STATIC void
xfs_fstrm_free_func(
unsigned long ino,
void *data)
{
fstrm_item_t *item = (fstrm_item_t *)data;
xfs_inode_t *ip = item->ip;
ASSERT(ip->i_ino == ino);
xfs_iflags_clear(ip, XFS_IFILESTREAM);
xfs_filestream_put_ag(ip->i_mount, item->ag);
TRACE_FREE(ip->i_mount, ip, item->pip, item->ag,
xfs_filestream_peek_ag(ip->i_mount, item->ag));
IRELE(ip);
if (item->pip)
IRELE(item->pip);
kmem_zone_free(item_zone, item);
}
STATIC int
xfs_file_fsync(
struct file *file,
loff_t start,
loff_t end,
int datasync)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
int error = 0;
int log_flushed = 0;
xfs_lsn_t lsn = 0;
trace_xfs_file_fsync(ip);
error = filemap_write_and_wait_range(inode->i_mapping, start, end);
if (error)
return error;
if (XFS_FORCED_SHUTDOWN(mp))
return -XFS_ERROR(EIO);
xfs_iflags_clear(ip, XFS_ITRUNCATED);
if (mp->m_flags & XFS_MOUNT_BARRIER) {
/*
* If we have an RT and/or log subvolume we need to make sure
* to flush the write cache the device used for file data
* first. This is to ensure newly written file data make
* it to disk before logging the new inode size in case of
* an extending write.
*/
if (XFS_IS_REALTIME_INODE(ip))
xfs_blkdev_issue_flush(mp->m_rtdev_targp);
else if (mp->m_logdev_targp != mp->m_ddev_targp)
xfs_blkdev_issue_flush(mp->m_ddev_targp);
}
xfs_ilock(ip, XFS_ILOCK_SHARED);
if (xfs_ipincount(ip)) {
if (!datasync ||
(ip->i_itemp->ili_fields & ~XFS_ILOG_TIMESTAMP))
lsn = ip->i_itemp->ili_last_lsn;
}
xfs_iunlock(ip, XFS_ILOCK_SHARED);
if (lsn)
error = _xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, &log_flushed);
if ((mp->m_flags & XFS_MOUNT_BARRIER) &&
mp->m_logdev_targp == mp->m_ddev_targp &&
!XFS_IS_REALTIME_INODE(ip) &&
!log_flushed)
xfs_blkdev_issue_flush(mp->m_ddev_targp);
return -error;
}
/*
* We ignore the datasync flag here because a datasync is effectively
* identical to an fsync. That is, datasync implies that we need to write
* only the metadata needed to be able to access the data that is written
* if we crash after the call completes. Hence if we are writing beyond
* EOF we have to log the inode size change as well, which makes it a
* full fsync. If we don't write beyond EOF, the inode core will be
* clean in memory and so we don't need to log the inode, just like
* fsync.
*/
STATIC int
xfs_file_fsync(
struct file *filp,
struct dentry *dentry,
int datasync)
{
xfs_iflags_clear(XFS_I(dentry->d_inode), XFS_ITRUNCATED);
return -xfs_fsync(XFS_I(dentry->d_inode));
}
STATIC int
xfs_file_fsync(
struct file *filp,
struct dentry *dentry,
int datasync)
{
int flags = FSYNC_WAIT;
if (datasync)
flags |= FSYNC_DATA;
xfs_iflags_clear(XFS_I(dentry->d_inode), XFS_ITRUNCATED);
return -xfs_fsync(XFS_I(dentry->d_inode), flags,
(xfs_off_t)0, (xfs_off_t)-1);
}
/*
* Revalidate the Linux inode from the XFS inode.
* Note: i_size _not_ updated; we must hold the inode
* semaphore when doing that - callers responsibility.
*/
int
vn_revalidate(
bhv_vnode_t *vp)
{
struct inode *inode = vn_to_inode(vp);
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
unsigned long xflags;
xfs_itrace_entry(ip);
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
xfs_ilock(ip, XFS_ILOCK_SHARED);
inode->i_mode = ip->i_d.di_mode;
inode->i_uid = ip->i_d.di_uid;
inode->i_gid = ip->i_d.di_gid;
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;
xflags = xfs_ip2xflags(ip);
if (xflags & XFS_XFLAG_IMMUTABLE)
inode->i_flags |= S_IMMUTABLE;
else
inode->i_flags &= ~S_IMMUTABLE;
if (xflags & XFS_XFLAG_APPEND)
inode->i_flags |= S_APPEND;
else
inode->i_flags &= ~S_APPEND;
if (xflags & XFS_XFLAG_SYNC)
inode->i_flags |= S_SYNC;
else
inode->i_flags &= ~S_SYNC;
if (xflags & XFS_XFLAG_NOATIME)
inode->i_flags |= S_NOATIME;
else
inode->i_flags &= ~S_NOATIME;
xfs_iunlock(ip, XFS_ILOCK_SHARED);
xfs_iflags_clear(ip, XFS_IMODIFIED);
return 0;
}
int
xfs_flushinval_pages(
xfs_inode_t *ip,
xfs_off_t first,
xfs_off_t last,
int fiopt)
{
struct address_space *mapping = ip->i_vnode->i_mapping;
int ret = 0;
if (mapping->nrpages) {
xfs_iflags_clear(ip, XFS_ITRUNCATED);
ret = filemap_write_and_wait(mapping);
if (!ret)
truncate_inode_pages(mapping, first);
}
return ret;
}
int
xfs_flushinval_pages(
xfs_inode_t *ip,
xfs_off_t first,
xfs_off_t last,
int fiopt)
{
struct address_space *mapping = VFS_I(ip)->i_mapping;
int ret = 0;
trace_xfs_pagecache_inval(ip, first, last);
xfs_iflags_clear(ip, XFS_ITRUNCATED);
ret = filemap_write_and_wait_range(mapping, first,
last == -1 ? LLONG_MAX : last);
if (!ret)
truncate_inode_pages_range(mapping, first, last);
return -ret;
}
/* xfs_fstrm_free_func(): callback for freeing cached stream items. */
STATIC void
xfs_fstrm_free_func(
unsigned long ino,
void *data)
{
fstrm_item_t *item = (fstrm_item_t *)data;
xfs_inode_t *ip = item->ip;
int ref;
ASSERT(ip->i_ino == ino);
xfs_iflags_clear(ip, XFS_IFILESTREAM);
/* Drop the reference taken on the AG when the item was added. */
ref = xfs_filestream_put_ag(ip->i_mount, item->ag);
ASSERT(ref >= 0);
TRACE_FREE(ip->i_mount, ip, item->pip, item->ag,
xfs_filestream_peek_ag(ip->i_mount, item->ag));
/*
* _xfs_filestream_update_ag() always takes a reference on the inode
* itself, whether it's a file or a directory. Release it here.
