Release 4.11 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);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Christoph Hellwig
28
73.68%
4
80.00%
Dave Chinner
10
26.32%
1
20.00%
Total
38
100.00%
5
100.00%


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);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Christoph Hellwig
169
93.37%
2
66.67%
Dave Chinner
12
6.63%
1
33.33%
Total
181
100.00%
3
100.00%

/*
 * 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);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Christoph Hellwig
102
100.00%
1
100.00%
Total
102
100.00%
1
100.00%


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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Christoph Hellwig
193
78.14%
6
66.67%
Dave Chinner
28
11.34%
2
22.22%
Josef Bacik
26
10.53%
1
11.11%
Total
247
100.00%
9
100.00%


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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Christoph Hellwig
82
82.00%
10
62.50%
Al Viro
8
8.00%
2
12.50%
Dave Chinner
7
7.00%
2
12.50%
Chris Mason
2
2.00%
1
6.25%
Bill O'Donnell
1
1.00%
1
6.25%
Total
100
100.00%
16
100.00%


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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Christoph Hellwig
86
84.31%
8
61.54%
Dave Chinner
10
9.80%
2
15.38%
Bill O'Donnell
3
2.94%
1
7.69%
Arnd Bergmann
2
1.96%
1
7.69%
Ross Zwisler
1
0.98%
1
7.69%
Total
102
100.00%
13
100.00%


STATIC ssize_t

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

	trace_xfs_file_buffered_read(ip, iov_iter_count(to), iocb->ki_pos);

	xfs_ilock(ip, XFS_IOLOCK_SHARED);
	ret = generic_file_read_iter(iocb, to);
	xfs_iunlock(ip, XFS_IOLOCK_SHARED);

	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Christoph Hellwig
69
93.24%
5
62.50%
Dave Chinner
2
2.70%
1
12.50%
Al Viro
2
2.70%
1
12.50%
Brian Foster
1
1.35%
1
12.50%
Total
74
100.00%
8
100.00%


STATIC ssize_t

xfs_file_read_iter(
	struct kiocb		*iocb,
	struct iov_iter		*to)
{
	struct inode		*inode = file_inode(iocb->ki_filp);
	struct xfs_mount	*mp = XFS_I(inode)->i_mount;
	ssize_t			ret = 0;

	XFS_STATS_INC(mp, xs_read_calls);

	if (XFS_FORCED_SHUTDOWN(mp))
		return -EIO;

	if (IS_DAX(inode))
		ret = xfs_file_dax_read(iocb, to);
	else if (iocb->ki_flags & IOCB_DIRECT)
		ret = xfs_file_dio_aio_read(iocb, to);
	else
		ret = xfs_file_buffered_aio_read(iocb, to);

	if (ret > 0)
		XFS_STATS_ADD(mp, xs_read_bytes, ret);
	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Christoph Hellwig
113
90.40%
4
50.00%
Dave Chinner
5
4.00%
2
25.00%
Al Viro
5
4.00%
1
12.50%
Bill O'Donnell
2
1.60%
1
12.50%
Total
125
100.00%
8
100.00%

/*
 * Zero any on disk space between the current EOF and the new, larger EOF.
 *
 * This handles the normal case of zeroing the remainder of the last block in
 * the file and the unusual case of zeroing blocks out beyond the size of the
 * file.  This second case only happens with fixed size extents and when the
 * system crashes before the inode size was updated but after blocks were
 * allocated.
 *
 * Expects the iolock to be held exclusive, and will take the ilock internally.
 */

int					/* error (positive) */

xfs_zero_eof(
	struct xfs_inode	*ip,
	xfs_off_t		offset,		/* starting I/O offset */
	xfs_fsize_t		isize,		/* current inode size */
	bool			*did_zeroing)
{
	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
	ASSERT(offset > isize);

	trace_xfs_zero_eof(ip, isize, offset - isize);
	return xfs_zero_range(ip, isize, offset - isize, did_zeroing);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
David Chinner
30
46.15%
1
25.00%
Christoph Hellwig
24
36.92%
2
50.00%
Brian Foster
11
16.92%
1
25.00%
Total
65
100.00%
4
100.00%

/*
 * Common pre-write limit and setup checks.
 *
 * Called with the iolocked held either shared and exclusive according to
 * @iolock, and returns with it held.  Might upgrade the iolock to exclusive
 * if called for a direct write beyond i_size.
 */

STATIC ssize_t

xfs_file_aio_write_checks(
	struct kiocb		*iocb,
	struct iov_iter		*from,
	int			*iolock)
{
	struct file		*file = iocb->ki_filp;
	struct inode		*inode = file->f_mapping->host;
	struct xfs_inode	*ip = XFS_I(inode);
	ssize_t			error = 0;
	size_t			count = iov_iter_count(from);
	bool			drained_dio = false;

restart:
	error = generic_write_checks(iocb, from);
	if (error <= 0)
		return error;

	error = xfs_break_layouts(inode, iolock);
	if (error)
		return error;

	/*
         * For changing security info in file_remove_privs() we need i_rwsem
         * exclusively.
         */
	if (*iolock == XFS_IOLOCK_SHARED && !IS_NOSEC(inode)) {
		xfs_iunlock(ip, *iolock);
		*iolock = XFS_IOLOCK_EXCL;
		xfs_ilock(ip, *iolock);
		goto restart;
	}
	/*
         * If the offset is beyond the size of the file, we need to zero any
         * blocks that fall between the existing EOF and the start of this
         * write.  If zeroing is needed and we are currently holding the
         * iolock shared, we need to update it to exclusive which implies
         * having to redo all checks before.
         *
         * We need to serialise against EOF updates that occur in IO
         * completions here. We want to make sure that nobody is changing the
         * size while we do this check until we have placed an IO barrier (i.e.
         * hold the XFS_IOLOCK_EXCL) that prevents new IO from being dispatched.
         * The spinlock effectively forms a memory barrier once we have the
         * XFS_IOLOCK_EXCL so we are guaranteed to see the latest EOF value
         * and hence be able to correctly determine if we need to run zeroing.
         */
	spin_lock(&ip->i_flags_lock);
	if (iocb->ki_pos > i_size_read(inode)) {
		bool	zero = false;

		spin_unlock(&ip->i_flags_lock);
		if (!drained_dio) {
			if (*iolock == XFS_IOLOCK_SHARED) {
				xfs_iunlock(ip, *iolock);
				*iolock = XFS_IOLOCK_EXCL;
				xfs_ilock(ip, *iolock);
				iov_iter_reexpand(from, count);
			}
			/*
                         * We now have an IO submission barrier in place, but
                         * AIO can do EOF updates during IO completion and hence
                         * we now need to wait for all of them to drain. Non-AIO
                         * DIO will have drained before we are given the
                         * XFS_IOLOCK_EXCL, and so for most cases this wait is a
                         * no-op.
                         */
			inode_dio_wait(inode);
			drained_dio = true;
			goto restart;
		}
		error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), &zero);
		if (error)
			return error;
	} else
		spin_unlock(&ip->i_flags_lock);

