoding_flags;	/* Filename charset encoding flags */
1430 1431
	__le32  s_orphan_file_inum;	/* Inode for tracking orphan inodes */
	__le32	s_reserved[94];		/* Padding to the end of the block */
1432
	__le32	s_checksum;		/* crc32c(superblock) */
1433 1434
};

1435 1436
#define EXT4_S_ERR_LEN (EXT4_S_ERR_END - EXT4_S_ERR_START)

1437
#ifdef __KERNEL__
1438

Jan Kara's avatar
Jan Kara committed
1439
/* Number of quota types we support */
Li Xi's avatar
Li Xi committed
1440
#define EXT4_MAXQUOTAS 3
Jan Kara's avatar
Jan Kara committed
1441

1442 1443
#define EXT4_ENC_UTF8_12_1	1

1444 1445
/* Types of ext4 journal triggers */
enum ext4_journal_trigger_type {
1446
	EXT4_JTR_ORPHAN_FILE,
1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462
	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);
}

1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477
#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 {
1478
	atomic_t ob_free_entries;	/* Number of free orphan entries in block */
1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491
	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 */
};

1492 1493 1494 1495 1496 1497 1498
/*
 * 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 */
1499
	unsigned long s_clusters_per_group; /* Number of clusters in a group */
1500 1501 1502 1503 1504
	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 */
1505
	ext4_group_t s_blockfile_groups;/* Groups acceptable for non-extent files */
1506
	unsigned long s_overhead;  /* # of fs overhead clusters */
1507 1508
	unsigned int s_cluster_ratio;	/* Number of blocks per cluster */
	unsigned int s_cluster_bits;	/* log2 of s_cluster_ratio */
1509 1510 1511
	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 */
1512
	/* Array of bh's for the block group descriptors */
1513
	struct buffer_head * __rcu *s_group_desc;
1514
	unsigned int s_mount_opt;
1515
	unsigned int s_mount_opt2;
1516
	unsigned long s_mount_flags;
1517
	unsigned int s_def_mount_opt;
1518
	unsigned int s_def_mount_opt2;
1519
	ext4_fsblk_t s_sb_block;
Lukas Czerner's avatar
Lukas Czerner committed
1520
	atomic64_t s_resv_clusters;
1521 1522
	kuid_t s_resuid;
	kgid_t s_resgid;
1523 1524 1525 1526 1527 1528 1529
	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;
1530
	unsigned int s_inode_goal;
1531 1532
	u32 s_hash_seed[4];
	int s_def_hash_version;
1533
	int s_hash_unsigned;	/* 3 if hash should be unsigned, 0 if not */
1534
	struct percpu_counter s_freeclusters_counter;
1535 1536
	struct percpu_counter s_freeinodes_counter;
	struct percpu_counter s_dirs_counter;
1537
	struct percpu_counter s_dirtyclusters_counter;
1538
	struct percpu_counter s_sra_exceeded_retry_limit;
1539 1540 1541 1542
	struct blockgroup_lock *s_blockgroup_lock;
	struct proc_dir_entry *s_proc;
	struct kobject s_kobj;
	struct completion s_kobj_unregister;
1543
	struct super_block *s_sb;
1544
	struct buffer_head *s_mmp_bh;
1545 1546 1547

	/* Journaling */
	struct journal_s *s_journal;
1548
	unsigned long s_ext4_flags;		/* Ext4 superblock flags */
1549 1550 1551 1552
	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;
1553 1554 1555
	unsigned long s_commit_interval;
	u32 s_max_batch_time;
	u32 s_min_batch_time;
1556
	struct file *s_journal_bdev_file;
1557
#ifdef CONFIG_QUOTA
1558 1559
	/* Names of quota files with journalled quota */
	char __rcu *s_qf_names[EXT4_MAXQUOTAS];
1560 1561 1562
	int s_jquota_fmt;			/* Format of quota to use */
#endif
	unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */
1563
	struct ext4_system_blocks __rcu *s_system_blks;
1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575

#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 */
1576
	struct ext4_group_info ** __rcu *s_group_info;
1577 1578 1579 1580
	struct inode *s_buddy_cache;
	spinlock_t s_md_lock;
	unsigned short *s_mb_offsets;
	unsigned int *s_mb_maxs;
1581
	unsigned int s_group_info_size;
1582
	unsigned int s_mb_free_pending;
1583
	struct list_head s_freed_data_list[2];	/* List of blocks to be freed
1584
						   after commit completed */
1585 1586
	struct list_head s_discard_list;
	struct work_struct s_discard_work;
1587
	atomic_t s_retry_alloc_pending;
1588 1589
	struct list_head *s_mb_avg_fragment_size;
	rwlock_t *s_mb_avg_fragment_size_locks;
1590 1591
	struct list_head *s_mb_largest_free_orders;
	rwlock_t *s_mb_largest_free_orders_locks;
1592 1593 1594

	/* tunables */
	unsigned long s_stripe;
1595
	unsigned int s_mb_max_linear_groups;
1596 1597 1598 1599 1600 1601
	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;
1602
	unsigned int s_max_dir_size_kb;
1603 1604 1605
	/* where last allocation was done - for stream allocation */
	unsigned long s_mb_last_group;
	unsigned long s_mb_last_start;
1606 1607
	unsigned int s_mb_prefetch;
	unsigned int s_mb_prefetch_limit;
1608
	unsigned int s_mb_best_avail_max_trim_order;
1609 1610 1611 1612 1613 1614

	/* 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 */
1615
	atomic_t s_bal_cX_ex_scanned[EXT4_MB_NUM_CRS];	/* total extents scanned */
1616
	atomic_t s_bal_groups_scanned;	/* number of groups scanned */
1617
	atomic_t s_bal_goals;	/* goal hits */
1618
	atomic_t s_bal_len_goals;	/* len goal hits */
1619 1620
	atomic_t s_bal_breaks;	/* too long searches */
	atomic_t s_bal_2orders;	/* 2^order hits */
1621 1622 1623
	atomic_t s_bal_p2_aligned_bad_suggestions;
	atomic_t s_bal_goal_fast_bad_suggestions;
	atomic_t s_bal_best_avail_bad_suggestions;
1624 1625 1626
	atomic64_t s_bal_cX_groups_considered[EXT4_MB_NUM_CRS];
	atomic64_t s_bal_cX_hits[EXT4_MB_NUM_CRS];
	atomic64_t s_bal_cX_failed[EXT4_MB_NUM_CRS];		/* cX loop didn't find blocks */
1627 1628
	atomic_t s_mb_buddies_generated;	/* number of buddies generated */
	atomic64_t s_mb_generation_time;
1629 1630 1631
	atomic_t s_mb_lost_chunks;
	atomic_t s_mb_preallocated;
	atomic_t s_mb_discarded;
1632
	atomic_t s_lock_busy;
1633 1634

	/* locality groups */
1635
	struct ext4_locality_group __percpu *s_locality_groups;
1636 1637 1638 1639 1640

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

1641 1642 1643
	/* the size of zero-out chunk */
	unsigned int s_extent_max_zeroout_kb;

1644
	unsigned int s_log_groups_per_flex;
1645
	struct flex_groups * __rcu *s_flex_groups;
1646
	ext4_group_t s_flex_groups_allocated;
1647

1648 1649
	/* workqueue for reserved extent conversions (buffered io) */
	struct workqueue_struct *rsv_conversion_wq;
1650 1651 1652

	/* timer for periodic error stats printing */
	struct timer_list s_err_report;
1653 1654 1655 1656 1657

	/* Lazy inode table initialization info */
	struct ext4_li_request *s_li_request;
	/* Wait multiplier for lazy initialization thread */
	unsigned int s_li_wait_mult;
1658 1659 1660

	/* Kernel thread for multiple mount protection */
	struct task_struct *s_mmp_tsk;
1661 1662

	/* record the last minlen when FITRIM is called. */
1663
	unsigned long s_last_trim_minblks;
1664 1665 1666

	/* Reference to checksum algorithm driver via cryptoapi */
	struct crypto_shash *s_chksum_driver;
1667 1668 1669

	/* Precomputed FS UUID checksum for seeding other checksums */
	__u32 s_csum_seed;
1670 1671

	/* Reclaim extents from extent status tree */
1672
	struct shrinker *s_es_shrinker;
1673
	struct list_head s_es_list;	/* List of inodes with reclaimable extents */
1674
	long s_es_nr_inode;
1675
	struct ext4_es_stats s_es_stats;
1676
	struct mb_cache *s_ea_block_cache;
1677
	struct mb_cache *s_ea_inode_cache;
1678
	spinlock_t s_es_lock ____cacheline_aligned_in_smp;
1679

1680 1681 1682
	/* Journal triggers for checksum computation */
	struct ext4_journal_trigger s_journal_triggers[EXT4_JOURNAL_TRIGGER_COUNT];

