if ((flags & DIO_LOCKING) && iov_iter_rw(iter) == READ)
inode_unlock(inode);
- if ((retval > 0) && end_io)
- end_io(iocb, pos, retval, bh.b_private);
+ if (end_io) {
+ int err;
+
+ err = end_io(iocb, pos, retval, bh.b_private);
+ if (err)
+ retval = err;
+ }
if (!(flags & DIO_SKIP_DIO_COUNT))
inode_dio_end(inode);
if (ret == 0)
ret = transferred;
- if (dio->end_io && dio->result)
- dio->end_io(dio->iocb, offset, transferred, dio->private);
+ if (dio->end_io) {
+ int err;
+
+ err = dio->end_io(dio->iocb, offset, ret, dio->private);
+ if (err)
+ ret = err;
+ }
if (!(dio->flags & DIO_SKIP_DIO_COUNT))
inode_dio_end(dio->inode);
}
#endif
-static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
+static int ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
ssize_t size, void *private)
{
ext4_io_end_t *io_end = iocb->private;
+ if (size <= 0)
+ return 0;
+
/* if not async direct IO just return */
if (!io_end)
- return;
+ return 0;
ext_debug("ext4_end_io_dio(): io_end 0x%p "
"for inode %lu, iocb 0x%p, offset %llu, size %zd\n",
io_end->offset = offset;
io_end->size = size;
ext4_put_io_end(io_end);
+
+ return 0;
}
/*
* particularly interested in the aio/dio case. We use the rw_lock DLM lock
* to protect io on one node from truncation on another.
*/
-static void ocfs2_dio_end_io(struct kiocb *iocb,
+static int ocfs2_dio_end_io(struct kiocb *iocb,
loff_t offset,
ssize_t bytes,
void *private)
struct inode *inode = file_inode(iocb->ki_filp);
int level;
+ if (bytes <= 0)
+ return 0;
+
/* this io's submitter should not have unlocked this before we could */
BUG_ON(!ocfs2_iocb_is_rw_locked(iocb));
level = ocfs2_iocb_rw_locked_level(iocb);
ocfs2_rw_unlock(inode, level);
}
+
+ return 0;
}
static int ocfs2_releasepage(struct page *page, gfp_t wait)
xfs_extent_busy_insert(cur->bc_tp, be32_to_cpu(agf->agf_seqno), bno, 1,
XFS_EXTENT_BUSY_SKIP_DISCARD);
xfs_trans_agbtree_delta(cur->bc_tp, -1);
-
- xfs_trans_binval(cur->bc_tp, bp);
return 0;
}
* Small attribute lists are packed as tightly as possible so as
* to fit into the literal area of the inode.
*/
-
-/*
- * Entries are packed toward the top as tight as possible.
- */
-typedef struct xfs_attr_shortform {
- struct xfs_attr_sf_hdr { /* constant-structure header block */
- __be16 totsize; /* total bytes in shortform list */
- __u8 count; /* count of active entries */
- } hdr;
- struct xfs_attr_sf_entry {
- __uint8_t namelen; /* actual length of name (no NULL) */
- __uint8_t valuelen; /* actual length of value (no NULL) */
- __uint8_t flags; /* flags bits (see xfs_attr_leaf.h) */
- __uint8_t nameval[1]; /* name & value bytes concatenated */
- } list[1]; /* variable sized array */
-} xfs_attr_shortform_t;
typedef struct xfs_attr_sf_hdr xfs_attr_sf_hdr_t;
typedef struct xfs_attr_sf_entry xfs_attr_sf_entry_t;
* We don't want to deal with the case of keeping inode data inline yet.
* So sending the data fork of a regular inode is invalid.
*/
- ASSERT(!(S_ISREG(ip->i_d.di_mode) && whichfork == XFS_DATA_FORK));
+ ASSERT(!(S_ISREG(VFS_I(ip)->i_mode) && whichfork == XFS_DATA_FORK));
ifp = XFS_IFORK_PTR(ip, whichfork);
ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL);
if (ip->i_df.if_bytes <= XFS_IFORK_DSIZE(ip))
return 0;
- if (S_ISDIR(ip->i_d.di_mode)) {
+ if (S_ISDIR(VFS_I(ip)->i_mode)) {
memset(&dargs, 0, sizeof(dargs));
dargs.geo = ip->i_mount->m_dir_geo;
dargs.dp = ip;
return xfs_dir2_sf_to_block(&dargs);
}
- if (S_ISLNK(ip->i_d.di_mode))
+ if (S_ISLNK(VFS_I(ip)->i_mode))
return xfs_bmap_local_to_extents(tp, ip, firstblock, 1,
flags, XFS_DATA_FORK,
xfs_symlink_local_to_remote);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
- xfs_trans_binval(tp, bp);
return 0;
}
return true;
}
+static int
+xfs_btree_free_block(
+ struct xfs_btree_cur *cur,
+ struct xfs_buf *bp)
+{
+ int error;
+
+ error = cur->bc_ops->free_block(cur, bp);
+ if (!error) {
+ xfs_trans_binval(cur->bc_tp, bp);
+ XFS_BTREE_STATS_INC(cur, free);
+ }
+ return error;
+}
+
/*
* Delete the btree cursor.
*/
int level;
int index;
int numrecs;
+ int error;
#ifdef DEBUG
union xfs_btree_ptr ptr;
int i;
cpp = xfs_btree_ptr_addr(cur, 1, cblock);
#ifdef DEBUG
for (i = 0; i < numrecs; i++) {
- int error;
-
error = xfs_btree_check_ptr(cur, cpp, i, level - 1);
if (error) {
XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
#endif
xfs_btree_copy_ptrs(cur, pp, cpp, numrecs);
- cur->bc_ops->free_block(cur, cbp);
- XFS_BTREE_STATS_INC(cur, free);
+ error = xfs_btree_free_block(cur, cbp);
+ if (error) {
+ XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
+ return error;
+ }
cur->bc_bufs[level - 1] = NULL;
be16_add_cpu(&block->bb_level, -1);
*/
cur->bc_ops->set_root(cur, newroot, -1);
- error = cur->bc_ops->free_block(cur, bp);
+ error = xfs_btree_free_block(cur, bp);
if (error) {
XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
return error;
}
- XFS_BTREE_STATS_INC(cur, free);
-
cur->bc_bufs[level] = NULL;
cur->bc_ra[level] = 0;
cur->bc_nlevels--;
}
/* Free the deleted block. */
- error = cur->bc_ops->free_block(cur, rbp);
+ error = xfs_btree_free_block(cur, rbp);
if (error)
goto error0;
- XFS_BTREE_STATS_INC(cur, free);
/*
* If we joined with the left neighbor, set the buffer in the
*/
#define XFS_ATTR_LEAF_MAPSIZE 3 /* how many freespace slots */
+/*
+ * Entries are packed toward the top as tight as possible.
+ */
+typedef struct xfs_attr_shortform {
+ struct xfs_attr_sf_hdr { /* constant-structure header block */
+ __be16 totsize; /* total bytes in shortform list */
+ __u8 count; /* count of active entries */
+ } hdr;
+ struct xfs_attr_sf_entry {
+ __uint8_t namelen; /* actual length of name (no NULL) */
+ __uint8_t valuelen; /* actual length of value (no NULL) */
+ __uint8_t flags; /* flags bits (see xfs_attr_leaf.h) */
+ __uint8_t nameval[1]; /* name & value bytes concatenated */
+ } list[1]; /* variable sized array */
+} xfs_attr_shortform_t;
+
typedef struct xfs_attr_leaf_map { /* RLE map of free bytes */
__be16 base; /* base of free region */
__be16 size; /* length of free region */
{
xfs_dir2_sf_hdr_t *sfp;
- ASSERT(S_ISDIR(dp->i_d.di_mode));
+ ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
if (dp->i_d.di_size == 0) /* might happen during shutdown. */
return 1;
if (dp->i_d.di_size > XFS_IFORK_DSIZE(dp))
struct xfs_da_args *args;
int error;
- ASSERT(S_ISDIR(dp->i_d.di_mode));
+ ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
error = xfs_dir_ino_validate(tp->t_mountp, pdp->i_ino);
if (error)
return error;
int rval;
int v; /* type-checking value */
- ASSERT(S_ISDIR(dp->i_d.di_mode));
+ ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
if (inum) {
rval = xfs_dir_ino_validate(tp->t_mountp, inum);
if (rval)
int v; /* type-checking value */
int lock_mode;
- ASSERT(S_ISDIR(dp->i_d.di_mode));
+ ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
XFS_STATS_INC(dp->i_mount, xs_dir_lookup);
/*
int rval;
int v; /* type-checking value */
- ASSERT(S_ISDIR(dp->i_d.di_mode));
+ ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
XFS_STATS_INC(dp->i_mount, xs_dir_remove);
args = kmem_zalloc(sizeof(*args), KM_SLEEP | KM_NOFS);
int rval;
int v; /* type-checking value */
- ASSERT(S_ISDIR(dp->i_d.di_mode));
+ ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
rval = xfs_dir_ino_validate(tp->t_mountp, inum);
if (rval)
struct xfs_btree_cur *cur,
struct xfs_buf *bp)
{
- xfs_fsblock_t fsbno;
- int error;
-
- fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, XFS_BUF_ADDR(bp));
- error = xfs_free_extent(cur->bc_tp, fsbno, 1);
- if (error)
- return error;
-
- xfs_trans_binval(cur->bc_tp, bp);
- return error;
+ return xfs_free_extent(cur->bc_tp,
+ XFS_DADDR_TO_FSB(cur->bc_mp, XFS_BUF_ADDR(bp)), 1);
}
STATIC int
}
void
-xfs_dinode_from_disk(
- xfs_icdinode_t *to,
- xfs_dinode_t *from)
+xfs_inode_from_disk(
+ struct xfs_inode *ip,
+ struct xfs_dinode *from)
{
- to->di_magic = be16_to_cpu(from->di_magic);
- to->di_mode = be16_to_cpu(from->di_mode);
- to->di_version = from ->di_version;
+ struct xfs_icdinode *to = &ip->i_d;
+ struct inode *inode = VFS_I(ip);
+
+
+ /*
+ * Convert v1 inodes immediately to v2 inode format as this is the
+ * minimum inode version format we support in the rest of the code.
+ */
+ to->di_version = from->di_version;
+ if (to->di_version == 1) {
+ set_nlink(inode, be16_to_cpu(from->di_onlink));
+ to->di_projid_lo = 0;
+ to->di_projid_hi = 0;
+ to->di_version = 2;
+ } else {
+ set_nlink(inode, be32_to_cpu(from->di_nlink));
+ to->di_projid_lo = be16_to_cpu(from->di_projid_lo);
+ to->di_projid_hi = be16_to_cpu(from->di_projid_hi);
+ }
+
to->di_format = from->di_format;
- to->di_onlink = be16_to_cpu(from->di_onlink);
to->di_uid = be32_to_cpu(from->di_uid);
to->di_gid = be32_to_cpu(from->di_gid);
- to->di_nlink = be32_to_cpu(from->di_nlink);
- to->di_projid_lo = be16_to_cpu(from->di_projid_lo);
- to->di_projid_hi = be16_to_cpu(from->di_projid_hi);
- memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad));
to->di_flushiter = be16_to_cpu(from->di_flushiter);
- to->di_atime.t_sec = be32_to_cpu(from->di_atime.t_sec);
- to->di_atime.t_nsec = be32_to_cpu(from->di_atime.t_nsec);
- to->di_mtime.t_sec = be32_to_cpu(from->di_mtime.t_sec);
- to->di_mtime.t_nsec = be32_to_cpu(from->di_mtime.t_nsec);
- to->di_ctime.t_sec = be32_to_cpu(from->di_ctime.t_sec);
- to->di_ctime.t_nsec = be32_to_cpu(from->di_ctime.t_nsec);
+
+ /*
+ * Time is signed, so need to convert to signed 32 bit before
+ * storing in inode timestamp which may be 64 bit. Otherwise
+ * a time before epoch is converted to a time long after epoch
+ * on 64 bit systems.
