ext4.h 63.3 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
/*
S
Shen Feng 已提交
34
 * The fourth extended filesystem constants/structures
35 36 37
 */

/*
38
 * Define EXT4FS_DEBUG to produce debug messages
39
 */
40
#undef EXT4FS_DEBUG
41 42 43 44

/*
 * Debug code
 */
45 46
#ifdef EXT4FS_DEBUG
#define ext4_debug(f, a...)						\
47
	do {								\
48
		printk(KERN_DEBUG "EXT4-fs DEBUG (%s, %d): %s:",	\
49
			__FILE__, __LINE__, __func__);			\
50
		printk(KERN_DEBUG f, ## a);				\
51 52
	} while (0)
#else
53
#define ext4_debug(f, a...)	do {} while (0)
54 55
#endif

56 57 58 59 60 61
#define EXT4_ERROR_INODE(inode, fmt, a...) \
	ext4_error_inode(__func__, (inode), (fmt), ## a);

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

62 63 64 65 66 67 68 69 70 71 72 73
/* 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;

74 75 76 77 78 79
/*
 * Flags used in mballoc's allocation_context flags field.  
 *
 * Also used to show what's going on for debugging purposes when the
 * flag field is exported via the traceport interface
 */
80

81
/* prefer goal again. length */
82
#define EXT4_MB_HINT_MERGE		0x0001
83
/* blocks already reserved */
84
#define EXT4_MB_HINT_RESERVED		0x0002
85
/* metadata is being allocated */
86
#define EXT4_MB_HINT_METADATA		0x0004
87
/* first blocks in the file */
88
#define EXT4_MB_HINT_FIRST		0x0008
89
/* search for the best chunk */
90
#define EXT4_MB_HINT_BEST		0x0010
91
/* data is being allocated */
92
#define EXT4_MB_HINT_DATA		0x0020
93
/* don't preallocate (for tails) */
94
#define EXT4_MB_HINT_NOPREALLOC		0x0040
95
/* allocate for locality group */
96
#define EXT4_MB_HINT_GROUP_ALLOC	0x0080
97
/* allocate goal blocks or none */
98
#define EXT4_MB_HINT_GOAL_ONLY		0x0100
99
/* goal is meaningful */
100
#define EXT4_MB_HINT_TRY_GOAL		0x0200
101
/* blocks already pre-reserved by delayed allocation */
102
#define EXT4_MB_DELALLOC_RESERVED	0x0400
103 104
/* We are doing stream allocation */
#define EXT4_MB_STREAM_ALLOC		0x0800
105

106 107 108 109

struct ext4_allocation_request {
	/* target inode for block we're allocating */
	struct inode *inode;
110 111
	/* how many blocks we want to allocate */
	unsigned int len;
112 113 114 115 116 117
	/* 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;
118 119 120 121 122
	/* 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 */
123 124
	ext4_fsblk_t pright;
	/* flags. see above EXT4_MB_HINT_* */
125
	unsigned int flags;
126 127
};

128 129 130 131 132 133 134 135 136 137 138 139 140 141
/*
 * 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;
};
142
#define	EXT4_IO_UNWRITTEN	0x1
143
typedef struct ext4_io_end {
144
	struct list_head	list;		/* per-file finished AIO list */
145
	struct inode		*inode;		/* file being written to */
146
	unsigned int		flag;		/* unwritten or not */
147
	struct page		*page;		/* page struct for buffer write */
148 149
	loff_t			offset;		/* offset in the file */
	ssize_t			size;		/* size of the extent */
150 151 152
	struct work_struct	work;		/* data work queue */
} ext4_io_end_t;

153 154 155
/*
 * Special inodes numbers
 */
156 157 158 159 160 161
#define	EXT4_BAD_INO		 1	/* Bad blocks inode */
#define EXT4_ROOT_INO		 2	/* Root inode */
#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 */
162

163 164
/* First non-reserved inode for old ext4 filesystems */
#define EXT4_GOOD_OLD_FIRST_INO	11
165 166 167 168

/*
 * Maximal count of links to a file
 */
169
#define EXT4_LINK_MAX		65000
170 171 172 173

/*
 * Macro-instructions used to manage several block sizes
 */
174
#define EXT4_MIN_BLOCK_SIZE		1024
175 176
#define	EXT4_MAX_BLOCK_SIZE		65536
#define EXT4_MIN_BLOCK_LOG_SIZE		10
177
#ifdef __KERNEL__
178
# define EXT4_BLOCK_SIZE(s)		((s)->s_blocksize)
179
#else
180
# define EXT4_BLOCK_SIZE(s)		(EXT4_MIN_BLOCK_SIZE << (s)->s_log_block_size)
181
#endif
182
#define	EXT4_ADDR_PER_BLOCK(s)		(EXT4_BLOCK_SIZE(s) / sizeof(__u32))
183
#ifdef __KERNEL__
184
# define EXT4_BLOCK_SIZE_BITS(s)	((s)->s_blocksize_bits)
185
#else
186
# define EXT4_BLOCK_SIZE_BITS(s)	((s)->s_log_block_size + 10)
187 188
#endif
#ifdef __KERNEL__
189 190 191
#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)
192
#else
193 194
#define EXT4_INODE_SIZE(s)	(((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \
				 EXT4_GOOD_OLD_INODE_SIZE : \
195
				 (s)->s_inode_size)
196 197
#define EXT4_FIRST_INO(s)	(((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \
				 EXT4_GOOD_OLD_FIRST_INO : \
198 199
				 (s)->s_first_ino)
#endif
A
Amit Arora 已提交
200
#define EXT4_BLOCK_ALIGN(size, blkbits)		ALIGN((size), (1 << (blkbits)))
201 202 203 204

/*
 * Structure of a blocks group descriptor
 */
205
struct ext4_group_desc
206
{
207
	__le32	bg_block_bitmap_lo;	/* Blocks bitmap block */
208 209
	__le32	bg_inode_bitmap_lo;	/* Inodes bitmap block */
	__le32	bg_inode_table_lo;	/* Inodes table block */
210 211 212
	__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
213 214
	__le16	bg_flags;		/* EXT4_BG_flags (INODE_UNINIT, etc) */
	__u32	bg_reserved[2];		/* Likely block/inode bitmap checksum */
215
	__le16  bg_itable_unused_lo;	/* Unused inodes count */
A
Andreas Dilger 已提交
216
	__le16  bg_checksum;		/* crc16(sb_uuid+group+desc) */
217 218 219
	__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 */
220 221 222
	__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 */
223
	__le16  bg_itable_unused_hi;    /* Unused inodes count MSB */
224
	__u32	bg_reserved2[3];
225 226
};

