ext4.h 81.2 KB
Newer Older
1
/*
2
 *  ext4.h
3 4 5 6 7 8 9 10 11 12 13 14 15
 *
 * Copyright (C) 1992, 1993, 1994, 1995
 * Remy Card (card@masi.ibp.fr)
 * Laboratoire MASI - Institut Blaise Pascal
 * Universite Pierre et Marie Curie (Paris VI)
 *
 *  from
 *
 *  linux/include/linux/minix_fs.h
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

16 17
#ifndef _EXT4_H
#define _EXT4_H
18 19

#include <linux/types.h>
20
#include <linux/blkdev.h>
21
#include <linux/magic.h>
22
#include <linux/jbd2.h>
23
#include <linux/quota.h>
24 25 26 27
#include <linux/rwsem.h>
#include <linux/rbtree.h>
#include <linux/seqlock.h>
#include <linux/mutex.h>
28 29 30 31
#include <linux/timer.h>
#include <linux/wait.h>
#include <linux/blockgroup_lock.h>
#include <linux/percpu_counter.h>
32 33 34
#ifdef __KERNEL__
#include <linux/compat.h>
#endif
35

36
/*
S
Shen Feng 已提交
37
 * The fourth extended filesystem constants/structures
38 39 40
 */

/*
41
 * Define EXT4FS_DEBUG to produce debug messages
42
 */
43
#undef EXT4FS_DEBUG
44 45 46 47

/*
 * Debug code
 */
48 49
#ifdef EXT4FS_DEBUG
#define ext4_debug(f, a...)						\
50
	do {								\
51
		printk(KERN_DEBUG "EXT4-fs DEBUG (%s, %d): %s:",	\
52
			__FILE__, __LINE__, __func__);			\
53
		printk(KERN_DEBUG f, ## a);				\
54 55
	} while (0)
#else
56
#define ext4_debug(f, a...)	do {} while (0)
57 58
#endif

59
#define EXT4_ERROR_INODE(inode, fmt, a...) \
60 61 62 63
	ext4_error_inode((inode), __func__, __LINE__, 0, (fmt), ## a)

#define EXT4_ERROR_INODE_BLOCK(inode, block, fmt, a...)			\
	ext4_error_inode((inode), __func__, __LINE__, (block), (fmt), ## a)
64

65 66
#define EXT4_ERROR_FILE(file, block, fmt, a...)				\
	ext4_error_file((file), __func__, __LINE__, (block), (fmt), ## a)
67

68 69 70 71 72 73 74 75 76 77 78 79
/* 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;

80
/*
81
 * Flags used in mballoc's allocation_context flags field.
82 83 84 85
 *
 * Also used to show what's going on for debugging purposes when the
 * flag field is exported via the traceport interface
 */
86

87
/* prefer goal again. length */
88
#define EXT4_MB_HINT_MERGE		0x0001
89
/* blocks already reserved */
90
#define EXT4_MB_HINT_RESERVED		0x0002
91
/* metadata is being allocated */
92
#define EXT4_MB_HINT_METADATA		0x0004
93
/* first blocks in the file */
94
#define EXT4_MB_HINT_FIRST		0x0008
95
/* search for the best chunk */
96
#define EXT4_MB_HINT_BEST		0x0010
97
/* data is being allocated */
98
#define EXT4_MB_HINT_DATA		0x0020
99
/* don't preallocate (for tails) */
100
#define EXT4_MB_HINT_NOPREALLOC		0x0040
101
/* allocate for locality group */
102
#define EXT4_MB_HINT_GROUP_ALLOC	0x0080
103
/* allocate goal blocks or none */
104
#define EXT4_MB_HINT_GOAL_ONLY		0x0100
105
/* goal is meaningful */
106
#define EXT4_MB_HINT_TRY_GOAL		0x0200
107
/* blocks already pre-reserved by delayed allocation */
108
#define EXT4_MB_DELALLOC_RESERVED	0x0400
109 110
/* We are doing stream allocation */
#define EXT4_MB_STREAM_ALLOC		0x0800
111 112
/* Use reserved root blocks if needed */
#define EXT4_MB_USE_ROOT_BLOCKS		0x1000
113 114 115 116

struct ext4_allocation_request {
	/* target inode for block we're allocating */
	struct inode *inode;
117 118
	/* how many blocks we want to allocate */
	unsigned int len;
119 120 121 122 123 124
	/* 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;
125 126 127 128 129
	/* 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 */
130 131
	ext4_fsblk_t pright;
	/* flags. see above EXT4_MB_HINT_* */
132
	unsigned int flags;
133 134
};

135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157
/*
 * Logical to physical block mapping, used by ext4_map_blocks()
 *
 * This structure is used to pass requests into ext4_map_blocks() as
 * well as to store the information returned by ext4_map_blocks().  It
 * takes less room on the stack than a struct buffer_head.
 */
#define EXT4_MAP_NEW		(1 << BH_New)
#define EXT4_MAP_MAPPED		(1 << BH_Mapped)
#define EXT4_MAP_UNWRITTEN	(1 << BH_Unwritten)
#define EXT4_MAP_BOUNDARY	(1 << BH_Boundary)
#define EXT4_MAP_UNINIT		(1 << BH_Uninit)
#define EXT4_MAP_FLAGS		(EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
				 EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY |\
				 EXT4_MAP_UNINIT)

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

158 159 160 161 162 163 164 165 166 167 168 169 170 171
/*
 * For delayed allocation tracking
 */
struct mpage_da_data {
	struct inode *inode;
	sector_t b_blocknr;		/* start block number of extent */
	size_t b_size;			/* size of extent */
	unsigned long b_state;		/* state of the extent */
	unsigned long first_page, next_page;	/* extent of pages */
	struct writeback_control *wbc;
	int io_done;
	int pages_written;
	int retval;
};
172 173 174 175 176 177

/*
 * Flags for ext4_io_end->flags
 */
#define	EXT4_IO_END_UNWRITTEN	0x0001
#define EXT4_IO_END_ERROR	0x0002
178
#define EXT4_IO_END_QUEUED	0x0004
179 180 181

struct ext4_io_page {
	struct page	*p_page;
182
	atomic_t	p_count;
183 184 185 186
};

#define MAX_IO_PAGES 128

187
typedef struct ext4_io_end {
188
	struct list_head	list;		/* per-file finished IO list */
189
	struct inode		*inode;		/* file being written to */
190
	unsigned int		flag;		/* unwritten or not */
191
	struct page		*page;		/* page struct for buffer write */
192 193
	loff_t			offset;		/* offset in the file */
	ssize_t			size;		/* size of the extent */
194
	struct work_struct	work;		/* data work queue */
195 196
	struct kiocb		*iocb;		/* iocb struct for AIO */
	int			result;		/* error value for AIO */
197 198
	int			num_io_pages;
	struct ext4_io_page	*pages[MAX_IO_PAGES];
199 200
} ext4_io_end_t;

201 202 203 204 205 206 207 208
struct ext4_io_submit {
	int			io_op;
	struct bio		*io_bio;
	ext4_io_end_t		*io_end;
	struct ext4_io_page	*io_page;
	sector_t		io_next_block;
};

209 210 211
/*
 * Special inodes numbers
 */
212 213
#define	EXT4_BAD_INO		 1	/* Bad blocks inode */
#define EXT4_ROOT_INO		 2	/* Root inode */
214 215
#define EXT4_USR_QUOTA_INO	 3	/* User quota inode */
#define EXT4_GRP_QUOTA_INO	 4	/* Group quota inode */
216 217 218 219
#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 */
220

221 222
/* First non-reserved inode for old ext4 filesystems */
#define EXT4_GOOD_OLD_FIRST_INO	11
223 224 225 226

/*
 * Maximal count of links to a file
 */
227
#define EXT4_LINK_MAX		65000
228 229 230 231

/*
 * Macro-instructions used to manage several block sizes
 */
232
#define EXT4_MIN_BLOCK_SIZE		1024
233 234
#define	EXT4_MAX_BLOCK_SIZE		65536
#define EXT4_MIN_BLOCK_LOG_SIZE		10
235
#define EXT4_MAX_BLOCK_LOG_SIZE		16
236
#ifdef __KERNEL__
237
# define EXT4_BLOCK_SIZE(s)		((s)->s_blocksize)
238
#else
239
# define EXT4_BLOCK_SIZE(s)		(EXT4_MIN_BLOCK_SIZE << (s)->s_log_block_size)
240
#endif
241
#define	EXT4_ADDR_PER_BLOCK(s)		(EXT4_BLOCK_SIZE(s) / sizeof(__u32))
242 243
#define EXT4_CLUSTER_SIZE(s)		(EXT4_BLOCK_SIZE(s) << \
					 EXT4_SB(s)->s_cluster_bits)
244
#ifdef __KERNEL__
245
# define EXT4_BLOCK_SIZE_BITS(s)	((s)->s_blocksize_bits)
246
# define EXT4_CLUSTER_BITS(s)		(EXT4_SB(s)->s_cluster_bits)
247
#else
248
# define EXT4_BLOCK_SIZE_BITS(s)	((s)->s_log_block_size + 10)
249 250
#endif
#ifdef __KERNEL__
251 252 253
#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)
254
#else
255 256
#define EXT4_INODE_SIZE(s)	(((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \
				 EXT4_GOOD_OLD_INODE_SIZE : \
257
				 (s)->s_inode_size)
258 259
#define EXT4_FIRST_INO(s)	(((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \
				 EXT4_GOOD_OLD_FIRST_INO : \
260 261
				 (s)->s_first_ino)
#endif
A
Amit Arora 已提交
262
#define EXT4_BLOCK_ALIGN(size, blkbits)		ALIGN((size), (1 << (blkbits)))
263

264 265 266 267 268 269 270 271
/* 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)

272 273 274
/*
 * Structure of a blocks group descriptor
 */
275
struct ext4_group_desc
276
{
277
	__le32	bg_block_bitmap_lo;	/* Blocks bitmap block */
278 279
	__le32	bg_inode_bitmap_lo;	/* Inodes bitmap block */
	__le32	bg_inode_table_lo;	/* Inodes table block */
280 281 282
	__le16	bg_free_blocks_count_lo;/* Free blocks count */
	__le16	bg_free_inodes_count_lo;/* Free inodes count */
	__le16	bg_used_dirs_count_lo;	/* Directories count */
A
Andreas Dilger 已提交
283 284
	__le16	bg_flags;		/* EXT4_BG_flags (INODE_UNINIT, etc) */
	__u32	bg_reserved[2];		/* Likely block/inode bitmap checksum */
285
	__le16  bg_itable_unused_lo;	/* Unused inodes count */
A
Andreas Dilger 已提交
286
	__le16  bg_checksum;		/* crc16(sb_uuid+group+desc) */
287 288 289
	__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 */
290 291 292
	__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 */
293
	__le16  bg_itable_unused_hi;    /* Unused inodes count MSB */
294
	__u32	bg_reserved2[3];
295 296
};