+ */
+ inode->i_atime.tv_sec = (int)be32_to_cpu(from->di_atime.t_sec);
+ inode->i_atime.tv_nsec = (int)be32_to_cpu(from->di_atime.t_nsec);
+ inode->i_mtime.tv_sec = (int)be32_to_cpu(from->di_mtime.t_sec);
+ inode->i_mtime.tv_nsec = (int)be32_to_cpu(from->di_mtime.t_nsec);
+ inode->i_ctime.tv_sec = (int)be32_to_cpu(from->di_ctime.t_sec);
+ inode->i_ctime.tv_nsec = (int)be32_to_cpu(from->di_ctime.t_nsec);
+ inode->i_generation = be32_to_cpu(from->di_gen);
+ inode->i_mode = be16_to_cpu(from->di_mode);
+
to->di_size = be64_to_cpu(from->di_size);
to->di_nblocks = be64_to_cpu(from->di_nblocks);
to->di_extsize = be32_to_cpu(from->di_extsize);
to->di_dmevmask = be32_to_cpu(from->di_dmevmask);
to->di_dmstate = be16_to_cpu(from->di_dmstate);
to->di_flags = be16_to_cpu(from->di_flags);
- to->di_gen = be32_to_cpu(from->di_gen);
if (to->di_version == 3) {
- to->di_changecount = be64_to_cpu(from->di_changecount);
+ inode->i_version = be64_to_cpu(from->di_changecount);
to->di_crtime.t_sec = be32_to_cpu(from->di_crtime.t_sec);
to->di_crtime.t_nsec = be32_to_cpu(from->di_crtime.t_nsec);
to->di_flags2 = be64_to_cpu(from->di_flags2);
- to->di_ino = be64_to_cpu(from->di_ino);
- to->di_lsn = be64_to_cpu(from->di_lsn);
- memcpy(to->di_pad2, from->di_pad2, sizeof(to->di_pad2));
- uuid_copy(&to->di_uuid, &from->di_uuid);
}
}
void
-xfs_dinode_to_disk(
- xfs_dinode_t *to,
- xfs_icdinode_t *from)
+xfs_inode_to_disk(
+ struct xfs_inode *ip,
+ struct xfs_dinode *to,
+ xfs_lsn_t lsn)
+{
+ struct xfs_icdinode *from = &ip->i_d;
+ struct inode *inode = VFS_I(ip);
+
+ to->di_magic = cpu_to_be16(XFS_DINODE_MAGIC);
+ to->di_onlink = 0;
+
+ to->di_version = from->di_version;
+ to->di_format = from->di_format;
+ to->di_uid = cpu_to_be32(from->di_uid);
+ to->di_gid = cpu_to_be32(from->di_gid);
+ to->di_projid_lo = cpu_to_be16(from->di_projid_lo);
+ to->di_projid_hi = cpu_to_be16(from->di_projid_hi);
+
+ memset(to->di_pad, 0, sizeof(to->di_pad));
+ to->di_atime.t_sec = cpu_to_be32(inode->i_atime.tv_sec);
+ to->di_atime.t_nsec = cpu_to_be32(inode->i_atime.tv_nsec);
+ to->di_mtime.t_sec = cpu_to_be32(inode->i_mtime.tv_sec);
+ to->di_mtime.t_nsec = cpu_to_be32(inode->i_mtime.tv_nsec);
+ to->di_ctime.t_sec = cpu_to_be32(inode->i_ctime.tv_sec);
+ to->di_ctime.t_nsec = cpu_to_be32(inode->i_ctime.tv_nsec);
+ to->di_nlink = cpu_to_be32(inode->i_nlink);
+ to->di_gen = cpu_to_be32(inode->i_generation);
+ to->di_mode = cpu_to_be16(inode->i_mode);
+
+ to->di_size = cpu_to_be64(from->di_size);
+ to->di_nblocks = cpu_to_be64(from->di_nblocks);
+ to->di_extsize = cpu_to_be32(from->di_extsize);
+ to->di_nextents = cpu_to_be32(from->di_nextents);
+ to->di_anextents = cpu_to_be16(from->di_anextents);
+ to->di_forkoff = from->di_forkoff;
+ to->di_aformat = from->di_aformat;
+ to->di_dmevmask = cpu_to_be32(from->di_dmevmask);
+ to->di_dmstate = cpu_to_be16(from->di_dmstate);
+ to->di_flags = cpu_to_be16(from->di_flags);
+
+ if (from->di_version == 3) {
+ to->di_changecount = cpu_to_be64(inode->i_version);
+ to->di_crtime.t_sec = cpu_to_be32(from->di_crtime.t_sec);
+ to->di_crtime.t_nsec = cpu_to_be32(from->di_crtime.t_nsec);
+ to->di_flags2 = cpu_to_be64(from->di_flags2);
+
+ to->di_ino = cpu_to_be64(ip->i_ino);
+ to->di_lsn = cpu_to_be64(lsn);
+ memset(to->di_pad2, 0, sizeof(to->di_pad2));
+ uuid_copy(&to->di_uuid, &ip->i_mount->m_sb.sb_meta_uuid);
+ to->di_flushiter = 0;
+ } else {
+ to->di_flushiter = cpu_to_be16(from->di_flushiter);
+ }
+}
+
+void
+xfs_log_dinode_to_disk(
+ struct xfs_log_dinode *from,
+ struct xfs_dinode *to)
{
to->di_magic = cpu_to_be16(from->di_magic);
to->di_mode = cpu_to_be16(from->di_mode);
- to->di_version = from ->di_version;
+ to->di_version = from->di_version;
to->di_format = from->di_format;
- to->di_onlink = cpu_to_be16(from->di_onlink);
+ to->di_onlink = 0;
to->di_uid = cpu_to_be32(from->di_uid);
to->di_gid = cpu_to_be32(from->di_gid);
to->di_nlink = cpu_to_be32(from->di_nlink);
to->di_projid_lo = cpu_to_be16(from->di_projid_lo);
to->di_projid_hi = cpu_to_be16(from->di_projid_hi);
memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad));
+
to->di_atime.t_sec = cpu_to_be32(from->di_atime.t_sec);
to->di_atime.t_nsec = cpu_to_be32(from->di_atime.t_nsec);
to->di_mtime.t_sec = cpu_to_be32(from->di_mtime.t_sec);
to->di_mtime.t_nsec = cpu_to_be32(from->di_mtime.t_nsec);
to->di_ctime.t_sec = cpu_to_be32(from->di_ctime.t_sec);
to->di_ctime.t_nsec = cpu_to_be32(from->di_ctime.t_nsec);
+
to->di_size = cpu_to_be64(from->di_size);
to->di_nblocks = cpu_to_be64(from->di_nblocks);
to->di_extsize = cpu_to_be32(from->di_extsize);
!(mp->m_flags & XFS_MOUNT_IKEEP)) {
/* initialise the on-disk inode core */
memset(&ip->i_d, 0, sizeof(ip->i_d));
- ip->i_d.di_magic = XFS_DINODE_MAGIC;
- ip->i_d.di_gen = prandom_u32();
- if (xfs_sb_version_hascrc(&mp->m_sb)) {
+ VFS_I(ip)->i_generation = prandom_u32();
+ if (xfs_sb_version_hascrc(&mp->m_sb))
ip->i_d.di_version = 3;
- ip->i_d.di_ino = ip->i_ino;
- uuid_copy(&ip->i_d.di_uuid, &mp->m_sb.sb_meta_uuid);
- } else
+ else
ip->i_d.di_version = 2;
return 0;
}
* Otherwise, just get the truly permanent information.
*/
if (dip->di_mode) {
- xfs_dinode_from_disk(&ip->i_d, dip);
+ xfs_inode_from_disk(ip, dip);
error = xfs_iformat_fork(ip, dip);
if (error) {
#ifdef DEBUG
* Partial initialisation of the in-core inode. Just the bits
* that xfs_ialloc won't overwrite or relies on being correct.
*/
- ip->i_d.di_magic = be16_to_cpu(dip->di_magic);
ip->i_d.di_version = dip->di_version;
- ip->i_d.di_gen = be32_to_cpu(dip->di_gen);
+ VFS_I(ip)->i_generation = be32_to_cpu(dip->di_gen);
ip->i_d.di_flushiter = be16_to_cpu(dip->di_flushiter);
- if (dip->di_version == 3) {
- ip->i_d.di_ino = be64_to_cpu(dip->di_ino);
- uuid_copy(&ip->i_d.di_uuid, &dip->di_uuid);
- }
-
/*
* Make sure to pull in the mode here as well in
* case the inode is released without being used.
* the inode is already free and not try to mess
* with the uninitialized part of it.
*/
- ip->i_d.di_mode = 0;
- }
-
- /*
- * Automatically convert version 1 inode formats in memory to version 2
- * inode format. If the inode is modified, it will get logged and
- * rewritten as a version 2 inode. We can do this because we set the
- * superblock feature bit for v2 inodes unconditionally during mount
- * and it means the reast of the code can assume the inode version is 2
- * or higher.
- */
- if (ip->i_d.di_version == 1) {
- ip->i_d.di_version = 2;
- memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));
- ip->i_d.di_nlink = ip->i_d.di_onlink;
- ip->i_d.di_onlink = 0;
- xfs_set_projid(ip, 0);
+ VFS_I(ip)->i_mode = 0;
}
+ ASSERT(ip->i_d.di_version >= 2);
ip->i_delayed_blks = 0;
/*
struct xfs_inode;
struct xfs_dinode;
-struct xfs_icdinode;
+
+/*
+ * In memory representation of the XFS inode. This is held in the in-core struct
+ * xfs_inode and represents the current on disk values but the structure is not
+ * in on-disk format. That is, this structure is always translated to on-disk
+ * format specific structures at the appropriate time.
+ */
+struct xfs_icdinode {
+ __int8_t di_version; /* inode version */
+ __int8_t di_format; /* format of di_c data */
+ __uint16_t di_flushiter; /* incremented on flush */
+ __uint32_t di_uid; /* owner's user id */
+ __uint32_t di_gid; /* owner's group id */
+ __uint16_t di_projid_lo; /* lower part of owner's project id */
+ __uint16_t di_projid_hi; /* higher part of owner's project id */
+ xfs_fsize_t di_size; /* number of bytes in file */
+ xfs_rfsblock_t di_nblocks; /* # of direct & btree blocks used */
+ xfs_extlen_t di_extsize; /* basic/minimum extent size for file */
+ xfs_extnum_t di_nextents; /* number of extents in data fork */
+ xfs_aextnum_t di_anextents; /* number of extents in attribute fork*/
+ __uint8_t di_forkoff; /* attr fork offs, <<3 for 64b align */
+ __int8_t di_aformat; /* format of attr fork's data */
+ __uint32_t di_dmevmask; /* DMIG event mask */
+ __uint16_t di_dmstate; /* DMIG state info */
+ __uint16_t di_flags; /* random flags, XFS_DIFLAG_... */
+
+ __uint64_t di_flags2; /* more random flags */
+
+ xfs_ictimestamp_t di_crtime; /* time created */
+};
/*
* Inode location information. Stored in the inode and passed to
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 *to, struct xfs_icdinode *from);
-void xfs_dinode_from_disk(struct xfs_icdinode *to, struct xfs_dinode *from);
+void xfs_inode_to_disk(struct xfs_inode *ip, struct xfs_dinode *to,
+ xfs_lsn_t lsn);
+void xfs_inode_from_disk(struct xfs_inode *ip, struct xfs_dinode *from);
+void xfs_log_dinode_to_disk(struct xfs_log_dinode *from,
+ struct xfs_dinode *to);
#if defined(DEBUG)
void xfs_inobp_check(struct xfs_mount *, struct xfs_buf *);
#include "xfs_error.h"
#include "xfs_trace.h"
#include "xfs_attr_sf.h"
+#include "xfs_da_format.h"
kmem_zone_t *xfs_ifork_zone;
return -EFSCORRUPTED;
}
- switch (ip->i_d.di_mode & S_IFMT) {
+ switch (VFS_I(ip)->i_mode & S_IFMT) {
case S_IFIFO:
case S_IFCHR:
case S_IFBLK:
__int32_t ilf_boffset; /* off of inode in buffer */
} xfs_inode_log_format_64_t;
+
/*
* Flags for xfs_trans_log_inode flags field.
*/
} xfs_ictimestamp_t;
/*
- * NOTE: This structure must be kept identical to struct xfs_dinode
- * except for the endianness annotations.
+ * Define the format of the inode core that is logged. This structure must be
+ * kept identical to struct xfs_dinode except for the endianness annotations.
