xfs: report ag header corruption errors to the health tracking system

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>

1 files changed, 10 insertions, 3 deletions

diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h
index bec7adf9fcf7..fb3f2b49087d 100644
--- a/fs/xfs/libxfs/xfs_health.h
+++ b/fs/xfs/libxfs/xfs_health.h
@@ -26,9 +26,11 @@
  * 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;
@@ -142,6 +144,8 @@ 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_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);
@@ -222,4 +226,7 @@ void xfs_fsop_geom_health(struct xfs_mount *mp, struct xfs_fsop_geom *geo);
 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__ */