xfs_format.h 57.6 KB
Newer Older
1
/* SPDX-License-Identifier: GPL-2.0 */
2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17
/*
 * Copyright (c) 2000-2005 Silicon Graphics, Inc.
 * All Rights Reserved.
 */
#ifndef __XFS_FORMAT_H__
#define __XFS_FORMAT_H__

/*
 * XFS On Disk Format Definitions
 *
 * This header file defines all the on-disk format definitions for 
 * general XFS objects. Directory and attribute related objects are defined in
 * xfs_da_format.h, which log and log item formats are defined in
 * xfs_log_format.h. Everything else goes here.
 */

18 19 20 21 22 23
struct xfs_mount;
struct xfs_trans;
struct xfs_inode;
struct xfs_buf;
struct xfs_ifork;

24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49
/*
 * Super block
 * Fits into a sector-sized buffer at address 0 of each allocation group.
 * Only the first of these is ever updated except during growfs.
 */
#define	XFS_SB_MAGIC		0x58465342	/* 'XFSB' */
#define	XFS_SB_VERSION_1	1		/* 5.3, 6.0.1, 6.1 */
#define	XFS_SB_VERSION_2	2		/* 6.2 - attributes */
#define	XFS_SB_VERSION_3	3		/* 6.2 - new inode version */
#define	XFS_SB_VERSION_4	4		/* 6.2+ - bitmask version */
#define	XFS_SB_VERSION_5	5		/* CRC enabled filesystem */
#define	XFS_SB_VERSION_NUMBITS		0x000f
#define	XFS_SB_VERSION_ALLFBITS		0xfff0
#define	XFS_SB_VERSION_ATTRBIT		0x0010
#define	XFS_SB_VERSION_NLINKBIT		0x0020
#define	XFS_SB_VERSION_QUOTABIT		0x0040
#define	XFS_SB_VERSION_ALIGNBIT		0x0080
#define	XFS_SB_VERSION_DALIGNBIT	0x0100
#define	XFS_SB_VERSION_SHAREDBIT	0x0200
#define XFS_SB_VERSION_LOGV2BIT		0x0400
#define XFS_SB_VERSION_SECTORBIT	0x0800
#define	XFS_SB_VERSION_EXTFLGBIT	0x1000
#define	XFS_SB_VERSION_DIRV2BIT		0x2000
#define	XFS_SB_VERSION_BORGBIT		0x4000	/* ASCII only case-insens. */
#define	XFS_SB_VERSION_MOREBITSBIT	0x8000

50 51 52 53 54 55 56 57
/*
 * The size of a single extended attribute on disk is limited by
 * the size of index values within the attribute entries themselves.
 * These are be16 fields, so we can only support attribute data
 * sizes up to 2^16 bytes in length.
 */
#define XFS_XATTR_SIZE_MAX (1 << 16)

58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88
/*
 * Supported feature bit list is just all bits in the versionnum field because
 * we've used them all up and understand them all. Except, of course, for the
 * shared superblock bit, which nobody knows what it does and so is unsupported.
 */
#define	XFS_SB_VERSION_OKBITS		\
	((XFS_SB_VERSION_NUMBITS | XFS_SB_VERSION_ALLFBITS) & \
		~XFS_SB_VERSION_SHAREDBIT)

/*
 * There are two words to hold XFS "feature" bits: the original
 * word, sb_versionnum, and sb_features2.  Whenever a bit is set in
 * sb_features2, the feature bit XFS_SB_VERSION_MOREBITSBIT must be set.
 *
 * These defines represent bits in sb_features2.
 */
#define XFS_SB_VERSION2_RESERVED1BIT	0x00000001
#define XFS_SB_VERSION2_LAZYSBCOUNTBIT	0x00000002	/* Superblk counters */
#define XFS_SB_VERSION2_RESERVED4BIT	0x00000004
#define XFS_SB_VERSION2_ATTR2BIT	0x00000008	/* Inline attr rework */
#define XFS_SB_VERSION2_PARENTBIT	0x00000010	/* parent pointers */
#define XFS_SB_VERSION2_PROJID32BIT	0x00000080	/* 32 bit project id */
#define XFS_SB_VERSION2_CRCBIT		0x00000100	/* metadata CRCs */
#define XFS_SB_VERSION2_FTYPE		0x00000200	/* inode type in dir */

#define	XFS_SB_VERSION2_OKBITS		\
	(XFS_SB_VERSION2_LAZYSBCOUNTBIT	| \
	 XFS_SB_VERSION2_ATTR2BIT	| \
	 XFS_SB_VERSION2_PROJID32BIT	| \
	 XFS_SB_VERSION2_FTYPE)

89 90 91
/* Maximum size of the xfs filesystem label, no terminating NULL */
#define XFSLABEL_MAX			12

92 93 94 95 96
/*
 * Superblock - in core version.  Must match the ondisk version below.
 * Must be padded to 64 bit alignment.
 */
typedef struct xfs_sb {
97 98
	uint32_t	sb_magicnum;	/* magic number == XFS_SB_MAGIC */
	uint32_t	sb_blocksize;	/* logical block size, bytes */
99 100 101
	xfs_rfsblock_t	sb_dblocks;	/* number of data blocks */
	xfs_rfsblock_t	sb_rblocks;	/* number of realtime blocks */
	xfs_rtblock_t	sb_rextents;	/* number of realtime extents */
102
	uuid_t		sb_uuid;	/* user-visible file system unique id */
103 104 105 106 107 108 109 110 111
	xfs_fsblock_t	sb_logstart;	/* starting block of log if internal */
	xfs_ino_t	sb_rootino;	/* root inode number */
	xfs_ino_t	sb_rbmino;	/* bitmap inode for realtime extents */
	xfs_ino_t	sb_rsumino;	/* summary inode for rt bitmap */
	xfs_agblock_t	sb_rextsize;	/* realtime extent size, blocks */
	xfs_agblock_t	sb_agblocks;	/* size of an allocation group */
	xfs_agnumber_t	sb_agcount;	/* number of allocation groups */
	xfs_extlen_t	sb_rbmblocks;	/* number of rt bitmap blocks */
	xfs_extlen_t	sb_logblocks;	/* number of log blocks */
112 113 114 115
	uint16_t	sb_versionnum;	/* header version == XFS_SB_VERSION */
	uint16_t	sb_sectsize;	/* volume sector size, bytes */
	uint16_t	sb_inodesize;	/* inode size, bytes */
	uint16_t	sb_inopblock;	/* inodes per block */
116
	char		sb_fname[XFSLABEL_MAX]; /* file system name */
117 118 119 120 121 122 123 124
	uint8_t		sb_blocklog;	/* log2 of sb_blocksize */
	uint8_t		sb_sectlog;	/* log2 of sb_sectsize */
	uint8_t		sb_inodelog;	/* log2 of sb_inodesize */
	uint8_t		sb_inopblog;	/* log2 of sb_inopblock */
	uint8_t		sb_agblklog;	/* log2 of sb_agblocks (rounded up) */
	uint8_t		sb_rextslog;	/* log2 of sb_rextents */
	uint8_t		sb_inprogress;	/* mkfs is in progress, don't mount */
	uint8_t		sb_imax_pct;	/* max % of fs for inode space */
125 126 127 128 129 130
					/* statistics */
	/*
	 * These fields must remain contiguous.  If you really
	 * want to change their layout, make sure you fix the
	 * code in xfs_trans_apply_sb_deltas().
	 */
131 132 133 134
	uint64_t	sb_icount;	/* allocated inodes */
	uint64_t	sb_ifree;	/* free inodes */
	uint64_t	sb_fdblocks;	/* free data blocks */
	uint64_t	sb_frextents;	/* free realtime extents */
135 136 137 138 139
	/*
	 * End contiguous fields.
	 */
	xfs_ino_t	sb_uquotino;	/* user quota inode */
	xfs_ino_t	sb_gquotino;	/* group quota inode */
140 141 142
	uint16_t	sb_qflags;	/* quota flags */
	uint8_t		sb_flags;	/* misc. flags */
	uint8_t		sb_shared_vn;	/* shared version number */
143
	xfs_extlen_t	sb_inoalignmt;	/* inode chunk alignment, fsblocks */
144 145 146 147 148 149 150
	uint32_t	sb_unit;	/* stripe or raid unit */
	uint32_t	sb_width;	/* stripe or raid width */
	uint8_t		sb_dirblklog;	/* log2 of dir block size (fsbs) */
	uint8_t		sb_logsectlog;	/* log2 of the log sector size */
	uint16_t	sb_logsectsize;	/* sector size for the log, bytes */
	uint32_t	sb_logsunit;	/* stripe unit size for the log */
	uint32_t	sb_features2;	/* additional feature bits */
151 152

	/*
153 154 155 156 157 158 159
	 * bad features2 field as a result of failing to pad the sb structure to
	 * 64 bits. Some machines will be using this field for features2 bits.
	 * Easiest just to mark it bad and not use it for anything else.
	 *
	 * This is not kept up to date in memory; it is always overwritten by
	 * the value in sb_features2 when formatting the incore superblock to
	 * the disk buffer.
160
	 */
161
	uint32_t	sb_bad_features2;
162 163 164 165

	/* version 5 superblock fields start here */

	/* feature masks */
166 167 168 169
	uint32_t	sb_features_compat;
	uint32_t	sb_features_ro_compat;
	uint32_t	sb_features_incompat;
	uint32_t	sb_features_log_incompat;
170

171
	uint32_t	sb_crc;		/* superblock crc */
172
	xfs_extlen_t	sb_spino_align;	/* sparse inode chunk alignment */
173 174 175

	xfs_ino_t	sb_pquotino;	/* project quota inode */
	xfs_lsn_t	sb_lsn;		/* last write sequence */
176
	uuid_t		sb_meta_uuid;	/* metadata file system unique id */
177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192

	/* must be padded to 64 bit alignment */
} xfs_sb_t;

#define XFS_SB_CRC_OFF		offsetof(struct xfs_sb, sb_crc)