297 298 299 300 301
/*
 * Structure of a flex block group info
 */

struct flex_groups {
302 303
	atomic_t free_inodes;
	atomic_t free_blocks;
304
	atomic_t used_dirs;
305 306
};

A
Andreas Dilger 已提交
307 308 309 310
#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 */

311 312 313
/*
 * Macro-instructions used to manage group descriptors
 */
314
#define EXT4_MIN_DESC_SIZE		32
315
#define EXT4_MIN_DESC_SIZE_64BIT	64
316 317
#define	EXT4_MAX_DESC_SIZE		EXT4_MIN_BLOCK_SIZE
#define EXT4_DESC_SIZE(s)		(EXT4_SB(s)->s_desc_size)
318
#ifdef __KERNEL__
319
# define EXT4_BLOCKS_PER_GROUP(s)	(EXT4_SB(s)->s_blocks_per_group)
320
# define EXT4_CLUSTERS_PER_GROUP(s)	(EXT4_SB(s)->s_clusters_per_group)
321 322 323
# 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)
324
#else
325
# define EXT4_BLOCKS_PER_GROUP(s)	((s)->s_blocks_per_group)
326
# define EXT4_DESC_PER_BLOCK(s)		(EXT4_BLOCK_SIZE(s) / EXT4_DESC_SIZE(s))
327
# define EXT4_INODES_PER_GROUP(s)	((s)->s_inodes_per_group)
328 329 330 331 332
#endif

/*
 * Constants relative to the data blocks
 */
333 334 335 336 337
#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)
338 339 340 341

/*
 * Inode flags
 */
342 343 344 345 346 347 348 349
#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 */
350
/* Reserved for compression usage... */
351 352 353 354
#define EXT4_DIRTY_FL			0x00000100
#define EXT4_COMPRBLK_FL		0x00000200 /* One or more compressed clusters */
#define EXT4_NOCOMPR_FL			0x00000400 /* Don't compress */
#define EXT4_ECOMPR_FL			0x00000800 /* Compression error */
355
/* End compression flags --- maybe not all used */
356 357 358 359 360 361
#define EXT4_INDEX_FL			0x00001000 /* hash-indexed directory */
#define EXT4_IMAGIC_FL			0x00002000 /* AFS directory */
#define EXT4_JOURNAL_DATA_FL		0x00004000 /* file data should be journaled */
#define EXT4_NOTAIL_FL			0x00008000 /* file tail should not be merged */
#define EXT4_DIRSYNC_FL			0x00010000 /* dirsync behaviour (directories only) */
#define EXT4_TOPDIR_FL			0x00020000 /* Top of directory hierarchies*/
A
Aneesh Kumar K.V 已提交
362
#define EXT4_HUGE_FILE_FL               0x00040000 /* Set to each huge file */
A
Alex Tomas 已提交
363
#define EXT4_EXTENTS_FL			0x00080000 /* Inode uses extents */
364
#define EXT4_EA_INODE_FL	        0x00200000 /* Inode used for large EA */
365
#define EXT4_EOFBLOCKS_FL		0x00400000 /* Blocks allocated beyond EOF */
A
Aneesh Kumar K.V 已提交
366
#define EXT4_RESERVED_FL		0x80000000 /* reserved for ext4 lib */
367

368 369
#define EXT4_FL_USER_VISIBLE		0x004BDFFF /* User visible flags */
#define EXT4_FL_USER_MODIFIABLE		0x004B80FF /* User modifiable flags */
370

371 372
/* Flags that should be inherited by new inodes from their parent. */
#define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\
373
			   EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
374 375 376
			   EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\
			   EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL)

377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393
/* Flags that are appropriate for regular files (all but dir-specific ones). */
#define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL))

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

/* Mask out flags that are inappropriate for the given type of inode. */
static inline __u32 ext4_mask_flags(umode_t mode, __u32 flags)
{
	if (S_ISDIR(mode))
		return flags;
	else if (S_ISREG(mode))
		return flags & EXT4_REG_FLMASK;
	else
		return flags & EXT4_OTHER_FLMASK;
}

394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470
/*
 * 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 */
	EXT4_INODE_ECOMPR	= 11,	/* Compression error */
/* End compression flags --- maybe not all used */
	EXT4_INODE_INDEX	= 12,	/* hash-indexed directory */
	EXT4_INODE_IMAGIC	= 13,	/* AFS directory */
	EXT4_INODE_JOURNAL_DATA	= 14,	/* file data should be journaled */
	EXT4_INODE_NOTAIL	= 15,	/* file tail should not be merged */
	EXT4_INODE_DIRSYNC	= 16,	/* dirsync behaviour (directories only) */
	EXT4_INODE_TOPDIR	= 17,	/* Top of directory hierarchies*/
	EXT4_INODE_HUGE_FILE	= 18,	/* Set to each huge file */
	EXT4_INODE_EXTENTS	= 19,	/* Inode uses extents */
	EXT4_INODE_EA_INODE	= 21,	/* Inode used for large EA */
	EXT4_INODE_EOFBLOCKS	= 22,	/* Blocks allocated beyond EOF */
	EXT4_INODE_RESERVED	= 31,	/* reserved for ext4 lib */
};

#define TEST_FLAG_VALUE(FLAG) (EXT4_##FLAG##_FL == (1 << EXT4_INODE_##FLAG))
#define CHECK_FLAG_VALUE(FLAG) if (!TEST_FLAG_VALUE(FLAG)) { \
	printk(KERN_EMERG "EXT4 flag fail: " #FLAG ": %d %d\n", \
		EXT4_##FLAG##_FL, EXT4_INODE_##FLAG); BUG_ON(1); }

/*
 * Since it's pretty easy to mix up bit numbers and hex values, and we
 * can't do a compile-time test for ENUM values, we use a run-time
 * test to make sure that EXT4_XXX_FL is consistent with respect to
 * EXT4_INODE_XXX.  If all is well the printk and BUG_ON will all drop
 * out so it won't cost any extra space in the compiled kernel image.
 * But it's important that these values are the same, since we are
 * using EXT4_INODE_XXX to test for the flag values, but EXT4_XX_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.
 *
 * It's not paranoia if the Murphy's Law really *is* out to get you.  :-)
 */
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);
	CHECK_FLAG_VALUE(ECOMPR);
	CHECK_FLAG_VALUE(INDEX);
	CHECK_FLAG_VALUE(IMAGIC);
	CHECK_FLAG_VALUE(JOURNAL_DATA);
	CHECK_FLAG_VALUE(NOTAIL);
	CHECK_FLAG_VALUE(DIRSYNC);
	CHECK_FLAG_VALUE(TOPDIR);
	CHECK_FLAG_VALUE(HUGE_FILE);
	CHECK_FLAG_VALUE(EXTENTS);
	CHECK_FLAG_VALUE(EA_INODE);
	CHECK_FLAG_VALUE(EOFBLOCKS);
	CHECK_FLAG_VALUE(RESERVED);
}

471
/* Used to pass group descriptor data when online resize is done */
472
struct ext4_new_group_input {
D
Dave Kleikamp 已提交
473 474 475 476 477 478
	__u32 group;		/* Group number for this data */
	__u64 block_bitmap;	/* Absolute block number of block bitmap */
	__u64 inode_bitmap;	/* Absolute block number of inode bitmap */
	__u64 inode_table;	/* Absolute block number of inode table start */
	__u32 blocks_count;	/* Total number of blocks in this group */
	__u16 reserved_blocks;	/* Number of reserved blocks in this group */
479 480 481
	__u16 unused;
};

482 483 484 485 486 487 488 489 490 491 492 493
#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

494 495
/* The struct ext4_new_group_input in kernel space, with free_blocks_count */
struct ext4_new_group_data {
496
	__u32 group;
L
Laurent Vivier 已提交
497 498 499
	__u64 block_bitmap;
	__u64 inode_bitmap;
	__u64 inode_table;
500 501 502 503 504 505
	__u32 blocks_count;
	__u16 reserved_blocks;
	__u16 unused;
	__u32 free_blocks_count;
};

A
Amit Arora 已提交
506
/*
507
 * Flags used by ext4_map_blocks()
A
Amit Arora 已提交
508
 */
509 510
	/* Allocate any needed blocks and/or convert an unitialized
	   extent to be an initialized ext4 */
511
#define EXT4_GET_BLOCKS_CREATE			0x0001
512
	/* Request the creation of an unitialized extent */
513
#define EXT4_GET_BLOCKS_UNINIT_EXT		0x0002
514 515 516
#define EXT4_GET_BLOCKS_CREATE_UNINIT_EXT	(EXT4_GET_BLOCKS_UNINIT_EXT|\
						 EXT4_GET_BLOCKS_CREATE)
	/* Caller is from the delayed allocation writeout path,
517
	   so set the magic i_delalloc_reserve_flag after taking the
518
	   inode allocation semaphore for */
519
#define EXT4_GET_BLOCKS_DELALLOC_RESERVE	0x0004
520 521 522
	/* caller is from the direct IO path, request to creation of an
	unitialized extents if not allocated, split the uninitialized
	extent if blocks has been preallocated already*/
523
#define EXT4_GET_BLOCKS_PRE_IO			0x0008
524
#define EXT4_GET_BLOCKS_CONVERT			0x0010
525
#define EXT4_GET_BLOCKS_IO_CREATE_EXT		(EXT4_GET_BLOCKS_PRE_IO|\
526
					 EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
527 528
	/* Convert extent to initialized after IO complete */
#define EXT4_GET_BLOCKS_IO_CONVERT_EXT		(EXT4_GET_BLOCKS_CONVERT|\
529
					 EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
530 531
	/* Punch out blocks of an extent */
#define EXT4_GET_BLOCKS_PUNCH_OUT_EXT		0x0020
532 533
	/* Don't normalize allocation size (used for fallocate) */
#define EXT4_GET_BLOCKS_NO_NORMALIZE		0x0040
534

535 536 537 538 539
/*
 * Flags used by ext4_free_blocks
 */
#define EXT4_FREE_BLOCKS_METADATA	0x0001
#define EXT4_FREE_BLOCKS_FORGET		0x0002
540
#define EXT4_FREE_BLOCKS_VALIDATED	0x0004
541
#define EXT4_FREE_BLOCKS_NO_QUOT_UPDATE	0x0008
542 543
#define EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER	0x0010
#define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER	0x0020
544

545 546 547 548 549
/*
 * Flags used by ext4_discard_partial_page_buffers
 */
#define EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED	0x0001

