コード例 #1
0
ファイル: xfs_iops.c プロジェクト: gxt/linux
STATIC int
xfs_vn_setattr(
	struct dentry		*dentry,
	struct iattr		*iattr)
{
	struct xfs_inode	*ip = XFS_I(d_inode(dentry));
	int			error;

	if (iattr->ia_valid & ATTR_SIZE) {
		uint		iolock = XFS_IOLOCK_EXCL;

		xfs_ilock(ip, iolock);
		error = xfs_break_layouts(d_inode(dentry), &iolock, true);
		if (!error) {
			xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
			iolock |= XFS_MMAPLOCK_EXCL;

			error = xfs_setattr_size(ip, iattr);
		}
		xfs_iunlock(ip, iolock);
	} else {
		error = xfs_setattr_nonsize(ip, iattr, 0);
	}

	return error;
}
コード例 #2
0
STATIC int
xfs_vn_setattr(
	struct dentry	*dentry,
	struct iattr	*iattr)
{
	if (iattr->ia_valid & ATTR_SIZE)
		return -xfs_setattr_size(XFS_I(dentry->d_inode), iattr, 0);
	return -xfs_setattr_nonsize(XFS_I(dentry->d_inode), iattr, 0);
}
コード例 #3
0
ファイル: xfs_iops.c プロジェクト: acton393/linux
int
xfs_vn_setattr_nonsize(
	struct dentry		*dentry,
	struct iattr		*iattr)
{
	struct xfs_inode	*ip = XFS_I(d_inode(dentry));
	int error;

	trace_xfs_setattr(ip);

	error = xfs_vn_change_ok(dentry, iattr);
	if (error)
		return error;
	return xfs_setattr_nonsize(ip, iattr, 0);
}
コード例 #4
0
ファイル: xfs_acl.c プロジェクト: aplnosun/linux
static int
xfs_set_mode(struct inode *inode, umode_t mode)
{
	int error = 0;

	if (mode != inode->i_mode) {
		struct iattr iattr;

		iattr.ia_valid = ATTR_MODE | ATTR_CTIME;
		iattr.ia_mode = mode;
		iattr.ia_ctime = current_fs_time(inode->i_sb);

		error = -xfs_setattr_nonsize(XFS_I(inode), &iattr, XFS_ATTR_NOACL);
	}

	return error;
}
コード例 #5
0
ファイル: xfs_iops.c プロジェクト: luyanseu/linux
STATIC int
xfs_vn_setattr(
	struct dentry		*dentry,
	struct iattr		*iattr)
{
	struct xfs_inode	*ip = XFS_I(dentry->d_inode);
	int			error;

	if (iattr->ia_valid & ATTR_SIZE) {
		xfs_ilock(ip, XFS_IOLOCK_EXCL);
		error = xfs_setattr_size(ip, iattr);
		xfs_iunlock(ip, XFS_IOLOCK_EXCL);
	} else {
		error = xfs_setattr_nonsize(ip, iattr, 0);
	}

	return -error;
}
コード例 #6
0
ファイル: xfs_iops.c プロジェクト: luyanseu/linux
/*
 * Truncate file.  Must have write permission and not be a directory.
 */
int
xfs_setattr_size(
	struct xfs_inode	*ip,
	struct iattr		*iattr)
{
	struct xfs_mount	*mp = ip->i_mount;
	struct inode		*inode = VFS_I(ip);
	xfs_off_t		oldsize, newsize;
	struct xfs_trans	*tp;
	int			error;
	uint			lock_flags = 0;
	uint			commit_flags = 0;

	trace_xfs_setattr(ip);

	if (mp->m_flags & XFS_MOUNT_RDONLY)
		return XFS_ERROR(EROFS);

	if (XFS_FORCED_SHUTDOWN(mp))
		return XFS_ERROR(EIO);

	error = -inode_change_ok(inode, iattr);
	if (error)
		return XFS_ERROR(error);