227 228 229 230 231
/*
 * Structure of a flex block group info
 */

struct flex_groups {
232 233
	atomic_t free_inodes;
	atomic_t free_blocks;
234
	atomic_t used_dirs;
235 236
};

A
Andreas Dilger 已提交
237 238 239 240
#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 */

241 242 243
/*
 * Macro-instructions used to manage group descriptors
 */
244
#define EXT4_MIN_DESC_SIZE		32
245
#define EXT4_MIN_DESC_SIZE_64BIT	64
246 247
#define	EXT4_MAX_DESC_SIZE		EXT4_MIN_BLOCK_SIZE
#define EXT4_DESC_SIZE(s)		(EXT4_SB(s)->s_desc_size)
248
#ifdef __KERNEL__
249 250 251 252
# define EXT4_BLOCKS_PER_GROUP(s)	(EXT4_SB(s)->s_blocks_per_group)
# 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)
253
#else
254
# define EXT4_BLOCKS_PER_GROUP(s)	((s)->s_blocks_per_group)
255
# define EXT4_DESC_PER_BLOCK(s)		(EXT4_BLOCK_SIZE(s) / EXT4_DESC_SIZE(s))
256
# define EXT4_INODES_PER_GROUP(s)	((s)->s_inodes_per_group)
257 258 259 260 261
#endif

/*
 * Constants relative to the data blocks
 */
262 263 264 265 266
#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)
267 268 269 270

/*
 * Inode flags
 */
271 272 273 274 275 276 277 278
#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 */
279
/* Reserved for compression usage... */
280 281 282 283
#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 */
284
/* End compression flags --- maybe not all used */
285 286 287 288 289 290
#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
291
#define EXT4_HUGE_FILE_FL               0x00040000 /* Set to each huge file */
A
Alex Tomas 已提交
292
#define EXT4_EXTENTS_FL			0x00080000 /* Inode uses extents */
293
#define EXT4_EA_INODE_FL	        0x00200000 /* Inode used for large EA */
294
#define EXT4_EOFBLOCKS_FL		0x00400000 /* Blocks allocated beyond EOF */
A
Aneesh Kumar K.V 已提交
295
#define EXT4_RESERVED_FL		0x80000000 /* reserved for ext4 lib */
296

297 298
#define EXT4_FL_USER_VISIBLE		0x004BDFFF /* User visible flags */
#define EXT4_FL_USER_MODIFIABLE		0x004B80FF /* User modifiable flags */
299

300 301 302 303 304 305 306
/* Flags that should be inherited by new inodes from their parent. */
#define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\
			   EXT4_SYNC_FL | EXT4_IMMUTABLE_FL | EXT4_APPEND_FL |\
			   EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
			   EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\
			   EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL)

307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323
/* 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;
}

324
/* Used to pass group descriptor data when online resize is done */
325
struct ext4_new_group_input {
D
Dave Kleikamp 已提交
326 327 328 329 330 331
	__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 */
332 333 334
	__u16 unused;
};

335 336
/* The struct ext4_new_group_input in kernel space, with free_blocks_count */
struct ext4_new_group_data {
337
	__u32 group;
L
Laurent Vivier 已提交
338 339 340
	__u64 block_bitmap;
	__u64 inode_bitmap;
	__u64 inode_table;
341 342 343 344 345 346
	__u32 blocks_count;
	__u16 reserved_blocks;
	__u16 unused;
	__u32 free_blocks_count;
};

A
Amit Arora 已提交
347
/*
348
 * Flags used by ext4_get_blocks()
A
Amit Arora 已提交
349
 */
350 351
	/* Allocate any needed blocks and/or convert an unitialized
	   extent to be an initialized ext4 */
352
#define EXT4_GET_BLOCKS_CREATE			0x0001
353
	/* Request the creation of an unitialized extent */
354
#define EXT4_GET_BLOCKS_UNINIT_EXT		0x0002
355 356 357
#define EXT4_GET_BLOCKS_CREATE_UNINIT_EXT	(EXT4_GET_BLOCKS_UNINIT_EXT|\
						 EXT4_GET_BLOCKS_CREATE)
	/* Caller is from the delayed allocation writeout path,
358 359
	   so set the magic i_delalloc_reserve_flag after taking the 
	   inode allocation semaphore for */
360
#define EXT4_GET_BLOCKS_DELALLOC_RESERVE	0x0004
361 362 363
	/* 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*/
364
#define EXT4_GET_BLOCKS_PRE_IO			0x0008
365
#define EXT4_GET_BLOCKS_CONVERT			0x0010
366
#define EXT4_GET_BLOCKS_IO_CREATE_EXT		(EXT4_GET_BLOCKS_PRE_IO|\
367
					 EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
368 369
	/* Convert extent to initialized after IO complete */
#define EXT4_GET_BLOCKS_IO_CONVERT_EXT		(EXT4_GET_BLOCKS_CONVERT|\
370
					 EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
371

372 373 374 375 376
/*
 * Flags used by ext4_free_blocks
 */
#define EXT4_FREE_BLOCKS_METADATA	0x0001
#define EXT4_FREE_BLOCKS_FORGET		0x0002
377
#define EXT4_FREE_BLOCKS_VALIDATED	0x0004
378

379 380 381
/*
 * ioctl commands
 */
382 383 384 385 386 387
#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
388
#ifdef CONFIG_JBD2_DEBUG
389
#define EXT4_IOC_WAIT_FOR_READONLY	_IOR('f', 99, long)
390
#endif
391 392
#define EXT4_IOC_GETRSVSZ		_IOR('f', 5, long)
#define EXT4_IOC_SETRSVSZ		_IOW('f', 6, long)
T
Theodore Ts'o 已提交
393 394 395
#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)
396
 /* note ioctl 10 reserved for an early version of the FIEMAP ioctl */
T
Theodore Ts'o 已提交
397
 /* note ioctl 11 reserved for filesystem-independent FIEMAP ioctl */
398
#define EXT4_IOC_ALLOC_DA_BLKS		_IO('f', 12)
399
#define EXT4_IOC_MOVE_EXT		_IOWR('f', 15, struct move_extent)
400 401 402 403

