linux/fs/xfs/scrub/reap.c

// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Copyright (C) 2022-2023 Oracle.  All Rights Reserved.
 * Author: Darrick J. Wong <[email protected]>
 */
#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.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_bmap.h"
#include "xfs_da_format.h"
#include "xfs_da_btree.h"
#include "xfs_attr.h"
#include "xfs_attr_remote.h"
#include "xfs_defer.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/trace.h"
#include "scrub/repair.h"
#include "scrub/bitmap.h"
#include "scrub/agb_bitmap.h"
#include "scrub/fsb_bitmap.h"
#include "scrub/reap.h"

/*
 * Disposal of Blocks from Old Metadata
 *
 * Now that we've constructed a new btree to replace the damaged one, we want
 * to dispose of the blocks that (we think) the old btree was using.
 * Previously, we used the rmapbt to collect the extents (bitmap) with the
 * rmap owner corresponding to the tree we rebuilt, collected extents for any
 * blocks with the same rmap owner that are owned by another data structure
 * (sublist), and subtracted sublist from bitmap.  In theory the extents
 * remaining in bitmap are the old btree's blocks.
 *
 * Unfortunately, it's possible that the btree was crosslinked with other
 * blocks on disk.  The rmap data can tell us if there are multiple owners, so
 * if the rmapbt says there is an owner of this block other than @oinfo, then
 * the block is crosslinked.  Remove the reverse mapping and continue.
 *
 * If there is one rmap record, we can free the block, which removes the
 * reverse mapping but doesn't add the block to the free space.  Our repair
 * strategy is to hope the other metadata objects crosslinked on this block
 * will be rebuilt (atop different blocks), thereby removing all the cross
 * links.
 *
 * If there are no rmap records at all, we also free the block.  If the btree
 * being rebuilt lives in the free space (bnobt/cntbt/rmapbt) then there isn't
 * supposed to be a rmap record and everything is ok.  For other btrees there
 * had to have been an rmap entry for the block to have ended up on @bitmap,
 * so if it's gone now there's something wrong and the fs will shut down.
 *
 * Note: If there are multiple rmap records with only the same rmap owner as
 * the btree we're trying to rebuild and the block is indeed owned by another
 * data structure with the same rmap owner, then the block will be in sublist
 * and therefore doesn't need disposal.  If there are multiple rmap records
 * with only the same rmap owner but the block is not owned by something with
 * the same rmap owner, the block will be freed.
 *
 * The caller is responsible for locking the AG headers/inode for the entire
 * rebuild operation so that nothing else can sneak in and change the incore
 * state while we're not looking.  We must also invalidate any buffers
 * associated with @bitmap.
 */

/* Information about reaping extents after a repair. */
struct xreap_state { … };

/* Put a block back on the AGFL. */
STATIC int
xreap_put_freelist(
	struct xfs_scrub	*sc,
	xfs_agblock_t		agbno)
{ … }

/* Are there any uncommitted reap operations? */
static inline bool xreap_dirty(const struct xreap_state *rs)
{ … }

#define XREAP_MAX_BINVAL …

/*
 * Decide if we want to roll the transaction after reaping an extent.  We don't
 * want to overrun the transaction reservation, so we prohibit more than
 * 128 EFIs per transaction.  For the same reason, we limit the number
 * of buffer invalidations to 2048.
 */
static inline bool xreap_want_roll(const struct xreap_state *rs)
{ … }

static inline void xreap_reset(struct xreap_state *rs)
{ … }

#define XREAP_MAX_DEFER_CHAIN …

/*
 * Decide if we want to finish the deferred ops that are attached to the scrub
 * transaction.  We don't want to queue huge chains of deferred ops because
 * that can consume a lot of log space and kernel memory.  Hence we trigger a
 * xfs_defer_finish if there are more than 2048 deferred reap operations or the
 * caller did some real work.
 */
static inline bool
xreap_want_defer_finish(const struct xreap_state *rs)
{ … }

static inline void xreap_defer_finish_reset(struct xreap_state *rs)
{ … }

/*
 * Compute the maximum length of a buffer cache scan (in units of sectors),
 * given a quantity of fs blocks.
 */
xfs_daddr_t
xrep_bufscan_max_sectors(
	struct xfs_mount	*mp,
	xfs_extlen_t		fsblocks)
{ … }

/*
 * Return an incore buffer from a sector scan, or NULL if there are no buffers
 * left to return.
 */
struct xfs_buf *
xrep_bufscan_advance(
	struct xfs_mount	*mp,
	struct xrep_bufscan	*scan)
{ … }

/* Try to invalidate the incore buffers for an extent that we're freeing. */
STATIC void
xreap_agextent_binval(
	struct xreap_state	*rs,
	xfs_agblock_t		agbno,
	xfs_extlen_t		*aglenp)
{ … }