	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
	ASSERT(S_ISREG(ip->i_d.di_mode));
	ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
		ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);

	oldsize = inode->i_size;
	newsize = iattr->ia_size;

	/*
	 * Short circuit the truncate case for zero length files.
	 */
	if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) {
		if (!(iattr->ia_valid & (ATTR_CTIME|ATTR_MTIME)))
			return 0;

		/*
		 * Use the regular setattr path to update the timestamps.
		 */
		iattr->ia_valid &= ~ATTR_SIZE;
		return xfs_setattr_nonsize(ip, iattr, 0);
	}

	/*
	 * Make sure that the dquots are attached to the inode.
	 */
	error = xfs_qm_dqattach(ip, 0);
	if (error)
		return error;

	/*
	 * Now we can make the changes.  Before we join the inode to the
	 * transaction, take care of the part of the truncation that must be
	 * done without the inode lock.  This needs to be done before joining
	 * the inode to the transaction, because the inode cannot be unlocked
	 * once it is a part of the transaction.
	 */
	if (newsize > oldsize) {
		/*
		 * Do the first part of growing a file: zero any data in the
		 * last block that is beyond the old EOF.  We need to do this
		 * before the inode is joined to the transaction to modify
		 * i_size.
		 */
		error = xfs_zero_eof(ip, newsize, oldsize);
		if (error)
			return error;
	}

	/*
	 * We are going to log the inode size change in this transaction so
	 * any previous writes that are beyond the on disk EOF and the new
	 * EOF that have not been written out need to be written here.  If we
	 * do not write the data out, we expose ourselves to the null files
	 * problem.
	 *
	 * Only flush from the on disk size to the smaller of the in memory
	 * file size or the new size as that's the range we really care about
	 * here and prevents waiting for other data not within the range we
	 * care about here.
	 */
	if (oldsize != ip->i_d.di_size && newsize > ip->i_d.di_size) {
		error = -filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
						      ip->i_d.di_size, newsize);
		if (error)
			return error;
	}

	/*
	 * Wait for all direct I/O to complete.
	 */
	inode_dio_wait(inode);

	error = -block_truncate_page(inode->i_mapping, newsize, xfs_get_blocks);
	if (error)
		return error;

	tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_SIZE);
	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_itruncate, 0, 0);
	if (error)
		goto out_trans_cancel;

	truncate_setsize(inode, newsize);

	commit_flags = XFS_TRANS_RELEASE_LOG_RES;
	lock_flags |= XFS_ILOCK_EXCL;

	xfs_ilock(ip, XFS_ILOCK_EXCL);

	xfs_trans_ijoin(tp, ip, 0);

	/*
	 * Only change the c/mtime if we are changing the size or we are
	 * explicitly asked to change it.  This handles the semantic difference
	 * between truncate() and ftruncate() as implemented in the VFS.
	 *
	 * The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a
	 * special case where we need to update the times despite not having
	 * these flags set.  For all other operations the VFS set these flags
	 * explicitly if it wants a timestamp update.
	 */
	if (newsize != oldsize &&
	    !(iattr->ia_valid & (ATTR_CTIME | ATTR_MTIME))) {
		iattr->ia_ctime = iattr->ia_mtime =
			current_fs_time(inode->i_sb);
		iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME;
	}

	/*
	 * The first thing we do is set the size to new_size permanently on
	 * disk.  This way we don't have to worry about anyone ever being able
	 * to look at the data being freed even in the face of a crash.
	 * What we're getting around here is the case where we free a block, it
	 * is allocated to another file, it is written to, and then we crash.
	 * If the new data gets written to the file but the log buffers
	 * containing the free and reallocation don't, then we'd end up with
	 * garbage in the blocks being freed.  As long as we make the new size
	 * permanent before actually freeing any blocks it doesn't matter if
	 * they get written to.
	 */
	ip->i_d.di_size = newsize;
	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);

	if (newsize <= oldsize) {
		error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, newsize);
		if (error)
			goto out_trans_abort;