/*
 * ioctl commands in 32 bit emulation
 */
404 405 406 407 408 409 410
#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)
411
#ifdef CONFIG_JBD2_DEBUG
412
#define EXT4_IOC32_WAIT_FOR_READONLY	_IOR('f', 99, int)
413
#endif
414 415
#define EXT4_IOC32_GETVERSION_OLD	FS_IOC32_GETVERSION
#define EXT4_IOC32_SETVERSION_OLD	FS_IOC32_SETVERSION
416 417 418 419 420


/*
 *  Mount options
 */
421
struct ext4_mount_options {
422 423 424 425
	unsigned long s_mount_opt;
	uid_t s_resuid;
	gid_t s_resgid;
	unsigned long s_commit_interval;
426
	u32 s_min_batch_time, s_max_batch_time;
427 428 429 430 431 432
#ifdef CONFIG_QUOTA
	int s_jquota_fmt;
	char *s_qf_names[MAXQUOTAS];
#endif
};

433 434 435
/* Max physical block we can addres w/o extents */
#define EXT4_MAX_BLOCK_FILE_PHYS	0xFFFFFFFF

436 437 438
/*
 * Structure of an inode on the disk
 */
439
struct ext4_inode {
440 441
	__le16	i_mode;		/* File mode */
	__le16	i_uid;		/* Low 16 bits of Owner Uid */
442
	__le32	i_size_lo;	/* Size in bytes */
443
	__le32	i_atime;	/* Access time */
K
Kalpak Shah 已提交
444
	__le32	i_ctime;	/* Inode Change time */
445 446 447 448
	__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 */
449
	__le32	i_blocks_lo;	/* Blocks count */
450 451 452
	__le32	i_flags;	/* File flags */
	union {
		struct {
453
			__le32  l_i_version;
454 455 456 457 458 459 460 461
		} linux1;
		struct {
			__u32  h_i_translator;
		} hurd1;
		struct {
			__u32  m_i_reserved1;
		} masix1;
	} osd1;				/* OS dependent 1 */
462
	__le32	i_block[EXT4_N_BLOCKS];/* Pointers to blocks */
463
	__le32	i_generation;	/* File version (for NFS) */
464
	__le32	i_file_acl_lo;	/* File ACL */
465
	__le32	i_size_high;
466
	__le32	i_obso_faddr;	/* Obsoleted fragment address */
467 468
	union {
		struct {
469
			__le16	l_i_blocks_high; /* were l_i_reserved1 */
B
Badari Pulavarty 已提交
470
			__le16	l_i_file_acl_high;
D
Dave Kleikamp 已提交
471
			__le16	l_i_uid_high;	/* these 2 fields */
472 473 474 475
			__le16	l_i_gid_high;	/* were reserved2[0] */
			__u32	l_i_reserved2;
		} linux2;
		struct {
476
			__le16	h_i_reserved1;	/* Obsoleted fragment number/size which are removed in ext4 */
477 478 479 480 481 482
			__u16	h_i_mode_high;
			__u16	h_i_uid_high;
			__u16	h_i_gid_high;
			__u32	h_i_author;
		} hurd2;
		struct {
483
			__le16	h_i_reserved1;	/* Obsoleted fragment number/size which are removed in ext4 */
B
Badari Pulavarty 已提交
484
			__le16	m_i_file_acl_high;
485 486 487 488 489
			__u32	m_i_reserved2[2];
		} masix2;
	} osd2;				/* OS dependent 2 */
	__le16	i_extra_isize;
	__le16	i_pad1;
K
Kalpak Shah 已提交
490 491 492 493 494
	__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) */
495
	__le32  i_version_hi;	/* high 32 bits for 64-bit version */
496 497
};

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

K
Kalpak Shah 已提交
507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529
#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 ?
530 531
			   (time->tv_sec >> 32) & EXT4_EPOCH_MASK : 0) |
                          ((time->tv_nsec << EXT4_EPOCH_BITS) & EXT4_NSEC_MASK));
K
Kalpak Shah 已提交
532 533 534 535 536 537 538
}

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;
539
       time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS;
K
Kalpak Shah 已提交
540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576
}

#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);	       \
} 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);	       \
} while (0)

577 578
#define i_disk_version osd1.linux1.l_i_version

579 580
#if defined(__KERNEL__) || defined(__linux__)
#define i_reserved1	osd1.linux1.l_i_reserved1
B
Badari Pulavarty 已提交
581
#define i_file_acl_high	osd2.linux2.l_i_file_acl_high
582
#define i_blocks_high	osd2.linux2.l_i_blocks_high
583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598
#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
599
#define i_file_acl_high	osd2.masix2.m_i_file_acl_high
600 601 602 603
#define i_reserved2	osd2.masix2.m_i_reserved2

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

604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630
/*
 * storage for cached extent
 */
struct ext4_ext_cache {
	ext4_fsblk_t	ec_start;
	ext4_lblk_t	ec_block;
	__u32		ec_len; /* must be 32bit to return holes */
	__u32		ec_type;
};

/*
 * fourth extended file system inode data in memory
 */
struct ext4_inode_info {
	__le32	i_data[15];	/* unconverted */
	__u32	i_flags;
	ext4_fsblk_t	i_file_acl;
	__u32	i_dtime;

	/*
	 * 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;
631
	unsigned long	i_state_flags;		/* Dynamic state flags */
632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696

	ext4_lblk_t		i_dir_start_lookup;
#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;
	struct jbd2_inode jinode;

	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;
	unsigned short i_delalloc_reserved_flag;
697 698
	sector_t i_da_metadata_calc_last_lblock;
	int i_da_metadata_calc_len;
699 700 701 702 703

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

	spinlock_t i_block_reservation_lock;
704 705 706 707
#ifdef CONFIG_QUOTA
	/* quota space reservation, managed internally by quota code */
	qsize_t i_reserved_quota;
#endif
708

709 710
	/* completed IOs that might need unwritten extents handling */
	struct list_head i_completed_io_list;
711
	spinlock_t i_completed_io_lock;
712 713
	/* current io_end structure for async DIO write*/
	ext4_io_end_t *cur_aio_dio;
714 715 716 717 718 719 720