/*
 * Superblock - on disk version.  Must match the in core version above.
 * Must be padded to 64 bit alignment.
 */
typedef struct xfs_dsb {
	__be32		sb_magicnum;	/* magic number == XFS_SB_MAGIC */
	__be32		sb_blocksize;	/* logical block size, bytes */
	__be64		sb_dblocks;	/* number of data blocks */
	__be64		sb_rblocks;	/* number of realtime blocks */
	__be64		sb_rextents;	/* number of realtime extents */
193
	uuid_t		sb_uuid;	/* user-visible file system unique id */
194 195 196 197 198 199 200 201 202 203 204 205 206
	__be64		sb_logstart;	/* starting block of log if internal */
	__be64		sb_rootino;	/* root inode number */
	__be64		sb_rbmino;	/* bitmap inode for realtime extents */
	__be64		sb_rsumino;	/* summary inode for rt bitmap */
	__be32		sb_rextsize;	/* realtime extent size, blocks */
	__be32		sb_agblocks;	/* size of an allocation group */
	__be32		sb_agcount;	/* number of allocation groups */
	__be32		sb_rbmblocks;	/* number of rt bitmap blocks */
	__be32		sb_logblocks;	/* number of log blocks */
	__be16		sb_versionnum;	/* header version == XFS_SB_VERSION */
	__be16		sb_sectsize;	/* volume sector size, bytes */
	__be16		sb_inodesize;	/* inode size, bytes */
	__be16		sb_inopblock;	/* inodes per block */
207
	char		sb_fname[XFSLABEL_MAX]; /* file system name */
208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258
	__u8		sb_blocklog;	/* log2 of sb_blocksize */
	__u8		sb_sectlog;	/* log2 of sb_sectsize */
	__u8		sb_inodelog;	/* log2 of sb_inodesize */
	__u8		sb_inopblog;	/* log2 of sb_inopblock */
	__u8		sb_agblklog;	/* log2 of sb_agblocks (rounded up) */
	__u8		sb_rextslog;	/* log2 of sb_rextents */
	__u8		sb_inprogress;	/* mkfs is in progress, don't mount */
	__u8		sb_imax_pct;	/* max % of fs for inode space */
					/* statistics */
	/*
	 * These fields must remain contiguous.  If you really
	 * want to change their layout, make sure you fix the
	 * code in xfs_trans_apply_sb_deltas().
	 */
	__be64		sb_icount;	/* allocated inodes */
	__be64		sb_ifree;	/* free inodes */
	__be64		sb_fdblocks;	/* free data blocks */
	__be64		sb_frextents;	/* free realtime extents */
	/*
	 * End contiguous fields.
	 */
	__be64		sb_uquotino;	/* user quota inode */
	__be64		sb_gquotino;	/* group quota inode */
	__be16		sb_qflags;	/* quota flags */
	__u8		sb_flags;	/* misc. flags */
	__u8		sb_shared_vn;	/* shared version number */
	__be32		sb_inoalignmt;	/* inode chunk alignment, fsblocks */
	__be32		sb_unit;	/* stripe or raid unit */
	__be32		sb_width;	/* stripe or raid width */
	__u8		sb_dirblklog;	/* log2 of dir block size (fsbs) */
	__u8		sb_logsectlog;	/* log2 of the log sector size */
	__be16		sb_logsectsize;	/* sector size for the log, bytes */
	__be32		sb_logsunit;	/* stripe unit size for the log */
	__be32		sb_features2;	/* additional feature bits */
	/*
	 * bad features2 field as a result of failing to pad the sb
	 * structure to 64 bits. Some machines will be using this field
	 * for features2 bits. Easiest just to mark it bad and not use
	 * it for anything else.
	 */
	__be32		sb_bad_features2;

	/* version 5 superblock fields start here */

	/* feature masks */
	__be32		sb_features_compat;
	__be32		sb_features_ro_compat;
	__be32		sb_features_incompat;
	__be32		sb_features_log_incompat;

	__le32		sb_crc;		/* superblock crc */
259
	__be32		sb_spino_align;	/* sparse inode chunk alignment */
260 261 262

	__be64		sb_pquotino;	/* project quota inode */
	__be64		sb_lsn;		/* last write sequence */
263
	uuid_t		sb_meta_uuid;	/* metadata file system unique id */
264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289

	/* must be padded to 64 bit alignment */
} xfs_dsb_t;


/*
 * Misc. Flags - warning - these will be cleared by xfs_repair unless
 * a feature bit is set when the flag is used.
 */
#define XFS_SBF_NOFLAGS		0x00	/* no flags set */
#define XFS_SBF_READONLY	0x01	/* only read-only mounts allowed */

/*
 * define max. shared version we can interoperate with
 */
#define XFS_SB_MAX_SHARED_VN	0

#define	XFS_SB_VERSION_NUM(sbp)	((sbp)->sb_versionnum & XFS_SB_VERSION_NUMBITS)

/*
 * The first XFS version we support is a v4 superblock with V2 directories.
 */
static inline bool xfs_sb_good_v4_features(struct xfs_sb *sbp)
{
	if (!(sbp->sb_versionnum & XFS_SB_VERSION_DIRV2BIT))
		return false;
290 291
	if (!(sbp->sb_versionnum & XFS_SB_VERSION_EXTFLGBIT))
		return false;
292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310

	/* check for unknown features in the fs */
	if ((sbp->sb_versionnum & ~XFS_SB_VERSION_OKBITS) ||
	    ((sbp->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT) &&
	     (sbp->sb_features2 & ~XFS_SB_VERSION2_OKBITS)))
		return false;

	return true;
}

static inline bool xfs_sb_good_version(struct xfs_sb *sbp)
{
	if (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5)
		return true;
	if (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4)
		return xfs_sb_good_v4_features(sbp);
	return false;
}

311 312 313 314 315
static inline bool xfs_sb_version_hasrealtime(struct xfs_sb *sbp)
{
	return sbp->sb_rblocks > 0;
}

316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443
/*
 * Detect a mismatched features2 field.  Older kernels read/wrote
 * this into the wrong slot, so to be safe we keep them in sync.
 */
static inline bool xfs_sb_has_mismatched_features2(struct xfs_sb *sbp)
{
	return sbp->sb_bad_features2 != sbp->sb_features2;
}

static inline bool xfs_sb_version_hasattr(struct xfs_sb *sbp)
{
	return (sbp->sb_versionnum & XFS_SB_VERSION_ATTRBIT);
}

static inline void xfs_sb_version_addattr(struct xfs_sb *sbp)
{
	sbp->sb_versionnum |= XFS_SB_VERSION_ATTRBIT;
}

static inline bool xfs_sb_version_hasquota(struct xfs_sb *sbp)
{
	return (sbp->sb_versionnum & XFS_SB_VERSION_QUOTABIT);
}

static inline void xfs_sb_version_addquota(struct xfs_sb *sbp)
{
	sbp->sb_versionnum |= XFS_SB_VERSION_QUOTABIT;
}

static inline bool xfs_sb_version_hasalign(struct xfs_sb *sbp)
{
	return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5 ||
		(sbp->sb_versionnum & XFS_SB_VERSION_ALIGNBIT));
}

static inline bool xfs_sb_version_hasdalign(struct xfs_sb *sbp)
{
	return (sbp->sb_versionnum & XFS_SB_VERSION_DALIGNBIT);
}

static inline bool xfs_sb_version_haslogv2(struct xfs_sb *sbp)
{
	return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5 ||
	       (sbp->sb_versionnum & XFS_SB_VERSION_LOGV2BIT);
}

static inline bool xfs_sb_version_hassector(struct xfs_sb *sbp)
{
	return (sbp->sb_versionnum & XFS_SB_VERSION_SECTORBIT);
}

static inline bool xfs_sb_version_hasasciici(struct xfs_sb *sbp)
{
	return (sbp->sb_versionnum & XFS_SB_VERSION_BORGBIT);
}

static inline bool xfs_sb_version_hasmorebits(struct xfs_sb *sbp)
{
	return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5 ||
	       (sbp->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT);
}

/*
 * sb_features2 bit version macros.
 */
static inline bool xfs_sb_version_haslazysbcount(struct xfs_sb *sbp)
{
	return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) ||
	       (xfs_sb_version_hasmorebits(sbp) &&
		(sbp->sb_features2 & XFS_SB_VERSION2_LAZYSBCOUNTBIT));
}

static inline bool xfs_sb_version_hasattr2(struct xfs_sb *sbp)
{
	return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) ||
	       (xfs_sb_version_hasmorebits(sbp) &&
		(sbp->sb_features2 & XFS_SB_VERSION2_ATTR2BIT));
}

static inline void xfs_sb_version_addattr2(struct xfs_sb *sbp)
{
	sbp->sb_versionnum |= XFS_SB_VERSION_MOREBITSBIT;
	sbp->sb_features2 |= XFS_SB_VERSION2_ATTR2BIT;
}

static inline void xfs_sb_version_removeattr2(struct xfs_sb *sbp)
{
	sbp->sb_features2 &= ~XFS_SB_VERSION2_ATTR2BIT;
	if (!sbp->sb_features2)
		sbp->sb_versionnum &= ~XFS_SB_VERSION_MOREBITSBIT;
}

static inline bool xfs_sb_version_hasprojid32bit(struct xfs_sb *sbp)
{
	return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) ||
	       (xfs_sb_version_hasmorebits(sbp) &&
		(sbp->sb_features2 & XFS_SB_VERSION2_PROJID32BIT));
}

static inline void xfs_sb_version_addprojid32bit(struct xfs_sb *sbp)
{
	sbp->sb_versionnum |= XFS_SB_VERSION_MOREBITSBIT;
	sbp->sb_features2 |= XFS_SB_VERSION2_PROJID32BIT;
}

/*
 * Extended v5 superblock feature masks. These are to be used for new v5
 * superblock features only.
 *
 * Compat features are new features that old kernels will not notice or affect
 * and so can mount read-write without issues.
 *
 * RO-Compat (read only) are features that old kernels can read but will break
 * if they write. Hence only read-only mounts of such filesystems are allowed on
 * kernels that don't support the feature bit.
 *
 * InCompat features are features which old kernels will not understand and so
 * must not mount.
 *
 * Log-InCompat features are for changes to log formats or new transactions that
 * can't be replayed on older kernels. The fields are set when the filesystem is
 * mounted, and a clean unmount clears the fields.
 */
#define XFS_SB_FEAT_COMPAT_ALL 0
#define XFS_SB_FEAT_COMPAT_UNKNOWN	~XFS_SB_FEAT_COMPAT_ALL
static inline bool
xfs_sb_has_compat_feature(
	struct xfs_sb	*sbp,
444
	uint32_t	feature)
445 446 447 448 449
{
	return (sbp->sb_features_compat & feature) != 0;
}

#define XFS_SB_FEAT_RO_COMPAT_FINOBT   (1 << 0)		/* free inode btree */
450
#define XFS_SB_FEAT_RO_COMPAT_RMAPBT   (1 << 1)		/* reverse map btree */
451
#define XFS_SB_FEAT_RO_COMPAT_REFLINK  (1 << 2)		/* reflinked files */
452
#define XFS_SB_FEAT_RO_COMPAT_ALL \
453
		(XFS_SB_FEAT_RO_COMPAT_FINOBT | \
454 455
		 XFS_SB_FEAT_RO_COMPAT_RMAPBT | \
		 XFS_SB_FEAT_RO_COMPAT_REFLINK)
456 457 458 459
#define XFS_SB_FEAT_RO_COMPAT_UNKNOWN	~XFS_SB_FEAT_RO_COMPAT_ALL
static inline bool
xfs_sb_has_ro_compat_feature(
	struct xfs_sb	*sbp,
460
	uint32_t	feature)
461 462 463 464 465
{
	return (sbp->sb_features_ro_compat & feature) != 0;
}