		/*
		 * Truncated "down", so we're removing references to old data
		 * here - if we delay flushing for a long time, we expose
		 * ourselves unduly to the notorious NULL files problem.  So,
		 * we mark this inode and flush it when the file is closed,
		 * and do not wait the usual (long) time for writeout.
		 */
		xfs_iflags_set(ip, XFS_ITRUNCATED);

		/* A truncate down always removes post-EOF blocks. */
		xfs_inode_clear_eofblocks_tag(ip);
	}

	if (iattr->ia_valid & ATTR_MODE)
		xfs_setattr_mode(ip, iattr);
	if (iattr->ia_valid & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME))
		xfs_setattr_time(ip, iattr);

	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);

	XFS_STATS_INC(xs_ig_attrchg);

	if (mp->m_flags & XFS_MOUNT_WSYNC)
		xfs_trans_set_sync(tp);

	error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
out_unlock:
	if (lock_flags)
		xfs_iunlock(ip, lock_flags);
	return error;

out_trans_abort:
	commit_flags |= XFS_TRANS_ABORT;
out_trans_cancel:
	xfs_trans_cancel(tp, commit_flags);
	goto out_unlock;
}
コード例 #7
0
ファイル: xfs_iops.c プロジェクト: gxt/linux
/*
 * Truncate file.  Must have write permission and not be a directory.
 */
int
xfs_setattr_size(
	struct xfs_inode	*ip,
	struct iattr		*iattr)
{
	struct xfs_mount	*mp = ip->i_mount;
	struct inode		*inode = VFS_I(ip);
	xfs_off_t		oldsize, newsize;
	struct xfs_trans	*tp;
	int			error;
	uint			lock_flags = 0;
	bool			did_zeroing = false;

	trace_xfs_setattr(ip);

	if (mp->m_flags & XFS_MOUNT_RDONLY)
		return -EROFS;

	if (XFS_FORCED_SHUTDOWN(mp))
		return -EIO;

	error = inode_change_ok(inode, iattr);
	if (error)
		return error;

	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
	ASSERT(xfs_isilocked(ip, XFS_MMAPLOCK_EXCL));
	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);

	oldsize = inode->i_size;
	newsize = iattr->ia_size;

	/*
	 * Short circuit the truncate case for zero length files.
	 */
	if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) {
		if (!(iattr->ia_valid & (ATTR_CTIME|ATTR_MTIME)))
			return 0;

		/*
		 * Use the regular setattr path to update the timestamps.
		 */
		iattr->ia_valid &= ~ATTR_SIZE;
		return xfs_setattr_nonsize(ip, iattr, 0);
	}

	/*
	 * Make sure that the dquots are attached to the inode.
	 */
	error = xfs_qm_dqattach(ip, 0);
	if (error)
		return error;

	/*
	 * Wait for all direct I/O to complete.
	 */
	inode_dio_wait(inode);

	/*
	 * File data changes must be complete before we start the transaction to
	 * modify the inode.  This needs to be done before joining the inode to
	 * the transaction because the inode cannot be unlocked once it is a
	 * part of the transaction.
	 *
	 * Start with zeroing any data beyond EOF that we may expose on file
	 * extension, or zeroing out the rest of the block on a downward
	 * truncate.
	 */
	if (newsize > oldsize) {
		error = xfs_zero_eof(ip, newsize, oldsize, &did_zeroing);
	} else {
		error = iomap_truncate_page(inode, newsize, &did_zeroing,
				&xfs_iomap_ops);
	}

	if (error)
		return error;

