[02/10] xfs: report ag header corruption errors to the health tracking system
diff mbox series

Message ID 157784069209.1360095.11446811087494881964.stgit@magnolia
State New
Headers show
Series
  • xfs: report corruption to the health trackers
Related show

Commit Message

Darrick J. Wong Jan. 1, 2020, 1:04 a.m. UTC
From: Darrick J. Wong <darrick.wong@oracle.com>

Whenever we encounter a corrupt AG header, we should report that to the
health monitoring system for later reporting.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_alloc.c  |    6 ++++++
 fs/xfs/libxfs/xfs_health.h |   13 ++++++++++---
 fs/xfs/libxfs/xfs_ialloc.c |    3 +++
 fs/xfs/libxfs/xfs_sb.c     |    2 ++
 fs/xfs/xfs_health.c        |   17 +++++++++++++++++
 fs/xfs/xfs_inode.c         |    9 +++++++++
 6 files changed, 47 insertions(+), 3 deletions(-)

Patch
diff mbox series

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index fc93fd88ec89..63d3fc97719c 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -26,6 +26,7 @@ 
 #include "xfs_log.h"
 #include "xfs_ag_resv.h"
 #include "xfs_bmap.h"
+#include "xfs_health.h"
 
 extern kmem_zone_t	*xfs_bmap_free_item_zone;
 
@@ -699,6 +700,8 @@  xfs_alloc_read_agfl(
 			mp, tp, mp->m_ddev_targp,
 			XFS_AG_DADDR(mp, agno, XFS_AGFL_DADDR(mp)),
 			XFS_FSS_TO_BB(mp, 1), 0, &bp, &xfs_agfl_buf_ops);
+	if (xfs_metadata_is_sick(error))
+		xfs_agno_mark_sick(mp, agno, XFS_SICK_AG_AGFL);
 	if (error)
 		return error;
 	xfs_buf_set_ref(bp, XFS_AGFL_REF);
@@ -722,6 +725,7 @@  xfs_alloc_update_counters(
 	if (unlikely(be32_to_cpu(agf->agf_freeblks) >
 		     be32_to_cpu(agf->agf_length))) {
 		xfs_buf_corruption_error(agbp);
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_AGF);
 		return -EFSCORRUPTED;
 	}
 
@@ -2960,6 +2964,8 @@  xfs_read_agf(
 			mp, tp, mp->m_ddev_targp,
 			XFS_AG_DADDR(mp, agno, XFS_AGF_DADDR(mp)),
 			XFS_FSS_TO_BB(mp, 1), flags, bpp, &xfs_agf_buf_ops);
+	if (xfs_metadata_is_sick(error))
+		xfs_agno_mark_sick(mp, agno, XFS_SICK_AG_AGF);
 	if (error)
 		return error;
 	if (!*bpp)
diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h
index 96919a257870..c34c393d5aa7 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;
@@ -121,6 +123,8 @@  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_checked(struct xfs_perag *pag, unsigned int mask);
 void xfs_ag_mark_healthy(struct xfs_perag *pag, unsigned int mask);
@@ -201,4 +205,7 @@  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__ */
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 67ad8ff95178..ce52fd9332e5 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -27,6 +27,7 @@ 
 #include "xfs_trace.h"
 #include "xfs_log.h"
 #include "xfs_rmap.h"
+#include "xfs_health.h"
 
 /*
  * Lookup a record by ino in the btree given by cur.
@@ -2643,6 +2644,8 @@  xfs_read_agi(
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
 			XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp)),
 			XFS_FSS_TO_BB(mp, 1), 0, bpp, &xfs_agi_buf_ops);
+	if (xfs_metadata_is_sick(error))
+		xfs_agno_mark_sick(mp, agno, XFS_SICK_AG_AGI);
 	if (error)
 		return error;
 	if (tp)
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 0ac69751fe85..4a923545465d 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -1169,6 +1169,8 @@  xfs_sb_read_secondary(
 	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);
diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index 860dc70c99e7..36c32b108b39 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -200,6 +200,23 @@  xfs_rt_measure_sickness(
 	spin_unlock(&mp->m_sb_lock);
 }
 
+/* Mark unhealthy per-ag metadata given a raw AG number. */
+void
+xfs_agno_mark_sick(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		agno,
+	unsigned int		mask)
+{
+	struct xfs_perag	*pag = xfs_perag_get(mp, agno);
+
+	/* per-ag structure not set up yet? */
+	if (!pag)
+		return;
+
+	xfs_ag_mark_sick(pag, mask);
+	xfs_perag_put(pag);
+}
+
 /* Mark unhealthy per-ag metadata. */
 void
 xfs_ag_mark_sick(
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 8a424fac2d27..906b0e2f68e2 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -35,6 +35,7 @@ 
 #include "xfs_log.h"
 #include "xfs_bmap_btree.h"
 #include "xfs_reflink.h"
+#include "xfs_health.h"
 
 kmem_zone_t *xfs_inode_zone;
 
@@ -781,6 +782,8 @@  xfs_ialloc(
 	 */
 	if ((pip && ino == pip->i_ino) || !xfs_verify_dir_ino(mp, ino)) {
 		xfs_alert(mp, "Allocated a known in-use inode 0x%llx!", ino);
+		xfs_agno_mark_sick(mp, XFS_INO_TO_AGNO(mp, ino),
+				XFS_SICK_AG_INOBT);
 		return -EFSCORRUPTED;
 	}
 
@@ -2111,6 +2114,7 @@  xfs_iunlink_update_bucket(
 	 */
 	if (old_value == new_agino) {
 		xfs_buf_corruption_error(agibp);
+		xfs_agno_mark_sick(tp->t_mountp, agno, XFS_SICK_AG_AGI);
 		return -EFSCORRUPTED;
 	}
 
@@ -2177,6 +2181,7 @@  xfs_iunlink_update_inode(
 	if (!xfs_verify_agino_or_null(mp, agno, old_value)) {
 		xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, dip,
 				sizeof(*dip), __this_address);
+		xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
 		error = -EFSCORRUPTED;
 		goto out;
 	}
@@ -2191,6 +2196,7 @@  xfs_iunlink_update_inode(
 		if (next_agino != NULLAGINO) {
 			xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__,
 					dip, sizeof(*dip), __this_address);
+			xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
 			error = -EFSCORRUPTED;
 		}
 		goto out;
@@ -2245,6 +2251,7 @@  xfs_iunlink(
 	if (next_agino == agino ||
 	    !xfs_verify_agino_or_null(mp, agno, next_agino)) {
 		xfs_buf_corruption_error(agibp);
+		xfs_agno_mark_sick(mp, agno, XFS_SICK_AG_AGI);
 		return -EFSCORRUPTED;
 	}
 
@@ -2382,6 +2389,7 @@  xfs_iunlink_map_prev(
 			XFS_CORRUPTION_ERROR(__func__,
 					XFS_ERRLEVEL_LOW, mp,
 					*dipp, sizeof(**dipp));
+			xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
 			error = -EFSCORRUPTED;
 			return error;
 		}
@@ -2428,6 +2436,7 @@  xfs_iunlink_remove(
 	if (!xfs_verify_agino(mp, agno, head_agino)) {
 		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
 				agi, sizeof(*agi));
+		xfs_agno_mark_sick(mp, agno, XFS_SICK_AG_AGI);
 		return -EFSCORRUPTED;
 	}