*/
-typedef struct xfs_icdinode {
+struct xfs_log_dinode {
__uint16_t di_magic; /* inode magic # = XFS_DINODE_MAGIC */
__uint16_t di_mode; /* mode and type of file */
__int8_t di_version; /* inode version */
__int8_t di_format; /* format of di_c data */
- __uint16_t di_onlink; /* old number of links to file */
+ __uint8_t di_pad3[2]; /* unused in v2/3 inodes */
__uint32_t di_uid; /* owner's user id */
__uint32_t di_gid; /* owner's group id */
__uint32_t di_nlink; /* number of links to file */
uuid_t di_uuid; /* UUID of the filesystem */
/* structure must be padded to 64 bit alignment */
-} xfs_icdinode_t;
+};
-static inline uint xfs_icdinode_size(int version)
+static inline uint xfs_log_dinode_size(int version)
{
if (version == 3)
- return sizeof(struct xfs_icdinode);
- return offsetof(struct xfs_icdinode, di_next_unlinked);
+ return sizeof(struct xfs_log_dinode);
+ return offsetof(struct xfs_log_dinode, di_next_unlinked);
}
/*
XFS_BLFT_ATTR_LEAF_BUF,
XFS_BLFT_ATTR_RMT_BUF,
XFS_BLFT_SB_BUF,
+ XFS_BLFT_RTBITMAP_BUF,
+ XFS_BLFT_RTSUMMARY_BUF,
XFS_BLFT_MAX_BUF = (1 << XFS_BLFT_BITS),
};
* Realtime allocator bitmap functions shared with userspace.
*/
+/*
+ * Real time buffers need verifiers to avoid runtime warnings during IO.
+ * We don't have anything to verify, however, so these are just dummy
+ * operations.
+ */
+static void
+xfs_rtbuf_verify_read(
+ struct xfs_buf *bp)
+{
+ return;
+}
+
+static void
+xfs_rtbuf_verify_write(
+ struct xfs_buf *bp)
+{
+ return;
+}
+
+const struct xfs_buf_ops xfs_rtbuf_ops = {
+ .name = "rtbuf",
+ .verify_read = xfs_rtbuf_verify_read,
+ .verify_write = xfs_rtbuf_verify_write,
+};
+
/*
* Get a buffer for the bitmap or summary file block specified.
* The buffer is returned read and locked.
ASSERT(map.br_startblock != NULLFSBLOCK);
error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
XFS_FSB_TO_DADDR(mp, map.br_startblock),
- mp->m_bsize, 0, &bp, NULL);
+ mp->m_bsize, 0, &bp, &xfs_rtbuf_ops);
if (error)
return error;
+
+ xfs_trans_buf_set_type(tp, bp, issum ? XFS_BLFT_RTSUMMARY_BUF
+ : XFS_BLFT_RTBITMAP_BUF);
*bpp = bp;
return 0;
}
mp->m_sb.sb_rextents) {
if (!(mp->m_rbmip->i_d.di_flags & XFS_DIFLAG_NEWRTBM))
mp->m_rbmip->i_d.di_flags |= XFS_DIFLAG_NEWRTBM;
- *(__uint64_t *)&mp->m_rbmip->i_d.di_atime = 0;
+ *(__uint64_t *)&VFS_I(mp->m_rbmip)->i_atime = 0;
xfs_trans_log_inode(tp, mp->m_rbmip, XFS_ILOG_CORE);
}
return 0;
extern void xfs_perag_put(struct xfs_perag *pag);
extern int xfs_initialize_perag_data(struct xfs_mount *, xfs_agnumber_t);
-extern void xfs_sb_calc_crc(struct xfs_buf *bp);
extern void xfs_log_sb(struct xfs_trans *tp);
extern int xfs_sync_sb(struct xfs_mount *mp, bool wait);
extern void xfs_sb_mount_common(struct xfs_mount *mp, struct xfs_sb *sbp);
extern const struct xfs_buf_ops xfs_sb_buf_ops;
extern const struct xfs_buf_ops xfs_sb_quiet_buf_ops;
extern const struct xfs_buf_ops xfs_symlink_buf_ops;
+extern const struct xfs_buf_ops xfs_rtbuf_ops;
/*
* Transaction types. Used to distinguish types of buffers. These never reach
#include <linux/pagevec.h>
#include <linux/writeback.h>
+/* flags for direct write completions */
+#define XFS_DIO_FLAG_UNWRITTEN (1 << 0)
+#define XFS_DIO_FLAG_APPEND (1 << 1)
+
void
xfs_count_page_state(
struct page *page,
struct xfs_inode *ip = XFS_I(ioend->io_inode);
int error = 0;
- if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
+ /*
+ * Set an error if the mount has shut down and proceed with end I/O
+ * processing so it can perform whatever cleanups are necessary.
+ */
+ if (XFS_FORCED_SHUTDOWN(ip->i_mount))
ioend->io_error = -EIO;
- goto done;
- }
/*
* For unwritten extents we need to issue transactions to convert a
}
/*
- * When we map a DIO buffer, we may need to attach an ioend that describes the
- * type of write IO we are doing. This passes to the completion function the
- * operations it needs to perform. If the mapping is for an overwrite wholly
- * within the EOF then we don't need an ioend and so we don't allocate one.
- * This avoids the unnecessary overhead of allocating and freeing ioends for
- * workloads that don't require transactions on IO completion.
- *
- * If we get multiple mappings in a single IO, we might be mapping different
- * types. But because the direct IO can only have a single private pointer, we
- * need to ensure that:
- *
- * a) i) the ioend spans the entire region of unwritten mappings; or
- * ii) the ioend spans all the mappings that cross or are beyond EOF; and
- * b) if it contains unwritten extents, it is *permanently* marked as such
- *
- * We could do this by chaining ioends like buffered IO does, but we only
- * actually get one IO completion callback from the direct IO, and that spans
- * the entire IO regardless of how many mappings and IOs are needed to complete
- * the DIO. There is only going to be one reference to the ioend and its life
- * cycle is constrained by the DIO completion code. hence we don't need
- * reference counting here.
+ * When we map a DIO buffer, we may need to pass flags to
+ * xfs_end_io_direct_write to tell it what kind of write IO we are doing.
*
* Note that for DIO, an IO to the highest supported file block offset (i.e.
* 2^63 - 1FSB bytes) will result in the offset + count overflowing a signed 64
* extending the file size. We won't know for sure until IO completion is run
* and the actual max write offset is communicated to the IO completion
* routine.
- *
- * For DAX page faults, we are preparing to never see unwritten extents here,
- * nor should we ever extend the inode size. Hence we will soon have nothing to
- * do here for this case, ensuring we don't have to provide an IO completion
- * callback to free an ioend that we don't actually need for a fault into the
- * page at offset (2^63 - 1FSB) bytes.
*/
-
static void
xfs_map_direct(
struct inode *inode,
struct buffer_head *bh_result,
struct xfs_bmbt_irec *imap,
- xfs_off_t offset,
- bool dax_fault)
+ xfs_off_t offset)
{
- struct xfs_ioend *ioend;
+ uintptr_t *flags = (uintptr_t *)&bh_result->b_private;
xfs_off_t size = bh_result->b_size;
- int type;
- if (ISUNWRITTEN(imap))
- type = XFS_IO_UNWRITTEN;
- else
- type = XFS_IO_OVERWRITE;
-
- trace_xfs_gbmap_direct(XFS_I(inode), offset, size, type, imap);
-
- if (dax_fault) {
- ASSERT(type == XFS_IO_OVERWRITE);
- trace_xfs_gbmap_direct_none(XFS_I(inode), offset, size, type,
- imap);
- return;
- }
-
- if (bh_result->b_private) {
- ioend = bh_result->b_private;
- ASSERT(ioend->io_size > 0);
- ASSERT(offset >= ioend->io_offset);
- if (offset + size > ioend->io_offset + ioend->io_size)
- ioend->io_size = offset - ioend->io_offset + size;
-
- if (type == XFS_IO_UNWRITTEN && type != ioend->io_type)
- ioend->io_type = XFS_IO_UNWRITTEN;
-
- trace_xfs_gbmap_direct_update(XFS_I(inode), ioend->io_offset,
- ioend->io_size, ioend->io_type,
- imap);
- } else if (type == XFS_IO_UNWRITTEN ||
- offset + size > i_size_read(inode) ||
- offset + size < 0) {
- ioend = xfs_alloc_ioend(inode, type);
- ioend->io_offset = offset;
- ioend->io_size = size;
+ trace_xfs_get_blocks_map_direct(XFS_I(inode), offset, size,
+ ISUNWRITTEN(imap) ? XFS_IO_UNWRITTEN : XFS_IO_OVERWRITE, imap);
- bh_result->b_private = ioend;
+ if (ISUNWRITTEN(imap)) {
+ *flags |= XFS_DIO_FLAG_UNWRITTEN;
+ set_buffer_defer_completion(bh_result);
+ } else if (offset + size > i_size_read(inode) || offset + size < 0) {
+ *flags |= XFS_DIO_FLAG_APPEND;
set_buffer_defer_completion(bh_result);
-
- trace_xfs_gbmap_direct_new(XFS_I(inode), offset, size, type,
- imap);
- } else {
- trace_xfs_gbmap_direct_none(XFS_I(inode), offset, size, type,
- imap);
}
}
if (ISUNWRITTEN(&imap))
set_buffer_unwritten(bh_result);
/* direct IO needs special help */
- if (create && direct)
- xfs_map_direct(inode, bh_result, &imap, offset,
- dax_fault);
+ if (create && direct) {
+ if (dax_fault)
+ ASSERT(!ISUNWRITTEN(&imap));
+ else
+ xfs_map_direct(inode, bh_result, &imap, offset);
+ }
}
/*
return __xfs_get_blocks(inode, iblock, bh_result, create, true, true);
}
-static void
-__xfs_end_io_direct_write(
- struct inode *inode,
- struct xfs_ioend *ioend,
+/*
+ * Complete a direct I/O write request.
+ *
+ * xfs_map_direct passes us some flags in the private data to tell us what to
+ * do. If no flags are set, then the write IO is an overwrite wholly within
+ * the existing allocated file size and so there is nothing for us to do.
+ *
+ * Note that in this case the completion can be called in interrupt context,
+ * whereas if we have flags set we will always be called in task context
+ * (i.e. from a workqueue).
+ */
+STATIC int
+xfs_end_io_direct_write(
+ struct kiocb *iocb,
loff_t offset,
- ssize_t size)
+ ssize_t size,
+ void *private)
{
- struct xfs_mount *mp = XFS_I(inode)->i_mount;
+ struct inode *inode = file_inode(iocb->ki_filp);
+ struct xfs_inode *ip = XFS_I(inode);
+ struct xfs_mount *mp = ip->i_mount;
+ uintptr_t flags = (uintptr_t)private;
+ int error = 0;
- if (XFS_FORCED_SHUTDOWN(mp) || ioend->io_error)
- goto out_end_io;
+ trace_xfs_end_io_direct_write(ip, offset, size);
- /*
- * dio completion end_io functions are only called on writes if more
- * than 0 bytes was written.
- */
- ASSERT(size > 0);
+ if (XFS_FORCED_SHUTDOWN(mp))
+ return -EIO;
- /*
- * The ioend only maps whole blocks, while the IO may be sector aligned.
- * Hence the ioend offset/size may not match the IO offset/size exactly.
- * Because we don't map overwrites within EOF into the ioend, the offset
- * may not match, but only if the endio spans EOF. Either way, write
- * the IO sizes into the ioend so that completion processing does the
- * right thing.
- */
- ASSERT(offset + size <= ioend->io_offset + ioend->io_size);
- ioend->io_size = size;
- ioend->io_offset = offset;
+ if (size <= 0)
+ return size;
/*
- * The ioend tells us whether we are doing unwritten extent conversion
+ * The flags tell us whether we are doing unwritten extent conversions
* or an append transaction that updates the on-disk file size. These
* cases are the only cases where we should *potentially* be needing
* to update the VFS inode size.
- *
+ */
+ if (flags == 0) {
+ ASSERT(offset + size <= i_size_read(inode));
+ return 0;
+ }
+
+ /*
* We need to update the in-core inode size here so that we don't end up
* with the on-disk inode size being outside the in-core inode size. We
* have no other method of updating EOF for AIO, so always do it here
* here can result in EOF moving backwards and Bad Things Happen when
* that occurs.
*/
- spin_lock(&XFS_I(inode)->i_flags_lock);
+ spin_lock(&ip->i_flags_lock);
if (offset + size > i_size_read(inode))
i_size_write(inode, offset + size);
- spin_unlock(&XFS_I(inode)->i_flags_lock);
+ spin_unlock(&ip->i_flags_lock);
- /*
- * If we are doing an append IO that needs to update the EOF on disk,
- * do the transaction reserve now so we can use common end io
- * processing. Stashing the error (if there is one) in the ioend will
- * result in the ioend processing passing on the error if it is
- * possible as we can't return it from here.
- */
- if (ioend->io_type == XFS_IO_OVERWRITE)
- ioend->io_error = xfs_setfilesize_trans_alloc(ioend);
+ if (flags & XFS_DIO_FLAG_UNWRITTEN) {
+ trace_xfs_end_io_direct_write_unwritten(ip, offset, size);
-out_end_io:
- xfs_end_io(&ioend->io_work);
- return;
-}
+ error = xfs_iomap_write_unwritten(ip, offset, size);
+ } else if (flags & XFS_DIO_FLAG_APPEND) {
+ struct xfs_trans *tp;
-/*
- * Complete a direct I/O write request.