550 551 552
/*
 * ioctl commands
 */
553 554 555 556 557 558
#define	EXT4_IOC_GETFLAGS		FS_IOC_GETFLAGS
#define	EXT4_IOC_SETFLAGS		FS_IOC_SETFLAGS
#define	EXT4_IOC_GETVERSION		_IOR('f', 3, long)
#define	EXT4_IOC_SETVERSION		_IOW('f', 4, long)
#define	EXT4_IOC_GETVERSION_OLD		FS_IOC_GETVERSION
#define	EXT4_IOC_SETVERSION_OLD		FS_IOC_SETVERSION
559
#ifdef CONFIG_JBD2_DEBUG
560
#define EXT4_IOC_WAIT_FOR_READONLY	_IOR('f', 99, long)
561
#endif
562 563
#define EXT4_IOC_GETRSVSZ		_IOR('f', 5, long)
#define EXT4_IOC_SETRSVSZ		_IOW('f', 6, long)
T
Theodore Ts'o 已提交
564 565 566
#define EXT4_IOC_GROUP_EXTEND		_IOW('f', 7, unsigned long)
#define EXT4_IOC_GROUP_ADD		_IOW('f', 8, struct ext4_new_group_input)
#define EXT4_IOC_MIGRATE		_IO('f', 9)
567
 /* note ioctl 10 reserved for an early version of the FIEMAP ioctl */
T
Theodore Ts'o 已提交
568
 /* note ioctl 11 reserved for filesystem-independent FIEMAP ioctl */
569
#define EXT4_IOC_ALLOC_DA_BLKS		_IO('f', 12)
570
#define EXT4_IOC_MOVE_EXT		_IOWR('f', 15, struct move_extent)
571

572
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
573 574 575
/*
 * ioctl commands in 32 bit emulation
 */
576 577 578 579 580 581 582
#define EXT4_IOC32_GETFLAGS		FS_IOC32_GETFLAGS
#define EXT4_IOC32_SETFLAGS		FS_IOC32_SETFLAGS
#define EXT4_IOC32_GETVERSION		_IOR('f', 3, int)
#define EXT4_IOC32_SETVERSION		_IOW('f', 4, int)
#define EXT4_IOC32_GETRSVSZ		_IOR('f', 5, int)
#define EXT4_IOC32_SETRSVSZ		_IOW('f', 6, int)
#define EXT4_IOC32_GROUP_EXTEND		_IOW('f', 7, unsigned int)
583
#define EXT4_IOC32_GROUP_ADD		_IOW('f', 8, struct compat_ext4_new_group_input)
584
#ifdef CONFIG_JBD2_DEBUG
585
#define EXT4_IOC32_WAIT_FOR_READONLY	_IOR('f', 99, int)
586
#endif
587 588
#define EXT4_IOC32_GETVERSION_OLD	FS_IOC32_GETVERSION
#define EXT4_IOC32_SETVERSION_OLD	FS_IOC32_SETVERSION
589
#endif
590

591
/* Max physical block we can address w/o extents */
592 593
#define EXT4_MAX_BLOCK_FILE_PHYS	0xFFFFFFFF

594 595 596
/*
 * Structure of an inode on the disk
 */
597
struct ext4_inode {
598 599
	__le16	i_mode;		/* File mode */
	__le16	i_uid;		/* Low 16 bits of Owner Uid */
600
	__le32	i_size_lo;	/* Size in bytes */
601
	__le32	i_atime;	/* Access time */
K
Kalpak Shah 已提交
602
	__le32	i_ctime;	/* Inode Change time */
603 604 605 606
	__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 */
607
	__le32	i_blocks_lo;	/* Blocks count */
608 609 610
	__le32	i_flags;	/* File flags */
	union {
		struct {
611
			__le32  l_i_version;
612 613 614 615 616 617 618 619
		} linux1;
		struct {
			__u32  h_i_translator;
		} hurd1;
		struct {
			__u32  m_i_reserved1;
		} masix1;
	} osd1;				/* OS dependent 1 */
620
	__le32	i_block[EXT4_N_BLOCKS];/* Pointers to blocks */
621
	__le32	i_generation;	/* File version (for NFS) */
622
	__le32	i_file_acl_lo;	/* File ACL */
623
	__le32	i_size_high;
624
	__le32	i_obso_faddr;	/* Obsoleted fragment address */
625 626
	union {
		struct {
627
			__le16	l_i_blocks_high; /* were l_i_reserved1 */
B
Badari Pulavarty 已提交
628
			__le16	l_i_file_acl_high;
D
Dave Kleikamp 已提交
629
			__le16	l_i_uid_high;	/* these 2 fields */
630 631 632 633
			__le16	l_i_gid_high;	/* were reserved2[0] */
			__u32	l_i_reserved2;
		} linux2;
		struct {
634
			__le16	h_i_reserved1;	/* Obsoleted fragment number/size which are removed in ext4 */
635 636 637 638 639 640
			__u16	h_i_mode_high;
			__u16	h_i_uid_high;
			__u16	h_i_gid_high;
			__u32	h_i_author;
		} hurd2;
		struct {
641
			__le16	h_i_reserved1;	/* Obsoleted fragment number/size which are removed in ext4 */
B
Badari Pulavarty 已提交
642
			__le16	m_i_file_acl_high;
643 644 645 646 647
			__u32	m_i_reserved2[2];
		} masix2;
	} osd2;				/* OS dependent 2 */
	__le16	i_extra_isize;
	__le16	i_pad1;
K
Kalpak Shah 已提交
648 649 650 651 652
	__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) */
653
	__le32  i_version_hi;	/* high 32 bits for 64-bit version */
654 655
};

656 657 658 659 660 661 662 663
struct move_extent {
	__u32 reserved;		/* should be zero */
	__u32 donor_fd;		/* donor file descriptor */
	__u64 orig_start;	/* logical start offset in block for orig */
	__u64 donor_start;	/* logical start offset in block for donor */
	__u64 len;		/* block length to be moved */
	__u64 moved_len;	/* moved block length */
};
664

K
Kalpak Shah 已提交
665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687
#define EXT4_EPOCH_BITS 2
#define EXT4_EPOCH_MASK ((1 << EXT4_EPOCH_BITS) - 1)
#define EXT4_NSEC_MASK  (~0UL << EXT4_EPOCH_BITS)

/*
 * Extended fields will fit into an inode if the filesystem was formatted
 * with large inodes (-I 256 or larger) and there are not currently any EAs
 * consuming all of the available space. For new inodes we always reserve
 * enough space for the kernel's known extended fields, but for inodes
 * created with an old kernel this might not have been the case. None of
 * the extended inode fields is critical for correct filesystem operation.
 * This macro checks if a certain field fits in the inode. Note that
 * inode-size = GOOD_OLD_INODE_SIZE + i_extra_isize
 */
#define EXT4_FITS_IN_INODE(ext4_inode, einode, field)	\
	((offsetof(typeof(*ext4_inode), field) +	\
	  sizeof((ext4_inode)->field))			\
	<= (EXT4_GOOD_OLD_INODE_SIZE +			\
	    (einode)->i_extra_isize))			\

static inline __le32 ext4_encode_extra_time(struct timespec *time)
{
       return cpu_to_le32((sizeof(time->tv_sec) > 4 ?
688 689
			   (time->tv_sec >> 32) & EXT4_EPOCH_MASK : 0) |
                          ((time->tv_nsec << EXT4_EPOCH_BITS) & EXT4_NSEC_MASK));
K
Kalpak Shah 已提交
690 691 692 693 694 695 696
}

static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra)
{
       if (sizeof(time->tv_sec) > 4)
	       time->tv_sec |= (__u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK)
			       << 32;
697
       time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS;
K
Kalpak Shah 已提交
698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722
}

#define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode)			       \
do {									       \
	(raw_inode)->xtime = cpu_to_le32((inode)->xtime.tv_sec);	       \
	if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra))     \
		(raw_inode)->xtime ## _extra =				       \
				ext4_encode_extra_time(&(inode)->xtime);       \
} while (0)

#define EXT4_EINODE_SET_XTIME(xtime, einode, raw_inode)			       \
do {									       \
	if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime))		       \
		(raw_inode)->xtime = cpu_to_le32((einode)->xtime.tv_sec);      \
	if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra))	       \
		(raw_inode)->xtime ## _extra =				       \
				ext4_encode_extra_time(&(einode)->xtime);      \
} while (0)

#define EXT4_INODE_GET_XTIME(xtime, inode, raw_inode)			       \
do {									       \
	(inode)->xtime.tv_sec = (signed)le32_to_cpu((raw_inode)->xtime);       \
	if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra))     \
		ext4_decode_extra_time(&(inode)->xtime,			       \
				       raw_inode->xtime ## _extra);	       \
723 724
	else								       \
		(inode)->xtime.tv_nsec = 0;				       \
K
Kalpak Shah 已提交
725 726 727 728 729 730 731 732 733 734
} while (0)

#define EXT4_EINODE_GET_XTIME(xtime, einode, raw_inode)			       \
do {									       \
	if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime))		       \
		(einode)->xtime.tv_sec = 				       \
			(signed)le32_to_cpu((raw_inode)->xtime);	       \
	if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra))	       \
		ext4_decode_extra_time(&(einode)->xtime,		       \
				       raw_inode->xtime ## _extra);	       \
735 736
	else								       \
		(einode)->xtime.tv_nsec = 0;				       \
K
Kalpak Shah 已提交
737 738
} while (0)

739 740
#define i_disk_version osd1.linux1.l_i_version

741 742
#if defined(__KERNEL__) || defined(__linux__)
#define i_reserved1	osd1.linux1.l_i_reserved1
B
Badari Pulavarty 已提交
743
#define i_file_acl_high	osd2.linux2.l_i_file_acl_high
744
#define i_blocks_high	osd2.linux2.l_i_blocks_high
745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760
#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
#define i_reserved2	osd2.linux2.l_i_reserved2

#elif defined(__GNU__)

#define i_translator	osd1.hurd1.h_i_translator
#define i_uid_high	osd2.hurd2.h_i_uid_high
#define i_gid_high	osd2.hurd2.h_i_gid_high
#define i_author	osd2.hurd2.h_i_author

#elif defined(__masix__)

#define i_reserved1	osd1.masix1.m_i_reserved1
B
Badari Pulavarty 已提交
761
#define i_file_acl_high	osd2.masix2.m_i_file_acl_high
762 763 764 765
#define i_reserved2	osd2.masix2.m_i_reserved2

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

766 767
/*
 * storage for cached extent
768 769
 * If ec_len == 0, then the cache is invalid.
 * If ec_start == 0, then the cache represents a gap (null mapping)
770 771 772 773 774 775 776 777 778 779 780 781 782
 */
struct ext4_ext_cache {
	ext4_fsblk_t	ec_start;
	ext4_lblk_t	ec_block;
	__u32		ec_len; /* must be 32bit to return holes */
};

/*
 * fourth extended file system inode data in memory
 */
struct ext4_inode_info {
	__le32	i_data[15];	/* unconverted */
	__u32	i_dtime;
783
	ext4_fsblk_t	i_file_acl;
784 785 786 787 788 789 790 791 792

