From 0b8686f19879d896bbe2d3e893f433a08160452d Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Thu, 22 Feb 2024 12:31:01 -0800 Subject: [PATCH] xfs: separate the marking of sick and checked metadata Split the setting of the sick and checked masks into separate functions as part of preparing to add the ability for regular runtime fs code (i.e. not scrub) to mark metadata structures sick when corruptions are found. Improve the documentation of libxfs' requirements for helper behavior. Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig --- fs/xfs/libxfs/xfs_health.h | 23 +++++++++++++- fs/xfs/scrub/health.c | 8 ++--- fs/xfs/xfs_health.c | 65 ++++++++++++++++++++++++++++++++++++++ fs/xfs/xfs_trace.h | 4 +++ 4 files changed, 95 insertions(+), 5 deletions(-) diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h index 2bfe2dc404a19..bec7adf9fcf7c 100644 --- a/fs/xfs/libxfs/xfs_health.h +++ b/fs/xfs/libxfs/xfs_health.h @@ -111,24 +111,45 @@ struct xfs_fsop_geom; XFS_SICK_INO_DIR_ZAPPED | \ XFS_SICK_INO_SYMLINK_ZAPPED) -/* These functions must be provided by the xfs implementation. */ +/* + * These functions must be provided by the xfs implementation. Function + * behavior with respect to the first argument should be as follows: + * + * xfs_*_mark_sick: Set the sick flags and do not set checked flags. + * Runtime code should call this upon encountering + * a corruption. + * + * xfs_*_mark_corrupt: Set the sick and checked flags simultaneously. + * Fsck tools should call this when corruption is + * found. + * + * xfs_*_mark_healthy: Clear the sick flags and set the checked flags. + * Fsck tools should call this after correcting errors. + * + * xfs_*_measure_sickness: Return the sick and check status in the provided + * out parameters. + */ void xfs_fs_mark_sick(struct xfs_mount *mp, unsigned int mask); +void xfs_fs_mark_corrupt(struct xfs_mount *mp, unsigned int mask); void xfs_fs_mark_healthy(struct xfs_mount *mp, unsigned int mask); void xfs_fs_measure_sickness(struct xfs_mount *mp, unsigned int *sick, unsigned int *checked); void xfs_rt_mark_sick(struct xfs_mount *mp, unsigned int mask); +void xfs_rt_mark_corrupt(struct xfs_mount *mp, unsigned int mask); void xfs_rt_mark_healthy(struct xfs_mount *mp, unsigned int mask); void xfs_rt_measure_sickness(struct xfs_mount *mp, unsigned int *sick, unsigned int *checked); void xfs_ag_mark_sick(struct xfs_perag *pag, unsigned int mask); +void xfs_ag_mark_corrupt(struct xfs_perag *pag, unsigned int mask); void xfs_ag_mark_healthy(struct xfs_perag *pag, unsigned int mask); void xfs_ag_measure_sickness(struct xfs_perag *pag, unsigned int *sick, unsigned int *checked); void xfs_inode_mark_sick(struct xfs_inode *ip, unsigned int mask); +void xfs_inode_mark_corrupt(struct xfs_inode *ip, unsigned int mask); void xfs_inode_mark_healthy(struct xfs_inode *ip, unsigned int mask); void xfs_inode_measure_sickness(struct xfs_inode *ip, unsigned int *sick, unsigned int *checked); diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c index 34519fbc2d40b..c682c70933534 100644 --- a/fs/xfs/scrub/health.c +++ b/fs/xfs/scrub/health.c @@ -175,7 +175,7 @@ xchk_update_health( case XHG_AG: pag = xfs_perag_get(sc->mp, sc->sm->sm_agno); if (bad) - xfs_ag_mark_sick(pag, sc->sick_mask); + xfs_ag_mark_corrupt(pag, sc->sick_mask); else xfs_ag_mark_healthy(pag, sc->sick_mask); xfs_perag_put(pag); @@ -184,19 +184,19 @@ xchk_update_health( if (!sc->ip) return; if (bad) - xfs_inode_mark_sick(sc->ip, sc->sick_mask); + xfs_inode_mark_corrupt(sc->ip, sc->sick_mask); else xfs_inode_mark_healthy(sc->ip, sc->sick_mask); break; case XHG_FS: if (bad) - xfs_fs_mark_sick(sc->mp, sc->sick_mask); + xfs_fs_mark_corrupt(sc->mp, sc->sick_mask); else xfs_fs_mark_healthy(sc->mp, sc->sick_mask); break; case XHG_RT: if (bad) - xfs_rt_mark_sick(sc->mp, sc->sick_mask); + xfs_rt_mark_corrupt(sc->mp, sc->sick_mask); else xfs_rt_mark_healthy(sc->mp, sc->sick_mask); break; diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c index 111c27a6b1079..e727a46a95a45 100644 --- a/fs/xfs/xfs_health.c +++ b/fs/xfs/xfs_health.c @@ -96,6 +96,20 @@ xfs_fs_mark_sick( ASSERT(!