2005-04-17 00:20:36 +02:00
|
|
|
/*
|
2005-11-02 04:58:39 +01:00
|
|
|
* Copyright (c) 2000-2003,2005 Silicon Graphics, Inc.
|
|
|
|
* All Rights Reserved.
|
2005-04-17 00:20:36 +02:00
|
|
|
*
|
2005-11-02 04:58:39 +01:00
|
|
|
* This program is free software; you can redistribute it and/or
|
|
|
|
* modify it under the terms of the GNU General Public License as
|
2005-04-17 00:20:36 +02:00
|
|
|
* published by the Free Software Foundation.
|
|
|
|
*
|
2005-11-02 04:58:39 +01:00
|
|
|
* 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.
|
2005-04-17 00:20:36 +02:00
|
|
|
*
|
2005-11-02 04:58:39 +01:00
|
|
|
* 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
|
2005-04-17 00:20:36 +02:00
|
|
|
*/
|
|
|
|
#ifndef __XFS_INODE_H__
|
|
|
|
#define __XFS_INODE_H__
|
|
|
|
|
2005-11-02 04:38:42 +01:00
|
|
|
/*
|
|
|
|
* Fork identifiers.
|
|
|
|
*/
|
|
|
|
#define XFS_DATA_FORK 0
|
|
|
|
#define XFS_ATTR_FORK 1
|
|
|
|
|
2006-03-14 03:30:23 +01:00
|
|
|
/*
|
|
|
|
* 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_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;
|
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
/*
|
|
|
|
* File incore extent information, present for each of data & attr forks.
|
|
|
|
*/
|
2006-03-14 03:30:23 +01:00
|
|
|
#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
|
2005-04-17 00:20:36 +02:00
|
|
|
typedef struct xfs_ifork {
|
|
|
|
int if_bytes; /* bytes in if_u1 */
|
|
|
|
int if_real_bytes; /* bytes allocated in if_u1 */
|
|
|
|
xfs_bmbt_block_t *if_broot; /* file's incore btree root */
|
|
|
|
short if_broot_bytes; /* bytes allocated for root */
|
|
|
|
unsigned char if_flags; /* per-fork flags */
|
|
|
|
unsigned char if_ext_max; /* max # of extent records */
|
|
|
|
xfs_extnum_t if_lastex; /* last if_extents used */
|
|
|
|
union {
|
|
|
|
xfs_bmbt_rec_t *if_extents; /* linear map file exts */
|
2006-03-14 03:30:23 +01:00
|
|
|
xfs_ext_irec_t *if_ext_irec; /* irec map file exts */
|
2005-04-17 00:20:36 +02:00
|
|
|
char *if_data; /* inline file data */
|
|
|
|
} if_u1;
|
|
|
|
union {
|
|
|
|
xfs_bmbt_rec_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;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Flags for xfs_ichgtime().
|
|
|
|
*/
|
|
|
|
#define XFS_ICHGTIME_MOD 0x1 /* data fork modification timestamp */
|
|
|
|
#define XFS_ICHGTIME_ACC 0x2 /* data fork access timestamp */
|
|
|
|
#define XFS_ICHGTIME_CHG 0x4 /* inode field change timestamp */
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Per-fork incore inode flags.
|
|
|
|
*/
|
2006-03-14 03:30:23 +01:00
|
|
|
#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 */
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
/*
|
2006-03-17 07:26:04 +01:00
|
|
|
* Flags for xfs_itobp(), xfs_imap() and xfs_dilocate().