- *
- * The ioend structure is passed from __xfs_get_blocks() to tell us what to do.
- * If no ioend exists (i.e. @private == NULL) then the write IO is an overwrite
- * wholly within the EOF and so there is nothing for us to do. Note that in this
- * case the completion can be called in interrupt context, whereas if we have an
- * ioend we will always be called in task context (i.e. from a workqueue).
- */
-STATIC void
-xfs_end_io_direct_write(
- struct kiocb *iocb,
- loff_t offset,
- ssize_t size,
- void *private)
-{
- struct inode *inode = file_inode(iocb->ki_filp);
- struct xfs_ioend *ioend = private;
+ trace_xfs_end_io_direct_write_append(ip, offset, size);
- trace_xfs_gbmap_direct_endio(XFS_I(inode), offset, size,
- ioend ? ioend->io_type : 0, NULL);
-
- if (!ioend) {
- ASSERT(offset + size <= i_size_read(inode));
- return;
+ tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
+ error = xfs_trans_reserve(tp, &M_RES(mp)->tr_fsyncts, 0, 0);
+ if (error) {
+ xfs_trans_cancel(tp);
+ return error;
+ }
+ error = xfs_setfilesize(ip, tp, offset, size);
}
- __xfs_end_io_direct_write(inode, ioend, offset, size);
+ return error;
}
-static inline ssize_t
-xfs_vm_do_dio(
- struct inode *inode,
+STATIC ssize_t
+xfs_vm_direct_IO(
struct kiocb *iocb,
struct iov_iter *iter,
- loff_t offset,
- void (*endio)(struct kiocb *iocb,
- loff_t offset,
- ssize_t size,
- void *private),
- int flags)
+ loff_t offset)
{
+ struct inode *inode = iocb->ki_filp->f_mapping->host;
+ dio_iodone_t *endio = NULL;
+ int flags = 0;
struct block_device *bdev;
- if (IS_DAX(inode))
+ if (iov_iter_rw(iter) == WRITE) {
+ endio = xfs_end_io_direct_write;
+ flags = DIO_ASYNC_EXTEND;
+ }
+
+ if (IS_DAX(inode)) {
return dax_do_io(iocb, inode, iter, offset,
xfs_get_blocks_direct, endio, 0);
+ }
bdev = xfs_find_bdev_for_inode(inode);
return __blockdev_direct_IO(iocb, inode, bdev, iter, offset,
- xfs_get_blocks_direct, endio, NULL, flags);
-}
-
-STATIC ssize_t
-xfs_vm_direct_IO(
- struct kiocb *iocb,
- struct iov_iter *iter,
- loff_t offset)
-{
- struct inode *inode = iocb->ki_filp->f_mapping->host;
-
- if (iov_iter_rw(iter) == WRITE)
- return xfs_vm_do_dio(inode, iocb, iter, offset,
- xfs_end_io_direct_write, DIO_ASYNC_EXTEND);
- return xfs_vm_do_dio(inode, iocb, iter, offset, NULL, 0);
+ xfs_get_blocks_direct, endio, NULL, flags);
}
/*
if (block_start >= to)
break;
- if (!buffer_delay(bh))
+ /*
+ * Process delalloc and unwritten buffers beyond EOF. We can
+ * encounter unwritten buffers in the event that a file has
+ * post-EOF unwritten extents and an extending write happens to
+ * fail (e.g., an unaligned write that also involves a delalloc
+ * to the same page).
+ */
+ if (!buffer_delay(bh) && !buffer_unwritten(bh))
continue;
if (!buffer_new(bh) && block_offset < i_size_read(inode))
continue;
- xfs_vm_kill_delalloc_range(inode, block_offset,
- block_offset + bh->b_size);
+ if (buffer_delay(bh))
+ xfs_vm_kill_delalloc_range(inode, block_offset,
+ block_offset + bh->b_size);
/*
* This buffer does not contain data anymore. make sure anyone
clear_buffer_mapped(bh);
clear_buffer_new(bh);
clear_buffer_dirty(bh);
+ clear_buffer_unwritten(bh);
}
}
ralen = MAXEXTLEN / mp->m_sb.sb_rextsize;
/*
- * Lock out other modifications to the RT bitmap inode.
+ * Lock out modifications to both the RT bitmap and summary inodes
*/
xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(ap->tp, mp->m_rbmip, XFS_ILOCK_EXCL);
+ xfs_ilock(mp->m_rsumip, XFS_ILOCK_EXCL);
+ xfs_trans_ijoin(ap->tp, mp->m_rsumip, XFS_ILOCK_EXCL);
/*
* If it's an allocation to an empty file at offset 0,
xfs_can_free_eofblocks(struct xfs_inode *ip, bool force)
{
/* prealloc/delalloc exists only on regular files */
- if (!S_ISREG(ip->i_d.di_mode))
+ if (!S_ISREG(VFS_I(ip)->i_mode))
return false;
/*
xfs_lock_two_inodes(ip, tip, XFS_MMAPLOCK_EXCL);
/* Verify that both files have the same format */
- if ((ip->i_d.di_mode & S_IFMT) != (tip->i_d.di_mode & S_IFMT)) {
+ if ((VFS_I(ip)->i_mode & S_IFMT) != (VFS_I(tip)->i_mode & S_IFMT)) {
error = -EINVAL;
goto out_unlock;
}
if (bp) {
trace_xfs_buf_read(bp, flags, _RET_IP_);
- if (!XFS_BUF_ISDONE(bp)) {
+ if (!(bp->b_flags & XBF_DONE)) {
XFS_STATS_INC(target->bt_mount, xb_get_read);
bp->b_ops = ops;
_xfs_buf_read(bp, flags);
/* Buffer Utility Routines */
extern void *xfs_buf_offset(struct xfs_buf *, size_t);
+extern void xfs_buf_stale(struct xfs_buf *bp);
/* Delayed Write Buffer Routines */
extern bool xfs_buf_delwri_queue(struct xfs_buf *, struct list_head *);
extern int xfs_buf_init(void);
extern void xfs_buf_terminate(void);
-#define XFS_BUF_ZEROFLAGS(bp) \
- ((bp)->b_flags &= ~(XBF_READ|XBF_WRITE|XBF_ASYNC| \
- XBF_SYNCIO|XBF_FUA|XBF_FLUSH| \
- XBF_WRITE_FAIL))
-
-void xfs_buf_stale(struct xfs_buf *bp);
-#define XFS_BUF_UNSTALE(bp) ((bp)->b_flags &= ~XBF_STALE)
-#define XFS_BUF_ISSTALE(bp) ((bp)->b_flags & XBF_STALE)
-
-#define XFS_BUF_DONE(bp) ((bp)->b_flags |= XBF_DONE)
-#define XFS_BUF_UNDONE(bp) ((bp)->b_flags &= ~XBF_DONE)
-#define XFS_BUF_ISDONE(bp) ((bp)->b_flags & XBF_DONE)
-
-#define XFS_BUF_ASYNC(bp) ((bp)->b_flags |= XBF_ASYNC)
-#define XFS_BUF_UNASYNC(bp) ((bp)->b_flags &= ~XBF_ASYNC)
-#define XFS_BUF_ISASYNC(bp) ((bp)->b_flags & XBF_ASYNC)
-
-#define XFS_BUF_READ(bp) ((bp)->b_flags |= XBF_READ)
-#define XFS_BUF_UNREAD(bp) ((bp)->b_flags &= ~XBF_READ)
-#define XFS_BUF_ISREAD(bp) ((bp)->b_flags & XBF_READ)
-
-#define XFS_BUF_WRITE(bp) ((bp)->b_flags |= XBF_WRITE)
-#define XFS_BUF_UNWRITE(bp) ((bp)->b_flags &= ~XBF_WRITE)
-#define XFS_BUF_ISWRITE(bp) ((bp)->b_flags & XBF_WRITE)
-
/*
* These macros use the IO block map rather than b_bn. b_bn is now really
* just for the buffer cache index for cached buffers. As IO does not use b_bn
if (freed && stale) {
ASSERT(bip->bli_flags & XFS_BLI_STALE);
ASSERT(xfs_buf_islocked(bp));
- ASSERT(XFS_BUF_ISSTALE(bp));
+ ASSERT(bp->b_flags & XBF_STALE);
ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
trace_xfs_buf_item_unpin_stale(bip);
xfs_buf_hold(bp);
bp->b_flags |= XBF_ASYNC;
xfs_buf_ioerror(bp, -EIO);
- XFS_BUF_UNDONE(bp);
+ bp->b_flags &= ~XBF_DONE;
xfs_buf_stale(bp);
xfs_buf_ioend(bp);
}
*/
if (XFS_FORCED_SHUTDOWN(mp)) {
xfs_buf_stale(bp);
- XFS_BUF_DONE(bp);
+ bp->b_flags |= XBF_DONE;
trace_xfs_buf_item_iodone(bp, _RET_IP_);
goto do_callbacks;
}
* errors tend to affect the whole device and a failing log write
* will make us give up. But we really ought to do better here.
*/
- if (XFS_BUF_ISASYNC(bp)) {
+ if (bp->b_flags & XBF_ASYNC) {
ASSERT(bp->b_iodone != NULL);
trace_xfs_buf_item_iodone_async(bp, _RET_IP_);
* sure to return the error to the caller of xfs_bwrite().
*/
xfs_buf_stale(bp);
- XFS_BUF_DONE(bp);
+ bp->b_flags |= XBF_DONE;
trace_xfs_buf_error_relse(bp, _RET_IP_);
if (XFS_FORCED_SHUTDOWN(dp->i_mount))
return -EIO;
- ASSERT(S_ISDIR(dp->i_d.di_mode));
+ ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
XFS_STATS_INC(dp->i_mount, xs_dir_getdents);
args.dp = dp;
return ERR_PTR(error);
}
- if (ip->i_d.di_gen != generation) {
+ if (VFS_I(ip)->i_generation != generation) {
IRELE(ip);
return ERR_PTR(-ESTALE);
}
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
if (!(flags & XFS_PREALLOC_INVISIBLE)) {
- ip->i_d.di_mode &= ~S_ISUID;
- if (ip->i_d.di_mode & S_IXGRP)
- ip->i_d.di_mode &= ~S_ISGID;
+ VFS_I(ip)->i_mode &= ~S_ISUID;
+ if (VFS_I(ip)->i_mode & S_IXGRP)
+ VFS_I(ip)->i_mode &= ~S_ISGID;
xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
}
xfs_agnumber_t ag, max_ag = NULLAGNUMBER;
int err, trylock, nscan;
- ASSERT(S_ISDIR(ip->i_d.di_mode));
+ ASSERT(S_ISDIR(VFS_I(ip)->i_mode));
/* 2% of an AG's blocks must be free for it to be chosen. */
minfree = mp->m_sb.sb_agblocks / 50;
xfs_agnumber_t startag, ag = NULLAGNUMBER;
struct xfs_mru_cache_elem *mru;
- ASSERT(S_ISREG(ip->i_d.di_mode));
+ ASSERT(S_ISREG(VFS_I(ip)->i_mode));
pip = xfs_filestream_get_parent(ip);
if (!pip)
extern int xfs_reserve_blocks(xfs_mount_t *mp, __uint64_t *inval,
xfs_fsop_resblks_t *outval);
extern int xfs_fs_goingdown(xfs_mount_t *mp, __uint32_t inflags);
-extern int xfs_fs_log_dummy(struct xfs_mount *mp);
#endif /* __XFS_FSOPS_H__ */
return NULL;
}
+ /* VFS doesn't initialise i_mode! */
+ VFS_I(ip)->i_mode = 0;
+
XFS_STATS_INC(mp, vn_active);
ASSERT(atomic_read(&ip->i_pincount) == 0);
ASSERT(!spin_is_locked(&ip->i_flags_lock));
memset(&ip->i_df, 0, sizeof(xfs_ifork_t));
ip->i_flags = 0;
ip->i_delayed_blks = 0;
- memset(&ip->i_d, 0, sizeof(xfs_icdinode_t));
+ memset(&ip->i_d, 0, sizeof(ip->i_d));
return ip;
}
xfs_inode_free(
struct xfs_inode *ip)
{
- switch (ip->i_d.di_mode & S_IFMT) {
+ switch (VFS_I(ip)->i_mode & S_IFMT) {
case S_IFREG:
case S_IFDIR:
case S_IFLNK:
call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback);
}
+/*
+ * When we recycle a reclaimable inode, we need to re-initialise the VFS inode
+ * part of the structure. This is made more complex by the fact we store
+ * information about the on-disk values in the VFS inode and so we can't just
+ * overwrite the values unconditionally. Hence we save the parameters we
+ * need to retain across reinitialisation, and rewrite them into the VFS inode
+ * after reinitialisation even if it fails.
