fs/xfs/xfs_inode.h

/*
 * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc.
 * All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it would be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write the Free Software Foundation,
 * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */
#ifndef	__XFS_INODE_H__
#define	__XFS_INODE_H__

struct posix_acl;
struct xfs_dinode;
struct xfs_inode;

/*
 * The following xfs_ext_irec_t struct introduces a second (top) level
 * to the in-core extent allocation scheme. These structs are allocated
 * in a contiguous block, creating an indirection array where each entry
 * (irec) contains a pointer to a buffer of in-core extent records which
 * it manages. Each extent buffer is 4k in size, since 4k is the system
 * page size on Linux i386 and systems with larger page sizes don't seem
 * to gain much, if anything, by using their native page size as the
 * extent buffer size. Also, using 4k extent buffers everywhere provides
 * a consistent interface for CXFS across different platforms.
 *
 * There is currently no limit on the number of irec's (extent lists)
 * allowed, so heavily fragmented files may require an indirection array
 * which spans multiple system pages of memory. The number of extents
 * which would require this amount of contiguous memory is very large
 * and should not cause problems in the foreseeable future. However,
 * if the memory needed for the contiguous array ever becomes a problem,
 * it is possible that a third level of indirection may be required.
 */
typedef struct xfs_ext_irec {
	xfs_bmbt_rec_host_t *er_extbuf;	/* block of extent records */
	xfs_extnum_t	er_extoff;	/* extent offset in file */
	xfs_extnum_t	er_extcount;	/* number of extents in page/block */
} xfs_ext_irec_t;

/*
 * File incore extent information, present for each of data & attr forks.
 */
#define	XFS_IEXT_BUFSZ		4096
#define	XFS_LINEAR_EXTS		(XFS_IEXT_BUFSZ / (uint)sizeof(xfs_bmbt_rec_t))
#define	XFS_INLINE_EXTS		2
#define	XFS_INLINE_DATA		32
typedef struct xfs_ifork {
	int			if_bytes;	/* bytes in if_u1 */
	int			if_real_bytes;	/* bytes allocated in if_u1 */
	struct xfs_btree_block	*if_broot;	/* file's incore btree root */
	short			if_broot_bytes;	/* bytes allocated for root */
	unsigned char		if_flags;	/* per-fork flags */
	union {
		xfs_bmbt_rec_host_t *if_extents;/* linear map file exts */
		xfs_ext_irec_t	*if_ext_irec;	/* irec map file exts */
		char		*if_data;	/* inline file data */
	} if_u1;
	union {
		xfs_bmbt_rec_host_t if_inline_ext[XFS_INLINE_EXTS];
						/* very small file extents */
		char		if_inline_data[XFS_INLINE_DATA];
						/* very small file data */
		xfs_dev_t	if_rdev;	/* dev number if special */
		uuid_t		if_uuid;	/* mount point value */
	} if_u2;
} xfs_ifork_t;

/*
 * Inode location information.  Stored in the inode and passed to
 * xfs_imap_to_bp() to get a buffer and dinode for a given inode.
 */
struct xfs_imap {
	xfs_daddr_t	im_blkno;	/* starting BB of inode chunk */
	ushort		im_len;		/* length in BBs of inode chunk */
	ushort		im_boffset;	/* inode offset in block in bytes */
};

/*
 * This is the xfs in-core inode structure.
 * Most of the on-disk inode is embedded in the i_d field.
 *
 * The extent pointers/inline file space, however, are managed
 * separately.  The memory for this information is pointed to by
 * the if_u1 unions depending on the type of the data.
 * This is used to linearize the array of extents for fast in-core
 * access.  This is used until the file's number of extents
 * surpasses XFS_MAX_INCORE_EXTENTS, at which point all extent pointers
 * are accessed through the buffer cache.
 *
 * Other state kept in the in-core inode is used for identification,
 * locking, transactional updating, etc of the inode.
 *
 * Generally, we do not want to hold the i_rlock while holding the
 * i_ilock. Hierarchy is i_iolock followed by i_rlock.
 *
 * xfs_iptr_t contains all the inode fields up to and including the
 * i_mnext and i_mprev fields, it is used as a marker in the inode
 * chain off the mount structure by xfs_sync calls.
 */

