niansa-misc/linux
1
0
Fork 0
mirror of synced 2025-03-06 20:59:54 +01:00
Code Issues Projects Releases Packages Wiki Activity
linux/fs/xfs/scrub/common.h
Darrick J. Wong 66314e9a57 xfs: fix online repair probing when CONFIG_XFS_ONLINE_REPAIR=n 
I received a report from the release engineering side of the house that
xfs_scrub without the -n flag (aka fix it mode) would try to fix a
broken filesystem even on a kernel that doesn't have online repair built
into it:

 # xfs_scrub -dTvn /mnt/test
 EXPERIMENTAL xfs_scrub program in use! Use at your own risk!
 Phase 1: Find filesystem geometry.
 /mnt/test: using 1 threads to scrub.
 Phase 1: Memory used: 132k/0k (108k/25k), time:  0.00/ 0.00/ 0.00s
 <snip>
 Phase 4: Repair filesystem.
 <snip>
 Info: /mnt/test/some/victimdir directory entries: Attempting repair. (repair.c line 351)
 Corruption: /mnt/test/some/victimdir directory entries: Repair unsuccessful; offline repair required. (repair.c line 204)

Source: https://blogs.oracle.com/linux/post/xfs-online-filesystem-repair

It is strange that xfs_scrub doesn't refuse to run, because the kernel
is supposed to return EOPNOTSUPP if we actually needed to run a repair,
and xfs_io's repair subcommand will perror that.  And yet:

 # xfs_io -x -c 'repair probe' /mnt/test
 #

The first problem is commit dcb660f922 (4.15) which should have had
xchk_probe set the CORRUPT OFLAG so that any of the repair machinery
will get called at all.

It turns out that some refactoring that happened in the 6.6-6.8 era
broke the operation of this corner case.  What we *really* want to
happen is that all the predicates that would steer xfs_scrub_metadata()
towards calling xrep_attempt() should function the same way that they do
when repair is compiled in; and then xrep_attempt gets to return the
fatal EOPNOTSUPP error code that causes the probe to fail.

Instead, commit 8336a64eb7 (6.6) started the failwhale swimming by
hoisting OFLAG checking logic into a helper whose non-repair stub always
returns false, causing scrub to return "repair not needed" when in fact
the repair is not supported.  Prior to that commit, the oflag checking
that was open-coded in scrub.c worked correctly.

Similarly, in commit 4bdfd7d157 (6.8) we hoisted the IFLAG_REPAIR
and ALREADY_FIXED logic into a helper whose non-repair stub always
returns false, so we never enter the if test body that would have called
xrep_attempt, let alone fail to decode the OFLAGs correctly.

The final insult (yes, we're doing The Naked Gun now) is commit
48a72f6086 (6.8) in which we hoisted the "are we going to try a
repair?" predicate into yet another function with a non-repair stub
always returns false.

Fix xchk_probe to trigger xrep_probe if repair is enabled, or return
EOPNOTSUPP directly if it is not.  For all the other scrub types, we
need to fix the header predicates so that the ->repair functions (which
are all xrep_notsupported) get called to return EOPNOTSUPP.  Commit
48a72 is tagged here because the scrub code prior to LTS 6.12 are
incomplete and not worth patching.

Reported-by: David Flynn <david.flynn@oracle.com>
Cc: <stable@vger.kernel.org> # v6.8
Fixes: 8336a64eb7 ("xfs: don't complain about unfixed metadata when repairs were injected")
Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
2025-02-14 09:37:25 +01:00