	/*
	 * Transactions that contain inode's metadata needed to complete
	 * fsync and fdatasync, respectively.
	 */
	tid_t i_sync_tid;
	tid_t i_datasync_tid;
721 722
};

723 724 725
/*
 * File system states
 */
726 727 728
#define	EXT4_VALID_FS			0x0001	/* Unmounted cleanly */
#define	EXT4_ERROR_FS			0x0002	/* Errors detected */
#define	EXT4_ORPHAN_FS			0x0004	/* Orphans being recovered */
729

730 731 732 733 734 735 736
/*
 * 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 */

737 738 739
/*
 * Mount flags
 */
740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755
#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 */
756
#define EXT4_MOUNT_NO_AUTO_DA_ALLOC	0x10000	/* No auto delalloc mapping */
757 758 759 760 761
#define EXT4_MOUNT_BARRIER		0x20000 /* Use block barriers */
#define EXT4_MOUNT_NOBH			0x40000 /* No bufferheads */
#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 */
762
#define EXT4_MOUNT_DIOREAD_NOLOCK	0x400000 /* Enable support for dio read nolocking */
763
#define EXT4_MOUNT_JOURNAL_CHECKSUM	0x800000 /* Journal checksums */
764
#define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT	0x1000000 /* Journal Async Commit */
765
#define EXT4_MOUNT_I_VERSION            0x2000000 /* i_version support */
766
#define EXT4_MOUNT_DELALLOC		0x8000000 /* Delalloc support */
767
#define EXT4_MOUNT_DATA_ERR_ABORT	0x10000000 /* Abort on file data write */
768
#define EXT4_MOUNT_BLOCK_VALIDITY	0x20000000 /* Block validity checking */
769
#define EXT4_MOUNT_DISCARD		0x40000000 /* Issue DISCARD requests */
770

771 772 773 774
#define clear_opt(o, opt)		o &= ~EXT4_MOUNT_##opt
#define set_opt(o, opt)			o |= EXT4_MOUNT_##opt
#define test_opt(sb, opt)		(EXT4_SB(sb)->s_mount_opt & \
					 EXT4_MOUNT_##opt)
775

776 777 778 779 780 781 782
#define ext4_set_bit			ext2_set_bit
#define ext4_set_bit_atomic		ext2_set_bit_atomic
#define ext4_clear_bit			ext2_clear_bit
#define ext4_clear_bit_atomic		ext2_clear_bit_atomic
#define ext4_test_bit			ext2_test_bit
#define ext4_find_first_zero_bit	ext2_find_first_zero_bit
#define ext4_find_next_zero_bit		ext2_find_next_zero_bit
783
#define ext4_find_next_bit		ext2_find_next_bit
784 785 786 787

/*
 * Maximal mount counts between two filesystem checks
 */
788 789
#define EXT4_DFL_MAX_MNT_COUNT		20	/* Allow 20 mounts */
#define EXT4_DFL_CHECKINTERVAL		0	/* Don't use interval check */
790 791 792 793

/*
 * Behaviour when detecting errors
 */
794 795 796 797
#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
798 799 800 801

/*
 * Structure of the super block
 */
802
struct ext4_super_block {
803
/*00*/	__le32	s_inodes_count;		/* Inodes count */
804
	__le32	s_blocks_count_lo;	/* Blocks count */
805 806
	__le32	s_r_blocks_count_lo;	/* Reserved blocks count */
	__le32	s_free_blocks_count_lo;	/* Free blocks count */
807 808 809
/*10*/	__le32	s_free_inodes_count;	/* Free inodes count */
	__le32	s_first_data_block;	/* First Data Block */
	__le32	s_log_block_size;	/* Block size */
810
	__le32	s_obso_log_frag_size;	/* Obsoleted fragment size */
811
/*20*/	__le32	s_blocks_per_group;	/* # Blocks per group */
812
	__le32	s_obso_frags_per_group;	/* Obsoleted fragments per group */
813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828
	__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 */
	/*
829
	 * These fields are for EXT4_DYNAMIC_REV superblocks only.
830 831 832 833 834 835 836 837 838 839 840 841
	 *
	 * 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 */
842
	__le16  s_inode_size;		/* size of inode structure */
843 844 845 846 847 848 849 850 851 852
	__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
853
	 * happen if the EXT4_FEATURE_COMPAT_DIR_PREALLOC flag is on.
854 855 856 857 858
	 */
	__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 */
	/*
859
	 * Journaling support valid if EXT4_FEATURE_COMPAT_HAS_JOURNAL set.
860 861 862 863 864 865 866 867
	 */
/*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 */
	__u8	s_reserved_char_pad;
868
	__le16  s_desc_size;		/* size of group descriptor */
L
Laurent Vivier 已提交
869
/*100*/	__le32	s_default_mount_opts;
870
	__le32	s_first_meta_bg;	/* First metablock block group */
L
Laurent Vivier 已提交
871 872 873 874 875 876
	__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
877 878 879 880 881 882 883
	__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 */
	__le16  s_mmp_interval;         /* # seconds to wait in MMP checking */
	__le64  s_mmp_block;            /* Block for multi-mount protection */
	__le32  s_raid_stripe_width;    /* blocks on all data disks (N*stride)*/
884 885 886
	__u8	s_log_groups_per_flex;  /* FLEX_BG group size */
	__u8	s_reserved_char_pad2;
	__le16  s_reserved_pad;
T
Theodore Ts'o 已提交
887 888
	__le64	s_kbytes_written;	/* nr of lifetime kilobytes written */
	__u32   s_reserved[160];        /* Padding to the end of the block */
889 890 891
};

#ifdef __KERNEL__
892 893

/*
894
 * run-time mount flags
895 896
 */
#define EXT4_MF_MNTDIR_SAMPLED	0x0001
897
#define EXT4_MF_FS_ABORTED	0x0002	/* Fatal error detected */
898