/*
 * Flags for xfs_ichgtime().
 */
#define	XFS_ICHGTIME_MOD	0x1	/* data fork modification timestamp */
#define	XFS_ICHGTIME_CHG	0x2	/* inode field change timestamp */
#define	XFS_ICHGTIME_CREATE	0x4	/* inode create timestamp */

/*
 * Per-fork incore inode flags.
 */
#define	XFS_IFINLINE	0x01	/* Inline data is read in */
#define	XFS_IFEXTENTS	0x02	/* All extent pointers are read in */
#define	XFS_IFBROOT	0x04	/* i_broot points to the bmap b-tree root */
#define	XFS_IFEXTIREC	0x08	/* Indirection array of extent blocks */

/*
 * Fork handling.
 */

#define XFS_IFORK_Q(ip)			((ip)->i_d.di_forkoff != 0)
#define XFS_IFORK_BOFF(ip)		((int)((ip)->i_d.di_forkoff << 3))

#define XFS_IFORK_PTR(ip,w)		\
	((w) == XFS_DATA_FORK ? \
		&(ip)->i_df : \
		(ip)->i_afp)
#define XFS_IFORK_DSIZE(ip) \
	(XFS_IFORK_Q(ip) ? \
		XFS_IFORK_BOFF(ip) : \
		XFS_LITINO((ip)->i_mount, (ip)->i_d.di_version))
#define XFS_IFORK_ASIZE(ip) \
	(XFS_IFORK_Q(ip) ? \
		XFS_LITINO((ip)->i_mount, (ip)->i_d.di_version) - \
			XFS_IFORK_BOFF(ip) : \
		0)
#define XFS_IFORK_SIZE(ip,w) \
	((w) == XFS_DATA_FORK ? \
		XFS_IFORK_DSIZE(ip) : \
		XFS_IFORK_ASIZE(ip))
#define XFS_IFORK_FORMAT(ip,w) \
	((w) == XFS_DATA_FORK ? \
		(ip)->i_d.di_format : \
		(ip)->i_d.di_aformat)
#define XFS_IFORK_FMT_SET(ip,w,n) \
	((w) == XFS_DATA_FORK ? \
		((ip)->i_d.di_format = (n)) : \
		((ip)->i_d.di_aformat = (n)))
#define XFS_IFORK_NEXTENTS(ip,w) \
	((w) == XFS_DATA_FORK ? \
		(ip)->i_d.di_nextents : \
		(ip)->i_d.di_anextents)
#define XFS_IFORK_NEXT_SET(ip,w,n) \
	((w) == XFS_DATA_FORK ? \
		((ip)->i_d.di_nextents = (n)) : \
		((ip)->i_d.di_anextents = (n)))
#define XFS_IFORK_MAXEXT(ip, w) \
	(XFS_IFORK_SIZE(ip, w) / sizeof(xfs_bmbt_rec_t))


#ifdef __KERNEL__

struct xfs_buf;
struct xfs_bmap_free;
struct xfs_bmbt_irec;
struct xfs_inode_log_item;
struct xfs_mount;
struct xfs_trans;
struct xfs_dquot;

typedef struct xfs_inode {
	/* Inode linking and identification information. */
	struct xfs_mount	*i_mount;	/* fs mount struct ptr */
	struct xfs_dquot	*i_udquot;	/* user dquot */
	struct xfs_dquot	*i_gdquot;	/* group dquot */
	struct xfs_dquot	*i_pdquot;	/* project dquot */

	/* Inode location stuff */
	xfs_ino_t		i_ino;		/* inode number (agno/agino)*/
	struct xfs_imap		i_imap;		/* location for xfs_imap() */

	/* Extent information. */
	xfs_ifork_t		*i_afp;		/* attribute fork pointer */
	xfs_ifork_t		i_df;		/* data fork */