297 lines
10 KiB
C
Raw Blame History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Copyright (C) 2017-2023 Oracle. All Rights Reserved.
* Author: Darrick J. Wong <djwong@kernel.org>
*/
#ifndef __XFS_SCRUB_COMMON_H__
#define __XFS_SCRUB_COMMON_H__
int xchk_trans_alloc(struct xfs_scrub *sc, uint resblks);
int xchk_trans_alloc_empty(struct xfs_scrub *sc);
void xchk_trans_cancel(struct xfs_scrub *sc);
bool xchk_process_error(struct xfs_scrub *sc, xfs_agnumber_t agno,
xfs_agblock_t bno, int *error);
bool xchk_process_rt_error(struct xfs_scrub *sc, xfs_rgnumber_t rgno,
xfs_rgblock_t rgbno, int *error);
bool xchk_fblock_process_error(struct xfs_scrub *sc, int whichfork,
xfs_fileoff_t offset, int *error);
bool xchk_xref_process_error(struct xfs_scrub *sc,
xfs_agnumber_t agno, xfs_agblock_t bno, int *error);
bool xchk_fblock_xref_process_error(struct xfs_scrub *sc,
int whichfork, xfs_fileoff_t offset, int *error);
void xchk_block_set_preen(struct xfs_scrub *sc,
struct xfs_buf *bp);
void xchk_ino_set_preen(struct xfs_scrub *sc, xfs_ino_t ino);
void xchk_set_corrupt(struct xfs_scrub *sc);
void xchk_block_set_corrupt(struct xfs_scrub *sc,
struct xfs_buf *bp);
void xchk_ino_set_corrupt(struct xfs_scrub *sc, xfs_ino_t ino);
void xchk_fblock_set_corrupt(struct xfs_scrub *sc, int whichfork,
xfs_fileoff_t offset);
#ifdef CONFIG_XFS_QUOTA
void xchk_qcheck_set_corrupt(struct xfs_scrub *sc, unsigned int dqtype,
xfs_dqid_t id);
#endif
void xchk_block_xref_set_corrupt(struct xfs_scrub *sc,
struct xfs_buf *bp);
void xchk_ino_xref_set_corrupt(struct xfs_scrub *sc,
xfs_ino_t ino);
void xchk_fblock_xref_set_corrupt(struct xfs_scrub *sc,
int whichfork, xfs_fileoff_t offset);
void xchk_ino_set_warning(struct xfs_scrub *sc, xfs_ino_t ino);
void xchk_fblock_set_warning(struct xfs_scrub *sc, int whichfork,
xfs_fileoff_t offset);
void xchk_set_incomplete(struct xfs_scrub *sc);
int xchk_checkpoint_log(struct xfs_mount *mp);
/* Are we set up for a cross-referencing check? */
bool xchk_should_check_xref(struct xfs_scrub *sc, int *error,
struct xfs_btree_cur **curpp);
static inline int xchk_setup_nothing(struct xfs_scrub *sc)
{
return -ENOENT;
}
/* Setup functions */
int xchk_setup_agheader(struct xfs_scrub *sc);
int xchk_setup_fs(struct xfs_scrub *sc);
int xchk_setup_rt(struct xfs_scrub *sc);
int xchk_setup_ag_allocbt(struct xfs_scrub *sc);
int xchk_setup_ag_iallocbt(struct xfs_scrub *sc);
int xchk_setup_ag_rmapbt(struct xfs_scrub *sc);
int xchk_setup_ag_refcountbt(struct xfs_scrub *sc);
int xchk_setup_inode(struct xfs_scrub *sc);
int xchk_setup_inode_bmap(struct xfs_scrub *sc);
int xchk_setup_inode_bmap_data(struct xfs_scrub *sc);
int xchk_setup_directory(struct xfs_scrub *sc);
int xchk_setup_xattr(struct xfs_scrub *sc);
int xchk_setup_symlink(struct xfs_scrub *sc);
int xchk_setup_parent(struct xfs_scrub *sc);
int xchk_setup_dirtree(struct xfs_scrub *sc);
int xchk_setup_metapath(struct xfs_scrub *sc);
#ifdef CONFIG_XFS_RT
int xchk_setup_rtbitmap(struct xfs_scrub *sc);
int xchk_setup_rtsummary(struct xfs_scrub *sc);
int xchk_setup_rgsuperblock(struct xfs_scrub *sc);
int xchk_setup_rtrmapbt(struct xfs_scrub *sc);
int xchk_setup_rtrefcountbt(struct xfs_scrub *sc);
#else
# define xchk_setup_rtbitmap xchk_setup_nothing
# define xchk_setup_rtsummary xchk_setup_nothing
# define xchk_setup_rgsuperblock xchk_setup_nothing
# define xchk_setup_rtrmapbt xchk_setup_nothing
# define xchk_setup_rtrefcountbt xchk_setup_nothing
#endif