	/*
	 * We are going to log the inode size change in this transaction so
	 * any previous writes that are beyond the on disk EOF and the new
	 * EOF that have not been written out need to be written here.  If we
	 * do not write the data out, we expose ourselves to the null files
	 * problem. Note that this includes any block zeroing we did above;
	 * otherwise those blocks may not be zeroed after a crash.
	 */
	if (did_zeroing ||
	    (newsize > ip->i_d.di_size && oldsize != ip->i_d.di_size)) {
		error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
						      ip->i_d.di_size, newsize);
		if (error)
			return error;
	}

	/*
	 * We've already locked out new page faults, so now we can safely remove
	 * pages from the page cache knowing they won't get refaulted until we
	 * drop the XFS_MMAP_EXCL lock after the extent manipulations are
	 * complete. The truncate_setsize() call also cleans partial EOF page
	 * PTEs on extending truncates and hence ensures sub-page block size
	 * filesystems are correctly handled, too.
	 *
	 * We have to do all the page cache truncate work outside the
	 * transaction context as the "lock" order is page lock->log space
	 * reservation as defined by extent allocation in the writeback path.
	 * Hence a truncate can fail with ENOMEM from xfs_trans_alloc(), but
	 * having already truncated the in-memory version of the file (i.e. made
	 * user visible changes). There's not much we can do about this, except
	 * to hope that the caller sees ENOMEM and retries the truncate
	 * operation.
	 */
	truncate_setsize(inode, newsize);

	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
	if (error)
		return error;

	lock_flags |= XFS_ILOCK_EXCL;
	xfs_ilock(ip, XFS_ILOCK_EXCL);
	xfs_trans_ijoin(tp, ip, 0);

	/*
	 * Only change the c/mtime if we are changing the size or we are
	 * explicitly asked to change it.  This handles the semantic difference
	 * between truncate() and ftruncate() as implemented in the VFS.
	 *
	 * The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a
	 * special case where we need to update the times despite not having
	 * these flags set.  For all other operations the VFS set these flags
	 * explicitly if it wants a timestamp update.
	 */
	if (newsize != oldsize &&
	    !(iattr->ia_valid & (ATTR_CTIME | ATTR_MTIME))) {
		iattr->ia_ctime = iattr->ia_mtime =
			current_fs_time(inode->i_sb);
		iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME;
	}

	/*
	 * The first thing we do is set the size to new_size permanently on
	 * disk.  This way we don't have to worry about anyone ever being able
	 * to look at the data being freed even in the face of a crash.
	 * What we're getting around here is the case where we free a block, it
	 * is allocated to another file, it is written to, and then we crash.
	 * If the new data gets written to the file but the log buffers
	 * containing the free and reallocation don't, then we'd end up with
	 * garbage in the blocks being freed.  As long as we make the new size
	 * permanent before actually freeing any blocks it doesn't matter if
	 * they get written to.
	 */
	ip->i_d.di_size = newsize;
	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);

	if (newsize <= oldsize) {
		error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, newsize);
		if (error)
			goto out_trans_cancel;

		/*
		 * Truncated "down", so we're removing references to old data
		 * here - if we delay flushing for a long time, we expose
		 * ourselves unduly to the notorious NULL files problem.  So,
		 * we mark this inode and flush it when the file is closed,
		 * and do not wait the usual (long) time for writeout.
		 */
		xfs_iflags_set(ip, XFS_ITRUNCATED);

		/* A truncate down always removes post-EOF blocks. */
		xfs_inode_clear_eofblocks_tag(ip);
	}

	if (iattr->ia_valid & ATTR_MODE)
		xfs_setattr_mode(ip, iattr);
	if (iattr->ia_valid & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME))
		xfs_setattr_time(ip, iattr);

	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);