	/* Transaction and locking information. */
	struct xfs_inode_log_item *i_itemp;	/* logging information */
	mrlock_t		i_lock;		/* inode lock */
	mrlock_t		i_iolock;	/* inode IO lock */
	atomic_t		i_pincount;	/* inode pin count */
	spinlock_t		i_flags_lock;	/* inode i_flags lock */
	/* Miscellaneous state. */
	unsigned long		i_flags;	/* see defined flags below */
	unsigned int		i_delayed_blks;	/* count of delay alloc blks */

	xfs_icdinode_t		i_d;		/* most of ondisk inode */

	/* VFS inode */
	struct inode		i_vnode;	/* embedded VFS inode */
} xfs_inode_t;

/* Convert from vfs inode to xfs inode */
static inline struct xfs_inode *XFS_I(struct inode *inode)
{
	return container_of(inode, struct xfs_inode, i_vnode);
}

/* convert from xfs inode to vfs inode */
static inline struct inode *VFS_I(struct xfs_inode *ip)
{
	return &ip->i_vnode;
}

/*
 * For regular files we only update the on-disk filesize when actually
 * writing data back to disk.  Until then only the copy in the VFS inode
 * is uptodate.
 */
static inline xfs_fsize_t XFS_ISIZE(struct xfs_inode *ip)
{
	if (S_ISREG(ip->i_d.di_mode))
		return i_size_read(VFS_I(ip));
	return ip->i_d.di_size;
}

/*
 * If this I/O goes past the on-disk inode size update it unless it would
 * be past the current in-core inode size.
 */
static inline xfs_fsize_t
xfs_new_eof(struct xfs_inode *ip, xfs_fsize_t new_size)
{
	xfs_fsize_t i_size = i_size_read(VFS_I(ip));

	if (new_size > i_size)
		new_size = i_size;
	return new_size > ip->i_d.di_size ? new_size : 0;
}

/*
 * i_flags helper functions
 */
static inline void
__xfs_iflags_set(xfs_inode_t *ip, unsigned short flags)
{
	ip->i_flags |= flags;
}

static inline void
xfs_iflags_set(xfs_inode_t *ip, unsigned short flags)
{
	spin_lock(&ip->i_flags_lock);
	__xfs_iflags_set(ip, flags);
	spin_unlock(&ip->i_flags_lock);
}

static inline void
xfs_iflags_clear(xfs_inode_t *ip, unsigned short flags)
{
	spin_lock(&ip->i_flags_lock);
	ip->i_flags &= ~flags;
	spin_unlock(&ip->i_flags_lock);
}

static inline int
__xfs_iflags_test(xfs_inode_t *ip, unsigned short flags)
{
	return (ip->i_flags & flags);
}

static inline int
xfs_iflags_test(xfs_inode_t *ip, unsigned short flags)
{
	int ret;
	spin_lock(&ip->i_flags_lock);
	ret = __xfs_iflags_test(ip, flags);
	spin_unlock(&ip->i_flags_lock);
	return ret;
}

static inline int
xfs_iflags_test_and_clear(xfs_inode_t *ip, unsigned short flags)
{
	int ret;

	spin_lock(&ip->i_flags_lock);
	ret = ip->i_flags & flags;
	if (ret)
		ip->i_flags &= ~flags;
	spin_unlock(&ip->i_flags_lock);
	return ret;
}

static inline int
xfs_iflags_test_and_set(xfs_inode_t *ip, unsigned short flags)
{
	int ret;

	spin_lock(&ip->i_flags_lock);
	ret = ip->i_flags & flags;
	if (!ret)
		ip->i_flags |= flags;
	spin_unlock(&ip->i_flags_lock);
	return ret;
}

/*
 * Project quota id helpers (previously projid was 16bit only
 * and using two 16bit values to hold new 32bit projid was chosen
 * to retain compatibility with "old" filesystems).
 */
static inline prid_t
xfs_get_projid(struct xfs_inode *ip)
{
	return (prid_t)ip->i_d.di_projid_hi << 16 | ip->i_d.di_projid_lo;
}

static inline void
xfs_set_projid(struct xfs_inode *ip,
		prid_t projid)
{
	ip->i_d.di_projid_hi = (__uint16_t) (projid >> 16);
	ip->i_d.di_projid_lo = (__uint16_t) (projid & 0xffff);
}