	/*
	 * i_block_group is the number of the block group which contains
	 * this file's inode.  Constant across the lifetime of the inode,
	 * it is ued for making block allocation decisions - we try to
	 * place a file's data blocks near its inode block, and new inodes
	 * near to their parent directory's inode.
	 */
	ext4_group_t	i_block_group;
793
	ext4_lblk_t	i_dir_start_lookup;
794
#if (BITS_PER_LONG < 64)
795
	unsigned long	i_state_flags;		/* Dynamic state flags */
796
#endif
797
	unsigned long	i_flags;
798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840

#ifdef CONFIG_EXT4_FS_XATTR
	/*
	 * Extended attributes can be read independently of the main file
	 * data. Taking i_mutex even when reading would cause contention
	 * between readers of EAs and writers of regular file data, so
	 * instead we synchronize on xattr_sem when reading or changing
	 * EAs.
	 */
	struct rw_semaphore xattr_sem;
#endif

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

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

	/*
	 * i_data_sem is for serialising ext4_truncate() against
	 * ext4_getblock().  In the 2.4 ext2 design, great chunks of inode's
	 * data tree are chopped off during truncate. We can't do that in
	 * ext4 because whenever we perform intermediate commits during
	 * truncate, the inode and all the metadata blocks *must* be in a
	 * consistent state which allows truncation of the orphans to restart
	 * during recovery.  Hence we must fix the get_block-vs-truncate race
	 * by other means, so we have i_data_sem.
	 */
	struct rw_semaphore i_data_sem;
	struct inode vfs_inode;
841
	struct jbd2_inode *jinode;
842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860

	struct ext4_ext_cache i_cached_extent;
	/*
	 * File creation time. Its function is same as that of
	 * struct timespec i_{a,c,m}time in the generic inode.
	 */
	struct timespec i_crtime;

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

	/* ialloc */
	ext4_group_t	i_last_alloc_group;

	/* allocation reservation info for delalloc */
	unsigned int i_reserved_data_blocks;
	unsigned int i_reserved_meta_blocks;
	unsigned int i_allocated_meta_blocks;
861
	ext4_lblk_t i_da_metadata_calc_last_lblock;
862
	int i_da_metadata_calc_len;
863 864 865 866

	/* on-disk additional length */
	__u16 i_extra_isize;

867 868 869 870
#ifdef CONFIG_QUOTA
	/* quota space reservation, managed internally by quota code */
	qsize_t i_reserved_quota;
#endif
871

872 873
	/* completed IOs that might need unwritten extents handling */
	struct list_head i_completed_io_list;
874
	spinlock_t i_completed_io_lock;
875
	atomic_t i_ioend_count;	/* Number of outstanding io_end structs */
876 877
	/* current io_end structure for async DIO write*/
	ext4_io_end_t *cur_aio_dio;
878
	atomic_t i_aiodio_unwritten; /* Nr. of inflight conversions pending */
879 880

	spinlock_t i_block_reservation_lock;
881 882 883 884 885 886 887

	/*
	 * Transactions that contain inode's metadata needed to complete
	 * fsync and fdatasync, respectively.
	 */
	tid_t i_sync_tid;
	tid_t i_datasync_tid;
888 889
};

890 891 892
/*
 * File system states
 */
893 894 895
#define	EXT4_VALID_FS			0x0001	/* Unmounted cleanly */
#define	EXT4_ERROR_FS			0x0002	/* Errors detected */
#define	EXT4_ORPHAN_FS			0x0004	/* Orphans being recovered */
896

897 898 899 900 901 902 903
/*
 * 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 */

904 905 906
/*
 * Mount flags
 */
907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922
#define EXT4_MOUNT_OLDALLOC		0x00002  /* Don't use the new Orlov allocator */
#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 */
#define EXT4_MOUNT_MINIX_DF		0x00080	/* Mimics the Minix statfs */
#define EXT4_MOUNT_NOLOAD		0x00100	/* Don't use existing journal*/
#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 */
923
#define EXT4_MOUNT_NO_AUTO_DA_ALLOC	0x10000	/* No auto delalloc mapping */
924 925 926 927
#define EXT4_MOUNT_BARRIER		0x20000 /* Use block barriers */
#define EXT4_MOUNT_QUOTA		0x80000 /* Some quota option set */
#define EXT4_MOUNT_USRQUOTA		0x100000 /* "old" user quota */
#define EXT4_MOUNT_GRPQUOTA		0x200000 /* "old" group quota */
928
#define EXT4_MOUNT_DIOREAD_NOLOCK	0x400000 /* Enable support for dio read nolocking */
929
#define EXT4_MOUNT_JOURNAL_CHECKSUM	0x800000 /* Journal checksums */
930
#define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT	0x1000000 /* Journal Async Commit */
931
#define EXT4_MOUNT_I_VERSION            0x2000000 /* i_version support */
932
#define EXT4_MOUNT_MBLK_IO_SUBMIT	0x4000000 /* multi-block io submits */
933
#define EXT4_MOUNT_DELALLOC		0x8000000 /* Delalloc support */
934
#define EXT4_MOUNT_DATA_ERR_ABORT	0x10000000 /* Abort on file data write */
935
#define EXT4_MOUNT_BLOCK_VALIDITY	0x20000000 /* Block validity checking */
936
#define EXT4_MOUNT_DISCARD		0x40000000 /* Issue DISCARD requests */
937
#define EXT4_MOUNT_INIT_INODE_TABLE	0x80000000 /* Initialize uninitialized itables */
938

939 940 941
#define EXT4_MOUNT2_EXPLICIT_DELALLOC	0x00000001 /* User explicitly
						      specified delalloc */

942 943 944 945
#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
946 947
#define test_opt(sb, opt)		(EXT4_SB(sb)->s_mount_opt & \
					 EXT4_MOUNT_##opt)
948

949 950 951 952 953 954 955
#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)

A
Akinobu Mita 已提交
956
#define ext4_set_bit			__test_and_set_bit_le
957
#define ext4_set_bit_atomic		ext2_set_bit_atomic
A
Akinobu Mita 已提交
958
#define ext4_clear_bit			__test_and_clear_bit_le
959
#define ext4_clear_bit_atomic		ext2_clear_bit_atomic
A
Akinobu Mita 已提交
960 961 962 963
#define ext4_test_bit			test_bit_le
#define ext4_find_first_zero_bit	find_first_zero_bit_le
#define ext4_find_next_zero_bit		find_next_zero_bit_le
#define ext4_find_next_bit		find_next_bit_le
964

965 966
extern void ext4_set_bits(void *bm, int cur, int len);

967 968 969
/*
 * Maximal mount counts between two filesystem checks
 */
970 971
#define EXT4_DFL_MAX_MNT_COUNT		20	/* Allow 20 mounts */
#define EXT4_DFL_CHECKINTERVAL		0	/* Don't use interval check */
972 973 974 975

/*
 * Behaviour when detecting errors
 */
976 977 978 979
#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
980 981 982 983

/*
 * Structure of the super block
 */
984
struct ext4_super_block {
985
/*00*/	__le32	s_inodes_count;		/* Inodes count */
986
	__le32	s_blocks_count_lo;	/* Blocks count */
987 988
	__le32	s_r_blocks_count_lo;	/* Reserved blocks count */
	__le32	s_free_blocks_count_lo;	/* Free blocks count */
989 990 991
/*10*/	__le32	s_free_inodes_count;	/* Free inodes count */
	__le32	s_first_data_block;	/* First Data Block */
	__le32	s_log_block_size;	/* Block size */
992
	__le32	s_log_cluster_size;	/* Allocation cluster size */
993
/*20*/	__le32	s_blocks_per_group;	/* # Blocks per group */
994
	__le32	s_clusters_per_group;	/* # Clusters per group */
995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010
	__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 */
	/*
1011
	 * These fields are for EXT4_DYNAMIC_REV superblocks only.
1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023
	 *
	 * 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 */
1024
	__le16  s_inode_size;		/* size of inode structure */
1025 1026 1027 1028 1029 1030 1031 1032 1033 1034
	__le16	s_block_group_nr;	/* block group # of this superblock */
	__le32	s_feature_compat;	/* compatible feature set */
/*60*/	__le32	s_feature_incompat;	/* incompatible feature set */
	__le32	s_feature_ro_compat;	/* readonly-compatible feature set */
/*68*/	__u8	s_uuid[16];		/* 128-bit uuid for volume */
/*78*/	char	s_volume_name[16];	/* volume name */
/*88*/	char	s_last_mounted[64];	/* directory where last mounted */
/*C8*/	__le32	s_algorithm_usage_bitmap; /* For compression */
	/*
	 * Performance hints.  Directory preallocation should only
1035
	 * happen if the EXT4_FEATURE_COMPAT_DIR_PREALLOC flag is on.
1036 1037 1038 1039 1040
	 */
	__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 */
	/*
1041
	 * Journaling support valid if EXT4_FEATURE_COMPAT_HAS_JOURNAL set.
1042 1043 1044 1045 1046 1047 1048
	 */
/*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 */
1049
	__u8	s_jnl_backup_type;
1050
	__le16  s_desc_size;		/* size of group descriptor */
L
Laurent Vivier 已提交
1051
/*100*/	__le32	s_default_mount_opts;
1052
	__le32	s_first_meta_bg;	/* First metablock block group */
L
Laurent Vivier 已提交
1053 1054 1055 1056 1057 1058
	__le32	s_mkfs_time;		/* When the filesystem was created */
	__le32	s_jnl_blocks[17];	/* Backup of the journal inode */
	/* 64bit support valid if EXT4_FEATURE_COMPAT_64BIT */
/*150*/	__le32	s_blocks_count_hi;	/* Blocks count */
	__le32	s_r_blocks_count_hi;	/* Reserved blocks count */
	__le32	s_free_blocks_count_hi;	/* Free blocks count */
A
Aneesh Kumar K.V 已提交
1059 1060 1061 1062
	__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 */
1063
	__le16  s_mmp_update_interval;  /* # seconds to wait in MMP checking */
A
Aneesh Kumar K.V 已提交
1064 1065
	__le64  s_mmp_block;            /* Block for multi-mount protection */
	__le32  s_raid_stripe_width;    /* blocks on all data disks (N*stride)*/
1066
	__u8	s_log_groups_per_flex;  /* FLEX_BG group size */
1067
	__u8	s_reserved_char_pad;
1068
	__le16  s_reserved_pad;
T
Theodore Ts'o 已提交
1069
	__le64	s_kbytes_written;	/* nr of lifetime kilobytes written */
1070 1071 1072 1073 1074 1075
	__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 */
1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087
#define EXT4_S_ERR_START offsetof(struct ext4_super_block, s_error_count)
	__le32	s_error_count;		/* number of fs errors */
	__le32	s_first_error_time;	/* first time an error happened */
	__le32	s_first_error_ino;	/* inode involved in first error */
	__le64	s_first_error_block;	/* block involved of first error */
	__u8	s_first_error_func[32];	/* function where the error happened */
	__le32	s_first_error_line;	/* line number where error happened */
	__le32	s_last_error_time;	/* most recent time of an error */
	__le32	s_last_error_ino;	/* inode involved in last error */
	__le32	s_last_error_line;	/* line number where error happened */
	__le64	s_last_error_block;	/* block involved of last error */
	__u8	s_last_error_func[32];	/* function where the error happened */
1088 1089
#define EXT4_S_ERR_END offsetof(struct ext4_super_block, s_mount_opts)
	__u8	s_mount_opts[64];
1090 1091 1092 1093
	__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 */
	__le32  s_reserved[109];        /* Padding to the end of the block */
1094 1095
};