* This can result in the inode being freed and so we must
* not hold any inode locks when freeing filesstreams objects
* otherwise we can deadlock here.
*/
IRELE(ip);
/*
* In the case of a regular file, _xfs_filestream_update_ag() also
* takes a ref on the parent inode to keep it in-core. Release that
* too.
*/
if (item->pip)
IRELE(item->pip);
/* Finally, free the memory allocated for the item. */
kmem_zone_free(item_zone, item);
}
int
xfs_flush_pages(
xfs_inode_t *ip,
xfs_off_t first,
xfs_off_t last,
uint64_t flags,
int fiopt)
{
struct address_space *mapping = VFS_I(ip)->i_mapping;
int ret = 0;
int ret2;
xfs_iflags_clear(ip, XFS_ITRUNCATED);
ret = -filemap_fdatawrite_range(mapping, first,
last == -1 ? LLONG_MAX : last);
if (flags & XBF_ASYNC)
return ret;
ret2 = xfs_wait_on_pages(ip, first, last);
if (!ret)
ret = ret2;
return ret;
}
int
xfs_flush_pages(
xfs_inode_t *ip,
xfs_off_t first,
xfs_off_t last,
uint64_t flags,
int fiopt)
{
struct address_space *mapping = VFS_I(ip)->i_mapping;
int ret = 0;
int ret2;
if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
xfs_iflags_clear(ip, XFS_ITRUNCATED);
ret = -filemap_fdatawrite(mapping);
}
if (flags & XBF_ASYNC)
return ret;
ret2 = xfs_wait_on_pages(ip, first, last);
if (!ret)
ret = ret2;
return ret;
}
/*
* Initialize the Linux inode, set up the operation vectors and
* unlock the inode.
*
* When reading existing inodes from disk this is called directly
* from xfs_iget, when creating a new inode it is called from
* xfs_ialloc after setting up the inode.
*
* We are always called with an uninitialised linux inode here.
* We need to initialise the necessary fields and take a reference
* on it.
*/
void
xfs_setup_inode(
struct xfs_inode *ip)
{
struct inode *inode = &ip->i_vnode;
inode->i_ino = ip->i_ino;
inode->i_state = I_NEW;
inode_sb_list_add(inode);
insert_inode_hash(inode);
inode->i_mode = ip->i_d.di_mode;
inode->i_nlink = ip->i_d.di_nlink;
inode->i_uid = ip->i_d.di_uid;
inode->i_gid = ip->i_d.di_gid;
switch (inode->i_mode & S_IFMT) {
case S_IFBLK:
case S_IFCHR:
inode->i_rdev =
MKDEV(sysv_major(ip->i_df.if_u2.if_rdev) & 0x1ff,
sysv_minor(ip->i_df.if_u2.if_rdev));
break;
default:
inode->i_rdev = 0;
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);
switch (inode->i_mode & S_IFMT) {
case S_IFREG:
inode->i_op = &xfs_inode_operations;
inode->i_fop = &xfs_file_operations;
inode->i_mapping->a_ops = &xfs_address_space_operations;
break;
case S_IFDIR:
if (xfs_sb_version_hasasciici(&XFS_M(inode->i_sb)->m_sb))
inode->i_op = &xfs_dir_ci_inode_operations;
else
inode->i_op = &xfs_dir_inode_operations;
inode->i_fop = &xfs_dir_file_operations;
break;
case S_IFLNK:
inode->i_op = &xfs_symlink_inode_operations;
if (!(ip->i_df.if_flags & XFS_IFINLINE))
inode->i_mapping->a_ops = &xfs_address_space_operations;
break;
default:
inode->i_op = &xfs_inode_operations;
init_special_inode(inode, inode->i_mode, inode->i_rdev);
break;
}
xfs_iflags_clear(ip, XFS_INEW);
barrier();
unlock_new_inode(inode);
}
/*
* Initialize the Linux inode, set up the operation vectors and
* unlock the inode.
*
* When reading existing inodes from disk this is called directly
* from xfs_iget, when creating a new inode it is called from
* xfs_ialloc after setting up the inode.
*
* We are always called with an uninitialised linux inode here.
* We need to initialise the necessary fields and take a reference
* on it.