1683 1684 1685 1686
	/* Ratelimit ext4 messages. */
	struct ratelimit_state s_err_ratelimit_state;
	struct ratelimit_state s_warning_ratelimit_state;
	struct ratelimit_state s_msg_ratelimit_state;
1687 1688
	atomic_t s_warning_count;
	atomic_t s_msg_count;
1689

1690 1691
	/* Encryption policy for '-o test_dummy_encryption' */
	struct fscrypt_dummy_policy s_dummy_enc_policy;
1692

1693 1694
	/*
	 * Barrier between writepages ops and changing any inode's JOURNAL_DATA
1695 1696
	 * or EXTENTS flag or between writepages ops and changing DELALLOC or
	 * DIOREAD_NOLOCK mount options on remount.
1697
	 */
1698
	struct percpu_rw_semaphore s_writepages_rwsem;
1699
	struct dax_device *s_daxdev;
1700
	u64 s_dax_part_off;
1701 1702 1703
#ifdef CONFIG_EXT4_DEBUG
	unsigned long s_simulate_fail;
#endif
1704 1705 1706
	/* Record the errseq of the backing block device */
	errseq_t s_bdev_wb_err;
	spinlock_t s_bdev_wb_lock;
1707

1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723
	/* 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;
	/*
1724 1725 1726 1727 1728
	 * If we are in a context where we cannot update the on-disk
	 * superblock, we queue the work here.  This is used to update
	 * the error information in the superblock, and for periodic
	 * updates of the superblock called from the commit callback
	 * function.
1729
	 */
1730
	struct work_struct s_sb_upd_work;
1731

1732
	/* Ext4 fast commit sub transaction ID */
1733
	atomic_t s_fc_subtid;
1734

1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753
	/*
	 * 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;
1754
	tid_t s_fc_ineligible_tid;
1755 1756 1757 1758
#ifdef CONFIG_EXT4_DEBUG
	int s_fc_debug_max_replay;
#endif
	struct ext4_fc_replay_state s_fc_replay_state;
1759 1760
};

1761
static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
1762 1763 1764
{
	return sb->s_fs_info;
}
1765
static inline struct ext4_inode_info *EXT4_I(struct inode *inode)
1766
{
1767
	return container_of(inode, struct ext4_inode_info, vfs_inode);
1768 1769
}

1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793
static inline int ext4_writepages_down_read(struct super_block *sb)
{
	percpu_down_read(&EXT4_SB(sb)->s_writepages_rwsem);
	return memalloc_nofs_save();
}

static inline void ext4_writepages_up_read(struct super_block *sb, int ctx)
{
	memalloc_nofs_restore(ctx);
	percpu_up_read(&EXT4_SB(sb)->s_writepages_rwsem);
}

static inline int ext4_writepages_down_write(struct super_block *sb)
{
	percpu_down_write(&EXT4_SB(sb)->s_writepages_rwsem);
	return memalloc_nofs_save();
}

static inline void ext4_writepages_up_write(struct super_block *sb, int ctx)
{
	memalloc_nofs_restore(ctx);
	percpu_up_write(&EXT4_SB(sb)->s_writepages_rwsem);
}

1794
static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
1795
{
1796 1797 1798
	return ino == EXT4_ROOT_INO ||
		(ino >= EXT4_FIRST_INO(sb) &&
		 ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
1799
}
1800

1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817
/*
 * 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;								   \
})

1818 1819 1820 1821 1822
/*
 * run-time mount flags
 */
enum {
	EXT4_MF_MNTDIR_SAMPLED,
1823
	EXT4_MF_FC_INELIGIBLE	/* Fast commit ineligible */
1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841
};

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);
}


1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875
/*
 * 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);
}

1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901
/*
 * 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

1902 1903 1904 1905 1906 1907 1908 1909 1910
/*
 * Inode dynamic state flags
 */
enum {
	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 */
1911
	EXT4_STATE_NEWENTRY,		/* File just added to dir */
1912
	EXT4_STATE_MAY_INLINE_DATA,	/* may have in-inode data */
1913
	EXT4_STATE_EXT_PRECACHED,	/* extents have been precached */
1914
	EXT4_STATE_LUSTRE_EA_INODE,	/* Lustre-style ea_inode */
1915
	EXT4_STATE_VERITY_IN_PROGRESS,	/* building fs-verity Merkle tree */
1916
	EXT4_STATE_FC_COMMITTING,	/* Fast commit ongoing */
1917
	EXT4_STATE_ORPHAN_FILE,		/* Inode orphaned in orphan file */
1918 1919
};

1920
#define EXT4_INODE_BIT_FNS(name, field, offset)				\
1921 1922
static inline int ext4_test_inode_##name(struct inode *inode, int bit)	\
{									\
1923
	return test_bit(bit + (offset), &EXT4_I(inode)->i_##field);	\
1924 1925 1926
}									\
static inline void ext4_set_inode_##name(struct inode *inode, int bit)	\
{									\
1927
	set_bit(bit + (offset), &EXT4_I(inode)->i_##field);		\
1928 1929 1930
}									\
static inline void ext4_clear_inode_##name(struct inode *inode, int bit) \
{									\
1931
	clear_bit(bit + (offset), &EXT4_I(inode)->i_##field);		\
1932 1933
}

1934 1935 1936 1937 1938
/* 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);
1939
EXT4_INODE_BIT_FNS(flag, flags, 0)
1940 1941 1942 1943 1944 1945

/* 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);
1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960
#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
1961
#else
1962
/* Assume that user mode programs are passing in an ext4fs superblock, not
1963 1964
 * a kernel struct super_block.  This will allow us to call the feature-test
 * macros from user land. */
1965
#define EXT4_SB(sb)	(sb)
1966 1967
#endif

1968 1969 1970 1971 1972 1973
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);
}

1974
#define NEXT_ORPHAN(inode) EXT4_I(inode)->i_dtime
1975 1976 1977 1978

/*
 * Codes for operating systems
 */
1979 1980 1981 1982 1983
#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
1984 1985 1986 1987

/*
 * Revision levels
 */
1988 1989
#define EXT4_GOOD_OLD_REV	0	/* The good old (original) format */
#define EXT4_DYNAMIC_REV	1	/* V2 format w/ dynamic inode sizes */
1990

1991
#define EXT4_MAX_SUPP_REV	EXT4_DYNAMIC_REV
1992

1993
#define EXT4_GOOD_OLD_INODE_SIZE 128
1994

1995 1996 1997 1998
#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

1999 2000 2001 2002
/*
 * Feature set definitions
 */

2003 2004 2005 2006 2007 2008
#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
2009
#define EXT4_FEATURE_COMPAT_SPARSE_SUPER2	0x0200
2010 2011 2012 2013 2014 2015 2016
/*
 * 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.
 */
2017
#define EXT4_FEATURE_COMPAT_FAST_COMMIT		0x0400
2018
#define EXT4_FEATURE_COMPAT_STABLE_INODES	0x0800
2019
#define EXT4_FEATURE_COMPAT_ORPHAN_FILE		0x1000	/* Orphan file exists */
2020 2021 2022 2023

#define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER	0x0001
#define EXT4_FEATURE_RO_COMPAT_LARGE_FILE	0x0002
#define EXT4_FEATURE_RO_COMPAT_BTREE_DIR	0x0004
2024
#define EXT4_FEATURE_RO_COMPAT_HUGE_FILE        0x0008
2025
#define EXT4_FEATURE_RO_COMPAT_GDT_CSUM		0x0010
2026
#define EXT4_FEATURE_RO_COMPAT_DIR_NLINK	0x0020
Kalpak Shah's avatar
Kalpak Shah committed
2027
#define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE	0x0040
2028
#define EXT4_FEATURE_RO_COMPAT_QUOTA		0x0100
2029
#define EXT4_FEATURE_RO_COMPAT_BIGALLOC		0x0200
2030 2031 2032 2033 2034 2035
/*
 * 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.
 */
2036
#define EXT4_FEATURE_RO_COMPAT_METADATA_CSUM	0x0400
2037
#define EXT4_FEATURE_RO_COMPAT_READONLY		0x1000
2038
#define EXT4_FEATURE_RO_COMPAT_PROJECT		0x2000
2039
#define EXT4_FEATURE_RO_COMPAT_VERITY		0x8000
2040 2041
#define EXT4_FEATURE_RO_COMPAT_ORPHAN_PRESENT	0x10000 /* Orphan file may be
							   non-empty */
2042 2043 2044 2045 2046 2047