1096 1097
#define EXT4_S_ERR_LEN (EXT4_S_ERR_END - EXT4_S_ERR_START)

1098
#ifdef __KERNEL__
1099 1100

/*
1101
 * run-time mount flags
1102 1103
 */
#define EXT4_MF_MNTDIR_SAMPLED	0x0001
1104
#define EXT4_MF_FS_ABORTED	0x0002	/* Fatal error detected */
1105

1106 1107 1108 1109 1110 1111 1112
/*
 * 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 */
1113
	unsigned long s_clusters_per_group; /* Number of clusters in a group */
1114 1115 1116 1117 1118
	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 */
1119
	ext4_group_t s_blockfile_groups;/* Groups acceptable for non-extent files */
1120 1121
	unsigned long s_overhead_last;  /* Last calculated overhead */
	unsigned long s_blocks_last;    /* Last seen block count */
1122 1123
	unsigned int s_cluster_ratio;	/* Number of blocks per cluster */
	unsigned int s_cluster_bits;	/* log2 of s_cluster_ratio */
1124 1125 1126 1127
	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 */
	struct buffer_head **s_group_desc;
1128
	unsigned int s_mount_opt;
1129
	unsigned int s_mount_opt2;
1130
	unsigned int s_mount_flags;
1131 1132 1133 1134 1135 1136 1137 1138 1139 1140
	ext4_fsblk_t s_sb_block;
	uid_t s_resuid;
	gid_t s_resgid;
	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;
1141
	unsigned int s_inode_goal;
1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159
	spinlock_t s_next_gen_lock;
	u32 s_next_generation;
	u32 s_hash_seed[4];
	int s_def_hash_version;
	int s_hash_unsigned;	/* 3 if hash should be signed, 0 if not */
	struct percpu_counter s_freeblocks_counter;
	struct percpu_counter s_freeinodes_counter;
	struct percpu_counter s_dirs_counter;
	struct percpu_counter s_dirtyblocks_counter;
	struct blockgroup_lock *s_blockgroup_lock;
	struct proc_dir_entry *s_proc;
	struct kobject s_kobj;
	struct completion s_kobj_unregister;

	/* Journaling */
	struct journal_s *s_journal;
	struct list_head s_orphan;
	struct mutex s_orphan_lock;
1160 1161
	unsigned long s_resize_flags;		/* Flags indicating if there
						   is a resizer */
1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174
	unsigned long s_commit_interval;
	u32 s_max_batch_time;
	u32 s_min_batch_time;
	struct block_device *journal_bdev;
#ifdef CONFIG_JBD2_DEBUG
	struct timer_list turn_ro_timer;	/* For turning read-only (crash simulation) */
	wait_queue_head_t ro_wait_queue;	/* For people waiting for the fs to go read-only */
#endif
#ifdef CONFIG_QUOTA
	char *s_qf_names[MAXQUOTAS];		/* Names of quota files with journalled quota */
	int s_jquota_fmt;			/* Format of quota to use */
#endif
	unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */
1175
	struct rb_root system_blks;
1176 1177 1178 1179 1180 1181 1182 1183 1184 1185

#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
1186 1187 1188
	/* ext4 extent cache stats */
	unsigned long extent_cache_hits;
	unsigned long extent_cache_misses;
1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204

	/* for buddy allocator */
	struct ext4_group_info ***s_group_info;
	struct inode *s_buddy_cache;
	spinlock_t s_md_lock;
	unsigned short *s_mb_offsets;
	unsigned int *s_mb_maxs;

	/* tunables */
	unsigned long s_stripe;
	unsigned int s_mb_stream_request;
	unsigned int s_mb_max_to_scan;
	unsigned int s_mb_min_to_scan;
	unsigned int s_mb_stats;
	unsigned int s_mb_order2_reqs;
	unsigned int s_mb_group_prealloc;
1205
	unsigned int s_max_writeback_mb_bump;
1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223
	/* where last allocation was done - for stream allocation */
	unsigned long s_mb_last_group;
	unsigned long s_mb_last_start;

	/* stats for buddy allocator */
	atomic_t s_bal_reqs;	/* number of reqs with len > 1 */
	atomic_t s_bal_success;	/* we found long enough chunks */
	atomic_t s_bal_allocated;	/* in blocks */
	atomic_t s_bal_ex_scanned;	/* total extents scanned */
	atomic_t s_bal_goals;	/* goal hits */
	atomic_t s_bal_breaks;	/* too long searches */
	atomic_t s_bal_2orders;	/* 2^order hits */
	spinlock_t s_bal_lock;
	unsigned long s_mb_buddies_generated;
	unsigned long long s_mb_generation_time;
	atomic_t s_mb_lost_chunks;
	atomic_t s_mb_preallocated;
	atomic_t s_mb_discarded;
1224
	atomic_t s_lock_busy;
1225 1226

	/* locality groups */
1227
	struct ext4_locality_group __percpu *s_locality_groups;
1228 1229 1230 1231 1232 1233 1234

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

	unsigned int s_log_groups_per_flex;
	struct flex_groups *s_flex_groups;
1235 1236 1237

	/* workqueue for dio unwritten */
	struct workqueue_struct *dio_unwritten_wq;
1238 1239 1240

	/* timer for periodic error stats printing */
	struct timer_list s_err_report;
1241 1242 1243 1244 1245

	/* Lazy inode table initialization info */
	struct ext4_li_request *s_li_request;
	/* Wait multiplier for lazy initialization thread */
	unsigned int s_li_wait_mult;
1246 1247 1248

	/* Kernel thread for multiple mount protection */
	struct task_struct *s_mmp_tsk;
1249 1250 1251

	/* record the last minlen when FITRIM is called. */
	atomic_t s_last_trim_minblks;
1252 1253
};

1254
static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
1255 1256 1257
{
	return sb->s_fs_info;
}
1258
static inline struct ext4_inode_info *EXT4_I(struct inode *inode)
1259
{
1260
	return container_of(inode, struct ext4_inode_info, vfs_inode);
1261 1262
}

K
Kalpak Shah 已提交
1263 1264 1265 1266 1267 1268
static inline struct timespec ext4_current_time(struct inode *inode)
{
	return (inode->i_sb->s_time_gran < NSEC_PER_SEC) ?
		current_fs_time(inode->i_sb) : CURRENT_TIME_SEC;
}

1269
static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
1270
{
1271 1272 1273 1274 1275
	return ino == EXT4_ROOT_INO ||
		ino == EXT4_JOURNAL_INO ||
		ino == EXT4_RESIZE_INO ||
		(ino >= EXT4_FIRST_INO(sb) &&
		 ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
1276
}
1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288

/*
 * Inode dynamic state flags
 */
enum {
	EXT4_STATE_JDATA,		/* journaled data exists */
	EXT4_STATE_NEW,			/* inode is newly created */
	EXT4_STATE_XATTR,		/* has in-inode xattrs */
	EXT4_STATE_NO_EXPAND,		/* No space for expansion */
	EXT4_STATE_DA_ALLOC_CLOSE,	/* Alloc DA blks on close */
	EXT4_STATE_EXT_MIGRATE,		/* Inode is migrating */
	EXT4_STATE_DIO_UNWRITTEN,	/* need convert on dio done*/
1289
	EXT4_STATE_NEWENTRY,		/* File just added to dir */
1290
	EXT4_STATE_DELALLOC_RESERVED,	/* blks already reserved for delalloc */
1291 1292
};

1293
#define EXT4_INODE_BIT_FNS(name, field, offset)				\
1294 1295
static inline int ext4_test_inode_##name(struct inode *inode, int bit)	\
{									\
1296
	return test_bit(bit + (offset), &EXT4_I(inode)->i_##field);	\
1297 1298 1299
}									\
static inline void ext4_set_inode_##name(struct inode *inode, int bit)	\
{									\
1300
	set_bit(bit + (offset), &EXT4_I(inode)->i_##field);		\
1301 1302 1303
}									\
static inline void ext4_clear_inode_##name(struct inode *inode, int bit) \
{									\
1304
	clear_bit(bit + (offset), &EXT4_I(inode)->i_##field);		\
1305 1306
}

1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322
EXT4_INODE_BIT_FNS(flag, flags, 0)
#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
1323
#else
1324
/* Assume that user mode programs are passing in an ext4fs superblock, not
1325 1326
 * a kernel struct super_block.  This will allow us to call the feature-test
 * macros from user land. */
1327
#define EXT4_SB(sb)	(sb)
1328 1329
#endif

1330
#define NEXT_ORPHAN(inode) EXT4_I(inode)->i_dtime
1331 1332 1333 1334

/*
 * Codes for operating systems
 */
1335 1336 1337 1338 1339
#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
1340 1341 1342 1343

/*
 * Revision levels
 */
1344 1345
#define EXT4_GOOD_OLD_REV	0	/* The good old (original) format */
#define EXT4_DYNAMIC_REV	1	/* V2 format w/ dynamic inode sizes */
1346

1347 1348
#define EXT4_CURRENT_REV	EXT4_GOOD_OLD_REV
#define EXT4_MAX_SUPP_REV	EXT4_DYNAMIC_REV
1349

1350
#define EXT4_GOOD_OLD_INODE_SIZE 128
1351 1352 1353 1354 1355

/*
 * Feature set definitions
 */

1356
#define EXT4_HAS_COMPAT_FEATURE(sb,mask)			\
A
Aneesh Kumar K.V 已提交
1357
	((EXT4_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask)) != 0)
1358
#define EXT4_HAS_RO_COMPAT_FEATURE(sb,mask)			\
A
Aneesh Kumar K.V 已提交
1359
	((EXT4_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask)) != 0)
1360
#define EXT4_HAS_INCOMPAT_FEATURE(sb,mask)			\
A
Aneesh Kumar K.V 已提交
1361
	((EXT4_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask)) != 0)
1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384
#define EXT4_SET_COMPAT_FEATURE(sb,mask)			\
	EXT4_SB(sb)->s_es->s_feature_compat |= cpu_to_le32(mask)
#define EXT4_SET_RO_COMPAT_FEATURE(sb,mask)			\
	EXT4_SB(sb)->s_es->s_feature_ro_compat |= cpu_to_le32(mask)
#define EXT4_SET_INCOMPAT_FEATURE(sb,mask)			\
	EXT4_SB(sb)->s_es->s_feature_incompat |= cpu_to_le32(mask)
#define EXT4_CLEAR_COMPAT_FEATURE(sb,mask)			\
	EXT4_SB(sb)->s_es->s_feature_compat &= ~cpu_to_le32(mask)
#define EXT4_CLEAR_RO_COMPAT_FEATURE(sb,mask)			\
	EXT4_SB(sb)->s_es->s_feature_ro_compat &= ~cpu_to_le32(mask)
#define EXT4_CLEAR_INCOMPAT_FEATURE(sb,mask)			\
	EXT4_SB(sb)->s_es->s_feature_incompat &= ~cpu_to_le32(mask)