#define XFS_SB_FEAT_INCOMPAT_FTYPE	(1 << 0)	/* filetype in dirent */
466
#define XFS_SB_FEAT_INCOMPAT_SPINODES	(1 << 1)	/* sparse inode chunks */
467
#define XFS_SB_FEAT_INCOMPAT_META_UUID	(1 << 2)	/* metadata UUID */
468
#define XFS_SB_FEAT_INCOMPAT_ALL \
469
		(XFS_SB_FEAT_INCOMPAT_FTYPE|	\
470 471
		 XFS_SB_FEAT_INCOMPAT_SPINODES|	\
		 XFS_SB_FEAT_INCOMPAT_META_UUID)
472 473 474 475 476

#define XFS_SB_FEAT_INCOMPAT_UNKNOWN	~XFS_SB_FEAT_INCOMPAT_ALL
static inline bool
xfs_sb_has_incompat_feature(
	struct xfs_sb	*sbp,
477
	uint32_t	feature)
478 479 480 481 482 483 484 485 486
{
	return (sbp->sb_features_incompat & feature) != 0;
}

#define XFS_SB_FEAT_INCOMPAT_LOG_ALL 0
#define XFS_SB_FEAT_INCOMPAT_LOG_UNKNOWN	~XFS_SB_FEAT_INCOMPAT_LOG_ALL
static inline bool
xfs_sb_has_incompat_log_feature(
	struct xfs_sb	*sbp,
487
	uint32_t	feature)
488 489 490 491 492 493 494
{
	return (sbp->sb_features_log_incompat & feature) != 0;
}

/*
 * V5 superblock specific feature checks
 */
495
static inline bool xfs_sb_version_hascrc(struct xfs_sb *sbp)
496 497 498 499
{
	return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5;
}

500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516
/*
 * v5 file systems support V3 inodes only, earlier file systems support
 * v2 and v1 inodes.
 */
static inline bool xfs_sb_version_has_v3inode(struct xfs_sb *sbp)
{
	return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5;
}

static inline bool xfs_dinode_good_version(struct xfs_sb *sbp,
		uint8_t version)
{
	if (xfs_sb_version_has_v3inode(sbp))
		return version == 3;
	return version == 1 || version == 2;
}

517
static inline bool xfs_sb_version_has_pquotino(struct xfs_sb *sbp)
518 519 520 521 522 523 524 525 526 527 528 529
{
	return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5;
}

static inline int xfs_sb_version_hasftype(struct xfs_sb *sbp)
{
	return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5 &&
		xfs_sb_has_incompat_feature(sbp, XFS_SB_FEAT_INCOMPAT_FTYPE)) ||
	       (xfs_sb_version_hasmorebits(sbp) &&
		 (sbp->sb_features2 & XFS_SB_VERSION2_FTYPE));
}

D
Darrick J. Wong 已提交
530
static inline bool xfs_sb_version_hasfinobt(xfs_sb_t *sbp)
531 532 533 534 535
{
	return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) &&
		(sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_FINOBT);
}

536 537 538 539 540 541
static inline bool xfs_sb_version_hassparseinodes(struct xfs_sb *sbp)
{
	return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5 &&
		xfs_sb_has_incompat_feature(sbp, XFS_SB_FEAT_INCOMPAT_SPINODES);
}

542 543 544 545 546 547 548 549 550 551 552 553
/*
 * XFS_SB_FEAT_INCOMPAT_META_UUID indicates that the metadata UUID
 * is stored separately from the user-visible UUID; this allows the
 * user-visible UUID to be changed on V5 filesystems which have a
 * filesystem UUID stamped into every piece of metadata.
 */
static inline bool xfs_sb_version_hasmetauuid(struct xfs_sb *sbp)
{
	return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) &&
		(sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_META_UUID);
}

554 555 556 557 558 559
static inline bool xfs_sb_version_hasrmapbt(struct xfs_sb *sbp)
{
	return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) &&
		(sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_RMAPBT);
}

560 561 562 563 564 565
static inline bool xfs_sb_version_hasreflink(struct xfs_sb *sbp)
{
	return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5 &&
		(sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_REFLINK);
}

566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604
/*
 * end of superblock version macros
 */

static inline bool
xfs_is_quota_inode(struct xfs_sb *sbp, xfs_ino_t ino)
{
	return (ino == sbp->sb_uquotino ||
		ino == sbp->sb_gquotino ||
		ino == sbp->sb_pquotino);
}

#define XFS_SB_DADDR		((xfs_daddr_t)0) /* daddr in filesystem/ag */
#define	XFS_SB_BLOCK(mp)	XFS_HDR_BLOCK(mp, XFS_SB_DADDR)

#define	XFS_HDR_BLOCK(mp,d)	((xfs_agblock_t)XFS_BB_TO_FSBT(mp,d))
#define	XFS_DADDR_TO_FSB(mp,d)	XFS_AGB_TO_FSB(mp, \
			xfs_daddr_to_agno(mp,d), xfs_daddr_to_agbno(mp,d))
#define	XFS_FSB_TO_DADDR(mp,fsbno)	XFS_AGB_TO_DADDR(mp, \
			XFS_FSB_TO_AGNO(mp,fsbno), XFS_FSB_TO_AGBNO(mp,fsbno))

/*
 * File system sector to basic block conversions.
 */
#define XFS_FSS_TO_BB(mp,sec)	((sec) << (mp)->m_sectbb_log)

/*
 * File system block to basic block conversions.
 */
#define	XFS_FSB_TO_BB(mp,fsbno)	((fsbno) << (mp)->m_blkbb_log)
#define	XFS_BB_TO_FSB(mp,bb)	\
	(((bb) + (XFS_FSB_TO_BB(mp,1) - 1)) >> (mp)->m_blkbb_log)
#define	XFS_BB_TO_FSBT(mp,bb)	((bb) >> (mp)->m_blkbb_log)

/*
 * File system block to byte conversions.
 */
#define XFS_FSB_TO_B(mp,fsbno)	((xfs_fsize_t)(fsbno) << (mp)->m_sb.sb_blocklog)
#define XFS_B_TO_FSB(mp,b)	\
605 606
	((((uint64_t)(b)) + (mp)->m_blockmask) >> (mp)->m_sb.sb_blocklog)
#define XFS_B_TO_FSBT(mp,b)	(((uint64_t)(b)) >> (mp)->m_sb.sb_blocklog)
607 608
#define XFS_B_FSB_OFFSET(mp,b)	((b) & (mp)->m_blockmask)

609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624
/*
 * Allocation group header
 *
 * This is divided into three structures, placed in sequential 512-byte
 * buffers after a copy of the superblock (also in a 512-byte buffer).
 */
#define	XFS_AGF_MAGIC	0x58414746	/* 'XAGF' */
#define	XFS_AGI_MAGIC	0x58414749	/* 'XAGI' */
#define	XFS_AGFL_MAGIC	0x5841464c	/* 'XAFL' */
#define	XFS_AGF_VERSION	1
#define	XFS_AGI_VERSION	1

#define	XFS_AGF_GOOD_VERSION(v)	((v) == XFS_AGF_VERSION)
#define	XFS_AGI_GOOD_VERSION(v)	((v) == XFS_AGI_VERSION)

/*
625
 * Btree number 0 is bno, 1 is cnt, 2 is rmap. This value gives the size of the
626 627
 * arrays below.
 */
628
#define	XFS_BTNUM_AGF	((int)XFS_BTNUM_RMAPi + 1)
629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644

/*
 * The second word of agf_levels in the first a.g. overlaps the EFS
 * superblock's magic number.  Since the magic numbers valid for EFS
 * are > 64k, our value cannot be confused for an EFS superblock's.
 */

typedef struct xfs_agf {
	/*
	 * Common allocation group header information
	 */
	__be32		agf_magicnum;	/* magic number == XFS_AGF_MAGIC */
	__be32		agf_versionnum;	/* header version == XFS_AGF_VERSION */
	__be32		agf_seqno;	/* sequence # starting from 0 */
	__be32		agf_length;	/* size in blocks of a.g. */
	/*
645
	 * Freespace and rmap information
646 647 648 649 650 651 652 653 654 655 656 657 658
	 */
	__be32		agf_roots[XFS_BTNUM_AGF];	/* root blocks */
	__be32		agf_levels[XFS_BTNUM_AGF];	/* btree levels */

	__be32		agf_flfirst;	/* first freelist block's index */
	__be32		agf_fllast;	/* last freelist block's index */
	__be32		agf_flcount;	/* count of blocks in freelist */
	__be32		agf_freeblks;	/* total free blocks */

	__be32		agf_longest;	/* longest free space */
	__be32		agf_btreeblks;	/* # of blocks held in AGF btrees */
	uuid_t		agf_uuid;	/* uuid of filesystem */

659
	__be32		agf_rmap_blocks;	/* rmapbt blocks used */
660 661 662 663
	__be32		agf_refcount_blocks;	/* refcountbt blocks used */

	__be32		agf_refcount_root;	/* refcount tree root block */
	__be32		agf_refcount_level;	/* refcount btree levels */
664

665 666 667 668 669
	/*
	 * reserve some contiguous space for future logged fields before we add
	 * the unlogged fields. This makes the range logging via flags and
	 * structure offsets much simpler.
	 */
670
	__be64		agf_spare64[14];
671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694

	/* unlogged fields, written during buffer writeback. */
	__be64		agf_lsn;	/* last write sequence */
	__be32		agf_crc;	/* crc of agf sector */
	__be32		agf_spare2;

	/* structure must be padded to 64 bit alignment */
} xfs_agf_t;

#define XFS_AGF_CRC_OFF		offsetof(struct xfs_agf, agf_crc)

#define	XFS_AGF_MAGICNUM	0x00000001
#define	XFS_AGF_VERSIONNUM	0x00000002
#define	XFS_AGF_SEQNO		0x00000004
#define	XFS_AGF_LENGTH		0x00000008
#define	XFS_AGF_ROOTS		0x00000010
#define	XFS_AGF_LEVELS		0x00000020
#define	XFS_AGF_FLFIRST		0x00000040
#define	XFS_AGF_FLLAST		0x00000080
#define	XFS_AGF_FLCOUNT		0x00000100
#define	XFS_AGF_FREEBLKS	0x00000200
#define	XFS_AGF_LONGEST		0x00000400
#define	XFS_AGF_BTREEBLKS	0x00000800
#define	XFS_AGF_UUID		0x00001000
695
#define	XFS_AGF_RMAP_BLOCKS	0x00002000
696 697 698 699 700
#define	XFS_AGF_REFCOUNT_BLOCKS	0x00004000
#define	XFS_AGF_REFCOUNT_ROOT	0x00008000
#define	XFS_AGF_REFCOUNT_LEVEL	0x00010000
#define	XFS_AGF_SPARE64		0x00020000
#define	XFS_AGF_NUM_BITS	18
701 702 703 704 705 706 707 708 709 710 711 712 713 714 715
#define	XFS_AGF_ALL_BITS	((1 << XFS_AGF_NUM_BITS) - 1)