#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
2048
#define EXT4_FEATURE_INCOMPAT_EXTENTS		0x0040 /* extents support */
Laurent Vivier's avatar
Laurent Vivier committed
2049
#define EXT4_FEATURE_INCOMPAT_64BIT		0x0080
2050
#define EXT4_FEATURE_INCOMPAT_MMP               0x0100
2051
#define EXT4_FEATURE_INCOMPAT_FLEX_BG		0x0200
2052 2053
#define EXT4_FEATURE_INCOMPAT_EA_INODE		0x0400 /* EA in inode */
#define EXT4_FEATURE_INCOMPAT_DIRDATA		0x1000 /* data in dirent */
2054
#define EXT4_FEATURE_INCOMPAT_CSUM_SEED		0x2000
2055
#define EXT4_FEATURE_INCOMPAT_LARGEDIR		0x4000 /* >2GB or 3-lvl htree */
2056
#define EXT4_FEATURE_INCOMPAT_INLINE_DATA	0x8000 /* data in inode */
2057
#define EXT4_FEATURE_INCOMPAT_ENCRYPT		0x10000
2058
#define EXT4_FEATURE_INCOMPAT_CASEFOLD		0x20000
2059

2060 2061
extern void ext4_update_dynamic_rev(struct super_block *sb);

2062 2063 2064 2065 2066 2067 2068 2069
#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) \
{ \
2070
	ext4_update_dynamic_rev(sb); \
2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087
	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) \
{ \
2088
	ext4_update_dynamic_rev(sb); \
2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105
	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) \
{ \
2106
	ext4_update_dynamic_rev(sb); \
2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122
	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)
2123
EXT4_FEATURE_COMPAT_FUNCS(fast_commit,		FAST_COMMIT)
2124
EXT4_FEATURE_COMPAT_FUNCS(stable_inodes,	STABLE_INODES)
2125
EXT4_FEATURE_COMPAT_FUNCS(orphan_file,		ORPHAN_FILE)
2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138

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)
2139
EXT4_FEATURE_RO_COMPAT_FUNCS(verity,		VERITY)
2140
EXT4_FEATURE_RO_COMPAT_FUNCS(orphan_present,	ORPHAN_PRESENT)
2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156

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)
2157
EXT4_FEATURE_INCOMPAT_FUNCS(casefold,		CASEFOLD)
2158

2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173
#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)

2174 2175
#define EXT4_FEATURE_COMPAT_SUPP	(EXT4_FEATURE_COMPAT_EXT_ATTR| \
					 EXT4_FEATURE_COMPAT_ORPHAN_FILE)
2176 2177
#define EXT4_FEATURE_INCOMPAT_SUPP	(EXT4_FEATURE_INCOMPAT_FILETYPE| \
					 EXT4_FEATURE_INCOMPAT_RECOVER| \
2178
					 EXT4_FEATURE_INCOMPAT_META_BG| \
Laurent Vivier's avatar
Laurent Vivier committed
2179
					 EXT4_FEATURE_INCOMPAT_EXTENTS| \
2180
					 EXT4_FEATURE_INCOMPAT_64BIT| \
2181
					 EXT4_FEATURE_INCOMPAT_FLEX_BG| \
Andreas Dilger's avatar
Andreas Dilger committed
2182
					 EXT4_FEATURE_INCOMPAT_EA_INODE| \
2183 2184
					 EXT4_FEATURE_INCOMPAT_MMP | \
					 EXT4_FEATURE_INCOMPAT_INLINE_DATA | \
2185
					 EXT4_FEATURE_INCOMPAT_ENCRYPT | \
2186
					 EXT4_FEATURE_INCOMPAT_CASEFOLD | \
2187 2188
					 EXT4_FEATURE_INCOMPAT_CSUM_SEED | \
					 EXT4_FEATURE_INCOMPAT_LARGEDIR)
2189 2190
#define EXT4_FEATURE_RO_COMPAT_SUPP	(EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
					 EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \
2191
					 EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \
2192
					 EXT4_FEATURE_RO_COMPAT_DIR_NLINK | \
Kalpak Shah's avatar
Kalpak Shah committed
2193
					 EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \
2194
					 EXT4_FEATURE_RO_COMPAT_BTREE_DIR |\
2195
					 EXT4_FEATURE_RO_COMPAT_HUGE_FILE |\
2196
					 EXT4_FEATURE_RO_COMPAT_BIGALLOC |\
2197
					 EXT4_FEATURE_RO_COMPAT_METADATA_CSUM|\
Li Xi's avatar
Li Xi committed
2198
					 EXT4_FEATURE_RO_COMPAT_QUOTA |\
2199
					 EXT4_FEATURE_RO_COMPAT_PROJECT |\
2200 2201
					 EXT4_FEATURE_RO_COMPAT_VERITY |\
					 EXT4_FEATURE_RO_COMPAT_ORPHAN_PRESENT)
2202

2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236
#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);
}

2237 2238
extern int ext4_feature_set_ok(struct super_block *sb, int readonly);

2239 2240 2241 2242
/*
 * Superblock flags
 */
#define EXT4_FLAGS_RESIZING	0
2243
#define EXT4_FLAGS_SHUTDOWN	1
2244
#define EXT4_FLAGS_BDEV_IS_DAX	2
2245

2246
static inline int ext4_forced_shutdown(struct super_block *sb)
2247
{
2248
	return test_bit(EXT4_FLAGS_SHUTDOWN, &EXT4_SB(sb)->s_ext4_flags);
2249
}
2250

2251 2252 2253
/*
 * Default values for user and/or group using reserved blocks
 */
2254 2255
#define	EXT4_DEF_RESUID		0
#define	EXT4_DEF_RESGID		0
2256

Li Xi's avatar
Li Xi committed
2257 2258 2259 2260 2261
/*
 * Default project ID
 */
#define	EXT4_DEF_PROJID		0

2262 2263
#define EXT4_DEF_INODE_READAHEAD_BLKS	32

2264 2265 2266
/*
 * Default mount options
 */
2267 2268 2269 2270 2271 2272 2273 2274 2275
#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
2276 2277 2278 2279
#define EXT4_DEFM_NOBARRIER	0x0100
#define EXT4_DEFM_BLOCK_VALIDITY 0x0200
#define EXT4_DEFM_DISCARD	0x0400
#define EXT4_DEFM_NODELALLOC	0x0800
2280

2281 2282 2283 2284 2285 2286
/*
 * Default journal batch times
 */
#define EXT4_DEF_MIN_BATCH_TIME	0
#define EXT4_DEF_MAX_BATCH_TIME	15000 /* 15ms */

2287 2288 2289 2290 2291 2292
/*
 * 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

2293 2294 2295
/*
 * Structure of a directory entry
 */
2296
#define EXT4_NAME_LEN 255
2297 2298 2299 2300
/*
 * 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)
2301

2302
struct ext4_dir_entry {
2303 2304 2305
	__le32	inode;			/* Inode number */
	__le16	rec_len;		/* Directory entry length */
	__le16	name_len;		/* Name length */
2306
	char	name[EXT4_NAME_LEN];	/* File name */
2307 2308
};

2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319

/*
 * 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;
};

2320
/*
2321
 * The new version of the directory entry.  Since EXT4 structures are
2322 2323 2324 2325
 * 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.
 */
2326
struct ext4_dir_entry_2 {
2327 2328 2329
	__le32	inode;			/* Inode number */
	__le16	rec_len;		/* Directory entry length */
	__u8	name_len;		/* Name length */
2330
	__u8	file_type;		/* See file type macros EXT4_FT_* below */
2331
	char	name[EXT4_NAME_LEN];	/* File name */
2332 2333
};

2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349
/*
 * 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);
}

2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361
/*
 * 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) */
};

2362 2363 2364 2365 2366
#define EXT4_DIRENT_TAIL(block, blocksize) \
	((struct ext4_dir_entry_tail *)(((void *)(block)) + \
					((blocksize) - \
					 sizeof(struct ext4_dir_entry_tail))))

2367
/*
2368
 * Ext4 directory file types.  Only the low 3 bits are used.  The
2369 2370
 * other bits are reserved for now.
 */
2371 2372 2373 2374 2375 2376 2377 2378
#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
2379

2380
#define EXT4_FT_MAX		8
2381

2382 2383
#define EXT4_FT_DIR_CSUM	0xDE

2384
/*
2385
 * EXT4_DIR_PAD defines the directory entries boundaries
2386 2387 2388
 *
 * NOTE: It must be a multiple of 4
 */
2389 2390
#define EXT4_DIR_PAD			4
#define EXT4_DIR_ROUND			(EXT4_DIR_PAD - 1)
2391 2392
#define EXT4_MAX_REC_LEN		((1<<16)-1)

2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408
/*
 * 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);
}

2409 2410 2411 2412 2413 2414 2415 2416 2417
/*
 * 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);

2418
#if (PAGE_SIZE >= 65536)
2419 2420 2421 2422 2423 2424 2425 2426 2427 2428
	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)
{
2429
	BUG_ON((len > blocksize) || (blocksize > (1 << 18)) || (len & 3));
2430
#if (PAGE_SIZE >= 65536)
2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444
	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
}

2445 2446 2447 2448 2449
/*
 * Hash Tree Directory indexing
 * (c) Daniel Phillips, 2001
 */