|
2005-04-17 00:20:36 +02:00
|
|
|
*/
|
2006-03-17 07:26:04 +01:00
|
|
|
#define XFS_IMAP_LOOKUP 0x1
|
|
|
|
#define XFS_IMAP_BULKSTAT 0x2
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
#ifdef __KERNEL__
|
|
|
|
struct bhv_desc;
|
2006-06-09 09:00:52 +02:00
|
|
|
struct bhv_vnode;
|
2005-04-17 00:20:36 +02:00
|
|
|
struct cred;
|
|
|
|
struct ktrace;
|
|
|
|
struct xfs_buf;
|
|
|
|
struct xfs_bmap_free;
|
|
|
|
struct xfs_bmbt_irec;
|
|
|
|
struct xfs_bmbt_block;
|
|
|
|
struct xfs_inode;
|
|
|
|
struct xfs_inode_log_item;
|
|
|
|
struct xfs_mount;
|
|
|
|
struct xfs_trans;
|
|
|
|
struct xfs_dquot;
|
|
|
|
|
|
|
|
#if defined(XFS_ILOCK_TRACE)
|
|
|
|
#define XFS_ILOCK_KTRACE_SIZE 32
|
|
|
|
extern ktrace_t *xfs_ilock_trace_buf;
|
|
|
|
extern void xfs_ilock_trace(struct xfs_inode *, int, unsigned int, inst_t *);
|
|
|
|
#else
|
|
|
|
#define xfs_ilock_trace(i,n,f,ra)
|
|
|
|
#endif
|
|
|
|
|
|
|
|
typedef struct dm_attrs_s {
|
|
|
|
__uint32_t da_dmevmask; /* DMIG event mask */
|
|
|
|
__uint16_t da_dmstate; /* DMIG state info */
|
|
|
|
__uint16_t da_pad; /* DMIG extra padding */
|
|
|
|
} dm_attrs_t;
|
|
|
|
|
|
|
|
typedef struct xfs_iocore {
|
|
|
|
void *io_obj; /* pointer to container
|
|
|
|
* inode or dcxvn structure */
|
|
|
|
struct xfs_mount *io_mount; /* fs mount struct ptr */
|
|
|
|
#ifdef DEBUG
|
|
|
|
mrlock_t *io_lock; /* inode IO lock */
|
|
|
|
mrlock_t *io_iolock; /* inode IO lock */
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/* I/O state */
|
|
|
|
xfs_fsize_t io_new_size; /* sz when write completes */
|
|
|
|
|
|
|
|
/* Miscellaneous state. */
|
|
|
|
unsigned int io_flags; /* IO related flags */
|
|
|
|
|
|
|
|
/* DMAPI state */
|
|
|
|
dm_attrs_t io_dmattrs;
|
|
|
|
|
|
|
|
} xfs_iocore_t;
|
|
|
|
|
|
|
|
#define io_dmevmask io_dmattrs.da_dmevmask
|
|
|
|
#define io_dmstate io_dmattrs.da_dmstate
|
|
|
|
|
|
|
|
#define XFS_IO_INODE(io) ((xfs_inode_t *) ((io)->io_obj))
|
|
|
|
#define XFS_IO_DCXVN(io) ((dcxvn_t *) ((io)->io_obj))
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Flags in the flags field
|
|
|
|
*/
|
|
|
|
|
|
|
|
#define XFS_IOCORE_RT 0x1
|
|
|
|
|
|
|
|
/*
|
|
|
|
* xfs_iocore prototypes
|
|
|
|
*/
|
|
|
|
|
|
|
|
extern void xfs_iocore_inode_init(struct xfs_inode *);
|
|
|
|
extern void xfs_iocore_inode_reinit(struct xfs_inode *);
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This is the type used in the xfs inode hash table.
|
|
|
|
* An array of these is allocated for each mounted
|
|
|
|
* file system to hash the inodes for that file system.
|
|
|
|
*/
|
|
|
|
typedef struct xfs_ihash {
|
|
|
|
struct xfs_inode *ih_next;
|
|
|
|
rwlock_t ih_lock;
|
|
|
|
uint ih_version;
|
|
|
|
} xfs_ihash_t;
|
|
|
|
|
|
|
|
#define XFS_IHASH(mp,ino) ((mp)->m_ihash + (((uint)(ino)) % (mp)->m_ihsize))
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This is the xfs inode cluster hash. This hash is used by xfs_iflush to
|
|
|
|
* find inodes that share a cluster and can be flushed to disk at the same
|
|
|
|
* time.
|
|
|
|
*/
|
|
|
|
typedef struct xfs_chashlist {
|
|
|
|
struct xfs_chashlist *chl_next;
|
2006-04-11 07:11:12 +02:00
|
|
|
struct xfs_chashlist *chl_prev;
|
2005-04-17 00:20:36 +02:00
|
|
|
struct xfs_inode *chl_ip;
|
|
|
|
xfs_daddr_t chl_blkno; /* starting block number of
|
|
|
|
* the cluster */
|
|
|
|
struct xfs_buf *chl_buf; /* the inode buffer */
|
|
|
|
} xfs_chashlist_t;
|
|
|
|
|
|
|
|
typedef struct xfs_chash {
|
|
|
|
xfs_chashlist_t *ch_list;
|
|
|
|
lock_t ch_lock;
|
|
|
|
} xfs_chash_t;
|
|
|
|
|
|
|
|
#define XFS_CHASH(mp,blk) ((mp)->m_chash + (((uint)blk) % (mp)->m_chsize))
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* 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 upto 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.
