path: root/fs/xfs/xfs_file.c

/*
 * Copyright (c) 2000-2005 Silicon Graphics, Inc.
 * All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it would be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write the Free Software Foundation,
 * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_da_format.h"
#include "xfs_da_btree.h"
#include "xfs_inode.h"
#include "xfs_trans.h"
#include "xfs_inode_item.h"
#include "xfs_bmap.h"
#include "xfs_bmap_util.h"
#include "xfs_error.h"
#include "xfs_dir2.h"
#include "xfs_dir2_priv.h"
#include "xfs_ioctl.h"
#include "xfs_trace.h"
#include "xfs_log.h"
#include "xfs_icache.h"
#include "xfs_pnfs.h"
#include "xfs_iomap.h"
#include "xfs_reflink.h"

#include <linux/dcache.h>
#include <linux/falloc.h>
#include <linux/pagevec.h>
#include <linux/backing-dev.h>

static const struct vm_operations_struct xfs_file_vm_ops;

/*
 * Clear the specified ranges to zero through either the pagecache or DAX.
 * Holes and unwritten extents will be left as-is as they already are zeroed.
 */
int
xfs_zero_range(
	struct xfs_inode	*ip,
	xfs_off_t		pos,
	xfs_off_t		count,
	bool			*did_zero)
{
	return iomap_zero_range(VFS_I(ip), pos, count, NULL, &xfs_iomap_ops);
}

int
xfs_update_prealloc_flags(
	struct xfs_inode	*ip,
	enum xfs_prealloc_flags	flags)
{
	struct xfs_trans	*tp;
	int			error;

	error = xfs_trans_alloc(ip->i_mount, &M_RES(ip->i_mount)->tr_writeid,
			0, 0, 0, &tp);
	if (error)
		return error;

	xfs_ilock(ip, XFS_ILOCK_EXCL);
	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);

	if (!(flags & XFS_PREALLOC_INVISIBLE)) {
		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);
	}

	if (flags & XFS_PREALLOC_SET)
		ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC;
	if (flags & XFS_PREALLOC_CLEAR)
		ip->i_d.di_flags &= ~XFS_DIFLAG_PREALLOC;

	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
	if (flags & XFS_PREALLOC_SYNC)
		xfs_trans_set_sync(tp);
	return xfs_trans_commit(tp);
}

/*
 * Fsync operations on directories are much simpler than on regular files,
 * as there is no file data to flush, and thus also no need for explicit
 * cache flush operations, and there are no non-transaction metadata updates
 * on directories either.
 */
STATIC int
xfs_dir_fsync(
	struct file		*file,
	loff_t			start,
	loff_t			end,
	int			datasync)
{
	struct xfs_inode	*ip = XFS_I(file->f_mapping->host);
	struct xfs_mount	*mp = ip->i_mount;
	xfs_lsn_t		lsn = 0;

	trace_xfs_dir_fsync(ip);

	xfs_ilock(ip, XFS_ILOCK_SHARED);
	if (xfs_ipincount(ip))
		lsn = ip->i_itemp->ili_last_lsn;
	xfs_iunlock(ip, XFS_ILOCK_SHARED);

	if (!lsn)
		return 0;
	return _xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, NULL);
}

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 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 ssize_t
xfs_file_dio_aio_read(
	struct kiocb		*iocb,
	struct iov_iter		*to)
{
	struct xfs_inode	*ip = XFS_I(file_inode(iocb->ki_filp));
	size_t			count = iov_iter_count(to);
	ssize_t			ret;

	trace_xfs_file_direct_read(ip, count, iocb->ki_pos);

	if (!count)
		return 0; /* skip atime */

	file_accessed(iocb->ki_filp);

	xfs_ilock(ip, XFS_IOLOCK_SHARED);
	ret = iomap_dio_rw(iocb, to, &xfs_iomap_ops, NULL);
	xfs_iunlock(ip, XFS_IOLOCK_SHARED);

	return ret;
}

static noinline ssize_t
xfs_file_dax_read(
	struct kiocb		*iocb,
	struct iov_iter		*to)
{
	struct xfs_inode	*ip = XFS_I(iocb->ki_filp->f_mapping->host);
	size_t			count = iov_iter_count(to);
	ssize_t			ret = 0;

	trace_xfs_file_dax_read(ip, count, iocb->ki_pos);

	if (!count)
		return 0; /* skip atime */

	xfs_ilock(ip, XFS_IOLOCK_SHARED);
	ret = dax_iomap_rw(iocb, to, &xfs_iomap_ops);
	xfs_iunlock(ip, XFS_IOLOCK_SHARED);

	file_accessed(iocb->ki_filp);
	return ret;
}

STATIC ssize_t
xfs_file_