[PATCH 03/10] xfs: clear BAD_SUMMARY if unmounting an unhealthy filesystem

["Darrick J. Wong" <darrick.wong@oracle.com>]

From: Darrick J. Wong <darrick.wong@oracle.com>

If we know the filesystem metadata isn't healthy during unmount, we want
to encourage the administrator to run xfs_repair right away.  We can't
do this if BAD_SUMMARY will cause an unclean log unmount to force
summary recalculation, so turn it off if the fs is bad.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_health.h |    2 +
 fs/xfs/xfs_health.c        |   59 ++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_mount.c         |    2 +
 fs/xfs/xfs_trace.h         |    3 ++
 4 files changed, 66 insertions(+)


diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h
index 0d51bd2689ea..269b124dc1d7 100644
--- a/fs/xfs/libxfs/xfs_health.h
+++ b/fs/xfs/libxfs/xfs_health.h
@@ -148,6 +148,8 @@ void xfs_inode_mark_sick(struct xfs_inode *ip, unsigned int mask);
 void xfs_inode_mark_healthy(struct xfs_inode *ip, unsigned int mask);
 unsigned int xfs_inode_measure_sickness(struct xfs_inode *ip);
 
+void xfs_health_unmount(struct xfs_mount *mp);
+
 /* Now some helpers. */
 
 static inline bool
diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index e9d6859f7501..6e2da858c356 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -19,6 +19,65 @@
 #include "xfs_trace.h"
 #include "xfs_health.h"
 
+/*
+ * Warn about metadata corruption that we detected but haven't fixed, and
+ * make sure we're not sitting on anything that would get in the way of
+ * recovery.
+ */
+void
+xfs_health_unmount(
+	struct xfs_mount	*mp)
+{
+	struct xfs_perag	*pag;
+	xfs_agnumber_t		agno;
+	unsigned int		sick;
+	bool			warn = false;
+
+	if (XFS_FORCED_SHUTDOWN(mp))
+		return;
+
+	/* Measure AG corruption levels. */
+	for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) {
+		pag = xfs_perag_get(mp, agno);
+		spin_lock(&pag->pag_state_lock);
+		if (pag->pag_sick) {
+			trace_xfs_ag_unfixed_corruption(mp, agno, sick);
+			warn = true;
+		}
+		spin_unlock(&pag->pag_state_lock);
+		xfs_perag_put(pag);
+	}
+
+	/* Measure realtime volume corruption levels. */
+	sick = xfs_rt_measure_sickness(mp);
+	if (sick) {
+		trace_xfs_rt_unfixed_corruption(mp, sick);
+		warn = true;
+	}
+
+	/* Measure fs corruption and keep the sample around for the warning. */
+	sick = xfs_fs_measure_sickness(mp);
+	if (sick) {
+		trace_xfs_fs_unfixed_corruption(mp, sick);
+		warn = true;
+	}
+
+	if (warn) {
+		xfs_warn(mp,
+"Uncorrected metadata errors detected; please run xfs_repair.");
+
+		/*
+		 * If we have unhealthy metadata, we want the admin to run
+		 * xfs_repair after unmounting.  They can't do that if the log
+		 * is written out without a clean unmount record (such as when
+		 * the summary counters are marked unhealthy to force
+		 * recalculation of the summary counters) so clear it.
+		 */
+		if (sick & XFS_HEALTH_FS_COUNTERS)
+			xfs_fs_mark_healthy(mp, XFS_HEALTH_FS_COUNTERS);
+	}
+}
+
 /* Mark unhealthy per-fs metadata. */
 void
 xfs_fs_mark_sick(
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index a43ca655a431..f0f73d598a0c 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -1075,6 +1075,7 @@ xfs_mountfs(
 	 */
 	cancel_delayed_work_sync(&mp->m_reclaim_work);
 	xfs_reclaim_inodes(mp, SYNC_WAIT);
+	xfs_health_unmount(mp);
  out_log_dealloc:
 	mp->m_flags |= XFS_MOUNT_UNMOUNTING;
 	xfs_log_mount_cancel(mp);
@@ -1157,6 +1158,7 @@ xfs_unmountfs(
 	 */
 	cancel_delayed_work_sync(&mp->m_reclaim_work);
 	xfs_reclaim_inodes(mp, SYNC_WAIT);
+	xfs_health_unmount(mp);
 
 	xfs_qm_unmount(mp);
 
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index f079841c7af6..2464ea351f83 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -3461,8 +3461,10 @@ DEFINE_EVENT(xfs_fs_corrupt_class, name,	\
 	TP_ARGS(mp, flags))
 DEFINE_FS_CORRUPT_EVENT(xfs_fs_mark_sick);
 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_healthy);
+DEFINE_FS_CORRUPT_EVENT(xfs_rt_unfixed_corruption);
 
 DECLARE_EVENT_CLASS(xfs_ag_corrupt_class,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, unsigned int flags),
@@ -3488,6 +3490,7 @@ DEFINE_EVENT(xfs_ag_corrupt_class, name,	\
 	TP_ARGS(mp, agno, flags))
 DEFINE_AG_CORRUPT_EVENT(xfs_ag_mark_sick);
 DEFINE_AG_CORRUPT_EVENT(xfs_ag_mark_healthy);
+DEFINE_AG_CORRUPT_EVENT(xfs_ag_unfixed_corruption);
 
 DECLARE_EVENT_CLASS(xfs_inode_corrupt_class,
 	TP_PROTO(struct xfs_inode *ip, unsigned int flags),