	/*
         * Updating the timestamps will grab the ilock again from
         * xfs_fs_dirty_inode, so we have to call it after dropping the
         * lock above.  Eventually we should look into a way to avoid
         * the pointless lock roundtrip.
         */
	if (likely(!(file->f_mode & FMODE_NOCMTIME))) {
		error = file_update_time(file);
		if (error)
			return error;
	}

	/*
         * If we're writing the file then make sure to clear the setuid and
         * setgid bits if the process is not being run by root.  This keeps
         * people from modifying setuid and setgid binaries.
         */
	if (!IS_NOSEC(inode))
		return file_remove_privs(file);
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Christoph Hellwig
121
37.81%
7
38.89%
Dave Chinner
81
25.31%
4
22.22%
Al Viro
40
12.50%
2
11.11%
Jan Kara
32
10.00%
2
11.11%
David Chinner
26
8.12%
1
5.56%
Brian Foster
14
4.38%
1
5.56%
Josef Bacik
6
1.88%
1
5.56%
Total
320
100.00%
18
100.00%


static int

xfs_dio_write_end_io(
	struct kiocb		*iocb,
	ssize_t			size,
	unsigned		flags)
{
	struct inode		*inode = file_inode(iocb->ki_filp);
	struct xfs_inode	*ip = XFS_I(inode);
	loff_t			offset = iocb->ki_pos;
	bool			update_size = false;
	int			error = 0;

	trace_xfs_end_io_direct_write(ip, offset, size);

	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
		return -EIO;

	if (size <= 0)
		return size;

	/*
         * 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
         * if necessary.
         *
         * We need to lock the test/set EOF update as we can be racing with
         * other IO completions here to update the EOF. Failing to serialise
         * here can result in EOF moving backwards and Bad Things Happen when
         * that occurs.
         */
	spin_lock(&ip->i_flags_lock);
	if (offset + size > i_size_read(inode)) {
		i_size_write(inode, offset + size);
		update_size = true;
	}
	spin_unlock(&ip->i_flags_lock);

	if (flags & IOMAP_DIO_COW) {
		error = xfs_reflink_end_cow(ip, offset, size);
		if (error)
			return error;
	}

	if (flags & IOMAP_DIO_UNWRITTEN)
		error = xfs_iomap_write_unwritten(ip, offset, size);
	else if (update_size)
		error = xfs_setfilesize(ip, offset, size);

	return error;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Christoph Hellwig
192
100.00%
1
100.00%
Total
192
100.00%
1
100.00%

/*
 * xfs_file_dio_aio_write - handle direct IO writes
 *
 * Lock the inode appropriately to prepare for and issue a direct IO write.
 * By separating it from the buffered write path we remove all the tricky to
 * follow locking changes and looping.
 *
 * If there are cached pages or we're extending the file, we need IOLOCK_EXCL
 * until we're sure the bytes at the new EOF have been zeroed and/or the cached
 * pages are flushed out.
 *
 * In most cases the direct IO writes will be done holding IOLOCK_SHARED
 * allowing them to be done in parallel with reads and other direct IO writes.
 * However, if the IO is not aligned to filesystem blocks, the direct IO layer
 * needs to do sub-block zeroing and that requires serialisation against other
 * direct IOs to the same block. In this case we need to serialise the
 * submission of the unaligned IOs so that we don't get racing block zeroing in
 * the dio layer.  To avoid the problem with aio, we also need to wait for
 * outstanding IOs to complete so that unwritten extent conversion is completed
 * before we try to map the overlapping block. This is currently implemented by
 * hitting it with a big hammer (i.e. inode_dio_wait()).
 *
 * Returns with locks held indicated by @iolock and errors indicated by
 * negative return values.
 */

STATIC ssize_t

xfs_file_dio_aio_write(
	struct kiocb		*iocb,
	struct iov_iter		*from)
{
	struct file		*file = iocb->ki_filp;
	struct address_space	*mapping = file->f_mapping;
	struct inode		*inode = mapping->host;
	struct xfs_inode	*ip = XFS_I(inode);
	struct xfs_mount	*mp = ip->i_mount;
	ssize_t			ret = 0;
	int			unaligned_io = 0;
	int			iolock;
	size_t			count = iov_iter_count(from);
	struct xfs_buftarg      *target = XFS_IS_REALTIME_INODE(ip) ?
					mp->m_rtdev_targp : mp->m_ddev_targp;

	/* DIO must be aligned to device logical sector size */
	if ((iocb->ki_pos | count) & target->bt_logical_sectormask)
		return -EINVAL;

	/*
         * Don't take the exclusive iolock here unless the I/O is unaligned to
         * the file system block size.  We don't need to consider the EOF
         * extension case here because xfs_file_aio_write_checks() will relock
         * the inode as necessary for EOF zeroing cases and fill out the new
         * inode size as appropriate.
         */
	if ((iocb->ki_pos & mp->m_blockmask) ||
	    ((iocb->ki_pos + count) & mp->m_blockmask)) {
		unaligned_io = 1;

