linux/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 <[email protected]>
 */
#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)
{ … }

/* Unlock two inodes after a file range exchange operation. */
void
xfs_exchrange_iunlock(
	struct xfs_inode	*ip1,
	struct xfs_inode	*ip2)
{ … }

/*
 * 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)
{ … }

#define QRETRY_IP1 …
#define QRETRY_IP2 …

/*
 * 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)
{ … }

/* Exchange the mappings (and hence the contents) of two files' forks. */
STATIC int
xfs_exchrange_mappings(
	const struct xfs_exchrange	*fxr,
	struct xfs_inode		*ip1,
	struct xfs_inode		*ip2)
{ … }

/*
 * Generic code for exchanging ranges of two files via XFS_IOC_EXCHANGE_RANGE.
 * This part deals with struct file objects and byte ranges and does not deal
 * with XFS-specific data structures such as xfs_inodes and block ranges.  This
 * separation may some day facilitate porting to another filesystem.
 *
 * The goal is to exchange fxr.length bytes starting at fxr.file1_offset in
 * file1 with the same number of bytes starting at fxr.file2_offset in file2.
 * Implementations must call xfs_exchange_range_prep to prepare the two
 * files prior to taking locks; and they must update the inode change and mod
 * times of both files as part of the metadata update.  The timestamp update
 * and freshness checks must be done atomically as part of the data exchange
 * operation to ensure correctness of the freshness check.
 * xfs_exchange_range_finish must be called after the operation completes
 * successfully but before locks are dropped.
 */

/* Verify that we have security clearance to perform this operation. */
static int
xfs_exchange_range_verify_area(
	struct xfs_exchrange	*fxr)
{ … }

/*
 * Performs necessary checks before doing a range exchange, having stabilized
 * mutable inode attributes via i_rwsem.
 */
static inline int
xfs_exchange_range_checks(
	struct xfs_exchrange	*fxr,
	unsigned int		alloc_unit)
{ … }

/*
 * Check that the two inodes are eligible for range exchanges, the ranges make
 * sense, and then flush all dirty data.  Caller must ensure that the inodes
 * have been locked against any other modifications.
 */
static inline int
xfs_exchange_range_prep(
	struct xfs_exchrange	*fxr,
	unsigned int		alloc_unit)
{ … }

/*
 * Finish a range exchange operation, if it was successful.  Caller must ensure
 * that the inodes are still locked against any other modifications.
 */
static inline int
xfs_exchange_range_finish(
	struct xfs_exchrange	*fxr)
{ … }

/*
 * Check the alignment of an exchange request when the allocation unit size
 * isn't a power of two.  The generic file-level helpers use (fast)
 * bitmask-based alignment checks, but here we have to use slow long division.
 */
static int
xfs_exchrange_check_rtalign(
	const struct xfs_exchrange	*fxr,
	struct xfs_inode		*ip1,
	struct xfs_inode		*ip2,
	unsigned int			alloc_unit)
{ … }

/* Prepare two files to have their data exchanged. */
STATIC int
xfs_exchrange_prep(
	struct xfs_exchrange	*fxr,
	struct xfs_inode	*ip1,
	struct xfs_inode	*ip2)
{ … }

/*
 * Exchange contents of files.  This is the binding between the generic
 * file-level concepts and the XFS inode-specific implementation.
 */
STATIC int
xfs_exchrange_contents(
	struct xfs_exchrange	*fxr)
{ … }

/* Exchange parts of two files. */
static int
xfs_exchange_range(
	struct xfs_exchrange	*fxr)
{ … }

/* Collect exchange-range arguments from userspace. */
long
xfs_ioc_exchange_range(
	struct file			*file,
	struct xfs_exchange_range __user *argp)
{ … }