*/
void
xfs_setup_inode(
struct xfs_inode *ip)
{
struct inode *inode = &ip->i_vnode;
gfp_t gfp_mask;
inode->i_ino = ip->i_ino;
inode->i_state = I_NEW;
inode_sb_list_add(inode);
/* 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);
switch (inode->i_mode & S_IFMT) {
case S_IFBLK:
case S_IFCHR:
inode->i_rdev =
MKDEV(sysv_major(ip->i_df.if_u2.if_rdev) & 0x1ff,
sysv_minor(ip->i_df.if_u2.if_rdev));
break;
default:
inode->i_rdev = 0;
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;
lockdep_set_class(&ip->i_lock.mr_lock, &xfs_nondir_ilock_class);
switch (inode->i_mode & S_IFMT) {
case S_IFREG:
inode->i_op = &xfs_inode_operations;
inode->i_fop = &xfs_file_operations;
inode->i_mapping->a_ops = &xfs_address_space_operations;
break;
case S_IFDIR:
lockdep_set_class(&ip->i_lock.mr_lock, &xfs_dir_ilock_class);
if (xfs_sb_version_hasasciici(&XFS_M(inode->i_sb)->m_sb))
inode->i_op = &xfs_dir_ci_inode_operations;
else
inode->i_op = &xfs_dir_inode_operations;
inode->i_fop = &xfs_dir_file_operations;
ip->d_ops = ip->i_mount->m_dir_inode_ops;
break;
case S_IFLNK:
inode->i_op = &xfs_symlink_inode_operations;
if (!(ip->i_df.if_flags & XFS_IFINLINE))
inode->i_mapping->a_ops = &xfs_address_space_operations;
break;
default:
inode->i_op = &xfs_inode_operations;
init_special_inode(inode, inode->i_mode, inode->i_rdev);
break;
}
/*
* Ensure all page cache allocations are done from GFP_NOFS context to
* prevent direct reclaim recursion back into the filesystem and blowing
* stacks or deadlocking.
*/
gfp_mask = mapping_gfp_mask(inode->i_mapping);
mapping_set_gfp_mask(inode->i_mapping, (gfp_mask & ~(__GFP_FS)));
/*
* If there is no attribute fork no ACL can exist on this inode,
* and it can't have any file capabilities attached to it either.
*/
if (!XFS_IFORK_Q(ip)) {
inode_has_no_xattr(inode);
cache_no_acl(inode);
}
xfs_iflags_clear(ip, XFS_INEW);
barrier();
unlock_new_inode(inode);
}
STATIC int
xfs_file_fsync(
struct file *file,
loff_t start,
loff_t end,
int datasync)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
int error = 0;
int log_flushed = 0;
xfs_lsn_t lsn = 0;
trace_xfs_file_fsync(ip);
error = filemap_write_and_wait_range(inode->i_mapping, start, end);
if (error)
return error;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
xfs_iflags_clear(ip, XFS_ITRUNCATED);
if (mp->m_flags & XFS_MOUNT_BARRIER) {
/*
* If we have an RT and/or log subvolume we need to make sure
* to flush the write cache the device used for file data
* first. This is to ensure newly written file data make
* it to disk before logging the new inode size in case of
* an extending write.
*/
if (XFS_IS_REALTIME_INODE(ip))
xfs_blkdev_issue_flush(mp->m_rtdev_targp);
else if (mp->m_logdev_targp != mp->m_ddev_targp)
xfs_blkdev_issue_flush(mp->m_ddev_targp);
}
/*
* All metadata updates are logged, which means that we just have
* to flush the log up to the latest LSN that touched the inode.
*/
xfs_ilock(ip, XFS_ILOCK_SHARED);
if (xfs_ipincount(ip)) {
if (!datasync ||
(ip->i_itemp->ili_fields & ~XFS_ILOG_TIMESTAMP))
lsn = ip->i_itemp->ili_last_lsn;
}
xfs_iunlock(ip, XFS_ILOCK_SHARED);
if (lsn)
error = _xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, &log_flushed);
/*
* If we only have a single device, and the log force about was
* a no-op we might have to flush the data device cache here.
* This can only happen for fdatasync/O_DSYNC if we were overwriting
* an already allocated file and thus do not have any metadata to
* commit.
*/
if ((mp->m_flags & XFS_MOUNT_BARRIER) &&
mp->m_logdev_targp == mp->m_ddev_targp &&
!XFS_IS_REALTIME_INODE(ip) &&
!log_flushed)
xfs_blkdev_issue_flush(mp->m_ddev_targp);
return error;
}
STATIC int
xfs_file_fsync(
struct file *file,
struct dentry *dentry,
int datasync)
{
struct xfs_inode *ip = XFS_I(dentry->d_inode);
struct xfs_trans *tp;
int error = 0;
int log_flushed = 0;
xfs_itrace_entry(ip);
if (XFS_FORCED_SHUTDOWN(ip->i_mount))
return -XFS_ERROR(EIO);
xfs_iflags_clear(ip, XFS_ITRUNCATED);
/*
* We always need to make sure that the required inode state is safe on
* disk. The inode might be clean but we still might need to force the
* log because of committed transactions that haven't hit the disk yet.
* Likewise, there could be unflushed non-transactional changes to the
* inode core that have to go to disk and this requires us to issue
* a synchronous transaction to capture these changes correctly.
*
* This code relies on the assumption that if the i_update_core field
* of the inode is clear and the inode is unpinned then it is clean
* and no action is required.
*/
xfs_ilock(ip, XFS_ILOCK_SHARED);
/*
* First check if the VFS inode is marked dirty. All the dirtying
* of non-transactional updates no goes through mark_inode_dirty*,
* which allows us to distinguish beteeen pure timestamp updates
* and i_size updates which need to be caught for fdatasync.
* After that also theck for the dirty state in the XFS inode, which
* might gets cleared when the inode gets written out via the AIL
* or xfs_iflush_cluster.