|
|
|
|
*/
|
|
|
|
|
|
|
|
typedef struct {
|
|
|
|
struct xfs_ihash *ip_hash; /* pointer to hash header */
|
|
|
|
struct xfs_inode *ip_next; /* inode hash link forw */
|
|
|
|
struct xfs_inode *ip_mnext; /* next inode in mount list */
|
|
|
|
struct xfs_inode *ip_mprev; /* ptr to prev inode */
|
|
|
|
struct xfs_inode **ip_prevp; /* ptr to prev i_next */
|
|
|
|
struct xfs_mount *ip_mount; /* fs mount struct ptr */
|
|
|
|
} xfs_iptr_t;
|
|
|
|
|
|
|
|
typedef struct xfs_inode {
|
|
|
|
/* Inode linking and identification information. */
|
|
|
|
struct xfs_ihash *i_hash; /* pointer to hash header */
|
|
|
|
struct xfs_inode *i_next; /* inode hash link forw */
|
|
|
|
struct xfs_inode *i_mnext; /* next inode in mount list */
|
|
|
|
struct xfs_inode *i_mprev; /* ptr to prev inode */
|
|
|
|
struct xfs_inode **i_prevp; /* ptr to prev i_next */
|
|
|
|
struct xfs_mount *i_mount; /* fs mount struct ptr */
|
|
|
|
struct list_head i_reclaim; /* reclaim list */
|
|
|
|
struct bhv_desc i_bhv_desc; /* inode behavior descriptor*/
|
|
|
|
struct xfs_dquot *i_udquot; /* user dquot */
|
|
|
|
struct xfs_dquot *i_gdquot; /* group dquot */
|
|
|
|
|
|
|
|
/* Inode location stuff */
|
|
|
|
xfs_ino_t i_ino; /* inode number (agno/agino)*/
|
|
|
|
xfs_daddr_t i_blkno; /* blkno of inode buffer */
|
|
|
|
ushort i_len; /* len of inode buffer */
|
|
|
|
ushort i_boffset; /* off of inode in buffer */
|
|
|
|
|
|
|
|
/* Extent information. */
|
|
|
|
xfs_ifork_t *i_afp; /* attribute fork pointer */
|
|
|
|
xfs_ifork_t i_df; /* data fork */
|
|
|
|
|
|
|
|
/* Transaction and locking information. */
|
|
|
|
struct xfs_trans *i_transp; /* ptr to owning transaction*/
|
|
|
|
struct xfs_inode_log_item *i_itemp; /* logging information */
|
|
|
|
mrlock_t i_lock; /* inode lock */
|
|
|
|
mrlock_t i_iolock; /* inode IO lock */
|
|
|
|
sema_t i_flock; /* inode flush lock */
|
|
|
|
atomic_t i_pincount; /* inode pin count */
|
|
|
|
wait_queue_head_t i_ipin_wait; /* inode pinning wait queue */
|
2006-09-28 03:06:03 +02:00
|
|
|
spinlock_t i_flags_lock; /* inode i_flags lock */
|
2005-04-17 00:20:36 +02:00
|
|
|
#ifdef HAVE_REFCACHE
|
|
|
|
struct xfs_inode **i_refcache; /* ptr to entry in ref cache */
|
|
|
|
struct xfs_inode *i_release; /* inode to unref */
|
|
|
|
#endif
|
|
|
|
/* I/O state */
|
|
|
|
xfs_iocore_t i_iocore; /* I/O core */
|
|
|
|
|
|
|
|
/* Miscellaneous state. */
|
|
|
|
unsigned short i_flags; /* see defined flags below */
|
|
|
|
unsigned char i_update_core; /* timestamps/size is dirty */
|
|
|
|
unsigned char i_update_size; /* di_size field is dirty */
|
|
|
|
unsigned int i_gen; /* generation count */
|
|
|
|
unsigned int i_delayed_blks; /* count of delay alloc blks */
|
|
|
|
|
|
|
|
xfs_dinode_core_t i_d; /* most of ondisk inode */
|
|
|
|
xfs_chashlist_t *i_chash; /* cluster hash list header */
|
|
|
|
struct xfs_inode *i_cnext; /* cluster hash link forward */
|
|
|
|
struct xfs_inode *i_cprev; /* cluster hash link backward */
|
|
|
|
|
[XFS] Fix to prevent the notorious 'NULL files' problem after a crash.
The problem that has been addressed is that of synchronising updates of
the file size with writes that extend a file. Without the fix the update
of a file's size, as a result of a write beyond eof, is independent of
when the cached data is flushed to disk. Often the file size update would
be written to the filesystem log before the data is flushed to disk. When
a system crashes between these two events and the filesystem log is
replayed on mount the file's size will be set but since the contents never
made it to disk the file is full of holes. If some of the cached data was
flushed to disk then it may just be a section of the file at the end that
has holes.
There are existing fixes to help alleviate this problem, particularly in
the case where a file has been truncated, that force cached data to be
flushed to disk when the file is closed. If the system crashes while the
file(s) are still open then this flushing will never occur.