	XFS_STATS_INC(mp, xs_ig_attrchg);

	if (mp->m_flags & XFS_MOUNT_WSYNC)
		xfs_trans_set_sync(tp);

	error = xfs_trans_commit(tp);
out_unlock:
	if (lock_flags)
		xfs_iunlock(ip, lock_flags);
	return error;

out_trans_cancel:
	xfs_trans_cancel(tp);
	goto out_unlock;
}
コード例 #8
0
/*
 * Truncate file.  Must have write permission and not be a directory.
 */
int
xfs_setattr_size(
	struct xfs_inode	*ip,
	struct iattr		*iattr,
	int			flags)
{
	struct xfs_mount	*mp = ip->i_mount;
	struct inode		*inode = VFS_I(ip);
	int			mask = iattr->ia_valid;
	struct xfs_trans	*tp;
	int			error;
	uint			lock_flags;
	uint			commit_flags = 0;

	trace_xfs_setattr(ip);

	if (mp->m_flags & XFS_MOUNT_RDONLY)
		return XFS_ERROR(EROFS);

	if (XFS_FORCED_SHUTDOWN(mp))
		return XFS_ERROR(EIO);

	error = -inode_change_ok(inode, iattr);
	if (error)
		return XFS_ERROR(error);

	ASSERT(S_ISREG(ip->i_d.di_mode));
	ASSERT((mask & (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
			ATTR_MTIME_SET|ATTR_KILL_SUID|ATTR_KILL_SGID|
			ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);

	lock_flags = XFS_ILOCK_EXCL;
	if (!(flags & XFS_ATTR_NOLOCK))
		lock_flags |= XFS_IOLOCK_EXCL;
	xfs_ilock(ip, lock_flags);

	/*
	 * Short circuit the truncate case for zero length files.
	 */
	if (iattr->ia_size == 0 &&
	    ip->i_size == 0 && ip->i_d.di_nextents == 0) {
		if (!(mask & (ATTR_CTIME|ATTR_MTIME)))
			goto out_unlock;

		/*
		 * Use the regular setattr path to update the timestamps.
		 */
		xfs_iunlock(ip, lock_flags);
		iattr->ia_valid &= ~ATTR_SIZE;
		return xfs_setattr_nonsize(ip, iattr, 0);
	}

	/*
	 * Make sure that the dquots are attached to the inode.
	 */
	error = xfs_qm_dqattach_locked(ip, 0);
	if (error)
		goto out_unlock;

	/*
	 * Now we can make the changes.  Before we join the inode to the
	 * transaction, take care of the part of the truncation that must be
	 * done without the inode lock.  This needs to be done before joining
	 * the inode to the transaction, because the inode cannot be unlocked
	 * once it is a part of the transaction.
	 */
	if (iattr->ia_size > ip->i_size) {
		/*
		 * Do the first part of growing a file: zero any data in the
		 * last block that is beyond the old EOF.  We need to do this
		 * before the inode is joined to the transaction to modify
		 * i_size.
		 */
		error = xfs_zero_eof(ip, iattr->ia_size, ip->i_size);
		if (error)
			goto out_unlock;
	}
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
	lock_flags &= ~XFS_ILOCK_EXCL;

	/*
	 * We are going to log the inode size change in this transaction so
	 * any previous writes that are beyond the on disk EOF and the new
	 * EOF that have not been written out need to be written here.  If we
	 * do not write the data out, we expose ourselves to the null files
	 * problem.
	 *
	 * Only flush from the on disk size to the smaller of the in memory
	 * file size or the new size as that's the range we really care about
	 * here and prevents waiting for other data not within the range we
	 * care about here.
	 */
	if (ip->i_size != ip->i_d.di_size && iattr->ia_size > ip->i_d.di_size) {
		error = xfs_flush_pages(ip, ip->i_d.di_size, iattr->ia_size,
					XBF_ASYNC, FI_NONE);
		if (error)
			goto out_unlock;
	}