*/
if (((dentry->d_inode->i_state & I_DIRTY_DATASYNC) ||
((dentry->d_inode->i_state & I_DIRTY_SYNC) && !datasync)) &&
ip->i_update_core) {
/*
* Kick off a transaction to log the inode core to get the
* updates. The sync transaction will also force the log.
*/
xfs_iunlock(ip, XFS_ILOCK_SHARED);
tp = xfs_trans_alloc(ip->i_mount, XFS_TRANS_FSYNC_TS);
error = xfs_trans_reserve(tp, 0,
XFS_FSYNC_TS_LOG_RES(ip->i_mount), 0, 0, 0);
if (error) {
xfs_trans_cancel(tp, 0);
return -error;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
/*
* Note - it's possible that we might have pushed ourselves out
* of the way during trans_reserve which would flush the inode.
* But there's no guarantee that the inode buffer has actually
* gone out yet (it's delwri). Plus the buffer could be pinned
* anyway if it's part of an inode in another recent
* transaction. So we play it safe and fire off the
* transaction anyway.
*/
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
xfs_trans_ihold(tp, ip);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
xfs_trans_set_sync(tp);
error = _xfs_trans_commit(tp, 0, &log_flushed);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
} else {
/*
* Timestamps/size haven't changed since last inode flush or
* inode transaction commit. That means either nothing got
* written or a transaction committed which caught the updates.
* If the latter happened and the transaction hasn't hit the
* disk yet, the inode will be still be pinned. If it is,
* force the log.
*/
if (xfs_ipincount(ip)) {
error = _xfs_log_force_lsn(ip->i_mount,
ip->i_itemp->ili_last_lsn,
XFS_LOG_SYNC, &log_flushed);
}
xfs_iunlock(ip, XFS_ILOCK_SHARED);
}
if (ip->i_mount->m_flags & XFS_MOUNT_BARRIER) {
/*
* If the log write didn't issue an ordered tag we need
* to flush the disk cache for the data device now.
*/
if (!log_flushed)
xfs_blkdev_issue_flush(ip->i_mount->m_ddev_targp);
/*
* If this inode is on the RT dev we need to flush that
* cache as well.
*/
if (XFS_IS_REALTIME_INODE(ip))
xfs_blkdev_issue_flush(ip->i_mount->m_rtdev_targp);
}
return -error;
}
/*
* Inodes in different states need to be treated differently, and the return
* value of xfs_iflush is not sufficient to get this right. The following table
* lists the inode states and the reclaim actions necessary for non-blocking
* reclaim:
*
*
* inode state iflush ret required action
* --------------- ---------- ---------------
* bad - reclaim
* shutdown EIO unpin and reclaim
* clean, unpinned 0 reclaim
* stale, unpinned 0 reclaim
* clean, pinned(*) 0 requeue
* stale, pinned EAGAIN requeue
* dirty, delwri ok 0 requeue
* dirty, delwri blocked EAGAIN requeue
* dirty, sync flush 0 reclaim
*
* (*) dgc: I don't think the clean, pinned state is possible but it gets
* handled anyway given the order of checks implemented.
*
* As can be seen from the table, the return value of xfs_iflush() is not
* sufficient to correctly decide the reclaim action here. The checks in
* xfs_iflush() might look like duplicates, but they are not.
*
* Also, because we get the flush lock first, we know that any inode that has
* been flushed delwri has had the flush completed by the time we check that
* the inode is clean. The clean inode check needs to be done before flushing
* the inode delwri otherwise we would loop forever requeuing clean inodes as
* we cannot tell apart a successful delwri flush and a clean inode from the
* return value of xfs_iflush().
*
* Note that because the inode is flushed delayed write by background
* writeback, the flush lock may already be held here and waiting on it can
* result in very long latencies. Hence for sync reclaims, where we wait on the
* flush lock, the caller should push out delayed write inodes first before
* trying to reclaim them to minimise the amount of time spent waiting. For
* background relaim, we just requeue the inode for the next pass.
*
* Hence the order of actions after gaining the locks should be:
* bad => reclaim
* shutdown => unpin and reclaim
* pinned, delwri => requeue
* pinned, sync => unpin
* stale => reclaim
* clean => reclaim
* dirty, delwri => flush and requeue
* dirty, sync => flush, wait and reclaim
*/
STATIC int
xfs_reclaim_inode(
struct xfs_inode *ip,
struct xfs_perag *pag,
int sync_mode)
{
int error;
restart:
error = 0;
xfs_ilock(ip, XFS_ILOCK_EXCL);
if (!xfs_iflock_nowait(ip)) {
if (!(sync_mode & SYNC_WAIT))
goto out;
/*
* If we only have a single dirty inode in a cluster there is
* a fair chance that the AIL push may have pushed it into
* the buffer, but xfsbufd won't touch it until 30 seconds
* from now, and thus we will lock up here.
*
* Promote the inode buffer to the front of the delwri list
* and wake up xfsbufd now.
*/
xfs_promote_inode(ip);
xfs_iflock(ip);
}
if (is_bad_inode(VFS_I(ip)))
goto reclaim;
if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
xfs_iunpin_wait(ip);
goto reclaim;
}
if (xfs_ipincount(ip)) {
if (!(sync_mode & SYNC_WAIT)) {
xfs_ifunlock(ip);
goto out;
}
xfs_iunpin_wait(ip);
}
if (xfs_iflags_test(ip, XFS_ISTALE))
goto reclaim;
if (xfs_inode_clean(ip))
goto reclaim;
/*
* Now we have an inode that needs flushing.
*
* We do a nonblocking flush here even if we are doing a SYNC_WAIT
* reclaim as we can deadlock with inode cluster removal.