#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

#define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER	0x0001
#define EXT4_FEATURE_RO_COMPAT_LARGE_FILE	0x0002
#define EXT4_FEATURE_RO_COMPAT_BTREE_DIR	0x0004
1385
#define EXT4_FEATURE_RO_COMPAT_HUGE_FILE        0x0008
A
Andreas Dilger 已提交
1386
#define EXT4_FEATURE_RO_COMPAT_GDT_CSUM		0x0010
1387
#define EXT4_FEATURE_RO_COMPAT_DIR_NLINK	0x0020
K
Kalpak Shah 已提交
1388
#define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE	0x0040
1389
#define EXT4_FEATURE_RO_COMPAT_QUOTA		0x0100
1390
#define EXT4_FEATURE_RO_COMPAT_BIGALLOC		0x0200
1391 1392 1393 1394 1395 1396

#define EXT4_FEATURE_INCOMPAT_COMPRESSION	0x0001
#define EXT4_FEATURE_INCOMPAT_FILETYPE		0x0002
#define EXT4_FEATURE_INCOMPAT_RECOVER		0x0004 /* Needs recovery */
#define EXT4_FEATURE_INCOMPAT_JOURNAL_DEV	0x0008 /* Journal device */
#define EXT4_FEATURE_INCOMPAT_META_BG		0x0010
A
Alex Tomas 已提交
1397
#define EXT4_FEATURE_INCOMPAT_EXTENTS		0x0040 /* extents support */
L
Laurent Vivier 已提交
1398
#define EXT4_FEATURE_INCOMPAT_64BIT		0x0080
1399
#define EXT4_FEATURE_INCOMPAT_MMP               0x0100
J
Jose R. Santos 已提交
1400
#define EXT4_FEATURE_INCOMPAT_FLEX_BG		0x0200
1401 1402
#define EXT4_FEATURE_INCOMPAT_EA_INODE		0x0400 /* EA in inode */
#define EXT4_FEATURE_INCOMPAT_DIRDATA		0x1000 /* data in dirent */
1403

1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418
#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)

1419 1420 1421
#define EXT4_FEATURE_COMPAT_SUPP	EXT2_FEATURE_COMPAT_EXT_ATTR
#define EXT4_FEATURE_INCOMPAT_SUPP	(EXT4_FEATURE_INCOMPAT_FILETYPE| \
					 EXT4_FEATURE_INCOMPAT_RECOVER| \
A
Alex Tomas 已提交
1422
					 EXT4_FEATURE_INCOMPAT_META_BG| \
L
Laurent Vivier 已提交
1423
					 EXT4_FEATURE_INCOMPAT_EXTENTS| \
J
Jose R. Santos 已提交
1424
					 EXT4_FEATURE_INCOMPAT_64BIT| \
1425 1426
					 EXT4_FEATURE_INCOMPAT_FLEX_BG| \
					 EXT4_FEATURE_INCOMPAT_MMP)
1427 1428
#define EXT4_FEATURE_RO_COMPAT_SUPP	(EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
					 EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \
A
Andreas Dilger 已提交
1429
					 EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \
1430
					 EXT4_FEATURE_RO_COMPAT_DIR_NLINK | \
K
Kalpak Shah 已提交
1431
					 EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \
1432 1433
					 EXT4_FEATURE_RO_COMPAT_BTREE_DIR |\
					 EXT4_FEATURE_RO_COMPAT_HUGE_FILE)
1434 1435 1436 1437

/*
 * Default values for user and/or group using reserved blocks
 */
1438 1439
#define	EXT4_DEF_RESUID		0
#define	EXT4_DEF_RESGID		0
1440

1441 1442
#define EXT4_DEF_INODE_READAHEAD_BLKS	32

1443 1444 1445
/*
 * Default mount options
 */
1446 1447 1448 1449 1450 1451 1452 1453 1454
#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
1455 1456 1457 1458
#define EXT4_DEFM_NOBARRIER	0x0100
#define EXT4_DEFM_BLOCK_VALIDITY 0x0200
#define EXT4_DEFM_DISCARD	0x0400
#define EXT4_DEFM_NODELALLOC	0x0800
1459

1460 1461 1462 1463 1464 1465
/*
 * Default journal batch times
 */
#define EXT4_DEF_MIN_BATCH_TIME	0
#define EXT4_DEF_MAX_BATCH_TIME	15000 /* 15ms */

1466 1467 1468 1469 1470 1471
/*
 * 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

1472 1473 1474
/*
 * Structure of a directory entry
 */
1475
#define EXT4_NAME_LEN 255
1476

1477
struct ext4_dir_entry {
1478 1479 1480
	__le32	inode;			/* Inode number */
	__le16	rec_len;		/* Directory entry length */
	__le16	name_len;		/* Name length */
1481
	char	name[EXT4_NAME_LEN];	/* File name */
1482 1483 1484
};

/*
1485
 * The new version of the directory entry.  Since EXT4 structures are
1486 1487 1488 1489
 * 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.
 */
1490
struct ext4_dir_entry_2 {
1491 1492 1493 1494
	__le32	inode;			/* Inode number */
	__le16	rec_len;		/* Directory entry length */
	__u8	name_len;		/* Name length */
	__u8	file_type;
1495
	char	name[EXT4_NAME_LEN];	/* File name */
1496 1497 1498
};

/*
1499
 * Ext4 directory file types.  Only the low 3 bits are used.  The
1500 1501
 * other bits are reserved for now.
 */
1502 1503 1504 1505 1506 1507 1508 1509
#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
1510

1511
#define EXT4_FT_MAX		8
1512 1513

/*
1514
 * EXT4_DIR_PAD defines the directory entries boundaries
1515 1516 1517
 *
 * NOTE: It must be a multiple of 4
 */
1518 1519 1520 1521
#define EXT4_DIR_PAD			4
#define EXT4_DIR_ROUND			(EXT4_DIR_PAD - 1)
#define EXT4_DIR_REC_LEN(name_len)	(((name_len) + 8 + EXT4_DIR_ROUND) & \
					 ~EXT4_DIR_ROUND)
1522 1523
#define EXT4_MAX_REC_LEN		((1<<16)-1)

1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560
/*
 * 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);

#if (PAGE_CACHE_SIZE >= 65536)
	if (len == EXT4_MAX_REC_LEN || len == 0)
		return blocksize;
	return (len & 65532) | ((len & 3) << 16);
#else
	return len;
#endif
}

static inline __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize)
{
	if ((len > blocksize) || (blocksize > (1 << 18)) || (len & 3))
		BUG();
#if (PAGE_CACHE_SIZE >= 65536)
	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
}

1561 1562 1563 1564 1565
/*
 * Hash Tree Directory indexing
 * (c) Daniel Phillips, 2001
 */

1566 1567
#define is_dx(dir) (EXT4_HAS_COMPAT_FEATURE(dir->i_sb, \
				      EXT4_FEATURE_COMPAT_DIR_INDEX) && \
1568
		    ext4_test_inode_flag((dir), EXT4_INODE_INDEX))
1569 1570
#define EXT4_DIR_LINK_MAX(dir) (!is_dx(dir) && (dir)->i_nlink >= EXT4_LINK_MAX)
#define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2 || (dir)->i_nlink == 1)
1571 1572 1573 1574 1575 1576

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

#define DX_HASH_LEGACY		0
#define DX_HASH_HALF_MD4	1
#define DX_HASH_TEA		2
1577 1578 1579
#define DX_HASH_LEGACY_UNSIGNED	3
#define DX_HASH_HALF_MD4_UNSIGNED	4
#define DX_HASH_TEA_UNSIGNED		5
1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591

#ifdef __KERNEL__

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

1592
#define EXT4_HTREE_EOF	0x7fffffff
1593 1594

/*
1595
 * Control parameters used by ext4_htree_next_block
1596 1597 1598 1599 1600 1601 1602
 */
#define HASH_NB_ALWAYS		1


/*
 * Describe an inode's exact location on disk and in memory
 */
1603
struct ext4_iloc
1604 1605 1606
{
	struct buffer_head *bh;
	unsigned long offset;
1607
	ext4_group_t block_group;
1608 1609
};

1610
static inline struct ext4_inode *ext4_raw_inode(struct ext4_iloc *iloc)
1611
{
1612
	return (struct ext4_inode *) (iloc->bh->b_data + iloc->offset);
1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630
}

/*
 * 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 */
1631
static inline ext4_fsblk_t
1632
ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no)
1633
{
1634 1635
	return group_no * (ext4_fsblk_t)EXT4_BLOCKS_PER_GROUP(sb) +
		le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
1636 1637 1638 1639 1640 1641 1642
}

/*
 * Special error return code only used by dx_probe() and its callers.
 */
#define ERR_BAD_DX_DIR	-75000

1643
void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
1644
			ext4_group_t *blockgrpp, ext4_grpblk_t *offsetp);
1645

1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671
/*
 * 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;
};

struct ext4_li_request {
	struct super_block	*lr_super;
	struct ext4_sb_info	*lr_sbi;
	ext4_group_t		lr_next_group;
	struct list_head	lr_request;
	unsigned long		lr_next_sched;
	unsigned long		lr_timeout;
};

1672 1673 1674 1675 1676
struct ext4_features {
	struct kobject f_kobj;
	struct completion f_kobj_unregister;
};

1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737
/*
 * 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;
	__le32	mmp_pad2[227];
};

/* 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

1738 1739 1740 1741 1742 1743
/*
 * Function prototypes
 */

/*
 * Ok, these declarations are also in <linux/kernel.h> but none of the
1744
 * ext4 source programs needs to include it so they are duplicated here.
1745
 */
D
Dave Kleikamp 已提交
1746 1747 1748
# define NORET_TYPE	/**/
# define ATTRIB_NORET	__attribute__((noreturn))
# define NORET_AND	noreturn,
1749

1750 1751 1752
/* bitmap.c */
extern unsigned int ext4_count_free(struct buffer_head *, unsigned);