#define XFS_AGF_FLAGS \
	{ XFS_AGF_MAGICNUM,	"MAGICNUM" }, \
	{ XFS_AGF_VERSIONNUM,	"VERSIONNUM" }, \
	{ XFS_AGF_SEQNO,	"SEQNO" }, \
	{ XFS_AGF_LENGTH,	"LENGTH" }, \
	{ XFS_AGF_ROOTS,	"ROOTS" }, \
	{ XFS_AGF_LEVELS,	"LEVELS" }, \
	{ XFS_AGF_FLFIRST,	"FLFIRST" }, \
	{ XFS_AGF_FLLAST,	"FLLAST" }, \
	{ XFS_AGF_FLCOUNT,	"FLCOUNT" }, \
	{ XFS_AGF_FREEBLKS,	"FREEBLKS" }, \
	{ XFS_AGF_LONGEST,	"LONGEST" }, \
	{ XFS_AGF_BTREEBLKS,	"BTREEBLKS" }, \
716
	{ XFS_AGF_UUID,		"UUID" }, \
717
	{ XFS_AGF_RMAP_BLOCKS,	"RMAP_BLOCKS" }, \
718 719 720
	{ XFS_AGF_REFCOUNT_BLOCKS,	"REFCOUNT_BLOCKS" }, \
	{ XFS_AGF_REFCOUNT_ROOT,	"REFCOUNT_ROOT" }, \
	{ XFS_AGF_REFCOUNT_LEVEL,	"REFCOUNT_LEVEL" }, \
721
	{ XFS_AGF_SPARE64,	"SPARE64" }
722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799

/* disk block (xfs_daddr_t) in the AG */
#define XFS_AGF_DADDR(mp)	((xfs_daddr_t)(1 << (mp)->m_sectbb_log))
#define	XFS_AGF_BLOCK(mp)	XFS_HDR_BLOCK(mp, XFS_AGF_DADDR(mp))

/*
 * Size of the unlinked inode hash table in the agi.
 */
#define	XFS_AGI_UNLINKED_BUCKETS	64

typedef struct xfs_agi {
	/*
	 * Common allocation group header information
	 */
	__be32		agi_magicnum;	/* magic number == XFS_AGI_MAGIC */
	__be32		agi_versionnum;	/* header version == XFS_AGI_VERSION */
	__be32		agi_seqno;	/* sequence # starting from 0 */
	__be32		agi_length;	/* size in blocks of a.g. */
	/*
	 * Inode information
	 * Inodes are mapped by interpreting the inode number, so no
	 * mapping data is needed here.
	 */
	__be32		agi_count;	/* count of allocated inodes */
	__be32		agi_root;	/* root of inode btree */
	__be32		agi_level;	/* levels in inode btree */
	__be32		agi_freecount;	/* number of free inodes */

	__be32		agi_newino;	/* new inode just allocated */
	__be32		agi_dirino;	/* last directory inode chunk */
	/*
	 * Hash table of inodes which have been unlinked but are
	 * still being referenced.
	 */
	__be32		agi_unlinked[XFS_AGI_UNLINKED_BUCKETS];
	/*
	 * This marks the end of logging region 1 and start of logging region 2.
	 */
	uuid_t		agi_uuid;	/* uuid of filesystem */
	__be32		agi_crc;	/* crc of agi sector */
	__be32		agi_pad32;
	__be64		agi_lsn;	/* last write sequence */

	__be32		agi_free_root; /* root of the free inode btree */
	__be32		agi_free_level;/* levels in free inode btree */

	/* structure must be padded to 64 bit alignment */
} xfs_agi_t;

#define XFS_AGI_CRC_OFF		offsetof(struct xfs_agi, agi_crc)

#define	XFS_AGI_MAGICNUM	(1 << 0)
#define	XFS_AGI_VERSIONNUM	(1 << 1)
#define	XFS_AGI_SEQNO		(1 << 2)
#define	XFS_AGI_LENGTH		(1 << 3)
#define	XFS_AGI_COUNT		(1 << 4)
#define	XFS_AGI_ROOT		(1 << 5)
#define	XFS_AGI_LEVEL		(1 << 6)
#define	XFS_AGI_FREECOUNT	(1 << 7)
#define	XFS_AGI_NEWINO		(1 << 8)
#define	XFS_AGI_DIRINO		(1 << 9)
#define	XFS_AGI_UNLINKED	(1 << 10)
#define	XFS_AGI_NUM_BITS_R1	11	/* end of the 1st agi logging region */
#define	XFS_AGI_ALL_BITS_R1	((1 << XFS_AGI_NUM_BITS_R1) - 1)
#define	XFS_AGI_FREE_ROOT	(1 << 11)
#define	XFS_AGI_FREE_LEVEL	(1 << 12)
#define	XFS_AGI_NUM_BITS_R2	13

/* disk block (xfs_daddr_t) in the AG */
#define XFS_AGI_DADDR(mp)	((xfs_daddr_t)(2 << (mp)->m_sectbb_log))
#define	XFS_AGI_BLOCK(mp)	XFS_HDR_BLOCK(mp, XFS_AGI_DADDR(mp))

/*
 * The third a.g. block contains the a.g. freelist, an array
 * of block pointers to blocks owned by the allocation btree code.
 */
#define XFS_AGFL_DADDR(mp)	((xfs_daddr_t)(3 << (mp)->m_sectbb_log))
#define	XFS_AGFL_BLOCK(mp)	XFS_HDR_BLOCK(mp, XFS_AGFL_DADDR(mp))
800
#define	XFS_BUF_TO_AGFL(bp)	((struct xfs_agfl *)((bp)->b_addr))
801

802
struct xfs_agfl {
803 804 805 806 807
	__be32		agfl_magicnum;
	__be32		agfl_seqno;
	uuid_t		agfl_uuid;
	__be64		agfl_lsn;
	__be32		agfl_crc;
808
} __attribute__((packed));
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

#define XFS_AGFL_CRC_OFF	offsetof(struct xfs_agfl, agfl_crc)

#define XFS_AGB_TO_FSB(mp,agno,agbno)	\
	(((xfs_fsblock_t)(agno) << (mp)->m_sb.sb_agblklog) | (agbno))
#define	XFS_FSB_TO_AGNO(mp,fsbno)	\
	((xfs_agnumber_t)((fsbno) >> (mp)->m_sb.sb_agblklog))
#define	XFS_FSB_TO_AGBNO(mp,fsbno)	\
	((xfs_agblock_t)((fsbno) & xfs_mask32lo((mp)->m_sb.sb_agblklog)))
#define	XFS_AGB_TO_DADDR(mp,agno,agbno)	\
	((xfs_daddr_t)XFS_FSB_TO_BB(mp, \
		(xfs_fsblock_t)(agno) * (mp)->m_sb.sb_agblocks + (agbno)))
#define	XFS_AG_DADDR(mp,agno,d)		(XFS_AGB_TO_DADDR(mp, agno, 0) + (d))

/*
 * For checking for bad ranges of xfs_daddr_t's, covering multiple
 * allocation groups or a single xfs_daddr_t that's a superblock copy.
 */
#define	XFS_AG_CHECK_DADDR(mp,d,len)	\
	((len) == 1 ? \
	    ASSERT((d) == XFS_SB_DADDR || \
		   xfs_daddr_to_agbno(mp, d) != XFS_SB_DADDR) : \
	    ASSERT(xfs_daddr_to_agno(mp, d) == \
		   xfs_daddr_to_agno(mp, (d) + (len) - 1)))

834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892
typedef struct xfs_timestamp {
	__be32		t_sec;		/* timestamp seconds */
	__be32		t_nsec;		/* timestamp nanoseconds */
} xfs_timestamp_t;

/*
 * On-disk inode structure.
 *
 * This is just the header or "dinode core", the inode is expanded to fill a
 * variable size the leftover area split into a data and an attribute fork.
 * The format of the data and attribute fork depends on the format of the
 * inode as indicated by di_format and di_aformat.  To access the data and
 * attribute use the XFS_DFORK_DPTR, XFS_DFORK_APTR, and XFS_DFORK_PTR macros
 * below.
 *
 * There is a very similar struct icdinode in xfs_inode which matches the
 * layout of the first 96 bytes of this structure, but is kept in native
 * format instead of big endian.
 *
 * Note: di_flushiter is only used by v1/2 inodes - it's effectively a zeroed
 * padding field for v3 inodes.
 */
#define	XFS_DINODE_MAGIC		0x494e	/* 'IN' */
typedef struct xfs_dinode {
	__be16		di_magic;	/* inode magic # = XFS_DINODE_MAGIC */
	__be16		di_mode;	/* mode and type of file */
	__u8		di_version;	/* inode version */
	__u8		di_format;	/* format of di_c data */
	__be16		di_onlink;	/* old number of links to file */
	__be32		di_uid;		/* owner's user id */
	__be32		di_gid;		/* owner's group id */
	__be32		di_nlink;	/* number of links to file */
	__be16		di_projid_lo;	/* lower part of owner's project id */
	__be16		di_projid_hi;	/* higher part owner's project id */
	__u8		di_pad[6];	/* unused, zeroed space */
	__be16		di_flushiter;	/* incremented on flush */
	xfs_timestamp_t	di_atime;	/* time last accessed */
	xfs_timestamp_t	di_mtime;	/* time last modified */
	xfs_timestamp_t	di_ctime;	/* time created/inode modified */
	__be64		di_size;	/* number of bytes in file */
	__be64		di_nblocks;	/* # of direct & btree blocks used */
	__be32		di_extsize;	/* basic/minimum extent size for file */
	__be32		di_nextents;	/* number of extents in data fork */
	__be16		di_anextents;	/* number of extents in attribute fork*/
	__u8		di_forkoff;	/* attr fork offs, <<3 for 64b align */
	__s8		di_aformat;	/* format of attr fork's data */
	__be32		di_dmevmask;	/* DMIG event mask */
	__be16		di_dmstate;	/* DMIG state info */
	__be16		di_flags;	/* random flags, XFS_DIFLAG_... */
	__be32		di_gen;		/* generation number */

	/* di_next_unlinked is the only non-core field in the old dinode */
	__be32		di_next_unlinked;/* agi unlinked list ptr */