* xfs_ifree_cluster() can lock the inode buffer before it locks the
* ip->i_lock, and we are doing the exact opposite here. As a result,
* doing a blocking xfs_itobp() to get the cluster buffer will result
* in an ABBA deadlock with xfs_ifree_cluster().
*
* As xfs_ifree_cluser() must gather all inodes that are active in the
* cache to mark them stale, if we hit this case we don't actually want
* to do IO here - we want the inode marked stale so we can simply
* reclaim it. Hence if we get an EAGAIN error on a SYNC_WAIT flush,
* just unlock the inode, back off and try again. Hopefully the next
* pass through will see the stale flag set on the inode.
*/
error = xfs_iflush(ip, SYNC_TRYLOCK | sync_mode);
if (sync_mode & SYNC_WAIT) {
if (error == EAGAIN) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
/* backoff longer than in xfs_ifree_cluster */
delay(2);
goto restart;
}
xfs_iflock(ip);
goto reclaim;
}
/*
* When we have to flush an inode but don't have SYNC_WAIT set, we
* flush the inode out using a delwri buffer and wait for the next
* call into reclaim to find it in a clean state instead of waiting for
* it now. We also don't return errors here - if the error is transient
* then the next reclaim pass will flush the inode, and if the error
* is permanent then the next sync reclaim will reclaim the inode and
* pass on the error.
*/
if (error && error != EAGAIN && !XFS_FORCED_SHUTDOWN(ip->i_mount)) {
xfs_warn(ip->i_mount,
"inode 0x%llx background reclaim flush failed with %d",
(long long)ip->i_ino, error);
}
out:
xfs_iflags_clear(ip, XFS_IRECLAIM);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
/*
* We could return EAGAIN here to make reclaim rescan the inode tree in
* a short while. However, this just burns CPU time scanning the tree
* waiting for IO to complete and xfssyncd never goes back to the idle
* state. Instead, return 0 to let the next scheduled background reclaim
* attempt to reclaim the inode again.
*/
return 0;
reclaim:
xfs_ifunlock(ip);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
XFS_STATS_INC(xs_ig_reclaims);
/*
* Remove the inode from the per-AG radix tree.
*
* Because radix_tree_delete won't complain even if the item was never
* added to the tree assert that it's been there before to catch
* problems with the inode life time early on.
*/
spin_lock(&pag->pag_ici_lock);
if (!radix_tree_delete(&pag->pag_ici_root,
XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino)))
ASSERT(0);
__xfs_inode_clear_reclaim(pag, ip);
spin_unlock(&pag->pag_ici_lock);
/*
* Here we do an (almost) spurious inode lock in order to coordinate
* with inode cache radix tree lookups. This is because the lookup
* can reference the inodes in the cache without taking references.
*
* We make that OK here by ensuring that we wait until the inode is
* unlocked after the lookup before we go ahead and free it. We get
* both the ilock and the iolock because the code may need to drop the
* ilock one but will still hold the iolock.
*/
xfs_ilock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
xfs_qm_dqdetach(ip);
xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
xfs_inode_free(ip);
return error;
}
/*
* Inodes in different states need to be treated differently. The following
* table lists the inode states and the reclaim actions necessary:
*
* inode state iflush ret required action
* --------------- ---------- ---------------
* bad - reclaim
* shutdown EIO unpin and reclaim
* clean, unpinned 0 reclaim
* stale, unpinned 0 reclaim
* clean, pinned(*) 0 requeue
* stale, pinned EAGAIN requeue
* dirty, async - requeue
* dirty, sync 0 reclaim
*
* (*) dgc: I don't think the clean, pinned state is possible but it gets
* handled anyway given the order of checks implemented.
*
* Also, because we get the flush lock first, we know that any inode that has
* been flushed delwri has had the flush completed by the time we check that
* the inode is clean.
*
* Note that because the inode is flushed delayed write by AIL pushing, the
* flush lock may already be held here and waiting on it can result in very
* long latencies. Hence for sync reclaims, where we wait on the flush lock,
* the caller should push the AIL first before trying to reclaim inodes to
* minimise the amount of time spent waiting. For background relaim, we only
* bother to reclaim clean inodes anyway.
*
* Hence the order of actions after gaining the locks should be:
* bad => reclaim
* shutdown => unpin and reclaim
* pinned, async => requeue
* pinned, sync => unpin
* stale => reclaim
* clean => reclaim
* dirty, async => requeue
* dirty, sync => flush, wait and reclaim
*/
STATIC int
xfs_reclaim_inode(
struct xfs_inode *ip,
struct xfs_perag *pag,
int sync_mode)
{
struct xfs_buf *bp = NULL;
xfs_ino_t ino = ip->i_ino; /* for radix_tree_delete */
int error;
restart:
error = 0;
xfs_ilock(ip, XFS_ILOCK_EXCL);
if (!xfs_iflock_nowait(ip)) {
if (!(sync_mode & SYNC_WAIT))
goto out;
xfs_iflock(ip);
}
if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
xfs_iunpin_wait(ip);
/* xfs_iflush_abort() drops the flush lock */
xfs_iflush_abort(ip, false);
goto reclaim;
}
if (xfs_ipincount(ip)) {
if (!(sync_mode & SYNC_WAIT))
goto out_ifunlock;
xfs_iunpin_wait(ip);
}
if (xfs_iflags_test(ip, XFS_ISTALE) || xfs_inode_clean(ip)) {
xfs_ifunlock(ip);
goto reclaim;
}
/*
* Never flush out dirty data during non-blocking reclaim, as it would
* just contend with AIL pushing trying to do the same job.