#ifdef CONFIG_XFS_QUOTA
int xchk_ino_dqattach(struct xfs_scrub *sc);
int xchk_setup_quota(struct xfs_scrub *sc);
int xchk_setup_quotacheck(struct xfs_scrub *sc);
#else
static inline int
xchk_ino_dqattach(struct xfs_scrub *sc)
{
return 0;
}
# define xchk_setup_quota xchk_setup_nothing
# define xchk_setup_quotacheck xchk_setup_nothing
#endif
int xchk_setup_fscounters(struct xfs_scrub *sc);
int xchk_setup_nlinks(struct xfs_scrub *sc);
void xchk_ag_free(struct xfs_scrub *sc, struct xchk_ag *sa);
int xchk_ag_init(struct xfs_scrub *sc, xfs_agnumber_t agno,
struct xchk_ag *sa);
int xchk_perag_drain_and_lock(struct xfs_scrub *sc);
/*
* Grab all AG resources, treating the inability to grab the perag structure as
* a fs corruption. This is intended for callers checking an ondisk reference
* to a given AG, which means that the AG must still exist.
*/
static inline int
xchk_ag_init_existing(
struct xfs_scrub *sc,
xfs_agnumber_t agno,
struct xchk_ag *sa)
{
int error = xchk_ag_init(sc, agno, sa);
return error == -ENOENT ? -EFSCORRUPTED : error;
}
#ifdef CONFIG_XFS_RT
/* All the locks we need to check an rtgroup. */
#define XCHK_RTGLOCK_ALL (XFS_RTGLOCK_BITMAP | \
XFS_RTGLOCK_RMAP | \
XFS_RTGLOCK_REFCOUNT)
int xchk_rtgroup_init(struct xfs_scrub *sc, xfs_rgnumber_t rgno,
struct xchk_rt *sr);
static inline int
xchk_rtgroup_init_existing(
struct xfs_scrub *sc,
xfs_rgnumber_t rgno,
struct xchk_rt *sr)
{
int error = xchk_rtgroup_init(sc, rgno, sr);
return error == -ENOENT ? -EFSCORRUPTED : error;
}
int xchk_rtgroup_lock(struct xfs_scrub *sc, struct xchk_rt *sr,
unsigned int rtglock_flags);
void xchk_rtgroup_unlock(struct xchk_rt *sr);
void xchk_rtgroup_btcur_free(struct xchk_rt *sr);
void xchk_rtgroup_free(struct xfs_scrub *sc, struct xchk_rt *sr);
#else
# define xchk_rtgroup_init(sc, rgno, sr) (-EFSCORRUPTED)
# define xchk_rtgroup_init_existing(sc, rgno, sr) (-EFSCORRUPTED)
# define xchk_rtgroup_lock(sc, sr, lockflags) (-EFSCORRUPTED)
# define xchk_rtgroup_unlock(sr) do { } while (0)
# define xchk_rtgroup_btcur_free(sr) do { } while (0)
# define xchk_rtgroup_free(sc, sr) do { } while (0)
#endif /* CONFIG_XFS_RT */
int xchk_ag_read_headers(struct xfs_scrub *sc, xfs_agnumber_t agno,
struct xchk_ag *sa);
void xchk_ag_btcur_free(struct xchk_ag *sa);
void xchk_ag_btcur_init(struct xfs_scrub *sc, struct xchk_ag *sa);
int xchk_count_rmap_ownedby_ag(struct xfs_scrub *sc, struct xfs_btree_cur *cur,
const struct xfs_owner_info *oinfo, xfs_filblks_t *blocks);
int xchk_setup_ag_btree(struct xfs_scrub *sc, bool force_log);
int xchk_iget_for_scrubbing(struct xfs_scrub *sc);
int xchk_setup_inode_contents(struct xfs_scrub *sc, unsigned int resblks);
int xchk_install_live_inode(struct xfs_scrub *sc, struct xfs_inode *ip);
void xchk_ilock(struct xfs_scrub *sc, unsigned int ilock_flags);
bool xchk_ilock_nowait(struct xfs_scrub *sc, unsigned int ilock_flags);
void xchk_iunlock(struct xfs_scrub *sc, unsigned int ilock_flags);
void xchk_buffer_recheck(struct xfs_scrub *sc, struct xfs_buf *bp);
/*
* Grab the inode at @inum. The caller must have created a scrub transaction
* so that we can confirm the inumber by walking the inobt and not deadlock on
* a loop in the inobt.
*/
int xchk_iget(struct xfs_scrub *sc, xfs_ino_t inum, struct xfs_inode **ipp);
int xchk_iget_agi(struct xfs_scrub *sc, xfs_ino_t inum,
struct xfs_buf **agi_bpp, struct xfs_inode **ipp);