	/* start of the extended dinode, writable fields */
	__le32		di_crc;		/* CRC of the inode */
	__be64		di_changecount;	/* number of attribute changes */
	__be64		di_lsn;		/* flush sequence */
	__be64		di_flags2;	/* more random flags */
893 894
	__be32		di_cowextsize;	/* basic cow extent size for file */
	__u8		di_pad2[12];	/* more padding for future expansion */
895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926

	/* fields only written to during inode creation */
	xfs_timestamp_t	di_crtime;	/* time created */
	__be64		di_ino;		/* inode number */
	uuid_t		di_uuid;	/* UUID of the filesystem */

	/* structure must be padded to 64 bit alignment */
} xfs_dinode_t;

#define XFS_DINODE_CRC_OFF	offsetof(struct xfs_dinode, di_crc)

#define DI_MAX_FLUSH 0xffff

/*
 * Size of the core inode on disk.  Version 1 and 2 inodes have
 * the same size, but version 3 has grown a few additional fields.
 */
static inline uint xfs_dinode_size(int version)
{
	if (version == 3)
		return sizeof(struct xfs_dinode);
	return offsetof(struct xfs_dinode, di_crc);
}

/*
 * The 32 bit link count in the inode theoretically maxes out at UINT_MAX.
 * Since the pathconf interface is signed, we use 2^31 - 1 instead.
 */
#define	XFS_MAXLINK		((1U << 31) - 1U)

/*
 * Values for di_format
927 928 929
 *
 * This enum is used in string mapping in xfs_trace.h; please keep the
 * TRACE_DEFINE_ENUMs for it up to date.
930
 */
931
enum xfs_dinode_fmt {
932 933 934 935
	XFS_DINODE_FMT_DEV,		/* xfs_dev_t */
	XFS_DINODE_FMT_LOCAL,		/* bulk data */
	XFS_DINODE_FMT_EXTENTS,		/* struct xfs_bmbt_rec */
	XFS_DINODE_FMT_BTREE,		/* struct xfs_bmdr_block */
936
	XFS_DINODE_FMT_UUID		/* added long ago, but never used */
937
};
938

939 940 941 942 943 944 945
#define XFS_INODE_FORMAT_STR \
	{ XFS_DINODE_FMT_DEV,		"dev" }, \
	{ XFS_DINODE_FMT_LOCAL,		"local" }, \
	{ XFS_DINODE_FMT_EXTENTS,	"extent" }, \
	{ XFS_DINODE_FMT_BTREE,		"btree" }, \
	{ XFS_DINODE_FMT_UUID,		"uuid" }

946 947 948 949 950 951 952 953 954 955 956
/*
 * Inode minimum and maximum sizes.
 */
#define	XFS_DINODE_MIN_LOG	8
#define	XFS_DINODE_MAX_LOG	11
#define	XFS_DINODE_MIN_SIZE	(1 << XFS_DINODE_MIN_LOG)
#define	XFS_DINODE_MAX_SIZE	(1 << XFS_DINODE_MAX_LOG)

/*
 * Inode size for given fs.
 */
957 958 959 960 961 962
#define XFS_DINODE_SIZE(sbp) \
	(xfs_sb_version_has_v3inode(sbp) ? \
		sizeof(struct xfs_dinode) : \
		offsetof(struct xfs_dinode, di_crc))
#define XFS_LITINO(mp) \
	((mp)->m_sb.sb_inodesize - XFS_DINODE_SIZE(&(mp)->m_sb))
963 964 965 966 967 968 969

/*
 * Inode data & attribute fork sizes, per inode.
 */
#define XFS_DFORK_BOFF(dip)		((int)((dip)->di_forkoff << 3))

#define XFS_DFORK_DSIZE(dip,mp) \
970
	((dip)->di_forkoff ? XFS_DFORK_BOFF(dip) : XFS_LITINO(mp))
971
#define XFS_DFORK_ASIZE(dip,mp) \
972
	((dip)->di_forkoff ? XFS_LITINO(mp) - XFS_DFORK_BOFF(dip) : 0)
973 974 975 976 977
#define XFS_DFORK_SIZE(dip,mp,w) \
	((w) == XFS_DATA_FORK ? \
		XFS_DFORK_DSIZE(dip, mp) : \
		XFS_DFORK_ASIZE(dip, mp))

978 979 980
#define XFS_DFORK_MAXEXT(dip, mp, w) \
	(XFS_DFORK_SIZE(dip, mp, w) / sizeof(struct xfs_bmbt_rec))

981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031
/*
 * Return pointers to the data or attribute forks.
 */
#define XFS_DFORK_DPTR(dip) \
	((char *)dip + xfs_dinode_size(dip->di_version))
#define XFS_DFORK_APTR(dip)	\
	(XFS_DFORK_DPTR(dip) + XFS_DFORK_BOFF(dip))
#define XFS_DFORK_PTR(dip,w)	\
	((w) == XFS_DATA_FORK ? XFS_DFORK_DPTR(dip) : XFS_DFORK_APTR(dip))

#define XFS_DFORK_FORMAT(dip,w) \
	((w) == XFS_DATA_FORK ? \
		(dip)->di_format : \
		(dip)->di_aformat)
#define XFS_DFORK_NEXTENTS(dip,w) \
	((w) == XFS_DATA_FORK ? \
		be32_to_cpu((dip)->di_nextents) : \
		be16_to_cpu((dip)->di_anextents))

/*
 * For block and character special files the 32bit dev_t is stored at the
 * beginning of the data fork.
 */
static inline xfs_dev_t xfs_dinode_get_rdev(struct xfs_dinode *dip)
{
	return be32_to_cpu(*(__be32 *)XFS_DFORK_DPTR(dip));
}

static inline void xfs_dinode_put_rdev(struct xfs_dinode *dip, xfs_dev_t rdev)
{
	*(__be32 *)XFS_DFORK_DPTR(dip) = cpu_to_be32(rdev);
}

/*
 * Values for di_flags
 */
#define XFS_DIFLAG_REALTIME_BIT  0	/* file's blocks come from rt area */
#define XFS_DIFLAG_PREALLOC_BIT  1	/* file space has been preallocated */
#define XFS_DIFLAG_NEWRTBM_BIT   2	/* for rtbitmap inode, new format */
#define XFS_DIFLAG_IMMUTABLE_BIT 3	/* inode is immutable */
#define XFS_DIFLAG_APPEND_BIT    4	/* inode is append-only */
#define XFS_DIFLAG_SYNC_BIT      5	/* inode is written synchronously */
#define XFS_DIFLAG_NOATIME_BIT   6	/* do not update atime */
#define XFS_DIFLAG_NODUMP_BIT    7	/* do not dump */
#define XFS_DIFLAG_RTINHERIT_BIT 8	/* create with realtime bit set */
#define XFS_DIFLAG_PROJINHERIT_BIT   9	/* create with parents projid */
#define XFS_DIFLAG_NOSYMLINKS_BIT   10	/* disallow symlink creation */
#define XFS_DIFLAG_EXTSIZE_BIT      11	/* inode extent size allocator hint */
#define XFS_DIFLAG_EXTSZINHERIT_BIT 12	/* inherit inode extent size */
#define XFS_DIFLAG_NODEFRAG_BIT     13	/* do not reorganize/defragment */
#define XFS_DIFLAG_FILESTREAM_BIT   14  /* use filestream allocator */
1032 1033
/* Do not use bit 15, di_flags is legacy and unchanging now */

1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056
#define XFS_DIFLAG_REALTIME      (1 << XFS_DIFLAG_REALTIME_BIT)
#define XFS_DIFLAG_PREALLOC      (1 << XFS_DIFLAG_PREALLOC_BIT)
#define XFS_DIFLAG_NEWRTBM       (1 << XFS_DIFLAG_NEWRTBM_BIT)
#define XFS_DIFLAG_IMMUTABLE     (1 << XFS_DIFLAG_IMMUTABLE_BIT)
#define XFS_DIFLAG_APPEND        (1 << XFS_DIFLAG_APPEND_BIT)
#define XFS_DIFLAG_SYNC          (1 << XFS_DIFLAG_SYNC_BIT)
#define XFS_DIFLAG_NOATIME       (1 << XFS_DIFLAG_NOATIME_BIT)
#define XFS_DIFLAG_NODUMP        (1 << XFS_DIFLAG_NODUMP_BIT)
#define XFS_DIFLAG_RTINHERIT     (1 << XFS_DIFLAG_RTINHERIT_BIT)
#define XFS_DIFLAG_PROJINHERIT   (1 << XFS_DIFLAG_PROJINHERIT_BIT)
#define XFS_DIFLAG_NOSYMLINKS    (1 << XFS_DIFLAG_NOSYMLINKS_BIT)
#define XFS_DIFLAG_EXTSIZE       (1 << XFS_DIFLAG_EXTSIZE_BIT)
#define XFS_DIFLAG_EXTSZINHERIT  (1 << XFS_DIFLAG_EXTSZINHERIT_BIT)
#define XFS_DIFLAG_NODEFRAG      (1 << XFS_DIFLAG_NODEFRAG_BIT)
#define XFS_DIFLAG_FILESTREAM    (1 << XFS_DIFLAG_FILESTREAM_BIT)

#define XFS_DIFLAG_ANY \
	(XFS_DIFLAG_REALTIME | XFS_DIFLAG_PREALLOC | XFS_DIFLAG_NEWRTBM | \
	 XFS_DIFLAG_IMMUTABLE | XFS_DIFLAG_APPEND | XFS_DIFLAG_SYNC | \
	 XFS_DIFLAG_NOATIME | XFS_DIFLAG_NODUMP | XFS_DIFLAG_RTINHERIT | \
	 XFS_DIFLAG_PROJINHERIT | XFS_DIFLAG_NOSYMLINKS | XFS_DIFLAG_EXTSIZE | \
	 XFS_DIFLAG_EXTSZINHERIT | XFS_DIFLAG_NODEFRAG | XFS_DIFLAG_FILESTREAM)

1057 1058 1059 1060 1061
/*
 * Values for di_flags2 These start by being exposed to userspace in the upper
 * 16 bits of the XFS_XFLAG_s range.
 */
#define XFS_DIFLAG2_DAX_BIT	0	/* use DAX for this inode */
1062 1063
#define XFS_DIFLAG2_REFLINK_BIT	1	/* file's blocks may be shared */
#define XFS_DIFLAG2_COWEXTSIZE_BIT   2  /* copy on write extent size hint */
1064
#define XFS_DIFLAG2_DAX		(1 << XFS_DIFLAG2_DAX_BIT)
1065 1066
#define XFS_DIFLAG2_REFLINK     (1 << XFS_DIFLAG2_REFLINK_BIT)
#define XFS_DIFLAG2_COWEXTSIZE  (1 << XFS_DIFLAG2_COWEXTSIZE_BIT)
1067