+ */
+static int
+xfs_reinit_inode(
+ struct xfs_mount *mp,
+ struct inode *inode)
+{
+ int error;
+ uint32_t nlink = inode->i_nlink;
+ uint32_t generation = inode->i_generation;
+ uint64_t version = inode->i_version;
+ umode_t mode = inode->i_mode;
+
+ error = inode_init_always(mp->m_super, inode);
+
+ set_nlink(inode, nlink);
+ inode->i_generation = generation;
+ inode->i_version = version;
+ inode->i_mode = mode;
+ return error;
+}
+
/*
* Check the validity of the inode we just found it the cache
*/
/*
* If lookup is racing with unlink return an error immediately.
*/
- if (ip->i_d.di_mode == 0 && !(flags & XFS_IGET_CREATE)) {
+ if (VFS_I(ip)->i_mode == 0 && !(flags & XFS_IGET_CREATE)) {
error = -ENOENT;
goto out_error;
}
spin_unlock(&ip->i_flags_lock);
rcu_read_unlock();
- error = inode_init_always(mp->m_super, inode);
+ error = xfs_reinit_inode(mp, inode);
if (error) {
/*
* Re-initializing the inode failed, and we are in deep
trace_xfs_iget_miss(ip);
- if ((ip->i_d.di_mode == 0) && !(flags & XFS_IGET_CREATE)) {
+ if ((VFS_I(ip)->i_mode == 0) && !(flags & XFS_IGET_CREATE)) {
error = -ENOENT;
goto out_destroy;
}
* If we have a real type for an on-disk inode, we can setup the inode
* now. If it's a new inode being created, xfs_ialloc will handle it.
*/
- if (xfs_iflags_test(ip, XFS_INEW) && ip->i_d.di_mode != 0)
+ if (xfs_iflags_test(ip, XFS_INEW) && VFS_I(ip)->i_mode != 0)
xfs_setup_existing_inode(ip);
return 0;
*/
#define XFS_ITRUNC_MAX_EXTENTS 2
-STATIC int xfs_iflush_int(xfs_inode_t *, xfs_buf_t *);
-
-STATIC int xfs_iunlink_remove(xfs_trans_t *, xfs_inode_t *);
+STATIC int xfs_iflush_int(struct xfs_inode *, struct xfs_buf *);
+STATIC int xfs_iunlink(struct xfs_trans *, struct xfs_inode *);
+STATIC int xfs_iunlink_remove(struct xfs_trans *, struct xfs_inode *);
/*
* helper function to extract extent size hint from inode
uint flags;
int error;
struct timespec tv;
+ struct inode *inode;
/*
* Call the space management code to pick
if (error)
return error;
ASSERT(ip != NULL);
+ inode = VFS_I(ip);
/*
* We always convert v1 inodes to v2 now - we only support filesystems
if (ip->i_d.di_version == 1)
ip->i_d.di_version = 2;
- ip->i_d.di_mode = mode;
- ip->i_d.di_onlink = 0;
- ip->i_d.di_nlink = nlink;
- ASSERT(ip->i_d.di_nlink == nlink);
+ inode->i_mode = mode;
+ set_nlink(inode, nlink);
ip->i_d.di_uid = xfs_kuid_to_uid(current_fsuid());
ip->i_d.di_gid = xfs_kgid_to_gid(current_fsgid());
xfs_set_projid(ip, prid);
- memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));
if (pip && XFS_INHERIT_GID(pip)) {
ip->i_d.di_gid = pip->i_d.di_gid;
- if ((pip->i_d.di_mode & S_ISGID) && S_ISDIR(mode)) {
- ip->i_d.di_mode |= S_ISGID;
- }
+ if ((VFS_I(pip)->i_mode & S_ISGID) && S_ISDIR(mode))
+ inode->i_mode |= S_ISGID;
}
/*
* (and only if the irix_sgid_inherit compatibility variable is set).
*/
if ((irix_sgid_inherit) &&
- (ip->i_d.di_mode & S_ISGID) &&
- (!in_group_p(xfs_gid_to_kgid(ip->i_d.di_gid)))) {
- ip->i_d.di_mode &= ~S_ISGID;
- }
+ (inode->i_mode & S_ISGID) &&
+ (!in_group_p(xfs_gid_to_kgid(ip->i_d.di_gid))))
+ inode->i_mode &= ~S_ISGID;
ip->i_d.di_size = 0;
ip->i_d.di_nextents = 0;
ASSERT(ip->i_d.di_nblocks == 0);
tv = current_fs_time(mp->m_super);
- ip->i_d.di_mtime.t_sec = (__int32_t)tv.tv_sec;
- ip->i_d.di_mtime.t_nsec = (__int32_t)tv.tv_nsec;
- ip->i_d.di_atime = ip->i_d.di_mtime;
- ip->i_d.di_ctime = ip->i_d.di_mtime;
+ inode->i_mtime = tv;
+ inode->i_atime = tv;
+ inode->i_ctime = tv;
- /*
- * di_gen will have been taken care of in xfs_iread.
- */
ip->i_d.di_extsize = 0;
ip->i_d.di_dmevmask = 0;
ip->i_d.di_dmstate = 0;
ip->i_d.di_flags = 0;
if (ip->i_d.di_version == 3) {
- ASSERT(ip->i_d.di_ino == ino);
- ASSERT(uuid_equal(&ip->i_d.di_uuid, &mp->m_sb.sb_meta_uuid));
- ip->i_d.di_crc = 0;
- ip->i_d.di_changecount = 1;
- ip->i_d.di_lsn = 0;
+ inode->i_version = 1;
ip->i_d.di_flags2 = 0;
- memset(&(ip->i_d.di_pad2[0]), 0, sizeof(ip->i_d.di_pad2));
- ip->i_d.di_crtime = ip->i_d.di_mtime;
+ ip->i_d.di_crtime.t_sec = (__int32_t)tv.tv_sec;
+ ip->i_d.di_crtime.t_nsec = (__int32_t)tv.tv_nsec;
}
}
/*
- * Decrement the link count on an inode & log the change.
- * If this causes the link count to go to zero, initiate the
- * logging activity required to truncate a file.
+ * Decrement the link count on an inode & log the change. If this causes the
+ * link count to go to zero, move the inode to AGI unlinked list so that it can
+ * be freed when the last active reference goes away via xfs_inactive().
*/
int /* error */
xfs_droplink(
xfs_trans_t *tp,
xfs_inode_t *ip)
{
- int error;
-
xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
- ASSERT (ip->i_d.di_nlink > 0);
- ip->i_d.di_nlink--;
drop_nlink(VFS_I(ip));
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
- error = 0;
- if (ip->i_d.di_nlink == 0) {
- /*
- * We're dropping the last link to this file.
- * Move the on-disk inode to the AGI unlinked list.
- * From xfs_inactive() we will pull the inode from
- * the list and free it.
- */
- error = xfs_iunlink(tp, ip);
- }
- return error;
+ if (VFS_I(ip)->i_nlink)
+ return 0;
+
+ return xfs_iunlink(tp, ip);
}
/*
xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
ASSERT(ip->i_d.di_version > 1);
- ASSERT(ip->i_d.di_nlink > 0 || (VFS_I(ip)->i_state & I_LINKABLE));
- ip->i_d.di_nlink++;
inc_nlink(VFS_I(ip));
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
return 0;
*/
xfs_qm_vop_create_dqattach(tp, ip, udqp, gdqp, pdqp);
- ip->i_d.di_nlink--;
error = xfs_iunlink(tp, ip);
if (error)
goto out_trans_cancel;
trace_xfs_link(tdp, target_name);
- ASSERT(!S_ISDIR(sip->i_d.di_mode));
+ ASSERT(!S_ISDIR(VFS_I(sip)->i_mode));
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
xfs_bmap_init(&free_list, &first_block);
- if (sip->i_d.di_nlink == 0) {
+ /*
+ * Handle initial link state of O_TMPFILE inode
+ */
+ if (VFS_I(sip)->i_nlink == 0) {
error = xfs_iunlink_remove(tp, sip);
if (error)
goto error_return;
xfs_mount_t *mp = ip->i_mount;
int error;
- if (!S_ISREG(ip->i_d.di_mode) || (ip->i_d.di_mode == 0))
+ if (!S_ISREG(VFS_I(ip)->i_mode) || (VFS_I(ip)->i_mode == 0))
return 0;
/* If this is a read-only mount, don't do this (would generate I/O) */
}
}
- if (ip->i_d.di_nlink == 0)
+ if (VFS_I(ip)->i_nlink == 0)
return 0;
if (xfs_can_free_eofblocks(ip, false)) {
* If the inode is already free, then there can be nothing
* to clean up here.
*/
- if (ip->i_d.di_mode == 0) {
+ if (VFS_I(ip)->i_mode == 0) {
ASSERT(ip->i_df.if_real_bytes == 0);
ASSERT(ip->i_df.if_broot_bytes == 0);
return;
if (mp->m_flags & XFS_MOUNT_RDONLY)
return;
- if (ip->i_d.di_nlink != 0) {
+ if (VFS_I(ip)->i_nlink != 0) {
/*
* force is true because we are evicting an inode from the
* cache. Post-eof blocks must be freed, lest we end up with
return;
}
- if (S_ISREG(ip->i_d.di_mode) &&
+ if (S_ISREG(VFS_I(ip)->i_mode) &&
(ip->i_d.di_size != 0 || XFS_ISIZE(ip) != 0 ||
ip->i_d.di_nextents > 0 || ip->i_delayed_blks > 0))
truncate = 1;
if (error)
return;
- if (S_ISLNK(ip->i_d.di_mode))
+ if (S_ISLNK(VFS_I(ip)->i_mode))
error = xfs_inactive_symlink(ip);
else if (truncate)
error = xfs_inactive_truncate(ip);
}
/*
- * This is called when the inode's link count goes to 0.
- * We place the on-disk inode on a list in the AGI. It
- * will be pulled from this list when the inode is freed.
+ * This is called when the inode's link count goes to 0 or we are creating a
+ * tmpfile via O_TMPFILE. In the case of a tmpfile, @ignore_linkcount will be
+ * set to true as the link count is dropped to zero by the VFS after we've
+ * created the file successfully, so we have to add it to the unlinked list
+ * while the link count is non-zero.
+ *
+ * We place the on-disk inode on a list in the AGI. It will be pulled from this
+ * list when the inode is freed.
*/
-int
+STATIC int
xfs_iunlink(
- xfs_trans_t *tp,
- xfs_inode_t *ip)
+ struct xfs_trans *tp,
+ struct xfs_inode *ip)
{
- xfs_mount_t *mp;
+ xfs_mount_t *mp = tp->t_mountp;
xfs_agi_t *agi;
xfs_dinode_t *dip;
xfs_buf_t *agibp;
int offset;
int error;
- ASSERT(ip->i_d.di_nlink == 0);
- ASSERT(ip->i_d.di_mode != 0);
-
- mp = tp->t_mountp;
+ ASSERT(VFS_I(ip)->i_mode != 0);
/*
* Get the agi buffer first. It ensures lock ordering
struct xfs_icluster xic = { 0 };
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
- ASSERT(ip->i_d.di_nlink == 0);
+ ASSERT(VFS_I(ip)->i_nlink == 0);
ASSERT(ip->i_d.di_nextents == 0);
ASSERT(ip->i_d.di_anextents == 0);
- ASSERT(ip->i_d.di_size == 0 || !S_ISREG(ip->i_d.di_mode));
+ ASSERT(ip->i_d.di_size == 0 || !S_ISREG(VFS_I(ip)->i_mode));
ASSERT(ip->i_d.di_nblocks == 0);
/*
if (error)
return error;
- ip->i_d.di_mode = 0; /* mark incore inode as free */
+ VFS_I(ip)->i_mode = 0; /* mark incore inode as free */
ip->i_d.di_flags = 0;
ip->i_d.di_dmevmask = 0;
ip->i_d.di_forkoff = 0; /* mark the attr fork not in use */
* Bump the generation count so no one will be confused
* by reincarnations of this inode.
*/
- ip->i_d.di_gen++;
+ VFS_I(ip)->i_generation++;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
if (xic.deleted)
{
xfs_mount_t *mp = dp->i_mount;
xfs_trans_t *tp = NULL;
- int is_dir = S_ISDIR(ip->i_d.di_mode);
+ int is_dir = S_ISDIR(VFS_I(ip)->i_mode);
int error = 0;
xfs_bmap_free_t free_list;
xfs_fsblock_t first_block;
* If we're removing a directory perform some additional validation.