/*
 * In-core inode flags.
 */
#define XFS_IRECLAIM		(1 << 0) /* started reclaiming this inode */
#define XFS_ISTALE		(1 << 1) /* inode has been staled */
#define XFS_IRECLAIMABLE	(1 << 2) /* inode can be reclaimed */
#define XFS_INEW		(1 << 3) /* inode has just been allocated */
#define XFS_IFILESTREAM		(1 << 4) /* inode is in a filestream dir. */
#define XFS_ITRUNCATED		(1 << 5) /* truncated down so flush-on-close */
#define XFS_IDIRTY_RELEASE	(1 << 6) /* dirty release already seen */
#define __XFS_IFLOCK_BIT	7	 /* inode is being flushed right now */
#define XFS_IFLOCK		(1 << __XFS_IFLOCK_BIT)
#define __XFS_IPINNED_BIT	8	 /* wakeup key for zero pin count */
#define XFS_IPINNED		(1 << __XFS_IPINNED_BIT)
#define XFS_IDONTCACHE		(1 << 9) /* don't cache the inode long term */

/*
 * Per-lifetime flags need to be reset when re-using a reclaimable inode during
 * inode lookup. This prevents unintended behaviour on the new inode from
 * ocurring.
 */
#define XFS_IRECLAIM_RESET_FLAGS	\
	(XFS_IRECLAIMABLE | XFS_IRECLAIM | \
	 XFS_IDIRTY_RELEASE | XFS_ITRUNCATED | \
	 XFS_IFILESTREAM);

/*
 * Synchronize processes attempting to flush the in-core inode back to disk.
 */

extern void __xfs_iflock(struct xfs_inode *ip);

static inline int xfs_iflock_nowait(struct xfs_inode *ip)
{
	return !xfs_iflags_test_and_set(ip, XFS_IFLOCK);
}

static inline void xfs_iflock(struct xfs_inode *ip)
{
	if (!xfs_iflock_nowait(ip))
		__xfs_iflock(ip);
}

static inline void xfs_ifunlock(struct xfs_inode *ip)
{
	xfs_iflags_clear(ip, XFS_IFLOCK);
	smp_mb();
	wake_up_bit(&ip->i_flags, __XFS_IFLOCK_BIT);
}

static inline int xfs_isiflocked(struct xfs_inode *ip)
{
	return xfs_iflags_test(ip, XFS_IFLOCK);
}

/*
 * Flags for inode locking.
 * Bit ranges:	1<<1  - 1<<16-1 -- iolock/ilock modes (bitfield)
 *		1<<16 - 1<<32-1 -- lockdep annotation (integers)
 */
#define	XFS_IOLOCK_EXCL		(1<<0)
#define	XFS_IOLOCK_SHARED	(1<<1)
#define	XFS_ILOCK_EXCL		(1<<2)
#define	XFS_ILOCK_SHARED	(1<<3)

#define XFS_LOCK_MASK		(XFS_IOLOCK_EXCL | XFS_IOLOCK_SHARED \
				| XFS_ILOCK_EXCL | XFS_ILOCK_SHARED)

#define XFS_LOCK_FLAGS \
	{ XFS_IOLOCK_EXCL,	"IOLOCK_EXCL" }, \
	{ XFS_IOLOCK_SHARED,	"IOLOCK_SHARED" }, \
	{ XFS_ILOCK_EXCL,	"ILOCK_EXCL" }, \
	{ XFS_ILOCK_SHARED,	"ILOCK_SHARED" }


/*
 * Flags for lockdep annotations.
 *
 * XFS_LOCK_PARENT - for directory operations that require locking a
 * parent directory inode and a child entry inode.  The parent gets locked
 * with this flag so it gets a lockdep subclass of 1 and the child entry
 * lock will have a lockdep subclass of 0.
 *
 * XFS_LOCK_RTBITMAP/XFS_LOCK_RTSUM - the realtime device bitmap and summary
 * inodes do not participate in the normal lock order, and thus have their
 * own subclasses.
 *
 * XFS_LOCK_INUMORDER - for locking several inodes at the some time
 * with xfs_lock_inodes().  This flag is used as the starting subclass
 * and each subsequent lock acquired will increment the subclass by one.
 * So the first lock acquired will have a lockdep subclass of 4, the
 * second lock will have a lockdep subclass of 5, and so on. It is
 * the responsibility of the class builder to shift this to the correct
 * portion of the lock_mode lockdep mask.
 */
#define XFS_LOCK_PARENT		1
#define XFS_LOCK_RTBITMAP	2
#define XFS_LOCK_RTSUM		3
#define XFS_LOCK_INUMORDER	4