	/*
	 * Wait for all I/O to complete.
	 */
	xfs_ioend_wait(ip);

	error = -block_truncate_page(inode->i_mapping, iattr->ia_size,
				     xfs_get_blocks);
	if (error)
		goto out_unlock;

	tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_SIZE);
	error = xfs_trans_reserve(tp, 0, XFS_ITRUNCATE_LOG_RES(mp), 0,
				 XFS_TRANS_PERM_LOG_RES,
				 XFS_ITRUNCATE_LOG_COUNT);
	if (error)
		goto out_trans_cancel;

	truncate_setsize(inode, iattr->ia_size);

	commit_flags = XFS_TRANS_RELEASE_LOG_RES;
	lock_flags |= XFS_ILOCK_EXCL;

	xfs_ilock(ip, XFS_ILOCK_EXCL);

	xfs_trans_ijoin(tp, ip);

	/*
	 * Only change the c/mtime if we are changing the size or we are
	 * explicitly asked to change it.  This handles the semantic difference
	 * between truncate() and ftruncate() as implemented in the VFS.
	 *
	 * The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a
	 * special case where we need to update the times despite not having
	 * these flags set.  For all other operations the VFS set these flags
	 * explicitly if it wants a timestamp update.
	 */
	if (iattr->ia_size != ip->i_size &&
	    (!(mask & (ATTR_CTIME | ATTR_MTIME)))) {
		iattr->ia_ctime = iattr->ia_mtime =
			current_fs_time(inode->i_sb);
		mask |= ATTR_CTIME | ATTR_MTIME;
	}

	if (iattr->ia_size > ip->i_size) {
		ip->i_d.di_size = iattr->ia_size;
		ip->i_size = iattr->ia_size;
	} else if (iattr->ia_size <= ip->i_size ||
		   (iattr->ia_size == 0 && ip->i_d.di_nextents)) {
		error = xfs_itruncate_data(&tp, ip, iattr->ia_size);
		if (error)
			goto out_trans_abort;

		/*
		 * Truncated "down", so we're removing references to old data
		 * here - if we delay flushing for a long time, we expose
		 * ourselves unduly to the notorious NULL files problem.  So,
		 * we mark this inode and flush it when the file is closed,
		 * and do not wait the usual (long) time for writeout.
		 */
		xfs_iflags_set(ip, XFS_ITRUNCATED);
	}

	if (mask & 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;
		ip->i_update_core = 1;
	}
	if (mask & 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;
		ip->i_update_core = 1;
	}

	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);

	XFS_STATS_INC(xs_ig_attrchg);

	if (mp->m_flags & XFS_MOUNT_WSYNC)
		xfs_trans_set_sync(tp);

	error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
out_unlock:
	if (lock_flags)
		xfs_iunlock(ip, lock_flags);
	return error;

out_trans_abort:
	commit_flags |= XFS_TRANS_ABORT;
out_trans_cancel:
	xfs_trans_cancel(tp, commit_flags);
	goto out_unlock;
}
コード例 #9
0
int
xfs_setattr_size(
	struct xfs_inode	*ip,
	struct iattr		*iattr,
	int			flags)
{
	struct xfs_mount	*mp = ip->i_mount;
	struct inode		*inode = VFS_I(ip);
	int			mask = iattr->ia_valid;
	xfs_off_t		oldsize, newsize;
	struct xfs_trans	*tp;
	int			error;
	uint			lock_flags;
	uint			commit_flags = 0;

	trace_xfs_setattr(ip);

	if (mp->m_flags & XFS_MOUNT_RDONLY)
		return XFS_ERROR(EROFS);

	if (XFS_FORCED_SHUTDOWN(mp))
		return XFS_ERROR(EIO);

	error = -inode_change_ok(inode, iattr);
	if (error)
		return XFS_ERROR(error);