2450
#define is_dx(dir) (ext4_has_feature_dir_index((dir)->i_sb) && \
2451
		    ext4_test_inode_flag((dir), EXT4_INODE_INDEX))
2452 2453
#define EXT4_DIR_LINK_MAX(dir) unlikely((dir)->i_nlink >= EXT4_LINK_MAX && \
		    !(ext4_has_feature_dir_nlink((dir)->i_sb) && is_dx(dir)))
2454
#define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2 || (dir)->i_nlink == 1)
2455 2456 2457

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

2458 2459 2460 2461
#define DX_HASH_LEGACY			0
#define DX_HASH_HALF_MD4		1
#define DX_HASH_TEA			2
#define DX_HASH_LEGACY_UNSIGNED		3
2462 2463
#define DX_HASH_HALF_MD4_UNSIGNED	4
#define DX_HASH_TEA_UNSIGNED		5
2464
#define DX_HASH_SIPHASH			6
2465

2466 2467 2468 2469 2470
static inline u32 ext4_chksum(struct ext4_sb_info *sbi, u32 crc,
			      const void *address, unsigned int length)
{
	struct {
		struct shash_desc shash;
2471
		char ctx[4];
2472 2473
	} desc;

2474 2475
	BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver)!=sizeof(desc.ctx));

2476 2477 2478
	desc.shash.tfm = sbi->s_chksum_driver;
	*(u32 *)desc.ctx = crc;

2479
	BUG_ON(crypto_shash_update(&desc.shash, address, length));
2480 2481 2482 2483

	return *(u32 *)desc.ctx;
}

2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494
#ifdef __KERNEL__

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

2495 2496 2497 2498 2499

/* 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)

2500 2501

/*
2502
 * Control parameters used by ext4_htree_next_block
2503 2504 2505
 */
#define HASH_NB_ALWAYS		1

2506 2507
struct ext4_filename {
	const struct qstr *usr_fname;
2508
	struct fscrypt_str disk_name;
2509
	struct dx_hash_info hinfo;
2510
#ifdef CONFIG_FS_ENCRYPTION
2511
	struct fscrypt_str crypto_buf;
2512
#endif
2513
#if IS_ENABLED(CONFIG_UNICODE)
2514
	struct qstr cf_name;
2515
#endif
2516 2517 2518
};

#define fname_name(p) ((p)->disk_name.name)
2519
#define fname_usr_name(p) ((p)->usr_fname->name)
2520
#define fname_len(p)  ((p)->disk_name.len)
2521 2522 2523 2524

/*
 * Describe an inode's exact location on disk and in memory
 */
2525
struct ext4_iloc
2526 2527 2528
{
	struct buffer_head *bh;
	unsigned long offset;
2529
	ext4_group_t block_group;
2530 2531
};

2532
static inline struct ext4_inode *ext4_raw_inode(struct ext4_iloc *iloc)
2533
{
2534
	return (struct ext4_inode *) (iloc->bh->b_data + iloc->offset);
2535 2536
}

2537 2538 2539 2540 2541
static inline bool ext4_is_quota_file(struct inode *inode)
{
	return IS_NOQUOTA(inode) &&
	       !(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL);
}
2542

2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558
/*
 * 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 */
2559
static inline ext4_fsblk_t
2560
ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no)
2561
{
2562 2563
	return group_no * (ext4_fsblk_t)EXT4_BLOCKS_PER_GROUP(sb) +
		le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
2564 2565 2566 2567 2568
}

/*
 * Special error return code only used by dx_probe() and its callers.
 */
2569
#define ERR_BAD_DX_DIR	(-(MAX_ERRNO - 1))
2570

2571 2572 2573 2574 2575 2576 2577 2578 2579 2580
/* 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;
}

2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597
/*
 * 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;
};

2598 2599 2600 2601 2602
enum ext4_li_mode {
	EXT4_LI_MODE_PREFETCH_BBITMAP,
	EXT4_LI_MODE_ITABLE,
};

2603 2604
struct ext4_li_request {
	struct super_block	*lr_super;
2605 2606
	enum ext4_li_mode	lr_mode;
	ext4_group_t		lr_first_not_zeroed;
2607 2608 2609 2610 2611 2612
	ext4_group_t		lr_next_group;
	struct list_head	lr_request;
	unsigned long		lr_next_sched;
	unsigned long		lr_timeout;
};

2613 2614 2615 2616 2617
struct ext4_features {
	struct kobject f_kobj;
	struct completion f_kobj_unregister;
};

2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649
/*
 * 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;
2650 2651
	__le32	mmp_pad2[226];
	__le32	mmp_checksum;		/* crc32c(uuid+mmp_block) */
2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679
};

/* 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

2680 2681 2682 2683 2684 2685
/*
 * Function prototypes
 */

/*
 * Ok, these declarations are also in <linux/kernel.h> but none of the
2686
 * ext4 source programs needs to include it so they are duplicated here.
2687
 */
Dave Kleikamp's avatar
Dave Kleikamp committed
2688 2689 2690
# define NORET_TYPE	/**/
# define ATTRIB_NORET	__attribute__((noreturn))
# define NORET_AND	noreturn,
2691

2692
/* bitmap.c */
2693
extern unsigned int ext4_count_free(char *bitmap, unsigned numchars);
2694
void ext4_inode_bitmap_csum_set(struct super_block *sb,
2695 2696
				struct ext4_group_desc *gdp,
				struct buffer_head *bh, int sz);
2697
int ext4_inode_bitmap_csum_verify(struct super_block *sb,
2698 2699
				  struct ext4_group_desc *gdp,
				  struct buffer_head *bh, int sz);
2700
void ext4_block_bitmap_csum_set(struct super_block *sb,
2701
				struct ext4_group_desc *gdp,
2702
				struct buffer_head *bh);
2703
int ext4_block_bitmap_csum_verify(struct super_block *sb,
2704
				  struct ext4_group_desc *gdp,
2705
				  struct buffer_head *bh);
2706

2707
/* balloc.c */
2708 2709 2710 2711 2712 2713 2714
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);

2715 2716 2717
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);
2718
extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
2719 2720 2721 2722
					 ext4_fsblk_t goal,
					 unsigned int flags,
					 unsigned long *count,
					 int *errp);
2723 2724
extern int ext4_claim_free_clusters(struct ext4_sb_info *sbi,
				    s64 nclusters, unsigned int flags);
2725
extern ext4_fsblk_t ext4_count_free_clusters(struct super_block *);
2726
extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
2727
						    ext4_group_t block_group,
2728
						    struct buffer_head ** bh);
2729 2730
extern struct ext4_group_info *ext4_get_group_info(struct super_block *sb,
						   ext4_group_t group);
2731
extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
2732 2733

extern struct buffer_head *ext4_read_block_bitmap_nowait(struct super_block *sb,
2734 2735
						ext4_group_t block_group,
						bool ignore_locked);
2736 2737 2738 2739 2740
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);
2741 2742 2743
extern unsigned ext4_free_clusters_after_init(struct super_block *sb,
					      ext4_group_t block_group,
					      struct ext4_group_desc *gdp);
2744
ext4_fsblk_t ext4_inode_to_goal_block(struct inode *);
2745

2746
#if IS_ENABLED(CONFIG_UNICODE)
2747
extern int ext4_fname_setup_ci_filename(struct inode *dir,
2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766
					const struct qstr *iname,
					struct ext4_filename *fname);

static inline void ext4_fname_free_ci_filename(struct ext4_filename *fname)
{
	kfree(fname->cf_name.name);
	fname->cf_name.name = NULL;
}
#else
static inline int ext4_fname_setup_ci_filename(struct inode *dir,
					       const struct qstr *iname,
					       struct ext4_filename *fname)
{
	return 0;
}

static inline void ext4_fname_free_ci_filename(struct ext4_filename *fname)
{
}
2767 2768
#endif

2769
/* ext4 encryption related stuff goes here crypto.c */
2770
#ifdef CONFIG_FS_ENCRYPTION
2771 2772
extern const struct fscrypt_operations ext4_cryptops;

2773 2774
int ext4_fname_setup_filename(struct inode *dir, const struct qstr *iname,
			      int lookup, struct ext4_filename *fname);
2775

2776 2777
int ext4_fname_prepare_lookup(struct inode *dir, struct dentry *dentry,
			      struct ext4_filename *fname);
2778

2779
void ext4_fname_free_filename(struct ext4_filename *fname);
2780

2781 2782
int ext4_ioctl_get_encryption_pwsalt(struct file *filp, void __user *arg);

2783
#else /* !CONFIG_FS_ENCRYPTION */
2784
static inline int ext4_fname_setup_filename(struct inode *dir,
2785 2786 2787
					    const struct qstr *iname,
					    int lookup,
					    struct ext4_filename *fname)
2788
{
2789 2790 2791
	fname->usr_fname = iname;
	fname->disk_name.name = (unsigned char *) iname->name;
	fname->disk_name.len = iname->len;
2792

2793
	return ext4_fname_setup_ci_filename(dir, iname, fname);
2794
}
2795

2796 2797 2798 2799 2800 2801 2802
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);
}

