From: "Darrick J. Wong" <darrick.wong@oracle.com>
To: darrick.wong@oracle.com
Cc: linux-xfs@vger.kernel.org
Subject: [PATCH 02/10] xfs: report ag header corruption errors to the health tracking system
Date: Sun, 03 Nov 2019 14:24:57 -0800 [thread overview]
Message-ID: <157281989728.4152102.8612960889220308936.stgit@magnolia> (raw)
In-Reply-To: <157281988489.4152102.1632857939932700344.stgit@magnolia>
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 | 14 +++++++++++---
fs/xfs/libxfs/xfs_ialloc.c | 3 +++
fs/xfs/libxfs/xfs_refcount.c | 1 +
fs/xfs/libxfs/xfs_rmap.c | 1 +
fs/xfs/libxfs/xfs_sb.c | 2 ++
fs/xfs/xfs_health.c | 17 +++++++++++++++++
fs/xfs/xfs_inode.c | 9 +++++++++
8 files changed, 50 insertions(+), 3 deletions(-)
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 8231be43f48d..72cfe243d58d 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;
@@ -694,6 +695,8 @@ 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);
@@ -717,6 +720,7 @@ 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;
}
@@ -2930,6 +2934,8 @@ 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..ce8954a10c66 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 +205,8 @@ 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) == -EIO || \
+ (error) == -EFSBADCRC))
+
#endif /* __XFS_HEALTH_H__ */
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 9232d9a03ebb..57da33556e9f 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.
@@ -2635,6 +2636,8 @@ 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_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 0d998e3b6acf..26ab2c629c1f 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -1178,6 +1178,7 @@ xfs_refcount_finish_one(
if (error)
return error;
if (XFS_CORRUPT_ON(tp->t_mountp, !agbp)) {
+ xfs_agno_mark_sick(tp->t_mountp, agno, XFS_SICK_AG_AGF);
return -EFSCORRUPTED;
}
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index 74efdbc56a60..03ce3d6f4c87 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -2395,6 +2395,7 @@ xfs_rmap_finish_one(
if (error)
return error;
if (XFS_CORRUPT_ON(tp->t_mountp, !agbp)) {
+ xfs_agno_mark_sick(tp->t_mountp, agno, XFS_SICK_AG_AGF);
return -EFSCORRUPTED;
}
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index ac6cdca63e15..6a8d821a1dbc 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -1168,6 +1168,8 @@ 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 a92d4521748d..d02246e2fb21 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;
@@ -787,6 +788,8 @@ 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;
}
@@ -2138,6 +2141,7 @@ 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;
}
@@ -2204,6 +2208,7 @@ 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;
}
@@ -2218,6 +2223,7 @@ 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;
@@ -2272,6 +2278,7 @@ 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;
}
@@ -2409,6 +2416,7 @@ 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;
}
@@ -2455,6 +2463,7 @@ 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;
}
next prev parent reply other threads:[~2019-11-03 22:25 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-11-03 22:24 [PATCH 00/10] xfs: report corruption to the health trackers Darrick J. Wong
2019-11-03 22:24 ` [PATCH 01/10] xfs: separate the marking of sick and checked metadata Darrick J. Wong
2019-11-03 22:24 ` Darrick J. Wong [this message]
2019-11-03 22:25 ` [PATCH 03/10] xfs: report block map corruption errors to the health tracking system Darrick J. Wong
2019-11-03 22:25 ` [PATCH 04/10] xfs: report btree block corruption errors to the health system Darrick J. Wong
2019-11-03 22:25 ` [PATCH 05/10] xfs: report dir/attr " Darrick J. Wong
2019-11-03 22:25 ` [PATCH 06/10] xfs: report symlink " Darrick J. Wong
2019-11-03 22:25 ` [PATCH 07/10] xfs: report inode " Darrick J. Wong
2019-11-03 22:25 ` [PATCH 08/10] xfs: report quota block " Darrick J. Wong
2019-11-03 22:25 ` [PATCH 09/10] xfs: report realtime metadata " Darrick J. Wong
2019-11-03 22:25 ` [PATCH 10/10] xfs: report XFS_CORRUPT_ON " Darrick J. Wong
2019-11-07 3:03 [PATCH 00/10] xfs: report corruption to the health trackers Darrick J. Wong
2019-11-07 3:03 ` [PATCH 02/10] xfs: report ag header corruption errors to the health tracking system Darrick J. Wong
2019-11-08 7:05 [PATCH v3 00/10] xfs: report corruption to the health trackers Darrick J. Wong
2019-11-08 7:05 ` [PATCH 02/10] xfs: report ag header corruption errors to the health tracking system Darrick J. Wong
2020-01-01 1:04 [PATCH 00/10] xfs: report corruption to the health trackers Darrick J. Wong
2020-01-01 1:04 ` [PATCH 02/10] xfs: report ag header corruption errors to the health tracking system Darrick J. Wong
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=157281989728.4152102.8612960889220308936.stgit@magnolia \
--to=darrick.wong@oracle.com \
--cc=linux-xfs@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).