*/
if (!(sync_mode & SYNC_WAIT))
goto out_ifunlock;
/*
* Now we have an inode that needs flushing.
*
* Note that xfs_iflush will never block on the inode buffer lock, as
* xfs_ifree_cluster() can lock the inode buffer before it locks the
* ip->i_lock, and we are doing the exact opposite here. As a result,
* doing a blocking xfs_imap_to_bp() to get the cluster buffer would
* result in an ABBA deadlock with xfs_ifree_cluster().
*
* As xfs_ifree_cluser() must gather all inodes that are active in the
* cache to mark them stale, if we hit this case we don't actually want
* to do IO here - we want the inode marked stale so we can simply
* reclaim it. Hence if we get an EAGAIN error here, just unlock the
* inode, back off and try again. Hopefully the next pass through will
* see the stale flag set on the inode.
*/
error = xfs_iflush(ip, &bp);
if (error == -EAGAIN) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
/* backoff longer than in xfs_ifree_cluster */
delay(2);
goto restart;
}
if (!error) {
error = xfs_bwrite(bp);
xfs_buf_relse(bp);
}
reclaim:
ASSERT(!xfs_isiflocked(ip));
/*
* Because we use RCU freeing we need to ensure the inode always appears
* to be reclaimed with an invalid inode number when in the free state.
* We do this as early as possible under the ILOCK so that
* xfs_iflush_cluster() can be guaranteed to detect races with us here.
* By doing this, we guarantee that once xfs_iflush_cluster has locked
* XFS_ILOCK that it will see either a valid, flushable inode that will
* serialise correctly, or it will see a clean (and invalid) inode that
* it can skip.
*/
spin_lock(&ip->i_flags_lock);
ip->i_flags = XFS_IRECLAIM;
ip->i_ino = 0;
spin_unlock(&ip->i_flags_lock);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
XFS_STATS_INC(ip->i_mount, xs_ig_reclaims);
/*
* Remove the inode from the per-AG radix tree.
*
* Because radix_tree_delete won't complain even if the item was never
* added to the tree assert that it's been there before to catch
* problems with the inode life time early on.
*/
spin_lock(&pag->pag_ici_lock);
if (!radix_tree_delete(&pag->pag_ici_root,
XFS_INO_TO_AGINO(ip->i_mount, ino)))
ASSERT(0);
xfs_perag_clear_reclaim_tag(pag);
spin_unlock(&pag->pag_ici_lock);
/*
* Here we do an (almost) spurious inode lock in order to coordinate
* with inode cache radix tree lookups. This is because the lookup
* can reference the inodes in the cache without taking references.
*
* We make that OK here by ensuring that we wait until the inode is
* unlocked after the lookup before we go ahead and free it.
*/
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_qm_dqdetach(ip);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
__xfs_inode_free(ip);
return error;
out_ifunlock:
xfs_ifunlock(ip);
out:
xfs_iflags_clear(ip, XFS_IRECLAIM);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
/*
* We could return -EAGAIN here to make reclaim rescan the inode tree in
* a short while. However, this just burns CPU time scanning the tree
* waiting for IO to complete and the reclaim work never goes back to
* the idle state. Instead, return 0 to let the next scheduled
* background reclaim attempt to reclaim the inode again.
*/
return 0;
}
/*
* Initialize the Linux inode, set up the operation vectors and
* unlock the inode.
*
* When reading existing inodes from disk this is called directly
* from xfs_iget, when creating a new inode it is called from
* xfs_ialloc after setting up the inode.
*
* We are always called with an uninitialised linux inode here.
* We need to initialise the necessary fields and take a reference
* on it.
*/
void
xfs_setup_inode(
struct xfs_inode *ip)
{
struct inode *inode = &ip->i_vnode;
gfp_t gfp_mask;
inode->i_ino = ip->i_ino;
inode->i_state = I_NEW|I_LOCK;
inode_add_to_lists(ip->i_mount->m_super, inode);
inode->i_mode = ip->i_d.di_mode;
inode->i_nlink = ip->i_d.di_nlink;
inode->i_uid = ip->i_d.di_uid;
inode->i_gid = ip->i_d.di_gid;
switch (inode->i_mode & S_IFMT) {
case S_IFBLK:
case S_IFCHR:
inode->i_rdev =
MKDEV(sysv_major(ip->i_df.if_u2.if_rdev) & 0x1ff,
sysv_minor(ip->i_df.if_u2.if_rdev));
break;
default:
inode->i_rdev = 0;
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);
switch (inode->i_mode & S_IFMT) {
case S_IFREG:
inode->i_op = &xfs_inode_operations;
inode->i_fop = &xfs_file_operations;
inode->i_mapping->a_ops = &xfs_address_space_operations;
break;
case S_IFDIR:
if (xfs_sb_version_hasasciici(&XFS_M(inode->i_sb)->m_sb))
inode->i_op = &xfs_dir_ci_inode_operations;
else
inode->i_op = &xfs_dir_inode_operations;
inode->i_fop = &xfs_dir_file_operations;
break;
case S_IFLNK:
inode->i_op = &xfs_symlink_inode_operations;
if (!(ip->i_df.if_flags & XFS_IFINLINE))
inode->i_mapping->a_ops = &xfs_address_space_operations;
break;
default:
inode->i_op = &xfs_inode_operations;
init_special_inode(inode, inode->i_mode, inode->i_rdev);
break;
}
/*
* Ensure all page cache allocations are done from GFP_NOFS context to
* prevent direct reclaim recursion back into the filesystem and blowing
* stacks or deadlocking.