The fix that we have implemented is to introduce a second file size,
called the in-memory file size, that represents the current file size as
viewed by the user. The existing file size, called the on-disk file size,
is the one that get's written to the filesystem log and we only update it
when it is safe to do so. When we write to a file beyond eof we only
update the in- memory file size in the write operation. Later when the I/O
operation, that flushes the cached data to disk completes, an I/O
completion routine will update the on-disk file size. The on-disk file
size will be updated to the maximum offset of the I/O or to the value of
the in-memory file size if the I/O includes eof.
SGI-PV: 958522
SGI-Modid: xfs-linux-melb:xfs-kern:28322a
Signed-off-by: Lachlan McIlroy <lachlan@sgi.com>
Signed-off-by: David Chinner <dgc@sgi.com>
Signed-off-by: Tim Shimmin <tes@sgi.com>
2007-05-08 05:49:46 +02:00
|
|
|
xfs_fsize_t i_size; /* in-memory size */
|
2005-04-17 00:20:36 +02:00
|
|
|
/* Trace buffers per inode. */
|
|
|
|
#ifdef XFS_BMAP_TRACE
|
|
|
|
struct ktrace *i_xtrace; /* inode extent list trace */
|
|
|
|
#endif
|
|
|
|
#ifdef XFS_BMBT_TRACE
|
|
|
|
struct ktrace *i_btrace; /* inode bmap btree trace */
|
|
|
|
#endif
|
|
|
|
#ifdef XFS_RW_TRACE
|
|
|
|
struct ktrace *i_rwtrace; /* inode read/write trace */
|
|
|
|
#endif
|
|
|
|
#ifdef XFS_ILOCK_TRACE
|
|
|
|
struct ktrace *i_lock_trace; /* inode lock/unlock trace */
|
|
|
|
#endif
|
|
|
|
#ifdef XFS_DIR2_TRACE
|
|
|
|
struct ktrace *i_dir_trace; /* inode directory trace */
|
|
|
|
#endif
|
|
|
|
} xfs_inode_t;
|
|
|
|
|
[XFS] Fix to prevent the notorious 'NULL files' problem after a crash.
The problem that has been addressed is that of synchronising updates of
the file size with writes that extend a file. Without the fix the update
of a file's size, as a result of a write beyond eof, is independent of
when the cached data is flushed to disk. Often the file size update would
be written to the filesystem log before the data is flushed to disk. When
a system crashes between these two events and the filesystem log is
replayed on mount the file's size will be set but since the contents never
made it to disk the file is full of holes. If some of the cached data was
flushed to disk then it may just be a section of the file at the end that
has holes.
There are existing fixes to help alleviate this problem, particularly in
the case where a file has been truncated, that force cached data to be
flushed to disk when the file is closed. If the system crashes while the
file(s) are still open then this flushing will never occur.
The fix that we have implemented is to introduce a second file size,
called the in-memory file size, that represents the current file size as
viewed by the user. The existing file size, called the on-disk file size,
is the one that get's written to the filesystem log and we only update it
when it is safe to do so. When we write to a file beyond eof we only
update the in- memory file size in the write operation. Later when the I/O
operation, that flushes the cached data to disk completes, an I/O
completion routine will update the on-disk file size. The on-disk file
size will be updated to the maximum offset of the I/O or to the value of
the in-memory file size if the I/O includes eof.
SGI-PV: 958522
SGI-Modid: xfs-linux-melb:xfs-kern:28322a
Signed-off-by: Lachlan McIlroy <lachlan@sgi.com>
Signed-off-by: David Chinner <dgc@sgi.com>
Signed-off-by: Tim Shimmin <tes@sgi.com>
2007-05-08 05:49:46 +02:00
|
|
|
#define XFS_ISIZE(ip) (((ip)->i_d.di_mode & S_IFMT) == S_IFREG) ? \
|
|
|
|
(ip)->i_size : (ip)->i_d.di_size;
|
2006-11-11 08:04:54 +01:00
|
|
|
|
|
|
|
/*
|
|
|
|
* 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;
|
|
|
|
}
|
2005-04-17 00:20:36 +02:00
|
|
|
#endif /* __KERNEL__ */
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Fork handling.