899 900 901 902 903 904 905 906 907 908 909 910
/*
 * 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 */
	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 */
911
	ext4_group_t s_blockfile_groups;/* Groups acceptable for non-extent files */
912 913 914 915 916 917
	unsigned long s_overhead_last;  /* Last calculated overhead */
	unsigned long s_blocks_last;    /* Last seen block count */
	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;
918
	unsigned int s_mount_opt;
919
	unsigned int s_mount_flags;
920 921 922 923 924 925 926 927 928 929
	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;
930
	unsigned int s_inode_goal;
931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963
	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 inode *s_journal_inode;
	struct journal_s *s_journal;
	struct list_head s_orphan;
	struct mutex s_orphan_lock;
	struct mutex s_resize_lock;
	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 */
964
	struct rb_root system_blks;
965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993

#ifdef EXTENTS_STATS
	/* ext4 extents stats */
	unsigned long s_ext_min;
	unsigned long s_ext_max;
	unsigned long s_depth_max;
	spinlock_t s_ext_stats_lock;
	unsigned long s_ext_blocks;
	unsigned long s_ext_extents;
#endif

	/* for buddy allocator */
	struct ext4_group_info ***s_group_info;
	struct inode *s_buddy_cache;
	long s_blocks_reserved;
	spinlock_t s_reserve_lock;
	spinlock_t s_md_lock;
	tid_t s_last_transaction;
	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;
994
	unsigned int s_max_writeback_mb_bump;
995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013
	/* where last allocation was done - for stream allocation */
	unsigned long s_mb_last_group;
	unsigned long s_mb_last_start;

	/* stats for buddy allocator */
	spinlock_t s_mb_pa_lock;
	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;
1014
	atomic_t s_lock_busy;
1015 1016

	/* locality groups */
1017
	struct ext4_locality_group __percpu *s_locality_groups;
1018 1019 1020 1021 1022 1023 1024

	/* 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;
1025 1026 1027

	/* workqueue for dio unwritten */
	struct workqueue_struct *dio_unwritten_wq;
1028 1029
};

1030
static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
1031 1032 1033
{
	return sb->s_fs_info;
}
1034
static inline struct ext4_inode_info *EXT4_I(struct inode *inode)
1035
{
1036
	return container_of(inode, struct ext4_inode_info, vfs_inode);
1037 1038
}

K
Kalpak Shah 已提交
1039 1040 1041 1042 1043 1044
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;
}

1045
static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
1046
{
1047 1048 1049 1050 1051
	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));
1052
}
1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080

/*
 * 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*/
};

static inline int ext4_test_inode_state(struct inode *inode, int bit)
{
	return test_bit(bit, &EXT4_I(inode)->i_state_flags);
}

static inline void ext4_set_inode_state(struct inode *inode, int bit)
{
	set_bit(bit, &EXT4_I(inode)->i_state_flags);
}

static inline void ext4_clear_inode_state(struct inode *inode, int bit)
{
	clear_bit(bit, &EXT4_I(inode)->i_state_flags);
}
1081
#else
1082
/* Assume that user mode programs are passing in an ext4fs superblock, not
1083 1084
 * a kernel struct super_block.  This will allow us to call the feature-test
 * macros from user land. */
1085
#define EXT4_SB(sb)	(sb)
1086 1087
#endif

1088
#define NEXT_ORPHAN(inode) EXT4_I(inode)->i_dtime
1089 1090 1091 1092

/*
 * Codes for operating systems
 */
1093 1094 1095 1096 1097
#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
1098 1099 1100 1101

/*
 * Revision levels
 */
1102 1103
#define EXT4_GOOD_OLD_REV	0	/* The good old (original) format */
#define EXT4_DYNAMIC_REV	1	/* V2 format w/ dynamic inode sizes */
1104

1105 1106
#define EXT4_CURRENT_REV	EXT4_GOOD_OLD_REV
#define EXT4_MAX_SUPP_REV	EXT4_DYNAMIC_REV
1107

1108
#define EXT4_GOOD_OLD_INODE_SIZE 128
1109 1110 1111 1112 1113

/*
 * Feature set definitions
 */

1114
#define EXT4_HAS_COMPAT_FEATURE(sb,mask)			\
A
Aneesh Kumar K.V 已提交
1115
	((EXT4_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask)) != 0)
1116
#define EXT4_HAS_RO_COMPAT_FEATURE(sb,mask)			\
A
Aneesh Kumar K.V 已提交
1117
	((EXT4_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask)) != 0)
1118
#define EXT4_HAS_INCOMPAT_FEATURE(sb,mask)			\
A
Aneesh Kumar K.V 已提交
1119
	((EXT4_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask)) != 0)
1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142
#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
1143
#define EXT4_FEATURE_RO_COMPAT_HUGE_FILE        0x0008
A
Andreas Dilger 已提交
1144
#define EXT4_FEATURE_RO_COMPAT_GDT_CSUM		0x0010
1145
#define EXT4_FEATURE_RO_COMPAT_DIR_NLINK	0x0020
K
Kalpak Shah 已提交
1146
#define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE	0x0040
1147 1148 1149 1150 1151 1152

#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
1153
#define EXT4_FEATURE_INCOMPAT_EXTENTS		0x0040 /* extents support */
L
Laurent Vivier 已提交
1154
#define EXT4_FEATURE_INCOMPAT_64BIT		0x0080
1155
#define EXT4_FEATURE_INCOMPAT_MMP               0x0100
J
Jose R. Santos 已提交
1156
#define EXT4_FEATURE_INCOMPAT_FLEX_BG		0x0200
1157 1158
#define EXT4_FEATURE_INCOMPAT_EA_INODE		0x0400 /* EA in inode */
#define EXT4_FEATURE_INCOMPAT_DIRDATA		0x1000 /* data in dirent */
1159 1160 1161 1162

#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
1163
					 EXT4_FEATURE_INCOMPAT_META_BG| \
L
Laurent Vivier 已提交
1164
					 EXT4_FEATURE_INCOMPAT_EXTENTS| \
J
Jose R. Santos 已提交
1165 1166
					 EXT4_FEATURE_INCOMPAT_64BIT| \
					 EXT4_FEATURE_INCOMPAT_FLEX_BG)
1167 1168
#define EXT4_FEATURE_RO_COMPAT_SUPP	(EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
					 EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \
A
Andreas Dilger 已提交
1169
					 EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \
1170
					 EXT4_FEATURE_RO_COMPAT_DIR_NLINK | \
K
Kalpak Shah 已提交
1171
					 EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \
1172 1173
					 EXT4_FEATURE_RO_COMPAT_BTREE_DIR |\
					 EXT4_FEATURE_RO_COMPAT_HUGE_FILE)
1174 1175 1176 1177