void xchk_irele(struct xfs_scrub *sc, struct xfs_inode *ip);
int xchk_install_handle_inode(struct xfs_scrub *sc, struct xfs_inode *ip);
/*
* Safe version of (untrusted) xchk_iget that uses an empty transaction to
* avoid deadlocking on loops in the inobt. This should only be used in a
* scrub or repair setup routine, and only prior to grabbing a transaction.
*/
static inline int
xchk_iget_safe(struct xfs_scrub *sc, xfs_ino_t inum, struct xfs_inode **ipp)
{
int error;
ASSERT(sc->tp == NULL);
error = xchk_trans_alloc(sc, 0);
if (error)
return error;
error = xchk_iget(sc, inum, ipp);
xchk_trans_cancel(sc);
return error;
}
/*
* Don't bother cross-referencing if we already found corruption or cross
* referencing discrepancies.
*/
static inline bool xchk_skip_xref(struct xfs_scrub_metadata *sm)
{
return sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT |
XFS_SCRUB_OFLAG_XCORRUPT);
}
bool xchk_dir_looks_zapped(struct xfs_inode *dp);
bool xchk_pptr_looks_zapped(struct xfs_inode *ip);
/* Decide if a repair is required. */
static inline bool xchk_needs_repair(const struct xfs_scrub_metadata *sm)
{
return sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT |
XFS_SCRUB_OFLAG_XCORRUPT |
XFS_SCRUB_OFLAG_PREEN);
}
/*
* "Should we prepare for a repair?"
*
* Return true if the caller permits us to repair metadata and we're not
* setting up for a post-repair evaluation.
*/
static inline bool xchk_could_repair(const struct xfs_scrub *sc)
{
return (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) &&
!(sc->flags & XREP_ALREADY_FIXED);
}
int xchk_metadata_inode_forks(struct xfs_scrub *sc);
/*
* Helper macros to allocate and format xfile description strings.
* Callers must kfree the pointer returned.
*/
#define xchk_xfile_descr(sc, fmt, ...) \
kasprintf(XCHK_GFP_FLAGS, "XFS (%s): " fmt, \
(sc)->mp->m_super->s_id, ##__VA_ARGS__)
#define xchk_xfile_ag_descr(sc, fmt, ...) \
kasprintf(XCHK_GFP_FLAGS, "XFS (%s): AG 0x%x " fmt, \
(sc)->mp->m_super->s_id, \
(sc)->sa.pag ? \
pag_agno((sc)->sa.pag) : (sc)->sm->sm_agno, \
##__VA_ARGS__)
#define xchk_xfile_ino_descr(sc, fmt, ...) \
kasprintf(XCHK_GFP_FLAGS, "XFS (%s): inode 0x%llx " fmt, \
(sc)->mp->m_super->s_id, \
(sc)->ip ? (sc)->ip->i_ino : (sc)->sm->sm_ino, \
##__VA_ARGS__)
#define xchk_xfile_rtgroup_descr(sc, fmt, ...) \
kasprintf(XCHK_GFP_FLAGS, "XFS (%s): rtgroup 0x%x " fmt, \
(sc)->mp->m_super->s_id, \
(sc)->sa.pag ? \
rtg_rgno((sc)->sr.rtg) : (sc)->sm->sm_agno, \
##__VA_ARGS__)
/*
* Setting up a hook to wait for intents to drain is costly -- we have to take
* the CPU hotplug lock and force an i-cache flush on all CPUs once to set it
* up, and again to tear it down. These costs add up quickly, so we only want
* to enable the drain waiter if the drain actually detected a conflict with
* running intent chains.
*/
static inline bool xchk_need_intent_drain(struct xfs_scrub *sc)
{
return sc->flags & XCHK_NEED_DRAIN;
}
void xchk_fsgates_enable(struct xfs_scrub *sc, unsigned int scrub_fshooks);
int xchk_inode_is_allocated(struct xfs_scrub *sc, xfs_agino_t agino,
bool *inuse);
int xchk_inode_count_blocks(struct xfs_scrub *sc, int whichfork,
xfs_extnum_t *nextents, xfs_filblks_t *count);
bool xchk_inode_is_dirtree_root(const struct xfs_inode *ip);
bool xchk_inode_is_sb_rooted(const struct xfs_inode *ip);
xfs_ino_t xchk_inode_rootdir_inum(const struct xfs_inode *ip);
#endif /* __XFS_SCRUB_COMMON_H__ */
Reference in a new issue View git blame Copy permalink