|
|
|
|
*/
|
2005-11-02 04:38:42 +01:00
|
|
|
#define XFS_IFORK_PTR(ip,w) \
|
|
|
|
((w) == XFS_DATA_FORK ? &(ip)->i_df : (ip)->i_afp)
|
2005-04-17 00:20:36 +02:00
|
|
|
#define XFS_IFORK_Q(ip) XFS_CFORK_Q(&(ip)->i_d)
|
|
|
|
#define XFS_IFORK_DSIZE(ip) XFS_CFORK_DSIZE(&ip->i_d, ip->i_mount)
|
|
|
|
#define XFS_IFORK_ASIZE(ip) XFS_CFORK_ASIZE(&ip->i_d, ip->i_mount)
|
|
|
|
#define XFS_IFORK_SIZE(ip,w) XFS_CFORK_SIZE(&ip->i_d, ip->i_mount, w)
|
|
|
|
#define XFS_IFORK_FORMAT(ip,w) XFS_CFORK_FORMAT(&ip->i_d, w)
|
|
|
|
#define XFS_IFORK_FMT_SET(ip,w,n) XFS_CFORK_FMT_SET(&ip->i_d, w, n)
|
|
|
|
#define XFS_IFORK_NEXTENTS(ip,w) XFS_CFORK_NEXTENTS(&ip->i_d, w)
|
|
|
|
#define XFS_IFORK_NEXT_SET(ip,w,n) XFS_CFORK_NEXT_SET(&ip->i_d, w, n)
|
|
|
|
|
|
|
|
|
|
|
|
#ifdef __KERNEL__
|
|
|
|
|
|
|
|
/*
|
|
|
|
* In-core inode flags.
|
|
|
|
*/
|
|
|
|
#define XFS_IGRIO 0x0001 /* inode used for guaranteed rate i/o */
|
|
|
|
#define XFS_IUIOSZ 0x0002 /* inode i/o sizes have been explicitly set */
|
|
|
|
#define XFS_IQUIESCE 0x0004 /* we have started quiescing for this inode */
|
|
|
|
#define XFS_IRECLAIM 0x0008 /* we have started reclaiming this inode */
|
|
|
|
#define XFS_ISTALE 0x0010 /* inode has been staled */
|
|
|
|
#define XFS_IRECLAIMABLE 0x0020 /* inode can be reclaimed */
|
|
|
|
#define XFS_INEW 0x0040
|
2007-07-11 03:09:12 +02:00
|
|
|
#define XFS_IFILESTREAM 0x0080 /* inode is in a filestream directory */
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Flags for inode locking.
|
2007-05-08 05:50:19 +02:00
|
|
|
* Bit ranges: 1<<1 - 1<<16-1 -- iolock/ilock modes (bitfield)
|
|
|
|
* 1<<16 - 1<<32-1 -- lockdep annotation (integers)
|
2005-04-17 00:20:36 +02:00
|
|
|
*/
|
2007-05-08 05:50:19 +02:00
|
|
|
#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_IUNLOCK_NONOTIFY (1<<4)
|
|
|
|
/* #define XFS_IOLOCK_NESTED (1<<5) */
|
|
|
|
#define XFS_EXTENT_TOKEN_RD (1<<6)
|
|
|
|
#define XFS_SIZE_TOKEN_RD (1<<7)
|
2005-04-17 00:20:36 +02:00
|
|
|
#define XFS_EXTSIZE_RD (XFS_EXTENT_TOKEN_RD|XFS_SIZE_TOKEN_RD)
|
2007-05-08 05:50:19 +02:00
|
|
|
#define XFS_WILLLEND (1<<8) /* Always acquire tokens for lending */
|
2005-04-17 00:20:36 +02:00
|
|
|
#define XFS_EXTENT_TOKEN_WR (XFS_EXTENT_TOKEN_RD | XFS_WILLLEND)
|
|
|
|
#define XFS_SIZE_TOKEN_WR (XFS_SIZE_TOKEN_RD | XFS_WILLLEND)
|
|
|
|
#define XFS_EXTSIZE_WR (XFS_EXTSIZE_RD | XFS_WILLLEND)
|
2007-05-08 05:50:19 +02:00
|
|
|
/* TODO:XFS_SIZE_TOKEN_WANT (1<<9) */
|
2005-04-17 00:20:36 +02:00
|
|
|
|
2007-05-08 05:50:19 +02:00
|
|
|
#define XFS_LOCK_MASK (XFS_IOLOCK_EXCL | XFS_IOLOCK_SHARED \
|
|
|
|
| XFS_ILOCK_EXCL | XFS_ILOCK_SHARED \
|
|
|
|
| XFS_EXTENT_TOKEN_RD | XFS_SIZE_TOKEN_RD \
|
|
|
|
| XFS_WILLLEND)
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Flags for lockdep annotations.
|
|
|
|
*
|
|
|
|
* XFS_I[O]LOCK_PARENT - for operations that require locking two inodes
|
|
|
|
* (ie directory operations that require locking a directory inode and
|
|
|
|
* an entry inode). The first inode gets locked with this flag so it
|
|
|
|
* gets a lockdep subclass of 1 and the second lock will have a lockdep
|
|
|
|
* subclass of 0.
|
|
|
|
*
|
|
|
|
* XFS_I[O]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 2, the
|
|
|
|
* second lock will have a lockdep subclass of 3, and so on.