1068 1069
#define XFS_DIFLAG2_ANY \
	(XFS_DIFLAG2_DAX | XFS_DIFLAG2_REFLINK | XFS_DIFLAG2_COWEXTSIZE)
1070

1071 1072 1073 1074 1075 1076 1077
/*
 * Inode number format:
 * low inopblog bits - offset in block
 * next agblklog bits - block number in ag
 * next agno_log bits - ag number
 * high agno_log-agblklog-inopblog bits - 0
 */
1078
#define	XFS_INO_MASK(k)			(uint32_t)((1ULL << (k)) - 1)
1079 1080
#define	XFS_INO_OFFSET_BITS(mp)		(mp)->m_sb.sb_inopblog
#define	XFS_INO_AGBNO_BITS(mp)		(mp)->m_sb.sb_agblklog
D
Darrick J. Wong 已提交
1081
#define	XFS_INO_AGINO_BITS(mp)		((mp)->m_ino_geo.agino_log)
1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102
#define	XFS_INO_AGNO_BITS(mp)		(mp)->m_agno_log
#define	XFS_INO_BITS(mp)		\
	XFS_INO_AGNO_BITS(mp) + XFS_INO_AGINO_BITS(mp)
#define	XFS_INO_TO_AGNO(mp,i)		\
	((xfs_agnumber_t)((i) >> XFS_INO_AGINO_BITS(mp)))
#define	XFS_INO_TO_AGINO(mp,i)		\
	((xfs_agino_t)(i) & XFS_INO_MASK(XFS_INO_AGINO_BITS(mp)))
#define	XFS_INO_TO_AGBNO(mp,i)		\
	(((xfs_agblock_t)(i) >> XFS_INO_OFFSET_BITS(mp)) & \
		XFS_INO_MASK(XFS_INO_AGBNO_BITS(mp)))
#define	XFS_INO_TO_OFFSET(mp,i)		\
	((int)(i) & XFS_INO_MASK(XFS_INO_OFFSET_BITS(mp)))
#define	XFS_INO_TO_FSB(mp,i)		\
	XFS_AGB_TO_FSB(mp, XFS_INO_TO_AGNO(mp,i), XFS_INO_TO_AGBNO(mp,i))
#define	XFS_AGINO_TO_INO(mp,a,i)	\
	(((xfs_ino_t)(a) << XFS_INO_AGINO_BITS(mp)) | (i))
#define	XFS_AGINO_TO_AGBNO(mp,i)	((i) >> XFS_INO_OFFSET_BITS(mp))
#define	XFS_AGINO_TO_OFFSET(mp,i)	\
	((i) & XFS_INO_MASK(XFS_INO_OFFSET_BITS(mp)))
#define	XFS_OFFBNO_TO_AGINO(mp,b,o)	\
	((xfs_agino_t)(((b) << XFS_INO_OFFSET_BITS(mp)) | (o)))
1103 1104
#define	XFS_FSB_TO_INO(mp, b)	((xfs_ino_t)((b) << XFS_INO_OFFSET_BITS(mp)))
#define	XFS_AGB_TO_AGINO(mp, b)	((xfs_agino_t)((b) << XFS_INO_OFFSET_BITS(mp)))
1105 1106 1107

#define	XFS_MAXINUMBER		((xfs_ino_t)((1ULL << 56) - 1ULL))
#define	XFS_MAXINUMBER_32	((xfs_ino_t)((1ULL << 32) - 1ULL))
1108

D
Dave Chinner 已提交
1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145
/*
 * RealTime Device format definitions
 */

/* Min and max rt extent sizes, specified in bytes */
#define	XFS_MAX_RTEXTSIZE	(1024 * 1024 * 1024)	/* 1GB */
#define	XFS_DFL_RTEXTSIZE	(64 * 1024)	        /* 64kB */
#define	XFS_MIN_RTEXTSIZE	(4 * 1024)		/* 4kB */

#define	XFS_BLOCKSIZE(mp)	((mp)->m_sb.sb_blocksize)
#define	XFS_BLOCKMASK(mp)	((mp)->m_blockmask)
#define	XFS_BLOCKWSIZE(mp)	((mp)->m_blockwsize)
#define	XFS_BLOCKWMASK(mp)	((mp)->m_blockwmask)

/*
 * RT Summary and bit manipulation macros.
 */
#define	XFS_SUMOFFS(mp,ls,bb)	((int)((ls) * (mp)->m_sb.sb_rbmblocks + (bb)))
#define	XFS_SUMOFFSTOBLOCK(mp,s)	\
	(((s) * (uint)sizeof(xfs_suminfo_t)) >> (mp)->m_sb.sb_blocklog)
#define	XFS_SUMPTR(mp,bp,so)	\
	((xfs_suminfo_t *)((bp)->b_addr + \
		(((so) * (uint)sizeof(xfs_suminfo_t)) & XFS_BLOCKMASK(mp))))

#define	XFS_BITTOBLOCK(mp,bi)	((bi) >> (mp)->m_blkbit_log)
#define	XFS_BLOCKTOBIT(mp,bb)	((bb) << (mp)->m_blkbit_log)
#define	XFS_BITTOWORD(mp,bi)	\
	((int)(((bi) >> XFS_NBWORDLOG) & XFS_BLOCKWMASK(mp)))

#define	XFS_RTMIN(a,b)	((a) < (b) ? (a) : (b))
#define	XFS_RTMAX(a,b)	((a) > (b) ? (a) : (b))

#define	XFS_RTLOBIT(w)	xfs_lowbit32(w)
#define	XFS_RTHIBIT(w)	xfs_highbit32(w)

#define	XFS_RTBLOCKLOG(b)	xfs_highbit64(b)

1146 1147 1148 1149
/*
 * Dquot and dquot block format definitions
 */
#define XFS_DQUOT_MAGIC		0x4451		/* 'DQ' */
D
Darrick J. Wong 已提交
1150
#define XFS_DQUOT_VERSION	(uint8_t)0x01	/* latest version number */
1151

1152 1153 1154 1155 1156 1157 1158 1159 1160
#define XFS_DQTYPE_USER		0x01		/* user dquot record */
#define XFS_DQTYPE_PROJ		0x02		/* project dquot record */
#define XFS_DQTYPE_GROUP	0x04		/* group dquot record */

/* bitmask to determine if this is a user/group/project dquot */
#define XFS_DQTYPE_REC_MASK	(XFS_DQTYPE_USER | \
				 XFS_DQTYPE_PROJ | \
				 XFS_DQTYPE_GROUP)

1161 1162
#define XFS_DQTYPE_ANY		(XFS_DQTYPE_REC_MASK)

1163
/*
1164 1165 1166
 * This is the main portion of the on-disk representation of quota information
 * for a user.  We pad this with some more expansion room to construct the on
 * disk structure.
1167
 */
1168
struct xfs_disk_dquot {
1169 1170
	__be16		d_magic;	/* dquot magic = XFS_DQUOT_MAGIC */
	__u8		d_version;	/* dquot version */
1171
	__u8		d_type;		/* XFS_DQTYPE_USER/PROJ/GROUP */
1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190
	__be32		d_id;		/* user,project,group id */
	__be64		d_blk_hardlimit;/* absolute limit on disk blks */
	__be64		d_blk_softlimit;/* preferred limit on disk blks */
	__be64		d_ino_hardlimit;/* maximum # allocated inodes */
	__be64		d_ino_softlimit;/* preferred inode limit */
	__be64		d_bcount;	/* disk blocks owned by the user */
	__be64		d_icount;	/* inodes owned by the user */
	__be32		d_itimer;	/* zero if within inode limits if not,
					   this is when we refuse service */
	__be32		d_btimer;	/* similar to above; for disk blocks */
	__be16		d_iwarns;	/* warnings issued wrt num inodes */
	__be16		d_bwarns;	/* warnings issued wrt disk blocks */
	__be32		d_pad0;		/* 64 bit align */
	__be64		d_rtb_hardlimit;/* absolute limit on realtime blks */
	__be64		d_rtb_softlimit;/* preferred limit on RT disk blks */
	__be64		d_rtbcount;	/* realtime blocks owned */
	__be32		d_rtbtimer;	/* similar to above; for RT disk blocks */
	__be16		d_rtbwarns;	/* warnings issued wrt RT disk blocks */
	__be16		d_pad;
1191
};
1192 1193 1194 1195 1196 1197

/*
 * This is what goes on disk. This is separated from the xfs_disk_dquot because
 * carrying the unnecessary padding would be a waste of memory.
 */
typedef struct xfs_dqblk {
1198 1199
	struct xfs_disk_dquot	dd_diskdq; /* portion living incore as well */
	char			dd_fill[4];/* filling for posterity */
1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210

	/*
	 * These two are only present on filesystems with the CRC bits set.
	 */
	__be32		  dd_crc;	/* checksum */
	__be64		  dd_lsn;	/* last modification in log */
	uuid_t		  dd_uuid;	/* location information */
} xfs_dqblk_t;

#define XFS_DQUOT_CRC_OFF	offsetof(struct xfs_dqblk, dd_crc)

1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226
/*
 * This defines the unit of allocation of dquots.
 *
 * Currently, it is just one file system block, and a 4K blk contains 30
 * (136 * 30 = 4080) dquots. It's probably not worth trying to make
 * this more dynamic.
 *
 * However, if this number is changed, we have to make sure that we don't
 * implicitly assume that we do allocations in chunks of a single filesystem
 * block in the dquot/xqm code.
 *
 * This is part of the ondisk format because the structure size is not a power
 * of two, which leaves slack at the end of the disk block.
 */
#define XFS_DQUOT_CLUSTER_SIZE_FSB	(xfs_filblks_t)1

1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242
/*
 * Remote symlink format and access functions.
 */
#define XFS_SYMLINK_MAGIC	0x58534c4d	/* XSLM */

struct xfs_dsymlink_hdr {
	__be32	sl_magic;
	__be32	sl_offset;
	__be32	sl_bytes;
	__be32	sl_crc;
	uuid_t	sl_uuid;
	__be64	sl_owner;
	__be64	sl_blkno;
	__be64	sl_lsn;
};

1243 1244
#define XFS_SYMLINK_CRC_OFF	offsetof(struct xfs_dsymlink_hdr, sl_crc)

1245
#define XFS_SYMLINK_MAXLEN	1024
1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256
/*
 * The maximum pathlen is 1024 bytes. Since the minimum file system
 * blocksize is 512 bytes, we can get a max of 3 extents back from
 * bmapi when crc headers are taken into account.
 */
#define XFS_SYMLINK_MAPS 3

#define XFS_SYMLINK_BUF_SPACE(mp, bufsize)	\
	((bufsize) - (xfs_sb_version_hascrc(&(mp)->m_sb) ? \
			sizeof(struct xfs_dsymlink_hdr) : 0))

