path: root/fs/xfs/xfs_file.c

// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (c) 2000-2005 Silicon Graphics, Inc.
 * All Rights Reserved.
 */
#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_inode.h"
#include "xfs_trans.h"
#include "xfs_inode_item.h"
#include "xfs_bmap.h"
#include "xfs_bmap_util.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 "xfs_file.h"

#include <linux/dax.h>
#include <linux/falloc.h>
#include <linux/backing-dev.h>
#include <linux/mman.h>
#include <linux/fadvise.h>
#include <linux/mount.h>

static const struct vm_operations_struct xfs_file_vm_ops;

/*
 * Decide if the given file range is aligned to the size of the fundamental
 * allocation unit for the file.
 */
bool
xfs_is_falloc_aligned(
	struct xfs_inode	*ip,
	loff_t			pos,
	long long int		len)
{
	unsigned int		alloc_unit = xfs_inode_alloc_unitsize(ip);

	if (!is_power_of_2(alloc_unit))
		return isaligned_64(pos, alloc_unit) &&
		       isaligned_64(len, alloc_unit);

	return !((pos | len) & (alloc_unit - 1));
}

/*
 * 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);

	trace_xfs_dir_fsync(ip);
	return xfs_log_force_inode(ip);
}

static xfs_csn_t
xfs_fsync_seq(
	struct xfs_inode	*ip,
	bool			datasync)
{
	if (!xfs_ipincount(ip))
		return 0;
	if (datasync && !(ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
		return 0;
	return ip->i_itemp->ili_commit_seq;
}

/*
 * 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 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.
 */
static  int
xfs_fsync_flush_log(
	struct xfs_inode	*ip,
	bool			datasync,
	int			*log_flushed)
{
	int			error = 0;
	xfs_csn_t		seq;

	xfs_ilock(ip, XFS_ILOCK_SHARED);
	seq = xfs_fsync_seq(ip, datasync);
	if (seq) {
		error = xfs_log_force_seq(ip->i_mount, seq, XFS_LOG_SYNC,
					  log_flushed);

		spin_lock(&ip->i_itemp->ili_lock);
		ip->i_itemp->ili_fsync_fields = 0;
		spin_unlock(&ip->i_itemp->ili_lock);
	}
	xfs_iunlock(ip, XFS_ILOCK_SHARED);
	return error;
}

STATIC int
xfs_file_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;
	int			error, err2;
	int			log_flushed = 0;

	trace_xfs_file_fsync(ip);

	error = file_write_and_wait_range(file, start, end);
	if (error)
		return error;

	if (xfs_is_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))
		error = blkdev_issue_flush(mp->m_rtdev_targp->bt_bdev);
	else if (mp->m_logdev_targp != mp->m_ddev_targp)
		error = blkdev_issue_flush(mp->m_ddev_targp->bt_bdev);

	/*
	 * Any inode that has dirty modifications in the log is pinned.  The
	 * racy check here for a pinned inode will not catch modifications
	 * that happen concurrently to the fsync call, but fsync semantics
	 * only require to sync previously completed I/O.
	 */
	if (xfs_ipincount(ip)) {
		err2 = xfs_fsync_flush_log(ip, datasync, &log_flushed);
		if (err2 && !error)
			error = err2;
	}

	/*
	 * 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
	 * a