|
|
|
|
*/
|
|
|
|
#define XFS_IOLOCK_SHIFT 16
|
|
|
|
#define XFS_IOLOCK_PARENT (1 << XFS_IOLOCK_SHIFT)
|
|
|
|
#define XFS_IOLOCK_INUMORDER (2 << XFS_IOLOCK_SHIFT)
|
|
|
|
|
|
|
|
#define XFS_ILOCK_SHIFT 24
|
|
|
|
#define XFS_ILOCK_PARENT (1 << XFS_ILOCK_SHIFT)
|
|
|
|
#define XFS_ILOCK_INUMORDER (2 << 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)
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Flags for xfs_iflush()
|
|
|
|
*/
|
|
|
|
#define XFS_IFLUSH_DELWRI_ELSE_SYNC 1
|
|
|
|
#define XFS_IFLUSH_DELWRI_ELSE_ASYNC 2
|
|
|
|
#define XFS_IFLUSH_SYNC 3
|
|
|
|
#define XFS_IFLUSH_ASYNC 4
|
|
|
|
#define XFS_IFLUSH_DELWRI 5
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Flags for xfs_itruncate_start().
|
|
|
|
*/
|
|
|
|
#define XFS_ITRUNC_DEFINITE 0x1
|
|
|
|
#define XFS_ITRUNC_MAYBE 0x2
|
|
|
|
|
|
|
|
#define XFS_ITOV(ip) BHV_TO_VNODE(XFS_ITOBHV(ip))
|
|
|
|
#define XFS_ITOV_NULL(ip) BHV_TO_VNODE_NULL(XFS_ITOBHV(ip))
|
|
|
|
#define XFS_ITOBHV(ip) ((struct bhv_desc *)(&((ip)->i_bhv_desc)))
|
2005-11-02 04:38:42 +01:00
|
|
|
#define XFS_BHVTOI(bhvp) ((xfs_inode_t *)((char *)(bhvp) - \
|
|
|
|
(char *)&(((xfs_inode_t *)0)->i_bhv_desc)))
|
2005-04-17 00:20:36 +02:00
|
|
|
#define BHV_IS_XFS(bdp) (BHV_OPS(bdp) == &xfs_vnodeops)
|
|
|
|
|
|
|
|
/*
|
|
|
|
* 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, vfsp) \
|
|
|
|
(((vfsp)->vfs_flag & VFS_GRPID) || ((pip)->i_d.di_mode & S_ISGID))
|
|
|
|
|
|
|
|
/*
|
2006-09-28 03:02:23 +02:00
|
|
|
* Flags for xfs_iget()
|
2005-04-17 00:20:36 +02:00
|
|
|
*/
|
2006-09-28 03:02:23 +02:00
|
|
|
#define XFS_IGET_CREATE 0x1
|
|
|
|
#define XFS_IGET_BULKSTAT 0x2
|
2005-04-17 00:20:36 +02:00
|
|
|
|
2006-09-28 03:02:23 +02:00
|
|
|
/*
|
|
|
|
* xfs_iget.c prototypes.
|
|
|
|
*/
|
2005-04-17 00:20:36 +02:00
|
|
|
void xfs_ihash_init(struct xfs_mount *);
|
|
|
|
void xfs_ihash_free(struct xfs_mount *);
|
|
|
|
void xfs_chash_init(struct xfs_mount *);
|
|
|
|
void xfs_chash_free(struct xfs_mount *);
|
|
|
|
xfs_inode_t *xfs_inode_incore(struct xfs_mount *, xfs_ino_t,
|
|
|
|
struct xfs_trans *);
|
2006-06-09 09:00:52 +02:00
|
|
|
void xfs_inode_lock_init(xfs_inode_t *, struct bhv_vnode *);
|
2005-04-17 00:20:36 +02:00
|
|
|
int xfs_iget(struct xfs_mount *, struct xfs_trans *, xfs_ino_t,
|
|
|
|
uint, uint, xfs_inode_t **, xfs_daddr_t);
|
|
|
|
void xfs_iput(xfs_inode_t *, uint);
|
|
|
|
void xfs_iput_new(xfs_inode_t *, uint);
|
|
|
|
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);
|
|
|
|
void xfs_iflock(xfs_inode_t *);
|
|
|
|
int xfs_iflock_nowait(xfs_inode_t *);
|
|
|
|
uint xfs_ilock_map_shared(xfs_inode_t *);
|
|
|
|
void xfs_iunlock_map_shared(xfs_inode_t *, uint);
|
|
|
|
void xfs_ifunlock(xfs_inode_t *);
|
|
|
|
void xfs_ireclaim(xfs_inode_t *);
|
|
|
|
int xfs_finish_reclaim(xfs_inode_t *, int, int);
|
|
|
|
int xfs_finish_reclaim_all(struct xfs_mount *, int);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* xfs_inode.c prototypes.