1753
/* balloc.c */
1754 1755 1756 1757
extern unsigned int ext4_block_group(struct super_block *sb,
			ext4_fsblk_t blocknr);
extern ext4_grpblk_t ext4_block_group_offset(struct super_block *sb,
			ext4_fsblk_t blocknr);
1758 1759 1760
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);
1761
extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
1762 1763 1764 1765 1766 1767
					 ext4_fsblk_t goal,
					 unsigned int flags,
					 unsigned long *count,
					 int *errp);
extern int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
				  s64 nblocks, unsigned int flags);
1768 1769
extern ext4_fsblk_t ext4_count_free_blocks(struct super_block *);
extern void ext4_check_blocks_bitmap(struct super_block *);
1770
extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
1771
						    ext4_group_t block_group,
1772
						    struct buffer_head ** bh);
1773
extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
1774 1775
struct buffer_head *ext4_read_block_bitmap(struct super_block *sb,
				      ext4_group_t block_group);
1776 1777 1778 1779 1780 1781 1782
extern void ext4_init_block_bitmap(struct super_block *sb,
				   struct buffer_head *bh,
				   ext4_group_t group,
				   struct ext4_group_desc *desc);
extern unsigned ext4_free_blocks_after_init(struct super_block *sb,
					    ext4_group_t block_group,
					    struct ext4_group_desc *gdp);
1783 1784 1785 1786 1787
extern unsigned ext4_num_base_meta_clusters(struct super_block *sb,
					    ext4_group_t block_group);
extern unsigned ext4_num_overhead_clusters(struct super_block *sb,
					   ext4_group_t block_group,
					   struct ext4_group_desc *gdp);
1788
ext4_fsblk_t ext4_inode_to_goal_block(struct inode *);
1789 1790

/* dir.c */
1791
extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *,
1792
				  struct file *,
1793 1794
				  struct ext4_dir_entry_2 *,
				  struct buffer_head *, unsigned int);
1795 1796 1797
#define ext4_check_dir_entry(dir, filp, de, bh, offset)			\
	unlikely(__ext4_check_dir_entry(__func__, __LINE__, (dir), (filp), \
					(de), (bh), (offset)))
1798
extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
1799
				    __u32 minor_hash,
1800 1801
				    struct ext4_dir_entry_2 *dirent);
extern void ext4_htree_free_dir_info(struct dir_private_info *p);
1802 1803

/* fsync.c */
1804
extern int ext4_sync_file(struct file *, loff_t, loff_t, int);
1805
extern int ext4_flush_completed_IO(struct inode *);
1806 1807

/* hash.c */
1808
extern int ext4fs_dirhash(const char *name, int len, struct
1809 1810 1811
			  dx_hash_info *hinfo);

/* ialloc.c */
1812
extern struct inode *ext4_new_inode(handle_t *, struct inode *, int,
1813
				    const struct qstr *qstr, __u32 goal);
1814 1815 1816 1817 1818
extern void ext4_free_inode(handle_t *, struct inode *);
extern struct inode * ext4_orphan_get(struct super_block *, unsigned long);
extern unsigned long ext4_count_free_inodes(struct super_block *);
extern unsigned long ext4_count_dirs(struct super_block *);
extern void ext4_check_inodes_bitmap(struct super_block *);
1819
extern void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
1820 1821
extern int ext4_init_inode_table(struct super_block *sb,
				 ext4_group_t group, int barrier);
1822

1823 1824 1825 1826 1827 1828 1829 1830
/* mballoc.c */
extern long ext4_mb_stats;
extern long ext4_mb_max_to_scan;
extern int ext4_mb_init(struct super_block *, int);
extern int ext4_mb_release(struct super_block *);
extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *,
				struct ext4_allocation_request *, int *);
extern int ext4_mb_reserve_blocks(struct super_block *, int);
1831
extern void ext4_discard_preallocations(struct inode *);
1832 1833
extern int __init ext4_init_mballoc(void);
extern void ext4_exit_mballoc(void);
1834
extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
1835 1836
			     struct buffer_head *bh, ext4_fsblk_t block,
			     unsigned long count, int flags);
1837
extern int ext4_mb_add_groupinfo(struct super_block *sb,
1838
		ext4_group_t i, struct ext4_group_desc *desc);
1839
extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
1840
				ext4_fsblk_t block, unsigned long count);
1841 1842
extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);

1843
/* inode.c */
A
Aneesh Kumar K.V 已提交
1844 1845 1846 1847
struct buffer_head *ext4_getblk(handle_t *, struct inode *,
						ext4_lblk_t, int, int *);
struct buffer_head *ext4_bread(handle_t *, struct inode *,
						ext4_lblk_t, int, int *);
1848 1849
int ext4_get_block(struct inode *inode, sector_t iblock,
				struct buffer_head *bh_result, int create);
1850

1851
extern struct inode *ext4_iget(struct super_block *, unsigned long);
1852
extern int  ext4_write_inode(struct inode *, struct writeback_control *);
1853
extern int  ext4_setattr(struct dentry *, struct iattr *);
1854 1855
extern int  ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
				struct kstat *stat);
A
Al Viro 已提交
1856 1857
extern void ext4_evict_inode(struct inode *);
extern void ext4_clear_inode(struct inode *);
1858
extern int  ext4_sync_inode(handle_t *, struct inode *);
1859
extern void ext4_dirty_inode(struct inode *, int);
1860 1861
extern int ext4_change_inode_journal_flag(struct inode *, int);
extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
1862
extern int ext4_can_truncate(struct inode *inode);
1863
extern void ext4_truncate(struct inode *);
1864
extern int ext4_punch_hole(struct file *file, loff_t offset, loff_t length);
1865
extern int ext4_truncate_restart_trans(handle_t *, struct inode *, int nblocks);
1866
extern void ext4_set_inode_flags(struct inode *);
1867
extern void ext4_get_inode_flags(struct ext4_inode_info *);
1868
extern int ext4_alloc_da_blocks(struct inode *inode);
1869
extern void ext4_set_aops(struct inode *inode);
A
Alex Tomas 已提交
1870
extern int ext4_writepage_trans_blocks(struct inode *);
1871
extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
1872
extern int ext4_block_truncate_page(handle_t *handle,
A
Alex Tomas 已提交
1873
		struct address_space *mapping, loff_t from);
1874 1875
extern int ext4_block_zero_page_range(handle_t *handle,
		struct address_space *mapping, loff_t from, loff_t length);
1876 1877 1878 1879 1880 1881
extern int ext4_discard_partial_page_buffers(handle_t *handle,
		struct address_space *mapping, loff_t from,
		loff_t length, int flags);
extern int ext4_discard_partial_page_buffers_no_lock(handle_t *handle,
		struct inode *inode, struct page *page, loff_t from,
		loff_t length, int flags);
1882
extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
1883
extern qsize_t *ext4_get_reserved_space(struct inode *inode);
1884 1885
extern void ext4_da_update_reserve_space(struct inode *inode,
					int used, int quota_claim);
1886 1887 1888 1889 1890 1891 1892 1893 1894

/* indirect.c */
extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
				struct ext4_map_blocks *map, int flags);
extern ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
				const struct iovec *iov, loff_t offset,
				unsigned long nr_segs);
extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock);
extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks, int chunk);
1895 1896
extern void ext4_ind_truncate(struct inode *inode);

1897
/* ioctl.c */
A
Andi Kleen 已提交
1898
extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
1899
extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
1900

1901
/* migrate.c */
1902
extern int ext4_ext_migrate(struct inode *);
1903

1904
/* namei.c */
1905 1906 1907
extern int ext4_orphan_add(handle_t *, struct inode *);
extern int ext4_orphan_del(handle_t *, struct inode *);
extern int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
1908 1909 1910
				__u32 start_minor_hash, __u32 *next_hash);

/* resize.c */
1911 1912 1913 1914 1915
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);
1916 1917

/* super.c */
1918 1919 1920
extern void *ext4_kvmalloc(size_t size, gfp_t flags);
extern void *ext4_kvzalloc(size_t size, gfp_t flags);
extern void ext4_kvfree(void *ptr);
1921 1922 1923 1924 1925 1926 1927 1928 1929
extern void __ext4_error(struct super_block *, const char *, unsigned int,
			 const char *, ...)
	__attribute__ ((format (printf, 4, 5)));
#define ext4_error(sb, message...)	__ext4_error(sb, __func__,	\
						     __LINE__, ## message)
extern void ext4_error_inode(struct inode *, const char *, unsigned int,
			     ext4_fsblk_t, const char *, ...)
	__attribute__ ((format (printf, 5, 6)));
extern void ext4_error_file(struct file *, const char *, unsigned int,
1930 1931
			    ext4_fsblk_t, const char *, ...)
	__attribute__ ((format (printf, 5, 6)));
1932 1933 1934 1935 1936
extern void __ext4_std_error(struct super_block *, const char *,
			     unsigned int, int);
extern void __ext4_abort(struct super_block *, const char *, unsigned int,
		       const char *, ...)
	__attribute__ ((format (printf, 4, 5)));
1937
#define ext4_abort(sb, message...)	__ext4_abort(sb, __func__, \
1938 1939
						       __LINE__, ## message)
extern void __ext4_warning(struct super_block *, const char *, unsigned int,
1940
			  const char *, ...)
1941 1942 1943
	__attribute__ ((format (printf, 4, 5)));
#define ext4_warning(sb, message...)	__ext4_warning(sb, __func__, \
						       __LINE__, ## message)
1944 1945
extern void ext4_msg(struct super_block *, const char *, const char *, ...)
	__attribute__ ((format (printf, 3, 4)));
1946 1947 1948 1949
extern void __dump_mmp_msg(struct super_block *, struct mmp_struct *mmp,
			   const char *, unsigned int, const char *);
#define dump_mmp_msg(sb, mmp, msg)	__dump_mmp_msg(sb, mmp, __func__, \
						       __LINE__, msg)
1950 1951 1952 1953 1954 1955 1956
extern void __ext4_grp_locked_error(const char *, unsigned int, \
				    struct super_block *, ext4_group_t, \
				    unsigned long, ext4_fsblk_t, \
				    const char *, ...)
	__attribute__ ((format (printf, 7, 8)));
#define ext4_grp_locked_error(sb, grp, message...) \
	__ext4_grp_locked_error(__func__, __LINE__, (sb), (grp), ## message)
1957
extern void ext4_update_dynamic_rev(struct super_block *sb);
1958 1959 1960 1961 1962 1963
extern int ext4_update_compat_feature(handle_t *handle, struct super_block *sb,
					__u32 compat);
extern int ext4_update_rocompat_feature(handle_t *handle,
					struct super_block *sb,	__u32 rocompat);
extern int ext4_update_incompat_feature(handle_t *handle,
					struct super_block *sb,	__u32 incompat);
1964 1965 1966 1967 1968 1969
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);
1970 1971 1972 1973 1974 1975 1976 1977
extern __u32 ext4_free_blks_count(struct super_block *sb,
				struct ext4_group_desc *bg);
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);
1978 1979 1980 1981 1982 1983
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);
1984 1985 1986 1987 1988 1989 1990 1991
extern void ext4_free_blks_set(struct super_block *sb,
			       struct ext4_group_desc *bg, __u32 count);
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);
1992 1993 1994 1995
extern __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 group,
				   struct ext4_group_desc *gdp);
extern int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 group,
				       struct ext4_group_desc *gdp);
L
Laurent Vivier 已提交
1996 1997 1998 1999