		/*
                 * We can't properly handle unaligned direct I/O to reflink
                 * files yet, as we can't unshare a partial block.
                 */
		if (xfs_is_reflink_inode(ip)) {
			trace_xfs_reflink_bounce_dio_write(ip, iocb->ki_pos, count);
			return -EREMCHG;
		}
		iolock = XFS_IOLOCK_EXCL;
	} else {
		iolock = XFS_IOLOCK_SHARED;
	}

	xfs_ilock(ip, iolock);

	ret = xfs_file_aio_write_checks(iocb, from, &iolock);
	if (ret)
		goto out;
	count = iov_iter_count(from);

	/*
         * If we are doing unaligned IO, wait for all other IO to drain,
         * otherwise demote the lock if we had to take the exclusive lock
         * for other reasons in xfs_file_aio_write_checks.
         */
	if (unaligned_io)
		inode_dio_wait(inode);
	else if (iolock == XFS_IOLOCK_EXCL) {
		xfs_ilock_demote(ip, XFS_IOLOCK_EXCL);
		iolock = XFS_IOLOCK_SHARED;
	}

	trace_xfs_file_direct_write(ip, count, iocb->ki_pos);
	ret = iomap_dio_rw(iocb, from, &xfs_iomap_ops, xfs_dio_write_end_io);
out:
	xfs_iunlock(ip, iolock);

	/*
         * No fallback to buffered IO on errors for XFS, direct IO will either
         * complete fully or fail.
         */
	ASSERT(ret < 0 || ret == count);
	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dave Chinner
153
50.83%
5
19.23%
Christoph Hellwig
82
27.24%
13
50.00%
Al Viro
34
11.30%
3
11.54%
David Chinner
17
5.65%
1
3.85%
Jan Kara
6
1.99%
1
3.85%
Brian Foster
5
1.66%
1
3.85%
Eric Sandeen
4
1.33%
2
7.69%
Total
301
100.00%
26
100.00%


static noinline ssize_t

xfs_file_dax_write(
	struct kiocb		*iocb,
	struct iov_iter		*from)
{
	struct inode		*inode = iocb->ki_filp->f_mapping->host;
	struct xfs_inode	*ip = XFS_I(inode);
	int			iolock = XFS_IOLOCK_EXCL;
	ssize_t			ret, error = 0;
	size_t			count;
	loff_t			pos;

	xfs_ilock(ip, iolock);
	ret = xfs_file_aio_write_checks(iocb, from, &iolock);
	if (ret)
		goto out;

	pos = iocb->ki_pos;
	count = iov_iter_count(from);

	trace_xfs_file_dax_write(ip, count, pos);
	ret = dax_iomap_rw(iocb, from, &xfs_iomap_ops);
	if (ret > 0 && iocb->ki_pos > i_size_read(inode)) {
		i_size_write(inode, iocb->ki_pos);
		error = xfs_setfilesize(ip, pos, ret);
	}
out:
	xfs_iunlock(ip, iolock);
	return error ? error : ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dave Chinner
90
52.63%
5
31.25%
Christoph Hellwig
74
43.27%
7
43.75%
Al Viro
4
2.34%
2
12.50%
Arnd Bergmann
2
1.17%
1
6.25%
Ross Zwisler
1
0.58%
1
6.25%
Total
171
100.00%
16
100.00%


STATIC ssize_t

xfs_file_buffered_aio_write(
	struct kiocb		*iocb,
	struct iov_iter		*from)
{
	struct file		*file = iocb->ki_filp;
	struct address_space	*mapping = file->f_mapping;
	struct inode		*inode = mapping->host;
	struct xfs_inode	*ip = XFS_I(inode);
	ssize_t			ret;
	int			enospc = 0;
	int			iolock;

write_retry:
	iolock = XFS_IOLOCK_EXCL;
	xfs_ilock(ip, iolock);

	ret = xfs_file_aio_write_checks(iocb, from, &iolock);
	if (ret)
		goto out;

	/* We can write back this queue in page reclaim */
	current->backing_dev_info = inode_to_bdi(inode);

	trace_xfs_file_buffered_write(ip, iov_iter_count(from), iocb->ki_pos);
	ret = iomap_file_buffered_write(iocb, from, &xfs_iomap_ops);
	if (likely(ret >= 0))
		iocb->ki_pos += ret;

	/*
         * If we hit a space limit, try to free up some lingering preallocated
         * space before returning an error. In the case of ENOSPC, first try to
         * write back all dirty inodes to free up some of the excess reserved
         * metadata space. This reduces the chances that the eofblocks scan
         * waits on dirty mappings. Since xfs_flush_inodes() is serialized, this
         * also behaves as a filter to prevent too many eofblocks scans from
         * running at the same time.
         */
	if (ret == -EDQUOT && !enospc) {
		xfs_iunlock(ip, iolock);
		enospc = xfs_inode_free_quota_eofblocks(ip);
		if (enospc)
			goto write_retry;
		enospc = xfs_inode_free_quota_cowblocks(ip);
		if (enospc)
			goto write_retry;
		iolock = 0;
	} else if (ret == -ENOSPC && !enospc) {
		struct xfs_eofblocks eofb = {0};

		enospc = 1;
		xfs_flush_inodes(ip->i_mount);

		xfs_iunlock(ip, iolock);
		eofb.eof_flags = XFS_EOF_FLAGS_SYNC;
		xfs_icache_free_eofblocks(ip->i_mount, &eofb);
		goto write_retry;
	}

	current->backing_dev_info = NULL;
out:
	if (iolock)
		xfs_iunlock(ip, iolock);
	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Christoph Hellwig
149
53.41%
6
37.50%
Brian Foster
80
28.67%
2
12.50%
Al Viro
20
7.17%
3
18.75%
Dave Chinner
16
5.73%
4
25.00%
Darrick J. Wong
14
5.02%
1
6.25%
Total
279
100.00%
16
100.00%


STATIC ssize_t

xfs_file_write_iter(
	struct kiocb		*iocb,
	struct iov_iter		*from)
{
	struct file		*file = iocb->ki_filp;
	struct address_space	*mapping = file->f_mapping;
	struct inode		*inode = mapping->host;
	struct xfs_inode	*ip = XFS_I(inode);
	ssize_t			ret;
	size_t			ocount = iov_iter_count(from);

	XFS_STATS_INC(ip->i_mount, xs_write_calls);

	if (ocount == 0)
		return 0;