*/
if (is_dir) {
- ASSERT(ip->i_d.di_nlink >= 2);
- if (ip->i_d.di_nlink != 2) {
+ ASSERT(VFS_I(ip)->i_nlink >= 2);
+ if (VFS_I(ip)->i_nlink != 2) {
error = -ENOTEMPTY;
goto out_trans_cancel;
}
if (dp1 != dp2) {
dp2_flags = XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;
- if (S_ISDIR(ip2->i_d.di_mode)) {
+ if (S_ISDIR(VFS_I(ip2)->i_mode)) {
error = xfs_dir_replace(tp, ip2, &xfs_name_dotdot,
dp1->i_ino, first_block,
free_list, spaceres);
goto out_trans_abort;
/* transfer ip2 ".." reference to dp1 */
- if (!S_ISDIR(ip1->i_d.di_mode)) {
+ if (!S_ISDIR(VFS_I(ip1)->i_mode)) {
error = xfs_droplink(tp, dp2);
if (error)
goto out_trans_abort;
ip2_flags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;
}
- if (S_ISDIR(ip1->i_d.di_mode)) {
+ if (S_ISDIR(VFS_I(ip1)->i_mode)) {
error = xfs_dir_replace(tp, ip1, &xfs_name_dotdot,
dp2->i_ino, first_block,
free_list, spaceres);
goto out_trans_abort;
/* transfer ip1 ".." reference to dp2 */
- if (!S_ISDIR(ip2->i_d.di_mode)) {
+ if (!S_ISDIR(VFS_I(ip2)->i_mode)) {
error = xfs_droplink(tp, dp1);
if (error)
goto out_trans_abort;
struct xfs_inode *inodes[__XFS_SORT_INODES];
int num_inodes = __XFS_SORT_INODES;
bool new_parent = (src_dp != target_dp);
- bool src_is_directory = S_ISDIR(src_ip->i_d.di_mode);
+ bool src_is_directory = S_ISDIR(VFS_I(src_ip)->i_mode);
int spaceres;
int error;
* target and source are directories and that target can be
* destroyed, or that neither is a directory.
*/
- if (S_ISDIR(target_ip->i_d.di_mode)) {
+ if (S_ISDIR(VFS_I(target_ip)->i_mode)) {
/*
* Make sure target dir is empty.
*/
if (!(xfs_dir_isempty(target_ip)) ||
- (target_ip->i_d.di_nlink > 2)) {
+ (VFS_I(target_ip)->i_nlink > 2)) {
error = -EEXIST;
goto out_trans_cancel;
}
* intermediate state on disk.
*/
if (wip) {
- ASSERT(VFS_I(wip)->i_nlink == 0 && wip->i_d.di_nlink == 0);
+ ASSERT(VFS_I(wip)->i_nlink == 0);
error = xfs_bumplink(tp, wip);
if (error)
goto out_bmap_cancel;
* mark it as stale and brelse.
*/
if (bp->b_iodone) {
- XFS_BUF_UNDONE(bp);
+ bp->b_flags &= ~XBF_DONE;
xfs_buf_stale(bp);
xfs_buf_ioerror(bp, -EIO);
xfs_buf_ioend(bp);
__func__, ip->i_ino, be16_to_cpu(dip->di_magic), dip);
goto corrupt_out;
}
- if (XFS_TEST_ERROR(ip->i_d.di_magic != XFS_DINODE_MAGIC,
- mp, XFS_ERRTAG_IFLUSH_2, XFS_RANDOM_IFLUSH_2)) {
- xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
- "%s: Bad inode %Lu, ptr 0x%p, magic number 0x%x",
- __func__, ip->i_ino, ip, ip->i_d.di_magic);
- goto corrupt_out;
- }
- if (S_ISREG(ip->i_d.di_mode)) {
+ if (S_ISREG(VFS_I(ip)->i_mode)) {
if (XFS_TEST_ERROR(
(ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS) &&
(ip->i_d.di_format != XFS_DINODE_FMT_BTREE),
__func__, ip->i_ino, ip);
goto corrupt_out;
}
- } else if (S_ISDIR(ip->i_d.di_mode)) {
+ } else if (S_ISDIR(VFS_I(ip)->i_mode)) {
if (XFS_TEST_ERROR(
(ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS) &&
(ip->i_d.di_format != XFS_DINODE_FMT_BTREE) &&
ip->i_d.di_flushiter++;
/*
- * Copy the dirty parts of the inode into the on-disk
- * inode. We always copy out the core of the inode,
- * because if the inode is dirty at all the core must
- * be.
+ * Copy the dirty parts of the inode into the on-disk inode. We always
+ * copy out the core of the inode, because if the inode is dirty at all
+ * the core must be.
*/
- xfs_dinode_to_disk(dip, &ip->i_d);
+ xfs_inode_to_disk(ip, dip, iip->ili_item.li_lsn);
/* Wrap, we never let the log put out DI_MAX_FLUSH */
if (ip->i_d.di_flushiter == DI_MAX_FLUSH)
*/
xfs_buf_attach_iodone(bp, xfs_iflush_done, &iip->ili_item);
- /* update the lsn in the on disk inode if required */
- if (ip->i_d.di_version == 3)
- dip->di_lsn = cpu_to_be64(iip->ili_item.li_lsn);
-
/* generate the checksum. */
xfs_dinode_calc_crc(mp, dip);
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 */
+ struct xfs_icdinode i_d; /* most of ondisk inode */
/* VFS inode */
struct inode i_vnode; /* embedded VFS inode */
*/
static inline xfs_fsize_t XFS_ISIZE(struct xfs_inode *ip)
{
- if (S_ISREG(ip->i_d.di_mode))
+ if (S_ISREG(VFS_I(ip)->i_mode))
return i_size_read(VFS_I(ip));
return ip->i_d.di_size;
}
*/
#define XFS_INHERIT_GID(pip) \
(((pip)->i_mount->m_flags & XFS_MOUNT_GRPID) || \
- ((pip)->i_d.di_mode & S_ISGID))
+ (VFS_I(pip)->i_mode & S_ISGID))
int xfs_release(struct xfs_inode *ip);
void xfs_inactive(struct xfs_inode *ip);
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 *);
*nvecs += 2;
*nbytes += sizeof(struct xfs_inode_log_format) +
- xfs_icdinode_size(ip->i_d.di_version);
+ xfs_log_dinode_size(ip->i_d.di_version);
xfs_inode_item_data_fork_size(iip, nvecs, nbytes);
if (XFS_IFORK_Q(ip))
}
}
+static void
+xfs_inode_to_log_dinode(
+ struct xfs_inode *ip,
+ struct xfs_log_dinode *to,
+ xfs_lsn_t lsn)
+{
+ struct xfs_icdinode *from = &ip->i_d;
+ struct inode *inode = VFS_I(ip);
+
+ to->di_magic = XFS_DINODE_MAGIC;
+
+ to->di_version = from->di_version;
+ to->di_format = from->di_format;
+ to->di_uid = from->di_uid;
+ to->di_gid = from->di_gid;
+ to->di_projid_lo = from->di_projid_lo;
+ to->di_projid_hi = from->di_projid_hi;
+
+ memset(to->di_pad, 0, sizeof(to->di_pad));
+ memset(to->di_pad3, 0, sizeof(to->di_pad3));
+ to->di_atime.t_sec = inode->i_atime.tv_sec;
+ to->di_atime.t_nsec = inode->i_atime.tv_nsec;
+ to->di_mtime.t_sec = inode->i_mtime.tv_sec;
+ to->di_mtime.t_nsec = inode->i_mtime.tv_nsec;
+ to->di_ctime.t_sec = inode->i_ctime.tv_sec;
+ to->di_ctime.t_nsec = inode->i_ctime.tv_nsec;
+ to->di_nlink = inode->i_nlink;
+ to->di_gen = inode->i_generation;
+ to->di_mode = inode->i_mode;
+
+ to->di_size = from->di_size;
+ to->di_nblocks = from->di_nblocks;
+ to->di_extsize = from->di_extsize;
+ to->di_nextents = from->di_nextents;
+ to->di_anextents = from->di_anextents;
+ to->di_forkoff = from->di_forkoff;
+ to->di_aformat = from->di_aformat;
+ to->di_dmevmask = from->di_dmevmask;
+ to->di_dmstate = from->di_dmstate;
+ to->di_flags = from->di_flags;
+
+ if (from->di_version == 3) {
+ to->di_changecount = inode->i_version;
+ to->di_crtime.t_sec = from->di_crtime.t_sec;
+ to->di_crtime.t_nsec = from->di_crtime.t_nsec;
+ to->di_flags2 = from->di_flags2;
+
+ to->di_ino = ip->i_ino;
+ to->di_lsn = lsn;
+ memset(to->di_pad2, 0, sizeof(to->di_pad2));
+ uuid_copy(&to->di_uuid, &ip->i_mount->m_sb.sb_meta_uuid);
+ to->di_flushiter = 0;
+ } else {
+ to->di_flushiter = from->di_flushiter;
+ }
+}
+
+/*
+ * Format the inode core. Current timestamp data is only in the VFS inode
+ * fields, so we need to grab them from there. Hence rather than just copying
+ * the XFS inode core structure, format the fields directly into the iovec.