|
|
|
|
*/
|
|
|
|
int xfs_itobp(struct xfs_mount *, struct xfs_trans *,
|
|
|
|
xfs_inode_t *, xfs_dinode_t **, struct xfs_buf **,
|
2006-03-17 07:26:04 +01:00
|
|
|
xfs_daddr_t, uint);
|
2005-04-17 00:20:36 +02:00
|
|
|
int xfs_iread(struct xfs_mount *, struct xfs_trans *, xfs_ino_t,
|
2006-09-28 03:02:23 +02:00
|
|
|
xfs_inode_t **, xfs_daddr_t, uint);
|
2005-04-17 00:20:36 +02:00
|
|
|
int xfs_iread_extents(struct xfs_trans *, xfs_inode_t *, int);
|
2005-05-05 22:25:00 +02:00
|
|
|
int xfs_ialloc(struct xfs_trans *, xfs_inode_t *, mode_t,
|
|
|
|
xfs_nlink_t, xfs_dev_t, struct cred *, xfs_prid_t,
|
|
|
|
int, struct xfs_buf **, boolean_t *, xfs_inode_t **);
|
2005-04-17 00:20:36 +02:00
|
|
|
void xfs_xlate_dinode_core(xfs_caddr_t, struct xfs_dinode_core *,
|
|
|
|
int);
|
|
|
|
uint xfs_ip2xflags(struct xfs_inode *);
|
|
|
|
uint xfs_dic2xflags(struct xfs_dinode_core *);
|
|
|
|
int xfs_ifree(struct xfs_trans *, xfs_inode_t *,
|
|
|
|
struct xfs_bmap_free *);
|
2007-05-08 05:49:27 +02:00
|
|
|
int xfs_itruncate_start(xfs_inode_t *, uint, xfs_fsize_t);
|
2005-04-17 00:20:36 +02:00
|
|
|
int xfs_itruncate_finish(struct xfs_trans **, xfs_inode_t *,
|
|
|
|
xfs_fsize_t, int, int);
|
|
|
|
int xfs_iunlink(struct xfs_trans *, xfs_inode_t *);
|
|
|
|
int xfs_igrow_start(xfs_inode_t *, xfs_fsize_t, struct cred *);
|
|
|
|
void xfs_igrow_finish(struct xfs_trans *, xfs_inode_t *,
|
|
|
|
xfs_fsize_t, int);
|
|
|
|
|
|
|
|
void xfs_idestroy_fork(xfs_inode_t *, int);
|
|
|
|
void xfs_idestroy(xfs_inode_t *);
|
|
|
|
void xfs_idata_realloc(xfs_inode_t *, int, int);
|
|
|
|
void xfs_iextract(xfs_inode_t *);
|
|
|
|
void xfs_iext_realloc(xfs_inode_t *, int, int);
|
|
|
|
void xfs_iroot_realloc(xfs_inode_t *, int, int);
|
|
|
|
void xfs_ipin(xfs_inode_t *);
|
|
|
|
void xfs_iunpin(xfs_inode_t *);
|
|
|
|
int xfs_iextents_copy(xfs_inode_t *, xfs_bmbt_rec_t *, int);
|
|
|
|
int xfs_iflush(xfs_inode_t *, uint);
|
2005-06-21 07:37:17 +02:00
|
|
|
void xfs_iflush_all(struct xfs_mount *);
|
2005-04-17 00:20:36 +02:00
|
|
|
int xfs_iaccess(xfs_inode_t *, mode_t, cred_t *);
|
|
|
|
uint xfs_iroundup(uint);
|
|
|
|
void xfs_ichgtime(xfs_inode_t *, int);
|
|
|
|
xfs_fsize_t xfs_file_last_byte(xfs_inode_t *);
|
|
|
|
void xfs_lock_inodes(xfs_inode_t **, int, int, uint);
|
|
|
|
|
2006-06-09 09:00:52 +02:00
|
|
|
xfs_inode_t *xfs_vtoi(struct bhv_vnode *vp);
|
2006-01-11 10:58:44 +01:00
|
|
|
|
2006-01-11 05:35:17 +01:00
|
|
|
void xfs_synchronize_atime(xfs_inode_t *);
|
|
|
|
|
2006-03-14 03:29:52 +01:00
|
|
|
xfs_bmbt_rec_t *xfs_iext_get_ext(xfs_ifork_t *, xfs_extnum_t);
|
|
|
|
void xfs_iext_insert(xfs_ifork_t *, xfs_extnum_t, xfs_extnum_t,
|
|
|
|
xfs_bmbt_irec_t *);
|
|
|
|
void xfs_iext_add(xfs_ifork_t *, xfs_extnum_t, int);
|
2006-03-14 03:30:23 +01:00
|
|
|
void xfs_iext_add_indirect_multi(xfs_ifork_t *, int, xfs_extnum_t, int);
|
2006-03-14 03:29:52 +01:00
|
|
|
void xfs_iext_remove(xfs_ifork_t *, xfs_extnum_t, 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);
|
2006-03-14 03:30:23 +01:00
|
|
|
void xfs_iext_remove_indirect(xfs_ifork_t *, xfs_extnum_t, int);
|
2006-03-14 03:29:52 +01:00
|
|
|
void xfs_iext_realloc_direct(xfs_ifork_t *, int);
|
2006-03-14 03:30:23 +01:00
|
|
|
void xfs_iext_realloc_indirect(xfs_ifork_t *, int);
|
|
|
|
void xfs_iext_indirect_to_direct(xfs_ifork_t *);
|
2006-03-14 03:29:52 +01:00
|
|
|
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] There are a few problems with the new