	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
		return -EIO;

	if (IS_DAX(inode))
		ret = xfs_file_dax_write(iocb, from);
	else if (iocb->ki_flags & IOCB_DIRECT) {
		/*
                 * Allow a directio write to fall back to a buffered
                 * write *only* in the case that we're doing a reflink
                 * CoW.  In all other directio scenarios we do not
                 * allow an operation to fall back to buffered mode.
                 */
		ret = xfs_file_dio_aio_write(iocb, from);
		if (ret == -EREMCHG)
			goto buffered;
	} else {
buffered:
		ret = xfs_file_buffered_aio_write(iocb, from);
	}

	if (ret > 0) {
		XFS_STATS_ADD(ip->i_mount, xs_write_bytes, ret);

		/* Handle various SYNC-type writes */
		ret = generic_write_sync(iocb, ret);
	}
	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dave Chinner
104
55.32%
2
14.29%
Christoph Hellwig
43
22.87%
5
35.71%
Darrick J. Wong
17
9.04%
1
7.14%
Al Viro
15
7.98%
4
28.57%
Bill O'Donnell
8
4.26%
1
7.14%
Josef Bacik
1
0.53%
1
7.14%
Total
188
100.00%
14
100.00%


#define	XFS_FALLOC_FL_SUPPORTED						\
		(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |           \
                 FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE |      \
                 FALLOC_FL_INSERT_RANGE | FALLOC_FL_UNSHARE_RANGE)


STATIC long

xfs_file_fallocate(
	struct file		*file,
	int			mode,
	loff_t			offset,
	loff_t			len)
{
	struct inode		*inode = file_inode(file);
	struct xfs_inode	*ip = XFS_I(inode);
	long			error;
	enum xfs_prealloc_flags	flags = 0;
	uint			iolock = XFS_IOLOCK_EXCL;
	loff_t			new_size = 0;
	bool			do_file_insert = 0;

	if (!S_ISREG(inode->i_mode))
		return -EINVAL;
	if (mode & ~XFS_FALLOC_FL_SUPPORTED)
		return -EOPNOTSUPP;

	xfs_ilock(ip, iolock);
	error = xfs_break_layouts(inode, &iolock);
	if (error)
		goto out_unlock;

	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
	iolock |= XFS_MMAPLOCK_EXCL;

	if (mode & FALLOC_FL_PUNCH_HOLE) {
		error = xfs_free_file_space(ip, offset, len);
		if (error)
			goto out_unlock;
	} else if (mode & FALLOC_FL_COLLAPSE_RANGE) {
		unsigned int blksize_mask = i_blocksize(inode) - 1;

		if (offset & blksize_mask || len & blksize_mask) {
			error = -EINVAL;
			goto out_unlock;
		}

		/*
                 * There is no need to overlap collapse range with EOF,
                 * in which case it is effectively a truncate operation
                 */
		if (offset + len >= i_size_read(inode)) {
			error = -EINVAL;
			goto out_unlock;
		}

		new_size = i_size_read(inode) - len;

		error = xfs_collapse_file_space(ip, offset, len);
		if (error)
			goto out_unlock;
	} else if (mode & FALLOC_FL_INSERT_RANGE) {
		unsigned int blksize_mask = i_blocksize(inode) - 1;

		new_size = i_size_read(inode) + len;
		if (offset & blksize_mask || len & blksize_mask) {
			error = -EINVAL;
			goto out_unlock;
		}

		/* check the new inode size does not wrap through zero */
		if (new_size > inode->i_sb->s_maxbytes) {
			error = -EFBIG;
			goto out_unlock;
		}

		/* Offset should be less than i_size */
		if (offset >= i_size_read(inode)) {
			error = -EINVAL;
			goto out_unlock;
		}
		do_file_insert = 1;
	} else {
		flags |= XFS_PREALLOC_SET;

		if (!(mode & FALLOC_FL_KEEP_SIZE) &&
		    offset + len > i_size_read(inode)) {
			new_size = offset + len;
			error = inode_newsize_ok(inode, new_size);
			if (error)
				goto out_unlock;
		}

		if (mode & FALLOC_FL_ZERO_RANGE)
			error = xfs_zero_file_space(ip, offset, len);
		else {
			if (mode & FALLOC_FL_UNSHARE_RANGE) {
				error = xfs_reflink_unshare(ip, offset, len);
				if (error)
					goto out_unlock;
			}
			error = xfs_alloc_file_space(ip, offset, len,
						     XFS_BMAPI_PREALLOC);
		}
		if (error)
			goto out_unlock;
	}

	if (file->f_flags & O_DSYNC)
		flags |= XFS_PREALLOC_SYNC;

	error = xfs_update_prealloc_flags(ip, flags);
	if (error)
		goto out_unlock;

	/* Change file size if needed */
	if (new_size) {
		struct iattr iattr;

		iattr.ia_valid = ATTR_SIZE;
		iattr.ia_size = new_size;
		error = xfs_vn_setattr_size(file_dentry(file), &iattr);
		if (error)
			goto out_unlock;
	}

	/*
         * Perform hole insertion now that the file size has been
         * updated so that if we crash during the operation we don't
         * leave shifted extents past EOF and hence losing access to
         * the data that is contained within them.
         */
	if (do_file_insert)
		error = xfs_insert_file_space(ip, offset, len);

out_unlock:
	xfs_iunlock(ip, iolock);
	return error;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Christoph Hellwig
266
48.63%
6
35.29%
Namjae Jeon
189
34.55%
2
11.76%
Lukas Czerner
31
5.67%
2
11.76%
Darrick J. Wong
28
5.12%
1
5.88%
Dave Chinner
17
3.11%
3
17.65%
Fabian Frederick
8
1.46%
1
5.88%
Jan Kara
5
0.91%
1
5.88%
Al Viro
3
0.55%
1
5.88%
Total
547
100.00%
17
100.00%


STATIC int

xfs_file_clone_range(
	struct file	*file_in,
	loff_t		pos_in,
	struct file	*file_out,
	loff_t		pos_out,
	u64		len)
{
	return xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out,
				     len, false);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Darrick J. Wong
31
75.61%
2
66.67%
Christoph Hellwig
10
24.39%
1
33.33%
Total
41
100.00%
3
100.00%