/*
 * Default values for user and/or group using reserved blocks
 */
1178 1179
#define	EXT4_DEF_RESUID		0
#define	EXT4_DEF_RESGID		0
1180

1181 1182
#define EXT4_DEF_INODE_READAHEAD_BLKS	32

1183 1184 1185
/*
 * Default mount options
 */
1186 1187 1188 1189 1190 1191 1192 1193 1194
#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
1195

1196 1197 1198 1199 1200 1201
/*
 * Default journal batch times
 */
#define EXT4_DEF_MIN_BATCH_TIME	0
#define EXT4_DEF_MAX_BATCH_TIME	15000 /* 15ms */

1202 1203 1204 1205 1206 1207
/*
 * 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

1208 1209 1210
/*
 * Structure of a directory entry
 */
1211
#define EXT4_NAME_LEN 255
1212

1213
struct ext4_dir_entry {
1214 1215 1216
	__le32	inode;			/* Inode number */
	__le16	rec_len;		/* Directory entry length */
	__le16	name_len;		/* Name length */
1217
	char	name[EXT4_NAME_LEN];	/* File name */
1218 1219 1220
};

/*
1221
 * The new version of the directory entry.  Since EXT4 structures are
1222 1223 1224 1225
 * 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.
 */
1226
struct ext4_dir_entry_2 {
1227 1228 1229 1230
	__le32	inode;			/* Inode number */
	__le16	rec_len;		/* Directory entry length */
	__u8	name_len;		/* Name length */
	__u8	file_type;
1231
	char	name[EXT4_NAME_LEN];	/* File name */
1232 1233 1234
};

/*
1235
 * Ext4 directory file types.  Only the low 3 bits are used.  The
1236 1237
 * other bits are reserved for now.
 */
1238 1239 1240 1241 1242 1243 1244 1245
#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
1246

1247
#define EXT4_FT_MAX		8
1248 1249

/*
1250
 * EXT4_DIR_PAD defines the directory entries boundaries
1251 1252 1253
 *
 * NOTE: It must be a multiple of 4
 */
1254 1255 1256 1257
#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)
1258 1259
#define EXT4_MAX_REC_LEN		((1<<16)-1)

1260 1261 1262 1263 1264
/*
 * Hash Tree Directory indexing
 * (c) Daniel Phillips, 2001
 */

1265 1266
#define is_dx(dir) (EXT4_HAS_COMPAT_FEATURE(dir->i_sb, \
				      EXT4_FEATURE_COMPAT_DIR_INDEX) && \
1267 1268 1269
		      (EXT4_I(dir)->i_flags & EXT4_INDEX_FL))
#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)
1270 1271 1272 1273 1274 1275

/* 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
1276 1277 1278
#define DX_HASH_LEGACY_UNSIGNED	3
#define DX_HASH_HALF_MD4_UNSIGNED	4
#define DX_HASH_TEA_UNSIGNED		5
1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290

#ifdef __KERNEL__

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

1291
#define EXT4_HTREE_EOF	0x7fffffff
1292 1293

/*
1294
 * Control parameters used by ext4_htree_next_block
1295 1296 1297 1298 1299 1300 1301
 */
#define HASH_NB_ALWAYS		1


/*
 * Describe an inode's exact location on disk and in memory
 */
1302
struct ext4_iloc
1303 1304 1305
{
	struct buffer_head *bh;
	unsigned long offset;
1306
	ext4_group_t block_group;
1307 1308
};

1309
static inline struct ext4_inode *ext4_raw_inode(struct ext4_iloc *iloc)
1310
{
1311
	return (struct ext4_inode *) (iloc->bh->b_data + iloc->offset);
1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329
}

/*
 * 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 */
1330
static inline ext4_fsblk_t
1331
ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no)
1332
{
1333 1334
	return group_no * (ext4_fsblk_t)EXT4_BLOCKS_PER_GROUP(sb) +
		le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
1335 1336 1337 1338 1339 1340 1341
}

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

1342
void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
1343
			ext4_group_t *blockgrpp, ext4_grpblk_t *offsetp);
1344

1345 1346
extern struct proc_dir_entry *ext4_proc_root;

1347 1348 1349 1350 1351 1352
/*
 * Function prototypes
 */

/*
 * Ok, these declarations are also in <linux/kernel.h> but none of the
1353
 * ext4 source programs needs to include it so they are duplicated here.
1354
 */
D
Dave Kleikamp 已提交
1355 1356 1357
# define NORET_TYPE	/**/
# define ATTRIB_NORET	__attribute__((noreturn))
# define NORET_AND	noreturn,
1358

1359 1360 1361
/* bitmap.c */
extern unsigned int ext4_count_free(struct buffer_head *, unsigned);

1362
/* balloc.c */
1363 1364 1365 1366
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);
1367 1368 1369
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);
1370
extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
1371
			ext4_fsblk_t goal, unsigned long *count, int *errp);
A
Aneesh Kumar K.V 已提交
1372
extern int ext4_claim_free_blocks(struct ext4_sb_info *sbi, s64 nblocks);
1373
extern int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks);
1374 1375
extern void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
				ext4_fsblk_t block, unsigned long count);
1376 1377
extern ext4_fsblk_t ext4_count_free_blocks(struct super_block *);
extern void ext4_check_blocks_bitmap(struct super_block *);
1378
extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
1379
						    ext4_group_t block_group,
1380
						    struct buffer_head ** bh);
1381
extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
1382 1383 1384 1385 1386 1387 1388 1389
struct buffer_head *ext4_read_block_bitmap(struct super_block *sb,
				      ext4_group_t block_group);
extern unsigned ext4_init_block_bitmap(struct super_block *sb,
				       struct buffer_head *bh,
				       ext4_group_t group,
				       struct ext4_group_desc *desc);
#define ext4_free_blocks_after_init(sb, group, desc)			\
		ext4_init_block_bitmap(sb, NULL, group, desc)
1390 1391

/* dir.c */
1392 1393
extern int ext4_check_dir_entry(const char *, struct inode *,
				struct ext4_dir_entry_2 *,
1394
				struct buffer_head *, unsigned int);
1395
extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
1396
				    __u32 minor_hash,
1397 1398
				    struct ext4_dir_entry_2 *dirent);
extern void ext4_htree_free_dir_info(struct dir_private_info *p);
1399 1400