2803 2804
static inline void ext4_fname_free_filename(struct ext4_filename *fname)
{
2805
	ext4_fname_free_ci_filename(fname);
2806
}
2807 2808 2809 2810 2811 2812

static inline int ext4_ioctl_get_encryption_pwsalt(struct file *filp,
						   void __user *arg)
{
	return -EOPNOTSUPP;
}
2813
#endif /* !CONFIG_FS_ENCRYPTION */
2814

2815
/* dir.c */
2816
extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *,
2817
				  struct file *,
2818
				  struct ext4_dir_entry_2 *,
2819 2820
				  struct buffer_head *, char *, int,
				  unsigned int);
2821
#define ext4_check_dir_entry(dir, filp, de, bh, buf, size, offset) \
2822
	unlikely(__ext4_check_dir_entry(__func__, __LINE__, (dir), (filp), \
2823
				(de), (bh), (buf), (size), (offset)))
2824
extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
2825 2826
				__u32 minor_hash,
				struct ext4_dir_entry_2 *dirent,
2827
				struct fscrypt_str *ent_name);
2828
extern void ext4_htree_free_dir_info(struct dir_private_info *p);
2829 2830 2831
extern int ext4_find_dest_de(struct inode *dir, struct inode *inode,
			     struct buffer_head *bh,
			     void *buf, int buf_size,
2832
			     struct ext4_filename *fname,
2833
			     struct ext4_dir_entry_2 **dest_de);
2834
void ext4_insert_dentry(struct inode *dir, struct inode *inode,
2835 2836 2837
			struct ext4_dir_entry_2 *de,
			int buf_size,
			struct ext4_filename *fname);
2838 2839
static inline void ext4_update_dx_flag(struct inode *inode)
{
2840 2841
	if (!ext4_has_feature_dir_index(inode->i_sb) &&
	    ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) {
2842 2843
		/* ext4_iget() should have caught this... */
		WARN_ON_ONCE(ext4_has_feature_metadata_csum(inode->i_sb));
2844
		ext4_clear_inode_flag(inode, EXT4_INODE_INDEX);
2845
	}
2846
}
2847
static const unsigned char ext4_filetype_table[] = {
2848 2849 2850 2851 2852
	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)
{
2853
	if (!ext4_has_feature_filetype(sb) || filetype >= EXT4_FT_MAX)
2854 2855 2856 2857
		return DT_UNKNOWN;

	return ext4_filetype_table[filetype];
}
2858 2859
extern int ext4_check_all_de(struct inode *dir, struct buffer_head *bh,
			     void *buf, int buf_size);
2860 2861

/* fsync.c */
2862
extern int ext4_sync_file(struct file *, loff_t, loff_t, int);
2863 2864

/* hash.c */
2865 2866
extern int ext4fs_dirhash(const struct inode *dir, const char *name, int len,
			  struct dx_hash_info *hinfo);
2867 2868

/* ialloc.c */
2869
extern int ext4_mark_inode_used(struct super_block *sb, int ino);
2870
extern struct inode *__ext4_new_inode(struct mnt_idmap *, handle_t *,
2871
				      struct inode *, umode_t,
2872
				      const struct qstr *qstr, __u32 goal,
2873 2874 2875
				      uid_t *owner, __u32 i_flags,
				      int handle_type, unsigned int line_no,
				      int nblocks);
2876

2877
#define ext4_new_inode(handle, dir, mode, qstr, goal, owner, i_flags)          \
2878
	__ext4_new_inode(&nop_mnt_idmap, (handle), (dir), (mode), (qstr),      \
2879
			 (goal), (owner), i_flags, 0, 0, 0)
2880
#define ext4_new_inode_start_handle(idmap, dir, mode, qstr, goal, owner, \
2881
				    type, nblocks)		    \
2882
	__ext4_new_inode((idmap), NULL, (dir), (mode), (qstr), (goal), (owner), \
2883
			 0, (type), __LINE__, (nblocks))
2884 2885


2886 2887 2888 2889
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 *);
2890
extern void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
2891 2892
extern int ext4_init_inode_table(struct super_block *sb,
				 ext4_group_t group, int barrier);
2893
extern void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate);
2894

2895
/* fast_commit.c */
2896
int ext4_fc_info_show(struct seq_file *seq, void *v);
2897
void ext4_fc_init(struct super_block *sb, journal_t *journal);
2898
void ext4_fc_init_inode(struct inode *inode);
2899
void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t start,
2900
			 ext4_lblk_t end);
2901 2902 2903 2904 2905 2906
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);
2907 2908
void __ext4_fc_track_create(handle_t *handle, struct inode *inode,
			    struct dentry *dentry);
2909 2910
void ext4_fc_track_create(handle_t *handle, struct dentry *dentry);
void ext4_fc_track_inode(handle_t *handle, struct inode *inode);
2911
void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handle);
2912 2913 2914
void ext4_fc_start_update(struct inode *inode);
void ext4_fc_stop_update(struct inode *inode);
void ext4_fc_del(struct inode *inode);
2915 2916
bool ext4_fc_replay_check_excluded(struct super_block *sb, ext4_fsblk_t block);
void ext4_fc_replay_cleanup(struct super_block *sb);
2917 2918
int ext4_fc_commit(journal_t *journal, tid_t commit_tid);
int __init ext4_fc_init_dentry_cache(void);
2919
void ext4_fc_destroy_dentry_cache(void);
2920 2921 2922
int ext4_fc_record_regions(struct super_block *sb, int ino,
			   ext4_lblk_t lblk, ext4_fsblk_t pblk,
			   int len, int replay);
2923

2924
/* mballoc.c */
2925
extern const struct seq_operations ext4_mb_seq_groups_ops;
2926
extern const struct seq_operations ext4_mb_seq_structs_summary_ops;
2927
extern int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset);
2928
extern int ext4_mb_init(struct super_block *);
2929
extern void ext4_mb_release(struct super_block *);
2930 2931
extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *,
				struct ext4_allocation_request *, int *);
2932
extern void ext4_discard_preallocations(struct inode *);
2933 2934
extern int __init ext4_init_mballoc(void);
extern void ext4_exit_mballoc(void);
2935 2936 2937 2938 2939 2940
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);

2941
extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
2942 2943
			     struct buffer_head *bh, ext4_fsblk_t block,
			     unsigned long count, int flags);
2944 2945
extern int ext4_mb_alloc_groupinfo(struct super_block *sb,
				   ext4_group_t ngroups);
2946
extern int ext4_mb_add_groupinfo(struct super_block *sb,
2947
		ext4_group_t i, struct ext4_group_desc *desc);
2948
extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
2949
				ext4_fsblk_t block, unsigned long count);
2950
extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);
2951
extern void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid);
2952
extern void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
2953
			    int len, bool state);
2954 2955 2956 2957
static inline bool ext4_mb_cr_expensive(enum criteria cr)
{
	return cr >= CR_GOAL_LEN_SLOW;
}
2958

2959
/* inode.c */
2960 2961
void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw,
			 struct ext4_inode_info *ei);
2962
int ext4_inode_is_fast_symlink(struct inode *inode);
2963
struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int);
2964
struct buffer_head *ext4_bread(handle_t *, struct inode *, ext4_lblk_t, int);
2965 2966
int ext4_bread_batch(struct inode *inode, ext4_lblk_t block, int bh_count,
		     bool wait, struct buffer_head **bhs);
2967 2968
int ext4_get_block_unwritten(struct inode *inode, sector_t iblock,
			     struct buffer_head *bh_result, int create);
2969
int ext4_get_block(struct inode *inode, sector_t iblock,
2970
		   struct buffer_head *bh_result, int create);
2971 2972
int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
			   struct buffer_head *bh, int create);
2973
int ext4_walk_page_buffers(handle_t *handle,
2974
			   struct inode *inode,
2975 2976 2977 2978
			   struct buffer_head *head,
			   unsigned from,
			   unsigned to,
			   int *partial,
2979
			   int (*fn)(handle_t *handle, struct inode *inode,
2980
				     struct buffer_head *bh));
2981
int do_journal_get_write_access(handle_t *handle, struct inode *inode,
2982
				struct buffer_head *bh);
2983 2984
#define FALL_BACK_TO_NONDELALLOC 1
#define CONVERT_INLINE_DATA	 2
2985

2986 2987 2988
typedef enum {
	EXT4_IGET_NORMAL =	0,
	EXT4_IGET_SPECIAL =	0x0001, /* OK to iget a system inode */
2989
	EXT4_IGET_HANDLE = 	0x0002,	/* Inode # is from a handle */
2990 2991
	EXT4_IGET_BAD =		0x0004, /* Allow to iget a bad inode */
	EXT4_IGET_EA_INODE =	0x0008	/* Inode should contain an EA value */
2992 2993 2994 2995 2996 2997 2998 2999 3000
} 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__)