static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es)
{
	return ((ext4_fsblk_t)le32_to_cpu(es->s_blocks_count_hi) << 32) |
2000
		le32_to_cpu(es->s_blocks_count_lo);
L
Laurent Vivier 已提交
2001 2002 2003 2004 2005
}

static inline ext4_fsblk_t ext4_r_blocks_count(struct ext4_super_block *es)
{
	return ((ext4_fsblk_t)le32_to_cpu(es->s_r_blocks_count_hi) << 32) |
2006
		le32_to_cpu(es->s_r_blocks_count_lo);
L
Laurent Vivier 已提交
2007 2008 2009 2010 2011
}

static inline ext4_fsblk_t ext4_free_blocks_count(struct ext4_super_block *es)
{
	return ((ext4_fsblk_t)le32_to_cpu(es->s_free_blocks_count_hi) << 32) |
2012
		le32_to_cpu(es->s_free_blocks_count_lo);
L
Laurent Vivier 已提交
2013 2014 2015 2016 2017
}

static inline void ext4_blocks_count_set(struct ext4_super_block *es,
					 ext4_fsblk_t blk)
{
2018
	es->s_blocks_count_lo = cpu_to_le32((u32)blk);
L
Laurent Vivier 已提交
2019 2020 2021 2022 2023 2024
	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)
{
2025
	es->s_free_blocks_count_lo = cpu_to_le32((u32)blk);
L
Laurent Vivier 已提交
2026 2027 2028 2029 2030 2031
	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)
{
2032
	es->s_r_blocks_count_lo = cpu_to_le32((u32)blk);
L
Laurent Vivier 已提交
2033 2034 2035
	es->s_r_blocks_count_hi = cpu_to_le32(blk >> 32);
}

2036 2037
static inline loff_t ext4_isize(struct ext4_inode *raw_inode)
{
2038 2039 2040 2041 2042
	if (S_ISREG(le16_to_cpu(raw_inode->i_mode)))
		return ((loff_t)le32_to_cpu(raw_inode->i_size_high) << 32) |
			le32_to_cpu(raw_inode->i_size_lo);
	else
		return (loff_t) le32_to_cpu(raw_inode->i_size_lo);
2043
}
L
Laurent Vivier 已提交
2044

2045 2046 2047 2048 2049
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);
}
2050

2051 2052
static inline
struct ext4_group_info *ext4_get_group_info(struct super_block *sb,
2053
					    ext4_group_t group)
2054 2055 2056 2057 2058 2059 2060 2061 2062
{
	 struct ext4_group_info ***grp_info;
	 long indexv, indexh;
	 grp_info = EXT4_SB(sb)->s_group_info;
	 indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb));
	 indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1);
	 return grp_info[indexv][indexh];
}

2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074
/*
 * 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;
}
2075

2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086
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;
}

2087
#define ext4_std_error(sb, errno)				\
2088 2089
do {								\
	if ((errno))						\
2090
		__ext4_std_error((sb), __func__, __LINE__, (errno));	\
2091 2092
} while (0)

2093
#ifdef CONFIG_SMP
2094
/* Each CPU can accumulate percpu_counter_batch blocks in their local
2095
 * counters. So we need to make sure we have free blocks more
2096
 * than percpu_counter_batch  * nr_cpu_ids. Also add a window of 4 times.
2097
 */
2098
#define EXT4_FREEBLOCKS_WATERMARK (4 * (percpu_counter_batch * nr_cpu_ids))
2099 2100 2101 2102
#else
#define EXT4_FREEBLOCKS_WATERMARK 0
#endif

2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113
static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
{
	/*
	 * XXX: replace with spinlock if seen contended -bzzz
	 */
	down_write(&EXT4_I(inode)->i_data_sem);
	if (newsize > EXT4_I(inode)->i_disksize)
		EXT4_I(inode)->i_disksize = newsize;
	up_write(&EXT4_I(inode)->i_data_sem);
	return ;
}
2114

2115 2116 2117
struct ext4_group_info {
	unsigned long   bb_state;
	struct rb_root  bb_free_root;
2118 2119 2120
	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 */
2121
	ext4_grpblk_t	bb_largest_free_order;/* order of largest frag in BG */
2122 2123 2124 2125 2126
	struct          list_head bb_prealloc_list;
#ifdef DOUBLE_CHECK
	void            *bb_bitmap;
#endif
	struct rw_semaphore alloc_sem;
2127 2128 2129 2130
	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. */
2131 2132
};

2133 2134
#define EXT4_GROUP_INFO_NEED_INIT_BIT		0
#define EXT4_GROUP_INFO_WAS_TRIMMED_BIT		1
2135 2136 2137 2138

#define EXT4_MB_GRP_NEED_INIT(grp)	\
	(test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))

2139 2140 2141 2142 2143 2144 2145
#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)))

2146 2147 2148
#define EXT4_MAX_CONTENTION		8
#define EXT4_CONTENTION_THRESHOLD	2

2149 2150
static inline spinlock_t *ext4_group_lock_ptr(struct super_block *sb,
					      ext4_group_t group)
2151
{
2152 2153
	return bgl_lock_ptr(EXT4_SB(sb)->s_blockgroup_lock, group);
}
2154

2155 2156 2157 2158 2159 2160 2161 2162 2163
/*
 * 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);
}

2164 2165
static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group)
{
2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181
	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);
	}
2182 2183 2184 2185 2186
}

static inline void ext4_unlock_group(struct super_block *sb,
					ext4_group_t group)
{
2187
	spin_unlock(ext4_group_lock_ptr(sb, group));
2188 2189
}

T
Theodore Ts'o 已提交
2190 2191 2192 2193 2194 2195
static inline void ext4_mark_super_dirty(struct super_block *sb)
{
	if (EXT4_SB(sb)->s_journal == NULL)
		sb->s_dirt =1;
}

2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208
/*
 * 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)

2209 2210 2211 2212 2213
/*
 * Inodes and files operations
 */

/* dir.c */
2214
extern const struct file_operations ext4_dir_operations;
2215 2216

/* file.c */
2217
extern const struct inode_operations ext4_file_inode_operations;
2218
extern const struct file_operations ext4_file_operations;
2219
extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
2220 2221

/* namei.c */
2222 2223
extern const struct inode_operations ext4_dir_inode_operations;
extern const struct inode_operations ext4_special_inode_operations;
2224
extern struct dentry *ext4_get_parent(struct dentry *child);
2225 2226

/* symlink.c */
2227 2228
extern const struct inode_operations ext4_symlink_inode_operations;
extern const struct inode_operations ext4_fast_symlink_inode_operations;
2229

2230 2231 2232
/* block_validity */
extern void ext4_release_system_zone(struct super_block *sb);
extern int ext4_setup_system_zone(struct super_block *sb);
2233 2234
extern int __init ext4_init_system_zone(void);
extern void ext4_exit_system_zone(void);
2235 2236 2237
extern int ext4_data_block_valid(struct ext4_sb_info *sbi,
				 ext4_fsblk_t start_blk,
				 unsigned int count);
2238 2239
extern int ext4_check_blockref(const char *, unsigned int,
			       struct inode *, __le32 *, unsigned int);
2240

A
Alex Tomas 已提交
2241 2242 2243
/* extents.c */
extern int ext4_ext_tree_init(handle_t *handle, struct inode *);
extern int ext4_ext_writepage_trans_blocks(struct inode *, int);
2244 2245
extern int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks,
				       int chunk);
2246 2247
extern int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
			       struct ext4_map_blocks *map, int flags);
2248
extern void ext4_ext_truncate(struct inode *);
2249 2250
extern int ext4_ext_punch_hole(struct file *file, loff_t offset,
				loff_t length);
A
Alex Tomas 已提交
2251 2252
extern void ext4_ext_init(struct super_block *);
extern void ext4_ext_release(struct super_block *);
2253
extern long ext4_fallocate(struct file *file, int mode, loff_t offset,
A
Amit Arora 已提交
2254
			  loff_t len);
2255
extern int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
2256
			  ssize_t len);
2257 2258
extern int ext4_map_blocks(handle_t *handle, struct inode *inode,
			   struct ext4_map_blocks *map, int flags);
A
Aneesh Kumar K.V 已提交
2259 2260
extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
			__u64 start, __u64 len);
2261 2262 2263 2264 2265
/* move_extent.c */
extern int ext4_move_extents(struct file *o_filp, struct file *d_filp,
			     __u64 start_orig, __u64 start_donor,
			     __u64 len, __u64 *moved_len);

2266
/* page-io.c */
2267 2268
extern int __init ext4_init_pageio(void);
extern void ext4_exit_pageio(void);
2269
extern void ext4_ioend_wait(struct inode *);
2270 2271 2272 2273 2274 2275 2276 2277
extern void ext4_free_io_end(ext4_io_end_t *io);
extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags);
extern int ext4_end_io_nolock(ext4_io_end_t *io);
extern void ext4_io_submit(struct ext4_io_submit *io);
extern int ext4_bio_write_page(struct ext4_io_submit *io,
			       struct page *page,
			       int len,
			       struct writeback_control *wbc);
A
Aneesh Kumar K.V 已提交
2278

2279 2280 2281
/* mmp.c */
extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);

2282 2283 2284 2285 2286 2287 2288 2289 2290
/* BH_Uninit flag: blocks are allocated but uninitialized on disk */
enum ext4_state_bits {
	BH_Uninit	/* blocks are allocated but uninitialized on disk */
	  = BH_JBDPrivateStart,
};

BUFFER_FNS(Uninit, uninit)
TAS_BUFFER_FNS(Uninit, uninit)

2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307
/*
 * Add new method to test wether block and inode bitmaps are properly
 * 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);
}

2308 2309
#define in_range(b, first, len)	((b) >= (first) && (b) <= (first) + (len) - 1)

2310 2311 2312 2313 2314 2315 2316 2317 2318
/* 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])
#define ext4_aio_mutex(v)  (&ext4__aio_mutex[((unsigned long)(v)) %\
					     EXT4_WQ_HASH_SZ])
extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
extern struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ];

2319 2320 2321 2322
#define EXT4_RESIZING	0
extern int ext4_resize_begin(struct super_block *sb);
extern void ext4_resize_end(struct super_block *sb);

2323 2324
#endif	/* __KERNEL__ */

2325
#endif	/* _EXT4_H */