xfs_bmap_search_multi_extents() wrapper function that I introduced in mod
xfs-linux:xfs-kern:207393a. The function was added as a wrapper around
xfs_bmap_do_search_extents() to avoid breaking the top-of-tree CXFS
interface. The idea of the function was basically to extract the target
extent buffer (if muli- level extent allocation mode), then call
xfs_bmap_do_search_extents() with either a pointer to the first extent in
the target buffer or a pointer to the first extent in the file, depending
on which extent mode was being used. However, in addition to locating the
target extent record for block bno, xfs_bmap_do_search_extents() also sets
four parameters needed by the caller: *lastx, *eofp, *gotp, *prevp.
Passing only the target extent buffer to xfs_bmap_do_search_extents()
causes *eofp to be set incorrectly if the extent is at the end of the
target list but there are actually more extents in the next er_extbuf.
Likewise, if the extent is the first one in the buffer but NOT the first
in the file, *prevp is incorrectly set to NULL. Adding the needed
functionality to xfs_bmap_search_multi_extents() to re-set any incorrectly
set fields is redundant and makes the call to xfs_bmap_do_search_extents()
not make much sense when multi-level extent allocation mode is being used.
This mod basically extracts the two functional components from
xfs_bmap_do_search_extents(), with the intent of obsoleting/removing
xfs_bmap_do_search_extents() after the CXFS mult-level in-core extent
changes are checked in. The two components are: 1) The binary search to
locate the target extent record, and 2) Setting the four parameters needed
by the caller (*lastx, *eofp, *gotp, *prevp). Component 1: I created a
new function in xfs_inode.c called xfs_iext_bno_to_ext(), which executes
the binary search to find the target extent record.
xfs_bmap_search_multi_extents() has been modified to call
xfs_iext_bno_to_ext() rather than xfs_bmap_do_search_extents(). Component
2: The parameter setting functionality has been added to
xfs_bmap_search_multi_extents(), eliminating the need for
xfs_bmap_do_search_extents(). These changes make the removal of
xfs_bmap_do_search_extents() trival once the CXFS changes are in place.
They also allow us to maintain the current XFS interface, using the new
search function introduced in mod xfs-linux:xfs-kern:207393a.
SGI-PV: 928864
SGI-Modid: xfs-linux-melb:xfs-kern:207866a
Signed-off-by: Mandy Kirkconnell <alkirkco@sgi.com>
Signed-off-by: Nathan Scott <nathans@sgi.com>
2006-03-17 07:25:04 +01:00
|
|
|
xfs_bmbt_rec_t *xfs_iext_bno_to_ext(xfs_ifork_t *, xfs_fileoff_t, int *);
|
2006-03-14 03:30:23 +01:00
|
|
|
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);
|
2006-03-14 03:29:52 +01:00
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
#define xfs_ipincount(ip) ((unsigned int) atomic_read(&ip->i_pincount))
|
|
|
|
|
|
|
|
#ifdef DEBUG
|
|
|
|
void xfs_isize_check(struct xfs_mount *, xfs_inode_t *, xfs_fsize_t);
|
|
|
|
#else /* DEBUG */
|
|
|
|
#define xfs_isize_check(mp, ip, isize)
|
|
|
|
#endif /* DEBUG */
|
|
|
|
|
|
|
|
#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_chashlist_zone;
|
|
|
|
extern struct kmem_zone *xfs_ifork_zone;
|
|
|
|
extern struct kmem_zone *xfs_inode_zone;
|
|
|
|
extern struct kmem_zone *xfs_ili_zone;
|
|
|
|
|
|
|
|
#endif /* __KERNEL__ */
|
|
|
|
|
|
|
|
#endif /* __XFS_INODE_H__ */
|