+ */
+static void
+xfs_inode_item_format_core(
+ struct xfs_inode *ip,
+ struct xfs_log_vec *lv,
+ struct xfs_log_iovec **vecp)
+{
+ struct xfs_log_dinode *dic;
+
+ dic = xlog_prepare_iovec(lv, vecp, XLOG_REG_TYPE_ICORE);
+ xfs_inode_to_log_dinode(ip, dic, ip->i_itemp->ili_item.li_lsn);
+ xlog_finish_iovec(lv, *vecp, xfs_log_dinode_size(ip->i_d.di_version));
+}
+
/*
* This is called to fill in the vector of log iovecs for the given inode
* log item. It fills the first item with an inode log format structure,
ilf->ilf_size = 2; /* format + core */
xlog_finish_iovec(lv, vecp, sizeof(struct xfs_inode_log_format));
- xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_ICORE,
- &ip->i_d,
- xfs_icdinode_size(ip->i_d.di_version));
-
+ xfs_inode_item_format_core(ip, lv, &vecp);
xfs_inode_item_format_data_fork(iip, ilf, lv, &vecp);
if (XFS_IFORK_Q(ip)) {
xfs_inode_item_format_attr_fork(iip, ilf, lv, &vecp);
handle.ha_fid.fid_len = sizeof(xfs_fid_t) -
sizeof(handle.ha_fid.fid_len);
handle.ha_fid.fid_pad = 0;
- handle.ha_fid.fid_gen = ip->i_d.di_gen;
+ handle.ha_fid.fid_gen = inode->i_generation;
handle.ha_fid.fid_ino = ip->i_ino;
hsize = XFS_HSIZE(handle);
di_flags |= XFS_DIFLAG_NODEFRAG;
if (xflags & FS_XFLAG_FILESTREAM)
di_flags |= XFS_DIFLAG_FILESTREAM;
- if (S_ISDIR(ip->i_d.di_mode)) {
+ if (S_ISDIR(VFS_I(ip)->i_mode)) {
if (xflags & FS_XFLAG_RTINHERIT)
di_flags |= XFS_DIFLAG_RTINHERIT;
if (xflags & FS_XFLAG_NOSYMLINKS)
di_flags |= XFS_DIFLAG_EXTSZINHERIT;
if (xflags & FS_XFLAG_PROJINHERIT)
di_flags |= XFS_DIFLAG_PROJINHERIT;
- } else if (S_ISREG(ip->i_d.di_mode)) {
+ } else if (S_ISREG(VFS_I(ip)->i_mode)) {
if (xflags & FS_XFLAG_REALTIME)
di_flags |= XFS_DIFLAG_REALTIME;
if (xflags & FS_XFLAG_EXTSIZE)
{
struct xfs_mount *mp = ip->i_mount;
- if ((fa->fsx_xflags & FS_XFLAG_EXTSIZE) && !S_ISREG(ip->i_d.di_mode))
+ if ((fa->fsx_xflags & FS_XFLAG_EXTSIZE) && !S_ISREG(VFS_I(ip)->i_mode))
return -EINVAL;
if ((fa->fsx_xflags & FS_XFLAG_EXTSZINHERIT) &&
- !S_ISDIR(ip->i_d.di_mode))
+ !S_ISDIR(VFS_I(ip)->i_mode))
return -EINVAL;
- if (S_ISREG(ip->i_d.di_mode) && ip->i_d.di_nextents &&
+ if (S_ISREG(VFS_I(ip)->i_mode) && ip->i_d.di_nextents &&
((ip->i_d.di_extsize << mp->m_sb.sb_blocklog) != fa->fsx_extsize))
return -EINVAL;
* successful return from chown()
*/
- if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) &&
+ if ((VFS_I(ip)->i_mode & (S_ISUID|S_ISGID)) &&
!capable_wrt_inode_uidgid(VFS_I(ip), CAP_FSETID))
- ip->i_d.di_mode &= ~(S_ISUID|S_ISGID);
+ VFS_I(ip)->i_mode &= ~(S_ISUID|S_ISGID);
/* Change the ownerships and register project quota modifications */
if (xfs_get_projid(ip) != fa->fsx_projid) {
stat->size = XFS_ISIZE(ip);
stat->dev = inode->i_sb->s_dev;
- stat->mode = ip->i_d.di_mode;
- stat->nlink = ip->i_d.di_nlink;
+ stat->mode = inode->i_mode;
+ stat->nlink = inode->i_nlink;
stat->uid = inode->i_uid;
stat->gid = inode->i_gid;
stat->ino = ip->i_ino;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
- ip->i_d.di_mode &= S_IFMT;
- ip->i_d.di_mode |= mode & ~S_IFMT;
-
inode->i_mode &= S_IFMT;
inode->i_mode |= mode & ~S_IFMT;
}
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
- if (iattr->ia_valid & ATTR_ATIME) {
+ if (iattr->ia_valid & ATTR_ATIME)
inode->i_atime = iattr->ia_atime;
- ip->i_d.di_atime.t_sec = iattr->ia_atime.tv_sec;
- ip->i_d.di_atime.t_nsec = iattr->ia_atime.tv_nsec;
- }
- if (iattr->ia_valid & ATTR_CTIME) {
+ if (iattr->ia_valid & ATTR_CTIME)
inode->i_ctime = iattr->ia_ctime;
- ip->i_d.di_ctime.t_sec = iattr->ia_ctime.tv_sec;
- ip->i_d.di_ctime.t_nsec = iattr->ia_ctime.tv_nsec;
- }
- if (iattr->ia_valid & ATTR_MTIME) {
+ if (iattr->ia_valid & ATTR_MTIME)
inode->i_mtime = iattr->ia_mtime;
- ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec;
- ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec;
- }
}
int
* The set-user-ID and set-group-ID bits of a file will be
* cleared upon successful return from chown()
*/
- if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) &&
+ if ((inode->i_mode & (S_ISUID|S_ISGID)) &&
!capable(CAP_FSETID))
- ip->i_d.di_mode &= ~(S_ISUID|S_ISGID);
+ inode->i_mode &= ~(S_ISUID|S_ISGID);
/*
* Change the ownerships and register quota modifications
ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
ASSERT(xfs_isilocked(ip, XFS_MMAPLOCK_EXCL));
- ASSERT(S_ISREG(ip->i_d.di_mode));
+ ASSERT(S_ISREG(inode->i_mode));
ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
- if (flags & S_CTIME) {
+ if (flags & S_CTIME)
inode->i_ctime = *now;
- ip->i_d.di_ctime.t_sec = (__int32_t)now->tv_sec;
- ip->i_d.di_ctime.t_nsec = (__int32_t)now->tv_nsec;
- }
- if (flags & S_MTIME) {
+ if (flags & S_MTIME)
inode->i_mtime = *now;
- ip->i_d.di_mtime.t_sec = (__int32_t)now->tv_sec;
- ip->i_d.di_mtime.t_nsec = (__int32_t)now->tv_nsec;
- }
- if (flags & S_ATIME) {
+ if (flags & S_ATIME)
inode->i_atime = *now;
- ip->i_d.di_atime.t_sec = (__int32_t)now->tv_sec;
- ip->i_d.di_atime.t_nsec = (__int32_t)now->tv_nsec;
- }
+
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
xfs_trans_log_inode(tp, ip, XFS_ILOG_TIMESTAMP);
return xfs_trans_commit(tp);
/* make the inode look hashed for the writeback code */
hlist_add_fake(&inode->i_hash);
- inode->i_mode = ip->i_d.di_mode;
- set_nlink(inode, ip->i_d.di_nlink);
inode->i_uid = xfs_uid_to_kuid(ip->i_d.di_uid);
inode->i_gid = xfs_gid_to_kgid(ip->i_d.di_gid);
break;
}
- inode->i_generation = ip->i_d.di_gen;
i_size_write(inode, ip->i_d.di_size);
- inode->i_atime.tv_sec = ip->i_d.di_atime.t_sec;
- inode->i_atime.tv_nsec = ip->i_d.di_atime.t_nsec;
- inode->i_mtime.tv_sec = ip->i_d.di_mtime.t_sec;
- inode->i_mtime.tv_nsec = ip->i_d.di_mtime.t_nsec;
- inode->i_ctime.tv_sec = ip->i_d.di_ctime.t_sec;
- inode->i_ctime.tv_nsec = ip->i_d.di_ctime.t_nsec;
xfs_diflags_to_iflags(inode, ip);
ip->d_ops = ip->i_mount->m_nondir_inode_ops;
{
struct xfs_icdinode *dic; /* dinode core info pointer */
struct xfs_inode *ip; /* incore inode pointer */
+ struct inode *inode;
struct xfs_bstat *buf; /* return buffer */
int error = 0; /* error value */
ASSERT(ip != NULL);
ASSERT(ip->i_imap.im_blkno != 0);
+ inode = VFS_I(ip);
dic = &ip->i_d;
/* xfs_iget returns the following without needing
* further change.
*/
- buf->bs_nlink = dic->di_nlink;
buf->bs_projid_lo = dic->di_projid_lo;
buf->bs_projid_hi = dic->di_projid_hi;
buf->bs_ino = ino;
- buf->bs_mode = dic->di_mode;
buf->bs_uid = dic->di_uid;
buf->bs_gid = dic->di_gid;
buf->bs_size = dic->di_size;
- buf->bs_atime.tv_sec = dic->di_atime.t_sec;
- buf->bs_atime.tv_nsec = dic->di_atime.t_nsec;
- buf->bs_mtime.tv_sec = dic->di_mtime.t_sec;
- buf->bs_mtime.tv_nsec = dic->di_mtime.t_nsec;
- buf->bs_ctime.tv_sec = dic->di_ctime.t_sec;
- buf->bs_ctime.tv_nsec = dic->di_ctime.t_nsec;
+
+ buf->bs_nlink = inode->i_nlink;
+ buf->bs_atime.tv_sec = inode->i_atime.tv_sec;
+ buf->bs_atime.tv_nsec = inode->i_atime.tv_nsec;
+ buf->bs_mtime.tv_sec = inode->i_mtime.tv_sec;
+ buf->bs_mtime.tv_nsec = inode->i_mtime.tv_nsec;
+ buf->bs_ctime.tv_sec = inode->i_ctime.tv_sec;
+ buf->bs_ctime.tv_nsec = inode->i_ctime.tv_nsec;
+ buf->bs_gen = inode->i_generation;
+ buf->bs_mode = inode->i_mode;
+
buf->bs_xflags = xfs_ip2xflags(ip);
buf->bs_extsize = dic->di_extsize << mp->m_sb.sb_blocklog;
buf->bs_extents = dic->di_nextents;
- buf->bs_gen = dic->di_gen;
memset(buf->bs_pad, 0, sizeof(buf->bs_pad));
buf->bs_dmevmask = dic->di_dmevmask;
buf->bs_dmstate = dic->di_dmstate;
}
/* log I/O is always issued ASYNC */
- ASSERT(XFS_BUF_ISASYNC(bp));
+ ASSERT(bp->b_flags & XBF_ASYNC);
xlog_state_done_syncing(iclog, aborted);
/*
bp->b_io_length = BTOBB(count);
bp->b_fspriv = iclog;
- XFS_BUF_ZEROFLAGS(bp);
- XFS_BUF_ASYNC(bp);
- bp->b_flags |= XBF_SYNCIO;
+ bp->b_flags &= ~(XBF_FUA | XBF_FLUSH);
+ bp->b_flags |= (XBF_ASYNC | XBF_SYNCIO | XBF_WRITE);
if (log->l_mp->m_flags & XFS_MOUNT_BARRIER) {
bp->b_flags |= XBF_FUA;
/* account for log which doesn't start at block #0 */
XFS_BUF_SET_ADDR(bp, XFS_BUF_ADDR(bp) + log->l_logBBstart);
+
/*
* Don't call xfs_bwrite here. We do log-syncs even when the filesystem
* is shutting down.
*/
- XFS_BUF_WRITE(bp);
-
error = xlog_bdstrat(bp);
if (error) {
xfs_buf_ioerror_alert(bp, "xlog_sync");
xfs_buf_associate_memory(bp,
(char *)&iclog->ic_header + count, split);
bp->b_fspriv = iclog;
- XFS_BUF_ZEROFLAGS(bp);
- XFS_BUF_ASYNC(bp);
- bp->b_flags |= XBF_SYNCIO;
+ bp->b_flags &= ~(XBF_FUA | XBF_FLUSH);
+ bp->b_flags |= (XBF_ASYNC | XBF_SYNCIO | XBF_WRITE);
if (log->l_mp->m_flags & XFS_MOUNT_BARRIER)
bp->b_flags |= XBF_FUA;
/* account for internal log which doesn't start at block #0 */
XFS_BUF_SET_ADDR(bp, XFS_BUF_ADDR(bp) + log->l_logBBstart);
- XFS_BUF_WRITE(bp);
error = xlog_bdstrat(bp);
if (error) {
xfs_buf_ioerror_alert(bp, "xlog_sync (split)");
log->l_flags & XLOG_ACTIVE_RECOVERY) {
mp->m_flags |= XFS_MOUNT_FS_SHUTDOWN;
if (mp->m_sb_bp)
- XFS_BUF_DONE(mp->m_sb_bp);
+ mp->m_sb_bp->b_flags |= XBF_DONE;
return 0;
}
spin_lock(&log->l_icloglock);
mp->m_flags |= XFS_MOUNT_FS_SHUTDOWN;
if (mp->m_sb_bp)
- XFS_BUF_DONE(mp->m_sb_bp);
+ mp->m_sb_bp->b_flags |= XBF_DONE;
/*
* Mark the log and the iclogs with IO error flags to prevent any
ASSERT(nbblks <= bp->b_length);
XFS_BUF_SET_ADDR(bp, log->l_logBBstart + blk_no);
- XFS_BUF_READ(bp);
+ bp->b_flags |= XBF_READ;
bp->b_io_length = nbblks;
bp->b_error = 0;
ASSERT(nbblks <= bp->b_length);
XFS_BUF_SET_ADDR(bp, log->l_logBBstart + blk_no);
- XFS_BUF_ZEROFLAGS(bp);
xfs_buf_hold(bp);
xfs_buf_lock(bp);
bp->b_io_length = nbblks;
}
bp->b_ops = &xfs_sb_buf_ops;
break;
+#ifdef CONFIG_XFS_RT
+ case XFS_BLFT_RTBITMAP_BUF:
+ case XFS_BLFT_RTSUMMARY_BUF:
+ /* no magic numbers for verification of RT buffers */
+ bp->b_ops = &xfs_rtbuf_ops;