1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300

/*
 * Allocation Btree format definitions
 *
 * There are two on-disk btrees, one sorted by blockno and one sorted
 * by blockcount and blockno.  All blocks look the same to make the code
 * simpler; if we have time later, we'll make the optimizations.
 */
#define	XFS_ABTB_MAGIC		0x41425442	/* 'ABTB' for bno tree */
#define	XFS_ABTB_CRC_MAGIC	0x41423342	/* 'AB3B' */
#define	XFS_ABTC_MAGIC		0x41425443	/* 'ABTC' for cnt tree */
#define	XFS_ABTC_CRC_MAGIC	0x41423343	/* 'AB3C' */

/*
 * Data record/key structure
 */
typedef struct xfs_alloc_rec {
	__be32		ar_startblock;	/* starting block number */
	__be32		ar_blockcount;	/* count of free blocks */
} xfs_alloc_rec_t, xfs_alloc_key_t;

typedef struct xfs_alloc_rec_incore {
	xfs_agblock_t	ar_startblock;	/* starting block number */
	xfs_extlen_t	ar_blockcount;	/* count of free blocks */
} xfs_alloc_rec_incore_t;

/* btree pointer type */
typedef __be32 xfs_alloc_ptr_t;

/*
 * Block numbers in the AG:
 * SB is sector 0, AGF is sector 1, AGI is sector 2, AGFL is sector 3.
 */
#define	XFS_BNO_BLOCK(mp)	((xfs_agblock_t)(XFS_AGFL_BLOCK(mp) + 1))
#define	XFS_CNT_BLOCK(mp)	((xfs_agblock_t)(XFS_BNO_BLOCK(mp) + 1))


/*
 * Inode Allocation Btree format definitions
 *
 * There is a btree for the inode map per allocation group.
 */
#define	XFS_IBT_MAGIC		0x49414254	/* 'IABT' */
#define	XFS_IBT_CRC_MAGIC	0x49414233	/* 'IAB3' */
1301 1302
#define	XFS_FIBT_MAGIC		0x46494254	/* 'FIBT' */
#define	XFS_FIBT_CRC_MAGIC	0x46494233	/* 'FIB3' */
1303

1304
typedef uint64_t	xfs_inofree_t;
1305 1306 1307 1308 1309
#define	XFS_INODES_PER_CHUNK		(NBBY * sizeof(xfs_inofree_t))
#define	XFS_INODES_PER_CHUNK_LOG	(XFS_NBBYLOG + 3)
#define	XFS_INOBT_ALL_FREE		((xfs_inofree_t)-1)
#define	XFS_INOBT_MASK(i)		((xfs_inofree_t)1 << (i))

1310
#define XFS_INOBT_HOLEMASK_FULL		0	/* holemask for full chunk */
1311
#define XFS_INOBT_HOLEMASK_BITS		(NBBY * sizeof(uint16_t))
1312
#define XFS_INODES_PER_HOLEMASK_BIT	\
1313
	(XFS_INODES_PER_CHUNK / (NBBY * sizeof(uint16_t)))
1314

1315 1316 1317 1318 1319 1320
static inline xfs_inofree_t xfs_inobt_maskn(int i, int n)
{
	return ((n >= XFS_INODES_PER_CHUNK ? 0 : XFS_INOBT_MASK(n)) - 1) << i;
}

/*
1321 1322 1323 1324 1325 1326 1327 1328
 * The on-disk inode record structure has two formats. The original "full"
 * format uses a 4-byte freecount. The "sparse" format uses a 1-byte freecount
 * and replaces the 3 high-order freecount bytes wth the holemask and inode
 * count.
 *
 * The holemask of the sparse record format allows an inode chunk to have holes
 * that refer to blocks not owned by the inode record. This facilitates inode
 * allocation in the event of severe free space fragmentation.
1329 1330 1331
 */
typedef struct xfs_inobt_rec {
	__be32		ir_startino;	/* starting inode number */
1332 1333 1334 1335 1336 1337 1338 1339 1340 1341
	union {
		struct {
			__be32	ir_freecount;	/* count of free inodes */
		} f;
		struct {
			__be16	ir_holemask;/* hole mask for sparse chunks */
			__u8	ir_count;	/* total inode count */
			__u8	ir_freecount;	/* count of free inodes */
		} sp;
	} ir_u;
1342 1343 1344 1345 1346
	__be64		ir_free;	/* free inode mask */
} xfs_inobt_rec_t;

typedef struct xfs_inobt_rec_incore {
	xfs_agino_t	ir_startino;	/* starting inode number */
1347 1348 1349
	uint16_t	ir_holemask;	/* hole mask for sparse chunks */
	uint8_t		ir_count;	/* total inode count */
	uint8_t		ir_freecount;	/* count of free inodes (set bits) */
1350 1351 1352
	xfs_inofree_t	ir_free;	/* free inode mask */
} xfs_inobt_rec_incore_t;

1353 1354 1355 1356 1357
static inline bool xfs_inobt_issparse(uint16_t holemask)
{
	/* non-zero holemask represents a sparse rec. */
	return holemask;
}
1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372

/*
 * Key structure
 */
typedef struct xfs_inobt_key {
	__be32		ir_startino;	/* starting inode number */
} xfs_inobt_key_t;

/* btree pointer type */
typedef __be32 xfs_inobt_ptr_t;

/*
 * block numbers in the AG.
 */
#define	XFS_IBT_BLOCK(mp)		((xfs_agblock_t)(XFS_CNT_BLOCK(mp) + 1))
1373 1374
#define	XFS_FIBT_BLOCK(mp)		((xfs_agblock_t)(XFS_IBT_BLOCK(mp) + 1))

1375 1376 1377 1378 1379 1380 1381
/*
 * Reverse mapping btree format definitions
 *
 * There is a btree for the reverse map per allocation group
 */
#define	XFS_RMAP_CRC_MAGIC	0x524d4233	/* 'RMB3' */

1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407
/*
 * Ownership info for an extent.  This is used to create reverse-mapping
 * entries.
 */
#define XFS_OWNER_INFO_ATTR_FORK	(1 << 0)
#define XFS_OWNER_INFO_BMBT_BLOCK	(1 << 1)
struct xfs_owner_info {
	uint64_t		oi_owner;
	xfs_fileoff_t		oi_offset;
	unsigned int		oi_flags;
};

/*
 * Special owner types.
 *
 * Seeing as we only support up to 8EB, we have the upper bit of the owner field
 * to tell us we have a special owner value. We use these for static metadata
 * allocated at mkfs/growfs time, as well as for freespace management metadata.
 */
#define XFS_RMAP_OWN_NULL	(-1ULL)	/* No owner, for growfs */
#define XFS_RMAP_OWN_UNKNOWN	(-2ULL)	/* Unknown owner, for EFI recovery */
#define XFS_RMAP_OWN_FS		(-3ULL)	/* static fs metadata */
#define XFS_RMAP_OWN_LOG	(-4ULL)	/* static fs metadata */
#define XFS_RMAP_OWN_AG		(-5ULL)	/* AG freespace btree blocks */
#define XFS_RMAP_OWN_INOBT	(-6ULL)	/* Inode btree blocks */
#define XFS_RMAP_OWN_INODES	(-7ULL)	/* Inode chunk */
1408
#define XFS_RMAP_OWN_REFC	(-8ULL) /* refcount tree */
1409 1410
#define XFS_RMAP_OWN_COW	(-9ULL) /* cow allocations */
#define XFS_RMAP_OWN_MIN	(-10ULL) /* guard */
1411

1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431
#define XFS_RMAP_NON_INODE_OWNER(owner)	(!!((owner) & (1ULL << 63)))

/*
 * Data record structure
 */
struct xfs_rmap_rec {
	__be32		rm_startblock;	/* extent start block */
	__be32		rm_blockcount;	/* extent length */
	__be64		rm_owner;	/* extent owner */
	__be64		rm_offset;	/* offset within the owner */
};

/*
 * rmap btree record
 *  rm_offset:63 is the attribute fork flag
 *  rm_offset:62 is the bmbt block flag
 *  rm_offset:61 is the unwritten extent flag (same as l0:63 in bmbt)
 *  rm_offset:54-60 aren't used and should be zero
 *  rm_offset:0-53 is the block offset within the inode
 */
1432 1433 1434
#define XFS_RMAP_OFF_ATTR_FORK	((uint64_t)1ULL << 63)
#define XFS_RMAP_OFF_BMBT_BLOCK	((uint64_t)1ULL << 62)
#define XFS_RMAP_OFF_UNWRITTEN	((uint64_t)1ULL << 61)
1435

1436
#define XFS_RMAP_LEN_MAX	((uint32_t)~0U)
1437 1438 1439
#define XFS_RMAP_OFF_FLAGS	(XFS_RMAP_OFF_ATTR_FORK | \
				 XFS_RMAP_OFF_BMBT_BLOCK | \
				 XFS_RMAP_OFF_UNWRITTEN)
1440
#define XFS_RMAP_OFF_MASK	((uint64_t)0x3FFFFFFFFFFFFFULL)
1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465

#define XFS_RMAP_OFF(off)		((off) & XFS_RMAP_OFF_MASK)

#define XFS_RMAP_IS_BMBT_BLOCK(off)	(!!((off) & XFS_RMAP_OFF_BMBT_BLOCK))
#define XFS_RMAP_IS_ATTR_FORK(off)	(!!((off) & XFS_RMAP_OFF_ATTR_FORK))
#define XFS_RMAP_IS_UNWRITTEN(len)	(!!((off) & XFS_RMAP_OFF_UNWRITTEN))

#define RMAPBT_STARTBLOCK_BITLEN	32
#define RMAPBT_BLOCKCOUNT_BITLEN	32
#define RMAPBT_OWNER_BITLEN		64
#define RMAPBT_ATTRFLAG_BITLEN		1
#define RMAPBT_BMBTFLAG_BITLEN		1
#define RMAPBT_EXNTFLAG_BITLEN		1
#define RMAPBT_UNUSED_OFFSET_BITLEN	7
#define RMAPBT_OFFSET_BITLEN		54

#define XFS_RMAP_ATTR_FORK		(1 << 0)
#define XFS_RMAP_BMBT_BLOCK		(1 << 1)
#define XFS_RMAP_UNWRITTEN		(1 << 2)
#define XFS_RMAP_KEY_FLAGS		(XFS_RMAP_ATTR_FORK | \
					 XFS_RMAP_BMBT_BLOCK)
#define XFS_RMAP_REC_FLAGS		(XFS_RMAP_UNWRITTEN)
struct xfs_rmap_irec {
	xfs_agblock_t	rm_startblock;	/* extent start block */
	xfs_extlen_t	rm_blockcount;	/* extent length */
1466 1467
	uint64_t	rm_owner;	/* extent owner */
	uint64_t	rm_offset;	/* offset within the owner */
1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484
	unsigned int	rm_flags;	/* state flags */
};