3001
extern int  ext4_write_inode(struct inode *, struct writeback_control *);
3002
extern int  ext4_setattr(struct mnt_idmap *, struct dentry *,
3003
			 struct iattr *);
Eric Biggers's avatar
Eric Biggers committed
3004
extern u32  ext4_dio_alignment(struct inode *inode);
3005
extern int  ext4_getattr(struct mnt_idmap *, const struct path *,
3006
			 struct kstat *, u32, unsigned int);
Al Viro's avatar
Al Viro committed
3007 3008
extern void ext4_evict_inode(struct inode *);
extern void ext4_clear_inode(struct inode *);
3009
extern int  ext4_file_getattr(struct mnt_idmap *, const struct path *,
3010
			      struct kstat *, u32, unsigned int);
3011
extern void ext4_dirty_inode(struct inode *, int);
3012 3013
extern int ext4_change_inode_journal_flag(struct inode *, int);
extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
3014 3015
extern int ext4_get_fc_inode_loc(struct super_block *sb, unsigned long ino,
			  struct ext4_iloc *iloc);
3016
extern int ext4_inode_attach_jinode(struct inode *inode);
3017
extern int ext4_can_truncate(struct inode *inode);
3018
extern int ext4_truncate(struct inode *);
3019
extern int ext4_break_layouts(struct inode *);
3020
extern int ext4_punch_hole(struct file *file, loff_t offset, loff_t length);
3021
extern void ext4_set_inode_flags(struct inode *, bool init);
3022
extern int ext4_alloc_da_blocks(struct inode *inode);
3023
extern void ext4_set_aops(struct inode *inode);
3024
extern int ext4_writepage_trans_blocks(struct inode *);
3025
extern int ext4_normal_submit_inode_data_buffers(struct jbd2_inode *jinode);
3026
extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
3027 3028
extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
			     loff_t lstart, loff_t lend);
3029
extern vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf);
3030
extern qsize_t *ext4_get_reserved_space(struct inode *inode);
Li Xi's avatar
Li Xi committed
3031
extern int ext4_get_projid(struct inode *inode, kprojid_t *projid);
3032
extern void ext4_da_release_space(struct inode *inode, int to_free);
3033 3034
extern void ext4_da_update_reserve_space(struct inode *inode,
					int used, int quota_claim);
Jan Kara's avatar
Jan Kara committed
3035 3036
extern int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk,
			      ext4_fsblk_t pblk, ext4_lblk_t len);
3037 3038 3039 3040

/* indirect.c */
extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
				struct ext4_map_blocks *map, int flags);
3041
extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks);
Theodore Ts'o's avatar
Theodore Ts'o committed
3042
extern void ext4_ind_truncate(handle_t *, struct inode *inode);
3043 3044
extern int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
				 ext4_lblk_t start, ext4_lblk_t end);
3045

3046
/* ioctl.c */
3047
extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
3048
extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
3049
int ext4_fileattr_set(struct mnt_idmap *idmap,
Miklos Szeredi's avatar
Miklos Szeredi committed
3050 3051
		      struct dentry *dentry, struct fileattr *fa);
int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa);
3052
extern void ext4_reset_inode_seed(struct inode *inode);
3053
int ext4_update_overhead(struct super_block *sb, bool force);
3054
int ext4_force_shutdown(struct super_block *sb, u32 flags);
3055

3056
/* migrate.c */
3057
extern int ext4_ext_migrate(struct inode *);
3058
extern int ext4_ind_migrate(struct inode *inode);
3059

3060
/* namei.c */
3061 3062
extern int ext4_init_new_dir(handle_t *handle, struct inode *dir,
			     struct inode *inode);
3063 3064
extern int ext4_dirblock_csum_verify(struct inode *inode,
				     struct buffer_head *bh);
3065
extern int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
3066
				__u32 start_minor_hash, __u32 *next_hash);
3067 3068 3069 3070 3071 3072 3073
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);
3074
extern int ext4_generic_delete_entry(struct inode *dir,
Tao Ma's avatar
Tao Ma committed
3075 3076 3077 3078 3079
				     struct ext4_dir_entry_2 *de_del,
				     struct buffer_head *bh,
				     void *entry_buf,
				     int buf_size,
				     int csum_size);
3080
extern bool ext4_empty_dir(struct inode *inode);
3081 3082

/* resize.c */
3083
extern void ext4_kvfree_array_rcu(void *to_free);
3084 3085 3086 3087 3088
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);
3089
extern int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count);
3090 3091 3092
extern unsigned int ext4_list_backups(struct super_block *sb,
				      unsigned int *three, unsigned int *five,
				      unsigned int *seven);
3093 3094

/* super.c */
3095
extern struct buffer_head *ext4_sb_bread(struct super_block *sb,
3096
					 sector_t block, blk_opf_t op_flags);
3097 3098
extern struct buffer_head *ext4_sb_bread_unmovable(struct super_block *sb,
						   sector_t block);
3099
extern void ext4_read_bh_nowait(struct buffer_head *bh, blk_opf_t op_flags,
3100
				bh_end_io_t *end_io);
3101
extern int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags,
3102
			bh_end_io_t *end_io);
3103
extern int ext4_read_bh_lock(struct buffer_head *bh, blk_opf_t op_flags, bool wait);
3104
extern void ext4_sb_breadahead_unmovable(struct super_block *sb, sector_t block);
3105
extern int ext4_seq_options_show(struct seq_file *seq, void *offset);
3106
extern int ext4_calculate_overhead(struct super_block *sb);
3107 3108
extern __le32 ext4_superblock_csum(struct super_block *sb,
				   struct ext4_super_block *es);
3109
extern void ext4_superblock_csum_set(struct super_block *sb);
3110 3111
extern int ext4_alloc_flex_bg_array(struct super_block *sb,
				    ext4_group_t ngroup);
3112 3113
extern const char *ext4_decode_error(struct super_block *sb, int errno,
				     char nbuf[16]);
3114 3115 3116
extern void ext4_mark_group_bitmap_corrupted(struct super_block *sb,
					     ext4_group_t block_group,
					     unsigned int flags);
3117 3118
extern unsigned int ext4_num_base_meta_blocks(struct super_block *sb,
					      ext4_group_t block_group);
3119

3120 3121 3122
extern __printf(7, 8)
void __ext4_error(struct super_block *, const char *, unsigned int, bool,
		  int, __u64, const char *, ...);
3123 3124 3125
extern __printf(6, 7)
void __ext4_error_inode(struct inode *, const char *, unsigned int,
			ext4_fsblk_t, int, const char *, ...);
3126
extern __printf(5, 6)
3127
void __ext4_error_file(struct file *, const char *, unsigned int, ext4_fsblk_t,
3128
		     const char *, ...);
3129 3130
extern void __ext4_std_error(struct super_block *, const char *,
			     unsigned int, int);
3131 3132 3133
extern __printf(4, 5)
void __ext4_warning(struct super_block *, const char *, unsigned int,
		    const char *, ...);
3134 3135 3136
extern __printf(4, 5)
void __ext4_warning_inode(const struct inode *inode, const char *function,
			  unsigned int line, const char *fmt, ...);
3137
extern __printf(3, 4)
3138
void __ext4_msg(struct super_block *, const char *, const char *, ...);
3139 3140
extern void __dump_mmp_msg(struct super_block *, struct mmp_struct *mmp,
			   const char *, unsigned int, const char *);
3141 3142 3143 3144 3145
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 *, ...);
3146

3147 3148 3149
#define EXT4_ERROR_INODE(inode, fmt, a...) \
	ext4_error_inode((inode), __func__, __LINE__, 0, (fmt), ## a)

3150 3151 3152 3153 3154 3155
#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)
3156 3157 3158 3159

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

3160 3161 3162
#define ext4_abort(sb, err, fmt, a...)					\
	__ext4_error((sb), __func__, __LINE__, true, (err), 0, (fmt), ## a)