/*
 * Figure out the longest run of blocks that we can dispose of with a single
 * call.  Cross-linked blocks should have their reverse mappings removed, but
 * single-owner extents can be freed.  AGFL blocks can only be put back one at
 * a time.
 */
STATIC int
xreap_agextent_select(
	struct xreap_state	*rs,
	xfs_agblock_t		agbno,
	xfs_agblock_t		agbno_next,
	bool			*crosslinked,
	xfs_extlen_t		*aglenp)
{ … }

/*
 * Dispose of as much of the beginning of this AG extent as possible.  The
 * number of blocks disposed of will be returned in @aglenp.
 */
STATIC int
xreap_agextent_iter(
	struct xreap_state	*rs,
	xfs_agblock_t		agbno,
	xfs_extlen_t		*aglenp,
	bool			crosslinked)
{ … }

/*
 * Break an AG metadata extent into sub-extents by fate (crosslinked, not
 * crosslinked), and dispose of each sub-extent separately.
 */
STATIC int
xreap_agmeta_extent(
	uint32_t		agbno,
	uint32_t		len,
	void			*priv)
{ … }

/* Dispose of every block of every AG metadata extent in the bitmap. */
int
xrep_reap_agblocks(
	struct xfs_scrub		*sc,
	struct xagb_bitmap		*bitmap,
	const struct xfs_owner_info	*oinfo,
	enum xfs_ag_resv_type		type)
{ … }

/*
 * Break a file metadata extent into sub-extents by fate (crosslinked, not
 * crosslinked), and dispose of each sub-extent separately.  The extent must
 * not cross an AG boundary.
 */
STATIC int
xreap_fsmeta_extent(
	uint64_t		fsbno,
	uint64_t		len,
	void			*priv)
{ … }

/*
 * Dispose of every block of every fs metadata extent in the bitmap.
 * Do not use this to dispose of the mappings in an ondisk inode fork.
 */
int
xrep_reap_fsblocks(
	struct xfs_scrub		*sc,
	struct xfsb_bitmap		*bitmap,
	const struct xfs_owner_info	*oinfo)
{ … }

/*
 * Metadata files are not supposed to share blocks with anything else.
 * If blocks are shared, we remove the reverse mapping (thus reducing the
 * crosslink factor); if blocks are not shared, we also need to free them.
 *
 * This first step determines the longest subset of the passed-in imap
 * (starting at its beginning) that is either crosslinked or not crosslinked.
 * The blockcount will be adjust down as needed.
 */
STATIC int
xreap_bmapi_select(
	struct xfs_scrub	*sc,
	struct xfs_inode	*ip,
	int			whichfork,
	struct xfs_bmbt_irec	*imap,
	bool			*crosslinked)
{ … }

/*
 * Decide if this buffer can be joined to a transaction.  This is true for most
 * buffers, but there are two cases that we want to catch: large remote xattr
 * value buffers are not logged and can overflow the buffer log item dirty
 * bitmap size; and oversized cached buffers if things have really gone
 * haywire.
 */
static inline bool
xreap_buf_loggable(
	const struct xfs_buf	*bp)
{ … }

/*
 * Invalidate any buffers for this file mapping.  The @imap blockcount may be
 * adjusted downward if we need to roll the transaction.
 */
STATIC int
xreap_bmapi_binval(
	struct xfs_scrub	*sc,
	struct xfs_inode	*ip,
	int			whichfork,
	struct xfs_bmbt_irec	*imap)
{ … }

/*
 * Dispose of as much of the beginning of this file fork mapping as possible.
 * The number of blocks disposed of is returned in @imap->br_blockcount.
 */
STATIC int
xrep_reap_bmapi_iter(
	struct xfs_scrub		*sc,
	struct xfs_inode		*ip,
	int				whichfork,
	struct xfs_bmbt_irec		*imap,
	bool				crosslinked)
{ … }

/*
 * Dispose of as much of this file extent as we can.  Upon successful return,
 * the imap will reflect the mapping that was removed from the fork.
 */
STATIC int
xreap_ifork_extent(
	struct xfs_scrub		*sc,
	struct xfs_inode		*ip,
	int				whichfork,
	struct xfs_bmbt_irec		*imap)
{ … }

/*
 * Dispose of each block mapped to the given fork of the given file.  Callers
 * must hold ILOCK_EXCL, and ip can only be sc->ip or sc->tempip.  The fork
 * must not have any delalloc reservations.
 */
int
xrep_reap_ifork(
	struct xfs_scrub	*sc,
	struct xfs_inode	*ip,
	int			whichfork)
{ … }