(mask & ~XFS_SICK_FS_PRIMARY)); trace_xfs_fs_mark_sick(mp, mask); + spin_lock(&mp->m_sb_lock); + mp->m_fs_sick |= mask; + spin_unlock(&mp->m_sb_lock); +} + +/* Mark per-fs metadata as having been checked and found unhealthy by fsck. */ +void +xfs_fs_mark_corrupt( + struct xfs_mount *mp, + unsigned int mask) +{ + ASSERT(!(mask & ~XFS_SICK_FS_PRIMARY)); + trace_xfs_fs_mark_corrupt(mp, mask); + spin_lock(&mp->m_sb_lock); mp->m_fs_sick |= mask; mp->m_fs_checked |= mask; @@ -139,6 +153,20 @@ xfs_rt_mark_sick( ASSERT(!(mask & ~XFS_SICK_RT_PRIMARY)); trace_xfs_rt_mark_sick(mp, mask); + spin_lock(&mp->m_sb_lock); + mp->m_rt_sick |= mask; + spin_unlock(&mp->m_sb_lock); +} + +/* Mark realtime metadata as having been checked and found unhealthy by fsck. */ +void +xfs_rt_mark_corrupt( + struct xfs_mount *mp, + unsigned int mask) +{ + ASSERT(!(mask & ~XFS_SICK_RT_PRIMARY)); + trace_xfs_rt_mark_corrupt(mp, mask); + spin_lock(&mp->m_sb_lock); mp->m_rt_sick |= mask; mp->m_rt_checked |= mask; @@ -182,6 +210,20 @@ xfs_ag_mark_sick( ASSERT(!(mask & ~XFS_SICK_AG_PRIMARY)); trace_xfs_ag_mark_sick(pag->pag_mount, pag->pag_agno, mask); + spin_lock(&pag->pag_state_lock); + pag->pag_sick |= mask; + spin_unlock(&pag->pag_state_lock); +} + +/* Mark per-ag metadata as having been checked and found unhealthy by fsck. */ +void +xfs_ag_mark_corrupt( + struct xfs_perag *pag, + unsigned int mask) +{ + ASSERT(!(mask & ~XFS_SICK_AG_PRIMARY)); + trace_xfs_ag_mark_corrupt(pag->pag_mount, pag->pag_agno, mask); + spin_lock(&pag->pag_state_lock); pag->pag_sick |= mask; pag->pag_checked |= mask; @@ -225,6 +267,29 @@ xfs_inode_mark_sick( ASSERT(!(mask & ~(XFS_SICK_INO_PRIMARY | XFS_SICK_INO_ZAPPED))); trace_xfs_inode_mark_sick(ip, mask); + spin_lock(&ip->i_flags_lock); + ip->i_sick |= mask; + spin_unlock(&ip->i_flags_lock); + + /* + * Keep this inode around so we don't lose the sickness report. Scrub + * grabs inodes with DONTCACHE assuming that most inode are ok, which + * is not the case here. + */ + spin_lock(&VFS_I(ip)->i_lock); + VFS_I(ip)->i_state &= ~I_DONTCACHE; + spin_unlock(&VFS_I(ip)->i_lock); +} + +/* Mark inode metadata as having been checked and found unhealthy by fsck. */ +void +xfs_inode_mark_corrupt( + struct xfs_inode *ip, + unsigned int mask) +{ + ASSERT(!(mask & ~(XFS_SICK_INO_PRIMARY | XFS_SICK_INO_ZAPPED))); + trace_xfs_inode_mark_corrupt(ip, mask); + spin_lock(&ip->i_flags_lock); ip->i_sick |= mask; ip->i_checked |= mask; diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index c7e57efe03566..667ecae469ccb 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -3926,9 +3926,11 @@ DEFINE_EVENT(xfs_fs_corrupt_class, name, \ TP_PROTO(struct xfs_mount *mp, unsigned int flags), \ TP_ARGS(mp, flags)) DEFINE_FS_CORRUPT_EVENT(xfs_fs_mark_sick); +DEFINE_FS_CORRUPT_EVENT(xfs_fs_mark_corrupt); DEFINE_FS_CORRUPT_EVENT(xfs_fs_mark_healthy); DEFINE_FS_CORRUPT_EVENT(xfs_fs_unfixed_corruption); DEFINE_FS_CORRUPT_EVENT(xfs_rt_mark_sick); +DEFINE_FS_CORRUPT_EVENT(xfs_rt_mark_corrupt); DEFINE_FS_CORRUPT_EVENT(xfs_rt_mark_healthy); DEFINE_FS_CORRUPT_EVENT(xfs_rt_unfixed_corruption); @@ -3955,6 +3957,7 @@ DEFINE_EVENT(xfs_ag_corrupt_class, name, \ unsigned int flags), \ TP_ARGS(mp, agno, flags)) DEFINE_AG_CORRUPT_EVENT(xfs_ag_mark_sick); +DEFINE_AG_CORRUPT_EVENT(xfs_ag_mark_corrupt); DEFINE_AG_CORRUPT_EVENT(xfs_ag_mark_healthy); DEFINE_AG_CORRUPT_EVENT(xfs_ag_unfixed_corruption); @@ -3980,6 +3983,7 @@ DEFINE_EVENT(xfs_inode_corrupt_class, name, \ TP_PROTO(struct xfs_inode *ip, unsigned int flags), \ TP_ARGS(ip, flags)) DEFINE_INODE_CORRUPT_EVENT(xfs_inode_mark_sick); +DEFINE_INODE_CORRUPT_EVENT(xfs_inode_mark_corrupt); DEFINE_INODE_CORRUPT_EVENT(xfs_inode_mark_healthy); TRACE_EVENT(xfs_iwalk_ag, -- 2.30.2