path: root/fs/xfs/scrub/bmap.c

// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Copyright (C) 2017-2023 Oracle.  All Rights Reserved.
 * Author: Darrick J. Wong <djwong@kernel.org>
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_btree.h"
#include "xfs_bit.h"
#include "xfs_log_format.h"
#include "xfs_trans.h"
#include "xfs_inode.h"
#include "xfs_alloc.h"
#include "xfs_bmap.h"
#include "xfs_bmap_btree.h"
#include "xfs_rmap.h"
#include "xfs_rmap_btree.h"
#include "xfs_health.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/btree.h"
#include "scrub/health.h"
#include "xfs_ag.h"

/* Set us up with an inode's bmap. */
int
xchk_setup_inode_bmap(
	struct xfs_scrub	*sc)
{
	int			error;

	if (xchk_need_intent_drain(sc))
		xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN);

	error = xchk_iget_for_scrubbing(sc);
	if (error)
		goto out;

	xchk_ilock(sc, XFS_IOLOCK_EXCL);

	/*
	 * We don't want any ephemeral data/cow fork updates sitting around
	 * while we inspect block mappings, so wait for directio to finish
	 * and flush dirty data if we have delalloc reservations.
	 */
	if (S_ISREG(VFS_I(sc->ip)->i_mode) &&
	    sc->sm->sm_type != XFS_SCRUB_TYPE_BMBTA) {
		struct address_space	*mapping = VFS_I(sc->ip)->i_mapping;
		bool			is_repair = xchk_could_repair(sc);

		xchk_ilock(sc, XFS_MMAPLOCK_EXCL);

		/* Break all our leases, we're going to mess with things. */
		if (is_repair) {
			error = xfs_break_layouts(VFS_I(sc->ip),
					&sc->ilock_flags, BREAK_WRITE);
			if (error)
				goto out;
		}

		inode_dio_wait(VFS_I(sc->ip));

		/*
		 * Try to flush all incore state to disk before we examine the
		 * space mappings for the data fork.  Leave accumulated errors
		 * in the mapping for the writer threads to consume.
		 *
		 * On ENOSPC or EIO writeback errors, we continue into the
		 * extent mapping checks because write failures do not
		 * necessarily imply anything about the correctness of the file
		 * metadata.  The metadata and the file data could be on
		 * completely separate devices; a media failure might only
		 * affect a subset of the disk, etc.  We can handle delalloc
		 * extents in the scrubber, so leaving them in memory is fine.
		 */
		error = filemap_fdatawrite(mapping);
		if (!error)
			error = filemap_fdatawait_keep_errors(mapping);
		if (error && (error != -ENOSPC && error != -EIO))
			goto out;

		/* Drop the page cache if we're repairing block mappings. */
		if (is_repair) {
			error = invalidate_inode_pages2(
					VFS_I(sc->ip)->i_mapping);
			if (error)
				goto out;
		}

	}

	/* Got the inode, lock it and we're ready to go. */
	error = xchk_trans_alloc(sc, 0);
	if (error)
		goto out;

	error = xchk_ino_dqattach(sc);
	if (error)
		goto out;

	xchk_ilock(sc, XFS_ILOCK_EXCL);
out:
	/* scrub teardown will unlock and release the inode */
	return error;
}

/*
 * Inode fork block mapping (BMBT) scrubber.
 * More complex than the others because we have to scrub
 * all the extents regardless of whether or not the fork
 * is in btree format.
 */

struct xchk_bmap_info {
	struct xfs_scrub	*sc;

	/* Incore extent tree cursor */
	struct xfs_iext_cursor	icur;

	/* Previous fork mapping that we examined */
	struct xfs_bmbt_irec	prev_rec;

	/* Is this a realtime fork? */
	bool			is_rt;

	/* May mappings point to shared space? */
	bool			is_shared;

	/* Was the incore extent tree loaded? */
	bool			was_loaded;

	/* Which inode fork are we checking? */
	int			whichfork;
};

/* Look for a corresponding rmap for this irec. */
static inline bool
xchk_bmap_get_rmap(
	struct xchk_bmap_info	*info,
	struct xfs_bmbt_irec	*irec,
	xfs_agblock_t		agbno,
	uint64_t		owner,
	struct xfs_rmap_irec	*rmap)
{
	xfs_fileoff_t		offset;
	unsigned int		rflags = 0;
	int			has_rmap;
	int			error;

	if (info->whichfork == XFS_ATTR_FORK)
		rflags |= XFS_RMAP_ATTR_FORK;
	if (irec->br_state == XFS_EXT_UNWRITTEN)
		rflags |= XFS_RMAP_UNWRITTEN;

	/*
	 * CoW staging extents are owned (on disk) by the refcountbt, so
	 * their rmaps do not have offsets.
	 */
	if (info->whichfork == XFS_COW_FORK)
		offset = 0;
	else
		offset = irec->br_startoff;

	/*
	 * If the caller thinks this could be a shared bmbt extent (IOWs,
	 * any data fork extent of a reflink inode) then we have to use the
	 * range rmap lookup to make sure we get the correct owner/offset.
	 */
	if (info->is_shared) {
		error = xfs_rmap_lookup_le_range(info->sc->sa.rmap_cur, agbno,
				owner, offset, rflags, rmap, &has_rmap);
	} else {
		error = xfs_rmap_lookup_le(info->sc->sa.rmap_cur, agbno,
				owner, offset, rflags, rmap, &has_rmap);
	}
	if (!xchk_should_check_xref(info->sc, &error, &info->sc->sa.rmap_cur))
		return false;

	if (!has_rmap)
		xchk_fblock_xref_set_corrupt(info->sc, info->whichfork,
			irec->br_startoff);
	return has_rmap;
}

/* Make sure that we have rmapbt records for this data/attr fork extent. */
STATIC void
xchk_bmap_xref_rmap(
	struct xchk_bmap_info	*info,
	struct xfs_bmbt_irec	*irec,
	xfs_agblock_t		agbno)
{
	struct xfs_rmap_irec	rmap;
	unsigned long long	rmap_end;
	uint64_t		owner = info->sc->ip->i_ino;

	if (!info->sc->sa.rmap_cur || xchk_skip_xref(info->sc->sm))
		return;