/*
 * Key structure
 *
 * We don't use the length for lookups
 */
struct xfs_rmap_key {
	__be32		rm_startblock;	/* extent start block */
	__be64		rm_owner;	/* extent owner */
	__be64		rm_offset;	/* offset within the owner */
} __attribute__((packed));

/* btree pointer type */
typedef __be32 xfs_rmap_ptr_t;

1485
#define	XFS_RMAP_BLOCK(mp) \
1486 1487 1488
	(xfs_sb_version_hasfinobt(&((mp)->m_sb)) ? \
	 XFS_FIBT_BLOCK(mp) + 1 : \
	 XFS_IBT_BLOCK(mp) + 1)
1489

1490 1491 1492 1493 1494 1495
/*
 * Reference Count Btree format definitions
 *
 */
#define	XFS_REFC_CRC_MAGIC	0x52334643	/* 'R3FC' */

1496 1497
unsigned int xfs_refc_block(struct xfs_mount *mp);

1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511
/*
 * Data record/key structure
 *
 * Each record associates a range of physical blocks (starting at
 * rc_startblock and ending rc_blockcount blocks later) with a reference
 * count (rc_refcount).  Extents that are being used to stage a copy on
 * write (CoW) operation are recorded in the refcount btree with a
 * refcount of 1.  All other records must have a refcount > 1 and must
 * track an extent mapped only by file data forks.
 *
 * Extents with a single owner (attributes, metadata, non-shared file
 * data) are not tracked here.  Free space is also not tracked here.
 * This is consistent with pre-reflink XFS.
 */
1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522

/*
 * Extents that are being used to stage a copy on write are stored
 * in the refcount btree with a refcount of 1 and the upper bit set
 * on the startblock.  This speeds up mount time deletion of stale
 * staging extents because they're all at the right side of the tree.
 */
#define XFS_REFC_COW_START		((xfs_agblock_t)(1U << 31))
#define REFCNTBT_COWFLAG_BITLEN		1
#define REFCNTBT_AGBLOCK_BITLEN		31

1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544
struct xfs_refcount_rec {
	__be32		rc_startblock;	/* starting block number */
	__be32		rc_blockcount;	/* count of blocks */
	__be32		rc_refcount;	/* number of inodes linked here */
};

struct xfs_refcount_key {
	__be32		rc_startblock;	/* starting block number */
};

struct xfs_refcount_irec {
	xfs_agblock_t	rc_startblock;	/* starting block number */
	xfs_extlen_t	rc_blockcount;	/* count of free blocks */
	xfs_nlink_t	rc_refcount;	/* number of inodes linked here */
};

#define MAXREFCOUNT	((xfs_nlink_t)~0U)
#define MAXREFCEXTLEN	((xfs_extlen_t)~0U)

/* btree pointer type */
typedef __be32 xfs_refcount_ptr_t;

1545

1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574
/*
 * BMAP Btree format definitions
 *
 * This includes both the root block definition that sits inside an inode fork
 * and the record/pointer formats for the leaf/node in the blocks.
 */
#define XFS_BMAP_MAGIC		0x424d4150	/* 'BMAP' */
#define XFS_BMAP_CRC_MAGIC	0x424d4133	/* 'BMA3' */

/*
 * Bmap root header, on-disk form only.
 */
typedef struct xfs_bmdr_block {
	__be16		bb_level;	/* 0 is a leaf */
	__be16		bb_numrecs;	/* current # of data records */
} xfs_bmdr_block_t;

/*
 * Bmap btree record and extent descriptor.
 *  l0:63 is an extent flag (value 1 indicates non-normal).
 *  l0:9-62 are startoff.
 *  l0:0-8 and l1:21-63 are startblock.
 *  l1:0-20 are blockcount.
 */
#define BMBT_EXNTFLAG_BITLEN	1
#define BMBT_STARTOFF_BITLEN	54
#define BMBT_STARTBLOCK_BITLEN	52
#define BMBT_BLOCKCOUNT_BITLEN	21

1575
#define BMBT_STARTOFF_MASK	((1ULL << BMBT_STARTOFF_BITLEN) - 1)
D
Darrick J. Wong 已提交
1576 1577 1578 1579 1580 1581 1582
#define BMBT_BLOCKCOUNT_MASK	((1ULL << BMBT_BLOCKCOUNT_BITLEN) - 1)

/*
 * bmbt records have a file offset (block) field that is 54 bits wide, so this
 * is the largest xfs_fileoff_t that we ever expect to see.
 */
#define XFS_MAX_FILEOFF		(BMBT_STARTOFF_MASK + BMBT_BLOCKCOUNT_MASK)
1583

1584 1585 1586 1587
typedef struct xfs_bmbt_rec {
	__be64			l0, l1;
} xfs_bmbt_rec_t;

1588
typedef uint64_t	xfs_bmbt_rec_base_t;	/* use this for casts */
1589 1590 1591 1592 1593 1594
typedef xfs_bmbt_rec_t xfs_bmdr_rec_t;

/*
 * Values and macros for delayed-allocation startblock fields.
 */
#define STARTBLOCKVALBITS	17
C
Christoph Hellwig 已提交
1595
#define STARTBLOCKMASKBITS	(15 + 20)
1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639
#define STARTBLOCKMASK		\
	(((((xfs_fsblock_t)1) << STARTBLOCKMASKBITS) - 1) << STARTBLOCKVALBITS)

static inline int isnullstartblock(xfs_fsblock_t x)
{
	return ((x) & STARTBLOCKMASK) == STARTBLOCKMASK;
}

static inline xfs_fsblock_t nullstartblock(int k)
{
	ASSERT(k < (1 << STARTBLOCKVALBITS));
	return STARTBLOCKMASK | (k);
}

static inline xfs_filblks_t startblockval(xfs_fsblock_t x)
{
	return (xfs_filblks_t)((x) & ~STARTBLOCKMASK);
}

/*
 * Key structure for non-leaf levels of the tree.
 */
typedef struct xfs_bmbt_key {
	__be64		br_startoff;	/* starting file offset */
} xfs_bmbt_key_t, xfs_bmdr_key_t;

/* btree pointer type */
typedef __be64 xfs_bmbt_ptr_t, xfs_bmdr_ptr_t;


/*
 * Generic Btree block format definitions
 *
 * This is a combination of the actual format used on disk for short and long
 * format btrees.  The first three fields are shared by both format, but the
 * pointers are different and should be used with care.
 *
 * To get the size of the actual short or long form headers please use the size
 * macros below.  Never use sizeof(xfs_btree_block).
 *
 * The blkno, crc, lsn, owner and uuid fields are only available in filesystems
 * with the crc feature bit, and all accesses to them must be conditional on
 * that flag.
 */
1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664
/* short form block header */
struct xfs_btree_block_shdr {
	__be32		bb_leftsib;
	__be32		bb_rightsib;

	__be64		bb_blkno;
	__be64		bb_lsn;
	uuid_t		bb_uuid;
	__be32		bb_owner;
	__le32		bb_crc;
};

/* long form block header */
struct xfs_btree_block_lhdr {
	__be64		bb_leftsib;
	__be64		bb_rightsib;

	__be64		bb_blkno;
	__be64		bb_lsn;
	uuid_t		bb_uuid;
	__be64		bb_owner;
	__le32		bb_crc;
	__be32		bb_pad; /* padding for alignment */
};

1665 1666 1667 1668 1669
struct xfs_btree_block {
	__be32		bb_magic;	/* magic number for block type */
	__be16		bb_level;	/* 0 is a leaf */
	__be16		bb_numrecs;	/* current # of data records */
	union {
1670 1671
		struct xfs_btree_block_shdr s;
		struct xfs_btree_block_lhdr l;
1672 1673 1674
	} bb_u;				/* rest */
};

1675 1676 1677 1678 1679 1680 1681 1682
/* size of a short form block */
#define XFS_BTREE_SBLOCK_LEN \
	(offsetof(struct xfs_btree_block, bb_u) + \
	 offsetof(struct xfs_btree_block_shdr, bb_blkno))
/* size of a long form block */
#define XFS_BTREE_LBLOCK_LEN \
	(offsetof(struct xfs_btree_block, bb_u) + \
	 offsetof(struct xfs_btree_block_lhdr, bb_blkno))
1683 1684

/* sizes of CRC enabled btree blocks */
1685 1686 1687 1688 1689 1690
#define XFS_BTREE_SBLOCK_CRC_LEN \
	(offsetof(struct xfs_btree_block, bb_u) + \
	 sizeof(struct xfs_btree_block_shdr))
#define XFS_BTREE_LBLOCK_CRC_LEN \
	(offsetof(struct xfs_btree_block, bb_u) + \
	 sizeof(struct xfs_btree_block_lhdr))
1691 1692 1693 1694 1695 1696

#define XFS_BTREE_SBLOCK_CRC_OFF \
	offsetof(struct xfs_btree_block, bb_u.s.bb_crc)
#define XFS_BTREE_LBLOCK_CRC_OFF \
	offsetof(struct xfs_btree_block, bb_u.l.bb_crc)

1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708
/*
 * On-disk XFS access control list structure.
 */
struct xfs_acl_entry {
	__be32	ae_tag;
	__be32	ae_id;
	__be16	ae_perm;
	__be16	ae_pad;		/* fill the implicit hole in the structure */
};

struct xfs_acl {
	__be32			acl_cnt;
1709
	struct xfs_acl_entry	acl_entry[];
1710 1711 1712 1713 1714 1715 1716 1717 1718
};

/*
 * The number of ACL entries allowed is defined by the on-disk format.
 * For v4 superblocks, that is limited to 25 entries. For v5 superblocks, it is
 * limited only by the maximum size of the xattr that stores the information.
 */
#define XFS_ACL_MAX_ENTRIES(mp)	\
	(xfs_sb_version_hascrc(&mp->m_sb) \
1719
		?  (XFS_XATTR_SIZE_MAX - sizeof(struct xfs_acl)) / \
1720 1721 1722
						sizeof(struct xfs_acl_entry) \
		: 25)

1723
#define XFS_ACL_SIZE(cnt) \
1724
	(sizeof(struct xfs_acl) + \
1725 1726 1727 1728 1729
		sizeof(struct xfs_acl_entry) * cnt)

#define XFS_ACL_MAX_SIZE(mp) \
	XFS_ACL_SIZE(XFS_ACL_MAX_ENTRIES((mp)))

1730 1731

/* On-disk XFS extended attribute names */
E
Eric Sandeen 已提交
1732 1733
#define SGI_ACL_FILE		"SGI_ACL_FILE"
#define SGI_ACL_DEFAULT		"SGI_ACL_DEFAULT"
1734 1735 1736
#define SGI_ACL_FILE_SIZE	(sizeof(SGI_ACL_FILE)-1)
#define SGI_ACL_DEFAULT_SIZE	(sizeof(SGI_ACL_DEFAULT)-1)

1737
#endif /* __XFS_FORMAT_H__ */