	ASSERT(S_ISREG(ip->i_d.di_mode));
	ASSERT((mask & (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
			ATTR_MTIME_SET|ATTR_KILL_SUID|ATTR_KILL_SGID|
			ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);

	lock_flags = XFS_ILOCK_EXCL;
	if (!(flags & XFS_ATTR_NOLOCK))
		lock_flags |= XFS_IOLOCK_EXCL;
	xfs_ilock(ip, lock_flags);

	oldsize = inode->i_size;
	newsize = iattr->ia_size;

	if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) {
		if (!(mask & (ATTR_CTIME|ATTR_MTIME)))
			goto out_unlock;

		xfs_iunlock(ip, lock_flags);
		iattr->ia_valid &= ~ATTR_SIZE;
		return xfs_setattr_nonsize(ip, iattr, 0);
	}

	error = xfs_qm_dqattach_locked(ip, 0);
	if (error)
		goto out_unlock;

	if (newsize > oldsize) {
		error = xfs_zero_eof(ip, newsize, oldsize);
		if (error)
			goto out_unlock;
	}
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
	lock_flags &= ~XFS_ILOCK_EXCL;

	/*
	 * We are going to log the inode size change in this transaction so
	 * any previous writes that are beyond the on disk EOF and the new
	 * EOF that have not been written out need to be written here.  If we
	 * do not write the data out, we expose ourselves to the null files
	 * problem.
	 *
	 * Only flush from the on disk size to the smaller of the in memory
	 * file size or the new size as that's the range we really care about
	 * here and prevents waiting for other data not within the range we
	 * care about here.
	 */
	if (oldsize != ip->i_d.di_size && newsize > ip->i_d.di_size) {
		error = xfs_flush_pages(ip, ip->i_d.di_size, newsize, 0,
					FI_NONE);
		if (error)
			goto out_unlock;
	}

	inode_dio_wait(inode);

	error = -block_truncate_page(inode->i_mapping, newsize, xfs_get_blocks);
	if (error)
		goto out_unlock;

	tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_SIZE);
	error = xfs_trans_reserve(tp, 0, XFS_ITRUNCATE_LOG_RES(mp), 0,
				 XFS_TRANS_PERM_LOG_RES,
				 XFS_ITRUNCATE_LOG_COUNT);
	if (error)
		goto out_trans_cancel;

	truncate_setsize(inode, newsize);

	commit_flags = XFS_TRANS_RELEASE_LOG_RES;
	lock_flags |= XFS_ILOCK_EXCL;

	xfs_ilock(ip, XFS_ILOCK_EXCL);

	xfs_trans_ijoin(tp, ip, 0);

	if (newsize != oldsize && (!(mask & (ATTR_CTIME | ATTR_MTIME)))) {
		iattr->ia_ctime = iattr->ia_mtime =
			current_fs_time(inode->i_sb);
		mask |= ATTR_CTIME | ATTR_MTIME;
	}

	/*
	 * The first thing we do is set the size to new_size permanently on
	 * disk.  This way we don't have to worry about anyone ever being able
	 * to look at the data being freed even in the face of a crash.
	 * What we're getting around here is the case where we free a block, it
	 * is allocated to another file, it is written to, and then we crash.
	 * If the new data gets written to the file but the log buffers
	 * containing the free and reallocation don't, then we'd end up with
	 * garbage in the blocks being freed.  As long as we make the new size
	 * permanent before actually freeing any blocks it doesn't matter if
	 * they get written to.
	 */
	ip->i_d.di_size = newsize;
	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);

	if (newsize <= oldsize) {
		error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, newsize);
		if (error)
			goto out_trans_abort;

		xfs_iflags_set(ip, XFS_ITRUNCATED);
	}

	if (mask & 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 (mask & 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;
	}

	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);

	XFS_STATS_INC(xs_ig_attrchg);

	if (mp->m_flags & XFS_MOUNT_WSYNC)
		xfs_trans_set_sync(tp);

	error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
out_unlock:
	if (lock_flags)
		xfs_iunlock(ip, lock_flags);
	return error;

out_trans_abort:
	commit_flags |= XFS_TRANS_ABORT;
out_trans_cancel:
	xfs_trans_cancel(tp, commit_flags);
	goto out_unlock;
}