3163 3164 3165
#ifdef CONFIG_PRINTK

#define ext4_error_inode(inode, func, line, block, fmt, ...)		\
3166 3167 3168 3169
	__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__)
3170 3171 3172
#define ext4_error_file(file, func, line, block, fmt, ...)		\
	__ext4_error_file(file, func, line, block, fmt, ##__VA_ARGS__)
#define ext4_error(sb, fmt, ...)					\
3173 3174
	__ext4_error((sb), __func__, __LINE__, false, 0, 0, (fmt),	\
		##__VA_ARGS__)
3175
#define ext4_error_err(sb, err, fmt, ...)				\
3176 3177
	__ext4_error((sb), __func__, __LINE__, false, (err), 0, (fmt),	\
		##__VA_ARGS__)
3178 3179
#define ext4_warning(sb, fmt, ...)					\
	__ext4_warning(sb, __func__, __LINE__, fmt, ##__VA_ARGS__)
3180 3181
#define ext4_warning_inode(inode, fmt, ...)				\
	__ext4_warning_inode(inode, __func__, __LINE__, fmt, ##__VA_ARGS__)
3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194
#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__);					\
3195 3196 3197 3198 3199 3200
	__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, " ");		\
3201 3202 3203 3204 3205 3206 3207 3208 3209
} 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__);					\
3210
	__ext4_error(sb, "", 0, false, 0, 0, " ");			\
3211 3212 3213 3214
} while (0)
#define ext4_error_err(sb, err, fmt, ...)				\
do {									\
	no_printk(fmt, ##__VA_ARGS__);					\
3215
	__ext4_error(sb, "", 0, false, err, 0, " ");			\
3216 3217 3218 3219 3220 3221
} while (0)
#define ext4_warning(sb, fmt, ...)					\
do {									\
	no_printk(fmt, ##__VA_ARGS__);					\
	__ext4_warning(sb, "", 0, " ");					\
} while (0)
3222 3223 3224 3225 3226
#define ext4_warning_inode(inode, fmt, ...)				\
do {									\
	no_printk(fmt, ##__VA_ARGS__);					\
	__ext4_warning_inode(inode, "", 0, " ");			\
} while (0)
3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241
#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

3242 3243 3244 3245 3246 3247
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);
3248 3249
extern __u32 ext4_free_group_clusters(struct super_block *sb,
				      struct ext4_group_desc *bg);
3250 3251 3252 3253 3254 3255
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);
3256 3257 3258 3259 3260 3261
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);
3262 3263 3264
extern void ext4_free_group_clusters_set(struct super_block *sb,
					 struct ext4_group_desc *bg,
					 __u32 count);
3265 3266 3267 3268 3269 3270
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);
3271
extern int ext4_group_desc_csum_verify(struct super_block *sb, __u32 group,
3272
				       struct ext4_group_desc *gdp);
3273 3274
extern void ext4_group_desc_csum_set(struct super_block *sb, __u32 group,
				     struct ext4_group_desc *gdp);
3275 3276
extern int ext4_register_li_request(struct super_block *sb,
				    ext4_group_t first_not_zeroed);
Laurent Vivier's avatar
Laurent Vivier committed
3277

3278 3279
static inline int ext4_has_metadata_csum(struct super_block *sb)
{
3280
	WARN_ON_ONCE(ext4_has_feature_metadata_csum(sb) &&
3281 3282
		     !EXT4_SB(sb)->s_chksum_driver);

3283 3284
	return ext4_has_feature_metadata_csum(sb) &&
	       (EXT4_SB(sb)->s_chksum_driver != NULL);
3285
}
3286 3287 3288 3289 3290 3291

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

3292 3293 3294 3295 3296
#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
3297 3298
static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es)
{
3299
	return ext4_read_incompat_64bit_val(es, s_blocks_count);
Laurent Vivier's avatar
Laurent Vivier committed
3300 3301 3302 3303
}

static inline ext4_fsblk_t ext4_r_blocks_count(struct ext4_super_block *es)
{
3304
	return ext4_read_incompat_64bit_val(es, s_r_blocks_count);
Laurent Vivier's avatar
Laurent Vivier committed
3305 3306 3307 3308
}

static inline ext4_fsblk_t ext4_free_blocks_count(struct ext4_super_block *es)
{
3309
	return ext4_read_incompat_64bit_val(es, s_free_blocks_count);
Laurent Vivier's avatar
Laurent Vivier committed
3310 3311 3312 3313 3314
}

static inline void ext4_blocks_count_set(struct ext4_super_block *es,
					 ext4_fsblk_t blk)
{
3315
	es->s_blocks_count_lo = cpu_to_le32((u32)blk);
Laurent Vivier's avatar
Laurent Vivier committed
3316 3317 3318 3319 3320 3321
	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)
{
3322
	es->s_free_blocks_count_lo = cpu_to_le32((u32)blk);
Laurent Vivier's avatar
Laurent Vivier committed
3323 3324 3325 3326 3327 3328
	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)
{
3329
	es->s_r_blocks_count_lo = cpu_to_le32((u32)blk);
Laurent Vivier's avatar
Laurent Vivier committed
3330 3331 3332
	es->s_r_blocks_count_hi = cpu_to_le32(blk >> 32);
}

3333 3334
static inline loff_t ext4_isize(struct super_block *sb,
				struct ext4_inode *raw_inode)
3335
{
3336 3337
	if (ext4_has_feature_largedir(sb) ||
	    S_ISREG(le16_to_cpu(raw_inode->i_mode)))
3338 3339
		return ((loff_t)le32_to_cpu(raw_inode->i_size_high) << 32) |
			le32_to_cpu(raw_inode->i_size_lo);
3340 3341

	return (loff_t) le32_to_cpu(raw_inode->i_size_lo);
3342
}
Laurent Vivier's avatar
Laurent Vivier committed
3343

3344 3345 3346 3347 3348
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);
}
3349

3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361
/*
 * 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;
}
3362

3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373
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;
}

3374
#define ext4_std_error(sb, errno)				\
3375 3376
do {								\
	if ((errno))						\
3377
		__ext4_std_error((sb), __func__, __LINE__, (errno));	\
3378 3379
} while (0)

3380
#ifdef CONFIG_SMP
3381 3382
/* Each CPU can accumulate percpu_counter_batch clusters in their local
 * counters. So we need to make sure we have free clusters more
3383
 * than percpu_counter_batch  * nr_cpu_ids. Also add a window of 4 times.
3384
 */
3385
#define EXT4_FREECLUSTERS_WATERMARK (4 * (percpu_counter_batch * nr_cpu_ids))
3386
#else
3387
#define EXT4_FREECLUSTERS_WATERMARK 0
3388 3389
#endif

3390
/* Update i_disksize. Requires i_rwsem to avoid races with truncate */
3391 3392
static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
{
3393
	WARN_ON_ONCE(S_ISREG(inode->i_mode) &&
Al Viro's avatar
Al Viro committed
3394
		     !inode_is_locked(inode));
3395 3396
	down_write(&EXT4_I(inode)->i_data_sem);
	if (newsize > EXT4_I(inode)->i_disksize)
3397
		WRITE_ONCE(EXT4_I(inode)->i_disksize, newsize);
3398 3399 3400
	up_write(&EXT4_I(inode)->i_data_sem);
}

3401
/* Update i_size, i_disksize. Requires i_rwsem to avoid races with truncate */
3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416
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;
}

3417 3418 3419
int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
				      loff_t len);

3420 3421
struct ext4_group_info {
	unsigned long   bb_state;
3422 3423 3424
#ifdef AGGRESSIVE_CHECK
	unsigned long	bb_check_counter;
#endif
3425
	struct rb_root  bb_free_root;
3426 3427 3428
	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 */
3429 3430
	int		bb_avg_fragment_size_order;	/* order of average
							   fragment in BG */
3431
	ext4_grpblk_t	bb_largest_free_order;/* order of largest frag in BG */
3432
	ext4_group_t	bb_group;	/* Group number */
3433 3434 3435 3436 3437
	struct          list_head bb_prealloc_list;
#ifdef DOUBLE_CHECK
	void            *bb_bitmap;
#endif
	struct rw_semaphore alloc_sem;
3438
	struct list_head bb_avg_fragment_size_node;
3439
	struct list_head bb_largest_free_order_node;
3440 3441 3442 3443
	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. */
3444 3445
};

3446 3447
#define EXT4_GROUP_INFO_NEED_INIT_BIT		0
#define EXT4_GROUP_INFO_WAS_TRIMMED_BIT		1
3448
#define EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT	2
3449
#define EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT	3
3450 3451 3452 3453
#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)
3454
#define EXT4_GROUP_INFO_BBITMAP_READ_BIT	4
3455 3456 3457

#define EXT4_MB_GRP_NEED_INIT(grp)	\
	(test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
3458 3459
#define EXT4_MB_GRP_BBITMAP_CORRUPT(grp)	\
	(test_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &((grp)->bb_state)))
3460 3461
#define EXT4_MB_GRP_IBITMAP_CORRUPT(grp)	\
	(test_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &((grp)->bb_state)))
3462

3463 3464 3465 3466 3467 3468
#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)))
3469 3470
#define EXT4_MB_GRP_TEST_AND_SET_READ(grp)	\
	(test_and_set_bit(EXT4_GROUP_INFO_BBITMAP_READ_BIT, &((grp)->bb_state)))
3471

3472 3473 3474
#define EXT4_MAX_CONTENTION		8
#define EXT4_CONTENTION_THRESHOLD	2

3475 3476
static inline spinlock_t *ext4_group_lock_ptr(struct super_block *sb,
					      ext4_group_t group)
3477
{
3478 3479
	return bgl_lock_ptr(EXT4_SB(sb)->s_blockgroup_lock, group);
}
3480

3481 3482 3483 3484 3485 3486 3487 3488 3489
/*
 * 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);
}