*/
gfp_mask = mapping_gfp_mask(inode->i_mapping);
mapping_set_gfp_mask(inode->i_mapping, (gfp_mask & ~(__GFP_FS)));
xfs_iflags_clear(ip, XFS_INEW);
barrier();
unlock_new_inode(inode);
}
/*
* Initialize the Linux inode, set up the operation vectors and
* unlock the inode.
*
* When reading existing inodes from disk this is called directly
* from xfs_iget, when creating a new inode it is called from
* xfs_ialloc after setting up the inode.
*
* We are always called with an uninitialised linux inode here.
* We need to initialise the necessary fields and take a reference
* on it.
*/
void
xfs_setup_inode(
struct xfs_inode *ip)
{
struct inode *inode = &ip->i_vnode;
inode->i_ino = ip->i_ino;
inode->i_state = I_NEW;
inode_sb_list_add(inode);
/* make the inode look hashed for the writeback code */
hlist_add_fake(&inode->i_hash);
inode->i_mode = ip->i_d.di_mode;
inode->i_nlink = ip->i_d.di_nlink;
inode->i_uid = ip->i_d.di_uid;
inode->i_gid = ip->i_d.di_gid;
switch (inode->i_mode & S_IFMT) {
case S_IFBLK:
case S_IFCHR:
inode->i_rdev =
MKDEV(sysv_major(ip->i_df.if_u2.if_rdev) & 0x1ff,
sysv_minor(ip->i_df.if_u2.if_rdev));
break;
default:
inode->i_rdev = 0;
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);
switch (inode->i_mode & S_IFMT) {
case S_IFREG:
inode->i_op = &xfs_inode_operations;
inode->i_fop = &xfs_file_operations;
inode->i_mapping->a_ops = &xfs_address_space_operations;
break;
case S_IFDIR:
if (xfs_sb_version_hasasciici(&XFS_M(inode->i_sb)->m_sb))
inode->i_op = &xfs_dir_ci_inode_operations;
else
inode->i_op = &xfs_dir_inode_operations;
inode->i_fop = &xfs_dir_file_operations;
break;
case S_IFLNK:
inode->i_op = &xfs_symlink_inode_operations;
if (!(ip->i_df.if_flags & XFS_IFINLINE))
inode->i_mapping->a_ops = &xfs_address_space_operations;
break;
default:
inode->i_op = &xfs_inode_operations;
init_special_inode(inode, inode->i_mode, inode->i_rdev);
break;
}
/*
* If there is no attribute fork no ACL can exist on this inode,
* and it can't have any file capabilities attached to it either.
*/
if (!XFS_IFORK_Q(ip)) {
inode_has_no_xattr(inode);
cache_no_acl(inode);
}
xfs_iflags_clear(ip, XFS_INEW);
barrier();
unlock_new_inode(inode);
}
STATIC int
xfs_file_fsync(
struct file *file,
loff_t start,
loff_t end,
int datasync)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
int error = 0;
int log_flushed = 0;
xfs_lsn_t lsn = 0;
trace_xfs_file_fsync(ip);
error = file_write_and_wait_range(file, start, end);
if (error)
return error;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
xfs_iflags_clear(ip, XFS_ITRUNCATED);
/*
* If we have an RT and/or log subvolume we need to make sure to flush
* the write cache the device used for file data first. This is to
* ensure newly written file data make it to disk before logging the new
* inode size in case of an extending write.
*/
if (XFS_IS_REALTIME_INODE(ip))
xfs_blkdev_issue_flush(mp->m_rtdev_targp);
else if (mp->m_logdev_targp != mp->m_ddev_targp)
xfs_blkdev_issue_flush(mp->m_ddev_targp);
/*
* All metadata updates are logged, which means that we just have to
* flush the log up to the latest LSN that touched the inode. If we have
* concurrent fsync/fdatasync() calls, we need them to all block on the
* log force before we clear the ili_fsync_fields field. This ensures
* that we don't get a racing sync operation that does not wait for the
* metadata to hit the journal before returning. If we race with
* clearing the ili_fsync_fields, then all that will happen is the log
* force will do nothing as the lsn will already be on disk. We can't
* race with setting ili_fsync_fields because that is done under
* XFS_ILOCK_EXCL, and that can't happen because we hold the lock shared
* until after the ili_fsync_fields is cleared.
*/
xfs_ilock(ip, XFS_ILOCK_SHARED);
if (xfs_ipincount(ip)) {
if (!datasync ||
(ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
lsn = ip->i_itemp->ili_last_lsn;
}
if (lsn) {
error = _xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, &log_flushed);
ip->i_itemp->ili_fsync_fields = 0;
}
xfs_iunlock(ip, XFS_ILOCK_SHARED);
/*
* If we only have a single device, and the log force about was
* a no-op we might have to flush the data device cache here.
* This can only happen for fdatasync/O_DSYNC if we were overwriting
* an already allocated file and thus do not have any metadata to
* commit.
