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

// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Copyright (C) 2018-2023 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_log_format.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_inode.h"
#include "xfs_alloc.h"
#include "xfs_alloc_btree.h"
#include "xfs_ialloc.h"
#include "xfs_ialloc_btree.h"
#include "xfs_rmap.h"
#include "xfs_rmap_btree.h"
#include "xfs_refcount_btree.h"
#include "xfs_extent_busy.h"
#include "xfs_ag.h"
#include "xfs_ag_resv.h"
#include "xfs_quota.h"
#include "xfs_qm.h"
#include "xfs_defer.h"
#include "xfs_errortag.h"
#include "xfs_error.h"
#include "xfs_reflink.h"
#include "xfs_health.h"
#include "xfs_buf_mem.h"
#include "xfs_da_format.h"
#include "xfs_da_btree.h"
#include "xfs_attr.h"
#include "xfs_dir2.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/trace.h"
#include "scrub/repair.h"
#include "scrub/bitmap.h"
#include "scrub/stats.h"
#include "scrub/xfile.h"
#include "scrub/attr_repair.h"

/*
 * Attempt to repair some metadata, if the metadata is corrupt and userspace
 * told us to fix it.  This function returns -EAGAIN to mean "re-run scrub",
 * and will set *fixed to true if it thinks it repaired anything.
 */
int
xrep_attempt(
	struct xfs_scrub	*sc,
	struct xchk_stats_run	*run)
{
	u64			repair_start;
	int			error = 0;

	trace_xrep_attempt(XFS_I(file_inode(sc->file)), sc->sm, error);

	xchk_ag_btcur_free(&sc->sa);

	/* Repair whatever's broken. */
	ASSERT(sc->ops->repair);
	run->repair_attempted = true;
	repair_start = xchk_stats_now();
	error = sc->ops->repair(sc);
	trace_xrep_done(XFS_I(file_inode(sc->file)), sc->sm, error);
	run->repair_ns += xchk_stats_elapsed_ns(repair_start);
	switch (error) {
	case 0:
		/*
		 * Repair succeeded.  Commit the fixes and perform a second
		 * scrub so that we can tell userspace if we fixed the problem.
		 */
		sc->sm->sm_flags &= ~XFS_SCRUB_FLAGS_OUT;
		sc->flags |= XREP_ALREADY_FIXED;
		run->repair_succeeded = true;
		return -EAGAIN;
	case -ECHRNG:
		sc->flags |= XCHK_NEED_DRAIN;
		run->retries++;
		return -EAGAIN;
	case -EDEADLOCK:
		/* Tell the caller to try again having grabbed all the locks. */
		if (!(sc->flags & XCHK_TRY_HARDER)) {
			sc->flags |= XCHK_TRY_HARDER;
			run->retries++;
			return -EAGAIN;
		}
		/*
		 * We tried harder but still couldn't grab all the resources
		 * we needed to fix it.  The corruption has not been fixed,
		 * so exit to userspace with the scan's output flags unchanged.
		 */
		return 0;
	default:
		/*
		 * EAGAIN tells the caller to re-scrub, so we cannot return
		 * that here.
		 */
		ASSERT(error != -EAGAIN);
		return error;
	}
}

/*
 * Complain about unfixable problems in the filesystem.  We don't log
 * corruptions when IFLAG_REPAIR wasn't set on the assumption that the driver
 * program is xfs_scrub, which will call back with IFLAG_REPAIR set if the
 * administrator isn't running xfs_scrub in no-repairs mode.
 *
 * Use this helper function because _ratelimited silently declares a static
 * structure to track rate limiting information.
 */
void
xrep_failure(
	struct xfs_mount	*mp)
{
	xfs_alert_ratelimited(mp,
"Corruption not fixed during online repair.  Unmount and run xfs_repair.");
}

/*
 * Repair probe -- userspace uses this to probe if we're willing to repair a
 * given mountpoint.
 */
int
xrep_probe(
	struct xfs_scrub	*sc)
{
	int			error = 0;

	if (xchk_should_terminate(sc, &error))
		return error;

	return 0;
}

/*
 * Roll a transaction, keeping the AG headers locked and reinitializing
 * the btree cursors.
 */
int
xrep_roll_ag_trans(
	struct xfs_scrub	*sc)
{
	int			error;

	/*
	 * Keep the AG header buffers locked while we roll the transaction.
	 * Ensure that both AG buffers are dirty and held when we roll the
	 * transaction so that they move forward in the log without losing the
	 * bli (and hence the bli type) when the transaction commits.
	 *
	 * Normal code would never hold clean buffers across a roll, but repair
	 * needs both buffers to maintain a total lock on the AG.
	 */
	if (sc->sa.agi_bp) {
		xfs_ialloc_log_agi(sc->tp, sc->sa.agi_bp, XFS_AGI_MAGICNUM);
		xfs_tra