STATIC ssize_t

xfs_file_dedupe_range(
	struct file	*src_file,
	u64		loff,
	u64		len,
	struct file	*dst_file,
	u64		dst_loff)
{
	int		error;

	error = xfs_reflink_remap_range(src_file, loff, dst_file, dst_loff,
				     len, true);
	if (error)
		return error;
	return len;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Darrick J. Wong
54
98.18%
2
66.67%
Christoph Hellwig
1
1.82%
1
33.33%
Total
55
100.00%
3
100.00%


STATIC int

xfs_file_open(
	struct inode	*inode,
	struct file	*file)
{
	if (!(file->f_flags & O_LARGEFILE) && i_size_read(inode) > MAX_NON_LFS)
		return -EFBIG;
	if (XFS_FORCED_SHUTDOWN(XFS_M(inode->i_sb)))
		return -EIO;
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Christoph Hellwig
51
89.47%
3
50.00%
Stephen Lord
3
5.26%
1
16.67%
Nathan Scott
3
5.26%
2
33.33%
Total
57
100.00%
6
100.00%


STATIC int

xfs_dir_open(
	struct inode	*inode,
	struct file	*file)
{
	struct xfs_inode *ip = XFS_I(inode);
	int		mode;
	int		error;

	error = xfs_file_open(inode, file);
	if (error)
		return error;

	/*
         * If there are any blocks, read-ahead block 0 as we're almost
         * certain to have the next operation be a read there.
         */
	mode = xfs_ilock_data_map_shared(ip);
	if (ip->i_d.di_nextents > 0)
		error = xfs_dir3_data_readahead(ip, 0, -1);
	xfs_iunlock(ip, mode);
	return error;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Christoph Hellwig
79
89.77%
4
50.00%
Nathan Scott
3
3.41%
1
12.50%
Darrick J. Wong
3
3.41%
1
12.50%
Dave Chinner
3
3.41%
2
25.00%
Total
88
100.00%
8
100.00%


STATIC int

xfs_file_release(
	struct inode	*inode,
	struct file	*filp)
{
	return xfs_release(XFS_I(inode));
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Christoph Hellwig
23
92.00%
2
50.00%
Nathan Scott
2
8.00%
2
50.00%
Total
25
100.00%
4
100.00%


STATIC int

xfs_file_readdir(
	struct file	*file,
	struct dir_context *ctx)
{
	struct inode	*inode = file_inode(file);
	xfs_inode_t	*ip = XFS_I(inode);
	size_t		bufsize;

	/*
         * The Linux API doesn't pass down the total size of the buffer
         * we read into down to the filesystem.  With the filldir concept
         * it's not needed for correct information, but the XFS dir2 leaf
         * code wants an estimate of the buffer size to calculate it's
         * readahead window and size the buffers used for mapping to
         * physical blocks.
         *
         * Try to give it an estimate that's good enough, maybe at some
         * point we can change the ->readdir prototype to include the
         * buffer size.  For now we use the current glibc buffer size.
         */
	bufsize = (size_t)min_t(loff_t, 32768, ip->i_d.di_size);

	return xfs_readdir(ip, ctx, bufsize);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Christoph Hellwig
37
55.22%
5
38.46%
David Woodhouse
12
17.91%
1
7.69%
Al Viro
9
13.43%
2
15.38%
Lachlan McIlroy
4
5.97%
1
7.69%
Nathan Scott
2
2.99%
2
15.38%
Eric Sandeen
2
2.99%
1
7.69%
Fengguang Wu
1
1.49%
1
7.69%
Total
67
100.00%
13
100.00%

/*
 * This type is designed to indicate the type of offset we would like
 * to search from page cache for xfs_seek_hole_data().
 */
enum {
	
HOLE_OFF = 0,
	
DATA_OFF,
};

/*
 * Lookup the desired type of offset from the given page.
 *
 * On success, return true and the offset argument will point to the
 * start of the region that was found.  Otherwise this function will
 * return false and keep the offset argument unchanged.
 */

STATIC bool

xfs_lookup_buffer_offset(
	struct page		*page,
	loff_t			*offset,
	unsigned int		type)
{
	loff_t			lastoff = page_offset(page);
	bool			found = false;
	struct buffer_head	*bh, *head;

	bh = head = page_buffers(page);
	do {
		/*
                 * Unwritten extents that have data in the page
                 * cache covering them can be identified by the
                 * BH_Unwritten state flag.  Pages with multiple
                 * buffers might have a mix of holes, data and
                 * unwritten extents - any buffer with valid
                 * data in it should have BH_Uptodate flag set
                 * on it.
                 */
		if (buffer_unwritten(bh) ||
		    buffer_uptodate(bh)) {
			if (type == DATA_OFF)
				found = true;
		} else {
			if (type == HOLE_OFF)
				found = true;
		}

		if (found) {
			*offset = lastoff;
			break;
		}
		lastoff += bh->b_size;
	} while ((bh = bh->b_this_page) != head);

	return found;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Jie Liu
124
100.00%
1
100.00%
Total
124
100.00%
1
100.00%

/*
 * This routine is called to find out and return a data or hole offset
 * from the page cache for unwritten extents according to the desired
 * type for xfs_seek_hole_data().
 *
 * The argument offset is used to tell where we start to search from the
 * page cache.  Map is used to figure out the end points of the range to
 * lookup pages.
 *
 * Return true if the desired type of offset was found, and the argument
 * offset is filled with that address.  Otherwise, return false and keep
 * offset unchanged.
 */