3490 3491
static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group)
{
3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507
	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);
	}
3508 3509 3510 3511 3512
}

static inline void ext4_unlock_group(struct super_block *sb,
					ext4_group_t group)
{
3513
	spin_unlock(ext4_group_lock_ptr(sb, group));
3514 3515
}

3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528
#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]);
}
3529
int ext4_enable_quotas(struct super_block *sb);
3530 3531
#endif

3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544
/*
 * 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)

3545 3546 3547 3548 3549
/*
 * Inodes and files operations
 */

/* dir.c */
3550
extern const struct file_operations ext4_dir_operations;
3551 3552

/* file.c */
3553
extern const struct inode_operations ext4_file_inode_operations;
3554
extern const struct file_operations ext4_file_operations;
3555
extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
3556

3557 3558 3559 3560 3561
/* 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_destroy_inline_data(handle_t *handle, struct inode *inode);

3562
int ext4_readpage_inline(struct inode *inode, struct folio *folio);
3563 3564 3565 3566
extern int ext4_try_to_write_inline_data(struct address_space *mapping,
					 struct inode *inode,
					 loff_t pos, unsigned len,
					 struct page **pagep);
3567 3568
int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len,
			       unsigned copied, struct folio *folio);
3569 3570 3571 3572 3573
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);
3574 3575
extern int ext4_try_add_inline_entry(handle_t *handle,
				     struct ext4_filename *fname,
3576
				     struct inode *dir, struct inode *inode);
3577 3578 3579 3580
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
3581
				struct dir_context *ctx,
3582
				int *has_inline_data);
3583 3584 3585 3586 3587
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);
3588
extern struct buffer_head *ext4_find_inline_entry(struct inode *dir,
3589
					struct ext4_filename *fname,
3590 3591 3592 3593 3594 3595 3596
					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);
3597
extern bool empty_inline_dir(struct inode *dir, int *has_inline_data);
3598 3599 3600
extern struct buffer_head *ext4_get_first_inline_block(struct inode *inode,
					struct ext4_dir_entry_2 **parent_de,
					int *retval);
3601
extern void *ext4_read_inline_link(struct inode *inode);
3602 3603 3604 3605

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

3606
extern int ext4_inline_data_truncate(struct inode *inode, int *has_inline);
3607 3608 3609

extern int ext4_convert_inline_data(struct inode *inode);

3610 3611 3612 3613 3614 3615
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;
}

3616
/* namei.c */
3617 3618
extern const struct inode_operations ext4_dir_inode_operations;
extern const struct inode_operations ext4_special_inode_operations;
3619
extern struct dentry *ext4_get_parent(struct dentry *child);
3620 3621 3622 3623
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);
3624 3625
extern void ext4_initialize_dirent_tail(struct buffer_head *bh,
					unsigned int blocksize);
3626 3627
extern int ext4_handle_dirty_dirblock(handle_t *handle, struct inode *inode,
				      struct buffer_head *bh);
3628 3629
extern int __ext4_unlink(struct inode *dir, const struct qstr *d_name,
			 struct inode *inode, struct dentry *dentry);
3630 3631
extern int __ext4_link(struct inode *dir, struct inode *inode,
		       struct dentry *dentry);
3632

3633
#define S_SHIFT 12
3634
static const unsigned char ext4_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = {
3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646
	[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) {
3647
	if (ext4_has_feature_filetype(sb))
3648 3649 3650
		de->file_type = ext4_type_by_mode[(mode & S_IFMT)>>S_SHIFT];
}

3651
/* readpages.c */
3652
extern int ext4_mpage_readpages(struct inode *inode,
3653
		struct readahead_control *rac, struct folio *folio);
3654 3655
extern int __init ext4_init_post_read_processing(void);
extern void ext4_exit_post_read_processing(void);
3656 3657

/* symlink.c */
3658
extern const struct inode_operations ext4_encrypted_symlink_inode_operations;
3659 3660
extern const struct inode_operations ext4_symlink_inode_operations;
extern const struct inode_operations ext4_fast_symlink_inode_operations;
3661

3662
/* sysfs.c */
3663
extern void ext4_notify_error_sysfs(struct ext4_sb_info *sbi);
3664
extern int ext4_register_sysfs(struct super_block *sb);
3665
extern void ext4_unregister_sysfs(struct super_block *sb);
3666 3667 3668
extern int __init ext4_init_sysfs(void);
extern void ext4_exit_sysfs(void);

3669 3670 3671
/* block_validity */
extern void ext4_release_system_zone(struct super_block *sb);
extern int ext4_setup_system_zone(struct super_block *sb);
3672 3673
extern int __init ext4_init_system_zone(void);
extern void ext4_exit_system_zone(void);
3674 3675 3676
extern int ext4_inode_block_valid(struct inode *inode,
				  ext4_fsblk_t start_blk,
				  unsigned int count);
3677 3678
extern int ext4_check_blockref(const char *, unsigned int,
			       struct inode *, __le32 *, unsigned int);
3679 3680 3681
extern int ext4_sb_block_valid(struct super_block *sb, struct inode *inode,
				ext4_fsblk_t start_blk, unsigned int count);

3682

3683
/* extents.c */
3684 3685 3686
struct ext4_ext_path;
struct ext4_extent;

Zheng Liu's avatar
Zheng Liu committed
3687 3688 3689 3690 3691 3692
/*
 * Maximum number of logical blocks in a file; ext4_extent's ee_block is
 * __le32.
 */
#define EXT_MAX_BLOCKS	0xffffffff

3693
extern void ext4_ext_tree_init(handle_t *handle, struct inode *inode);
3694
extern int ext4_ext_index_trans_blocks(struct inode *inode, int extents);
3695 3696
extern int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
			       struct ext4_map_blocks *map, int flags);
3697
extern int ext4_ext_truncate(handle_t *, struct inode *);
Theodore Ts'o's avatar
Theodore Ts'o committed
3698 3699
extern int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
				 ext4_lblk_t end);
3700 3701
extern void ext4_ext_init(struct super_block *);
extern void ext4_ext_release(struct super_block *);
3702
extern long ext4_fallocate(struct file *file, int mode, loff_t offset,
Amit Arora's avatar
Amit Arora committed
3703
			  loff_t len);
3704 3705
extern int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode,
					  loff_t offset, ssize_t len);
3706 3707
extern int ext4_convert_unwritten_io_end_vec(handle_t *handle,
					     ext4_io_end_t *io_end);
3708 3709
extern int ext4_map_blocks(handle_t *handle, struct inode *inode,
			   struct ext4_map_blocks *map, int flags);
3710 3711 3712 3713
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 *,
3714
				  struct ext4_ext_path **,
3715
				  struct ext4_extent *, int);
3716 3717 3718
extern struct ext4_ext_path *ext4_find_extent(struct inode *, ext4_lblk_t,
					      struct ext4_ext_path **,
					      int flags);
3719
extern void ext4_free_ext_path(struct ext4_ext_path *);
3720
extern int ext4_ext_check_inode(struct inode *inode);
3721
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
3722 3723
extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
			__u64 start, __u64 len);
3724 3725 3726
extern int ext4_get_es_cache(struct inode *inode,
			     struct fiemap_extent_info *fieinfo,
			     __u64 start, __u64 len);
3727
extern int ext4_ext_precache(struct inode *inode);
3728 3729 3730 3731
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);
3732
extern int ext4_clu_mapped(struct inode *inode, ext4_lblk_t lclu);
3733
extern int ext4_datasem_ensure_credits(handle_t *handle, struct inode *inode,
3734 3735
				       int check_cred, int restart_cred,
				       int revoke_cred);
3736 3737 3738 3739 3740
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);
3741

3742

3743
/* move_extent.c */
3744 3745 3746 3747
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);
3748 3749 3750 3751
extern int ext4_move_extents(struct file *o_filp, struct file *d_filp,
			     __u64 start_orig, __u64 start_donor,
			     __u64 len, __u64 *moved_len);

3752
/* page-io.c */
3753 3754
extern int __init ext4_init_pageio(void);
extern void ext4_exit_pageio(void);
3755
extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags);
Jan Kara's avatar
Jan Kara committed
3756 3757 3758 3759 3760
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);
3761
extern void ext4_end_io_rsv_work(struct work_struct *work);
3762
extern void ext4_io_submit(struct ext4_io_submit *io);
3763 3764
int ext4_bio_write_folio(struct ext4_io_submit *io, struct folio *page,
		size_t len);
3765 3766
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
3767

3768 3769 3770
/* mmp.c */
extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);

3771 3772 3773
/* mmp.c */
extern void ext4_stop_mmpd(struct ext4_sb_info *sbi);

3774 3775 3776
/* verity.c */
extern const struct fsverity_operations ext4_verityops;

3777 3778 3779 3780 3781
/* 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);
3782 3783 3784 3785 3786 3787 3788
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);
3789

3790
/*
3791
 * Add new method to test whether block and inode bitmaps are properly
3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806
 * 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);
}

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 */