+ break;
+#endif /* CONFIG_XFS_RT */
default:
xfs_warn(mp, "Unknown buffer type %d!",
xfs_blft_from_flags(buf_f));
return -ENOMEM;
/* instantiate the inode */
- xfs_dinode_from_disk(&ip->i_d, dip);
+ xfs_inode_from_disk(ip, dip);
ASSERT(ip->i_d.di_version >= 3);
error = xfs_iformat_fork(ip, dip);
int error;
int attr_index;
uint fields;
- xfs_icdinode_t *dicp;
+ struct xfs_log_dinode *ldip;
uint isize;
int need_free = 0;
error = -EFSCORRUPTED;
goto out_release;
}
- dicp = item->ri_buf[1].i_addr;
- if (unlikely(dicp->di_magic != XFS_DINODE_MAGIC)) {
+ ldip = item->ri_buf[1].i_addr;
+ if (unlikely(ldip->di_magic != XFS_DINODE_MAGIC)) {
xfs_alert(mp,
"%s: Bad inode log record, rec ptr 0x%p, ino %Ld",
__func__, item, in_f->ilf_ino);
* to skip replay when the on disk inode is newer than the log one
*/
if (!xfs_sb_version_hascrc(&mp->m_sb) &&
- dicp->di_flushiter < be16_to_cpu(dip->di_flushiter)) {
+ ldip->di_flushiter < be16_to_cpu(dip->di_flushiter)) {
/*
* Deal with the wrap case, DI_MAX_FLUSH is less
* than smaller numbers
*/
if (be16_to_cpu(dip->di_flushiter) == DI_MAX_FLUSH &&
- dicp->di_flushiter < (DI_MAX_FLUSH >> 1)) {
+ ldip->di_flushiter < (DI_MAX_FLUSH >> 1)) {
/* do nothing */
} else {
trace_xfs_log_recover_inode_skip(log, in_f);
}
/* Take the opportunity to reset the flush iteration count */
- dicp->di_flushiter = 0;
+ ldip->di_flushiter = 0;
- if (unlikely(S_ISREG(dicp->di_mode))) {
- if ((dicp->di_format != XFS_DINODE_FMT_EXTENTS) &&
- (dicp->di_format != XFS_DINODE_FMT_BTREE)) {
+ if (unlikely(S_ISREG(ldip->di_mode))) {
+ if ((ldip->di_format != XFS_DINODE_FMT_EXTENTS) &&
+ (ldip->di_format != XFS_DINODE_FMT_BTREE)) {
XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(3)",
- XFS_ERRLEVEL_LOW, mp, dicp);
+ XFS_ERRLEVEL_LOW, mp, ldip);
xfs_alert(mp,
"%s: Bad regular inode log record, rec ptr 0x%p, "
"ino ptr = 0x%p, ino bp = 0x%p, ino %Ld",
error = -EFSCORRUPTED;
goto out_release;
}
- } else if (unlikely(S_ISDIR(dicp->di_mode))) {
- if ((dicp->di_format != XFS_DINODE_FMT_EXTENTS) &&
- (dicp->di_format != XFS_DINODE_FMT_BTREE) &&
- (dicp->di_format != XFS_DINODE_FMT_LOCAL)) {
+ } else if (unlikely(S_ISDIR(ldip->di_mode))) {
+ if ((ldip->di_format != XFS_DINODE_FMT_EXTENTS) &&
+ (ldip->di_format != XFS_DINODE_FMT_BTREE) &&
+ (ldip->di_format != XFS_DINODE_FMT_LOCAL)) {
XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(4)",
- XFS_ERRLEVEL_LOW, mp, dicp);
+ XFS_ERRLEVEL_LOW, mp, ldip);
xfs_alert(mp,
"%s: Bad dir inode log record, rec ptr 0x%p, "
"ino ptr = 0x%p, ino bp = 0x%p, ino %Ld",
goto out_release;
}
}
- if (unlikely(dicp->di_nextents + dicp->di_anextents > dicp->di_nblocks)){
+ if (unlikely(ldip->di_nextents + ldip->di_anextents > ldip->di_nblocks)){
XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(5)",
- XFS_ERRLEVEL_LOW, mp, dicp);
+ XFS_ERRLEVEL_LOW, mp, ldip);
xfs_alert(mp,
"%s: Bad inode log record, rec ptr 0x%p, dino ptr 0x%p, "
"dino bp 0x%p, ino %Ld, total extents = %d, nblocks = %Ld",
__func__, item, dip, bp, in_f->ilf_ino,
- dicp->di_nextents + dicp->di_anextents,
- dicp->di_nblocks);
+ ldip->di_nextents + ldip->di_anextents,
+ ldip->di_nblocks);
error = -EFSCORRUPTED;
goto out_release;
}
- if (unlikely(dicp->di_forkoff > mp->m_sb.sb_inodesize)) {
+ if (unlikely(ldip->di_forkoff > mp->m_sb.sb_inodesize)) {
XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(6)",
- XFS_ERRLEVEL_LOW, mp, dicp);
+ XFS_ERRLEVEL_LOW, mp, ldip);
xfs_alert(mp,
"%s: Bad inode log record, rec ptr 0x%p, dino ptr 0x%p, "
"dino bp 0x%p, ino %Ld, forkoff 0x%x", __func__,
- item, dip, bp, in_f->ilf_ino, dicp->di_forkoff);
+ item, dip, bp, in_f->ilf_ino, ldip->di_forkoff);
error = -EFSCORRUPTED;
goto out_release;
}
- isize = xfs_icdinode_size(dicp->di_version);
+ isize = xfs_log_dinode_size(ldip->di_version);
if (unlikely(item->ri_buf[1].i_len > isize)) {
XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(7)",
- XFS_ERRLEVEL_LOW, mp, dicp);
+ XFS_ERRLEVEL_LOW, mp, ldip);
xfs_alert(mp,
"%s: Bad inode log record length %d, rec ptr 0x%p",
__func__, item->ri_buf[1].i_len, item);
goto out_release;
}
- /* The core is in in-core format */
- xfs_dinode_to_disk(dip, dicp);
+ /* recover the log dinode inode into the on disk inode */
+ xfs_log_dinode_to_disk(ldip, dip);
/* the rest is in on-disk format */
if (item->ri_buf[1].i_len > isize) {
if (error)
goto fail_iput;
- ASSERT(ip->i_d.di_nlink == 0);
- ASSERT(ip->i_d.di_mode != 0);
+ ASSERT(VFS_I(ip)->i_nlink == 0);
+ ASSERT(VFS_I(ip)->i_mode != 0);
/* setup for the next pass */
agino = be32_to_cpu(dip->di_next_unlinked);
* know precisely what failed.
*/
if (pass == XLOG_RECOVER_CRCPASS) {
- if (rhead->h_crc && crc != le32_to_cpu(rhead->h_crc))
+ if (rhead->h_crc && crc != rhead->h_crc)
return -EFSBADCRC;
return 0;
}
* zero CRC check prevents warnings from being emitted when upgrading
* the kernel from one that does not add CRCs by default.
*/
- if (crc != le32_to_cpu(rhead->h_crc)) {
+ if (crc != rhead->h_crc) {
if (rhead->h_crc || xfs_sb_version_hascrc(&log->l_mp->m_sb)) {
xfs_alert(log->l_mp,
"log record CRC mismatch: found 0x%x, expected 0x%x.",
* updates, re-read in the superblock and reverify it.
*/
bp = xfs_getsb(log->l_mp, 0);
- XFS_BUF_UNDONE(bp);
- ASSERT(!(XFS_BUF_ISWRITE(bp)));
- XFS_BUF_READ(bp);
- XFS_BUF_UNASYNC(bp);
+ bp->b_flags &= ~(XBF_DONE | XBF_ASYNC);
+ ASSERT(!(bp->b_flags & XBF_WRITE));
+ bp->b_flags |= XBF_READ;
bp->b_ops = &xfs_sb_buf_ops;
error = xfs_buf_submit_wait(bp);
ASSERT(rip != NULL);
- if (unlikely(!S_ISDIR(rip->i_d.di_mode))) {
+ if (unlikely(!S_ISDIR(VFS_I(rip)->i_mode))) {
xfs_warn(mp, "corrupted root inode %llu: not a directory",
(unsigned long long)rip->i_ino);
xfs_iunlock(rip, XFS_ILOCK_EXCL);
}
xfs_buf_hold(bp);
- ASSERT(XFS_BUF_ISDONE(bp));
+ ASSERT(bp->b_flags & XBF_DONE);
return bp;
}
bool reserved);
extern int xfs_mod_frextents(struct xfs_mount *mp, int64_t delta);
-extern int xfs_mount_log_sb(xfs_mount_t *);
extern struct xfs_buf *xfs_getsb(xfs_mount_t *, int);
extern int xfs_readsb(xfs_mount_t *, int);
extern void xfs_freesb(xfs_mount_t *);
ASSERT(xfs_isilocked(mp->m_rbmip, XFS_ILOCK_EXCL));
- seqp = (__uint64_t *)&mp->m_rbmip->i_d.di_atime;
+ seqp = (__uint64_t *)&VFS_I(mp->m_rbmip)->i_atime;
if (!(mp->m_rbmip->i_d.di_flags & XFS_DIFLAG_NEWRTBM)) {
mp->m_rbmip->i_d.di_flags |= XFS_DIFLAG_NEWRTBM;
*seqp = 0;
DEFINE_IOMAP_EVENT(xfs_map_blocks_alloc);
DEFINE_IOMAP_EVENT(xfs_get_blocks_found);
DEFINE_IOMAP_EVENT(xfs_get_blocks_alloc);
-DEFINE_IOMAP_EVENT(xfs_gbmap_direct);
-DEFINE_IOMAP_EVENT(xfs_gbmap_direct_new);
-DEFINE_IOMAP_EVENT(xfs_gbmap_direct_update);
-DEFINE_IOMAP_EVENT(xfs_gbmap_direct_none);
-DEFINE_IOMAP_EVENT(xfs_gbmap_direct_endio);
+DEFINE_IOMAP_EVENT(xfs_get_blocks_map_direct);
DECLARE_EVENT_CLASS(xfs_simple_io_class,
TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count),
DEFINE_SIMPLE_IO_EVENT(xfs_get_blocks_notfound);
DEFINE_SIMPLE_IO_EVENT(xfs_setfilesize);
DEFINE_SIMPLE_IO_EVENT(xfs_zero_eof);
+DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write);
+DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write_unwritten);
+DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write_append);
DECLARE_EVENT_CLASS(xfs_itrunc_class,
TP_PROTO(struct xfs_inode *ip, xfs_fsize_t new_size),
long tout = 0; /* milliseconds */
current->flags |= PF_MEMALLOC;
+ set_freezable();
while (!kthread_should_stop()) {
if (tout && tout <= 20)
if (!xfs_ail_min(ailp) &&
ailp->xa_target == ailp->xa_target_prev) {
spin_unlock(&ailp->xa_lock);
- schedule();
+ freezable_schedule();
tout = 0;
continue;
}
spin_unlock(&ailp->xa_lock);
if (tout)
- schedule_timeout(msecs_to_jiffies(tout));
+ freezable_schedule_timeout(msecs_to_jiffies(tout));
__set_current_state(TASK_RUNNING);
ASSERT(xfs_buf_islocked(bp));
if (XFS_FORCED_SHUTDOWN(tp->t_mountp)) {
xfs_buf_stale(bp);
- XFS_BUF_DONE(bp);
+ bp->b_flags |= XBF_DONE;
}
ASSERT(bp->b_transp == tp);
* inside the b_bdstrat callback so that this won't get written to
* disk.
*/
- XFS_BUF_DONE(bp);
+ bp->b_flags |= XBF_DONE;
ASSERT(atomic_read(&bip->bli_refcount) > 0);
bp->b_iodone = xfs_buf_iodone_callbacks;
*/
if (bip->bli_flags & XFS_BLI_STALE) {
bip->bli_flags &= ~XFS_BLI_STALE;
- ASSERT(XFS_BUF_ISSTALE(bp));
- XFS_BUF_UNSTALE(bp);
+ ASSERT(bp->b_flags & XBF_STALE);
+ bp->b_flags &= ~XBF_STALE;
bip->__bli_format.blf_flags &= ~XFS_BLF_CANCEL;
}
* If the buffer is already invalidated, then
* just return.
*/
- ASSERT(XFS_BUF_ISSTALE(bp));
+ ASSERT(bp->b_flags & XBF_STALE);
ASSERT(!(bip->bli_flags & (XFS_BLI_LOGGED | XFS_BLI_DIRTY)));
ASSERT(!(bip->__bli_format.blf_flags & XFS_BLF_INODE_BUF));
ASSERT(!(bip->__bli_format.blf_flags & XFS_BLFT_MASK));
tv = current_fs_time(inode->i_sb);
- if ((flags & XFS_ICHGTIME_MOD) &&
- !timespec_equal(&inode->i_mtime, &tv)) {
+ if (flags & XFS_ICHGTIME_MOD)
inode->i_mtime = tv;
- ip->i_d.di_mtime.t_sec = tv.tv_sec;
- ip->i_d.di_mtime.t_nsec = tv.tv_nsec;
- }
- if ((flags & XFS_ICHGTIME_CHG) &&
- !timespec_equal(&inode->i_ctime, &tv)) {
+ if (flags & XFS_ICHGTIME_CHG)
inode->i_ctime = tv;
- ip->i_d.di_ctime.t_sec = tv.tv_sec;
- ip->i_d.di_ctime.t_nsec = tv.tv_nsec;
- }
}
/*
*/
if (!(ip->i_itemp->ili_item.li_desc->lid_flags & XFS_LID_DIRTY) &&
IS_I_VERSION(VFS_I(ip))) {
- ip->i_d.di_changecount = ++VFS_I(ip)->i_version;
+ VFS_I(ip)->i_version++;
flags |= XFS_ILOG_CORE;
}
struct buffer_head;
typedef int (get_block_t)(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
-typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
+typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
ssize_t bytes, void *private);
typedef void (dax_iodone_t)(struct buffer_head *bh_map, int uptodate);