#define XFS_IOLOCK_SHIFT	16
#define	XFS_IOLOCK_PARENT	(XFS_LOCK_PARENT << XFS_IOLOCK_SHIFT)

#define XFS_ILOCK_SHIFT		24
#define	XFS_ILOCK_PARENT	(XFS_LOCK_PARENT << XFS_ILOCK_SHIFT)
#define	XFS_ILOCK_RTBITMAP	(XFS_LOCK_RTBITMAP << XFS_ILOCK_SHIFT)
#define	XFS_ILOCK_RTSUM		(XFS_LOCK_RTSUM << XFS_ILOCK_SHIFT)

#define XFS_IOLOCK_DEP_MASK	0x00ff0000
#define XFS_ILOCK_DEP_MASK	0xff000000
#define XFS_LOCK_DEP_MASK	(XFS_IOLOCK_DEP_MASK | XFS_ILOCK_DEP_MASK)

#define XFS_IOLOCK_DEP(flags)	(((flags) & XFS_IOLOCK_DEP_MASK) >> XFS_IOLOCK_SHIFT)
#define XFS_ILOCK_DEP(flags)	(((flags) & XFS_ILOCK_DEP_MASK) >> XFS_ILOCK_SHIFT)

/*
 * For multiple groups support: if S_ISGID bit is set in the parent
 * directory, group of new file is set to that of the parent, and
 * new subdirectory gets S_ISGID bit from parent.
 */
#define XFS_INHERIT_GID(pip)	\
	(((pip)->i_mount->m_flags & XFS_MOUNT_GRPID) || \
	 ((pip)->i_d.di_mode & S_ISGID))


/*
 * xfs_inode.c prototypes.
 */
void		xfs_ilock(xfs_inode_t *, uint);
int		xfs_ilock_nowait(xfs_inode_t *, uint);
void		xfs_iunlock(xfs_inode_t *, uint);
void		xfs_ilock_demote(xfs_inode_t *, uint);
int		xfs_isilocked(xfs_inode_t *, uint);
uint		xfs_ilock_map_shared(xfs_inode_t *);
void		xfs_iunlock_map_shared(xfs_inode_t *, uint);
int		xfs_ialloc(struct xfs_trans *, xfs_inode_t *, umode_t,
			   xfs_nlink_t, xfs_dev_t, prid_t, int,
			   struct xfs_buf **, xfs_inode_t **);

uint		xfs_ip2xflags(struct xfs_inode *);
uint		xfs_dic2xflags(struct xfs_dinode *);
int		xfs_ifree(struct xfs_trans *, xfs_inode_t *,
			   struct xfs_bmap_free *);
int		xfs_itruncate_extents(struct xfs_trans **, struct xfs_inode *,
				      int, xfs_fsize_t);
int		xfs_iunlink(struct xfs_trans *, xfs_inode_t *);

void		xfs_iext_realloc(xfs_inode_t *, int, int);
void		xfs_iunpin_wait(xfs_inode_t *);
int		xfs_iflush(struct xfs_inode *, struct xfs_buf **);
void		xfs_lock_inodes(xfs_inode_t **, int, uint);
void		xfs_lock_two_inodes(xfs_inode_t *, xfs_inode_t *, uint);

xfs_extlen_t	xfs_get_extsz_hint(struct xfs_inode *ip);

#define IHOLD(ip) \
do { \
	ASSERT(atomic_read(&VFS_I(ip)->i_count) > 0) ; \
	ihold(VFS_I(ip)); \
	trace_xfs_ihold(ip, _THIS_IP_); \
} while (0)

