path: root/fs/xfs/xfs_exchrange.c

// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Copyright (c) 2020-2024 Oracle.  All Rights Reserved.
 * Author: Darrick J. Wong <djwong@kernel.org>
 */
#include "xfs.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_defer.h"
#include "xfs_inode.h"
#include "xfs_trans.h"
#include "xfs_quota.h"
#include "xfs_bmap_util.h"
#include "xfs_reflink.h"
#include "xfs_trace.h"
#include "xfs_exchrange.h"
#include "xfs_exchmaps.h"
#include "xfs_sb.h"
#include "xfs_icache.h"
#include "xfs_log.h"
#include "xfs_rtbitmap.h"
#include <linux/fsnotify.h>

/* Lock (and optionally join) two inodes for a file range exchange. */
void
xfs_exchrange_ilock(
	struct xfs_trans	*tp,
	struct xfs_inode	*ip1,
	struct xfs_inode	*ip2)
{
	if (ip1 != ip2)
		xfs_lock_two_inodes(ip1, XFS_ILOCK_EXCL,
				    ip2, XFS_ILOCK_EXCL);
	else
		xfs_ilock(ip1, XFS_ILOCK_EXCL);
	if (tp) {
		xfs_trans_ijoin(tp, ip1, 0);
		if (ip2 != ip1)
			xfs_trans_ijoin(tp, ip2, 0);
	}

}

/* Unlock two inodes after a file range exchange operation. */
void
xfs_exchrange_iunlock(
	struct xfs_inode	*ip1,
	struct xfs_inode	*ip2)
{
	if (ip2 != ip1)
		xfs_iunlock(ip2, XFS_ILOCK_EXCL);
	xfs_iunlock(ip1, XFS_ILOCK_EXCL);
}

/*
 * Estimate the resource requirements to exchange file contents between the two
 * files.  The caller is required to hold the IOLOCK and the MMAPLOCK and to
 * have flushed both inodes' pagecache and active direct-ios.
 */
int
xfs_exchrange_estimate(
	struct xfs_exchmaps_req	*req)
{
	int			error;

	xfs_exchrange_ilock(NULL, req->ip1, req->ip2);
	error = xfs_exchmaps_estimate(req);
	xfs_exchrange_iunlock(req->ip1, req->ip2);
	return error;
}

/*
 * Check that file2's metadata agree with the snapshot that we took for the
 * range commit request.
 *
 * This should be called after the filesystem has locked /all/ inode metadata
 * against modification.
 */
STATIC int
xfs_exchrange_check_freshness(
	const struct xfs_exchrange	*fxr,
	struct xfs_inode		*ip2)
{
	struct inode			*inode2 = VFS_I(ip2);
	struct timespec64		ctime = inode_get_ctime(inode2);
	struct timespec64		mtime = inode_get_mtime(inode2);

	trace_xfs_exchrange_freshness(fxr, ip2);

	/* Check that file2 hasn't otherwise been modified. */
	if (fxr->file2_ino != ip2->i_ino ||
	    fxr->file2_gen != inode2->i_generation ||
	    !timespec64_equal(&fxr->file2_ctime, &ctime) ||
	    !timespec64_equal(&fxr->file2_mtime, &mtime))
		return -EBUSY;

	return 0;
}

#define QRETRY_IP1	(0x1)
#define QRETRY_IP2	(0x2)

/*
 * Obtain a quota reservation to make sure we don't hit EDQUOT.  We can skip
 * this if quota enforcement is disabled or if both inodes' dquots are the
 * same.  The qretry structure must be initialized to zeroes before the first
 * call to this function.
 */
STATIC int
xfs_exchrange_reserve_quota(
	struct xfs_trans		*tp,
	const struct xfs_exchmaps_req	*req,
	unsigned int			*qretry)
{
	int64_t				ddelta, rdelta;
	int				ip1_error = 0;
	int				error;

	ASSERT(!xfs_is_metadir_inode(req->ip1));
	ASSERT(!xfs_is_metadir_inode(req->ip2));

	/*
	 * Don't bother with a quota reservation if we're not enforcing them
	 * or the two inodes have the same dquots.
	 */
	if (!XFS_IS_QUOTA_ON(tp->t_mountp) || req->ip1 == req->ip2 ||
	    (req->ip1->i_udquot == req->ip2->i_udquot &&
	     req->ip1->i_gdquot == req->ip2->i_gdquot &&
	     req->ip1->i_pdquot == req->ip2->i_pdquot))
		return 0;

	*qretry = 0;

	/*
	 * For each file, compute the net gain in the number of regular blocks
	 * that will be mapped into that file and reserve that much quota.  The
	 * quota counts must be able to absorb at least that much space.
	 */
	ddelta = req->ip2_bcount - req->ip1_bcount;
	rdelta = req->ip2_rtbcount - req->ip1_rtbcount;
	if (ddelta > 0 || rdelta > 0) {
		error = xfs_trans_reserve_quota_nblks(tp, req->ip1,
				ddelta > 0 ? ddelta : 0,
				rdelta > 0 ? rdelta : 0,
				false);
		if (error == -EDQUOT || error == -ENOSPC) {
			/*
			 * Save this error and see what happens if we try to
			 * reserve quota for ip2.  Then report both.
			 */
			*qretry |= QRETRY_IP1;
			ip1_error = error;
			error = 0;
		}
		if (error)
			return error;
	}
	if (ddelta < 0 || rdelta < 0) {
		error = xfs_trans_reserve_quota_nblks(tp, req->ip2,
				ddelta < 0 ? -ddelta : 0,
				rdelta < 0 ? -rdelta : 0,
				false);
		if (error == -EDQUOT || error == -ENOSPC)
			*qretry |= QRETRY_IP2;
		if (error)