STATIC bool

xfs_find_get_desired_pgoff(
	struct inode		*inode,
	struct xfs_bmbt_irec	*map,
	unsigned int		type,
	loff_t			*offset)
{
	struct xfs_inode	*ip = XFS_I(inode);
	struct xfs_mount	*mp = ip->i_mount;
	struct pagevec		pvec;
	pgoff_t			index;
	pgoff_t			end;
	loff_t			endoff;
	loff_t			startoff = *offset;
	loff_t			lastoff = startoff;
	bool			found = false;

	pagevec_init(&pvec, 0);

	index = startoff >> PAGE_SHIFT;
	endoff = XFS_FSB_TO_B(mp, map->br_startoff + map->br_blockcount);
	end = endoff >> PAGE_SHIFT;
	do {
		int		want;
		unsigned	nr_pages;
		unsigned int	i;

		want = min_t(pgoff_t, end - index, PAGEVEC_SIZE);
		nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index,
					  want);
		/*
                 * No page mapped into given range.  If we are searching holes
                 * and if this is the first time we got into the loop, it means
                 * that the given offset is landed in a hole, return it.
                 *
                 * If we have already stepped through some block buffers to find
                 * holes but they all contains data.  In this case, the last
                 * offset is already updated and pointed to the end of the last
                 * mapped page, if it does not reach the endpoint to search,
                 * that means there should be a hole between them.
                 */
		if (nr_pages == 0) {
			/* Data search found nothing */
			if (type == DATA_OFF)
				break;

			ASSERT(type == HOLE_OFF);
			if (lastoff == startoff || lastoff < endoff) {
				found = true;
				*offset = lastoff;
			}
			break;
		}

		/*
                 * At lease we found one page.  If this is the first time we
                 * step into the loop, and if the first page index offset is
                 * greater than the given search offset, a hole was found.
                 */
		if (type == HOLE_OFF && lastoff == startoff &&
		    lastoff < page_offset(pvec.pages[0])) {
			found = true;
			break;
		}

		for (i = 0; i < nr_pages; i++) {
			struct page	*page = pvec.pages[i];
			loff_t		b_offset;

			/*
                         * At this point, the page may be truncated or
                         * invalidated (changing page->mapping to NULL),
                         * or even swizzled back from swapper_space to tmpfs
                         * file mapping. However, page->index will not change
                         * because we have a reference on the page.
                         *
                         * Searching done if the page index is out of range.
                         * If the current offset is not reaches the end of
                         * the specified search range, there should be a hole
                         * between them.
                         */
			if (page->index > end) {
				if (type == HOLE_OFF && lastoff < endoff) {
					*offset = lastoff;
					found = true;
				}
				goto out;
			}

			lock_page(page);
			/*
                         * Page truncated or invalidated(page->mapping == NULL).
                         * We can freely skip it and proceed to check the next
                         * page.
                         */
			if (unlikely(page->mapping != inode->i_mapping)) {
				unlock_page(page);
				continue;
			}

			if (!page_has_buffers(page)) {
				unlock_page(page);
				continue;
			}

			found = xfs_lookup_buffer_offset(page, &b_offset, type);
			if (found) {
				/*
                                 * The found offset may be less than the start
                                 * point to search if this is the first time to
                                 * come here.
                                 */
				*offset = max_t(loff_t, startoff, b_offset);
				unlock_page(page);
				goto out;
			}

			/*
                         * We either searching data but nothing was found, or
                         * searching hole but found a data buffer.  In either
                         * case, probably the next page contains the desired
                         * things, update the last offset to it so.
                         */
			lastoff = page_offset(page) + PAGE_SIZE;
			unlock_page(page);
		}

		/*
                 * The number of returned pages less than our desired, search
                 * done.  In this case, nothing was found for searching data,
                 * but we found a hole behind the last offset.
                 */
		if (nr_pages < want) {
			if (type == HOLE_OFF) {
				*offset = lastoff;
				found = true;
			}
			break;
		}

		index = pvec.pages[i - 1]->index + 1;
		pagevec_release(&pvec);
	} while (index <= end);

out:
	pagevec_release(&pvec);
	return found;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Jie Liu
451
99.56%
1
50.00%
Kirill A. Shutemov
2
0.44%
1
50.00%
Total
453
100.00%
2
100.00%

/*
 * caller must lock inode with xfs_ilock_data_map_shared,
 * can we craft an appropriate ASSERT?
 *
 * end is because the VFS-level lseek interface is defined such that any
 * offset past i_size shall return -ENXIO, but we use this for quota code
 * which does not maintain i_size, and we want to SEEK_DATA past i_size.
 */

loff_t

__xfs_seek_hole_data(
	struct inode		*inode,
	loff_t			start,
	loff_t			end,
	int			whence)
{
	struct xfs_inode	*ip = XFS_I(inode);
	struct xfs_mount	*mp = ip->i_mount;
	loff_t			uninitialized_var(offset);
	xfs_fileoff_t		fsbno;
	xfs_filblks_t		lastbno;
	int			error;

	if (start >= end) {
		error = -ENXIO;
		goto out_error;
	}

	/*
         * Try to read extents from the first block indicated
         * by fsbno to the end block of the file.
         */
	fsbno = XFS_B_TO_FSBT(mp, start);
	lastbno = XFS_B_TO_FSB(mp, end);

	for (;;) {
		struct xfs_bmbt_irec	map[2];
		int			nmap = 2;
		unsigned int		i;

		error = xfs_bmapi_read(ip, fsbno, lastbno - fsbno, map, &nmap,
				       XFS_BMAPI_ENTIRE);
		if (error)
			goto out_error;

		/* No extents at given offset, must be beyond EOF */
		if (nmap == 0) {
			error = -ENXIO;
			goto out_error;
		}

		for (i = 0; i < nmap; i++) {
			offset = max_t(loff_t, start,
				       XFS_FSB_TO_B(mp, map[i].br_startoff));

			/* Landed in the hole we wanted? */
			if (whence == SEEK_HOLE &&
			    map[i].br_startblock == HOLESTARTBLOCK)
				goto out;

			/* Landed in the data extent we wanted? */
			if (whence == SEEK_DATA &&
			    (map[i].br_startblock == DELAYSTARTBLOCK ||
			     (map[i].br_state == XFS_EXT_NORM &&
			      !isnullstartblock(map[i].br_startblock))))
				goto out;

			/*
                         * Landed in an unwritten extent, try to search
                         * for hole or data from page cache.
                         */
			if (map[i].br_state == XFS_EXT_UNWRITTEN) {
				if (xfs_find_get_desired_pgoff(inode, &map[i],
				      whence == SEEK_HOLE ? HOLE_OFF : DATA_OFF,
							&offset))
					goto out;
			}
		}