#define IRELE(ip) \
do { \
	trace_xfs_irele(ip, _THIS_IP_); \
	iput(VFS_I(ip)); \
} while (0)

#endif /* __KERNEL__ */

/*
 * Flags for xfs_iget()
 */
#define XFS_IGET_CREATE		0x1
#define XFS_IGET_UNTRUSTED	0x2
#define XFS_IGET_DONTCACHE	0x4

int		xfs_imap_to_bp(struct xfs_mount *, struct xfs_trans *,
			       struct xfs_imap *, struct xfs_dinode **,
			       struct xfs_buf **, uint, uint);
int		xfs_iread(struct xfs_mount *, struct xfs_trans *,
			  struct xfs_inode *, uint);
void		xfs_dinode_calc_crc(struct xfs_mount *, struct xfs_dinode *);
void		xfs_dinode_to_disk(struct xfs_dinode *,
				   struct xfs_icdinode *);
void		xfs_idestroy_fork(struct xfs_inode *, int);
void		xfs_idata_realloc(struct xfs_inode *, int, int);
void		xfs_iroot_realloc(struct xfs_inode *, int, int);
int		xfs_iread_extents(struct xfs_trans *, struct xfs_inode *, int);
int		xfs_iextents_copy(struct xfs_inode *, xfs_bmbt_rec_t *, int);

xfs_bmbt_rec_host_t *xfs_iext_get_ext(xfs_ifork_t *, xfs_extnum_t);
void		xfs_iext_insert(xfs_inode_t *, xfs_extnum_t, xfs_extnum_t,
				xfs_bmbt_irec_t *, int);
void		xfs_iext_add(xfs_ifork_t *, xfs_extnum_t, int);
void		xfs_iext_add_indirect_multi(xfs_ifork_t *, int, xfs_extnum_t, int);
void		xfs_iext_remove(xfs_inode_t *, xfs_extnum_t, int, int);
void		xfs_iext_remove_inline(xfs_ifork_t *, xfs_extnum_t, int);
void		xfs_iext_remove_direct(xfs_ifork_t *, xfs_extnum_t, int);
void		xfs_iext_remove_indirect(xfs_ifork_t *, xfs_extnum_t, int);
void		xfs_iext_realloc_direct(xfs_ifork_t *, int);
void		xfs_iext_direct_to_inline(xfs_ifork_t *, xfs_extnum_t);
void		xfs_iext_inline_to_direct(xfs_ifork_t *, int);
void		xfs_iext_destroy(xfs_ifork_t *);
xfs_bmbt_rec_host_t *xfs_iext_bno_to_ext(xfs_ifork_t *, xfs_fileoff_t, int *);
xfs_ext_irec_t	*xfs_iext_bno_to_irec(xfs_ifork_t *, xfs_fileoff_t, int *);
xfs_ext_irec_t	*xfs_iext_idx_to_irec(xfs_ifork_t *, xfs_extnum_t *, int *, int);
void		xfs_iext_irec_init(xfs_ifork_t *);
xfs_ext_irec_t *xfs_iext_irec_new(xfs_ifork_t *, int);
void		xfs_iext_irec_remove(xfs_ifork_t *, int);
void		xfs_iext_irec_compact(xfs_ifork_t *);
void		xfs_iext_irec_compact_pages(xfs_ifork_t *);
void		xfs_iext_irec_compact_full(xfs_ifork_t *);
void		xfs_iext_irec_update_extoffs(xfs_ifork_t *, int, int);
bool		xfs_can_free_eofblocks(struct xfs_inode *, bool);

#define xfs_ipincount(ip)	((unsigned int) atomic_read(&ip->i_pincount))

#if defined(DEBUG)
void		xfs_inobp_check(struct xfs_mount *, struct xfs_buf *);
#else
#define	xfs_inobp_check(mp, bp)
#endif /* DEBUG */

extern struct kmem_zone	*xfs_ifork_zone;
extern struct kmem_zone	*xfs_inode_zone;
extern const struct xfs_buf_ops xfs_inode_buf_ops;

#endif	/* __XFS_INODE_H__ */