*/
if (!log_flushed && !XFS_IS_REALTIME_INODE(ip) &&
mp->m_logdev_targp == mp->m_ddev_targp)
xfs_blkdev_issue_flush(mp->m_ddev_targp);
return error;
}
STATIC int
xfs_reclaim_inode(
struct xfs_inode *ip,
struct xfs_perag *pag,
int sync_mode)
{
int error;
restart:
error = 0;
xfs_ilock(ip, XFS_ILOCK_EXCL);
if (!xfs_iflock_nowait(ip)) {
if (!(sync_mode & SYNC_WAIT))
goto out;
xfs_promote_inode(ip);
xfs_iflock(ip);
}
if (is_bad_inode(VFS_I(ip)))
goto reclaim;
if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
xfs_iunpin_wait(ip);
goto reclaim;
}
if (xfs_ipincount(ip)) {
if (!(sync_mode & SYNC_WAIT)) {
xfs_ifunlock(ip);
goto out;
}
xfs_iunpin_wait(ip);
}
if (xfs_iflags_test(ip, XFS_ISTALE))
goto reclaim;
if (xfs_inode_clean(ip))
goto reclaim;
error = xfs_iflush(ip, SYNC_TRYLOCK | sync_mode);
if (sync_mode & SYNC_WAIT) {
if (error == EAGAIN) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
delay(2);
goto restart;
}
xfs_iflock(ip);
goto reclaim;
}
if (error && error != EAGAIN && !XFS_FORCED_SHUTDOWN(ip->i_mount)) {
xfs_warn(ip->i_mount,
"inode 0x%llx background reclaim flush failed with %d",
(long long)ip->i_ino, error);
}
out:
xfs_iflags_clear(ip, XFS_IRECLAIM);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return 0;
reclaim:
xfs_ifunlock(ip);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
XFS_STATS_INC(xs_ig_reclaims);
spin_lock(&pag->pag_ici_lock);
if (!radix_tree_delete(&pag->pag_ici_root,
XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino)))
ASSERT(0);
__xfs_inode_clear_reclaim(pag, ip);
spin_unlock(&pag->pag_ici_lock);
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_qm_dqdetach(ip);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
xfs_inode_free(ip);
return error;
}
STATIC int
xfs_file_fsync(
struct file *file,
loff_t start,
loff_t end,
int datasync)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
struct xfs_trans *tp;
int error = 0;
int log_flushed = 0;
trace_xfs_file_fsync(ip);
error = filemap_write_and_wait_range(inode->i_mapping, start, end);
if (error)
return error;
if (XFS_FORCED_SHUTDOWN(mp))
return -XFS_ERROR(EIO);
xfs_iflags_clear(ip, XFS_ITRUNCATED);
xfs_ilock(ip, XFS_IOLOCK_SHARED);
xfs_ioend_wait(ip);
xfs_iunlock(ip, XFS_IOLOCK_SHARED);
if (mp->m_flags & XFS_MOUNT_BARRIER) {
/*
* If we have an RT and/or log subvolume we need to make sure
* to flush the write cache the device used for file data
* first. This is to ensure newly written file data make
* it to disk before logging the new inode size in case of
* an extending write.
*/
if (XFS_IS_REALTIME_INODE(ip))
xfs_blkdev_issue_flush(mp->m_rtdev_targp);
else if (mp->m_logdev_targp != mp->m_ddev_targp)
xfs_blkdev_issue_flush(mp->m_ddev_targp);
}
/*
* We always need to make sure that the required inode state is safe on
* disk. The inode might be clean but we still might need to force the
* log because of committed transactions that haven't hit the disk yet.
* Likewise, there could be unflushed non-transactional changes to the
* inode core that have to go to disk and this requires us to issue
* a synchronous transaction to capture these changes correctly.
*
* This code relies on the assumption that if the i_update_core field
* of the inode is clear and the inode is unpinned then it is clean
* and no action is required.
*/
xfs_ilock(ip, XFS_ILOCK_SHARED);
/*
* First check if the VFS inode is marked dirty. All the dirtying
* of non-transactional updates no goes through mark_inode_dirty*,
* which allows us to distinguish beteeen pure timestamp updates
* and i_size updates which need to be caught for fdatasync.
* After that also theck for the dirty state in the XFS inode, which
* might gets cleared when the inode gets written out via the AIL
* or xfs_iflush_cluster.
*/
if (((inode->i_state & I_DIRTY_DATASYNC) ||
((inode->i_state & I_DIRTY_SYNC) && !datasync)) &&
ip->i_update_core) {
/*
* Kick off a transaction to log the inode core to get the
* updates. The sync transaction will also force the log.
*/
xfs_iunlock(ip, XFS_ILOCK_SHARED);
tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
error = xfs_trans_reserve(tp, 0,
XFS_FSYNC_TS_LOG_RES(mp), 0, 0, 0);
if (error) {
xfs_trans_cancel(tp, 0);
return -error;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
/*
* Note - it's possible that we might have pushed ourselves out
* of the way during trans_reserve which would flush the inode.
* But there's no guarantee that the inode buffer has actually
* gone out yet (it's delwri). Plus the buffer could be pinned
* anyway if it's part of an inode in another recent
* transaction. So we play it safe and fire off the
* transaction anyway.
*/
xfs_trans_ijoin(tp, ip);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
xfs_trans_set_sync(tp);
error = _xfs_trans_commit(tp, 0, &log_flushed);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
} else {
/*
* Timestamps/size haven't changed since last inode flush or
* inode transaction commit. That means either nothing got
* written or a transaction committed which caught the updates.
* If the latter happened and the transaction hasn't hit the
* disk yet, the inode will be still be pinned. If it is,
* force the log.
*/
if (xfs_ipincount(ip)) {
error = _xfs_log_force_lsn(mp,
ip->i_itemp->ili_last_lsn,
XFS_LOG_SYNC, &log_flushed);
}
xfs_iunlock(ip, XFS_ILOCK_SHARED);
}
/*
* If we only have a single device, and the log force about was
* a no-op we might have to flush the data device cache here.
* This can only happen for fdatasync/O_DSYNC if we were overwriting
* an already allocated file and thus do not have any metadata to
* commit.
*/
if ((mp->m_flags & XFS_MOUNT_BARRIER) &&
mp->m_logdev_targp == mp->m_ddev_targp &&
!XFS_IS_REALTIME_INODE(ip) &&
!log_flushed)
xfs_blkdev_issue_flush(mp->m_ddev_targp);
return -error;
}