/* fsync.c */
1401
extern int ext4_sync_file(struct file *, struct dentry *, int);
1402 1403

/* hash.c */
1404
extern int ext4fs_dirhash(const char *name, int len, struct
1405 1406 1407
			  dx_hash_info *hinfo);

/* ialloc.c */
1408
extern struct inode *ext4_new_inode(handle_t *, struct inode *, int,
1409
				    const struct qstr *qstr, __u32 goal);
1410 1411 1412 1413 1414
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 *);
1415 1416 1417 1418 1419
extern unsigned ext4_init_inode_bitmap(struct super_block *sb,
				       struct buffer_head *bh,
				       ext4_group_t group,
				       struct ext4_group_desc *desc);
extern void mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
1420

1421 1422 1423 1424 1425 1426 1427 1428
/* 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);
1429
extern void ext4_discard_preallocations(struct inode *);
1430 1431
extern int __init init_ext4_mballoc(void);
extern void exit_ext4_mballoc(void);
1432
extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
1433 1434
			     struct buffer_head *bh, ext4_fsblk_t block,
			     unsigned long count, int flags);
1435
extern int ext4_mb_add_groupinfo(struct super_block *sb,
1436
		ext4_group_t i, struct ext4_group_desc *desc);
1437 1438 1439
extern int ext4_mb_get_buddy_cache_lock(struct super_block *, ext4_group_t);
extern void ext4_mb_put_buddy_cache_lock(struct super_block *,
						ext4_group_t, int);
1440
/* inode.c */
A
Aneesh Kumar K.V 已提交
1441 1442 1443 1444
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 *);
1445 1446
int ext4_get_block(struct inode *inode, sector_t iblock,
				struct buffer_head *bh_result, int create);
1447

1448
extern struct inode *ext4_iget(struct super_block *, unsigned long);
1449
extern int  ext4_write_inode(struct inode *, struct writeback_control *);
1450
extern int  ext4_setattr(struct dentry *, struct iattr *);
1451 1452
extern int  ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
				struct kstat *stat);
1453 1454
extern void ext4_delete_inode(struct inode *);
extern int  ext4_sync_inode(handle_t *, struct inode *);
1455 1456 1457
extern void ext4_dirty_inode(struct inode *);
extern int ext4_change_inode_journal_flag(struct inode *, int);
extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
1458
extern int ext4_can_truncate(struct inode *inode);
1459
extern void ext4_truncate(struct inode *);
1460
extern int ext4_truncate_restart_trans(handle_t *, struct inode *, int nblocks);
1461
extern void ext4_set_inode_flags(struct inode *);
1462
extern void ext4_get_inode_flags(struct ext4_inode_info *);
1463
extern int ext4_alloc_da_blocks(struct inode *inode);
1464
extern void ext4_set_aops(struct inode *inode);
A
Alex Tomas 已提交
1465
extern int ext4_writepage_trans_blocks(struct inode *);
1466
extern int ext4_meta_trans_blocks(struct inode *, int nrblocks, int idxblocks);
1467
extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
1468
extern int ext4_block_truncate_page(handle_t *handle,
A
Alex Tomas 已提交
1469
		struct address_space *mapping, loff_t from);
1470
extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
1471
extern qsize_t *ext4_get_reserved_space(struct inode *inode);
1472
extern int flush_completed_IO(struct inode *inode);
1473 1474
extern void ext4_da_update_reserve_space(struct inode *inode,
					int used, int quota_claim);
1475
/* ioctl.c */
A
Andi Kleen 已提交
1476
extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
1477
extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
1478

1479
/* migrate.c */
1480
extern int ext4_ext_migrate(struct inode *);
1481

1482
/* namei.c */
1483 1484
extern unsigned int ext4_rec_len_from_disk(__le16 dlen, unsigned blocksize);
extern __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize);
1485 1486 1487
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,
1488 1489 1490
				__u32 start_minor_hash, __u32 *next_hash);

/* resize.c */
1491 1492 1493 1494 1495
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);
1496 1497

/* super.c */
1498
extern void __ext4_error(struct super_block *, const char *, const char *, ...)
1499
	__attribute__ ((format (printf, 3, 4)));
1500
#define ext4_error(sb, message...)	__ext4_error(sb, __func__, ## message)
1501 1502 1503
extern void ext4_error_inode(const char *, struct inode *, const char *, ...)
	__attribute__ ((format (printf, 3, 4)));
extern void ext4_error_file(const char *, struct file *, const char *, ...)
1504
	__attribute__ ((format (printf, 3, 4)));
1505 1506
extern void __ext4_std_error(struct super_block *, const char *, int);
extern void ext4_abort(struct super_block *, const char *, const char *, ...)
1507
	__attribute__ ((format (printf, 3, 4)));
1508 1509
extern void __ext4_warning(struct super_block *, const char *,
			  const char *, ...)
1510
	__attribute__ ((format (printf, 3, 4)));
1511
#define ext4_warning(sb, message...)	__ext4_warning(sb, __func__, ## message)
1512 1513
extern void ext4_msg(struct super_block *, const char *, const char *, ...)
	__attribute__ ((format (printf, 3, 4)));
1514 1515 1516
extern void ext4_grp_locked_error(struct super_block *, ext4_group_t,
				const char *, const char *, ...)
	__attribute__ ((format (printf, 4, 5)));
1517
extern void ext4_update_dynamic_rev(struct super_block *sb);
1518 1519 1520 1521 1522 1523
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);
1524 1525 1526 1527 1528 1529
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);
1530 1531 1532 1533 1534 1535 1536 1537
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);
1538 1539 1540 1541 1542 1543
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);
1544 1545 1546 1547 1548 1549 1550 1551
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);
1552 1553 1554 1555
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
1556 1557 1558 1559

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) |
1560
		le32_to_cpu(es->s_blocks_count_lo);
L
Laurent Vivier 已提交
1561 1562 1563 1564 1565
}

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) |
1566
		le32_to_cpu(es->s_r_blocks_count_lo);
L
Laurent Vivier 已提交
1567 1568 1569 1570 1571
}