		/*
                 * We only received one extent out of the two requested. This
                 * means we've hit EOF and didn't find what we are looking for.
                 */
		if (nmap == 1) {
			/*
                         * If we were looking for a hole, set offset to
                         * the end of the file (i.e., there is an implicit
                         * hole at the end of any file).
                         */
			if (whence == SEEK_HOLE) {
				offset = end;
				break;
			}
			/*
                         * If we were looking for data, it's nowhere to be found
                         */
			ASSERT(whence == SEEK_DATA);
			error = -ENXIO;
			goto out_error;
		}

		ASSERT(i > 1);

		/*
                 * Nothing was found, proceed to the next round of search
                 * if the next reading offset is not at or beyond EOF.
                 */
		fsbno = map[i - 1].br_startoff + map[i - 1].br_blockcount;
		start = XFS_FSB_TO_B(mp, fsbno);
		if (start >= end) {
			if (whence == SEEK_HOLE) {
				offset = end;
				break;
			}
			ASSERT(whence == SEEK_DATA);
			error = -ENXIO;
			goto out_error;
		}
	}

out:
	/*
         * If at this point we have found the hole we wanted, the returned
         * offset may be bigger than the file size as it may be aligned to
         * page boundary for unwritten extents.  We need to deal with this
         * situation in particular.
         */
	if (whence == SEEK_HOLE)
		offset = min_t(loff_t, offset, end);

	return offset;

out_error:
	return error;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Jie Liu
325
74.88%
3
50.00%
Eric Sandeen
105
24.19%
2
33.33%
Dave Chinner
4
0.92%
1
16.67%
Total
434
100.00%
6
100.00%


STATIC loff_t

xfs_seek_hole_data(
	struct file		*file,
	loff_t			start,
	int			whence)
{
	struct inode		*inode = file->f_mapping->host;
	struct xfs_inode	*ip = XFS_I(inode);
	struct xfs_mount	*mp = ip->i_mount;
	uint			lock;
	loff_t			offset, end;
	int			error = 0;

	if (XFS_FORCED_SHUTDOWN(mp))
		return -EIO;

	lock = xfs_ilock_data_map_shared(ip);

	end = i_size_read(inode);
	offset = __xfs_seek_hole_data(inode, start, end, whence);
	if (offset < 0) {
		error = offset;
		goto out_unlock;
	}

	offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);

out_unlock:
	xfs_iunlock(ip, lock);

	if (error)
		return error;
	return offset;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Eric Sandeen
110
74.83%
1
25.00%
Jie Liu
36
24.49%
2
50.00%
Christoph Hellwig
1
0.68%
1
25.00%
Total
147
100.00%
4
100.00%


STATIC loff_t

xfs_file_llseek(
	struct file	*file,
	loff_t		offset,
	int		whence)
{
	switch (whence) {
	case SEEK_END:
	case SEEK_CUR:
	case SEEK_SET:
		return generic_file_llseek(file, offset, whence);
	case SEEK_HOLE:
	case SEEK_DATA:
		return xfs_seek_hole_data(file, offset, whence);
	default:
		return -EINVAL;
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Jie Liu
55
87.30%
1
33.33%
Eric Sandeen
8
12.70%
2
66.67%
Total
63
100.00%
3
100.00%

/*
 * Locking for serialisation of IO during page faults. This results in a lock
 * ordering of:
 *
 * mmap_sem (MM)
 *   sb_start_pagefault(vfs, freeze)
 *     i_mmaplock (XFS - truncate serialisation)
 *       page_lock (MM)
 *         i_lock (XFS - extent map serialisation)
 */

/*
 * mmap()d file has taken write protection fault and is being made writable. We
 * can set the page state up correctly for a writable page, which means we can
 * do correct delalloc accounting (ENOSPC checking!) and unwritten extent
 * mapping.
 */

STATIC int

xfs_filemap_page_mkwrite(
	struct vm_fault		*vmf)
{
	struct inode		*inode = file_inode(vmf->vma->vm_file);
	int			ret;

	trace_xfs_filemap_page_mkwrite(XFS_I(inode));

	sb_start_pagefault(inode->i_sb);
	file_update_time(vmf->vma->vm_file);
	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);

	if (IS_DAX(inode)) {
		ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &xfs_iomap_ops);
	} else {
		ret = iomap_page_mkwrite(vmf, &xfs_iomap_ops);
		ret = block_page_mkwrite_return(ret);
	}

	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
	sb_end_pagefault(inode->i_sb);

	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dave Chinner
111
90.24%
2
28.57%
Dave Jiang
6
4.88%
2
28.57%
Christoph Hellwig
5
4.07%
2
28.57%
Ross Zwisler
1
0.81%
1
14.29%
Total
123
100.00%
7
100.00%


STATIC int

xfs_filemap_fault(
	struct vm_fault		*vmf)
{
	struct inode		*inode = file_inode(vmf->vma->vm_file);
	int			ret;

	trace_xfs_filemap_fault(XFS_I(inode));

	/* DAX can shortcut the normal fault path on write faults! */
	if ((vmf->flags & FAULT_FLAG_WRITE) && IS_DAX(inode))
		return xfs_filemap_page_mkwrite(vmf);

	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
	if (IS_DAX(inode))
		ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &xfs_iomap_ops);
	else
		ret = filemap_fault(vmf);
	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);

	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dave Chinner
101
93.52%
4
50.00%
Dave Jiang
4
3.70%
2
25.00%
Christoph Hellwig
2
1.85%
1
12.50%
Ross Zwisler
1
0.93%
1
12.50%
Total
108
100.00%
8
100.00%

/*
 * Similar to xfs_filemap_fault(), the DAX fault path can call into here on
 * both read and write faults. Hence we need to handle both cases. There is no
 * ->huge_mkwrite callout for huge pages, so we have a single function here to
 * handle both cases here. @flags carries the information on the type of fault
 * occuring.
 */

