Source kernel commit:
de6077ec4198b9313c6e09e4c6acbe9179d057c1
Whenever we encounter a corrupt AG header, we should report that to the
health monitoring system for later reporting. Buffer readers that don't
respond to corruption events with a _mark_sick call can be detected with
the following script:
#!/bin/bash
# Detect missing calls to xfs_*_mark_sick
filter=cat
tty -s && filter=less
git grep -A10 -E '( = xfs_trans_read_buf| = xfs_buf_read\()' fs/xfs/*.[ch] fs/xfs/libxfs/*.[ch] | awk '
BEGIN {
ignore = 0;
lineno = 0;
delete lines;
}
{
if ($0 == "--") {
if (!ignore) {
for (i = 0; i < lineno; i++) {
print(lines[i]);
}
printf("--\n");
}
delete lines;
lineno = 0;
ignore = 0;
} else if ($0 ~ /mark_sick/) {
ignore = 1;
} else {
lines[lineno++] = $0;
}
}
' | $filter
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
void xfs_ag_geom_health(struct xfs_perag *pag, struct xfs_ag_geometry *ageo) { }
void xfs_fs_mark_sick(struct xfs_mount *mp, unsigned int mask) { }
+void xfs_agno_mark_sick(struct xfs_mount *mp, xfs_agnumber_t agno,
+ unsigned int mask) { }
+void xfs_ag_mark_sick(struct xfs_perag *pag, unsigned int mask) { }
#include "xfs_ag.h"
#include "xfs_ag_resv.h"
#include "xfs_bmap.h"
+#include "xfs_health.h"
struct kmem_cache *xfs_extfree_item_cache;
mp, tp, mp->m_ddev_targp,
XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGFL_DADDR(mp)),
XFS_FSS_TO_BB(mp, 1), 0, &bp, &xfs_agfl_buf_ops);
+ if (xfs_metadata_is_sick(error))
+ xfs_ag_mark_sick(pag, XFS_SICK_AG_AGFL);
if (error)
return error;
xfs_buf_set_ref(bp, XFS_AGFL_REF);
if (unlikely(be32_to_cpu(agf->agf_freeblks) >
be32_to_cpu(agf->agf_length))) {
xfs_buf_mark_corrupt(agbp);
+ xfs_ag_mark_sick(agbp->b_pag, XFS_SICK_AG_AGF);
return -EFSCORRUPTED;
}
error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGF_DADDR(mp)),
XFS_FSS_TO_BB(mp, 1), flags, agfbpp, &xfs_agf_buf_ops);
+ if (xfs_metadata_is_sick(error))
+ xfs_ag_mark_sick(pag, XFS_SICK_AG_AGF);
if (error)
return error;
* and the "sick" field tells us if that piece was found to need repairs.
* Therefore we can conclude that for a given sick flag value:
*
- * - checked && sick => metadata needs repair
- * - checked && !sick => metadata is ok
- * - !checked => has not been examined since mount
+ * - checked && sick => metadata needs repair
+ * - checked && !sick => metadata is ok
+ * - !checked && sick => errors have been observed during normal operation,
+ * but the metadata has not been checked thoroughly
+ * - !checked && !sick => has not been examined since mount
*/
struct xfs_mount;
void xfs_rt_measure_sickness(struct xfs_mount *mp, unsigned int *sick,
unsigned int *checked);
+void xfs_agno_mark_sick(struct xfs_mount *mp, xfs_agnumber_t agno,
+ unsigned int mask);
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_geom_health(struct xfs_perag *pag, struct xfs_ag_geometry *ageo);
void xfs_bulkstat_health(struct xfs_inode *ip, struct xfs_bulkstat *bs);
+#define xfs_metadata_is_sick(error) \
+ (unlikely((error) == -EFSCORRUPTED || (error) == -EFSBADCRC))
+
#endif /* __XFS_HEALTH_H__ */
#include "xfs_trace.h"
#include "xfs_rmap.h"
#include "xfs_ag.h"
+#include "xfs_health.h"
/*
* Lookup a record by ino in the btree given by cur.
error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGI_DADDR(mp)),
XFS_FSS_TO_BB(mp, 1), 0, agibpp, &xfs_agi_buf_ops);
+ if (xfs_metadata_is_sick(error))
+ xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
if (error)
return error;
if (tp)
error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
XFS_AG_DADDR(mp, agno, XFS_SB_BLOCK(mp)),
XFS_FSS_TO_BB(mp, 1), 0, &bp, &xfs_sb_buf_ops);
+ if (xfs_metadata_is_sick(error))
+ xfs_agno_mark_sick(mp, agno, XFS_SICK_AG_SB);
if (error)
return error;
xfs_buf_set_ref(bp, XFS_SSB_REF);