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) |
1572
		le32_to_cpu(es->s_free_blocks_count_lo);
L
Laurent Vivier 已提交
1573 1574 1575 1576 1577
}

static inline void ext4_blocks_count_set(struct ext4_super_block *es,
					 ext4_fsblk_t blk)
{
1578
	es->s_blocks_count_lo = cpu_to_le32((u32)blk);
L
Laurent Vivier 已提交
1579 1580 1581 1582 1583 1584
	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)
{
1585
	es->s_free_blocks_count_lo = cpu_to_le32((u32)blk);
L
Laurent Vivier 已提交
1586 1587 1588 1589 1590 1591
	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)
{
1592
	es->s_r_blocks_count_lo = cpu_to_le32((u32)blk);
L
Laurent Vivier 已提交
1593 1594 1595
	es->s_r_blocks_count_hi = cpu_to_le32(blk >> 32);
}

1596 1597
static inline loff_t ext4_isize(struct ext4_inode *raw_inode)
{
1598 1599 1600 1601 1602
	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);
1603
}
L
Laurent Vivier 已提交
1604

1605 1606 1607 1608 1609
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);
}
1610

1611 1612
static inline
struct ext4_group_info *ext4_get_group_info(struct super_block *sb,
1613
					    ext4_group_t group)
1614 1615 1616 1617 1618 1619 1620 1621 1622
{
	 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];
}

1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634
/*
 * 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;
}
1635

1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646
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;
}

1647
#define ext4_std_error(sb, errno)				\
1648 1649
do {								\
	if ((errno))						\
1650
		__ext4_std_error((sb), __func__, (errno));	\
1651 1652
} while (0)

1653
#ifdef CONFIG_SMP
1654
/* Each CPU can accumulate percpu_counter_batch blocks in their local
1655
 * counters. So we need to make sure we have free blocks more
1656
 * than percpu_counter_batch  * nr_cpu_ids. Also add a window of 4 times.
1657
 */
1658
#define EXT4_FREEBLOCKS_WATERMARK (4 * (percpu_counter_batch * nr_cpu_ids))
1659 1660 1661 1662
#else
#define EXT4_FREEBLOCKS_WATERMARK 0
#endif

1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673
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 ;
}
1674

1675 1676 1677
struct ext4_group_info {
	unsigned long   bb_state;
	struct rb_root  bb_free_root;
1678 1679 1680
	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 */
1681
	ext4_grpblk_t	bb_largest_free_order;/* order of largest frag in BG */
1682 1683 1684 1685 1686
	struct          list_head bb_prealloc_list;
#ifdef DOUBLE_CHECK
	void            *bb_bitmap;
#endif
	struct rw_semaphore alloc_sem;
1687 1688 1689 1690
	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. */
1691 1692 1693 1694 1695 1696 1697
};

#define EXT4_GROUP_INFO_NEED_INIT_BIT	0

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

1698 1699 1700
#define EXT4_MAX_CONTENTION		8
#define EXT4_CONTENTION_THRESHOLD	2

1701 1702
static inline spinlock_t *ext4_group_lock_ptr(struct super_block *sb,
					      ext4_group_t group)
1703
{
1704 1705
	return bgl_lock_ptr(EXT4_SB(sb)->s_blockgroup_lock, group);
}
1706

1707 1708 1709 1710 1711 1712 1713 1714 1715
/*
 * 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);
}

1716 1717
static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group)
{
1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733
	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);
	}
1734 1735 1736 1737 1738
}

static inline void ext4_unlock_group(struct super_block *sb,
					ext4_group_t group)
{
1739
	spin_unlock(ext4_group_lock_ptr(sb, group));
1740 1741
}

1742 1743 1744 1745 1746
/*
 * Inodes and files operations
 */

/* dir.c */
1747
extern const struct file_operations ext4_dir_operations;
1748 1749

/* file.c */
1750
extern const struct inode_operations ext4_file_inode_operations;
1751
extern const struct file_operations ext4_file_operations;
1752 1753

/* namei.c */
1754 1755
extern const struct inode_operations ext4_dir_inode_operations;
extern const struct inode_operations ext4_special_inode_operations;
1756
extern struct dentry *ext4_get_parent(struct dentry *child);
1757 1758

/* symlink.c */
1759 1760
extern const struct inode_operations ext4_symlink_inode_operations;
extern const struct inode_operations ext4_fast_symlink_inode_operations;
1761

1762 1763 1764 1765 1766 1767 1768 1769 1770
/* block_validity */
extern void ext4_release_system_zone(struct super_block *sb);
extern int ext4_setup_system_zone(struct super_block *sb);
extern int __init init_ext4_system_zone(void);
extern void exit_ext4_system_zone(void);
extern int ext4_data_block_valid(struct ext4_sb_info *sbi,
				 ext4_fsblk_t start_blk,
				 unsigned int count);

A
Alex Tomas 已提交
1771 1772 1773
/* extents.c */
extern int ext4_ext_tree_init(handle_t *handle, struct inode *);
extern int ext4_ext_writepage_trans_blocks(struct inode *, int);
1774 1775
extern int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks,
				       int chunk);
A
Alex Tomas 已提交
1776
extern int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
1777
			       ext4_lblk_t iblock, unsigned int max_blocks,
1778
			       struct buffer_head *bh_result, int flags);
1779
extern void ext4_ext_truncate(struct inode *);
A
Alex Tomas 已提交
1780 1781
extern void ext4_ext_init(struct super_block *);
extern void ext4_ext_release(struct super_block *);
A
Amit Arora 已提交
1782 1783
extern long ext4_fallocate(struct inode *inode, int mode, loff_t offset,
			  loff_t len);
1784
extern int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
1785
			  ssize_t len);
1786 1787
extern int ext4_get_blocks(handle_t *handle, struct inode *inode,
			   sector_t block, unsigned int max_blocks,
1788
			   struct buffer_head *bh, int flags);
A
Aneesh Kumar K.V 已提交
1789 1790
extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
			__u64 start, __u64 len);
1791 1792 1793 1794 1795
/* 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);

A
Aneesh Kumar K.V 已提交
1796

1797 1798 1799 1800 1801 1802 1803 1804 1805
/* 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)

1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822
/*
 * 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);
}

1823 1824
#define in_range(b, first, len)	((b) >= (first) && (b) <= (first) + (len) - 1)

1825 1826
#endif	/* __KERNEL__ */

1827
#endif	/* _EXT4_H */