STATIC int

xfs_filemap_huge_fault(
	struct vm_fault		*vmf,
	enum page_entry_size	pe_size)
{
	struct inode		*inode = file_inode(vmf->vma->vm_file);
	struct xfs_inode	*ip = XFS_I(inode);
	int			ret;

	if (!IS_DAX(inode))
		return VM_FAULT_FALLBACK;

	trace_xfs_filemap_huge_fault(ip);

	if (vmf->flags & FAULT_FLAG_WRITE) {
		sb_start_pagefault(inode->i_sb);
		file_update_time(vmf->vma->vm_file);
	}

	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
	ret = dax_iomap_fault(vmf, pe_size, &xfs_iomap_ops);
	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);

	if (vmf->flags & FAULT_FLAG_WRITE)
		sb_end_pagefault(inode->i_sb);

	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Matthew Wilcox
98
73.13%
1
14.29%
Dave Jiang
20
14.93%
4
57.14%
Dave Chinner
14
10.45%
1
14.29%
Ross Zwisler
2
1.49%
1
14.29%
Total
134
100.00%
7
100.00%

/*
 * pfn_mkwrite was originally inteneded to ensure we capture time stamp
 * updates on write faults. In reality, it's need to serialise against
 * truncate similar to page_mkwrite. Hence we cycle the XFS_MMAPLOCK_SHARED
 * to ensure we serialise the fault barrier in place.
 */

static int

xfs_filemap_pfn_mkwrite(
	struct vm_fault		*vmf)
{

	struct inode		*inode = file_inode(vmf->vma->vm_file);
	struct xfs_inode	*ip = XFS_I(inode);
	int			ret = VM_FAULT_NOPAGE;
	loff_t			size;

	trace_xfs_filemap_pfn_mkwrite(ip);

	sb_start_pagefault(inode->i_sb);
	file_update_time(vmf->vma->vm_file);

	/* check if the faulting page hasn't raced with truncate */
	xfs_ilock(ip, XFS_MMAPLOCK_SHARED);
	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
	if (vmf->pgoff >= size)
		ret = VM_FAULT_SIGBUS;
	else if (IS_DAX(inode))
		ret = dax_pfn_mkwrite(vmf);
	xfs_iunlock(ip, XFS_MMAPLOCK_SHARED);
	sb_end_pagefault(inode->i_sb);
	return ret;

}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dave Chinner
101
77.10%
1
25.00%
Ross Zwisler
15
11.45%
1
25.00%
Matthew Wilcox
11
8.40%
1
25.00%
Dave Jiang
4
3.05%
1
25.00%
Total
131
100.00%
4
100.00%


static const struct vm_operations_struct xfs_file_vm_ops = {
	.fault		= xfs_filemap_fault,
	.huge_fault	= xfs_filemap_huge_fault,
	.map_pages	= filemap_map_pages,
	.page_mkwrite	= xfs_filemap_page_mkwrite,
	.pfn_mkwrite	= xfs_filemap_pfn_mkwrite,
};


STATIC int

xfs_file_mmap(
	struct file	*filp,
	struct vm_area_struct *vma)
{
	file_accessed(filp);
	vma->vm_ops = &xfs_file_vm_ops;
	if (IS_DAX(file_inode(filp)))
		vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Dave Chinner
47
95.92%
3
75.00%
Matthew Wilcox
2
4.08%
1
25.00%
Total
49
100.00%
4
100.00%


const struct file_operations xfs_file_operations = {
	.llseek		= xfs_file_llseek,
	.read_iter	= xfs_file_read_iter,
	.write_iter	= xfs_file_write_iter,
	.splice_read	= generic_file_splice_read,
	.splice_write	= iter_file_splice_write,
	.unlocked_ioctl	= xfs_file_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= xfs_file_compat_ioctl,
#endif
	.mmap		= xfs_file_mmap,
	.open		= xfs_file_open,
	.release	= xfs_file_release,
	.fsync		= xfs_file_fsync,
	.get_unmapped_area = thp_get_unmapped_area,
	.fallocate	= xfs_file_fallocate,
	.clone_file_range = xfs_file_clone_range,
	.dedupe_file_range = xfs_file_dedupe_range,
};


const struct file_operations xfs_dir_file_operations = {
	.open		= xfs_dir_open,
	.read		= generic_read_dir,
	.iterate_shared	= xfs_file_readdir,
	.llseek		= generic_file_llseek,
	.unlocked_ioctl	= xfs_file_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= xfs_file_compat_ioctl,
#endif
	.fsync		= xfs_dir_fsync,
};
Overall Contributors
Person
Tokens
Prop
Commits
CommitProp
Christoph Hellwig
2087
38.53%
54
32.34%
Jie Liu
1005
18.56%
5
2.99%
Dave Chinner
975
18.00%
36
21.56%
Eric Sandeen
232
4.28%
6
3.59%
Namjae Jeon
193
3.56%
2
1.20%
Darrick J. Wong
161
2.97%
6
3.59%
Al Viro
152
2.81%
15
8.98%
Brian Foster
114
2.10%
4
2.40%
Matthew Wilcox
114
2.10%
1
0.60%
David Chinner
74
1.37%
2
1.20%
Jan Kara
43
0.79%
3
1.80%
Nathan Scott
40
0.74%
5
2.99%
Dave Jiang
37
0.68%
5
2.99%
Josef Bacik
33
0.61%
2
1.20%
Lukas Czerner
31
0.57%
2
1.20%
Ross Zwisler
22
0.41%
3
1.80%
Stephen Lord
16
0.30%
2
1.20%
Russell Cattelan
16
0.30%
1
0.60%
Bill O'Donnell
14
0.26%
1
0.60%
Andi Kleen
13
0.24%
1
0.60%
David Woodhouse
12
0.22%
1
0.60%
Fabian Frederick
8
0.15%
1
0.60%
Toshi Kani
5
0.09%
1
0.60%
Lachlan McIlroy
4
0.07%
1
0.60%
Arnd Bergmann
4
0.07%
1
0.60%
Tejun Heo
3
0.06%
1
0.60%
Chris Mason
2
0.04%
1
0.60%
Kirill A. Shutemov
2
0.04%
1
0.60%
Arjan van de Ven
2
0.04%
1
0.60%
Alexey Dobriyan
1
0.02%
1
0.60%
Fengguang Wu
1
0.02%
1
0.60%
Total
5416
100.00%
167
100.00%
Directory: fs/xfs

Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.